1499 files changed, 62993 insertions, 32284 deletions

diff --git a/Documentation/ABI/testing/sysfs-driver-hid-logitech-lg4ff b/Documentation/ABI/testing/sysfs-driver-hid-logitech-lg4ff
index b3f6a2ac5007..db197a879580 100644
--- a/Documentation/ABI/testing/sysfs-driver-hid-logitech-lg4ff
+++ b/Documentation/ABI/testing/sysfs-driver-hid-logitech-lg4ff
@@ -1,7 +1,7 @@
-What:		/sys/module/hid_logitech/drivers/hid:logitech/<dev>/range.
+What:		/sys/bus/hid/drivers/logitech/<dev>/range
 Date:		July 2011
 KernelVersion:	3.2
-Contact:	Michal Malý <madcatxster@gmail.com>
+Contact:	Michal Malý <madcatxster@devoid-pointer.net>
 Description:	Display minimum, maximum and current range of the steering
 		wheel. Writing a value within min and max boundaries sets the
 		range of the wheel.
@@ -9,7 +9,7 @@ Description:	Display minimum, maximum and current range of the steering
 What:		/sys/bus/hid/drivers/logitech/<dev>/alternate_modes
 Date:		Feb 2015
 KernelVersion:	4.1
-Contact:	Michal Malý <madcatxster@gmail.com>
+Contact:	Michal Malý <madcatxster@devoid-pointer.net>
 Description:	Displays a set of alternate modes supported by a wheel. Each
 		mode is listed as follows:
 		  Tag: Mode Name
@@ -45,7 +45,7 @@ Description:	Displays a set of alternate modes supported by a wheel. Each
 What:		/sys/bus/hid/drivers/logitech/<dev>/real_id
 Date:		Feb 2015
 KernelVersion:	4.1
-Contact:	Michal Malý <madcatxster@gmail.com>
+Contact:	Michal Malý <madcatxster@devoid-pointer.net>
 Description:	Displays the real model of the wheel regardless of any
 		alternate mode the wheel might be switched to.
 		It is a read-only value.
diff --git a/Documentation/ABI/testing/sysfs-firmware-efi b/Documentation/ABI/testing/sysfs-firmware-efi
index 05874da7ce80..e794eac32a90 100644
--- a/Documentation/ABI/testing/sysfs-firmware-efi
+++ b/Documentation/ABI/testing/sysfs-firmware-efi
@@ -18,3 +18,13 @@ Contact:	Dave Young <dyoung@redhat.com>
 Description:	It shows the physical address of config table entry in the EFI
 		system table.
 Users:		Kexec
+
+What:		/sys/firmware/efi/systab
+Date:		April 2005
+Contact:	linux-efi@vger.kernel.org
+Description:	Displays the physical addresses of all EFI Configuration
+		Tables found via the EFI System Table. The order in
+		which the tables are printed forms an ABI and newer
+		versions are always printed first, i.e. ACPI20 comes
+		before ACPI.
+Users:		dmidecode
diff --git a/Documentation/ABI/testing/sysfs-firmware-efi-esrt b/Documentation/ABI/testing/sysfs-firmware-efi-esrt
new file mode 100644
index 000000000000..6e431d1a4e79
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-firmware-efi-esrt
@@ -0,0 +1,81 @@
+What:		/sys/firmware/efi/esrt/
+Date:		February 2015
+Contact:	Peter Jones <pjones@redhat.com>
+Description:	Provides userland access to read the EFI System Resource Table
+		(ESRT), a catalog of firmware for which can be updated with
+		the UEFI UpdateCapsule mechanism described in section 7.5 of
+		the UEFI Standard.
+Users:		fwupdate - https://github.com/rhinstaller/fwupdate
+
+What:		/sys/firmware/efi/esrt/fw_resource_count
+Date:		February 2015
+Contact:	Peter Jones <pjones@redhat.com>
+Description:	The number of entries in the ESRT
+
+What:		/sys/firmware/efi/esrt/fw_resource_count_max
+Date:		February 2015
+Contact:	Peter Jones <pjones@redhat.com>
+Description:	The maximum number of entries that /could/ be registered
+		in the allocation the table is currently in.  This is
+		really only useful to the system firmware itself.
+
+What:		/sys/firmware/efi/esrt/fw_resource_version
+Date:		February 2015
+Contact:	Peter Jones <pjones@redhat.com>
+Description:	The version of the ESRT structure provided by the firmware.
+
+What:		/sys/firmware/efi/esrt/entries/entry$N/
+Date:		February 2015
+Contact:	Peter Jones <pjones@redhat.com>
+Description:	Each ESRT entry is identified by a GUID, and each gets a
+		subdirectory under entries/ .
+		example: /sys/firmware/efi/esrt/entries/entry0/
+
+What:		/sys/firmware/efi/esrt/entries/entry$N/fw_type
+Date:		February 2015
+Contact:	Peter Jones <pjones@redhat.com>
+Description:	What kind of firmware entry this is:
+		0 - Unknown
+		1 - System Firmware
+		2 - Device Firmware
+		3 - UEFI Driver
+
+What:		/sys/firmware/efi/esrt/entries/entry$N/fw_class
+Date:		February 2015
+Contact:	Peter Jones <pjones@redhat.com>
+Description:	This is the entry's guid, and will match the directory name.
+
+What:		/sys/firmware/efi/esrt/entries/entry$N/fw_version
+Date:		February 2015
+Contact:	Peter Jones <pjones@redhat.com>
+Description:	The version of the firmware currently installed.  This is a
+		32-bit unsigned integer.
+
+What:		/sys/firmware/efi/esrt/entries/entry$N/lowest_supported_fw_version
+Date:		February 2015
+Contact:	Peter Jones <pjones@redhat.com>
+Description:	The lowest version of the firmware that can be installed.
+
+What:		/sys/firmware/efi/esrt/entries/entry$N/capsule_flags
+Date:		February 2015
+Contact:	Peter Jones <pjones@redhat.com>
+Description:	Flags that must be passed to UpdateCapsule()
+
+What:		/sys/firmware/efi/esrt/entries/entry$N/last_attempt_version
+Date:		February 2015
+Contact:	Peter Jones <pjones@redhat.com>
+Description:	The last firmware version for which an update was attempted.
+
+What:		/sys/firmware/efi/esrt/entries/entry$N/last_attempt_status
+Date:		February 2015
+Contact:	Peter Jones <pjones@redhat.com>
+Description:	The result of the last firmware update attempt for the
+		firmware resource entry.
+		0 - Success
+		1 - Insufficient resources
+		2 - Incorrect version
+		3 - Invalid format
+		4 - Authentication error
+		5 - AC power event
+		6 - Battery power event
+
diff --git a/Documentation/DMA-API-HOWTO.txt b/Documentation/DMA-API-HOWTO.txt
index 0f7afb2bb442..aef8cc5a677b 100644
--- a/Documentation/DMA-API-HOWTO.txt
+++ b/Documentation/DMA-API-HOWTO.txt
@@ -25,13 +25,18 @@ physical addresses.  These are the addresses in /proc/iomem.  The physical
 address is not directly useful to a driver; it must use ioremap() to map
 the space and produce a virtual address.
 
-I/O devices use a third kind of address: a "bus address" or "DMA address".
-If a device has registers at an MMIO address, or if it performs DMA to read
-or write system memory, the addresses used by the device are bus addresses.
-In some systems, bus addresses are identical to CPU physical addresses, but
-in general they are not.  IOMMUs and host bridges can produce arbitrary
+I/O devices use a third kind of address: a "bus address".  If a device has
+registers at an MMIO address, or if it performs DMA to read or write system
+memory, the addresses used by the device are bus addresses.  In some
+systems, bus addresses are identical to CPU physical addresses, but in
+general they are not.  IOMMUs and host bridges can produce arbitrary
 mappings between physical and bus addresses.
 
+From a device's point of view, DMA uses the bus address space, but it may
+be restricted to a subset of that space.  For example, even if a system
+supports 64-bit addresses for main memory and PCI BARs, it may use an IOMMU
+so devices only need to use 32-bit DMA addresses.
+
 Here's a picture and some examples:
 
                CPU                  CPU                  Bus
@@ -72,11 +77,11 @@ can use virtual address X to access the buffer, but the device itself
 cannot because DMA doesn't go through the CPU virtual memory system.
 
 In some simple systems, the device can do DMA directly to physical address
-Y.  But in many others, there is IOMMU hardware that translates bus
+Y.  But in many others, there is IOMMU hardware that translates DMA
 addresses to physical addresses, e.g., it translates Z to Y.  This is part
 of the reason for the DMA API: the driver can give a virtual address X to
 an interface like dma_map_single(), which sets up any required IOMMU
-mapping and returns the bus address Z.  The driver then tells the device to
+mapping and returns the DMA address Z.  The driver then tells the device to
 do DMA to Z, and the IOMMU maps it to the buffer at address Y in system
 RAM.
 
@@ -98,7 +103,7 @@ First of all, you should make sure
 #include <linux/dma-mapping.h>
 
 is in your driver, which provides the definition of dma_addr_t.  This type
-can hold any valid DMA or bus address for the platform and should be used
+can hold any valid DMA address for the platform and should be used
 everywhere you hold a DMA address returned from the DMA mapping functions.
 
 			 What memory is DMA'able?
@@ -316,7 +321,7 @@ There are two types of DMA mappings:
   Think of "consistent" as "synchronous" or "coherent".
 
   The current default is to return consistent memory in the low 32
-  bits of the bus space.  However, for future compatibility you should
+  bits of the DMA space.  However, for future compatibility you should
   set the consistent mask even if this default is fine for your
   driver.
 
@@ -403,7 +408,7 @@ dma_alloc_coherent() returns two values: the virtual address which you
 can use to access it from the CPU and dma_handle which you pass to the
 card.
 
-The CPU virtual address and the DMA bus address are both
+The CPU virtual address and the DMA address are both
 guaranteed to be aligned to the smallest PAGE_SIZE order which
 is greater than or equal to the requested size.  This invariant
 exists (for example) to guarantee that if you allocate a chunk
@@ -645,8 +650,8 @@ PLEASE NOTE:  The 'nents' argument to the dma_unmap_sg call must be
               dma_map_sg call.
 
 Every dma_map_{single,sg}() call should have its dma_unmap_{single,sg}()
-counterpart, because the bus address space is a shared resource and
-you could render the machine unusable by consuming all bus addresses.
+counterpart, because the DMA address space is a shared resource and
+you could render the machine unusable by consuming all DMA addresses.
 
 If you need to use the same streaming DMA region multiple times and touch
 the data in between the DMA transfers, the buffer needs to be synced
diff --git a/Documentation/DMA-API.txt b/Documentation/DMA-API.txt
index 52088408668a..7eba542eff7c 100644
--- a/Documentation/DMA-API.txt
+++ b/Documentation/DMA-API.txt
@@ -18,10 +18,10 @@ Part I - dma_ API
 To get the dma_ API, you must #include <linux/dma-mapping.h>.  This
 provides dma_addr_t and the interfaces described below.
 
-A dma_addr_t can hold any valid DMA or bus address for the platform.  It
-can be given to a device to use as a DMA source or target.  A CPU cannot
-reference a dma_addr_t directly because there may be translation between
-its physical address space and the bus address space.
+A dma_addr_t can hold any valid DMA address for the platform.  It can be
+given to a device to use as a DMA source or target.  A CPU cannot reference
+a dma_addr_t directly because there may be translation between its physical
+address space and the DMA address space.
 
 Part Ia - Using large DMA-coherent buffers
 ------------------------------------------
@@ -42,7 +42,7 @@ It returns a pointer to the allocated region (in the processor's virtual
 address space) or NULL if the allocation failed.
 
 It also returns a <dma_handle> which may be cast to an unsigned integer the
-same width as the bus and given to the device as the bus address base of
+same width as the bus and given to the device as the DMA address base of
 the region.
 
 Note: consistent memory can be expensive on some platforms, and the
@@ -193,7 +193,7 @@ dma_map_single(struct device *dev, void *cpu_addr, size_t size,
 		      enum dma_data_direction direction)
 
 Maps a piece of processor virtual memory so it can be accessed by the
-device and returns the bus address of the memory.
+device and returns the DMA address of the memory.
 
 The direction for both APIs may be converted freely by casting.
 However the dma_ API uses a strongly typed enumerator for its
@@ -212,20 +212,20 @@ contiguous piece of memory.  For this reason, memory to be mapped by
 this API should be obtained from sources which guarantee it to be
 physically contiguous (like kmalloc).
 
-Further, the bus address of the memory must be within the
+Further, the DMA address of the memory must be within the
 dma_mask of the device (the dma_mask is a bit mask of the
-addressable region for the device, i.e., if the bus address of
-the memory ANDed with the dma_mask is still equal to the bus
+addressable region for the device, i.e., if the DMA address of
+the memory ANDed with the dma_mask is still equal to the DMA
 address, then the device can perform DMA to the memory).  To
 ensure that the memory allocated by kmalloc is within the dma_mask,
 the driver may specify various platform-dependent flags to restrict
-the bus address range of the allocation (e.g., on x86, GFP_DMA
-guarantees to be within the first 16MB of available bus addresses,
+the DMA address range of the allocation (e.g., on x86, GFP_DMA
+guarantees to be within the first 16MB of available DMA addresses,
 as required by ISA devices).
 
 Note also that the above constraints on physical contiguity and
 dma_mask may not apply if the platform has an IOMMU (a device which
-maps an I/O bus address to a physical memory address).  However, to be
+maps an I/O DMA address to a physical memory address).  However, to be
 portable, device driver writers may *not* assume that such an IOMMU
 exists.
 
@@ -296,7 +296,7 @@ reduce current DMA mapping usage or delay and try again later).
 	dma_map_sg(struct device *dev, struct scatterlist *sg,
 		int nents, enum dma_data_direction direction)
 
-Returns: the number of bus address segments mapped (this may be shorter
+Returns: the number of DMA address segments mapped (this may be shorter
 than <nents> passed in if some elements of the scatter/gather list are
 physically or virtually adjacent and an IOMMU maps them with a single
 entry).
@@ -340,7 +340,7 @@ must be the same as those and passed in to the scatter/gather mapping
 API.
 
 Note: <nents> must be the number you passed in, *not* the number of
-bus address entries returned.
+DMA address entries returned.
 
 void
 dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, size_t size,
@@ -507,7 +507,7 @@ it's asked for coherent memory for this device.
 phys_addr is the CPU physical address to which the memory is currently
 assigned (this will be ioremapped so the CPU can access the region).
 
-device_addr is the bus address the device needs to be programmed
+device_addr is the DMA address the device needs to be programmed
 with to actually address this memory (this will be handed out as the
 dma_addr_t in dma_alloc_coherent()).
 
diff --git a/Documentation/DocBook/crypto-API.tmpl b/Documentation/DocBook/crypto-API.tmpl
index efc8d90a9a3f..0992531ffefb 100644
--- a/Documentation/DocBook/crypto-API.tmpl
+++ b/Documentation/DocBook/crypto-API.tmpl
@@ -119,7 +119,7 @@
 
     <para>
      Note: The terms "transformation" and cipher algorithm are used
-     interchangably.
+     interchangeably.
     </para>
    </sect1>
 
@@ -536,8 +536,8 @@
 
      <para>
       For other use cases of AEAD ciphers, the ASCII art applies as
-      well, but the caller may not use the GIVCIPHER interface. In
-      this case, the caller must generate the IV.
+      well, but the caller may not use the AEAD cipher with a separate
+      IV generator. In this case, the caller must generate the IV.
      </para>
 
      <para>
@@ -584,8 +584,8 @@ kernel crypto API                                |   IPSEC Layer
                                                  |
 +-----------+                                    |
 |           |            (1)
-| givcipher | <-----------------------------------  esp_output
-|  (seqiv)  | ---+
+|   aead    | <-----------------------------------  esp_output
+| (seqniv)  | ---+
 +-----------+    |
                  | (2)
 +-----------+    |
@@ -620,8 +620,8 @@ kernel crypto API                                |   IPSEC Layer
      <orderedlist>
       <listitem>
        <para>
-        esp_output() invokes crypto_aead_givencrypt() to trigger an encryption
-        operation of the GIVCIPHER implementation.
+        esp_output() invokes crypto_aead_encrypt() to trigger an encryption
+        operation of the AEAD cipher with IV generator.
        </para>
 
        <para>
@@ -1563,7 +1563,7 @@ struct sockaddr_alg sa = {
 
    <sect1><title>Zero-Copy Interface</title>
     <para>
-     In addition to the send/write/read/recv system call familty, the AF_ALG
+     In addition to the send/write/read/recv system call family, the AF_ALG
      interface can be accessed with the zero-copy interface of splice/vmsplice.
      As the name indicates, the kernel tries to avoid a copy operation into
      kernel space.
@@ -1669,9 +1669,19 @@ read(opfd, out, outlen);
   </chapter>
 
   <chapter id="API"><title>Programming Interface</title>
+   <para>
+    Please note that the kernel crypto API contains the AEAD givcrypt
+    API (crypto_aead_giv* and aead_givcrypt_* function calls in
+    include/crypto/aead.h). This API is obsolete and will be removed
+    in the future. To obtain the functionality of an AEAD cipher with
+    internal IV generation, use the IV generator as a regular cipher.
+    For example, rfc4106(gcm(aes)) is the AEAD cipher with external
+    IV generation and seqniv(rfc4106(gcm(aes))) implies that the kernel
+    crypto API generates the IV. Different IV generators are available.
+   </para>
    <sect1><title>Block Cipher Context Data Structures</title>
 !Pinclude/linux/crypto.h Block Cipher Context Data Structures
-!Finclude/linux/crypto.h aead_request
+!Finclude/crypto/aead.h aead_request
    </sect1>
    <sect1><title>Block Cipher Algorithm Definitions</title>
 !Pinclude/linux/crypto.h Block Cipher Algorithm Definitions
@@ -1680,7 +1690,7 @@ read(opfd, out, outlen);
 !Finclude/linux/crypto.h aead_alg
 !Finclude/linux/crypto.h blkcipher_alg
 !Finclude/linux/crypto.h cipher_alg
-!Finclude/linux/crypto.h rng_alg
+!Finclude/crypto/rng.h rng_alg
    </sect1>
    <sect1><title>Asynchronous Block Cipher API</title>
 !Pinclude/linux/crypto.h Asynchronous Block Cipher API
@@ -1704,26 +1714,27 @@ read(opfd, out, outlen);
 !Finclude/linux/crypto.h ablkcipher_request_set_crypt
    </sect1>
    <sect1><title>Authenticated Encryption With Associated Data (AEAD) Cipher API</title>
-!Pinclude/linux/crypto.h Authenticated Encryption With Associated Data (AEAD) Cipher API
-!Finclude/linux/crypto.h crypto_alloc_aead
-!Finclude/linux/crypto.h crypto_free_aead
-!Finclude/linux/crypto.h crypto_aead_ivsize
-!Finclude/linux/crypto.h crypto_aead_authsize
-!Finclude/linux/crypto.h crypto_aead_blocksize
-!Finclude/linux/crypto.h crypto_aead_setkey
-!Finclude/linux/crypto.h crypto_aead_setauthsize
-!Finclude/linux/crypto.h crypto_aead_encrypt
-!Finclude/linux/crypto.h crypto_aead_decrypt
+!Pinclude/crypto/aead.h Authenticated Encryption With Associated Data (AEAD) Cipher API
+!Finclude/crypto/aead.h crypto_alloc_aead
+!Finclude/crypto/aead.h crypto_free_aead
+!Finclude/crypto/aead.h crypto_aead_ivsize
+!Finclude/crypto/aead.h crypto_aead_authsize
+!Finclude/crypto/aead.h crypto_aead_blocksize
+!Finclude/crypto/aead.h crypto_aead_setkey
+!Finclude/crypto/aead.h crypto_aead_setauthsize
+!Finclude/crypto/aead.h crypto_aead_encrypt
+!Finclude/crypto/aead.h crypto_aead_decrypt
    </sect1>
    <sect1><title>Asynchronous AEAD Request Handle</title>
-!Pinclude/linux/crypto.h Asynchronous AEAD Request Handle
-!Finclude/linux/crypto.h crypto_aead_reqsize
-!Finclude/linux/crypto.h aead_request_set_tfm
-!Finclude/linux/crypto.h aead_request_alloc
-!Finclude/linux/crypto.h aead_request_free
-!Finclude/linux/crypto.h aead_request_set_callback
-!Finclude/linux/crypto.h aead_request_set_crypt
-!Finclude/linux/crypto.h aead_request_set_assoc
+!Pinclude/crypto/aead.h Asynchronous AEAD Request Handle
+!Finclude/crypto/aead.h crypto_aead_reqsize
+!Finclude/crypto/aead.h aead_request_set_tfm
+!Finclude/crypto/aead.h aead_request_alloc
+!Finclude/crypto/aead.h aead_request_free
+!Finclude/crypto/aead.h aead_request_set_callback
+!Finclude/crypto/aead.h aead_request_set_crypt
+!Finclude/crypto/aead.h aead_request_set_assoc
+!Finclude/crypto/aead.h aead_request_set_ad
    </sect1>
    <sect1><title>Synchronous Block Cipher API</title>
 !Pinclude/linux/crypto.h Synchronous Block Cipher API
diff --git a/Documentation/RCU/arrayRCU.txt b/Documentation/RCU/arrayRCU.txt
index 453ebe6953ee..f05a9afb2c39 100644
--- a/Documentation/RCU/arrayRCU.txt
+++ b/Documentation/RCU/arrayRCU.txt
@@ -10,7 +10,19 @@ also be used to protect arrays.  Three situations are as follows:
 
 3.  Resizeable Arrays
 
-Each of these situations are discussed below.
+Each of these three situations involves an RCU-protected pointer to an
+array that is separately indexed.  It might be tempting to consider use
+of RCU to instead protect the index into an array, however, this use
+case is -not- supported.  The problem with RCU-protected indexes into
+arrays is that compilers can play way too many optimization games with
+integers, which means that the rules governing handling of these indexes
+are far more trouble than they are worth.  If RCU-protected indexes into
+arrays prove to be particularly valuable (which they have not thus far),
+explicit cooperation from the compiler will be required to permit them
+to be safely used.
+
+That aside, each of the three RCU-protected pointer situations are
+described in the following sections.
 
 
 Situation 1: Hash Tables
@@ -36,9 +48,9 @@ Quick Quiz:  Why is it so important that updates be rare when
 Situation 3: Resizeable Arrays
 
 Use of RCU for resizeable arrays is demonstrated by the grow_ary()
-function used by the System V IPC code.  The array is used to map from
-semaphore, message-queue, and shared-memory IDs to the data structure
-that represents the corresponding IPC construct.  The grow_ary()
+function formerly used by the System V IPC code.  The array is used
+to map from semaphore, message-queue, and shared-memory IDs to the data
+structure that represents the corresponding IPC construct.  The grow_ary()
 function does not acquire any locks; instead its caller must hold the
 ids->sem semaphore.
 
diff --git a/Documentation/RCU/lockdep.txt b/Documentation/RCU/lockdep.txt
index cd83d2348fef..da51d3068850 100644
--- a/Documentation/RCU/lockdep.txt
+++ b/Documentation/RCU/lockdep.txt
@@ -47,11 +47,6 @@ checking of rcu_dereference() primitives:
 		Use explicit check expression "c" along with
 		srcu_read_lock_held()().  This is useful in code that
 		is invoked by both SRCU readers and updaters.
-	rcu_dereference_index_check(p, c):
-		Use explicit check expression "c", but the caller
-		must supply one of the rcu_read_lock_held() functions.
-		This is useful in code that uses RCU-protected arrays
-		that is invoked by both RCU readers and updaters.
 	rcu_dereference_raw(p):
 		Don't check.  (Use sparingly, if at all.)
 	rcu_dereference_protected(p, c):
@@ -64,11 +59,6 @@ checking of rcu_dereference() primitives:
 		but retain the compiler constraints that prevent duplicating
 		or coalescsing.  This is useful when when testing the
 		value of the pointer itself, for example, against NULL.
-	rcu_access_index(idx):
-		Return the value of the index and omit all barriers, but
-		retain the compiler constraints that prevent duplicating
-		or coalescsing.  This is useful when when testing the
-		value of the index itself, for example, against -1.
 
 The rcu_dereference_check() check expression can be any boolean
 expression, but would normally include a lockdep expression.  However,
diff --git a/Documentation/RCU/rcu_dereference.txt b/Documentation/RCU/rcu_dereference.txt
index ceb05da5a5ac..1e6c0da994f5 100644
--- a/Documentation/RCU/rcu_dereference.txt
+++ b/Documentation/RCU/rcu_dereference.txt
@@ -25,17 +25,6 @@ o	You must use one of the rcu_dereference() family of primitives
 	for an example where the compiler can in fact deduce the exact
 	value of the pointer, and thus cause misordering.
 
-o	Do not use single-element RCU-protected arrays.  The compiler
-	is within its right to assume that the value of an index into
-	such an array must necessarily evaluate to zero.  The compiler
-	could then substitute the constant zero for the computation, so
-	that the array index no longer depended on the value returned
-	by rcu_dereference().  If the array index no longer depends
-	on rcu_dereference(), then both the compiler and the CPU
-	are within their rights to order the array access before the
-	rcu_dereference(), which can cause the array access to return
-	garbage.
-
 o	Avoid cancellation when using the "+" and "-" infix arithmetic
 	operators.  For example, for a given variable "x", avoid
 	"(x-x)".  There are similar arithmetic pitfalls from other
@@ -76,14 +65,15 @@ o	Do not use the results from the boolean "&&" and "||" when
 	dereferencing.	For example, the following (rather improbable)
 	code is buggy:
 
-		int a[2];
-		int index;
-		int force_zero_index = 1;
+		int *p;
+		int *q;
 
 		...
 
-		r1 = rcu_dereference(i1)
-		r2 = a[r1 && force_zero_index];  /* BUGGY!!! */
+		p = rcu_dereference(gp)
+		q = &global_q;
+		q += p != &oom_p1 && p != &oom_p2;
+		r1 = *q;  /* BUGGY!!! */
 
 	The reason this is buggy is that "&&" and "||" are often compiled
 	using branches.  While weak-memory machines such as ARM or PowerPC
@@ -94,14 +84,15 @@ o	Do not use the results from relational operators ("==", "!=",
 	">", ">=", "<", or "<=") when dereferencing.  For example,
 	the following (quite strange) code is buggy:
 
-		int a[2];
-		int index;
-		int flip_index = 0;
+		int *p;
+		int *q;
 
 		...
 
-		r1 = rcu_dereference(i1)
-		r2 = a[r1 != flip_index];  /* BUGGY!!! */
+		p = rcu_dereference(gp)
+		q = &global_q;
+		q += p > &oom_p;
+		r1 = *q;  /* BUGGY!!! */
 
 	As before, the reason this is buggy is that relational operators
 	are often compiled using branches.  And as before, although
@@ -193,6 +184,11 @@ o	Be very careful about comparing pointers obtained from
 		pointer.  Note that the volatile cast in rcu_dereference()
 		will normally prevent the compiler from knowing too much.
 
+		However, please note that if the compiler knows that the
+		pointer takes on only one of two values, a not-equal
+		comparison will provide exactly the information that the
+		compiler needs to deduce the value of the pointer.
+
 o	Disable any value-speculation optimizations that your compiler
 	might provide, especially if you are making use of feedback-based
 	optimizations that take data collected from prior runs.  Such
diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt
index 88dfce182f66..5746b0c77f3e 100644
--- a/Documentation/RCU/whatisRCU.txt
+++ b/Documentation/RCU/whatisRCU.txt
@@ -256,7 +256,9 @@ rcu_dereference()
 	If you are going to be fetching multiple fields from the
 	RCU-protected structure, using the local variable is of
 	course preferred.  Repeated rcu_dereference() calls look
-	ugly and incur unnecessary overhead on Alpha CPUs.
+	ugly, do not guarantee that the same pointer will be returned
+	if an update happened while in the critical section, and incur
+	unnecessary overhead on Alpha CPUs.
 
 	Note that the value returned by rcu_dereference() is valid
 	only within the enclosing RCU read-side critical section.
@@ -879,9 +881,7 @@ SRCU:	Initialization/cleanup
 
 All:  lockdep-checked RCU-protected pointer access
 
-	rcu_access_index
 	rcu_access_pointer
-	rcu_dereference_index_check
 	rcu_dereference_raw
 	rcu_lockdep_assert
 	rcu_sleep_check
diff --git a/Documentation/cputopology.txt b/Documentation/cputopology.txt
index 0aad6deb2d96..12b1b25b4da9 100644
--- a/Documentation/cputopology.txt
+++ b/Documentation/cputopology.txt
@@ -1,6 +1,6 @@
 
 Export CPU topology info via sysfs. Items (attributes) are similar
-to /proc/cpuinfo.
+to /proc/cpuinfo output of some architectures:
 
 1) /sys/devices/system/cpu/cpuX/topology/physical_package_id:
 
@@ -23,20 +23,35 @@ to /proc/cpuinfo.
 4) /sys/devices/system/cpu/cpuX/topology/thread_siblings:
 
 	internal kernel map of cpuX's hardware threads within the same
-	core as cpuX
+	core as cpuX.
 
-5) /sys/devices/system/cpu/cpuX/topology/core_siblings:
+5) /sys/devices/system/cpu/cpuX/topology/thread_siblings_list:
+
+	human-readable list of cpuX's hardware threads within the same
+	core as cpuX.
+
+6) /sys/devices/system/cpu/cpuX/topology/core_siblings:
 
 	internal kernel map of cpuX's hardware threads within the same
 	physical_package_id.
 
-6) /sys/devices/system/cpu/cpuX/topology/book_siblings:
+7) /sys/devices/system/cpu/cpuX/topology/core_siblings_list:
+
+	human-readable list of cpuX's hardware threads within the same
+	physical_package_id.
+
+8) /sys/devices/system/cpu/cpuX/topology/book_siblings:
 
 	internal kernel map of cpuX's hardware threads within the same
 	book_id.
 
+9) /sys/devices/system/cpu/cpuX/topology/book_siblings_list:
+
+	human-readable list of cpuX's hardware threads within the same
+	book_id.
+
 To implement it in an architecture-neutral way, a new source file,
-drivers/base/topology.c, is to export the 4 or 6 attributes. The two book
+drivers/base/topology.c, is to export the 6 or 9 attributes. The three book
 related sysfs files will only be created if CONFIG_SCHED_BOOK is selected.
 
 For an architecture to support this feature, it must define some of
@@ -44,20 +59,22 @@ these macros in include/asm-XXX/topology.h:
 #define topology_physical_package_id(cpu)
 #define topology_core_id(cpu)
 #define topology_book_id(cpu)
-#define topology_thread_cpumask(cpu)
+#define topology_sibling_cpumask(cpu)
 #define topology_core_cpumask(cpu)
 #define topology_book_cpumask(cpu)
 
-The type of **_id is int.
-The type of siblings is (const) struct cpumask *.
+The type of **_id macros is int.
+The type of **_cpumask macros is (const) struct cpumask *. The latter
+correspond with appropriate **_siblings sysfs attributes (except for
+topology_sibling_cpumask() which corresponds with thread_siblings).
 
 To be consistent on all architectures, include/linux/topology.h
 provides default definitions for any of the above macros that are
 not defined by include/asm-XXX/topology.h:
 1) physical_package_id: -1
 2) core_id: 0
-3) thread_siblings: just the given CPU
-4) core_siblings: just the given CPU
+3) sibling_cpumask: just the given CPU
+4) core_cpumask: just the given CPU
 
 For architectures that don't support books (CONFIG_SCHED_BOOK) there are no
 default definitions for topology_book_id() and topology_book_cpumask().
diff --git a/Documentation/devicetree/bindings/arm/armv7m_systick.txt b/Documentation/devicetree/bindings/arm/armv7m_systick.txt
new file mode 100644
index 000000000000..7cf4a24601eb
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/armv7m_systick.txt
@@ -0,0 +1,26 @@
+* ARMv7M System Timer
+
+ARMv7-M includes a system timer, known as SysTick. Current driver only
+implements the clocksource feature.
+
+Required properties:
+- compatible	  : Should be "arm,armv7m-systick"
+- reg		  : The address range of the timer
+
+Required clocking property, have to be one of:
+- clocks	  : The input clock of the timer
+- clock-frequency : The rate in HZ in input of the ARM SysTick
+
+Examples:
+
+systick: timer@e000e010 {
+	compatible = "arm,armv7m-systick";
+	reg = <0xe000e010 0x10>;
+	clocks = <&clk_systick>;
+};
+
+systick: timer@e000e010 {
+	compatible = "arm,armv7m-systick";
+	reg = <0xe000e010 0x10>;
+	clock-frequency = <90000000>;
+};
diff --git a/Documentation/devicetree/bindings/clock/at91-clock.txt b/Documentation/devicetree/bindings/clock/at91-clock.txt
index 7a4d4926f44e..5ba6450693b9 100644
--- a/Documentation/devicetree/bindings/clock/at91-clock.txt
+++ b/Documentation/devicetree/bindings/clock/at91-clock.txt
@@ -248,7 +248,7 @@ Required properties for peripheral clocks:
 - #address-cells : shall be 1 (reg is used to encode clk id).
 - clocks : shall be the master clock phandle.
 	e.g. clocks = <&mck>;
-- name: device tree node describing a specific system clock.
+- name: device tree node describing a specific peripheral clock.
 	* #clock-cells : from common clock binding; shall be set to 0.
 	* reg: peripheral id. See Atmel's datasheets to get a full
 	  list of peripheral ids.
diff --git a/Documentation/devicetree/bindings/crypto/fsl-sec2.txt b/Documentation/devicetree/bindings/crypto/fsl-sec2.txt
index 38988ef1336b..f0d926bf9f36 100644
--- a/Documentation/devicetree/bindings/crypto/fsl-sec2.txt
+++ b/Documentation/devicetree/bindings/crypto/fsl-sec2.txt
@@ -1,9 +1,11 @@
-Freescale SoC SEC Security Engines versions 2.x-3.x
+Freescale SoC SEC Security Engines versions 1.x-2.x-3.x
 
 Required properties:
 
 - compatible : Should contain entries for this and backward compatible
-  SEC versions, high to low, e.g., "fsl,sec2.1", "fsl,sec2.0"
+  SEC versions, high to low, e.g., "fsl,sec2.1", "fsl,sec2.0" (SEC2/3)
+                             e.g., "fsl,sec1.2", "fsl,sec1.0" (SEC1)
+    warning: SEC1 and SEC2 are mutually exclusive
 - reg : Offset and length of the register set for the device
 - interrupts : the SEC's interrupt number
 - fsl,num-channels : An integer representing the number of channels
diff --git a/Documentation/devicetree/bindings/crypto/marvell-cesa.txt b/Documentation/devicetree/bindings/crypto/marvell-cesa.txt
new file mode 100644
index 000000000000..c6c6a4a045bd
--- /dev/null
+++ b/Documentation/devicetree/bindings/crypto/marvell-cesa.txt
@@ -0,0 +1,45 @@
+Marvell Cryptographic Engines And Security Accelerator
+
+Required properties:
+- compatible: should be one of the following string
+	      "marvell,orion-crypto"
+	      "marvell,kirkwood-crypto"
+	      "marvell,dove-crypto"
+	      "marvell,armada-370-crypto"
+	      "marvell,armada-xp-crypto"
+	      "marvell,armada-375-crypto"
+	      "marvell,armada-38x-crypto"
+- reg: base physical address of the engine and length of memory mapped
+       region. Can also contain an entry for the SRAM attached to the CESA,
+       but this representation is deprecated and marvell,crypto-srams should
+       be used instead
+- reg-names: "regs". Can contain an "sram" entry, but this representation
+	     is deprecated and marvell,crypto-srams should be used instead
+- interrupts: interrupt number
+- clocks: reference to the crypto engines clocks. This property is not
+	  required for orion and kirkwood platforms
+- clock-names: "cesaX" and "cesazX", X should be replaced by the crypto engine
+	       id.
+	       This property is not required for the orion and kirkwoord
+	       platforms.
+	       "cesazX" clocks are not required on armada-370 platforms
+- marvell,crypto-srams: phandle to crypto SRAM definitions
+
+Optional properties:
+- marvell,crypto-sram-size: SRAM size reserved for crypto operations, if not
+			    specified the whole SRAM is used (2KB)
+
+
+Examples:
+
+	crypto@90000 {
+		compatible = "marvell,armada-xp-crypto";
+		reg = <0x90000 0x10000>;
+		reg-names = "regs";
+		interrupts = <48>, <49>;
+		clocks = <&gateclk 23>, <&gateclk 23>;
+		clock-names = "cesa0", "cesa1";
+		marvell,crypto-srams = <&crypto_sram0>, <&crypto_sram1>;
+		marvell,crypto-sram-size = <0x600>;
+		status = "okay";
+	};
diff --git a/Documentation/devicetree/bindings/crypto/mv_cesa.txt b/Documentation/devicetree/bindings/crypto/mv_cesa.txt
index 47229b1a594b..c0c35f00335b 100644
--- a/Documentation/devicetree/bindings/crypto/mv_cesa.txt
+++ b/Documentation/devicetree/bindings/crypto/mv_cesa.txt
@@ -1,20 +1,33 @@
 Marvell Cryptographic Engines And Security Accelerator
 
 Required properties:
-- compatible : should be "marvell,orion-crypto"
-- reg : base physical address of the engine and length of memory mapped
-        region, followed by base physical address of sram and its memory
-        length
-- reg-names : "regs" , "sram";
-- interrupts : interrupt number
+- compatible: should be one of the following string
+	      "marvell,orion-crypto"
+	      "marvell,kirkwood-crypto"
+	      "marvell,dove-crypto"
+- reg: base physical address of the engine and length of memory mapped
+       region. Can also contain an entry for the SRAM attached to the CESA,
+       but this representation is deprecated and marvell,crypto-srams should
+       be used instead
+- reg-names: "regs". Can contain an "sram" entry, but this representation
+	     is deprecated and marvell,crypto-srams should be used instead
+- interrupts: interrupt number
+- clocks: reference to the crypto engines clocks. This property is only
+	  required for Dove platforms
+- marvell,crypto-srams: phandle to crypto SRAM definitions
+
+Optional properties:
+- marvell,crypto-sram-size: SRAM size reserved for crypto operations, if not
+			    specified the whole SRAM is used (2KB)
 
 Examples:
 
 	crypto@30000 {
 		compatible = "marvell,orion-crypto";
-		reg = <0x30000 0x10000>,
-		      <0x4000000 0x800>;
-		reg-names = "regs" , "sram";
+		reg = <0x30000 0x10000>;
+		reg-names = "regs";
 		interrupts = <22>;
+		marvell,crypto-srams = <&crypto_sram>;
+		marvell,crypto-sram-size = <0x600>;
 		status = "okay";
 	};
diff --git a/Documentation/devicetree/bindings/gpio/brcm,brcmstb-gpio.txt b/Documentation/devicetree/bindings/gpio/brcm,brcmstb-gpio.txt
new file mode 100644
index 000000000000..435f1bcca341
--- /dev/null
+++ b/Documentation/devicetree/bindings/gpio/brcm,brcmstb-gpio.txt
@@ -0,0 +1,65 @@
+Broadcom STB "UPG GIO" GPIO controller
+
+The controller's registers are organized as sets of eight 32-bit
+registers with each set controlling a bank of up to 32 pins.  A single
+interrupt is shared for all of the banks handled by the controller.
+
+Required properties:
+
+- compatible:
+    Must be "brcm,brcmstb-gpio"
+
+- reg:
+    Define the base and range of the I/O address space containing
+    the brcmstb GPIO controller registers
+
+- #gpio-cells:
+    Should be <2>.  The first cell is the pin number (within the controller's
+    pin space), and the second is used for the following:
+    bit[0]: polarity (0 for active-high, 1 for active-low)
+
+- gpio-controller:
+    Specifies that the node is a GPIO controller.
+
+- brcm,gpio-bank-widths:
+    Number of GPIO lines for each bank.  Number of elements must
+    correspond to number of banks suggested by the 'reg' property.
+
+Optional properties:
+
+- interrupts:
+    The interrupt shared by all GPIO lines for this controller.
+
+- interrupt-parent:
+    phandle of the parent interrupt controller
+
+- #interrupt-cells:
+    Should be <2>.  The first cell is the GPIO number, the second should specify
+    flags.  The following subset of flags is supported:
+    - bits[3:0] trigger type and level flags
+        1 = low-to-high edge triggered
+        2 = high-to-low edge triggered
+        4 = active high level-sensitive
+        8 = active low level-sensitive
+      Valid combinations are 1, 2, 3, 4, 8.
+    See also Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
+
+- interrupt-controller:
+    Marks the device node as an interrupt controller
+
+- interrupt-names:
+    The name of the IRQ resource used by this controller
+
+Example:
+	upg_gio: gpio@f040a700 {
+		#gpio-cells = <0x2>;
+		#interrupt-cells = <0x2>;
+		compatible = "brcm,bcm7445-gpio", "brcm,brcmstb-gpio";
+		gpio-controller;
+		interrupt-controller;
+		reg = <0xf040a700 0x80>;
+		interrupt-parent = <0xf>;
+		interrupts = <0x6>;
+		interrupt-names = "upg_gio";
+		brcm,gpio-bank-widths = <0x20 0x20 0x20 0x18>;
+	};
diff --git a/Documentation/devicetree/bindings/gpio/gpio-etraxfs.txt b/Documentation/devicetree/bindings/gpio/gpio-etraxfs.txt
new file mode 100644
index 000000000000..abf4db736c6e
--- /dev/null
+++ b/Documentation/devicetree/bindings/gpio/gpio-etraxfs.txt
@@ -0,0 +1,21 @@
+Axis ETRAX FS General I/O controller bindings
+
+Required properties:
+
+- compatible:
+  - "axis,etraxfs-gio"
+- reg: Physical base address and length of the controller's registers.
+- #gpio-cells: Should be 3
+  - The first cell is the gpio offset number.
+  - The second cell is reserved and is currently unused.
+  - The third cell is the port number (hex).
+- gpio-controller: Marks the device node as a GPIO controller.
+
+Example:
+
+	gio: gpio@b001a000 {
+		compatible = "axis,etraxfs-gio";
+		reg = <0xb001a000 0x1000>;
+		gpio-controller;
+		#gpio-cells = <3>;
+	};
diff --git a/Documentation/devicetree/bindings/gpio/gpio-xlp.txt b/Documentation/devicetree/bindings/gpio/gpio-xlp.txt
new file mode 100644
index 000000000000..262ee4ddf2cb
--- /dev/null
+++ b/Documentation/devicetree/bindings/gpio/gpio-xlp.txt
@@ -0,0 +1,47 @@
+Netlogic XLP Family GPIO
+========================
+
+This GPIO driver is used for following Netlogic XLP SoCs:
+	XLP832, XLP316, XLP208, XLP980, XLP532
+
+Required properties:
+-------------------
+
+- compatible: Should be one of the following:
+  - "netlogic,xlp832-gpio": For Netlogic XLP832
+  - "netlogic,xlp316-gpio": For Netlogic XLP316
+  - "netlogic,xlp208-gpio": For Netlogic XLP208
+  - "netlogic,xlp980-gpio": For Netlogic XLP980
+  - "netlogic,xlp532-gpio": For Netlogic XLP532
+- reg: Physical base address and length of the controller's registers.
+- #gpio-cells: Should be two. The first cell is the pin number and the second
+  cell is used to specify optional parameters (currently unused).
+- gpio-controller: Marks the device node as a GPIO controller.
+- nr-gpios: Number of GPIO pins supported by the controller.
+- interrupt-cells: Should be two. The first cell is the GPIO Number. The
+  second cell is used to specify flags. The following subset of flags is
+  supported:
+  - trigger type:
+	1 = low to high edge triggered.
+	2 = high to low edge triggered.
+	4 = active high level-sensitive.
+	8 = active low level-sensitive.
+- interrupts: Interrupt number for this device.
+- interrupt-parent: phandle of the parent interrupt controller.
+- interrupt-controller: Identifies the node as an interrupt controller.
+
+Example:
+
+	gpio: xlp_gpio@34000 {
+		compatible = "netlogic,xlp316-gpio";
+		reg = <0 0x34100 0x1000
+		       0 0x35100 0x1000>;
+		#gpio-cells = <2>;
+		gpio-controller;
+		nr-gpios = <57>;
+
+		#interrupt-cells = <2>;
+		interrupt-parent = <&pic>;
+		interrupts = <39>;
+		interrupt-controller;
+	};
diff --git a/Documentation/devicetree/bindings/gpio/gpio-zynq.txt b/Documentation/devicetree/bindings/gpio/gpio-zynq.txt
index 986371a4be2c..db4c6a663c03 100644
--- a/Documentation/devicetree/bindings/gpio/gpio-zynq.txt
+++ b/Documentation/devicetree/bindings/gpio/gpio-zynq.txt
@@ -6,7 +6,7 @@ Required properties:
 			  - First cell is the GPIO line number
 			  - Second cell is used to specify optional
 			    parameters (unused)
-- compatible		: Should be "xlnx,zynq-gpio-1.0"
+- compatible		: Should be "xlnx,zynq-gpio-1.0" or "xlnx,zynqmp-gpio-1.0"
 - clocks		: Clock specifier (see clock bindings for details)
 - gpio-controller	: Marks the device node as a GPIO controller.
 - interrupts		: Interrupt specifier (see interrupt bindings for
diff --git a/Documentation/devicetree/bindings/gpio/nxp,lpc1850-gpio.txt b/Documentation/devicetree/bindings/gpio/nxp,lpc1850-gpio.txt
new file mode 100644
index 000000000000..eb7cdd69e10b
--- /dev/null
+++ b/Documentation/devicetree/bindings/gpio/nxp,lpc1850-gpio.txt
@@ -0,0 +1,39 @@
+NXP LPC18xx/43xx GPIO controller Device Tree Bindings
+-----------------------------------------------------
+
+Required properties:
+- compatible		: Should be "nxp,lpc1850-gpio"
+- reg			: Address and length of the register set for the device
+- clocks		: Clock specifier (see clock bindings for details)
+- gpio-controller	: Marks the device node as a GPIO controller.
+- #gpio-cells 		: Should be two
+			  - First cell is the GPIO line number
+			  - Second cell is used to specify polarity
+
+Optional properties:
+- gpio-ranges		: Mapping between GPIO and pinctrl
+
+Example:
+#define LPC_GPIO(port, pin)	(port * 32 + pin)
+#define LPC_PIN(port, pin)	(0x##port * 32 + pin)
+
+gpio: gpio@400f4000 {
+	compatible = "nxp,lpc1850-gpio";
+	reg = <0x400f4000 0x4000>;
+	clocks = <&ccu1 CLK_CPU_GPIO>;
+	gpio-controller;
+	#gpio-cells = <2>;
+	gpio-ranges =	<&pinctrl LPC_GPIO(0,0)  LPC_PIN(0,0)  2>,
+			...
+			<&pinctrl LPC_GPIO(7,19) LPC_PIN(f,5)  7>;
+};
+
+gpio_joystick {
+	compatible = "gpio-keys-polled";
+	...
+
+	button@0 {
+		...
+		gpios = <&gpio LPC_GPIO(4,8) GPIO_ACTIVE_LOW>;
+	};
+};
diff --git a/Documentation/devicetree/bindings/hwmon/ntc_thermistor.txt b/Documentation/devicetree/bindings/hwmon/ntc_thermistor.txt
index fcca8e744f41..a04a80f9cc70 100644
--- a/Documentation/devicetree/bindings/hwmon/ntc_thermistor.txt
+++ b/Documentation/devicetree/bindings/hwmon/ntc_thermistor.txt
@@ -9,6 +9,7 @@ Requires node properties:
 	"murata,ncp21wb473"
 	"murata,ncp03wb473"
 	"murata,ncp15wl333"
+	"murata,ncp03wf104"
 
 /* Usage of vendor name "ntc" is deprecated */
 <DEPRECATED>	"ntc,ncp15wb473"
diff --git a/Documentation/devicetree/bindings/interrupt-controller/atmel,aic.txt b/Documentation/devicetree/bindings/interrupt-controller/atmel,aic.txt
index f292917fa00d..0e9f09a6a2fe 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/atmel,aic.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/atmel,aic.txt
@@ -2,7 +2,7 @@
 
 Required properties:
 - compatible: Should be "atmel,<chip>-aic"
-  <chip> can be "at91rm9200", "sama5d3" or "sama5d4"
+  <chip> can be "at91rm9200", "sama5d2", "sama5d3" or "sama5d4"
 - interrupt-controller: Identifies the node as an interrupt controller.
 - interrupt-parent: For single AIC system, it is an empty property.
 - #interrupt-cells: The number of cells to define the interrupts. It should be 3.
diff --git a/Documentation/devicetree/bindings/interrupt-controller/renesas,intc-irqpin.txt b/Documentation/devicetree/bindings/interrupt-controller/renesas,intc-irqpin.txt
index 4f7946ae8adc..772c550d3b4b 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/renesas,intc-irqpin.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/renesas,intc-irqpin.txt
@@ -13,9 +13,12 @@ Required properties:
 - reg: Base address and length of each register bank used by the external
   IRQ pins driven by the interrupt controller hardware module. The base
   addresses, length and number of required register banks varies with soctype.
-
+- interrupt-controller: Identifies the node as an interrupt controller.
 - #interrupt-cells: has to be <2>: an interrupt index and flags, as defined in
-  interrupts.txt in this directory
+  interrupts.txt in this directory.
+- interrupts: Must contain a list of interrupt specifiers. For each interrupt
+  provided by this irqpin controller instance, there must be one entry,
+  referring to the corresponding parent interrupt.
 
 Optional properties:
 
@@ -25,3 +28,35 @@ Optional properties:
   if different from the default 4 bits
 - control-parent: disable and enable interrupts on the parent interrupt
   controller, needed for some broken implementations
+- clocks: Must contain a reference to the functional clock.  This property is
+  mandatory if the hardware implements a controllable functional clock for
+  the irqpin controller instance.
+- power-domains: Must contain a reference to the power domain. This property is
+  mandatory if the irqpin controller instance is part of a controllable power
+  domain.
+
+
+Example
+-------
+
+	irqpin1: interrupt-controller@e6900004 {
+		compatible = "renesas,intc-irqpin-r8a7740",
+			     "renesas,intc-irqpin";
+		#interrupt-cells = <2>;
+		interrupt-controller;
+		reg = <0xe6900004 4>,
+			<0xe6900014 4>,
+			<0xe6900024 1>,
+			<0xe6900044 1>,
+			<0xe6900064 1>;
+		interrupts = <0 149 IRQ_TYPE_LEVEL_HIGH
+			      0 149 IRQ_TYPE_LEVEL_HIGH
+			      0 149 IRQ_TYPE_LEVEL_HIGH
+			      0 149 IRQ_TYPE_LEVEL_HIGH
+			      0 149 IRQ_TYPE_LEVEL_HIGH
+			      0 149 IRQ_TYPE_LEVEL_HIGH
+			      0 149 IRQ_TYPE_LEVEL_HIGH
+			      0 149 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp2_clks R8A7740_CLK_INTCA>;
+		power-domains = <&pd_a4s>;
+	};
diff --git a/Documentation/devicetree/bindings/mmc/arasan,sdhci.txt b/Documentation/devicetree/bindings/mmc/arasan,sdhci.txt
index 98ee2abbe138..7e9490313d5a 100644
--- a/Documentation/devicetree/bindings/mmc/arasan,sdhci.txt
+++ b/Documentation/devicetree/bindings/mmc/arasan,sdhci.txt
@@ -8,7 +8,8 @@ Device Tree Bindings for the Arasan SDHCI Controller
   [3] Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
 
 Required Properties:
-  - compatible: Compatibility string. Must be 'arasan,sdhci-8.9a'
+  - compatible: Compatibility string. Must be 'arasan,sdhci-8.9a' or
+                'arasan,sdhci-4.9a'
   - reg: From mmc bindings: Register location and length.
   - clocks: From clock bindings: Handles to clock inputs.
   - clock-names: From clock bindings: Tuple including "clk_xin" and "clk_ahb"
diff --git a/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.txt b/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.txt
index 415c5575cbf7..5d0376b8f202 100644
--- a/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.txt
+++ b/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.txt
@@ -7,7 +7,14 @@ This file documents differences between the core properties described
 by mmc.txt and the properties used by the sdhci-esdhc-imx driver.
 
 Required properties:
-- compatible : Should be "fsl,<chip>-esdhc"
+- compatible : Should be "fsl,<chip>-esdhc", the supported chips include
+	       "fsl,imx25-esdhc"
+	       "fsl,imx35-esdhc"
+	       "fsl,imx51-esdhc"
+	       "fsl,imx53-esdhc"
+	       "fsl,imx6q-usdhc"
+	       "fsl,imx6sl-usdhc"
+	       "fsl,imx6sx-usdhc"
 
 Optional properties:
 - fsl,cd-controller : Indicate to use controller internal card detection
diff --git a/Documentation/devicetree/bindings/mmc/k3-dw-mshc.txt b/Documentation/devicetree/bindings/mmc/k3-dw-mshc.txt
index 3b3544931437..df370585cbcc 100644
--- a/Documentation/devicetree/bindings/mmc/k3-dw-mshc.txt
+++ b/Documentation/devicetree/bindings/mmc/k3-dw-mshc.txt
@@ -13,6 +13,10 @@ Required Properties:
 
 * compatible: should be one of the following.
   - "hisilicon,hi4511-dw-mshc": for controllers with hi4511 specific extensions.
+  - "hisilicon,hi6220-dw-mshc": for controllers with hi6220 specific extensions.
+
+Optional Properties:
+- hisilicon,peripheral-syscon: phandle of syscon used to control peripheral.
 
 Example:
 
@@ -42,3 +46,27 @@ Example:
 		cap-mmc-highspeed;
 		cap-sd-highspeed;
 	};
+
+	/* for Hi6220 */
+
+	dwmmc_1: dwmmc1@f723e000 {
+		compatible = "hisilicon,hi6220-dw-mshc";
+		num-slots = <0x1>;
+		bus-width = <0x4>;
+		disable-wp;
+		cap-sd-highspeed;
+		sd-uhs-sdr12;
+		sd-uhs-sdr25;
+		card-detect-delay = <200>;
+		hisilicon,peripheral-syscon = <&ao_ctrl>;
+		reg = <0x0 0xf723e000 0x0 0x1000>;
+		interrupts = <0x0 0x49 0x4>;
+		clocks = <&clock_sys HI6220_MMC1_CIUCLK>, <&clock_sys HI6220_MMC1_CLK>;
+		clock-names = "ciu", "biu";
+		cd-gpios = <&gpio1 0 1>;
+		pinctrl-names = "default", "idle";
+		pinctrl-0 = <&sd_pmx_func &sd_clk_cfg_func &sd_cfg_func>;
+		pinctrl-1 = <&sd_pmx_idle &sd_clk_cfg_idle &sd_cfg_idle>;
+		vqmmc-supply = <&ldo7>;
+		vmmc-supply = <&ldo10>;
+	};
diff --git a/Documentation/devicetree/bindings/mmc/mmc-pwrseq-simple.txt b/Documentation/devicetree/bindings/mmc/mmc-pwrseq-simple.txt
index a462c50f19a8..ce0e76749671 100644
--- a/Documentation/devicetree/bindings/mmc/mmc-pwrseq-simple.txt
+++ b/Documentation/devicetree/bindings/mmc/mmc-pwrseq-simple.txt
@@ -21,5 +21,7 @@ Example:
 
 	sdhci0_pwrseq {
 		compatible = "mmc-pwrseq-simple";
-		reset-gpios = <&gpio1 12 0>;
+		reset-gpios = <&gpio1 12 GPIO_ACTIVE_LOW>;
+		clocks = <&clk_32768_ck>;
+		clock-names = "ext_clock";
 	}
diff --git a/Documentation/devicetree/bindings/mmc/mmc.txt b/Documentation/devicetree/bindings/mmc/mmc.txt
index 438899e8829b..0384fc3f64e8 100644
--- a/Documentation/devicetree/bindings/mmc/mmc.txt
+++ b/Documentation/devicetree/bindings/mmc/mmc.txt
@@ -21,6 +21,11 @@ Optional properties:
   below for the case, when a GPIO is used for the CD line
 - wp-inverted: when present, polarity on the WP line is inverted. See the note
   below for the case, when a GPIO is used for the WP line
+- disable-wp: When set no physical WP line is present. This property should
+  only be specified when the controller has a dedicated write-protect
+  detection logic. If a GPIO is always used for the write-protect detection
+  logic it is sufficient to not specify wp-gpios property in the absence of a WP
+  line.
 - max-frequency: maximum operating clock frequency
 - no-1-8-v: when present, denotes that 1.8v card voltage is not supported on
   this system, even if the controller claims it is.
diff --git a/Documentation/devicetree/bindings/mmc/mtk-sd.txt b/Documentation/devicetree/bindings/mmc/mtk-sd.txt
new file mode 100644
index 000000000000..a1adfa495ad3
--- /dev/null
+++ b/Documentation/devicetree/bindings/mmc/mtk-sd.txt
@@ -0,0 +1,32 @@
+* MTK MMC controller
+
+The MTK  MSDC can act as a MMC controller
+to support MMC, SD, and SDIO types of memory cards.
+
+This file documents differences between the core properties in mmc.txt
+and the properties used by the msdc driver.
+
+Required properties:
+- compatible: Should be "mediatek,mt8173-mmc","mediatek,mt8135-mmc"
+- interrupts: Should contain MSDC interrupt number
+- clocks: MSDC source clock, HCLK
+- clock-names: "source", "hclk"
+- pinctrl-names: should be "default", "state_uhs"
+- pinctrl-0: should contain default/high speed pin ctrl
+- pinctrl-1: should contain uhs mode pin ctrl
+- vmmc-supply: power to the Core
+- vqmmc-supply: power to the IO
+
+Examples:
+mmc0: mmc@11230000 {
+	compatible = "mediatek,mt8173-mmc", "mediatek,mt8135-mmc";
+	reg = <0 0x11230000 0 0x108>;
+	interrupts = <GIC_SPI 39 IRQ_TYPE_LEVEL_LOW>;
+	vmmc-supply = <&mt6397_vemc_3v3_reg>;
+	vqmmc-supply = <&mt6397_vio18_reg>;
+	clocks = <&pericfg CLK_PERI_MSDC30_0>, <&topckgen CLK_TOP_MSDC50_0_H_SEL>;
+	clock-names = "source", "hclk";
+	pinctrl-names = "default", "state_uhs";
+	pinctrl-0 = <&mmc0_pins_default>;
+	pinctrl-1 = <&mmc0_pins_uhs>;
+};
diff --git a/Documentation/devicetree/bindings/mmc/renesas,mmcif.txt b/Documentation/devicetree/bindings/mmc/renesas,mmcif.txt
index 299081f94abd..d38942f6c5ae 100644
--- a/Documentation/devicetree/bindings/mmc/renesas,mmcif.txt
+++ b/Documentation/devicetree/bindings/mmc/renesas,mmcif.txt
@@ -18,6 +18,8 @@ Required properties:
   dma-names property.
 - dma-names: must contain "tx" for the transmit DMA channel and "rx" for the
   receive DMA channel.
+- max-frequency: Maximum operating clock frequency, driver uses default clock
+  frequency if it is not set.
 
 
 Example: R8A7790 (R-Car H2) MMCIF0
@@ -29,4 +31,5 @@ Example: R8A7790 (R-Car H2) MMCIF0
 		clocks = <&mstp3_clks R8A7790_CLK_MMCIF0>;
 		dmas = <&dmac0 0xd1>, <&dmac0 0xd2>;
 		dma-names = "tx", "rx";
+		max-frequency = <97500000>;
 	};
diff --git a/Documentation/devicetree/bindings/pci/xgene-pci-msi.txt b/Documentation/devicetree/bindings/pci/xgene-pci-msi.txt
new file mode 100644
index 000000000000..36d881c8e6d4
--- /dev/null
+++ b/Documentation/devicetree/bindings/pci/xgene-pci-msi.txt
@@ -0,0 +1,68 @@
+* AppliedMicro X-Gene v1 PCIe MSI controller
+
+Required properties:
+
+- compatible: should be "apm,xgene1-msi" to identify
+	      X-Gene v1 PCIe MSI controller block.
+- msi-controller: indicates that this is X-Gene v1 PCIe MSI controller node
+- reg: physical base address (0x79000000) and length (0x900000) for controller
+       registers. These registers include the MSI termination address and data
+       registers as well as the MSI interrupt status registers.
+- reg-names: not required
+- interrupts: A list of 16 interrupt outputs of the controller, starting from
+	      interrupt number 0x10 to 0x1f.
+- interrupt-names: not required
+
+Each PCIe node needs to have property msi-parent that points to msi controller node
+
+Examples:
+
+SoC DTSI:
+
+	+ MSI node:
+	msi@79000000 {
+		compatible = "apm,xgene1-msi";
+		msi-controller;
+		reg = <0x00 0x79000000 0x0 0x900000>;
+		interrupts = 	<0x0 0x10 0x4>
+				<0x0 0x11 0x4>
+				<0x0 0x12 0x4>
+				<0x0 0x13 0x4>
+				<0x0 0x14 0x4>
+				<0x0 0x15 0x4>
+				<0x0 0x16 0x4>
+				<0x0 0x17 0x4>
+				<0x0 0x18 0x4>
+				<0x0 0x19 0x4>
+				<0x0 0x1a 0x4>
+				<0x0 0x1b 0x4>
+				<0x0 0x1c 0x4>
+				<0x0 0x1d 0x4>
+				<0x0 0x1e 0x4>
+				<0x0 0x1f 0x4>;
+	};
+
+	+ PCIe controller node with msi-parent property pointing to MSI node:
+	pcie0: pcie@1f2b0000 {
+		status = "disabled";
+		device_type = "pci";
+		compatible = "apm,xgene-storm-pcie", "apm,xgene-pcie";
+		#interrupt-cells = <1>;
+		#size-cells = <2>;
+		#address-cells = <3>;
+		reg = < 0x00 0x1f2b0000 0x0 0x00010000   /* Controller registers */
+			0xe0 0xd0000000 0x0 0x00040000>; /* PCI config space */
+		reg-names = "csr", "cfg";
+		ranges = <0x01000000 0x00 0x00000000 0xe0 0x10000000 0x00 0x00010000   /* io */
+			  0x02000000 0x00 0x80000000 0xe1 0x80000000 0x00 0x80000000>; /* mem */
+		dma-ranges = <0x42000000 0x80 0x00000000 0x80 0x00000000 0x00 0x80000000
+			      0x42000000 0x00 0x00000000 0x00 0x00000000 0x80 0x00000000>;
+		interrupt-map-mask = <0x0 0x0 0x0 0x7>;
+		interrupt-map = <0x0 0x0 0x0 0x1 &gic 0x0 0xc2 0x1
+				 0x0 0x0 0x0 0x2 &gic 0x0 0xc3 0x1
+				 0x0 0x0 0x0 0x3 &gic 0x0 0xc4 0x1
+				 0x0 0x0 0x0 0x4 &gic 0x0 0xc5 0x1>;
+		dma-coherent;
+		clocks = <&pcie0clk 0>;
+		msi-parent= <&msi>;
+	};
diff --git a/Documentation/devicetree/bindings/timer/nxp,lpc3220-timer.txt b/Documentation/devicetree/bindings/timer/nxp,lpc3220-timer.txt
new file mode 100644
index 000000000000..51b05a0e70d1
--- /dev/null
+++ b/Documentation/devicetree/bindings/timer/nxp,lpc3220-timer.txt
@@ -0,0 +1,26 @@
+* NXP LPC3220 timer
+
+The NXP LPC3220 timer is used on a wide range of NXP SoCs. This
+includes LPC32xx, LPC178x, LPC18xx and LPC43xx parts.
+
+Required properties:
+- compatible:
+	Should be "nxp,lpc3220-timer".
+- reg:
+	Address and length of the register set.
+- interrupts:
+	Reference to the timer interrupt
+- clocks:
+	Should contain a reference to timer clock.
+- clock-names:
+	Should contain "timerclk".
+
+Example:
+
+timer1: timer@40085000 {
+	compatible = "nxp,lpc3220-timer";
+	reg = <0x40085000 0x1000>;
+	interrupts = <13>;
+	clocks = <&ccu1 CLK_CPU_TIMER1>;
+	clock-names = "timerclk";
+};
diff --git a/Documentation/devicetree/bindings/timer/st,stm32-timer.txt b/Documentation/devicetree/bindings/timer/st,stm32-timer.txt
new file mode 100644
index 000000000000..8ef28e70d6e8
--- /dev/null
+++ b/Documentation/devicetree/bindings/timer/st,stm32-timer.txt
@@ -0,0 +1,22 @@
+. STMicroelectronics STM32 timer
+
+The STM32 MCUs family has several general-purpose 16 and 32 bits timers.
+
+Required properties:
+- compatible : Should be "st,stm32-timer"
+- reg : Address and length of the register set
+- clocks : Reference on the timer input clock
+- interrupts : Reference to the timer interrupt
+
+Optional properties:
+- resets: Reference to a reset controller asserting the timer
+
+Example:
+
+timer5: timer@40000c00 {
+	compatible = "st,stm32-timer";
+	reg = <0x40000c00 0x400>;
+	interrupts = <50>;
+	resets = <&rrc 259>;
+	clocks = <&clk_pmtr1>;
+};
diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 0a926e2ba3ab..6a34a0f4d37c 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -50,8 +50,8 @@ prototypes:
 	int (*rename2) (struct inode *, struct dentry *,
 			struct inode *, struct dentry *, unsigned int);
 	int (*readlink) (struct dentry *, char __user *,int);
-	void * (*follow_link) (struct dentry *, struct nameidata *);
-	void (*put_link) (struct dentry *, struct nameidata *, void *);
+	const char *(*follow_link) (struct dentry *, void **);
+	void (*put_link) (struct inode *, void *);
 	void (*truncate) (struct inode *);
 	int (*permission) (struct inode *, int, unsigned int);
 	int (*get_acl)(struct inode *, int);
diff --git a/Documentation/filesystems/automount-support.txt b/Documentation/filesystems/automount-support.txt
index 7cac200e2a85..7eb762eb3136 100644
--- a/Documentation/filesystems/automount-support.txt
+++ b/Documentation/filesystems/automount-support.txt
@@ -1,41 +1,15 @@
-Support is available for filesystems that wish to do automounting support (such
-as kAFS which can be found in fs/afs/). This facility includes allowing
-in-kernel mounts to be performed and mountpoint degradation to be
-requested. The latter can also be requested by userspace.
+Support is available for filesystems that wish to do automounting
+support (such as kAFS which can be found in fs/afs/ and NFS in
+fs/nfs/). This facility includes allowing in-kernel mounts to be
+performed and mountpoint degradation to be requested. The latter can
+also be requested by userspace.
 
 
 ======================
 IN-KERNEL AUTOMOUNTING
 ======================
 
-A filesystem can now mount another filesystem on one of its directories by the
-following procedure:
-
- (1) Give the directory a follow_link() operation.
-
-     When the directory is accessed, the follow_link op will be called, and
-     it will be provided with the location of the mountpoint in the nameidata
-     structure (vfsmount and dentry).
-
- (2) Have the follow_link() op do the following steps:
-
-     (a) Call vfs_kern_mount() to call the appropriate filesystem to set up a
-         superblock and gain a vfsmount structure representing it.
-
-     (b) Copy the nameidata provided as an argument and substitute the dentry
-	 argument into it the copy.
-
-     (c) Call do_add_mount() to install the new vfsmount into the namespace's
-	 mountpoint tree, thus making it accessible to userspace. Use the
-	 nameidata set up in (b) as the destination.
-
-	 If the mountpoint will be automatically expired, then do_add_mount()
-	 should also be given the location of an expiration list (see further
-	 down).
-
-     (d) Release the path in the nameidata argument and substitute in the new
-	 vfsmount and its root dentry. The ref counts on these will need
-	 incrementing.
+See section "Mount Traps" of  Documentation/filesystems/autofs4.txt
 
 Then from userspace, you can just do something like:
 
@@ -61,17 +35,18 @@ AUTOMATIC MOUNTPOINT EXPIRY
 ===========================
 
 Automatic expiration of mountpoints is easy, provided you've mounted the
-mountpoint to be expired in the automounting procedure outlined above.
+mountpoint to be expired in the automounting procedure outlined separately.
 
 To do expiration, you need to follow these steps:
 
- (3) Create at least one list off which the vfsmounts to be expired can be
-     hung. Access to this list will be governed by the vfsmount_lock.
+ (1) Create at least one list off which the vfsmounts to be expired can be
+     hung.
 
- (4) In step (2c) above, the call to do_add_mount() should be provided with a
-     pointer to this list. It will hang the vfsmount off of it if it succeeds.
+ (2) When a new mountpoint is created in the ->d_automount method, add
+     the mnt to the list using mnt_set_expiry()
+             mnt_set_expiry(newmnt, &afs_vfsmounts);
 
- (5) When you want mountpoints to be expired, call mark_mounts_for_expiry()
+ (3) When you want mountpoints to be expired, call mark_mounts_for_expiry()
      with a pointer to this list. This will process the list, marking every
      vfsmount thereon for potential expiry on the next call.
 
diff --git a/Documentation/filesystems/porting b/Documentation/filesystems/porting
index e69274de8d0c..3eae250254d5 100644
--- a/Documentation/filesystems/porting
+++ b/Documentation/filesystems/porting
@@ -483,3 +483,20 @@ in your dentry operations instead.
 --
 [mandatory]
 	->aio_read/->aio_write are gone.  Use ->read_iter/->write_iter.
+---
+[recommended]
+	for embedded ("fast") symlinks just set inode->i_link to wherever the
+	symlink body is and use simple_follow_link() as ->follow_link().
+--
+[mandatory]
+	calling conventions for ->follow_link() have changed.  Instead of returning
+	cookie and using nd_set_link() to store the body to traverse, we return
+	the body to traverse and store the cookie using explicit void ** argument.
+	nameidata isn't passed at all - nd_jump_link() doesn't need it and
+	nd_[gs]et_link() is gone.
+--
+[mandatory]
+	calling conventions for ->put_link() have changed.  It gets inode instead of
+	dentry,  it does not get nameidata at all and it gets called only when cookie
+	is non-NULL.  Note that link body isn't available anymore, so if you need it,
+	store it as cookie.
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index 5d833b32bbcd..b403b29ef710 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -350,8 +350,8 @@ struct inode_operations {
 	int (*rename2) (struct inode *, struct dentry *,
 			struct inode *, struct dentry *, unsigned int);
 	int (*readlink) (struct dentry *, char __user *,int);
-        void * (*follow_link) (struct dentry *, struct nameidata *);
-        void (*put_link) (struct dentry *, struct nameidata *, void *);
+	const char *(*follow_link) (struct dentry *, void **);
+	void (*put_link) (struct inode *, void *);
 	int (*permission) (struct inode *, int);
 	int (*get_acl)(struct inode *, int);
 	int (*setattr) (struct dentry *, struct iattr *);
@@ -436,16 +436,18 @@ otherwise noted.
 
   follow_link: called by the VFS to follow a symbolic link to the
 	inode it points to.  Only required if you want to support
-	symbolic links.  This method returns a void pointer cookie
-	that is passed to put_link().
+	symbolic links.  This method returns the symlink body
+	to traverse (and possibly resets the current position with
+	nd_jump_link()).  If the body won't go away until the inode
+	is gone, nothing else is needed; if it needs to be otherwise
+	pinned, the data needed to release whatever we'd grabbed
+	is to be stored in void * variable passed by address to
+	follow_link() instance.
 
   put_link: called by the VFS to release resources allocated by
-  	follow_link().  The cookie returned by follow_link() is passed
-  	to this method as the last parameter.  It is used by
-  	filesystems such as NFS where page cache is not stable
-  	(i.e. page that was installed when the symbolic link walk
-  	started might not be in the page cache at the end of the
-  	walk).
+	follow_link().  The cookie stored by follow_link() is passed
+	to this method as the last parameter; only called when
+	cookie isn't NULL.
 
   permission: called by the VFS to check for access rights on a POSIX-like
   	filesystem.
diff --git a/Documentation/gpio/consumer.txt b/Documentation/gpio/consumer.txt
index c21c1313f09e..bbc8b5888b80 100644
--- a/Documentation/gpio/consumer.txt
+++ b/Documentation/gpio/consumer.txt
@@ -241,18 +241,18 @@ Set multiple GPIO outputs with a single function call
 -----------------------------------------------------
 The following functions set the output values of an array of GPIOs:
 
-	void gpiod_set_array(unsigned int array_size,
-			     struct gpio_desc **desc_array,
-			     int *value_array)
-	void gpiod_set_raw_array(unsigned int array_size,
-				 struct gpio_desc **desc_array,
-				 int *value_array)
-	void gpiod_set_array_cansleep(unsigned int array_size,
-				      struct gpio_desc **desc_array,
-				      int *value_array)
-	void gpiod_set_raw_array_cansleep(unsigned int array_size,
-					  struct gpio_desc **desc_array,
-					  int *value_array)
+	void gpiod_set_array_value(unsigned int array_size,
+				   struct gpio_desc **desc_array,
+				   int *value_array)
+	void gpiod_set_raw_array_value(unsigned int array_size,
+				       struct gpio_desc **desc_array,
+				       int *value_array)
+	void gpiod_set_array_value_cansleep(unsigned int array_size,
+					    struct gpio_desc **desc_array,
+					    int *value_array)
+	void gpiod_set_raw_array_value_cansleep(unsigned int array_size,
+						struct gpio_desc **desc_array,
+						int *value_array)
 
 The array can be an arbitrary set of GPIOs. The functions will try to set
 GPIOs belonging to the same bank or chip simultaneously if supported by the
@@ -271,8 +271,8 @@ matches the desired group of GPIOs, those GPIOs can be set by simply using
 the struct gpio_descs returned by gpiod_get_array():
 
 	struct gpio_descs *my_gpio_descs = gpiod_get_array(...);
-	gpiod_set_array(my_gpio_descs->ndescs, my_gpio_descs->desc,
-			my_gpio_values);
+	gpiod_set_array_value(my_gpio_descs->ndescs, my_gpio_descs->desc,
+			      my_gpio_values);
 
 It is also possible to set a completely arbitrary array of descriptors. The
 descriptors may be obtained using any combination of gpiod_get() and
diff --git a/Documentation/gpio/gpio-legacy.txt b/Documentation/gpio/gpio-legacy.txt
index 6f83fa965b4b..79ab5648d69b 100644
--- a/Documentation/gpio/gpio-legacy.txt
+++ b/Documentation/gpio/gpio-legacy.txt
@@ -751,9 +751,6 @@ requested using gpio_request():
 	int gpio_export_link(struct device *dev, const char *name,
 		unsigned gpio)
 
-	/* change the polarity of a GPIO node in sysfs */
-	int gpio_sysfs_set_active_low(unsigned gpio, int value);
-
 After a kernel driver requests a GPIO, it may only be made available in
 the sysfs interface by gpio_export().  The driver can control whether the
 signal direction may change.  This helps drivers prevent userspace code
@@ -767,9 +764,3 @@ After the GPIO has been exported, gpio_export_link() allows creating
 symlinks from elsewhere in sysfs to the GPIO sysfs node.  Drivers can
 use this to provide the interface under their own device in sysfs with
 a descriptive name.
-
-Drivers can use gpio_sysfs_set_active_low() to hide GPIO line polarity
-differences between boards from user space.  This only affects the
-sysfs interface.  Polarity change can be done both before and after
-gpio_export(), and previously enabled poll(2) support for either
-rising or falling edge will be reconfigured to follow this setting.
diff --git a/Documentation/gpio/sysfs.txt b/Documentation/gpio/sysfs.txt
index c2c3a97f8ff7..535b6a8a7a7c 100644
--- a/Documentation/gpio/sysfs.txt
+++ b/Documentation/gpio/sysfs.txt
@@ -132,9 +132,6 @@ requested using gpio_request():
 	int gpiod_export_link(struct device *dev, const char *name,
 		      struct gpio_desc *desc);
 
-	/* change the polarity of a GPIO node in sysfs */
-	int gpiod_sysfs_set_active_low(struct gpio_desc *desc, int value);
-
 After a kernel driver requests a GPIO, it may only be made available in
 the sysfs interface by gpiod_export(). The driver can control whether the
 signal direction may change. This helps drivers prevent userspace code
@@ -148,8 +145,3 @@ After the GPIO has been exported, gpiod_export_link() allows creating
 symlinks from elsewhere in sysfs to the GPIO sysfs node. Drivers can
 use this to provide the interface under their own device in sysfs with
 a descriptive name.
-
-Drivers can use gpiod_sysfs_set_active_low() to hide GPIO line polarity
-differences between boards from user space. Polarity change can be done both
-before and after gpiod_export(), and previously enabled poll(2) support for
-either rising or falling edge will be reconfigured to follow this setting.
diff --git a/Documentation/hwmon/ntc_thermistor b/Documentation/hwmon/ntc_thermistor
index c5e05e2900a3..1d4cc847c6fe 100644
--- a/Documentation/hwmon/ntc_thermistor
+++ b/Documentation/hwmon/ntc_thermistor
@@ -2,8 +2,10 @@ Kernel driver ntc_thermistor
 =================
 
 Supported thermistors from Murata:
-* Murata NTC Thermistors NCP15WB473, NCP18WB473, NCP21WB473, NCP03WB473, NCP15WL333
-  Prefixes: 'ncp15wb473', 'ncp18wb473', 'ncp21wb473', 'ncp03wb473', 'ncp15wl333'
+* Murata NTC Thermistors NCP15WB473, NCP18WB473, NCP21WB473, NCP03WB473,
+  NCP15WL333, NCP03WF104
+  Prefixes: 'ncp15wb473', 'ncp18wb473', 'ncp21wb473', 'ncp03wb473',
+  'ncp15wl333', 'ncp03wf104'
   Datasheet: Publicly available at Murata
 
 Supported thermistors from EPCOS:
diff --git a/Documentation/hwmon/tc74 b/Documentation/hwmon/tc74
new file mode 100644
index 000000000000..43027aad5f8e
--- /dev/null
+++ b/Documentation/hwmon/tc74
@@ -0,0 +1,20 @@
+Kernel driver tc74
+====================
+
+Supported chips:
+   * Microchip TC74
+     Prefix: 'tc74'
+     Datasheet: Publicly available at Microchip website.
+
+Description
+-----------
+
+Driver supports the above part.
+
+The tc74 has an 8-bit sensor, with 1 degree centigrade resolution
+and +- 2 degrees centigrade accuracy.
+
+Notes
+-----
+
+Currently entering low power standby mode is not supported.
diff --git a/Documentation/i2c/slave-interface b/Documentation/i2c/slave-interface
index 389bb5d61854..b228ca54bcf4 100644
--- a/Documentation/i2c/slave-interface
+++ b/Documentation/i2c/slave-interface
@@ -31,10 +31,10 @@ User manual
 ===========
 
 I2C slave backends behave like standard I2C clients. So, you can instantiate
-them like described in the document 'instantiating-devices'. A quick example
-for instantiating the slave-eeprom driver from userspace:
+them as described in the document 'instantiating-devices'. A quick example for
+instantiating the slave-eeprom driver from userspace at address 0x64 on bus 1:
 
-  # echo 0-0064 > /sys/bus/i2c/drivers/i2c-slave-eeprom/bind
+  # echo slave-24c02 0x64 > /sys/bus/i2c/devices/i2c-1/new_device
 
 Each backend should come with separate documentation to describe its specific
 behaviour and setup.
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 10f879221821..ae4474940fe2 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -746,6 +746,12 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 	cpuidle.off=1	[CPU_IDLE]
 			disable the cpuidle sub-system
 
+	cpu_init_udelay=N
+			[X86] Delay for N microsec between assert and de-assert
+			of APIC INIT to start processors.  This delay occurs
+			on every CPU online, such as boot, and resume from suspend.
+			Default: 10000
+
 	cpcihp_generic=	[HW,PCI] Generic port I/O CompactPCI driver
 			Format:
 			<first_slot>,<last_slot>,<port>,<enum_bit>[,<debug>]
@@ -937,6 +943,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			Enable debug messages at boot time.  See
 			Documentation/dynamic-debug-howto.txt for details.
 
+	nompx		[X86] Disables Intel Memory Protection Extensions.
+			See Documentation/x86/intel_mpx.txt for more
+			information about the feature.
+
 	eagerfpu=	[X86]
 			on	enable eager fpu restore
 			off	disable eager fpu restore
@@ -2998,11 +3008,34 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			Set maximum number of finished RCU callbacks to
 			process in one batch.
 
+	rcutree.dump_tree=	[KNL]
+			Dump the structure of the rcu_node combining tree
+			out at early boot.  This is used for diagnostic
+			purposes, to verify correct tree setup.
+
+	rcutree.gp_cleanup_delay=	[KNL]
+			Set the number of jiffies to delay each step of
+			RCU grace-period cleanup.  This only has effect
+			when CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP is set.
+
 	rcutree.gp_init_delay=	[KNL]
 			Set the number of jiffies to delay each step of
 			RCU grace-period initialization.  This only has
-			effect when CONFIG_RCU_TORTURE_TEST_SLOW_INIT is
-			set.
+			effect when CONFIG_RCU_TORTURE_TEST_SLOW_INIT
+			is set.
+
+	rcutree.gp_preinit_delay=	[KNL]
+			Set the number of jiffies to delay each step of
+			RCU grace-period pre-initialization, that is,
+			the propagation of recent CPU-hotplug changes up
+			the rcu_node combining tree.  This only has effect
+			when CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT is set.
+
+	rcutree.rcu_fanout_exact= [KNL]
+			Disable autobalancing of the rcu_node combining
+			tree.  This is used by rcutorture, and might
+			possibly be useful for architectures having high
+			cache-to-cache transfer latencies.
 
 	rcutree.rcu_fanout_leaf= [KNL]
 			Increase the number of CPUs assigned to each
@@ -3107,7 +3140,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			test, hence the "fake".
 
 	rcutorture.nreaders= [KNL]
-			Set number of RCU readers.
+			Set number of RCU readers.  The value -1 selects
+			N-1, where N is the number of CPUs.  A value
+			"n" less than -1 selects N-n-2, where N is again
+			the number of CPUs.  For example, -2 selects N
+			(the number of CPUs), -3 selects N+1, and so on.
 
 	rcutorture.object_debug= [KNL]
 			Enable debug-object double-call_rcu() testing.
diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index f95746189b5d..13feb697271f 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -617,16 +617,16 @@ case what's actually required is:
 However, stores are not speculated.  This means that ordering -is- provided
 for load-store control dependencies, as in the following example:
 
-	q = ACCESS_ONCE(a);
+	q = READ_ONCE_CTRL(a);
 	if (q) {
 		ACCESS_ONCE(b) = p;
 	}
 
-Control dependencies pair normally with other types of barriers.
-That said, please note that ACCESS_ONCE() is not optional!  Without the
-ACCESS_ONCE(), might combine the load from 'a' with other loads from
-'a', and the store to 'b' with other stores to 'b', with possible highly
-counterintuitive effects on ordering.
+Control dependencies pair normally with other types of barriers.  That
+said, please note that READ_ONCE_CTRL() is not optional!  Without the
+READ_ONCE_CTRL(), the compiler might combine the load from 'a' with
+other loads from 'a', and the store to 'b' with other stores to 'b',
+with possible highly counterintuitive effects on ordering.
 
 Worse yet, if the compiler is able to prove (say) that the value of
 variable 'a' is always non-zero, it would be well within its rights
@@ -636,12 +636,15 @@ as follows:
 	q = a;
 	b = p;  /* BUG: Compiler and CPU can both reorder!!! */
 
-So don't leave out the ACCESS_ONCE().
+Finally, the READ_ONCE_CTRL() includes an smp_read_barrier_depends()
+that DEC Alpha needs in order to respect control depedencies.
+
+So don't leave out the READ_ONCE_CTRL().
 
 It is tempting to try to enforce ordering on identical stores on both
 branches of the "if" statement as follows:
 
-	q = ACCESS_ONCE(a);
+	q = READ_ONCE_CTRL(a);
 	if (q) {
 		barrier();
 		ACCESS_ONCE(b) = p;
@@ -655,7 +658,7 @@ branches of the "if" statement as follows:
 Unfortunately, current compilers will transform this as follows at high
 optimization levels:
 
-	q = ACCESS_ONCE(a);
+	q = READ_ONCE_CTRL(a);
 	barrier();
 	ACCESS_ONCE(b) = p;  /* BUG: No ordering vs. load from a!!! */
 	if (q) {
@@ -685,7 +688,7 @@ memory barriers, for example, smp_store_release():
 In contrast, without explicit memory barriers, two-legged-if control
 ordering is guaranteed only when the stores differ, for example:
 
-	q = ACCESS_ONCE(a);
+	q = READ_ONCE_CTRL(a);
 	if (q) {
 		ACCESS_ONCE(b) = p;
 		do_something();
@@ -694,14 +697,14 @@ ordering is guaranteed only when the stores differ, for example:
 		do_something_else();
 	}
 
-The initial ACCESS_ONCE() is still required to prevent the compiler from
-proving the value of 'a'.
+The initial READ_ONCE_CTRL() is still required to prevent the compiler
+from proving the value of 'a'.
 
 In addition, you need to be careful what you do with the local variable 'q',
 otherwise the compiler might be able to guess the value and again remove
 the needed conditional.  For example:
 
-	q = ACCESS_ONCE(a);
+	q = READ_ONCE_CTRL(a);
 	if (q % MAX) {
 		ACCESS_ONCE(b) = p;
 		do_something();
@@ -714,7 +717,7 @@ If MAX is defined to be 1, then the compiler knows that (q % MAX) is
 equal to zero, in which case the compiler is within its rights to
 transform the above code into the following:
 
-	q = ACCESS_ONCE(a);
+	q = READ_ONCE_CTRL(a);
 	ACCESS_ONCE(b) = p;
 	do_something_else();
 
@@ -725,7 +728,7 @@ is gone, and the barrier won't bring it back.  Therefore, if you are
 relying on this ordering, you should make sure that MAX is greater than
 one, perhaps as follows:
 
-	q = ACCESS_ONCE(a);
+	q = READ_ONCE_CTRL(a);
 	BUILD_BUG_ON(MAX <= 1); /* Order load from a with store to b. */
 	if (q % MAX) {
 		ACCESS_ONCE(b) = p;
@@ -742,14 +745,15 @@ of the 'if' statement.
 You must also be careful not to rely too much on boolean short-circuit
 evaluation.  Consider this example:
 
-	q = ACCESS_ONCE(a);
+	q = READ_ONCE_CTRL(a);
 	if (a || 1 > 0)
 		ACCESS_ONCE(b) = 1;
 
-Because the second condition is always true, the compiler can transform
-this example as following, defeating control dependency:
+Because the first condition cannot fault and the second condition is
+always true, the compiler can transform this example as following,
+defeating control dependency:
 
-	q = ACCESS_ONCE(a);
+	q = READ_ONCE_CTRL(a);
 	ACCESS_ONCE(b) = 1;
 
 This example underscores the need to ensure that the compiler cannot
@@ -762,8 +766,8 @@ demonstrated by two related examples, with the initial values of
 x and y both being zero:
 
 	CPU 0                     CPU 1
-	=====================     =====================
-	r1 = ACCESS_ONCE(x);      r2 = ACCESS_ONCE(y);
+	=======================   =======================
+	r1 = READ_ONCE_CTRL(x);   r2 = READ_ONCE_CTRL(y);
 	if (r1 > 0)               if (r2 > 0)
 	  ACCESS_ONCE(y) = 1;       ACCESS_ONCE(x) = 1;
 
@@ -783,7 +787,8 @@ But because control dependencies do -not- provide transitivity, the above
 assertion can fail after the combined three-CPU example completes.  If you
 need the three-CPU example to provide ordering, you will need smp_mb()
 between the loads and stores in the CPU 0 and CPU 1 code fragments,
-that is, just before or just after the "if" statements.
+that is, just before or just after the "if" statements.  Furthermore,
+the original two-CPU example is very fragile and should be avoided.
 
 These two examples are the LB and WWC litmus tests from this paper:
 http://www.cl.cam.ac.uk/users/pes20/ppc-supplemental/test6.pdf and this
@@ -791,6 +796,12 @@ site: https://www.cl.cam.ac.uk/~pes20/ppcmem/index.html.
 
 In summary:
 
+  (*) Control dependencies must be headed by READ_ONCE_CTRL().
+      Or, as a much less preferable alternative, interpose
+      be headed by READ_ONCE() or an ACCESS_ONCE() read and must
+      have smp_read_barrier_depends() between this read and the
+      control-dependent write.
+
   (*) Control dependencies can order prior loads against later stores.
       However, they do -not- guarantee any other sort of ordering:
       Not prior loads against later loads, nor prior stores against
@@ -1662,7 +1673,7 @@ CPU from reordering them.
 
 There are some more advanced barrier functions:
 
- (*) set_mb(var, value)
+ (*) smp_store_mb(var, value)
 
      This assigns the value to the variable and then inserts a full memory
      barrier after it, depending on the function.  It isn't guaranteed to
@@ -1784,10 +1795,9 @@ for each construct.  These operations all imply certain barriers:
 
      Memory operations issued before the ACQUIRE may be completed after
      the ACQUIRE operation has completed.  An smp_mb__before_spinlock(),
-     combined with a following ACQUIRE, orders prior loads against
-     subsequent loads and stores and also orders prior stores against
-     subsequent stores.  Note that this is weaker than smp_mb()!  The
-     smp_mb__before_spinlock() primitive is free on many architectures.
+     combined with a following ACQUIRE, orders prior stores against
+     subsequent loads and stores. Note that this is weaker than smp_mb()!
+     The smp_mb__before_spinlock() primitive is free on many architectures.
 
  (2) RELEASE operation implication:
 
@@ -1975,7 +1985,7 @@ after it has altered the task state:
 	CPU 1
 	===============================
 	set_current_state();
-	  set_mb();
+	  smp_store_mb();
 	    STORE current->state
 	    <general barrier>
 	LOAD event_indicated
@@ -2016,7 +2026,7 @@ between the STORE to indicate the event and the STORE to set TASK_RUNNING:
 	CPU 1				CPU 2
 	===============================	===============================
 	set_current_state();		STORE event_indicated
-	  set_mb();			wake_up();
+	  smp_store_mb();		wake_up();
 	    STORE current->state	  <write barrier>
 	    <general barrier>		  STORE current->state
 	LOAD event_indicated
diff --git a/Documentation/preempt-locking.txt b/Documentation/preempt-locking.txt
index 57883ca2498b..e89ce6624af2 100644
--- a/Documentation/preempt-locking.txt
+++ b/Documentation/preempt-locking.txt
@@ -48,7 +48,7 @@ preemption must be disabled around such regions.
 
 Note, some FPU functions are already explicitly preempt safe.  For example,
 kernel_fpu_begin and kernel_fpu_end will disable and enable preemption.
-However, math_state_restore must be called with preemption disabled.
+However, fpu__restore() must be called with preemption disabled.
 
 
 RULE #3: Lock acquire and release must be performed by same task
diff --git a/Documentation/scheduler/sched-deadline.txt b/Documentation/scheduler/sched-deadline.txt
index 21461a0441c1..e114513a2731 100644
--- a/Documentation/scheduler/sched-deadline.txt
+++ b/Documentation/scheduler/sched-deadline.txt
@@ -8,6 +8,10 @@ CONTENTS
  1. Overview
  2. Scheduling algorithm
  3. Scheduling Real-Time Tasks
+   3.1 Definitions
+   3.2 Schedulability Analysis for Uniprocessor Systems
+   3.3 Schedulability Analysis for Multiprocessor Systems
+   3.4 Relationship with SCHED_DEADLINE Parameters
  4. Bandwidth management
    4.1 System-wide settings
    4.2 Task interface
@@ -43,7 +47,7 @@ CONTENTS
  "deadline", to schedule tasks. A SCHED_DEADLINE task should receive
  "runtime" microseconds of execution time every "period" microseconds, and
  these "runtime" microseconds are available within "deadline" microseconds
- from the beginning of the period.  In order to implement this behaviour,
+ from the beginning of the period.  In order to implement this behavior,
  every time the task wakes up, the scheduler computes a "scheduling deadline"
  consistent with the guarantee (using the CBS[2,3] algorithm). Tasks are then
  scheduled using EDF[1] on these scheduling deadlines (the task with the
@@ -52,7 +56,7 @@ CONTENTS
  "admission control" strategy (see Section "4. Bandwidth management") is used
  (clearly, if the system is overloaded this guarantee cannot be respected).
 
- Summing up, the CBS[2,3] algorithms assigns scheduling deadlines to tasks so
+ Summing up, the CBS[2,3] algorithm assigns scheduling deadlines to tasks so
  that each task runs for at most its runtime every period, avoiding any
  interference between different tasks (bandwidth isolation), while the EDF[1]
  algorithm selects the task with the earliest scheduling deadline as the one
@@ -63,7 +67,7 @@ CONTENTS
  In more details, the CBS algorithm assigns scheduling deadlines to
  tasks in the following way:
 
-  - Each SCHED_DEADLINE task is characterised by the "runtime",
+  - Each SCHED_DEADLINE task is characterized by the "runtime",
     "deadline", and "period" parameters;
 
   - The state of the task is described by a "scheduling deadline", and
@@ -78,7 +82,7 @@ CONTENTS
 
     then, if the scheduling deadline is smaller than the current time, or
     this condition is verified, the scheduling deadline and the
-    remaining runtime are re-initialised as
+    remaining runtime are re-initialized as
 
          scheduling deadline = current time + deadline
          remaining runtime = runtime
@@ -126,31 +130,37 @@ CONTENTS
  suited for periodic or sporadic real-time tasks that need guarantees on their
  timing behavior, e.g., multimedia, streaming, control applications, etc.
 
+3.1 Definitions
+------------------------
+
  A typical real-time task is composed of a repetition of computation phases
  (task instances, or jobs) which are activated on a periodic or sporadic
  fashion.
- Each job J_j (where J_j is the j^th job of the task) is characterised by an
+ Each job J_j (where J_j is the j^th job of the task) is characterized by an
  arrival time r_j (the time when the job starts), an amount of computation
  time c_j needed to finish the job, and a job absolute deadline d_j, which
  is the time within which the job should be finished. The maximum execution
- time max_j{c_j} is called "Worst Case Execution Time" (WCET) for the task.
+ time max{c_j} is called "Worst Case Execution Time" (WCET) for the task.
  A real-time task can be periodic with period P if r_{j+1} = r_j + P, or
  sporadic with minimum inter-arrival time P is r_{j+1} >= r_j + P. Finally,
  d_j = r_j + D, where D is the task's relative deadline.
- The utilisation of a real-time task is defined as the ratio between its
+ Summing up, a real-time task can be described as
+	Task = (WCET, D, P)
+
+ The utilization of a real-time task is defined as the ratio between its
  WCET and its period (or minimum inter-arrival time), and represents
  the fraction of CPU time needed to execute the task.
 
- If the total utilisation sum_i(WCET_i/P_i) is larger than M (with M equal
+ If the total utilization U=sum(WCET_i/P_i) is larger than M (with M equal
  to the number of CPUs), then the scheduler is unable to respect all the
  deadlines.
- Note that total utilisation is defined as the sum of the utilisations
+ Note that total utilization is defined as the sum of the utilizations
  WCET_i/P_i over all the real-time tasks in the system. When considering
  multiple real-time tasks, the parameters of the i-th task are indicated
  with the "_i" suffix.
- Moreover, if the total utilisation is larger than M, then we risk starving
+ Moreover, if the total utilization is larger than M, then we risk starving
  non- real-time tasks by real-time tasks.
- If, instead, the total utilisation is smaller than M, then non real-time
+ If, instead, the total utilization is smaller than M, then non real-time
  tasks will not be starved and the system might be able to respect all the
  deadlines.
  As a matter of fact, in this case it is possible to provide an upper bound
@@ -159,38 +169,119 @@ CONTENTS
  More precisely, it can be proven that using a global EDF scheduler the
  maximum tardiness of each task is smaller or equal than
 	((M − 1) · WCET_max − WCET_min)/(M − (M − 2) · U_max) + WCET_max
- where WCET_max = max_i{WCET_i} is the maximum WCET, WCET_min=min_i{WCET_i}
- is the minimum WCET, and U_max = max_i{WCET_i/P_i} is the maximum utilisation.
+ where WCET_max = max{WCET_i} is the maximum WCET, WCET_min=min{WCET_i}
+ is the minimum WCET, and U_max = max{WCET_i/P_i} is the maximum
+ utilization[12].
+
+3.2 Schedulability Analysis for Uniprocessor Systems
+------------------------
 
  If M=1 (uniprocessor system), or in case of partitioned scheduling (each
  real-time task is statically assigned to one and only one CPU), it is
  possible to formally check if all the deadlines are respected.
  If D_i = P_i for all tasks, then EDF is able to respect all the deadlines
- of all the tasks executing on a CPU if and only if the total utilisation
+ of all the tasks executing on a CPU if and only if the total utilization
  of the tasks running on such a CPU is smaller or equal than 1.
  If D_i != P_i for some task, then it is possible to define the density of
- a task as C_i/min{D_i,T_i}, and EDF is able to respect all the deadlines
- of all the tasks running on a CPU if the sum sum_i C_i/min{D_i,T_i} of the
- densities of the tasks running on such a CPU is smaller or equal than 1
- (notice that this condition is only sufficient, and not necessary).
+ a task as WCET_i/min{D_i,P_i}, and EDF is able to respect all the deadlines
+ of all the tasks running on a CPU if the sum of the densities of the tasks
+ running on such a CPU is smaller or equal than 1:
+	sum(WCET_i / min{D_i, P_i}) <= 1
+ It is important to notice that this condition is only sufficient, and not
+ necessary: there are task sets that are schedulable, but do not respect the
+ condition. For example, consider the task set {Task_1,Task_2} composed by
+ Task_1=(50ms,50ms,100ms) and Task_2=(10ms,100ms,100ms).
+ EDF is clearly able to schedule the two tasks without missing any deadline
+ (Task_1 is scheduled as soon as it is released, and finishes just in time
+ to respect its deadline; Task_2 is scheduled immediately after Task_1, hence
+ its response time cannot be larger than 50ms + 10ms = 60ms) even if
+	50 / min{50,100} + 10 / min{100, 100} = 50 / 50 + 10 / 100 = 1.1
+ Of course it is possible to test the exact schedulability of tasks with
+ D_i != P_i (checking a condition that is both sufficient and necessary),
+ but this cannot be done by comparing the total utilization or density with
+ a constant. Instead, the so called "processor demand" approach can be used,
+ computing the total amount of CPU time h(t) needed by all the tasks to
+ respect all of their deadlines in a time interval of size t, and comparing
+ such a time with the interval size t. If h(t) is smaller than t (that is,
+ the amount of time needed by the tasks in a time interval of size t is
+ smaller than the size of the interval) for all the possible values of t, then
+ EDF is able to schedule the tasks respecting all of their deadlines. Since
+ performing this check for all possible values of t is impossible, it has been
+ proven[4,5,6] that it is sufficient to perform the test for values of t
+ between 0 and a maximum value L. The cited papers contain all of the
+ mathematical details and explain how to compute h(t) and L.
+ In any case, this kind of analysis is too complex as well as too
+ time-consuming to be performed on-line. Hence, as explained in Section
+ 4 Linux uses an admission test based on the tasks' utilizations.
+
+3.3 Schedulability Analysis for Multiprocessor Systems
+------------------------
 
  On multiprocessor systems with global EDF scheduling (non partitioned
  systems), a sufficient test for schedulability can not be based on the
- utilisations (it can be shown that task sets with utilisations slightly
- larger than 1 can miss deadlines regardless of the number of CPUs M).
- However, as previously stated, enforcing that the total utilisation is smaller
- than M is enough to guarantee that non real-time tasks are not starved and
- that the tardiness of real-time tasks has an upper bound.
+ utilizations or densities: it can be shown that even if D_i = P_i task
+ sets with utilizations slightly larger than 1 can miss deadlines regardless
+ of the number of CPUs.
+
+ Consider a set {Task_1,...Task_{M+1}} of M+1 tasks on a system with M
+ CPUs, with the first task Task_1=(P,P,P) having period, relative deadline
+ and WCET equal to P. The remaining M tasks Task_i=(e,P-1,P-1) have an
+ arbitrarily small worst case execution time (indicated as "e" here) and a
+ period smaller than the one of the first task. Hence, if all the tasks
+ activate at the same time t, global EDF schedules these M tasks first
+ (because their absolute deadlines are equal to t + P - 1, hence they are
+ smaller than the absolute deadline of Task_1, which is t + P). As a
+ result, Task_1 can be scheduled only at time t + e, and will finish at
+ time t + e + P, after its absolute deadline. The total utilization of the
+ task set is U = M · e / (P - 1) + P / P = M · e / (P - 1) + 1, and for small
+ values of e this can become very close to 1. This is known as "Dhall's
+ effect"[7]. Note: the example in the original paper by Dhall has been
+ slightly simplified here (for example, Dhall more correctly computed
+ lim_{e->0}U).
+
+ More complex schedulability tests for global EDF have been developed in
+ real-time literature[8,9], but they are not based on a simple comparison
+ between total utilization (or density) and a fixed constant. If all tasks
+ have D_i = P_i, a sufficient schedulability condition can be expressed in
+ a simple way:
+	sum(WCET_i / P_i) <= M - (M - 1) · U_max
+ where U_max = max{WCET_i / P_i}[10]. Notice that for U_max = 1,
+ M - (M - 1) · U_max becomes M - M + 1 = 1 and this schedulability condition
+ just confirms the Dhall's effect. A more complete survey of the literature
+ about schedulability tests for multi-processor real-time scheduling can be
+ found in [11].
+
+ As seen, enforcing that the total utilization is smaller than M does not
+ guarantee that global EDF schedules the tasks without missing any deadline
+ (in other words, global EDF is not an optimal scheduling algorithm). However,
+ a total utilization smaller than M is enough to guarantee that non real-time
+ tasks are not starved and that the tardiness of real-time tasks has an upper
+ bound[12] (as previously noted). Different bounds on the maximum tardiness
+ experienced by real-time tasks have been developed in various papers[13,14],
+ but the theoretical result that is important for SCHED_DEADLINE is that if
+ the total utilization is smaller or equal than M then the response times of
+ the tasks are limited.
+
+3.4 Relationship with SCHED_DEADLINE Parameters
+------------------------
 
- SCHED_DEADLINE can be used to schedule real-time tasks guaranteeing that
- the jobs' deadlines of a task are respected. In order to do this, a task
- must be scheduled by setting:
+ Finally, it is important to understand the relationship between the
+ SCHED_DEADLINE scheduling parameters described in Section 2 (runtime,
+ deadline and period) and the real-time task parameters (WCET, D, P)
+ described in this section. Note that the tasks' temporal constraints are
+ represented by its absolute deadlines d_j = r_j + D described above, while
+ SCHED_DEADLINE schedules the tasks according to scheduling deadlines (see
+ Section 2).
+ If an admission test is used to guarantee that the scheduling deadlines
+ are respected, then SCHED_DEADLINE can be used to schedule real-time tasks
+ guaranteeing that all the jobs' deadlines of a task are respected.
+ In order to do this, a task must be scheduled by setting:
 
   - runtime >= WCET
   - deadline = D
   - period <= P
 
- IOW, if runtime >= WCET and if period is >= P, then the scheduling deadlines
+ IOW, if runtime >= WCET and if period is <= P, then the scheduling deadlines
  and the absolute deadlines (d_j) coincide, so a proper admission control
  allows to respect the jobs' absolute deadlines for this task (this is what is
  called "hard schedulability property" and is an extension of Lemma 1 of [2]).
@@ -206,6 +297,39 @@ CONTENTS
       Symposium, 1998. http://retis.sssup.it/~giorgio/paps/1998/rtss98-cbs.pdf
   3 - L. Abeni. Server Mechanisms for Multimedia Applications. ReTiS Lab
       Technical Report. http://disi.unitn.it/~abeni/tr-98-01.pdf
+  4 - J. Y. Leung and M.L. Merril. A Note on Preemptive Scheduling of
+      Periodic, Real-Time Tasks. Information Processing Letters, vol. 11,
+      no. 3, pp. 115-118, 1980.
+  5 - S. K. Baruah, A. K. Mok and L. E. Rosier. Preemptively Scheduling
+      Hard-Real-Time Sporadic Tasks on One Processor. Proceedings of the
+      11th IEEE Real-time Systems Symposium, 1990.
+  6 - S. K. Baruah, L. E. Rosier and R. R. Howell. Algorithms and Complexity
+      Concerning the Preemptive Scheduling of Periodic Real-Time tasks on
+      One Processor. Real-Time Systems Journal, vol. 4, no. 2, pp 301-324,
+      1990.
+  7 - S. J. Dhall and C. L. Liu. On a real-time scheduling problem. Operations
+      research, vol. 26, no. 1, pp 127-140, 1978.
+  8 - T. Baker. Multiprocessor EDF and Deadline Monotonic Schedulability
+      Analysis. Proceedings of the 24th IEEE Real-Time Systems Symposium, 2003.
+  9 - T. Baker. An Analysis of EDF Schedulability on a Multiprocessor.
+      IEEE Transactions on Parallel and Distributed Systems, vol. 16, no. 8,
+      pp 760-768, 2005.
+  10 - J. Goossens, S. Funk and S. Baruah, Priority-Driven Scheduling of
+       Periodic Task Systems on Multiprocessors. Real-Time Systems Journal,
+       vol. 25, no. 2–3, pp. 187–205, 2003.
+  11 - R. Davis and A. Burns. A Survey of Hard Real-Time Scheduling for
+       Multiprocessor Systems. ACM Computing Surveys, vol. 43, no. 4, 2011.
+       http://www-users.cs.york.ac.uk/~robdavis/papers/MPSurveyv5.0.pdf
+  12 - U. C. Devi and J. H. Anderson. Tardiness Bounds under Global EDF
+       Scheduling on a Multiprocessor. Real-Time Systems Journal, vol. 32,
+       no. 2, pp 133-189, 2008.
+  13 - P. Valente and G. Lipari. An Upper Bound to the Lateness of Soft
+       Real-Time Tasks Scheduled by EDF on Multiprocessors. Proceedings of
+       the 26th IEEE Real-Time Systems Symposium, 2005.
+  14 - J. Erickson, U. Devi and S. Baruah. Improved tardiness bounds for
+       Global EDF. Proceedings of the 22nd Euromicro Conference on
+       Real-Time Systems, 2010.
+
 
 4. Bandwidth management
 =======================
@@ -218,10 +342,10 @@ CONTENTS
  no guarantee can be given on the actual scheduling of the -deadline tasks.
 
  As already stated in Section 3, a necessary condition to be respected to
- correctly schedule a set of real-time tasks is that the total utilisation
+ correctly schedule a set of real-time tasks is that the total utilization
  is smaller than M. When talking about -deadline tasks, this requires that
  the sum of the ratio between runtime and period for all tasks is smaller
- than M. Notice that the ratio runtime/period is equivalent to the utilisation
+ than M. Notice that the ratio runtime/period is equivalent to the utilization
  of a "traditional" real-time task, and is also often referred to as
  "bandwidth".
  The interface used to control the CPU bandwidth that can be allocated
@@ -251,7 +375,7 @@ CONTENTS
  The system wide settings are configured under the /proc virtual file system.
 
  For now the -rt knobs are used for -deadline admission control and the
- -deadline runtime is accounted against the -rt runtime. We realise that this
+ -deadline runtime is accounted against the -rt runtime. We realize that this
  isn't entirely desirable; however, it is better to have a small interface for
  now, and be able to change it easily later. The ideal situation (see 5.) is to
  run -rt tasks from a -deadline server; in which case the -rt bandwidth is a
diff --git a/Documentation/x86/boot.txt b/Documentation/x86/boot.txt
index 88b85899d309..7c1f9fad6674 100644
--- a/Documentation/x86/boot.txt
+++ b/Documentation/x86/boot.txt
@@ -1124,7 +1124,6 @@ The boot loader *must* fill out the following fields in bp,
 
     o hdr.code32_start
     o hdr.cmd_line_ptr
-    o hdr.cmdline_size
     o hdr.ramdisk_image (if applicable)
     o hdr.ramdisk_size  (if applicable)
 
diff --git a/Documentation/x86/entry_64.txt b/Documentation/x86/entry_64.txt
index 9132b86176a3..33884d156125 100644
--- a/Documentation/x86/entry_64.txt
+++ b/Documentation/x86/entry_64.txt
@@ -18,10 +18,10 @@ Some of these entries are:
 
  - system_call: syscall instruction from 64-bit code.
 
- - ia32_syscall: int 0x80 from 32-bit or 64-bit code; compat syscall
+ - entry_INT80_compat: int 0x80 from 32-bit or 64-bit code; compat syscall
    either way.
 
- - ia32_syscall, ia32_sysenter: syscall and sysenter from 32-bit
+ - entry_INT80_compat, ia32_sysenter: syscall and sysenter from 32-bit
    code
 
  - interrupt: An array of entries.  Every IDT vector that doesn't
diff --git a/Documentation/x86/x86_64/kernel-stacks b/Documentation/x86/kernel-stacks
index e3c8a49d1a2f..0f3a6c201943 100644
--- a/Documentation/x86/x86_64/kernel-stacks
+++ b/Documentation/x86/kernel-stacks
@@ -1,3 +1,6 @@
+Kernel stacks on x86-64 bit
+---------------------------
+
 Most of the text from Keith Owens, hacked by AK
 
 x86_64 page size (PAGE_SIZE) is 4K.
@@ -56,13 +59,6 @@ If that assumption is ever broken then the stacks will become corrupt.
 
 The currently assigned IST stacks are :-
 
-* STACKFAULT_STACK.  EXCEPTION_STKSZ (PAGE_SIZE).
-
-  Used for interrupt 12 - Stack Fault Exception (#SS).
-
-  This allows the CPU to recover from invalid stack segments. Rarely
-  happens.
-
 * DOUBLEFAULT_STACK.  EXCEPTION_STKSZ (PAGE_SIZE).
 
   Used for interrupt 8 - Double Fault Exception (#DF).
@@ -99,3 +95,47 @@ The currently assigned IST stacks are :-
   assumptions about the previous state of the kernel stack.
 
 For more details see the Intel IA32 or AMD AMD64 architecture manuals.
+
+
+Printing backtraces on x86
+--------------------------
+
+The question about the '?' preceding function names in an x86 stacktrace
+keeps popping up, here's an indepth explanation. It helps if the reader
+stares at print_context_stack() and the whole machinery in and around
+arch/x86/kernel/dumpstack.c.
+
+Adapted from Ingo's mail, Message-ID: <20150521101614.GA10889@gmail.com>:
+
+We always scan the full kernel stack for return addresses stored on
+the kernel stack(s) [*], from stack top to stack bottom, and print out
+anything that 'looks like' a kernel text address.
+
+If it fits into the frame pointer chain, we print it without a question
+mark, knowing that it's part of the real backtrace.
+
+If the address does not fit into our expected frame pointer chain we
+still print it, but we print a '?'. It can mean two things:
+
+ - either the address is not part of the call chain: it's just stale
+   values on the kernel stack, from earlier function calls. This is
+   the common case.
+
+ - or it is part of the call chain, but the frame pointer was not set
+   up properly within the function, so we don't recognize it.
+
+This way we will always print out the real call chain (plus a few more
+entries), regardless of whether the frame pointer was set up correctly
+or not - but in most cases we'll get the call chain right as well. The
+entries printed are strictly in stack order, so you can deduce more
+information from that as well.
+
+The most important property of this method is that we _never_ lose
+information: we always strive to print _all_ addresses on the stack(s)
+that look like kernel text addresses, so if debug information is wrong,
+we still print out the real call chain as well - just with more question
+marks than ideal.
+
+[*] For things like IRQ and IST stacks, we also scan those stacks, in
+    the right order, and try to cross from one stack into another
+    reconstructing the call chain. This works most of the time.
diff --git a/Documentation/x86/mtrr.txt b/Documentation/x86/mtrr.txt
index cc071dc333c2..860bc3adc223 100644
--- a/Documentation/x86/mtrr.txt
+++ b/Documentation/x86/mtrr.txt
@@ -1,7 +1,19 @@
 MTRR (Memory Type Range Register) control
-3 Jun 1999
-Richard Gooch
-<rgooch@atnf.csiro.au>
+
+Richard Gooch <rgooch@atnf.csiro.au> - 3 Jun 1999
+Luis R. Rodriguez <mcgrof@do-not-panic.com> - April 9, 2015
+
+===============================================================================
+Phasing out MTRR use
+
+MTRR use is replaced on modern x86 hardware with PAT. Over time the only type
+of effective MTRR that is expected to be supported will be for write-combining.
+As MTRR use is phased out device drivers should use arch_phys_wc_add() to make
+MTRR effective on non-PAT systems while a no-op on PAT enabled systems.
+
+For details refer to Documentation/x86/pat.txt.
+
+===============================================================================
 
   On Intel P6 family processors (Pentium Pro, Pentium II and later)
   the Memory Type Range Registers (MTRRs) may be used to control
diff --git a/Documentation/x86/pat.txt b/Documentation/x86/pat.txt
index cf08c9fff3cd..54944c71b819 100644
--- a/Documentation/x86/pat.txt
+++ b/Documentation/x86/pat.txt
@@ -12,7 +12,7 @@ virtual addresses.
 
 PAT allows for different types of memory attributes. The most commonly used
 ones that will be supported at this time are Write-back, Uncached,
-Write-combined and Uncached Minus.
+Write-combined, Write-through and Uncached Minus.
 
 
 PAT APIs
@@ -34,16 +34,23 @@ ioremap                |    --    |    UC-     |       UC-        |
                        |          |            |                  |
 ioremap_cache          |    --    |    WB      |       WB         |
                        |          |            |                  |
+ioremap_uc             |    --    |    UC      |       UC         |
+                       |          |            |                  |
 ioremap_nocache        |    --    |    UC-     |       UC-        |
                        |          |            |                  |
 ioremap_wc             |    --    |    --      |       WC         |
                        |          |            |                  |
+ioremap_wt             |    --    |    --      |       WT         |
+                       |          |            |                  |
 set_memory_uc          |    UC-   |    --      |       --         |
  set_memory_wb         |          |            |                  |
                        |          |            |                  |
 set_memory_wc          |    WC    |    --      |       --         |
  set_memory_wb         |          |            |                  |
                        |          |            |                  |
+set_memory_wt          |    WT    |    --      |       --         |
+ set_memory_wb         |          |            |                  |
+                       |          |            |                  |
 pci sysfs resource     |    --    |    --      |       UC-        |
                        |          |            |                  |
 pci sysfs resource_wc  |    --    |    --      |       WC         |
@@ -102,7 +109,38 @@ wants to export a RAM region, it has to do set_memory_uc() or set_memory_wc()
 as step 0 above and also track the usage of those pages and use set_memory_wb()
 before the page is freed to free pool.
 
-
+MTRR effects on PAT / non-PAT systems
+-------------------------------------
+
+The following table provides the effects of using write-combining MTRRs when
+using ioremap*() calls on x86 for both non-PAT and PAT systems. Ideally
+mtrr_add() usage will be phased out in favor of arch_phys_wc_add() which will
+be a no-op on PAT enabled systems. The region over which a arch_phys_wc_add()
+is made, should already have been ioremapped with WC attributes or PAT entries,
+this can be done by using ioremap_wc() / set_memory_wc().  Devices which
+combine areas of IO memory desired to remain uncacheable with areas where
+write-combining is desirable should consider use of ioremap_uc() followed by
+set_memory_wc() to white-list effective write-combined areas.  Such use is
+nevertheless discouraged as the effective memory type is considered
+implementation defined, yet this strategy can be used as last resort on devices
+with size-constrained regions where otherwise MTRR write-combining would
+otherwise not be effective.
+
+----------------------------------------------------------------------
+MTRR Non-PAT   PAT    Linux ioremap value        Effective memory type
+----------------------------------------------------------------------
+                                                  Non-PAT |  PAT
+     PAT
+     |PCD
+     ||PWT
+     |||
+WC   000      WB      _PAGE_CACHE_MODE_WB            WC   |   WC
+WC   001      WC      _PAGE_CACHE_MODE_WC            WC*  |   WC
+WC   010      UC-     _PAGE_CACHE_MODE_UC_MINUS      WC*  |   UC
+WC   011      UC      _PAGE_CACHE_MODE_UC            UC   |   UC
+----------------------------------------------------------------------
+
+(*) denotes implementation defined and is discouraged
 
 Notes:
 
@@ -115,8 +153,8 @@ can be more restrictive, in case of any existing aliasing for that address.
 For example: If there is an existing uncached mapping, a new ioremap_wc can
 return uncached mapping in place of write-combine requested.
 
-set_memory_[uc|wc] and set_memory_wb should be used in pairs, where driver will
-first make a region uc or wc and switch it back to wb after use.
+set_memory_[uc|wc|wt] and set_memory_wb should be used in pairs, where driver
+will first make a region uc, wc or wt and switch it back to wb after use.
 
 Over time writes to /proc/mtrr will be deprecated in favor of using PAT based
 interfaces. Users writing to /proc/mtrr are suggested to use above interfaces.
@@ -124,7 +162,7 @@ interfaces. Users writing to /proc/mtrr are suggested to use above interfaces.
 Drivers should use ioremap_[uc|wc] to access PCI BARs with [uc|wc] access
 types.
 
-Drivers should use set_memory_[uc|wc] to set access type for RAM ranges.
+Drivers should use set_memory_[uc|wc|wt] to set access type for RAM ranges.
 
 
 PAT debugging
diff --git a/Documentation/x86/x86_64/boot-options.txt b/Documentation/x86/x86_64/boot-options.txt
index 5223479291a2..68ed3114c363 100644
--- a/Documentation/x86/x86_64/boot-options.txt
+++ b/Documentation/x86/x86_64/boot-options.txt
@@ -31,6 +31,9 @@ Machine check
 		(e.g. BIOS or hardware monitoring applications), conflicting
 		with OS's error handling, and you cannot deactivate the agent,
 		then this option will be a help.
+   mce=no_lmce
+		Do not opt-in to Local MCE delivery. Use legacy method
+		to broadcast MCEs.
    mce=bootlog
 		Enable logging of machine checks left over from booting.
 		Disabled by default on AMD because some BIOS leave bogus ones.
diff --git a/Documentation/zh_CN/gpio.txt b/Documentation/zh_CN/gpio.txt
index d5b8f01833f4..bce972521065 100644
--- a/Documentation/zh_CN/gpio.txt
+++ b/Documentation/zh_CN/gpio.txt
@@ -638,9 +638,6 @@ GPIO 控制器的路径类似 /sys/class/gpio/gpiochip42/ (对于从#42 GPIO
 	int gpio_export_link(struct device *dev, const char *name,
 		unsigned gpio)
 
-	/* 改变 sysfs 中的一个 GPIO 节点的极性 */
-	int gpio_sysfs_set_active_low(unsigned gpio, int value);
-
 在一个内核驱动申请一个 GPIO 之后，它可以通过 gpio_export()使其在 sysfs
 接口中可见。该驱动可以控制信号方向是否可修改。这有助于防止用户空间代码无意间
 破坏重要的系统状态。
@@ -651,8 +648,3 @@ GPIO 控制器的路径类似 /sys/class/gpio/gpiochip42/ (对于从#42 GPIO
 在 GPIO 被导出之后，gpio_export_link()允许在 sysfs 文件系统的任何地方
 创建一个到这个 GPIO sysfs 节点的符号链接。这样驱动就可以通过一个描述性的
 名字，在 sysfs 中他们所拥有的设备下提供一个(到这个 GPIO sysfs 节点的)接口。
-
-驱动可以使用 gpio_sysfs_set_active_low() 来在用户空间隐藏电路板之间
-GPIO 线的极性差异。这个仅对 sysfs 接口起作用。极性的改变可以在 gpio_export()
-前后进行,且之前使能的轮询操作(poll(2))支持(上升或下降沿)将会被重新配置来遵循
-这个设置。
diff --git a/Kbuild b/Kbuild
index 6f0d82a9245d..df99a5f53beb 100644
--- a/Kbuild
+++ b/Kbuild
@@ -2,8 +2,9 @@
 # Kbuild for top-level directory of the kernel
 # This file takes care of the following:
 # 1) Generate bounds.h
-# 2) Generate asm-offsets.h (may need bounds.h)
-# 3) Check for missing system calls
+# 2) Generate timeconst.h
+# 3) Generate asm-offsets.h (may need bounds.h and timeconst.h)
+# 4) Check for missing system calls
 
 # Default sed regexp - multiline due to syntax constraints
 define sed-y
@@ -47,7 +48,26 @@ $(obj)/$(bounds-file): kernel/bounds.s FORCE
 	$(call filechk,offsets,__LINUX_BOUNDS_H__)
 
 #####
-# 2) Generate asm-offsets.h
+# 2) Generate timeconst.h
+
+timeconst-file := include/generated/timeconst.h
+
+#always  += $(timeconst-file)
+targets += $(timeconst-file)
+
+quiet_cmd_gentimeconst = GEN     $@
+define cmd_gentimeconst
+	(echo $(CONFIG_HZ) | bc -q $< ) > $@
+endef
+define filechk_gentimeconst
+	(echo $(CONFIG_HZ) | bc -q $< )
+endef
+
+$(obj)/$(timeconst-file): kernel/time/timeconst.bc FORCE
+	$(call filechk,gentimeconst)
+
+#####
+# 3) Generate asm-offsets.h
 #
 
 offsets-file := include/generated/asm-offsets.h
@@ -57,7 +77,7 @@ targets += arch/$(SRCARCH)/kernel/asm-offsets.s
 
 # We use internal kbuild rules to avoid the "is up to date" message from make
 arch/$(SRCARCH)/kernel/asm-offsets.s: arch/$(SRCARCH)/kernel/asm-offsets.c \
-                                      $(obj)/$(bounds-file) FORCE
+                                      $(obj)/$(timeconst-file) $(obj)/$(bounds-file) FORCE
 	$(Q)mkdir -p $(dir $@)
 	$(call if_changed_dep,cc_s_c)
 
@@ -65,7 +85,7 @@ $(obj)/$(offsets-file): arch/$(SRCARCH)/kernel/asm-offsets.s FORCE
 	$(call filechk,offsets,__ASM_OFFSETS_H__)
 
 #####
-# 3) Check for missing system calls
+# 4) Check for missing system calls
 #
 
 always += missing-syscalls
@@ -77,5 +97,5 @@ quiet_cmd_syscalls = CALL    $<
 missing-syscalls: scripts/checksyscalls.sh $(offsets-file) FORCE
 	$(call cmd,syscalls)
 
-# Keep these two files during make clean
-no-clean-files := $(bounds-file) $(offsets-file)
+# Keep these three files during make clean
+no-clean-files := $(bounds-file) $(offsets-file) $(timeconst-file)
diff --git a/MAINTAINERS b/MAINTAINERS
index d8afd2953678..e41e535648ca 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2250,6 +2250,13 @@ N:	bcm9583*
 N:	bcm583*
 N:	bcm113*
 
+BROADCOM BRCMSTB GPIO DRIVER
+M:	Gregory Fong <gregory.0xf0@gmail.com>
+L:	bcm-kernel-feedback-list@broadcom.com>
+S:	Supported
+F:	drivers/gpio/gpio-brcmstb.c
+F:	Documentation/devicetree/bindings/gpio/brcm,brcmstb-gpio.txt
+
 BROADCOM KONA GPIO DRIVER
 M:	Ray Jui <rjui@broadcom.com>
 L:	bcm-kernel-feedback-list@broadcom.com
@@ -4643,6 +4650,18 @@ F:	drivers/hid/
 F:	include/linux/hid*
 F:	include/uapi/linux/hid*
 
+HID SENSOR HUB DRIVERS
+M:	Jiri Kosina <jkosina@suse.cz>
+M:	Jonathan Cameron <jic23@kernel.org>
+M:	Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
+L:	linux-input@vger.kernel.org
+L:	linux-iio@vger.kernel.org
+S:	Maintained
+F:	Documentation/hid/hid-sensor*
+F:	drivers/hid/hid-sensor-*
+F:	drivers/iio/*/hid-*
+F:	include/linux/hid-sensor-*
+
 HIGH-RESOLUTION TIMERS, CLOCKEVENTS, DYNTICKS
 M:	Thomas Gleixner <tglx@linutronix.de>
 L:	linux-kernel@vger.kernel.org
@@ -4879,13 +4898,23 @@ M:	Marcelo Henrique Cerri <mhcerri@linux.vnet.ibm.com>
 M:	Fionnuala Gunter <fin@linux.vnet.ibm.com>
 L:	linux-crypto@vger.kernel.org
 S:	Supported
-F:	drivers/crypto/nx/
+F:	drivers/crypto/nx/Makefile
+F:	drivers/crypto/nx/Kconfig
+F:	drivers/crypto/nx/nx-aes*
+F:	drivers/crypto/nx/nx-sha*
+F:	drivers/crypto/nx/nx.*
+F:	drivers/crypto/nx/nx_csbcpb.h
+F:	drivers/crypto/nx/nx_debugfs.h
 
 IBM Power 842 compression accelerator
 M:	Dan Streetman <ddstreet@us.ibm.com>
 S:	Supported
-F:	drivers/crypto/nx/nx-842.c
-F:	include/linux/nx842.h
+F:	drivers/crypto/nx/Makefile
+F:	drivers/crypto/nx/Kconfig
+F:	drivers/crypto/nx/nx-842*
+F:	include/linux/sw842.h
+F:	crypto/842.c
+F:	lib/842/
 
 IBM Power Linux RAID adapter
 M:	Brian King <brking@us.ibm.com>
@@ -7594,6 +7623,14 @@ L:	linux-pci@vger.kernel.org
 S:	Maintained
 F:	drivers/pci/host/*spear*
 
+PCI MSI DRIVER FOR APPLIEDMICRO XGENE
+M:	Duc Dang <dhdang@apm.com>
+L:	linux-pci@vger.kernel.org
+L:	linux-arm-kernel@lists.infradead.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/pci/xgene-pci-msi.txt
+F:	drivers/pci/host/pci-xgene-msi.c
+
 PCMCIA SUBSYSTEM
 P:	Linux PCMCIA Team
 L:	linux-pcmcia@lists.infradead.org
@@ -7634,7 +7671,6 @@ F:	kernel/delayacct.c
 
 PERFORMANCE EVENTS SUBSYSTEM
 M:	Peter Zijlstra <a.p.zijlstra@chello.nl>
-M:	Paul Mackerras <paulus@samba.org>
 M:	Ingo Molnar <mingo@redhat.com>
 M:	Arnaldo Carvalho de Melo <acme@kernel.org>
 L:	linux-kernel@vger.kernel.org
@@ -10017,7 +10053,7 @@ F:	include/linux/toshiba.h
 F:	include/uapi/linux/toshiba.h
 
 TMIO MMC DRIVER
-M:	Ian Molton <ian.molton@codethink.co.uk>
+M:	Ian Molton <ian@mnementh.co.uk>
 L:	linux-mmc@vger.kernel.org
 S:	Maintained
 F:	drivers/mmc/host/tmio_mmc*
@@ -10895,7 +10931,7 @@ M:	Andy Lutomirski <luto@amacapital.net>
 L:	linux-kernel@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/vdso
 S:	Maintained
-F:	arch/x86/vdso/
+F:	arch/x86/entry/vdso/
 
 XC2028/3028 TUNER DRIVER
 M:	Mauro Carvalho Chehab <mchehab@osg.samsung.com>
diff --git a/Makefile b/Makefile
index 3ba504496cb2..6c6f14628f32 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 1
 SUBLEVEL = 0
-EXTRAVERSION = -rc8
+EXTRAVERSION =
 NAME = Hurr durr I'ma sheep
 
 # *DOCUMENTATION*
@@ -215,7 +215,6 @@ VPATH		:= $(srctree)$(if $(KBUILD_EXTMOD),:$(KBUILD_EXTMOD))
 
 export srctree objtree VPATH
 
-
 # SUBARCH tells the usermode build what the underlying arch is.  That is set
 # first, and if a usermode build is happening, the "ARCH=um" on the command
 # line overrides the setting of ARCH below.  If a native build is happening,
@@ -1497,11 +1496,11 @@ image_name:
 # Clear a bunch of variables before executing the submake
 tools/: FORCE
 	$(Q)mkdir -p $(objtree)/tools
-	$(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(filter --j% -j,$(MAKEFLAGS))" O=$(objtree) subdir=tools -C $(src)/tools/
+	$(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(filter --j% -j,$(MAKEFLAGS))" O=$(O) subdir=tools -C $(src)/tools/
 
 tools/%: FORCE
 	$(Q)mkdir -p $(objtree)/tools
-	$(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(filter --j% -j,$(MAKEFLAGS))" O=$(objtree) subdir=tools -C $(src)/tools/ $*
+	$(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(filter --j% -j,$(MAKEFLAGS))" O=$(O) subdir=tools -C $(src)/tools/ $*
 
 # Single targets
 # ---------------------------------------------------------------------------
diff --git a/arch/alpha/include/asm/cmpxchg.h b/arch/alpha/include/asm/cmpxchg.h
index 429e8cd0d78e..e5117766529e 100644
--- a/arch/alpha/include/asm/cmpxchg.h
+++ b/arch/alpha/include/asm/cmpxchg.h
@@ -66,6 +66,4 @@
 #undef __ASM__MB
 #undef ____cmpxchg
 
-#define __HAVE_ARCH_CMPXCHG 1
-
 #endif /* _ALPHA_CMPXCHG_H */
diff --git a/arch/alpha/include/asm/pci.h b/arch/alpha/include/asm/pci.h
index f7f680f7457d..8b02afeb6319 100644
--- a/arch/alpha/include/asm/pci.h
+++ b/arch/alpha/include/asm/pci.h
@@ -71,22 +71,6 @@ extern void pcibios_set_master(struct pci_dev *dev);
 /* implement the pci_ DMA API in terms of the generic device dma_ one */
 #include <asm-generic/pci-dma-compat.h>
 
-static inline void pci_dma_burst_advice(struct pci_dev *pdev,
-					enum pci_dma_burst_strategy *strat,
-					unsigned long *strategy_parameter)
-{
-	unsigned long cacheline_size;
-	u8 byte;
-
-	pci_read_config_byte(pdev, PCI_CACHE_LINE_SIZE, &byte);
-	if (byte == 0)
-		cacheline_size = 1024;
-	else
-		cacheline_size = (int) byte * 4;
-
-	*strat = PCI_DMA_BURST_BOUNDARY;
-	*strategy_parameter = cacheline_size;
-}
 #endif
 
 /* TODO: integrate with include/asm-generic/pci.h ? */
diff --git a/arch/alpha/kernel/core_irongate.c b/arch/alpha/kernel/core_irongate.c
index 00096df0f6ad..83d0a359a1b2 100644
--- a/arch/alpha/kernel/core_irongate.c
+++ b/arch/alpha/kernel/core_irongate.c
@@ -22,7 +22,6 @@
 #include <linux/bootmem.h>
 
 #include <asm/ptrace.h>
-#include <asm/pci.h>
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
 
diff --git a/arch/alpha/kernel/sys_eiger.c b/arch/alpha/kernel/sys_eiger.c
index 79d69d7f63f8..15f42083bdb3 100644
--- a/arch/alpha/kernel/sys_eiger.c
+++ b/arch/alpha/kernel/sys_eiger.c
@@ -22,7 +22,6 @@
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
 #include <asm/io.h>
-#include <asm/pci.h>
 #include <asm/pgtable.h>
 #include <asm/core_tsunami.h>
 #include <asm/hwrpb.h>
diff --git a/arch/alpha/kernel/sys_nautilus.c b/arch/alpha/kernel/sys_nautilus.c
index 700686d04869..2cfaa0e5c577 100644
--- a/arch/alpha/kernel/sys_nautilus.c
+++ b/arch/alpha/kernel/sys_nautilus.c
@@ -39,7 +39,6 @@
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
 #include <asm/io.h>
-#include <asm/pci.h>
 #include <asm/pgtable.h>
 #include <asm/core_irongate.h>
 #include <asm/hwrpb.h>
diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c
index 9d0ac091a52a..4a905bd667e2 100644
--- a/arch/alpha/mm/fault.c
+++ b/arch/alpha/mm/fault.c
@@ -23,8 +23,7 @@
 #include <linux/smp.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
-
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 extern void die_if_kernel(char *,struct pt_regs *,long, unsigned long *);
 
@@ -107,7 +106,7 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
 
 	/* If we're in an interrupt context, or have no user context,
 	   we must not take the fault.  */
-	if (!mm || in_atomic())
+	if (!mm || faulthandler_disabled())
 		goto no_context;
 
 #ifdef CONFIG_ALPHA_LARGE_VMALLOC
diff --git a/arch/arc/include/asm/futex.h b/arch/arc/include/asm/futex.h
index 4dc64ddebece..05b5aaf5b0f9 100644
--- a/arch/arc/include/asm/futex.h
+++ b/arch/arc/include/asm/futex.h
@@ -53,7 +53,7 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
 		return -EFAULT;
 
-	pagefault_disable();	/* implies preempt_disable() */
+	pagefault_disable();
 
 	switch (op) {
 	case FUTEX_OP_SET:
@@ -75,7 +75,7 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 		ret = -ENOSYS;
 	}
 
-	pagefault_enable();	/* subsumes preempt_enable() */
+	pagefault_enable();
 
 	if (!ret) {
 		switch (cmp) {
@@ -104,7 +104,7 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 	return ret;
 }
 
-/* Compare-xchg with preemption disabled.
+/* Compare-xchg with pagefaults disabled.
  *  Notes:
  *      -Best-Effort: Exchg happens only if compare succeeds.
  *          If compare fails, returns; leaving retry/looping to upper layers
@@ -121,7 +121,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval,
 	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
 		return -EFAULT;
 
-	pagefault_disable();	/* implies preempt_disable() */
+	pagefault_disable();
 
 	/* TBD : can use llock/scond */
 	__asm__ __volatile__(
@@ -142,7 +142,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval,
 	: "r"(oldval), "r"(newval), "r"(uaddr), "ir"(-EFAULT)
 	: "cc", "memory");
 
-	pagefault_enable();	/* subsumes preempt_enable() */
+	pagefault_enable();
 
 	*uval = val;
 	return val;
diff --git a/arch/arc/include/asm/io.h b/arch/arc/include/asm/io.h
index cabd518cb253..7cc4ced5dbf4 100644
--- a/arch/arc/include/asm/io.h
+++ b/arch/arc/include/asm/io.h
@@ -20,6 +20,7 @@ extern void iounmap(const void __iomem *addr);
 
 #define ioremap_nocache(phy, sz)	ioremap(phy, sz)
 #define ioremap_wc(phy, sz)		ioremap(phy, sz)
+#define ioremap_wt(phy, sz)		ioremap(phy, sz)
 
 /* Change struct page to physical address */
 #define page_to_phys(page)		(page_to_pfn(page) << PAGE_SHIFT)
diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c
index 6a2e006cbcce..d948e4e9d89c 100644
--- a/arch/arc/mm/fault.c
+++ b/arch/arc/mm/fault.c
@@ -86,7 +86,7 @@ void do_page_fault(unsigned long address, struct pt_regs *regs)
 	 * If we're in an interrupt or have no user
 	 * context, we must not take the fault..
 	 */
-	if (in_atomic() || !mm)
+	if (faulthandler_disabled() || !mm)
 		goto no_context;
 
 	if (user_mode(regs))
diff --git a/arch/arm/common/sa1111.c b/arch/arm/common/sa1111.c
index 5cc779c8e9c6..93ee70dbbdd3 100644
--- a/arch/arm/common/sa1111.c
+++ b/arch/arm/common/sa1111.c
@@ -501,8 +501,8 @@ static int sa1111_setup_irq(struct sa1111 *sachip, unsigned irq_base)
 	 * Register SA1111 interrupt
 	 */
 	irq_set_irq_type(sachip->irq, IRQ_TYPE_EDGE_RISING);
-	irq_set_handler_data(sachip->irq, sachip);
-	irq_set_chained_handler(sachip->irq, sa1111_irq_handler);
+	irq_set_chained_handler_and_data(sachip->irq, sa1111_irq_handler,
+					 sachip);
 
 	dev_info(sachip->dev, "Providing IRQ%u-%u\n",
 		sachip->irq_base, sachip->irq_base + SA1111_IRQ_NR - 1);
@@ -836,8 +836,7 @@ static void __sa1111_remove(struct sa1111 *sachip)
 	clk_unprepare(sachip->clk);
 
 	if (sachip->irq != NO_IRQ) {
-		irq_set_chained_handler(sachip->irq, NULL);
-		irq_set_handler_data(sachip->irq, NULL);
+		irq_set_chained_handler_and_data(sachip->irq, NULL, NULL);
 		irq_free_descs(sachip->irq_base, SA1111_IRQ_NR);
 
 		release_mem_region(sachip->phys + SA1111_INTC, 512);
diff --git a/arch/arm/crypto/Kconfig b/arch/arm/crypto/Kconfig
index 8da2207b0072..27ed1b1cd1d7 100644
--- a/arch/arm/crypto/Kconfig
+++ b/arch/arm/crypto/Kconfig
@@ -53,20 +53,13 @@ config CRYPTO_SHA256_ARM
 	  SHA-256 secure hash standard (DFIPS 180-2) implemented
 	  using optimized ARM assembler and NEON, when available.
 
-config CRYPTO_SHA512_ARM_NEON
-	tristate "SHA384 and SHA512 digest algorithm (ARM NEON)"
-	depends on KERNEL_MODE_NEON
-	select CRYPTO_SHA512
+config CRYPTO_SHA512_ARM
+	tristate "SHA-384/512 digest algorithm (ARM-asm and NEON)"
 	select CRYPTO_HASH
+	depends on !CPU_V7M
 	help
 	  SHA-512 secure hash standard (DFIPS 180-2) implemented
-	  using ARM NEON instructions, when available.
-
-	  This version of SHA implements a 512 bit hash with 256 bits of
-	  security against collision attacks.
-
-	  This code also includes SHA-384, a 384 bit hash with 192 bits
-	  of security against collision attacks.
+	  using optimized ARM assembler and NEON, when available.
 
 config CRYPTO_AES_ARM
 	tristate "AES cipher algorithms (ARM-asm)"
diff --git a/arch/arm/crypto/Makefile b/arch/arm/crypto/Makefile
index 6ea828241fcb..fc5150702b64 100644
--- a/arch/arm/crypto/Makefile
+++ b/arch/arm/crypto/Makefile
@@ -7,7 +7,7 @@ obj-$(CONFIG_CRYPTO_AES_ARM_BS) += aes-arm-bs.o
 obj-$(CONFIG_CRYPTO_SHA1_ARM) += sha1-arm.o
 obj-$(CONFIG_CRYPTO_SHA1_ARM_NEON) += sha1-arm-neon.o
 obj-$(CONFIG_CRYPTO_SHA256_ARM) += sha256-arm.o
-obj-$(CONFIG_CRYPTO_SHA512_ARM_NEON) += sha512-arm-neon.o
+obj-$(CONFIG_CRYPTO_SHA512_ARM) += sha512-arm.o
 
 ce-obj-$(CONFIG_CRYPTO_AES_ARM_CE) += aes-arm-ce.o
 ce-obj-$(CONFIG_CRYPTO_SHA1_ARM_CE) += sha1-arm-ce.o
@@ -30,7 +30,8 @@ sha1-arm-y	:= sha1-armv4-large.o sha1_glue.o
 sha1-arm-neon-y	:= sha1-armv7-neon.o sha1_neon_glue.o
 sha256-arm-neon-$(CONFIG_KERNEL_MODE_NEON) := sha256_neon_glue.o
 sha256-arm-y	:= sha256-core.o sha256_glue.o $(sha256-arm-neon-y)
-sha512-arm-neon-y := sha512-armv7-neon.o sha512_neon_glue.o
+sha512-arm-neon-$(CONFIG_KERNEL_MODE_NEON) := sha512-neon-glue.o
+sha512-arm-y	:= sha512-core.o sha512-glue.o $(sha512-arm-neon-y)
 sha1-arm-ce-y	:= sha1-ce-core.o sha1-ce-glue.o
 sha2-arm-ce-y	:= sha2-ce-core.o sha2-ce-glue.o
 aes-arm-ce-y	:= aes-ce-core.o aes-ce-glue.o
@@ -45,4 +46,7 @@ $(src)/aesbs-core.S_shipped: $(src)/bsaes-armv7.pl
 $(src)/sha256-core.S_shipped: $(src)/sha256-armv4.pl
 	$(call cmd,perl)
 
-.PRECIOUS: $(obj)/aesbs-core.S $(obj)/sha256-core.S
+$(src)/sha512-core.S_shipped: $(src)/sha512-armv4.pl
+	$(call cmd,perl)
+
+.PRECIOUS: $(obj)/aesbs-core.S $(obj)/sha256-core.S $(obj)/sha512-core.S
diff --git a/arch/arm/crypto/aes-ce-core.S b/arch/arm/crypto/aes-ce-core.S
index 8cfa468ee570..987aa632c9f0 100644
--- a/arch/arm/crypto/aes-ce-core.S
+++ b/arch/arm/crypto/aes-ce-core.S
@@ -101,15 +101,14 @@
 	\dround		q10, q11
 	blo		0f			@ AES-128: 10 rounds
 	vld1.8		{q10-q11}, [ip]!
-	beq		1f			@ AES-192: 12 rounds
 	\dround		q12, q13
+	beq		1f			@ AES-192: 12 rounds
 	vld1.8		{q12-q13}, [ip]
 	\dround		q10, q11
 0:	\fround		q12, q13, q14
 	bx		lr
 
-1:	\dround		q12, q13
-	\fround		q10, q11, q14
+1:	\fround		q10, q11, q14
 	bx		lr
 	.endm
 
@@ -122,8 +121,8 @@
 	 *   q2        : third in/output block (_3x version only)
 	 *   q8        : first round key
 	 *   q9        : secound round key
-	 *   ip        : address of 3rd round key
 	 *   q14       : final round key
+	 *   r2        : address of round key array
 	 *   r3        : number of rounds
 	 */
 	.align		6
diff --git a/arch/arm/crypto/sha512-armv4.pl b/arch/arm/crypto/sha512-armv4.pl
new file mode 100644
index 000000000000..a2b11a844357
--- /dev/null
+++ b/arch/arm/crypto/sha512-armv4.pl
@@ -0,0 +1,649 @@
+#!/usr/bin/env perl
+
+# ====================================================================
+# Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
+# project. The module is, however, dual licensed under OpenSSL and
+# CRYPTOGAMS licenses depending on where you obtain it. For further
+# details see http://www.openssl.org/~appro/cryptogams/.
+#
+# Permission to use under GPL terms is granted.
+# ====================================================================
+
+# SHA512 block procedure for ARMv4. September 2007.
+
+# This code is ~4.5 (four and a half) times faster than code generated
+# by gcc 3.4 and it spends ~72 clock cycles per byte [on single-issue
+# Xscale PXA250 core].
+#
+# July 2010.
+#
+# Rescheduling for dual-issue pipeline resulted in 6% improvement on
+# Cortex A8 core and ~40 cycles per processed byte.
+
+# February 2011.
+#
+# Profiler-assisted and platform-specific optimization resulted in 7%
+# improvement on Coxtex A8 core and ~38 cycles per byte.
+
+# March 2011.
+#
+# Add NEON implementation. On Cortex A8 it was measured to process
+# one byte in 23.3 cycles or ~60% faster than integer-only code.
+
+# August 2012.
+#
+# Improve NEON performance by 12% on Snapdragon S4. In absolute
+# terms it's 22.6 cycles per byte, which is disappointing result.
+# Technical writers asserted that 3-way S4 pipeline can sustain
+# multiple NEON instructions per cycle, but dual NEON issue could
+# not be observed, see http://www.openssl.org/~appro/Snapdragon-S4.html
+# for further details. On side note Cortex-A15 processes one byte in
+# 16 cycles.
+
+# Byte order [in]dependence. =========================================
+#
+# Originally caller was expected to maintain specific *dword* order in
+# h[0-7], namely with most significant dword at *lower* address, which
+# was reflected in below two parameters as 0 and 4. Now caller is
+# expected to maintain native byte order for whole 64-bit values.
+$hi="HI";
+$lo="LO";
+# ====================================================================
+
+while (($output=shift) && ($output!~/^\w[\w\-]*\.\w+$/)) {}
+open STDOUT,">$output";
+
+$ctx="r0";	# parameter block
+$inp="r1";
+$len="r2";
+
+$Tlo="r3";
+$Thi="r4";
+$Alo="r5";
+$Ahi="r6";
+$Elo="r7";
+$Ehi="r8";
+$t0="r9";
+$t1="r10";
+$t2="r11";
+$t3="r12";
+############	r13 is stack pointer
+$Ktbl="r14";
+############	r15 is program counter
+
+$Aoff=8*0;
+$Boff=8*1;
+$Coff=8*2;
+$Doff=8*3;
+$Eoff=8*4;
+$Foff=8*5;
+$Goff=8*6;
+$Hoff=8*7;
+$Xoff=8*8;
+
+sub BODY_00_15() {
+my $magic = shift;
+$code.=<<___;
+	@ Sigma1(x)	(ROTR((x),14) ^ ROTR((x),18)  ^ ROTR((x),41))
+	@ LO		lo>>14^hi<<18 ^ lo>>18^hi<<14 ^ hi>>9^lo<<23
+	@ HI		hi>>14^lo<<18 ^ hi>>18^lo<<14 ^ lo>>9^hi<<23
+	mov	$t0,$Elo,lsr#14
+	str	$Tlo,[sp,#$Xoff+0]
+	mov	$t1,$Ehi,lsr#14
+	str	$Thi,[sp,#$Xoff+4]
+	eor	$t0,$t0,$Ehi,lsl#18
+	ldr	$t2,[sp,#$Hoff+0]	@ h.lo
+	eor	$t1,$t1,$Elo,lsl#18
+	ldr	$t3,[sp,#$Hoff+4]	@ h.hi
+	eor	$t0,$t0,$Elo,lsr#18
+	eor	$t1,$t1,$Ehi,lsr#18
+	eor	$t0,$t0,$Ehi,lsl#14
+	eor	$t1,$t1,$Elo,lsl#14
+	eor	$t0,$t0,$Ehi,lsr#9
+	eor	$t1,$t1,$Elo,lsr#9
+	eor	$t0,$t0,$Elo,lsl#23
+	eor	$t1,$t1,$Ehi,lsl#23	@ Sigma1(e)
+	adds	$Tlo,$Tlo,$t0
+	ldr	$t0,[sp,#$Foff+0]	@ f.lo
+	adc	$Thi,$Thi,$t1		@ T += Sigma1(e)
+	ldr	$t1,[sp,#$Foff+4]	@ f.hi
+	adds	$Tlo,$Tlo,$t2
+	ldr	$t2,[sp,#$Goff+0]	@ g.lo
+	adc	$Thi,$Thi,$t3		@ T += h
+	ldr	$t3,[sp,#$Goff+4]	@ g.hi
+
+	eor	$t0,$t0,$t2
+	str	$Elo,[sp,#$Eoff+0]
+	eor	$t1,$t1,$t3
+	str	$Ehi,[sp,#$Eoff+4]
+	and	$t0,$t0,$Elo
+	str	$Alo,[sp,#$Aoff+0]
+	and	$t1,$t1,$Ehi
+	str	$Ahi,[sp,#$Aoff+4]
+	eor	$t0,$t0,$t2
+	ldr	$t2,[$Ktbl,#$lo]	@ K[i].lo
+	eor	$t1,$t1,$t3		@ Ch(e,f,g)
+	ldr	$t3,[$Ktbl,#$hi]	@ K[i].hi
+
+	adds	$Tlo,$Tlo,$t0
+	ldr	$Elo,[sp,#$Doff+0]	@ d.lo
+	adc	$Thi,$Thi,$t1		@ T += Ch(e,f,g)
+	ldr	$Ehi,[sp,#$Doff+4]	@ d.hi
+	adds	$Tlo,$Tlo,$t2
+	and	$t0,$t2,#0xff
+	adc	$Thi,$Thi,$t3		@ T += K[i]
+	adds	$Elo,$Elo,$Tlo
+	ldr	$t2,[sp,#$Boff+0]	@ b.lo
+	adc	$Ehi,$Ehi,$Thi		@ d += T
+	teq	$t0,#$magic
+
+	ldr	$t3,[sp,#$Coff+0]	@ c.lo
+#if __ARM_ARCH__>=7
+	it	eq			@ Thumb2 thing, sanity check in ARM
+#endif
+	orreq	$Ktbl,$Ktbl,#1
+	@ Sigma0(x)	(ROTR((x),28) ^ ROTR((x),34) ^ ROTR((x),39))
+	@ LO		lo>>28^hi<<4  ^ hi>>2^lo<<30 ^ hi>>7^lo<<25
+	@ HI		hi>>28^lo<<4  ^ lo>>2^hi<<30 ^ lo>>7^hi<<25
+	mov	$t0,$Alo,lsr#28
+	mov	$t1,$Ahi,lsr#28
+	eor	$t0,$t0,$Ahi,lsl#4
+	eor	$t1,$t1,$Alo,lsl#4
+	eor	$t0,$t0,$Ahi,lsr#2
+	eor	$t1,$t1,$Alo,lsr#2
+	eor	$t0,$t0,$Alo,lsl#30
+	eor	$t1,$t1,$Ahi,lsl#30
+	eor	$t0,$t0,$Ahi,lsr#7
+	eor	$t1,$t1,$Alo,lsr#7
+	eor	$t0,$t0,$Alo,lsl#25
+	eor	$t1,$t1,$Ahi,lsl#25	@ Sigma0(a)
+	adds	$Tlo,$Tlo,$t0
+	and	$t0,$Alo,$t2
+	adc	$Thi,$Thi,$t1		@ T += Sigma0(a)
+
+	ldr	$t1,[sp,#$Boff+4]	@ b.hi
+	orr	$Alo,$Alo,$t2
+	ldr	$t2,[sp,#$Coff+4]	@ c.hi
+	and	$Alo,$Alo,$t3
+	and	$t3,$Ahi,$t1
+	orr	$Ahi,$Ahi,$t1
+	orr	$Alo,$Alo,$t0		@ Maj(a,b,c).lo
+	and	$Ahi,$Ahi,$t2
+	adds	$Alo,$Alo,$Tlo
+	orr	$Ahi,$Ahi,$t3		@ Maj(a,b,c).hi
+	sub	sp,sp,#8
+	adc	$Ahi,$Ahi,$Thi		@ h += T
+	tst	$Ktbl,#1
+	add	$Ktbl,$Ktbl,#8
+___
+}
+$code=<<___;
+#ifndef __KERNEL__
+# include "arm_arch.h"
+# define VFP_ABI_PUSH	vstmdb	sp!,{d8-d15}
+# define VFP_ABI_POP	vldmia	sp!,{d8-d15}
+#else
+# define __ARM_ARCH__ __LINUX_ARM_ARCH__
+# define __ARM_MAX_ARCH__ 7
+# define VFP_ABI_PUSH
+# define VFP_ABI_POP
+#endif
+
+#ifdef __ARMEL__
+# define LO 0
+# define HI 4
+# define WORD64(hi0,lo0,hi1,lo1)	.word	lo0,hi0, lo1,hi1
+#else
+# define HI 0
+# define LO 4
+# define WORD64(hi0,lo0,hi1,lo1)	.word	hi0,lo0, hi1,lo1
+#endif
+
+.text
+#if __ARM_ARCH__<7
+.code	32
+#else
+.syntax unified
+# ifdef __thumb2__
+#  define adrl adr
+.thumb
+# else
+.code   32
+# endif
+#endif
+
+.type	K512,%object
+.align	5
+K512:
+WORD64(0x428a2f98,0xd728ae22, 0x71374491,0x23ef65cd)
+WORD64(0xb5c0fbcf,0xec4d3b2f, 0xe9b5dba5,0x8189dbbc)
+WORD64(0x3956c25b,0xf348b538, 0x59f111f1,0xb605d019)
+WORD64(0x923f82a4,0xaf194f9b, 0xab1c5ed5,0xda6d8118)
+WORD64(0xd807aa98,0xa3030242, 0x12835b01,0x45706fbe)
+WORD64(0x243185be,0x4ee4b28c, 0x550c7dc3,0xd5ffb4e2)
+WORD64(0x72be5d74,0xf27b896f, 0x80deb1fe,0x3b1696b1)
+WORD64(0x9bdc06a7,0x25c71235, 0xc19bf174,0xcf692694)
+WORD64(0xe49b69c1,0x9ef14ad2, 0xefbe4786,0x384f25e3)
+WORD64(0x0fc19dc6,0x8b8cd5b5, 0x240ca1cc,0x77ac9c65)
+WORD64(0x2de92c6f,0x592b0275, 0x4a7484aa,0x6ea6e483)
+WORD64(0x5cb0a9dc,0xbd41fbd4, 0x76f988da,0x831153b5)
+WORD64(0x983e5152,0xee66dfab, 0xa831c66d,0x2db43210)
+WORD64(0xb00327c8,0x98fb213f, 0xbf597fc7,0xbeef0ee4)
+WORD64(0xc6e00bf3,0x3da88fc2, 0xd5a79147,0x930aa725)
+WORD64(0x06ca6351,0xe003826f, 0x14292967,0x0a0e6e70)
+WORD64(0x27b70a85,0x46d22ffc, 0x2e1b2138,0x5c26c926)
+WORD64(0x4d2c6dfc,0x5ac42aed, 0x53380d13,0x9d95b3df)
+WORD64(0x650a7354,0x8baf63de, 0x766a0abb,0x3c77b2a8)
+WORD64(0x81c2c92e,0x47edaee6, 0x92722c85,0x1482353b)
+WORD64(0xa2bfe8a1,0x4cf10364, 0xa81a664b,0xbc423001)
+WORD64(0xc24b8b70,0xd0f89791, 0xc76c51a3,0x0654be30)
+WORD64(0xd192e819,0xd6ef5218, 0xd6990624,0x5565a910)
+WORD64(0xf40e3585,0x5771202a, 0x106aa070,0x32bbd1b8)
+WORD64(0x19a4c116,0xb8d2d0c8, 0x1e376c08,0x5141ab53)
+WORD64(0x2748774c,0xdf8eeb99, 0x34b0bcb5,0xe19b48a8)
+WORD64(0x391c0cb3,0xc5c95a63, 0x4ed8aa4a,0xe3418acb)
+WORD64(0x5b9cca4f,0x7763e373, 0x682e6ff3,0xd6b2b8a3)
+WORD64(0x748f82ee,0x5defb2fc, 0x78a5636f,0x43172f60)
+WORD64(0x84c87814,0xa1f0ab72, 0x8cc70208,0x1a6439ec)
+WORD64(0x90befffa,0x23631e28, 0xa4506ceb,0xde82bde9)
+WORD64(0xbef9a3f7,0xb2c67915, 0xc67178f2,0xe372532b)
+WORD64(0xca273ece,0xea26619c, 0xd186b8c7,0x21c0c207)
+WORD64(0xeada7dd6,0xcde0eb1e, 0xf57d4f7f,0xee6ed178)
+WORD64(0x06f067aa,0x72176fba, 0x0a637dc5,0xa2c898a6)
+WORD64(0x113f9804,0xbef90dae, 0x1b710b35,0x131c471b)
+WORD64(0x28db77f5,0x23047d84, 0x32caab7b,0x40c72493)
+WORD64(0x3c9ebe0a,0x15c9bebc, 0x431d67c4,0x9c100d4c)
+WORD64(0x4cc5d4be,0xcb3e42b6, 0x597f299c,0xfc657e2a)
+WORD64(0x5fcb6fab,0x3ad6faec, 0x6c44198c,0x4a475817)
+.size	K512,.-K512
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+.LOPENSSL_armcap:
+.word	OPENSSL_armcap_P-sha512_block_data_order
+.skip	32-4
+#else
+.skip	32
+#endif
+
+.global	sha512_block_data_order
+.type	sha512_block_data_order,%function
+sha512_block_data_order:
+#if __ARM_ARCH__<7
+	sub	r3,pc,#8		@ sha512_block_data_order
+#else
+	adr	r3,sha512_block_data_order
+#endif
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+	ldr	r12,.LOPENSSL_armcap
+	ldr	r12,[r3,r12]		@ OPENSSL_armcap_P
+	tst	r12,#1
+	bne	.LNEON
+#endif
+	add	$len,$inp,$len,lsl#7	@ len to point at the end of inp
+	stmdb	sp!,{r4-r12,lr}
+	sub	$Ktbl,r3,#672		@ K512
+	sub	sp,sp,#9*8
+
+	ldr	$Elo,[$ctx,#$Eoff+$lo]
+	ldr	$Ehi,[$ctx,#$Eoff+$hi]
+	ldr	$t0, [$ctx,#$Goff+$lo]
+	ldr	$t1, [$ctx,#$Goff+$hi]
+	ldr	$t2, [$ctx,#$Hoff+$lo]
+	ldr	$t3, [$ctx,#$Hoff+$hi]
+.Loop:
+	str	$t0, [sp,#$Goff+0]
+	str	$t1, [sp,#$Goff+4]
+	str	$t2, [sp,#$Hoff+0]
+	str	$t3, [sp,#$Hoff+4]
+	ldr	$Alo,[$ctx,#$Aoff+$lo]
+	ldr	$Ahi,[$ctx,#$Aoff+$hi]
+	ldr	$Tlo,[$ctx,#$Boff+$lo]
+	ldr	$Thi,[$ctx,#$Boff+$hi]
+	ldr	$t0, [$ctx,#$Coff+$lo]
+	ldr	$t1, [$ctx,#$Coff+$hi]
+	ldr	$t2, [$ctx,#$Doff+$lo]
+	ldr	$t3, [$ctx,#$Doff+$hi]
+	str	$Tlo,[sp,#$Boff+0]
+	str	$Thi,[sp,#$Boff+4]
+	str	$t0, [sp,#$Coff+0]
+	str	$t1, [sp,#$Coff+4]
+	str	$t2, [sp,#$Doff+0]
+	str	$t3, [sp,#$Doff+4]
+	ldr	$Tlo,[$ctx,#$Foff+$lo]
+	ldr	$Thi,[$ctx,#$Foff+$hi]
+	str	$Tlo,[sp,#$Foff+0]
+	str	$Thi,[sp,#$Foff+4]
+
+.L00_15:
+#if __ARM_ARCH__<7
+	ldrb	$Tlo,[$inp,#7]
+	ldrb	$t0, [$inp,#6]
+	ldrb	$t1, [$inp,#5]
+	ldrb	$t2, [$inp,#4]
+	ldrb	$Thi,[$inp,#3]
+	ldrb	$t3, [$inp,#2]
+	orr	$Tlo,$Tlo,$t0,lsl#8
+	ldrb	$t0, [$inp,#1]
+	orr	$Tlo,$Tlo,$t1,lsl#16
+	ldrb	$t1, [$inp],#8
+	orr	$Tlo,$Tlo,$t2,lsl#24
+	orr	$Thi,$Thi,$t3,lsl#8
+	orr	$Thi,$Thi,$t0,lsl#16
+	orr	$Thi,$Thi,$t1,lsl#24
+#else
+	ldr	$Tlo,[$inp,#4]
+	ldr	$Thi,[$inp],#8
+#ifdef __ARMEL__
+	rev	$Tlo,$Tlo
+	rev	$Thi,$Thi
+#endif
+#endif
+___
+	&BODY_00_15(0x94);
+$code.=<<___;
+	tst	$Ktbl,#1
+	beq	.L00_15
+	ldr	$t0,[sp,#`$Xoff+8*(16-1)`+0]
+	ldr	$t1,[sp,#`$Xoff+8*(16-1)`+4]
+	bic	$Ktbl,$Ktbl,#1
+.L16_79:
+	@ sigma0(x)	(ROTR((x),1)  ^ ROTR((x),8)  ^ ((x)>>7))
+	@ LO		lo>>1^hi<<31  ^ lo>>8^hi<<24 ^ lo>>7^hi<<25
+	@ HI		hi>>1^lo<<31  ^ hi>>8^lo<<24 ^ hi>>7
+	mov	$Tlo,$t0,lsr#1
+	ldr	$t2,[sp,#`$Xoff+8*(16-14)`+0]
+	mov	$Thi,$t1,lsr#1
+	ldr	$t3,[sp,#`$Xoff+8*(16-14)`+4]
+	eor	$Tlo,$Tlo,$t1,lsl#31
+	eor	$Thi,$Thi,$t0,lsl#31
+	eor	$Tlo,$Tlo,$t0,lsr#8
+	eor	$Thi,$Thi,$t1,lsr#8
+	eor	$Tlo,$Tlo,$t1,lsl#24
+	eor	$Thi,$Thi,$t0,lsl#24
+	eor	$Tlo,$Tlo,$t0,lsr#7
+	eor	$Thi,$Thi,$t1,lsr#7
+	eor	$Tlo,$Tlo,$t1,lsl#25
+
+	@ sigma1(x)	(ROTR((x),19) ^ ROTR((x),61) ^ ((x)>>6))
+	@ LO		lo>>19^hi<<13 ^ hi>>29^lo<<3 ^ lo>>6^hi<<26
+	@ HI		hi>>19^lo<<13 ^ lo>>29^hi<<3 ^ hi>>6
+	mov	$t0,$t2,lsr#19
+	mov	$t1,$t3,lsr#19
+	eor	$t0,$t0,$t3,lsl#13
+	eor	$t1,$t1,$t2,lsl#13
+	eor	$t0,$t0,$t3,lsr#29
+	eor	$t1,$t1,$t2,lsr#29
+	eor	$t0,$t0,$t2,lsl#3
+	eor	$t1,$t1,$t3,lsl#3
+	eor	$t0,$t0,$t2,lsr#6
+	eor	$t1,$t1,$t3,lsr#6
+	ldr	$t2,[sp,#`$Xoff+8*(16-9)`+0]
+	eor	$t0,$t0,$t3,lsl#26
+
+	ldr	$t3,[sp,#`$Xoff+8*(16-9)`+4]
+	adds	$Tlo,$Tlo,$t0
+	ldr	$t0,[sp,#`$Xoff+8*16`+0]
+	adc	$Thi,$Thi,$t1
+
+	ldr	$t1,[sp,#`$Xoff+8*16`+4]
+	adds	$Tlo,$Tlo,$t2
+	adc	$Thi,$Thi,$t3
+	adds	$Tlo,$Tlo,$t0
+	adc	$Thi,$Thi,$t1
+___
+	&BODY_00_15(0x17);
+$code.=<<___;
+#if __ARM_ARCH__>=7
+	ittt	eq			@ Thumb2 thing, sanity check in ARM
+#endif
+	ldreq	$t0,[sp,#`$Xoff+8*(16-1)`+0]
+	ldreq	$t1,[sp,#`$Xoff+8*(16-1)`+4]
+	beq	.L16_79
+	bic	$Ktbl,$Ktbl,#1
+
+	ldr	$Tlo,[sp,#$Boff+0]
+	ldr	$Thi,[sp,#$Boff+4]
+	ldr	$t0, [$ctx,#$Aoff+$lo]
+	ldr	$t1, [$ctx,#$Aoff+$hi]
+	ldr	$t2, [$ctx,#$Boff+$lo]
+	ldr	$t3, [$ctx,#$Boff+$hi]
+	adds	$t0,$Alo,$t0
+	str	$t0, [$ctx,#$Aoff+$lo]
+	adc	$t1,$Ahi,$t1
+	str	$t1, [$ctx,#$Aoff+$hi]
+	adds	$t2,$Tlo,$t2
+	str	$t2, [$ctx,#$Boff+$lo]
+	adc	$t3,$Thi,$t3
+	str	$t3, [$ctx,#$Boff+$hi]
+
+	ldr	$Alo,[sp,#$Coff+0]
+	ldr	$Ahi,[sp,#$Coff+4]
+	ldr	$Tlo,[sp,#$Doff+0]
+	ldr	$Thi,[sp,#$Doff+4]
+	ldr	$t0, [$ctx,#$Coff+$lo]
+	ldr	$t1, [$ctx,#$Coff+$hi]
+	ldr	$t2, [$ctx,#$Doff+$lo]
+	ldr	$t3, [$ctx,#$Doff+$hi]
+	adds	$t0,$Alo,$t0
+	str	$t0, [$ctx,#$Coff+$lo]
+	adc	$t1,$Ahi,$t1
+	str	$t1, [$ctx,#$Coff+$hi]
+	adds	$t2,$Tlo,$t2
+	str	$t2, [$ctx,#$Doff+$lo]
+	adc	$t3,$Thi,$t3
+	str	$t3, [$ctx,#$Doff+$hi]
+
+	ldr	$Tlo,[sp,#$Foff+0]
+	ldr	$Thi,[sp,#$Foff+4]
+	ldr	$t0, [$ctx,#$Eoff+$lo]
+	ldr	$t1, [$ctx,#$Eoff+$hi]
+	ldr	$t2, [$ctx,#$Foff+$lo]
+	ldr	$t3, [$ctx,#$Foff+$hi]
+	adds	$Elo,$Elo,$t0
+	str	$Elo,[$ctx,#$Eoff+$lo]
+	adc	$Ehi,$Ehi,$t1
+	str	$Ehi,[$ctx,#$Eoff+$hi]
+	adds	$t2,$Tlo,$t2
+	str	$t2, [$ctx,#$Foff+$lo]
+	adc	$t3,$Thi,$t3
+	str	$t3, [$ctx,#$Foff+$hi]
+
+	ldr	$Alo,[sp,#$Goff+0]
+	ldr	$Ahi,[sp,#$Goff+4]
+	ldr	$Tlo,[sp,#$Hoff+0]
+	ldr	$Thi,[sp,#$Hoff+4]
+	ldr	$t0, [$ctx,#$Goff+$lo]
+	ldr	$t1, [$ctx,#$Goff+$hi]
+	ldr	$t2, [$ctx,#$Hoff+$lo]
+	ldr	$t3, [$ctx,#$Hoff+$hi]
+	adds	$t0,$Alo,$t0
+	str	$t0, [$ctx,#$Goff+$lo]
+	adc	$t1,$Ahi,$t1
+	str	$t1, [$ctx,#$Goff+$hi]
+	adds	$t2,$Tlo,$t2
+	str	$t2, [$ctx,#$Hoff+$lo]
+	adc	$t3,$Thi,$t3
+	str	$t3, [$ctx,#$Hoff+$hi]
+
+	add	sp,sp,#640
+	sub	$Ktbl,$Ktbl,#640
+
+	teq	$inp,$len
+	bne	.Loop
+
+	add	sp,sp,#8*9		@ destroy frame
+#if __ARM_ARCH__>=5
+	ldmia	sp!,{r4-r12,pc}
+#else
+	ldmia	sp!,{r4-r12,lr}
+	tst	lr,#1
+	moveq	pc,lr			@ be binary compatible with V4, yet
+	bx	lr			@ interoperable with Thumb ISA:-)
+#endif
+.size	sha512_block_data_order,.-sha512_block_data_order
+___
+
+{
+my @Sigma0=(28,34,39);
+my @Sigma1=(14,18,41);
+my @sigma0=(1, 8, 7);
+my @sigma1=(19,61,6);
+
+my $Ktbl="r3";
+my $cnt="r12";	# volatile register known as ip, intra-procedure-call scratch
+
+my @X=map("d$_",(0..15));
+my @V=($A,$B,$C,$D,$E,$F,$G,$H)=map("d$_",(16..23));
+
+sub NEON_00_15() {
+my $i=shift;
+my ($a,$b,$c,$d,$e,$f,$g,$h)=@_;
+my ($t0,$t1,$t2,$T1,$K,$Ch,$Maj)=map("d$_",(24..31));	# temps
+
+$code.=<<___ if ($i<16 || $i&1);
+	vshr.u64	$t0,$e,#@Sigma1[0]	@ $i
+#if $i<16
+	vld1.64		{@X[$i%16]},[$inp]!	@ handles unaligned
+#endif
+	vshr.u64	$t1,$e,#@Sigma1[1]
+#if $i>0
+	 vadd.i64	$a,$Maj			@ h+=Maj from the past
+#endif
+	vshr.u64	$t2,$e,#@Sigma1[2]
+___
+$code.=<<___;
+	vld1.64		{$K},[$Ktbl,:64]!	@ K[i++]
+	vsli.64		$t0,$e,#`64-@Sigma1[0]`
+	vsli.64		$t1,$e,#`64-@Sigma1[1]`
+	vmov		$Ch,$e
+	vsli.64		$t2,$e,#`64-@Sigma1[2]`
+#if $i<16 && defined(__ARMEL__)
+	vrev64.8	@X[$i],@X[$i]
+#endif
+	veor		$t1,$t0
+	vbsl		$Ch,$f,$g		@ Ch(e,f,g)
+	vshr.u64	$t0,$a,#@Sigma0[0]
+	veor		$t2,$t1			@ Sigma1(e)
+	vadd.i64	$T1,$Ch,$h
+	vshr.u64	$t1,$a,#@Sigma0[1]
+	vsli.64		$t0,$a,#`64-@Sigma0[0]`
+	vadd.i64	$T1,$t2
+	vshr.u64	$t2,$a,#@Sigma0[2]
+	vadd.i64	$K,@X[$i%16]
+	vsli.64		$t1,$a,#`64-@Sigma0[1]`
+	veor		$Maj,$a,$b
+	vsli.64		$t2,$a,#`64-@Sigma0[2]`
+	veor		$h,$t0,$t1
+	vadd.i64	$T1,$K
+	vbsl		$Maj,$c,$b		@ Maj(a,b,c)
+	veor		$h,$t2			@ Sigma0(a)
+	vadd.i64	$d,$T1
+	vadd.i64	$Maj,$T1
+	@ vadd.i64	$h,$Maj
+___
+}
+
+sub NEON_16_79() {
+my $i=shift;
+
+if ($i&1)	{ &NEON_00_15($i,@_); return; }
+
+# 2x-vectorized, therefore runs every 2nd round
+my @X=map("q$_",(0..7));			# view @X as 128-bit vector
+my ($t0,$t1,$s0,$s1) = map("q$_",(12..15));	# temps
+my ($d0,$d1,$d2) = map("d$_",(24..26));		# temps from NEON_00_15
+my $e=@_[4];					# $e from NEON_00_15
+$i /= 2;
+$code.=<<___;
+	vshr.u64	$t0,@X[($i+7)%8],#@sigma1[0]
+	vshr.u64	$t1,@X[($i+7)%8],#@sigma1[1]
+	 vadd.i64	@_[0],d30			@ h+=Maj from the past
+	vshr.u64	$s1,@X[($i+7)%8],#@sigma1[2]
+	vsli.64		$t0,@X[($i+7)%8],#`64-@sigma1[0]`
+	vext.8		$s0,@X[$i%8],@X[($i+1)%8],#8	@ X[i+1]
+	vsli.64		$t1,@X[($i+7)%8],#`64-@sigma1[1]`
+	veor		$s1,$t0
+	vshr.u64	$t0,$s0,#@sigma0[0]
+	veor		$s1,$t1				@ sigma1(X[i+14])
+	vshr.u64	$t1,$s0,#@sigma0[1]
+	vadd.i64	@X[$i%8],$s1
+	vshr.u64	$s1,$s0,#@sigma0[2]
+	vsli.64		$t0,$s0,#`64-@sigma0[0]`
+	vsli.64		$t1,$s0,#`64-@sigma0[1]`
+	vext.8		$s0,@X[($i+4)%8],@X[($i+5)%8],#8	@ X[i+9]
+	veor		$s1,$t0
+	vshr.u64	$d0,$e,#@Sigma1[0]		@ from NEON_00_15
+	vadd.i64	@X[$i%8],$s0
+	vshr.u64	$d1,$e,#@Sigma1[1]		@ from NEON_00_15
+	veor		$s1,$t1				@ sigma0(X[i+1])
+	vshr.u64	$d2,$e,#@Sigma1[2]		@ from NEON_00_15
+	vadd.i64	@X[$i%8],$s1
+___
+	&NEON_00_15(2*$i,@_);
+}
+
+$code.=<<___;
+#if __ARM_MAX_ARCH__>=7
+.arch	armv7-a
+.fpu	neon
+
+.global	sha512_block_data_order_neon
+.type	sha512_block_data_order_neon,%function
+.align	4
+sha512_block_data_order_neon:
+.LNEON:
+	dmb				@ errata #451034 on early Cortex A8
+	add	$len,$inp,$len,lsl#7	@ len to point at the end of inp
+	VFP_ABI_PUSH
+	adrl	$Ktbl,K512
+	vldmia	$ctx,{$A-$H}		@ load context
+.Loop_neon:
+___
+for($i=0;$i<16;$i++)	{ &NEON_00_15($i,@V); unshift(@V,pop(@V)); }
+$code.=<<___;
+	mov		$cnt,#4
+.L16_79_neon:
+	subs		$cnt,#1
+___
+for(;$i<32;$i++)	{ &NEON_16_79($i,@V); unshift(@V,pop(@V)); }
+$code.=<<___;
+	bne		.L16_79_neon
+
+	 vadd.i64	$A,d30		@ h+=Maj from the past
+	vldmia		$ctx,{d24-d31}	@ load context to temp
+	vadd.i64	q8,q12		@ vectorized accumulate
+	vadd.i64	q9,q13
+	vadd.i64	q10,q14
+	vadd.i64	q11,q15
+	vstmia		$ctx,{$A-$H}	@ save context
+	teq		$inp,$len
+	sub		$Ktbl,#640	@ rewind K512
+	bne		.Loop_neon
+
+	VFP_ABI_POP
+	ret				@ bx lr
+.size	sha512_block_data_order_neon,.-sha512_block_data_order_neon
+#endif
+___
+}
+$code.=<<___;
+.asciz	"SHA512 block transform for ARMv4/NEON, CRYPTOGAMS by <appro\@openssl.org>"
+.align	2
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+.comm	OPENSSL_armcap_P,4,4
+#endif
+___
+
+$code =~ s/\`([^\`]*)\`/eval $1/gem;
+$code =~ s/\bbx\s+lr\b/.word\t0xe12fff1e/gm;	# make it possible to compile with -march=armv4
+$code =~ s/\bret\b/bx	lr/gm;
+
+open SELF,$0;
+while(<SELF>) {
+	next if (/^#!/);
+	last if (!s/^#/@/ and !/^$/);
+	print;
+}
+close SELF;
+
+print $code;
+close STDOUT; # enforce flush
diff --git a/arch/arm/crypto/sha512-armv7-neon.S b/arch/arm/crypto/sha512-armv7-neon.S
deleted file mode 100644
index fe99472e507c..000000000000
--- a/arch/arm/crypto/sha512-armv7-neon.S
+++ /dev/null
@@ -1,455 +0,0 @@
-/* sha512-armv7-neon.S  -  ARM/NEON assembly implementation of SHA-512 transform
- *
- * Copyright © 2013-2014 Jussi Kivilinna <jussi.kivilinna@iki.fi>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- */
-
-#include <linux/linkage.h>
-
-
-.syntax unified
-.code   32
-.fpu neon
-
-.text
-
-/* structure of SHA512_CONTEXT */
-#define hd_a 0
-#define hd_b ((hd_a) + 8)
-#define hd_c ((hd_b) + 8)
-#define hd_d ((hd_c) + 8)
-#define hd_e ((hd_d) + 8)
-#define hd_f ((hd_e) + 8)
-#define hd_g ((hd_f) + 8)
-
-/* register macros */
-#define RK %r2
-
-#define RA d0
-#define RB d1
-#define RC d2
-#define RD d3
-#define RE d4
-#define RF d5
-#define RG d6
-#define RH d7
-
-#define RT0 d8
-#define RT1 d9
-#define RT2 d10
-#define RT3 d11
-#define RT4 d12
-#define RT5 d13
-#define RT6 d14
-#define RT7 d15
-
-#define RT01q q4
-#define RT23q q5
-#define RT45q q6
-#define RT67q q7
-
-#define RW0 d16
-#define RW1 d17
-#define RW2 d18
-#define RW3 d19
-#define RW4 d20
-#define RW5 d21
-#define RW6 d22
-#define RW7 d23
-#define RW8 d24
-#define RW9 d25
-#define RW10 d26
-#define RW11 d27
-#define RW12 d28
-#define RW13 d29
-#define RW14 d30
-#define RW15 d31
-
-#define RW01q q8
-#define RW23q q9
-#define RW45q q10
-#define RW67q q11
-#define RW89q q12
-#define RW1011q q13
-#define RW1213q q14
-#define RW1415q q15
-
-/***********************************************************************
- * ARM assembly implementation of sha512 transform
- ***********************************************************************/
-#define rounds2_0_63(ra, rb, rc, rd, re, rf, rg, rh, rw0, rw1, rw01q, rw2, \
-                     rw23q, rw1415q, rw9, rw10, interleave_op, arg1) \
-	/* t1 = h + Sum1 (e) + Ch (e, f, g) + k[t] + w[t]; */ \
-	vshr.u64 RT2, re, #14; \
-	vshl.u64 RT3, re, #64 - 14; \
-	interleave_op(arg1); \
-	vshr.u64 RT4, re, #18; \
-	vshl.u64 RT5, re, #64 - 18; \
-	vld1.64 {RT0}, [RK]!; \
-	veor.64 RT23q, RT23q, RT45q; \
-	vshr.u64 RT4, re, #41; \
-	vshl.u64 RT5, re, #64 - 41; \
-	vadd.u64 RT0, RT0, rw0; \
-	veor.64 RT23q, RT23q, RT45q; \
-	vmov.64 RT7, re; \
-	veor.64 RT1, RT2, RT3; \
-	vbsl.64 RT7, rf, rg; \
-	\
-	vadd.u64 RT1, RT1, rh; \
-	vshr.u64 RT2, ra, #28; \
-	vshl.u64 RT3, ra, #64 - 28; \
-	vadd.u64 RT1, RT1, RT0; \
-	vshr.u64 RT4, ra, #34; \
-	vshl.u64 RT5, ra, #64 - 34; \
-	vadd.u64 RT1, RT1, RT7; \
-	\
-	/* h = Sum0 (a) + Maj (a, b, c); */ \
-	veor.64 RT23q, RT23q, RT45q; \
-	vshr.u64 RT4, ra, #39; \
-	vshl.u64 RT5, ra, #64 - 39; \
-	veor.64 RT0, ra, rb; \
-	veor.64 RT23q, RT23q, RT45q; \
-	vbsl.64 RT0, rc, rb; \
-	vadd.u64 rd, rd, RT1; /* d+=t1; */ \
-	veor.64 rh, RT2, RT3; \
-	\
-	/* t1 = g + Sum1 (d) + Ch (d, e, f) + k[t] + w[t]; */ \
-	vshr.u64 RT2, rd, #14; \
-	vshl.u64 RT3, rd, #64 - 14; \
-	vadd.u64 rh, rh, RT0; \
-	vshr.u64 RT4, rd, #18; \
-	vshl.u64 RT5, rd, #64 - 18; \
-	vadd.u64 rh, rh, RT1; /* h+=t1; */ \
-	vld1.64 {RT0}, [RK]!; \
-	veor.64 RT23q, RT23q, RT45q; \
-	vshr.u64 RT4, rd, #41; \
-	vshl.u64 RT5, rd, #64 - 41; \
-	vadd.u64 RT0, RT0, rw1; \
-	veor.64 RT23q, RT23q, RT45q; \
-	vmov.64 RT7, rd; \
-	veor.64 RT1, RT2, RT3; \
-	vbsl.64 RT7, re, rf; \
-	\
-	vadd.u64 RT1, RT1, rg; \
-	vshr.u64 RT2, rh, #28; \
-	vshl.u64 RT3, rh, #64 - 28; \
-	vadd.u64 RT1, RT1, RT0; \
-	vshr.u64 RT4, rh, #34; \
-	vshl.u64 RT5, rh, #64 - 34; \
-	vadd.u64 RT1, RT1, RT7; \
-	\
-	/* g = Sum0 (h) + Maj (h, a, b); */ \
-	veor.64 RT23q, RT23q, RT45q; \
-	vshr.u64 RT4, rh, #39; \
-	vshl.u64 RT5, rh, #64 - 39; \
-	veor.64 RT0, rh, ra; \
-	veor.64 RT23q, RT23q, RT45q; \
-	vbsl.64 RT0, rb, ra; \
-	vadd.u64 rc, rc, RT1; /* c+=t1; */ \
-	veor.64 rg, RT2, RT3; \
-	\
-	/* w[0] += S1 (w[14]) + w[9] + S0 (w[1]); */ \
-	/* w[1] += S1 (w[15]) + w[10] + S0 (w[2]); */ \
-	\
-	/**** S0(w[1:2]) */ \
-	\
-	/* w[0:1] += w[9:10] */ \
-	/* RT23q = rw1:rw2 */ \
-	vext.u64 RT23q, rw01q, rw23q, #1; \
-	vadd.u64 rw0, rw9; \
-	vadd.u64 rg, rg, RT0; \
-	vadd.u64 rw1, rw10;\
-	vadd.u64 rg, rg, RT1; /* g+=t1; */ \
-	\
-	vshr.u64 RT45q, RT23q, #1; \
-	vshl.u64 RT67q, RT23q, #64 - 1; \
-	vshr.u64 RT01q, RT23q, #8; \
-	veor.u64 RT45q, RT45q, RT67q; \
-	vshl.u64 RT67q, RT23q, #64 - 8; \
-	veor.u64 RT45q, RT45q, RT01q; \
-	vshr.u64 RT01q, RT23q, #7; \
-	veor.u64 RT45q, RT45q, RT67q; \
-	\
-	/**** S1(w[14:15]) */ \
-	vshr.u64 RT23q, rw1415q, #6; \
-	veor.u64 RT01q, RT01q, RT45q; \
-	vshr.u64 RT45q, rw1415q, #19; \
-	vshl.u64 RT67q, rw1415q, #64 - 19; \
-	veor.u64 RT23q, RT23q, RT45q; \
-	vshr.u64 RT45q, rw1415q, #61; \
-	veor.u64 RT23q, RT23q, RT67q; \
-	vshl.u64 RT67q, rw1415q, #64 - 61; \
-	veor.u64 RT23q, RT23q, RT45q; \
-	vadd.u64 rw01q, RT01q; /* w[0:1] += S(w[1:2]) */ \
-	veor.u64 RT01q, RT23q, RT67q;
-#define vadd_RT01q(rw01q) \
-	/* w[0:1] += S(w[14:15]) */ \
-	vadd.u64 rw01q, RT01q;
-
-#define dummy(_) /*_*/
-
-#define rounds2_64_79(ra, rb, rc, rd, re, rf, rg, rh, rw0, rw1, \
-	              interleave_op1, arg1, interleave_op2, arg2) \
-	/* t1 = h + Sum1 (e) + Ch (e, f, g) + k[t] + w[t]; */ \
-	vshr.u64 RT2, re, #14; \
-	vshl.u64 RT3, re, #64 - 14; \
-	interleave_op1(arg1); \
-	vshr.u64 RT4, re, #18; \
-	vshl.u64 RT5, re, #64 - 18; \
-	interleave_op2(arg2); \
-	vld1.64 {RT0}, [RK]!; \
-	veor.64 RT23q, RT23q, RT45q; \
-	vshr.u64 RT4, re, #41; \
-	vshl.u64 RT5, re, #64 - 41; \
-	vadd.u64 RT0, RT0, rw0; \
-	veor.64 RT23q, RT23q, RT45q; \
-	vmov.64 RT7, re; \
-	veor.64 RT1, RT2, RT3; \
-	vbsl.64 RT7, rf, rg; \
-	\
-	vadd.u64 RT1, RT1, rh; \
-	vshr.u64 RT2, ra, #28; \
-	vshl.u64 RT3, ra, #64 - 28; \
-	vadd.u64 RT1, RT1, RT0; \
-	vshr.u64 RT4, ra, #34; \
-	vshl.u64 RT5, ra, #64 - 34; \
-	vadd.u64 RT1, RT1, RT7; \
-	\
-	/* h = Sum0 (a) + Maj (a, b, c); */ \
-	veor.64 RT23q, RT23q, RT45q; \
-	vshr.u64 RT4, ra, #39; \
-	vshl.u64 RT5, ra, #64 - 39; \
-	veor.64 RT0, ra, rb; \
-	veor.64 RT23q, RT23q, RT45q; \
-	vbsl.64 RT0, rc, rb; \
-	vadd.u64 rd, rd, RT1; /* d+=t1; */ \
-	veor.64 rh, RT2, RT3; \
-	\
-	/* t1 = g + Sum1 (d) + Ch (d, e, f) + k[t] + w[t]; */ \
-	vshr.u64 RT2, rd, #14; \
-	vshl.u64 RT3, rd, #64 - 14; \
-	vadd.u64 rh, rh, RT0; \
-	vshr.u64 RT4, rd, #18; \
-	vshl.u64 RT5, rd, #64 - 18; \
-	vadd.u64 rh, rh, RT1; /* h+=t1; */ \
-	vld1.64 {RT0}, [RK]!; \
-	veor.64 RT23q, RT23q, RT45q; \
-	vshr.u64 RT4, rd, #41; \
-	vshl.u64 RT5, rd, #64 - 41; \
-	vadd.u64 RT0, RT0, rw1; \
-	veor.64 RT23q, RT23q, RT45q; \
-	vmov.64 RT7, rd; \
-	veor.64 RT1, RT2, RT3; \
-	vbsl.64 RT7, re, rf; \
-	\
-	vadd.u64 RT1, RT1, rg; \
-	vshr.u64 RT2, rh, #28; \
-	vshl.u64 RT3, rh, #64 - 28; \
-	vadd.u64 RT1, RT1, RT0; \
-	vshr.u64 RT4, rh, #34; \
-	vshl.u64 RT5, rh, #64 - 34; \
-	vadd.u64 RT1, RT1, RT7; \
-	\
-	/* g = Sum0 (h) + Maj (h, a, b); */ \
-	veor.64 RT23q, RT23q, RT45q; \
-	vshr.u64 RT4, rh, #39; \
-	vshl.u64 RT5, rh, #64 - 39; \
-	veor.64 RT0, rh, ra; \
-	veor.64 RT23q, RT23q, RT45q; \
-	vbsl.64 RT0, rb, ra; \
-	vadd.u64 rc, rc, RT1; /* c+=t1; */ \
-	veor.64 rg, RT2, RT3;
-#define vadd_rg_RT0(rg) \
-	vadd.u64 rg, rg, RT0;
-#define vadd_rg_RT1(rg) \
-	vadd.u64 rg, rg, RT1; /* g+=t1; */
-
-.align 3
-ENTRY(sha512_transform_neon)
-	/* Input:
-	 *	%r0: SHA512_CONTEXT
-	 *	%r1: data
-	 *	%r2: u64 k[] constants
-	 *	%r3: nblks
-	 */
-	push {%lr};
-
-	mov %lr, #0;
-
-	/* Load context to d0-d7 */
-	vld1.64 {RA-RD}, [%r0]!;
-	vld1.64 {RE-RH}, [%r0];
-	sub %r0, #(4*8);
-
-	/* Load input to w[16], d16-d31 */
-	/* NOTE: Assumes that on ARMv7 unaligned accesses are always allowed. */
-	vld1.64 {RW0-RW3}, [%r1]!;
-	vld1.64 {RW4-RW7}, [%r1]!;
-	vld1.64 {RW8-RW11}, [%r1]!;
-	vld1.64 {RW12-RW15}, [%r1]!;
-#ifdef __ARMEL__
-	/* byteswap */
-	vrev64.8 RW01q, RW01q;
-	vrev64.8 RW23q, RW23q;
-	vrev64.8 RW45q, RW45q;
-	vrev64.8 RW67q, RW67q;
-	vrev64.8 RW89q, RW89q;
-	vrev64.8 RW1011q, RW1011q;
-	vrev64.8 RW1213q, RW1213q;
-	vrev64.8 RW1415q, RW1415q;
-#endif
-
-	/* EABI says that d8-d15 must be preserved by callee. */
-	/*vpush {RT0-RT7};*/
-
-.Loop:
-	rounds2_0_63(RA, RB, RC, RD, RE, RF, RG, RH, RW0, RW1, RW01q, RW2,
-		     RW23q, RW1415q, RW9, RW10, dummy, _);
-	b .Lenter_rounds;
-
-.Loop_rounds:
-	rounds2_0_63(RA, RB, RC, RD, RE, RF, RG, RH, RW0, RW1, RW01q, RW2,
-		     RW23q, RW1415q, RW9, RW10, vadd_RT01q, RW1415q);
-.Lenter_rounds:
-	rounds2_0_63(RG, RH, RA, RB, RC, RD, RE, RF, RW2, RW3, RW23q, RW4,
-		     RW45q, RW01q, RW11, RW12, vadd_RT01q, RW01q);
-	rounds2_0_63(RE, RF, RG, RH, RA, RB, RC, RD, RW4, RW5, RW45q, RW6,
-		     RW67q, RW23q, RW13, RW14, vadd_RT01q, RW23q);
-	rounds2_0_63(RC, RD, RE, RF, RG, RH, RA, RB, RW6, RW7, RW67q, RW8,
-		     RW89q, RW45q, RW15, RW0, vadd_RT01q, RW45q);
-	rounds2_0_63(RA, RB, RC, RD, RE, RF, RG, RH, RW8, RW9, RW89q, RW10,
-		     RW1011q, RW67q, RW1, RW2, vadd_RT01q, RW67q);
-	rounds2_0_63(RG, RH, RA, RB, RC, RD, RE, RF, RW10, RW11, RW1011q, RW12,
-		     RW1213q, RW89q, RW3, RW4, vadd_RT01q, RW89q);
-	add %lr, #16;
-	rounds2_0_63(RE, RF, RG, RH, RA, RB, RC, RD, RW12, RW13, RW1213q, RW14,
-		     RW1415q, RW1011q, RW5, RW6, vadd_RT01q, RW1011q);
-	cmp %lr, #64;
-	rounds2_0_63(RC, RD, RE, RF, RG, RH, RA, RB, RW14, RW15, RW1415q, RW0,
-		     RW01q, RW1213q, RW7, RW8, vadd_RT01q, RW1213q);
-	bne .Loop_rounds;
-
-	subs %r3, #1;
-
-	rounds2_64_79(RA, RB, RC, RD, RE, RF, RG, RH, RW0, RW1,
-		      vadd_RT01q, RW1415q, dummy, _);
-	rounds2_64_79(RG, RH, RA, RB, RC, RD, RE, RF, RW2, RW3,
-		      vadd_rg_RT0, RG, vadd_rg_RT1, RG);
-	beq .Lhandle_tail;
-	vld1.64 {RW0-RW3}, [%r1]!;
-	rounds2_64_79(RE, RF, RG, RH, RA, RB, RC, RD, RW4, RW5,
-		      vadd_rg_RT0, RE, vadd_rg_RT1, RE);
-	rounds2_64_79(RC, RD, RE, RF, RG, RH, RA, RB, RW6, RW7,
-		      vadd_rg_RT0, RC, vadd_rg_RT1, RC);
-#ifdef __ARMEL__
-	vrev64.8 RW01q, RW01q;
-	vrev64.8 RW23q, RW23q;
-#endif
-	vld1.64 {RW4-RW7}, [%r1]!;
-	rounds2_64_79(RA, RB, RC, RD, RE, RF, RG, RH, RW8, RW9,
-		      vadd_rg_RT0, RA, vadd_rg_RT1, RA);
-	rounds2_64_79(RG, RH, RA, RB, RC, RD, RE, RF, RW10, RW11,
-		      vadd_rg_RT0, RG, vadd_rg_RT1, RG);
-#ifdef __ARMEL__
-	vrev64.8 RW45q, RW45q;
-	vrev64.8 RW67q, RW67q;
-#endif
-	vld1.64 {RW8-RW11}, [%r1]!;
-	rounds2_64_79(RE, RF, RG, RH, RA, RB, RC, RD, RW12, RW13,
-		      vadd_rg_RT0, RE, vadd_rg_RT1, RE);
-	rounds2_64_79(RC, RD, RE, RF, RG, RH, RA, RB, RW14, RW15,
-		      vadd_rg_RT0, RC, vadd_rg_RT1, RC);
-#ifdef __ARMEL__
-	vrev64.8 RW89q, RW89q;
-	vrev64.8 RW1011q, RW1011q;
-#endif
-	vld1.64 {RW12-RW15}, [%r1]!;
-	vadd_rg_RT0(RA);
-	vadd_rg_RT1(RA);
-
-	/* Load context */
-	vld1.64 {RT0-RT3}, [%r0]!;
-	vld1.64 {RT4-RT7}, [%r0];
-	sub %r0, #(4*8);
-
-#ifdef __ARMEL__
-	vrev64.8 RW1213q, RW1213q;
-	vrev64.8 RW1415q, RW1415q;
-#endif
-
-	vadd.u64 RA, RT0;
-	vadd.u64 RB, RT1;
-	vadd.u64 RC, RT2;
-	vadd.u64 RD, RT3;
-	vadd.u64 RE, RT4;
-	vadd.u64 RF, RT5;
-	vadd.u64 RG, RT6;
-	vadd.u64 RH, RT7;
-
-	/* Store the first half of context */
-	vst1.64 {RA-RD}, [%r0]!;
-	sub RK, $(8*80);
-	vst1.64 {RE-RH}, [%r0]; /* Store the last half of context */
-	mov %lr, #0;
-	sub %r0, #(4*8);
-
-	b .Loop;
-
-.Lhandle_tail:
-	rounds2_64_79(RE, RF, RG, RH, RA, RB, RC, RD, RW4, RW5,
-		      vadd_rg_RT0, RE, vadd_rg_RT1, RE);
-	rounds2_64_79(RC, RD, RE, RF, RG, RH, RA, RB, RW6, RW7,
-		      vadd_rg_RT0, RC, vadd_rg_RT1, RC);
-	rounds2_64_79(RA, RB, RC, RD, RE, RF, RG, RH, RW8, RW9,
-		      vadd_rg_RT0, RA, vadd_rg_RT1, RA);
-	rounds2_64_79(RG, RH, RA, RB, RC, RD, RE, RF, RW10, RW11,
-		      vadd_rg_RT0, RG, vadd_rg_RT1, RG);
-	rounds2_64_79(RE, RF, RG, RH, RA, RB, RC, RD, RW12, RW13,
-		      vadd_rg_RT0, RE, vadd_rg_RT1, RE);
-	rounds2_64_79(RC, RD, RE, RF, RG, RH, RA, RB, RW14, RW15,
-		      vadd_rg_RT0, RC, vadd_rg_RT1, RC);
-
-	/* Load context to d16-d23 */
-	vld1.64 {RW0-RW3}, [%r0]!;
-	vadd_rg_RT0(RA);
-	vld1.64 {RW4-RW7}, [%r0];
-	vadd_rg_RT1(RA);
-	sub %r0, #(4*8);
-
-	vadd.u64 RA, RW0;
-	vadd.u64 RB, RW1;
-	vadd.u64 RC, RW2;
-	vadd.u64 RD, RW3;
-	vadd.u64 RE, RW4;
-	vadd.u64 RF, RW5;
-	vadd.u64 RG, RW6;
-	vadd.u64 RH, RW7;
-
-	/* Store the first half of context */
-	vst1.64 {RA-RD}, [%r0]!;
-
-	/* Clear used registers */
-	/* d16-d31 */
-	veor.u64 RW01q, RW01q;
-	veor.u64 RW23q, RW23q;
-	veor.u64 RW45q, RW45q;
-	veor.u64 RW67q, RW67q;
-	vst1.64 {RE-RH}, [%r0]; /* Store the last half of context */
-	veor.u64 RW89q, RW89q;
-	veor.u64 RW1011q, RW1011q;
-	veor.u64 RW1213q, RW1213q;
-	veor.u64 RW1415q, RW1415q;
-	/* d8-d15 */
-	/*vpop {RT0-RT7};*/
-	/* d0-d7 (q0-q3) */
-	veor.u64 %q0, %q0;
-	veor.u64 %q1, %q1;
-	veor.u64 %q2, %q2;
-	veor.u64 %q3, %q3;
-
-	pop {%pc};
-ENDPROC(sha512_transform_neon)
diff --git a/arch/arm/crypto/sha512-core.S_shipped b/arch/arm/crypto/sha512-core.S_shipped
new file mode 100644
index 000000000000..3694c4d4ca2b
--- /dev/null
+++ b/arch/arm/crypto/sha512-core.S_shipped
@@ -0,0 +1,1861 @@
+
+@ ====================================================================
+@ Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
+@ project. The module is, however, dual licensed under OpenSSL and
+@ CRYPTOGAMS licenses depending on where you obtain it. For further
+@ details see http://www.openssl.org/~appro/cryptogams/.
+@
+@ Permission to use under GPL terms is granted.
+@ ====================================================================
+
+@ SHA512 block procedure for ARMv4. September 2007.
+
+@ This code is ~4.5 (four and a half) times faster than code generated
+@ by gcc 3.4 and it spends ~72 clock cycles per byte [on single-issue
+@ Xscale PXA250 core].
+@
+@ July 2010.
+@
+@ Rescheduling for dual-issue pipeline resulted in 6% improvement on
+@ Cortex A8 core and ~40 cycles per processed byte.
+
+@ February 2011.
+@
+@ Profiler-assisted and platform-specific optimization resulted in 7%
+@ improvement on Coxtex A8 core and ~38 cycles per byte.
+
+@ March 2011.
+@
+@ Add NEON implementation. On Cortex A8 it was measured to process
+@ one byte in 23.3 cycles or ~60% faster than integer-only code.
+
+@ August 2012.
+@
+@ Improve NEON performance by 12% on Snapdragon S4. In absolute
+@ terms it's 22.6 cycles per byte, which is disappointing result.
+@ Technical writers asserted that 3-way S4 pipeline can sustain
+@ multiple NEON instructions per cycle, but dual NEON issue could
+@ not be observed, see http://www.openssl.org/~appro/Snapdragon-S4.html
+@ for further details. On side note Cortex-A15 processes one byte in
+@ 16 cycles.
+
+@ Byte order [in]dependence. =========================================
+@
+@ Originally caller was expected to maintain specific *dword* order in
+@ h[0-7], namely with most significant dword at *lower* address, which
+@ was reflected in below two parameters as 0 and 4. Now caller is
+@ expected to maintain native byte order for whole 64-bit values.
+#ifndef __KERNEL__
+# include "arm_arch.h"
+# define VFP_ABI_PUSH	vstmdb	sp!,{d8-d15}
+# define VFP_ABI_POP	vldmia	sp!,{d8-d15}
+#else
+# define __ARM_ARCH__ __LINUX_ARM_ARCH__
+# define __ARM_MAX_ARCH__ 7
+# define VFP_ABI_PUSH
+# define VFP_ABI_POP
+#endif
+
+#ifdef __ARMEL__
+# define LO 0
+# define HI 4
+# define WORD64(hi0,lo0,hi1,lo1)	.word	lo0,hi0, lo1,hi1
+#else
+# define HI 0
+# define LO 4
+# define WORD64(hi0,lo0,hi1,lo1)	.word	hi0,lo0, hi1,lo1
+#endif
+
+.text
+#if __ARM_ARCH__<7
+.code	32
+#else
+.syntax unified
+# ifdef __thumb2__
+#  define adrl adr
+.thumb
+# else
+.code   32
+# endif
+#endif
+
+.type	K512,%object
+.align	5
+K512:
+WORD64(0x428a2f98,0xd728ae22, 0x71374491,0x23ef65cd)
+WORD64(0xb5c0fbcf,0xec4d3b2f, 0xe9b5dba5,0x8189dbbc)
+WORD64(0x3956c25b,0xf348b538, 0x59f111f1,0xb605d019)
+WORD64(0x923f82a4,0xaf194f9b, 0xab1c5ed5,0xda6d8118)
+WORD64(0xd807aa98,0xa3030242, 0x12835b01,0x45706fbe)
+WORD64(0x243185be,0x4ee4b28c, 0x550c7dc3,0xd5ffb4e2)
+WORD64(0x72be5d74,0xf27b896f, 0x80deb1fe,0x3b1696b1)
+WORD64(0x9bdc06a7,0x25c71235, 0xc19bf174,0xcf692694)
+WORD64(0xe49b69c1,0x9ef14ad2, 0xefbe4786,0x384f25e3)
+WORD64(0x0fc19dc6,0x8b8cd5b5, 0x240ca1cc,0x77ac9c65)
+WORD64(0x2de92c6f,0x592b0275, 0x4a7484aa,0x6ea6e483)
+WORD64(0x5cb0a9dc,0xbd41fbd4, 0x76f988da,0x831153b5)
+WORD64(0x983e5152,0xee66dfab, 0xa831c66d,0x2db43210)
+WORD64(0xb00327c8,0x98fb213f, 0xbf597fc7,0xbeef0ee4)
+WORD64(0xc6e00bf3,0x3da88fc2, 0xd5a79147,0x930aa725)
+WORD64(0x06ca6351,0xe003826f, 0x14292967,0x0a0e6e70)
+WORD64(0x27b70a85,0x46d22ffc, 0x2e1b2138,0x5c26c926)
+WORD64(0x4d2c6dfc,0x5ac42aed, 0x53380d13,0x9d95b3df)
+WORD64(0x650a7354,0x8baf63de, 0x766a0abb,0x3c77b2a8)
+WORD64(0x81c2c92e,0x47edaee6, 0x92722c85,0x1482353b)
+WORD64(0xa2bfe8a1,0x4cf10364, 0xa81a664b,0xbc423001)
+WORD64(0xc24b8b70,0xd0f89791, 0xc76c51a3,0x0654be30)
+WORD64(0xd192e819,0xd6ef5218, 0xd6990624,0x5565a910)
+WORD64(0xf40e3585,0x5771202a, 0x106aa070,0x32bbd1b8)
+WORD64(0x19a4c116,0xb8d2d0c8, 0x1e376c08,0x5141ab53)
+WORD64(0x2748774c,0xdf8eeb99, 0x34b0bcb5,0xe19b48a8)
+WORD64(0x391c0cb3,0xc5c95a63, 0x4ed8aa4a,0xe3418acb)
+WORD64(0x5b9cca4f,0x7763e373, 0x682e6ff3,0xd6b2b8a3)
+WORD64(0x748f82ee,0x5defb2fc, 0x78a5636f,0x43172f60)
+WORD64(0x84c87814,0xa1f0ab72, 0x8cc70208,0x1a6439ec)
+WORD64(0x90befffa,0x23631e28, 0xa4506ceb,0xde82bde9)
+WORD64(0xbef9a3f7,0xb2c67915, 0xc67178f2,0xe372532b)
+WORD64(0xca273ece,0xea26619c, 0xd186b8c7,0x21c0c207)
+WORD64(0xeada7dd6,0xcde0eb1e, 0xf57d4f7f,0xee6ed178)
+WORD64(0x06f067aa,0x72176fba, 0x0a637dc5,0xa2c898a6)
+WORD64(0x113f9804,0xbef90dae, 0x1b710b35,0x131c471b)
+WORD64(0x28db77f5,0x23047d84, 0x32caab7b,0x40c72493)
+WORD64(0x3c9ebe0a,0x15c9bebc, 0x431d67c4,0x9c100d4c)
+WORD64(0x4cc5d4be,0xcb3e42b6, 0x597f299c,0xfc657e2a)
+WORD64(0x5fcb6fab,0x3ad6faec, 0x6c44198c,0x4a475817)
+.size	K512,.-K512
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+.LOPENSSL_armcap:
+.word	OPENSSL_armcap_P-sha512_block_data_order
+.skip	32-4
+#else
+.skip	32
+#endif
+
+.global	sha512_block_data_order
+.type	sha512_block_data_order,%function
+sha512_block_data_order:
+#if __ARM_ARCH__<7
+	sub	r3,pc,#8		@ sha512_block_data_order
+#else
+	adr	r3,sha512_block_data_order
+#endif
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+	ldr	r12,.LOPENSSL_armcap
+	ldr	r12,[r3,r12]		@ OPENSSL_armcap_P
+	tst	r12,#1
+	bne	.LNEON
+#endif
+	add	r2,r1,r2,lsl#7	@ len to point at the end of inp
+	stmdb	sp!,{r4-r12,lr}
+	sub	r14,r3,#672		@ K512
+	sub	sp,sp,#9*8
+
+	ldr	r7,[r0,#32+LO]
+	ldr	r8,[r0,#32+HI]
+	ldr	r9, [r0,#48+LO]
+	ldr	r10, [r0,#48+HI]
+	ldr	r11, [r0,#56+LO]
+	ldr	r12, [r0,#56+HI]
+.Loop:
+	str	r9, [sp,#48+0]
+	str	r10, [sp,#48+4]
+	str	r11, [sp,#56+0]
+	str	r12, [sp,#56+4]
+	ldr	r5,[r0,#0+LO]
+	ldr	r6,[r0,#0+HI]
+	ldr	r3,[r0,#8+LO]
+	ldr	r4,[r0,#8+HI]
+	ldr	r9, [r0,#16+LO]
+	ldr	r10, [r0,#16+HI]
+	ldr	r11, [r0,#24+LO]
+	ldr	r12, [r0,#24+HI]
+	str	r3,[sp,#8+0]
+	str	r4,[sp,#8+4]
+	str	r9, [sp,#16+0]
+	str	r10, [sp,#16+4]
+	str	r11, [sp,#24+0]
+	str	r12, [sp,#24+4]
+	ldr	r3,[r0,#40+LO]
+	ldr	r4,[r0,#40+HI]
+	str	r3,[sp,#40+0]
+	str	r4,[sp,#40+4]
+
+.L00_15:
+#if __ARM_ARCH__<7
+	ldrb	r3,[r1,#7]
+	ldrb	r9, [r1,#6]
+	ldrb	r10, [r1,#5]
+	ldrb	r11, [r1,#4]
+	ldrb	r4,[r1,#3]
+	ldrb	r12, [r1,#2]
+	orr	r3,r3,r9,lsl#8
+	ldrb	r9, [r1,#1]
+	orr	r3,r3,r10,lsl#16
+	ldrb	r10, [r1],#8
+	orr	r3,r3,r11,lsl#24
+	orr	r4,r4,r12,lsl#8
+	orr	r4,r4,r9,lsl#16
+	orr	r4,r4,r10,lsl#24
+#else
+	ldr	r3,[r1,#4]
+	ldr	r4,[r1],#8
+#ifdef __ARMEL__
+	rev	r3,r3
+	rev	r4,r4
+#endif
+#endif
+	@ Sigma1(x)	(ROTR((x),14) ^ ROTR((x),18)  ^ ROTR((x),41))
+	@ LO		lo>>14^hi<<18 ^ lo>>18^hi<<14 ^ hi>>9^lo<<23
+	@ HI		hi>>14^lo<<18 ^ hi>>18^lo<<14 ^ lo>>9^hi<<23
+	mov	r9,r7,lsr#14
+	str	r3,[sp,#64+0]
+	mov	r10,r8,lsr#14
+	str	r4,[sp,#64+4]
+	eor	r9,r9,r8,lsl#18
+	ldr	r11,[sp,#56+0]	@ h.lo
+	eor	r10,r10,r7,lsl#18
+	ldr	r12,[sp,#56+4]	@ h.hi
+	eor	r9,r9,r7,lsr#18
+	eor	r10,r10,r8,lsr#18
+	eor	r9,r9,r8,lsl#14
+	eor	r10,r10,r7,lsl#14
+	eor	r9,r9,r8,lsr#9
+	eor	r10,r10,r7,lsr#9
+	eor	r9,r9,r7,lsl#23
+	eor	r10,r10,r8,lsl#23	@ Sigma1(e)
+	adds	r3,r3,r9
+	ldr	r9,[sp,#40+0]	@ f.lo
+	adc	r4,r4,r10		@ T += Sigma1(e)
+	ldr	r10,[sp,#40+4]	@ f.hi
+	adds	r3,r3,r11
+	ldr	r11,[sp,#48+0]	@ g.lo
+	adc	r4,r4,r12		@ T += h
+	ldr	r12,[sp,#48+4]	@ g.hi
+
+	eor	r9,r9,r11
+	str	r7,[sp,#32+0]
+	eor	r10,r10,r12
+	str	r8,[sp,#32+4]
+	and	r9,r9,r7
+	str	r5,[sp,#0+0]
+	and	r10,r10,r8
+	str	r6,[sp,#0+4]
+	eor	r9,r9,r11
+	ldr	r11,[r14,#LO]	@ K[i].lo
+	eor	r10,r10,r12		@ Ch(e,f,g)
+	ldr	r12,[r14,#HI]	@ K[i].hi
+
+	adds	r3,r3,r9
+	ldr	r7,[sp,#24+0]	@ d.lo
+	adc	r4,r4,r10		@ T += Ch(e,f,g)
+	ldr	r8,[sp,#24+4]	@ d.hi
+	adds	r3,r3,r11
+	and	r9,r11,#0xff
+	adc	r4,r4,r12		@ T += K[i]
+	adds	r7,r7,r3
+	ldr	r11,[sp,#8+0]	@ b.lo
+	adc	r8,r8,r4		@ d += T
+	teq	r9,#148
+
+	ldr	r12,[sp,#16+0]	@ c.lo
+#if __ARM_ARCH__>=7
+	it	eq			@ Thumb2 thing, sanity check in ARM
+#endif
+	orreq	r14,r14,#1
+	@ Sigma0(x)	(ROTR((x),28) ^ ROTR((x),34) ^ ROTR((x),39))
+	@ LO		lo>>28^hi<<4  ^ hi>>2^lo<<30 ^ hi>>7^lo<<25
+	@ HI		hi>>28^lo<<4  ^ lo>>2^hi<<30 ^ lo>>7^hi<<25
+	mov	r9,r5,lsr#28
+	mov	r10,r6,lsr#28
+	eor	r9,r9,r6,lsl#4
+	eor	r10,r10,r5,lsl#4
+	eor	r9,r9,r6,lsr#2
+	eor	r10,r10,r5,lsr#2
+	eor	r9,r9,r5,lsl#30
+	eor	r10,r10,r6,lsl#30
+	eor	r9,r9,r6,lsr#7
+	eor	r10,r10,r5,lsr#7
+	eor	r9,r9,r5,lsl#25
+	eor	r10,r10,r6,lsl#25	@ Sigma0(a)
+	adds	r3,r3,r9
+	and	r9,r5,r11
+	adc	r4,r4,r10		@ T += Sigma0(a)
+
+	ldr	r10,[sp,#8+4]	@ b.hi
+	orr	r5,r5,r11
+	ldr	r11,[sp,#16+4]	@ c.hi
+	and	r5,r5,r12
+	and	r12,r6,r10
+	orr	r6,r6,r10
+	orr	r5,r5,r9		@ Maj(a,b,c).lo
+	and	r6,r6,r11
+	adds	r5,r5,r3
+	orr	r6,r6,r12		@ Maj(a,b,c).hi
+	sub	sp,sp,#8
+	adc	r6,r6,r4		@ h += T
+	tst	r14,#1
+	add	r14,r14,#8
+	tst	r14,#1
+	beq	.L00_15
+	ldr	r9,[sp,#184+0]
+	ldr	r10,[sp,#184+4]
+	bic	r14,r14,#1
+.L16_79:
+	@ sigma0(x)	(ROTR((x),1)  ^ ROTR((x),8)  ^ ((x)>>7))
+	@ LO		lo>>1^hi<<31  ^ lo>>8^hi<<24 ^ lo>>7^hi<<25
+	@ HI		hi>>1^lo<<31  ^ hi>>8^lo<<24 ^ hi>>7
+	mov	r3,r9,lsr#1
+	ldr	r11,[sp,#80+0]
+	mov	r4,r10,lsr#1
+	ldr	r12,[sp,#80+4]
+	eor	r3,r3,r10,lsl#31
+	eor	r4,r4,r9,lsl#31
+	eor	r3,r3,r9,lsr#8
+	eor	r4,r4,r10,lsr#8
+	eor	r3,r3,r10,lsl#24
+	eor	r4,r4,r9,lsl#24
+	eor	r3,r3,r9,lsr#7
+	eor	r4,r4,r10,lsr#7
+	eor	r3,r3,r10,lsl#25
+
+	@ sigma1(x)	(ROTR((x),19) ^ ROTR((x),61) ^ ((x)>>6))
+	@ LO		lo>>19^hi<<13 ^ hi>>29^lo<<3 ^ lo>>6^hi<<26
+	@ HI		hi>>19^lo<<13 ^ lo>>29^hi<<3 ^ hi>>6
+	mov	r9,r11,lsr#19
+	mov	r10,r12,lsr#19
+	eor	r9,r9,r12,lsl#13
+	eor	r10,r10,r11,lsl#13
+	eor	r9,r9,r12,lsr#29
+	eor	r10,r10,r11,lsr#29
+	eor	r9,r9,r11,lsl#3
+	eor	r10,r10,r12,lsl#3
+	eor	r9,r9,r11,lsr#6
+	eor	r10,r10,r12,lsr#6
+	ldr	r11,[sp,#120+0]
+	eor	r9,r9,r12,lsl#26
+
+	ldr	r12,[sp,#120+4]
+	adds	r3,r3,r9
+	ldr	r9,[sp,#192+0]
+	adc	r4,r4,r10
+
+	ldr	r10,[sp,#192+4]
+	adds	r3,r3,r11
+	adc	r4,r4,r12
+	adds	r3,r3,r9
+	adc	r4,r4,r10
+	@ Sigma1(x)	(ROTR((x),14) ^ ROTR((x),18)  ^ ROTR((x),41))
+	@ LO		lo>>14^hi<<18 ^ lo>>18^hi<<14 ^ hi>>9^lo<<23
+	@ HI		hi>>14^lo<<18 ^ hi>>18^lo<<14 ^ lo>>9^hi<<23
+	mov	r9,r7,lsr#14
+	str	r3,[sp,#64+0]
+	mov	r10,r8,lsr#14
+	str	r4,[sp,#64+4]
+	eor	r9,r9,r8,lsl#18
+	ldr	r11,[sp,#56+0]	@ h.lo
+	eor	r10,r10,r7,lsl#18
+	ldr	r12,[sp,#56+4]	@ h.hi
+	eor	r9,r9,r7,lsr#18
+	eor	r10,r10,r8,lsr#18
+	eor	r9,r9,r8,lsl#14
+	eor	r10,r10,r7,lsl#14
+	eor	r9,r9,r8,lsr#9
+	eor	r10,r10,r7,lsr#9
+	eor	r9,r9,r7,lsl#23
+	eor	r10,r10,r8,lsl#23	@ Sigma1(e)
+	adds	r3,r3,r9
+	ldr	r9,[sp,#40+0]	@ f.lo
+	adc	r4,r4,r10		@ T += Sigma1(e)
+	ldr	r10,[sp,#40+4]	@ f.hi
+	adds	r3,r3,r11
+	ldr	r11,[sp,#48+0]	@ g.lo
+	adc	r4,r4,r12		@ T += h
+	ldr	r12,[sp,#48+4]	@ g.hi
+
+	eor	r9,r9,r11
+	str	r7,[sp,#32+0]
+	eor	r10,r10,r12
+	str	r8,[sp,#32+4]
+	and	r9,r9,r7
+	str	r5,[sp,#0+0]
+	and	r10,r10,r8
+	str	r6,[sp,#0+4]
+	eor	r9,r9,r11
+	ldr	r11,[r14,#LO]	@ K[i].lo
+	eor	r10,r10,r12		@ Ch(e,f,g)
+	ldr	r12,[r14,#HI]	@ K[i].hi
+
+	adds	r3,r3,r9
+	ldr	r7,[sp,#24+0]	@ d.lo
+	adc	r4,r4,r10		@ T += Ch(e,f,g)
+	ldr	r8,[sp,#24+4]	@ d.hi
+	adds	r3,r3,r11
+	and	r9,r11,#0xff
+	adc	r4,r4,r12		@ T += K[i]
+	adds	r7,r7,r3
+	ldr	r11,[sp,#8+0]	@ b.lo
+	adc	r8,r8,r4		@ d += T
+	teq	r9,#23
+
+	ldr	r12,[sp,#16+0]	@ c.lo
+#if __ARM_ARCH__>=7
+	it	eq			@ Thumb2 thing, sanity check in ARM
+#endif
+	orreq	r14,r14,#1
+	@ Sigma0(x)	(ROTR((x),28) ^ ROTR((x),34) ^ ROTR((x),39))
+	@ LO		lo>>28^hi<<4  ^ hi>>2^lo<<30 ^ hi>>7^lo<<25
+	@ HI		hi>>28^lo<<4  ^ lo>>2^hi<<30 ^ lo>>7^hi<<25
+	mov	r9,r5,lsr#28
+	mov	r10,r6,lsr#28
+	eor	r9,r9,r6,lsl#4
+	eor	r10,r10,r5,lsl#4
+	eor	r9,r9,r6,lsr#2
+	eor	r10,r10,r5,lsr#2
+	eor	r9,r9,r5,lsl#30
+	eor	r10,r10,r6,lsl#30
+	eor	r9,r9,r6,lsr#7
+	eor	r10,r10,r5,lsr#7
+	eor	r9,r9,r5,lsl#25
+	eor	r10,r10,r6,lsl#25	@ Sigma0(a)
+	adds	r3,r3,r9
+	and	r9,r5,r11
+	adc	r4,r4,r10		@ T += Sigma0(a)
+
+	ldr	r10,[sp,#8+4]	@ b.hi
+	orr	r5,r5,r11
+	ldr	r11,[sp,#16+4]	@ c.hi
+	and	r5,r5,r12
+	and	r12,r6,r10
+	orr	r6,r6,r10
+	orr	r5,r5,r9		@ Maj(a,b,c).lo
+	and	r6,r6,r11
+	adds	r5,r5,r3
+	orr	r6,r6,r12		@ Maj(a,b,c).hi
+	sub	sp,sp,#8
+	adc	r6,r6,r4		@ h += T
+	tst	r14,#1
+	add	r14,r14,#8
+#if __ARM_ARCH__>=7
+	ittt	eq			@ Thumb2 thing, sanity check in ARM
+#endif
+	ldreq	r9,[sp,#184+0]
+	ldreq	r10,[sp,#184+4]
+	beq	.L16_79
+	bic	r14,r14,#1
+
+	ldr	r3,[sp,#8+0]
+	ldr	r4,[sp,#8+4]
+	ldr	r9, [r0,#0+LO]
+	ldr	r10, [r0,#0+HI]
+	ldr	r11, [r0,#8+LO]
+	ldr	r12, [r0,#8+HI]
+	adds	r9,r5,r9
+	str	r9, [r0,#0+LO]
+	adc	r10,r6,r10
+	str	r10, [r0,#0+HI]
+	adds	r11,r3,r11
+	str	r11, [r0,#8+LO]
+	adc	r12,r4,r12
+	str	r12, [r0,#8+HI]
+
+	ldr	r5,[sp,#16+0]
+	ldr	r6,[sp,#16+4]
+	ldr	r3,[sp,#24+0]
+	ldr	r4,[sp,#24+4]
+	ldr	r9, [r0,#16+LO]
+	ldr	r10, [r0,#16+HI]
+	ldr	r11, [r0,#24+LO]
+	ldr	r12, [r0,#24+HI]
+	adds	r9,r5,r9
+	str	r9, [r0,#16+LO]
+	adc	r10,r6,r10
+	str	r10, [r0,#16+HI]
+	adds	r11,r3,r11
+	str	r11, [r0,#24+LO]
+	adc	r12,r4,r12
+	str	r12, [r0,#24+HI]
+
+	ldr	r3,[sp,#40+0]
+	ldr	r4,[sp,#40+4]
+	ldr	r9, [r0,#32+LO]
+	ldr	r10, [r0,#32+HI]
+	ldr	r11, [r0,#40+LO]
+	ldr	r12, [r0,#40+HI]
+	adds	r7,r7,r9
+	str	r7,[r0,#32+LO]
+	adc	r8,r8,r10
+	str	r8,[r0,#32+HI]
+	adds	r11,r3,r11
+	str	r11, [r0,#40+LO]
+	adc	r12,r4,r12
+	str	r12, [r0,#40+HI]
+
+	ldr	r5,[sp,#48+0]
+	ldr	r6,[sp,#48+4]
+	ldr	r3,[sp,#56+0]
+	ldr	r4,[sp,#56+4]
+	ldr	r9, [r0,#48+LO]
+	ldr	r10, [r0,#48+HI]
+	ldr	r11, [r0,#56+LO]
+	ldr	r12, [r0,#56+HI]
+	adds	r9,r5,r9
+	str	r9, [r0,#48+LO]
+	adc	r10,r6,r10
+	str	r10, [r0,#48+HI]
+	adds	r11,r3,r11
+	str	r11, [r0,#56+LO]
+	adc	r12,r4,r12
+	str	r12, [r0,#56+HI]
+
+	add	sp,sp,#640
+	sub	r14,r14,#640
+
+	teq	r1,r2
+	bne	.Loop
+
+	add	sp,sp,#8*9		@ destroy frame
+#if __ARM_ARCH__>=5
+	ldmia	sp!,{r4-r12,pc}
+#else
+	ldmia	sp!,{r4-r12,lr}
+	tst	lr,#1
+	moveq	pc,lr			@ be binary compatible with V4, yet
+	.word	0xe12fff1e			@ interoperable with Thumb ISA:-)
+#endif
+.size	sha512_block_data_order,.-sha512_block_data_order
+#if __ARM_MAX_ARCH__>=7
+.arch	armv7-a
+.fpu	neon
+
+.global	sha512_block_data_order_neon
+.type	sha512_block_data_order_neon,%function
+.align	4
+sha512_block_data_order_neon:
+.LNEON:
+	dmb				@ errata #451034 on early Cortex A8
+	add	r2,r1,r2,lsl#7	@ len to point at the end of inp
+	VFP_ABI_PUSH
+	adrl	r3,K512
+	vldmia	r0,{d16-d23}		@ load context
+.Loop_neon:
+	vshr.u64	d24,d20,#14	@ 0
+#if 0<16
+	vld1.64		{d0},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d20,#18
+#if 0>0
+	 vadd.i64	d16,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d20,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d20,#50
+	vsli.64		d25,d20,#46
+	vmov		d29,d20
+	vsli.64		d26,d20,#23
+#if 0<16 && defined(__ARMEL__)
+	vrev64.8	d0,d0
+#endif
+	veor		d25,d24
+	vbsl		d29,d21,d22		@ Ch(e,f,g)
+	vshr.u64	d24,d16,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d23
+	vshr.u64	d25,d16,#34
+	vsli.64		d24,d16,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d16,#39
+	vadd.i64	d28,d0
+	vsli.64		d25,d16,#30
+	veor		d30,d16,d17
+	vsli.64		d26,d16,#25
+	veor		d23,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d18,d17		@ Maj(a,b,c)
+	veor		d23,d26			@ Sigma0(a)
+	vadd.i64	d19,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d23,d30
+	vshr.u64	d24,d19,#14	@ 1
+#if 1<16
+	vld1.64		{d1},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d19,#18
+#if 1>0
+	 vadd.i64	d23,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d19,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d19,#50
+	vsli.64		d25,d19,#46
+	vmov		d29,d19
+	vsli.64		d26,d19,#23
+#if 1<16 && defined(__ARMEL__)
+	vrev64.8	d1,d1
+#endif
+	veor		d25,d24
+	vbsl		d29,d20,d21		@ Ch(e,f,g)
+	vshr.u64	d24,d23,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d22
+	vshr.u64	d25,d23,#34
+	vsli.64		d24,d23,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d23,#39
+	vadd.i64	d28,d1
+	vsli.64		d25,d23,#30
+	veor		d30,d23,d16
+	vsli.64		d26,d23,#25
+	veor		d22,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d17,d16		@ Maj(a,b,c)
+	veor		d22,d26			@ Sigma0(a)
+	vadd.i64	d18,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d22,d30
+	vshr.u64	d24,d18,#14	@ 2
+#if 2<16
+	vld1.64		{d2},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d18,#18
+#if 2>0
+	 vadd.i64	d22,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d18,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d18,#50
+	vsli.64		d25,d18,#46
+	vmov		d29,d18
+	vsli.64		d26,d18,#23
+#if 2<16 && defined(__ARMEL__)
+	vrev64.8	d2,d2
+#endif
+	veor		d25,d24
+	vbsl		d29,d19,d20		@ Ch(e,f,g)
+	vshr.u64	d24,d22,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d21
+	vshr.u64	d25,d22,#34
+	vsli.64		d24,d22,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d22,#39
+	vadd.i64	d28,d2
+	vsli.64		d25,d22,#30
+	veor		d30,d22,d23
+	vsli.64		d26,d22,#25
+	veor		d21,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d16,d23		@ Maj(a,b,c)
+	veor		d21,d26			@ Sigma0(a)
+	vadd.i64	d17,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d21,d30
+	vshr.u64	d24,d17,#14	@ 3
+#if 3<16
+	vld1.64		{d3},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d17,#18
+#if 3>0
+	 vadd.i64	d21,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d17,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d17,#50
+	vsli.64		d25,d17,#46
+	vmov		d29,d17
+	vsli.64		d26,d17,#23
+#if 3<16 && defined(__ARMEL__)
+	vrev64.8	d3,d3
+#endif
+	veor		d25,d24
+	vbsl		d29,d18,d19		@ Ch(e,f,g)
+	vshr.u64	d24,d21,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d20
+	vshr.u64	d25,d21,#34
+	vsli.64		d24,d21,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d21,#39
+	vadd.i64	d28,d3
+	vsli.64		d25,d21,#30
+	veor		d30,d21,d22
+	vsli.64		d26,d21,#25
+	veor		d20,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d23,d22		@ Maj(a,b,c)
+	veor		d20,d26			@ Sigma0(a)
+	vadd.i64	d16,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d20,d30
+	vshr.u64	d24,d16,#14	@ 4
+#if 4<16
+	vld1.64		{d4},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d16,#18
+#if 4>0
+	 vadd.i64	d20,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d16,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d16,#50
+	vsli.64		d25,d16,#46
+	vmov		d29,d16
+	vsli.64		d26,d16,#23
+#if 4<16 && defined(__ARMEL__)
+	vrev64.8	d4,d4
+#endif
+	veor		d25,d24
+	vbsl		d29,d17,d18		@ Ch(e,f,g)
+	vshr.u64	d24,d20,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d19
+	vshr.u64	d25,d20,#34
+	vsli.64		d24,d20,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d20,#39
+	vadd.i64	d28,d4
+	vsli.64		d25,d20,#30
+	veor		d30,d20,d21
+	vsli.64		d26,d20,#25
+	veor		d19,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d22,d21		@ Maj(a,b,c)
+	veor		d19,d26			@ Sigma0(a)
+	vadd.i64	d23,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d19,d30
+	vshr.u64	d24,d23,#14	@ 5
+#if 5<16
+	vld1.64		{d5},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d23,#18
+#if 5>0
+	 vadd.i64	d19,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d23,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d23,#50
+	vsli.64		d25,d23,#46
+	vmov		d29,d23
+	vsli.64		d26,d23,#23
+#if 5<16 && defined(__ARMEL__)
+	vrev64.8	d5,d5
+#endif
+	veor		d25,d24
+	vbsl		d29,d16,d17		@ Ch(e,f,g)
+	vshr.u64	d24,d19,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d18
+	vshr.u64	d25,d19,#34
+	vsli.64		d24,d19,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d19,#39
+	vadd.i64	d28,d5
+	vsli.64		d25,d19,#30
+	veor		d30,d19,d20
+	vsli.64		d26,d19,#25
+	veor		d18,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d21,d20		@ Maj(a,b,c)
+	veor		d18,d26			@ Sigma0(a)
+	vadd.i64	d22,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d18,d30
+	vshr.u64	d24,d22,#14	@ 6
+#if 6<16
+	vld1.64		{d6},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d22,#18
+#if 6>0
+	 vadd.i64	d18,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d22,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d22,#50
+	vsli.64		d25,d22,#46
+	vmov		d29,d22
+	vsli.64		d26,d22,#23
+#if 6<16 && defined(__ARMEL__)
+	vrev64.8	d6,d6
+#endif
+	veor		d25,d24
+	vbsl		d29,d23,d16		@ Ch(e,f,g)
+	vshr.u64	d24,d18,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d17
+	vshr.u64	d25,d18,#34
+	vsli.64		d24,d18,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d18,#39
+	vadd.i64	d28,d6
+	vsli.64		d25,d18,#30
+	veor		d30,d18,d19
+	vsli.64		d26,d18,#25
+	veor		d17,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d20,d19		@ Maj(a,b,c)
+	veor		d17,d26			@ Sigma0(a)
+	vadd.i64	d21,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d17,d30
+	vshr.u64	d24,d21,#14	@ 7
+#if 7<16
+	vld1.64		{d7},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d21,#18
+#if 7>0
+	 vadd.i64	d17,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d21,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d21,#50
+	vsli.64		d25,d21,#46
+	vmov		d29,d21
+	vsli.64		d26,d21,#23
+#if 7<16 && defined(__ARMEL__)
+	vrev64.8	d7,d7
+#endif
+	veor		d25,d24
+	vbsl		d29,d22,d23		@ Ch(e,f,g)
+	vshr.u64	d24,d17,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d16
+	vshr.u64	d25,d17,#34
+	vsli.64		d24,d17,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d17,#39
+	vadd.i64	d28,d7
+	vsli.64		d25,d17,#30
+	veor		d30,d17,d18
+	vsli.64		d26,d17,#25
+	veor		d16,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d19,d18		@ Maj(a,b,c)
+	veor		d16,d26			@ Sigma0(a)
+	vadd.i64	d20,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d16,d30
+	vshr.u64	d24,d20,#14	@ 8
+#if 8<16
+	vld1.64		{d8},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d20,#18
+#if 8>0
+	 vadd.i64	d16,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d20,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d20,#50
+	vsli.64		d25,d20,#46
+	vmov		d29,d20
+	vsli.64		d26,d20,#23
+#if 8<16 && defined(__ARMEL__)
+	vrev64.8	d8,d8
+#endif
+	veor		d25,d24
+	vbsl		d29,d21,d22		@ Ch(e,f,g)
+	vshr.u64	d24,d16,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d23
+	vshr.u64	d25,d16,#34
+	vsli.64		d24,d16,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d16,#39
+	vadd.i64	d28,d8
+	vsli.64		d25,d16,#30
+	veor		d30,d16,d17
+	vsli.64		d26,d16,#25
+	veor		d23,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d18,d17		@ Maj(a,b,c)
+	veor		d23,d26			@ Sigma0(a)
+	vadd.i64	d19,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d23,d30
+	vshr.u64	d24,d19,#14	@ 9
+#if 9<16
+	vld1.64		{d9},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d19,#18
+#if 9>0
+	 vadd.i64	d23,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d19,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d19,#50
+	vsli.64		d25,d19,#46
+	vmov		d29,d19
+	vsli.64		d26,d19,#23
+#if 9<16 && defined(__ARMEL__)
+	vrev64.8	d9,d9
+#endif
+	veor		d25,d24
+	vbsl		d29,d20,d21		@ Ch(e,f,g)
+	vshr.u64	d24,d23,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d22
+	vshr.u64	d25,d23,#34
+	vsli.64		d24,d23,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d23,#39
+	vadd.i64	d28,d9
+	vsli.64		d25,d23,#30
+	veor		d30,d23,d16
+	vsli.64		d26,d23,#25
+	veor		d22,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d17,d16		@ Maj(a,b,c)
+	veor		d22,d26			@ Sigma0(a)
+	vadd.i64	d18,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d22,d30
+	vshr.u64	d24,d18,#14	@ 10
+#if 10<16
+	vld1.64		{d10},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d18,#18
+#if 10>0
+	 vadd.i64	d22,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d18,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d18,#50
+	vsli.64		d25,d18,#46
+	vmov		d29,d18
+	vsli.64		d26,d18,#23
+#if 10<16 && defined(__ARMEL__)
+	vrev64.8	d10,d10
+#endif
+	veor		d25,d24
+	vbsl		d29,d19,d20		@ Ch(e,f,g)
+	vshr.u64	d24,d22,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d21
+	vshr.u64	d25,d22,#34
+	vsli.64		d24,d22,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d22,#39
+	vadd.i64	d28,d10
+	vsli.64		d25,d22,#30
+	veor		d30,d22,d23
+	vsli.64		d26,d22,#25
+	veor		d21,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d16,d23		@ Maj(a,b,c)
+	veor		d21,d26			@ Sigma0(a)
+	vadd.i64	d17,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d21,d30
+	vshr.u64	d24,d17,#14	@ 11
+#if 11<16
+	vld1.64		{d11},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d17,#18
+#if 11>0
+	 vadd.i64	d21,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d17,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d17,#50
+	vsli.64		d25,d17,#46
+	vmov		d29,d17
+	vsli.64		d26,d17,#23
+#if 11<16 && defined(__ARMEL__)
+	vrev64.8	d11,d11
+#endif
+	veor		d25,d24
+	vbsl		d29,d18,d19		@ Ch(e,f,g)
+	vshr.u64	d24,d21,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d20
+	vshr.u64	d25,d21,#34
+	vsli.64		d24,d21,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d21,#39
+	vadd.i64	d28,d11
+	vsli.64		d25,d21,#30
+	veor		d30,d21,d22
+	vsli.64		d26,d21,#25
+	veor		d20,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d23,d22		@ Maj(a,b,c)
+	veor		d20,d26			@ Sigma0(a)
+	vadd.i64	d16,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d20,d30
+	vshr.u64	d24,d16,#14	@ 12
+#if 12<16
+	vld1.64		{d12},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d16,#18
+#if 12>0
+	 vadd.i64	d20,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d16,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d16,#50
+	vsli.64		d25,d16,#46
+	vmov		d29,d16
+	vsli.64		d26,d16,#23
+#if 12<16 && defined(__ARMEL__)
+	vrev64.8	d12,d12
+#endif
+	veor		d25,d24
+	vbsl		d29,d17,d18		@ Ch(e,f,g)
+	vshr.u64	d24,d20,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d19
+	vshr.u64	d25,d20,#34
+	vsli.64		d24,d20,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d20,#39
+	vadd.i64	d28,d12
+	vsli.64		d25,d20,#30
+	veor		d30,d20,d21
+	vsli.64		d26,d20,#25
+	veor		d19,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d22,d21		@ Maj(a,b,c)
+	veor		d19,d26			@ Sigma0(a)
+	vadd.i64	d23,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d19,d30
+	vshr.u64	d24,d23,#14	@ 13
+#if 13<16
+	vld1.64		{d13},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d23,#18
+#if 13>0
+	 vadd.i64	d19,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d23,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d23,#50
+	vsli.64		d25,d23,#46
+	vmov		d29,d23
+	vsli.64		d26,d23,#23
+#if 13<16 && defined(__ARMEL__)
+	vrev64.8	d13,d13
+#endif
+	veor		d25,d24
+	vbsl		d29,d16,d17		@ Ch(e,f,g)
+	vshr.u64	d24,d19,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d18
+	vshr.u64	d25,d19,#34
+	vsli.64		d24,d19,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d19,#39
+	vadd.i64	d28,d13
+	vsli.64		d25,d19,#30
+	veor		d30,d19,d20
+	vsli.64		d26,d19,#25
+	veor		d18,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d21,d20		@ Maj(a,b,c)
+	veor		d18,d26			@ Sigma0(a)
+	vadd.i64	d22,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d18,d30
+	vshr.u64	d24,d22,#14	@ 14
+#if 14<16
+	vld1.64		{d14},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d22,#18
+#if 14>0
+	 vadd.i64	d18,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d22,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d22,#50
+	vsli.64		d25,d22,#46
+	vmov		d29,d22
+	vsli.64		d26,d22,#23
+#if 14<16 && defined(__ARMEL__)
+	vrev64.8	d14,d14
+#endif
+	veor		d25,d24
+	vbsl		d29,d23,d16		@ Ch(e,f,g)
+	vshr.u64	d24,d18,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d17
+	vshr.u64	d25,d18,#34
+	vsli.64		d24,d18,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d18,#39
+	vadd.i64	d28,d14
+	vsli.64		d25,d18,#30
+	veor		d30,d18,d19
+	vsli.64		d26,d18,#25
+	veor		d17,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d20,d19		@ Maj(a,b,c)
+	veor		d17,d26			@ Sigma0(a)
+	vadd.i64	d21,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d17,d30
+	vshr.u64	d24,d21,#14	@ 15
+#if 15<16
+	vld1.64		{d15},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d21,#18
+#if 15>0
+	 vadd.i64	d17,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d21,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d21,#50
+	vsli.64		d25,d21,#46
+	vmov		d29,d21
+	vsli.64		d26,d21,#23
+#if 15<16 && defined(__ARMEL__)
+	vrev64.8	d15,d15
+#endif
+	veor		d25,d24
+	vbsl		d29,d22,d23		@ Ch(e,f,g)
+	vshr.u64	d24,d17,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d16
+	vshr.u64	d25,d17,#34
+	vsli.64		d24,d17,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d17,#39
+	vadd.i64	d28,d15
+	vsli.64		d25,d17,#30
+	veor		d30,d17,d18
+	vsli.64		d26,d17,#25
+	veor		d16,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d19,d18		@ Maj(a,b,c)
+	veor		d16,d26			@ Sigma0(a)
+	vadd.i64	d20,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d16,d30
+	mov		r12,#4
+.L16_79_neon:
+	subs		r12,#1
+	vshr.u64	q12,q7,#19
+	vshr.u64	q13,q7,#61
+	 vadd.i64	d16,d30			@ h+=Maj from the past
+	vshr.u64	q15,q7,#6
+	vsli.64		q12,q7,#45
+	vext.8		q14,q0,q1,#8	@ X[i+1]
+	vsli.64		q13,q7,#3
+	veor		q15,q12
+	vshr.u64	q12,q14,#1
+	veor		q15,q13				@ sigma1(X[i+14])
+	vshr.u64	q13,q14,#8
+	vadd.i64	q0,q15
+	vshr.u64	q15,q14,#7
+	vsli.64		q12,q14,#63
+	vsli.64		q13,q14,#56
+	vext.8		q14,q4,q5,#8	@ X[i+9]
+	veor		q15,q12
+	vshr.u64	d24,d20,#14		@ from NEON_00_15
+	vadd.i64	q0,q14
+	vshr.u64	d25,d20,#18		@ from NEON_00_15
+	veor		q15,q13				@ sigma0(X[i+1])
+	vshr.u64	d26,d20,#41		@ from NEON_00_15
+	vadd.i64	q0,q15
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d20,#50
+	vsli.64		d25,d20,#46
+	vmov		d29,d20
+	vsli.64		d26,d20,#23
+#if 16<16 && defined(__ARMEL__)
+	vrev64.8	,
+#endif
+	veor		d25,d24
+	vbsl		d29,d21,d22		@ Ch(e,f,g)
+	vshr.u64	d24,d16,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d23
+	vshr.u64	d25,d16,#34
+	vsli.64		d24,d16,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d16,#39
+	vadd.i64	d28,d0
+	vsli.64		d25,d16,#30
+	veor		d30,d16,d17
+	vsli.64		d26,d16,#25
+	veor		d23,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d18,d17		@ Maj(a,b,c)
+	veor		d23,d26			@ Sigma0(a)
+	vadd.i64	d19,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d23,d30
+	vshr.u64	d24,d19,#14	@ 17
+#if 17<16
+	vld1.64		{d1},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d19,#18
+#if 17>0
+	 vadd.i64	d23,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d19,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d19,#50
+	vsli.64		d25,d19,#46
+	vmov		d29,d19
+	vsli.64		d26,d19,#23
+#if 17<16 && defined(__ARMEL__)
+	vrev64.8	,
+#endif
+	veor		d25,d24
+	vbsl		d29,d20,d21		@ Ch(e,f,g)
+	vshr.u64	d24,d23,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d22
+	vshr.u64	d25,d23,#34
+	vsli.64		d24,d23,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d23,#39
+	vadd.i64	d28,d1
+	vsli.64		d25,d23,#30
+	veor		d30,d23,d16
+	vsli.64		d26,d23,#25
+	veor		d22,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d17,d16		@ Maj(a,b,c)
+	veor		d22,d26			@ Sigma0(a)
+	vadd.i64	d18,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d22,d30
+	vshr.u64	q12,q0,#19
+	vshr.u64	q13,q0,#61
+	 vadd.i64	d22,d30			@ h+=Maj from the past
+	vshr.u64	q15,q0,#6
+	vsli.64		q12,q0,#45
+	vext.8		q14,q1,q2,#8	@ X[i+1]
+	vsli.64		q13,q0,#3
+	veor		q15,q12
+	vshr.u64	q12,q14,#1
+	veor		q15,q13				@ sigma1(X[i+14])
+	vshr.u64	q13,q14,#8
+	vadd.i64	q1,q15
+	vshr.u64	q15,q14,#7
+	vsli.64		q12,q14,#63
+	vsli.64		q13,q14,#56
+	vext.8		q14,q5,q6,#8	@ X[i+9]
+	veor		q15,q12
+	vshr.u64	d24,d18,#14		@ from NEON_00_15
+	vadd.i64	q1,q14
+	vshr.u64	d25,d18,#18		@ from NEON_00_15
+	veor		q15,q13				@ sigma0(X[i+1])
+	vshr.u64	d26,d18,#41		@ from NEON_00_15
+	vadd.i64	q1,q15
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d18,#50
+	vsli.64		d25,d18,#46
+	vmov		d29,d18
+	vsli.64		d26,d18,#23
+#if 18<16 && defined(__ARMEL__)
+	vrev64.8	,
+#endif
+	veor		d25,d24
+	vbsl		d29,d19,d20		@ Ch(e,f,g)
+	vshr.u64	d24,d22,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d21
+	vshr.u64	d25,d22,#34
+	vsli.64		d24,d22,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d22,#39
+	vadd.i64	d28,d2
+	vsli.64		d25,d22,#30
+	veor		d30,d22,d23
+	vsli.64		d26,d22,#25
+	veor		d21,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d16,d23		@ Maj(a,b,c)
+	veor		d21,d26			@ Sigma0(a)
+	vadd.i64	d17,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d21,d30
+	vshr.u64	d24,d17,#14	@ 19
+#if 19<16
+	vld1.64		{d3},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d17,#18
+#if 19>0
+	 vadd.i64	d21,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d17,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d17,#50
+	vsli.64		d25,d17,#46
+	vmov		d29,d17
+	vsli.64		d26,d17,#23
+#if 19<16 && defined(__ARMEL__)
+	vrev64.8	,
+#endif
+	veor		d25,d24
+	vbsl		d29,d18,d19		@ Ch(e,f,g)
+	vshr.u64	d24,d21,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d20
+	vshr.u64	d25,d21,#34
+	vsli.64		d24,d21,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d21,#39
+	vadd.i64	d28,d3
+	vsli.64		d25,d21,#30
+	veor		d30,d21,d22
+	vsli.64		d26,d21,#25
+	veor		d20,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d23,d22		@ Maj(a,b,c)
+	veor		d20,d26			@ Sigma0(a)
+	vadd.i64	d16,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d20,d30
+	vshr.u64	q12,q1,#19
+	vshr.u64	q13,q1,#61
+	 vadd.i64	d20,d30			@ h+=Maj from the past
+	vshr.u64	q15,q1,#6
+	vsli.64		q12,q1,#45
+	vext.8		q14,q2,q3,#8	@ X[i+1]
+	vsli.64		q13,q1,#3
+	veor		q15,q12
+	vshr.u64	q12,q14,#1
+	veor		q15,q13				@ sigma1(X[i+14])
+	vshr.u64	q13,q14,#8
+	vadd.i64	q2,q15
+	vshr.u64	q15,q14,#7
+	vsli.64		q12,q14,#63
+	vsli.64		q13,q14,#56
+	vext.8		q14,q6,q7,#8	@ X[i+9]
+	veor		q15,q12
+	vshr.u64	d24,d16,#14		@ from NEON_00_15
+	vadd.i64	q2,q14
+	vshr.u64	d25,d16,#18		@ from NEON_00_15
+	veor		q15,q13				@ sigma0(X[i+1])
+	vshr.u64	d26,d16,#41		@ from NEON_00_15
+	vadd.i64	q2,q15
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d16,#50
+	vsli.64		d25,d16,#46
+	vmov		d29,d16
+	vsli.64		d26,d16,#23
+#if 20<16 && defined(__ARMEL__)
+	vrev64.8	,
+#endif
+	veor		d25,d24
+	vbsl		d29,d17,d18		@ Ch(e,f,g)
+	vshr.u64	d24,d20,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d19
+	vshr.u64	d25,d20,#34
+	vsli.64		d24,d20,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d20,#39
+	vadd.i64	d28,d4
+	vsli.64		d25,d20,#30
+	veor		d30,d20,d21
+	vsli.64		d26,d20,#25
+	veor		d19,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d22,d21		@ Maj(a,b,c)
+	veor		d19,d26			@ Sigma0(a)
+	vadd.i64	d23,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d19,d30
+	vshr.u64	d24,d23,#14	@ 21
+#if 21<16
+	vld1.64		{d5},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d23,#18
+#if 21>0
+	 vadd.i64	d19,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d23,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d23,#50
+	vsli.64		d25,d23,#46
+	vmov		d29,d23
+	vsli.64		d26,d23,#23
+#if 21<16 && defined(__ARMEL__)
+	vrev64.8	,
+#endif
+	veor		d25,d24
+	vbsl		d29,d16,d17		@ Ch(e,f,g)
+	vshr.u64	d24,d19,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d18
+	vshr.u64	d25,d19,#34
+	vsli.64		d24,d19,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d19,#39
+	vadd.i64	d28,d5
+	vsli.64		d25,d19,#30
+	veor		d30,d19,d20
+	vsli.64		d26,d19,#25
+	veor		d18,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d21,d20		@ Maj(a,b,c)
+	veor		d18,d26			@ Sigma0(a)
+	vadd.i64	d22,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d18,d30
+	vshr.u64	q12,q2,#19
+	vshr.u64	q13,q2,#61
+	 vadd.i64	d18,d30			@ h+=Maj from the past
+	vshr.u64	q15,q2,#6
+	vsli.64		q12,q2,#45
+	vext.8		q14,q3,q4,#8	@ X[i+1]
+	vsli.64		q13,q2,#3
+	veor		q15,q12
+	vshr.u64	q12,q14,#1
+	veor		q15,q13				@ sigma1(X[i+14])
+	vshr.u64	q13,q14,#8
+	vadd.i64	q3,q15
+	vshr.u64	q15,q14,#7
+	vsli.64		q12,q14,#63
+	vsli.64		q13,q14,#56
+	vext.8		q14,q7,q0,#8	@ X[i+9]
+	veor		q15,q12
+	vshr.u64	d24,d22,#14		@ from NEON_00_15
+	vadd.i64	q3,q14
+	vshr.u64	d25,d22,#18		@ from NEON_00_15
+	veor		q15,q13				@ sigma0(X[i+1])
+	vshr.u64	d26,d22,#41		@ from NEON_00_15
+	vadd.i64	q3,q15
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d22,#50
+	vsli.64		d25,d22,#46
+	vmov		d29,d22
+	vsli.64		d26,d22,#23
+#if 22<16 && defined(__ARMEL__)
+	vrev64.8	,
+#endif
+	veor		d25,d24
+	vbsl		d29,d23,d16		@ Ch(e,f,g)
+	vshr.u64	d24,d18,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d17
+	vshr.u64	d25,d18,#34
+	vsli.64		d24,d18,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d18,#39
+	vadd.i64	d28,d6
+	vsli.64		d25,d18,#30
+	veor		d30,d18,d19
+	vsli.64		d26,d18,#25
+	veor		d17,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d20,d19		@ Maj(a,b,c)
+	veor		d17,d26			@ Sigma0(a)
+	vadd.i64	d21,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d17,d30
+	vshr.u64	d24,d21,#14	@ 23
+#if 23<16
+	vld1.64		{d7},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d21,#18
+#if 23>0
+	 vadd.i64	d17,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d21,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d21,#50
+	vsli.64		d25,d21,#46
+	vmov		d29,d21
+	vsli.64		d26,d21,#23
+#if 23<16 && defined(__ARMEL__)
+	vrev64.8	,
+#endif
+	veor		d25,d24
+	vbsl		d29,d22,d23		@ Ch(e,f,g)
+	vshr.u64	d24,d17,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d16
+	vshr.u64	d25,d17,#34
+	vsli.64		d24,d17,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d17,#39
+	vadd.i64	d28,d7
+	vsli.64		d25,d17,#30
+	veor		d30,d17,d18
+	vsli.64		d26,d17,#25
+	veor		d16,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d19,d18		@ Maj(a,b,c)
+	veor		d16,d26			@ Sigma0(a)
+	vadd.i64	d20,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d16,d30
+	vshr.u64	q12,q3,#19
+	vshr.u64	q13,q3,#61
+	 vadd.i64	d16,d30			@ h+=Maj from the past
+	vshr.u64	q15,q3,#6
+	vsli.64		q12,q3,#45
+	vext.8		q14,q4,q5,#8	@ X[i+1]
+	vsli.64		q13,q3,#3
+	veor		q15,q12
+	vshr.u64	q12,q14,#1
+	veor		q15,q13				@ sigma1(X[i+14])
+	vshr.u64	q13,q14,#8
+	vadd.i64	q4,q15
+	vshr.u64	q15,q14,#7
+	vsli.64		q12,q14,#63
+	vsli.64		q13,q14,#56
+	vext.8		q14,q0,q1,#8	@ X[i+9]
+	veor		q15,q12
+	vshr.u64	d24,d20,#14		@ from NEON_00_15
+	vadd.i64	q4,q14
+	vshr.u64	d25,d20,#18		@ from NEON_00_15
+	veor		q15,q13				@ sigma0(X[i+1])
+	vshr.u64	d26,d20,#41		@ from NEON_00_15
+	vadd.i64	q4,q15
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d20,#50
+	vsli.64		d25,d20,#46
+	vmov		d29,d20
+	vsli.64		d26,d20,#23
+#if 24<16 && defined(__ARMEL__)
+	vrev64.8	,
+#endif
+	veor		d25,d24
+	vbsl		d29,d21,d22		@ Ch(e,f,g)
+	vshr.u64	d24,d16,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d23
+	vshr.u64	d25,d16,#34
+	vsli.64		d24,d16,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d16,#39
+	vadd.i64	d28,d8
+	vsli.64		d25,d16,#30
+	veor		d30,d16,d17
+	vsli.64		d26,d16,#25
+	veor		d23,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d18,d17		@ Maj(a,b,c)
+	veor		d23,d26			@ Sigma0(a)
+	vadd.i64	d19,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d23,d30
+	vshr.u64	d24,d19,#14	@ 25
+#if 25<16
+	vld1.64		{d9},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d19,#18
+#if 25>0
+	 vadd.i64	d23,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d19,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d19,#50
+	vsli.64		d25,d19,#46
+	vmov		d29,d19
+	vsli.64		d26,d19,#23
+#if 25<16 && defined(__ARMEL__)
+	vrev64.8	,
+#endif
+	veor		d25,d24
+	vbsl		d29,d20,d21		@ Ch(e,f,g)
+	vshr.u64	d24,d23,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d22
+	vshr.u64	d25,d23,#34
+	vsli.64		d24,d23,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d23,#39
+	vadd.i64	d28,d9
+	vsli.64		d25,d23,#30
+	veor		d30,d23,d16
+	vsli.64		d26,d23,#25
+	veor		d22,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d17,d16		@ Maj(a,b,c)
+	veor		d22,d26			@ Sigma0(a)
+	vadd.i64	d18,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d22,d30
+	vshr.u64	q12,q4,#19
+	vshr.u64	q13,q4,#61
+	 vadd.i64	d22,d30			@ h+=Maj from the past
+	vshr.u64	q15,q4,#6
+	vsli.64		q12,q4,#45
+	vext.8		q14,q5,q6,#8	@ X[i+1]
+	vsli.64		q13,q4,#3
+	veor		q15,q12
+	vshr.u64	q12,q14,#1
+	veor		q15,q13				@ sigma1(X[i+14])
+	vshr.u64	q13,q14,#8
+	vadd.i64	q5,q15
+	vshr.u64	q15,q14,#7
+	vsli.64		q12,q14,#63
+	vsli.64		q13,q14,#56
+	vext.8		q14,q1,q2,#8	@ X[i+9]
+	veor		q15,q12
+	vshr.u64	d24,d18,#14		@ from NEON_00_15
+	vadd.i64	q5,q14
+	vshr.u64	d25,d18,#18		@ from NEON_00_15
+	veor		q15,q13				@ sigma0(X[i+1])
+	vshr.u64	d26,d18,#41		@ from NEON_00_15
+	vadd.i64	q5,q15
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d18,#50
+	vsli.64		d25,d18,#46
+	vmov		d29,d18
+	vsli.64		d26,d18,#23
+#if 26<16 && defined(__ARMEL__)
+	vrev64.8	,
+#endif
+	veor		d25,d24
+	vbsl		d29,d19,d20		@ Ch(e,f,g)
+	vshr.u64	d24,d22,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d21
+	vshr.u64	d25,d22,#34
+	vsli.64		d24,d22,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d22,#39
+	vadd.i64	d28,d10
+	vsli.64		d25,d22,#30
+	veor		d30,d22,d23
+	vsli.64		d26,d22,#25
+	veor		d21,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d16,d23		@ Maj(a,b,c)
+	veor		d21,d26			@ Sigma0(a)
+	vadd.i64	d17,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d21,d30
+	vshr.u64	d24,d17,#14	@ 27
+#if 27<16
+	vld1.64		{d11},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d17,#18
+#if 27>0
+	 vadd.i64	d21,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d17,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d17,#50
+	vsli.64		d25,d17,#46
+	vmov		d29,d17
+	vsli.64		d26,d17,#23
+#if 27<16 && defined(__ARMEL__)
+	vrev64.8	,
+#endif
+	veor		d25,d24
+	vbsl		d29,d18,d19		@ Ch(e,f,g)
+	vshr.u64	d24,d21,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d20
+	vshr.u64	d25,d21,#34
+	vsli.64		d24,d21,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d21,#39
+	vadd.i64	d28,d11
+	vsli.64		d25,d21,#30
+	veor		d30,d21,d22
+	vsli.64		d26,d21,#25
+	veor		d20,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d23,d22		@ Maj(a,b,c)
+	veor		d20,d26			@ Sigma0(a)
+	vadd.i64	d16,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d20,d30
+	vshr.u64	q12,q5,#19
+	vshr.u64	q13,q5,#61
+	 vadd.i64	d20,d30			@ h+=Maj from the past
+	vshr.u64	q15,q5,#6
+	vsli.64		q12,q5,#45
+	vext.8		q14,q6,q7,#8	@ X[i+1]
+	vsli.64		q13,q5,#3
+	veor		q15,q12
+	vshr.u64	q12,q14,#1
+	veor		q15,q13				@ sigma1(X[i+14])
+	vshr.u64	q13,q14,#8
+	vadd.i64	q6,q15
+	vshr.u64	q15,q14,#7
+	vsli.64		q12,q14,#63
+	vsli.64		q13,q14,#56
+	vext.8		q14,q2,q3,#8	@ X[i+9]
+	veor		q15,q12
+	vshr.u64	d24,d16,#14		@ from NEON_00_15
+	vadd.i64	q6,q14
+	vshr.u64	d25,d16,#18		@ from NEON_00_15
+	veor		q15,q13				@ sigma0(X[i+1])
+	vshr.u64	d26,d16,#41		@ from NEON_00_15
+	vadd.i64	q6,q15
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d16,#50
+	vsli.64		d25,d16,#46
+	vmov		d29,d16
+	vsli.64		d26,d16,#23
+#if 28<16 && defined(__ARMEL__)
+	vrev64.8	,
+#endif
+	veor		d25,d24
+	vbsl		d29,d17,d18		@ Ch(e,f,g)
+	vshr.u64	d24,d20,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d19
+	vshr.u64	d25,d20,#34
+	vsli.64		d24,d20,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d20,#39
+	vadd.i64	d28,d12
+	vsli.64		d25,d20,#30
+	veor		d30,d20,d21
+	vsli.64		d26,d20,#25
+	veor		d19,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d22,d21		@ Maj(a,b,c)
+	veor		d19,d26			@ Sigma0(a)
+	vadd.i64	d23,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d19,d30
+	vshr.u64	d24,d23,#14	@ 29
+#if 29<16
+	vld1.64		{d13},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d23,#18
+#if 29>0
+	 vadd.i64	d19,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d23,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d23,#50
+	vsli.64		d25,d23,#46
+	vmov		d29,d23
+	vsli.64		d26,d23,#23
+#if 29<16 && defined(__ARMEL__)
+	vrev64.8	,
+#endif
+	veor		d25,d24
+	vbsl		d29,d16,d17		@ Ch(e,f,g)
+	vshr.u64	d24,d19,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d18
+	vshr.u64	d25,d19,#34
+	vsli.64		d24,d19,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d19,#39
+	vadd.i64	d28,d13
+	vsli.64		d25,d19,#30
+	veor		d30,d19,d20
+	vsli.64		d26,d19,#25
+	veor		d18,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d21,d20		@ Maj(a,b,c)
+	veor		d18,d26			@ Sigma0(a)
+	vadd.i64	d22,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d18,d30
+	vshr.u64	q12,q6,#19
+	vshr.u64	q13,q6,#61
+	 vadd.i64	d18,d30			@ h+=Maj from the past
+	vshr.u64	q15,q6,#6
+	vsli.64		q12,q6,#45
+	vext.8		q14,q7,q0,#8	@ X[i+1]
+	vsli.64		q13,q6,#3
+	veor		q15,q12
+	vshr.u64	q12,q14,#1
+	veor		q15,q13				@ sigma1(X[i+14])
+	vshr.u64	q13,q14,#8
+	vadd.i64	q7,q15
+	vshr.u64	q15,q14,#7
+	vsli.64		q12,q14,#63
+	vsli.64		q13,q14,#56
+	vext.8		q14,q3,q4,#8	@ X[i+9]
+	veor		q15,q12
+	vshr.u64	d24,d22,#14		@ from NEON_00_15
+	vadd.i64	q7,q14
+	vshr.u64	d25,d22,#18		@ from NEON_00_15
+	veor		q15,q13				@ sigma0(X[i+1])
+	vshr.u64	d26,d22,#41		@ from NEON_00_15
+	vadd.i64	q7,q15
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d22,#50
+	vsli.64		d25,d22,#46
+	vmov		d29,d22
+	vsli.64		d26,d22,#23
+#if 30<16 && defined(__ARMEL__)
+	vrev64.8	,
+#endif
+	veor		d25,d24
+	vbsl		d29,d23,d16		@ Ch(e,f,g)
+	vshr.u64	d24,d18,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d17
+	vshr.u64	d25,d18,#34
+	vsli.64		d24,d18,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d18,#39
+	vadd.i64	d28,d14
+	vsli.64		d25,d18,#30
+	veor		d30,d18,d19
+	vsli.64		d26,d18,#25
+	veor		d17,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d20,d19		@ Maj(a,b,c)
+	veor		d17,d26			@ Sigma0(a)
+	vadd.i64	d21,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d17,d30
+	vshr.u64	d24,d21,#14	@ 31
+#if 31<16
+	vld1.64		{d15},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d21,#18
+#if 31>0
+	 vadd.i64	d17,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d21,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d21,#50
+	vsli.64		d25,d21,#46
+	vmov		d29,d21
+	vsli.64		d26,d21,#23
+#if 31<16 && defined(__ARMEL__)
+	vrev64.8	,
+#endif
+	veor		d25,d24
+	vbsl		d29,d22,d23		@ Ch(e,f,g)
+	vshr.u64	d24,d17,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d16
+	vshr.u64	d25,d17,#34
+	vsli.64		d24,d17,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d17,#39
+	vadd.i64	d28,d15
+	vsli.64		d25,d17,#30
+	veor		d30,d17,d18
+	vsli.64		d26,d17,#25
+	veor		d16,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d19,d18		@ Maj(a,b,c)
+	veor		d16,d26			@ Sigma0(a)
+	vadd.i64	d20,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d16,d30
+	bne		.L16_79_neon
+
+	 vadd.i64	d16,d30		@ h+=Maj from the past
+	vldmia		r0,{d24-d31}	@ load context to temp
+	vadd.i64	q8,q12		@ vectorized accumulate
+	vadd.i64	q9,q13
+	vadd.i64	q10,q14
+	vadd.i64	q11,q15
+	vstmia		r0,{d16-d23}	@ save context
+	teq		r1,r2
+	sub		r3,#640	@ rewind K512
+	bne		.Loop_neon
+
+	VFP_ABI_POP
+	bx	lr				@ .word	0xe12fff1e
+.size	sha512_block_data_order_neon,.-sha512_block_data_order_neon
+#endif
+.asciz	"SHA512 block transform for ARMv4/NEON, CRYPTOGAMS by <appro@openssl.org>"
+.align	2
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+.comm	OPENSSL_armcap_P,4,4
+#endif
diff --git a/arch/arm/crypto/sha512-glue.c b/arch/arm/crypto/sha512-glue.c
new file mode 100644
index 000000000000..269a394e4a53
--- /dev/null
+++ b/arch/arm/crypto/sha512-glue.c
@@ -0,0 +1,121 @@
+/*
+ * sha512-glue.c - accelerated SHA-384/512 for ARM
+ *
+ * Copyright (C) 2015 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <crypto/internal/hash.h>
+#include <crypto/sha.h>
+#include <crypto/sha512_base.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+#include <asm/hwcap.h>
+#include <asm/neon.h>
+
+#include "sha512.h"
+
+MODULE_DESCRIPTION("Accelerated SHA-384/SHA-512 secure hash for ARM");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+
+MODULE_ALIAS_CRYPTO("sha384");
+MODULE_ALIAS_CRYPTO("sha512");
+MODULE_ALIAS_CRYPTO("sha384-arm");
+MODULE_ALIAS_CRYPTO("sha512-arm");
+
+asmlinkage void sha512_block_data_order(u64 *state, u8 const *src, int blocks);
+
+int sha512_arm_update(struct shash_desc *desc, const u8 *data,
+		      unsigned int len)
+{
+	return sha512_base_do_update(desc, data, len,
+		(sha512_block_fn *)sha512_block_data_order);
+}
+
+int sha512_arm_final(struct shash_desc *desc, u8 *out)
+{
+	sha512_base_do_finalize(desc,
+		(sha512_block_fn *)sha512_block_data_order);
+	return sha512_base_finish(desc, out);
+}
+
+int sha512_arm_finup(struct shash_desc *desc, const u8 *data,
+		     unsigned int len, u8 *out)
+{
+	sha512_base_do_update(desc, data, len,
+		(sha512_block_fn *)sha512_block_data_order);
+	return sha512_arm_final(desc, out);
+}
+
+static struct shash_alg sha512_arm_algs[] = { {
+	.init			= sha384_base_init,
+	.update			= sha512_arm_update,
+	.final			= sha512_arm_final,
+	.finup			= sha512_arm_finup,
+	.descsize		= sizeof(struct sha512_state),
+	.digestsize		= SHA384_DIGEST_SIZE,
+	.base			= {
+		.cra_name		= "sha384",
+		.cra_driver_name	= "sha384-arm",
+		.cra_priority		= 250,
+		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
+		.cra_blocksize		= SHA512_BLOCK_SIZE,
+		.cra_module		= THIS_MODULE,
+	}
+},  {
+	.init			= sha512_base_init,
+	.update			= sha512_arm_update,
+	.final			= sha512_arm_final,
+	.finup			= sha512_arm_finup,
+	.descsize		= sizeof(struct sha512_state),
+	.digestsize		= SHA512_DIGEST_SIZE,
+	.base			= {
+		.cra_name		= "sha512",
+		.cra_driver_name	= "sha512-arm",
+		.cra_priority		= 250,
+		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
+		.cra_blocksize		= SHA512_BLOCK_SIZE,
+		.cra_module		= THIS_MODULE,
+	}
+} };
+
+static int __init sha512_arm_mod_init(void)
+{
+	int err;
+
+	err = crypto_register_shashes(sha512_arm_algs,
+				      ARRAY_SIZE(sha512_arm_algs));
+	if (err)
+		return err;
+
+	if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && cpu_has_neon()) {
+		err = crypto_register_shashes(sha512_neon_algs,
+					      ARRAY_SIZE(sha512_neon_algs));
+		if (err)
+			goto err_unregister;
+	}
+	return 0;
+
+err_unregister:
+	crypto_unregister_shashes(sha512_arm_algs,
+				  ARRAY_SIZE(sha512_arm_algs));
+
+	return err;
+}
+
+static void __exit sha512_arm_mod_fini(void)
+{
+	crypto_unregister_shashes(sha512_arm_algs,
+				  ARRAY_SIZE(sha512_arm_algs));
+	if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && cpu_has_neon())
+		crypto_unregister_shashes(sha512_neon_algs,
+					  ARRAY_SIZE(sha512_neon_algs));
+}
+
+module_init(sha512_arm_mod_init);
+module_exit(sha512_arm_mod_fini);
diff --git a/arch/arm/crypto/sha512-neon-glue.c b/arch/arm/crypto/sha512-neon-glue.c
new file mode 100644
index 000000000000..32693684a3ab
--- /dev/null
+++ b/arch/arm/crypto/sha512-neon-glue.c
@@ -0,0 +1,98 @@
+/*
+ * sha512-neon-glue.c - accelerated SHA-384/512 for ARM NEON
+ *
+ * Copyright (C) 2015 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <crypto/internal/hash.h>
+#include <crypto/sha.h>
+#include <crypto/sha512_base.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+#include <asm/simd.h>
+#include <asm/neon.h>
+
+#include "sha512.h"
+
+MODULE_ALIAS_CRYPTO("sha384-neon");
+MODULE_ALIAS_CRYPTO("sha512-neon");
+
+asmlinkage void sha512_block_data_order_neon(u64 *state, u8 const *src,
+					     int blocks);
+
+static int sha512_neon_update(struct shash_desc *desc, const u8 *data,
+			      unsigned int len)
+{
+	struct sha512_state *sctx = shash_desc_ctx(desc);
+
+	if (!may_use_simd() ||
+	    (sctx->count[0] % SHA512_BLOCK_SIZE) + len < SHA512_BLOCK_SIZE)
+		return sha512_arm_update(desc, data, len);
+
+	kernel_neon_begin();
+	sha512_base_do_update(desc, data, len,
+		(sha512_block_fn *)sha512_block_data_order_neon);
+	kernel_neon_end();
+
+	return 0;
+}
+
+static int sha512_neon_finup(struct shash_desc *desc, const u8 *data,
+			     unsigned int len, u8 *out)
+{
+	if (!may_use_simd())
+		return sha512_arm_finup(desc, data, len, out);
+
+	kernel_neon_begin();
+	if (len)
+		sha512_base_do_update(desc, data, len,
+			(sha512_block_fn *)sha512_block_data_order_neon);
+	sha512_base_do_finalize(desc,
+		(sha512_block_fn *)sha512_block_data_order_neon);
+	kernel_neon_end();
+
+	return sha512_base_finish(desc, out);
+}
+
+static int sha512_neon_final(struct shash_desc *desc, u8 *out)
+{
+	return sha512_neon_finup(desc, NULL, 0, out);
+}
+
+struct shash_alg sha512_neon_algs[] = { {
+	.init			= sha384_base_init,
+	.update			= sha512_neon_update,
+	.final			= sha512_neon_final,
+	.finup			= sha512_neon_finup,
+	.descsize		= sizeof(struct sha512_state),
+	.digestsize		= SHA384_DIGEST_SIZE,
+	.base			= {
+		.cra_name		= "sha384",
+		.cra_driver_name	= "sha384-neon",
+		.cra_priority		= 300,
+		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
+		.cra_blocksize		= SHA384_BLOCK_SIZE,
+		.cra_module		= THIS_MODULE,
+
+	}
+},  {
+	.init			= sha512_base_init,
+	.update			= sha512_neon_update,
+	.final			= sha512_neon_final,
+	.finup			= sha512_neon_finup,
+	.descsize		= sizeof(struct sha512_state),
+	.digestsize		= SHA512_DIGEST_SIZE,
+	.base			= {
+		.cra_name		= "sha512",
+		.cra_driver_name	= "sha512-neon",
+		.cra_priority		= 300,
+		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
+		.cra_blocksize		= SHA512_BLOCK_SIZE,
+		.cra_module		= THIS_MODULE,
+	}
+} };
diff --git a/arch/arm/crypto/sha512.h b/arch/arm/crypto/sha512.h
new file mode 100644
index 000000000000..a75d9a82988a
--- /dev/null
+++ b/arch/arm/crypto/sha512.h
@@ -0,0 +1,8 @@
+
+int sha512_arm_update(struct shash_desc *desc, const u8 *data,
+		      unsigned int len);
+
+int sha512_arm_finup(struct shash_desc *desc, const u8 *data,
+		     unsigned int len, u8 *out);
+
+extern struct shash_alg sha512_neon_algs[2];
diff --git a/arch/arm/crypto/sha512_neon_glue.c b/arch/arm/crypto/sha512_neon_glue.c
deleted file mode 100644
index b124dce838d6..000000000000
--- a/arch/arm/crypto/sha512_neon_glue.c
+++ /dev/null
@@ -1,305 +0,0 @@
-/*
- * Glue code for the SHA512 Secure Hash Algorithm assembly implementation
- * using NEON instructions.
- *
- * Copyright © 2014 Jussi Kivilinna <jussi.kivilinna@iki.fi>
- *
- * This file is based on sha512_ssse3_glue.c:
- *   Copyright (C) 2013 Intel Corporation
- *   Author: Tim Chen <tim.c.chen@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
- */
-
-#include <crypto/internal/hash.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/mm.h>
-#include <linux/cryptohash.h>
-#include <linux/types.h>
-#include <linux/string.h>
-#include <crypto/sha.h>
-#include <asm/byteorder.h>
-#include <asm/simd.h>
-#include <asm/neon.h>
-
-
-static const u64 sha512_k[] = {
-	0x428a2f98d728ae22ULL, 0x7137449123ef65cdULL,
-	0xb5c0fbcfec4d3b2fULL, 0xe9b5dba58189dbbcULL,
-	0x3956c25bf348b538ULL, 0x59f111f1b605d019ULL,
-	0x923f82a4af194f9bULL, 0xab1c5ed5da6d8118ULL,
-	0xd807aa98a3030242ULL, 0x12835b0145706fbeULL,
-	0x243185be4ee4b28cULL, 0x550c7dc3d5ffb4e2ULL,
-	0x72be5d74f27b896fULL, 0x80deb1fe3b1696b1ULL,
-	0x9bdc06a725c71235ULL, 0xc19bf174cf692694ULL,
-	0xe49b69c19ef14ad2ULL, 0xefbe4786384f25e3ULL,
-	0x0fc19dc68b8cd5b5ULL, 0x240ca1cc77ac9c65ULL,
-	0x2de92c6f592b0275ULL, 0x4a7484aa6ea6e483ULL,
-	0x5cb0a9dcbd41fbd4ULL, 0x76f988da831153b5ULL,
-	0x983e5152ee66dfabULL, 0xa831c66d2db43210ULL,
-	0xb00327c898fb213fULL, 0xbf597fc7beef0ee4ULL,
-	0xc6e00bf33da88fc2ULL, 0xd5a79147930aa725ULL,
-	0x06ca6351e003826fULL, 0x142929670a0e6e70ULL,
-	0x27b70a8546d22ffcULL, 0x2e1b21385c26c926ULL,
-	0x4d2c6dfc5ac42aedULL, 0x53380d139d95b3dfULL,
-	0x650a73548baf63deULL, 0x766a0abb3c77b2a8ULL,
-	0x81c2c92e47edaee6ULL, 0x92722c851482353bULL,
-	0xa2bfe8a14cf10364ULL, 0xa81a664bbc423001ULL,
-	0xc24b8b70d0f89791ULL, 0xc76c51a30654be30ULL,
-	0xd192e819d6ef5218ULL, 0xd69906245565a910ULL,
-	0xf40e35855771202aULL, 0x106aa07032bbd1b8ULL,
-	0x19a4c116b8d2d0c8ULL, 0x1e376c085141ab53ULL,
-	0x2748774cdf8eeb99ULL, 0x34b0bcb5e19b48a8ULL,
-	0x391c0cb3c5c95a63ULL, 0x4ed8aa4ae3418acbULL,
-	0x5b9cca4f7763e373ULL, 0x682e6ff3d6b2b8a3ULL,
-	0x748f82ee5defb2fcULL, 0x78a5636f43172f60ULL,
-	0x84c87814a1f0ab72ULL, 0x8cc702081a6439ecULL,
-	0x90befffa23631e28ULL, 0xa4506cebde82bde9ULL,
-	0xbef9a3f7b2c67915ULL, 0xc67178f2e372532bULL,
-	0xca273eceea26619cULL, 0xd186b8c721c0c207ULL,
-	0xeada7dd6cde0eb1eULL, 0xf57d4f7fee6ed178ULL,
-	0x06f067aa72176fbaULL, 0x0a637dc5a2c898a6ULL,
-	0x113f9804bef90daeULL, 0x1b710b35131c471bULL,
-	0x28db77f523047d84ULL, 0x32caab7b40c72493ULL,
-	0x3c9ebe0a15c9bebcULL, 0x431d67c49c100d4cULL,
-	0x4cc5d4becb3e42b6ULL, 0x597f299cfc657e2aULL,
-	0x5fcb6fab3ad6faecULL, 0x6c44198c4a475817ULL
-};
-
-
-asmlinkage void sha512_transform_neon(u64 *digest, const void *data,
-				      const u64 k[], unsigned int num_blks);
-
-
-static int sha512_neon_init(struct shash_desc *desc)
-{
-	struct sha512_state *sctx = shash_desc_ctx(desc);
-
-	sctx->state[0] = SHA512_H0;
-	sctx->state[1] = SHA512_H1;
-	sctx->state[2] = SHA512_H2;
-	sctx->state[3] = SHA512_H3;
-	sctx->state[4] = SHA512_H4;
-	sctx->state[5] = SHA512_H5;
-	sctx->state[6] = SHA512_H6;
-	sctx->state[7] = SHA512_H7;
-	sctx->count[0] = sctx->count[1] = 0;
-
-	return 0;
-}
-
-static int __sha512_neon_update(struct shash_desc *desc, const u8 *data,
-				unsigned int len, unsigned int partial)
-{
-	struct sha512_state *sctx = shash_desc_ctx(desc);
-	unsigned int done = 0;
-
-	sctx->count[0] += len;
-	if (sctx->count[0] < len)
-		sctx->count[1]++;
-
-	if (partial) {
-		done = SHA512_BLOCK_SIZE - partial;
-		memcpy(sctx->buf + partial, data, done);
-		sha512_transform_neon(sctx->state, sctx->buf, sha512_k, 1);
-	}
-
-	if (len - done >= SHA512_BLOCK_SIZE) {
-		const unsigned int rounds = (len - done) / SHA512_BLOCK_SIZE;
-
-		sha512_transform_neon(sctx->state, data + done, sha512_k,
-				      rounds);
-
-		done += rounds * SHA512_BLOCK_SIZE;
-	}
-
-	memcpy(sctx->buf, data + done, len - done);
-
-	return 0;
-}
-
-static int sha512_neon_update(struct shash_desc *desc, const u8 *data,
-			     unsigned int len)
-{
-	struct sha512_state *sctx = shash_desc_ctx(desc);
-	unsigned int partial = sctx->count[0] % SHA512_BLOCK_SIZE;
-	int res;
-
-	/* Handle the fast case right here */
-	if (partial + len < SHA512_BLOCK_SIZE) {
-		sctx->count[0] += len;
-		if (sctx->count[0] < len)
-			sctx->count[1]++;
-		memcpy(sctx->buf + partial, data, len);
-
-		return 0;
-	}
-
-	if (!may_use_simd()) {
-		res = crypto_sha512_update(desc, data, len);
-	} else {
-		kernel_neon_begin();
-		res = __sha512_neon_update(desc, data, len, partial);
-		kernel_neon_end();
-	}
-
-	return res;
-}
-
-
-/* Add padding and return the message digest. */
-static int sha512_neon_final(struct shash_desc *desc, u8 *out)
-{
-	struct sha512_state *sctx = shash_desc_ctx(desc);
-	unsigned int i, index, padlen;
-	__be64 *dst = (__be64 *)out;
-	__be64 bits[2];
-	static const u8 padding[SHA512_BLOCK_SIZE] = { 0x80, };
-
-	/* save number of bits */
-	bits[1] = cpu_to_be64(sctx->count[0] << 3);
-	bits[0] = cpu_to_be64(sctx->count[1] << 3 | sctx->count[0] >> 61);
-
-	/* Pad out to 112 mod 128 and append length */
-	index = sctx->count[0] & 0x7f;
-	padlen = (index < 112) ? (112 - index) : ((128+112) - index);
-
-	if (!may_use_simd()) {
-		crypto_sha512_update(desc, padding, padlen);
-		crypto_sha512_update(desc, (const u8 *)&bits, sizeof(bits));
-	} else {
-		kernel_neon_begin();
-		/* We need to fill a whole block for __sha512_neon_update() */
-		if (padlen <= 112) {
-			sctx->count[0] += padlen;
-			if (sctx->count[0] < padlen)
-				sctx->count[1]++;
-			memcpy(sctx->buf + index, padding, padlen);
-		} else {
-			__sha512_neon_update(desc, padding, padlen, index);
-		}
-		__sha512_neon_update(desc, (const u8 *)&bits,
-					sizeof(bits), 112);
-		kernel_neon_end();
-	}
-
-	/* Store state in digest */
-	for (i = 0; i < 8; i++)
-		dst[i] = cpu_to_be64(sctx->state[i]);
-
-	/* Wipe context */
-	memset(sctx, 0, sizeof(*sctx));
-
-	return 0;
-}
-
-static int sha512_neon_export(struct shash_desc *desc, void *out)
-{
-	struct sha512_state *sctx = shash_desc_ctx(desc);
-
-	memcpy(out, sctx, sizeof(*sctx));
-
-	return 0;
-}
-
-static int sha512_neon_import(struct shash_desc *desc, const void *in)
-{
-	struct sha512_state *sctx = shash_desc_ctx(desc);
-
-	memcpy(sctx, in, sizeof(*sctx));
-
-	return 0;
-}
-
-static int sha384_neon_init(struct shash_desc *desc)
-{
-	struct sha512_state *sctx = shash_desc_ctx(desc);
-
-	sctx->state[0] = SHA384_H0;
-	sctx->state[1] = SHA384_H1;
-	sctx->state[2] = SHA384_H2;
-	sctx->state[3] = SHA384_H3;
-	sctx->state[4] = SHA384_H4;
-	sctx->state[5] = SHA384_H5;
-	sctx->state[6] = SHA384_H6;
-	sctx->state[7] = SHA384_H7;
-
-	sctx->count[0] = sctx->count[1] = 0;
-
-	return 0;
-}
-
-static int sha384_neon_final(struct shash_desc *desc, u8 *hash)
-{
-	u8 D[SHA512_DIGEST_SIZE];
-
-	sha512_neon_final(desc, D);
-
-	memcpy(hash, D, SHA384_DIGEST_SIZE);
-	memzero_explicit(D, SHA512_DIGEST_SIZE);
-
-	return 0;
-}
-
-static struct shash_alg algs[] = { {
-	.digestsize	=	SHA512_DIGEST_SIZE,
-	.init		=	sha512_neon_init,
-	.update		=	sha512_neon_update,
-	.final		=	sha512_neon_final,
-	.export		=	sha512_neon_export,
-	.import		=	sha512_neon_import,
-	.descsize	=	sizeof(struct sha512_state),
-	.statesize	=	sizeof(struct sha512_state),
-	.base		=	{
-		.cra_name	=	"sha512",
-		.cra_driver_name =	"sha512-neon",
-		.cra_priority	=	250,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
-		.cra_blocksize	=	SHA512_BLOCK_SIZE,
-		.cra_module	=	THIS_MODULE,
-	}
-},  {
-	.digestsize	=	SHA384_DIGEST_SIZE,
-	.init		=	sha384_neon_init,
-	.update		=	sha512_neon_update,
-	.final		=	sha384_neon_final,
-	.export		=	sha512_neon_export,
-	.import		=	sha512_neon_import,
-	.descsize	=	sizeof(struct sha512_state),
-	.statesize	=	sizeof(struct sha512_state),
-	.base		=	{
-		.cra_name	=	"sha384",
-		.cra_driver_name =	"sha384-neon",
-		.cra_priority	=	250,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
-		.cra_blocksize	=	SHA384_BLOCK_SIZE,
-		.cra_module	=	THIS_MODULE,
-	}
-} };
-
-static int __init sha512_neon_mod_init(void)
-{
-	if (!cpu_has_neon())
-		return -ENODEV;
-
-	return crypto_register_shashes(algs, ARRAY_SIZE(algs));
-}
-
-static void __exit sha512_neon_mod_fini(void)
-{
-	crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
-}
-
-module_init(sha512_neon_mod_init);
-module_exit(sha512_neon_mod_fini);
-
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("SHA512 Secure Hash Algorithm, NEON accelerated");
-
-MODULE_ALIAS_CRYPTO("sha512");
-MODULE_ALIAS_CRYPTO("sha384");
diff --git a/arch/arm/include/asm/barrier.h b/arch/arm/include/asm/barrier.h
index d2f81e6b8c1c..6c2327e1c732 100644
--- a/arch/arm/include/asm/barrier.h
+++ b/arch/arm/include/asm/barrier.h
@@ -81,7 +81,7 @@ do {									\
 #define read_barrier_depends()		do { } while(0)
 #define smp_read_barrier_depends()	do { } while(0)
 
-#define set_mb(var, value)	do { var = value; smp_mb(); } while (0)
+#define smp_store_mb(var, value)	do { WRITE_ONCE(var, value); smp_mb(); } while (0)
 
 #define smp_mb__before_atomic()	smp_mb()
 #define smp_mb__after_atomic()	smp_mb()
diff --git a/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h
index 4e78065a16aa..5eed82809d82 100644
--- a/arch/arm/include/asm/futex.h
+++ b/arch/arm/include/asm/futex.h
@@ -93,6 +93,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
+	preempt_disable();
 	__asm__ __volatile__("@futex_atomic_cmpxchg_inatomic\n"
 	"1:	" TUSER(ldr) "	%1, [%4]\n"
 	"	teq	%1, %2\n"
@@ -104,6 +105,8 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	: "cc", "memory");
 
 	*uval = val;
+	preempt_enable();
+
 	return ret;
 }
 
@@ -124,7 +127,10 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
-	pagefault_disable();	/* implies preempt_disable() */
+#ifndef CONFIG_SMP
+	preempt_disable();
+#endif
+	pagefault_disable();
 
 	switch (op) {
 	case FUTEX_OP_SET:
@@ -146,7 +152,10 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 		ret = -ENOSYS;
 	}
 
-	pagefault_enable();	/* subsumes preempt_enable() */
+	pagefault_enable();
+#ifndef CONFIG_SMP
+	preempt_enable();
+#endif
 
 	if (!ret) {
 		switch (cmp) {
diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h
index db58deb00aa7..1b7677d1e5e1 100644
--- a/arch/arm/include/asm/io.h
+++ b/arch/arm/include/asm/io.h
@@ -336,6 +336,7 @@ extern void _memset_io(volatile void __iomem *, int, size_t);
 #define ioremap_nocache(cookie,size)	__arm_ioremap((cookie), (size), MT_DEVICE)
 #define ioremap_cache(cookie,size)	__arm_ioremap((cookie), (size), MT_DEVICE_CACHED)
 #define ioremap_wc(cookie,size)		__arm_ioremap((cookie), (size), MT_DEVICE_WC)
+#define ioremap_wt(cookie,size)		__arm_ioremap((cookie), (size), MT_DEVICE)
 #define iounmap				__arm_iounmap
 
 /*
diff --git a/arch/arm/include/asm/kvm_asm.h b/arch/arm/include/asm/kvm_asm.h
index 25410b2d8bc1..194c91b610ff 100644
--- a/arch/arm/include/asm/kvm_asm.h
+++ b/arch/arm/include/asm/kvm_asm.h
@@ -23,7 +23,7 @@
 #define c0_MPIDR	1	/* MultiProcessor ID Register */
 #define c0_CSSELR	2	/* Cache Size Selection Register */
 #define c1_SCTLR	3	/* System Control Register */
-#define c1_ACTLR	4	/* Auxilliary Control Register */
+#define c1_ACTLR	4	/* Auxiliary Control Register */
 #define c1_CPACR	5	/* Coprocessor Access Control */
 #define c2_TTBR0	6	/* Translation Table Base Register 0 */
 #define c2_TTBR0_high	7	/* TTBR0 top 32 bits */
diff --git a/arch/arm/include/asm/pci.h b/arch/arm/include/asm/pci.h
index 585dc33a7a24..a5635444ca41 100644
--- a/arch/arm/include/asm/pci.h
+++ b/arch/arm/include/asm/pci.h
@@ -31,16 +31,6 @@ static inline int pci_proc_domain(struct pci_bus *bus)
  */
 #define PCI_DMA_BUS_IS_PHYS     (1)
 
-#ifdef CONFIG_PCI
-static inline void pci_dma_burst_advice(struct pci_dev *pdev,
-					enum pci_dma_burst_strategy *strat,
-					unsigned long *strategy_parameter)
-{
-	*strat = PCI_DMA_BURST_INFINITY;
-	*strategy_parameter = ~0UL;
-}
-#endif
-
 #define HAVE_PCI_MMAP
 extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
                                enum pci_mmap_state mmap_state, int write_combine);
diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h
index 2fe85fff5cca..370f7a732900 100644
--- a/arch/arm/include/asm/topology.h
+++ b/arch/arm/include/asm/topology.h
@@ -18,7 +18,7 @@ extern struct cputopo_arm cpu_topology[NR_CPUS];
 #define topology_physical_package_id(cpu)	(cpu_topology[cpu].socket_id)
 #define topology_core_id(cpu)		(cpu_topology[cpu].core_id)
 #define topology_core_cpumask(cpu)	(&cpu_topology[cpu].core_sibling)
-#define topology_thread_cpumask(cpu)	(&cpu_topology[cpu].thread_sibling)
+#define topology_sibling_cpumask(cpu)	(&cpu_topology[cpu].thread_sibling)
 
 void init_cpu_topology(void);
 void store_cpu_topology(unsigned int cpuid);
diff --git a/arch/arm/lib/lib1funcs.S b/arch/arm/lib/lib1funcs.S
index 947567ff67f9..af2267f6a529 100644
--- a/arch/arm/lib/lib1funcs.S
+++ b/arch/arm/lib/lib1funcs.S
@@ -167,7 +167,7 @@ Boston, MA 02111-1307, USA.  */
 
 #endif
 
-	@ Perform all needed substractions to keep only the reminder.
+	@ Perform all needed subtractions to keep only the reminder.
 	@ Do comparisons in batch of 4 first.
 	subs	\order, \order, #3		@ yes, 3 is intended here
 	blt	2f
@@ -189,7 +189,7 @@ Boston, MA 02111-1307, USA.  */
 	teqne	\dividend, #0
 	beq	5f
 
-	@ Either 1, 2 or 3 comparison/substractions are left.
+	@ Either 1, 2 or 3 comparison/subtractions are left.
 2:	cmn	\order, #2
 	blt	4f
 	beq	3f
diff --git a/arch/arm/mach-gemini/gpio.c b/arch/arm/mach-gemini/gpio.c
index f8cb5710d6ee..3292f2e6ed6f 100644
--- a/arch/arm/mach-gemini/gpio.c
+++ b/arch/arm/mach-gemini/gpio.c
@@ -223,8 +223,8 @@ void __init gemini_gpio_init(void)
 			set_irq_flags(j, IRQF_VALID);
 		}
 
-		irq_set_chained_handler(IRQ_GPIO(i), gpio_irq_handler);
-		irq_set_handler_data(IRQ_GPIO(i), (void *)i);
+		irq_set_chained_handler_and_data(IRQ_GPIO(i), gpio_irq_handler,
+						 (void *)i);
 	}
 
 	BUG_ON(gpiochip_add(&gemini_gpio_chip));
diff --git a/arch/arm/mach-sa1100/neponset.c b/arch/arm/mach-sa1100/neponset.c
index af868d258e66..99d9a3b1bf34 100644
--- a/arch/arm/mach-sa1100/neponset.c
+++ b/arch/arm/mach-sa1100/neponset.c
@@ -327,8 +327,7 @@ static int neponset_probe(struct platform_device *dev)
 	irq_set_chip(d->irq_base + NEP_IRQ_SA1111, &nochip);
 
 	irq_set_irq_type(irq, IRQ_TYPE_EDGE_RISING);
-	irq_set_handler_data(irq, d);
-	irq_set_chained_handler(irq, neponset_irq_handler);
+	irq_set_chained_handler_and_data(irq, neponset_irq_handler, d);
 
 	/*
 	 * We would set IRQ_GPIO25 to be a wake-up IRQ, but unfortunately
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index 6333d9c17875..0d629b8f973f 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -276,7 +276,7 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	 * If we're in an interrupt or have no user
 	 * context, we must not take the fault..
 	 */
-	if (in_atomic() || !mm)
+	if (faulthandler_disabled() || !mm)
 		goto no_context;
 
 	if (user_mode(regs))
diff --git a/arch/arm/mm/highmem.c b/arch/arm/mm/highmem.c
index b98895d9fe57..ee8dfa793989 100644
--- a/arch/arm/mm/highmem.c
+++ b/arch/arm/mm/highmem.c
@@ -59,6 +59,7 @@ void *kmap_atomic(struct page *page)
 	void *kmap;
 	int type;
 
+	preempt_disable();
 	pagefault_disable();
 	if (!PageHighMem(page))
 		return page_address(page);
@@ -121,6 +122,7 @@ void __kunmap_atomic(void *kvaddr)
 		kunmap_high(pte_page(pkmap_page_table[PKMAP_NR(vaddr)]));
 	}
 	pagefault_enable();
+	preempt_enable();
 }
 EXPORT_SYMBOL(__kunmap_atomic);
 
@@ -130,6 +132,7 @@ void *kmap_atomic_pfn(unsigned long pfn)
 	int idx, type;
 	struct page *page = pfn_to_page(pfn);
 
+	preempt_disable();
 	pagefault_disable();
 	if (!PageHighMem(page))
 		return page_address(page);
diff --git a/arch/arm64/boot/dts/apm/apm-storm.dtsi b/arch/arm64/boot/dts/apm/apm-storm.dtsi
index c8d3e0e86678..d8f3a1c65ecd 100644
--- a/arch/arm64/boot/dts/apm/apm-storm.dtsi
+++ b/arch/arm64/boot/dts/apm/apm-storm.dtsi
@@ -374,6 +374,28 @@
 			};
 		};
 
+		msi: msi@79000000 {
+			compatible = "apm,xgene1-msi";
+			msi-controller;
+			reg = <0x00 0x79000000 0x0 0x900000>;
+			interrupts = <  0x0 0x10 0x4
+					0x0 0x11 0x4
+					0x0 0x12 0x4
+					0x0 0x13 0x4
+					0x0 0x14 0x4
+					0x0 0x15 0x4
+					0x0 0x16 0x4
+					0x0 0x17 0x4
+					0x0 0x18 0x4
+					0x0 0x19 0x4
+					0x0 0x1a 0x4
+					0x0 0x1b 0x4
+					0x0 0x1c 0x4
+					0x0 0x1d 0x4
+					0x0 0x1e 0x4
+					0x0 0x1f 0x4>;
+		};
+
 		pcie0: pcie@1f2b0000 {
 			status = "disabled";
 			device_type = "pci";
@@ -395,6 +417,7 @@
 					 0x0 0x0 0x0 0x4 &gic 0x0 0xc5 0x1>;
 			dma-coherent;
 			clocks = <&pcie0clk 0>;
+			msi-parent = <&msi>;
 		};
 
 		pcie1: pcie@1f2c0000 {
@@ -418,6 +441,7 @@
 					 0x0 0x0 0x0 0x4 &gic 0x0 0xcb 0x1>;
 			dma-coherent;
 			clocks = <&pcie1clk 0>;
+			msi-parent = <&msi>;
 		};
 
 		pcie2: pcie@1f2d0000 {
@@ -441,6 +465,7 @@
 					 0x0 0x0 0x0 0x4 &gic 0x0 0xd1 0x1>;
 			dma-coherent;
 			clocks = <&pcie2clk 0>;
+			msi-parent = <&msi>;
 		};
 
 		pcie3: pcie@1f500000 {
@@ -464,6 +489,7 @@
 					 0x0 0x0 0x0 0x4 &gic 0x0 0xd7 0x1>;
 			dma-coherent;
 			clocks = <&pcie3clk 0>;
+			msi-parent = <&msi>;
 		};
 
 		pcie4: pcie@1f510000 {
@@ -487,6 +513,7 @@
 					 0x0 0x0 0x0 0x4 &gic 0x0 0xdd 0x1>;
 			dma-coherent;
 			clocks = <&pcie4clk 0>;
+			msi-parent = <&msi>;
 		};
 
 		serial0: serial@1c020000 {
diff --git a/arch/arm64/crypto/aes-ce-ccm-glue.c b/arch/arm64/crypto/aes-ce-ccm-glue.c
index 6c348df5bf36..3303e8a7b837 100644
--- a/arch/arm64/crypto/aes-ce-ccm-glue.c
+++ b/arch/arm64/crypto/aes-ce-ccm-glue.c
@@ -13,7 +13,7 @@
 #include <crypto/aes.h>
 #include <crypto/algapi.h>
 #include <crypto/scatterwalk.h>
-#include <linux/crypto.h>
+#include <crypto/internal/aead.h>
 #include <linux/module.h>
 
 #include "aes-ce-setkey.h"
diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index 71f19c4dc0de..0fa47c4275cb 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -114,7 +114,7 @@ do {									\
 #define read_barrier_depends()		do { } while(0)
 #define smp_read_barrier_depends()	do { } while(0)
 
-#define set_mb(var, value)	do { var = value; smp_mb(); } while (0)
+#define smp_store_mb(var, value)	do { WRITE_ONCE(var, value); smp_mb(); } while (0)
 #define nop()		asm volatile("nop");
 
 #define smp_mb__before_atomic()	smp_mb()
diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h
index 5f750dc96e0f..74069b3bd919 100644
--- a/arch/arm64/include/asm/futex.h
+++ b/arch/arm64/include/asm/futex.h
@@ -58,7 +58,7 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
-	pagefault_disable();	/* implies preempt_disable() */
+	pagefault_disable();
 
 	switch (op) {
 	case FUTEX_OP_SET:
@@ -85,7 +85,7 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 		ret = -ENOSYS;
 	}
 
-	pagefault_enable();	/* subsumes preempt_enable() */
+	pagefault_enable();
 
 	if (!ret) {
 		switch (cmp) {
diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h
index 540f7c0aea82..7116d3973058 100644
--- a/arch/arm64/include/asm/io.h
+++ b/arch/arm64/include/asm/io.h
@@ -170,6 +170,7 @@ extern void __iomem *ioremap_cache(phys_addr_t phys_addr, size_t size);
 #define ioremap(addr, size)		__ioremap((addr), (size), __pgprot(PROT_DEVICE_nGnRE))
 #define ioremap_nocache(addr, size)	__ioremap((addr), (size), __pgprot(PROT_DEVICE_nGnRE))
 #define ioremap_wc(addr, size)		__ioremap((addr), (size), __pgprot(PROT_NORMAL_NC))
+#define ioremap_wt(addr, size)		__ioremap((addr), (size), __pgprot(PROT_DEVICE_nGnRE))
 #define iounmap				__iounmap
 
 /*
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 4f7310fa77f0..c4c11d20ca17 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -27,7 +27,7 @@
 #define	MPIDR_EL1	1	/* MultiProcessor Affinity Register */
 #define	CSSELR_EL1	2	/* Cache Size Selection Register */
 #define	SCTLR_EL1	3	/* System Control Register */
-#define	ACTLR_EL1	4	/* Auxilliary Control Register */
+#define	ACTLR_EL1	4	/* Auxiliary Control Register */
 #define	CPACR_EL1	5	/* Coprocessor Access Control */
 #define	TTBR0_EL1	6	/* Translation Table Base Register 0 */
 #define	TTBR1_EL1	7	/* Translation Table Base Register 1 */
diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h
index 7ebcd31ce51c..225ec3524fbf 100644
--- a/arch/arm64/include/asm/topology.h
+++ b/arch/arm64/include/asm/topology.h
@@ -18,7 +18,7 @@ extern struct cpu_topology cpu_topology[NR_CPUS];
 #define topology_physical_package_id(cpu)	(cpu_topology[cpu].cluster_id)
 #define topology_core_id(cpu)		(cpu_topology[cpu].core_id)
 #define topology_core_cpumask(cpu)	(&cpu_topology[cpu].core_sibling)
-#define topology_thread_cpumask(cpu)	(&cpu_topology[cpu].thread_sibling)
+#define topology_sibling_cpumask(cpu)	(&cpu_topology[cpu].thread_sibling)
 
 void init_cpu_topology(void);
 void store_cpu_topology(unsigned int cpuid);
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 96da13167d4a..0948d327d013 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -211,7 +211,7 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
 	 * If we're in an interrupt or have no user context, we must not take
 	 * the fault.
 	 */
-	if (in_atomic() || !mm)
+	if (faulthandler_disabled() || !mm)
 		goto no_context;
 
 	if (user_mode(regs))
diff --git a/arch/avr32/include/asm/cmpxchg.h b/arch/avr32/include/asm/cmpxchg.h
index 962a6aeab787..366bbeaeb405 100644
--- a/arch/avr32/include/asm/cmpxchg.h
+++ b/arch/avr32/include/asm/cmpxchg.h
@@ -70,8 +70,6 @@ extern unsigned long __cmpxchg_u64_unsupported_on_32bit_kernels(
    if something tries to do an invalid cmpxchg().  */
 extern void __cmpxchg_called_with_bad_pointer(void);
 
-#define __HAVE_ARCH_CMPXCHG 1
-
 static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
 				      unsigned long new, int size)
 {
diff --git a/arch/avr32/include/asm/io.h b/arch/avr32/include/asm/io.h
index 4f5ec2bb7172..e998ff5d8e1a 100644
--- a/arch/avr32/include/asm/io.h
+++ b/arch/avr32/include/asm/io.h
@@ -296,6 +296,7 @@ extern void __iounmap(void __iomem *addr);
 	__iounmap(addr)
 
 #define ioremap_wc ioremap_nocache
+#define ioremap_wt ioremap_nocache
 
 #define cached(addr) P1SEGADDR(addr)
 #define uncached(addr) P2SEGADDR(addr)
diff --git a/arch/avr32/include/asm/uaccess.h b/arch/avr32/include/asm/uaccess.h
index a46f7cf3e1ea..68cf638faf48 100644
--- a/arch/avr32/include/asm/uaccess.h
+++ b/arch/avr32/include/asm/uaccess.h
@@ -97,7 +97,8 @@ static inline __kernel_size_t __copy_from_user(void *to,
  * @x:   Value to copy to user space.
  * @ptr: Destination address, in user space.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple value from kernel space to user
  * space.  It supports simple types like char and int, but not larger
@@ -116,7 +117,8 @@ static inline __kernel_size_t __copy_from_user(void *to,
  * @x:   Variable to store result.
  * @ptr: Source address, in user space.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple variable from user space to kernel
  * space.  It supports simple types like char and int, but not larger
@@ -136,7 +138,8 @@ static inline __kernel_size_t __copy_from_user(void *to,
  * @x:   Value to copy to user space.
  * @ptr: Destination address, in user space.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple value from kernel space to user
  * space.  It supports simple types like char and int, but not larger
@@ -158,7 +161,8 @@ static inline __kernel_size_t __copy_from_user(void *to,
  * @x:   Variable to store result.
  * @ptr: Source address, in user space.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple variable from user space to kernel
  * space.  It supports simple types like char and int, but not larger
diff --git a/arch/avr32/mm/fault.c b/arch/avr32/mm/fault.c
index d223a8b57c1e..c03533937a9f 100644
--- a/arch/avr32/mm/fault.c
+++ b/arch/avr32/mm/fault.c
@@ -14,11 +14,11 @@
 #include <linux/pagemap.h>
 #include <linux/kdebug.h>
 #include <linux/kprobes.h>
+#include <linux/uaccess.h>
 
 #include <asm/mmu_context.h>
 #include <asm/sysreg.h>
 #include <asm/tlb.h>
-#include <asm/uaccess.h>
 
 #ifdef CONFIG_KPROBES
 static inline int notify_page_fault(struct pt_regs *regs, int trap)
@@ -81,7 +81,7 @@ asmlinkage void do_page_fault(unsigned long ecr, struct pt_regs *regs)
 	 * If we're in an interrupt or have no user context, we must
 	 * not take the fault...
 	 */
-	if (in_atomic() || !mm || regs->sr & SYSREG_BIT(GM))
+	if (faulthandler_disabled() || !mm || regs->sr & SYSREG_BIT(GM))
 		goto no_context;
 
 	local_irq_enable();
diff --git a/arch/cris/mm/fault.c b/arch/cris/mm/fault.c
index 83f12f2ed9e3..3066d40a6db1 100644
--- a/arch/cris/mm/fault.c
+++ b/arch/cris/mm/fault.c
@@ -8,7 +8,7 @@
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/wait.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <arch/system.h>
 
 extern int find_fixup_code(struct pt_regs *);
@@ -109,11 +109,11 @@ do_page_fault(unsigned long address, struct pt_regs *regs,
 	info.si_code = SEGV_MAPERR;
 
 	/*
-	 * If we're in an interrupt or "atomic" operation or have no
+	 * If we're in an interrupt, have pagefaults disabled or have no
 	 * user context, we must not take the fault.
 	 */
 
-	if (in_atomic() || !mm)
+	if (faulthandler_disabled() || !mm)
 		goto no_context;
 
 	if (user_mode(regs))
diff --git a/arch/frv/include/asm/io.h b/arch/frv/include/asm/io.h
index 0b78bc89e840..a31b63ec4930 100644
--- a/arch/frv/include/asm/io.h
+++ b/arch/frv/include/asm/io.h
@@ -17,6 +17,8 @@
 
 #ifdef __KERNEL__
 
+#define ARCH_HAS_IOREMAP_WT
+
 #include <linux/types.h>
 #include <asm/virtconvert.h>
 #include <asm/string.h>
@@ -265,7 +267,7 @@ static inline void __iomem *ioremap_nocache(unsigned long physaddr, unsigned lon
 	return __ioremap(physaddr, size, IOMAP_NOCACHE_SER);
 }
 
-static inline void __iomem *ioremap_writethrough(unsigned long physaddr, unsigned long size)
+static inline void __iomem *ioremap_wt(unsigned long physaddr, unsigned long size)
 {
 	return __ioremap(physaddr, size, IOMAP_WRITETHROUGH);
 }
diff --git a/arch/frv/include/asm/pci.h b/arch/frv/include/asm/pci.h
index 2035a4d3f9b9..a6d4ed042c70 100644
--- a/arch/frv/include/asm/pci.h
+++ b/arch/frv/include/asm/pci.h
@@ -41,16 +41,6 @@ extern void pci_free_consistent(struct pci_dev *hwdev, size_t size,
 /* Return the index of the PCI controller for device PDEV. */
 #define pci_controller_num(PDEV)	(0)
 
-#ifdef CONFIG_PCI
-static inline void pci_dma_burst_advice(struct pci_dev *pdev,
-					enum pci_dma_burst_strategy *strat,
-					unsigned long *strategy_parameter)
-{
-	*strat = PCI_DMA_BURST_INFINITY;
-	*strategy_parameter = ~0UL;
-}
-#endif
-
 /*
  *	These are pretty much arbitrary with the CoMEM implementation.
  *	We have the whole address space to ourselves.
diff --git a/arch/frv/mm/fault.c b/arch/frv/mm/fault.c
index ec4917ddf678..61d99767fe16 100644
--- a/arch/frv/mm/fault.c
+++ b/arch/frv/mm/fault.c
@@ -19,9 +19,9 @@
 #include <linux/kernel.h>
 #include <linux/ptrace.h>
 #include <linux/hardirq.h>
+#include <linux/uaccess.h>
 
 #include <asm/pgtable.h>
-#include <asm/uaccess.h>
 #include <asm/gdb-stub.h>
 
 /*****************************************************************************/
@@ -78,7 +78,7 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear
 	 * If we're in an interrupt or have no user
 	 * context, we must not take the fault..
 	 */
-	if (in_atomic() || !mm)
+	if (faulthandler_disabled() || !mm)
 		goto no_context;
 
 	if (user_mode(__frame))
diff --git a/arch/frv/mm/highmem.c b/arch/frv/mm/highmem.c
index bed9a9bd3c10..785344bbdc07 100644
--- a/arch/frv/mm/highmem.c
+++ b/arch/frv/mm/highmem.c
@@ -42,6 +42,7 @@ void *kmap_atomic(struct page *page)
 	unsigned long paddr;
 	int type;
 
+	preempt_disable();
 	pagefault_disable();
 	type = kmap_atomic_idx_push();
 	paddr = page_to_phys(page);
@@ -85,5 +86,6 @@ void __kunmap_atomic(void *kvaddr)
 	}
 	kmap_atomic_idx_pop();
 	pagefault_enable();
+	preempt_enable();
 }
 EXPORT_SYMBOL(__kunmap_atomic);
diff --git a/arch/hexagon/include/asm/cmpxchg.h b/arch/hexagon/include/asm/cmpxchg.h
index 9e7802911a57..a6e34e2acbba 100644
--- a/arch/hexagon/include/asm/cmpxchg.h
+++ b/arch/hexagon/include/asm/cmpxchg.h
@@ -64,7 +64,6 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr,
  *  looks just like atomic_cmpxchg on our arch currently with a bunch of
  *  variable casting.
  */
-#define __HAVE_ARCH_CMPXCHG 1
 
 #define cmpxchg(ptr, old, new)					\
 ({								\
diff --git a/arch/hexagon/include/asm/uaccess.h b/arch/hexagon/include/asm/uaccess.h
index e4127e4d6a5b..f000a382bc7f 100644
--- a/arch/hexagon/include/asm/uaccess.h
+++ b/arch/hexagon/include/asm/uaccess.h
@@ -36,7 +36,8 @@
  * @addr: User space pointer to start of block to check
  * @size: Size of block to check
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Checks if a pointer to a block of memory in user space is valid.
  *
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 76d25b2cfbbe..42a91a7aa2b0 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -137,29 +137,6 @@ config AUDIT_ARCH
 	bool
 	default y
 
-menuconfig PARAVIRT_GUEST
-	bool "Paravirtualized guest support"
-	depends on BROKEN
-	help
-	  Say Y here to get to see options related to running Linux under
-	  various hypervisors.  This option alone does not add any kernel code.
-
-	  If you say N, all options in this submenu will be skipped and disabled.
-
-if PARAVIRT_GUEST
-
-config PARAVIRT
-	bool "Enable paravirtualization code"
-	depends on PARAVIRT_GUEST
-	default y
-	help
-	  This changes the kernel so it can modify itself when it is run
-	  under a hypervisor, potentially improving performance significantly
-	  over full virtualization.  However, when run without a hypervisor
-	  the kernel is theoretically slower and slightly larger.
-
-endif
-
 choice
 	prompt "System type"
 	default IA64_GENERIC
diff --git a/arch/ia64/include/asm/barrier.h b/arch/ia64/include/asm/barrier.h
index f6769eb2bbf9..843ba435e43b 100644
--- a/arch/ia64/include/asm/barrier.h
+++ b/arch/ia64/include/asm/barrier.h
@@ -77,12 +77,7 @@ do {									\
 	___p1;								\
 })
 
-/*
- * XXX check on this ---I suspect what Linus really wants here is
- * acquire vs release semantics but we can't discuss this stuff with
- * Linus just yet.  Grrr...
- */
-#define set_mb(var, value)	do { (var) = (value); mb(); } while (0)
+#define smp_store_mb(var, value)	do { WRITE_ONCE(var, value); mb(); } while (0)
 
 /*
  * The group barrier in front of the rsm & ssm are necessary to ensure
diff --git a/arch/ia64/include/asm/hw_irq.h b/arch/ia64/include/asm/hw_irq.h
index 668786e84af8..74347ebf7d68 100644
--- a/arch/ia64/include/asm/hw_irq.h
+++ b/arch/ia64/include/asm/hw_irq.h
@@ -15,11 +15,7 @@
 #include <asm/ptrace.h>
 #include <asm/smp.h>
 
-#ifndef CONFIG_PARAVIRT
 typedef u8 ia64_vector;
-#else
-typedef u16 ia64_vector;
-#endif
 
 /*
  * 0 special
@@ -114,15 +110,11 @@ DECLARE_PER_CPU(int[IA64_NUM_VECTORS], vector_irq);
 
 extern struct irq_chip irq_type_ia64_lsapic;	/* CPU-internal interrupt controller */
 
-#ifdef CONFIG_PARAVIRT_GUEST
-#include <asm/paravirt.h>
-#else
 #define ia64_register_ipi	ia64_native_register_ipi
 #define assign_irq_vector	ia64_native_assign_irq_vector
 #define free_irq_vector		ia64_native_free_irq_vector
 #define register_percpu_irq	ia64_native_register_percpu_irq
 #define ia64_resend_irq		ia64_native_resend_irq
-#endif
 
 extern void ia64_native_register_ipi(void);
 extern int bind_irq_vector(int irq, int vector, cpumask_t domain);
diff --git a/arch/ia64/include/asm/intrinsics.h b/arch/ia64/include/asm/intrinsics.h
index 20477ea111ba..ec970a920132 100644
--- a/arch/ia64/include/asm/intrinsics.h
+++ b/arch/ia64/include/asm/intrinsics.h
@@ -7,19 +7,6 @@
 #ifndef _ASM_IA64_INTRINSICS_H
 #define _ASM_IA64_INTRINSICS_H
 
-#include <asm/paravirt_privop.h>
 #include <uapi/asm/intrinsics.h>
 
-#ifndef __ASSEMBLY__
-#if defined(CONFIG_PARAVIRT)
-# undef IA64_INTRINSIC_API
-# undef IA64_INTRINSIC_MACRO
-# ifdef ASM_SUPPORTED
-#  define IA64_INTRINSIC_API(name)	paravirt_ ## name
-# else
-#  define IA64_INTRINSIC_API(name)	pv_cpu_ops.name
-# endif
-#define IA64_INTRINSIC_MACRO(name)	paravirt_ ## name
-#endif
-#endif /* !__ASSEMBLY__ */
 #endif /* _ASM_IA64_INTRINSICS_H */
diff --git a/arch/ia64/include/asm/iosapic.h b/arch/ia64/include/asm/iosapic.h
index 94c89a2d97fe..4ae1fbd7f10e 100644
--- a/arch/ia64/include/asm/iosapic.h
+++ b/arch/ia64/include/asm/iosapic.h
@@ -55,14 +55,10 @@
 
 #define NR_IOSAPICS			256
 
-#ifdef CONFIG_PARAVIRT_GUEST
-#include <asm/paravirt.h>
-#else
 #define iosapic_pcat_compat_init	ia64_native_iosapic_pcat_compat_init
 #define __iosapic_read			__ia64_native_iosapic_read
 #define __iosapic_write			__ia64_native_iosapic_write
 #define iosapic_get_irq_chip		ia64_native_iosapic_get_irq_chip
-#endif
 
 extern void __init ia64_native_iosapic_pcat_compat_init(void);
 extern struct irq_chip *ia64_native_iosapic_get_irq_chip(unsigned long trigger);
diff --git a/arch/ia64/include/asm/irq_remapping.h b/arch/ia64/include/asm/irq_remapping.h
index e3b3556e2e1b..a8687b1d8906 100644
--- a/arch/ia64/include/asm/irq_remapping.h
+++ b/arch/ia64/include/asm/irq_remapping.h
@@ -1,6 +1,4 @@
 #ifndef __IA64_INTR_REMAPPING_H
 #define __IA64_INTR_REMAPPING_H
 #define irq_remapping_enabled 0
-#define dmar_alloc_hwirq	create_irq
-#define dmar_free_hwirq		destroy_irq
 #endif
diff --git a/arch/ia64/include/asm/module.h b/arch/ia64/include/asm/module.h
index dfba22a872c3..f31894b2a354 100644
--- a/arch/ia64/include/asm/module.h
+++ b/arch/ia64/include/asm/module.h
@@ -18,12 +18,6 @@ struct mod_arch_specific {
 	struct elf64_shdr *got;		/* global offset table */
 	struct elf64_shdr *opd;		/* official procedure descriptors */
 	struct elf64_shdr *unwind;	/* unwind-table section */
-#ifdef CONFIG_PARAVIRT
-	struct elf64_shdr *paravirt_bundles;
-					/* paravirt_alt_bundle_patch table */
-	struct elf64_shdr *paravirt_insts;
-					/* paravirt_alt_inst_patch table */
-#endif
 	unsigned long gp;		/* global-pointer for module */
 
 	void *core_unw_table;		/* core unwind-table cookie returned by unwinder */
diff --git a/arch/ia64/include/asm/native/inst.h b/arch/ia64/include/asm/native/inst.h
index d2d46efb3e6e..7e08f17accd5 100644
--- a/arch/ia64/include/asm/native/inst.h
+++ b/arch/ia64/include/asm/native/inst.h
@@ -22,32 +22,6 @@
 
 #define DO_SAVE_MIN		IA64_NATIVE_DO_SAVE_MIN
 
-#define __paravirt_switch_to			ia64_native_switch_to
-#define __paravirt_leave_syscall		ia64_native_leave_syscall
-#define __paravirt_work_processed_syscall	ia64_native_work_processed_syscall
-#define __paravirt_leave_kernel			ia64_native_leave_kernel
-#define __paravirt_pending_syscall_end		ia64_work_pending_syscall_end
-#define __paravirt_work_processed_syscall_target \
-						ia64_work_processed_syscall
-
-#define paravirt_fsyscall_table			ia64_native_fsyscall_table
-#define paravirt_fsys_bubble_down		ia64_native_fsys_bubble_down
-
-#ifdef CONFIG_PARAVIRT_GUEST_ASM_CLOBBER_CHECK
-# define PARAVIRT_POISON	0xdeadbeefbaadf00d
-# define CLOBBER(clob)				\
-	;;					\
-	movl clob = PARAVIRT_POISON;		\
-	;;
-# define CLOBBER_PRED(pred_clob)		\
-	;;					\
-	cmp.eq pred_clob, p0 = r0, r0		\
-	;;
-#else
-# define CLOBBER(clob)			/* nothing */
-# define CLOBBER_PRED(pred_clob)	/* nothing */
-#endif
-
 #define MOV_FROM_IFA(reg)	\
 	mov reg = cr.ifa
 
@@ -70,106 +44,76 @@
 	mov reg = cr.iip
 
 #define MOV_FROM_IVR(reg, clob)	\
-	mov reg = cr.ivr	\
-	CLOBBER(clob)
+	mov reg = cr.ivr
 
 #define MOV_FROM_PSR(pred, reg, clob)	\
-(pred)	mov reg = psr			\
-	CLOBBER(clob)
+(pred)	mov reg = psr
 
 #define MOV_FROM_ITC(pred, pred_clob, reg, clob)	\
-(pred)	mov reg = ar.itc				\
-	CLOBBER(clob)					\
-	CLOBBER_PRED(pred_clob)
+(pred)	mov reg = ar.itc
 
 #define MOV_TO_IFA(reg, clob)	\
-	mov cr.ifa = reg	\
-	CLOBBER(clob)
+	mov cr.ifa = reg
 
 #define MOV_TO_ITIR(pred, reg, clob)	\
-(pred)	mov cr.itir = reg		\
-	CLOBBER(clob)
+(pred)	mov cr.itir = reg
 
 #define MOV_TO_IHA(pred, reg, clob)	\
-(pred)	mov cr.iha = reg		\
-	CLOBBER(clob)
+(pred)	mov cr.iha = reg
 
 #define MOV_TO_IPSR(pred, reg, clob)		\
-(pred)	mov cr.ipsr = reg			\
-	CLOBBER(clob)
+(pred)	mov cr.ipsr = reg
 
 #define MOV_TO_IFS(pred, reg, clob)	\
-(pred)	mov cr.ifs = reg		\
-	CLOBBER(clob)
+(pred)	mov cr.ifs = reg
 
 #define MOV_TO_IIP(reg, clob)	\
-	mov cr.iip = reg	\
-	CLOBBER(clob)
+	mov cr.iip = reg
 
 #define MOV_TO_KR(kr, reg, clob0, clob1)	\
-	mov IA64_KR(kr) = reg			\
-	CLOBBER(clob0)				\
-	CLOBBER(clob1)
+	mov IA64_KR(kr) = reg
 
 #define ITC_I(pred, reg, clob)	\
-(pred)	itc.i reg		\
-	CLOBBER(clob)
+(pred)	itc.i reg
 
 #define ITC_D(pred, reg, clob)	\
-(pred)	itc.d reg		\
-	CLOBBER(clob)
+(pred)	itc.d reg
 
 #define ITC_I_AND_D(pred_i, pred_d, reg, clob)	\
 (pred_i) itc.i reg;				\
-(pred_d) itc.d reg				\
-	CLOBBER(clob)
+(pred_d) itc.d reg
 
 #define THASH(pred, reg0, reg1, clob)		\
-(pred)	thash reg0 = reg1			\
-	CLOBBER(clob)
+(pred)	thash reg0 = reg1
 
 #define SSM_PSR_IC_AND_DEFAULT_BITS_AND_SRLZ_I(clob0, clob1)		\
 	ssm psr.ic | PSR_DEFAULT_BITS					\
-	CLOBBER(clob0)							\
-	CLOBBER(clob1)							\
 	;;								\
 	srlz.i /* guarantee that interruption collectin is on */	\
 	;;
 
 #define SSM_PSR_IC_AND_SRLZ_D(clob0, clob1)	\
 	ssm psr.ic				\
-	CLOBBER(clob0)				\
-	CLOBBER(clob1)				\
 	;;					\
 	srlz.d
 
 #define RSM_PSR_IC(clob)	\
-	rsm psr.ic		\
-	CLOBBER(clob)
+	rsm psr.ic
 
 #define SSM_PSR_I(pred, pred_clob, clob)	\
-(pred)	ssm psr.i				\
-	CLOBBER(clob)				\
-	CLOBBER_PRED(pred_clob)
+(pred)	ssm psr.i
 
 #define RSM_PSR_I(pred, clob0, clob1)	\
-(pred)	rsm psr.i			\
-	CLOBBER(clob0)			\
-	CLOBBER(clob1)
+(pred)	rsm psr.i
 
 #define RSM_PSR_I_IC(clob0, clob1, clob2)	\
-	rsm psr.i | psr.ic			\
-	CLOBBER(clob0)				\
-	CLOBBER(clob1)				\
-	CLOBBER(clob2)
+	rsm psr.i | psr.ic
 
 #define RSM_PSR_DT		\
 	rsm psr.dt
 
 #define RSM_PSR_BE_I(clob0, clob1)	\
-	rsm psr.be | psr.i		\
-	CLOBBER(clob0)			\
-	CLOBBER(clob1)
+	rsm psr.be | psr.i
 
 #define SSM_PSR_DT_AND_SRLZ_I	\
 	ssm psr.dt		\
@@ -177,15 +121,10 @@
 	srlz.i
 
 #define BSW_0(clob0, clob1, clob2)	\
-	bsw.0				\
-	CLOBBER(clob0)			\
-	CLOBBER(clob1)			\
-	CLOBBER(clob2)
+	bsw.0
 
 #define BSW_1(clob0, clob1)	\
-	bsw.1			\
-	CLOBBER(clob0)		\
-	CLOBBER(clob1)
+	bsw.1
 
 #define COVER	\
 	cover
diff --git a/arch/ia64/include/asm/native/pvchk_inst.h b/arch/ia64/include/asm/native/pvchk_inst.h
deleted file mode 100644
index 8d72962ec838..000000000000
--- a/arch/ia64/include/asm/native/pvchk_inst.h
+++ /dev/null
@@ -1,271 +0,0 @@
-#ifndef _ASM_NATIVE_PVCHK_INST_H
-#define _ASM_NATIVE_PVCHK_INST_H
-
-/******************************************************************************
- * arch/ia64/include/asm/native/pvchk_inst.h
- * Checker for paravirtualizations of privileged operations.
- *
- * Copyright (C) 2005 Hewlett-Packard Co
- *      Dan Magenheimer <dan.magenheimer@hp.com>
- *
- * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
- *                    VA Linux Systems Japan K.K.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- */
-
-/**********************************************
- * Instructions paravirtualized for correctness
- **********************************************/
-
-/* "fc" and "thash" are privilege-sensitive instructions, meaning they
- *  may have different semantics depending on whether they are executed
- *  at PL0 vs PL!=0.  When paravirtualized, these instructions mustn't
- *  be allowed to execute directly, lest incorrect semantics result.
- */
-
-#define fc	.error "fc should not be used directly."
-#define thash	.error "thash should not be used directly."
-
-/* Note that "ttag" and "cover" are also privilege-sensitive; "ttag"
- * is not currently used (though it may be in a long-format VHPT system!)
- * and the semantics of cover only change if psr.ic is off which is very
- * rare (and currently non-existent outside of assembly code
- */
-#define ttag	.error "ttag should not be used directly."
-#define cover	.error "cover should not be used directly."
-
-/* There are also privilege-sensitive registers.  These registers are
- * readable at any privilege level but only writable at PL0.
- */
-#define cpuid	.error "cpuid should not be used directly."
-#define pmd	.error "pmd should not be used directly."
-
-/*
- * mov ar.eflag =
- * mov = ar.eflag
- */
-
-/**********************************************
- * Instructions paravirtualized for performance
- **********************************************/
-/*
- * Those instructions include '.' which can't be handled by cpp.
- * or can't be handled by cpp easily.
- * They are handled by sed instead of cpp.
- */
-
-/* for .S
- * itc.i
- * itc.d
- *
- * bsw.0
- * bsw.1
- *
- * ssm psr.ic | PSR_DEFAULT_BITS
- * ssm psr.ic
- * rsm psr.ic
- * ssm psr.i
- * rsm psr.i
- * rsm psr.i | psr.ic
- * rsm psr.dt
- * ssm psr.dt
- *
- * mov = cr.ifa
- * mov = cr.itir
- * mov = cr.isr
- * mov = cr.iha
- * mov = cr.ipsr
- * mov = cr.iim
- * mov = cr.iip
- * mov = cr.ivr
- * mov = psr
- *
- * mov cr.ifa =
- * mov cr.itir =
- * mov cr.iha =
- * mov cr.ipsr =
- * mov cr.ifs =
- * mov cr.iip =
- * mov cr.kr =
- */
-
-/* for intrinsics
- * ssm psr.i
- * rsm psr.i
- * mov = psr
- * mov = ivr
- * mov = tpr
- * mov cr.itm =
- * mov eoi =
- * mov rr[] =
- * mov = rr[]
- * mov = kr
- * mov kr =
- * ptc.ga
- */
-
-/*************************************************************
- * define paravirtualized instrcution macros as nop to ingore.
- * and check whether arguments are appropriate.
- *************************************************************/
-
-/* check whether reg is a regular register */
-.macro is_rreg_in reg
-	.ifc "\reg", "r0"
-		nop 0
-		.exitm
-	.endif
-	;;
-	mov \reg = r0
-	;;
-.endm
-#define IS_RREG_IN(reg)	is_rreg_in reg ;
-
-#define IS_RREG_OUT(reg)			\
-	;;					\
-	mov reg = r0				\
-	;;
-
-#define IS_RREG_CLOB(reg)	IS_RREG_OUT(reg)
-
-/* check whether pred is a predicate register */
-#define IS_PRED_IN(pred)			\
-	;;					\
-	(pred)	nop 0				\
-	;;
-
-#define IS_PRED_OUT(pred)			\
-	;;					\
-	cmp.eq pred, p0 = r0, r0		\
-	;;
-
-#define IS_PRED_CLOB(pred)	IS_PRED_OUT(pred)
-
-
-#define DO_SAVE_MIN(__COVER, SAVE_IFS, EXTRA, WORKAROUND)	\
-	nop 0
-#define MOV_FROM_IFA(reg)			\
-	IS_RREG_OUT(reg)
-#define MOV_FROM_ITIR(reg)			\
-	IS_RREG_OUT(reg)
-#define MOV_FROM_ISR(reg)			\
-	IS_RREG_OUT(reg)
-#define MOV_FROM_IHA(reg)			\
-	IS_RREG_OUT(reg)
-#define MOV_FROM_IPSR(pred, reg)		\
-	IS_PRED_IN(pred)			\
-	IS_RREG_OUT(reg)
-#define MOV_FROM_IIM(reg)			\
-	IS_RREG_OUT(reg)
-#define MOV_FROM_IIP(reg)			\
-	IS_RREG_OUT(reg)
-#define MOV_FROM_IVR(reg, clob)			\
-	IS_RREG_OUT(reg)			\
-	IS_RREG_CLOB(clob)
-#define MOV_FROM_PSR(pred, reg, clob)		\
-	IS_PRED_IN(pred)			\
-	IS_RREG_OUT(reg)			\
-	IS_RREG_CLOB(clob)
-#define MOV_FROM_ITC(pred, pred_clob, reg, clob)	\
-	IS_PRED_IN(pred)				\
-	IS_PRED_CLOB(pred_clob)				\
-	IS_RREG_OUT(reg)				\
-	IS_RREG_CLOB(clob)
-#define MOV_TO_IFA(reg, clob)			\
-	IS_RREG_IN(reg)				\
-	IS_RREG_CLOB(clob)
-#define MOV_TO_ITIR(pred, reg, clob)		\
-	IS_PRED_IN(pred)			\
-	IS_RREG_IN(reg)				\
-	IS_RREG_CLOB(clob)
-#define MOV_TO_IHA(pred, reg, clob)		\
-	IS_PRED_IN(pred)			\
-	IS_RREG_IN(reg)				\
-	IS_RREG_CLOB(clob)
-#define MOV_TO_IPSR(pred, reg, clob)		\
-	IS_PRED_IN(pred)			\
-	IS_RREG_IN(reg)				\
-	IS_RREG_CLOB(clob)
-#define MOV_TO_IFS(pred, reg, clob)		\
-	IS_PRED_IN(pred)			\
-	IS_RREG_IN(reg)				\
-	IS_RREG_CLOB(clob)
-#define MOV_TO_IIP(reg, clob)			\
-	IS_RREG_IN(reg)				\
-	IS_RREG_CLOB(clob)
-#define MOV_TO_KR(kr, reg, clob0, clob1)	\
-	IS_RREG_IN(reg)				\
-	IS_RREG_CLOB(clob0)			\
-	IS_RREG_CLOB(clob1)
-#define ITC_I(pred, reg, clob)			\
-	IS_PRED_IN(pred)			\
-	IS_RREG_IN(reg)				\
-	IS_RREG_CLOB(clob)
-#define ITC_D(pred, reg, clob)			\
-	IS_PRED_IN(pred)			\
-	IS_RREG_IN(reg)				\
-	IS_RREG_CLOB(clob)
-#define ITC_I_AND_D(pred_i, pred_d, reg, clob)	\
-	IS_PRED_IN(pred_i)			\
-	IS_PRED_IN(pred_d)			\
-	IS_RREG_IN(reg)				\
-	IS_RREG_CLOB(clob)
-#define THASH(pred, reg0, reg1, clob)		\
-	IS_PRED_IN(pred)			\
-	IS_RREG_OUT(reg0)			\
-	IS_RREG_IN(reg1)			\
-	IS_RREG_CLOB(clob)
-#define SSM_PSR_IC_AND_DEFAULT_BITS_AND_SRLZ_I(clob0, clob1)	\
-	IS_RREG_CLOB(clob0)					\
-	IS_RREG_CLOB(clob1)
-#define SSM_PSR_IC_AND_SRLZ_D(clob0, clob1)	\
-	IS_RREG_CLOB(clob0)			\
-	IS_RREG_CLOB(clob1)
-#define RSM_PSR_IC(clob)			\
-	IS_RREG_CLOB(clob)
-#define SSM_PSR_I(pred, pred_clob, clob)	\
-	IS_PRED_IN(pred)			\
-	IS_PRED_CLOB(pred_clob)			\
-	IS_RREG_CLOB(clob)
-#define RSM_PSR_I(pred, clob0, clob1)		\
-	IS_PRED_IN(pred)			\
-	IS_RREG_CLOB(clob0)			\
-	IS_RREG_CLOB(clob1)
-#define RSM_PSR_I_IC(clob0, clob1, clob2)	\
-	IS_RREG_CLOB(clob0)			\
-	IS_RREG_CLOB(clob1)			\
-	IS_RREG_CLOB(clob2)
-#define RSM_PSR_DT				\
-	nop 0
-#define RSM_PSR_BE_I(clob0, clob1)		\
-	IS_RREG_CLOB(clob0)			\
-	IS_RREG_CLOB(clob1)
-#define SSM_PSR_DT_AND_SRLZ_I			\
-	nop 0
-#define BSW_0(clob0, clob1, clob2)		\
-	IS_RREG_CLOB(clob0)			\
-	IS_RREG_CLOB(clob1)			\
-	IS_RREG_CLOB(clob2)
-#define BSW_1(clob0, clob1)			\
-	IS_RREG_CLOB(clob0)			\
-	IS_RREG_CLOB(clob1)
-#define COVER					\
-	nop 0
-#define RFI					\
-	br.ret.sptk.many rp /* defining nop causes dependency error */
-
-#endif /* _ASM_NATIVE_PVCHK_INST_H */
diff --git a/arch/ia64/include/asm/paravirt.h b/arch/ia64/include/asm/paravirt.h
deleted file mode 100644
index b53518a98026..000000000000
--- a/arch/ia64/include/asm/paravirt.h
+++ /dev/null
@@ -1,321 +0,0 @@
-/******************************************************************************
- * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
- *                    VA Linux Systems Japan K.K.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- */
-
-
-#ifndef __ASM_PARAVIRT_H
-#define __ASM_PARAVIRT_H
-
-#ifndef __ASSEMBLY__
-/******************************************************************************
- * fsys related addresses
- */
-struct pv_fsys_data {
-	unsigned long *fsyscall_table;
-	void *fsys_bubble_down;
-};
-
-extern struct pv_fsys_data pv_fsys_data;
-
-unsigned long *paravirt_get_fsyscall_table(void);
-char *paravirt_get_fsys_bubble_down(void);
-
-/******************************************************************************
- * patchlist addresses for gate page
- */
-enum pv_gate_patchlist {
-	PV_GATE_START_FSYSCALL,
-	PV_GATE_END_FSYSCALL,
-
-	PV_GATE_START_BRL_FSYS_BUBBLE_DOWN,
-	PV_GATE_END_BRL_FSYS_BUBBLE_DOWN,
-
-	PV_GATE_START_VTOP,
-	PV_GATE_END_VTOP,
-
-	PV_GATE_START_MCKINLEY_E9,
-	PV_GATE_END_MCKINLEY_E9,
-};
-
-struct pv_patchdata {
-	unsigned long start_fsyscall_patchlist;
-	unsigned long end_fsyscall_patchlist;
-	unsigned long start_brl_fsys_bubble_down_patchlist;
-	unsigned long end_brl_fsys_bubble_down_patchlist;
-	unsigned long start_vtop_patchlist;
-	unsigned long end_vtop_patchlist;
-	unsigned long start_mckinley_e9_patchlist;
-	unsigned long end_mckinley_e9_patchlist;
-
-	void *gate_section;
-};
-
-extern struct pv_patchdata pv_patchdata;
-
-unsigned long paravirt_get_gate_patchlist(enum pv_gate_patchlist type);
-void *paravirt_get_gate_section(void);
-#endif
-
-#ifdef CONFIG_PARAVIRT_GUEST
-
-#define PARAVIRT_HYPERVISOR_TYPE_DEFAULT	0
-
-#ifndef __ASSEMBLY__
-
-#include <asm/hw_irq.h>
-#include <asm/meminit.h>
-
-/******************************************************************************
- * general info
- */
-struct pv_info {
-	unsigned int kernel_rpl;
-	int paravirt_enabled;
-	const char *name;
-};
-
-extern struct pv_info pv_info;
-
-static inline int paravirt_enabled(void)
-{
-	return pv_info.paravirt_enabled;
-}
-
-static inline unsigned int get_kernel_rpl(void)
-{
-	return pv_info.kernel_rpl;
-}
-
-/******************************************************************************
- * initialization hooks.
- */
-struct rsvd_region;
-
-struct pv_init_ops {
-	void (*banner)(void);
-
-	int (*reserve_memory)(struct rsvd_region *region);
-
-	void (*arch_setup_early)(void);
-	void (*arch_setup_console)(char **cmdline_p);
-	int (*arch_setup_nomca)(void);
-
-	void (*post_smp_prepare_boot_cpu)(void);
-
-#ifdef ASM_SUPPORTED
-	unsigned long (*patch_bundle)(void *sbundle, void *ebundle,
-				      unsigned long type);
-	unsigned long (*patch_inst)(unsigned long stag, unsigned long etag,
-				    unsigned long type);
-#endif
-	void (*patch_branch)(unsigned long tag, unsigned long type);
-};
-
-extern struct pv_init_ops pv_init_ops;
-
-static inline void paravirt_banner(void)
-{
-	if (pv_init_ops.banner)
-		pv_init_ops.banner();
-}
-
-static inline int paravirt_reserve_memory(struct rsvd_region *region)
-{
-	if (pv_init_ops.reserve_memory)
-		return pv_init_ops.reserve_memory(region);
-	return 0;
-}
-
-static inline void paravirt_arch_setup_early(void)
-{
-	if (pv_init_ops.arch_setup_early)
-		pv_init_ops.arch_setup_early();
-}
-
-static inline void paravirt_arch_setup_console(char **cmdline_p)
-{
-	if (pv_init_ops.arch_setup_console)
-		pv_init_ops.arch_setup_console(cmdline_p);
-}
-
-static inline int paravirt_arch_setup_nomca(void)
-{
-	if (pv_init_ops.arch_setup_nomca)
-		return pv_init_ops.arch_setup_nomca();
-	return 0;
-}
-
-static inline void paravirt_post_smp_prepare_boot_cpu(void)
-{
-	if (pv_init_ops.post_smp_prepare_boot_cpu)
-		pv_init_ops.post_smp_prepare_boot_cpu();
-}
-
-/******************************************************************************
- * replacement of iosapic operations.
- */
-
-struct pv_iosapic_ops {
-	void (*pcat_compat_init)(void);
-
-	struct irq_chip *(*__get_irq_chip)(unsigned long trigger);
-
-	unsigned int (*__read)(char __iomem *iosapic, unsigned int reg);
-	void (*__write)(char __iomem *iosapic, unsigned int reg, u32 val);
-};
-
-extern struct pv_iosapic_ops pv_iosapic_ops;
-
-static inline void
-iosapic_pcat_compat_init(void)
-{
-	if (pv_iosapic_ops.pcat_compat_init)
-		pv_iosapic_ops.pcat_compat_init();
-}
-
-static inline struct irq_chip*
-iosapic_get_irq_chip(unsigned long trigger)
-{
-	return pv_iosapic_ops.__get_irq_chip(trigger);
-}
-
-static inline unsigned int
-__iosapic_read(char __iomem *iosapic, unsigned int reg)
-{
-	return pv_iosapic_ops.__read(iosapic, reg);
-}
-
-static inline void
-__iosapic_write(char __iomem *iosapic, unsigned int reg, u32 val)
-{
-	return pv_iosapic_ops.__write(iosapic, reg, val);
-}
-
-/******************************************************************************
- * replacement of irq operations.
- */
-
-struct pv_irq_ops {
-	void (*register_ipi)(void);
-
-	int (*assign_irq_vector)(int irq);
-	void (*free_irq_vector)(int vector);
-
-	void (*register_percpu_irq)(ia64_vector vec,
-				    struct irqaction *action);
-
-	void (*resend_irq)(unsigned int vector);
-};
-
-extern struct pv_irq_ops pv_irq_ops;
-
-static inline void
-ia64_register_ipi(void)
-{
-	pv_irq_ops.register_ipi();
-}
-
-static inline int
-assign_irq_vector(int irq)
-{
-	return pv_irq_ops.assign_irq_vector(irq);
-}
-
-static inline void
-free_irq_vector(int vector)
-{
-	return pv_irq_ops.free_irq_vector(vector);
-}
-
-static inline void
-register_percpu_irq(ia64_vector vec, struct irqaction *action)
-{
-	pv_irq_ops.register_percpu_irq(vec, action);
-}
-
-static inline void
-ia64_resend_irq(unsigned int vector)
-{
-	pv_irq_ops.resend_irq(vector);
-}
-
-/******************************************************************************
- * replacement of time operations.
- */
-
-extern struct itc_jitter_data_t itc_jitter_data;
-extern volatile int time_keeper_id;
-
-struct pv_time_ops {
-	void (*init_missing_ticks_accounting)(int cpu);
-	int (*do_steal_accounting)(unsigned long *new_itm);
-
-	void (*clocksource_resume)(void);
-
-	unsigned long long (*sched_clock)(void);
-};
-
-extern struct pv_time_ops pv_time_ops;
-
-static inline void
-paravirt_init_missing_ticks_accounting(int cpu)
-{
-	if (pv_time_ops.init_missing_ticks_accounting)
-		pv_time_ops.init_missing_ticks_accounting(cpu);
-}
-
-struct static_key;
-extern struct static_key paravirt_steal_enabled;
-extern struct static_key paravirt_steal_rq_enabled;
-
-static inline int
-paravirt_do_steal_accounting(unsigned long *new_itm)
-{
-	return pv_time_ops.do_steal_accounting(new_itm);
-}
-
-static inline unsigned long long paravirt_sched_clock(void)
-{
-	return pv_time_ops.sched_clock();
-}
-
-#endif /* !__ASSEMBLY__ */
-
-#else
-/* fallback for native case */
-
-#ifndef __ASSEMBLY__
-
-#define paravirt_banner()				do { } while (0)
-#define paravirt_reserve_memory(region)			0
-
-#define paravirt_arch_setup_early()			do { } while (0)
-#define paravirt_arch_setup_console(cmdline_p)		do { } while (0)
-#define paravirt_arch_setup_nomca()			0
-#define paravirt_post_smp_prepare_boot_cpu()		do { } while (0)
-
-#define paravirt_init_missing_ticks_accounting(cpu)	do { } while (0)
-#define paravirt_do_steal_accounting(new_itm)		0
-
-#endif /* __ASSEMBLY__ */
-
-
-#endif /* CONFIG_PARAVIRT_GUEST */
-
-#endif /* __ASM_PARAVIRT_H */
diff --git a/arch/ia64/include/asm/paravirt_patch.h b/arch/ia64/include/asm/paravirt_patch.h
deleted file mode 100644
index 128ff5db6e67..000000000000
--- a/arch/ia64/include/asm/paravirt_patch.h
+++ /dev/null
@@ -1,143 +0,0 @@
-/******************************************************************************
- * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
- *                    VA Linux Systems Japan K.K.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- */
-
-#ifndef __ASM_PARAVIRT_PATCH_H
-#define __ASM_PARAVIRT_PATCH_H
-
-#ifdef __ASSEMBLY__
-
-	.section .paravirt_branches, "a"
-	.previous
-#define PARAVIRT_PATCH_SITE_BR(type)		\
-	{					\
-	[1:] ;					\
-	br.cond.sptk.many 2f ;			\
-	nop.b 0 ;				\
-	nop.b 0;; ;				\
-	} ;					\
-	2:					\
-	.xdata8 ".paravirt_branches", 1b, type
-
-#else
-
-#include <linux/stringify.h>
-#include <asm/intrinsics.h>
-
-/* for binary patch */
-struct paravirt_patch_site_bundle {
-	void		*sbundle;
-	void		*ebundle;
-	unsigned long	type;
-};
-
-/* label means the beginning of new bundle */
-#define paravirt_alt_bundle(instr, privop)				\
-	"\t998:\n"							\
-	"\t" instr "\n"							\
-	"\t999:\n"							\
-	"\t.pushsection .paravirt_bundles, \"a\"\n"			\
-	"\t.popsection\n"						\
-	"\t.xdata8 \".paravirt_bundles\", 998b, 999b, "			\
-	__stringify(privop) "\n"
-
-
-struct paravirt_patch_bundle_elem {
-	const void	*sbundle;
-	const void	*ebundle;
-	unsigned long	type;
-};
-
-
-struct paravirt_patch_site_inst {
-	unsigned long	stag;
-	unsigned long	etag;
-	unsigned long	type;
-};
-
-#define paravirt_alt_inst(instr, privop)				\
-	"\t[998:]\n"							\
-	"\t" instr "\n"							\
-	"\t[999:]\n"							\
-	"\t.pushsection .paravirt_insts, \"a\"\n"			\
-	"\t.popsection\n"						\
-	"\t.xdata8 \".paravirt_insts\", 998b, 999b, "			\
-	__stringify(privop) "\n"
-
-struct paravirt_patch_site_branch {
-	unsigned long	tag;
-	unsigned long	type;
-};
-
-struct paravirt_patch_branch_target {
-	const void	*entry;
-	unsigned long	type;
-};
-
-void
-__paravirt_patch_apply_branch(
-	unsigned long tag, unsigned long type,
-	const struct paravirt_patch_branch_target *entries,
-	unsigned int nr_entries);
-
-void
-paravirt_patch_reloc_br(unsigned long tag, const void *target);
-
-void
-paravirt_patch_reloc_brl(unsigned long tag, const void *target);
-
-
-#if defined(ASM_SUPPORTED) && defined(CONFIG_PARAVIRT)
-unsigned long
-ia64_native_patch_bundle(void *sbundle, void *ebundle, unsigned long type);
-
-unsigned long
-__paravirt_patch_apply_bundle(void *sbundle, void *ebundle, unsigned long type,
-			      const struct paravirt_patch_bundle_elem *elems,
-			      unsigned long nelems,
-			      const struct paravirt_patch_bundle_elem **found);
-
-void
-paravirt_patch_apply_bundle(const struct paravirt_patch_site_bundle *start,
-			    const struct paravirt_patch_site_bundle *end);
-
-void
-paravirt_patch_apply_inst(const struct paravirt_patch_site_inst *start,
-			  const struct paravirt_patch_site_inst *end);
-
-void paravirt_patch_apply(void);
-#else
-#define paravirt_patch_apply_bundle(start, end)	do { } while (0)
-#define paravirt_patch_apply_inst(start, end)	do { } while (0)
-#define paravirt_patch_apply()			do { } while (0)
-#endif
-
-#endif /* !__ASSEMBLEY__ */
-
-#endif /* __ASM_PARAVIRT_PATCH_H */
-
-/*
- * Local variables:
- * mode: C
- * c-set-style: "linux"
- * c-basic-offset: 8
- * tab-width: 8
- * indent-tabs-mode: t
- * End:
- */
diff --git a/arch/ia64/include/asm/paravirt_privop.h b/arch/ia64/include/asm/paravirt_privop.h
deleted file mode 100644
index 8f6cb11c9fae..000000000000
--- a/arch/ia64/include/asm/paravirt_privop.h
+++ /dev/null
@@ -1,479 +0,0 @@
-/******************************************************************************
- * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
- *                    VA Linux Systems Japan K.K.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- */
-
-#ifndef _ASM_IA64_PARAVIRT_PRIVOP_H
-#define _ASM_IA64_PARAVIRT_PRIVOP_H
-
-#ifdef CONFIG_PARAVIRT
-
-#ifndef __ASSEMBLY__
-
-#include <linux/types.h>
-#include <asm/kregs.h> /* for IA64_PSR_I */
-
-/******************************************************************************
- * replacement of intrinsics operations.
- */
-
-struct pv_cpu_ops {
-	void (*fc)(void *addr);
-	unsigned long (*thash)(unsigned long addr);
-	unsigned long (*get_cpuid)(int index);
-	unsigned long (*get_pmd)(int index);
-	unsigned long (*getreg)(int reg);
-	void (*setreg)(int reg, unsigned long val);
-	void (*ptcga)(unsigned long addr, unsigned long size);
-	unsigned long (*get_rr)(unsigned long index);
-	void (*set_rr)(unsigned long index, unsigned long val);
-	void (*set_rr0_to_rr4)(unsigned long val0, unsigned long val1,
-			       unsigned long val2, unsigned long val3,
-			       unsigned long val4);
-	void (*ssm_i)(void);
-	void (*rsm_i)(void);
-	unsigned long (*get_psr_i)(void);
-	void (*intrin_local_irq_restore)(unsigned long flags);
-};
-
-extern struct pv_cpu_ops pv_cpu_ops;
-
-extern void ia64_native_setreg_func(int regnum, unsigned long val);
-extern unsigned long ia64_native_getreg_func(int regnum);
-
-/************************************************/
-/* Instructions paravirtualized for performance */
-/************************************************/
-
-#ifndef ASM_SUPPORTED
-#define paravirt_ssm_i()	pv_cpu_ops.ssm_i()
-#define paravirt_rsm_i()	pv_cpu_ops.rsm_i()
-#define __paravirt_getreg()	pv_cpu_ops.getreg()
-#endif
-
-/* mask for ia64_native_ssm/rsm() must be constant.("i" constraing).
- * static inline function doesn't satisfy it. */
-#define paravirt_ssm(mask)			\
-	do {					\
-		if ((mask) == IA64_PSR_I)	\
-			paravirt_ssm_i();	\
-		else				\
-			ia64_native_ssm(mask);	\
-	} while (0)
-
-#define paravirt_rsm(mask)			\
-	do {					\
-		if ((mask) == IA64_PSR_I)	\
-			paravirt_rsm_i();	\
-		else				\
-			ia64_native_rsm(mask);	\
-	} while (0)
-
-/* returned ip value should be the one in the caller,
- * not in __paravirt_getreg() */
-#define paravirt_getreg(reg)					\
-	({							\
-		unsigned long res;				\
-		if ((reg) == _IA64_REG_IP)			\
-			res = ia64_native_getreg(_IA64_REG_IP); \
-		else						\
-			res = __paravirt_getreg(reg);		\
-		res;						\
-	})
-
-/******************************************************************************
- * replacement of hand written assembly codes.
- */
-struct pv_cpu_asm_switch {
-	unsigned long switch_to;
-	unsigned long leave_syscall;
-	unsigned long work_processed_syscall;
-	unsigned long leave_kernel;
-};
-void paravirt_cpu_asm_init(const struct pv_cpu_asm_switch *cpu_asm_switch);
-
-#endif /* __ASSEMBLY__ */
-
-#define IA64_PARAVIRT_ASM_FUNC(name)	paravirt_ ## name
-
-#else
-
-/* fallback for native case */
-#define IA64_PARAVIRT_ASM_FUNC(name)	ia64_native_ ## name
-
-#endif /* CONFIG_PARAVIRT */
-
-#if defined(CONFIG_PARAVIRT) && defined(ASM_SUPPORTED)
-#define paravirt_dv_serialize_data()	ia64_dv_serialize_data()
-#else
-#define paravirt_dv_serialize_data()	/* nothing */
-#endif
-
-/* these routines utilize privilege-sensitive or performance-sensitive
- * privileged instructions so the code must be replaced with
- * paravirtualized versions */
-#define ia64_switch_to			IA64_PARAVIRT_ASM_FUNC(switch_to)
-#define ia64_leave_syscall		IA64_PARAVIRT_ASM_FUNC(leave_syscall)
-#define ia64_work_processed_syscall	\
-	IA64_PARAVIRT_ASM_FUNC(work_processed_syscall)
-#define ia64_leave_kernel		IA64_PARAVIRT_ASM_FUNC(leave_kernel)
-
-
-#if defined(CONFIG_PARAVIRT)
-/******************************************************************************
- * binary patching infrastructure
- */
-#define PARAVIRT_PATCH_TYPE_FC				1
-#define PARAVIRT_PATCH_TYPE_THASH			2
-#define PARAVIRT_PATCH_TYPE_GET_CPUID			3
-#define PARAVIRT_PATCH_TYPE_GET_PMD			4
-#define PARAVIRT_PATCH_TYPE_PTCGA			5
-#define PARAVIRT_PATCH_TYPE_GET_RR			6
-#define PARAVIRT_PATCH_TYPE_SET_RR			7
-#define PARAVIRT_PATCH_TYPE_SET_RR0_TO_RR4		8
-#define PARAVIRT_PATCH_TYPE_SSM_I			9
-#define PARAVIRT_PATCH_TYPE_RSM_I			10
-#define PARAVIRT_PATCH_TYPE_GET_PSR_I			11
-#define PARAVIRT_PATCH_TYPE_INTRIN_LOCAL_IRQ_RESTORE	12
-
-/* PARAVIRT_PATY_TYPE_[GS]ETREG + _IA64_REG_xxx */
-#define PARAVIRT_PATCH_TYPE_GETREG			0x10000000
-#define PARAVIRT_PATCH_TYPE_SETREG			0x20000000
-
-/*
- * struct task_struct* (*ia64_switch_to)(void* next_task);
- * void *ia64_leave_syscall;
- * void *ia64_work_processed_syscall
- * void *ia64_leave_kernel;
- */
-
-#define PARAVIRT_PATCH_TYPE_BR_START			0x30000000
-#define PARAVIRT_PATCH_TYPE_BR_SWITCH_TO		\
-	(PARAVIRT_PATCH_TYPE_BR_START + 0)
-#define PARAVIRT_PATCH_TYPE_BR_LEAVE_SYSCALL		\
-	(PARAVIRT_PATCH_TYPE_BR_START + 1)
-#define PARAVIRT_PATCH_TYPE_BR_WORK_PROCESSED_SYSCALL	\
-	(PARAVIRT_PATCH_TYPE_BR_START + 2)
-#define PARAVIRT_PATCH_TYPE_BR_LEAVE_KERNEL		\
-	(PARAVIRT_PATCH_TYPE_BR_START + 3)
-
-#ifdef ASM_SUPPORTED
-#include <asm/paravirt_patch.h>
-
-/*
- * pv_cpu_ops calling stub.
- * normal function call convension can't be written by gcc
- * inline assembly.
- *
- * from the caller's point of view,
- * the following registers will be clobbered.
- * r2, r3
- * r8-r15
- * r16, r17
- * b6, b7
- * p6-p15
- * ar.ccv
- *
- * from the callee's point of view ,
- * the following registers can be used.
- * r2, r3: scratch
- * r8: scratch, input argument0 and return value
- * r0-r15: scratch, input argument1-5
- * b6: return pointer
- * b7: scratch
- * p6-p15: scratch
- * ar.ccv: scratch
- *
- * other registers must not be changed. especially
- * b0: rp: preserved. gcc ignores b0 in clobbered register.
- * r16: saved gp
- */
-/* 5 bundles */
-#define __PARAVIRT_BR							\
-	";;\n"								\
-	"{ .mlx\n"							\
-	"nop 0\n"							\
-	"movl r2 = %[op_addr]\n"/* get function pointer address */	\
-	";;\n"								\
-	"}\n"								\
-	"1:\n"								\
-	"{ .mii\n"							\
-	"ld8 r2 = [r2]\n"	/* load function descriptor address */	\
-	"mov r17 = ip\n"	/* get ip to calc return address */	\
-	"mov r16 = gp\n"	/* save gp */				\
-	";;\n"								\
-	"}\n"								\
-	"{ .mii\n"							\
-	"ld8 r3 = [r2], 8\n"	/* load entry address */		\
-	"adds r17 =  1f - 1b, r17\n"	/* calculate return address */	\
-	";;\n"								\
-	"mov b7 = r3\n"		/* set entry address */			\
-	"}\n"								\
-	"{ .mib\n"							\
-	"ld8 gp = [r2]\n"	/* load gp value */			\
-	"mov b6 = r17\n"	/* set return address */		\
-	"br.cond.sptk.few b7\n"	/* intrinsics are very short isns */	\
-	"}\n"								\
-	"1:\n"								\
-	"{ .mii\n"							\
-	"mov gp = r16\n"	/* restore gp value */			\
-	"nop 0\n"							\
-	"nop 0\n"							\
-	";;\n"								\
-	"}\n"
-
-#define PARAVIRT_OP(op)				\
-	[op_addr] "i"(&pv_cpu_ops.op)
-
-#define PARAVIRT_TYPE(type)			\
-	PARAVIRT_PATCH_TYPE_ ## type
-
-#define PARAVIRT_REG_CLOBBERS0					\
-	"r2", "r3", /*"r8",*/ "r9", "r10", "r11", "r14",	\
-		"r15", "r16", "r17"
-
-#define PARAVIRT_REG_CLOBBERS1					\
-	"r2","r3", /*"r8",*/ "r9", "r10", "r11", "r14",		\
-		"r15", "r16", "r17"
-
-#define PARAVIRT_REG_CLOBBERS2					\
-	"r2", "r3", /*"r8", "r9",*/ "r10", "r11", "r14",	\
-		"r15", "r16", "r17"
-
-#define PARAVIRT_REG_CLOBBERS5					\
-	"r2", "r3", /*"r8", "r9", "r10", "r11", "r14",*/	\
-		"r15", "r16", "r17"
-
-#define PARAVIRT_BR_CLOBBERS			\
-	"b6", "b7"
-
-#define PARAVIRT_PR_CLOBBERS						\
-	"p6", "p7", "p8", "p9", "p10", "p11", "p12", "p13", "p14", "p15"
-
-#define PARAVIRT_AR_CLOBBERS			\
-	"ar.ccv"
-
-#define PARAVIRT_CLOBBERS0			\
-		PARAVIRT_REG_CLOBBERS0,		\
-		PARAVIRT_BR_CLOBBERS,		\
-		PARAVIRT_PR_CLOBBERS,		\
-		PARAVIRT_AR_CLOBBERS,		\
-		"memory"
-
-#define PARAVIRT_CLOBBERS1			\
-		PARAVIRT_REG_CLOBBERS1,		\
-		PARAVIRT_BR_CLOBBERS,		\
-		PARAVIRT_PR_CLOBBERS,		\
-		PARAVIRT_AR_CLOBBERS,		\
-		"memory"
-
-#define PARAVIRT_CLOBBERS2			\
-		PARAVIRT_REG_CLOBBERS2,		\
-		PARAVIRT_BR_CLOBBERS,		\
-		PARAVIRT_PR_CLOBBERS,		\
-		PARAVIRT_AR_CLOBBERS,		\
-		"memory"
-
-#define PARAVIRT_CLOBBERS5			\
-		PARAVIRT_REG_CLOBBERS5,		\
-		PARAVIRT_BR_CLOBBERS,		\
-		PARAVIRT_PR_CLOBBERS,		\
-		PARAVIRT_AR_CLOBBERS,		\
-		"memory"
-
-#define PARAVIRT_BR0(op, type)					\
-	register unsigned long ia64_clobber asm ("r8");		\
-	asm volatile (paravirt_alt_bundle(__PARAVIRT_BR,	\
-					  PARAVIRT_TYPE(type))	\
-		      :	"=r"(ia64_clobber)			\
-		      : PARAVIRT_OP(op)				\
-		      : PARAVIRT_CLOBBERS0)
-
-#define PARAVIRT_BR0_RET(op, type)				\
-	register unsigned long ia64_intri_res asm ("r8");	\
-	asm volatile (paravirt_alt_bundle(__PARAVIRT_BR,	\
-					  PARAVIRT_TYPE(type))	\
-		      : "=r"(ia64_intri_res)			\
-		      : PARAVIRT_OP(op)				\
-		      : PARAVIRT_CLOBBERS0)
-
-#define PARAVIRT_BR1(op, type, arg1)				\
-	register unsigned long __##arg1 asm ("r8") = arg1;	\
-	register unsigned long ia64_clobber asm ("r8");		\
-	asm volatile (paravirt_alt_bundle(__PARAVIRT_BR,	\
-					  PARAVIRT_TYPE(type))	\
-		      :	"=r"(ia64_clobber)			\
-		      : PARAVIRT_OP(op), "0"(__##arg1)		\
-		      : PARAVIRT_CLOBBERS1)
-
-#define PARAVIRT_BR1_RET(op, type, arg1)			\
-	register unsigned long ia64_intri_res asm ("r8");	\
-	register unsigned long __##arg1 asm ("r8") = arg1;	\
-	asm volatile (paravirt_alt_bundle(__PARAVIRT_BR,	\
-					  PARAVIRT_TYPE(type))	\
-		      : "=r"(ia64_intri_res)			\
-		      : PARAVIRT_OP(op), "0"(__##arg1)		\
-		      : PARAVIRT_CLOBBERS1)
-
-#define PARAVIRT_BR1_VOID(op, type, arg1)			\
-	register void *__##arg1 asm ("r8") = arg1;		\
-	register unsigned long ia64_clobber asm ("r8");		\
-	asm volatile (paravirt_alt_bundle(__PARAVIRT_BR,	\
-					  PARAVIRT_TYPE(type))	\
-		      :	"=r"(ia64_clobber)			\
-		      : PARAVIRT_OP(op), "0"(__##arg1)		\
-		      : PARAVIRT_CLOBBERS1)
-
-#define PARAVIRT_BR2(op, type, arg1, arg2)				\
-	register unsigned long __##arg1 asm ("r8") = arg1;		\
-	register unsigned long __##arg2 asm ("r9") = arg2;		\
-	register unsigned long ia64_clobber1 asm ("r8");		\
-	register unsigned long ia64_clobber2 asm ("r9");		\
-	asm volatile (paravirt_alt_bundle(__PARAVIRT_BR,		\
-					  PARAVIRT_TYPE(type))		\
-		      : "=r"(ia64_clobber1), "=r"(ia64_clobber2)	\
-		      : PARAVIRT_OP(op), "0"(__##arg1), "1"(__##arg2)	\
-		      : PARAVIRT_CLOBBERS2)
-
-
-#define PARAVIRT_DEFINE_CPU_OP0(op, type)		\
-	static inline void				\
-	paravirt_ ## op (void)				\
-	{						\
-		PARAVIRT_BR0(op, type);			\
-	}
-
-#define PARAVIRT_DEFINE_CPU_OP0_RET(op, type)		\
-	static inline unsigned long			\
-	paravirt_ ## op (void)				\
-	{						\
-		PARAVIRT_BR0_RET(op, type);		\
-		return ia64_intri_res;			\
-	}
-
-#define PARAVIRT_DEFINE_CPU_OP1_VOID(op, type)		\
-	static inline void				\
-	paravirt_ ## op (void *arg1)			\
-	{						\
-		PARAVIRT_BR1_VOID(op, type, arg1);	\
-	}
-
-#define PARAVIRT_DEFINE_CPU_OP1(op, type)		\
-	static inline void				\
-	paravirt_ ## op (unsigned long arg1)		\
-	{						\
-		PARAVIRT_BR1(op, type, arg1);		\
-	}
-
-#define PARAVIRT_DEFINE_CPU_OP1_RET(op, type)		\
-	static inline unsigned long			\
-	paravirt_ ## op (unsigned long arg1)		\
-	{						\
-		PARAVIRT_BR1_RET(op, type, arg1);	\
-		return ia64_intri_res;			\
-	}
-
-#define PARAVIRT_DEFINE_CPU_OP2(op, type)		\
-	static inline void				\
-	paravirt_ ## op (unsigned long arg1,		\
-			 unsigned long arg2)		\
-	{						\
-		PARAVIRT_BR2(op, type, arg1, arg2);	\
-	}
-
-
-PARAVIRT_DEFINE_CPU_OP1_VOID(fc, FC);
-PARAVIRT_DEFINE_CPU_OP1_RET(thash, THASH)
-PARAVIRT_DEFINE_CPU_OP1_RET(get_cpuid, GET_CPUID)
-PARAVIRT_DEFINE_CPU_OP1_RET(get_pmd, GET_PMD)
-PARAVIRT_DEFINE_CPU_OP2(ptcga, PTCGA)
-PARAVIRT_DEFINE_CPU_OP1_RET(get_rr, GET_RR)
-PARAVIRT_DEFINE_CPU_OP2(set_rr, SET_RR)
-PARAVIRT_DEFINE_CPU_OP0(ssm_i, SSM_I)
-PARAVIRT_DEFINE_CPU_OP0(rsm_i, RSM_I)
-PARAVIRT_DEFINE_CPU_OP0_RET(get_psr_i, GET_PSR_I)
-PARAVIRT_DEFINE_CPU_OP1(intrin_local_irq_restore, INTRIN_LOCAL_IRQ_RESTORE)
-
-static inline void
-paravirt_set_rr0_to_rr4(unsigned long val0, unsigned long val1,
-			unsigned long val2, unsigned long val3,
-			unsigned long val4)
-{
-	register unsigned long __val0 asm ("r8") = val0;
-	register unsigned long __val1 asm ("r9") = val1;
-	register unsigned long __val2 asm ("r10") = val2;
-	register unsigned long __val3 asm ("r11") = val3;
-	register unsigned long __val4 asm ("r14") = val4;
-
-	register unsigned long ia64_clobber0 asm ("r8");
-	register unsigned long ia64_clobber1 asm ("r9");
-	register unsigned long ia64_clobber2 asm ("r10");
-	register unsigned long ia64_clobber3 asm ("r11");
-	register unsigned long ia64_clobber4 asm ("r14");
-
-	asm volatile (paravirt_alt_bundle(__PARAVIRT_BR,
-					  PARAVIRT_TYPE(SET_RR0_TO_RR4))
-		      : "=r"(ia64_clobber0),
-			"=r"(ia64_clobber1),
-			"=r"(ia64_clobber2),
-			"=r"(ia64_clobber3),
-			"=r"(ia64_clobber4)
-		      : PARAVIRT_OP(set_rr0_to_rr4),
-			"0"(__val0), "1"(__val1), "2"(__val2),
-			"3"(__val3), "4"(__val4)
-		      : PARAVIRT_CLOBBERS5);
-}
-
-/* unsigned long paravirt_getreg(int reg) */
-#define __paravirt_getreg(reg)						\
-	({								\
-		register unsigned long ia64_intri_res asm ("r8");	\
-		register unsigned long __reg asm ("r8") = (reg);	\
-									\
-		asm volatile (paravirt_alt_bundle(__PARAVIRT_BR,	\
-						  PARAVIRT_TYPE(GETREG) \
-						  + (reg))		\
-			      : "=r"(ia64_intri_res)			\
-			      : PARAVIRT_OP(getreg), "0"(__reg)		\
-			      : PARAVIRT_CLOBBERS1);			\
-									\
-		ia64_intri_res;						\
-	})
-
-/* void paravirt_setreg(int reg, unsigned long val) */
-#define paravirt_setreg(reg, val)					\
-	do {								\
-		register unsigned long __val asm ("r8") = val;		\
-		register unsigned long __reg asm ("r9") = reg;		\
-		register unsigned long ia64_clobber1 asm ("r8");	\
-		register unsigned long ia64_clobber2 asm ("r9");	\
-									\
-		asm volatile (paravirt_alt_bundle(__PARAVIRT_BR,	\
-						  PARAVIRT_TYPE(SETREG) \
-						  + (reg))		\
-			      : "=r"(ia64_clobber1),			\
-				"=r"(ia64_clobber2)			\
-			      : PARAVIRT_OP(setreg),			\
-				"1"(__reg), "0"(__val)			\
-			      : PARAVIRT_CLOBBERS2);			\
-	} while (0)
-
-#endif /* ASM_SUPPORTED */
-#endif /* CONFIG_PARAVIRT && ASM_SUPPOTED */
-
-#endif /* _ASM_IA64_PARAVIRT_PRIVOP_H */
diff --git a/arch/ia64/include/asm/pci.h b/arch/ia64/include/asm/pci.h
index 52af5ed9f60b..b897fae1f0ca 100644
--- a/arch/ia64/include/asm/pci.h
+++ b/arch/ia64/include/asm/pci.h
@@ -52,25 +52,6 @@ extern unsigned long ia64_max_iommu_merge_mask;
 
 #include <asm-generic/pci-dma-compat.h>
 
-#ifdef CONFIG_PCI
-static inline void pci_dma_burst_advice(struct pci_dev *pdev,
-					enum pci_dma_burst_strategy *strat,
-					unsigned long *strategy_parameter)
-{
-	unsigned long cacheline_size;
-	u8 byte;
-
-	pci_read_config_byte(pdev, PCI_CACHE_LINE_SIZE, &byte);
-	if (byte == 0)
-		cacheline_size = 1024;
-	else
-		cacheline_size = (int) byte * 4;
-
-	*strat = PCI_DMA_BURST_MULTIPLE;
-	*strategy_parameter = cacheline_size;
-}
-#endif
-
 #define HAVE_PCI_MMAP
 extern int pci_mmap_page_range (struct pci_dev *dev, struct vm_area_struct *vma,
 				enum pci_mmap_state mmap_state, int write_combine);
@@ -108,19 +89,6 @@ static inline int pci_proc_domain(struct pci_bus *bus)
 	return (pci_domain_nr(bus) != 0);
 }
 
-static inline struct resource *
-pcibios_select_root(struct pci_dev *pdev, struct resource *res)
-{
-	struct resource *root = NULL;
-
-	if (res->flags & IORESOURCE_IO)
-		root = &ioport_resource;
-	if (res->flags & IORESOURCE_MEM)
-		root = &iomem_resource;
-
-	return root;
-}
-
 #define HAVE_ARCH_PCI_GET_LEGACY_IDE_IRQ
 static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
 {
diff --git a/arch/ia64/include/asm/topology.h b/arch/ia64/include/asm/topology.h
index 6437ca21f61b..3ad8f6988363 100644
--- a/arch/ia64/include/asm/topology.h
+++ b/arch/ia64/include/asm/topology.h
@@ -53,7 +53,7 @@ void build_cpu_to_node_map(void);
 #define topology_physical_package_id(cpu)	(cpu_data(cpu)->socket_id)
 #define topology_core_id(cpu)			(cpu_data(cpu)->core_id)
 #define topology_core_cpumask(cpu)		(&cpu_core_map[cpu])
-#define topology_thread_cpumask(cpu)		(&per_cpu(cpu_sibling_map, cpu))
+#define topology_sibling_cpumask(cpu)		(&per_cpu(cpu_sibling_map, cpu))
 #endif
 
 extern void arch_fix_phys_package_id(int num, u32 slot);
diff --git a/arch/ia64/include/uapi/asm/cmpxchg.h b/arch/ia64/include/uapi/asm/cmpxchg.h
index f35109b1d907..a0e3620f8f13 100644
--- a/arch/ia64/include/uapi/asm/cmpxchg.h
+++ b/arch/ia64/include/uapi/asm/cmpxchg.h
@@ -61,8 +61,6 @@ extern void ia64_xchg_called_with_bad_pointer(void);
  * indicated by comparing RETURN with OLD.
  */
 
-#define __HAVE_ARCH_CMPXCHG 1
-
 /*
  * This function doesn't exist, so you'll get a linker error
  * if something tries to do an invalid cmpxchg().
diff --git a/arch/ia64/kernel/Makefile b/arch/ia64/kernel/Makefile
index d68b5cf81e31..3686d6abafde 100644
--- a/arch/ia64/kernel/Makefile
+++ b/arch/ia64/kernel/Makefile
@@ -9,7 +9,7 @@ endif
 extra-y	:= head.o init_task.o vmlinux.lds
 
 obj-y := entry.o efi.o efi_stub.o gate-data.o fsys.o ia64_ksyms.o irq.o irq_ia64.o	\
-	 irq_lsapic.o ivt.o machvec.o pal.o paravirt_patchlist.o patch.o process.o perfmon.o ptrace.o sal.o		\
+	 irq_lsapic.o ivt.o machvec.o pal.o patch.o process.o perfmon.o ptrace.o sal.o		\
 	 salinfo.o setup.o signal.o sys_ia64.o time.o traps.o unaligned.o \
 	 unwind.o mca.o mca_asm.o topology.o dma-mapping.o
 
@@ -35,9 +35,6 @@ mca_recovery-y			+= mca_drv.o mca_drv_asm.o
 obj-$(CONFIG_IA64_MC_ERR_INJECT)+= err_inject.o
 obj-$(CONFIG_STACKTRACE)	+= stacktrace.o
 
-obj-$(CONFIG_PARAVIRT)		+= paravirt.o paravirtentry.o \
-				   paravirt_patch.o
-
 obj-$(CONFIG_IA64_ESI)		+= esi.o
 ifneq ($(CONFIG_IA64_ESI),)
 obj-y				+= esi_stub.o	# must be in kernel proper
@@ -52,8 +49,6 @@ CFLAGS_traps.o  += -mfixed-range=f2-f5,f16-f31
 
 # The gate DSO image is built using a special linker script.
 include $(src)/Makefile.gate
-# tell compiled for native
-CPPFLAGS_gate.lds += -D__IA64_GATE_PARAVIRTUALIZED_NATIVE
 
 # Calculate NR_IRQ = max(IA64_NATIVE_NR_IRQS, XEN_NR_IRQS, ...) based on config
 define sed-y
@@ -84,30 +79,3 @@ arch/$(SRCARCH)/kernel/nr-irqs.s: arch/$(SRCARCH)/kernel/nr-irqs.c
 include/generated/nr-irqs.h: arch/$(SRCARCH)/kernel/nr-irqs.s
 	$(Q)mkdir -p $(dir $@)
 	$(call cmd,nr_irqs)
-
-#
-# native ivt.S, entry.S and fsys.S
-#
-ASM_PARAVIRT_OBJS = ivt.o entry.o fsys.o
-define paravirtualized_native
-AFLAGS_$(1) += -D__IA64_ASM_PARAVIRTUALIZED_NATIVE
-AFLAGS_pvchk-sed-$(1) += -D__IA64_ASM_PARAVIRTUALIZED_PVCHECK
-extra-y += pvchk-$(1)
-endef
-$(foreach obj,$(ASM_PARAVIRT_OBJS),$(eval $(call paravirtualized_native,$(obj))))
-
-#
-# Checker for paravirtualizations of privileged operations.
-#
-quiet_cmd_pv_check_sed = PVCHK   $@
-define cmd_pv_check_sed
-	sed -f $(srctree)/arch/$(SRCARCH)/scripts/pvcheck.sed $< > $@
-endef
-
-$(obj)/pvchk-sed-%.s: $(src)/%.S $(srctree)/arch/$(SRCARCH)/scripts/pvcheck.sed FORCE
-	$(call if_changed_dep,as_s_S)
-$(obj)/pvchk-%.s: $(obj)/pvchk-sed-%.s FORCE
-	$(call if_changed,pv_check_sed)
-$(obj)/pvchk-%.o: $(obj)/pvchk-%.s FORCE
-	$(call if_changed,as_o_S)
-.PRECIOUS: $(obj)/pvchk-sed-%.s $(obj)/pvchk-%.s $(obj)/pvchk-%.o
diff --git a/arch/ia64/kernel/efi.c b/arch/ia64/kernel/efi.c
index c52d7540dc05..47e962f7ed5a 100644
--- a/arch/ia64/kernel/efi.c
+++ b/arch/ia64/kernel/efi.c
@@ -464,7 +464,6 @@ efi_map_pal_code (void)
 		 GRANULEROUNDDOWN((unsigned long) pal_vaddr),
 		 pte_val(pfn_pte(__pa(pal_vaddr) >> PAGE_SHIFT, PAGE_KERNEL)),
 		 IA64_GRANULE_SHIFT);
-	paravirt_dv_serialize_data();
 	ia64_set_psr(psr);		/* restore psr */
 }
 
diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S
index fcf8b8cbca0b..ae0de7bf5525 100644
--- a/arch/ia64/kernel/entry.S
+++ b/arch/ia64/kernel/entry.S
@@ -51,7 +51,6 @@
 
 #include "minstate.h"
 
-#ifdef __IA64_ASM_PARAVIRTUALIZED_NATIVE
 	/*
 	 * execve() is special because in case of success, we need to
 	 * setup a null register window frame.
@@ -161,7 +160,6 @@ GLOBAL_ENTRY(sys_clone)
 	mov rp=loc0
 	br.ret.sptk.many rp
 END(sys_clone)
-#endif /* __IA64_ASM_PARAVIRTUALIZED_NATIVE */
 
 /*
  * prev_task <- ia64_switch_to(struct task_struct *next)
@@ -169,7 +167,7 @@ END(sys_clone)
  *	called.  The code starting at .map relies on this.  The rest of the code
  *	doesn't care about the interrupt masking status.
  */
-GLOBAL_ENTRY(__paravirt_switch_to)
+GLOBAL_ENTRY(ia64_switch_to)
 	.prologue
 	alloc r16=ar.pfs,1,0,0,0
 	DO_SAVE_SWITCH_STACK
@@ -221,9 +219,8 @@ GLOBAL_ENTRY(__paravirt_switch_to)
 	itr.d dtr[r25]=r23		// wire in new mapping...
 	SSM_PSR_IC_AND_SRLZ_D(r8, r9)	// reenable the psr.ic bit
 	br.cond.sptk .done
-END(__paravirt_switch_to)
+END(ia64_switch_to)
 
-#ifdef __IA64_ASM_PARAVIRTUALIZED_NATIVE
 /*
  * Note that interrupts are enabled during save_switch_stack and load_switch_stack.  This
  * means that we may get an interrupt with "sp" pointing to the new kernel stack while
@@ -639,16 +636,8 @@ GLOBAL_ENTRY(ia64_ret_from_syscall)
 	adds r2=PT(R8)+16,sp			// r2 = &pt_regs.r8
 	mov r10=r0				// clear error indication in r10
 (p7)	br.cond.spnt handle_syscall_error	// handle potential syscall failure
-#ifdef CONFIG_PARAVIRT
-	;;
-	br.cond.sptk.few ia64_leave_syscall
-	;;
-#endif /* CONFIG_PARAVIRT */
 END(ia64_ret_from_syscall)
-#ifndef CONFIG_PARAVIRT
 	// fall through
-#endif
-#endif /* __IA64_ASM_PARAVIRTUALIZED_NATIVE */
 
 /*
  * ia64_leave_syscall(): Same as ia64_leave_kernel, except that it doesn't
@@ -694,7 +683,7 @@ END(ia64_ret_from_syscall)
  *	      ar.csd: cleared
  *	      ar.ssd: cleared
  */
-GLOBAL_ENTRY(__paravirt_leave_syscall)
+GLOBAL_ENTRY(ia64_leave_syscall)
 	PT_REGS_UNWIND_INFO(0)
 	/*
 	 * work.need_resched etc. mustn't get changed by this CPU before it returns to
@@ -722,8 +711,8 @@ GLOBAL_ENTRY(__paravirt_leave_syscall)
 	cmp.eq pLvSys,p0=r0,r0		// pLvSys=1: leave from syscall
 (pUStk)	cmp.eq.unc p6,p0=r0,r0		// p6 <- pUStk
 #endif
-.global __paravirt_work_processed_syscall;
-__paravirt_work_processed_syscall:
+.global ia64_work_processed_syscall;
+ia64_work_processed_syscall:
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 	adds r2=PT(LOADRS)+16,r12
 	MOV_FROM_ITC(pUStk, p9, r22, r19)	// fetch time at leave
@@ -836,9 +825,9 @@ __paravirt_work_processed_syscall:
 	mov.m ar.ssd=r0			// M2   clear ar.ssd
 	mov f11=f0			// F    clear f11
 	br.cond.sptk.many rbs_switch	// B
-END(__paravirt_leave_syscall)
+END(ia64_leave_syscall)
 
-GLOBAL_ENTRY(__paravirt_leave_kernel)
+GLOBAL_ENTRY(ia64_leave_kernel)
 	PT_REGS_UNWIND_INFO(0)
 	/*
 	 * work.need_resched etc. mustn't get changed by this CPU before it returns to
@@ -1171,26 +1160,25 @@ skip_rbs_switch:
 (p6)	br.cond.sptk.few .notify
 	br.call.spnt.many rp=preempt_schedule_irq
 .ret9:	cmp.eq p6,p0=r0,r0	// p6 <- 1 (re-check)
-(pLvSys)br.cond.sptk.few  __paravirt_pending_syscall_end
+(pLvSys)br.cond.sptk.few  ia64_work_pending_syscall_end
 	br.cond.sptk.many .work_processed_kernel
 
 .notify:
 (pUStk)	br.call.spnt.many rp=notify_resume_user
 .ret10:	cmp.ne p6,p0=r0,r0	// p6 <- 0 (don't re-check)
-(pLvSys)br.cond.sptk.few  __paravirt_pending_syscall_end
+(pLvSys)br.cond.sptk.few  ia64_work_pending_syscall_end
 	br.cond.sptk.many .work_processed_kernel
 
-.global __paravirt_pending_syscall_end;
-__paravirt_pending_syscall_end:
+.global ia64_work_pending_syscall_end;
+ia64_work_pending_syscall_end:
 	adds r2=PT(R8)+16,r12
 	adds r3=PT(R10)+16,r12
 	;;
 	ld8 r8=[r2]
 	ld8 r10=[r3]
-	br.cond.sptk.many __paravirt_work_processed_syscall_target
-END(__paravirt_leave_kernel)
+	br.cond.sptk.many ia64_work_processed_syscall
+END(ia64_leave_kernel)
 
-#ifdef __IA64_ASM_PARAVIRTUALIZED_NATIVE
 ENTRY(handle_syscall_error)
 	/*
 	 * Some system calls (e.g., ptrace, mmap) can return arbitrary values which could
@@ -1294,7 +1282,7 @@ ENTRY(sys_rt_sigreturn)
 	adds sp=16,sp
 	;;
 	ld8 r9=[sp]				// load new ar.unat
-	mov.sptk b7=r8,ia64_native_leave_kernel
+	mov.sptk b7=r8,ia64_leave_kernel
 	;;
 	mov ar.unat=r9
 	br.many b7
@@ -1782,4 +1770,3 @@ sys_call_table:
 	data8 sys_execveat
 
 	.org sys_call_table + 8*NR_syscalls	// guard against failures to increase NR_syscalls
-#endif /* __IA64_ASM_PARAVIRTUALIZED_NATIVE */
diff --git a/arch/ia64/kernel/fsys.S b/arch/ia64/kernel/fsys.S
index abc6dee3799c..edbf7af95849 100644
--- a/arch/ia64/kernel/fsys.S
+++ b/arch/ia64/kernel/fsys.S
@@ -24,7 +24,7 @@
 #include <asm/unistd.h>
 
 #include "entry.h"
-#include "paravirt_inst.h"
+#include <asm/native/inst.h>
 
 /*
  * See Documentation/ia64/fsys.txt for details on fsyscalls.
@@ -402,7 +402,7 @@ ENTRY(fsys_fallback_syscall)
 	mov r26=ar.pfs
 END(fsys_fallback_syscall)
 	/* FALL THROUGH */
-GLOBAL_ENTRY(paravirt_fsys_bubble_down)
+GLOBAL_ENTRY(fsys_bubble_down)
 	.prologue
 	.altrp b6
 	.body
@@ -440,7 +440,7 @@ GLOBAL_ENTRY(paravirt_fsys_bubble_down)
 	 *
 	 * PSR.BE : already is turned off in __kernel_syscall_via_epc()
 	 * PSR.AC : don't care (kernel normally turns PSR.AC on)
-	 * PSR.I  : already turned off by the time paravirt_fsys_bubble_down gets
+	 * PSR.I  : already turned off by the time fsys_bubble_down gets
 	 *	    invoked
 	 * PSR.DFL: always 0 (kernel never turns it on)
 	 * PSR.DFH: don't care --- kernel never touches f32-f127 on its own
@@ -450,7 +450,7 @@ GLOBAL_ENTRY(paravirt_fsys_bubble_down)
 	 * PSR.DB : don't care --- kernel never enables kernel-level
 	 *	    breakpoints
 	 * PSR.TB : must be 0 already; if it wasn't zero on entry to
-	 *          __kernel_syscall_via_epc, the branch to paravirt_fsys_bubble_down
+	 *          __kernel_syscall_via_epc, the branch to fsys_bubble_down
 	 *          will trigger a taken branch; the taken-trap-handler then
 	 *          converts the syscall into a break-based system-call.
 	 */
@@ -541,14 +541,14 @@ GLOBAL_ENTRY(paravirt_fsys_bubble_down)
 	nop.m 0
 (p8)	br.call.sptk.many b6=b6			// B    (ignore return address)
 	br.cond.spnt ia64_trace_syscall		// B
-END(paravirt_fsys_bubble_down)
+END(fsys_bubble_down)
 
 	.rodata
 	.align 8
-	.globl paravirt_fsyscall_table
+	.globl fsyscall_table
 
-	data8 paravirt_fsys_bubble_down
-paravirt_fsyscall_table:
+	data8 fsys_bubble_down
+fsyscall_table:
 	data8 fsys_ni_syscall
 	data8 0				// exit			// 1025
 	data8 0				// read
@@ -833,4 +833,4 @@ paravirt_fsyscall_table:
 
 	// fill in zeros for the remaining entries
 	.zero:
-	.space paravirt_fsyscall_table + 8*NR_syscalls - .zero, 0
+	.space fsyscall_table + 8*NR_syscalls - .zero, 0
diff --git a/arch/ia64/kernel/gate.S b/arch/ia64/kernel/gate.S
index b5f8bdd8618e..0bd1b3bfaf1c 100644
--- a/arch/ia64/kernel/gate.S
+++ b/arch/ia64/kernel/gate.S
@@ -14,7 +14,7 @@
 #include <asm/unistd.h>
 #include <asm/kregs.h>
 #include <asm/page.h>
-#include "paravirt_inst.h"
+#include <asm/native/inst.h>
 
 /*
  * We can't easily refer to symbols inside the kernel.  To avoid full runtime relocation,
@@ -376,11 +376,4 @@ GLOBAL_ENTRY(__kernel_syscall_via_epc)
 (p9)	mov r8=ENOSYS
 	FSYS_RETURN
 
-#ifdef CONFIG_PARAVIRT
-	/*
-	 * padd to make the size of this symbol constant
-	 * independent of paravirtualization.
-	 */
-	.align PAGE_SIZE / 8
-#endif
 END(__kernel_syscall_via_epc)
diff --git a/arch/ia64/kernel/gate.lds.S b/arch/ia64/kernel/gate.lds.S
index e518f7902af6..3e8271e85a1e 100644
--- a/arch/ia64/kernel/gate.lds.S
+++ b/arch/ia64/kernel/gate.lds.S
@@ -6,7 +6,6 @@
  */
 
 #include <asm/page.h>
-#include "paravirt_patchlist.h"
 
 SECTIONS
 {
@@ -33,21 +32,21 @@ SECTIONS
 	. = GATE_ADDR + 0x600;
 
 	.data..patch		: {
-		__paravirt_start_gate_mckinley_e9_patchlist = .;
+		__start_gate_mckinley_e9_patchlist = .;
 		*(.data..patch.mckinley_e9)
-		__paravirt_end_gate_mckinley_e9_patchlist = .;
+		__end_gate_mckinley_e9_patchlist = .;
 
-		__paravirt_start_gate_vtop_patchlist = .;
+		__start_gate_vtop_patchlist = .;
 		*(.data..patch.vtop)
-		__paravirt_end_gate_vtop_patchlist = .;
+		__end_gate_vtop_patchlist = .;
 
-		__paravirt_start_gate_fsyscall_patchlist = .;
+		__start_gate_fsyscall_patchlist = .;
 		*(.data..patch.fsyscall_table)
-		__paravirt_end_gate_fsyscall_patchlist = .;
+		__end_gate_fsyscall_patchlist = .;
 
-		__paravirt_start_gate_brl_fsys_bubble_down_patchlist = .;
+		__start_gate_brl_fsys_bubble_down_patchlist = .;
 		*(.data..patch.brl_fsys_bubble_down)
-		__paravirt_end_gate_brl_fsys_bubble_down_patchlist = .;
+		__end_gate_brl_fsys_bubble_down_patchlist = .;
 	}						:readable
 
 	.IA_64.unwind_info	: { *(.IA_64.unwind_info*) }
diff --git a/arch/ia64/kernel/head.S b/arch/ia64/kernel/head.S
index a4acddad0c78..bb748c596443 100644
--- a/arch/ia64/kernel/head.S
+++ b/arch/ia64/kernel/head.S
@@ -26,7 +26,6 @@
 #include <asm/mmu_context.h>
 #include <asm/asm-offsets.h>
 #include <asm/pal.h>
-#include <asm/paravirt.h>
 #include <asm/pgtable.h>
 #include <asm/processor.h>
 #include <asm/ptrace.h>
@@ -394,41 +393,6 @@ start_ap:
 	;;
 (isBP)	st8 [r2]=r28		// save the address of the boot param area passed by the bootloader
 
-#ifdef CONFIG_PARAVIRT
-
-	movl r14=hypervisor_setup_hooks
-	movl r15=hypervisor_type
-	mov r16=num_hypervisor_hooks
-	;;
-	ld8 r2=[r15]
-	;;
-	cmp.ltu p7,p0=r2,r16	// array size check
-	shladd r8=r2,3,r14
-	;;
-(p7)	ld8 r9=[r8]
-	;;
-(p7)	mov b1=r9
-(p7)	cmp.ne.unc p7,p0=r9,r0	// no actual branch to NULL
-	;;
-(p7)	br.call.sptk.many rp=b1
-
-	__INITDATA
-
-default_setup_hook = 0		// Currently nothing needs to be done.
-
-	.global hypervisor_type
-hypervisor_type:
-	data8		PARAVIRT_HYPERVISOR_TYPE_DEFAULT
-
-	// must have the same order with PARAVIRT_HYPERVISOR_TYPE_xxx
-
-hypervisor_setup_hooks:
-	data8		default_setup_hook
-num_hypervisor_hooks = (. - hypervisor_setup_hooks) / 8
-	.previous
-
-#endif
-
 #ifdef CONFIG_SMP
 (isAP)	br.call.sptk.many rp=start_secondary
 .ret0:
@@ -1063,12 +1027,6 @@ GLOBAL_ENTRY(ia64_native_sched_clock)
 	shrp r8=r9,r8,IA64_NSEC_PER_CYC_SHIFT
 	br.ret.sptk.many rp
 END(ia64_native_sched_clock)
-#ifndef CONFIG_PARAVIRT
-	//unsigned long long
-	//sched_clock(void) __attribute__((alias("ia64_native_sched_clock")));
-	.global sched_clock
-sched_clock = ia64_native_sched_clock
-#endif
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 GLOBAL_ENTRY(cycle_to_cputime)
diff --git a/arch/ia64/kernel/ivt.S b/arch/ia64/kernel/ivt.S
index e42bf7a913f3..b1c3cfc93e71 100644
--- a/arch/ia64/kernel/ivt.S
+++ b/arch/ia64/kernel/ivt.S
@@ -937,7 +937,6 @@ END(interrupt)
 	 *	- ar.fpsr: set to kernel settings
 	 *	-  b6: preserved (same as on entry)
 	 */
-#ifdef __IA64_ASM_PARAVIRTUALIZED_NATIVE
 GLOBAL_ENTRY(ia64_syscall_setup)
 #if PT(B6) != 0
 # error This code assumes that b6 is the first field in pt_regs.
@@ -1029,7 +1028,6 @@ GLOBAL_ENTRY(ia64_syscall_setup)
 (p10)	mov r8=-EINVAL
 	br.ret.sptk.many b7
 END(ia64_syscall_setup)
-#endif /* __IA64_ASM_PARAVIRTUALIZED_NATIVE */
 
 	.org ia64_ivt+0x3c00
 /////////////////////////////////////////////////////////////////////////////////////////
@@ -1043,7 +1041,7 @@ END(ia64_syscall_setup)
 	DBG_FAULT(16)
 	FAULT(16)
 
-#if defined(CONFIG_VIRT_CPU_ACCOUNTING_NATIVE) && defined(__IA64_ASM_PARAVIRTUALIZED_NATIVE)
+#if defined(CONFIG_VIRT_CPU_ACCOUNTING_NATIVE)
 	/*
 	 * There is no particular reason for this code to be here, other than
 	 * that there happens to be space here that would go unused otherwise.
diff --git a/arch/ia64/kernel/minstate.h b/arch/ia64/kernel/minstate.h
index cc82a7d744c9..5704700fb703 100644
--- a/arch/ia64/kernel/minstate.h
+++ b/arch/ia64/kernel/minstate.h
@@ -2,7 +2,7 @@
 #include <asm/cache.h>
 
 #include "entry.h"
-#include "paravirt_inst.h"
+#include <asm/native/inst.h>
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 /* read ar.itc in advance, and use it before leaving bank 0 */
diff --git a/arch/ia64/kernel/module.c b/arch/ia64/kernel/module.c
index 29754aae5177..b15933c31b2f 100644
--- a/arch/ia64/kernel/module.c
+++ b/arch/ia64/kernel/module.c
@@ -439,14 +439,6 @@ module_frob_arch_sections (Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, char *secstrings,
 			mod->arch.opd = s;
 		else if (strcmp(".IA_64.unwind", secstrings + s->sh_name) == 0)
 			mod->arch.unwind = s;
-#ifdef CONFIG_PARAVIRT
-		else if (strcmp(".paravirt_bundles",
-				secstrings + s->sh_name) == 0)
-			mod->arch.paravirt_bundles = s;
-		else if (strcmp(".paravirt_insts",
-				secstrings + s->sh_name) == 0)
-			mod->arch.paravirt_insts = s;
-#endif
 
 	if (!mod->arch.core_plt || !mod->arch.init_plt || !mod->arch.got || !mod->arch.opd) {
 		printk(KERN_ERR "%s: sections missing\n", mod->name);
@@ -914,30 +906,6 @@ module_finalize (const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, struct module *mo
 	DEBUGP("%s: init: entry=%p\n", __func__, mod->init);
 	if (mod->arch.unwind)
 		register_unwind_table(mod);
-#ifdef CONFIG_PARAVIRT
-        if (mod->arch.paravirt_bundles) {
-                struct paravirt_patch_site_bundle *start =
-                        (struct paravirt_patch_site_bundle *)
-                        mod->arch.paravirt_bundles->sh_addr;
-                struct paravirt_patch_site_bundle *end =
-                        (struct paravirt_patch_site_bundle *)
-                        (mod->arch.paravirt_bundles->sh_addr +
-                         mod->arch.paravirt_bundles->sh_size);
-
-                paravirt_patch_apply_bundle(start, end);
-        }
-        if (mod->arch.paravirt_insts) {
-                struct paravirt_patch_site_inst *start =
-                        (struct paravirt_patch_site_inst *)
-                        mod->arch.paravirt_insts->sh_addr;
-                struct paravirt_patch_site_inst *end =
-                        (struct paravirt_patch_site_inst *)
-                        (mod->arch.paravirt_insts->sh_addr +
-                         mod->arch.paravirt_insts->sh_size);
-
-                paravirt_patch_apply_inst(start, end);
-        }
-#endif
 	return 0;
 }
 
diff --git a/arch/ia64/kernel/msi_ia64.c b/arch/ia64/kernel/msi_ia64.c
index 9dd7464f8c17..d70bf15c690a 100644
--- a/arch/ia64/kernel/msi_ia64.c
+++ b/arch/ia64/kernel/msi_ia64.c
@@ -165,7 +165,7 @@ static struct irq_chip dmar_msi_type = {
 	.irq_retrigger = ia64_msi_retrigger_irq,
 };
 
-static int
+static void
 msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_msg *msg)
 {
 	struct irq_cfg *cfg = irq_cfg + irq;
@@ -186,21 +186,29 @@ msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_msg *msg)
 		MSI_DATA_LEVEL_ASSERT |
 		MSI_DATA_DELIVERY_FIXED |
 		MSI_DATA_VECTOR(cfg->vector);
-	return 0;
 }
 
-int arch_setup_dmar_msi(unsigned int irq)
+int dmar_alloc_hwirq(int id, int node, void *arg)
 {
-	int ret;
+	int irq;
 	struct msi_msg msg;
 
-	ret = msi_compose_msg(NULL, irq, &msg);
-	if (ret < 0)
-		return ret;
-	dmar_msi_write(irq, &msg);
-	irq_set_chip_and_handler_name(irq, &dmar_msi_type, handle_edge_irq,
-				      "edge");
-	return 0;
+	irq = create_irq();
+	if (irq > 0) {
+		irq_set_handler_data(irq, arg);
+		irq_set_chip_and_handler_name(irq, &dmar_msi_type,
+					      handle_edge_irq, "edge");
+		msi_compose_msg(NULL, irq, &msg);
+		dmar_msi_write(irq, &msg);
+	}
+
+	return irq;
+}
+
+void dmar_free_hwirq(int irq)
+{
+	irq_set_handler_data(irq, NULL);
+	destroy_irq(irq);
 }
 #endif /* CONFIG_INTEL_IOMMU */
 
diff --git a/arch/ia64/kernel/paravirt.c b/arch/ia64/kernel/paravirt.c
deleted file mode 100644
index 1b22f6de2932..000000000000
--- a/arch/ia64/kernel/paravirt.c
+++ /dev/null
@@ -1,902 +0,0 @@
-/******************************************************************************
- * arch/ia64/kernel/paravirt.c
- *
- * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
- *                    VA Linux Systems Japan K.K.
- *     Yaozu (Eddie) Dong <eddie.dong@intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- */
-
-#include <linux/init.h>
-
-#include <linux/compiler.h>
-#include <linux/io.h>
-#include <linux/irq.h>
-#include <linux/module.h>
-#include <linux/types.h>
-
-#include <asm/iosapic.h>
-#include <asm/paravirt.h>
-
-/***************************************************************************
- * general info
- */
-struct pv_info pv_info = {
-	.kernel_rpl = 0,
-	.paravirt_enabled = 0,
-	.name = "bare hardware"
-};
-
-/***************************************************************************
- * pv_init_ops
- * initialization hooks.
- */
-
-static void __init
-ia64_native_patch_branch(unsigned long tag, unsigned long type);
-
-struct pv_init_ops pv_init_ops =
-{
-#ifdef ASM_SUPPORTED
-	.patch_bundle = ia64_native_patch_bundle,
-#endif
-	.patch_branch = ia64_native_patch_branch,
-};
-
-/***************************************************************************
- * pv_cpu_ops
- * intrinsics hooks.
- */
-
-#ifndef ASM_SUPPORTED
-/* ia64_native_xxx are macros so that we have to make them real functions */
-
-#define DEFINE_VOID_FUNC1(name)					\
-	static void						\
-	ia64_native_ ## name ## _func(unsigned long arg)	\
-	{							\
-		ia64_native_ ## name(arg);			\
-	}
-
-#define DEFINE_VOID_FUNC1_VOID(name)				\
-	static void						\
-	ia64_native_ ## name ## _func(void *arg)		\
-	{							\
-		ia64_native_ ## name(arg);			\
-	}
-
-#define DEFINE_VOID_FUNC2(name)					\
-	static void						\
-	ia64_native_ ## name ## _func(unsigned long arg0,	\
-				      unsigned long arg1)	\
-	{							\
-		ia64_native_ ## name(arg0, arg1);		\
-	}
-
-#define DEFINE_FUNC0(name)			\
-	static unsigned long			\
-	ia64_native_ ## name ## _func(void)	\
-	{					\
-		return ia64_native_ ## name();	\
-	}
-
-#define DEFINE_FUNC1(name, type)			\
-	static unsigned long				\
-	ia64_native_ ## name ## _func(type arg)		\
-	{						\
-		return ia64_native_ ## name(arg);	\
-	}						\
-
-DEFINE_VOID_FUNC1_VOID(fc);
-DEFINE_VOID_FUNC1(intrin_local_irq_restore);
-
-DEFINE_VOID_FUNC2(ptcga);
-DEFINE_VOID_FUNC2(set_rr);
-
-DEFINE_FUNC0(get_psr_i);
-
-DEFINE_FUNC1(thash, unsigned long);
-DEFINE_FUNC1(get_cpuid, int);
-DEFINE_FUNC1(get_pmd, int);
-DEFINE_FUNC1(get_rr, unsigned long);
-
-static void
-ia64_native_ssm_i_func(void)
-{
-	ia64_native_ssm(IA64_PSR_I);
-}
-
-static void
-ia64_native_rsm_i_func(void)
-{
-	ia64_native_rsm(IA64_PSR_I);
-}
-
-static void
-ia64_native_set_rr0_to_rr4_func(unsigned long val0, unsigned long val1,
-				unsigned long val2, unsigned long val3,
-				unsigned long val4)
-{
-	ia64_native_set_rr0_to_rr4(val0, val1, val2, val3, val4);
-}
-
-#define CASE_GET_REG(id)				\
-	case _IA64_REG_ ## id:				\
-	res = ia64_native_getreg(_IA64_REG_ ## id);	\
-	break;
-#define CASE_GET_AR(id) CASE_GET_REG(AR_ ## id)
-#define CASE_GET_CR(id) CASE_GET_REG(CR_ ## id)
-
-unsigned long
-ia64_native_getreg_func(int regnum)
-{
-	unsigned long res = -1;
-	switch (regnum) {
-	CASE_GET_REG(GP);
-	/*CASE_GET_REG(IP);*/ /* returned ip value shouldn't be constant */
-	CASE_GET_REG(PSR);
-	CASE_GET_REG(TP);
-	CASE_GET_REG(SP);
-
-	CASE_GET_AR(KR0);
-	CASE_GET_AR(KR1);
-	CASE_GET_AR(KR2);
-	CASE_GET_AR(KR3);
-	CASE_GET_AR(KR4);
-	CASE_GET_AR(KR5);
-	CASE_GET_AR(KR6);
-	CASE_GET_AR(KR7);
-	CASE_GET_AR(RSC);
-	CASE_GET_AR(BSP);
-	CASE_GET_AR(BSPSTORE);
-	CASE_GET_AR(RNAT);
-	CASE_GET_AR(FCR);
-	CASE_GET_AR(EFLAG);
-	CASE_GET_AR(CSD);
-	CASE_GET_AR(SSD);
-	CASE_GET_AR(CFLAG);
-	CASE_GET_AR(FSR);
-	CASE_GET_AR(FIR);
-	CASE_GET_AR(FDR);
-	CASE_GET_AR(CCV);
-	CASE_GET_AR(UNAT);
-	CASE_GET_AR(FPSR);
-	CASE_GET_AR(ITC);
-	CASE_GET_AR(PFS);
-	CASE_GET_AR(LC);
-	CASE_GET_AR(EC);
-
-	CASE_GET_CR(DCR);
-	CASE_GET_CR(ITM);
-	CASE_GET_CR(IVA);
-	CASE_GET_CR(PTA);
-	CASE_GET_CR(IPSR);
-	CASE_GET_CR(ISR);
-	CASE_GET_CR(IIP);
-	CASE_GET_CR(IFA);
-	CASE_GET_CR(ITIR);
-	CASE_GET_CR(IIPA);
-	CASE_GET_CR(IFS);
-	CASE_GET_CR(IIM);
-	CASE_GET_CR(IHA);
-	CASE_GET_CR(LID);
-	CASE_GET_CR(IVR);
-	CASE_GET_CR(TPR);
-	CASE_GET_CR(EOI);
-	CASE_GET_CR(IRR0);
-	CASE_GET_CR(IRR1);
-	CASE_GET_CR(IRR2);
-	CASE_GET_CR(IRR3);
-	CASE_GET_CR(ITV);
-	CASE_GET_CR(PMV);
-	CASE_GET_CR(CMCV);
-	CASE_GET_CR(LRR0);
-	CASE_GET_CR(LRR1);
-
-	default:
-		printk(KERN_CRIT "wrong_getreg %d\n", regnum);
-		break;
-	}
-	return res;
-}
-
-#define CASE_SET_REG(id)				\
-	case _IA64_REG_ ## id:				\
-	ia64_native_setreg(_IA64_REG_ ## id, val);	\
-	break;
-#define CASE_SET_AR(id) CASE_SET_REG(AR_ ## id)
-#define CASE_SET_CR(id) CASE_SET_REG(CR_ ## id)
-
-void
-ia64_native_setreg_func(int regnum, unsigned long val)
-{
-	switch (regnum) {
-	case _IA64_REG_PSR_L:
-		ia64_native_setreg(_IA64_REG_PSR_L, val);
-		ia64_dv_serialize_data();
-		break;
-	CASE_SET_REG(SP);
-	CASE_SET_REG(GP);
-
-	CASE_SET_AR(KR0);
-	CASE_SET_AR(KR1);
-	CASE_SET_AR(KR2);
-	CASE_SET_AR(KR3);
-	CASE_SET_AR(KR4);
-	CASE_SET_AR(KR5);
-	CASE_SET_AR(KR6);
-	CASE_SET_AR(KR7);
-	CASE_SET_AR(RSC);
-	CASE_SET_AR(BSP);
-	CASE_SET_AR(BSPSTORE);
-	CASE_SET_AR(RNAT);
-	CASE_SET_AR(FCR);
-	CASE_SET_AR(EFLAG);
-	CASE_SET_AR(CSD);
-	CASE_SET_AR(SSD);
-	CASE_SET_AR(CFLAG);
-	CASE_SET_AR(FSR);
-	CASE_SET_AR(FIR);
-	CASE_SET_AR(FDR);
-	CASE_SET_AR(CCV);
-	CASE_SET_AR(UNAT);
-	CASE_SET_AR(FPSR);
-	CASE_SET_AR(ITC);
-	CASE_SET_AR(PFS);
-	CASE_SET_AR(LC);
-	CASE_SET_AR(EC);
-
-	CASE_SET_CR(DCR);
-	CASE_SET_CR(ITM);
-	CASE_SET_CR(IVA);
-	CASE_SET_CR(PTA);
-	CASE_SET_CR(IPSR);
-	CASE_SET_CR(ISR);
-	CASE_SET_CR(IIP);
-	CASE_SET_CR(IFA);
-	CASE_SET_CR(ITIR);
-	CASE_SET_CR(IIPA);
-	CASE_SET_CR(IFS);
-	CASE_SET_CR(IIM);
-	CASE_SET_CR(IHA);
-	CASE_SET_CR(LID);
-	CASE_SET_CR(IVR);
-	CASE_SET_CR(TPR);
-	CASE_SET_CR(EOI);
-	CASE_SET_CR(IRR0);
-	CASE_SET_CR(IRR1);
-	CASE_SET_CR(IRR2);
-	CASE_SET_CR(IRR3);
-	CASE_SET_CR(ITV);
-	CASE_SET_CR(PMV);
-	CASE_SET_CR(CMCV);
-	CASE_SET_CR(LRR0);
-	CASE_SET_CR(LRR1);
-	default:
-		printk(KERN_CRIT "wrong setreg %d\n", regnum);
-		break;
-	}
-}
-#else
-
-#define __DEFINE_FUNC(name, code)					\
-	extern const char ia64_native_ ## name ## _direct_start[];	\
-	extern const char ia64_native_ ## name ## _direct_end[];	\
-	asm (".align 32\n"						\
-	     ".proc ia64_native_" #name "_func\n"			\
-	     "ia64_native_" #name "_func:\n"				\
-	     "ia64_native_" #name "_direct_start:\n"			\
-	     code							\
-	     "ia64_native_" #name "_direct_end:\n"			\
-	     "br.cond.sptk.many b6\n"					\
-	     ".endp ia64_native_" #name "_func\n")
-
-#define DEFINE_VOID_FUNC0(name, code)				\
-	extern void						\
-	ia64_native_ ## name ## _func(void);			\
-	__DEFINE_FUNC(name, code)
-
-#define DEFINE_VOID_FUNC1(name, code)				\
-	extern void						\
-	ia64_native_ ## name ## _func(unsigned long arg);	\
-	__DEFINE_FUNC(name, code)
-
-#define DEFINE_VOID_FUNC1_VOID(name, code)			\
-	extern void						\
-	ia64_native_ ## name ## _func(void *arg);		\
-	__DEFINE_FUNC(name, code)
-
-#define DEFINE_VOID_FUNC2(name, code)				\
-	extern void						\
-	ia64_native_ ## name ## _func(unsigned long arg0,	\
-				      unsigned long arg1);	\
-	__DEFINE_FUNC(name, code)
-
-#define DEFINE_FUNC0(name, code)		\
-	extern unsigned long			\
-	ia64_native_ ## name ## _func(void);	\
-	__DEFINE_FUNC(name, code)
-
-#define DEFINE_FUNC1(name, type, code)			\
-	extern unsigned long				\
-	ia64_native_ ## name ## _func(type arg);	\
-	__DEFINE_FUNC(name, code)
-
-DEFINE_VOID_FUNC1_VOID(fc,
-		       "fc r8\n");
-DEFINE_VOID_FUNC1(intrin_local_irq_restore,
-		  ";;\n"
-		  "     cmp.ne p6, p7 = r8, r0\n"
-		  ";;\n"
-		  "(p6) ssm psr.i\n"
-		  "(p7) rsm psr.i\n"
-		  ";;\n"
-		  "(p6) srlz.d\n");
-
-DEFINE_VOID_FUNC2(ptcga,
-		  "ptc.ga r8, r9\n");
-DEFINE_VOID_FUNC2(set_rr,
-		  "mov rr[r8] = r9\n");
-
-/* ia64_native_getreg(_IA64_REG_PSR) & IA64_PSR_I */
-DEFINE_FUNC0(get_psr_i,
-	     "mov r2 = " __stringify(1 << IA64_PSR_I_BIT) "\n"
-	     "mov r8 = psr\n"
-	     ";;\n"
-	     "and r8 = r2, r8\n");
-
-DEFINE_FUNC1(thash, unsigned long,
-	     "thash r8 = r8\n");
-DEFINE_FUNC1(get_cpuid, int,
-	     "mov r8 = cpuid[r8]\n");
-DEFINE_FUNC1(get_pmd, int,
-	     "mov r8 = pmd[r8]\n");
-DEFINE_FUNC1(get_rr, unsigned long,
-	     "mov r8 = rr[r8]\n");
-
-DEFINE_VOID_FUNC0(ssm_i,
-		  "ssm psr.i\n");
-DEFINE_VOID_FUNC0(rsm_i,
-		  "rsm psr.i\n");
-
-extern void
-ia64_native_set_rr0_to_rr4_func(unsigned long val0, unsigned long val1,
-				unsigned long val2, unsigned long val3,
-				unsigned long val4);
-__DEFINE_FUNC(set_rr0_to_rr4,
-	      "mov rr[r0] = r8\n"
-	      "movl r2 = 0x2000000000000000\n"
-	      ";;\n"
-	      "mov rr[r2] = r9\n"
-	      "shl r3 = r2, 1\n"	/* movl r3 = 0x4000000000000000 */
-	      ";;\n"
-	      "add r2 = r2, r3\n"	/* movl r2 = 0x6000000000000000 */
-	      "mov rr[r3] = r10\n"
-	      ";;\n"
-	      "mov rr[r2] = r11\n"
-	      "shl r3 = r3, 1\n"	/* movl r3 = 0x8000000000000000 */
-	      ";;\n"
-	      "mov rr[r3] = r14\n");
-
-extern unsigned long ia64_native_getreg_func(int regnum);
-asm(".global ia64_native_getreg_func\n");
-#define __DEFINE_GET_REG(id, reg)			\
-	"mov r2 = " __stringify(_IA64_REG_ ## id) "\n"	\
-	";;\n"						\
-	"cmp.eq p6, p0 = r2, r8\n"			\
-	";;\n"						\
-	"(p6) mov r8 = " #reg "\n"			\
-	"(p6) br.cond.sptk.many b6\n"			\
-	";;\n"
-#define __DEFINE_GET_AR(id, reg)	__DEFINE_GET_REG(AR_ ## id, ar.reg)
-#define __DEFINE_GET_CR(id, reg)	__DEFINE_GET_REG(CR_ ## id, cr.reg)
-
-__DEFINE_FUNC(getreg,
-	      __DEFINE_GET_REG(GP, gp)
-	      /*__DEFINE_GET_REG(IP, ip)*/ /* returned ip value shouldn't be constant */
-	      __DEFINE_GET_REG(PSR, psr)
-	      __DEFINE_GET_REG(TP, tp)
-	      __DEFINE_GET_REG(SP, sp)
-
-	      __DEFINE_GET_REG(AR_KR0, ar0)
-	      __DEFINE_GET_REG(AR_KR1, ar1)
-	      __DEFINE_GET_REG(AR_KR2, ar2)
-	      __DEFINE_GET_REG(AR_KR3, ar3)
-	      __DEFINE_GET_REG(AR_KR4, ar4)
-	      __DEFINE_GET_REG(AR_KR5, ar5)
-	      __DEFINE_GET_REG(AR_KR6, ar6)
-	      __DEFINE_GET_REG(AR_KR7, ar7)
-	      __DEFINE_GET_AR(RSC, rsc)
-	      __DEFINE_GET_AR(BSP, bsp)
-	      __DEFINE_GET_AR(BSPSTORE, bspstore)
-	      __DEFINE_GET_AR(RNAT, rnat)
-	      __DEFINE_GET_AR(FCR, fcr)
-	      __DEFINE_GET_AR(EFLAG, eflag)
-	      __DEFINE_GET_AR(CSD, csd)
-	      __DEFINE_GET_AR(SSD, ssd)
-	      __DEFINE_GET_REG(AR_CFLAG, ar27)
-	      __DEFINE_GET_AR(FSR, fsr)
-	      __DEFINE_GET_AR(FIR, fir)
-	      __DEFINE_GET_AR(FDR, fdr)
-	      __DEFINE_GET_AR(CCV, ccv)
-	      __DEFINE_GET_AR(UNAT, unat)
-	      __DEFINE_GET_AR(FPSR, fpsr)
-	      __DEFINE_GET_AR(ITC, itc)
-	      __DEFINE_GET_AR(PFS, pfs)
-	      __DEFINE_GET_AR(LC, lc)
-	      __DEFINE_GET_AR(EC, ec)
-
-	      __DEFINE_GET_CR(DCR, dcr)
-	      __DEFINE_GET_CR(ITM, itm)
-	      __DEFINE_GET_CR(IVA, iva)
-	      __DEFINE_GET_CR(PTA, pta)
-	      __DEFINE_GET_CR(IPSR, ipsr)
-	      __DEFINE_GET_CR(ISR, isr)
-	      __DEFINE_GET_CR(IIP, iip)
-	      __DEFINE_GET_CR(IFA, ifa)
-	      __DEFINE_GET_CR(ITIR, itir)
-	      __DEFINE_GET_CR(IIPA, iipa)
-	      __DEFINE_GET_CR(IFS, ifs)
-	      __DEFINE_GET_CR(IIM, iim)
-	      __DEFINE_GET_CR(IHA, iha)
-	      __DEFINE_GET_CR(LID, lid)
-	      __DEFINE_GET_CR(IVR, ivr)
-	      __DEFINE_GET_CR(TPR, tpr)
-	      __DEFINE_GET_CR(EOI, eoi)
-	      __DEFINE_GET_CR(IRR0, irr0)
-	      __DEFINE_GET_CR(IRR1, irr1)
-	      __DEFINE_GET_CR(IRR2, irr2)
-	      __DEFINE_GET_CR(IRR3, irr3)
-	      __DEFINE_GET_CR(ITV, itv)
-	      __DEFINE_GET_CR(PMV, pmv)
-	      __DEFINE_GET_CR(CMCV, cmcv)
-	      __DEFINE_GET_CR(LRR0, lrr0)
-	      __DEFINE_GET_CR(LRR1, lrr1)
-
-	      "mov r8 = -1\n"	/* unsupported case */
-	);
-
-extern void ia64_native_setreg_func(int regnum, unsigned long val);
-asm(".global ia64_native_setreg_func\n");
-#define __DEFINE_SET_REG(id, reg)			\
-	"mov r2 = " __stringify(_IA64_REG_ ## id) "\n"	\
-	";;\n"						\
-	"cmp.eq p6, p0 = r2, r9\n"			\
-	";;\n"						\
-	"(p6) mov " #reg " = r8\n"			\
-	"(p6) br.cond.sptk.many b6\n"			\
-	";;\n"
-#define __DEFINE_SET_AR(id, reg)	__DEFINE_SET_REG(AR_ ## id, ar.reg)
-#define __DEFINE_SET_CR(id, reg)	__DEFINE_SET_REG(CR_ ## id, cr.reg)
-__DEFINE_FUNC(setreg,
-	      "mov r2 = " __stringify(_IA64_REG_PSR_L) "\n"
-	      ";;\n"
-	      "cmp.eq p6, p0 = r2, r9\n"
-	      ";;\n"
-	      "(p6) mov psr.l = r8\n"
-#ifdef HAVE_SERIALIZE_DIRECTIVE
-	      ".serialize.data\n"
-#endif
-	      "(p6) br.cond.sptk.many b6\n"
-	      __DEFINE_SET_REG(GP, gp)
-	      __DEFINE_SET_REG(SP, sp)
-
-	      __DEFINE_SET_REG(AR_KR0, ar0)
-	      __DEFINE_SET_REG(AR_KR1, ar1)
-	      __DEFINE_SET_REG(AR_KR2, ar2)
-	      __DEFINE_SET_REG(AR_KR3, ar3)
-	      __DEFINE_SET_REG(AR_KR4, ar4)
-	      __DEFINE_SET_REG(AR_KR5, ar5)
-	      __DEFINE_SET_REG(AR_KR6, ar6)
-	      __DEFINE_SET_REG(AR_KR7, ar7)
-	      __DEFINE_SET_AR(RSC, rsc)
-	      __DEFINE_SET_AR(BSP, bsp)
-	      __DEFINE_SET_AR(BSPSTORE, bspstore)
-	      __DEFINE_SET_AR(RNAT, rnat)
-	      __DEFINE_SET_AR(FCR, fcr)
-	      __DEFINE_SET_AR(EFLAG, eflag)
-	      __DEFINE_SET_AR(CSD, csd)
-	      __DEFINE_SET_AR(SSD, ssd)
-	      __DEFINE_SET_REG(AR_CFLAG, ar27)
-	      __DEFINE_SET_AR(FSR, fsr)
-	      __DEFINE_SET_AR(FIR, fir)
-	      __DEFINE_SET_AR(FDR, fdr)
-	      __DEFINE_SET_AR(CCV, ccv)
-	      __DEFINE_SET_AR(UNAT, unat)
-	      __DEFINE_SET_AR(FPSR, fpsr)
-	      __DEFINE_SET_AR(ITC, itc)
-	      __DEFINE_SET_AR(PFS, pfs)
-	      __DEFINE_SET_AR(LC, lc)
-	      __DEFINE_SET_AR(EC, ec)
-
-	      __DEFINE_SET_CR(DCR, dcr)
-	      __DEFINE_SET_CR(ITM, itm)
-	      __DEFINE_SET_CR(IVA, iva)
-	      __DEFINE_SET_CR(PTA, pta)
-	      __DEFINE_SET_CR(IPSR, ipsr)
-	      __DEFINE_SET_CR(ISR, isr)
-	      __DEFINE_SET_CR(IIP, iip)
-	      __DEFINE_SET_CR(IFA, ifa)
-	      __DEFINE_SET_CR(ITIR, itir)
-	      __DEFINE_SET_CR(IIPA, iipa)
-	      __DEFINE_SET_CR(IFS, ifs)
-	      __DEFINE_SET_CR(IIM, iim)
-	      __DEFINE_SET_CR(IHA, iha)
-	      __DEFINE_SET_CR(LID, lid)
-	      __DEFINE_SET_CR(IVR, ivr)
-	      __DEFINE_SET_CR(TPR, tpr)
-	      __DEFINE_SET_CR(EOI, eoi)
-	      __DEFINE_SET_CR(IRR0, irr0)
-	      __DEFINE_SET_CR(IRR1, irr1)
-	      __DEFINE_SET_CR(IRR2, irr2)
-	      __DEFINE_SET_CR(IRR3, irr3)
-	      __DEFINE_SET_CR(ITV, itv)
-	      __DEFINE_SET_CR(PMV, pmv)
-	      __DEFINE_SET_CR(CMCV, cmcv)
-	      __DEFINE_SET_CR(LRR0, lrr0)
-	      __DEFINE_SET_CR(LRR1, lrr1)
-	);
-#endif
-
-struct pv_cpu_ops pv_cpu_ops = {
-	.fc		= ia64_native_fc_func,
-	.thash		= ia64_native_thash_func,
-	.get_cpuid	= ia64_native_get_cpuid_func,
-	.get_pmd	= ia64_native_get_pmd_func,
-	.ptcga		= ia64_native_ptcga_func,
-	.get_rr		= ia64_native_get_rr_func,
-	.set_rr		= ia64_native_set_rr_func,
-	.set_rr0_to_rr4	= ia64_native_set_rr0_to_rr4_func,
-	.ssm_i		= ia64_native_ssm_i_func,
-	.getreg		= ia64_native_getreg_func,
-	.setreg		= ia64_native_setreg_func,
-	.rsm_i		= ia64_native_rsm_i_func,
-	.get_psr_i	= ia64_native_get_psr_i_func,
-	.intrin_local_irq_restore
-			= ia64_native_intrin_local_irq_restore_func,
-};
-EXPORT_SYMBOL(pv_cpu_ops);
-
-/******************************************************************************
- * replacement of hand written assembly codes.
- */
-
-void
-paravirt_cpu_asm_init(const struct pv_cpu_asm_switch *cpu_asm_switch)
-{
-	extern unsigned long paravirt_switch_to_targ;
-	extern unsigned long paravirt_leave_syscall_targ;
-	extern unsigned long paravirt_work_processed_syscall_targ;
-	extern unsigned long paravirt_leave_kernel_targ;
-
-	paravirt_switch_to_targ = cpu_asm_switch->switch_to;
-	paravirt_leave_syscall_targ = cpu_asm_switch->leave_syscall;
-	paravirt_work_processed_syscall_targ =
-		cpu_asm_switch->work_processed_syscall;
-	paravirt_leave_kernel_targ = cpu_asm_switch->leave_kernel;
-}
-
-/***************************************************************************
- * pv_iosapic_ops
- * iosapic read/write hooks.
- */
-
-static unsigned int
-ia64_native_iosapic_read(char __iomem *iosapic, unsigned int reg)
-{
-	return __ia64_native_iosapic_read(iosapic, reg);
-}
-
-static void
-ia64_native_iosapic_write(char __iomem *iosapic, unsigned int reg, u32 val)
-{
-	__ia64_native_iosapic_write(iosapic, reg, val);
-}
-
-struct pv_iosapic_ops pv_iosapic_ops = {
-	.pcat_compat_init = ia64_native_iosapic_pcat_compat_init,
-	.__get_irq_chip = ia64_native_iosapic_get_irq_chip,
-
-	.__read = ia64_native_iosapic_read,
-	.__write = ia64_native_iosapic_write,
-};
-
-/***************************************************************************
- * pv_irq_ops
- * irq operations
- */
-
-struct pv_irq_ops pv_irq_ops = {
-	.register_ipi = ia64_native_register_ipi,
-
-	.assign_irq_vector = ia64_native_assign_irq_vector,
-	.free_irq_vector = ia64_native_free_irq_vector,
-	.register_percpu_irq = ia64_native_register_percpu_irq,
-
-	.resend_irq = ia64_native_resend_irq,
-};
-
-/***************************************************************************
- * pv_time_ops
- * time operations
- */
-struct static_key paravirt_steal_enabled;
-struct static_key paravirt_steal_rq_enabled;
-
-static int
-ia64_native_do_steal_accounting(unsigned long *new_itm)
-{
-	return 0;
-}
-
-struct pv_time_ops pv_time_ops = {
-	.do_steal_accounting = ia64_native_do_steal_accounting,
-	.sched_clock = ia64_native_sched_clock,
-};
-
-/***************************************************************************
- * binary pacthing
- * pv_init_ops.patch_bundle
- */
-
-#ifdef ASM_SUPPORTED
-#define IA64_NATIVE_PATCH_DEFINE_GET_REG(name, reg)	\
-	__DEFINE_FUNC(get_ ## name,			\
-		      ";;\n"				\
-		      "mov r8 = " #reg "\n"		\
-		      ";;\n")
-
-#define IA64_NATIVE_PATCH_DEFINE_SET_REG(name, reg)	\
-	__DEFINE_FUNC(set_ ## name,			\
-		      ";;\n"				\
-		      "mov " #reg " = r8\n"		\
-		      ";;\n")
-
-#define IA64_NATIVE_PATCH_DEFINE_REG(name, reg)		\
-	IA64_NATIVE_PATCH_DEFINE_GET_REG(name, reg);	\
-	IA64_NATIVE_PATCH_DEFINE_SET_REG(name, reg)	\
-
-#define IA64_NATIVE_PATCH_DEFINE_AR(name, reg)			\
-	IA64_NATIVE_PATCH_DEFINE_REG(ar_ ## name, ar.reg)
-
-#define IA64_NATIVE_PATCH_DEFINE_CR(name, reg)			\
-	IA64_NATIVE_PATCH_DEFINE_REG(cr_ ## name, cr.reg)
-
-
-IA64_NATIVE_PATCH_DEFINE_GET_REG(psr, psr);
-IA64_NATIVE_PATCH_DEFINE_GET_REG(tp, tp);
-
-/* IA64_NATIVE_PATCH_DEFINE_SET_REG(psr_l, psr.l); */
-__DEFINE_FUNC(set_psr_l,
-	      ";;\n"
-	      "mov psr.l = r8\n"
-#ifdef HAVE_SERIALIZE_DIRECTIVE
-	      ".serialize.data\n"
-#endif
-	      ";;\n");
-
-IA64_NATIVE_PATCH_DEFINE_REG(gp, gp);
-IA64_NATIVE_PATCH_DEFINE_REG(sp, sp);
-
-IA64_NATIVE_PATCH_DEFINE_REG(kr0, ar0);
-IA64_NATIVE_PATCH_DEFINE_REG(kr1, ar1);
-IA64_NATIVE_PATCH_DEFINE_REG(kr2, ar2);
-IA64_NATIVE_PATCH_DEFINE_REG(kr3, ar3);
-IA64_NATIVE_PATCH_DEFINE_REG(kr4, ar4);
-IA64_NATIVE_PATCH_DEFINE_REG(kr5, ar5);
-IA64_NATIVE_PATCH_DEFINE_REG(kr6, ar6);
-IA64_NATIVE_PATCH_DEFINE_REG(kr7, ar7);
-
-IA64_NATIVE_PATCH_DEFINE_AR(rsc, rsc);
-IA64_NATIVE_PATCH_DEFINE_AR(bsp, bsp);
-IA64_NATIVE_PATCH_DEFINE_AR(bspstore, bspstore);
-IA64_NATIVE_PATCH_DEFINE_AR(rnat, rnat);
-IA64_NATIVE_PATCH_DEFINE_AR(fcr, fcr);
-IA64_NATIVE_PATCH_DEFINE_AR(eflag, eflag);
-IA64_NATIVE_PATCH_DEFINE_AR(csd, csd);
-IA64_NATIVE_PATCH_DEFINE_AR(ssd, ssd);
-IA64_NATIVE_PATCH_DEFINE_REG(ar27, ar27);
-IA64_NATIVE_PATCH_DEFINE_AR(fsr, fsr);
-IA64_NATIVE_PATCH_DEFINE_AR(fir, fir);
-IA64_NATIVE_PATCH_DEFINE_AR(fdr, fdr);
-IA64_NATIVE_PATCH_DEFINE_AR(ccv, ccv);
-IA64_NATIVE_PATCH_DEFINE_AR(unat, unat);
-IA64_NATIVE_PATCH_DEFINE_AR(fpsr, fpsr);
-IA64_NATIVE_PATCH_DEFINE_AR(itc, itc);
-IA64_NATIVE_PATCH_DEFINE_AR(pfs, pfs);
-IA64_NATIVE_PATCH_DEFINE_AR(lc, lc);
-IA64_NATIVE_PATCH_DEFINE_AR(ec, ec);
-
-IA64_NATIVE_PATCH_DEFINE_CR(dcr, dcr);
-IA64_NATIVE_PATCH_DEFINE_CR(itm, itm);
-IA64_NATIVE_PATCH_DEFINE_CR(iva, iva);
-IA64_NATIVE_PATCH_DEFINE_CR(pta, pta);
-IA64_NATIVE_PATCH_DEFINE_CR(ipsr, ipsr);
-IA64_NATIVE_PATCH_DEFINE_CR(isr, isr);
-IA64_NATIVE_PATCH_DEFINE_CR(iip, iip);
-IA64_NATIVE_PATCH_DEFINE_CR(ifa, ifa);
-IA64_NATIVE_PATCH_DEFINE_CR(itir, itir);
-IA64_NATIVE_PATCH_DEFINE_CR(iipa, iipa);
-IA64_NATIVE_PATCH_DEFINE_CR(ifs, ifs);
-IA64_NATIVE_PATCH_DEFINE_CR(iim, iim);
-IA64_NATIVE_PATCH_DEFINE_CR(iha, iha);
-IA64_NATIVE_PATCH_DEFINE_CR(lid, lid);
-IA64_NATIVE_PATCH_DEFINE_CR(ivr, ivr);
-IA64_NATIVE_PATCH_DEFINE_CR(tpr, tpr);
-IA64_NATIVE_PATCH_DEFINE_CR(eoi, eoi);
-IA64_NATIVE_PATCH_DEFINE_CR(irr0, irr0);
-IA64_NATIVE_PATCH_DEFINE_CR(irr1, irr1);
-IA64_NATIVE_PATCH_DEFINE_CR(irr2, irr2);
-IA64_NATIVE_PATCH_DEFINE_CR(irr3, irr3);
-IA64_NATIVE_PATCH_DEFINE_CR(itv, itv);
-IA64_NATIVE_PATCH_DEFINE_CR(pmv, pmv);
-IA64_NATIVE_PATCH_DEFINE_CR(cmcv, cmcv);
-IA64_NATIVE_PATCH_DEFINE_CR(lrr0, lrr0);
-IA64_NATIVE_PATCH_DEFINE_CR(lrr1, lrr1);
-
-static const struct paravirt_patch_bundle_elem ia64_native_patch_bundle_elems[]
-__initdata_or_module =
-{
-#define IA64_NATIVE_PATCH_BUNDLE_ELEM(name, type)		\
-	{							\
-		(void*)ia64_native_ ## name ## _direct_start,	\
-		(void*)ia64_native_ ## name ## _direct_end,	\
-		PARAVIRT_PATCH_TYPE_ ## type,			\
-	}
-
-	IA64_NATIVE_PATCH_BUNDLE_ELEM(fc, FC),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM(thash, THASH),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM(get_cpuid, GET_CPUID),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM(get_pmd, GET_PMD),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM(ptcga, PTCGA),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM(get_rr, GET_RR),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM(set_rr, SET_RR),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM(set_rr0_to_rr4, SET_RR0_TO_RR4),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM(ssm_i, SSM_I),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM(rsm_i, RSM_I),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM(get_psr_i, GET_PSR_I),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM(intrin_local_irq_restore,
-				      INTRIN_LOCAL_IRQ_RESTORE),
-
-#define IA64_NATIVE_PATCH_BUNDLE_ELEM_GETREG(name, reg)			\
-	{								\
-		(void*)ia64_native_get_ ## name ## _direct_start,	\
-		(void*)ia64_native_get_ ## name ## _direct_end,		\
-		PARAVIRT_PATCH_TYPE_GETREG + _IA64_REG_ ## reg,		\
-	}
-
-#define IA64_NATIVE_PATCH_BUNDLE_ELEM_SETREG(name, reg)			\
-	{								\
-		(void*)ia64_native_set_ ## name ## _direct_start,	\
-		(void*)ia64_native_set_ ## name ## _direct_end,		\
-		PARAVIRT_PATCH_TYPE_SETREG + _IA64_REG_ ## reg,		\
-	}
-
-#define IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(name, reg)		\
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_GETREG(name, reg),	\
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_SETREG(name, reg)		\
-
-#define IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(name, reg)		\
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(ar_ ## name, AR_ ## reg)
-
-#define IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(name, reg)		\
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(cr_ ## name, CR_ ## reg)
-
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_GETREG(psr, PSR),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_GETREG(tp, TP),
-
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_SETREG(psr_l, PSR_L),
-
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(gp, GP),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(sp, SP),
-
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(kr0, AR_KR0),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(kr1, AR_KR1),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(kr2, AR_KR2),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(kr3, AR_KR3),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(kr4, AR_KR4),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(kr5, AR_KR5),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(kr6, AR_KR6),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(kr7, AR_KR7),
-
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(rsc, RSC),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(bsp, BSP),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(bspstore, BSPSTORE),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(rnat, RNAT),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(fcr, FCR),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(eflag, EFLAG),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(csd, CSD),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(ssd, SSD),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(ar27, AR_CFLAG),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(fsr, FSR),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(fir, FIR),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(fdr, FDR),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(ccv, CCV),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(unat, UNAT),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(fpsr, FPSR),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(itc, ITC),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(pfs, PFS),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(lc, LC),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(ec, EC),
-
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(dcr, DCR),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(itm, ITM),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(iva, IVA),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(pta, PTA),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(ipsr, IPSR),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(isr, ISR),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(iip, IIP),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(ifa, IFA),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(itir, ITIR),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(iipa, IIPA),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(ifs, IFS),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(iim, IIM),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(iha, IHA),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(lid, LID),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(ivr, IVR),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(tpr, TPR),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(eoi, EOI),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(irr0, IRR0),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(irr1, IRR1),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(irr2, IRR2),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(irr3, IRR3),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(itv, ITV),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(pmv, PMV),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(cmcv, CMCV),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(lrr0, LRR0),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(lrr1, LRR1),
-};
-
-unsigned long __init_or_module
-ia64_native_patch_bundle(void *sbundle, void *ebundle, unsigned long type)
-{
-	const unsigned long nelems = sizeof(ia64_native_patch_bundle_elems) /
-		sizeof(ia64_native_patch_bundle_elems[0]);
-
-	return __paravirt_patch_apply_bundle(sbundle, ebundle, type,
-					      ia64_native_patch_bundle_elems,
-					      nelems, NULL);
-}
-#endif /* ASM_SUPPOTED */
-
-extern const char ia64_native_switch_to[];
-extern const char ia64_native_leave_syscall[];
-extern const char ia64_native_work_processed_syscall[];
-extern const char ia64_native_leave_kernel[];
-
-const struct paravirt_patch_branch_target ia64_native_branch_target[]
-__initconst = {
-#define PARAVIRT_BR_TARGET(name, type)			\
-	{						\
-		ia64_native_ ## name,			\
-		PARAVIRT_PATCH_TYPE_BR_ ## type,	\
-	}
-	PARAVIRT_BR_TARGET(switch_to, SWITCH_TO),
-	PARAVIRT_BR_TARGET(leave_syscall, LEAVE_SYSCALL),
-	PARAVIRT_BR_TARGET(work_processed_syscall, WORK_PROCESSED_SYSCALL),
-	PARAVIRT_BR_TARGET(leave_kernel, LEAVE_KERNEL),
-};
-
-static void __init
-ia64_native_patch_branch(unsigned long tag, unsigned long type)
-{
-	const unsigned long nelem =
-		sizeof(ia64_native_branch_target) /
-		sizeof(ia64_native_branch_target[0]);
-	__paravirt_patch_apply_branch(tag, type,
-				      ia64_native_branch_target, nelem);
-}
diff --git a/arch/ia64/kernel/paravirt_inst.h b/arch/ia64/kernel/paravirt_inst.h
deleted file mode 100644
index 1ad7512b5f65..000000000000
--- a/arch/ia64/kernel/paravirt_inst.h
+++ /dev/null
@@ -1,28 +0,0 @@
-/******************************************************************************
- * linux/arch/ia64/xen/paravirt_inst.h
- *
- * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
- *                    VA Linux Systems Japan K.K.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- */
-
-#ifdef __IA64_ASM_PARAVIRTUALIZED_PVCHECK
-#include <asm/native/pvchk_inst.h>
-#else
-#include <asm/native/inst.h>
-#endif
-
diff --git a/arch/ia64/kernel/paravirt_patch.c b/arch/ia64/kernel/paravirt_patch.c
deleted file mode 100644
index bfdfef1b1ffd..000000000000
--- a/arch/ia64/kernel/paravirt_patch.c
+++ /dev/null
@@ -1,514 +0,0 @@
-/******************************************************************************
- * linux/arch/ia64/xen/paravirt_patch.c
- *
- * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
- *                    VA Linux Systems Japan K.K.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- */
-
-#include <linux/init.h>
-#include <asm/intrinsics.h>
-#include <asm/kprobes.h>
-#include <asm/paravirt.h>
-#include <asm/paravirt_patch.h>
-
-typedef union ia64_inst {
-        struct {
-		unsigned long long qp : 6;
-		unsigned long long : 31;
-		unsigned long long opcode : 4;
-		unsigned long long reserved : 23;
-        } generic;
-        unsigned long long l;
-} ia64_inst_t;
-
-/*
- * flush_icache_range() can't be used here.
- * we are here before cpu_init() which initializes
- * ia64_i_cache_stride_shift. flush_icache_range() uses it.
- */
-void __init_or_module
-paravirt_flush_i_cache_range(const void *instr, unsigned long size)
-{
-	extern void paravirt_fc_i(const void *addr);
-	unsigned long i;
-
-	for (i = 0; i < size; i += sizeof(bundle_t))
-		paravirt_fc_i(instr + i);
-}
-
-bundle_t* __init_or_module
-paravirt_get_bundle(unsigned long tag)
-{
-	return (bundle_t *)(tag & ~3UL);
-}
-
-unsigned long __init_or_module
-paravirt_get_slot(unsigned long tag)
-{
-	return tag & 3UL;
-}
-
-unsigned long __init_or_module
-paravirt_get_num_inst(unsigned long stag, unsigned long etag)
-{
-	bundle_t *sbundle = paravirt_get_bundle(stag);
-	unsigned long sslot = paravirt_get_slot(stag);
-	bundle_t *ebundle = paravirt_get_bundle(etag);
-	unsigned long eslot = paravirt_get_slot(etag);
-
-	return (ebundle - sbundle) * 3 + eslot - sslot + 1;
-}
-
-unsigned long __init_or_module
-paravirt_get_next_tag(unsigned long tag)
-{
-	unsigned long slot = paravirt_get_slot(tag);
-
-	switch (slot) {
-	case 0:
-	case 1:
-		return tag + 1;
-	case 2: {
-		bundle_t *bundle = paravirt_get_bundle(tag);
-		return (unsigned long)(bundle + 1);
-	}
-	default:
-		BUG();
-	}
-	/* NOTREACHED */
-}
-
-ia64_inst_t __init_or_module
-paravirt_read_slot0(const bundle_t *bundle)
-{
-	ia64_inst_t inst;
-	inst.l = bundle->quad0.slot0;
-	return inst;
-}
-
-ia64_inst_t __init_or_module
-paravirt_read_slot1(const bundle_t *bundle)
-{
-	ia64_inst_t inst;
-	inst.l = bundle->quad0.slot1_p0 |
-		((unsigned long long)bundle->quad1.slot1_p1 << 18UL);
-	return inst;
-}
-
-ia64_inst_t __init_or_module
-paravirt_read_slot2(const bundle_t *bundle)
-{
-	ia64_inst_t inst;
-	inst.l = bundle->quad1.slot2;
-	return inst;
-}
-
-ia64_inst_t __init_or_module
-paravirt_read_inst(unsigned long tag)
-{
-	bundle_t *bundle = paravirt_get_bundle(tag);
-	unsigned long slot = paravirt_get_slot(tag);
-
-	switch (slot) {
-	case 0:
-		return paravirt_read_slot0(bundle);
-	case 1:
-		return paravirt_read_slot1(bundle);
-	case 2:
-		return paravirt_read_slot2(bundle);
-	default:
-		BUG();
-	}
-	/* NOTREACHED */
-}
-
-void __init_or_module
-paravirt_write_slot0(bundle_t *bundle, ia64_inst_t inst)
-{
-	bundle->quad0.slot0 = inst.l;
-}
-
-void __init_or_module
-paravirt_write_slot1(bundle_t *bundle, ia64_inst_t inst)
-{
-	bundle->quad0.slot1_p0 = inst.l;
-	bundle->quad1.slot1_p1 = inst.l >> 18UL;
-}
-
-void __init_or_module
-paravirt_write_slot2(bundle_t *bundle, ia64_inst_t inst)
-{
-	bundle->quad1.slot2 = inst.l;
-}
-
-void __init_or_module
-paravirt_write_inst(unsigned long tag, ia64_inst_t inst)
-{
-	bundle_t *bundle = paravirt_get_bundle(tag);
-	unsigned long slot = paravirt_get_slot(tag);
-
-	switch (slot) {
-	case 0:
-		paravirt_write_slot0(bundle, inst);
-		break;
-	case 1:
-		paravirt_write_slot1(bundle, inst);
-		break;
-	case 2:
-		paravirt_write_slot2(bundle, inst);
-		break;
-	default:
-		BUG();
-		break;
-	}
-	paravirt_flush_i_cache_range(bundle, sizeof(*bundle));
-}
-
-/* for debug */
-void
-paravirt_print_bundle(const bundle_t *bundle)
-{
-	const unsigned long *quad = (const unsigned long *)bundle;
-	ia64_inst_t slot0 = paravirt_read_slot0(bundle);
-	ia64_inst_t slot1 = paravirt_read_slot1(bundle);
-	ia64_inst_t slot2 = paravirt_read_slot2(bundle);
-
-	printk(KERN_DEBUG
-	       "bundle 0x%p 0x%016lx 0x%016lx\n", bundle, quad[0], quad[1]);
-	printk(KERN_DEBUG
-	       "bundle template 0x%x\n",
-	       bundle->quad0.template);
-	printk(KERN_DEBUG
-	       "slot0 0x%lx slot1_p0 0x%lx slot1_p1 0x%lx slot2 0x%lx\n",
-	       (unsigned long)bundle->quad0.slot0,
-	       (unsigned long)bundle->quad0.slot1_p0,
-	       (unsigned long)bundle->quad1.slot1_p1,
-	       (unsigned long)bundle->quad1.slot2);
-	printk(KERN_DEBUG
-	       "slot0 0x%016llx slot1 0x%016llx slot2 0x%016llx\n",
-	       slot0.l, slot1.l, slot2.l);
-}
-
-static int noreplace_paravirt __init_or_module = 0;
-
-static int __init setup_noreplace_paravirt(char *str)
-{
-	noreplace_paravirt = 1;
-	return 1;
-}
-__setup("noreplace-paravirt", setup_noreplace_paravirt);
-
-#ifdef ASM_SUPPORTED
-static void __init_or_module
-fill_nop_bundle(void *sbundle, void *ebundle)
-{
-	extern const char paravirt_nop_bundle[];
-	extern const unsigned long paravirt_nop_bundle_size;
-
-	void *bundle = sbundle;
-
-	BUG_ON((((unsigned long)sbundle) % sizeof(bundle_t)) != 0);
-	BUG_ON((((unsigned long)ebundle) % sizeof(bundle_t)) != 0);
-
-	while (bundle < ebundle) {
-		memcpy(bundle, paravirt_nop_bundle, paravirt_nop_bundle_size);
-
-		bundle += paravirt_nop_bundle_size;
-	}
-}
-
-/* helper function */
-unsigned long __init_or_module
-__paravirt_patch_apply_bundle(void *sbundle, void *ebundle, unsigned long type,
-			      const struct paravirt_patch_bundle_elem *elems,
-			      unsigned long nelems,
-			      const struct paravirt_patch_bundle_elem **found)
-{
-	unsigned long used = 0;
-	unsigned long i;
-
-	BUG_ON((((unsigned long)sbundle) % sizeof(bundle_t)) != 0);
-	BUG_ON((((unsigned long)ebundle) % sizeof(bundle_t)) != 0);
-
-	found = NULL;
-	for (i = 0; i < nelems; i++) {
-		const struct paravirt_patch_bundle_elem *p = &elems[i];
-		if (p->type == type) {
-			unsigned long need = p->ebundle - p->sbundle;
-			unsigned long room = ebundle - sbundle;
-
-			if (found != NULL)
-				*found = p;
-
-			if (room < need) {
-				/* no room to replace. skip it */
-				printk(KERN_DEBUG
-				       "the space is too small to put "
-				       "bundles. type %ld need %ld room %ld\n",
-				       type, need, room);
-				break;
-			}
-
-			used = need;
-			memcpy(sbundle, p->sbundle, used);
-			break;
-		}
-	}
-
-	return used;
-}
-
-void __init_or_module
-paravirt_patch_apply_bundle(const struct paravirt_patch_site_bundle *start,
-			    const struct paravirt_patch_site_bundle *end)
-{
-	const struct paravirt_patch_site_bundle *p;
-
-	if (noreplace_paravirt)
-		return;
-	if (pv_init_ops.patch_bundle == NULL)
-		return;
-
-	for (p = start; p < end; p++) {
-		unsigned long used;
-
-		used = (*pv_init_ops.patch_bundle)(p->sbundle, p->ebundle,
-						   p->type);
-		if (used == 0)
-			continue;
-
-		fill_nop_bundle(p->sbundle + used, p->ebundle);
-		paravirt_flush_i_cache_range(p->sbundle,
-					     p->ebundle - p->sbundle);
-	}
-	ia64_sync_i();
-	ia64_srlz_i();
-}
-
-/*
- * nop.i, nop.m, nop.f instruction are same format.
- * but nop.b has differennt format.
- * This doesn't support nop.b for now.
- */
-static void __init_or_module
-fill_nop_inst(unsigned long stag, unsigned long etag)
-{
-	extern const bundle_t paravirt_nop_mfi_inst_bundle[];
-	unsigned long tag;
-	const ia64_inst_t nop_inst =
-		paravirt_read_slot0(paravirt_nop_mfi_inst_bundle);
-
-	for (tag = stag; tag < etag; tag = paravirt_get_next_tag(tag))
-		paravirt_write_inst(tag, nop_inst);
-}
-
-void __init_or_module
-paravirt_patch_apply_inst(const struct paravirt_patch_site_inst *start,
-			  const struct paravirt_patch_site_inst *end)
-{
-	const struct paravirt_patch_site_inst *p;
-
-	if (noreplace_paravirt)
-		return;
-	if (pv_init_ops.patch_inst == NULL)
-		return;
-
-	for (p = start; p < end; p++) {
-		unsigned long tag;
-		bundle_t *sbundle;
-		bundle_t *ebundle;
-
-		tag = (*pv_init_ops.patch_inst)(p->stag, p->etag, p->type);
-		if (tag == p->stag)
-			continue;
-
-		fill_nop_inst(tag, p->etag);
-		sbundle = paravirt_get_bundle(p->stag);
-		ebundle = paravirt_get_bundle(p->etag) + 1;
-		paravirt_flush_i_cache_range(sbundle, (ebundle - sbundle) *
-					     sizeof(bundle_t));
-	}
-	ia64_sync_i();
-	ia64_srlz_i();
-}
-#endif /* ASM_SUPPOTED */
-
-/* brl.cond.sptk.many <target64> X3 */
-typedef union inst_x3_op {
-	ia64_inst_t inst;
-	struct {
-		unsigned long qp: 6;
-		unsigned long btyp: 3;
-		unsigned long unused: 3;
-		unsigned long p: 1;
-		unsigned long imm20b: 20;
-		unsigned long wh: 2;
-		unsigned long d: 1;
-		unsigned long i: 1;
-		unsigned long opcode: 4;
-	};
-	unsigned long l;
-} inst_x3_op_t;
-
-typedef union inst_x3_imm {
-	ia64_inst_t inst;
-	struct {
-		unsigned long unused: 2;
-		unsigned long imm39: 39;
-	};
-	unsigned long l;
-} inst_x3_imm_t;
-
-void __init_or_module
-paravirt_patch_reloc_brl(unsigned long tag, const void *target)
-{
-	unsigned long tag_op = paravirt_get_next_tag(tag);
-	unsigned long tag_imm = tag;
-	bundle_t *bundle = paravirt_get_bundle(tag);
-
-	ia64_inst_t inst_op = paravirt_read_inst(tag_op);
-	ia64_inst_t inst_imm = paravirt_read_inst(tag_imm);
-
-	inst_x3_op_t inst_x3_op = { .l = inst_op.l };
-	inst_x3_imm_t inst_x3_imm = { .l = inst_imm.l };
-
-	unsigned long imm60 =
-		((unsigned long)target - (unsigned long)bundle) >> 4;
-
-	BUG_ON(paravirt_get_slot(tag) != 1); /* MLX */
-	BUG_ON(((unsigned long)target & (sizeof(bundle_t) - 1)) != 0);
-
-	/* imm60[59] 1bit */
-	inst_x3_op.i = (imm60 >> 59) & 1;
-	/* imm60[19:0] 20bit */
-	inst_x3_op.imm20b = imm60 & ((1UL << 20) - 1);
-	/* imm60[58:20] 39bit */
-	inst_x3_imm.imm39 = (imm60 >> 20) & ((1UL << 39) - 1);
-
-	inst_op.l = inst_x3_op.l;
-	inst_imm.l = inst_x3_imm.l;
-
-	paravirt_write_inst(tag_op, inst_op);
-	paravirt_write_inst(tag_imm, inst_imm);
-}
-
-/* br.cond.sptk.many <target25>	B1 */
-typedef union inst_b1 {
-	ia64_inst_t inst;
-	struct {
-		unsigned long qp: 6;
-		unsigned long btype: 3;
-		unsigned long unused: 3;
-		unsigned long p: 1;
-		unsigned long imm20b: 20;
-		unsigned long wh: 2;
-		unsigned long d: 1;
-		unsigned long s: 1;
-		unsigned long opcode: 4;
-	};
-	unsigned long l;
-} inst_b1_t;
-
-void __init
-paravirt_patch_reloc_br(unsigned long tag, const void *target)
-{
-	bundle_t *bundle = paravirt_get_bundle(tag);
-	ia64_inst_t inst = paravirt_read_inst(tag);
-	unsigned long target25 = (unsigned long)target - (unsigned long)bundle;
-	inst_b1_t inst_b1;
-
-	BUG_ON(((unsigned long)target & (sizeof(bundle_t) - 1)) != 0);
-
-	inst_b1.l = inst.l;
-	if (target25 & (1UL << 63))
-		inst_b1.s = 1;
-	else
-		inst_b1.s = 0;
-
-	inst_b1.imm20b = target25 >> 4;
-	inst.l = inst_b1.l;
-
-	paravirt_write_inst(tag, inst);
-}
-
-void __init
-__paravirt_patch_apply_branch(
-	unsigned long tag, unsigned long type,
-	const struct paravirt_patch_branch_target *entries,
-	unsigned int nr_entries)
-{
-	unsigned int i;
-	for (i = 0; i < nr_entries; i++) {
-		if (entries[i].type == type) {
-			paravirt_patch_reloc_br(tag, entries[i].entry);
-			break;
-		}
-	}
-}
-
-static void __init
-paravirt_patch_apply_branch(const struct paravirt_patch_site_branch *start,
-			    const struct paravirt_patch_site_branch *end)
-{
-	const struct paravirt_patch_site_branch *p;
-
-	if (noreplace_paravirt)
-		return;
-	if (pv_init_ops.patch_branch == NULL)
-		return;
-
-	for (p = start; p < end; p++)
-		(*pv_init_ops.patch_branch)(p->tag, p->type);
-
-	ia64_sync_i();
-	ia64_srlz_i();
-}
-
-void __init
-paravirt_patch_apply(void)
-{
-	extern const char __start_paravirt_bundles[];
-	extern const char __stop_paravirt_bundles[];
-	extern const char __start_paravirt_insts[];
-	extern const char __stop_paravirt_insts[];
-	extern const char __start_paravirt_branches[];
-	extern const char __stop_paravirt_branches[];
-
-	paravirt_patch_apply_bundle((const struct paravirt_patch_site_bundle *)
-				    __start_paravirt_bundles,
-				    (const struct paravirt_patch_site_bundle *)
-				    __stop_paravirt_bundles);
-	paravirt_patch_apply_inst((const struct paravirt_patch_site_inst *)
-				  __start_paravirt_insts,
-				  (const struct paravirt_patch_site_inst *)
-				  __stop_paravirt_insts);
-	paravirt_patch_apply_branch((const struct paravirt_patch_site_branch *)
-				    __start_paravirt_branches,
-				    (const struct paravirt_patch_site_branch *)
-				    __stop_paravirt_branches);
-}
-
-/*
- * Local variables:
- * mode: C
- * c-set-style: "linux"
- * c-basic-offset: 8
- * tab-width: 8
- * indent-tabs-mode: t
- * End:
- */
diff --git a/arch/ia64/kernel/paravirt_patchlist.c b/arch/ia64/kernel/paravirt_patchlist.c
deleted file mode 100644
index 0a70720662ed..000000000000
--- a/arch/ia64/kernel/paravirt_patchlist.c
+++ /dev/null
@@ -1,81 +0,0 @@
-/******************************************************************************
- * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
- *                    VA Linux Systems Japan K.K.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- */
-
-#include <linux/bug.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <asm/paravirt.h>
-
-#define DECLARE(name)						\
-	extern unsigned long					\
-		__ia64_native_start_gate_##name##_patchlist[];	\
-	extern unsigned long					\
-		__ia64_native_end_gate_##name##_patchlist[]
-
-DECLARE(fsyscall);
-DECLARE(brl_fsys_bubble_down);
-DECLARE(vtop);
-DECLARE(mckinley_e9);
-
-extern unsigned long __start_gate_section[];
-
-#define ASSIGN(name)							    \
-	.start_##name##_patchlist =					    \
-		(unsigned long)__ia64_native_start_gate_##name##_patchlist, \
-	.end_##name##_patchlist =					    \
-		(unsigned long)__ia64_native_end_gate_##name##_patchlist
-
-struct pv_patchdata pv_patchdata __initdata = {
-	ASSIGN(fsyscall),
-	ASSIGN(brl_fsys_bubble_down),
-	ASSIGN(vtop),
-	ASSIGN(mckinley_e9),
-
-	.gate_section = (void*)__start_gate_section,
-};
-
-
-unsigned long __init
-paravirt_get_gate_patchlist(enum pv_gate_patchlist type)
-{
-
-#define CASE(NAME, name)					\
-	case PV_GATE_START_##NAME:				\
-		return pv_patchdata.start_##name##_patchlist;	\
-	case PV_GATE_END_##NAME:				\
-		return pv_patchdata.end_##name##_patchlist;	\
-
-	switch (type) {
-		CASE(FSYSCALL, fsyscall);
-		CASE(BRL_FSYS_BUBBLE_DOWN, brl_fsys_bubble_down);
-		CASE(VTOP, vtop);
-		CASE(MCKINLEY_E9, mckinley_e9);
-	default:
-		BUG();
-		break;
-	}
-	return 0;
-}
-
-void * __init
-paravirt_get_gate_section(void)
-{
-	return pv_patchdata.gate_section;
-}
diff --git a/arch/ia64/kernel/paravirt_patchlist.h b/arch/ia64/kernel/paravirt_patchlist.h
deleted file mode 100644
index 67cffc3643a3..000000000000
--- a/arch/ia64/kernel/paravirt_patchlist.h
+++ /dev/null
@@ -1,24 +0,0 @@
-/******************************************************************************
- * linux/arch/ia64/xen/paravirt_patchlist.h
- *
- * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
- *                    VA Linux Systems Japan K.K.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- */
-
-#include <asm/native/patchlist.h>
-
diff --git a/arch/ia64/kernel/paravirtentry.S b/arch/ia64/kernel/paravirtentry.S
deleted file mode 100644
index 92d880c4d3d1..000000000000
--- a/arch/ia64/kernel/paravirtentry.S
+++ /dev/null
@@ -1,121 +0,0 @@
-/******************************************************************************
- * linux/arch/ia64/xen/paravirtentry.S
- *
- * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
- *                    VA Linux Systems Japan K.K.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- */
-
-#include <linux/init.h>
-#include <asm/asmmacro.h>
-#include <asm/asm-offsets.h>
-#include <asm/paravirt_privop.h>
-#include <asm/paravirt_patch.h>
-#include "entry.h"
-
-#define DATA8(sym, init_value)			\
-	.pushsection .data..read_mostly ;	\
-	.align 8 ;				\
-	.global sym ;				\
-	sym: ;					\
-	data8 init_value ;			\
-	.popsection
-
-#define BRANCH(targ, reg, breg, type)					\
-	PARAVIRT_PATCH_SITE_BR(PARAVIRT_PATCH_TYPE_BR_ ## type) ;	\
-	;;								\
-	movl reg=targ ;							\
-	;;								\
-	ld8 reg=[reg] ;							\
-	;;								\
-	mov breg=reg ;							\
-	br.cond.sptk.many breg
-
-#define BRANCH_PROC(sym, reg, breg, type)				\
-	DATA8(paravirt_ ## sym ## _targ, ia64_native_ ## sym) ;		\
-	GLOBAL_ENTRY(paravirt_ ## sym) ;				\
-		BRANCH(paravirt_ ## sym ## _targ, reg, breg, type) ;	\
-	END(paravirt_ ## sym)
-
-#define BRANCH_PROC_UNWINFO(sym, reg, breg, type)			\
-	DATA8(paravirt_ ## sym ## _targ, ia64_native_ ## sym) ;		\
-	GLOBAL_ENTRY(paravirt_ ## sym) ;				\
-		PT_REGS_UNWIND_INFO(0) ;				\
-		BRANCH(paravirt_ ## sym ## _targ, reg, breg, type) ;	\
-	END(paravirt_ ## sym)
-
-
-BRANCH_PROC(switch_to, r22, b7, SWITCH_TO)
-BRANCH_PROC_UNWINFO(leave_syscall, r22, b7, LEAVE_SYSCALL)
-BRANCH_PROC(work_processed_syscall, r2, b7, WORK_PROCESSED_SYSCALL)
-BRANCH_PROC_UNWINFO(leave_kernel, r22, b7, LEAVE_KERNEL)
-
-
-#ifdef CONFIG_MODULES
-#define __INIT_OR_MODULE	.text
-#define __INITDATA_OR_MODULE	.data
-#else
-#define __INIT_OR_MODULE	__INIT
-#define __INITDATA_OR_MODULE	__INITDATA
-#endif /* CONFIG_MODULES */
-
-	__INIT_OR_MODULE
-	GLOBAL_ENTRY(paravirt_fc_i)
-	fc.i r32
-	br.ret.sptk.many rp
-	END(paravirt_fc_i)
-	__FINIT
-
-	__INIT_OR_MODULE
-	.align 32
-	GLOBAL_ENTRY(paravirt_nop_b_inst_bundle)
-	{
-		nop.b 0
-		nop.b 0
-		nop.b 0
-	}
-	END(paravirt_nop_b_inst_bundle)
-	__FINIT
-
-	/* NOTE: nop.[mfi] has same format */
-	__INIT_OR_MODULE
-	GLOBAL_ENTRY(paravirt_nop_mfi_inst_bundle)
-	{
-		nop.m 0
-		nop.f 0
-		nop.i 0
-	}
-	END(paravirt_nop_mfi_inst_bundle)
-	__FINIT
-
-	__INIT_OR_MODULE
-	GLOBAL_ENTRY(paravirt_nop_bundle)
-paravirt_nop_bundle_start:
-	{
-		nop 0
-		nop 0
-		nop 0
-	}
-paravirt_nop_bundle_end:
-	END(paravirt_nop_bundle)
-	__FINIT
-
-	__INITDATA_OR_MODULE
-	.align 8
-	.global paravirt_nop_bundle_size
-paravirt_nop_bundle_size:
-	data8	paravirt_nop_bundle_end - paravirt_nop_bundle_start
diff --git a/arch/ia64/kernel/patch.c b/arch/ia64/kernel/patch.c
index 1cf091793714..944a8e2438a6 100644
--- a/arch/ia64/kernel/patch.c
+++ b/arch/ia64/kernel/patch.c
@@ -7,7 +7,6 @@
 #include <linux/init.h>
 #include <linux/string.h>
 
-#include <asm/paravirt.h>
 #include <asm/patch.h>
 #include <asm/processor.h>
 #include <asm/sections.h>
@@ -169,35 +168,16 @@ ia64_patch_mckinley_e9 (unsigned long start, unsigned long end)
 	ia64_srlz_i();
 }
 
-extern unsigned long ia64_native_fsyscall_table[NR_syscalls];
-extern char ia64_native_fsys_bubble_down[];
-struct pv_fsys_data pv_fsys_data __initdata = {
-	.fsyscall_table = (unsigned long *)ia64_native_fsyscall_table,
-	.fsys_bubble_down = (void *)ia64_native_fsys_bubble_down,
-};
-
-unsigned long * __init
-paravirt_get_fsyscall_table(void)
-{
-	return pv_fsys_data.fsyscall_table;
-}
-
-char * __init
-paravirt_get_fsys_bubble_down(void)
-{
-	return pv_fsys_data.fsys_bubble_down;
-}
-
 static void __init
 patch_fsyscall_table (unsigned long start, unsigned long end)
 {
-	u64 fsyscall_table = (u64)paravirt_get_fsyscall_table();
+	extern unsigned long fsyscall_table[NR_syscalls];
 	s32 *offp = (s32 *) start;
 	u64 ip;
 
 	while (offp < (s32 *) end) {
 		ip = (u64) ia64_imva((char *) offp + *offp);
-		ia64_patch_imm64(ip, fsyscall_table);
+		ia64_patch_imm64(ip, (u64) fsyscall_table);
 		ia64_fc((void *) ip);
 		++offp;
 	}
@@ -208,7 +188,7 @@ patch_fsyscall_table (unsigned long start, unsigned long end)
 static void __init
 patch_brl_fsys_bubble_down (unsigned long start, unsigned long end)
 {
-	u64 fsys_bubble_down = (u64)paravirt_get_fsys_bubble_down();
+	extern char fsys_bubble_down[];
 	s32 *offp = (s32 *) start;
 	u64 ip;
 
@@ -226,13 +206,13 @@ patch_brl_fsys_bubble_down (unsigned long start, unsigned long end)
 void __init
 ia64_patch_gate (void)
 {
-#	define START(name)	paravirt_get_gate_patchlist(PV_GATE_START_##name)
-#	define END(name)	paravirt_get_gate_patchlist(PV_GATE_END_##name)
+#	define START(name)	((unsigned long) __start_gate_##name##_patchlist)
+#	define END(name)	((unsigned long)__end_gate_##name##_patchlist)
 
-	patch_fsyscall_table(START(FSYSCALL), END(FSYSCALL));
-	patch_brl_fsys_bubble_down(START(BRL_FSYS_BUBBLE_DOWN), END(BRL_FSYS_BUBBLE_DOWN));
-	ia64_patch_vtop(START(VTOP), END(VTOP));
-	ia64_patch_mckinley_e9(START(MCKINLEY_E9), END(MCKINLEY_E9));
+	patch_fsyscall_table(START(fsyscall), END(fsyscall));
+	patch_brl_fsys_bubble_down(START(brl_fsys_bubble_down), END(brl_fsys_bubble_down));
+	ia64_patch_vtop(START(vtop), END(vtop));
+	ia64_patch_mckinley_e9(START(mckinley_e9), END(mckinley_e9));
 }
 
 void ia64_patch_phys_stack_reg(unsigned long val)
diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index b9761389cb8d..4f118b0d3091 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -50,8 +50,6 @@
 #include <asm/mca.h>
 #include <asm/meminit.h>
 #include <asm/page.h>
-#include <asm/paravirt.h>
-#include <asm/paravirt_patch.h>
 #include <asm/patch.h>
 #include <asm/pgtable.h>
 #include <asm/processor.h>
@@ -360,8 +358,6 @@ reserve_memory (void)
 	rsvd_region[n].end   = (unsigned long) ia64_imva(_end);
 	n++;
 
-	n += paravirt_reserve_memory(&rsvd_region[n]);
-
 #ifdef CONFIG_BLK_DEV_INITRD
 	if (ia64_boot_param->initrd_start) {
 		rsvd_region[n].start = (unsigned long)__va(ia64_boot_param->initrd_start);
@@ -528,10 +524,7 @@ setup_arch (char **cmdline_p)
 {
 	unw_init();
 
-	paravirt_arch_setup_early();
-
 	ia64_patch_vtop((u64) __start___vtop_patchlist, (u64) __end___vtop_patchlist);
-	paravirt_patch_apply();
 
 	*cmdline_p = __va(ia64_boot_param->command_line);
 	strlcpy(boot_command_line, *cmdline_p, COMMAND_LINE_SIZE);
@@ -594,9 +587,6 @@ setup_arch (char **cmdline_p)
 	cpu_init();	/* initialize the bootstrap CPU */
 	mmu_context_init();	/* initialize context_id bitmap */
 
-	paravirt_banner();
-	paravirt_arch_setup_console(cmdline_p);
-
 #ifdef CONFIG_VT
 	if (!conswitchp) {
 # if defined(CONFIG_DUMMY_CONSOLE)
@@ -616,8 +606,6 @@ setup_arch (char **cmdline_p)
 #endif
 
 	/* enable IA-64 Machine Check Abort Handling unless disabled */
-	if (paravirt_arch_setup_nomca())
-		nomca = 1;
 	if (!nomca)
 		ia64_mca_init();
 
diff --git a/arch/ia64/kernel/smpboot.c b/arch/ia64/kernel/smpboot.c
index b054c5c6e713..0e76fad27975 100644
--- a/arch/ia64/kernel/smpboot.c
+++ b/arch/ia64/kernel/smpboot.c
@@ -49,7 +49,6 @@
 #include <asm/machvec.h>
 #include <asm/mca.h>
 #include <asm/page.h>
-#include <asm/paravirt.h>
 #include <asm/pgalloc.h>
 #include <asm/pgtable.h>
 #include <asm/processor.h>
@@ -569,7 +568,6 @@ void smp_prepare_boot_cpu(void)
 	cpumask_set_cpu(smp_processor_id(), &cpu_callin_map);
 	set_numa_node(cpu_to_node_map[smp_processor_id()]);
 	per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE;
-	paravirt_post_smp_prepare_boot_cpu();
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c
index 9a0104a38cd3..c8dbe2acd735 100644
--- a/arch/ia64/kernel/time.c
+++ b/arch/ia64/kernel/time.c
@@ -25,7 +25,6 @@
 #include <asm/machvec.h>
 #include <asm/delay.h>
 #include <asm/hw_irq.h>
-#include <asm/paravirt.h>
 #include <asm/ptrace.h>
 #include <asm/sal.h>
 #include <asm/sections.h>
@@ -47,33 +46,12 @@ EXPORT_SYMBOL(last_cli_ip);
 
 #endif
 
-#ifdef CONFIG_PARAVIRT
-/* We need to define a real function for sched_clock, to override the
-   weak default version */
-unsigned long long sched_clock(void)
-{
-        return paravirt_sched_clock();
-}
-#endif
-
-#ifdef CONFIG_PARAVIRT
-static void
-paravirt_clocksource_resume(struct clocksource *cs)
-{
-	if (pv_time_ops.clocksource_resume)
-		pv_time_ops.clocksource_resume();
-}
-#endif
-
 static struct clocksource clocksource_itc = {
 	.name           = "itc",
 	.rating         = 350,
 	.read           = itc_get_cycles,
 	.mask           = CLOCKSOURCE_MASK(64),
 	.flags          = CLOCK_SOURCE_IS_CONTINUOUS,
-#ifdef CONFIG_PARAVIRT
-	.resume		= paravirt_clocksource_resume,
-#endif
 };
 static struct clocksource *itc_clocksource;
 
@@ -164,9 +142,6 @@ timer_interrupt (int irq, void *dev_id)
 
 	profile_tick(CPU_PROFILING);
 
-	if (paravirt_do_steal_accounting(&new_itm))
-		goto skip_process_time_accounting;
-
 	while (1) {
 		update_process_times(user_mode(get_irq_regs()));
 
@@ -187,8 +162,6 @@ timer_interrupt (int irq, void *dev_id)
 		local_irq_disable();
 	}
 
-skip_process_time_accounting:
-
 	do {
 		/*
 		 * If we're too close to the next clock tick for
@@ -337,8 +310,6 @@ void ia64_init_itm(void)
 		 */
 		clocksource_itc.rating = 50;
 
-	paravirt_init_missing_ticks_accounting(smp_processor_id());
-
 	/* avoid softlock up message when cpu is unplug and plugged again. */
 	touch_softlockup_watchdog();
 
diff --git a/arch/ia64/kernel/vmlinux.lds.S b/arch/ia64/kernel/vmlinux.lds.S
index 84f8a52ac5ae..dc506b05ffbd 100644
--- a/arch/ia64/kernel/vmlinux.lds.S
+++ b/arch/ia64/kernel/vmlinux.lds.S
@@ -136,27 +136,6 @@ SECTIONS {
 		__end___mckinley_e9_bundles = .;
 	}
 
-#if defined(CONFIG_PARAVIRT)
-	. = ALIGN(16);
-	.paravirt_bundles : AT(ADDR(.paravirt_bundles) - LOAD_OFFSET) {
-		__start_paravirt_bundles = .;
-		*(.paravirt_bundles)
-		__stop_paravirt_bundles = .;
-	}
-	. = ALIGN(16);
-	.paravirt_insts : AT(ADDR(.paravirt_insts) - LOAD_OFFSET) {
-		__start_paravirt_insts = .;
-		*(.paravirt_insts)
-		__stop_paravirt_insts = .;
-	}
-	. = ALIGN(16);
-	.paravirt_branches : AT(ADDR(.paravirt_branches) - LOAD_OFFSET) {
-		__start_paravirt_branches = .;
-		*(.paravirt_branches)
-		__stop_paravirt_branches = .;
-	}
-#endif
-
 #if defined(CONFIG_IA64_GENERIC)
 	/* Machine Vector */
 	. = ALIGN(16);
diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c
index ba5ba7accd0d..70b40d1205a6 100644
--- a/arch/ia64/mm/fault.c
+++ b/arch/ia64/mm/fault.c
@@ -11,10 +11,10 @@
 #include <linux/kprobes.h>
 #include <linux/kdebug.h>
 #include <linux/prefetch.h>
+#include <linux/uaccess.h>
 
 #include <asm/pgtable.h>
 #include <asm/processor.h>
-#include <asm/uaccess.h>
 
 extern int die(char *, struct pt_regs *, long);
 
@@ -96,7 +96,7 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re
 	/*
 	 * If we're in an interrupt or have no user context, we must not take the fault..
 	 */
-	if (in_atomic() || !mm)
+	if (faulthandler_disabled() || !mm)
 		goto no_context;
 
 #ifdef CONFIG_VIRTUAL_MEM_MAP
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index a9b65cf7b34a..7f3028965064 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -34,7 +34,6 @@
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
 #include <asm/mca.h>
-#include <asm/paravirt.h>
 
 extern void ia64_tlb_init (void);
 
@@ -244,7 +243,6 @@ put_kernel_page (struct page *page, unsigned long address, pgprot_t pgprot)
 static void __init
 setup_gate (void)
 {
-	void *gate_section;
 	struct page *page;
 
 	/*
@@ -252,11 +250,10 @@ setup_gate (void)
 	 * headers etc. and once execute-only page to enable
 	 * privilege-promotion via "epc":
 	 */
-	gate_section = paravirt_get_gate_section();
-	page = virt_to_page(ia64_imva(gate_section));
+	page = virt_to_page(ia64_imva(__start_gate_section));
 	put_kernel_page(page, GATE_ADDR, PAGE_READONLY);
 #ifdef HAVE_BUGGY_SEGREL
-	page = virt_to_page(ia64_imva(gate_section + PAGE_SIZE));
+	page = virt_to_page(ia64_imva(__start_gate_section + PAGE_SIZE));
 	put_kernel_page(page, GATE_ADDR + PAGE_SIZE, PAGE_GATE);
 #else
 	put_kernel_page(page, GATE_ADDR + PERCPU_PAGE_SIZE, PAGE_GATE);
@@ -642,8 +639,8 @@ mem_init (void)
 	 * code can tell them apart.
 	 */
 	for (i = 0; i < NR_syscalls; ++i) {
+		extern unsigned long fsyscall_table[NR_syscalls];
 		extern unsigned long sys_call_table[NR_syscalls];
-		unsigned long *fsyscall_table = paravirt_get_fsyscall_table();
 
 		if (!fsyscall_table[i] || nolwsys)
 			fsyscall_table[i] = sys_call_table[i] | 1;
diff --git a/arch/ia64/scripts/pvcheck.sed b/arch/ia64/scripts/pvcheck.sed
deleted file mode 100644
index e59809a3fc01..000000000000
--- a/arch/ia64/scripts/pvcheck.sed
+++ /dev/null
@@ -1,33 +0,0 @@
-#
-# Checker for paravirtualizations of privileged operations.
-#
-s/ssm.*psr\.ic.*/.warning \"ssm psr.ic should not be used directly\"/g
-s/rsm.*psr\.ic.*/.warning \"rsm psr.ic should not be used directly\"/g
-s/ssm.*psr\.i.*/.warning \"ssm psr.i should not be used directly\"/g
-s/rsm.*psr\.i.*/.warning \"rsm psr.i should not be used directly\"/g
-s/ssm.*psr\.dt.*/.warning \"ssm psr.dt should not be used directly\"/g
-s/rsm.*psr\.dt.*/.warning \"rsm psr.dt should not be used directly\"/g
-s/mov.*=.*cr\.ifa/.warning \"cr.ifa should not used directly\"/g
-s/mov.*=.*cr\.itir/.warning \"cr.itir should not used directly\"/g
-s/mov.*=.*cr\.isr/.warning \"cr.isr should not used directly\"/g
-s/mov.*=.*cr\.iha/.warning \"cr.iha should not used directly\"/g
-s/mov.*=.*cr\.ipsr/.warning \"cr.ipsr should not used directly\"/g
-s/mov.*=.*cr\.iim/.warning \"cr.iim should not used directly\"/g
-s/mov.*=.*cr\.iip/.warning \"cr.iip should not used directly\"/g
-s/mov.*=.*cr\.ivr/.warning \"cr.ivr should not used directly\"/g
-s/mov.*=[^\.]*psr/.warning \"psr should not used directly\"/g	# avoid ar.fpsr
-s/mov.*=.*ar\.eflags/.warning \"ar.eflags should not used directly\"/g
-s/mov.*=.*ar\.itc.*/.warning \"ar.itc should not used directly\"/g
-s/mov.*cr\.ifa.*=.*/.warning \"cr.ifa should not used directly\"/g
-s/mov.*cr\.itir.*=.*/.warning \"cr.itir should not used directly\"/g
-s/mov.*cr\.iha.*=.*/.warning \"cr.iha should not used directly\"/g
-s/mov.*cr\.ipsr.*=.*/.warning \"cr.ipsr should not used directly\"/g
-s/mov.*cr\.ifs.*=.*/.warning \"cr.ifs should not used directly\"/g
-s/mov.*cr\.iip.*=.*/.warning \"cr.iip should not used directly\"/g
-s/mov.*cr\.kr.*=.*/.warning \"cr.kr should not used directly\"/g
-s/mov.*ar\.eflags.*=.*/.warning \"ar.eflags should not used directly\"/g
-s/itc\.i.*/.warning \"itc.i should not be used directly.\"/g
-s/itc\.d.*/.warning \"itc.d should not be used directly.\"/g
-s/bsw\.0/.warning \"bsw.0 should not be used directly.\"/g
-s/bsw\.1/.warning \"bsw.1 should not be used directly.\"/g
-s/ptc\.ga.*/.warning \"ptc.ga should not be used directly.\"/g
diff --git a/arch/m32r/include/asm/cmpxchg.h b/arch/m32r/include/asm/cmpxchg.h
index de651db20b43..14bf9b739dd2 100644
--- a/arch/m32r/include/asm/cmpxchg.h
+++ b/arch/m32r/include/asm/cmpxchg.h
@@ -107,8 +107,6 @@ __xchg_local(unsigned long x, volatile void *ptr, int size)
 	((__typeof__(*(ptr)))__xchg_local((unsigned long)(x), (ptr),	\
 			sizeof(*(ptr))))
 
-#define __HAVE_ARCH_CMPXCHG	1
-
 static inline unsigned long
 __cmpxchg_u32(volatile unsigned int *p, unsigned int old, unsigned int new)
 {
diff --git a/arch/m32r/include/asm/io.h b/arch/m32r/include/asm/io.h
index 9cc00dbd59ce..0c3f25ee3381 100644
--- a/arch/m32r/include/asm/io.h
+++ b/arch/m32r/include/asm/io.h
@@ -68,6 +68,7 @@ static inline void __iomem *ioremap(unsigned long offset, unsigned long size)
 extern void iounmap(volatile void __iomem *addr);
 #define ioremap_nocache(off,size) ioremap(off,size)
 #define ioremap_wc ioremap_nocache
+#define ioremap_wt ioremap_nocache
 
 /*
  * IO bus memory addresses are also 1:1 with the physical address
diff --git a/arch/m32r/include/asm/uaccess.h b/arch/m32r/include/asm/uaccess.h
index 71adff209405..cac7014daef3 100644
--- a/arch/m32r/include/asm/uaccess.h
+++ b/arch/m32r/include/asm/uaccess.h
@@ -91,7 +91,8 @@ static inline void set_fs(mm_segment_t s)
  * @addr: User space pointer to start of block to check
  * @size: Size of block to check
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Checks if a pointer to a block of memory in user space is valid.
  *
@@ -155,7 +156,8 @@ extern int fixup_exception(struct pt_regs *regs);
  * @x:   Variable to store result.
  * @ptr: Source address, in user space.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple variable from user space to kernel
  * space.  It supports simple types like char and int, but not larger
@@ -175,7 +177,8 @@ extern int fixup_exception(struct pt_regs *regs);
  * @x:   Value to copy to user space.
  * @ptr: Destination address, in user space.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple value from kernel space to user
  * space.  It supports simple types like char and int, but not larger
@@ -194,7 +197,8 @@ extern int fixup_exception(struct pt_regs *regs);
  * @x:   Variable to store result.
  * @ptr: Source address, in user space.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple variable from user space to kernel
  * space.  It supports simple types like char and int, but not larger
@@ -274,7 +278,8 @@ do {									\
  * @x:   Value to copy to user space.
  * @ptr: Destination address, in user space.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple value from kernel space to user
  * space.  It supports simple types like char and int, but not larger
@@ -568,7 +573,8 @@ unsigned long __generic_copy_from_user(void *, const void __user *, unsigned lon
  * @from: Source address, in kernel space.
  * @n:    Number of bytes to copy.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Copy data from kernel space to user space.  Caller must check
  * the specified block with access_ok() before calling this function.
@@ -588,7 +594,8 @@ unsigned long __generic_copy_from_user(void *, const void __user *, unsigned lon
  * @from: Source address, in kernel space.
  * @n:    Number of bytes to copy.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Copy data from kernel space to user space.
  *
@@ -606,7 +613,8 @@ unsigned long __generic_copy_from_user(void *, const void __user *, unsigned lon
  * @from: Source address, in user space.
  * @n:    Number of bytes to copy.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Copy data from user space to kernel space.  Caller must check
  * the specified block with access_ok() before calling this function.
@@ -626,7 +634,8 @@ unsigned long __generic_copy_from_user(void *, const void __user *, unsigned lon
  * @from: Source address, in user space.
  * @n:    Number of bytes to copy.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Copy data from user space to kernel space.
  *
@@ -677,7 +686,8 @@ unsigned long clear_user(void __user *mem, unsigned long len);
  * strlen_user: - Get the size of a string in user space.
  * @str: The string to measure.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Get the size of a NUL-terminated string in user space.
  *
diff --git a/arch/m32r/mm/fault.c b/arch/m32r/mm/fault.c
index e3d4d4890104..8f9875b7933d 100644
--- a/arch/m32r/mm/fault.c
+++ b/arch/m32r/mm/fault.c
@@ -24,9 +24,9 @@
 #include <linux/vt_kern.h>		/* For unblank_screen() */
 #include <linux/highmem.h>
 #include <linux/module.h>
+#include <linux/uaccess.h>
 
 #include <asm/m32r.h>
-#include <asm/uaccess.h>
 #include <asm/hardirq.h>
 #include <asm/mmu_context.h>
 #include <asm/tlbflush.h>
@@ -111,10 +111,10 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code,
 	mm = tsk->mm;
 
 	/*
-	 * If we're in an interrupt or have no user context or are running in an
-	 * atomic region then we must not take the fault..
+	 * If we're in an interrupt or have no user context or have pagefaults
+	 * disabled then we must not take the fault.
 	 */
-	if (in_atomic() || !mm)
+	if (faulthandler_disabled() || !mm)
 		goto bad_area_nosemaphore;
 
 	if (error_code & ACE_USERMODE)
diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig
index ed1643b4c678..753a6237f99a 100644
--- a/arch/m68k/configs/amiga_defconfig
+++ b/arch/m68k/configs/amiga_defconfig
@@ -177,9 +177,9 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NFT_MASQ_IPV4=m
 CONFIG_NFT_REDIR_IPV4=m
@@ -267,7 +267,9 @@ CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
 CONFIG_NETLINK_DIAG=m
+CONFIG_MPLS=y
 CONFIG_NET_MPLS_GSO=m
+CONFIG_MPLS_ROUTING=m
 # CONFIG_WIRELESS is not set
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
@@ -285,6 +287,7 @@ CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_DRBD=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_PMEM=m
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_ATA_OVER_ETH=m
 CONFIG_DUMMY_IRQ=m
@@ -324,6 +327,7 @@ CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
 CONFIG_DM_MULTIPATH=m
 CONFIG_DM_UEVENT=y
+CONFIG_DM_LOG_WRITES=m
 CONFIG_TARGET_CORE=m
 CONFIG_TCM_IBLOCK=m
 CONFIG_TCM_FILEIO=m
@@ -348,6 +352,7 @@ CONFIG_VETH=m
 CONFIG_A2065=y
 CONFIG_ARIADNE=y
 # CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 # CONFIG_NET_VENDOR_CIRRUS is not set
 # CONFIG_NET_VENDOR_HP is not set
@@ -414,7 +419,6 @@ CONFIG_HID=m
 CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
-# CONFIG_HID_PLANTRONICS is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_MSM6242=m
diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig
index d38822b1847e..1f93dcaf02e5 100644
--- a/arch/m68k/configs/apollo_defconfig
+++ b/arch/m68k/configs/apollo_defconfig
@@ -175,9 +175,9 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NFT_MASQ_IPV4=m
 CONFIG_NFT_REDIR_IPV4=m
@@ -265,7 +265,9 @@ CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
 CONFIG_NETLINK_DIAG=m
+CONFIG_MPLS=y
 CONFIG_NET_MPLS_GSO=m
+CONFIG_MPLS_ROUTING=m
 # CONFIG_WIRELESS is not set
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
@@ -277,6 +279,7 @@ CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_DRBD=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_PMEM=m
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_ATA_OVER_ETH=m
 CONFIG_DUMMY_IRQ=m
@@ -306,6 +309,7 @@ CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
 CONFIG_DM_MULTIPATH=m
 CONFIG_DM_UEVENT=y
+CONFIG_DM_LOG_WRITES=m
 CONFIG_TARGET_CORE=m
 CONFIG_TCM_IBLOCK=m
 CONFIG_TCM_FILEIO=m
@@ -327,6 +331,7 @@ CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
 # CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
@@ -375,7 +380,6 @@ CONFIG_HID=m
 CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
-# CONFIG_HID_PLANTRONICS is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_GENERIC=m
diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig
index c429199cf4a9..831b8b8b92ad 100644
--- a/arch/m68k/configs/atari_defconfig
+++ b/arch/m68k/configs/atari_defconfig
@@ -175,9 +175,9 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NFT_MASQ_IPV4=m
 CONFIG_NFT_REDIR_IPV4=m
@@ -265,7 +265,9 @@ CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
 CONFIG_NETLINK_DIAG=m
+CONFIG_MPLS=y
 CONFIG_NET_MPLS_GSO=m
+CONFIG_MPLS_ROUTING=m
 # CONFIG_WIRELESS is not set
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
@@ -281,6 +283,7 @@ CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_DRBD=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_PMEM=m
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_ATA_OVER_ETH=m
 CONFIG_DUMMY_IRQ=m
@@ -315,6 +318,7 @@ CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
 CONFIG_DM_MULTIPATH=m
 CONFIG_DM_UEVENT=y
+CONFIG_DM_LOG_WRITES=m
 CONFIG_TARGET_CORE=m
 CONFIG_TCM_IBLOCK=m
 CONFIG_TCM_FILEIO=m
@@ -337,6 +341,7 @@ CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
 CONFIG_ATARILANCE=y
 # CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
@@ -391,7 +396,6 @@ CONFIG_DMASOUND_ATARI=m
 CONFIG_HID=m
 CONFIG_HIDRAW=y
 CONFIG_UHID=m
-# CONFIG_HID_PLANTRONICS is not set
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_IOMMU_SUPPORT is not set
diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig
index 9b880371d642..91fd187c16d5 100644
--- a/arch/m68k/configs/bvme6000_defconfig
+++ b/arch/m68k/configs/bvme6000_defconfig
@@ -173,9 +173,9 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NFT_MASQ_IPV4=m
 CONFIG_NFT_REDIR_IPV4=m
@@ -263,7 +263,9 @@ CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
 CONFIG_NETLINK_DIAG=m
+CONFIG_MPLS=y
 CONFIG_NET_MPLS_GSO=m
+CONFIG_MPLS_ROUTING=m
 # CONFIG_WIRELESS is not set
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
@@ -275,6 +277,7 @@ CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_DRBD=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_PMEM=m
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_ATA_OVER_ETH=m
 CONFIG_DUMMY_IRQ=m
@@ -305,6 +308,7 @@ CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
 CONFIG_DM_MULTIPATH=m
 CONFIG_DM_UEVENT=y
+CONFIG_DM_LOG_WRITES=m
 CONFIG_TARGET_CORE=m
 CONFIG_TCM_IBLOCK=m
 CONFIG_TCM_FILEIO=m
@@ -326,6 +330,7 @@ CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
 # CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 CONFIG_BVME6000_NET=y
 # CONFIG_NET_VENDOR_MARVELL is not set
@@ -369,7 +374,6 @@ CONFIG_HID=m
 CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
-# CONFIG_HID_PLANTRONICS is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_GENERIC=m
diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig
index 49ae3376e993..9d4934f1d2c3 100644
--- a/arch/m68k/configs/hp300_defconfig
+++ b/arch/m68k/configs/hp300_defconfig
@@ -175,9 +175,9 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NFT_MASQ_IPV4=m
 CONFIG_NFT_REDIR_IPV4=m
@@ -265,7 +265,9 @@ CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
 CONFIG_NETLINK_DIAG=m
+CONFIG_MPLS=y
 CONFIG_NET_MPLS_GSO=m
+CONFIG_MPLS_ROUTING=m
 # CONFIG_WIRELESS is not set
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
@@ -277,6 +279,7 @@ CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_DRBD=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_PMEM=m
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_ATA_OVER_ETH=m
 CONFIG_DUMMY_IRQ=m
@@ -306,6 +309,7 @@ CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
 CONFIG_DM_MULTIPATH=m
 CONFIG_DM_UEVENT=y
+CONFIG_DM_LOG_WRITES=m
 CONFIG_TARGET_CORE=m
 CONFIG_TCM_IBLOCK=m
 CONFIG_TCM_FILEIO=m
@@ -328,6 +332,7 @@ CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
 CONFIG_HPLANCE=y
 # CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
@@ -378,7 +383,6 @@ CONFIG_HID=m
 CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
-# CONFIG_HID_PLANTRONICS is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_GENERIC=m
diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig
index ee143a57058c..72bc187ca995 100644
--- a/arch/m68k/configs/mac_defconfig
+++ b/arch/m68k/configs/mac_defconfig
@@ -174,9 +174,9 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NFT_MASQ_IPV4=m
 CONFIG_NFT_REDIR_IPV4=m
@@ -267,7 +267,9 @@ CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
 CONFIG_NETLINK_DIAG=m
+CONFIG_MPLS=y
 CONFIG_NET_MPLS_GSO=m
+CONFIG_MPLS_ROUTING=m
 # CONFIG_WIRELESS is not set
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
@@ -280,6 +282,7 @@ CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_DRBD=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_PMEM=m
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_ATA_OVER_ETH=m
 CONFIG_DUMMY_IRQ=m
@@ -315,6 +318,7 @@ CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
 CONFIG_DM_MULTIPATH=m
 CONFIG_DM_UEVENT=y
+CONFIG_DM_LOG_WRITES=m
 CONFIG_TARGET_CORE=m
 CONFIG_TCM_IBLOCK=m
 CONFIG_TCM_FILEIO=m
@@ -344,6 +348,7 @@ CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
 CONFIG_MACMACE=y
 # CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 CONFIG_MAC89x0=y
 # CONFIG_NET_VENDOR_INTEL is not set
@@ -400,7 +405,6 @@ CONFIG_HID=m
 CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
-# CONFIG_HID_PLANTRONICS is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_GENERIC=m
diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig
index c777aa05048f..8fb65535597f 100644
--- a/arch/m68k/configs/multi_defconfig
+++ b/arch/m68k/configs/multi_defconfig
@@ -184,9 +184,9 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NFT_MASQ_IPV4=m
 CONFIG_NFT_REDIR_IPV4=m
@@ -277,7 +277,9 @@ CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
 CONFIG_NETLINK_DIAG=m
+CONFIG_MPLS=y
 CONFIG_NET_MPLS_GSO=m
+CONFIG_MPLS_ROUTING=m
 # CONFIG_WIRELESS is not set
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
@@ -299,6 +301,7 @@ CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_DRBD=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_PMEM=m
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_ATA_OVER_ETH=m
 CONFIG_DUMMY_IRQ=m
@@ -348,6 +351,7 @@ CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
 CONFIG_DM_MULTIPATH=m
 CONFIG_DM_UEVENT=y
+CONFIG_DM_LOG_WRITES=m
 CONFIG_TARGET_CORE=m
 CONFIG_TCM_IBLOCK=m
 CONFIG_TCM_FILEIO=m
@@ -384,6 +388,7 @@ CONFIG_MVME147_NET=y
 CONFIG_SUN3LANCE=y
 CONFIG_MACMACE=y
 # CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 CONFIG_MAC89x0=y
 # CONFIG_NET_VENDOR_HP is not set
@@ -468,7 +473,6 @@ CONFIG_HID=m
 CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
-# CONFIG_HID_PLANTRONICS is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_MSM6242=m
diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig
index a7628a85e260..f34491ec0126 100644
--- a/arch/m68k/configs/mvme147_defconfig
+++ b/arch/m68k/configs/mvme147_defconfig
@@ -172,9 +172,9 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NFT_MASQ_IPV4=m
 CONFIG_NFT_REDIR_IPV4=m
@@ -262,7 +262,9 @@ CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
 CONFIG_NETLINK_DIAG=m
+CONFIG_MPLS=y
 CONFIG_NET_MPLS_GSO=m
+CONFIG_MPLS_ROUTING=m
 # CONFIG_WIRELESS is not set
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
@@ -274,6 +276,7 @@ CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_DRBD=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_PMEM=m
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_ATA_OVER_ETH=m
 CONFIG_DUMMY_IRQ=m
@@ -304,6 +307,7 @@ CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
 CONFIG_DM_MULTIPATH=m
 CONFIG_DM_UEVENT=y
+CONFIG_DM_LOG_WRITES=m
 CONFIG_TARGET_CORE=m
 CONFIG_TCM_IBLOCK=m
 CONFIG_TCM_FILEIO=m
@@ -326,6 +330,7 @@ CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
 CONFIG_MVME147_NET=y
 # CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
@@ -369,7 +374,6 @@ CONFIG_HID=m
 CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
-# CONFIG_HID_PLANTRONICS is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_GENERIC=m
diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig
index ebaa68268a4a..3d3614d1b041 100644
--- a/arch/m68k/configs/mvme16x_defconfig
+++ b/arch/m68k/configs/mvme16x_defconfig
@@ -173,9 +173,9 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NFT_MASQ_IPV4=m
 CONFIG_NFT_REDIR_IPV4=m
@@ -263,7 +263,9 @@ CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
 CONFIG_NETLINK_DIAG=m
+CONFIG_MPLS=y
 CONFIG_NET_MPLS_GSO=m
+CONFIG_MPLS_ROUTING=m
 # CONFIG_WIRELESS is not set
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
@@ -275,6 +277,7 @@ CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_DRBD=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_PMEM=m
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_ATA_OVER_ETH=m
 CONFIG_DUMMY_IRQ=m
@@ -305,6 +308,7 @@ CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
 CONFIG_DM_MULTIPATH=m
 CONFIG_DM_UEVENT=y
+CONFIG_DM_LOG_WRITES=m
 CONFIG_TARGET_CORE=m
 CONFIG_TCM_IBLOCK=m
 CONFIG_TCM_FILEIO=m
@@ -326,6 +330,7 @@ CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
 # CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 CONFIG_MVME16x_NET=y
 # CONFIG_NET_VENDOR_MARVELL is not set
@@ -369,7 +374,6 @@ CONFIG_HID=m
 CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
-# CONFIG_HID_PLANTRONICS is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_GENERIC=m
diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig
index 2c16853aedd3..643e9c93bea7 100644
--- a/arch/m68k/configs/q40_defconfig
+++ b/arch/m68k/configs/q40_defconfig
@@ -173,9 +173,9 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NFT_MASQ_IPV4=m
 CONFIG_NFT_REDIR_IPV4=m
@@ -263,7 +263,9 @@ CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
 CONFIG_NETLINK_DIAG=m
+CONFIG_MPLS=y
 CONFIG_NET_MPLS_GSO=m
+CONFIG_MPLS_ROUTING=m
 # CONFIG_WIRELESS is not set
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
@@ -278,6 +280,7 @@ CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_DRBD=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_PMEM=m
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_ATA_OVER_ETH=m
 CONFIG_DUMMY_IRQ=m
@@ -311,6 +314,7 @@ CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
 CONFIG_DM_MULTIPATH=m
 CONFIG_DM_UEVENT=y
+CONFIG_DM_LOG_WRITES=m
 CONFIG_TARGET_CORE=m
 CONFIG_TCM_IBLOCK=m
 CONFIG_TCM_FILEIO=m
@@ -334,6 +338,7 @@ CONFIG_VETH=m
 # CONFIG_NET_VENDOR_3COM is not set
 # CONFIG_NET_VENDOR_AMD is not set
 # CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 # CONFIG_NET_VENDOR_CIRRUS is not set
 # CONFIG_NET_VENDOR_HP is not set
@@ -390,7 +395,6 @@ CONFIG_HID=m
 CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
-# CONFIG_HID_PLANTRONICS is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_GENERIC=m
diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig
index e3056bf0f65b..8fecc5aa166c 100644
--- a/arch/m68k/configs/sun3_defconfig
+++ b/arch/m68k/configs/sun3_defconfig
@@ -170,9 +170,9 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NFT_MASQ_IPV4=m
 CONFIG_NFT_REDIR_IPV4=m
@@ -260,7 +260,9 @@ CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
 CONFIG_NETLINK_DIAG=m
+CONFIG_MPLS=y
 CONFIG_NET_MPLS_GSO=m
+CONFIG_MPLS_ROUTING=m
 # CONFIG_WIRELESS is not set
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
@@ -272,6 +274,7 @@ CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_DRBD=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_PMEM=m
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_ATA_OVER_ETH=m
 CONFIG_DUMMY_IRQ=m
@@ -302,6 +305,7 @@ CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
 CONFIG_DM_MULTIPATH=m
 CONFIG_DM_UEVENT=y
+CONFIG_DM_LOG_WRITES=m
 CONFIG_TARGET_CORE=m
 CONFIG_TCM_IBLOCK=m
 CONFIG_TCM_FILEIO=m
@@ -324,6 +328,7 @@ CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
 CONFIG_SUN3LANCE=y
 # CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_CADENCE is not set
 CONFIG_SUN3_82586=y
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
@@ -370,7 +375,6 @@ CONFIG_HID=m
 CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
-# CONFIG_HID_PLANTRONICS is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_GENERIC=m
diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig
index 73c36b7a0009..9902c5bfbdc8 100644
--- a/arch/m68k/configs/sun3x_defconfig
+++ b/arch/m68k/configs/sun3x_defconfig
@@ -170,9 +170,9 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NFT_MASQ_IPV4=m
 CONFIG_NFT_REDIR_IPV4=m
@@ -260,7 +260,9 @@ CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
 CONFIG_NETLINK_DIAG=m
+CONFIG_MPLS=y
 CONFIG_NET_MPLS_GSO=m
+CONFIG_MPLS_ROUTING=m
 # CONFIG_WIRELESS is not set
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
@@ -272,6 +274,7 @@ CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_DRBD=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_PMEM=m
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_ATA_OVER_ETH=m
 CONFIG_DUMMY_IRQ=m
@@ -302,6 +305,7 @@ CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
 CONFIG_DM_MULTIPATH=m
 CONFIG_DM_UEVENT=y
+CONFIG_DM_LOG_WRITES=m
 CONFIG_TARGET_CORE=m
 CONFIG_TCM_IBLOCK=m
 CONFIG_TCM_FILEIO=m
@@ -324,6 +328,7 @@ CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
 CONFIG_SUN3LANCE=y
 # CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
@@ -370,7 +375,6 @@ CONFIG_HID=m
 CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
-# CONFIG_HID_PLANTRONICS is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_GENERIC=m
diff --git a/arch/m68k/include/asm/cmpxchg.h b/arch/m68k/include/asm/cmpxchg.h
index bc755bc620ad..83b1df80f0ac 100644
--- a/arch/m68k/include/asm/cmpxchg.h
+++ b/arch/m68k/include/asm/cmpxchg.h
@@ -90,7 +90,6 @@ extern unsigned long __invalid_cmpxchg_size(volatile void *,
  * indicated by comparing RETURN with OLD.
  */
 #ifdef CONFIG_RMW_INSNS
-#define __HAVE_ARCH_CMPXCHG	1
 
 static inline unsigned long __cmpxchg(volatile void *p, unsigned long old,
 				      unsigned long new, int size)
diff --git a/arch/m68k/include/asm/io_mm.h b/arch/m68k/include/asm/io_mm.h
index 8955b40a5dc4..618c85d3c786 100644
--- a/arch/m68k/include/asm/io_mm.h
+++ b/arch/m68k/include/asm/io_mm.h
@@ -20,6 +20,8 @@
 
 #ifdef __KERNEL__
 
+#define ARCH_HAS_IOREMAP_WT
+
 #include <linux/compiler.h>
 #include <asm/raw_io.h>
 #include <asm/virtconvert.h>
@@ -465,7 +467,7 @@ static inline void __iomem *ioremap_nocache(unsigned long physaddr, unsigned lon
 {
 	return __ioremap(physaddr, size, IOMAP_NOCACHE_SER);
 }
-static inline void __iomem *ioremap_writethrough(unsigned long physaddr,
+static inline void __iomem *ioremap_wt(unsigned long physaddr,
 					 unsigned long size)
 {
 	return __ioremap(physaddr, size, IOMAP_WRITETHROUGH);
diff --git a/arch/m68k/include/asm/io_no.h b/arch/m68k/include/asm/io_no.h
index a93c8cde4d38..ad7bd40e6742 100644
--- a/arch/m68k/include/asm/io_no.h
+++ b/arch/m68k/include/asm/io_no.h
@@ -3,6 +3,8 @@
 
 #ifdef __KERNEL__
 
+#define ARCH_HAS_IOREMAP_WT
+
 #include <asm/virtconvert.h>
 #include <asm-generic/iomap.h>
 
@@ -153,7 +155,7 @@ static inline void *ioremap_nocache(unsigned long physaddr, unsigned long size)
 {
 	return __ioremap(physaddr, size, IOMAP_NOCACHE_SER);
 }
-static inline void *ioremap_writethrough(unsigned long physaddr, unsigned long size)
+static inline void *ioremap_wt(unsigned long physaddr, unsigned long size)
 {
 	return __ioremap(physaddr, size, IOMAP_WRITETHROUGH);
 }
diff --git a/arch/m68k/include/asm/irqflags.h b/arch/m68k/include/asm/irqflags.h
index a823cd73dc09..b5941818346f 100644
--- a/arch/m68k/include/asm/irqflags.h
+++ b/arch/m68k/include/asm/irqflags.h
@@ -2,9 +2,6 @@
 #define _M68K_IRQFLAGS_H
 
 #include <linux/types.h>
-#ifdef CONFIG_MMU
-#include <linux/preempt_mask.h>
-#endif
 #include <linux/preempt.h>
 #include <asm/thread_info.h>
 #include <asm/entry.h>
diff --git a/arch/m68k/kernel/dma.c b/arch/m68k/kernel/dma.c
index e546a5534dd4..564665f9af30 100644
--- a/arch/m68k/kernel/dma.c
+++ b/arch/m68k/kernel/dma.c
@@ -120,13 +120,16 @@ void dma_sync_single_for_device(struct device *dev, dma_addr_t handle,
 }
 EXPORT_SYMBOL(dma_sync_single_for_device);
 
-void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nents,
-			    enum dma_data_direction dir)
+void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sglist,
+			    int nents, enum dma_data_direction dir)
 {
 	int i;
+	struct scatterlist *sg;
 
-	for (i = 0; i < nents; sg++, i++)
-		dma_sync_single_for_device(dev, sg->dma_address, sg->length, dir);
+	for_each_sg(sglist, sg, nents, i) {
+		dma_sync_single_for_device(dev, sg->dma_address, sg->length,
+					   dir);
+	}
 }
 EXPORT_SYMBOL(dma_sync_sg_for_device);
 
@@ -151,14 +154,16 @@ dma_addr_t dma_map_page(struct device *dev, struct page *page,
 }
 EXPORT_SYMBOL(dma_map_page);
 
-int dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
+int dma_map_sg(struct device *dev, struct scatterlist *sglist, int nents,
 	       enum dma_data_direction dir)
 {
 	int i;
+	struct scatterlist *sg;
 
-	for (i = 0; i < nents; sg++, i++) {
+	for_each_sg(sglist, sg, nents, i) {
 		sg->dma_address = sg_phys(sg);
-		dma_sync_single_for_device(dev, sg->dma_address, sg->length, dir);
+		dma_sync_single_for_device(dev, sg->dma_address, sg->length,
+					   dir);
 	}
 	return nents;
 }
diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c
index b2f04aee46ec..6a94cdd0c830 100644
--- a/arch/m68k/mm/fault.c
+++ b/arch/m68k/mm/fault.c
@@ -10,10 +10,10 @@
 #include <linux/ptrace.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
+#include <linux/uaccess.h>
 
 #include <asm/setup.h>
 #include <asm/traps.h>
-#include <asm/uaccess.h>
 #include <asm/pgalloc.h>
 
 extern void die_if_kernel(char *, struct pt_regs *, long);
@@ -81,7 +81,7 @@ int do_page_fault(struct pt_regs *regs, unsigned long address,
 	 * If we're in an interrupt or have no user
 	 * context, we must not take the fault..
 	 */
-	if (in_atomic() || !mm)
+	if (faulthandler_disabled() || !mm)
 		goto no_context;
 
 	if (user_mode(regs))
diff --git a/arch/metag/include/asm/barrier.h b/arch/metag/include/asm/barrier.h
index d703d8e26a65..5a696e507930 100644
--- a/arch/metag/include/asm/barrier.h
+++ b/arch/metag/include/asm/barrier.h
@@ -84,7 +84,7 @@ static inline void fence(void)
 #define read_barrier_depends()		do { } while (0)
 #define smp_read_barrier_depends()	do { } while (0)
 
-#define set_mb(var, value) do { var = value; smp_mb(); } while (0)
+#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); smp_mb(); } while (0)
 
 #define smp_store_release(p, v)						\
 do {									\
diff --git a/arch/metag/include/asm/cmpxchg.h b/arch/metag/include/asm/cmpxchg.h
index b1bc1be8540f..be29e3e44321 100644
--- a/arch/metag/include/asm/cmpxchg.h
+++ b/arch/metag/include/asm/cmpxchg.h
@@ -51,8 +51,6 @@ static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
 	return old;
 }
 
-#define __HAVE_ARCH_CMPXCHG 1
-
 #define cmpxchg(ptr, o, n)						\
 	({								\
 		__typeof__(*(ptr)) _o_ = (o);				\
diff --git a/arch/metag/include/asm/io.h b/arch/metag/include/asm/io.h
index d5779b0ec573..9890f21eadbe 100644
--- a/arch/metag/include/asm/io.h
+++ b/arch/metag/include/asm/io.h
@@ -160,6 +160,9 @@ extern void __iounmap(void __iomem *addr);
 #define ioremap_wc(offset, size)                \
 	__ioremap((offset), (size), _PAGE_WR_COMBINE)
 
+#define ioremap_wt(offset, size)                \
+	__ioremap((offset), (size), 0)
+
 #define iounmap(addr)                           \
 	__iounmap(addr)
 
diff --git a/arch/metag/mm/fault.c b/arch/metag/mm/fault.c
index 2de5dc695a87..f57edca63609 100644
--- a/arch/metag/mm/fault.c
+++ b/arch/metag/mm/fault.c
@@ -105,7 +105,7 @@ int do_page_fault(struct pt_regs *regs, unsigned long address,
 
 	mm = tsk->mm;
 
-	if (in_atomic() || !mm)
+	if (faulthandler_disabled() || !mm)
 		goto no_context;
 
 	if (user_mode(regs))
diff --git a/arch/metag/mm/highmem.c b/arch/metag/mm/highmem.c
index d71f621a2c0b..807f1b1c4e65 100644
--- a/arch/metag/mm/highmem.c
+++ b/arch/metag/mm/highmem.c
@@ -43,7 +43,7 @@ void *kmap_atomic(struct page *page)
 	unsigned long vaddr;
 	int type;
 
-	/* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */
+	preempt_disable();
 	pagefault_disable();
 	if (!PageHighMem(page))
 		return page_address(page);
@@ -82,6 +82,7 @@ void __kunmap_atomic(void *kvaddr)
 	}
 
 	pagefault_enable();
+	preempt_enable();
 }
 EXPORT_SYMBOL(__kunmap_atomic);
 
@@ -95,6 +96,7 @@ void *kmap_atomic_pfn(unsigned long pfn)
 	unsigned long vaddr;
 	int type;
 
+	preempt_disable();
 	pagefault_disable();
 
 	type = kmap_atomic_idx_push();
diff --git a/arch/microblaze/include/asm/io.h b/arch/microblaze/include/asm/io.h
index 940f5fc1d1da..39b6315db82e 100644
--- a/arch/microblaze/include/asm/io.h
+++ b/arch/microblaze/include/asm/io.h
@@ -39,10 +39,10 @@ extern resource_size_t isa_mem_base;
 extern void iounmap(void __iomem *addr);
 
 extern void __iomem *ioremap(phys_addr_t address, unsigned long size);
-#define ioremap_writethrough(addr, size)	ioremap((addr), (size))
 #define ioremap_nocache(addr, size)		ioremap((addr), (size))
 #define ioremap_fullcache(addr, size)		ioremap((addr), (size))
 #define ioremap_wc(addr, size)			ioremap((addr), (size))
+#define ioremap_wt(addr, size)			ioremap((addr), (size))
 
 #endif /* CONFIG_MMU */
 
diff --git a/arch/microblaze/include/asm/pci.h b/arch/microblaze/include/asm/pci.h
index 468aca8cec0d..fdf2e75d7033 100644
--- a/arch/microblaze/include/asm/pci.h
+++ b/arch/microblaze/include/asm/pci.h
@@ -44,16 +44,6 @@ struct pci_dev;
  */
 #define pcibios_assign_all_busses()	0
 
-#ifdef CONFIG_PCI
-static inline void pci_dma_burst_advice(struct pci_dev *pdev,
-					enum pci_dma_burst_strategy *strat,
-					unsigned long *strategy_parameter)
-{
-	*strat = PCI_DMA_BURST_INFINITY;
-	*strategy_parameter = ~0UL;
-}
-#endif
-
 extern int pci_domain_nr(struct pci_bus *bus);
 
 /* Decide whether to display the domain number in /proc */
@@ -83,19 +73,6 @@ extern int pci_mmap_legacy_page_range(struct pci_bus *bus,
  */
 #define PCI_DMA_BUS_IS_PHYS     (1)
 
-static inline struct resource *pcibios_select_root(struct pci_dev *pdev,
-			struct resource *res)
-{
-	struct resource *root = NULL;
-
-	if (res->flags & IORESOURCE_IO)
-		root = &ioport_resource;
-	if (res->flags & IORESOURCE_MEM)
-		root = &iomem_resource;
-
-	return root;
-}
-
 extern void pcibios_claim_one_bus(struct pci_bus *b);
 
 extern void pcibios_finish_adding_to_bus(struct pci_bus *bus);
diff --git a/arch/microblaze/include/asm/uaccess.h b/arch/microblaze/include/asm/uaccess.h
index 62942fd12672..331b0d35f89c 100644
--- a/arch/microblaze/include/asm/uaccess.h
+++ b/arch/microblaze/include/asm/uaccess.h
@@ -178,7 +178,8 @@ extern long __user_bad(void);
  * @x:   Variable to store result.
  * @ptr: Source address, in user space.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple variable from user space to kernel
  * space.  It supports simple types like char and int, but not larger
@@ -290,7 +291,8 @@ extern long __user_bad(void);
  * @x:   Value to copy to user space.
  * @ptr: Destination address, in user space.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple value from kernel space to user
  * space.  It supports simple types like char and int, but not larger
diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c
index d46a5ebb7570..177dfc003643 100644
--- a/arch/microblaze/mm/fault.c
+++ b/arch/microblaze/mm/fault.c
@@ -107,14 +107,14 @@ void do_page_fault(struct pt_regs *regs, unsigned long address,
 	if ((error_code & 0x13) == 0x13 || (error_code & 0x11) == 0x11)
 		is_write = 0;
 
-	if (unlikely(in_atomic() || !mm)) {
+	if (unlikely(faulthandler_disabled() || !mm)) {
 		if (kernel_mode(regs))
 			goto bad_area_nosemaphore;
 
-		/* in_atomic() in user mode is really bad,
+		/* faulthandler_disabled() in user mode is really bad,
 		   as is current->mm == NULL. */
-		pr_emerg("Page fault in user mode with in_atomic(), mm = %p\n",
-									mm);
+		pr_emerg("Page fault in user mode with faulthandler_disabled(), mm = %p\n",
+			 mm);
 		pr_emerg("r15 = %lx  MSR = %lx\n",
 		       regs->r15, regs->msr);
 		die("Weird page fault", regs, SIGSEGV);
diff --git a/arch/microblaze/mm/highmem.c b/arch/microblaze/mm/highmem.c
index 5a92576fad92..2fcc5a52d84d 100644
--- a/arch/microblaze/mm/highmem.c
+++ b/arch/microblaze/mm/highmem.c
@@ -37,7 +37,7 @@ void *kmap_atomic_prot(struct page *page, pgprot_t prot)
 	unsigned long vaddr;
 	int idx, type;
 
-	/* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */
+	preempt_disable();
 	pagefault_disable();
 	if (!PageHighMem(page))
 		return page_address(page);
@@ -63,6 +63,7 @@ void __kunmap_atomic(void *kvaddr)
 
 	if (vaddr < __fix_to_virt(FIX_KMAP_END)) {
 		pagefault_enable();
+		preempt_enable();
 		return;
 	}
 
@@ -84,5 +85,6 @@ void __kunmap_atomic(void *kvaddr)
 #endif
 	kmap_atomic_idx_pop();
 	pagefault_enable();
+	preempt_enable();
 }
 EXPORT_SYMBOL(__kunmap_atomic);
diff --git a/arch/mips/cavium-octeon/crypto/octeon-md5.c b/arch/mips/cavium-octeon/crypto/octeon-md5.c
index 12dccdb38286..af4c712f7afc 100644
--- a/arch/mips/cavium-octeon/crypto/octeon-md5.c
+++ b/arch/mips/cavium-octeon/crypto/octeon-md5.c
@@ -69,10 +69,10 @@ static int octeon_md5_init(struct shash_desc *desc)
 {
 	struct md5_state *mctx = shash_desc_ctx(desc);
 
-	mctx->hash[0] = cpu_to_le32(0x67452301);
-	mctx->hash[1] = cpu_to_le32(0xefcdab89);
-	mctx->hash[2] = cpu_to_le32(0x98badcfe);
-	mctx->hash[3] = cpu_to_le32(0x10325476);
+	mctx->hash[0] = cpu_to_le32(MD5_H0);
+	mctx->hash[1] = cpu_to_le32(MD5_H1);
+	mctx->hash[2] = cpu_to_le32(MD5_H2);
+	mctx->hash[3] = cpu_to_le32(MD5_H3);
 	mctx->byte_count = 0;
 
 	return 0;
diff --git a/arch/mips/include/asm/barrier.h b/arch/mips/include/asm/barrier.h
index 2b8bbbcb9be0..7ecba84656d4 100644
--- a/arch/mips/include/asm/barrier.h
+++ b/arch/mips/include/asm/barrier.h
@@ -112,8 +112,8 @@
 #define __WEAK_LLSC_MB		"		\n"
 #endif
 
-#define set_mb(var, value) \
-	do { var = value; smp_mb(); } while (0)
+#define smp_store_mb(var, value) \
+	do { WRITE_ONCE(var, value); smp_mb(); } while (0)
 
 #define smp_llsc_mb()	__asm__ __volatile__(__WEAK_LLSC_MB : : :"memory")
 
diff --git a/arch/mips/include/asm/cmpxchg.h b/arch/mips/include/asm/cmpxchg.h
index 412f945f1f5e..b71ab4a5fd50 100644
--- a/arch/mips/include/asm/cmpxchg.h
+++ b/arch/mips/include/asm/cmpxchg.h
@@ -138,8 +138,6 @@ static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int siz
 		__xchg((unsigned long)(x), (ptr), sizeof(*(ptr))));	\
 })
 
-#define __HAVE_ARCH_CMPXCHG 1
-
 #define __cmpxchg_asm(ld, st, m, old, new)				\
 ({									\
 	__typeof(*(m)) __ret;						\
diff --git a/arch/mips/include/asm/pci.h b/arch/mips/include/asm/pci.h
index d9692993fc83..70dcc5498128 100644
--- a/arch/mips/include/asm/pci.h
+++ b/arch/mips/include/asm/pci.h
@@ -113,16 +113,6 @@ struct pci_dev;
  */
 extern unsigned int PCI_DMA_BUS_IS_PHYS;
 
-#ifdef CONFIG_PCI
-static inline void pci_dma_burst_advice(struct pci_dev *pdev,
-					enum pci_dma_burst_strategy *strat,
-					unsigned long *strategy_parameter)
-{
-	*strat = PCI_DMA_BURST_INFINITY;
-	*strategy_parameter = ~0UL;
-}
-#endif
-
 #ifdef CONFIG_PCI_DOMAINS
 #define pci_domain_nr(bus) ((struct pci_controller *)(bus)->sysdata)->index
 
diff --git a/arch/mips/include/asm/topology.h b/arch/mips/include/asm/topology.h
index 3e307ec2afba..7afda4150a59 100644
--- a/arch/mips/include/asm/topology.h
+++ b/arch/mips/include/asm/topology.h
@@ -15,7 +15,7 @@
 #define topology_physical_package_id(cpu)	(cpu_data[cpu].package)
 #define topology_core_id(cpu)			(cpu_data[cpu].core)
 #define topology_core_cpumask(cpu)		(&cpu_core_map[cpu])
-#define topology_thread_cpumask(cpu)		(&cpu_sibling_map[cpu])
+#define topology_sibling_cpumask(cpu)		(&cpu_sibling_map[cpu])
 #endif
 
 #endif /* __ASM_TOPOLOGY_H */
diff --git a/arch/mips/include/asm/uaccess.h b/arch/mips/include/asm/uaccess.h
index bf8b32450ef6..9722357d2854 100644
--- a/arch/mips/include/asm/uaccess.h
+++ b/arch/mips/include/asm/uaccess.h
@@ -103,7 +103,8 @@ extern u64 __ua_limit;
  * @addr: User space pointer to start of block to check
  * @size: Size of block to check
  *
- * Context: User context only.	This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Checks if a pointer to a block of memory in user space is valid.
  *
@@ -138,7 +139,8 @@ extern u64 __ua_limit;
  * @x:	 Value to copy to user space.
  * @ptr: Destination address, in user space.
  *
- * Context: User context only.	This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple value from kernel space to user
  * space.  It supports simple types like char and int, but not larger
@@ -157,7 +159,8 @@ extern u64 __ua_limit;
  * @x:	 Variable to store result.
  * @ptr: Source address, in user space.
  *
- * Context: User context only.	This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple variable from user space to kernel
  * space.  It supports simple types like char and int, but not larger
@@ -177,7 +180,8 @@ extern u64 __ua_limit;
  * @x:	 Value to copy to user space.
  * @ptr: Destination address, in user space.
  *
- * Context: User context only.	This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple value from kernel space to user
  * space.  It supports simple types like char and int, but not larger
@@ -199,7 +203,8 @@ extern u64 __ua_limit;
  * @x:	 Variable to store result.
  * @ptr: Source address, in user space.
  *
- * Context: User context only.	This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple variable from user space to kernel
  * space.  It supports simple types like char and int, but not larger
@@ -498,7 +503,8 @@ extern void __put_user_unknown(void);
  * @x:	 Value to copy to user space.
  * @ptr: Destination address, in user space.
  *
- * Context: User context only.	This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple value from kernel space to user
  * space.  It supports simple types like char and int, but not larger
@@ -517,7 +523,8 @@ extern void __put_user_unknown(void);
  * @x:	 Variable to store result.
  * @ptr: Source address, in user space.
  *
- * Context: User context only.	This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple variable from user space to kernel
  * space.  It supports simple types like char and int, but not larger
@@ -537,7 +544,8 @@ extern void __put_user_unknown(void);
  * @x:	 Value to copy to user space.
  * @ptr: Destination address, in user space.
  *
- * Context: User context only.	This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple value from kernel space to user
  * space.  It supports simple types like char and int, but not larger
@@ -559,7 +567,8 @@ extern void __put_user_unknown(void);
  * @x:	 Variable to store result.
  * @ptr: Source address, in user space.
  *
- * Context: User context only.	This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple variable from user space to kernel
  * space.  It supports simple types like char and int, but not larger
@@ -815,7 +824,8 @@ extern size_t __copy_user(void *__to, const void *__from, size_t __n);
  * @from: Source address, in kernel space.
  * @n:	  Number of bytes to copy.
  *
- * Context: User context only.	This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Copy data from kernel space to user space.  Caller must check
  * the specified block with access_ok() before calling this function.
@@ -888,7 +898,8 @@ extern size_t __copy_user_inatomic(void *__to, const void *__from, size_t __n);
  * @from: Source address, in kernel space.
  * @n:	  Number of bytes to copy.
  *
- * Context: User context only.	This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Copy data from kernel space to user space.
  *
@@ -1075,7 +1086,8 @@ extern size_t __copy_in_user_eva(void *__to, const void *__from, size_t __n);
  * @from: Source address, in user space.
  * @n:	  Number of bytes to copy.
  *
- * Context: User context only.	This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Copy data from user space to kernel space.  Caller must check
  * the specified block with access_ok() before calling this function.
@@ -1107,7 +1119,8 @@ extern size_t __copy_in_user_eva(void *__to, const void *__from, size_t __n);
  * @from: Source address, in user space.
  * @n:	  Number of bytes to copy.
  *
- * Context: User context only.	This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Copy data from user space to kernel space.
  *
@@ -1329,7 +1342,8 @@ strncpy_from_user(char *__to, const char __user *__from, long __len)
  * strlen_user: - Get the size of a string in user space.
  * @str: The string to measure.
  *
- * Context: User context only.	This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Get the size of a NUL-terminated string in user space.
  *
@@ -1398,7 +1412,8 @@ static inline long __strnlen_user(const char __user *s, long n)
  * strnlen_user: - Get the size of a string in user space.
  * @str: The string to measure.
  *
- * Context: User context only.	This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Get the size of a NUL-terminated string in user space.
  *
diff --git a/arch/mips/kernel/signal-common.h b/arch/mips/kernel/signal-common.h
index 06805e09bcd3..0b85f827cd18 100644
--- a/arch/mips/kernel/signal-common.h
+++ b/arch/mips/kernel/signal-common.h
@@ -28,12 +28,7 @@ extern void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs,
 extern int fpcsr_pending(unsigned int __user *fpcsr);
 
 /* Make sure we will not lose FPU ownership */
-#ifdef CONFIG_PREEMPT
-#define lock_fpu_owner()	preempt_disable()
-#define unlock_fpu_owner()	preempt_enable()
-#else
-#define lock_fpu_owner()	pagefault_disable()
-#define unlock_fpu_owner()	pagefault_enable()
-#endif
+#define lock_fpu_owner()	({ preempt_disable(); pagefault_disable(); })
+#define unlock_fpu_owner()	({ pagefault_enable(); preempt_enable(); })
 
 #endif	/* __SIGNAL_COMMON_H */
diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c
index 7ff8637e530d..36c0f26fac6b 100644
--- a/arch/mips/mm/fault.c
+++ b/arch/mips/mm/fault.c
@@ -21,10 +21,10 @@
 #include <linux/module.h>
 #include <linux/kprobes.h>
 #include <linux/perf_event.h>
+#include <linux/uaccess.h>
 
 #include <asm/branch.h>
 #include <asm/mmu_context.h>
-#include <asm/uaccess.h>
 #include <asm/ptrace.h>
 #include <asm/highmem.h>		/* For VMALLOC_END */
 #include <linux/kdebug.h>
@@ -94,7 +94,7 @@ static void __kprobes __do_page_fault(struct pt_regs *regs, unsigned long write,
 	 * If we're in an interrupt or have no user
 	 * context, we must not take the fault..
 	 */
-	if (in_atomic() || !mm)
+	if (faulthandler_disabled() || !mm)
 		goto bad_area_nosemaphore;
 
 	if (user_mode(regs))
diff --git a/arch/mips/mm/highmem.c b/arch/mips/mm/highmem.c
index da815d295239..11661cbc11a8 100644
--- a/arch/mips/mm/highmem.c
+++ b/arch/mips/mm/highmem.c
@@ -47,7 +47,7 @@ void *kmap_atomic(struct page *page)
 	unsigned long vaddr;
 	int idx, type;
 
-	/* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */
+	preempt_disable();
 	pagefault_disable();
 	if (!PageHighMem(page))
 		return page_address(page);
@@ -72,6 +72,7 @@ void __kunmap_atomic(void *kvaddr)
 
 	if (vaddr < FIXADDR_START) { // FIXME
 		pagefault_enable();
+		preempt_enable();
 		return;
 	}
 
@@ -92,6 +93,7 @@ void __kunmap_atomic(void *kvaddr)
 #endif
 	kmap_atomic_idx_pop();
 	pagefault_enable();
+	preempt_enable();
 }
 EXPORT_SYMBOL(__kunmap_atomic);
 
@@ -104,6 +106,7 @@ void *kmap_atomic_pfn(unsigned long pfn)
 	unsigned long vaddr;
 	int idx, type;
 
+	preempt_disable();
 	pagefault_disable();
 
 	type = kmap_atomic_idx_push();
diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c
index faa5c9822ecc..198a3147dd7d 100644
--- a/arch/mips/mm/init.c
+++ b/arch/mips/mm/init.c
@@ -90,6 +90,7 @@ static void *__kmap_pgprot(struct page *page, unsigned long addr, pgprot_t prot)
 
 	BUG_ON(Page_dcache_dirty(page));
 
+	preempt_disable();
 	pagefault_disable();
 	idx = (addr >> PAGE_SHIFT) & (FIX_N_COLOURS - 1);
 	idx += in_interrupt() ? FIX_N_COLOURS : 0;
@@ -152,6 +153,7 @@ void kunmap_coherent(void)
 	write_c0_entryhi(old_ctx);
 	local_irq_restore(flags);
 	pagefault_enable();
+	preempt_enable();
 }
 
 void copy_user_highpage(struct page *to, struct page *from,
diff --git a/arch/mips/pci/fixup-cobalt.c b/arch/mips/pci/fixup-cobalt.c
index a138e8ee5cfc..b3ab59318d91 100644
--- a/arch/mips/pci/fixup-cobalt.c
+++ b/arch/mips/pci/fixup-cobalt.c
@@ -13,7 +13,6 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 
-#include <asm/pci.h>
 #include <asm/io.h>
 #include <asm/gt64120.h>
 
diff --git a/arch/mips/pci/ops-mace.c b/arch/mips/pci/ops-mace.c
index 6b5821febc38..951d8070fb48 100644
--- a/arch/mips/pci/ops-mace.c
+++ b/arch/mips/pci/ops-mace.c
@@ -8,7 +8,6 @@
 #include <linux/kernel.h>
 #include <linux/pci.h>
 #include <linux/types.h>
-#include <asm/pci.h>
 #include <asm/ip32/mace.h>
 
 #if 0
diff --git a/arch/mips/pci/pci-lantiq.c b/arch/mips/pci/pci-lantiq.c
index 8b117e638306..c5347d99cf3a 100644
--- a/arch/mips/pci/pci-lantiq.c
+++ b/arch/mips/pci/pci-lantiq.c
@@ -20,7 +20,6 @@
 #include <linux/of_irq.h>
 #include <linux/of_pci.h>
 
-#include <asm/pci.h>
 #include <asm/gpio.h>
 #include <asm/addrspace.h>
 
diff --git a/arch/mn10300/include/asm/highmem.h b/arch/mn10300/include/asm/highmem.h
index 2fbbe4d920aa..1ddea5afba09 100644
--- a/arch/mn10300/include/asm/highmem.h
+++ b/arch/mn10300/include/asm/highmem.h
@@ -75,6 +75,7 @@ static inline void *kmap_atomic(struct page *page)
 	unsigned long vaddr;
 	int idx, type;
 
+	preempt_disable();
 	pagefault_disable();
 	if (page < highmem_start_page)
 		return page_address(page);
@@ -98,6 +99,7 @@ static inline void __kunmap_atomic(unsigned long vaddr)
 
 	if (vaddr < FIXADDR_START) { /* FIXME */
 		pagefault_enable();
+		preempt_enable();
 		return;
 	}
 
@@ -122,6 +124,7 @@ static inline void __kunmap_atomic(unsigned long vaddr)
 
 	kmap_atomic_idx_pop();
 	pagefault_enable();
+	preempt_enable();
 }
 #endif /* __KERNEL__ */
 
diff --git a/arch/mn10300/include/asm/io.h b/arch/mn10300/include/asm/io.h
index cc4a2ba9e228..07c5b4a3903b 100644
--- a/arch/mn10300/include/asm/io.h
+++ b/arch/mn10300/include/asm/io.h
@@ -282,6 +282,7 @@ static inline void __iomem *ioremap_nocache(unsigned long offset, unsigned long
 }
 
 #define ioremap_wc ioremap_nocache
+#define ioremap_wt ioremap_nocache
 
 static inline void iounmap(void __iomem *addr)
 {
diff --git a/arch/mn10300/include/asm/pci.h b/arch/mn10300/include/asm/pci.h
index 5f70af25c7d0..c222d1792d5b 100644
--- a/arch/mn10300/include/asm/pci.h
+++ b/arch/mn10300/include/asm/pci.h
@@ -83,19 +83,6 @@ extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
 /* implement the pci_ DMA API in terms of the generic device dma_ one */
 #include <asm-generic/pci-dma-compat.h>
 
-static inline struct resource *
-pcibios_select_root(struct pci_dev *pdev, struct resource *res)
-{
-	struct resource *root = NULL;
-
-	if (res->flags & IORESOURCE_IO)
-		root = &ioport_resource;
-	if (res->flags & IORESOURCE_MEM)
-		root = &iomem_resource;
-
-	return root;
-}
-
 static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
 {
 	return channel ? 15 : 14;
diff --git a/arch/mn10300/mm/fault.c b/arch/mn10300/mm/fault.c
index 0c2cc5d39c8e..4a1d181ed32f 100644
--- a/arch/mn10300/mm/fault.c
+++ b/arch/mn10300/mm/fault.c
@@ -23,8 +23,8 @@
 #include <linux/interrupt.h>
 #include <linux/init.h>
 #include <linux/vt_kern.h>		/* For unblank_screen() */
+#include <linux/uaccess.h>
 
-#include <asm/uaccess.h>
 #include <asm/pgalloc.h>
 #include <asm/hardirq.h>
 #include <asm/cpu-regs.h>
@@ -168,7 +168,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long fault_code,
 	 * If we're in an interrupt or have no user
 	 * context, we must not take the fault..
 	 */
-	if (in_atomic() || !mm)
+	if (faulthandler_disabled() || !mm)
 		goto no_context;
 
 	if ((fault_code & MMUFCR_xFC_ACCESS) == MMUFCR_xFC_ACCESS_USR)
diff --git a/arch/nios2/include/asm/io.h b/arch/nios2/include/asm/io.h
index 6e24d7cceb0c..c5a62da22cd2 100644
--- a/arch/nios2/include/asm/io.h
+++ b/arch/nios2/include/asm/io.h
@@ -46,6 +46,7 @@ static inline void iounmap(void __iomem *addr)
 }
 
 #define ioremap_wc ioremap_nocache
+#define ioremap_wt ioremap_nocache
 
 /* Pages to physical address... */
 #define page_to_phys(page)	virt_to_phys(page_to_virt(page))
diff --git a/arch/nios2/kernel/time.c b/arch/nios2/kernel/time.c
index 7f4547418ee1..be186a75f622 100644
--- a/arch/nios2/kernel/time.c
+++ b/arch/nios2/kernel/time.c
@@ -8,6 +8,7 @@
  * for more details.
  */
 
+#include <linux/export.h>
 #include <linux/interrupt.h>
 #include <linux/clockchips.h>
 #include <linux/clocksource.h>
@@ -106,6 +107,7 @@ cycles_t get_cycles(void)
 {
 	return nios2_timer_read(&nios2_cs.cs);
 }
+EXPORT_SYMBOL(get_cycles);
 
 static void nios2_timer_start(struct nios2_timer *timer)
 {
diff --git a/arch/nios2/mm/fault.c b/arch/nios2/mm/fault.c
index 0c9b6afe69e9..b51878b0c6b8 100644
--- a/arch/nios2/mm/fault.c
+++ b/arch/nios2/mm/fault.c
@@ -77,7 +77,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long cause,
 	 * If we're in an interrupt or have no user
 	 * context, we must not take the fault..
 	 */
-	if (in_atomic() || !mm)
+	if (faulthandler_disabled() || !mm)
 		goto bad_area_nosemaphore;
 
 	if (user_mode(regs))
diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h
index de65f66ea64e..ec2df4bab302 100644
--- a/arch/parisc/include/asm/cacheflush.h
+++ b/arch/parisc/include/asm/cacheflush.h
@@ -142,6 +142,7 @@ static inline void kunmap(struct page *page)
 
 static inline void *kmap_atomic(struct page *page)
 {
+	preempt_disable();
 	pagefault_disable();
 	return page_address(page);
 }
@@ -150,6 +151,7 @@ static inline void __kunmap_atomic(void *addr)
 {
 	flush_kernel_dcache_page_addr(addr);
 	pagefault_enable();
+	preempt_enable();
 }
 
 #define kmap_atomic_prot(page, prot)	kmap_atomic(page)
diff --git a/arch/parisc/include/asm/cmpxchg.h b/arch/parisc/include/asm/cmpxchg.h
index dbd13354ec41..0a90b965cccb 100644
--- a/arch/parisc/include/asm/cmpxchg.h
+++ b/arch/parisc/include/asm/cmpxchg.h
@@ -46,8 +46,6 @@ __xchg(unsigned long x, __volatile__ void *ptr, int size)
 #define xchg(ptr, x) \
 	((__typeof__(*(ptr)))__xchg((unsigned long)(x), (ptr), sizeof(*(ptr))))
 
-#define __HAVE_ARCH_CMPXCHG	1
-
 /* bug catcher for when unsupported size is used - won't link */
 extern void __cmpxchg_called_with_bad_pointer(void);
 
diff --git a/arch/parisc/include/asm/pci.h b/arch/parisc/include/asm/pci.h
index 20df2b04fc09..bf5e044281d6 100644
--- a/arch/parisc/include/asm/pci.h
+++ b/arch/parisc/include/asm/pci.h
@@ -196,25 +196,6 @@ static inline void pcibios_register_hba(struct pci_hba_data *x)
 /* export the pci_ DMA API in terms of the dma_ one */
 #include <asm-generic/pci-dma-compat.h>
 
-#ifdef CONFIG_PCI
-static inline void pci_dma_burst_advice(struct pci_dev *pdev,
-					enum pci_dma_burst_strategy *strat,
-					unsigned long *strategy_parameter)
-{
-	unsigned long cacheline_size;
-	u8 byte;
-
-	pci_read_config_byte(pdev, PCI_CACHE_LINE_SIZE, &byte);
-	if (byte == 0)
-		cacheline_size = 1024;
-	else
-		cacheline_size = (int) byte * 4;
-
-	*strat = PCI_DMA_BURST_MULTIPLE;
-	*strategy_parameter = cacheline_size;
-}
-#endif
-
 static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
 {
 	return channel ? 15 : 14;
diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c
index 47ee620d15d2..6548fd1d2e62 100644
--- a/arch/parisc/kernel/traps.c
+++ b/arch/parisc/kernel/traps.c
@@ -26,9 +26,9 @@
 #include <linux/console.h>
 #include <linux/bug.h>
 #include <linux/ratelimit.h>
+#include <linux/uaccess.h>
 
 #include <asm/assembly.h>
-#include <asm/uaccess.h>
 #include <asm/io.h>
 #include <asm/irq.h>
 #include <asm/traps.h>
@@ -800,7 +800,7 @@ void notrace handle_interruption(int code, struct pt_regs *regs)
 	     * unless pagefault_disable() was called before.
 	     */
 
-	    if (fault_space == 0 && !in_atomic())
+	    if (fault_space == 0 && !faulthandler_disabled())
 	    {
 		pdc_chassis_send_status(PDC_CHASSIS_DIRECT_PANIC);
 		parisc_terminate("Kernel Fault", regs, code, fault_address);
diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c
index e5120e653240..15503adddf4f 100644
--- a/arch/parisc/mm/fault.c
+++ b/arch/parisc/mm/fault.c
@@ -15,8 +15,8 @@
 #include <linux/sched.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
+#include <linux/uaccess.h>
 
-#include <asm/uaccess.h>
 #include <asm/traps.h>
 
 /* Various important other fields */
@@ -207,7 +207,7 @@ void do_page_fault(struct pt_regs *regs, unsigned long code,
 	int fault;
 	unsigned int flags;
 
-	if (in_atomic())
+	if (pagefault_disabled())
 		goto no_context;
 
 	tsk = current;
diff --git a/arch/powerpc/boot/dts/fsl/p2041si-post.dtsi b/arch/powerpc/boot/dts/fsl/p2041si-post.dtsi
index f2feacfd9a25..b6a0e88ee5ce 100644
--- a/arch/powerpc/boot/dts/fsl/p2041si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p2041si-post.dtsi
@@ -370,6 +370,7 @@
 
 /include/ "qoriq-esdhc-0.dtsi"
 	sdhc@114000 {
+		compatible = "fsl,p2041-esdhc", "fsl,esdhc";
 		fsl,iommu-parent = <&pamu1>;
 		fsl,liodn-reg = <&guts 0x530>; /* eSDHCLIODNR */
 		sdhci,auto-cmd12;
diff --git a/arch/powerpc/boot/dts/fsl/p3041si-post.dtsi b/arch/powerpc/boot/dts/fsl/p3041si-post.dtsi
index d6fea37395ad..cf18f7bf824f 100644
--- a/arch/powerpc/boot/dts/fsl/p3041si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p3041si-post.dtsi
@@ -397,6 +397,7 @@
 
 /include/ "qoriq-esdhc-0.dtsi"
 	sdhc@114000 {
+		compatible = "fsl,p3041-esdhc", "fsl,esdhc";
 		fsl,iommu-parent = <&pamu1>;
 		fsl,liodn-reg = <&guts 0x530>; /* eSDHCLIODNR */
 		sdhci,auto-cmd12;
diff --git a/arch/powerpc/boot/dts/fsl/p4080si-post.dtsi b/arch/powerpc/boot/dts/fsl/p4080si-post.dtsi
index 89482c9b2301..90431c0b53ad 100644
--- a/arch/powerpc/boot/dts/fsl/p4080si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p4080si-post.dtsi
@@ -469,6 +469,7 @@
 
 /include/ "qoriq-esdhc-0.dtsi"
 	sdhc@114000 {
+		compatible = "fsl,p4080-esdhc", "fsl,esdhc";
 		fsl,iommu-parent = <&pamu1>;
 		fsl,liodn-reg = <&guts 0x530>; /* eSDHCLIODNR */
 		voltage-ranges = <3300 3300>;
diff --git a/arch/powerpc/boot/dts/fsl/p5020si-post.dtsi b/arch/powerpc/boot/dts/fsl/p5020si-post.dtsi
index 6e04851e2fc9..8be61d11349e 100644
--- a/arch/powerpc/boot/dts/fsl/p5020si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p5020si-post.dtsi
@@ -384,6 +384,7 @@
 
 /include/ "qoriq-esdhc-0.dtsi"
 	sdhc@114000 {
+		compatible = "fsl,p5020-esdhc", "fsl,esdhc";
 		fsl,iommu-parent = <&pamu1>;
 		fsl,liodn-reg = <&guts 0x530>; /* eSDHCLIODNR */
 		sdhci,auto-cmd12;
diff --git a/arch/powerpc/boot/dts/fsl/p5040si-post.dtsi b/arch/powerpc/boot/dts/fsl/p5040si-post.dtsi
index 5e44dfa1e1a5..48e232f2d50d 100644
--- a/arch/powerpc/boot/dts/fsl/p5040si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p5040si-post.dtsi
@@ -362,6 +362,7 @@
 
 /include/ "qoriq-esdhc-0.dtsi"
 	sdhc@114000 {
+		compatible = "fsl,p5040-esdhc", "fsl,esdhc";
 		fsl,iommu-parent = <&pamu2>;
 		fsl,liodn-reg = <&guts 0x530>; /* eSDHCLIODNR */
 		sdhci,auto-cmd12;
diff --git a/arch/powerpc/crypto/md5-glue.c b/arch/powerpc/crypto/md5-glue.c
index 452fb4dc575f..92289679b4c4 100644
--- a/arch/powerpc/crypto/md5-glue.c
+++ b/arch/powerpc/crypto/md5-glue.c
@@ -37,10 +37,10 @@ static int ppc_md5_init(struct shash_desc *desc)
 {
 	struct md5_state *sctx = shash_desc_ctx(desc);
 
-	sctx->hash[0] = 0x67452301;
-	sctx->hash[1] = 0xefcdab89;
-	sctx->hash[2] = 0x98badcfe;
-	sctx->hash[3] =	0x10325476;
+	sctx->hash[0] = MD5_H0;
+	sctx->hash[1] = MD5_H1;
+	sctx->hash[2] = MD5_H2;
+	sctx->hash[3] =	MD5_H3;
 	sctx->byte_count = 0;
 
 	return 0;
diff --git a/arch/powerpc/include/asm/barrier.h b/arch/powerpc/include/asm/barrier.h
index a3bf5be111ff..51ccc7232042 100644
--- a/arch/powerpc/include/asm/barrier.h
+++ b/arch/powerpc/include/asm/barrier.h
@@ -34,7 +34,7 @@
 #define rmb()  __asm__ __volatile__ ("sync" : : : "memory")
 #define wmb()  __asm__ __volatile__ ("sync" : : : "memory")
 
-#define set_mb(var, value)	do { var = value; mb(); } while (0)
+#define smp_store_mb(var, value)	do { WRITE_ONCE(var, value); mb(); } while (0)
 
 #ifdef __SUBARCH_HAS_LWSYNC
 #    define SMPWMB      LWSYNC
@@ -89,5 +89,6 @@ do {									\
 
 #define smp_mb__before_atomic()     smp_mb()
 #define smp_mb__after_atomic()      smp_mb()
+#define smp_mb__before_spinlock()   smp_mb()
 
 #endif /* _ASM_POWERPC_BARRIER_H */
diff --git a/arch/powerpc/include/asm/cmpxchg.h b/arch/powerpc/include/asm/cmpxchg.h
index d463c68fe7f0..ad6263cffb0f 100644
--- a/arch/powerpc/include/asm/cmpxchg.h
+++ b/arch/powerpc/include/asm/cmpxchg.h
@@ -144,7 +144,6 @@ __xchg_local(volatile void *ptr, unsigned long x, unsigned int size)
  * Compare and exchange - if *p == old, set it to new,
  * and return the old value of *p.
  */
-#define __HAVE_ARCH_CMPXCHG	1
 
 static __always_inline unsigned long
 __cmpxchg_u32(volatile unsigned int *p, unsigned long old, unsigned long new)
diff --git a/arch/powerpc/include/asm/icswx.h b/arch/powerpc/include/asm/icswx.h
new file mode 100644
index 000000000000..9f8402b35115
--- /dev/null
+++ b/arch/powerpc/include/asm/icswx.h
@@ -0,0 +1,184 @@
+/*
+ * ICSWX api
+ *
+ * Copyright (C) 2015 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * This provides the Initiate Coprocessor Store Word Indexed (ICSWX)
+ * instruction.  This instruction is used to communicate with PowerPC
+ * coprocessors.  This also provides definitions of the structures used
+ * to communicate with the coprocessor.
+ *
+ * The RFC02130: Coprocessor Architecture document is the reference for
+ * everything in this file unless otherwise noted.
+ */
+#ifndef _ARCH_POWERPC_INCLUDE_ASM_ICSWX_H_
+#define _ARCH_POWERPC_INCLUDE_ASM_ICSWX_H_
+
+#include <asm/ppc-opcode.h> /* for PPC_ICSWX */
+
+/* Chapter 6.5.8 Coprocessor-Completion Block (CCB) */
+
+#define CCB_VALUE		(0x3fffffffffffffff)
+#define CCB_ADDRESS		(0xfffffffffffffff8)
+#define CCB_CM			(0x0000000000000007)
+#define CCB_CM0			(0x0000000000000004)
+#define CCB_CM12		(0x0000000000000003)
+
+#define CCB_CM0_ALL_COMPLETIONS	(0x0)
+#define CCB_CM0_LAST_IN_CHAIN	(0x4)
+#define CCB_CM12_STORE		(0x0)
+#define CCB_CM12_INTERRUPT	(0x1)
+
+#define CCB_SIZE		(0x10)
+#define CCB_ALIGN		CCB_SIZE
+
+struct coprocessor_completion_block {
+	__be64 value;
+	__be64 address;
+} __packed __aligned(CCB_ALIGN);
+
+
+/* Chapter 6.5.7 Coprocessor-Status Block (CSB) */
+
+#define CSB_V			(0x80)
+#define CSB_F			(0x04)
+#define CSB_CH			(0x03)
+#define CSB_CE_INCOMPLETE	(0x80)
+#define CSB_CE_TERMINATION	(0x40)
+#define CSB_CE_TPBC		(0x20)
+
+#define CSB_CC_SUCCESS		(0)
+#define CSB_CC_INVALID_ALIGN	(1)
+#define CSB_CC_OPERAND_OVERLAP	(2)
+#define CSB_CC_DATA_LENGTH	(3)
+#define CSB_CC_TRANSLATION	(5)
+#define CSB_CC_PROTECTION	(6)
+#define CSB_CC_RD_EXTERNAL	(7)
+#define CSB_CC_INVALID_OPERAND	(8)
+#define CSB_CC_PRIVILEGE	(9)
+#define CSB_CC_INTERNAL		(10)
+#define CSB_CC_WR_EXTERNAL	(12)
+#define CSB_CC_NOSPC		(13)
+#define CSB_CC_EXCESSIVE_DDE	(14)
+#define CSB_CC_WR_TRANSLATION	(15)
+#define CSB_CC_WR_PROTECTION	(16)
+#define CSB_CC_UNKNOWN_CODE	(17)
+#define CSB_CC_ABORT		(18)
+#define CSB_CC_TRANSPORT	(20)
+#define CSB_CC_SEGMENTED_DDL	(31)
+#define CSB_CC_PROGRESS_POINT	(32)
+#define CSB_CC_DDE_OVERFLOW	(33)
+#define CSB_CC_SESSION		(34)
+#define CSB_CC_PROVISION	(36)
+#define CSB_CC_CHAIN		(37)
+#define CSB_CC_SEQUENCE		(38)
+#define CSB_CC_HW		(39)
+
+#define CSB_SIZE		(0x10)
+#define CSB_ALIGN		CSB_SIZE
+
+struct coprocessor_status_block {
+	u8 flags;
+	u8 cs;
+	u8 cc;
+	u8 ce;
+	__be32 count;
+	__be64 address;
+} __packed __aligned(CSB_ALIGN);
+
+
+/* Chapter 6.5.10 Data-Descriptor List (DDL)
+ * each list contains one or more Data-Descriptor Entries (DDE)
+ */
+
+#define DDE_P			(0x8000)
+
+#define DDE_SIZE		(0x10)
+#define DDE_ALIGN		DDE_SIZE
+
+struct data_descriptor_entry {
+	__be16 flags;
+	u8 count;
+	u8 index;
+	__be32 length;
+	__be64 address;
+} __packed __aligned(DDE_ALIGN);
+
+
+/* Chapter 6.5.2 Coprocessor-Request Block (CRB) */
+
+#define CRB_SIZE		(0x80)
+#define CRB_ALIGN		(0x100) /* Errata: requires 256 alignment */
+
+/* Coprocessor Status Block field
+ *   ADDRESS	address of CSB
+ *   C		CCB is valid
+ *   AT		0 = addrs are virtual, 1 = addrs are phys
+ *   M		enable perf monitor
+ */
+#define CRB_CSB_ADDRESS		(0xfffffffffffffff0)
+#define CRB_CSB_C		(0x0000000000000008)
+#define CRB_CSB_AT		(0x0000000000000002)
+#define CRB_CSB_M		(0x0000000000000001)
+
+struct coprocessor_request_block {
+	__be32 ccw;
+	__be32 flags;
+	__be64 csb_addr;
+
+	struct data_descriptor_entry source;
+	struct data_descriptor_entry target;
+
+	struct coprocessor_completion_block ccb;
+
+	u8 reserved[48];
+
+	struct coprocessor_status_block csb;
+} __packed __aligned(CRB_ALIGN);
+
+
+/* RFC02167 Initiate Coprocessor Instructions document
+ * Chapter 8.2.1.1.1 RS
+ * Chapter 8.2.3 Coprocessor Directive
+ * Chapter 8.2.4 Execution
+ *
+ * The CCW must be converted to BE before passing to icswx()
+ */
+
+#define CCW_PS			(0xff000000)
+#define CCW_CT			(0x00ff0000)
+#define CCW_CD			(0x0000ffff)
+#define CCW_CL			(0x0000c000)
+
+
+/* RFC02167 Initiate Coprocessor Instructions document
+ * Chapter 8.2.1 Initiate Coprocessor Store Word Indexed (ICSWX)
+ * Chapter 8.2.4.1 Condition Register 0
+ */
+
+#define ICSWX_INITIATED		(0x8)
+#define ICSWX_BUSY		(0x4)
+#define ICSWX_REJECTED		(0x2)
+
+static inline int icswx(__be32 ccw, struct coprocessor_request_block *crb)
+{
+	__be64 ccw_reg = ccw;
+	u32 cr;
+
+	__asm__ __volatile__(
+	PPC_ICSWX(%1,0,%2) "\n"
+	"mfcr %0\n"
+	: "=r" (cr)
+	: "r" (ccw_reg), "r" (crb)
+	: "cr0", "memory");
+
+	return (int)((cr >> 28) & 0xf);
+}
+
+
+#endif /* _ARCH_POWERPC_INCLUDE_ASM_ICSWX_H_ */
diff --git a/arch/powerpc/include/asm/pci.h b/arch/powerpc/include/asm/pci.h
index 4aef8d660999..99dc432b256a 100644
--- a/arch/powerpc/include/asm/pci.h
+++ b/arch/powerpc/include/asm/pci.h
@@ -71,36 +71,6 @@ extern struct dma_map_ops *get_pci_dma_ops(void);
  */
 #define PCI_DISABLE_MWI
 
-#ifdef CONFIG_PCI
-static inline void pci_dma_burst_advice(struct pci_dev *pdev,
-					enum pci_dma_burst_strategy *strat,
-					unsigned long *strategy_parameter)
-{
-	unsigned long cacheline_size;
-	u8 byte;
-
-	pci_read_config_byte(pdev, PCI_CACHE_LINE_SIZE, &byte);
-	if (byte == 0)
-		cacheline_size = 1024;
-	else
-		cacheline_size = (int) byte * 4;
-
-	*strat = PCI_DMA_BURST_MULTIPLE;
-	*strategy_parameter = cacheline_size;
-}
-#endif
-
-#else /* 32-bit */
-
-#ifdef CONFIG_PCI
-static inline void pci_dma_burst_advice(struct pci_dev *pdev,
-					enum pci_dma_burst_strategy *strat,
-					unsigned long *strategy_parameter)
-{
-	*strat = PCI_DMA_BURST_INFINITY;
-	*strategy_parameter = ~0UL;
-}
-#endif
 #endif /* CONFIG_PPC64 */
 
 extern int pci_domain_nr(struct pci_bus *bus);
diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index 5c93f691b495..8452335661a5 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -136,6 +136,8 @@
 #define PPC_INST_DCBAL			0x7c2005ec
 #define PPC_INST_DCBZL			0x7c2007ec
 #define PPC_INST_ICBT			0x7c00002c
+#define PPC_INST_ICSWX			0x7c00032d
+#define PPC_INST_ICSWEPX		0x7c00076d
 #define PPC_INST_ISEL			0x7c00001e
 #define PPC_INST_ISEL_MASK		0xfc00003e
 #define PPC_INST_LDARX			0x7c0000a8
@@ -403,4 +405,15 @@
 #define MFTMR(tmr, r)		stringify_in_c(.long PPC_INST_MFTMR | \
 					       TMRN(tmr) | ___PPC_RT(r))
 
+/* Coprocessor instructions */
+#define PPC_ICSWX(s, a, b)	stringify_in_c(.long PPC_INST_ICSWX |	\
+					       ___PPC_RS(s) |		\
+					       ___PPC_RA(a) |		\
+					       ___PPC_RB(b))
+#define PPC_ICSWEPX(s, a, b)	stringify_in_c(.long PPC_INST_ICSWEPX | \
+					       ___PPC_RS(s) |		\
+					       ___PPC_RA(a) |		\
+					       ___PPC_RB(b))
+
+
 #endif /* _ASM_POWERPC_PPC_OPCODE_H */
diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index 5f1048eaa5b6..8b3b46b7b0f2 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -87,7 +87,7 @@ static inline int prrn_is_enabled(void)
 #include <asm/smp.h>
 
 #define topology_physical_package_id(cpu)	(cpu_to_chip_id(cpu))
-#define topology_thread_cpumask(cpu)	(per_cpu(cpu_sibling_map, cpu))
+#define topology_sibling_cpumask(cpu)	(per_cpu(cpu_sibling_map, cpu))
 #define topology_core_cpumask(cpu)	(per_cpu(cpu_core_map, cpu))
 #define topology_core_id(cpu)		(cpu_to_core_id(cpu))
 #endif
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 308c5e15676b..50a508714f87 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -46,7 +46,6 @@
 #include <asm/mmu.h>
 #include <asm/paca.h>
 #include <asm/pgtable.h>
-#include <asm/pci.h>
 #include <asm/iommu.h>
 #include <asm/btext.h>
 #include <asm/sections.h>
@@ -800,6 +799,7 @@ int of_get_ibm_chip_id(struct device_node *np)
 	}
 	return -1;
 }
+EXPORT_SYMBOL(of_get_ibm_chip_id);
 
 /**
  * cpu_to_chip_id - Return the cpus chip-id
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index fd1fe4c37599..fcca8077e6a2 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -37,7 +37,6 @@
 #include <asm/smp.h>
 #include <asm/mmu.h>
 #include <asm/pgtable.h>
-#include <asm/pci.h>
 #include <asm/iommu.h>
 #include <asm/btext.h>
 #include <asm/sections.h>
diff --git a/arch/powerpc/lib/vmx-helper.c b/arch/powerpc/lib/vmx-helper.c
index 3cf529ceec5b..ac93a3bd2730 100644
--- a/arch/powerpc/lib/vmx-helper.c
+++ b/arch/powerpc/lib/vmx-helper.c
@@ -27,11 +27,11 @@ int enter_vmx_usercopy(void)
 	if (in_interrupt())
 		return 0;
 
-	/* This acts as preempt_disable() as well and will make
-	 * enable_kernel_altivec(). We need to disable page faults
-	 * as they can call schedule and thus make us lose the VMX
-	 * context. So on page faults, we just fail which will cause
-	 * a fallback to the normal non-vmx copy.
+	preempt_disable();
+	/*
+	 * We need to disable page faults as they can call schedule and
+	 * thus make us lose the VMX context. So on page faults, we just
+	 * fail which will cause a fallback to the normal non-vmx copy.
 	 */
 	pagefault_disable();
 
@@ -47,6 +47,7 @@ int enter_vmx_usercopy(void)
 int exit_vmx_usercopy(void)
 {
 	pagefault_enable();
+	preempt_enable();
 	return 0;
 }
 
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index b396868d2aa7..6d535973b200 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -33,13 +33,13 @@
 #include <linux/ratelimit.h>
 #include <linux/context_tracking.h>
 #include <linux/hugetlb.h>
+#include <linux/uaccess.h>
 
 #include <asm/firmware.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/mmu.h>
 #include <asm/mmu_context.h>
-#include <asm/uaccess.h>
 #include <asm/tlbflush.h>
 #include <asm/siginfo.h>
 #include <asm/debug.h>
@@ -272,15 +272,16 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
 	if (!arch_irq_disabled_regs(regs))
 		local_irq_enable();
 
-	if (in_atomic() || mm == NULL) {
+	if (faulthandler_disabled() || mm == NULL) {
 		if (!user_mode(regs)) {
 			rc = SIGSEGV;
 			goto bail;
 		}
-		/* in_atomic() in user mode is really bad,
+		/* faulthandler_disabled() in user mode is really bad,
 		   as is current->mm == NULL. */
 		printk(KERN_EMERG "Page fault in user mode with "
-		       "in_atomic() = %d mm = %p\n", in_atomic(), mm);
+		       "faulthandler_disabled() = %d mm = %p\n",
+		       faulthandler_disabled(), mm);
 		printk(KERN_EMERG "NIP = %lx  MSR = %lx\n",
 		       regs->nip, regs->msr);
 		die("Weird page fault", regs, SIGSEGV);
diff --git a/arch/powerpc/mm/highmem.c b/arch/powerpc/mm/highmem.c
index e7450bdbe83a..e292c8a60952 100644
--- a/arch/powerpc/mm/highmem.c
+++ b/arch/powerpc/mm/highmem.c
@@ -34,7 +34,7 @@ void *kmap_atomic_prot(struct page *page, pgprot_t prot)
 	unsigned long vaddr;
 	int idx, type;
 
-	/* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */
+	preempt_disable();
 	pagefault_disable();
 	if (!PageHighMem(page))
 		return page_address(page);
@@ -59,6 +59,7 @@ void __kunmap_atomic(void *kvaddr)
 
 	if (vaddr < __fix_to_virt(FIX_KMAP_END)) {
 		pagefault_enable();
+		preempt_enable();
 		return;
 	}
 
@@ -82,5 +83,6 @@ void __kunmap_atomic(void *kvaddr)
 
 	kmap_atomic_idx_pop();
 	pagefault_enable();
+	preempt_enable();
 }
 EXPORT_SYMBOL(__kunmap_atomic);
diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c
index cbd3d069897f..723a099f6be3 100644
--- a/arch/powerpc/mm/tlb_nohash.c
+++ b/arch/powerpc/mm/tlb_nohash.c
@@ -217,7 +217,7 @@ static DEFINE_RAW_SPINLOCK(tlbivax_lock);
 static int mm_is_core_local(struct mm_struct *mm)
 {
 	return cpumask_subset(mm_cpumask(mm),
-			      topology_thread_cpumask(smp_processor_id()));
+			      topology_sibling_cpumask(smp_processor_id()));
 }
 
 struct tlb_flush_param {
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_pci.c b/arch/powerpc/platforms/52xx/mpc52xx_pci.c
index e2d401ad8fbb..6eb3b2abae90 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_pci.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_pci.c
@@ -12,7 +12,7 @@
 
 #undef DEBUG
 
-#include <asm/pci.h>
+#include <linux/pci.h>
 #include <asm/mpc52xx.h>
 #include <asm/delay.h>
 #include <asm/machdep.h>
diff --git a/arch/s390/include/asm/barrier.h b/arch/s390/include/asm/barrier.h
index 8d724718ec21..e6f8615a11eb 100644
--- a/arch/s390/include/asm/barrier.h
+++ b/arch/s390/include/asm/barrier.h
@@ -36,7 +36,7 @@
 #define smp_mb__before_atomic()		smp_mb()
 #define smp_mb__after_atomic()		smp_mb()
 
-#define set_mb(var, value)		do { var = value; mb(); } while (0)
+#define smp_store_mb(var, value)		do { WRITE_ONCE(var, value); mb(); } while (0)
 
 #define smp_store_release(p, v)						\
 do {									\
diff --git a/arch/s390/include/asm/cmpxchg.h b/arch/s390/include/asm/cmpxchg.h
index 4eadec466b8c..411464f4c97a 100644
--- a/arch/s390/include/asm/cmpxchg.h
+++ b/arch/s390/include/asm/cmpxchg.h
@@ -32,8 +32,6 @@
 	__old;								\
 })
 
-#define __HAVE_ARCH_CMPXCHG
-
 #define __cmpxchg_double_op(p1, p2, o1, o2, n1, n2, insn)		\
 ({									\
 	register __typeof__(*(p1)) __old1 asm("2") = (o1);		\
diff --git a/arch/s390/include/asm/io.h b/arch/s390/include/asm/io.h
index 30fd5c84680e..cb5fdf3a78fc 100644
--- a/arch/s390/include/asm/io.h
+++ b/arch/s390/include/asm/io.h
@@ -29,6 +29,7 @@ void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr);
 
 #define ioremap_nocache(addr, size)	ioremap(addr, size)
 #define ioremap_wc			ioremap_nocache
+#define ioremap_wt			ioremap_nocache
 
 static inline void __iomem *ioremap(unsigned long offset, unsigned long size)
 {
diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h
index 98eb2a579223..dcb6312a0b91 100644
--- a/arch/s390/include/asm/timex.h
+++ b/arch/s390/include/asm/timex.h
@@ -10,6 +10,7 @@
 #define _ASM_S390_TIMEX_H
 
 #include <asm/lowcore.h>
+#include <linux/time64.h>
 
 /* The value of the TOD clock for 1.1.1970. */
 #define TOD_UNIX_EPOCH 0x7d91048bca000000ULL
@@ -108,10 +109,10 @@ int get_sync_clock(unsigned long long *clock);
 void init_cpu_timer(void);
 unsigned long long monotonic_clock(void);
 
-void tod_to_timeval(__u64, struct timespec *);
+void tod_to_timeval(__u64 todval, struct timespec64 *xt);
 
 static inline
-void stck_to_timespec(unsigned long long stck, struct timespec *ts)
+void stck_to_timespec64(unsigned long long stck, struct timespec64 *ts)
 {
 	tod_to_timeval(stck - TOD_UNIX_EPOCH, ts);
 }
diff --git a/arch/s390/include/asm/topology.h b/arch/s390/include/asm/topology.h
index b1453a2ae1ca..4990f6c66288 100644
--- a/arch/s390/include/asm/topology.h
+++ b/arch/s390/include/asm/topology.h
@@ -22,7 +22,8 @@ DECLARE_PER_CPU(struct cpu_topology_s390, cpu_topology);
 
 #define topology_physical_package_id(cpu) (per_cpu(cpu_topology, cpu).socket_id)
 #define topology_thread_id(cpu)		  (per_cpu(cpu_topology, cpu).thread_id)
-#define topology_thread_cpumask(cpu)	  (&per_cpu(cpu_topology, cpu).thread_mask)
+#define topology_sibling_cpumask(cpu) \
+		(&per_cpu(cpu_topology, cpu).thread_mask)
 #define topology_core_id(cpu)		  (per_cpu(cpu_topology, cpu).core_id)
 #define topology_core_cpumask(cpu)	  (&per_cpu(cpu_topology, cpu).core_mask)
 #define topology_book_id(cpu)		  (per_cpu(cpu_topology, cpu).book_id)
diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h
index d64a7a62164f..9dd4cc47ddc7 100644
--- a/arch/s390/include/asm/uaccess.h
+++ b/arch/s390/include/asm/uaccess.h
@@ -98,7 +98,8 @@ static inline unsigned long extable_fixup(const struct exception_table_entry *x)
  * @from: Source address, in user space.
  * @n:	  Number of bytes to copy.
  *
- * Context: User context only.	This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Copy data from user space to kernel space.  Caller must check
  * the specified block with access_ok() before calling this function.
@@ -118,7 +119,8 @@ unsigned long __must_check __copy_from_user(void *to, const void __user *from,
  * @from: Source address, in kernel space.
  * @n:	  Number of bytes to copy.
  *
- * Context: User context only.	This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Copy data from kernel space to user space.  Caller must check
  * the specified block with access_ok() before calling this function.
@@ -264,7 +266,8 @@ int __get_user_bad(void) __attribute__((noreturn));
  * @from: Source address, in kernel space.
  * @n:    Number of bytes to copy.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Copy data from kernel space to user space.
  *
@@ -290,7 +293,8 @@ __compiletime_warning("copy_from_user() buffer size is not provably correct")
  * @from: Source address, in user space.
  * @n:    Number of bytes to copy.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Copy data from user space to kernel space.
  *
@@ -348,7 +352,8 @@ static inline unsigned long strnlen_user(const char __user *src, unsigned long n
  * strlen_user: - Get the size of a string in user space.
  * @str: The string to measure.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Get the size of a NUL-terminated string in user space.
  *
diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c
index c1f21aca76e7..6fca0e46464e 100644
--- a/arch/s390/kernel/debug.c
+++ b/arch/s390/kernel/debug.c
@@ -1457,23 +1457,24 @@ int
 debug_dflt_header_fn(debug_info_t * id, struct debug_view *view,
 			 int area, debug_entry_t * entry, char *out_buf)
 {
-	struct timespec time_spec;
+	struct timespec64 time_spec;
 	char *except_str;
 	unsigned long caller;
 	int rc = 0;
 	unsigned int level;
 
 	level = entry->id.fields.level;
-	stck_to_timespec(entry->id.stck, &time_spec);
+	stck_to_timespec64(entry->id.stck, &time_spec);
 
 	if (entry->id.fields.exception)
 		except_str = "*";
 	else
 		except_str = "-";
 	caller = ((unsigned long) entry->caller) & PSW_ADDR_INSN;
-	rc += sprintf(out_buf, "%02i %011lu:%06lu %1u %1s %02i %p  ",
-		      area, time_spec.tv_sec, time_spec.tv_nsec / 1000, level,
-		      except_str, entry->id.fields.cpuid, (void *) caller);
+	rc += sprintf(out_buf, "%02i %011lld:%06lu %1u %1s %02i %p  ",
+		      area, (long long)time_spec.tv_sec,
+		      time_spec.tv_nsec / 1000, level, except_str,
+		      entry->id.fields.cpuid, (void *)caller);
 	return rc;
 }
 EXPORT_SYMBOL(debug_dflt_header_fn);
diff --git a/arch/s390/kernel/suspend.c b/arch/s390/kernel/suspend.c
index d3236c9e226b..39e2f41b6cf0 100644
--- a/arch/s390/kernel/suspend.c
+++ b/arch/s390/kernel/suspend.c
@@ -9,10 +9,10 @@
 #include <linux/pfn.h>
 #include <linux/suspend.h>
 #include <linux/mm.h>
+#include <linux/pci.h>
 #include <asm/ctl_reg.h>
 #include <asm/ipl.h>
 #include <asm/cio.h>
-#include <asm/pci.h>
 #include <asm/sections.h>
 #include "entry.h"
 
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index 170ddd2018b3..9e733d965e08 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -76,7 +76,7 @@ unsigned long long monotonic_clock(void)
 }
 EXPORT_SYMBOL(monotonic_clock);
 
-void tod_to_timeval(__u64 todval, struct timespec *xt)
+void tod_to_timeval(__u64 todval, struct timespec64 *xt)
 {
 	unsigned long long sec;
 
@@ -181,12 +181,12 @@ static void timing_alert_interrupt(struct ext_code ext_code,
 static void etr_reset(void);
 static void stp_reset(void);
 
-void read_persistent_clock(struct timespec *ts)
+void read_persistent_clock64(struct timespec64 *ts)
 {
 	tod_to_timeval(get_tod_clock() - TOD_UNIX_EPOCH, ts);
 }
 
-void read_boot_clock(struct timespec *ts)
+void read_boot_clock64(struct timespec64 *ts)
 {
 	tod_to_timeval(sched_clock_base_cc - TOD_UNIX_EPOCH, ts);
 }
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 76515bcea2f1..4c8f5d7f9c23 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -399,7 +399,7 @@ static inline int do_exception(struct pt_regs *regs, int access)
 	 * user context.
 	 */
 	fault = VM_FAULT_BADCONTEXT;
-	if (unlikely(!user_space_fault(regs) || in_atomic() || !mm))
+	if (unlikely(!user_space_fault(regs) || faulthandler_disabled() || !mm))
 		goto out;
 
 	address = trans_exc_code & __FAIL_ADDR_MASK;
diff --git a/arch/score/include/asm/cmpxchg.h b/arch/score/include/asm/cmpxchg.h
index f384839c3ee5..cc3f6420b71c 100644
--- a/arch/score/include/asm/cmpxchg.h
+++ b/arch/score/include/asm/cmpxchg.h
@@ -42,8 +42,6 @@ static inline unsigned long __cmpxchg(volatile unsigned long *m,
 					(unsigned long)(o),	\
 					(unsigned long)(n)))
 
-#define __HAVE_ARCH_CMPXCHG	1
-
 #include <asm-generic/cmpxchg-local.h>
 
 #endif /* _ASM_SCORE_CMPXCHG_H */
diff --git a/arch/score/include/asm/uaccess.h b/arch/score/include/asm/uaccess.h
index ab66ddde777b..20a3591225cc 100644
--- a/arch/score/include/asm/uaccess.h
+++ b/arch/score/include/asm/uaccess.h
@@ -36,7 +36,8 @@
  * @addr: User space pointer to start of block to check
  * @size: Size of block to check
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Checks if a pointer to a block of memory in user space is valid.
  *
@@ -61,7 +62,8 @@
  * @x:   Value to copy to user space.
  * @ptr: Destination address, in user space.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple value from kernel space to user
  * space.  It supports simple types like char and int, but not larger
@@ -79,7 +81,8 @@
  * @x:   Variable to store result.
  * @ptr: Source address, in user space.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple variable from user space to kernel
  * space.  It supports simple types like char and int, but not larger
@@ -98,7 +101,8 @@
  * @x:   Value to copy to user space.
  * @ptr: Destination address, in user space.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple value from kernel space to user
  * space.  It supports simple types like char and int, but not larger
@@ -119,7 +123,8 @@
  * @x:   Variable to store result.
  * @ptr: Source address, in user space.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple variable from user space to kernel
  * space.  It supports simple types like char and int, but not larger
diff --git a/arch/score/mm/fault.c b/arch/score/mm/fault.c
index 6860beb2a280..37a6c2e0e969 100644
--- a/arch/score/mm/fault.c
+++ b/arch/score/mm/fault.c
@@ -34,6 +34,7 @@
 #include <linux/string.h>
 #include <linux/types.h>
 #include <linux/ptrace.h>
+#include <linux/uaccess.h>
 
 /*
  * This routine handles page faults.  It determines the address,
@@ -73,7 +74,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long write,
 	* If we're in an interrupt or have no user
 	* context, we must not take the fault..
 	*/
-	if (in_atomic() || !mm)
+	if (pagefault_disabled() || !mm)
 		goto bad_area_nosemaphore;
 
 	if (user_mode(regs))
diff --git a/arch/sh/drivers/pci/ops-sh5.c b/arch/sh/drivers/pci/ops-sh5.c
index 4ce95a001b80..45361946460f 100644
--- a/arch/sh/drivers/pci/ops-sh5.c
+++ b/arch/sh/drivers/pci/ops-sh5.c
@@ -18,7 +18,6 @@
 #include <linux/delay.h>
 #include <linux/types.h>
 #include <linux/irq.h>
-#include <asm/pci.h>
 #include <asm/io.h>
 #include "pci-sh5.h"
 
diff --git a/arch/sh/drivers/pci/pci-sh5.c b/arch/sh/drivers/pci/pci-sh5.c
index 16c1e721bf54..8229114c6a58 100644
--- a/arch/sh/drivers/pci/pci-sh5.c
+++ b/arch/sh/drivers/pci/pci-sh5.c
@@ -20,7 +20,6 @@
 #include <linux/types.h>
 #include <linux/irq.h>
 #include <cpu/irq.h>
-#include <asm/pci.h>
 #include <asm/io.h>
 #include "pci-sh5.h"
 
diff --git a/arch/sh/include/asm/barrier.h b/arch/sh/include/asm/barrier.h
index 43715308b068..bf91037db4e0 100644
--- a/arch/sh/include/asm/barrier.h
+++ b/arch/sh/include/asm/barrier.h
@@ -32,7 +32,7 @@
 #define ctrl_barrier()	__asm__ __volatile__ ("nop;nop;nop;nop;nop;nop;nop;nop")
 #endif
 
-#define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
+#define smp_store_mb(var, value) do { (void)xchg(&var, value); } while (0)
 
 #include <asm-generic/barrier.h>
 
diff --git a/arch/sh/include/asm/cmpxchg.h b/arch/sh/include/asm/cmpxchg.h
index f6bd1406b897..85c97b188d71 100644
--- a/arch/sh/include/asm/cmpxchg.h
+++ b/arch/sh/include/asm/cmpxchg.h
@@ -46,8 +46,6 @@ extern void __xchg_called_with_bad_pointer(void);
  * if something tries to do an invalid cmpxchg(). */
 extern void __cmpxchg_called_with_bad_pointer(void);
 
-#define __HAVE_ARCH_CMPXCHG 1
-
 static inline unsigned long __cmpxchg(volatile void * ptr, unsigned long old,
 		unsigned long new, int size)
 {
diff --git a/arch/sh/include/asm/pci.h b/arch/sh/include/asm/pci.h
index 5b4511552998..e343dbd02e41 100644
--- a/arch/sh/include/asm/pci.h
+++ b/arch/sh/include/asm/pci.h
@@ -86,24 +86,6 @@ extern void pcibios_set_master(struct pci_dev *dev);
  * direct memory write.
  */
 #define PCI_DISABLE_MWI
-
-static inline void pci_dma_burst_advice(struct pci_dev *pdev,
-					enum pci_dma_burst_strategy *strat,
-					unsigned long *strategy_parameter)
-{
-	unsigned long cacheline_size;
-	u8 byte;
-
-	pci_read_config_byte(pdev, PCI_CACHE_LINE_SIZE, &byte);
-
-	if (byte == 0)
-		cacheline_size = L1_CACHE_BYTES;
-	else
-		cacheline_size = byte << 2;
-
-	*strat = PCI_DMA_BURST_MULTIPLE;
-	*strategy_parameter = cacheline_size;
-}
 #endif
 
 /* Board-specific fixup routines. */
diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c
index a58fec9b55e0..79d8276377d1 100644
--- a/arch/sh/mm/fault.c
+++ b/arch/sh/mm/fault.c
@@ -17,6 +17,7 @@
 #include <linux/kprobes.h>
 #include <linux/perf_event.h>
 #include <linux/kdebug.h>
+#include <linux/uaccess.h>
 #include <asm/io_trapped.h>
 #include <asm/mmu_context.h>
 #include <asm/tlbflush.h>
@@ -438,9 +439,9 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
 
 	/*
 	 * If we're in an interrupt, have no user context or are running
-	 * in an atomic region then we must not take the fault:
+	 * with pagefaults disabled then we must not take the fault:
 	 */
-	if (unlikely(in_atomic() || !mm)) {
+	if (unlikely(faulthandler_disabled() || !mm)) {
 		bad_area_nosemaphore(regs, error_code, address);
 		return;
 	}
diff --git a/arch/sparc/crypto/md5_glue.c b/arch/sparc/crypto/md5_glue.c
index b688731d7ede..c9d2b922734b 100644
--- a/arch/sparc/crypto/md5_glue.c
+++ b/arch/sparc/crypto/md5_glue.c
@@ -33,10 +33,10 @@ static int md5_sparc64_init(struct shash_desc *desc)
 {
 	struct md5_state *mctx = shash_desc_ctx(desc);
 
-	mctx->hash[0] = cpu_to_le32(0x67452301);
-	mctx->hash[1] = cpu_to_le32(0xefcdab89);
-	mctx->hash[2] = cpu_to_le32(0x98badcfe);
-	mctx->hash[3] = cpu_to_le32(0x10325476);
+	mctx->hash[0] = cpu_to_le32(MD5_H0);
+	mctx->hash[1] = cpu_to_le32(MD5_H1);
+	mctx->hash[2] = cpu_to_le32(MD5_H2);
+	mctx->hash[3] = cpu_to_le32(MD5_H3);
 	mctx->byte_count = 0;
 
 	return 0;
diff --git a/arch/sparc/include/asm/barrier_64.h b/arch/sparc/include/asm/barrier_64.h
index 76648941fea7..809941e33e12 100644
--- a/arch/sparc/include/asm/barrier_64.h
+++ b/arch/sparc/include/asm/barrier_64.h
@@ -40,8 +40,8 @@ do {	__asm__ __volatile__("ba,pt	%%xcc, 1f\n\t" \
 #define dma_rmb()	rmb()
 #define dma_wmb()	wmb()
 
-#define set_mb(__var, __value) \
-	do { __var = __value; membar_safe("#StoreLoad"); } while(0)
+#define smp_store_mb(__var, __value) \
+	do { WRITE_ONCE(__var, __value); membar_safe("#StoreLoad"); } while(0)
 
 #ifdef CONFIG_SMP
 #define smp_mb()	mb()
diff --git a/arch/sparc/include/asm/cmpxchg_32.h b/arch/sparc/include/asm/cmpxchg_32.h
index d38b52dca216..83ffb83c5397 100644
--- a/arch/sparc/include/asm/cmpxchg_32.h
+++ b/arch/sparc/include/asm/cmpxchg_32.h
@@ -34,7 +34,6 @@ static inline unsigned long __xchg(unsigned long x, __volatile__ void * ptr, int
  *
  * Cribbed from <asm-parisc/atomic.h>
  */
-#define __HAVE_ARCH_CMPXCHG	1
 
 /* bug catcher for when unsupported size is used - won't link */
 void __cmpxchg_called_with_bad_pointer(void);
diff --git a/arch/sparc/include/asm/cmpxchg_64.h b/arch/sparc/include/asm/cmpxchg_64.h
index 0e1ed6cfbf68..faa2f61058c2 100644
--- a/arch/sparc/include/asm/cmpxchg_64.h
+++ b/arch/sparc/include/asm/cmpxchg_64.h
@@ -65,8 +65,6 @@ static inline unsigned long __xchg(unsigned long x, __volatile__ void * ptr,
 
 #include <asm-generic/cmpxchg-local.h>
 
-#define __HAVE_ARCH_CMPXCHG 1
-
 static inline unsigned long
 __cmpxchg_u32(volatile int *m, int old, int new)
 {
diff --git a/arch/sparc/include/asm/io_32.h b/arch/sparc/include/asm/io_32.h
index 407ac14295f4..57f26c398dc9 100644
--- a/arch/sparc/include/asm/io_32.h
+++ b/arch/sparc/include/asm/io_32.h
@@ -129,6 +129,7 @@ static inline void sbus_memcpy_toio(volatile void __iomem *dst,
 void __iomem *ioremap(unsigned long offset, unsigned long size);
 #define ioremap_nocache(X,Y)	ioremap((X),(Y))
 #define ioremap_wc(X,Y)		ioremap((X),(Y))
+#define ioremap_wt(X,Y)		ioremap((X),(Y))
 void iounmap(volatile void __iomem *addr);
 
 /* Create a virtual mapping cookie for an IO port range */
diff --git a/arch/sparc/include/asm/io_64.h b/arch/sparc/include/asm/io_64.h
index 50d4840d9aeb..c32fa3f752c8 100644
--- a/arch/sparc/include/asm/io_64.h
+++ b/arch/sparc/include/asm/io_64.h
@@ -402,6 +402,7 @@ static inline void __iomem *ioremap(unsigned long offset, unsigned long size)
 
 #define ioremap_nocache(X,Y)		ioremap((X),(Y))
 #define ioremap_wc(X,Y)			ioremap((X),(Y))
+#define ioremap_wt(X,Y)			ioremap((X),(Y))
 
 static inline void iounmap(volatile void __iomem *addr)
 {
diff --git a/arch/sparc/include/asm/pci_32.h b/arch/sparc/include/asm/pci_32.h
index 53e9b4987db0..b7c092df3134 100644
--- a/arch/sparc/include/asm/pci_32.h
+++ b/arch/sparc/include/asm/pci_32.h
@@ -22,16 +22,6 @@
 
 struct pci_dev;
 
-#ifdef CONFIG_PCI
-static inline void pci_dma_burst_advice(struct pci_dev *pdev,
-					enum pci_dma_burst_strategy *strat,
-					unsigned long *strategy_parameter)
-{
-	*strat = PCI_DMA_BURST_INFINITY;
-	*strategy_parameter = ~0UL;
-}
-#endif
-
 #endif /* __KERNEL__ */
 
 #ifndef CONFIG_LEON_PCI
diff --git a/arch/sparc/include/asm/pci_64.h b/arch/sparc/include/asm/pci_64.h
index bd00a6226169..022d16008a00 100644
--- a/arch/sparc/include/asm/pci_64.h
+++ b/arch/sparc/include/asm/pci_64.h
@@ -31,25 +31,6 @@
 #define PCI64_REQUIRED_MASK	(~(u64)0)
 #define PCI64_ADDR_BASE		0xfffc000000000000UL
 
-#ifdef CONFIG_PCI
-static inline void pci_dma_burst_advice(struct pci_dev *pdev,
-					enum pci_dma_burst_strategy *strat,
-					unsigned long *strategy_parameter)
-{
-	unsigned long cacheline_size;
-	u8 byte;
-
-	pci_read_config_byte(pdev, PCI_CACHE_LINE_SIZE, &byte);
-	if (byte == 0)
-		cacheline_size = 1024;
-	else
-		cacheline_size = (int) byte * 4;
-
-	*strat = PCI_DMA_BURST_BOUNDARY;
-	*strategy_parameter = cacheline_size;
-}
-#endif
-
 /* Return the index of the PCI controller for device PDEV. */
 
 int pci_domain_nr(struct pci_bus *bus);
diff --git a/arch/sparc/include/asm/topology_64.h b/arch/sparc/include/asm/topology_64.h
index d1761df5cca6..01d17046225a 100644
--- a/arch/sparc/include/asm/topology_64.h
+++ b/arch/sparc/include/asm/topology_64.h
@@ -41,7 +41,7 @@ static inline int pcibus_to_node(struct pci_bus *pbus)
 #define topology_physical_package_id(cpu)	(cpu_data(cpu).proc_id)
 #define topology_core_id(cpu)			(cpu_data(cpu).core_id)
 #define topology_core_cpumask(cpu)		(&cpu_core_sib_map[cpu])
-#define topology_thread_cpumask(cpu)		(&per_cpu(cpu_sibling_map, cpu))
+#define topology_sibling_cpumask(cpu)		(&per_cpu(cpu_sibling_map, cpu))
 #endif /* CONFIG_SMP */
 
 extern cpumask_t cpu_core_map[NR_CPUS];
diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c
index 70d817154fe8..c399e7b3b035 100644
--- a/arch/sparc/mm/fault_32.c
+++ b/arch/sparc/mm/fault_32.c
@@ -21,6 +21,7 @@
 #include <linux/perf_event.h>
 #include <linux/interrupt.h>
 #include <linux/kdebug.h>
+#include <linux/uaccess.h>
 
 #include <asm/page.h>
 #include <asm/pgtable.h>
@@ -29,7 +30,6 @@
 #include <asm/setup.h>
 #include <asm/smp.h>
 #include <asm/traps.h>
-#include <asm/uaccess.h>
 
 #include "mm_32.h"
 
@@ -196,7 +196,7 @@ asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write,
 	 * If we're in an interrupt or have no user
 	 * context, we must not take the fault..
 	 */
-	if (in_atomic() || !mm)
+	if (pagefault_disabled() || !mm)
 		goto no_context;
 
 	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index 479823249429..e9268ea1a68d 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -22,12 +22,12 @@
 #include <linux/kdebug.h>
 #include <linux/percpu.h>
 #include <linux/context_tracking.h>
+#include <linux/uaccess.h>
 
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/openprom.h>
 #include <asm/oplib.h>
-#include <asm/uaccess.h>
 #include <asm/asi.h>
 #include <asm/lsu.h>
 #include <asm/sections.h>
@@ -330,7 +330,7 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs)
 	 * If we're in an interrupt or have no user
 	 * context, we must not take the fault..
 	 */
-	if (in_atomic() || !mm)
+	if (faulthandler_disabled() || !mm)
 		goto intr_or_no_mm;
 
 	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
diff --git a/arch/sparc/mm/highmem.c b/arch/sparc/mm/highmem.c
index 449f864f0cef..a454ec5ff07a 100644
--- a/arch/sparc/mm/highmem.c
+++ b/arch/sparc/mm/highmem.c
@@ -53,7 +53,7 @@ void *kmap_atomic(struct page *page)
 	unsigned long vaddr;
 	long idx, type;
 
-	/* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */
+	preempt_disable();
 	pagefault_disable();
 	if (!PageHighMem(page))
 		return page_address(page);
@@ -91,6 +91,7 @@ void __kunmap_atomic(void *kvaddr)
 
 	if (vaddr < FIXADDR_START) { // FIXME
 		pagefault_enable();
+		preempt_enable();
 		return;
 	}
 
@@ -126,5 +127,6 @@ void __kunmap_atomic(void *kvaddr)
 
 	kmap_atomic_idx_pop();
 	pagefault_enable();
+	preempt_enable();
 }
 EXPORT_SYMBOL(__kunmap_atomic);
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 559cb744112c..c5d08b89a96c 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -2738,7 +2738,7 @@ void hugetlb_setup(struct pt_regs *regs)
 	struct mm_struct *mm = current->mm;
 	struct tsb_config *tp;
 
-	if (in_atomic() || !mm) {
+	if (faulthandler_disabled() || !mm) {
 		const struct exception_table_entry *entry;
 
 		entry = search_exception_tables(regs->tpc);
diff --git a/arch/tile/include/asm/atomic_64.h b/arch/tile/include/asm/atomic_64.h
index 7b11c5fadd42..0496970cef82 100644
--- a/arch/tile/include/asm/atomic_64.h
+++ b/arch/tile/include/asm/atomic_64.h
@@ -105,9 +105,6 @@ static inline long atomic64_add_unless(atomic64_t *v, long a, long u)
 
 #define atomic64_inc_not_zero(v)	atomic64_add_unless((v), 1, 0)
 
-/* Define this to indicate that cmpxchg is an efficient operation. */
-#define __HAVE_ARCH_CMPXCHG
-
 #endif /* !__ASSEMBLY__ */
 
 #endif /* _ASM_TILE_ATOMIC_64_H */
diff --git a/arch/tile/include/asm/io.h b/arch/tile/include/asm/io.h
index 6ef4ecab1df2..dc61de15c1f9 100644
--- a/arch/tile/include/asm/io.h
+++ b/arch/tile/include/asm/io.h
@@ -54,7 +54,7 @@ extern void iounmap(volatile void __iomem *addr);
 
 #define ioremap_nocache(physaddr, size)		ioremap(physaddr, size)
 #define ioremap_wc(physaddr, size)		ioremap(physaddr, size)
-#define ioremap_writethrough(physaddr, size)	ioremap(physaddr, size)
+#define ioremap_wt(physaddr, size)		ioremap(physaddr, size)
 #define ioremap_fullcache(physaddr, size)	ioremap(physaddr, size)
 
 #define mmiowb()
diff --git a/arch/tile/include/asm/topology.h b/arch/tile/include/asm/topology.h
index 938311844233..76b0d0ebb244 100644
--- a/arch/tile/include/asm/topology.h
+++ b/arch/tile/include/asm/topology.h
@@ -55,7 +55,7 @@ static inline const struct cpumask *cpumask_of_node(int node)
 #define topology_physical_package_id(cpu)       ((void)(cpu), 0)
 #define topology_core_id(cpu)                   (cpu)
 #define topology_core_cpumask(cpu)              ((void)(cpu), cpu_online_mask)
-#define topology_thread_cpumask(cpu)            cpumask_of(cpu)
+#define topology_sibling_cpumask(cpu)           cpumask_of(cpu)
 #endif
 
 #endif /* _ASM_TILE_TOPOLOGY_H */
diff --git a/arch/tile/include/asm/uaccess.h b/arch/tile/include/asm/uaccess.h
index f41cb53cf645..a33276bf5ca1 100644
--- a/arch/tile/include/asm/uaccess.h
+++ b/arch/tile/include/asm/uaccess.h
@@ -78,7 +78,8 @@ int __range_ok(unsigned long addr, unsigned long size);
  * @addr: User space pointer to start of block to check
  * @size: Size of block to check
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Checks if a pointer to a block of memory in user space is valid.
  *
@@ -192,7 +193,8 @@ extern int __get_user_bad(void)
  * @x:   Variable to store result.
  * @ptr: Source address, in user space.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple variable from user space to kernel
  * space.  It supports simple types like char and int, but not larger
@@ -274,7 +276,8 @@ extern int __put_user_bad(void)
  * @x:   Value to copy to user space.
  * @ptr: Destination address, in user space.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple value from kernel space to user
  * space.  It supports simple types like char and int, but not larger
@@ -330,7 +333,8 @@ extern int __put_user_bad(void)
  * @from: Source address, in kernel space.
  * @n:    Number of bytes to copy.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Copy data from kernel space to user space.  Caller must check
  * the specified block with access_ok() before calling this function.
@@ -366,7 +370,8 @@ copy_to_user(void __user *to, const void *from, unsigned long n)
  * @from: Source address, in user space.
  * @n:    Number of bytes to copy.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Copy data from user space to kernel space.  Caller must check
  * the specified block with access_ok() before calling this function.
@@ -437,7 +442,8 @@ static inline unsigned long __must_check copy_from_user(void *to,
  * @from: Source address, in user space.
  * @n:    Number of bytes to copy.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Copy data from user space to user space.  Caller must check
  * the specified blocks with access_ok() before calling this function.
diff --git a/arch/tile/mm/fault.c b/arch/tile/mm/fault.c
index e83cc999da02..3f4f58d34a92 100644
--- a/arch/tile/mm/fault.c
+++ b/arch/tile/mm/fault.c
@@ -354,9 +354,9 @@ static int handle_page_fault(struct pt_regs *regs,
 
 	/*
 	 * If we're in an interrupt, have no user context or are running in an
-	 * atomic region then we must not take the fault.
+	 * region with pagefaults disabled then we must not take the fault.
 	 */
-	if (in_atomic() || !mm) {
+	if (pagefault_disabled() || !mm) {
 		vma = NULL;  /* happy compiler */
 		goto bad_area_nosemaphore;
 	}
diff --git a/arch/tile/mm/highmem.c b/arch/tile/mm/highmem.c
index 6aa2f2625447..fcd545014e79 100644
--- a/arch/tile/mm/highmem.c
+++ b/arch/tile/mm/highmem.c
@@ -201,7 +201,7 @@ void *kmap_atomic_prot(struct page *page, pgprot_t prot)
 	int idx, type;
 	pte_t *pte;
 
-	/* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */
+	preempt_disable();
 	pagefault_disable();
 
 	/* Avoid icache flushes by disallowing atomic executable mappings. */
@@ -259,6 +259,7 @@ void __kunmap_atomic(void *kvaddr)
 	}
 
 	pagefault_enable();
+	preempt_enable();
 }
 EXPORT_SYMBOL(__kunmap_atomic);
 
diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c
index 8e4daf44e980..47ff9b7f3e5d 100644
--- a/arch/um/kernel/trap.c
+++ b/arch/um/kernel/trap.c
@@ -7,6 +7,7 @@
 #include <linux/sched.h>
 #include <linux/hardirq.h>
 #include <linux/module.h>
+#include <linux/uaccess.h>
 #include <asm/current.h>
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
@@ -35,10 +36,10 @@ int handle_page_fault(unsigned long address, unsigned long ip,
 	*code_out = SEGV_MAPERR;
 
 	/*
-	 * If the fault was during atomic operation, don't take the fault, just
+	 * If the fault was with pagefaults disabled, don't take the fault, just
 	 * fail.
 	 */
-	if (in_atomic())
+	if (faulthandler_disabled())
 		goto out_nosemaphore;
 
 	if (is_user)
diff --git a/arch/unicore32/include/asm/pci.h b/arch/unicore32/include/asm/pci.h
index 654407e98619..38b3f3785c3c 100644
--- a/arch/unicore32/include/asm/pci.h
+++ b/arch/unicore32/include/asm/pci.h
@@ -18,16 +18,6 @@
 #include <asm-generic/pci.h>
 #include <mach/hardware.h> /* for PCIBIOS_MIN_* */
 
-#ifdef CONFIG_PCI
-static inline void pci_dma_burst_advice(struct pci_dev *pdev,
-					enum pci_dma_burst_strategy *strat,
-					unsigned long *strategy_parameter)
-{
-	*strat = PCI_DMA_BURST_INFINITY;
-	*strategy_parameter = ~0UL;
-}
-#endif
-
 #define HAVE_PCI_MMAP
 extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
 	enum pci_mmap_state mmap_state, int write_combine);
diff --git a/arch/unicore32/mm/fault.c b/arch/unicore32/mm/fault.c
index 0dc922dba915..afccef5529cc 100644
--- a/arch/unicore32/mm/fault.c
+++ b/arch/unicore32/mm/fault.c
@@ -218,7 +218,7 @@ static int do_pf(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	 * If we're in an interrupt or have no user
 	 * context, we must not take the fault..
 	 */
-	if (in_atomic() || !mm)
+	if (faulthandler_disabled() || !mm)
 		goto no_context;
 
 	if (user_mode(regs))
diff --git a/arch/x86/Kbuild b/arch/x86/Kbuild
index 3942f74c92d7..1538562cc720 100644
--- a/arch/x86/Kbuild
+++ b/arch/x86/Kbuild
@@ -1,3 +1,6 @@
+
+obj-y += entry/
+
 obj-$(CONFIG_KVM) += kvm/
 
 # Xen paravirtualization support
@@ -11,7 +14,7 @@ obj-y += kernel/
 obj-y += mm/
 
 obj-y += crypto/
-obj-y += vdso/
+
 obj-$(CONFIG_IA32_EMULATION) += ia32/
 
 obj-y += platform/
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 226d5696e1d1..7e39f9b22705 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -9,140 +9,141 @@ config 64BIT
 config X86_32
 	def_bool y
 	depends on !64BIT
-	select CLKSRC_I8253
-	select HAVE_UID16
 
 config X86_64
 	def_bool y
 	depends on 64BIT
-	select X86_DEV_DMA_OPS
-	select ARCH_USE_CMPXCHG_LOCKREF
-	select HAVE_LIVEPATCH
 
 ### Arch settings
 config X86
 	def_bool y
-	select ACPI_SYSTEM_POWER_STATES_SUPPORT if ACPI
-	select ARCH_MIGHT_HAVE_ACPI_PDC if ACPI
+	select ACPI_LEGACY_TABLES_LOOKUP	if ACPI
+	select ACPI_SYSTEM_POWER_STATES_SUPPORT	if ACPI
+	select ANON_INODES
+	select ARCH_CLOCKSOURCE_DATA
+	select ARCH_DISCARD_MEMBLOCK
+	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
 	select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS
+	select ARCH_HAS_ELF_RANDOMIZE
 	select ARCH_HAS_FAST_MULTIPLIER
 	select ARCH_HAS_GCOV_PROFILE_ALL
+	select ARCH_HAS_SG_CHAIN
+	select ARCH_HAVE_NMI_SAFE_CMPXCHG
+	select ARCH_MIGHT_HAVE_ACPI_PDC		if ACPI
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
-	select HAVE_AOUT if X86_32
-	select HAVE_UNSTABLE_SCHED_CLOCK
-	select ARCH_SUPPORTS_NUMA_BALANCING if X86_64
-	select ARCH_SUPPORTS_INT128 if X86_64
-	select HAVE_IDE
-	select HAVE_OPROFILE
-	select HAVE_PCSPKR_PLATFORM
-	select HAVE_PERF_EVENTS
-	select HAVE_IOREMAP_PROT
-	select HAVE_KPROBES
-	select HAVE_MEMBLOCK
-	select HAVE_MEMBLOCK_NODE_MAP
-	select ARCH_DISCARD_MEMBLOCK
-	select ARCH_WANT_OPTIONAL_GPIOLIB
+	select ARCH_SUPPORTS_ATOMIC_RMW
+	select ARCH_SUPPORTS_INT128		if X86_64
+	select ARCH_SUPPORTS_NUMA_BALANCING	if X86_64
+	select ARCH_USE_BUILTIN_BSWAP
+	select ARCH_USE_CMPXCHG_LOCKREF		if X86_64
+	select ARCH_USE_QUEUED_RWLOCKS
+	select ARCH_USE_QUEUED_SPINLOCKS
 	select ARCH_WANT_FRAME_POINTERS
-	select HAVE_DMA_ATTRS
-	select HAVE_DMA_CONTIGUOUS
-	select HAVE_KRETPROBES
+	select ARCH_WANT_IPC_PARSE_VERSION	if X86_32
+	select ARCH_WANT_OPTIONAL_GPIOLIB
+	select BUILDTIME_EXTABLE_SORT
+	select CLKEVT_I8253
+	select CLKSRC_I8253			if X86_32
+	select CLOCKSOURCE_VALIDATE_LAST_CYCLE
+	select CLOCKSOURCE_WATCHDOG
+	select CLONE_BACKWARDS			if X86_32
+	select COMPAT_OLD_SIGACTION		if IA32_EMULATION
+	select DCACHE_WORD_ACCESS
+	select GENERIC_CLOCKEVENTS
+	select GENERIC_CLOCKEVENTS_BROADCAST	if X86_64 || (X86_32 && X86_LOCAL_APIC)
+	select GENERIC_CLOCKEVENTS_MIN_ADJUST
+	select GENERIC_CMOS_UPDATE
+	select GENERIC_CPU_AUTOPROBE
 	select GENERIC_EARLY_IOREMAP
-	select HAVE_OPTPROBES
-	select HAVE_KPROBES_ON_FTRACE
-	select HAVE_FTRACE_MCOUNT_RECORD
-	select HAVE_FENTRY if X86_64
+	select GENERIC_FIND_FIRST_BIT
+	select GENERIC_IOMAP
+	select GENERIC_IRQ_PROBE
+	select GENERIC_IRQ_SHOW
+	select GENERIC_PENDING_IRQ		if SMP
+	select GENERIC_SMP_IDLE_THREAD
+	select GENERIC_STRNCPY_FROM_USER
+	select GENERIC_STRNLEN_USER
+	select GENERIC_TIME_VSYSCALL
+	select HAVE_ACPI_APEI			if ACPI
+	select HAVE_ACPI_APEI_NMI		if ACPI
+	select HAVE_ALIGNED_STRUCT_PAGE		if SLUB
+	select HAVE_AOUT			if X86_32
+	select HAVE_ARCH_AUDITSYSCALL
+	select HAVE_ARCH_HUGE_VMAP		if X86_64 || X86_PAE
+	select HAVE_ARCH_JUMP_LABEL
+	select HAVE_ARCH_KASAN			if X86_64 && SPARSEMEM_VMEMMAP
+	select HAVE_ARCH_KGDB
+	select HAVE_ARCH_KMEMCHECK
+	select HAVE_ARCH_SECCOMP_FILTER
+	select HAVE_ARCH_SOFT_DIRTY		if X86_64
+	select HAVE_ARCH_TRACEHOOK
+	select HAVE_ARCH_TRANSPARENT_HUGEPAGE
+	select HAVE_BPF_JIT			if X86_64
+	select HAVE_CC_STACKPROTECTOR
+	select HAVE_CMPXCHG_DOUBLE
+	select HAVE_CMPXCHG_LOCAL
+	select HAVE_CONTEXT_TRACKING		if X86_64
 	select HAVE_C_RECORDMCOUNT
+	select HAVE_DEBUG_KMEMLEAK
+	select HAVE_DEBUG_STACKOVERFLOW
+	select HAVE_DMA_API_DEBUG
+	select HAVE_DMA_ATTRS
+	select HAVE_DMA_CONTIGUOUS
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS
-	select HAVE_FUNCTION_TRACER
-	select HAVE_FUNCTION_GRAPH_TRACER
-	select HAVE_FUNCTION_GRAPH_FP_TEST
-	select HAVE_SYSCALL_TRACEPOINTS
-	select SYSCTL_EXCEPTION_TRACE
-	select HAVE_KVM
-	select HAVE_ARCH_KGDB
-	select HAVE_ARCH_TRACEHOOK
-	select HAVE_GENERIC_DMA_COHERENT if X86_32
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
-	select USER_STACKTRACE_SUPPORT
-	select HAVE_REGS_AND_STACK_ACCESS_API
-	select HAVE_DMA_API_DEBUG
-	select HAVE_KERNEL_GZIP
+	select HAVE_FENTRY			if X86_64
+	select HAVE_FTRACE_MCOUNT_RECORD
+	select HAVE_FUNCTION_GRAPH_FP_TEST
+	select HAVE_FUNCTION_GRAPH_TRACER
+	select HAVE_FUNCTION_TRACER
+	select HAVE_GENERIC_DMA_COHERENT	if X86_32
+	select HAVE_HW_BREAKPOINT
+	select HAVE_IDE
+	select HAVE_IOREMAP_PROT
+	select HAVE_IRQ_EXIT_ON_IRQ_STACK	if X86_64
+	select HAVE_IRQ_TIME_ACCOUNTING
 	select HAVE_KERNEL_BZIP2
+	select HAVE_KERNEL_GZIP
+	select HAVE_KERNEL_LZ4
 	select HAVE_KERNEL_LZMA
-	select HAVE_KERNEL_XZ
 	select HAVE_KERNEL_LZO
-	select HAVE_KERNEL_LZ4
-	select HAVE_HW_BREAKPOINT
+	select HAVE_KERNEL_XZ
+	select HAVE_KPROBES
+	select HAVE_KPROBES_ON_FTRACE
+	select HAVE_KRETPROBES
+	select HAVE_KVM
+	select HAVE_LIVEPATCH			if X86_64
+	select HAVE_MEMBLOCK
+	select HAVE_MEMBLOCK_NODE_MAP
 	select HAVE_MIXED_BREAKPOINTS_REGS
-	select PERF_EVENTS
+	select HAVE_OPROFILE
+	select HAVE_OPTPROBES
+	select HAVE_PCSPKR_PLATFORM
+	select HAVE_PERF_EVENTS
 	select HAVE_PERF_EVENTS_NMI
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
-	select HAVE_DEBUG_KMEMLEAK
-	select ANON_INODES
-	select HAVE_ALIGNED_STRUCT_PAGE if SLUB
-	select HAVE_CMPXCHG_LOCAL
-	select HAVE_CMPXCHG_DOUBLE
-	select HAVE_ARCH_KMEMCHECK
-	select HAVE_ARCH_KASAN if X86_64 && SPARSEMEM_VMEMMAP
+	select HAVE_REGS_AND_STACK_ACCESS_API
+	select HAVE_SYSCALL_TRACEPOINTS
+	select HAVE_UID16			if X86_32
+	select HAVE_UNSTABLE_SCHED_CLOCK
 	select HAVE_USER_RETURN_NOTIFIER
-	select ARCH_HAS_ELF_RANDOMIZE
-	select HAVE_ARCH_JUMP_LABEL
-	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
-	select SPARSE_IRQ
-	select GENERIC_FIND_FIRST_BIT
-	select GENERIC_IRQ_PROBE
-	select GENERIC_PENDING_IRQ if SMP
-	select GENERIC_IRQ_SHOW
-	select GENERIC_CLOCKEVENTS_MIN_ADJUST
 	select IRQ_FORCED_THREADING
-	select HAVE_BPF_JIT if X86_64
-	select HAVE_ARCH_TRANSPARENT_HUGEPAGE
-	select HAVE_ARCH_HUGE_VMAP if X86_64 || (X86_32 && X86_PAE)
-	select ARCH_HAS_SG_CHAIN
-	select CLKEVT_I8253
-	select ARCH_HAVE_NMI_SAFE_CMPXCHG
-	select GENERIC_IOMAP
-	select DCACHE_WORD_ACCESS
-	select GENERIC_SMP_IDLE_THREAD
-	select ARCH_WANT_IPC_PARSE_VERSION if X86_32
-	select HAVE_ARCH_SECCOMP_FILTER
-	select BUILDTIME_EXTABLE_SORT
-	select GENERIC_CMOS_UPDATE
-	select HAVE_ARCH_SOFT_DIRTY if X86_64
-	select CLOCKSOURCE_WATCHDOG
-	select GENERIC_CLOCKEVENTS
-	select ARCH_CLOCKSOURCE_DATA
-	select CLOCKSOURCE_VALIDATE_LAST_CYCLE
-	select GENERIC_CLOCKEVENTS_BROADCAST if X86_64 || (X86_32 && X86_LOCAL_APIC)
-	select GENERIC_TIME_VSYSCALL
-	select GENERIC_STRNCPY_FROM_USER
-	select GENERIC_STRNLEN_USER
-	select HAVE_CONTEXT_TRACKING if X86_64
-	select HAVE_IRQ_TIME_ACCOUNTING
-	select VIRT_TO_BUS
-	select MODULES_USE_ELF_REL if X86_32
-	select MODULES_USE_ELF_RELA if X86_64
-	select CLONE_BACKWARDS if X86_32
-	select ARCH_USE_BUILTIN_BSWAP
-	select ARCH_USE_QUEUE_RWLOCK
-	select OLD_SIGSUSPEND3 if X86_32 || IA32_EMULATION
-	select OLD_SIGACTION if X86_32
-	select COMPAT_OLD_SIGACTION if IA32_EMULATION
+	select MODULES_USE_ELF_RELA		if X86_64
+	select MODULES_USE_ELF_REL		if X86_32
+	select OLD_SIGACTION			if X86_32
+	select OLD_SIGSUSPEND3			if X86_32 || IA32_EMULATION
+	select PERF_EVENTS
 	select RTC_LIB
-	select HAVE_DEBUG_STACKOVERFLOW
-	select HAVE_IRQ_EXIT_ON_IRQ_STACK if X86_64
-	select HAVE_CC_STACKPROTECTOR
-	select GENERIC_CPU_AUTOPROBE
-	select HAVE_ARCH_AUDITSYSCALL
-	select ARCH_SUPPORTS_ATOMIC_RMW
-	select HAVE_ACPI_APEI if ACPI
-	select HAVE_ACPI_APEI_NMI if ACPI
-	select ACPI_LEGACY_TABLES_LOOKUP if ACPI
-	select X86_FEATURE_NAMES if PROC_FS
+	select SPARSE_IRQ
 	select SRCU
+	select SYSCTL_EXCEPTION_TRACE
+	select USER_STACKTRACE_SUPPORT
+	select VIRT_TO_BUS
+	select X86_DEV_DMA_OPS			if X86_64
+	select X86_FEATURE_NAMES		if PROC_FS
 
 config INSTRUCTION_DECODER
 	def_bool y
@@ -260,10 +261,6 @@ config X86_64_SMP
 	def_bool y
 	depends on X86_64 && SMP
 
-config X86_HT
-	def_bool y
-	depends on SMP
-
 config X86_32_LAZY_GS
 	def_bool y
 	depends on X86_32 && !CC_STACKPROTECTOR
@@ -341,7 +338,7 @@ config X86_FEATURE_NAMES
 
 config X86_X2APIC
 	bool "Support x2apic"
-	depends on X86_LOCAL_APIC && X86_64 && IRQ_REMAP
+	depends on X86_LOCAL_APIC && X86_64 && (IRQ_REMAP || HYPERVISOR_GUEST)
 	---help---
 	  This enables x2apic support on CPUs that have this feature.
 
@@ -441,6 +438,7 @@ config X86_UV
 	depends on X86_EXTENDED_PLATFORM
 	depends on NUMA
 	depends on X86_X2APIC
+	depends on PCI
 	---help---
 	  This option is needed in order to support SGI Ultraviolet systems.
 	  If you don't have one of these, you should say N here.
@@ -466,7 +464,6 @@ config X86_INTEL_CE
 	select X86_REBOOTFIXUPS
 	select OF
 	select OF_EARLY_FLATTREE
-	select IRQ_DOMAIN
 	---help---
 	  Select for the Intel CE media processor (CE4100) SOC.
 	  This option compiles in support for the CE4100 SOC for settop
@@ -666,7 +663,7 @@ config PARAVIRT_DEBUG
 config PARAVIRT_SPINLOCKS
 	bool "Paravirtualization layer for spinlocks"
 	depends on PARAVIRT && SMP
-	select UNINLINE_SPIN_UNLOCK
+	select UNINLINE_SPIN_UNLOCK if !QUEUED_SPINLOCKS
 	---help---
 	  Paravirtualized spinlocks allow a pvops backend to replace the
 	  spinlock implementation with something virtualization-friendly
@@ -851,11 +848,12 @@ config NR_CPUS
 	default "1" if !SMP
 	default "8192" if MAXSMP
 	default "32" if SMP && X86_BIGSMP
-	default "8" if SMP
+	default "8" if SMP && X86_32
+	default "64" if SMP
 	---help---
 	  This allows you to specify the maximum number of CPUs which this
 	  kernel will support.  If CPUMASK_OFFSTACK is enabled, the maximum
-	  supported value is 4096, otherwise the maximum value is 512.  The
+	  supported value is 8192, otherwise the maximum value is 512.  The
 	  minimum value which makes sense is 2.
 
 	  This is purely to save memory - each supported CPU adds
@@ -863,7 +861,7 @@ config NR_CPUS
 
 config SCHED_SMT
 	bool "SMT (Hyperthreading) scheduler support"
-	depends on X86_HT
+	depends on SMP
 	---help---
 	  SMT scheduler support improves the CPU scheduler's decision making
 	  when dealing with Intel Pentium 4 chips with HyperThreading at a
@@ -873,7 +871,7 @@ config SCHED_SMT
 config SCHED_MC
 	def_bool y
 	prompt "Multi-core scheduler support"
-	depends on X86_HT
+	depends on SMP
 	---help---
 	  Multi-core scheduler support improves the CPU scheduler's decision
 	  making when dealing with multi-core CPU chips at a cost of slightly
@@ -914,12 +912,12 @@ config X86_UP_IOAPIC
 config X86_LOCAL_APIC
 	def_bool y
 	depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_APIC || PCI_MSI
-	select GENERIC_IRQ_LEGACY_ALLOC_HWIRQ
+	select IRQ_DOMAIN_HIERARCHY
+	select PCI_MSI_IRQ_DOMAIN if PCI_MSI
 
 config X86_IO_APIC
 	def_bool y
 	depends on X86_LOCAL_APIC || X86_UP_IOAPIC
-	select IRQ_DOMAIN
 
 config X86_REROUTE_FOR_BROKEN_BOOT_IRQS
 	bool "Reroute for broken boot IRQs"
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index 72484a645f05..a15893d17c55 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -332,4 +332,27 @@ config X86_DEBUG_STATIC_CPU_HAS
 
 	  If unsure, say N.
 
+config X86_DEBUG_FPU
+	bool "Debug the x86 FPU code"
+	depends on DEBUG_KERNEL
+	default y
+	---help---
+	  If this option is enabled then there will be extra sanity
+	  checks and (boot time) debug printouts added to the kernel.
+	  This debugging adds some small amount of runtime overhead
+	  to the kernel.
+
+	  If unsure, say N.
+
+config PUNIT_ATOM_DEBUG
+	tristate "ATOM Punit debug driver"
+	select DEBUG_FS
+	select IOSF_MBI
+	---help---
+	  This is a debug driver, which gets the power states
+	  of all Punit North Complex devices. The power states of
+	  each device is exposed as part of the debugfs interface.
+	  The current power state can be read from
+	  /sys/kernel/debug/punit_atom/dev_power_state
+
 endmenu
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 2fda005bb334..118e6debc483 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -77,6 +77,12 @@ else
         KBUILD_AFLAGS += -m64
         KBUILD_CFLAGS += -m64
 
+        # Align jump targets to 1 byte, not the default 16 bytes:
+        KBUILD_CFLAGS += -falign-jumps=1
+
+        # Pack loops tightly as well:
+        KBUILD_CFLAGS += -falign-loops=1
+
         # Don't autogenerate traditional x87 instructions
         KBUILD_CFLAGS += $(call cc-option,-mno-80387)
         KBUILD_CFLAGS += $(call cc-option,-mno-fp-ret-in-387)
@@ -84,6 +90,9 @@ else
 	# Use -mpreferred-stack-boundary=3 if supported.
 	KBUILD_CFLAGS += $(call cc-option,-mpreferred-stack-boundary=3)
 
+	# Use -mskip-rax-setup if supported.
+	KBUILD_CFLAGS += $(call cc-option,-mskip-rax-setup)
+
         # FIXME - should be integrated in Makefile.cpu (Makefile_32.cpu)
         cflags-$(CONFIG_MK8) += $(call cc-option,-march=k8)
         cflags-$(CONFIG_MPSC) += $(call cc-option,-march=nocona)
@@ -140,12 +149,6 @@ endif
 sp-$(CONFIG_X86_32) := esp
 sp-$(CONFIG_X86_64) := rsp
 
-# do binutils support CFI?
-cfi := $(call as-instr,.cfi_startproc\n.cfi_rel_offset $(sp-y)$(comma)0\n.cfi_endproc,-DCONFIG_AS_CFI=1)
-# is .cfi_signal_frame supported too?
-cfi-sigframe := $(call as-instr,.cfi_startproc\n.cfi_signal_frame\n.cfi_endproc,-DCONFIG_AS_CFI_SIGNAL_FRAME=1)
-cfi-sections := $(call as-instr,.cfi_sections .debug_frame,-DCONFIG_AS_CFI_SECTIONS=1)
-
 # does binutils support specific instructions?
 asinstr := $(call as-instr,fxsaveq (%rax),-DCONFIG_AS_FXSAVEQ=1)
 asinstr += $(call as-instr,pshufb %xmm0$(comma)%xmm0,-DCONFIG_AS_SSSE3=1)
@@ -153,8 +156,8 @@ asinstr += $(call as-instr,crc32l %eax$(comma)%eax,-DCONFIG_AS_CRC32=1)
 avx_instr := $(call as-instr,vxorps %ymm0$(comma)%ymm1$(comma)%ymm2,-DCONFIG_AS_AVX=1)
 avx2_instr :=$(call as-instr,vpbroadcastb %xmm0$(comma)%ymm1,-DCONFIG_AS_AVX2=1)
 
-KBUILD_AFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr)
-KBUILD_CFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr)
+KBUILD_AFLAGS += $(asinstr) $(avx_instr) $(avx2_instr)
+KBUILD_CFLAGS += $(asinstr) $(avx_instr) $(avx2_instr)
 
 LDFLAGS := -m elf_$(UTS_MACHINE)
 
@@ -178,7 +181,7 @@ archscripts: scripts_basic
 # Syscall table generation
 
 archheaders:
-	$(Q)$(MAKE) $(build)=arch/x86/syscalls all
+	$(Q)$(MAKE) $(build)=arch/x86/entry/syscalls all
 
 archprepare:
 ifeq ($(CONFIG_KEXEC_FILE),y)
@@ -241,7 +244,7 @@ install:
 
 PHONY += vdso_install
 vdso_install:
-	$(Q)$(MAKE) $(build)=arch/x86/vdso $@
+	$(Q)$(MAKE) $(build)=arch/x86/entry/vdso $@
 
 archclean:
 	$(Q)rm -rf $(objtree)/arch/i386
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index 112cefacf2af..2bfc8a7c88c1 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -32,7 +32,7 @@
 #include <crypto/lrw.h>
 #include <crypto/xts.h>
 #include <asm/cpu_device_id.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 #include <asm/crypto/aes.h>
 #include <crypto/ablk_helper.h>
 #include <crypto/scatterwalk.h>
@@ -44,15 +44,19 @@
 #endif
 
 
+#define AESNI_ALIGN	16
+#define AES_BLOCK_MASK	(~(AES_BLOCK_SIZE - 1))
+#define RFC4106_HASH_SUBKEY_SIZE 16
+
 /* This data is stored at the end of the crypto_tfm struct.
  * It's a type of per "session" data storage location.
  * This needs to be 16 byte aligned.
  */
 struct aesni_rfc4106_gcm_ctx {
-	u8 hash_subkey[16];
-	struct crypto_aes_ctx aes_key_expanded;
+	u8 hash_subkey[16] __attribute__ ((__aligned__(AESNI_ALIGN)));
+	struct crypto_aes_ctx aes_key_expanded
+		__attribute__ ((__aligned__(AESNI_ALIGN)));
 	u8 nonce[4];
-	struct cryptd_aead *cryptd_tfm;
 };
 
 struct aesni_gcm_set_hash_subkey_result {
@@ -66,10 +70,6 @@ struct aesni_hash_subkey_req_data {
 	struct scatterlist sg;
 };
 
-#define AESNI_ALIGN	(16)
-#define AES_BLOCK_MASK	(~(AES_BLOCK_SIZE-1))
-#define RFC4106_HASH_SUBKEY_SIZE 16
-
 struct aesni_lrw_ctx {
 	struct lrw_table_ctx lrw_table;
 	u8 raw_aes_ctx[sizeof(struct crypto_aes_ctx) + AESNI_ALIGN - 1];
@@ -283,10 +283,11 @@ static void (*aesni_gcm_dec_tfm)(void *ctx, u8 *out,
 static inline struct
 aesni_rfc4106_gcm_ctx *aesni_rfc4106_gcm_ctx_get(struct crypto_aead *tfm)
 {
-	return
-		(struct aesni_rfc4106_gcm_ctx *)
-		PTR_ALIGN((u8 *)
-		crypto_tfm_ctx(crypto_aead_tfm(tfm)), AESNI_ALIGN);
+	unsigned long align = AESNI_ALIGN;
+
+	if (align <= crypto_tfm_ctx_alignment())
+		align = 1;
+	return PTR_ALIGN(crypto_aead_ctx(tfm), align);
 }
 #endif
 
@@ -790,36 +791,30 @@ static int xts_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
 #endif
 
 #ifdef CONFIG_X86_64
-static int rfc4106_init(struct crypto_tfm *tfm)
+static int rfc4106_init(struct crypto_aead *aead)
 {
 	struct cryptd_aead *cryptd_tfm;
-	struct aesni_rfc4106_gcm_ctx *ctx = (struct aesni_rfc4106_gcm_ctx *)
-		PTR_ALIGN((u8 *)crypto_tfm_ctx(tfm), AESNI_ALIGN);
-	struct crypto_aead *cryptd_child;
-	struct aesni_rfc4106_gcm_ctx *child_ctx;
+	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
+
 	cryptd_tfm = cryptd_alloc_aead("__driver-gcm-aes-aesni",
 				       CRYPTO_ALG_INTERNAL,
 				       CRYPTO_ALG_INTERNAL);
 	if (IS_ERR(cryptd_tfm))
 		return PTR_ERR(cryptd_tfm);
 
-	cryptd_child = cryptd_aead_child(cryptd_tfm);
-	child_ctx = aesni_rfc4106_gcm_ctx_get(cryptd_child);
-	memcpy(child_ctx, ctx, sizeof(*ctx));
-	ctx->cryptd_tfm = cryptd_tfm;
-	tfm->crt_aead.reqsize = sizeof(struct aead_request)
-		+ crypto_aead_reqsize(&cryptd_tfm->base);
+	*ctx = cryptd_tfm;
+	crypto_aead_set_reqsize(
+		aead,
+		sizeof(struct aead_request) +
+		crypto_aead_reqsize(&cryptd_tfm->base));
 	return 0;
 }
 
-static void rfc4106_exit(struct crypto_tfm *tfm)
+static void rfc4106_exit(struct crypto_aead *aead)
 {
-	struct aesni_rfc4106_gcm_ctx *ctx =
-		(struct aesni_rfc4106_gcm_ctx *)
-		PTR_ALIGN((u8 *)crypto_tfm_ctx(tfm), AESNI_ALIGN);
-	if (!IS_ERR(ctx->cryptd_tfm))
-		cryptd_free_aead(ctx->cryptd_tfm);
-	return;
+	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
+
+	cryptd_free_aead(*ctx);
 }
 
 static void
@@ -845,8 +840,6 @@ rfc4106_set_hash_subkey(u8 *hash_subkey, const u8 *key, unsigned int key_len)
 	if (IS_ERR(ctr_tfm))
 		return PTR_ERR(ctr_tfm);
 
-	crypto_ablkcipher_clear_flags(ctr_tfm, ~0);
-
 	ret = crypto_ablkcipher_setkey(ctr_tfm, key, key_len);
 	if (ret)
 		goto out_free_ablkcipher;
@@ -895,73 +888,29 @@ out_free_ablkcipher:
 static int common_rfc4106_set_key(struct crypto_aead *aead, const u8 *key,
 				  unsigned int key_len)
 {
-	int ret = 0;
-	struct crypto_tfm *tfm = crypto_aead_tfm(aead);
 	struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(aead);
-	u8 *new_key_align, *new_key_mem = NULL;
 
 	if (key_len < 4) {
-		crypto_tfm_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		crypto_aead_set_flags(aead, CRYPTO_TFM_RES_BAD_KEY_LEN);
 		return -EINVAL;
 	}
 	/*Account for 4 byte nonce at the end.*/
 	key_len -= 4;
-	if (key_len != AES_KEYSIZE_128 && key_len != AES_KEYSIZE_192 &&
-	    key_len != AES_KEYSIZE_256) {
-		crypto_tfm_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
-		return -EINVAL;
-	}
 
 	memcpy(ctx->nonce, key + key_len, sizeof(ctx->nonce));
-	/*This must be on a 16 byte boundary!*/
-	if ((unsigned long)(&(ctx->aes_key_expanded.key_enc[0])) % AESNI_ALIGN)
-		return -EINVAL;
-
-	if ((unsigned long)key % AESNI_ALIGN) {
-		/*key is not aligned: use an auxuliar aligned pointer*/
-		new_key_mem = kmalloc(key_len+AESNI_ALIGN, GFP_KERNEL);
-		if (!new_key_mem)
-			return -ENOMEM;
-
-		new_key_align = PTR_ALIGN(new_key_mem, AESNI_ALIGN);
-		memcpy(new_key_align, key, key_len);
-		key = new_key_align;
-	}
 
-	if (!irq_fpu_usable())
-		ret = crypto_aes_expand_key(&(ctx->aes_key_expanded),
-		key, key_len);
-	else {
-		kernel_fpu_begin();
-		ret = aesni_set_key(&(ctx->aes_key_expanded), key, key_len);
-		kernel_fpu_end();
-	}
-	/*This must be on a 16 byte boundary!*/
-	if ((unsigned long)(&(ctx->hash_subkey[0])) % AESNI_ALIGN) {
-		ret = -EINVAL;
-		goto exit;
-	}
-	ret = rfc4106_set_hash_subkey(ctx->hash_subkey, key, key_len);
-exit:
-	kfree(new_key_mem);
-	return ret;
+	return aes_set_key_common(crypto_aead_tfm(aead),
+				  &ctx->aes_key_expanded, key, key_len) ?:
+	       rfc4106_set_hash_subkey(ctx->hash_subkey, key, key_len);
 }
 
 static int rfc4106_set_key(struct crypto_aead *parent, const u8 *key,
 			   unsigned int key_len)
 {
-	struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(parent);
-	struct crypto_aead *child = cryptd_aead_child(ctx->cryptd_tfm);
-	struct aesni_rfc4106_gcm_ctx *c_ctx = aesni_rfc4106_gcm_ctx_get(child);
-	struct cryptd_aead *cryptd_tfm = ctx->cryptd_tfm;
-	int ret;
+	struct cryptd_aead **ctx = crypto_aead_ctx(parent);
+	struct cryptd_aead *cryptd_tfm = *ctx;
 
-	ret = crypto_aead_setkey(child, key, key_len);
-	if (!ret) {
-		memcpy(ctx, c_ctx, sizeof(*ctx));
-		ctx->cryptd_tfm = cryptd_tfm;
-	}
-	return ret;
+	return crypto_aead_setkey(&cryptd_tfm->base, key, key_len);
 }
 
 static int common_rfc4106_set_authsize(struct crypto_aead *aead,
@@ -975,7 +924,7 @@ static int common_rfc4106_set_authsize(struct crypto_aead *aead,
 	default:
 		return -EINVAL;
 	}
-	crypto_aead_crt(aead)->authsize = authsize;
+
 	return 0;
 }
 
@@ -984,30 +933,23 @@ static int common_rfc4106_set_authsize(struct crypto_aead *aead,
 static int rfc4106_set_authsize(struct crypto_aead *parent,
 				unsigned int authsize)
 {
-	struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(parent);
-	struct crypto_aead *child = cryptd_aead_child(ctx->cryptd_tfm);
-	int ret;
+	struct cryptd_aead **ctx = crypto_aead_ctx(parent);
+	struct cryptd_aead *cryptd_tfm = *ctx;
 
-	ret = crypto_aead_setauthsize(child, authsize);
-	if (!ret)
-		crypto_aead_crt(parent)->authsize = authsize;
-	return ret;
+	return crypto_aead_setauthsize(&cryptd_tfm->base, authsize);
 }
 
-static int __driver_rfc4106_encrypt(struct aead_request *req)
+static int helper_rfc4106_encrypt(struct aead_request *req)
 {
 	u8 one_entry_in_sg = 0;
 	u8 *src, *dst, *assoc;
 	__be32 counter = cpu_to_be32(1);
 	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
 	struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm);
-	u32 key_len = ctx->aes_key_expanded.key_length;
 	void *aes_ctx = &(ctx->aes_key_expanded);
 	unsigned long auth_tag_len = crypto_aead_authsize(tfm);
-	u8 iv_tab[16+AESNI_ALIGN];
-	u8* iv = (u8 *) PTR_ALIGN((u8 *)iv_tab, AESNI_ALIGN);
+	u8 iv[16] __attribute__ ((__aligned__(AESNI_ALIGN)));
 	struct scatter_walk src_sg_walk;
-	struct scatter_walk assoc_sg_walk;
 	struct scatter_walk dst_sg_walk;
 	unsigned int i;
 
@@ -1016,12 +958,6 @@ static int __driver_rfc4106_encrypt(struct aead_request *req)
 	/* to 8 or 12 bytes */
 	if (unlikely(req->assoclen != 8 && req->assoclen != 12))
 		return -EINVAL;
-	if (unlikely(auth_tag_len != 8 && auth_tag_len != 12 && auth_tag_len != 16))
-	        return -EINVAL;
-	if (unlikely(key_len != AES_KEYSIZE_128 &&
-	             key_len != AES_KEYSIZE_192 &&
-	             key_len != AES_KEYSIZE_256))
-	        return -EINVAL;
 
 	/* IV below built */
 	for (i = 0; i < 4; i++)
@@ -1030,55 +966,57 @@ static int __driver_rfc4106_encrypt(struct aead_request *req)
 		*(iv+4+i) = req->iv[i];
 	*((__be32 *)(iv+12)) = counter;
 
-	if ((sg_is_last(req->src)) && (sg_is_last(req->assoc))) {
+	if (sg_is_last(req->src) &&
+	    req->src->offset + req->src->length <= PAGE_SIZE &&
+	    sg_is_last(req->dst) &&
+	    req->dst->offset + req->dst->length <= PAGE_SIZE) {
 		one_entry_in_sg = 1;
 		scatterwalk_start(&src_sg_walk, req->src);
-		scatterwalk_start(&assoc_sg_walk, req->assoc);
-		src = scatterwalk_map(&src_sg_walk);
-		assoc = scatterwalk_map(&assoc_sg_walk);
+		assoc = scatterwalk_map(&src_sg_walk);
+		src = assoc + req->assoclen;
 		dst = src;
 		if (unlikely(req->src != req->dst)) {
 			scatterwalk_start(&dst_sg_walk, req->dst);
-			dst = scatterwalk_map(&dst_sg_walk);
+			dst = scatterwalk_map(&dst_sg_walk) + req->assoclen;
 		}
-
 	} else {
 		/* Allocate memory for src, dst, assoc */
-		src = kmalloc(req->cryptlen + auth_tag_len + req->assoclen,
+		assoc = kmalloc(req->cryptlen + auth_tag_len + req->assoclen,
 			GFP_ATOMIC);
-		if (unlikely(!src))
+		if (unlikely(!assoc))
 			return -ENOMEM;
-		assoc = (src + req->cryptlen + auth_tag_len);
-		scatterwalk_map_and_copy(src, req->src, 0, req->cryptlen, 0);
-		scatterwalk_map_and_copy(assoc, req->assoc, 0,
-					req->assoclen, 0);
+		scatterwalk_map_and_copy(assoc, req->src, 0,
+					 req->assoclen + req->cryptlen, 0);
+		src = assoc + req->assoclen;
 		dst = src;
 	}
 
+	kernel_fpu_begin();
 	aesni_gcm_enc_tfm(aes_ctx, dst, src, (unsigned long)req->cryptlen, iv,
 		ctx->hash_subkey, assoc, (unsigned long)req->assoclen, dst
 		+ ((unsigned long)req->cryptlen), auth_tag_len);
+	kernel_fpu_end();
 
 	/* The authTag (aka the Integrity Check Value) needs to be written
 	 * back to the packet. */
 	if (one_entry_in_sg) {
 		if (unlikely(req->src != req->dst)) {
-			scatterwalk_unmap(dst);
-			scatterwalk_done(&dst_sg_walk, 0, 0);
+			scatterwalk_unmap(dst - req->assoclen);
+			scatterwalk_advance(&dst_sg_walk, req->dst->length);
+			scatterwalk_done(&dst_sg_walk, 1, 0);
 		}
-		scatterwalk_unmap(src);
 		scatterwalk_unmap(assoc);
-		scatterwalk_done(&src_sg_walk, 0, 0);
-		scatterwalk_done(&assoc_sg_walk, 0, 0);
+		scatterwalk_advance(&src_sg_walk, req->src->length);
+		scatterwalk_done(&src_sg_walk, req->src == req->dst, 0);
 	} else {
-		scatterwalk_map_and_copy(dst, req->dst, 0,
-			req->cryptlen + auth_tag_len, 1);
-		kfree(src);
+		scatterwalk_map_and_copy(dst, req->dst, req->assoclen,
+					 req->cryptlen + auth_tag_len, 1);
+		kfree(assoc);
 	}
 	return 0;
 }
 
-static int __driver_rfc4106_decrypt(struct aead_request *req)
+static int helper_rfc4106_decrypt(struct aead_request *req)
 {
 	u8 one_entry_in_sg = 0;
 	u8 *src, *dst, *assoc;
@@ -1087,26 +1025,16 @@ static int __driver_rfc4106_decrypt(struct aead_request *req)
 	int retval = 0;
 	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
 	struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm);
-	u32 key_len = ctx->aes_key_expanded.key_length;
 	void *aes_ctx = &(ctx->aes_key_expanded);
 	unsigned long auth_tag_len = crypto_aead_authsize(tfm);
-	u8 iv_and_authTag[32+AESNI_ALIGN];
-	u8 *iv = (u8 *) PTR_ALIGN((u8 *)iv_and_authTag, AESNI_ALIGN);
-	u8 *authTag = iv + 16;
+	u8 iv[16] __attribute__ ((__aligned__(AESNI_ALIGN)));
+	u8 authTag[16];
 	struct scatter_walk src_sg_walk;
-	struct scatter_walk assoc_sg_walk;
 	struct scatter_walk dst_sg_walk;
 	unsigned int i;
 
-	if (unlikely((req->cryptlen < auth_tag_len) ||
-		(req->assoclen != 8 && req->assoclen != 12)))
+	if (unlikely(req->assoclen != 8 && req->assoclen != 12))
 		return -EINVAL;
-	if (unlikely(auth_tag_len != 8 && auth_tag_len != 12 && auth_tag_len != 16))
-	        return -EINVAL;
-	if (unlikely(key_len != AES_KEYSIZE_128 &&
-	             key_len != AES_KEYSIZE_192 &&
-	             key_len != AES_KEYSIZE_256))
-	        return -EINVAL;
 
 	/* Assuming we are supporting rfc4106 64-bit extended */
 	/* sequence numbers We need to have the AAD length */
@@ -1120,33 +1048,36 @@ static int __driver_rfc4106_decrypt(struct aead_request *req)
 		*(iv+4+i) = req->iv[i];
 	*((__be32 *)(iv+12)) = counter;
 
-	if ((sg_is_last(req->src)) && (sg_is_last(req->assoc))) {
+	if (sg_is_last(req->src) &&
+	    req->src->offset + req->src->length <= PAGE_SIZE &&
+	    sg_is_last(req->dst) &&
+	    req->dst->offset + req->dst->length <= PAGE_SIZE) {
 		one_entry_in_sg = 1;
 		scatterwalk_start(&src_sg_walk, req->src);
-		scatterwalk_start(&assoc_sg_walk, req->assoc);
-		src = scatterwalk_map(&src_sg_walk);
-		assoc = scatterwalk_map(&assoc_sg_walk);
+		assoc = scatterwalk_map(&src_sg_walk);
+		src = assoc + req->assoclen;
 		dst = src;
 		if (unlikely(req->src != req->dst)) {
 			scatterwalk_start(&dst_sg_walk, req->dst);
-			dst = scatterwalk_map(&dst_sg_walk);
+			dst = scatterwalk_map(&dst_sg_walk) + req->assoclen;
 		}
 
 	} else {
 		/* Allocate memory for src, dst, assoc */
-		src = kmalloc(req->cryptlen + req->assoclen, GFP_ATOMIC);
-		if (!src)
+		assoc = kmalloc(req->cryptlen + req->assoclen, GFP_ATOMIC);
+		if (!assoc)
 			return -ENOMEM;
-		assoc = (src + req->cryptlen);
-		scatterwalk_map_and_copy(src, req->src, 0, req->cryptlen, 0);
-		scatterwalk_map_and_copy(assoc, req->assoc, 0,
-			req->assoclen, 0);
+		scatterwalk_map_and_copy(assoc, req->src, 0,
+					 req->assoclen + req->cryptlen, 0);
+		src = assoc + req->assoclen;
 		dst = src;
 	}
 
+	kernel_fpu_begin();
 	aesni_gcm_dec_tfm(aes_ctx, dst, src, tempCipherLen, iv,
 		ctx->hash_subkey, assoc, (unsigned long)req->assoclen,
 		authTag, auth_tag_len);
+	kernel_fpu_end();
 
 	/* Compare generated tag with passed in tag. */
 	retval = crypto_memneq(src + tempCipherLen, authTag, auth_tag_len) ?
@@ -1154,90 +1085,59 @@ static int __driver_rfc4106_decrypt(struct aead_request *req)
 
 	if (one_entry_in_sg) {
 		if (unlikely(req->src != req->dst)) {
-			scatterwalk_unmap(dst);
-			scatterwalk_done(&dst_sg_walk, 0, 0);
+			scatterwalk_unmap(dst - req->assoclen);
+			scatterwalk_advance(&dst_sg_walk, req->dst->length);
+			scatterwalk_done(&dst_sg_walk, 1, 0);
 		}
-		scatterwalk_unmap(src);
 		scatterwalk_unmap(assoc);
-		scatterwalk_done(&src_sg_walk, 0, 0);
-		scatterwalk_done(&assoc_sg_walk, 0, 0);
+		scatterwalk_advance(&src_sg_walk, req->src->length);
+		scatterwalk_done(&src_sg_walk, req->src == req->dst, 0);
 	} else {
-		scatterwalk_map_and_copy(dst, req->dst, 0, tempCipherLen, 1);
-		kfree(src);
+		scatterwalk_map_and_copy(dst, req->dst, req->assoclen,
+					 tempCipherLen, 1);
+		kfree(assoc);
 	}
 	return retval;
 }
 
 static int rfc4106_encrypt(struct aead_request *req)
 {
-	int ret;
 	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
-	struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm);
+	struct cryptd_aead **ctx = crypto_aead_ctx(tfm);
+	struct cryptd_aead *cryptd_tfm = *ctx;
+	struct aead_request *subreq = aead_request_ctx(req);
 
-	if (!irq_fpu_usable()) {
-		struct aead_request *cryptd_req =
-			(struct aead_request *) aead_request_ctx(req);
+	aead_request_set_tfm(subreq, irq_fpu_usable() ?
+				     cryptd_aead_child(cryptd_tfm) :
+				     &cryptd_tfm->base);
 
-		memcpy(cryptd_req, req, sizeof(*req));
-		aead_request_set_tfm(cryptd_req, &ctx->cryptd_tfm->base);
-		ret = crypto_aead_encrypt(cryptd_req);
-	} else {
-		kernel_fpu_begin();
-		ret = __driver_rfc4106_encrypt(req);
-		kernel_fpu_end();
-	}
-	return ret;
+	aead_request_set_callback(subreq, req->base.flags,
+				  req->base.complete, req->base.data);
+	aead_request_set_crypt(subreq, req->src, req->dst,
+			       req->cryptlen, req->iv);
+	aead_request_set_ad(subreq, req->assoclen);
+
+	return crypto_aead_encrypt(subreq);
 }
 
 static int rfc4106_decrypt(struct aead_request *req)
 {
-	int ret;
 	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
-	struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm);
+	struct cryptd_aead **ctx = crypto_aead_ctx(tfm);
+	struct cryptd_aead *cryptd_tfm = *ctx;
+	struct aead_request *subreq = aead_request_ctx(req);
 
-	if (!irq_fpu_usable()) {
-		struct aead_request *cryptd_req =
-			(struct aead_request *) aead_request_ctx(req);
+	aead_request_set_tfm(subreq, irq_fpu_usable() ?
+				     cryptd_aead_child(cryptd_tfm) :
+				     &cryptd_tfm->base);
 
-		memcpy(cryptd_req, req, sizeof(*req));
-		aead_request_set_tfm(cryptd_req, &ctx->cryptd_tfm->base);
-		ret = crypto_aead_decrypt(cryptd_req);
-	} else {
-		kernel_fpu_begin();
-		ret = __driver_rfc4106_decrypt(req);
-		kernel_fpu_end();
-	}
-	return ret;
-}
-
-static int helper_rfc4106_encrypt(struct aead_request *req)
-{
-	int ret;
-
-	if (unlikely(!irq_fpu_usable())) {
-		WARN_ONCE(1, "__gcm-aes-aesni alg used in invalid context");
-		ret = -EINVAL;
-	} else {
-		kernel_fpu_begin();
-		ret = __driver_rfc4106_encrypt(req);
-		kernel_fpu_end();
-	}
-	return ret;
-}
-
-static int helper_rfc4106_decrypt(struct aead_request *req)
-{
-	int ret;
+	aead_request_set_callback(subreq, req->base.flags,
+				  req->base.complete, req->base.data);
+	aead_request_set_crypt(subreq, req->src, req->dst,
+			       req->cryptlen, req->iv);
+	aead_request_set_ad(subreq, req->assoclen);
 
-	if (unlikely(!irq_fpu_usable())) {
-		WARN_ONCE(1, "__gcm-aes-aesni alg used in invalid context");
-		ret = -EINVAL;
-	} else {
-		kernel_fpu_begin();
-		ret = __driver_rfc4106_decrypt(req);
-		kernel_fpu_end();
-	}
-	return ret;
+	return crypto_aead_decrypt(subreq);
 }
 #endif
 
@@ -1410,51 +1310,6 @@ static struct crypto_alg aesni_algs[] = { {
 			.geniv		= "chainiv",
 		},
 	},
-}, {
-	.cra_name		= "__gcm-aes-aesni",
-	.cra_driver_name	= "__driver-gcm-aes-aesni",
-	.cra_priority		= 0,
-	.cra_flags		= CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_INTERNAL,
-	.cra_blocksize		= 1,
-	.cra_ctxsize		= sizeof(struct aesni_rfc4106_gcm_ctx) +
-				  AESNI_ALIGN,
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_aead_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.aead = {
-			.setkey		= common_rfc4106_set_key,
-			.setauthsize	= common_rfc4106_set_authsize,
-			.encrypt	= helper_rfc4106_encrypt,
-			.decrypt	= helper_rfc4106_decrypt,
-			.ivsize		= 8,
-			.maxauthsize	= 16,
-		},
-	},
-}, {
-	.cra_name		= "rfc4106(gcm(aes))",
-	.cra_driver_name	= "rfc4106-gcm-aesni",
-	.cra_priority		= 400,
-	.cra_flags		= CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= 1,
-	.cra_ctxsize		= sizeof(struct aesni_rfc4106_gcm_ctx) +
-				  AESNI_ALIGN,
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_nivaead_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= rfc4106_init,
-	.cra_exit		= rfc4106_exit,
-	.cra_u = {
-		.aead = {
-			.setkey		= rfc4106_set_key,
-			.setauthsize	= rfc4106_set_authsize,
-			.encrypt	= rfc4106_encrypt,
-			.decrypt	= rfc4106_decrypt,
-			.geniv		= "seqiv",
-			.ivsize		= 8,
-			.maxauthsize	= 16,
-		},
-	},
 #endif
 #if IS_ENABLED(CONFIG_CRYPTO_PCBC)
 }, {
@@ -1569,6 +1424,46 @@ static struct crypto_alg aesni_algs[] = { {
 	},
 } };
 
+#ifdef CONFIG_X86_64
+static struct aead_alg aesni_aead_algs[] = { {
+	.setkey			= common_rfc4106_set_key,
+	.setauthsize		= common_rfc4106_set_authsize,
+	.encrypt		= helper_rfc4106_encrypt,
+	.decrypt		= helper_rfc4106_decrypt,
+	.ivsize			= 8,
+	.maxauthsize		= 16,
+	.base = {
+		.cra_name		= "__gcm-aes-aesni",
+		.cra_driver_name	= "__driver-gcm-aes-aesni",
+		.cra_flags		= CRYPTO_ALG_INTERNAL,
+		.cra_blocksize		= 1,
+		.cra_ctxsize		= sizeof(struct aesni_rfc4106_gcm_ctx),
+		.cra_alignmask		= AESNI_ALIGN - 1,
+		.cra_module		= THIS_MODULE,
+	},
+}, {
+	.init			= rfc4106_init,
+	.exit			= rfc4106_exit,
+	.setkey			= rfc4106_set_key,
+	.setauthsize		= rfc4106_set_authsize,
+	.encrypt		= rfc4106_encrypt,
+	.decrypt		= rfc4106_decrypt,
+	.ivsize			= 8,
+	.maxauthsize		= 16,
+	.base = {
+		.cra_name		= "rfc4106(gcm(aes))",
+		.cra_driver_name	= "rfc4106-gcm-aesni",
+		.cra_priority		= 400,
+		.cra_flags		= CRYPTO_ALG_ASYNC,
+		.cra_blocksize		= 1,
+		.cra_ctxsize		= sizeof(struct cryptd_aead *),
+		.cra_module		= THIS_MODULE,
+	},
+} };
+#else
+static struct aead_alg aesni_aead_algs[0];
+#endif
+
 
 static const struct x86_cpu_id aesni_cpu_id[] = {
 	X86_FEATURE_MATCH(X86_FEATURE_AES),
@@ -1616,11 +1511,27 @@ static int __init aesni_init(void)
 	if (err)
 		return err;
 
-	return crypto_register_algs(aesni_algs, ARRAY_SIZE(aesni_algs));
+	err = crypto_register_algs(aesni_algs, ARRAY_SIZE(aesni_algs));
+	if (err)
+		goto fpu_exit;
+
+	err = crypto_register_aeads(aesni_aead_algs,
+				    ARRAY_SIZE(aesni_aead_algs));
+	if (err)
+		goto unregister_algs;
+
+	return err;
+
+unregister_algs:
+	crypto_unregister_algs(aesni_algs, ARRAY_SIZE(aesni_algs));
+fpu_exit:
+	crypto_fpu_exit();
+	return err;
 }
 
 static void __exit aesni_exit(void)
 {
+	crypto_unregister_aeads(aesni_aead_algs, ARRAY_SIZE(aesni_aead_algs));
 	crypto_unregister_algs(aesni_algs, ARRAY_SIZE(aesni_algs));
 
 	crypto_fpu_exit();
diff --git a/arch/x86/crypto/camellia_aesni_avx2_glue.c b/arch/x86/crypto/camellia_aesni_avx2_glue.c
index baf0ac21ace5..4c65c70e628b 100644
--- a/arch/x86/crypto/camellia_aesni_avx2_glue.c
+++ b/arch/x86/crypto/camellia_aesni_avx2_glue.c
@@ -19,8 +19,7 @@
 #include <crypto/ctr.h>
 #include <crypto/lrw.h>
 #include <crypto/xts.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
+#include <asm/fpu/api.h>
 #include <asm/crypto/camellia.h>
 #include <asm/crypto/glue_helper.h>
 
@@ -561,16 +560,15 @@ static struct crypto_alg cmll_algs[10] = { {
 
 static int __init camellia_aesni_init(void)
 {
-	u64 xcr0;
+	const char *feature_name;
 
 	if (!cpu_has_avx2 || !cpu_has_avx || !cpu_has_aes || !cpu_has_osxsave) {
 		pr_info("AVX2 or AES-NI instructions are not detected.\n");
 		return -ENODEV;
 	}
 
-	xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
-	if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
-		pr_info("AVX2 detected but unusable.\n");
+	if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) {
+		pr_info("CPU feature '%s' is not supported.\n", feature_name);
 		return -ENODEV;
 	}
 
diff --git a/arch/x86/crypto/camellia_aesni_avx_glue.c b/arch/x86/crypto/camellia_aesni_avx_glue.c
index 78818a1e73e3..80a0e4389c9a 100644
--- a/arch/x86/crypto/camellia_aesni_avx_glue.c
+++ b/arch/x86/crypto/camellia_aesni_avx_glue.c
@@ -19,8 +19,7 @@
 #include <crypto/ctr.h>
 #include <crypto/lrw.h>
 #include <crypto/xts.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
+#include <asm/fpu/api.h>
 #include <asm/crypto/camellia.h>
 #include <asm/crypto/glue_helper.h>
 
@@ -553,16 +552,10 @@ static struct crypto_alg cmll_algs[10] = { {
 
 static int __init camellia_aesni_init(void)
 {
-	u64 xcr0;
+	const char *feature_name;
 
-	if (!cpu_has_avx || !cpu_has_aes || !cpu_has_osxsave) {
-		pr_info("AVX or AES-NI instructions are not detected.\n");
-		return -ENODEV;
-	}
-
-	xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
-	if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
-		pr_info("AVX detected but unusable.\n");
+	if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) {
+		pr_info("CPU feature '%s' is not supported.\n", feature_name);
 		return -ENODEV;
 	}
 
diff --git a/arch/x86/crypto/cast5_avx_glue.c b/arch/x86/crypto/cast5_avx_glue.c
index 236c80974457..be00aa48b2b5 100644
--- a/arch/x86/crypto/cast5_avx_glue.c
+++ b/arch/x86/crypto/cast5_avx_glue.c
@@ -31,8 +31,7 @@
 #include <crypto/cast5.h>
 #include <crypto/cryptd.h>
 #include <crypto/ctr.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
+#include <asm/fpu/api.h>
 #include <asm/crypto/glue_helper.h>
 
 #define CAST5_PARALLEL_BLOCKS 16
@@ -468,16 +467,10 @@ static struct crypto_alg cast5_algs[6] = { {
 
 static int __init cast5_init(void)
 {
-	u64 xcr0;
+	const char *feature_name;
 
-	if (!cpu_has_avx || !cpu_has_osxsave) {
-		pr_info("AVX instructions are not detected.\n");
-		return -ENODEV;
-	}
-
-	xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
-	if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
-		pr_info("AVX detected but unusable.\n");
+	if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) {
+		pr_info("CPU feature '%s' is not supported.\n", feature_name);
 		return -ENODEV;
 	}
 
diff --git a/arch/x86/crypto/cast6_avx_glue.c b/arch/x86/crypto/cast6_avx_glue.c
index f448810ca4ac..5dbba7224221 100644
--- a/arch/x86/crypto/cast6_avx_glue.c
+++ b/arch/x86/crypto/cast6_avx_glue.c
@@ -36,8 +36,7 @@
 #include <crypto/ctr.h>
 #include <crypto/lrw.h>
 #include <crypto/xts.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
+#include <asm/fpu/api.h>
 #include <asm/crypto/glue_helper.h>
 
 #define CAST6_PARALLEL_BLOCKS 8
@@ -590,16 +589,10 @@ static struct crypto_alg cast6_algs[10] = { {
 
 static int __init cast6_init(void)
 {
-	u64 xcr0;
+	const char *feature_name;
 
-	if (!cpu_has_avx || !cpu_has_osxsave) {
-		pr_info("AVX instructions are not detected.\n");
-		return -ENODEV;
-	}
-
-	xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
-	if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
-		pr_info("AVX detected but unusable.\n");
+	if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) {
+		pr_info("CPU feature '%s' is not supported.\n", feature_name);
 		return -ENODEV;
 	}
 
diff --git a/arch/x86/crypto/crc32-pclmul_glue.c b/arch/x86/crypto/crc32-pclmul_glue.c
index 1937fc1d8763..07d2c6c86a54 100644
--- a/arch/x86/crypto/crc32-pclmul_glue.c
+++ b/arch/x86/crypto/crc32-pclmul_glue.c
@@ -35,7 +35,7 @@
 
 #include <asm/cpufeature.h>
 #include <asm/cpu_device_id.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 
 #define CHKSUM_BLOCK_SIZE	1
 #define CHKSUM_DIGEST_SIZE	4
diff --git a/arch/x86/crypto/crc32c-intel_glue.c b/arch/x86/crypto/crc32c-intel_glue.c
index 28640c3d6af7..81a595d75cf5 100644
--- a/arch/x86/crypto/crc32c-intel_glue.c
+++ b/arch/x86/crypto/crc32c-intel_glue.c
@@ -32,8 +32,7 @@
 
 #include <asm/cpufeature.h>
 #include <asm/cpu_device_id.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
 
 #define CHKSUM_BLOCK_SIZE	1
 #define CHKSUM_DIGEST_SIZE	4
diff --git a/arch/x86/crypto/crct10dif-pclmul_glue.c b/arch/x86/crypto/crct10dif-pclmul_glue.c
index b6c67bf30fdf..a3fcfc97a311 100644
--- a/arch/x86/crypto/crct10dif-pclmul_glue.c
+++ b/arch/x86/crypto/crct10dif-pclmul_glue.c
@@ -29,7 +29,7 @@
 #include <linux/init.h>
 #include <linux/string.h>
 #include <linux/kernel.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 #include <asm/cpufeature.h>
 #include <asm/cpu_device_id.h>
 
diff --git a/arch/x86/crypto/fpu.c b/arch/x86/crypto/fpu.c
index f368ba261739..e7d679e2a018 100644
--- a/arch/x86/crypto/fpu.c
+++ b/arch/x86/crypto/fpu.c
@@ -18,7 +18,7 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/crypto.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 
 struct crypto_fpu_ctx {
 	struct crypto_blkcipher *child;
@@ -156,7 +156,7 @@ int __init crypto_fpu_init(void)
 	return crypto_register_template(&crypto_fpu_tmpl);
 }
 
-void __exit crypto_fpu_exit(void)
+void crypto_fpu_exit(void)
 {
 	crypto_unregister_template(&crypto_fpu_tmpl);
 }
diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c
index 2079baf06bdd..64d7cf1b50e1 100644
--- a/arch/x86/crypto/ghash-clmulni-intel_glue.c
+++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c
@@ -19,7 +19,7 @@
 #include <crypto/cryptd.h>
 #include <crypto/gf128mul.h>
 #include <crypto/internal/hash.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 #include <asm/cpu_device_id.h>
 
 #define GHASH_BLOCK_SIZE	16
diff --git a/arch/x86/crypto/serpent_avx2_glue.c b/arch/x86/crypto/serpent_avx2_glue.c
index 2f63dc89e7a9..7d838dc4d888 100644
--- a/arch/x86/crypto/serpent_avx2_glue.c
+++ b/arch/x86/crypto/serpent_avx2_glue.c
@@ -20,8 +20,7 @@
 #include <crypto/lrw.h>
 #include <crypto/xts.h>
 #include <crypto/serpent.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
+#include <asm/fpu/api.h>
 #include <asm/crypto/serpent-avx.h>
 #include <asm/crypto/glue_helper.h>
 
@@ -537,16 +536,14 @@ static struct crypto_alg srp_algs[10] = { {
 
 static int __init init(void)
 {
-	u64 xcr0;
+	const char *feature_name;
 
 	if (!cpu_has_avx2 || !cpu_has_osxsave) {
 		pr_info("AVX2 instructions are not detected.\n");
 		return -ENODEV;
 	}
-
-	xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
-	if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
-		pr_info("AVX detected but unusable.\n");
+	if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) {
+		pr_info("CPU feature '%s' is not supported.\n", feature_name);
 		return -ENODEV;
 	}
 
diff --git a/arch/x86/crypto/serpent_avx_glue.c b/arch/x86/crypto/serpent_avx_glue.c
index c8d478af8456..da7dafc9b16d 100644
--- a/arch/x86/crypto/serpent_avx_glue.c
+++ b/arch/x86/crypto/serpent_avx_glue.c
@@ -36,8 +36,7 @@
 #include <crypto/ctr.h>
 #include <crypto/lrw.h>
 #include <crypto/xts.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
+#include <asm/fpu/api.h>
 #include <asm/crypto/serpent-avx.h>
 #include <asm/crypto/glue_helper.h>
 
@@ -596,16 +595,10 @@ static struct crypto_alg serpent_algs[10] = { {
 
 static int __init serpent_init(void)
 {
-	u64 xcr0;
+	const char *feature_name;
 
-	if (!cpu_has_avx || !cpu_has_osxsave) {
-		printk(KERN_INFO "AVX instructions are not detected.\n");
-		return -ENODEV;
-	}
-
-	xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
-	if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
-		printk(KERN_INFO "AVX detected but unusable.\n");
+	if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) {
+		pr_info("CPU feature '%s' is not supported.\n", feature_name);
 		return -ENODEV;
 	}
 
diff --git a/arch/x86/crypto/sha-mb/sha1_mb.c b/arch/x86/crypto/sha-mb/sha1_mb.c
index e510b1c5d690..a841e9765bd6 100644
--- a/arch/x86/crypto/sha-mb/sha1_mb.c
+++ b/arch/x86/crypto/sha-mb/sha1_mb.c
@@ -65,11 +65,8 @@
 #include <crypto/mcryptd.h>
 #include <crypto/crypto_wq.h>
 #include <asm/byteorder.h>
-#include <asm/i387.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
 #include <linux/hardirq.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/api.h>
 #include "sha_mb_ctx.h"
 
 #define FLUSH_INTERVAL 1000 /* in usec */
@@ -885,7 +882,8 @@ static int __init sha1_mb_mod_init(void)
 		INIT_DELAYED_WORK(&cpu_state->flush, mcryptd_flusher);
 		cpu_state->cpu = cpu;
 		cpu_state->alg_state = &sha1_mb_alg_state;
-		cpu_state->mgr = (struct sha1_ctx_mgr *) kzalloc(sizeof(struct sha1_ctx_mgr), GFP_KERNEL);
+		cpu_state->mgr = kzalloc(sizeof(struct sha1_ctx_mgr),
+					GFP_KERNEL);
 		if (!cpu_state->mgr)
 			goto err2;
 		sha1_ctx_mgr_init(cpu_state->mgr);
diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c
index 33d1b9dc14cc..7c48e8b20848 100644
--- a/arch/x86/crypto/sha1_ssse3_glue.c
+++ b/arch/x86/crypto/sha1_ssse3_glue.c
@@ -29,9 +29,7 @@
 #include <linux/types.h>
 #include <crypto/sha.h>
 #include <crypto/sha1_base.h>
-#include <asm/i387.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
+#include <asm/fpu/api.h>
 
 
 asmlinkage void sha1_transform_ssse3(u32 *digest, const char *data,
@@ -123,15 +121,9 @@ static struct shash_alg alg = {
 #ifdef CONFIG_AS_AVX
 static bool __init avx_usable(void)
 {
-	u64 xcr0;
-
-	if (!cpu_has_avx || !cpu_has_osxsave)
-		return false;
-
-	xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
-	if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
-		pr_info("AVX detected but unusable.\n");
-
+	if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, NULL)) {
+		if (cpu_has_avx)
+			pr_info("AVX detected but unusable.\n");
 		return false;
 	}
 
diff --git a/arch/x86/crypto/sha256_ssse3_glue.c b/arch/x86/crypto/sha256_ssse3_glue.c
index ccc338881ee8..f8097fc0d1d1 100644
--- a/arch/x86/crypto/sha256_ssse3_glue.c
+++ b/arch/x86/crypto/sha256_ssse3_glue.c
@@ -37,9 +37,7 @@
 #include <linux/types.h>
 #include <crypto/sha.h>
 #include <crypto/sha256_base.h>
-#include <asm/i387.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
+#include <asm/fpu/api.h>
 #include <linux/string.h>
 
 asmlinkage void sha256_transform_ssse3(u32 *digest, const char *data,
@@ -132,15 +130,9 @@ static struct shash_alg algs[] = { {
 #ifdef CONFIG_AS_AVX
 static bool __init avx_usable(void)
 {
-	u64 xcr0;
-
-	if (!cpu_has_avx || !cpu_has_osxsave)
-		return false;
-
-	xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
-	if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
-		pr_info("AVX detected but unusable.\n");
-
+	if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, NULL)) {
+		if (cpu_has_avx)
+			pr_info("AVX detected but unusable.\n");
 		return false;
 	}
 
diff --git a/arch/x86/crypto/sha512_ssse3_glue.c b/arch/x86/crypto/sha512_ssse3_glue.c
index d9fa4c1e063f..2edad7b81870 100644
--- a/arch/x86/crypto/sha512_ssse3_glue.c
+++ b/arch/x86/crypto/sha512_ssse3_glue.c
@@ -35,9 +35,7 @@
 #include <linux/types.h>
 #include <crypto/sha.h>
 #include <crypto/sha512_base.h>
-#include <asm/i387.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
+#include <asm/fpu/api.h>
 
 #include <linux/string.h>
 
@@ -131,15 +129,9 @@ static struct shash_alg algs[] = { {
 #ifdef CONFIG_AS_AVX
 static bool __init avx_usable(void)
 {
-	u64 xcr0;
-
-	if (!cpu_has_avx || !cpu_has_osxsave)
-		return false;
-
-	xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
-	if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
-		pr_info("AVX detected but unusable.\n");
-
+	if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, NULL)) {
+		if (cpu_has_avx)
+			pr_info("AVX detected but unusable.\n");
 		return false;
 	}
 
diff --git a/arch/x86/crypto/twofish_avx_glue.c b/arch/x86/crypto/twofish_avx_glue.c
index b5e2d5651851..c2bd0ce718ee 100644
--- a/arch/x86/crypto/twofish_avx_glue.c
+++ b/arch/x86/crypto/twofish_avx_glue.c
@@ -36,9 +36,7 @@
 #include <crypto/ctr.h>
 #include <crypto/lrw.h>
 #include <crypto/xts.h>
-#include <asm/i387.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
+#include <asm/fpu/api.h>
 #include <asm/crypto/twofish.h>
 #include <asm/crypto/glue_helper.h>
 #include <crypto/scatterwalk.h>
@@ -558,16 +556,10 @@ static struct crypto_alg twofish_algs[10] = { {
 
 static int __init twofish_init(void)
 {
-	u64 xcr0;
+	const char *feature_name;
 
-	if (!cpu_has_avx || !cpu_has_osxsave) {
-		printk(KERN_INFO "AVX instructions are not detected.\n");
-		return -ENODEV;
-	}
-
-	xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
-	if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
-		printk(KERN_INFO "AVX detected but unusable.\n");
+	if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) {
+		pr_info("CPU feature '%s' is not supported.\n", feature_name);
 		return -ENODEV;
 	}
 
diff --git a/arch/x86/entry/Makefile b/arch/x86/entry/Makefile
new file mode 100644
index 000000000000..7a144971db79
--- /dev/null
+++ b/arch/x86/entry/Makefile
@@ -0,0 +1,10 @@
+#
+# Makefile for the x86 low level entry code
+#
+obj-y				:= entry_$(BITS).o thunk_$(BITS).o syscall_$(BITS).o
+
+obj-y				+= vdso/
+obj-y				+= vsyscall/
+
+obj-$(CONFIG_IA32_EMULATION)	+= entry_64_compat.o syscall_32.o
+
diff --git a/arch/x86/include/asm/calling.h b/arch/x86/entry/calling.h
index 1c8b50edb2db..f4e6308c4200 100644
--- a/arch/x86/include/asm/calling.h
+++ b/arch/x86/entry/calling.h
@@ -46,8 +46,6 @@ For 32-bit we have the following conventions - kernel is built with
 
 */
 
-#include <asm/dwarf2.h>
-
 #ifdef CONFIG_X86_64
 
 /*
@@ -91,28 +89,27 @@ For 32-bit we have the following conventions - kernel is built with
 #define SIZEOF_PTREGS	21*8
 
 	.macro ALLOC_PT_GPREGS_ON_STACK addskip=0
-	subq	$15*8+\addskip, %rsp
-	CFI_ADJUST_CFA_OFFSET 15*8+\addskip
+	addq	$-(15*8+\addskip), %rsp
 	.endm
 
 	.macro SAVE_C_REGS_HELPER offset=0 rax=1 rcx=1 r8910=1 r11=1
 	.if \r11
-	movq_cfi r11, 6*8+\offset
+	movq %r11, 6*8+\offset(%rsp)
 	.endif
 	.if \r8910
-	movq_cfi r10, 7*8+\offset
-	movq_cfi r9,  8*8+\offset
-	movq_cfi r8,  9*8+\offset
+	movq %r10, 7*8+\offset(%rsp)
+	movq %r9,  8*8+\offset(%rsp)
+	movq %r8,  9*8+\offset(%rsp)
 	.endif
 	.if \rax
-	movq_cfi rax, 10*8+\offset
+	movq %rax, 10*8+\offset(%rsp)
 	.endif
 	.if \rcx
-	movq_cfi rcx, 11*8+\offset
+	movq %rcx, 11*8+\offset(%rsp)
 	.endif
-	movq_cfi rdx, 12*8+\offset
-	movq_cfi rsi, 13*8+\offset
-	movq_cfi rdi, 14*8+\offset
+	movq %rdx, 12*8+\offset(%rsp)
+	movq %rsi, 13*8+\offset(%rsp)
+	movq %rdi, 14*8+\offset(%rsp)
 	.endm
 	.macro SAVE_C_REGS offset=0
 	SAVE_C_REGS_HELPER \offset, 1, 1, 1, 1
@@ -131,24 +128,24 @@ For 32-bit we have the following conventions - kernel is built with
 	.endm
 
 	.macro SAVE_EXTRA_REGS offset=0
-	movq_cfi r15, 0*8+\offset
-	movq_cfi r14, 1*8+\offset
-	movq_cfi r13, 2*8+\offset
-	movq_cfi r12, 3*8+\offset
-	movq_cfi rbp, 4*8+\offset
-	movq_cfi rbx, 5*8+\offset
+	movq %r15, 0*8+\offset(%rsp)
+	movq %r14, 1*8+\offset(%rsp)
+	movq %r13, 2*8+\offset(%rsp)
+	movq %r12, 3*8+\offset(%rsp)
+	movq %rbp, 4*8+\offset(%rsp)
+	movq %rbx, 5*8+\offset(%rsp)
 	.endm
 	.macro SAVE_EXTRA_REGS_RBP offset=0
-	movq_cfi rbp, 4*8+\offset
+	movq %rbp, 4*8+\offset(%rsp)
 	.endm
 
 	.macro RESTORE_EXTRA_REGS offset=0
-	movq_cfi_restore 0*8+\offset, r15
-	movq_cfi_restore 1*8+\offset, r14
-	movq_cfi_restore 2*8+\offset, r13
-	movq_cfi_restore 3*8+\offset, r12
-	movq_cfi_restore 4*8+\offset, rbp
-	movq_cfi_restore 5*8+\offset, rbx
+	movq 0*8+\offset(%rsp), %r15
+	movq 1*8+\offset(%rsp), %r14
+	movq 2*8+\offset(%rsp), %r13
+	movq 3*8+\offset(%rsp), %r12
+	movq 4*8+\offset(%rsp), %rbp
+	movq 5*8+\offset(%rsp), %rbx
 	.endm
 
 	.macro ZERO_EXTRA_REGS
@@ -162,24 +159,24 @@ For 32-bit we have the following conventions - kernel is built with
 
 	.macro RESTORE_C_REGS_HELPER rstor_rax=1, rstor_rcx=1, rstor_r11=1, rstor_r8910=1, rstor_rdx=1
 	.if \rstor_r11
-	movq_cfi_restore 6*8, r11
+	movq 6*8(%rsp), %r11
 	.endif
 	.if \rstor_r8910
-	movq_cfi_restore 7*8, r10
-	movq_cfi_restore 8*8, r9
-	movq_cfi_restore 9*8, r8
+	movq 7*8(%rsp), %r10
+	movq 8*8(%rsp), %r9
+	movq 9*8(%rsp), %r8
 	.endif
 	.if \rstor_rax
-	movq_cfi_restore 10*8, rax
+	movq 10*8(%rsp), %rax
 	.endif
 	.if \rstor_rcx
-	movq_cfi_restore 11*8, rcx
+	movq 11*8(%rsp), %rcx
 	.endif
 	.if \rstor_rdx
-	movq_cfi_restore 12*8, rdx
+	movq 12*8(%rsp), %rdx
 	.endif
-	movq_cfi_restore 13*8, rsi
-	movq_cfi_restore 14*8, rdi
+	movq 13*8(%rsp), %rsi
+	movq 14*8(%rsp), %rdi
 	.endm
 	.macro RESTORE_C_REGS
 	RESTORE_C_REGS_HELPER 1,1,1,1,1
@@ -204,8 +201,7 @@ For 32-bit we have the following conventions - kernel is built with
 	.endm
 
 	.macro REMOVE_PT_GPREGS_FROM_STACK addskip=0
-	addq $15*8+\addskip, %rsp
-	CFI_ADJUST_CFA_OFFSET -(15*8+\addskip)
+	subq $-(15*8+\addskip), %rsp
 	.endm
 
 	.macro icebp
@@ -224,23 +220,23 @@ For 32-bit we have the following conventions - kernel is built with
  */
 
 	.macro SAVE_ALL
-	pushl_cfi_reg eax
-	pushl_cfi_reg ebp
-	pushl_cfi_reg edi
-	pushl_cfi_reg esi
-	pushl_cfi_reg edx
-	pushl_cfi_reg ecx
-	pushl_cfi_reg ebx
+	pushl %eax
+	pushl %ebp
+	pushl %edi
+	pushl %esi
+	pushl %edx
+	pushl %ecx
+	pushl %ebx
 	.endm
 
 	.macro RESTORE_ALL
-	popl_cfi_reg ebx
-	popl_cfi_reg ecx
-	popl_cfi_reg edx
-	popl_cfi_reg esi
-	popl_cfi_reg edi
-	popl_cfi_reg ebp
-	popl_cfi_reg eax
+	popl %ebx
+	popl %ecx
+	popl %edx
+	popl %esi
+	popl %edi
+	popl %ebp
+	popl %eax
 	.endm
 
 #endif /* CONFIG_X86_64 */
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
new file mode 100644
index 000000000000..21dc60a60b5f
--- /dev/null
+++ b/arch/x86/entry/entry_32.S
@@ -0,0 +1,1248 @@
+/*
+ *  Copyright (C) 1991,1992  Linus Torvalds
+ *
+ * entry_32.S contains the system-call and low-level fault and trap handling routines.
+ *
+ * Stack layout in 'syscall_exit':
+ *	ptrace needs to have all registers on the stack.
+ *	If the order here is changed, it needs to be
+ *	updated in fork.c:copy_process(), signal.c:do_signal(),
+ *	ptrace.c and ptrace.h
+ *
+ *	 0(%esp) - %ebx
+ *	 4(%esp) - %ecx
+ *	 8(%esp) - %edx
+ *	 C(%esp) - %esi
+ *	10(%esp) - %edi
+ *	14(%esp) - %ebp
+ *	18(%esp) - %eax
+ *	1C(%esp) - %ds
+ *	20(%esp) - %es
+ *	24(%esp) - %fs
+ *	28(%esp) - %gs		saved iff !CONFIG_X86_32_LAZY_GS
+ *	2C(%esp) - orig_eax
+ *	30(%esp) - %eip
+ *	34(%esp) - %cs
+ *	38(%esp) - %eflags
+ *	3C(%esp) - %oldesp
+ *	40(%esp) - %oldss
+ */
+
+#include <linux/linkage.h>
+#include <linux/err.h>
+#include <asm/thread_info.h>
+#include <asm/irqflags.h>
+#include <asm/errno.h>
+#include <asm/segment.h>
+#include <asm/smp.h>
+#include <asm/page_types.h>
+#include <asm/percpu.h>
+#include <asm/processor-flags.h>
+#include <asm/ftrace.h>
+#include <asm/irq_vectors.h>
+#include <asm/cpufeature.h>
+#include <asm/alternative-asm.h>
+#include <asm/asm.h>
+#include <asm/smap.h>
+
+/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this.  */
+#include <linux/elf-em.h>
+#define AUDIT_ARCH_I386		(EM_386|__AUDIT_ARCH_LE)
+#define __AUDIT_ARCH_LE		0x40000000
+
+#ifndef CONFIG_AUDITSYSCALL
+# define sysenter_audit		syscall_trace_entry
+# define sysexit_audit		syscall_exit_work
+#endif
+
+	.section .entry.text, "ax"
+
+/*
+ * We use macros for low-level operations which need to be overridden
+ * for paravirtualization.  The following will never clobber any registers:
+ *   INTERRUPT_RETURN (aka. "iret")
+ *   GET_CR0_INTO_EAX (aka. "movl %cr0, %eax")
+ *   ENABLE_INTERRUPTS_SYSEXIT (aka "sti; sysexit").
+ *
+ * For DISABLE_INTERRUPTS/ENABLE_INTERRUPTS (aka "cli"/"sti"), you must
+ * specify what registers can be overwritten (CLBR_NONE, CLBR_EAX/EDX/ECX/ANY).
+ * Allowing a register to be clobbered can shrink the paravirt replacement
+ * enough to patch inline, increasing performance.
+ */
+
+#ifdef CONFIG_PREEMPT
+# define preempt_stop(clobbers)	DISABLE_INTERRUPTS(clobbers); TRACE_IRQS_OFF
+#else
+# define preempt_stop(clobbers)
+# define resume_kernel		restore_all
+#endif
+
+.macro TRACE_IRQS_IRET
+#ifdef CONFIG_TRACE_IRQFLAGS
+	testl	$X86_EFLAGS_IF, PT_EFLAGS(%esp)     # interrupts off?
+	jz	1f
+	TRACE_IRQS_ON
+1:
+#endif
+.endm
+
+/*
+ * User gs save/restore
+ *
+ * %gs is used for userland TLS and kernel only uses it for stack
+ * canary which is required to be at %gs:20 by gcc.  Read the comment
+ * at the top of stackprotector.h for more info.
+ *
+ * Local labels 98 and 99 are used.
+ */
+#ifdef CONFIG_X86_32_LAZY_GS
+
+ /* unfortunately push/pop can't be no-op */
+.macro PUSH_GS
+	pushl	$0
+.endm
+.macro POP_GS pop=0
+	addl	$(4 + \pop), %esp
+.endm
+.macro POP_GS_EX
+.endm
+
+ /* all the rest are no-op */
+.macro PTGS_TO_GS
+.endm
+.macro PTGS_TO_GS_EX
+.endm
+.macro GS_TO_REG reg
+.endm
+.macro REG_TO_PTGS reg
+.endm
+.macro SET_KERNEL_GS reg
+.endm
+
+#else	/* CONFIG_X86_32_LAZY_GS */
+
+.macro PUSH_GS
+	pushl	%gs
+.endm
+
+.macro POP_GS pop=0
+98:	popl	%gs
+  .if \pop <> 0
+	add	$\pop, %esp
+  .endif
+.endm
+.macro POP_GS_EX
+.pushsection .fixup, "ax"
+99:	movl	$0, (%esp)
+	jmp	98b
+.popsection
+	_ASM_EXTABLE(98b, 99b)
+.endm
+
+.macro PTGS_TO_GS
+98:	mov	PT_GS(%esp), %gs
+.endm
+.macro PTGS_TO_GS_EX
+.pushsection .fixup, "ax"
+99:	movl	$0, PT_GS(%esp)
+	jmp	98b
+.popsection
+	_ASM_EXTABLE(98b, 99b)
+.endm
+
+.macro GS_TO_REG reg
+	movl	%gs, \reg
+.endm
+.macro REG_TO_PTGS reg
+	movl	\reg, PT_GS(%esp)
+.endm
+.macro SET_KERNEL_GS reg
+	movl	$(__KERNEL_STACK_CANARY), \reg
+	movl	\reg, %gs
+.endm
+
+#endif /* CONFIG_X86_32_LAZY_GS */
+
+.macro SAVE_ALL
+	cld
+	PUSH_GS
+	pushl	%fs
+	pushl	%es
+	pushl	%ds
+	pushl	%eax
+	pushl	%ebp
+	pushl	%edi
+	pushl	%esi
+	pushl	%edx
+	pushl	%ecx
+	pushl	%ebx
+	movl	$(__USER_DS), %edx
+	movl	%edx, %ds
+	movl	%edx, %es
+	movl	$(__KERNEL_PERCPU), %edx
+	movl	%edx, %fs
+	SET_KERNEL_GS %edx
+.endm
+
+.macro RESTORE_INT_REGS
+	popl	%ebx
+	popl	%ecx
+	popl	%edx
+	popl	%esi
+	popl	%edi
+	popl	%ebp
+	popl	%eax
+.endm
+
+.macro RESTORE_REGS pop=0
+	RESTORE_INT_REGS
+1:	popl	%ds
+2:	popl	%es
+3:	popl	%fs
+	POP_GS \pop
+.pushsection .fixup, "ax"
+4:	movl	$0, (%esp)
+	jmp	1b
+5:	movl	$0, (%esp)
+	jmp	2b
+6:	movl	$0, (%esp)
+	jmp	3b
+.popsection
+	_ASM_EXTABLE(1b, 4b)
+	_ASM_EXTABLE(2b, 5b)
+	_ASM_EXTABLE(3b, 6b)
+	POP_GS_EX
+.endm
+
+ENTRY(ret_from_fork)
+	pushl	%eax
+	call	schedule_tail
+	GET_THREAD_INFO(%ebp)
+	popl	%eax
+	pushl	$0x0202				# Reset kernel eflags
+	popfl
+	jmp	syscall_exit
+END(ret_from_fork)
+
+ENTRY(ret_from_kernel_thread)
+	pushl	%eax
+	call	schedule_tail
+	GET_THREAD_INFO(%ebp)
+	popl	%eax
+	pushl	$0x0202				# Reset kernel eflags
+	popfl
+	movl	PT_EBP(%esp), %eax
+	call	*PT_EBX(%esp)
+	movl	$0, PT_EAX(%esp)
+	jmp	syscall_exit
+ENDPROC(ret_from_kernel_thread)
+
+/*
+ * Return to user mode is not as complex as all this looks,
+ * but we want the default path for a system call return to
+ * go as quickly as possible which is why some of this is
+ * less clear than it otherwise should be.
+ */
+
+	# userspace resumption stub bypassing syscall exit tracing
+	ALIGN
+ret_from_exception:
+	preempt_stop(CLBR_ANY)
+ret_from_intr:
+	GET_THREAD_INFO(%ebp)
+#ifdef CONFIG_VM86
+	movl	PT_EFLAGS(%esp), %eax		# mix EFLAGS and CS
+	movb	PT_CS(%esp), %al
+	andl	$(X86_EFLAGS_VM | SEGMENT_RPL_MASK), %eax
+#else
+	/*
+	 * We can be coming here from child spawned by kernel_thread().
+	 */
+	movl	PT_CS(%esp), %eax
+	andl	$SEGMENT_RPL_MASK, %eax
+#endif
+	cmpl	$USER_RPL, %eax
+	jb	resume_kernel			# not returning to v8086 or userspace
+
+ENTRY(resume_userspace)
+	LOCKDEP_SYS_EXIT
+	DISABLE_INTERRUPTS(CLBR_ANY)		# make sure we don't miss an interrupt
+						# setting need_resched or sigpending
+						# between sampling and the iret
+	TRACE_IRQS_OFF
+	movl	TI_flags(%ebp), %ecx
+	andl	$_TIF_WORK_MASK, %ecx		# is there any work to be done on
+						# int/exception return?
+	jne	work_pending
+	jmp	restore_all
+END(ret_from_exception)
+
+#ifdef CONFIG_PREEMPT
+ENTRY(resume_kernel)
+	DISABLE_INTERRUPTS(CLBR_ANY)
+need_resched:
+	cmpl	$0, PER_CPU_VAR(__preempt_count)
+	jnz	restore_all
+	testl	$X86_EFLAGS_IF, PT_EFLAGS(%esp)	# interrupts off (exception path) ?
+	jz	restore_all
+	call	preempt_schedule_irq
+	jmp	need_resched
+END(resume_kernel)
+#endif
+
+/*
+ * SYSENTER_RETURN points to after the SYSENTER instruction
+ * in the vsyscall page.  See vsyscall-sysentry.S, which defines
+ * the symbol.
+ */
+
+	# SYSENTER  call handler stub
+ENTRY(entry_SYSENTER_32)
+	movl	TSS_sysenter_sp0(%esp), %esp
+sysenter_past_esp:
+	/*
+	 * Interrupts are disabled here, but we can't trace it until
+	 * enough kernel state to call TRACE_IRQS_OFF can be called - but
+	 * we immediately enable interrupts at that point anyway.
+	 */
+	pushl	$__USER_DS
+	pushl	%ebp
+	pushfl
+	orl	$X86_EFLAGS_IF, (%esp)
+	pushl	$__USER_CS
+	/*
+	 * Push current_thread_info()->sysenter_return to the stack.
+	 * A tiny bit of offset fixup is necessary: TI_sysenter_return
+	 * is relative to thread_info, which is at the bottom of the
+	 * kernel stack page.  4*4 means the 4 words pushed above;
+	 * TOP_OF_KERNEL_STACK_PADDING takes us to the top of the stack;
+	 * and THREAD_SIZE takes us to the bottom.
+	 */
+	pushl	((TI_sysenter_return) - THREAD_SIZE + TOP_OF_KERNEL_STACK_PADDING + 4*4)(%esp)
+
+	pushl	%eax
+	SAVE_ALL
+	ENABLE_INTERRUPTS(CLBR_NONE)
+
+/*
+ * Load the potential sixth argument from user stack.
+ * Careful about security.
+ */
+	cmpl	$__PAGE_OFFSET-3, %ebp
+	jae	syscall_fault
+	ASM_STAC
+1:	movl	(%ebp), %ebp
+	ASM_CLAC
+	movl	%ebp, PT_EBP(%esp)
+	_ASM_EXTABLE(1b, syscall_fault)
+
+	GET_THREAD_INFO(%ebp)
+
+	testl	$_TIF_WORK_SYSCALL_ENTRY, TI_flags(%ebp)
+	jnz	sysenter_audit
+sysenter_do_call:
+	cmpl	$(NR_syscalls), %eax
+	jae	sysenter_badsys
+	call	*sys_call_table(, %eax, 4)
+sysenter_after_call:
+	movl	%eax, PT_EAX(%esp)
+	LOCKDEP_SYS_EXIT
+	DISABLE_INTERRUPTS(CLBR_ANY)
+	TRACE_IRQS_OFF
+	movl	TI_flags(%ebp), %ecx
+	testl	$_TIF_ALLWORK_MASK, %ecx
+	jnz	sysexit_audit
+sysenter_exit:
+/* if something modifies registers it must also disable sysexit */
+	movl	PT_EIP(%esp), %edx
+	movl	PT_OLDESP(%esp), %ecx
+	xorl	%ebp, %ebp
+	TRACE_IRQS_ON
+1:	mov	PT_FS(%esp), %fs
+	PTGS_TO_GS
+	ENABLE_INTERRUPTS_SYSEXIT
+
+#ifdef CONFIG_AUDITSYSCALL
+sysenter_audit:
+	testl	$(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT), TI_flags(%ebp)
+	jnz	syscall_trace_entry
+	/* movl	PT_EAX(%esp), %eax already set, syscall number: 1st arg to audit */
+	movl	PT_EBX(%esp), %edx		/* ebx/a0: 2nd arg to audit */
+	/* movl	PT_ECX(%esp), %ecx already set, a1: 3nd arg to audit */
+	pushl	PT_ESI(%esp)			/* a3: 5th arg */
+	pushl	PT_EDX+4(%esp)			/* a2: 4th arg */
+	call	__audit_syscall_entry
+	popl	%ecx				/* get that remapped edx off the stack */
+	popl	%ecx				/* get that remapped esi off the stack */
+	movl	PT_EAX(%esp), %eax		/* reload syscall number */
+	jmp	sysenter_do_call
+
+sysexit_audit:
+	testl	$(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %ecx
+	jnz	syscall_exit_work
+	TRACE_IRQS_ON
+	ENABLE_INTERRUPTS(CLBR_ANY)
+	movl	%eax, %edx			/* second arg, syscall return value */
+	cmpl	$-MAX_ERRNO, %eax		/* is it an error ? */
+	setbe %al				/* 1 if so, 0 if not */
+	movzbl %al, %eax			/* zero-extend that */
+	call	__audit_syscall_exit
+	DISABLE_INTERRUPTS(CLBR_ANY)
+	TRACE_IRQS_OFF
+	movl	TI_flags(%ebp), %ecx
+	testl	$(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %ecx
+	jnz	syscall_exit_work
+	movl	PT_EAX(%esp), %eax		/* reload syscall return value */
+	jmp	sysenter_exit
+#endif
+
+.pushsection .fixup, "ax"
+2:	movl	$0, PT_FS(%esp)
+	jmp	1b
+.popsection
+	_ASM_EXTABLE(1b, 2b)
+	PTGS_TO_GS_EX
+ENDPROC(entry_SYSENTER_32)
+
+	# system call handler stub
+ENTRY(entry_INT80_32)
+	ASM_CLAC
+	pushl	%eax				# save orig_eax
+	SAVE_ALL
+	GET_THREAD_INFO(%ebp)
+						# system call tracing in operation / emulation
+	testl	$_TIF_WORK_SYSCALL_ENTRY, TI_flags(%ebp)
+	jnz	syscall_trace_entry
+	cmpl	$(NR_syscalls), %eax
+	jae	syscall_badsys
+syscall_call:
+	call	*sys_call_table(, %eax, 4)
+syscall_after_call:
+	movl	%eax, PT_EAX(%esp)		# store the return value
+syscall_exit:
+	LOCKDEP_SYS_EXIT
+	DISABLE_INTERRUPTS(CLBR_ANY)		# make sure we don't miss an interrupt
+						# setting need_resched or sigpending
+						# between sampling and the iret
+	TRACE_IRQS_OFF
+	movl	TI_flags(%ebp), %ecx
+	testl	$_TIF_ALLWORK_MASK, %ecx	# current->work
+	jnz	syscall_exit_work
+
+restore_all:
+	TRACE_IRQS_IRET
+restore_all_notrace:
+#ifdef CONFIG_X86_ESPFIX32
+	movl	PT_EFLAGS(%esp), %eax		# mix EFLAGS, SS and CS
+	/*
+	 * Warning: PT_OLDSS(%esp) contains the wrong/random values if we
+	 * are returning to the kernel.
+	 * See comments in process.c:copy_thread() for details.
+	 */
+	movb	PT_OLDSS(%esp), %ah
+	movb	PT_CS(%esp), %al
+	andl	$(X86_EFLAGS_VM | (SEGMENT_TI_MASK << 8) | SEGMENT_RPL_MASK), %eax
+	cmpl	$((SEGMENT_LDT << 8) | USER_RPL), %eax
+	je ldt_ss				# returning to user-space with LDT SS
+#endif
+restore_nocheck:
+	RESTORE_REGS 4				# skip orig_eax/error_code
+irq_return:
+	INTERRUPT_RETURN
+.section .fixup, "ax"
+ENTRY(iret_exc	)
+	pushl	$0				# no error code
+	pushl	$do_iret_error
+	jmp	error_code
+.previous
+	_ASM_EXTABLE(irq_return, iret_exc)
+
+#ifdef CONFIG_X86_ESPFIX32
+ldt_ss:
+#ifdef CONFIG_PARAVIRT
+	/*
+	 * The kernel can't run on a non-flat stack if paravirt mode
+	 * is active.  Rather than try to fixup the high bits of
+	 * ESP, bypass this code entirely.  This may break DOSemu
+	 * and/or Wine support in a paravirt VM, although the option
+	 * is still available to implement the setting of the high
+	 * 16-bits in the INTERRUPT_RETURN paravirt-op.
+	 */
+	cmpl	$0, pv_info+PARAVIRT_enabled
+	jne	restore_nocheck
+#endif
+
+/*
+ * Setup and switch to ESPFIX stack
+ *
+ * We're returning to userspace with a 16 bit stack. The CPU will not
+ * restore the high word of ESP for us on executing iret... This is an
+ * "official" bug of all the x86-compatible CPUs, which we can work
+ * around to make dosemu and wine happy. We do this by preloading the
+ * high word of ESP with the high word of the userspace ESP while
+ * compensating for the offset by changing to the ESPFIX segment with
+ * a base address that matches for the difference.
+ */
+#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page) + (GDT_ENTRY_ESPFIX_SS * 8)
+	mov	%esp, %edx			/* load kernel esp */
+	mov	PT_OLDESP(%esp), %eax		/* load userspace esp */
+	mov	%dx, %ax			/* eax: new kernel esp */
+	sub	%eax, %edx			/* offset (low word is 0) */
+	shr	$16, %edx
+	mov	%dl, GDT_ESPFIX_SS + 4		/* bits 16..23 */
+	mov	%dh, GDT_ESPFIX_SS + 7		/* bits 24..31 */
+	pushl	$__ESPFIX_SS
+	pushl	%eax				/* new kernel esp */
+	/*
+	 * Disable interrupts, but do not irqtrace this section: we
+	 * will soon execute iret and the tracer was already set to
+	 * the irqstate after the IRET:
+	 */
+	DISABLE_INTERRUPTS(CLBR_EAX)
+	lss	(%esp), %esp			/* switch to espfix segment */
+	jmp	restore_nocheck
+#endif
+ENDPROC(entry_INT80_32)
+
+	# perform work that needs to be done immediately before resumption
+	ALIGN
+work_pending:
+	testb	$_TIF_NEED_RESCHED, %cl
+	jz	work_notifysig
+work_resched:
+	call	schedule
+	LOCKDEP_SYS_EXIT
+	DISABLE_INTERRUPTS(CLBR_ANY)		# make sure we don't miss an interrupt
+						# setting need_resched or sigpending
+						# between sampling and the iret
+	TRACE_IRQS_OFF
+	movl	TI_flags(%ebp), %ecx
+	andl	$_TIF_WORK_MASK, %ecx		# is there any work to be done other
+						# than syscall tracing?
+	jz	restore_all
+	testb	$_TIF_NEED_RESCHED, %cl
+	jnz	work_resched
+
+work_notifysig:					# deal with pending signals and
+						# notify-resume requests
+#ifdef CONFIG_VM86
+	testl	$X86_EFLAGS_VM, PT_EFLAGS(%esp)
+	movl	%esp, %eax
+	jnz	work_notifysig_v86		# returning to kernel-space or
+						# vm86-space
+1:
+#else
+	movl	%esp, %eax
+#endif
+	TRACE_IRQS_ON
+	ENABLE_INTERRUPTS(CLBR_NONE)
+	movb	PT_CS(%esp), %bl
+	andb	$SEGMENT_RPL_MASK, %bl
+	cmpb	$USER_RPL, %bl
+	jb	resume_kernel
+	xorl	%edx, %edx
+	call	do_notify_resume
+	jmp	resume_userspace
+
+#ifdef CONFIG_VM86
+	ALIGN
+work_notifysig_v86:
+	pushl	%ecx				# save ti_flags for do_notify_resume
+	call	save_v86_state			# %eax contains pt_regs pointer
+	popl	%ecx
+	movl	%eax, %esp
+	jmp	1b
+#endif
+END(work_pending)
+
+	# perform syscall exit tracing
+	ALIGN
+syscall_trace_entry:
+	movl	$-ENOSYS, PT_EAX(%esp)
+	movl	%esp, %eax
+	call	syscall_trace_enter
+	/* What it returned is what we'll actually use.  */
+	cmpl	$(NR_syscalls), %eax
+	jnae	syscall_call
+	jmp	syscall_exit
+END(syscall_trace_entry)
+
+	# perform syscall exit tracing
+	ALIGN
+syscall_exit_work:
+	testl	$_TIF_WORK_SYSCALL_EXIT, %ecx
+	jz	work_pending
+	TRACE_IRQS_ON
+	ENABLE_INTERRUPTS(CLBR_ANY)		# could let syscall_trace_leave() call
+						# schedule() instead
+	movl	%esp, %eax
+	call	syscall_trace_leave
+	jmp	resume_userspace
+END(syscall_exit_work)
+
+syscall_fault:
+	ASM_CLAC
+	GET_THREAD_INFO(%ebp)
+	movl	$-EFAULT, PT_EAX(%esp)
+	jmp	resume_userspace
+END(syscall_fault)
+
+syscall_badsys:
+	movl	$-ENOSYS, %eax
+	jmp	syscall_after_call
+END(syscall_badsys)
+
+sysenter_badsys:
+	movl	$-ENOSYS, %eax
+	jmp	sysenter_after_call
+END(sysenter_badsys)
+
+.macro FIXUP_ESPFIX_STACK
+/*
+ * Switch back for ESPFIX stack to the normal zerobased stack
+ *
+ * We can't call C functions using the ESPFIX stack. This code reads
+ * the high word of the segment base from the GDT and swiches to the
+ * normal stack and adjusts ESP with the matching offset.
+ */
+#ifdef CONFIG_X86_ESPFIX32
+	/* fixup the stack */
+	mov	GDT_ESPFIX_SS + 4, %al /* bits 16..23 */
+	mov	GDT_ESPFIX_SS + 7, %ah /* bits 24..31 */
+	shl	$16, %eax
+	addl	%esp, %eax			/* the adjusted stack pointer */
+	pushl	$__KERNEL_DS
+	pushl	%eax
+	lss	(%esp), %esp			/* switch to the normal stack segment */
+#endif
+.endm
+.macro UNWIND_ESPFIX_STACK
+#ifdef CONFIG_X86_ESPFIX32
+	movl	%ss, %eax
+	/* see if on espfix stack */
+	cmpw	$__ESPFIX_SS, %ax
+	jne	27f
+	movl	$__KERNEL_DS, %eax
+	movl	%eax, %ds
+	movl	%eax, %es
+	/* switch to normal stack */
+	FIXUP_ESPFIX_STACK
+27:
+#endif
+.endm
+
+/*
+ * Build the entry stubs with some assembler magic.
+ * We pack 1 stub into every 8-byte block.
+ */
+	.align 8
+ENTRY(irq_entries_start)
+    vector=FIRST_EXTERNAL_VECTOR
+    .rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR)
+	pushl	$(~vector+0x80)			/* Note: always in signed byte range */
+    vector=vector+1
+	jmp	common_interrupt
+	.align	8
+    .endr
+END(irq_entries_start)
+
+/*
+ * the CPU automatically disables interrupts when executing an IRQ vector,
+ * so IRQ-flags tracing has to follow that:
+ */
+	.p2align CONFIG_X86_L1_CACHE_SHIFT
+common_interrupt:
+	ASM_CLAC
+	addl	$-0x80, (%esp)			/* Adjust vector into the [-256, -1] range */
+	SAVE_ALL
+	TRACE_IRQS_OFF
+	movl	%esp, %eax
+	call	do_IRQ
+	jmp	ret_from_intr
+ENDPROC(common_interrupt)
+
+#define BUILD_INTERRUPT3(name, nr, fn)	\
+ENTRY(name)				\
+	ASM_CLAC;			\
+	pushl	$~(nr);			\
+	SAVE_ALL;			\
+	TRACE_IRQS_OFF			\
+	movl	%esp, %eax;		\
+	call	fn;			\
+	jmp	ret_from_intr;		\
+ENDPROC(name)
+
+
+#ifdef CONFIG_TRACING
+# define TRACE_BUILD_INTERRUPT(name, nr)	BUILD_INTERRUPT3(trace_##name, nr, smp_trace_##name)
+#else
+# define TRACE_BUILD_INTERRUPT(name, nr)
+#endif
+
+#define BUILD_INTERRUPT(name, nr)		\
+	BUILD_INTERRUPT3(name, nr, smp_##name);	\
+	TRACE_BUILD_INTERRUPT(name, nr)
+
+/* The include is where all of the SMP etc. interrupts come from */
+#include <asm/entry_arch.h>
+
+ENTRY(coprocessor_error)
+	ASM_CLAC
+	pushl	$0
+	pushl	$do_coprocessor_error
+	jmp	error_code
+END(coprocessor_error)
+
+ENTRY(simd_coprocessor_error)
+	ASM_CLAC
+	pushl	$0
+#ifdef CONFIG_X86_INVD_BUG
+	/* AMD 486 bug: invd from userspace calls exception 19 instead of #GP */
+	ALTERNATIVE "pushl	$do_general_protection",	\
+		    "pushl	$do_simd_coprocessor_error",	\
+		    X86_FEATURE_XMM
+#else
+	pushl	$do_simd_coprocessor_error
+#endif
+	jmp	error_code
+END(simd_coprocessor_error)
+
+ENTRY(device_not_available)
+	ASM_CLAC
+	pushl	$-1				# mark this as an int
+	pushl	$do_device_not_available
+	jmp	error_code
+END(device_not_available)
+
+#ifdef CONFIG_PARAVIRT
+ENTRY(native_iret)
+	iret
+	_ASM_EXTABLE(native_iret, iret_exc)
+END(native_iret)
+
+ENTRY(native_irq_enable_sysexit)
+	sti
+	sysexit
+END(native_irq_enable_sysexit)
+#endif
+
+ENTRY(overflow)
+	ASM_CLAC
+	pushl	$0
+	pushl	$do_overflow
+	jmp	error_code
+END(overflow)
+
+ENTRY(bounds)
+	ASM_CLAC
+	pushl	$0
+	pushl	$do_bounds
+	jmp	error_code
+END(bounds)
+
+ENTRY(invalid_op)
+	ASM_CLAC
+	pushl	$0
+	pushl	$do_invalid_op
+	jmp	error_code
+END(invalid_op)
+
+ENTRY(coprocessor_segment_overrun)
+	ASM_CLAC
+	pushl	$0
+	pushl	$do_coprocessor_segment_overrun
+	jmp	error_code
+END(coprocessor_segment_overrun)
+
+ENTRY(invalid_TSS)
+	ASM_CLAC
+	pushl	$do_invalid_TSS
+	jmp	error_code
+END(invalid_TSS)
+
+ENTRY(segment_not_present)
+	ASM_CLAC
+	pushl	$do_segment_not_present
+	jmp	error_code
+END(segment_not_present)
+
+ENTRY(stack_segment)
+	ASM_CLAC
+	pushl	$do_stack_segment
+	jmp	error_code
+END(stack_segment)
+
+ENTRY(alignment_check)
+	ASM_CLAC
+	pushl	$do_alignment_check
+	jmp	error_code
+END(alignment_check)
+
+ENTRY(divide_error)
+	ASM_CLAC
+	pushl	$0				# no error code
+	pushl	$do_divide_error
+	jmp	error_code
+END(divide_error)
+
+#ifdef CONFIG_X86_MCE
+ENTRY(machine_check)
+	ASM_CLAC
+	pushl	$0
+	pushl	machine_check_vector
+	jmp	error_code
+END(machine_check)
+#endif
+
+ENTRY(spurious_interrupt_bug)
+	ASM_CLAC
+	pushl	$0
+	pushl	$do_spurious_interrupt_bug
+	jmp	error_code
+END(spurious_interrupt_bug)
+
+#ifdef CONFIG_XEN
+/*
+ * Xen doesn't set %esp to be precisely what the normal SYSENTER
+ * entry point expects, so fix it up before using the normal path.
+ */
+ENTRY(xen_sysenter_target)
+	addl	$5*4, %esp			/* remove xen-provided frame */
+	jmp	sysenter_past_esp
+
+ENTRY(xen_hypervisor_callback)
+	pushl	$-1				/* orig_ax = -1 => not a system call */
+	SAVE_ALL
+	TRACE_IRQS_OFF
+
+	/*
+	 * Check to see if we got the event in the critical
+	 * region in xen_iret_direct, after we've reenabled
+	 * events and checked for pending events.  This simulates
+	 * iret instruction's behaviour where it delivers a
+	 * pending interrupt when enabling interrupts:
+	 */
+	movl	PT_EIP(%esp), %eax
+	cmpl	$xen_iret_start_crit, %eax
+	jb	1f
+	cmpl	$xen_iret_end_crit, %eax
+	jae	1f
+
+	jmp	xen_iret_crit_fixup
+
+ENTRY(xen_do_upcall)
+1:	mov	%esp, %eax
+	call	xen_evtchn_do_upcall
+#ifndef CONFIG_PREEMPT
+	call	xen_maybe_preempt_hcall
+#endif
+	jmp	ret_from_intr
+ENDPROC(xen_hypervisor_callback)
+
+/*
+ * Hypervisor uses this for application faults while it executes.
+ * We get here for two reasons:
+ *  1. Fault while reloading DS, ES, FS or GS
+ *  2. Fault while executing IRET
+ * Category 1 we fix up by reattempting the load, and zeroing the segment
+ * register if the load fails.
+ * Category 2 we fix up by jumping to do_iret_error. We cannot use the
+ * normal Linux return path in this case because if we use the IRET hypercall
+ * to pop the stack frame we end up in an infinite loop of failsafe callbacks.
+ * We distinguish between categories by maintaining a status value in EAX.
+ */
+ENTRY(xen_failsafe_callback)
+	pushl	%eax
+	movl	$1, %eax
+1:	mov	4(%esp), %ds
+2:	mov	8(%esp), %es
+3:	mov	12(%esp), %fs
+4:	mov	16(%esp), %gs
+	/* EAX == 0 => Category 1 (Bad segment)
+	   EAX != 0 => Category 2 (Bad IRET) */
+	testl	%eax, %eax
+	popl	%eax
+	lea	16(%esp), %esp
+	jz	5f
+	jmp	iret_exc
+5:	pushl	$-1				/* orig_ax = -1 => not a system call */
+	SAVE_ALL
+	jmp	ret_from_exception
+
+.section .fixup, "ax"
+6:	xorl	%eax, %eax
+	movl	%eax, 4(%esp)
+	jmp	1b
+7:	xorl	%eax, %eax
+	movl	%eax, 8(%esp)
+	jmp	2b
+8:	xorl	%eax, %eax
+	movl	%eax, 12(%esp)
+	jmp	3b
+9:	xorl	%eax, %eax
+	movl	%eax, 16(%esp)
+	jmp	4b
+.previous
+	_ASM_EXTABLE(1b, 6b)
+	_ASM_EXTABLE(2b, 7b)
+	_ASM_EXTABLE(3b, 8b)
+	_ASM_EXTABLE(4b, 9b)
+ENDPROC(xen_failsafe_callback)
+
+BUILD_INTERRUPT3(xen_hvm_callback_vector, HYPERVISOR_CALLBACK_VECTOR,
+		xen_evtchn_do_upcall)
+
+#endif /* CONFIG_XEN */
+
+#if IS_ENABLED(CONFIG_HYPERV)
+
+BUILD_INTERRUPT3(hyperv_callback_vector, HYPERVISOR_CALLBACK_VECTOR,
+	hyperv_vector_handler)
+
+#endif /* CONFIG_HYPERV */
+
+#ifdef CONFIG_FUNCTION_TRACER
+#ifdef CONFIG_DYNAMIC_FTRACE
+
+ENTRY(mcount)
+	ret
+END(mcount)
+
+ENTRY(ftrace_caller)
+	pushl	%eax
+	pushl	%ecx
+	pushl	%edx
+	pushl	$0				/* Pass NULL as regs pointer */
+	movl	4*4(%esp), %eax
+	movl	0x4(%ebp), %edx
+	movl	function_trace_op, %ecx
+	subl	$MCOUNT_INSN_SIZE, %eax
+
+.globl ftrace_call
+ftrace_call:
+	call	ftrace_stub
+
+	addl	$4, %esp			/* skip NULL pointer */
+	popl	%edx
+	popl	%ecx
+	popl	%eax
+ftrace_ret:
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+.globl ftrace_graph_call
+ftrace_graph_call:
+	jmp	ftrace_stub
+#endif
+
+.globl ftrace_stub
+ftrace_stub:
+	ret
+END(ftrace_caller)
+
+ENTRY(ftrace_regs_caller)
+	pushf	/* push flags before compare (in cs location) */
+
+	/*
+	 * i386 does not save SS and ESP when coming from kernel.
+	 * Instead, to get sp, &regs->sp is used (see ptrace.h).
+	 * Unfortunately, that means eflags must be at the same location
+	 * as the current return ip is. We move the return ip into the
+	 * ip location, and move flags into the return ip location.
+	 */
+	pushl	4(%esp)				/* save return ip into ip slot */
+
+	pushl	$0				/* Load 0 into orig_ax */
+	pushl	%gs
+	pushl	%fs
+	pushl	%es
+	pushl	%ds
+	pushl	%eax
+	pushl	%ebp
+	pushl	%edi
+	pushl	%esi
+	pushl	%edx
+	pushl	%ecx
+	pushl	%ebx
+
+	movl	13*4(%esp), %eax		/* Get the saved flags */
+	movl	%eax, 14*4(%esp)		/* Move saved flags into regs->flags location */
+						/* clobbering return ip */
+	movl	$__KERNEL_CS, 13*4(%esp)
+
+	movl	12*4(%esp), %eax		/* Load ip (1st parameter) */
+	subl	$MCOUNT_INSN_SIZE, %eax		/* Adjust ip */
+	movl	0x4(%ebp), %edx			/* Load parent ip (2nd parameter) */
+	movl	function_trace_op, %ecx		/* Save ftrace_pos in 3rd parameter */
+	pushl	%esp				/* Save pt_regs as 4th parameter */
+
+GLOBAL(ftrace_regs_call)
+	call	ftrace_stub
+
+	addl	$4, %esp			/* Skip pt_regs */
+	movl	14*4(%esp), %eax		/* Move flags back into cs */
+	movl	%eax, 13*4(%esp)		/* Needed to keep addl	from modifying flags */
+	movl	12*4(%esp), %eax		/* Get return ip from regs->ip */
+	movl	%eax, 14*4(%esp)		/* Put return ip back for ret */
+
+	popl	%ebx
+	popl	%ecx
+	popl	%edx
+	popl	%esi
+	popl	%edi
+	popl	%ebp
+	popl	%eax
+	popl	%ds
+	popl	%es
+	popl	%fs
+	popl	%gs
+	addl	$8, %esp			/* Skip orig_ax and ip */
+	popf					/* Pop flags at end (no addl to corrupt flags) */
+	jmp	ftrace_ret
+
+	popf
+	jmp	ftrace_stub
+#else /* ! CONFIG_DYNAMIC_FTRACE */
+
+ENTRY(mcount)
+	cmpl	$__PAGE_OFFSET, %esp
+	jb	ftrace_stub			/* Paging not enabled yet? */
+
+	cmpl	$ftrace_stub, ftrace_trace_function
+	jnz	trace
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	cmpl	$ftrace_stub, ftrace_graph_return
+	jnz	ftrace_graph_caller
+
+	cmpl	$ftrace_graph_entry_stub, ftrace_graph_entry
+	jnz	ftrace_graph_caller
+#endif
+.globl ftrace_stub
+ftrace_stub:
+	ret
+
+	/* taken from glibc */
+trace:
+	pushl	%eax
+	pushl	%ecx
+	pushl	%edx
+	movl	0xc(%esp), %eax
+	movl	0x4(%ebp), %edx
+	subl	$MCOUNT_INSN_SIZE, %eax
+
+	call	*ftrace_trace_function
+
+	popl	%edx
+	popl	%ecx
+	popl	%eax
+	jmp	ftrace_stub
+END(mcount)
+#endif /* CONFIG_DYNAMIC_FTRACE */
+#endif /* CONFIG_FUNCTION_TRACER */
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ENTRY(ftrace_graph_caller)
+	pushl	%eax
+	pushl	%ecx
+	pushl	%edx
+	movl	0xc(%esp), %eax
+	lea	0x4(%ebp), %edx
+	movl	(%ebp), %ecx
+	subl	$MCOUNT_INSN_SIZE, %eax
+	call	prepare_ftrace_return
+	popl	%edx
+	popl	%ecx
+	popl	%eax
+	ret
+END(ftrace_graph_caller)
+
+.globl return_to_handler
+return_to_handler:
+	pushl	%eax
+	pushl	%edx
+	movl	%ebp, %eax
+	call	ftrace_return_to_handler
+	movl	%eax, %ecx
+	popl	%edx
+	popl	%eax
+	jmp	*%ecx
+#endif
+
+#ifdef CONFIG_TRACING
+ENTRY(trace_page_fault)
+	ASM_CLAC
+	pushl	$trace_do_page_fault
+	jmp	error_code
+END(trace_page_fault)
+#endif
+
+ENTRY(page_fault)
+	ASM_CLAC
+	pushl	$do_page_fault
+	ALIGN
+error_code:
+	/* the function address is in %gs's slot on the stack */
+	pushl	%fs
+	pushl	%es
+	pushl	%ds
+	pushl	%eax
+	pushl	%ebp
+	pushl	%edi
+	pushl	%esi
+	pushl	%edx
+	pushl	%ecx
+	pushl	%ebx
+	cld
+	movl	$(__KERNEL_PERCPU), %ecx
+	movl	%ecx, %fs
+	UNWIND_ESPFIX_STACK
+	GS_TO_REG %ecx
+	movl	PT_GS(%esp), %edi		# get the function address
+	movl	PT_ORIG_EAX(%esp), %edx		# get the error code
+	movl	$-1, PT_ORIG_EAX(%esp)		# no syscall to restart
+	REG_TO_PTGS %ecx
+	SET_KERNEL_GS %ecx
+	movl	$(__USER_DS), %ecx
+	movl	%ecx, %ds
+	movl	%ecx, %es
+	TRACE_IRQS_OFF
+	movl	%esp, %eax			# pt_regs pointer
+	call	*%edi
+	jmp	ret_from_exception
+END(page_fault)
+
+/*
+ * Debug traps and NMI can happen at the one SYSENTER instruction
+ * that sets up the real kernel stack. Check here, since we can't
+ * allow the wrong stack to be used.
+ *
+ * "TSS_sysenter_sp0+12" is because the NMI/debug handler will have
+ * already pushed 3 words if it hits on the sysenter instruction:
+ * eflags, cs and eip.
+ *
+ * We just load the right stack, and push the three (known) values
+ * by hand onto the new stack - while updating the return eip past
+ * the instruction that would have done it for sysenter.
+ */
+.macro FIX_STACK offset ok label
+	cmpw	$__KERNEL_CS, 4(%esp)
+	jne	\ok
+\label:
+	movl	TSS_sysenter_sp0 + \offset(%esp), %esp
+	pushfl
+	pushl	$__KERNEL_CS
+	pushl	$sysenter_past_esp
+.endm
+
+ENTRY(debug)
+	ASM_CLAC
+	cmpl	$entry_SYSENTER_32, (%esp)
+	jne	debug_stack_correct
+	FIX_STACK 12, debug_stack_correct, debug_esp_fix_insn
+debug_stack_correct:
+	pushl	$-1				# mark this as an int
+	SAVE_ALL
+	TRACE_IRQS_OFF
+	xorl	%edx, %edx			# error code 0
+	movl	%esp, %eax			# pt_regs pointer
+	call	do_debug
+	jmp	ret_from_exception
+END(debug)
+
+/*
+ * NMI is doubly nasty. It can happen _while_ we're handling
+ * a debug fault, and the debug fault hasn't yet been able to
+ * clear up the stack. So we first check whether we got  an
+ * NMI on the sysenter entry path, but after that we need to
+ * check whether we got an NMI on the debug path where the debug
+ * fault happened on the sysenter path.
+ */
+ENTRY(nmi)
+	ASM_CLAC
+#ifdef CONFIG_X86_ESPFIX32
+	pushl	%eax
+	movl	%ss, %eax
+	cmpw	$__ESPFIX_SS, %ax
+	popl	%eax
+	je	nmi_espfix_stack
+#endif
+	cmpl	$entry_SYSENTER_32, (%esp)
+	je	nmi_stack_fixup
+	pushl	%eax
+	movl	%esp, %eax
+	/*
+	 * Do not access memory above the end of our stack page,
+	 * it might not exist.
+	 */
+	andl	$(THREAD_SIZE-1), %eax
+	cmpl	$(THREAD_SIZE-20), %eax
+	popl	%eax
+	jae	nmi_stack_correct
+	cmpl	$entry_SYSENTER_32, 12(%esp)
+	je	nmi_debug_stack_check
+nmi_stack_correct:
+	pushl	%eax
+	SAVE_ALL
+	xorl	%edx, %edx			# zero error code
+	movl	%esp, %eax			# pt_regs pointer
+	call	do_nmi
+	jmp	restore_all_notrace
+
+nmi_stack_fixup:
+	FIX_STACK 12, nmi_stack_correct, 1
+	jmp	nmi_stack_correct
+
+nmi_debug_stack_check:
+	cmpw	$__KERNEL_CS, 16(%esp)
+	jne	nmi_stack_correct
+	cmpl	$debug, (%esp)
+	jb	nmi_stack_correct
+	cmpl	$debug_esp_fix_insn, (%esp)
+	ja	nmi_stack_correct
+	FIX_STACK 24, nmi_stack_correct, 1
+	jmp	nmi_stack_correct
+
+#ifdef CONFIG_X86_ESPFIX32
+nmi_espfix_stack:
+	/*
+	 * create the pointer to lss back
+	 */
+	pushl	%ss
+	pushl	%esp
+	addl	$4, (%esp)
+	/* copy the iret frame of 12 bytes */
+	.rept 3
+	pushl	16(%esp)
+	.endr
+	pushl	%eax
+	SAVE_ALL
+	FIXUP_ESPFIX_STACK			# %eax == %esp
+	xorl	%edx, %edx			# zero error code
+	call	do_nmi
+	RESTORE_REGS
+	lss	12+4(%esp), %esp		# back to espfix stack
+	jmp	irq_return
+#endif
+END(nmi)
+
+ENTRY(int3)
+	ASM_CLAC
+	pushl	$-1				# mark this as an int
+	SAVE_ALL
+	TRACE_IRQS_OFF
+	xorl	%edx, %edx			# zero error code
+	movl	%esp, %eax			# pt_regs pointer
+	call	do_int3
+	jmp	ret_from_exception
+END(int3)
+
+ENTRY(general_protection)
+	pushl	$do_general_protection
+	jmp	error_code
+END(general_protection)
+
+#ifdef CONFIG_KVM_GUEST
+ENTRY(async_page_fault)
+	ASM_CLAC
+	pushl	$do_async_page_fault
+	jmp	error_code
+END(async_page_fault)
+#endif
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/entry/entry_64.S
index 02c2eff7478d..3bb2c4302df1 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -4,34 +4,25 @@
  *  Copyright (C) 1991, 1992  Linus Torvalds
  *  Copyright (C) 2000, 2001, 2002  Andi Kleen SuSE Labs
  *  Copyright (C) 2000  Pavel Machek <pavel@suse.cz>
- */
-
-/*
+ *
  * entry.S contains the system-call and fault low-level handling routines.
  *
  * Some of this is documented in Documentation/x86/entry_64.txt
  *
- * NOTE: This code handles signal-recognition, which happens every time
- * after an interrupt and after each system call.
- *
  * A note on terminology:
- * - iret frame: Architecture defined interrupt frame from SS to RIP
- * at the top of the kernel process stack.
+ * - iret frame:	Architecture defined interrupt frame from SS to RIP
+ *			at the top of the kernel process stack.
  *
  * Some macro usage:
- * - CFI macros are used to generate dwarf2 unwind information for better
- * backtraces. They don't change any code.
- * - ENTRY/END Define functions in the symbol table.
- * - TRACE_IRQ_* - Trace hard interrupt state for lock debugging.
- * - idtentry - Define exception entry points.
+ * - ENTRY/END:		Define functions in the symbol table.
+ * - TRACE_IRQ_*:	Trace hardirq state for lock debugging.
+ * - idtentry:		Define exception entry points.
  */
-
 #include <linux/linkage.h>
 #include <asm/segment.h>
 #include <asm/cache.h>
 #include <asm/errno.h>
-#include <asm/dwarf2.h>
-#include <asm/calling.h>
+#include "calling.h"
 #include <asm/asm-offsets.h>
 #include <asm/msr.h>
 #include <asm/unistd.h>
@@ -49,13 +40,12 @@
 
 /* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this.  */
 #include <linux/elf-em.h>
-#define AUDIT_ARCH_X86_64	(EM_X86_64|__AUDIT_ARCH_64BIT|__AUDIT_ARCH_LE)
-#define __AUDIT_ARCH_64BIT 0x80000000
-#define __AUDIT_ARCH_LE	   0x40000000
-
-	.code64
-	.section .entry.text, "ax"
+#define AUDIT_ARCH_X86_64			(EM_X86_64|__AUDIT_ARCH_64BIT|__AUDIT_ARCH_LE)
+#define __AUDIT_ARCH_64BIT			0x80000000
+#define __AUDIT_ARCH_LE				0x40000000
 
+.code64
+.section .entry.text, "ax"
 
 #ifdef CONFIG_PARAVIRT
 ENTRY(native_usergs_sysret64)
@@ -64,11 +54,10 @@ ENTRY(native_usergs_sysret64)
 ENDPROC(native_usergs_sysret64)
 #endif /* CONFIG_PARAVIRT */
 
-
 .macro TRACE_IRQS_IRETQ
 #ifdef CONFIG_TRACE_IRQFLAGS
-	bt   $9,EFLAGS(%rsp)	/* interrupts off? */
-	jnc  1f
+	bt	$9, EFLAGS(%rsp)		/* interrupts off? */
+	jnc	1f
 	TRACE_IRQS_ON
 1:
 #endif
@@ -88,89 +77,34 @@ ENDPROC(native_usergs_sysret64)
 #if defined(CONFIG_DYNAMIC_FTRACE) && defined(CONFIG_TRACE_IRQFLAGS)
 
 .macro TRACE_IRQS_OFF_DEBUG
-	call debug_stack_set_zero
+	call	debug_stack_set_zero
 	TRACE_IRQS_OFF
-	call debug_stack_reset
+	call	debug_stack_reset
 .endm
 
 .macro TRACE_IRQS_ON_DEBUG
-	call debug_stack_set_zero
+	call	debug_stack_set_zero
 	TRACE_IRQS_ON
-	call debug_stack_reset
+	call	debug_stack_reset
 .endm
 
 .macro TRACE_IRQS_IRETQ_DEBUG
-	bt   $9,EFLAGS(%rsp)	/* interrupts off? */
-	jnc  1f
+	bt	$9, EFLAGS(%rsp)		/* interrupts off? */
+	jnc	1f
 	TRACE_IRQS_ON_DEBUG
 1:
 .endm
 
 #else
-# define TRACE_IRQS_OFF_DEBUG		TRACE_IRQS_OFF
-# define TRACE_IRQS_ON_DEBUG		TRACE_IRQS_ON
-# define TRACE_IRQS_IRETQ_DEBUG		TRACE_IRQS_IRETQ
+# define TRACE_IRQS_OFF_DEBUG			TRACE_IRQS_OFF
+# define TRACE_IRQS_ON_DEBUG			TRACE_IRQS_ON
+# define TRACE_IRQS_IRETQ_DEBUG			TRACE_IRQS_IRETQ
 #endif
 
 /*
- * empty frame
- */
-	.macro EMPTY_FRAME start=1 offset=0
-	.if \start
-	CFI_STARTPROC simple
-	CFI_SIGNAL_FRAME
-	CFI_DEF_CFA rsp,8+\offset
-	.else
-	CFI_DEF_CFA_OFFSET 8+\offset
-	.endif
-	.endm
-
-/*
- * initial frame state for interrupts (and exceptions without error code)
- */
-	.macro INTR_FRAME start=1 offset=0
-	EMPTY_FRAME \start, 5*8+\offset
-	/*CFI_REL_OFFSET ss, 4*8+\offset*/
-	CFI_REL_OFFSET rsp, 3*8+\offset
-	/*CFI_REL_OFFSET rflags, 2*8+\offset*/
-	/*CFI_REL_OFFSET cs, 1*8+\offset*/
-	CFI_REL_OFFSET rip, 0*8+\offset
-	.endm
-
-/*
- * initial frame state for exceptions with error code (and interrupts
- * with vector already pushed)
- */
-	.macro XCPT_FRAME start=1 offset=0
-	INTR_FRAME \start, 1*8+\offset
-	.endm
-
-/*
- * frame that enables passing a complete pt_regs to a C function.
- */
-	.macro DEFAULT_FRAME start=1 offset=0
-	XCPT_FRAME \start, ORIG_RAX+\offset
-	CFI_REL_OFFSET rdi, RDI+\offset
-	CFI_REL_OFFSET rsi, RSI+\offset
-	CFI_REL_OFFSET rdx, RDX+\offset
-	CFI_REL_OFFSET rcx, RCX+\offset
-	CFI_REL_OFFSET rax, RAX+\offset
-	CFI_REL_OFFSET r8, R8+\offset
-	CFI_REL_OFFSET r9, R9+\offset
-	CFI_REL_OFFSET r10, R10+\offset
-	CFI_REL_OFFSET r11, R11+\offset
-	CFI_REL_OFFSET rbx, RBX+\offset
-	CFI_REL_OFFSET rbp, RBP+\offset
-	CFI_REL_OFFSET r12, R12+\offset
-	CFI_REL_OFFSET r13, R13+\offset
-	CFI_REL_OFFSET r14, R14+\offset
-	CFI_REL_OFFSET r15, R15+\offset
-	.endm
-
-/*
- * 64bit SYSCALL instruction entry. Up to 6 arguments in registers.
+ * 64-bit SYSCALL instruction entry. Up to 6 arguments in registers.
  *
- * 64bit SYSCALL saves rip to rcx, clears rflags.RF, then saves rflags to r11,
+ * 64-bit SYSCALL saves rip to rcx, clears rflags.RF, then saves rflags to r11,
  * then loads new ss, cs, and rip from previously programmed MSRs.
  * rflags gets masked by a value from another MSR (so CLD and CLAC
  * are not needed). SYSCALL does not save anything on the stack
@@ -186,7 +120,7 @@ ENDPROC(native_usergs_sysret64)
  * r10  arg3 (needs to be moved to rcx to conform to C ABI)
  * r8   arg4
  * r9   arg5
- * (note: r12-r15,rbp,rbx are callee-preserved in C ABI)
+ * (note: r12-r15, rbp, rbx are callee-preserved in C ABI)
  *
  * Only called from user space.
  *
@@ -195,13 +129,7 @@ ENDPROC(native_usergs_sysret64)
  * with them due to bugs in both AMD and Intel CPUs.
  */
 
-ENTRY(system_call)
-	CFI_STARTPROC	simple
-	CFI_SIGNAL_FRAME
-	CFI_DEF_CFA	rsp,0
-	CFI_REGISTER	rip,rcx
-	/*CFI_REGISTER	rflags,r11*/
-
+ENTRY(entry_SYSCALL_64)
 	/*
 	 * Interrupts are off on entry.
 	 * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
@@ -213,14 +141,14 @@ ENTRY(system_call)
 	 * after the swapgs, so that it can do the swapgs
 	 * for the guest and jump here on syscall.
 	 */
-GLOBAL(system_call_after_swapgs)
+GLOBAL(entry_SYSCALL_64_after_swapgs)
 
-	movq	%rsp,PER_CPU_VAR(rsp_scratch)
-	movq	PER_CPU_VAR(kernel_stack),%rsp
+	movq	%rsp, PER_CPU_VAR(rsp_scratch)
+	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
 
 	/* Construct struct pt_regs on stack */
-	pushq_cfi $__USER_DS			/* pt_regs->ss */
-	pushq_cfi PER_CPU_VAR(rsp_scratch)	/* pt_regs->sp */
+	pushq	$__USER_DS			/* pt_regs->ss */
+	pushq	PER_CPU_VAR(rsp_scratch)	/* pt_regs->sp */
 	/*
 	 * Re-enable interrupts.
 	 * We use 'rsp_scratch' as a scratch space, hence irq-off block above
@@ -229,36 +157,34 @@ GLOBAL(system_call_after_swapgs)
 	 * with using rsp_scratch:
 	 */
 	ENABLE_INTERRUPTS(CLBR_NONE)
-	pushq_cfi	%r11			/* pt_regs->flags */
-	pushq_cfi	$__USER_CS		/* pt_regs->cs */
-	pushq_cfi	%rcx			/* pt_regs->ip */
-	CFI_REL_OFFSET rip,0
-	pushq_cfi_reg	rax			/* pt_regs->orig_ax */
-	pushq_cfi_reg	rdi			/* pt_regs->di */
-	pushq_cfi_reg	rsi			/* pt_regs->si */
-	pushq_cfi_reg	rdx			/* pt_regs->dx */
-	pushq_cfi_reg	rcx			/* pt_regs->cx */
-	pushq_cfi	$-ENOSYS		/* pt_regs->ax */
-	pushq_cfi_reg	r8			/* pt_regs->r8 */
-	pushq_cfi_reg	r9			/* pt_regs->r9 */
-	pushq_cfi_reg	r10			/* pt_regs->r10 */
-	pushq_cfi_reg	r11			/* pt_regs->r11 */
-	sub	$(6*8),%rsp /* pt_regs->bp,bx,r12-15 not saved */
-	CFI_ADJUST_CFA_OFFSET 6*8
-
-	testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
-	jnz tracesys
-system_call_fastpath:
+	pushq	%r11				/* pt_regs->flags */
+	pushq	$__USER_CS			/* pt_regs->cs */
+	pushq	%rcx				/* pt_regs->ip */
+	pushq	%rax				/* pt_regs->orig_ax */
+	pushq	%rdi				/* pt_regs->di */
+	pushq	%rsi				/* pt_regs->si */
+	pushq	%rdx				/* pt_regs->dx */
+	pushq	%rcx				/* pt_regs->cx */
+	pushq	$-ENOSYS			/* pt_regs->ax */
+	pushq	%r8				/* pt_regs->r8 */
+	pushq	%r9				/* pt_regs->r9 */
+	pushq	%r10				/* pt_regs->r10 */
+	pushq	%r11				/* pt_regs->r11 */
+	sub	$(6*8), %rsp			/* pt_regs->bp, bx, r12-15 not saved */
+
+	testl	$_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+	jnz	tracesys
+entry_SYSCALL_64_fastpath:
 #if __SYSCALL_MASK == ~0
-	cmpq $__NR_syscall_max,%rax
+	cmpq	$__NR_syscall_max, %rax
 #else
-	andl $__SYSCALL_MASK,%eax
-	cmpl $__NR_syscall_max,%eax
+	andl	$__SYSCALL_MASK, %eax
+	cmpl	$__NR_syscall_max, %eax
 #endif
-	ja	1f	/* return -ENOSYS (already in pt_regs->ax) */
-	movq %r10,%rcx
-	call *sys_call_table(,%rax,8)
-	movq %rax,RAX(%rsp)
+	ja	1f				/* return -ENOSYS (already in pt_regs->ax) */
+	movq	%r10, %rcx
+	call	*sys_call_table(, %rax, 8)
+	movq	%rax, RAX(%rsp)
 1:
 /*
  * Syscall return path ending with SYSRET (fast path).
@@ -279,19 +205,15 @@ system_call_fastpath:
 	 * flags (TIF_NOTIFY_RESUME, TIF_USER_RETURN_NOTIFY, etc) set is
 	 * very bad.
 	 */
-	testl $_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
-	jnz int_ret_from_sys_call_irqs_off	/* Go to the slow path */
-
-	CFI_REMEMBER_STATE
+	testl	$_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+	jnz	int_ret_from_sys_call_irqs_off	/* Go to the slow path */
 
 	RESTORE_C_REGS_EXCEPT_RCX_R11
-	movq	RIP(%rsp),%rcx
-	CFI_REGISTER	rip,rcx
-	movq	EFLAGS(%rsp),%r11
-	/*CFI_REGISTER	rflags,r11*/
-	movq	RSP(%rsp),%rsp
+	movq	RIP(%rsp), %rcx
+	movq	EFLAGS(%rsp), %r11
+	movq	RSP(%rsp), %rsp
 	/*
-	 * 64bit SYSRET restores rip from rcx,
+	 * 64-bit SYSRET restores rip from rcx,
 	 * rflags from r11 (but RF and VM bits are forced to 0),
 	 * cs and ss are loaded from MSRs.
 	 * Restoration of rflags re-enables interrupts.
@@ -307,25 +229,23 @@ system_call_fastpath:
 	 */
 	USERGS_SYSRET64
 
-	CFI_RESTORE_STATE
-
 	/* Do syscall entry tracing */
 tracesys:
-	movq %rsp, %rdi
-	movl $AUDIT_ARCH_X86_64, %esi
-	call syscall_trace_enter_phase1
-	test %rax, %rax
-	jnz tracesys_phase2		/* if needed, run the slow path */
-	RESTORE_C_REGS_EXCEPT_RAX	/* else restore clobbered regs */
-	movq ORIG_RAX(%rsp), %rax
-	jmp system_call_fastpath	/*      and return to the fast path */
+	movq	%rsp, %rdi
+	movl	$AUDIT_ARCH_X86_64, %esi
+	call	syscall_trace_enter_phase1
+	test	%rax, %rax
+	jnz	tracesys_phase2			/* if needed, run the slow path */
+	RESTORE_C_REGS_EXCEPT_RAX		/* else restore clobbered regs */
+	movq	ORIG_RAX(%rsp), %rax
+	jmp	entry_SYSCALL_64_fastpath	/* and return to the fast path */
 
 tracesys_phase2:
 	SAVE_EXTRA_REGS
-	movq %rsp, %rdi
-	movl $AUDIT_ARCH_X86_64, %esi
-	movq %rax,%rdx
-	call syscall_trace_enter_phase2
+	movq	%rsp, %rdi
+	movl	$AUDIT_ARCH_X86_64, %esi
+	movq	%rax, %rdx
+	call	syscall_trace_enter_phase2
 
 	/*
 	 * Reload registers from stack in case ptrace changed them.
@@ -335,15 +255,15 @@ tracesys_phase2:
 	RESTORE_C_REGS_EXCEPT_RAX
 	RESTORE_EXTRA_REGS
 #if __SYSCALL_MASK == ~0
-	cmpq $__NR_syscall_max,%rax
+	cmpq	$__NR_syscall_max, %rax
 #else
-	andl $__SYSCALL_MASK,%eax
-	cmpl $__NR_syscall_max,%eax
+	andl	$__SYSCALL_MASK, %eax
+	cmpl	$__NR_syscall_max, %eax
 #endif
-	ja	1f	/* return -ENOSYS (already in pt_regs->ax) */
-	movq %r10,%rcx	/* fixup for C */
-	call *sys_call_table(,%rax,8)
-	movq %rax,RAX(%rsp)
+	ja	1f				/* return -ENOSYS (already in pt_regs->ax) */
+	movq	%r10, %rcx			/* fixup for C */
+	call	*sys_call_table(, %rax, 8)
+	movq	%rax, RAX(%rsp)
 1:
 	/* Use IRET because user could have changed pt_regs->foo */
 
@@ -355,31 +275,33 @@ GLOBAL(int_ret_from_sys_call)
 	DISABLE_INTERRUPTS(CLBR_NONE)
 int_ret_from_sys_call_irqs_off: /* jumps come here from the irqs-off SYSRET path */
 	TRACE_IRQS_OFF
-	movl $_TIF_ALLWORK_MASK,%edi
+	movl	$_TIF_ALLWORK_MASK, %edi
 	/* edi:	mask to check */
 GLOBAL(int_with_check)
 	LOCKDEP_SYS_EXIT_IRQ
 	GET_THREAD_INFO(%rcx)
-	movl TI_flags(%rcx),%edx
-	andl %edi,%edx
-	jnz   int_careful
-	andl	$~TS_COMPAT,TI_status(%rcx)
+	movl	TI_flags(%rcx), %edx
+	andl	%edi, %edx
+	jnz	int_careful
+	andl	$~TS_COMPAT, TI_status(%rcx)
 	jmp	syscall_return
 
-	/* Either reschedule or signal or syscall exit tracking needed. */
-	/* First do a reschedule test. */
-	/* edx:	work, edi: workmask */
+	/*
+	 * Either reschedule or signal or syscall exit tracking needed.
+	 * First do a reschedule test.
+	 * edx:	work, edi: workmask
+	 */
 int_careful:
-	bt $TIF_NEED_RESCHED,%edx
-	jnc  int_very_careful
+	bt	$TIF_NEED_RESCHED, %edx
+	jnc	int_very_careful
 	TRACE_IRQS_ON
 	ENABLE_INTERRUPTS(CLBR_NONE)
-	pushq_cfi %rdi
+	pushq	%rdi
 	SCHEDULE_USER
-	popq_cfi %rdi
+	popq	%rdi
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
-	jmp int_with_check
+	jmp	int_with_check
 
 	/* handle signals and tracing -- both require a full pt_regs */
 int_very_careful:
@@ -387,27 +309,27 @@ int_very_careful:
 	ENABLE_INTERRUPTS(CLBR_NONE)
 	SAVE_EXTRA_REGS
 	/* Check for syscall exit trace */
-	testl $_TIF_WORK_SYSCALL_EXIT,%edx
-	jz int_signal
-	pushq_cfi %rdi
-	leaq 8(%rsp),%rdi	# &ptregs -> arg1
-	call syscall_trace_leave
-	popq_cfi %rdi
-	andl $~(_TIF_WORK_SYSCALL_EXIT|_TIF_SYSCALL_EMU),%edi
-	jmp int_restore_rest
+	testl	$_TIF_WORK_SYSCALL_EXIT, %edx
+	jz	int_signal
+	pushq	%rdi
+	leaq	8(%rsp), %rdi			/* &ptregs -> arg1 */
+	call	syscall_trace_leave
+	popq	%rdi
+	andl	$~(_TIF_WORK_SYSCALL_EXIT|_TIF_SYSCALL_EMU), %edi
+	jmp	int_restore_rest
 
 int_signal:
-	testl $_TIF_DO_NOTIFY_MASK,%edx
-	jz 1f
-	movq %rsp,%rdi		# &ptregs -> arg1
-	xorl %esi,%esi		# oldset -> arg2
-	call do_notify_resume
-1:	movl $_TIF_WORK_MASK,%edi
+	testl	$_TIF_DO_NOTIFY_MASK, %edx
+	jz	1f
+	movq	%rsp, %rdi			/* &ptregs -> arg1 */
+	xorl	%esi, %esi			/* oldset -> arg2 */
+	call	do_notify_resume
+1:	movl	$_TIF_WORK_MASK, %edi
 int_restore_rest:
 	RESTORE_EXTRA_REGS
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
-	jmp int_with_check
+	jmp	int_with_check
 
 syscall_return:
 	/* The IRETQ could re-enable interrupts: */
@@ -418,34 +340,37 @@ syscall_return:
 	 * Try to use SYSRET instead of IRET if we're returning to
 	 * a completely clean 64-bit userspace context.
 	 */
-	movq RCX(%rsp),%rcx
-	cmpq %rcx,RIP(%rsp)		/* RCX == RIP */
-	jne opportunistic_sysret_failed
+	movq	RCX(%rsp), %rcx
+	movq	RIP(%rsp), %r11
+	cmpq	%rcx, %r11			/* RCX == RIP */
+	jne	opportunistic_sysret_failed
 
 	/*
 	 * On Intel CPUs, SYSRET with non-canonical RCX/RIP will #GP
 	 * in kernel space.  This essentially lets the user take over
-	 * the kernel, since userspace controls RSP.  It's not worth
-	 * testing for canonicalness exactly -- this check detects any
-	 * of the 17 high bits set, which is true for non-canonical
-	 * or kernel addresses.  (This will pessimize vsyscall=native.
-	 * Big deal.)
+	 * the kernel, since userspace controls RSP.
 	 *
-	 * If virtual addresses ever become wider, this will need
+	 * If width of "canonical tail" ever becomes variable, this will need
 	 * to be updated to remain correct on both old and new CPUs.
 	 */
 	.ifne __VIRTUAL_MASK_SHIFT - 47
 	.error "virtual address width changed -- SYSRET checks need update"
 	.endif
-	shr $__VIRTUAL_MASK_SHIFT, %rcx
-	jnz opportunistic_sysret_failed
 
-	cmpq $__USER_CS,CS(%rsp)	/* CS must match SYSRET */
-	jne opportunistic_sysret_failed
+	/* Change top 16 bits to be the sign-extension of 47th bit */
+	shl	$(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx
+	sar	$(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx
 
-	movq R11(%rsp),%r11
-	cmpq %r11,EFLAGS(%rsp)		/* R11 == RFLAGS */
-	jne opportunistic_sysret_failed
+	/* If this changed %rcx, it was not canonical */
+	cmpq	%rcx, %r11
+	jne	opportunistic_sysret_failed
+
+	cmpq	$__USER_CS, CS(%rsp)		/* CS must match SYSRET */
+	jne	opportunistic_sysret_failed
+
+	movq	R11(%rsp), %r11
+	cmpq	%r11, EFLAGS(%rsp)		/* R11 == RFLAGS */
+	jne	opportunistic_sysret_failed
 
 	/*
 	 * SYSRET can't restore RF.  SYSRET can restore TF, but unlike IRET,
@@ -454,47 +379,41 @@ syscall_return:
 	 * with register state that satisfies the opportunistic SYSRET
 	 * conditions.  For example, single-stepping this user code:
 	 *
-	 *           movq $stuck_here,%rcx
+	 *           movq	$stuck_here, %rcx
 	 *           pushfq
 	 *           popq %r11
 	 *   stuck_here:
 	 *
 	 * would never get past 'stuck_here'.
 	 */
-	testq $(X86_EFLAGS_RF|X86_EFLAGS_TF), %r11
-	jnz opportunistic_sysret_failed
+	testq	$(X86_EFLAGS_RF|X86_EFLAGS_TF), %r11
+	jnz	opportunistic_sysret_failed
 
 	/* nothing to check for RSP */
 
-	cmpq $__USER_DS,SS(%rsp)	/* SS must match SYSRET */
-	jne opportunistic_sysret_failed
+	cmpq	$__USER_DS, SS(%rsp)		/* SS must match SYSRET */
+	jne	opportunistic_sysret_failed
 
 	/*
-	 * We win!  This label is here just for ease of understanding
-	 * perf profiles.  Nothing jumps here.
+	 * We win! This label is here just for ease of understanding
+	 * perf profiles. Nothing jumps here.
 	 */
 syscall_return_via_sysret:
-	CFI_REMEMBER_STATE
-	/* r11 is already restored (see code above) */
-	RESTORE_C_REGS_EXCEPT_R11
-	movq RSP(%rsp),%rsp
+	/* rcx and r11 are already restored (see code above) */
+	RESTORE_C_REGS_EXCEPT_RCX_R11
+	movq	RSP(%rsp), %rsp
 	USERGS_SYSRET64
-	CFI_RESTORE_STATE
 
 opportunistic_sysret_failed:
 	SWAPGS
 	jmp	restore_c_regs_and_iret
-	CFI_ENDPROC
-END(system_call)
+END(entry_SYSCALL_64)
 
 
 	.macro FORK_LIKE func
 ENTRY(stub_\func)
-	CFI_STARTPROC
-	DEFAULT_FRAME 0, 8		/* offset 8: return address */
 	SAVE_EXTRA_REGS 8
-	jmp sys_\func
-	CFI_ENDPROC
+	jmp	sys_\func
 END(stub_\func)
 	.endm
 
@@ -503,8 +422,6 @@ END(stub_\func)
 	FORK_LIKE  vfork
 
 ENTRY(stub_execve)
-	CFI_STARTPROC
-	DEFAULT_FRAME 0, 8
 	call	sys_execve
 return_from_execve:
 	testl	%eax, %eax
@@ -514,11 +431,9 @@ return_from_execve:
 1:
 	/* must use IRET code path (pt_regs->cs may have changed) */
 	addq	$8, %rsp
-	CFI_ADJUST_CFA_OFFSET -8
 	ZERO_EXTRA_REGS
-	movq	%rax,RAX(%rsp)
+	movq	%rax, RAX(%rsp)
 	jmp	int_ret_from_sys_call
-	CFI_ENDPROC
 END(stub_execve)
 /*
  * Remaining execve stubs are only 7 bytes long.
@@ -526,47 +441,25 @@ END(stub_execve)
  */
 	.align	8
 GLOBAL(stub_execveat)
-	CFI_STARTPROC
-	DEFAULT_FRAME 0, 8
 	call	sys_execveat
 	jmp	return_from_execve
-	CFI_ENDPROC
 END(stub_execveat)
 
-#ifdef CONFIG_X86_X32_ABI
+#if defined(CONFIG_X86_X32_ABI) || defined(CONFIG_IA32_EMULATION)
 	.align	8
 GLOBAL(stub_x32_execve)
-	CFI_STARTPROC
-	DEFAULT_FRAME 0, 8
-	call	compat_sys_execve
-	jmp	return_from_execve
-	CFI_ENDPROC
-END(stub_x32_execve)
-	.align	8
-GLOBAL(stub_x32_execveat)
-	CFI_STARTPROC
-	DEFAULT_FRAME 0, 8
-	call	compat_sys_execveat
-	jmp	return_from_execve
-	CFI_ENDPROC
-END(stub_x32_execveat)
-#endif
-
-#ifdef CONFIG_IA32_EMULATION
-	.align	8
 GLOBAL(stub32_execve)
-	CFI_STARTPROC
 	call	compat_sys_execve
 	jmp	return_from_execve
-	CFI_ENDPROC
 END(stub32_execve)
+END(stub_x32_execve)
 	.align	8
+GLOBAL(stub_x32_execveat)
 GLOBAL(stub32_execveat)
-	CFI_STARTPROC
 	call	compat_sys_execveat
 	jmp	return_from_execve
-	CFI_ENDPROC
 END(stub32_execveat)
+END(stub_x32_execveat)
 #endif
 
 /*
@@ -574,8 +467,6 @@ END(stub32_execveat)
  * This cannot be done with SYSRET, so use the IRET return path instead.
  */
 ENTRY(stub_rt_sigreturn)
-	CFI_STARTPROC
-	DEFAULT_FRAME 0, 8
 	/*
 	 * SAVE_EXTRA_REGS result is not normally needed:
 	 * sigreturn overwrites all pt_regs->GPREGS.
@@ -584,24 +475,19 @@ ENTRY(stub_rt_sigreturn)
 	 * we SAVE_EXTRA_REGS here.
 	 */
 	SAVE_EXTRA_REGS 8
-	call sys_rt_sigreturn
+	call	sys_rt_sigreturn
 return_from_stub:
 	addq	$8, %rsp
-	CFI_ADJUST_CFA_OFFSET -8
 	RESTORE_EXTRA_REGS
-	movq %rax,RAX(%rsp)
-	jmp int_ret_from_sys_call
-	CFI_ENDPROC
+	movq	%rax, RAX(%rsp)
+	jmp	int_ret_from_sys_call
 END(stub_rt_sigreturn)
 
 #ifdef CONFIG_X86_X32_ABI
 ENTRY(stub_x32_rt_sigreturn)
-	CFI_STARTPROC
-	DEFAULT_FRAME 0, 8
 	SAVE_EXTRA_REGS 8
-	call sys32_x32_rt_sigreturn
-	jmp  return_from_stub
-	CFI_ENDPROC
+	call	sys32_x32_rt_sigreturn
+	jmp	return_from_stub
 END(stub_x32_rt_sigreturn)
 #endif
 
@@ -611,36 +497,36 @@ END(stub_x32_rt_sigreturn)
  * rdi: prev task we switched from
  */
 ENTRY(ret_from_fork)
-	DEFAULT_FRAME
 
-	LOCK ; btr $TIF_FORK,TI_flags(%r8)
+	LOCK ; btr $TIF_FORK, TI_flags(%r8)
 
-	pushq_cfi $0x0002
-	popfq_cfi				# reset kernel eflags
+	pushq	$0x0002
+	popfq					/* reset kernel eflags */
 
-	call schedule_tail			# rdi: 'prev' task parameter
+	call	schedule_tail			/* rdi: 'prev' task parameter */
 
 	RESTORE_EXTRA_REGS
 
-	testl $3,CS(%rsp)			# from kernel_thread?
+	testb	$3, CS(%rsp)			/* from kernel_thread? */
 
 	/*
 	 * By the time we get here, we have no idea whether our pt_regs,
 	 * ti flags, and ti status came from the 64-bit SYSCALL fast path,
-	 * the slow path, or one of the ia32entry paths.
+	 * the slow path, or one of the 32-bit compat paths.
 	 * Use IRET code path to return, since it can safely handle
 	 * all of the above.
 	 */
 	jnz	int_ret_from_sys_call
 
-	/* We came from kernel_thread */
-	/* nb: we depend on RESTORE_EXTRA_REGS above */
-	movq %rbp, %rdi
-	call *%rbx
-	movl $0, RAX(%rsp)
+	/*
+	 * We came from kernel_thread
+	 * nb: we depend on RESTORE_EXTRA_REGS above
+	 */
+	movq	%rbp, %rdi
+	call	*%rbx
+	movl	$0, RAX(%rsp)
 	RESTORE_EXTRA_REGS
-	jmp int_ret_from_sys_call
-	CFI_ENDPROC
+	jmp	int_ret_from_sys_call
 END(ret_from_fork)
 
 /*
@@ -649,16 +535,13 @@ END(ret_from_fork)
  */
 	.align 8
 ENTRY(irq_entries_start)
-	INTR_FRAME
     vector=FIRST_EXTERNAL_VECTOR
     .rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR)
-	pushq_cfi $(~vector+0x80)	/* Note: always in signed byte range */
+	pushq	$(~vector+0x80)			/* Note: always in signed byte range */
     vector=vector+1
 	jmp	common_interrupt
-	CFI_ADJUST_CFA_OFFSET -8
 	.align	8
     .endr
-	CFI_ENDPROC
 END(irq_entries_start)
 
 /*
@@ -684,10 +567,10 @@ END(irq_entries_start)
 	/* this goes to 0(%rsp) for unwinder, not for saving the value: */
 	SAVE_EXTRA_REGS_RBP -RBP
 
-	leaq -RBP(%rsp),%rdi	/* arg1 for \func (pointer to pt_regs) */
+	leaq	-RBP(%rsp), %rdi		/* arg1 for \func (pointer to pt_regs) */
 
-	testl $3, CS-RBP(%rsp)
-	je 1f
+	testb	$3, CS-RBP(%rsp)
+	jz	1f
 	SWAPGS
 1:
 	/*
@@ -697,24 +580,14 @@ END(irq_entries_start)
 	 * a little cheaper to use a separate counter in the PDA (short of
 	 * moving irq_enter into assembly, which would be too much work)
 	 */
-	movq %rsp, %rsi
-	incl PER_CPU_VAR(irq_count)
-	cmovzq PER_CPU_VAR(irq_stack_ptr),%rsp
-	CFI_DEF_CFA_REGISTER	rsi
-	pushq %rsi
-	/*
-	 * For debugger:
-	 * "CFA (Current Frame Address) is the value on stack + offset"
-	 */
-	CFI_ESCAPE	0x0f /* DW_CFA_def_cfa_expression */, 6, \
-			0x77 /* DW_OP_breg7 (rsp) */, 0, \
-			0x06 /* DW_OP_deref */, \
-			0x08 /* DW_OP_const1u */, SIZEOF_PTREGS-RBP, \
-			0x22 /* DW_OP_plus */
+	movq	%rsp, %rsi
+	incl	PER_CPU_VAR(irq_count)
+	cmovzq	PER_CPU_VAR(irq_stack_ptr), %rsp
+	pushq	%rsi
 	/* We entered an interrupt context - irqs are off: */
 	TRACE_IRQS_OFF
 
-	call \func
+	call	\func
 	.endm
 
 	/*
@@ -723,42 +596,36 @@ END(irq_entries_start)
 	 */
 	.p2align CONFIG_X86_L1_CACHE_SHIFT
 common_interrupt:
-	XCPT_FRAME
 	ASM_CLAC
-	addq $-0x80,(%rsp)		/* Adjust vector to [-256,-1] range */
+	addq	$-0x80, (%rsp)			/* Adjust vector to [-256, -1] range */
 	interrupt do_IRQ
 	/* 0(%rsp): old RSP */
 ret_from_intr:
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
-	decl PER_CPU_VAR(irq_count)
+	decl	PER_CPU_VAR(irq_count)
 
 	/* Restore saved previous stack */
-	popq %rsi
-	CFI_DEF_CFA rsi,SIZEOF_PTREGS-RBP /* reg/off reset after def_cfa_expr */
+	popq	%rsi
 	/* return code expects complete pt_regs - adjust rsp accordingly: */
-	leaq -RBP(%rsi),%rsp
-	CFI_DEF_CFA_REGISTER	rsp
-	CFI_ADJUST_CFA_OFFSET	RBP
+	leaq	-RBP(%rsi), %rsp
 
-	testl $3,CS(%rsp)
-	je retint_kernel
+	testb	$3, CS(%rsp)
+	jz	retint_kernel
 	/* Interrupt came from user space */
-
+retint_user:
 	GET_THREAD_INFO(%rcx)
-	/*
-	 * %rcx: thread info. Interrupts off.
-	 */
+
+	/* %rcx: thread info. Interrupts are off. */
 retint_with_reschedule:
-	movl $_TIF_WORK_MASK,%edi
+	movl	$_TIF_WORK_MASK, %edi
 retint_check:
 	LOCKDEP_SYS_EXIT_IRQ
-	movl TI_flags(%rcx),%edx
-	andl %edi,%edx
-	CFI_REMEMBER_STATE
-	jnz  retint_careful
+	movl	TI_flags(%rcx), %edx
+	andl	%edi, %edx
+	jnz	retint_careful
 
-retint_swapgs:		/* return to user-space */
+retint_swapgs:					/* return to user-space */
 	/*
 	 * The iretq could re-enable interrupts:
 	 */
@@ -773,9 +640,9 @@ retint_kernel:
 #ifdef CONFIG_PREEMPT
 	/* Interrupts are off */
 	/* Check if we need preemption */
-	bt	$9,EFLAGS(%rsp)	/* interrupts were off? */
+	bt	$9, EFLAGS(%rsp)		/* were interrupts off? */
 	jnc	1f
-0:	cmpl	$0,PER_CPU_VAR(__preempt_count)
+0:	cmpl	$0, PER_CPU_VAR(__preempt_count)
 	jnz	1f
 	call	preempt_schedule_irq
 	jmp	0b
@@ -793,8 +660,6 @@ retint_kernel:
 restore_c_regs_and_iret:
 	RESTORE_C_REGS
 	REMOVE_PT_GPREGS_FROM_STACK 8
-
-irq_return:
 	INTERRUPT_RETURN
 
 ENTRY(native_iret)
@@ -803,8 +668,8 @@ ENTRY(native_iret)
 	 * 64-bit mode SS:RSP on the exception stack is always valid.
 	 */
 #ifdef CONFIG_X86_ESPFIX64
-	testb $4,(SS-RIP)(%rsp)
-	jnz native_irq_return_ldt
+	testb	$4, (SS-RIP)(%rsp)
+	jnz	native_irq_return_ldt
 #endif
 
 .global native_irq_return_iret
@@ -819,62 +684,60 @@ native_irq_return_iret:
 
 #ifdef CONFIG_X86_ESPFIX64
 native_irq_return_ldt:
-	pushq_cfi %rax
-	pushq_cfi %rdi
+	pushq	%rax
+	pushq	%rdi
 	SWAPGS
-	movq PER_CPU_VAR(espfix_waddr),%rdi
-	movq %rax,(0*8)(%rdi)	/* RAX */
-	movq (2*8)(%rsp),%rax	/* RIP */
-	movq %rax,(1*8)(%rdi)
-	movq (3*8)(%rsp),%rax	/* CS */
-	movq %rax,(2*8)(%rdi)
-	movq (4*8)(%rsp),%rax	/* RFLAGS */
-	movq %rax,(3*8)(%rdi)
-	movq (6*8)(%rsp),%rax	/* SS */
-	movq %rax,(5*8)(%rdi)
-	movq (5*8)(%rsp),%rax	/* RSP */
-	movq %rax,(4*8)(%rdi)
-	andl $0xffff0000,%eax
-	popq_cfi %rdi
-	orq PER_CPU_VAR(espfix_stack),%rax
+	movq	PER_CPU_VAR(espfix_waddr), %rdi
+	movq	%rax, (0*8)(%rdi)		/* RAX */
+	movq	(2*8)(%rsp), %rax		/* RIP */
+	movq	%rax, (1*8)(%rdi)
+	movq	(3*8)(%rsp), %rax		/* CS */
+	movq	%rax, (2*8)(%rdi)
+	movq	(4*8)(%rsp), %rax		/* RFLAGS */
+	movq	%rax, (3*8)(%rdi)
+	movq	(6*8)(%rsp), %rax		/* SS */
+	movq	%rax, (5*8)(%rdi)
+	movq	(5*8)(%rsp), %rax		/* RSP */
+	movq	%rax, (4*8)(%rdi)
+	andl	$0xffff0000, %eax
+	popq	%rdi
+	orq	PER_CPU_VAR(espfix_stack), %rax
 	SWAPGS
-	movq %rax,%rsp
-	popq_cfi %rax
-	jmp native_irq_return_iret
+	movq	%rax, %rsp
+	popq	%rax
+	jmp	native_irq_return_iret
 #endif
 
 	/* edi: workmask, edx: work */
 retint_careful:
-	CFI_RESTORE_STATE
-	bt    $TIF_NEED_RESCHED,%edx
-	jnc   retint_signal
+	bt	$TIF_NEED_RESCHED, %edx
+	jnc	retint_signal
 	TRACE_IRQS_ON
 	ENABLE_INTERRUPTS(CLBR_NONE)
-	pushq_cfi %rdi
+	pushq	%rdi
 	SCHEDULE_USER
-	popq_cfi %rdi
+	popq	%rdi
 	GET_THREAD_INFO(%rcx)
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
-	jmp retint_check
+	jmp	retint_check
 
 retint_signal:
-	testl $_TIF_DO_NOTIFY_MASK,%edx
-	jz    retint_swapgs
+	testl	$_TIF_DO_NOTIFY_MASK, %edx
+	jz	retint_swapgs
 	TRACE_IRQS_ON
 	ENABLE_INTERRUPTS(CLBR_NONE)
 	SAVE_EXTRA_REGS
-	movq $-1,ORIG_RAX(%rsp)
-	xorl %esi,%esi		# oldset
-	movq %rsp,%rdi		# &pt_regs
-	call do_notify_resume
+	movq	$-1, ORIG_RAX(%rsp)
+	xorl	%esi, %esi			/* oldset */
+	movq	%rsp, %rdi			/* &pt_regs */
+	call	do_notify_resume
 	RESTORE_EXTRA_REGS
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
 	GET_THREAD_INFO(%rcx)
-	jmp retint_with_reschedule
+	jmp	retint_with_reschedule
 
-	CFI_ENDPROC
 END(common_interrupt)
 
 /*
@@ -882,13 +745,11 @@ END(common_interrupt)
  */
 .macro apicinterrupt3 num sym do_sym
 ENTRY(\sym)
-	INTR_FRAME
 	ASM_CLAC
-	pushq_cfi $~(\num)
+	pushq	$~(\num)
 .Lcommon_\sym:
 	interrupt \do_sym
-	jmp ret_from_intr
-	CFI_ENDPROC
+	jmp	ret_from_intr
 END(\sym)
 .endm
 
@@ -910,53 +771,45 @@ trace_apicinterrupt \num \sym
 .endm
 
 #ifdef CONFIG_SMP
-apicinterrupt3 IRQ_MOVE_CLEANUP_VECTOR \
-	irq_move_cleanup_interrupt smp_irq_move_cleanup_interrupt
-apicinterrupt3 REBOOT_VECTOR \
-	reboot_interrupt smp_reboot_interrupt
+apicinterrupt3 IRQ_MOVE_CLEANUP_VECTOR		irq_move_cleanup_interrupt	smp_irq_move_cleanup_interrupt
+apicinterrupt3 REBOOT_VECTOR			reboot_interrupt		smp_reboot_interrupt
 #endif
 
 #ifdef CONFIG_X86_UV
-apicinterrupt3 UV_BAU_MESSAGE \
-	uv_bau_message_intr1 uv_bau_message_interrupt
+apicinterrupt3 UV_BAU_MESSAGE			uv_bau_message_intr1		uv_bau_message_interrupt
 #endif
-apicinterrupt LOCAL_TIMER_VECTOR \
-	apic_timer_interrupt smp_apic_timer_interrupt
-apicinterrupt X86_PLATFORM_IPI_VECTOR \
-	x86_platform_ipi smp_x86_platform_ipi
+
+apicinterrupt LOCAL_TIMER_VECTOR		apic_timer_interrupt		smp_apic_timer_interrupt
+apicinterrupt X86_PLATFORM_IPI_VECTOR		x86_platform_ipi		smp_x86_platform_ipi
 
 #ifdef CONFIG_HAVE_KVM
-apicinterrupt3 POSTED_INTR_VECTOR \
-	kvm_posted_intr_ipi smp_kvm_posted_intr_ipi
+apicinterrupt3 POSTED_INTR_VECTOR		kvm_posted_intr_ipi		smp_kvm_posted_intr_ipi
+apicinterrupt3 POSTED_INTR_WAKEUP_VECTOR	kvm_posted_intr_wakeup_ipi	smp_kvm_posted_intr_wakeup_ipi
 #endif
 
 #ifdef CONFIG_X86_MCE_THRESHOLD
-apicinterrupt THRESHOLD_APIC_VECTOR \
-	threshold_interrupt smp_threshold_interrupt
+apicinterrupt THRESHOLD_APIC_VECTOR		threshold_interrupt		smp_threshold_interrupt
+#endif
+
+#ifdef CONFIG_X86_MCE_AMD
+apicinterrupt DEFERRED_ERROR_VECTOR		deferred_error_interrupt	smp_deferred_error_interrupt
 #endif
 
 #ifdef CONFIG_X86_THERMAL_VECTOR
-apicinterrupt THERMAL_APIC_VECTOR \
-	thermal_interrupt smp_thermal_interrupt
+apicinterrupt THERMAL_APIC_VECTOR		thermal_interrupt		smp_thermal_interrupt
 #endif
 
 #ifdef CONFIG_SMP
-apicinterrupt CALL_FUNCTION_SINGLE_VECTOR \
-	call_function_single_interrupt smp_call_function_single_interrupt
-apicinterrupt CALL_FUNCTION_VECTOR \
-	call_function_interrupt smp_call_function_interrupt
-apicinterrupt RESCHEDULE_VECTOR \
-	reschedule_interrupt smp_reschedule_interrupt
+apicinterrupt CALL_FUNCTION_SINGLE_VECTOR	call_function_single_interrupt	smp_call_function_single_interrupt
+apicinterrupt CALL_FUNCTION_VECTOR		call_function_interrupt		smp_call_function_interrupt
+apicinterrupt RESCHEDULE_VECTOR			reschedule_interrupt		smp_reschedule_interrupt
 #endif
 
-apicinterrupt ERROR_APIC_VECTOR \
-	error_interrupt smp_error_interrupt
-apicinterrupt SPURIOUS_APIC_VECTOR \
-	spurious_interrupt smp_spurious_interrupt
+apicinterrupt ERROR_APIC_VECTOR			error_interrupt			smp_error_interrupt
+apicinterrupt SPURIOUS_APIC_VECTOR		spurious_interrupt		smp_spurious_interrupt
 
 #ifdef CONFIG_IRQ_WORK
-apicinterrupt IRQ_WORK_VECTOR \
-	irq_work_interrupt smp_irq_work_interrupt
+apicinterrupt IRQ_WORK_VECTOR			irq_work_interrupt		smp_irq_work_interrupt
 #endif
 
 /*
@@ -971,100 +824,87 @@ ENTRY(\sym)
 	.error "using shift_ist requires paranoid=1"
 	.endif
 
-	.if \has_error_code
-	XCPT_FRAME
-	.else
-	INTR_FRAME
-	.endif
-
 	ASM_CLAC
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
 
 	.ifeq \has_error_code
-	pushq_cfi $-1			/* ORIG_RAX: no syscall to restart */
+	pushq	$-1				/* ORIG_RAX: no syscall to restart */
 	.endif
 
 	ALLOC_PT_GPREGS_ON_STACK
 
 	.if \paranoid
 	.if \paranoid == 1
-	CFI_REMEMBER_STATE
-	testl $3, CS(%rsp)		/* If coming from userspace, switch */
-	jnz 1f				/* stacks. */
+	testb	$3, CS(%rsp)			/* If coming from userspace, switch stacks */
+	jnz	1f
 	.endif
-	call paranoid_entry
+	call	paranoid_entry
 	.else
-	call error_entry
+	call	error_entry
 	.endif
 	/* returned flag: ebx=0: need swapgs on exit, ebx=1: don't need it */
 
-	DEFAULT_FRAME 0
-
 	.if \paranoid
 	.if \shift_ist != -1
-	TRACE_IRQS_OFF_DEBUG		/* reload IDT in case of recursion */
+	TRACE_IRQS_OFF_DEBUG			/* reload IDT in case of recursion */
 	.else
 	TRACE_IRQS_OFF
 	.endif
 	.endif
 
-	movq %rsp,%rdi			/* pt_regs pointer */
+	movq	%rsp, %rdi			/* pt_regs pointer */
 
 	.if \has_error_code
-	movq ORIG_RAX(%rsp),%rsi	/* get error code */
-	movq $-1,ORIG_RAX(%rsp)		/* no syscall to restart */
+	movq	ORIG_RAX(%rsp), %rsi		/* get error code */
+	movq	$-1, ORIG_RAX(%rsp)		/* no syscall to restart */
 	.else
-	xorl %esi,%esi			/* no error code */
+	xorl	%esi, %esi			/* no error code */
 	.endif
 
 	.if \shift_ist != -1
-	subq $EXCEPTION_STKSZ, CPU_TSS_IST(\shift_ist)
+	subq	$EXCEPTION_STKSZ, CPU_TSS_IST(\shift_ist)
 	.endif
 
-	call \do_sym
+	call	\do_sym
 
 	.if \shift_ist != -1
-	addq $EXCEPTION_STKSZ, CPU_TSS_IST(\shift_ist)
+	addq	$EXCEPTION_STKSZ, CPU_TSS_IST(\shift_ist)
 	.endif
 
 	/* these procedures expect "no swapgs" flag in ebx */
 	.if \paranoid
-	jmp paranoid_exit
+	jmp	paranoid_exit
 	.else
-	jmp error_exit
+	jmp	error_exit
 	.endif
 
 	.if \paranoid == 1
-	CFI_RESTORE_STATE
 	/*
 	 * Paranoid entry from userspace.  Switch stacks and treat it
 	 * as a normal entry.  This means that paranoid handlers
 	 * run in real process context if user_mode(regs).
 	 */
 1:
-	call error_entry
+	call	error_entry
 
-	DEFAULT_FRAME 0
 
-	movq %rsp,%rdi			/* pt_regs pointer */
-	call sync_regs
-	movq %rax,%rsp			/* switch stack */
+	movq	%rsp, %rdi			/* pt_regs pointer */
+	call	sync_regs
+	movq	%rax, %rsp			/* switch stack */
 
-	movq %rsp,%rdi			/* pt_regs pointer */
+	movq	%rsp, %rdi			/* pt_regs pointer */
 
 	.if \has_error_code
-	movq ORIG_RAX(%rsp),%rsi	/* get error code */
-	movq $-1,ORIG_RAX(%rsp)		/* no syscall to restart */
+	movq	ORIG_RAX(%rsp), %rsi		/* get error code */
+	movq	$-1, ORIG_RAX(%rsp)		/* no syscall to restart */
 	.else
-	xorl %esi,%esi			/* no error code */
+	xorl	%esi, %esi			/* no error code */
 	.endif
 
-	call \do_sym
+	call	\do_sym
 
-	jmp error_exit			/* %ebx: no swapgs flag */
+	jmp	error_exit			/* %ebx: no swapgs flag */
 	.endif
-
-	CFI_ENDPROC
 END(\sym)
 .endm
 
@@ -1079,65 +919,58 @@ idtentry \sym \do_sym has_error_code=\has_error_code
 .endm
 #endif
 
-idtentry divide_error do_divide_error has_error_code=0
-idtentry overflow do_overflow has_error_code=0
-idtentry bounds do_bounds has_error_code=0
-idtentry invalid_op do_invalid_op has_error_code=0
-idtentry device_not_available do_device_not_available has_error_code=0
-idtentry double_fault do_double_fault has_error_code=1 paranoid=2
-idtentry coprocessor_segment_overrun do_coprocessor_segment_overrun has_error_code=0
-idtentry invalid_TSS do_invalid_TSS has_error_code=1
-idtentry segment_not_present do_segment_not_present has_error_code=1
-idtentry spurious_interrupt_bug do_spurious_interrupt_bug has_error_code=0
-idtentry coprocessor_error do_coprocessor_error has_error_code=0
-idtentry alignment_check do_alignment_check has_error_code=1
-idtentry simd_coprocessor_error do_simd_coprocessor_error has_error_code=0
-
-
-	/* Reload gs selector with exception handling */
-	/* edi:  new selector */
+idtentry divide_error			do_divide_error			has_error_code=0
+idtentry overflow			do_overflow			has_error_code=0
+idtentry bounds				do_bounds			has_error_code=0
+idtentry invalid_op			do_invalid_op			has_error_code=0
+idtentry device_not_available		do_device_not_available		has_error_code=0
+idtentry double_fault			do_double_fault			has_error_code=1 paranoid=2
+idtentry coprocessor_segment_overrun	do_coprocessor_segment_overrun	has_error_code=0
+idtentry invalid_TSS			do_invalid_TSS			has_error_code=1
+idtentry segment_not_present		do_segment_not_present		has_error_code=1
+idtentry spurious_interrupt_bug		do_spurious_interrupt_bug	has_error_code=0
+idtentry coprocessor_error		do_coprocessor_error		has_error_code=0
+idtentry alignment_check		do_alignment_check		has_error_code=1
+idtentry simd_coprocessor_error		do_simd_coprocessor_error	has_error_code=0
+
+
+	/*
+	 * Reload gs selector with exception handling
+	 * edi:  new selector
+	 */
 ENTRY(native_load_gs_index)
-	CFI_STARTPROC
-	pushfq_cfi
+	pushfq
 	DISABLE_INTERRUPTS(CLBR_ANY & ~CLBR_RDI)
 	SWAPGS
 gs_change:
-	movl %edi,%gs
-2:	mfence		/* workaround */
+	movl	%edi, %gs
+2:	mfence					/* workaround */
 	SWAPGS
-	popfq_cfi
+	popfq
 	ret
-	CFI_ENDPROC
 END(native_load_gs_index)
 
-	_ASM_EXTABLE(gs_change,bad_gs)
-	.section .fixup,"ax"
+	_ASM_EXTABLE(gs_change, bad_gs)
+	.section .fixup, "ax"
 	/* running with kernelgs */
 bad_gs:
-	SWAPGS			/* switch back to user gs */
-	xorl %eax,%eax
-	movl %eax,%gs
-	jmp  2b
+	SWAPGS					/* switch back to user gs */
+	xorl	%eax, %eax
+	movl	%eax, %gs
+	jmp	2b
 	.previous
 
 /* Call softirq on interrupt stack. Interrupts are off. */
 ENTRY(do_softirq_own_stack)
-	CFI_STARTPROC
-	pushq_cfi %rbp
-	CFI_REL_OFFSET rbp,0
-	mov  %rsp,%rbp
-	CFI_DEF_CFA_REGISTER rbp
-	incl PER_CPU_VAR(irq_count)
-	cmove PER_CPU_VAR(irq_stack_ptr),%rsp
-	push  %rbp			# backlink for old unwinder
-	call __do_softirq
+	pushq	%rbp
+	mov	%rsp, %rbp
+	incl	PER_CPU_VAR(irq_count)
+	cmove	PER_CPU_VAR(irq_stack_ptr), %rsp
+	push	%rbp				/* frame pointer backlink */
+	call	__do_softirq
 	leaveq
-	CFI_RESTORE		rbp
-	CFI_DEF_CFA_REGISTER	rsp
-	CFI_ADJUST_CFA_OFFSET   -8
-	decl PER_CPU_VAR(irq_count)
+	decl	PER_CPU_VAR(irq_count)
 	ret
-	CFI_ENDPROC
 END(do_softirq_own_stack)
 
 #ifdef CONFIG_XEN
@@ -1156,29 +989,24 @@ idtentry xen_hypervisor_callback xen_do_hypervisor_callback has_error_code=0
  * existing activation in its critical region -- if so, we pop the current
  * activation and restart the handler using the previous one.
  */
-ENTRY(xen_do_hypervisor_callback)   # do_hypervisor_callback(struct *pt_regs)
-	CFI_STARTPROC
+ENTRY(xen_do_hypervisor_callback)		/* do_hypervisor_callback(struct *pt_regs) */
+
 /*
  * Since we don't modify %rdi, evtchn_do_upall(struct *pt_regs) will
  * see the correct pointer to the pt_regs
  */
-	movq %rdi, %rsp            # we don't return, adjust the stack frame
-	CFI_ENDPROC
-	DEFAULT_FRAME
-11:	incl PER_CPU_VAR(irq_count)
-	movq %rsp,%rbp
-	CFI_DEF_CFA_REGISTER rbp
-	cmovzq PER_CPU_VAR(irq_stack_ptr),%rsp
-	pushq %rbp			# backlink for old unwinder
-	call xen_evtchn_do_upcall
-	popq %rsp
-	CFI_DEF_CFA_REGISTER rsp
-	decl PER_CPU_VAR(irq_count)
+	movq	%rdi, %rsp			/* we don't return, adjust the stack frame */
+11:	incl	PER_CPU_VAR(irq_count)
+	movq	%rsp, %rbp
+	cmovzq	PER_CPU_VAR(irq_stack_ptr), %rsp
+	pushq	%rbp				/* frame pointer backlink */
+	call	xen_evtchn_do_upcall
+	popq	%rsp
+	decl	PER_CPU_VAR(irq_count)
 #ifndef CONFIG_PREEMPT
-	call xen_maybe_preempt_hcall
+	call	xen_maybe_preempt_hcall
 #endif
-	jmp  error_exit
-	CFI_ENDPROC
+	jmp	error_exit
 END(xen_do_hypervisor_callback)
 
 /*
@@ -1195,51 +1023,35 @@ END(xen_do_hypervisor_callback)
  * with its current contents: any discrepancy means we in category 1.
  */
 ENTRY(xen_failsafe_callback)
-	INTR_FRAME 1 (6*8)
-	/*CFI_REL_OFFSET gs,GS*/
-	/*CFI_REL_OFFSET fs,FS*/
-	/*CFI_REL_OFFSET es,ES*/
-	/*CFI_REL_OFFSET ds,DS*/
-	CFI_REL_OFFSET r11,8
-	CFI_REL_OFFSET rcx,0
-	movw %ds,%cx
-	cmpw %cx,0x10(%rsp)
-	CFI_REMEMBER_STATE
-	jne 1f
-	movw %es,%cx
-	cmpw %cx,0x18(%rsp)
-	jne 1f
-	movw %fs,%cx
-	cmpw %cx,0x20(%rsp)
-	jne 1f
-	movw %gs,%cx
-	cmpw %cx,0x28(%rsp)
-	jne 1f
+	movl	%ds, %ecx
+	cmpw	%cx, 0x10(%rsp)
+	jne	1f
+	movl	%es, %ecx
+	cmpw	%cx, 0x18(%rsp)
+	jne	1f
+	movl	%fs, %ecx
+	cmpw	%cx, 0x20(%rsp)
+	jne	1f
+	movl	%gs, %ecx
+	cmpw	%cx, 0x28(%rsp)
+	jne	1f
 	/* All segments match their saved values => Category 2 (Bad IRET). */
-	movq (%rsp),%rcx
-	CFI_RESTORE rcx
-	movq 8(%rsp),%r11
-	CFI_RESTORE r11
-	addq $0x30,%rsp
-	CFI_ADJUST_CFA_OFFSET -0x30
-	pushq_cfi $0	/* RIP */
-	pushq_cfi %r11
-	pushq_cfi %rcx
-	jmp general_protection
-	CFI_RESTORE_STATE
+	movq	(%rsp), %rcx
+	movq	8(%rsp), %r11
+	addq	$0x30, %rsp
+	pushq	$0				/* RIP */
+	pushq	%r11
+	pushq	%rcx
+	jmp	general_protection
 1:	/* Segment mismatch => Category 1 (Bad segment). Retry the IRET. */
-	movq (%rsp),%rcx
-	CFI_RESTORE rcx
-	movq 8(%rsp),%r11
-	CFI_RESTORE r11
-	addq $0x30,%rsp
-	CFI_ADJUST_CFA_OFFSET -0x30
-	pushq_cfi $-1 /* orig_ax = -1 => not a system call */
+	movq	(%rsp), %rcx
+	movq	8(%rsp), %r11
+	addq	$0x30, %rsp
+	pushq	$-1 /* orig_ax = -1 => not a system call */
 	ALLOC_PT_GPREGS_ON_STACK
 	SAVE_C_REGS
 	SAVE_EXTRA_REGS
-	jmp error_exit
-	CFI_ENDPROC
+	jmp	error_exit
 END(xen_failsafe_callback)
 
 apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \
@@ -1252,21 +1064,25 @@ apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \
 	hyperv_callback_vector hyperv_vector_handler
 #endif /* CONFIG_HYPERV */
 
-idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK
-idtentry int3 do_int3 has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK
-idtentry stack_segment do_stack_segment has_error_code=1
+idtentry debug			do_debug		has_error_code=0	paranoid=1 shift_ist=DEBUG_STACK
+idtentry int3			do_int3			has_error_code=0	paranoid=1 shift_ist=DEBUG_STACK
+idtentry stack_segment		do_stack_segment	has_error_code=1
+
 #ifdef CONFIG_XEN
-idtentry xen_debug do_debug has_error_code=0
-idtentry xen_int3 do_int3 has_error_code=0
-idtentry xen_stack_segment do_stack_segment has_error_code=1
+idtentry xen_debug		do_debug		has_error_code=0
+idtentry xen_int3		do_int3			has_error_code=0
+idtentry xen_stack_segment	do_stack_segment	has_error_code=1
 #endif
-idtentry general_protection do_general_protection has_error_code=1
-trace_idtentry page_fault do_page_fault has_error_code=1
+
+idtentry general_protection	do_general_protection	has_error_code=1
+trace_idtentry page_fault	do_page_fault		has_error_code=1
+
 #ifdef CONFIG_KVM_GUEST
-idtentry async_page_fault do_async_page_fault has_error_code=1
+idtentry async_page_fault	do_async_page_fault	has_error_code=1
 #endif
+
 #ifdef CONFIG_X86_MCE
-idtentry machine_check has_error_code=0 paranoid=1 do_sym=*machine_check_vector(%rip)
+idtentry machine_check					has_error_code=0	paranoid=1 do_sym=*machine_check_vector(%rip)
 #endif
 
 /*
@@ -1275,19 +1091,17 @@ idtentry machine_check has_error_code=0 paranoid=1 do_sym=*machine_check_vector(
  * Return: ebx=0: need swapgs on exit, ebx=1: otherwise
  */
 ENTRY(paranoid_entry)
-	XCPT_FRAME 1 15*8
 	cld
 	SAVE_C_REGS 8
 	SAVE_EXTRA_REGS 8
-	movl $1,%ebx
-	movl $MSR_GS_BASE,%ecx
+	movl	$1, %ebx
+	movl	$MSR_GS_BASE, %ecx
 	rdmsr
-	testl %edx,%edx
-	js 1f	/* negative -> in kernel */
+	testl	%edx, %edx
+	js	1f				/* negative -> in kernel */
 	SWAPGS
-	xorl %ebx,%ebx
+	xorl	%ebx, %ebx
 1:	ret
-	CFI_ENDPROC
 END(paranoid_entry)
 
 /*
@@ -1299,17 +1113,17 @@ END(paranoid_entry)
  * in syscall entry), so checking for preemption here would
  * be complicated.  Fortunately, we there's no good reason
  * to try to handle preemption here.
+ *
+ * On entry, ebx is "no swapgs" flag (1: don't need swapgs, 0: need it)
  */
-/* On entry, ebx is "no swapgs" flag (1: don't need swapgs, 0: need it) */
 ENTRY(paranoid_exit)
-	DEFAULT_FRAME
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF_DEBUG
-	testl %ebx,%ebx				/* swapgs needed? */
-	jnz paranoid_exit_no_swapgs
+	testl	%ebx, %ebx			/* swapgs needed? */
+	jnz	paranoid_exit_no_swapgs
 	TRACE_IRQS_IRETQ
 	SWAPGS_UNSAFE_STACK
-	jmp paranoid_exit_restore
+	jmp	paranoid_exit_restore
 paranoid_exit_no_swapgs:
 	TRACE_IRQS_IRETQ_DEBUG
 paranoid_exit_restore:
@@ -1317,24 +1131,24 @@ paranoid_exit_restore:
 	RESTORE_C_REGS
 	REMOVE_PT_GPREGS_FROM_STACK 8
 	INTERRUPT_RETURN
-	CFI_ENDPROC
 END(paranoid_exit)
 
 /*
  * Save all registers in pt_regs, and switch gs if needed.
- * Return: ebx=0: need swapgs on exit, ebx=1: otherwise
+ * Return: EBX=0: came from user mode; EBX=1: otherwise
  */
 ENTRY(error_entry)
-	XCPT_FRAME 1 15*8
 	cld
 	SAVE_C_REGS 8
 	SAVE_EXTRA_REGS 8
-	xorl %ebx,%ebx
-	testl $3,CS+8(%rsp)
-	je error_kernelspace
-error_swapgs:
+	xorl	%ebx, %ebx
+	testb	$3, CS+8(%rsp)
+	jz	error_kernelspace
+
+	/* We entered from user mode */
 	SWAPGS
-error_sti:
+
+error_entry_done:
 	TRACE_IRQS_OFF
 	ret
 
@@ -1345,56 +1159,66 @@ error_sti:
 	 * for these here too.
 	 */
 error_kernelspace:
-	CFI_REL_OFFSET rcx, RCX+8
-	incl %ebx
-	leaq native_irq_return_iret(%rip),%rcx
-	cmpq %rcx,RIP+8(%rsp)
-	je error_bad_iret
-	movl %ecx,%eax	/* zero extend */
-	cmpq %rax,RIP+8(%rsp)
-	je bstep_iret
-	cmpq $gs_change,RIP+8(%rsp)
-	je error_swapgs
-	jmp error_sti
+	incl	%ebx
+	leaq	native_irq_return_iret(%rip), %rcx
+	cmpq	%rcx, RIP+8(%rsp)
+	je	error_bad_iret
+	movl	%ecx, %eax			/* zero extend */
+	cmpq	%rax, RIP+8(%rsp)
+	je	bstep_iret
+	cmpq	$gs_change, RIP+8(%rsp)
+	jne	error_entry_done
+
+	/*
+	 * hack: gs_change can fail with user gsbase.  If this happens, fix up
+	 * gsbase and proceed.  We'll fix up the exception and land in
+	 * gs_change's error handler with kernel gsbase.
+	 */
+	SWAPGS
+	jmp	error_entry_done
 
 bstep_iret:
 	/* Fix truncated RIP */
-	movq %rcx,RIP+8(%rsp)
+	movq	%rcx, RIP+8(%rsp)
 	/* fall through */
 
 error_bad_iret:
+	/*
+	 * We came from an IRET to user mode, so we have user gsbase.
+	 * Switch to kernel gsbase:
+	 */
 	SWAPGS
-	mov %rsp,%rdi
-	call fixup_bad_iret
-	mov %rax,%rsp
-	decl %ebx	/* Return to usergs */
-	jmp error_sti
-	CFI_ENDPROC
+
+	/*
+	 * Pretend that the exception came from user mode: set up pt_regs
+	 * as if we faulted immediately after IRET and clear EBX so that
+	 * error_exit knows that we will be returning to user mode.
+	 */
+	mov	%rsp, %rdi
+	call	fixup_bad_iret
+	mov	%rax, %rsp
+	decl	%ebx
+	jmp	error_entry_done
 END(error_entry)
 
 
-/* On entry, ebx is "no swapgs" flag (1: don't need swapgs, 0: need it) */
+/*
+ * On entry, EBS is a "return to kernel mode" flag:
+ *   1: already in kernel mode, don't need SWAPGS
+ *   0: user gsbase is loaded, we need SWAPGS and standard preparation for return to usermode
+ */
 ENTRY(error_exit)
-	DEFAULT_FRAME
-	movl %ebx,%eax
+	movl	%ebx, %eax
 	RESTORE_EXTRA_REGS
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
-	GET_THREAD_INFO(%rcx)
-	testl %eax,%eax
-	jne retint_kernel
-	LOCKDEP_SYS_EXIT_IRQ
-	movl TI_flags(%rcx),%edx
-	movl $_TIF_WORK_MASK,%edi
-	andl %edi,%edx
-	jnz retint_careful
-	jmp retint_swapgs
-	CFI_ENDPROC
+	testl	%eax, %eax
+	jnz	retint_kernel
+	jmp	retint_user
 END(error_exit)
 
 /* Runs on exception stack */
 ENTRY(nmi)
-	INTR_FRAME
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
 	/*
 	 * We allow breakpoints in NMIs. If a breakpoint occurs, then
@@ -1429,22 +1253,21 @@ ENTRY(nmi)
 	 */
 
 	/* Use %rdx as our temp variable throughout */
-	pushq_cfi %rdx
-	CFI_REL_OFFSET rdx, 0
+	pushq	%rdx
 
 	/*
 	 * If %cs was not the kernel segment, then the NMI triggered in user
 	 * space, which means it is definitely not nested.
 	 */
-	cmpl $__KERNEL_CS, 16(%rsp)
-	jne first_nmi
+	cmpl	$__KERNEL_CS, 16(%rsp)
+	jne	first_nmi
 
 	/*
 	 * Check the special variable on the stack to see if NMIs are
 	 * executing.
 	 */
-	cmpl $1, -8(%rsp)
-	je nested_nmi
+	cmpl	$1, -8(%rsp)
+	je	nested_nmi
 
 	/*
 	 * Now test if the previous stack was an NMI stack.
@@ -1458,51 +1281,46 @@ ENTRY(nmi)
 	cmpq	%rdx, 4*8(%rsp)
 	/* If the stack pointer is above the NMI stack, this is a normal NMI */
 	ja	first_nmi
+
 	subq	$EXCEPTION_STKSZ, %rdx
 	cmpq	%rdx, 4*8(%rsp)
 	/* If it is below the NMI stack, it is a normal NMI */
 	jb	first_nmi
 	/* Ah, it is within the NMI stack, treat it as nested */
 
-	CFI_REMEMBER_STATE
-
 nested_nmi:
 	/*
 	 * Do nothing if we interrupted the fixup in repeat_nmi.
 	 * It's about to repeat the NMI handler, so we are fine
 	 * with ignoring this one.
 	 */
-	movq $repeat_nmi, %rdx
-	cmpq 8(%rsp), %rdx
-	ja 1f
-	movq $end_repeat_nmi, %rdx
-	cmpq 8(%rsp), %rdx
-	ja nested_nmi_out
+	movq	$repeat_nmi, %rdx
+	cmpq	8(%rsp), %rdx
+	ja	1f
+	movq	$end_repeat_nmi, %rdx
+	cmpq	8(%rsp), %rdx
+	ja	nested_nmi_out
 
 1:
 	/* Set up the interrupted NMIs stack to jump to repeat_nmi */
-	leaq -1*8(%rsp), %rdx
-	movq %rdx, %rsp
-	CFI_ADJUST_CFA_OFFSET 1*8
-	leaq -10*8(%rsp), %rdx
-	pushq_cfi $__KERNEL_DS
-	pushq_cfi %rdx
-	pushfq_cfi
-	pushq_cfi $__KERNEL_CS
-	pushq_cfi $repeat_nmi
+	leaq	-1*8(%rsp), %rdx
+	movq	%rdx, %rsp
+	leaq	-10*8(%rsp), %rdx
+	pushq	$__KERNEL_DS
+	pushq	%rdx
+	pushfq
+	pushq	$__KERNEL_CS
+	pushq	$repeat_nmi
 
 	/* Put stack back */
-	addq $(6*8), %rsp
-	CFI_ADJUST_CFA_OFFSET -6*8
+	addq	$(6*8), %rsp
 
 nested_nmi_out:
-	popq_cfi %rdx
-	CFI_RESTORE rdx
+	popq	%rdx
 
 	/* No need to check faults here */
 	INTERRUPT_RETURN
 
-	CFI_RESTORE_STATE
 first_nmi:
 	/*
 	 * Because nested NMIs will use the pushed location that we
@@ -1540,23 +1358,18 @@ first_nmi:
 	 * is also used by nested NMIs and can not be trusted on exit.
 	 */
 	/* Do not pop rdx, nested NMIs will corrupt that part of the stack */
-	movq (%rsp), %rdx
-	CFI_RESTORE rdx
+	movq	(%rsp), %rdx
 
 	/* Set the NMI executing variable on the stack. */
-	pushq_cfi $1
+	pushq	$1
 
-	/*
-	 * Leave room for the "copied" frame
-	 */
-	subq $(5*8), %rsp
-	CFI_ADJUST_CFA_OFFSET 5*8
+	/* Leave room for the "copied" frame */
+	subq	$(5*8), %rsp
 
 	/* Copy the stack frame to the Saved frame */
 	.rept 5
-	pushq_cfi 11*8(%rsp)
+	pushq	11*8(%rsp)
 	.endr
-	CFI_DEF_CFA_OFFSET 5*8
 
 	/* Everything up to here is safe from nested NMIs */
 
@@ -1575,16 +1388,14 @@ repeat_nmi:
 	 * is benign for the non-repeat case, where 1 was pushed just above
 	 * to this very stack slot).
 	 */
-	movq $1, 10*8(%rsp)
+	movq	$1, 10*8(%rsp)
 
 	/* Make another copy, this one may be modified by nested NMIs */
-	addq $(10*8), %rsp
-	CFI_ADJUST_CFA_OFFSET -10*8
+	addq	$(10*8), %rsp
 	.rept 5
-	pushq_cfi -6*8(%rsp)
+	pushq	-6*8(%rsp)
 	.endr
-	subq $(5*8), %rsp
-	CFI_DEF_CFA_OFFSET 5*8
+	subq	$(5*8), %rsp
 end_repeat_nmi:
 
 	/*
@@ -1592,7 +1403,7 @@ end_repeat_nmi:
 	 * NMI if the first NMI took an exception and reset our iret stack
 	 * so that we repeat another NMI.
 	 */
-	pushq_cfi $-1		/* ORIG_RAX: no syscall to restart */
+	pushq	$-1				/* ORIG_RAX: no syscall to restart */
 	ALLOC_PT_GPREGS_ON_STACK
 
 	/*
@@ -1602,8 +1413,7 @@ end_repeat_nmi:
 	 * setting NEED_RESCHED or anything that normal interrupts and
 	 * exceptions might do.
 	 */
-	call paranoid_entry
-	DEFAULT_FRAME 0
+	call	paranoid_entry
 
 	/*
 	 * Save off the CR2 register. If we take a page fault in the NMI then
@@ -1614,22 +1424,21 @@ end_repeat_nmi:
 	 * origin fault. Save it off and restore it if it changes.
 	 * Use the r12 callee-saved register.
 	 */
-	movq %cr2, %r12
+	movq	%cr2, %r12
 
 	/* paranoidentry do_nmi, 0; without TRACE_IRQS_OFF */
-	movq %rsp,%rdi
-	movq $-1,%rsi
-	call do_nmi
+	movq	%rsp, %rdi
+	movq	$-1, %rsi
+	call	do_nmi
 
 	/* Did the NMI take a page fault? Restore cr2 if it did */
-	movq %cr2, %rcx
-	cmpq %rcx, %r12
-	je 1f
-	movq %r12, %cr2
+	movq	%cr2, %rcx
+	cmpq	%rcx, %r12
+	je	1f
+	movq	%r12, %cr2
 1:
-	
-	testl %ebx,%ebx				/* swapgs needed? */
-	jnz nmi_restore
+	testl	%ebx, %ebx			/* swapgs needed? */
+	jnz	nmi_restore
 nmi_swapgs:
 	SWAPGS_UNSAFE_STACK
 nmi_restore:
@@ -1639,15 +1448,11 @@ nmi_restore:
 	REMOVE_PT_GPREGS_FROM_STACK 6*8
 
 	/* Clear the NMI executing stack variable */
-	movq $0, 5*8(%rsp)
-	jmp irq_return
-	CFI_ENDPROC
+	movq	$0, 5*8(%rsp)
+	INTERRUPT_RETURN
 END(nmi)
 
 ENTRY(ignore_sysret)
-	CFI_STARTPROC
-	mov $-ENOSYS,%eax
+	mov	$-ENOSYS, %eax
 	sysret
-	CFI_ENDPROC
 END(ignore_sysret)
-
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
new file mode 100644
index 000000000000..bb187a6a877c
--- /dev/null
+++ b/arch/x86/entry/entry_64_compat.S
@@ -0,0 +1,556 @@
+/*
+ * Compatibility mode system call entry point for x86-64.
+ *
+ * Copyright 2000-2002 Andi Kleen, SuSE Labs.
+ */
+#include "calling.h"
+#include <asm/asm-offsets.h>
+#include <asm/current.h>
+#include <asm/errno.h>
+#include <asm/ia32_unistd.h>
+#include <asm/thread_info.h>
+#include <asm/segment.h>
+#include <asm/irqflags.h>
+#include <asm/asm.h>
+#include <asm/smap.h>
+#include <linux/linkage.h>
+#include <linux/err.h>
+
+/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this.  */
+#include <linux/elf-em.h>
+#define AUDIT_ARCH_I386		(EM_386|__AUDIT_ARCH_LE)
+#define __AUDIT_ARCH_LE		0x40000000
+
+#ifndef CONFIG_AUDITSYSCALL
+# define sysexit_audit		ia32_ret_from_sys_call
+# define sysretl_audit		ia32_ret_from_sys_call
+#endif
+
+	.section .entry.text, "ax"
+
+#ifdef CONFIG_PARAVIRT
+ENTRY(native_usergs_sysret32)
+	swapgs
+	sysretl
+ENDPROC(native_usergs_sysret32)
+#endif
+
+/*
+ * 32-bit SYSENTER instruction entry.
+ *
+ * SYSENTER loads ss, rsp, cs, and rip from previously programmed MSRs.
+ * IF and VM in rflags are cleared (IOW: interrupts are off).
+ * SYSENTER does not save anything on the stack,
+ * and does not save old rip (!!!) and rflags.
+ *
+ * Arguments:
+ * eax  system call number
+ * ebx  arg1
+ * ecx  arg2
+ * edx  arg3
+ * esi  arg4
+ * edi  arg5
+ * ebp  user stack
+ * 0(%ebp) arg6
+ *
+ * This is purely a fast path. For anything complicated we use the int 0x80
+ * path below. We set up a complete hardware stack frame to share code
+ * with the int 0x80 path.
+ */
+ENTRY(entry_SYSENTER_compat)
+	/*
+	 * Interrupts are off on entry.
+	 * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
+	 * it is too small to ever cause noticeable irq latency.
+	 */
+	SWAPGS_UNSAFE_STACK
+	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
+	ENABLE_INTERRUPTS(CLBR_NONE)
+
+	/* Zero-extending 32-bit regs, do not remove */
+	movl	%ebp, %ebp
+	movl	%eax, %eax
+
+	movl	ASM_THREAD_INFO(TI_sysenter_return, %rsp, 0), %r10d
+
+	/* Construct struct pt_regs on stack */
+	pushq	$__USER32_DS		/* pt_regs->ss */
+	pushq	%rbp			/* pt_regs->sp */
+	pushfq				/* pt_regs->flags */
+	pushq	$__USER32_CS		/* pt_regs->cs */
+	pushq	%r10			/* pt_regs->ip = thread_info->sysenter_return */
+	pushq	%rax			/* pt_regs->orig_ax */
+	pushq	%rdi			/* pt_regs->di */
+	pushq	%rsi			/* pt_regs->si */
+	pushq	%rdx			/* pt_regs->dx */
+	pushq	%rcx			/* pt_regs->cx */
+	pushq	$-ENOSYS		/* pt_regs->ax */
+	cld
+	sub	$(10*8), %rsp /* pt_regs->r8-11, bp, bx, r12-15 not saved */
+
+	/*
+	 * no need to do an access_ok check here because rbp has been
+	 * 32-bit zero extended
+	 */
+	ASM_STAC
+1:	movl	(%rbp), %ebp
+	_ASM_EXTABLE(1b, ia32_badarg)
+	ASM_CLAC
+
+	/*
+	 * Sysenter doesn't filter flags, so we need to clear NT
+	 * ourselves.  To save a few cycles, we can check whether
+	 * NT was set instead of doing an unconditional popfq.
+	 */
+	testl	$X86_EFLAGS_NT, EFLAGS(%rsp)
+	jnz	sysenter_fix_flags
+sysenter_flags_fixed:
+
+	orl	$TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
+	testl	$_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+	jnz	sysenter_tracesys
+
+sysenter_do_call:
+	/* 32-bit syscall -> 64-bit C ABI argument conversion */
+	movl	%edi, %r8d		/* arg5 */
+	movl	%ebp, %r9d		/* arg6 */
+	xchg	%ecx, %esi		/* rsi:arg2, rcx:arg4 */
+	movl	%ebx, %edi		/* arg1 */
+	movl	%edx, %edx		/* arg3 (zero extension) */
+sysenter_dispatch:
+	cmpq	$(IA32_NR_syscalls-1), %rax
+	ja	1f
+	call	*ia32_sys_call_table(, %rax, 8)
+	movq	%rax, RAX(%rsp)
+1:
+	DISABLE_INTERRUPTS(CLBR_NONE)
+	TRACE_IRQS_OFF
+	testl	$_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+	jnz	sysexit_audit
+sysexit_from_sys_call:
+	/*
+	 * NB: SYSEXIT is not obviously safe for 64-bit kernels -- an
+	 * NMI between STI and SYSEXIT has poorly specified behavior,
+	 * and and NMI followed by an IRQ with usergs is fatal.  So
+	 * we just pretend we're using SYSEXIT but we really use
+	 * SYSRETL instead.
+	 *
+	 * This code path is still called 'sysexit' because it pairs
+	 * with 'sysenter' and it uses the SYSENTER calling convention.
+	 */
+	andl	$~TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
+	movl	RIP(%rsp), %ecx		/* User %eip */
+	RESTORE_RSI_RDI
+	xorl	%edx, %edx		/* Do not leak kernel information */
+	xorq	%r8, %r8
+	xorq	%r9, %r9
+	xorq	%r10, %r10
+	movl	EFLAGS(%rsp), %r11d	/* User eflags */
+	TRACE_IRQS_ON
+
+	/*
+	 * SYSRETL works even on Intel CPUs.  Use it in preference to SYSEXIT,
+	 * since it avoids a dicey window with interrupts enabled.
+	 */
+	movl	RSP(%rsp), %esp
+
+	/*
+	 * USERGS_SYSRET32 does:
+	 *  gsbase = user's gs base
+	 *  eip = ecx
+	 *  rflags = r11
+	 *  cs = __USER32_CS
+	 *  ss = __USER_DS
+	 *
+	 * The prologue set RIP(%rsp) to VDSO32_SYSENTER_RETURN, which does:
+	 *
+	 *  pop %ebp
+	 *  pop %edx
+	 *  pop %ecx
+	 *
+	 * Therefore, we invoke SYSRETL with EDX and R8-R10 zeroed to
+	 * avoid info leaks.  R11 ends up with VDSO32_SYSENTER_RETURN's
+	 * address (already known to user code), and R12-R15 are
+	 * callee-saved and therefore don't contain any interesting
+	 * kernel data.
+	 */
+	USERGS_SYSRET32
+
+#ifdef CONFIG_AUDITSYSCALL
+	.macro auditsys_entry_common
+	/*
+	 * At this point, registers hold syscall args in the 32-bit syscall ABI:
+	 * EAX is syscall number, the 6 args are in EBX,ECX,EDX,ESI,EDI,EBP.
+	 *
+	 * We want to pass them to __audit_syscall_entry(), which is a 64-bit
+	 * C function with 5 parameters, so shuffle them to match what
+	 * the function expects: RDI,RSI,RDX,RCX,R8.
+	 */
+	movl	%esi, %r8d		/* arg5 (R8 ) <= 4th syscall arg (ESI) */
+	xchg	%ecx, %edx		/* arg4 (RCX) <= 3rd syscall arg (EDX) */
+					/* arg3 (RDX) <= 2nd syscall arg (ECX) */
+	movl	%ebx, %esi		/* arg2 (RSI) <= 1st syscall arg (EBX) */
+	movl	%eax, %edi		/* arg1 (RDI) <= syscall number  (EAX) */
+	call	__audit_syscall_entry
+
+	/*
+	 * We are going to jump back to the syscall dispatch code.
+	 * Prepare syscall args as required by the 64-bit C ABI.
+	 * Registers clobbered by __audit_syscall_entry() are
+	 * loaded from pt_regs on stack:
+	 */
+	movl	ORIG_RAX(%rsp), %eax	/* syscall number */
+	movl	%ebx, %edi		/* arg1 */
+	movl	RCX(%rsp), %esi		/* arg2 */
+	movl	RDX(%rsp), %edx		/* arg3 */
+	movl	RSI(%rsp), %ecx		/* arg4 */
+	movl	RDI(%rsp), %r8d		/* arg5 */
+	movl	%ebp, %r9d		/* arg6 */
+	.endm
+
+	.macro auditsys_exit exit
+	testl	$(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+	jnz	ia32_ret_from_sys_call
+	TRACE_IRQS_ON
+	ENABLE_INTERRUPTS(CLBR_NONE)
+	movl	%eax, %esi		/* second arg, syscall return value */
+	cmpl	$-MAX_ERRNO, %eax	/* is it an error ? */
+	jbe	1f
+	movslq	%eax, %rsi		/* if error sign extend to 64 bits */
+1:	setbe	%al			/* 1 if error, 0 if not */
+	movzbl	%al, %edi		/* zero-extend that into %edi */
+	call	__audit_syscall_exit
+	movq	RAX(%rsp), %rax		/* reload syscall return value */
+	movl	$(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %edi
+	DISABLE_INTERRUPTS(CLBR_NONE)
+	TRACE_IRQS_OFF
+	testl	%edi, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+	jz	\exit
+	xorl	%eax, %eax		/* Do not leak kernel information */
+	movq	%rax, R11(%rsp)
+	movq	%rax, R10(%rsp)
+	movq	%rax, R9(%rsp)
+	movq	%rax, R8(%rsp)
+	jmp	int_with_check
+	.endm
+
+sysenter_auditsys:
+	auditsys_entry_common
+	jmp	sysenter_dispatch
+
+sysexit_audit:
+	auditsys_exit sysexit_from_sys_call
+#endif
+
+sysenter_fix_flags:
+	pushq	$(X86_EFLAGS_IF|X86_EFLAGS_FIXED)
+	popfq
+	jmp	sysenter_flags_fixed
+
+sysenter_tracesys:
+#ifdef CONFIG_AUDITSYSCALL
+	testl	$(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+	jz	sysenter_auditsys
+#endif
+	SAVE_EXTRA_REGS
+	xorl	%eax, %eax		/* Do not leak kernel information */
+	movq	%rax, R11(%rsp)
+	movq	%rax, R10(%rsp)
+	movq	%rax, R9(%rsp)
+	movq	%rax, R8(%rsp)
+	movq	%rsp, %rdi		/* &pt_regs -> arg1 */
+	call	syscall_trace_enter
+
+	/* Reload arg registers from stack. (see sysenter_tracesys) */
+	movl	RCX(%rsp), %ecx
+	movl	RDX(%rsp), %edx
+	movl	RSI(%rsp), %esi
+	movl	RDI(%rsp), %edi
+	movl	%eax, %eax		/* zero extension */
+
+	RESTORE_EXTRA_REGS
+	jmp	sysenter_do_call
+ENDPROC(entry_SYSENTER_compat)
+
+/*
+ * 32-bit SYSCALL instruction entry.
+ *
+ * 32-bit SYSCALL saves rip to rcx, clears rflags.RF, then saves rflags to r11,
+ * then loads new ss, cs, and rip from previously programmed MSRs.
+ * rflags gets masked by a value from another MSR (so CLD and CLAC
+ * are not needed). SYSCALL does not save anything on the stack
+ * and does not change rsp.
+ *
+ * Note: rflags saving+masking-with-MSR happens only in Long mode
+ * (in legacy 32-bit mode, IF, RF and VM bits are cleared and that's it).
+ * Don't get confused: rflags saving+masking depends on Long Mode Active bit
+ * (EFER.LMA=1), NOT on bitness of userspace where SYSCALL executes
+ * or target CS descriptor's L bit (SYSCALL does not read segment descriptors).
+ *
+ * Arguments:
+ * eax  system call number
+ * ecx  return address
+ * ebx  arg1
+ * ebp  arg2	(note: not saved in the stack frame, should not be touched)
+ * edx  arg3
+ * esi  arg4
+ * edi  arg5
+ * esp  user stack
+ * 0(%esp) arg6
+ *
+ * This is purely a fast path. For anything complicated we use the int 0x80
+ * path below. We set up a complete hardware stack frame to share code
+ * with the int 0x80 path.
+ */
+ENTRY(entry_SYSCALL_compat)
+	/*
+	 * Interrupts are off on entry.
+	 * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
+	 * it is too small to ever cause noticeable irq latency.
+	 */
+	SWAPGS_UNSAFE_STACK
+	movl	%esp, %r8d
+	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
+	ENABLE_INTERRUPTS(CLBR_NONE)
+
+	/* Zero-extending 32-bit regs, do not remove */
+	movl	%eax, %eax
+
+	/* Construct struct pt_regs on stack */
+	pushq	$__USER32_DS		/* pt_regs->ss */
+	pushq	%r8			/* pt_regs->sp */
+	pushq	%r11			/* pt_regs->flags */
+	pushq	$__USER32_CS		/* pt_regs->cs */
+	pushq	%rcx			/* pt_regs->ip */
+	pushq	%rax			/* pt_regs->orig_ax */
+	pushq	%rdi			/* pt_regs->di */
+	pushq	%rsi			/* pt_regs->si */
+	pushq	%rdx			/* pt_regs->dx */
+	pushq	%rbp			/* pt_regs->cx */
+	movl	%ebp, %ecx
+	pushq	$-ENOSYS		/* pt_regs->ax */
+	sub	$(10*8), %rsp		/* pt_regs->r8-11, bp, bx, r12-15 not saved */
+
+	/*
+	 * No need to do an access_ok check here because r8 has been
+	 * 32-bit zero extended:
+	 */
+	ASM_STAC
+1:	movl	(%r8), %ebp
+	_ASM_EXTABLE(1b, ia32_badarg)
+	ASM_CLAC
+	orl	$TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
+	testl	$_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+	jnz	cstar_tracesys
+
+cstar_do_call:
+	/* 32-bit syscall -> 64-bit C ABI argument conversion */
+	movl	%edi, %r8d		/* arg5 */
+	movl	%ebp, %r9d		/* arg6 */
+	xchg	%ecx, %esi		/* rsi:arg2, rcx:arg4 */
+	movl	%ebx, %edi		/* arg1 */
+	movl	%edx, %edx		/* arg3 (zero extension) */
+
+cstar_dispatch:
+	cmpq	$(IA32_NR_syscalls-1), %rax
+	ja	1f
+
+	call	*ia32_sys_call_table(, %rax, 8)
+	movq	%rax, RAX(%rsp)
+1:
+	movl	RCX(%rsp), %ebp
+	DISABLE_INTERRUPTS(CLBR_NONE)
+	TRACE_IRQS_OFF
+	testl	$_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+	jnz	sysretl_audit
+
+sysretl_from_sys_call:
+	andl	$~TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
+	RESTORE_RSI_RDI_RDX
+	movl	RIP(%rsp), %ecx
+	movl	EFLAGS(%rsp), %r11d
+	xorq	%r10, %r10
+	xorq	%r9, %r9
+	xorq	%r8, %r8
+	TRACE_IRQS_ON
+	movl	RSP(%rsp), %esp
+	/*
+	 * 64-bit->32-bit SYSRET restores eip from ecx,
+	 * eflags from r11 (but RF and VM bits are forced to 0),
+	 * cs and ss are loaded from MSRs.
+	 * (Note: 32-bit->32-bit SYSRET is different: since r11
+	 * does not exist, it merely sets eflags.IF=1).
+	 *
+	 * NB: On AMD CPUs with the X86_BUG_SYSRET_SS_ATTRS bug, the ss
+	 * descriptor is not reinitialized.  This means that we must
+	 * avoid SYSRET with SS == NULL, which could happen if we schedule,
+	 * exit the kernel, and re-enter using an interrupt vector.  (All
+	 * interrupt entries on x86_64 set SS to NULL.)  We prevent that
+	 * from happening by reloading SS in __switch_to.
+	 */
+	USERGS_SYSRET32
+
+#ifdef CONFIG_AUDITSYSCALL
+cstar_auditsys:
+	auditsys_entry_common
+	jmp	cstar_dispatch
+
+sysretl_audit:
+	auditsys_exit sysretl_from_sys_call
+#endif
+
+cstar_tracesys:
+#ifdef CONFIG_AUDITSYSCALL
+	testl	$(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+	jz	cstar_auditsys
+#endif
+	SAVE_EXTRA_REGS
+	xorl	%eax, %eax		/* Do not leak kernel information */
+	movq	%rax, R11(%rsp)
+	movq	%rax, R10(%rsp)
+	movq	%rax, R9(%rsp)
+	movq	%rax, R8(%rsp)
+	movq	%rsp, %rdi		/* &pt_regs -> arg1 */
+	call	syscall_trace_enter
+
+	/* Reload arg registers from stack. (see sysenter_tracesys) */
+	movl	RCX(%rsp), %ecx
+	movl	RDX(%rsp), %edx
+	movl	RSI(%rsp), %esi
+	movl	RDI(%rsp), %edi
+	movl	%eax, %eax		/* zero extension */
+
+	RESTORE_EXTRA_REGS
+	jmp	cstar_do_call
+END(entry_SYSCALL_compat)
+
+ia32_badarg:
+	ASM_CLAC
+	movq	$-EFAULT, RAX(%rsp)
+ia32_ret_from_sys_call:
+	xorl	%eax, %eax		/* Do not leak kernel information */
+	movq	%rax, R11(%rsp)
+	movq	%rax, R10(%rsp)
+	movq	%rax, R9(%rsp)
+	movq	%rax, R8(%rsp)
+	jmp	int_ret_from_sys_call
+
+/*
+ * Emulated IA32 system calls via int 0x80.
+ *
+ * Arguments:
+ * eax  system call number
+ * ebx  arg1
+ * ecx  arg2
+ * edx  arg3
+ * esi  arg4
+ * edi  arg5
+ * ebp  arg6	(note: not saved in the stack frame, should not be touched)
+ *
+ * Notes:
+ * Uses the same stack frame as the x86-64 version.
+ * All registers except eax must be saved (but ptrace may violate that).
+ * Arguments are zero extended. For system calls that want sign extension and
+ * take long arguments a wrapper is needed. Most calls can just be called
+ * directly.
+ * Assumes it is only called from user space and entered with interrupts off.
+ */
+
+ENTRY(entry_INT80_compat)
+	/*
+	 * Interrupts are off on entry.
+	 * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
+	 * it is too small to ever cause noticeable irq latency.
+	 */
+	PARAVIRT_ADJUST_EXCEPTION_FRAME
+	SWAPGS
+	ENABLE_INTERRUPTS(CLBR_NONE)
+
+	/* Zero-extending 32-bit regs, do not remove */
+	movl	%eax, %eax
+
+	/* Construct struct pt_regs on stack (iret frame is already on stack) */
+	pushq	%rax			/* pt_regs->orig_ax */
+	pushq	%rdi			/* pt_regs->di */
+	pushq	%rsi			/* pt_regs->si */
+	pushq	%rdx			/* pt_regs->dx */
+	pushq	%rcx			/* pt_regs->cx */
+	pushq	$-ENOSYS		/* pt_regs->ax */
+	pushq	$0			/* pt_regs->r8 */
+	pushq	$0			/* pt_regs->r9 */
+	pushq	$0			/* pt_regs->r10 */
+	pushq	$0			/* pt_regs->r11 */
+	cld
+	sub	$(6*8), %rsp /* pt_regs->bp, bx, r12-15 not saved */
+
+	orl	$TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
+	testl	$_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+	jnz	ia32_tracesys
+
+ia32_do_call:
+	/* 32-bit syscall -> 64-bit C ABI argument conversion */
+	movl	%edi, %r8d		/* arg5 */
+	movl	%ebp, %r9d		/* arg6 */
+	xchg	%ecx, %esi		/* rsi:arg2, rcx:arg4 */
+	movl	%ebx, %edi		/* arg1 */
+	movl	%edx, %edx		/* arg3 (zero extension) */
+	cmpq	$(IA32_NR_syscalls-1), %rax
+	ja	1f
+
+	call	*ia32_sys_call_table(, %rax, 8)
+	movq	%rax, RAX(%rsp)
+1:
+	jmp	int_ret_from_sys_call
+
+ia32_tracesys:
+	SAVE_EXTRA_REGS
+	movq	%rsp, %rdi			/* &pt_regs -> arg1 */
+	call	syscall_trace_enter
+	/*
+	 * Reload arg registers from stack in case ptrace changed them.
+	 * Don't reload %eax because syscall_trace_enter() returned
+	 * the %rax value we should see.  But do truncate it to 32 bits.
+	 * If it's -1 to make us punt the syscall, then (u32)-1 is still
+	 * an appropriately invalid value.
+	 */
+	movl	RCX(%rsp), %ecx
+	movl	RDX(%rsp), %edx
+	movl	RSI(%rsp), %esi
+	movl	RDI(%rsp), %edi
+	movl	%eax, %eax		/* zero extension */
+	RESTORE_EXTRA_REGS
+	jmp	ia32_do_call
+END(entry_INT80_compat)
+
+	.macro PTREGSCALL label, func
+	ALIGN
+GLOBAL(\label)
+	leaq	\func(%rip), %rax
+	jmp	ia32_ptregs_common
+	.endm
+
+	PTREGSCALL stub32_rt_sigreturn,	sys32_rt_sigreturn
+	PTREGSCALL stub32_sigreturn,	sys32_sigreturn
+	PTREGSCALL stub32_fork,		sys_fork
+	PTREGSCALL stub32_vfork,	sys_vfork
+
+	ALIGN
+GLOBAL(stub32_clone)
+	leaq	sys_clone(%rip), %rax
+	/*
+	 * The 32-bit clone ABI is: clone(..., int tls_val, int *child_tidptr).
+	 * The 64-bit clone ABI is: clone(..., int *child_tidptr, int tls_val).
+	 *
+	 * The native 64-bit kernel's sys_clone() implements the latter,
+	 * so we need to swap arguments here before calling it:
+	 */
+	xchg	%r8, %rcx
+	jmp	ia32_ptregs_common
+
+	ALIGN
+ia32_ptregs_common:
+	SAVE_EXTRA_REGS 8
+	call	*%rax
+	RESTORE_EXTRA_REGS 8
+	ret
+END(ia32_ptregs_common)
diff --git a/arch/x86/kernel/syscall_32.c b/arch/x86/entry/syscall_32.c
index 3777189c4a19..8ea34f94e973 100644
--- a/arch/x86/kernel/syscall_32.c
+++ b/arch/x86/entry/syscall_32.c
@@ -10,7 +10,7 @@
 #else
 #define SYM(sym, compat) sym
 #define ia32_sys_call_table sys_call_table
-#define __NR_ia32_syscall_max __NR_syscall_max
+#define __NR_syscall_compat_max __NR_syscall_max
 #endif
 
 #define __SYSCALL_I386(nr, sym, compat) extern asmlinkage void SYM(sym, compat)(void) ;
@@ -23,11 +23,11 @@ typedef asmlinkage void (*sys_call_ptr_t)(void);
 
 extern asmlinkage void sys_ni_syscall(void);
 
-__visible const sys_call_ptr_t ia32_sys_call_table[__NR_ia32_syscall_max+1] = {
+__visible const sys_call_ptr_t ia32_sys_call_table[__NR_syscall_compat_max+1] = {
 	/*
 	 * Smells like a compiler bug -- it doesn't work
 	 * when the & below is removed.
 	 */
-	[0 ... __NR_ia32_syscall_max] = &sys_ni_syscall,
+	[0 ... __NR_syscall_compat_max] = &sys_ni_syscall,
 #include <asm/syscalls_32.h>
 };
diff --git a/arch/x86/kernel/syscall_64.c b/arch/x86/entry/syscall_64.c
index 4ac730b37f0b..4ac730b37f0b 100644
--- a/arch/x86/kernel/syscall_64.c
+++ b/arch/x86/entry/syscall_64.c
diff --git a/arch/x86/syscalls/Makefile b/arch/x86/entry/syscalls/Makefile
index a55abb9f6c5e..57aa59fd140c 100644
--- a/arch/x86/syscalls/Makefile
+++ b/arch/x86/entry/syscalls/Makefile
@@ -1,5 +1,5 @@
-out := $(obj)/../include/generated/asm
-uapi := $(obj)/../include/generated/uapi/asm
+out := $(obj)/../../include/generated/asm
+uapi := $(obj)/../../include/generated/uapi/asm
 
 # Create output directory if not already present
 _dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') \
diff --git a/arch/x86/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index ef8187f9d28d..ef8187f9d28d 100644
--- a/arch/x86/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 9ef32d5f1b19..9ef32d5f1b19 100644
--- a/arch/x86/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
diff --git a/arch/x86/syscalls/syscallhdr.sh b/arch/x86/entry/syscalls/syscallhdr.sh
index 31fd5f1f38f7..31fd5f1f38f7 100644
--- a/arch/x86/syscalls/syscallhdr.sh
+++ b/arch/x86/entry/syscalls/syscallhdr.sh
diff --git a/arch/x86/syscalls/syscalltbl.sh b/arch/x86/entry/syscalls/syscalltbl.sh
index 0e7f8ec071e7..0e7f8ec071e7 100644
--- a/arch/x86/syscalls/syscalltbl.sh
+++ b/arch/x86/entry/syscalls/syscalltbl.sh
diff --git a/arch/x86/lib/thunk_32.S b/arch/x86/entry/thunk_32.S
index 5eb715087b80..e5a17114a8c4 100644
--- a/arch/x86/lib/thunk_32.S
+++ b/arch/x86/entry/thunk_32.S
@@ -6,16 +6,14 @@
  */
 	#include <linux/linkage.h>
 	#include <asm/asm.h>
-	#include <asm/dwarf2.h>
 
 	/* put return address in eax (arg1) */
 	.macro THUNK name, func, put_ret_addr_in_eax=0
 	.globl \name
 \name:
-	CFI_STARTPROC
-	pushl_cfi_reg eax
-	pushl_cfi_reg ecx
-	pushl_cfi_reg edx
+	pushl %eax
+	pushl %ecx
+	pushl %edx
 
 	.if \put_ret_addr_in_eax
 	/* Place EIP in the arg1 */
@@ -23,11 +21,10 @@
 	.endif
 
 	call \func
-	popl_cfi_reg edx
-	popl_cfi_reg ecx
-	popl_cfi_reg eax
+	popl %edx
+	popl %ecx
+	popl %eax
 	ret
-	CFI_ENDPROC
 	_ASM_NOKPROBE(\name)
 	.endm
 
@@ -38,8 +35,6 @@
 
 #ifdef CONFIG_PREEMPT
 	THUNK ___preempt_schedule, preempt_schedule
-#ifdef CONFIG_CONTEXT_TRACKING
-	THUNK ___preempt_schedule_context, preempt_schedule_context
-#endif
+	THUNK ___preempt_schedule_notrace, preempt_schedule_notrace
 #endif
 
diff --git a/arch/x86/lib/thunk_64.S b/arch/x86/entry/thunk_64.S
index f89ba4e93025..efb2b932b748 100644
--- a/arch/x86/lib/thunk_64.S
+++ b/arch/x86/entry/thunk_64.S
@@ -6,35 +6,32 @@
  * Subject to the GNU public license, v.2. No warranty of any kind.
  */
 #include <linux/linkage.h>
-#include <asm/dwarf2.h>
-#include <asm/calling.h>
+#include "calling.h"
 #include <asm/asm.h>
 
 	/* rdi:	arg1 ... normal C conventions. rax is saved/restored. */
 	.macro THUNK name, func, put_ret_addr_in_rdi=0
 	.globl \name
 \name:
-	CFI_STARTPROC
 
 	/* this one pushes 9 elems, the next one would be %rIP */
-	pushq_cfi_reg rdi
-	pushq_cfi_reg rsi
-	pushq_cfi_reg rdx
-	pushq_cfi_reg rcx
-	pushq_cfi_reg rax
-	pushq_cfi_reg r8
-	pushq_cfi_reg r9
-	pushq_cfi_reg r10
-	pushq_cfi_reg r11
+	pushq %rdi
+	pushq %rsi
+	pushq %rdx
+	pushq %rcx
+	pushq %rax
+	pushq %r8
+	pushq %r9
+	pushq %r10
+	pushq %r11
 
 	.if \put_ret_addr_in_rdi
 	/* 9*8(%rsp) is return addr on stack */
-	movq_cfi_restore 9*8, rdi
+	movq 9*8(%rsp), %rdi
 	.endif
 
 	call \func
 	jmp  restore
-	CFI_ENDPROC
 	_ASM_NOKPROBE(\name)
 	.endm
 
@@ -49,27 +46,22 @@
 
 #ifdef CONFIG_PREEMPT
 	THUNK ___preempt_schedule, preempt_schedule
-#ifdef CONFIG_CONTEXT_TRACKING
-	THUNK ___preempt_schedule_context, preempt_schedule_context
-#endif
+	THUNK ___preempt_schedule_notrace, preempt_schedule_notrace
 #endif
 
 #if defined(CONFIG_TRACE_IRQFLAGS) \
  || defined(CONFIG_DEBUG_LOCK_ALLOC) \
  || defined(CONFIG_PREEMPT)
-	CFI_STARTPROC
-	CFI_ADJUST_CFA_OFFSET 9*8
 restore:
-	popq_cfi_reg r11
-	popq_cfi_reg r10
-	popq_cfi_reg r9
-	popq_cfi_reg r8
-	popq_cfi_reg rax
-	popq_cfi_reg rcx
-	popq_cfi_reg rdx
-	popq_cfi_reg rsi
-	popq_cfi_reg rdi
+	popq %r11
+	popq %r10
+	popq %r9
+	popq %r8
+	popq %rax
+	popq %rcx
+	popq %rdx
+	popq %rsi
+	popq %rdi
 	ret
-	CFI_ENDPROC
 	_ASM_NOKPROBE(restore)
 #endif
diff --git a/arch/x86/vdso/.gitignore b/arch/x86/entry/vdso/.gitignore
index aae8ffdd5880..aae8ffdd5880 100644
--- a/arch/x86/vdso/.gitignore
+++ b/arch/x86/entry/vdso/.gitignore
diff --git a/arch/x86/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index e97032069f88..e97032069f88 100644
--- a/arch/x86/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
diff --git a/arch/x86/vdso/checkundef.sh b/arch/x86/entry/vdso/checkundef.sh
index 7ee90a9b549d..7ee90a9b549d 100755
--- a/arch/x86/vdso/checkundef.sh
+++ b/arch/x86/entry/vdso/checkundef.sh
diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c
index 9793322751e0..9793322751e0 100644
--- a/arch/x86/vdso/vclock_gettime.c
+++ b/arch/x86/entry/vdso/vclock_gettime.c
diff --git a/arch/x86/vdso/vdso-layout.lds.S b/arch/x86/entry/vdso/vdso-layout.lds.S
index de2c921025f5..de2c921025f5 100644
--- a/arch/x86/vdso/vdso-layout.lds.S
+++ b/arch/x86/entry/vdso/vdso-layout.lds.S
diff --git a/arch/x86/vdso/vdso-note.S b/arch/x86/entry/vdso/vdso-note.S
index 79a071e4357e..79a071e4357e 100644
--- a/arch/x86/vdso/vdso-note.S
+++ b/arch/x86/entry/vdso/vdso-note.S
diff --git a/arch/x86/vdso/vdso.lds.S b/arch/x86/entry/vdso/vdso.lds.S
index 6807932643c2..6807932643c2 100644
--- a/arch/x86/vdso/vdso.lds.S
+++ b/arch/x86/entry/vdso/vdso.lds.S
diff --git a/arch/x86/vdso/vdso2c.c b/arch/x86/entry/vdso/vdso2c.c
index 8627db24a7f6..8627db24a7f6 100644
--- a/arch/x86/vdso/vdso2c.c
+++ b/arch/x86/entry/vdso/vdso2c.c
diff --git a/arch/x86/vdso/vdso2c.h b/arch/x86/entry/vdso/vdso2c.h
index 0224987556ce..0224987556ce 100644
--- a/arch/x86/vdso/vdso2c.h
+++ b/arch/x86/entry/vdso/vdso2c.h
diff --git a/arch/x86/vdso/vdso32-setup.c b/arch/x86/entry/vdso/vdso32-setup.c
index e904c270573b..e904c270573b 100644
--- a/arch/x86/vdso/vdso32-setup.c
+++ b/arch/x86/entry/vdso/vdso32-setup.c
diff --git a/arch/x86/vdso/vdso32/.gitignore b/arch/x86/entry/vdso/vdso32/.gitignore
index e45fba9d0ced..e45fba9d0ced 100644
--- a/arch/x86/vdso/vdso32/.gitignore
+++ b/arch/x86/entry/vdso/vdso32/.gitignore
diff --git a/arch/x86/vdso/vdso32/int80.S b/arch/x86/entry/vdso/vdso32/int80.S
index b15b7c01aedb..b15b7c01aedb 100644
--- a/arch/x86/vdso/vdso32/int80.S
+++ b/arch/x86/entry/vdso/vdso32/int80.S
diff --git a/arch/x86/vdso/vdso32/note.S b/arch/x86/entry/vdso/vdso32/note.S
index c83f25734696..c83f25734696 100644
--- a/arch/x86/vdso/vdso32/note.S
+++ b/arch/x86/entry/vdso/vdso32/note.S
diff --git a/arch/x86/vdso/vdso32/sigreturn.S b/arch/x86/entry/vdso/vdso32/sigreturn.S
index d7ec4e251c0a..d7ec4e251c0a 100644
--- a/arch/x86/vdso/vdso32/sigreturn.S
+++ b/arch/x86/entry/vdso/vdso32/sigreturn.S
diff --git a/arch/x86/vdso/vdso32/syscall.S b/arch/x86/entry/vdso/vdso32/syscall.S
index 6b286bb5251c..6b286bb5251c 100644
--- a/arch/x86/vdso/vdso32/syscall.S
+++ b/arch/x86/entry/vdso/vdso32/syscall.S
diff --git a/arch/x86/vdso/vdso32/sysenter.S b/arch/x86/entry/vdso/vdso32/sysenter.S
index e354bceee0e0..e354bceee0e0 100644
--- a/arch/x86/vdso/vdso32/sysenter.S
+++ b/arch/x86/entry/vdso/vdso32/sysenter.S
diff --git a/arch/x86/vdso/vdso32/vclock_gettime.c b/arch/x86/entry/vdso/vdso32/vclock_gettime.c
index 175cc72c0f68..175cc72c0f68 100644
--- a/arch/x86/vdso/vdso32/vclock_gettime.c
+++ b/arch/x86/entry/vdso/vdso32/vclock_gettime.c
diff --git a/arch/x86/vdso/vdso32/vdso-fakesections.c b/arch/x86/entry/vdso/vdso32/vdso-fakesections.c
index 541468e25265..541468e25265 100644
--- a/arch/x86/vdso/vdso32/vdso-fakesections.c
+++ b/arch/x86/entry/vdso/vdso32/vdso-fakesections.c
diff --git a/arch/x86/vdso/vdso32/vdso32.lds.S b/arch/x86/entry/vdso/vdso32/vdso32.lds.S
index 31056cf294bf..31056cf294bf 100644
--- a/arch/x86/vdso/vdso32/vdso32.lds.S
+++ b/arch/x86/entry/vdso/vdso32/vdso32.lds.S
diff --git a/arch/x86/vdso/vdsox32.lds.S b/arch/x86/entry/vdso/vdsox32.lds.S
index 697c11ece90c..697c11ece90c 100644
--- a/arch/x86/vdso/vdsox32.lds.S
+++ b/arch/x86/entry/vdso/vdsox32.lds.S
diff --git a/arch/x86/vdso/vgetcpu.c b/arch/x86/entry/vdso/vgetcpu.c
index 8ec3d1f4ce9a..8ec3d1f4ce9a 100644
--- a/arch/x86/vdso/vgetcpu.c
+++ b/arch/x86/entry/vdso/vgetcpu.c
diff --git a/arch/x86/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index 1c9f750c3859..1c9f750c3859 100644
--- a/arch/x86/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
diff --git a/arch/x86/entry/vsyscall/Makefile b/arch/x86/entry/vsyscall/Makefile
new file mode 100644
index 000000000000..a9f4856f622a
--- /dev/null
+++ b/arch/x86/entry/vsyscall/Makefile
@@ -0,0 +1,7 @@
+#
+# Makefile for the x86 low level vsyscall code
+#
+obj-y					:= vsyscall_gtod.o
+
+obj-$(CONFIG_X86_VSYSCALL_EMULATION)	+= vsyscall_64.o vsyscall_emu_64.o
+
diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c
index 2dcc6ff6fdcc..2dcc6ff6fdcc 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/entry/vsyscall/vsyscall_64.c
diff --git a/arch/x86/kernel/vsyscall_emu_64.S b/arch/x86/entry/vsyscall/vsyscall_emu_64.S
index c9596a9af159..c9596a9af159 100644
--- a/arch/x86/kernel/vsyscall_emu_64.S
+++ b/arch/x86/entry/vsyscall/vsyscall_emu_64.S
diff --git a/arch/x86/kernel/vsyscall_gtod.c b/arch/x86/entry/vsyscall/vsyscall_gtod.c
index 51e330416995..51e330416995 100644
--- a/arch/x86/kernel/vsyscall_gtod.c
+++ b/arch/x86/entry/vsyscall/vsyscall_gtod.c
diff --git a/arch/x86/kernel/vsyscall_trace.h b/arch/x86/entry/vsyscall/vsyscall_trace.h
index a8b2edec54fe..9dd7359a38a8 100644
--- a/arch/x86/kernel/vsyscall_trace.h
+++ b/arch/x86/entry/vsyscall/vsyscall_trace.h
@@ -24,6 +24,6 @@ TRACE_EVENT(emulate_vsyscall,
 #endif
 
 #undef TRACE_INCLUDE_PATH
-#define TRACE_INCLUDE_PATH ../../arch/x86/kernel
+#define TRACE_INCLUDE_PATH ../../arch/x86/entry/vsyscall/
 #define TRACE_INCLUDE_FILE vsyscall_trace
 #include <trace/define_trace.h>
diff --git a/arch/x86/ia32/Makefile b/arch/x86/ia32/Makefile
index bb635c641869..cd4339bae066 100644
--- a/arch/x86/ia32/Makefile
+++ b/arch/x86/ia32/Makefile
@@ -2,7 +2,7 @@
 # Makefile for the ia32 kernel emulation subsystem.
 #
 
-obj-$(CONFIG_IA32_EMULATION) := ia32entry.o sys_ia32.o ia32_signal.o
+obj-$(CONFIG_IA32_EMULATION) := sys_ia32.o ia32_signal.o
 
 obj-$(CONFIG_IA32_AOUT) += ia32_aout.o
 
diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c
index c81d35e6c7f1..ae3a29ae875b 100644
--- a/arch/x86/ia32/ia32_signal.c
+++ b/arch/x86/ia32/ia32_signal.c
@@ -21,8 +21,8 @@
 #include <linux/binfmts.h>
 #include <asm/ucontext.h>
 #include <asm/uaccess.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
+#include <asm/fpu/signal.h>
 #include <asm/ptrace.h>
 #include <asm/ia32_unistd.h>
 #include <asm/user32.h>
@@ -198,7 +198,7 @@ static int ia32_restore_sigcontext(struct pt_regs *regs,
 		buf = compat_ptr(tmp);
 	} get_user_catch(err);
 
-	err |= restore_xstate_sig(buf, 1);
+	err |= fpu__restore_sig(buf, 1);
 
 	force_iret();
 
@@ -308,6 +308,7 @@ static void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs,
 				 size_t frame_size,
 				 void __user **fpstate)
 {
+	struct fpu *fpu = &current->thread.fpu;
 	unsigned long sp;
 
 	/* Default to using normal stack */
@@ -322,12 +323,12 @@ static void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs,
 		 ksig->ka.sa.sa_restorer)
 		sp = (unsigned long) ksig->ka.sa.sa_restorer;
 
-	if (used_math()) {
+	if (fpu->fpstate_active) {
 		unsigned long fx_aligned, math_size;
 
-		sp = alloc_mathframe(sp, 1, &fx_aligned, &math_size);
+		sp = fpu__alloc_mathframe(sp, 1, &fx_aligned, &math_size);
 		*fpstate = (struct _fpstate_ia32 __user *) sp;
-		if (save_xstate_sig(*fpstate, (void __user *)fx_aligned,
+		if (copy_fpstate_to_sigframe(*fpstate, (void __user *)fx_aligned,
 				    math_size) < 0)
 			return (void __user *) -1L;
 	}
diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
deleted file mode 100644
index 72bf2680f819..000000000000
--- a/arch/x86/ia32/ia32entry.S
+++ /dev/null
@@ -1,611 +0,0 @@
-/*
- * Compatibility mode system call entry point for x86-64. 
- * 		
- * Copyright 2000-2002 Andi Kleen, SuSE Labs.
- */		 
-
-#include <asm/dwarf2.h>
-#include <asm/calling.h>
-#include <asm/asm-offsets.h>
-#include <asm/current.h>
-#include <asm/errno.h>
-#include <asm/ia32_unistd.h>	
-#include <asm/thread_info.h>	
-#include <asm/segment.h>
-#include <asm/irqflags.h>
-#include <asm/asm.h>
-#include <asm/smap.h>
-#include <linux/linkage.h>
-#include <linux/err.h>
-
-/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this.  */
-#include <linux/elf-em.h>
-#define AUDIT_ARCH_I386		(EM_386|__AUDIT_ARCH_LE)
-#define __AUDIT_ARCH_LE	   0x40000000
-
-#ifndef CONFIG_AUDITSYSCALL
-#define sysexit_audit ia32_ret_from_sys_call
-#define sysretl_audit ia32_ret_from_sys_call
-#endif
-
-	.section .entry.text, "ax"
-
-	/* clobbers %rax */
-	.macro  CLEAR_RREGS _r9=rax
-	xorl 	%eax,%eax
-	movq	%rax,R11(%rsp)
-	movq	%rax,R10(%rsp)
-	movq	%\_r9,R9(%rsp)
-	movq	%rax,R8(%rsp)
-	.endm
-
-	/*
-	 * Reload arg registers from stack in case ptrace changed them.
-	 * We don't reload %eax because syscall_trace_enter() returned
-	 * the %rax value we should see.  Instead, we just truncate that
-	 * value to 32 bits again as we did on entry from user mode.
-	 * If it's a new value set by user_regset during entry tracing,
-	 * this matches the normal truncation of the user-mode value.
-	 * If it's -1 to make us punt the syscall, then (u32)-1 is still
-	 * an appropriately invalid value.
-	 */
-	.macro LOAD_ARGS32 _r9=0
-	.if \_r9
-	movl R9(%rsp),%r9d
-	.endif
-	movl RCX(%rsp),%ecx
-	movl RDX(%rsp),%edx
-	movl RSI(%rsp),%esi
-	movl RDI(%rsp),%edi
-	movl %eax,%eax			/* zero extension */
-	.endm
-	
-	.macro CFI_STARTPROC32 simple
-	CFI_STARTPROC	\simple
-	CFI_UNDEFINED	r8
-	CFI_UNDEFINED	r9
-	CFI_UNDEFINED	r10
-	CFI_UNDEFINED	r11
-	CFI_UNDEFINED	r12
-	CFI_UNDEFINED	r13
-	CFI_UNDEFINED	r14
-	CFI_UNDEFINED	r15
-	.endm
-
-#ifdef CONFIG_PARAVIRT
-ENTRY(native_usergs_sysret32)
-	swapgs
-	sysretl
-ENDPROC(native_usergs_sysret32)
-
-ENTRY(native_irq_enable_sysexit)
-	swapgs
-	sti
-	sysexit
-ENDPROC(native_irq_enable_sysexit)
-#endif
-
-/*
- * 32bit SYSENTER instruction entry.
- *
- * SYSENTER loads ss, rsp, cs, and rip from previously programmed MSRs.
- * IF and VM in rflags are cleared (IOW: interrupts are off).
- * SYSENTER does not save anything on the stack,
- * and does not save old rip (!!!) and rflags.
- *
- * Arguments:
- * eax  system call number
- * ebx  arg1
- * ecx  arg2
- * edx  arg3
- * esi  arg4
- * edi  arg5
- * ebp  user stack
- * 0(%ebp) arg6
- *
- * This is purely a fast path. For anything complicated we use the int 0x80
- * path below. We set up a complete hardware stack frame to share code
- * with the int 0x80 path.
- */
-ENTRY(ia32_sysenter_target)
-	CFI_STARTPROC32	simple
-	CFI_SIGNAL_FRAME
-	CFI_DEF_CFA	rsp,0
-	CFI_REGISTER	rsp,rbp
-
-	/*
-	 * Interrupts are off on entry.
-	 * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
-	 * it is too small to ever cause noticeable irq latency.
-	 */
-	SWAPGS_UNSAFE_STACK
-	movq	PER_CPU_VAR(cpu_tss + TSS_sp0), %rsp
-	ENABLE_INTERRUPTS(CLBR_NONE)
-
-	/* Zero-extending 32-bit regs, do not remove */
-	movl	%ebp, %ebp
-	movl	%eax, %eax
-
-	movl	ASM_THREAD_INFO(TI_sysenter_return, %rsp, 0), %r10d
-	CFI_REGISTER rip,r10
-
-	/* Construct struct pt_regs on stack */
-	pushq_cfi	$__USER32_DS		/* pt_regs->ss */
-	pushq_cfi	%rbp			/* pt_regs->sp */
-	CFI_REL_OFFSET	rsp,0
-	pushfq_cfi				/* pt_regs->flags */
-	pushq_cfi	$__USER32_CS		/* pt_regs->cs */
-	pushq_cfi	%r10 /* pt_regs->ip = thread_info->sysenter_return */
-	CFI_REL_OFFSET	rip,0
-	pushq_cfi_reg	rax			/* pt_regs->orig_ax */
-	pushq_cfi_reg	rdi			/* pt_regs->di */
-	pushq_cfi_reg	rsi			/* pt_regs->si */
-	pushq_cfi_reg	rdx			/* pt_regs->dx */
-	pushq_cfi_reg	rcx			/* pt_regs->cx */
-	pushq_cfi_reg	rax			/* pt_regs->ax */
-	cld
-	sub	$(10*8),%rsp /* pt_regs->r8-11,bp,bx,r12-15 not saved */
-	CFI_ADJUST_CFA_OFFSET 10*8
-
-	/*
-	 * no need to do an access_ok check here because rbp has been
-	 * 32bit zero extended
-	 */
-	ASM_STAC
-1:	movl	(%rbp),%ebp
-	_ASM_EXTABLE(1b,ia32_badarg)
-	ASM_CLAC
-
-	/*
-	 * Sysenter doesn't filter flags, so we need to clear NT
-	 * ourselves.  To save a few cycles, we can check whether
-	 * NT was set instead of doing an unconditional popfq.
-	 */
-	testl $X86_EFLAGS_NT,EFLAGS(%rsp)
-	jnz sysenter_fix_flags
-sysenter_flags_fixed:
-
-	orl     $TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
-	testl   $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
-	CFI_REMEMBER_STATE
-	jnz  sysenter_tracesys
-	cmpq	$(IA32_NR_syscalls-1),%rax
-	ja	ia32_badsys
-sysenter_do_call:
-	/* 32bit syscall -> 64bit C ABI argument conversion */
-	movl	%edi,%r8d	/* arg5 */
-	movl	%ebp,%r9d	/* arg6 */
-	xchg	%ecx,%esi	/* rsi:arg2, rcx:arg4 */
-	movl	%ebx,%edi	/* arg1 */
-	movl	%edx,%edx	/* arg3 (zero extension) */
-sysenter_dispatch:
-	call	*ia32_sys_call_table(,%rax,8)
-	movq	%rax,RAX(%rsp)
-	DISABLE_INTERRUPTS(CLBR_NONE)
-	TRACE_IRQS_OFF
-	testl	$_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
-	jnz	sysexit_audit
-sysexit_from_sys_call:
-	/*
-	 * NB: SYSEXIT is not obviously safe for 64-bit kernels -- an
-	 * NMI between STI and SYSEXIT has poorly specified behavior,
-	 * and and NMI followed by an IRQ with usergs is fatal.  So
-	 * we just pretend we're using SYSEXIT but we really use
-	 * SYSRETL instead.
-	 *
-	 * This code path is still called 'sysexit' because it pairs
-	 * with 'sysenter' and it uses the SYSENTER calling convention.
-	 */
-	andl    $~TS_COMPAT,ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
-	movl	RIP(%rsp),%ecx		/* User %eip */
-	CFI_REGISTER rip,rcx
-	RESTORE_RSI_RDI
-	xorl	%edx,%edx		/* avoid info leaks */
-	xorq	%r8,%r8
-	xorq	%r9,%r9
-	xorq	%r10,%r10
-	movl	EFLAGS(%rsp),%r11d	/* User eflags */
-	/*CFI_RESTORE rflags*/
-	TRACE_IRQS_ON
-
-	/*
-	 * SYSRETL works even on Intel CPUs.  Use it in preference to SYSEXIT,
-	 * since it avoids a dicey window with interrupts enabled.
-	 */
-	movl	RSP(%rsp),%esp
-
-	/*
-	 * USERGS_SYSRET32 does:
-	 *  gsbase = user's gs base
-	 *  eip = ecx
-	 *  rflags = r11
-	 *  cs = __USER32_CS
-	 *  ss = __USER_DS
-	 *
-	 * The prologue set RIP(%rsp) to VDSO32_SYSENTER_RETURN, which does:
-	 *
-	 *  pop %ebp
-	 *  pop %edx
-	 *  pop %ecx
-	 *
-	 * Therefore, we invoke SYSRETL with EDX and R8-R10 zeroed to
-	 * avoid info leaks.  R11 ends up with VDSO32_SYSENTER_RETURN's
-	 * address (already known to user code), and R12-R15 are
-	 * callee-saved and therefore don't contain any interesting
-	 * kernel data.
-	 */
-	USERGS_SYSRET32
-
-	CFI_RESTORE_STATE
-
-#ifdef CONFIG_AUDITSYSCALL
-	.macro auditsys_entry_common
-	movl %esi,%r8d			/* 5th arg: 4th syscall arg */
-	movl %ecx,%r9d			/*swap with edx*/
-	movl %edx,%ecx			/* 4th arg: 3rd syscall arg */
-	movl %r9d,%edx			/* 3rd arg: 2nd syscall arg */
-	movl %ebx,%esi			/* 2nd arg: 1st syscall arg */
-	movl %eax,%edi			/* 1st arg: syscall number */
-	call __audit_syscall_entry
-	movl RAX(%rsp),%eax	/* reload syscall number */
-	cmpq $(IA32_NR_syscalls-1),%rax
-	ja ia32_badsys
-	movl %ebx,%edi			/* reload 1st syscall arg */
-	movl RCX(%rsp),%esi	/* reload 2nd syscall arg */
-	movl RDX(%rsp),%edx	/* reload 3rd syscall arg */
-	movl RSI(%rsp),%ecx	/* reload 4th syscall arg */
-	movl RDI(%rsp),%r8d	/* reload 5th syscall arg */
-	.endm
-
-	.macro auditsys_exit exit
-	testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
-	jnz ia32_ret_from_sys_call
-	TRACE_IRQS_ON
-	ENABLE_INTERRUPTS(CLBR_NONE)
-	movl %eax,%esi		/* second arg, syscall return value */
-	cmpl $-MAX_ERRNO,%eax	/* is it an error ? */
-	jbe 1f
-	movslq %eax, %rsi	/* if error sign extend to 64 bits */
-1:	setbe %al		/* 1 if error, 0 if not */
-	movzbl %al,%edi		/* zero-extend that into %edi */
-	call __audit_syscall_exit
-	movq RAX(%rsp),%rax	/* reload syscall return value */
-	movl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),%edi
-	DISABLE_INTERRUPTS(CLBR_NONE)
-	TRACE_IRQS_OFF
-	testl %edi, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
-	jz \exit
-	CLEAR_RREGS
-	jmp int_with_check
-	.endm
-
-sysenter_auditsys:
-	auditsys_entry_common
-	movl %ebp,%r9d			/* reload 6th syscall arg */
-	jmp sysenter_dispatch
-
-sysexit_audit:
-	auditsys_exit sysexit_from_sys_call
-#endif
-
-sysenter_fix_flags:
-	pushq_cfi $(X86_EFLAGS_IF|X86_EFLAGS_FIXED)
-	popfq_cfi
-	jmp sysenter_flags_fixed
-
-sysenter_tracesys:
-#ifdef CONFIG_AUDITSYSCALL
-	testl	$(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
-	jz	sysenter_auditsys
-#endif
-	SAVE_EXTRA_REGS
-	CLEAR_RREGS
-	movq	$-ENOSYS,RAX(%rsp)/* ptrace can change this for a bad syscall */
-	movq	%rsp,%rdi        /* &pt_regs -> arg1 */
-	call	syscall_trace_enter
-	LOAD_ARGS32  /* reload args from stack in case ptrace changed it */
-	RESTORE_EXTRA_REGS
-	cmpq	$(IA32_NR_syscalls-1),%rax
-	ja	int_ret_from_sys_call /* sysenter_tracesys has set RAX(%rsp) */
-	jmp	sysenter_do_call
-	CFI_ENDPROC
-ENDPROC(ia32_sysenter_target)
-
-/*
- * 32bit SYSCALL instruction entry.
- *
- * 32bit SYSCALL saves rip to rcx, clears rflags.RF, then saves rflags to r11,
- * then loads new ss, cs, and rip from previously programmed MSRs.
- * rflags gets masked by a value from another MSR (so CLD and CLAC
- * are not needed). SYSCALL does not save anything on the stack
- * and does not change rsp.
- *
- * Note: rflags saving+masking-with-MSR happens only in Long mode
- * (in legacy 32bit mode, IF, RF and VM bits are cleared and that's it).
- * Don't get confused: rflags saving+masking depends on Long Mode Active bit
- * (EFER.LMA=1), NOT on bitness of userspace where SYSCALL executes
- * or target CS descriptor's L bit (SYSCALL does not read segment descriptors).
- *
- * Arguments:
- * eax  system call number
- * ecx  return address
- * ebx  arg1
- * ebp  arg2	(note: not saved in the stack frame, should not be touched)
- * edx  arg3
- * esi  arg4
- * edi  arg5
- * esp  user stack
- * 0(%esp) arg6
- *
- * This is purely a fast path. For anything complicated we use the int 0x80
- * path below. We set up a complete hardware stack frame to share code
- * with the int 0x80 path.
- */
-ENTRY(ia32_cstar_target)
-	CFI_STARTPROC32	simple
-	CFI_SIGNAL_FRAME
-	CFI_DEF_CFA	rsp,0
-	CFI_REGISTER	rip,rcx
-	/*CFI_REGISTER	rflags,r11*/
-
-	/*
-	 * Interrupts are off on entry.
-	 * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
-	 * it is too small to ever cause noticeable irq latency.
-	 */
-	SWAPGS_UNSAFE_STACK
-	movl	%esp,%r8d
-	CFI_REGISTER	rsp,r8
-	movq	PER_CPU_VAR(kernel_stack),%rsp
-	ENABLE_INTERRUPTS(CLBR_NONE)
-
-	/* Zero-extending 32-bit regs, do not remove */
-	movl	%eax,%eax
-
-	/* Construct struct pt_regs on stack */
-	pushq_cfi	$__USER32_DS		/* pt_regs->ss */
-	pushq_cfi	%r8			/* pt_regs->sp */
-	CFI_REL_OFFSET rsp,0
-	pushq_cfi	%r11			/* pt_regs->flags */
-	pushq_cfi	$__USER32_CS		/* pt_regs->cs */
-	pushq_cfi	%rcx			/* pt_regs->ip */
-	CFI_REL_OFFSET rip,0
-	pushq_cfi_reg	rax			/* pt_regs->orig_ax */
-	pushq_cfi_reg	rdi			/* pt_regs->di */
-	pushq_cfi_reg	rsi			/* pt_regs->si */
-	pushq_cfi_reg	rdx			/* pt_regs->dx */
-	pushq_cfi_reg	rbp			/* pt_regs->cx */
-	movl	%ebp,%ecx
-	pushq_cfi_reg	rax			/* pt_regs->ax */
-	sub	$(10*8),%rsp /* pt_regs->r8-11,bp,bx,r12-15 not saved */
-	CFI_ADJUST_CFA_OFFSET 10*8
-
-	/*
-	 * no need to do an access_ok check here because r8 has been
-	 * 32bit zero extended
-	 */
-	ASM_STAC
-1:	movl	(%r8),%r9d
-	_ASM_EXTABLE(1b,ia32_badarg)
-	ASM_CLAC
-	orl     $TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
-	testl   $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
-	CFI_REMEMBER_STATE
-	jnz   cstar_tracesys
-	cmpq $IA32_NR_syscalls-1,%rax
-	ja  ia32_badsys
-cstar_do_call:
-	/* 32bit syscall -> 64bit C ABI argument conversion */
-	movl	%edi,%r8d	/* arg5 */
-	/* r9 already loaded */	/* arg6 */
-	xchg	%ecx,%esi	/* rsi:arg2, rcx:arg4 */
-	movl	%ebx,%edi	/* arg1 */
-	movl	%edx,%edx	/* arg3 (zero extension) */
-cstar_dispatch:
-	call *ia32_sys_call_table(,%rax,8)
-	movq %rax,RAX(%rsp)
-	DISABLE_INTERRUPTS(CLBR_NONE)
-	TRACE_IRQS_OFF
-	testl $_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
-	jnz sysretl_audit
-sysretl_from_sys_call:
-	andl $~TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
-	RESTORE_RSI_RDI_RDX
-	movl RIP(%rsp),%ecx
-	CFI_REGISTER rip,rcx
-	movl EFLAGS(%rsp),%r11d
-	/*CFI_REGISTER rflags,r11*/
-	xorq	%r10,%r10
-	xorq	%r9,%r9
-	xorq	%r8,%r8
-	TRACE_IRQS_ON
-	movl RSP(%rsp),%esp
-	CFI_RESTORE rsp
-	/*
-	 * 64bit->32bit SYSRET restores eip from ecx,
-	 * eflags from r11 (but RF and VM bits are forced to 0),
-	 * cs and ss are loaded from MSRs.
-	 * (Note: 32bit->32bit SYSRET is different: since r11
-	 * does not exist, it merely sets eflags.IF=1).
-	 *
-	 * NB: On AMD CPUs with the X86_BUG_SYSRET_SS_ATTRS bug, the ss
-	 * descriptor is not reinitialized.  This means that we must
-	 * avoid SYSRET with SS == NULL, which could happen if we schedule,
-	 * exit the kernel, and re-enter using an interrupt vector.  (All
-	 * interrupt entries on x86_64 set SS to NULL.)  We prevent that
-	 * from happening by reloading SS in __switch_to.
-	 */
-	USERGS_SYSRET32
-
-#ifdef CONFIG_AUDITSYSCALL
-cstar_auditsys:
-	CFI_RESTORE_STATE
-	movl %r9d,R9(%rsp)	/* register to be clobbered by call */
-	auditsys_entry_common
-	movl R9(%rsp),%r9d	/* reload 6th syscall arg */
-	jmp cstar_dispatch
-
-sysretl_audit:
-	auditsys_exit sysretl_from_sys_call
-#endif
-
-cstar_tracesys:
-#ifdef CONFIG_AUDITSYSCALL
-	testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
-	jz cstar_auditsys
-#endif
-	xchgl %r9d,%ebp
-	SAVE_EXTRA_REGS
-	CLEAR_RREGS r9
-	movq $-ENOSYS,RAX(%rsp)	/* ptrace can change this for a bad syscall */
-	movq %rsp,%rdi        /* &pt_regs -> arg1 */
-	call syscall_trace_enter
-	LOAD_ARGS32 1	/* reload args from stack in case ptrace changed it */
-	RESTORE_EXTRA_REGS
-	xchgl %ebp,%r9d
-	cmpq $(IA32_NR_syscalls-1),%rax
-	ja int_ret_from_sys_call /* cstar_tracesys has set RAX(%rsp) */
-	jmp cstar_do_call
-END(ia32_cstar_target)
-				
-ia32_badarg:
-	ASM_CLAC
-	movq $-EFAULT,%rax
-	jmp ia32_sysret
-	CFI_ENDPROC
-
-/*
- * Emulated IA32 system calls via int 0x80.
- *
- * Arguments:
- * eax  system call number
- * ebx  arg1
- * ecx  arg2
- * edx  arg3
- * esi  arg4
- * edi  arg5
- * ebp  arg6	(note: not saved in the stack frame, should not be touched)
- *
- * Notes:
- * Uses the same stack frame as the x86-64 version.
- * All registers except eax must be saved (but ptrace may violate that).
- * Arguments are zero extended. For system calls that want sign extension and
- * take long arguments a wrapper is needed. Most calls can just be called
- * directly.
- * Assumes it is only called from user space and entered with interrupts off.
- */
-
-ENTRY(ia32_syscall)
-	CFI_STARTPROC32	simple
-	CFI_SIGNAL_FRAME
-	CFI_DEF_CFA	rsp,5*8
-	/*CFI_REL_OFFSET	ss,4*8 */
-	CFI_REL_OFFSET	rsp,3*8
-	/*CFI_REL_OFFSET	rflags,2*8 */
-	/*CFI_REL_OFFSET	cs,1*8 */
-	CFI_REL_OFFSET	rip,0*8
-
-	/*
-	 * Interrupts are off on entry.
-	 * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
-	 * it is too small to ever cause noticeable irq latency.
-	 */
-	PARAVIRT_ADJUST_EXCEPTION_FRAME
-	SWAPGS
-	ENABLE_INTERRUPTS(CLBR_NONE)
-
-	/* Zero-extending 32-bit regs, do not remove */
-	movl	%eax,%eax
-
-	/* Construct struct pt_regs on stack (iret frame is already on stack) */
-	pushq_cfi_reg	rax			/* pt_regs->orig_ax */
-	pushq_cfi_reg	rdi			/* pt_regs->di */
-	pushq_cfi_reg	rsi			/* pt_regs->si */
-	pushq_cfi_reg	rdx			/* pt_regs->dx */
-	pushq_cfi_reg	rcx			/* pt_regs->cx */
-	pushq_cfi_reg	rax			/* pt_regs->ax */
-	cld
-	sub	$(10*8),%rsp /* pt_regs->r8-11,bp,bx,r12-15 not saved */
-	CFI_ADJUST_CFA_OFFSET 10*8
-
-	orl $TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
-	testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
-	jnz ia32_tracesys
-	cmpq $(IA32_NR_syscalls-1),%rax
-	ja ia32_badsys
-ia32_do_call:
-	/* 32bit syscall -> 64bit C ABI argument conversion */
-	movl %edi,%r8d	/* arg5 */
-	movl %ebp,%r9d	/* arg6 */
-	xchg %ecx,%esi	/* rsi:arg2, rcx:arg4 */
-	movl %ebx,%edi	/* arg1 */
-	movl %edx,%edx	/* arg3 (zero extension) */
-	call *ia32_sys_call_table(,%rax,8) # xxx: rip relative
-ia32_sysret:
-	movq %rax,RAX(%rsp)
-ia32_ret_from_sys_call:
-	CLEAR_RREGS
-	jmp int_ret_from_sys_call
-
-ia32_tracesys:
-	SAVE_EXTRA_REGS
-	CLEAR_RREGS
-	movq $-ENOSYS,RAX(%rsp)	/* ptrace can change this for a bad syscall */
-	movq %rsp,%rdi        /* &pt_regs -> arg1 */
-	call syscall_trace_enter
-	LOAD_ARGS32	/* reload args from stack in case ptrace changed it */
-	RESTORE_EXTRA_REGS
-	cmpq $(IA32_NR_syscalls-1),%rax
-	ja  int_ret_from_sys_call	/* ia32_tracesys has set RAX(%rsp) */
-	jmp ia32_do_call
-END(ia32_syscall)
-
-ia32_badsys:
-	movq $0,ORIG_RAX(%rsp)
-	movq $-ENOSYS,%rax
-	jmp ia32_sysret
-
-	CFI_ENDPROC
-	
-	.macro PTREGSCALL label, func
-	ALIGN
-GLOBAL(\label)
-	leaq \func(%rip),%rax
-	jmp  ia32_ptregs_common	
-	.endm
-
-	CFI_STARTPROC32
-
-	PTREGSCALL stub32_rt_sigreturn, sys32_rt_sigreturn
-	PTREGSCALL stub32_sigreturn, sys32_sigreturn
-	PTREGSCALL stub32_fork, sys_fork
-	PTREGSCALL stub32_vfork, sys_vfork
-
-	ALIGN
-GLOBAL(stub32_clone)
-	leaq sys_clone(%rip),%rax
-	mov	%r8, %rcx
-	jmp  ia32_ptregs_common	
-
-	ALIGN
-ia32_ptregs_common:
-	CFI_ENDPROC
-	CFI_STARTPROC32	simple
-	CFI_SIGNAL_FRAME
-	CFI_DEF_CFA	rsp,SIZEOF_PTREGS
-	CFI_REL_OFFSET	rax,RAX
-	CFI_REL_OFFSET	rcx,RCX
-	CFI_REL_OFFSET	rdx,RDX
-	CFI_REL_OFFSET	rsi,RSI
-	CFI_REL_OFFSET	rdi,RDI
-	CFI_REL_OFFSET	rip,RIP
-/*	CFI_REL_OFFSET	cs,CS*/
-/*	CFI_REL_OFFSET	rflags,EFLAGS*/
-	CFI_REL_OFFSET	rsp,RSP
-/*	CFI_REL_OFFSET	ss,SS*/
-	SAVE_EXTRA_REGS 8
-	call *%rax
-	RESTORE_EXTRA_REGS 8
-	ret
-	CFI_ENDPROC
-END(ia32_ptregs_common)
diff --git a/arch/x86/include/asm/alternative-asm.h b/arch/x86/include/asm/alternative-asm.h
index bdf02eeee765..e7636bac7372 100644
--- a/arch/x86/include/asm/alternative-asm.h
+++ b/arch/x86/include/asm/alternative-asm.h
@@ -18,6 +18,12 @@
 	.endm
 #endif
 
+/*
+ * Issue one struct alt_instr descriptor entry (need to put it into
+ * the section .altinstructions, see below). This entry contains
+ * enough information for the alternatives patching code to patch an
+ * instruction. See apply_alternatives().
+ */
 .macro altinstruction_entry orig alt feature orig_len alt_len pad_len
 	.long \orig - .
 	.long \alt - .
@@ -27,6 +33,12 @@
 	.byte \pad_len
 .endm
 
+/*
+ * Define an alternative between two instructions. If @feature is
+ * present, early code in apply_alternatives() replaces @oldinstr with
+ * @newinstr. ".skip" directive takes care of proper instruction padding
+ * in case @newinstr is longer than @oldinstr.
+ */
 .macro ALTERNATIVE oldinstr, newinstr, feature
 140:
 	\oldinstr
@@ -55,6 +67,12 @@
  */
 #define alt_max_short(a, b)	((a) ^ (((a) ^ (b)) & -(-((a) < (b)))))
 
+
+/*
+ * Same as ALTERNATIVE macro above but for two alternatives. If CPU
+ * has @feature1, it replaces @oldinstr with @newinstr1. If CPU has
+ * @feature2, it replaces @oldinstr with @feature2.
+ */
 .macro ALTERNATIVE_2 oldinstr, newinstr1, feature1, newinstr2, feature2
 140:
 	\oldinstr
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index ba32af062f61..7bfc85bbb8ff 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -52,6 +52,12 @@ struct alt_instr {
 	u8  padlen;		/* length of build-time padding */
 } __packed;
 
+/*
+ * Debug flag that can be tested to see whether alternative
+ * instructions were patched in already:
+ */
+extern int alternatives_patched;
+
 extern void alternative_instructions(void);
 extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end);
 
diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h
index aaac3b2fb746..1a5da2e63aee 100644
--- a/arch/x86/include/asm/amd_nb.h
+++ b/arch/x86/include/asm/amd_nb.h
@@ -98,11 +98,22 @@ static inline u16 amd_get_node_id(struct pci_dev *pdev)
 	return 0;
 }
 
+static inline bool amd_gart_present(void)
+{
+	/* GART present only on Fam15h, upto model 0fh */
+	if (boot_cpu_data.x86 == 0xf || boot_cpu_data.x86 == 0x10 ||
+	    (boot_cpu_data.x86 == 0x15 && boot_cpu_data.x86_model < 0x10))
+		return true;
+
+	return false;
+}
+
 #else
 
 #define amd_nb_num(x)		0
 #define amd_nb_has_feature(x)	false
 #define node_to_amd_nb(x)	NULL
+#define amd_gart_present(x)	false
 
 #endif
 
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 976b86a325e5..c8393634ca0c 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -644,6 +644,12 @@ static inline void entering_ack_irq(void)
 	entering_irq();
 }
 
+static inline void ipi_entering_ack_irq(void)
+{
+	ack_APIC_irq();
+	irq_enter();
+}
+
 static inline void exiting_irq(void)
 {
 	irq_exit();
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index 7730c1c5c83a..189679aba703 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -63,6 +63,31 @@
 	_ASM_ALIGN ;						\
 	_ASM_PTR (entry);					\
 	.popsection
+
+.macro ALIGN_DESTINATION
+	/* check for bad alignment of destination */
+	movl %edi,%ecx
+	andl $7,%ecx
+	jz 102f				/* already aligned */
+	subl $8,%ecx
+	negl %ecx
+	subl %ecx,%edx
+100:	movb (%rsi),%al
+101:	movb %al,(%rdi)
+	incq %rsi
+	incq %rdi
+	decl %ecx
+	jnz 100b
+102:
+	.section .fixup,"ax"
+103:	addl %ecx,%edx			/* ecx is zerorest also */
+	jmp copy_user_handle_tail
+	.previous
+
+	_ASM_EXTABLE(100b,103b)
+	_ASM_EXTABLE(101b,103b)
+	.endm
+
 #else
 # define _ASM_EXTABLE(from,to)					\
 	" .pushsection \"__ex_table\",\"a\"\n"			\
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index 5e5cd123fdfb..e9168955c42f 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -22,7 +22,7 @@
  *
  * Atomically reads the value of @v.
  */
-static inline int atomic_read(const atomic_t *v)
+static __always_inline int atomic_read(const atomic_t *v)
 {
 	return ACCESS_ONCE((v)->counter);
 }
@@ -34,7 +34,7 @@ static inline int atomic_read(const atomic_t *v)
  *
  * Atomically sets the value of @v to @i.
  */
-static inline void atomic_set(atomic_t *v, int i)
+static __always_inline void atomic_set(atomic_t *v, int i)
 {
 	v->counter = i;
 }
@@ -46,7 +46,7 @@ static inline void atomic_set(atomic_t *v, int i)
  *
  * Atomically adds @i to @v.
  */
-static inline void atomic_add(int i, atomic_t *v)
+static __always_inline void atomic_add(int i, atomic_t *v)
 {
 	asm volatile(LOCK_PREFIX "addl %1,%0"
 		     : "+m" (v->counter)
@@ -60,7 +60,7 @@ static inline void atomic_add(int i, atomic_t *v)
  *
  * Atomically subtracts @i from @v.
  */
-static inline void atomic_sub(int i, atomic_t *v)
+static __always_inline void atomic_sub(int i, atomic_t *v)
 {
 	asm volatile(LOCK_PREFIX "subl %1,%0"
 		     : "+m" (v->counter)
@@ -76,7 +76,7 @@ static inline void atomic_sub(int i, atomic_t *v)
  * true if the result is zero, or false for all
  * other cases.
  */
-static inline int atomic_sub_and_test(int i, atomic_t *v)
+static __always_inline int atomic_sub_and_test(int i, atomic_t *v)
 {
 	GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, "er", i, "%0", "e");
 }
@@ -87,7 +87,7 @@ static inline int atomic_sub_and_test(int i, atomic_t *v)
  *
  * Atomically increments @v by 1.
  */
-static inline void atomic_inc(atomic_t *v)
+static __always_inline void atomic_inc(atomic_t *v)
 {
 	asm volatile(LOCK_PREFIX "incl %0"
 		     : "+m" (v->counter));
@@ -99,7 +99,7 @@ static inline void atomic_inc(atomic_t *v)
  *
  * Atomically decrements @v by 1.
  */
-static inline void atomic_dec(atomic_t *v)
+static __always_inline void atomic_dec(atomic_t *v)
 {
 	asm volatile(LOCK_PREFIX "decl %0"
 		     : "+m" (v->counter));
@@ -113,7 +113,7 @@ static inline void atomic_dec(atomic_t *v)
  * returns true if the result is 0, or false for all other
  * cases.
  */
-static inline int atomic_dec_and_test(atomic_t *v)
+static __always_inline int atomic_dec_and_test(atomic_t *v)
 {
 	GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", "e");
 }
@@ -126,7 +126,7 @@ static inline int atomic_dec_and_test(atomic_t *v)
  * and returns true if the result is zero, or false for all
  * other cases.
  */
-static inline int atomic_inc_and_test(atomic_t *v)
+static __always_inline int atomic_inc_and_test(atomic_t *v)
 {
 	GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, "%0", "e");
 }
@@ -140,7 +140,7 @@ static inline int atomic_inc_and_test(atomic_t *v)
  * if the result is negative, or false when
  * result is greater than or equal to zero.
  */
-static inline int atomic_add_negative(int i, atomic_t *v)
+static __always_inline int atomic_add_negative(int i, atomic_t *v)
 {
 	GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, "er", i, "%0", "s");
 }
@@ -152,7 +152,7 @@ static inline int atomic_add_negative(int i, atomic_t *v)
  *
  * Atomically adds @i to @v and returns @i + @v
  */
-static inline int atomic_add_return(int i, atomic_t *v)
+static __always_inline int atomic_add_return(int i, atomic_t *v)
 {
 	return i + xadd(&v->counter, i);
 }
@@ -164,7 +164,7 @@ static inline int atomic_add_return(int i, atomic_t *v)
  *
  * Atomically subtracts @i from @v and returns @v - @i
  */
-static inline int atomic_sub_return(int i, atomic_t *v)
+static __always_inline int atomic_sub_return(int i, atomic_t *v)
 {
 	return atomic_add_return(-i, v);
 }
@@ -172,7 +172,7 @@ static inline int atomic_sub_return(int i, atomic_t *v)
 #define atomic_inc_return(v)  (atomic_add_return(1, v))
 #define atomic_dec_return(v)  (atomic_sub_return(1, v))
 
-static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
+static __always_inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 {
 	return cmpxchg(&v->counter, old, new);
 }
@@ -191,7 +191,7 @@ static inline int atomic_xchg(atomic_t *v, int new)
  * Atomically adds @a to @v, so long as @v was not already @u.
  * Returns the old value of @v.
  */
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
+static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u)
 {
 	int c, old;
 	c = atomic_read(v);
@@ -213,7 +213,7 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
  * Atomically adds 1 to @v
  * Returns the new value of @u
  */
-static inline short int atomic_inc_short(short int *v)
+static __always_inline short int atomic_inc_short(short int *v)
 {
 	asm(LOCK_PREFIX "addw $1, %0" : "+m" (*v));
 	return *v;
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index f8d273e18516..b965f9e03f2a 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -40,7 +40,7 @@ static inline void atomic64_set(atomic64_t *v, long i)
  *
  * Atomically adds @i to @v.
  */
-static inline void atomic64_add(long i, atomic64_t *v)
+static __always_inline void atomic64_add(long i, atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "addq %1,%0"
 		     : "=m" (v->counter)
@@ -81,7 +81,7 @@ static inline int atomic64_sub_and_test(long i, atomic64_t *v)
  *
  * Atomically increments @v by 1.
  */
-static inline void atomic64_inc(atomic64_t *v)
+static __always_inline void atomic64_inc(atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "incq %0"
 		     : "=m" (v->counter)
@@ -94,7 +94,7 @@ static inline void atomic64_inc(atomic64_t *v)
  *
  * Atomically decrements @v by 1.
  */
-static inline void atomic64_dec(atomic64_t *v)
+static __always_inline void atomic64_dec(atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "decq %0"
 		     : "=m" (v->counter)
@@ -148,7 +148,7 @@ static inline int atomic64_add_negative(long i, atomic64_t *v)
  *
  * Atomically adds @i to @v and returns @i + @v
  */
-static inline long atomic64_add_return(long i, atomic64_t *v)
+static __always_inline long atomic64_add_return(long i, atomic64_t *v)
 {
 	return i + xadd(&v->counter, i);
 }
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index 959e45b81fe2..e51a8f803f55 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -35,12 +35,12 @@
 #define smp_mb()	mb()
 #define smp_rmb()	dma_rmb()
 #define smp_wmb()	barrier()
-#define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
+#define smp_store_mb(var, value) do { (void)xchg(&var, value); } while (0)
 #else /* !SMP */
 #define smp_mb()	barrier()
 #define smp_rmb()	barrier()
 #define smp_wmb()	barrier()
-#define set_mb(var, value) do { var = value; barrier(); } while (0)
+#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); barrier(); } while (0)
 #endif /* SMP */
 
 #define read_barrier_depends()		do { } while (0)
diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h
index 47c8e32f621a..b6f7457d12e4 100644
--- a/arch/x86/include/asm/cacheflush.h
+++ b/arch/x86/include/asm/cacheflush.h
@@ -8,7 +8,7 @@
 /*
  * The set_memory_* API can be used to change various attributes of a virtual
  * address range. The attributes include:
- * Cachability   : UnCached, WriteCombining, WriteBack
+ * Cachability   : UnCached, WriteCombining, WriteThrough, WriteBack
  * Executability : eXeutable, NoteXecutable
  * Read/Write    : ReadOnly, ReadWrite
  * Presence      : NotPresent
@@ -35,9 +35,11 @@
 
 int _set_memory_uc(unsigned long addr, int numpages);
 int _set_memory_wc(unsigned long addr, int numpages);
+int _set_memory_wt(unsigned long addr, int numpages);
 int _set_memory_wb(unsigned long addr, int numpages);
 int set_memory_uc(unsigned long addr, int numpages);
 int set_memory_wc(unsigned long addr, int numpages);
+int set_memory_wt(unsigned long addr, int numpages);
 int set_memory_wb(unsigned long addr, int numpages);
 int set_memory_x(unsigned long addr, int numpages);
 int set_memory_nx(unsigned long addr, int numpages);
@@ -48,10 +50,12 @@ int set_memory_4k(unsigned long addr, int numpages);
 
 int set_memory_array_uc(unsigned long *addr, int addrinarray);
 int set_memory_array_wc(unsigned long *addr, int addrinarray);
+int set_memory_array_wt(unsigned long *addr, int addrinarray);
 int set_memory_array_wb(unsigned long *addr, int addrinarray);
 
 int set_pages_array_uc(struct page **pages, int addrinarray);
 int set_pages_array_wc(struct page **pages, int addrinarray);
+int set_pages_array_wt(struct page **pages, int addrinarray);
 int set_pages_array_wb(struct page **pages, int addrinarray);
 
 /*
diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h
index 99c105d78b7e..ad19841eddfe 100644
--- a/arch/x86/include/asm/cmpxchg.h
+++ b/arch/x86/include/asm/cmpxchg.h
@@ -4,8 +4,6 @@
 #include <linux/compiler.h>
 #include <asm/alternative.h> /* Provides LOCK_PREFIX */
 
-#define __HAVE_ARCH_CMPXCHG 1
-
 /*
  * Non-existant functions to indicate usage errors at link time
  * (or compile-time if the compiler implements __compiletime_error().
diff --git a/arch/x86/include/asm/crypto/glue_helper.h b/arch/x86/include/asm/crypto/glue_helper.h
index 1eef55596e82..03bb1065c335 100644
--- a/arch/x86/include/asm/crypto/glue_helper.h
+++ b/arch/x86/include/asm/crypto/glue_helper.h
@@ -7,7 +7,7 @@
 
 #include <linux/kernel.h>
 #include <linux/crypto.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 #include <crypto/b128ops.h>
 
 typedef void (*common_glue_func_t)(void *ctx, u8 *dst, const u8 *src);
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index 808dae63eeea..1f5b7287d1ad 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -127,50 +127,14 @@ static inline gfp_t dma_alloc_coherent_gfp_flags(struct device *dev, gfp_t gfp)
 
 #define dma_alloc_coherent(d,s,h,f)	dma_alloc_attrs(d,s,h,f,NULL)
 
-static inline void *
+void *
 dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
-		gfp_t gfp, struct dma_attrs *attrs)
-{
-	struct dma_map_ops *ops = get_dma_ops(dev);
-	void *memory;
-
-	gfp &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32);
-
-	if (dma_alloc_from_coherent(dev, size, dma_handle, &memory))
-		return memory;
-
-	if (!dev)
-		dev = &x86_dma_fallback_dev;
-
-	if (!is_device_dma_capable(dev))
-		return NULL;
-
-	if (!ops->alloc)
-		return NULL;
-
-	memory = ops->alloc(dev, size, dma_handle,
-			    dma_alloc_coherent_gfp_flags(dev, gfp), attrs);
-	debug_dma_alloc_coherent(dev, size, *dma_handle, memory);
-
-	return memory;
-}
+		gfp_t gfp, struct dma_attrs *attrs);
 
 #define dma_free_coherent(d,s,c,h) dma_free_attrs(d,s,c,h,NULL)
 
-static inline void dma_free_attrs(struct device *dev, size_t size,
-				  void *vaddr, dma_addr_t bus,
-				  struct dma_attrs *attrs)
-{
-	struct dma_map_ops *ops = get_dma_ops(dev);
-
-	WARN_ON(irqs_disabled());       /* for portability */
-
-	if (dma_release_from_coherent(dev, get_order(size), vaddr))
-		return;
-
-	debug_dma_free_coherent(dev, size, vaddr, bus);
-	if (ops->free)
-		ops->free(dev, size, vaddr, bus, attrs);
-}
+void dma_free_attrs(struct device *dev, size_t size,
+		    void *vaddr, dma_addr_t bus,
+		    struct dma_attrs *attrs);
 
 #endif
diff --git a/arch/x86/include/asm/dwarf2.h b/arch/x86/include/asm/dwarf2.h
deleted file mode 100644
index de1cdaf4d743..000000000000
--- a/arch/x86/include/asm/dwarf2.h
+++ /dev/null
@@ -1,170 +0,0 @@
-#ifndef _ASM_X86_DWARF2_H
-#define _ASM_X86_DWARF2_H
-
-#ifndef __ASSEMBLY__
-#warning "asm/dwarf2.h should be only included in pure assembly files"
-#endif
-
-/*
- * Macros for dwarf2 CFI unwind table entries.
- * See "as.info" for details on these pseudo ops. Unfortunately
- * they are only supported in very new binutils, so define them
- * away for older version.
- */
-
-#ifdef CONFIG_AS_CFI
-
-#define CFI_STARTPROC		.cfi_startproc
-#define CFI_ENDPROC		.cfi_endproc
-#define CFI_DEF_CFA		.cfi_def_cfa
-#define CFI_DEF_CFA_REGISTER	.cfi_def_cfa_register
-#define CFI_DEF_CFA_OFFSET	.cfi_def_cfa_offset
-#define CFI_ADJUST_CFA_OFFSET	.cfi_adjust_cfa_offset
-#define CFI_OFFSET		.cfi_offset
-#define CFI_REL_OFFSET		.cfi_rel_offset
-#define CFI_REGISTER		.cfi_register
-#define CFI_RESTORE		.cfi_restore
-#define CFI_REMEMBER_STATE	.cfi_remember_state
-#define CFI_RESTORE_STATE	.cfi_restore_state
-#define CFI_UNDEFINED		.cfi_undefined
-#define CFI_ESCAPE		.cfi_escape
-
-#ifdef CONFIG_AS_CFI_SIGNAL_FRAME
-#define CFI_SIGNAL_FRAME	.cfi_signal_frame
-#else
-#define CFI_SIGNAL_FRAME
-#endif
-
-#if defined(CONFIG_AS_CFI_SECTIONS) && defined(__ASSEMBLY__)
-	/*
-	 * Emit CFI data in .debug_frame sections, not .eh_frame sections.
-	 * The latter we currently just discard since we don't do DWARF
-	 * unwinding at runtime.  So only the offline DWARF information is
-	 * useful to anyone.  Note we should not use this directive if this
-	 * file is used in the vDSO assembly, or if vmlinux.lds.S gets
-	 * changed so it doesn't discard .eh_frame.
-	 */
-	.cfi_sections .debug_frame
-#endif
-
-#else
-
-/*
- * Due to the structure of pre-exisiting code, don't use assembler line
- * comment character # to ignore the arguments. Instead, use a dummy macro.
- */
-.macro cfi_ignore a=0, b=0, c=0, d=0
-.endm
-
-#define CFI_STARTPROC		cfi_ignore
-#define CFI_ENDPROC		cfi_ignore
-#define CFI_DEF_CFA		cfi_ignore
-#define CFI_DEF_CFA_REGISTER	cfi_ignore
-#define CFI_DEF_CFA_OFFSET	cfi_ignore
-#define CFI_ADJUST_CFA_OFFSET	cfi_ignore
-#define CFI_OFFSET		cfi_ignore
-#define CFI_REL_OFFSET		cfi_ignore
-#define CFI_REGISTER		cfi_ignore
-#define CFI_RESTORE		cfi_ignore
-#define CFI_REMEMBER_STATE	cfi_ignore
-#define CFI_RESTORE_STATE	cfi_ignore
-#define CFI_UNDEFINED		cfi_ignore
-#define CFI_ESCAPE		cfi_ignore
-#define CFI_SIGNAL_FRAME	cfi_ignore
-
-#endif
-
-/*
- * An attempt to make CFI annotations more or less
- * correct and shorter. It is implied that you know
- * what you're doing if you use them.
- */
-#ifdef __ASSEMBLY__
-#ifdef CONFIG_X86_64
-	.macro pushq_cfi reg
-	pushq \reg
-	CFI_ADJUST_CFA_OFFSET 8
-	.endm
-
-	.macro pushq_cfi_reg reg
-	pushq %\reg
-	CFI_ADJUST_CFA_OFFSET 8
-	CFI_REL_OFFSET \reg, 0
-	.endm
-
-	.macro popq_cfi reg
-	popq \reg
-	CFI_ADJUST_CFA_OFFSET -8
-	.endm
-
-	.macro popq_cfi_reg reg
-	popq %\reg
-	CFI_ADJUST_CFA_OFFSET -8
-	CFI_RESTORE \reg
-	.endm
-
-	.macro pushfq_cfi
-	pushfq
-	CFI_ADJUST_CFA_OFFSET 8
-	.endm
-
-	.macro popfq_cfi
-	popfq
-	CFI_ADJUST_CFA_OFFSET -8
-	.endm
-
-	.macro movq_cfi reg offset=0
-	movq %\reg, \offset(%rsp)
-	CFI_REL_OFFSET \reg, \offset
-	.endm
-
-	.macro movq_cfi_restore offset reg
-	movq \offset(%rsp), %\reg
-	CFI_RESTORE \reg
-	.endm
-#else /*!CONFIG_X86_64*/
-	.macro pushl_cfi reg
-	pushl \reg
-	CFI_ADJUST_CFA_OFFSET 4
-	.endm
-
-	.macro pushl_cfi_reg reg
-	pushl %\reg
-	CFI_ADJUST_CFA_OFFSET 4
-	CFI_REL_OFFSET \reg, 0
-	.endm
-
-	.macro popl_cfi reg
-	popl \reg
-	CFI_ADJUST_CFA_OFFSET -4
-	.endm
-
-	.macro popl_cfi_reg reg
-	popl %\reg
-	CFI_ADJUST_CFA_OFFSET -4
-	CFI_RESTORE \reg
-	.endm
-
-	.macro pushfl_cfi
-	pushfl
-	CFI_ADJUST_CFA_OFFSET 4
-	.endm
-
-	.macro popfl_cfi
-	popfl
-	CFI_ADJUST_CFA_OFFSET -4
-	.endm
-
-	.macro movl_cfi reg offset=0
-	movl %\reg, \offset(%esp)
-	CFI_REL_OFFSET \reg, \offset
-	.endm
-
-	.macro movl_cfi_restore offset reg
-	movl \offset(%esp), %\reg
-	CFI_RESTORE \reg
-	.endm
-#endif /*!CONFIG_X86_64*/
-#endif /*__ASSEMBLY__*/
-
-#endif /* _ASM_X86_DWARF2_H */
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 3738b138b843..155162ea0e00 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -1,7 +1,7 @@
 #ifndef _ASM_X86_EFI_H
 #define _ASM_X86_EFI_H
 
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 #include <asm/pgtable.h>
 
 /*
diff --git a/arch/x86/include/asm/entry_arch.h b/arch/x86/include/asm/entry_arch.h
index dc5fa661465f..df002992d8fd 100644
--- a/arch/x86/include/asm/entry_arch.h
+++ b/arch/x86/include/asm/entry_arch.h
@@ -23,6 +23,8 @@ BUILD_INTERRUPT(x86_platform_ipi, X86_PLATFORM_IPI_VECTOR)
 #ifdef CONFIG_HAVE_KVM
 BUILD_INTERRUPT3(kvm_posted_intr_ipi, POSTED_INTR_VECTOR,
 		 smp_kvm_posted_intr_ipi)
+BUILD_INTERRUPT3(kvm_posted_intr_wakeup_ipi, POSTED_INTR_WAKEUP_VECTOR,
+		 smp_kvm_posted_intr_wakeup_ipi)
 #endif
 
 /*
@@ -50,4 +52,7 @@ BUILD_INTERRUPT(thermal_interrupt,THERMAL_APIC_VECTOR)
 BUILD_INTERRUPT(threshold_interrupt,THRESHOLD_APIC_VECTOR)
 #endif
 
+#ifdef CONFIG_X86_MCE_AMD
+BUILD_INTERRUPT(deferred_error_interrupt, DEFERRED_ERROR_VECTOR)
+#endif
 #endif
diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h
deleted file mode 100644
index da5e96756570..000000000000
--- a/arch/x86/include/asm/fpu-internal.h
+++ /dev/null
@@ -1,626 +0,0 @@
-/*
- * Copyright (C) 1994 Linus Torvalds
- *
- * Pentium III FXSR, SSE support
- * General FPU state handling cleanups
- *	Gareth Hughes <gareth@valinux.com>, May 2000
- * x86-64 work by Andi Kleen 2002
- */
-
-#ifndef _FPU_INTERNAL_H
-#define _FPU_INTERNAL_H
-
-#include <linux/kernel_stat.h>
-#include <linux/regset.h>
-#include <linux/compat.h>
-#include <linux/slab.h>
-#include <asm/asm.h>
-#include <asm/cpufeature.h>
-#include <asm/processor.h>
-#include <asm/sigcontext.h>
-#include <asm/user.h>
-#include <asm/uaccess.h>
-#include <asm/xsave.h>
-#include <asm/smap.h>
-
-#ifdef CONFIG_X86_64
-# include <asm/sigcontext32.h>
-# include <asm/user32.h>
-struct ksignal;
-int ia32_setup_rt_frame(int sig, struct ksignal *ksig,
-			compat_sigset_t *set, struct pt_regs *regs);
-int ia32_setup_frame(int sig, struct ksignal *ksig,
-		     compat_sigset_t *set, struct pt_regs *regs);
-#else
-# define user_i387_ia32_struct	user_i387_struct
-# define user32_fxsr_struct	user_fxsr_struct
-# define ia32_setup_frame	__setup_frame
-# define ia32_setup_rt_frame	__setup_rt_frame
-#endif
-
-extern unsigned int mxcsr_feature_mask;
-extern void fpu_init(void);
-extern void eager_fpu_init(void);
-
-DECLARE_PER_CPU(struct task_struct *, fpu_owner_task);
-
-extern void convert_from_fxsr(struct user_i387_ia32_struct *env,
-			      struct task_struct *tsk);
-extern void convert_to_fxsr(struct task_struct *tsk,
-			    const struct user_i387_ia32_struct *env);
-
-extern user_regset_active_fn fpregs_active, xfpregs_active;
-extern user_regset_get_fn fpregs_get, xfpregs_get, fpregs_soft_get,
-				xstateregs_get;
-extern user_regset_set_fn fpregs_set, xfpregs_set, fpregs_soft_set,
-				 xstateregs_set;
-
-/*
- * xstateregs_active == fpregs_active. Please refer to the comment
- * at the definition of fpregs_active.
- */
-#define xstateregs_active	fpregs_active
-
-#ifdef CONFIG_MATH_EMULATION
-extern void finit_soft_fpu(struct i387_soft_struct *soft);
-#else
-static inline void finit_soft_fpu(struct i387_soft_struct *soft) {}
-#endif
-
-/*
- * Must be run with preemption disabled: this clears the fpu_owner_task,
- * on this CPU.
- *
- * This will disable any lazy FPU state restore of the current FPU state,
- * but if the current thread owns the FPU, it will still be saved by.
- */
-static inline void __cpu_disable_lazy_restore(unsigned int cpu)
-{
-	per_cpu(fpu_owner_task, cpu) = NULL;
-}
-
-/*
- * Used to indicate that the FPU state in memory is newer than the FPU
- * state in registers, and the FPU state should be reloaded next time the
- * task is run. Only safe on the current task, or non-running tasks.
- */
-static inline void task_disable_lazy_fpu_restore(struct task_struct *tsk)
-{
-	tsk->thread.fpu.last_cpu = ~0;
-}
-
-static inline int fpu_lazy_restore(struct task_struct *new, unsigned int cpu)
-{
-	return new == this_cpu_read_stable(fpu_owner_task) &&
-		cpu == new->thread.fpu.last_cpu;
-}
-
-static inline int is_ia32_compat_frame(void)
-{
-	return config_enabled(CONFIG_IA32_EMULATION) &&
-	       test_thread_flag(TIF_IA32);
-}
-
-static inline int is_ia32_frame(void)
-{
-	return config_enabled(CONFIG_X86_32) || is_ia32_compat_frame();
-}
-
-static inline int is_x32_frame(void)
-{
-	return config_enabled(CONFIG_X86_X32_ABI) && test_thread_flag(TIF_X32);
-}
-
-#define X87_FSW_ES (1 << 7)	/* Exception Summary */
-
-static __always_inline __pure bool use_eager_fpu(void)
-{
-	return static_cpu_has_safe(X86_FEATURE_EAGER_FPU);
-}
-
-static __always_inline __pure bool use_xsaveopt(void)
-{
-	return static_cpu_has_safe(X86_FEATURE_XSAVEOPT);
-}
-
-static __always_inline __pure bool use_xsave(void)
-{
-	return static_cpu_has_safe(X86_FEATURE_XSAVE);
-}
-
-static __always_inline __pure bool use_fxsr(void)
-{
-	return static_cpu_has_safe(X86_FEATURE_FXSR);
-}
-
-static inline void fx_finit(struct i387_fxsave_struct *fx)
-{
-	fx->cwd = 0x37f;
-	fx->mxcsr = MXCSR_DEFAULT;
-}
-
-extern void __sanitize_i387_state(struct task_struct *);
-
-static inline void sanitize_i387_state(struct task_struct *tsk)
-{
-	if (!use_xsaveopt())
-		return;
-	__sanitize_i387_state(tsk);
-}
-
-#define user_insn(insn, output, input...)				\
-({									\
-	int err;							\
-	asm volatile(ASM_STAC "\n"					\
-		     "1:" #insn "\n\t"					\
-		     "2: " ASM_CLAC "\n"				\
-		     ".section .fixup,\"ax\"\n"				\
-		     "3:  movl $-1,%[err]\n"				\
-		     "    jmp  2b\n"					\
-		     ".previous\n"					\
-		     _ASM_EXTABLE(1b, 3b)				\
-		     : [err] "=r" (err), output				\
-		     : "0"(0), input);					\
-	err;								\
-})
-
-#define check_insn(insn, output, input...)				\
-({									\
-	int err;							\
-	asm volatile("1:" #insn "\n\t"					\
-		     "2:\n"						\
-		     ".section .fixup,\"ax\"\n"				\
-		     "3:  movl $-1,%[err]\n"				\
-		     "    jmp  2b\n"					\
-		     ".previous\n"					\
-		     _ASM_EXTABLE(1b, 3b)				\
-		     : [err] "=r" (err), output				\
-		     : "0"(0), input);					\
-	err;								\
-})
-
-static inline int fsave_user(struct i387_fsave_struct __user *fx)
-{
-	return user_insn(fnsave %[fx]; fwait,  [fx] "=m" (*fx), "m" (*fx));
-}
-
-static inline int fxsave_user(struct i387_fxsave_struct __user *fx)
-{
-	if (config_enabled(CONFIG_X86_32))
-		return user_insn(fxsave %[fx], [fx] "=m" (*fx), "m" (*fx));
-	else if (config_enabled(CONFIG_AS_FXSAVEQ))
-		return user_insn(fxsaveq %[fx], [fx] "=m" (*fx), "m" (*fx));
-
-	/* See comment in fpu_fxsave() below. */
-	return user_insn(rex64/fxsave (%[fx]), "=m" (*fx), [fx] "R" (fx));
-}
-
-static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
-{
-	if (config_enabled(CONFIG_X86_32))
-		return check_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
-	else if (config_enabled(CONFIG_AS_FXSAVEQ))
-		return check_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
-
-	/* See comment in fpu_fxsave() below. */
-	return check_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx),
-			  "m" (*fx));
-}
-
-static inline int fxrstor_user(struct i387_fxsave_struct __user *fx)
-{
-	if (config_enabled(CONFIG_X86_32))
-		return user_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
-	else if (config_enabled(CONFIG_AS_FXSAVEQ))
-		return user_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
-
-	/* See comment in fpu_fxsave() below. */
-	return user_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx),
-			  "m" (*fx));
-}
-
-static inline int frstor_checking(struct i387_fsave_struct *fx)
-{
-	return check_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
-}
-
-static inline int frstor_user(struct i387_fsave_struct __user *fx)
-{
-	return user_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
-}
-
-static inline void fpu_fxsave(struct fpu *fpu)
-{
-	if (config_enabled(CONFIG_X86_32))
-		asm volatile( "fxsave %[fx]" : [fx] "=m" (fpu->state->fxsave));
-	else if (config_enabled(CONFIG_AS_FXSAVEQ))
-		asm volatile("fxsaveq %[fx]" : [fx] "=m" (fpu->state->fxsave));
-	else {
-		/* Using "rex64; fxsave %0" is broken because, if the memory
-		 * operand uses any extended registers for addressing, a second
-		 * REX prefix will be generated (to the assembler, rex64
-		 * followed by semicolon is a separate instruction), and hence
-		 * the 64-bitness is lost.
-		 *
-		 * Using "fxsaveq %0" would be the ideal choice, but is only
-		 * supported starting with gas 2.16.
-		 *
-		 * Using, as a workaround, the properly prefixed form below
-		 * isn't accepted by any binutils version so far released,
-		 * complaining that the same type of prefix is used twice if
-		 * an extended register is needed for addressing (fix submitted
-		 * to mainline 2005-11-21).
-		 *
-		 *  asm volatile("rex64/fxsave %0" : "=m" (fpu->state->fxsave));
-		 *
-		 * This, however, we can work around by forcing the compiler to
-		 * select an addressing mode that doesn't require extended
-		 * registers.
-		 */
-		asm volatile( "rex64/fxsave (%[fx])"
-			     : "=m" (fpu->state->fxsave)
-			     : [fx] "R" (&fpu->state->fxsave));
-	}
-}
-
-/*
- * These must be called with preempt disabled. Returns
- * 'true' if the FPU state is still intact.
- */
-static inline int fpu_save_init(struct fpu *fpu)
-{
-	if (use_xsave()) {
-		fpu_xsave(fpu);
-
-		/*
-		 * xsave header may indicate the init state of the FP.
-		 */
-		if (!(fpu->state->xsave.xsave_hdr.xstate_bv & XSTATE_FP))
-			return 1;
-	} else if (use_fxsr()) {
-		fpu_fxsave(fpu);
-	} else {
-		asm volatile("fnsave %[fx]; fwait"
-			     : [fx] "=m" (fpu->state->fsave));
-		return 0;
-	}
-
-	/*
-	 * If exceptions are pending, we need to clear them so
-	 * that we don't randomly get exceptions later.
-	 *
-	 * FIXME! Is this perhaps only true for the old-style
-	 * irq13 case? Maybe we could leave the x87 state
-	 * intact otherwise?
-	 */
-	if (unlikely(fpu->state->fxsave.swd & X87_FSW_ES)) {
-		asm volatile("fnclex");
-		return 0;
-	}
-	return 1;
-}
-
-static inline int __save_init_fpu(struct task_struct *tsk)
-{
-	return fpu_save_init(&tsk->thread.fpu);
-}
-
-static inline int fpu_restore_checking(struct fpu *fpu)
-{
-	if (use_xsave())
-		return fpu_xrstor_checking(&fpu->state->xsave);
-	else if (use_fxsr())
-		return fxrstor_checking(&fpu->state->fxsave);
-	else
-		return frstor_checking(&fpu->state->fsave);
-}
-
-static inline int restore_fpu_checking(struct task_struct *tsk)
-{
-	/*
-	 * AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception is
-	 * pending. Clear the x87 state here by setting it to fixed values.
-	 * "m" is a random variable that should be in L1.
-	 */
-	if (unlikely(static_cpu_has_bug_safe(X86_BUG_FXSAVE_LEAK))) {
-		asm volatile(
-			"fnclex\n\t"
-			"emms\n\t"
-			"fildl %P[addr]"	/* set F?P to defined value */
-			: : [addr] "m" (tsk->thread.fpu.has_fpu));
-	}
-
-	return fpu_restore_checking(&tsk->thread.fpu);
-}
-
-/*
- * Software FPU state helpers. Careful: these need to
- * be preemption protection *and* they need to be
- * properly paired with the CR0.TS changes!
- */
-static inline int __thread_has_fpu(struct task_struct *tsk)
-{
-	return tsk->thread.fpu.has_fpu;
-}
-
-/* Must be paired with an 'stts' after! */
-static inline void __thread_clear_has_fpu(struct task_struct *tsk)
-{
-	tsk->thread.fpu.has_fpu = 0;
-	this_cpu_write(fpu_owner_task, NULL);
-}
-
-/* Must be paired with a 'clts' before! */
-static inline void __thread_set_has_fpu(struct task_struct *tsk)
-{
-	tsk->thread.fpu.has_fpu = 1;
-	this_cpu_write(fpu_owner_task, tsk);
-}
-
-/*
- * Encapsulate the CR0.TS handling together with the
- * software flag.
- *
- * These generally need preemption protection to work,
- * do try to avoid using these on their own.
- */
-static inline void __thread_fpu_end(struct task_struct *tsk)
-{
-	__thread_clear_has_fpu(tsk);
-	if (!use_eager_fpu())
-		stts();
-}
-
-static inline void __thread_fpu_begin(struct task_struct *tsk)
-{
-	if (!use_eager_fpu())
-		clts();
-	__thread_set_has_fpu(tsk);
-}
-
-static inline void drop_fpu(struct task_struct *tsk)
-{
-	/*
-	 * Forget coprocessor state..
-	 */
-	preempt_disable();
-	tsk->thread.fpu_counter = 0;
-
-	if (__thread_has_fpu(tsk)) {
-		/* Ignore delayed exceptions from user space */
-		asm volatile("1: fwait\n"
-			     "2:\n"
-			     _ASM_EXTABLE(1b, 2b));
-		__thread_fpu_end(tsk);
-	}
-
-	clear_stopped_child_used_math(tsk);
-	preempt_enable();
-}
-
-static inline void restore_init_xstate(void)
-{
-	if (use_xsave())
-		xrstor_state(init_xstate_buf, -1);
-	else
-		fxrstor_checking(&init_xstate_buf->i387);
-}
-
-/*
- * Reset the FPU state in the eager case and drop it in the lazy case (later use
- * will reinit it).
- */
-static inline void fpu_reset_state(struct task_struct *tsk)
-{
-	if (!use_eager_fpu())
-		drop_fpu(tsk);
-	else
-		restore_init_xstate();
-}
-
-/*
- * FPU state switching for scheduling.
- *
- * This is a two-stage process:
- *
- *  - switch_fpu_prepare() saves the old state and
- *    sets the new state of the CR0.TS bit. This is
- *    done within the context of the old process.
- *
- *  - switch_fpu_finish() restores the new state as
- *    necessary.
- */
-typedef struct { int preload; } fpu_switch_t;
-
-static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct task_struct *new, int cpu)
-{
-	fpu_switch_t fpu;
-
-	/*
-	 * If the task has used the math, pre-load the FPU on xsave processors
-	 * or if the past 5 consecutive context-switches used math.
-	 */
-	fpu.preload = tsk_used_math(new) &&
-		      (use_eager_fpu() || new->thread.fpu_counter > 5);
-
-	if (__thread_has_fpu(old)) {
-		if (!__save_init_fpu(old))
-			task_disable_lazy_fpu_restore(old);
-		else
-			old->thread.fpu.last_cpu = cpu;
-
-		/* But leave fpu_owner_task! */
-		old->thread.fpu.has_fpu = 0;
-
-		/* Don't change CR0.TS if we just switch! */
-		if (fpu.preload) {
-			new->thread.fpu_counter++;
-			__thread_set_has_fpu(new);
-			prefetch(new->thread.fpu.state);
-		} else if (!use_eager_fpu())
-			stts();
-	} else {
-		old->thread.fpu_counter = 0;
-		task_disable_lazy_fpu_restore(old);
-		if (fpu.preload) {
-			new->thread.fpu_counter++;
-			if (fpu_lazy_restore(new, cpu))
-				fpu.preload = 0;
-			else
-				prefetch(new->thread.fpu.state);
-			__thread_fpu_begin(new);
-		}
-	}
-	return fpu;
-}
-
-/*
- * By the time this gets called, we've already cleared CR0.TS and
- * given the process the FPU if we are going to preload the FPU
- * state - all we need to do is to conditionally restore the register
- * state itself.
- */
-static inline void switch_fpu_finish(struct task_struct *new, fpu_switch_t fpu)
-{
-	if (fpu.preload) {
-		if (unlikely(restore_fpu_checking(new)))
-			fpu_reset_state(new);
-	}
-}
-
-/*
- * Signal frame handlers...
- */
-extern int save_xstate_sig(void __user *buf, void __user *fx, int size);
-extern int __restore_xstate_sig(void __user *buf, void __user *fx, int size);
-
-static inline int xstate_sigframe_size(void)
-{
-	return use_xsave() ? xstate_size + FP_XSTATE_MAGIC2_SIZE : xstate_size;
-}
-
-static inline int restore_xstate_sig(void __user *buf, int ia32_frame)
-{
-	void __user *buf_fx = buf;
-	int size = xstate_sigframe_size();
-
-	if (ia32_frame && use_fxsr()) {
-		buf_fx = buf + sizeof(struct i387_fsave_struct);
-		size += sizeof(struct i387_fsave_struct);
-	}
-
-	return __restore_xstate_sig(buf, buf_fx, size);
-}
-
-/*
- * Needs to be preemption-safe.
- *
- * NOTE! user_fpu_begin() must be used only immediately before restoring
- * the save state. It does not do any saving/restoring on its own. In
- * lazy FPU mode, it is just an optimization to avoid a #NM exception,
- * the task can lose the FPU right after preempt_enable().
- */
-static inline void user_fpu_begin(void)
-{
-	preempt_disable();
-	if (!user_has_fpu())
-		__thread_fpu_begin(current);
-	preempt_enable();
-}
-
-static inline void __save_fpu(struct task_struct *tsk)
-{
-	if (use_xsave()) {
-		if (unlikely(system_state == SYSTEM_BOOTING))
-			xsave_state_booting(&tsk->thread.fpu.state->xsave, -1);
-		else
-			xsave_state(&tsk->thread.fpu.state->xsave, -1);
-	} else
-		fpu_fxsave(&tsk->thread.fpu);
-}
-
-/*
- * i387 state interaction
- */
-static inline unsigned short get_fpu_cwd(struct task_struct *tsk)
-{
-	if (cpu_has_fxsr) {
-		return tsk->thread.fpu.state->fxsave.cwd;
-	} else {
-		return (unsigned short)tsk->thread.fpu.state->fsave.cwd;
-	}
-}
-
-static inline unsigned short get_fpu_swd(struct task_struct *tsk)
-{
-	if (cpu_has_fxsr) {
-		return tsk->thread.fpu.state->fxsave.swd;
-	} else {
-		return (unsigned short)tsk->thread.fpu.state->fsave.swd;
-	}
-}
-
-static inline unsigned short get_fpu_mxcsr(struct task_struct *tsk)
-{
-	if (cpu_has_xmm) {
-		return tsk->thread.fpu.state->fxsave.mxcsr;
-	} else {
-		return MXCSR_DEFAULT;
-	}
-}
-
-static bool fpu_allocated(struct fpu *fpu)
-{
-	return fpu->state != NULL;
-}
-
-static inline int fpu_alloc(struct fpu *fpu)
-{
-	if (fpu_allocated(fpu))
-		return 0;
-	fpu->state = kmem_cache_alloc(task_xstate_cachep, GFP_KERNEL);
-	if (!fpu->state)
-		return -ENOMEM;
-	WARN_ON((unsigned long)fpu->state & 15);
-	return 0;
-}
-
-static inline void fpu_free(struct fpu *fpu)
-{
-	if (fpu->state) {
-		kmem_cache_free(task_xstate_cachep, fpu->state);
-		fpu->state = NULL;
-	}
-}
-
-static inline void fpu_copy(struct task_struct *dst, struct task_struct *src)
-{
-	if (use_eager_fpu()) {
-		memset(&dst->thread.fpu.state->xsave, 0, xstate_size);
-		__save_fpu(dst);
-	} else {
-		struct fpu *dfpu = &dst->thread.fpu;
-		struct fpu *sfpu = &src->thread.fpu;
-
-		unlazy_fpu(src);
-		memcpy(dfpu->state, sfpu->state, xstate_size);
-	}
-}
-
-static inline unsigned long
-alloc_mathframe(unsigned long sp, int ia32_frame, unsigned long *buf_fx,
-		unsigned long *size)
-{
-	unsigned long frame_size = xstate_sigframe_size();
-
-	*buf_fx = sp = round_down(sp - frame_size, 64);
-	if (ia32_frame && use_fxsr()) {
-		frame_size += sizeof(struct i387_fsave_struct);
-		sp -= sizeof(struct i387_fsave_struct);
-	}
-
-	*size = frame_size;
-	return sp;
-}
-
-#endif
diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h
new file mode 100644
index 000000000000..1429a7c736db
--- /dev/null
+++ b/arch/x86/include/asm/fpu/api.h
@@ -0,0 +1,48 @@
+/*
+ * Copyright (C) 1994 Linus Torvalds
+ *
+ * Pentium III FXSR, SSE support
+ * General FPU state handling cleanups
+ *	Gareth Hughes <gareth@valinux.com>, May 2000
+ * x86-64 work by Andi Kleen 2002
+ */
+
+#ifndef _ASM_X86_FPU_API_H
+#define _ASM_X86_FPU_API_H
+
+/*
+ * Careful: __kernel_fpu_begin/end() must be called with preempt disabled
+ * and they don't touch the preempt state on their own.
+ * If you enable preemption after __kernel_fpu_begin(), preempt notifier
+ * should call the __kernel_fpu_end() to prevent the kernel/user FPU
+ * state from getting corrupted. KVM for example uses this model.
+ *
+ * All other cases use kernel_fpu_begin/end() which disable preemption
+ * during kernel FPU usage.
+ */
+extern void __kernel_fpu_begin(void);
+extern void __kernel_fpu_end(void);
+extern void kernel_fpu_begin(void);
+extern void kernel_fpu_end(void);
+extern bool irq_fpu_usable(void);
+
+/*
+ * Some instructions like VIA's padlock instructions generate a spurious
+ * DNA fault but don't modify SSE registers. And these instructions
+ * get used from interrupt context as well. To prevent these kernel instructions
+ * in interrupt context interacting wrongly with other user/kernel fpu usage, we
+ * should use them only in the context of irq_ts_save/restore()
+ */
+extern int  irq_ts_save(void);
+extern void irq_ts_restore(int TS_state);
+
+/*
+ * Query the presence of one or more xfeatures. Works on any legacy CPU as well.
+ *
+ * If 'feature_name' is set then put a human-readable description of
+ * the feature there as well - this can be used to print error (or success)
+ * messages.
+ */
+extern int cpu_has_xfeatures(u64 xfeatures_mask, const char **feature_name);
+
+#endif /* _ASM_X86_FPU_API_H */
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
new file mode 100644
index 000000000000..3c3550c3a4a3
--- /dev/null
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -0,0 +1,694 @@
+/*
+ * Copyright (C) 1994 Linus Torvalds
+ *
+ * Pentium III FXSR, SSE support
+ * General FPU state handling cleanups
+ *	Gareth Hughes <gareth@valinux.com>, May 2000
+ * x86-64 work by Andi Kleen 2002
+ */
+
+#ifndef _ASM_X86_FPU_INTERNAL_H
+#define _ASM_X86_FPU_INTERNAL_H
+
+#include <linux/compat.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+
+#include <asm/user.h>
+#include <asm/fpu/api.h>
+#include <asm/fpu/xstate.h>
+
+/*
+ * High level FPU state handling functions:
+ */
+extern void fpu__activate_curr(struct fpu *fpu);
+extern void fpu__activate_fpstate_read(struct fpu *fpu);
+extern void fpu__activate_fpstate_write(struct fpu *fpu);
+extern void fpu__save(struct fpu *fpu);
+extern void fpu__restore(struct fpu *fpu);
+extern int  fpu__restore_sig(void __user *buf, int ia32_frame);
+extern void fpu__drop(struct fpu *fpu);
+extern int  fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu);
+extern void fpu__clear(struct fpu *fpu);
+extern int  fpu__exception_code(struct fpu *fpu, int trap_nr);
+extern int  dump_fpu(struct pt_regs *ptregs, struct user_i387_struct *fpstate);
+
+/*
+ * Boot time FPU initialization functions:
+ */
+extern void fpu__init_cpu(void);
+extern void fpu__init_system_xstate(void);
+extern void fpu__init_cpu_xstate(void);
+extern void fpu__init_system(struct cpuinfo_x86 *c);
+extern void fpu__init_check_bugs(void);
+extern void fpu__resume_cpu(void);
+
+/*
+ * Debugging facility:
+ */
+#ifdef CONFIG_X86_DEBUG_FPU
+# define WARN_ON_FPU(x) WARN_ON_ONCE(x)
+#else
+# define WARN_ON_FPU(x) ({ (void)(x); 0; })
+#endif
+
+/*
+ * FPU related CPU feature flag helper routines:
+ */
+static __always_inline __pure bool use_eager_fpu(void)
+{
+	return static_cpu_has_safe(X86_FEATURE_EAGER_FPU);
+}
+
+static __always_inline __pure bool use_xsaveopt(void)
+{
+	return static_cpu_has_safe(X86_FEATURE_XSAVEOPT);
+}
+
+static __always_inline __pure bool use_xsave(void)
+{
+	return static_cpu_has_safe(X86_FEATURE_XSAVE);
+}
+
+static __always_inline __pure bool use_fxsr(void)
+{
+	return static_cpu_has_safe(X86_FEATURE_FXSR);
+}
+
+/*
+ * fpstate handling functions:
+ */
+
+extern union fpregs_state init_fpstate;
+
+extern void fpstate_init(union fpregs_state *state);
+#ifdef CONFIG_MATH_EMULATION
+extern void fpstate_init_soft(struct swregs_state *soft);
+#else
+static inline void fpstate_init_soft(struct swregs_state *soft) {}
+#endif
+static inline void fpstate_init_fxstate(struct fxregs_state *fx)
+{
+	fx->cwd = 0x37f;
+	fx->mxcsr = MXCSR_DEFAULT;
+}
+extern void fpstate_sanitize_xstate(struct fpu *fpu);
+
+#define user_insn(insn, output, input...)				\
+({									\
+	int err;							\
+	asm volatile(ASM_STAC "\n"					\
+		     "1:" #insn "\n\t"					\
+		     "2: " ASM_CLAC "\n"				\
+		     ".section .fixup,\"ax\"\n"				\
+		     "3:  movl $-1,%[err]\n"				\
+		     "    jmp  2b\n"					\
+		     ".previous\n"					\
+		     _ASM_EXTABLE(1b, 3b)				\
+		     : [err] "=r" (err), output				\
+		     : "0"(0), input);					\
+	err;								\
+})
+
+#define check_insn(insn, output, input...)				\
+({									\
+	int err;							\
+	asm volatile("1:" #insn "\n\t"					\
+		     "2:\n"						\
+		     ".section .fixup,\"ax\"\n"				\
+		     "3:  movl $-1,%[err]\n"				\
+		     "    jmp  2b\n"					\
+		     ".previous\n"					\
+		     _ASM_EXTABLE(1b, 3b)				\
+		     : [err] "=r" (err), output				\
+		     : "0"(0), input);					\
+	err;								\
+})
+
+static inline int copy_fregs_to_user(struct fregs_state __user *fx)
+{
+	return user_insn(fnsave %[fx]; fwait,  [fx] "=m" (*fx), "m" (*fx));
+}
+
+static inline int copy_fxregs_to_user(struct fxregs_state __user *fx)
+{
+	if (config_enabled(CONFIG_X86_32))
+		return user_insn(fxsave %[fx], [fx] "=m" (*fx), "m" (*fx));
+	else if (config_enabled(CONFIG_AS_FXSAVEQ))
+		return user_insn(fxsaveq %[fx], [fx] "=m" (*fx), "m" (*fx));
+
+	/* See comment in copy_fxregs_to_kernel() below. */
+	return user_insn(rex64/fxsave (%[fx]), "=m" (*fx), [fx] "R" (fx));
+}
+
+static inline void copy_kernel_to_fxregs(struct fxregs_state *fx)
+{
+	int err;
+
+	if (config_enabled(CONFIG_X86_32)) {
+		err = check_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+	} else {
+		if (config_enabled(CONFIG_AS_FXSAVEQ)) {
+			err = check_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
+		} else {
+			/* See comment in copy_fxregs_to_kernel() below. */
+			err = check_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx), "m" (*fx));
+		}
+	}
+	/* Copying from a kernel buffer to FPU registers should never fail: */
+	WARN_ON_FPU(err);
+}
+
+static inline int copy_user_to_fxregs(struct fxregs_state __user *fx)
+{
+	if (config_enabled(CONFIG_X86_32))
+		return user_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+	else if (config_enabled(CONFIG_AS_FXSAVEQ))
+		return user_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
+
+	/* See comment in copy_fxregs_to_kernel() below. */
+	return user_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx),
+			  "m" (*fx));
+}
+
+static inline void copy_kernel_to_fregs(struct fregs_state *fx)
+{
+	int err = check_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+
+	WARN_ON_FPU(err);
+}
+
+static inline int copy_user_to_fregs(struct fregs_state __user *fx)
+{
+	return user_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+}
+
+static inline void copy_fxregs_to_kernel(struct fpu *fpu)
+{
+	if (config_enabled(CONFIG_X86_32))
+		asm volatile( "fxsave %[fx]" : [fx] "=m" (fpu->state.fxsave));
+	else if (config_enabled(CONFIG_AS_FXSAVEQ))
+		asm volatile("fxsaveq %[fx]" : [fx] "=m" (fpu->state.fxsave));
+	else {
+		/* Using "rex64; fxsave %0" is broken because, if the memory
+		 * operand uses any extended registers for addressing, a second
+		 * REX prefix will be generated (to the assembler, rex64
+		 * followed by semicolon is a separate instruction), and hence
+		 * the 64-bitness is lost.
+		 *
+		 * Using "fxsaveq %0" would be the ideal choice, but is only
+		 * supported starting with gas 2.16.
+		 *
+		 * Using, as a workaround, the properly prefixed form below
+		 * isn't accepted by any binutils version so far released,
+		 * complaining that the same type of prefix is used twice if
+		 * an extended register is needed for addressing (fix submitted
+		 * to mainline 2005-11-21).
+		 *
+		 *  asm volatile("rex64/fxsave %0" : "=m" (fpu->state.fxsave));
+		 *
+		 * This, however, we can work around by forcing the compiler to
+		 * select an addressing mode that doesn't require extended
+		 * registers.
+		 */
+		asm volatile( "rex64/fxsave (%[fx])"
+			     : "=m" (fpu->state.fxsave)
+			     : [fx] "R" (&fpu->state.fxsave));
+	}
+}
+
+/* These macros all use (%edi)/(%rdi) as the single memory argument. */
+#define XSAVE		".byte " REX_PREFIX "0x0f,0xae,0x27"
+#define XSAVEOPT	".byte " REX_PREFIX "0x0f,0xae,0x37"
+#define XSAVES		".byte " REX_PREFIX "0x0f,0xc7,0x2f"
+#define XRSTOR		".byte " REX_PREFIX "0x0f,0xae,0x2f"
+#define XRSTORS		".byte " REX_PREFIX "0x0f,0xc7,0x1f"
+
+/* xstate instruction fault handler: */
+#define xstate_fault(__err)		\
+					\
+	".section .fixup,\"ax\"\n"	\
+					\
+	"3:  movl $-2,%[_err]\n"	\
+	"    jmp  2b\n"			\
+					\
+	".previous\n"			\
+					\
+	_ASM_EXTABLE(1b, 3b)		\
+	: [_err] "=r" (__err)
+
+/*
+ * This function is called only during boot time when x86 caps are not set
+ * up and alternative can not be used yet.
+ */
+static inline void copy_xregs_to_kernel_booting(struct xregs_state *xstate)
+{
+	u64 mask = -1;
+	u32 lmask = mask;
+	u32 hmask = mask >> 32;
+	int err = 0;
+
+	WARN_ON(system_state != SYSTEM_BOOTING);
+
+	if (boot_cpu_has(X86_FEATURE_XSAVES))
+		asm volatile("1:"XSAVES"\n\t"
+			"2:\n\t"
+			     xstate_fault(err)
+			: "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err)
+			: "memory");
+	else
+		asm volatile("1:"XSAVE"\n\t"
+			"2:\n\t"
+			     xstate_fault(err)
+			: "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err)
+			: "memory");
+
+	/* We should never fault when copying to a kernel buffer: */
+	WARN_ON_FPU(err);
+}
+
+/*
+ * This function is called only during boot time when x86 caps are not set
+ * up and alternative can not be used yet.
+ */
+static inline void copy_kernel_to_xregs_booting(struct xregs_state *xstate)
+{
+	u64 mask = -1;
+	u32 lmask = mask;
+	u32 hmask = mask >> 32;
+	int err = 0;
+
+	WARN_ON(system_state != SYSTEM_BOOTING);
+
+	if (boot_cpu_has(X86_FEATURE_XSAVES))
+		asm volatile("1:"XRSTORS"\n\t"
+			"2:\n\t"
+			     xstate_fault(err)
+			: "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err)
+			: "memory");
+	else
+		asm volatile("1:"XRSTOR"\n\t"
+			"2:\n\t"
+			     xstate_fault(err)
+			: "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err)
+			: "memory");
+
+	/* We should never fault when copying from a kernel buffer: */
+	WARN_ON_FPU(err);
+}
+
+/*
+ * Save processor xstate to xsave area.
+ */
+static inline void copy_xregs_to_kernel(struct xregs_state *xstate)
+{
+	u64 mask = -1;
+	u32 lmask = mask;
+	u32 hmask = mask >> 32;
+	int err = 0;
+
+	WARN_ON(!alternatives_patched);
+
+	/*
+	 * If xsaves is enabled, xsaves replaces xsaveopt because
+	 * it supports compact format and supervisor states in addition to
+	 * modified optimization in xsaveopt.
+	 *
+	 * Otherwise, if xsaveopt is enabled, xsaveopt replaces xsave
+	 * because xsaveopt supports modified optimization which is not
+	 * supported by xsave.
+	 *
+	 * If none of xsaves and xsaveopt is enabled, use xsave.
+	 */
+	alternative_input_2(
+		"1:"XSAVE,
+		XSAVEOPT,
+		X86_FEATURE_XSAVEOPT,
+		XSAVES,
+		X86_FEATURE_XSAVES,
+		[xstate] "D" (xstate), "a" (lmask), "d" (hmask) :
+		"memory");
+	asm volatile("2:\n\t"
+		     xstate_fault(err)
+		     : "0" (err)
+		     : "memory");
+
+	/* We should never fault when copying to a kernel buffer: */
+	WARN_ON_FPU(err);
+}
+
+/*
+ * Restore processor xstate from xsave area.
+ */
+static inline void copy_kernel_to_xregs(struct xregs_state *xstate, u64 mask)
+{
+	u32 lmask = mask;
+	u32 hmask = mask >> 32;
+	int err = 0;
+
+	/*
+	 * Use xrstors to restore context if it is enabled. xrstors supports
+	 * compacted format of xsave area which is not supported by xrstor.
+	 */
+	alternative_input(
+		"1: " XRSTOR,
+		XRSTORS,
+		X86_FEATURE_XSAVES,
+		"D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask)
+		: "memory");
+
+	asm volatile("2:\n"
+		     xstate_fault(err)
+		     : "0" (err)
+		     : "memory");
+
+	/* We should never fault when copying from a kernel buffer: */
+	WARN_ON_FPU(err);
+}
+
+/*
+ * Save xstate to user space xsave area.
+ *
+ * We don't use modified optimization because xrstor/xrstors might track
+ * a different application.
+ *
+ * We don't use compacted format xsave area for
+ * backward compatibility for old applications which don't understand
+ * compacted format of xsave area.
+ */
+static inline int copy_xregs_to_user(struct xregs_state __user *buf)
+{
+	int err;
+
+	/*
+	 * Clear the xsave header first, so that reserved fields are
+	 * initialized to zero.
+	 */
+	err = __clear_user(&buf->header, sizeof(buf->header));
+	if (unlikely(err))
+		return -EFAULT;
+
+	__asm__ __volatile__(ASM_STAC "\n"
+			     "1:"XSAVE"\n"
+			     "2: " ASM_CLAC "\n"
+			     xstate_fault(err)
+			     : "D" (buf), "a" (-1), "d" (-1), "0" (err)
+			     : "memory");
+	return err;
+}
+
+/*
+ * Restore xstate from user space xsave area.
+ */
+static inline int copy_user_to_xregs(struct xregs_state __user *buf, u64 mask)
+{
+	struct xregs_state *xstate = ((__force struct xregs_state *)buf);
+	u32 lmask = mask;
+	u32 hmask = mask >> 32;
+	int err = 0;
+
+	__asm__ __volatile__(ASM_STAC "\n"
+			     "1:"XRSTOR"\n"
+			     "2: " ASM_CLAC "\n"
+			     xstate_fault(err)
+			     : "D" (xstate), "a" (lmask), "d" (hmask), "0" (err)
+			     : "memory");	/* memory required? */
+	return err;
+}
+
+/*
+ * These must be called with preempt disabled. Returns
+ * 'true' if the FPU state is still intact and we can
+ * keep registers active.
+ *
+ * The legacy FNSAVE instruction cleared all FPU state
+ * unconditionally, so registers are essentially destroyed.
+ * Modern FPU state can be kept in registers, if there are
+ * no pending FP exceptions.
+ */
+static inline int copy_fpregs_to_fpstate(struct fpu *fpu)
+{
+	if (likely(use_xsave())) {
+		copy_xregs_to_kernel(&fpu->state.xsave);
+		return 1;
+	}
+
+	if (likely(use_fxsr())) {
+		copy_fxregs_to_kernel(fpu);
+		return 1;
+	}
+
+	/*
+	 * Legacy FPU register saving, FNSAVE always clears FPU registers,
+	 * so we have to mark them inactive:
+	 */
+	asm volatile("fnsave %[fp]; fwait" : [fp] "=m" (fpu->state.fsave));
+
+	return 0;
+}
+
+static inline void __copy_kernel_to_fpregs(union fpregs_state *fpstate)
+{
+	if (use_xsave()) {
+		copy_kernel_to_xregs(&fpstate->xsave, -1);
+	} else {
+		if (use_fxsr())
+			copy_kernel_to_fxregs(&fpstate->fxsave);
+		else
+			copy_kernel_to_fregs(&fpstate->fsave);
+	}
+}
+
+static inline void copy_kernel_to_fpregs(union fpregs_state *fpstate)
+{
+	/*
+	 * AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception is
+	 * pending. Clear the x87 state here by setting it to fixed values.
+	 * "m" is a random variable that should be in L1.
+	 */
+	if (unlikely(static_cpu_has_bug_safe(X86_BUG_FXSAVE_LEAK))) {
+		asm volatile(
+			"fnclex\n\t"
+			"emms\n\t"
+			"fildl %P[addr]"	/* set F?P to defined value */
+			: : [addr] "m" (fpstate));
+	}
+
+	__copy_kernel_to_fpregs(fpstate);
+}
+
+extern int copy_fpstate_to_sigframe(void __user *buf, void __user *fp, int size);
+
+/*
+ * FPU context switch related helper methods:
+ */
+
+DECLARE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx);
+
+/*
+ * Must be run with preemption disabled: this clears the fpu_fpregs_owner_ctx,
+ * on this CPU.
+ *
+ * This will disable any lazy FPU state restore of the current FPU state,
+ * but if the current thread owns the FPU, it will still be saved by.
+ */
+static inline void __cpu_disable_lazy_restore(unsigned int cpu)
+{
+	per_cpu(fpu_fpregs_owner_ctx, cpu) = NULL;
+}
+
+static inline int fpu_want_lazy_restore(struct fpu *fpu, unsigned int cpu)
+{
+	return fpu == this_cpu_read_stable(fpu_fpregs_owner_ctx) && cpu == fpu->last_cpu;
+}
+
+
+/*
+ * Wrap lazy FPU TS handling in a 'hw fpregs activation/deactivation'
+ * idiom, which is then paired with the sw-flag (fpregs_active) later on:
+ */
+
+static inline void __fpregs_activate_hw(void)
+{
+	if (!use_eager_fpu())
+		clts();
+}
+
+static inline void __fpregs_deactivate_hw(void)
+{
+	if (!use_eager_fpu())
+		stts();
+}
+
+/* Must be paired with an 'stts' (fpregs_deactivate_hw()) after! */
+static inline void __fpregs_deactivate(struct fpu *fpu)
+{
+	WARN_ON_FPU(!fpu->fpregs_active);
+
+	fpu->fpregs_active = 0;
+	this_cpu_write(fpu_fpregs_owner_ctx, NULL);
+}
+
+/* Must be paired with a 'clts' (fpregs_activate_hw()) before! */
+static inline void __fpregs_activate(struct fpu *fpu)
+{
+	WARN_ON_FPU(fpu->fpregs_active);
+
+	fpu->fpregs_active = 1;
+	this_cpu_write(fpu_fpregs_owner_ctx, fpu);
+}
+
+/*
+ * The question "does this thread have fpu access?"
+ * is slightly racy, since preemption could come in
+ * and revoke it immediately after the test.
+ *
+ * However, even in that very unlikely scenario,
+ * we can just assume we have FPU access - typically
+ * to save the FP state - we'll just take a #NM
+ * fault and get the FPU access back.
+ */
+static inline int fpregs_active(void)
+{
+	return current->thread.fpu.fpregs_active;
+}
+
+/*
+ * Encapsulate the CR0.TS handling together with the
+ * software flag.
+ *
+ * These generally need preemption protection to work,
+ * do try to avoid using these on their own.
+ */
+static inline void fpregs_activate(struct fpu *fpu)
+{
+	__fpregs_activate_hw();
+	__fpregs_activate(fpu);
+}
+
+static inline void fpregs_deactivate(struct fpu *fpu)
+{
+	__fpregs_deactivate(fpu);
+	__fpregs_deactivate_hw();
+}
+
+/*
+ * FPU state switching for scheduling.
+ *
+ * This is a two-stage process:
+ *
+ *  - switch_fpu_prepare() saves the old state and
+ *    sets the new state of the CR0.TS bit. This is
+ *    done within the context of the old process.
+ *
+ *  - switch_fpu_finish() restores the new state as
+ *    necessary.
+ */
+typedef struct { int preload; } fpu_switch_t;
+
+static inline fpu_switch_t
+switch_fpu_prepare(struct fpu *old_fpu, struct fpu *new_fpu, int cpu)
+{
+	fpu_switch_t fpu;
+
+	/*
+	 * If the task has used the math, pre-load the FPU on xsave processors
+	 * or if the past 5 consecutive context-switches used math.
+	 */
+	fpu.preload = new_fpu->fpstate_active &&
+		      (use_eager_fpu() || new_fpu->counter > 5);
+
+	if (old_fpu->fpregs_active) {
+		if (!copy_fpregs_to_fpstate(old_fpu))
+			old_fpu->last_cpu = -1;
+		else
+			old_fpu->last_cpu = cpu;
+
+		/* But leave fpu_fpregs_owner_ctx! */
+		old_fpu->fpregs_active = 0;
+
+		/* Don't change CR0.TS if we just switch! */
+		if (fpu.preload) {
+			new_fpu->counter++;
+			__fpregs_activate(new_fpu);
+			prefetch(&new_fpu->state);
+		} else {
+			__fpregs_deactivate_hw();
+		}
+	} else {
+		old_fpu->counter = 0;
+		old_fpu->last_cpu = -1;
+		if (fpu.preload) {
+			new_fpu->counter++;
+			if (fpu_want_lazy_restore(new_fpu, cpu))
+				fpu.preload = 0;
+			else
+				prefetch(&new_fpu->state);
+			fpregs_activate(new_fpu);
+		}
+	}
+	return fpu;
+}
+
+/*
+ * Misc helper functions:
+ */
+
+/*
+ * By the time this gets called, we've already cleared CR0.TS and
+ * given the process the FPU if we are going to preload the FPU
+ * state - all we need to do is to conditionally restore the register
+ * state itself.
+ */
+static inline void switch_fpu_finish(struct fpu *new_fpu, fpu_switch_t fpu_switch)
+{
+	if (fpu_switch.preload)
+		copy_kernel_to_fpregs(&new_fpu->state);
+}
+
+/*
+ * Needs to be preemption-safe.
+ *
+ * NOTE! user_fpu_begin() must be used only immediately before restoring
+ * the save state. It does not do any saving/restoring on its own. In
+ * lazy FPU mode, it is just an optimization to avoid a #NM exception,
+ * the task can lose the FPU right after preempt_enable().
+ */
+static inline void user_fpu_begin(void)
+{
+	struct fpu *fpu = &current->thread.fpu;
+
+	preempt_disable();
+	if (!fpregs_active())
+		fpregs_activate(fpu);
+	preempt_enable();
+}
+
+/*
+ * MXCSR and XCR definitions:
+ */
+
+extern unsigned int mxcsr_feature_mask;
+
+#define XCR_XFEATURE_ENABLED_MASK	0x00000000
+
+static inline u64 xgetbv(u32 index)
+{
+	u32 eax, edx;
+
+	asm volatile(".byte 0x0f,0x01,0xd0" /* xgetbv */
+		     : "=a" (eax), "=d" (edx)
+		     : "c" (index));
+	return eax + ((u64)edx << 32);
+}
+
+static inline void xsetbv(u32 index, u64 value)
+{
+	u32 eax = value;
+	u32 edx = value >> 32;
+
+	asm volatile(".byte 0x0f,0x01,0xd1" /* xsetbv */
+		     : : "a" (eax), "d" (edx), "c" (index));
+}
+
+#endif /* _ASM_X86_FPU_INTERNAL_H */
diff --git a/arch/x86/include/asm/fpu/regset.h b/arch/x86/include/asm/fpu/regset.h
new file mode 100644
index 000000000000..39d3107ac6c7
--- /dev/null
+++ b/arch/x86/include/asm/fpu/regset.h
@@ -0,0 +1,21 @@
+/*
+ * FPU regset handling methods:
+ */
+#ifndef _ASM_X86_FPU_REGSET_H
+#define _ASM_X86_FPU_REGSET_H
+
+#include <linux/regset.h>
+
+extern user_regset_active_fn regset_fpregs_active, regset_xregset_fpregs_active;
+extern user_regset_get_fn fpregs_get, xfpregs_get, fpregs_soft_get,
+				xstateregs_get;
+extern user_regset_set_fn fpregs_set, xfpregs_set, fpregs_soft_set,
+				 xstateregs_set;
+
+/*
+ * xstateregs_active == regset_fpregs_active. Please refer to the comment
+ * at the definition of regset_fpregs_active.
+ */
+#define xstateregs_active	regset_fpregs_active
+
+#endif /* _ASM_X86_FPU_REGSET_H */
diff --git a/arch/x86/include/asm/fpu/signal.h b/arch/x86/include/asm/fpu/signal.h
new file mode 100644
index 000000000000..7358e9d61f1e
--- /dev/null
+++ b/arch/x86/include/asm/fpu/signal.h
@@ -0,0 +1,33 @@
+/*
+ * x86 FPU signal frame handling methods:
+ */
+#ifndef _ASM_X86_FPU_SIGNAL_H
+#define _ASM_X86_FPU_SIGNAL_H
+
+#ifdef CONFIG_X86_64
+# include <asm/sigcontext32.h>
+# include <asm/user32.h>
+struct ksignal;
+int ia32_setup_rt_frame(int sig, struct ksignal *ksig,
+			compat_sigset_t *set, struct pt_regs *regs);
+int ia32_setup_frame(int sig, struct ksignal *ksig,
+		     compat_sigset_t *set, struct pt_regs *regs);
+#else
+# define user_i387_ia32_struct	user_i387_struct
+# define user32_fxsr_struct	user_fxsr_struct
+# define ia32_setup_frame	__setup_frame
+# define ia32_setup_rt_frame	__setup_rt_frame
+#endif
+
+extern void convert_from_fxsr(struct user_i387_ia32_struct *env,
+			      struct task_struct *tsk);
+extern void convert_to_fxsr(struct task_struct *tsk,
+			    const struct user_i387_ia32_struct *env);
+
+unsigned long
+fpu__alloc_mathframe(unsigned long sp, int ia32_frame,
+		     unsigned long *buf_fx, unsigned long *size);
+
+extern void fpu__init_prepare_fx_sw_frame(void);
+
+#endif /* _ASM_X86_FPU_SIGNAL_H */
diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h
new file mode 100644
index 000000000000..0637826292de
--- /dev/null
+++ b/arch/x86/include/asm/fpu/types.h
@@ -0,0 +1,293 @@
+/*
+ * FPU data structures:
+ */
+#ifndef _ASM_X86_FPU_H
+#define _ASM_X86_FPU_H
+
+/*
+ * The legacy x87 FPU state format, as saved by FSAVE and
+ * restored by the FRSTOR instructions:
+ */
+struct fregs_state {
+	u32			cwd;	/* FPU Control Word		*/
+	u32			swd;	/* FPU Status Word		*/
+	u32			twd;	/* FPU Tag Word			*/
+	u32			fip;	/* FPU IP Offset		*/
+	u32			fcs;	/* FPU IP Selector		*/
+	u32			foo;	/* FPU Operand Pointer Offset	*/
+	u32			fos;	/* FPU Operand Pointer Selector	*/
+
+	/* 8*10 bytes for each FP-reg = 80 bytes:			*/
+	u32			st_space[20];
+
+	/* Software status information [not touched by FSAVE]:		*/
+	u32			status;
+};
+
+/*
+ * The legacy fx SSE/MMX FPU state format, as saved by FXSAVE and
+ * restored by the FXRSTOR instructions. It's similar to the FSAVE
+ * format, but differs in some areas, plus has extensions at
+ * the end for the XMM registers.
+ */
+struct fxregs_state {
+	u16			cwd; /* Control Word			*/
+	u16			swd; /* Status Word			*/
+	u16			twd; /* Tag Word			*/
+	u16			fop; /* Last Instruction Opcode		*/
+	union {
+		struct {
+			u64	rip; /* Instruction Pointer		*/
+			u64	rdp; /* Data Pointer			*/
+		};
+		struct {
+			u32	fip; /* FPU IP Offset			*/
+			u32	fcs; /* FPU IP Selector			*/
+			u32	foo; /* FPU Operand Offset		*/
+			u32	fos; /* FPU Operand Selector		*/
+		};
+	};
+	u32			mxcsr;		/* MXCSR Register State */
+	u32			mxcsr_mask;	/* MXCSR Mask		*/
+
+	/* 8*16 bytes for each FP-reg = 128 bytes:			*/
+	u32			st_space[32];
+
+	/* 16*16 bytes for each XMM-reg = 256 bytes:			*/
+	u32			xmm_space[64];
+
+	u32			padding[12];
+
+	union {
+		u32		padding1[12];
+		u32		sw_reserved[12];
+	};
+
+} __attribute__((aligned(16)));
+
+/* Default value for fxregs_state.mxcsr: */
+#define MXCSR_DEFAULT		0x1f80
+
+/*
+ * Software based FPU emulation state. This is arbitrary really,
+ * it matches the x87 format to make it easier to understand:
+ */
+struct swregs_state {
+	u32			cwd;
+	u32			swd;
+	u32			twd;
+	u32			fip;
+	u32			fcs;
+	u32			foo;
+	u32			fos;
+	/* 8*10 bytes for each FP-reg = 80 bytes: */
+	u32			st_space[20];
+	u8			ftop;
+	u8			changed;
+	u8			lookahead;
+	u8			no_update;
+	u8			rm;
+	u8			alimit;
+	struct math_emu_info	*info;
+	u32			entry_eip;
+};
+
+/*
+ * List of XSAVE features Linux knows about:
+ */
+enum xfeature_bit {
+	XSTATE_BIT_FP,
+	XSTATE_BIT_SSE,
+	XSTATE_BIT_YMM,
+	XSTATE_BIT_BNDREGS,
+	XSTATE_BIT_BNDCSR,
+	XSTATE_BIT_OPMASK,
+	XSTATE_BIT_ZMM_Hi256,
+	XSTATE_BIT_Hi16_ZMM,
+
+	XFEATURES_NR_MAX,
+};
+
+#define XSTATE_FP		(1 << XSTATE_BIT_FP)
+#define XSTATE_SSE		(1 << XSTATE_BIT_SSE)
+#define XSTATE_YMM		(1 << XSTATE_BIT_YMM)
+#define XSTATE_BNDREGS		(1 << XSTATE_BIT_BNDREGS)
+#define XSTATE_BNDCSR		(1 << XSTATE_BIT_BNDCSR)
+#define XSTATE_OPMASK		(1 << XSTATE_BIT_OPMASK)
+#define XSTATE_ZMM_Hi256	(1 << XSTATE_BIT_ZMM_Hi256)
+#define XSTATE_Hi16_ZMM		(1 << XSTATE_BIT_Hi16_ZMM)
+
+#define XSTATE_FPSSE		(XSTATE_FP | XSTATE_SSE)
+#define XSTATE_AVX512		(XSTATE_OPMASK | XSTATE_ZMM_Hi256 | XSTATE_Hi16_ZMM)
+
+/*
+ * There are 16x 256-bit AVX registers named YMM0-YMM15.
+ * The low 128 bits are aliased to the 16 SSE registers (XMM0-XMM15)
+ * and are stored in 'struct fxregs_state::xmm_space[]'.
+ *
+ * The high 128 bits are stored here:
+ *    16x 128 bits == 256 bytes.
+ */
+struct ymmh_struct {
+	u8				ymmh_space[256];
+};
+
+/* We don't support LWP yet: */
+struct lwp_struct {
+	u8				reserved[128];
+};
+
+/* Intel MPX support: */
+struct bndreg {
+	u64				lower_bound;
+	u64				upper_bound;
+} __packed;
+
+struct bndcsr {
+	u64				bndcfgu;
+	u64				bndstatus;
+} __packed;
+
+struct mpx_struct {
+	struct bndreg			bndreg[4];
+	struct bndcsr			bndcsr;
+};
+
+struct xstate_header {
+	u64				xfeatures;
+	u64				xcomp_bv;
+	u64				reserved[6];
+} __attribute__((packed));
+
+/* New processor state extensions should be added here: */
+#define XSTATE_RESERVE			(sizeof(struct ymmh_struct) + \
+					 sizeof(struct lwp_struct)  + \
+					 sizeof(struct mpx_struct)  )
+/*
+ * This is our most modern FPU state format, as saved by the XSAVE
+ * and restored by the XRSTOR instructions.
+ *
+ * It consists of a legacy fxregs portion, an xstate header and
+ * subsequent fixed size areas as defined by the xstate header.
+ * Not all CPUs support all the extensions.
+ */
+struct xregs_state {
+	struct fxregs_state		i387;
+	struct xstate_header		header;
+	u8				__reserved[XSTATE_RESERVE];
+} __attribute__ ((packed, aligned (64)));
+
+/*
+ * This is a union of all the possible FPU state formats
+ * put together, so that we can pick the right one runtime.
+ *
+ * The size of the structure is determined by the largest
+ * member - which is the xsave area:
+ */
+union fpregs_state {
+	struct fregs_state		fsave;
+	struct fxregs_state		fxsave;
+	struct swregs_state		soft;
+	struct xregs_state		xsave;
+};
+
+/*
+ * Highest level per task FPU state data structure that
+ * contains the FPU register state plus various FPU
+ * state fields:
+ */
+struct fpu {
+	/*
+	 * @state:
+	 *
+	 * In-memory copy of all FPU registers that we save/restore
+	 * over context switches. If the task is using the FPU then
+	 * the registers in the FPU are more recent than this state
+	 * copy. If the task context-switches away then they get
+	 * saved here and represent the FPU state.
+	 *
+	 * After context switches there may be a (short) time period
+	 * during which the in-FPU hardware registers are unchanged
+	 * and still perfectly match this state, if the tasks
+	 * scheduled afterwards are not using the FPU.
+	 *
+	 * This is the 'lazy restore' window of optimization, which
+	 * we track though 'fpu_fpregs_owner_ctx' and 'fpu->last_cpu'.
+	 *
+	 * We detect whether a subsequent task uses the FPU via setting
+	 * CR0::TS to 1, which causes any FPU use to raise a #NM fault.
+	 *
+	 * During this window, if the task gets scheduled again, we
+	 * might be able to skip having to do a restore from this
+	 * memory buffer to the hardware registers - at the cost of
+	 * incurring the overhead of #NM fault traps.
+	 *
+	 * Note that on modern CPUs that support the XSAVEOPT (or other
+	 * optimized XSAVE instructions), we don't use #NM traps anymore,
+	 * as the hardware can track whether FPU registers need saving
+	 * or not. On such CPUs we activate the non-lazy ('eagerfpu')
+	 * logic, which unconditionally saves/restores all FPU state
+	 * across context switches. (if FPU state exists.)
+	 */
+	union fpregs_state		state;
+
+	/*
+	 * @last_cpu:
+	 *
+	 * Records the last CPU on which this context was loaded into
+	 * FPU registers. (In the lazy-restore case we might be
+	 * able to reuse FPU registers across multiple context switches
+	 * this way, if no intermediate task used the FPU.)
+	 *
+	 * A value of -1 is used to indicate that the FPU state in context
+	 * memory is newer than the FPU state in registers, and that the
+	 * FPU state should be reloaded next time the task is run.
+	 */
+	unsigned int			last_cpu;
+
+	/*
+	 * @fpstate_active:
+	 *
+	 * This flag indicates whether this context is active: if the task
+	 * is not running then we can restore from this context, if the task
+	 * is running then we should save into this context.
+	 */
+	unsigned char			fpstate_active;
+
+	/*
+	 * @fpregs_active:
+	 *
+	 * This flag determines whether a given context is actively
+	 * loaded into the FPU's registers and that those registers
+	 * represent the task's current FPU state.
+	 *
+	 * Note the interaction with fpstate_active:
+	 *
+	 *   # task does not use the FPU:
+	 *   fpstate_active == 0
+	 *
+	 *   # task uses the FPU and regs are active:
+	 *   fpstate_active == 1 && fpregs_active == 1
+	 *
+	 *   # the regs are inactive but still match fpstate:
+	 *   fpstate_active == 1 && fpregs_active == 0 && fpregs_owner == fpu
+	 *
+	 * The third state is what we use for the lazy restore optimization
+	 * on lazy-switching CPUs.
+	 */
+	unsigned char			fpregs_active;
+
+	/*
+	 * @counter:
+	 *
+	 * This counter contains the number of consecutive context switches
+	 * during which the FPU stays used. If this is over a threshold, the
+	 * lazy FPU restore logic becomes eager, to save the trap overhead.
+	 * This is an unsigned char so that after 256 iterations the counter
+	 * wraps and the context switch behavior turns lazy again; this is to
+	 * deal with bursty apps that only use the FPU for a short time:
+	 */
+	unsigned char			counter;
+};
+
+#endif /* _ASM_X86_FPU_H */
diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
new file mode 100644
index 000000000000..4656b25bb9a7
--- /dev/null
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -0,0 +1,46 @@
+#ifndef __ASM_X86_XSAVE_H
+#define __ASM_X86_XSAVE_H
+
+#include <linux/types.h>
+#include <asm/processor.h>
+#include <linux/uaccess.h>
+
+/* Bit 63 of XCR0 is reserved for future expansion */
+#define XSTATE_EXTEND_MASK	(~(XSTATE_FPSSE | (1ULL << 63)))
+
+#define XSTATE_CPUID		0x0000000d
+
+#define FXSAVE_SIZE	512
+
+#define XSAVE_HDR_SIZE	    64
+#define XSAVE_HDR_OFFSET    FXSAVE_SIZE
+
+#define XSAVE_YMM_SIZE	    256
+#define XSAVE_YMM_OFFSET    (XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET)
+
+/* Supported features which support lazy state saving */
+#define XSTATE_LAZY	(XSTATE_FP | XSTATE_SSE | XSTATE_YMM		      \
+			| XSTATE_OPMASK | XSTATE_ZMM_Hi256 | XSTATE_Hi16_ZMM)
+
+/* Supported features which require eager state saving */
+#define XSTATE_EAGER	(XSTATE_BNDREGS | XSTATE_BNDCSR)
+
+/* All currently supported features */
+#define XCNTXT_MASK	(XSTATE_LAZY | XSTATE_EAGER)
+
+#ifdef CONFIG_X86_64
+#define REX_PREFIX	"0x48, "
+#else
+#define REX_PREFIX
+#endif
+
+extern unsigned int xstate_size;
+extern u64 xfeatures_mask;
+extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS];
+
+extern void update_regset_xstate_info(unsigned int size, u64 xstate_mask);
+
+void *get_xsave_addr(struct xregs_state *xsave, int xstate);
+const void *get_xsave_field_ptr(int xstate_field);
+
+#endif
diff --git a/arch/x86/include/asm/frame.h b/arch/x86/include/asm/frame.h
index 3b629f47eb65..793179cf8e21 100644
--- a/arch/x86/include/asm/frame.h
+++ b/arch/x86/include/asm/frame.h
@@ -1,20 +1,17 @@
 #ifdef __ASSEMBLY__
 
 #include <asm/asm.h>
-#include <asm/dwarf2.h>
 
 /* The annotation hides the frame from the unwinder and makes it look
    like a ordinary ebp save/restore. This avoids some special cases for
    frame pointer later */
 #ifdef CONFIG_FRAME_POINTER
 	.macro FRAME
-	__ASM_SIZE(push,_cfi)	%__ASM_REG(bp)
-	CFI_REL_OFFSET		__ASM_REG(bp), 0
+	__ASM_SIZE(push,)	%__ASM_REG(bp)
 	__ASM_SIZE(mov)		%__ASM_REG(sp), %__ASM_REG(bp)
 	.endm
 	.macro ENDFRAME
-	__ASM_SIZE(pop,_cfi)	%__ASM_REG(bp)
-	CFI_RESTORE		__ASM_REG(bp)
+	__ASM_SIZE(pop,)	%__ASM_REG(bp)
 	.endm
 #else
 	.macro FRAME
diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index 0f5fb6b6567e..7178043b0e1d 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -14,6 +14,7 @@ typedef struct {
 #endif
 #ifdef CONFIG_HAVE_KVM
 	unsigned int kvm_posted_intr_ipis;
+	unsigned int kvm_posted_intr_wakeup_ipis;
 #endif
 	unsigned int x86_platform_ipis;	/* arch dependent */
 	unsigned int apic_perf_irqs;
@@ -33,6 +34,9 @@ typedef struct {
 #ifdef CONFIG_X86_MCE_THRESHOLD
 	unsigned int irq_threshold_count;
 #endif
+#ifdef CONFIG_X86_MCE_AMD
+	unsigned int irq_deferred_error_count;
+#endif
 #if IS_ENABLED(CONFIG_HYPERV) || defined(CONFIG_XEN)
 	unsigned int irq_hv_callback_count;
 #endif
diff --git a/arch/x86/include/asm/hpet.h b/arch/x86/include/asm/hpet.h
index 36f7125945e3..5fa9fb0f8809 100644
--- a/arch/x86/include/asm/hpet.h
+++ b/arch/x86/include/asm/hpet.h
@@ -74,20 +74,16 @@ extern unsigned int hpet_readl(unsigned int a);
 extern void force_hpet_resume(void);
 
 struct irq_data;
+struct hpet_dev;
+struct irq_domain;
+
 extern void hpet_msi_unmask(struct irq_data *data);
 extern void hpet_msi_mask(struct irq_data *data);
-struct hpet_dev;
 extern void hpet_msi_write(struct hpet_dev *hdev, struct msi_msg *msg);
 extern void hpet_msi_read(struct hpet_dev *hdev, struct msi_msg *msg);
-
-#ifdef CONFIG_PCI_MSI
-extern int default_setup_hpet_msi(unsigned int irq, unsigned int id);
-#else
-static inline int default_setup_hpet_msi(unsigned int irq, unsigned int id)
-{
-	return -EINVAL;
-}
-#endif
+extern struct irq_domain *hpet_create_irq_domain(int hpet_id);
+extern int hpet_assign_irq(struct irq_domain *domain,
+			   struct hpet_dev *dev, int dev_num);
 
 #ifdef CONFIG_HPET_EMULATE_RTC
 
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index e9571ddabc4f..6615032e19c8 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -29,6 +29,7 @@
 extern asmlinkage void apic_timer_interrupt(void);
 extern asmlinkage void x86_platform_ipi(void);
 extern asmlinkage void kvm_posted_intr_ipi(void);
+extern asmlinkage void kvm_posted_intr_wakeup_ipi(void);
 extern asmlinkage void error_interrupt(void);
 extern asmlinkage void irq_work_interrupt(void);
 
@@ -36,43 +37,10 @@ extern asmlinkage void spurious_interrupt(void);
 extern asmlinkage void thermal_interrupt(void);
 extern asmlinkage void reschedule_interrupt(void);
 
-extern asmlinkage void invalidate_interrupt(void);
-extern asmlinkage void invalidate_interrupt0(void);
-extern asmlinkage void invalidate_interrupt1(void);
-extern asmlinkage void invalidate_interrupt2(void);
-extern asmlinkage void invalidate_interrupt3(void);
-extern asmlinkage void invalidate_interrupt4(void);
-extern asmlinkage void invalidate_interrupt5(void);
-extern asmlinkage void invalidate_interrupt6(void);
-extern asmlinkage void invalidate_interrupt7(void);
-extern asmlinkage void invalidate_interrupt8(void);
-extern asmlinkage void invalidate_interrupt9(void);
-extern asmlinkage void invalidate_interrupt10(void);
-extern asmlinkage void invalidate_interrupt11(void);
-extern asmlinkage void invalidate_interrupt12(void);
-extern asmlinkage void invalidate_interrupt13(void);
-extern asmlinkage void invalidate_interrupt14(void);
-extern asmlinkage void invalidate_interrupt15(void);
-extern asmlinkage void invalidate_interrupt16(void);
-extern asmlinkage void invalidate_interrupt17(void);
-extern asmlinkage void invalidate_interrupt18(void);
-extern asmlinkage void invalidate_interrupt19(void);
-extern asmlinkage void invalidate_interrupt20(void);
-extern asmlinkage void invalidate_interrupt21(void);
-extern asmlinkage void invalidate_interrupt22(void);
-extern asmlinkage void invalidate_interrupt23(void);
-extern asmlinkage void invalidate_interrupt24(void);
-extern asmlinkage void invalidate_interrupt25(void);
-extern asmlinkage void invalidate_interrupt26(void);
-extern asmlinkage void invalidate_interrupt27(void);
-extern asmlinkage void invalidate_interrupt28(void);
-extern asmlinkage void invalidate_interrupt29(void);
-extern asmlinkage void invalidate_interrupt30(void);
-extern asmlinkage void invalidate_interrupt31(void);
-
 extern asmlinkage void irq_move_cleanup_interrupt(void);
 extern asmlinkage void reboot_interrupt(void);
 extern asmlinkage void threshold_interrupt(void);
+extern asmlinkage void deferred_error_interrupt(void);
 
 extern asmlinkage void call_function_interrupt(void);
 extern asmlinkage void call_function_single_interrupt(void);
@@ -87,60 +55,93 @@ extern void trace_spurious_interrupt(void);
 extern void trace_thermal_interrupt(void);
 extern void trace_reschedule_interrupt(void);
 extern void trace_threshold_interrupt(void);
+extern void trace_deferred_error_interrupt(void);
 extern void trace_call_function_interrupt(void);
 extern void trace_call_function_single_interrupt(void);
 #define trace_irq_move_cleanup_interrupt  irq_move_cleanup_interrupt
 #define trace_reboot_interrupt  reboot_interrupt
 #define trace_kvm_posted_intr_ipi kvm_posted_intr_ipi
+#define trace_kvm_posted_intr_wakeup_ipi kvm_posted_intr_wakeup_ipi
 #endif /* CONFIG_TRACING */
 
-#ifdef CONFIG_IRQ_REMAP
-/* Intel specific interrupt remapping information */
-struct irq_2_iommu {
-	struct intel_iommu *iommu;
-	u16 irte_index;
-	u16 sub_handle;
-	u8  irte_mask;
-};
-
-/* AMD specific interrupt remapping information */
-struct irq_2_irte {
-	u16 devid; /* Device ID for IRTE table */
-	u16 index; /* Index into IRTE table*/
-};
-#endif	/* CONFIG_IRQ_REMAP */
-
 #ifdef	CONFIG_X86_LOCAL_APIC
 struct irq_data;
+struct pci_dev;
+struct msi_desc;
+
+enum irq_alloc_type {
+	X86_IRQ_ALLOC_TYPE_IOAPIC = 1,
+	X86_IRQ_ALLOC_TYPE_HPET,
+	X86_IRQ_ALLOC_TYPE_MSI,
+	X86_IRQ_ALLOC_TYPE_MSIX,
+	X86_IRQ_ALLOC_TYPE_DMAR,
+	X86_IRQ_ALLOC_TYPE_UV,
+};
 
-struct irq_cfg {
-	cpumask_var_t		domain;
-	cpumask_var_t		old_domain;
-	u8			vector;
-	u8			move_in_progress : 1;
-#ifdef CONFIG_IRQ_REMAP
-	u8			remapped : 1;
+struct irq_alloc_info {
+	enum irq_alloc_type	type;
+	u32			flags;
+	const struct cpumask	*mask;	/* CPU mask for vector allocation */
 	union {
-		struct irq_2_iommu irq_2_iommu;
-		struct irq_2_irte  irq_2_irte;
-	};
+		int		unused;
+#ifdef	CONFIG_HPET_TIMER
+		struct {
+			int		hpet_id;
+			int		hpet_index;
+			void		*hpet_data;
+		};
 #endif
-	union {
-#ifdef CONFIG_X86_IO_APIC
+#ifdef	CONFIG_PCI_MSI
 		struct {
-			struct list_head	irq_2_pin;
+			struct pci_dev	*msi_dev;
+			irq_hw_number_t	msi_hwirq;
+		};
+#endif
+#ifdef	CONFIG_X86_IO_APIC
+		struct {
+			int		ioapic_id;
+			int		ioapic_pin;
+			int		ioapic_node;
+			u32		ioapic_trigger : 1;
+			u32		ioapic_polarity : 1;
+			u32		ioapic_valid : 1;
+			struct IO_APIC_route_entry *ioapic_entry;
+		};
+#endif
+#ifdef	CONFIG_DMAR_TABLE
+		struct {
+			int		dmar_id;
+			void		*dmar_data;
+		};
+#endif
+#ifdef	CONFIG_HT_IRQ
+		struct {
+			int		ht_pos;
+			int		ht_idx;
+			struct pci_dev	*ht_dev;
+			void		*ht_update;
+		};
+#endif
+#ifdef	CONFIG_X86_UV
+		struct {
+			int		uv_limit;
+			int		uv_blade;
+			unsigned long	uv_offset;
+			char		*uv_name;
 		};
 #endif
 	};
 };
 
+struct irq_cfg {
+	unsigned int		dest_apicid;
+	u8			vector;
+};
+
 extern struct irq_cfg *irq_cfg(unsigned int irq);
 extern struct irq_cfg *irqd_cfg(struct irq_data *irq_data);
-extern struct irq_cfg *alloc_irq_and_cfg_at(unsigned int at, int node);
 extern void lock_vector_lock(void);
 extern void unlock_vector_lock(void);
-extern int assign_irq_vector(int, struct irq_cfg *, const struct cpumask *);
-extern void clear_irq_vector(int irq, struct irq_cfg *cfg);
 extern void setup_vector_irq(int cpu);
 #ifdef CONFIG_SMP
 extern void send_cleanup_vector(struct irq_cfg *);
@@ -150,10 +151,7 @@ static inline void send_cleanup_vector(struct irq_cfg *c) { }
 static inline void irq_complete_move(struct irq_cfg *c) { }
 #endif
 
-extern int apic_retrigger_irq(struct irq_data *data);
 extern void apic_ack_edge(struct irq_data *data);
-extern int apic_set_affinity(struct irq_data *data, const struct cpumask *mask,
-			     unsigned int *dest_id);
 #else	/*  CONFIG_X86_LOCAL_APIC */
 static inline void lock_vector_lock(void) {}
 static inline void unlock_vector_lock(void) {}
@@ -163,8 +161,7 @@ static inline void unlock_vector_lock(void) {}
 extern atomic_t irq_err_count;
 extern atomic_t irq_mis_count;
 
-/* EISA */
-extern void eisa_set_level_irq(unsigned int irq);
+extern void elcr_set_level_irq(unsigned int irq);
 
 /* SMP */
 extern __visible void smp_apic_timer_interrupt(struct pt_regs *);
@@ -178,7 +175,6 @@ extern asmlinkage void smp_irq_move_cleanup_interrupt(void);
 extern __visible void smp_reschedule_interrupt(struct pt_regs *);
 extern __visible void smp_call_function_interrupt(struct pt_regs *);
 extern __visible void smp_call_function_single_interrupt(struct pt_regs *);
-extern __visible void smp_invalidate_interrupt(struct pt_regs *);
 #endif
 
 extern char irq_entries_start[];
diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h
deleted file mode 100644
index 6eb6fcb83f63..000000000000
--- a/arch/x86/include/asm/i387.h
+++ /dev/null
@@ -1,108 +0,0 @@
-/*
- * Copyright (C) 1994 Linus Torvalds
- *
- * Pentium III FXSR, SSE support
- * General FPU state handling cleanups
- *	Gareth Hughes <gareth@valinux.com>, May 2000
- * x86-64 work by Andi Kleen 2002
- */
-
-#ifndef _ASM_X86_I387_H
-#define _ASM_X86_I387_H
-
-#ifndef __ASSEMBLY__
-
-#include <linux/sched.h>
-#include <linux/hardirq.h>
-
-struct pt_regs;
-struct user_i387_struct;
-
-extern int init_fpu(struct task_struct *child);
-extern void fpu_finit(struct fpu *fpu);
-extern int dump_fpu(struct pt_regs *, struct user_i387_struct *);
-extern void math_state_restore(void);
-
-extern bool irq_fpu_usable(void);
-
-/*
- * Careful: __kernel_fpu_begin/end() must be called with preempt disabled
- * and they don't touch the preempt state on their own.
- * If you enable preemption after __kernel_fpu_begin(), preempt notifier
- * should call the __kernel_fpu_end() to prevent the kernel/user FPU
- * state from getting corrupted. KVM for example uses this model.
- *
- * All other cases use kernel_fpu_begin/end() which disable preemption
- * during kernel FPU usage.
- */
-extern void __kernel_fpu_begin(void);
-extern void __kernel_fpu_end(void);
-
-static inline void kernel_fpu_begin(void)
-{
-	preempt_disable();
-	WARN_ON_ONCE(!irq_fpu_usable());
-	__kernel_fpu_begin();
-}
-
-static inline void kernel_fpu_end(void)
-{
-	__kernel_fpu_end();
-	preempt_enable();
-}
-
-/* Must be called with preempt disabled */
-extern void kernel_fpu_disable(void);
-extern void kernel_fpu_enable(void);
-
-/*
- * Some instructions like VIA's padlock instructions generate a spurious
- * DNA fault but don't modify SSE registers. And these instructions
- * get used from interrupt context as well. To prevent these kernel instructions
- * in interrupt context interacting wrongly with other user/kernel fpu usage, we
- * should use them only in the context of irq_ts_save/restore()
- */
-static inline int irq_ts_save(void)
-{
-	/*
-	 * If in process context and not atomic, we can take a spurious DNA fault.
-	 * Otherwise, doing clts() in process context requires disabling preemption
-	 * or some heavy lifting like kernel_fpu_begin()
-	 */
-	if (!in_atomic())
-		return 0;
-
-	if (read_cr0() & X86_CR0_TS) {
-		clts();
-		return 1;
-	}
-
-	return 0;
-}
-
-static inline void irq_ts_restore(int TS_state)
-{
-	if (TS_state)
-		stts();
-}
-
-/*
- * The question "does this thread have fpu access?"
- * is slightly racy, since preemption could come in
- * and revoke it immediately after the test.
- *
- * However, even in that very unlikely scenario,
- * we can just assume we have FPU access - typically
- * to save the FP state - we'll just take a #NM
- * fault and get the FPU access back.
- */
-static inline int user_has_fpu(void)
-{
-	return current->thread.fpu.has_fpu;
-}
-
-extern void unlazy_fpu(struct task_struct *tsk);
-
-#endif /* __ASSEMBLY__ */
-
-#endif /* _ASM_X86_I387_H */
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index 34a5b93704d3..83ec9b1d77cc 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -35,11 +35,13 @@
   */
 
 #define ARCH_HAS_IOREMAP_WC
+#define ARCH_HAS_IOREMAP_WT
 
 #include <linux/string.h>
 #include <linux/compiler.h>
 #include <asm/page.h>
 #include <asm/early_ioremap.h>
+#include <asm/pgtable_types.h>
 
 #define build_mmio_read(name, size, type, reg, barrier) \
 static inline type name(const volatile void __iomem *addr) \
@@ -177,6 +179,7 @@ static inline unsigned int isa_virt_to_bus(volatile void *address)
  * look at pci_iomap().
  */
 extern void __iomem *ioremap_nocache(resource_size_t offset, unsigned long size);
+extern void __iomem *ioremap_uc(resource_size_t offset, unsigned long size);
 extern void __iomem *ioremap_cache(resource_size_t offset, unsigned long size);
 extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size,
 				unsigned long prot_val);
@@ -197,8 +200,6 @@ extern void set_iounmap_nonlazy(void);
 
 #include <asm-generic/iomap.h>
 
-#include <linux/vmalloc.h>
-
 /*
  * Convert a virtual cached pointer to an uncached pointer
  */
@@ -320,6 +321,7 @@ extern void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr);
 extern int ioremap_change_attr(unsigned long vaddr, unsigned long size,
 				enum page_cache_mode pcm);
 extern void __iomem *ioremap_wc(resource_size_t offset, unsigned long size);
+extern void __iomem *ioremap_wt(resource_size_t offset, unsigned long size);
 
 extern bool is_early_ioremap_ptep(pte_t *ptep);
 
@@ -338,6 +340,9 @@ extern bool xen_biovec_phys_mergeable(const struct bio_vec *vec1,
 #define IO_SPACE_LIMIT 0xffff
 
 #ifdef CONFIG_MTRR
+extern int __must_check arch_phys_wc_index(int handle);
+#define arch_phys_wc_index arch_phys_wc_index
+
 extern int __must_check arch_phys_wc_add(unsigned long base,
 					 unsigned long size);
 extern void arch_phys_wc_del(int handle);
diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h
index 2f91685fe1cd..6cbf2cfb3f8a 100644
--- a/arch/x86/include/asm/io_apic.h
+++ b/arch/x86/include/asm/io_apic.h
@@ -95,9 +95,22 @@ struct IR_IO_APIC_route_entry {
 		index		: 15;
 } __attribute__ ((packed));
 
-#define IOAPIC_AUTO     -1
-#define IOAPIC_EDGE     0
-#define IOAPIC_LEVEL    1
+struct irq_alloc_info;
+struct ioapic_domain_cfg;
+
+#define IOAPIC_AUTO			-1
+#define IOAPIC_EDGE			0
+#define IOAPIC_LEVEL			1
+
+#define IOAPIC_MASKED			1
+#define IOAPIC_UNMASKED			0
+
+#define IOAPIC_POL_HIGH			0
+#define IOAPIC_POL_LOW			1
+
+#define IOAPIC_DEST_MODE_PHYSICAL	0
+#define IOAPIC_DEST_MODE_LOGICAL	1
+
 #define	IOAPIC_MAP_ALLOC		0x1
 #define	IOAPIC_MAP_CHECK		0x2
 
@@ -110,9 +123,6 @@ extern int nr_ioapics;
 
 extern int mpc_ioapic_id(int ioapic);
 extern unsigned int mpc_ioapic_addr(int ioapic);
-extern struct mp_ioapic_gsi *mp_ioapic_gsi_routing(int ioapic);
-
-#define MP_MAX_IOAPIC_PIN 127
 
 /* # of MP IRQ source entries */
 extern int mp_irq_entries;
@@ -120,9 +130,6 @@ extern int mp_irq_entries;
 /* MP IRQ source entries */
 extern struct mpc_intsrc mp_irqs[MAX_IRQ_SOURCES];
 
-/* Older SiS APIC requires we rewrite the index register */
-extern int sis_apic_bug;
-
 /* 1 if "noapic" boot option passed */
 extern int skip_ioapic_setup;
 
@@ -132,6 +139,8 @@ extern int noioapicquirk;
 /* -1 if "noapic" boot option passed */
 extern int noioapicreroute;
 
+extern u32 gsi_top;
+
 extern unsigned long io_apic_irqs;
 
 #define IO_APIC_IRQ(x) (((x) >= NR_IRQS_LEGACY) || ((1 << (x)) & io_apic_irqs))
@@ -147,13 +156,6 @@ struct irq_cfg;
 extern void ioapic_insert_resources(void);
 extern int arch_early_ioapic_init(void);
 
-extern int native_setup_ioapic_entry(int, struct IO_APIC_route_entry *,
-				     unsigned int, int,
-				     struct io_apic_irq_attr *);
-extern void eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg);
-
-extern void native_eoi_ioapic_pin(int apic, int pin, int vector);
-
 extern int save_ioapic_entries(void);
 extern void mask_ioapic_entries(void);
 extern int restore_ioapic_entries(void);
@@ -161,82 +163,32 @@ extern int restore_ioapic_entries(void);
 extern void setup_ioapic_ids_from_mpc(void);
 extern void setup_ioapic_ids_from_mpc_nocheck(void);
 
-struct io_apic_irq_attr {
-	int ioapic;
-	int ioapic_pin;
-	int trigger;
-	int polarity;
-};
-
-enum ioapic_domain_type {
-	IOAPIC_DOMAIN_INVALID,
-	IOAPIC_DOMAIN_LEGACY,
-	IOAPIC_DOMAIN_STRICT,
-	IOAPIC_DOMAIN_DYNAMIC,
-};
-
-struct device_node;
-struct irq_domain;
-struct irq_domain_ops;
-
-struct ioapic_domain_cfg {
-	enum ioapic_domain_type		type;
-	const struct irq_domain_ops	*ops;
-	struct device_node		*dev;
-};
-
-struct mp_ioapic_gsi{
-	u32 gsi_base;
-	u32 gsi_end;
-};
-extern u32 gsi_top;
-
 extern int mp_find_ioapic(u32 gsi);
 extern int mp_find_ioapic_pin(int ioapic, u32 gsi);
-extern u32 mp_pin_to_gsi(int ioapic, int pin);
-extern int mp_map_gsi_to_irq(u32 gsi, unsigned int flags);
+extern int mp_map_gsi_to_irq(u32 gsi, unsigned int flags,
+			     struct irq_alloc_info *info);
 extern void mp_unmap_irq(int irq);
 extern int mp_register_ioapic(int id, u32 address, u32 gsi_base,
 			      struct ioapic_domain_cfg *cfg);
 extern int mp_unregister_ioapic(u32 gsi_base);
 extern int mp_ioapic_registered(u32 gsi_base);
-extern int mp_irqdomain_map(struct irq_domain *domain, unsigned int virq,
-			    irq_hw_number_t hwirq);
-extern void mp_irqdomain_unmap(struct irq_domain *domain, unsigned int virq);
-extern int mp_set_gsi_attr(u32 gsi, int trigger, int polarity, int node);
-extern void __init pre_init_apic_IRQ0(void);
+
+extern void ioapic_set_alloc_attr(struct irq_alloc_info *info,
+				  int node, int trigger, int polarity);
 
 extern void mp_save_irq(struct mpc_intsrc *m);
 
 extern void disable_ioapic_support(void);
 
-extern void __init native_io_apic_init_mappings(void);
+extern void __init io_apic_init_mappings(void);
 extern unsigned int native_io_apic_read(unsigned int apic, unsigned int reg);
-extern void native_io_apic_write(unsigned int apic, unsigned int reg, unsigned int val);
-extern void native_io_apic_modify(unsigned int apic, unsigned int reg, unsigned int val);
 extern void native_disable_io_apic(void);
-extern void native_io_apic_print_entries(unsigned int apic, unsigned int nr_entries);
-extern void intel_ir_io_apic_print_entries(unsigned int apic, unsigned int nr_entries);
-extern int native_ioapic_set_affinity(struct irq_data *,
-				      const struct cpumask *,
-				      bool);
 
 static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg)
 {
 	return x86_io_apic_ops.read(apic, reg);
 }
 
-static inline void io_apic_write(unsigned int apic, unsigned int reg, unsigned int value)
-{
-	x86_io_apic_ops.write(apic, reg, value);
-}
-static inline void io_apic_modify(unsigned int apic, unsigned int reg, unsigned int value)
-{
-	x86_io_apic_ops.modify(apic, reg, value);
-}
-
-extern void io_apic_eoi(unsigned int apic, unsigned int vector);
-
 extern void setup_IO_APIC(void);
 extern void enable_IO_APIC(void);
 extern void disable_IO_APIC(void);
@@ -253,8 +205,12 @@ static inline int arch_early_ioapic_init(void) { return 0; }
 static inline void print_IO_APICs(void) {}
 #define gsi_top (NR_IRQS_LEGACY)
 static inline int mp_find_ioapic(u32 gsi) { return 0; }
-static inline u32 mp_pin_to_gsi(int ioapic, int pin) { return UINT_MAX; }
-static inline int mp_map_gsi_to_irq(u32 gsi, unsigned int flags) { return gsi; }
+static inline int mp_map_gsi_to_irq(u32 gsi, unsigned int flags,
+				    struct irq_alloc_info *info)
+{
+	return gsi;
+}
+
 static inline void mp_unmap_irq(int irq) { }
 
 static inline int save_ioapic_entries(void)
@@ -268,17 +224,11 @@ static inline int restore_ioapic_entries(void)
 	return -ENOMEM;
 }
 
-static inline void mp_save_irq(struct mpc_intsrc *m) { };
+static inline void mp_save_irq(struct mpc_intsrc *m) { }
 static inline void disable_ioapic_support(void) { }
-#define native_io_apic_init_mappings	NULL
+static inline void io_apic_init_mappings(void) { }
 #define native_io_apic_read		NULL
-#define native_io_apic_write		NULL
-#define native_io_apic_modify		NULL
 #define native_disable_io_apic		NULL
-#define native_io_apic_print_entries	NULL
-#define native_ioapic_set_affinity	NULL
-#define native_setup_ioapic_entry	NULL
-#define native_eoi_ioapic_pin		NULL
 
 static inline void setup_IO_APIC(void) { }
 static inline void enable_IO_APIC(void) { }
diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h
index a80cbb88ea91..8008d06581c7 100644
--- a/arch/x86/include/asm/irq.h
+++ b/arch/x86/include/asm/irq.h
@@ -30,6 +30,10 @@ extern void fixup_irqs(void);
 extern void irq_force_complete_move(int);
 #endif
 
+#ifdef CONFIG_HAVE_KVM
+extern void kvm_set_posted_intr_wakeup_handler(void (*handler)(void));
+#endif
+
 extern void (*x86_platform_ipi_callback)(void);
 extern void native_init_IRQ(void);
 extern bool handle_irq(unsigned irq, struct pt_regs *regs);
diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h
index 6224d316c405..046c7fb1ca43 100644
--- a/arch/x86/include/asm/irq_remapping.h
+++ b/arch/x86/include/asm/irq_remapping.h
@@ -22,84 +22,72 @@
 #ifndef __X86_IRQ_REMAPPING_H
 #define __X86_IRQ_REMAPPING_H
 
+#include <asm/irqdomain.h>
+#include <asm/hw_irq.h>
 #include <asm/io_apic.h>
 
-struct IO_APIC_route_entry;
-struct io_apic_irq_attr;
-struct irq_chip;
 struct msi_msg;
-struct pci_dev;
-struct irq_cfg;
+struct irq_alloc_info;
+
+enum irq_remap_cap {
+	IRQ_POSTING_CAP = 0,
+};
 
 #ifdef CONFIG_IRQ_REMAP
 
+extern bool irq_remapping_cap(enum irq_remap_cap cap);
 extern void set_irq_remapping_broken(void);
 extern int irq_remapping_prepare(void);
 extern int irq_remapping_enable(void);
 extern void irq_remapping_disable(void);
 extern int irq_remapping_reenable(int);
 extern int irq_remap_enable_fault_handling(void);
-extern int setup_ioapic_remapped_entry(int irq,
-				       struct IO_APIC_route_entry *entry,
-				       unsigned int destination,
-				       int vector,
-				       struct io_apic_irq_attr *attr);
-extern void free_remapped_irq(int irq);
-extern void compose_remapped_msi_msg(struct pci_dev *pdev,
-				     unsigned int irq, unsigned int dest,
-				     struct msi_msg *msg, u8 hpet_id);
-extern int setup_hpet_msi_remapped(unsigned int irq, unsigned int id);
 extern void panic_if_irq_remap(const char *msg);
-extern bool setup_remapped_irq(int irq,
-			       struct irq_cfg *cfg,
-			       struct irq_chip *chip);
 
-void irq_remap_modify_chip_defaults(struct irq_chip *chip);
+extern struct irq_domain *
+irq_remapping_get_ir_irq_domain(struct irq_alloc_info *info);
+extern struct irq_domain *
+irq_remapping_get_irq_domain(struct irq_alloc_info *info);
+
+/* Create PCI MSI/MSIx irqdomain, use @parent as the parent irqdomain. */
+extern struct irq_domain *arch_create_msi_irq_domain(struct irq_domain *parent);
+
+/* Get parent irqdomain for interrupt remapping irqdomain */
+static inline struct irq_domain *arch_get_ir_parent_domain(void)
+{
+	return x86_vector_domain;
+}
+
+struct vcpu_data {
+	u64 pi_desc_addr;	/* Physical address of PI Descriptor */
+	u32 vector;		/* Guest vector of the interrupt */
+};
 
 #else  /* CONFIG_IRQ_REMAP */
 
+static inline bool irq_remapping_cap(enum irq_remap_cap cap) { return 0; }
 static inline void set_irq_remapping_broken(void) { }
 static inline int irq_remapping_prepare(void) { return -ENODEV; }
 static inline int irq_remapping_enable(void) { return -ENODEV; }
 static inline void irq_remapping_disable(void) { }
 static inline int irq_remapping_reenable(int eim) { return -ENODEV; }
 static inline int irq_remap_enable_fault_handling(void) { return -ENODEV; }
-static inline int setup_ioapic_remapped_entry(int irq,
-					      struct IO_APIC_route_entry *entry,
-					      unsigned int destination,
-					      int vector,
-					      struct io_apic_irq_attr *attr)
-{
-	return -ENODEV;
-}
-static inline void free_remapped_irq(int irq) { }
-static inline void compose_remapped_msi_msg(struct pci_dev *pdev,
-					    unsigned int irq, unsigned int dest,
-					    struct msi_msg *msg, u8 hpet_id)
-{
-}
-static inline int setup_hpet_msi_remapped(unsigned int irq, unsigned int id)
-{
-	return -ENODEV;
-}
 
 static inline void panic_if_irq_remap(const char *msg)
 {
 }
 
-static inline void irq_remap_modify_chip_defaults(struct irq_chip *chip)
+static inline struct irq_domain *
+irq_remapping_get_ir_irq_domain(struct irq_alloc_info *info)
 {
+	return NULL;
 }
 
-static inline bool setup_remapped_irq(int irq,
-				      struct irq_cfg *cfg,
-				      struct irq_chip *chip)
+static inline struct irq_domain *
+irq_remapping_get_irq_domain(struct irq_alloc_info *info)
 {
-	return false;
+	return NULL;
 }
-#endif /* CONFIG_IRQ_REMAP */
-
-#define dmar_alloc_hwirq()	irq_alloc_hwirq(-1)
-#define dmar_free_hwirq		irq_free_hwirq
 
+#endif /* CONFIG_IRQ_REMAP */
 #endif /* __X86_IRQ_REMAPPING_H */
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index 666c89ec4bd7..4c2d2eb2060a 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -47,31 +47,12 @@
 #define IRQ_MOVE_CLEANUP_VECTOR		FIRST_EXTERNAL_VECTOR
 
 #define IA32_SYSCALL_VECTOR		0x80
-#ifdef CONFIG_X86_32
-# define SYSCALL_VECTOR			0x80
-#endif
 
 /*
  * Vectors 0x30-0x3f are used for ISA interrupts.
  *   round up to the next 16-vector boundary
  */
-#define IRQ0_VECTOR			((FIRST_EXTERNAL_VECTOR + 16) & ~15)
-
-#define IRQ1_VECTOR			(IRQ0_VECTOR +  1)
-#define IRQ2_VECTOR			(IRQ0_VECTOR +  2)
-#define IRQ3_VECTOR			(IRQ0_VECTOR +  3)
-#define IRQ4_VECTOR			(IRQ0_VECTOR +  4)
-#define IRQ5_VECTOR			(IRQ0_VECTOR +  5)
-#define IRQ6_VECTOR			(IRQ0_VECTOR +  6)
-#define IRQ7_VECTOR			(IRQ0_VECTOR +  7)
-#define IRQ8_VECTOR			(IRQ0_VECTOR +  8)
-#define IRQ9_VECTOR			(IRQ0_VECTOR +  9)
-#define IRQ10_VECTOR			(IRQ0_VECTOR + 10)
-#define IRQ11_VECTOR			(IRQ0_VECTOR + 11)
-#define IRQ12_VECTOR			(IRQ0_VECTOR + 12)
-#define IRQ13_VECTOR			(IRQ0_VECTOR + 13)
-#define IRQ14_VECTOR			(IRQ0_VECTOR + 14)
-#define IRQ15_VECTOR			(IRQ0_VECTOR + 15)
+#define ISA_IRQ_VECTOR(irq)		(((FIRST_EXTERNAL_VECTOR + 16) & ~15) + irq)
 
 /*
  * Special IRQ vectors used by the SMP architecture, 0xf0-0xff
@@ -102,21 +83,23 @@
  */
 #define X86_PLATFORM_IPI_VECTOR		0xf7
 
-/* Vector for KVM to deliver posted interrupt IPI */
-#ifdef CONFIG_HAVE_KVM
-#define POSTED_INTR_VECTOR		0xf2
-#endif
-
+#define POSTED_INTR_WAKEUP_VECTOR	0xf1
 /*
  * IRQ work vector:
  */
 #define IRQ_WORK_VECTOR			0xf6
 
 #define UV_BAU_MESSAGE			0xf5
+#define DEFERRED_ERROR_VECTOR		0xf4
 
 /* Vector on which hypervisor callbacks will be delivered */
 #define HYPERVISOR_CALLBACK_VECTOR	0xf3
 
+/* Vector for KVM to deliver posted interrupt IPI */
+#ifdef CONFIG_HAVE_KVM
+#define POSTED_INTR_VECTOR		0xf2
+#endif
+
 /*
  * Local APIC timer IRQ vector is on a different priority level,
  * to work around the 'lost local interrupt if more than 2 IRQ
@@ -155,18 +138,22 @@ static inline int invalid_vm86_irq(int irq)
  * static arrays.
  */
 
-#define NR_IRQS_LEGACY			  16
+#define NR_IRQS_LEGACY			16
 
-#define IO_APIC_VECTOR_LIMIT		( 32 * MAX_IO_APICS )
+#define CPU_VECTOR_LIMIT		(64 * NR_CPUS)
+#define IO_APIC_VECTOR_LIMIT		(32 * MAX_IO_APICS)
 
-#ifdef CONFIG_X86_IO_APIC
-# define CPU_VECTOR_LIMIT		(64 * NR_CPUS)
-# define NR_IRQS					\
+#if defined(CONFIG_X86_IO_APIC) && defined(CONFIG_PCI_MSI)
+#define NR_IRQS						\
 	(CPU_VECTOR_LIMIT > IO_APIC_VECTOR_LIMIT ?	\
 		(NR_VECTORS + CPU_VECTOR_LIMIT)  :	\
 		(NR_VECTORS + IO_APIC_VECTOR_LIMIT))
-#else /* !CONFIG_X86_IO_APIC: */
-# define NR_IRQS			NR_IRQS_LEGACY
+#elif defined(CONFIG_X86_IO_APIC)
+#define	NR_IRQS				(NR_VECTORS + IO_APIC_VECTOR_LIMIT)
+#elif defined(CONFIG_PCI_MSI)
+#define NR_IRQS				(NR_VECTORS + CPU_VECTOR_LIMIT)
+#else
+#define NR_IRQS				NR_IRQS_LEGACY
 #endif
 
 #endif /* _ASM_X86_IRQ_VECTORS_H */
diff --git a/arch/x86/include/asm/irqdomain.h b/arch/x86/include/asm/irqdomain.h
new file mode 100644
index 000000000000..d26075b52885
--- /dev/null
+++ b/arch/x86/include/asm/irqdomain.h
@@ -0,0 +1,63 @@
+#ifndef _ASM_IRQDOMAIN_H
+#define _ASM_IRQDOMAIN_H
+
+#include <linux/irqdomain.h>
+#include <asm/hw_irq.h>
+
+#ifdef CONFIG_X86_LOCAL_APIC
+enum {
+	/* Allocate contiguous CPU vectors */
+	X86_IRQ_ALLOC_CONTIGUOUS_VECTORS		= 0x1,
+};
+
+extern struct irq_domain *x86_vector_domain;
+
+extern void init_irq_alloc_info(struct irq_alloc_info *info,
+				const struct cpumask *mask);
+extern void copy_irq_alloc_info(struct irq_alloc_info *dst,
+				struct irq_alloc_info *src);
+#endif /* CONFIG_X86_LOCAL_APIC */
+
+#ifdef CONFIG_X86_IO_APIC
+struct device_node;
+struct irq_data;
+
+enum ioapic_domain_type {
+	IOAPIC_DOMAIN_INVALID,
+	IOAPIC_DOMAIN_LEGACY,
+	IOAPIC_DOMAIN_STRICT,
+	IOAPIC_DOMAIN_DYNAMIC,
+};
+
+struct ioapic_domain_cfg {
+	enum ioapic_domain_type		type;
+	const struct irq_domain_ops	*ops;
+	struct device_node		*dev;
+};
+
+extern const struct irq_domain_ops mp_ioapic_irqdomain_ops;
+
+extern int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq,
+			      unsigned int nr_irqs, void *arg);
+extern void mp_irqdomain_free(struct irq_domain *domain, unsigned int virq,
+			      unsigned int nr_irqs);
+extern void mp_irqdomain_activate(struct irq_domain *domain,
+				  struct irq_data *irq_data);
+extern void mp_irqdomain_deactivate(struct irq_domain *domain,
+				    struct irq_data *irq_data);
+extern int mp_irqdomain_ioapic_idx(struct irq_domain *domain);
+#endif /* CONFIG_X86_IO_APIC */
+
+#ifdef CONFIG_PCI_MSI
+extern void arch_init_msi_domain(struct irq_domain *domain);
+#else
+static inline void arch_init_msi_domain(struct irq_domain *domain) { }
+#endif
+
+#ifdef CONFIG_HT_IRQ
+extern void arch_init_htirq_domain(struct irq_domain *domain);
+#else
+static inline void arch_init_htirq_domain(struct irq_domain *domain) { }
+#endif
+
+#endif
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index f4a555beef19..f8c0ec3a4a97 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1002,8 +1002,6 @@ void kvm_pic_clear_all(struct kvm_pic *pic, int irq_source_id);
 
 void kvm_inject_nmi(struct kvm_vcpu *vcpu);
 
-int fx_init(struct kvm_vcpu *vcpu);
-
 void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 		       const u8 *new, int bytes);
 int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn);
diff --git a/arch/x86/include/asm/livepatch.h b/arch/x86/include/asm/livepatch.h
index 2d29197bd2fb..19c099afa861 100644
--- a/arch/x86/include/asm/livepatch.h
+++ b/arch/x86/include/asm/livepatch.h
@@ -21,6 +21,7 @@
 #ifndef _ASM_X86_LIVEPATCH_H
 #define _ASM_X86_LIVEPATCH_H
 
+#include <asm/setup.h>
 #include <linux/module.h>
 #include <linux/ftrace.h>
 
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 1f5a86d518db..982dfc3679ad 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -17,11 +17,16 @@
 #define MCG_EXT_CNT(c)		(((c) & MCG_EXT_CNT_MASK) >> MCG_EXT_CNT_SHIFT)
 #define MCG_SER_P		(1ULL<<24)   /* MCA recovery/new status bits */
 #define MCG_ELOG_P		(1ULL<<26)   /* Extended error log supported */
+#define MCG_LMCE_P		(1ULL<<27)   /* Local machine check supported */
 
 /* MCG_STATUS register defines */
 #define MCG_STATUS_RIPV  (1ULL<<0)   /* restart ip valid */
 #define MCG_STATUS_EIPV  (1ULL<<1)   /* ip points to correct instruction */
 #define MCG_STATUS_MCIP  (1ULL<<2)   /* machine check in progress */
+#define MCG_STATUS_LMCES (1ULL<<3)   /* LMCE signaled */
+
+/* MCG_EXT_CTL register defines */
+#define MCG_EXT_CTL_LMCE_EN (1ULL<<0) /* Enable LMCE */
 
 /* MCi_STATUS register defines */
 #define MCI_STATUS_VAL   (1ULL<<63)  /* valid error */
@@ -104,6 +109,7 @@ struct mce_log {
 struct mca_config {
 	bool dont_log_ce;
 	bool cmci_disabled;
+	bool lmce_disabled;
 	bool ignore_ce;
 	bool disabled;
 	bool ser;
@@ -117,8 +123,19 @@ struct mca_config {
 };
 
 struct mce_vendor_flags {
-	__u64		overflow_recov	: 1, /* cpuid_ebx(80000007) */
-			__reserved_0	: 63;
+			/*
+			 * overflow recovery cpuid bit indicates that overflow
+			 * conditions are not fatal
+			 */
+	__u64		overflow_recov	: 1,
+
+			/*
+			 * SUCCOR stands for S/W UnCorrectable error COntainment
+			 * and Recovery. It indicates support for data poisoning
+			 * in HW and deferred error interrupts.
+			 */
+			succor		: 1,
+			__reserved_0	: 62;
 };
 extern struct mce_vendor_flags mce_flags;
 
@@ -168,12 +185,16 @@ void cmci_clear(void);
 void cmci_reenable(void);
 void cmci_rediscover(void);
 void cmci_recheck(void);
+void lmce_clear(void);
+void lmce_enable(void);
 #else
 static inline void mce_intel_feature_init(struct cpuinfo_x86 *c) { }
 static inline void cmci_clear(void) {}
 static inline void cmci_reenable(void) {}
 static inline void cmci_rediscover(void) {}
 static inline void cmci_recheck(void) {}
+static inline void lmce_clear(void) {}
+static inline void lmce_enable(void) {}
 #endif
 
 #ifdef CONFIG_X86_MCE_AMD
@@ -223,6 +244,9 @@ void do_machine_check(struct pt_regs *, long);
 extern void (*mce_threshold_vector)(void);
 extern void (*threshold_cpu_callback)(unsigned long action, unsigned int cpu);
 
+/* Deferred error interrupt handler */
+extern void (*deferred_error_int_vector)(void);
+
 /*
  * Thermal handler
  */
diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h
index 2fb20d6f7e23..9e6278c7140e 100644
--- a/arch/x86/include/asm/microcode.h
+++ b/arch/x86/include/asm/microcode.h
@@ -1,6 +1,8 @@
 #ifndef _ASM_X86_MICROCODE_H
 #define _ASM_X86_MICROCODE_H
 
+#include <linux/earlycpio.h>
+
 #define native_rdmsr(msr, val1, val2)			\
 do {							\
 	u64 __val = native_read_msr((msr));		\
@@ -152,6 +154,7 @@ extern void __init load_ucode_bsp(void);
 extern void load_ucode_ap(void);
 extern int __init save_microcode_in_initrd(void);
 void reload_early_microcode(void);
+extern bool get_builtin_firmware(struct cpio_data *cd, const char *name);
 #else
 static inline void __init load_ucode_bsp(void) {}
 static inline void load_ucode_ap(void) {}
@@ -160,6 +163,9 @@ static inline int __init save_microcode_in_initrd(void)
 	return 0;
 }
 static inline void reload_early_microcode(void) {}
+static inline bool get_builtin_firmware(struct cpio_data *cd, const char *name)
+{
+	return false;
+}
 #endif
-
 #endif /* _ASM_X86_MICROCODE_H */
diff --git a/arch/x86/include/asm/microcode_amd.h b/arch/x86/include/asm/microcode_amd.h
index af935397e053..ac6d328977a6 100644
--- a/arch/x86/include/asm/microcode_amd.h
+++ b/arch/x86/include/asm/microcode_amd.h
@@ -65,12 +65,12 @@ extern enum ucode_state load_microcode_amd(int cpu, u8 family, const u8 *data, s
 extern u8 amd_ucode_patch[PATCH_MAX_SIZE];
 
 #ifdef CONFIG_MICROCODE_AMD_EARLY
-extern void __init load_ucode_amd_bsp(void);
+extern void __init load_ucode_amd_bsp(unsigned int family);
 extern void load_ucode_amd_ap(void);
 extern int __init save_microcode_in_initrd_amd(void);
 void reload_ucode_amd(void);
 #else
-static inline void __init load_ucode_amd_bsp(void) {}
+static inline void __init load_ucode_amd_bsp(unsigned int family) {}
 static inline void load_ucode_amd_ap(void) {}
 static inline int __init save_microcode_in_initrd_amd(void) { return -EINVAL; }
 void reload_ucode_amd(void) {}
diff --git a/arch/x86/include/asm/microcode_intel.h b/arch/x86/include/asm/microcode_intel.h
index 2b9209c46ca9..7991c606125d 100644
--- a/arch/x86/include/asm/microcode_intel.h
+++ b/arch/x86/include/asm/microcode_intel.h
@@ -51,20 +51,11 @@ struct extended_sigtable {
 	(((struct microcode_intel *)mc)->hdr.datasize ? \
 	 ((struct microcode_intel *)mc)->hdr.datasize : DEFAULT_UCODE_DATASIZE)
 
-#define sigmatch(s1, s2, p1, p2) \
-	(((s1) == (s2)) && (((p1) & (p2)) || (((p1) == 0) && ((p2) == 0))))
-
 #define exttable_size(et) ((et)->count * EXT_SIGNATURE_SIZE + EXT_HEADER_SIZE)
 
-extern int get_matching_microcode(unsigned int csig, int cpf, int rev, void *mc);
+extern int has_newer_microcode(void *mc, unsigned int csig, int cpf, int rev);
 extern int microcode_sanity_check(void *mc, int print_err);
-extern int get_matching_sig(unsigned int csig, int cpf, int rev, void *mc);
-
-static inline int
-revision_is_newer(struct microcode_header_intel *mc_header, int rev)
-{
-	return (mc_header->rev <= rev) ? 0 : 1;
-}
+extern int find_matching_signature(void *mc, unsigned int csig, int cpf);
 
 #ifdef CONFIG_MICROCODE_INTEL_EARLY
 extern void __init load_ucode_intel_bsp(void);
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 883f6b933fa4..5e8daee7c5c9 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -142,6 +142,19 @@ static inline void arch_exit_mmap(struct mm_struct *mm)
 	paravirt_arch_exit_mmap(mm);
 }
 
+#ifdef CONFIG_X86_64
+static inline bool is_64bit_mm(struct mm_struct *mm)
+{
+	return	!config_enabled(CONFIG_IA32_EMULATION) ||
+		!(mm->context.ia32_compat == TIF_IA32);
+}
+#else
+static inline bool is_64bit_mm(struct mm_struct *mm)
+{
+	return false;
+}
+#endif
+
 static inline void arch_bprm_mm_init(struct mm_struct *mm,
 		struct vm_area_struct *vma)
 {
diff --git a/arch/x86/include/asm/mpx.h b/arch/x86/include/asm/mpx.h
index a952a13d59a7..7a35495275a9 100644
--- a/arch/x86/include/asm/mpx.h
+++ b/arch/x86/include/asm/mpx.h
@@ -13,55 +13,50 @@
 #define MPX_BNDCFG_ENABLE_FLAG	0x1
 #define MPX_BD_ENTRY_VALID_FLAG	0x1
 
-#ifdef CONFIG_X86_64
-
-/* upper 28 bits [47:20] of the virtual address in 64-bit used to
- * index into bounds directory (BD).
- */
-#define MPX_BD_ENTRY_OFFSET	28
-#define MPX_BD_ENTRY_SHIFT	3
-/* bits [19:3] of the virtual address in 64-bit used to index into
- * bounds table (BT).
+/*
+ * The upper 28 bits [47:20] of the virtual address in 64-bit
+ * are used to index into bounds directory (BD).
+ *
+ * The directory is 2G (2^31) in size, and with 8-byte entries
+ * it has 2^28 entries.
  */
-#define MPX_BT_ENTRY_OFFSET	17
-#define MPX_BT_ENTRY_SHIFT	5
-#define MPX_IGN_BITS		3
-#define MPX_BD_ENTRY_TAIL	3
+#define MPX_BD_SIZE_BYTES_64	(1UL<<31)
+#define MPX_BD_ENTRY_BYTES_64	8
+#define MPX_BD_NR_ENTRIES_64	(MPX_BD_SIZE_BYTES_64/MPX_BD_ENTRY_BYTES_64)
 
-#else
-
-#define MPX_BD_ENTRY_OFFSET	20
-#define MPX_BD_ENTRY_SHIFT	2
-#define MPX_BT_ENTRY_OFFSET	10
-#define MPX_BT_ENTRY_SHIFT	4
-#define MPX_IGN_BITS		2
-#define MPX_BD_ENTRY_TAIL	2
+/*
+ * The 32-bit directory is 4MB (2^22) in size, and with 4-byte
+ * entries it has 2^20 entries.
+ */
+#define MPX_BD_SIZE_BYTES_32	(1UL<<22)
+#define MPX_BD_ENTRY_BYTES_32	4
+#define MPX_BD_NR_ENTRIES_32	(MPX_BD_SIZE_BYTES_32/MPX_BD_ENTRY_BYTES_32)
 
-#endif
+/*
+ * A 64-bit table is 4MB total in size, and an entry is
+ * 4 64-bit pointers in size.
+ */
+#define MPX_BT_SIZE_BYTES_64	(1UL<<22)
+#define MPX_BT_ENTRY_BYTES_64	32
+#define MPX_BT_NR_ENTRIES_64	(MPX_BT_SIZE_BYTES_64/MPX_BT_ENTRY_BYTES_64)
 
-#define MPX_BD_SIZE_BYTES (1UL<<(MPX_BD_ENTRY_OFFSET+MPX_BD_ENTRY_SHIFT))
-#define MPX_BT_SIZE_BYTES (1UL<<(MPX_BT_ENTRY_OFFSET+MPX_BT_ENTRY_SHIFT))
+/*
+ * A 32-bit table is 16kB total in size, and an entry is
+ * 4 32-bit pointers in size.
+ */
+#define MPX_BT_SIZE_BYTES_32	(1UL<<14)
+#define MPX_BT_ENTRY_BYTES_32	16
+#define MPX_BT_NR_ENTRIES_32	(MPX_BT_SIZE_BYTES_32/MPX_BT_ENTRY_BYTES_32)
 
 #define MPX_BNDSTA_TAIL		2
 #define MPX_BNDCFG_TAIL		12
 #define MPX_BNDSTA_ADDR_MASK	(~((1UL<<MPX_BNDSTA_TAIL)-1))
 #define MPX_BNDCFG_ADDR_MASK	(~((1UL<<MPX_BNDCFG_TAIL)-1))
-#define MPX_BT_ADDR_MASK	(~((1UL<<MPX_BD_ENTRY_TAIL)-1))
-
-#define MPX_BNDCFG_ADDR_MASK	(~((1UL<<MPX_BNDCFG_TAIL)-1))
 #define MPX_BNDSTA_ERROR_CODE	0x3
 
-#define MPX_BD_ENTRY_MASK	((1<<MPX_BD_ENTRY_OFFSET)-1)
-#define MPX_BT_ENTRY_MASK	((1<<MPX_BT_ENTRY_OFFSET)-1)
-#define MPX_GET_BD_ENTRY_OFFSET(addr)	((((addr)>>(MPX_BT_ENTRY_OFFSET+ \
-		MPX_IGN_BITS)) & MPX_BD_ENTRY_MASK) << MPX_BD_ENTRY_SHIFT)
-#define MPX_GET_BT_ENTRY_OFFSET(addr)	((((addr)>>MPX_IGN_BITS) & \
-		MPX_BT_ENTRY_MASK) << MPX_BT_ENTRY_SHIFT)
-
 #ifdef CONFIG_X86_INTEL_MPX
-siginfo_t *mpx_generate_siginfo(struct pt_regs *regs,
-				struct xsave_struct *xsave_buf);
-int mpx_handle_bd_fault(struct xsave_struct *xsave_buf);
+siginfo_t *mpx_generate_siginfo(struct pt_regs *regs);
+int mpx_handle_bd_fault(void);
 static inline int kernel_managing_mpx_tables(struct mm_struct *mm)
 {
 	return (mm->bd_addr != MPX_INVALID_BOUNDS_DIR);
@@ -77,12 +72,11 @@ static inline void mpx_mm_init(struct mm_struct *mm)
 void mpx_notify_unmap(struct mm_struct *mm, struct vm_area_struct *vma,
 		      unsigned long start, unsigned long end);
 #else
-static inline siginfo_t *mpx_generate_siginfo(struct pt_regs *regs,
-					      struct xsave_struct *xsave_buf)
+static inline siginfo_t *mpx_generate_siginfo(struct pt_regs *regs)
 {
 	return NULL;
 }
-static inline int mpx_handle_bd_fault(struct xsave_struct *xsave_buf)
+static inline int mpx_handle_bd_fault(void)
 {
 	return -EINVAL;
 }
diff --git a/arch/x86/include/asm/msi.h b/arch/x86/include/asm/msi.h
new file mode 100644
index 000000000000..93724cc62177
--- /dev/null
+++ b/arch/x86/include/asm/msi.h
@@ -0,0 +1,7 @@
+#ifndef _ASM_X86_MSI_H
+#define _ASM_X86_MSI_H
+#include <asm/hw_irq.h>
+
+typedef struct irq_alloc_info msi_alloc_info_t;
+
+#endif /* _ASM_X86_MSI_H */
diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 3c6bb342a48f..9ebc3d009373 100644
--- a/arch/x86/include/uapi/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -56,6 +56,7 @@
 #define MSR_IA32_MCG_CAP		0x00000179
 #define MSR_IA32_MCG_STATUS		0x0000017a
 #define MSR_IA32_MCG_CTL		0x0000017b
+#define MSR_IA32_MCG_EXT_CTL		0x000004d0
 
 #define MSR_OFFCORE_RSP_0		0x000001a6
 #define MSR_OFFCORE_RSP_1		0x000001a7
@@ -380,6 +381,7 @@
 #define FEATURE_CONTROL_LOCKED				(1<<0)
 #define FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX	(1<<1)
 #define FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX	(1<<2)
+#define FEATURE_CONTROL_LMCE				(1<<20)
 
 #define MSR_IA32_APICBASE		0x0000001b
 #define MSR_IA32_APICBASE_BSP		(1<<8)
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index de36f22eb0b9..e6a707eb5081 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -1,13 +1,14 @@
 #ifndef _ASM_X86_MSR_H
 #define _ASM_X86_MSR_H
 
-#include <uapi/asm/msr.h>
+#include "msr-index.h"
 
 #ifndef __ASSEMBLY__
 
 #include <asm/asm.h>
 #include <asm/errno.h>
 #include <asm/cpumask.h>
+#include <uapi/asm/msr.h>
 
 struct msr {
 	union {
@@ -205,8 +206,13 @@ do {                                                            \
 
 #endif	/* !CONFIG_PARAVIRT */
 
-#define wrmsrl_safe(msr, val) wrmsr_safe((msr), (u32)(val),		\
-					     (u32)((val) >> 32))
+/*
+ * 64-bit version of wrmsr_safe():
+ */
+static inline int wrmsrl_safe(u32 msr, u64 val)
+{
+	return wrmsr_safe(msr, (u32)val,  (u32)(val >> 32));
+}
 
 #define write_tsc(low, high) wrmsr(MSR_IA32_TSC, (low), (high))
 
diff --git a/arch/x86/include/asm/mtrr.h b/arch/x86/include/asm/mtrr.h
index f768f6298419..b94f6f64e23d 100644
--- a/arch/x86/include/asm/mtrr.h
+++ b/arch/x86/include/asm/mtrr.h
@@ -31,7 +31,7 @@
  * arch_phys_wc_add and arch_phys_wc_del.
  */
 # ifdef CONFIG_MTRR
-extern u8 mtrr_type_lookup(u64 addr, u64 end);
+extern u8 mtrr_type_lookup(u64 addr, u64 end, u8 *uniform);
 extern void mtrr_save_fixed_ranges(void *);
 extern void mtrr_save_state(void);
 extern int mtrr_add(unsigned long base, unsigned long size,
@@ -48,14 +48,13 @@ extern void mtrr_aps_init(void);
 extern void mtrr_bp_restore(void);
 extern int mtrr_trim_uncached_memory(unsigned long end_pfn);
 extern int amd_special_default_mtrr(void);
-extern int phys_wc_to_mtrr_index(int handle);
 #  else
-static inline u8 mtrr_type_lookup(u64 addr, u64 end)
+static inline u8 mtrr_type_lookup(u64 addr, u64 end, u8 *uniform)
 {
 	/*
 	 * Return no-MTRRs:
 	 */
-	return 0xff;
+	return MTRR_TYPE_INVALID;
 }
 #define mtrr_save_fixed_ranges(arg) do {} while (0)
 #define mtrr_save_state() do {} while (0)
@@ -84,10 +83,6 @@ static inline int mtrr_trim_uncached_memory(unsigned long end_pfn)
 static inline void mtrr_centaur_report_mcr(int mcr, u32 lo, u32 hi)
 {
 }
-static inline int phys_wc_to_mtrr_index(int handle)
-{
-	return -1;
-}
 
 #define mtrr_ap_init() do {} while (0)
 #define mtrr_bp_init() do {} while (0)
@@ -127,4 +122,8 @@ struct mtrr_gentry32 {
 				 _IOW(MTRR_IOCTL_BASE,  9, struct mtrr_sentry32)
 #endif /* CONFIG_COMPAT */
 
+/* Bit fields for enabled in struct mtrr_state_type */
+#define MTRR_STATE_MTRR_FIXED_ENABLED	0x01
+#define MTRR_STATE_MTRR_ENABLED		0x02
+
 #endif /* _ASM_X86_MTRR_H */
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 8957810ad7d1..d143bfad45d7 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -712,6 +712,31 @@ static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx,
 
 #if defined(CONFIG_SMP) && defined(CONFIG_PARAVIRT_SPINLOCKS)
 
+#ifdef CONFIG_QUEUED_SPINLOCKS
+
+static __always_inline void pv_queued_spin_lock_slowpath(struct qspinlock *lock,
+							u32 val)
+{
+	PVOP_VCALL2(pv_lock_ops.queued_spin_lock_slowpath, lock, val);
+}
+
+static __always_inline void pv_queued_spin_unlock(struct qspinlock *lock)
+{
+	PVOP_VCALLEE1(pv_lock_ops.queued_spin_unlock, lock);
+}
+
+static __always_inline void pv_wait(u8 *ptr, u8 val)
+{
+	PVOP_VCALL2(pv_lock_ops.wait, ptr, val);
+}
+
+static __always_inline void pv_kick(int cpu)
+{
+	PVOP_VCALL1(pv_lock_ops.kick, cpu);
+}
+
+#else /* !CONFIG_QUEUED_SPINLOCKS */
+
 static __always_inline void __ticket_lock_spinning(struct arch_spinlock *lock,
 							__ticket_t ticket)
 {
@@ -724,7 +749,9 @@ static __always_inline void __ticket_unlock_kick(struct arch_spinlock *lock,
 	PVOP_VCALL2(pv_lock_ops.unlock_kick, lock, ticket);
 }
 
-#endif
+#endif /* CONFIG_QUEUED_SPINLOCKS */
+
+#endif /* SMP && PARAVIRT_SPINLOCKS */
 
 #ifdef CONFIG_X86_32
 #define PV_SAVE_REGS "pushl %ecx; pushl %edx;"
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index f7b0b5c112f2..a6b8f9fadb06 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -160,13 +160,14 @@ struct pv_cpu_ops {
 	u64 (*read_pmc)(int counter);
 	unsigned long long (*read_tscp)(unsigned int *aux);
 
+#ifdef CONFIG_X86_32
 	/*
 	 * Atomically enable interrupts and return to userspace.  This
-	 * is only ever used to return to 32-bit processes; in a
-	 * 64-bit kernel, it's used for 32-on-64 compat processes, but
-	 * never native 64-bit processes.  (Jump, not call.)
+	 * is only used in 32-bit kernels.  64-bit kernels use
+	 * usergs_sysret32 instead.
 	 */
 	void (*irq_enable_sysexit)(void);
+#endif
 
 	/*
 	 * Switch to usermode gs and return to 64-bit usermode using
@@ -333,9 +334,19 @@ struct arch_spinlock;
 typedef u16 __ticket_t;
 #endif
 
+struct qspinlock;
+
 struct pv_lock_ops {
+#ifdef CONFIG_QUEUED_SPINLOCKS
+	void (*queued_spin_lock_slowpath)(struct qspinlock *lock, u32 val);
+	struct paravirt_callee_save queued_spin_unlock;
+
+	void (*wait)(u8 *ptr, u8 val);
+	void (*kick)(int cpu);
+#else /* !CONFIG_QUEUED_SPINLOCKS */
 	struct paravirt_callee_save lock_spinning;
 	void (*unlock_kick)(struct arch_spinlock *lock, __ticket_t ticket);
+#endif /* !CONFIG_QUEUED_SPINLOCKS */
 };
 
 /* This contains all the paravirt structures: we get a convenient
diff --git a/arch/x86/include/asm/pat.h b/arch/x86/include/asm/pat.h
index 91bc4ba95f91..ca6c228d5e62 100644
--- a/arch/x86/include/asm/pat.h
+++ b/arch/x86/include/asm/pat.h
@@ -4,14 +4,9 @@
 #include <linux/types.h>
 #include <asm/pgtable_types.h>
 
-#ifdef CONFIG_X86_PAT
-extern int pat_enabled;
-#else
-static const int pat_enabled;
-#endif
-
+bool pat_enabled(void);
 extern void pat_init(void);
-void pat_init_cache_modes(void);
+void pat_init_cache_modes(u64);
 
 extern int reserve_memtype(u64 start, u64 end,
 		enum page_cache_mode req_pcm, enum page_cache_mode *ret_pcm);
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index 4e370a5d8117..b962e0fe5658 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -80,13 +80,6 @@ extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
 
 #ifdef CONFIG_PCI
 extern void early_quirks(void);
-static inline void pci_dma_burst_advice(struct pci_dev *pdev,
-					enum pci_dma_burst_strategy *strat,
-					unsigned long *strategy_parameter)
-{
-	*strat = PCI_DMA_BURST_INFINITY;
-	*strategy_parameter = ~0UL;
-}
 #else
 static inline void early_quirks(void) { }
 #endif
@@ -96,15 +89,10 @@ extern void pci_iommu_alloc(void);
 #ifdef CONFIG_PCI_MSI
 /* implemented in arch/x86/kernel/apic/io_apic. */
 struct msi_desc;
-void native_compose_msi_msg(struct pci_dev *pdev, unsigned int irq,
-			    unsigned int dest, struct msi_msg *msg, u8 hpet_id);
 int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type);
 void native_teardown_msi_irq(unsigned int irq);
 void native_restore_msi_irqs(struct pci_dev *dev);
-int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc,
-		  unsigned int irq_base, unsigned int irq_offset);
 #else
-#define native_compose_msi_msg		NULL
 #define native_setup_msi_irqs		NULL
 #define native_teardown_msi_irq		NULL
 #endif
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index fe57e7a98839..2562e303405b 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -398,11 +398,17 @@ static inline int is_new_memtype_allowed(u64 paddr, unsigned long size,
 	 * requested memtype:
 	 * - request is uncached, return cannot be write-back
 	 * - request is write-combine, return cannot be write-back
+	 * - request is write-through, return cannot be write-back
+	 * - request is write-through, return cannot be write-combine
 	 */
 	if ((pcm == _PAGE_CACHE_MODE_UC_MINUS &&
 	     new_pcm == _PAGE_CACHE_MODE_WB) ||
 	    (pcm == _PAGE_CACHE_MODE_WC &&
-	     new_pcm == _PAGE_CACHE_MODE_WB)) {
+	     new_pcm == _PAGE_CACHE_MODE_WB) ||
+	    (pcm == _PAGE_CACHE_MODE_WT &&
+	     new_pcm == _PAGE_CACHE_MODE_WB) ||
+	    (pcm == _PAGE_CACHE_MODE_WT &&
+	     new_pcm == _PAGE_CACHE_MODE_WC)) {
 		return 0;
 	}
 
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 78f0c8cbe316..13f310bfc09a 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -367,6 +367,9 @@ extern int nx_enabled;
 #define pgprot_writecombine	pgprot_writecombine
 extern pgprot_t pgprot_writecombine(pgprot_t prot);
 
+#define pgprot_writethrough	pgprot_writethrough
+extern pgprot_t pgprot_writethrough(pgprot_t prot);
+
 /* Indicate that x86 has its own track and untrack pfn vma functions */
 #define __HAVE_PFNMAP_TRACKING
 
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index 8f3271842533..dca71714f860 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -99,11 +99,9 @@ static __always_inline bool should_resched(void)
   extern asmlinkage void ___preempt_schedule(void);
 # define __preempt_schedule() asm ("call ___preempt_schedule")
   extern asmlinkage void preempt_schedule(void);
-# ifdef CONFIG_CONTEXT_TRACKING
-    extern asmlinkage void ___preempt_schedule_context(void);
-#   define __preempt_schedule_context() asm ("call ___preempt_schedule_context")
-    extern asmlinkage void preempt_schedule_context(void);
-# endif
+  extern asmlinkage void ___preempt_schedule_notrace(void);
+# define __preempt_schedule_notrace() asm ("call ___preempt_schedule_notrace")
+  extern asmlinkage void preempt_schedule_notrace(void);
 #endif
 
 #endif /* __ASM_PREEMPT_H */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 23ba6765b718..43e6519df0d5 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -21,6 +21,7 @@ struct mm_struct;
 #include <asm/desc_defs.h>
 #include <asm/nops.h>
 #include <asm/special_insns.h>
+#include <asm/fpu/types.h>
 
 #include <linux/personality.h>
 #include <linux/cpumask.h>
@@ -52,11 +53,16 @@ static inline void *current_text_addr(void)
 	return pc;
 }
 
+/*
+ * These alignment constraints are for performance in the vSMP case,
+ * but in the task_struct case we must also meet hardware imposed
+ * alignment requirements of the FPU state:
+ */
 #ifdef CONFIG_X86_VSMP
 # define ARCH_MIN_TASKALIGN		(1 << INTERNODE_CACHE_SHIFT)
 # define ARCH_MIN_MMSTRUCT_ALIGN	(1 << INTERNODE_CACHE_SHIFT)
 #else
-# define ARCH_MIN_TASKALIGN		16
+# define ARCH_MIN_TASKALIGN		__alignof__(union fpregs_state)
 # define ARCH_MIN_MMSTRUCT_ALIGN	0
 #endif
 
@@ -166,7 +172,6 @@ extern const struct seq_operations cpuinfo_op;
 #define cache_line_size()	(boot_cpu_data.x86_cache_alignment)
 
 extern void cpu_detect(struct cpuinfo_x86 *c);
-extern void fpu_detect(struct cpuinfo_x86 *c);
 
 extern void early_cpu_init(void);
 extern void identify_boot_cpu(void);
@@ -313,128 +318,6 @@ struct orig_ist {
 	unsigned long		ist[7];
 };
 
-#define	MXCSR_DEFAULT		0x1f80
-
-struct i387_fsave_struct {
-	u32			cwd;	/* FPU Control Word		*/
-	u32			swd;	/* FPU Status Word		*/
-	u32			twd;	/* FPU Tag Word			*/
-	u32			fip;	/* FPU IP Offset		*/
-	u32			fcs;	/* FPU IP Selector		*/
-	u32			foo;	/* FPU Operand Pointer Offset	*/
-	u32			fos;	/* FPU Operand Pointer Selector	*/
-
-	/* 8*10 bytes for each FP-reg = 80 bytes:			*/
-	u32			st_space[20];
-
-	/* Software status information [not touched by FSAVE ]:		*/
-	u32			status;
-};
-
-struct i387_fxsave_struct {
-	u16			cwd; /* Control Word			*/
-	u16			swd; /* Status Word			*/
-	u16			twd; /* Tag Word			*/
-	u16			fop; /* Last Instruction Opcode		*/
-	union {
-		struct {
-			u64	rip; /* Instruction Pointer		*/
-			u64	rdp; /* Data Pointer			*/
-		};
-		struct {
-			u32	fip; /* FPU IP Offset			*/
-			u32	fcs; /* FPU IP Selector			*/
-			u32	foo; /* FPU Operand Offset		*/
-			u32	fos; /* FPU Operand Selector		*/
-		};
-	};
-	u32			mxcsr;		/* MXCSR Register State */
-	u32			mxcsr_mask;	/* MXCSR Mask		*/
-
-	/* 8*16 bytes for each FP-reg = 128 bytes:			*/
-	u32			st_space[32];
-
-	/* 16*16 bytes for each XMM-reg = 256 bytes:			*/
-	u32			xmm_space[64];
-
-	u32			padding[12];
-
-	union {
-		u32		padding1[12];
-		u32		sw_reserved[12];
-	};
-
-} __attribute__((aligned(16)));
-
-struct i387_soft_struct {
-	u32			cwd;
-	u32			swd;
-	u32			twd;
-	u32			fip;
-	u32			fcs;
-	u32			foo;
-	u32			fos;
-	/* 8*10 bytes for each FP-reg = 80 bytes: */
-	u32			st_space[20];
-	u8			ftop;
-	u8			changed;
-	u8			lookahead;
-	u8			no_update;
-	u8			rm;
-	u8			alimit;
-	struct math_emu_info	*info;
-	u32			entry_eip;
-};
-
-struct ymmh_struct {
-	/* 16 * 16 bytes for each YMMH-reg = 256 bytes */
-	u32 ymmh_space[64];
-};
-
-/* We don't support LWP yet: */
-struct lwp_struct {
-	u8 reserved[128];
-};
-
-struct bndreg {
-	u64 lower_bound;
-	u64 upper_bound;
-} __packed;
-
-struct bndcsr {
-	u64 bndcfgu;
-	u64 bndstatus;
-} __packed;
-
-struct xsave_hdr_struct {
-	u64 xstate_bv;
-	u64 xcomp_bv;
-	u64 reserved[6];
-} __attribute__((packed));
-
-struct xsave_struct {
-	struct i387_fxsave_struct i387;
-	struct xsave_hdr_struct xsave_hdr;
-	struct ymmh_struct ymmh;
-	struct lwp_struct lwp;
-	struct bndreg bndreg[4];
-	struct bndcsr bndcsr;
-	/* new processor state extensions will go here */
-} __attribute__ ((packed, aligned (64)));
-
-union thread_xstate {
-	struct i387_fsave_struct	fsave;
-	struct i387_fxsave_struct	fxsave;
-	struct i387_soft_struct		soft;
-	struct xsave_struct		xsave;
-};
-
-struct fpu {
-	unsigned int last_cpu;
-	unsigned int has_fpu;
-	union thread_xstate *state;
-};
-
 #ifdef CONFIG_X86_64
 DECLARE_PER_CPU(struct orig_ist, orig_ist);
 
@@ -483,8 +366,6 @@ DECLARE_PER_CPU(struct irq_stack *, softirq_stack);
 #endif	/* X86_64 */
 
 extern unsigned int xstate_size;
-extern void free_thread_xstate(struct task_struct *);
-extern struct kmem_cache *task_xstate_cachep;
 
 struct perf_event;
 
@@ -508,6 +389,10 @@ struct thread_struct {
 	unsigned long		fs;
 #endif
 	unsigned long		gs;
+
+	/* Floating point and extended processor state */
+	struct fpu		fpu;
+
 	/* Save middle states of ptrace breakpoints */
 	struct perf_event	*ptrace_bps[HBP_NUM];
 	/* Debug status used for traps, single steps, etc... */
@@ -518,8 +403,6 @@ struct thread_struct {
 	unsigned long		cr2;
 	unsigned long		trap_nr;
 	unsigned long		error_code;
-	/* floating point and extended processor state */
-	struct fpu		fpu;
 #ifdef CONFIG_X86_32
 	/* Virtual 86 mode info */
 	struct vm86_struct __user *vm86_info;
@@ -535,15 +418,6 @@ struct thread_struct {
 	unsigned long		iopl;
 	/* Max allowed port in the bitmap, in bytes: */
 	unsigned		io_bitmap_max;
-	/*
-	 * fpu_counter contains the number of consecutive context switches
-	 * that the FPU is used. If this is over a threshold, the lazy fpu
-	 * saving becomes unlazy to save the trap. This is an unsigned char
-	 * so that after 256 times the counter wraps and the behavior turns
-	 * lazy again; this to deal with bursty apps that only use FPU for
-	 * a short time
-	 */
-	unsigned char fpu_counter;
 };
 
 /*
@@ -928,24 +802,25 @@ extern int get_tsc_mode(unsigned long adr);
 extern int set_tsc_mode(unsigned int val);
 
 /* Register/unregister a process' MPX related resource */
-#define MPX_ENABLE_MANAGEMENT(tsk)	mpx_enable_management((tsk))
-#define MPX_DISABLE_MANAGEMENT(tsk)	mpx_disable_management((tsk))
+#define MPX_ENABLE_MANAGEMENT()	mpx_enable_management()
+#define MPX_DISABLE_MANAGEMENT()	mpx_disable_management()
 
 #ifdef CONFIG_X86_INTEL_MPX
-extern int mpx_enable_management(struct task_struct *tsk);
-extern int mpx_disable_management(struct task_struct *tsk);
+extern int mpx_enable_management(void);
+extern int mpx_disable_management(void);
 #else
-static inline int mpx_enable_management(struct task_struct *tsk)
+static inline int mpx_enable_management(void)
 {
 	return -EINVAL;
 }
-static inline int mpx_disable_management(struct task_struct *tsk)
+static inline int mpx_disable_management(void)
 {
 	return -EINVAL;
 }
 #endif /* CONFIG_X86_INTEL_MPX */
 
 extern u16 amd_get_nb_id(int cpu);
+extern u32 amd_get_nodes_per_socket(void);
 
 static inline uint32_t hypervisor_cpuid_base(const char *sig, uint32_t leaves)
 {
diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h
index a90f8972dad5..a4a77286cb1d 100644
--- a/arch/x86/include/asm/proto.h
+++ b/arch/x86/include/asm/proto.h
@@ -5,12 +5,14 @@
 
 /* misc architecture specific prototypes */
 
-void system_call(void);
 void syscall_init(void);
 
-void ia32_syscall(void);
-void ia32_cstar_target(void);
-void ia32_sysenter_target(void);
+void entry_SYSCALL_64(void);
+void entry_SYSCALL_compat(void);
+void entry_INT80_32(void);
+void entry_INT80_compat(void);
+void entry_SYSENTER_32(void);
+void entry_SYSENTER_compat(void);
 
 void x86_configure_nx(void);
 void x86_report_nx(void);
diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h
new file mode 100644
index 000000000000..9d51fae1cba3
--- /dev/null
+++ b/arch/x86/include/asm/qspinlock.h
@@ -0,0 +1,57 @@
+#ifndef _ASM_X86_QSPINLOCK_H
+#define _ASM_X86_QSPINLOCK_H
+
+#include <asm/cpufeature.h>
+#include <asm-generic/qspinlock_types.h>
+#include <asm/paravirt.h>
+
+#define	queued_spin_unlock queued_spin_unlock
+/**
+ * queued_spin_unlock - release a queued spinlock
+ * @lock : Pointer to queued spinlock structure
+ *
+ * A smp_store_release() on the least-significant byte.
+ */
+static inline void native_queued_spin_unlock(struct qspinlock *lock)
+{
+	smp_store_release((u8 *)lock, 0);
+}
+
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+extern void native_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
+extern void __pv_init_lock_hash(void);
+extern void __pv_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
+extern void __raw_callee_save___pv_queued_spin_unlock(struct qspinlock *lock);
+
+static inline void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
+{
+	pv_queued_spin_lock_slowpath(lock, val);
+}
+
+static inline void queued_spin_unlock(struct qspinlock *lock)
+{
+	pv_queued_spin_unlock(lock);
+}
+#else
+static inline void queued_spin_unlock(struct qspinlock *lock)
+{
+	native_queued_spin_unlock(lock);
+}
+#endif
+
+#define virt_queued_spin_lock virt_queued_spin_lock
+
+static inline bool virt_queued_spin_lock(struct qspinlock *lock)
+{
+	if (!static_cpu_has(X86_FEATURE_HYPERVISOR))
+		return false;
+
+	while (atomic_cmpxchg(&lock->val, 0, _Q_LOCKED_VAL) != 0)
+		cpu_relax();
+
+	return true;
+}
+
+#include <asm-generic/qspinlock.h>
+
+#endif /* _ASM_X86_QSPINLOCK_H */
diff --git a/arch/x86/include/asm/qspinlock_paravirt.h b/arch/x86/include/asm/qspinlock_paravirt.h
new file mode 100644
index 000000000000..b002e711ba88
--- /dev/null
+++ b/arch/x86/include/asm/qspinlock_paravirt.h
@@ -0,0 +1,6 @@
+#ifndef __ASM_QSPINLOCK_PARAVIRT_H
+#define __ASM_QSPINLOCK_PARAVIRT_H
+
+PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock);
+
+#endif
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index f69e06b283fb..11af24e09c8a 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -60,17 +60,24 @@ static inline void x86_ce4100_early_setup(void) { }
 #ifndef _SETUP
 
 #include <asm/espfix.h>
+#include <linux/kernel.h>
 
 /*
  * This is set up by the setup-routine at boot-time
  */
 extern struct boot_params boot_params;
+extern char _text[];
 
 static inline bool kaslr_enabled(void)
 {
 	return !!(boot_params.hdr.loadflags & KASLR_FLAG);
 }
 
+static inline unsigned long kaslr_offset(void)
+{
+	return (unsigned long)&_text - __START_KERNEL;
+}
+
 /*
  * Do NOT EVER look at the BIOS memory size location.
  * It does not work on many machines.
diff --git a/arch/x86/include/asm/simd.h b/arch/x86/include/asm/simd.h
index ee80b92f0096..6c8a7ed13365 100644
--- a/arch/x86/include/asm/simd.h
+++ b/arch/x86/include/asm/simd.h
@@ -1,5 +1,5 @@
 
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 
 /*
  * may_use_simd - whether it is allowable at this time to issue SIMD
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 17a8dced12da..222a6a3ca2b5 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -37,16 +37,6 @@ DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map);
 DECLARE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id);
 DECLARE_PER_CPU_READ_MOSTLY(int, cpu_number);
 
-static inline struct cpumask *cpu_sibling_mask(int cpu)
-{
-	return per_cpu(cpu_sibling_map, cpu);
-}
-
-static inline struct cpumask *cpu_core_mask(int cpu)
-{
-	return per_cpu(cpu_core_map, cpu);
-}
-
 static inline struct cpumask *cpu_llc_shared_mask(int cpu)
 {
 	return per_cpu(cpu_llc_shared_map, cpu);
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index aeb4666e0c0a..2270e41b32fd 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -215,6 +215,44 @@ static inline void clwb(volatile void *__p)
 		: [pax] "a" (p));
 }
 
+/**
+ * pcommit_sfence() - persistent commit and fence
+ *
+ * The PCOMMIT instruction ensures that data that has been flushed from the
+ * processor's cache hierarchy with CLWB, CLFLUSHOPT or CLFLUSH is accepted to
+ * memory and is durable on the DIMM.  The primary use case for this is
+ * persistent memory.
+ *
+ * This function shows how to properly use CLWB/CLFLUSHOPT/CLFLUSH and PCOMMIT
+ * with appropriate fencing.
+ *
+ * Example:
+ * void flush_and_commit_buffer(void *vaddr, unsigned int size)
+ * {
+ *         unsigned long clflush_mask = boot_cpu_data.x86_clflush_size - 1;
+ *         void *vend = vaddr + size;
+ *         void *p;
+ *
+ *         for (p = (void *)((unsigned long)vaddr & ~clflush_mask);
+ *              p < vend; p += boot_cpu_data.x86_clflush_size)
+ *                 clwb(p);
+ *
+ *         // SFENCE to order CLWB/CLFLUSHOPT/CLFLUSH cache flushes
+ *         // MFENCE via mb() also works
+ *         wmb();
+ *
+ *         // PCOMMIT and the required SFENCE for ordering
+ *         pcommit_sfence();
+ * }
+ *
+ * After this function completes the data pointed to by 'vaddr' has been
+ * accepted to memory and will be durable if the 'vaddr' points to persistent
+ * memory.
+ *
+ * PCOMMIT must always be ordered by an MFENCE or SFENCE, so to help simplify
+ * things we include both the PCOMMIT and the required SFENCE in the
+ * alternatives generated by pcommit_sfence().
+ */
 static inline void pcommit_sfence(void)
 {
 	alternative(ASM_NOP7,
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index 64b611782ef0..be0a05913b91 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -42,6 +42,10 @@
 extern struct static_key paravirt_ticketlocks_enabled;
 static __always_inline bool static_key_false(struct static_key *key);
 
+#ifdef CONFIG_QUEUED_SPINLOCKS
+#include <asm/qspinlock.h>
+#else
+
 #ifdef CONFIG_PARAVIRT_SPINLOCKS
 
 static inline void __ticket_enter_slowpath(arch_spinlock_t *lock)
@@ -196,6 +200,7 @@ static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
 		cpu_relax();
 	}
 }
+#endif /* CONFIG_QUEUED_SPINLOCKS */
 
 /*
  * Read-write spinlocks, allowing multiple readers
diff --git a/arch/x86/include/asm/spinlock_types.h b/arch/x86/include/asm/spinlock_types.h
index 5f9d7572d82b..65c3e37f879a 100644
--- a/arch/x86/include/asm/spinlock_types.h
+++ b/arch/x86/include/asm/spinlock_types.h
@@ -23,6 +23,9 @@ typedef u32 __ticketpair_t;
 
 #define TICKET_SHIFT	(sizeof(__ticket_t) * 8)
 
+#ifdef CONFIG_QUEUED_SPINLOCKS
+#include <asm-generic/qspinlock_types.h>
+#else
 typedef struct arch_spinlock {
 	union {
 		__ticketpair_t head_tail;
@@ -33,6 +36,7 @@ typedef struct arch_spinlock {
 } arch_spinlock_t;
 
 #define __ARCH_SPIN_LOCK_UNLOCKED	{ { 0 } }
+#endif /* CONFIG_QUEUED_SPINLOCKS */
 
 #include <asm-generic/qrwlock_types.h>
 
diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h
index 6a998598f172..c2e00bb2a136 100644
--- a/arch/x86/include/asm/stackprotector.h
+++ b/arch/x86/include/asm/stackprotector.h
@@ -39,7 +39,9 @@
 #include <asm/processor.h>
 #include <asm/percpu.h>
 #include <asm/desc.h>
+
 #include <linux/random.h>
+#include <linux/sched.h>
 
 /*
  * 24 byte read-only segment initializer for stack canary.  Linker
diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h
index 552d6c90a6d4..d1793f06854d 100644
--- a/arch/x86/include/asm/suspend_32.h
+++ b/arch/x86/include/asm/suspend_32.h
@@ -7,7 +7,7 @@
 #define _ASM_X86_SUSPEND_32_H
 
 #include <asm/desc.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 
 /* image of the saved processor state */
 struct saved_context {
diff --git a/arch/x86/include/asm/suspend_64.h b/arch/x86/include/asm/suspend_64.h
index bc6232834bab..7ebf0ebe4e68 100644
--- a/arch/x86/include/asm/suspend_64.h
+++ b/arch/x86/include/asm/suspend_64.h
@@ -7,7 +7,7 @@
 #define _ASM_X86_SUSPEND_64_H
 
 #include <asm/desc.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 
 /*
  * Image of the saved processor state, used by the low level ACPI suspend to
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index b4bdec3e9523..225ee545e1a0 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -177,8 +177,6 @@ struct thread_info {
  */
 #ifndef __ASSEMBLY__
 
-DECLARE_PER_CPU(unsigned long, kernel_stack);
-
 static inline struct thread_info *current_thread_info(void)
 {
 	return (struct thread_info *)(current_top_of_stack() - THREAD_SIZE);
@@ -197,9 +195,13 @@ static inline unsigned long current_stack_pointer(void)
 
 #else /* !__ASSEMBLY__ */
 
+#ifdef CONFIG_X86_64
+# define cpu_current_top_of_stack (cpu_tss + TSS_sp0)
+#endif
+
 /* Load thread_info address into "reg" */
 #define GET_THREAD_INFO(reg) \
-	_ASM_MOV PER_CPU_VAR(kernel_stack),reg ; \
+	_ASM_MOV PER_CPU_VAR(cpu_current_top_of_stack),reg ; \
 	_ASM_SUB $(THREAD_SIZE),reg ;
 
 /*
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 0e8f04f2c26f..0fb46482dfde 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -26,7 +26,7 @@
 #define _ASM_X86_TOPOLOGY_H
 
 #ifdef CONFIG_X86_32
-# ifdef CONFIG_X86_HT
+# ifdef CONFIG_SMP
 #  define ENABLE_TOPO_DEFINES
 # endif
 #else
@@ -124,7 +124,7 @@ extern const struct cpumask *cpu_coregroup_mask(int cpu);
 
 #ifdef ENABLE_TOPO_DEFINES
 #define topology_core_cpumask(cpu)		(per_cpu(cpu_core_map, cpu))
-#define topology_thread_cpumask(cpu)		(per_cpu(cpu_sibling_map, cpu))
+#define topology_sibling_cpumask(cpu)		(per_cpu(cpu_sibling_map, cpu))
 #endif
 
 static inline void arch_fix_phys_package_id(int num, u32 slot)
diff --git a/arch/x86/include/asm/trace/irq_vectors.h b/arch/x86/include/asm/trace/irq_vectors.h
index 4cab890007a7..38a09a13a9bc 100644
--- a/arch/x86/include/asm/trace/irq_vectors.h
+++ b/arch/x86/include/asm/trace/irq_vectors.h
@@ -101,6 +101,12 @@ DEFINE_IRQ_VECTOR_EVENT(call_function_single);
 DEFINE_IRQ_VECTOR_EVENT(threshold_apic);
 
 /*
+ * deferred_error_apic - called when entering/exiting a deferred apic interrupt
+ * vector handler
+ */
+DEFINE_IRQ_VECTOR_EVENT(deferred_error_apic);
+
+/*
  * thermal_apic - called when entering/exiting a thermal apic interrupt
  * vector handler
  */
diff --git a/arch/x86/include/asm/trace/mpx.h b/arch/x86/include/asm/trace/mpx.h
new file mode 100644
index 000000000000..173dd3ba108c
--- /dev/null
+++ b/arch/x86/include/asm/trace/mpx.h
@@ -0,0 +1,132 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM mpx
+
+#if !defined(_TRACE_MPX_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_MPX_H
+
+#include <linux/tracepoint.h>
+
+#ifdef CONFIG_X86_INTEL_MPX
+
+TRACE_EVENT(mpx_bounds_register_exception,
+
+	TP_PROTO(void *addr_referenced,
+		 const struct bndreg *bndreg),
+	TP_ARGS(addr_referenced, bndreg),
+
+	TP_STRUCT__entry(
+		__field(void *, addr_referenced)
+		__field(u64, lower_bound)
+		__field(u64, upper_bound)
+	),
+
+	TP_fast_assign(
+		__entry->addr_referenced = addr_referenced;
+		__entry->lower_bound = bndreg->lower_bound;
+		__entry->upper_bound = bndreg->upper_bound;
+	),
+	/*
+	 * Note that we are printing out the '~' of the upper
+	 * bounds register here.  It is actually stored in its
+	 * one's complement form so that its 'init' state
+	 * corresponds to all 0's.  But, that looks like
+	 * gibberish when printed out, so print out the 1's
+	 * complement instead of the actual value here.  Note
+	 * though that you still need to specify filters for the
+	 * actual value, not the displayed one.
+	 */
+	TP_printk("address referenced: 0x%p bounds: lower: 0x%llx ~upper: 0x%llx",
+		__entry->addr_referenced,
+		__entry->lower_bound,
+		~__entry->upper_bound
+	)
+);
+
+TRACE_EVENT(bounds_exception_mpx,
+
+	TP_PROTO(const struct bndcsr *bndcsr),
+	TP_ARGS(bndcsr),
+
+	TP_STRUCT__entry(
+		__field(u64, bndcfgu)
+		__field(u64, bndstatus)
+	),
+
+	TP_fast_assign(
+		/* need to get rid of the 'const' on bndcsr */
+		__entry->bndcfgu   = (u64)bndcsr->bndcfgu;
+		__entry->bndstatus = (u64)bndcsr->bndstatus;
+	),
+
+	TP_printk("bndcfgu:0x%llx bndstatus:0x%llx",
+		__entry->bndcfgu,
+		__entry->bndstatus)
+);
+
+DECLARE_EVENT_CLASS(mpx_range_trace,
+
+	TP_PROTO(unsigned long start,
+		 unsigned long end),
+	TP_ARGS(start, end),
+
+	TP_STRUCT__entry(
+		__field(unsigned long, start)
+		__field(unsigned long, end)
+	),
+
+	TP_fast_assign(
+		__entry->start = start;
+		__entry->end   = end;
+	),
+
+	TP_printk("[0x%p:0x%p]",
+		(void *)__entry->start,
+		(void *)__entry->end
+	)
+);
+
+DEFINE_EVENT(mpx_range_trace, mpx_unmap_zap,
+	TP_PROTO(unsigned long start, unsigned long end),
+	TP_ARGS(start, end)
+);
+
+DEFINE_EVENT(mpx_range_trace, mpx_unmap_search,
+	TP_PROTO(unsigned long start, unsigned long end),
+	TP_ARGS(start, end)
+);
+
+TRACE_EVENT(mpx_new_bounds_table,
+
+	TP_PROTO(unsigned long table_vaddr),
+	TP_ARGS(table_vaddr),
+
+	TP_STRUCT__entry(
+		__field(unsigned long, table_vaddr)
+	),
+
+	TP_fast_assign(
+		__entry->table_vaddr = table_vaddr;
+	),
+
+	TP_printk("table vaddr:%p", (void *)__entry->table_vaddr)
+);
+
+#else
+
+/*
+ * This gets used outside of MPX-specific code, so we need a stub.
+ */
+static inline void trace_bounds_exception_mpx(const struct bndcsr *bndcsr)
+{
+}
+
+#endif /* CONFIG_X86_INTEL_MPX */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH asm/trace/
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE mpx
+#endif /* _TRACE_MPX_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index 4e49d7dff78e..c5380bea2a36 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -108,7 +108,8 @@ extern int panic_on_unrecovered_nmi;
 void math_emulate(struct math_emu_info *);
 #ifndef CONFIG_X86_32
 asmlinkage void smp_thermal_interrupt(void);
-asmlinkage void mce_threshold_interrupt(void);
+asmlinkage void smp_threshold_interrupt(void);
+asmlinkage void smp_deferred_error_interrupt(void);
 #endif
 
 extern enum ctx_state ist_enter(struct pt_regs *regs);
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index ace9dec050b1..a8df874f3e88 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -74,7 +74,8 @@ static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size, un
  * @addr: User space pointer to start of block to check
  * @size: Size of block to check
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Checks if a pointer to a block of memory in user space is valid.
  *
@@ -145,7 +146,8 @@ __typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL))
  * @x:   Variable to store result.
  * @ptr: Source address, in user space.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple variable from user space to kernel
  * space.  It supports simple types like char and int, but not larger
@@ -240,7 +242,8 @@ extern void __put_user_8(void);
  * @x:   Value to copy to user space.
  * @ptr: Destination address, in user space.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple value from kernel space to user
  * space.  It supports simple types like char and int, but not larger
@@ -455,7 +458,8 @@ struct __large_struct { unsigned long buf[100]; };
  * @x:   Variable to store result.
  * @ptr: Source address, in user space.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple variable from user space to kernel
  * space.  It supports simple types like char and int, but not larger
@@ -479,7 +483,8 @@ struct __large_struct { unsigned long buf[100]; };
  * @x:   Value to copy to user space.
  * @ptr: Destination address, in user space.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple value from kernel space to user
  * space.  It supports simple types like char and int, but not larger
diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h
index 3c03a5de64d3..f5dcb5204dcd 100644
--- a/arch/x86/include/asm/uaccess_32.h
+++ b/arch/x86/include/asm/uaccess_32.h
@@ -59,6 +59,10 @@ __copy_to_user_inatomic(void __user *to, const void *from, unsigned long n)
 			__put_user_size(*(u32 *)from, (u32 __user *)to,
 					4, ret, 4);
 			return ret;
+		case 8:
+			__put_user_size(*(u64 *)from, (u64 __user *)to,
+					8, ret, 8);
+			return ret;
 		}
 	}
 	return __copy_to_user_ll(to, from, n);
@@ -70,7 +74,8 @@ __copy_to_user_inatomic(void __user *to, const void *from, unsigned long n)
  * @from: Source address, in kernel space.
  * @n:    Number of bytes to copy.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Copy data from kernel space to user space.  Caller must check
  * the specified block with access_ok() before calling this function.
@@ -117,7 +122,8 @@ __copy_from_user_inatomic(void *to, const void __user *from, unsigned long n)
  * @from: Source address, in user space.
  * @n:    Number of bytes to copy.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Copy data from user space to kernel space.  Caller must check
  * the specified block with access_ok() before calling this function.
diff --git a/arch/x86/include/asm/user.h b/arch/x86/include/asm/user.h
index ccab4af1646d..59a54e869f15 100644
--- a/arch/x86/include/asm/user.h
+++ b/arch/x86/include/asm/user.h
@@ -14,8 +14,8 @@ struct user_ymmh_regs {
 	__u32 ymmh_space[64];
 };
 
-struct user_xsave_hdr {
-	__u64 xstate_bv;
+struct user_xstate_header {
+	__u64 xfeatures;
 	__u64 reserved1[2];
 	__u64 reserved2[5];
 };
@@ -41,11 +41,11 @@ struct user_xsave_hdr {
  * particular process/thread.
  *
  * Also when the user modifies certain state FP/SSE/etc through the
- * ptrace interface, they must ensure that the xsave_hdr.xstate_bv
+ * ptrace interface, they must ensure that the header.xfeatures
  * bytes[512..519] of the memory layout are updated correspondingly.
  * i.e., for example when FP state is modified to a non-init state,
- * xsave_hdr.xstate_bv's bit 0 must be set to '1', when SSE is modified to
- * non-init state, xsave_hdr.xstate_bv's bit 1 must to be set to '1', etc.
+ * header.xfeatures's bit 0 must be set to '1', when SSE is modified to
+ * non-init state, header.xfeatures's bit 1 must to be set to '1', etc.
  */
 #define USER_XSTATE_FX_SW_WORDS 6
 #define USER_XSTATE_XCR0_WORD	0
@@ -55,7 +55,7 @@ struct user_xstateregs {
 		__u64 fpx_space[58];
 		__u64 xstate_fx_sw[USER_XSTATE_FX_SW_WORDS];
 	} i387;
-	struct user_xsave_hdr xsave_hdr;
+	struct user_xstate_header header;
 	struct user_ymmh_regs ymmh;
 	/* further processor state extensions go here */
 };
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index f58a9c7a3c86..48d34d28f5a6 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -171,38 +171,17 @@ struct x86_platform_ops {
 };
 
 struct pci_dev;
-struct msi_msg;
 
 struct x86_msi_ops {
 	int (*setup_msi_irqs)(struct pci_dev *dev, int nvec, int type);
-	void (*compose_msi_msg)(struct pci_dev *dev, unsigned int irq,
-				unsigned int dest, struct msi_msg *msg,
-			       u8 hpet_id);
 	void (*teardown_msi_irq)(unsigned int irq);
 	void (*teardown_msi_irqs)(struct pci_dev *dev);
 	void (*restore_msi_irqs)(struct pci_dev *dev);
-	int  (*setup_hpet_msi)(unsigned int irq, unsigned int id);
 };
 
-struct IO_APIC_route_entry;
-struct io_apic_irq_attr;
-struct irq_data;
-struct cpumask;
-
 struct x86_io_apic_ops {
-	void		(*init)   (void);
 	unsigned int	(*read)   (unsigned int apic, unsigned int reg);
-	void		(*write)  (unsigned int apic, unsigned int reg, unsigned int value);
-	void		(*modify) (unsigned int apic, unsigned int reg, unsigned int value);
 	void		(*disable)(void);
-	void		(*print_entries)(unsigned int apic, unsigned int nr_entries);
-	int		(*set_affinity)(struct irq_data *data,
-					const struct cpumask *mask,
-					bool force);
-	int		(*setup_entry)(int irq, struct IO_APIC_route_entry *entry,
-				       unsigned int destination, int vector,
-				       struct io_apic_irq_attr *attr);
-	void		(*eoi_ioapic_pin)(int apic, int pin, int vector);
 };
 
 extern struct x86_init_ops x86_init;
diff --git a/arch/x86/include/asm/xcr.h b/arch/x86/include/asm/xcr.h
deleted file mode 100644
index f2cba4e79a23..000000000000
--- a/arch/x86/include/asm/xcr.h
+++ /dev/null
@@ -1,49 +0,0 @@
-/* -*- linux-c -*- ------------------------------------------------------- *
- *
- *   Copyright 2008 rPath, Inc. - All Rights Reserved
- *
- *   This file is part of the Linux kernel, and is made available under
- *   the terms of the GNU General Public License version 2 or (at your
- *   option) any later version; incorporated herein by reference.
- *
- * ----------------------------------------------------------------------- */
-
-/*
- * asm-x86/xcr.h
- *
- * Definitions for the eXtended Control Register instructions
- */
-
-#ifndef _ASM_X86_XCR_H
-#define _ASM_X86_XCR_H
-
-#define XCR_XFEATURE_ENABLED_MASK	0x00000000
-
-#ifdef __KERNEL__
-# ifndef __ASSEMBLY__
-
-#include <linux/types.h>
-
-static inline u64 xgetbv(u32 index)
-{
-	u32 eax, edx;
-
-	asm volatile(".byte 0x0f,0x01,0xd0" /* xgetbv */
-		     : "=a" (eax), "=d" (edx)
-		     : "c" (index));
-	return eax + ((u64)edx << 32);
-}
-
-static inline void xsetbv(u32 index, u64 value)
-{
-	u32 eax = value;
-	u32 edx = value >> 32;
-
-	asm volatile(".byte 0x0f,0x01,0xd1" /* xsetbv */
-		     : : "a" (eax), "d" (edx), "c" (index));
-}
-
-# endif /* __ASSEMBLY__ */
-#endif /* __KERNEL__ */
-
-#endif /* _ASM_X86_XCR_H */
diff --git a/arch/x86/include/asm/xor.h b/arch/x86/include/asm/xor.h
index d8829751b3f8..1f5c5161ead6 100644
--- a/arch/x86/include/asm/xor.h
+++ b/arch/x86/include/asm/xor.h
@@ -36,7 +36,7 @@
  * no advantages to be gotten from x86-64 here anyways.
  */
 
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 
 #ifdef CONFIG_X86_32
 /* reduce register pressure */
diff --git a/arch/x86/include/asm/xor_32.h b/arch/x86/include/asm/xor_32.h
index ce05722e3c68..5a08bc8bff33 100644
--- a/arch/x86/include/asm/xor_32.h
+++ b/arch/x86/include/asm/xor_32.h
@@ -26,7 +26,7 @@
 #define XO3(x, y)	"       pxor   8*("#x")(%4), %%mm"#y"   ;\n"
 #define XO4(x, y)	"       pxor   8*("#x")(%5), %%mm"#y"   ;\n"
 
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 
 static void
 xor_pII_mmx_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
diff --git a/arch/x86/include/asm/xor_avx.h b/arch/x86/include/asm/xor_avx.h
index 492b29802f57..7c0a517ec751 100644
--- a/arch/x86/include/asm/xor_avx.h
+++ b/arch/x86/include/asm/xor_avx.h
@@ -18,7 +18,7 @@
 #ifdef CONFIG_AS_AVX
 
 #include <linux/compiler.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 
 #define BLOCK4(i) \
 		BLOCK(32 * i, 0) \
diff --git a/arch/x86/include/asm/xsave.h b/arch/x86/include/asm/xsave.h
deleted file mode 100644
index c9a6d68b8d62..000000000000
--- a/arch/x86/include/asm/xsave.h
+++ /dev/null
@@ -1,257 +0,0 @@
-#ifndef __ASM_X86_XSAVE_H
-#define __ASM_X86_XSAVE_H
-
-#include <linux/types.h>
-#include <asm/processor.h>
-
-#define XSTATE_CPUID		0x0000000d
-
-#define XSTATE_FP		0x1
-#define XSTATE_SSE		0x2
-#define XSTATE_YMM		0x4
-#define XSTATE_BNDREGS		0x8
-#define XSTATE_BNDCSR		0x10
-#define XSTATE_OPMASK		0x20
-#define XSTATE_ZMM_Hi256	0x40
-#define XSTATE_Hi16_ZMM		0x80
-
-#define XSTATE_FPSSE	(XSTATE_FP | XSTATE_SSE)
-#define XSTATE_AVX512	(XSTATE_OPMASK | XSTATE_ZMM_Hi256 | XSTATE_Hi16_ZMM)
-/* Bit 63 of XCR0 is reserved for future expansion */
-#define XSTATE_EXTEND_MASK	(~(XSTATE_FPSSE | (1ULL << 63)))
-
-#define FXSAVE_SIZE	512
-
-#define XSAVE_HDR_SIZE	    64
-#define XSAVE_HDR_OFFSET    FXSAVE_SIZE
-
-#define XSAVE_YMM_SIZE	    256
-#define XSAVE_YMM_OFFSET    (XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET)
-
-/* Supported features which support lazy state saving */
-#define XSTATE_LAZY	(XSTATE_FP | XSTATE_SSE | XSTATE_YMM		      \
-			| XSTATE_OPMASK | XSTATE_ZMM_Hi256 | XSTATE_Hi16_ZMM)
-
-/* Supported features which require eager state saving */
-#define XSTATE_EAGER	(XSTATE_BNDREGS | XSTATE_BNDCSR)
-
-/* All currently supported features */
-#define XCNTXT_MASK	(XSTATE_LAZY | XSTATE_EAGER)
-
-#ifdef CONFIG_X86_64
-#define REX_PREFIX	"0x48, "
-#else
-#define REX_PREFIX
-#endif
-
-extern unsigned int xstate_size;
-extern u64 pcntxt_mask;
-extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS];
-extern struct xsave_struct *init_xstate_buf;
-
-extern void xsave_init(void);
-extern void update_regset_xstate_info(unsigned int size, u64 xstate_mask);
-extern int init_fpu(struct task_struct *child);
-
-/* These macros all use (%edi)/(%rdi) as the single memory argument. */
-#define XSAVE		".byte " REX_PREFIX "0x0f,0xae,0x27"
-#define XSAVEOPT	".byte " REX_PREFIX "0x0f,0xae,0x37"
-#define XSAVES		".byte " REX_PREFIX "0x0f,0xc7,0x2f"
-#define XRSTOR		".byte " REX_PREFIX "0x0f,0xae,0x2f"
-#define XRSTORS		".byte " REX_PREFIX "0x0f,0xc7,0x1f"
-
-#define xstate_fault	".section .fixup,\"ax\"\n"	\
-			"3:  movl $-1,%[err]\n"		\
-			"    jmp  2b\n"			\
-			".previous\n"			\
-			_ASM_EXTABLE(1b, 3b)		\
-			: [err] "=r" (err)
-
-/*
- * This function is called only during boot time when x86 caps are not set
- * up and alternative can not be used yet.
- */
-static inline int xsave_state_booting(struct xsave_struct *fx, u64 mask)
-{
-	u32 lmask = mask;
-	u32 hmask = mask >> 32;
-	int err = 0;
-
-	WARN_ON(system_state != SYSTEM_BOOTING);
-
-	if (boot_cpu_has(X86_FEATURE_XSAVES))
-		asm volatile("1:"XSAVES"\n\t"
-			"2:\n\t"
-			     xstate_fault
-			: "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
-			:   "memory");
-	else
-		asm volatile("1:"XSAVE"\n\t"
-			"2:\n\t"
-			     xstate_fault
-			: "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
-			:   "memory");
-	return err;
-}
-
-/*
- * This function is called only during boot time when x86 caps are not set
- * up and alternative can not be used yet.
- */
-static inline int xrstor_state_booting(struct xsave_struct *fx, u64 mask)
-{
-	u32 lmask = mask;
-	u32 hmask = mask >> 32;
-	int err = 0;
-
-	WARN_ON(system_state != SYSTEM_BOOTING);
-
-	if (boot_cpu_has(X86_FEATURE_XSAVES))
-		asm volatile("1:"XRSTORS"\n\t"
-			"2:\n\t"
-			     xstate_fault
-			: "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
-			:   "memory");
-	else
-		asm volatile("1:"XRSTOR"\n\t"
-			"2:\n\t"
-			     xstate_fault
-			: "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
-			:   "memory");
-	return err;
-}
-
-/*
- * Save processor xstate to xsave area.
- */
-static inline int xsave_state(struct xsave_struct *fx, u64 mask)
-{
-	u32 lmask = mask;
-	u32 hmask = mask >> 32;
-	int err = 0;
-
-	/*
-	 * If xsaves is enabled, xsaves replaces xsaveopt because
-	 * it supports compact format and supervisor states in addition to
-	 * modified optimization in xsaveopt.
-	 *
-	 * Otherwise, if xsaveopt is enabled, xsaveopt replaces xsave
-	 * because xsaveopt supports modified optimization which is not
-	 * supported by xsave.
-	 *
-	 * If none of xsaves and xsaveopt is enabled, use xsave.
-	 */
-	alternative_input_2(
-		"1:"XSAVE,
-		XSAVEOPT,
-		X86_FEATURE_XSAVEOPT,
-		XSAVES,
-		X86_FEATURE_XSAVES,
-		[fx] "D" (fx), "a" (lmask), "d" (hmask) :
-		"memory");
-	asm volatile("2:\n\t"
-		     xstate_fault
-		     : "0" (0)
-		     : "memory");
-
-	return err;
-}
-
-/*
- * Restore processor xstate from xsave area.
- */
-static inline int xrstor_state(struct xsave_struct *fx, u64 mask)
-{
-	int err = 0;
-	u32 lmask = mask;
-	u32 hmask = mask >> 32;
-
-	/*
-	 * Use xrstors to restore context if it is enabled. xrstors supports
-	 * compacted format of xsave area which is not supported by xrstor.
-	 */
-	alternative_input(
-		"1: " XRSTOR,
-		XRSTORS,
-		X86_FEATURE_XSAVES,
-		"D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
-		: "memory");
-
-	asm volatile("2:\n"
-		     xstate_fault
-		     : "0" (0)
-		     : "memory");
-
-	return err;
-}
-
-/*
- * Save xstate context for old process during context switch.
- */
-static inline void fpu_xsave(struct fpu *fpu)
-{
-	xsave_state(&fpu->state->xsave, -1);
-}
-
-/*
- * Restore xstate context for new process during context switch.
- */
-static inline int fpu_xrstor_checking(struct xsave_struct *fx)
-{
-	return xrstor_state(fx, -1);
-}
-
-/*
- * Save xstate to user space xsave area.
- *
- * We don't use modified optimization because xrstor/xrstors might track
- * a different application.
- *
- * We don't use compacted format xsave area for
- * backward compatibility for old applications which don't understand
- * compacted format of xsave area.
- */
-static inline int xsave_user(struct xsave_struct __user *buf)
-{
-	int err;
-
-	/*
-	 * Clear the xsave header first, so that reserved fields are
-	 * initialized to zero.
-	 */
-	err = __clear_user(&buf->xsave_hdr, sizeof(buf->xsave_hdr));
-	if (unlikely(err))
-		return -EFAULT;
-
-	__asm__ __volatile__(ASM_STAC "\n"
-			     "1:"XSAVE"\n"
-			     "2: " ASM_CLAC "\n"
-			     xstate_fault
-			     : "D" (buf), "a" (-1), "d" (-1), "0" (0)
-			     : "memory");
-	return err;
-}
-
-/*
- * Restore xstate from user space xsave area.
- */
-static inline int xrestore_user(struct xsave_struct __user *buf, u64 mask)
-{
-	int err = 0;
-	struct xsave_struct *xstate = ((__force struct xsave_struct *)buf);
-	u32 lmask = mask;
-	u32 hmask = mask >> 32;
-
-	__asm__ __volatile__(ASM_STAC "\n"
-			     "1:"XRSTOR"\n"
-			     "2: " ASM_CLAC "\n"
-			     xstate_fault
-			     : "D" (xstate), "a" (lmask), "d" (hmask), "0" (0)
-			     : "memory");	/* memory required? */
-	return err;
-}
-
-void *get_xsave_addr(struct xsave_struct *xsave, int xstate);
-void setup_xstate_comp(void);
-
-#endif
diff --git a/arch/x86/include/uapi/asm/msr.h b/arch/x86/include/uapi/asm/msr.h
index 155e51048fa4..c41f4fe25483 100644
--- a/arch/x86/include/uapi/asm/msr.h
+++ b/arch/x86/include/uapi/asm/msr.h
@@ -1,8 +1,6 @@
 #ifndef _UAPI_ASM_X86_MSR_H
 #define _UAPI_ASM_X86_MSR_H
 
-#include <asm/msr-index.h>
-
 #ifndef __ASSEMBLY__
 
 #include <linux/types.h>
diff --git a/arch/x86/include/uapi/asm/mtrr.h b/arch/x86/include/uapi/asm/mtrr.h
index d0acb658c8f4..7528dcf59691 100644
--- a/arch/x86/include/uapi/asm/mtrr.h
+++ b/arch/x86/include/uapi/asm/mtrr.h
@@ -103,7 +103,7 @@ struct mtrr_state_type {
 #define MTRRIOC_GET_PAGE_ENTRY   _IOWR(MTRR_IOCTL_BASE, 8, struct mtrr_gentry)
 #define MTRRIOC_KILL_PAGE_ENTRY  _IOW(MTRR_IOCTL_BASE,  9, struct mtrr_sentry)
 
-/*  These are the region types  */
+/* MTRR memory types, which are defined in SDM */
 #define MTRR_TYPE_UNCACHABLE 0
 #define MTRR_TYPE_WRCOMB     1
 /*#define MTRR_TYPE_         2*/
@@ -113,5 +113,11 @@ struct mtrr_state_type {
 #define MTRR_TYPE_WRBACK     6
 #define MTRR_NUM_TYPES       7
 
+/*
+ * Invalid MTRR memory type.  mtrr_type_lookup() returns this value when
+ * MTRRs are disabled.  Note, this value is allocated from the reserved
+ * values (0x7-0xff) of the MTRR memory types.
+ */
+#define MTRR_TYPE_INVALID    0xff
 
 #endif /* _UAPI_ASM_X86_MTRR_H */
diff --git a/arch/x86/include/uapi/asm/sigcontext.h b/arch/x86/include/uapi/asm/sigcontext.h
index 16dc4e8a2cd3..0e8a973de9ee 100644
--- a/arch/x86/include/uapi/asm/sigcontext.h
+++ b/arch/x86/include/uapi/asm/sigcontext.h
@@ -25,7 +25,7 @@ struct _fpx_sw_bytes {
 	__u32 extended_size;	/* total size of the layout referred by
 				 * fpstate pointer in the sigcontext.
 				 */
-	__u64 xstate_bv;
+	__u64 xfeatures;
 				/* feature bit mask (including fp/sse/extended
 				 * state) that is present in the memory
 				 * layout.
@@ -209,8 +209,8 @@ struct sigcontext {
 
 #endif /* !__i386__ */
 
-struct _xsave_hdr {
-	__u64 xstate_bv;
+struct _header {
+	__u64 xfeatures;
 	__u64 reserved1[2];
 	__u64 reserved2[5];
 };
@@ -228,7 +228,7 @@ struct _ymmh_state {
  */
 struct _xstate {
 	struct _fpstate fpstate;
-	struct _xsave_hdr xstate_hdr;
+	struct _header xstate_hdr;
 	struct _ymmh_state ymmh;
 	/* new processor state extensions go here */
 };
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 9bcd0b56ca17..0f15af41bd80 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -22,7 +22,7 @@ KASAN_SANITIZE_dumpstack_$(BITS).o := n
 
 CFLAGS_irq.o := -I$(src)/../include/asm/trace
 
-obj-y			:= process_$(BITS).o signal.o entry_$(BITS).o
+obj-y			:= process_$(BITS).o signal.o
 obj-y			+= traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o
 obj-y			+= time.o ioport.o ldt.o dumpstack.o nmi.o
 obj-y			+= setup.o x86_init.o i8259.o irqinit.o jump_label.o
@@ -31,9 +31,6 @@ obj-y			+= probe_roms.o
 obj-$(CONFIG_X86_32)	+= i386_ksyms_32.o
 obj-$(CONFIG_X86_64)	+= sys_x86_64.o x8664_ksyms_64.o
 obj-$(CONFIG_X86_64)	+= mcount_64.o
-obj-y			+= syscall_$(BITS).o vsyscall_gtod.o
-obj-$(CONFIG_IA32_EMULATION)	+= syscall_32.o
-obj-$(CONFIG_X86_VSYSCALL_EMULATION)	+= vsyscall_64.o vsyscall_emu_64.o
 obj-$(CONFIG_X86_ESPFIX64)	+= espfix_64.o
 obj-$(CONFIG_SYSFS)	+= ksysfs.o
 obj-y			+= bootflag.o e820.o
@@ -44,7 +41,7 @@ obj-y			+= pci-iommu_table.o
 obj-y			+= resource.o
 
 obj-y				+= process.o
-obj-y				+= i387.o xsave.o
+obj-y				+= fpu/
 obj-y				+= ptrace.o
 obj-$(CONFIG_X86_32)		+= tls.o
 obj-$(CONFIG_IA32_EMULATION)	+= tls.o
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index dbe76a14c3c9..e49ee24da85e 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -31,12 +31,12 @@
 #include <linux/module.h>
 #include <linux/dmi.h>
 #include <linux/irq.h>
-#include <linux/irqdomain.h>
 #include <linux/slab.h>
 #include <linux/bootmem.h>
 #include <linux/ioport.h>
 #include <linux/pci.h>
 
+#include <asm/irqdomain.h>
 #include <asm/pci_x86.h>
 #include <asm/pgtable.h>
 #include <asm/io_apic.h>
@@ -400,57 +400,13 @@ static int mp_config_acpi_gsi(struct device *dev, u32 gsi, int trigger,
 	return 0;
 }
 
-static int mp_register_gsi(struct device *dev, u32 gsi, int trigger,
-			   int polarity)
-{
-	int irq, node;
-
-	if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC)
-		return gsi;
-
-	trigger = trigger == ACPI_EDGE_SENSITIVE ? 0 : 1;
-	polarity = polarity == ACPI_ACTIVE_HIGH ? 0 : 1;
-	node = dev ? dev_to_node(dev) : NUMA_NO_NODE;
-	if (mp_set_gsi_attr(gsi, trigger, polarity, node)) {
-		pr_warn("Failed to set pin attr for GSI%d\n", gsi);
-		return -1;
-	}
-
-	irq = mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC);
-	if (irq < 0)
-		return irq;
-
-	/* Don't set up the ACPI SCI because it's already set up */
-	if (enable_update_mptable && acpi_gbl_FADT.sci_interrupt != gsi)
-		mp_config_acpi_gsi(dev, gsi, trigger, polarity);
-
-	return irq;
-}
-
-static void mp_unregister_gsi(u32 gsi)
-{
-	int irq;
-
-	if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC)
-		return;
-
-	irq = mp_map_gsi_to_irq(gsi, 0);
-	if (irq > 0)
-		mp_unmap_irq(irq);
-}
-
-static struct irq_domain_ops acpi_irqdomain_ops = {
-	.map = mp_irqdomain_map,
-	.unmap = mp_irqdomain_unmap,
-};
-
 static int __init
 acpi_parse_ioapic(struct acpi_subtable_header * header, const unsigned long end)
 {
 	struct acpi_madt_io_apic *ioapic = NULL;
 	struct ioapic_domain_cfg cfg = {
 		.type = IOAPIC_DOMAIN_DYNAMIC,
-		.ops = &acpi_irqdomain_ops,
+		.ops = &mp_ioapic_irqdomain_ops,
 	};
 
 	ioapic = (struct acpi_madt_io_apic *)header;
@@ -652,7 +608,7 @@ static int acpi_register_gsi_pic(struct device *dev, u32 gsi,
 	 * Make sure all (legacy) PCI IRQs are set as level-triggered.
 	 */
 	if (trigger == ACPI_LEVEL_SENSITIVE)
-		eisa_set_level_irq(gsi);
+		elcr_set_level_irq(gsi);
 #endif
 
 	return gsi;
@@ -663,10 +619,21 @@ static int acpi_register_gsi_ioapic(struct device *dev, u32 gsi,
 				    int trigger, int polarity)
 {
 	int irq = gsi;
-
 #ifdef CONFIG_X86_IO_APIC
+	int node;
+	struct irq_alloc_info info;
+
+	node = dev ? dev_to_node(dev) : NUMA_NO_NODE;
+	trigger = trigger == ACPI_EDGE_SENSITIVE ? 0 : 1;
+	polarity = polarity == ACPI_ACTIVE_HIGH ? 0 : 1;
+	ioapic_set_alloc_attr(&info, node, trigger, polarity);
+
 	mutex_lock(&acpi_ioapic_lock);
-	irq = mp_register_gsi(dev, gsi, trigger, polarity);
+	irq = mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC, &info);
+	/* Don't set up the ACPI SCI because it's already set up */
+	if (irq >= 0 && enable_update_mptable &&
+	    acpi_gbl_FADT.sci_interrupt != gsi)
+		mp_config_acpi_gsi(dev, gsi, trigger, polarity);
 	mutex_unlock(&acpi_ioapic_lock);
 #endif
 
@@ -676,8 +643,12 @@ static int acpi_register_gsi_ioapic(struct device *dev, u32 gsi,
 static void acpi_unregister_gsi_ioapic(u32 gsi)
 {
 #ifdef CONFIG_X86_IO_APIC
+	int irq;
+
 	mutex_lock(&acpi_ioapic_lock);
-	mp_unregister_gsi(gsi);
+	irq = mp_map_gsi_to_irq(gsi, 0, NULL);
+	if (irq > 0)
+		mp_unmap_irq(irq);
 	mutex_unlock(&acpi_ioapic_lock);
 #endif
 }
@@ -786,7 +757,7 @@ int acpi_register_ioapic(acpi_handle handle, u64 phys_addr, u32 gsi_base)
 	u64 addr;
 	struct ioapic_domain_cfg cfg = {
 		.type = IOAPIC_DOMAIN_DYNAMIC,
-		.ops = &acpi_irqdomain_ops,
+		.ops = &mp_ioapic_irqdomain_ops,
 	};
 
 	ioapic_id = acpi_get_ioapic_id(handle, gsi_base, &addr);
diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S
index ae693b51ed8e..8c35df468104 100644
--- a/arch/x86/kernel/acpi/wakeup_64.S
+++ b/arch/x86/kernel/acpi/wakeup_64.S
@@ -62,7 +62,7 @@ ENTRY(do_suspend_lowlevel)
 	pushfq
 	popq	pt_regs_flags(%rax)
 
-	movq	$resume_point, saved_rip(%rip)
+	movq	$.Lresume_point, saved_rip(%rip)
 
 	movq	%rsp, saved_rsp
 	movq	%rbp, saved_rbp
@@ -75,10 +75,10 @@ ENTRY(do_suspend_lowlevel)
 	xorl	%eax, %eax
 	call	x86_acpi_enter_sleep_state
 	/* in case something went wrong, restore the machine status and go on */
-	jmp	resume_point
+	jmp	.Lresume_point
 
 	.align 4
-resume_point:
+.Lresume_point:
 	/* We don't restore %rax, it must be 0 anyway */
 	movq	$saved_context, %rax
 	movq	saved_context_cr4(%rax), %rbx
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index aef653193160..c42827eb86cf 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -21,6 +21,10 @@
 #include <asm/io.h>
 #include <asm/fixmap.h>
 
+int __read_mostly alternatives_patched;
+
+EXPORT_SYMBOL_GPL(alternatives_patched);
+
 #define MAX_PATCH_LEN (255-1)
 
 static int __initdata_or_module debug_alternative;
@@ -227,6 +231,15 @@ void __init arch_init_ideal_nops(void)
 #endif
 		}
 		break;
+
+	case X86_VENDOR_AMD:
+		if (boot_cpu_data.x86 > 0xf) {
+			ideal_nops = p6_nops;
+			return;
+		}
+
+		/* fall through */
+
 	default:
 #ifdef CONFIG_X86_64
 		ideal_nops = k8_nops;
@@ -627,6 +640,7 @@ void __init alternative_instructions(void)
 	apply_paravirt(__parainstructions, __parainstructions_end);
 
 	restart_nmi();
+	alternatives_patched = 1;
 }
 
 /**
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index 5caed1dd7ccf..29fa475ec518 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -89,9 +89,7 @@ int amd_cache_northbridges(void)
 			next_northbridge(link, amd_nb_link_ids);
 	}
 
-	/* GART present only on Fam15h upto model 0fh */
-	if (boot_cpu_data.x86 == 0xf || boot_cpu_data.x86 == 0x10 ||
-	    (boot_cpu_data.x86 == 0x15 && boot_cpu_data.x86_model < 0x10))
+	if (amd_gart_present())
 		amd_northbridges.flags |= AMD_NB_GART;
 
 	/*
diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c
index 6a7c23ff21d3..ede92c3364d3 100644
--- a/arch/x86/kernel/apb_timer.c
+++ b/arch/x86/kernel/apb_timer.c
@@ -171,10 +171,6 @@ static int __init apbt_clockevent_register(void)
 
 static void apbt_setup_irq(struct apbt_dev *adev)
 {
-	/* timer0 irq has been setup early */
-	if (adev->irq == 0)
-		return;
-
 	irq_modify_status(adev->irq, 0, IRQ_MOVE_PCNTXT);
 	irq_set_affinity(adev->irq, cpumask_of(adev->cpu));
 }
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index 76164e173a24..6e85f713641d 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -262,6 +262,9 @@ void __init early_gart_iommu_check(void)
 	u64 aper_base = 0, last_aper_base = 0;
 	int aper_enabled = 0, last_aper_enabled = 0, last_valid = 0;
 
+	if (!amd_gart_present())
+		return;
+
 	if (!early_pci_allowed())
 		return;
 
@@ -355,6 +358,9 @@ int __init gart_iommu_hole_init(void)
 	int fix, slot, valid_agp = 0;
 	int i, node;
 
+	if (!amd_gart_present())
+		return -ENODEV;
+
 	if (gart_iommu_aperture_disabled || !fix_aperture ||
 	    !early_pci_allowed())
 		return -ENODEV;
@@ -452,7 +458,7 @@ out:
 		   force_iommu ||
 		   valid_agp ||
 		   fallback_aper_force) {
-		pr_info("Your BIOS doesn't leave a aperture memory hole\n");
+		pr_info("Your BIOS doesn't leave an aperture memory hole\n");
 		pr_info("Please enable the IOMMU option in the BIOS setup\n");
 		pr_info("This costs you %dMB of RAM\n",
 			32 << fallback_aper_order);
diff --git a/arch/x86/kernel/apic/htirq.c b/arch/x86/kernel/apic/htirq.c
index 816f36e979ad..ae50d3454d78 100644
--- a/arch/x86/kernel/apic/htirq.c
+++ b/arch/x86/kernel/apic/htirq.c
@@ -3,6 +3,8 @@
  *
  * Copyright (C) 1997, 1998, 1999, 2000, 2009 Ingo Molnar, Hajnalka Szabo
  *	Moved from arch/x86/kernel/apic/io_apic.c.
+ * Jiang Liu <jiang.liu@linux.intel.com>
+ *	Add support of hierarchical irqdomain
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -14,78 +16,112 @@
 #include <linux/device.h>
 #include <linux/pci.h>
 #include <linux/htirq.h>
+#include <asm/irqdomain.h>
 #include <asm/hw_irq.h>
 #include <asm/apic.h>
 #include <asm/hypertransport.h>
 
+static struct irq_domain *htirq_domain;
+
 /*
  * Hypertransport interrupt support
  */
-static void target_ht_irq(unsigned int irq, unsigned int dest, u8 vector)
-{
-	struct ht_irq_msg msg;
-
-	fetch_ht_irq_msg(irq, &msg);
-
-	msg.address_lo &= ~(HT_IRQ_LOW_VECTOR_MASK | HT_IRQ_LOW_DEST_ID_MASK);
-	msg.address_hi &= ~(HT_IRQ_HIGH_DEST_ID_MASK);
-
-	msg.address_lo |= HT_IRQ_LOW_VECTOR(vector) | HT_IRQ_LOW_DEST_ID(dest);
-	msg.address_hi |= HT_IRQ_HIGH_DEST_ID(dest);
-
-	write_ht_irq_msg(irq, &msg);
-}
-
 static int
 ht_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force)
 {
-	struct irq_cfg *cfg = irqd_cfg(data);
-	unsigned int dest;
+	struct irq_data *parent = data->parent_data;
 	int ret;
 
-	ret = apic_set_affinity(data, mask, &dest);
-	if (ret)
-		return ret;
-
-	target_ht_irq(data->irq, dest, cfg->vector);
-	return IRQ_SET_MASK_OK_NOCOPY;
+	ret = parent->chip->irq_set_affinity(parent, mask, force);
+	if (ret >= 0) {
+		struct ht_irq_msg msg;
+		struct irq_cfg *cfg = irqd_cfg(data);
+
+		fetch_ht_irq_msg(data->irq, &msg);
+		msg.address_lo &= ~(HT_IRQ_LOW_VECTOR_MASK |
+				    HT_IRQ_LOW_DEST_ID_MASK);
+		msg.address_lo |= HT_IRQ_LOW_VECTOR(cfg->vector) |
+				  HT_IRQ_LOW_DEST_ID(cfg->dest_apicid);
+		msg.address_hi &= ~(HT_IRQ_HIGH_DEST_ID_MASK);
+		msg.address_hi |= HT_IRQ_HIGH_DEST_ID(cfg->dest_apicid);
+		write_ht_irq_msg(data->irq, &msg);
+	}
+
+	return ret;
 }
 
 static struct irq_chip ht_irq_chip = {
 	.name			= "PCI-HT",
 	.irq_mask		= mask_ht_irq,
 	.irq_unmask		= unmask_ht_irq,
-	.irq_ack		= apic_ack_edge,
+	.irq_ack		= irq_chip_ack_parent,
 	.irq_set_affinity	= ht_set_affinity,
-	.irq_retrigger		= apic_retrigger_irq,
+	.irq_retrigger		= irq_chip_retrigger_hierarchy,
 	.flags			= IRQCHIP_SKIP_SET_WAKE,
 };
 
-int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev)
+static int htirq_domain_alloc(struct irq_domain *domain, unsigned int virq,
+			      unsigned int nr_irqs, void *arg)
 {
-	struct irq_cfg *cfg;
-	struct ht_irq_msg msg;
-	unsigned dest;
-	int err;
+	struct ht_irq_cfg *ht_cfg;
+	struct irq_alloc_info *info = arg;
+	struct pci_dev *dev;
+	irq_hw_number_t hwirq;
+	int ret;
 
-	if (disable_apic)
-		return -ENXIO;
+	if (nr_irqs > 1 || !info)
+		return -EINVAL;
 
-	cfg = irq_cfg(irq);
-	err = assign_irq_vector(irq, cfg, apic->target_cpus());
-	if (err)
-		return err;
+	dev = info->ht_dev;
+	hwirq = (info->ht_idx & 0xFF) |
+		PCI_DEVID(dev->bus->number, dev->devfn) << 8 |
+		(pci_domain_nr(dev->bus) & 0xFFFFFFFF) << 24;
+	if (irq_find_mapping(domain, hwirq) > 0)
+		return -EEXIST;
 
-	err = apic->cpu_mask_to_apicid_and(cfg->domain,
-					   apic->target_cpus(), &dest);
-	if (err)
-		return err;
+	ht_cfg = kmalloc(sizeof(*ht_cfg), GFP_KERNEL);
+	if (!ht_cfg)
+		return -ENOMEM;
 
-	msg.address_hi = HT_IRQ_HIGH_DEST_ID(dest);
+	ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, info);
+	if (ret < 0) {
+		kfree(ht_cfg);
+		return ret;
+	}
+
+	/* Initialize msg to a value that will never match the first write. */
+	ht_cfg->msg.address_lo = 0xffffffff;
+	ht_cfg->msg.address_hi = 0xffffffff;
+	ht_cfg->dev = info->ht_dev;
+	ht_cfg->update = info->ht_update;
+	ht_cfg->pos = info->ht_pos;
+	ht_cfg->idx = 0x10 + (info->ht_idx * 2);
+	irq_domain_set_info(domain, virq, hwirq, &ht_irq_chip, ht_cfg,
+			    handle_edge_irq, ht_cfg, "edge");
+
+	return 0;
+}
+
+static void htirq_domain_free(struct irq_domain *domain, unsigned int virq,
+			      unsigned int nr_irqs)
+{
+	struct irq_data *irq_data = irq_domain_get_irq_data(domain, virq);
+
+	BUG_ON(nr_irqs != 1);
+	kfree(irq_data->chip_data);
+	irq_domain_free_irqs_top(domain, virq, nr_irqs);
+}
 
+static void htirq_domain_activate(struct irq_domain *domain,
+				  struct irq_data *irq_data)
+{
+	struct ht_irq_msg msg;
+	struct irq_cfg *cfg = irqd_cfg(irq_data);
+
+	msg.address_hi = HT_IRQ_HIGH_DEST_ID(cfg->dest_apicid);
 	msg.address_lo =
 		HT_IRQ_LOW_BASE |
-		HT_IRQ_LOW_DEST_ID(dest) |
+		HT_IRQ_LOW_DEST_ID(cfg->dest_apicid) |
 		HT_IRQ_LOW_VECTOR(cfg->vector) |
 		((apic->irq_dest_mode == 0) ?
 			HT_IRQ_LOW_DM_PHYSICAL :
@@ -95,13 +131,56 @@ int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev)
 			HT_IRQ_LOW_MT_FIXED :
 			HT_IRQ_LOW_MT_ARBITRATED) |
 		HT_IRQ_LOW_IRQ_MASKED;
+	write_ht_irq_msg(irq_data->irq, &msg);
+}
 
-	write_ht_irq_msg(irq, &msg);
+static void htirq_domain_deactivate(struct irq_domain *domain,
+				    struct irq_data *irq_data)
+{
+	struct ht_irq_msg msg;
 
-	irq_set_chip_and_handler_name(irq, &ht_irq_chip,
-				      handle_edge_irq, "edge");
+	memset(&msg, 0, sizeof(msg));
+	write_ht_irq_msg(irq_data->irq, &msg);
+}
 
-	dev_dbg(&dev->dev, "irq %d for HT\n", irq);
+static const struct irq_domain_ops htirq_domain_ops = {
+	.alloc		= htirq_domain_alloc,
+	.free		= htirq_domain_free,
+	.activate	= htirq_domain_activate,
+	.deactivate	= htirq_domain_deactivate,
+};
 
-	return 0;
+void arch_init_htirq_domain(struct irq_domain *parent)
+{
+	if (disable_apic)
+		return;
+
+	htirq_domain = irq_domain_add_tree(NULL, &htirq_domain_ops, NULL);
+	if (!htirq_domain)
+		pr_warn("failed to initialize irqdomain for HTIRQ.\n");
+	else
+		htirq_domain->parent = parent;
+}
+
+int arch_setup_ht_irq(int idx, int pos, struct pci_dev *dev,
+		      ht_irq_update_t *update)
+{
+	struct irq_alloc_info info;
+
+	if (!htirq_domain)
+		return -ENOSYS;
+
+	init_irq_alloc_info(&info, NULL);
+	info.ht_idx = idx;
+	info.ht_pos = pos;
+	info.ht_dev = dev;
+	info.ht_update = update;
+
+	return irq_domain_alloc_irqs(htirq_domain, 1, dev_to_node(&dev->dev),
+				     &info);
+}
+
+void arch_teardown_ht_irq(unsigned int irq)
+{
+	irq_domain_free_irqs(irq, 1);
 }
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index f4dc2462a1ac..845dc0df2002 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -18,6 +18,16 @@
  *					and Rolf G. Tews
  *					for testing these extensively
  *	Paul Diefenbaugh	:	Added full ACPI support
+ *
+ * Historical information which is worth to be preserved:
+ *
+ * - SiS APIC rmw bug:
+ *
+ *	We used to have a workaround for a bug in SiS chips which
+ *	required to rewrite the index register for a read-modify-write
+ *	operation as the chip lost the index information which was
+ *	setup for the read already. We cache the data now, so that
+ *	workaround has been removed.
  */
 
 #include <linux/mm.h>
@@ -31,13 +41,13 @@
 #include <linux/acpi.h>
 #include <linux/module.h>
 #include <linux/syscore_ops.h>
-#include <linux/irqdomain.h>
 #include <linux/freezer.h>
 #include <linux/kthread.h>
 #include <linux/jiffies.h>	/* time_after() */
 #include <linux/slab.h>
 #include <linux/bootmem.h>
 
+#include <asm/irqdomain.h>
 #include <asm/idle.h>
 #include <asm/io.h>
 #include <asm/smp.h>
@@ -63,27 +73,31 @@
 #define	for_each_ioapic_pin(idx, pin)	\
 	for_each_ioapic((idx))		\
 		for_each_pin((idx), (pin))
-
 #define for_each_irq_pin(entry, head) \
 	list_for_each_entry(entry, &head, list)
 
-/*
- *      Is the SiS APIC rmw bug present ?
- *      -1 = don't know, 0 = no, 1 = yes
- */
-int sis_apic_bug = -1;
-
 static DEFINE_RAW_SPINLOCK(ioapic_lock);
 static DEFINE_MUTEX(ioapic_mutex);
 static unsigned int ioapic_dynirq_base;
 static int ioapic_initialized;
 
-struct mp_pin_info {
+struct irq_pin_list {
+	struct list_head list;
+	int apic, pin;
+};
+
+struct mp_chip_data {
+	struct list_head irq_2_pin;
+	struct IO_APIC_route_entry entry;
 	int trigger;
 	int polarity;
-	int node;
-	int set;
 	u32 count;
+	bool isa_irq;
+};
+
+struct mp_ioapic_gsi {
+	u32 gsi_base;
+	u32 gsi_end;
 };
 
 static struct ioapic {
@@ -101,7 +115,6 @@ static struct ioapic {
 	struct mp_ioapic_gsi  gsi_config;
 	struct ioapic_domain_cfg irqdomain_cfg;
 	struct irq_domain *irqdomain;
-	struct mp_pin_info *pin_info;
 	struct resource *iomem_res;
 } ioapics[MAX_IO_APICS];
 
@@ -117,7 +130,7 @@ unsigned int mpc_ioapic_addr(int ioapic_idx)
 	return ioapics[ioapic_idx].mp_config.apicaddr;
 }
 
-struct mp_ioapic_gsi *mp_ioapic_gsi_routing(int ioapic_idx)
+static inline struct mp_ioapic_gsi *mp_ioapic_gsi_routing(int ioapic_idx)
 {
 	return &ioapics[ioapic_idx].gsi_config;
 }
@@ -129,11 +142,16 @@ static inline int mp_ioapic_pin_count(int ioapic)
 	return gsi_cfg->gsi_end - gsi_cfg->gsi_base + 1;
 }
 
-u32 mp_pin_to_gsi(int ioapic, int pin)
+static inline u32 mp_pin_to_gsi(int ioapic, int pin)
 {
 	return mp_ioapic_gsi_routing(ioapic)->gsi_base + pin;
 }
 
+static inline bool mp_is_legacy_irq(int irq)
+{
+	return irq >= 0 && irq < nr_legacy_irqs();
+}
+
 /*
  * Initialize all legacy IRQs and all pins on the first IOAPIC
  * if we have legacy interrupt controller. Kernel boot option "pirq="
@@ -144,12 +162,7 @@ static inline int mp_init_irq_at_boot(int ioapic, int irq)
 	if (!nr_legacy_irqs())
 		return 0;
 
-	return ioapic == 0 || (irq >= 0 && irq < nr_legacy_irqs());
-}
-
-static inline struct mp_pin_info *mp_pin_info(int ioapic_idx, int pin)
-{
-	return ioapics[ioapic_idx].pin_info + pin;
+	return ioapic == 0 || mp_is_legacy_irq(irq);
 }
 
 static inline struct irq_domain *mp_ioapic_irqdomain(int ioapic)
@@ -216,16 +229,6 @@ void mp_save_irq(struct mpc_intsrc *m)
 		panic("Max # of irq sources exceeded!!\n");
 }
 
-struct irq_pin_list {
-	struct list_head list;
-	int apic, pin;
-};
-
-static struct irq_pin_list *alloc_irq_pin_list(int node)
-{
-	return kzalloc_node(sizeof(struct irq_pin_list), GFP_KERNEL, node);
-}
-
 static void alloc_ioapic_saved_registers(int idx)
 {
 	size_t size;
@@ -247,8 +250,7 @@ static void free_ioapic_saved_registers(int idx)
 
 int __init arch_early_ioapic_init(void)
 {
-	struct irq_cfg *cfg;
-	int i, node = cpu_to_node(0);
+	int i;
 
 	if (!nr_legacy_irqs())
 		io_apic_irqs = ~0UL;
@@ -256,16 +258,6 @@ int __init arch_early_ioapic_init(void)
 	for_each_ioapic(i)
 		alloc_ioapic_saved_registers(i);
 
-	/*
-	 * For legacy IRQ's, start with assigning irq0 to irq15 to
-	 * IRQ0_VECTOR to IRQ15_VECTOR for all cpu's.
-	 */
-	for (i = 0; i < nr_legacy_irqs(); i++) {
-		cfg = alloc_irq_and_cfg_at(i, node);
-		cfg->vector = IRQ0_VECTOR + i;
-		cpumask_setall(cfg->domain);
-	}
-
 	return 0;
 }
 
@@ -283,7 +275,7 @@ static __attribute_const__ struct io_apic __iomem *io_apic_base(int idx)
 		+ (mpc_ioapic_addr(idx) & ~PAGE_MASK);
 }
 
-void io_apic_eoi(unsigned int apic, unsigned int vector)
+static inline void io_apic_eoi(unsigned int apic, unsigned int vector)
 {
 	struct io_apic __iomem *io_apic = io_apic_base(apic);
 	writel(vector, &io_apic->eoi);
@@ -296,7 +288,8 @@ unsigned int native_io_apic_read(unsigned int apic, unsigned int reg)
 	return readl(&io_apic->data);
 }
 
-void native_io_apic_write(unsigned int apic, unsigned int reg, unsigned int value)
+static void io_apic_write(unsigned int apic, unsigned int reg,
+			  unsigned int value)
 {
 	struct io_apic __iomem *io_apic = io_apic_base(apic);
 
@@ -304,21 +297,6 @@ void native_io_apic_write(unsigned int apic, unsigned int reg, unsigned int valu
 	writel(value, &io_apic->data);
 }
 
-/*
- * Re-write a value: to be used for read-modify-write
- * cycles where the read already set up the index register.
- *
- * Older SiS APIC requires we rewrite the index register
- */
-void native_io_apic_modify(unsigned int apic, unsigned int reg, unsigned int value)
-{
-	struct io_apic __iomem *io_apic = io_apic_base(apic);
-
-	if (sis_apic_bug)
-		writel(reg, &io_apic->index);
-	writel(value, &io_apic->data);
-}
-
 union entry_union {
 	struct { u32 w1, w2; };
 	struct IO_APIC_route_entry entry;
@@ -378,7 +356,7 @@ static void ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e)
 static void ioapic_mask_entry(int apic, int pin)
 {
 	unsigned long flags;
-	union entry_union eu = { .entry.mask = 1 };
+	union entry_union eu = { .entry.mask = IOAPIC_MASKED };
 
 	raw_spin_lock_irqsave(&ioapic_lock, flags);
 	io_apic_write(apic, 0x10 + 2*pin, eu.w1);
@@ -391,16 +369,17 @@ static void ioapic_mask_entry(int apic, int pin)
  * shared ISA-space IRQs, so we have to support them. We are super
  * fast in the common case, and fast for shared ISA-space IRQs.
  */
-static int __add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pin)
+static int __add_pin_to_irq_node(struct mp_chip_data *data,
+				 int node, int apic, int pin)
 {
 	struct irq_pin_list *entry;
 
 	/* don't allow duplicates */
-	for_each_irq_pin(entry, cfg->irq_2_pin)
+	for_each_irq_pin(entry, data->irq_2_pin)
 		if (entry->apic == apic && entry->pin == pin)
 			return 0;
 
-	entry = alloc_irq_pin_list(node);
+	entry = kzalloc_node(sizeof(struct irq_pin_list), GFP_ATOMIC, node);
 	if (!entry) {
 		pr_err("can not alloc irq_pin_list (%d,%d,%d)\n",
 		       node, apic, pin);
@@ -408,16 +387,16 @@ static int __add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pi
 	}
 	entry->apic = apic;
 	entry->pin = pin;
+	list_add_tail(&entry->list, &data->irq_2_pin);
 
-	list_add_tail(&entry->list, &cfg->irq_2_pin);
 	return 0;
 }
 
-static void __remove_pin_from_irq(struct irq_cfg *cfg, int apic, int pin)
+static void __remove_pin_from_irq(struct mp_chip_data *data, int apic, int pin)
 {
 	struct irq_pin_list *tmp, *entry;
 
-	list_for_each_entry_safe(entry, tmp, &cfg->irq_2_pin, list)
+	list_for_each_entry_safe(entry, tmp, &data->irq_2_pin, list)
 		if (entry->apic == apic && entry->pin == pin) {
 			list_del(&entry->list);
 			kfree(entry);
@@ -425,22 +404,23 @@ static void __remove_pin_from_irq(struct irq_cfg *cfg, int apic, int pin)
 		}
 }
 
-static void add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pin)
+static void add_pin_to_irq_node(struct mp_chip_data *data,
+				int node, int apic, int pin)
 {
-	if (__add_pin_to_irq_node(cfg, node, apic, pin))
+	if (__add_pin_to_irq_node(data, node, apic, pin))
 		panic("IO-APIC: failed to add irq-pin. Can not proceed\n");
 }
 
 /*
  * Reroute an IRQ to a different pin.
  */
-static void __init replace_pin_at_irq_node(struct irq_cfg *cfg, int node,
+static void __init replace_pin_at_irq_node(struct mp_chip_data *data, int node,
 					   int oldapic, int oldpin,
 					   int newapic, int newpin)
 {
 	struct irq_pin_list *entry;
 
-	for_each_irq_pin(entry, cfg->irq_2_pin) {
+	for_each_irq_pin(entry, data->irq_2_pin) {
 		if (entry->apic == oldapic && entry->pin == oldpin) {
 			entry->apic = newapic;
 			entry->pin = newpin;
@@ -450,32 +430,26 @@ static void __init replace_pin_at_irq_node(struct irq_cfg *cfg, int node,
 	}
 
 	/* old apic/pin didn't exist, so just add new ones */
-	add_pin_to_irq_node(cfg, node, newapic, newpin);
-}
-
-static void __io_apic_modify_irq(struct irq_pin_list *entry,
-				 int mask_and, int mask_or,
-				 void (*final)(struct irq_pin_list *entry))
-{
-	unsigned int reg, pin;
-
-	pin = entry->pin;
-	reg = io_apic_read(entry->apic, 0x10 + pin * 2);
-	reg &= mask_and;
-	reg |= mask_or;
-	io_apic_modify(entry->apic, 0x10 + pin * 2, reg);
-	if (final)
-		final(entry);
+	add_pin_to_irq_node(data, node, newapic, newpin);
 }
 
-static void io_apic_modify_irq(struct irq_cfg *cfg,
+static void io_apic_modify_irq(struct mp_chip_data *data,
 			       int mask_and, int mask_or,
 			       void (*final)(struct irq_pin_list *entry))
 {
+	union entry_union eu;
 	struct irq_pin_list *entry;
 
-	for_each_irq_pin(entry, cfg->irq_2_pin)
-		__io_apic_modify_irq(entry, mask_and, mask_or, final);
+	eu.entry = data->entry;
+	eu.w1 &= mask_and;
+	eu.w1 |= mask_or;
+	data->entry = eu.entry;
+
+	for_each_irq_pin(entry, data->irq_2_pin) {
+		io_apic_write(entry->apic, 0x10 + 2 * entry->pin, eu.w1);
+		if (final)
+			final(entry);
+	}
 }
 
 static void io_apic_sync(struct irq_pin_list *entry)
@@ -490,39 +464,31 @@ static void io_apic_sync(struct irq_pin_list *entry)
 	readl(&io_apic->data);
 }
 
-static void mask_ioapic(struct irq_cfg *cfg)
+static void mask_ioapic_irq(struct irq_data *irq_data)
 {
+	struct mp_chip_data *data = irq_data->chip_data;
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&ioapic_lock, flags);
-	io_apic_modify_irq(cfg, ~0, IO_APIC_REDIR_MASKED, &io_apic_sync);
+	io_apic_modify_irq(data, ~0, IO_APIC_REDIR_MASKED, &io_apic_sync);
 	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 }
 
-static void mask_ioapic_irq(struct irq_data *data)
+static void __unmask_ioapic(struct mp_chip_data *data)
 {
-	mask_ioapic(irqd_cfg(data));
+	io_apic_modify_irq(data, ~IO_APIC_REDIR_MASKED, 0, NULL);
 }
 
-static void __unmask_ioapic(struct irq_cfg *cfg)
-{
-	io_apic_modify_irq(cfg, ~IO_APIC_REDIR_MASKED, 0, NULL);
-}
-
-static void unmask_ioapic(struct irq_cfg *cfg)
+static void unmask_ioapic_irq(struct irq_data *irq_data)
 {
+	struct mp_chip_data *data = irq_data->chip_data;
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&ioapic_lock, flags);
-	__unmask_ioapic(cfg);
+	__unmask_ioapic(data);
 	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 }
 
-static void unmask_ioapic_irq(struct irq_data *data)
-{
-	unmask_ioapic(irqd_cfg(data));
-}
-
 /*
  * IO-APIC versions below 0x20 don't support EOI register.
  * For the record, here is the information about various versions:
@@ -539,7 +505,7 @@ static void unmask_ioapic_irq(struct irq_data *data)
  * Otherwise, we simulate the EOI message manually by changing the trigger
  * mode to edge and then back to level, with RTE being masked during this.
  */
-void native_eoi_ioapic_pin(int apic, int pin, int vector)
+static void __eoi_ioapic_pin(int apic, int pin, int vector)
 {
 	if (mpc_ioapic_ver(apic) >= 0x20) {
 		io_apic_eoi(apic, vector);
@@ -551,7 +517,7 @@ void native_eoi_ioapic_pin(int apic, int pin, int vector)
 		/*
 		 * Mask the entry and change the trigger mode to edge.
 		 */
-		entry1.mask = 1;
+		entry1.mask = IOAPIC_MASKED;
 		entry1.trigger = IOAPIC_EDGE;
 
 		__ioapic_write_entry(apic, pin, entry1);
@@ -563,15 +529,14 @@ void native_eoi_ioapic_pin(int apic, int pin, int vector)
 	}
 }
 
-void eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg)
+void eoi_ioapic_pin(int vector, struct mp_chip_data *data)
 {
-	struct irq_pin_list *entry;
 	unsigned long flags;
+	struct irq_pin_list *entry;
 
 	raw_spin_lock_irqsave(&ioapic_lock, flags);
-	for_each_irq_pin(entry, cfg->irq_2_pin)
-		x86_io_apic_ops.eoi_ioapic_pin(entry->apic, entry->pin,
-					       cfg->vector);
+	for_each_irq_pin(entry, data->irq_2_pin)
+		__eoi_ioapic_pin(entry->apic, entry->pin, vector);
 	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 }
 
@@ -588,8 +553,8 @@ static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin)
 	 * Make sure the entry is masked and re-read the contents to check
 	 * if it is a level triggered pin and if the remote-IRR is set.
 	 */
-	if (!entry.mask) {
-		entry.mask = 1;
+	if (entry.mask == IOAPIC_UNMASKED) {
+		entry.mask = IOAPIC_MASKED;
 		ioapic_write_entry(apic, pin, entry);
 		entry = ioapic_read_entry(apic, pin);
 	}
@@ -602,13 +567,12 @@ static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin)
 		 * doesn't clear the remote-IRR if the trigger mode is not
 		 * set to level.
 		 */
-		if (!entry.trigger) {
+		if (entry.trigger == IOAPIC_EDGE) {
 			entry.trigger = IOAPIC_LEVEL;
 			ioapic_write_entry(apic, pin, entry);
 		}
-
 		raw_spin_lock_irqsave(&ioapic_lock, flags);
-		x86_io_apic_ops.eoi_ioapic_pin(apic, pin, entry.vector);
+		__eoi_ioapic_pin(apic, pin, entry.vector);
 		raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 	}
 
@@ -706,8 +670,8 @@ void mask_ioapic_entries(void)
 			struct IO_APIC_route_entry entry;
 
 			entry = ioapics[apic].saved_registers[pin];
-			if (!entry.mask) {
-				entry.mask = 1;
+			if (entry.mask == IOAPIC_UNMASKED) {
+				entry.mask = IOAPIC_MASKED;
 				ioapic_write_entry(apic, pin, entry);
 			}
 		}
@@ -809,11 +773,11 @@ static int EISA_ELCR(unsigned int irq)
 
 #endif
 
-/* ISA interrupts are always polarity zero edge triggered,
+/* ISA interrupts are always active high edge triggered,
  * when listed as conforming in the MP table. */
 
-#define default_ISA_trigger(idx)	(0)
-#define default_ISA_polarity(idx)	(0)
+#define default_ISA_trigger(idx)	(IOAPIC_EDGE)
+#define default_ISA_polarity(idx)	(IOAPIC_POL_HIGH)
 
 /* EISA interrupts are always polarity zero and can be edge or level
  * trigger depending on the ELCR value.  If an interrupt is listed as
@@ -823,53 +787,55 @@ static int EISA_ELCR(unsigned int irq)
 #define default_EISA_trigger(idx)	(EISA_ELCR(mp_irqs[idx].srcbusirq))
 #define default_EISA_polarity(idx)	default_ISA_polarity(idx)
 
-/* PCI interrupts are always polarity one level triggered,
+/* PCI interrupts are always active low level triggered,
  * when listed as conforming in the MP table. */
 
-#define default_PCI_trigger(idx)	(1)
-#define default_PCI_polarity(idx)	(1)
+#define default_PCI_trigger(idx)	(IOAPIC_LEVEL)
+#define default_PCI_polarity(idx)	(IOAPIC_POL_LOW)
 
 static int irq_polarity(int idx)
 {
 	int bus = mp_irqs[idx].srcbus;
-	int polarity;
 
 	/*
 	 * Determine IRQ line polarity (high active or low active):
 	 */
-	switch (mp_irqs[idx].irqflag & 3)
-	{
-		case 0: /* conforms, ie. bus-type dependent polarity */
-			if (test_bit(bus, mp_bus_not_pci))
-				polarity = default_ISA_polarity(idx);
-			else
-				polarity = default_PCI_polarity(idx);
-			break;
-		case 1: /* high active */
-		{
-			polarity = 0;
-			break;
-		}
-		case 2: /* reserved */
-		{
-			pr_warn("broken BIOS!!\n");
-			polarity = 1;
-			break;
-		}
-		case 3: /* low active */
-		{
-			polarity = 1;
-			break;
-		}
-		default: /* invalid */
-		{
-			pr_warn("broken BIOS!!\n");
-			polarity = 1;
-			break;
-		}
+	switch (mp_irqs[idx].irqflag & 0x03) {
+	case 0:
+		/* conforms to spec, ie. bus-type dependent polarity */
+		if (test_bit(bus, mp_bus_not_pci))
+			return default_ISA_polarity(idx);
+		else
+			return default_PCI_polarity(idx);
+	case 1:
+		return IOAPIC_POL_HIGH;
+	case 2:
+		pr_warn("IOAPIC: Invalid polarity: 2, defaulting to low\n");
+	case 3:
+	default: /* Pointless default required due to do gcc stupidity */
+		return IOAPIC_POL_LOW;
+	}
+}
+
+#ifdef CONFIG_EISA
+static int eisa_irq_trigger(int idx, int bus, int trigger)
+{
+	switch (mp_bus_id_to_type[bus]) {
+	case MP_BUS_PCI:
+	case MP_BUS_ISA:
+		return trigger;
+	case MP_BUS_EISA:
+		return default_EISA_trigger(idx);
 	}
-	return polarity;
+	pr_warn("IOAPIC: Invalid srcbus: %d defaulting to level\n", bus);
+	return IOAPIC_LEVEL;
 }
+#else
+static inline int eisa_irq_trigger(int idx, int bus, int trigger)
+{
+	return trigger;
+}
+#endif
 
 static int irq_trigger(int idx)
 {
@@ -879,153 +845,227 @@ static int irq_trigger(int idx)
 	/*
 	 * Determine IRQ trigger mode (edge or level sensitive):
 	 */
-	switch ((mp_irqs[idx].irqflag>>2) & 3)
-	{
-		case 0: /* conforms, ie. bus-type dependent */
-			if (test_bit(bus, mp_bus_not_pci))
-				trigger = default_ISA_trigger(idx);
-			else
-				trigger = default_PCI_trigger(idx);
-#ifdef CONFIG_EISA
-			switch (mp_bus_id_to_type[bus]) {
-				case MP_BUS_ISA: /* ISA pin */
-				{
-					/* set before the switch */
-					break;
-				}
-				case MP_BUS_EISA: /* EISA pin */
-				{
-					trigger = default_EISA_trigger(idx);
-					break;
-				}
-				case MP_BUS_PCI: /* PCI pin */
-				{
-					/* set before the switch */
-					break;
-				}
-				default:
-				{
-					pr_warn("broken BIOS!!\n");
-					trigger = 1;
-					break;
-				}
-			}
+	switch ((mp_irqs[idx].irqflag >> 2) & 0x03) {
+	case 0:
+		/* conforms to spec, ie. bus-type dependent trigger mode */
+		if (test_bit(bus, mp_bus_not_pci))
+			trigger = default_ISA_trigger(idx);
+		else
+			trigger = default_PCI_trigger(idx);
+		/* Take EISA into account */
+		return eisa_irq_trigger(idx, bus, trigger);
+	case 1:
+		return IOAPIC_EDGE;
+	case 2:
+		pr_warn("IOAPIC: Invalid trigger mode 2 defaulting to level\n");
+	case 3:
+	default: /* Pointless default required due to do gcc stupidity */
+		return IOAPIC_LEVEL;
+	}
+}
+
+void ioapic_set_alloc_attr(struct irq_alloc_info *info, int node,
+			   int trigger, int polarity)
+{
+	init_irq_alloc_info(info, NULL);
+	info->type = X86_IRQ_ALLOC_TYPE_IOAPIC;
+	info->ioapic_node = node;
+	info->ioapic_trigger = trigger;
+	info->ioapic_polarity = polarity;
+	info->ioapic_valid = 1;
+}
+
+#ifndef CONFIG_ACPI
+int acpi_get_override_irq(u32 gsi, int *trigger, int *polarity);
 #endif
-			break;
-		case 1: /* edge */
-		{
-			trigger = 0;
-			break;
-		}
-		case 2: /* reserved */
-		{
-			pr_warn("broken BIOS!!\n");
-			trigger = 1;
-			break;
-		}
-		case 3: /* level */
-		{
-			trigger = 1;
-			break;
-		}
-		default: /* invalid */
-		{
-			pr_warn("broken BIOS!!\n");
-			trigger = 0;
-			break;
+
+static void ioapic_copy_alloc_attr(struct irq_alloc_info *dst,
+				   struct irq_alloc_info *src,
+				   u32 gsi, int ioapic_idx, int pin)
+{
+	int trigger, polarity;
+
+	copy_irq_alloc_info(dst, src);
+	dst->type = X86_IRQ_ALLOC_TYPE_IOAPIC;
+	dst->ioapic_id = mpc_ioapic_id(ioapic_idx);
+	dst->ioapic_pin = pin;
+	dst->ioapic_valid = 1;
+	if (src && src->ioapic_valid) {
+		dst->ioapic_node = src->ioapic_node;
+		dst->ioapic_trigger = src->ioapic_trigger;
+		dst->ioapic_polarity = src->ioapic_polarity;
+	} else {
+		dst->ioapic_node = NUMA_NO_NODE;
+		if (acpi_get_override_irq(gsi, &trigger, &polarity) >= 0) {
+			dst->ioapic_trigger = trigger;
+			dst->ioapic_polarity = polarity;
+		} else {
+			/*
+			 * PCI interrupts are always active low level
+			 * triggered.
+			 */
+			dst->ioapic_trigger = IOAPIC_LEVEL;
+			dst->ioapic_polarity = IOAPIC_POL_LOW;
 		}
 	}
-	return trigger;
 }
 
-static int alloc_irq_from_domain(struct irq_domain *domain, u32 gsi, int pin)
+static int ioapic_alloc_attr_node(struct irq_alloc_info *info)
+{
+	return (info && info->ioapic_valid) ? info->ioapic_node : NUMA_NO_NODE;
+}
+
+static void mp_register_handler(unsigned int irq, unsigned long trigger)
+{
+	irq_flow_handler_t hdl;
+	bool fasteoi;
+
+	if (trigger) {
+		irq_set_status_flags(irq, IRQ_LEVEL);
+		fasteoi = true;
+	} else {
+		irq_clear_status_flags(irq, IRQ_LEVEL);
+		fasteoi = false;
+	}
+
+	hdl = fasteoi ? handle_fasteoi_irq : handle_edge_irq;
+	__irq_set_handler(irq, hdl, 0, fasteoi ? "fasteoi" : "edge");
+}
+
+static bool mp_check_pin_attr(int irq, struct irq_alloc_info *info)
 {
+	struct mp_chip_data *data = irq_get_chip_data(irq);
+
+	/*
+	 * setup_IO_APIC_irqs() programs all legacy IRQs with default trigger
+	 * and polarity attirbutes. So allow the first user to reprogram the
+	 * pin with real trigger and polarity attributes.
+	 */
+	if (irq < nr_legacy_irqs() && data->count == 1) {
+		if (info->ioapic_trigger != data->trigger)
+			mp_register_handler(irq, data->trigger);
+		data->entry.trigger = data->trigger = info->ioapic_trigger;
+		data->entry.polarity = data->polarity = info->ioapic_polarity;
+	}
+
+	return data->trigger == info->ioapic_trigger &&
+	       data->polarity == info->ioapic_polarity;
+}
+
+static int alloc_irq_from_domain(struct irq_domain *domain, int ioapic, u32 gsi,
+				 struct irq_alloc_info *info)
+{
+	bool legacy = false;
 	int irq = -1;
-	int ioapic = (int)(long)domain->host_data;
 	int type = ioapics[ioapic].irqdomain_cfg.type;
 
 	switch (type) {
 	case IOAPIC_DOMAIN_LEGACY:
 		/*
-		 * Dynamically allocate IRQ number for non-ISA IRQs in the first 16
-		 * GSIs on some weird platforms.
+		 * Dynamically allocate IRQ number for non-ISA IRQs in the first
+		 * 16 GSIs on some weird platforms.
 		 */
-		if (gsi < nr_legacy_irqs())
-			irq = irq_create_mapping(domain, pin);
-		else if (irq_create_strict_mappings(domain, gsi, pin, 1) == 0)
+		if (!ioapic_initialized || gsi >= nr_legacy_irqs())
 			irq = gsi;
+		legacy = mp_is_legacy_irq(irq);
 		break;
 	case IOAPIC_DOMAIN_STRICT:
-		if (irq_create_strict_mappings(domain, gsi, pin, 1) == 0)
-			irq = gsi;
+		irq = gsi;
 		break;
 	case IOAPIC_DOMAIN_DYNAMIC:
-		irq = irq_create_mapping(domain, pin);
 		break;
 	default:
 		WARN(1, "ioapic: unknown irqdomain type %d\n", type);
-		break;
+		return -1;
+	}
+
+	return __irq_domain_alloc_irqs(domain, irq, 1,
+				       ioapic_alloc_attr_node(info),
+				       info, legacy);
+}
+
+/*
+ * Need special handling for ISA IRQs because there may be multiple IOAPIC pins
+ * sharing the same ISA IRQ number and irqdomain only supports 1:1 mapping
+ * between IOAPIC pin and IRQ number. A typical IOAPIC has 24 pins, pin 0-15 are
+ * used for legacy IRQs and pin 16-23 are used for PCI IRQs (PIRQ A-H).
+ * When ACPI is disabled, only legacy IRQ numbers (IRQ0-15) are available, and
+ * some BIOSes may use MP Interrupt Source records to override IRQ numbers for
+ * PIRQs instead of reprogramming the interrupt routing logic. Thus there may be
+ * multiple pins sharing the same legacy IRQ number when ACPI is disabled.
+ */
+static int alloc_isa_irq_from_domain(struct irq_domain *domain,
+				     int irq, int ioapic, int pin,
+				     struct irq_alloc_info *info)
+{
+	struct mp_chip_data *data;
+	struct irq_data *irq_data = irq_get_irq_data(irq);
+	int node = ioapic_alloc_attr_node(info);
+
+	/*
+	 * Legacy ISA IRQ has already been allocated, just add pin to
+	 * the pin list assoicated with this IRQ and program the IOAPIC
+	 * entry. The IOAPIC entry
+	 */
+	if (irq_data && irq_data->parent_data) {
+		if (!mp_check_pin_attr(irq, info))
+			return -EBUSY;
+		if (__add_pin_to_irq_node(irq_data->chip_data, node, ioapic,
+					  info->ioapic_pin))
+			return -ENOMEM;
+	} else {
+		irq = __irq_domain_alloc_irqs(domain, irq, 1, node, info, true);
+		if (irq >= 0) {
+			irq_data = irq_domain_get_irq_data(domain, irq);
+			data = irq_data->chip_data;
+			data->isa_irq = true;
+		}
 	}
 
-	return irq > 0 ? irq : -1;
+	return irq;
 }
 
 static int mp_map_pin_to_irq(u32 gsi, int idx, int ioapic, int pin,
-			     unsigned int flags)
+			     unsigned int flags, struct irq_alloc_info *info)
 {
 	int irq;
+	bool legacy = false;
+	struct irq_alloc_info tmp;
+	struct mp_chip_data *data;
 	struct irq_domain *domain = mp_ioapic_irqdomain(ioapic);
-	struct mp_pin_info *info = mp_pin_info(ioapic, pin);
 
 	if (!domain)
-		return -1;
+		return -ENOSYS;
 
-	mutex_lock(&ioapic_mutex);
-
-	/*
-	 * Don't use irqdomain to manage ISA IRQs because there may be
-	 * multiple IOAPIC pins sharing the same ISA IRQ number and
-	 * irqdomain only supports 1:1 mapping between IOAPIC pin and
-	 * IRQ number. A typical IOAPIC has 24 pins, pin 0-15 are used
-	 * for legacy IRQs and pin 16-23 are used for PCI IRQs (PIRQ A-H).
-	 * When ACPI is disabled, only legacy IRQ numbers (IRQ0-15) are
-	 * available, and some BIOSes may use MP Interrupt Source records
-	 * to override IRQ numbers for PIRQs instead of reprogramming
-	 * the interrupt routing logic. Thus there may be multiple pins
-	 * sharing the same legacy IRQ number when ACPI is disabled.
-	 */
 	if (idx >= 0 && test_bit(mp_irqs[idx].srcbus, mp_bus_not_pci)) {
 		irq = mp_irqs[idx].srcbusirq;
-		if (flags & IOAPIC_MAP_ALLOC) {
-			if (info->count == 0 &&
-			    mp_irqdomain_map(domain, irq, pin) != 0)
-				irq = -1;
+		legacy = mp_is_legacy_irq(irq);
+	}
 
-			/* special handling for timer IRQ0 */
+	mutex_lock(&ioapic_mutex);
+	if (!(flags & IOAPIC_MAP_ALLOC)) {
+		if (!legacy) {
+			irq = irq_find_mapping(domain, pin);
 			if (irq == 0)
-				info->count++;
+				irq = -ENOENT;
 		}
 	} else {
-		irq = irq_find_mapping(domain, pin);
-		if (irq <= 0 && (flags & IOAPIC_MAP_ALLOC))
-			irq = alloc_irq_from_domain(domain, gsi, pin);
-	}
-
-	if (flags & IOAPIC_MAP_ALLOC) {
-		/* special handling for legacy IRQs */
-		if (irq < nr_legacy_irqs() && info->count == 1 &&
-		    mp_irqdomain_map(domain, irq, pin) != 0)
-			irq = -1;
-
-		if (irq > 0)
-			info->count++;
-		else if (info->count == 0)
-			info->set = 0;
+		ioapic_copy_alloc_attr(&tmp, info, gsi, ioapic, pin);
+		if (legacy)
+			irq = alloc_isa_irq_from_domain(domain, irq,
+							ioapic, pin, &tmp);
+		else if ((irq = irq_find_mapping(domain, pin)) == 0)
+			irq = alloc_irq_from_domain(domain, ioapic, gsi, &tmp);
+		else if (!mp_check_pin_attr(irq, &tmp))
+			irq = -EBUSY;
+		if (irq >= 0) {
+			data = irq_get_chip_data(irq);
+			data->count++;
+		}
 	}
-
 	mutex_unlock(&ioapic_mutex);
 
-	return irq > 0 ? irq : -1;
+	return irq;
 }
 
 static int pin_2_irq(int idx, int ioapic, int pin, unsigned int flags)
@@ -1058,10 +1098,10 @@ static int pin_2_irq(int idx, int ioapic, int pin, unsigned int flags)
 	}
 #endif
 
-	return  mp_map_pin_to_irq(gsi, idx, ioapic, pin, flags);
+	return  mp_map_pin_to_irq(gsi, idx, ioapic, pin, flags, NULL);
 }
 
-int mp_map_gsi_to_irq(u32 gsi, unsigned int flags)
+int mp_map_gsi_to_irq(u32 gsi, unsigned int flags, struct irq_alloc_info *info)
 {
 	int ioapic, pin, idx;
 
@@ -1074,31 +1114,24 @@ int mp_map_gsi_to_irq(u32 gsi, unsigned int flags)
 	if ((flags & IOAPIC_MAP_CHECK) && idx < 0)
 		return -1;
 
-	return mp_map_pin_to_irq(gsi, idx, ioapic, pin, flags);
+	return mp_map_pin_to_irq(gsi, idx, ioapic, pin, flags, info);
 }
 
 void mp_unmap_irq(int irq)
 {
-	struct irq_data *data = irq_get_irq_data(irq);
-	struct mp_pin_info *info;
-	int ioapic, pin;
+	struct irq_data *irq_data = irq_get_irq_data(irq);
+	struct mp_chip_data *data;
 
-	if (!data || !data->domain)
+	if (!irq_data || !irq_data->domain)
 		return;
 
-	ioapic = (int)(long)data->domain->host_data;
-	pin = (int)data->hwirq;
-	info = mp_pin_info(ioapic, pin);
+	data = irq_data->chip_data;
+	if (!data || data->isa_irq)
+		return;
 
 	mutex_lock(&ioapic_mutex);
-	if (--info->count == 0) {
-		info->set = 0;
-		if (irq < nr_legacy_irqs() &&
-		    ioapics[ioapic].irqdomain_cfg.type == IOAPIC_DOMAIN_LEGACY)
-			mp_irqdomain_unmap(data->domain, irq);
-		else
-			irq_dispose_mapping(irq);
-	}
+	if (--data->count == 0)
+		irq_domain_free_irqs(irq, 1);
 	mutex_unlock(&ioapic_mutex);
 }
 
@@ -1165,7 +1198,7 @@ out:
 }
 EXPORT_SYMBOL(IO_APIC_get_PCI_irq_vector);
 
-static struct irq_chip ioapic_chip;
+static struct irq_chip ioapic_chip, ioapic_ir_chip;
 
 #ifdef CONFIG_X86_32
 static inline int IO_APIC_irq_trigger(int irq)
@@ -1189,96 +1222,6 @@ static inline int IO_APIC_irq_trigger(int irq)
 }
 #endif
 
-static void ioapic_register_intr(unsigned int irq, struct irq_cfg *cfg,
-				 unsigned long trigger)
-{
-	struct irq_chip *chip = &ioapic_chip;
-	irq_flow_handler_t hdl;
-	bool fasteoi;
-
-	if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) ||
-	    trigger == IOAPIC_LEVEL) {
-		irq_set_status_flags(irq, IRQ_LEVEL);
-		fasteoi = true;
-	} else {
-		irq_clear_status_flags(irq, IRQ_LEVEL);
-		fasteoi = false;
-	}
-
-	if (setup_remapped_irq(irq, cfg, chip))
-		fasteoi = trigger != 0;
-
-	hdl = fasteoi ? handle_fasteoi_irq : handle_edge_irq;
-	irq_set_chip_and_handler_name(irq, chip, hdl,
-				      fasteoi ? "fasteoi" : "edge");
-}
-
-int native_setup_ioapic_entry(int irq, struct IO_APIC_route_entry *entry,
-			      unsigned int destination, int vector,
-			      struct io_apic_irq_attr *attr)
-{
-	memset(entry, 0, sizeof(*entry));
-
-	entry->delivery_mode = apic->irq_delivery_mode;
-	entry->dest_mode     = apic->irq_dest_mode;
-	entry->dest	     = destination;
-	entry->vector	     = vector;
-	entry->mask	     = 0;			/* enable IRQ */
-	entry->trigger	     = attr->trigger;
-	entry->polarity	     = attr->polarity;
-
-	/*
-	 * Mask level triggered irqs.
-	 * Use IRQ_DELAYED_DISABLE for edge triggered irqs.
-	 */
-	if (attr->trigger)
-		entry->mask = 1;
-
-	return 0;
-}
-
-static void setup_ioapic_irq(unsigned int irq, struct irq_cfg *cfg,
-				struct io_apic_irq_attr *attr)
-{
-	struct IO_APIC_route_entry entry;
-	unsigned int dest;
-
-	if (!IO_APIC_IRQ(irq))
-		return;
-
-	if (assign_irq_vector(irq, cfg, apic->target_cpus()))
-		return;
-
-	if (apic->cpu_mask_to_apicid_and(cfg->domain, apic->target_cpus(),
-					 &dest)) {
-		pr_warn("Failed to obtain apicid for ioapic %d, pin %d\n",
-			mpc_ioapic_id(attr->ioapic), attr->ioapic_pin);
-		clear_irq_vector(irq, cfg);
-
-		return;
-	}
-
-	apic_printk(APIC_VERBOSE,KERN_DEBUG
-		    "IOAPIC[%d]: Set routing entry (%d-%d -> 0x%x -> "
-		    "IRQ %d Mode:%i Active:%i Dest:%d)\n",
-		    attr->ioapic, mpc_ioapic_id(attr->ioapic), attr->ioapic_pin,
-		    cfg->vector, irq, attr->trigger, attr->polarity, dest);
-
-	if (x86_io_apic_ops.setup_entry(irq, &entry, dest, cfg->vector, attr)) {
-		pr_warn("Failed to setup ioapic entry for ioapic  %d, pin %d\n",
-			mpc_ioapic_id(attr->ioapic), attr->ioapic_pin);
-		clear_irq_vector(irq, cfg);
-
-		return;
-	}
-
-	ioapic_register_intr(irq, cfg, attr->trigger);
-	if (irq < nr_legacy_irqs())
-		legacy_pic->mask(irq);
-
-	ioapic_write_entry(attr->ioapic, attr->ioapic_pin, entry);
-}
-
 static void __init setup_IO_APIC_irqs(void)
 {
 	unsigned int ioapic, pin;
@@ -1298,106 +1241,41 @@ static void __init setup_IO_APIC_irqs(void)
 	}
 }
 
-/*
- * Set up the timer pin, possibly with the 8259A-master behind.
- */
-static void __init setup_timer_IRQ0_pin(unsigned int ioapic_idx,
-					unsigned int pin, int vector)
-{
-	struct IO_APIC_route_entry entry;
-	unsigned int dest;
-
-	memset(&entry, 0, sizeof(entry));
-
-	/*
-	 * We use logical delivery to get the timer IRQ
-	 * to the first CPU.
-	 */
-	if (unlikely(apic->cpu_mask_to_apicid_and(apic->target_cpus(),
-						  apic->target_cpus(), &dest)))
-		dest = BAD_APICID;
-
-	entry.dest_mode = apic->irq_dest_mode;
-	entry.mask = 0;			/* don't mask IRQ for edge */
-	entry.dest = dest;
-	entry.delivery_mode = apic->irq_delivery_mode;
-	entry.polarity = 0;
-	entry.trigger = 0;
-	entry.vector = vector;
-
-	/*
-	 * The timer IRQ doesn't have to know that behind the
-	 * scene we may have a 8259A-master in AEOI mode ...
-	 */
-	irq_set_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq,
-				      "edge");
-
-	/*
-	 * Add it to the IO-APIC irq-routing table:
-	 */
-	ioapic_write_entry(ioapic_idx, pin, entry);
-}
-
-void native_io_apic_print_entries(unsigned int apic, unsigned int nr_entries)
+void ioapic_zap_locks(void)
 {
-	int i;
-
-	pr_debug(" NR Dst Mask Trig IRR Pol Stat Dmod Deli Vect:\n");
-
-	for (i = 0; i <= nr_entries; i++) {
-		struct IO_APIC_route_entry entry;
-
-		entry = ioapic_read_entry(apic, i);
-
-		pr_debug(" %02x %02X  ", i, entry.dest);
-		pr_cont("%1d    %1d    %1d   %1d   %1d    "
-			"%1d    %1d    %02X\n",
-			entry.mask,
-			entry.trigger,
-			entry.irr,
-			entry.polarity,
-			entry.delivery_status,
-			entry.dest_mode,
-			entry.delivery_mode,
-			entry.vector);
-	}
+	raw_spin_lock_init(&ioapic_lock);
 }
 
-void intel_ir_io_apic_print_entries(unsigned int apic,
-				    unsigned int nr_entries)
+static void io_apic_print_entries(unsigned int apic, unsigned int nr_entries)
 {
 	int i;
+	char buf[256];
+	struct IO_APIC_route_entry entry;
+	struct IR_IO_APIC_route_entry *ir_entry = (void *)&entry;
 
-	pr_debug(" NR Indx Fmt Mask Trig IRR Pol Stat Indx2 Zero Vect:\n");
-
+	printk(KERN_DEBUG "IOAPIC %d:\n", apic);
 	for (i = 0; i <= nr_entries; i++) {
-		struct IR_IO_APIC_route_entry *ir_entry;
-		struct IO_APIC_route_entry entry;
-
 		entry = ioapic_read_entry(apic, i);
-
-		ir_entry = (struct IR_IO_APIC_route_entry *)&entry;
-
-		pr_debug(" %02x %04X ", i, ir_entry->index);
-		pr_cont("%1d   %1d    %1d    %1d   %1d   "
-			"%1d    %1d     %X    %02X\n",
-			ir_entry->format,
-			ir_entry->mask,
-			ir_entry->trigger,
-			ir_entry->irr,
-			ir_entry->polarity,
-			ir_entry->delivery_status,
-			ir_entry->index2,
-			ir_entry->zero,
-			ir_entry->vector);
+		snprintf(buf, sizeof(buf),
+			 " pin%02x, %s, %s, %s, V(%02X), IRR(%1d), S(%1d)",
+			 i,
+			 entry.mask == IOAPIC_MASKED ? "disabled" : "enabled ",
+			 entry.trigger == IOAPIC_LEVEL ? "level" : "edge ",
+			 entry.polarity == IOAPIC_POL_LOW ? "low " : "high",
+			 entry.vector, entry.irr, entry.delivery_status);
+		if (ir_entry->format)
+			printk(KERN_DEBUG "%s, remapped, I(%04X),  Z(%X)\n",
+			       buf, (ir_entry->index << 15) | ir_entry->index,
+			       ir_entry->zero);
+		else
+			printk(KERN_DEBUG "%s, %s, D(%02X), M(%1d)\n",
+			       buf,
+			       entry.dest_mode == IOAPIC_DEST_MODE_LOGICAL ?
+			       "logical " : "physical",
+			       entry.dest, entry.delivery_mode);
 	}
 }
 
-void ioapic_zap_locks(void)
-{
-	raw_spin_lock_init(&ioapic_lock);
-}
-
 static void __init print_IO_APIC(int ioapic_idx)
 {
 	union IO_APIC_reg_00 reg_00;
@@ -1451,16 +1329,13 @@ static void __init print_IO_APIC(int ioapic_idx)
 	}
 
 	printk(KERN_DEBUG ".... IRQ redirection table:\n");
-
-	x86_io_apic_ops.print_entries(ioapic_idx, reg_01.bits.entries);
+	io_apic_print_entries(ioapic_idx, reg_01.bits.entries);
 }
 
 void __init print_IO_APICs(void)
 {
 	int ioapic_idx;
-	struct irq_cfg *cfg;
 	unsigned int irq;
-	struct irq_chip *chip;
 
 	printk(KERN_DEBUG "number of MP IRQ sources: %d.\n", mp_irq_entries);
 	for_each_ioapic(ioapic_idx)
@@ -1480,18 +1355,20 @@ void __init print_IO_APICs(void)
 	printk(KERN_DEBUG "IRQ to pin mappings:\n");
 	for_each_active_irq(irq) {
 		struct irq_pin_list *entry;
+		struct irq_chip *chip;
+		struct mp_chip_data *data;
 
 		chip = irq_get_chip(irq);
-		if (chip != &ioapic_chip)
+		if (chip != &ioapic_chip && chip != &ioapic_ir_chip)
 			continue;
-
-		cfg = irq_cfg(irq);
-		if (!cfg)
+		data = irq_get_chip_data(irq);
+		if (!data)
 			continue;
-		if (list_empty(&cfg->irq_2_pin))
+		if (list_empty(&data->irq_2_pin))
 			continue;
+
 		printk(KERN_DEBUG "IRQ%d ", irq);
-		for_each_irq_pin(entry, cfg->irq_2_pin)
+		for_each_irq_pin(entry, data->irq_2_pin)
 			pr_cont("-> %d:%d", entry->apic, entry->pin);
 		pr_cont("\n");
 	}
@@ -1564,15 +1441,12 @@ void native_disable_io_apic(void)
 		struct IO_APIC_route_entry entry;
 
 		memset(&entry, 0, sizeof(entry));
-		entry.mask            = 0; /* Enabled */
-		entry.trigger         = 0; /* Edge */
-		entry.irr             = 0;
-		entry.polarity        = 0; /* High */
-		entry.delivery_status = 0;
-		entry.dest_mode       = 0; /* Physical */
-		entry.delivery_mode   = dest_ExtINT; /* ExtInt */
-		entry.vector          = 0;
-		entry.dest            = read_apic_id();
+		entry.mask		= IOAPIC_UNMASKED;
+		entry.trigger		= IOAPIC_EDGE;
+		entry.polarity		= IOAPIC_POL_HIGH;
+		entry.dest_mode		= IOAPIC_DEST_MODE_PHYSICAL;
+		entry.delivery_mode	= dest_ExtINT;
+		entry.dest		= read_apic_id();
 
 		/*
 		 * Add it to the IO-APIC irq-routing table:
@@ -1582,7 +1456,6 @@ void native_disable_io_apic(void)
 
 	if (cpu_has_apic || apic_from_smp_config())
 		disconnect_bsp_APIC(ioapic_i8259.pin != -1);
-
 }
 
 /*
@@ -1792,7 +1665,6 @@ static int __init timer_irq_works(void)
  * This is not complete - we should be able to fake
  * an edge even if it isn't on the 8259A...
  */
-
 static unsigned int startup_ioapic_irq(struct irq_data *data)
 {
 	int was_pending = 0, irq = data->irq;
@@ -1804,74 +1676,22 @@ static unsigned int startup_ioapic_irq(struct irq_data *data)
 		if (legacy_pic->irq_pending(irq))
 			was_pending = 1;
 	}
-	__unmask_ioapic(irqd_cfg(data));
+	__unmask_ioapic(data->chip_data);
 	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 
 	return was_pending;
 }
 
-/*
- * Level and edge triggered IO-APIC interrupts need different handling,
- * so we use two separate IRQ descriptors. Edge triggered IRQs can be
- * handled with the level-triggered descriptor, but that one has slightly
- * more overhead. Level-triggered interrupts cannot be handled with the
- * edge-triggered handler, without risking IRQ storms and other ugly
- * races.
- */
-
-static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, struct irq_cfg *cfg)
-{
-	int apic, pin;
-	struct irq_pin_list *entry;
-	u8 vector = cfg->vector;
-
-	for_each_irq_pin(entry, cfg->irq_2_pin) {
-		unsigned int reg;
-
-		apic = entry->apic;
-		pin = entry->pin;
-
-		io_apic_write(apic, 0x11 + pin*2, dest);
-		reg = io_apic_read(apic, 0x10 + pin*2);
-		reg &= ~IO_APIC_REDIR_VECTOR_MASK;
-		reg |= vector;
-		io_apic_modify(apic, 0x10 + pin*2, reg);
-	}
-}
-
-int native_ioapic_set_affinity(struct irq_data *data,
-			       const struct cpumask *mask,
-			       bool force)
-{
-	unsigned int dest, irq = data->irq;
-	unsigned long flags;
-	int ret;
-
-	if (!config_enabled(CONFIG_SMP))
-		return -EPERM;
-
-	raw_spin_lock_irqsave(&ioapic_lock, flags);
-	ret = apic_set_affinity(data, mask, &dest);
-	if (!ret) {
-		/* Only the high 8 bits are valid. */
-		dest = SET_APIC_LOGICAL_ID(dest);
-		__target_IO_APIC_irq(irq, dest, irqd_cfg(data));
-		ret = IRQ_SET_MASK_OK_NOCOPY;
-	}
-	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
-	return ret;
-}
-
 atomic_t irq_mis_count;
 
 #ifdef CONFIG_GENERIC_PENDING_IRQ
-static bool io_apic_level_ack_pending(struct irq_cfg *cfg)
+static bool io_apic_level_ack_pending(struct mp_chip_data *data)
 {
 	struct irq_pin_list *entry;
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&ioapic_lock, flags);
-	for_each_irq_pin(entry, cfg->irq_2_pin) {
+	for_each_irq_pin(entry, data->irq_2_pin) {
 		unsigned int reg;
 		int pin;
 
@@ -1888,18 +1708,17 @@ static bool io_apic_level_ack_pending(struct irq_cfg *cfg)
 	return false;
 }
 
-static inline bool ioapic_irqd_mask(struct irq_data *data, struct irq_cfg *cfg)
+static inline bool ioapic_irqd_mask(struct irq_data *data)
 {
 	/* If we are moving the irq we need to mask it */
 	if (unlikely(irqd_is_setaffinity_pending(data))) {
-		mask_ioapic(cfg);
+		mask_ioapic_irq(data);
 		return true;
 	}
 	return false;
 }
 
-static inline void ioapic_irqd_unmask(struct irq_data *data,
-				      struct irq_cfg *cfg, bool masked)
+static inline void ioapic_irqd_unmask(struct irq_data *data, bool masked)
 {
 	if (unlikely(masked)) {
 		/* Only migrate the irq if the ack has been received.
@@ -1928,31 +1747,30 @@ static inline void ioapic_irqd_unmask(struct irq_data *data,
 		 * accurate and is causing problems then it is a hardware bug
 		 * and you can go talk to the chipset vendor about it.
 		 */
-		if (!io_apic_level_ack_pending(cfg))
+		if (!io_apic_level_ack_pending(data->chip_data))
 			irq_move_masked_irq(data);
-		unmask_ioapic(cfg);
+		unmask_ioapic_irq(data);
 	}
 }
 #else
-static inline bool ioapic_irqd_mask(struct irq_data *data, struct irq_cfg *cfg)
+static inline bool ioapic_irqd_mask(struct irq_data *data)
 {
 	return false;
 }
-static inline void ioapic_irqd_unmask(struct irq_data *data,
-				      struct irq_cfg *cfg, bool masked)
+static inline void ioapic_irqd_unmask(struct irq_data *data, bool masked)
 {
 }
 #endif
 
-static void ack_ioapic_level(struct irq_data *data)
+static void ioapic_ack_level(struct irq_data *irq_data)
 {
-	struct irq_cfg *cfg = irqd_cfg(data);
-	int i, irq = data->irq;
+	struct irq_cfg *cfg = irqd_cfg(irq_data);
 	unsigned long v;
 	bool masked;
+	int i;
 
 	irq_complete_move(cfg);
-	masked = ioapic_irqd_mask(data, cfg);
+	masked = ioapic_irqd_mask(irq_data);
 
 	/*
 	 * It appears there is an erratum which affects at least version 0x11
@@ -2004,11 +1822,49 @@ static void ack_ioapic_level(struct irq_data *data)
 	 */
 	if (!(v & (1 << (i & 0x1f)))) {
 		atomic_inc(&irq_mis_count);
+		eoi_ioapic_pin(cfg->vector, irq_data->chip_data);
+	}
+
+	ioapic_irqd_unmask(irq_data, masked);
+}
+
+static void ioapic_ir_ack_level(struct irq_data *irq_data)
+{
+	struct mp_chip_data *data = irq_data->chip_data;
+
+	/*
+	 * Intr-remapping uses pin number as the virtual vector
+	 * in the RTE. Actual vector is programmed in
+	 * intr-remapping table entry. Hence for the io-apic
+	 * EOI we use the pin number.
+	 */
+	ack_APIC_irq();
+	eoi_ioapic_pin(data->entry.vector, data);
+}
 
-		eoi_ioapic_irq(irq, cfg);
+static int ioapic_set_affinity(struct irq_data *irq_data,
+			       const struct cpumask *mask, bool force)
+{
+	struct irq_data *parent = irq_data->parent_data;
+	struct mp_chip_data *data = irq_data->chip_data;
+	struct irq_pin_list *entry;
+	struct irq_cfg *cfg;
+	unsigned long flags;
+	int ret;
+
+	ret = parent->chip->irq_set_affinity(parent, mask, force);
+	raw_spin_lock_irqsave(&ioapic_lock, flags);
+	if (ret >= 0 && ret != IRQ_SET_MASK_OK_DONE) {
+		cfg = irqd_cfg(irq_data);
+		data->entry.dest = cfg->dest_apicid;
+		data->entry.vector = cfg->vector;
+		for_each_irq_pin(entry, data->irq_2_pin)
+			__ioapic_write_entry(entry->apic, entry->pin,
+					     data->entry);
 	}
+	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 
-	ioapic_irqd_unmask(data, cfg, masked);
+	return ret;
 }
 
 static struct irq_chip ioapic_chip __read_mostly = {
@@ -2016,10 +1872,20 @@ static struct irq_chip ioapic_chip __read_mostly = {
 	.irq_startup		= startup_ioapic_irq,
 	.irq_mask		= mask_ioapic_irq,
 	.irq_unmask		= unmask_ioapic_irq,
-	.irq_ack		= apic_ack_edge,
-	.irq_eoi		= ack_ioapic_level,
-	.irq_set_affinity	= native_ioapic_set_affinity,
-	.irq_retrigger		= apic_retrigger_irq,
+	.irq_ack		= irq_chip_ack_parent,
+	.irq_eoi		= ioapic_ack_level,
+	.irq_set_affinity	= ioapic_set_affinity,
+	.flags			= IRQCHIP_SKIP_SET_WAKE,
+};
+
+static struct irq_chip ioapic_ir_chip __read_mostly = {
+	.name			= "IR-IO-APIC",
+	.irq_startup		= startup_ioapic_irq,
+	.irq_mask		= mask_ioapic_irq,
+	.irq_unmask		= unmask_ioapic_irq,
+	.irq_ack		= irq_chip_ack_parent,
+	.irq_eoi		= ioapic_ir_ack_level,
+	.irq_set_affinity	= ioapic_set_affinity,
 	.flags			= IRQCHIP_SKIP_SET_WAKE,
 };
 
@@ -2113,12 +1979,12 @@ static inline void __init unlock_ExtINT_logic(void)
 
 	memset(&entry1, 0, sizeof(entry1));
 
-	entry1.dest_mode = 0;			/* physical delivery */
-	entry1.mask = 0;			/* unmask IRQ now */
+	entry1.dest_mode = IOAPIC_DEST_MODE_PHYSICAL;
+	entry1.mask = IOAPIC_UNMASKED;
 	entry1.dest = hard_smp_processor_id();
 	entry1.delivery_mode = dest_ExtINT;
 	entry1.polarity = entry0.polarity;
-	entry1.trigger = 0;
+	entry1.trigger = IOAPIC_EDGE;
 	entry1.vector = 0;
 
 	ioapic_write_entry(apic, pin, entry1);
@@ -2152,6 +2018,25 @@ static int __init disable_timer_pin_setup(char *arg)
 }
 early_param("disable_timer_pin_1", disable_timer_pin_setup);
 
+static int mp_alloc_timer_irq(int ioapic, int pin)
+{
+	int irq = -1;
+	struct irq_domain *domain = mp_ioapic_irqdomain(ioapic);
+
+	if (domain) {
+		struct irq_alloc_info info;
+
+		ioapic_set_alloc_attr(&info, NUMA_NO_NODE, 0, 0);
+		info.ioapic_id = mpc_ioapic_id(ioapic);
+		info.ioapic_pin = pin;
+		mutex_lock(&ioapic_mutex);
+		irq = alloc_isa_irq_from_domain(domain, 0, ioapic, pin, &info);
+		mutex_unlock(&ioapic_mutex);
+	}
+
+	return irq;
+}
+
 /*
  * This code may look a bit paranoid, but it's supposed to cooperate with
  * a wide range of boards and BIOS bugs.  Fortunately only the timer IRQ
@@ -2162,7 +2047,9 @@ early_param("disable_timer_pin_1", disable_timer_pin_setup);
  */
 static inline void __init check_timer(void)
 {
-	struct irq_cfg *cfg = irq_cfg(0);
+	struct irq_data *irq_data = irq_get_irq_data(0);
+	struct mp_chip_data *data = irq_data->chip_data;
+	struct irq_cfg *cfg = irqd_cfg(irq_data);
 	int node = cpu_to_node(0);
 	int apic1, pin1, apic2, pin2;
 	unsigned long flags;
@@ -2174,7 +2061,6 @@ static inline void __init check_timer(void)
 	 * get/set the timer IRQ vector:
 	 */
 	legacy_pic->mask(0);
-	assign_irq_vector(0, cfg, apic->target_cpus());
 
 	/*
 	 * As IRQ0 is to be enabled in the 8259A, the virtual
@@ -2215,23 +2101,21 @@ static inline void __init check_timer(void)
 	}
 
 	if (pin1 != -1) {
-		/*
-		 * Ok, does IRQ0 through the IOAPIC work?
-		 */
+		/* Ok, does IRQ0 through the IOAPIC work? */
 		if (no_pin1) {
-			add_pin_to_irq_node(cfg, node, apic1, pin1);
-			setup_timer_IRQ0_pin(apic1, pin1, cfg->vector);
+			mp_alloc_timer_irq(apic1, pin1);
 		} else {
-			/* for edge trigger, setup_ioapic_irq already
-			 * leave it unmasked.
+			/*
+			 * for edge trigger, it's already unmasked,
 			 * so only need to unmask if it is level-trigger
 			 * do we really have level trigger timer?
 			 */
 			int idx;
 			idx = find_irq_entry(apic1, pin1, mp_INT);
 			if (idx != -1 && irq_trigger(idx))
-				unmask_ioapic(cfg);
+				unmask_ioapic_irq(irq_get_chip_data(0));
 		}
+		irq_domain_activate_irq(irq_data);
 		if (timer_irq_works()) {
 			if (disable_timer_pin_1 > 0)
 				clear_IO_APIC_pin(0, pin1);
@@ -2251,8 +2135,8 @@ static inline void __init check_timer(void)
 		/*
 		 * legacy devices should be connected to IO APIC #0
 		 */
-		replace_pin_at_irq_node(cfg, node, apic1, pin1, apic2, pin2);
-		setup_timer_IRQ0_pin(apic2, pin2, cfg->vector);
+		replace_pin_at_irq_node(data, node, apic1, pin1, apic2, pin2);
+		irq_domain_activate_irq(irq_data);
 		legacy_pic->unmask(0);
 		if (timer_irq_works()) {
 			apic_printk(APIC_QUIET, KERN_INFO "....... works.\n");
@@ -2329,36 +2213,35 @@ out:
 
 static int mp_irqdomain_create(int ioapic)
 {
-	size_t size;
+	struct irq_alloc_info info;
+	struct irq_domain *parent;
 	int hwirqs = mp_ioapic_pin_count(ioapic);
 	struct ioapic *ip = &ioapics[ioapic];
 	struct ioapic_domain_cfg *cfg = &ip->irqdomain_cfg;
 	struct mp_ioapic_gsi *gsi_cfg = mp_ioapic_gsi_routing(ioapic);
 
-	size = sizeof(struct mp_pin_info) * mp_ioapic_pin_count(ioapic);
-	ip->pin_info = kzalloc(size, GFP_KERNEL);
-	if (!ip->pin_info)
-		return -ENOMEM;
-
 	if (cfg->type == IOAPIC_DOMAIN_INVALID)
 		return 0;
 
+	init_irq_alloc_info(&info, NULL);
+	info.type = X86_IRQ_ALLOC_TYPE_IOAPIC;
+	info.ioapic_id = mpc_ioapic_id(ioapic);
+	parent = irq_remapping_get_ir_irq_domain(&info);
+	if (!parent)
+		parent = x86_vector_domain;
+
 	ip->irqdomain = irq_domain_add_linear(cfg->dev, hwirqs, cfg->ops,
 					      (void *)(long)ioapic);
-	if(!ip->irqdomain) {
-		kfree(ip->pin_info);
-		ip->pin_info = NULL;
+	if (!ip->irqdomain)
 		return -ENOMEM;
-	}
+
+	ip->irqdomain->parent = parent;
 
 	if (cfg->type == IOAPIC_DOMAIN_LEGACY ||
 	    cfg->type == IOAPIC_DOMAIN_STRICT)
 		ioapic_dynirq_base = max(ioapic_dynirq_base,
 					 gsi_cfg->gsi_end + 1);
 
-	if (gsi_cfg->gsi_base == 0)
-		irq_set_default_host(ip->irqdomain);
-
 	return 0;
 }
 
@@ -2368,8 +2251,6 @@ static void ioapic_destroy_irqdomain(int idx)
 		irq_domain_remove(ioapics[idx].irqdomain);
 		ioapics[idx].irqdomain = NULL;
 	}
-	kfree(ioapics[idx].pin_info);
-	ioapics[idx].pin_info = NULL;
 }
 
 void __init setup_IO_APIC(void)
@@ -2399,20 +2280,6 @@ void __init setup_IO_APIC(void)
 	ioapic_initialized = 1;
 }
 
-/*
- *      Called after all the initialization is done. If we didn't find any
- *      APIC bugs then we can allow the modify fast path
- */
-
-static int __init io_apic_bug_finalize(void)
-{
-	if (sis_apic_bug == -1)
-		sis_apic_bug = 0;
-	return 0;
-}
-
-late_initcall(io_apic_bug_finalize);
-
 static void resume_ioapic_id(int ioapic_idx)
 {
 	unsigned long flags;
@@ -2451,20 +2318,6 @@ static int __init ioapic_init_ops(void)
 
 device_initcall(ioapic_init_ops);
 
-static int
-io_apic_setup_irq_pin(unsigned int irq, int node, struct io_apic_irq_attr *attr)
-{
-	struct irq_cfg *cfg = alloc_irq_and_cfg_at(irq, node);
-	int ret;
-
-	if (!cfg)
-		return -EINVAL;
-	ret = __add_pin_to_irq_node(cfg, node, attr->ioapic, attr->ioapic_pin);
-	if (!ret)
-		setup_ioapic_irq(irq, cfg, attr);
-	return ret;
-}
-
 static int io_apic_get_redir_entries(int ioapic)
 {
 	union IO_APIC_reg_01	reg_01;
@@ -2692,7 +2545,7 @@ void __init setup_ioapic_dest(void)
 		else
 			mask = apic->target_cpus();
 
-		x86_io_apic_ops.set_affinity(idata, mask, false);
+		irq_set_affinity(irq, mask);
 	}
 
 }
@@ -2737,7 +2590,7 @@ static struct resource * __init ioapic_setup_resources(void)
 	return res;
 }
 
-void __init native_io_apic_init_mappings(void)
+void __init io_apic_init_mappings(void)
 {
 	unsigned long ioapic_phys, idx = FIX_IO_APIC_BASE_0;
 	struct resource *ioapic_res;
@@ -2962,7 +2815,6 @@ int mp_unregister_ioapic(u32 gsi_base)
 {
 	int ioapic, pin;
 	int found = 0;
-	struct mp_pin_info *pin_info;
 
 	for_each_ioapic(ioapic)
 		if (ioapics[ioapic].gsi_config.gsi_base == gsi_base) {
@@ -2975,11 +2827,17 @@ int mp_unregister_ioapic(u32 gsi_base)
 	}
 
 	for_each_pin(ioapic, pin) {
-		pin_info = mp_pin_info(ioapic, pin);
-		if (pin_info->count) {
-			pr_warn("pin%d on IOAPIC%d is still in use.\n",
-				pin, ioapic);
-			return -EBUSY;
+		u32 gsi = mp_pin_to_gsi(ioapic, pin);
+		int irq = mp_map_gsi_to_irq(gsi, 0, NULL);
+		struct mp_chip_data *data;
+
+		if (irq >= 0) {
+			data = irq_get_chip_data(irq);
+			if (data && data->count) {
+				pr_warn("pin%d on IOAPIC%d is still in use.\n",
+					pin, ioapic);
+				return -EBUSY;
+			}
 		}
 	}
 
@@ -3006,108 +2864,141 @@ int mp_ioapic_registered(u32 gsi_base)
 	return 0;
 }
 
-static inline void set_io_apic_irq_attr(struct io_apic_irq_attr *irq_attr,
-					int ioapic, int ioapic_pin,
-					int trigger, int polarity)
+static void mp_irqdomain_get_attr(u32 gsi, struct mp_chip_data *data,
+				  struct irq_alloc_info *info)
 {
-	irq_attr->ioapic	= ioapic;
-	irq_attr->ioapic_pin	= ioapic_pin;
-	irq_attr->trigger	= trigger;
-	irq_attr->polarity	= polarity;
+	if (info && info->ioapic_valid) {
+		data->trigger = info->ioapic_trigger;
+		data->polarity = info->ioapic_polarity;
+	} else if (acpi_get_override_irq(gsi, &data->trigger,
+					 &data->polarity) < 0) {
+		/* PCI interrupts are always active low level triggered. */
+		data->trigger = IOAPIC_LEVEL;
+		data->polarity = IOAPIC_POL_LOW;
+	}
 }
 
-int mp_irqdomain_map(struct irq_domain *domain, unsigned int virq,
-		     irq_hw_number_t hwirq)
+static void mp_setup_entry(struct irq_cfg *cfg, struct mp_chip_data *data,
+			   struct IO_APIC_route_entry *entry)
 {
-	int ioapic = (int)(long)domain->host_data;
-	struct mp_pin_info *info = mp_pin_info(ioapic, hwirq);
-	struct io_apic_irq_attr attr;
+	memset(entry, 0, sizeof(*entry));
+	entry->delivery_mode = apic->irq_delivery_mode;
+	entry->dest_mode     = apic->irq_dest_mode;
+	entry->dest	     = cfg->dest_apicid;
+	entry->vector	     = cfg->vector;
+	entry->trigger	     = data->trigger;
+	entry->polarity	     = data->polarity;
+	/*
+	 * Mask level triggered irqs. Edge triggered irqs are masked
+	 * by the irq core code in case they fire.
+	 */
+	if (data->trigger == IOAPIC_LEVEL)
+		entry->mask = IOAPIC_MASKED;
+	else
+		entry->mask = IOAPIC_UNMASKED;
+}
 
-	/* Get default attribute if not set by caller yet */
-	if (!info->set) {
-		u32 gsi = mp_pin_to_gsi(ioapic, hwirq);
+int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq,
+		       unsigned int nr_irqs, void *arg)
+{
+	int ret, ioapic, pin;
+	struct irq_cfg *cfg;
+	struct irq_data *irq_data;
+	struct mp_chip_data *data;
+	struct irq_alloc_info *info = arg;
 
-		if (acpi_get_override_irq(gsi, &info->trigger,
-					  &info->polarity) < 0) {
-			/*
-			 * PCI interrupts are always polarity one level
-			 * triggered.
-			 */
-			info->trigger = 1;
-			info->polarity = 1;
-		}
-		info->node = NUMA_NO_NODE;
+	if (!info || nr_irqs > 1)
+		return -EINVAL;
+	irq_data = irq_domain_get_irq_data(domain, virq);
+	if (!irq_data)
+		return -EINVAL;
 
-		/*
-		 * setup_IO_APIC_irqs() programs all legacy IRQs with default
-		 * trigger and polarity attributes. Don't set the flag for that
-		 * case so the first legacy IRQ user could reprogram the pin
-		 * with real trigger and polarity attributes.
-		 */
-		if (virq >= nr_legacy_irqs() || info->count)
-			info->set = 1;
-	}
-	set_io_apic_irq_attr(&attr, ioapic, hwirq, info->trigger,
-			     info->polarity);
+	ioapic = mp_irqdomain_ioapic_idx(domain);
+	pin = info->ioapic_pin;
+	if (irq_find_mapping(domain, (irq_hw_number_t)pin) > 0)
+		return -EEXIST;
 
-	return io_apic_setup_irq_pin(virq, info->node, &attr);
-}
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
 
-void mp_irqdomain_unmap(struct irq_domain *domain, unsigned int virq)
-{
-	struct irq_data *data = irq_get_irq_data(virq);
-	struct irq_cfg *cfg = irq_cfg(virq);
-	int ioapic = (int)(long)domain->host_data;
-	int pin = (int)data->hwirq;
+	info->ioapic_entry = &data->entry;
+	ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, info);
+	if (ret < 0) {
+		kfree(data);
+		return ret;
+	}
+
+	INIT_LIST_HEAD(&data->irq_2_pin);
+	irq_data->hwirq = info->ioapic_pin;
+	irq_data->chip = (domain->parent == x86_vector_domain) ?
+			  &ioapic_chip : &ioapic_ir_chip;
+	irq_data->chip_data = data;
+	mp_irqdomain_get_attr(mp_pin_to_gsi(ioapic, pin), data, info);
+
+	cfg = irqd_cfg(irq_data);
+	add_pin_to_irq_node(data, ioapic_alloc_attr_node(info), ioapic, pin);
+	if (info->ioapic_entry)
+		mp_setup_entry(cfg, data, info->ioapic_entry);
+	mp_register_handler(virq, data->trigger);
+	if (virq < nr_legacy_irqs())
+		legacy_pic->mask(virq);
+
+	apic_printk(APIC_VERBOSE, KERN_DEBUG
+		    "IOAPIC[%d]: Set routing entry (%d-%d -> 0x%x -> IRQ %d Mode:%i Active:%i Dest:%d)\n",
+		    ioapic, mpc_ioapic_id(ioapic), pin, cfg->vector,
+		    virq, data->trigger, data->polarity, cfg->dest_apicid);
 
-	ioapic_mask_entry(ioapic, pin);
-	__remove_pin_from_irq(cfg, ioapic, pin);
-	WARN_ON(!list_empty(&cfg->irq_2_pin));
-	arch_teardown_hwirq(virq);
+	return 0;
 }
 
-int mp_set_gsi_attr(u32 gsi, int trigger, int polarity, int node)
+void mp_irqdomain_free(struct irq_domain *domain, unsigned int virq,
+		       unsigned int nr_irqs)
 {
-	int ret = 0;
-	int ioapic, pin;
-	struct mp_pin_info *info;
+	struct irq_data *irq_data;
+	struct mp_chip_data *data;
 
-	ioapic = mp_find_ioapic(gsi);
-	if (ioapic < 0)
-		return -ENODEV;
-
-	pin = mp_find_ioapic_pin(ioapic, gsi);
-	info = mp_pin_info(ioapic, pin);
-	trigger = trigger ? 1 : 0;
-	polarity = polarity ? 1 : 0;
-
-	mutex_lock(&ioapic_mutex);
-	if (!info->set) {
-		info->trigger = trigger;
-		info->polarity = polarity;
-		info->node = node;
-		info->set = 1;
-	} else if (info->trigger != trigger || info->polarity != polarity) {
-		ret = -EBUSY;
+	BUG_ON(nr_irqs != 1);
+	irq_data = irq_domain_get_irq_data(domain, virq);
+	if (irq_data && irq_data->chip_data) {
+		data = irq_data->chip_data;
+		__remove_pin_from_irq(data, mp_irqdomain_ioapic_idx(domain),
+				      (int)irq_data->hwirq);
+		WARN_ON(!list_empty(&data->irq_2_pin));
+		kfree(irq_data->chip_data);
 	}
-	mutex_unlock(&ioapic_mutex);
-
-	return ret;
+	irq_domain_free_irqs_top(domain, virq, nr_irqs);
 }
 
-/* Enable IOAPIC early just for system timer */
-void __init pre_init_apic_IRQ0(void)
+void mp_irqdomain_activate(struct irq_domain *domain,
+			   struct irq_data *irq_data)
 {
-	struct io_apic_irq_attr attr = { 0, 0, 0, 0 };
+	unsigned long flags;
+	struct irq_pin_list *entry;
+	struct mp_chip_data *data = irq_data->chip_data;
 
-	printk(KERN_INFO "Early APIC setup for system timer0\n");
-#ifndef CONFIG_SMP
-	physid_set_mask_of_physid(boot_cpu_physical_apicid,
-					 &phys_cpu_present_map);
-#endif
-	setup_local_APIC();
+	raw_spin_lock_irqsave(&ioapic_lock, flags);
+	for_each_irq_pin(entry, data->irq_2_pin)
+		__ioapic_write_entry(entry->apic, entry->pin, data->entry);
+	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
+}
 
-	io_apic_setup_irq_pin(0, 0, &attr);
-	irq_set_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq,
-				      "edge");
+void mp_irqdomain_deactivate(struct irq_domain *domain,
+			     struct irq_data *irq_data)
+{
+	/* It won't be called for IRQ with multiple IOAPIC pins associated */
+	ioapic_mask_entry(mp_irqdomain_ioapic_idx(domain),
+			  (int)irq_data->hwirq);
+}
+
+int mp_irqdomain_ioapic_idx(struct irq_domain *domain)
+{
+	return (int)(long)domain->host_data;
 }
+
+const struct irq_domain_ops mp_ioapic_irqdomain_ops = {
+	.alloc		= mp_irqdomain_alloc,
+	.free		= mp_irqdomain_free,
+	.activate	= mp_irqdomain_activate,
+	.deactivate	= mp_irqdomain_deactivate,
+};
diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c
index d6ba2d660dc5..1a9d735e09c6 100644
--- a/arch/x86/kernel/apic/msi.c
+++ b/arch/x86/kernel/apic/msi.c
@@ -3,6 +3,8 @@
  *
  * Copyright (C) 1997, 1998, 1999, 2000, 2009 Ingo Molnar, Hajnalka Szabo
  *	Moved from arch/x86/kernel/apic/io_apic.c.
+ * Jiang Liu <jiang.liu@linux.intel.com>
+ *	Convert to hierarchical irqdomain
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -14,22 +16,23 @@
 #include <linux/dmar.h>
 #include <linux/hpet.h>
 #include <linux/msi.h>
+#include <asm/irqdomain.h>
 #include <asm/msidef.h>
 #include <asm/hpet.h>
 #include <asm/hw_irq.h>
 #include <asm/apic.h>
 #include <asm/irq_remapping.h>
 
-void native_compose_msi_msg(struct pci_dev *pdev,
-			    unsigned int irq, unsigned int dest,
-			    struct msi_msg *msg, u8 hpet_id)
+static struct irq_domain *msi_default_domain;
+
+static void irq_msi_compose_msg(struct irq_data *data, struct msi_msg *msg)
 {
-	struct irq_cfg *cfg = irq_cfg(irq);
+	struct irq_cfg *cfg = irqd_cfg(data);
 
 	msg->address_hi = MSI_ADDR_BASE_HI;
 
 	if (x2apic_enabled())
-		msg->address_hi |= MSI_ADDR_EXT_DEST_ID(dest);
+		msg->address_hi |= MSI_ADDR_EXT_DEST_ID(cfg->dest_apicid);
 
 	msg->address_lo =
 		MSI_ADDR_BASE_LO |
@@ -39,7 +42,7 @@ void native_compose_msi_msg(struct pci_dev *pdev,
 		((apic->irq_delivery_mode != dest_LowestPrio) ?
 			MSI_ADDR_REDIRECTION_CPU :
 			MSI_ADDR_REDIRECTION_LOWPRI) |
-		MSI_ADDR_DEST_ID(dest);
+		MSI_ADDR_DEST_ID(cfg->dest_apicid);
 
 	msg->data =
 		MSI_DATA_TRIGGER_EDGE |
@@ -50,180 +53,201 @@ void native_compose_msi_msg(struct pci_dev *pdev,
 		MSI_DATA_VECTOR(cfg->vector);
 }
 
-static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq,
-			   struct msi_msg *msg, u8 hpet_id)
+/*
+ * IRQ Chip for MSI PCI/PCI-X/PCI-Express Devices,
+ * which implement the MSI or MSI-X Capability Structure.
+ */
+static struct irq_chip pci_msi_controller = {
+	.name			= "PCI-MSI",
+	.irq_unmask		= pci_msi_unmask_irq,
+	.irq_mask		= pci_msi_mask_irq,
+	.irq_ack		= irq_chip_ack_parent,
+	.irq_retrigger		= irq_chip_retrigger_hierarchy,
+	.irq_compose_msi_msg	= irq_msi_compose_msg,
+	.flags			= IRQCHIP_SKIP_SET_WAKE,
+};
+
+int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 {
-	struct irq_cfg *cfg;
-	int err;
-	unsigned dest;
+	struct irq_domain *domain;
+	struct irq_alloc_info info;
 
-	if (disable_apic)
-		return -ENXIO;
+	init_irq_alloc_info(&info, NULL);
+	info.type = X86_IRQ_ALLOC_TYPE_MSI;
+	info.msi_dev = dev;
 
-	cfg = irq_cfg(irq);
-	err = assign_irq_vector(irq, cfg, apic->target_cpus());
-	if (err)
-		return err;
+	domain = irq_remapping_get_irq_domain(&info);
+	if (domain == NULL)
+		domain = msi_default_domain;
+	if (domain == NULL)
+		return -ENOSYS;
 
-	err = apic->cpu_mask_to_apicid_and(cfg->domain,
-					   apic->target_cpus(), &dest);
-	if (err)
-		return err;
+	return pci_msi_domain_alloc_irqs(domain, dev, nvec, type);
+}
 
-	x86_msi.compose_msi_msg(pdev, irq, dest, msg, hpet_id);
+void native_teardown_msi_irq(unsigned int irq)
+{
+	irq_domain_free_irqs(irq, 1);
+}
 
-	return 0;
+static irq_hw_number_t pci_msi_get_hwirq(struct msi_domain_info *info,
+					 msi_alloc_info_t *arg)
+{
+	return arg->msi_hwirq;
 }
 
-static int
-msi_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force)
+static int pci_msi_prepare(struct irq_domain *domain, struct device *dev,
+			   int nvec, msi_alloc_info_t *arg)
 {
-	struct irq_cfg *cfg = irqd_cfg(data);
-	struct msi_msg msg;
-	unsigned int dest;
-	int ret;
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct msi_desc *desc = first_pci_msi_entry(pdev);
+
+	init_irq_alloc_info(arg, NULL);
+	arg->msi_dev = pdev;
+	if (desc->msi_attrib.is_msix) {
+		arg->type = X86_IRQ_ALLOC_TYPE_MSIX;
+	} else {
+		arg->type = X86_IRQ_ALLOC_TYPE_MSI;
+		arg->flags |= X86_IRQ_ALLOC_CONTIGUOUS_VECTORS;
+	}
 
-	ret = apic_set_affinity(data, mask, &dest);
-	if (ret)
-		return ret;
+	return 0;
+}
 
-	__get_cached_msi_msg(data->msi_desc, &msg);
+static void pci_msi_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc)
+{
+	arg->msi_hwirq = pci_msi_domain_calc_hwirq(arg->msi_dev, desc);
+}
+
+static struct msi_domain_ops pci_msi_domain_ops = {
+	.get_hwirq	= pci_msi_get_hwirq,
+	.msi_prepare	= pci_msi_prepare,
+	.set_desc	= pci_msi_set_desc,
+};
 
-	msg.data &= ~MSI_DATA_VECTOR_MASK;
-	msg.data |= MSI_DATA_VECTOR(cfg->vector);
-	msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK;
-	msg.address_lo |= MSI_ADDR_DEST_ID(dest);
+static struct msi_domain_info pci_msi_domain_info = {
+	.flags		= MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS |
+			  MSI_FLAG_PCI_MSIX,
+	.ops		= &pci_msi_domain_ops,
+	.chip		= &pci_msi_controller,
+	.handler	= handle_edge_irq,
+	.handler_name	= "edge",
+};
 
-	__pci_write_msi_msg(data->msi_desc, &msg);
+void arch_init_msi_domain(struct irq_domain *parent)
+{
+	if (disable_apic)
+		return;
 
-	return IRQ_SET_MASK_OK_NOCOPY;
+	msi_default_domain = pci_msi_create_irq_domain(NULL,
+					&pci_msi_domain_info, parent);
+	if (!msi_default_domain)
+		pr_warn("failed to initialize irqdomain for MSI/MSI-x.\n");
 }
 
-/*
- * IRQ Chip for MSI PCI/PCI-X/PCI-Express Devices,
- * which implement the MSI or MSI-X Capability Structure.
- */
-static struct irq_chip msi_chip = {
-	.name			= "PCI-MSI",
+#ifdef CONFIG_IRQ_REMAP
+static struct irq_chip pci_msi_ir_controller = {
+	.name			= "IR-PCI-MSI",
 	.irq_unmask		= pci_msi_unmask_irq,
 	.irq_mask		= pci_msi_mask_irq,
-	.irq_ack		= apic_ack_edge,
-	.irq_set_affinity	= msi_set_affinity,
-	.irq_retrigger		= apic_retrigger_irq,
+	.irq_ack		= irq_chip_ack_parent,
+	.irq_retrigger		= irq_chip_retrigger_hierarchy,
+	.irq_set_vcpu_affinity	= irq_chip_set_vcpu_affinity_parent,
 	.flags			= IRQCHIP_SKIP_SET_WAKE,
 };
 
-int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc,
-		  unsigned int irq_base, unsigned int irq_offset)
-{
-	struct irq_chip *chip = &msi_chip;
-	struct msi_msg msg;
-	unsigned int irq = irq_base + irq_offset;
-	int ret;
-
-	ret = msi_compose_msg(dev, irq, &msg, -1);
-	if (ret < 0)
-		return ret;
-
-	irq_set_msi_desc_off(irq_base, irq_offset, msidesc);
-
-	/*
-	 * MSI-X message is written per-IRQ, the offset is always 0.
-	 * MSI message denotes a contiguous group of IRQs, written for 0th IRQ.
-	 */
-	if (!irq_offset)
-		pci_write_msi_msg(irq, &msg);
+static struct msi_domain_info pci_msi_ir_domain_info = {
+	.flags		= MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS |
+			  MSI_FLAG_MULTI_PCI_MSI | MSI_FLAG_PCI_MSIX,
+	.ops		= &pci_msi_domain_ops,
+	.chip		= &pci_msi_ir_controller,
+	.handler	= handle_edge_irq,
+	.handler_name	= "edge",
+};
 
-	setup_remapped_irq(irq, irq_cfg(irq), chip);
+struct irq_domain *arch_create_msi_irq_domain(struct irq_domain *parent)
+{
+	return pci_msi_create_irq_domain(NULL, &pci_msi_ir_domain_info, parent);
+}
+#endif
 
-	irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge");
+#ifdef CONFIG_DMAR_TABLE
+static void dmar_msi_write_msg(struct irq_data *data, struct msi_msg *msg)
+{
+	dmar_msi_write(data->irq, msg);
+}
 
-	dev_dbg(&dev->dev, "irq %d for MSI/MSI-X\n", irq);
+static struct irq_chip dmar_msi_controller = {
+	.name			= "DMAR-MSI",
+	.irq_unmask		= dmar_msi_unmask,
+	.irq_mask		= dmar_msi_mask,
+	.irq_ack		= irq_chip_ack_parent,
+	.irq_set_affinity	= msi_domain_set_affinity,
+	.irq_retrigger		= irq_chip_retrigger_hierarchy,
+	.irq_compose_msi_msg	= irq_msi_compose_msg,
+	.irq_write_msi_msg	= dmar_msi_write_msg,
+	.flags			= IRQCHIP_SKIP_SET_WAKE,
+};
 
-	return 0;
+static irq_hw_number_t dmar_msi_get_hwirq(struct msi_domain_info *info,
+					  msi_alloc_info_t *arg)
+{
+	return arg->dmar_id;
 }
 
-int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
+static int dmar_msi_init(struct irq_domain *domain,
+			 struct msi_domain_info *info, unsigned int virq,
+			 irq_hw_number_t hwirq, msi_alloc_info_t *arg)
 {
-	struct msi_desc *msidesc;
-	unsigned int irq;
-	int node, ret;
+	irq_domain_set_info(domain, virq, arg->dmar_id, info->chip, NULL,
+			    handle_edge_irq, arg->dmar_data, "edge");
 
-	/* Multiple MSI vectors only supported with interrupt remapping */
-	if (type == PCI_CAP_ID_MSI && nvec > 1)
-		return 1;
+	return 0;
+}
 
-	node = dev_to_node(&dev->dev);
+static struct msi_domain_ops dmar_msi_domain_ops = {
+	.get_hwirq	= dmar_msi_get_hwirq,
+	.msi_init	= dmar_msi_init,
+};
 
-	list_for_each_entry(msidesc, &dev->msi_list, list) {
-		irq = irq_alloc_hwirq(node);
-		if (!irq)
-			return -ENOSPC;
+static struct msi_domain_info dmar_msi_domain_info = {
+	.ops		= &dmar_msi_domain_ops,
+	.chip		= &dmar_msi_controller,
+};
 
-		ret = setup_msi_irq(dev, msidesc, irq, 0);
-		if (ret < 0) {
-			irq_free_hwirq(irq);
-			return ret;
-		}
+static struct irq_domain *dmar_get_irq_domain(void)
+{
+	static struct irq_domain *dmar_domain;
+	static DEFINE_MUTEX(dmar_lock);
 
-	}
-	return 0;
-}
+	mutex_lock(&dmar_lock);
+	if (dmar_domain == NULL)
+		dmar_domain = msi_create_irq_domain(NULL, &dmar_msi_domain_info,
+						    x86_vector_domain);
+	mutex_unlock(&dmar_lock);
 
-void native_teardown_msi_irq(unsigned int irq)
-{
-	irq_free_hwirq(irq);
+	return dmar_domain;
 }
 
-#ifdef CONFIG_DMAR_TABLE
-static int
-dmar_msi_set_affinity(struct irq_data *data, const struct cpumask *mask,
-		      bool force)
+int dmar_alloc_hwirq(int id, int node, void *arg)
 {
-	struct irq_cfg *cfg = irqd_cfg(data);
-	unsigned int dest, irq = data->irq;
-	struct msi_msg msg;
-	int ret;
-
-	ret = apic_set_affinity(data, mask, &dest);
-	if (ret)
-		return ret;
+	struct irq_domain *domain = dmar_get_irq_domain();
+	struct irq_alloc_info info;
 
-	dmar_msi_read(irq, &msg);
+	if (!domain)
+		return -1;
 
-	msg.data &= ~MSI_DATA_VECTOR_MASK;
-	msg.data |= MSI_DATA_VECTOR(cfg->vector);
-	msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK;
-	msg.address_lo |= MSI_ADDR_DEST_ID(dest);
-	msg.address_hi = MSI_ADDR_BASE_HI | MSI_ADDR_EXT_DEST_ID(dest);
+	init_irq_alloc_info(&info, NULL);
+	info.type = X86_IRQ_ALLOC_TYPE_DMAR;
+	info.dmar_id = id;
+	info.dmar_data = arg;
 
-	dmar_msi_write(irq, &msg);
-
-	return IRQ_SET_MASK_OK_NOCOPY;
+	return irq_domain_alloc_irqs(domain, 1, node, &info);
 }
 
-static struct irq_chip dmar_msi_type = {
-	.name			= "DMAR_MSI",
-	.irq_unmask		= dmar_msi_unmask,
-	.irq_mask		= dmar_msi_mask,
-	.irq_ack		= apic_ack_edge,
-	.irq_set_affinity	= dmar_msi_set_affinity,
-	.irq_retrigger		= apic_retrigger_irq,
-	.flags			= IRQCHIP_SKIP_SET_WAKE,
-};
-
-int arch_setup_dmar_msi(unsigned int irq)
+void dmar_free_hwirq(int irq)
 {
-	int ret;
-	struct msi_msg msg;
-
-	ret = msi_compose_msg(NULL, irq, &msg, -1);
-	if (ret < 0)
-		return ret;
-	dmar_msi_write(irq, &msg);
-	irq_set_chip_and_handler_name(irq, &dmar_msi_type, handle_edge_irq,
-				      "edge");
-	return 0;
+	irq_domain_free_irqs(irq, 1);
 }
 #endif
 
@@ -231,56 +255,103 @@ int arch_setup_dmar_msi(unsigned int irq)
  * MSI message composition
  */
 #ifdef CONFIG_HPET_TIMER
+static inline int hpet_dev_id(struct irq_domain *domain)
+{
+	struct msi_domain_info *info = msi_get_domain_info(domain);
+
+	return (int)(long)info->data;
+}
 
-static int hpet_msi_set_affinity(struct irq_data *data,
-				 const struct cpumask *mask, bool force)
+static void hpet_msi_write_msg(struct irq_data *data, struct msi_msg *msg)
 {
-	struct irq_cfg *cfg = irqd_cfg(data);
-	struct msi_msg msg;
-	unsigned int dest;
-	int ret;
+	hpet_msi_write(data->handler_data, msg);
+}
 
-	ret = apic_set_affinity(data, mask, &dest);
-	if (ret)
-		return ret;
+static struct irq_chip hpet_msi_controller = {
+	.name = "HPET-MSI",
+	.irq_unmask = hpet_msi_unmask,
+	.irq_mask = hpet_msi_mask,
+	.irq_ack = irq_chip_ack_parent,
+	.irq_set_affinity = msi_domain_set_affinity,
+	.irq_retrigger = irq_chip_retrigger_hierarchy,
+	.irq_compose_msi_msg = irq_msi_compose_msg,
+	.irq_write_msi_msg = hpet_msi_write_msg,
+	.flags = IRQCHIP_SKIP_SET_WAKE,
+};
 
-	hpet_msi_read(data->handler_data, &msg);
+static irq_hw_number_t hpet_msi_get_hwirq(struct msi_domain_info *info,
+					  msi_alloc_info_t *arg)
+{
+	return arg->hpet_index;
+}
 
-	msg.data &= ~MSI_DATA_VECTOR_MASK;
-	msg.data |= MSI_DATA_VECTOR(cfg->vector);
-	msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK;
-	msg.address_lo |= MSI_ADDR_DEST_ID(dest);
+static int hpet_msi_init(struct irq_domain *domain,
+			 struct msi_domain_info *info, unsigned int virq,
+			 irq_hw_number_t hwirq, msi_alloc_info_t *arg)
+{
+	irq_set_status_flags(virq, IRQ_MOVE_PCNTXT);
+	irq_domain_set_info(domain, virq, arg->hpet_index, info->chip, NULL,
+			    handle_edge_irq, arg->hpet_data, "edge");
 
-	hpet_msi_write(data->handler_data, &msg);
+	return 0;
+}
 
-	return IRQ_SET_MASK_OK_NOCOPY;
+static void hpet_msi_free(struct irq_domain *domain,
+			  struct msi_domain_info *info, unsigned int virq)
+{
+	irq_clear_status_flags(virq, IRQ_MOVE_PCNTXT);
 }
 
-static struct irq_chip hpet_msi_type = {
-	.name = "HPET_MSI",
-	.irq_unmask = hpet_msi_unmask,
-	.irq_mask = hpet_msi_mask,
-	.irq_ack = apic_ack_edge,
-	.irq_set_affinity = hpet_msi_set_affinity,
-	.irq_retrigger = apic_retrigger_irq,
-	.flags = IRQCHIP_SKIP_SET_WAKE,
+static struct msi_domain_ops hpet_msi_domain_ops = {
+	.get_hwirq	= hpet_msi_get_hwirq,
+	.msi_init	= hpet_msi_init,
+	.msi_free	= hpet_msi_free,
+};
+
+static struct msi_domain_info hpet_msi_domain_info = {
+	.ops		= &hpet_msi_domain_ops,
+	.chip		= &hpet_msi_controller,
 };
 
-int default_setup_hpet_msi(unsigned int irq, unsigned int id)
+struct irq_domain *hpet_create_irq_domain(int hpet_id)
 {
-	struct irq_chip *chip = &hpet_msi_type;
-	struct msi_msg msg;
-	int ret;
+	struct irq_domain *parent;
+	struct irq_alloc_info info;
+	struct msi_domain_info *domain_info;
+
+	if (x86_vector_domain == NULL)
+		return NULL;
+
+	domain_info = kzalloc(sizeof(*domain_info), GFP_KERNEL);
+	if (!domain_info)
+		return NULL;
+
+	*domain_info = hpet_msi_domain_info;
+	domain_info->data = (void *)(long)hpet_id;
+
+	init_irq_alloc_info(&info, NULL);
+	info.type = X86_IRQ_ALLOC_TYPE_HPET;
+	info.hpet_id = hpet_id;
+	parent = irq_remapping_get_ir_irq_domain(&info);
+	if (parent == NULL)
+		parent = x86_vector_domain;
+	else
+		hpet_msi_controller.name = "IR-HPET-MSI";
+
+	return msi_create_irq_domain(NULL, domain_info, parent);
+}
 
-	ret = msi_compose_msg(NULL, irq, &msg, id);
-	if (ret < 0)
-		return ret;
+int hpet_assign_irq(struct irq_domain *domain, struct hpet_dev *dev,
+		    int dev_num)
+{
+	struct irq_alloc_info info;
 
-	hpet_msi_write(irq_get_handler_data(irq), &msg);
-	irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
-	setup_remapped_irq(irq, irq_cfg(irq), chip);
+	init_irq_alloc_info(&info, NULL);
+	info.type = X86_IRQ_ALLOC_TYPE_HPET;
+	info.hpet_data = dev;
+	info.hpet_id = hpet_dev_id(domain);
+	info.hpet_index = dev_num;
 
-	irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge");
-	return 0;
+	return irq_domain_alloc_irqs(domain, 1, NUMA_NO_NODE, &info);
 }
 #endif
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index 6cedd7914581..28eba2d38b15 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -3,6 +3,8 @@
  *
  * Copyright (C) 1997, 1998, 1999, 2000, 2009 Ingo Molnar, Hajnalka Szabo
  *	Moved from arch/x86/kernel/apic/io_apic.c.
+ * Jiang Liu <jiang.liu@linux.intel.com>
+ *	Enable support of hierarchical irqdomains
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -11,15 +13,28 @@
 #include <linux/interrupt.h>
 #include <linux/init.h>
 #include <linux/compiler.h>
-#include <linux/irqdomain.h>
 #include <linux/slab.h>
+#include <asm/irqdomain.h>
 #include <asm/hw_irq.h>
 #include <asm/apic.h>
 #include <asm/i8259.h>
 #include <asm/desc.h>
 #include <asm/irq_remapping.h>
 
+struct apic_chip_data {
+	struct irq_cfg		cfg;
+	cpumask_var_t		domain;
+	cpumask_var_t		old_domain;
+	u8			move_in_progress : 1;
+};
+
+struct irq_domain *x86_vector_domain;
 static DEFINE_RAW_SPINLOCK(vector_lock);
+static cpumask_var_t vector_cpumask;
+static struct irq_chip lapic_controller;
+#ifdef	CONFIG_X86_IO_APIC
+static struct apic_chip_data *legacy_irq_data[NR_IRQS_LEGACY];
+#endif
 
 void lock_vector_lock(void)
 {
@@ -34,71 +49,59 @@ void unlock_vector_lock(void)
 	raw_spin_unlock(&vector_lock);
 }
 
-struct irq_cfg *irq_cfg(unsigned int irq)
+static struct apic_chip_data *apic_chip_data(struct irq_data *irq_data)
 {
-	return irq_get_chip_data(irq);
+	if (!irq_data)
+		return NULL;
+
+	while (irq_data->parent_data)
+		irq_data = irq_data->parent_data;
+
+	return irq_data->chip_data;
 }
 
 struct irq_cfg *irqd_cfg(struct irq_data *irq_data)
 {
-	return irq_data->chip_data;
+	struct apic_chip_data *data = apic_chip_data(irq_data);
+
+	return data ? &data->cfg : NULL;
 }
 
-static struct irq_cfg *alloc_irq_cfg(unsigned int irq, int node)
+struct irq_cfg *irq_cfg(unsigned int irq)
 {
-	struct irq_cfg *cfg;
+	return irqd_cfg(irq_get_irq_data(irq));
+}
 
-	cfg = kzalloc_node(sizeof(*cfg), GFP_KERNEL, node);
-	if (!cfg)
+static struct apic_chip_data *alloc_apic_chip_data(int node)
+{
+	struct apic_chip_data *data;
+
+	data = kzalloc_node(sizeof(*data), GFP_KERNEL, node);
+	if (!data)
 		return NULL;
-	if (!zalloc_cpumask_var_node(&cfg->domain, GFP_KERNEL, node))
-		goto out_cfg;
-	if (!zalloc_cpumask_var_node(&cfg->old_domain, GFP_KERNEL, node))
+	if (!zalloc_cpumask_var_node(&data->domain, GFP_KERNEL, node))
+		goto out_data;
+	if (!zalloc_cpumask_var_node(&data->old_domain, GFP_KERNEL, node))
 		goto out_domain;
-#ifdef	CONFIG_X86_IO_APIC
-	INIT_LIST_HEAD(&cfg->irq_2_pin);
-#endif
-	return cfg;
+	return data;
 out_domain:
-	free_cpumask_var(cfg->domain);
-out_cfg:
-	kfree(cfg);
+	free_cpumask_var(data->domain);
+out_data:
+	kfree(data);
 	return NULL;
 }
 
-struct irq_cfg *alloc_irq_and_cfg_at(unsigned int at, int node)
+static void free_apic_chip_data(struct apic_chip_data *data)
 {
-	int res = irq_alloc_desc_at(at, node);
-	struct irq_cfg *cfg;
-
-	if (res < 0) {
-		if (res != -EEXIST)
-			return NULL;
-		cfg = irq_cfg(at);
-		if (cfg)
-			return cfg;
+	if (data) {
+		free_cpumask_var(data->domain);
+		free_cpumask_var(data->old_domain);
+		kfree(data);
 	}
-
-	cfg = alloc_irq_cfg(at, node);
-	if (cfg)
-		irq_set_chip_data(at, cfg);
-	else
-		irq_free_desc(at);
-	return cfg;
-}
-
-static void free_irq_cfg(unsigned int at, struct irq_cfg *cfg)
-{
-	if (!cfg)
-		return;
-	irq_set_chip_data(at, NULL);
-	free_cpumask_var(cfg->domain);
-	free_cpumask_var(cfg->old_domain);
-	kfree(cfg);
 }
 
-static int
-__assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask)
+static int __assign_irq_vector(int irq, struct apic_chip_data *d,
+			       const struct cpumask *mask)
 {
 	/*
 	 * NOTE! The local APIC isn't very good at handling
@@ -114,36 +117,33 @@ __assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask)
 	static int current_vector = FIRST_EXTERNAL_VECTOR + VECTOR_OFFSET_START;
 	static int current_offset = VECTOR_OFFSET_START % 16;
 	int cpu, err;
-	cpumask_var_t tmp_mask;
 
-	if (cfg->move_in_progress)
+	if (d->move_in_progress)
 		return -EBUSY;
 
-	if (!alloc_cpumask_var(&tmp_mask, GFP_ATOMIC))
-		return -ENOMEM;
-
 	/* Only try and allocate irqs on cpus that are present */
 	err = -ENOSPC;
-	cpumask_clear(cfg->old_domain);
+	cpumask_clear(d->old_domain);
 	cpu = cpumask_first_and(mask, cpu_online_mask);
 	while (cpu < nr_cpu_ids) {
 		int new_cpu, vector, offset;
 
-		apic->vector_allocation_domain(cpu, tmp_mask, mask);
+		apic->vector_allocation_domain(cpu, vector_cpumask, mask);
 
-		if (cpumask_subset(tmp_mask, cfg->domain)) {
+		if (cpumask_subset(vector_cpumask, d->domain)) {
 			err = 0;
-			if (cpumask_equal(tmp_mask, cfg->domain))
+			if (cpumask_equal(vector_cpumask, d->domain))
 				break;
 			/*
 			 * New cpumask using the vector is a proper subset of
 			 * the current in use mask. So cleanup the vector
 			 * allocation for the members that are not used anymore.
 			 */
-			cpumask_andnot(cfg->old_domain, cfg->domain, tmp_mask);
-			cfg->move_in_progress =
-			   cpumask_intersects(cfg->old_domain, cpu_online_mask);
-			cpumask_and(cfg->domain, cfg->domain, tmp_mask);
+			cpumask_andnot(d->old_domain, d->domain,
+				       vector_cpumask);
+			d->move_in_progress =
+			   cpumask_intersects(d->old_domain, cpu_online_mask);
+			cpumask_and(d->domain, d->domain, vector_cpumask);
 			break;
 		}
 
@@ -157,16 +157,18 @@ next:
 		}
 
 		if (unlikely(current_vector == vector)) {
-			cpumask_or(cfg->old_domain, cfg->old_domain, tmp_mask);
-			cpumask_andnot(tmp_mask, mask, cfg->old_domain);
-			cpu = cpumask_first_and(tmp_mask, cpu_online_mask);
+			cpumask_or(d->old_domain, d->old_domain,
+				   vector_cpumask);
+			cpumask_andnot(vector_cpumask, mask, d->old_domain);
+			cpu = cpumask_first_and(vector_cpumask,
+						cpu_online_mask);
 			continue;
 		}
 
 		if (test_bit(vector, used_vectors))
 			goto next;
 
-		for_each_cpu_and(new_cpu, tmp_mask, cpu_online_mask) {
+		for_each_cpu_and(new_cpu, vector_cpumask, cpu_online_mask) {
 			if (per_cpu(vector_irq, new_cpu)[vector] >
 			    VECTOR_UNDEFINED)
 				goto next;
@@ -174,55 +176,73 @@ next:
 		/* Found one! */
 		current_vector = vector;
 		current_offset = offset;
-		if (cfg->vector) {
-			cpumask_copy(cfg->old_domain, cfg->domain);
-			cfg->move_in_progress =
-			   cpumask_intersects(cfg->old_domain, cpu_online_mask);
+		if (d->cfg.vector) {
+			cpumask_copy(d->old_domain, d->domain);
+			d->move_in_progress =
+			   cpumask_intersects(d->old_domain, cpu_online_mask);
 		}
-		for_each_cpu_and(new_cpu, tmp_mask, cpu_online_mask)
+		for_each_cpu_and(new_cpu, vector_cpumask, cpu_online_mask)
 			per_cpu(vector_irq, new_cpu)[vector] = irq;
-		cfg->vector = vector;
-		cpumask_copy(cfg->domain, tmp_mask);
+		d->cfg.vector = vector;
+		cpumask_copy(d->domain, vector_cpumask);
 		err = 0;
 		break;
 	}
-	free_cpumask_var(tmp_mask);
+
+	if (!err) {
+		/* cache destination APIC IDs into cfg->dest_apicid */
+		err = apic->cpu_mask_to_apicid_and(mask, d->domain,
+						   &d->cfg.dest_apicid);
+	}
 
 	return err;
 }
 
-int assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask)
+static int assign_irq_vector(int irq, struct apic_chip_data *data,
+			     const struct cpumask *mask)
 {
 	int err;
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&vector_lock, flags);
-	err = __assign_irq_vector(irq, cfg, mask);
+	err = __assign_irq_vector(irq, data, mask);
 	raw_spin_unlock_irqrestore(&vector_lock, flags);
 	return err;
 }
 
-void clear_irq_vector(int irq, struct irq_cfg *cfg)
+static int assign_irq_vector_policy(int irq, int node,
+				    struct apic_chip_data *data,
+				    struct irq_alloc_info *info)
+{
+	if (info && info->mask)
+		return assign_irq_vector(irq, data, info->mask);
+	if (node != NUMA_NO_NODE &&
+	    assign_irq_vector(irq, data, cpumask_of_node(node)) == 0)
+		return 0;
+	return assign_irq_vector(irq, data, apic->target_cpus());
+}
+
+static void clear_irq_vector(int irq, struct apic_chip_data *data)
 {
 	int cpu, vector;
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&vector_lock, flags);
-	BUG_ON(!cfg->vector);
+	BUG_ON(!data->cfg.vector);
 
-	vector = cfg->vector;
-	for_each_cpu_and(cpu, cfg->domain, cpu_online_mask)
+	vector = data->cfg.vector;
+	for_each_cpu_and(cpu, data->domain, cpu_online_mask)
 		per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED;
 
-	cfg->vector = 0;
-	cpumask_clear(cfg->domain);
+	data->cfg.vector = 0;
+	cpumask_clear(data->domain);
 
-	if (likely(!cfg->move_in_progress)) {
+	if (likely(!data->move_in_progress)) {
 		raw_spin_unlock_irqrestore(&vector_lock, flags);
 		return;
 	}
 
-	for_each_cpu_and(cpu, cfg->old_domain, cpu_online_mask) {
+	for_each_cpu_and(cpu, data->old_domain, cpu_online_mask) {
 		for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS;
 		     vector++) {
 			if (per_cpu(vector_irq, cpu)[vector] != irq)
@@ -231,10 +251,95 @@ void clear_irq_vector(int irq, struct irq_cfg *cfg)
 			break;
 		}
 	}
-	cfg->move_in_progress = 0;
+	data->move_in_progress = 0;
 	raw_spin_unlock_irqrestore(&vector_lock, flags);
 }
 
+void init_irq_alloc_info(struct irq_alloc_info *info,
+			 const struct cpumask *mask)
+{
+	memset(info, 0, sizeof(*info));
+	info->mask = mask;
+}
+
+void copy_irq_alloc_info(struct irq_alloc_info *dst, struct irq_alloc_info *src)
+{
+	if (src)
+		*dst = *src;
+	else
+		memset(dst, 0, sizeof(*dst));
+}
+
+static void x86_vector_free_irqs(struct irq_domain *domain,
+				 unsigned int virq, unsigned int nr_irqs)
+{
+	struct irq_data *irq_data;
+	int i;
+
+	for (i = 0; i < nr_irqs; i++) {
+		irq_data = irq_domain_get_irq_data(x86_vector_domain, virq + i);
+		if (irq_data && irq_data->chip_data) {
+			clear_irq_vector(virq + i, irq_data->chip_data);
+			free_apic_chip_data(irq_data->chip_data);
+#ifdef	CONFIG_X86_IO_APIC
+			if (virq + i < nr_legacy_irqs())
+				legacy_irq_data[virq + i] = NULL;
+#endif
+			irq_domain_reset_irq_data(irq_data);
+		}
+	}
+}
+
+static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq,
+				 unsigned int nr_irqs, void *arg)
+{
+	struct irq_alloc_info *info = arg;
+	struct apic_chip_data *data;
+	struct irq_data *irq_data;
+	int i, err;
+
+	if (disable_apic)
+		return -ENXIO;
+
+	/* Currently vector allocator can't guarantee contiguous allocations */
+	if ((info->flags & X86_IRQ_ALLOC_CONTIGUOUS_VECTORS) && nr_irqs > 1)
+		return -ENOSYS;
+
+	for (i = 0; i < nr_irqs; i++) {
+		irq_data = irq_domain_get_irq_data(domain, virq + i);
+		BUG_ON(!irq_data);
+#ifdef	CONFIG_X86_IO_APIC
+		if (virq + i < nr_legacy_irqs() && legacy_irq_data[virq + i])
+			data = legacy_irq_data[virq + i];
+		else
+#endif
+			data = alloc_apic_chip_data(irq_data->node);
+		if (!data) {
+			err = -ENOMEM;
+			goto error;
+		}
+
+		irq_data->chip = &lapic_controller;
+		irq_data->chip_data = data;
+		irq_data->hwirq = virq + i;
+		err = assign_irq_vector_policy(virq, irq_data->node, data,
+					       info);
+		if (err)
+			goto error;
+	}
+
+	return 0;
+
+error:
+	x86_vector_free_irqs(domain, virq, i + 1);
+	return err;
+}
+
+static const struct irq_domain_ops x86_vector_domain_ops = {
+	.alloc	= x86_vector_alloc_irqs,
+	.free	= x86_vector_free_irqs,
+};
+
 int __init arch_probe_nr_irqs(void)
 {
 	int nr;
@@ -258,8 +363,43 @@ int __init arch_probe_nr_irqs(void)
 	return nr_legacy_irqs();
 }
 
+#ifdef	CONFIG_X86_IO_APIC
+static void init_legacy_irqs(void)
+{
+	int i, node = cpu_to_node(0);
+	struct apic_chip_data *data;
+
+	/*
+	 * For legacy IRQ's, start with assigning irq0 to irq15 to
+	 * ISA_IRQ_VECTOR(i) for all cpu's.
+	 */
+	for (i = 0; i < nr_legacy_irqs(); i++) {
+		data = legacy_irq_data[i] = alloc_apic_chip_data(node);
+		BUG_ON(!data);
+
+		data->cfg.vector = ISA_IRQ_VECTOR(i);
+		cpumask_setall(data->domain);
+		irq_set_chip_data(i, data);
+	}
+}
+#else
+static void init_legacy_irqs(void) { }
+#endif
+
 int __init arch_early_irq_init(void)
 {
+	init_legacy_irqs();
+
+	x86_vector_domain = irq_domain_add_tree(NULL, &x86_vector_domain_ops,
+						NULL);
+	BUG_ON(x86_vector_domain == NULL);
+	irq_set_default_host(x86_vector_domain);
+
+	arch_init_msi_domain(x86_vector_domain);
+	arch_init_htirq_domain(x86_vector_domain);
+
+	BUG_ON(!alloc_cpumask_var(&vector_cpumask, GFP_KERNEL));
+
 	return arch_early_ioapic_init();
 }
 
@@ -267,7 +407,7 @@ static void __setup_vector_irq(int cpu)
 {
 	/* Initialize vector_irq on a new cpu */
 	int irq, vector;
-	struct irq_cfg *cfg;
+	struct apic_chip_data *data;
 
 	/*
 	 * vector_lock will make sure that we don't run into irq vector
@@ -277,13 +417,13 @@ static void __setup_vector_irq(int cpu)
 	raw_spin_lock(&vector_lock);
 	/* Mark the inuse vectors */
 	for_each_active_irq(irq) {
-		cfg = irq_cfg(irq);
-		if (!cfg)
+		data = apic_chip_data(irq_get_irq_data(irq));
+		if (!data)
 			continue;
 
-		if (!cpumask_test_cpu(cpu, cfg->domain))
+		if (!cpumask_test_cpu(cpu, data->domain))
 			continue;
-		vector = cfg->vector;
+		vector = data->cfg.vector;
 		per_cpu(vector_irq, cpu)[vector] = irq;
 	}
 	/* Mark the free vectors */
@@ -292,8 +432,8 @@ static void __setup_vector_irq(int cpu)
 		if (irq <= VECTOR_UNDEFINED)
 			continue;
 
-		cfg = irq_cfg(irq);
-		if (!cpumask_test_cpu(cpu, cfg->domain))
+		data = apic_chip_data(irq_get_irq_data(irq));
+		if (!cpumask_test_cpu(cpu, data->domain))
 			per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED;
 	}
 	raw_spin_unlock(&vector_lock);
@@ -314,20 +454,20 @@ void setup_vector_irq(int cpu)
 	 * legacy vector to irq mapping:
 	 */
 	for (irq = 0; irq < nr_legacy_irqs(); irq++)
-		per_cpu(vector_irq, cpu)[IRQ0_VECTOR + irq] = irq;
+		per_cpu(vector_irq, cpu)[ISA_IRQ_VECTOR(irq)] = irq;
 
 	__setup_vector_irq(cpu);
 }
 
-int apic_retrigger_irq(struct irq_data *data)
+static int apic_retrigger_irq(struct irq_data *irq_data)
 {
-	struct irq_cfg *cfg = irqd_cfg(data);
+	struct apic_chip_data *data = apic_chip_data(irq_data);
 	unsigned long flags;
 	int cpu;
 
 	raw_spin_lock_irqsave(&vector_lock, flags);
-	cpu = cpumask_first_and(cfg->domain, cpu_online_mask);
-	apic->send_IPI_mask(cpumask_of(cpu), cfg->vector);
+	cpu = cpumask_first_and(data->domain, cpu_online_mask);
+	apic->send_IPI_mask(cpumask_of(cpu), data->cfg.vector);
 	raw_spin_unlock_irqrestore(&vector_lock, flags);
 
 	return 1;
@@ -340,73 +480,76 @@ void apic_ack_edge(struct irq_data *data)
 	ack_APIC_irq();
 }
 
-/*
- * Either sets data->affinity to a valid value, and returns
- * ->cpu_mask_to_apicid of that in dest_id, or returns -1 and
- * leaves data->affinity untouched.
- */
-int apic_set_affinity(struct irq_data *data, const struct cpumask *mask,
-		      unsigned int *dest_id)
+static int apic_set_affinity(struct irq_data *irq_data,
+			     const struct cpumask *dest, bool force)
 {
-	struct irq_cfg *cfg = irqd_cfg(data);
-	unsigned int irq = data->irq;
-	int err;
+	struct apic_chip_data *data = irq_data->chip_data;
+	int err, irq = irq_data->irq;
 
 	if (!config_enabled(CONFIG_SMP))
 		return -EPERM;
 
-	if (!cpumask_intersects(mask, cpu_online_mask))
+	if (!cpumask_intersects(dest, cpu_online_mask))
 		return -EINVAL;
 
-	err = assign_irq_vector(irq, cfg, mask);
-	if (err)
-		return err;
-
-	err = apic->cpu_mask_to_apicid_and(mask, cfg->domain, dest_id);
+	err = assign_irq_vector(irq, data, dest);
 	if (err) {
-		if (assign_irq_vector(irq, cfg, data->affinity))
+		struct irq_data *top = irq_get_irq_data(irq);
+
+		if (assign_irq_vector(irq, data, top->affinity))
 			pr_err("Failed to recover vector for irq %d\n", irq);
 		return err;
 	}
 
-	cpumask_copy(data->affinity, mask);
-
-	return 0;
+	return IRQ_SET_MASK_OK;
 }
 
+static struct irq_chip lapic_controller = {
+	.irq_ack		= apic_ack_edge,
+	.irq_set_affinity	= apic_set_affinity,
+	.irq_retrigger		= apic_retrigger_irq,
+};
+
 #ifdef CONFIG_SMP
-void send_cleanup_vector(struct irq_cfg *cfg)
+static void __send_cleanup_vector(struct apic_chip_data *data)
 {
 	cpumask_var_t cleanup_mask;
 
 	if (unlikely(!alloc_cpumask_var(&cleanup_mask, GFP_ATOMIC))) {
 		unsigned int i;
 
-		for_each_cpu_and(i, cfg->old_domain, cpu_online_mask)
+		for_each_cpu_and(i, data->old_domain, cpu_online_mask)
 			apic->send_IPI_mask(cpumask_of(i),
 					    IRQ_MOVE_CLEANUP_VECTOR);
 	} else {
-		cpumask_and(cleanup_mask, cfg->old_domain, cpu_online_mask);
+		cpumask_and(cleanup_mask, data->old_domain, cpu_online_mask);
 		apic->send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR);
 		free_cpumask_var(cleanup_mask);
 	}
-	cfg->move_in_progress = 0;
+	data->move_in_progress = 0;
+}
+
+void send_cleanup_vector(struct irq_cfg *cfg)
+{
+	struct apic_chip_data *data;
+
+	data = container_of(cfg, struct apic_chip_data, cfg);
+	if (data->move_in_progress)
+		__send_cleanup_vector(data);
 }
 
 asmlinkage __visible void smp_irq_move_cleanup_interrupt(void)
 {
 	unsigned vector, me;
 
-	ack_APIC_irq();
-	irq_enter();
-	exit_idle();
+	entering_ack_irq();
 
 	me = smp_processor_id();
 	for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) {
 		int irq;
 		unsigned int irr;
 		struct irq_desc *desc;
-		struct irq_cfg *cfg;
+		struct apic_chip_data *data;
 
 		irq = __this_cpu_read(vector_irq[vector]);
 
@@ -417,8 +560,8 @@ asmlinkage __visible void smp_irq_move_cleanup_interrupt(void)
 		if (!desc)
 			continue;
 
-		cfg = irq_cfg(irq);
-		if (!cfg)
+		data = apic_chip_data(&desc->irq_data);
+		if (!data)
 			continue;
 
 		raw_spin_lock(&desc->lock);
@@ -427,10 +570,11 @@ asmlinkage __visible void smp_irq_move_cleanup_interrupt(void)
 		 * Check if the irq migration is in progress. If so, we
 		 * haven't received the cleanup request yet for this irq.
 		 */
-		if (cfg->move_in_progress)
+		if (data->move_in_progress)
 			goto unlock;
 
-		if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain))
+		if (vector == data->cfg.vector &&
+		    cpumask_test_cpu(me, data->domain))
 			goto unlock;
 
 		irr = apic_read(APIC_IRR + (vector / 32 * 0x10));
@@ -450,20 +594,21 @@ unlock:
 		raw_spin_unlock(&desc->lock);
 	}
 
-	irq_exit();
+	exiting_irq();
 }
 
 static void __irq_complete_move(struct irq_cfg *cfg, unsigned vector)
 {
 	unsigned me;
+	struct apic_chip_data *data;
 
-	if (likely(!cfg->move_in_progress))
+	data = container_of(cfg, struct apic_chip_data, cfg);
+	if (likely(!data->move_in_progress))
 		return;
 
 	me = smp_processor_id();
-
-	if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain))
-		send_cleanup_vector(cfg);
+	if (vector == data->cfg.vector && cpumask_test_cpu(me, data->domain))
+		__send_cleanup_vector(data);
 }
 
 void irq_complete_move(struct irq_cfg *cfg)
@@ -475,46 +620,11 @@ void irq_force_complete_move(int irq)
 {
 	struct irq_cfg *cfg = irq_cfg(irq);
 
-	if (!cfg)
-		return;
-
-	__irq_complete_move(cfg, cfg->vector);
+	if (cfg)
+		__irq_complete_move(cfg, cfg->vector);
 }
 #endif
 
-/*
- * Dynamic irq allocate and deallocation. Should be replaced by irq domains!
- */
-int arch_setup_hwirq(unsigned int irq, int node)
-{
-	struct irq_cfg *cfg;
-	unsigned long flags;
-	int ret;
-
-	cfg = alloc_irq_cfg(irq, node);
-	if (!cfg)
-		return -ENOMEM;
-
-	raw_spin_lock_irqsave(&vector_lock, flags);
-	ret = __assign_irq_vector(irq, cfg, apic->target_cpus());
-	raw_spin_unlock_irqrestore(&vector_lock, flags);
-
-	if (!ret)
-		irq_set_chip_data(irq, cfg);
-	else
-		free_irq_cfg(irq, cfg);
-	return ret;
-}
-
-void arch_teardown_hwirq(unsigned int irq)
-{
-	struct irq_cfg *cfg = irq_cfg(irq);
-
-	free_remapped_irq(irq);
-	clear_irq_vector(irq, cfg);
-	free_irq_cfg(irq, cfg);
-}
-
 static void __init print_APIC_field(int base)
 {
 	int i;
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
index 6fae733e9194..3ffd925655e0 100644
--- a/arch/x86/kernel/apic/x2apic_phys.c
+++ b/arch/x86/kernel/apic/x2apic_phys.c
@@ -21,11 +21,13 @@ early_param("x2apic_phys", set_x2apic_phys_mode);
 
 static bool x2apic_fadt_phys(void)
 {
+#ifdef CONFIG_ACPI
 	if ((acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID) &&
 		(acpi_gbl_FADT.flags & ACPI_FADT_APIC_PHYSICAL)) {
 		printk(KERN_DEBUG "System requires x2apic physical mode\n");
 		return true;
 	}
+#endif
 	return false;
 }
 
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index 9f6b9341950f..8e3d22a1af94 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -41,6 +41,25 @@ void common(void) {
 	OFFSET(pbe_orig_address, pbe, orig_address);
 	OFFSET(pbe_next, pbe, next);
 
+#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
+	BLANK();
+	OFFSET(IA32_SIGCONTEXT_ax, sigcontext_ia32, ax);
+	OFFSET(IA32_SIGCONTEXT_bx, sigcontext_ia32, bx);
+	OFFSET(IA32_SIGCONTEXT_cx, sigcontext_ia32, cx);
+	OFFSET(IA32_SIGCONTEXT_dx, sigcontext_ia32, dx);
+	OFFSET(IA32_SIGCONTEXT_si, sigcontext_ia32, si);
+	OFFSET(IA32_SIGCONTEXT_di, sigcontext_ia32, di);
+	OFFSET(IA32_SIGCONTEXT_bp, sigcontext_ia32, bp);
+	OFFSET(IA32_SIGCONTEXT_sp, sigcontext_ia32, sp);
+	OFFSET(IA32_SIGCONTEXT_ip, sigcontext_ia32, ip);
+
+	BLANK();
+	OFFSET(TI_sysenter_return, thread_info, sysenter_return);
+
+	BLANK();
+	OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe_ia32, uc.uc_mcontext);
+#endif
+
 #ifdef CONFIG_PARAVIRT
 	BLANK();
 	OFFSET(PARAVIRT_enabled, pv_info, paravirt_enabled);
@@ -49,7 +68,9 @@ void common(void) {
 	OFFSET(PV_IRQ_irq_disable, pv_irq_ops, irq_disable);
 	OFFSET(PV_IRQ_irq_enable, pv_irq_ops, irq_enable);
 	OFFSET(PV_CPU_iret, pv_cpu_ops, iret);
+#ifdef CONFIG_X86_32
 	OFFSET(PV_CPU_irq_enable_sysexit, pv_cpu_ops, irq_enable_sysexit);
+#endif
 	OFFSET(PV_CPU_read_cr0, pv_cpu_ops, read_cr0);
 	OFFSET(PV_MMU_read_cr2, pv_mmu_ops, read_cr2);
 #endif
diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c
index 47703aed74cf..6ce39025f467 100644
--- a/arch/x86/kernel/asm-offsets_32.c
+++ b/arch/x86/kernel/asm-offsets_32.c
@@ -17,17 +17,6 @@ void foo(void);
 
 void foo(void)
 {
-	OFFSET(IA32_SIGCONTEXT_ax, sigcontext, ax);
-	OFFSET(IA32_SIGCONTEXT_bx, sigcontext, bx);
-	OFFSET(IA32_SIGCONTEXT_cx, sigcontext, cx);
-	OFFSET(IA32_SIGCONTEXT_dx, sigcontext, dx);
-	OFFSET(IA32_SIGCONTEXT_si, sigcontext, si);
-	OFFSET(IA32_SIGCONTEXT_di, sigcontext, di);
-	OFFSET(IA32_SIGCONTEXT_bp, sigcontext, bp);
-	OFFSET(IA32_SIGCONTEXT_sp, sigcontext, sp);
-	OFFSET(IA32_SIGCONTEXT_ip, sigcontext, ip);
-	BLANK();
-
 	OFFSET(CPUINFO_x86, cpuinfo_x86, x86);
 	OFFSET(CPUINFO_x86_vendor, cpuinfo_x86, x86_vendor);
 	OFFSET(CPUINFO_x86_model, cpuinfo_x86, x86_model);
@@ -37,10 +26,6 @@ void foo(void)
 	OFFSET(CPUINFO_x86_vendor_id, cpuinfo_x86, x86_vendor_id);
 	BLANK();
 
-	OFFSET(TI_sysenter_return, thread_info, sysenter_return);
-	OFFSET(TI_cpu, thread_info, cpu);
-	BLANK();
-
 	OFFSET(PT_EBX, pt_regs, bx);
 	OFFSET(PT_ECX, pt_regs, cx);
 	OFFSET(PT_EDX, pt_regs, dx);
@@ -60,9 +45,6 @@ void foo(void)
 	OFFSET(PT_OLDSS,  pt_regs, ss);
 	BLANK();
 
-	OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe, uc.uc_mcontext);
-	BLANK();
-
 	OFFSET(saved_context_gdt_desc, saved_context, gdt_desc);
 	BLANK();
 
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index 5ce6f2da8763..d8f42f902a0f 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -29,27 +29,6 @@ int main(void)
 	BLANK();
 #endif
 
-#ifdef CONFIG_IA32_EMULATION
-	OFFSET(TI_sysenter_return, thread_info, sysenter_return);
-	BLANK();
-
-#define ENTRY(entry) OFFSET(IA32_SIGCONTEXT_ ## entry, sigcontext_ia32, entry)
-	ENTRY(ax);
-	ENTRY(bx);
-	ENTRY(cx);
-	ENTRY(dx);
-	ENTRY(si);
-	ENTRY(di);
-	ENTRY(bp);
-	ENTRY(sp);
-	ENTRY(ip);
-	BLANK();
-#undef ENTRY
-
-	OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe_ia32, uc.uc_mcontext);
-	BLANK();
-#endif
-
 #define ENTRY(entry) OFFSET(pt_regs_ ## entry, pt_regs, entry)
 	ENTRY(bx);
 	ENTRY(cx);
@@ -87,7 +66,7 @@ int main(void)
 	DEFINE(__NR_syscall_max, sizeof(syscalls_64) - 1);
 	DEFINE(NR_syscalls, sizeof(syscalls_64));
 
-	DEFINE(__NR_ia32_syscall_max, sizeof(syscalls_ia32) - 1);
+	DEFINE(__NR_syscall_compat_max, sizeof(syscalls_ia32) - 1);
 	DEFINE(IA32_NR_syscalls, sizeof(syscalls_ia32));
 
 	return 0;
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index e4cf63301ff4..dd3a4baffe50 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -19,6 +19,13 @@
 
 #include "cpu.h"
 
+/*
+ * nodes_per_socket: Stores the number of nodes per socket.
+ * Refer to Fam15h Models 00-0fh BKDG - CPUID Fn8000_001E_ECX
+ * Node Identifiers[10:8]
+ */
+static u32 nodes_per_socket = 1;
+
 static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p)
 {
 	u32 gprs[8] = { 0 };
@@ -288,10 +295,10 @@ static int nearby_node(int apicid)
  *     Assumption: Number of cores in each internal node is the same.
  * (2) AMD processors supporting compute units
  */
-#ifdef CONFIG_X86_HT
+#ifdef CONFIG_SMP
 static void amd_get_topology(struct cpuinfo_x86 *c)
 {
-	u32 nodes, cores_per_cu = 1;
+	u32 cores_per_cu = 1;
 	u8 node_id;
 	int cpu = smp_processor_id();
 
@@ -300,7 +307,7 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
 		u32 eax, ebx, ecx, edx;
 
 		cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
-		nodes = ((ecx >> 8) & 7) + 1;
+		nodes_per_socket = ((ecx >> 8) & 7) + 1;
 		node_id = ecx & 7;
 
 		/* get compute unit information */
@@ -311,18 +318,18 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
 		u64 value;
 
 		rdmsrl(MSR_FAM10H_NODE_ID, value);
-		nodes = ((value >> 3) & 7) + 1;
+		nodes_per_socket = ((value >> 3) & 7) + 1;
 		node_id = value & 7;
 	} else
 		return;
 
 	/* fixup multi-node processor information */
-	if (nodes > 1) {
+	if (nodes_per_socket > 1) {
 		u32 cores_per_node;
 		u32 cus_per_node;
 
 		set_cpu_cap(c, X86_FEATURE_AMD_DCM);
-		cores_per_node = c->x86_max_cores / nodes;
+		cores_per_node = c->x86_max_cores / nodes_per_socket;
 		cus_per_node = cores_per_node / cores_per_cu;
 
 		/* store NodeID, use llc_shared_map to store sibling info */
@@ -341,7 +348,7 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
  */
 static void amd_detect_cmp(struct cpuinfo_x86 *c)
 {
-#ifdef CONFIG_X86_HT
+#ifdef CONFIG_SMP
 	unsigned bits;
 	int cpu = smp_processor_id();
 
@@ -366,6 +373,12 @@ u16 amd_get_nb_id(int cpu)
 }
 EXPORT_SYMBOL_GPL(amd_get_nb_id);
 
+u32 amd_get_nodes_per_socket(void)
+{
+	return nodes_per_socket;
+}
+EXPORT_SYMBOL_GPL(amd_get_nodes_per_socket);
+
 static void srat_detect_node(struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_NUMA
@@ -420,7 +433,7 @@ static void srat_detect_node(struct cpuinfo_x86 *c)
 
 static void early_init_amd_mc(struct cpuinfo_x86 *c)
 {
-#ifdef CONFIG_X86_HT
+#ifdef CONFIG_SMP
 	unsigned bits, ecx;
 
 	/* Multi core CPU? */
@@ -520,8 +533,16 @@ static void early_init_amd(struct cpuinfo_x86 *c)
 			set_cpu_cap(c, X86_FEATURE_K6_MTRR);
 #endif
 #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_PCI)
-	/* check CPU config space for extended APIC ID */
-	if (cpu_has_apic && c->x86 >= 0xf) {
+	/*
+	 * ApicID can always be treated as an 8-bit value for AMD APIC versions
+	 * >= 0x10, but even old K8s came out of reset with version 0x10. So, we
+	 * can safely set X86_FEATURE_EXTD_APICID unconditionally for families
+	 * after 16h.
+	 */
+	if (cpu_has_apic && c->x86 > 0x16) {
+		set_cpu_cap(c, X86_FEATURE_EXTD_APICID);
+	} else if (cpu_has_apic && c->x86 >= 0xf) {
+		/* check CPU config space for extended APIC ID */
 		unsigned int val;
 		val = read_pci_config(0, 24, 0, 0x68);
 		if ((val & ((1 << 17) | (1 << 18))) == ((1 << 17) | (1 << 18)))
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 03445346ee0a..bd17db15a2c1 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -12,57 +12,11 @@
 #include <asm/bugs.h>
 #include <asm/processor.h>
 #include <asm/processor-flags.h>
-#include <asm/i387.h>
+#include <asm/fpu/internal.h>
 #include <asm/msr.h>
 #include <asm/paravirt.h>
 #include <asm/alternative.h>
 
-static double __initdata x = 4195835.0;
-static double __initdata y = 3145727.0;
-
-/*
- * This used to check for exceptions..
- * However, it turns out that to support that,
- * the XMM trap handlers basically had to
- * be buggy. So let's have a correct XMM trap
- * handler, and forget about printing out
- * some status at boot.
- *
- * We should really only care about bugs here
- * anyway. Not features.
- */
-static void __init check_fpu(void)
-{
-	s32 fdiv_bug;
-
-	kernel_fpu_begin();
-
-	/*
-	 * trap_init() enabled FXSR and company _before_ testing for FP
-	 * problems here.
-	 *
-	 * Test for the divl bug: http://en.wikipedia.org/wiki/Fdiv_bug
-	 */
-	__asm__("fninit\n\t"
-		"fldl %1\n\t"
-		"fdivl %2\n\t"
-		"fmull %2\n\t"
-		"fldl %1\n\t"
-		"fsubp %%st,%%st(1)\n\t"
-		"fistpl %0\n\t"
-		"fwait\n\t"
-		"fninit"
-		: "=m" (*&fdiv_bug)
-		: "m" (*&x), "m" (*&y));
-
-	kernel_fpu_end();
-
-	if (fdiv_bug) {
-		set_cpu_bug(&boot_cpu_data, X86_BUG_FDIV);
-		pr_warn("Hmm, FPU with FDIV bug\n");
-	}
-}
-
 void __init check_bugs(void)
 {
 	identify_boot_cpu();
@@ -85,10 +39,5 @@ void __init check_bugs(void)
 		'0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86);
 	alternative_instructions();
 
-	/*
-	 * kernel_fpu_begin/end() in check_fpu() relies on the patched
-	 * alternative instructions.
-	 */
-	if (cpu_has_fpu)
-		check_fpu();
+	fpu__init_check_bugs();
 }
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index a62cf04dac8a..9fc5e3d9d9c8 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -5,6 +5,7 @@
 #include <linux/module.h>
 #include <linux/percpu.h>
 #include <linux/string.h>
+#include <linux/ctype.h>
 #include <linux/delay.h>
 #include <linux/sched.h>
 #include <linux/init.h>
@@ -31,8 +32,7 @@
 #include <asm/setup.h>
 #include <asm/apic.h>
 #include <asm/desc.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
 #include <asm/mtrr.h>
 #include <linux/numa.h>
 #include <asm/asm.h>
@@ -145,32 +145,21 @@ DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = {
 } };
 EXPORT_PER_CPU_SYMBOL_GPL(gdt_page);
 
-static int __init x86_xsave_setup(char *s)
+static int __init x86_mpx_setup(char *s)
 {
+	/* require an exact match without trailing characters */
 	if (strlen(s))
 		return 0;
-	setup_clear_cpu_cap(X86_FEATURE_XSAVE);
-	setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
-	setup_clear_cpu_cap(X86_FEATURE_XSAVES);
-	setup_clear_cpu_cap(X86_FEATURE_AVX);
-	setup_clear_cpu_cap(X86_FEATURE_AVX2);
-	return 1;
-}
-__setup("noxsave", x86_xsave_setup);
 
-static int __init x86_xsaveopt_setup(char *s)
-{
-	setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
-	return 1;
-}
-__setup("noxsaveopt", x86_xsaveopt_setup);
+	/* do not emit a message if the feature is not present */
+	if (!boot_cpu_has(X86_FEATURE_MPX))
+		return 1;
 
-static int __init x86_xsaves_setup(char *s)
-{
-	setup_clear_cpu_cap(X86_FEATURE_XSAVES);
+	setup_clear_cpu_cap(X86_FEATURE_MPX);
+	pr_info("nompx: Intel Memory Protection Extensions (MPX) disabled\n");
 	return 1;
 }
-__setup("noxsaves", x86_xsaves_setup);
+__setup("nompx", x86_mpx_setup);
 
 #ifdef CONFIG_X86_32
 static int cachesize_override = -1;
@@ -183,14 +172,6 @@ static int __init cachesize_setup(char *str)
 }
 __setup("cachesize=", cachesize_setup);
 
-static int __init x86_fxsr_setup(char *s)
-{
-	setup_clear_cpu_cap(X86_FEATURE_FXSR);
-	setup_clear_cpu_cap(X86_FEATURE_XMM);
-	return 1;
-}
-__setup("nofxsr", x86_fxsr_setup);
-
 static int __init x86_sep_setup(char *s)
 {
 	setup_clear_cpu_cap(X86_FEATURE_SEP);
@@ -419,7 +400,7 @@ static const struct cpu_dev *cpu_devs[X86_VENDOR_NUM] = {};
 static void get_model_name(struct cpuinfo_x86 *c)
 {
 	unsigned int *v;
-	char *p, *q;
+	char *p, *q, *s;
 
 	if (c->extended_cpuid_level < 0x80000004)
 		return;
@@ -430,19 +411,21 @@ static void get_model_name(struct cpuinfo_x86 *c)
 	cpuid(0x80000004, &v[8], &v[9], &v[10], &v[11]);
 	c->x86_model_id[48] = 0;
 
-	/*
-	 * Intel chips right-justify this string for some dumb reason;
-	 * undo that brain damage:
-	 */
-	p = q = &c->x86_model_id[0];
+	/* Trim whitespace */
+	p = q = s = &c->x86_model_id[0];
+
 	while (*p == ' ')
 		p++;
-	if (p != q) {
-		while (*p)
-			*q++ = *p++;
-		while (q <= &c->x86_model_id[48])
-			*q++ = '\0';	/* Zero-pad the rest */
+
+	while (*p) {
+		/* Note the last non-whitespace index */
+		if (!isspace(*p))
+			s = q;
+
+		*q++ = *p++;
 	}
+
+	*(s + 1) = '\0';
 }
 
 void cpu_detect_cache_sizes(struct cpuinfo_x86 *c)
@@ -508,7 +491,7 @@ static void cpu_detect_tlb(struct cpuinfo_x86 *c)
 
 void detect_ht(struct cpuinfo_x86 *c)
 {
-#ifdef CONFIG_X86_HT
+#ifdef CONFIG_SMP
 	u32 eax, ebx, ecx, edx;
 	int index_msb, core_bits;
 	static bool printed;
@@ -759,7 +742,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 	cpu_detect(c);
 	get_cpu_vendor(c);
 	get_cpu_cap(c);
-	fpu_detect(c);
+	fpu__init_system(c);
 
 	if (this_cpu->c_early_init)
 		this_cpu->c_early_init(c);
@@ -844,7 +827,7 @@ static void generic_identify(struct cpuinfo_x86 *c)
 	if (c->cpuid_level >= 0x00000001) {
 		c->initial_apicid = (cpuid_ebx(1) >> 24) & 0xFF;
 #ifdef CONFIG_X86_32
-# ifdef CONFIG_X86_HT
+# ifdef CONFIG_SMP
 		c->apicid = apic->phys_pkg_id(c->initial_apicid, 0);
 # else
 		c->apicid = c->initial_apicid;
@@ -1026,7 +1009,7 @@ void enable_sep_cpu(void)
 	      (unsigned long)tss + offsetofend(struct tss_struct, SYSENTER_stack),
 	      0);
 
-	wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long)ia32_sysenter_target, 0);
+	wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long)entry_SYSENTER_32, 0);
 
 out:
 	put_cpu();
@@ -1122,7 +1105,7 @@ void print_cpu_info(struct cpuinfo_x86 *c)
 		printk(KERN_CONT "%s ", vendor);
 
 	if (c->x86_model_id[0])
-		printk(KERN_CONT "%s", strim(c->x86_model_id));
+		printk(KERN_CONT "%s", c->x86_model_id);
 	else
 		printk(KERN_CONT "%d86", c->x86);
 
@@ -1155,10 +1138,6 @@ static __init int setup_disablecpuid(char *arg)
 }
 __setup("clearcpuid=", setup_disablecpuid);
 
-DEFINE_PER_CPU(unsigned long, kernel_stack) =
-	(unsigned long)&init_thread_union + THREAD_SIZE;
-EXPORT_PER_CPU_SYMBOL(kernel_stack);
-
 #ifdef CONFIG_X86_64
 struct desc_ptr idt_descr = { NR_VECTORS * 16 - 1, (unsigned long) idt_table };
 struct desc_ptr debug_idt_descr = { NR_VECTORS * 16 - 1,
@@ -1183,8 +1162,6 @@ DEFINE_PER_CPU(unsigned int, irq_count) __visible = -1;
 DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT;
 EXPORT_PER_CPU_SYMBOL(__preempt_count);
 
-DEFINE_PER_CPU(struct task_struct *, fpu_owner_task);
-
 /*
  * Special IST stacks which the CPU switches to when it calls
  * an IST-marked descriptor entry. Up to 7 stacks (hardware
@@ -1208,10 +1185,10 @@ void syscall_init(void)
 	 * set CS/DS but only a 32bit target. LSTAR sets the 64bit rip.
 	 */
 	wrmsrl(MSR_STAR,  ((u64)__USER32_CS)<<48  | ((u64)__KERNEL_CS)<<32);
-	wrmsrl(MSR_LSTAR, system_call);
+	wrmsrl(MSR_LSTAR, entry_SYSCALL_64);
 
 #ifdef CONFIG_IA32_EMULATION
-	wrmsrl(MSR_CSTAR, ia32_cstar_target);
+	wrmsrl(MSR_CSTAR, entry_SYSCALL_compat);
 	/*
 	 * This only works on Intel CPUs.
 	 * On AMD CPUs these MSRs are 32-bit, CPU truncates MSR_IA32_SYSENTER_EIP.
@@ -1220,7 +1197,7 @@ void syscall_init(void)
 	 */
 	wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS);
 	wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL);
-	wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)ia32_sysenter_target);
+	wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)entry_SYSENTER_compat);
 #else
 	wrmsrl(MSR_CSTAR, ignore_sysret);
 	wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)GDT_ENTRY_INVALID_SEG);
@@ -1275,7 +1252,6 @@ DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task;
 EXPORT_PER_CPU_SYMBOL(current_task);
 DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT;
 EXPORT_PER_CPU_SYMBOL(__preempt_count);
-DEFINE_PER_CPU(struct task_struct *, fpu_owner_task);
 
 /*
  * On x86_32, vm86 modifies tss.sp0, so sp0 isn't a reliable way to find
@@ -1439,7 +1415,7 @@ void cpu_init(void)
 	clear_all_debug_regs();
 	dbg_restore_debug_regs();
 
-	fpu_init();
+	fpu__init_cpu();
 
 	if (is_uv_system())
 		uv_cpu_init();
@@ -1495,7 +1471,7 @@ void cpu_init(void)
 	clear_all_debug_regs();
 	dbg_restore_debug_regs();
 
-	fpu_init();
+	fpu__init_cpu();
 }
 #endif
 
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index edcb0e28c336..be4febc58b94 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -654,7 +654,7 @@ unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c)
 	unsigned int new_l1d = 0, new_l1i = 0; /* Cache sizes from cpuid(4) */
 	unsigned int new_l2 = 0, new_l3 = 0, i; /* Cache sizes from cpuid(4) */
 	unsigned int l2_id = 0, l3_id = 0, num_threads_sharing, index_msb;
-#ifdef CONFIG_X86_HT
+#ifdef CONFIG_SMP
 	unsigned int cpu = c->cpu_index;
 #endif
 
@@ -773,19 +773,19 @@ unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c)
 
 	if (new_l2) {
 		l2 = new_l2;
-#ifdef CONFIG_X86_HT
+#ifdef CONFIG_SMP
 		per_cpu(cpu_llc_id, cpu) = l2_id;
 #endif
 	}
 
 	if (new_l3) {
 		l3 = new_l3;
-#ifdef CONFIG_X86_HT
+#ifdef CONFIG_SMP
 		per_cpu(cpu_llc_id, cpu) = l3_id;
 #endif
 	}
 
-#ifdef CONFIG_X86_HT
+#ifdef CONFIG_SMP
 	/*
 	 * If cpu_llc_id is not yet set, this means cpuid_level < 4 which in
 	 * turns means that the only possibility is SMT (as indicated in
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 20190bdac9d5..df919ff103c3 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -53,9 +53,12 @@
 static DEFINE_MUTEX(mce_chrdev_read_mutex);
 
 #define rcu_dereference_check_mce(p) \
-	rcu_dereference_index_check((p), \
-			      rcu_read_lock_sched_held() || \
-			      lockdep_is_held(&mce_chrdev_read_mutex))
+({ \
+	rcu_lockdep_assert(rcu_read_lock_sched_held() || \
+			   lockdep_is_held(&mce_chrdev_read_mutex), \
+			   "suspicious rcu_dereference_check_mce() usage"); \
+	smp_load_acquire(&(p)); \
+})
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/mce.h>
@@ -1050,6 +1053,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 	char *msg = "Unknown";
 	u64 recover_paddr = ~0ull;
 	int flags = MF_ACTION_REQUIRED;
+	int lmce = 0;
 
 	prev_state = ist_enter(regs);
 
@@ -1077,11 +1081,20 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 		kill_it = 1;
 
 	/*
-	 * Go through all the banks in exclusion of the other CPUs.
-	 * This way we don't report duplicated events on shared banks
-	 * because the first one to see it will clear it.
+	 * Check if this MCE is signaled to only this logical processor
 	 */
-	order = mce_start(&no_way_out);
+	if (m.mcgstatus & MCG_STATUS_LMCES)
+		lmce = 1;
+	else {
+		/*
+		 * Go through all the banks in exclusion of the other CPUs.
+		 * This way we don't report duplicated events on shared banks
+		 * because the first one to see it will clear it.
+		 * If this is a Local MCE, then no need to perform rendezvous.
+		 */
+		order = mce_start(&no_way_out);
+	}
+
 	for (i = 0; i < cfg->banks; i++) {
 		__clear_bit(i, toclear);
 		if (!test_bit(i, valid_banks))
@@ -1158,8 +1171,18 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 	 * Do most of the synchronization with other CPUs.
 	 * When there's any problem use only local no_way_out state.
 	 */
-	if (mce_end(order) < 0)
-		no_way_out = worst >= MCE_PANIC_SEVERITY;
+	if (!lmce) {
+		if (mce_end(order) < 0)
+			no_way_out = worst >= MCE_PANIC_SEVERITY;
+	} else {
+		/*
+		 * Local MCE skipped calling mce_reign()
+		 * If we found a fatal error, we need to panic here.
+		 */
+		 if (worst >= MCE_PANIC_SEVERITY && mca_cfg.tolerant < 3)
+			mce_panic("Machine check from unknown source",
+				NULL, NULL);
+	}
 
 	/*
 	 * At insane "tolerant" levels we take no action. Otherwise
@@ -1640,10 +1663,16 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
 		mce_intel_feature_init(c);
 		mce_adjust_timer = cmci_intel_adjust_timer;
 		break;
-	case X86_VENDOR_AMD:
+
+	case X86_VENDOR_AMD: {
+		u32 ebx = cpuid_ebx(0x80000007);
+
 		mce_amd_feature_init(c);
-		mce_flags.overflow_recov = cpuid_ebx(0x80000007) & 0x1;
+		mce_flags.overflow_recov = !!(ebx & BIT(0));
+		mce_flags.succor	 = !!(ebx & BIT(1));
 		break;
+		}
+
 	default:
 		break;
 	}
@@ -1887,7 +1916,7 @@ out:
 static unsigned int mce_chrdev_poll(struct file *file, poll_table *wait)
 {
 	poll_wait(file, &mce_chrdev_wait, wait);
-	if (rcu_access_index(mcelog.next))
+	if (READ_ONCE(mcelog.next))
 		return POLLIN | POLLRDNORM;
 	if (!mce_apei_read_done && apei_check_mce())
 		return POLLIN | POLLRDNORM;
@@ -1932,8 +1961,8 @@ void register_mce_write_callback(ssize_t (*fn)(struct file *filp,
 }
 EXPORT_SYMBOL_GPL(register_mce_write_callback);
 
-ssize_t mce_chrdev_write(struct file *filp, const char __user *ubuf,
-			 size_t usize, loff_t *off)
+static ssize_t mce_chrdev_write(struct file *filp, const char __user *ubuf,
+				size_t usize, loff_t *off)
 {
 	if (mce_write)
 		return mce_write(filp, ubuf, usize, off);
@@ -1979,6 +2008,7 @@ void mce_disable_bank(int bank)
 /*
  * mce=off Disables machine check
  * mce=no_cmci Disables CMCI
+ * mce=no_lmce Disables LMCE
  * mce=dont_log_ce Clears corrected events silently, no log created for CEs.
  * mce=ignore_ce Disables polling and CMCI, corrected events are not cleared.
  * mce=TOLERANCELEVEL[,monarchtimeout] (number, see above)
@@ -2002,6 +2032,8 @@ static int __init mcheck_enable(char *str)
 		cfg->disabled = true;
 	else if (!strcmp(str, "no_cmci"))
 		cfg->cmci_disabled = true;
+	else if (!strcmp(str, "no_lmce"))
+		cfg->lmce_disabled = true;
 	else if (!strcmp(str, "dont_log_ce"))
 		cfg->dont_log_ce = true;
 	else if (!strcmp(str, "ignore_ce"))
@@ -2011,11 +2043,8 @@ static int __init mcheck_enable(char *str)
 	else if (!strcmp(str, "bios_cmci_threshold"))
 		cfg->bios_cmci_threshold = true;
 	else if (isdigit(str[0])) {
-		get_option(&str, &(cfg->tolerant));
-		if (*str == ',') {
-			++str;
+		if (get_option(&str, &cfg->tolerant) == 2)
 			get_option(&str, &(cfg->monarch_timeout));
-		}
 	} else {
 		pr_info("mce argument %s ignored. Please use /sys\n", str);
 		return 0;
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 55ad9b37cae8..e99b15077e94 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -1,19 +1,13 @@
 /*
- *  (c) 2005-2012 Advanced Micro Devices, Inc.
+ *  (c) 2005-2015 Advanced Micro Devices, Inc.
  *  Your use of this code is subject to the terms and conditions of the
  *  GNU general public license version 2. See "COPYING" or
  *  http://www.gnu.org/licenses/gpl.html
  *
  *  Written by Jacob Shin - AMD, Inc.
- *
  *  Maintained by: Borislav Petkov <bp@alien8.de>
  *
- *  April 2006
- *     - added support for AMD Family 0x10 processors
- *  May 2012
- *     - major scrubbing
- *
- *  All MC4_MISCi registers are shared between multi-cores
+ *  All MC4_MISCi registers are shared between cores on a node.
  */
 #include <linux/interrupt.h>
 #include <linux/notifier.h>
@@ -32,6 +26,7 @@
 #include <asm/idle.h>
 #include <asm/mce.h>
 #include <asm/msr.h>
+#include <asm/trace/irq_vectors.h>
 
 #define NR_BLOCKS         9
 #define THRESHOLD_MAX     0xFFF
@@ -47,6 +42,13 @@
 #define MASK_BLKPTR_LO    0xFF000000
 #define MCG_XBLK_ADDR     0xC0000400
 
+/* Deferred error settings */
+#define MSR_CU_DEF_ERR		0xC0000410
+#define MASK_DEF_LVTOFF		0x000000F0
+#define MASK_DEF_INT_TYPE	0x00000006
+#define DEF_LVT_OFF		0x2
+#define DEF_INT_TYPE_APIC	0x2
+
 static const char * const th_names[] = {
 	"load_store",
 	"insn_fetch",
@@ -60,6 +62,13 @@ static DEFINE_PER_CPU(struct threshold_bank **, threshold_banks);
 static DEFINE_PER_CPU(unsigned char, bank_map);	/* see which banks are on */
 
 static void amd_threshold_interrupt(void);
+static void amd_deferred_error_interrupt(void);
+
+static void default_deferred_error_interrupt(void)
+{
+	pr_err("Unexpected deferred interrupt at vector %x\n", DEFERRED_ERROR_VECTOR);
+}
+void (*deferred_error_int_vector)(void) = default_deferred_error_interrupt;
 
 /*
  * CPU Initialization
@@ -196,7 +205,7 @@ static void mce_threshold_block_init(struct threshold_block *b, int offset)
 	threshold_restart_bank(&tr);
 };
 
-static int setup_APIC_mce(int reserved, int new)
+static int setup_APIC_mce_threshold(int reserved, int new)
 {
 	if (reserved < 0 && !setup_APIC_eilvt(new, THRESHOLD_APIC_VECTOR,
 					      APIC_EILVT_MSG_FIX, 0))
@@ -205,6 +214,39 @@ static int setup_APIC_mce(int reserved, int new)
 	return reserved;
 }
 
+static int setup_APIC_deferred_error(int reserved, int new)
+{
+	if (reserved < 0 && !setup_APIC_eilvt(new, DEFERRED_ERROR_VECTOR,
+					      APIC_EILVT_MSG_FIX, 0))
+		return new;
+
+	return reserved;
+}
+
+static void deferred_error_interrupt_enable(struct cpuinfo_x86 *c)
+{
+	u32 low = 0, high = 0;
+	int def_offset = -1, def_new;
+
+	if (rdmsr_safe(MSR_CU_DEF_ERR, &low, &high))
+		return;
+
+	def_new = (low & MASK_DEF_LVTOFF) >> 4;
+	if (!(low & MASK_DEF_LVTOFF)) {
+		pr_err(FW_BUG "Your BIOS is not setting up LVT offset 0x2 for deferred error IRQs correctly.\n");
+		def_new = DEF_LVT_OFF;
+		low = (low & ~MASK_DEF_LVTOFF) | (DEF_LVT_OFF << 4);
+	}
+
+	def_offset = setup_APIC_deferred_error(def_offset, def_new);
+	if ((def_offset == def_new) &&
+	    (deferred_error_int_vector != amd_deferred_error_interrupt))
+		deferred_error_int_vector = amd_deferred_error_interrupt;
+
+	low = (low & ~MASK_DEF_INT_TYPE) | DEF_INT_TYPE_APIC;
+	wrmsr(MSR_CU_DEF_ERR, low, high);
+}
+
 /* cpu init entry point, called from mce.c with preempt off */
 void mce_amd_feature_init(struct cpuinfo_x86 *c)
 {
@@ -252,7 +294,7 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
 
 			b.interrupt_enable = 1;
 			new	= (high & MASK_LVTOFF_HI) >> 20;
-			offset  = setup_APIC_mce(offset, new);
+			offset  = setup_APIC_mce_threshold(offset, new);
 
 			if ((offset == new) &&
 			    (mce_threshold_vector != amd_threshold_interrupt))
@@ -262,6 +304,73 @@ init:
 			mce_threshold_block_init(&b, offset);
 		}
 	}
+
+	if (mce_flags.succor)
+		deferred_error_interrupt_enable(c);
+}
+
+static void __log_error(unsigned int bank, bool threshold_err, u64 misc)
+{
+	struct mce m;
+	u64 status;
+
+	rdmsrl(MSR_IA32_MCx_STATUS(bank), status);
+	if (!(status & MCI_STATUS_VAL))
+		return;
+
+	mce_setup(&m);
+
+	m.status = status;
+	m.bank = bank;
+
+	if (threshold_err)
+		m.misc = misc;
+
+	if (m.status & MCI_STATUS_ADDRV)
+		rdmsrl(MSR_IA32_MCx_ADDR(bank), m.addr);
+
+	mce_log(&m);
+	wrmsrl(MSR_IA32_MCx_STATUS(bank), 0);
+}
+
+static inline void __smp_deferred_error_interrupt(void)
+{
+	inc_irq_stat(irq_deferred_error_count);
+	deferred_error_int_vector();
+}
+
+asmlinkage __visible void smp_deferred_error_interrupt(void)
+{
+	entering_irq();
+	__smp_deferred_error_interrupt();
+	exiting_ack_irq();
+}
+
+asmlinkage __visible void smp_trace_deferred_error_interrupt(void)
+{
+	entering_irq();
+	trace_deferred_error_apic_entry(DEFERRED_ERROR_VECTOR);
+	__smp_deferred_error_interrupt();
+	trace_deferred_error_apic_exit(DEFERRED_ERROR_VECTOR);
+	exiting_ack_irq();
+}
+
+/* APIC interrupt handler for deferred errors */
+static void amd_deferred_error_interrupt(void)
+{
+	u64 status;
+	unsigned int bank;
+
+	for (bank = 0; bank < mca_cfg.banks; ++bank) {
+		rdmsrl(MSR_IA32_MCx_STATUS(bank), status);
+
+		if (!(status & MCI_STATUS_VAL) ||
+		    !(status & MCI_STATUS_DEFERRED))
+			continue;
+
+		__log_error(bank, false, 0);
+		break;
+	}
 }
 
 /*
@@ -273,12 +382,12 @@ init:
  * the interrupt goes off when error_count reaches threshold_limit.
  * the handler will simply log mcelog w/ software defined bank number.
  */
+
 static void amd_threshold_interrupt(void)
 {
 	u32 low = 0, high = 0, address = 0;
 	int cpu = smp_processor_id();
 	unsigned int bank, block;
-	struct mce m;
 
 	/* assume first bank caused it */
 	for (bank = 0; bank < mca_cfg.banks; ++bank) {
@@ -321,15 +430,7 @@ static void amd_threshold_interrupt(void)
 	return;
 
 log:
-	mce_setup(&m);
-	rdmsrl(MSR_IA32_MCx_STATUS(bank), m.status);
-	if (!(m.status & MCI_STATUS_VAL))
-		return;
-	m.misc = ((u64)high << 32) | low;
-	m.bank = bank;
-	mce_log(&m);
-
-	wrmsrl(MSR_IA32_MCx_STATUS(bank), 0);
+	__log_error(bank, true, ((u64)high << 32) | low);
 }
 
 /*
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index b4a41cf030ed..844f56c5616d 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -91,6 +91,36 @@ static int cmci_supported(int *banks)
 	return !!(cap & MCG_CMCI_P);
 }
 
+static bool lmce_supported(void)
+{
+	u64 tmp;
+
+	if (mca_cfg.lmce_disabled)
+		return false;
+
+	rdmsrl(MSR_IA32_MCG_CAP, tmp);
+
+	/*
+	 * LMCE depends on recovery support in the processor. Hence both
+	 * MCG_SER_P and MCG_LMCE_P should be present in MCG_CAP.
+	 */
+	if ((tmp & (MCG_SER_P | MCG_LMCE_P)) !=
+		   (MCG_SER_P | MCG_LMCE_P))
+		return false;
+
+	/*
+	 * BIOS should indicate support for LMCE by setting bit 20 in
+	 * IA32_FEATURE_CONTROL without which touching MCG_EXT_CTL will
+	 * generate a #GP fault.
+	 */
+	rdmsrl(MSR_IA32_FEATURE_CONTROL, tmp);
+	if ((tmp & (FEATURE_CONTROL_LOCKED | FEATURE_CONTROL_LMCE)) ==
+		   (FEATURE_CONTROL_LOCKED | FEATURE_CONTROL_LMCE))
+		return true;
+
+	return false;
+}
+
 bool mce_intel_cmci_poll(void)
 {
 	if (__this_cpu_read(cmci_storm_state) == CMCI_STORM_NONE)
@@ -405,8 +435,22 @@ static void intel_init_cmci(void)
 	cmci_recheck();
 }
 
+void intel_init_lmce(void)
+{
+	u64 val;
+
+	if (!lmce_supported())
+		return;
+
+	rdmsrl(MSR_IA32_MCG_EXT_CTL, val);
+
+	if (!(val & MCG_EXT_CTL_LMCE_EN))
+		wrmsrl(MSR_IA32_MCG_EXT_CTL, val | MCG_EXT_CTL_LMCE_EN);
+}
+
 void mce_intel_feature_init(struct cpuinfo_x86 *c)
 {
 	intel_init_thermal(c);
 	intel_init_cmci();
+	intel_init_lmce();
 }
diff --git a/arch/x86/kernel/cpu/microcode/amd_early.c b/arch/x86/kernel/cpu/microcode/amd_early.c
index 737737edbd1e..e8a215a9a345 100644
--- a/arch/x86/kernel/cpu/microcode/amd_early.c
+++ b/arch/x86/kernel/cpu/microcode/amd_early.c
@@ -228,7 +228,23 @@ static void apply_ucode_in_initrd(void *ucode, size_t size, bool save_patch)
 	}
 }
 
-void __init load_ucode_amd_bsp(void)
+static bool __init load_builtin_amd_microcode(struct cpio_data *cp,
+					      unsigned int family)
+{
+#ifdef CONFIG_X86_64
+	char fw_name[36] = "amd-ucode/microcode_amd.bin";
+
+	if (family >= 0x15)
+		snprintf(fw_name, sizeof(fw_name),
+			 "amd-ucode/microcode_amd_fam%.2xh.bin", family);
+
+	return get_builtin_firmware(cp, fw_name);
+#else
+	return false;
+#endif
+}
+
+void __init load_ucode_amd_bsp(unsigned int family)
 {
 	struct cpio_data cp;
 	void **data;
@@ -243,8 +259,10 @@ void __init load_ucode_amd_bsp(void)
 #endif
 
 	cp = find_ucode_in_initrd();
-	if (!cp.data)
-		return;
+	if (!cp.data) {
+		if (!load_builtin_amd_microcode(&cp, family))
+			return;
+	}
 
 	*data = cp.data;
 	*size = cp.size;
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 36a83617eb21..6236a54a63f4 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -1,74 +1,16 @@
 /*
- *	Intel CPU Microcode Update Driver for Linux
+ * CPU Microcode Update Driver for Linux
  *
- *	Copyright (C) 2000-2006 Tigran Aivazian <tigran@aivazian.fsnet.co.uk>
- *		      2006	Shaohua Li <shaohua.li@intel.com>
+ * Copyright (C) 2000-2006 Tigran Aivazian <tigran@aivazian.fsnet.co.uk>
+ *	      2006	Shaohua Li <shaohua.li@intel.com>
+ *	      2013-2015	Borislav Petkov <bp@alien8.de>
  *
- *	This driver allows to upgrade microcode on Intel processors
- *	belonging to IA-32 family - PentiumPro, Pentium II,
- *	Pentium III, Xeon, Pentium 4, etc.
+ * This driver allows to upgrade microcode on x86 processors.
  *
- *	Reference: Section 8.11 of Volume 3a, IA-32 Intel? Architecture
- *	Software Developer's Manual
- *	Order Number 253668 or free download from:
- *
- *	http://developer.intel.com/Assets/PDF/manual/253668.pdf	
- *
- *	For more information, go to http://www.urbanmyth.org/microcode
- *
- *	This program is free software; you can redistribute it and/or
- *	modify it under the terms of the GNU General Public License
- *	as published by the Free Software Foundation; either version
- *	2 of the License, or (at your option) any later version.
- *
- *	1.0	16 Feb 2000, Tigran Aivazian <tigran@sco.com>
- *		Initial release.
- *	1.01	18 Feb 2000, Tigran Aivazian <tigran@sco.com>
- *		Added read() support + cleanups.
- *	1.02	21 Feb 2000, Tigran Aivazian <tigran@sco.com>
- *		Added 'device trimming' support. open(O_WRONLY) zeroes
- *		and frees the saved copy of applied microcode.
- *	1.03	29 Feb 2000, Tigran Aivazian <tigran@sco.com>
- *		Made to use devfs (/dev/cpu/microcode) + cleanups.
- *	1.04	06 Jun 2000, Simon Trimmer <simon@veritas.com>
- *		Added misc device support (now uses both devfs and misc).
- *		Added MICROCODE_IOCFREE ioctl to clear memory.
- *	1.05	09 Jun 2000, Simon Trimmer <simon@veritas.com>
- *		Messages for error cases (non Intel & no suitable microcode).
- *	1.06	03 Aug 2000, Tigran Aivazian <tigran@veritas.com>
- *		Removed ->release(). Removed exclusive open and status bitmap.
- *		Added microcode_rwsem to serialize read()/write()/ioctl().
- *		Removed global kernel lock usage.
- *	1.07	07 Sep 2000, Tigran Aivazian <tigran@veritas.com>
- *		Write 0 to 0x8B msr and then cpuid before reading revision,
- *		so that it works even if there were no update done by the
- *		BIOS. Otherwise, reading from 0x8B gives junk (which happened
- *		to be 0 on my machine which is why it worked even when I
- *		disabled update by the BIOS)
- *		Thanks to Eric W. Biederman <ebiederman@lnxi.com> for the fix.
- *	1.08	11 Dec 2000, Richard Schaal <richard.schaal@intel.com> and
- *			     Tigran Aivazian <tigran@veritas.com>
- *		Intel Pentium 4 processor support and bugfixes.
- *	1.09	30 Oct 2001, Tigran Aivazian <tigran@veritas.com>
- *		Bugfix for HT (Hyper-Threading) enabled processors
- *		whereby processor resources are shared by all logical processors
- *		in a single CPU package.
- *	1.10	28 Feb 2002 Asit K Mallick <asit.k.mallick@intel.com> and
- *		Tigran Aivazian <tigran@veritas.com>,
- *		Serialize updates as required on HT processors due to
- *		speculative nature of implementation.
- *	1.11	22 Mar 2002 Tigran Aivazian <tigran@veritas.com>
- *		Fix the panic when writing zero-length microcode chunk.
- *	1.12	29 Sep 2003 Nitin Kamble <nitin.a.kamble@intel.com>,
- *		Jun Nakajima <jun.nakajima@intel.com>
- *		Support for the microcode updates in the new format.
- *	1.13	10 Oct 2003 Tigran Aivazian <tigran@veritas.com>
- *		Removed ->read() method and obsoleted MICROCODE_IOCFREE ioctl
- *		because we no longer hold a copy of applied microcode
- *		in kernel memory.
- *	1.14	25 Jun 2004 Tigran Aivazian <tigran@veritas.com>
- *		Fix sigmatch() macro to handle old CPUs with pf == 0.
- *		Thanks to Stuart Swales for pointing out this bug.
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
diff --git a/arch/x86/kernel/cpu/microcode/core_early.c b/arch/x86/kernel/cpu/microcode/core_early.c
index a413a69cbd74..8ebc421d6299 100644
--- a/arch/x86/kernel/cpu/microcode/core_early.c
+++ b/arch/x86/kernel/cpu/microcode/core_early.c
@@ -3,6 +3,7 @@
  *
  *	Copyright (C) 2012 Fenghua Yu <fenghua.yu@intel.com>
  *			   H Peter Anvin" <hpa@zytor.com>
+ *		  (C) 2015 Borislav Petkov <bp@alien8.de>
  *
  *	This driver allows to early upgrade microcode on Intel processors
  *	belonging to IA-32 family - PentiumPro, Pentium II,
@@ -17,6 +18,7 @@
  *	2 of the License, or (at your option) any later version.
  */
 #include <linux/module.h>
+#include <linux/firmware.h>
 #include <asm/microcode.h>
 #include <asm/microcode_intel.h>
 #include <asm/microcode_amd.h>
@@ -43,9 +45,29 @@ static bool __init check_loader_disabled_bsp(void)
 	return *res;
 }
 
+extern struct builtin_fw __start_builtin_fw[];
+extern struct builtin_fw __end_builtin_fw[];
+
+bool get_builtin_firmware(struct cpio_data *cd, const char *name)
+{
+#ifdef CONFIG_FW_LOADER
+	struct builtin_fw *b_fw;
+
+	for (b_fw = __start_builtin_fw; b_fw != __end_builtin_fw; b_fw++) {
+		if (!strcmp(name, b_fw->name)) {
+			cd->size = b_fw->size;
+			cd->data = b_fw->data;
+			return true;
+		}
+	}
+#endif
+	return false;
+}
+
 void __init load_ucode_bsp(void)
 {
-	int vendor, family;
+	int vendor;
+	unsigned int family;
 
 	if (check_loader_disabled_bsp())
 		return;
@@ -63,7 +85,7 @@ void __init load_ucode_bsp(void)
 		break;
 	case X86_VENDOR_AMD:
 		if (family >= 0x10)
-			load_ucode_amd_bsp();
+			load_ucode_amd_bsp(family);
 		break;
 	default:
 		break;
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index a41beadb3db9..969dc17eb1b4 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -1,74 +1,13 @@
 /*
- *	Intel CPU Microcode Update Driver for Linux
+ * Intel CPU Microcode Update Driver for Linux
  *
- *	Copyright (C) 2000-2006 Tigran Aivazian <tigran@aivazian.fsnet.co.uk>
- *		      2006	Shaohua Li <shaohua.li@intel.com>
+ * Copyright (C) 2000-2006 Tigran Aivazian <tigran@aivazian.fsnet.co.uk>
+ *		 2006 Shaohua Li <shaohua.li@intel.com>
  *
- *	This driver allows to upgrade microcode on Intel processors
- *	belonging to IA-32 family - PentiumPro, Pentium II,
- *	Pentium III, Xeon, Pentium 4, etc.
- *
- *	Reference: Section 8.11 of Volume 3a, IA-32 Intel? Architecture
- *	Software Developer's Manual
- *	Order Number 253668 or free download from:
- *
- *	http://developer.intel.com/Assets/PDF/manual/253668.pdf	
- *
- *	For more information, go to http://www.urbanmyth.org/microcode
- *
- *	This program is free software; you can redistribute it and/or
- *	modify it under the terms of the GNU General Public License
- *	as published by the Free Software Foundation; either version
- *	2 of the License, or (at your option) any later version.
- *
- *	1.0	16 Feb 2000, Tigran Aivazian <tigran@sco.com>
- *		Initial release.
- *	1.01	18 Feb 2000, Tigran Aivazian <tigran@sco.com>
- *		Added read() support + cleanups.
- *	1.02	21 Feb 2000, Tigran Aivazian <tigran@sco.com>
- *		Added 'device trimming' support. open(O_WRONLY) zeroes
- *		and frees the saved copy of applied microcode.
- *	1.03	29 Feb 2000, Tigran Aivazian <tigran@sco.com>
- *		Made to use devfs (/dev/cpu/microcode) + cleanups.
- *	1.04	06 Jun 2000, Simon Trimmer <simon@veritas.com>
- *		Added misc device support (now uses both devfs and misc).
- *		Added MICROCODE_IOCFREE ioctl to clear memory.
- *	1.05	09 Jun 2000, Simon Trimmer <simon@veritas.com>
- *		Messages for error cases (non Intel & no suitable microcode).
- *	1.06	03 Aug 2000, Tigran Aivazian <tigran@veritas.com>
- *		Removed ->release(). Removed exclusive open and status bitmap.
- *		Added microcode_rwsem to serialize read()/write()/ioctl().
- *		Removed global kernel lock usage.
- *	1.07	07 Sep 2000, Tigran Aivazian <tigran@veritas.com>
- *		Write 0 to 0x8B msr and then cpuid before reading revision,
- *		so that it works even if there were no update done by the
- *		BIOS. Otherwise, reading from 0x8B gives junk (which happened
- *		to be 0 on my machine which is why it worked even when I
- *		disabled update by the BIOS)
- *		Thanks to Eric W. Biederman <ebiederman@lnxi.com> for the fix.
- *	1.08	11 Dec 2000, Richard Schaal <richard.schaal@intel.com> and
- *			     Tigran Aivazian <tigran@veritas.com>
- *		Intel Pentium 4 processor support and bugfixes.
- *	1.09	30 Oct 2001, Tigran Aivazian <tigran@veritas.com>
- *		Bugfix for HT (Hyper-Threading) enabled processors
- *		whereby processor resources are shared by all logical processors
- *		in a single CPU package.
- *	1.10	28 Feb 2002 Asit K Mallick <asit.k.mallick@intel.com> and
- *		Tigran Aivazian <tigran@veritas.com>,
- *		Serialize updates as required on HT processors due to
- *		speculative nature of implementation.
- *	1.11	22 Mar 2002 Tigran Aivazian <tigran@veritas.com>
- *		Fix the panic when writing zero-length microcode chunk.
- *	1.12	29 Sep 2003 Nitin Kamble <nitin.a.kamble@intel.com>,
- *		Jun Nakajima <jun.nakajima@intel.com>
- *		Support for the microcode updates in the new format.
- *	1.13	10 Oct 2003 Tigran Aivazian <tigran@veritas.com>
- *		Removed ->read() method and obsoleted MICROCODE_IOCFREE ioctl
- *		because we no longer hold a copy of applied microcode
- *		in kernel memory.
- *	1.14	25 Jun 2004 Tigran Aivazian <tigran@veritas.com>
- *		Fix sigmatch() macro to handle old CPUs with pf == 0.
- *		Thanks to Stuart Swales for pointing out this bug.
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -124,7 +63,7 @@ static int get_matching_mc(struct microcode_intel *mc_intel, int cpu)
 	cpf = cpu_sig.pf;
 	crev = cpu_sig.rev;
 
-	return get_matching_microcode(csig, cpf, crev, mc_intel);
+	return has_newer_microcode(mc_intel, csig, cpf, crev);
 }
 
 static int apply_microcode_intel(int cpu)
@@ -226,7 +165,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
 
 		csig = uci->cpu_sig.sig;
 		cpf = uci->cpu_sig.pf;
-		if (get_matching_microcode(csig, cpf, new_rev, mc)) {
+		if (has_newer_microcode(mc, csig, cpf, new_rev)) {
 			vfree(new_mc);
 			new_rev = mc_header.rev;
 			new_mc  = mc;
diff --git a/arch/x86/kernel/cpu/microcode/intel_early.c b/arch/x86/kernel/cpu/microcode/intel_early.c
index 2f49ab4ac0ae..8187b7247d1c 100644
--- a/arch/x86/kernel/cpu/microcode/intel_early.c
+++ b/arch/x86/kernel/cpu/microcode/intel_early.c
@@ -59,10 +59,10 @@ load_microcode_early(struct microcode_intel **saved,
 		ucode_ptr = saved[i];
 		mc_hdr	  = (struct microcode_header_intel *)ucode_ptr;
 
-		ret = get_matching_microcode(uci->cpu_sig.sig,
-					     uci->cpu_sig.pf,
-					     new_rev,
-					     ucode_ptr);
+		ret = has_newer_microcode(ucode_ptr,
+					  uci->cpu_sig.sig,
+					  uci->cpu_sig.pf,
+					  new_rev);
 		if (!ret)
 			continue;
 
@@ -246,7 +246,7 @@ static unsigned int _save_mc(struct microcode_intel **mc_saved,
 			     u8 *ucode_ptr, unsigned int num_saved)
 {
 	struct microcode_header_intel *mc_hdr, *mc_saved_hdr;
-	unsigned int sig, pf, new_rev;
+	unsigned int sig, pf;
 	int found = 0, i;
 
 	mc_hdr = (struct microcode_header_intel *)ucode_ptr;
@@ -255,14 +255,13 @@ static unsigned int _save_mc(struct microcode_intel **mc_saved,
 		mc_saved_hdr = (struct microcode_header_intel *)mc_saved[i];
 		sig	     = mc_saved_hdr->sig;
 		pf	     = mc_saved_hdr->pf;
-		new_rev	     = mc_hdr->rev;
 
-		if (!get_matching_sig(sig, pf, new_rev, ucode_ptr))
+		if (!find_matching_signature(ucode_ptr, sig, pf))
 			continue;
 
 		found = 1;
 
-		if (!revision_is_newer(mc_hdr, new_rev))
+		if (mc_hdr->rev <= mc_saved_hdr->rev)
 			continue;
 
 		/*
@@ -522,6 +521,27 @@ out:
 EXPORT_SYMBOL_GPL(save_mc_for_early);
 #endif
 
+static bool __init load_builtin_intel_microcode(struct cpio_data *cp)
+{
+#ifdef CONFIG_X86_64
+	unsigned int eax = 0x00000001, ebx, ecx = 0, edx;
+	unsigned int family, model, stepping;
+	char name[30];
+
+	native_cpuid(&eax, &ebx, &ecx, &edx);
+
+	family   = __x86_family(eax);
+	model    = x86_model(eax);
+	stepping = eax & 0xf;
+
+	sprintf(name, "intel-ucode/%02x-%02x-%02x", family, model, stepping);
+
+	return get_builtin_firmware(cp, name);
+#else
+	return false;
+#endif
+}
+
 static __initdata char ucode_name[] = "kernel/x86/microcode/GenuineIntel.bin";
 static __init enum ucode_state
 scan_microcode(struct mc_saved_data *mc_saved_data, unsigned long *initrd,
@@ -540,8 +560,10 @@ scan_microcode(struct mc_saved_data *mc_saved_data, unsigned long *initrd,
 	cd.size = 0;
 
 	cd = find_cpio_data(p, (void *)start, size, &offset);
-	if (!cd.data)
-		return UCODE_ERROR;
+	if (!cd.data) {
+		if (!load_builtin_intel_microcode(&cd))
+			return UCODE_ERROR;
+	}
 
 	return get_matching_model_microcode(0, start, cd.data, cd.size,
 					    mc_saved_data, initrd, uci);
diff --git a/arch/x86/kernel/cpu/microcode/intel_lib.c b/arch/x86/kernel/cpu/microcode/intel_lib.c
index cd47a510a3f1..1883d252ff7d 100644
--- a/arch/x86/kernel/cpu/microcode/intel_lib.c
+++ b/arch/x86/kernel/cpu/microcode/intel_lib.c
@@ -31,11 +31,18 @@
 #include <asm/processor.h>
 #include <asm/msr.h>
 
-static inline int
-update_match_cpu(unsigned int csig, unsigned int cpf,
-		 unsigned int sig, unsigned int pf)
+static inline bool cpu_signatures_match(unsigned int s1, unsigned int p1,
+					unsigned int s2, unsigned int p2)
 {
-	return (!sigmatch(sig, csig, pf, cpf)) ? 0 : 1;
+	if (s1 != s2)
+		return false;
+
+	/* Processor flags are either both 0 ... */
+	if (!p1 && !p2)
+		return true;
+
+	/* ... or they intersect. */
+	return p1 & p2;
 }
 
 int microcode_sanity_check(void *mc, int print_err)
@@ -124,27 +131,25 @@ EXPORT_SYMBOL_GPL(microcode_sanity_check);
 /*
  * Returns 1 if update has been found, 0 otherwise.
  */
-int get_matching_sig(unsigned int csig, int cpf, int rev, void *mc)
+int find_matching_signature(void *mc, unsigned int csig, int cpf)
 {
-	struct microcode_header_intel *mc_header = mc;
-	struct extended_sigtable *ext_header;
-	unsigned long total_size = get_totalsize(mc_header);
-	int ext_sigcount, i;
+	struct microcode_header_intel *mc_hdr = mc;
+	struct extended_sigtable *ext_hdr;
 	struct extended_signature *ext_sig;
+	int i;
 
-	if (update_match_cpu(csig, cpf, mc_header->sig, mc_header->pf))
+	if (cpu_signatures_match(csig, cpf, mc_hdr->sig, mc_hdr->pf))
 		return 1;
 
 	/* Look for ext. headers: */
-	if (total_size <= get_datasize(mc_header) + MC_HEADER_SIZE)
+	if (get_totalsize(mc_hdr) <= get_datasize(mc_hdr) + MC_HEADER_SIZE)
 		return 0;
 
-	ext_header = mc + get_datasize(mc_header) + MC_HEADER_SIZE;
-	ext_sigcount = ext_header->count;
-	ext_sig = (void *)ext_header + EXT_HEADER_SIZE;
+	ext_hdr = mc + get_datasize(mc_hdr) + MC_HEADER_SIZE;
+	ext_sig = (void *)ext_hdr + EXT_HEADER_SIZE;
 
-	for (i = 0; i < ext_sigcount; i++) {
-		if (update_match_cpu(csig, cpf, ext_sig->sig, ext_sig->pf))
+	for (i = 0; i < ext_hdr->count; i++) {
+		if (cpu_signatures_match(csig, cpf, ext_sig->sig, ext_sig->pf))
 			return 1;
 		ext_sig++;
 	}
@@ -154,13 +159,13 @@ int get_matching_sig(unsigned int csig, int cpf, int rev, void *mc)
 /*
  * Returns 1 if update has been found, 0 otherwise.
  */
-int get_matching_microcode(unsigned int csig, int cpf, int rev, void *mc)
+int has_newer_microcode(void *mc, unsigned int csig, int cpf, int new_rev)
 {
 	struct microcode_header_intel *mc_hdr = mc;
 
-	if (!revision_is_newer(mc_hdr, rev))
+	if (mc_hdr->rev <= new_rev)
 		return 0;
 
-	return get_matching_sig(csig, cpf, rev, mc);
+	return find_matching_signature(mc, csig, cpf);
 }
-EXPORT_SYMBOL_GPL(get_matching_microcode);
+EXPORT_SYMBOL_GPL(has_newer_microcode);
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 939155ffdece..aad4bd84b475 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -39,14 +39,12 @@ void hyperv_vector_handler(struct pt_regs *regs)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
 
-	irq_enter();
-	exit_idle();
-
+	entering_irq();
 	inc_irq_stat(irq_hv_callback_count);
 	if (vmbus_handler)
 		vmbus_handler();
 
-	irq_exit();
+	exiting_irq();
 	set_irq_regs(old_regs);
 }
 
diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c
index 5f90b85ff22e..70d7c93f4550 100644
--- a/arch/x86/kernel/cpu/mtrr/cleanup.c
+++ b/arch/x86/kernel/cpu/mtrr/cleanup.c
@@ -98,7 +98,8 @@ x86_get_mtrr_mem_range(struct range *range, int nr_range,
 			continue;
 		base = range_state[i].base_pfn;
 		if (base < (1<<(20-PAGE_SHIFT)) && mtrr_state.have_fixed &&
-		    (mtrr_state.enabled & 1)) {
+		    (mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED) &&
+		    (mtrr_state.enabled & MTRR_STATE_MTRR_FIXED_ENABLED)) {
 			/* Var MTRR contains UC entry below 1M? Skip it: */
 			printk(BIOS_BUG_MSG, i);
 			if (base + size <= (1<<(20-PAGE_SHIFT)))
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 7d74f7b3c6ba..3b533cf37c74 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -102,59 +102,76 @@ static int check_type_overlap(u8 *prev, u8 *curr)
 	return 0;
 }
 
-/*
- * Error/Semi-error returns:
- * 0xFF - when MTRR is not enabled
- * *repeat == 1 implies [start:end] spanned across MTRR range and type returned
- *		corresponds only to [start:*partial_end].
- *		Caller has to lookup again for [*partial_end:end].
+/**
+ * mtrr_type_lookup_fixed - look up memory type in MTRR fixed entries
+ *
+ * Return the MTRR fixed memory type of 'start'.
+ *
+ * MTRR fixed entries are divided into the following ways:
+ *  0x00000 - 0x7FFFF : This range is divided into eight 64KB sub-ranges
+ *  0x80000 - 0xBFFFF : This range is divided into sixteen 16KB sub-ranges
+ *  0xC0000 - 0xFFFFF : This range is divided into sixty-four 4KB sub-ranges
+ *
+ * Return Values:
+ * MTRR_TYPE_(type)  - Matched memory type
+ * MTRR_TYPE_INVALID - Unmatched
+ */
+static u8 mtrr_type_lookup_fixed(u64 start, u64 end)
+{
+	int idx;
+
+	if (start >= 0x100000)
+		return MTRR_TYPE_INVALID;
+
+	/* 0x0 - 0x7FFFF */
+	if (start < 0x80000) {
+		idx = 0;
+		idx += (start >> 16);
+		return mtrr_state.fixed_ranges[idx];
+	/* 0x80000 - 0xBFFFF */
+	} else if (start < 0xC0000) {
+		idx = 1 * 8;
+		idx += ((start - 0x80000) >> 14);
+		return mtrr_state.fixed_ranges[idx];
+	}
+
+	/* 0xC0000 - 0xFFFFF */
+	idx = 3 * 8;
+	idx += ((start - 0xC0000) >> 12);
+	return mtrr_state.fixed_ranges[idx];
+}
+
+/**
+ * mtrr_type_lookup_variable - look up memory type in MTRR variable entries
+ *
+ * Return Value:
+ * MTRR_TYPE_(type) - Matched memory type or default memory type (unmatched)
+ *
+ * Output Arguments:
+ * repeat - Set to 1 when [start:end] spanned across MTRR range and type
+ *	    returned corresponds only to [start:*partial_end].  Caller has
+ *	    to lookup again for [*partial_end:end].
+ *
+ * uniform - Set to 1 when an MTRR covers the region uniformly, i.e. the
+ *	     region is fully covered by a single MTRR entry or the default
+ *	     type.
  */
-static u8 __mtrr_type_lookup(u64 start, u64 end, u64 *partial_end, int *repeat)
+static u8 mtrr_type_lookup_variable(u64 start, u64 end, u64 *partial_end,
+				    int *repeat, u8 *uniform)
 {
 	int i;
 	u64 base, mask;
 	u8 prev_match, curr_match;
 
 	*repeat = 0;
-	if (!mtrr_state_set)
-		return 0xFF;
-
-	if (!mtrr_state.enabled)
-		return 0xFF;
+	*uniform = 1;
 
-	/* Make end inclusive end, instead of exclusive */
+	/* Make end inclusive instead of exclusive */
 	end--;
 
-	/* Look in fixed ranges. Just return the type as per start */
-	if (mtrr_state.have_fixed && (start < 0x100000)) {
-		int idx;
-
-		if (start < 0x80000) {
-			idx = 0;
-			idx += (start >> 16);
-			return mtrr_state.fixed_ranges[idx];
-		} else if (start < 0xC0000) {
-			idx = 1 * 8;
-			idx += ((start - 0x80000) >> 14);
-			return mtrr_state.fixed_ranges[idx];
-		} else if (start < 0x1000000) {
-			idx = 3 * 8;
-			idx += ((start - 0xC0000) >> 12);
-			return mtrr_state.fixed_ranges[idx];
-		}
-	}
-
-	/*
-	 * Look in variable ranges
-	 * Look of multiple ranges matching this address and pick type
-	 * as per MTRR precedence
-	 */
-	if (!(mtrr_state.enabled & 2))
-		return mtrr_state.def_type;
-
-	prev_match = 0xFF;
+	prev_match = MTRR_TYPE_INVALID;
 	for (i = 0; i < num_var_ranges; ++i) {
-		unsigned short start_state, end_state;
+		unsigned short start_state, end_state, inclusive;
 
 		if (!(mtrr_state.var_ranges[i].mask_lo & (1 << 11)))
 			continue;
@@ -166,20 +183,29 @@ static u8 __mtrr_type_lookup(u64 start, u64 end, u64 *partial_end, int *repeat)
 
 		start_state = ((start & mask) == (base & mask));
 		end_state = ((end & mask) == (base & mask));
+		inclusive = ((start < base) && (end > base));
 
-		if (start_state != end_state) {
+		if ((start_state != end_state) || inclusive) {
 			/*
 			 * We have start:end spanning across an MTRR.
-			 * We split the region into
-			 * either
-			 * (start:mtrr_end) (mtrr_end:end)
-			 * or
-			 * (start:mtrr_start) (mtrr_start:end)
+			 * We split the region into either
+			 *
+			 * - start_state:1
+			 * (start:mtrr_end)(mtrr_end:end)
+			 * - end_state:1
+			 * (start:mtrr_start)(mtrr_start:end)
+			 * - inclusive:1
+			 * (start:mtrr_start)(mtrr_start:mtrr_end)(mtrr_end:end)
+			 *
 			 * depending on kind of overlap.
-			 * Return the type for first region and a pointer to
-			 * the start of second region so that caller will
-			 * lookup again on the second region.
-			 * Note: This way we handle multiple overlaps as well.
+			 *
+			 * Return the type of the first region and a pointer
+			 * to the start of next region so that caller will be
+			 * advised to lookup again after having adjusted start
+			 * and end.
+			 *
+			 * Note: This way we handle overlaps with multiple
+			 * entries and the default type properly.
 			 */
 			if (start_state)
 				*partial_end = base + get_mtrr_size(mask);
@@ -193,59 +219,94 @@ static u8 __mtrr_type_lookup(u64 start, u64 end, u64 *partial_end, int *repeat)
 
 			end = *partial_end - 1; /* end is inclusive */
 			*repeat = 1;
+			*uniform = 0;
 		}
 
 		if ((start & mask) != (base & mask))
 			continue;
 
 		curr_match = mtrr_state.var_ranges[i].base_lo & 0xff;
-		if (prev_match == 0xFF) {
+		if (prev_match == MTRR_TYPE_INVALID) {
 			prev_match = curr_match;
 			continue;
 		}
 
+		*uniform = 0;
 		if (check_type_overlap(&prev_match, &curr_match))
 			return curr_match;
 	}
 
-	if (mtrr_tom2) {
-		if (start >= (1ULL<<32) && (end < mtrr_tom2))
-			return MTRR_TYPE_WRBACK;
-	}
-
-	if (prev_match != 0xFF)
+	if (prev_match != MTRR_TYPE_INVALID)
 		return prev_match;
 
 	return mtrr_state.def_type;
 }
 
-/*
- * Returns the effective MTRR type for the region
- * Error return:
- * 0xFF - when MTRR is not enabled
+/**
+ * mtrr_type_lookup - look up memory type in MTRR
+ *
+ * Return Values:
+ * MTRR_TYPE_(type)  - The effective MTRR type for the region
+ * MTRR_TYPE_INVALID - MTRR is disabled
+ *
+ * Output Argument:
+ * uniform - Set to 1 when an MTRR covers the region uniformly, i.e. the
+ *	     region is fully covered by a single MTRR entry or the default
+ *	     type.
  */
-u8 mtrr_type_lookup(u64 start, u64 end)
+u8 mtrr_type_lookup(u64 start, u64 end, u8 *uniform)
 {
-	u8 type, prev_type;
+	u8 type, prev_type, is_uniform = 1, dummy;
 	int repeat;
 	u64 partial_end;
 
-	type = __mtrr_type_lookup(start, end, &partial_end, &repeat);
+	if (!mtrr_state_set)
+		return MTRR_TYPE_INVALID;
+
+	if (!(mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED))
+		return MTRR_TYPE_INVALID;
+
+	/*
+	 * Look up the fixed ranges first, which take priority over
+	 * the variable ranges.
+	 */
+	if ((start < 0x100000) &&
+	    (mtrr_state.have_fixed) &&
+	    (mtrr_state.enabled & MTRR_STATE_MTRR_FIXED_ENABLED)) {
+		is_uniform = 0;
+		type = mtrr_type_lookup_fixed(start, end);
+		goto out;
+	}
+
+	/*
+	 * Look up the variable ranges.  Look of multiple ranges matching
+	 * this address and pick type as per MTRR precedence.
+	 */
+	type = mtrr_type_lookup_variable(start, end, &partial_end,
+					 &repeat, &is_uniform);
 
 	/*
 	 * Common path is with repeat = 0.
 	 * However, we can have cases where [start:end] spans across some
-	 * MTRR range. Do repeated lookups for that case here.
+	 * MTRR ranges and/or the default type.  Do repeated lookups for
+	 * that case here.
 	 */
 	while (repeat) {
 		prev_type = type;
 		start = partial_end;
-		type = __mtrr_type_lookup(start, end, &partial_end, &repeat);
+		is_uniform = 0;
+		type = mtrr_type_lookup_variable(start, end, &partial_end,
+						 &repeat, &dummy);
 
 		if (check_type_overlap(&prev_type, &type))
-			return type;
+			goto out;
 	}
 
+	if (mtrr_tom2 && (start >= (1ULL<<32)) && (end < mtrr_tom2))
+		type = MTRR_TYPE_WRBACK;
+
+out:
+	*uniform = is_uniform;
 	return type;
 }
 
@@ -347,7 +408,9 @@ static void __init print_mtrr_state(void)
 		 mtrr_attrib_to_str(mtrr_state.def_type));
 	if (mtrr_state.have_fixed) {
 		pr_debug("MTRR fixed ranges %sabled:\n",
-			 mtrr_state.enabled & 1 ? "en" : "dis");
+			((mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED) &&
+			 (mtrr_state.enabled & MTRR_STATE_MTRR_FIXED_ENABLED)) ?
+			 "en" : "dis");
 		print_fixed(0x00000, 0x10000, mtrr_state.fixed_ranges + 0);
 		for (i = 0; i < 2; ++i)
 			print_fixed(0x80000 + i * 0x20000, 0x04000,
@@ -360,7 +423,7 @@ static void __init print_mtrr_state(void)
 		print_fixed_last();
 	}
 	pr_debug("MTRR variable ranges %sabled:\n",
-		 mtrr_state.enabled & 2 ? "en" : "dis");
+		 mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED ? "en" : "dis");
 	high_width = (__ffs64(size_or_mask) - (32 - PAGE_SHIFT) + 3) / 4;
 
 	for (i = 0; i < num_var_ranges; ++i) {
@@ -382,7 +445,7 @@ static void __init print_mtrr_state(void)
 }
 
 /* Grab all of the MTRR state for this CPU into *state */
-void __init get_mtrr_state(void)
+bool __init get_mtrr_state(void)
 {
 	struct mtrr_var_range *vrs;
 	unsigned long flags;
@@ -426,6 +489,8 @@ void __init get_mtrr_state(void)
 
 	post_set();
 	local_irq_restore(flags);
+
+	return !!(mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED);
 }
 
 /* Some BIOS's are messed up and don't set all MTRRs the same! */
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index ea5f363a1948..e7ed0d8ebacb 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -59,6 +59,12 @@
 #define MTRR_TO_PHYS_WC_OFFSET 1000
 
 u32 num_var_ranges;
+static bool __mtrr_enabled;
+
+static bool mtrr_enabled(void)
+{
+	return __mtrr_enabled;
+}
 
 unsigned int mtrr_usage_table[MTRR_MAX_VAR_RANGES];
 static DEFINE_MUTEX(mtrr_mutex);
@@ -286,7 +292,7 @@ int mtrr_add_page(unsigned long base, unsigned long size,
 	int i, replace, error;
 	mtrr_type ltype;
 
-	if (!mtrr_if)
+	if (!mtrr_enabled())
 		return -ENXIO;
 
 	error = mtrr_if->validate_add_page(base, size, type);
@@ -435,6 +441,8 @@ static int mtrr_check(unsigned long base, unsigned long size)
 int mtrr_add(unsigned long base, unsigned long size, unsigned int type,
 	     bool increment)
 {
+	if (!mtrr_enabled())
+		return -ENODEV;
 	if (mtrr_check(base, size))
 		return -EINVAL;
 	return mtrr_add_page(base >> PAGE_SHIFT, size >> PAGE_SHIFT, type,
@@ -463,8 +471,8 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size)
 	unsigned long lbase, lsize;
 	int error = -EINVAL;
 
-	if (!mtrr_if)
-		return -ENXIO;
+	if (!mtrr_enabled())
+		return -ENODEV;
 
 	max = num_var_ranges;
 	/* No CPU hotplug when we change MTRR entries */
@@ -523,6 +531,8 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size)
  */
 int mtrr_del(int reg, unsigned long base, unsigned long size)
 {
+	if (!mtrr_enabled())
+		return -ENODEV;
 	if (mtrr_check(base, size))
 		return -EINVAL;
 	return mtrr_del_page(reg, base >> PAGE_SHIFT, size >> PAGE_SHIFT);
@@ -538,6 +548,9 @@ EXPORT_SYMBOL(mtrr_del);
  * attempts to add a WC MTRR covering size bytes starting at base and
  * logs an error if this fails.
  *
+ * The called should provide a power of two size on an equivalent
+ * power of two boundary.
+ *
  * Drivers must store the return value to pass to mtrr_del_wc_if_needed,
  * but drivers should not try to interpret that return value.
  */
@@ -545,7 +558,7 @@ int arch_phys_wc_add(unsigned long base, unsigned long size)
 {
 	int ret;
 
-	if (pat_enabled)
+	if (pat_enabled() || !mtrr_enabled())
 		return 0;  /* Success!  (We don't need to do anything.) */
 
 	ret = mtrr_add(base, size, MTRR_TYPE_WRCOMB, true);
@@ -577,7 +590,7 @@ void arch_phys_wc_del(int handle)
 EXPORT_SYMBOL(arch_phys_wc_del);
 
 /*
- * phys_wc_to_mtrr_index - translates arch_phys_wc_add's return value
+ * arch_phys_wc_index - translates arch_phys_wc_add's return value
  * @handle: Return value from arch_phys_wc_add
  *
  * This will turn the return value from arch_phys_wc_add into an mtrr
@@ -587,14 +600,14 @@ EXPORT_SYMBOL(arch_phys_wc_del);
  * in printk line.  Alas there is an illegitimate use in some ancient
  * drm ioctls.
  */
-int phys_wc_to_mtrr_index(int handle)
+int arch_phys_wc_index(int handle)
 {
 	if (handle < MTRR_TO_PHYS_WC_OFFSET)
 		return -1;
 	else
 		return handle - MTRR_TO_PHYS_WC_OFFSET;
 }
-EXPORT_SYMBOL_GPL(phys_wc_to_mtrr_index);
+EXPORT_SYMBOL_GPL(arch_phys_wc_index);
 
 /*
  * HACK ALERT!
@@ -734,10 +747,12 @@ void __init mtrr_bp_init(void)
 	}
 
 	if (mtrr_if) {
+		__mtrr_enabled = true;
 		set_num_var_ranges();
 		init_table();
 		if (use_intel()) {
-			get_mtrr_state();
+			/* BIOS may override */
+			__mtrr_enabled = get_mtrr_state();
 
 			if (mtrr_cleanup(phys_addr)) {
 				changed_by_mtrr_cleanup = 1;
@@ -745,10 +760,16 @@ void __init mtrr_bp_init(void)
 			}
 		}
 	}
+
+	if (!mtrr_enabled())
+		pr_info("MTRR: Disabled\n");
 }
 
 void mtrr_ap_init(void)
 {
+	if (!mtrr_enabled())
+		return;
+
 	if (!use_intel() || mtrr_aps_delayed_init)
 		return;
 	/*
@@ -774,6 +795,9 @@ void mtrr_save_state(void)
 {
 	int first_cpu;
 
+	if (!mtrr_enabled())
+		return;
+
 	get_online_cpus();
 	first_cpu = cpumask_first(cpu_online_mask);
 	smp_call_function_single(first_cpu, mtrr_save_fixed_ranges, NULL, 1);
@@ -782,6 +806,8 @@ void mtrr_save_state(void)
 
 void set_mtrr_aps_delayed_init(void)
 {
+	if (!mtrr_enabled())
+		return;
 	if (!use_intel())
 		return;
 
@@ -793,7 +819,7 @@ void set_mtrr_aps_delayed_init(void)
  */
 void mtrr_aps_init(void)
 {
-	if (!use_intel())
+	if (!use_intel() || !mtrr_enabled())
 		return;
 
 	/*
@@ -810,7 +836,7 @@ void mtrr_aps_init(void)
 
 void mtrr_bp_restore(void)
 {
-	if (!use_intel())
+	if (!use_intel() || !mtrr_enabled())
 		return;
 
 	mtrr_if->set_all();
@@ -818,7 +844,7 @@ void mtrr_bp_restore(void)
 
 static int __init mtrr_init_finialize(void)
 {
-	if (!mtrr_if)
+	if (!mtrr_enabled())
 		return 0;
 
 	if (use_intel()) {
diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.h b/arch/x86/kernel/cpu/mtrr/mtrr.h
index df5e41f31a27..951884dcc433 100644
--- a/arch/x86/kernel/cpu/mtrr/mtrr.h
+++ b/arch/x86/kernel/cpu/mtrr/mtrr.h
@@ -51,7 +51,7 @@ void set_mtrr_prepare_save(struct set_mtrr_context *ctxt);
 
 void fill_mtrr_var_range(unsigned int index,
 		u32 base_lo, u32 base_hi, u32 mask_lo, u32 mask_hi);
-void get_mtrr_state(void);
+bool get_mtrr_state(void);
 
 extern void set_mtrr_ops(const struct mtrr_ops *ops);
 
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 4f7001f28936..5801a14f7524 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -135,6 +135,7 @@ static int x86_pmu_extra_regs(u64 config, struct perf_event *event)
 }
 
 static atomic_t active_events;
+static atomic_t pmc_refcount;
 static DEFINE_MUTEX(pmc_reserve_mutex);
 
 #ifdef CONFIG_X86_LOCAL_APIC
@@ -270,11 +271,8 @@ msr_fail:
 
 static void hw_perf_event_destroy(struct perf_event *event)
 {
-	if (atomic_dec_and_mutex_lock(&active_events, &pmc_reserve_mutex)) {
-		release_pmc_hardware();
-		release_ds_buffers();
-		mutex_unlock(&pmc_reserve_mutex);
-	}
+	x86_release_hardware();
+	atomic_dec(&active_events);
 }
 
 void hw_perf_lbr_event_destroy(struct perf_event *event)
@@ -324,6 +322,35 @@ set_ext_hw_attr(struct hw_perf_event *hwc, struct perf_event *event)
 	return x86_pmu_extra_regs(val, event);
 }
 
+int x86_reserve_hardware(void)
+{
+	int err = 0;
+
+	if (!atomic_inc_not_zero(&pmc_refcount)) {
+		mutex_lock(&pmc_reserve_mutex);
+		if (atomic_read(&pmc_refcount) == 0) {
+			if (!reserve_pmc_hardware())
+				err = -EBUSY;
+			else
+				reserve_ds_buffers();
+		}
+		if (!err)
+			atomic_inc(&pmc_refcount);
+		mutex_unlock(&pmc_reserve_mutex);
+	}
+
+	return err;
+}
+
+void x86_release_hardware(void)
+{
+	if (atomic_dec_and_mutex_lock(&pmc_refcount, &pmc_reserve_mutex)) {
+		release_pmc_hardware();
+		release_ds_buffers();
+		mutex_unlock(&pmc_reserve_mutex);
+	}
+}
+
 /*
  * Check if we can create event of a certain type (that no conflicting events
  * are present).
@@ -336,21 +363,34 @@ int x86_add_exclusive(unsigned int what)
 		return 0;
 
 	mutex_lock(&pmc_reserve_mutex);
-	for (i = 0; i < ARRAY_SIZE(x86_pmu.lbr_exclusive); i++)
+	for (i = 0; i < ARRAY_SIZE(x86_pmu.lbr_exclusive); i++) {
 		if (i != what && atomic_read(&x86_pmu.lbr_exclusive[i]))
 			goto out;
+	}
 
 	atomic_inc(&x86_pmu.lbr_exclusive[what]);
 	ret = 0;
 
 out:
 	mutex_unlock(&pmc_reserve_mutex);
+
+	/*
+	 * Assuming that all exclusive events will share the PMI handler
+	 * (which checks active_events for whether there is work to do),
+	 * we can bump active_events counter right here, except for
+	 * x86_lbr_exclusive_lbr events that go through x86_pmu_event_init()
+	 * path, which already bumps active_events for them.
+	 */
+	if (!ret && what != x86_lbr_exclusive_lbr)
+		atomic_inc(&active_events);
+
 	return ret;
 }
 
 void x86_del_exclusive(unsigned int what)
 {
 	atomic_dec(&x86_pmu.lbr_exclusive[what]);
+	atomic_dec(&active_events);
 }
 
 int x86_setup_perfctr(struct perf_event *event)
@@ -527,22 +567,11 @@ static int __x86_pmu_event_init(struct perf_event *event)
 	if (!x86_pmu_initialized())
 		return -ENODEV;
 
-	err = 0;
-	if (!atomic_inc_not_zero(&active_events)) {
-		mutex_lock(&pmc_reserve_mutex);
-		if (atomic_read(&active_events) == 0) {
-			if (!reserve_pmc_hardware())
-				err = -EBUSY;
-			else
-				reserve_ds_buffers();
-		}
-		if (!err)
-			atomic_inc(&active_events);
-		mutex_unlock(&pmc_reserve_mutex);
-	}
+	err = x86_reserve_hardware();
 	if (err)
 		return err;
 
+	atomic_inc(&active_events);
 	event->destroy = hw_perf_event_destroy;
 
 	event->hw.idx = -1;
@@ -881,10 +910,7 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
 			if (x86_pmu.commit_scheduling)
 				x86_pmu.commit_scheduling(cpuc, i, assign[i]);
 		}
-	}
-
-	if (!assign || unsched) {
-
+	} else {
 		for (i = 0; i < n; i++) {
 			e = cpuc->event_list[i];
 			/*
@@ -1097,13 +1123,16 @@ int x86_perf_event_set_period(struct perf_event *event)
 
 	per_cpu(pmc_prev_left[idx], smp_processor_id()) = left;
 
-	/*
-	 * The hw event starts counting from this event offset,
-	 * mark it to be able to extra future deltas:
-	 */
-	local64_set(&hwc->prev_count, (u64)-left);
+	if (!(hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) ||
+	    local64_read(&hwc->prev_count) != (u64)-left) {
+		/*
+		 * The hw event starts counting from this event offset,
+		 * mark it to be able to extra future deltas:
+		 */
+		local64_set(&hwc->prev_count, (u64)-left);
 
-	wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask);
+		wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask);
+	}
 
 	/*
 	 * Due to erratum on certan cpu we need
@@ -1415,6 +1444,10 @@ perf_event_nmi_handler(unsigned int cmd, struct pt_regs *regs)
 	u64 finish_clock;
 	int ret;
 
+	/*
+	 * All PMUs/events that share this PMI handler should make sure to
+	 * increment active_events for their events.
+	 */
 	if (!atomic_read(&active_events))
 		return NMI_DONE;
 
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index ef78516850fb..3e7fd27dfe20 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -75,6 +75,8 @@ struct event_constraint {
 #define PERF_X86_EVENT_DYNAMIC		0x0080 /* dynamic alloc'd constraint */
 #define PERF_X86_EVENT_RDPMC_ALLOWED	0x0100 /* grant rdpmc permission */
 #define PERF_X86_EVENT_EXCL_ACCT	0x0200 /* accounted EXCL event */
+#define PERF_X86_EVENT_AUTO_RELOAD	0x0400 /* use PEBS auto-reload */
+#define PERF_X86_EVENT_FREERUNNING	0x0800 /* use freerunning PEBS */
 
 
 struct amd_nb {
@@ -88,6 +90,18 @@ struct amd_nb {
 #define MAX_PEBS_EVENTS		8
 
 /*
+ * Flags PEBS can handle without an PMI.
+ *
+ * TID can only be handled by flushing at context switch.
+ *
+ */
+#define PEBS_FREERUNNING_FLAGS \
+	(PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_ADDR | \
+	PERF_SAMPLE_ID | PERF_SAMPLE_CPU | PERF_SAMPLE_STREAM_ID | \
+	PERF_SAMPLE_DATA_SRC | PERF_SAMPLE_IDENTIFIER | \
+	PERF_SAMPLE_TRANSACTION)
+
+/*
  * A debug store configuration.
  *
  * We only support architectures that use 64bit fields.
@@ -133,7 +147,6 @@ enum intel_excl_state_type {
 };
 
 struct intel_excl_states {
-	enum intel_excl_state_type init_state[X86_PMC_IDX_MAX];
 	enum intel_excl_state_type state[X86_PMC_IDX_MAX];
 	bool sched_started; /* true if scheduling has started */
 };
@@ -527,10 +540,10 @@ struct x86_pmu {
 	void		(*put_event_constraints)(struct cpu_hw_events *cpuc,
 						 struct perf_event *event);
 
-	void		(*commit_scheduling)(struct cpu_hw_events *cpuc, int idx, int cntr);
-
 	void		(*start_scheduling)(struct cpu_hw_events *cpuc);
 
+	void		(*commit_scheduling)(struct cpu_hw_events *cpuc, int idx, int cntr);
+
 	void		(*stop_scheduling)(struct cpu_hw_events *cpuc);
 
 	struct event_constraint *event_constraints;
@@ -703,6 +716,10 @@ int x86_add_exclusive(unsigned int what);
 
 void x86_del_exclusive(unsigned int what);
 
+int x86_reserve_hardware(void);
+
+void x86_release_hardware(void);
+
 void hw_perf_lbr_event_destroy(struct perf_event *event);
 
 int x86_setup_perfctr(struct perf_event *event);
@@ -866,6 +883,8 @@ void intel_pmu_pebs_enable_all(void);
 
 void intel_pmu_pebs_disable_all(void);
 
+void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in);
+
 void intel_ds_init(void);
 
 void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in);
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index a1e35c9f06b9..b9826a981fb2 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1903,9 +1903,8 @@ static void
 intel_start_scheduling(struct cpu_hw_events *cpuc)
 {
 	struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs;
-	struct intel_excl_states *xl, *xlo;
+	struct intel_excl_states *xl;
 	int tid = cpuc->excl_thread_id;
-	int o_tid = 1 - tid; /* sibling thread */
 
 	/*
 	 * nothing needed if in group validation mode
@@ -1916,10 +1915,9 @@ intel_start_scheduling(struct cpu_hw_events *cpuc)
 	/*
 	 * no exclusion needed
 	 */
-	if (!excl_cntrs)
+	if (WARN_ON_ONCE(!excl_cntrs))
 		return;
 
-	xlo = &excl_cntrs->states[o_tid];
 	xl = &excl_cntrs->states[tid];
 
 	xl->sched_started = true;
@@ -1928,22 +1926,41 @@ intel_start_scheduling(struct cpu_hw_events *cpuc)
 	 * in stop_event_scheduling()
 	 * makes scheduling appear as a transaction
 	 */
-	WARN_ON_ONCE(!irqs_disabled());
 	raw_spin_lock(&excl_cntrs->lock);
+}
 
-	/*
-	 * save initial state of sibling thread
-	 */
-	memcpy(xlo->init_state, xlo->state, sizeof(xlo->init_state));
+static void intel_commit_scheduling(struct cpu_hw_events *cpuc, int idx, int cntr)
+{
+	struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs;
+	struct event_constraint *c = cpuc->event_constraint[idx];
+	struct intel_excl_states *xl;
+	int tid = cpuc->excl_thread_id;
+
+	if (cpuc->is_fake || !is_ht_workaround_enabled())
+		return;
+
+	if (WARN_ON_ONCE(!excl_cntrs))
+		return;
+
+	if (!(c->flags & PERF_X86_EVENT_DYNAMIC))
+		return;
+
+	xl = &excl_cntrs->states[tid];
+
+	lockdep_assert_held(&excl_cntrs->lock);
+
+	if (c->flags & PERF_X86_EVENT_EXCL)
+		xl->state[cntr] = INTEL_EXCL_EXCLUSIVE;
+	else
+		xl->state[cntr] = INTEL_EXCL_SHARED;
 }
 
 static void
 intel_stop_scheduling(struct cpu_hw_events *cpuc)
 {
 	struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs;
-	struct intel_excl_states *xl, *xlo;
+	struct intel_excl_states *xl;
 	int tid = cpuc->excl_thread_id;
-	int o_tid = 1 - tid; /* sibling thread */
 
 	/*
 	 * nothing needed if in group validation mode
@@ -1953,17 +1970,11 @@ intel_stop_scheduling(struct cpu_hw_events *cpuc)
 	/*
 	 * no exclusion needed
 	 */
-	if (!excl_cntrs)
+	if (WARN_ON_ONCE(!excl_cntrs))
 		return;
 
-	xlo = &excl_cntrs->states[o_tid];
 	xl = &excl_cntrs->states[tid];
 
-	/*
-	 * make new sibling thread state visible
-	 */
-	memcpy(xlo->state, xlo->init_state, sizeof(xlo->state));
-
 	xl->sched_started = false;
 	/*
 	 * release shared state lock (acquired in intel_start_scheduling())
@@ -1975,12 +1986,10 @@ static struct event_constraint *
 intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event,
 			   int idx, struct event_constraint *c)
 {
-	struct event_constraint *cx;
 	struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs;
-	struct intel_excl_states *xl, *xlo;
-	int is_excl, i;
+	struct intel_excl_states *xlo;
 	int tid = cpuc->excl_thread_id;
-	int o_tid = 1 - tid; /* alternate */
+	int is_excl, i;
 
 	/*
 	 * validating a group does not require
@@ -1992,27 +2001,8 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event,
 	/*
 	 * no exclusion needed
 	 */
-	if (!excl_cntrs)
+	if (WARN_ON_ONCE(!excl_cntrs))
 		return c;
-	/*
-	 * event requires exclusive counter access
-	 * across HT threads
-	 */
-	is_excl = c->flags & PERF_X86_EVENT_EXCL;
-	if (is_excl && !(event->hw.flags & PERF_X86_EVENT_EXCL_ACCT)) {
-		event->hw.flags |= PERF_X86_EVENT_EXCL_ACCT;
-		if (!cpuc->n_excl++)
-			WRITE_ONCE(excl_cntrs->has_exclusive[tid], 1);
-	}
-
-	/*
-	 * xl = state of current HT
-	 * xlo = state of sibling HT
-	 */
-	xl = &excl_cntrs->states[tid];
-	xlo = &excl_cntrs->states[o_tid];
-
-	cx = c;
 
 	/*
 	 * because we modify the constraint, we need
@@ -2023,10 +2013,7 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event,
 	 * been cloned (marked dynamic)
 	 */
 	if (!(c->flags & PERF_X86_EVENT_DYNAMIC)) {
-
-		/* sanity check */
-		if (idx < 0)
-			return &emptyconstraint;
+		struct event_constraint *cx;
 
 		/*
 		 * grab pre-allocated constraint entry
@@ -2037,13 +2024,14 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event,
 		 * initialize dynamic constraint
 		 * with static constraint
 		 */
-		memcpy(cx, c, sizeof(*cx));
+		*cx = *c;
 
 		/*
 		 * mark constraint as dynamic, so we
 		 * can free it later on
 		 */
 		cx->flags |= PERF_X86_EVENT_DYNAMIC;
+		c = cx;
 	}
 
 	/*
@@ -2054,6 +2042,22 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event,
 	 */
 
 	/*
+	 * state of sibling HT
+	 */
+	xlo = &excl_cntrs->states[tid ^ 1];
+
+	/*
+	 * event requires exclusive counter access
+	 * across HT threads
+	 */
+	is_excl = c->flags & PERF_X86_EVENT_EXCL;
+	if (is_excl && !(event->hw.flags & PERF_X86_EVENT_EXCL_ACCT)) {
+		event->hw.flags |= PERF_X86_EVENT_EXCL_ACCT;
+		if (!cpuc->n_excl++)
+			WRITE_ONCE(excl_cntrs->has_exclusive[tid], 1);
+	}
+
+	/*
 	 * Modify static constraint with current dynamic
 	 * state of thread
 	 *
@@ -2061,37 +2065,37 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event,
 	 * SHARED   : sibling counter measuring non-exclusive event
 	 * UNUSED   : sibling counter unused
 	 */
-	for_each_set_bit(i, cx->idxmsk, X86_PMC_IDX_MAX) {
+	for_each_set_bit(i, c->idxmsk, X86_PMC_IDX_MAX) {
 		/*
 		 * exclusive event in sibling counter
 		 * our corresponding counter cannot be used
 		 * regardless of our event
 		 */
-		if (xl->state[i] == INTEL_EXCL_EXCLUSIVE)
-			__clear_bit(i, cx->idxmsk);
+		if (xlo->state[i] == INTEL_EXCL_EXCLUSIVE)
+			__clear_bit(i, c->idxmsk);
 		/*
 		 * if measuring an exclusive event, sibling
 		 * measuring non-exclusive, then counter cannot
 		 * be used
 		 */
-		if (is_excl && xl->state[i] == INTEL_EXCL_SHARED)
-			__clear_bit(i, cx->idxmsk);
+		if (is_excl && xlo->state[i] == INTEL_EXCL_SHARED)
+			__clear_bit(i, c->idxmsk);
 	}
 
 	/*
 	 * recompute actual bit weight for scheduling algorithm
 	 */
-	cx->weight = hweight64(cx->idxmsk64);
+	c->weight = hweight64(c->idxmsk64);
 
 	/*
 	 * if we return an empty mask, then switch
 	 * back to static empty constraint to avoid
 	 * the cost of freeing later on
 	 */
-	if (cx->weight == 0)
-		cx = &emptyconstraint;
+	if (c->weight == 0)
+		c = &emptyconstraint;
 
-	return cx;
+	return c;
 }
 
 static struct event_constraint *
@@ -2124,10 +2128,8 @@ static void intel_put_excl_constraints(struct cpu_hw_events *cpuc,
 {
 	struct hw_perf_event *hwc = &event->hw;
 	struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs;
-	struct intel_excl_states *xlo, *xl;
-	unsigned long flags = 0; /* keep compiler happy */
 	int tid = cpuc->excl_thread_id;
-	int o_tid = 1 - tid;
+	struct intel_excl_states *xl;
 
 	/*
 	 * nothing needed if in group validation mode
@@ -2135,13 +2137,9 @@ static void intel_put_excl_constraints(struct cpu_hw_events *cpuc,
 	if (cpuc->is_fake)
 		return;
 
-	WARN_ON_ONCE(!excl_cntrs);
-
-	if (!excl_cntrs)
+	if (WARN_ON_ONCE(!excl_cntrs))
 		return;
 
-	xl = &excl_cntrs->states[tid];
-	xlo = &excl_cntrs->states[o_tid];
 	if (hwc->flags & PERF_X86_EVENT_EXCL_ACCT) {
 		hwc->flags &= ~PERF_X86_EVENT_EXCL_ACCT;
 		if (!--cpuc->n_excl)
@@ -2149,22 +2147,25 @@ static void intel_put_excl_constraints(struct cpu_hw_events *cpuc,
 	}
 
 	/*
-	 * put_constraint may be called from x86_schedule_events()
-	 * which already has the lock held so here make locking
-	 * conditional
+	 * If event was actually assigned, then mark the counter state as
+	 * unused now.
 	 */
-	if (!xl->sched_started)
-		raw_spin_lock_irqsave(&excl_cntrs->lock, flags);
+	if (hwc->idx >= 0) {
+		xl = &excl_cntrs->states[tid];
 
-	/*
-	 * if event was actually assigned, then mark the
-	 * counter state as unused now
-	 */
-	if (hwc->idx >= 0)
-		xlo->state[hwc->idx] = INTEL_EXCL_UNUSED;
+		/*
+		 * put_constraint may be called from x86_schedule_events()
+		 * which already has the lock held so here make locking
+		 * conditional.
+		 */
+		if (!xl->sched_started)
+			raw_spin_lock(&excl_cntrs->lock);
+
+		xl->state[hwc->idx] = INTEL_EXCL_UNUSED;
 
-	if (!xl->sched_started)
-		raw_spin_unlock_irqrestore(&excl_cntrs->lock, flags);
+		if (!xl->sched_started)
+			raw_spin_unlock(&excl_cntrs->lock);
+	}
 }
 
 static void
@@ -2196,41 +2197,6 @@ static void intel_put_event_constraints(struct cpu_hw_events *cpuc,
 		intel_put_excl_constraints(cpuc, event);
 }
 
-static void intel_commit_scheduling(struct cpu_hw_events *cpuc, int idx, int cntr)
-{
-	struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs;
-	struct event_constraint *c = cpuc->event_constraint[idx];
-	struct intel_excl_states *xlo, *xl;
-	int tid = cpuc->excl_thread_id;
-	int o_tid = 1 - tid;
-	int is_excl;
-
-	if (cpuc->is_fake || !c)
-		return;
-
-	is_excl = c->flags & PERF_X86_EVENT_EXCL;
-
-	if (!(c->flags & PERF_X86_EVENT_DYNAMIC))
-		return;
-
-	WARN_ON_ONCE(!excl_cntrs);
-
-	if (!excl_cntrs)
-		return;
-
-	xl = &excl_cntrs->states[tid];
-	xlo = &excl_cntrs->states[o_tid];
-
-	WARN_ON_ONCE(!raw_spin_is_locked(&excl_cntrs->lock));
-
-	if (cntr >= 0) {
-		if (is_excl)
-			xlo->init_state[cntr] = INTEL_EXCL_EXCLUSIVE;
-		else
-			xlo->init_state[cntr] = INTEL_EXCL_SHARED;
-	}
-}
-
 static void intel_pebs_aliases_core2(struct perf_event *event)
 {
 	if ((event->hw.config & X86_RAW_EVENT_MASK) == 0x003c) {
@@ -2294,8 +2260,15 @@ static int intel_pmu_hw_config(struct perf_event *event)
 	if (ret)
 		return ret;
 
-	if (event->attr.precise_ip && x86_pmu.pebs_aliases)
-		x86_pmu.pebs_aliases(event);
+	if (event->attr.precise_ip) {
+		if (!event->attr.freq) {
+			event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD;
+			if (!(event->attr.sample_type & ~PEBS_FREERUNNING_FLAGS))
+				event->hw.flags |= PERF_X86_EVENT_FREERUNNING;
+		}
+		if (x86_pmu.pebs_aliases)
+			x86_pmu.pebs_aliases(event);
+	}
 
 	if (needs_branch_stack(event)) {
 		ret = intel_pmu_setup_lbr_filter(event);
@@ -2544,19 +2517,11 @@ struct intel_shared_regs *allocate_shared_regs(int cpu)
 static struct intel_excl_cntrs *allocate_excl_cntrs(int cpu)
 {
 	struct intel_excl_cntrs *c;
-	int i;
 
 	c = kzalloc_node(sizeof(struct intel_excl_cntrs),
 			 GFP_KERNEL, cpu_to_node(cpu));
 	if (c) {
 		raw_spin_lock_init(&c->lock);
-		for (i = 0; i < X86_PMC_IDX_MAX; i++) {
-			c->states[0].state[i] = INTEL_EXCL_UNUSED;
-			c->states[0].init_state[i] = INTEL_EXCL_UNUSED;
-
-			c->states[1].state[i] = INTEL_EXCL_UNUSED;
-			c->states[1].init_state[i] = INTEL_EXCL_UNUSED;
-		}
 		c->core_id = -1;
 	}
 	return c;
@@ -2611,7 +2576,7 @@ static void intel_pmu_cpu_starting(int cpu)
 	if (!(x86_pmu.flags & PMU_FL_NO_HT_SHARING)) {
 		void **onln = &cpuc->kfree_on_online[X86_PERF_KFREE_SHARED];
 
-		for_each_cpu(i, topology_thread_cpumask(cpu)) {
+		for_each_cpu(i, topology_sibling_cpumask(cpu)) {
 			struct intel_shared_regs *pc;
 
 			pc = per_cpu(cpu_hw_events, i).shared_regs;
@@ -2629,7 +2594,7 @@ static void intel_pmu_cpu_starting(int cpu)
 		cpuc->lbr_sel = &cpuc->shared_regs->regs[EXTRA_REG_LBR];
 
 	if (x86_pmu.flags & PMU_FL_EXCL_CNTRS) {
-		for_each_cpu(i, topology_thread_cpumask(cpu)) {
+		for_each_cpu(i, topology_sibling_cpumask(cpu)) {
 			struct intel_excl_cntrs *c;
 
 			c = per_cpu(cpu_hw_events, i).excl_cntrs;
@@ -2677,6 +2642,15 @@ static void intel_pmu_cpu_dying(int cpu)
 	fini_debug_store_on_cpu(cpu);
 }
 
+static void intel_pmu_sched_task(struct perf_event_context *ctx,
+				 bool sched_in)
+{
+	if (x86_pmu.pebs_active)
+		intel_pmu_pebs_sched_task(ctx, sched_in);
+	if (x86_pmu.lbr_nr)
+		intel_pmu_lbr_sched_task(ctx, sched_in);
+}
+
 PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63");
 
 PMU_FORMAT_ATTR(ldlat, "config1:0-15");
@@ -2766,7 +2740,7 @@ static __initconst const struct x86_pmu intel_pmu = {
 	.cpu_starting		= intel_pmu_cpu_starting,
 	.cpu_dying		= intel_pmu_cpu_dying,
 	.guest_get_msrs		= intel_guest_get_msrs,
-	.sched_task		= intel_pmu_lbr_sched_task,
+	.sched_task		= intel_pmu_sched_task,
 };
 
 static __init void intel_clovertown_quirk(void)
@@ -2939,8 +2913,8 @@ static __init void intel_ht_bug(void)
 {
 	x86_pmu.flags |= PMU_FL_EXCL_CNTRS | PMU_FL_EXCL_ENABLED;
 
-	x86_pmu.commit_scheduling = intel_commit_scheduling;
 	x86_pmu.start_scheduling = intel_start_scheduling;
+	x86_pmu.commit_scheduling = intel_commit_scheduling;
 	x86_pmu.stop_scheduling = intel_stop_scheduling;
 }
 
@@ -3253,6 +3227,8 @@ __init int intel_pmu_init(void)
 
 	case 61: /* 14nm Broadwell Core-M */
 	case 86: /* 14nm Broadwell Xeon D */
+	case 71: /* 14nm Broadwell + GT3e (Intel Iris Pro graphics) */
+	case 79: /* 14nm Broadwell Server */
 		x86_pmu.late_ack = true;
 		memcpy(hw_cache_event_ids, hsw_hw_cache_event_ids, sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, hsw_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
@@ -3322,13 +3298,13 @@ __init int intel_pmu_init(void)
 		 * counter, so do not extend mask to generic counters
 		 */
 		for_each_event_constraint(c, x86_pmu.event_constraints) {
-			if (c->cmask != FIXED_EVENT_FLAGS
-			    || c->idxmsk64 == INTEL_PMC_MSK_FIXED_REF_CYCLES) {
-				continue;
+			if (c->cmask == FIXED_EVENT_FLAGS
+			    && c->idxmsk64 != INTEL_PMC_MSK_FIXED_REF_CYCLES) {
+				c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1;
 			}
-
-			c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1;
-			c->weight += x86_pmu.num_counters;
+			c->idxmsk64 &=
+				~(~0UL << (INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed));
+			c->weight = hweight64(c->idxmsk64);
 		}
 	}
 
@@ -3386,7 +3362,7 @@ static __init int fixup_ht_bug(void)
 	if (!(x86_pmu.flags & PMU_FL_EXCL_ENABLED))
 		return 0;
 
-	w = cpumask_weight(topology_thread_cpumask(cpu));
+	w = cpumask_weight(topology_sibling_cpumask(cpu));
 	if (w > 1) {
 		pr_info("PMU erratum BJ122, BV98, HSD29 worked around, HT is on\n");
 		return 0;
@@ -3396,8 +3372,8 @@ static __init int fixup_ht_bug(void)
 
 	x86_pmu.flags &= ~(PMU_FL_EXCL_CNTRS | PMU_FL_EXCL_ENABLED);
 
-	x86_pmu.commit_scheduling = NULL;
 	x86_pmu.start_scheduling = NULL;
+	x86_pmu.commit_scheduling = NULL;
 	x86_pmu.stop_scheduling = NULL;
 
 	watchdog_nmi_enable_all();
diff --git a/arch/x86/kernel/cpu/perf_event_intel_bts.c b/arch/x86/kernel/cpu/perf_event_intel_bts.c
index ac1f0c55f379..7795f3f8b1d5 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_bts.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_bts.c
@@ -483,17 +483,26 @@ static int bts_event_add(struct perf_event *event, int mode)
 
 static void bts_event_destroy(struct perf_event *event)
 {
+	x86_release_hardware();
 	x86_del_exclusive(x86_lbr_exclusive_bts);
 }
 
 static int bts_event_init(struct perf_event *event)
 {
+	int ret;
+
 	if (event->attr.type != bts_pmu.type)
 		return -ENOENT;
 
 	if (x86_add_exclusive(x86_lbr_exclusive_bts))
 		return -EBUSY;
 
+	ret = x86_reserve_hardware();
+	if (ret) {
+		x86_del_exclusive(x86_lbr_exclusive_bts);
+		return ret;
+	}
+
 	event->destroy = bts_event_destroy;
 
 	return 0;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_cqm.c b/arch/x86/kernel/cpu/perf_event_intel_cqm.c
index e4d1b8b738fa..188076161c1b 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_cqm.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_cqm.c
@@ -13,16 +13,35 @@
 #define MSR_IA32_QM_CTR		0x0c8e
 #define MSR_IA32_QM_EVTSEL	0x0c8d
 
-static unsigned int cqm_max_rmid = -1;
+static u32 cqm_max_rmid = -1;
 static unsigned int cqm_l3_scale; /* supposedly cacheline size */
 
-struct intel_cqm_state {
-	raw_spinlock_t		lock;
-	int			rmid;
-	int			cnt;
+/**
+ * struct intel_pqr_state - State cache for the PQR MSR
+ * @rmid:		The cached Resource Monitoring ID
+ * @closid:		The cached Class Of Service ID
+ * @rmid_usecnt:	The usage counter for rmid
+ *
+ * The upper 32 bits of MSR_IA32_PQR_ASSOC contain closid and the
+ * lower 10 bits rmid. The update to MSR_IA32_PQR_ASSOC always
+ * contains both parts, so we need to cache them.
+ *
+ * The cache also helps to avoid pointless updates if the value does
+ * not change.
+ */
+struct intel_pqr_state {
+	u32			rmid;
+	u32			closid;
+	int			rmid_usecnt;
 };
 
-static DEFINE_PER_CPU(struct intel_cqm_state, cqm_state);
+/*
+ * The cached intel_pqr_state is strictly per CPU and can never be
+ * updated from a remote CPU. Both functions which modify the state
+ * (intel_cqm_event_start and intel_cqm_event_stop) are called with
+ * interrupts disabled, which is sufficient for the protection.
+ */
+static DEFINE_PER_CPU(struct intel_pqr_state, pqr_state);
 
 /*
  * Protects cache_cgroups and cqm_rmid_free_lru and cqm_rmid_limbo_lru.
@@ -57,7 +76,7 @@ static cpumask_t cqm_cpumask;
  * near-zero occupancy value, i.e. no cachelines are tagged with this
  * RMID, once __intel_cqm_rmid_rotate() returns.
  */
-static unsigned int intel_cqm_rotation_rmid;
+static u32 intel_cqm_rotation_rmid;
 
 #define INVALID_RMID		(-1)
 
@@ -69,7 +88,7 @@ static unsigned int intel_cqm_rotation_rmid;
  * Likewise, an rmid value of -1 is used to indicate "no rmid currently
  * assigned" and is used as part of the rotation code.
  */
-static inline bool __rmid_valid(unsigned int rmid)
+static inline bool __rmid_valid(u32 rmid)
 {
 	if (!rmid || rmid == INVALID_RMID)
 		return false;
@@ -77,7 +96,7 @@ static inline bool __rmid_valid(unsigned int rmid)
 	return true;
 }
 
-static u64 __rmid_read(unsigned int rmid)
+static u64 __rmid_read(u32 rmid)
 {
 	u64 val;
 
@@ -102,7 +121,7 @@ enum rmid_recycle_state {
 };
 
 struct cqm_rmid_entry {
-	unsigned int rmid;
+	u32 rmid;
 	enum rmid_recycle_state state;
 	struct list_head list;
 	unsigned long queue_time;
@@ -147,7 +166,7 @@ static LIST_HEAD(cqm_rmid_limbo_lru);
  */
 static struct cqm_rmid_entry **cqm_rmid_ptrs;
 
-static inline struct cqm_rmid_entry *__rmid_entry(int rmid)
+static inline struct cqm_rmid_entry *__rmid_entry(u32 rmid)
 {
 	struct cqm_rmid_entry *entry;
 
@@ -162,7 +181,7 @@ static inline struct cqm_rmid_entry *__rmid_entry(int rmid)
  *
  * We expect to be called with cache_mutex held.
  */
-static int __get_rmid(void)
+static u32 __get_rmid(void)
 {
 	struct cqm_rmid_entry *entry;
 
@@ -177,7 +196,7 @@ static int __get_rmid(void)
 	return entry->rmid;
 }
 
-static void __put_rmid(unsigned int rmid)
+static void __put_rmid(u32 rmid)
 {
 	struct cqm_rmid_entry *entry;
 
@@ -372,7 +391,7 @@ static bool __conflict_event(struct perf_event *a, struct perf_event *b)
 }
 
 struct rmid_read {
-	unsigned int rmid;
+	u32 rmid;
 	atomic64_t value;
 };
 
@@ -381,12 +400,11 @@ static void __intel_cqm_event_count(void *info);
 /*
  * Exchange the RMID of a group of events.
  */
-static unsigned int
-intel_cqm_xchg_rmid(struct perf_event *group, unsigned int rmid)
+static u32 intel_cqm_xchg_rmid(struct perf_event *group, u32 rmid)
 {
 	struct perf_event *event;
-	unsigned int old_rmid = group->hw.cqm_rmid;
 	struct list_head *head = &group->hw.cqm_group_entry;
+	u32 old_rmid = group->hw.cqm_rmid;
 
 	lockdep_assert_held(&cache_mutex);
 
@@ -451,7 +469,7 @@ static void intel_cqm_stable(void *arg)
  * If we have group events waiting for an RMID that don't conflict with
  * events already running, assign @rmid.
  */
-static bool intel_cqm_sched_in_event(unsigned int rmid)
+static bool intel_cqm_sched_in_event(u32 rmid)
 {
 	struct perf_event *leader, *event;
 
@@ -598,7 +616,7 @@ static bool intel_cqm_rmid_stabilize(unsigned int *available)
 static void __intel_cqm_pick_and_rotate(struct perf_event *next)
 {
 	struct perf_event *rotor;
-	unsigned int rmid;
+	u32 rmid;
 
 	lockdep_assert_held(&cache_mutex);
 
@@ -626,7 +644,7 @@ static void __intel_cqm_pick_and_rotate(struct perf_event *next)
 static void intel_cqm_sched_out_conflicting_events(struct perf_event *event)
 {
 	struct perf_event *group, *g;
-	unsigned int rmid;
+	u32 rmid;
 
 	lockdep_assert_held(&cache_mutex);
 
@@ -828,8 +846,8 @@ static void intel_cqm_setup_event(struct perf_event *event,
 				  struct perf_event **group)
 {
 	struct perf_event *iter;
-	unsigned int rmid;
 	bool conflict = false;
+	u32 rmid;
 
 	list_for_each_entry(iter, &cache_groups, hw.cqm_groups_entry) {
 		rmid = iter->hw.cqm_rmid;
@@ -860,7 +878,7 @@ static void intel_cqm_setup_event(struct perf_event *event,
 static void intel_cqm_event_read(struct perf_event *event)
 {
 	unsigned long flags;
-	unsigned int rmid;
+	u32 rmid;
 	u64 val;
 
 	/*
@@ -961,55 +979,48 @@ out:
 
 static void intel_cqm_event_start(struct perf_event *event, int mode)
 {
-	struct intel_cqm_state *state = this_cpu_ptr(&cqm_state);
-	unsigned int rmid = event->hw.cqm_rmid;
-	unsigned long flags;
+	struct intel_pqr_state *state = this_cpu_ptr(&pqr_state);
+	u32 rmid = event->hw.cqm_rmid;
 
 	if (!(event->hw.cqm_state & PERF_HES_STOPPED))
 		return;
 
 	event->hw.cqm_state &= ~PERF_HES_STOPPED;
 
-	raw_spin_lock_irqsave(&state->lock, flags);
-
-	if (state->cnt++)
-		WARN_ON_ONCE(state->rmid != rmid);
-	else
+	if (state->rmid_usecnt++) {
+		if (!WARN_ON_ONCE(state->rmid != rmid))
+			return;
+	} else {
 		WARN_ON_ONCE(state->rmid);
+	}
 
 	state->rmid = rmid;
-	wrmsrl(MSR_IA32_PQR_ASSOC, state->rmid);
-
-	raw_spin_unlock_irqrestore(&state->lock, flags);
+	wrmsr(MSR_IA32_PQR_ASSOC, rmid, state->closid);
 }
 
 static void intel_cqm_event_stop(struct perf_event *event, int mode)
 {
-	struct intel_cqm_state *state = this_cpu_ptr(&cqm_state);
-	unsigned long flags;
+	struct intel_pqr_state *state = this_cpu_ptr(&pqr_state);
 
 	if (event->hw.cqm_state & PERF_HES_STOPPED)
 		return;
 
 	event->hw.cqm_state |= PERF_HES_STOPPED;
 
-	raw_spin_lock_irqsave(&state->lock, flags);
 	intel_cqm_event_read(event);
 
-	if (!--state->cnt) {
+	if (!--state->rmid_usecnt) {
 		state->rmid = 0;
-		wrmsrl(MSR_IA32_PQR_ASSOC, 0);
+		wrmsr(MSR_IA32_PQR_ASSOC, 0, state->closid);
 	} else {
 		WARN_ON_ONCE(!state->rmid);
 	}
-
-	raw_spin_unlock_irqrestore(&state->lock, flags);
 }
 
 static int intel_cqm_event_add(struct perf_event *event, int mode)
 {
 	unsigned long flags;
-	unsigned int rmid;
+	u32 rmid;
 
 	raw_spin_lock_irqsave(&cache_lock, flags);
 
@@ -1024,11 +1035,6 @@ static int intel_cqm_event_add(struct perf_event *event, int mode)
 	return 0;
 }
 
-static void intel_cqm_event_del(struct perf_event *event, int mode)
-{
-	intel_cqm_event_stop(event, mode);
-}
-
 static void intel_cqm_event_destroy(struct perf_event *event)
 {
 	struct perf_event *group_other = NULL;
@@ -1057,7 +1063,7 @@ static void intel_cqm_event_destroy(struct perf_event *event)
 			list_replace(&event->hw.cqm_groups_entry,
 				     &group_other->hw.cqm_groups_entry);
 		} else {
-			unsigned int rmid = event->hw.cqm_rmid;
+			u32 rmid = event->hw.cqm_rmid;
 
 			if (__rmid_valid(rmid))
 				__put_rmid(rmid);
@@ -1221,7 +1227,7 @@ static struct pmu intel_cqm_pmu = {
 	.task_ctx_nr	     = perf_sw_context,
 	.event_init	     = intel_cqm_event_init,
 	.add		     = intel_cqm_event_add,
-	.del		     = intel_cqm_event_del,
+	.del		     = intel_cqm_event_stop,
 	.start		     = intel_cqm_event_start,
 	.stop		     = intel_cqm_event_stop,
 	.read		     = intel_cqm_event_read,
@@ -1243,12 +1249,12 @@ static inline void cqm_pick_event_reader(int cpu)
 
 static void intel_cqm_cpu_prepare(unsigned int cpu)
 {
-	struct intel_cqm_state *state = &per_cpu(cqm_state, cpu);
+	struct intel_pqr_state *state = &per_cpu(pqr_state, cpu);
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 
-	raw_spin_lock_init(&state->lock);
 	state->rmid = 0;
-	state->cnt  = 0;
+	state->closid = 0;
+	state->rmid_usecnt = 0;
 
 	WARN_ON(c->x86_cache_max_rmid != cqm_max_rmid);
 	WARN_ON(c->x86_cache_occ_scale != cqm_l3_scale);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 7f73b3553e2e..71fc40238843 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -11,7 +11,7 @@
 #define BTS_RECORD_SIZE		24
 
 #define BTS_BUFFER_SIZE		(PAGE_SIZE << 4)
-#define PEBS_BUFFER_SIZE	PAGE_SIZE
+#define PEBS_BUFFER_SIZE	(PAGE_SIZE << 4)
 #define PEBS_FIXUP_SIZE		PAGE_SIZE
 
 /*
@@ -250,7 +250,7 @@ static int alloc_pebs_buffer(int cpu)
 {
 	struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
 	int node = cpu_to_node(cpu);
-	int max, thresh = 1; /* always use a single PEBS record */
+	int max;
 	void *buffer, *ibuffer;
 
 	if (!x86_pmu.pebs)
@@ -280,9 +280,6 @@ static int alloc_pebs_buffer(int cpu)
 	ds->pebs_absolute_maximum = ds->pebs_buffer_base +
 		max * x86_pmu.pebs_record_size;
 
-	ds->pebs_interrupt_threshold = ds->pebs_buffer_base +
-		thresh * x86_pmu.pebs_record_size;
-
 	return 0;
 }
 
@@ -549,6 +546,19 @@ int intel_pmu_drain_bts_buffer(void)
 	return 1;
 }
 
+static inline void intel_pmu_drain_pebs_buffer(void)
+{
+	struct pt_regs regs;
+
+	x86_pmu.drain_pebs(&regs);
+}
+
+void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in)
+{
+	if (!sched_in)
+		intel_pmu_drain_pebs_buffer();
+}
+
 /*
  * PEBS
  */
@@ -684,25 +694,66 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event)
 	return &emptyconstraint;
 }
 
+static inline bool pebs_is_enabled(struct cpu_hw_events *cpuc)
+{
+	return (cpuc->pebs_enabled & ((1ULL << MAX_PEBS_EVENTS) - 1));
+}
+
 void intel_pmu_pebs_enable(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
+	struct debug_store *ds = cpuc->ds;
+	bool first_pebs;
+	u64 threshold;
 
 	hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT;
 
+	first_pebs = !pebs_is_enabled(cpuc);
 	cpuc->pebs_enabled |= 1ULL << hwc->idx;
 
 	if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT)
 		cpuc->pebs_enabled |= 1ULL << (hwc->idx + 32);
 	else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST)
 		cpuc->pebs_enabled |= 1ULL << 63;
+
+	/*
+	 * When the event is constrained enough we can use a larger
+	 * threshold and run the event with less frequent PMI.
+	 */
+	if (hwc->flags & PERF_X86_EVENT_FREERUNNING) {
+		threshold = ds->pebs_absolute_maximum -
+			x86_pmu.max_pebs_events * x86_pmu.pebs_record_size;
+
+		if (first_pebs)
+			perf_sched_cb_inc(event->ctx->pmu);
+	} else {
+		threshold = ds->pebs_buffer_base + x86_pmu.pebs_record_size;
+
+		/*
+		 * If not all events can use larger buffer,
+		 * roll back to threshold = 1
+		 */
+		if (!first_pebs &&
+		    (ds->pebs_interrupt_threshold > threshold))
+			perf_sched_cb_dec(event->ctx->pmu);
+	}
+
+	/* Use auto-reload if possible to save a MSR write in the PMI */
+	if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) {
+		ds->pebs_event_reset[hwc->idx] =
+			(u64)(-hwc->sample_period) & x86_pmu.cntval_mask;
+	}
+
+	if (first_pebs || ds->pebs_interrupt_threshold > threshold)
+		ds->pebs_interrupt_threshold = threshold;
 }
 
 void intel_pmu_pebs_disable(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
+	struct debug_store *ds = cpuc->ds;
 
 	cpuc->pebs_enabled &= ~(1ULL << hwc->idx);
 
@@ -711,6 +762,13 @@ void intel_pmu_pebs_disable(struct perf_event *event)
 	else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST)
 		cpuc->pebs_enabled &= ~(1ULL << 63);
 
+	if (ds->pebs_interrupt_threshold >
+	    ds->pebs_buffer_base + x86_pmu.pebs_record_size) {
+		intel_pmu_drain_pebs_buffer();
+		if (!pebs_is_enabled(cpuc))
+			perf_sched_cb_dec(event->ctx->pmu);
+	}
+
 	if (cpuc->enabled)
 		wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
 
@@ -846,8 +904,10 @@ static inline u64 intel_hsw_transaction(struct pebs_record_hsw *pebs)
 	return txn;
 }
 
-static void __intel_pmu_pebs_event(struct perf_event *event,
-				   struct pt_regs *iregs, void *__pebs)
+static void setup_pebs_sample_data(struct perf_event *event,
+				   struct pt_regs *iregs, void *__pebs,
+				   struct perf_sample_data *data,
+				   struct pt_regs *regs)
 {
 #define PERF_X86_EVENT_PEBS_HSW_PREC \
 		(PERF_X86_EVENT_PEBS_ST_HSW | \
@@ -859,13 +919,11 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 	 */
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct pebs_record_hsw *pebs = __pebs;
-	struct perf_sample_data data;
-	struct pt_regs regs;
 	u64 sample_type;
 	int fll, fst, dsrc;
 	int fl = event->hw.flags;
 
-	if (!intel_pmu_save_and_restart(event))
+	if (pebs == NULL)
 		return;
 
 	sample_type = event->attr.sample_type;
@@ -874,15 +932,15 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 	fll = fl & PERF_X86_EVENT_PEBS_LDLAT;
 	fst = fl & (PERF_X86_EVENT_PEBS_ST | PERF_X86_EVENT_PEBS_HSW_PREC);
 
-	perf_sample_data_init(&data, 0, event->hw.last_period);
+	perf_sample_data_init(data, 0, event->hw.last_period);
 
-	data.period = event->hw.last_period;
+	data->period = event->hw.last_period;
 
 	/*
 	 * Use latency for weight (only avail with PEBS-LL)
 	 */
 	if (fll && (sample_type & PERF_SAMPLE_WEIGHT))
-		data.weight = pebs->lat;
+		data->weight = pebs->lat;
 
 	/*
 	 * data.data_src encodes the data source
@@ -895,7 +953,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 			val = precise_datala_hsw(event, pebs->dse);
 		else if (fst)
 			val = precise_store_data(pebs->dse);
-		data.data_src.val = val;
+		data->data_src.val = val;
 	}
 
 	/*
@@ -908,61 +966,123 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 	 * PERF_SAMPLE_IP and PERF_SAMPLE_CALLCHAIN to function properly.
 	 * A possible PERF_SAMPLE_REGS will have to transfer all regs.
 	 */
-	regs = *iregs;
-	regs.flags = pebs->flags;
-	set_linear_ip(&regs, pebs->ip);
-	regs.bp = pebs->bp;
-	regs.sp = pebs->sp;
+	*regs = *iregs;
+	regs->flags = pebs->flags;
+	set_linear_ip(regs, pebs->ip);
+	regs->bp = pebs->bp;
+	regs->sp = pebs->sp;
 
 	if (sample_type & PERF_SAMPLE_REGS_INTR) {
-		regs.ax = pebs->ax;
-		regs.bx = pebs->bx;
-		regs.cx = pebs->cx;
-		regs.dx = pebs->dx;
-		regs.si = pebs->si;
-		regs.di = pebs->di;
-		regs.bp = pebs->bp;
-		regs.sp = pebs->sp;
-
-		regs.flags = pebs->flags;
+		regs->ax = pebs->ax;
+		regs->bx = pebs->bx;
+		regs->cx = pebs->cx;
+		regs->dx = pebs->dx;
+		regs->si = pebs->si;
+		regs->di = pebs->di;
+		regs->bp = pebs->bp;
+		regs->sp = pebs->sp;
+
+		regs->flags = pebs->flags;
 #ifndef CONFIG_X86_32
-		regs.r8 = pebs->r8;
-		regs.r9 = pebs->r9;
-		regs.r10 = pebs->r10;
-		regs.r11 = pebs->r11;
-		regs.r12 = pebs->r12;
-		regs.r13 = pebs->r13;
-		regs.r14 = pebs->r14;
-		regs.r15 = pebs->r15;
+		regs->r8 = pebs->r8;
+		regs->r9 = pebs->r9;
+		regs->r10 = pebs->r10;
+		regs->r11 = pebs->r11;
+		regs->r12 = pebs->r12;
+		regs->r13 = pebs->r13;
+		regs->r14 = pebs->r14;
+		regs->r15 = pebs->r15;
 #endif
 	}
 
 	if (event->attr.precise_ip > 1 && x86_pmu.intel_cap.pebs_format >= 2) {
-		regs.ip = pebs->real_ip;
-		regs.flags |= PERF_EFLAGS_EXACT;
-	} else if (event->attr.precise_ip > 1 && intel_pmu_pebs_fixup_ip(&regs))
-		regs.flags |= PERF_EFLAGS_EXACT;
+		regs->ip = pebs->real_ip;
+		regs->flags |= PERF_EFLAGS_EXACT;
+	} else if (event->attr.precise_ip > 1 && intel_pmu_pebs_fixup_ip(regs))
+		regs->flags |= PERF_EFLAGS_EXACT;
 	else
-		regs.flags &= ~PERF_EFLAGS_EXACT;
+		regs->flags &= ~PERF_EFLAGS_EXACT;
 
 	if ((sample_type & PERF_SAMPLE_ADDR) &&
 	    x86_pmu.intel_cap.pebs_format >= 1)
-		data.addr = pebs->dla;
+		data->addr = pebs->dla;
 
 	if (x86_pmu.intel_cap.pebs_format >= 2) {
 		/* Only set the TSX weight when no memory weight. */
 		if ((sample_type & PERF_SAMPLE_WEIGHT) && !fll)
-			data.weight = intel_hsw_weight(pebs);
+			data->weight = intel_hsw_weight(pebs);
 
 		if (sample_type & PERF_SAMPLE_TRANSACTION)
-			data.txn = intel_hsw_transaction(pebs);
+			data->txn = intel_hsw_transaction(pebs);
 	}
 
 	if (has_branch_stack(event))
-		data.br_stack = &cpuc->lbr_stack;
+		data->br_stack = &cpuc->lbr_stack;
+}
+
+static inline void *
+get_next_pebs_record_by_bit(void *base, void *top, int bit)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	void *at;
+	u64 pebs_status;
+
+	if (base == NULL)
+		return NULL;
+
+	for (at = base; at < top; at += x86_pmu.pebs_record_size) {
+		struct pebs_record_nhm *p = at;
+
+		if (test_bit(bit, (unsigned long *)&p->status)) {
+			/* PEBS v3 has accurate status bits */
+			if (x86_pmu.intel_cap.pebs_format >= 3)
+				return at;
 
-	if (perf_event_overflow(event, &data, &regs))
+			if (p->status == (1 << bit))
+				return at;
+
+			/* clear non-PEBS bit and re-check */
+			pebs_status = p->status & cpuc->pebs_enabled;
+			pebs_status &= (1ULL << MAX_PEBS_EVENTS) - 1;
+			if (pebs_status == (1 << bit))
+				return at;
+		}
+	}
+	return NULL;
+}
+
+static void __intel_pmu_pebs_event(struct perf_event *event,
+				   struct pt_regs *iregs,
+				   void *base, void *top,
+				   int bit, int count)
+{
+	struct perf_sample_data data;
+	struct pt_regs regs;
+	void *at = get_next_pebs_record_by_bit(base, top, bit);
+
+	if (!intel_pmu_save_and_restart(event) &&
+	    !(event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD))
+		return;
+
+	while (count > 1) {
+		setup_pebs_sample_data(event, iregs, at, &data, &regs);
+		perf_event_output(event, &data, &regs);
+		at += x86_pmu.pebs_record_size;
+		at = get_next_pebs_record_by_bit(at, top, bit);
+		count--;
+	}
+
+	setup_pebs_sample_data(event, iregs, at, &data, &regs);
+
+	/*
+	 * All but the last records are processed.
+	 * The last one is left to be able to call the overflow handler.
+	 */
+	if (perf_event_overflow(event, &data, &regs)) {
 		x86_pmu_stop(event, 0);
+		return;
+	}
+
 }
 
 static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
@@ -992,72 +1112,99 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
 	if (!event->attr.precise_ip)
 		return;
 
-	n = top - at;
+	n = (top - at) / x86_pmu.pebs_record_size;
 	if (n <= 0)
 		return;
 
-	/*
-	 * Should not happen, we program the threshold at 1 and do not
-	 * set a reset value.
-	 */
-	WARN_ONCE(n > 1, "bad leftover pebs %d\n", n);
-	at += n - 1;
-
-	__intel_pmu_pebs_event(event, iregs, at);
+	__intel_pmu_pebs_event(event, iregs, at, top, 0, n);
 }
 
 static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct debug_store *ds = cpuc->ds;
-	struct perf_event *event = NULL;
-	void *at, *top;
-	u64 status = 0;
-	int bit;
+	struct perf_event *event;
+	void *base, *at, *top;
+	short counts[MAX_PEBS_EVENTS] = {};
+	short error[MAX_PEBS_EVENTS] = {};
+	int bit, i;
 
 	if (!x86_pmu.pebs_active)
 		return;
 
-	at  = (struct pebs_record_nhm *)(unsigned long)ds->pebs_buffer_base;
+	base = (struct pebs_record_nhm *)(unsigned long)ds->pebs_buffer_base;
 	top = (struct pebs_record_nhm *)(unsigned long)ds->pebs_index;
 
 	ds->pebs_index = ds->pebs_buffer_base;
 
-	if (unlikely(at > top))
+	if (unlikely(base >= top))
 		return;
 
-	/*
-	 * Should not happen, we program the threshold at 1 and do not
-	 * set a reset value.
-	 */
-	WARN_ONCE(top - at > x86_pmu.max_pebs_events * x86_pmu.pebs_record_size,
-		  "Unexpected number of pebs records %ld\n",
-		  (long)(top - at) / x86_pmu.pebs_record_size);
-
-	for (; at < top; at += x86_pmu.pebs_record_size) {
+	for (at = base; at < top; at += x86_pmu.pebs_record_size) {
 		struct pebs_record_nhm *p = at;
 
-		for_each_set_bit(bit, (unsigned long *)&p->status,
-				 x86_pmu.max_pebs_events) {
-			event = cpuc->events[bit];
-			if (!test_bit(bit, cpuc->active_mask))
-				continue;
-
-			WARN_ON_ONCE(!event);
+		/* PEBS v3 has accurate status bits */
+		if (x86_pmu.intel_cap.pebs_format >= 3) {
+			for_each_set_bit(bit, (unsigned long *)&p->status,
+					 MAX_PEBS_EVENTS)
+				counts[bit]++;
 
-			if (!event->attr.precise_ip)
-				continue;
+			continue;
+		}
 
-			if (__test_and_set_bit(bit, (unsigned long *)&status))
+		bit = find_first_bit((unsigned long *)&p->status,
+					x86_pmu.max_pebs_events);
+		if (bit >= x86_pmu.max_pebs_events)
+			continue;
+		if (!test_bit(bit, cpuc->active_mask))
+			continue;
+		/*
+		 * The PEBS hardware does not deal well with the situation
+		 * when events happen near to each other and multiple bits
+		 * are set. But it should happen rarely.
+		 *
+		 * If these events include one PEBS and multiple non-PEBS
+		 * events, it doesn't impact PEBS record. The record will
+		 * be handled normally. (slow path)
+		 *
+		 * If these events include two or more PEBS events, the
+		 * records for the events can be collapsed into a single
+		 * one, and it's not possible to reconstruct all events
+		 * that caused the PEBS record. It's called collision.
+		 * If collision happened, the record will be dropped.
+		 *
+		 */
+		if (p->status != (1 << bit)) {
+			u64 pebs_status;
+
+			/* slow path */
+			pebs_status = p->status & cpuc->pebs_enabled;
+			pebs_status &= (1ULL << MAX_PEBS_EVENTS) - 1;
+			if (pebs_status != (1 << bit)) {
+				for_each_set_bit(i, (unsigned long *)&pebs_status,
+						 MAX_PEBS_EVENTS)
+					error[i]++;
 				continue;
-
-			break;
+			}
 		}
+		counts[bit]++;
+	}
 
-		if (!event || bit >= x86_pmu.max_pebs_events)
+	for (bit = 0; bit < x86_pmu.max_pebs_events; bit++) {
+		if ((counts[bit] == 0) && (error[bit] == 0))
 			continue;
+		event = cpuc->events[bit];
+		WARN_ON_ONCE(!event);
+		WARN_ON_ONCE(!event->attr.precise_ip);
 
-		__intel_pmu_pebs_event(event, iregs, at);
+		/* log dropped samples number */
+		if (error[bit])
+			perf_log_lost_samples(event, error[bit]);
+
+		if (counts[bit]) {
+			__intel_pmu_pebs_event(event, iregs, base,
+					       top, bit, counts[bit]);
+		}
 	}
 }
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index 94e5b506caa6..452a7bd2dedb 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -96,6 +96,7 @@ enum {
 	X86_BR_NO_TX		= 1 << 14,/* not in transaction */
 	X86_BR_ZERO_CALL	= 1 << 15,/* zero length call */
 	X86_BR_CALL_STACK	= 1 << 16,/* call stack */
+	X86_BR_IND_JMP		= 1 << 17,/* indirect jump */
 };
 
 #define X86_BR_PLM (X86_BR_USER | X86_BR_KERNEL)
@@ -113,6 +114,7 @@ enum {
 	 X86_BR_IRQ	 |\
 	 X86_BR_ABORT	 |\
 	 X86_BR_IND_CALL |\
+	 X86_BR_IND_JMP  |\
 	 X86_BR_ZERO_CALL)
 
 #define X86_BR_ALL (X86_BR_PLM | X86_BR_ANY)
@@ -262,9 +264,6 @@ void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in)
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct x86_perf_task_context *task_ctx;
 
-	if (!x86_pmu.lbr_nr)
-		return;
-
 	/*
 	 * If LBR callstack feature is enabled and the stack was saved when
 	 * the task was scheduled out, restore the stack. Otherwise flush
@@ -523,6 +522,9 @@ static int intel_pmu_setup_sw_lbr_filter(struct perf_event *event)
 			X86_BR_CALL_STACK;
 	}
 
+	if (br_type & PERF_SAMPLE_BRANCH_IND_JUMP)
+		mask |= X86_BR_IND_JMP;
+
 	/*
 	 * stash actual user request into reg, it may
 	 * be used by fixup code for some CPU
@@ -736,7 +738,7 @@ static int branch_type(unsigned long from, unsigned long to, int abort)
 			break;
 		case 4:
 		case 5:
-			ret = X86_BR_JMP;
+			ret = X86_BR_IND_JMP;
 			break;
 		}
 		break;
@@ -844,6 +846,7 @@ static const int nhm_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = {
 	 */
 	[PERF_SAMPLE_BRANCH_IND_CALL_SHIFT] = LBR_IND_CALL | LBR_IND_JMP,
 	[PERF_SAMPLE_BRANCH_COND_SHIFT]     = LBR_JCC,
+	[PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT] = LBR_IND_JMP,
 };
 
 static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = {
@@ -856,6 +859,7 @@ static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = {
 						| LBR_FAR,
 	[PERF_SAMPLE_BRANCH_IND_CALL_SHIFT]	= LBR_IND_CALL,
 	[PERF_SAMPLE_BRANCH_COND_SHIFT]		= LBR_JCC,
+	[PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT]	= LBR_IND_JMP,
 };
 
 static const int hsw_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = {
@@ -870,6 +874,7 @@ static const int hsw_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = {
 	[PERF_SAMPLE_BRANCH_COND_SHIFT]		= LBR_JCC,
 	[PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT]	= LBR_REL_CALL | LBR_IND_CALL
 						| LBR_RETURN | LBR_CALL_STACK,
+	[PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT]	= LBR_IND_JMP,
 };
 
 /* core */
diff --git a/arch/x86/kernel/cpu/perf_event_intel_pt.c b/arch/x86/kernel/cpu/perf_event_intel_pt.c
index 123ff1bb2f60..159887c3a89d 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_pt.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_pt.c
@@ -187,15 +187,6 @@ static bool pt_event_valid(struct perf_event *event)
  * These all are cpu affine and operate on a local PT
  */
 
-static bool pt_is_running(void)
-{
-	u64 ctl;
-
-	rdmsrl(MSR_IA32_RTIT_CTL, ctl);
-
-	return !!(ctl & RTIT_CTL_TRACEEN);
-}
-
 static void pt_config(struct perf_event *event)
 {
 	u64 reg;
@@ -609,7 +600,12 @@ static unsigned int pt_topa_next_entry(struct pt_buffer *buf, unsigned int pg)
  * @handle:	Current output handle.
  *
  * Place INT and STOP marks to prevent overwriting old data that the consumer
- * hasn't yet collected.
+ * hasn't yet collected and waking up the consumer after a certain fraction of
+ * the buffer has filled up. Only needed and sensible for non-snapshot counters.
+ *
+ * This obviously relies on buf::head to figure out buffer markers, so it has
+ * to be called after pt_buffer_reset_offsets() and before the hardware tracing
+ * is enabled.
  */
 static int pt_buffer_reset_markers(struct pt_buffer *buf,
 				   struct perf_output_handle *handle)
@@ -618,9 +614,6 @@ static int pt_buffer_reset_markers(struct pt_buffer *buf,
 	unsigned long head = local64_read(&buf->head);
 	unsigned long idx, npages, wakeup;
 
-	if (buf->snapshot)
-		return 0;
-
 	/* can't stop in the middle of an output region */
 	if (buf->output_off + handle->size + 1 <
 	    sizes(TOPA_ENTRY(buf->cur, buf->cur_idx)->size))
@@ -674,7 +667,7 @@ static void pt_buffer_setup_topa_index(struct pt_buffer *buf)
 	struct topa *cur = buf->first, *prev = buf->last;
 	struct topa_entry *te_cur = TOPA_ENTRY(cur, 0),
 		*te_prev = TOPA_ENTRY(prev, prev->last - 1);
-	int pg = 0, idx = 0, ntopa = 0;
+	int pg = 0, idx = 0;
 
 	while (pg < buf->nr_pages) {
 		int tidx;
@@ -689,9 +682,9 @@ static void pt_buffer_setup_topa_index(struct pt_buffer *buf)
 			/* advance to next topa table */
 			idx = 0;
 			cur = list_entry(cur->list.next, struct topa, list);
-			ntopa++;
-		} else
+		} else {
 			idx++;
+		}
 		te_cur = TOPA_ENTRY(cur, idx);
 	}
 
@@ -703,7 +696,14 @@ static void pt_buffer_setup_topa_index(struct pt_buffer *buf)
  * @head:	Write pointer (aux_head) from AUX buffer.
  *
  * Find the ToPA table and entry corresponding to given @head and set buffer's
- * "current" pointers accordingly.
+ * "current" pointers accordingly. This is done after we have obtained the
+ * current aux_head position from a successful call to perf_aux_output_begin()
+ * to make sure the hardware is writing to the right place.
+ *
+ * This function modifies buf::{cur,cur_idx,output_off} that will be programmed
+ * into PT msrs when the tracing is enabled and buf::head and buf::data_size,
+ * which are used to determine INT and STOP markers' locations by a subsequent
+ * call to pt_buffer_reset_markers().
  */
 static void pt_buffer_reset_offsets(struct pt_buffer *buf, unsigned long head)
 {
@@ -901,6 +901,7 @@ void intel_pt_interrupt(void)
 		}
 
 		pt_buffer_reset_offsets(buf, pt->handle.head);
+		/* snapshot counters don't use PMI, so it's safe */
 		ret = pt_buffer_reset_markers(buf, &pt->handle);
 		if (ret) {
 			perf_aux_output_end(&pt->handle, 0, true);
@@ -923,7 +924,7 @@ static void pt_event_start(struct perf_event *event, int mode)
 	struct pt *pt = this_cpu_ptr(&pt_ctx);
 	struct pt_buffer *buf = perf_get_aux(&pt->handle);
 
-	if (pt_is_running() || !buf || pt_buffer_is_full(buf, pt)) {
+	if (!buf || pt_buffer_is_full(buf, pt)) {
 		event->hw.state = PERF_HES_STOPPED;
 		return;
 	}
@@ -954,7 +955,6 @@ static void pt_event_stop(struct perf_event *event, int mode)
 	event->hw.state = PERF_HES_STOPPED;
 
 	if (mode & PERF_EF_UPDATE) {
-		struct pt *pt = this_cpu_ptr(&pt_ctx);
 		struct pt_buffer *buf = perf_get_aux(&pt->handle);
 
 		if (!buf)
diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
index 358c54ad20d4..5cbd4e64feb5 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
@@ -204,9 +204,8 @@ again:
 
 static void rapl_start_hrtimer(struct rapl_pmu *pmu)
 {
-	__hrtimer_start_range_ns(&pmu->hrtimer,
-			pmu->timer_interval, 0,
-			HRTIMER_MODE_REL_PINNED, 0);
+       hrtimer_start(&pmu->hrtimer, pmu->timer_interval,
+		     HRTIMER_MODE_REL_PINNED);
 }
 
 static void rapl_stop_hrtimer(struct rapl_pmu *pmu)
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 90b7c501c95b..21b5e38c921b 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -233,9 +233,8 @@ static enum hrtimer_restart uncore_pmu_hrtimer(struct hrtimer *hrtimer)
 
 void uncore_pmu_start_hrtimer(struct intel_uncore_box *box)
 {
-	__hrtimer_start_range_ns(&box->hrtimer,
-			ns_to_ktime(box->hrtimer_duration), 0,
-			HRTIMER_MODE_REL_PINNED, 0);
+	hrtimer_start(&box->hrtimer, ns_to_ktime(box->hrtimer_duration),
+		      HRTIMER_MODE_REL_PINNED);
 }
 
 void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box)
@@ -922,6 +921,9 @@ static int __init uncore_pci_init(void)
 	case 69: /* Haswell Celeron */
 		ret = hsw_uncore_pci_init();
 		break;
+	case 61: /* Broadwell */
+		ret = bdw_uncore_pci_init();
+		break;
 	default:
 		return 0;
 	}
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
index ceac8f5dc018..0f77f0a196e4 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
@@ -325,6 +325,7 @@ extern struct event_constraint uncore_constraint_empty;
 int snb_uncore_pci_init(void);
 int ivb_uncore_pci_init(void);
 int hsw_uncore_pci_init(void);
+int bdw_uncore_pci_init(void);
 void snb_uncore_cpu_init(void);
 void nhm_uncore_cpu_init(void);
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
index 4562e9e22c60..b005a78c7012 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
@@ -7,6 +7,7 @@
 #define PCI_DEVICE_ID_INTEL_IVB_E3_IMC	0x0150
 #define PCI_DEVICE_ID_INTEL_HSW_IMC	0x0c00
 #define PCI_DEVICE_ID_INTEL_HSW_U_IMC	0x0a04
+#define PCI_DEVICE_ID_INTEL_BDW_IMC	0x1604
 
 /* SNB event control */
 #define SNB_UNC_CTL_EV_SEL_MASK			0x000000ff
@@ -486,6 +487,14 @@ static const struct pci_device_id hsw_uncore_pci_ids[] = {
 	{ /* end: all zeroes */ },
 };
 
+static const struct pci_device_id bdw_uncore_pci_ids[] = {
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BDW_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* end: all zeroes */ },
+};
+
 static struct pci_driver snb_uncore_pci_driver = {
 	.name		= "snb_uncore",
 	.id_table	= snb_uncore_pci_ids,
@@ -501,6 +510,11 @@ static struct pci_driver hsw_uncore_pci_driver = {
 	.id_table	= hsw_uncore_pci_ids,
 };
 
+static struct pci_driver bdw_uncore_pci_driver = {
+	.name		= "bdw_uncore",
+	.id_table	= bdw_uncore_pci_ids,
+};
+
 struct imc_uncore_pci_dev {
 	__u32 pci_id;
 	struct pci_driver *driver;
@@ -514,6 +528,7 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = {
 	IMC_DEV(IVB_E3_IMC, &ivb_uncore_pci_driver), /* Xeon E3-1200 v2/3rd Gen Core processor */
 	IMC_DEV(HSW_IMC, &hsw_uncore_pci_driver),    /* 4th Gen Core Processor */
 	IMC_DEV(HSW_U_IMC, &hsw_uncore_pci_driver),  /* 4th Gen Core ULT Mobile Processor */
+	IMC_DEV(BDW_IMC, &bdw_uncore_pci_driver),    /* 5th Gen Core U */
 	{  /* end marker */ }
 };
 
@@ -561,6 +576,11 @@ int hsw_uncore_pci_init(void)
 	return imc_uncore_pci_init();
 }
 
+int bdw_uncore_pci_init(void)
+{
+	return imc_uncore_pci_init();
+}
+
 /* end of Sandy Bridge uncore support */
 
 /* Nehalem uncore support */
diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c
index e7d8c7608471..18ca99f2798b 100644
--- a/arch/x86/kernel/cpu/proc.c
+++ b/arch/x86/kernel/cpu/proc.c
@@ -12,7 +12,8 @@ static void show_cpuinfo_core(struct seq_file *m, struct cpuinfo_x86 *c,
 {
 #ifdef CONFIG_SMP
 	seq_printf(m, "physical id\t: %d\n", c->phys_proc_id);
-	seq_printf(m, "siblings\t: %d\n", cpumask_weight(cpu_core_mask(cpu)));
+	seq_printf(m, "siblings\t: %d\n",
+		   cpumask_weight(topology_core_cpumask(cpu)));
 	seq_printf(m, "core id\t\t: %d\n", c->cpu_core_id);
 	seq_printf(m, "cpu cores\t: %d\n", c->booted_cores);
 	seq_printf(m, "apicid\t\t: %d\n", c->apicid);
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index c76d3e37c6e1..e068d6683dba 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -22,6 +22,7 @@
 #include <linux/elfcore.h>
 #include <linux/module.h>
 #include <linux/slab.h>
+#include <linux/vmalloc.h>
 
 #include <asm/processor.h>
 #include <asm/hardirq.h>
diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
index 6367a780cc8c..5ee771859b6f 100644
--- a/arch/x86/kernel/devicetree.c
+++ b/arch/x86/kernel/devicetree.c
@@ -4,7 +4,6 @@
 #include <linux/bootmem.h>
 #include <linux/export.h>
 #include <linux/io.h>
-#include <linux/irqdomain.h>
 #include <linux/interrupt.h>
 #include <linux/list.h>
 #include <linux/of.h>
@@ -17,6 +16,7 @@
 #include <linux/of_pci.h>
 #include <linux/initrd.h>
 
+#include <asm/irqdomain.h>
 #include <asm/hpet.h>
 #include <asm/apic.h>
 #include <asm/pci_x86.h>
@@ -196,38 +196,31 @@ static struct of_ioapic_type of_ioapic_type[] =
 	},
 };
 
-static int ioapic_xlate(struct irq_domain *domain,
-			struct device_node *controller,
-			const u32 *intspec, u32 intsize,
-			irq_hw_number_t *out_hwirq, u32 *out_type)
+static int dt_irqdomain_alloc(struct irq_domain *domain, unsigned int virq,
+			      unsigned int nr_irqs, void *arg)
 {
+	struct of_phandle_args *irq_data = (void *)arg;
 	struct of_ioapic_type *it;
-	u32 line, idx, gsi;
+	struct irq_alloc_info tmp;
 
-	if (WARN_ON(intsize < 2))
+	if (WARN_ON(irq_data->args_count < 2))
 		return -EINVAL;
-
-	line = intspec[0];
-
-	if (intspec[1] >= ARRAY_SIZE(of_ioapic_type))
+	if (irq_data->args[1] >= ARRAY_SIZE(of_ioapic_type))
 		return -EINVAL;
 
-	it = &of_ioapic_type[intspec[1]];
+	it = &of_ioapic_type[irq_data->args[1]];
+	ioapic_set_alloc_attr(&tmp, NUMA_NO_NODE, it->trigger, it->polarity);
+	tmp.ioapic_id = mpc_ioapic_id(mp_irqdomain_ioapic_idx(domain));
+	tmp.ioapic_pin = irq_data->args[0];
 
-	idx = (u32)(long)domain->host_data;
-	gsi = mp_pin_to_gsi(idx, line);
-	if (mp_set_gsi_attr(gsi, it->trigger, it->polarity, cpu_to_node(0)))
-		return -EBUSY;
-
-	*out_hwirq = line;
-	*out_type = it->out_type;
-	return 0;
+	return mp_irqdomain_alloc(domain, virq, nr_irqs, &tmp);
 }
 
-const struct irq_domain_ops ioapic_irq_domain_ops = {
-	.map = mp_irqdomain_map,
-	.unmap = mp_irqdomain_unmap,
-	.xlate = ioapic_xlate,
+static const struct irq_domain_ops ioapic_irq_domain_ops = {
+	.alloc		= dt_irqdomain_alloc,
+	.free		= mp_irqdomain_free,
+	.activate	= mp_irqdomain_activate,
+	.deactivate	= mp_irqdomain_deactivate,
 };
 
 static void __init dtb_add_ioapic(struct device_node *dn)
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index fe9f0b79a18b..5cb9a4d6f623 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -627,8 +627,12 @@ static struct chipset early_qrk[] __initdata = {
 	{ PCI_VENDOR_ID_INTEL, PCI_ANY_ID, PCI_CLASS_DISPLAY_VGA, PCI_ANY_ID,
 	  QFLAG_APPLY_ONCE, intel_graphics_stolen },
 	/*
-	 * HPET on current version of Baytrail platform has accuracy
-	 * problems, disable it for now:
+	 * HPET on the current version of the Baytrail platform has accuracy
+	 * problems: it will halt in deep idle state - so we disable it.
+	 *
+	 * More details can be found in section 18.10.1.3 of the datasheet:
+	 *
+	 *    http://www.intel.com/content/dam/www/public/us/en/documents/datasheets/atom-z8000-datasheet-vol-1.pdf
 	 */
 	{ PCI_VENDOR_ID_INTEL, 0x0f00,
 		PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet},
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
deleted file mode 100644
index 1c309763e321..000000000000
--- a/arch/x86/kernel/entry_32.S
+++ /dev/null
@@ -1,1401 +0,0 @@
-/*
- *
- *  Copyright (C) 1991, 1992  Linus Torvalds
- */
-
-/*
- * entry.S contains the system-call and fault low-level handling routines.
- * This also contains the timer-interrupt handler, as well as all interrupts
- * and faults that can result in a task-switch.
- *
- * NOTE: This code handles signal-recognition, which happens every time
- * after a timer-interrupt and after each system call.
- *
- * I changed all the .align's to 4 (16 byte alignment), as that's faster
- * on a 486.
- *
- * Stack layout in 'syscall_exit':
- * 	ptrace needs to have all regs on the stack.
- *	if the order here is changed, it needs to be
- *	updated in fork.c:copy_process, signal.c:do_signal,
- *	ptrace.c and ptrace.h
- *
- *	 0(%esp) - %ebx
- *	 4(%esp) - %ecx
- *	 8(%esp) - %edx
- *       C(%esp) - %esi
- *	10(%esp) - %edi
- *	14(%esp) - %ebp
- *	18(%esp) - %eax
- *	1C(%esp) - %ds
- *	20(%esp) - %es
- *	24(%esp) - %fs
- *	28(%esp) - %gs		saved iff !CONFIG_X86_32_LAZY_GS
- *	2C(%esp) - orig_eax
- *	30(%esp) - %eip
- *	34(%esp) - %cs
- *	38(%esp) - %eflags
- *	3C(%esp) - %oldesp
- *	40(%esp) - %oldss
- *
- * "current" is in register %ebx during any slow entries.
- */
-
-#include <linux/linkage.h>
-#include <linux/err.h>
-#include <asm/thread_info.h>
-#include <asm/irqflags.h>
-#include <asm/errno.h>
-#include <asm/segment.h>
-#include <asm/smp.h>
-#include <asm/page_types.h>
-#include <asm/percpu.h>
-#include <asm/dwarf2.h>
-#include <asm/processor-flags.h>
-#include <asm/ftrace.h>
-#include <asm/irq_vectors.h>
-#include <asm/cpufeature.h>
-#include <asm/alternative-asm.h>
-#include <asm/asm.h>
-#include <asm/smap.h>
-
-/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this.  */
-#include <linux/elf-em.h>
-#define AUDIT_ARCH_I386		(EM_386|__AUDIT_ARCH_LE)
-#define __AUDIT_ARCH_LE	   0x40000000
-
-#ifndef CONFIG_AUDITSYSCALL
-#define sysenter_audit	syscall_trace_entry
-#define sysexit_audit	syscall_exit_work
-#endif
-
-	.section .entry.text, "ax"
-
-/*
- * We use macros for low-level operations which need to be overridden
- * for paravirtualization.  The following will never clobber any registers:
- *   INTERRUPT_RETURN (aka. "iret")
- *   GET_CR0_INTO_EAX (aka. "movl %cr0, %eax")
- *   ENABLE_INTERRUPTS_SYSEXIT (aka "sti; sysexit").
- *
- * For DISABLE_INTERRUPTS/ENABLE_INTERRUPTS (aka "cli"/"sti"), you must
- * specify what registers can be overwritten (CLBR_NONE, CLBR_EAX/EDX/ECX/ANY).
- * Allowing a register to be clobbered can shrink the paravirt replacement
- * enough to patch inline, increasing performance.
- */
-
-#ifdef CONFIG_PREEMPT
-#define preempt_stop(clobbers)	DISABLE_INTERRUPTS(clobbers); TRACE_IRQS_OFF
-#else
-#define preempt_stop(clobbers)
-#define resume_kernel		restore_all
-#endif
-
-.macro TRACE_IRQS_IRET
-#ifdef CONFIG_TRACE_IRQFLAGS
-	testl $X86_EFLAGS_IF,PT_EFLAGS(%esp)     # interrupts off?
-	jz 1f
-	TRACE_IRQS_ON
-1:
-#endif
-.endm
-
-/*
- * User gs save/restore
- *
- * %gs is used for userland TLS and kernel only uses it for stack
- * canary which is required to be at %gs:20 by gcc.  Read the comment
- * at the top of stackprotector.h for more info.
- *
- * Local labels 98 and 99 are used.
- */
-#ifdef CONFIG_X86_32_LAZY_GS
-
- /* unfortunately push/pop can't be no-op */
-.macro PUSH_GS
-	pushl_cfi $0
-.endm
-.macro POP_GS pop=0
-	addl $(4 + \pop), %esp
-	CFI_ADJUST_CFA_OFFSET -(4 + \pop)
-.endm
-.macro POP_GS_EX
-.endm
-
- /* all the rest are no-op */
-.macro PTGS_TO_GS
-.endm
-.macro PTGS_TO_GS_EX
-.endm
-.macro GS_TO_REG reg
-.endm
-.macro REG_TO_PTGS reg
-.endm
-.macro SET_KERNEL_GS reg
-.endm
-
-#else	/* CONFIG_X86_32_LAZY_GS */
-
-.macro PUSH_GS
-	pushl_cfi %gs
-	/*CFI_REL_OFFSET gs, 0*/
-.endm
-
-.macro POP_GS pop=0
-98:	popl_cfi %gs
-	/*CFI_RESTORE gs*/
-  .if \pop <> 0
-	add $\pop, %esp
-	CFI_ADJUST_CFA_OFFSET -\pop
-  .endif
-.endm
-.macro POP_GS_EX
-.pushsection .fixup, "ax"
-99:	movl $0, (%esp)
-	jmp 98b
-.popsection
-	_ASM_EXTABLE(98b,99b)
-.endm
-
-.macro PTGS_TO_GS
-98:	mov PT_GS(%esp), %gs
-.endm
-.macro PTGS_TO_GS_EX
-.pushsection .fixup, "ax"
-99:	movl $0, PT_GS(%esp)
-	jmp 98b
-.popsection
-	_ASM_EXTABLE(98b,99b)
-.endm
-
-.macro GS_TO_REG reg
-	movl %gs, \reg
-	/*CFI_REGISTER gs, \reg*/
-.endm
-.macro REG_TO_PTGS reg
-	movl \reg, PT_GS(%esp)
-	/*CFI_REL_OFFSET gs, PT_GS*/
-.endm
-.macro SET_KERNEL_GS reg
-	movl $(__KERNEL_STACK_CANARY), \reg
-	movl \reg, %gs
-.endm
-
-#endif	/* CONFIG_X86_32_LAZY_GS */
-
-.macro SAVE_ALL
-	cld
-	PUSH_GS
-	pushl_cfi %fs
-	/*CFI_REL_OFFSET fs, 0;*/
-	pushl_cfi %es
-	/*CFI_REL_OFFSET es, 0;*/
-	pushl_cfi %ds
-	/*CFI_REL_OFFSET ds, 0;*/
-	pushl_cfi %eax
-	CFI_REL_OFFSET eax, 0
-	pushl_cfi %ebp
-	CFI_REL_OFFSET ebp, 0
-	pushl_cfi %edi
-	CFI_REL_OFFSET edi, 0
-	pushl_cfi %esi
-	CFI_REL_OFFSET esi, 0
-	pushl_cfi %edx
-	CFI_REL_OFFSET edx, 0
-	pushl_cfi %ecx
-	CFI_REL_OFFSET ecx, 0
-	pushl_cfi %ebx
-	CFI_REL_OFFSET ebx, 0
-	movl $(__USER_DS), %edx
-	movl %edx, %ds
-	movl %edx, %es
-	movl $(__KERNEL_PERCPU), %edx
-	movl %edx, %fs
-	SET_KERNEL_GS %edx
-.endm
-
-.macro RESTORE_INT_REGS
-	popl_cfi %ebx
-	CFI_RESTORE ebx
-	popl_cfi %ecx
-	CFI_RESTORE ecx
-	popl_cfi %edx
-	CFI_RESTORE edx
-	popl_cfi %esi
-	CFI_RESTORE esi
-	popl_cfi %edi
-	CFI_RESTORE edi
-	popl_cfi %ebp
-	CFI_RESTORE ebp
-	popl_cfi %eax
-	CFI_RESTORE eax
-.endm
-
-.macro RESTORE_REGS pop=0
-	RESTORE_INT_REGS
-1:	popl_cfi %ds
-	/*CFI_RESTORE ds;*/
-2:	popl_cfi %es
-	/*CFI_RESTORE es;*/
-3:	popl_cfi %fs
-	/*CFI_RESTORE fs;*/
-	POP_GS \pop
-.pushsection .fixup, "ax"
-4:	movl $0, (%esp)
-	jmp 1b
-5:	movl $0, (%esp)
-	jmp 2b
-6:	movl $0, (%esp)
-	jmp 3b
-.popsection
-	_ASM_EXTABLE(1b,4b)
-	_ASM_EXTABLE(2b,5b)
-	_ASM_EXTABLE(3b,6b)
-	POP_GS_EX
-.endm
-
-.macro RING0_INT_FRAME
-	CFI_STARTPROC simple
-	CFI_SIGNAL_FRAME
-	CFI_DEF_CFA esp, 3*4
-	/*CFI_OFFSET cs, -2*4;*/
-	CFI_OFFSET eip, -3*4
-.endm
-
-.macro RING0_EC_FRAME
-	CFI_STARTPROC simple
-	CFI_SIGNAL_FRAME
-	CFI_DEF_CFA esp, 4*4
-	/*CFI_OFFSET cs, -2*4;*/
-	CFI_OFFSET eip, -3*4
-.endm
-
-.macro RING0_PTREGS_FRAME
-	CFI_STARTPROC simple
-	CFI_SIGNAL_FRAME
-	CFI_DEF_CFA esp, PT_OLDESP-PT_EBX
-	/*CFI_OFFSET cs, PT_CS-PT_OLDESP;*/
-	CFI_OFFSET eip, PT_EIP-PT_OLDESP
-	/*CFI_OFFSET es, PT_ES-PT_OLDESP;*/
-	/*CFI_OFFSET ds, PT_DS-PT_OLDESP;*/
-	CFI_OFFSET eax, PT_EAX-PT_OLDESP
-	CFI_OFFSET ebp, PT_EBP-PT_OLDESP
-	CFI_OFFSET edi, PT_EDI-PT_OLDESP
-	CFI_OFFSET esi, PT_ESI-PT_OLDESP
-	CFI_OFFSET edx, PT_EDX-PT_OLDESP
-	CFI_OFFSET ecx, PT_ECX-PT_OLDESP
-	CFI_OFFSET ebx, PT_EBX-PT_OLDESP
-.endm
-
-ENTRY(ret_from_fork)
-	CFI_STARTPROC
-	pushl_cfi %eax
-	call schedule_tail
-	GET_THREAD_INFO(%ebp)
-	popl_cfi %eax
-	pushl_cfi $0x0202		# Reset kernel eflags
-	popfl_cfi
-	jmp syscall_exit
-	CFI_ENDPROC
-END(ret_from_fork)
-
-ENTRY(ret_from_kernel_thread)
-	CFI_STARTPROC
-	pushl_cfi %eax
-	call schedule_tail
-	GET_THREAD_INFO(%ebp)
-	popl_cfi %eax
-	pushl_cfi $0x0202		# Reset kernel eflags
-	popfl_cfi
-	movl PT_EBP(%esp),%eax
-	call *PT_EBX(%esp)
-	movl $0,PT_EAX(%esp)
-	jmp syscall_exit
-	CFI_ENDPROC
-ENDPROC(ret_from_kernel_thread)
-
-/*
- * Return to user mode is not as complex as all this looks,
- * but we want the default path for a system call return to
- * go as quickly as possible which is why some of this is
- * less clear than it otherwise should be.
- */
-
-	# userspace resumption stub bypassing syscall exit tracing
-	ALIGN
-	RING0_PTREGS_FRAME
-ret_from_exception:
-	preempt_stop(CLBR_ANY)
-ret_from_intr:
-	GET_THREAD_INFO(%ebp)
-#ifdef CONFIG_VM86
-	movl PT_EFLAGS(%esp), %eax	# mix EFLAGS and CS
-	movb PT_CS(%esp), %al
-	andl $(X86_EFLAGS_VM | SEGMENT_RPL_MASK), %eax
-#else
-	/*
-	 * We can be coming here from child spawned by kernel_thread().
-	 */
-	movl PT_CS(%esp), %eax
-	andl $SEGMENT_RPL_MASK, %eax
-#endif
-	cmpl $USER_RPL, %eax
-	jb resume_kernel		# not returning to v8086 or userspace
-
-ENTRY(resume_userspace)
-	LOCKDEP_SYS_EXIT
- 	DISABLE_INTERRUPTS(CLBR_ANY)	# make sure we don't miss an interrupt
-					# setting need_resched or sigpending
-					# between sampling and the iret
-	TRACE_IRQS_OFF
-	movl TI_flags(%ebp), %ecx
-	andl $_TIF_WORK_MASK, %ecx	# is there any work to be done on
-					# int/exception return?
-	jne work_pending
-	jmp restore_all
-END(ret_from_exception)
-
-#ifdef CONFIG_PREEMPT
-ENTRY(resume_kernel)
-	DISABLE_INTERRUPTS(CLBR_ANY)
-need_resched:
-	cmpl $0,PER_CPU_VAR(__preempt_count)
-	jnz restore_all
-	testl $X86_EFLAGS_IF,PT_EFLAGS(%esp)	# interrupts off (exception path) ?
-	jz restore_all
-	call preempt_schedule_irq
-	jmp need_resched
-END(resume_kernel)
-#endif
-	CFI_ENDPROC
-
-/* SYSENTER_RETURN points to after the "sysenter" instruction in
-   the vsyscall page.  See vsyscall-sysentry.S, which defines the symbol.  */
-
-	# sysenter call handler stub
-ENTRY(ia32_sysenter_target)
-	CFI_STARTPROC simple
-	CFI_SIGNAL_FRAME
-	CFI_DEF_CFA esp, 0
-	CFI_REGISTER esp, ebp
-	movl TSS_sysenter_sp0(%esp),%esp
-sysenter_past_esp:
-	/*
-	 * Interrupts are disabled here, but we can't trace it until
-	 * enough kernel state to call TRACE_IRQS_OFF can be called - but
-	 * we immediately enable interrupts at that point anyway.
-	 */
-	pushl_cfi $__USER_DS
-	/*CFI_REL_OFFSET ss, 0*/
-	pushl_cfi %ebp
-	CFI_REL_OFFSET esp, 0
-	pushfl_cfi
-	orl $X86_EFLAGS_IF, (%esp)
-	pushl_cfi $__USER_CS
-	/*CFI_REL_OFFSET cs, 0*/
-	/*
-	 * Push current_thread_info()->sysenter_return to the stack.
-	 * A tiny bit of offset fixup is necessary: TI_sysenter_return
-	 * is relative to thread_info, which is at the bottom of the
-	 * kernel stack page.  4*4 means the 4 words pushed above;
-	 * TOP_OF_KERNEL_STACK_PADDING takes us to the top of the stack;
-	 * and THREAD_SIZE takes us to the bottom.
-	 */
-	pushl_cfi ((TI_sysenter_return) - THREAD_SIZE + TOP_OF_KERNEL_STACK_PADDING + 4*4)(%esp)
-	CFI_REL_OFFSET eip, 0
-
-	pushl_cfi %eax
-	SAVE_ALL
-	ENABLE_INTERRUPTS(CLBR_NONE)
-
-/*
- * Load the potential sixth argument from user stack.
- * Careful about security.
- */
-	cmpl $__PAGE_OFFSET-3,%ebp
-	jae syscall_fault
-	ASM_STAC
-1:	movl (%ebp),%ebp
-	ASM_CLAC
-	movl %ebp,PT_EBP(%esp)
-	_ASM_EXTABLE(1b,syscall_fault)
-
-	GET_THREAD_INFO(%ebp)
-
-	testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%ebp)
-	jnz sysenter_audit
-sysenter_do_call:
-	cmpl $(NR_syscalls), %eax
-	jae sysenter_badsys
-	call *sys_call_table(,%eax,4)
-sysenter_after_call:
-	movl %eax,PT_EAX(%esp)
-	LOCKDEP_SYS_EXIT
-	DISABLE_INTERRUPTS(CLBR_ANY)
-	TRACE_IRQS_OFF
-	movl TI_flags(%ebp), %ecx
-	testl $_TIF_ALLWORK_MASK, %ecx
-	jnz sysexit_audit
-sysenter_exit:
-/* if something modifies registers it must also disable sysexit */
-	movl PT_EIP(%esp), %edx
-	movl PT_OLDESP(%esp), %ecx
-	xorl %ebp,%ebp
-	TRACE_IRQS_ON
-1:	mov  PT_FS(%esp), %fs
-	PTGS_TO_GS
-	ENABLE_INTERRUPTS_SYSEXIT
-
-#ifdef CONFIG_AUDITSYSCALL
-sysenter_audit:
-	testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags(%ebp)
-	jnz syscall_trace_entry
-	/* movl PT_EAX(%esp), %eax	already set, syscall number: 1st arg to audit */
-	movl PT_EBX(%esp), %edx		/* ebx/a0: 2nd arg to audit */
-	/* movl PT_ECX(%esp), %ecx	already set, a1: 3nd arg to audit */
-	pushl_cfi PT_ESI(%esp)		/* a3: 5th arg */
-	pushl_cfi PT_EDX+4(%esp)	/* a2: 4th arg */
-	call __audit_syscall_entry
-	popl_cfi %ecx /* get that remapped edx off the stack */
-	popl_cfi %ecx /* get that remapped esi off the stack */
-	movl PT_EAX(%esp),%eax		/* reload syscall number */
-	jmp sysenter_do_call
-
-sysexit_audit:
-	testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %ecx
-	jnz syscall_exit_work
-	TRACE_IRQS_ON
-	ENABLE_INTERRUPTS(CLBR_ANY)
-	movl %eax,%edx		/* second arg, syscall return value */
-	cmpl $-MAX_ERRNO,%eax	/* is it an error ? */
-	setbe %al		/* 1 if so, 0 if not */
-	movzbl %al,%eax		/* zero-extend that */
-	call __audit_syscall_exit
-	DISABLE_INTERRUPTS(CLBR_ANY)
-	TRACE_IRQS_OFF
-	movl TI_flags(%ebp), %ecx
-	testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %ecx
-	jnz syscall_exit_work
-	movl PT_EAX(%esp),%eax	/* reload syscall return value */
-	jmp sysenter_exit
-#endif
-
-	CFI_ENDPROC
-.pushsection .fixup,"ax"
-2:	movl $0,PT_FS(%esp)
-	jmp 1b
-.popsection
-	_ASM_EXTABLE(1b,2b)
-	PTGS_TO_GS_EX
-ENDPROC(ia32_sysenter_target)
-
-	# system call handler stub
-ENTRY(system_call)
-	RING0_INT_FRAME			# can't unwind into user space anyway
-	ASM_CLAC
-	pushl_cfi %eax			# save orig_eax
-	SAVE_ALL
-	GET_THREAD_INFO(%ebp)
-					# system call tracing in operation / emulation
-	testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%ebp)
-	jnz syscall_trace_entry
-	cmpl $(NR_syscalls), %eax
-	jae syscall_badsys
-syscall_call:
-	call *sys_call_table(,%eax,4)
-syscall_after_call:
-	movl %eax,PT_EAX(%esp)		# store the return value
-syscall_exit:
-	LOCKDEP_SYS_EXIT
-	DISABLE_INTERRUPTS(CLBR_ANY)	# make sure we don't miss an interrupt
-					# setting need_resched or sigpending
-					# between sampling and the iret
-	TRACE_IRQS_OFF
-	movl TI_flags(%ebp), %ecx
-	testl $_TIF_ALLWORK_MASK, %ecx	# current->work
-	jnz syscall_exit_work
-
-restore_all:
-	TRACE_IRQS_IRET
-restore_all_notrace:
-#ifdef CONFIG_X86_ESPFIX32
-	movl PT_EFLAGS(%esp), %eax	# mix EFLAGS, SS and CS
-	# Warning: PT_OLDSS(%esp) contains the wrong/random values if we
-	# are returning to the kernel.
-	# See comments in process.c:copy_thread() for details.
-	movb PT_OLDSS(%esp), %ah
-	movb PT_CS(%esp), %al
-	andl $(X86_EFLAGS_VM | (SEGMENT_TI_MASK << 8) | SEGMENT_RPL_MASK), %eax
-	cmpl $((SEGMENT_LDT << 8) | USER_RPL), %eax
-	CFI_REMEMBER_STATE
-	je ldt_ss			# returning to user-space with LDT SS
-#endif
-restore_nocheck:
-	RESTORE_REGS 4			# skip orig_eax/error_code
-irq_return:
-	INTERRUPT_RETURN
-.section .fixup,"ax"
-ENTRY(iret_exc)
-	pushl $0			# no error code
-	pushl $do_iret_error
-	jmp error_code
-.previous
-	_ASM_EXTABLE(irq_return,iret_exc)
-
-#ifdef CONFIG_X86_ESPFIX32
-	CFI_RESTORE_STATE
-ldt_ss:
-#ifdef CONFIG_PARAVIRT
-	/*
-	 * The kernel can't run on a non-flat stack if paravirt mode
-	 * is active.  Rather than try to fixup the high bits of
-	 * ESP, bypass this code entirely.  This may break DOSemu
-	 * and/or Wine support in a paravirt VM, although the option
-	 * is still available to implement the setting of the high
-	 * 16-bits in the INTERRUPT_RETURN paravirt-op.
-	 */
-	cmpl $0, pv_info+PARAVIRT_enabled
-	jne restore_nocheck
-#endif
-
-/*
- * Setup and switch to ESPFIX stack
- *
- * We're returning to userspace with a 16 bit stack. The CPU will not
- * restore the high word of ESP for us on executing iret... This is an
- * "official" bug of all the x86-compatible CPUs, which we can work
- * around to make dosemu and wine happy. We do this by preloading the
- * high word of ESP with the high word of the userspace ESP while
- * compensating for the offset by changing to the ESPFIX segment with
- * a base address that matches for the difference.
- */
-#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page) + (GDT_ENTRY_ESPFIX_SS * 8)
-	mov %esp, %edx			/* load kernel esp */
-	mov PT_OLDESP(%esp), %eax	/* load userspace esp */
-	mov %dx, %ax			/* eax: new kernel esp */
-	sub %eax, %edx			/* offset (low word is 0) */
-	shr $16, %edx
-	mov %dl, GDT_ESPFIX_SS + 4 /* bits 16..23 */
-	mov %dh, GDT_ESPFIX_SS + 7 /* bits 24..31 */
-	pushl_cfi $__ESPFIX_SS
-	pushl_cfi %eax			/* new kernel esp */
-	/* Disable interrupts, but do not irqtrace this section: we
-	 * will soon execute iret and the tracer was already set to
-	 * the irqstate after the iret */
-	DISABLE_INTERRUPTS(CLBR_EAX)
-	lss (%esp), %esp		/* switch to espfix segment */
-	CFI_ADJUST_CFA_OFFSET -8
-	jmp restore_nocheck
-#endif
-	CFI_ENDPROC
-ENDPROC(system_call)
-
-	# perform work that needs to be done immediately before resumption
-	ALIGN
-	RING0_PTREGS_FRAME		# can't unwind into user space anyway
-work_pending:
-	testb $_TIF_NEED_RESCHED, %cl
-	jz work_notifysig
-work_resched:
-	call schedule
-	LOCKDEP_SYS_EXIT
-	DISABLE_INTERRUPTS(CLBR_ANY)	# make sure we don't miss an interrupt
-					# setting need_resched or sigpending
-					# between sampling and the iret
-	TRACE_IRQS_OFF
-	movl TI_flags(%ebp), %ecx
-	andl $_TIF_WORK_MASK, %ecx	# is there any work to be done other
-					# than syscall tracing?
-	jz restore_all
-	testb $_TIF_NEED_RESCHED, %cl
-	jnz work_resched
-
-work_notifysig:				# deal with pending signals and
-					# notify-resume requests
-#ifdef CONFIG_VM86
-	testl $X86_EFLAGS_VM, PT_EFLAGS(%esp)
-	movl %esp, %eax
-	jnz work_notifysig_v86		# returning to kernel-space or
-					# vm86-space
-1:
-#else
-	movl %esp, %eax
-#endif
-	TRACE_IRQS_ON
-	ENABLE_INTERRUPTS(CLBR_NONE)
-	movb PT_CS(%esp), %bl
-	andb $SEGMENT_RPL_MASK, %bl
-	cmpb $USER_RPL, %bl
-	jb resume_kernel
-	xorl %edx, %edx
-	call do_notify_resume
-	jmp resume_userspace
-
-#ifdef CONFIG_VM86
-	ALIGN
-work_notifysig_v86:
-	pushl_cfi %ecx			# save ti_flags for do_notify_resume
-	call save_v86_state		# %eax contains pt_regs pointer
-	popl_cfi %ecx
-	movl %eax, %esp
-	jmp 1b
-#endif
-END(work_pending)
-
-	# perform syscall exit tracing
-	ALIGN
-syscall_trace_entry:
-	movl $-ENOSYS,PT_EAX(%esp)
-	movl %esp, %eax
-	call syscall_trace_enter
-	/* What it returned is what we'll actually use.  */
-	cmpl $(NR_syscalls), %eax
-	jnae syscall_call
-	jmp syscall_exit
-END(syscall_trace_entry)
-
-	# perform syscall exit tracing
-	ALIGN
-syscall_exit_work:
-	testl $_TIF_WORK_SYSCALL_EXIT, %ecx
-	jz work_pending
-	TRACE_IRQS_ON
-	ENABLE_INTERRUPTS(CLBR_ANY)	# could let syscall_trace_leave() call
-					# schedule() instead
-	movl %esp, %eax
-	call syscall_trace_leave
-	jmp resume_userspace
-END(syscall_exit_work)
-	CFI_ENDPROC
-
-	RING0_INT_FRAME			# can't unwind into user space anyway
-syscall_fault:
-	ASM_CLAC
-	GET_THREAD_INFO(%ebp)
-	movl $-EFAULT,PT_EAX(%esp)
-	jmp resume_userspace
-END(syscall_fault)
-
-syscall_badsys:
-	movl $-ENOSYS,%eax
-	jmp syscall_after_call
-END(syscall_badsys)
-
-sysenter_badsys:
-	movl $-ENOSYS,%eax
-	jmp sysenter_after_call
-END(sysenter_badsys)
-	CFI_ENDPROC
-
-.macro FIXUP_ESPFIX_STACK
-/*
- * Switch back for ESPFIX stack to the normal zerobased stack
- *
- * We can't call C functions using the ESPFIX stack. This code reads
- * the high word of the segment base from the GDT and swiches to the
- * normal stack and adjusts ESP with the matching offset.
- */
-#ifdef CONFIG_X86_ESPFIX32
-	/* fixup the stack */
-	mov GDT_ESPFIX_SS + 4, %al /* bits 16..23 */
-	mov GDT_ESPFIX_SS + 7, %ah /* bits 24..31 */
-	shl $16, %eax
-	addl %esp, %eax			/* the adjusted stack pointer */
-	pushl_cfi $__KERNEL_DS
-	pushl_cfi %eax
-	lss (%esp), %esp		/* switch to the normal stack segment */
-	CFI_ADJUST_CFA_OFFSET -8
-#endif
-.endm
-.macro UNWIND_ESPFIX_STACK
-#ifdef CONFIG_X86_ESPFIX32
-	movl %ss, %eax
-	/* see if on espfix stack */
-	cmpw $__ESPFIX_SS, %ax
-	jne 27f
-	movl $__KERNEL_DS, %eax
-	movl %eax, %ds
-	movl %eax, %es
-	/* switch to normal stack */
-	FIXUP_ESPFIX_STACK
-27:
-#endif
-.endm
-
-/*
- * Build the entry stubs with some assembler magic.
- * We pack 1 stub into every 8-byte block.
- */
-	.align 8
-ENTRY(irq_entries_start)
-	RING0_INT_FRAME
-    vector=FIRST_EXTERNAL_VECTOR
-    .rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR)
-	pushl_cfi $(~vector+0x80)	/* Note: always in signed byte range */
-    vector=vector+1
-	jmp	common_interrupt
-	CFI_ADJUST_CFA_OFFSET -4
-	.align	8
-    .endr
-END(irq_entries_start)
-
-/*
- * the CPU automatically disables interrupts when executing an IRQ vector,
- * so IRQ-flags tracing has to follow that:
- */
-	.p2align CONFIG_X86_L1_CACHE_SHIFT
-common_interrupt:
-	ASM_CLAC
-	addl $-0x80,(%esp)	/* Adjust vector into the [-256,-1] range */
-	SAVE_ALL
-	TRACE_IRQS_OFF
-	movl %esp,%eax
-	call do_IRQ
-	jmp ret_from_intr
-ENDPROC(common_interrupt)
-	CFI_ENDPROC
-
-#define BUILD_INTERRUPT3(name, nr, fn)	\
-ENTRY(name)				\
-	RING0_INT_FRAME;		\
-	ASM_CLAC;			\
-	pushl_cfi $~(nr);		\
-	SAVE_ALL;			\
-	TRACE_IRQS_OFF			\
-	movl %esp,%eax;			\
-	call fn;			\
-	jmp ret_from_intr;		\
-	CFI_ENDPROC;			\
-ENDPROC(name)
-
-
-#ifdef CONFIG_TRACING
-#define TRACE_BUILD_INTERRUPT(name, nr)		\
-	BUILD_INTERRUPT3(trace_##name, nr, smp_trace_##name)
-#else
-#define TRACE_BUILD_INTERRUPT(name, nr)
-#endif
-
-#define BUILD_INTERRUPT(name, nr) \
-	BUILD_INTERRUPT3(name, nr, smp_##name); \
-	TRACE_BUILD_INTERRUPT(name, nr)
-
-/* The include is where all of the SMP etc. interrupts come from */
-#include <asm/entry_arch.h>
-
-ENTRY(coprocessor_error)
-	RING0_INT_FRAME
-	ASM_CLAC
-	pushl_cfi $0
-	pushl_cfi $do_coprocessor_error
-	jmp error_code
-	CFI_ENDPROC
-END(coprocessor_error)
-
-ENTRY(simd_coprocessor_error)
-	RING0_INT_FRAME
-	ASM_CLAC
-	pushl_cfi $0
-#ifdef CONFIG_X86_INVD_BUG
-	/* AMD 486 bug: invd from userspace calls exception 19 instead of #GP */
-	ALTERNATIVE "pushl_cfi $do_general_protection",	\
-		    "pushl $do_simd_coprocessor_error", \
-		    X86_FEATURE_XMM
-#else
-	pushl_cfi $do_simd_coprocessor_error
-#endif
-	jmp error_code
-	CFI_ENDPROC
-END(simd_coprocessor_error)
-
-ENTRY(device_not_available)
-	RING0_INT_FRAME
-	ASM_CLAC
-	pushl_cfi $-1			# mark this as an int
-	pushl_cfi $do_device_not_available
-	jmp error_code
-	CFI_ENDPROC
-END(device_not_available)
-
-#ifdef CONFIG_PARAVIRT
-ENTRY(native_iret)
-	iret
-	_ASM_EXTABLE(native_iret, iret_exc)
-END(native_iret)
-
-ENTRY(native_irq_enable_sysexit)
-	sti
-	sysexit
-END(native_irq_enable_sysexit)
-#endif
-
-ENTRY(overflow)
-	RING0_INT_FRAME
-	ASM_CLAC
-	pushl_cfi $0
-	pushl_cfi $do_overflow
-	jmp error_code
-	CFI_ENDPROC
-END(overflow)
-
-ENTRY(bounds)
-	RING0_INT_FRAME
-	ASM_CLAC
-	pushl_cfi $0
-	pushl_cfi $do_bounds
-	jmp error_code
-	CFI_ENDPROC
-END(bounds)
-
-ENTRY(invalid_op)
-	RING0_INT_FRAME
-	ASM_CLAC
-	pushl_cfi $0
-	pushl_cfi $do_invalid_op
-	jmp error_code
-	CFI_ENDPROC
-END(invalid_op)
-
-ENTRY(coprocessor_segment_overrun)
-	RING0_INT_FRAME
-	ASM_CLAC
-	pushl_cfi $0
-	pushl_cfi $do_coprocessor_segment_overrun
-	jmp error_code
-	CFI_ENDPROC
-END(coprocessor_segment_overrun)
-
-ENTRY(invalid_TSS)
-	RING0_EC_FRAME
-	ASM_CLAC
-	pushl_cfi $do_invalid_TSS
-	jmp error_code
-	CFI_ENDPROC
-END(invalid_TSS)
-
-ENTRY(segment_not_present)
-	RING0_EC_FRAME
-	ASM_CLAC
-	pushl_cfi $do_segment_not_present
-	jmp error_code
-	CFI_ENDPROC
-END(segment_not_present)
-
-ENTRY(stack_segment)
-	RING0_EC_FRAME
-	ASM_CLAC
-	pushl_cfi $do_stack_segment
-	jmp error_code
-	CFI_ENDPROC
-END(stack_segment)
-
-ENTRY(alignment_check)
-	RING0_EC_FRAME
-	ASM_CLAC
-	pushl_cfi $do_alignment_check
-	jmp error_code
-	CFI_ENDPROC
-END(alignment_check)
-
-ENTRY(divide_error)
-	RING0_INT_FRAME
-	ASM_CLAC
-	pushl_cfi $0			# no error code
-	pushl_cfi $do_divide_error
-	jmp error_code
-	CFI_ENDPROC
-END(divide_error)
-
-#ifdef CONFIG_X86_MCE
-ENTRY(machine_check)
-	RING0_INT_FRAME
-	ASM_CLAC
-	pushl_cfi $0
-	pushl_cfi machine_check_vector
-	jmp error_code
-	CFI_ENDPROC
-END(machine_check)
-#endif
-
-ENTRY(spurious_interrupt_bug)
-	RING0_INT_FRAME
-	ASM_CLAC
-	pushl_cfi $0
-	pushl_cfi $do_spurious_interrupt_bug
-	jmp error_code
-	CFI_ENDPROC
-END(spurious_interrupt_bug)
-
-#ifdef CONFIG_XEN
-/* Xen doesn't set %esp to be precisely what the normal sysenter
-   entrypoint expects, so fix it up before using the normal path. */
-ENTRY(xen_sysenter_target)
-	RING0_INT_FRAME
-	addl $5*4, %esp		/* remove xen-provided frame */
-	CFI_ADJUST_CFA_OFFSET -5*4
-	jmp sysenter_past_esp
-	CFI_ENDPROC
-
-ENTRY(xen_hypervisor_callback)
-	CFI_STARTPROC
-	pushl_cfi $-1 /* orig_ax = -1 => not a system call */
-	SAVE_ALL
-	TRACE_IRQS_OFF
-
-	/* Check to see if we got the event in the critical
-	   region in xen_iret_direct, after we've reenabled
-	   events and checked for pending events.  This simulates
-	   iret instruction's behaviour where it delivers a
-	   pending interrupt when enabling interrupts. */
-	movl PT_EIP(%esp),%eax
-	cmpl $xen_iret_start_crit,%eax
-	jb   1f
-	cmpl $xen_iret_end_crit,%eax
-	jae  1f
-
-	jmp  xen_iret_crit_fixup
-
-ENTRY(xen_do_upcall)
-1:	mov %esp, %eax
-	call xen_evtchn_do_upcall
-#ifndef CONFIG_PREEMPT
-	call xen_maybe_preempt_hcall
-#endif
-	jmp  ret_from_intr
-	CFI_ENDPROC
-ENDPROC(xen_hypervisor_callback)
-
-# Hypervisor uses this for application faults while it executes.
-# We get here for two reasons:
-#  1. Fault while reloading DS, ES, FS or GS
-#  2. Fault while executing IRET
-# Category 1 we fix up by reattempting the load, and zeroing the segment
-# register if the load fails.
-# Category 2 we fix up by jumping to do_iret_error. We cannot use the
-# normal Linux return path in this case because if we use the IRET hypercall
-# to pop the stack frame we end up in an infinite loop of failsafe callbacks.
-# We distinguish between categories by maintaining a status value in EAX.
-ENTRY(xen_failsafe_callback)
-	CFI_STARTPROC
-	pushl_cfi %eax
-	movl $1,%eax
-1:	mov 4(%esp),%ds
-2:	mov 8(%esp),%es
-3:	mov 12(%esp),%fs
-4:	mov 16(%esp),%gs
-	/* EAX == 0 => Category 1 (Bad segment)
-	   EAX != 0 => Category 2 (Bad IRET) */
-	testl %eax,%eax
-	popl_cfi %eax
-	lea 16(%esp),%esp
-	CFI_ADJUST_CFA_OFFSET -16
-	jz 5f
-	jmp iret_exc
-5:	pushl_cfi $-1 /* orig_ax = -1 => not a system call */
-	SAVE_ALL
-	jmp ret_from_exception
-	CFI_ENDPROC
-
-.section .fixup,"ax"
-6:	xorl %eax,%eax
-	movl %eax,4(%esp)
-	jmp 1b
-7:	xorl %eax,%eax
-	movl %eax,8(%esp)
-	jmp 2b
-8:	xorl %eax,%eax
-	movl %eax,12(%esp)
-	jmp 3b
-9:	xorl %eax,%eax
-	movl %eax,16(%esp)
-	jmp 4b
-.previous
-	_ASM_EXTABLE(1b,6b)
-	_ASM_EXTABLE(2b,7b)
-	_ASM_EXTABLE(3b,8b)
-	_ASM_EXTABLE(4b,9b)
-ENDPROC(xen_failsafe_callback)
-
-BUILD_INTERRUPT3(xen_hvm_callback_vector, HYPERVISOR_CALLBACK_VECTOR,
-		xen_evtchn_do_upcall)
-
-#endif	/* CONFIG_XEN */
-
-#if IS_ENABLED(CONFIG_HYPERV)
-
-BUILD_INTERRUPT3(hyperv_callback_vector, HYPERVISOR_CALLBACK_VECTOR,
-	hyperv_vector_handler)
-
-#endif /* CONFIG_HYPERV */
-
-#ifdef CONFIG_FUNCTION_TRACER
-#ifdef CONFIG_DYNAMIC_FTRACE
-
-ENTRY(mcount)
-	ret
-END(mcount)
-
-ENTRY(ftrace_caller)
-	pushl %eax
-	pushl %ecx
-	pushl %edx
-	pushl $0	/* Pass NULL as regs pointer */
-	movl 4*4(%esp), %eax
-	movl 0x4(%ebp), %edx
-	movl function_trace_op, %ecx
-	subl $MCOUNT_INSN_SIZE, %eax
-
-.globl ftrace_call
-ftrace_call:
-	call ftrace_stub
-
-	addl $4,%esp	/* skip NULL pointer */
-	popl %edx
-	popl %ecx
-	popl %eax
-ftrace_ret:
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-.globl ftrace_graph_call
-ftrace_graph_call:
-	jmp ftrace_stub
-#endif
-
-.globl ftrace_stub
-ftrace_stub:
-	ret
-END(ftrace_caller)
-
-ENTRY(ftrace_regs_caller)
-	pushf	/* push flags before compare (in cs location) */
-
-	/*
-	 * i386 does not save SS and ESP when coming from kernel.
-	 * Instead, to get sp, &regs->sp is used (see ptrace.h).
-	 * Unfortunately, that means eflags must be at the same location
-	 * as the current return ip is. We move the return ip into the
-	 * ip location, and move flags into the return ip location.
-	 */
-	pushl 4(%esp)	/* save return ip into ip slot */
-
-	pushl $0	/* Load 0 into orig_ax */
-	pushl %gs
-	pushl %fs
-	pushl %es
-	pushl %ds
-	pushl %eax
-	pushl %ebp
-	pushl %edi
-	pushl %esi
-	pushl %edx
-	pushl %ecx
-	pushl %ebx
-
-	movl 13*4(%esp), %eax	/* Get the saved flags */
-	movl %eax, 14*4(%esp)	/* Move saved flags into regs->flags location */
-				/* clobbering return ip */
-	movl $__KERNEL_CS,13*4(%esp)
-
-	movl 12*4(%esp), %eax	/* Load ip (1st parameter) */
-	subl $MCOUNT_INSN_SIZE, %eax	/* Adjust ip */
-	movl 0x4(%ebp), %edx	/* Load parent ip (2nd parameter) */
-	movl function_trace_op, %ecx /* Save ftrace_pos in 3rd parameter */
-	pushl %esp		/* Save pt_regs as 4th parameter */
-
-GLOBAL(ftrace_regs_call)
-	call ftrace_stub
-
-	addl $4, %esp		/* Skip pt_regs */
-	movl 14*4(%esp), %eax	/* Move flags back into cs */
-	movl %eax, 13*4(%esp)	/* Needed to keep addl from modifying flags */
-	movl 12*4(%esp), %eax	/* Get return ip from regs->ip */
-	movl %eax, 14*4(%esp)	/* Put return ip back for ret */
-
-	popl %ebx
-	popl %ecx
-	popl %edx
-	popl %esi
-	popl %edi
-	popl %ebp
-	popl %eax
-	popl %ds
-	popl %es
-	popl %fs
-	popl %gs
-	addl $8, %esp		/* Skip orig_ax and ip */
-	popf			/* Pop flags at end (no addl to corrupt flags) */
-	jmp ftrace_ret
-
-	popf
-	jmp  ftrace_stub
-#else /* ! CONFIG_DYNAMIC_FTRACE */
-
-ENTRY(mcount)
-	cmpl $__PAGE_OFFSET, %esp
-	jb ftrace_stub		/* Paging not enabled yet? */
-
-	cmpl $ftrace_stub, ftrace_trace_function
-	jnz trace
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	cmpl $ftrace_stub, ftrace_graph_return
-	jnz ftrace_graph_caller
-
-	cmpl $ftrace_graph_entry_stub, ftrace_graph_entry
-	jnz ftrace_graph_caller
-#endif
-.globl ftrace_stub
-ftrace_stub:
-	ret
-
-	/* taken from glibc */
-trace:
-	pushl %eax
-	pushl %ecx
-	pushl %edx
-	movl 0xc(%esp), %eax
-	movl 0x4(%ebp), %edx
-	subl $MCOUNT_INSN_SIZE, %eax
-
-	call *ftrace_trace_function
-
-	popl %edx
-	popl %ecx
-	popl %eax
-	jmp ftrace_stub
-END(mcount)
-#endif /* CONFIG_DYNAMIC_FTRACE */
-#endif /* CONFIG_FUNCTION_TRACER */
-
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-ENTRY(ftrace_graph_caller)
-	pushl %eax
-	pushl %ecx
-	pushl %edx
-	movl 0xc(%esp), %eax
-	lea 0x4(%ebp), %edx
-	movl (%ebp), %ecx
-	subl $MCOUNT_INSN_SIZE, %eax
-	call prepare_ftrace_return
-	popl %edx
-	popl %ecx
-	popl %eax
-	ret
-END(ftrace_graph_caller)
-
-.globl return_to_handler
-return_to_handler:
-	pushl %eax
-	pushl %edx
-	movl %ebp, %eax
-	call ftrace_return_to_handler
-	movl %eax, %ecx
-	popl %edx
-	popl %eax
-	jmp *%ecx
-#endif
-
-#ifdef CONFIG_TRACING
-ENTRY(trace_page_fault)
-	RING0_EC_FRAME
-	ASM_CLAC
-	pushl_cfi $trace_do_page_fault
-	jmp error_code
-	CFI_ENDPROC
-END(trace_page_fault)
-#endif
-
-ENTRY(page_fault)
-	RING0_EC_FRAME
-	ASM_CLAC
-	pushl_cfi $do_page_fault
-	ALIGN
-error_code:
-	/* the function address is in %gs's slot on the stack */
-	pushl_cfi %fs
-	/*CFI_REL_OFFSET fs, 0*/
-	pushl_cfi %es
-	/*CFI_REL_OFFSET es, 0*/
-	pushl_cfi %ds
-	/*CFI_REL_OFFSET ds, 0*/
-	pushl_cfi_reg eax
-	pushl_cfi_reg ebp
-	pushl_cfi_reg edi
-	pushl_cfi_reg esi
-	pushl_cfi_reg edx
-	pushl_cfi_reg ecx
-	pushl_cfi_reg ebx
-	cld
-	movl $(__KERNEL_PERCPU), %ecx
-	movl %ecx, %fs
-	UNWIND_ESPFIX_STACK
-	GS_TO_REG %ecx
-	movl PT_GS(%esp), %edi		# get the function address
-	movl PT_ORIG_EAX(%esp), %edx	# get the error code
-	movl $-1, PT_ORIG_EAX(%esp)	# no syscall to restart
-	REG_TO_PTGS %ecx
-	SET_KERNEL_GS %ecx
-	movl $(__USER_DS), %ecx
-	movl %ecx, %ds
-	movl %ecx, %es
-	TRACE_IRQS_OFF
-	movl %esp,%eax			# pt_regs pointer
-	call *%edi
-	jmp ret_from_exception
-	CFI_ENDPROC
-END(page_fault)
-
-/*
- * Debug traps and NMI can happen at the one SYSENTER instruction
- * that sets up the real kernel stack. Check here, since we can't
- * allow the wrong stack to be used.
- *
- * "TSS_sysenter_sp0+12" is because the NMI/debug handler will have
- * already pushed 3 words if it hits on the sysenter instruction:
- * eflags, cs and eip.
- *
- * We just load the right stack, and push the three (known) values
- * by hand onto the new stack - while updating the return eip past
- * the instruction that would have done it for sysenter.
- */
-.macro FIX_STACK offset ok label
-	cmpw $__KERNEL_CS, 4(%esp)
-	jne \ok
-\label:
-	movl TSS_sysenter_sp0 + \offset(%esp), %esp
-	CFI_DEF_CFA esp, 0
-	CFI_UNDEFINED eip
-	pushfl_cfi
-	pushl_cfi $__KERNEL_CS
-	pushl_cfi $sysenter_past_esp
-	CFI_REL_OFFSET eip, 0
-.endm
-
-ENTRY(debug)
-	RING0_INT_FRAME
-	ASM_CLAC
-	cmpl $ia32_sysenter_target,(%esp)
-	jne debug_stack_correct
-	FIX_STACK 12, debug_stack_correct, debug_esp_fix_insn
-debug_stack_correct:
-	pushl_cfi $-1			# mark this as an int
-	SAVE_ALL
-	TRACE_IRQS_OFF
-	xorl %edx,%edx			# error code 0
-	movl %esp,%eax			# pt_regs pointer
-	call do_debug
-	jmp ret_from_exception
-	CFI_ENDPROC
-END(debug)
-
-/*
- * NMI is doubly nasty. It can happen _while_ we're handling
- * a debug fault, and the debug fault hasn't yet been able to
- * clear up the stack. So we first check whether we got  an
- * NMI on the sysenter entry path, but after that we need to
- * check whether we got an NMI on the debug path where the debug
- * fault happened on the sysenter path.
- */
-ENTRY(nmi)
-	RING0_INT_FRAME
-	ASM_CLAC
-#ifdef CONFIG_X86_ESPFIX32
-	pushl_cfi %eax
-	movl %ss, %eax
-	cmpw $__ESPFIX_SS, %ax
-	popl_cfi %eax
-	je nmi_espfix_stack
-#endif
-	cmpl $ia32_sysenter_target,(%esp)
-	je nmi_stack_fixup
-	pushl_cfi %eax
-	movl %esp,%eax
-	/* Do not access memory above the end of our stack page,
-	 * it might not exist.
-	 */
-	andl $(THREAD_SIZE-1),%eax
-	cmpl $(THREAD_SIZE-20),%eax
-	popl_cfi %eax
-	jae nmi_stack_correct
-	cmpl $ia32_sysenter_target,12(%esp)
-	je nmi_debug_stack_check
-nmi_stack_correct:
-	/* We have a RING0_INT_FRAME here */
-	pushl_cfi %eax
-	SAVE_ALL
-	xorl %edx,%edx		# zero error code
-	movl %esp,%eax		# pt_regs pointer
-	call do_nmi
-	jmp restore_all_notrace
-	CFI_ENDPROC
-
-nmi_stack_fixup:
-	RING0_INT_FRAME
-	FIX_STACK 12, nmi_stack_correct, 1
-	jmp nmi_stack_correct
-
-nmi_debug_stack_check:
-	/* We have a RING0_INT_FRAME here */
-	cmpw $__KERNEL_CS,16(%esp)
-	jne nmi_stack_correct
-	cmpl $debug,(%esp)
-	jb nmi_stack_correct
-	cmpl $debug_esp_fix_insn,(%esp)
-	ja nmi_stack_correct
-	FIX_STACK 24, nmi_stack_correct, 1
-	jmp nmi_stack_correct
-
-#ifdef CONFIG_X86_ESPFIX32
-nmi_espfix_stack:
-	/* We have a RING0_INT_FRAME here.
-	 *
-	 * create the pointer to lss back
-	 */
-	pushl_cfi %ss
-	pushl_cfi %esp
-	addl $4, (%esp)
-	/* copy the iret frame of 12 bytes */
-	.rept 3
-	pushl_cfi 16(%esp)
-	.endr
-	pushl_cfi %eax
-	SAVE_ALL
-	FIXUP_ESPFIX_STACK		# %eax == %esp
-	xorl %edx,%edx			# zero error code
-	call do_nmi
-	RESTORE_REGS
-	lss 12+4(%esp), %esp		# back to espfix stack
-	CFI_ADJUST_CFA_OFFSET -24
-	jmp irq_return
-#endif
-	CFI_ENDPROC
-END(nmi)
-
-ENTRY(int3)
-	RING0_INT_FRAME
-	ASM_CLAC
-	pushl_cfi $-1			# mark this as an int
-	SAVE_ALL
-	TRACE_IRQS_OFF
-	xorl %edx,%edx		# zero error code
-	movl %esp,%eax		# pt_regs pointer
-	call do_int3
-	jmp ret_from_exception
-	CFI_ENDPROC
-END(int3)
-
-ENTRY(general_protection)
-	RING0_EC_FRAME
-	pushl_cfi $do_general_protection
-	jmp error_code
-	CFI_ENDPROC
-END(general_protection)
-
-#ifdef CONFIG_KVM_GUEST
-ENTRY(async_page_fault)
-	RING0_EC_FRAME
-	ASM_CLAC
-	pushl_cfi $do_async_page_fault
-	jmp error_code
-	CFI_ENDPROC
-END(async_page_fault)
-#endif
-
diff --git a/arch/x86/kernel/fpu/Makefile b/arch/x86/kernel/fpu/Makefile
new file mode 100644
index 000000000000..68279efb811a
--- /dev/null
+++ b/arch/x86/kernel/fpu/Makefile
@@ -0,0 +1,5 @@
+#
+# Build rules for the FPU support code:
+#
+
+obj-y				+= init.o bugs.o core.o regset.o signal.o xstate.o
diff --git a/arch/x86/kernel/fpu/bugs.c b/arch/x86/kernel/fpu/bugs.c
new file mode 100644
index 000000000000..dd9ca9b60ff3
--- /dev/null
+++ b/arch/x86/kernel/fpu/bugs.c
@@ -0,0 +1,71 @@
+/*
+ * x86 FPU bug checks:
+ */
+#include <asm/fpu/internal.h>
+
+/*
+ * Boot time CPU/FPU FDIV bug detection code:
+ */
+
+static double __initdata x = 4195835.0;
+static double __initdata y = 3145727.0;
+
+/*
+ * This used to check for exceptions..
+ * However, it turns out that to support that,
+ * the XMM trap handlers basically had to
+ * be buggy. So let's have a correct XMM trap
+ * handler, and forget about printing out
+ * some status at boot.
+ *
+ * We should really only care about bugs here
+ * anyway. Not features.
+ */
+static void __init check_fpu(void)
+{
+	u32 cr0_saved;
+	s32 fdiv_bug;
+
+	/* We might have CR0::TS set already, clear it: */
+	cr0_saved = read_cr0();
+	write_cr0(cr0_saved & ~X86_CR0_TS);
+
+	kernel_fpu_begin();
+
+	/*
+	 * trap_init() enabled FXSR and company _before_ testing for FP
+	 * problems here.
+	 *
+	 * Test for the divl bug: http://en.wikipedia.org/wiki/Fdiv_bug
+	 */
+	__asm__("fninit\n\t"
+		"fldl %1\n\t"
+		"fdivl %2\n\t"
+		"fmull %2\n\t"
+		"fldl %1\n\t"
+		"fsubp %%st,%%st(1)\n\t"
+		"fistpl %0\n\t"
+		"fwait\n\t"
+		"fninit"
+		: "=m" (*&fdiv_bug)
+		: "m" (*&x), "m" (*&y));
+
+	kernel_fpu_end();
+
+	write_cr0(cr0_saved);
+
+	if (fdiv_bug) {
+		set_cpu_bug(&boot_cpu_data, X86_BUG_FDIV);
+		pr_warn("Hmm, FPU with FDIV bug\n");
+	}
+}
+
+void __init fpu__init_check_bugs(void)
+{
+	/*
+	 * kernel_fpu_begin/end() in check_fpu() relies on the patched
+	 * alternative instructions.
+	 */
+	if (cpu_has_fpu)
+		check_fpu();
+}
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
new file mode 100644
index 000000000000..79de954626fd
--- /dev/null
+++ b/arch/x86/kernel/fpu/core.c
@@ -0,0 +1,523 @@
+/*
+ *  Copyright (C) 1994 Linus Torvalds
+ *
+ *  Pentium III FXSR, SSE support
+ *  General FPU state handling cleanups
+ *	Gareth Hughes <gareth@valinux.com>, May 2000
+ */
+#include <asm/fpu/internal.h>
+#include <asm/fpu/regset.h>
+#include <asm/fpu/signal.h>
+#include <asm/traps.h>
+
+#include <linux/hardirq.h>
+
+/*
+ * Represents the initial FPU state. It's mostly (but not completely) zeroes,
+ * depending on the FPU hardware format:
+ */
+union fpregs_state init_fpstate __read_mostly;
+
+/*
+ * Track whether the kernel is using the FPU state
+ * currently.
+ *
+ * This flag is used:
+ *
+ *   - by IRQ context code to potentially use the FPU
+ *     if it's unused.
+ *
+ *   - to debug kernel_fpu_begin()/end() correctness
+ */
+static DEFINE_PER_CPU(bool, in_kernel_fpu);
+
+/*
+ * Track which context is using the FPU on the CPU:
+ */
+DEFINE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx);
+
+static void kernel_fpu_disable(void)
+{
+	WARN_ON_FPU(this_cpu_read(in_kernel_fpu));
+	this_cpu_write(in_kernel_fpu, true);
+}
+
+static void kernel_fpu_enable(void)
+{
+	WARN_ON_FPU(!this_cpu_read(in_kernel_fpu));
+	this_cpu_write(in_kernel_fpu, false);
+}
+
+static bool kernel_fpu_disabled(void)
+{
+	return this_cpu_read(in_kernel_fpu);
+}
+
+/*
+ * Were we in an interrupt that interrupted kernel mode?
+ *
+ * On others, we can do a kernel_fpu_begin/end() pair *ONLY* if that
+ * pair does nothing at all: the thread must not have fpu (so
+ * that we don't try to save the FPU state), and TS must
+ * be set (so that the clts/stts pair does nothing that is
+ * visible in the interrupted kernel thread).
+ *
+ * Except for the eagerfpu case when we return true; in the likely case
+ * the thread has FPU but we are not going to set/clear TS.
+ */
+static bool interrupted_kernel_fpu_idle(void)
+{
+	if (kernel_fpu_disabled())
+		return false;
+
+	if (use_eager_fpu())
+		return true;
+
+	return !current->thread.fpu.fpregs_active && (read_cr0() & X86_CR0_TS);
+}
+
+/*
+ * Were we in user mode (or vm86 mode) when we were
+ * interrupted?
+ *
+ * Doing kernel_fpu_begin/end() is ok if we are running
+ * in an interrupt context from user mode - we'll just
+ * save the FPU state as required.
+ */
+static bool interrupted_user_mode(void)
+{
+	struct pt_regs *regs = get_irq_regs();
+	return regs && user_mode(regs);
+}
+
+/*
+ * Can we use the FPU in kernel mode with the
+ * whole "kernel_fpu_begin/end()" sequence?
+ *
+ * It's always ok in process context (ie "not interrupt")
+ * but it is sometimes ok even from an irq.
+ */
+bool irq_fpu_usable(void)
+{
+	return !in_interrupt() ||
+		interrupted_user_mode() ||
+		interrupted_kernel_fpu_idle();
+}
+EXPORT_SYMBOL(irq_fpu_usable);
+
+void __kernel_fpu_begin(void)
+{
+	struct fpu *fpu = &current->thread.fpu;
+
+	WARN_ON_FPU(!irq_fpu_usable());
+
+	kernel_fpu_disable();
+
+	if (fpu->fpregs_active) {
+		copy_fpregs_to_fpstate(fpu);
+	} else {
+		this_cpu_write(fpu_fpregs_owner_ctx, NULL);
+		__fpregs_activate_hw();
+	}
+}
+EXPORT_SYMBOL(__kernel_fpu_begin);
+
+void __kernel_fpu_end(void)
+{
+	struct fpu *fpu = &current->thread.fpu;
+
+	if (fpu->fpregs_active)
+		copy_kernel_to_fpregs(&fpu->state);
+	else
+		__fpregs_deactivate_hw();
+
+	kernel_fpu_enable();
+}
+EXPORT_SYMBOL(__kernel_fpu_end);
+
+void kernel_fpu_begin(void)
+{
+	preempt_disable();
+	__kernel_fpu_begin();
+}
+EXPORT_SYMBOL_GPL(kernel_fpu_begin);
+
+void kernel_fpu_end(void)
+{
+	__kernel_fpu_end();
+	preempt_enable();
+}
+EXPORT_SYMBOL_GPL(kernel_fpu_end);
+
+/*
+ * CR0::TS save/restore functions:
+ */
+int irq_ts_save(void)
+{
+	/*
+	 * If in process context and not atomic, we can take a spurious DNA fault.
+	 * Otherwise, doing clts() in process context requires disabling preemption
+	 * or some heavy lifting like kernel_fpu_begin()
+	 */
+	if (!in_atomic())
+		return 0;
+
+	if (read_cr0() & X86_CR0_TS) {
+		clts();
+		return 1;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(irq_ts_save);
+
+void irq_ts_restore(int TS_state)
+{
+	if (TS_state)
+		stts();
+}
+EXPORT_SYMBOL_GPL(irq_ts_restore);
+
+/*
+ * Save the FPU state (mark it for reload if necessary):
+ *
+ * This only ever gets called for the current task.
+ */
+void fpu__save(struct fpu *fpu)
+{
+	WARN_ON_FPU(fpu != &current->thread.fpu);
+
+	preempt_disable();
+	if (fpu->fpregs_active) {
+		if (!copy_fpregs_to_fpstate(fpu))
+			fpregs_deactivate(fpu);
+	}
+	preempt_enable();
+}
+EXPORT_SYMBOL_GPL(fpu__save);
+
+/*
+ * Legacy x87 fpstate state init:
+ */
+static inline void fpstate_init_fstate(struct fregs_state *fp)
+{
+	fp->cwd = 0xffff037fu;
+	fp->swd = 0xffff0000u;
+	fp->twd = 0xffffffffu;
+	fp->fos = 0xffff0000u;
+}
+
+void fpstate_init(union fpregs_state *state)
+{
+	if (!cpu_has_fpu) {
+		fpstate_init_soft(&state->soft);
+		return;
+	}
+
+	memset(state, 0, xstate_size);
+
+	if (cpu_has_fxsr)
+		fpstate_init_fxstate(&state->fxsave);
+	else
+		fpstate_init_fstate(&state->fsave);
+}
+EXPORT_SYMBOL_GPL(fpstate_init);
+
+/*
+ * Copy the current task's FPU state to a new task's FPU context.
+ *
+ * In both the 'eager' and the 'lazy' case we save hardware registers
+ * directly to the destination buffer.
+ */
+static void fpu_copy(struct fpu *dst_fpu, struct fpu *src_fpu)
+{
+	WARN_ON_FPU(src_fpu != &current->thread.fpu);
+
+	/*
+	 * Don't let 'init optimized' areas of the XSAVE area
+	 * leak into the child task:
+	 */
+	if (use_eager_fpu())
+		memset(&dst_fpu->state.xsave, 0, xstate_size);
+
+	/*
+	 * Save current FPU registers directly into the child
+	 * FPU context, without any memory-to-memory copying.
+	 *
+	 * If the FPU context got destroyed in the process (FNSAVE
+	 * done on old CPUs) then copy it back into the source
+	 * context and mark the current task for lazy restore.
+	 *
+	 * We have to do all this with preemption disabled,
+	 * mostly because of the FNSAVE case, because in that
+	 * case we must not allow preemption in the window
+	 * between the FNSAVE and us marking the context lazy.
+	 *
+	 * It shouldn't be an issue as even FNSAVE is plenty
+	 * fast in terms of critical section length.
+	 */
+	preempt_disable();
+	if (!copy_fpregs_to_fpstate(dst_fpu)) {
+		memcpy(&src_fpu->state, &dst_fpu->state, xstate_size);
+		fpregs_deactivate(src_fpu);
+	}
+	preempt_enable();
+}
+
+int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu)
+{
+	dst_fpu->counter = 0;
+	dst_fpu->fpregs_active = 0;
+	dst_fpu->last_cpu = -1;
+
+	if (src_fpu->fpstate_active)
+		fpu_copy(dst_fpu, src_fpu);
+
+	return 0;
+}
+
+/*
+ * Activate the current task's in-memory FPU context,
+ * if it has not been used before:
+ */
+void fpu__activate_curr(struct fpu *fpu)
+{
+	WARN_ON_FPU(fpu != &current->thread.fpu);
+
+	if (!fpu->fpstate_active) {
+		fpstate_init(&fpu->state);
+
+		/* Safe to do for the current task: */
+		fpu->fpstate_active = 1;
+	}
+}
+EXPORT_SYMBOL_GPL(fpu__activate_curr);
+
+/*
+ * This function must be called before we read a task's fpstate.
+ *
+ * If the task has not used the FPU before then initialize its
+ * fpstate.
+ *
+ * If the task has used the FPU before then save it.
+ */
+void fpu__activate_fpstate_read(struct fpu *fpu)
+{
+	/*
+	 * If fpregs are active (in the current CPU), then
+	 * copy them to the fpstate:
+	 */
+	if (fpu->fpregs_active) {
+		fpu__save(fpu);
+	} else {
+		if (!fpu->fpstate_active) {
+			fpstate_init(&fpu->state);
+
+			/* Safe to do for current and for stopped child tasks: */
+			fpu->fpstate_active = 1;
+		}
+	}
+}
+
+/*
+ * This function must be called before we write a task's fpstate.
+ *
+ * If the task has used the FPU before then unlazy it.
+ * If the task has not used the FPU before then initialize its fpstate.
+ *
+ * After this function call, after registers in the fpstate are
+ * modified and the child task has woken up, the child task will
+ * restore the modified FPU state from the modified context. If we
+ * didn't clear its lazy status here then the lazy in-registers
+ * state pending on its former CPU could be restored, corrupting
+ * the modifications.
+ */
+void fpu__activate_fpstate_write(struct fpu *fpu)
+{
+	/*
+	 * Only stopped child tasks can be used to modify the FPU
+	 * state in the fpstate buffer:
+	 */
+	WARN_ON_FPU(fpu == &current->thread.fpu);
+
+	if (fpu->fpstate_active) {
+		/* Invalidate any lazy state: */
+		fpu->last_cpu = -1;
+	} else {
+		fpstate_init(&fpu->state);
+
+		/* Safe to do for stopped child tasks: */
+		fpu->fpstate_active = 1;
+	}
+}
+
+/*
+ * 'fpu__restore()' is called to copy FPU registers from
+ * the FPU fpstate to the live hw registers and to activate
+ * access to the hardware registers, so that FPU instructions
+ * can be used afterwards.
+ *
+ * Must be called with kernel preemption disabled (for example
+ * with local interrupts disabled, as it is in the case of
+ * do_device_not_available()).
+ */
+void fpu__restore(struct fpu *fpu)
+{
+	fpu__activate_curr(fpu);
+
+	/* Avoid __kernel_fpu_begin() right after fpregs_activate() */
+	kernel_fpu_disable();
+	fpregs_activate(fpu);
+	copy_kernel_to_fpregs(&fpu->state);
+	fpu->counter++;
+	kernel_fpu_enable();
+}
+EXPORT_SYMBOL_GPL(fpu__restore);
+
+/*
+ * Drops current FPU state: deactivates the fpregs and
+ * the fpstate. NOTE: it still leaves previous contents
+ * in the fpregs in the eager-FPU case.
+ *
+ * This function can be used in cases where we know that
+ * a state-restore is coming: either an explicit one,
+ * or a reschedule.
+ */
+void fpu__drop(struct fpu *fpu)
+{
+	preempt_disable();
+	fpu->counter = 0;
+
+	if (fpu->fpregs_active) {
+		/* Ignore delayed exceptions from user space */
+		asm volatile("1: fwait\n"
+			     "2:\n"
+			     _ASM_EXTABLE(1b, 2b));
+		fpregs_deactivate(fpu);
+	}
+
+	fpu->fpstate_active = 0;
+
+	preempt_enable();
+}
+
+/*
+ * Clear FPU registers by setting them up from
+ * the init fpstate:
+ */
+static inline void copy_init_fpstate_to_fpregs(void)
+{
+	if (use_xsave())
+		copy_kernel_to_xregs(&init_fpstate.xsave, -1);
+	else
+		copy_kernel_to_fxregs(&init_fpstate.fxsave);
+}
+
+/*
+ * Clear the FPU state back to init state.
+ *
+ * Called by sys_execve(), by the signal handler code and by various
+ * error paths.
+ */
+void fpu__clear(struct fpu *fpu)
+{
+	WARN_ON_FPU(fpu != &current->thread.fpu); /* Almost certainly an anomaly */
+
+	if (!use_eager_fpu()) {
+		/* FPU state will be reallocated lazily at the first use. */
+		fpu__drop(fpu);
+	} else {
+		if (!fpu->fpstate_active) {
+			fpu__activate_curr(fpu);
+			user_fpu_begin();
+		}
+		copy_init_fpstate_to_fpregs();
+	}
+}
+
+/*
+ * x87 math exception handling:
+ */
+
+static inline unsigned short get_fpu_cwd(struct fpu *fpu)
+{
+	if (cpu_has_fxsr) {
+		return fpu->state.fxsave.cwd;
+	} else {
+		return (unsigned short)fpu->state.fsave.cwd;
+	}
+}
+
+static inline unsigned short get_fpu_swd(struct fpu *fpu)
+{
+	if (cpu_has_fxsr) {
+		return fpu->state.fxsave.swd;
+	} else {
+		return (unsigned short)fpu->state.fsave.swd;
+	}
+}
+
+static inline unsigned short get_fpu_mxcsr(struct fpu *fpu)
+{
+	if (cpu_has_xmm) {
+		return fpu->state.fxsave.mxcsr;
+	} else {
+		return MXCSR_DEFAULT;
+	}
+}
+
+int fpu__exception_code(struct fpu *fpu, int trap_nr)
+{
+	int err;
+
+	if (trap_nr == X86_TRAP_MF) {
+		unsigned short cwd, swd;
+		/*
+		 * (~cwd & swd) will mask out exceptions that are not set to unmasked
+		 * status.  0x3f is the exception bits in these regs, 0x200 is the
+		 * C1 reg you need in case of a stack fault, 0x040 is the stack
+		 * fault bit.  We should only be taking one exception at a time,
+		 * so if this combination doesn't produce any single exception,
+		 * then we have a bad program that isn't synchronizing its FPU usage
+		 * and it will suffer the consequences since we won't be able to
+		 * fully reproduce the context of the exception
+		 */
+		cwd = get_fpu_cwd(fpu);
+		swd = get_fpu_swd(fpu);
+
+		err = swd & ~cwd;
+	} else {
+		/*
+		 * The SIMD FPU exceptions are handled a little differently, as there
+		 * is only a single status/control register.  Thus, to determine which
+		 * unmasked exception was caught we must mask the exception mask bits
+		 * at 0x1f80, and then use these to mask the exception bits at 0x3f.
+		 */
+		unsigned short mxcsr = get_fpu_mxcsr(fpu);
+		err = ~(mxcsr >> 7) & mxcsr;
+	}
+
+	if (err & 0x001) {	/* Invalid op */
+		/*
+		 * swd & 0x240 == 0x040: Stack Underflow
+		 * swd & 0x240 == 0x240: Stack Overflow
+		 * User must clear the SF bit (0x40) if set
+		 */
+		return FPE_FLTINV;
+	} else if (err & 0x004) { /* Divide by Zero */
+		return FPE_FLTDIV;
+	} else if (err & 0x008) { /* Overflow */
+		return FPE_FLTOVF;
+	} else if (err & 0x012) { /* Denormal, Underflow */
+		return FPE_FLTUND;
+	} else if (err & 0x020) { /* Precision */
+		return FPE_FLTRES;
+	}
+
+	/*
+	 * If we're using IRQ 13, or supposedly even some trap
+	 * X86_TRAP_MF implementations, it's possible
+	 * we get a spurious trap, which is not an error.
+	 */
+	return 0;
+}
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
new file mode 100644
index 000000000000..fc878fee6a51
--- /dev/null
+++ b/arch/x86/kernel/fpu/init.c
@@ -0,0 +1,354 @@
+/*
+ * x86 FPU boot time init code:
+ */
+#include <asm/fpu/internal.h>
+#include <asm/tlbflush.h>
+
+/*
+ * Initialize the TS bit in CR0 according to the style of context-switches
+ * we are using:
+ */
+static void fpu__init_cpu_ctx_switch(void)
+{
+	if (!cpu_has_eager_fpu)
+		stts();
+	else
+		clts();
+}
+
+/*
+ * Initialize the registers found in all CPUs, CR0 and CR4:
+ */
+static void fpu__init_cpu_generic(void)
+{
+	unsigned long cr0;
+	unsigned long cr4_mask = 0;
+
+	if (cpu_has_fxsr)
+		cr4_mask |= X86_CR4_OSFXSR;
+	if (cpu_has_xmm)
+		cr4_mask |= X86_CR4_OSXMMEXCPT;
+	if (cr4_mask)
+		cr4_set_bits(cr4_mask);
+
+	cr0 = read_cr0();
+	cr0 &= ~(X86_CR0_TS|X86_CR0_EM); /* clear TS and EM */
+	if (!cpu_has_fpu)
+		cr0 |= X86_CR0_EM;
+	write_cr0(cr0);
+
+	/* Flush out any pending x87 state: */
+	asm volatile ("fninit");
+}
+
+/*
+ * Enable all supported FPU features. Called when a CPU is brought online:
+ */
+void fpu__init_cpu(void)
+{
+	fpu__init_cpu_generic();
+	fpu__init_cpu_xstate();
+	fpu__init_cpu_ctx_switch();
+}
+
+/*
+ * The earliest FPU detection code.
+ *
+ * Set the X86_FEATURE_FPU CPU-capability bit based on
+ * trying to execute an actual sequence of FPU instructions:
+ */
+static void fpu__init_system_early_generic(struct cpuinfo_x86 *c)
+{
+	unsigned long cr0;
+	u16 fsw, fcw;
+
+	fsw = fcw = 0xffff;
+
+	cr0 = read_cr0();
+	cr0 &= ~(X86_CR0_TS | X86_CR0_EM);
+	write_cr0(cr0);
+
+	asm volatile("fninit ; fnstsw %0 ; fnstcw %1"
+		     : "+m" (fsw), "+m" (fcw));
+
+	if (fsw == 0 && (fcw & 0x103f) == 0x003f)
+		set_cpu_cap(c, X86_FEATURE_FPU);
+	else
+		clear_cpu_cap(c, X86_FEATURE_FPU);
+
+#ifndef CONFIG_MATH_EMULATION
+	if (!cpu_has_fpu) {
+		pr_emerg("x86/fpu: Giving up, no FPU found and no math emulation present\n");
+		for (;;)
+			asm volatile("hlt");
+	}
+#endif
+}
+
+/*
+ * Boot time FPU feature detection code:
+ */
+unsigned int mxcsr_feature_mask __read_mostly = 0xffffffffu;
+
+static void __init fpu__init_system_mxcsr(void)
+{
+	unsigned int mask = 0;
+
+	if (cpu_has_fxsr) {
+		struct fxregs_state fx_tmp __aligned(32) = { };
+
+		asm volatile("fxsave %0" : "+m" (fx_tmp));
+
+		mask = fx_tmp.mxcsr_mask;
+
+		/*
+		 * If zero then use the default features mask,
+		 * which has all features set, except the
+		 * denormals-are-zero feature bit:
+		 */
+		if (mask == 0)
+			mask = 0x0000ffbf;
+	}
+	mxcsr_feature_mask &= mask;
+}
+
+/*
+ * Once per bootup FPU initialization sequences that will run on most x86 CPUs:
+ */
+static void __init fpu__init_system_generic(void)
+{
+	/*
+	 * Set up the legacy init FPU context. (xstate init might overwrite this
+	 * with a more modern format, if the CPU supports it.)
+	 */
+	fpstate_init_fxstate(&init_fpstate.fxsave);
+
+	fpu__init_system_mxcsr();
+}
+
+/*
+ * Size of the FPU context state. All tasks in the system use the
+ * same context size, regardless of what portion they use.
+ * This is inherent to the XSAVE architecture which puts all state
+ * components into a single, continuous memory block:
+ */
+unsigned int xstate_size;
+EXPORT_SYMBOL_GPL(xstate_size);
+
+/*
+ * Set up the xstate_size based on the legacy FPU context size.
+ *
+ * We set this up first, and later it will be overwritten by
+ * fpu__init_system_xstate() if the CPU knows about xstates.
+ */
+static void __init fpu__init_system_xstate_size_legacy(void)
+{
+	static int on_boot_cpu = 1;
+
+	WARN_ON_FPU(!on_boot_cpu);
+	on_boot_cpu = 0;
+
+	/*
+	 * Note that xstate_size might be overwriten later during
+	 * fpu__init_system_xstate().
+	 */
+
+	if (!cpu_has_fpu) {
+		/*
+		 * Disable xsave as we do not support it if i387
+		 * emulation is enabled.
+		 */
+		setup_clear_cpu_cap(X86_FEATURE_XSAVE);
+		setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
+		xstate_size = sizeof(struct swregs_state);
+	} else {
+		if (cpu_has_fxsr)
+			xstate_size = sizeof(struct fxregs_state);
+		else
+			xstate_size = sizeof(struct fregs_state);
+	}
+	/*
+	 * Quirk: we don't yet handle the XSAVES* instructions
+	 * correctly, as we don't correctly convert between
+	 * standard and compacted format when interfacing
+	 * with user-space - so disable it for now.
+	 *
+	 * The difference is small: with recent CPUs the
+	 * compacted format is only marginally smaller than
+	 * the standard FPU state format.
+	 *
+	 * ( This is easy to backport while we are fixing
+	 *   XSAVES* support. )
+	 */
+	setup_clear_cpu_cap(X86_FEATURE_XSAVES);
+}
+
+/*
+ * FPU context switching strategies:
+ *
+ * Against popular belief, we don't do lazy FPU saves, due to the
+ * task migration complications it brings on SMP - we only do
+ * lazy FPU restores.
+ *
+ * 'lazy' is the traditional strategy, which is based on setting
+ * CR0::TS to 1 during context-switch (instead of doing a full
+ * restore of the FPU state), which causes the first FPU instruction
+ * after the context switch (whenever it is executed) to fault - at
+ * which point we lazily restore the FPU state into FPU registers.
+ *
+ * Tasks are of course under no obligation to execute FPU instructions,
+ * so it can easily happen that another context-switch occurs without
+ * a single FPU instruction being executed. If we eventually switch
+ * back to the original task (that still owns the FPU) then we have
+ * not only saved the restores along the way, but we also have the
+ * FPU ready to be used for the original task.
+ *
+ * 'eager' switching is used on modern CPUs, there we switch the FPU
+ * state during every context switch, regardless of whether the task
+ * has used FPU instructions in that time slice or not. This is done
+ * because modern FPU context saving instructions are able to optimize
+ * state saving and restoration in hardware: they can detect both
+ * unused and untouched FPU state and optimize accordingly.
+ *
+ * [ Note that even in 'lazy' mode we might optimize context switches
+ *   to use 'eager' restores, if we detect that a task is using the FPU
+ *   frequently. See the fpu->counter logic in fpu/internal.h for that. ]
+ */
+static enum { AUTO, ENABLE, DISABLE } eagerfpu = AUTO;
+
+static int __init eager_fpu_setup(char *s)
+{
+	if (!strcmp(s, "on"))
+		eagerfpu = ENABLE;
+	else if (!strcmp(s, "off"))
+		eagerfpu = DISABLE;
+	else if (!strcmp(s, "auto"))
+		eagerfpu = AUTO;
+	return 1;
+}
+__setup("eagerfpu=", eager_fpu_setup);
+
+/*
+ * Pick the FPU context switching strategy:
+ */
+static void __init fpu__init_system_ctx_switch(void)
+{
+	static bool on_boot_cpu = 1;
+
+	WARN_ON_FPU(!on_boot_cpu);
+	on_boot_cpu = 0;
+
+	WARN_ON_FPU(current->thread.fpu.fpstate_active);
+	current_thread_info()->status = 0;
+
+	/* Auto enable eagerfpu for xsaveopt */
+	if (cpu_has_xsaveopt && eagerfpu != DISABLE)
+		eagerfpu = ENABLE;
+
+	if (xfeatures_mask & XSTATE_EAGER) {
+		if (eagerfpu == DISABLE) {
+			pr_err("x86/fpu: eagerfpu switching disabled, disabling the following xstate features: 0x%llx.\n",
+			       xfeatures_mask & XSTATE_EAGER);
+			xfeatures_mask &= ~XSTATE_EAGER;
+		} else {
+			eagerfpu = ENABLE;
+		}
+	}
+
+	if (eagerfpu == ENABLE)
+		setup_force_cpu_cap(X86_FEATURE_EAGER_FPU);
+
+	printk(KERN_INFO "x86/fpu: Using '%s' FPU context switches.\n", eagerfpu == ENABLE ? "eager" : "lazy");
+}
+
+/*
+ * Called on the boot CPU once per system bootup, to set up the initial
+ * FPU state that is later cloned into all processes:
+ */
+void __init fpu__init_system(struct cpuinfo_x86 *c)
+{
+	fpu__init_system_early_generic(c);
+
+	/*
+	 * The FPU has to be operational for some of the
+	 * later FPU init activities:
+	 */
+	fpu__init_cpu();
+
+	/*
+	 * But don't leave CR0::TS set yet, as some of the FPU setup
+	 * methods depend on being able to execute FPU instructions
+	 * that will fault on a set TS, such as the FXSAVE in
+	 * fpu__init_system_mxcsr().
+	 */
+	clts();
+
+	fpu__init_system_generic();
+	fpu__init_system_xstate_size_legacy();
+	fpu__init_system_xstate();
+
+	fpu__init_system_ctx_switch();
+}
+
+/*
+ * Boot parameter to turn off FPU support and fall back to math-emu:
+ */
+static int __init no_387(char *s)
+{
+	setup_clear_cpu_cap(X86_FEATURE_FPU);
+	return 1;
+}
+__setup("no387", no_387);
+
+/*
+ * Disable all xstate CPU features:
+ */
+static int __init x86_noxsave_setup(char *s)
+{
+	if (strlen(s))
+		return 0;
+
+	setup_clear_cpu_cap(X86_FEATURE_XSAVE);
+	setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
+	setup_clear_cpu_cap(X86_FEATURE_XSAVES);
+	setup_clear_cpu_cap(X86_FEATURE_AVX);
+	setup_clear_cpu_cap(X86_FEATURE_AVX2);
+
+	return 1;
+}
+__setup("noxsave", x86_noxsave_setup);
+
+/*
+ * Disable the XSAVEOPT instruction specifically:
+ */
+static int __init x86_noxsaveopt_setup(char *s)
+{
+	setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
+
+	return 1;
+}
+__setup("noxsaveopt", x86_noxsaveopt_setup);
+
+/*
+ * Disable the XSAVES instruction:
+ */
+static int __init x86_noxsaves_setup(char *s)
+{
+	setup_clear_cpu_cap(X86_FEATURE_XSAVES);
+
+	return 1;
+}
+__setup("noxsaves", x86_noxsaves_setup);
+
+/*
+ * Disable FX save/restore and SSE support:
+ */
+static int __init x86_nofxsr_setup(char *s)
+{
+	setup_clear_cpu_cap(X86_FEATURE_FXSR);
+	setup_clear_cpu_cap(X86_FEATURE_FXSR_OPT);
+	setup_clear_cpu_cap(X86_FEATURE_XMM);
+
+	return 1;
+}
+__setup("nofxsr", x86_nofxsr_setup);
diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c
new file mode 100644
index 000000000000..dc60810c1c74
--- /dev/null
+++ b/arch/x86/kernel/fpu/regset.c
@@ -0,0 +1,356 @@
+/*
+ * FPU register's regset abstraction, for ptrace, core dumps, etc.
+ */
+#include <asm/fpu/internal.h>
+#include <asm/fpu/signal.h>
+#include <asm/fpu/regset.h>
+
+/*
+ * The xstateregs_active() routine is the same as the regset_fpregs_active() routine,
+ * as the "regset->n" for the xstate regset will be updated based on the feature
+ * capabilites supported by the xsave.
+ */
+int regset_fpregs_active(struct task_struct *target, const struct user_regset *regset)
+{
+	struct fpu *target_fpu = &target->thread.fpu;
+
+	return target_fpu->fpstate_active ? regset->n : 0;
+}
+
+int regset_xregset_fpregs_active(struct task_struct *target, const struct user_regset *regset)
+{
+	struct fpu *target_fpu = &target->thread.fpu;
+
+	return (cpu_has_fxsr && target_fpu->fpstate_active) ? regset->n : 0;
+}
+
+int xfpregs_get(struct task_struct *target, const struct user_regset *regset,
+		unsigned int pos, unsigned int count,
+		void *kbuf, void __user *ubuf)
+{
+	struct fpu *fpu = &target->thread.fpu;
+
+	if (!cpu_has_fxsr)
+		return -ENODEV;
+
+	fpu__activate_fpstate_read(fpu);
+	fpstate_sanitize_xstate(fpu);
+
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+				   &fpu->state.fxsave, 0, -1);
+}
+
+int xfpregs_set(struct task_struct *target, const struct user_regset *regset,
+		unsigned int pos, unsigned int count,
+		const void *kbuf, const void __user *ubuf)
+{
+	struct fpu *fpu = &target->thread.fpu;
+	int ret;
+
+	if (!cpu_has_fxsr)
+		return -ENODEV;
+
+	fpu__activate_fpstate_write(fpu);
+	fpstate_sanitize_xstate(fpu);
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 &fpu->state.fxsave, 0, -1);
+
+	/*
+	 * mxcsr reserved bits must be masked to zero for security reasons.
+	 */
+	fpu->state.fxsave.mxcsr &= mxcsr_feature_mask;
+
+	/*
+	 * update the header bits in the xsave header, indicating the
+	 * presence of FP and SSE state.
+	 */
+	if (cpu_has_xsave)
+		fpu->state.xsave.header.xfeatures |= XSTATE_FPSSE;
+
+	return ret;
+}
+
+int xstateregs_get(struct task_struct *target, const struct user_regset *regset,
+		unsigned int pos, unsigned int count,
+		void *kbuf, void __user *ubuf)
+{
+	struct fpu *fpu = &target->thread.fpu;
+	struct xregs_state *xsave;
+	int ret;
+
+	if (!cpu_has_xsave)
+		return -ENODEV;
+
+	fpu__activate_fpstate_read(fpu);
+
+	xsave = &fpu->state.xsave;
+
+	/*
+	 * Copy the 48bytes defined by the software first into the xstate
+	 * memory layout in the thread struct, so that we can copy the entire
+	 * xstateregs to the user using one user_regset_copyout().
+	 */
+	memcpy(&xsave->i387.sw_reserved,
+		xstate_fx_sw_bytes, sizeof(xstate_fx_sw_bytes));
+	/*
+	 * Copy the xstate memory layout.
+	 */
+	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, xsave, 0, -1);
+	return ret;
+}
+
+int xstateregs_set(struct task_struct *target, const struct user_regset *regset,
+		  unsigned int pos, unsigned int count,
+		  const void *kbuf, const void __user *ubuf)
+{
+	struct fpu *fpu = &target->thread.fpu;
+	struct xregs_state *xsave;
+	int ret;
+
+	if (!cpu_has_xsave)
+		return -ENODEV;
+
+	fpu__activate_fpstate_write(fpu);
+
+	xsave = &fpu->state.xsave;
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, xsave, 0, -1);
+	/*
+	 * mxcsr reserved bits must be masked to zero for security reasons.
+	 */
+	xsave->i387.mxcsr &= mxcsr_feature_mask;
+	xsave->header.xfeatures &= xfeatures_mask;
+	/*
+	 * These bits must be zero.
+	 */
+	memset(&xsave->header.reserved, 0, 48);
+
+	return ret;
+}
+
+#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
+
+/*
+ * FPU tag word conversions.
+ */
+
+static inline unsigned short twd_i387_to_fxsr(unsigned short twd)
+{
+	unsigned int tmp; /* to avoid 16 bit prefixes in the code */
+
+	/* Transform each pair of bits into 01 (valid) or 00 (empty) */
+	tmp = ~twd;
+	tmp = (tmp | (tmp>>1)) & 0x5555; /* 0V0V0V0V0V0V0V0V */
+	/* and move the valid bits to the lower byte. */
+	tmp = (tmp | (tmp >> 1)) & 0x3333; /* 00VV00VV00VV00VV */
+	tmp = (tmp | (tmp >> 2)) & 0x0f0f; /* 0000VVVV0000VVVV */
+	tmp = (tmp | (tmp >> 4)) & 0x00ff; /* 00000000VVVVVVVV */
+
+	return tmp;
+}
+
+#define FPREG_ADDR(f, n)	((void *)&(f)->st_space + (n) * 16)
+#define FP_EXP_TAG_VALID	0
+#define FP_EXP_TAG_ZERO		1
+#define FP_EXP_TAG_SPECIAL	2
+#define FP_EXP_TAG_EMPTY	3
+
+static inline u32 twd_fxsr_to_i387(struct fxregs_state *fxsave)
+{
+	struct _fpxreg *st;
+	u32 tos = (fxsave->swd >> 11) & 7;
+	u32 twd = (unsigned long) fxsave->twd;
+	u32 tag;
+	u32 ret = 0xffff0000u;
+	int i;
+
+	for (i = 0; i < 8; i++, twd >>= 1) {
+		if (twd & 0x1) {
+			st = FPREG_ADDR(fxsave, (i - tos) & 7);
+
+			switch (st->exponent & 0x7fff) {
+			case 0x7fff:
+				tag = FP_EXP_TAG_SPECIAL;
+				break;
+			case 0x0000:
+				if (!st->significand[0] &&
+				    !st->significand[1] &&
+				    !st->significand[2] &&
+				    !st->significand[3])
+					tag = FP_EXP_TAG_ZERO;
+				else
+					tag = FP_EXP_TAG_SPECIAL;
+				break;
+			default:
+				if (st->significand[3] & 0x8000)
+					tag = FP_EXP_TAG_VALID;
+				else
+					tag = FP_EXP_TAG_SPECIAL;
+				break;
+			}
+		} else {
+			tag = FP_EXP_TAG_EMPTY;
+		}
+		ret |= tag << (2 * i);
+	}
+	return ret;
+}
+
+/*
+ * FXSR floating point environment conversions.
+ */
+
+void
+convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk)
+{
+	struct fxregs_state *fxsave = &tsk->thread.fpu.state.fxsave;
+	struct _fpreg *to = (struct _fpreg *) &env->st_space[0];
+	struct _fpxreg *from = (struct _fpxreg *) &fxsave->st_space[0];
+	int i;
+
+	env->cwd = fxsave->cwd | 0xffff0000u;
+	env->swd = fxsave->swd | 0xffff0000u;
+	env->twd = twd_fxsr_to_i387(fxsave);
+
+#ifdef CONFIG_X86_64
+	env->fip = fxsave->rip;
+	env->foo = fxsave->rdp;
+	/*
+	 * should be actually ds/cs at fpu exception time, but
+	 * that information is not available in 64bit mode.
+	 */
+	env->fcs = task_pt_regs(tsk)->cs;
+	if (tsk == current) {
+		savesegment(ds, env->fos);
+	} else {
+		env->fos = tsk->thread.ds;
+	}
+	env->fos |= 0xffff0000;
+#else
+	env->fip = fxsave->fip;
+	env->fcs = (u16) fxsave->fcs | ((u32) fxsave->fop << 16);
+	env->foo = fxsave->foo;
+	env->fos = fxsave->fos;
+#endif
+
+	for (i = 0; i < 8; ++i)
+		memcpy(&to[i], &from[i], sizeof(to[0]));
+}
+
+void convert_to_fxsr(struct task_struct *tsk,
+		     const struct user_i387_ia32_struct *env)
+
+{
+	struct fxregs_state *fxsave = &tsk->thread.fpu.state.fxsave;
+	struct _fpreg *from = (struct _fpreg *) &env->st_space[0];
+	struct _fpxreg *to = (struct _fpxreg *) &fxsave->st_space[0];
+	int i;
+
+	fxsave->cwd = env->cwd;
+	fxsave->swd = env->swd;
+	fxsave->twd = twd_i387_to_fxsr(env->twd);
+	fxsave->fop = (u16) ((u32) env->fcs >> 16);
+#ifdef CONFIG_X86_64
+	fxsave->rip = env->fip;
+	fxsave->rdp = env->foo;
+	/* cs and ds ignored */
+#else
+	fxsave->fip = env->fip;
+	fxsave->fcs = (env->fcs & 0xffff);
+	fxsave->foo = env->foo;
+	fxsave->fos = env->fos;
+#endif
+
+	for (i = 0; i < 8; ++i)
+		memcpy(&to[i], &from[i], sizeof(from[0]));
+}
+
+int fpregs_get(struct task_struct *target, const struct user_regset *regset,
+	       unsigned int pos, unsigned int count,
+	       void *kbuf, void __user *ubuf)
+{
+	struct fpu *fpu = &target->thread.fpu;
+	struct user_i387_ia32_struct env;
+
+	fpu__activate_fpstate_read(fpu);
+
+	if (!static_cpu_has(X86_FEATURE_FPU))
+		return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf);
+
+	if (!cpu_has_fxsr)
+		return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+					   &fpu->state.fsave, 0,
+					   -1);
+
+	fpstate_sanitize_xstate(fpu);
+
+	if (kbuf && pos == 0 && count == sizeof(env)) {
+		convert_from_fxsr(kbuf, target);
+		return 0;
+	}
+
+	convert_from_fxsr(&env, target);
+
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &env, 0, -1);
+}
+
+int fpregs_set(struct task_struct *target, const struct user_regset *regset,
+	       unsigned int pos, unsigned int count,
+	       const void *kbuf, const void __user *ubuf)
+{
+	struct fpu *fpu = &target->thread.fpu;
+	struct user_i387_ia32_struct env;
+	int ret;
+
+	fpu__activate_fpstate_write(fpu);
+	fpstate_sanitize_xstate(fpu);
+
+	if (!static_cpu_has(X86_FEATURE_FPU))
+		return fpregs_soft_set(target, regset, pos, count, kbuf, ubuf);
+
+	if (!cpu_has_fxsr)
+		return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+					  &fpu->state.fsave, 0,
+					  -1);
+
+	if (pos > 0 || count < sizeof(env))
+		convert_from_fxsr(&env, target);
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &env, 0, -1);
+	if (!ret)
+		convert_to_fxsr(target, &env);
+
+	/*
+	 * update the header bit in the xsave header, indicating the
+	 * presence of FP.
+	 */
+	if (cpu_has_xsave)
+		fpu->state.xsave.header.xfeatures |= XSTATE_FP;
+	return ret;
+}
+
+/*
+ * FPU state for core dumps.
+ * This is only used for a.out dumps now.
+ * It is declared generically using elf_fpregset_t (which is
+ * struct user_i387_struct) but is in fact only used for 32-bit
+ * dumps, so on 64-bit it is really struct user_i387_ia32_struct.
+ */
+int dump_fpu(struct pt_regs *regs, struct user_i387_struct *ufpu)
+{
+	struct task_struct *tsk = current;
+	struct fpu *fpu = &tsk->thread.fpu;
+	int fpvalid;
+
+	fpvalid = fpu->fpstate_active;
+	if (fpvalid)
+		fpvalid = !fpregs_get(tsk, NULL,
+				      0, sizeof(struct user_i387_ia32_struct),
+				      ufpu, NULL);
+
+	return fpvalid;
+}
+EXPORT_SYMBOL(dump_fpu);
+
+#endif	/* CONFIG_X86_32 || CONFIG_IA32_EMULATION */
diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
new file mode 100644
index 000000000000..50ec9af1bd51
--- /dev/null
+++ b/arch/x86/kernel/fpu/signal.c
@@ -0,0 +1,404 @@
+/*
+ * FPU signal frame handling routines.
+ */
+
+#include <linux/compat.h>
+#include <linux/cpu.h>
+
+#include <asm/fpu/internal.h>
+#include <asm/fpu/signal.h>
+#include <asm/fpu/regset.h>
+
+#include <asm/sigframe.h>
+
+static struct _fpx_sw_bytes fx_sw_reserved, fx_sw_reserved_ia32;
+
+/*
+ * Check for the presence of extended state information in the
+ * user fpstate pointer in the sigcontext.
+ */
+static inline int check_for_xstate(struct fxregs_state __user *buf,
+				   void __user *fpstate,
+				   struct _fpx_sw_bytes *fx_sw)
+{
+	int min_xstate_size = sizeof(struct fxregs_state) +
+			      sizeof(struct xstate_header);
+	unsigned int magic2;
+
+	if (__copy_from_user(fx_sw, &buf->sw_reserved[0], sizeof(*fx_sw)))
+		return -1;
+
+	/* Check for the first magic field and other error scenarios. */
+	if (fx_sw->magic1 != FP_XSTATE_MAGIC1 ||
+	    fx_sw->xstate_size < min_xstate_size ||
+	    fx_sw->xstate_size > xstate_size ||
+	    fx_sw->xstate_size > fx_sw->extended_size)
+		return -1;
+
+	/*
+	 * Check for the presence of second magic word at the end of memory
+	 * layout. This detects the case where the user just copied the legacy
+	 * fpstate layout with out copying the extended state information
+	 * in the memory layout.
+	 */
+	if (__get_user(magic2, (__u32 __user *)(fpstate + fx_sw->xstate_size))
+	    || magic2 != FP_XSTATE_MAGIC2)
+		return -1;
+
+	return 0;
+}
+
+/*
+ * Signal frame handlers.
+ */
+static inline int save_fsave_header(struct task_struct *tsk, void __user *buf)
+{
+	if (use_fxsr()) {
+		struct xregs_state *xsave = &tsk->thread.fpu.state.xsave;
+		struct user_i387_ia32_struct env;
+		struct _fpstate_ia32 __user *fp = buf;
+
+		convert_from_fxsr(&env, tsk);
+
+		if (__copy_to_user(buf, &env, sizeof(env)) ||
+		    __put_user(xsave->i387.swd, &fp->status) ||
+		    __put_user(X86_FXSR_MAGIC, &fp->magic))
+			return -1;
+	} else {
+		struct fregs_state __user *fp = buf;
+		u32 swd;
+		if (__get_user(swd, &fp->swd) || __put_user(swd, &fp->status))
+			return -1;
+	}
+
+	return 0;
+}
+
+static inline int save_xstate_epilog(void __user *buf, int ia32_frame)
+{
+	struct xregs_state __user *x = buf;
+	struct _fpx_sw_bytes *sw_bytes;
+	u32 xfeatures;
+	int err;
+
+	/* Setup the bytes not touched by the [f]xsave and reserved for SW. */
+	sw_bytes = ia32_frame ? &fx_sw_reserved_ia32 : &fx_sw_reserved;
+	err = __copy_to_user(&x->i387.sw_reserved, sw_bytes, sizeof(*sw_bytes));
+
+	if (!use_xsave())
+		return err;
+
+	err |= __put_user(FP_XSTATE_MAGIC2, (__u32 *)(buf + xstate_size));
+
+	/*
+	 * Read the xfeatures which we copied (directly from the cpu or
+	 * from the state in task struct) to the user buffers.
+	 */
+	err |= __get_user(xfeatures, (__u32 *)&x->header.xfeatures);
+
+	/*
+	 * For legacy compatible, we always set FP/SSE bits in the bit
+	 * vector while saving the state to the user context. This will
+	 * enable us capturing any changes(during sigreturn) to
+	 * the FP/SSE bits by the legacy applications which don't touch
+	 * xfeatures in the xsave header.
+	 *
+	 * xsave aware apps can change the xfeatures in the xsave
+	 * header as well as change any contents in the memory layout.
+	 * xrestore as part of sigreturn will capture all the changes.
+	 */
+	xfeatures |= XSTATE_FPSSE;
+
+	err |= __put_user(xfeatures, (__u32 *)&x->header.xfeatures);
+
+	return err;
+}
+
+static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf)
+{
+	int err;
+
+	if (use_xsave())
+		err = copy_xregs_to_user(buf);
+	else if (use_fxsr())
+		err = copy_fxregs_to_user((struct fxregs_state __user *) buf);
+	else
+		err = copy_fregs_to_user((struct fregs_state __user *) buf);
+
+	if (unlikely(err) && __clear_user(buf, xstate_size))
+		err = -EFAULT;
+	return err;
+}
+
+/*
+ * Save the fpu, extended register state to the user signal frame.
+ *
+ * 'buf_fx' is the 64-byte aligned pointer at which the [f|fx|x]save
+ *  state is copied.
+ *  'buf' points to the 'buf_fx' or to the fsave header followed by 'buf_fx'.
+ *
+ *	buf == buf_fx for 64-bit frames and 32-bit fsave frame.
+ *	buf != buf_fx for 32-bit frames with fxstate.
+ *
+ * If the fpu, extended register state is live, save the state directly
+ * to the user frame pointed by the aligned pointer 'buf_fx'. Otherwise,
+ * copy the thread's fpu state to the user frame starting at 'buf_fx'.
+ *
+ * If this is a 32-bit frame with fxstate, put a fsave header before
+ * the aligned state at 'buf_fx'.
+ *
+ * For [f]xsave state, update the SW reserved fields in the [f]xsave frame
+ * indicating the absence/presence of the extended state to the user.
+ */
+int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size)
+{
+	struct xregs_state *xsave = &current->thread.fpu.state.xsave;
+	struct task_struct *tsk = current;
+	int ia32_fxstate = (buf != buf_fx);
+
+	ia32_fxstate &= (config_enabled(CONFIG_X86_32) ||
+			 config_enabled(CONFIG_IA32_EMULATION));
+
+	if (!access_ok(VERIFY_WRITE, buf, size))
+		return -EACCES;
+
+	if (!static_cpu_has(X86_FEATURE_FPU))
+		return fpregs_soft_get(current, NULL, 0,
+			sizeof(struct user_i387_ia32_struct), NULL,
+			(struct _fpstate_ia32 __user *) buf) ? -1 : 1;
+
+	if (fpregs_active()) {
+		/* Save the live register state to the user directly. */
+		if (copy_fpregs_to_sigframe(buf_fx))
+			return -1;
+		/* Update the thread's fxstate to save the fsave header. */
+		if (ia32_fxstate)
+			copy_fxregs_to_kernel(&tsk->thread.fpu);
+	} else {
+		fpstate_sanitize_xstate(&tsk->thread.fpu);
+		if (__copy_to_user(buf_fx, xsave, xstate_size))
+			return -1;
+	}
+
+	/* Save the fsave header for the 32-bit frames. */
+	if ((ia32_fxstate || !use_fxsr()) && save_fsave_header(tsk, buf))
+		return -1;
+
+	if (use_fxsr() && save_xstate_epilog(buf_fx, ia32_fxstate))
+		return -1;
+
+	return 0;
+}
+
+static inline void
+sanitize_restored_xstate(struct task_struct *tsk,
+			 struct user_i387_ia32_struct *ia32_env,
+			 u64 xfeatures, int fx_only)
+{
+	struct xregs_state *xsave = &tsk->thread.fpu.state.xsave;
+	struct xstate_header *header = &xsave->header;
+
+	if (use_xsave()) {
+		/* These bits must be zero. */
+		memset(header->reserved, 0, 48);
+
+		/*
+		 * Init the state that is not present in the memory
+		 * layout and not enabled by the OS.
+		 */
+		if (fx_only)
+			header->xfeatures = XSTATE_FPSSE;
+		else
+			header->xfeatures &= (xfeatures_mask & xfeatures);
+	}
+
+	if (use_fxsr()) {
+		/*
+		 * mscsr reserved bits must be masked to zero for security
+		 * reasons.
+		 */
+		xsave->i387.mxcsr &= mxcsr_feature_mask;
+
+		convert_to_fxsr(tsk, ia32_env);
+	}
+}
+
+/*
+ * Restore the extended state if present. Otherwise, restore the FP/SSE state.
+ */
+static inline int copy_user_to_fpregs_zeroing(void __user *buf, u64 xbv, int fx_only)
+{
+	if (use_xsave()) {
+		if ((unsigned long)buf % 64 || fx_only) {
+			u64 init_bv = xfeatures_mask & ~XSTATE_FPSSE;
+			copy_kernel_to_xregs(&init_fpstate.xsave, init_bv);
+			return copy_user_to_fxregs(buf);
+		} else {
+			u64 init_bv = xfeatures_mask & ~xbv;
+			if (unlikely(init_bv))
+				copy_kernel_to_xregs(&init_fpstate.xsave, init_bv);
+			return copy_user_to_xregs(buf, xbv);
+		}
+	} else if (use_fxsr()) {
+		return copy_user_to_fxregs(buf);
+	} else
+		return copy_user_to_fregs(buf);
+}
+
+static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
+{
+	int ia32_fxstate = (buf != buf_fx);
+	struct task_struct *tsk = current;
+	struct fpu *fpu = &tsk->thread.fpu;
+	int state_size = xstate_size;
+	u64 xfeatures = 0;
+	int fx_only = 0;
+
+	ia32_fxstate &= (config_enabled(CONFIG_X86_32) ||
+			 config_enabled(CONFIG_IA32_EMULATION));
+
+	if (!buf) {
+		fpu__clear(fpu);
+		return 0;
+	}
+
+	if (!access_ok(VERIFY_READ, buf, size))
+		return -EACCES;
+
+	fpu__activate_curr(fpu);
+
+	if (!static_cpu_has(X86_FEATURE_FPU))
+		return fpregs_soft_set(current, NULL,
+				       0, sizeof(struct user_i387_ia32_struct),
+				       NULL, buf) != 0;
+
+	if (use_xsave()) {
+		struct _fpx_sw_bytes fx_sw_user;
+		if (unlikely(check_for_xstate(buf_fx, buf_fx, &fx_sw_user))) {
+			/*
+			 * Couldn't find the extended state information in the
+			 * memory layout. Restore just the FP/SSE and init all
+			 * the other extended state.
+			 */
+			state_size = sizeof(struct fxregs_state);
+			fx_only = 1;
+		} else {
+			state_size = fx_sw_user.xstate_size;
+			xfeatures = fx_sw_user.xfeatures;
+		}
+	}
+
+	if (ia32_fxstate) {
+		/*
+		 * For 32-bit frames with fxstate, copy the user state to the
+		 * thread's fpu state, reconstruct fxstate from the fsave
+		 * header. Sanitize the copied state etc.
+		 */
+		struct fpu *fpu = &tsk->thread.fpu;
+		struct user_i387_ia32_struct env;
+		int err = 0;
+
+		/*
+		 * Drop the current fpu which clears fpu->fpstate_active. This ensures
+		 * that any context-switch during the copy of the new state,
+		 * avoids the intermediate state from getting restored/saved.
+		 * Thus avoiding the new restored state from getting corrupted.
+		 * We will be ready to restore/save the state only after
+		 * fpu->fpstate_active is again set.
+		 */
+		fpu__drop(fpu);
+
+		if (__copy_from_user(&fpu->state.xsave, buf_fx, state_size) ||
+		    __copy_from_user(&env, buf, sizeof(env))) {
+			fpstate_init(&fpu->state);
+			err = -1;
+		} else {
+			sanitize_restored_xstate(tsk, &env, xfeatures, fx_only);
+		}
+
+		fpu->fpstate_active = 1;
+		if (use_eager_fpu()) {
+			preempt_disable();
+			fpu__restore(fpu);
+			preempt_enable();
+		}
+
+		return err;
+	} else {
+		/*
+		 * For 64-bit frames and 32-bit fsave frames, restore the user
+		 * state to the registers directly (with exceptions handled).
+		 */
+		user_fpu_begin();
+		if (copy_user_to_fpregs_zeroing(buf_fx, xfeatures, fx_only)) {
+			fpu__clear(fpu);
+			return -1;
+		}
+	}
+
+	return 0;
+}
+
+static inline int xstate_sigframe_size(void)
+{
+	return use_xsave() ? xstate_size + FP_XSTATE_MAGIC2_SIZE : xstate_size;
+}
+
+/*
+ * Restore FPU state from a sigframe:
+ */
+int fpu__restore_sig(void __user *buf, int ia32_frame)
+{
+	void __user *buf_fx = buf;
+	int size = xstate_sigframe_size();
+
+	if (ia32_frame && use_fxsr()) {
+		buf_fx = buf + sizeof(struct fregs_state);
+		size += sizeof(struct fregs_state);
+	}
+
+	return __fpu__restore_sig(buf, buf_fx, size);
+}
+
+unsigned long
+fpu__alloc_mathframe(unsigned long sp, int ia32_frame,
+		     unsigned long *buf_fx, unsigned long *size)
+{
+	unsigned long frame_size = xstate_sigframe_size();
+
+	*buf_fx = sp = round_down(sp - frame_size, 64);
+	if (ia32_frame && use_fxsr()) {
+		frame_size += sizeof(struct fregs_state);
+		sp -= sizeof(struct fregs_state);
+	}
+
+	*size = frame_size;
+
+	return sp;
+}
+/*
+ * Prepare the SW reserved portion of the fxsave memory layout, indicating
+ * the presence of the extended state information in the memory layout
+ * pointed by the fpstate pointer in the sigcontext.
+ * This will be saved when ever the FP and extended state context is
+ * saved on the user stack during the signal handler delivery to the user.
+ */
+void fpu__init_prepare_fx_sw_frame(void)
+{
+	int fsave_header_size = sizeof(struct fregs_state);
+	int size = xstate_size + FP_XSTATE_MAGIC2_SIZE;
+
+	if (config_enabled(CONFIG_X86_32))
+		size += fsave_header_size;
+
+	fx_sw_reserved.magic1 = FP_XSTATE_MAGIC1;
+	fx_sw_reserved.extended_size = size;
+	fx_sw_reserved.xfeatures = xfeatures_mask;
+	fx_sw_reserved.xstate_size = xstate_size;
+
+	if (config_enabled(CONFIG_IA32_EMULATION)) {
+		fx_sw_reserved_ia32 = fx_sw_reserved;
+		fx_sw_reserved_ia32.extended_size += fsave_header_size;
+	}
+}
+
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
new file mode 100644
index 000000000000..62fc001c7846
--- /dev/null
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -0,0 +1,461 @@
+/*
+ * xsave/xrstor support.
+ *
+ * Author: Suresh Siddha <suresh.b.siddha@intel.com>
+ */
+#include <linux/compat.h>
+#include <linux/cpu.h>
+
+#include <asm/fpu/api.h>
+#include <asm/fpu/internal.h>
+#include <asm/fpu/signal.h>
+#include <asm/fpu/regset.h>
+
+#include <asm/tlbflush.h>
+
+static const char *xfeature_names[] =
+{
+	"x87 floating point registers"	,
+	"SSE registers"			,
+	"AVX registers"			,
+	"MPX bounds registers"		,
+	"MPX CSR"			,
+	"AVX-512 opmask"		,
+	"AVX-512 Hi256"			,
+	"AVX-512 ZMM_Hi256"		,
+	"unknown xstate feature"	,
+};
+
+/*
+ * Mask of xstate features supported by the CPU and the kernel:
+ */
+u64 xfeatures_mask __read_mostly;
+
+static unsigned int xstate_offsets[XFEATURES_NR_MAX] = { [ 0 ... XFEATURES_NR_MAX - 1] = -1};
+static unsigned int xstate_sizes[XFEATURES_NR_MAX]   = { [ 0 ... XFEATURES_NR_MAX - 1] = -1};
+static unsigned int xstate_comp_offsets[sizeof(xfeatures_mask)*8];
+
+/* The number of supported xfeatures in xfeatures_mask: */
+static unsigned int xfeatures_nr;
+
+/*
+ * Return whether the system supports a given xfeature.
+ *
+ * Also return the name of the (most advanced) feature that the caller requested:
+ */
+int cpu_has_xfeatures(u64 xfeatures_needed, const char **feature_name)
+{
+	u64 xfeatures_missing = xfeatures_needed & ~xfeatures_mask;
+
+	if (unlikely(feature_name)) {
+		long xfeature_idx, max_idx;
+		u64 xfeatures_print;
+		/*
+		 * So we use FLS here to be able to print the most advanced
+		 * feature that was requested but is missing. So if a driver
+		 * asks about "XSTATE_SSE | XSTATE_YMM" we'll print the
+		 * missing AVX feature - this is the most informative message
+		 * to users:
+		 */
+		if (xfeatures_missing)
+			xfeatures_print = xfeatures_missing;
+		else
+			xfeatures_print = xfeatures_needed;
+
+		xfeature_idx = fls64(xfeatures_print)-1;
+		max_idx = ARRAY_SIZE(xfeature_names)-1;
+		xfeature_idx = min(xfeature_idx, max_idx);
+
+		*feature_name = xfeature_names[xfeature_idx];
+	}
+
+	if (xfeatures_missing)
+		return 0;
+
+	return 1;
+}
+EXPORT_SYMBOL_GPL(cpu_has_xfeatures);
+
+/*
+ * When executing XSAVEOPT (or other optimized XSAVE instructions), if
+ * a processor implementation detects that an FPU state component is still
+ * (or is again) in its initialized state, it may clear the corresponding
+ * bit in the header.xfeatures field, and can skip the writeout of registers
+ * to the corresponding memory layout.
+ *
+ * This means that when the bit is zero, the state component might still contain
+ * some previous - non-initialized register state.
+ *
+ * Before writing xstate information to user-space we sanitize those components,
+ * to always ensure that the memory layout of a feature will be in the init state
+ * if the corresponding header bit is zero. This is to ensure that user-space doesn't
+ * see some stale state in the memory layout during signal handling, debugging etc.
+ */
+void fpstate_sanitize_xstate(struct fpu *fpu)
+{
+	struct fxregs_state *fx = &fpu->state.fxsave;
+	int feature_bit;
+	u64 xfeatures;
+
+	if (!use_xsaveopt())
+		return;
+
+	xfeatures = fpu->state.xsave.header.xfeatures;
+
+	/*
+	 * None of the feature bits are in init state. So nothing else
+	 * to do for us, as the memory layout is up to date.
+	 */
+	if ((xfeatures & xfeatures_mask) == xfeatures_mask)
+		return;
+
+	/*
+	 * FP is in init state
+	 */
+	if (!(xfeatures & XSTATE_FP)) {
+		fx->cwd = 0x37f;
+		fx->swd = 0;
+		fx->twd = 0;
+		fx->fop = 0;
+		fx->rip = 0;
+		fx->rdp = 0;
+		memset(&fx->st_space[0], 0, 128);
+	}
+
+	/*
+	 * SSE is in init state
+	 */
+	if (!(xfeatures & XSTATE_SSE))
+		memset(&fx->xmm_space[0], 0, 256);
+
+	/*
+	 * First two features are FPU and SSE, which above we handled
+	 * in a special way already:
+	 */
+	feature_bit = 0x2;
+	xfeatures = (xfeatures_mask & ~xfeatures) >> 2;
+
+	/*
+	 * Update all the remaining memory layouts according to their
+	 * standard xstate layout, if their header bit is in the init
+	 * state:
+	 */
+	while (xfeatures) {
+		if (xfeatures & 0x1) {
+			int offset = xstate_offsets[feature_bit];
+			int size = xstate_sizes[feature_bit];
+
+			memcpy((void *)fx + offset,
+			       (void *)&init_fpstate.xsave + offset,
+			       size);
+		}
+
+		xfeatures >>= 1;
+		feature_bit++;
+	}
+}
+
+/*
+ * Enable the extended processor state save/restore feature.
+ * Called once per CPU onlining.
+ */
+void fpu__init_cpu_xstate(void)
+{
+	if (!cpu_has_xsave || !xfeatures_mask)
+		return;
+
+	cr4_set_bits(X86_CR4_OSXSAVE);
+	xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask);
+}
+
+/*
+ * Record the offsets and sizes of various xstates contained
+ * in the XSAVE state memory layout.
+ *
+ * ( Note that certain features might be non-present, for them
+ *   we'll have 0 offset and 0 size. )
+ */
+static void __init setup_xstate_features(void)
+{
+	u32 eax, ebx, ecx, edx, leaf;
+
+	xfeatures_nr = fls64(xfeatures_mask);
+
+	for (leaf = 2; leaf < xfeatures_nr; leaf++) {
+		cpuid_count(XSTATE_CPUID, leaf, &eax, &ebx, &ecx, &edx);
+
+		xstate_offsets[leaf] = ebx;
+		xstate_sizes[leaf] = eax;
+
+		printk(KERN_INFO "x86/fpu: xstate_offset[%d]: %04x, xstate_sizes[%d]: %04x\n", leaf, ebx, leaf, eax);
+	}
+}
+
+static void __init print_xstate_feature(u64 xstate_mask)
+{
+	const char *feature_name;
+
+	if (cpu_has_xfeatures(xstate_mask, &feature_name))
+		pr_info("x86/fpu: Supporting XSAVE feature 0x%02Lx: '%s'\n", xstate_mask, feature_name);
+}
+
+/*
+ * Print out all the supported xstate features:
+ */
+static void __init print_xstate_features(void)
+{
+	print_xstate_feature(XSTATE_FP);
+	print_xstate_feature(XSTATE_SSE);
+	print_xstate_feature(XSTATE_YMM);
+	print_xstate_feature(XSTATE_BNDREGS);
+	print_xstate_feature(XSTATE_BNDCSR);
+	print_xstate_feature(XSTATE_OPMASK);
+	print_xstate_feature(XSTATE_ZMM_Hi256);
+	print_xstate_feature(XSTATE_Hi16_ZMM);
+}
+
+/*
+ * This function sets up offsets and sizes of all extended states in
+ * xsave area. This supports both standard format and compacted format
+ * of the xsave aread.
+ */
+static void __init setup_xstate_comp(void)
+{
+	unsigned int xstate_comp_sizes[sizeof(xfeatures_mask)*8];
+	int i;
+
+	/*
+	 * The FP xstates and SSE xstates are legacy states. They are always
+	 * in the fixed offsets in the xsave area in either compacted form
+	 * or standard form.
+	 */
+	xstate_comp_offsets[0] = 0;
+	xstate_comp_offsets[1] = offsetof(struct fxregs_state, xmm_space);
+
+	if (!cpu_has_xsaves) {
+		for (i = 2; i < xfeatures_nr; i++) {
+			if (test_bit(i, (unsigned long *)&xfeatures_mask)) {
+				xstate_comp_offsets[i] = xstate_offsets[i];
+				xstate_comp_sizes[i] = xstate_sizes[i];
+			}
+		}
+		return;
+	}
+
+	xstate_comp_offsets[2] = FXSAVE_SIZE + XSAVE_HDR_SIZE;
+
+	for (i = 2; i < xfeatures_nr; i++) {
+		if (test_bit(i, (unsigned long *)&xfeatures_mask))
+			xstate_comp_sizes[i] = xstate_sizes[i];
+		else
+			xstate_comp_sizes[i] = 0;
+
+		if (i > 2)
+			xstate_comp_offsets[i] = xstate_comp_offsets[i-1]
+					+ xstate_comp_sizes[i-1];
+
+	}
+}
+
+/*
+ * setup the xstate image representing the init state
+ */
+static void __init setup_init_fpu_buf(void)
+{
+	static int on_boot_cpu = 1;
+
+	WARN_ON_FPU(!on_boot_cpu);
+	on_boot_cpu = 0;
+
+	if (!cpu_has_xsave)
+		return;
+
+	setup_xstate_features();
+	print_xstate_features();
+
+	if (cpu_has_xsaves) {
+		init_fpstate.xsave.header.xcomp_bv = (u64)1 << 63 | xfeatures_mask;
+		init_fpstate.xsave.header.xfeatures = xfeatures_mask;
+	}
+
+	/*
+	 * Init all the features state with header_bv being 0x0
+	 */
+	copy_kernel_to_xregs_booting(&init_fpstate.xsave);
+
+	/*
+	 * Dump the init state again. This is to identify the init state
+	 * of any feature which is not represented by all zero's.
+	 */
+	copy_xregs_to_kernel_booting(&init_fpstate.xsave);
+}
+
+/*
+ * Calculate total size of enabled xstates in XCR0/xfeatures_mask.
+ */
+static void __init init_xstate_size(void)
+{
+	unsigned int eax, ebx, ecx, edx;
+	int i;
+
+	if (!cpu_has_xsaves) {
+		cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx);
+		xstate_size = ebx;
+		return;
+	}
+
+	xstate_size = FXSAVE_SIZE + XSAVE_HDR_SIZE;
+	for (i = 2; i < 64; i++) {
+		if (test_bit(i, (unsigned long *)&xfeatures_mask)) {
+			cpuid_count(XSTATE_CPUID, i, &eax, &ebx, &ecx, &edx);
+			xstate_size += eax;
+		}
+	}
+}
+
+/*
+ * Enable and initialize the xsave feature.
+ * Called once per system bootup.
+ */
+void __init fpu__init_system_xstate(void)
+{
+	unsigned int eax, ebx, ecx, edx;
+	static int on_boot_cpu = 1;
+
+	WARN_ON_FPU(!on_boot_cpu);
+	on_boot_cpu = 0;
+
+	if (!cpu_has_xsave) {
+		pr_info("x86/fpu: Legacy x87 FPU detected.\n");
+		return;
+	}
+
+	if (boot_cpu_data.cpuid_level < XSTATE_CPUID) {
+		WARN_ON_FPU(1);
+		return;
+	}
+
+	cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx);
+	xfeatures_mask = eax + ((u64)edx << 32);
+
+	if ((xfeatures_mask & XSTATE_FPSSE) != XSTATE_FPSSE) {
+		pr_err("x86/fpu: FP/SSE not present amongst the CPU's xstate features: 0x%llx.\n", xfeatures_mask);
+		BUG();
+	}
+
+	/* Support only the state known to the OS: */
+	xfeatures_mask = xfeatures_mask & XCNTXT_MASK;
+
+	/* Enable xstate instructions to be able to continue with initialization: */
+	fpu__init_cpu_xstate();
+
+	/* Recompute the context size for enabled features: */
+	init_xstate_size();
+
+	update_regset_xstate_info(xstate_size, xfeatures_mask);
+	fpu__init_prepare_fx_sw_frame();
+	setup_init_fpu_buf();
+	setup_xstate_comp();
+
+	pr_info("x86/fpu: Enabled xstate features 0x%llx, context size is 0x%x bytes, using '%s' format.\n",
+		xfeatures_mask,
+		xstate_size,
+		cpu_has_xsaves ? "compacted" : "standard");
+}
+
+/*
+ * Restore minimal FPU state after suspend:
+ */
+void fpu__resume_cpu(void)
+{
+	/*
+	 * Restore XCR0 on xsave capable CPUs:
+	 */
+	if (cpu_has_xsave)
+		xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask);
+}
+
+/*
+ * Given the xsave area and a state inside, this function returns the
+ * address of the state.
+ *
+ * This is the API that is called to get xstate address in either
+ * standard format or compacted format of xsave area.
+ *
+ * Note that if there is no data for the field in the xsave buffer
+ * this will return NULL.
+ *
+ * Inputs:
+ *	xstate: the thread's storage area for all FPU data
+ *	xstate_feature: state which is defined in xsave.h (e.g.
+ *	XSTATE_FP, XSTATE_SSE, etc...)
+ * Output:
+ *	address of the state in the xsave area, or NULL if the
+ *	field is not present in the xsave buffer.
+ */
+void *get_xsave_addr(struct xregs_state *xsave, int xstate_feature)
+{
+	int feature_nr = fls64(xstate_feature) - 1;
+	/*
+	 * Do we even *have* xsave state?
+	 */
+	if (!boot_cpu_has(X86_FEATURE_XSAVE))
+		return NULL;
+
+	xsave = &current->thread.fpu.state.xsave;
+	/*
+	 * We should not ever be requesting features that we
+	 * have not enabled.  Remember that pcntxt_mask is
+	 * what we write to the XCR0 register.
+	 */
+	WARN_ONCE(!(xfeatures_mask & xstate_feature),
+		  "get of unsupported state");
+	/*
+	 * This assumes the last 'xsave*' instruction to
+	 * have requested that 'xstate_feature' be saved.
+	 * If it did not, we might be seeing and old value
+	 * of the field in the buffer.
+	 *
+	 * This can happen because the last 'xsave' did not
+	 * request that this feature be saved (unlikely)
+	 * or because the "init optimization" caused it
+	 * to not be saved.
+	 */
+	if (!(xsave->header.xfeatures & xstate_feature))
+		return NULL;
+
+	return (void *)xsave + xstate_comp_offsets[feature_nr];
+}
+EXPORT_SYMBOL_GPL(get_xsave_addr);
+
+/*
+ * This wraps up the common operations that need to occur when retrieving
+ * data from xsave state.  It first ensures that the current task was
+ * using the FPU and retrieves the data in to a buffer.  It then calculates
+ * the offset of the requested field in the buffer.
+ *
+ * This function is safe to call whether the FPU is in use or not.
+ *
+ * Note that this only works on the current task.
+ *
+ * Inputs:
+ *	@xsave_state: state which is defined in xsave.h (e.g. XSTATE_FP,
+ *	XSTATE_SSE, etc...)
+ * Output:
+ *	address of the state in the xsave area or NULL if the state
+ *	is not present or is in its 'init state'.
+ */
+const void *get_xsave_field_ptr(int xsave_state)
+{
+	struct fpu *fpu = &current->thread.fpu;
+
+	if (!fpu->fpstate_active)
+		return NULL;
+	/*
+	 * fpu__save() takes the CPU's xstate registers
+	 * and saves them off to the 'fpu memory buffer.
+	 */
+	fpu__save(fpu);
+
+	return get_xsave_addr(&fpu->state.xsave, xsave_state);
+}
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 53eeb226657c..0e2d96ffd158 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -62,9 +62,16 @@
 #define PAGE_TABLE_SIZE(pages) ((pages) / PTRS_PER_PGD)
 #endif
 
-/* Number of possible pages in the lowmem region */
-LOWMEM_PAGES = (((1<<32) - __PAGE_OFFSET) >> PAGE_SHIFT)
-	
+/*
+ * Number of possible pages in the lowmem region.
+ *
+ * We shift 2 by 31 instead of 1 by 32 to the left in order to avoid a
+ * gas warning about overflowing shift count when gas has been compiled
+ * with only a host target support using a 32-bit type for internal
+ * representation.
+ */
+LOWMEM_PAGES = (((2<<31) - __PAGE_OFFSET) >> PAGE_SHIFT)
+
 /* Enough space to fit pagetables for the low memory linear map */
 MAPPING_BEYOND_END = PAGE_TABLE_SIZE(LOWMEM_PAGES) << PAGE_SHIFT
 
@@ -550,7 +557,7 @@ early_idt_handler_common:
 	cld
 
 	cmpl $2,(%esp)		# X86_TRAP_NMI
-	je is_nmi		# Ignore NMI
+	je .Lis_nmi		# Ignore NMI
 
 	cmpl $2,%ss:early_recursion_flag
 	je hlt_loop
@@ -603,7 +610,7 @@ ex_entry:
 	pop %ecx
 	pop %eax
 	decl %ss:early_recursion_flag
-is_nmi:
+.Lis_nmi:
 	addl $8,%esp		/* drop vector number and error code */
 	iret
 ENDPROC(early_idt_handler_common)
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index df7e78057ae0..e5c27f729a38 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -346,7 +346,7 @@ early_idt_handler_common:
 	cld
 
 	cmpl $2,(%rsp)		# X86_TRAP_NMI
-	je is_nmi		# Ignore NMI
+	je .Lis_nmi		# Ignore NMI
 
 	cmpl $2,early_recursion_flag(%rip)
 	jz  1f
@@ -411,7 +411,7 @@ early_idt_handler_common:
 	popq %rcx
 	popq %rax
 	decl early_recursion_flag(%rip)
-is_nmi:
+.Lis_nmi:
 	addq $16,%rsp		# drop vector number and error code
 	INTERRUPT_RETURN
 ENDPROC(early_idt_handler_common)
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 3acbff4716b0..10757d0a3fcf 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -12,6 +12,7 @@
 #include <linux/pm.h>
 #include <linux/io.h>
 
+#include <asm/irqdomain.h>
 #include <asm/fixmap.h>
 #include <asm/hpet.h>
 #include <asm/time.h>
@@ -305,8 +306,6 @@ static void hpet_legacy_clockevent_register(void)
 	printk(KERN_DEBUG "hpet clockevent registered\n");
 }
 
-static int hpet_setup_msi_irq(unsigned int irq);
-
 static void hpet_set_mode(enum clock_event_mode mode,
 			  struct clock_event_device *evt, int timer)
 {
@@ -357,7 +356,7 @@ static void hpet_set_mode(enum clock_event_mode mode,
 			hpet_enable_legacy_int();
 		} else {
 			struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt);
-			hpet_setup_msi_irq(hdev->irq);
+			irq_domain_activate_irq(irq_get_irq_data(hdev->irq));
 			disable_irq(hdev->irq);
 			irq_set_affinity(hdev->irq, cpumask_of(hdev->cpu));
 			enable_irq(hdev->irq);
@@ -423,6 +422,7 @@ static int hpet_legacy_next_event(unsigned long delta,
 
 static DEFINE_PER_CPU(struct hpet_dev *, cpu_hpet_dev);
 static struct hpet_dev	*hpet_devs;
+static struct irq_domain *hpet_domain;
 
 void hpet_msi_unmask(struct irq_data *data)
 {
@@ -473,31 +473,6 @@ static int hpet_msi_next_event(unsigned long delta,
 	return hpet_next_event(delta, evt, hdev->num);
 }
 
-static int hpet_setup_msi_irq(unsigned int irq)
-{
-	if (x86_msi.setup_hpet_msi(irq, hpet_blockid)) {
-		irq_free_hwirq(irq);
-		return -EINVAL;
-	}
-	return 0;
-}
-
-static int hpet_assign_irq(struct hpet_dev *dev)
-{
-	unsigned int irq = irq_alloc_hwirq(-1);
-
-	if (!irq)
-		return -EINVAL;
-
-	irq_set_handler_data(irq, dev);
-
-	if (hpet_setup_msi_irq(irq))
-		return -EINVAL;
-
-	dev->irq = irq;
-	return 0;
-}
-
 static irqreturn_t hpet_interrupt_handler(int irq, void *data)
 {
 	struct hpet_dev *dev = (struct hpet_dev *)data;
@@ -540,9 +515,6 @@ static void init_one_hpet_msi_clockevent(struct hpet_dev *hdev, int cpu)
 	if (!(hdev->flags & HPET_DEV_VALID))
 		return;
 
-	if (hpet_setup_msi_irq(hdev->irq))
-		return;
-
 	hdev->cpu = cpu;
 	per_cpu(cpu_hpet_dev, cpu) = hdev;
 	evt->name = hdev->name;
@@ -574,7 +546,7 @@ static void hpet_msi_capability_lookup(unsigned int start_timer)
 	unsigned int id;
 	unsigned int num_timers;
 	unsigned int num_timers_used = 0;
-	int i;
+	int i, irq;
 
 	if (hpet_msi_disable)
 		return;
@@ -587,6 +559,10 @@ static void hpet_msi_capability_lookup(unsigned int start_timer)
 	num_timers++; /* Value read out starts from 0 */
 	hpet_print_config();
 
+	hpet_domain = hpet_create_irq_domain(hpet_blockid);
+	if (!hpet_domain)
+		return;
+
 	hpet_devs = kzalloc(sizeof(struct hpet_dev) * num_timers, GFP_KERNEL);
 	if (!hpet_devs)
 		return;
@@ -604,12 +580,14 @@ static void hpet_msi_capability_lookup(unsigned int start_timer)
 		hdev->flags = 0;
 		if (cfg & HPET_TN_PERIODIC_CAP)
 			hdev->flags |= HPET_DEV_PERI_CAP;
+		sprintf(hdev->name, "hpet%d", i);
 		hdev->num = i;
 
-		sprintf(hdev->name, "hpet%d", i);
-		if (hpet_assign_irq(hdev))
+		irq = hpet_assign_irq(hpet_domain, hdev, hdev->num);
+		if (irq <= 0)
 			continue;
 
+		hdev->irq = irq;
 		hdev->flags |= HPET_DEV_FSB_CAP;
 		hdev->flags |= HPET_DEV_VALID;
 		num_timers_used++;
@@ -709,10 +687,6 @@ static int hpet_cpuhp_notify(struct notifier_block *n,
 }
 #else
 
-static int hpet_setup_msi_irq(unsigned int irq)
-{
-	return 0;
-}
 static void hpet_msi_capability_lookup(unsigned int start_timer)
 {
 	return;
diff --git a/arch/x86/kernel/i386_ksyms_32.c b/arch/x86/kernel/i386_ksyms_32.c
index 05fd74f537d6..64341aa485ae 100644
--- a/arch/x86/kernel/i386_ksyms_32.c
+++ b/arch/x86/kernel/i386_ksyms_32.c
@@ -40,7 +40,5 @@ EXPORT_SYMBOL(empty_zero_page);
 
 #ifdef CONFIG_PREEMPT
 EXPORT_SYMBOL(___preempt_schedule);
-#ifdef CONFIG_CONTEXT_TRACKING
-EXPORT_SYMBOL(___preempt_schedule_context);
-#endif
+EXPORT_SYMBOL(___preempt_schedule_notrace);
 #endif
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
deleted file mode 100644
index 6185d3141219..000000000000
--- a/arch/x86/kernel/i387.c
+++ /dev/null
@@ -1,671 +0,0 @@
-/*
- *  Copyright (C) 1994 Linus Torvalds
- *
- *  Pentium III FXSR, SSE support
- *  General FPU state handling cleanups
- *	Gareth Hughes <gareth@valinux.com>, May 2000
- */
-#include <linux/module.h>
-#include <linux/regset.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
-
-#include <asm/sigcontext.h>
-#include <asm/processor.h>
-#include <asm/math_emu.h>
-#include <asm/tlbflush.h>
-#include <asm/uaccess.h>
-#include <asm/ptrace.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
-#include <asm/user.h>
-
-static DEFINE_PER_CPU(bool, in_kernel_fpu);
-
-void kernel_fpu_disable(void)
-{
-	WARN_ON(this_cpu_read(in_kernel_fpu));
-	this_cpu_write(in_kernel_fpu, true);
-}
-
-void kernel_fpu_enable(void)
-{
-	this_cpu_write(in_kernel_fpu, false);
-}
-
-/*
- * Were we in an interrupt that interrupted kernel mode?
- *
- * On others, we can do a kernel_fpu_begin/end() pair *ONLY* if that
- * pair does nothing at all: the thread must not have fpu (so
- * that we don't try to save the FPU state), and TS must
- * be set (so that the clts/stts pair does nothing that is
- * visible in the interrupted kernel thread).
- *
- * Except for the eagerfpu case when we return true; in the likely case
- * the thread has FPU but we are not going to set/clear TS.
- */
-static inline bool interrupted_kernel_fpu_idle(void)
-{
-	if (this_cpu_read(in_kernel_fpu))
-		return false;
-
-	if (use_eager_fpu())
-		return true;
-
-	return !__thread_has_fpu(current) &&
-		(read_cr0() & X86_CR0_TS);
-}
-
-/*
- * Were we in user mode (or vm86 mode) when we were
- * interrupted?
- *
- * Doing kernel_fpu_begin/end() is ok if we are running
- * in an interrupt context from user mode - we'll just
- * save the FPU state as required.
- */
-static inline bool interrupted_user_mode(void)
-{
-	struct pt_regs *regs = get_irq_regs();
-	return regs && user_mode(regs);
-}
-
-/*
- * Can we use the FPU in kernel mode with the
- * whole "kernel_fpu_begin/end()" sequence?
- *
- * It's always ok in process context (ie "not interrupt")
- * but it is sometimes ok even from an irq.
- */
-bool irq_fpu_usable(void)
-{
-	return !in_interrupt() ||
-		interrupted_user_mode() ||
-		interrupted_kernel_fpu_idle();
-}
-EXPORT_SYMBOL(irq_fpu_usable);
-
-void __kernel_fpu_begin(void)
-{
-	struct task_struct *me = current;
-
-	this_cpu_write(in_kernel_fpu, true);
-
-	if (__thread_has_fpu(me)) {
-		__save_init_fpu(me);
-	} else {
-		this_cpu_write(fpu_owner_task, NULL);
-		if (!use_eager_fpu())
-			clts();
-	}
-}
-EXPORT_SYMBOL(__kernel_fpu_begin);
-
-void __kernel_fpu_end(void)
-{
-	struct task_struct *me = current;
-
-	if (__thread_has_fpu(me)) {
-		if (WARN_ON(restore_fpu_checking(me)))
-			fpu_reset_state(me);
-	} else if (!use_eager_fpu()) {
-		stts();
-	}
-
-	this_cpu_write(in_kernel_fpu, false);
-}
-EXPORT_SYMBOL(__kernel_fpu_end);
-
-void unlazy_fpu(struct task_struct *tsk)
-{
-	preempt_disable();
-	if (__thread_has_fpu(tsk)) {
-		if (use_eager_fpu()) {
-			__save_fpu(tsk);
-		} else {
-			__save_init_fpu(tsk);
-			__thread_fpu_end(tsk);
-		}
-	}
-	preempt_enable();
-}
-EXPORT_SYMBOL(unlazy_fpu);
-
-unsigned int mxcsr_feature_mask __read_mostly = 0xffffffffu;
-unsigned int xstate_size;
-EXPORT_SYMBOL_GPL(xstate_size);
-static struct i387_fxsave_struct fx_scratch;
-
-static void mxcsr_feature_mask_init(void)
-{
-	unsigned long mask = 0;
-
-	if (cpu_has_fxsr) {
-		memset(&fx_scratch, 0, sizeof(struct i387_fxsave_struct));
-		asm volatile("fxsave %0" : "+m" (fx_scratch));
-		mask = fx_scratch.mxcsr_mask;
-		if (mask == 0)
-			mask = 0x0000ffbf;
-	}
-	mxcsr_feature_mask &= mask;
-}
-
-static void init_thread_xstate(void)
-{
-	/*
-	 * Note that xstate_size might be overwriten later during
-	 * xsave_init().
-	 */
-
-	if (!cpu_has_fpu) {
-		/*
-		 * Disable xsave as we do not support it if i387
-		 * emulation is enabled.
-		 */
-		setup_clear_cpu_cap(X86_FEATURE_XSAVE);
-		setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
-		xstate_size = sizeof(struct i387_soft_struct);
-		return;
-	}
-
-	if (cpu_has_fxsr)
-		xstate_size = sizeof(struct i387_fxsave_struct);
-	else
-		xstate_size = sizeof(struct i387_fsave_struct);
-
-	/*
-	 * Quirk: we don't yet handle the XSAVES* instructions
-	 * correctly, as we don't correctly convert between
-	 * standard and compacted format when interfacing
-	 * with user-space - so disable it for now.
-	 *
-	 * The difference is small: with recent CPUs the
-	 * compacted format is only marginally smaller than
-	 * the standard FPU state format.
-	 *
-	 * ( This is easy to backport while we are fixing
-	 *   XSAVES* support. )
-	 */
-	setup_clear_cpu_cap(X86_FEATURE_XSAVES);
-}
-
-/*
- * Called at bootup to set up the initial FPU state that is later cloned
- * into all processes.
- */
-
-void fpu_init(void)
-{
-	unsigned long cr0;
-	unsigned long cr4_mask = 0;
-
-#ifndef CONFIG_MATH_EMULATION
-	if (!cpu_has_fpu) {
-		pr_emerg("No FPU found and no math emulation present\n");
-		pr_emerg("Giving up\n");
-		for (;;)
-			asm volatile("hlt");
-	}
-#endif
-	if (cpu_has_fxsr)
-		cr4_mask |= X86_CR4_OSFXSR;
-	if (cpu_has_xmm)
-		cr4_mask |= X86_CR4_OSXMMEXCPT;
-	if (cr4_mask)
-		cr4_set_bits(cr4_mask);
-
-	cr0 = read_cr0();
-	cr0 &= ~(X86_CR0_TS|X86_CR0_EM); /* clear TS and EM */
-	if (!cpu_has_fpu)
-		cr0 |= X86_CR0_EM;
-	write_cr0(cr0);
-
-	/*
-	 * init_thread_xstate is only called once to avoid overriding
-	 * xstate_size during boot time or during CPU hotplug.
-	 */
-	if (xstate_size == 0)
-		init_thread_xstate();
-
-	mxcsr_feature_mask_init();
-	xsave_init();
-	eager_fpu_init();
-}
-
-void fpu_finit(struct fpu *fpu)
-{
-	if (!cpu_has_fpu) {
-		finit_soft_fpu(&fpu->state->soft);
-		return;
-	}
-
-	memset(fpu->state, 0, xstate_size);
-
-	if (cpu_has_fxsr) {
-		fx_finit(&fpu->state->fxsave);
-	} else {
-		struct i387_fsave_struct *fp = &fpu->state->fsave;
-		fp->cwd = 0xffff037fu;
-		fp->swd = 0xffff0000u;
-		fp->twd = 0xffffffffu;
-		fp->fos = 0xffff0000u;
-	}
-}
-EXPORT_SYMBOL_GPL(fpu_finit);
-
-/*
- * The _current_ task is using the FPU for the first time
- * so initialize it and set the mxcsr to its default
- * value at reset if we support XMM instructions and then
- * remember the current task has used the FPU.
- */
-int init_fpu(struct task_struct *tsk)
-{
-	int ret;
-
-	if (tsk_used_math(tsk)) {
-		if (cpu_has_fpu && tsk == current)
-			unlazy_fpu(tsk);
-		task_disable_lazy_fpu_restore(tsk);
-		return 0;
-	}
-
-	/*
-	 * Memory allocation at the first usage of the FPU and other state.
-	 */
-	ret = fpu_alloc(&tsk->thread.fpu);
-	if (ret)
-		return ret;
-
-	fpu_finit(&tsk->thread.fpu);
-
-	set_stopped_child_used_math(tsk);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(init_fpu);
-
-/*
- * The xstateregs_active() routine is the same as the fpregs_active() routine,
- * as the "regset->n" for the xstate regset will be updated based on the feature
- * capabilites supported by the xsave.
- */
-int fpregs_active(struct task_struct *target, const struct user_regset *regset)
-{
-	return tsk_used_math(target) ? regset->n : 0;
-}
-
-int xfpregs_active(struct task_struct *target, const struct user_regset *regset)
-{
-	return (cpu_has_fxsr && tsk_used_math(target)) ? regset->n : 0;
-}
-
-int xfpregs_get(struct task_struct *target, const struct user_regset *regset,
-		unsigned int pos, unsigned int count,
-		void *kbuf, void __user *ubuf)
-{
-	int ret;
-
-	if (!cpu_has_fxsr)
-		return -ENODEV;
-
-	ret = init_fpu(target);
-	if (ret)
-		return ret;
-
-	sanitize_i387_state(target);
-
-	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
-				   &target->thread.fpu.state->fxsave, 0, -1);
-}
-
-int xfpregs_set(struct task_struct *target, const struct user_regset *regset,
-		unsigned int pos, unsigned int count,
-		const void *kbuf, const void __user *ubuf)
-{
-	int ret;
-
-	if (!cpu_has_fxsr)
-		return -ENODEV;
-
-	ret = init_fpu(target);
-	if (ret)
-		return ret;
-
-	sanitize_i387_state(target);
-
-	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-				 &target->thread.fpu.state->fxsave, 0, -1);
-
-	/*
-	 * mxcsr reserved bits must be masked to zero for security reasons.
-	 */
-	target->thread.fpu.state->fxsave.mxcsr &= mxcsr_feature_mask;
-
-	/*
-	 * update the header bits in the xsave header, indicating the
-	 * presence of FP and SSE state.
-	 */
-	if (cpu_has_xsave)
-		target->thread.fpu.state->xsave.xsave_hdr.xstate_bv |= XSTATE_FPSSE;
-
-	return ret;
-}
-
-int xstateregs_get(struct task_struct *target, const struct user_regset *regset,
-		unsigned int pos, unsigned int count,
-		void *kbuf, void __user *ubuf)
-{
-	struct xsave_struct *xsave;
-	int ret;
-
-	if (!cpu_has_xsave)
-		return -ENODEV;
-
-	ret = init_fpu(target);
-	if (ret)
-		return ret;
-
-	xsave = &target->thread.fpu.state->xsave;
-
-	/*
-	 * Copy the 48bytes defined by the software first into the xstate
-	 * memory layout in the thread struct, so that we can copy the entire
-	 * xstateregs to the user using one user_regset_copyout().
-	 */
-	memcpy(&xsave->i387.sw_reserved,
-		xstate_fx_sw_bytes, sizeof(xstate_fx_sw_bytes));
-	/*
-	 * Copy the xstate memory layout.
-	 */
-	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, xsave, 0, -1);
-	return ret;
-}
-
-int xstateregs_set(struct task_struct *target, const struct user_regset *regset,
-		  unsigned int pos, unsigned int count,
-		  const void *kbuf, const void __user *ubuf)
-{
-	struct xsave_struct *xsave;
-	int ret;
-
-	if (!cpu_has_xsave)
-		return -ENODEV;
-
-	ret = init_fpu(target);
-	if (ret)
-		return ret;
-
-	xsave = &target->thread.fpu.state->xsave;
-
-	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, xsave, 0, -1);
-	/*
-	 * mxcsr reserved bits must be masked to zero for security reasons.
-	 */
-	xsave->i387.mxcsr &= mxcsr_feature_mask;
-	xsave->xsave_hdr.xstate_bv &= pcntxt_mask;
-	/*
-	 * These bits must be zero.
-	 */
-	memset(&xsave->xsave_hdr.reserved, 0, 48);
-	return ret;
-}
-
-#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
-
-/*
- * FPU tag word conversions.
- */
-
-static inline unsigned short twd_i387_to_fxsr(unsigned short twd)
-{
-	unsigned int tmp; /* to avoid 16 bit prefixes in the code */
-
-	/* Transform each pair of bits into 01 (valid) or 00 (empty) */
-	tmp = ~twd;
-	tmp = (tmp | (tmp>>1)) & 0x5555; /* 0V0V0V0V0V0V0V0V */
-	/* and move the valid bits to the lower byte. */
-	tmp = (tmp | (tmp >> 1)) & 0x3333; /* 00VV00VV00VV00VV */
-	tmp = (tmp | (tmp >> 2)) & 0x0f0f; /* 0000VVVV0000VVVV */
-	tmp = (tmp | (tmp >> 4)) & 0x00ff; /* 00000000VVVVVVVV */
-
-	return tmp;
-}
-
-#define FPREG_ADDR(f, n)	((void *)&(f)->st_space + (n) * 16)
-#define FP_EXP_TAG_VALID	0
-#define FP_EXP_TAG_ZERO		1
-#define FP_EXP_TAG_SPECIAL	2
-#define FP_EXP_TAG_EMPTY	3
-
-static inline u32 twd_fxsr_to_i387(struct i387_fxsave_struct *fxsave)
-{
-	struct _fpxreg *st;
-	u32 tos = (fxsave->swd >> 11) & 7;
-	u32 twd = (unsigned long) fxsave->twd;
-	u32 tag;
-	u32 ret = 0xffff0000u;
-	int i;
-
-	for (i = 0; i < 8; i++, twd >>= 1) {
-		if (twd & 0x1) {
-			st = FPREG_ADDR(fxsave, (i - tos) & 7);
-
-			switch (st->exponent & 0x7fff) {
-			case 0x7fff:
-				tag = FP_EXP_TAG_SPECIAL;
-				break;
-			case 0x0000:
-				if (!st->significand[0] &&
-				    !st->significand[1] &&
-				    !st->significand[2] &&
-				    !st->significand[3])
-					tag = FP_EXP_TAG_ZERO;
-				else
-					tag = FP_EXP_TAG_SPECIAL;
-				break;
-			default:
-				if (st->significand[3] & 0x8000)
-					tag = FP_EXP_TAG_VALID;
-				else
-					tag = FP_EXP_TAG_SPECIAL;
-				break;
-			}
-		} else {
-			tag = FP_EXP_TAG_EMPTY;
-		}
-		ret |= tag << (2 * i);
-	}
-	return ret;
-}
-
-/*
- * FXSR floating point environment conversions.
- */
-
-void
-convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk)
-{
-	struct i387_fxsave_struct *fxsave = &tsk->thread.fpu.state->fxsave;
-	struct _fpreg *to = (struct _fpreg *) &env->st_space[0];
-	struct _fpxreg *from = (struct _fpxreg *) &fxsave->st_space[0];
-	int i;
-
-	env->cwd = fxsave->cwd | 0xffff0000u;
-	env->swd = fxsave->swd | 0xffff0000u;
-	env->twd = twd_fxsr_to_i387(fxsave);
-
-#ifdef CONFIG_X86_64
-	env->fip = fxsave->rip;
-	env->foo = fxsave->rdp;
-	/*
-	 * should be actually ds/cs at fpu exception time, but
-	 * that information is not available in 64bit mode.
-	 */
-	env->fcs = task_pt_regs(tsk)->cs;
-	if (tsk == current) {
-		savesegment(ds, env->fos);
-	} else {
-		env->fos = tsk->thread.ds;
-	}
-	env->fos |= 0xffff0000;
-#else
-	env->fip = fxsave->fip;
-	env->fcs = (u16) fxsave->fcs | ((u32) fxsave->fop << 16);
-	env->foo = fxsave->foo;
-	env->fos = fxsave->fos;
-#endif
-
-	for (i = 0; i < 8; ++i)
-		memcpy(&to[i], &from[i], sizeof(to[0]));
-}
-
-void convert_to_fxsr(struct task_struct *tsk,
-		     const struct user_i387_ia32_struct *env)
-
-{
-	struct i387_fxsave_struct *fxsave = &tsk->thread.fpu.state->fxsave;
-	struct _fpreg *from = (struct _fpreg *) &env->st_space[0];
-	struct _fpxreg *to = (struct _fpxreg *) &fxsave->st_space[0];
-	int i;
-
-	fxsave->cwd = env->cwd;
-	fxsave->swd = env->swd;
-	fxsave->twd = twd_i387_to_fxsr(env->twd);
-	fxsave->fop = (u16) ((u32) env->fcs >> 16);
-#ifdef CONFIG_X86_64
-	fxsave->rip = env->fip;
-	fxsave->rdp = env->foo;
-	/* cs and ds ignored */
-#else
-	fxsave->fip = env->fip;
-	fxsave->fcs = (env->fcs & 0xffff);
-	fxsave->foo = env->foo;
-	fxsave->fos = env->fos;
-#endif
-
-	for (i = 0; i < 8; ++i)
-		memcpy(&to[i], &from[i], sizeof(from[0]));
-}
-
-int fpregs_get(struct task_struct *target, const struct user_regset *regset,
-	       unsigned int pos, unsigned int count,
-	       void *kbuf, void __user *ubuf)
-{
-	struct user_i387_ia32_struct env;
-	int ret;
-
-	ret = init_fpu(target);
-	if (ret)
-		return ret;
-
-	if (!static_cpu_has(X86_FEATURE_FPU))
-		return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf);
-
-	if (!cpu_has_fxsr)
-		return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
-					   &target->thread.fpu.state->fsave, 0,
-					   -1);
-
-	sanitize_i387_state(target);
-
-	if (kbuf && pos == 0 && count == sizeof(env)) {
-		convert_from_fxsr(kbuf, target);
-		return 0;
-	}
-
-	convert_from_fxsr(&env, target);
-
-	return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &env, 0, -1);
-}
-
-int fpregs_set(struct task_struct *target, const struct user_regset *regset,
-	       unsigned int pos, unsigned int count,
-	       const void *kbuf, const void __user *ubuf)
-{
-	struct user_i387_ia32_struct env;
-	int ret;
-
-	ret = init_fpu(target);
-	if (ret)
-		return ret;
-
-	sanitize_i387_state(target);
-
-	if (!static_cpu_has(X86_FEATURE_FPU))
-		return fpregs_soft_set(target, regset, pos, count, kbuf, ubuf);
-
-	if (!cpu_has_fxsr)
-		return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-					  &target->thread.fpu.state->fsave, 0,
-					  -1);
-
-	if (pos > 0 || count < sizeof(env))
-		convert_from_fxsr(&env, target);
-
-	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &env, 0, -1);
-	if (!ret)
-		convert_to_fxsr(target, &env);
-
-	/*
-	 * update the header bit in the xsave header, indicating the
-	 * presence of FP.
-	 */
-	if (cpu_has_xsave)
-		target->thread.fpu.state->xsave.xsave_hdr.xstate_bv |= XSTATE_FP;
-	return ret;
-}
-
-/*
- * FPU state for core dumps.
- * This is only used for a.out dumps now.
- * It is declared generically using elf_fpregset_t (which is
- * struct user_i387_struct) but is in fact only used for 32-bit
- * dumps, so on 64-bit it is really struct user_i387_ia32_struct.
- */
-int dump_fpu(struct pt_regs *regs, struct user_i387_struct *fpu)
-{
-	struct task_struct *tsk = current;
-	int fpvalid;
-
-	fpvalid = !!used_math();
-	if (fpvalid)
-		fpvalid = !fpregs_get(tsk, NULL,
-				      0, sizeof(struct user_i387_ia32_struct),
-				      fpu, NULL);
-
-	return fpvalid;
-}
-EXPORT_SYMBOL(dump_fpu);
-
-#endif	/* CONFIG_X86_32 || CONFIG_IA32_EMULATION */
-
-static int __init no_387(char *s)
-{
-	setup_clear_cpu_cap(X86_FEATURE_FPU);
-	return 1;
-}
-
-__setup("no387", no_387);
-
-void fpu_detect(struct cpuinfo_x86 *c)
-{
-	unsigned long cr0;
-	u16 fsw, fcw;
-
-	fsw = fcw = 0xffff;
-
-	cr0 = read_cr0();
-	cr0 &= ~(X86_CR0_TS | X86_CR0_EM);
-	write_cr0(cr0);
-
-	asm volatile("fninit ; fnstsw %0 ; fnstcw %1"
-		     : "+m" (fsw), "+m" (fcw));
-
-	if (fsw == 0 && (fcw & 0x103f) == 0x003f)
-		set_cpu_cap(c, X86_FEATURE_FPU);
-	else
-		clear_cpu_cap(c, X86_FEATURE_FPU);
-
-	/* The final cr0 value is set in fpu_init() */
-}
diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c
index e7cc5370cd2f..16cb827a5b27 100644
--- a/arch/x86/kernel/i8259.c
+++ b/arch/x86/kernel/i8259.c
@@ -329,8 +329,8 @@ static void init_8259A(int auto_eoi)
 	 */
 	outb_pic(0x11, PIC_MASTER_CMD);	/* ICW1: select 8259A-1 init */
 
-	/* ICW2: 8259A-1 IR0-7 mapped to 0x30-0x37 */
-	outb_pic(IRQ0_VECTOR, PIC_MASTER_IMR);
+	/* ICW2: 8259A-1 IR0-7 mapped to ISA_IRQ_VECTOR(0) */
+	outb_pic(ISA_IRQ_VECTOR(0), PIC_MASTER_IMR);
 
 	/* 8259A-1 (the master) has a slave on IR2 */
 	outb_pic(1U << PIC_CASCADE_IR, PIC_MASTER_IMR);
@@ -342,8 +342,8 @@ static void init_8259A(int auto_eoi)
 
 	outb_pic(0x11, PIC_SLAVE_CMD);	/* ICW1: select 8259A-2 init */
 
-	/* ICW2: 8259A-2 IR0-7 mapped to IRQ8_VECTOR */
-	outb_pic(IRQ8_VECTOR, PIC_SLAVE_IMR);
+	/* ICW2: 8259A-2 IR0-7 mapped to ISA_IRQ_VECTOR(8) */
+	outb_pic(ISA_IRQ_VECTOR(8), PIC_SLAVE_IMR);
 	/* 8259A-2 is a slave on master's IR2 */
 	outb_pic(PIC_CASCADE_IR, PIC_SLAVE_IMR);
 	/* (slave's support for AEOI in flat mode is to be investigated) */
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index e5952c225532..88b366487b0e 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -22,6 +22,12 @@
 #define CREATE_TRACE_POINTS
 #include <asm/trace/irq_vectors.h>
 
+DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
+EXPORT_PER_CPU_SYMBOL(irq_stat);
+
+DEFINE_PER_CPU(struct pt_regs *, irq_regs);
+EXPORT_PER_CPU_SYMBOL(irq_regs);
+
 atomic_t irq_err_count;
 
 /* Function pointer for generic interrupt vector handling */
@@ -116,6 +122,12 @@ int arch_show_interrupts(struct seq_file *p, int prec)
 		seq_printf(p, "%10u ", irq_stats(j)->irq_threshold_count);
 	seq_puts(p, "  Threshold APIC interrupts\n");
 #endif
+#ifdef CONFIG_X86_MCE_AMD
+	seq_printf(p, "%*s: ", prec, "DFR");
+	for_each_online_cpu(j)
+		seq_printf(p, "%10u ", irq_stats(j)->irq_deferred_error_count);
+	seq_puts(p, "  Deferred Error APIC interrupts\n");
+#endif
 #ifdef CONFIG_X86_MCE
 	seq_printf(p, "%*s: ", prec, "MCE");
 	for_each_online_cpu(j)
@@ -136,6 +148,18 @@ int arch_show_interrupts(struct seq_file *p, int prec)
 #if defined(CONFIG_X86_IO_APIC)
 	seq_printf(p, "%*s: %10u\n", prec, "MIS", atomic_read(&irq_mis_count));
 #endif
+#ifdef CONFIG_HAVE_KVM
+	seq_printf(p, "%*s: ", prec, "PIN");
+	for_each_online_cpu(j)
+		seq_printf(p, "%10u ", irq_stats(j)->kvm_posted_intr_ipis);
+	seq_puts(p, "  Posted-interrupt notification event\n");
+
+	seq_printf(p, "%*s: ", prec, "PIW");
+	for_each_online_cpu(j)
+		seq_printf(p, "%10u ",
+			   irq_stats(j)->kvm_posted_intr_wakeup_ipis);
+	seq_puts(p, "  Posted-interrupt wakeup event\n");
+#endif
 	return 0;
 }
 
@@ -192,8 +216,7 @@ __visible unsigned int __irq_entry do_IRQ(struct pt_regs *regs)
 	unsigned vector = ~regs->orig_ax;
 	unsigned irq;
 
-	irq_enter();
-	exit_idle();
+	entering_irq();
 
 	irq = __this_cpu_read(vector_irq[vector]);
 
@@ -209,7 +232,7 @@ __visible unsigned int __irq_entry do_IRQ(struct pt_regs *regs)
 		}
 	}
 
-	irq_exit();
+	exiting_irq();
 
 	set_irq_regs(old_regs);
 	return 1;
@@ -237,6 +260,18 @@ __visible void smp_x86_platform_ipi(struct pt_regs *regs)
 }
 
 #ifdef CONFIG_HAVE_KVM
+static void dummy_handler(void) {}
+static void (*kvm_posted_intr_wakeup_handler)(void) = dummy_handler;
+
+void kvm_set_posted_intr_wakeup_handler(void (*handler)(void))
+{
+	if (handler)
+		kvm_posted_intr_wakeup_handler = handler;
+	else
+		kvm_posted_intr_wakeup_handler = dummy_handler;
+}
+EXPORT_SYMBOL_GPL(kvm_set_posted_intr_wakeup_handler);
+
 /*
  * Handler for POSTED_INTERRUPT_VECTOR.
  */
@@ -244,16 +279,23 @@ __visible void smp_kvm_posted_intr_ipi(struct pt_regs *regs)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
 
-	ack_APIC_irq();
-
-	irq_enter();
-
-	exit_idle();
-
+	entering_ack_irq();
 	inc_irq_stat(kvm_posted_intr_ipis);
+	exiting_irq();
+	set_irq_regs(old_regs);
+}
 
-	irq_exit();
+/*
+ * Handler for POSTED_INTERRUPT_WAKEUP_VECTOR.
+ */
+__visible void smp_kvm_posted_intr_wakeup_ipi(struct pt_regs *regs)
+{
+	struct pt_regs *old_regs = set_irq_regs(regs);
 
+	entering_ack_irq();
+	inc_irq_stat(kvm_posted_intr_wakeup_ipis);
+	kvm_posted_intr_wakeup_handler();
+	exiting_irq();
 	set_irq_regs(old_regs);
 }
 #endif
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index f9fd86a7fcc7..cd74f5978ab9 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -21,12 +21,6 @@
 
 #include <asm/apic.h>
 
-DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
-EXPORT_PER_CPU_SYMBOL(irq_stat);
-
-DEFINE_PER_CPU(struct pt_regs *, irq_regs);
-EXPORT_PER_CPU_SYMBOL(irq_regs);
-
 #ifdef CONFIG_DEBUG_STACKOVERFLOW
 
 int sysctl_panic_on_stackoverflow __read_mostly;
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index 394e643d7830..bc4604e500a3 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -20,12 +20,6 @@
 #include <asm/idle.h>
 #include <asm/apic.h>
 
-DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
-EXPORT_PER_CPU_SYMBOL(irq_stat);
-
-DEFINE_PER_CPU(struct pt_regs *, irq_regs);
-EXPORT_PER_CPU_SYMBOL(irq_regs);
-
 int sysctl_panic_on_stackoverflow;
 
 /*
diff --git a/arch/x86/kernel/irq_work.c b/arch/x86/kernel/irq_work.c
index 15d741ddfeeb..dc5fa6a1e8d6 100644
--- a/arch/x86/kernel/irq_work.c
+++ b/arch/x86/kernel/irq_work.c
@@ -10,12 +10,6 @@
 #include <asm/apic.h>
 #include <asm/trace/irq_vectors.h>
 
-static inline void irq_work_entering_irq(void)
-{
-	irq_enter();
-	ack_APIC_irq();
-}
-
 static inline void __smp_irq_work_interrupt(void)
 {
 	inc_irq_stat(apic_irq_work_irqs);
@@ -24,14 +18,14 @@ static inline void __smp_irq_work_interrupt(void)
 
 __visible void smp_irq_work_interrupt(struct pt_regs *regs)
 {
-	irq_work_entering_irq();
+	ipi_entering_ack_irq();
 	__smp_irq_work_interrupt();
 	exiting_irq();
 }
 
 __visible void smp_trace_irq_work_interrupt(struct pt_regs *regs)
 {
-	irq_work_entering_irq();
+	ipi_entering_ack_irq();
 	trace_irq_work_entry(IRQ_WORK_VECTOR);
 	__smp_irq_work_interrupt();
 	trace_irq_work_exit(IRQ_WORK_VECTOR);
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index cd10a6437264..a3a5e158ed69 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -86,7 +86,7 @@ void __init init_IRQ(void)
 	int i;
 
 	/*
-	 * On cpu 0, Assign IRQ0_VECTOR..IRQ15_VECTOR's to IRQ 0..15.
+	 * On cpu 0, Assign ISA_IRQ_VECTOR(irq) to IRQ 0..15.
 	 * If these IRQ's are handled by legacy interrupt-controllers like PIC,
 	 * then this configuration will likely be static after the boot. If
 	 * these IRQ's are handled by more mordern controllers like IO-APIC,
@@ -94,7 +94,7 @@ void __init init_IRQ(void)
 	 * irq's migrate etc.
 	 */
 	for (i = 0; i < nr_legacy_irqs(); i++)
-		per_cpu(vector_irq, 0)[IRQ0_VECTOR + i] = i;
+		per_cpu(vector_irq, 0)[ISA_IRQ_VECTOR(i)] = i;
 
 	x86_init.irqs.intr_init();
 }
@@ -135,6 +135,10 @@ static void __init apic_intr_init(void)
 	alloc_intr_gate(THRESHOLD_APIC_VECTOR, threshold_interrupt);
 #endif
 
+#ifdef CONFIG_X86_MCE_AMD
+	alloc_intr_gate(DEFERRED_ERROR_VECTOR, deferred_error_interrupt);
+#endif
+
 #ifdef CONFIG_X86_LOCAL_APIC
 	/* self generated IPI for local APIC timer */
 	alloc_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt);
@@ -144,6 +148,8 @@ static void __init apic_intr_init(void)
 #ifdef CONFIG_HAVE_KVM
 	/* IPI for KVM to deliver posted interrupt */
 	alloc_intr_gate(POSTED_INTR_VECTOR, kvm_posted_intr_ipi);
+	/* IPI for KVM to deliver interrupt to wake up tasks */
+	alloc_intr_gate(POSTED_INTR_WAKEUP_VECTOR, kvm_posted_intr_wakeup_ipi);
 #endif
 
 	/* IPI vectors for APIC spurious and error interrupts */
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 9435620062df..1681504e44a4 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -584,6 +584,39 @@ static void kvm_kick_cpu(int cpu)
 	kvm_hypercall2(KVM_HC_KICK_CPU, flags, apicid);
 }
 
+
+#ifdef CONFIG_QUEUED_SPINLOCKS
+
+#include <asm/qspinlock.h>
+
+static void kvm_wait(u8 *ptr, u8 val)
+{
+	unsigned long flags;
+
+	if (in_nmi())
+		return;
+
+	local_irq_save(flags);
+
+	if (READ_ONCE(*ptr) != val)
+		goto out;
+
+	/*
+	 * halt until it's our turn and kicked. Note that we do safe halt
+	 * for irq enabled case to avoid hang when lock info is overwritten
+	 * in irq spinlock slowpath and no spurious interrupt occur to save us.
+	 */
+	if (arch_irqs_disabled_flags(flags))
+		halt();
+	else
+		safe_halt();
+
+out:
+	local_irq_restore(flags);
+}
+
+#else /* !CONFIG_QUEUED_SPINLOCKS */
+
 enum kvm_contention_stat {
 	TAKEN_SLOW,
 	TAKEN_SLOW_PICKUP,
@@ -817,6 +850,8 @@ static void kvm_unlock_kick(struct arch_spinlock *lock, __ticket_t ticket)
 	}
 }
 
+#endif /* !CONFIG_QUEUED_SPINLOCKS */
+
 /*
  * Setup pv_lock_ops to exploit KVM_FEATURE_PV_UNHALT if present.
  */
@@ -828,8 +863,16 @@ void __init kvm_spinlock_init(void)
 	if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT))
 		return;
 
+#ifdef CONFIG_QUEUED_SPINLOCKS
+	__pv_init_lock_hash();
+	pv_lock_ops.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath;
+	pv_lock_ops.queued_spin_unlock = PV_CALLEE_SAVE(__pv_queued_spin_unlock);
+	pv_lock_ops.wait = kvm_wait;
+	pv_lock_ops.kick = kvm_kick_cpu;
+#else /* !CONFIG_QUEUED_SPINLOCKS */
 	pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(kvm_lock_spinning);
 	pv_lock_ops.unlock_kick = kvm_unlock_kick;
+#endif
 }
 
 static __init int kvm_spinlock_init_jump(void)
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 415480d3ea84..819ab3f9c9c7 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -17,6 +17,7 @@
 #include <linux/ftrace.h>
 #include <linux/io.h>
 #include <linux/suspend.h>
+#include <linux/vmalloc.h>
 
 #include <asm/init.h>
 #include <asm/pgtable.h>
@@ -25,6 +26,7 @@
 #include <asm/io_apic.h>
 #include <asm/debugreg.h>
 #include <asm/kexec-bzimage64.h>
+#include <asm/setup.h>
 
 #ifdef CONFIG_KEXEC_FILE
 static struct kexec_file_ops *kexec_file_loaders[] = {
@@ -334,7 +336,7 @@ void arch_crash_save_vmcoreinfo(void)
 	VMCOREINFO_LENGTH(node_data, MAX_NUMNODES);
 #endif
 	vmcoreinfo_append_str("KERNELOFFSET=%lx\n",
-			      (unsigned long)&_text - __START_KERNEL);
+			      kaslr_offset());
 }
 
 /* arch-dependent functionality related to kexec file-based syscall */
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index 2d2a237f2c73..30ca7607cbbb 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -19,8 +19,8 @@
 #include <linux/module.h>
 #include <linux/smp.h>
 #include <linux/pci.h>
-#include <linux/irqdomain.h>
 
+#include <asm/irqdomain.h>
 #include <asm/mtrr.h>
 #include <asm/mpspec.h>
 #include <asm/pgalloc.h>
@@ -113,11 +113,6 @@ static void __init MP_bus_info(struct mpc_bus *m)
 		pr_warn("Unknown bustype %s - ignoring\n", str);
 }
 
-static struct irq_domain_ops mp_ioapic_irqdomain_ops = {
-	.map = mp_irqdomain_map,
-	.unmap = mp_irqdomain_unmap,
-};
-
 static void __init MP_ioapic_info(struct mpc_ioapic *m)
 {
 	struct ioapic_domain_cfg cfg = {
diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c
index bbb6c7316341..33ee3e0efd65 100644
--- a/arch/x86/kernel/paravirt-spinlocks.c
+++ b/arch/x86/kernel/paravirt-spinlocks.c
@@ -8,11 +8,33 @@
 
 #include <asm/paravirt.h>
 
+#ifdef CONFIG_QUEUED_SPINLOCKS
+__visible void __native_queued_spin_unlock(struct qspinlock *lock)
+{
+	native_queued_spin_unlock(lock);
+}
+
+PV_CALLEE_SAVE_REGS_THUNK(__native_queued_spin_unlock);
+
+bool pv_is_native_spin_unlock(void)
+{
+	return pv_lock_ops.queued_spin_unlock.func ==
+		__raw_callee_save___native_queued_spin_unlock;
+}
+#endif
+
 struct pv_lock_ops pv_lock_ops = {
 #ifdef CONFIG_SMP
+#ifdef CONFIG_QUEUED_SPINLOCKS
+	.queued_spin_lock_slowpath = native_queued_spin_lock_slowpath,
+	.queued_spin_unlock = PV_CALLEE_SAVE(__native_queued_spin_unlock),
+	.wait = paravirt_nop,
+	.kick = paravirt_nop,
+#else /* !CONFIG_QUEUED_SPINLOCKS */
 	.lock_spinning = __PV_IS_CALLEE_SAVE(paravirt_nop),
 	.unlock_kick = paravirt_nop,
-#endif
+#endif /* !CONFIG_QUEUED_SPINLOCKS */
+#endif /* SMP */
 };
 EXPORT_SYMBOL(pv_lock_ops);
 
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index c614dd492f5f..58bcfb67c01f 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -154,7 +154,9 @@ unsigned paravirt_patch_default(u8 type, u16 clobbers, void *insnbuf,
 		ret = paravirt_patch_ident_64(insnbuf, len);
 
 	else if (type == PARAVIRT_PATCH(pv_cpu_ops.iret) ||
+#ifdef CONFIG_X86_32
 		 type == PARAVIRT_PATCH(pv_cpu_ops.irq_enable_sysexit) ||
+#endif
 		 type == PARAVIRT_PATCH(pv_cpu_ops.usergs_sysret32) ||
 		 type == PARAVIRT_PATCH(pv_cpu_ops.usergs_sysret64))
 		/* If operation requires a jmp, then jmp */
@@ -371,7 +373,7 @@ __visible struct pv_cpu_ops pv_cpu_ops = {
 
 	.load_sp0 = native_load_sp0,
 
-#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
+#if defined(CONFIG_X86_32)
 	.irq_enable_sysexit = native_irq_enable_sysexit,
 #endif
 #ifdef CONFIG_X86_64
diff --git a/arch/x86/kernel/paravirt_patch_32.c b/arch/x86/kernel/paravirt_patch_32.c
index d9f32e6d6ab6..e1b013696dde 100644
--- a/arch/x86/kernel/paravirt_patch_32.c
+++ b/arch/x86/kernel/paravirt_patch_32.c
@@ -12,6 +12,10 @@ DEF_NATIVE(pv_mmu_ops, read_cr3, "mov %cr3, %eax");
 DEF_NATIVE(pv_cpu_ops, clts, "clts");
 DEF_NATIVE(pv_cpu_ops, read_tsc, "rdtsc");
 
+#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS)
+DEF_NATIVE(pv_lock_ops, queued_spin_unlock, "movb $0, (%eax)");
+#endif
+
 unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len)
 {
 	/* arg in %eax, return in %eax */
@@ -24,6 +28,8 @@ unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len)
 	return 0;
 }
 
+extern bool pv_is_native_spin_unlock(void);
+
 unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
 		      unsigned long addr, unsigned len)
 {
@@ -47,14 +53,22 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
 		PATCH_SITE(pv_mmu_ops, write_cr3);
 		PATCH_SITE(pv_cpu_ops, clts);
 		PATCH_SITE(pv_cpu_ops, read_tsc);
-
-	patch_site:
-		ret = paravirt_patch_insns(ibuf, len, start, end);
-		break;
+#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS)
+		case PARAVIRT_PATCH(pv_lock_ops.queued_spin_unlock):
+			if (pv_is_native_spin_unlock()) {
+				start = start_pv_lock_ops_queued_spin_unlock;
+				end   = end_pv_lock_ops_queued_spin_unlock;
+				goto patch_site;
+			}
+#endif
 
 	default:
 		ret = paravirt_patch_default(type, clobbers, ibuf, addr, len);
 		break;
+
+patch_site:
+		ret = paravirt_patch_insns(ibuf, len, start, end);
+		break;
 	}
 #undef PATCH_SITE
 	return ret;
diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c
index a1da6737ba5b..8aa05583bc42 100644
--- a/arch/x86/kernel/paravirt_patch_64.c
+++ b/arch/x86/kernel/paravirt_patch_64.c
@@ -21,6 +21,10 @@ DEF_NATIVE(pv_cpu_ops, swapgs, "swapgs");
 DEF_NATIVE(, mov32, "mov %edi, %eax");
 DEF_NATIVE(, mov64, "mov %rdi, %rax");
 
+#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS)
+DEF_NATIVE(pv_lock_ops, queued_spin_unlock, "movb $0, (%rdi)");
+#endif
+
 unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len)
 {
 	return paravirt_patch_insns(insnbuf, len,
@@ -33,6 +37,8 @@ unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len)
 				    start__mov64, end__mov64);
 }
 
+extern bool pv_is_native_spin_unlock(void);
+
 unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
 		      unsigned long addr, unsigned len)
 {
@@ -49,7 +55,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
 		PATCH_SITE(pv_irq_ops, save_fl);
 		PATCH_SITE(pv_irq_ops, irq_enable);
 		PATCH_SITE(pv_irq_ops, irq_disable);
-		PATCH_SITE(pv_cpu_ops, irq_enable_sysexit);
 		PATCH_SITE(pv_cpu_ops, usergs_sysret32);
 		PATCH_SITE(pv_cpu_ops, usergs_sysret64);
 		PATCH_SITE(pv_cpu_ops, swapgs);
@@ -59,14 +64,22 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
 		PATCH_SITE(pv_cpu_ops, clts);
 		PATCH_SITE(pv_mmu_ops, flush_tlb_single);
 		PATCH_SITE(pv_cpu_ops, wbinvd);
-
-	patch_site:
-		ret = paravirt_patch_insns(ibuf, len, start, end);
-		break;
+#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS)
+		case PARAVIRT_PATCH(pv_lock_ops.queued_spin_unlock):
+			if (pv_is_native_spin_unlock()) {
+				start = start_pv_lock_ops_queued_spin_unlock;
+				end   = end_pv_lock_ops_queued_spin_unlock;
+				goto patch_site;
+			}
+#endif
 
 	default:
 		ret = paravirt_patch_default(type, clobbers, ibuf, addr, len);
 		break;
+
+patch_site:
+		ret = paravirt_patch_insns(ibuf, len, start, end);
+		break;
 	}
 #undef PATCH_SITE
 	return ret;
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index a25e202bb319..353972c1946c 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -140,6 +140,51 @@ void dma_generic_free_coherent(struct device *dev, size_t size, void *vaddr,
 		free_pages((unsigned long)vaddr, get_order(size));
 }
 
+void *dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
+		      gfp_t gfp, struct dma_attrs *attrs)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+	void *memory;
+
+	gfp &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32);
+
+	if (dma_alloc_from_coherent(dev, size, dma_handle, &memory))
+		return memory;
+
+	if (!dev)
+		dev = &x86_dma_fallback_dev;
+
+	if (!is_device_dma_capable(dev))
+		return NULL;
+
+	if (!ops->alloc)
+		return NULL;
+
+	memory = ops->alloc(dev, size, dma_handle,
+			    dma_alloc_coherent_gfp_flags(dev, gfp), attrs);
+	debug_dma_alloc_coherent(dev, size, *dma_handle, memory);
+
+	return memory;
+}
+EXPORT_SYMBOL(dma_alloc_attrs);
+
+void dma_free_attrs(struct device *dev, size_t size,
+		    void *vaddr, dma_addr_t bus,
+		    struct dma_attrs *attrs)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+
+	WARN_ON(irqs_disabled());       /* for portability */
+
+	if (dma_release_from_coherent(dev, get_order(size), vaddr))
+		return;
+
+	debug_dma_free_coherent(dev, size, vaddr, bus);
+	if (ops->free)
+		ops->free(dev, size, vaddr, bus, attrs);
+}
+EXPORT_SYMBOL(dma_free_attrs);
+
 /*
  * See <Documentation/x86/x86_64/boot-options.txt> for the iommu kernel
  * parameter documentation.
diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c
index 77dd0ad58be4..adf0392d549a 100644
--- a/arch/x86/kernel/pci-swiotlb.c
+++ b/arch/x86/kernel/pci-swiotlb.c
@@ -20,6 +20,13 @@ void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 {
 	void *vaddr;
 
+	/*
+	 * Don't print a warning when the first allocation attempt fails.
+	 * swiotlb_alloc_coherent() will print a warning when the DMA
+	 * memory allocation ultimately failed.
+	 */
+	flags |= __GFP_NOWARN;
+
 	vaddr = dma_generic_alloc_coherent(hwdev, size, dma_handle, flags,
 					   attrs);
 	if (vaddr)
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 6e338e3b1dc0..9cad694ed7c4 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -25,8 +25,7 @@
 #include <asm/idle.h>
 #include <asm/uaccess.h>
 #include <asm/mwait.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
 #include <asm/debugreg.h>
 #include <asm/nmi.h>
 #include <asm/tlbflush.h>
@@ -76,9 +75,6 @@ void idle_notifier_unregister(struct notifier_block *n)
 EXPORT_SYMBOL_GPL(idle_notifier_unregister);
 #endif
 
-struct kmem_cache *task_xstate_cachep;
-EXPORT_SYMBOL_GPL(task_xstate_cachep);
-
 /*
  * this gets called so that we can store lazy state into memory and copy the
  * current task into the new thread.
@@ -87,36 +83,7 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 {
 	*dst = *src;
 
-	dst->thread.fpu_counter = 0;
-	dst->thread.fpu.has_fpu = 0;
-	dst->thread.fpu.state = NULL;
-	task_disable_lazy_fpu_restore(dst);
-	if (tsk_used_math(src)) {
-		int err = fpu_alloc(&dst->thread.fpu);
-		if (err)
-			return err;
-		fpu_copy(dst, src);
-	}
-	return 0;
-}
-
-void free_thread_xstate(struct task_struct *tsk)
-{
-	fpu_free(&tsk->thread.fpu);
-}
-
-void arch_release_task_struct(struct task_struct *tsk)
-{
-	free_thread_xstate(tsk);
-}
-
-void arch_task_cache_init(void)
-{
-        task_xstate_cachep =
-        	kmem_cache_create("task_xstate", xstate_size,
-				  __alignof__(union thread_xstate),
-				  SLAB_PANIC | SLAB_NOTRACK, NULL);
-	setup_xstate_comp();
+	return fpu__copy(&dst->thread.fpu, &src->thread.fpu);
 }
 
 /*
@@ -127,6 +94,7 @@ void exit_thread(void)
 	struct task_struct *me = current;
 	struct thread_struct *t = &me->thread;
 	unsigned long *bp = t->io_bitmap_ptr;
+	struct fpu *fpu = &t->fpu;
 
 	if (bp) {
 		struct tss_struct *tss = &per_cpu(cpu_tss, get_cpu());
@@ -142,7 +110,7 @@ void exit_thread(void)
 		kfree(bp);
 	}
 
-	drop_fpu(me);
+	fpu__drop(fpu);
 }
 
 void flush_thread(void)
@@ -152,19 +120,7 @@ void flush_thread(void)
 	flush_ptrace_hw_breakpoint(tsk);
 	memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array));
 
-	if (!use_eager_fpu()) {
-		/* FPU state will be reallocated lazily at the first use. */
-		drop_fpu(tsk);
-		free_thread_xstate(tsk);
-	} else {
-		if (!tsk_used_math(tsk)) {
-			/* kthread execs. TODO: cleanup this horror. */
-			if (WARN_ON(init_fpu(tsk)))
-				force_sig(SIGKILL, tsk);
-			user_fpu_begin();
-		}
-		restore_init_xstate();
-	}
+	fpu__clear(&tsk->thread.fpu);
 }
 
 static void hard_disable_TSC(void)
@@ -445,11 +401,10 @@ static int prefer_mwait_c1_over_halt(const struct cpuinfo_x86 *c)
 }
 
 /*
- * MONITOR/MWAIT with no hints, used for default default C1 state.
- * This invokes MWAIT with interrutps enabled and no flags,
- * which is backwards compatible with the original MWAIT implementation.
+ * MONITOR/MWAIT with no hints, used for default C1 state. This invokes MWAIT
+ * with interrupts enabled and no flags, which is backwards compatible with the
+ * original MWAIT implementation.
  */
-
 static void mwait_idle(void)
 {
 	if (!current_set_polling_and_test()) {
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 8ed2106b06da..c09c99ccf3e3 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -39,8 +39,7 @@
 #include <asm/pgtable.h>
 #include <asm/ldt.h>
 #include <asm/processor.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
 #include <asm/desc.h>
 #ifdef CONFIG_MATH_EMULATION
 #include <asm/math_emu.h>
@@ -242,14 +241,16 @@ __visible __notrace_funcgraph struct task_struct *
 __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 {
 	struct thread_struct *prev = &prev_p->thread,
-				 *next = &next_p->thread;
+			     *next = &next_p->thread;
+	struct fpu *prev_fpu = &prev->fpu;
+	struct fpu *next_fpu = &next->fpu;
 	int cpu = smp_processor_id();
 	struct tss_struct *tss = &per_cpu(cpu_tss, cpu);
-	fpu_switch_t fpu;
+	fpu_switch_t fpu_switch;
 
 	/* never put a printk in __switch_to... printk() calls wake_up*() indirectly */
 
-	fpu = switch_fpu_prepare(prev_p, next_p, cpu);
+	fpu_switch = switch_fpu_prepare(prev_fpu, next_fpu, cpu);
 
 	/*
 	 * Save away %gs. No need to save %fs, as it was saved on the
@@ -296,19 +297,16 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	 * Leave lazy mode, flushing any hypercalls made here.
 	 * This must be done before restoring TLS segments so
 	 * the GDT and LDT are properly updated, and must be
-	 * done before math_state_restore, so the TS bit is up
+	 * done before fpu__restore(), so the TS bit is up
 	 * to date.
 	 */
 	arch_end_context_switch(next_p);
 
 	/*
-	 * Reload esp0, kernel_stack, and current_top_of_stack.  This changes
+	 * Reload esp0 and cpu_current_top_of_stack.  This changes
 	 * current_thread_info().
 	 */
 	load_sp0(tss, next);
-	this_cpu_write(kernel_stack,
-		       (unsigned long)task_stack_page(next_p) +
-		       THREAD_SIZE);
 	this_cpu_write(cpu_current_top_of_stack,
 		       (unsigned long)task_stack_page(next_p) +
 		       THREAD_SIZE);
@@ -319,7 +317,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	if (prev->gs | next->gs)
 		lazy_load_gs(next->gs);
 
-	switch_fpu_finish(next_p, fpu);
+	switch_fpu_finish(next_fpu, fpu_switch);
 
 	this_cpu_write(current_task, next_p);
 
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index ddfdbf74f174..843f92e4c711 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -38,8 +38,7 @@
 
 #include <asm/pgtable.h>
 #include <asm/processor.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
 #include <asm/mmu_context.h>
 #include <asm/prctl.h>
 #include <asm/desc.h>
@@ -274,12 +273,14 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 {
 	struct thread_struct *prev = &prev_p->thread;
 	struct thread_struct *next = &next_p->thread;
+	struct fpu *prev_fpu = &prev->fpu;
+	struct fpu *next_fpu = &next->fpu;
 	int cpu = smp_processor_id();
 	struct tss_struct *tss = &per_cpu(cpu_tss, cpu);
 	unsigned fsindex, gsindex;
-	fpu_switch_t fpu;
+	fpu_switch_t fpu_switch;
 
-	fpu = switch_fpu_prepare(prev_p, next_p, cpu);
+	fpu_switch = switch_fpu_prepare(prev_fpu, next_fpu, cpu);
 
 	/* We must save %fs and %gs before load_TLS() because
 	 * %fs and %gs may be cleared by load_TLS().
@@ -299,7 +300,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	 * Leave lazy mode, flushing any hypercalls made here.  This
 	 * must be done after loading TLS entries in the GDT but before
 	 * loading segments that might reference them, and and it must
-	 * be done before math_state_restore, so the TS bit is up to
+	 * be done before fpu__restore(), so the TS bit is up to
 	 * date.
 	 */
 	arch_end_context_switch(next_p);
@@ -391,7 +392,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 		wrmsrl(MSR_KERNEL_GS_BASE, next->gs);
 	prev->gsindex = gsindex;
 
-	switch_fpu_finish(next_p, fpu);
+	switch_fpu_finish(next_fpu, fpu_switch);
 
 	/*
 	 * Switch the PDA and FPU contexts.
@@ -409,9 +410,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	/* Reload esp0 and ss1.  This changes current_thread_info(). */
 	load_sp0(tss, next);
 
-	this_cpu_write(kernel_stack,
-		(unsigned long)task_stack_page(next_p) + THREAD_SIZE);
-
 	/*
 	 * Now maybe reload the debug registers and handle I/O bitmaps
 	 */
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index a7bc79480719..9be72bc3613f 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -11,7 +11,6 @@
 #include <linux/errno.h>
 #include <linux/slab.h>
 #include <linux/ptrace.h>
-#include <linux/regset.h>
 #include <linux/tracehook.h>
 #include <linux/user.h>
 #include <linux/elf.h>
@@ -28,8 +27,9 @@
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/processor.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
+#include <asm/fpu/signal.h>
+#include <asm/fpu/regset.h>
 #include <asm/debugreg.h>
 #include <asm/ldt.h>
 #include <asm/desc.h>
@@ -1297,7 +1297,7 @@ static struct user_regset x86_64_regsets[] __read_mostly = {
 		.core_note_type = NT_PRFPREG,
 		.n = sizeof(struct user_i387_struct) / sizeof(long),
 		.size = sizeof(long), .align = sizeof(long),
-		.active = xfpregs_active, .get = xfpregs_get, .set = xfpregs_set
+		.active = regset_xregset_fpregs_active, .get = xfpregs_get, .set = xfpregs_set
 	},
 	[REGSET_XSTATE] = {
 		.core_note_type = NT_X86_XSTATE,
@@ -1338,13 +1338,13 @@ static struct user_regset x86_32_regsets[] __read_mostly = {
 		.core_note_type = NT_PRFPREG,
 		.n = sizeof(struct user_i387_ia32_struct) / sizeof(u32),
 		.size = sizeof(u32), .align = sizeof(u32),
-		.active = fpregs_active, .get = fpregs_get, .set = fpregs_set
+		.active = regset_fpregs_active, .get = fpregs_get, .set = fpregs_set
 	},
 	[REGSET_XFP] = {
 		.core_note_type = NT_PRXFPREG,
 		.n = sizeof(struct user32_fxsr_struct) / sizeof(u32),
 		.size = sizeof(u32), .align = sizeof(u32),
-		.active = xfpregs_active, .get = xfpregs_get, .set = xfpregs_set
+		.active = regset_xregset_fpregs_active, .get = xfpregs_get, .set = xfpregs_set
 	},
 	[REGSET_XSTATE] = {
 		.core_note_type = NT_X86_XSTATE,
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index d74ac33290ae..39ca113676fe 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -531,12 +531,14 @@ static void __init reserve_crashkernel_low(void)
 	if (ret != 0) {
 		/*
 		 * two parts from lib/swiotlb.c:
-		 *	swiotlb size: user specified with swiotlb= or default.
-		 *	swiotlb overflow buffer: now is hardcoded to 32k.
-		 *		We round it to 8M for other buffers that
-		 *		may need to stay low too.
+		 * -swiotlb size: user-specified with swiotlb= or default.
+		 *
+		 * -swiotlb overflow buffer: now hardcoded to 32k. We round it
+		 * to 8M for other buffers that may need to stay low too. Also
+		 * make sure we allocate enough extra low memory so that we
+		 * don't run out of DMA buffers for 32-bit devices.
 		 */
-		low_size = swiotlb_size_or_default() + (8UL<<20);
+		low_size = max(swiotlb_size_or_default() + (8UL<<20), 256UL<<20);
 		auto_set = true;
 	} else {
 		/* passed with crashkernel=0,low ? */
@@ -834,7 +836,7 @@ dump_kernel_offset(struct notifier_block *self, unsigned long v, void *p)
 {
 	if (kaslr_enabled()) {
 		pr_emerg("Kernel Offset: 0x%lx from 0x%lx (relocation range: 0x%lx-0x%lx)\n",
-			 (unsigned long)&_text - __START_KERNEL,
+			 kaslr_offset(),
 			 __START_KERNEL,
 			 __START_KERNEL_map,
 			 MODULES_VADDR-1);
@@ -1222,8 +1224,7 @@ void __init setup_arch(char **cmdline_p)
 	init_cpu_to_node();
 
 	init_apic_mappings();
-	if (x86_io_apic_ops.init)
-		x86_io_apic_ops.init();
+	io_apic_init_mappings();
 
 	kvm_guest_init();
 
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 1ea14fd53933..206996c1669d 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -26,8 +26,8 @@
 
 #include <asm/processor.h>
 #include <asm/ucontext.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
+#include <asm/fpu/signal.h>
 #include <asm/vdso.h>
 #include <asm/mce.h>
 #include <asm/sighandling.h>
@@ -103,7 +103,7 @@ int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc)
 		get_user_ex(buf, &sc->fpstate);
 	} get_user_catch(err);
 
-	err |= restore_xstate_sig(buf, config_enabled(CONFIG_X86_32));
+	err |= fpu__restore_sig(buf, config_enabled(CONFIG_X86_32));
 
 	force_iret();
 
@@ -199,6 +199,7 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size,
 	unsigned long sp = regs->sp;
 	unsigned long buf_fx = 0;
 	int onsigstack = on_sig_stack(sp);
+	struct fpu *fpu = &current->thread.fpu;
 
 	/* redzone */
 	if (config_enabled(CONFIG_X86_64))
@@ -218,9 +219,9 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size,
 		}
 	}
 
-	if (used_math()) {
-		sp = alloc_mathframe(sp, config_enabled(CONFIG_X86_32),
-				     &buf_fx, &math_size);
+	if (fpu->fpstate_active) {
+		sp = fpu__alloc_mathframe(sp, config_enabled(CONFIG_X86_32),
+					  &buf_fx, &math_size);
 		*fpstate = (void __user *)sp;
 	}
 
@@ -234,8 +235,8 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size,
 		return (void __user *)-1L;
 
 	/* save i387 and extended state */
-	if (used_math() &&
-	    save_xstate_sig(*fpstate, (void __user *)buf_fx, math_size) < 0)
+	if (fpu->fpstate_active &&
+	    copy_fpstate_to_sigframe(*fpstate, (void __user *)buf_fx, math_size) < 0)
 		return (void __user *)-1L;
 
 	return (void __user *)sp;
@@ -593,6 +594,22 @@ badframe:
 	return 0;
 }
 
+static inline int is_ia32_compat_frame(void)
+{
+	return config_enabled(CONFIG_IA32_EMULATION) &&
+	       test_thread_flag(TIF_IA32);
+}
+
+static inline int is_ia32_frame(void)
+{
+	return config_enabled(CONFIG_X86_32) || is_ia32_compat_frame();
+}
+
+static inline int is_x32_frame(void)
+{
+	return config_enabled(CONFIG_X86_X32_ABI) && test_thread_flag(TIF_X32);
+}
+
 static int
 setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs)
 {
@@ -617,6 +634,7 @@ static void
 handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 {
 	bool stepping, failed;
+	struct fpu *fpu = &current->thread.fpu;
 
 	/* Are we from a system call? */
 	if (syscall_get_nr(current, regs) >= 0) {
@@ -665,8 +683,8 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 		/*
 		 * Ensure the signal handler starts with the new fpu state.
 		 */
-		if (used_math())
-			fpu_reset_state(current);
+		if (fpu->fpstate_active)
+			fpu__clear(fpu);
 	}
 	signal_setup_done(failed, ksig, stepping);
 }
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index be8e1bde07aa..15aaa69bbb5e 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -170,8 +170,7 @@ static int smp_stop_nmi_callback(unsigned int val, struct pt_regs *regs)
 
 asmlinkage __visible void smp_reboot_interrupt(void)
 {
-	ack_APIC_irq();
-	irq_enter();
+	ipi_entering_ack_irq();
 	stop_this_cpu(NULL);
 	irq_exit();
 }
@@ -265,12 +264,6 @@ __visible void smp_reschedule_interrupt(struct pt_regs *regs)
 	 */
 }
 
-static inline void smp_entering_irq(void)
-{
-	ack_APIC_irq();
-	irq_enter();
-}
-
 __visible void smp_trace_reschedule_interrupt(struct pt_regs *regs)
 {
 	/*
@@ -279,7 +272,7 @@ __visible void smp_trace_reschedule_interrupt(struct pt_regs *regs)
 	 * scheduler_ipi(). This is OK, since those functions are allowed
 	 * to nest.
 	 */
-	smp_entering_irq();
+	ipi_entering_ack_irq();
 	trace_reschedule_entry(RESCHEDULE_VECTOR);
 	__smp_reschedule_interrupt();
 	trace_reschedule_exit(RESCHEDULE_VECTOR);
@@ -297,14 +290,14 @@ static inline void __smp_call_function_interrupt(void)
 
 __visible void smp_call_function_interrupt(struct pt_regs *regs)
 {
-	smp_entering_irq();
+	ipi_entering_ack_irq();
 	__smp_call_function_interrupt();
 	exiting_irq();
 }
 
 __visible void smp_trace_call_function_interrupt(struct pt_regs *regs)
 {
-	smp_entering_irq();
+	ipi_entering_ack_irq();
 	trace_call_function_entry(CALL_FUNCTION_VECTOR);
 	__smp_call_function_interrupt();
 	trace_call_function_exit(CALL_FUNCTION_VECTOR);
@@ -319,14 +312,14 @@ static inline void __smp_call_function_single_interrupt(void)
 
 __visible void smp_call_function_single_interrupt(struct pt_regs *regs)
 {
-	smp_entering_irq();
+	ipi_entering_ack_irq();
 	__smp_call_function_single_interrupt();
 	exiting_irq();
 }
 
 __visible void smp_trace_call_function_single_interrupt(struct pt_regs *regs)
 {
-	smp_entering_irq();
+	ipi_entering_ack_irq();
 	trace_call_function_single_entry(CALL_FUNCTION_SINGLE_VECTOR);
 	__smp_call_function_single_interrupt();
 	trace_call_function_single_exit(CALL_FUNCTION_SINGLE_VECTOR);
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 50e547eac8cd..8add66b22f33 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -68,8 +68,7 @@
 #include <asm/mwait.h>
 #include <asm/apic.h>
 #include <asm/io_apic.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
 #include <asm/setup.h>
 #include <asm/uv/uv.h>
 #include <linux/mc146818rtc.h>
@@ -314,10 +313,10 @@ topology_sane(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o, const char *name)
 		cpu1, name, cpu2, cpu_to_node(cpu1), cpu_to_node(cpu2));
 }
 
-#define link_mask(_m, c1, c2)						\
+#define link_mask(mfunc, c1, c2)					\
 do {									\
-	cpumask_set_cpu((c1), cpu_##_m##_mask(c2));			\
-	cpumask_set_cpu((c2), cpu_##_m##_mask(c1));			\
+	cpumask_set_cpu((c1), mfunc(c2));				\
+	cpumask_set_cpu((c2), mfunc(c1));				\
 } while (0)
 
 static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
@@ -398,9 +397,9 @@ void set_cpu_sibling_map(int cpu)
 	cpumask_set_cpu(cpu, cpu_sibling_setup_mask);
 
 	if (!has_mp) {
-		cpumask_set_cpu(cpu, cpu_sibling_mask(cpu));
+		cpumask_set_cpu(cpu, topology_sibling_cpumask(cpu));
 		cpumask_set_cpu(cpu, cpu_llc_shared_mask(cpu));
-		cpumask_set_cpu(cpu, cpu_core_mask(cpu));
+		cpumask_set_cpu(cpu, topology_core_cpumask(cpu));
 		c->booted_cores = 1;
 		return;
 	}
@@ -409,32 +408,34 @@ void set_cpu_sibling_map(int cpu)
 		o = &cpu_data(i);
 
 		if ((i == cpu) || (has_smt && match_smt(c, o)))
-			link_mask(sibling, cpu, i);
+			link_mask(topology_sibling_cpumask, cpu, i);
 
 		if ((i == cpu) || (has_mp && match_llc(c, o)))
-			link_mask(llc_shared, cpu, i);
+			link_mask(cpu_llc_shared_mask, cpu, i);
 
 	}
 
 	/*
 	 * This needs a separate iteration over the cpus because we rely on all
-	 * cpu_sibling_mask links to be set-up.
+	 * topology_sibling_cpumask links to be set-up.
 	 */
 	for_each_cpu(i, cpu_sibling_setup_mask) {
 		o = &cpu_data(i);
 
 		if ((i == cpu) || (has_mp && match_die(c, o))) {
-			link_mask(core, cpu, i);
+			link_mask(topology_core_cpumask, cpu, i);
 
 			/*
 			 *  Does this new cpu bringup a new core?
 			 */
-			if (cpumask_weight(cpu_sibling_mask(cpu)) == 1) {
+			if (cpumask_weight(
+			    topology_sibling_cpumask(cpu)) == 1) {
 				/*
 				 * for each core in package, increment
 				 * the booted_cores for this new cpu
 				 */
-				if (cpumask_first(cpu_sibling_mask(i)) == i)
+				if (cpumask_first(
+				    topology_sibling_cpumask(i)) == i)
 					c->booted_cores++;
 				/*
 				 * increment the core count for all
@@ -514,6 +515,40 @@ void __inquire_remote_apic(int apicid)
 }
 
 /*
+ * The Multiprocessor Specification 1.4 (1997) example code suggests
+ * that there should be a 10ms delay between the BSP asserting INIT
+ * and de-asserting INIT, when starting a remote processor.
+ * But that slows boot and resume on modern processors, which include
+ * many cores and don't require that delay.
+ *
+ * Cmdline "init_cpu_udelay=" is available to over-ride this delay.
+ * Modern processor families are quirked to remove the delay entirely.
+ */
+#define UDELAY_10MS_DEFAULT 10000
+
+static unsigned int init_udelay = UDELAY_10MS_DEFAULT;
+
+static int __init cpu_init_udelay(char *str)
+{
+	get_option(&str, &init_udelay);
+
+	return 0;
+}
+early_param("cpu_init_udelay", cpu_init_udelay);
+
+static void __init smp_quirk_init_udelay(void)
+{
+	/* if cmdline changed it from default, leave it alone */
+	if (init_udelay != UDELAY_10MS_DEFAULT)
+		return;
+
+	/* if modern processor, use no delay */
+	if (((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) && (boot_cpu_data.x86 == 6)) ||
+	    ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && (boot_cpu_data.x86 >= 0xF)))
+		init_udelay = 0;
+}
+
+/*
  * Poke the other CPU in the eye via NMI to wake it up. Remember that the normal
  * INIT, INIT, STARTUP sequence will reset the chip hard for us, and this
  * won't ... remember to clear down the APIC, etc later.
@@ -555,7 +590,7 @@ wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip)
 static int
 wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip)
 {
-	unsigned long send_status, accept_status = 0;
+	unsigned long send_status = 0, accept_status = 0;
 	int maxlvt, num_starts, j;
 
 	maxlvt = lapic_get_maxlvt();
@@ -583,7 +618,7 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip)
 	pr_debug("Waiting for send to finish...\n");
 	send_status = safe_apic_wait_icr_idle();
 
-	mdelay(10);
+	udelay(init_udelay);
 
 	pr_debug("Deasserting INIT\n");
 
@@ -651,6 +686,7 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip)
 		 * Give the other CPU some time to accept the IPI.
 		 */
 		udelay(200);
+
 		if (maxlvt > 3)		/* Due to the Pentium erratum 3AP.  */
 			apic_write(APIC_ESR, 0);
 		accept_status = (apic_read(APIC_ESR) & 0xEF);
@@ -792,8 +828,6 @@ void common_cpu_up(unsigned int cpu, struct task_struct *idle)
 	clear_tsk_thread_flag(idle, TIF_FORK);
 	initial_gs = per_cpu_offset(cpu);
 #endif
-	per_cpu(kernel_stack, cpu) =
-		(unsigned long)task_stack_page(idle) + THREAD_SIZE;
 }
 
 /*
@@ -1009,8 +1043,8 @@ static __init void disable_smp(void)
 		physid_set_mask_of_physid(boot_cpu_physical_apicid, &phys_cpu_present_map);
 	else
 		physid_set_mask_of_physid(0, &phys_cpu_present_map);
-	cpumask_set_cpu(0, cpu_sibling_mask(0));
-	cpumask_set_cpu(0, cpu_core_mask(0));
+	cpumask_set_cpu(0, topology_sibling_cpumask(0));
+	cpumask_set_cpu(0, topology_core_cpumask(0));
 }
 
 enum {
@@ -1176,6 +1210,8 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 		uv_system_init();
 
 	set_mtrr_aps_delayed_init();
+
+	smp_quirk_init_udelay();
 }
 
 void arch_enable_nonboot_cpus_begin(void)
@@ -1293,22 +1329,22 @@ static void remove_siblinginfo(int cpu)
 	int sibling;
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 
-	for_each_cpu(sibling, cpu_core_mask(cpu)) {
-		cpumask_clear_cpu(cpu, cpu_core_mask(sibling));
+	for_each_cpu(sibling, topology_core_cpumask(cpu)) {
+		cpumask_clear_cpu(cpu, topology_core_cpumask(sibling));
 		/*/
 		 * last thread sibling in this cpu core going down
 		 */
-		if (cpumask_weight(cpu_sibling_mask(cpu)) == 1)
+		if (cpumask_weight(topology_sibling_cpumask(cpu)) == 1)
 			cpu_data(sibling).booted_cores--;
 	}
 
-	for_each_cpu(sibling, cpu_sibling_mask(cpu))
-		cpumask_clear_cpu(cpu, cpu_sibling_mask(sibling));
+	for_each_cpu(sibling, topology_sibling_cpumask(cpu))
+		cpumask_clear_cpu(cpu, topology_sibling_cpumask(sibling));
 	for_each_cpu(sibling, cpu_llc_shared_mask(cpu))
 		cpumask_clear_cpu(cpu, cpu_llc_shared_mask(sibling));
 	cpumask_clear(cpu_llc_shared_mask(cpu));
-	cpumask_clear(cpu_sibling_mask(cpu));
-	cpumask_clear(cpu_core_mask(cpu));
+	cpumask_clear(topology_sibling_cpumask(cpu));
+	cpumask_clear(topology_core_cpumask(cpu));
 	c->phys_proc_id = 0;
 	c->cpu_core_id = 0;
 	cpumask_clear_cpu(cpu, cpu_sibling_setup_mask);
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 324ab5247687..f5791927aa64 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -54,12 +54,13 @@
 #include <asm/ftrace.h>
 #include <asm/traps.h>
 #include <asm/desc.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
 #include <asm/mce.h>
 #include <asm/fixmap.h>
 #include <asm/mach_traps.h>
 #include <asm/alternative.h>
+#include <asm/fpu/xstate.h>
+#include <asm/trace/mpx.h>
 #include <asm/mpx.h>
 
 #ifdef CONFIG_X86_64
@@ -72,8 +73,7 @@ gate_desc debug_idt_table[NR_VECTORS] __page_aligned_bss;
 #else
 #include <asm/processor-flags.h>
 #include <asm/setup.h>
-
-asmlinkage int system_call(void);
+#include <asm/proto.h>
 #endif
 
 /* Must be page-aligned because the real IDT is used in a fixmap. */
@@ -371,10 +371,8 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
 
 dotraplinkage void do_bounds(struct pt_regs *regs, long error_code)
 {
-	struct task_struct *tsk = current;
-	struct xsave_struct *xsave_buf;
 	enum ctx_state prev_state;
-	struct bndcsr *bndcsr;
+	const struct bndcsr *bndcsr;
 	siginfo_t *info;
 
 	prev_state = exception_enter();
@@ -393,15 +391,15 @@ dotraplinkage void do_bounds(struct pt_regs *regs, long error_code)
 
 	/*
 	 * We need to look at BNDSTATUS to resolve this exception.
-	 * It is not directly accessible, though, so we need to
-	 * do an xsave and then pull it out of the xsave buffer.
+	 * A NULL here might mean that it is in its 'init state',
+	 * which is all zeros which indicates MPX was not
+	 * responsible for the exception.
 	 */
-	fpu_save_init(&tsk->thread.fpu);
-	xsave_buf = &(tsk->thread.fpu.state->xsave);
-	bndcsr = get_xsave_addr(xsave_buf, XSTATE_BNDCSR);
+	bndcsr = get_xsave_field_ptr(XSTATE_BNDCSR);
 	if (!bndcsr)
 		goto exit_trap;
 
+	trace_bounds_exception_mpx(bndcsr);
 	/*
 	 * The error code field of the BNDSTATUS register communicates status
 	 * information of a bound range exception #BR or operation involving
@@ -409,11 +407,11 @@ dotraplinkage void do_bounds(struct pt_regs *regs, long error_code)
 	 */
 	switch (bndcsr->bndstatus & MPX_BNDSTA_ERROR_CODE) {
 	case 2:	/* Bound directory has invalid entry. */
-		if (mpx_handle_bd_fault(xsave_buf))
+		if (mpx_handle_bd_fault())
 			goto exit_trap;
 		break; /* Success, it was handled */
 	case 1: /* Bound violation. */
-		info = mpx_generate_siginfo(regs, xsave_buf);
+		info = mpx_generate_siginfo(regs);
 		if (IS_ERR(info)) {
 			/*
 			 * We failed to decode the MPX instruction.  Act as if
@@ -709,8 +707,8 @@ NOKPROBE_SYMBOL(do_debug);
 static void math_error(struct pt_regs *regs, int error_code, int trapnr)
 {
 	struct task_struct *task = current;
+	struct fpu *fpu = &task->thread.fpu;
 	siginfo_t info;
-	unsigned short err;
 	char *str = (trapnr == X86_TRAP_MF) ? "fpu exception" :
 						"simd exception";
 
@@ -718,8 +716,7 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr)
 		return;
 	conditional_sti(regs);
 
-	if (!user_mode(regs))
-	{
+	if (!user_mode(regs)) {
 		if (!fixup_exception(regs)) {
 			task->thread.error_code = error_code;
 			task->thread.trap_nr = trapnr;
@@ -731,62 +728,20 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr)
 	/*
 	 * Save the info for the exception handler and clear the error.
 	 */
-	unlazy_fpu(task);
-	task->thread.trap_nr = trapnr;
+	fpu__save(fpu);
+
+	task->thread.trap_nr	= trapnr;
 	task->thread.error_code = error_code;
-	info.si_signo = SIGFPE;
-	info.si_errno = 0;
-	info.si_addr = (void __user *)uprobe_get_trap_addr(regs);
-	if (trapnr == X86_TRAP_MF) {
-		unsigned short cwd, swd;
-		/*
-		 * (~cwd & swd) will mask out exceptions that are not set to unmasked
-		 * status.  0x3f is the exception bits in these regs, 0x200 is the
-		 * C1 reg you need in case of a stack fault, 0x040 is the stack
-		 * fault bit.  We should only be taking one exception at a time,
-		 * so if this combination doesn't produce any single exception,
-		 * then we have a bad program that isn't synchronizing its FPU usage
-		 * and it will suffer the consequences since we won't be able to
-		 * fully reproduce the context of the exception
-		 */
-		cwd = get_fpu_cwd(task);
-		swd = get_fpu_swd(task);
+	info.si_signo		= SIGFPE;
+	info.si_errno		= 0;
+	info.si_addr		= (void __user *)uprobe_get_trap_addr(regs);
 
-		err = swd & ~cwd;
-	} else {
-		/*
-		 * The SIMD FPU exceptions are handled a little differently, as there
-		 * is only a single status/control register.  Thus, to determine which
-		 * unmasked exception was caught we must mask the exception mask bits
-		 * at 0x1f80, and then use these to mask the exception bits at 0x3f.
-		 */
-		unsigned short mxcsr = get_fpu_mxcsr(task);
-		err = ~(mxcsr >> 7) & mxcsr;
-	}
+	info.si_code = fpu__exception_code(fpu, trapnr);
 
-	if (err & 0x001) {	/* Invalid op */
-		/*
-		 * swd & 0x240 == 0x040: Stack Underflow
-		 * swd & 0x240 == 0x240: Stack Overflow
-		 * User must clear the SF bit (0x40) if set
-		 */
-		info.si_code = FPE_FLTINV;
-	} else if (err & 0x004) { /* Divide by Zero */
-		info.si_code = FPE_FLTDIV;
-	} else if (err & 0x008) { /* Overflow */
-		info.si_code = FPE_FLTOVF;
-	} else if (err & 0x012) { /* Denormal, Underflow */
-		info.si_code = FPE_FLTUND;
-	} else if (err & 0x020) { /* Precision */
-		info.si_code = FPE_FLTRES;
-	} else {
-		/*
-		 * If we're using IRQ 13, or supposedly even some trap
-		 * X86_TRAP_MF implementations, it's possible
-		 * we get a spurious trap, which is not an error.
-		 */
+	/* Retry when we get spurious exceptions: */
+	if (!info.si_code)
 		return;
-	}
+
 	force_sig_info(SIGFPE, &info, task);
 }
 
@@ -813,62 +768,8 @@ dotraplinkage void
 do_spurious_interrupt_bug(struct pt_regs *regs, long error_code)
 {
 	conditional_sti(regs);
-#if 0
-	/* No need to warn about this any longer. */
-	pr_info("Ignoring P6 Local APIC Spurious Interrupt Bug...\n");
-#endif
-}
-
-asmlinkage __visible void __attribute__((weak)) smp_thermal_interrupt(void)
-{
 }
 
-asmlinkage __visible void __attribute__((weak)) smp_threshold_interrupt(void)
-{
-}
-
-/*
- * 'math_state_restore()' saves the current math information in the
- * old math state array, and gets the new ones from the current task
- *
- * Careful.. There are problems with IBM-designed IRQ13 behaviour.
- * Don't touch unless you *really* know how it works.
- *
- * Must be called with kernel preemption disabled (eg with local
- * local interrupts as in the case of do_device_not_available).
- */
-void math_state_restore(void)
-{
-	struct task_struct *tsk = current;
-
-	if (!tsk_used_math(tsk)) {
-		local_irq_enable();
-		/*
-		 * does a slab alloc which can sleep
-		 */
-		if (init_fpu(tsk)) {
-			/*
-			 * ran out of memory!
-			 */
-			do_group_exit(SIGKILL);
-			return;
-		}
-		local_irq_disable();
-	}
-
-	/* Avoid __kernel_fpu_begin() right after __thread_fpu_begin() */
-	kernel_fpu_disable();
-	__thread_fpu_begin(tsk);
-	if (unlikely(restore_fpu_checking(tsk))) {
-		fpu_reset_state(tsk);
-		force_sig_info(SIGSEGV, SEND_SIG_PRIV, tsk);
-	} else {
-		tsk->thread.fpu_counter++;
-	}
-	kernel_fpu_enable();
-}
-EXPORT_SYMBOL_GPL(math_state_restore);
-
 dotraplinkage void
 do_device_not_available(struct pt_regs *regs, long error_code)
 {
@@ -889,7 +790,7 @@ do_device_not_available(struct pt_regs *regs, long error_code)
 		return;
 	}
 #endif
-	math_state_restore(); /* interrupts still off */
+	fpu__restore(&current->thread.fpu); /* interrupts still off */
 #ifdef CONFIG_X86_32
 	conditional_sti(regs);
 #endif
@@ -992,13 +893,13 @@ void __init trap_init(void)
 		set_bit(i, used_vectors);
 
 #ifdef CONFIG_IA32_EMULATION
-	set_system_intr_gate(IA32_SYSCALL_VECTOR, ia32_syscall);
+	set_system_intr_gate(IA32_SYSCALL_VECTOR, entry_INT80_compat);
 	set_bit(IA32_SYSCALL_VECTOR, used_vectors);
 #endif
 
 #ifdef CONFIG_X86_32
-	set_system_trap_gate(SYSCALL_VECTOR, &system_call);
-	set_bit(SYSCALL_VECTOR, used_vectors);
+	set_system_trap_gate(IA32_SYSCALL_VECTOR, entry_INT80_32);
+	set_bit(IA32_SYSCALL_VECTOR, used_vectors);
 #endif
 
 	/*
diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c
index 26488487bc61..dd8d0791dfb5 100644
--- a/arch/x86/kernel/tsc_sync.c
+++ b/arch/x86/kernel/tsc_sync.c
@@ -113,7 +113,7 @@ static void check_tsc_warp(unsigned int timeout)
  */
 static inline unsigned int loop_timeout(int cpu)
 {
-	return (cpumask_weight(cpu_core_mask(cpu)) > 1) ? 2 : 20;
+	return (cpumask_weight(topology_core_cpumask(cpu)) > 1) ? 2 : 20;
 }
 
 /*
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index 0b81ad67da07..66476244731e 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -29,6 +29,7 @@
 #include <linux/kdebug.h>
 #include <asm/processor.h>
 #include <asm/insn.h>
+#include <asm/mmu_context.h>
 
 /* Post-execution fixups. */
 
@@ -312,11 +313,6 @@ static int uprobe_init_insn(struct arch_uprobe *auprobe, struct insn *insn, bool
 }
 
 #ifdef CONFIG_X86_64
-static inline bool is_64bit_mm(struct mm_struct *mm)
-{
-	return	!config_enabled(CONFIG_IA32_EMULATION) ||
-		!(mm->context.ia32_compat == TIF_IA32);
-}
 /*
  * If arch_uprobe->insn doesn't use rip-relative addressing, return
  * immediately.  Otherwise, rewrite the instruction so that it accesses
@@ -497,10 +493,6 @@ static void riprel_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
 	}
 }
 #else /* 32-bit: */
-static inline bool is_64bit_mm(struct mm_struct *mm)
-{
-	return false;
-}
 /*
  * No RIP-relative addressing on 32-bit
  */
diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c
index 37d8fa4438f0..a0695be19864 100644
--- a/arch/x86/kernel/x8664_ksyms_64.c
+++ b/arch/x86/kernel/x8664_ksyms_64.c
@@ -75,7 +75,5 @@ EXPORT_SYMBOL(native_load_gs_index);
 
 #ifdef CONFIG_PREEMPT
 EXPORT_SYMBOL(___preempt_schedule);
-#ifdef CONFIG_CONTEXT_TRACKING
-EXPORT_SYMBOL(___preempt_schedule_context);
-#endif
+EXPORT_SYMBOL(___preempt_schedule_notrace);
 #endif
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index 234b0722de53..3839628d962e 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -11,7 +11,6 @@
 #include <asm/bios_ebda.h>
 #include <asm/paravirt.h>
 #include <asm/pci_x86.h>
-#include <asm/pci.h>
 #include <asm/mpspec.h>
 #include <asm/setup.h>
 #include <asm/apic.h>
@@ -111,11 +110,9 @@ EXPORT_SYMBOL_GPL(x86_platform);
 #if defined(CONFIG_PCI_MSI)
 struct x86_msi_ops x86_msi = {
 	.setup_msi_irqs		= native_setup_msi_irqs,
-	.compose_msi_msg	= native_compose_msi_msg,
 	.teardown_msi_irq	= native_teardown_msi_irq,
 	.teardown_msi_irqs	= default_teardown_msi_irqs,
 	.restore_msi_irqs	= default_restore_msi_irqs,
-	.setup_hpet_msi		= default_setup_hpet_msi,
 };
 
 /* MSI arch specific hooks */
@@ -141,13 +138,6 @@ void arch_restore_msi_irqs(struct pci_dev *dev)
 #endif
 
 struct x86_io_apic_ops x86_io_apic_ops = {
-	.init			= native_io_apic_init_mappings,
 	.read			= native_io_apic_read,
-	.write			= native_io_apic_write,
-	.modify			= native_io_apic_modify,
 	.disable		= native_disable_io_apic,
-	.print_entries		= native_io_apic_print_entries,
-	.set_affinity		= native_ioapic_set_affinity,
-	.setup_entry		= native_setup_ioapic_entry,
-	.eoi_ioapic_pin		= native_eoi_ioapic_pin,
 };
diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c
deleted file mode 100644
index 87a815b85f3e..000000000000
--- a/arch/x86/kernel/xsave.c
+++ /dev/null
@@ -1,724 +0,0 @@
-/*
- * xsave/xrstor support.
- *
- * Author: Suresh Siddha <suresh.b.siddha@intel.com>
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/bootmem.h>
-#include <linux/compat.h>
-#include <linux/cpu.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
-#include <asm/sigframe.h>
-#include <asm/tlbflush.h>
-#include <asm/xcr.h>
-
-/*
- * Supported feature mask by the CPU and the kernel.
- */
-u64 pcntxt_mask;
-
-/*
- * Represents init state for the supported extended state.
- */
-struct xsave_struct *init_xstate_buf;
-
-static struct _fpx_sw_bytes fx_sw_reserved, fx_sw_reserved_ia32;
-static unsigned int *xstate_offsets, *xstate_sizes;
-static unsigned int xstate_comp_offsets[sizeof(pcntxt_mask)*8];
-static unsigned int xstate_features;
-
-/*
- * If a processor implementation discern that a processor state component is
- * in its initialized state it may modify the corresponding bit in the
- * xsave_hdr.xstate_bv as '0', with out modifying the corresponding memory
- * layout in the case of xsaveopt. While presenting the xstate information to
- * the user, we always ensure that the memory layout of a feature will be in
- * the init state if the corresponding header bit is zero. This is to ensure
- * that the user doesn't see some stale state in the memory layout during
- * signal handling, debugging etc.
- */
-void __sanitize_i387_state(struct task_struct *tsk)
-{
-	struct i387_fxsave_struct *fx = &tsk->thread.fpu.state->fxsave;
-	int feature_bit = 0x2;
-	u64 xstate_bv;
-
-	if (!fx)
-		return;
-
-	xstate_bv = tsk->thread.fpu.state->xsave.xsave_hdr.xstate_bv;
-
-	/*
-	 * None of the feature bits are in init state. So nothing else
-	 * to do for us, as the memory layout is up to date.
-	 */
-	if ((xstate_bv & pcntxt_mask) == pcntxt_mask)
-		return;
-
-	/*
-	 * FP is in init state
-	 */
-	if (!(xstate_bv & XSTATE_FP)) {
-		fx->cwd = 0x37f;
-		fx->swd = 0;
-		fx->twd = 0;
-		fx->fop = 0;
-		fx->rip = 0;
-		fx->rdp = 0;
-		memset(&fx->st_space[0], 0, 128);
-	}
-
-	/*
-	 * SSE is in init state
-	 */
-	if (!(xstate_bv & XSTATE_SSE))
-		memset(&fx->xmm_space[0], 0, 256);
-
-	xstate_bv = (pcntxt_mask & ~xstate_bv) >> 2;
-
-	/*
-	 * Update all the other memory layouts for which the corresponding
-	 * header bit is in the init state.
-	 */
-	while (xstate_bv) {
-		if (xstate_bv & 0x1) {
-			int offset = xstate_offsets[feature_bit];
-			int size = xstate_sizes[feature_bit];
-
-			memcpy(((void *) fx) + offset,
-			       ((void *) init_xstate_buf) + offset,
-			       size);
-		}
-
-		xstate_bv >>= 1;
-		feature_bit++;
-	}
-}
-
-/*
- * Check for the presence of extended state information in the
- * user fpstate pointer in the sigcontext.
- */
-static inline int check_for_xstate(struct i387_fxsave_struct __user *buf,
-				   void __user *fpstate,
-				   struct _fpx_sw_bytes *fx_sw)
-{
-	int min_xstate_size = sizeof(struct i387_fxsave_struct) +
-			      sizeof(struct xsave_hdr_struct);
-	unsigned int magic2;
-
-	if (__copy_from_user(fx_sw, &buf->sw_reserved[0], sizeof(*fx_sw)))
-		return -1;
-
-	/* Check for the first magic field and other error scenarios. */
-	if (fx_sw->magic1 != FP_XSTATE_MAGIC1 ||
-	    fx_sw->xstate_size < min_xstate_size ||
-	    fx_sw->xstate_size > xstate_size ||
-	    fx_sw->xstate_size > fx_sw->extended_size)
-		return -1;
-
-	/*
-	 * Check for the presence of second magic word at the end of memory
-	 * layout. This detects the case where the user just copied the legacy
-	 * fpstate layout with out copying the extended state information
-	 * in the memory layout.
-	 */
-	if (__get_user(magic2, (__u32 __user *)(fpstate + fx_sw->xstate_size))
-	    || magic2 != FP_XSTATE_MAGIC2)
-		return -1;
-
-	return 0;
-}
-
-/*
- * Signal frame handlers.
- */
-static inline int save_fsave_header(struct task_struct *tsk, void __user *buf)
-{
-	if (use_fxsr()) {
-		struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave;
-		struct user_i387_ia32_struct env;
-		struct _fpstate_ia32 __user *fp = buf;
-
-		convert_from_fxsr(&env, tsk);
-
-		if (__copy_to_user(buf, &env, sizeof(env)) ||
-		    __put_user(xsave->i387.swd, &fp->status) ||
-		    __put_user(X86_FXSR_MAGIC, &fp->magic))
-			return -1;
-	} else {
-		struct i387_fsave_struct __user *fp = buf;
-		u32 swd;
-		if (__get_user(swd, &fp->swd) || __put_user(swd, &fp->status))
-			return -1;
-	}
-
-	return 0;
-}
-
-static inline int save_xstate_epilog(void __user *buf, int ia32_frame)
-{
-	struct xsave_struct __user *x = buf;
-	struct _fpx_sw_bytes *sw_bytes;
-	u32 xstate_bv;
-	int err;
-
-	/* Setup the bytes not touched by the [f]xsave and reserved for SW. */
-	sw_bytes = ia32_frame ? &fx_sw_reserved_ia32 : &fx_sw_reserved;
-	err = __copy_to_user(&x->i387.sw_reserved, sw_bytes, sizeof(*sw_bytes));
-
-	if (!use_xsave())
-		return err;
-
-	err |= __put_user(FP_XSTATE_MAGIC2, (__u32 *)(buf + xstate_size));
-
-	/*
-	 * Read the xstate_bv which we copied (directly from the cpu or
-	 * from the state in task struct) to the user buffers.
-	 */
-	err |= __get_user(xstate_bv, (__u32 *)&x->xsave_hdr.xstate_bv);
-
-	/*
-	 * For legacy compatible, we always set FP/SSE bits in the bit
-	 * vector while saving the state to the user context. This will
-	 * enable us capturing any changes(during sigreturn) to
-	 * the FP/SSE bits by the legacy applications which don't touch
-	 * xstate_bv in the xsave header.
-	 *
-	 * xsave aware apps can change the xstate_bv in the xsave
-	 * header as well as change any contents in the memory layout.
-	 * xrestore as part of sigreturn will capture all the changes.
-	 */
-	xstate_bv |= XSTATE_FPSSE;
-
-	err |= __put_user(xstate_bv, (__u32 *)&x->xsave_hdr.xstate_bv);
-
-	return err;
-}
-
-static inline int save_user_xstate(struct xsave_struct __user *buf)
-{
-	int err;
-
-	if (use_xsave())
-		err = xsave_user(buf);
-	else if (use_fxsr())
-		err = fxsave_user((struct i387_fxsave_struct __user *) buf);
-	else
-		err = fsave_user((struct i387_fsave_struct __user *) buf);
-
-	if (unlikely(err) && __clear_user(buf, xstate_size))
-		err = -EFAULT;
-	return err;
-}
-
-/*
- * Save the fpu, extended register state to the user signal frame.
- *
- * 'buf_fx' is the 64-byte aligned pointer at which the [f|fx|x]save
- *  state is copied.
- *  'buf' points to the 'buf_fx' or to the fsave header followed by 'buf_fx'.
- *
- *	buf == buf_fx for 64-bit frames and 32-bit fsave frame.
- *	buf != buf_fx for 32-bit frames with fxstate.
- *
- * If the fpu, extended register state is live, save the state directly
- * to the user frame pointed by the aligned pointer 'buf_fx'. Otherwise,
- * copy the thread's fpu state to the user frame starting at 'buf_fx'.
- *
- * If this is a 32-bit frame with fxstate, put a fsave header before
- * the aligned state at 'buf_fx'.
- *
- * For [f]xsave state, update the SW reserved fields in the [f]xsave frame
- * indicating the absence/presence of the extended state to the user.
- */
-int save_xstate_sig(void __user *buf, void __user *buf_fx, int size)
-{
-	struct xsave_struct *xsave = &current->thread.fpu.state->xsave;
-	struct task_struct *tsk = current;
-	int ia32_fxstate = (buf != buf_fx);
-
-	ia32_fxstate &= (config_enabled(CONFIG_X86_32) ||
-			 config_enabled(CONFIG_IA32_EMULATION));
-
-	if (!access_ok(VERIFY_WRITE, buf, size))
-		return -EACCES;
-
-	if (!static_cpu_has(X86_FEATURE_FPU))
-		return fpregs_soft_get(current, NULL, 0,
-			sizeof(struct user_i387_ia32_struct), NULL,
-			(struct _fpstate_ia32 __user *) buf) ? -1 : 1;
-
-	if (user_has_fpu()) {
-		/* Save the live register state to the user directly. */
-		if (save_user_xstate(buf_fx))
-			return -1;
-		/* Update the thread's fxstate to save the fsave header. */
-		if (ia32_fxstate)
-			fpu_fxsave(&tsk->thread.fpu);
-	} else {
-		sanitize_i387_state(tsk);
-		if (__copy_to_user(buf_fx, xsave, xstate_size))
-			return -1;
-	}
-
-	/* Save the fsave header for the 32-bit frames. */
-	if ((ia32_fxstate || !use_fxsr()) && save_fsave_header(tsk, buf))
-		return -1;
-
-	if (use_fxsr() && save_xstate_epilog(buf_fx, ia32_fxstate))
-		return -1;
-
-	return 0;
-}
-
-static inline void
-sanitize_restored_xstate(struct task_struct *tsk,
-			 struct user_i387_ia32_struct *ia32_env,
-			 u64 xstate_bv, int fx_only)
-{
-	struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave;
-	struct xsave_hdr_struct *xsave_hdr = &xsave->xsave_hdr;
-
-	if (use_xsave()) {
-		/* These bits must be zero. */
-		memset(xsave_hdr->reserved, 0, 48);
-
-		/*
-		 * Init the state that is not present in the memory
-		 * layout and not enabled by the OS.
-		 */
-		if (fx_only)
-			xsave_hdr->xstate_bv = XSTATE_FPSSE;
-		else
-			xsave_hdr->xstate_bv &= (pcntxt_mask & xstate_bv);
-	}
-
-	if (use_fxsr()) {
-		/*
-		 * mscsr reserved bits must be masked to zero for security
-		 * reasons.
-		 */
-		xsave->i387.mxcsr &= mxcsr_feature_mask;
-
-		convert_to_fxsr(tsk, ia32_env);
-	}
-}
-
-/*
- * Restore the extended state if present. Otherwise, restore the FP/SSE state.
- */
-static inline int restore_user_xstate(void __user *buf, u64 xbv, int fx_only)
-{
-	if (use_xsave()) {
-		if ((unsigned long)buf % 64 || fx_only) {
-			u64 init_bv = pcntxt_mask & ~XSTATE_FPSSE;
-			xrstor_state(init_xstate_buf, init_bv);
-			return fxrstor_user(buf);
-		} else {
-			u64 init_bv = pcntxt_mask & ~xbv;
-			if (unlikely(init_bv))
-				xrstor_state(init_xstate_buf, init_bv);
-			return xrestore_user(buf, xbv);
-		}
-	} else if (use_fxsr()) {
-		return fxrstor_user(buf);
-	} else
-		return frstor_user(buf);
-}
-
-int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size)
-{
-	int ia32_fxstate = (buf != buf_fx);
-	struct task_struct *tsk = current;
-	int state_size = xstate_size;
-	u64 xstate_bv = 0;
-	int fx_only = 0;
-
-	ia32_fxstate &= (config_enabled(CONFIG_X86_32) ||
-			 config_enabled(CONFIG_IA32_EMULATION));
-
-	if (!buf) {
-		fpu_reset_state(tsk);
-		return 0;
-	}
-
-	if (!access_ok(VERIFY_READ, buf, size))
-		return -EACCES;
-
-	if (!used_math() && init_fpu(tsk))
-		return -1;
-
-	if (!static_cpu_has(X86_FEATURE_FPU))
-		return fpregs_soft_set(current, NULL,
-				       0, sizeof(struct user_i387_ia32_struct),
-				       NULL, buf) != 0;
-
-	if (use_xsave()) {
-		struct _fpx_sw_bytes fx_sw_user;
-		if (unlikely(check_for_xstate(buf_fx, buf_fx, &fx_sw_user))) {
-			/*
-			 * Couldn't find the extended state information in the
-			 * memory layout. Restore just the FP/SSE and init all
-			 * the other extended state.
-			 */
-			state_size = sizeof(struct i387_fxsave_struct);
-			fx_only = 1;
-		} else {
-			state_size = fx_sw_user.xstate_size;
-			xstate_bv = fx_sw_user.xstate_bv;
-		}
-	}
-
-	if (ia32_fxstate) {
-		/*
-		 * For 32-bit frames with fxstate, copy the user state to the
-		 * thread's fpu state, reconstruct fxstate from the fsave
-		 * header. Sanitize the copied state etc.
-		 */
-		struct fpu *fpu = &tsk->thread.fpu;
-		struct user_i387_ia32_struct env;
-		int err = 0;
-
-		/*
-		 * Drop the current fpu which clears used_math(). This ensures
-		 * that any context-switch during the copy of the new state,
-		 * avoids the intermediate state from getting restored/saved.
-		 * Thus avoiding the new restored state from getting corrupted.
-		 * We will be ready to restore/save the state only after
-		 * set_used_math() is again set.
-		 */
-		drop_fpu(tsk);
-
-		if (__copy_from_user(&fpu->state->xsave, buf_fx, state_size) ||
-		    __copy_from_user(&env, buf, sizeof(env))) {
-			fpu_finit(fpu);
-			err = -1;
-		} else {
-			sanitize_restored_xstate(tsk, &env, xstate_bv, fx_only);
-		}
-
-		set_used_math();
-		if (use_eager_fpu()) {
-			preempt_disable();
-			math_state_restore();
-			preempt_enable();
-		}
-
-		return err;
-	} else {
-		/*
-		 * For 64-bit frames and 32-bit fsave frames, restore the user
-		 * state to the registers directly (with exceptions handled).
-		 */
-		user_fpu_begin();
-		if (restore_user_xstate(buf_fx, xstate_bv, fx_only)) {
-			fpu_reset_state(tsk);
-			return -1;
-		}
-	}
-
-	return 0;
-}
-
-/*
- * Prepare the SW reserved portion of the fxsave memory layout, indicating
- * the presence of the extended state information in the memory layout
- * pointed by the fpstate pointer in the sigcontext.
- * This will be saved when ever the FP and extended state context is
- * saved on the user stack during the signal handler delivery to the user.
- */
-static void prepare_fx_sw_frame(void)
-{
-	int fsave_header_size = sizeof(struct i387_fsave_struct);
-	int size = xstate_size + FP_XSTATE_MAGIC2_SIZE;
-
-	if (config_enabled(CONFIG_X86_32))
-		size += fsave_header_size;
-
-	fx_sw_reserved.magic1 = FP_XSTATE_MAGIC1;
-	fx_sw_reserved.extended_size = size;
-	fx_sw_reserved.xstate_bv = pcntxt_mask;
-	fx_sw_reserved.xstate_size = xstate_size;
-
-	if (config_enabled(CONFIG_IA32_EMULATION)) {
-		fx_sw_reserved_ia32 = fx_sw_reserved;
-		fx_sw_reserved_ia32.extended_size += fsave_header_size;
-	}
-}
-
-/*
- * Enable the extended processor state save/restore feature
- */
-static inline void xstate_enable(void)
-{
-	cr4_set_bits(X86_CR4_OSXSAVE);
-	xsetbv(XCR_XFEATURE_ENABLED_MASK, pcntxt_mask);
-}
-
-/*
- * Record the offsets and sizes of different state managed by the xsave
- * memory layout.
- */
-static void __init setup_xstate_features(void)
-{
-	int eax, ebx, ecx, edx, leaf = 0x2;
-
-	xstate_features = fls64(pcntxt_mask);
-	xstate_offsets = alloc_bootmem(xstate_features * sizeof(int));
-	xstate_sizes = alloc_bootmem(xstate_features * sizeof(int));
-
-	do {
-		cpuid_count(XSTATE_CPUID, leaf, &eax, &ebx, &ecx, &edx);
-
-		if (eax == 0)
-			break;
-
-		xstate_offsets[leaf] = ebx;
-		xstate_sizes[leaf] = eax;
-
-		leaf++;
-	} while (1);
-}
-
-/*
- * This function sets up offsets and sizes of all extended states in
- * xsave area. This supports both standard format and compacted format
- * of the xsave aread.
- *
- * Input: void
- * Output: void
- */
-void setup_xstate_comp(void)
-{
-	unsigned int xstate_comp_sizes[sizeof(pcntxt_mask)*8];
-	int i;
-
-	/*
-	 * The FP xstates and SSE xstates are legacy states. They are always
-	 * in the fixed offsets in the xsave area in either compacted form
-	 * or standard form.
-	 */
-	xstate_comp_offsets[0] = 0;
-	xstate_comp_offsets[1] = offsetof(struct i387_fxsave_struct, xmm_space);
-
-	if (!cpu_has_xsaves) {
-		for (i = 2; i < xstate_features; i++) {
-			if (test_bit(i, (unsigned long *)&pcntxt_mask)) {
-				xstate_comp_offsets[i] = xstate_offsets[i];
-				xstate_comp_sizes[i] = xstate_sizes[i];
-			}
-		}
-		return;
-	}
-
-	xstate_comp_offsets[2] = FXSAVE_SIZE + XSAVE_HDR_SIZE;
-
-	for (i = 2; i < xstate_features; i++) {
-		if (test_bit(i, (unsigned long *)&pcntxt_mask))
-			xstate_comp_sizes[i] = xstate_sizes[i];
-		else
-			xstate_comp_sizes[i] = 0;
-
-		if (i > 2)
-			xstate_comp_offsets[i] = xstate_comp_offsets[i-1]
-					+ xstate_comp_sizes[i-1];
-
-	}
-}
-
-/*
- * setup the xstate image representing the init state
- */
-static void __init setup_init_fpu_buf(void)
-{
-	/*
-	 * Setup init_xstate_buf to represent the init state of
-	 * all the features managed by the xsave
-	 */
-	init_xstate_buf = alloc_bootmem_align(xstate_size,
-					      __alignof__(struct xsave_struct));
-	fx_finit(&init_xstate_buf->i387);
-
-	if (!cpu_has_xsave)
-		return;
-
-	setup_xstate_features();
-
-	if (cpu_has_xsaves) {
-		init_xstate_buf->xsave_hdr.xcomp_bv =
-						(u64)1 << 63 | pcntxt_mask;
-		init_xstate_buf->xsave_hdr.xstate_bv = pcntxt_mask;
-	}
-
-	/*
-	 * Init all the features state with header_bv being 0x0
-	 */
-	xrstor_state_booting(init_xstate_buf, -1);
-	/*
-	 * Dump the init state again. This is to identify the init state
-	 * of any feature which is not represented by all zero's.
-	 */
-	xsave_state_booting(init_xstate_buf, -1);
-}
-
-static enum { AUTO, ENABLE, DISABLE } eagerfpu = AUTO;
-static int __init eager_fpu_setup(char *s)
-{
-	if (!strcmp(s, "on"))
-		eagerfpu = ENABLE;
-	else if (!strcmp(s, "off"))
-		eagerfpu = DISABLE;
-	else if (!strcmp(s, "auto"))
-		eagerfpu = AUTO;
-	return 1;
-}
-__setup("eagerfpu=", eager_fpu_setup);
-
-
-/*
- * Calculate total size of enabled xstates in XCR0/pcntxt_mask.
- */
-static void __init init_xstate_size(void)
-{
-	unsigned int eax, ebx, ecx, edx;
-	int i;
-
-	if (!cpu_has_xsaves) {
-		cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx);
-		xstate_size = ebx;
-		return;
-	}
-
-	xstate_size = FXSAVE_SIZE + XSAVE_HDR_SIZE;
-	for (i = 2; i < 64; i++) {
-		if (test_bit(i, (unsigned long *)&pcntxt_mask)) {
-			cpuid_count(XSTATE_CPUID, i, &eax, &ebx, &ecx, &edx);
-			xstate_size += eax;
-		}
-	}
-}
-
-/*
- * Enable and initialize the xsave feature.
- */
-static void __init xstate_enable_boot_cpu(void)
-{
-	unsigned int eax, ebx, ecx, edx;
-
-	if (boot_cpu_data.cpuid_level < XSTATE_CPUID) {
-		WARN(1, KERN_ERR "XSTATE_CPUID missing\n");
-		return;
-	}
-
-	cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx);
-	pcntxt_mask = eax + ((u64)edx << 32);
-
-	if ((pcntxt_mask & XSTATE_FPSSE) != XSTATE_FPSSE) {
-		pr_err("FP/SSE not shown under xsave features 0x%llx\n",
-		       pcntxt_mask);
-		BUG();
-	}
-
-	/*
-	 * Support only the state known to OS.
-	 */
-	pcntxt_mask = pcntxt_mask & XCNTXT_MASK;
-
-	xstate_enable();
-
-	/*
-	 * Recompute the context size for enabled features
-	 */
-	init_xstate_size();
-
-	update_regset_xstate_info(xstate_size, pcntxt_mask);
-	prepare_fx_sw_frame();
-	setup_init_fpu_buf();
-
-	/* Auto enable eagerfpu for xsaveopt */
-	if (cpu_has_xsaveopt && eagerfpu != DISABLE)
-		eagerfpu = ENABLE;
-
-	if (pcntxt_mask & XSTATE_EAGER) {
-		if (eagerfpu == DISABLE) {
-			pr_err("eagerfpu not present, disabling some xstate features: 0x%llx\n",
-					pcntxt_mask & XSTATE_EAGER);
-			pcntxt_mask &= ~XSTATE_EAGER;
-		} else {
-			eagerfpu = ENABLE;
-		}
-	}
-
-	pr_info("enabled xstate_bv 0x%llx, cntxt size 0x%x using %s\n",
-		pcntxt_mask, xstate_size,
-		cpu_has_xsaves ? "compacted form" : "standard form");
-}
-
-/*
- * For the very first instance, this calls xstate_enable_boot_cpu();
- * for all subsequent instances, this calls xstate_enable().
- *
- * This is somewhat obfuscated due to the lack of powerful enough
- * overrides for the section checks.
- */
-void xsave_init(void)
-{
-	static __refdata void (*next_func)(void) = xstate_enable_boot_cpu;
-	void (*this_func)(void);
-
-	if (!cpu_has_xsave)
-		return;
-
-	this_func = next_func;
-	next_func = xstate_enable;
-	this_func();
-}
-
-/*
- * setup_init_fpu_buf() is __init and it is OK to call it here because
- * init_xstate_buf will be unset only once during boot.
- */
-void __init_refok eager_fpu_init(void)
-{
-	WARN_ON(used_math());
-	current_thread_info()->status = 0;
-
-	if (eagerfpu == ENABLE)
-		setup_force_cpu_cap(X86_FEATURE_EAGER_FPU);
-
-	if (!cpu_has_eager_fpu) {
-		stts();
-		return;
-	}
-
-	if (!init_xstate_buf)
-		setup_init_fpu_buf();
-}
-
-/*
- * Given the xsave area and a state inside, this function returns the
- * address of the state.
- *
- * This is the API that is called to get xstate address in either
- * standard format or compacted format of xsave area.
- *
- * Inputs:
- *	xsave: base address of the xsave area;
- *	xstate: state which is defined in xsave.h (e.g. XSTATE_FP, XSTATE_SSE,
- *	etc.)
- * Output:
- *	address of the state in the xsave area.
- */
-void *get_xsave_addr(struct xsave_struct *xsave, int xstate)
-{
-	int feature = fls64(xstate) - 1;
-	if (!test_bit(feature, (unsigned long *)&pcntxt_mask))
-		return NULL;
-
-	return (void *)xsave + xstate_comp_offsets[feature];
-}
-EXPORT_SYMBOL_GPL(get_xsave_addr);
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 1d08ad3582d0..9f705e618af5 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -16,10 +16,8 @@
 #include <linux/module.h>
 #include <linux/vmalloc.h>
 #include <linux/uaccess.h>
-#include <asm/i387.h> /* For use_eager_fpu.  Ugh! */
-#include <asm/fpu-internal.h> /* For use_eager_fpu.  Ugh! */
 #include <asm/user.h>
-#include <asm/xsave.h>
+#include <asm/fpu/xstate.h>
 #include "cpuid.h"
 #include "lapic.h"
 #include "mmu.h"
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 629af0f1c5c4..4c7deb4f78a1 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1090,6 +1090,17 @@ static void update_divide_count(struct kvm_lapic *apic)
 				   apic->divide_count);
 }
 
+static void apic_update_lvtt(struct kvm_lapic *apic)
+{
+	u32 timer_mode = kvm_apic_get_reg(apic, APIC_LVTT) &
+			apic->lapic_timer.timer_mode_mask;
+
+	if (apic->lapic_timer.timer_mode != timer_mode) {
+		apic->lapic_timer.timer_mode = timer_mode;
+		hrtimer_cancel(&apic->lapic_timer.timer);
+	}
+}
+
 static void apic_timer_expired(struct kvm_lapic *apic)
 {
 	struct kvm_vcpu *vcpu = apic->vcpu;
@@ -1298,6 +1309,7 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
 				apic_set_reg(apic, APIC_LVTT + 0x10 * i,
 					     lvt_val | APIC_LVT_MASKED);
 			}
+			apic_update_lvtt(apic);
 			atomic_set(&apic->lapic_timer.pending, 0);
 
 		}
@@ -1330,20 +1342,13 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
 
 		break;
 
-	case APIC_LVTT: {
-		u32 timer_mode = val & apic->lapic_timer.timer_mode_mask;
-
-		if (apic->lapic_timer.timer_mode != timer_mode) {
-			apic->lapic_timer.timer_mode = timer_mode;
-			hrtimer_cancel(&apic->lapic_timer.timer);
-		}
-
+	case APIC_LVTT:
 		if (!kvm_apic_sw_enabled(apic))
 			val |= APIC_LVT_MASKED;
 		val &= (apic_lvt_mask[0] | apic->lapic_timer.timer_mode_mask);
 		apic_set_reg(apic, APIC_LVTT, val);
+		apic_update_lvtt(apic);
 		break;
-	}
 
 	case APIC_TMICT:
 		if (apic_lvtt_tscdeadline(apic))
@@ -1576,7 +1581,7 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu)
 
 	for (i = 0; i < APIC_LVT_NUM; i++)
 		apic_set_reg(apic, APIC_LVTT + 0x10 * i, APIC_LVT_MASKED);
-	apic->lapic_timer.timer_mode = 0;
+	apic_update_lvtt(apic);
 	apic_set_reg(apic, APIC_LVT0,
 		     SET_APIC_DELIVERY_MODE(0, APIC_MODE_EXTINT));
 
@@ -1802,6 +1807,7 @@ void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu,
 
 	apic_update_ppr(apic);
 	hrtimer_cancel(&apic->lapic_timer.timer);
+	apic_update_lvtt(apic);
 	update_divide_count(apic);
 	start_apic_timer(apic);
 	apic->irr_pending = true;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 2d73807f0d31..e11dd59398f1 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -40,8 +40,7 @@
 #include <asm/vmx.h>
 #include <asm/virtext.h>
 #include <asm/mce.h>
-#include <asm/i387.h>
-#include <asm/xcr.h>
+#include <asm/fpu/internal.h>
 #include <asm/perf_event.h>
 #include <asm/debugreg.h>
 #include <asm/kexec.h>
@@ -1883,7 +1882,7 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx)
 	 * If the FPU is not active (through the host task or
 	 * the guest vcpu), then restore the cr0.TS bit.
 	 */
-	if (!user_has_fpu() && !vmx->vcpu.guest_fpu_loaded)
+	if (!fpregs_active() && !vmx->vcpu.guest_fpu_loaded)
 		stts();
 	load_gdt(this_cpu_ptr(&host_gdt));
 }
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index ea306adbbc13..26eaeb522cab 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -59,9 +59,8 @@
 #include <asm/desc.h>
 #include <asm/mtrr.h>
 #include <asm/mce.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h> /* Ugh! */
-#include <asm/xcr.h>
+#include <linux/kernel_stat.h>
+#include <asm/fpu/internal.h> /* Ugh! */
 #include <asm/pvclock.h>
 #include <asm/div64.h>
 
@@ -3194,8 +3193,8 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu,
 
 static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu)
 {
-	struct xsave_struct *xsave = &vcpu->arch.guest_fpu.state->xsave;
-	u64 xstate_bv = xsave->xsave_hdr.xstate_bv;
+	struct xregs_state *xsave = &vcpu->arch.guest_fpu.state.xsave;
+	u64 xstate_bv = xsave->header.xfeatures;
 	u64 valid;
 
 	/*
@@ -3230,7 +3229,7 @@ static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu)
 
 static void load_xsave(struct kvm_vcpu *vcpu, u8 *src)
 {
-	struct xsave_struct *xsave = &vcpu->arch.guest_fpu.state->xsave;
+	struct xregs_state *xsave = &vcpu->arch.guest_fpu.state.xsave;
 	u64 xstate_bv = *(u64 *)(src + XSAVE_HDR_OFFSET);
 	u64 valid;
 
@@ -3241,9 +3240,9 @@ static void load_xsave(struct kvm_vcpu *vcpu, u8 *src)
 	memcpy(xsave, src, XSAVE_HDR_OFFSET);
 
 	/* Set XSTATE_BV and possibly XCOMP_BV.  */
-	xsave->xsave_hdr.xstate_bv = xstate_bv;
+	xsave->header.xfeatures = xstate_bv;
 	if (cpu_has_xsaves)
-		xsave->xsave_hdr.xcomp_bv = host_xcr0 | XSTATE_COMPACTION_ENABLED;
+		xsave->header.xcomp_bv = host_xcr0 | XSTATE_COMPACTION_ENABLED;
 
 	/*
 	 * Copy each region from the non-compacted offset to the
@@ -3275,8 +3274,8 @@ static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
 		fill_xsave((u8 *) guest_xsave->region, vcpu);
 	} else {
 		memcpy(guest_xsave->region,
-			&vcpu->arch.guest_fpu.state->fxsave,
-			sizeof(struct i387_fxsave_struct));
+			&vcpu->arch.guest_fpu.state.fxsave,
+			sizeof(struct fxregs_state));
 		*(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)] =
 			XSTATE_FPSSE;
 	}
@@ -3300,8 +3299,8 @@ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
 	} else {
 		if (xstate_bv & ~XSTATE_FPSSE)
 			return -EINVAL;
-		memcpy(&vcpu->arch.guest_fpu.state->fxsave,
-			guest_xsave->region, sizeof(struct i387_fxsave_struct));
+		memcpy(&vcpu->arch.guest_fpu.state.fxsave,
+			guest_xsave->region, sizeof(struct fxregs_state));
 	}
 	return 0;
 }
@@ -6597,11 +6596,11 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu)
 
 int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
+	struct fpu *fpu = &current->thread.fpu;
 	int r;
 	sigset_t sigsaved;
 
-	if (!tsk_used_math(current) && init_fpu(current))
-		return -ENOMEM;
+	fpu__activate_curr(fpu);
 
 	if (vcpu->sigset_active)
 		sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
@@ -6971,8 +6970,8 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
 
 int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 {
-	struct i387_fxsave_struct *fxsave =
-			&vcpu->arch.guest_fpu.state->fxsave;
+	struct fxregs_state *fxsave =
+			&vcpu->arch.guest_fpu.state.fxsave;
 
 	memcpy(fpu->fpr, fxsave->st_space, 128);
 	fpu->fcw = fxsave->cwd;
@@ -6988,8 +6987,8 @@ int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 
 int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 {
-	struct i387_fxsave_struct *fxsave =
-			&vcpu->arch.guest_fpu.state->fxsave;
+	struct fxregs_state *fxsave =
+			&vcpu->arch.guest_fpu.state.fxsave;
 
 	memcpy(fxsave->st_space, fpu->fpr, 128);
 	fxsave->cwd = fpu->fcw;
@@ -7003,17 +7002,11 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 	return 0;
 }
 
-int fx_init(struct kvm_vcpu *vcpu)
+static void fx_init(struct kvm_vcpu *vcpu)
 {
-	int err;
-
-	err = fpu_alloc(&vcpu->arch.guest_fpu);
-	if (err)
-		return err;
-
-	fpu_finit(&vcpu->arch.guest_fpu);
+	fpstate_init(&vcpu->arch.guest_fpu.state);
 	if (cpu_has_xsaves)
-		vcpu->arch.guest_fpu.state->xsave.xsave_hdr.xcomp_bv =
+		vcpu->arch.guest_fpu.state.xsave.header.xcomp_bv =
 			host_xcr0 | XSTATE_COMPACTION_ENABLED;
 
 	/*
@@ -7022,14 +7015,6 @@ int fx_init(struct kvm_vcpu *vcpu)
 	vcpu->arch.xcr0 = XSTATE_FP;
 
 	vcpu->arch.cr0 |= X86_CR0_ET;
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(fx_init);
-
-static void fx_free(struct kvm_vcpu *vcpu)
-{
-	fpu_free(&vcpu->arch.guest_fpu);
 }
 
 void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
@@ -7045,7 +7030,7 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
 	kvm_put_guest_xcr0(vcpu);
 	vcpu->guest_fpu_loaded = 1;
 	__kernel_fpu_begin();
-	fpu_restore_checking(&vcpu->arch.guest_fpu);
+	__copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state);
 	trace_kvm_fpu(1);
 }
 
@@ -7057,7 +7042,7 @@ void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
 		return;
 
 	vcpu->guest_fpu_loaded = 0;
-	fpu_save_init(&vcpu->arch.guest_fpu);
+	copy_fpregs_to_fpstate(&vcpu->arch.guest_fpu);
 	__kernel_fpu_end();
 	++vcpu->stat.fpu_reload;
 	if (!vcpu->arch.eager_fpu)
@@ -7071,7 +7056,6 @@ void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
 	kvmclock_reset(vcpu);
 
 	free_cpumask_var(vcpu->arch.wbinvd_dirty_mask);
-	fx_free(vcpu);
 	kvm_x86_ops->vcpu_free(vcpu);
 }
 
@@ -7137,7 +7121,6 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 	kvm_mmu_unload(vcpu);
 	vcpu_put(vcpu);
 
-	fx_free(vcpu);
 	kvm_x86_ops->vcpu_free(vcpu);
 }
 
@@ -7363,9 +7346,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 		goto fail_free_mce_banks;
 	}
 
-	r = fx_init(vcpu);
-	if (r)
-		goto fail_free_wbinvd_dirty_mask;
+	fx_init(vcpu);
 
 	vcpu->arch.ia32_tsc_adjust_msr = 0x0;
 	vcpu->arch.pv_time_enabled = false;
@@ -7379,8 +7360,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 	kvm_pmu_init(vcpu);
 
 	return 0;
-fail_free_wbinvd_dirty_mask:
-	free_cpumask_var(vcpu->arch.wbinvd_dirty_mask);
+
 fail_free_mce_banks:
 	kfree(vcpu->arch.mce_banks);
 fail_free_lapic:
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index 8f9a133cc099..f2dc08c003eb 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -70,7 +70,7 @@
 #include <asm/e820.h>
 #include <asm/mce.h>
 #include <asm/io.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 #include <asm/stackprotector.h>
 #include <asm/reboot.h>		/* for struct machine_ops */
 #include <asm/kvm_para.h>
@@ -90,7 +90,7 @@ struct lguest_data lguest_data = {
 	.noirq_iret = (u32)lguest_noirq_iret,
 	.kernel_address = PAGE_OFFSET,
 	.blocked_interrupts = { 1 }, /* Block timer interrupts */
-	.syscall_vec = SYSCALL_VECTOR,
+	.syscall_vec = IA32_SYSCALL_VECTOR,
 };
 
 /*G:037
@@ -866,7 +866,7 @@ static void __init lguest_init_IRQ(void)
 	for (i = FIRST_EXTERNAL_VECTOR; i < FIRST_SYSTEM_VECTOR; i++) {
 		/* Some systems map "vectors" to interrupts weirdly.  Not us! */
 		__this_cpu_write(vector_irq[i], i - FIRST_EXTERNAL_VECTOR);
-		if (i != SYSCALL_VECTOR)
+		if (i != IA32_SYSCALL_VECTOR)
 			set_intr_gate(i, irq_entries_start +
 					8 * (i - FIRST_EXTERNAL_VECTOR));
 	}
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index 1530afb07c85..f2587888d987 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -17,7 +17,6 @@ clean-files := inat-tables.c
 obj-$(CONFIG_SMP) += msr-smp.o cache-smp.o
 
 lib-y := delay.o misc.o cmdline.o
-lib-y += thunk_$(BITS).o
 lib-y += usercopy_$(BITS).o usercopy.o getuser.o putuser.o
 lib-y += memcpy_$(BITS).o
 lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o
@@ -40,6 +39,6 @@ else
         lib-y += csum-partial_64.o csum-copy_64.o csum-wrappers_64.o
         lib-y += clear_page_64.o copy_page_64.o
         lib-y += memmove_64.o memset_64.o
-        lib-y += copy_user_64.o copy_user_nocache_64.o
+        lib-y += copy_user_64.o
 	lib-y += cmpxchg16b_emu.o
 endif
diff --git a/arch/x86/lib/atomic64_386_32.S b/arch/x86/lib/atomic64_386_32.S
index 00933d5e992f..9b0ca8fe80fc 100644
--- a/arch/x86/lib/atomic64_386_32.S
+++ b/arch/x86/lib/atomic64_386_32.S
@@ -11,26 +11,23 @@
 
 #include <linux/linkage.h>
 #include <asm/alternative-asm.h>
-#include <asm/dwarf2.h>
 
 /* if you want SMP support, implement these with real spinlocks */
 .macro LOCK reg
-	pushfl_cfi
+	pushfl
 	cli
 .endm
 
 .macro UNLOCK reg
-	popfl_cfi
+	popfl
 .endm
 
 #define BEGIN(op) \
 .macro endp; \
-	CFI_ENDPROC; \
 ENDPROC(atomic64_##op##_386); \
 .purgem endp; \
 .endm; \
 ENTRY(atomic64_##op##_386); \
-	CFI_STARTPROC; \
 	LOCK v;
 
 #define ENDP endp
diff --git a/arch/x86/lib/atomic64_cx8_32.S b/arch/x86/lib/atomic64_cx8_32.S
index 082a85167a5b..db3ae85440ff 100644
--- a/arch/x86/lib/atomic64_cx8_32.S
+++ b/arch/x86/lib/atomic64_cx8_32.S
@@ -11,7 +11,6 @@
 
 #include <linux/linkage.h>
 #include <asm/alternative-asm.h>
-#include <asm/dwarf2.h>
 
 .macro read64 reg
 	movl %ebx, %eax
@@ -22,16 +21,11 @@
 .endm
 
 ENTRY(atomic64_read_cx8)
-	CFI_STARTPROC
-
 	read64 %ecx
 	ret
-	CFI_ENDPROC
 ENDPROC(atomic64_read_cx8)
 
 ENTRY(atomic64_set_cx8)
-	CFI_STARTPROC
-
 1:
 /* we don't need LOCK_PREFIX since aligned 64-bit writes
  * are atomic on 586 and newer */
@@ -39,28 +33,23 @@ ENTRY(atomic64_set_cx8)
 	jne 1b
 
 	ret
-	CFI_ENDPROC
 ENDPROC(atomic64_set_cx8)
 
 ENTRY(atomic64_xchg_cx8)
-	CFI_STARTPROC
-
 1:
 	LOCK_PREFIX
 	cmpxchg8b (%esi)
 	jne 1b
 
 	ret
-	CFI_ENDPROC
 ENDPROC(atomic64_xchg_cx8)
 
 .macro addsub_return func ins insc
 ENTRY(atomic64_\func\()_return_cx8)
-	CFI_STARTPROC
-	pushl_cfi_reg ebp
-	pushl_cfi_reg ebx
-	pushl_cfi_reg esi
-	pushl_cfi_reg edi
+	pushl %ebp
+	pushl %ebx
+	pushl %esi
+	pushl %edi
 
 	movl %eax, %esi
 	movl %edx, %edi
@@ -79,12 +68,11 @@ ENTRY(atomic64_\func\()_return_cx8)
 10:
 	movl %ebx, %eax
 	movl %ecx, %edx
-	popl_cfi_reg edi
-	popl_cfi_reg esi
-	popl_cfi_reg ebx
-	popl_cfi_reg ebp
+	popl %edi
+	popl %esi
+	popl %ebx
+	popl %ebp
 	ret
-	CFI_ENDPROC
 ENDPROC(atomic64_\func\()_return_cx8)
 .endm
 
@@ -93,8 +81,7 @@ addsub_return sub sub sbb
 
 .macro incdec_return func ins insc
 ENTRY(atomic64_\func\()_return_cx8)
-	CFI_STARTPROC
-	pushl_cfi_reg ebx
+	pushl %ebx
 
 	read64 %esi
 1:
@@ -109,9 +96,8 @@ ENTRY(atomic64_\func\()_return_cx8)
 10:
 	movl %ebx, %eax
 	movl %ecx, %edx
-	popl_cfi_reg ebx
+	popl %ebx
 	ret
-	CFI_ENDPROC
 ENDPROC(atomic64_\func\()_return_cx8)
 .endm
 
@@ -119,8 +105,7 @@ incdec_return inc add adc
 incdec_return dec sub sbb
 
 ENTRY(atomic64_dec_if_positive_cx8)
-	CFI_STARTPROC
-	pushl_cfi_reg ebx
+	pushl %ebx
 
 	read64 %esi
 1:
@@ -136,18 +121,16 @@ ENTRY(atomic64_dec_if_positive_cx8)
 2:
 	movl %ebx, %eax
 	movl %ecx, %edx
-	popl_cfi_reg ebx
+	popl %ebx
 	ret
-	CFI_ENDPROC
 ENDPROC(atomic64_dec_if_positive_cx8)
 
 ENTRY(atomic64_add_unless_cx8)
-	CFI_STARTPROC
-	pushl_cfi_reg ebp
-	pushl_cfi_reg ebx
+	pushl %ebp
+	pushl %ebx
 /* these just push these two parameters on the stack */
-	pushl_cfi_reg edi
-	pushl_cfi_reg ecx
+	pushl %edi
+	pushl %ecx
 
 	movl %eax, %ebp
 	movl %edx, %edi
@@ -168,21 +151,18 @@ ENTRY(atomic64_add_unless_cx8)
 	movl $1, %eax
 3:
 	addl $8, %esp
-	CFI_ADJUST_CFA_OFFSET -8
-	popl_cfi_reg ebx
-	popl_cfi_reg ebp
+	popl %ebx
+	popl %ebp
 	ret
 4:
 	cmpl %edx, 4(%esp)
 	jne 2b
 	xorl %eax, %eax
 	jmp 3b
-	CFI_ENDPROC
 ENDPROC(atomic64_add_unless_cx8)
 
 ENTRY(atomic64_inc_not_zero_cx8)
-	CFI_STARTPROC
-	pushl_cfi_reg ebx
+	pushl %ebx
 
 	read64 %esi
 1:
@@ -199,7 +179,6 @@ ENTRY(atomic64_inc_not_zero_cx8)
 
 	movl $1, %eax
 3:
-	popl_cfi_reg ebx
+	popl %ebx
 	ret
-	CFI_ENDPROC
 ENDPROC(atomic64_inc_not_zero_cx8)
diff --git a/arch/x86/lib/checksum_32.S b/arch/x86/lib/checksum_32.S
index 9bc944a91274..c1e623209853 100644
--- a/arch/x86/lib/checksum_32.S
+++ b/arch/x86/lib/checksum_32.S
@@ -26,7 +26,6 @@
  */
 
 #include <linux/linkage.h>
-#include <asm/dwarf2.h>
 #include <asm/errno.h>
 #include <asm/asm.h>
 				
@@ -50,9 +49,8 @@ unsigned int csum_partial(const unsigned char * buff, int len, unsigned int sum)
 	   * alignment for the unrolled loop.
 	   */		
 ENTRY(csum_partial)
-	CFI_STARTPROC
-	pushl_cfi_reg esi
-	pushl_cfi_reg ebx
+	pushl %esi
+	pushl %ebx
 	movl 20(%esp),%eax	# Function arg: unsigned int sum
 	movl 16(%esp),%ecx	# Function arg: int len
 	movl 12(%esp),%esi	# Function arg: unsigned char *buff
@@ -129,10 +127,9 @@ ENTRY(csum_partial)
 	jz 8f
 	roll $8, %eax
 8:
-	popl_cfi_reg ebx
-	popl_cfi_reg esi
+	popl %ebx
+	popl %esi
 	ret
-	CFI_ENDPROC
 ENDPROC(csum_partial)
 
 #else
@@ -140,9 +137,8 @@ ENDPROC(csum_partial)
 /* Version for PentiumII/PPro */
 
 ENTRY(csum_partial)
-	CFI_STARTPROC
-	pushl_cfi_reg esi
-	pushl_cfi_reg ebx
+	pushl %esi
+	pushl %ebx
 	movl 20(%esp),%eax	# Function arg: unsigned int sum
 	movl 16(%esp),%ecx	# Function arg: int len
 	movl 12(%esp),%esi	# Function arg:	const unsigned char *buf
@@ -249,10 +245,9 @@ ENTRY(csum_partial)
 	jz 90f
 	roll $8, %eax
 90: 
-	popl_cfi_reg ebx
-	popl_cfi_reg esi
+	popl %ebx
+	popl %esi
 	ret
-	CFI_ENDPROC
 ENDPROC(csum_partial)
 				
 #endif
@@ -287,12 +282,10 @@ unsigned int csum_partial_copy_generic (const char *src, char *dst,
 #define FP		12
 		
 ENTRY(csum_partial_copy_generic)
-	CFI_STARTPROC
 	subl  $4,%esp	
-	CFI_ADJUST_CFA_OFFSET 4
-	pushl_cfi_reg edi
-	pushl_cfi_reg esi
-	pushl_cfi_reg ebx
+	pushl %edi
+	pushl %esi
+	pushl %ebx
 	movl ARGBASE+16(%esp),%eax	# sum
 	movl ARGBASE+12(%esp),%ecx	# len
 	movl ARGBASE+4(%esp),%esi	# src
@@ -401,12 +394,11 @@ DST(	movb %cl, (%edi)	)
 
 .previous
 
-	popl_cfi_reg ebx
-	popl_cfi_reg esi
-	popl_cfi_reg edi
-	popl_cfi %ecx			# equivalent to addl $4,%esp
+	popl %ebx
+	popl %esi
+	popl %edi
+	popl %ecx			# equivalent to addl $4,%esp
 	ret	
-	CFI_ENDPROC
 ENDPROC(csum_partial_copy_generic)
 
 #else
@@ -426,10 +418,9 @@ ENDPROC(csum_partial_copy_generic)
 #define ARGBASE 12
 		
 ENTRY(csum_partial_copy_generic)
-	CFI_STARTPROC
-	pushl_cfi_reg ebx
-	pushl_cfi_reg edi
-	pushl_cfi_reg esi
+	pushl %ebx
+	pushl %edi
+	pushl %esi
 	movl ARGBASE+4(%esp),%esi	#src
 	movl ARGBASE+8(%esp),%edi	#dst	
 	movl ARGBASE+12(%esp),%ecx	#len
@@ -489,11 +480,10 @@ DST(	movb %dl, (%edi)         )
 	jmp  7b			
 .previous				
 
-	popl_cfi_reg esi
-	popl_cfi_reg edi
-	popl_cfi_reg ebx
+	popl %esi
+	popl %edi
+	popl %ebx
 	ret
-	CFI_ENDPROC
 ENDPROC(csum_partial_copy_generic)
 				
 #undef ROUND
diff --git a/arch/x86/lib/clear_page_64.S b/arch/x86/lib/clear_page_64.S
index e67e579c93bd..a2fe51b00cce 100644
--- a/arch/x86/lib/clear_page_64.S
+++ b/arch/x86/lib/clear_page_64.S
@@ -1,5 +1,4 @@
 #include <linux/linkage.h>
-#include <asm/dwarf2.h>
 #include <asm/cpufeature.h>
 #include <asm/alternative-asm.h>
 
@@ -15,7 +14,6 @@
  * %rdi	- page
  */
 ENTRY(clear_page)
-	CFI_STARTPROC
 
 	ALTERNATIVE_2 "jmp clear_page_orig", "", X86_FEATURE_REP_GOOD, \
 		      "jmp clear_page_c_e", X86_FEATURE_ERMS
@@ -24,11 +22,9 @@ ENTRY(clear_page)
 	xorl %eax,%eax
 	rep stosq
 	ret
-	CFI_ENDPROC
 ENDPROC(clear_page)
 
 ENTRY(clear_page_orig)
-	CFI_STARTPROC
 
 	xorl   %eax,%eax
 	movl   $4096/64,%ecx
@@ -48,14 +44,11 @@ ENTRY(clear_page_orig)
 	jnz	.Lloop
 	nop
 	ret
-	CFI_ENDPROC
 ENDPROC(clear_page_orig)
 
 ENTRY(clear_page_c_e)
-	CFI_STARTPROC
 	movl $4096,%ecx
 	xorl %eax,%eax
 	rep stosb
 	ret
-	CFI_ENDPROC
 ENDPROC(clear_page_c_e)
diff --git a/arch/x86/lib/cmpxchg16b_emu.S b/arch/x86/lib/cmpxchg16b_emu.S
index 40a172541ee2..9b330242e740 100644
--- a/arch/x86/lib/cmpxchg16b_emu.S
+++ b/arch/x86/lib/cmpxchg16b_emu.S
@@ -6,7 +6,6 @@
  *
  */
 #include <linux/linkage.h>
-#include <asm/dwarf2.h>
 #include <asm/percpu.h>
 
 .text
@@ -21,7 +20,6 @@
  * %al  : Operation successful
  */
 ENTRY(this_cpu_cmpxchg16b_emu)
-CFI_STARTPROC
 
 #
 # Emulate 'cmpxchg16b %gs:(%rsi)' except we return the result in %al not
@@ -32,7 +30,7 @@ CFI_STARTPROC
 # *atomic* on a single cpu (as provided by the this_cpu_xx class of
 # macros).
 #
-	pushfq_cfi
+	pushfq
 	cli
 
 	cmpq PER_CPU_VAR((%rsi)), %rax
@@ -43,17 +41,13 @@ CFI_STARTPROC
 	movq %rbx, PER_CPU_VAR((%rsi))
 	movq %rcx, PER_CPU_VAR(8(%rsi))
 
-	CFI_REMEMBER_STATE
-	popfq_cfi
+	popfq
 	mov $1, %al
 	ret
 
-	CFI_RESTORE_STATE
 .Lnot_same:
-	popfq_cfi
+	popfq
 	xor %al,%al
 	ret
 
-CFI_ENDPROC
-
 ENDPROC(this_cpu_cmpxchg16b_emu)
diff --git a/arch/x86/lib/cmpxchg8b_emu.S b/arch/x86/lib/cmpxchg8b_emu.S
index b4807fce5177..ad5349778490 100644
--- a/arch/x86/lib/cmpxchg8b_emu.S
+++ b/arch/x86/lib/cmpxchg8b_emu.S
@@ -7,7 +7,6 @@
  */
 
 #include <linux/linkage.h>
-#include <asm/dwarf2.h>
 
 .text
 
@@ -20,14 +19,13 @@
  * %ecx : high 32 bits of new value
  */
 ENTRY(cmpxchg8b_emu)
-CFI_STARTPROC
 
 #
 # Emulate 'cmpxchg8b (%esi)' on UP except we don't
 # set the whole ZF thing (caller will just compare
 # eax:edx with the expected value)
 #
-	pushfl_cfi
+	pushfl
 	cli
 
 	cmpl  (%esi), %eax
@@ -38,18 +36,15 @@ CFI_STARTPROC
 	movl %ebx,  (%esi)
 	movl %ecx, 4(%esi)
 
-	CFI_REMEMBER_STATE
-	popfl_cfi
+	popfl
 	ret
 
-	CFI_RESTORE_STATE
 .Lnot_same:
 	movl  (%esi), %eax
 .Lhalf_same:
 	movl 4(%esi), %edx
 
-	popfl_cfi
+	popfl
 	ret
 
-CFI_ENDPROC
 ENDPROC(cmpxchg8b_emu)
diff --git a/arch/x86/lib/copy_page_64.S b/arch/x86/lib/copy_page_64.S
index 8239dbcbf984..009f98216b7e 100644
--- a/arch/x86/lib/copy_page_64.S
+++ b/arch/x86/lib/copy_page_64.S
@@ -1,7 +1,6 @@
 /* Written 2003 by Andi Kleen, based on a kernel by Evandro Menezes */
 
 #include <linux/linkage.h>
-#include <asm/dwarf2.h>
 #include <asm/cpufeature.h>
 #include <asm/alternative-asm.h>
 
@@ -13,22 +12,16 @@
  */
 	ALIGN
 ENTRY(copy_page)
-	CFI_STARTPROC
 	ALTERNATIVE "jmp copy_page_regs", "", X86_FEATURE_REP_GOOD
 	movl	$4096/8, %ecx
 	rep	movsq
 	ret
-	CFI_ENDPROC
 ENDPROC(copy_page)
 
 ENTRY(copy_page_regs)
-	CFI_STARTPROC
 	subq	$2*8,	%rsp
-	CFI_ADJUST_CFA_OFFSET 2*8
 	movq	%rbx,	(%rsp)
-	CFI_REL_OFFSET rbx, 0
 	movq	%r12,	1*8(%rsp)
-	CFI_REL_OFFSET r12, 1*8
 
 	movl	$(4096/64)-5,	%ecx
 	.p2align 4
@@ -87,11 +80,7 @@ ENTRY(copy_page_regs)
 	jnz	.Loop2
 
 	movq	(%rsp), %rbx
-	CFI_RESTORE rbx
 	movq	1*8(%rsp), %r12
-	CFI_RESTORE r12
 	addq	$2*8, %rsp
-	CFI_ADJUST_CFA_OFFSET -2*8
 	ret
-	CFI_ENDPROC
 ENDPROC(copy_page_regs)
diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index fa997dfaef24..982ce34f4a9b 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -7,7 +7,6 @@
  */
 
 #include <linux/linkage.h>
-#include <asm/dwarf2.h>
 #include <asm/current.h>
 #include <asm/asm-offsets.h>
 #include <asm/thread_info.h>
@@ -16,33 +15,8 @@
 #include <asm/asm.h>
 #include <asm/smap.h>
 
-	.macro ALIGN_DESTINATION
-	/* check for bad alignment of destination */
-	movl %edi,%ecx
-	andl $7,%ecx
-	jz 102f				/* already aligned */
-	subl $8,%ecx
-	negl %ecx
-	subl %ecx,%edx
-100:	movb (%rsi),%al
-101:	movb %al,(%rdi)
-	incq %rsi
-	incq %rdi
-	decl %ecx
-	jnz 100b
-102:
-	.section .fixup,"ax"
-103:	addl %ecx,%edx			/* ecx is zerorest also */
-	jmp copy_user_handle_tail
-	.previous
-
-	_ASM_EXTABLE(100b,103b)
-	_ASM_EXTABLE(101b,103b)
-	.endm
-
 /* Standard copy_to_user with segment limit checking */
 ENTRY(_copy_to_user)
-	CFI_STARTPROC
 	GET_THREAD_INFO(%rax)
 	movq %rdi,%rcx
 	addq %rdx,%rcx
@@ -54,12 +28,10 @@ ENTRY(_copy_to_user)
 		      X86_FEATURE_REP_GOOD,			\
 		      "jmp copy_user_enhanced_fast_string",	\
 		      X86_FEATURE_ERMS
-	CFI_ENDPROC
 ENDPROC(_copy_to_user)
 
 /* Standard copy_from_user with segment limit checking */
 ENTRY(_copy_from_user)
-	CFI_STARTPROC
 	GET_THREAD_INFO(%rax)
 	movq %rsi,%rcx
 	addq %rdx,%rcx
@@ -71,14 +43,12 @@ ENTRY(_copy_from_user)
 		      X86_FEATURE_REP_GOOD,			\
 		      "jmp copy_user_enhanced_fast_string",	\
 		      X86_FEATURE_ERMS
-	CFI_ENDPROC
 ENDPROC(_copy_from_user)
 
 	.section .fixup,"ax"
 	/* must zero dest */
 ENTRY(bad_from_user)
 bad_from_user:
-	CFI_STARTPROC
 	movl %edx,%ecx
 	xorl %eax,%eax
 	rep
@@ -86,7 +56,6 @@ bad_from_user:
 bad_to_user:
 	movl %edx,%eax
 	ret
-	CFI_ENDPROC
 ENDPROC(bad_from_user)
 	.previous
 
@@ -104,7 +73,6 @@ ENDPROC(bad_from_user)
  * eax uncopied bytes or 0 if successful.
  */
 ENTRY(copy_user_generic_unrolled)
-	CFI_STARTPROC
 	ASM_STAC
 	cmpl $8,%edx
 	jb 20f		/* less then 8 bytes, go to byte copy loop */
@@ -186,7 +154,6 @@ ENTRY(copy_user_generic_unrolled)
 	_ASM_EXTABLE(19b,40b)
 	_ASM_EXTABLE(21b,50b)
 	_ASM_EXTABLE(22b,50b)
-	CFI_ENDPROC
 ENDPROC(copy_user_generic_unrolled)
 
 /* Some CPUs run faster using the string copy instructions.
@@ -208,7 +175,6 @@ ENDPROC(copy_user_generic_unrolled)
  * eax uncopied bytes or 0 if successful.
  */
 ENTRY(copy_user_generic_string)
-	CFI_STARTPROC
 	ASM_STAC
 	cmpl $8,%edx
 	jb 2f		/* less than 8 bytes, go to byte copy loop */
@@ -233,7 +199,6 @@ ENTRY(copy_user_generic_string)
 
 	_ASM_EXTABLE(1b,11b)
 	_ASM_EXTABLE(3b,12b)
-	CFI_ENDPROC
 ENDPROC(copy_user_generic_string)
 
 /*
@@ -249,7 +214,6 @@ ENDPROC(copy_user_generic_string)
  * eax uncopied bytes or 0 if successful.
  */
 ENTRY(copy_user_enhanced_fast_string)
-	CFI_STARTPROC
 	ASM_STAC
 	movl %edx,%ecx
 1:	rep
@@ -264,5 +228,94 @@ ENTRY(copy_user_enhanced_fast_string)
 	.previous
 
 	_ASM_EXTABLE(1b,12b)
-	CFI_ENDPROC
 ENDPROC(copy_user_enhanced_fast_string)
+
+/*
+ * copy_user_nocache - Uncached memory copy with exception handling
+ * This will force destination/source out of cache for more performance.
+ */
+ENTRY(__copy_user_nocache)
+	ASM_STAC
+	cmpl $8,%edx
+	jb 20f		/* less then 8 bytes, go to byte copy loop */
+	ALIGN_DESTINATION
+	movl %edx,%ecx
+	andl $63,%edx
+	shrl $6,%ecx
+	jz 17f
+1:	movq (%rsi),%r8
+2:	movq 1*8(%rsi),%r9
+3:	movq 2*8(%rsi),%r10
+4:	movq 3*8(%rsi),%r11
+5:	movnti %r8,(%rdi)
+6:	movnti %r9,1*8(%rdi)
+7:	movnti %r10,2*8(%rdi)
+8:	movnti %r11,3*8(%rdi)
+9:	movq 4*8(%rsi),%r8
+10:	movq 5*8(%rsi),%r9
+11:	movq 6*8(%rsi),%r10
+12:	movq 7*8(%rsi),%r11
+13:	movnti %r8,4*8(%rdi)
+14:	movnti %r9,5*8(%rdi)
+15:	movnti %r10,6*8(%rdi)
+16:	movnti %r11,7*8(%rdi)
+	leaq 64(%rsi),%rsi
+	leaq 64(%rdi),%rdi
+	decl %ecx
+	jnz 1b
+17:	movl %edx,%ecx
+	andl $7,%edx
+	shrl $3,%ecx
+	jz 20f
+18:	movq (%rsi),%r8
+19:	movnti %r8,(%rdi)
+	leaq 8(%rsi),%rsi
+	leaq 8(%rdi),%rdi
+	decl %ecx
+	jnz 18b
+20:	andl %edx,%edx
+	jz 23f
+	movl %edx,%ecx
+21:	movb (%rsi),%al
+22:	movb %al,(%rdi)
+	incq %rsi
+	incq %rdi
+	decl %ecx
+	jnz 21b
+23:	xorl %eax,%eax
+	ASM_CLAC
+	sfence
+	ret
+
+	.section .fixup,"ax"
+30:	shll $6,%ecx
+	addl %ecx,%edx
+	jmp 60f
+40:	lea (%rdx,%rcx,8),%rdx
+	jmp 60f
+50:	movl %ecx,%edx
+60:	sfence
+	jmp copy_user_handle_tail
+	.previous
+
+	_ASM_EXTABLE(1b,30b)
+	_ASM_EXTABLE(2b,30b)
+	_ASM_EXTABLE(3b,30b)
+	_ASM_EXTABLE(4b,30b)
+	_ASM_EXTABLE(5b,30b)
+	_ASM_EXTABLE(6b,30b)
+	_ASM_EXTABLE(7b,30b)
+	_ASM_EXTABLE(8b,30b)
+	_ASM_EXTABLE(9b,30b)
+	_ASM_EXTABLE(10b,30b)
+	_ASM_EXTABLE(11b,30b)
+	_ASM_EXTABLE(12b,30b)
+	_ASM_EXTABLE(13b,30b)
+	_ASM_EXTABLE(14b,30b)
+	_ASM_EXTABLE(15b,30b)
+	_ASM_EXTABLE(16b,30b)
+	_ASM_EXTABLE(18b,40b)
+	_ASM_EXTABLE(19b,40b)
+	_ASM_EXTABLE(21b,50b)
+	_ASM_EXTABLE(22b,50b)
+ENDPROC(__copy_user_nocache)
diff --git a/arch/x86/lib/copy_user_nocache_64.S b/arch/x86/lib/copy_user_nocache_64.S
deleted file mode 100644
index 6a4f43c2d9e6..000000000000
--- a/arch/x86/lib/copy_user_nocache_64.S
+++ /dev/null
@@ -1,136 +0,0 @@
-/*
- * Copyright 2008 Vitaly Mayatskikh <vmayatsk@redhat.com>
- * Copyright 2002 Andi Kleen, SuSE Labs.
- * Subject to the GNU Public License v2.
- *
- * Functions to copy from and to user space.
- */
-
-#include <linux/linkage.h>
-#include <asm/dwarf2.h>
-
-#define FIX_ALIGNMENT 1
-
-#include <asm/current.h>
-#include <asm/asm-offsets.h>
-#include <asm/thread_info.h>
-#include <asm/asm.h>
-#include <asm/smap.h>
-
-	.macro ALIGN_DESTINATION
-#ifdef FIX_ALIGNMENT
-	/* check for bad alignment of destination */
-	movl %edi,%ecx
-	andl $7,%ecx
-	jz 102f				/* already aligned */
-	subl $8,%ecx
-	negl %ecx
-	subl %ecx,%edx
-100:	movb (%rsi),%al
-101:	movb %al,(%rdi)
-	incq %rsi
-	incq %rdi
-	decl %ecx
-	jnz 100b
-102:
-	.section .fixup,"ax"
-103:	addl %ecx,%edx			/* ecx is zerorest also */
-	jmp copy_user_handle_tail
-	.previous
-
-	_ASM_EXTABLE(100b,103b)
-	_ASM_EXTABLE(101b,103b)
-#endif
-	.endm
-
-/*
- * copy_user_nocache - Uncached memory copy with exception handling
- * This will force destination/source out of cache for more performance.
- */
-ENTRY(__copy_user_nocache)
-	CFI_STARTPROC
-	ASM_STAC
-	cmpl $8,%edx
-	jb 20f		/* less then 8 bytes, go to byte copy loop */
-	ALIGN_DESTINATION
-	movl %edx,%ecx
-	andl $63,%edx
-	shrl $6,%ecx
-	jz 17f
-1:	movq (%rsi),%r8
-2:	movq 1*8(%rsi),%r9
-3:	movq 2*8(%rsi),%r10
-4:	movq 3*8(%rsi),%r11
-5:	movnti %r8,(%rdi)
-6:	movnti %r9,1*8(%rdi)
-7:	movnti %r10,2*8(%rdi)
-8:	movnti %r11,3*8(%rdi)
-9:	movq 4*8(%rsi),%r8
-10:	movq 5*8(%rsi),%r9
-11:	movq 6*8(%rsi),%r10
-12:	movq 7*8(%rsi),%r11
-13:	movnti %r8,4*8(%rdi)
-14:	movnti %r9,5*8(%rdi)
-15:	movnti %r10,6*8(%rdi)
-16:	movnti %r11,7*8(%rdi)
-	leaq 64(%rsi),%rsi
-	leaq 64(%rdi),%rdi
-	decl %ecx
-	jnz 1b
-17:	movl %edx,%ecx
-	andl $7,%edx
-	shrl $3,%ecx
-	jz 20f
-18:	movq (%rsi),%r8
-19:	movnti %r8,(%rdi)
-	leaq 8(%rsi),%rsi
-	leaq 8(%rdi),%rdi
-	decl %ecx
-	jnz 18b
-20:	andl %edx,%edx
-	jz 23f
-	movl %edx,%ecx
-21:	movb (%rsi),%al
-22:	movb %al,(%rdi)
-	incq %rsi
-	incq %rdi
-	decl %ecx
-	jnz 21b
-23:	xorl %eax,%eax
-	ASM_CLAC
-	sfence
-	ret
-
-	.section .fixup,"ax"
-30:	shll $6,%ecx
-	addl %ecx,%edx
-	jmp 60f
-40:	lea (%rdx,%rcx,8),%rdx
-	jmp 60f
-50:	movl %ecx,%edx
-60:	sfence
-	jmp copy_user_handle_tail
-	.previous
-
-	_ASM_EXTABLE(1b,30b)
-	_ASM_EXTABLE(2b,30b)
-	_ASM_EXTABLE(3b,30b)
-	_ASM_EXTABLE(4b,30b)
-	_ASM_EXTABLE(5b,30b)
-	_ASM_EXTABLE(6b,30b)
-	_ASM_EXTABLE(7b,30b)
-	_ASM_EXTABLE(8b,30b)
-	_ASM_EXTABLE(9b,30b)
-	_ASM_EXTABLE(10b,30b)
-	_ASM_EXTABLE(11b,30b)
-	_ASM_EXTABLE(12b,30b)
-	_ASM_EXTABLE(13b,30b)
-	_ASM_EXTABLE(14b,30b)
-	_ASM_EXTABLE(15b,30b)
-	_ASM_EXTABLE(16b,30b)
-	_ASM_EXTABLE(18b,40b)
-	_ASM_EXTABLE(19b,40b)
-	_ASM_EXTABLE(21b,50b)
-	_ASM_EXTABLE(22b,50b)
-	CFI_ENDPROC
-ENDPROC(__copy_user_nocache)
diff --git a/arch/x86/lib/csum-copy_64.S b/arch/x86/lib/csum-copy_64.S
index 9734182966f3..7e48807b2fa1 100644
--- a/arch/x86/lib/csum-copy_64.S
+++ b/arch/x86/lib/csum-copy_64.S
@@ -6,7 +6,6 @@
  * for more details. No warranty for anything given at all.
  */
 #include <linux/linkage.h>
-#include <asm/dwarf2.h>
 #include <asm/errno.h>
 #include <asm/asm.h>
 
@@ -47,23 +46,16 @@
 
 
 ENTRY(csum_partial_copy_generic)
-	CFI_STARTPROC
 	cmpl	$3*64, %edx
 	jle	.Lignore
 
 .Lignore:
 	subq  $7*8, %rsp
-	CFI_ADJUST_CFA_OFFSET 7*8
 	movq  %rbx, 2*8(%rsp)
-	CFI_REL_OFFSET rbx, 2*8
 	movq  %r12, 3*8(%rsp)
-	CFI_REL_OFFSET r12, 3*8
 	movq  %r14, 4*8(%rsp)
-	CFI_REL_OFFSET r14, 4*8
 	movq  %r13, 5*8(%rsp)
-	CFI_REL_OFFSET r13, 5*8
 	movq  %rbp, 6*8(%rsp)
-	CFI_REL_OFFSET rbp, 6*8
 
 	movq  %r8, (%rsp)
 	movq  %r9, 1*8(%rsp)
@@ -206,22 +198,14 @@ ENTRY(csum_partial_copy_generic)
 	addl %ebx, %eax
 	adcl %r9d, %eax		/* carry */
 
-	CFI_REMEMBER_STATE
 .Lende:
 	movq 2*8(%rsp), %rbx
-	CFI_RESTORE rbx
 	movq 3*8(%rsp), %r12
-	CFI_RESTORE r12
 	movq 4*8(%rsp), %r14
-	CFI_RESTORE r14
 	movq 5*8(%rsp), %r13
-	CFI_RESTORE r13
 	movq 6*8(%rsp), %rbp
-	CFI_RESTORE rbp
 	addq $7*8, %rsp
-	CFI_ADJUST_CFA_OFFSET -7*8
 	ret
-	CFI_RESTORE_STATE
 
 	/* Exception handlers. Very simple, zeroing is done in the wrappers */
 .Lbad_source:
@@ -237,5 +221,4 @@ ENTRY(csum_partial_copy_generic)
 	jz   .Lende
 	movl $-EFAULT, (%rax)
 	jmp .Lende
-	CFI_ENDPROC
 ENDPROC(csum_partial_copy_generic)
diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S
index a4512359656a..46668cda4ffd 100644
--- a/arch/x86/lib/getuser.S
+++ b/arch/x86/lib/getuser.S
@@ -26,7 +26,6 @@
  */
 
 #include <linux/linkage.h>
-#include <asm/dwarf2.h>
 #include <asm/page_types.h>
 #include <asm/errno.h>
 #include <asm/asm-offsets.h>
@@ -36,7 +35,6 @@
 
 	.text
 ENTRY(__get_user_1)
-	CFI_STARTPROC
 	GET_THREAD_INFO(%_ASM_DX)
 	cmp TI_addr_limit(%_ASM_DX),%_ASM_AX
 	jae bad_get_user
@@ -45,11 +43,9 @@ ENTRY(__get_user_1)
 	xor %eax,%eax
 	ASM_CLAC
 	ret
-	CFI_ENDPROC
 ENDPROC(__get_user_1)
 
 ENTRY(__get_user_2)
-	CFI_STARTPROC
 	add $1,%_ASM_AX
 	jc bad_get_user
 	GET_THREAD_INFO(%_ASM_DX)
@@ -60,11 +56,9 @@ ENTRY(__get_user_2)
 	xor %eax,%eax
 	ASM_CLAC
 	ret
-	CFI_ENDPROC
 ENDPROC(__get_user_2)
 
 ENTRY(__get_user_4)
-	CFI_STARTPROC
 	add $3,%_ASM_AX
 	jc bad_get_user
 	GET_THREAD_INFO(%_ASM_DX)
@@ -75,11 +69,9 @@ ENTRY(__get_user_4)
 	xor %eax,%eax
 	ASM_CLAC
 	ret
-	CFI_ENDPROC
 ENDPROC(__get_user_4)
 
 ENTRY(__get_user_8)
-	CFI_STARTPROC
 #ifdef CONFIG_X86_64
 	add $7,%_ASM_AX
 	jc bad_get_user
@@ -104,28 +96,23 @@ ENTRY(__get_user_8)
 	ASM_CLAC
 	ret
 #endif
-	CFI_ENDPROC
 ENDPROC(__get_user_8)
 
 
 bad_get_user:
-	CFI_STARTPROC
 	xor %edx,%edx
 	mov $(-EFAULT),%_ASM_AX
 	ASM_CLAC
 	ret
-	CFI_ENDPROC
 END(bad_get_user)
 
 #ifdef CONFIG_X86_32
 bad_get_user_8:
-	CFI_STARTPROC
 	xor %edx,%edx
 	xor %ecx,%ecx
 	mov $(-EFAULT),%_ASM_AX
 	ASM_CLAC
 	ret
-	CFI_ENDPROC
 END(bad_get_user_8)
 #endif
 
diff --git a/arch/x86/lib/iomap_copy_64.S b/arch/x86/lib/iomap_copy_64.S
index 05a95e713da8..33147fef3452 100644
--- a/arch/x86/lib/iomap_copy_64.S
+++ b/arch/x86/lib/iomap_copy_64.S
@@ -16,15 +16,12 @@
  */
 
 #include <linux/linkage.h>
-#include <asm/dwarf2.h>
 
 /*
  * override generic version in lib/iomap_copy.c
  */
 ENTRY(__iowrite32_copy)
-	CFI_STARTPROC
 	movl %edx,%ecx
 	rep movsd
 	ret
-	CFI_ENDPROC
 ENDPROC(__iowrite32_copy)
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index b046664f5a1c..16698bba87de 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -2,7 +2,6 @@
 
 #include <linux/linkage.h>
 #include <asm/cpufeature.h>
-#include <asm/dwarf2.h>
 #include <asm/alternative-asm.h>
 
 /*
@@ -53,7 +52,6 @@ ENTRY(memcpy_erms)
 ENDPROC(memcpy_erms)
 
 ENTRY(memcpy_orig)
-	CFI_STARTPROC
 	movq %rdi, %rax
 
 	cmpq $0x20, %rdx
@@ -178,5 +176,4 @@ ENTRY(memcpy_orig)
 
 .Lend:
 	retq
-	CFI_ENDPROC
 ENDPROC(memcpy_orig)
diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S
index 0f8a0d0331b9..ca2afdd6d98e 100644
--- a/arch/x86/lib/memmove_64.S
+++ b/arch/x86/lib/memmove_64.S
@@ -6,7 +6,6 @@
  *	- Copyright 2011 Fenghua Yu <fenghua.yu@intel.com>
  */
 #include <linux/linkage.h>
-#include <asm/dwarf2.h>
 #include <asm/cpufeature.h>
 #include <asm/alternative-asm.h>
 
@@ -27,7 +26,6 @@
 
 ENTRY(memmove)
 ENTRY(__memmove)
-	CFI_STARTPROC
 
 	/* Handle more 32 bytes in loop */
 	mov %rdi, %rax
@@ -207,6 +205,5 @@ ENTRY(__memmove)
 	movb %r11b, (%rdi)
 13:
 	retq
-	CFI_ENDPROC
 ENDPROC(__memmove)
 ENDPROC(memmove)
diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S
index 93118fb23976..2661fad05827 100644
--- a/arch/x86/lib/memset_64.S
+++ b/arch/x86/lib/memset_64.S
@@ -1,7 +1,6 @@
 /* Copyright 2002 Andi Kleen, SuSE Labs */
 
 #include <linux/linkage.h>
-#include <asm/dwarf2.h>
 #include <asm/cpufeature.h>
 #include <asm/alternative-asm.h>
 
@@ -66,7 +65,6 @@ ENTRY(memset_erms)
 ENDPROC(memset_erms)
 
 ENTRY(memset_orig)
-	CFI_STARTPROC
 	movq %rdi,%r10
 
 	/* expand byte value  */
@@ -78,7 +76,6 @@ ENTRY(memset_orig)
 	movl  %edi,%r9d
 	andl  $7,%r9d
 	jnz  .Lbad_alignment
-	CFI_REMEMBER_STATE
 .Lafter_bad_alignment:
 
 	movq  %rdx,%rcx
@@ -128,7 +125,6 @@ ENTRY(memset_orig)
 	movq	%r10,%rax
 	ret
 
-	CFI_RESTORE_STATE
 .Lbad_alignment:
 	cmpq $7,%rdx
 	jbe	.Lhandle_7
@@ -139,5 +135,4 @@ ENTRY(memset_orig)
 	subq %r8,%rdx
 	jmp .Lafter_bad_alignment
 .Lfinal:
-	CFI_ENDPROC
 ENDPROC(memset_orig)
diff --git a/arch/x86/lib/mmx_32.c b/arch/x86/lib/mmx_32.c
index c9f2d9ba8dd8..e5e3ed8dc079 100644
--- a/arch/x86/lib/mmx_32.c
+++ b/arch/x86/lib/mmx_32.c
@@ -22,7 +22,7 @@
 #include <linux/sched.h>
 #include <linux/types.h>
 
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 #include <asm/asm.h>
 
 void *_mmx_memcpy(void *to, const void *from, size_t len)
diff --git a/arch/x86/lib/msr-reg.S b/arch/x86/lib/msr-reg.S
index 3ca5218fbece..c81556409bbb 100644
--- a/arch/x86/lib/msr-reg.S
+++ b/arch/x86/lib/msr-reg.S
@@ -1,6 +1,5 @@
 #include <linux/linkage.h>
 #include <linux/errno.h>
-#include <asm/dwarf2.h>
 #include <asm/asm.h>
 #include <asm/msr.h>
 
@@ -13,9 +12,8 @@
  */
 .macro op_safe_regs op
 ENTRY(\op\()_safe_regs)
-	CFI_STARTPROC
-	pushq_cfi_reg rbx
-	pushq_cfi_reg rbp
+	pushq %rbx
+	pushq %rbp
 	movq	%rdi, %r10	/* Save pointer */
 	xorl	%r11d, %r11d	/* Return value */
 	movl    (%rdi), %eax
@@ -25,7 +23,6 @@ ENTRY(\op\()_safe_regs)
 	movl    20(%rdi), %ebp
 	movl    24(%rdi), %esi
 	movl    28(%rdi), %edi
-	CFI_REMEMBER_STATE
 1:	\op
 2:	movl    %eax, (%r10)
 	movl	%r11d, %eax	/* Return value */
@@ -35,16 +32,14 @@ ENTRY(\op\()_safe_regs)
 	movl    %ebp, 20(%r10)
 	movl    %esi, 24(%r10)
 	movl    %edi, 28(%r10)
-	popq_cfi_reg rbp
-	popq_cfi_reg rbx
+	popq %rbp
+	popq %rbx
 	ret
 3:
-	CFI_RESTORE_STATE
 	movl    $-EIO, %r11d
 	jmp     2b
 
 	_ASM_EXTABLE(1b, 3b)
-	CFI_ENDPROC
 ENDPROC(\op\()_safe_regs)
 .endm
 
@@ -52,13 +47,12 @@ ENDPROC(\op\()_safe_regs)
 
 .macro op_safe_regs op
 ENTRY(\op\()_safe_regs)
-	CFI_STARTPROC
-	pushl_cfi_reg ebx
-	pushl_cfi_reg ebp
-	pushl_cfi_reg esi
-	pushl_cfi_reg edi
-	pushl_cfi $0              /* Return value */
-	pushl_cfi %eax
+	pushl %ebx
+	pushl %ebp
+	pushl %esi
+	pushl %edi
+	pushl $0              /* Return value */
+	pushl %eax
 	movl    4(%eax), %ecx
 	movl    8(%eax), %edx
 	movl    12(%eax), %ebx
@@ -66,32 +60,28 @@ ENTRY(\op\()_safe_regs)
 	movl    24(%eax), %esi
 	movl    28(%eax), %edi
 	movl    (%eax), %eax
-	CFI_REMEMBER_STATE
 1:	\op
-2:	pushl_cfi %eax
+2:	pushl %eax
 	movl    4(%esp), %eax
-	popl_cfi (%eax)
+	popl (%eax)
 	addl    $4, %esp
-	CFI_ADJUST_CFA_OFFSET -4
 	movl    %ecx, 4(%eax)
 	movl    %edx, 8(%eax)
 	movl    %ebx, 12(%eax)
 	movl    %ebp, 20(%eax)
 	movl    %esi, 24(%eax)
 	movl    %edi, 28(%eax)
-	popl_cfi %eax
-	popl_cfi_reg edi
-	popl_cfi_reg esi
-	popl_cfi_reg ebp
-	popl_cfi_reg ebx
+	popl %eax
+	popl %edi
+	popl %esi
+	popl %ebp
+	popl %ebx
 	ret
 3:
-	CFI_RESTORE_STATE
 	movl    $-EIO, 4(%esp)
 	jmp     2b
 
 	_ASM_EXTABLE(1b, 3b)
-	CFI_ENDPROC
 ENDPROC(\op\()_safe_regs)
 .endm
 
diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S
index fc6ba17a7eec..e0817a12d323 100644
--- a/arch/x86/lib/putuser.S
+++ b/arch/x86/lib/putuser.S
@@ -11,7 +11,6 @@
  * return value.
  */
 #include <linux/linkage.h>
-#include <asm/dwarf2.h>
 #include <asm/thread_info.h>
 #include <asm/errno.h>
 #include <asm/asm.h>
@@ -30,11 +29,9 @@
  * as they get called from within inline assembly.
  */
 
-#define ENTER	CFI_STARTPROC ; \
-		GET_THREAD_INFO(%_ASM_BX)
+#define ENTER	GET_THREAD_INFO(%_ASM_BX)
 #define EXIT	ASM_CLAC ;	\
-		ret ;		\
-		CFI_ENDPROC
+		ret
 
 .text
 ENTRY(__put_user_1)
@@ -87,7 +84,6 @@ ENTRY(__put_user_8)
 ENDPROC(__put_user_8)
 
 bad_put_user:
-	CFI_STARTPROC
 	movl $-EFAULT,%eax
 	EXIT
 END(bad_put_user)
diff --git a/arch/x86/lib/rwsem.S b/arch/x86/lib/rwsem.S
index 2322abe4da3b..40027db99140 100644
--- a/arch/x86/lib/rwsem.S
+++ b/arch/x86/lib/rwsem.S
@@ -15,7 +15,6 @@
 
 #include <linux/linkage.h>
 #include <asm/alternative-asm.h>
-#include <asm/dwarf2.h>
 
 #define __ASM_HALF_REG(reg)	__ASM_SEL(reg, e##reg)
 #define __ASM_HALF_SIZE(inst)	__ASM_SEL(inst##w, inst##l)
@@ -34,10 +33,10 @@
  */
 
 #define save_common_regs \
-	pushl_cfi_reg ecx
+	pushl %ecx
 
 #define restore_common_regs \
-	popl_cfi_reg ecx
+	popl %ecx
 
 	/* Avoid uglifying the argument copying x86-64 needs to do. */
 	.macro movq src, dst
@@ -64,50 +63,45 @@
  */
 
 #define save_common_regs \
-	pushq_cfi_reg rdi; \
-	pushq_cfi_reg rsi; \
-	pushq_cfi_reg rcx; \
-	pushq_cfi_reg r8;  \
-	pushq_cfi_reg r9;  \
-	pushq_cfi_reg r10; \
-	pushq_cfi_reg r11
+	pushq %rdi; \
+	pushq %rsi; \
+	pushq %rcx; \
+	pushq %r8;  \
+	pushq %r9;  \
+	pushq %r10; \
+	pushq %r11
 
 #define restore_common_regs \
-	popq_cfi_reg r11; \
-	popq_cfi_reg r10; \
-	popq_cfi_reg r9; \
-	popq_cfi_reg r8; \
-	popq_cfi_reg rcx; \
-	popq_cfi_reg rsi; \
-	popq_cfi_reg rdi
+	popq %r11; \
+	popq %r10; \
+	popq %r9; \
+	popq %r8; \
+	popq %rcx; \
+	popq %rsi; \
+	popq %rdi
 
 #endif
 
 /* Fix up special calling conventions */
 ENTRY(call_rwsem_down_read_failed)
-	CFI_STARTPROC
 	save_common_regs
-	__ASM_SIZE(push,_cfi_reg) __ASM_REG(dx)
+	__ASM_SIZE(push,) %__ASM_REG(dx)
 	movq %rax,%rdi
 	call rwsem_down_read_failed
-	__ASM_SIZE(pop,_cfi_reg) __ASM_REG(dx)
+	__ASM_SIZE(pop,) %__ASM_REG(dx)
 	restore_common_regs
 	ret
-	CFI_ENDPROC
 ENDPROC(call_rwsem_down_read_failed)
 
 ENTRY(call_rwsem_down_write_failed)
-	CFI_STARTPROC
 	save_common_regs
 	movq %rax,%rdi
 	call rwsem_down_write_failed
 	restore_common_regs
 	ret
-	CFI_ENDPROC
 ENDPROC(call_rwsem_down_write_failed)
 
 ENTRY(call_rwsem_wake)
-	CFI_STARTPROC
 	/* do nothing if still outstanding active readers */
 	__ASM_HALF_SIZE(dec) %__ASM_HALF_REG(dx)
 	jnz 1f
@@ -116,17 +110,14 @@ ENTRY(call_rwsem_wake)
 	call rwsem_wake
 	restore_common_regs
 1:	ret
-	CFI_ENDPROC
 ENDPROC(call_rwsem_wake)
 
 ENTRY(call_rwsem_downgrade_wake)
-	CFI_STARTPROC
 	save_common_regs
-	__ASM_SIZE(push,_cfi_reg) __ASM_REG(dx)
+	__ASM_SIZE(push,) %__ASM_REG(dx)
 	movq %rax,%rdi
 	call rwsem_downgrade_wake
-	__ASM_SIZE(pop,_cfi_reg) __ASM_REG(dx)
+	__ASM_SIZE(pop,) %__ASM_REG(dx)
 	restore_common_regs
 	ret
-	CFI_ENDPROC
 ENDPROC(call_rwsem_downgrade_wake)
diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c
index e2f5e21c03b3..91d93b95bd86 100644
--- a/arch/x86/lib/usercopy_32.c
+++ b/arch/x86/lib/usercopy_32.c
@@ -647,7 +647,8 @@ EXPORT_SYMBOL(__copy_from_user_ll_nocache_nozero);
  * @from: Source address, in kernel space.
  * @n:    Number of bytes to copy.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Copy data from kernel space to user space.
  *
@@ -668,7 +669,8 @@ EXPORT_SYMBOL(_copy_to_user);
  * @from: Source address, in user space.
  * @n:    Number of bytes to copy.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Copy data from user space to kernel space.
  *
diff --git a/arch/x86/math-emu/fpu_aux.c b/arch/x86/math-emu/fpu_aux.c
index dc8adad10a2f..dd76a05729b0 100644
--- a/arch/x86/math-emu/fpu_aux.c
+++ b/arch/x86/math-emu/fpu_aux.c
@@ -30,7 +30,7 @@ static void fclex(void)
 }
 
 /* Needs to be externally visible */
-void finit_soft_fpu(struct i387_soft_struct *soft)
+void fpstate_init_soft(struct swregs_state *soft)
 {
 	struct address *oaddr, *iaddr;
 	memset(soft, 0, sizeof(*soft));
@@ -52,7 +52,7 @@ void finit_soft_fpu(struct i387_soft_struct *soft)
 
 void finit(void)
 {
-	finit_soft_fpu(&current->thread.fpu.state->soft);
+	fpstate_init_soft(&current->thread.fpu.state.soft);
 }
 
 /*
diff --git a/arch/x86/math-emu/fpu_entry.c b/arch/x86/math-emu/fpu_entry.c
index 9b868124128d..f37e84ab49f3 100644
--- a/arch/x86/math-emu/fpu_entry.c
+++ b/arch/x86/math-emu/fpu_entry.c
@@ -31,7 +31,7 @@
 #include <asm/traps.h>
 #include <asm/desc.h>
 #include <asm/user.h>
-#include <asm/i387.h>
+#include <asm/fpu/internal.h>
 
 #include "fpu_system.h"
 #include "fpu_emu.h"
@@ -147,13 +147,9 @@ void math_emulate(struct math_emu_info *info)
 	unsigned long code_base = 0;
 	unsigned long code_limit = 0;	/* Initialized to stop compiler warnings */
 	struct desc_struct code_descriptor;
+	struct fpu *fpu = &current->thread.fpu;
 
-	if (!used_math()) {
-		if (init_fpu(current)) {
-			do_group_exit(SIGKILL);
-			return;
-		}
-	}
+	fpu__activate_curr(fpu);
 
 #ifdef RE_ENTRANT_CHECKING
 	if (emulating) {
@@ -673,7 +669,7 @@ void math_abort(struct math_emu_info *info, unsigned int signal)
 #endif /* PARANOID */
 }
 
-#define S387 ((struct i387_soft_struct *)s387)
+#define S387 ((struct swregs_state *)s387)
 #define sstatus_word() \
   ((S387->swd & ~SW_Top & 0xffff) | ((S387->ftop << SW_Top_Shift) & SW_Top))
 
@@ -682,14 +678,14 @@ int fpregs_soft_set(struct task_struct *target,
 		    unsigned int pos, unsigned int count,
 		    const void *kbuf, const void __user *ubuf)
 {
-	struct i387_soft_struct *s387 = &target->thread.fpu.state->soft;
+	struct swregs_state *s387 = &target->thread.fpu.state.soft;
 	void *space = s387->st_space;
 	int ret;
 	int offset, other, i, tags, regnr, tag, newtop;
 
 	RE_ENTRANT_CHECK_OFF;
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, s387, 0,
-				 offsetof(struct i387_soft_struct, st_space));
+				 offsetof(struct swregs_state, st_space));
 	RE_ENTRANT_CHECK_ON;
 
 	if (ret)
@@ -734,7 +730,7 @@ int fpregs_soft_get(struct task_struct *target,
 		    unsigned int pos, unsigned int count,
 		    void *kbuf, void __user *ubuf)
 {
-	struct i387_soft_struct *s387 = &target->thread.fpu.state->soft;
+	struct swregs_state *s387 = &target->thread.fpu.state.soft;
 	const void *space = s387->st_space;
 	int ret;
 	int offset = (S387->ftop & 7) * 10, other = 80 - offset;
@@ -752,7 +748,7 @@ int fpregs_soft_get(struct task_struct *target,
 #endif /* PECULIAR_486 */
 
 	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, s387, 0,
-				  offsetof(struct i387_soft_struct, st_space));
+				  offsetof(struct swregs_state, st_space));
 
 	/* Copy all registers in stack order. */
 	if (!ret)
diff --git a/arch/x86/math-emu/fpu_system.h b/arch/x86/math-emu/fpu_system.h
index 2c614410a5f3..9ccecb61a4fa 100644
--- a/arch/x86/math-emu/fpu_system.h
+++ b/arch/x86/math-emu/fpu_system.h
@@ -31,7 +31,7 @@
 #define SEG_EXPAND_DOWN(s)	(((s).b & ((1 << 11) | (1 << 10))) \
 				 == (1 << 10))
 
-#define I387			(current->thread.fpu.state)
+#define I387			(&current->thread.fpu.state)
 #define FPU_info		(I387->soft.info)
 
 #define FPU_CS			(*(unsigned short *) &(FPU_info->regs->cs))
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 181c53bac3a7..9dc909841739 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -13,6 +13,7 @@
 #include <linux/hugetlb.h>		/* hstate_index_to_shift	*/
 #include <linux/prefetch.h>		/* prefetchw			*/
 #include <linux/context_tracking.h>	/* exception_enter(), ...	*/
+#include <linux/uaccess.h>		/* faulthandler_disabled()	*/
 
 #include <asm/traps.h>			/* dotraplinkage, ...		*/
 #include <asm/pgalloc.h>		/* pgd_*(), ...			*/
@@ -1126,9 +1127,9 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code,
 
 	/*
 	 * If we're in an interrupt, have no user context or are running
-	 * in an atomic region then we must not take the fault:
+	 * in a region with pagefaults disabled then we must not take the fault
 	 */
-	if (unlikely(in_atomic() || !mm)) {
+	if (unlikely(faulthandler_disabled() || !mm)) {
 		bad_area_nosemaphore(regs, error_code, address);
 		return;
 	}
diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c
index 4500142bc4aa..eecb207a2037 100644
--- a/arch/x86/mm/highmem_32.c
+++ b/arch/x86/mm/highmem_32.c
@@ -35,7 +35,7 @@ void *kmap_atomic_prot(struct page *page, pgprot_t prot)
 	unsigned long vaddr;
 	int idx, type;
 
-	/* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */
+	preempt_disable();
 	pagefault_disable();
 
 	if (!PageHighMem(page))
@@ -100,6 +100,7 @@ void __kunmap_atomic(void *kvaddr)
 #endif
 
 	pagefault_enable();
+	preempt_enable();
 }
 EXPORT_SYMBOL(__kunmap_atomic);
 
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 1d553186c434..8533b46e6bee 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -40,7 +40,7 @@
  */
 uint16_t __cachemode2pte_tbl[_PAGE_CACHE_MODE_NUM] = {
 	[_PAGE_CACHE_MODE_WB      ]	= 0         | 0        ,
-	[_PAGE_CACHE_MODE_WC      ]	= _PAGE_PWT | 0        ,
+	[_PAGE_CACHE_MODE_WC      ]	= 0         | _PAGE_PCD,
 	[_PAGE_CACHE_MODE_UC_MINUS]	= 0         | _PAGE_PCD,
 	[_PAGE_CACHE_MODE_UC      ]	= _PAGE_PWT | _PAGE_PCD,
 	[_PAGE_CACHE_MODE_WT      ]	= 0         | _PAGE_PCD,
@@ -50,11 +50,11 @@ EXPORT_SYMBOL(__cachemode2pte_tbl);
 
 uint8_t __pte2cachemode_tbl[8] = {
 	[__pte2cm_idx( 0        | 0         | 0        )] = _PAGE_CACHE_MODE_WB,
-	[__pte2cm_idx(_PAGE_PWT | 0         | 0        )] = _PAGE_CACHE_MODE_WC,
+	[__pte2cm_idx(_PAGE_PWT | 0         | 0        )] = _PAGE_CACHE_MODE_UC_MINUS,
 	[__pte2cm_idx( 0        | _PAGE_PCD | 0        )] = _PAGE_CACHE_MODE_UC_MINUS,
 	[__pte2cm_idx(_PAGE_PWT | _PAGE_PCD | 0        )] = _PAGE_CACHE_MODE_UC,
 	[__pte2cm_idx( 0        | 0         | _PAGE_PAT)] = _PAGE_CACHE_MODE_WB,
-	[__pte2cm_idx(_PAGE_PWT | 0         | _PAGE_PAT)] = _PAGE_CACHE_MODE_WC,
+	[__pte2cm_idx(_PAGE_PWT | 0         | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC_MINUS,
 	[__pte2cm_idx(0         | _PAGE_PCD | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC_MINUS,
 	[__pte2cm_idx(_PAGE_PWT | _PAGE_PCD | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC,
 };
diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c
index 9ca35fc60cfe..9c0ff045fdd4 100644
--- a/arch/x86/mm/iomap_32.c
+++ b/arch/x86/mm/iomap_32.c
@@ -59,6 +59,7 @@ void *kmap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot)
 	unsigned long vaddr;
 	int idx, type;
 
+	preempt_disable();
 	pagefault_disable();
 
 	type = kmap_atomic_idx_push();
@@ -77,13 +78,13 @@ void __iomem *
 iomap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot)
 {
 	/*
-	 * For non-PAT systems, promote PAGE_KERNEL_WC to PAGE_KERNEL_UC_MINUS.
-	 * PAGE_KERNEL_WC maps to PWT, which translates to uncached if the
-	 * MTRR is UC or WC.  UC_MINUS gets the real intention, of the
-	 * user, which is "WC if the MTRR is WC, UC if you can't do that."
+	 * For non-PAT systems, translate non-WB request to UC- just in
+	 * case the caller set the PWT bit to prot directly without using
+	 * pgprot_writecombine(). UC- translates to uncached if the MTRR
+	 * is UC or WC. UC- gets the real intention, of the user, which is
+	 * "WC if the MTRR is WC, UC if you can't do that."
 	 */
-	if (!pat_enabled && pgprot_val(prot) ==
-	    (__PAGE_KERNEL | cachemode2protval(_PAGE_CACHE_MODE_WC)))
+	if (!pat_enabled() && pgprot2cachemode(prot) != _PAGE_CACHE_MODE_WB)
 		prot = __pgprot(__PAGE_KERNEL |
 				cachemode2protval(_PAGE_CACHE_MODE_UC_MINUS));
 
@@ -117,5 +118,6 @@ iounmap_atomic(void __iomem *kvaddr)
 	}
 
 	pagefault_enable();
+	preempt_enable();
 }
 EXPORT_SYMBOL_GPL(iounmap_atomic);
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 70e7444c6835..cc5ccc415cc0 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -42,6 +42,9 @@ int ioremap_change_attr(unsigned long vaddr, unsigned long size,
 	case _PAGE_CACHE_MODE_WC:
 		err = _set_memory_wc(vaddr, nrpages);
 		break;
+	case _PAGE_CACHE_MODE_WT:
+		err = _set_memory_wt(vaddr, nrpages);
+		break;
 	case _PAGE_CACHE_MODE_WB:
 		err = _set_memory_wb(vaddr, nrpages);
 		break;
@@ -172,6 +175,10 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
 		prot = __pgprot(pgprot_val(prot) |
 				cachemode2protval(_PAGE_CACHE_MODE_WC));
 		break;
+	case _PAGE_CACHE_MODE_WT:
+		prot = __pgprot(pgprot_val(prot) |
+				cachemode2protval(_PAGE_CACHE_MODE_WT));
+		break;
 	case _PAGE_CACHE_MODE_WB:
 		break;
 	}
@@ -234,10 +241,11 @@ void __iomem *ioremap_nocache(resource_size_t phys_addr, unsigned long size)
 {
 	/*
 	 * Ideally, this should be:
-	 *	pat_enabled ? _PAGE_CACHE_MODE_UC : _PAGE_CACHE_MODE_UC_MINUS;
+	 *	pat_enabled() ? _PAGE_CACHE_MODE_UC : _PAGE_CACHE_MODE_UC_MINUS;
 	 *
 	 * Till we fix all X drivers to use ioremap_wc(), we will use
-	 * UC MINUS.
+	 * UC MINUS. Drivers that are certain they need or can already
+	 * be converted over to strong UC can use ioremap_uc().
 	 */
 	enum page_cache_mode pcm = _PAGE_CACHE_MODE_UC_MINUS;
 
@@ -247,6 +255,39 @@ void __iomem *ioremap_nocache(resource_size_t phys_addr, unsigned long size)
 EXPORT_SYMBOL(ioremap_nocache);
 
 /**
+ * ioremap_uc     -   map bus memory into CPU space as strongly uncachable
+ * @phys_addr:    bus address of the memory
+ * @size:      size of the resource to map
+ *
+ * ioremap_uc performs a platform specific sequence of operations to
+ * make bus memory CPU accessible via the readb/readw/readl/writeb/
+ * writew/writel functions and the other mmio helpers. The returned
+ * address is not guaranteed to be usable directly as a virtual
+ * address.
+ *
+ * This version of ioremap ensures that the memory is marked with a strong
+ * preference as completely uncachable on the CPU when possible. For non-PAT
+ * systems this ends up setting page-attribute flags PCD=1, PWT=1. For PAT
+ * systems this will set the PAT entry for the pages as strong UC.  This call
+ * will honor existing caching rules from things like the PCI bus. Note that
+ * there are other caches and buffers on many busses. In particular driver
+ * authors should read up on PCI writes.
+ *
+ * It's useful if some control registers are in such an area and
+ * write combining or read caching is not desirable:
+ *
+ * Must be freed with iounmap.
+ */
+void __iomem *ioremap_uc(resource_size_t phys_addr, unsigned long size)
+{
+	enum page_cache_mode pcm = _PAGE_CACHE_MODE_UC;
+
+	return __ioremap_caller(phys_addr, size, pcm,
+				__builtin_return_address(0));
+}
+EXPORT_SYMBOL_GPL(ioremap_uc);
+
+/**
  * ioremap_wc	-	map memory into CPU space write combined
  * @phys_addr:	bus address of the memory
  * @size:	size of the resource to map
@@ -258,14 +299,28 @@ EXPORT_SYMBOL(ioremap_nocache);
  */
 void __iomem *ioremap_wc(resource_size_t phys_addr, unsigned long size)
 {
-	if (pat_enabled)
-		return __ioremap_caller(phys_addr, size, _PAGE_CACHE_MODE_WC,
+	return __ioremap_caller(phys_addr, size, _PAGE_CACHE_MODE_WC,
 					__builtin_return_address(0));
-	else
-		return ioremap_nocache(phys_addr, size);
 }
 EXPORT_SYMBOL(ioremap_wc);
 
+/**
+ * ioremap_wt	-	map memory into CPU space write through
+ * @phys_addr:	bus address of the memory
+ * @size:	size of the resource to map
+ *
+ * This version of ioremap ensures that the memory is marked write through.
+ * Write through stores data into memory while keeping the cache up-to-date.
+ *
+ * Must be freed with iounmap.
+ */
+void __iomem *ioremap_wt(resource_size_t phys_addr, unsigned long size)
+{
+	return __ioremap_caller(phys_addr, size, _PAGE_CACHE_MODE_WT,
+					__builtin_return_address(0));
+}
+EXPORT_SYMBOL(ioremap_wt);
+
 void __iomem *ioremap_cache(resource_size_t phys_addr, unsigned long size)
 {
 	return __ioremap_caller(phys_addr, size, _PAGE_CACHE_MODE_WB,
@@ -331,7 +386,7 @@ void iounmap(volatile void __iomem *addr)
 }
 EXPORT_SYMBOL(iounmap);
 
-int arch_ioremap_pud_supported(void)
+int __init arch_ioremap_pud_supported(void)
 {
 #ifdef CONFIG_X86_64
 	return cpu_has_gbpages;
@@ -340,7 +395,7 @@ int arch_ioremap_pud_supported(void)
 #endif
 }
 
-int arch_ioremap_pmd_supported(void)
+int __init arch_ioremap_pmd_supported(void)
 {
 	return cpu_has_pse;
 }
@@ -353,18 +408,18 @@ void *xlate_dev_mem_ptr(phys_addr_t phys)
 {
 	unsigned long start  = phys &  PAGE_MASK;
 	unsigned long offset = phys & ~PAGE_MASK;
-	unsigned long vaddr;
+	void *vaddr;
 
 	/* If page is RAM, we can use __va. Otherwise ioremap and unmap. */
 	if (page_is_ram(start >> PAGE_SHIFT))
 		return __va(phys);
 
-	vaddr = (unsigned long)ioremap_cache(start, PAGE_SIZE);
+	vaddr = ioremap_cache(start, PAGE_SIZE);
 	/* Only add the offset on success and return NULL if the ioremap() failed: */
 	if (vaddr)
 		vaddr += offset;
 
-	return (void *)vaddr;
+	return vaddr;
 }
 
 void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr)
@@ -373,7 +428,6 @@ void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr)
 		return;
 
 	iounmap((void __iomem *)((unsigned long)addr & PAGE_MASK));
-	return;
 }
 
 static pte_t bm_pte[PAGE_SIZE/sizeof(pte_t)] __page_aligned_bss;
diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c
index c439ec478216..7a657f58bbea 100644
--- a/arch/x86/mm/mpx.c
+++ b/arch/x86/mm/mpx.c
@@ -10,13 +10,15 @@
 #include <linux/syscalls.h>
 #include <linux/sched/sysctl.h>
 
-#include <asm/i387.h>
 #include <asm/insn.h>
 #include <asm/mman.h>
 #include <asm/mmu_context.h>
 #include <asm/mpx.h>
 #include <asm/processor.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
+
+#define CREATE_TRACE_POINTS
+#include <asm/trace/mpx.h>
 
 static const char *mpx_mapping_name(struct vm_area_struct *vma)
 {
@@ -32,6 +34,22 @@ static int is_mpx_vma(struct vm_area_struct *vma)
 	return (vma->vm_ops == &mpx_vma_ops);
 }
 
+static inline unsigned long mpx_bd_size_bytes(struct mm_struct *mm)
+{
+	if (is_64bit_mm(mm))
+		return MPX_BD_SIZE_BYTES_64;
+	else
+		return MPX_BD_SIZE_BYTES_32;
+}
+
+static inline unsigned long mpx_bt_size_bytes(struct mm_struct *mm)
+{
+	if (is_64bit_mm(mm))
+		return MPX_BT_SIZE_BYTES_64;
+	else
+		return MPX_BT_SIZE_BYTES_32;
+}
+
 /*
  * This is really a simplified "vm_mmap". it only handles MPX
  * bounds tables (the bounds directory is user-allocated).
@@ -47,8 +65,8 @@ static unsigned long mpx_mmap(unsigned long len)
 	vm_flags_t vm_flags;
 	struct vm_area_struct *vma;
 
-	/* Only bounds table and bounds directory can be allocated here */
-	if (len != MPX_BD_SIZE_BYTES && len != MPX_BT_SIZE_BYTES)
+	/* Only bounds table can be allocated here */
+	if (len != mpx_bt_size_bytes(mm))
 		return -EINVAL;
 
 	down_write(&mm->mmap_sem);
@@ -272,10 +290,9 @@ bad_opcode:
  *
  * The caller is expected to kfree() the returned siginfo_t.
  */
-siginfo_t *mpx_generate_siginfo(struct pt_regs *regs,
-				struct xsave_struct *xsave_buf)
+siginfo_t *mpx_generate_siginfo(struct pt_regs *regs)
 {
-	struct bndreg *bndregs, *bndreg;
+	const struct bndreg *bndregs, *bndreg;
 	siginfo_t *info = NULL;
 	struct insn insn;
 	uint8_t bndregno;
@@ -295,8 +312,8 @@ siginfo_t *mpx_generate_siginfo(struct pt_regs *regs,
 		err = -EINVAL;
 		goto err_out;
 	}
-	/* get the bndregs _area_ of the xsave structure */
-	bndregs = get_xsave_addr(xsave_buf, XSTATE_BNDREGS);
+	/* get bndregs field from current task's xsave area */
+	bndregs = get_xsave_field_ptr(XSTATE_BNDREGS);
 	if (!bndregs) {
 		err = -EINVAL;
 		goto err_out;
@@ -334,6 +351,7 @@ siginfo_t *mpx_generate_siginfo(struct pt_regs *regs,
 		err = -EINVAL;
 		goto err_out;
 	}
+	trace_mpx_bounds_register_exception(info->si_addr, bndreg);
 	return info;
 err_out:
 	/* info might be NULL, but kfree() handles that */
@@ -341,25 +359,18 @@ err_out:
 	return ERR_PTR(err);
 }
 
-static __user void *task_get_bounds_dir(struct task_struct *tsk)
+static __user void *mpx_get_bounds_dir(void)
 {
-	struct bndcsr *bndcsr;
+	const struct bndcsr *bndcsr;
 
 	if (!cpu_feature_enabled(X86_FEATURE_MPX))
 		return MPX_INVALID_BOUNDS_DIR;
 
 	/*
-	 * 32-bit binaries on 64-bit kernels are currently
-	 * unsupported.
-	 */
-	if (IS_ENABLED(CONFIG_X86_64) && test_thread_flag(TIF_IA32))
-		return MPX_INVALID_BOUNDS_DIR;
-	/*
 	 * The bounds directory pointer is stored in a register
 	 * only accessible if we first do an xsave.
 	 */
-	fpu_save_init(&tsk->thread.fpu);
-	bndcsr = get_xsave_addr(&tsk->thread.fpu.state->xsave, XSTATE_BNDCSR);
+	bndcsr = get_xsave_field_ptr(XSTATE_BNDCSR);
 	if (!bndcsr)
 		return MPX_INVALID_BOUNDS_DIR;
 
@@ -378,10 +389,10 @@ static __user void *task_get_bounds_dir(struct task_struct *tsk)
 		(bndcsr->bndcfgu & MPX_BNDCFG_ADDR_MASK);
 }
 
-int mpx_enable_management(struct task_struct *tsk)
+int mpx_enable_management(void)
 {
 	void __user *bd_base = MPX_INVALID_BOUNDS_DIR;
-	struct mm_struct *mm = tsk->mm;
+	struct mm_struct *mm = current->mm;
 	int ret = 0;
 
 	/*
@@ -390,11 +401,12 @@ int mpx_enable_management(struct task_struct *tsk)
 	 * directory into XSAVE/XRSTOR Save Area and enable MPX through
 	 * XRSTOR instruction.
 	 *
-	 * fpu_xsave() is expected to be very expensive. Storing the bounds
-	 * directory here means that we do not have to do xsave in the unmap
-	 * path; we can just use mm->bd_addr instead.
+	 * The copy_xregs_to_kernel() beneath get_xsave_field_ptr() is
+	 * expected to be relatively expensive. Storing the bounds
+	 * directory here means that we do not have to do xsave in the
+	 * unmap path; we can just use mm->bd_addr instead.
 	 */
-	bd_base = task_get_bounds_dir(tsk);
+	bd_base = mpx_get_bounds_dir();
 	down_write(&mm->mmap_sem);
 	mm->bd_addr = bd_base;
 	if (mm->bd_addr == MPX_INVALID_BOUNDS_DIR)
@@ -404,7 +416,7 @@ int mpx_enable_management(struct task_struct *tsk)
 	return ret;
 }
 
-int mpx_disable_management(struct task_struct *tsk)
+int mpx_disable_management(void)
 {
 	struct mm_struct *mm = current->mm;
 
@@ -417,29 +429,59 @@ int mpx_disable_management(struct task_struct *tsk)
 	return 0;
 }
 
+static int mpx_cmpxchg_bd_entry(struct mm_struct *mm,
+		unsigned long *curval,
+		unsigned long __user *addr,
+		unsigned long old_val, unsigned long new_val)
+{
+	int ret;
+	/*
+	 * user_atomic_cmpxchg_inatomic() actually uses sizeof()
+	 * the pointer that we pass to it to figure out how much
+	 * data to cmpxchg.  We have to be careful here not to
+	 * pass a pointer to a 64-bit data type when we only want
+	 * a 32-bit copy.
+	 */
+	if (is_64bit_mm(mm)) {
+		ret = user_atomic_cmpxchg_inatomic(curval,
+				addr, old_val, new_val);
+	} else {
+		u32 uninitialized_var(curval_32);
+		u32 old_val_32 = old_val;
+		u32 new_val_32 = new_val;
+		u32 __user *addr_32 = (u32 __user *)addr;
+
+		ret = user_atomic_cmpxchg_inatomic(&curval_32,
+				addr_32, old_val_32, new_val_32);
+		*curval = curval_32;
+	}
+	return ret;
+}
+
 /*
- * With 32-bit mode, MPX_BT_SIZE_BYTES is 4MB, and the size of each
- * bounds table is 16KB. With 64-bit mode, MPX_BT_SIZE_BYTES is 2GB,
+ * With 32-bit mode, a bounds directory is 4MB, and the size of each
+ * bounds table is 16KB. With 64-bit mode, a bounds directory is 2GB,
  * and the size of each bounds table is 4MB.
  */
-static int allocate_bt(long __user *bd_entry)
+static int allocate_bt(struct mm_struct *mm, long __user *bd_entry)
 {
 	unsigned long expected_old_val = 0;
 	unsigned long actual_old_val = 0;
 	unsigned long bt_addr;
+	unsigned long bd_new_entry;
 	int ret = 0;
 
 	/*
 	 * Carve the virtual space out of userspace for the new
 	 * bounds table:
 	 */
-	bt_addr = mpx_mmap(MPX_BT_SIZE_BYTES);
+	bt_addr = mpx_mmap(mpx_bt_size_bytes(mm));
 	if (IS_ERR((void *)bt_addr))
 		return PTR_ERR((void *)bt_addr);
 	/*
 	 * Set the valid flag (kinda like _PAGE_PRESENT in a pte)
 	 */
-	bt_addr = bt_addr | MPX_BD_ENTRY_VALID_FLAG;
+	bd_new_entry = bt_addr | MPX_BD_ENTRY_VALID_FLAG;
 
 	/*
 	 * Go poke the address of the new bounds table in to the
@@ -452,8 +494,8 @@ static int allocate_bt(long __user *bd_entry)
 	 * mmap_sem at this point, unlike some of the other part
 	 * of the MPX code that have to pagefault_disable().
 	 */
-	ret = user_atomic_cmpxchg_inatomic(&actual_old_val, bd_entry,
-					   expected_old_val, bt_addr);
+	ret = mpx_cmpxchg_bd_entry(mm, &actual_old_val,	bd_entry,
+				   expected_old_val, bd_new_entry);
 	if (ret)
 		goto out_unmap;
 
@@ -481,9 +523,10 @@ static int allocate_bt(long __user *bd_entry)
 		ret = -EINVAL;
 		goto out_unmap;
 	}
+	trace_mpx_new_bounds_table(bt_addr);
 	return 0;
 out_unmap:
-	vm_munmap(bt_addr & MPX_BT_ADDR_MASK, MPX_BT_SIZE_BYTES);
+	vm_munmap(bt_addr, mpx_bt_size_bytes(mm));
 	return ret;
 }
 
@@ -498,12 +541,13 @@ out_unmap:
  * bound table is 16KB. With 64-bit mode, the size of BD is 2GB,
  * and the size of each bound table is 4MB.
  */
-static int do_mpx_bt_fault(struct xsave_struct *xsave_buf)
+static int do_mpx_bt_fault(void)
 {
 	unsigned long bd_entry, bd_base;
-	struct bndcsr *bndcsr;
+	const struct bndcsr *bndcsr;
+	struct mm_struct *mm = current->mm;
 
-	bndcsr = get_xsave_addr(xsave_buf, XSTATE_BNDCSR);
+	bndcsr = get_xsave_field_ptr(XSTATE_BNDCSR);
 	if (!bndcsr)
 		return -EINVAL;
 	/*
@@ -520,13 +564,13 @@ static int do_mpx_bt_fault(struct xsave_struct *xsave_buf)
 	 * the directory is.
 	 */
 	if ((bd_entry < bd_base) ||
-	    (bd_entry >= bd_base + MPX_BD_SIZE_BYTES))
+	    (bd_entry >= bd_base + mpx_bd_size_bytes(mm)))
 		return -EINVAL;
 
-	return allocate_bt((long __user *)bd_entry);
+	return allocate_bt(mm, (long __user *)bd_entry);
 }
 
-int mpx_handle_bd_fault(struct xsave_struct *xsave_buf)
+int mpx_handle_bd_fault(void)
 {
 	/*
 	 * Userspace never asked us to manage the bounds tables,
@@ -535,7 +579,7 @@ int mpx_handle_bd_fault(struct xsave_struct *xsave_buf)
 	if (!kernel_managing_mpx_tables(current->mm))
 		return -EINVAL;
 
-	if (do_mpx_bt_fault(xsave_buf)) {
+	if (do_mpx_bt_fault()) {
 		force_sig(SIGSEGV, current);
 		/*
 		 * The force_sig() is essentially "handling" this
@@ -572,29 +616,55 @@ static int mpx_resolve_fault(long __user *addr, int write)
 	return 0;
 }
 
+static unsigned long mpx_bd_entry_to_bt_addr(struct mm_struct *mm,
+					     unsigned long bd_entry)
+{
+	unsigned long bt_addr = bd_entry;
+	int align_to_bytes;
+	/*
+	 * Bit 0 in a bt_entry is always the valid bit.
+	 */
+	bt_addr &= ~MPX_BD_ENTRY_VALID_FLAG;
+	/*
+	 * Tables are naturally aligned at 8-byte boundaries
+	 * on 64-bit and 4-byte boundaries on 32-bit.  The
+	 * documentation makes it appear that the low bits
+	 * are ignored by the hardware, so we do the same.
+	 */
+	if (is_64bit_mm(mm))
+		align_to_bytes = 8;
+	else
+		align_to_bytes = 4;
+	bt_addr &= ~(align_to_bytes-1);
+	return bt_addr;
+}
+
 /*
  * Get the base of bounds tables pointed by specific bounds
  * directory entry.
  */
 static int get_bt_addr(struct mm_struct *mm,
-			long __user *bd_entry, unsigned long *bt_addr)
+			long __user *bd_entry_ptr,
+			unsigned long *bt_addr_result)
 {
 	int ret;
 	int valid_bit;
+	unsigned long bd_entry;
+	unsigned long bt_addr;
 
-	if (!access_ok(VERIFY_READ, (bd_entry), sizeof(*bd_entry)))
+	if (!access_ok(VERIFY_READ, (bd_entry_ptr), sizeof(*bd_entry_ptr)))
 		return -EFAULT;
 
 	while (1) {
 		int need_write = 0;
 
 		pagefault_disable();
-		ret = get_user(*bt_addr, bd_entry);
+		ret = get_user(bd_entry, bd_entry_ptr);
 		pagefault_enable();
 		if (!ret)
 			break;
 		if (ret == -EFAULT)
-			ret = mpx_resolve_fault(bd_entry, need_write);
+			ret = mpx_resolve_fault(bd_entry_ptr, need_write);
 		/*
 		 * If we could not resolve the fault, consider it
 		 * userspace's fault and error out.
@@ -603,8 +673,8 @@ static int get_bt_addr(struct mm_struct *mm,
 			return ret;
 	}
 
-	valid_bit = *bt_addr & MPX_BD_ENTRY_VALID_FLAG;
-	*bt_addr &= MPX_BT_ADDR_MASK;
+	valid_bit = bd_entry & MPX_BD_ENTRY_VALID_FLAG;
+	bt_addr = mpx_bd_entry_to_bt_addr(mm, bd_entry);
 
 	/*
 	 * When the kernel is managing bounds tables, a bounds directory
@@ -613,7 +683,7 @@ static int get_bt_addr(struct mm_struct *mm,
 	 * data in the address field, we know something is wrong. This
 	 * -EINVAL return will cause a SIGSEGV.
 	 */
-	if (!valid_bit && *bt_addr)
+	if (!valid_bit && bt_addr)
 		return -EINVAL;
 	/*
 	 * Do we have an completely zeroed bt entry?  That is OK.  It
@@ -624,19 +694,100 @@ static int get_bt_addr(struct mm_struct *mm,
 	if (!valid_bit)
 		return -ENOENT;
 
+	*bt_addr_result = bt_addr;
 	return 0;
 }
 
+static inline int bt_entry_size_bytes(struct mm_struct *mm)
+{
+	if (is_64bit_mm(mm))
+		return MPX_BT_ENTRY_BYTES_64;
+	else
+		return MPX_BT_ENTRY_BYTES_32;
+}
+
+/*
+ * Take a virtual address and turns it in to the offset in bytes
+ * inside of the bounds table where the bounds table entry
+ * controlling 'addr' can be found.
+ */
+static unsigned long mpx_get_bt_entry_offset_bytes(struct mm_struct *mm,
+		unsigned long addr)
+{
+	unsigned long bt_table_nr_entries;
+	unsigned long offset = addr;
+
+	if (is_64bit_mm(mm)) {
+		/* Bottom 3 bits are ignored on 64-bit */
+		offset >>= 3;
+		bt_table_nr_entries = MPX_BT_NR_ENTRIES_64;
+	} else {
+		/* Bottom 2 bits are ignored on 32-bit */
+		offset >>= 2;
+		bt_table_nr_entries = MPX_BT_NR_ENTRIES_32;
+	}
+	/*
+	 * We know the size of the table in to which we are
+	 * indexing, and we have eliminated all the low bits
+	 * which are ignored for indexing.
+	 *
+	 * Mask out all the high bits which we do not need
+	 * to index in to the table.  Note that the tables
+	 * are always powers of two so this gives us a proper
+	 * mask.
+	 */
+	offset &= (bt_table_nr_entries-1);
+	/*
+	 * We now have an entry offset in terms of *entries* in
+	 * the table.  We need to scale it back up to bytes.
+	 */
+	offset *= bt_entry_size_bytes(mm);
+	return offset;
+}
+
+/*
+ * How much virtual address space does a single bounds
+ * directory entry cover?
+ *
+ * Note, we need a long long because 4GB doesn't fit in
+ * to a long on 32-bit.
+ */
+static inline unsigned long bd_entry_virt_space(struct mm_struct *mm)
+{
+	unsigned long long virt_space = (1ULL << boot_cpu_data.x86_virt_bits);
+	if (is_64bit_mm(mm))
+		return virt_space / MPX_BD_NR_ENTRIES_64;
+	else
+		return virt_space / MPX_BD_NR_ENTRIES_32;
+}
+
 /*
  * Free the backing physical pages of bounds table 'bt_addr'.
  * Assume start...end is within that bounds table.
  */
-static int zap_bt_entries(struct mm_struct *mm,
+static noinline int zap_bt_entries_mapping(struct mm_struct *mm,
 		unsigned long bt_addr,
-		unsigned long start, unsigned long end)
+		unsigned long start_mapping, unsigned long end_mapping)
 {
 	struct vm_area_struct *vma;
 	unsigned long addr, len;
+	unsigned long start;
+	unsigned long end;
+
+	/*
+	 * if we 'end' on a boundary, the offset will be 0 which
+	 * is not what we want.  Back it up a byte to get the
+	 * last bt entry.  Then once we have the entry itself,
+	 * move 'end' back up by the table entry size.
+	 */
+	start = bt_addr + mpx_get_bt_entry_offset_bytes(mm, start_mapping);
+	end   = bt_addr + mpx_get_bt_entry_offset_bytes(mm, end_mapping - 1);
+	/*
+	 * Move end back up by one entry.  Among other things
+	 * this ensures that it remains page-aligned and does
+	 * not screw up zap_page_range()
+	 */
+	end += bt_entry_size_bytes(mm);
 
 	/*
 	 * Find the first overlapping vma. If vma->vm_start > start, there
@@ -648,7 +799,7 @@ static int zap_bt_entries(struct mm_struct *mm,
 		return -EINVAL;
 
 	/*
-	 * A NUMA policy on a VM_MPX VMA could cause this bouds table to
+	 * A NUMA policy on a VM_MPX VMA could cause this bounds table to
 	 * be split. So we need to look across the entire 'start -> end'
 	 * range of this bounds table, find all of the VM_MPX VMAs, and
 	 * zap only those.
@@ -666,27 +817,65 @@ static int zap_bt_entries(struct mm_struct *mm,
 
 		len = min(vma->vm_end, end) - addr;
 		zap_page_range(vma, addr, len, NULL);
+		trace_mpx_unmap_zap(addr, addr+len);
 
 		vma = vma->vm_next;
 		addr = vma->vm_start;
 	}
-
 	return 0;
 }
 
-static int unmap_single_bt(struct mm_struct *mm,
+static unsigned long mpx_get_bd_entry_offset(struct mm_struct *mm,
+		unsigned long addr)
+{
+	/*
+	 * There are several ways to derive the bd offsets.  We
+	 * use the following approach here:
+	 * 1. We know the size of the virtual address space
+	 * 2. We know the number of entries in a bounds table
+	 * 3. We know that each entry covers a fixed amount of
+	 *    virtual address space.
+	 * So, we can just divide the virtual address by the
+	 * virtual space used by one entry to determine which
+	 * entry "controls" the given virtual address.
+	 */
+	if (is_64bit_mm(mm)) {
+		int bd_entry_size = 8; /* 64-bit pointer */
+		/*
+		 * Take the 64-bit addressing hole in to account.
+		 */
+		addr &= ((1UL << boot_cpu_data.x86_virt_bits) - 1);
+		return (addr / bd_entry_virt_space(mm)) * bd_entry_size;
+	} else {
+		int bd_entry_size = 4; /* 32-bit pointer */
+		/*
+		 * 32-bit has no hole so this case needs no mask
+		 */
+		return (addr / bd_entry_virt_space(mm)) * bd_entry_size;
+	}
+	/*
+	 * The two return calls above are exact copies.  If we
+	 * pull out a single copy and put it in here, gcc won't
+	 * realize that we're doing a power-of-2 divide and use
+	 * shifts.  It uses a real divide.  If we put them up
+	 * there, it manages to figure it out (gcc 4.8.3).
+	 */
+}
+
+static int unmap_entire_bt(struct mm_struct *mm,
 		long __user *bd_entry, unsigned long bt_addr)
 {
 	unsigned long expected_old_val = bt_addr | MPX_BD_ENTRY_VALID_FLAG;
-	unsigned long actual_old_val = 0;
+	unsigned long uninitialized_var(actual_old_val);
 	int ret;
 
 	while (1) {
 		int need_write = 1;
+		unsigned long cleared_bd_entry = 0;
 
 		pagefault_disable();
-		ret = user_atomic_cmpxchg_inatomic(&actual_old_val, bd_entry,
-						   expected_old_val, 0);
+		ret = mpx_cmpxchg_bd_entry(mm, &actual_old_val,
+				bd_entry, expected_old_val, cleared_bd_entry);
 		pagefault_enable();
 		if (!ret)
 			break;
@@ -705,9 +894,8 @@ static int unmap_single_bt(struct mm_struct *mm,
 	if (actual_old_val != expected_old_val) {
 		/*
 		 * Someone else raced with us to unmap the table.
-		 * There was no bounds table pointed to by the
-		 * directory, so declare success.  Somebody freed
-		 * it.
+		 * That is OK, since we were both trying to do
+		 * the same thing.  Declare success.
 		 */
 		if (!actual_old_val)
 			return 0;
@@ -720,176 +908,113 @@ static int unmap_single_bt(struct mm_struct *mm,
 		 */
 		return -EINVAL;
 	}
-
 	/*
 	 * Note, we are likely being called under do_munmap() already. To
 	 * avoid recursion, do_munmap() will check whether it comes
 	 * from one bounds table through VM_MPX flag.
 	 */
-	return do_munmap(mm, bt_addr, MPX_BT_SIZE_BYTES);
+	return do_munmap(mm, bt_addr, mpx_bt_size_bytes(mm));
 }
 
-/*
- * If the bounds table pointed by bounds directory 'bd_entry' is
- * not shared, unmap this whole bounds table. Otherwise, only free
- * those backing physical pages of bounds table entries covered
- * in this virtual address region start...end.
- */
-static int unmap_shared_bt(struct mm_struct *mm,
-		long __user *bd_entry, unsigned long start,
-		unsigned long end, bool prev_shared, bool next_shared)
+static int try_unmap_single_bt(struct mm_struct *mm,
+	       unsigned long start, unsigned long end)
 {
-	unsigned long bt_addr;
-	int ret;
-
-	ret = get_bt_addr(mm, bd_entry, &bt_addr);
+	struct vm_area_struct *next;
+	struct vm_area_struct *prev;
 	/*
-	 * We could see an "error" ret for not-present bounds
-	 * tables (not really an error), or actual errors, but
-	 * stop unmapping either way.
+	 * "bta" == Bounds Table Area: the area controlled by the
+	 * bounds table that we are unmapping.
 	 */
-	if (ret)
-		return ret;
-
-	if (prev_shared && next_shared)
-		ret = zap_bt_entries(mm, bt_addr,
-				bt_addr+MPX_GET_BT_ENTRY_OFFSET(start),
-				bt_addr+MPX_GET_BT_ENTRY_OFFSET(end));
-	else if (prev_shared)
-		ret = zap_bt_entries(mm, bt_addr,
-				bt_addr+MPX_GET_BT_ENTRY_OFFSET(start),
-				bt_addr+MPX_BT_SIZE_BYTES);
-	else if (next_shared)
-		ret = zap_bt_entries(mm, bt_addr, bt_addr,
-				bt_addr+MPX_GET_BT_ENTRY_OFFSET(end));
-	else
-		ret = unmap_single_bt(mm, bd_entry, bt_addr);
-
-	return ret;
-}
-
-/*
- * A virtual address region being munmap()ed might share bounds table
- * with adjacent VMAs. We only need to free the backing physical
- * memory of these shared bounds tables entries covered in this virtual
- * address region.
- */
-static int unmap_edge_bts(struct mm_struct *mm,
-		unsigned long start, unsigned long end)
-{
+	unsigned long bta_start_vaddr = start & ~(bd_entry_virt_space(mm)-1);
+	unsigned long bta_end_vaddr = bta_start_vaddr + bd_entry_virt_space(mm);
+	unsigned long uninitialized_var(bt_addr);
+	void __user *bde_vaddr;
 	int ret;
-	long __user *bde_start, *bde_end;
-	struct vm_area_struct *prev, *next;
-	bool prev_shared = false, next_shared = false;
-
-	bde_start = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(start);
-	bde_end = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(end-1);
-
 	/*
-	 * Check whether bde_start and bde_end are shared with adjacent
-	 * VMAs.
-	 *
-	 * We already unliked the VMAs from the mm's rbtree so 'start'
+	 * We already unlinked the VMAs from the mm's rbtree so 'start'
 	 * is guaranteed to be in a hole. This gets us the first VMA
 	 * before the hole in to 'prev' and the next VMA after the hole
 	 * in to 'next'.
 	 */
 	next = find_vma_prev(mm, start, &prev);
-	if (prev && (mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(prev->vm_end-1))
-			== bde_start)
-		prev_shared = true;
-	if (next && (mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(next->vm_start))
-			== bde_end)
-		next_shared = true;
-
 	/*
-	 * This virtual address region being munmap()ed is only
-	 * covered by one bounds table.
-	 *
-	 * In this case, if this table is also shared with adjacent
-	 * VMAs, only part of the backing physical memory of the bounds
-	 * table need be freeed. Otherwise the whole bounds table need
-	 * be unmapped.
-	 */
-	if (bde_start == bde_end) {
-		return unmap_shared_bt(mm, bde_start, start, end,
-				prev_shared, next_shared);
+	 * Do not count other MPX bounds table VMAs as neighbors.
+	 * Although theoretically possible, we do not allow bounds
+	 * tables for bounds tables so our heads do not explode.
+	 * If we count them as neighbors here, we may end up with
+	 * lots of tables even though we have no actual table
+	 * entries in use.
+	 */
+	while (next && is_mpx_vma(next))
+		next = next->vm_next;
+	while (prev && is_mpx_vma(prev))
+		prev = prev->vm_prev;
+	/*
+	 * We know 'start' and 'end' lie within an area controlled
+	 * by a single bounds table.  See if there are any other
+	 * VMAs controlled by that bounds table.  If there are not
+	 * then we can "expand" the are we are unmapping to possibly
+	 * cover the entire table.
+	 */
+	next = find_vma_prev(mm, start, &prev);
+	if ((!prev || prev->vm_end <= bta_start_vaddr) &&
+	    (!next || next->vm_start >= bta_end_vaddr)) {
+		/*
+		 * No neighbor VMAs controlled by same bounds
+		 * table.  Try to unmap the whole thing
+		 */
+		start = bta_start_vaddr;
+		end = bta_end_vaddr;
 	}
 
+	bde_vaddr = mm->bd_addr + mpx_get_bd_entry_offset(mm, start);
+	ret = get_bt_addr(mm, bde_vaddr, &bt_addr);
 	/*
-	 * If more than one bounds tables are covered in this virtual
-	 * address region being munmap()ed, we need to separately check
-	 * whether bde_start and bde_end are shared with adjacent VMAs.
+	 * No bounds table there, so nothing to unmap.
 	 */
-	ret = unmap_shared_bt(mm, bde_start, start, end, prev_shared, false);
-	if (ret)
-		return ret;
-	ret = unmap_shared_bt(mm, bde_end, start, end, false, next_shared);
+	if (ret == -ENOENT) {
+		ret = 0;
+		return 0;
+	}
 	if (ret)
 		return ret;
-
-	return 0;
+	/*
+	 * We are unmapping an entire table.  Either because the
+	 * unmap that started this whole process was large enough
+	 * to cover an entire table, or that the unmap was small
+	 * but was the area covered by a bounds table.
+	 */
+	if ((start == bta_start_vaddr) &&
+	    (end == bta_end_vaddr))
+		return unmap_entire_bt(mm, bde_vaddr, bt_addr);
+	return zap_bt_entries_mapping(mm, bt_addr, start, end);
 }
 
 static int mpx_unmap_tables(struct mm_struct *mm,
 		unsigned long start, unsigned long end)
 {
-	int ret;
-	long __user *bd_entry, *bde_start, *bde_end;
-	unsigned long bt_addr;
-
-	/*
-	 * "Edge" bounds tables are those which are being used by the region
-	 * (start -> end), but that may be shared with adjacent areas.  If they
-	 * turn out to be completely unshared, they will be freed.  If they are
-	 * shared, we will free the backing store (like an MADV_DONTNEED) for
-	 * areas used by this region.
-	 */
-	ret = unmap_edge_bts(mm, start, end);
-	switch (ret) {
-		/* non-present tables are OK */
-		case 0:
-		case -ENOENT:
-			/* Success, or no tables to unmap */
-			break;
-		case -EINVAL:
-		case -EFAULT:
-		default:
-			return ret;
-	}
-
-	/*
-	 * Only unmap the bounds table that are
-	 *   1. fully covered
-	 *   2. not at the edges of the mapping, even if full aligned
-	 */
-	bde_start = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(start);
-	bde_end = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(end-1);
-	for (bd_entry = bde_start + 1; bd_entry < bde_end; bd_entry++) {
-		ret = get_bt_addr(mm, bd_entry, &bt_addr);
-		switch (ret) {
-			case 0:
-				break;
-			case -ENOENT:
-				/* No table here, try the next one */
-				continue;
-			case -EINVAL:
-			case -EFAULT:
-			default:
-				/*
-				 * Note: we are being strict here.
-				 * Any time we run in to an issue
-				 * unmapping tables, we stop and
-				 * SIGSEGV.
-				 */
-				return ret;
-		}
-
-		ret = unmap_single_bt(mm, bd_entry, bt_addr);
+	unsigned long one_unmap_start;
+	trace_mpx_unmap_search(start, end);
+
+	one_unmap_start = start;
+	while (one_unmap_start < end) {
+		int ret;
+		unsigned long next_unmap_start = ALIGN(one_unmap_start+1,
+						       bd_entry_virt_space(mm));
+		unsigned long one_unmap_end = end;
+		/*
+		 * if the end is beyond the current bounds table,
+		 * move it back so we only deal with a single one
+		 * at a time
+		 */
+		if (one_unmap_end > next_unmap_start)
+			one_unmap_end = next_unmap_start;
+		ret = try_unmap_single_bt(mm, one_unmap_start, one_unmap_end);
 		if (ret)
 			return ret;
-	}
 
+		one_unmap_start = next_unmap_start;
+	}
 	return 0;
 }
 
diff --git a/arch/x86/mm/pageattr-test.c b/arch/x86/mm/pageattr-test.c
index 6629f397b467..8ff686aa7e8c 100644
--- a/arch/x86/mm/pageattr-test.c
+++ b/arch/x86/mm/pageattr-test.c
@@ -9,6 +9,7 @@
 #include <linux/random.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
+#include <linux/vmalloc.h>
 
 #include <asm/cacheflush.h>
 #include <asm/pgtable.h>
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 89af288ec674..727158cb3b3c 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -14,6 +14,7 @@
 #include <linux/percpu.h>
 #include <linux/gfp.h>
 #include <linux/pci.h>
+#include <linux/vmalloc.h>
 
 #include <asm/e820.h>
 #include <asm/processor.h>
@@ -129,16 +130,15 @@ within(unsigned long addr, unsigned long start, unsigned long end)
  */
 void clflush_cache_range(void *vaddr, unsigned int size)
 {
-	void *vend = vaddr + size - 1;
+	unsigned long clflush_mask = boot_cpu_data.x86_clflush_size - 1;
+	void *vend = vaddr + size;
+	void *p;
 
 	mb();
 
-	for (; vaddr < vend; vaddr += boot_cpu_data.x86_clflush_size)
-		clflushopt(vaddr);
-	/*
-	 * Flush any possible final partial cacheline:
-	 */
-	clflushopt(vend);
+	for (p = (void *)((unsigned long)vaddr & ~clflush_mask);
+	     p < vend; p += boot_cpu_data.x86_clflush_size)
+		clflushopt(p);
 
 	mb();
 }
@@ -418,13 +418,11 @@ phys_addr_t slow_virt_to_phys(void *__virt_addr)
 	phys_addr_t phys_addr;
 	unsigned long offset;
 	enum pg_level level;
-	unsigned long psize;
 	unsigned long pmask;
 	pte_t *pte;
 
 	pte = lookup_address(virt_addr, &level);
 	BUG_ON(!pte);
-	psize = page_level_size(level);
 	pmask = page_level_mask(level);
 	offset = virt_addr & ~pmask;
 	phys_addr = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT;
@@ -1468,6 +1466,9 @@ int _set_memory_uc(unsigned long addr, int numpages)
 {
 	/*
 	 * for now UC MINUS. see comments in ioremap_nocache()
+	 * If you really need strong UC use ioremap_uc(), but note
+	 * that you cannot override IO areas with set_memory_*() as
+	 * these helpers cannot work with IO memory.
 	 */
 	return change_page_attr_set(&addr, numpages,
 				    cachemode2pgprot(_PAGE_CACHE_MODE_UC_MINUS),
@@ -1502,12 +1503,10 @@ EXPORT_SYMBOL(set_memory_uc);
 static int _set_memory_array(unsigned long *addr, int addrinarray,
 		enum page_cache_mode new_type)
 {
+	enum page_cache_mode set_type;
 	int i, j;
 	int ret;
 
-	/*
-	 * for now UC MINUS. see comments in ioremap_nocache()
-	 */
 	for (i = 0; i < addrinarray; i++) {
 		ret = reserve_memtype(__pa(addr[i]), __pa(addr[i]) + PAGE_SIZE,
 					new_type, NULL);
@@ -1515,9 +1514,12 @@ static int _set_memory_array(unsigned long *addr, int addrinarray,
 			goto out_free;
 	}
 
+	/* If WC, set to UC- first and then WC */
+	set_type = (new_type == _PAGE_CACHE_MODE_WC) ?
+				_PAGE_CACHE_MODE_UC_MINUS : new_type;
+
 	ret = change_page_attr_set(addr, addrinarray,
-				   cachemode2pgprot(_PAGE_CACHE_MODE_UC_MINUS),
-				   1);
+				   cachemode2pgprot(set_type), 1);
 
 	if (!ret && new_type == _PAGE_CACHE_MODE_WC)
 		ret = change_page_attr_set_clr(addr, addrinarray,
@@ -1549,6 +1551,12 @@ int set_memory_array_wc(unsigned long *addr, int addrinarray)
 }
 EXPORT_SYMBOL(set_memory_array_wc);
 
+int set_memory_array_wt(unsigned long *addr, int addrinarray)
+{
+	return _set_memory_array(addr, addrinarray, _PAGE_CACHE_MODE_WT);
+}
+EXPORT_SYMBOL_GPL(set_memory_array_wt);
+
 int _set_memory_wc(unsigned long addr, int numpages)
 {
 	int ret;
@@ -1571,27 +1579,42 @@ int set_memory_wc(unsigned long addr, int numpages)
 {
 	int ret;
 
-	if (!pat_enabled)
-		return set_memory_uc(addr, numpages);
-
 	ret = reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE,
 		_PAGE_CACHE_MODE_WC, NULL);
 	if (ret)
-		goto out_err;
+		return ret;
 
 	ret = _set_memory_wc(addr, numpages);
 	if (ret)
-		goto out_free;
-
-	return 0;
+		free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE);
 
-out_free:
-	free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE);
-out_err:
 	return ret;
 }
 EXPORT_SYMBOL(set_memory_wc);
 
+int _set_memory_wt(unsigned long addr, int numpages)
+{
+	return change_page_attr_set(&addr, numpages,
+				    cachemode2pgprot(_PAGE_CACHE_MODE_WT), 0);
+}
+
+int set_memory_wt(unsigned long addr, int numpages)
+{
+	int ret;
+
+	ret = reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE,
+			      _PAGE_CACHE_MODE_WT, NULL);
+	if (ret)
+		return ret;
+
+	ret = _set_memory_wt(addr, numpages);
+	if (ret)
+		free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(set_memory_wt);
+
 int _set_memory_wb(unsigned long addr, int numpages)
 {
 	/* WB cache mode is hard wired to all cache attribute bits being 0 */
@@ -1682,6 +1705,7 @@ static int _set_pages_array(struct page **pages, int addrinarray,
 {
 	unsigned long start;
 	unsigned long end;
+	enum page_cache_mode set_type;
 	int i;
 	int free_idx;
 	int ret;
@@ -1695,8 +1719,12 @@ static int _set_pages_array(struct page **pages, int addrinarray,
 			goto err_out;
 	}
 
+	/* If WC, set to UC- first and then WC */
+	set_type = (new_type == _PAGE_CACHE_MODE_WC) ?
+				_PAGE_CACHE_MODE_UC_MINUS : new_type;
+
 	ret = cpa_set_pages_array(pages, addrinarray,
-			cachemode2pgprot(_PAGE_CACHE_MODE_UC_MINUS));
+				  cachemode2pgprot(set_type));
 	if (!ret && new_type == _PAGE_CACHE_MODE_WC)
 		ret = change_page_attr_set_clr(NULL, addrinarray,
 					       cachemode2pgprot(
@@ -1730,6 +1758,12 @@ int set_pages_array_wc(struct page **pages, int addrinarray)
 }
 EXPORT_SYMBOL(set_pages_array_wc);
 
+int set_pages_array_wt(struct page **pages, int addrinarray)
+{
+	return _set_pages_array(pages, addrinarray, _PAGE_CACHE_MODE_WT);
+}
+EXPORT_SYMBOL_GPL(set_pages_array_wt);
+
 int set_pages_wb(struct page *page, int numpages)
 {
 	unsigned long addr = (unsigned long)page_address(page);
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 35af6771a95a..188e3e07eeeb 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -33,13 +33,17 @@
 #include "pat_internal.h"
 #include "mm_internal.h"
 
-#ifdef CONFIG_X86_PAT
-int __read_mostly pat_enabled = 1;
+#undef pr_fmt
+#define pr_fmt(fmt) "" fmt
+
+static bool boot_cpu_done;
+
+static int __read_mostly __pat_enabled = IS_ENABLED(CONFIG_X86_PAT);
 
 static inline void pat_disable(const char *reason)
 {
-	pat_enabled = 0;
-	printk(KERN_INFO "%s\n", reason);
+	__pat_enabled = 0;
+	pr_info("x86/PAT: %s\n", reason);
 }
 
 static int __init nopat(char *str)
@@ -48,13 +52,12 @@ static int __init nopat(char *str)
 	return 0;
 }
 early_param("nopat", nopat);
-#else
-static inline void pat_disable(const char *reason)
+
+bool pat_enabled(void)
 {
-	(void)reason;
+	return !!__pat_enabled;
 }
-#endif
-
+EXPORT_SYMBOL_GPL(pat_enabled);
 
 int pat_debug_enable;
 
@@ -65,22 +68,24 @@ static int __init pat_debug_setup(char *str)
 }
 __setup("debugpat", pat_debug_setup);
 
-static u64 __read_mostly boot_pat_state;
-
 #ifdef CONFIG_X86_PAT
 /*
- * X86 PAT uses page flags WC and Uncached together to keep track of
- * memory type of pages that have backing page struct. X86 PAT supports 3
- * different memory types, _PAGE_CACHE_MODE_WB, _PAGE_CACHE_MODE_WC and
- * _PAGE_CACHE_MODE_UC_MINUS and fourth state where page's memory type has not
- * been changed from its default (value of -1 used to denote this).
- * Note we do not support _PAGE_CACHE_MODE_UC here.
+ * X86 PAT uses page flags arch_1 and uncached together to keep track of
+ * memory type of pages that have backing page struct.
+ *
+ * X86 PAT supports 4 different memory types:
+ *  - _PAGE_CACHE_MODE_WB
+ *  - _PAGE_CACHE_MODE_WC
+ *  - _PAGE_CACHE_MODE_UC_MINUS
+ *  - _PAGE_CACHE_MODE_WT
+ *
+ * _PAGE_CACHE_MODE_WB is the default type.
  */
 
-#define _PGMT_DEFAULT		0
+#define _PGMT_WB		0
 #define _PGMT_WC		(1UL << PG_arch_1)
 #define _PGMT_UC_MINUS		(1UL << PG_uncached)
-#define _PGMT_WB		(1UL << PG_uncached | 1UL << PG_arch_1)
+#define _PGMT_WT		(1UL << PG_uncached | 1UL << PG_arch_1)
 #define _PGMT_MASK		(1UL << PG_uncached | 1UL << PG_arch_1)
 #define _PGMT_CLEAR_MASK	(~_PGMT_MASK)
 
@@ -88,14 +93,14 @@ static inline enum page_cache_mode get_page_memtype(struct page *pg)
 {
 	unsigned long pg_flags = pg->flags & _PGMT_MASK;
 
-	if (pg_flags == _PGMT_DEFAULT)
-		return -1;
+	if (pg_flags == _PGMT_WB)
+		return _PAGE_CACHE_MODE_WB;
 	else if (pg_flags == _PGMT_WC)
 		return _PAGE_CACHE_MODE_WC;
 	else if (pg_flags == _PGMT_UC_MINUS)
 		return _PAGE_CACHE_MODE_UC_MINUS;
 	else
-		return _PAGE_CACHE_MODE_WB;
+		return _PAGE_CACHE_MODE_WT;
 }
 
 static inline void set_page_memtype(struct page *pg,
@@ -112,11 +117,12 @@ static inline void set_page_memtype(struct page *pg,
 	case _PAGE_CACHE_MODE_UC_MINUS:
 		memtype_flags = _PGMT_UC_MINUS;
 		break;
-	case _PAGE_CACHE_MODE_WB:
-		memtype_flags = _PGMT_WB;
+	case _PAGE_CACHE_MODE_WT:
+		memtype_flags = _PGMT_WT;
 		break;
+	case _PAGE_CACHE_MODE_WB:
 	default:
-		memtype_flags = _PGMT_DEFAULT;
+		memtype_flags = _PGMT_WB;
 		break;
 	}
 
@@ -174,78 +180,154 @@ static enum page_cache_mode pat_get_cache_mode(unsigned pat_val, char *msg)
  * configuration.
  * Using lower indices is preferred, so we start with highest index.
  */
-void pat_init_cache_modes(void)
+void pat_init_cache_modes(u64 pat)
 {
-	int i;
 	enum page_cache_mode cache;
 	char pat_msg[33];
-	u64 pat;
+	int i;
 
-	rdmsrl(MSR_IA32_CR_PAT, pat);
 	pat_msg[32] = 0;
 	for (i = 7; i >= 0; i--) {
 		cache = pat_get_cache_mode((pat >> (i * 8)) & 7,
 					   pat_msg + 4 * i);
 		update_cache_mode_entry(i, cache);
 	}
-	pr_info("PAT configuration [0-7]: %s\n", pat_msg);
+	pr_info("x86/PAT: Configuration [0-7]: %s\n", pat_msg);
 }
 
 #define PAT(x, y)	((u64)PAT_ ## y << ((x)*8))
 
-void pat_init(void)
+static void pat_bsp_init(u64 pat)
 {
-	u64 pat;
-	bool boot_cpu = !boot_pat_state;
+	u64 tmp_pat;
 
-	if (!pat_enabled)
+	if (!cpu_has_pat) {
+		pat_disable("PAT not supported by CPU.");
 		return;
+	}
 
-	if (!cpu_has_pat) {
-		if (!boot_pat_state) {
-			pat_disable("PAT not supported by CPU.");
-			return;
-		} else {
-			/*
-			 * If this happens we are on a secondary CPU, but
-			 * switched to PAT on the boot CPU. We have no way to
-			 * undo PAT.
-			 */
-			printk(KERN_ERR "PAT enabled, "
-			       "but not supported by secondary CPU\n");
-			BUG();
-		}
+	if (!pat_enabled())
+		goto done;
+
+	rdmsrl(MSR_IA32_CR_PAT, tmp_pat);
+	if (!tmp_pat) {
+		pat_disable("PAT MSR is 0, disabled.");
+		return;
 	}
 
-	/* Set PWT to Write-Combining. All other bits stay the same */
-	/*
-	 * PTE encoding used in Linux:
-	 *      PAT
-	 *      |PCD
-	 *      ||PWT
-	 *      |||
-	 *      000 WB		_PAGE_CACHE_WB
-	 *      001 WC		_PAGE_CACHE_WC
-	 *      010 UC-		_PAGE_CACHE_UC_MINUS
-	 *      011 UC		_PAGE_CACHE_UC
-	 * PAT bit unused
-	 */
-	pat = PAT(0, WB) | PAT(1, WC) | PAT(2, UC_MINUS) | PAT(3, UC) |
-	      PAT(4, WB) | PAT(5, WC) | PAT(6, UC_MINUS) | PAT(7, UC);
-
-	/* Boot CPU check */
-	if (!boot_pat_state) {
-		rdmsrl(MSR_IA32_CR_PAT, boot_pat_state);
-		if (!boot_pat_state) {
-			pat_disable("PAT read returns always zero, disabled.");
-			return;
-		}
+	wrmsrl(MSR_IA32_CR_PAT, pat);
+
+done:
+	pat_init_cache_modes(pat);
+}
+
+static void pat_ap_init(u64 pat)
+{
+	if (!pat_enabled())
+		return;
+
+	if (!cpu_has_pat) {
+		/*
+		 * If this happens we are on a secondary CPU, but switched to
+		 * PAT on the boot CPU. We have no way to undo PAT.
+		 */
+		panic("x86/PAT: PAT enabled, but not supported by secondary CPU\n");
 	}
 
 	wrmsrl(MSR_IA32_CR_PAT, pat);
+}
+
+void pat_init(void)
+{
+	u64 pat;
+	struct cpuinfo_x86 *c = &boot_cpu_data;
+
+	if (!pat_enabled()) {
+		/*
+		 * No PAT. Emulate the PAT table that corresponds to the two
+		 * cache bits, PWT (Write Through) and PCD (Cache Disable). This
+		 * setup is the same as the BIOS default setup when the system
+		 * has PAT but the "nopat" boot option has been specified. This
+		 * emulated PAT table is used when MSR_IA32_CR_PAT returns 0.
+		 *
+		 * PTE encoding:
+		 *
+		 *       PCD
+		 *       |PWT  PAT
+		 *       ||    slot
+		 *       00    0    WB : _PAGE_CACHE_MODE_WB
+		 *       01    1    WT : _PAGE_CACHE_MODE_WT
+		 *       10    2    UC-: _PAGE_CACHE_MODE_UC_MINUS
+		 *       11    3    UC : _PAGE_CACHE_MODE_UC
+		 *
+		 * NOTE: When WC or WP is used, it is redirected to UC- per
+		 * the default setup in __cachemode2pte_tbl[].
+		 */
+		pat = PAT(0, WB) | PAT(1, WT) | PAT(2, UC_MINUS) | PAT(3, UC) |
+		      PAT(4, WB) | PAT(5, WT) | PAT(6, UC_MINUS) | PAT(7, UC);
 
-	if (boot_cpu)
-		pat_init_cache_modes();
+	} else if ((c->x86_vendor == X86_VENDOR_INTEL) &&
+		   (((c->x86 == 0x6) && (c->x86_model <= 0xd)) ||
+		    ((c->x86 == 0xf) && (c->x86_model <= 0x6)))) {
+		/*
+		 * PAT support with the lower four entries. Intel Pentium 2,
+		 * 3, M, and 4 are affected by PAT errata, which makes the
+		 * upper four entries unusable. To be on the safe side, we don't
+		 * use those.
+		 *
+		 *  PTE encoding:
+		 *      PAT
+		 *      |PCD
+		 *      ||PWT  PAT
+		 *      |||    slot
+		 *      000    0    WB : _PAGE_CACHE_MODE_WB
+		 *      001    1    WC : _PAGE_CACHE_MODE_WC
+		 *      010    2    UC-: _PAGE_CACHE_MODE_UC_MINUS
+		 *      011    3    UC : _PAGE_CACHE_MODE_UC
+		 * PAT bit unused
+		 *
+		 * NOTE: When WT or WP is used, it is redirected to UC- per
+		 * the default setup in __cachemode2pte_tbl[].
+		 */
+		pat = PAT(0, WB) | PAT(1, WC) | PAT(2, UC_MINUS) | PAT(3, UC) |
+		      PAT(4, WB) | PAT(5, WC) | PAT(6, UC_MINUS) | PAT(7, UC);
+	} else {
+		/*
+		 * Full PAT support.  We put WT in slot 7 to improve
+		 * robustness in the presence of errata that might cause
+		 * the high PAT bit to be ignored.  This way, a buggy slot 7
+		 * access will hit slot 3, and slot 3 is UC, so at worst
+		 * we lose performance without causing a correctness issue.
+		 * Pentium 4 erratum N46 is an example for such an erratum,
+		 * although we try not to use PAT at all on affected CPUs.
+		 *
+		 *  PTE encoding:
+		 *      PAT
+		 *      |PCD
+		 *      ||PWT  PAT
+		 *      |||    slot
+		 *      000    0    WB : _PAGE_CACHE_MODE_WB
+		 *      001    1    WC : _PAGE_CACHE_MODE_WC
+		 *      010    2    UC-: _PAGE_CACHE_MODE_UC_MINUS
+		 *      011    3    UC : _PAGE_CACHE_MODE_UC
+		 *      100    4    WB : Reserved
+		 *      101    5    WC : Reserved
+		 *      110    6    UC-: Reserved
+		 *      111    7    WT : _PAGE_CACHE_MODE_WT
+		 *
+		 * The reserved slots are unused, but mapped to their
+		 * corresponding types in the presence of PAT errata.
+		 */
+		pat = PAT(0, WB) | PAT(1, WC) | PAT(2, UC_MINUS) | PAT(3, UC) |
+		      PAT(4, WB) | PAT(5, WC) | PAT(6, UC_MINUS) | PAT(7, WT);
+	}
+
+	if (!boot_cpu_done) {
+		pat_bsp_init(pat);
+		boot_cpu_done = true;
+	} else {
+		pat_ap_init(pat);
+	}
 }
 
 #undef PAT
@@ -267,9 +349,9 @@ static unsigned long pat_x_mtrr_type(u64 start, u64 end,
 	 * request is for WB.
 	 */
 	if (req_type == _PAGE_CACHE_MODE_WB) {
-		u8 mtrr_type;
+		u8 mtrr_type, uniform;
 
-		mtrr_type = mtrr_type_lookup(start, end);
+		mtrr_type = mtrr_type_lookup(start, end, &uniform);
 		if (mtrr_type != MTRR_TYPE_WRBACK)
 			return _PAGE_CACHE_MODE_UC_MINUS;
 
@@ -324,9 +406,14 @@ static int pat_pagerange_is_ram(resource_size_t start, resource_size_t end)
 
 /*
  * For RAM pages, we use page flags to mark the pages with appropriate type.
- * Here we do two pass:
- * - Find the memtype of all the pages in the range, look for any conflicts
- * - In case of no conflicts, set the new memtype for pages in the range
+ * The page flags are limited to four types, WB (default), WC, WT and UC-.
+ * WP request fails with -EINVAL, and UC gets redirected to UC-.  Setting
+ * a new memory type is only allowed for a page mapped with the default WB
+ * type.
+ *
+ * Here we do two passes:
+ * - Find the memtype of all the pages in the range, look for any conflicts.
+ * - In case of no conflicts, set the new memtype for pages in the range.
  */
 static int reserve_ram_pages_type(u64 start, u64 end,
 				  enum page_cache_mode req_type,
@@ -335,6 +422,12 @@ static int reserve_ram_pages_type(u64 start, u64 end,
 	struct page *page;
 	u64 pfn;
 
+	if (req_type == _PAGE_CACHE_MODE_WP) {
+		if (new_type)
+			*new_type = _PAGE_CACHE_MODE_UC_MINUS;
+		return -EINVAL;
+	}
+
 	if (req_type == _PAGE_CACHE_MODE_UC) {
 		/* We do not support strong UC */
 		WARN_ON_ONCE(1);
@@ -346,8 +439,8 @@ static int reserve_ram_pages_type(u64 start, u64 end,
 
 		page = pfn_to_page(pfn);
 		type = get_page_memtype(page);
-		if (type != -1) {
-			pr_info("reserve_ram_pages_type failed [mem %#010Lx-%#010Lx], track 0x%x, req 0x%x\n",
+		if (type != _PAGE_CACHE_MODE_WB) {
+			pr_info("x86/PAT: reserve_ram_pages_type failed [mem %#010Lx-%#010Lx], track 0x%x, req 0x%x\n",
 				start, end - 1, type, req_type);
 			if (new_type)
 				*new_type = type;
@@ -373,7 +466,7 @@ static int free_ram_pages_type(u64 start, u64 end)
 
 	for (pfn = (start >> PAGE_SHIFT); pfn < (end >> PAGE_SHIFT); ++pfn) {
 		page = pfn_to_page(pfn);
-		set_page_memtype(page, -1);
+		set_page_memtype(page, _PAGE_CACHE_MODE_WB);
 	}
 	return 0;
 }
@@ -384,6 +477,7 @@ static int free_ram_pages_type(u64 start, u64 end)
  * - _PAGE_CACHE_MODE_WC
  * - _PAGE_CACHE_MODE_UC_MINUS
  * - _PAGE_CACHE_MODE_UC
+ * - _PAGE_CACHE_MODE_WT
  *
  * If new_type is NULL, function will return an error if it cannot reserve the
  * region with req_type. If new_type is non-NULL, function will return
@@ -400,14 +494,10 @@ int reserve_memtype(u64 start, u64 end, enum page_cache_mode req_type,
 
 	BUG_ON(start >= end); /* end is exclusive */
 
-	if (!pat_enabled) {
+	if (!pat_enabled()) {
 		/* This is identical to page table setting without PAT */
-		if (new_type) {
-			if (req_type == _PAGE_CACHE_MODE_WC)
-				*new_type = _PAGE_CACHE_MODE_UC_MINUS;
-			else
-				*new_type = req_type;
-		}
+		if (new_type)
+			*new_type = req_type;
 		return 0;
 	}
 
@@ -451,9 +541,9 @@ int reserve_memtype(u64 start, u64 end, enum page_cache_mode req_type,
 
 	err = rbt_memtype_check_insert(new, new_type);
 	if (err) {
-		printk(KERN_INFO "reserve_memtype failed [mem %#010Lx-%#010Lx], track %s, req %s\n",
-		       start, end - 1,
-		       cattr_name(new->type), cattr_name(req_type));
+		pr_info("x86/PAT: reserve_memtype failed [mem %#010Lx-%#010Lx], track %s, req %s\n",
+			start, end - 1,
+			cattr_name(new->type), cattr_name(req_type));
 		kfree(new);
 		spin_unlock(&memtype_lock);
 
@@ -475,7 +565,7 @@ int free_memtype(u64 start, u64 end)
 	int is_range_ram;
 	struct memtype *entry;
 
-	if (!pat_enabled)
+	if (!pat_enabled())
 		return 0;
 
 	/* Low ISA region is always mapped WB. No need to track */
@@ -497,8 +587,8 @@ int free_memtype(u64 start, u64 end)
 	spin_unlock(&memtype_lock);
 
 	if (!entry) {
-		printk(KERN_INFO "%s:%d freeing invalid memtype [mem %#010Lx-%#010Lx]\n",
-		       current->comm, current->pid, start, end - 1);
+		pr_info("x86/PAT: %s:%d freeing invalid memtype [mem %#010Lx-%#010Lx]\n",
+			current->comm, current->pid, start, end - 1);
 		return -EINVAL;
 	}
 
@@ -517,7 +607,7 @@ int free_memtype(u64 start, u64 end)
  * Only to be called when PAT is enabled
  *
  * Returns _PAGE_CACHE_MODE_WB, _PAGE_CACHE_MODE_WC, _PAGE_CACHE_MODE_UC_MINUS
- * or _PAGE_CACHE_MODE_UC
+ * or _PAGE_CACHE_MODE_WT.
  */
 static enum page_cache_mode lookup_memtype(u64 paddr)
 {
@@ -529,16 +619,9 @@ static enum page_cache_mode lookup_memtype(u64 paddr)
 
 	if (pat_pagerange_is_ram(paddr, paddr + PAGE_SIZE)) {
 		struct page *page;
-		page = pfn_to_page(paddr >> PAGE_SHIFT);
-		rettype = get_page_memtype(page);
-		/*
-		 * -1 from get_page_memtype() implies RAM page is in its
-		 * default state and not reserved, and hence of type WB
-		 */
-		if (rettype == -1)
-			rettype = _PAGE_CACHE_MODE_WB;
 
-		return rettype;
+		page = pfn_to_page(paddr >> PAGE_SHIFT);
+		return get_page_memtype(page);
 	}
 
 	spin_lock(&memtype_lock);
@@ -623,13 +706,13 @@ static inline int range_is_allowed(unsigned long pfn, unsigned long size)
 	u64 to = from + size;
 	u64 cursor = from;
 
-	if (!pat_enabled)
+	if (!pat_enabled())
 		return 1;
 
 	while (cursor < to) {
 		if (!devmem_is_allowed(pfn)) {
-			printk(KERN_INFO "Program %s tried to access /dev/mem between [mem %#010Lx-%#010Lx], PAT prevents it\n",
-			       current->comm, from, to - 1);
+			pr_info("x86/PAT: Program %s tried to access /dev/mem between [mem %#010Lx-%#010Lx], PAT prevents it\n",
+				current->comm, from, to - 1);
 			return 0;
 		}
 		cursor += PAGE_SIZE;
@@ -659,7 +742,7 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
 	 * caching for the high addresses through the KEN pin, but
 	 * we maintain the tradition of paranoia in this code.
 	 */
-	if (!pat_enabled &&
+	if (!pat_enabled() &&
 	    !(boot_cpu_has(X86_FEATURE_MTRR) ||
 	      boot_cpu_has(X86_FEATURE_K6_MTRR) ||
 	      boot_cpu_has(X86_FEATURE_CYRIX_ARR) ||
@@ -698,8 +781,7 @@ int kernel_map_sync_memtype(u64 base, unsigned long size,
 				size;
 
 	if (ioremap_change_attr((unsigned long)__va(base), id_sz, pcm) < 0) {
-		printk(KERN_INFO "%s:%d ioremap_change_attr failed %s "
-			"for [mem %#010Lx-%#010Lx]\n",
+		pr_info("x86/PAT: %s:%d ioremap_change_attr failed %s for [mem %#010Lx-%#010Lx]\n",
 			current->comm, current->pid,
 			cattr_name(pcm),
 			base, (unsigned long long)(base + size-1));
@@ -729,12 +811,12 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot,
 	 * the type requested matches the type of first page in the range.
 	 */
 	if (is_ram) {
-		if (!pat_enabled)
+		if (!pat_enabled())
 			return 0;
 
 		pcm = lookup_memtype(paddr);
 		if (want_pcm != pcm) {
-			printk(KERN_WARNING "%s:%d map pfn RAM range req %s for [mem %#010Lx-%#010Lx], got %s\n",
+			pr_warn("x86/PAT: %s:%d map pfn RAM range req %s for [mem %#010Lx-%#010Lx], got %s\n",
 				current->comm, current->pid,
 				cattr_name(want_pcm),
 				(unsigned long long)paddr,
@@ -755,13 +837,12 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot,
 		if (strict_prot ||
 		    !is_new_memtype_allowed(paddr, size, want_pcm, pcm)) {
 			free_memtype(paddr, paddr + size);
-			printk(KERN_ERR "%s:%d map pfn expected mapping type %s"
-				" for [mem %#010Lx-%#010Lx], got %s\n",
-				current->comm, current->pid,
-				cattr_name(want_pcm),
-				(unsigned long long)paddr,
-				(unsigned long long)(paddr + size - 1),
-				cattr_name(pcm));
+			pr_err("x86/PAT: %s:%d map pfn expected mapping type %s for [mem %#010Lx-%#010Lx], got %s\n",
+			       current->comm, current->pid,
+			       cattr_name(want_pcm),
+			       (unsigned long long)paddr,
+			       (unsigned long long)(paddr + size - 1),
+			       cattr_name(pcm));
 			return -EINVAL;
 		}
 		/*
@@ -844,7 +925,7 @@ int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
 		return ret;
 	}
 
-	if (!pat_enabled)
+	if (!pat_enabled())
 		return 0;
 
 	/*
@@ -872,7 +953,7 @@ int track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot,
 {
 	enum page_cache_mode pcm;
 
-	if (!pat_enabled)
+	if (!pat_enabled())
 		return 0;
 
 	/* Set prot based on lookup */
@@ -913,14 +994,18 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
 
 pgprot_t pgprot_writecombine(pgprot_t prot)
 {
-	if (pat_enabled)
-		return __pgprot(pgprot_val(prot) |
+	return __pgprot(pgprot_val(prot) |
 				cachemode2protval(_PAGE_CACHE_MODE_WC));
-	else
-		return pgprot_noncached(prot);
 }
 EXPORT_SYMBOL_GPL(pgprot_writecombine);
 
+pgprot_t pgprot_writethrough(pgprot_t prot)
+{
+	return __pgprot(pgprot_val(prot) |
+				cachemode2protval(_PAGE_CACHE_MODE_WT));
+}
+EXPORT_SYMBOL_GPL(pgprot_writethrough);
+
 #if defined(CONFIG_DEBUG_FS) && defined(CONFIG_X86_PAT)
 
 static struct memtype *memtype_get_idx(loff_t pos)
@@ -996,7 +1081,7 @@ static const struct file_operations memtype_fops = {
 
 static int __init pat_memtype_list_init(void)
 {
-	if (pat_enabled) {
+	if (pat_enabled()) {
 		debugfs_create_file("pat_memtype_list", S_IRUSR,
 				    arch_debugfs_dir, NULL, &memtype_fops);
 	}
diff --git a/arch/x86/mm/pat_internal.h b/arch/x86/mm/pat_internal.h
index f6411620305d..a739bfc40690 100644
--- a/arch/x86/mm/pat_internal.h
+++ b/arch/x86/mm/pat_internal.h
@@ -4,7 +4,7 @@
 extern int pat_debug_enable;
 
 #define dprintk(fmt, arg...) \
-	do { if (pat_debug_enable) printk(KERN_INFO fmt, ##arg); } while (0)
+	do { if (pat_debug_enable) pr_info("x86/PAT: " fmt, ##arg); } while (0)
 
 struct memtype {
 	u64			start;
diff --git a/arch/x86/mm/pat_rbtree.c b/arch/x86/mm/pat_rbtree.c
index 6582adcc8bd9..63931080366a 100644
--- a/arch/x86/mm/pat_rbtree.c
+++ b/arch/x86/mm/pat_rbtree.c
@@ -160,9 +160,9 @@ success:
 	return 0;
 
 failure:
-	printk(KERN_INFO "%s:%d conflicting memory types "
-		"%Lx-%Lx %s<->%s\n", current->comm, current->pid, start,
-		end, cattr_name(found_type), cattr_name(match->type));
+	pr_info("x86/PAT: %s:%d conflicting memory types %Lx-%Lx %s<->%s\n",
+		current->comm, current->pid, start, end,
+		cattr_name(found_type), cattr_name(match->type));
 	return -EBUSY;
 }
 
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 0b97d2c75df3..fb0a9dd1d6e4 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -563,16 +563,31 @@ void native_set_fixmap(enum fixed_addresses idx, phys_addr_t phys,
 }
 
 #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
+/**
+ * pud_set_huge - setup kernel PUD mapping
+ *
+ * MTRRs can override PAT memory types with 4KiB granularity. Therefore, this
+ * function sets up a huge page only if any of the following conditions are met:
+ *
+ * - MTRRs are disabled, or
+ *
+ * - MTRRs are enabled and the range is completely covered by a single MTRR, or
+ *
+ * - MTRRs are enabled and the corresponding MTRR memory type is WB, which
+ *   has no effect on the requested PAT memory type.
+ *
+ * Callers should try to decrease page size (1GB -> 2MB -> 4K) if the bigger
+ * page mapping attempt fails.
+ *
+ * Returns 1 on success and 0 on failure.
+ */
 int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot)
 {
-	u8 mtrr;
+	u8 mtrr, uniform;
 
-	/*
-	 * Do not use a huge page when the range is covered by non-WB type
-	 * of MTRRs.
-	 */
-	mtrr = mtrr_type_lookup(addr, addr + PUD_SIZE);
-	if ((mtrr != MTRR_TYPE_WRBACK) && (mtrr != 0xFF))
+	mtrr = mtrr_type_lookup(addr, addr + PUD_SIZE, &uniform);
+	if ((mtrr != MTRR_TYPE_INVALID) && (!uniform) &&
+	    (mtrr != MTRR_TYPE_WRBACK))
 		return 0;
 
 	prot = pgprot_4k_2_large(prot);
@@ -584,17 +599,24 @@ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot)
 	return 1;
 }
 
+/**
+ * pmd_set_huge - setup kernel PMD mapping
+ *
+ * See text over pud_set_huge() above.
+ *
+ * Returns 1 on success and 0 on failure.
+ */
 int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot)
 {
-	u8 mtrr;
+	u8 mtrr, uniform;
 
-	/*
-	 * Do not use a huge page when the range is covered by non-WB type
-	 * of MTRRs.
-	 */
-	mtrr = mtrr_type_lookup(addr, addr + PMD_SIZE);
-	if ((mtrr != MTRR_TYPE_WRBACK) && (mtrr != 0xFF))
+	mtrr = mtrr_type_lookup(addr, addr + PMD_SIZE, &uniform);
+	if ((mtrr != MTRR_TYPE_INVALID) && (!uniform) &&
+	    (mtrr != MTRR_TYPE_WRBACK)) {
+		pr_warn_once("%s: Cannot satisfy [mem %#010llx-%#010llx] with a huge-page mapping due to MTRR override.\n",
+			     __func__, addr, addr + PMD_SIZE);
 		return 0;
+	}
 
 	prot = pgprot_4k_2_large(prot);
 
@@ -605,6 +627,11 @@ int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot)
 	return 1;
 }
 
+/**
+ * pud_clear_huge - clear kernel PUD mapping when it is set
+ *
+ * Returns 1 on success and 0 on failure (no PUD map is found).
+ */
 int pud_clear_huge(pud_t *pud)
 {
 	if (pud_large(*pud)) {
@@ -615,6 +642,11 @@ int pud_clear_huge(pud_t *pud)
 	return 0;
 }
 
+/**
+ * pmd_clear_huge - clear kernel PMD mapping when it is set
+ *
+ * Returns 1 on success and 0 on failure (no PMD map is found).
+ */
 int pmd_clear_huge(pmd_t *pmd)
 {
 	if (pmd_large(*pmd)) {
diff --git a/arch/x86/net/bpf_jit.S b/arch/x86/net/bpf_jit.S
index 6440221ced0d..4093216b3791 100644
--- a/arch/x86/net/bpf_jit.S
+++ b/arch/x86/net/bpf_jit.S
@@ -8,7 +8,6 @@
  * of the License.
  */
 #include <linux/linkage.h>
-#include <asm/dwarf2.h>
 
 /*
  * Calling convention :
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index 14a63ed6fe09..ff9911707160 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -81,6 +81,17 @@ static const struct dmi_system_id pci_crs_quirks[] __initconst = {
 			DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies, LTD"),
 		},
 	},
+	/* https://bugs.launchpad.net/ubuntu/+source/alsa-driver/+bug/931368 */
+	/* https://bugs.launchpad.net/ubuntu/+source/alsa-driver/+bug/1033299 */
+	{
+		.callback = set_use_crs,
+		.ident = "Foxconn K8M890-8237A",
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "Foxconn"),
+			DMI_MATCH(DMI_BOARD_NAME, "K8M890-8237A"),
+			DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies, LTD"),
+		},
+	},
 
 	/* Now for the blacklist.. */
 
@@ -121,8 +132,10 @@ void __init pci_acpi_crs_quirks(void)
 {
 	int year;
 
-	if (dmi_get_date(DMI_BIOS_DATE, &year, NULL, NULL) && year < 2008)
-		pci_use_crs = false;
+	if (dmi_get_date(DMI_BIOS_DATE, &year, NULL, NULL) && year < 2008) {
+		if (iomem_resource.end <= 0xffffffff)
+			pci_use_crs = false;
+	}
 
 	dmi_check_system(pci_crs_quirks);
 
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index 349c0d32cc0b..0a9f2caf358f 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -429,12 +429,12 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
  	 * Caller can followup with UC MINUS request and add a WC mtrr if there
  	 * is a free mtrr slot.
  	 */
-	if (!pat_enabled && write_combine)
+	if (!pat_enabled() && write_combine)
 		return -EINVAL;
 
-	if (pat_enabled && write_combine)
+	if (pat_enabled() && write_combine)
 		prot |= cachemode2protval(_PAGE_CACHE_MODE_WC);
-	else if (pat_enabled || boot_cpu_data.x86 > 3)
+	else if (pat_enabled() || boot_cpu_data.x86 > 3)
 		/*
 		 * ioremap() and ioremap_nocache() defaults to UC MINUS for now.
 		 * To avoid attribute conflicts, request UC MINUS here
diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c
index 852aa4c92da0..27062303c881 100644
--- a/arch/x86/pci/intel_mid_pci.c
+++ b/arch/x86/pci/intel_mid_pci.c
@@ -208,6 +208,7 @@ static int pci_write(struct pci_bus *bus, unsigned int devfn, int where,
 
 static int intel_mid_pci_irq_enable(struct pci_dev *dev)
 {
+	struct irq_alloc_info info;
 	int polarity;
 
 	if (dev->irq_managed && dev->irq > 0)
@@ -217,14 +218,13 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev)
 		polarity = 0; /* active high */
 	else
 		polarity = 1; /* active low */
+	ioapic_set_alloc_attr(&info, dev_to_node(&dev->dev), 1, polarity);
 
 	/*
 	 * MRST only have IOAPIC, the PCI irq lines are 1:1 mapped to
 	 * IOAPIC RTE entries, so we just enable RTE for the device.
 	 */
-	if (mp_set_gsi_attr(dev->irq, 1, polarity, dev_to_node(&dev->dev)))
-		return -EBUSY;
-	if (mp_map_gsi_to_irq(dev->irq, IOAPIC_MAP_ALLOC) < 0)
+	if (mp_map_gsi_to_irq(dev->irq, IOAPIC_MAP_ALLOC, &info) < 0)
 		return -EBUSY;
 
 	dev->irq_managed = 1;
diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c
index 5dc6ca5e1741..9bd115484745 100644
--- a/arch/x86/pci/irq.c
+++ b/arch/x86/pci/irq.c
@@ -146,19 +146,20 @@ static void __init pirq_peer_trick(void)
 
 /*
  *  Code for querying and setting of IRQ routes on various interrupt routers.
+ *  PIC Edge/Level Control Registers (ELCR) 0x4d0 & 0x4d1.
  */
 
-void eisa_set_level_irq(unsigned int irq)
+void elcr_set_level_irq(unsigned int irq)
 {
 	unsigned char mask = 1 << (irq & 7);
 	unsigned int port = 0x4d0 + (irq >> 3);
 	unsigned char val;
-	static u16 eisa_irq_mask;
+	static u16 elcr_irq_mask;
 
-	if (irq >= 16 || (1 << irq) & eisa_irq_mask)
+	if (irq >= 16 || (1 << irq) & elcr_irq_mask)
 		return;
 
-	eisa_irq_mask |= (1 << irq);
+	elcr_irq_mask |= (1 << irq);
 	printk(KERN_DEBUG "PCI: setting IRQ %u as level-triggered\n", irq);
 	val = inb(port);
 	if (!(val & mask)) {
@@ -965,11 +966,11 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign)
 	} else if (r->get && (irq = r->get(pirq_router_dev, dev, pirq)) && \
 	((!(pci_probe & PCI_USE_PIRQ_MASK)) || ((1 << irq) & mask))) {
 		msg = "found";
-		eisa_set_level_irq(irq);
+		elcr_set_level_irq(irq);
 	} else if (newirq && r->set &&
 		(dev->class >> 8) != PCI_CLASS_DISPLAY_VGA) {
 		if (r->set(pirq_router_dev, dev, pirq, newirq)) {
-			eisa_set_level_irq(newirq);
+			elcr_set_level_irq(newirq);
 			msg = "assigned";
 			irq = newirq;
 		}
diff --git a/arch/x86/platform/Makefile b/arch/x86/platform/Makefile
index a62e0be3a2f1..f1a6c8e86ddd 100644
--- a/arch/x86/platform/Makefile
+++ b/arch/x86/platform/Makefile
@@ -1,4 +1,5 @@
 # Platform specific code goes here
+obj-y	+= atom/
 obj-y	+= ce4100/
 obj-y	+= efi/
 obj-y	+= geode/
diff --git a/arch/x86/platform/atom/Makefile b/arch/x86/platform/atom/Makefile
new file mode 100644
index 000000000000..0a3a40cbc794
--- /dev/null
+++ b/arch/x86/platform/atom/Makefile
@@ -0,0 +1 @@
+obj-$(CONFIG_PUNIT_ATOM_DEBUG) += punit_atom_debug.o
diff --git a/arch/x86/platform/atom/punit_atom_debug.c b/arch/x86/platform/atom/punit_atom_debug.c
new file mode 100644
index 000000000000..5ca8ead91579
--- /dev/null
+++ b/arch/x86/platform/atom/punit_atom_debug.c
@@ -0,0 +1,183 @@
+/*
+ * Intel SOC Punit device state debug driver
+ * Punit controls power management for North Complex devices (Graphics
+ * blocks, Image Signal Processing, video processing, display, DSP etc.)
+ *
+ * Copyright (c) 2015, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/device.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+#include <linux/io.h>
+#include <asm/cpu_device_id.h>
+#include <asm/iosf_mbi.h>
+
+/* Side band Interface port */
+#define PUNIT_PORT		0x04
+/* Power gate status reg */
+#define PWRGT_STATUS		0x61
+/* Subsystem config/status Video processor */
+#define VED_SS_PM0		0x32
+/* Subsystem config/status ISP (Image Signal Processor) */
+#define ISP_SS_PM0		0x39
+/* Subsystem config/status Input/output controller */
+#define MIO_SS_PM		0x3B
+/* Shift bits for getting status for video, isp and i/o */
+#define SSS_SHIFT		24
+/* Shift bits for getting status for graphics rendering */
+#define RENDER_POS		0
+/* Shift bits for getting status for media control */
+#define MEDIA_POS		2
+/* Shift bits for getting status for Valley View/Baytrail display */
+#define VLV_DISPLAY_POS		6
+/* Subsystem config/status display for Cherry Trail SOC */
+#define CHT_DSP_SSS		0x36
+/* Shift bits for getting status for display */
+#define CHT_DSP_SSS_POS		16
+
+struct punit_device {
+	char *name;
+	int reg;
+	int sss_pos;
+};
+
+static const struct punit_device punit_device_byt[] = {
+	{ "GFX RENDER",	PWRGT_STATUS,	RENDER_POS },
+	{ "GFX MEDIA",	PWRGT_STATUS,	MEDIA_POS },
+	{ "DISPLAY",	PWRGT_STATUS,	VLV_DISPLAY_POS },
+	{ "VED",	VED_SS_PM0,	SSS_SHIFT },
+	{ "ISP",	ISP_SS_PM0,	SSS_SHIFT },
+	{ "MIO",	MIO_SS_PM,	SSS_SHIFT },
+	{ NULL }
+};
+
+static const struct punit_device punit_device_cht[] = {
+	{ "GFX RENDER",	PWRGT_STATUS,	RENDER_POS },
+	{ "GFX MEDIA",	PWRGT_STATUS,	MEDIA_POS },
+	{ "DISPLAY",	CHT_DSP_SSS,	CHT_DSP_SSS_POS },
+	{ "VED",	VED_SS_PM0,	SSS_SHIFT },
+	{ "ISP",	ISP_SS_PM0,	SSS_SHIFT },
+	{ "MIO",	MIO_SS_PM,	SSS_SHIFT },
+	{ NULL }
+};
+
+static const char * const dstates[] = {"D0", "D0i1", "D0i2", "D0i3"};
+
+static int punit_dev_state_show(struct seq_file *seq_file, void *unused)
+{
+	u32 punit_pwr_status;
+	struct punit_device *punit_devp = seq_file->private;
+	int index;
+	int status;
+
+	seq_puts(seq_file, "\n\nPUNIT NORTH COMPLEX DEVICES :\n");
+	while (punit_devp->name) {
+		status = iosf_mbi_read(PUNIT_PORT, BT_MBI_PMC_READ,
+				       punit_devp->reg,
+				       &punit_pwr_status);
+		if (status) {
+			seq_printf(seq_file, "%9s : Read Failed\n",
+				   punit_devp->name);
+		} else  {
+			index = (punit_pwr_status >> punit_devp->sss_pos) & 3;
+			seq_printf(seq_file, "%9s : %s\n", punit_devp->name,
+				   dstates[index]);
+		}
+		punit_devp++;
+	}
+
+	return 0;
+}
+
+static int punit_dev_state_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, punit_dev_state_show, inode->i_private);
+}
+
+static const struct file_operations punit_dev_state_ops = {
+	.open		= punit_dev_state_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static struct dentry *punit_dbg_file;
+
+static int punit_dbgfs_register(struct punit_device *punit_device)
+{
+	static struct dentry *dev_state;
+
+	punit_dbg_file = debugfs_create_dir("punit_atom", NULL);
+	if (!punit_dbg_file)
+		return -ENXIO;
+
+	dev_state = debugfs_create_file("dev_power_state", S_IFREG | S_IRUGO,
+					punit_dbg_file, punit_device,
+					&punit_dev_state_ops);
+	if (!dev_state) {
+		pr_err("punit_dev_state register failed\n");
+		debugfs_remove(punit_dbg_file);
+		return -ENXIO;
+	}
+
+	return 0;
+}
+
+static void punit_dbgfs_unregister(void)
+{
+	debugfs_remove_recursive(punit_dbg_file);
+}
+
+#define ICPU(model, drv_data) \
+	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_MWAIT,\
+	  (kernel_ulong_t)&drv_data }
+
+static const struct x86_cpu_id intel_punit_cpu_ids[] = {
+	ICPU(55, punit_device_byt), /* Valleyview, Bay Trail */
+	ICPU(76, punit_device_cht), /* Braswell, Cherry Trail */
+	{}
+};
+
+MODULE_DEVICE_TABLE(x86cpu, intel_punit_cpu_ids);
+
+static int __init punit_atom_debug_init(void)
+{
+	const struct x86_cpu_id *id;
+	int ret;
+
+	id = x86_match_cpu(intel_punit_cpu_ids);
+	if (!id)
+		return -ENODEV;
+
+	ret = punit_dbgfs_register((struct punit_device *)id->driver_data);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+static void __exit punit_atom_debug_exit(void)
+{
+	punit_dbgfs_unregister();
+}
+
+module_init(punit_atom_debug_init);
+module_exit(punit_atom_debug_exit);
+
+MODULE_AUTHOR("Kumar P, Mahesh <mahesh.kumar.p@intel.com>");
+MODULE_AUTHOR("Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>");
+MODULE_DESCRIPTION("Driver for Punit devices states debugging");
+MODULE_LICENSE("GPL v2");
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 02744df576d5..3b984c3aa1b0 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -501,6 +501,8 @@ void __init efi_init(void)
 
 	if (efi_enabled(EFI_DBG))
 		print_efi_memmap();
+
+	efi_esrt_init();
 }
 
 void __init efi_late_init(void)
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_wdt.c b/arch/x86/platform/intel-mid/device_libs/platform_wdt.c
index 0b283d4d0ad7..de734134bc8d 100644
--- a/arch/x86/platform/intel-mid/device_libs/platform_wdt.c
+++ b/arch/x86/platform/intel-mid/device_libs/platform_wdt.c
@@ -27,6 +27,7 @@ static struct platform_device wdt_dev = {
 static int tangier_probe(struct platform_device *pdev)
 {
 	int gsi;
+	struct irq_alloc_info info;
 	struct intel_mid_wdt_pdata *pdata = pdev->dev.platform_data;
 
 	if (!pdata)
@@ -34,8 +35,8 @@ static int tangier_probe(struct platform_device *pdev)
 
 	/* IOAPIC builds identity mapping between GSI and IRQ on MID */
 	gsi = pdata->irq;
-	if (mp_set_gsi_attr(gsi, 1, 0, cpu_to_node(0)) ||
-	    mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC) <= 0) {
+	ioapic_set_alloc_attr(&info, cpu_to_node(0), 1, 0);
+	if (mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC, &info) <= 0) {
 		dev_warn(&pdev->dev, "cannot find interrupt %d in ioapic\n",
 			 gsi);
 		return -EINVAL;
diff --git a/arch/x86/platform/intel-mid/intel-mid.c b/arch/x86/platform/intel-mid/intel-mid.c
index 3005f0c89f2e..01d54ea766c1 100644
--- a/arch/x86/platform/intel-mid/intel-mid.c
+++ b/arch/x86/platform/intel-mid/intel-mid.c
@@ -81,26 +81,34 @@ static unsigned long __init intel_mid_calibrate_tsc(void)
 	return 0;
 }
 
+static void __init intel_mid_setup_bp_timer(void)
+{
+	apbt_time_init();
+	setup_boot_APIC_clock();
+}
+
 static void __init intel_mid_time_init(void)
 {
 	sfi_table_parse(SFI_SIG_MTMR, NULL, NULL, sfi_parse_mtmr);
+
 	switch (intel_mid_timer_options) {
 	case INTEL_MID_TIMER_APBT_ONLY:
 		break;
 	case INTEL_MID_TIMER_LAPIC_APBT:
-		x86_init.timers.setup_percpu_clockev = setup_boot_APIC_clock;
+		/* Use apbt and local apic */
+		x86_init.timers.setup_percpu_clockev = intel_mid_setup_bp_timer;
 		x86_cpuinit.setup_percpu_clockev = setup_secondary_APIC_clock;
-		break;
+		return;
 	default:
 		if (!boot_cpu_has(X86_FEATURE_ARAT))
 			break;
+		/* Lapic only, no apbt */
 		x86_init.timers.setup_percpu_clockev = setup_boot_APIC_clock;
 		x86_cpuinit.setup_percpu_clockev = setup_secondary_APIC_clock;
 		return;
 	}
-	/* we need at least one APB timer */
-	pre_init_apic_IRQ0();
-	apbt_time_init();
+
+	x86_init.timers.setup_percpu_clockev = apbt_time_init;
 }
 
 static void intel_mid_arch_setup(void)
diff --git a/arch/x86/platform/intel-mid/sfi.c b/arch/x86/platform/intel-mid/sfi.c
index c14ad34776c4..ce992e8cc065 100644
--- a/arch/x86/platform/intel-mid/sfi.c
+++ b/arch/x86/platform/intel-mid/sfi.c
@@ -95,18 +95,16 @@ int __init sfi_parse_mtmr(struct sfi_table_header *table)
 		pr_debug("timer[%d]: paddr = 0x%08x, freq = %dHz, irq = %d\n",
 			totallen, (u32)pentry->phys_addr,
 			pentry->freq_hz, pentry->irq);
-			if (!pentry->irq)
-				continue;
-			mp_irq.type = MP_INTSRC;
-			mp_irq.irqtype = mp_INT;
-/* triggering mode edge bit 2-3, active high polarity bit 0-1 */
-			mp_irq.irqflag = 5;
-			mp_irq.srcbus = MP_BUS_ISA;
-			mp_irq.srcbusirq = pentry->irq;	/* IRQ */
-			mp_irq.dstapic = MP_APIC_ALL;
-			mp_irq.dstirq = pentry->irq;
-			mp_save_irq(&mp_irq);
-			mp_map_gsi_to_irq(pentry->irq, IOAPIC_MAP_ALLOC);
+		mp_irq.type = MP_INTSRC;
+		mp_irq.irqtype = mp_INT;
+		/* triggering mode edge bit 2-3, active high polarity bit 0-1 */
+		mp_irq.irqflag = 5;
+		mp_irq.srcbus = MP_BUS_ISA;
+		mp_irq.srcbusirq = pentry->irq;	/* IRQ */
+		mp_irq.dstapic = MP_APIC_ALL;
+		mp_irq.dstirq = pentry->irq;
+		mp_save_irq(&mp_irq);
+		mp_map_gsi_to_irq(pentry->irq, IOAPIC_MAP_ALLOC, NULL);
 	}
 
 	return 0;
@@ -177,7 +175,7 @@ int __init sfi_parse_mrtc(struct sfi_table_header *table)
 		mp_irq.dstapic = MP_APIC_ALL;
 		mp_irq.dstirq = pentry->irq;
 		mp_save_irq(&mp_irq);
-		mp_map_gsi_to_irq(pentry->irq, IOAPIC_MAP_ALLOC);
+		mp_map_gsi_to_irq(pentry->irq, IOAPIC_MAP_ALLOC, NULL);
 	}
 	return 0;
 }
@@ -436,6 +434,7 @@ static int __init sfi_parse_devs(struct sfi_table_header *table)
 	struct devs_id *dev = NULL;
 	int num, i, ret;
 	int polarity;
+	struct irq_alloc_info info;
 
 	sb = (struct sfi_table_simple *)table;
 	num = SFI_GET_NUM_ENTRIES(sb, struct sfi_device_table_entry);
@@ -469,9 +468,8 @@ static int __init sfi_parse_devs(struct sfi_table_header *table)
 				polarity = 1;
 			}
 
-			ret = mp_set_gsi_attr(irq, 1, polarity, NUMA_NO_NODE);
-			if (ret == 0)
-				ret = mp_map_gsi_to_irq(irq, IOAPIC_MAP_ALLOC);
+			ioapic_set_alloc_attr(&info, NUMA_NO_NODE, 1, polarity);
+			ret = mp_map_gsi_to_irq(irq, IOAPIC_MAP_ALLOC, &info);
 			WARN_ON(ret < 0);
 		}
 
diff --git a/arch/x86/platform/sfi/sfi.c b/arch/x86/platform/sfi/sfi.c
index 2a8a74f3bd76..6c7111bbd1e9 100644
--- a/arch/x86/platform/sfi/sfi.c
+++ b/arch/x86/platform/sfi/sfi.c
@@ -25,8 +25,8 @@
 #include <linux/init.h>
 #include <linux/sfi.h>
 #include <linux/io.h>
-#include <linux/irqdomain.h>
 
+#include <asm/irqdomain.h>
 #include <asm/io_apic.h>
 #include <asm/mpspec.h>
 #include <asm/setup.h>
@@ -71,9 +71,6 @@ static int __init sfi_parse_cpus(struct sfi_table_header *table)
 #endif /* CONFIG_X86_LOCAL_APIC */
 
 #ifdef CONFIG_X86_IO_APIC
-static struct irq_domain_ops sfi_ioapic_irqdomain_ops = {
-	.map = mp_irqdomain_map,
-};
 
 static int __init sfi_parse_ioapic(struct sfi_table_header *table)
 {
@@ -82,7 +79,7 @@ static int __init sfi_parse_ioapic(struct sfi_table_header *table)
 	int i, num;
 	struct ioapic_domain_cfg cfg = {
 		.type = IOAPIC_DOMAIN_STRICT,
-		.ops = &sfi_ioapic_irqdomain_ops,
+		.ops = &mp_ioapic_irqdomain_ops,
 	};
 
 	sb = (struct sfi_table_simple *)table;
diff --git a/arch/x86/platform/uv/uv_irq.c b/arch/x86/platform/uv/uv_irq.c
index 0ce673645432..8570abe68be1 100644
--- a/arch/x86/platform/uv/uv_irq.c
+++ b/arch/x86/platform/uv/uv_irq.c
@@ -13,22 +13,37 @@
 #include <linux/slab.h>
 #include <linux/irq.h>
 
+#include <asm/irqdomain.h>
 #include <asm/apic.h>
 #include <asm/uv/uv_irq.h>
 #include <asm/uv/uv_hub.h>
 
 /* MMR offset and pnode of hub sourcing interrupts for a given irq */
-struct uv_irq_2_mmr_pnode{
-	struct rb_node		list;
+struct uv_irq_2_mmr_pnode {
 	unsigned long		offset;
 	int			pnode;
-	int			irq;
 };
 
-static DEFINE_SPINLOCK(uv_irq_lock);
-static struct rb_root		uv_irq_root;
+static void uv_program_mmr(struct irq_cfg *cfg, struct uv_irq_2_mmr_pnode *info)
+{
+	unsigned long mmr_value;
+	struct uv_IO_APIC_route_entry *entry;
+
+	BUILD_BUG_ON(sizeof(struct uv_IO_APIC_route_entry) !=
+		     sizeof(unsigned long));
+
+	mmr_value = 0;
+	entry = (struct uv_IO_APIC_route_entry *)&mmr_value;
+	entry->vector		= cfg->vector;
+	entry->delivery_mode	= apic->irq_delivery_mode;
+	entry->dest_mode	= apic->irq_dest_mode;
+	entry->polarity		= 0;
+	entry->trigger		= 0;
+	entry->mask		= 0;
+	entry->dest		= cfg->dest_apicid;
 
-static int uv_set_irq_affinity(struct irq_data *, const struct cpumask *, bool);
+	uv_write_global_mmr64(info->pnode, info->offset, mmr_value);
+}
 
 static void uv_noop(struct irq_data *data) { }
 
@@ -37,6 +52,23 @@ static void uv_ack_apic(struct irq_data *data)
 	ack_APIC_irq();
 }
 
+static int
+uv_set_irq_affinity(struct irq_data *data, const struct cpumask *mask,
+		    bool force)
+{
+	struct irq_data *parent = data->parent_data;
+	struct irq_cfg *cfg = irqd_cfg(data);
+	int ret;
+
+	ret = parent->chip->irq_set_affinity(parent, mask, force);
+	if (ret >= 0) {
+		uv_program_mmr(cfg, data->chip_data);
+		send_cleanup_vector(cfg);
+	}
+
+	return ret;
+}
+
 static struct irq_chip uv_irq_chip = {
 	.name			= "UV-CORE",
 	.irq_mask		= uv_noop,
@@ -45,189 +77,99 @@ static struct irq_chip uv_irq_chip = {
 	.irq_set_affinity	= uv_set_irq_affinity,
 };
 
-/*
- * Add offset and pnode information of the hub sourcing interrupts to the
- * rb tree for a specific irq.
- */
-static int uv_set_irq_2_mmr_info(int irq, unsigned long offset, unsigned blade)
+static int uv_domain_alloc(struct irq_domain *domain, unsigned int virq,
+			   unsigned int nr_irqs, void *arg)
 {
-	struct rb_node **link = &uv_irq_root.rb_node;
-	struct rb_node *parent = NULL;
-	struct uv_irq_2_mmr_pnode *n;
-	struct uv_irq_2_mmr_pnode *e;
-	unsigned long irqflags;
-
-	n = kmalloc_node(sizeof(struct uv_irq_2_mmr_pnode), GFP_KERNEL,
-				uv_blade_to_memory_nid(blade));
-	if (!n)
+	struct uv_irq_2_mmr_pnode *chip_data;
+	struct irq_alloc_info *info = arg;
+	struct irq_data *irq_data = irq_domain_get_irq_data(domain, virq);
+	int ret;
+
+	if (nr_irqs > 1 || !info || info->type != X86_IRQ_ALLOC_TYPE_UV)
+		return -EINVAL;
+
+	chip_data = kmalloc_node(sizeof(*chip_data), GFP_KERNEL,
+				 irq_data->node);
+	if (!chip_data)
 		return -ENOMEM;
 
-	n->irq = irq;
-	n->offset = offset;
-	n->pnode = uv_blade_to_pnode(blade);
-	spin_lock_irqsave(&uv_irq_lock, irqflags);
-	/* Find the right place in the rbtree: */
-	while (*link) {
-		parent = *link;
-		e = rb_entry(parent, struct uv_irq_2_mmr_pnode, list);
-
-		if (unlikely(irq == e->irq)) {
-			/* irq entry exists */
-			e->pnode = uv_blade_to_pnode(blade);
-			e->offset = offset;
-			spin_unlock_irqrestore(&uv_irq_lock, irqflags);
-			kfree(n);
-			return 0;
-		}
-
-		if (irq < e->irq)
-			link = &(*link)->rb_left;
+	ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, arg);
+	if (ret >= 0) {
+		if (info->uv_limit == UV_AFFINITY_CPU)
+			irq_set_status_flags(virq, IRQ_NO_BALANCING);
 		else
-			link = &(*link)->rb_right;
+			irq_set_status_flags(virq, IRQ_MOVE_PCNTXT);
+
+		chip_data->pnode = uv_blade_to_pnode(info->uv_blade);
+		chip_data->offset = info->uv_offset;
+		irq_domain_set_info(domain, virq, virq, &uv_irq_chip, chip_data,
+				    handle_percpu_irq, NULL, info->uv_name);
+	} else {
+		kfree(chip_data);
 	}
 
-	/* Insert the node into the rbtree. */
-	rb_link_node(&n->list, parent, link);
-	rb_insert_color(&n->list, &uv_irq_root);
-
-	spin_unlock_irqrestore(&uv_irq_lock, irqflags);
-	return 0;
+	return ret;
 }
 
-/* Retrieve offset and pnode information from the rb tree for a specific irq */
-int uv_irq_2_mmr_info(int irq, unsigned long *offset, int *pnode)
+static void uv_domain_free(struct irq_domain *domain, unsigned int virq,
+			   unsigned int nr_irqs)
 {
-	struct uv_irq_2_mmr_pnode *e;
-	struct rb_node *n;
-	unsigned long irqflags;
-
-	spin_lock_irqsave(&uv_irq_lock, irqflags);
-	n = uv_irq_root.rb_node;
-	while (n) {
-		e = rb_entry(n, struct uv_irq_2_mmr_pnode, list);
-
-		if (e->irq == irq) {
-			*offset = e->offset;
-			*pnode = e->pnode;
-			spin_unlock_irqrestore(&uv_irq_lock, irqflags);
-			return 0;
-		}
-
-		if (irq < e->irq)
-			n = n->rb_left;
-		else
-			n = n->rb_right;
-	}
-	spin_unlock_irqrestore(&uv_irq_lock, irqflags);
-	return -1;
+	struct irq_data *irq_data = irq_domain_get_irq_data(domain, virq);
+
+	BUG_ON(nr_irqs != 1);
+	kfree(irq_data->chip_data);
+	irq_clear_status_flags(virq, IRQ_MOVE_PCNTXT);
+	irq_clear_status_flags(virq, IRQ_NO_BALANCING);
+	irq_domain_free_irqs_top(domain, virq, nr_irqs);
 }
 
 /*
  * Re-target the irq to the specified CPU and enable the specified MMR located
  * on the specified blade to allow the sending of MSIs to the specified CPU.
  */
-static int
-arch_enable_uv_irq(char *irq_name, unsigned int irq, int cpu, int mmr_blade,
-		       unsigned long mmr_offset, int limit)
+static void uv_domain_activate(struct irq_domain *domain,
+			       struct irq_data *irq_data)
 {
-	const struct cpumask *eligible_cpu = cpumask_of(cpu);
-	struct irq_cfg *cfg = irq_cfg(irq);
-	unsigned long mmr_value;
-	struct uv_IO_APIC_route_entry *entry;
-	int mmr_pnode, err;
-	unsigned int dest;
-
-	BUILD_BUG_ON(sizeof(struct uv_IO_APIC_route_entry) !=
-			sizeof(unsigned long));
-
-	err = assign_irq_vector(irq, cfg, eligible_cpu);
-	if (err != 0)
-		return err;
-
-	err = apic->cpu_mask_to_apicid_and(eligible_cpu, eligible_cpu, &dest);
-	if (err != 0)
-		return err;
-
-	if (limit == UV_AFFINITY_CPU)
-		irq_set_status_flags(irq, IRQ_NO_BALANCING);
-	else
-		irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
-
-	irq_set_chip_and_handler_name(irq, &uv_irq_chip, handle_percpu_irq,
-				      irq_name);
-
-	mmr_value = 0;
-	entry = (struct uv_IO_APIC_route_entry *)&mmr_value;
-	entry->vector		= cfg->vector;
-	entry->delivery_mode	= apic->irq_delivery_mode;
-	entry->dest_mode	= apic->irq_dest_mode;
-	entry->polarity		= 0;
-	entry->trigger		= 0;
-	entry->mask		= 0;
-	entry->dest		= dest;
-
-	mmr_pnode = uv_blade_to_pnode(mmr_blade);
-	uv_write_global_mmr64(mmr_pnode, mmr_offset, mmr_value);
-
-	if (cfg->move_in_progress)
-		send_cleanup_vector(cfg);
-
-	return irq;
+	uv_program_mmr(irqd_cfg(irq_data), irq_data->chip_data);
 }
 
 /*
  * Disable the specified MMR located on the specified blade so that MSIs are
  * longer allowed to be sent.
  */
-static void arch_disable_uv_irq(int mmr_pnode, unsigned long mmr_offset)
+static void uv_domain_deactivate(struct irq_domain *domain,
+				 struct irq_data *irq_data)
 {
 	unsigned long mmr_value;
 	struct uv_IO_APIC_route_entry *entry;
 
-	BUILD_BUG_ON(sizeof(struct uv_IO_APIC_route_entry) !=
-			sizeof(unsigned long));
-
 	mmr_value = 0;
 	entry = (struct uv_IO_APIC_route_entry *)&mmr_value;
 	entry->mask = 1;
-
-	uv_write_global_mmr64(mmr_pnode, mmr_offset, mmr_value);
+	uv_program_mmr(irqd_cfg(irq_data), irq_data->chip_data);
 }
 
-static int
-uv_set_irq_affinity(struct irq_data *data, const struct cpumask *mask,
-		    bool force)
-{
-	struct irq_cfg *cfg = irqd_cfg(data);
-	unsigned int dest;
-	unsigned long mmr_value, mmr_offset;
-	struct uv_IO_APIC_route_entry *entry;
-	int mmr_pnode;
-
-	if (apic_set_affinity(data, mask, &dest))
-		return -1;
-
-	mmr_value = 0;
-	entry = (struct uv_IO_APIC_route_entry *)&mmr_value;
-
-	entry->vector		= cfg->vector;
-	entry->delivery_mode	= apic->irq_delivery_mode;
-	entry->dest_mode	= apic->irq_dest_mode;
-	entry->polarity		= 0;
-	entry->trigger		= 0;
-	entry->mask		= 0;
-	entry->dest		= dest;
-
-	/* Get previously stored MMR and pnode of hub sourcing interrupts */
-	if (uv_irq_2_mmr_info(data->irq, &mmr_offset, &mmr_pnode))
-		return -1;
-
-	uv_write_global_mmr64(mmr_pnode, mmr_offset, mmr_value);
+static const struct irq_domain_ops uv_domain_ops = {
+	.alloc		= uv_domain_alloc,
+	.free		= uv_domain_free,
+	.activate	= uv_domain_activate,
+	.deactivate	= uv_domain_deactivate,
+};
 
-	if (cfg->move_in_progress)
-		send_cleanup_vector(cfg);
+static struct irq_domain *uv_get_irq_domain(void)
+{
+	static struct irq_domain *uv_domain;
+	static DEFINE_MUTEX(uv_lock);
+
+	mutex_lock(&uv_lock);
+	if (uv_domain == NULL) {
+		uv_domain = irq_domain_add_tree(NULL, &uv_domain_ops, NULL);
+		if (uv_domain)
+			uv_domain->parent = x86_vector_domain;
+	}
+	mutex_unlock(&uv_lock);
 
-	return IRQ_SET_MASK_OK_NOCOPY;
+	return uv_domain;
 }
 
 /*
@@ -238,19 +180,21 @@ uv_set_irq_affinity(struct irq_data *data, const struct cpumask *mask,
 int uv_setup_irq(char *irq_name, int cpu, int mmr_blade,
 		 unsigned long mmr_offset, int limit)
 {
-	int ret, irq = irq_alloc_hwirq(uv_blade_to_memory_nid(mmr_blade));
+	struct irq_alloc_info info;
+	struct irq_domain *domain = uv_get_irq_domain();
 
-	if (!irq)
-		return -EBUSY;
+	if (!domain)
+		return -ENOMEM;
 
-	ret = arch_enable_uv_irq(irq_name, irq, cpu, mmr_blade, mmr_offset,
-		limit);
-	if (ret == irq)
-		uv_set_irq_2_mmr_info(irq, mmr_offset, mmr_blade);
-	else
-		irq_free_hwirq(irq);
+	init_irq_alloc_info(&info, cpumask_of(cpu));
+	info.type = X86_IRQ_ALLOC_TYPE_UV;
+	info.uv_limit = limit;
+	info.uv_blade = mmr_blade;
+	info.uv_offset = mmr_offset;
+	info.uv_name = irq_name;
 
-	return ret;
+	return irq_domain_alloc_irqs(domain, 1,
+				     uv_blade_to_memory_nid(mmr_blade), &info);
 }
 EXPORT_SYMBOL_GPL(uv_setup_irq);
 
@@ -263,26 +207,6 @@ EXPORT_SYMBOL_GPL(uv_setup_irq);
  */
 void uv_teardown_irq(unsigned int irq)
 {
-	struct uv_irq_2_mmr_pnode *e;
-	struct rb_node *n;
-	unsigned long irqflags;
-
-	spin_lock_irqsave(&uv_irq_lock, irqflags);
-	n = uv_irq_root.rb_node;
-	while (n) {
-		e = rb_entry(n, struct uv_irq_2_mmr_pnode, list);
-		if (e->irq == irq) {
-			arch_disable_uv_irq(e->pnode, e->offset);
-			rb_erase(n, &uv_irq_root);
-			kfree(e);
-			break;
-		}
-		if (irq < e->irq)
-			n = n->rb_left;
-		else
-			n = n->rb_right;
-	}
-	spin_unlock_irqrestore(&uv_irq_lock, irqflags);
-	irq_free_hwirq(irq);
+	irq_domain_free_irqs(irq, 1);
 }
 EXPORT_SYMBOL_GPL(uv_teardown_irq);
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index 757678fb26e1..0d7dd1f5ac36 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -18,10 +18,9 @@
 #include <asm/mtrr.h>
 #include <asm/page.h>
 #include <asm/mce.h>
-#include <asm/xcr.h>
 #include <asm/suspend.h>
+#include <asm/fpu/internal.h>
 #include <asm/debugreg.h>
-#include <asm/fpu-internal.h> /* pcntxt_mask */
 #include <asm/cpu.h>
 
 #ifdef CONFIG_X86_32
@@ -155,6 +154,8 @@ static void fix_processor_context(void)
 #endif
 	load_TR_desc();				/* This does ltr */
 	load_LDT(&current->active_mm->context);	/* This does lldt */
+
+	fpu__resume_cpu();
 }
 
 /**
@@ -221,12 +222,6 @@ static void notrace __restore_processor_state(struct saved_context *ctxt)
 	wrmsrl(MSR_KERNEL_GS_BASE, ctxt->gs_kernel_base);
 #endif
 
-	/*
-	 * restore XCR0 for xsave capable cpu's.
-	 */
-	if (cpu_has_xsave)
-		xsetbv(XCR_XFEATURE_ENABLED_MASK, pcntxt_mask);
-
 	fix_processor_context();
 
 	do_fpu_end();
diff --git a/arch/x86/power/hibernate_asm_64.S b/arch/x86/power/hibernate_asm_64.S
index 3c4469a7a929..e2386cb4e0c3 100644
--- a/arch/x86/power/hibernate_asm_64.S
+++ b/arch/x86/power/hibernate_asm_64.S
@@ -78,9 +78,9 @@ ENTRY(restore_image)
 
 	/* code below has been relocated to a safe page */
 ENTRY(core_restore_code)
-loop:
+.Lloop:
 	testq	%rdx, %rdx
-	jz	done
+	jz	.Ldone
 
 	/* get addresses from the pbe and copy the page */
 	movq	pbe_address(%rdx), %rsi
@@ -91,8 +91,8 @@ loop:
 
 	/* progress to the next pbe */
 	movq	pbe_next(%rdx), %rdx
-	jmp	loop
-done:
+	jmp	.Lloop
+.Ldone:
 	/* jump to the restore_registers address from the image header */
 	jmpq	*%rax
 	/*
diff --git a/arch/x86/um/Makefile b/arch/x86/um/Makefile
index acb384d24669..a8fecc226946 100644
--- a/arch/x86/um/Makefile
+++ b/arch/x86/um/Makefile
@@ -26,7 +26,7 @@ else
 
 obj-y += syscalls_64.o vdso/
 
-subarch-y = ../lib/csum-partial_64.o ../lib/memcpy_64.o ../lib/thunk_64.o \
+subarch-y = ../lib/csum-partial_64.o ../lib/memcpy_64.o ../entry/thunk_64.o \
 		../lib/rwsem.o
 
 endif
diff --git a/arch/x86/um/asm/barrier.h b/arch/x86/um/asm/barrier.h
index 7e8a1a650435..b9531d343134 100644
--- a/arch/x86/um/asm/barrier.h
+++ b/arch/x86/um/asm/barrier.h
@@ -39,7 +39,8 @@
 #define smp_mb()	barrier()
 #define smp_rmb()	barrier()
 #define smp_wmb()	barrier()
-#define set_mb(var, value) do { var = value; barrier(); } while (0)
+
+#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); barrier(); } while (0)
 
 #define read_barrier_depends()		do { } while (0)
 #define smp_read_barrier_depends()	do { } while (0)
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 46957ead3060..0b95c9b8283f 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1181,10 +1181,11 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = {
 	.read_tscp = native_read_tscp,
 
 	.iret = xen_iret,
-	.irq_enable_sysexit = xen_sysexit,
 #ifdef CONFIG_X86_64
 	.usergs_sysret32 = xen_sysret32,
 	.usergs_sysret64 = xen_sysret64,
+#else
+	.irq_enable_sysexit = xen_sysexit,
 #endif
 
 	.load_tr_desc = paravirt_nop,
@@ -1423,7 +1424,7 @@ static void xen_pvh_set_cr_flags(int cpu)
 		return;
 	/*
 	 * For BSP, PSE PGE are set in probe_page_size_mask(), for APs
-	 * set them here. For all, OSFXSR OSXMMEXCPT are set in fpu_init.
+	 * set them here. For all, OSFXSR OSXMMEXCPT are set in fpu__init_cpu().
 	*/
 	if (cpu_has_pse)
 		cr4_set_bits_and_update_boot(X86_CR4_PSE);
@@ -1467,6 +1468,7 @@ asmlinkage __visible void __init xen_start_kernel(void)
 {
 	struct physdev_set_iopl set_iopl;
 	unsigned long initrd_start = 0;
+	u64 pat;
 	int rc;
 
 	if (!xen_start_info)
@@ -1574,8 +1576,8 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	 * Modify the cache mode translation tables to match Xen's PAT
 	 * configuration.
 	 */
-
-	pat_init_cache_modes();
+	rdmsrl(MSR_IA32_CR_PAT, pat);
+	pat_init_cache_modes(pat);
 
 	/* keep using Xen gdt for now; no urgent need to change it */
 
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index b47124d4cd67..8b7f18e200aa 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -67,6 +67,7 @@
 #include <linux/seq_file.h>
 #include <linux/bootmem.h>
 #include <linux/slab.h>
+#include <linux/vmalloc.h>
 
 #include <asm/cache.h>
 #include <asm/setup.h>
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index 956374c1edbc..9e2ba5c6e1dd 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -17,6 +17,56 @@
 #include "xen-ops.h"
 #include "debugfs.h"
 
+static DEFINE_PER_CPU(int, lock_kicker_irq) = -1;
+static DEFINE_PER_CPU(char *, irq_name);
+static bool xen_pvspin = true;
+
+#ifdef CONFIG_QUEUED_SPINLOCKS
+
+#include <asm/qspinlock.h>
+
+static void xen_qlock_kick(int cpu)
+{
+	xen_send_IPI_one(cpu, XEN_SPIN_UNLOCK_VECTOR);
+}
+
+/*
+ * Halt the current CPU & release it back to the host
+ */
+static void xen_qlock_wait(u8 *byte, u8 val)
+{
+	int irq = __this_cpu_read(lock_kicker_irq);
+
+	/* If kicker interrupts not initialized yet, just spin */
+	if (irq == -1)
+		return;
+
+	/* clear pending */
+	xen_clear_irq_pending(irq);
+	barrier();
+
+	/*
+	 * We check the byte value after clearing pending IRQ to make sure
+	 * that we won't miss a wakeup event because of the clearing.
+	 *
+	 * The sync_clear_bit() call in xen_clear_irq_pending() is atomic.
+	 * So it is effectively a memory barrier for x86.
+	 */
+	if (READ_ONCE(*byte) != val)
+		return;
+
+	/*
+	 * If an interrupt happens here, it will leave the wakeup irq
+	 * pending, which will cause xen_poll_irq() to return
+	 * immediately.
+	 */
+
+	/* Block until irq becomes pending (or perhaps a spurious wakeup) */
+	xen_poll_irq(irq);
+}
+
+#else /* CONFIG_QUEUED_SPINLOCKS */
+
 enum xen_contention_stat {
 	TAKEN_SLOW,
 	TAKEN_SLOW_PICKUP,
@@ -100,12 +150,9 @@ struct xen_lock_waiting {
 	__ticket_t want;
 };
 
-static DEFINE_PER_CPU(int, lock_kicker_irq) = -1;
-static DEFINE_PER_CPU(char *, irq_name);
 static DEFINE_PER_CPU(struct xen_lock_waiting, lock_waiting);
 static cpumask_t waiting_cpus;
 
-static bool xen_pvspin = true;
 __visible void xen_lock_spinning(struct arch_spinlock *lock, __ticket_t want)
 {
 	int irq = __this_cpu_read(lock_kicker_irq);
@@ -217,6 +264,7 @@ static void xen_unlock_kick(struct arch_spinlock *lock, __ticket_t next)
 		}
 	}
 }
+#endif /* CONFIG_QUEUED_SPINLOCKS */
 
 static irqreturn_t dummy_handler(int irq, void *dev_id)
 {
@@ -280,8 +328,16 @@ void __init xen_init_spinlocks(void)
 		return;
 	}
 	printk(KERN_DEBUG "xen: PV spinlocks enabled\n");
+#ifdef CONFIG_QUEUED_SPINLOCKS
+	__pv_init_lock_hash();
+	pv_lock_ops.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath;
+	pv_lock_ops.queued_spin_unlock = PV_CALLEE_SAVE(__pv_queued_spin_unlock);
+	pv_lock_ops.wait = xen_qlock_wait;
+	pv_lock_ops.kick = xen_qlock_kick;
+#else
 	pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(xen_lock_spinning);
 	pv_lock_ops.unlock_kick = xen_unlock_kick;
+#endif
 }
 
 /*
@@ -310,7 +366,7 @@ static __init int xen_parse_nopvspin(char *arg)
 }
 early_param("xen_nopvspin", xen_parse_nopvspin);
 
-#ifdef CONFIG_XEN_DEBUG_FS
+#if defined(CONFIG_XEN_DEBUG_FS) && !defined(CONFIG_QUEUED_SPINLOCKS)
 
 static struct dentry *d_spin_debug;
 
diff --git a/arch/x86/xen/xen-asm_64.S b/arch/x86/xen/xen-asm_64.S
index 985fc3ee0973..f22667abf7b9 100644
--- a/arch/x86/xen/xen-asm_64.S
+++ b/arch/x86/xen/xen-asm_64.S
@@ -15,6 +15,8 @@
 #include <asm/percpu.h>
 #include <asm/processor-flags.h>
 #include <asm/segment.h>
+#include <asm/asm-offsets.h>
+#include <asm/thread_info.h>
 
 #include <xen/interface/xen.h>
 
@@ -47,29 +49,13 @@ ENTRY(xen_iret)
 ENDPATCH(xen_iret)
 RELOC(xen_iret, 1b+1)
 
-/*
- * sysexit is not used for 64-bit processes, so it's only ever used to
- * return to 32-bit compat userspace.
- */
-ENTRY(xen_sysexit)
-	pushq $__USER32_DS
-	pushq %rcx
-	pushq $X86_EFLAGS_IF
-	pushq $__USER32_CS
-	pushq %rdx
-
-	pushq $0
-1:	jmp hypercall_iret
-ENDPATCH(xen_sysexit)
-RELOC(xen_sysexit, 1b+1)
-
 ENTRY(xen_sysret64)
 	/*
 	 * We're already on the usermode stack at this point, but
 	 * still with the kernel gs, so we can easily switch back
 	 */
 	movq %rsp, PER_CPU_VAR(rsp_scratch)
-	movq PER_CPU_VAR(kernel_stack), %rsp
+	movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
 
 	pushq $__USER_DS
 	pushq PER_CPU_VAR(rsp_scratch)
@@ -88,7 +74,7 @@ ENTRY(xen_sysret32)
 	 * still with the kernel gs, so we can easily switch back
 	 */
 	movq %rsp, PER_CPU_VAR(rsp_scratch)
-	movq PER_CPU_VAR(kernel_stack), %rsp
+	movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
 
 	pushq $__USER32_DS
 	pushq PER_CPU_VAR(rsp_scratch)
@@ -128,7 +114,7 @@ RELOC(xen_sysret32, 1b+1)
 /* Normal 64-bit system call target */
 ENTRY(xen_syscall_target)
 	undo_xen_syscall
-	jmp system_call_after_swapgs
+	jmp entry_SYSCALL_64_after_swapgs
 ENDPROC(xen_syscall_target)
 
 #ifdef CONFIG_IA32_EMULATION
@@ -136,13 +122,13 @@ ENDPROC(xen_syscall_target)
 /* 32-bit compat syscall target */
 ENTRY(xen_syscall32_target)
 	undo_xen_syscall
-	jmp ia32_cstar_target
+	jmp entry_SYSCALL_compat
 ENDPROC(xen_syscall32_target)
 
 /* 32-bit compat sysenter target */
 ENTRY(xen_sysenter_target)
 	undo_xen_syscall
-	jmp ia32_sysenter_target
+	jmp entry_SYSENTER_compat
 ENDPROC(xen_sysenter_target)
 
 #else /* !CONFIG_IA32_EMULATION */
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 9e195c683549..c20fe29e65f4 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -134,7 +134,9 @@ DECL_ASM(void, xen_restore_fl_direct, unsigned long);
 
 /* These are not functions, and cannot be called normally */
 __visible void xen_iret(void);
+#ifdef CONFIG_X86_32
 __visible void xen_sysexit(void);
+#endif
 __visible void xen_sysret32(void);
 __visible void xen_sysret64(void);
 __visible void xen_adjust_exception_frame(void);
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index 87be10e8b57a..e5b872ba2484 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -151,7 +151,7 @@ config HAVE_SMP
 	  the CPU core definition and currently needs to be selected manually.
 
 	  Multiprocessor support in implemented with external cache and
-	  interrupt controlers.
+	  interrupt controllers.
 
 	  The MX interrupt distributer adds Interprocessor Interrupts
 	  and causes the IRQ numbers to be increased by 4 for devices
diff --git a/arch/xtensa/include/asm/io.h b/arch/xtensa/include/asm/io.h
index fe1600a09438..c39bb6e61911 100644
--- a/arch/xtensa/include/asm/io.h
+++ b/arch/xtensa/include/asm/io.h
@@ -59,6 +59,7 @@ static inline void __iomem *ioremap_cache(unsigned long offset,
 }
 
 #define ioremap_wc ioremap_nocache
+#define ioremap_wt ioremap_nocache
 
 static inline void __iomem *ioremap(unsigned long offset, unsigned long size)
 {
diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c
index 9e3571a6535c..83a44a33cfa1 100644
--- a/arch/xtensa/mm/fault.c
+++ b/arch/xtensa/mm/fault.c
@@ -15,10 +15,10 @@
 #include <linux/mm.h>
 #include <linux/module.h>
 #include <linux/hardirq.h>
+#include <linux/uaccess.h>
 #include <asm/mmu_context.h>
 #include <asm/cacheflush.h>
 #include <asm/hardirq.h>
-#include <asm/uaccess.h>
 #include <asm/pgalloc.h>
 
 DEFINE_PER_CPU(unsigned long, asid_cache) = ASID_USER_FIRST;
@@ -57,7 +57,7 @@ void do_page_fault(struct pt_regs *regs)
 	/* If we're in an interrupt or have no user
 	 * context, we must not take the fault..
 	 */
-	if (in_atomic() || !mm) {
+	if (faulthandler_disabled() || !mm) {
 		bad_page_fault(regs, address, SIGSEGV);
 		return;
 	}
diff --git a/arch/xtensa/mm/highmem.c b/arch/xtensa/mm/highmem.c
index 8cfb71ec0937..184ceadccc1a 100644
--- a/arch/xtensa/mm/highmem.c
+++ b/arch/xtensa/mm/highmem.c
@@ -42,6 +42,7 @@ void *kmap_atomic(struct page *page)
 	enum fixed_addresses idx;
 	unsigned long vaddr;
 
+	preempt_disable();
 	pagefault_disable();
 	if (!PageHighMem(page))
 		return page_address(page);
@@ -79,6 +80,7 @@ void __kunmap_atomic(void *kvaddr)
 	}
 
 	pagefault_enable();
+	preempt_enable();
 }
 EXPORT_SYMBOL(__kunmap_atomic);
 
diff --git a/block/blk-mq-cpumap.c b/block/blk-mq-cpumap.c
index 5f13f4d0bcce..1e28ddb656b8 100644
--- a/block/blk-mq-cpumap.c
+++ b/block/blk-mq-cpumap.c
@@ -24,7 +24,7 @@ static int get_first_sibling(unsigned int cpu)
 {
 	unsigned int ret;
 
-	ret = cpumask_first(topology_thread_cpumask(cpu));
+	ret = cpumask_first(topology_sibling_cpumask(cpu));
 	if (ret < nr_cpu_ids)
 		return ret;
 
diff --git a/crypto/842.c b/crypto/842.c
index b48f4f108c47..98e387efb8c8 100644
--- a/crypto/842.c
+++ b/crypto/842.c
@@ -1,5 +1,5 @@
 /*
- * Cryptographic API for the 842 compression algorithm.
+ * Cryptographic API for the 842 software compression algorithm.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -11,173 +11,73 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ * Copyright (C) IBM Corporation, 2011-2015
  *
- * Copyright (C) IBM Corporation, 2011
+ * Original Authors: Robert Jennings <rcj@linux.vnet.ibm.com>
+ *                   Seth Jennings <sjenning@linux.vnet.ibm.com>
  *
- * Authors: Robert Jennings <rcj@linux.vnet.ibm.com>
- *          Seth Jennings <sjenning@linux.vnet.ibm.com>
+ * Rewrite: Dan Streetman <ddstreet@ieee.org>
+ *
+ * This is the software implementation of compression and decompression using
+ * the 842 format.  This uses the software 842 library at lib/842/ which is
+ * only a reference implementation, and is very, very slow as compared to other
+ * software compressors.  You probably do not want to use this software
+ * compression.  If you have access to the PowerPC 842 compression hardware, you
+ * want to use the 842 hardware compression interface, which is at:
+ * drivers/crypto/nx/nx-842-crypto.c
  */
 
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/crypto.h>
-#include <linux/vmalloc.h>
-#include <linux/nx842.h>
-#include <linux/lzo.h>
-#include <linux/timer.h>
-
-static int nx842_uselzo;
-
-struct nx842_ctx {
-	void *nx842_wmem; /* working memory for 842/lzo */
-};
+#include <linux/sw842.h>
 
-enum nx842_crypto_type {
-	NX842_CRYPTO_TYPE_842,
-	NX842_CRYPTO_TYPE_LZO
+struct crypto842_ctx {
+	char wmem[SW842_MEM_COMPRESS];	/* working memory for compress */
 };
 
-#define NX842_SENTINEL 0xdeadbeef
-
-struct nx842_crypto_header {
-	unsigned int sentinel; /* debug */
-	enum nx842_crypto_type type;
-};
-
-static int nx842_init(struct crypto_tfm *tfm)
-{
-	struct nx842_ctx *ctx = crypto_tfm_ctx(tfm);
-	int wmemsize;
-
-	wmemsize = max_t(int, nx842_get_workmem_size(), LZO1X_MEM_COMPRESS);
-	ctx->nx842_wmem = kmalloc(wmemsize, GFP_NOFS);
-	if (!ctx->nx842_wmem)
-		return -ENOMEM;
-
-	return 0;
-}
-
-static void nx842_exit(struct crypto_tfm *tfm)
-{
-	struct nx842_ctx *ctx = crypto_tfm_ctx(tfm);
-
-	kfree(ctx->nx842_wmem);
-}
-
-static void nx842_reset_uselzo(unsigned long data)
+static int crypto842_compress(struct crypto_tfm *tfm,
+			      const u8 *src, unsigned int slen,
+			      u8 *dst, unsigned int *dlen)
 {
-	nx842_uselzo = 0;
-}
-
-static DEFINE_TIMER(failover_timer, nx842_reset_uselzo, 0, 0);
-
-static int nx842_crypto_compress(struct crypto_tfm *tfm, const u8 *src,
-			    unsigned int slen, u8 *dst, unsigned int *dlen)
-{
-	struct nx842_ctx *ctx = crypto_tfm_ctx(tfm);
-	struct nx842_crypto_header *hdr;
-	unsigned int tmp_len = *dlen;
-	size_t lzodlen; /* needed for lzo */
-	int err;
-
-	*dlen = 0;
-	hdr = (struct nx842_crypto_header *)dst;
-	hdr->sentinel = NX842_SENTINEL; /* debug */
-	dst += sizeof(struct nx842_crypto_header);
-	tmp_len -= sizeof(struct nx842_crypto_header);
-	lzodlen = tmp_len;
-
-	if (likely(!nx842_uselzo)) {
-		err = nx842_compress(src, slen, dst, &tmp_len, ctx->nx842_wmem);
-
-		if (likely(!err)) {
-			hdr->type = NX842_CRYPTO_TYPE_842;
-			*dlen = tmp_len + sizeof(struct nx842_crypto_header);
-			return 0;
-		}
-
-		/* hardware failed */
-		nx842_uselzo = 1;
+	struct crypto842_ctx *ctx = crypto_tfm_ctx(tfm);
 
-		/* set timer to check for hardware again in 1 second */
-		mod_timer(&failover_timer, jiffies + msecs_to_jiffies(1000));
-	}
-
-	/* no hardware, use lzo */
-	err = lzo1x_1_compress(src, slen, dst, &lzodlen, ctx->nx842_wmem);
-	if (err != LZO_E_OK)
-		return -EINVAL;
-
-	hdr->type = NX842_CRYPTO_TYPE_LZO;
-	*dlen = lzodlen + sizeof(struct nx842_crypto_header);
-	return 0;
+	return sw842_compress(src, slen, dst, dlen, ctx->wmem);
 }
 
-static int nx842_crypto_decompress(struct crypto_tfm *tfm, const u8 *src,
-			      unsigned int slen, u8 *dst, unsigned int *dlen)
+static int crypto842_decompress(struct crypto_tfm *tfm,
+				const u8 *src, unsigned int slen,
+				u8 *dst, unsigned int *dlen)
 {
-	struct nx842_ctx *ctx = crypto_tfm_ctx(tfm);
-	struct nx842_crypto_header *hdr;
-	unsigned int tmp_len = *dlen;
-	size_t lzodlen; /* needed for lzo */
-	int err;
-
-	*dlen = 0;
-	hdr = (struct nx842_crypto_header *)src;
-
-	if (unlikely(hdr->sentinel != NX842_SENTINEL))
-		return -EINVAL;
-
-	src += sizeof(struct nx842_crypto_header);
-	slen -= sizeof(struct nx842_crypto_header);
-
-	if (likely(hdr->type == NX842_CRYPTO_TYPE_842)) {
-		err = nx842_decompress(src, slen, dst, &tmp_len,
-			ctx->nx842_wmem);
-		if (err)
-			return -EINVAL;
-		*dlen = tmp_len;
-	} else if (hdr->type == NX842_CRYPTO_TYPE_LZO) {
-		lzodlen = tmp_len;
-		err = lzo1x_decompress_safe(src, slen, dst, &lzodlen);
-		if (err != LZO_E_OK)
-			return -EINVAL;
-		*dlen = lzodlen;
-	} else
-		return -EINVAL;
-
-	return 0;
+	return sw842_decompress(src, slen, dst, dlen);
 }
 
 static struct crypto_alg alg = {
 	.cra_name		= "842",
+	.cra_driver_name	= "842-generic",
+	.cra_priority		= 100,
 	.cra_flags		= CRYPTO_ALG_TYPE_COMPRESS,
-	.cra_ctxsize		= sizeof(struct nx842_ctx),
+	.cra_ctxsize		= sizeof(struct crypto842_ctx),
 	.cra_module		= THIS_MODULE,
-	.cra_init		= nx842_init,
-	.cra_exit		= nx842_exit,
 	.cra_u			= { .compress = {
-	.coa_compress		= nx842_crypto_compress,
-	.coa_decompress		= nx842_crypto_decompress } }
+	.coa_compress		= crypto842_compress,
+	.coa_decompress		= crypto842_decompress } }
 };
 
-static int __init nx842_mod_init(void)
+static int __init crypto842_mod_init(void)
 {
-	del_timer(&failover_timer);
 	return crypto_register_alg(&alg);
 }
+module_init(crypto842_mod_init);
 
-static void __exit nx842_mod_exit(void)
+static void __exit crypto842_mod_exit(void)
 {
 	crypto_unregister_alg(&alg);
 }
-
-module_init(nx842_mod_init);
-module_exit(nx842_mod_exit);
+module_exit(crypto842_mod_exit);
 
 MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("842 Compression Algorithm");
+MODULE_DESCRIPTION("842 Software Compression Algorithm");
 MODULE_ALIAS_CRYPTO("842");
+MODULE_ALIAS_CRYPTO("842-generic");
+MODULE_AUTHOR("Dan Streetman <ddstreet@ieee.org>");
diff --git a/crypto/Kconfig b/crypto/Kconfig
index 362905e7c841..b4cfc5754033 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -78,6 +78,10 @@ config CRYPTO_RNG2
 	tristate
 	select CRYPTO_ALGAPI2
 
+config CRYPTO_RNG_DEFAULT
+	tristate
+	select CRYPTO_DRBG_MENU
+
 config CRYPTO_PCOMP
 	tristate
 	select CRYPTO_PCOMP2
@@ -87,6 +91,23 @@ config CRYPTO_PCOMP2
 	tristate
 	select CRYPTO_ALGAPI2
 
+config CRYPTO_AKCIPHER2
+	tristate
+	select CRYPTO_ALGAPI2
+
+config CRYPTO_AKCIPHER
+	tristate
+	select CRYPTO_AKCIPHER2
+	select CRYPTO_ALGAPI
+
+config CRYPTO_RSA
+	tristate "RSA algorithm"
+	select CRYPTO_AKCIPHER
+	select MPILIB
+	select ASN1
+	help
+	  Generic implementation of the RSA public key algorithm.
+
 config CRYPTO_MANAGER
 	tristate "Cryptographic algorithm manager"
 	select CRYPTO_MANAGER2
@@ -100,6 +121,7 @@ config CRYPTO_MANAGER2
 	select CRYPTO_HASH2
 	select CRYPTO_BLKCIPHER2
 	select CRYPTO_PCOMP2
+	select CRYPTO_AKCIPHER2
 
 config CRYPTO_USER
 	tristate "Userspace cryptographic algorithm configuration"
@@ -217,15 +239,39 @@ config CRYPTO_GCM
 	  Support for Galois/Counter Mode (GCM) and Galois Message
 	  Authentication Code (GMAC). Required for IPSec.
 
+config CRYPTO_CHACHA20POLY1305
+	tristate "ChaCha20-Poly1305 AEAD support"
+	select CRYPTO_CHACHA20
+	select CRYPTO_POLY1305
+	select CRYPTO_AEAD
+	help
+	  ChaCha20-Poly1305 AEAD support, RFC7539.
+
+	  Support for the AEAD wrapper using the ChaCha20 stream cipher combined
+	  with the Poly1305 authenticator. It is defined in RFC7539 for use in
+	  IETF protocols.
+
 config CRYPTO_SEQIV
 	tristate "Sequence Number IV Generator"
 	select CRYPTO_AEAD
 	select CRYPTO_BLKCIPHER
-	select CRYPTO_RNG
+	select CRYPTO_NULL
+	select CRYPTO_RNG_DEFAULT
 	help
 	  This IV generator generates an IV based on a sequence number by
 	  xoring it with a salt.  This algorithm is mainly useful for CTR
 
+config CRYPTO_ECHAINIV
+	tristate "Encrypted Chain IV Generator"
+	select CRYPTO_AEAD
+	select CRYPTO_NULL
+	select CRYPTO_RNG_DEFAULT
+	default m
+	help
+	  This IV generator generates an IV based on the encryption of
+	  a sequence number xored with a salt.  This is the default
+	  algorithm for CBC.
+
 comment "Block modes"
 
 config CRYPTO_CBC
@@ -415,6 +461,15 @@ config CRYPTO_GHASH
 	help
 	  GHASH is message digest algorithm for GCM (Galois/Counter Mode).
 
+config CRYPTO_POLY1305
+	tristate "Poly1305 authenticator algorithm"
+	help
+	  Poly1305 authenticator algorithm, RFC7539.
+
+	  Poly1305 is an authenticator algorithm designed by Daniel J. Bernstein.
+	  It is used for the ChaCha20-Poly1305 AEAD, specified in RFC7539 for use
+	  in IETF protocols. This is the portable C implementation of Poly1305.
+
 config CRYPTO_MD4
 	tristate "MD4 digest algorithm"
 	select CRYPTO_HASH
@@ -1145,6 +1200,19 @@ config CRYPTO_SALSA20_X86_64
 	  The Salsa20 stream cipher algorithm is designed by Daniel J.
 	  Bernstein <djb@cr.yp.to>. See <http://cr.yp.to/snuffle.html>
 
+config CRYPTO_CHACHA20
+	tristate "ChaCha20 cipher algorithm"
+	select CRYPTO_BLKCIPHER
+	help
+	  ChaCha20 cipher algorithm, RFC7539.
+
+	  ChaCha20 is a 256-bit high-speed stream cipher designed by Daniel J.
+	  Bernstein and further specified in RFC7539 for use in IETF protocols.
+	  This is the portable C implementation of ChaCha20.
+
+	  See also:
+	  <http://cr.yp.to/chacha/chacha-20080128.pdf>
+
 config CRYPTO_SEED
 	tristate "SEED cipher algorithm"
 	select CRYPTO_ALGAPI
@@ -1412,10 +1480,9 @@ config CRYPTO_LZO
 
 config CRYPTO_842
 	tristate "842 compression algorithm"
-	depends on CRYPTO_DEV_NX_COMPRESS
-	# 842 uses lzo if the hardware becomes unavailable
-	select LZO_COMPRESS
-	select LZO_DECOMPRESS
+	select CRYPTO_ALGAPI
+	select 842_COMPRESS
+	select 842_DECOMPRESS
 	help
 	  This is the 842 algorithm.
 
@@ -1439,7 +1506,6 @@ comment "Random Number Generation"
 
 config CRYPTO_ANSI_CPRNG
 	tristate "Pseudo Random Number Generation for Cryptographic modules"
-	default m
 	select CRYPTO_AES
 	select CRYPTO_RNG
 	help
@@ -1457,15 +1523,14 @@ menuconfig CRYPTO_DRBG_MENU
 if CRYPTO_DRBG_MENU
 
 config CRYPTO_DRBG_HMAC
-	bool "Enable HMAC DRBG"
+	bool
 	default y
 	select CRYPTO_HMAC
-	help
-	  Enable the HMAC DRBG variant as defined in NIST SP800-90A.
+	select CRYPTO_SHA256
 
 config CRYPTO_DRBG_HASH
 	bool "Enable Hash DRBG"
-	select CRYPTO_HASH
+	select CRYPTO_SHA256
 	help
 	  Enable the Hash DRBG variant as defined in NIST SP800-90A.
 
@@ -1477,11 +1542,21 @@ config CRYPTO_DRBG_CTR
 
 config CRYPTO_DRBG
 	tristate
-	default CRYPTO_DRBG_MENU if (CRYPTO_DRBG_HMAC || CRYPTO_DRBG_HASH || CRYPTO_DRBG_CTR)
+	default CRYPTO_DRBG_MENU
 	select CRYPTO_RNG
+	select CRYPTO_JITTERENTROPY
 
 endif	# if CRYPTO_DRBG_MENU
 
+config CRYPTO_JITTERENTROPY
+	tristate "Jitterentropy Non-Deterministic Random Number Generator"
+	help
+	  The Jitterentropy RNG is a noise that is intended
+	  to provide seed to another RNG. The RNG does not
+	  perform any cryptographic whitening of the generated
+	  random numbers. This Jitterentropy RNG registers with
+	  the kernel crypto API and can be used by any caller.
+
 config CRYPTO_USER_API
 	tristate
 
@@ -1512,6 +1587,15 @@ config CRYPTO_USER_API_RNG
 	  This option enables the user-spaces interface for random
 	  number generator algorithms.
 
+config CRYPTO_USER_API_AEAD
+	tristate "User-space interface for AEAD cipher algorithms"
+	depends on NET
+	select CRYPTO_AEAD
+	select CRYPTO_USER_API
+	help
+	  This option enables the user-spaces interface for AEAD
+	  cipher algorithms.
+
 config CRYPTO_HASH_INFO
 	bool
 
diff --git a/crypto/Makefile b/crypto/Makefile
index 97b7d3ac87e7..0077476f5024 100644
--- a/crypto/Makefile
+++ b/crypto/Makefile
@@ -21,12 +21,22 @@ obj-$(CONFIG_CRYPTO_BLKCIPHER2) += crypto_blkcipher.o
 obj-$(CONFIG_CRYPTO_BLKCIPHER2) += chainiv.o
 obj-$(CONFIG_CRYPTO_BLKCIPHER2) += eseqiv.o
 obj-$(CONFIG_CRYPTO_SEQIV) += seqiv.o
+obj-$(CONFIG_CRYPTO_ECHAINIV) += echainiv.o
 
 crypto_hash-y += ahash.o
 crypto_hash-y += shash.o
 obj-$(CONFIG_CRYPTO_HASH2) += crypto_hash.o
 
 obj-$(CONFIG_CRYPTO_PCOMP2) += pcompress.o
+obj-$(CONFIG_CRYPTO_AKCIPHER2) += akcipher.o
+
+$(obj)/rsakey-asn1.o: $(obj)/rsakey-asn1.c $(obj)/rsakey-asn1.h
+clean-files += rsakey-asn1.c rsakey-asn1.h
+
+rsa_generic-y := rsakey-asn1.o
+rsa_generic-y += rsa.o
+rsa_generic-y += rsa_helper.o
+obj-$(CONFIG_CRYPTO_RSA) += rsa_generic.o
 
 cryptomgr-y := algboss.o testmgr.o
 
@@ -58,6 +68,7 @@ obj-$(CONFIG_CRYPTO_XTS) += xts.o
 obj-$(CONFIG_CRYPTO_CTR) += ctr.o
 obj-$(CONFIG_CRYPTO_GCM) += gcm.o
 obj-$(CONFIG_CRYPTO_CCM) += ccm.o
+obj-$(CONFIG_CRYPTO_CHACHA20POLY1305) += chacha20poly1305.o
 obj-$(CONFIG_CRYPTO_PCRYPT) += pcrypt.o
 obj-$(CONFIG_CRYPTO_CRYPTD) += cryptd.o
 obj-$(CONFIG_CRYPTO_MCRYPTD) += mcryptd.o
@@ -79,6 +90,8 @@ obj-$(CONFIG_CRYPTO_KHAZAD) += khazad.o
 obj-$(CONFIG_CRYPTO_ANUBIS) += anubis.o
 obj-$(CONFIG_CRYPTO_SEED) += seed.o
 obj-$(CONFIG_CRYPTO_SALSA20) += salsa20_generic.o
+obj-$(CONFIG_CRYPTO_CHACHA20) += chacha20_generic.o
+obj-$(CONFIG_CRYPTO_POLY1305) += poly1305_generic.o
 obj-$(CONFIG_CRYPTO_DEFLATE) += deflate.o
 obj-$(CONFIG_CRYPTO_ZLIB) += zlib.o
 obj-$(CONFIG_CRYPTO_MICHAEL_MIC) += michael_mic.o
@@ -91,9 +104,9 @@ obj-$(CONFIG_CRYPTO_LZ4) += lz4.o
 obj-$(CONFIG_CRYPTO_LZ4HC) += lz4hc.o
 obj-$(CONFIG_CRYPTO_842) += 842.o
 obj-$(CONFIG_CRYPTO_RNG2) += rng.o
-obj-$(CONFIG_CRYPTO_RNG2) += krng.o
 obj-$(CONFIG_CRYPTO_ANSI_CPRNG) += ansi_cprng.o
 obj-$(CONFIG_CRYPTO_DRBG) += drbg.o
+obj-$(CONFIG_CRYPTO_JITTERENTROPY) += jitterentropy.o
 obj-$(CONFIG_CRYPTO_TEST) += tcrypt.o
 obj-$(CONFIG_CRYPTO_GHASH) += ghash-generic.o
 obj-$(CONFIG_CRYPTO_USER_API) += af_alg.o
diff --git a/crypto/ablkcipher.c b/crypto/ablkcipher.c
index db201bca1581..b788f169cc98 100644
--- a/crypto/ablkcipher.c
+++ b/crypto/ablkcipher.c
@@ -454,7 +454,7 @@ static int crypto_init_givcipher_ops(struct crypto_tfm *tfm, u32 type,
 		      alg->setkey : setkey;
 	crt->encrypt = alg->encrypt;
 	crt->decrypt = alg->decrypt;
-	crt->givencrypt = alg->givencrypt;
+	crt->givencrypt = alg->givencrypt ?: no_givdecrypt;
 	crt->givdecrypt = alg->givdecrypt ?: no_givdecrypt;
 	crt->base = __crypto_ablkcipher_cast(tfm);
 	crt->ivsize = alg->ivsize;
@@ -586,6 +586,13 @@ static int crypto_givcipher_default(struct crypto_alg *alg, u32 type, u32 mask)
 	if (!tmpl)
 		goto kill_larval;
 
+	if (tmpl->create) {
+		err = tmpl->create(tmpl, tb);
+		if (err)
+			goto put_tmpl;
+		goto ok;
+	}
+
 	inst = tmpl->alloc(tb);
 	err = PTR_ERR(inst);
 	if (IS_ERR(inst))
@@ -597,6 +604,7 @@ static int crypto_givcipher_default(struct crypto_alg *alg, u32 type, u32 mask)
 		goto put_tmpl;
 	}
 
+ok:
 	/* Redo the lookup to use the instance we just registered. */
 	err = -EAGAIN;
 
@@ -636,7 +644,7 @@ struct crypto_alg *crypto_lookup_skcipher(const char *name, u32 type, u32 mask)
 
 	if ((alg->cra_flags & CRYPTO_ALG_TYPE_MASK) ==
 	    CRYPTO_ALG_TYPE_GIVCIPHER) {
-		if ((alg->cra_flags ^ type ^ ~mask) & CRYPTO_ALG_TESTED) {
+		if (~alg->cra_flags & (type ^ ~mask) & CRYPTO_ALG_TESTED) {
 			crypto_mod_put(alg);
 			alg = ERR_PTR(-ENOENT);
 		}
diff --git a/crypto/aead.c b/crypto/aead.c
index 222271070b49..07bf99773548 100644
--- a/crypto/aead.c
+++ b/crypto/aead.c
@@ -12,7 +12,8 @@
  *
  */
 
-#include <crypto/internal/aead.h>
+#include <crypto/internal/geniv.h>
+#include <crypto/scatterwalk.h>
 #include <linux/err.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
@@ -26,10 +27,20 @@
 
 #include "internal.h"
 
+struct compat_request_ctx {
+	struct scatterlist src[2];
+	struct scatterlist dst[2];
+	struct scatterlist ivbuf[2];
+	struct scatterlist *ivsg;
+	struct aead_givcrypt_request subreq;
+};
+
+static int aead_null_givencrypt(struct aead_givcrypt_request *req);
+static int aead_null_givdecrypt(struct aead_givcrypt_request *req);
+
 static int setkey_unaligned(struct crypto_aead *tfm, const u8 *key,
 			    unsigned int keylen)
 {
-	struct aead_alg *aead = crypto_aead_alg(tfm);
 	unsigned long alignmask = crypto_aead_alignmask(tfm);
 	int ret;
 	u8 *buffer, *alignbuffer;
@@ -42,47 +53,95 @@ static int setkey_unaligned(struct crypto_aead *tfm, const u8 *key,
 
 	alignbuffer = (u8 *)ALIGN((unsigned long)buffer, alignmask + 1);
 	memcpy(alignbuffer, key, keylen);
-	ret = aead->setkey(tfm, alignbuffer, keylen);
+	ret = tfm->setkey(tfm, alignbuffer, keylen);
 	memset(alignbuffer, 0, keylen);
 	kfree(buffer);
 	return ret;
 }
 
-static int setkey(struct crypto_aead *tfm, const u8 *key, unsigned int keylen)
+int crypto_aead_setkey(struct crypto_aead *tfm,
+		       const u8 *key, unsigned int keylen)
 {
-	struct aead_alg *aead = crypto_aead_alg(tfm);
 	unsigned long alignmask = crypto_aead_alignmask(tfm);
 
+	tfm = tfm->child;
+
 	if ((unsigned long)key & alignmask)
 		return setkey_unaligned(tfm, key, keylen);
 
-	return aead->setkey(tfm, key, keylen);
+	return tfm->setkey(tfm, key, keylen);
 }
+EXPORT_SYMBOL_GPL(crypto_aead_setkey);
 
 int crypto_aead_setauthsize(struct crypto_aead *tfm, unsigned int authsize)
 {
-	struct aead_tfm *crt = crypto_aead_crt(tfm);
 	int err;
 
-	if (authsize > crypto_aead_alg(tfm)->maxauthsize)
+	if (authsize > crypto_aead_maxauthsize(tfm))
 		return -EINVAL;
 
-	if (crypto_aead_alg(tfm)->setauthsize) {
-		err = crypto_aead_alg(tfm)->setauthsize(crt->base, authsize);
+	if (tfm->setauthsize) {
+		err = tfm->setauthsize(tfm->child, authsize);
 		if (err)
 			return err;
 	}
 
-	crypto_aead_crt(crt->base)->authsize = authsize;
-	crt->authsize = authsize;
+	tfm->child->authsize = authsize;
+	tfm->authsize = authsize;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(crypto_aead_setauthsize);
 
-static unsigned int crypto_aead_ctxsize(struct crypto_alg *alg, u32 type,
-					u32 mask)
+struct aead_old_request {
+	struct scatterlist srcbuf[2];
+	struct scatterlist dstbuf[2];
+	struct aead_request subreq;
+};
+
+unsigned int crypto_aead_reqsize(struct crypto_aead *tfm)
 {
-	return alg->cra_ctxsize;
+	return tfm->reqsize + sizeof(struct aead_old_request);
+}
+EXPORT_SYMBOL_GPL(crypto_aead_reqsize);
+
+static int old_crypt(struct aead_request *req,
+		     int (*crypt)(struct aead_request *req))
+{
+	struct aead_old_request *nreq = aead_request_ctx(req);
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct scatterlist *src, *dst;
+
+	if (req->old)
+		return crypt(req);
+
+	src = scatterwalk_ffwd(nreq->srcbuf, req->src, req->assoclen);
+	dst = req->src == req->dst ?
+	      src : scatterwalk_ffwd(nreq->dstbuf, req->dst, req->assoclen);
+
+	aead_request_set_tfm(&nreq->subreq, aead);
+	aead_request_set_callback(&nreq->subreq, aead_request_flags(req),
+				  req->base.complete, req->base.data);
+	aead_request_set_crypt(&nreq->subreq, src, dst, req->cryptlen,
+			       req->iv);
+	aead_request_set_assoc(&nreq->subreq, req->src, req->assoclen);
+
+	return crypt(&nreq->subreq);
+}
+
+static int old_encrypt(struct aead_request *req)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct old_aead_alg *alg = crypto_old_aead_alg(aead);
+
+	return old_crypt(req, alg->encrypt);
+}
+
+static int old_decrypt(struct aead_request *req)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct old_aead_alg *alg = crypto_old_aead_alg(aead);
+
+	return old_crypt(req, alg->decrypt);
 }
 
 static int no_givcrypt(struct aead_givcrypt_request *req)
@@ -90,32 +149,68 @@ static int no_givcrypt(struct aead_givcrypt_request *req)
 	return -ENOSYS;
 }
 
-static int crypto_init_aead_ops(struct crypto_tfm *tfm, u32 type, u32 mask)
+static int crypto_old_aead_init_tfm(struct crypto_tfm *tfm)
 {
-	struct aead_alg *alg = &tfm->__crt_alg->cra_aead;
-	struct aead_tfm *crt = &tfm->crt_aead;
+	struct old_aead_alg *alg = &tfm->__crt_alg->cra_aead;
+	struct crypto_aead *crt = __crypto_aead_cast(tfm);
 
 	if (max(alg->maxauthsize, alg->ivsize) > PAGE_SIZE / 8)
 		return -EINVAL;
 
-	crt->setkey = tfm->__crt_alg->cra_flags & CRYPTO_ALG_GENIV ?
-		      alg->setkey : setkey;
-	crt->encrypt = alg->encrypt;
-	crt->decrypt = alg->decrypt;
-	crt->givencrypt = alg->givencrypt ?: no_givcrypt;
-	crt->givdecrypt = alg->givdecrypt ?: no_givcrypt;
-	crt->base = __crypto_aead_cast(tfm);
-	crt->ivsize = alg->ivsize;
+	crt->setkey = alg->setkey;
+	crt->setauthsize = alg->setauthsize;
+	crt->encrypt = old_encrypt;
+	crt->decrypt = old_decrypt;
+	if (alg->ivsize) {
+		crt->givencrypt = alg->givencrypt ?: no_givcrypt;
+		crt->givdecrypt = alg->givdecrypt ?: no_givcrypt;
+	} else {
+		crt->givencrypt = aead_null_givencrypt;
+		crt->givdecrypt = aead_null_givdecrypt;
+	}
+	crt->child = __crypto_aead_cast(tfm);
 	crt->authsize = alg->maxauthsize;
 
 	return 0;
 }
 
+static void crypto_aead_exit_tfm(struct crypto_tfm *tfm)
+{
+	struct crypto_aead *aead = __crypto_aead_cast(tfm);
+	struct aead_alg *alg = crypto_aead_alg(aead);
+
+	alg->exit(aead);
+}
+
+static int crypto_aead_init_tfm(struct crypto_tfm *tfm)
+{
+	struct crypto_aead *aead = __crypto_aead_cast(tfm);
+	struct aead_alg *alg = crypto_aead_alg(aead);
+
+	if (crypto_old_aead_alg(aead)->encrypt)
+		return crypto_old_aead_init_tfm(tfm);
+
+	aead->setkey = alg->setkey;
+	aead->setauthsize = alg->setauthsize;
+	aead->encrypt = alg->encrypt;
+	aead->decrypt = alg->decrypt;
+	aead->child = __crypto_aead_cast(tfm);
+	aead->authsize = alg->maxauthsize;
+
+	if (alg->exit)
+		aead->base.exit = crypto_aead_exit_tfm;
+
+	if (alg->init)
+		return alg->init(aead);
+
+	return 0;
+}
+
 #ifdef CONFIG_NET
-static int crypto_aead_report(struct sk_buff *skb, struct crypto_alg *alg)
+static int crypto_old_aead_report(struct sk_buff *skb, struct crypto_alg *alg)
 {
 	struct crypto_report_aead raead;
-	struct aead_alg *aead = &alg->cra_aead;
+	struct old_aead_alg *aead = &alg->cra_aead;
 
 	strncpy(raead.type, "aead", sizeof(raead.type));
 	strncpy(raead.geniv, aead->geniv ?: "<built-in>", sizeof(raead.geniv));
@@ -133,6 +228,64 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 #else
+static int crypto_old_aead_report(struct sk_buff *skb, struct crypto_alg *alg)
+{
+	return -ENOSYS;
+}
+#endif
+
+static void crypto_old_aead_show(struct seq_file *m, struct crypto_alg *alg)
+	__attribute__ ((unused));
+static void crypto_old_aead_show(struct seq_file *m, struct crypto_alg *alg)
+{
+	struct old_aead_alg *aead = &alg->cra_aead;
+
+	seq_printf(m, "type         : aead\n");
+	seq_printf(m, "async        : %s\n", alg->cra_flags & CRYPTO_ALG_ASYNC ?
+					     "yes" : "no");
+	seq_printf(m, "blocksize    : %u\n", alg->cra_blocksize);
+	seq_printf(m, "ivsize       : %u\n", aead->ivsize);
+	seq_printf(m, "maxauthsize  : %u\n", aead->maxauthsize);
+	seq_printf(m, "geniv        : %s\n", aead->geniv ?: "<built-in>");
+}
+
+const struct crypto_type crypto_aead_type = {
+	.extsize = crypto_alg_extsize,
+	.init_tfm = crypto_aead_init_tfm,
+#ifdef CONFIG_PROC_FS
+	.show = crypto_old_aead_show,
+#endif
+	.report = crypto_old_aead_report,
+	.lookup = crypto_lookup_aead,
+	.maskclear = ~(CRYPTO_ALG_TYPE_MASK | CRYPTO_ALG_GENIV),
+	.maskset = CRYPTO_ALG_TYPE_MASK,
+	.type = CRYPTO_ALG_TYPE_AEAD,
+	.tfmsize = offsetof(struct crypto_aead, base),
+};
+EXPORT_SYMBOL_GPL(crypto_aead_type);
+
+#ifdef CONFIG_NET
+static int crypto_aead_report(struct sk_buff *skb, struct crypto_alg *alg)
+{
+	struct crypto_report_aead raead;
+	struct aead_alg *aead = container_of(alg, struct aead_alg, base);
+
+	strncpy(raead.type, "aead", sizeof(raead.type));
+	strncpy(raead.geniv, "<none>", sizeof(raead.geniv));
+
+	raead.blocksize = alg->cra_blocksize;
+	raead.maxauthsize = aead->maxauthsize;
+	raead.ivsize = aead->ivsize;
+
+	if (nla_put(skb, CRYPTOCFGA_REPORT_AEAD,
+		    sizeof(struct crypto_report_aead), &raead))
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -EMSGSIZE;
+}
+#else
 static int crypto_aead_report(struct sk_buff *skb, struct crypto_alg *alg)
 {
 	return -ENOSYS;
@@ -143,7 +296,7 @@ static void crypto_aead_show(struct seq_file *m, struct crypto_alg *alg)
 	__attribute__ ((unused));
 static void crypto_aead_show(struct seq_file *m, struct crypto_alg *alg)
 {
-	struct aead_alg *aead = &alg->cra_aead;
+	struct aead_alg *aead = container_of(alg, struct aead_alg, base);
 
 	seq_printf(m, "type         : aead\n");
 	seq_printf(m, "async        : %s\n", alg->cra_flags & CRYPTO_ALG_ASYNC ?
@@ -151,18 +304,21 @@ static void crypto_aead_show(struct seq_file *m, struct crypto_alg *alg)
 	seq_printf(m, "blocksize    : %u\n", alg->cra_blocksize);
 	seq_printf(m, "ivsize       : %u\n", aead->ivsize);
 	seq_printf(m, "maxauthsize  : %u\n", aead->maxauthsize);
-	seq_printf(m, "geniv        : %s\n", aead->geniv ?: "<built-in>");
+	seq_printf(m, "geniv        : <none>\n");
 }
 
-const struct crypto_type crypto_aead_type = {
-	.ctxsize = crypto_aead_ctxsize,
-	.init = crypto_init_aead_ops,
+static const struct crypto_type crypto_new_aead_type = {
+	.extsize = crypto_alg_extsize,
+	.init_tfm = crypto_aead_init_tfm,
 #ifdef CONFIG_PROC_FS
 	.show = crypto_aead_show,
 #endif
 	.report = crypto_aead_report,
+	.maskclear = ~CRYPTO_ALG_TYPE_MASK,
+	.maskset = CRYPTO_ALG_TYPE_MASK,
+	.type = CRYPTO_ALG_TYPE_AEAD,
+	.tfmsize = offsetof(struct crypto_aead, base),
 };
-EXPORT_SYMBOL_GPL(crypto_aead_type);
 
 static int aead_null_givencrypt(struct aead_givcrypt_request *req)
 {
@@ -174,33 +330,11 @@ static int aead_null_givdecrypt(struct aead_givcrypt_request *req)
 	return crypto_aead_decrypt(&req->areq);
 }
 
-static int crypto_init_nivaead_ops(struct crypto_tfm *tfm, u32 type, u32 mask)
-{
-	struct aead_alg *alg = &tfm->__crt_alg->cra_aead;
-	struct aead_tfm *crt = &tfm->crt_aead;
-
-	if (max(alg->maxauthsize, alg->ivsize) > PAGE_SIZE / 8)
-		return -EINVAL;
-
-	crt->setkey = setkey;
-	crt->encrypt = alg->encrypt;
-	crt->decrypt = alg->decrypt;
-	if (!alg->ivsize) {
-		crt->givencrypt = aead_null_givencrypt;
-		crt->givdecrypt = aead_null_givdecrypt;
-	}
-	crt->base = __crypto_aead_cast(tfm);
-	crt->ivsize = alg->ivsize;
-	crt->authsize = alg->maxauthsize;
-
-	return 0;
-}
-
 #ifdef CONFIG_NET
 static int crypto_nivaead_report(struct sk_buff *skb, struct crypto_alg *alg)
 {
 	struct crypto_report_aead raead;
-	struct aead_alg *aead = &alg->cra_aead;
+	struct old_aead_alg *aead = &alg->cra_aead;
 
 	strncpy(raead.type, "nivaead", sizeof(raead.type));
 	strncpy(raead.geniv, aead->geniv, sizeof(raead.geniv));
@@ -229,7 +363,7 @@ static void crypto_nivaead_show(struct seq_file *m, struct crypto_alg *alg)
 	__attribute__ ((unused));
 static void crypto_nivaead_show(struct seq_file *m, struct crypto_alg *alg)
 {
-	struct aead_alg *aead = &alg->cra_aead;
+	struct old_aead_alg *aead = &alg->cra_aead;
 
 	seq_printf(m, "type         : nivaead\n");
 	seq_printf(m, "async        : %s\n", alg->cra_flags & CRYPTO_ALG_ASYNC ?
@@ -241,43 +375,215 @@ static void crypto_nivaead_show(struct seq_file *m, struct crypto_alg *alg)
 }
 
 const struct crypto_type crypto_nivaead_type = {
-	.ctxsize = crypto_aead_ctxsize,
-	.init = crypto_init_nivaead_ops,
+	.extsize = crypto_alg_extsize,
+	.init_tfm = crypto_aead_init_tfm,
 #ifdef CONFIG_PROC_FS
 	.show = crypto_nivaead_show,
 #endif
 	.report = crypto_nivaead_report,
+	.maskclear = ~(CRYPTO_ALG_TYPE_MASK | CRYPTO_ALG_GENIV),
+	.maskset = CRYPTO_ALG_TYPE_MASK | CRYPTO_ALG_GENIV,
+	.type = CRYPTO_ALG_TYPE_AEAD,
+	.tfmsize = offsetof(struct crypto_aead, base),
 };
 EXPORT_SYMBOL_GPL(crypto_nivaead_type);
 
 static int crypto_grab_nivaead(struct crypto_aead_spawn *spawn,
 			       const char *name, u32 type, u32 mask)
 {
-	struct crypto_alg *alg;
+	spawn->base.frontend = &crypto_nivaead_type;
+	return crypto_grab_spawn(&spawn->base, name, type, mask);
+}
+
+static int aead_geniv_setkey(struct crypto_aead *tfm,
+			     const u8 *key, unsigned int keylen)
+{
+	struct aead_geniv_ctx *ctx = crypto_aead_ctx(tfm);
+
+	return crypto_aead_setkey(ctx->child, key, keylen);
+}
+
+static int aead_geniv_setauthsize(struct crypto_aead *tfm,
+				  unsigned int authsize)
+{
+	struct aead_geniv_ctx *ctx = crypto_aead_ctx(tfm);
+
+	return crypto_aead_setauthsize(ctx->child, authsize);
+}
+
+static void compat_encrypt_complete2(struct aead_request *req, int err)
+{
+	struct compat_request_ctx *rctx = aead_request_ctx(req);
+	struct aead_givcrypt_request *subreq = &rctx->subreq;
+	struct crypto_aead *geniv;
+
+	if (err == -EINPROGRESS)
+		return;
+
+	if (err)
+		goto out;
+
+	geniv = crypto_aead_reqtfm(req);
+	scatterwalk_map_and_copy(subreq->giv, rctx->ivsg, 0,
+				 crypto_aead_ivsize(geniv), 1);
+
+out:
+	kzfree(subreq->giv);
+}
+
+static void compat_encrypt_complete(struct crypto_async_request *base, int err)
+{
+	struct aead_request *req = base->data;
+
+	compat_encrypt_complete2(req, err);
+	aead_request_complete(req, err);
+}
+
+static int compat_encrypt(struct aead_request *req)
+{
+	struct crypto_aead *geniv = crypto_aead_reqtfm(req);
+	struct aead_geniv_ctx *ctx = crypto_aead_ctx(geniv);
+	struct compat_request_ctx *rctx = aead_request_ctx(req);
+	struct aead_givcrypt_request *subreq = &rctx->subreq;
+	unsigned int ivsize = crypto_aead_ivsize(geniv);
+	struct scatterlist *src, *dst;
+	crypto_completion_t compl;
+	void *data;
+	u8 *info;
+	__be64 seq;
 	int err;
 
-	type &= ~(CRYPTO_ALG_TYPE_MASK | CRYPTO_ALG_GENIV);
-	type |= CRYPTO_ALG_TYPE_AEAD;
-	mask |= CRYPTO_ALG_TYPE_MASK | CRYPTO_ALG_GENIV;
+	if (req->cryptlen < ivsize)
+		return -EINVAL;
 
-	alg = crypto_alg_mod_lookup(name, type, mask);
-	if (IS_ERR(alg))
-		return PTR_ERR(alg);
+	compl = req->base.complete;
+	data = req->base.data;
+
+	rctx->ivsg = scatterwalk_ffwd(rctx->ivbuf, req->dst, req->assoclen);
+	info = PageHighMem(sg_page(rctx->ivsg)) ? NULL : sg_virt(rctx->ivsg);
+
+	if (!info) {
+		info = kmalloc(ivsize, req->base.flags &
+				       CRYPTO_TFM_REQ_MAY_SLEEP ? GFP_KERNEL:
+								  GFP_ATOMIC);
+		if (!info)
+			return -ENOMEM;
+
+		compl = compat_encrypt_complete;
+		data = req;
+	}
+
+	memcpy(&seq, req->iv + ivsize - sizeof(seq), sizeof(seq));
+
+	src = scatterwalk_ffwd(rctx->src, req->src, req->assoclen + ivsize);
+	dst = req->src == req->dst ?
+	      src : scatterwalk_ffwd(rctx->dst, rctx->ivsg, ivsize);
+
+	aead_givcrypt_set_tfm(subreq, ctx->child);
+	aead_givcrypt_set_callback(subreq, req->base.flags,
+				   req->base.complete, req->base.data);
+	aead_givcrypt_set_crypt(subreq, src, dst,
+				req->cryptlen - ivsize, req->iv);
+	aead_givcrypt_set_assoc(subreq, req->src, req->assoclen);
+	aead_givcrypt_set_giv(subreq, info, be64_to_cpu(seq));
+
+	err = crypto_aead_givencrypt(subreq);
+	if (unlikely(PageHighMem(sg_page(rctx->ivsg))))
+		compat_encrypt_complete2(req, err);
+	return err;
+}
+
+static int compat_decrypt(struct aead_request *req)
+{
+	struct crypto_aead *geniv = crypto_aead_reqtfm(req);
+	struct aead_geniv_ctx *ctx = crypto_aead_ctx(geniv);
+	struct compat_request_ctx *rctx = aead_request_ctx(req);
+	struct aead_request *subreq = &rctx->subreq.areq;
+	unsigned int ivsize = crypto_aead_ivsize(geniv);
+	struct scatterlist *src, *dst;
+	crypto_completion_t compl;
+	void *data;
+
+	if (req->cryptlen < ivsize)
+		return -EINVAL;
+
+	aead_request_set_tfm(subreq, ctx->child);
+
+	compl = req->base.complete;
+	data = req->base.data;
+
+	src = scatterwalk_ffwd(rctx->src, req->src, req->assoclen + ivsize);
+	dst = req->src == req->dst ?
+	      src : scatterwalk_ffwd(rctx->dst, req->dst,
+				     req->assoclen + ivsize);
+
+	aead_request_set_callback(subreq, req->base.flags, compl, data);
+	aead_request_set_crypt(subreq, src, dst,
+			       req->cryptlen - ivsize, req->iv);
+	aead_request_set_assoc(subreq, req->src, req->assoclen);
+
+	scatterwalk_map_and_copy(req->iv, req->src, req->assoclen, ivsize, 0);
+
+	return crypto_aead_decrypt(subreq);
+}
+
+static int compat_encrypt_first(struct aead_request *req)
+{
+	struct crypto_aead *geniv = crypto_aead_reqtfm(req);
+	struct aead_geniv_ctx *ctx = crypto_aead_ctx(geniv);
+	int err = 0;
+
+	spin_lock_bh(&ctx->lock);
+	if (geniv->encrypt != compat_encrypt_first)
+		goto unlock;
+
+	geniv->encrypt = compat_encrypt;
+
+unlock:
+	spin_unlock_bh(&ctx->lock);
+
+	if (err)
+		return err;
+
+	return compat_encrypt(req);
+}
+
+static int aead_geniv_init_compat(struct crypto_tfm *tfm)
+{
+	struct crypto_aead *geniv = __crypto_aead_cast(tfm);
+	struct aead_geniv_ctx *ctx = crypto_aead_ctx(geniv);
+	int err;
+
+	spin_lock_init(&ctx->lock);
+
+	crypto_aead_set_reqsize(geniv, sizeof(struct compat_request_ctx));
+
+	err = aead_geniv_init(tfm);
+
+	ctx->child = geniv->child;
+	geniv->child = geniv;
 
-	err = crypto_init_spawn(&spawn->base, alg, spawn->base.inst, mask);
-	crypto_mod_put(alg);
 	return err;
 }
 
-struct crypto_instance *aead_geniv_alloc(struct crypto_template *tmpl,
-					 struct rtattr **tb, u32 type,
-					 u32 mask)
+static void aead_geniv_exit_compat(struct crypto_tfm *tfm)
+{
+	struct crypto_aead *geniv = __crypto_aead_cast(tfm);
+	struct aead_geniv_ctx *ctx = crypto_aead_ctx(geniv);
+
+	crypto_free_aead(ctx->child);
+}
+
+struct aead_instance *aead_geniv_alloc(struct crypto_template *tmpl,
+				       struct rtattr **tb, u32 type, u32 mask)
 {
 	const char *name;
 	struct crypto_aead_spawn *spawn;
 	struct crypto_attr_type *algt;
-	struct crypto_instance *inst;
-	struct crypto_alg *alg;
+	struct aead_instance *inst;
+	struct aead_alg *alg;
+	unsigned int ivsize;
+	unsigned int maxauthsize;
 	int err;
 
 	algt = crypto_get_attr_type(tb);
@@ -296,20 +602,25 @@ struct crypto_instance *aead_geniv_alloc(struct crypto_template *tmpl,
 	if (!inst)
 		return ERR_PTR(-ENOMEM);
 
-	spawn = crypto_instance_ctx(inst);
+	spawn = aead_instance_ctx(inst);
 
 	/* Ignore async algorithms if necessary. */
 	mask |= crypto_requires_sync(algt->type, algt->mask);
 
-	crypto_set_aead_spawn(spawn, inst);
-	err = crypto_grab_nivaead(spawn, name, type, mask);
+	crypto_set_aead_spawn(spawn, aead_crypto_instance(inst));
+	err = (algt->mask & CRYPTO_ALG_GENIV) ?
+	      crypto_grab_nivaead(spawn, name, type, mask) :
+	      crypto_grab_aead(spawn, name, type, mask);
 	if (err)
 		goto err_free_inst;
 
-	alg = crypto_aead_spawn_alg(spawn);
+	alg = crypto_spawn_aead_alg(spawn);
+
+	ivsize = crypto_aead_alg_ivsize(alg);
+	maxauthsize = crypto_aead_alg_maxauthsize(alg);
 
 	err = -EINVAL;
-	if (!alg->cra_aead.ivsize)
+	if (ivsize < sizeof(u64))
 		goto err_drop_alg;
 
 	/*
@@ -318,39 +629,64 @@ struct crypto_instance *aead_geniv_alloc(struct crypto_template *tmpl,
 	 * template name and double-check the IV generator.
 	 */
 	if (algt->mask & CRYPTO_ALG_GENIV) {
-		if (strcmp(tmpl->name, alg->cra_aead.geniv))
+		if (!alg->base.cra_aead.encrypt)
+			goto err_drop_alg;
+		if (strcmp(tmpl->name, alg->base.cra_aead.geniv))
 			goto err_drop_alg;
 
-		memcpy(inst->alg.cra_name, alg->cra_name, CRYPTO_MAX_ALG_NAME);
-		memcpy(inst->alg.cra_driver_name, alg->cra_driver_name,
+		memcpy(inst->alg.base.cra_name, alg->base.cra_name,
 		       CRYPTO_MAX_ALG_NAME);
-	} else {
-		err = -ENAMETOOLONG;
-		if (snprintf(inst->alg.cra_name, CRYPTO_MAX_ALG_NAME,
-			     "%s(%s)", tmpl->name, alg->cra_name) >=
-		    CRYPTO_MAX_ALG_NAME)
-			goto err_drop_alg;
-		if (snprintf(inst->alg.cra_driver_name, CRYPTO_MAX_ALG_NAME,
-			     "%s(%s)", tmpl->name, alg->cra_driver_name) >=
-		    CRYPTO_MAX_ALG_NAME)
-			goto err_drop_alg;
+		memcpy(inst->alg.base.cra_driver_name,
+		       alg->base.cra_driver_name, CRYPTO_MAX_ALG_NAME);
+
+		inst->alg.base.cra_flags = CRYPTO_ALG_TYPE_AEAD |
+					   CRYPTO_ALG_GENIV;
+		inst->alg.base.cra_flags |= alg->base.cra_flags &
+					    CRYPTO_ALG_ASYNC;
+		inst->alg.base.cra_priority = alg->base.cra_priority;
+		inst->alg.base.cra_blocksize = alg->base.cra_blocksize;
+		inst->alg.base.cra_alignmask = alg->base.cra_alignmask;
+		inst->alg.base.cra_type = &crypto_aead_type;
+
+		inst->alg.base.cra_aead.ivsize = ivsize;
+		inst->alg.base.cra_aead.maxauthsize = maxauthsize;
+
+		inst->alg.base.cra_aead.setkey = alg->base.cra_aead.setkey;
+		inst->alg.base.cra_aead.setauthsize =
+			alg->base.cra_aead.setauthsize;
+		inst->alg.base.cra_aead.encrypt = alg->base.cra_aead.encrypt;
+		inst->alg.base.cra_aead.decrypt = alg->base.cra_aead.decrypt;
+
+		goto out;
 	}
 
-	inst->alg.cra_flags = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_GENIV;
-	inst->alg.cra_flags |= alg->cra_flags & CRYPTO_ALG_ASYNC;
-	inst->alg.cra_priority = alg->cra_priority;
-	inst->alg.cra_blocksize = alg->cra_blocksize;
-	inst->alg.cra_alignmask = alg->cra_alignmask;
-	inst->alg.cra_type = &crypto_aead_type;
+	err = -ENAMETOOLONG;
+	if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME,
+		     "%s(%s)", tmpl->name, alg->base.cra_name) >=
+	    CRYPTO_MAX_ALG_NAME)
+		goto err_drop_alg;
+	if (snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME,
+		     "%s(%s)", tmpl->name, alg->base.cra_driver_name) >=
+	    CRYPTO_MAX_ALG_NAME)
+		goto err_drop_alg;
+
+	inst->alg.base.cra_flags = alg->base.cra_flags & CRYPTO_ALG_ASYNC;
+	inst->alg.base.cra_priority = alg->base.cra_priority;
+	inst->alg.base.cra_blocksize = alg->base.cra_blocksize;
+	inst->alg.base.cra_alignmask = alg->base.cra_alignmask;
+	inst->alg.base.cra_ctxsize = sizeof(struct aead_geniv_ctx);
+
+	inst->alg.setkey = aead_geniv_setkey;
+	inst->alg.setauthsize = aead_geniv_setauthsize;
 
-	inst->alg.cra_aead.ivsize = alg->cra_aead.ivsize;
-	inst->alg.cra_aead.maxauthsize = alg->cra_aead.maxauthsize;
-	inst->alg.cra_aead.geniv = alg->cra_aead.geniv;
+	inst->alg.ivsize = ivsize;
+	inst->alg.maxauthsize = maxauthsize;
 
-	inst->alg.cra_aead.setkey = alg->cra_aead.setkey;
-	inst->alg.cra_aead.setauthsize = alg->cra_aead.setauthsize;
-	inst->alg.cra_aead.encrypt = alg->cra_aead.encrypt;
-	inst->alg.cra_aead.decrypt = alg->cra_aead.decrypt;
+	inst->alg.encrypt = compat_encrypt_first;
+	inst->alg.decrypt = compat_decrypt;
+
+	inst->alg.base.cra_init = aead_geniv_init_compat;
+	inst->alg.base.cra_exit = aead_geniv_exit_compat;
 
 out:
 	return inst;
@@ -364,9 +700,9 @@ err_free_inst:
 }
 EXPORT_SYMBOL_GPL(aead_geniv_alloc);
 
-void aead_geniv_free(struct crypto_instance *inst)
+void aead_geniv_free(struct aead_instance *inst)
 {
-	crypto_drop_aead(crypto_instance_ctx(inst));
+	crypto_drop_aead(aead_instance_ctx(inst));
 	kfree(inst);
 }
 EXPORT_SYMBOL_GPL(aead_geniv_free);
@@ -374,14 +710,17 @@ EXPORT_SYMBOL_GPL(aead_geniv_free);
 int aead_geniv_init(struct crypto_tfm *tfm)
 {
 	struct crypto_instance *inst = (void *)tfm->__crt_alg;
+	struct crypto_aead *child;
 	struct crypto_aead *aead;
 
-	aead = crypto_spawn_aead(crypto_instance_ctx(inst));
-	if (IS_ERR(aead))
-		return PTR_ERR(aead);
+	aead = __crypto_aead_cast(tfm);
+
+	child = crypto_spawn_aead(crypto_instance_ctx(inst));
+	if (IS_ERR(child))
+		return PTR_ERR(child);
 
-	tfm->crt_aead.base = aead;
-	tfm->crt_aead.reqsize += crypto_aead_reqsize(aead);
+	aead->child = child;
+	aead->reqsize += crypto_aead_reqsize(child);
 
 	return 0;
 }
@@ -389,7 +728,7 @@ EXPORT_SYMBOL_GPL(aead_geniv_init);
 
 void aead_geniv_exit(struct crypto_tfm *tfm)
 {
-	crypto_free_aead(tfm->crt_aead.base);
+	crypto_free_aead(__crypto_aead_cast(tfm)->child);
 }
 EXPORT_SYMBOL_GPL(aead_geniv_exit);
 
@@ -443,6 +782,13 @@ static int crypto_nivaead_default(struct crypto_alg *alg, u32 type, u32 mask)
 	if (!tmpl)
 		goto kill_larval;
 
+	if (tmpl->create) {
+		err = tmpl->create(tmpl, tb);
+		if (err)
+			goto put_tmpl;
+		goto ok;
+	}
+
 	inst = tmpl->alloc(tb);
 	err = PTR_ERR(inst);
 	if (IS_ERR(inst))
@@ -454,6 +800,7 @@ static int crypto_nivaead_default(struct crypto_alg *alg, u32 type, u32 mask)
 		goto put_tmpl;
 	}
 
+ok:
 	/* Redo the lookup to use the instance we just registered. */
 	err = -EAGAIN;
 
@@ -489,7 +836,7 @@ struct crypto_alg *crypto_lookup_aead(const char *name, u32 type, u32 mask)
 		return alg;
 
 	if (alg->cra_type == &crypto_aead_type) {
-		if ((alg->cra_flags ^ type ^ ~mask) & CRYPTO_ALG_TESTED) {
+		if (~alg->cra_flags & (type ^ ~mask) & CRYPTO_ALG_TESTED) {
 			crypto_mod_put(alg);
 			alg = ERR_PTR(-ENOENT);
 		}
@@ -505,62 +852,91 @@ EXPORT_SYMBOL_GPL(crypto_lookup_aead);
 int crypto_grab_aead(struct crypto_aead_spawn *spawn, const char *name,
 		     u32 type, u32 mask)
 {
-	struct crypto_alg *alg;
-	int err;
+	spawn->base.frontend = &crypto_aead_type;
+	return crypto_grab_spawn(&spawn->base, name, type, mask);
+}
+EXPORT_SYMBOL_GPL(crypto_grab_aead);
 
-	type &= ~(CRYPTO_ALG_TYPE_MASK | CRYPTO_ALG_GENIV);
-	type |= CRYPTO_ALG_TYPE_AEAD;
-	mask &= ~(CRYPTO_ALG_TYPE_MASK | CRYPTO_ALG_GENIV);
-	mask |= CRYPTO_ALG_TYPE_MASK;
+struct crypto_aead *crypto_alloc_aead(const char *alg_name, u32 type, u32 mask)
+{
+	return crypto_alloc_tfm(alg_name, &crypto_aead_type, type, mask);
+}
+EXPORT_SYMBOL_GPL(crypto_alloc_aead);
 
-	alg = crypto_lookup_aead(name, type, mask);
-	if (IS_ERR(alg))
-		return PTR_ERR(alg);
+static int aead_prepare_alg(struct aead_alg *alg)
+{
+	struct crypto_alg *base = &alg->base;
 
-	err = crypto_init_spawn(&spawn->base, alg, spawn->base.inst, mask);
-	crypto_mod_put(alg);
-	return err;
+	if (max(alg->maxauthsize, alg->ivsize) > PAGE_SIZE / 8)
+		return -EINVAL;
+
+	base->cra_type = &crypto_new_aead_type;
+	base->cra_flags &= ~CRYPTO_ALG_TYPE_MASK;
+	base->cra_flags |= CRYPTO_ALG_TYPE_AEAD;
+
+	return 0;
 }
-EXPORT_SYMBOL_GPL(crypto_grab_aead);
 
-struct crypto_aead *crypto_alloc_aead(const char *alg_name, u32 type, u32 mask)
+int crypto_register_aead(struct aead_alg *alg)
 {
-	struct crypto_tfm *tfm;
+	struct crypto_alg *base = &alg->base;
 	int err;
 
-	type &= ~(CRYPTO_ALG_TYPE_MASK | CRYPTO_ALG_GENIV);
-	type |= CRYPTO_ALG_TYPE_AEAD;
-	mask &= ~(CRYPTO_ALG_TYPE_MASK | CRYPTO_ALG_GENIV);
-	mask |= CRYPTO_ALG_TYPE_MASK;
+	err = aead_prepare_alg(alg);
+	if (err)
+		return err;
 
-	for (;;) {
-		struct crypto_alg *alg;
+	return crypto_register_alg(base);
+}
+EXPORT_SYMBOL_GPL(crypto_register_aead);
 
-		alg = crypto_lookup_aead(alg_name, type, mask);
-		if (IS_ERR(alg)) {
-			err = PTR_ERR(alg);
-			goto err;
-		}
+void crypto_unregister_aead(struct aead_alg *alg)
+{
+	crypto_unregister_alg(&alg->base);
+}
+EXPORT_SYMBOL_GPL(crypto_unregister_aead);
 
-		tfm = __crypto_alloc_tfm(alg, type, mask);
-		if (!IS_ERR(tfm))
-			return __crypto_aead_cast(tfm);
+int crypto_register_aeads(struct aead_alg *algs, int count)
+{
+	int i, ret;
 
-		crypto_mod_put(alg);
-		err = PTR_ERR(tfm);
+	for (i = 0; i < count; i++) {
+		ret = crypto_register_aead(&algs[i]);
+		if (ret)
+			goto err;
+	}
+
+	return 0;
 
 err:
-		if (err != -EAGAIN)
-			break;
-		if (signal_pending(current)) {
-			err = -EINTR;
-			break;
-		}
-	}
+	for (--i; i >= 0; --i)
+		crypto_unregister_aead(&algs[i]);
 
-	return ERR_PTR(err);
+	return ret;
 }
-EXPORT_SYMBOL_GPL(crypto_alloc_aead);
+EXPORT_SYMBOL_GPL(crypto_register_aeads);
+
+void crypto_unregister_aeads(struct aead_alg *algs, int count)
+{
+	int i;
+
+	for (i = count - 1; i >= 0; --i)
+		crypto_unregister_aead(&algs[i]);
+}
+EXPORT_SYMBOL_GPL(crypto_unregister_aeads);
+
+int aead_register_instance(struct crypto_template *tmpl,
+			   struct aead_instance *inst)
+{
+	int err;
+
+	err = aead_prepare_alg(&inst->alg);
+	if (err)
+		return err;
+
+	return crypto_register_instance(tmpl, aead_crypto_instance(inst));
+}
+EXPORT_SYMBOL_GPL(aead_register_instance);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Authenticated Encryption with Associated Data (AEAD)");
diff --git a/crypto/af_alg.c b/crypto/af_alg.c
index f22cc56fd1b3..2bc180e02115 100644
--- a/crypto/af_alg.c
+++ b/crypto/af_alg.c
@@ -127,6 +127,7 @@ EXPORT_SYMBOL_GPL(af_alg_release);
 
 static int alg_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 {
+	const u32 forbidden = CRYPTO_ALG_INTERNAL;
 	struct sock *sk = sock->sk;
 	struct alg_sock *ask = alg_sk(sk);
 	struct sockaddr_alg *sa = (void *)uaddr;
@@ -151,7 +152,9 @@ static int alg_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	if (IS_ERR(type))
 		return PTR_ERR(type);
 
-	private = type->bind(sa->salg_name, sa->salg_feat, sa->salg_mask);
+	private = type->bind(sa->salg_name,
+			     sa->salg_feat & ~forbidden,
+			     sa->salg_mask & ~forbidden);
 	if (IS_ERR(private)) {
 		module_put(type->owner);
 		return PTR_ERR(private);
diff --git a/crypto/akcipher.c b/crypto/akcipher.c
new file mode 100644
index 000000000000..d7986414814e
--- /dev/null
+++ b/crypto/akcipher.c
@@ -0,0 +1,117 @@
+/*
+ * Public Key Encryption
+ *
+ * Copyright (c) 2015, Intel Corporation
+ * Authors: Tadeusz Struk <tadeusz.struk@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ */
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/crypto.h>
+#include <crypto/algapi.h>
+#include <linux/cryptouser.h>
+#include <net/netlink.h>
+#include <crypto/akcipher.h>
+#include <crypto/public_key.h>
+#include "internal.h"
+
+#ifdef CONFIG_NET
+static int crypto_akcipher_report(struct sk_buff *skb, struct crypto_alg *alg)
+{
+	struct crypto_report_akcipher rakcipher;
+
+	strncpy(rakcipher.type, "akcipher", sizeof(rakcipher.type));
+
+	if (nla_put(skb, CRYPTOCFGA_REPORT_AKCIPHER,
+		    sizeof(struct crypto_report_akcipher), &rakcipher))
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -EMSGSIZE;
+}
+#else
+static int crypto_akcipher_report(struct sk_buff *skb, struct crypto_alg *alg)
+{
+	return -ENOSYS;
+}
+#endif
+
+static void crypto_akcipher_show(struct seq_file *m, struct crypto_alg *alg)
+	__attribute__ ((unused));
+
+static void crypto_akcipher_show(struct seq_file *m, struct crypto_alg *alg)
+{
+	seq_puts(m, "type         : akcipher\n");
+}
+
+static void crypto_akcipher_exit_tfm(struct crypto_tfm *tfm)
+{
+	struct crypto_akcipher *akcipher = __crypto_akcipher_tfm(tfm);
+	struct akcipher_alg *alg = crypto_akcipher_alg(akcipher);
+
+	alg->exit(akcipher);
+}
+
+static int crypto_akcipher_init_tfm(struct crypto_tfm *tfm)
+{
+	struct crypto_akcipher *akcipher = __crypto_akcipher_tfm(tfm);
+	struct akcipher_alg *alg = crypto_akcipher_alg(akcipher);
+
+	if (alg->exit)
+		akcipher->base.exit = crypto_akcipher_exit_tfm;
+
+	if (alg->init)
+		return alg->init(akcipher);
+
+	return 0;
+}
+
+static const struct crypto_type crypto_akcipher_type = {
+	.extsize = crypto_alg_extsize,
+	.init_tfm = crypto_akcipher_init_tfm,
+#ifdef CONFIG_PROC_FS
+	.show = crypto_akcipher_show,
+#endif
+	.report = crypto_akcipher_report,
+	.maskclear = ~CRYPTO_ALG_TYPE_MASK,
+	.maskset = CRYPTO_ALG_TYPE_MASK,
+	.type = CRYPTO_ALG_TYPE_AKCIPHER,
+	.tfmsize = offsetof(struct crypto_akcipher, base),
+};
+
+struct crypto_akcipher *crypto_alloc_akcipher(const char *alg_name, u32 type,
+					      u32 mask)
+{
+	return crypto_alloc_tfm(alg_name, &crypto_akcipher_type, type, mask);
+}
+EXPORT_SYMBOL_GPL(crypto_alloc_akcipher);
+
+int crypto_register_akcipher(struct akcipher_alg *alg)
+{
+	struct crypto_alg *base = &alg->base;
+
+	base->cra_type = &crypto_akcipher_type;
+	base->cra_flags &= ~CRYPTO_ALG_TYPE_MASK;
+	base->cra_flags |= CRYPTO_ALG_TYPE_AKCIPHER;
+	return crypto_register_alg(base);
+}
+EXPORT_SYMBOL_GPL(crypto_register_akcipher);
+
+void crypto_unregister_akcipher(struct akcipher_alg *alg)
+{
+	crypto_unregister_alg(&alg->base);
+}
+EXPORT_SYMBOL_GPL(crypto_unregister_akcipher);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Generic public key cihper type");
diff --git a/crypto/algapi.c b/crypto/algapi.c
index d2627a3d4ed8..3c079b7f23f6 100644
--- a/crypto/algapi.c
+++ b/crypto/algapi.c
@@ -12,6 +12,7 @@
 
 #include <linux/err.h>
 #include <linux/errno.h>
+#include <linux/fips.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/list.h>
@@ -43,12 +44,9 @@ static inline int crypto_set_driver_name(struct crypto_alg *alg)
 
 static inline void crypto_check_module_sig(struct module *mod)
 {
-#ifdef CONFIG_CRYPTO_FIPS
-	if (fips_enabled && mod && !mod->sig_ok)
+	if (fips_enabled && mod && !module_sig_ok(mod))
 		panic("Module %s signature verification failed in FIPS mode\n",
-		      mod->name);
-#endif
-	return;
+		      module_name(mod));
 }
 
 static int crypto_check_alg(struct crypto_alg *alg)
@@ -614,6 +612,22 @@ out:
 }
 EXPORT_SYMBOL_GPL(crypto_init_spawn2);
 
+int crypto_grab_spawn(struct crypto_spawn *spawn, const char *name,
+		      u32 type, u32 mask)
+{
+	struct crypto_alg *alg;
+	int err;
+
+	alg = crypto_find_alg(name, spawn->frontend, type, mask);
+	if (IS_ERR(alg))
+		return PTR_ERR(alg);
+
+	err = crypto_init_spawn(spawn, alg, spawn->inst, mask);
+	crypto_mod_put(alg);
+	return err;
+}
+EXPORT_SYMBOL_GPL(crypto_grab_spawn);
+
 void crypto_drop_spawn(struct crypto_spawn *spawn)
 {
 	if (!spawn->alg)
@@ -964,6 +978,13 @@ void crypto_xor(u8 *dst, const u8 *src, unsigned int size)
 }
 EXPORT_SYMBOL_GPL(crypto_xor);
 
+unsigned int crypto_alg_extsize(struct crypto_alg *alg)
+{
+	return alg->cra_ctxsize +
+	       (alg->cra_alignmask & ~(crypto_tfm_ctx_alignment() - 1));
+}
+EXPORT_SYMBOL_GPL(crypto_alg_extsize);
+
 static int __init crypto_algapi_init(void)
 {
 	crypto_init_proc();
diff --git a/crypto/algif_aead.c b/crypto/algif_aead.c
index 69abada22373..e0408a480d2f 100644
--- a/crypto/algif_aead.c
+++ b/crypto/algif_aead.c
@@ -13,6 +13,7 @@
  * any later version.
  */
 
+#include <crypto/aead.h>
 #include <crypto/scatterwalk.h>
 #include <crypto/if_alg.h>
 #include <linux/init.h>
@@ -71,7 +72,7 @@ static inline bool aead_sufficient_data(struct aead_ctx *ctx)
 {
 	unsigned as = crypto_aead_authsize(crypto_aead_reqtfm(&ctx->aead_req));
 
-	return (ctx->used >= (ctx->aead_assoclen + (ctx->enc ? 0 : as)));
+	return ctx->used >= ctx->aead_assoclen + as;
 }
 
 static void aead_put_sgl(struct sock *sk)
@@ -352,12 +353,8 @@ static int aead_recvmsg(struct socket *sock, struct msghdr *msg, size_t ignored,
 	struct sock *sk = sock->sk;
 	struct alg_sock *ask = alg_sk(sk);
 	struct aead_ctx *ctx = ask->private;
-	unsigned bs = crypto_aead_blocksize(crypto_aead_reqtfm(&ctx->aead_req));
 	unsigned as = crypto_aead_authsize(crypto_aead_reqtfm(&ctx->aead_req));
 	struct aead_sg_list *sgl = &ctx->tsgl;
-	struct scatterlist *sg = NULL;
-	struct scatterlist assoc[ALG_MAX_PAGES];
-	size_t assoclen = 0;
 	unsigned int i = 0;
 	int err = -EINVAL;
 	unsigned long used = 0;
@@ -406,23 +403,13 @@ static int aead_recvmsg(struct socket *sock, struct msghdr *msg, size_t ignored,
 	if (!aead_sufficient_data(ctx))
 		goto unlock;
 
+	outlen = used;
+
 	/*
 	 * The cipher operation input data is reduced by the associated data
 	 * length as this data is processed separately later on.
 	 */
-	used -= ctx->aead_assoclen;
-
-	if (ctx->enc) {
-		/* round up output buffer to multiple of block size */
-		outlen = ((used + bs - 1) / bs * bs);
-		/* add the size needed for the auth tag to be created */
-		outlen += as;
-	} else {
-		/* output data size is input without the authentication tag */
-		outlen = used - as;
-		/* round up output buffer to multiple of block size */
-		outlen = ((outlen + bs - 1) / bs * bs);
-	}
+	used -= ctx->aead_assoclen + (ctx->enc ? as : 0);
 
 	/* convert iovecs of output buffers into scatterlists */
 	while (iov_iter_count(&msg->msg_iter)) {
@@ -451,47 +438,11 @@ static int aead_recvmsg(struct socket *sock, struct msghdr *msg, size_t ignored,
 	if (usedpages < outlen)
 		goto unlock;
 
-	sg_init_table(assoc, ALG_MAX_PAGES);
-	assoclen = ctx->aead_assoclen;
-	/*
-	 * Split scatterlist into two: first part becomes AD, second part
-	 * is plaintext / ciphertext. The first part is assigned to assoc
-	 * scatterlist. When this loop finishes, sg points to the start of the
-	 * plaintext / ciphertext.
-	 */
-	for (i = 0; i < ctx->tsgl.cur; i++) {
-		sg = sgl->sg + i;
-		if (sg->length <= assoclen) {
-			/* AD is larger than one page */
-			sg_set_page(assoc + i, sg_page(sg),
-				    sg->length, sg->offset);
-			assoclen -= sg->length;
-			if (i >= ctx->tsgl.cur)
-				goto unlock;
-		} else if (!assoclen) {
-			/* current page is to start of plaintext / ciphertext */
-			if (i)
-				/* AD terminates at page boundary */
-				sg_mark_end(assoc + i - 1);
-			else
-				/* AD size is zero */
-				sg_mark_end(assoc);
-			break;
-		} else {
-			/* AD does not terminate at page boundary */
-			sg_set_page(assoc + i, sg_page(sg),
-				    assoclen, sg->offset);
-			sg_mark_end(assoc + i);
-			/* plaintext / ciphertext starts after AD */
-			sg->length -= assoclen;
-			sg->offset += assoclen;
-			break;
-		}
-	}
+	sg_mark_end(sgl->sg + sgl->cur - 1);
 
-	aead_request_set_assoc(&ctx->aead_req, assoc, ctx->aead_assoclen);
-	aead_request_set_crypt(&ctx->aead_req, sg, ctx->rsgl[0].sg, used,
-			       ctx->iv);
+	aead_request_set_crypt(&ctx->aead_req, sgl->sg, ctx->rsgl[0].sg,
+			       used, ctx->iv);
+	aead_request_set_ad(&ctx->aead_req, ctx->aead_assoclen);
 
 	err = af_alg_wait_for_completion(ctx->enc ?
 					 crypto_aead_encrypt(&ctx->aead_req) :
@@ -563,7 +514,8 @@ static struct proto_ops algif_aead_ops = {
 
 static void *aead_bind(const char *name, u32 type, u32 mask)
 {
-	return crypto_alloc_aead(name, type, mask);
+	return crypto_alloc_aead(name, type | CRYPTO_ALG_AEAD_NEW,
+				 mask | CRYPTO_ALG_AEAD_NEW);
 }
 
 static void aead_release(void *private)
diff --git a/crypto/algif_rng.c b/crypto/algif_rng.c
index 8109aaad2726..150c2b6480ed 100644
--- a/crypto/algif_rng.c
+++ b/crypto/algif_rng.c
@@ -164,7 +164,7 @@ static int rng_setkey(void *private, const u8 *seed, unsigned int seedlen)
 	 * Check whether seedlen is of sufficient size is done in RNG
 	 * implementations.
 	 */
-	return crypto_rng_reset(private, (u8 *)seed, seedlen);
+	return crypto_rng_reset(private, seed, seedlen);
 }
 
 static const struct af_alg_type algif_type_rng = {
diff --git a/crypto/ansi_cprng.c b/crypto/ansi_cprng.c
index 765fe7609348..eff337ce9003 100644
--- a/crypto/ansi_cprng.c
+++ b/crypto/ansi_cprng.c
@@ -20,8 +20,6 @@
 #include <linux/moduleparam.h>
 #include <linux/string.h>
 
-#include "internal.h"
-
 #define DEFAULT_PRNG_KEY "0123456789abcdef"
 #define DEFAULT_PRNG_KSZ 16
 #define DEFAULT_BLK_SZ 16
@@ -281,11 +279,11 @@ static void free_prng_context(struct prng_context *ctx)
 }
 
 static int reset_prng_context(struct prng_context *ctx,
-			      unsigned char *key, size_t klen,
-			      unsigned char *V, unsigned char *DT)
+			      const unsigned char *key, size_t klen,
+			      const unsigned char *V, const unsigned char *DT)
 {
 	int ret;
-	unsigned char *prng_key;
+	const unsigned char *prng_key;
 
 	spin_lock_bh(&ctx->prng_lock);
 	ctx->flags |= PRNG_NEED_RESET;
@@ -353,8 +351,9 @@ static void cprng_exit(struct crypto_tfm *tfm)
 	free_prng_context(crypto_tfm_ctx(tfm));
 }
 
-static int cprng_get_random(struct crypto_rng *tfm, u8 *rdata,
-			    unsigned int dlen)
+static int cprng_get_random(struct crypto_rng *tfm,
+			    const u8 *src, unsigned int slen,
+			    u8 *rdata, unsigned int dlen)
 {
 	struct prng_context *prng = crypto_rng_ctx(tfm);
 
@@ -367,11 +366,12 @@ static int cprng_get_random(struct crypto_rng *tfm, u8 *rdata,
  *  V and KEY are required during reset, and DT is optional, detected
  *  as being present by testing the length of the seed
  */
-static int cprng_reset(struct crypto_rng *tfm, u8 *seed, unsigned int slen)
+static int cprng_reset(struct crypto_rng *tfm,
+		       const u8 *seed, unsigned int slen)
 {
 	struct prng_context *prng = crypto_rng_ctx(tfm);
-	u8 *key = seed + DEFAULT_BLK_SZ;
-	u8 *dt = NULL;
+	const u8 *key = seed + DEFAULT_BLK_SZ;
+	const u8 *dt = NULL;
 
 	if (slen < DEFAULT_PRNG_KSZ + DEFAULT_BLK_SZ)
 		return -EINVAL;
@@ -387,18 +387,20 @@ static int cprng_reset(struct crypto_rng *tfm, u8 *seed, unsigned int slen)
 }
 
 #ifdef CONFIG_CRYPTO_FIPS
-static int fips_cprng_get_random(struct crypto_rng *tfm, u8 *rdata,
-			    unsigned int dlen)
+static int fips_cprng_get_random(struct crypto_rng *tfm,
+				 const u8 *src, unsigned int slen,
+				 u8 *rdata, unsigned int dlen)
 {
 	struct prng_context *prng = crypto_rng_ctx(tfm);
 
 	return get_prng_bytes(rdata, dlen, prng, 1);
 }
 
-static int fips_cprng_reset(struct crypto_rng *tfm, u8 *seed, unsigned int slen)
+static int fips_cprng_reset(struct crypto_rng *tfm,
+			    const u8 *seed, unsigned int slen)
 {
 	u8 rdata[DEFAULT_BLK_SZ];
-	u8 *key = seed + DEFAULT_BLK_SZ;
+	const u8 *key = seed + DEFAULT_BLK_SZ;
 	int rc;
 
 	struct prng_context *prng = crypto_rng_ctx(tfm);
@@ -424,40 +426,32 @@ out:
 }
 #endif
 
-static struct crypto_alg rng_algs[] = { {
-	.cra_name		= "stdrng",
-	.cra_driver_name	= "ansi_cprng",
-	.cra_priority		= 100,
-	.cra_flags		= CRYPTO_ALG_TYPE_RNG,
-	.cra_ctxsize		= sizeof(struct prng_context),
-	.cra_type		= &crypto_rng_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= cprng_init,
-	.cra_exit		= cprng_exit,
-	.cra_u			= {
-		.rng = {
-			.rng_make_random	= cprng_get_random,
-			.rng_reset		= cprng_reset,
-			.seedsize = DEFAULT_PRNG_KSZ + 2*DEFAULT_BLK_SZ,
-		}
+static struct rng_alg rng_algs[] = { {
+	.generate		= cprng_get_random,
+	.seed			= cprng_reset,
+	.seedsize		= DEFAULT_PRNG_KSZ + 2 * DEFAULT_BLK_SZ,
+	.base			=	{
+		.cra_name		= "stdrng",
+		.cra_driver_name	= "ansi_cprng",
+		.cra_priority		= 100,
+		.cra_ctxsize		= sizeof(struct prng_context),
+		.cra_module		= THIS_MODULE,
+		.cra_init		= cprng_init,
+		.cra_exit		= cprng_exit,
 	}
 #ifdef CONFIG_CRYPTO_FIPS
 }, {
-	.cra_name		= "fips(ansi_cprng)",
-	.cra_driver_name	= "fips_ansi_cprng",
-	.cra_priority		= 300,
-	.cra_flags		= CRYPTO_ALG_TYPE_RNG,
-	.cra_ctxsize		= sizeof(struct prng_context),
-	.cra_type		= &crypto_rng_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= cprng_init,
-	.cra_exit		= cprng_exit,
-	.cra_u			= {
-		.rng = {
-			.rng_make_random	= fips_cprng_get_random,
-			.rng_reset		= fips_cprng_reset,
-			.seedsize = DEFAULT_PRNG_KSZ + 2*DEFAULT_BLK_SZ,
-		}
+	.generate		= fips_cprng_get_random,
+	.seed			= fips_cprng_reset,
+	.seedsize		= DEFAULT_PRNG_KSZ + 2 * DEFAULT_BLK_SZ,
+	.base			=	{
+		.cra_name		= "fips(ansi_cprng)",
+		.cra_driver_name	= "fips_ansi_cprng",
+		.cra_priority		= 300,
+		.cra_ctxsize		= sizeof(struct prng_context),
+		.cra_module		= THIS_MODULE,
+		.cra_init		= cprng_init,
+		.cra_exit		= cprng_exit,
 	}
 #endif
 } };
@@ -465,12 +459,12 @@ static struct crypto_alg rng_algs[] = { {
 /* Module initalization */
 static int __init prng_mod_init(void)
 {
-	return crypto_register_algs(rng_algs, ARRAY_SIZE(rng_algs));
+	return crypto_register_rngs(rng_algs, ARRAY_SIZE(rng_algs));
 }
 
 static void __exit prng_mod_fini(void)
 {
-	crypto_unregister_algs(rng_algs, ARRAY_SIZE(rng_algs));
+	crypto_unregister_rngs(rng_algs, ARRAY_SIZE(rng_algs));
 }
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/authenc.c b/crypto/authenc.c
index 78fb16cab13f..3e852299afb4 100644
--- a/crypto/authenc.c
+++ b/crypto/authenc.c
@@ -10,7 +10,7 @@
  *
  */
 
-#include <crypto/aead.h>
+#include <crypto/internal/aead.h>
 #include <crypto/internal/hash.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/authenc.h>
@@ -570,13 +570,14 @@ static int crypto_authenc_init_tfm(struct crypto_tfm *tfm)
 			    crypto_ahash_alignmask(auth) + 1) +
 		      crypto_ablkcipher_ivsize(enc);
 
-	tfm->crt_aead.reqsize = sizeof(struct authenc_request_ctx) +
-				ctx->reqoff +
-				max_t(unsigned int,
-				crypto_ahash_reqsize(auth) +
-				sizeof(struct ahash_request),
-				sizeof(struct skcipher_givcrypt_request) +
-				crypto_ablkcipher_reqsize(enc));
+	crypto_aead_set_reqsize(__crypto_aead_cast(tfm),
+		sizeof(struct authenc_request_ctx) +
+		ctx->reqoff +
+		max_t(unsigned int,
+			crypto_ahash_reqsize(auth) +
+			sizeof(struct ahash_request),
+			sizeof(struct skcipher_givcrypt_request) +
+			crypto_ablkcipher_reqsize(enc)));
 
 	return 0;
 
diff --git a/crypto/authencesn.c b/crypto/authencesn.c
index 024bff2344fc..a3da6770bc9e 100644
--- a/crypto/authencesn.c
+++ b/crypto/authencesn.c
@@ -12,7 +12,7 @@
  *
  */
 
-#include <crypto/aead.h>
+#include <crypto/internal/aead.h>
 #include <crypto/internal/hash.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/authenc.h>
@@ -662,13 +662,14 @@ static int crypto_authenc_esn_init_tfm(struct crypto_tfm *tfm)
 			    crypto_ahash_alignmask(auth) + 1) +
 		      crypto_ablkcipher_ivsize(enc);
 
-	tfm->crt_aead.reqsize = sizeof(struct authenc_esn_request_ctx) +
-				ctx->reqoff +
-				max_t(unsigned int,
-				crypto_ahash_reqsize(auth) +
-				sizeof(struct ahash_request),
-				sizeof(struct skcipher_givcrypt_request) +
-				crypto_ablkcipher_reqsize(enc));
+	crypto_aead_set_reqsize(__crypto_aead_cast(tfm),
+		sizeof(struct authenc_esn_request_ctx) +
+		ctx->reqoff +
+		max_t(unsigned int,
+			crypto_ahash_reqsize(auth) +
+			sizeof(struct ahash_request),
+			sizeof(struct skcipher_givcrypt_request) +
+			crypto_ablkcipher_reqsize(enc)));
 
 	return 0;
 
diff --git a/crypto/blkcipher.c b/crypto/blkcipher.c
index 0122bec38564..11b981492031 100644
--- a/crypto/blkcipher.c
+++ b/crypto/blkcipher.c
@@ -14,6 +14,7 @@
  *
  */
 
+#include <crypto/aead.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/scatterwalk.h>
 #include <linux/errno.h>
diff --git a/crypto/ccm.c b/crypto/ccm.c
index 003bbbd21a2b..a4d1a5eda18b 100644
--- a/crypto/ccm.c
+++ b/crypto/ccm.c
@@ -453,9 +453,9 @@ static int crypto_ccm_init_tfm(struct crypto_tfm *tfm)
 
 	align = crypto_tfm_alg_alignmask(tfm);
 	align &= ~(crypto_tfm_ctx_alignment() - 1);
-	tfm->crt_aead.reqsize = align +
-				sizeof(struct crypto_ccm_req_priv_ctx) +
-				crypto_ablkcipher_reqsize(ctr);
+	crypto_aead_set_reqsize(__crypto_aead_cast(tfm),
+		align + sizeof(struct crypto_ccm_req_priv_ctx) +
+		crypto_ablkcipher_reqsize(ctr));
 
 	return 0;
 
@@ -729,10 +729,10 @@ static int crypto_rfc4309_init_tfm(struct crypto_tfm *tfm)
 
 	align = crypto_aead_alignmask(aead);
 	align &= ~(crypto_tfm_ctx_alignment() - 1);
-	tfm->crt_aead.reqsize = sizeof(struct aead_request) +
-				ALIGN(crypto_aead_reqsize(aead),
-				      crypto_tfm_ctx_alignment()) +
-				align + 16;
+	crypto_aead_set_reqsize(__crypto_aead_cast(tfm),
+		sizeof(struct aead_request) +
+		ALIGN(crypto_aead_reqsize(aead), crypto_tfm_ctx_alignment()) +
+		align + 16);
 
 	return 0;
 }
diff --git a/crypto/chacha20_generic.c b/crypto/chacha20_generic.c
new file mode 100644
index 000000000000..fa42e708aa96
--- /dev/null
+++ b/crypto/chacha20_generic.c
@@ -0,0 +1,216 @@
+/*
+ * ChaCha20 256-bit cipher algorithm, RFC7539
+ *
+ * Copyright (C) 2015 Martin Willi
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <crypto/algapi.h>
+#include <linux/crypto.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#define CHACHA20_NONCE_SIZE 16
+#define CHACHA20_KEY_SIZE   32
+#define CHACHA20_BLOCK_SIZE 64
+
+struct chacha20_ctx {
+	u32 key[8];
+};
+
+static inline u32 rotl32(u32 v, u8 n)
+{
+	return (v << n) | (v >> (sizeof(v) * 8 - n));
+}
+
+static inline u32 le32_to_cpuvp(const void *p)
+{
+	return le32_to_cpup(p);
+}
+
+static void chacha20_block(u32 *state, void *stream)
+{
+	u32 x[16], *out = stream;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(x); i++)
+		x[i] = state[i];
+
+	for (i = 0; i < 20; i += 2) {
+		x[0]  += x[4];    x[12] = rotl32(x[12] ^ x[0],  16);
+		x[1]  += x[5];    x[13] = rotl32(x[13] ^ x[1],  16);
+		x[2]  += x[6];    x[14] = rotl32(x[14] ^ x[2],  16);
+		x[3]  += x[7];    x[15] = rotl32(x[15] ^ x[3],  16);
+
+		x[8]  += x[12];   x[4]  = rotl32(x[4]  ^ x[8],  12);
+		x[9]  += x[13];   x[5]  = rotl32(x[5]  ^ x[9],  12);
+		x[10] += x[14];   x[6]  = rotl32(x[6]  ^ x[10], 12);
+		x[11] += x[15];   x[7]  = rotl32(x[7]  ^ x[11], 12);
+
+		x[0]  += x[4];    x[12] = rotl32(x[12] ^ x[0],   8);
+		x[1]  += x[5];    x[13] = rotl32(x[13] ^ x[1],   8);
+		x[2]  += x[6];    x[14] = rotl32(x[14] ^ x[2],   8);
+		x[3]  += x[7];    x[15] = rotl32(x[15] ^ x[3],   8);
+
+		x[8]  += x[12];   x[4]  = rotl32(x[4]  ^ x[8],   7);
+		x[9]  += x[13];   x[5]  = rotl32(x[5]  ^ x[9],   7);
+		x[10] += x[14];   x[6]  = rotl32(x[6]  ^ x[10],  7);
+		x[11] += x[15];   x[7]  = rotl32(x[7]  ^ x[11],  7);
+
+		x[0]  += x[5];    x[15] = rotl32(x[15] ^ x[0],  16);
+		x[1]  += x[6];    x[12] = rotl32(x[12] ^ x[1],  16);
+		x[2]  += x[7];    x[13] = rotl32(x[13] ^ x[2],  16);
+		x[3]  += x[4];    x[14] = rotl32(x[14] ^ x[3],  16);
+
+		x[10] += x[15];   x[5]  = rotl32(x[5]  ^ x[10], 12);
+		x[11] += x[12];   x[6]  = rotl32(x[6]  ^ x[11], 12);
+		x[8]  += x[13];   x[7]  = rotl32(x[7]  ^ x[8],  12);
+		x[9]  += x[14];   x[4]  = rotl32(x[4]  ^ x[9],  12);
+
+		x[0]  += x[5];    x[15] = rotl32(x[15] ^ x[0],   8);
+		x[1]  += x[6];    x[12] = rotl32(x[12] ^ x[1],   8);
+		x[2]  += x[7];    x[13] = rotl32(x[13] ^ x[2],   8);
+		x[3]  += x[4];    x[14] = rotl32(x[14] ^ x[3],   8);
+
+		x[10] += x[15];   x[5]  = rotl32(x[5]  ^ x[10],  7);
+		x[11] += x[12];   x[6]  = rotl32(x[6]  ^ x[11],  7);
+		x[8]  += x[13];   x[7]  = rotl32(x[7]  ^ x[8],   7);
+		x[9]  += x[14];   x[4]  = rotl32(x[4]  ^ x[9],   7);
+	}
+
+	for (i = 0; i < ARRAY_SIZE(x); i++)
+		out[i] = cpu_to_le32(x[i] + state[i]);
+
+	state[12]++;
+}
+
+static void chacha20_docrypt(u32 *state, u8 *dst, const u8 *src,
+			     unsigned int bytes)
+{
+	u8 stream[CHACHA20_BLOCK_SIZE];
+
+	if (dst != src)
+		memcpy(dst, src, bytes);
+
+	while (bytes >= CHACHA20_BLOCK_SIZE) {
+		chacha20_block(state, stream);
+		crypto_xor(dst, stream, CHACHA20_BLOCK_SIZE);
+		bytes -= CHACHA20_BLOCK_SIZE;
+		dst += CHACHA20_BLOCK_SIZE;
+	}
+	if (bytes) {
+		chacha20_block(state, stream);
+		crypto_xor(dst, stream, bytes);
+	}
+}
+
+static void chacha20_init(u32 *state, struct chacha20_ctx *ctx, u8 *iv)
+{
+	static const char constant[16] = "expand 32-byte k";
+
+	state[0]  = le32_to_cpuvp(constant +  0);
+	state[1]  = le32_to_cpuvp(constant +  4);
+	state[2]  = le32_to_cpuvp(constant +  8);
+	state[3]  = le32_to_cpuvp(constant + 12);
+	state[4]  = ctx->key[0];
+	state[5]  = ctx->key[1];
+	state[6]  = ctx->key[2];
+	state[7]  = ctx->key[3];
+	state[8]  = ctx->key[4];
+	state[9]  = ctx->key[5];
+	state[10] = ctx->key[6];
+	state[11] = ctx->key[7];
+	state[12] = le32_to_cpuvp(iv +  0);
+	state[13] = le32_to_cpuvp(iv +  4);
+	state[14] = le32_to_cpuvp(iv +  8);
+	state[15] = le32_to_cpuvp(iv + 12);
+}
+
+static int chacha20_setkey(struct crypto_tfm *tfm, const u8 *key,
+			   unsigned int keysize)
+{
+	struct chacha20_ctx *ctx = crypto_tfm_ctx(tfm);
+	int i;
+
+	if (keysize != CHACHA20_KEY_SIZE)
+		return -EINVAL;
+
+	for (i = 0; i < ARRAY_SIZE(ctx->key); i++)
+		ctx->key[i] = le32_to_cpuvp(key + i * sizeof(u32));
+
+	return 0;
+}
+
+static int chacha20_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+			  struct scatterlist *src, unsigned int nbytes)
+{
+	struct blkcipher_walk walk;
+	u32 state[16];
+	int err;
+
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt_block(desc, &walk, CHACHA20_BLOCK_SIZE);
+
+	chacha20_init(state, crypto_blkcipher_ctx(desc->tfm), walk.iv);
+
+	while (walk.nbytes >= CHACHA20_BLOCK_SIZE) {
+		chacha20_docrypt(state, walk.dst.virt.addr, walk.src.virt.addr,
+				 rounddown(walk.nbytes, CHACHA20_BLOCK_SIZE));
+		err = blkcipher_walk_done(desc, &walk,
+					  walk.nbytes % CHACHA20_BLOCK_SIZE);
+	}
+
+	if (walk.nbytes) {
+		chacha20_docrypt(state, walk.dst.virt.addr, walk.src.virt.addr,
+				 walk.nbytes);
+		err = blkcipher_walk_done(desc, &walk, 0);
+	}
+
+	return err;
+}
+
+static struct crypto_alg alg = {
+	.cra_name		= "chacha20",
+	.cra_driver_name	= "chacha20-generic",
+	.cra_priority		= 100,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= 1,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_ctxsize		= sizeof(struct chacha20_ctx),
+	.cra_alignmask		= sizeof(u32) - 1,
+	.cra_module		= THIS_MODULE,
+	.cra_u			= {
+		.blkcipher = {
+			.min_keysize	= CHACHA20_KEY_SIZE,
+			.max_keysize	= CHACHA20_KEY_SIZE,
+			.ivsize		= CHACHA20_NONCE_SIZE,
+			.geniv		= "seqiv",
+			.setkey		= chacha20_setkey,
+			.encrypt	= chacha20_crypt,
+			.decrypt	= chacha20_crypt,
+		},
+	},
+};
+
+static int __init chacha20_generic_mod_init(void)
+{
+	return crypto_register_alg(&alg);
+}
+
+static void __exit chacha20_generic_mod_fini(void)
+{
+	crypto_unregister_alg(&alg);
+}
+
+module_init(chacha20_generic_mod_init);
+module_exit(chacha20_generic_mod_fini);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Martin Willi <martin@strongswan.org>");
+MODULE_DESCRIPTION("chacha20 cipher algorithm");
+MODULE_ALIAS_CRYPTO("chacha20");
+MODULE_ALIAS_CRYPTO("chacha20-generic");
diff --git a/crypto/chacha20poly1305.c b/crypto/chacha20poly1305.c
new file mode 100644
index 000000000000..7b46ed799a64
--- /dev/null
+++ b/crypto/chacha20poly1305.c
@@ -0,0 +1,695 @@
+/*
+ * ChaCha20-Poly1305 AEAD, RFC7539
+ *
+ * Copyright (C) 2015 Martin Willi
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <crypto/internal/aead.h>
+#include <crypto/internal/hash.h>
+#include <crypto/internal/skcipher.h>
+#include <crypto/scatterwalk.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#include "internal.h"
+
+#define POLY1305_BLOCK_SIZE	16
+#define POLY1305_DIGEST_SIZE	16
+#define POLY1305_KEY_SIZE	32
+#define CHACHA20_KEY_SIZE	32
+#define CHACHA20_IV_SIZE	16
+#define CHACHAPOLY_IV_SIZE	12
+
+struct chachapoly_instance_ctx {
+	struct crypto_skcipher_spawn chacha;
+	struct crypto_ahash_spawn poly;
+	unsigned int saltlen;
+};
+
+struct chachapoly_ctx {
+	struct crypto_ablkcipher *chacha;
+	struct crypto_ahash *poly;
+	/* key bytes we use for the ChaCha20 IV */
+	unsigned int saltlen;
+	u8 salt[];
+};
+
+struct poly_req {
+	/* zero byte padding for AD/ciphertext, as needed */
+	u8 pad[POLY1305_BLOCK_SIZE];
+	/* tail data with AD/ciphertext lengths */
+	struct {
+		__le64 assoclen;
+		__le64 cryptlen;
+	} tail;
+	struct scatterlist src[1];
+	struct ahash_request req; /* must be last member */
+};
+
+struct chacha_req {
+	u8 iv[CHACHA20_IV_SIZE];
+	struct scatterlist src[1];
+	struct ablkcipher_request req; /* must be last member */
+};
+
+struct chachapoly_req_ctx {
+	/* the key we generate for Poly1305 using Chacha20 */
+	u8 key[POLY1305_KEY_SIZE];
+	/* calculated Poly1305 tag */
+	u8 tag[POLY1305_DIGEST_SIZE];
+	/* length of data to en/decrypt, without ICV */
+	unsigned int cryptlen;
+	union {
+		struct poly_req poly;
+		struct chacha_req chacha;
+	} u;
+};
+
+static inline void async_done_continue(struct aead_request *req, int err,
+				       int (*cont)(struct aead_request *))
+{
+	if (!err)
+		err = cont(req);
+
+	if (err != -EINPROGRESS && err != -EBUSY)
+		aead_request_complete(req, err);
+}
+
+static void chacha_iv(u8 *iv, struct aead_request *req, u32 icb)
+{
+	struct chachapoly_ctx *ctx = crypto_aead_ctx(crypto_aead_reqtfm(req));
+	__le32 leicb = cpu_to_le32(icb);
+
+	memcpy(iv, &leicb, sizeof(leicb));
+	memcpy(iv + sizeof(leicb), ctx->salt, ctx->saltlen);
+	memcpy(iv + sizeof(leicb) + ctx->saltlen, req->iv,
+	       CHACHA20_IV_SIZE - sizeof(leicb) - ctx->saltlen);
+}
+
+static int poly_verify_tag(struct aead_request *req)
+{
+	struct chachapoly_req_ctx *rctx = aead_request_ctx(req);
+	u8 tag[sizeof(rctx->tag)];
+
+	scatterwalk_map_and_copy(tag, req->src, rctx->cryptlen, sizeof(tag), 0);
+	if (crypto_memneq(tag, rctx->tag, sizeof(tag)))
+		return -EBADMSG;
+	return 0;
+}
+
+static int poly_copy_tag(struct aead_request *req)
+{
+	struct chachapoly_req_ctx *rctx = aead_request_ctx(req);
+
+	scatterwalk_map_and_copy(rctx->tag, req->dst, rctx->cryptlen,
+				 sizeof(rctx->tag), 1);
+	return 0;
+}
+
+static void chacha_decrypt_done(struct crypto_async_request *areq, int err)
+{
+	async_done_continue(areq->data, err, poly_verify_tag);
+}
+
+static int chacha_decrypt(struct aead_request *req)
+{
+	struct chachapoly_ctx *ctx = crypto_aead_ctx(crypto_aead_reqtfm(req));
+	struct chachapoly_req_ctx *rctx = aead_request_ctx(req);
+	struct chacha_req *creq = &rctx->u.chacha;
+	int err;
+
+	chacha_iv(creq->iv, req, 1);
+
+	ablkcipher_request_set_callback(&creq->req, aead_request_flags(req),
+					chacha_decrypt_done, req);
+	ablkcipher_request_set_tfm(&creq->req, ctx->chacha);
+	ablkcipher_request_set_crypt(&creq->req, req->src, req->dst,
+				     rctx->cryptlen, creq->iv);
+	err = crypto_ablkcipher_decrypt(&creq->req);
+	if (err)
+		return err;
+
+	return poly_verify_tag(req);
+}
+
+static int poly_tail_continue(struct aead_request *req)
+{
+	struct chachapoly_req_ctx *rctx = aead_request_ctx(req);
+
+	if (rctx->cryptlen == req->cryptlen) /* encrypting */
+		return poly_copy_tag(req);
+
+	return chacha_decrypt(req);
+}
+
+static void poly_tail_done(struct crypto_async_request *areq, int err)
+{
+	async_done_continue(areq->data, err, poly_tail_continue);
+}
+
+static int poly_tail(struct aead_request *req)
+{
+	struct chachapoly_ctx *ctx = crypto_aead_ctx(crypto_aead_reqtfm(req));
+	struct chachapoly_req_ctx *rctx = aead_request_ctx(req);
+	struct poly_req *preq = &rctx->u.poly;
+	__le64 len;
+	int err;
+
+	sg_init_table(preq->src, 1);
+	len = cpu_to_le64(req->assoclen);
+	memcpy(&preq->tail.assoclen, &len, sizeof(len));
+	len = cpu_to_le64(rctx->cryptlen);
+	memcpy(&preq->tail.cryptlen, &len, sizeof(len));
+	sg_set_buf(preq->src, &preq->tail, sizeof(preq->tail));
+
+	ahash_request_set_callback(&preq->req, aead_request_flags(req),
+				   poly_tail_done, req);
+	ahash_request_set_tfm(&preq->req, ctx->poly);
+	ahash_request_set_crypt(&preq->req, preq->src,
+				rctx->tag, sizeof(preq->tail));
+
+	err = crypto_ahash_finup(&preq->req);
+	if (err)
+		return err;
+
+	return poly_tail_continue(req);
+}
+
+static void poly_cipherpad_done(struct crypto_async_request *areq, int err)
+{
+	async_done_continue(areq->data, err, poly_tail);
+}
+
+static int poly_cipherpad(struct aead_request *req)
+{
+	struct chachapoly_ctx *ctx = crypto_aead_ctx(crypto_aead_reqtfm(req));
+	struct chachapoly_req_ctx *rctx = aead_request_ctx(req);
+	struct poly_req *preq = &rctx->u.poly;
+	unsigned int padlen, bs = POLY1305_BLOCK_SIZE;
+	int err;
+
+	padlen = (bs - (rctx->cryptlen % bs)) % bs;
+	memset(preq->pad, 0, sizeof(preq->pad));
+	sg_init_table(preq->src, 1);
+	sg_set_buf(preq->src, &preq->pad, padlen);
+
+	ahash_request_set_callback(&preq->req, aead_request_flags(req),
+				   poly_cipherpad_done, req);
+	ahash_request_set_tfm(&preq->req, ctx->poly);
+	ahash_request_set_crypt(&preq->req, preq->src, NULL, padlen);
+
+	err = crypto_ahash_update(&preq->req);
+	if (err)
+		return err;
+
+	return poly_tail(req);
+}
+
+static void poly_cipher_done(struct crypto_async_request *areq, int err)
+{
+	async_done_continue(areq->data, err, poly_cipherpad);
+}
+
+static int poly_cipher(struct aead_request *req)
+{
+	struct chachapoly_ctx *ctx = crypto_aead_ctx(crypto_aead_reqtfm(req));
+	struct chachapoly_req_ctx *rctx = aead_request_ctx(req);
+	struct poly_req *preq = &rctx->u.poly;
+	struct scatterlist *crypt = req->src;
+	int err;
+
+	if (rctx->cryptlen == req->cryptlen) /* encrypting */
+		crypt = req->dst;
+
+	ahash_request_set_callback(&preq->req, aead_request_flags(req),
+				   poly_cipher_done, req);
+	ahash_request_set_tfm(&preq->req, ctx->poly);
+	ahash_request_set_crypt(&preq->req, crypt, NULL, rctx->cryptlen);
+
+	err = crypto_ahash_update(&preq->req);
+	if (err)
+		return err;
+
+	return poly_cipherpad(req);
+}
+
+static void poly_adpad_done(struct crypto_async_request *areq, int err)
+{
+	async_done_continue(areq->data, err, poly_cipher);
+}
+
+static int poly_adpad(struct aead_request *req)
+{
+	struct chachapoly_ctx *ctx = crypto_aead_ctx(crypto_aead_reqtfm(req));
+	struct chachapoly_req_ctx *rctx = aead_request_ctx(req);
+	struct poly_req *preq = &rctx->u.poly;
+	unsigned int padlen, bs = POLY1305_BLOCK_SIZE;
+	int err;
+
+	padlen = (bs - (req->assoclen % bs)) % bs;
+	memset(preq->pad, 0, sizeof(preq->pad));
+	sg_init_table(preq->src, 1);
+	sg_set_buf(preq->src, preq->pad, padlen);
+
+	ahash_request_set_callback(&preq->req, aead_request_flags(req),
+				   poly_adpad_done, req);
+	ahash_request_set_tfm(&preq->req, ctx->poly);
+	ahash_request_set_crypt(&preq->req, preq->src, NULL, padlen);
+
+	err = crypto_ahash_update(&preq->req);
+	if (err)
+		return err;
+
+	return poly_cipher(req);
+}
+
+static void poly_ad_done(struct crypto_async_request *areq, int err)
+{
+	async_done_continue(areq->data, err, poly_adpad);
+}
+
+static int poly_ad(struct aead_request *req)
+{
+	struct chachapoly_ctx *ctx = crypto_aead_ctx(crypto_aead_reqtfm(req));
+	struct chachapoly_req_ctx *rctx = aead_request_ctx(req);
+	struct poly_req *preq = &rctx->u.poly;
+	int err;
+
+	ahash_request_set_callback(&preq->req, aead_request_flags(req),
+				   poly_ad_done, req);
+	ahash_request_set_tfm(&preq->req, ctx->poly);
+	ahash_request_set_crypt(&preq->req, req->assoc, NULL, req->assoclen);
+
+	err = crypto_ahash_update(&preq->req);
+	if (err)
+		return err;
+
+	return poly_adpad(req);
+}
+
+static void poly_setkey_done(struct crypto_async_request *areq, int err)
+{
+	async_done_continue(areq->data, err, poly_ad);
+}
+
+static int poly_setkey(struct aead_request *req)
+{
+	struct chachapoly_ctx *ctx = crypto_aead_ctx(crypto_aead_reqtfm(req));
+	struct chachapoly_req_ctx *rctx = aead_request_ctx(req);
+	struct poly_req *preq = &rctx->u.poly;
+	int err;
+
+	sg_init_table(preq->src, 1);
+	sg_set_buf(preq->src, rctx->key, sizeof(rctx->key));
+
+	ahash_request_set_callback(&preq->req, aead_request_flags(req),
+				   poly_setkey_done, req);
+	ahash_request_set_tfm(&preq->req, ctx->poly);
+	ahash_request_set_crypt(&preq->req, preq->src, NULL, sizeof(rctx->key));
+
+	err = crypto_ahash_update(&preq->req);
+	if (err)
+		return err;
+
+	return poly_ad(req);
+}
+
+static void poly_init_done(struct crypto_async_request *areq, int err)
+{
+	async_done_continue(areq->data, err, poly_setkey);
+}
+
+static int poly_init(struct aead_request *req)
+{
+	struct chachapoly_ctx *ctx = crypto_aead_ctx(crypto_aead_reqtfm(req));
+	struct chachapoly_req_ctx *rctx = aead_request_ctx(req);
+	struct poly_req *preq = &rctx->u.poly;
+	int err;
+
+	ahash_request_set_callback(&preq->req, aead_request_flags(req),
+				   poly_init_done, req);
+	ahash_request_set_tfm(&preq->req, ctx->poly);
+
+	err = crypto_ahash_init(&preq->req);
+	if (err)
+		return err;
+
+	return poly_setkey(req);
+}
+
+static void poly_genkey_done(struct crypto_async_request *areq, int err)
+{
+	async_done_continue(areq->data, err, poly_init);
+}
+
+static int poly_genkey(struct aead_request *req)
+{
+	struct chachapoly_ctx *ctx = crypto_aead_ctx(crypto_aead_reqtfm(req));
+	struct chachapoly_req_ctx *rctx = aead_request_ctx(req);
+	struct chacha_req *creq = &rctx->u.chacha;
+	int err;
+
+	sg_init_table(creq->src, 1);
+	memset(rctx->key, 0, sizeof(rctx->key));
+	sg_set_buf(creq->src, rctx->key, sizeof(rctx->key));
+
+	chacha_iv(creq->iv, req, 0);
+
+	ablkcipher_request_set_callback(&creq->req, aead_request_flags(req),
+					poly_genkey_done, req);
+	ablkcipher_request_set_tfm(&creq->req, ctx->chacha);
+	ablkcipher_request_set_crypt(&creq->req, creq->src, creq->src,
+				     POLY1305_KEY_SIZE, creq->iv);
+
+	err = crypto_ablkcipher_decrypt(&creq->req);
+	if (err)
+		return err;
+
+	return poly_init(req);
+}
+
+static void chacha_encrypt_done(struct crypto_async_request *areq, int err)
+{
+	async_done_continue(areq->data, err, poly_genkey);
+}
+
+static int chacha_encrypt(struct aead_request *req)
+{
+	struct chachapoly_ctx *ctx = crypto_aead_ctx(crypto_aead_reqtfm(req));
+	struct chachapoly_req_ctx *rctx = aead_request_ctx(req);
+	struct chacha_req *creq = &rctx->u.chacha;
+	int err;
+
+	chacha_iv(creq->iv, req, 1);
+
+	ablkcipher_request_set_callback(&creq->req, aead_request_flags(req),
+					chacha_encrypt_done, req);
+	ablkcipher_request_set_tfm(&creq->req, ctx->chacha);
+	ablkcipher_request_set_crypt(&creq->req, req->src, req->dst,
+				     req->cryptlen, creq->iv);
+	err = crypto_ablkcipher_encrypt(&creq->req);
+	if (err)
+		return err;
+
+	return poly_genkey(req);
+}
+
+static int chachapoly_encrypt(struct aead_request *req)
+{
+	struct chachapoly_req_ctx *rctx = aead_request_ctx(req);
+
+	rctx->cryptlen = req->cryptlen;
+
+	/* encrypt call chain:
+	 * - chacha_encrypt/done()
+	 * - poly_genkey/done()
+	 * - poly_init/done()
+	 * - poly_setkey/done()
+	 * - poly_ad/done()
+	 * - poly_adpad/done()
+	 * - poly_cipher/done()
+	 * - poly_cipherpad/done()
+	 * - poly_tail/done/continue()
+	 * - poly_copy_tag()
+	 */
+	return chacha_encrypt(req);
+}
+
+static int chachapoly_decrypt(struct aead_request *req)
+{
+	struct chachapoly_req_ctx *rctx = aead_request_ctx(req);
+
+	if (req->cryptlen < POLY1305_DIGEST_SIZE)
+		return -EINVAL;
+	rctx->cryptlen = req->cryptlen - POLY1305_DIGEST_SIZE;
+
+	/* decrypt call chain:
+	 * - poly_genkey/done()
+	 * - poly_init/done()
+	 * - poly_setkey/done()
+	 * - poly_ad/done()
+	 * - poly_adpad/done()
+	 * - poly_cipher/done()
+	 * - poly_cipherpad/done()
+	 * - poly_tail/done/continue()
+	 * - chacha_decrypt/done()
+	 * - poly_verify_tag()
+	 */
+	return poly_genkey(req);
+}
+
+static int chachapoly_setkey(struct crypto_aead *aead, const u8 *key,
+			     unsigned int keylen)
+{
+	struct chachapoly_ctx *ctx = crypto_aead_ctx(aead);
+	int err;
+
+	if (keylen != ctx->saltlen + CHACHA20_KEY_SIZE)
+		return -EINVAL;
+
+	keylen -= ctx->saltlen;
+	memcpy(ctx->salt, key + keylen, ctx->saltlen);
+
+	crypto_ablkcipher_clear_flags(ctx->chacha, CRYPTO_TFM_REQ_MASK);
+	crypto_ablkcipher_set_flags(ctx->chacha, crypto_aead_get_flags(aead) &
+				    CRYPTO_TFM_REQ_MASK);
+
+	err = crypto_ablkcipher_setkey(ctx->chacha, key, keylen);
+	crypto_aead_set_flags(aead, crypto_ablkcipher_get_flags(ctx->chacha) &
+			      CRYPTO_TFM_RES_MASK);
+	return err;
+}
+
+static int chachapoly_setauthsize(struct crypto_aead *tfm,
+				  unsigned int authsize)
+{
+	if (authsize != POLY1305_DIGEST_SIZE)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int chachapoly_init(struct crypto_tfm *tfm)
+{
+	struct crypto_instance *inst = (void *)tfm->__crt_alg;
+	struct chachapoly_instance_ctx *ictx = crypto_instance_ctx(inst);
+	struct chachapoly_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct crypto_ablkcipher *chacha;
+	struct crypto_ahash *poly;
+	unsigned long align;
+
+	poly = crypto_spawn_ahash(&ictx->poly);
+	if (IS_ERR(poly))
+		return PTR_ERR(poly);
+
+	chacha = crypto_spawn_skcipher(&ictx->chacha);
+	if (IS_ERR(chacha)) {
+		crypto_free_ahash(poly);
+		return PTR_ERR(chacha);
+	}
+
+	ctx->chacha = chacha;
+	ctx->poly = poly;
+	ctx->saltlen = ictx->saltlen;
+
+	align = crypto_tfm_alg_alignmask(tfm);
+	align &= ~(crypto_tfm_ctx_alignment() - 1);
+	crypto_aead_set_reqsize(__crypto_aead_cast(tfm),
+				align + offsetof(struct chachapoly_req_ctx, u) +
+				max(offsetof(struct chacha_req, req) +
+				    sizeof(struct ablkcipher_request) +
+				    crypto_ablkcipher_reqsize(chacha),
+				    offsetof(struct poly_req, req) +
+				    sizeof(struct ahash_request) +
+				    crypto_ahash_reqsize(poly)));
+
+	return 0;
+}
+
+static void chachapoly_exit(struct crypto_tfm *tfm)
+{
+	struct chachapoly_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	crypto_free_ahash(ctx->poly);
+	crypto_free_ablkcipher(ctx->chacha);
+}
+
+static struct crypto_instance *chachapoly_alloc(struct rtattr **tb,
+						const char *name,
+						unsigned int ivsize)
+{
+	struct crypto_attr_type *algt;
+	struct crypto_instance *inst;
+	struct crypto_alg *chacha;
+	struct crypto_alg *poly;
+	struct ahash_alg *poly_ahash;
+	struct chachapoly_instance_ctx *ctx;
+	const char *chacha_name, *poly_name;
+	int err;
+
+	if (ivsize > CHACHAPOLY_IV_SIZE)
+		return ERR_PTR(-EINVAL);
+
+	algt = crypto_get_attr_type(tb);
+	if (IS_ERR(algt))
+		return ERR_CAST(algt);
+
+	if ((algt->type ^ CRYPTO_ALG_TYPE_AEAD) & algt->mask)
+		return ERR_PTR(-EINVAL);
+
+	chacha_name = crypto_attr_alg_name(tb[1]);
+	if (IS_ERR(chacha_name))
+		return ERR_CAST(chacha_name);
+	poly_name = crypto_attr_alg_name(tb[2]);
+	if (IS_ERR(poly_name))
+		return ERR_CAST(poly_name);
+
+	poly = crypto_find_alg(poly_name, &crypto_ahash_type,
+			       CRYPTO_ALG_TYPE_HASH,
+			       CRYPTO_ALG_TYPE_AHASH_MASK);
+	if (IS_ERR(poly))
+		return ERR_CAST(poly);
+
+	err = -ENOMEM;
+	inst = kzalloc(sizeof(*inst) + sizeof(*ctx), GFP_KERNEL);
+	if (!inst)
+		goto out_put_poly;
+
+	ctx = crypto_instance_ctx(inst);
+	ctx->saltlen = CHACHAPOLY_IV_SIZE - ivsize;
+	poly_ahash = container_of(poly, struct ahash_alg, halg.base);
+	err = crypto_init_ahash_spawn(&ctx->poly, &poly_ahash->halg, inst);
+	if (err)
+		goto err_free_inst;
+
+	crypto_set_skcipher_spawn(&ctx->chacha, inst);
+	err = crypto_grab_skcipher(&ctx->chacha, chacha_name, 0,
+				   crypto_requires_sync(algt->type,
+							algt->mask));
+	if (err)
+		goto err_drop_poly;
+
+	chacha = crypto_skcipher_spawn_alg(&ctx->chacha);
+
+	err = -EINVAL;
+	/* Need 16-byte IV size, including Initial Block Counter value */
+	if (chacha->cra_ablkcipher.ivsize != CHACHA20_IV_SIZE)
+		goto out_drop_chacha;
+	/* Not a stream cipher? */
+	if (chacha->cra_blocksize != 1)
+		goto out_drop_chacha;
+
+	err = -ENAMETOOLONG;
+	if (snprintf(inst->alg.cra_name, CRYPTO_MAX_ALG_NAME,
+		     "%s(%s,%s)", name, chacha_name,
+		     poly_name) >= CRYPTO_MAX_ALG_NAME)
+		goto out_drop_chacha;
+	if (snprintf(inst->alg.cra_driver_name, CRYPTO_MAX_ALG_NAME,
+		     "%s(%s,%s)", name, chacha->cra_driver_name,
+		     poly->cra_driver_name) >= CRYPTO_MAX_ALG_NAME)
+		goto out_drop_chacha;
+
+	inst->alg.cra_flags = CRYPTO_ALG_TYPE_AEAD;
+	inst->alg.cra_flags |= (chacha->cra_flags |
+				poly->cra_flags) & CRYPTO_ALG_ASYNC;
+	inst->alg.cra_priority = (chacha->cra_priority +
+				  poly->cra_priority) / 2;
+	inst->alg.cra_blocksize = 1;
+	inst->alg.cra_alignmask = chacha->cra_alignmask | poly->cra_alignmask;
+	inst->alg.cra_type = &crypto_nivaead_type;
+	inst->alg.cra_aead.ivsize = ivsize;
+	inst->alg.cra_aead.maxauthsize = POLY1305_DIGEST_SIZE;
+	inst->alg.cra_ctxsize = sizeof(struct chachapoly_ctx) + ctx->saltlen;
+	inst->alg.cra_init = chachapoly_init;
+	inst->alg.cra_exit = chachapoly_exit;
+	inst->alg.cra_aead.encrypt = chachapoly_encrypt;
+	inst->alg.cra_aead.decrypt = chachapoly_decrypt;
+	inst->alg.cra_aead.setkey = chachapoly_setkey;
+	inst->alg.cra_aead.setauthsize = chachapoly_setauthsize;
+	inst->alg.cra_aead.geniv = "seqiv";
+
+out:
+	crypto_mod_put(poly);
+	return inst;
+
+out_drop_chacha:
+	crypto_drop_skcipher(&ctx->chacha);
+err_drop_poly:
+	crypto_drop_ahash(&ctx->poly);
+err_free_inst:
+	kfree(inst);
+out_put_poly:
+	inst = ERR_PTR(err);
+	goto out;
+}
+
+static struct crypto_instance *rfc7539_alloc(struct rtattr **tb)
+{
+	return chachapoly_alloc(tb, "rfc7539", 12);
+}
+
+static struct crypto_instance *rfc7539esp_alloc(struct rtattr **tb)
+{
+	return chachapoly_alloc(tb, "rfc7539esp", 8);
+}
+
+static void chachapoly_free(struct crypto_instance *inst)
+{
+	struct chachapoly_instance_ctx *ctx = crypto_instance_ctx(inst);
+
+	crypto_drop_skcipher(&ctx->chacha);
+	crypto_drop_ahash(&ctx->poly);
+	kfree(inst);
+}
+
+static struct crypto_template rfc7539_tmpl = {
+	.name = "rfc7539",
+	.alloc = rfc7539_alloc,
+	.free = chachapoly_free,
+	.module = THIS_MODULE,
+};
+
+static struct crypto_template rfc7539esp_tmpl = {
+	.name = "rfc7539esp",
+	.alloc = rfc7539esp_alloc,
+	.free = chachapoly_free,
+	.module = THIS_MODULE,
+};
+
+static int __init chacha20poly1305_module_init(void)
+{
+	int err;
+
+	err = crypto_register_template(&rfc7539_tmpl);
+	if (err)
+		return err;
+
+	err = crypto_register_template(&rfc7539esp_tmpl);
+	if (err)
+		crypto_unregister_template(&rfc7539_tmpl);
+
+	return err;
+}
+
+static void __exit chacha20poly1305_module_exit(void)
+{
+	crypto_unregister_template(&rfc7539esp_tmpl);
+	crypto_unregister_template(&rfc7539_tmpl);
+}
+
+module_init(chacha20poly1305_module_init);
+module_exit(chacha20poly1305_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Martin Willi <martin@strongswan.org>");
+MODULE_DESCRIPTION("ChaCha20-Poly1305 AEAD");
+MODULE_ALIAS_CRYPTO("chacha20poly1305");
+MODULE_ALIAS_CRYPTO("rfc7539");
+MODULE_ALIAS_CRYPTO("rfc7539esp");
diff --git a/crypto/chainiv.c b/crypto/chainiv.c
index 63c17d5992f7..b4340018c8d4 100644
--- a/crypto/chainiv.c
+++ b/crypto/chainiv.c
@@ -80,44 +80,37 @@ unlock:
 	return err;
 }
 
-static int chainiv_givencrypt_first(struct skcipher_givcrypt_request *req)
+static int chainiv_init_common(struct crypto_tfm *tfm, char iv[])
 {
-	struct crypto_ablkcipher *geniv = skcipher_givcrypt_reqtfm(req);
-	struct chainiv_ctx *ctx = crypto_ablkcipher_ctx(geniv);
+	struct crypto_ablkcipher *geniv = __crypto_ablkcipher_cast(tfm);
 	int err = 0;
 
-	spin_lock_bh(&ctx->lock);
-	if (crypto_ablkcipher_crt(geniv)->givencrypt !=
-	    chainiv_givencrypt_first)
-		goto unlock;
-
-	crypto_ablkcipher_crt(geniv)->givencrypt = chainiv_givencrypt;
-	err = crypto_rng_get_bytes(crypto_default_rng, ctx->iv,
-				   crypto_ablkcipher_ivsize(geniv));
-
-unlock:
-	spin_unlock_bh(&ctx->lock);
-
-	if (err)
-		return err;
-
-	return chainiv_givencrypt(req);
-}
-
-static int chainiv_init_common(struct crypto_tfm *tfm)
-{
 	tfm->crt_ablkcipher.reqsize = sizeof(struct ablkcipher_request);
 
-	return skcipher_geniv_init(tfm);
+	if (iv) {
+		err = crypto_rng_get_bytes(crypto_default_rng, iv,
+					   crypto_ablkcipher_ivsize(geniv));
+		crypto_put_default_rng();
+	}
+
+	return err ?: skcipher_geniv_init(tfm);
 }
 
 static int chainiv_init(struct crypto_tfm *tfm)
 {
+	struct crypto_ablkcipher *geniv = __crypto_ablkcipher_cast(tfm);
 	struct chainiv_ctx *ctx = crypto_tfm_ctx(tfm);
+	char *iv;
 
 	spin_lock_init(&ctx->lock);
 
-	return chainiv_init_common(tfm);
+	iv = NULL;
+	if (!crypto_get_default_rng()) {
+		crypto_ablkcipher_crt(geniv)->givencrypt = chainiv_givencrypt;
+		iv = ctx->iv;
+	}
+
+	return chainiv_init_common(tfm, iv);
 }
 
 static int async_chainiv_schedule_work(struct async_chainiv_ctx *ctx)
@@ -205,33 +198,6 @@ postpone:
 	return async_chainiv_postpone_request(req);
 }
 
-static int async_chainiv_givencrypt_first(struct skcipher_givcrypt_request *req)
-{
-	struct crypto_ablkcipher *geniv = skcipher_givcrypt_reqtfm(req);
-	struct async_chainiv_ctx *ctx = crypto_ablkcipher_ctx(geniv);
-	int err = 0;
-
-	if (test_and_set_bit(CHAINIV_STATE_INUSE, &ctx->state))
-		goto out;
-
-	if (crypto_ablkcipher_crt(geniv)->givencrypt !=
-	    async_chainiv_givencrypt_first)
-		goto unlock;
-
-	crypto_ablkcipher_crt(geniv)->givencrypt = async_chainiv_givencrypt;
-	err = crypto_rng_get_bytes(crypto_default_rng, ctx->iv,
-				   crypto_ablkcipher_ivsize(geniv));
-
-unlock:
-	clear_bit(CHAINIV_STATE_INUSE, &ctx->state);
-
-	if (err)
-		return err;
-
-out:
-	return async_chainiv_givencrypt(req);
-}
-
 static void async_chainiv_do_postponed(struct work_struct *work)
 {
 	struct async_chainiv_ctx *ctx = container_of(work,
@@ -263,14 +229,23 @@ static void async_chainiv_do_postponed(struct work_struct *work)
 
 static int async_chainiv_init(struct crypto_tfm *tfm)
 {
+	struct crypto_ablkcipher *geniv = __crypto_ablkcipher_cast(tfm);
 	struct async_chainiv_ctx *ctx = crypto_tfm_ctx(tfm);
+	char *iv;
 
 	spin_lock_init(&ctx->lock);
 
 	crypto_init_queue(&ctx->queue, 100);
 	INIT_WORK(&ctx->postponed, async_chainiv_do_postponed);
 
-	return chainiv_init_common(tfm);
+	iv = NULL;
+	if (!crypto_get_default_rng()) {
+		crypto_ablkcipher_crt(geniv)->givencrypt =
+			async_chainiv_givencrypt;
+		iv = ctx->iv;
+	}
+
+	return chainiv_init_common(tfm, iv);
 }
 
 static void async_chainiv_exit(struct crypto_tfm *tfm)
@@ -288,21 +263,14 @@ static struct crypto_instance *chainiv_alloc(struct rtattr **tb)
 {
 	struct crypto_attr_type *algt;
 	struct crypto_instance *inst;
-	int err;
 
 	algt = crypto_get_attr_type(tb);
 	if (IS_ERR(algt))
 		return ERR_CAST(algt);
 
-	err = crypto_get_default_rng();
-	if (err)
-		return ERR_PTR(err);
-
 	inst = skcipher_geniv_alloc(&chainiv_tmpl, tb, 0, 0);
 	if (IS_ERR(inst))
-		goto put_rng;
-
-	inst->alg.cra_ablkcipher.givencrypt = chainiv_givencrypt_first;
+		goto out;
 
 	inst->alg.cra_init = chainiv_init;
 	inst->alg.cra_exit = skcipher_geniv_exit;
@@ -312,9 +280,6 @@ static struct crypto_instance *chainiv_alloc(struct rtattr **tb)
 	if (!crypto_requires_sync(algt->type, algt->mask)) {
 		inst->alg.cra_flags |= CRYPTO_ALG_ASYNC;
 
-		inst->alg.cra_ablkcipher.givencrypt =
-			async_chainiv_givencrypt_first;
-
 		inst->alg.cra_init = async_chainiv_init;
 		inst->alg.cra_exit = async_chainiv_exit;
 
@@ -325,22 +290,12 @@ static struct crypto_instance *chainiv_alloc(struct rtattr **tb)
 
 out:
 	return inst;
-
-put_rng:
-	crypto_put_default_rng();
-	goto out;
-}
-
-static void chainiv_free(struct crypto_instance *inst)
-{
-	skcipher_geniv_free(inst);
-	crypto_put_default_rng();
 }
 
 static struct crypto_template chainiv_tmpl = {
 	.name = "chainiv",
 	.alloc = chainiv_alloc,
-	.free = chainiv_free,
+	.free = skcipher_geniv_free,
 	.module = THIS_MODULE,
 };
 
diff --git a/crypto/cryptd.c b/crypto/cryptd.c
index b0602ba03111..22ba81f76764 100644
--- a/crypto/cryptd.c
+++ b/crypto/cryptd.c
@@ -295,6 +295,23 @@ static void cryptd_blkcipher_exit_tfm(struct crypto_tfm *tfm)
 	crypto_free_blkcipher(ctx->child);
 }
 
+static int cryptd_init_instance(struct crypto_instance *inst,
+				struct crypto_alg *alg)
+{
+	if (snprintf(inst->alg.cra_driver_name, CRYPTO_MAX_ALG_NAME,
+		     "cryptd(%s)",
+		     alg->cra_driver_name) >= CRYPTO_MAX_ALG_NAME)
+		return -ENAMETOOLONG;
+
+	memcpy(inst->alg.cra_name, alg->cra_name, CRYPTO_MAX_ALG_NAME);
+
+	inst->alg.cra_priority = alg->cra_priority + 50;
+	inst->alg.cra_blocksize = alg->cra_blocksize;
+	inst->alg.cra_alignmask = alg->cra_alignmask;
+
+	return 0;
+}
+
 static void *cryptd_alloc_instance(struct crypto_alg *alg, unsigned int head,
 				   unsigned int tail)
 {
@@ -308,17 +325,10 @@ static void *cryptd_alloc_instance(struct crypto_alg *alg, unsigned int head,
 
 	inst = (void *)(p + head);
 
-	err = -ENAMETOOLONG;
-	if (snprintf(inst->alg.cra_driver_name, CRYPTO_MAX_ALG_NAME,
-		     "cryptd(%s)", alg->cra_driver_name) >= CRYPTO_MAX_ALG_NAME)
+	err = cryptd_init_instance(inst, alg);
+	if (err)
 		goto out_free_inst;
 
-	memcpy(inst->alg.cra_name, alg->cra_name, CRYPTO_MAX_ALG_NAME);
-
-	inst->alg.cra_priority = alg->cra_priority + 50;
-	inst->alg.cra_blocksize = alg->cra_blocksize;
-	inst->alg.cra_alignmask = alg->cra_alignmask;
-
 out:
 	return p;
 
@@ -654,6 +664,24 @@ out_put_alg:
 	return err;
 }
 
+static int cryptd_aead_setkey(struct crypto_aead *parent,
+			      const u8 *key, unsigned int keylen)
+{
+	struct cryptd_aead_ctx *ctx = crypto_aead_ctx(parent);
+	struct crypto_aead *child = ctx->child;
+
+	return crypto_aead_setkey(child, key, keylen);
+}
+
+static int cryptd_aead_setauthsize(struct crypto_aead *parent,
+				   unsigned int authsize)
+{
+	struct cryptd_aead_ctx *ctx = crypto_aead_ctx(parent);
+	struct crypto_aead *child = ctx->child;
+
+	return crypto_aead_setauthsize(child, authsize);
+}
+
 static void cryptd_aead_crypt(struct aead_request *req,
 			struct crypto_aead *child,
 			int err,
@@ -715,27 +743,26 @@ static int cryptd_aead_decrypt_enqueue(struct aead_request *req)
 	return cryptd_aead_enqueue(req, cryptd_aead_decrypt );
 }
 
-static int cryptd_aead_init_tfm(struct crypto_tfm *tfm)
+static int cryptd_aead_init_tfm(struct crypto_aead *tfm)
 {
-	struct crypto_instance *inst = crypto_tfm_alg_instance(tfm);
-	struct aead_instance_ctx *ictx = crypto_instance_ctx(inst);
+	struct aead_instance *inst = aead_alg_instance(tfm);
+	struct aead_instance_ctx *ictx = aead_instance_ctx(inst);
 	struct crypto_aead_spawn *spawn = &ictx->aead_spawn;
-	struct cryptd_aead_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct cryptd_aead_ctx *ctx = crypto_aead_ctx(tfm);
 	struct crypto_aead *cipher;
 
 	cipher = crypto_spawn_aead(spawn);
 	if (IS_ERR(cipher))
 		return PTR_ERR(cipher);
 
-	crypto_aead_set_flags(cipher, CRYPTO_TFM_REQ_MAY_SLEEP);
 	ctx->child = cipher;
-	tfm->crt_aead.reqsize = sizeof(struct cryptd_aead_request_ctx);
+	crypto_aead_set_reqsize(tfm, sizeof(struct cryptd_aead_request_ctx));
 	return 0;
 }
 
-static void cryptd_aead_exit_tfm(struct crypto_tfm *tfm)
+static void cryptd_aead_exit_tfm(struct crypto_aead *tfm)
 {
-	struct cryptd_aead_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct cryptd_aead_ctx *ctx = crypto_aead_ctx(tfm);
 	crypto_free_aead(ctx->child);
 }
 
@@ -744,57 +771,57 @@ static int cryptd_create_aead(struct crypto_template *tmpl,
 			      struct cryptd_queue *queue)
 {
 	struct aead_instance_ctx *ctx;
-	struct crypto_instance *inst;
-	struct crypto_alg *alg;
-	u32 type = CRYPTO_ALG_TYPE_AEAD;
-	u32 mask = CRYPTO_ALG_TYPE_MASK;
+	struct aead_instance *inst;
+	struct aead_alg *alg;
+	const char *name;
+	u32 type = 0;
+	u32 mask = 0;
 	int err;
 
 	cryptd_check_internal(tb, &type, &mask);
 
-	alg = crypto_get_attr_alg(tb, type, mask);
-        if (IS_ERR(alg))
-		return PTR_ERR(alg);
+	name = crypto_attr_alg_name(tb[1]);
+	if (IS_ERR(name))
+		return PTR_ERR(name);
 
-	inst = cryptd_alloc_instance(alg, 0, sizeof(*ctx));
-	err = PTR_ERR(inst);
-	if (IS_ERR(inst))
-		goto out_put_alg;
+	inst = kzalloc(sizeof(*inst) + sizeof(*ctx), GFP_KERNEL);
+	if (!inst)
+		return -ENOMEM;
 
-	ctx = crypto_instance_ctx(inst);
+	ctx = aead_instance_ctx(inst);
 	ctx->queue = queue;
 
-	err = crypto_init_spawn(&ctx->aead_spawn.base, alg, inst,
-			CRYPTO_ALG_TYPE_MASK | CRYPTO_ALG_ASYNC);
+	crypto_set_aead_spawn(&ctx->aead_spawn, aead_crypto_instance(inst));
+	err = crypto_grab_aead(&ctx->aead_spawn, name, type, mask);
 	if (err)
 		goto out_free_inst;
 
-	type = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC;
-	if (alg->cra_flags & CRYPTO_ALG_INTERNAL)
-		type |= CRYPTO_ALG_INTERNAL;
-	inst->alg.cra_flags = type;
-	inst->alg.cra_type = alg->cra_type;
-	inst->alg.cra_ctxsize = sizeof(struct cryptd_aead_ctx);
-	inst->alg.cra_init = cryptd_aead_init_tfm;
-	inst->alg.cra_exit = cryptd_aead_exit_tfm;
-	inst->alg.cra_aead.setkey      = alg->cra_aead.setkey;
-	inst->alg.cra_aead.setauthsize = alg->cra_aead.setauthsize;
-	inst->alg.cra_aead.geniv       = alg->cra_aead.geniv;
-	inst->alg.cra_aead.ivsize      = alg->cra_aead.ivsize;
-	inst->alg.cra_aead.maxauthsize = alg->cra_aead.maxauthsize;
-	inst->alg.cra_aead.encrypt     = cryptd_aead_encrypt_enqueue;
-	inst->alg.cra_aead.decrypt     = cryptd_aead_decrypt_enqueue;
-	inst->alg.cra_aead.givencrypt  = alg->cra_aead.givencrypt;
-	inst->alg.cra_aead.givdecrypt  = alg->cra_aead.givdecrypt;
+	alg = crypto_spawn_aead_alg(&ctx->aead_spawn);
+	err = cryptd_init_instance(aead_crypto_instance(inst), &alg->base);
+	if (err)
+		goto out_drop_aead;
 
-	err = crypto_register_instance(tmpl, inst);
+	inst->alg.base.cra_flags = CRYPTO_ALG_ASYNC |
+				   (alg->base.cra_flags & CRYPTO_ALG_INTERNAL);
+	inst->alg.base.cra_ctxsize = sizeof(struct cryptd_aead_ctx);
+
+	inst->alg.ivsize = crypto_aead_alg_ivsize(alg);
+	inst->alg.maxauthsize = crypto_aead_alg_maxauthsize(alg);
+
+	inst->alg.init = cryptd_aead_init_tfm;
+	inst->alg.exit = cryptd_aead_exit_tfm;
+	inst->alg.setkey = cryptd_aead_setkey;
+	inst->alg.setauthsize = cryptd_aead_setauthsize;
+	inst->alg.encrypt = cryptd_aead_encrypt_enqueue;
+	inst->alg.decrypt = cryptd_aead_decrypt_enqueue;
+
+	err = aead_register_instance(tmpl, inst);
 	if (err) {
-		crypto_drop_spawn(&ctx->aead_spawn.base);
+out_drop_aead:
+		crypto_drop_aead(&ctx->aead_spawn);
 out_free_inst:
 		kfree(inst);
 	}
-out_put_alg:
-	crypto_mod_put(alg);
 	return err;
 }
 
@@ -832,8 +859,8 @@ static void cryptd_free(struct crypto_instance *inst)
 		kfree(ahash_instance(inst));
 		return;
 	case CRYPTO_ALG_TYPE_AEAD:
-		crypto_drop_spawn(&aead_ctx->aead_spawn.base);
-		kfree(inst);
+		crypto_drop_aead(&aead_ctx->aead_spawn);
+		kfree(aead_instance(inst));
 		return;
 	default:
 		crypto_drop_spawn(&ctx->spawn);
diff --git a/crypto/crypto_null.c b/crypto/crypto_null.c
index a20319132e33..941c9a434d50 100644
--- a/crypto/crypto_null.c
+++ b/crypto/crypto_null.c
@@ -25,6 +25,10 @@
 #include <linux/mm.h>
 #include <linux/string.h>
 
+static DEFINE_MUTEX(crypto_default_null_skcipher_lock);
+static struct crypto_blkcipher *crypto_default_null_skcipher;
+static int crypto_default_null_skcipher_refcnt;
+
 static int null_compress(struct crypto_tfm *tfm, const u8 *src,
 			 unsigned int slen, u8 *dst, unsigned int *dlen)
 {
@@ -149,6 +153,41 @@ MODULE_ALIAS_CRYPTO("compress_null");
 MODULE_ALIAS_CRYPTO("digest_null");
 MODULE_ALIAS_CRYPTO("cipher_null");
 
+struct crypto_blkcipher *crypto_get_default_null_skcipher(void)
+{
+	struct crypto_blkcipher *tfm;
+
+	mutex_lock(&crypto_default_null_skcipher_lock);
+	tfm = crypto_default_null_skcipher;
+
+	if (!tfm) {
+		tfm = crypto_alloc_blkcipher("ecb(cipher_null)", 0, 0);
+		if (IS_ERR(tfm))
+			goto unlock;
+
+		crypto_default_null_skcipher = tfm;
+	}
+
+	crypto_default_null_skcipher_refcnt++;
+
+unlock:
+	mutex_unlock(&crypto_default_null_skcipher_lock);
+
+	return tfm;
+}
+EXPORT_SYMBOL_GPL(crypto_get_default_null_skcipher);
+
+void crypto_put_default_null_skcipher(void)
+{
+	mutex_lock(&crypto_default_null_skcipher_lock);
+	if (!--crypto_default_null_skcipher_refcnt) {
+		crypto_free_blkcipher(crypto_default_null_skcipher);
+		crypto_default_null_skcipher = NULL;
+	}
+	mutex_unlock(&crypto_default_null_skcipher_lock);
+}
+EXPORT_SYMBOL_GPL(crypto_put_default_null_skcipher);
+
 static int __init crypto_null_mod_init(void)
 {
 	int ret = 0;
diff --git a/crypto/crypto_user.c b/crypto/crypto_user.c
index 41dfe762b7fb..08ea2867fc8a 100644
--- a/crypto/crypto_user.c
+++ b/crypto/crypto_user.c
@@ -27,6 +27,8 @@
 #include <net/net_namespace.h>
 #include <crypto/internal/aead.h>
 #include <crypto/internal/skcipher.h>
+#include <crypto/internal/rng.h>
+#include <crypto/akcipher.h>
 
 #include "internal.h"
 
@@ -110,6 +112,21 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
+static int crypto_report_akcipher(struct sk_buff *skb, struct crypto_alg *alg)
+{
+	struct crypto_report_akcipher rakcipher;
+
+	strncpy(rakcipher.type, "akcipher", sizeof(rakcipher.type));
+
+	if (nla_put(skb, CRYPTOCFGA_REPORT_AKCIPHER,
+		    sizeof(struct crypto_report_akcipher), &rakcipher))
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -EMSGSIZE;
+}
+
 static int crypto_report_one(struct crypto_alg *alg,
 			     struct crypto_user_alg *ualg, struct sk_buff *skb)
 {
@@ -154,6 +171,12 @@ static int crypto_report_one(struct crypto_alg *alg,
 			goto nla_put_failure;
 
 		break;
+
+	case CRYPTO_ALG_TYPE_AKCIPHER:
+		if (crypto_report_akcipher(skb, alg))
+			goto nla_put_failure;
+
+		break;
 	}
 
 out:
@@ -450,13 +473,21 @@ static int crypto_add_alg(struct sk_buff *skb, struct nlmsghdr *nlh,
 	return 0;
 }
 
+static int crypto_del_rng(struct sk_buff *skb, struct nlmsghdr *nlh,
+			  struct nlattr **attrs)
+{
+	if (!netlink_capable(skb, CAP_NET_ADMIN))
+		return -EPERM;
+	return crypto_del_default_rng();
+}
+
 #define MSGSIZE(type) sizeof(struct type)
 
 static const int crypto_msg_min[CRYPTO_NR_MSGTYPES] = {
 	[CRYPTO_MSG_NEWALG	- CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg),
 	[CRYPTO_MSG_DELALG	- CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg),
 	[CRYPTO_MSG_UPDATEALG	- CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg),
-	[CRYPTO_MSG_GETALG	- CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg),
+	[CRYPTO_MSG_DELRNG	- CRYPTO_MSG_BASE] = 0,
 };
 
 static const struct nla_policy crypto_policy[CRYPTOCFGA_MAX+1] = {
@@ -476,6 +507,7 @@ static const struct crypto_link {
 	[CRYPTO_MSG_GETALG	- CRYPTO_MSG_BASE] = { .doit = crypto_report,
 						       .dump = crypto_dump_report,
 						       .done = crypto_dump_report_done},
+	[CRYPTO_MSG_DELRNG	- CRYPTO_MSG_BASE] = { .doit = crypto_del_rng },
 };
 
 static int crypto_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
diff --git a/crypto/drbg.c b/crypto/drbg.c
index b69409cb7e6a..a7c23146b87f 100644
--- a/crypto/drbg.c
+++ b/crypto/drbg.c
@@ -98,6 +98,7 @@
  */
 
 #include <crypto/drbg.h>
+#include <linux/kernel.h>
 
 /***************************************************************
  * Backend cipher definitions available to DRBG
@@ -190,6 +191,8 @@ static const struct drbg_core drbg_cores[] = {
 #endif /* CONFIG_CRYPTO_DRBG_HMAC */
 };
 
+static int drbg_uninstantiate(struct drbg_state *drbg);
+
 /******************************************************************
  * Generic helper functions
  ******************************************************************/
@@ -235,7 +238,7 @@ static bool drbg_fips_continuous_test(struct drbg_state *drbg,
 #ifdef CONFIG_CRYPTO_FIPS
 	int ret = 0;
 	/* skip test if we test the overall system */
-	if (drbg->test_data)
+	if (list_empty(&drbg->test_data.list))
 		return true;
 	/* only perform test in FIPS mode */
 	if (0 == fips_enabled)
@@ -487,7 +490,7 @@ static int drbg_ctr_df(struct drbg_state *drbg,
 
 out:
 	memset(iv, 0, drbg_blocklen(drbg));
-	memset(temp, 0, drbg_statelen(drbg));
+	memset(temp, 0, drbg_statelen(drbg) + drbg_blocklen(drbg));
 	memset(pad, 0, drbg_blocklen(drbg));
 	return ret;
 }
@@ -1041,6 +1044,58 @@ static struct drbg_state_ops drbg_hash_ops = {
  * Functions common for DRBG implementations
  ******************************************************************/
 
+static inline int __drbg_seed(struct drbg_state *drbg, struct list_head *seed,
+			      int reseed)
+{
+	int ret = drbg->d_ops->update(drbg, seed, reseed);
+
+	if (ret)
+		return ret;
+
+	drbg->seeded = true;
+	/* 10.1.1.2 / 10.1.1.3 step 5 */
+	drbg->reseed_ctr = 1;
+
+	return ret;
+}
+
+static void drbg_async_seed(struct work_struct *work)
+{
+	struct drbg_string data;
+	LIST_HEAD(seedlist);
+	struct drbg_state *drbg = container_of(work, struct drbg_state,
+					       seed_work);
+	unsigned int entropylen = drbg_sec_strength(drbg->core->flags);
+	unsigned char entropy[32];
+
+	BUG_ON(!entropylen);
+	BUG_ON(entropylen > sizeof(entropy));
+	get_random_bytes(entropy, entropylen);
+
+	drbg_string_fill(&data, entropy, entropylen);
+	list_add_tail(&data.list, &seedlist);
+
+	mutex_lock(&drbg->drbg_mutex);
+
+	/* If nonblocking pool is initialized, deactivate Jitter RNG */
+	crypto_free_rng(drbg->jent);
+	drbg->jent = NULL;
+
+	/* Set seeded to false so that if __drbg_seed fails the
+	 * next generate call will trigger a reseed.
+	 */
+	drbg->seeded = false;
+
+	__drbg_seed(drbg, &seedlist, true);
+
+	if (drbg->seeded)
+		drbg->reseed_threshold = drbg_max_requests(drbg);
+
+	mutex_unlock(&drbg->drbg_mutex);
+
+	memzero_explicit(entropy, entropylen);
+}
+
 /*
  * Seeding or reseeding of the DRBG
  *
@@ -1055,9 +1110,9 @@ static struct drbg_state_ops drbg_hash_ops = {
 static int drbg_seed(struct drbg_state *drbg, struct drbg_string *pers,
 		     bool reseed)
 {
-	int ret = 0;
-	unsigned char *entropy = NULL;
-	size_t entropylen = 0;
+	int ret;
+	unsigned char entropy[((32 + 16) * 2)];
+	unsigned int entropylen = drbg_sec_strength(drbg->core->flags);
 	struct drbg_string data1;
 	LIST_HEAD(seedlist);
 
@@ -1068,31 +1123,45 @@ static int drbg_seed(struct drbg_state *drbg, struct drbg_string *pers,
 		return -EINVAL;
 	}
 
-	if (drbg->test_data && drbg->test_data->testentropy) {
-		drbg_string_fill(&data1, drbg->test_data->testentropy->buf,
-				 drbg->test_data->testentropy->len);
+	if (list_empty(&drbg->test_data.list)) {
+		drbg_string_fill(&data1, drbg->test_data.buf,
+				 drbg->test_data.len);
 		pr_devel("DRBG: using test entropy\n");
 	} else {
 		/*
 		 * Gather entropy equal to the security strength of the DRBG.
 		 * With a derivation function, a nonce is required in addition
 		 * to the entropy. A nonce must be at least 1/2 of the security
-		 * strength of the DRBG in size. Thus, entropy * nonce is 3/2
+		 * strength of the DRBG in size. Thus, entropy + nonce is 3/2
 		 * of the strength. The consideration of a nonce is only
 		 * applicable during initial seeding.
 		 */
-		entropylen = drbg_sec_strength(drbg->core->flags);
-		if (!entropylen)
-			return -EFAULT;
+		BUG_ON(!entropylen);
 		if (!reseed)
 			entropylen = ((entropylen + 1) / 2) * 3;
-		pr_devel("DRBG: (re)seeding with %zu bytes of entropy\n",
-			 entropylen);
-		entropy = kzalloc(entropylen, GFP_KERNEL);
-		if (!entropy)
-			return -ENOMEM;
+		BUG_ON((entropylen * 2) > sizeof(entropy));
+
+		/* Get seed from in-kernel /dev/urandom */
 		get_random_bytes(entropy, entropylen);
-		drbg_string_fill(&data1, entropy, entropylen);
+
+		if (!drbg->jent) {
+			drbg_string_fill(&data1, entropy, entropylen);
+			pr_devel("DRBG: (re)seeding with %u bytes of entropy\n",
+				 entropylen);
+		} else {
+			/* Get seed from Jitter RNG */
+			ret = crypto_rng_get_bytes(drbg->jent,
+						   entropy + entropylen,
+						   entropylen);
+			if (ret) {
+				pr_devel("DRBG: jent failed with %d\n", ret);
+				return ret;
+			}
+
+			drbg_string_fill(&data1, entropy, entropylen * 2);
+			pr_devel("DRBG: (re)seeding with %u bytes of entropy\n",
+				 entropylen * 2);
+		}
 	}
 	list_add_tail(&data1.list, &seedlist);
 
@@ -1111,16 +1180,10 @@ static int drbg_seed(struct drbg_state *drbg, struct drbg_string *pers,
 		memset(drbg->C, 0, drbg_statelen(drbg));
 	}
 
-	ret = drbg->d_ops->update(drbg, &seedlist, reseed);
-	if (ret)
-		goto out;
+	ret = __drbg_seed(drbg, &seedlist, reseed);
 
-	drbg->seeded = true;
-	/* 10.1.1.2 / 10.1.1.3 step 5 */
-	drbg->reseed_ctr = 1;
+	memzero_explicit(entropy, entropylen * 2);
 
-out:
-	kzfree(entropy);
 	return ret;
 }
 
@@ -1136,6 +1199,8 @@ static inline void drbg_dealloc_state(struct drbg_state *drbg)
 	kzfree(drbg->scratchpad);
 	drbg->scratchpad = NULL;
 	drbg->reseed_ctr = 0;
+	drbg->d_ops = NULL;
+	drbg->core = NULL;
 #ifdef CONFIG_CRYPTO_FIPS
 	kzfree(drbg->prev);
 	drbg->prev = NULL;
@@ -1152,6 +1217,27 @@ static inline int drbg_alloc_state(struct drbg_state *drbg)
 	int ret = -ENOMEM;
 	unsigned int sb_size = 0;
 
+	switch (drbg->core->flags & DRBG_TYPE_MASK) {
+#ifdef CONFIG_CRYPTO_DRBG_HMAC
+	case DRBG_HMAC:
+		drbg->d_ops = &drbg_hmac_ops;
+		break;
+#endif /* CONFIG_CRYPTO_DRBG_HMAC */
+#ifdef CONFIG_CRYPTO_DRBG_HASH
+	case DRBG_HASH:
+		drbg->d_ops = &drbg_hash_ops;
+		break;
+#endif /* CONFIG_CRYPTO_DRBG_HASH */
+#ifdef CONFIG_CRYPTO_DRBG_CTR
+	case DRBG_CTR:
+		drbg->d_ops = &drbg_ctr_ops;
+		break;
+#endif /* CONFIG_CRYPTO_DRBG_CTR */
+	default:
+		ret = -EOPNOTSUPP;
+		goto err;
+	}
+
 	drbg->V = kmalloc(drbg_statelen(drbg), GFP_KERNEL);
 	if (!drbg->V)
 		goto err;
@@ -1181,87 +1267,14 @@ static inline int drbg_alloc_state(struct drbg_state *drbg)
 		if (!drbg->scratchpad)
 			goto err;
 	}
-	spin_lock_init(&drbg->drbg_lock);
-	return 0;
-
-err:
-	drbg_dealloc_state(drbg);
-	return ret;
-}
-
-/*
- * Strategy to avoid holding long term locks: generate a shadow copy of DRBG
- * and perform all operations on this shadow copy. After finishing, restore
- * the updated state of the shadow copy into original drbg state. This way,
- * only the read and write operations of the original drbg state must be
- * locked
- */
-static inline void drbg_copy_drbg(struct drbg_state *src,
-				  struct drbg_state *dst)
-{
-	if (!src || !dst)
-		return;
-	memcpy(dst->V, src->V, drbg_statelen(src));
-	memcpy(dst->C, src->C, drbg_statelen(src));
-	dst->reseed_ctr = src->reseed_ctr;
-	dst->seeded = src->seeded;
-	dst->pr = src->pr;
-#ifdef CONFIG_CRYPTO_FIPS
-	dst->fips_primed = src->fips_primed;
-	memcpy(dst->prev, src->prev, drbg_blocklen(src));
-#endif
-	/*
-	 * Not copied:
-	 * scratchpad is initialized drbg_alloc_state;
-	 * priv_data is initialized with call to crypto_init;
-	 * d_ops and core are set outside, as these parameters are const;
-	 * test_data is set outside to prevent it being copied back.
-	 */
-}
-
-static int drbg_make_shadow(struct drbg_state *drbg, struct drbg_state **shadow)
-{
-	int ret = -ENOMEM;
-	struct drbg_state *tmp = NULL;
-
-	tmp = kzalloc(sizeof(struct drbg_state), GFP_KERNEL);
-	if (!tmp)
-		return -ENOMEM;
-
-	/* read-only data as they are defined as const, no lock needed */
-	tmp->core = drbg->core;
-	tmp->d_ops = drbg->d_ops;
 
-	ret = drbg_alloc_state(tmp);
-	if (ret)
-		goto err;
-
-	spin_lock_bh(&drbg->drbg_lock);
-	drbg_copy_drbg(drbg, tmp);
-	/* only make a link to the test buffer, as we only read that data */
-	tmp->test_data = drbg->test_data;
-	spin_unlock_bh(&drbg->drbg_lock);
-	*shadow = tmp;
 	return 0;
 
 err:
-	kzfree(tmp);
+	drbg_dealloc_state(drbg);
 	return ret;
 }
 
-static void drbg_restore_shadow(struct drbg_state *drbg,
-				struct drbg_state **shadow)
-{
-	struct drbg_state *tmp = *shadow;
-
-	spin_lock_bh(&drbg->drbg_lock);
-	drbg_copy_drbg(tmp, drbg);
-	spin_unlock_bh(&drbg->drbg_lock);
-	drbg_dealloc_state(tmp);
-	kzfree(tmp);
-	*shadow = NULL;
-}
-
 /*************************************************************************
  * DRBG interface functions
  *************************************************************************/
@@ -1287,14 +1300,12 @@ static int drbg_generate(struct drbg_state *drbg,
 			 struct drbg_string *addtl)
 {
 	int len = 0;
-	struct drbg_state *shadow = NULL;
 	LIST_HEAD(addtllist);
-	struct drbg_string timestamp;
-	union {
-		cycles_t cycles;
-		unsigned char char_cycles[sizeof(cycles_t)];
-	} now;
 
+	if (!drbg->core) {
+		pr_devel("DRBG: not yet seeded\n");
+		return -EINVAL;
+	}
 	if (0 == buflen || !buf) {
 		pr_devel("DRBG: no output buffer provided\n");
 		return -EINVAL;
@@ -1304,15 +1315,9 @@ static int drbg_generate(struct drbg_state *drbg,
 		return -EINVAL;
 	}
 
-	len = drbg_make_shadow(drbg, &shadow);
-	if (len) {
-		pr_devel("DRBG: shadow copy cannot be generated\n");
-		return len;
-	}
-
 	/* 9.3.1 step 2 */
 	len = -EINVAL;
-	if (buflen > (drbg_max_request_bytes(shadow))) {
+	if (buflen > (drbg_max_request_bytes(drbg))) {
 		pr_devel("DRBG: requested random numbers too large %u\n",
 			 buflen);
 		goto err;
@@ -1321,7 +1326,7 @@ static int drbg_generate(struct drbg_state *drbg,
 	/* 9.3.1 step 3 is implicit with the chosen DRBG */
 
 	/* 9.3.1 step 4 */
-	if (addtl && addtl->len > (drbg_max_addtl(shadow))) {
+	if (addtl && addtl->len > (drbg_max_addtl(drbg))) {
 		pr_devel("DRBG: additional information string too long %zu\n",
 			 addtl->len);
 		goto err;
@@ -1332,46 +1337,29 @@ static int drbg_generate(struct drbg_state *drbg,
 	 * 9.3.1 step 6 and 9 supplemented by 9.3.2 step c is implemented
 	 * here. The spec is a bit convoluted here, we make it simpler.
 	 */
-	if ((drbg_max_requests(shadow)) < shadow->reseed_ctr)
-		shadow->seeded = false;
+	if (drbg->reseed_threshold < drbg->reseed_ctr)
+		drbg->seeded = false;
 
-	/* allocate cipher handle */
-	len = shadow->d_ops->crypto_init(shadow);
-	if (len)
-		goto err;
-
-	if (shadow->pr || !shadow->seeded) {
+	if (drbg->pr || !drbg->seeded) {
 		pr_devel("DRBG: reseeding before generation (prediction "
 			 "resistance: %s, state %s)\n",
 			 drbg->pr ? "true" : "false",
 			 drbg->seeded ? "seeded" : "unseeded");
 		/* 9.3.1 steps 7.1 through 7.3 */
-		len = drbg_seed(shadow, addtl, true);
+		len = drbg_seed(drbg, addtl, true);
 		if (len)
 			goto err;
 		/* 9.3.1 step 7.4 */
 		addtl = NULL;
 	}
 
-	/*
-	 * Mix the time stamp into the DRBG state if the DRBG is not in
-	 * test mode. If there are two callers invoking the DRBG at the same
-	 * time, i.e. before the first caller merges its shadow state back,
-	 * both callers would obtain the same random number stream without
-	 * changing the state here.
-	 */
-	if (!drbg->test_data) {
-		now.cycles = random_get_entropy();
-		drbg_string_fill(&timestamp, now.char_cycles, sizeof(cycles_t));
-		list_add_tail(&timestamp.list, &addtllist);
-	}
 	if (addtl && 0 < addtl->len)
 		list_add_tail(&addtl->list, &addtllist);
 	/* 9.3.1 step 8 and 10 */
-	len = shadow->d_ops->generate(shadow, buf, buflen, &addtllist);
+	len = drbg->d_ops->generate(drbg, buf, buflen, &addtllist);
 
 	/* 10.1.1.4 step 6, 10.1.2.5 step 7, 10.2.1.5.2 step 7 */
-	shadow->reseed_ctr++;
+	drbg->reseed_ctr++;
 	if (0 >= len)
 		goto err;
 
@@ -1391,7 +1379,7 @@ static int drbg_generate(struct drbg_state *drbg,
 	 * case somebody has a need to implement the test of 11.3.3.
 	 */
 #if 0
-	if (shadow->reseed_ctr && !(shadow->reseed_ctr % 4096)) {
+	if (drbg->reseed_ctr && !(drbg->reseed_ctr % 4096)) {
 		int err = 0;
 		pr_devel("DRBG: start to perform self test\n");
 		if (drbg->core->flags & DRBG_HMAC)
@@ -1410,8 +1398,6 @@ static int drbg_generate(struct drbg_state *drbg,
 			 * are returned when reusing this DRBG cipher handle
 			 */
 			drbg_uninstantiate(drbg);
-			drbg_dealloc_state(shadow);
-			kzfree(shadow);
 			return 0;
 		} else {
 			pr_devel("DRBG: self test successful\n");
@@ -1425,8 +1411,6 @@ static int drbg_generate(struct drbg_state *drbg,
 	 */
 	len = 0;
 err:
-	shadow->d_ops->crypto_fini(shadow);
-	drbg_restore_shadow(drbg, &shadow);
 	return len;
 }
 
@@ -1442,19 +1426,68 @@ static int drbg_generate_long(struct drbg_state *drbg,
 			      unsigned char *buf, unsigned int buflen,
 			      struct drbg_string *addtl)
 {
-	int len = 0;
+	unsigned int len = 0;
 	unsigned int slice = 0;
 	do {
-		int tmplen = 0;
+		int err = 0;
 		unsigned int chunk = 0;
 		slice = ((buflen - len) / drbg_max_request_bytes(drbg));
 		chunk = slice ? drbg_max_request_bytes(drbg) : (buflen - len);
-		tmplen = drbg_generate(drbg, buf + len, chunk, addtl);
-		if (0 >= tmplen)
-			return tmplen;
-		len += tmplen;
+		mutex_lock(&drbg->drbg_mutex);
+		err = drbg_generate(drbg, buf + len, chunk, addtl);
+		mutex_unlock(&drbg->drbg_mutex);
+		if (0 > err)
+			return err;
+		len += chunk;
 	} while (slice > 0 && (len < buflen));
-	return len;
+	return 0;
+}
+
+static void drbg_schedule_async_seed(struct random_ready_callback *rdy)
+{
+	struct drbg_state *drbg = container_of(rdy, struct drbg_state,
+					       random_ready);
+
+	schedule_work(&drbg->seed_work);
+}
+
+static int drbg_prepare_hrng(struct drbg_state *drbg)
+{
+	int err;
+
+	/* We do not need an HRNG in test mode. */
+	if (list_empty(&drbg->test_data.list))
+		return 0;
+
+	INIT_WORK(&drbg->seed_work, drbg_async_seed);
+
+	drbg->random_ready.owner = THIS_MODULE;
+	drbg->random_ready.func = drbg_schedule_async_seed;
+
+	err = add_random_ready_callback(&drbg->random_ready);
+
+	switch (err) {
+	case 0:
+		break;
+
+	case -EALREADY:
+		err = 0;
+		/* fall through */
+
+	default:
+		drbg->random_ready.func = NULL;
+		return err;
+	}
+
+	drbg->jent = crypto_alloc_rng("jitterentropy_rng", 0, 0);
+
+	/*
+	 * Require frequent reseeds until the seed source is fully
+	 * initialized.
+	 */
+	drbg->reseed_threshold = 50;
+
+	return err;
 }
 
 /*
@@ -1477,32 +1510,12 @@ static int drbg_generate_long(struct drbg_state *drbg,
 static int drbg_instantiate(struct drbg_state *drbg, struct drbg_string *pers,
 			    int coreref, bool pr)
 {
-	int ret = -ENOMEM;
+	int ret;
+	bool reseed = true;
 
 	pr_devel("DRBG: Initializing DRBG core %d with prediction resistance "
 		 "%s\n", coreref, pr ? "enabled" : "disabled");
-	drbg->core = &drbg_cores[coreref];
-	drbg->pr = pr;
-	drbg->seeded = false;
-	switch (drbg->core->flags & DRBG_TYPE_MASK) {
-#ifdef CONFIG_CRYPTO_DRBG_HMAC
-	case DRBG_HMAC:
-		drbg->d_ops = &drbg_hmac_ops;
-		break;
-#endif /* CONFIG_CRYPTO_DRBG_HMAC */
-#ifdef CONFIG_CRYPTO_DRBG_HASH
-	case DRBG_HASH:
-		drbg->d_ops = &drbg_hash_ops;
-		break;
-#endif /* CONFIG_CRYPTO_DRBG_HASH */
-#ifdef CONFIG_CRYPTO_DRBG_CTR
-	case DRBG_CTR:
-		drbg->d_ops = &drbg_ctr_ops;
-		break;
-#endif /* CONFIG_CRYPTO_DRBG_CTR */
-	default:
-		return -EOPNOTSUPP;
-	}
+	mutex_lock(&drbg->drbg_mutex);
 
 	/* 9.1 step 1 is implicit with the selected DRBG type */
 
@@ -1514,22 +1527,52 @@ static int drbg_instantiate(struct drbg_state *drbg, struct drbg_string *pers,
 
 	/* 9.1 step 4 is implicit in  drbg_sec_strength */
 
-	ret = drbg_alloc_state(drbg);
-	if (ret)
-		return ret;
+	if (!drbg->core) {
+		drbg->core = &drbg_cores[coreref];
+		drbg->pr = pr;
+		drbg->seeded = false;
+		drbg->reseed_threshold = drbg_max_requests(drbg);
 
-	ret = -EFAULT;
-	if (drbg->d_ops->crypto_init(drbg))
-		goto err;
-	ret = drbg_seed(drbg, pers, false);
-	drbg->d_ops->crypto_fini(drbg);
-	if (ret)
-		goto err;
+		ret = drbg_alloc_state(drbg);
+		if (ret)
+			goto unlock;
 
-	return 0;
+		ret = -EFAULT;
+		if (drbg->d_ops->crypto_init(drbg))
+			goto err;
+
+		ret = drbg_prepare_hrng(drbg);
+		if (ret)
+			goto free_everything;
+
+		if (IS_ERR(drbg->jent)) {
+			ret = PTR_ERR(drbg->jent);
+			drbg->jent = NULL;
+			if (fips_enabled || ret != -ENOENT)
+				goto free_everything;
+			pr_info("DRBG: Continuing without Jitter RNG\n");
+		}
+
+		reseed = false;
+	}
+
+	ret = drbg_seed(drbg, pers, reseed);
+
+	if (ret && !reseed)
+		goto free_everything;
+
+	mutex_unlock(&drbg->drbg_mutex);
+	return ret;
 
 err:
 	drbg_dealloc_state(drbg);
+unlock:
+	mutex_unlock(&drbg->drbg_mutex);
+	return ret;
+
+free_everything:
+	mutex_unlock(&drbg->drbg_mutex);
+	drbg_uninstantiate(drbg);
 	return ret;
 }
 
@@ -1544,10 +1587,17 @@ err:
  */
 static int drbg_uninstantiate(struct drbg_state *drbg)
 {
-	spin_lock_bh(&drbg->drbg_lock);
+	if (drbg->random_ready.func) {
+		del_random_ready_callback(&drbg->random_ready);
+		cancel_work_sync(&drbg->seed_work);
+		crypto_free_rng(drbg->jent);
+		drbg->jent = NULL;
+	}
+
+	if (drbg->d_ops)
+		drbg->d_ops->crypto_fini(drbg);
 	drbg_dealloc_state(drbg);
 	/* no scrubbing of test_data -- this shall survive an uninstantiate */
-	spin_unlock_bh(&drbg->drbg_lock);
 	return 0;
 }
 
@@ -1555,16 +1605,17 @@ static int drbg_uninstantiate(struct drbg_state *drbg)
  * Helper function for setting the test data in the DRBG
  *
  * @drbg DRBG state handle
- * @test_data test data to sets
+ * @data test data
+ * @len test data length
  */
-static inline void drbg_set_testdata(struct drbg_state *drbg,
-				     struct drbg_test_data *test_data)
+static void drbg_kcapi_set_entropy(struct crypto_rng *tfm,
+				   const u8 *data, unsigned int len)
 {
-	if (!test_data || !test_data->testentropy)
-		return;
-	spin_lock_bh(&drbg->drbg_lock);
-	drbg->test_data = test_data;
-	spin_unlock_bh(&drbg->drbg_lock);
+	struct drbg_state *drbg = crypto_rng_ctx(tfm);
+
+	mutex_lock(&drbg->drbg_mutex);
+	drbg_string_fill(&drbg->test_data, data, len);
+	mutex_unlock(&drbg->drbg_mutex);
 }
 
 /***************************************************************
@@ -1584,7 +1635,8 @@ static int drbg_init_hash_kernel(struct drbg_state *drbg)
 
 	tfm = crypto_alloc_shash(drbg->core->backend_cra_name, 0, 0);
 	if (IS_ERR(tfm)) {
-		pr_info("DRBG: could not allocate digest TFM handle\n");
+		pr_info("DRBG: could not allocate digest TFM handle: %s\n",
+				drbg->core->backend_cra_name);
 		return PTR_ERR(tfm);
 	}
 	BUG_ON(drbg_blocklen(drbg) != crypto_shash_digestsize(tfm));
@@ -1635,7 +1687,8 @@ static int drbg_init_sym_kernel(struct drbg_state *drbg)
 
 	tfm = crypto_alloc_cipher(drbg->core->backend_cra_name, 0, 0);
 	if (IS_ERR(tfm)) {
-		pr_info("DRBG: could not allocate cipher TFM handle\n");
+		pr_info("DRBG: could not allocate cipher TFM handle: %s\n",
+				drbg->core->backend_cra_name);
 		return PTR_ERR(tfm);
 	}
 	BUG_ON(drbg_blocklen(drbg) != crypto_cipher_blocksize(tfm));
@@ -1714,15 +1767,10 @@ static inline void drbg_convert_tfm_core(const char *cra_driver_name,
 static int drbg_kcapi_init(struct crypto_tfm *tfm)
 {
 	struct drbg_state *drbg = crypto_tfm_ctx(tfm);
-	bool pr = false;
-	int coreref = 0;
 
-	drbg_convert_tfm_core(crypto_tfm_alg_driver_name(tfm), &coreref, &pr);
-	/*
-	 * when personalization string is needed, the caller must call reset
-	 * and provide the personalization string as seed information
-	 */
-	return drbg_instantiate(drbg, NULL, coreref, pr);
+	mutex_init(&drbg->drbg_mutex);
+
+	return 0;
 }
 
 static void drbg_kcapi_cleanup(struct crypto_tfm *tfm)
@@ -1734,65 +1782,49 @@ static void drbg_kcapi_cleanup(struct crypto_tfm *tfm)
  * Generate random numbers invoked by the kernel crypto API:
  * The API of the kernel crypto API is extended as follows:
  *
- * If dlen is larger than zero, rdata is interpreted as the output buffer
- * where random data is to be stored.
- *
- * If dlen is zero, rdata is interpreted as a pointer to a struct drbg_gen
- * which holds the additional information string that is used for the
- * DRBG generation process. The output buffer that is to be used to store
- * data is also pointed to by struct drbg_gen.
+ * src is additional input supplied to the RNG.
+ * slen is the length of src.
+ * dst is the output buffer where random data is to be stored.
+ * dlen is the length of dst.
  */
-static int drbg_kcapi_random(struct crypto_rng *tfm, u8 *rdata,
-			     unsigned int dlen)
+static int drbg_kcapi_random(struct crypto_rng *tfm,
+			     const u8 *src, unsigned int slen,
+			     u8 *dst, unsigned int dlen)
 {
 	struct drbg_state *drbg = crypto_rng_ctx(tfm);
-	if (0 < dlen) {
-		return drbg_generate_long(drbg, rdata, dlen, NULL);
-	} else {
-		struct drbg_gen *data = (struct drbg_gen *)rdata;
-		struct drbg_string addtl;
-		/* catch NULL pointer */
-		if (!data)
-			return 0;
-		drbg_set_testdata(drbg, data->test_data);
+	struct drbg_string *addtl = NULL;
+	struct drbg_string string;
+
+	if (slen) {
 		/* linked list variable is now local to allow modification */
-		drbg_string_fill(&addtl, data->addtl->buf, data->addtl->len);
-		return drbg_generate_long(drbg, data->outbuf, data->outlen,
-					  &addtl);
+		drbg_string_fill(&string, src, slen);
+		addtl = &string;
 	}
+
+	return drbg_generate_long(drbg, dst, dlen, addtl);
 }
 
 /*
- * Reset the DRBG invoked by the kernel crypto API
- * The reset implies a full re-initialization of the DRBG. Similar to the
- * generate function of drbg_kcapi_random, this function extends the
- * kernel crypto API interface with struct drbg_gen
+ * Seed the DRBG invoked by the kernel crypto API
  */
-static int drbg_kcapi_reset(struct crypto_rng *tfm, u8 *seed, unsigned int slen)
+static int drbg_kcapi_seed(struct crypto_rng *tfm,
+			   const u8 *seed, unsigned int slen)
 {
 	struct drbg_state *drbg = crypto_rng_ctx(tfm);
 	struct crypto_tfm *tfm_base = crypto_rng_tfm(tfm);
 	bool pr = false;
-	struct drbg_string seed_string;
+	struct drbg_string string;
+	struct drbg_string *seed_string = NULL;
 	int coreref = 0;
 
-	drbg_uninstantiate(drbg);
 	drbg_convert_tfm_core(crypto_tfm_alg_driver_name(tfm_base), &coreref,
 			      &pr);
 	if (0 < slen) {
-		drbg_string_fill(&seed_string, seed, slen);
-		return drbg_instantiate(drbg, &seed_string, coreref, pr);
-	} else {
-		struct drbg_gen *data = (struct drbg_gen *)seed;
-		/* allow invocation of API call with NULL, 0 */
-		if (!data)
-			return drbg_instantiate(drbg, NULL, coreref, pr);
-		drbg_set_testdata(drbg, data->test_data);
-		/* linked list variable is now local to allow modification */
-		drbg_string_fill(&seed_string, data->addtl->buf,
-				 data->addtl->len);
-		return drbg_instantiate(drbg, &seed_string, coreref, pr);
+		drbg_string_fill(&string, seed, slen);
+		seed_string = &string;
 	}
+
+	return drbg_instantiate(drbg, seed_string, coreref, pr);
 }
 
 /***************************************************************
@@ -1811,7 +1843,6 @@ static int drbg_kcapi_reset(struct crypto_rng *tfm, u8 *seed, unsigned int slen)
  */
 static inline int __init drbg_healthcheck_sanity(void)
 {
-#ifdef CONFIG_CRYPTO_FIPS
 	int len = 0;
 #define OUTBUFLEN 16
 	unsigned char buf[OUTBUFLEN];
@@ -1839,6 +1870,8 @@ static inline int __init drbg_healthcheck_sanity(void)
 	if (!drbg)
 		return -ENOMEM;
 
+	mutex_init(&drbg->drbg_mutex);
+
 	/*
 	 * if the following tests fail, it is likely that there is a buffer
 	 * overflow as buf is much smaller than the requested or provided
@@ -1877,37 +1910,33 @@ static inline int __init drbg_healthcheck_sanity(void)
 outbuf:
 	kzfree(drbg);
 	return rc;
-#else /* CONFIG_CRYPTO_FIPS */
-	return 0;
-#endif /* CONFIG_CRYPTO_FIPS */
 }
 
-static struct crypto_alg drbg_algs[22];
+static struct rng_alg drbg_algs[22];
 
 /*
  * Fill the array drbg_algs used to register the different DRBGs
  * with the kernel crypto API. To fill the array, the information
  * from drbg_cores[] is used.
  */
-static inline void __init drbg_fill_array(struct crypto_alg *alg,
+static inline void __init drbg_fill_array(struct rng_alg *alg,
 					  const struct drbg_core *core, int pr)
 {
 	int pos = 0;
-	static int priority = 100;
+	static int priority = 200;
 
-	memset(alg, 0, sizeof(struct crypto_alg));
-	memcpy(alg->cra_name, "stdrng", 6);
+	memcpy(alg->base.cra_name, "stdrng", 6);
 	if (pr) {
-		memcpy(alg->cra_driver_name, "drbg_pr_", 8);
+		memcpy(alg->base.cra_driver_name, "drbg_pr_", 8);
 		pos = 8;
 	} else {
-		memcpy(alg->cra_driver_name, "drbg_nopr_", 10);
+		memcpy(alg->base.cra_driver_name, "drbg_nopr_", 10);
 		pos = 10;
 	}
-	memcpy(alg->cra_driver_name + pos, core->cra_name,
+	memcpy(alg->base.cra_driver_name + pos, core->cra_name,
 	       strlen(core->cra_name));
 
-	alg->cra_priority = priority;
+	alg->base.cra_priority = priority;
 	priority++;
 	/*
 	 * If FIPS mode enabled, the selected DRBG shall have the
@@ -1915,17 +1944,16 @@ static inline void __init drbg_fill_array(struct crypto_alg *alg,
 	 * it is selected.
 	 */
 	if (fips_enabled)
-		alg->cra_priority += 200;
-
-	alg->cra_flags		= CRYPTO_ALG_TYPE_RNG;
-	alg->cra_ctxsize 	= sizeof(struct drbg_state);
-	alg->cra_type		= &crypto_rng_type;
-	alg->cra_module		= THIS_MODULE;
-	alg->cra_init		= drbg_kcapi_init;
-	alg->cra_exit		= drbg_kcapi_cleanup;
-	alg->cra_u.rng.rng_make_random	= drbg_kcapi_random;
-	alg->cra_u.rng.rng_reset	= drbg_kcapi_reset;
-	alg->cra_u.rng.seedsize	= 0;
+		alg->base.cra_priority += 200;
+
+	alg->base.cra_ctxsize 	= sizeof(struct drbg_state);
+	alg->base.cra_module	= THIS_MODULE;
+	alg->base.cra_init	= drbg_kcapi_init;
+	alg->base.cra_exit	= drbg_kcapi_cleanup;
+	alg->generate		= drbg_kcapi_random;
+	alg->seed		= drbg_kcapi_seed;
+	alg->set_ent		= drbg_kcapi_set_entropy;
+	alg->seedsize		= 0;
 }
 
 static int __init drbg_init(void)
@@ -1958,12 +1986,12 @@ static int __init drbg_init(void)
 		drbg_fill_array(&drbg_algs[i], &drbg_cores[j], 1);
 	for (j = 0; ARRAY_SIZE(drbg_cores) > j; j++, i++)
 		drbg_fill_array(&drbg_algs[i], &drbg_cores[j], 0);
-	return crypto_register_algs(drbg_algs, (ARRAY_SIZE(drbg_cores) * 2));
+	return crypto_register_rngs(drbg_algs, (ARRAY_SIZE(drbg_cores) * 2));
 }
 
 static void __exit drbg_exit(void)
 {
-	crypto_unregister_algs(drbg_algs, (ARRAY_SIZE(drbg_cores) * 2));
+	crypto_unregister_rngs(drbg_algs, (ARRAY_SIZE(drbg_cores) * 2));
 }
 
 module_init(drbg_init);
@@ -1984,3 +2012,4 @@ MODULE_DESCRIPTION("NIST SP800-90A Deterministic Random Bit Generator (DRBG) "
 		   CRYPTO_DRBG_HASH_STRING
 		   CRYPTO_DRBG_HMAC_STRING
 		   CRYPTO_DRBG_CTR_STRING);
+MODULE_ALIAS_CRYPTO("stdrng");
diff --git a/crypto/echainiv.c b/crypto/echainiv.c
new file mode 100644
index 000000000000..b6e43dc61356
--- /dev/null
+++ b/crypto/echainiv.c
@@ -0,0 +1,312 @@
+/*
+ * echainiv: Encrypted Chain IV Generator
+ *
+ * This generator generates an IV based on a sequence number by xoring it
+ * with a salt and then encrypting it with the same key as used to encrypt
+ * the plain text.  This algorithm requires that the block size be equal
+ * to the IV size.  It is mainly useful for CBC.
+ *
+ * This generator can only be used by algorithms where authentication
+ * is performed after encryption (i.e., authenc).
+ *
+ * Copyright (c) 2015 Herbert Xu <herbert@gondor.apana.org.au>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ */
+
+#include <crypto/internal/geniv.h>
+#include <crypto/null.h>
+#include <crypto/rng.h>
+#include <crypto/scatterwalk.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/percpu.h>
+#include <linux/spinlock.h>
+#include <linux/string.h>
+
+#define MAX_IV_SIZE 16
+
+struct echainiv_ctx {
+	/* aead_geniv_ctx must be first the element */
+	struct aead_geniv_ctx geniv;
+	struct crypto_blkcipher *null;
+	u8 salt[] __attribute__ ((aligned(__alignof__(u32))));
+};
+
+static DEFINE_PER_CPU(u32 [MAX_IV_SIZE / sizeof(u32)], echainiv_iv);
+
+/* We don't care if we get preempted and read/write IVs from the next CPU. */
+static void echainiv_read_iv(u8 *dst, unsigned size)
+{
+	u32 *a = (u32 *)dst;
+	u32 __percpu *b = echainiv_iv;
+
+	for (; size >= 4; size -= 4) {
+		*a++ = this_cpu_read(*b);
+		b++;
+	}
+}
+
+static void echainiv_write_iv(const u8 *src, unsigned size)
+{
+	const u32 *a = (const u32 *)src;
+	u32 __percpu *b = echainiv_iv;
+
+	for (; size >= 4; size -= 4) {
+		this_cpu_write(*b, *a);
+		a++;
+		b++;
+	}
+}
+
+static void echainiv_encrypt_complete2(struct aead_request *req, int err)
+{
+	struct aead_request *subreq = aead_request_ctx(req);
+	struct crypto_aead *geniv;
+	unsigned int ivsize;
+
+	if (err == -EINPROGRESS)
+		return;
+
+	if (err)
+		goto out;
+
+	geniv = crypto_aead_reqtfm(req);
+	ivsize = crypto_aead_ivsize(geniv);
+
+	echainiv_write_iv(subreq->iv, ivsize);
+
+	if (req->iv != subreq->iv)
+		memcpy(req->iv, subreq->iv, ivsize);
+
+out:
+	if (req->iv != subreq->iv)
+		kzfree(subreq->iv);
+}
+
+static void echainiv_encrypt_complete(struct crypto_async_request *base,
+					 int err)
+{
+	struct aead_request *req = base->data;
+
+	echainiv_encrypt_complete2(req, err);
+	aead_request_complete(req, err);
+}
+
+static int echainiv_encrypt(struct aead_request *req)
+{
+	struct crypto_aead *geniv = crypto_aead_reqtfm(req);
+	struct echainiv_ctx *ctx = crypto_aead_ctx(geniv);
+	struct aead_request *subreq = aead_request_ctx(req);
+	crypto_completion_t compl;
+	void *data;
+	u8 *info;
+	unsigned int ivsize = crypto_aead_ivsize(geniv);
+	int err;
+
+	if (req->cryptlen < ivsize)
+		return -EINVAL;
+
+	aead_request_set_tfm(subreq, ctx->geniv.child);
+
+	compl = echainiv_encrypt_complete;
+	data = req;
+	info = req->iv;
+
+	if (req->src != req->dst) {
+		struct blkcipher_desc desc = {
+			.tfm = ctx->null,
+		};
+
+		err = crypto_blkcipher_encrypt(
+			&desc, req->dst, req->src,
+			req->assoclen + req->cryptlen);
+		if (err)
+			return err;
+	}
+
+	if (unlikely(!IS_ALIGNED((unsigned long)info,
+				 crypto_aead_alignmask(geniv) + 1))) {
+		info = kmalloc(ivsize, req->base.flags &
+				       CRYPTO_TFM_REQ_MAY_SLEEP ? GFP_KERNEL:
+								  GFP_ATOMIC);
+		if (!info)
+			return -ENOMEM;
+
+		memcpy(info, req->iv, ivsize);
+	}
+
+	aead_request_set_callback(subreq, req->base.flags, compl, data);
+	aead_request_set_crypt(subreq, req->dst, req->dst,
+			       req->cryptlen - ivsize, info);
+	aead_request_set_ad(subreq, req->assoclen + ivsize);
+
+	crypto_xor(info, ctx->salt, ivsize);
+	scatterwalk_map_and_copy(info, req->dst, req->assoclen, ivsize, 1);
+	echainiv_read_iv(info, ivsize);
+
+	err = crypto_aead_encrypt(subreq);
+	echainiv_encrypt_complete2(req, err);
+	return err;
+}
+
+static int echainiv_decrypt(struct aead_request *req)
+{
+	struct crypto_aead *geniv = crypto_aead_reqtfm(req);
+	struct echainiv_ctx *ctx = crypto_aead_ctx(geniv);
+	struct aead_request *subreq = aead_request_ctx(req);
+	crypto_completion_t compl;
+	void *data;
+	unsigned int ivsize = crypto_aead_ivsize(geniv);
+
+	if (req->cryptlen < ivsize + crypto_aead_authsize(geniv))
+		return -EINVAL;
+
+	aead_request_set_tfm(subreq, ctx->geniv.child);
+
+	compl = req->base.complete;
+	data = req->base.data;
+
+	aead_request_set_callback(subreq, req->base.flags, compl, data);
+	aead_request_set_crypt(subreq, req->src, req->dst,
+			       req->cryptlen - ivsize, req->iv);
+	aead_request_set_ad(subreq, req->assoclen + ivsize);
+
+	scatterwalk_map_and_copy(req->iv, req->src, req->assoclen, ivsize, 0);
+	if (req->src != req->dst)
+		scatterwalk_map_and_copy(req->iv, req->dst,
+					 req->assoclen, ivsize, 1);
+
+	return crypto_aead_decrypt(subreq);
+}
+
+static int echainiv_init(struct crypto_tfm *tfm)
+{
+	struct crypto_aead *geniv = __crypto_aead_cast(tfm);
+	struct echainiv_ctx *ctx = crypto_aead_ctx(geniv);
+	int err;
+
+	spin_lock_init(&ctx->geniv.lock);
+
+	crypto_aead_set_reqsize(geniv, sizeof(struct aead_request));
+
+	err = crypto_get_default_rng();
+	if (err)
+		goto out;
+
+	err = crypto_rng_get_bytes(crypto_default_rng, ctx->salt,
+				   crypto_aead_ivsize(geniv));
+	crypto_put_default_rng();
+	if (err)
+		goto out;
+
+	ctx->null = crypto_get_default_null_skcipher();
+	err = PTR_ERR(ctx->null);
+	if (IS_ERR(ctx->null))
+		goto out;
+
+	err = aead_geniv_init(tfm);
+	if (err)
+		goto drop_null;
+
+	ctx->geniv.child = geniv->child;
+	geniv->child = geniv;
+
+out:
+	return err;
+
+drop_null:
+	crypto_put_default_null_skcipher();
+	goto out;
+}
+
+static void echainiv_exit(struct crypto_tfm *tfm)
+{
+	struct echainiv_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	crypto_free_aead(ctx->geniv.child);
+	crypto_put_default_null_skcipher();
+}
+
+static int echainiv_aead_create(struct crypto_template *tmpl,
+				struct rtattr **tb)
+{
+	struct aead_instance *inst;
+	struct crypto_aead_spawn *spawn;
+	struct aead_alg *alg;
+	int err;
+
+	inst = aead_geniv_alloc(tmpl, tb, 0, 0);
+
+	if (IS_ERR(inst))
+		return PTR_ERR(inst);
+
+	spawn = aead_instance_ctx(inst);
+	alg = crypto_spawn_aead_alg(spawn);
+
+	if (alg->base.cra_aead.encrypt)
+		goto done;
+
+	err = -EINVAL;
+	if (inst->alg.ivsize & (sizeof(u32) - 1) ||
+	    inst->alg.ivsize > MAX_IV_SIZE)
+		goto free_inst;
+
+	inst->alg.encrypt = echainiv_encrypt;
+	inst->alg.decrypt = echainiv_decrypt;
+
+	inst->alg.base.cra_init = echainiv_init;
+	inst->alg.base.cra_exit = echainiv_exit;
+
+	inst->alg.base.cra_alignmask |= __alignof__(u32) - 1;
+	inst->alg.base.cra_ctxsize = sizeof(struct echainiv_ctx);
+	inst->alg.base.cra_ctxsize += inst->alg.ivsize;
+
+done:
+	err = aead_register_instance(tmpl, inst);
+	if (err)
+		goto free_inst;
+
+out:
+	return err;
+
+free_inst:
+	aead_geniv_free(inst);
+	goto out;
+}
+
+static void echainiv_free(struct crypto_instance *inst)
+{
+	aead_geniv_free(aead_instance(inst));
+}
+
+static struct crypto_template echainiv_tmpl = {
+	.name = "echainiv",
+	.create = echainiv_aead_create,
+	.free = echainiv_free,
+	.module = THIS_MODULE,
+};
+
+static int __init echainiv_module_init(void)
+{
+	return crypto_register_template(&echainiv_tmpl);
+}
+
+static void __exit echainiv_module_exit(void)
+{
+	crypto_unregister_template(&echainiv_tmpl);
+}
+
+module_init(echainiv_module_init);
+module_exit(echainiv_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Encrypted Chain IV Generator");
+MODULE_ALIAS_CRYPTO("echainiv");
diff --git a/crypto/eseqiv.c b/crypto/eseqiv.c
index f116fae766f8..16dda72fc4f8 100644
--- a/crypto/eseqiv.c
+++ b/crypto/eseqiv.c
@@ -146,35 +146,13 @@ out:
 	return err;
 }
 
-static int eseqiv_givencrypt_first(struct skcipher_givcrypt_request *req)
-{
-	struct crypto_ablkcipher *geniv = skcipher_givcrypt_reqtfm(req);
-	struct eseqiv_ctx *ctx = crypto_ablkcipher_ctx(geniv);
-	int err = 0;
-
-	spin_lock_bh(&ctx->lock);
-	if (crypto_ablkcipher_crt(geniv)->givencrypt != eseqiv_givencrypt_first)
-		goto unlock;
-
-	crypto_ablkcipher_crt(geniv)->givencrypt = eseqiv_givencrypt;
-	err = crypto_rng_get_bytes(crypto_default_rng, ctx->salt,
-				   crypto_ablkcipher_ivsize(geniv));
-
-unlock:
-	spin_unlock_bh(&ctx->lock);
-
-	if (err)
-		return err;
-
-	return eseqiv_givencrypt(req);
-}
-
 static int eseqiv_init(struct crypto_tfm *tfm)
 {
 	struct crypto_ablkcipher *geniv = __crypto_ablkcipher_cast(tfm);
 	struct eseqiv_ctx *ctx = crypto_ablkcipher_ctx(geniv);
 	unsigned long alignmask;
 	unsigned int reqsize;
+	int err;
 
 	spin_lock_init(&ctx->lock);
 
@@ -198,7 +176,15 @@ static int eseqiv_init(struct crypto_tfm *tfm)
 	tfm->crt_ablkcipher.reqsize = reqsize +
 				      sizeof(struct ablkcipher_request);
 
-	return skcipher_geniv_init(tfm);
+	err = 0;
+	if (!crypto_get_default_rng()) {
+		crypto_ablkcipher_crt(geniv)->givencrypt = eseqiv_givencrypt;
+		err = crypto_rng_get_bytes(crypto_default_rng, ctx->salt,
+					   crypto_ablkcipher_ivsize(geniv));
+		crypto_put_default_rng();
+	}
+
+	return err ?: skcipher_geniv_init(tfm);
 }
 
 static struct crypto_template eseqiv_tmpl;
@@ -208,20 +194,14 @@ static struct crypto_instance *eseqiv_alloc(struct rtattr **tb)
 	struct crypto_instance *inst;
 	int err;
 
-	err = crypto_get_default_rng();
-	if (err)
-		return ERR_PTR(err);
-
 	inst = skcipher_geniv_alloc(&eseqiv_tmpl, tb, 0, 0);
 	if (IS_ERR(inst))
-		goto put_rng;
+		goto out;
 
 	err = -EINVAL;
 	if (inst->alg.cra_ablkcipher.ivsize != inst->alg.cra_blocksize)
 		goto free_inst;
 
-	inst->alg.cra_ablkcipher.givencrypt = eseqiv_givencrypt_first;
-
 	inst->alg.cra_init = eseqiv_init;
 	inst->alg.cra_exit = skcipher_geniv_exit;
 
@@ -234,21 +214,13 @@ out:
 free_inst:
 	skcipher_geniv_free(inst);
 	inst = ERR_PTR(err);
-put_rng:
-	crypto_put_default_rng();
 	goto out;
 }
 
-static void eseqiv_free(struct crypto_instance *inst)
-{
-	skcipher_geniv_free(inst);
-	crypto_put_default_rng();
-}
-
 static struct crypto_template eseqiv_tmpl = {
 	.name = "eseqiv",
 	.alloc = eseqiv_alloc,
-	.free = eseqiv_free,
+	.free = skcipher_geniv_free,
 	.module = THIS_MODULE,
 };
 
diff --git a/crypto/fips.c b/crypto/fips.c
index 553970081c62..9d627c1cf8bc 100644
--- a/crypto/fips.c
+++ b/crypto/fips.c
@@ -10,7 +10,12 @@
  *
  */
 
-#include "internal.h"
+#include <linux/export.h>
+#include <linux/fips.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/sysctl.h>
 
 int fips_enabled;
 EXPORT_SYMBOL_GPL(fips_enabled);
@@ -25,3 +30,49 @@ static int fips_enable(char *str)
 }
 
 __setup("fips=", fips_enable);
+
+static struct ctl_table crypto_sysctl_table[] = {
+	{
+		.procname       = "fips_enabled",
+		.data           = &fips_enabled,
+		.maxlen         = sizeof(int),
+		.mode           = 0444,
+		.proc_handler   = proc_dointvec
+	},
+	{}
+};
+
+static struct ctl_table crypto_dir_table[] = {
+	{
+		.procname       = "crypto",
+		.mode           = 0555,
+		.child          = crypto_sysctl_table
+	},
+	{}
+};
+
+static struct ctl_table_header *crypto_sysctls;
+
+static void crypto_proc_fips_init(void)
+{
+	crypto_sysctls = register_sysctl_table(crypto_dir_table);
+}
+
+static void crypto_proc_fips_exit(void)
+{
+	unregister_sysctl_table(crypto_sysctls);
+}
+
+static int __init fips_init(void)
+{
+	crypto_proc_fips_init();
+	return 0;
+}
+
+static void __exit fips_exit(void)
+{
+	crypto_proc_fips_exit();
+}
+
+module_init(fips_init);
+module_exit(fips_exit);
diff --git a/crypto/gcm.c b/crypto/gcm.c
index 2e403f6138c1..7d32d4720564 100644
--- a/crypto/gcm.c
+++ b/crypto/gcm.c
@@ -12,6 +12,7 @@
 #include <crypto/internal/aead.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/internal/hash.h>
+#include <crypto/null.h>
 #include <crypto/scatterwalk.h>
 #include <crypto/hash.h>
 #include "internal.h"
@@ -39,7 +40,6 @@ struct crypto_rfc4106_ctx {
 
 struct crypto_rfc4543_instance_ctx {
 	struct crypto_aead_spawn aead;
-	struct crypto_skcipher_spawn null;
 };
 
 struct crypto_rfc4543_ctx {
@@ -49,25 +49,22 @@ struct crypto_rfc4543_ctx {
 };
 
 struct crypto_rfc4543_req_ctx {
-	u8 auth_tag[16];
-	u8 assocbuf[32];
-	struct scatterlist cipher[1];
-	struct scatterlist payload[2];
-	struct scatterlist assoc[2];
 	struct aead_request subreq;
 };
 
 struct crypto_gcm_ghash_ctx {
 	unsigned int cryptlen;
 	struct scatterlist *src;
-	void (*complete)(struct aead_request *req, int err);
+	int (*complete)(struct aead_request *req, u32 flags);
 };
 
 struct crypto_gcm_req_priv_ctx {
+	u8 iv[16];
 	u8 auth_tag[16];
 	u8 iauth_tag[16];
-	struct scatterlist src[2];
-	struct scatterlist dst[2];
+	struct scatterlist src[3];
+	struct scatterlist dst[3];
+	struct scatterlist sg;
 	struct crypto_gcm_ghash_ctx ghash_ctx;
 	union {
 		struct ahash_request ahreq;
@@ -80,7 +77,12 @@ struct crypto_gcm_setkey_result {
 	struct completion completion;
 };
 
-static void *gcm_zeroes;
+static struct {
+	u8 buf[16];
+	struct scatterlist sg;
+} *gcm_zeroes;
+
+static int crypto_rfc4543_copy_src_to_dst(struct aead_request *req, bool enc);
 
 static inline struct crypto_gcm_req_priv_ctx *crypto_gcm_reqctx(
 	struct aead_request *req)
@@ -120,15 +122,13 @@ static int crypto_gcm_setkey(struct crypto_aead *aead, const u8 *key,
 
 	crypto_ablkcipher_clear_flags(ctr, CRYPTO_TFM_REQ_MASK);
 	crypto_ablkcipher_set_flags(ctr, crypto_aead_get_flags(aead) &
-				   CRYPTO_TFM_REQ_MASK);
-
+					 CRYPTO_TFM_REQ_MASK);
 	err = crypto_ablkcipher_setkey(ctr, key, keylen);
+	crypto_aead_set_flags(aead, crypto_ablkcipher_get_flags(ctr) &
+				    CRYPTO_TFM_RES_MASK);
 	if (err)
 		return err;
 
-	crypto_aead_set_flags(aead, crypto_ablkcipher_get_flags(ctr) &
-				       CRYPTO_TFM_RES_MASK);
-
 	data = kzalloc(sizeof(*data) + crypto_ablkcipher_reqsize(ctr),
 		       GFP_KERNEL);
 	if (!data)
@@ -163,7 +163,7 @@ static int crypto_gcm_setkey(struct crypto_aead *aead, const u8 *key,
 			      CRYPTO_TFM_RES_MASK);
 
 out:
-	kfree(data);
+	kzfree(data);
 	return err;
 }
 
@@ -186,35 +186,46 @@ static int crypto_gcm_setauthsize(struct crypto_aead *tfm,
 	return 0;
 }
 
-static void crypto_gcm_init_crypt(struct ablkcipher_request *ablk_req,
-				  struct aead_request *req,
-				  unsigned int cryptlen)
+static void crypto_gcm_init_common(struct aead_request *req)
 {
-	struct crypto_aead *aead = crypto_aead_reqtfm(req);
-	struct crypto_gcm_ctx *ctx = crypto_aead_ctx(aead);
 	struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req);
-	struct scatterlist *dst;
 	__be32 counter = cpu_to_be32(1);
+	struct scatterlist *sg;
 
 	memset(pctx->auth_tag, 0, sizeof(pctx->auth_tag));
-	memcpy(req->iv + 12, &counter, 4);
+	memcpy(pctx->iv, req->iv, 12);
+	memcpy(pctx->iv + 12, &counter, 4);
 
-	sg_init_table(pctx->src, 2);
+	sg_init_table(pctx->src, 3);
 	sg_set_buf(pctx->src, pctx->auth_tag, sizeof(pctx->auth_tag));
-	scatterwalk_sg_chain(pctx->src, 2, req->src);
+	sg = scatterwalk_ffwd(pctx->src + 1, req->src, req->assoclen);
+	if (sg != pctx->src + 1)
+		scatterwalk_sg_chain(pctx->src, 2, sg);
 
-	dst = pctx->src;
 	if (req->src != req->dst) {
-		sg_init_table(pctx->dst, 2);
+		sg_init_table(pctx->dst, 3);
 		sg_set_buf(pctx->dst, pctx->auth_tag, sizeof(pctx->auth_tag));
-		scatterwalk_sg_chain(pctx->dst, 2, req->dst);
-		dst = pctx->dst;
+		sg = scatterwalk_ffwd(pctx->dst + 1, req->dst, req->assoclen);
+		if (sg != pctx->dst + 1)
+			scatterwalk_sg_chain(pctx->dst, 2, sg);
 	}
+}
+
+static void crypto_gcm_init_crypt(struct aead_request *req,
+				  unsigned int cryptlen)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct crypto_gcm_ctx *ctx = crypto_aead_ctx(aead);
+	struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req);
+	struct ablkcipher_request *ablk_req = &pctx->u.abreq;
+	struct scatterlist *dst;
+
+	dst = req->src == req->dst ? pctx->src : pctx->dst;
 
 	ablkcipher_request_set_tfm(ablk_req, ctx->ctr);
 	ablkcipher_request_set_crypt(ablk_req, pctx->src, dst,
 				     cryptlen + sizeof(pctx->auth_tag),
-				     req->iv);
+				     pctx->iv);
 }
 
 static inline unsigned int gcm_remain(unsigned int len)
@@ -224,41 +235,31 @@ static inline unsigned int gcm_remain(unsigned int len)
 }
 
 static void gcm_hash_len_done(struct crypto_async_request *areq, int err);
-static void gcm_hash_final_done(struct crypto_async_request *areq, int err);
 
 static int gcm_hash_update(struct aead_request *req,
-			   struct crypto_gcm_req_priv_ctx *pctx,
 			   crypto_completion_t compl,
 			   struct scatterlist *src,
-			   unsigned int len)
+			   unsigned int len, u32 flags)
 {
+	struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req);
 	struct ahash_request *ahreq = &pctx->u.ahreq;
 
-	ahash_request_set_callback(ahreq, aead_request_flags(req),
-				   compl, req);
+	ahash_request_set_callback(ahreq, flags, compl, req);
 	ahash_request_set_crypt(ahreq, src, NULL, len);
 
 	return crypto_ahash_update(ahreq);
 }
 
 static int gcm_hash_remain(struct aead_request *req,
-			   struct crypto_gcm_req_priv_ctx *pctx,
 			   unsigned int remain,
-			   crypto_completion_t compl)
+			   crypto_completion_t compl, u32 flags)
 {
-	struct ahash_request *ahreq = &pctx->u.ahreq;
-
-	ahash_request_set_callback(ahreq, aead_request_flags(req),
-				   compl, req);
-	sg_init_one(pctx->src, gcm_zeroes, remain);
-	ahash_request_set_crypt(ahreq, pctx->src, NULL, remain);
-
-	return crypto_ahash_update(ahreq);
+	return gcm_hash_update(req, compl, &gcm_zeroes->sg, remain, flags);
 }
 
-static int gcm_hash_len(struct aead_request *req,
-			struct crypto_gcm_req_priv_ctx *pctx)
+static int gcm_hash_len(struct aead_request *req, u32 flags)
 {
+	struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req);
 	struct ahash_request *ahreq = &pctx->u.ahreq;
 	struct crypto_gcm_ghash_ctx *gctx = &pctx->ghash_ctx;
 	u128 lengths;
@@ -266,76 +267,41 @@ static int gcm_hash_len(struct aead_request *req,
 	lengths.a = cpu_to_be64(req->assoclen * 8);
 	lengths.b = cpu_to_be64(gctx->cryptlen * 8);
 	memcpy(pctx->iauth_tag, &lengths, 16);
-	sg_init_one(pctx->src, pctx->iauth_tag, 16);
-	ahash_request_set_callback(ahreq, aead_request_flags(req),
-				   gcm_hash_len_done, req);
-	ahash_request_set_crypt(ahreq, pctx->src,
-				NULL, sizeof(lengths));
+	sg_init_one(&pctx->sg, pctx->iauth_tag, 16);
+	ahash_request_set_callback(ahreq, flags, gcm_hash_len_done, req);
+	ahash_request_set_crypt(ahreq, &pctx->sg,
+				pctx->iauth_tag, sizeof(lengths));
 
-	return crypto_ahash_update(ahreq);
-}
-
-static int gcm_hash_final(struct aead_request *req,
-			  struct crypto_gcm_req_priv_ctx *pctx)
-{
-	struct ahash_request *ahreq = &pctx->u.ahreq;
-
-	ahash_request_set_callback(ahreq, aead_request_flags(req),
-				   gcm_hash_final_done, req);
-	ahash_request_set_crypt(ahreq, NULL, pctx->iauth_tag, 0);
-
-	return crypto_ahash_final(ahreq);
+	return crypto_ahash_finup(ahreq);
 }
 
-static void __gcm_hash_final_done(struct aead_request *req, int err)
+static int gcm_hash_len_continue(struct aead_request *req, u32 flags)
 {
 	struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req);
 	struct crypto_gcm_ghash_ctx *gctx = &pctx->ghash_ctx;
 
-	if (!err)
-		crypto_xor(pctx->auth_tag, pctx->iauth_tag, 16);
-
-	gctx->complete(req, err);
+	return gctx->complete(req, flags);
 }
 
-static void gcm_hash_final_done(struct crypto_async_request *areq, int err)
+static void gcm_hash_len_done(struct crypto_async_request *areq, int err)
 {
 	struct aead_request *req = areq->data;
 
-	__gcm_hash_final_done(req, err);
-}
-
-static void __gcm_hash_len_done(struct aead_request *req, int err)
-{
-	struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req);
-
-	if (!err) {
-		err = gcm_hash_final(req, pctx);
-		if (err == -EINPROGRESS || err == -EBUSY)
-			return;
-	}
-
-	__gcm_hash_final_done(req, err);
-}
+	if (err)
+		goto out;
 
-static void gcm_hash_len_done(struct crypto_async_request *areq, int err)
-{
-	struct aead_request *req = areq->data;
+	err = gcm_hash_len_continue(req, 0);
+	if (err == -EINPROGRESS)
+		return;
 
-	__gcm_hash_len_done(req, err);
+out:
+	aead_request_complete(req, err);
 }
 
-static void __gcm_hash_crypt_remain_done(struct aead_request *req, int err)
+static int gcm_hash_crypt_remain_continue(struct aead_request *req, u32 flags)
 {
-	struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req);
-
-	if (!err) {
-		err = gcm_hash_len(req, pctx);
-		if (err == -EINPROGRESS || err == -EBUSY)
-			return;
-	}
-
-	__gcm_hash_len_done(req, err);
+	return gcm_hash_len(req, flags) ?:
+	       gcm_hash_len_continue(req, flags);
 }
 
 static void gcm_hash_crypt_remain_done(struct crypto_async_request *areq,
@@ -343,55 +309,58 @@ static void gcm_hash_crypt_remain_done(struct crypto_async_request *areq,
 {
 	struct aead_request *req = areq->data;
 
-	__gcm_hash_crypt_remain_done(req, err);
+	if (err)
+		goto out;
+
+	err = gcm_hash_crypt_remain_continue(req, 0);
+	if (err == -EINPROGRESS)
+		return;
+
+out:
+	aead_request_complete(req, err);
 }
 
-static void __gcm_hash_crypt_done(struct aead_request *req, int err)
+static int gcm_hash_crypt_continue(struct aead_request *req, u32 flags)
 {
 	struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req);
 	struct crypto_gcm_ghash_ctx *gctx = &pctx->ghash_ctx;
 	unsigned int remain;
 
-	if (!err) {
-		remain = gcm_remain(gctx->cryptlen);
-		BUG_ON(!remain);
-		err = gcm_hash_remain(req, pctx, remain,
-				      gcm_hash_crypt_remain_done);
-		if (err == -EINPROGRESS || err == -EBUSY)
-			return;
-	}
+	remain = gcm_remain(gctx->cryptlen);
+	if (remain)
+		return gcm_hash_remain(req, remain,
+				       gcm_hash_crypt_remain_done, flags) ?:
+		       gcm_hash_crypt_remain_continue(req, flags);
 
-	__gcm_hash_crypt_remain_done(req, err);
+	return gcm_hash_crypt_remain_continue(req, flags);
 }
 
 static void gcm_hash_crypt_done(struct crypto_async_request *areq, int err)
 {
 	struct aead_request *req = areq->data;
 
-	__gcm_hash_crypt_done(req, err);
+	if (err)
+		goto out;
+
+	err = gcm_hash_crypt_continue(req, 0);
+	if (err == -EINPROGRESS)
+		return;
+
+out:
+	aead_request_complete(req, err);
 }
 
-static void __gcm_hash_assoc_remain_done(struct aead_request *req, int err)
+static int gcm_hash_assoc_remain_continue(struct aead_request *req, u32 flags)
 {
 	struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req);
 	struct crypto_gcm_ghash_ctx *gctx = &pctx->ghash_ctx;
-	crypto_completion_t compl;
-	unsigned int remain = 0;
-
-	if (!err && gctx->cryptlen) {
-		remain = gcm_remain(gctx->cryptlen);
-		compl = remain ? gcm_hash_crypt_done :
-			gcm_hash_crypt_remain_done;
-		err = gcm_hash_update(req, pctx, compl,
-				      gctx->src, gctx->cryptlen);
-		if (err == -EINPROGRESS || err == -EBUSY)
-			return;
-	}
 
-	if (remain)
-		__gcm_hash_crypt_done(req, err);
-	else
-		__gcm_hash_crypt_remain_done(req, err);
+	if (gctx->cryptlen)
+		return gcm_hash_update(req, gcm_hash_crypt_done,
+				       gctx->src, gctx->cryptlen, flags) ?:
+		       gcm_hash_crypt_continue(req, flags);
+
+	return gcm_hash_crypt_remain_continue(req, flags);
 }
 
 static void gcm_hash_assoc_remain_done(struct crypto_async_request *areq,
@@ -399,146 +368,120 @@ static void gcm_hash_assoc_remain_done(struct crypto_async_request *areq,
 {
 	struct aead_request *req = areq->data;
 
-	__gcm_hash_assoc_remain_done(req, err);
+	if (err)
+		goto out;
+
+	err = gcm_hash_assoc_remain_continue(req, 0);
+	if (err == -EINPROGRESS)
+		return;
+
+out:
+	aead_request_complete(req, err);
 }
 
-static void __gcm_hash_assoc_done(struct aead_request *req, int err)
+static int gcm_hash_assoc_continue(struct aead_request *req, u32 flags)
 {
-	struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req);
 	unsigned int remain;
 
-	if (!err) {
-		remain = gcm_remain(req->assoclen);
-		BUG_ON(!remain);
-		err = gcm_hash_remain(req, pctx, remain,
-				      gcm_hash_assoc_remain_done);
-		if (err == -EINPROGRESS || err == -EBUSY)
-			return;
-	}
+	remain = gcm_remain(req->assoclen);
+	if (remain)
+		return gcm_hash_remain(req, remain,
+				       gcm_hash_assoc_remain_done, flags) ?:
+		       gcm_hash_assoc_remain_continue(req, flags);
 
-	__gcm_hash_assoc_remain_done(req, err);
+	return gcm_hash_assoc_remain_continue(req, flags);
 }
 
 static void gcm_hash_assoc_done(struct crypto_async_request *areq, int err)
 {
 	struct aead_request *req = areq->data;
 
-	__gcm_hash_assoc_done(req, err);
+	if (err)
+		goto out;
+
+	err = gcm_hash_assoc_continue(req, 0);
+	if (err == -EINPROGRESS)
+		return;
+
+out:
+	aead_request_complete(req, err);
 }
 
-static void __gcm_hash_init_done(struct aead_request *req, int err)
+static int gcm_hash_init_continue(struct aead_request *req, u32 flags)
 {
-	struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req);
-	crypto_completion_t compl;
-	unsigned int remain = 0;
-
-	if (!err && req->assoclen) {
-		remain = gcm_remain(req->assoclen);
-		compl = remain ? gcm_hash_assoc_done :
-			gcm_hash_assoc_remain_done;
-		err = gcm_hash_update(req, pctx, compl,
-				      req->assoc, req->assoclen);
-		if (err == -EINPROGRESS || err == -EBUSY)
-			return;
-	}
+	if (req->assoclen)
+		return gcm_hash_update(req, gcm_hash_assoc_done,
+				       req->src, req->assoclen, flags) ?:
+		       gcm_hash_assoc_continue(req, flags);
 
-	if (remain)
-		__gcm_hash_assoc_done(req, err);
-	else
-		__gcm_hash_assoc_remain_done(req, err);
+	return gcm_hash_assoc_remain_continue(req, flags);
 }
 
 static void gcm_hash_init_done(struct crypto_async_request *areq, int err)
 {
 	struct aead_request *req = areq->data;
 
-	__gcm_hash_init_done(req, err);
+	if (err)
+		goto out;
+
+	err = gcm_hash_init_continue(req, 0);
+	if (err == -EINPROGRESS)
+		return;
+
+out:
+	aead_request_complete(req, err);
 }
 
-static int gcm_hash(struct aead_request *req,
-		    struct crypto_gcm_req_priv_ctx *pctx)
+static int gcm_hash(struct aead_request *req, u32 flags)
 {
+	struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req);
 	struct ahash_request *ahreq = &pctx->u.ahreq;
-	struct crypto_gcm_ghash_ctx *gctx = &pctx->ghash_ctx;
-	struct crypto_gcm_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
-	unsigned int remain;
-	crypto_completion_t compl;
-	int err;
+	struct crypto_gcm_ctx *ctx = crypto_aead_ctx(crypto_aead_reqtfm(req));
 
 	ahash_request_set_tfm(ahreq, ctx->ghash);
 
-	ahash_request_set_callback(ahreq, aead_request_flags(req),
-				   gcm_hash_init_done, req);
-	err = crypto_ahash_init(ahreq);
-	if (err)
-		return err;
-	remain = gcm_remain(req->assoclen);
-	compl = remain ? gcm_hash_assoc_done : gcm_hash_assoc_remain_done;
-	err = gcm_hash_update(req, pctx, compl, req->assoc, req->assoclen);
-	if (err)
-		return err;
-	if (remain) {
-		err = gcm_hash_remain(req, pctx, remain,
-				      gcm_hash_assoc_remain_done);
-		if (err)
-			return err;
-	}
-	remain = gcm_remain(gctx->cryptlen);
-	compl = remain ? gcm_hash_crypt_done : gcm_hash_crypt_remain_done;
-	err = gcm_hash_update(req, pctx, compl, gctx->src, gctx->cryptlen);
-	if (err)
-		return err;
-	if (remain) {
-		err = gcm_hash_remain(req, pctx, remain,
-				      gcm_hash_crypt_remain_done);
-		if (err)
-			return err;
-	}
-	err = gcm_hash_len(req, pctx);
-	if (err)
-		return err;
-	err = gcm_hash_final(req, pctx);
-	if (err)
-		return err;
-
-	return 0;
+	ahash_request_set_callback(ahreq, flags, gcm_hash_init_done, req);
+	return crypto_ahash_init(ahreq) ?:
+	       gcm_hash_init_continue(req, flags);
 }
 
-static void gcm_enc_copy_hash(struct aead_request *req,
-			      struct crypto_gcm_req_priv_ctx *pctx)
+static int gcm_enc_copy_hash(struct aead_request *req, u32 flags)
 {
+	struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req);
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
 	u8 *auth_tag = pctx->auth_tag;
 
-	scatterwalk_map_and_copy(auth_tag, req->dst, req->cryptlen,
+	crypto_xor(auth_tag, pctx->iauth_tag, 16);
+	scatterwalk_map_and_copy(auth_tag, req->dst,
+				 req->assoclen + req->cryptlen,
 				 crypto_aead_authsize(aead), 1);
+	return 0;
 }
 
-static void gcm_enc_hash_done(struct aead_request *req, int err)
+static int gcm_encrypt_continue(struct aead_request *req, u32 flags)
 {
 	struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req);
+	struct crypto_gcm_ghash_ctx *gctx = &pctx->ghash_ctx;
 
-	if (!err)
-		gcm_enc_copy_hash(req, pctx);
+	gctx->src = sg_next(req->src == req->dst ? pctx->src : pctx->dst);
+	gctx->cryptlen = req->cryptlen;
+	gctx->complete = gcm_enc_copy_hash;
 
-	aead_request_complete(req, err);
+	return gcm_hash(req, flags);
 }
 
 static void gcm_encrypt_done(struct crypto_async_request *areq, int err)
 {
 	struct aead_request *req = areq->data;
-	struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req);
 
-	if (!err) {
-		err = gcm_hash(req, pctx);
-		if (err == -EINPROGRESS || err == -EBUSY)
-			return;
-		else if (!err) {
-			crypto_xor(pctx->auth_tag, pctx->iauth_tag, 16);
-			gcm_enc_copy_hash(req, pctx);
-		}
-	}
+	if (err)
+		goto out;
+
+	err = gcm_encrypt_continue(req, 0);
+	if (err == -EINPROGRESS)
+		return;
 
+out:
 	aead_request_complete(req, err);
 }
 
@@ -546,34 +489,19 @@ static int crypto_gcm_encrypt(struct aead_request *req)
 {
 	struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req);
 	struct ablkcipher_request *abreq = &pctx->u.abreq;
-	struct crypto_gcm_ghash_ctx *gctx = &pctx->ghash_ctx;
-	int err;
-
-	crypto_gcm_init_crypt(abreq, req, req->cryptlen);
-	ablkcipher_request_set_callback(abreq, aead_request_flags(req),
-					gcm_encrypt_done, req);
-
-	gctx->src = req->dst;
-	gctx->cryptlen = req->cryptlen;
-	gctx->complete = gcm_enc_hash_done;
-
-	err = crypto_ablkcipher_encrypt(abreq);
-	if (err)
-		return err;
-
-	err = gcm_hash(req, pctx);
-	if (err)
-		return err;
+	u32 flags = aead_request_flags(req);
 
-	crypto_xor(pctx->auth_tag, pctx->iauth_tag, 16);
-	gcm_enc_copy_hash(req, pctx);
+	crypto_gcm_init_common(req);
+	crypto_gcm_init_crypt(req, req->cryptlen);
+	ablkcipher_request_set_callback(abreq, flags, gcm_encrypt_done, req);
 
-	return 0;
+	return crypto_ablkcipher_encrypt(abreq) ?:
+	       gcm_encrypt_continue(req, flags);
 }
 
-static int crypto_gcm_verify(struct aead_request *req,
-			     struct crypto_gcm_req_priv_ctx *pctx)
+static int crypto_gcm_verify(struct aead_request *req)
 {
+	struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req);
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
 	u8 *auth_tag = pctx->auth_tag;
 	u8 *iauth_tag = pctx->iauth_tag;
@@ -581,78 +509,57 @@ static int crypto_gcm_verify(struct aead_request *req,
 	unsigned int cryptlen = req->cryptlen - authsize;
 
 	crypto_xor(auth_tag, iauth_tag, 16);
-	scatterwalk_map_and_copy(iauth_tag, req->src, cryptlen, authsize, 0);
+	scatterwalk_map_and_copy(iauth_tag, req->src,
+				 req->assoclen + cryptlen, authsize, 0);
 	return crypto_memneq(iauth_tag, auth_tag, authsize) ? -EBADMSG : 0;
 }
 
 static void gcm_decrypt_done(struct crypto_async_request *areq, int err)
 {
 	struct aead_request *req = areq->data;
-	struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req);
 
 	if (!err)
-		err = crypto_gcm_verify(req, pctx);
+		err = crypto_gcm_verify(req);
 
 	aead_request_complete(req, err);
 }
 
-static void gcm_dec_hash_done(struct aead_request *req, int err)
+static int gcm_dec_hash_continue(struct aead_request *req, u32 flags)
 {
 	struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req);
 	struct ablkcipher_request *abreq = &pctx->u.abreq;
 	struct crypto_gcm_ghash_ctx *gctx = &pctx->ghash_ctx;
 
-	if (!err) {
-		ablkcipher_request_set_callback(abreq, aead_request_flags(req),
-						gcm_decrypt_done, req);
-		crypto_gcm_init_crypt(abreq, req, gctx->cryptlen);
-		err = crypto_ablkcipher_decrypt(abreq);
-		if (err == -EINPROGRESS || err == -EBUSY)
-			return;
-		else if (!err)
-			err = crypto_gcm_verify(req, pctx);
-	}
-
-	aead_request_complete(req, err);
+	crypto_gcm_init_crypt(req, gctx->cryptlen);
+	ablkcipher_request_set_callback(abreq, flags, gcm_decrypt_done, req);
+	return crypto_ablkcipher_decrypt(abreq) ?: crypto_gcm_verify(req);
 }
 
 static int crypto_gcm_decrypt(struct aead_request *req)
 {
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
 	struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req);
-	struct ablkcipher_request *abreq = &pctx->u.abreq;
 	struct crypto_gcm_ghash_ctx *gctx = &pctx->ghash_ctx;
 	unsigned int authsize = crypto_aead_authsize(aead);
 	unsigned int cryptlen = req->cryptlen;
-	int err;
+	u32 flags = aead_request_flags(req);
 
-	if (cryptlen < authsize)
-		return -EINVAL;
 	cryptlen -= authsize;
 
-	gctx->src = req->src;
-	gctx->cryptlen = cryptlen;
-	gctx->complete = gcm_dec_hash_done;
-
-	err = gcm_hash(req, pctx);
-	if (err)
-		return err;
+	crypto_gcm_init_common(req);
 
-	ablkcipher_request_set_callback(abreq, aead_request_flags(req),
-					gcm_decrypt_done, req);
-	crypto_gcm_init_crypt(abreq, req, cryptlen);
-	err = crypto_ablkcipher_decrypt(abreq);
-	if (err)
-		return err;
+	gctx->src = sg_next(pctx->src);
+	gctx->cryptlen = cryptlen;
+	gctx->complete = gcm_dec_hash_continue;
 
-	return crypto_gcm_verify(req, pctx);
+	return gcm_hash(req, flags);
 }
 
-static int crypto_gcm_init_tfm(struct crypto_tfm *tfm)
+static int crypto_gcm_init_tfm(struct crypto_aead *tfm)
 {
-	struct crypto_instance *inst = (void *)tfm->__crt_alg;
-	struct gcm_instance_ctx *ictx = crypto_instance_ctx(inst);
-	struct crypto_gcm_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct aead_instance *inst = aead_alg_instance(tfm);
+	struct gcm_instance_ctx *ictx = aead_instance_ctx(inst);
+	struct crypto_gcm_ctx *ctx = crypto_aead_ctx(tfm);
 	struct crypto_ablkcipher *ctr;
 	struct crypto_ahash *ghash;
 	unsigned long align;
@@ -670,14 +577,14 @@ static int crypto_gcm_init_tfm(struct crypto_tfm *tfm)
 	ctx->ctr = ctr;
 	ctx->ghash = ghash;
 
-	align = crypto_tfm_alg_alignmask(tfm);
+	align = crypto_aead_alignmask(tfm);
 	align &= ~(crypto_tfm_ctx_alignment() - 1);
-	tfm->crt_aead.reqsize = align +
-		offsetof(struct crypto_gcm_req_priv_ctx, u) +
+	crypto_aead_set_reqsize(tfm,
+		align + offsetof(struct crypto_gcm_req_priv_ctx, u) +
 		max(sizeof(struct ablkcipher_request) +
 		    crypto_ablkcipher_reqsize(ctr),
 		    sizeof(struct ahash_request) +
-		    crypto_ahash_reqsize(ghash));
+		    crypto_ahash_reqsize(ghash)));
 
 	return 0;
 
@@ -686,53 +593,59 @@ err_free_hash:
 	return err;
 }
 
-static void crypto_gcm_exit_tfm(struct crypto_tfm *tfm)
+static void crypto_gcm_exit_tfm(struct crypto_aead *tfm)
 {
-	struct crypto_gcm_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct crypto_gcm_ctx *ctx = crypto_aead_ctx(tfm);
 
 	crypto_free_ahash(ctx->ghash);
 	crypto_free_ablkcipher(ctx->ctr);
 }
 
-static struct crypto_instance *crypto_gcm_alloc_common(struct rtattr **tb,
-						       const char *full_name,
-						       const char *ctr_name,
-						       const char *ghash_name)
+static int crypto_gcm_create_common(struct crypto_template *tmpl,
+				    struct rtattr **tb,
+				    const char *full_name,
+				    const char *ctr_name,
+				    const char *ghash_name)
 {
 	struct crypto_attr_type *algt;
-	struct crypto_instance *inst;
+	struct aead_instance *inst;
 	struct crypto_alg *ctr;
 	struct crypto_alg *ghash_alg;
-	struct ahash_alg *ghash_ahash_alg;
+	struct hash_alg_common *ghash;
 	struct gcm_instance_ctx *ctx;
 	int err;
 
 	algt = crypto_get_attr_type(tb);
 	if (IS_ERR(algt))
-		return ERR_CAST(algt);
+		return PTR_ERR(algt);
 
 	if ((algt->type ^ CRYPTO_ALG_TYPE_AEAD) & algt->mask)
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 
 	ghash_alg = crypto_find_alg(ghash_name, &crypto_ahash_type,
 				    CRYPTO_ALG_TYPE_HASH,
 				    CRYPTO_ALG_TYPE_AHASH_MASK);
 	if (IS_ERR(ghash_alg))
-		return ERR_CAST(ghash_alg);
+		return PTR_ERR(ghash_alg);
+
+	ghash = __crypto_hash_alg_common(ghash_alg);
 
 	err = -ENOMEM;
 	inst = kzalloc(sizeof(*inst) + sizeof(*ctx), GFP_KERNEL);
 	if (!inst)
 		goto out_put_ghash;
 
-	ctx = crypto_instance_ctx(inst);
-	ghash_ahash_alg = container_of(ghash_alg, struct ahash_alg, halg.base);
-	err = crypto_init_ahash_spawn(&ctx->ghash, &ghash_ahash_alg->halg,
-				      inst);
+	ctx = aead_instance_ctx(inst);
+	err = crypto_init_ahash_spawn(&ctx->ghash, ghash,
+				      aead_crypto_instance(inst));
 	if (err)
 		goto err_free_inst;
 
-	crypto_set_skcipher_spawn(&ctx->ctr, inst);
+	err = -EINVAL;
+	if (ghash->digestsize != 16)
+		goto err_drop_ghash;
+
+	crypto_set_skcipher_spawn(&ctx->ctr, aead_crypto_instance(inst));
 	err = crypto_grab_skcipher(&ctx->ctr, ctr_name, 0,
 				   crypto_requires_sync(algt->type,
 							algt->mask));
@@ -751,33 +664,38 @@ static struct crypto_instance *crypto_gcm_alloc_common(struct rtattr **tb,
 		goto out_put_ctr;
 
 	err = -ENAMETOOLONG;
-	if (snprintf(inst->alg.cra_driver_name, CRYPTO_MAX_ALG_NAME,
+	if (snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME,
 		     "gcm_base(%s,%s)", ctr->cra_driver_name,
 		     ghash_alg->cra_driver_name) >=
 	    CRYPTO_MAX_ALG_NAME)
 		goto out_put_ctr;
 
-	memcpy(inst->alg.cra_name, full_name, CRYPTO_MAX_ALG_NAME);
-
-	inst->alg.cra_flags = CRYPTO_ALG_TYPE_AEAD;
-	inst->alg.cra_flags |= ctr->cra_flags & CRYPTO_ALG_ASYNC;
-	inst->alg.cra_priority = ctr->cra_priority;
-	inst->alg.cra_blocksize = 1;
-	inst->alg.cra_alignmask = ctr->cra_alignmask | (__alignof__(u64) - 1);
-	inst->alg.cra_type = &crypto_aead_type;
-	inst->alg.cra_aead.ivsize = 16;
-	inst->alg.cra_aead.maxauthsize = 16;
-	inst->alg.cra_ctxsize = sizeof(struct crypto_gcm_ctx);
-	inst->alg.cra_init = crypto_gcm_init_tfm;
-	inst->alg.cra_exit = crypto_gcm_exit_tfm;
-	inst->alg.cra_aead.setkey = crypto_gcm_setkey;
-	inst->alg.cra_aead.setauthsize = crypto_gcm_setauthsize;
-	inst->alg.cra_aead.encrypt = crypto_gcm_encrypt;
-	inst->alg.cra_aead.decrypt = crypto_gcm_decrypt;
+	memcpy(inst->alg.base.cra_name, full_name, CRYPTO_MAX_ALG_NAME);
+
+	inst->alg.base.cra_flags = (ghash->base.cra_flags | ctr->cra_flags) &
+				   CRYPTO_ALG_ASYNC;
+	inst->alg.base.cra_priority = (ghash->base.cra_priority +
+				       ctr->cra_priority) / 2;
+	inst->alg.base.cra_blocksize = 1;
+	inst->alg.base.cra_alignmask = ghash->base.cra_alignmask |
+				       ctr->cra_alignmask;
+	inst->alg.base.cra_ctxsize = sizeof(struct crypto_gcm_ctx);
+	inst->alg.ivsize = 12;
+	inst->alg.maxauthsize = 16;
+	inst->alg.init = crypto_gcm_init_tfm;
+	inst->alg.exit = crypto_gcm_exit_tfm;
+	inst->alg.setkey = crypto_gcm_setkey;
+	inst->alg.setauthsize = crypto_gcm_setauthsize;
+	inst->alg.encrypt = crypto_gcm_encrypt;
+	inst->alg.decrypt = crypto_gcm_decrypt;
+
+	err = aead_register_instance(tmpl, inst);
+	if (err)
+		goto out_put_ctr;
 
-out:
+out_put_ghash:
 	crypto_mod_put(ghash_alg);
-	return inst;
+	return err;
 
 out_put_ctr:
 	crypto_drop_skcipher(&ctx->ctr);
@@ -785,12 +703,10 @@ err_drop_ghash:
 	crypto_drop_ahash(&ctx->ghash);
 err_free_inst:
 	kfree(inst);
-out_put_ghash:
-	inst = ERR_PTR(err);
-	goto out;
+	goto out_put_ghash;
 }
 
-static struct crypto_instance *crypto_gcm_alloc(struct rtattr **tb)
+static int crypto_gcm_create(struct crypto_template *tmpl, struct rtattr **tb)
 {
 	const char *cipher_name;
 	char ctr_name[CRYPTO_MAX_ALG_NAME];
@@ -798,17 +714,18 @@ static struct crypto_instance *crypto_gcm_alloc(struct rtattr **tb)
 
 	cipher_name = crypto_attr_alg_name(tb[1]);
 	if (IS_ERR(cipher_name))
-		return ERR_CAST(cipher_name);
+		return PTR_ERR(cipher_name);
 
 	if (snprintf(ctr_name, CRYPTO_MAX_ALG_NAME, "ctr(%s)", cipher_name) >=
 	    CRYPTO_MAX_ALG_NAME)
-		return ERR_PTR(-ENAMETOOLONG);
+		return -ENAMETOOLONG;
 
 	if (snprintf(full_name, CRYPTO_MAX_ALG_NAME, "gcm(%s)", cipher_name) >=
 	    CRYPTO_MAX_ALG_NAME)
-		return ERR_PTR(-ENAMETOOLONG);
+		return -ENAMETOOLONG;
 
-	return crypto_gcm_alloc_common(tb, full_name, ctr_name, "ghash");
+	return crypto_gcm_create_common(tmpl, tb, full_name,
+					ctr_name, "ghash");
 }
 
 static void crypto_gcm_free(struct crypto_instance *inst)
@@ -817,17 +734,18 @@ static void crypto_gcm_free(struct crypto_instance *inst)
 
 	crypto_drop_skcipher(&ctx->ctr);
 	crypto_drop_ahash(&ctx->ghash);
-	kfree(inst);
+	kfree(aead_instance(inst));
 }
 
 static struct crypto_template crypto_gcm_tmpl = {
 	.name = "gcm",
-	.alloc = crypto_gcm_alloc,
+	.create = crypto_gcm_create,
 	.free = crypto_gcm_free,
 	.module = THIS_MODULE,
 };
 
-static struct crypto_instance *crypto_gcm_base_alloc(struct rtattr **tb)
+static int crypto_gcm_base_create(struct crypto_template *tmpl,
+				  struct rtattr **tb)
 {
 	const char *ctr_name;
 	const char *ghash_name;
@@ -835,22 +753,23 @@ static struct crypto_instance *crypto_gcm_base_alloc(struct rtattr **tb)
 
 	ctr_name = crypto_attr_alg_name(tb[1]);
 	if (IS_ERR(ctr_name))
-		return ERR_CAST(ctr_name);
+		return PTR_ERR(ctr_name);
 
 	ghash_name = crypto_attr_alg_name(tb[2]);
 	if (IS_ERR(ghash_name))
-		return ERR_CAST(ghash_name);
+		return PTR_ERR(ghash_name);
 
 	if (snprintf(full_name, CRYPTO_MAX_ALG_NAME, "gcm_base(%s,%s)",
 		     ctr_name, ghash_name) >= CRYPTO_MAX_ALG_NAME)
-		return ERR_PTR(-ENAMETOOLONG);
+		return -ENAMETOOLONG;
 
-	return crypto_gcm_alloc_common(tb, full_name, ctr_name, ghash_name);
+	return crypto_gcm_create_common(tmpl, tb, full_name,
+					ctr_name, ghash_name);
 }
 
 static struct crypto_template crypto_gcm_base_tmpl = {
 	.name = "gcm_base",
-	.alloc = crypto_gcm_base_alloc,
+	.create = crypto_gcm_base_create,
 	.free = crypto_gcm_free,
 	.module = THIS_MODULE,
 };
@@ -911,7 +830,7 @@ static struct aead_request *crypto_rfc4106_crypt(struct aead_request *req)
 	aead_request_set_callback(subreq, req->base.flags, req->base.complete,
 				  req->base.data);
 	aead_request_set_crypt(subreq, req->src, req->dst, req->cryptlen, iv);
-	aead_request_set_assoc(subreq, req->assoc, req->assoclen);
+	aead_request_set_ad(subreq, req->assoclen);
 
 	return subreq;
 }
@@ -930,11 +849,11 @@ static int crypto_rfc4106_decrypt(struct aead_request *req)
 	return crypto_aead_decrypt(req);
 }
 
-static int crypto_rfc4106_init_tfm(struct crypto_tfm *tfm)
+static int crypto_rfc4106_init_tfm(struct crypto_aead *tfm)
 {
-	struct crypto_instance *inst = (void *)tfm->__crt_alg;
-	struct crypto_aead_spawn *spawn = crypto_instance_ctx(inst);
-	struct crypto_rfc4106_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct aead_instance *inst = aead_alg_instance(tfm);
+	struct crypto_aead_spawn *spawn = aead_instance_ctx(inst);
+	struct crypto_rfc4106_ctx *ctx = crypto_aead_ctx(tfm);
 	struct crypto_aead *aead;
 	unsigned long align;
 
@@ -946,126 +865,120 @@ static int crypto_rfc4106_init_tfm(struct crypto_tfm *tfm)
 
 	align = crypto_aead_alignmask(aead);
 	align &= ~(crypto_tfm_ctx_alignment() - 1);
-	tfm->crt_aead.reqsize = sizeof(struct aead_request) +
-				ALIGN(crypto_aead_reqsize(aead),
-				      crypto_tfm_ctx_alignment()) +
-				align + 16;
+	crypto_aead_set_reqsize(
+		tfm,
+		sizeof(struct aead_request) +
+		ALIGN(crypto_aead_reqsize(aead), crypto_tfm_ctx_alignment()) +
+		align + 12);
 
 	return 0;
 }
 
-static void crypto_rfc4106_exit_tfm(struct crypto_tfm *tfm)
+static void crypto_rfc4106_exit_tfm(struct crypto_aead *tfm)
 {
-	struct crypto_rfc4106_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct crypto_rfc4106_ctx *ctx = crypto_aead_ctx(tfm);
 
 	crypto_free_aead(ctx->child);
 }
 
-static struct crypto_instance *crypto_rfc4106_alloc(struct rtattr **tb)
+static int crypto_rfc4106_create(struct crypto_template *tmpl,
+				 struct rtattr **tb)
 {
 	struct crypto_attr_type *algt;
-	struct crypto_instance *inst;
+	struct aead_instance *inst;
 	struct crypto_aead_spawn *spawn;
-	struct crypto_alg *alg;
+	struct aead_alg *alg;
 	const char *ccm_name;
 	int err;
 
 	algt = crypto_get_attr_type(tb);
 	if (IS_ERR(algt))
-		return ERR_CAST(algt);
+		return PTR_ERR(algt);
 
 	if ((algt->type ^ CRYPTO_ALG_TYPE_AEAD) & algt->mask)
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 
 	ccm_name = crypto_attr_alg_name(tb[1]);
 	if (IS_ERR(ccm_name))
-		return ERR_CAST(ccm_name);
+		return PTR_ERR(ccm_name);
 
 	inst = kzalloc(sizeof(*inst) + sizeof(*spawn), GFP_KERNEL);
 	if (!inst)
-		return ERR_PTR(-ENOMEM);
+		return -ENOMEM;
 
-	spawn = crypto_instance_ctx(inst);
-	crypto_set_aead_spawn(spawn, inst);
+	spawn = aead_instance_ctx(inst);
+	crypto_set_aead_spawn(spawn, aead_crypto_instance(inst));
 	err = crypto_grab_aead(spawn, ccm_name, 0,
 			       crypto_requires_sync(algt->type, algt->mask));
 	if (err)
 		goto out_free_inst;
 
-	alg = crypto_aead_spawn_alg(spawn);
+	alg = crypto_spawn_aead_alg(spawn);
 
 	err = -EINVAL;
 
-	/* We only support 16-byte blocks. */
-	if (alg->cra_aead.ivsize != 16)
+	/* Underlying IV size must be 12. */
+	if (crypto_aead_alg_ivsize(alg) != 12)
 		goto out_drop_alg;
 
 	/* Not a stream cipher? */
-	if (alg->cra_blocksize != 1)
+	if (alg->base.cra_blocksize != 1)
 		goto out_drop_alg;
 
 	err = -ENAMETOOLONG;
-	if (snprintf(inst->alg.cra_name, CRYPTO_MAX_ALG_NAME,
-		     "rfc4106(%s)", alg->cra_name) >= CRYPTO_MAX_ALG_NAME ||
-	    snprintf(inst->alg.cra_driver_name, CRYPTO_MAX_ALG_NAME,
-		     "rfc4106(%s)", alg->cra_driver_name) >=
+	if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME,
+		     "rfc4106(%s)", alg->base.cra_name) >=
+	    CRYPTO_MAX_ALG_NAME ||
+	    snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME,
+		     "rfc4106(%s)", alg->base.cra_driver_name) >=
 	    CRYPTO_MAX_ALG_NAME)
 		goto out_drop_alg;
 
-	inst->alg.cra_flags = CRYPTO_ALG_TYPE_AEAD;
-	inst->alg.cra_flags |= alg->cra_flags & CRYPTO_ALG_ASYNC;
-	inst->alg.cra_priority = alg->cra_priority;
-	inst->alg.cra_blocksize = 1;
-	inst->alg.cra_alignmask = alg->cra_alignmask;
-	inst->alg.cra_type = &crypto_nivaead_type;
+	inst->alg.base.cra_flags |= alg->base.cra_flags & CRYPTO_ALG_ASYNC;
+	inst->alg.base.cra_priority = alg->base.cra_priority;
+	inst->alg.base.cra_blocksize = 1;
+	inst->alg.base.cra_alignmask = alg->base.cra_alignmask;
 
-	inst->alg.cra_aead.ivsize = 8;
-	inst->alg.cra_aead.maxauthsize = 16;
+	inst->alg.base.cra_ctxsize = sizeof(struct crypto_rfc4106_ctx);
 
-	inst->alg.cra_ctxsize = sizeof(struct crypto_rfc4106_ctx);
+	inst->alg.ivsize = 8;
+	inst->alg.maxauthsize = crypto_aead_alg_maxauthsize(alg);
 
-	inst->alg.cra_init = crypto_rfc4106_init_tfm;
-	inst->alg.cra_exit = crypto_rfc4106_exit_tfm;
+	inst->alg.init = crypto_rfc4106_init_tfm;
+	inst->alg.exit = crypto_rfc4106_exit_tfm;
 
-	inst->alg.cra_aead.setkey = crypto_rfc4106_setkey;
-	inst->alg.cra_aead.setauthsize = crypto_rfc4106_setauthsize;
-	inst->alg.cra_aead.encrypt = crypto_rfc4106_encrypt;
-	inst->alg.cra_aead.decrypt = crypto_rfc4106_decrypt;
+	inst->alg.setkey = crypto_rfc4106_setkey;
+	inst->alg.setauthsize = crypto_rfc4106_setauthsize;
+	inst->alg.encrypt = crypto_rfc4106_encrypt;
+	inst->alg.decrypt = crypto_rfc4106_decrypt;
 
-	inst->alg.cra_aead.geniv = "seqiv";
+	err = aead_register_instance(tmpl, inst);
+	if (err)
+		goto out_drop_alg;
 
 out:
-	return inst;
+	return err;
 
 out_drop_alg:
 	crypto_drop_aead(spawn);
 out_free_inst:
 	kfree(inst);
-	inst = ERR_PTR(err);
 	goto out;
 }
 
 static void crypto_rfc4106_free(struct crypto_instance *inst)
 {
-	crypto_drop_spawn(crypto_instance_ctx(inst));
-	kfree(inst);
+	crypto_drop_aead(crypto_instance_ctx(inst));
+	kfree(aead_instance(inst));
 }
 
 static struct crypto_template crypto_rfc4106_tmpl = {
 	.name = "rfc4106",
-	.alloc = crypto_rfc4106_alloc,
+	.create = crypto_rfc4106_create,
 	.free = crypto_rfc4106_free,
 	.module = THIS_MODULE,
 };
 
-static inline struct crypto_rfc4543_req_ctx *crypto_rfc4543_reqctx(
-	struct aead_request *req)
-{
-	unsigned long align = crypto_aead_alignmask(crypto_aead_reqtfm(req));
-
-	return (void *)PTR_ALIGN((u8 *)aead_request_ctx(req), align + 1);
-}
-
 static int crypto_rfc4543_setkey(struct crypto_aead *parent, const u8 *key,
 				 unsigned int keylen)
 {
@@ -1100,83 +1013,35 @@ static int crypto_rfc4543_setauthsize(struct crypto_aead *parent,
 	return crypto_aead_setauthsize(ctx->child, authsize);
 }
 
-static void crypto_rfc4543_done(struct crypto_async_request *areq, int err)
-{
-	struct aead_request *req = areq->data;
-	struct crypto_aead *aead = crypto_aead_reqtfm(req);
-	struct crypto_rfc4543_req_ctx *rctx = crypto_rfc4543_reqctx(req);
-
-	if (!err) {
-		scatterwalk_map_and_copy(rctx->auth_tag, req->dst,
-					 req->cryptlen,
-					 crypto_aead_authsize(aead), 1);
-	}
-
-	aead_request_complete(req, err);
-}
-
-static struct aead_request *crypto_rfc4543_crypt(struct aead_request *req,
-						 bool enc)
+static int crypto_rfc4543_crypt(struct aead_request *req, bool enc)
 {
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
 	struct crypto_rfc4543_ctx *ctx = crypto_aead_ctx(aead);
-	struct crypto_rfc4543_req_ctx *rctx = crypto_rfc4543_reqctx(req);
+	struct crypto_rfc4543_req_ctx *rctx = aead_request_ctx(req);
 	struct aead_request *subreq = &rctx->subreq;
-	struct scatterlist *src = req->src;
-	struct scatterlist *cipher = rctx->cipher;
-	struct scatterlist *payload = rctx->payload;
-	struct scatterlist *assoc = rctx->assoc;
 	unsigned int authsize = crypto_aead_authsize(aead);
-	unsigned int assoclen = req->assoclen;
-	struct page *srcp;
-	u8 *vsrc;
 	u8 *iv = PTR_ALIGN((u8 *)(rctx + 1) + crypto_aead_reqsize(ctx->child),
 			   crypto_aead_alignmask(ctx->child) + 1);
+	int err;
+
+	if (req->src != req->dst) {
+		err = crypto_rfc4543_copy_src_to_dst(req, enc);
+		if (err)
+			return err;
+	}
 
 	memcpy(iv, ctx->nonce, 4);
 	memcpy(iv + 4, req->iv, 8);
 
-	/* construct cipher/plaintext */
-	if (enc)
-		memset(rctx->auth_tag, 0, authsize);
-	else
-		scatterwalk_map_and_copy(rctx->auth_tag, src,
-					 req->cryptlen - authsize,
-					 authsize, 0);
-
-	sg_init_one(cipher, rctx->auth_tag, authsize);
-
-	/* construct the aad */
-	srcp = sg_page(src);
-	vsrc = PageHighMem(srcp) ? NULL : page_address(srcp) + src->offset;
-
-	sg_init_table(payload, 2);
-	sg_set_buf(payload, req->iv, 8);
-	scatterwalk_crypto_chain(payload, src, vsrc == req->iv + 8, 2);
-	assoclen += 8 + req->cryptlen - (enc ? 0 : authsize);
-
-	if (req->assoc->length == req->assoclen) {
-		sg_init_table(assoc, 2);
-		sg_set_page(assoc, sg_page(req->assoc), req->assoc->length,
-			    req->assoc->offset);
-	} else {
-		BUG_ON(req->assoclen > sizeof(rctx->assocbuf));
-
-		scatterwalk_map_and_copy(rctx->assocbuf, req->assoc, 0,
-					 req->assoclen, 0);
-
-		sg_init_table(assoc, 2);
-		sg_set_buf(assoc, rctx->assocbuf, req->assoclen);
-	}
-	scatterwalk_crypto_chain(assoc, payload, 0, 2);
-
 	aead_request_set_tfm(subreq, ctx->child);
-	aead_request_set_callback(subreq, req->base.flags, crypto_rfc4543_done,
-				  req);
-	aead_request_set_crypt(subreq, cipher, cipher, enc ? 0 : authsize, iv);
-	aead_request_set_assoc(subreq, assoc, assoclen);
-
-	return subreq;
+	aead_request_set_callback(subreq, req->base.flags,
+				  req->base.complete, req->base.data);
+	aead_request_set_crypt(subreq, req->src, req->dst,
+			       enc ? 0 : authsize, iv);
+	aead_request_set_ad(subreq, req->assoclen + req->cryptlen -
+				    subreq->cryptlen);
+
+	return enc ? crypto_aead_encrypt(subreq) : crypto_aead_decrypt(subreq);
 }
 
 static int crypto_rfc4543_copy_src_to_dst(struct aead_request *req, bool enc)
@@ -1184,7 +1049,8 @@ static int crypto_rfc4543_copy_src_to_dst(struct aead_request *req, bool enc)
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
 	struct crypto_rfc4543_ctx *ctx = crypto_aead_ctx(aead);
 	unsigned int authsize = crypto_aead_authsize(aead);
-	unsigned int nbytes = req->cryptlen - (enc ? 0 : authsize);
+	unsigned int nbytes = req->assoclen + req->cryptlen -
+			      (enc ? 0 : authsize);
 	struct blkcipher_desc desc = {
 		.tfm = ctx->null,
 	};
@@ -1194,49 +1060,20 @@ static int crypto_rfc4543_copy_src_to_dst(struct aead_request *req, bool enc)
 
 static int crypto_rfc4543_encrypt(struct aead_request *req)
 {
-	struct crypto_aead *aead = crypto_aead_reqtfm(req);
-	struct crypto_rfc4543_req_ctx *rctx = crypto_rfc4543_reqctx(req);
-	struct aead_request *subreq;
-	int err;
-
-	if (req->src != req->dst) {
-		err = crypto_rfc4543_copy_src_to_dst(req, true);
-		if (err)
-			return err;
-	}
-
-	subreq = crypto_rfc4543_crypt(req, true);
-	err = crypto_aead_encrypt(subreq);
-	if (err)
-		return err;
-
-	scatterwalk_map_and_copy(rctx->auth_tag, req->dst, req->cryptlen,
-				 crypto_aead_authsize(aead), 1);
-
-	return 0;
+	return crypto_rfc4543_crypt(req, true);
 }
 
 static int crypto_rfc4543_decrypt(struct aead_request *req)
 {
-	int err;
-
-	if (req->src != req->dst) {
-		err = crypto_rfc4543_copy_src_to_dst(req, false);
-		if (err)
-			return err;
-	}
-
-	req = crypto_rfc4543_crypt(req, false);
-
-	return crypto_aead_decrypt(req);
+	return crypto_rfc4543_crypt(req, false);
 }
 
-static int crypto_rfc4543_init_tfm(struct crypto_tfm *tfm)
+static int crypto_rfc4543_init_tfm(struct crypto_aead *tfm)
 {
-	struct crypto_instance *inst = (void *)tfm->__crt_alg;
-	struct crypto_rfc4543_instance_ctx *ictx = crypto_instance_ctx(inst);
+	struct aead_instance *inst = aead_alg_instance(tfm);
+	struct crypto_rfc4543_instance_ctx *ictx = aead_instance_ctx(inst);
 	struct crypto_aead_spawn *spawn = &ictx->aead;
-	struct crypto_rfc4543_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct crypto_rfc4543_ctx *ctx = crypto_aead_ctx(tfm);
 	struct crypto_aead *aead;
 	struct crypto_blkcipher *null;
 	unsigned long align;
@@ -1246,7 +1083,7 @@ static int crypto_rfc4543_init_tfm(struct crypto_tfm *tfm)
 	if (IS_ERR(aead))
 		return PTR_ERR(aead);
 
-	null = crypto_spawn_blkcipher(&ictx->null.base);
+	null = crypto_get_default_null_skcipher();
 	err = PTR_ERR(null);
 	if (IS_ERR(null))
 		goto err_free_aead;
@@ -1256,10 +1093,11 @@ static int crypto_rfc4543_init_tfm(struct crypto_tfm *tfm)
 
 	align = crypto_aead_alignmask(aead);
 	align &= ~(crypto_tfm_ctx_alignment() - 1);
-	tfm->crt_aead.reqsize = sizeof(struct crypto_rfc4543_req_ctx) +
-				ALIGN(crypto_aead_reqsize(aead),
-				      crypto_tfm_ctx_alignment()) +
-				align + 16;
+	crypto_aead_set_reqsize(
+		tfm,
+		sizeof(struct crypto_rfc4543_req_ctx) +
+		ALIGN(crypto_aead_reqsize(aead), crypto_tfm_ctx_alignment()) +
+		align + 12);
 
 	return 0;
 
@@ -1268,107 +1106,98 @@ err_free_aead:
 	return err;
 }
 
-static void crypto_rfc4543_exit_tfm(struct crypto_tfm *tfm)
+static void crypto_rfc4543_exit_tfm(struct crypto_aead *tfm)
 {
-	struct crypto_rfc4543_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct crypto_rfc4543_ctx *ctx = crypto_aead_ctx(tfm);
 
 	crypto_free_aead(ctx->child);
-	crypto_free_blkcipher(ctx->null);
+	crypto_put_default_null_skcipher();
 }
 
-static struct crypto_instance *crypto_rfc4543_alloc(struct rtattr **tb)
+static int crypto_rfc4543_create(struct crypto_template *tmpl,
+				struct rtattr **tb)
 {
 	struct crypto_attr_type *algt;
-	struct crypto_instance *inst;
+	struct aead_instance *inst;
 	struct crypto_aead_spawn *spawn;
-	struct crypto_alg *alg;
+	struct aead_alg *alg;
 	struct crypto_rfc4543_instance_ctx *ctx;
 	const char *ccm_name;
 	int err;
 
 	algt = crypto_get_attr_type(tb);
 	if (IS_ERR(algt))
-		return ERR_CAST(algt);
+		return PTR_ERR(algt);
 
 	if ((algt->type ^ CRYPTO_ALG_TYPE_AEAD) & algt->mask)
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 
 	ccm_name = crypto_attr_alg_name(tb[1]);
 	if (IS_ERR(ccm_name))
-		return ERR_CAST(ccm_name);
+		return PTR_ERR(ccm_name);
 
 	inst = kzalloc(sizeof(*inst) + sizeof(*ctx), GFP_KERNEL);
 	if (!inst)
-		return ERR_PTR(-ENOMEM);
+		return -ENOMEM;
 
-	ctx = crypto_instance_ctx(inst);
+	ctx = aead_instance_ctx(inst);
 	spawn = &ctx->aead;
-	crypto_set_aead_spawn(spawn, inst);
+	crypto_set_aead_spawn(spawn, aead_crypto_instance(inst));
 	err = crypto_grab_aead(spawn, ccm_name, 0,
 			       crypto_requires_sync(algt->type, algt->mask));
 	if (err)
 		goto out_free_inst;
 
-	alg = crypto_aead_spawn_alg(spawn);
-
-	crypto_set_skcipher_spawn(&ctx->null, inst);
-	err = crypto_grab_skcipher(&ctx->null, "ecb(cipher_null)", 0,
-				   CRYPTO_ALG_ASYNC);
-	if (err)
-		goto out_drop_alg;
-
-	crypto_skcipher_spawn_alg(&ctx->null);
+	alg = crypto_spawn_aead_alg(spawn);
 
 	err = -EINVAL;
 
-	/* We only support 16-byte blocks. */
-	if (alg->cra_aead.ivsize != 16)
-		goto out_drop_ecbnull;
+	/* Underlying IV size must be 12. */
+	if (crypto_aead_alg_ivsize(alg) != 12)
+		goto out_drop_alg;
 
 	/* Not a stream cipher? */
-	if (alg->cra_blocksize != 1)
-		goto out_drop_ecbnull;
+	if (alg->base.cra_blocksize != 1)
+		goto out_drop_alg;
 
 	err = -ENAMETOOLONG;
-	if (snprintf(inst->alg.cra_name, CRYPTO_MAX_ALG_NAME,
-		     "rfc4543(%s)", alg->cra_name) >= CRYPTO_MAX_ALG_NAME ||
-	    snprintf(inst->alg.cra_driver_name, CRYPTO_MAX_ALG_NAME,
-		     "rfc4543(%s)", alg->cra_driver_name) >=
+	if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME,
+		     "rfc4543(%s)", alg->base.cra_name) >=
+	    CRYPTO_MAX_ALG_NAME ||
+	    snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME,
+		     "rfc4543(%s)", alg->base.cra_driver_name) >=
 	    CRYPTO_MAX_ALG_NAME)
-		goto out_drop_ecbnull;
+		goto out_drop_alg;
 
-	inst->alg.cra_flags = CRYPTO_ALG_TYPE_AEAD;
-	inst->alg.cra_flags |= alg->cra_flags & CRYPTO_ALG_ASYNC;
-	inst->alg.cra_priority = alg->cra_priority;
-	inst->alg.cra_blocksize = 1;
-	inst->alg.cra_alignmask = alg->cra_alignmask;
-	inst->alg.cra_type = &crypto_nivaead_type;
+	inst->alg.base.cra_flags = alg->base.cra_flags & CRYPTO_ALG_ASYNC;
+	inst->alg.base.cra_priority = alg->base.cra_priority;
+	inst->alg.base.cra_blocksize = 1;
+	inst->alg.base.cra_alignmask = alg->base.cra_alignmask;
 
-	inst->alg.cra_aead.ivsize = 8;
-	inst->alg.cra_aead.maxauthsize = 16;
+	inst->alg.base.cra_ctxsize = sizeof(struct crypto_rfc4543_ctx);
 
-	inst->alg.cra_ctxsize = sizeof(struct crypto_rfc4543_ctx);
+	inst->alg.ivsize = 8;
+	inst->alg.maxauthsize = crypto_aead_alg_maxauthsize(alg);
 
-	inst->alg.cra_init = crypto_rfc4543_init_tfm;
-	inst->alg.cra_exit = crypto_rfc4543_exit_tfm;
+	inst->alg.init = crypto_rfc4543_init_tfm;
+	inst->alg.exit = crypto_rfc4543_exit_tfm;
 
-	inst->alg.cra_aead.setkey = crypto_rfc4543_setkey;
-	inst->alg.cra_aead.setauthsize = crypto_rfc4543_setauthsize;
-	inst->alg.cra_aead.encrypt = crypto_rfc4543_encrypt;
-	inst->alg.cra_aead.decrypt = crypto_rfc4543_decrypt;
+	inst->alg.setkey = crypto_rfc4543_setkey;
+	inst->alg.setauthsize = crypto_rfc4543_setauthsize;
+	inst->alg.encrypt = crypto_rfc4543_encrypt;
+	inst->alg.decrypt = crypto_rfc4543_decrypt;
 
-	inst->alg.cra_aead.geniv = "seqiv";
+	err = aead_register_instance(tmpl, inst);
+	if (err)
+		goto out_drop_alg;
 
 out:
-	return inst;
+	return err;
 
-out_drop_ecbnull:
-	crypto_drop_skcipher(&ctx->null);
 out_drop_alg:
 	crypto_drop_aead(spawn);
 out_free_inst:
 	kfree(inst);
-	inst = ERR_PTR(err);
 	goto out;
 }
 
@@ -1377,14 +1206,13 @@ static void crypto_rfc4543_free(struct crypto_instance *inst)
 	struct crypto_rfc4543_instance_ctx *ctx = crypto_instance_ctx(inst);
 
 	crypto_drop_aead(&ctx->aead);
-	crypto_drop_skcipher(&ctx->null);
 
-	kfree(inst);
+	kfree(aead_instance(inst));
 }
 
 static struct crypto_template crypto_rfc4543_tmpl = {
 	.name = "rfc4543",
-	.alloc = crypto_rfc4543_alloc,
+	.create = crypto_rfc4543_create,
 	.free = crypto_rfc4543_free,
 	.module = THIS_MODULE,
 };
@@ -1393,10 +1221,12 @@ static int __init crypto_gcm_module_init(void)
 {
 	int err;
 
-	gcm_zeroes = kzalloc(16, GFP_KERNEL);
+	gcm_zeroes = kzalloc(sizeof(*gcm_zeroes), GFP_KERNEL);
 	if (!gcm_zeroes)
 		return -ENOMEM;
 
+	sg_init_one(&gcm_zeroes->sg, gcm_zeroes->buf, sizeof(gcm_zeroes->buf));
+
 	err = crypto_register_template(&crypto_gcm_base_tmpl);
 	if (err)
 		goto out;
diff --git a/crypto/internal.h b/crypto/internal.h
index bd39bfc92eab..00e42a3ed814 100644
--- a/crypto/internal.h
+++ b/crypto/internal.h
@@ -25,7 +25,6 @@
 #include <linux/notifier.h>
 #include <linux/rwsem.h>
 #include <linux/slab.h>
-#include <linux/fips.h>
 
 /* Crypto notification events. */
 enum {
@@ -103,6 +102,8 @@ int crypto_register_notifier(struct notifier_block *nb);
 int crypto_unregister_notifier(struct notifier_block *nb);
 int crypto_probing_notify(unsigned long val, void *v);
 
+unsigned int crypto_alg_extsize(struct crypto_alg *alg);
+
 static inline struct crypto_alg *crypto_alg_get(struct crypto_alg *alg)
 {
 	atomic_inc(&alg->cra_refcnt);
diff --git a/crypto/jitterentropy.c b/crypto/jitterentropy.c
new file mode 100644
index 000000000000..d3c30452edee
--- /dev/null
+++ b/crypto/jitterentropy.c
@@ -0,0 +1,928 @@
+/*
+ * Non-physical true random number generator based on timing jitter.
+ *
+ * Copyright Stephan Mueller <smueller@chronox.de>, 2014
+ *
+ * Design
+ * ======
+ *
+ * See http://www.chronox.de/jent.html
+ *
+ * License
+ * =======
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, and the entire permission notice in its entirety,
+ *    including the disclaimer of warranties.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. The name of the author may not be used to endorse or promote
+ *    products derived from this software without specific prior
+ *    written permission.
+ *
+ * ALTERNATIVELY, this product may be distributed under the terms of
+ * the GNU General Public License, in which case the provisions of the GPL2 are
+ * required INSTEAD OF the above restrictions.  (This clause is
+ * necessary due to a potential bad interaction between the GPL and
+ * the restrictions contained in a BSD-style copyright.)
+ *
+ * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
+ * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
+ * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE, ALL OF
+ * WHICH ARE HEREBY DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT
+ * OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+ * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE
+ * USE OF THIS SOFTWARE, EVEN IF NOT ADVISED OF THE POSSIBILITY OF SUCH
+ * DAMAGE.
+ */
+
+/*
+ * This Jitterentropy RNG is based on the jitterentropy library
+ * version 1.1.0 provided at http://www.chronox.de/jent.html
+ */
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/fips.h>
+#include <linux/time.h>
+#include <linux/crypto.h>
+#include <crypto/internal/rng.h>
+
+/* The entropy pool */
+struct rand_data {
+	/* all data values that are vital to maintain the security
+	 * of the RNG are marked as SENSITIVE. A user must not
+	 * access that information while the RNG executes its loops to
+	 * calculate the next random value. */
+	__u64 data;		/* SENSITIVE Actual random number */
+	__u64 old_data;		/* SENSITIVE Previous random number */
+	__u64 prev_time;	/* SENSITIVE Previous time stamp */
+#define DATA_SIZE_BITS ((sizeof(__u64)) * 8)
+	__u64 last_delta;	/* SENSITIVE stuck test */
+	__s64 last_delta2;	/* SENSITIVE stuck test */
+	unsigned int stuck:1;	/* Time measurement stuck */
+	unsigned int osr;	/* Oversample rate */
+	unsigned int stir:1;		/* Post-processing stirring */
+	unsigned int disable_unbias:1;	/* Deactivate Von-Neuman unbias */
+#define JENT_MEMORY_BLOCKS 64
+#define JENT_MEMORY_BLOCKSIZE 32
+#define JENT_MEMORY_ACCESSLOOPS 128
+#define JENT_MEMORY_SIZE (JENT_MEMORY_BLOCKS*JENT_MEMORY_BLOCKSIZE)
+	unsigned char *mem;	/* Memory access location with size of
+				 * memblocks * memblocksize */
+	unsigned int memlocation; /* Pointer to byte in *mem */
+	unsigned int memblocks;	/* Number of memory blocks in *mem */
+	unsigned int memblocksize; /* Size of one memory block in bytes */
+	unsigned int memaccessloops; /* Number of memory accesses per random
+				      * bit generation */
+};
+
+/* Flags that can be used to initialize the RNG */
+#define JENT_DISABLE_STIR (1<<0) /* Disable stirring the entropy pool */
+#define JENT_DISABLE_UNBIAS (1<<1) /* Disable the Von-Neuman Unbiaser */
+#define JENT_DISABLE_MEMORY_ACCESS (1<<2) /* Disable memory access for more
+					   * entropy, saves MEMORY_SIZE RAM for
+					   * entropy collector */
+
+#define DRIVER_NAME     "jitterentropy"
+
+/* -- error codes for init function -- */
+#define JENT_ENOTIME		1 /* Timer service not available */
+#define JENT_ECOARSETIME	2 /* Timer too coarse for RNG */
+#define JENT_ENOMONOTONIC	3 /* Timer is not monotonic increasing */
+#define JENT_EMINVARIATION	4 /* Timer variations too small for RNG */
+#define JENT_EVARVAR		5 /* Timer does not produce variations of
+				   * variations (2nd derivation of time is
+				   * zero). */
+#define JENT_EMINVARVAR		6 /* Timer variations of variations is tooi
+				   * small. */
+
+/***************************************************************************
+ * Helper functions
+ ***************************************************************************/
+
+static inline void jent_get_nstime(__u64 *out)
+{
+	struct timespec ts;
+	__u64 tmp = 0;
+
+	tmp = random_get_entropy();
+
+	/*
+	 * If random_get_entropy does not return a value (which is possible on,
+	 * for example, MIPS), invoke __getnstimeofday
+	 * hoping that there are timers we can work with.
+	 *
+	 * The list of available timers can be obtained from
+	 * /sys/devices/system/clocksource/clocksource0/available_clocksource
+	 * and are registered with clocksource_register()
+	 */
+	if ((0 == tmp) &&
+	   (0 == __getnstimeofday(&ts))) {
+		tmp = ts.tv_sec;
+		tmp = tmp << 32;
+		tmp = tmp | ts.tv_nsec;
+	}
+
+	*out = tmp;
+}
+
+
+/**
+ * Update of the loop count used for the next round of
+ * an entropy collection.
+ *
+ * Input:
+ * @ec entropy collector struct -- may be NULL
+ * @bits is the number of low bits of the timer to consider
+ * @min is the number of bits we shift the timer value to the right at
+ *	the end to make sure we have a guaranteed minimum value
+ *
+ * @return Newly calculated loop counter
+ */
+static __u64 jent_loop_shuffle(struct rand_data *ec,
+			       unsigned int bits, unsigned int min)
+{
+	__u64 time = 0;
+	__u64 shuffle = 0;
+	unsigned int i = 0;
+	unsigned int mask = (1<<bits) - 1;
+
+	jent_get_nstime(&time);
+	/*
+	 * mix the current state of the random number into the shuffle
+	 * calculation to balance that shuffle a bit more
+	 */
+	if (ec)
+		time ^= ec->data;
+	/*
+	 * we fold the time value as much as possible to ensure that as many
+	 * bits of the time stamp are included as possible
+	 */
+	for (i = 0; (DATA_SIZE_BITS / bits) > i; i++) {
+		shuffle ^= time & mask;
+		time = time >> bits;
+	}
+
+	/*
+	 * We add a lower boundary value to ensure we have a minimum
+	 * RNG loop count.
+	 */
+	return (shuffle + (1<<min));
+}
+
+/***************************************************************************
+ * Noise sources
+ ***************************************************************************/
+
+/*
+ * The disabling of the optimizations is performed as documented and assessed
+ * thoroughly in http://www.chronox.de/jent.html. However, instead of disabling
+ * the optimization of the entire C file, only the main functions the jitter is
+ * measured for are not optimized. These functions include the noise sources as
+ * well as the main functions triggering the noise sources. As the time
+ * measurement is done from one invocation of the jitter noise source to the
+ * next, even the execution jitter of the code invoking the noise sources
+ * contribute to the overall randomness as well. The behavior of the RNG and the
+ * statistical characteristics when only the mentioned functions are not
+ * optimized is almost equal to the a completely non-optimized RNG compilation
+ * as tested with the test tools provided at the initially mentioned web site.
+ */
+
+/**
+ * CPU Jitter noise source -- this is the noise source based on the CPU
+ *			      execution time jitter
+ *
+ * This function folds the time into one bit units by iterating
+ * through the DATA_SIZE_BITS bit time value as follows: assume our time value
+ * is 0xabcd
+ * 1st loop, 1st shift generates 0xd000
+ * 1st loop, 2nd shift generates 0x000d
+ * 2nd loop, 1st shift generates 0xcd00
+ * 2nd loop, 2nd shift generates 0x000c
+ * 3rd loop, 1st shift generates 0xbcd0
+ * 3rd loop, 2nd shift generates 0x000b
+ * 4th loop, 1st shift generates 0xabcd
+ * 4th loop, 2nd shift generates 0x000a
+ * Now, the values at the end of the 2nd shifts are XORed together.
+ *
+ * The code is deliberately inefficient and shall stay that way. This function
+ * is the root cause why the code shall be compiled without optimization. This
+ * function not only acts as folding operation, but this function's execution
+ * is used to measure the CPU execution time jitter. Any change to the loop in
+ * this function implies that careful retesting must be done.
+ *
+ * Input:
+ * @ec entropy collector struct -- may be NULL
+ * @time time stamp to be folded
+ * @loop_cnt if a value not equal to 0 is set, use the given value as number of
+ *	     loops to perform the folding
+ *
+ * Output:
+ * @folded result of folding operation
+ *
+ * @return Number of loops the folding operation is performed
+ */
+#pragma GCC push_options
+#pragma GCC optimize ("-O0")
+static __u64 jent_fold_time(struct rand_data *ec, __u64 time,
+			    __u64 *folded, __u64 loop_cnt)
+{
+	unsigned int i;
+	__u64 j = 0;
+	__u64 new = 0;
+#define MAX_FOLD_LOOP_BIT 4
+#define MIN_FOLD_LOOP_BIT 0
+	__u64 fold_loop_cnt =
+		jent_loop_shuffle(ec, MAX_FOLD_LOOP_BIT, MIN_FOLD_LOOP_BIT);
+
+	/*
+	 * testing purposes -- allow test app to set the counter, not
+	 * needed during runtime
+	 */
+	if (loop_cnt)
+		fold_loop_cnt = loop_cnt;
+	for (j = 0; j < fold_loop_cnt; j++) {
+		new = 0;
+		for (i = 1; (DATA_SIZE_BITS) >= i; i++) {
+			__u64 tmp = time << (DATA_SIZE_BITS - i);
+
+			tmp = tmp >> (DATA_SIZE_BITS - 1);
+			new ^= tmp;
+		}
+	}
+	*folded = new;
+	return fold_loop_cnt;
+}
+#pragma GCC pop_options
+
+/**
+ * Memory Access noise source -- this is a noise source based on variations in
+ *				 memory access times
+ *
+ * This function performs memory accesses which will add to the timing
+ * variations due to an unknown amount of CPU wait states that need to be
+ * added when accessing memory. The memory size should be larger than the L1
+ * caches as outlined in the documentation and the associated testing.
+ *
+ * The L1 cache has a very high bandwidth, albeit its access rate is  usually
+ * slower than accessing CPU registers. Therefore, L1 accesses only add minimal
+ * variations as the CPU has hardly to wait. Starting with L2, significant
+ * variations are added because L2 typically does not belong to the CPU any more
+ * and therefore a wider range of CPU wait states is necessary for accesses.
+ * L3 and real memory accesses have even a wider range of wait states. However,
+ * to reliably access either L3 or memory, the ec->mem memory must be quite
+ * large which is usually not desirable.
+ *
+ * Input:
+ * @ec Reference to the entropy collector with the memory access data -- if
+ *     the reference to the memory block to be accessed is NULL, this noise
+ *     source is disabled
+ * @loop_cnt if a value not equal to 0 is set, use the given value as number of
+ *	     loops to perform the folding
+ *
+ * @return Number of memory access operations
+ */
+#pragma GCC push_options
+#pragma GCC optimize ("-O0")
+static unsigned int jent_memaccess(struct rand_data *ec, __u64 loop_cnt)
+{
+	unsigned char *tmpval = NULL;
+	unsigned int wrap = 0;
+	__u64 i = 0;
+#define MAX_ACC_LOOP_BIT 7
+#define MIN_ACC_LOOP_BIT 0
+	__u64 acc_loop_cnt =
+		jent_loop_shuffle(ec, MAX_ACC_LOOP_BIT, MIN_ACC_LOOP_BIT);
+
+	if (NULL == ec || NULL == ec->mem)
+		return 0;
+	wrap = ec->memblocksize * ec->memblocks;
+
+	/*
+	 * testing purposes -- allow test app to set the counter, not
+	 * needed during runtime
+	 */
+	if (loop_cnt)
+		acc_loop_cnt = loop_cnt;
+
+	for (i = 0; i < (ec->memaccessloops + acc_loop_cnt); i++) {
+		tmpval = ec->mem + ec->memlocation;
+		/*
+		 * memory access: just add 1 to one byte,
+		 * wrap at 255 -- memory access implies read
+		 * from and write to memory location
+		 */
+		*tmpval = (*tmpval + 1) & 0xff;
+		/*
+		 * Addition of memblocksize - 1 to pointer
+		 * with wrap around logic to ensure that every
+		 * memory location is hit evenly
+		 */
+		ec->memlocation = ec->memlocation + ec->memblocksize - 1;
+		ec->memlocation = ec->memlocation % wrap;
+	}
+	return i;
+}
+#pragma GCC pop_options
+
+/***************************************************************************
+ * Start of entropy processing logic
+ ***************************************************************************/
+
+/**
+ * Stuck test by checking the:
+ *	1st derivation of the jitter measurement (time delta)
+ *	2nd derivation of the jitter measurement (delta of time deltas)
+ *	3rd derivation of the jitter measurement (delta of delta of time deltas)
+ *
+ * All values must always be non-zero.
+ *
+ * Input:
+ * @ec Reference to entropy collector
+ * @current_delta Jitter time delta
+ *
+ * @return
+ *	0 jitter measurement not stuck (good bit)
+ *	1 jitter measurement stuck (reject bit)
+ */
+static void jent_stuck(struct rand_data *ec, __u64 current_delta)
+{
+	__s64 delta2 = ec->last_delta - current_delta;
+	__s64 delta3 = delta2 - ec->last_delta2;
+
+	ec->last_delta = current_delta;
+	ec->last_delta2 = delta2;
+
+	if (!current_delta || !delta2 || !delta3)
+		ec->stuck = 1;
+}
+
+/**
+ * This is the heart of the entropy generation: calculate time deltas and
+ * use the CPU jitter in the time deltas. The jitter is folded into one
+ * bit. You can call this function the "random bit generator" as it
+ * produces one random bit per invocation.
+ *
+ * WARNING: ensure that ->prev_time is primed before using the output
+ *	    of this function! This can be done by calling this function
+ *	    and not using its result.
+ *
+ * Input:
+ * @entropy_collector Reference to entropy collector
+ *
+ * @return One random bit
+ */
+#pragma GCC push_options
+#pragma GCC optimize ("-O0")
+static __u64 jent_measure_jitter(struct rand_data *ec)
+{
+	__u64 time = 0;
+	__u64 data = 0;
+	__u64 current_delta = 0;
+
+	/* Invoke one noise source before time measurement to add variations */
+	jent_memaccess(ec, 0);
+
+	/*
+	 * Get time stamp and calculate time delta to previous
+	 * invocation to measure the timing variations
+	 */
+	jent_get_nstime(&time);
+	current_delta = time - ec->prev_time;
+	ec->prev_time = time;
+
+	/* Now call the next noise sources which also folds the data */
+	jent_fold_time(ec, current_delta, &data, 0);
+
+	/*
+	 * Check whether we have a stuck measurement. The enforcement
+	 * is performed after the stuck value has been mixed into the
+	 * entropy pool.
+	 */
+	jent_stuck(ec, current_delta);
+
+	return data;
+}
+#pragma GCC pop_options
+
+/**
+ * Von Neuman unbias as explained in RFC 4086 section 4.2. As shown in the
+ * documentation of that RNG, the bits from jent_measure_jitter are considered
+ * independent which implies that the Von Neuman unbias operation is applicable.
+ * A proof of the Von-Neumann unbias operation to remove skews is given in the
+ * document "A proposal for: Functionality classes for random number
+ * generators", version 2.0 by Werner Schindler, section 5.4.1.
+ *
+ * Input:
+ * @entropy_collector Reference to entropy collector
+ *
+ * @return One random bit
+ */
+static __u64 jent_unbiased_bit(struct rand_data *entropy_collector)
+{
+	do {
+		__u64 a = jent_measure_jitter(entropy_collector);
+		__u64 b = jent_measure_jitter(entropy_collector);
+
+		if (a == b)
+			continue;
+		if (1 == a)
+			return 1;
+		else
+			return 0;
+	} while (1);
+}
+
+/**
+ * Shuffle the pool a bit by mixing some value with a bijective function (XOR)
+ * into the pool.
+ *
+ * The function generates a mixer value that depends on the bits set and the
+ * location of the set bits in the random number generated by the entropy
+ * source. Therefore, based on the generated random number, this mixer value
+ * can have 2**64 different values. That mixer value is initialized with the
+ * first two SHA-1 constants. After obtaining the mixer value, it is XORed into
+ * the random number.
+ *
+ * The mixer value is not assumed to contain any entropy. But due to the XOR
+ * operation, it can also not destroy any entropy present in the entropy pool.
+ *
+ * Input:
+ * @entropy_collector Reference to entropy collector
+ */
+static void jent_stir_pool(struct rand_data *entropy_collector)
+{
+	/*
+	 * to shut up GCC on 32 bit, we have to initialize the 64 variable
+	 * with two 32 bit variables
+	 */
+	union c {
+		__u64 u64;
+		__u32 u32[2];
+	};
+	/*
+	 * This constant is derived from the first two 32 bit initialization
+	 * vectors of SHA-1 as defined in FIPS 180-4 section 5.3.1
+	 */
+	union c constant;
+	/*
+	 * The start value of the mixer variable is derived from the third
+	 * and fourth 32 bit initialization vector of SHA-1 as defined in
+	 * FIPS 180-4 section 5.3.1
+	 */
+	union c mixer;
+	unsigned int i = 0;
+
+	/*
+	 * Store the SHA-1 constants in reverse order to make up the 64 bit
+	 * value -- this applies to a little endian system, on a big endian
+	 * system, it reverses as expected. But this really does not matter
+	 * as we do not rely on the specific numbers. We just pick the SHA-1
+	 * constants as they have a good mix of bit set and unset.
+	 */
+	constant.u32[1] = 0x67452301;
+	constant.u32[0] = 0xefcdab89;
+	mixer.u32[1] = 0x98badcfe;
+	mixer.u32[0] = 0x10325476;
+
+	for (i = 0; i < DATA_SIZE_BITS; i++) {
+		/*
+		 * get the i-th bit of the input random number and only XOR
+		 * the constant into the mixer value when that bit is set
+		 */
+		if ((entropy_collector->data >> i) & 1)
+			mixer.u64 ^= constant.u64;
+		mixer.u64 = rol64(mixer.u64, 1);
+	}
+	entropy_collector->data ^= mixer.u64;
+}
+
+/**
+ * Generator of one 64 bit random number
+ * Function fills rand_data->data
+ *
+ * Input:
+ * @ec Reference to entropy collector
+ */
+#pragma GCC push_options
+#pragma GCC optimize ("-O0")
+static void jent_gen_entropy(struct rand_data *ec)
+{
+	unsigned int k = 0;
+
+	/* priming of the ->prev_time value */
+	jent_measure_jitter(ec);
+
+	while (1) {
+		__u64 data = 0;
+
+		if (ec->disable_unbias == 1)
+			data = jent_measure_jitter(ec);
+		else
+			data = jent_unbiased_bit(ec);
+
+		/* enforcement of the jent_stuck test */
+		if (ec->stuck) {
+			/*
+			 * We only mix in the bit considered not appropriate
+			 * without the LSFR. The reason is that if we apply
+			 * the LSFR and we do not rotate, the 2nd bit with LSFR
+			 * will cancel out the first LSFR application on the
+			 * bad bit.
+			 *
+			 * And we do not rotate as we apply the next bit to the
+			 * current bit location again.
+			 */
+			ec->data ^= data;
+			ec->stuck = 0;
+			continue;
+		}
+
+		/*
+		 * Fibonacci LSFR with polynom of
+		 *  x^64 + x^61 + x^56 + x^31 + x^28 + x^23 + 1 which is
+		 *  primitive according to
+		 *   http://poincare.matf.bg.ac.rs/~ezivkovm/publications/primpol1.pdf
+		 * (the shift values are the polynom values minus one
+		 * due to counting bits from 0 to 63). As the current
+		 * position is always the LSB, the polynom only needs
+		 * to shift data in from the left without wrap.
+		 */
+		ec->data ^= data;
+		ec->data ^= ((ec->data >> 63) & 1);
+		ec->data ^= ((ec->data >> 60) & 1);
+		ec->data ^= ((ec->data >> 55) & 1);
+		ec->data ^= ((ec->data >> 30) & 1);
+		ec->data ^= ((ec->data >> 27) & 1);
+		ec->data ^= ((ec->data >> 22) & 1);
+		ec->data = rol64(ec->data, 1);
+
+		/*
+		 * We multiply the loop value with ->osr to obtain the
+		 * oversampling rate requested by the caller
+		 */
+		if (++k >= (DATA_SIZE_BITS * ec->osr))
+			break;
+	}
+	if (ec->stir)
+		jent_stir_pool(ec);
+}
+#pragma GCC pop_options
+
+/**
+ * The continuous test required by FIPS 140-2 -- the function automatically
+ * primes the test if needed.
+ *
+ * Return:
+ * 0 if FIPS test passed
+ * < 0 if FIPS test failed
+ */
+static void jent_fips_test(struct rand_data *ec)
+{
+	if (!fips_enabled)
+		return;
+
+	/* prime the FIPS test */
+	if (!ec->old_data) {
+		ec->old_data = ec->data;
+		jent_gen_entropy(ec);
+	}
+
+	if (ec->data == ec->old_data)
+		panic(DRIVER_NAME ": Duplicate output detected\n");
+
+	ec->old_data = ec->data;
+}
+
+
+/**
+ * Entry function: Obtain entropy for the caller.
+ *
+ * This function invokes the entropy gathering logic as often to generate
+ * as many bytes as requested by the caller. The entropy gathering logic
+ * creates 64 bit per invocation.
+ *
+ * This function truncates the last 64 bit entropy value output to the exact
+ * size specified by the caller.
+ *
+ * Input:
+ * @ec Reference to entropy collector
+ * @data pointer to buffer for storing random data -- buffer must already
+ *	 exist
+ * @len size of the buffer, specifying also the requested number of random
+ *	in bytes
+ *
+ * @return 0 when request is fulfilled or an error
+ *
+ * The following error codes can occur:
+ *	-1	entropy_collector is NULL
+ */
+static ssize_t jent_read_entropy(struct rand_data *ec, u8 *data, size_t len)
+{
+	u8 *p = data;
+
+	if (!ec)
+		return -EINVAL;
+
+	while (0 < len) {
+		size_t tocopy;
+
+		jent_gen_entropy(ec);
+		jent_fips_test(ec);
+		if ((DATA_SIZE_BITS / 8) < len)
+			tocopy = (DATA_SIZE_BITS / 8);
+		else
+			tocopy = len;
+		memcpy(p, &ec->data, tocopy);
+
+		len -= tocopy;
+		p += tocopy;
+	}
+
+	return 0;
+}
+
+/***************************************************************************
+ * Initialization logic
+ ***************************************************************************/
+
+static struct rand_data *jent_entropy_collector_alloc(unsigned int osr,
+						      unsigned int flags)
+{
+	struct rand_data *entropy_collector;
+
+	entropy_collector = kzalloc(sizeof(struct rand_data), GFP_KERNEL);
+	if (!entropy_collector)
+		return NULL;
+
+	if (!(flags & JENT_DISABLE_MEMORY_ACCESS)) {
+		/* Allocate memory for adding variations based on memory
+		 * access
+		 */
+		entropy_collector->mem = kzalloc(JENT_MEMORY_SIZE, GFP_KERNEL);
+		if (!entropy_collector->mem) {
+			kfree(entropy_collector);
+			return NULL;
+		}
+		entropy_collector->memblocksize = JENT_MEMORY_BLOCKSIZE;
+		entropy_collector->memblocks = JENT_MEMORY_BLOCKS;
+		entropy_collector->memaccessloops = JENT_MEMORY_ACCESSLOOPS;
+	}
+
+	/* verify and set the oversampling rate */
+	if (0 == osr)
+		osr = 1; /* minimum sampling rate is 1 */
+	entropy_collector->osr = osr;
+
+	entropy_collector->stir = 1;
+	if (flags & JENT_DISABLE_STIR)
+		entropy_collector->stir = 0;
+	if (flags & JENT_DISABLE_UNBIAS)
+		entropy_collector->disable_unbias = 1;
+
+	/* fill the data pad with non-zero values */
+	jent_gen_entropy(entropy_collector);
+
+	return entropy_collector;
+}
+
+static void jent_entropy_collector_free(struct rand_data *entropy_collector)
+{
+	if (entropy_collector->mem)
+		kzfree(entropy_collector->mem);
+	entropy_collector->mem = NULL;
+	if (entropy_collector)
+		kzfree(entropy_collector);
+	entropy_collector = NULL;
+}
+
+static int jent_entropy_init(void)
+{
+	int i;
+	__u64 delta_sum = 0;
+	__u64 old_delta = 0;
+	int time_backwards = 0;
+	int count_var = 0;
+	int count_mod = 0;
+
+	/* We could perform statistical tests here, but the problem is
+	 * that we only have a few loop counts to do testing. These
+	 * loop counts may show some slight skew and we produce
+	 * false positives.
+	 *
+	 * Moreover, only old systems show potentially problematic
+	 * jitter entropy that could potentially be caught here. But
+	 * the RNG is intended for hardware that is available or widely
+	 * used, but not old systems that are long out of favor. Thus,
+	 * no statistical tests.
+	 */
+
+	/*
+	 * We could add a check for system capabilities such as clock_getres or
+	 * check for CONFIG_X86_TSC, but it does not make much sense as the
+	 * following sanity checks verify that we have a high-resolution
+	 * timer.
+	 */
+	/*
+	 * TESTLOOPCOUNT needs some loops to identify edge systems. 100 is
+	 * definitely too little.
+	 */
+#define TESTLOOPCOUNT 300
+#define CLEARCACHE 100
+	for (i = 0; (TESTLOOPCOUNT + CLEARCACHE) > i; i++) {
+		__u64 time = 0;
+		__u64 time2 = 0;
+		__u64 folded = 0;
+		__u64 delta = 0;
+		unsigned int lowdelta = 0;
+
+		jent_get_nstime(&time);
+		jent_fold_time(NULL, time, &folded, 1<<MIN_FOLD_LOOP_BIT);
+		jent_get_nstime(&time2);
+
+		/* test whether timer works */
+		if (!time || !time2)
+			return JENT_ENOTIME;
+		delta = time2 - time;
+		/*
+		 * test whether timer is fine grained enough to provide
+		 * delta even when called shortly after each other -- this
+		 * implies that we also have a high resolution timer
+		 */
+		if (!delta)
+			return JENT_ECOARSETIME;
+
+		/*
+		 * up to here we did not modify any variable that will be
+		 * evaluated later, but we already performed some work. Thus we
+		 * already have had an impact on the caches, branch prediction,
+		 * etc. with the goal to clear it to get the worst case
+		 * measurements.
+		 */
+		if (CLEARCACHE > i)
+			continue;
+
+		/* test whether we have an increasing timer */
+		if (!(time2 > time))
+			time_backwards++;
+
+		/*
+		 * Avoid modulo of 64 bit integer to allow code to compile
+		 * on 32 bit architectures.
+		 */
+		lowdelta = time2 - time;
+		if (!(lowdelta % 100))
+			count_mod++;
+
+		/*
+		 * ensure that we have a varying delta timer which is necessary
+		 * for the calculation of entropy -- perform this check
+		 * only after the first loop is executed as we need to prime
+		 * the old_data value
+		 */
+		if (i) {
+			if (delta != old_delta)
+				count_var++;
+			if (delta > old_delta)
+				delta_sum += (delta - old_delta);
+			else
+				delta_sum += (old_delta - delta);
+		}
+		old_delta = delta;
+	}
+
+	/*
+	 * we allow up to three times the time running backwards.
+	 * CLOCK_REALTIME is affected by adjtime and NTP operations. Thus,
+	 * if such an operation just happens to interfere with our test, it
+	 * should not fail. The value of 3 should cover the NTP case being
+	 * performed during our test run.
+	 */
+	if (3 < time_backwards)
+		return JENT_ENOMONOTONIC;
+	/* Error if the time variances are always identical */
+	if (!delta_sum)
+		return JENT_EVARVAR;
+
+	/*
+	 * Variations of deltas of time must on average be larger
+	 * than 1 to ensure the entropy estimation
+	 * implied with 1 is preserved
+	 */
+	if (delta_sum <= 1)
+		return JENT_EMINVARVAR;
+
+	/*
+	 * Ensure that we have variations in the time stamp below 10 for at
+	 * least 10% of all checks -- on some platforms, the counter
+	 * increments in multiples of 100, but not always
+	 */
+	if ((TESTLOOPCOUNT/10 * 9) < count_mod)
+		return JENT_ECOARSETIME;
+
+	return 0;
+}
+
+/***************************************************************************
+ * Kernel crypto API interface
+ ***************************************************************************/
+
+struct jitterentropy {
+	spinlock_t jent_lock;
+	struct rand_data *entropy_collector;
+};
+
+static int jent_kcapi_init(struct crypto_tfm *tfm)
+{
+	struct jitterentropy *rng = crypto_tfm_ctx(tfm);
+	int ret = 0;
+
+	rng->entropy_collector = jent_entropy_collector_alloc(1, 0);
+	if (!rng->entropy_collector)
+		ret = -ENOMEM;
+
+	spin_lock_init(&rng->jent_lock);
+	return ret;
+}
+
+static void jent_kcapi_cleanup(struct crypto_tfm *tfm)
+{
+	struct jitterentropy *rng = crypto_tfm_ctx(tfm);
+
+	spin_lock(&rng->jent_lock);
+	if (rng->entropy_collector)
+		jent_entropy_collector_free(rng->entropy_collector);
+	rng->entropy_collector = NULL;
+	spin_unlock(&rng->jent_lock);
+}
+
+static int jent_kcapi_random(struct crypto_rng *tfm,
+			     const u8 *src, unsigned int slen,
+			     u8 *rdata, unsigned int dlen)
+{
+	struct jitterentropy *rng = crypto_rng_ctx(tfm);
+	int ret = 0;
+
+	spin_lock(&rng->jent_lock);
+	ret = jent_read_entropy(rng->entropy_collector, rdata, dlen);
+	spin_unlock(&rng->jent_lock);
+
+	return ret;
+}
+
+static int jent_kcapi_reset(struct crypto_rng *tfm,
+			    const u8 *seed, unsigned int slen)
+{
+	return 0;
+}
+
+static struct rng_alg jent_alg = {
+	.generate		= jent_kcapi_random,
+	.seed			= jent_kcapi_reset,
+	.seedsize		= 0,
+	.base			= {
+		.cra_name               = "jitterentropy_rng",
+		.cra_driver_name        = "jitterentropy_rng",
+		.cra_priority           = 100,
+		.cra_ctxsize            = sizeof(struct jitterentropy),
+		.cra_module             = THIS_MODULE,
+		.cra_init               = jent_kcapi_init,
+		.cra_exit               = jent_kcapi_cleanup,
+
+	}
+};
+
+static int __init jent_mod_init(void)
+{
+	int ret = 0;
+
+	ret = jent_entropy_init();
+	if (ret) {
+		pr_info(DRIVER_NAME ": Initialization failed with host not compliant with requirements: %d\n", ret);
+		return -EFAULT;
+	}
+	return crypto_register_rng(&jent_alg);
+}
+
+static void __exit jent_mod_exit(void)
+{
+	crypto_unregister_rng(&jent_alg);
+}
+
+module_init(jent_mod_init);
+module_exit(jent_mod_exit);
+
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_AUTHOR("Stephan Mueller <smueller@chronox.de>");
+MODULE_DESCRIPTION("Non-physical True Random Number Generator based on CPU Jitter");
+MODULE_ALIAS_CRYPTO("jitterentropy_rng");
diff --git a/crypto/krng.c b/crypto/krng.c
deleted file mode 100644
index 0224841b6579..000000000000
--- a/crypto/krng.c
+++ /dev/null
@@ -1,66 +0,0 @@
-/*
- * RNG implementation using standard kernel RNG.
- *
- * Copyright (c) 2008 Herbert Xu <herbert@gondor.apana.org.au>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the
- * Free Software Foundation; either version 2 of the License, or (at your
- * any later version.
- *
- */
-
-#include <crypto/internal/rng.h>
-#include <linux/err.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/random.h>
-
-static int krng_get_random(struct crypto_rng *tfm, u8 *rdata, unsigned int dlen)
-{
-	get_random_bytes(rdata, dlen);
-	return 0;
-}
-
-static int krng_reset(struct crypto_rng *tfm, u8 *seed, unsigned int slen)
-{
-	return 0;
-}
-
-static struct crypto_alg krng_alg = {
-	.cra_name		= "stdrng",
-	.cra_driver_name	= "krng",
-	.cra_priority		= 200,
-	.cra_flags		= CRYPTO_ALG_TYPE_RNG,
-	.cra_ctxsize		= 0,
-	.cra_type		= &crypto_rng_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u			= {
-		.rng = {
-			.rng_make_random	= krng_get_random,
-			.rng_reset		= krng_reset,
-			.seedsize		= 0,
-		}
-	}
-};
-
-
-/* Module initalization */
-static int __init krng_mod_init(void)
-{
-	return crypto_register_alg(&krng_alg);
-}
-
-static void __exit krng_mod_fini(void)
-{
-	crypto_unregister_alg(&krng_alg);
-	return;
-}
-
-module_init(krng_mod_init);
-module_exit(krng_mod_fini);
-
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("Kernel Random Number Generator");
-MODULE_ALIAS_CRYPTO("stdrng");
-MODULE_ALIAS_CRYPTO("krng");
diff --git a/crypto/md5.c b/crypto/md5.c
index 36f5e5b103f3..33d17e9a8702 100644
--- a/crypto/md5.c
+++ b/crypto/md5.c
@@ -51,10 +51,10 @@ static int md5_init(struct shash_desc *desc)
 {
 	struct md5_state *mctx = shash_desc_ctx(desc);
 
-	mctx->hash[0] = 0x67452301;
-	mctx->hash[1] = 0xefcdab89;
-	mctx->hash[2] = 0x98badcfe;
-	mctx->hash[3] = 0x10325476;
+	mctx->hash[0] = MD5_H0;
+	mctx->hash[1] = MD5_H1;
+	mctx->hash[2] = MD5_H2;
+	mctx->hash[3] = MD5_H3;
 	mctx->byte_count = 0;
 
 	return 0;
diff --git a/crypto/pcompress.c b/crypto/pcompress.c
index 7140fe70c7af..7a13b4088857 100644
--- a/crypto/pcompress.c
+++ b/crypto/pcompress.c
@@ -38,11 +38,6 @@ static int crypto_pcomp_init(struct crypto_tfm *tfm, u32 type, u32 mask)
 	return 0;
 }
 
-static unsigned int crypto_pcomp_extsize(struct crypto_alg *alg)
-{
-	return alg->cra_ctxsize;
-}
-
 static int crypto_pcomp_init_tfm(struct crypto_tfm *tfm)
 {
 	return 0;
@@ -77,7 +72,7 @@ static void crypto_pcomp_show(struct seq_file *m, struct crypto_alg *alg)
 }
 
 static const struct crypto_type crypto_pcomp_type = {
-	.extsize	= crypto_pcomp_extsize,
+	.extsize	= crypto_alg_extsize,
 	.init		= crypto_pcomp_init,
 	.init_tfm	= crypto_pcomp_init_tfm,
 #ifdef CONFIG_PROC_FS
diff --git a/crypto/pcrypt.c b/crypto/pcrypt.c
index c305d4112735..45e7d5155672 100644
--- a/crypto/pcrypt.c
+++ b/crypto/pcrypt.c
@@ -20,6 +20,7 @@
 
 #include <crypto/algapi.h>
 #include <crypto/internal/aead.h>
+#include <linux/atomic.h>
 #include <linux/err.h>
 #include <linux/init.h>
 #include <linux/module.h>
@@ -60,8 +61,8 @@ static struct padata_pcrypt pdecrypt;
 static struct kset           *pcrypt_kset;
 
 struct pcrypt_instance_ctx {
-	struct crypto_spawn spawn;
-	unsigned int tfm_count;
+	struct crypto_aead_spawn spawn;
+	atomic_t tfm_count;
 };
 
 struct pcrypt_aead_ctx {
@@ -122,14 +123,6 @@ static void pcrypt_aead_serial(struct padata_priv *padata)
 	aead_request_complete(req->base.data, padata->info);
 }
 
-static void pcrypt_aead_giv_serial(struct padata_priv *padata)
-{
-	struct pcrypt_request *preq = pcrypt_padata_request(padata);
-	struct aead_givcrypt_request *req = pcrypt_request_ctx(preq);
-
-	aead_request_complete(req->areq.base.data, padata->info);
-}
-
 static void pcrypt_aead_done(struct crypto_async_request *areq, int err)
 {
 	struct aead_request *req = areq->data;
@@ -175,7 +168,7 @@ static int pcrypt_aead_encrypt(struct aead_request *req)
 				  pcrypt_aead_done, req);
 	aead_request_set_crypt(creq, req->src, req->dst,
 			       req->cryptlen, req->iv);
-	aead_request_set_assoc(creq, req->assoc, req->assoclen);
+	aead_request_set_ad(creq, req->assoclen);
 
 	err = pcrypt_do_parallel(padata, &ctx->cb_cpu, &pencrypt);
 	if (!err)
@@ -217,7 +210,7 @@ static int pcrypt_aead_decrypt(struct aead_request *req)
 				  pcrypt_aead_done, req);
 	aead_request_set_crypt(creq, req->src, req->dst,
 			       req->cryptlen, req->iv);
-	aead_request_set_assoc(creq, req->assoc, req->assoclen);
+	aead_request_set_ad(creq, req->assoclen);
 
 	err = pcrypt_do_parallel(padata, &ctx->cb_cpu, &pdecrypt);
 	if (!err)
@@ -226,182 +219,134 @@ static int pcrypt_aead_decrypt(struct aead_request *req)
 	return err;
 }
 
-static void pcrypt_aead_givenc(struct padata_priv *padata)
-{
-	struct pcrypt_request *preq = pcrypt_padata_request(padata);
-	struct aead_givcrypt_request *req = pcrypt_request_ctx(preq);
-
-	padata->info = crypto_aead_givencrypt(req);
-
-	if (padata->info == -EINPROGRESS)
-		return;
-
-	padata_do_serial(padata);
-}
-
-static int pcrypt_aead_givencrypt(struct aead_givcrypt_request *req)
-{
-	int err;
-	struct aead_request *areq = &req->areq;
-	struct pcrypt_request *preq = aead_request_ctx(areq);
-	struct aead_givcrypt_request *creq = pcrypt_request_ctx(preq);
-	struct padata_priv *padata = pcrypt_request_padata(preq);
-	struct crypto_aead *aead = aead_givcrypt_reqtfm(req);
-	struct pcrypt_aead_ctx *ctx = crypto_aead_ctx(aead);
-	u32 flags = aead_request_flags(areq);
-
-	memset(padata, 0, sizeof(struct padata_priv));
-
-	padata->parallel = pcrypt_aead_givenc;
-	padata->serial = pcrypt_aead_giv_serial;
-
-	aead_givcrypt_set_tfm(creq, ctx->child);
-	aead_givcrypt_set_callback(creq, flags & ~CRYPTO_TFM_REQ_MAY_SLEEP,
-				   pcrypt_aead_done, areq);
-	aead_givcrypt_set_crypt(creq, areq->src, areq->dst,
-				areq->cryptlen, areq->iv);
-	aead_givcrypt_set_assoc(creq, areq->assoc, areq->assoclen);
-	aead_givcrypt_set_giv(creq, req->giv, req->seq);
-
-	err = pcrypt_do_parallel(padata, &ctx->cb_cpu, &pencrypt);
-	if (!err)
-		return -EINPROGRESS;
-
-	return err;
-}
-
-static int pcrypt_aead_init_tfm(struct crypto_tfm *tfm)
+static int pcrypt_aead_init_tfm(struct crypto_aead *tfm)
 {
 	int cpu, cpu_index;
-	struct crypto_instance *inst = crypto_tfm_alg_instance(tfm);
-	struct pcrypt_instance_ctx *ictx = crypto_instance_ctx(inst);
-	struct pcrypt_aead_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct aead_instance *inst = aead_alg_instance(tfm);
+	struct pcrypt_instance_ctx *ictx = aead_instance_ctx(inst);
+	struct pcrypt_aead_ctx *ctx = crypto_aead_ctx(tfm);
 	struct crypto_aead *cipher;
 
-	ictx->tfm_count++;
-
-	cpu_index = ictx->tfm_count % cpumask_weight(cpu_online_mask);
+	cpu_index = (unsigned int)atomic_inc_return(&ictx->tfm_count) %
+		    cpumask_weight(cpu_online_mask);
 
 	ctx->cb_cpu = cpumask_first(cpu_online_mask);
 	for (cpu = 0; cpu < cpu_index; cpu++)
 		ctx->cb_cpu = cpumask_next(ctx->cb_cpu, cpu_online_mask);
 
-	cipher = crypto_spawn_aead(crypto_instance_ctx(inst));
+	cipher = crypto_spawn_aead(&ictx->spawn);
 
 	if (IS_ERR(cipher))
 		return PTR_ERR(cipher);
 
 	ctx->child = cipher;
-	tfm->crt_aead.reqsize = sizeof(struct pcrypt_request)
-		+ sizeof(struct aead_givcrypt_request)
-		+ crypto_aead_reqsize(cipher);
+	crypto_aead_set_reqsize(tfm, sizeof(struct pcrypt_request) +
+				     sizeof(struct aead_request) +
+				     crypto_aead_reqsize(cipher));
 
 	return 0;
 }
 
-static void pcrypt_aead_exit_tfm(struct crypto_tfm *tfm)
+static void pcrypt_aead_exit_tfm(struct crypto_aead *tfm)
 {
-	struct pcrypt_aead_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct pcrypt_aead_ctx *ctx = crypto_aead_ctx(tfm);
 
 	crypto_free_aead(ctx->child);
 }
 
-static struct crypto_instance *pcrypt_alloc_instance(struct crypto_alg *alg)
+static int pcrypt_init_instance(struct crypto_instance *inst,
+				struct crypto_alg *alg)
 {
-	struct crypto_instance *inst;
-	struct pcrypt_instance_ctx *ctx;
-	int err;
-
-	inst = kzalloc(sizeof(*inst) + sizeof(*ctx), GFP_KERNEL);
-	if (!inst) {
-		inst = ERR_PTR(-ENOMEM);
-		goto out;
-	}
-
-	err = -ENAMETOOLONG;
 	if (snprintf(inst->alg.cra_driver_name, CRYPTO_MAX_ALG_NAME,
 		     "pcrypt(%s)", alg->cra_driver_name) >= CRYPTO_MAX_ALG_NAME)
-		goto out_free_inst;
+		return -ENAMETOOLONG;
 
 	memcpy(inst->alg.cra_name, alg->cra_name, CRYPTO_MAX_ALG_NAME);
 
-	ctx = crypto_instance_ctx(inst);
-	err = crypto_init_spawn(&ctx->spawn, alg, inst,
-				CRYPTO_ALG_TYPE_MASK);
-	if (err)
-		goto out_free_inst;
-
 	inst->alg.cra_priority = alg->cra_priority + 100;
 	inst->alg.cra_blocksize = alg->cra_blocksize;
 	inst->alg.cra_alignmask = alg->cra_alignmask;
 
-out:
-	return inst;
-
-out_free_inst:
-	kfree(inst);
-	inst = ERR_PTR(err);
-	goto out;
+	return 0;
 }
 
-static struct crypto_instance *pcrypt_alloc_aead(struct rtattr **tb,
-						 u32 type, u32 mask)
+static int pcrypt_create_aead(struct crypto_template *tmpl, struct rtattr **tb,
+			      u32 type, u32 mask)
 {
-	struct crypto_instance *inst;
-	struct crypto_alg *alg;
+	struct pcrypt_instance_ctx *ctx;
+	struct aead_instance *inst;
+	struct aead_alg *alg;
+	const char *name;
+	int err;
+
+	name = crypto_attr_alg_name(tb[1]);
+	if (IS_ERR(name))
+		return PTR_ERR(name);
+
+	inst = kzalloc(sizeof(*inst) + sizeof(*ctx), GFP_KERNEL);
+	if (!inst)
+		return -ENOMEM;
+
+	ctx = aead_instance_ctx(inst);
+	crypto_set_aead_spawn(&ctx->spawn, aead_crypto_instance(inst));
+
+	err = crypto_grab_aead(&ctx->spawn, name, 0, 0);
+	if (err)
+		goto out_free_inst;
 
-	alg = crypto_get_attr_alg(tb, type, (mask & CRYPTO_ALG_TYPE_MASK));
-	if (IS_ERR(alg))
-		return ERR_CAST(alg);
+	alg = crypto_spawn_aead_alg(&ctx->spawn);
+	err = pcrypt_init_instance(aead_crypto_instance(inst), &alg->base);
+	if (err)
+		goto out_drop_aead;
 
-	inst = pcrypt_alloc_instance(alg);
-	if (IS_ERR(inst))
-		goto out_put_alg;
+	inst->alg.ivsize = crypto_aead_alg_ivsize(alg);
+	inst->alg.maxauthsize = crypto_aead_alg_maxauthsize(alg);
 
-	inst->alg.cra_flags = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC;
-	inst->alg.cra_type = &crypto_aead_type;
+	inst->alg.base.cra_ctxsize = sizeof(struct pcrypt_aead_ctx);
 
-	inst->alg.cra_aead.ivsize = alg->cra_aead.ivsize;
-	inst->alg.cra_aead.geniv = alg->cra_aead.geniv;
-	inst->alg.cra_aead.maxauthsize = alg->cra_aead.maxauthsize;
+	inst->alg.init = pcrypt_aead_init_tfm;
+	inst->alg.exit = pcrypt_aead_exit_tfm;
 
-	inst->alg.cra_ctxsize = sizeof(struct pcrypt_aead_ctx);
+	inst->alg.setkey = pcrypt_aead_setkey;
+	inst->alg.setauthsize = pcrypt_aead_setauthsize;
+	inst->alg.encrypt = pcrypt_aead_encrypt;
+	inst->alg.decrypt = pcrypt_aead_decrypt;
 
-	inst->alg.cra_init = pcrypt_aead_init_tfm;
-	inst->alg.cra_exit = pcrypt_aead_exit_tfm;
+	err = aead_register_instance(tmpl, inst);
+	if (err)
+		goto out_drop_aead;
 
-	inst->alg.cra_aead.setkey = pcrypt_aead_setkey;
-	inst->alg.cra_aead.setauthsize = pcrypt_aead_setauthsize;
-	inst->alg.cra_aead.encrypt = pcrypt_aead_encrypt;
-	inst->alg.cra_aead.decrypt = pcrypt_aead_decrypt;
-	inst->alg.cra_aead.givencrypt = pcrypt_aead_givencrypt;
+out:
+	return err;
 
-out_put_alg:
-	crypto_mod_put(alg);
-	return inst;
+out_drop_aead:
+	crypto_drop_aead(&ctx->spawn);
+out_free_inst:
+	kfree(inst);
+	goto out;
 }
 
-static struct crypto_instance *pcrypt_alloc(struct rtattr **tb)
+static int pcrypt_create(struct crypto_template *tmpl, struct rtattr **tb)
 {
 	struct crypto_attr_type *algt;
 
 	algt = crypto_get_attr_type(tb);
 	if (IS_ERR(algt))
-		return ERR_CAST(algt);
+		return PTR_ERR(algt);
 
 	switch (algt->type & algt->mask & CRYPTO_ALG_TYPE_MASK) {
 	case CRYPTO_ALG_TYPE_AEAD:
-		return pcrypt_alloc_aead(tb, algt->type, algt->mask);
+		return pcrypt_create_aead(tmpl, tb, algt->type, algt->mask);
 	}
 
-	return ERR_PTR(-EINVAL);
+	return -EINVAL;
 }
 
 static void pcrypt_free(struct crypto_instance *inst)
 {
 	struct pcrypt_instance_ctx *ctx = crypto_instance_ctx(inst);
 
-	crypto_drop_spawn(&ctx->spawn);
+	crypto_drop_aead(&ctx->spawn);
 	kfree(inst);
 }
 
@@ -516,7 +461,7 @@ static void pcrypt_fini_padata(struct padata_pcrypt *pcrypt)
 
 static struct crypto_template pcrypt_tmpl = {
 	.name = "pcrypt",
-	.alloc = pcrypt_alloc,
+	.create = pcrypt_create,
 	.free = pcrypt_free,
 	.module = THIS_MODULE,
 };
diff --git a/crypto/poly1305_generic.c b/crypto/poly1305_generic.c
new file mode 100644
index 000000000000..387b5c887a80
--- /dev/null
+++ b/crypto/poly1305_generic.c
@@ -0,0 +1,321 @@
+/*
+ * Poly1305 authenticator algorithm, RFC7539
+ *
+ * Copyright (C) 2015 Martin Willi
+ *
+ * Based on public domain code by Andrew Moon and Daniel J. Bernstein.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <crypto/algapi.h>
+#include <crypto/internal/hash.h>
+#include <linux/crypto.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#define POLY1305_BLOCK_SIZE	16
+#define POLY1305_KEY_SIZE	32
+#define POLY1305_DIGEST_SIZE	16
+
+struct poly1305_desc_ctx {
+	/* key */
+	u32 r[5];
+	/* finalize key */
+	u32 s[4];
+	/* accumulator */
+	u32 h[5];
+	/* partial buffer */
+	u8 buf[POLY1305_BLOCK_SIZE];
+	/* bytes used in partial buffer */
+	unsigned int buflen;
+	/* r key has been set */
+	bool rset;
+	/* s key has been set */
+	bool sset;
+};
+
+static inline u64 mlt(u64 a, u64 b)
+{
+	return a * b;
+}
+
+static inline u32 sr(u64 v, u_char n)
+{
+	return v >> n;
+}
+
+static inline u32 and(u32 v, u32 mask)
+{
+	return v & mask;
+}
+
+static inline u32 le32_to_cpuvp(const void *p)
+{
+	return le32_to_cpup(p);
+}
+
+static int poly1305_init(struct shash_desc *desc)
+{
+	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
+
+	memset(dctx->h, 0, sizeof(dctx->h));
+	dctx->buflen = 0;
+	dctx->rset = false;
+	dctx->sset = false;
+
+	return 0;
+}
+
+static int poly1305_setkey(struct crypto_shash *tfm,
+			   const u8 *key, unsigned int keylen)
+{
+	/* Poly1305 requires a unique key for each tag, which implies that
+	 * we can't set it on the tfm that gets accessed by multiple users
+	 * simultaneously. Instead we expect the key as the first 32 bytes in
+	 * the update() call. */
+	return -ENOTSUPP;
+}
+
+static void poly1305_setrkey(struct poly1305_desc_ctx *dctx, const u8 *key)
+{
+	/* r &= 0xffffffc0ffffffc0ffffffc0fffffff */
+	dctx->r[0] = (le32_to_cpuvp(key +  0) >> 0) & 0x3ffffff;
+	dctx->r[1] = (le32_to_cpuvp(key +  3) >> 2) & 0x3ffff03;
+	dctx->r[2] = (le32_to_cpuvp(key +  6) >> 4) & 0x3ffc0ff;
+	dctx->r[3] = (le32_to_cpuvp(key +  9) >> 6) & 0x3f03fff;
+	dctx->r[4] = (le32_to_cpuvp(key + 12) >> 8) & 0x00fffff;
+}
+
+static void poly1305_setskey(struct poly1305_desc_ctx *dctx, const u8 *key)
+{
+	dctx->s[0] = le32_to_cpuvp(key +  0);
+	dctx->s[1] = le32_to_cpuvp(key +  4);
+	dctx->s[2] = le32_to_cpuvp(key +  8);
+	dctx->s[3] = le32_to_cpuvp(key + 12);
+}
+
+static unsigned int poly1305_blocks(struct poly1305_desc_ctx *dctx,
+				    const u8 *src, unsigned int srclen,
+				    u32 hibit)
+{
+	u32 r0, r1, r2, r3, r4;
+	u32 s1, s2, s3, s4;
+	u32 h0, h1, h2, h3, h4;
+	u64 d0, d1, d2, d3, d4;
+
+	if (unlikely(!dctx->sset)) {
+		if (!dctx->rset && srclen >= POLY1305_BLOCK_SIZE) {
+			poly1305_setrkey(dctx, src);
+			src += POLY1305_BLOCK_SIZE;
+			srclen -= POLY1305_BLOCK_SIZE;
+			dctx->rset = true;
+		}
+		if (srclen >= POLY1305_BLOCK_SIZE) {
+			poly1305_setskey(dctx, src);
+			src += POLY1305_BLOCK_SIZE;
+			srclen -= POLY1305_BLOCK_SIZE;
+			dctx->sset = true;
+		}
+	}
+
+	r0 = dctx->r[0];
+	r1 = dctx->r[1];
+	r2 = dctx->r[2];
+	r3 = dctx->r[3];
+	r4 = dctx->r[4];
+
+	s1 = r1 * 5;
+	s2 = r2 * 5;
+	s3 = r3 * 5;
+	s4 = r4 * 5;
+
+	h0 = dctx->h[0];
+	h1 = dctx->h[1];
+	h2 = dctx->h[2];
+	h3 = dctx->h[3];
+	h4 = dctx->h[4];
+
+	while (likely(srclen >= POLY1305_BLOCK_SIZE)) {
+
+		/* h += m[i] */
+		h0 += (le32_to_cpuvp(src +  0) >> 0) & 0x3ffffff;
+		h1 += (le32_to_cpuvp(src +  3) >> 2) & 0x3ffffff;
+		h2 += (le32_to_cpuvp(src +  6) >> 4) & 0x3ffffff;
+		h3 += (le32_to_cpuvp(src +  9) >> 6) & 0x3ffffff;
+		h4 += (le32_to_cpuvp(src + 12) >> 8) | hibit;
+
+		/* h *= r */
+		d0 = mlt(h0, r0) + mlt(h1, s4) + mlt(h2, s3) +
+		     mlt(h3, s2) + mlt(h4, s1);
+		d1 = mlt(h0, r1) + mlt(h1, r0) + mlt(h2, s4) +
+		     mlt(h3, s3) + mlt(h4, s2);
+		d2 = mlt(h0, r2) + mlt(h1, r1) + mlt(h2, r0) +
+		     mlt(h3, s4) + mlt(h4, s3);
+		d3 = mlt(h0, r3) + mlt(h1, r2) + mlt(h2, r1) +
+		     mlt(h3, r0) + mlt(h4, s4);
+		d4 = mlt(h0, r4) + mlt(h1, r3) + mlt(h2, r2) +
+		     mlt(h3, r1) + mlt(h4, r0);
+
+		/* (partial) h %= p */
+		d1 += sr(d0, 26);     h0 = and(d0, 0x3ffffff);
+		d2 += sr(d1, 26);     h1 = and(d1, 0x3ffffff);
+		d3 += sr(d2, 26);     h2 = and(d2, 0x3ffffff);
+		d4 += sr(d3, 26);     h3 = and(d3, 0x3ffffff);
+		h0 += sr(d4, 26) * 5; h4 = and(d4, 0x3ffffff);
+		h1 += h0 >> 26;       h0 = h0 & 0x3ffffff;
+
+		src += POLY1305_BLOCK_SIZE;
+		srclen -= POLY1305_BLOCK_SIZE;
+	}
+
+	dctx->h[0] = h0;
+	dctx->h[1] = h1;
+	dctx->h[2] = h2;
+	dctx->h[3] = h3;
+	dctx->h[4] = h4;
+
+	return srclen;
+}
+
+static int poly1305_update(struct shash_desc *desc,
+			   const u8 *src, unsigned int srclen)
+{
+	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
+	unsigned int bytes;
+
+	if (unlikely(dctx->buflen)) {
+		bytes = min(srclen, POLY1305_BLOCK_SIZE - dctx->buflen);
+		memcpy(dctx->buf + dctx->buflen, src, bytes);
+		src += bytes;
+		srclen -= bytes;
+		dctx->buflen += bytes;
+
+		if (dctx->buflen == POLY1305_BLOCK_SIZE) {
+			poly1305_blocks(dctx, dctx->buf,
+					POLY1305_BLOCK_SIZE, 1 << 24);
+			dctx->buflen = 0;
+		}
+	}
+
+	if (likely(srclen >= POLY1305_BLOCK_SIZE)) {
+		bytes = poly1305_blocks(dctx, src, srclen, 1 << 24);
+		src += srclen - bytes;
+		srclen = bytes;
+	}
+
+	if (unlikely(srclen)) {
+		dctx->buflen = srclen;
+		memcpy(dctx->buf, src, srclen);
+	}
+
+	return 0;
+}
+
+static int poly1305_final(struct shash_desc *desc, u8 *dst)
+{
+	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
+	__le32 *mac = (__le32 *)dst;
+	u32 h0, h1, h2, h3, h4;
+	u32 g0, g1, g2, g3, g4;
+	u32 mask;
+	u64 f = 0;
+
+	if (unlikely(!dctx->sset))
+		return -ENOKEY;
+
+	if (unlikely(dctx->buflen)) {
+		dctx->buf[dctx->buflen++] = 1;
+		memset(dctx->buf + dctx->buflen, 0,
+		       POLY1305_BLOCK_SIZE - dctx->buflen);
+		poly1305_blocks(dctx, dctx->buf, POLY1305_BLOCK_SIZE, 0);
+	}
+
+	/* fully carry h */
+	h0 = dctx->h[0];
+	h1 = dctx->h[1];
+	h2 = dctx->h[2];
+	h3 = dctx->h[3];
+	h4 = dctx->h[4];
+
+	h2 += (h1 >> 26);     h1 = h1 & 0x3ffffff;
+	h3 += (h2 >> 26);     h2 = h2 & 0x3ffffff;
+	h4 += (h3 >> 26);     h3 = h3 & 0x3ffffff;
+	h0 += (h4 >> 26) * 5; h4 = h4 & 0x3ffffff;
+	h1 += (h0 >> 26);     h0 = h0 & 0x3ffffff;
+
+	/* compute h + -p */
+	g0 = h0 + 5;
+	g1 = h1 + (g0 >> 26);             g0 &= 0x3ffffff;
+	g2 = h2 + (g1 >> 26);             g1 &= 0x3ffffff;
+	g3 = h3 + (g2 >> 26);             g2 &= 0x3ffffff;
+	g4 = h4 + (g3 >> 26) - (1 << 26); g3 &= 0x3ffffff;
+
+	/* select h if h < p, or h + -p if h >= p */
+	mask = (g4 >> ((sizeof(u32) * 8) - 1)) - 1;
+	g0 &= mask;
+	g1 &= mask;
+	g2 &= mask;
+	g3 &= mask;
+	g4 &= mask;
+	mask = ~mask;
+	h0 = (h0 & mask) | g0;
+	h1 = (h1 & mask) | g1;
+	h2 = (h2 & mask) | g2;
+	h3 = (h3 & mask) | g3;
+	h4 = (h4 & mask) | g4;
+
+	/* h = h % (2^128) */
+	h0 = (h0 >>  0) | (h1 << 26);
+	h1 = (h1 >>  6) | (h2 << 20);
+	h2 = (h2 >> 12) | (h3 << 14);
+	h3 = (h3 >> 18) | (h4 <<  8);
+
+	/* mac = (h + s) % (2^128) */
+	f = (f >> 32) + h0 + dctx->s[0]; mac[0] = cpu_to_le32(f);
+	f = (f >> 32) + h1 + dctx->s[1]; mac[1] = cpu_to_le32(f);
+	f = (f >> 32) + h2 + dctx->s[2]; mac[2] = cpu_to_le32(f);
+	f = (f >> 32) + h3 + dctx->s[3]; mac[3] = cpu_to_le32(f);
+
+	return 0;
+}
+
+static struct shash_alg poly1305_alg = {
+	.digestsize	= POLY1305_DIGEST_SIZE,
+	.init		= poly1305_init,
+	.update		= poly1305_update,
+	.final		= poly1305_final,
+	.setkey		= poly1305_setkey,
+	.descsize	= sizeof(struct poly1305_desc_ctx),
+	.base		= {
+		.cra_name		= "poly1305",
+		.cra_driver_name	= "poly1305-generic",
+		.cra_priority		= 100,
+		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
+		.cra_alignmask		= sizeof(u32) - 1,
+		.cra_blocksize		= POLY1305_BLOCK_SIZE,
+		.cra_module		= THIS_MODULE,
+	},
+};
+
+static int __init poly1305_mod_init(void)
+{
+	return crypto_register_shash(&poly1305_alg);
+}
+
+static void __exit poly1305_mod_exit(void)
+{
+	crypto_unregister_shash(&poly1305_alg);
+}
+
+module_init(poly1305_mod_init);
+module_exit(poly1305_mod_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Martin Willi <martin@strongswan.org>");
+MODULE_DESCRIPTION("Poly1305 authenticator");
+MODULE_ALIAS_CRYPTO("poly1305");
+MODULE_ALIAS_CRYPTO("poly1305-generic");
diff --git a/crypto/proc.c b/crypto/proc.c
index 4ffe73b51612..2cc10c96d753 100644
--- a/crypto/proc.c
+++ b/crypto/proc.c
@@ -20,47 +20,8 @@
 #include <linux/rwsem.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
-#include <linux/sysctl.h>
 #include "internal.h"
 
-#ifdef CONFIG_CRYPTO_FIPS
-static struct ctl_table crypto_sysctl_table[] = {
-	{
-		.procname       = "fips_enabled",
-		.data           = &fips_enabled,
-		.maxlen         = sizeof(int),
-		.mode           = 0444,
-		.proc_handler   = proc_dointvec
-	},
-	{}
-};
-
-static struct ctl_table crypto_dir_table[] = {
-	{
-		.procname       = "crypto",
-		.mode           = 0555,
-		.child          = crypto_sysctl_table
-	},
-	{}
-};
-
-static struct ctl_table_header *crypto_sysctls;
-
-static void crypto_proc_fips_init(void)
-{
-	crypto_sysctls = register_sysctl_table(crypto_dir_table);
-}
-
-static void crypto_proc_fips_exit(void)
-{
-	if (crypto_sysctls)
-		unregister_sysctl_table(crypto_sysctls);
-}
-#else
-#define crypto_proc_fips_init()
-#define crypto_proc_fips_exit()
-#endif
-
 static void *c_start(struct seq_file *m, loff_t *pos)
 {
 	down_read(&crypto_alg_sem);
@@ -148,11 +109,9 @@ static const struct file_operations proc_crypto_ops = {
 void __init crypto_init_proc(void)
 {
 	proc_create("crypto", 0, NULL, &proc_crypto_ops);
-	crypto_proc_fips_init();
 }
 
 void __exit crypto_exit_proc(void)
 {
-	crypto_proc_fips_exit();
 	remove_proc_entry("crypto", NULL);
 }
diff --git a/crypto/rng.c b/crypto/rng.c
index e0a25c2456de..b81cffb13bab 100644
--- a/crypto/rng.c
+++ b/crypto/rng.c
@@ -4,6 +4,7 @@
  * RNG operations.
  *
  * Copyright (c) 2008 Neil Horman <nhorman@tuxdriver.com>
+ * Copyright (c) 2015 Herbert Xu <herbert@gondor.apana.org.au>
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms of the GNU General Public License as published by the Free
@@ -24,12 +25,19 @@
 #include <linux/cryptouser.h>
 #include <net/netlink.h>
 
+#include "internal.h"
+
 static DEFINE_MUTEX(crypto_default_rng_lock);
 struct crypto_rng *crypto_default_rng;
 EXPORT_SYMBOL_GPL(crypto_default_rng);
 static int crypto_default_rng_refcnt;
 
-static int rngapi_reset(struct crypto_rng *tfm, u8 *seed, unsigned int slen)
+static inline struct crypto_rng *__crypto_rng_cast(struct crypto_tfm *tfm)
+{
+	return container_of(tfm, struct crypto_rng, base);
+}
+
+int crypto_rng_reset(struct crypto_rng *tfm, const u8 *seed, unsigned int slen)
 {
 	u8 *buf = NULL;
 	int err;
@@ -43,21 +51,23 @@ static int rngapi_reset(struct crypto_rng *tfm, u8 *seed, unsigned int slen)
 		seed = buf;
 	}
 
-	err = crypto_rng_alg(tfm)->rng_reset(tfm, seed, slen);
+	err = crypto_rng_alg(tfm)->seed(tfm, seed, slen);
 
-	kfree(buf);
+	kzfree(buf);
 	return err;
 }
+EXPORT_SYMBOL_GPL(crypto_rng_reset);
 
-static int crypto_init_rng_ops(struct crypto_tfm *tfm, u32 type, u32 mask)
+static int crypto_rng_init_tfm(struct crypto_tfm *tfm)
 {
-	struct rng_alg *alg = &tfm->__crt_alg->cra_rng;
-	struct rng_tfm *ops = &tfm->crt_rng;
+	return 0;
+}
 
-	ops->rng_gen_random = alg->rng_make_random;
-	ops->rng_reset = rngapi_reset;
+static unsigned int seedsize(struct crypto_alg *alg)
+{
+	struct rng_alg *ralg = container_of(alg, struct rng_alg, base);
 
-	return 0;
+	return ralg->seedsize;
 }
 
 #ifdef CONFIG_NET
@@ -67,7 +77,7 @@ static int crypto_rng_report(struct sk_buff *skb, struct crypto_alg *alg)
 
 	strncpy(rrng.type, "rng", sizeof(rrng.type));
 
-	rrng.seedsize = alg->cra_rng.seedsize;
+	rrng.seedsize = seedsize(alg);
 
 	if (nla_put(skb, CRYPTOCFGA_REPORT_RNG,
 		    sizeof(struct crypto_report_rng), &rrng))
@@ -89,24 +99,27 @@ static void crypto_rng_show(struct seq_file *m, struct crypto_alg *alg)
 static void crypto_rng_show(struct seq_file *m, struct crypto_alg *alg)
 {
 	seq_printf(m, "type         : rng\n");
-	seq_printf(m, "seedsize     : %u\n", alg->cra_rng.seedsize);
-}
-
-static unsigned int crypto_rng_ctxsize(struct crypto_alg *alg, u32 type,
-				       u32 mask)
-{
-	return alg->cra_ctxsize;
+	seq_printf(m, "seedsize     : %u\n", seedsize(alg));
 }
 
-const struct crypto_type crypto_rng_type = {
-	.ctxsize = crypto_rng_ctxsize,
-	.init = crypto_init_rng_ops,
+static const struct crypto_type crypto_rng_type = {
+	.extsize = crypto_alg_extsize,
+	.init_tfm = crypto_rng_init_tfm,
 #ifdef CONFIG_PROC_FS
 	.show = crypto_rng_show,
 #endif
 	.report = crypto_rng_report,
+	.maskclear = ~CRYPTO_ALG_TYPE_MASK,
+	.maskset = CRYPTO_ALG_TYPE_MASK,
+	.type = CRYPTO_ALG_TYPE_RNG,
+	.tfmsize = offsetof(struct crypto_rng, base),
 };
-EXPORT_SYMBOL_GPL(crypto_rng_type);
+
+struct crypto_rng *crypto_alloc_rng(const char *alg_name, u32 type, u32 mask)
+{
+	return crypto_alloc_tfm(alg_name, &crypto_rng_type, type, mask);
+}
+EXPORT_SYMBOL_GPL(crypto_alloc_rng);
 
 int crypto_get_default_rng(void)
 {
@@ -142,13 +155,82 @@ EXPORT_SYMBOL_GPL(crypto_get_default_rng);
 void crypto_put_default_rng(void)
 {
 	mutex_lock(&crypto_default_rng_lock);
-	if (!--crypto_default_rng_refcnt) {
-		crypto_free_rng(crypto_default_rng);
-		crypto_default_rng = NULL;
-	}
+	crypto_default_rng_refcnt--;
 	mutex_unlock(&crypto_default_rng_lock);
 }
 EXPORT_SYMBOL_GPL(crypto_put_default_rng);
 
+#if defined(CONFIG_CRYPTO_RNG) || defined(CONFIG_CRYPTO_RNG_MODULE)
+int crypto_del_default_rng(void)
+{
+	int err = -EBUSY;
+
+	mutex_lock(&crypto_default_rng_lock);
+	if (crypto_default_rng_refcnt)
+		goto out;
+
+	crypto_free_rng(crypto_default_rng);
+	crypto_default_rng = NULL;
+
+	err = 0;
+
+out:
+	mutex_unlock(&crypto_default_rng_lock);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(crypto_del_default_rng);
+#endif
+
+int crypto_register_rng(struct rng_alg *alg)
+{
+	struct crypto_alg *base = &alg->base;
+
+	if (alg->seedsize > PAGE_SIZE / 8)
+		return -EINVAL;
+
+	base->cra_type = &crypto_rng_type;
+	base->cra_flags &= ~CRYPTO_ALG_TYPE_MASK;
+	base->cra_flags |= CRYPTO_ALG_TYPE_RNG;
+
+	return crypto_register_alg(base);
+}
+EXPORT_SYMBOL_GPL(crypto_register_rng);
+
+void crypto_unregister_rng(struct rng_alg *alg)
+{
+	crypto_unregister_alg(&alg->base);
+}
+EXPORT_SYMBOL_GPL(crypto_unregister_rng);
+
+int crypto_register_rngs(struct rng_alg *algs, int count)
+{
+	int i, ret;
+
+	for (i = 0; i < count; i++) {
+		ret = crypto_register_rng(algs + i);
+		if (ret)
+			goto err;
+	}
+
+	return 0;
+
+err:
+	for (--i; i >= 0; --i)
+		crypto_unregister_rng(algs + i);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(crypto_register_rngs);
+
+void crypto_unregister_rngs(struct rng_alg *algs, int count)
+{
+	int i;
+
+	for (i = count - 1; i >= 0; --i)
+		crypto_unregister_rng(algs + i);
+}
+EXPORT_SYMBOL_GPL(crypto_unregister_rngs);
+
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Random Number Generator");
diff --git a/crypto/rsa.c b/crypto/rsa.c
new file mode 100644
index 000000000000..752af0656f2e
--- /dev/null
+++ b/crypto/rsa.c
@@ -0,0 +1,315 @@
+/* RSA asymmetric public-key algorithm [RFC3447]
+ *
+ * Copyright (c) 2015, Intel Corporation
+ * Authors: Tadeusz Struk <tadeusz.struk@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <crypto/internal/rsa.h>
+#include <crypto/internal/akcipher.h>
+#include <crypto/akcipher.h>
+
+/*
+ * RSAEP function [RFC3447 sec 5.1.1]
+ * c = m^e mod n;
+ */
+static int _rsa_enc(const struct rsa_key *key, MPI c, MPI m)
+{
+	/* (1) Validate 0 <= m < n */
+	if (mpi_cmp_ui(m, 0) < 0 || mpi_cmp(m, key->n) >= 0)
+		return -EINVAL;
+
+	/* (2) c = m^e mod n */
+	return mpi_powm(c, m, key->e, key->n);
+}
+
+/*
+ * RSADP function [RFC3447 sec 5.1.2]
+ * m = c^d mod n;
+ */
+static int _rsa_dec(const struct rsa_key *key, MPI m, MPI c)
+{
+	/* (1) Validate 0 <= c < n */
+	if (mpi_cmp_ui(c, 0) < 0 || mpi_cmp(c, key->n) >= 0)
+		return -EINVAL;
+
+	/* (2) m = c^d mod n */
+	return mpi_powm(m, c, key->d, key->n);
+}
+
+/*
+ * RSASP1 function [RFC3447 sec 5.2.1]
+ * s = m^d mod n
+ */
+static int _rsa_sign(const struct rsa_key *key, MPI s, MPI m)
+{
+	/* (1) Validate 0 <= m < n */
+	if (mpi_cmp_ui(m, 0) < 0 || mpi_cmp(m, key->n) >= 0)
+		return -EINVAL;
+
+	/* (2) s = m^d mod n */
+	return mpi_powm(s, m, key->d, key->n);
+}
+
+/*
+ * RSAVP1 function [RFC3447 sec 5.2.2]
+ * m = s^e mod n;
+ */
+static int _rsa_verify(const struct rsa_key *key, MPI m, MPI s)
+{
+	/* (1) Validate 0 <= s < n */
+	if (mpi_cmp_ui(s, 0) < 0 || mpi_cmp(s, key->n) >= 0)
+		return -EINVAL;
+
+	/* (2) m = s^e mod n */
+	return mpi_powm(m, s, key->e, key->n);
+}
+
+static inline struct rsa_key *rsa_get_key(struct crypto_akcipher *tfm)
+{
+	return akcipher_tfm_ctx(tfm);
+}
+
+static int rsa_enc(struct akcipher_request *req)
+{
+	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
+	const struct rsa_key *pkey = rsa_get_key(tfm);
+	MPI m, c = mpi_alloc(0);
+	int ret = 0;
+	int sign;
+
+	if (!c)
+		return -ENOMEM;
+
+	if (unlikely(!pkey->n || !pkey->e)) {
+		ret = -EINVAL;
+		goto err_free_c;
+	}
+
+	if (req->dst_len < mpi_get_size(pkey->n)) {
+		req->dst_len = mpi_get_size(pkey->n);
+		ret = -EOVERFLOW;
+		goto err_free_c;
+	}
+
+	m = mpi_read_raw_data(req->src, req->src_len);
+	if (!m) {
+		ret = -ENOMEM;
+		goto err_free_c;
+	}
+
+	ret = _rsa_enc(pkey, c, m);
+	if (ret)
+		goto err_free_m;
+
+	ret = mpi_read_buffer(c, req->dst, req->dst_len, &req->dst_len, &sign);
+	if (ret)
+		goto err_free_m;
+
+	if (sign < 0) {
+		ret = -EBADMSG;
+		goto err_free_m;
+	}
+
+err_free_m:
+	mpi_free(m);
+err_free_c:
+	mpi_free(c);
+	return ret;
+}
+
+static int rsa_dec(struct akcipher_request *req)
+{
+	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
+	const struct rsa_key *pkey = rsa_get_key(tfm);
+	MPI c, m = mpi_alloc(0);
+	int ret = 0;
+	int sign;
+
+	if (!m)
+		return -ENOMEM;
+
+	if (unlikely(!pkey->n || !pkey->d)) {
+		ret = -EINVAL;
+		goto err_free_m;
+	}
+
+	if (req->dst_len < mpi_get_size(pkey->n)) {
+		req->dst_len = mpi_get_size(pkey->n);
+		ret = -EOVERFLOW;
+		goto err_free_m;
+	}
+
+	c = mpi_read_raw_data(req->src, req->src_len);
+	if (!c) {
+		ret = -ENOMEM;
+		goto err_free_m;
+	}
+
+	ret = _rsa_dec(pkey, m, c);
+	if (ret)
+		goto err_free_c;
+
+	ret = mpi_read_buffer(m, req->dst, req->dst_len, &req->dst_len, &sign);
+	if (ret)
+		goto err_free_c;
+
+	if (sign < 0) {
+		ret = -EBADMSG;
+		goto err_free_c;
+	}
+
+err_free_c:
+	mpi_free(c);
+err_free_m:
+	mpi_free(m);
+	return ret;
+}
+
+static int rsa_sign(struct akcipher_request *req)
+{
+	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
+	const struct rsa_key *pkey = rsa_get_key(tfm);
+	MPI m, s = mpi_alloc(0);
+	int ret = 0;
+	int sign;
+
+	if (!s)
+		return -ENOMEM;
+
+	if (unlikely(!pkey->n || !pkey->d)) {
+		ret = -EINVAL;
+		goto err_free_s;
+	}
+
+	if (req->dst_len < mpi_get_size(pkey->n)) {
+		req->dst_len = mpi_get_size(pkey->n);
+		ret = -EOVERFLOW;
+		goto err_free_s;
+	}
+
+	m = mpi_read_raw_data(req->src, req->src_len);
+	if (!m) {
+		ret = -ENOMEM;
+		goto err_free_s;
+	}
+
+	ret = _rsa_sign(pkey, s, m);
+	if (ret)
+		goto err_free_m;
+
+	ret = mpi_read_buffer(s, req->dst, req->dst_len, &req->dst_len, &sign);
+	if (ret)
+		goto err_free_m;
+
+	if (sign < 0) {
+		ret = -EBADMSG;
+		goto err_free_m;
+	}
+
+err_free_m:
+	mpi_free(m);
+err_free_s:
+	mpi_free(s);
+	return ret;
+}
+
+static int rsa_verify(struct akcipher_request *req)
+{
+	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
+	const struct rsa_key *pkey = rsa_get_key(tfm);
+	MPI s, m = mpi_alloc(0);
+	int ret = 0;
+	int sign;
+
+	if (!m)
+		return -ENOMEM;
+
+	if (unlikely(!pkey->n || !pkey->e)) {
+		ret = -EINVAL;
+		goto err_free_m;
+	}
+
+	if (req->dst_len < mpi_get_size(pkey->n)) {
+		req->dst_len = mpi_get_size(pkey->n);
+		ret = -EOVERFLOW;
+		goto err_free_m;
+	}
+
+	s = mpi_read_raw_data(req->src, req->src_len);
+	if (!s) {
+		ret = -ENOMEM;
+		goto err_free_m;
+	}
+
+	ret = _rsa_verify(pkey, m, s);
+	if (ret)
+		goto err_free_s;
+
+	ret = mpi_read_buffer(m, req->dst, req->dst_len, &req->dst_len, &sign);
+	if (ret)
+		goto err_free_s;
+
+	if (sign < 0) {
+		ret = -EBADMSG;
+		goto err_free_s;
+	}
+
+err_free_s:
+	mpi_free(s);
+err_free_m:
+	mpi_free(m);
+	return ret;
+}
+
+static int rsa_setkey(struct crypto_akcipher *tfm, const void *key,
+		      unsigned int keylen)
+{
+	struct rsa_key *pkey = akcipher_tfm_ctx(tfm);
+
+	return rsa_parse_key(pkey, key, keylen);
+}
+
+static void rsa_exit_tfm(struct crypto_akcipher *tfm)
+{
+	struct rsa_key *pkey = akcipher_tfm_ctx(tfm);
+
+	rsa_free_key(pkey);
+}
+
+static struct akcipher_alg rsa = {
+	.encrypt = rsa_enc,
+	.decrypt = rsa_dec,
+	.sign = rsa_sign,
+	.verify = rsa_verify,
+	.setkey = rsa_setkey,
+	.exit = rsa_exit_tfm,
+	.base = {
+		.cra_name = "rsa",
+		.cra_driver_name = "rsa-generic",
+		.cra_priority = 100,
+		.cra_module = THIS_MODULE,
+		.cra_ctxsize = sizeof(struct rsa_key),
+	},
+};
+
+static int rsa_init(void)
+{
+	return crypto_register_akcipher(&rsa);
+}
+
+static void rsa_exit(void)
+{
+	crypto_unregister_akcipher(&rsa);
+}
+
+module_init(rsa_init);
+module_exit(rsa_exit);
+MODULE_ALIAS_CRYPTO("rsa");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("RSA generic algorithm");
diff --git a/crypto/rsa_helper.c b/crypto/rsa_helper.c
new file mode 100644
index 000000000000..3e8e0a9e5a8e
--- /dev/null
+++ b/crypto/rsa_helper.c
@@ -0,0 +1,121 @@
+/*
+ * RSA key extract helper
+ *
+ * Copyright (c) 2015, Intel Corporation
+ * Authors: Tadeusz Struk <tadeusz.struk@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ */
+#include <linux/kernel.h>
+#include <linux/export.h>
+#include <linux/err.h>
+#include <linux/fips.h>
+#include <crypto/internal/rsa.h>
+#include "rsakey-asn1.h"
+
+int rsa_get_n(void *context, size_t hdrlen, unsigned char tag,
+	      const void *value, size_t vlen)
+{
+	struct rsa_key *key = context;
+
+	key->n = mpi_read_raw_data(value, vlen);
+
+	if (!key->n)
+		return -ENOMEM;
+
+	/* In FIPS mode only allow key size 2K & 3K */
+	if (fips_enabled && (mpi_get_size(key->n) != 256 ||
+			     mpi_get_size(key->n) != 384)) {
+		pr_err("RSA: key size not allowed in FIPS mode\n");
+		mpi_free(key->n);
+		key->n = NULL;
+		return -EINVAL;
+	}
+	return 0;
+}
+
+int rsa_get_e(void *context, size_t hdrlen, unsigned char tag,
+	      const void *value, size_t vlen)
+{
+	struct rsa_key *key = context;
+
+	key->e = mpi_read_raw_data(value, vlen);
+
+	if (!key->e)
+		return -ENOMEM;
+
+	return 0;
+}
+
+int rsa_get_d(void *context, size_t hdrlen, unsigned char tag,
+	      const void *value, size_t vlen)
+{
+	struct rsa_key *key = context;
+
+	key->d = mpi_read_raw_data(value, vlen);
+
+	if (!key->d)
+		return -ENOMEM;
+
+	/* In FIPS mode only allow key size 2K & 3K */
+	if (fips_enabled && (mpi_get_size(key->d) != 256 ||
+			     mpi_get_size(key->d) != 384)) {
+		pr_err("RSA: key size not allowed in FIPS mode\n");
+		mpi_free(key->d);
+		key->d = NULL;
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static void free_mpis(struct rsa_key *key)
+{
+	mpi_free(key->n);
+	mpi_free(key->e);
+	mpi_free(key->d);
+	key->n = NULL;
+	key->e = NULL;
+	key->d = NULL;
+}
+
+/**
+ * rsa_free_key() - frees rsa key allocated by rsa_parse_key()
+ *
+ * @rsa_key:	struct rsa_key key representation
+ */
+void rsa_free_key(struct rsa_key *key)
+{
+	free_mpis(key);
+}
+EXPORT_SYMBOL_GPL(rsa_free_key);
+
+/**
+ * rsa_parse_key() - extracts an rsa key from BER encoded buffer
+ *		     and stores it in the provided struct rsa_key
+ *
+ * @rsa_key:	struct rsa_key key representation
+ * @key:	key in BER format
+ * @key_len:	length of key
+ *
+ * Return:	0 on success or error code in case of error
+ */
+int rsa_parse_key(struct rsa_key *rsa_key, const void *key,
+		  unsigned int key_len)
+{
+	int ret;
+
+	free_mpis(rsa_key);
+	ret = asn1_ber_decoder(&rsakey_decoder, rsa_key, key, key_len);
+	if (ret < 0)
+		goto error;
+
+	return 0;
+error:
+	free_mpis(rsa_key);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(rsa_parse_key);
diff --git a/crypto/rsakey.asn1 b/crypto/rsakey.asn1
new file mode 100644
index 000000000000..3c7b5df7b428
--- /dev/null
+++ b/crypto/rsakey.asn1
@@ -0,0 +1,5 @@
+RsaKey ::= SEQUENCE {
+	n INTEGER ({ rsa_get_n }),
+	e INTEGER ({ rsa_get_e }),
+	d INTEGER ({ rsa_get_d })
+}
diff --git a/crypto/scatterwalk.c b/crypto/scatterwalk.c
index 3bd749c7bb70..ea5815c5e128 100644
--- a/crypto/scatterwalk.c
+++ b/crypto/scatterwalk.c
@@ -54,7 +54,11 @@ static void scatterwalk_pagedone(struct scatter_walk *walk, int out,
 		struct page *page;
 
 		page = sg_page(walk->sg) + ((walk->offset - 1) >> PAGE_SHIFT);
-		if (!PageSlab(page))
+		/* Test ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE first as
+		 * PageSlab cannot be optimised away per se due to
+		 * use of volatile pointer.
+		 */
+		if (ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE && !PageSlab(page))
 			flush_dcache_page(page);
 	}
 
@@ -104,22 +108,18 @@ void scatterwalk_map_and_copy(void *buf, struct scatterlist *sg,
 			      unsigned int start, unsigned int nbytes, int out)
 {
 	struct scatter_walk walk;
-	unsigned int offset = 0;
+	struct scatterlist tmp[2];
 
 	if (!nbytes)
 		return;
 
-	for (;;) {
-		scatterwalk_start(&walk, sg);
-
-		if (start < offset + sg->length)
-			break;
+	sg = scatterwalk_ffwd(tmp, sg, start);
 
-		offset += sg->length;
-		sg = sg_next(sg);
-	}
+	if (sg_page(sg) == virt_to_page(buf) &&
+	    sg->offset == offset_in_page(buf))
+		return;
 
-	scatterwalk_advance(&walk, start - offset);
+	scatterwalk_start(&walk, sg);
 	scatterwalk_copychunks(buf, &walk, nbytes, out);
 	scatterwalk_done(&walk, out, 0);
 }
@@ -146,3 +146,26 @@ int scatterwalk_bytes_sglen(struct scatterlist *sg, int num_bytes)
 	return n;
 }
 EXPORT_SYMBOL_GPL(scatterwalk_bytes_sglen);
+
+struct scatterlist *scatterwalk_ffwd(struct scatterlist dst[2],
+				     struct scatterlist *src,
+				     unsigned int len)
+{
+	for (;;) {
+		if (!len)
+			return src;
+
+		if (src->length > len)
+			break;
+
+		len -= src->length;
+		src = sg_next(src);
+	}
+
+	sg_init_table(dst, 2);
+	sg_set_page(dst, sg_page(src), src->length - len, src->offset + len);
+	scatterwalk_crypto_chain(dst, sg_next(src), 0, 2);
+
+	return dst;
+}
+EXPORT_SYMBOL_GPL(scatterwalk_ffwd);
diff --git a/crypto/seqiv.c b/crypto/seqiv.c
index b7bb9a2f4a31..122c56e3491b 100644
--- a/crypto/seqiv.c
+++ b/crypto/seqiv.c
@@ -13,9 +13,11 @@
  *
  */
 
-#include <crypto/internal/aead.h>
+#include <crypto/internal/geniv.h>
 #include <crypto/internal/skcipher.h>
+#include <crypto/null.h>
 #include <crypto/rng.h>
+#include <crypto/scatterwalk.h>
 #include <linux/err.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
@@ -24,11 +26,25 @@
 #include <linux/spinlock.h>
 #include <linux/string.h>
 
+struct seqniv_request_ctx {
+	struct scatterlist dst[2];
+	struct aead_request subreq;
+};
+
 struct seqiv_ctx {
 	spinlock_t lock;
 	u8 salt[] __attribute__ ((aligned(__alignof__(u32))));
 };
 
+struct seqiv_aead_ctx {
+	/* aead_geniv_ctx must be first the element */
+	struct aead_geniv_ctx geniv;
+	struct crypto_blkcipher *null;
+	u8 salt[] __attribute__ ((aligned(__alignof__(u32))));
+};
+
+static void seqiv_free(struct crypto_instance *inst);
+
 static void seqiv_complete2(struct skcipher_givcrypt_request *req, int err)
 {
 	struct ablkcipher_request *subreq = skcipher_givcrypt_reqctx(req);
@@ -81,6 +97,77 @@ static void seqiv_aead_complete(struct crypto_async_request *base, int err)
 	aead_givcrypt_complete(req, err);
 }
 
+static void seqiv_aead_encrypt_complete2(struct aead_request *req, int err)
+{
+	struct aead_request *subreq = aead_request_ctx(req);
+	struct crypto_aead *geniv;
+
+	if (err == -EINPROGRESS)
+		return;
+
+	if (err)
+		goto out;
+
+	geniv = crypto_aead_reqtfm(req);
+	memcpy(req->iv, subreq->iv, crypto_aead_ivsize(geniv));
+
+out:
+	kzfree(subreq->iv);
+}
+
+static void seqiv_aead_encrypt_complete(struct crypto_async_request *base,
+					int err)
+{
+	struct aead_request *req = base->data;
+
+	seqiv_aead_encrypt_complete2(req, err);
+	aead_request_complete(req, err);
+}
+
+static void seqniv_aead_encrypt_complete2(struct aead_request *req, int err)
+{
+	unsigned int ivsize = 8;
+	u8 data[20];
+
+	if (err == -EINPROGRESS)
+		return;
+
+	/* Swap IV and ESP header back to correct order. */
+	scatterwalk_map_and_copy(data, req->dst, 0, req->assoclen + ivsize, 0);
+	scatterwalk_map_and_copy(data + ivsize, req->dst, 0, req->assoclen, 1);
+	scatterwalk_map_and_copy(data, req->dst, req->assoclen, ivsize, 1);
+}
+
+static void seqniv_aead_encrypt_complete(struct crypto_async_request *base,
+					int err)
+{
+	struct aead_request *req = base->data;
+
+	seqniv_aead_encrypt_complete2(req, err);
+	aead_request_complete(req, err);
+}
+
+static void seqniv_aead_decrypt_complete2(struct aead_request *req, int err)
+{
+	u8 data[4];
+
+	if (err == -EINPROGRESS)
+		return;
+
+	/* Move ESP header back to correct location. */
+	scatterwalk_map_and_copy(data, req->dst, 16, req->assoclen - 8, 0);
+	scatterwalk_map_and_copy(data, req->dst, 8, req->assoclen - 8, 1);
+}
+
+static void seqniv_aead_decrypt_complete(struct crypto_async_request *base,
+					 int err)
+{
+	struct aead_request *req = base->data;
+
+	seqniv_aead_decrypt_complete2(req, err);
+	aead_request_complete(req, err);
+}
+
 static void seqiv_geniv(struct seqiv_ctx *ctx, u8 *info, u64 seq,
 			unsigned int ivsize)
 {
@@ -186,160 +273,477 @@ static int seqiv_aead_givencrypt(struct aead_givcrypt_request *req)
 	return err;
 }
 
-static int seqiv_givencrypt_first(struct skcipher_givcrypt_request *req)
+static int seqniv_aead_encrypt(struct aead_request *req)
 {
-	struct crypto_ablkcipher *geniv = skcipher_givcrypt_reqtfm(req);
-	struct seqiv_ctx *ctx = crypto_ablkcipher_ctx(geniv);
-	int err = 0;
+	struct crypto_aead *geniv = crypto_aead_reqtfm(req);
+	struct seqiv_aead_ctx *ctx = crypto_aead_ctx(geniv);
+	struct seqniv_request_ctx *rctx = aead_request_ctx(req);
+	struct aead_request *subreq = &rctx->subreq;
+	struct scatterlist *dst;
+	crypto_completion_t compl;
+	void *data;
+	unsigned int ivsize = 8;
+	u8 buf[20] __attribute__ ((aligned(__alignof__(u32))));
+	int err;
 
-	spin_lock_bh(&ctx->lock);
-	if (crypto_ablkcipher_crt(geniv)->givencrypt != seqiv_givencrypt_first)
-		goto unlock;
+	if (req->cryptlen < ivsize)
+		return -EINVAL;
 
-	crypto_ablkcipher_crt(geniv)->givencrypt = seqiv_givencrypt;
-	err = crypto_rng_get_bytes(crypto_default_rng, ctx->salt,
-				   crypto_ablkcipher_ivsize(geniv));
+	/* ESP AD is at most 12 bytes (ESN). */
+	if (req->assoclen > 12)
+		return -EINVAL;
 
-unlock:
-	spin_unlock_bh(&ctx->lock);
+	aead_request_set_tfm(subreq, ctx->geniv.child);
 
-	if (err)
-		return err;
+	compl = seqniv_aead_encrypt_complete;
+	data = req;
+
+	if (req->src != req->dst) {
+		struct blkcipher_desc desc = {
+			.tfm = ctx->null,
+		};
+
+		err = crypto_blkcipher_encrypt(&desc, req->dst, req->src,
+					       req->assoclen + req->cryptlen);
+		if (err)
+			return err;
+	}
 
-	return seqiv_givencrypt(req);
+	dst = scatterwalk_ffwd(rctx->dst, req->dst, ivsize);
+
+	aead_request_set_callback(subreq, req->base.flags, compl, data);
+	aead_request_set_crypt(subreq, dst, dst,
+			       req->cryptlen - ivsize, req->iv);
+	aead_request_set_ad(subreq, req->assoclen);
+
+	memcpy(buf, req->iv, ivsize);
+	crypto_xor(buf, ctx->salt, ivsize);
+	memcpy(req->iv, buf, ivsize);
+
+	/* Swap order of IV and ESP AD for ICV generation. */
+	scatterwalk_map_and_copy(buf + ivsize, req->dst, 0, req->assoclen, 0);
+	scatterwalk_map_and_copy(buf, req->dst, 0, req->assoclen + ivsize, 1);
+
+	err = crypto_aead_encrypt(subreq);
+	seqniv_aead_encrypt_complete2(req, err);
+	return err;
 }
 
-static int seqiv_aead_givencrypt_first(struct aead_givcrypt_request *req)
+static int seqiv_aead_encrypt(struct aead_request *req)
 {
-	struct crypto_aead *geniv = aead_givcrypt_reqtfm(req);
-	struct seqiv_ctx *ctx = crypto_aead_ctx(geniv);
-	int err = 0;
+	struct crypto_aead *geniv = crypto_aead_reqtfm(req);
+	struct seqiv_aead_ctx *ctx = crypto_aead_ctx(geniv);
+	struct aead_request *subreq = aead_request_ctx(req);
+	crypto_completion_t compl;
+	void *data;
+	u8 *info;
+	unsigned int ivsize = 8;
+	int err;
 
-	spin_lock_bh(&ctx->lock);
-	if (crypto_aead_crt(geniv)->givencrypt != seqiv_aead_givencrypt_first)
-		goto unlock;
+	if (req->cryptlen < ivsize)
+		return -EINVAL;
 
-	crypto_aead_crt(geniv)->givencrypt = seqiv_aead_givencrypt;
-	err = crypto_rng_get_bytes(crypto_default_rng, ctx->salt,
-				   crypto_aead_ivsize(geniv));
+	aead_request_set_tfm(subreq, ctx->geniv.child);
 
-unlock:
-	spin_unlock_bh(&ctx->lock);
+	compl = req->base.complete;
+	data = req->base.data;
+	info = req->iv;
 
-	if (err)
-		return err;
+	if (req->src != req->dst) {
+		struct blkcipher_desc desc = {
+			.tfm = ctx->null,
+		};
 
-	return seqiv_aead_givencrypt(req);
+		err = crypto_blkcipher_encrypt(&desc, req->dst, req->src,
+					       req->assoclen + req->cryptlen);
+		if (err)
+			return err;
+	}
+
+	if (unlikely(!IS_ALIGNED((unsigned long)info,
+				 crypto_aead_alignmask(geniv) + 1))) {
+		info = kmalloc(ivsize, req->base.flags &
+				       CRYPTO_TFM_REQ_MAY_SLEEP ? GFP_KERNEL:
+								  GFP_ATOMIC);
+		if (!info)
+			return -ENOMEM;
+
+		memcpy(info, req->iv, ivsize);
+		compl = seqiv_aead_encrypt_complete;
+		data = req;
+	}
+
+	aead_request_set_callback(subreq, req->base.flags, compl, data);
+	aead_request_set_crypt(subreq, req->dst, req->dst,
+			       req->cryptlen - ivsize, info);
+	aead_request_set_ad(subreq, req->assoclen + ivsize);
+
+	crypto_xor(info, ctx->salt, ivsize);
+	scatterwalk_map_and_copy(info, req->dst, req->assoclen, ivsize, 1);
+
+	err = crypto_aead_encrypt(subreq);
+	if (unlikely(info != req->iv))
+		seqiv_aead_encrypt_complete2(req, err);
+	return err;
+}
+
+static int seqniv_aead_decrypt(struct aead_request *req)
+{
+	struct crypto_aead *geniv = crypto_aead_reqtfm(req);
+	struct seqiv_aead_ctx *ctx = crypto_aead_ctx(geniv);
+	struct seqniv_request_ctx *rctx = aead_request_ctx(req);
+	struct aead_request *subreq = &rctx->subreq;
+	struct scatterlist *dst;
+	crypto_completion_t compl;
+	void *data;
+	unsigned int ivsize = 8;
+	u8 buf[20];
+	int err;
+
+	if (req->cryptlen < ivsize + crypto_aead_authsize(geniv))
+		return -EINVAL;
+
+	aead_request_set_tfm(subreq, ctx->geniv.child);
+
+	compl = req->base.complete;
+	data = req->base.data;
+
+	if (req->assoclen > 12)
+		return -EINVAL;
+	else if (req->assoclen > 8) {
+		compl = seqniv_aead_decrypt_complete;
+		data = req;
+	}
+
+	if (req->src != req->dst) {
+		struct blkcipher_desc desc = {
+			.tfm = ctx->null,
+		};
+
+		err = crypto_blkcipher_encrypt(&desc, req->dst, req->src,
+					       req->assoclen + req->cryptlen);
+		if (err)
+			return err;
+	}
+
+	/* Move ESP AD forward for ICV generation. */
+	scatterwalk_map_and_copy(buf, req->dst, 0, req->assoclen + ivsize, 0);
+	memcpy(req->iv, buf + req->assoclen, ivsize);
+	scatterwalk_map_and_copy(buf, req->dst, ivsize, req->assoclen, 1);
+
+	dst = scatterwalk_ffwd(rctx->dst, req->dst, ivsize);
+
+	aead_request_set_callback(subreq, req->base.flags, compl, data);
+	aead_request_set_crypt(subreq, dst, dst,
+			       req->cryptlen - ivsize, req->iv);
+	aead_request_set_ad(subreq, req->assoclen);
+
+	err = crypto_aead_decrypt(subreq);
+	if (req->assoclen > 8)
+		seqniv_aead_decrypt_complete2(req, err);
+	return err;
+}
+
+static int seqiv_aead_decrypt(struct aead_request *req)
+{
+	struct crypto_aead *geniv = crypto_aead_reqtfm(req);
+	struct seqiv_aead_ctx *ctx = crypto_aead_ctx(geniv);
+	struct aead_request *subreq = aead_request_ctx(req);
+	crypto_completion_t compl;
+	void *data;
+	unsigned int ivsize = 8;
+
+	if (req->cryptlen < ivsize + crypto_aead_authsize(geniv))
+		return -EINVAL;
+
+	aead_request_set_tfm(subreq, ctx->geniv.child);
+
+	compl = req->base.complete;
+	data = req->base.data;
+
+	aead_request_set_callback(subreq, req->base.flags, compl, data);
+	aead_request_set_crypt(subreq, req->src, req->dst,
+			       req->cryptlen - ivsize, req->iv);
+	aead_request_set_ad(subreq, req->assoclen + ivsize);
+
+	scatterwalk_map_and_copy(req->iv, req->src, req->assoclen, ivsize, 0);
+	if (req->src != req->dst)
+		scatterwalk_map_and_copy(req->iv, req->dst,
+					 req->assoclen, ivsize, 1);
+
+	return crypto_aead_decrypt(subreq);
 }
 
 static int seqiv_init(struct crypto_tfm *tfm)
 {
 	struct crypto_ablkcipher *geniv = __crypto_ablkcipher_cast(tfm);
 	struct seqiv_ctx *ctx = crypto_ablkcipher_ctx(geniv);
+	int err;
 
 	spin_lock_init(&ctx->lock);
 
 	tfm->crt_ablkcipher.reqsize = sizeof(struct ablkcipher_request);
 
-	return skcipher_geniv_init(tfm);
+	err = 0;
+	if (!crypto_get_default_rng()) {
+		crypto_ablkcipher_crt(geniv)->givencrypt = seqiv_givencrypt;
+		err = crypto_rng_get_bytes(crypto_default_rng, ctx->salt,
+					   crypto_ablkcipher_ivsize(geniv));
+		crypto_put_default_rng();
+	}
+
+	return err ?: skcipher_geniv_init(tfm);
 }
 
-static int seqiv_aead_init(struct crypto_tfm *tfm)
+static int seqiv_old_aead_init(struct crypto_tfm *tfm)
 {
 	struct crypto_aead *geniv = __crypto_aead_cast(tfm);
 	struct seqiv_ctx *ctx = crypto_aead_ctx(geniv);
+	int err;
 
 	spin_lock_init(&ctx->lock);
 
-	tfm->crt_aead.reqsize = sizeof(struct aead_request);
+	crypto_aead_set_reqsize(__crypto_aead_cast(tfm),
+				sizeof(struct aead_request));
+	err = 0;
+	if (!crypto_get_default_rng()) {
+		geniv->givencrypt = seqiv_aead_givencrypt;
+		err = crypto_rng_get_bytes(crypto_default_rng, ctx->salt,
+					   crypto_aead_ivsize(geniv));
+		crypto_put_default_rng();
+	}
 
-	return aead_geniv_init(tfm);
+	return err ?: aead_geniv_init(tfm);
 }
 
-static struct crypto_template seqiv_tmpl;
-
-static struct crypto_instance *seqiv_ablkcipher_alloc(struct rtattr **tb)
+static int seqiv_aead_init_common(struct crypto_tfm *tfm, unsigned int reqsize)
 {
-	struct crypto_instance *inst;
+	struct crypto_aead *geniv = __crypto_aead_cast(tfm);
+	struct seqiv_aead_ctx *ctx = crypto_aead_ctx(geniv);
+	int err;
 
-	inst = skcipher_geniv_alloc(&seqiv_tmpl, tb, 0, 0);
+	spin_lock_init(&ctx->geniv.lock);
 
-	if (IS_ERR(inst))
+	crypto_aead_set_reqsize(geniv, sizeof(struct aead_request));
+
+	err = crypto_get_default_rng();
+	if (err)
 		goto out;
 
-	if (inst->alg.cra_ablkcipher.ivsize < sizeof(u64)) {
-		skcipher_geniv_free(inst);
-		inst = ERR_PTR(-EINVAL);
+	err = crypto_rng_get_bytes(crypto_default_rng, ctx->salt,
+				   crypto_aead_ivsize(geniv));
+	crypto_put_default_rng();
+	if (err)
 		goto out;
-	}
 
-	inst->alg.cra_ablkcipher.givencrypt = seqiv_givencrypt_first;
+	ctx->null = crypto_get_default_null_skcipher();
+	err = PTR_ERR(ctx->null);
+	if (IS_ERR(ctx->null))
+		goto out;
 
-	inst->alg.cra_init = seqiv_init;
-	inst->alg.cra_exit = skcipher_geniv_exit;
+	err = aead_geniv_init(tfm);
+	if (err)
+		goto drop_null;
 
-	inst->alg.cra_ctxsize += inst->alg.cra_ablkcipher.ivsize;
+	ctx->geniv.child = geniv->child;
+	geniv->child = geniv;
 
 out:
-	return inst;
+	return err;
+
+drop_null:
+	crypto_put_default_null_skcipher();
+	goto out;
+}
+
+static int seqiv_aead_init(struct crypto_tfm *tfm)
+{
+	return seqiv_aead_init_common(tfm, sizeof(struct aead_request));
+}
+
+static int seqniv_aead_init(struct crypto_tfm *tfm)
+{
+	return seqiv_aead_init_common(tfm, sizeof(struct seqniv_request_ctx));
+}
+
+static void seqiv_aead_exit(struct crypto_tfm *tfm)
+{
+	struct seqiv_aead_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	crypto_free_aead(ctx->geniv.child);
+	crypto_put_default_null_skcipher();
 }
 
-static struct crypto_instance *seqiv_aead_alloc(struct rtattr **tb)
+static int seqiv_ablkcipher_create(struct crypto_template *tmpl,
+				   struct rtattr **tb)
 {
 	struct crypto_instance *inst;
+	int err;
 
-	inst = aead_geniv_alloc(&seqiv_tmpl, tb, 0, 0);
+	inst = skcipher_geniv_alloc(tmpl, tb, 0, 0);
 
 	if (IS_ERR(inst))
-		goto out;
+		return PTR_ERR(inst);
 
-	if (inst->alg.cra_aead.ivsize < sizeof(u64)) {
-		aead_geniv_free(inst);
-		inst = ERR_PTR(-EINVAL);
-		goto out;
-	}
+	err = -EINVAL;
+	if (inst->alg.cra_ablkcipher.ivsize < sizeof(u64))
+		goto free_inst;
+
+	inst->alg.cra_init = seqiv_init;
+	inst->alg.cra_exit = skcipher_geniv_exit;
+
+	inst->alg.cra_ctxsize += inst->alg.cra_ablkcipher.ivsize;
+	inst->alg.cra_ctxsize += sizeof(struct seqiv_ctx);
+
+	inst->alg.cra_alignmask |= __alignof__(u32) - 1;
 
-	inst->alg.cra_aead.givencrypt = seqiv_aead_givencrypt_first;
+	err = crypto_register_instance(tmpl, inst);
+	if (err)
+		goto free_inst;
 
-	inst->alg.cra_init = seqiv_aead_init;
+out:
+	return err;
+
+free_inst:
+	skcipher_geniv_free(inst);
+	goto out;
+}
+
+static int seqiv_old_aead_create(struct crypto_template *tmpl,
+				 struct aead_instance *aead)
+{
+	struct crypto_instance *inst = aead_crypto_instance(aead);
+	int err = -EINVAL;
+
+	if (inst->alg.cra_aead.ivsize < sizeof(u64))
+		goto free_inst;
+
+	inst->alg.cra_init = seqiv_old_aead_init;
 	inst->alg.cra_exit = aead_geniv_exit;
 
 	inst->alg.cra_ctxsize = inst->alg.cra_aead.ivsize;
+	inst->alg.cra_ctxsize += sizeof(struct seqiv_ctx);
+
+	err = crypto_register_instance(tmpl, inst);
+	if (err)
+		goto free_inst;
 
 out:
-	return inst;
+	return err;
+
+free_inst:
+	aead_geniv_free(aead);
+	goto out;
 }
 
-static struct crypto_instance *seqiv_alloc(struct rtattr **tb)
+static int seqiv_aead_create(struct crypto_template *tmpl, struct rtattr **tb)
+{
+	struct aead_instance *inst;
+	struct crypto_aead_spawn *spawn;
+	struct aead_alg *alg;
+	int err;
+
+	inst = aead_geniv_alloc(tmpl, tb, 0, 0);
+
+	if (IS_ERR(inst))
+		return PTR_ERR(inst);
+
+	inst->alg.base.cra_alignmask |= __alignof__(u32) - 1;
+
+	if (inst->alg.base.cra_aead.encrypt)
+		return seqiv_old_aead_create(tmpl, inst);
+
+	spawn = aead_instance_ctx(inst);
+	alg = crypto_spawn_aead_alg(spawn);
+
+	if (alg->base.cra_aead.encrypt)
+		goto done;
+
+	err = -EINVAL;
+	if (inst->alg.ivsize != sizeof(u64))
+		goto free_inst;
+
+	inst->alg.encrypt = seqiv_aead_encrypt;
+	inst->alg.decrypt = seqiv_aead_decrypt;
+
+	inst->alg.base.cra_init = seqiv_aead_init;
+	inst->alg.base.cra_exit = seqiv_aead_exit;
+
+	inst->alg.base.cra_ctxsize = sizeof(struct seqiv_aead_ctx);
+	inst->alg.base.cra_ctxsize += inst->alg.base.cra_aead.ivsize;
+
+done:
+	err = aead_register_instance(tmpl, inst);
+	if (err)
+		goto free_inst;
+
+out:
+	return err;
+
+free_inst:
+	aead_geniv_free(inst);
+	goto out;
+}
+
+static int seqiv_create(struct crypto_template *tmpl, struct rtattr **tb)
 {
 	struct crypto_attr_type *algt;
-	struct crypto_instance *inst;
 	int err;
 
 	algt = crypto_get_attr_type(tb);
 	if (IS_ERR(algt))
-		return ERR_CAST(algt);
-
-	err = crypto_get_default_rng();
-	if (err)
-		return ERR_PTR(err);
+		return PTR_ERR(algt);
 
 	if ((algt->type ^ CRYPTO_ALG_TYPE_AEAD) & CRYPTO_ALG_TYPE_MASK)
-		inst = seqiv_ablkcipher_alloc(tb);
+		err = seqiv_ablkcipher_create(tmpl, tb);
 	else
-		inst = seqiv_aead_alloc(tb);
+		err = seqiv_aead_create(tmpl, tb);
 
+	return err;
+}
+
+static int seqniv_create(struct crypto_template *tmpl, struct rtattr **tb)
+{
+	struct aead_instance *inst;
+	struct crypto_aead_spawn *spawn;
+	struct aead_alg *alg;
+	int err;
+
+	inst = aead_geniv_alloc(tmpl, tb, 0, 0);
+	err = PTR_ERR(inst);
 	if (IS_ERR(inst))
-		goto put_rng;
+		goto out;
 
-	inst->alg.cra_alignmask |= __alignof__(u32) - 1;
-	inst->alg.cra_ctxsize += sizeof(struct seqiv_ctx);
+	spawn = aead_instance_ctx(inst);
+	alg = crypto_spawn_aead_alg(spawn);
+
+	if (alg->base.cra_aead.encrypt)
+		goto done;
+
+	err = -EINVAL;
+	if (inst->alg.ivsize != sizeof(u64))
+		goto free_inst;
+
+	inst->alg.encrypt = seqniv_aead_encrypt;
+	inst->alg.decrypt = seqniv_aead_decrypt;
+
+	inst->alg.base.cra_init = seqniv_aead_init;
+	inst->alg.base.cra_exit = seqiv_aead_exit;
+
+	inst->alg.base.cra_alignmask |= __alignof__(u32) - 1;
+	inst->alg.base.cra_ctxsize = sizeof(struct seqiv_aead_ctx);
+	inst->alg.base.cra_ctxsize += inst->alg.ivsize;
+
+done:
+	err = aead_register_instance(tmpl, inst);
+	if (err)
+		goto free_inst;
 
 out:
-	return inst;
+	return err;
 
-put_rng:
-	crypto_put_default_rng();
+free_inst:
+	aead_geniv_free(inst);
 	goto out;
 }
 
@@ -348,24 +752,46 @@ static void seqiv_free(struct crypto_instance *inst)
 	if ((inst->alg.cra_flags ^ CRYPTO_ALG_TYPE_AEAD) & CRYPTO_ALG_TYPE_MASK)
 		skcipher_geniv_free(inst);
 	else
-		aead_geniv_free(inst);
-	crypto_put_default_rng();
+		aead_geniv_free(aead_instance(inst));
 }
 
 static struct crypto_template seqiv_tmpl = {
 	.name = "seqiv",
-	.alloc = seqiv_alloc,
+	.create = seqiv_create,
+	.free = seqiv_free,
+	.module = THIS_MODULE,
+};
+
+static struct crypto_template seqniv_tmpl = {
+	.name = "seqniv",
+	.create = seqniv_create,
 	.free = seqiv_free,
 	.module = THIS_MODULE,
 };
 
 static int __init seqiv_module_init(void)
 {
-	return crypto_register_template(&seqiv_tmpl);
+	int err;
+
+	err = crypto_register_template(&seqiv_tmpl);
+	if (err)
+		goto out;
+
+	err = crypto_register_template(&seqniv_tmpl);
+	if (err)
+		goto out_undo_niv;
+
+out:
+	return err;
+
+out_undo_niv:
+	crypto_unregister_template(&seqiv_tmpl);
+	goto out;
 }
 
 static void __exit seqiv_module_exit(void)
 {
+	crypto_unregister_template(&seqniv_tmpl);
 	crypto_unregister_template(&seqiv_tmpl);
 }
 
@@ -375,3 +801,4 @@ module_exit(seqiv_module_exit);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Sequence Number IV Generator");
 MODULE_ALIAS_CRYPTO("seqiv");
+MODULE_ALIAS_CRYPTO("seqniv");
diff --git a/crypto/shash.c b/crypto/shash.c
index 47c713954bf3..ecb1e3d39bf0 100644
--- a/crypto/shash.c
+++ b/crypto/shash.c
@@ -520,11 +520,6 @@ static int crypto_shash_init_tfm(struct crypto_tfm *tfm)
 	return 0;
 }
 
-static unsigned int crypto_shash_extsize(struct crypto_alg *alg)
-{
-	return alg->cra_ctxsize;
-}
-
 #ifdef CONFIG_NET
 static int crypto_shash_report(struct sk_buff *skb, struct crypto_alg *alg)
 {
@@ -564,7 +559,7 @@ static void crypto_shash_show(struct seq_file *m, struct crypto_alg *alg)
 
 static const struct crypto_type crypto_shash_type = {
 	.ctxsize = crypto_shash_ctxsize,
-	.extsize = crypto_shash_extsize,
+	.extsize = crypto_alg_extsize,
 	.init = crypto_init_shash_ops,
 	.init_tfm = crypto_shash_init_tfm,
 #ifdef CONFIG_PROC_FS
diff --git a/crypto/tcrypt.c b/crypto/tcrypt.c
index 1a2800107fc8..9f6f10b498ba 100644
--- a/crypto/tcrypt.c
+++ b/crypto/tcrypt.c
@@ -22,8 +22,10 @@
  *
  */
 
+#include <crypto/aead.h>
 #include <crypto/hash.h>
 #include <linux/err.h>
+#include <linux/fips.h>
 #include <linux/init.h>
 #include <linux/gfp.h>
 #include <linux/module.h>
@@ -34,7 +36,6 @@
 #include <linux/timex.h>
 #include <linux/interrupt.h>
 #include "tcrypt.h"
-#include "internal.h"
 
 /*
  * Need slab memory for testing (size in number of pages).
@@ -257,12 +258,12 @@ static void sg_init_aead(struct scatterlist *sg, char *xbuf[XBUFSIZE],
 		rem = buflen % PAGE_SIZE;
 	}
 
-	sg_init_table(sg, np);
+	sg_init_table(sg, np + 1);
 	np--;
 	for (k = 0; k < np; k++)
-		sg_set_buf(&sg[k], xbuf[k], PAGE_SIZE);
+		sg_set_buf(&sg[k + 1], xbuf[k], PAGE_SIZE);
 
-	sg_set_buf(&sg[k], xbuf[k], rem);
+	sg_set_buf(&sg[k + 1], xbuf[k], rem);
 }
 
 static void test_aead_speed(const char *algo, int enc, unsigned int secs,
@@ -276,7 +277,6 @@ static void test_aead_speed(const char *algo, int enc, unsigned int secs,
 	const char *key;
 	struct aead_request *req;
 	struct scatterlist *sg;
-	struct scatterlist *asg;
 	struct scatterlist *sgout;
 	const char *e;
 	void *assoc;
@@ -308,11 +308,10 @@ static void test_aead_speed(const char *algo, int enc, unsigned int secs,
 	if (testmgr_alloc_buf(xoutbuf))
 		goto out_nooutbuf;
 
-	sg = kmalloc(sizeof(*sg) * 8 * 3, GFP_KERNEL);
+	sg = kmalloc(sizeof(*sg) * 9 * 2, GFP_KERNEL);
 	if (!sg)
 		goto out_nosg;
-	asg = &sg[8];
-	sgout = &asg[8];
+	sgout = &sg[9];
 
 	tfm = crypto_alloc_aead(algo, 0, 0);
 
@@ -338,7 +337,6 @@ static void test_aead_speed(const char *algo, int enc, unsigned int secs,
 		do {
 			assoc = axbuf[0];
 			memset(assoc, 0xff, aad_size);
-			sg_init_one(&asg[0], assoc, aad_size);
 
 			if ((*keysize + *b_size) > TVMEMSIZE * PAGE_SIZE) {
 				pr_err("template (%u) too big for tvmem (%lu)\n",
@@ -374,14 +372,17 @@ static void test_aead_speed(const char *algo, int enc, unsigned int secs,
 				goto out;
 			}
 
-			sg_init_aead(&sg[0], xbuf,
+			sg_init_aead(sg, xbuf,
 				    *b_size + (enc ? authsize : 0));
 
-			sg_init_aead(&sgout[0], xoutbuf,
+			sg_init_aead(sgout, xoutbuf,
 				    *b_size + (enc ? authsize : 0));
 
+			sg_set_buf(&sg[0], assoc, aad_size);
+			sg_set_buf(&sgout[0], assoc, aad_size);
+
 			aead_request_set_crypt(req, sg, sgout, *b_size, iv);
-			aead_request_set_assoc(req, asg, aad_size);
+			aead_request_set_ad(req, aad_size);
 
 			if (secs)
 				ret = test_aead_jiffies(req, enc, *b_size,
@@ -808,7 +809,7 @@ static int test_ahash_jiffies(struct ahash_request *req, int blen,
 
 	for (start = jiffies, end = start + secs * HZ, bcount = 0;
 	     time_before(jiffies, end); bcount++) {
-		ret = crypto_ahash_init(req);
+		ret = do_one_ahash_op(req, crypto_ahash_init(req));
 		if (ret)
 			return ret;
 		for (pcount = 0; pcount < blen; pcount += plen) {
@@ -877,7 +878,7 @@ static int test_ahash_cycles(struct ahash_request *req, int blen,
 
 	/* Warm-up run. */
 	for (i = 0; i < 4; i++) {
-		ret = crypto_ahash_init(req);
+		ret = do_one_ahash_op(req, crypto_ahash_init(req));
 		if (ret)
 			goto out;
 		for (pcount = 0; pcount < blen; pcount += plen) {
@@ -896,7 +897,7 @@ static int test_ahash_cycles(struct ahash_request *req, int blen,
 
 		start = get_cycles();
 
-		ret = crypto_ahash_init(req);
+		ret = do_one_ahash_op(req, crypto_ahash_init(req));
 		if (ret)
 			goto out;
 		for (pcount = 0; pcount < blen; pcount += plen) {
@@ -1761,6 +1762,11 @@ static int do_test(const char *alg, u32 type, u32 mask, int m)
 				NULL, 0, 16, 8, aead_speed_template_20);
 		break;
 
+	case 212:
+		test_aead_speed("rfc4309(ccm(aes))", ENCRYPT, sec,
+				NULL, 0, 16, 8, aead_speed_template_19);
+		break;
+
 	case 300:
 		if (alg) {
 			test_hash_speed(alg, sec, generic_hash_speed_template);
diff --git a/crypto/tcrypt.h b/crypto/tcrypt.h
index 6c7e21a09f78..6cc1b856871b 100644
--- a/crypto/tcrypt.h
+++ b/crypto/tcrypt.h
@@ -65,6 +65,7 @@ static u8 speed_template_32_64[] = {32, 64, 0};
 /*
  * AEAD speed tests
  */
+static u8 aead_speed_template_19[] = {19, 0};
 static u8 aead_speed_template_20[] = {20, 0};
 
 /*
diff --git a/crypto/testmgr.c b/crypto/testmgr.c
index f9bce3d7ee7f..975e1eac3e2d 100644
--- a/crypto/testmgr.c
+++ b/crypto/testmgr.c
@@ -20,14 +20,17 @@
  *
  */
 
+#include <crypto/aead.h>
 #include <crypto/hash.h>
 #include <linux/err.h>
+#include <linux/fips.h>
 #include <linux/module.h>
 #include <linux/scatterlist.h>
 #include <linux/slab.h>
 #include <linux/string.h>
 #include <crypto/rng.h>
 #include <crypto/drbg.h>
+#include <crypto/akcipher.h>
 
 #include "internal.h"
 
@@ -114,6 +117,11 @@ struct drbg_test_suite {
 	unsigned int count;
 };
 
+struct akcipher_test_suite {
+	struct akcipher_testvec *vecs;
+	unsigned int count;
+};
+
 struct alg_test_desc {
 	const char *alg;
 	int (*test)(const struct alg_test_desc *desc, const char *driver,
@@ -128,6 +136,7 @@ struct alg_test_desc {
 		struct hash_test_suite hash;
 		struct cprng_test_suite cprng;
 		struct drbg_test_suite drbg;
+		struct akcipher_test_suite akcipher;
 	} suite;
 };
 
@@ -425,7 +434,6 @@ static int __test_aead(struct crypto_aead *tfm, int enc,
 	char *key;
 	struct aead_request *req;
 	struct scatterlist *sg;
-	struct scatterlist *asg;
 	struct scatterlist *sgout;
 	const char *e, *d;
 	struct tcrypt_result result;
@@ -452,11 +460,10 @@ static int __test_aead(struct crypto_aead *tfm, int enc,
 		goto out_nooutbuf;
 
 	/* avoid "the frame size is larger than 1024 bytes" compiler warning */
-	sg = kmalloc(sizeof(*sg) * 8 * (diff_dst ? 3 : 2), GFP_KERNEL);
+	sg = kmalloc(sizeof(*sg) * 8 * (diff_dst ? 4 : 2), GFP_KERNEL);
 	if (!sg)
 		goto out_nosg;
-	asg = &sg[8];
-	sgout = &asg[8];
+	sgout = &sg[16];
 
 	if (diff_dst)
 		d = "-ddst";
@@ -535,23 +542,27 @@ static int __test_aead(struct crypto_aead *tfm, int enc,
 			goto out;
 		}
 
+		k = !!template[i].alen;
+		sg_init_table(sg, k + 1);
+		sg_set_buf(&sg[0], assoc, template[i].alen);
+		sg_set_buf(&sg[k], input,
+			   template[i].ilen + (enc ? authsize : 0));
+		output = input;
+
 		if (diff_dst) {
+			sg_init_table(sgout, k + 1);
+			sg_set_buf(&sgout[0], assoc, template[i].alen);
+
 			output = xoutbuf[0];
 			output += align_offset;
-			sg_init_one(&sg[0], input, template[i].ilen);
-			sg_init_one(&sgout[0], output, template[i].rlen);
-		} else {
-			sg_init_one(&sg[0], input,
-				    template[i].ilen + (enc ? authsize : 0));
-			output = input;
+			sg_set_buf(&sgout[k], output,
+				   template[i].rlen + (enc ? 0 : authsize));
 		}
 
-		sg_init_one(&asg[0], assoc, template[i].alen);
-
 		aead_request_set_crypt(req, sg, (diff_dst) ? sgout : sg,
 				       template[i].ilen, iv);
 
-		aead_request_set_assoc(req, asg, template[i].alen);
+		aead_request_set_ad(req, template[i].alen);
 
 		ret = enc ? crypto_aead_encrypt(req) : crypto_aead_decrypt(req);
 
@@ -631,9 +642,29 @@ static int __test_aead(struct crypto_aead *tfm, int enc,
 		authsize = abs(template[i].rlen - template[i].ilen);
 
 		ret = -EINVAL;
-		sg_init_table(sg, template[i].np);
+		sg_init_table(sg, template[i].anp + template[i].np);
 		if (diff_dst)
-			sg_init_table(sgout, template[i].np);
+			sg_init_table(sgout, template[i].anp + template[i].np);
+
+		ret = -EINVAL;
+		for (k = 0, temp = 0; k < template[i].anp; k++) {
+			if (WARN_ON(offset_in_page(IDX[k]) +
+				    template[i].atap[k] > PAGE_SIZE))
+				goto out;
+			sg_set_buf(&sg[k],
+				   memcpy(axbuf[IDX[k] >> PAGE_SHIFT] +
+					  offset_in_page(IDX[k]),
+					  template[i].assoc + temp,
+					  template[i].atap[k]),
+				   template[i].atap[k]);
+			if (diff_dst)
+				sg_set_buf(&sgout[k],
+					   axbuf[IDX[k] >> PAGE_SHIFT] +
+					   offset_in_page(IDX[k]),
+					   template[i].atap[k]);
+			temp += template[i].atap[k];
+		}
+
 		for (k = 0, temp = 0; k < template[i].np; k++) {
 			if (WARN_ON(offset_in_page(IDX[k]) +
 				    template[i].tap[k] > PAGE_SIZE))
@@ -641,7 +672,8 @@ static int __test_aead(struct crypto_aead *tfm, int enc,
 
 			q = xbuf[IDX[k] >> PAGE_SHIFT] + offset_in_page(IDX[k]);
 			memcpy(q, template[i].input + temp, template[i].tap[k]);
-			sg_set_buf(&sg[k], q, template[i].tap[k]);
+			sg_set_buf(&sg[template[i].anp + k],
+				   q, template[i].tap[k]);
 
 			if (diff_dst) {
 				q = xoutbuf[IDX[k] >> PAGE_SHIFT] +
@@ -649,7 +681,8 @@ static int __test_aead(struct crypto_aead *tfm, int enc,
 
 				memset(q, 0, template[i].tap[k]);
 
-				sg_set_buf(&sgout[k], q, template[i].tap[k]);
+				sg_set_buf(&sgout[template[i].anp + k],
+					   q, template[i].tap[k]);
 			}
 
 			n = template[i].tap[k];
@@ -669,39 +702,24 @@ static int __test_aead(struct crypto_aead *tfm, int enc,
 		}
 
 		if (enc) {
-			if (WARN_ON(sg[k - 1].offset +
-				    sg[k - 1].length + authsize >
-				    PAGE_SIZE)) {
+			if (WARN_ON(sg[template[i].anp + k - 1].offset +
+				    sg[template[i].anp + k - 1].length +
+				    authsize > PAGE_SIZE)) {
 				ret = -EINVAL;
 				goto out;
 			}
 
 			if (diff_dst)
-				sgout[k - 1].length += authsize;
-			else
-				sg[k - 1].length += authsize;
-		}
-
-		sg_init_table(asg, template[i].anp);
-		ret = -EINVAL;
-		for (k = 0, temp = 0; k < template[i].anp; k++) {
-			if (WARN_ON(offset_in_page(IDX[k]) +
-				    template[i].atap[k] > PAGE_SIZE))
-				goto out;
-			sg_set_buf(&asg[k],
-				   memcpy(axbuf[IDX[k] >> PAGE_SHIFT] +
-					  offset_in_page(IDX[k]),
-					  template[i].assoc + temp,
-					  template[i].atap[k]),
-				   template[i].atap[k]);
-			temp += template[i].atap[k];
+				sgout[template[i].anp + k - 1].length +=
+					authsize;
+			sg[template[i].anp + k - 1].length += authsize;
 		}
 
 		aead_request_set_crypt(req, sg, (diff_dst) ? sgout : sg,
 				       template[i].ilen,
 				       iv);
 
-		aead_request_set_assoc(req, asg, template[i].alen);
+		aead_request_set_ad(req, template[i].alen);
 
 		ret = enc ? crypto_aead_encrypt(req) : crypto_aead_decrypt(req);
 
@@ -1814,6 +1832,147 @@ static int alg_test_drbg(const struct alg_test_desc *desc, const char *driver,
 
 }
 
+static int do_test_rsa(struct crypto_akcipher *tfm,
+		       struct akcipher_testvec *vecs)
+{
+	struct akcipher_request *req;
+	void *outbuf_enc = NULL;
+	void *outbuf_dec = NULL;
+	struct tcrypt_result result;
+	unsigned int out_len_max, out_len = 0;
+	int err = -ENOMEM;
+
+	req = akcipher_request_alloc(tfm, GFP_KERNEL);
+	if (!req)
+		return err;
+
+	init_completion(&result.completion);
+	err = crypto_akcipher_setkey(tfm, vecs->key, vecs->key_len);
+	if (err)
+		goto free_req;
+
+	akcipher_request_set_crypt(req, vecs->m, outbuf_enc, vecs->m_size,
+				   out_len);
+	/* expect this to fail, and update the required buf len */
+	crypto_akcipher_encrypt(req);
+	out_len = req->dst_len;
+	if (!out_len) {
+		err = -EINVAL;
+		goto free_req;
+	}
+
+	out_len_max = out_len;
+	err = -ENOMEM;
+	outbuf_enc = kzalloc(out_len_max, GFP_KERNEL);
+	if (!outbuf_enc)
+		goto free_req;
+
+	akcipher_request_set_crypt(req, vecs->m, outbuf_enc, vecs->m_size,
+				   out_len);
+	akcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+				      tcrypt_complete, &result);
+
+	/* Run RSA encrypt - c = m^e mod n;*/
+	err = wait_async_op(&result, crypto_akcipher_encrypt(req));
+	if (err) {
+		pr_err("alg: rsa: encrypt test failed. err %d\n", err);
+		goto free_all;
+	}
+	if (out_len != vecs->c_size) {
+		pr_err("alg: rsa: encrypt test failed. Invalid output len\n");
+		err = -EINVAL;
+		goto free_all;
+	}
+	/* verify that encrypted message is equal to expected */
+	if (memcmp(vecs->c, outbuf_enc, vecs->c_size)) {
+		pr_err("alg: rsa: encrypt test failed. Invalid output\n");
+		err = -EINVAL;
+		goto free_all;
+	}
+	/* Don't invoke decrypt for vectors with public key */
+	if (vecs->public_key_vec) {
+		err = 0;
+		goto free_all;
+	}
+	outbuf_dec = kzalloc(out_len_max, GFP_KERNEL);
+	if (!outbuf_dec) {
+		err = -ENOMEM;
+		goto free_all;
+	}
+	init_completion(&result.completion);
+	akcipher_request_set_crypt(req, outbuf_enc, outbuf_dec, vecs->c_size,
+				   out_len);
+
+	/* Run RSA decrypt - m = c^d mod n;*/
+	err = wait_async_op(&result, crypto_akcipher_decrypt(req));
+	if (err) {
+		pr_err("alg: rsa: decrypt test failed. err %d\n", err);
+		goto free_all;
+	}
+	out_len = req->dst_len;
+	if (out_len != vecs->m_size) {
+		pr_err("alg: rsa: decrypt test failed. Invalid output len\n");
+		err = -EINVAL;
+		goto free_all;
+	}
+	/* verify that decrypted message is equal to the original msg */
+	if (memcmp(vecs->m, outbuf_dec, vecs->m_size)) {
+		pr_err("alg: rsa: decrypt test failed. Invalid output\n");
+		err = -EINVAL;
+	}
+free_all:
+	kfree(outbuf_dec);
+	kfree(outbuf_enc);
+free_req:
+	akcipher_request_free(req);
+	return err;
+}
+
+static int test_rsa(struct crypto_akcipher *tfm, struct akcipher_testvec *vecs,
+		    unsigned int tcount)
+{
+	int ret, i;
+
+	for (i = 0; i < tcount; i++) {
+		ret = do_test_rsa(tfm, vecs++);
+		if (ret) {
+			pr_err("alg: rsa: test failed on vector %d, err=%d\n",
+			       i + 1, ret);
+			return ret;
+		}
+	}
+	return 0;
+}
+
+static int test_akcipher(struct crypto_akcipher *tfm, const char *alg,
+			 struct akcipher_testvec *vecs, unsigned int tcount)
+{
+	if (strncmp(alg, "rsa", 3) == 0)
+		return test_rsa(tfm, vecs, tcount);
+
+	return 0;
+}
+
+static int alg_test_akcipher(const struct alg_test_desc *desc,
+			     const char *driver, u32 type, u32 mask)
+{
+	struct crypto_akcipher *tfm;
+	int err = 0;
+
+	tfm = crypto_alloc_akcipher(driver, type | CRYPTO_ALG_INTERNAL, mask);
+	if (IS_ERR(tfm)) {
+		pr_err("alg: akcipher: Failed to load tfm for %s: %ld\n",
+		       driver, PTR_ERR(tfm));
+		return PTR_ERR(tfm);
+	}
+	if (desc->suite.akcipher.vecs)
+		err = test_akcipher(tfm, desc->alg, desc->suite.akcipher.vecs,
+				    desc->suite.akcipher.count);
+
+	crypto_free_akcipher(tfm);
+	return err;
+}
+
 static int alg_test_null(const struct alg_test_desc *desc,
 			     const char *driver, u32 type, u32 mask)
 {
@@ -2297,6 +2456,21 @@ static const struct alg_test_desc alg_test_descs[] = {
 			}
 		}
 	}, {
+		.alg = "chacha20",
+		.test = alg_test_skcipher,
+		.suite = {
+			.cipher = {
+				.enc = {
+					.vecs = chacha20_enc_tv_template,
+					.count = CHACHA20_ENC_TEST_VECTORS
+				},
+				.dec = {
+					.vecs = chacha20_enc_tv_template,
+					.count = CHACHA20_ENC_TEST_VECTORS
+				},
+			}
+		}
+	}, {
 		.alg = "cmac(aes)",
 		.test = alg_test_hash,
 		.suite = {
@@ -2318,6 +2492,15 @@ static const struct alg_test_desc alg_test_descs[] = {
 		.alg = "compress_null",
 		.test = alg_test_null,
 	}, {
+		.alg = "crc32",
+		.test = alg_test_hash,
+		.suite = {
+			.hash = {
+				.vecs = crc32_tv_template,
+				.count = CRC32_TEST_VECTORS
+			}
+		}
+	}, {
 		.alg = "crc32c",
 		.test = alg_test_crc32c,
 		.fips_allowed = 1,
@@ -3095,6 +3278,10 @@ static const struct alg_test_desc alg_test_descs[] = {
 			}
 		}
 	}, {
+		.alg = "jitterentropy_rng",
+		.fips_allowed = 1,
+		.test = alg_test_null,
+	}, {
 		.alg = "lrw(aes)",
 		.test = alg_test_skcipher,
 		.suite = {
@@ -3276,6 +3463,15 @@ static const struct alg_test_desc alg_test_descs[] = {
 			}
 		}
 	}, {
+		.alg = "poly1305",
+		.test = alg_test_hash,
+		.suite = {
+			.hash = {
+				.vecs = poly1305_tv_template,
+				.count = POLY1305_TEST_VECTORS
+			}
+		}
+	}, {
 		.alg = "rfc3686(ctr(aes))",
 		.test = alg_test_skcipher,
 		.fips_allowed = 1,
@@ -3339,6 +3535,36 @@ static const struct alg_test_desc alg_test_descs[] = {
 			}
 		}
 	}, {
+		.alg = "rfc7539(chacha20,poly1305)",
+		.test = alg_test_aead,
+		.suite = {
+			.aead = {
+				.enc = {
+					.vecs = rfc7539_enc_tv_template,
+					.count = RFC7539_ENC_TEST_VECTORS
+				},
+				.dec = {
+					.vecs = rfc7539_dec_tv_template,
+					.count = RFC7539_DEC_TEST_VECTORS
+				},
+			}
+		}
+	}, {
+		.alg = "rfc7539esp(chacha20,poly1305)",
+		.test = alg_test_aead,
+		.suite = {
+			.aead = {
+				.enc = {
+					.vecs = rfc7539esp_enc_tv_template,
+					.count = RFC7539ESP_ENC_TEST_VECTORS
+				},
+				.dec = {
+					.vecs = rfc7539esp_dec_tv_template,
+					.count = RFC7539ESP_DEC_TEST_VECTORS
+				},
+			}
+		}
+	}, {
 		.alg = "rmd128",
 		.test = alg_test_hash,
 		.suite = {
@@ -3375,6 +3601,16 @@ static const struct alg_test_desc alg_test_descs[] = {
 			}
 		}
 	}, {
+		.alg = "rsa",
+		.test = alg_test_akcipher,
+		.fips_allowed = 1,
+		.suite = {
+			.akcipher = {
+				.vecs = rsa_tv_template,
+				.count = RSA_TEST_VECTORS
+			}
+		}
+	}, {
 		.alg = "salsa20",
 		.test = alg_test_skcipher,
 		.suite = {
diff --git a/crypto/testmgr.h b/crypto/testmgr.h
index 62e2485bb428..868edf117041 100644
--- a/crypto/testmgr.h
+++ b/crypto/testmgr.h
@@ -46,6 +46,24 @@ struct hash_testvec {
 	unsigned char ksize;
 };
 
+/*
+ * cipher_testvec:	structure to describe a cipher test
+ * @key:	A pointer to a key used by the test
+ * @klen:	The length of @key
+ * @iv:		A pointer to the IV used by the test
+ * @input:	A pointer to data used as input
+ * @ilen	The length of data in @input
+ * @result:	A pointer to what the test need to produce
+ * @rlen:	The length of data in @result
+ * @fail:	If set to one, the test need to fail
+ * @wk:		Does the test need CRYPTO_TFM_REQ_WEAK_KEY
+ * 		( e.g. test needs to fail due to a weak key )
+ * @np: 	numbers of SG to distribute data in (from 1 to MAX_TAP)
+ * @tap:	How to distribute data in @np SGs
+ * @also_non_np: 	if set to 1, the test will be also done without
+ * 			splitting data in @np SGs
+ */
+
 struct cipher_testvec {
 	char *key;
 	char *iv;
@@ -54,7 +72,7 @@ struct cipher_testvec {
 	unsigned short tap[MAX_TAP];
 	int np;
 	unsigned char also_non_np;
-	unsigned char fail;
+	bool fail;
 	unsigned char wk; /* weak key flag */
 	unsigned char klen;
 	unsigned short ilen;
@@ -71,7 +89,7 @@ struct aead_testvec {
 	unsigned char atap[MAX_TAP];
 	int np;
 	int anp;
-	unsigned char fail;
+	bool fail;
 	unsigned char novrfy;	/* ccm dec verification failure expected */
 	unsigned char wk; /* weak key flag */
 	unsigned char klen;
@@ -107,9 +125,196 @@ struct drbg_testvec {
 	size_t expectedlen;
 };
 
+struct akcipher_testvec {
+	unsigned char *key;
+	unsigned char *m;
+	unsigned char *c;
+	unsigned int key_len;
+	unsigned int m_size;
+	unsigned int c_size;
+	bool public_key_vec;
+};
+
 static char zeroed_string[48];
 
 /*
+ * RSA test vectors. Borrowed from openSSL.
+ */
+#ifdef CONFIG_CRYPTO_FIPS
+#define RSA_TEST_VECTORS	2
+#else
+#define RSA_TEST_VECTORS	4
+#endif
+static struct akcipher_testvec rsa_tv_template[] = {
+	{
+#ifndef CONFIG_CRYPTO_FIPS
+	.key =
+	"\x30\x81\x88" /* sequence of 136 bytes */
+	"\x02\x41" /* modulus - integer of 65 bytes */
+	"\x00\xAA\x36\xAB\xCE\x88\xAC\xFD\xFF\x55\x52\x3C\x7F\xC4\x52\x3F"
+	"\x90\xEF\xA0\x0D\xF3\x77\x4A\x25\x9F\x2E\x62\xB4\xC5\xD9\x9C\xB5"
+	"\xAD\xB3\x00\xA0\x28\x5E\x53\x01\x93\x0E\x0C\x70\xFB\x68\x76\x93"
+	"\x9C\xE6\x16\xCE\x62\x4A\x11\xE0\x08\x6D\x34\x1E\xBC\xAC\xA0\xA1"
+	"\xF5"
+	"\x02\x01\x11" /* public key - integer of 1 byte */
+	"\x02\x40" /* private key - integer of 64 bytes */
+	"\x0A\x03\x37\x48\x62\x64\x87\x69\x5F\x5F\x30\xBC\x38\xB9\x8B\x44"
+	"\xC2\xCD\x2D\xFF\x43\x40\x98\xCD\x20\xD8\xA1\x38\xD0\x90\xBF\x64"
+	"\x79\x7C\x3F\xA7\xA2\xCD\xCB\x3C\xD1\xE0\xBD\xBA\x26\x54\xB4\xF9"
+	"\xDF\x8E\x8A\xE5\x9D\x73\x3D\x9F\x33\xB3\x01\x62\x4A\xFD\x1D\x51",
+	.m = "\x54\x85\x9b\x34\x2c\x49\xea\x2a",
+	.c =
+	"\x63\x1c\xcd\x7b\xe1\x7e\xe4\xde\xc9\xa8\x89\xa1\x74\xcb\x3c\x63"
+	"\x7d\x24\xec\x83\xc3\x15\xe4\x7f\x73\x05\x34\xd1\xec\x22\xbb\x8a"
+	"\x5e\x32\x39\x6d\xc1\x1d\x7d\x50\x3b\x9f\x7a\xad\xf0\x2e\x25\x53"
+	"\x9f\x6e\xbd\x4c\x55\x84\x0c\x9b\xcf\x1a\x4b\x51\x1e\x9e\x0c\x06",
+	.key_len = 139,
+	.m_size = 8,
+	.c_size = 64,
+	}, {
+	.key =
+	"\x30\x82\x01\x0B" /* sequence of 267 bytes */
+	"\x02\x81\x81" /* modulus - integer of 129 bytes */
+	"\x00\xBB\xF8\x2F\x09\x06\x82\xCE\x9C\x23\x38\xAC\x2B\x9D\xA8\x71"
+	"\xF7\x36\x8D\x07\xEE\xD4\x10\x43\xA4\x40\xD6\xB6\xF0\x74\x54\xF5"
+	"\x1F\xB8\xDF\xBA\xAF\x03\x5C\x02\xAB\x61\xEA\x48\xCE\xEB\x6F\xCD"
+	"\x48\x76\xED\x52\x0D\x60\xE1\xEC\x46\x19\x71\x9D\x8A\x5B\x8B\x80"
+	"\x7F\xAF\xB8\xE0\xA3\xDF\xC7\x37\x72\x3E\xE6\xB4\xB7\xD9\x3A\x25"
+	"\x84\xEE\x6A\x64\x9D\x06\x09\x53\x74\x88\x34\xB2\x45\x45\x98\x39"
+	"\x4E\xE0\xAA\xB1\x2D\x7B\x61\xA5\x1F\x52\x7A\x9A\x41\xF6\xC1\x68"
+	"\x7F\xE2\x53\x72\x98\xCA\x2A\x8F\x59\x46\xF8\xE5\xFD\x09\x1D\xBD"
+	"\xCB"
+	"\x02\x01\x11" /* public key - integer of 1 byte */
+	"\x02\x81\x81"  /* private key - integer of 129 bytes */
+	"\x00\xA5\xDA\xFC\x53\x41\xFA\xF2\x89\xC4\xB9\x88\xDB\x30\xC1\xCD"
+	"\xF8\x3F\x31\x25\x1E\x06\x68\xB4\x27\x84\x81\x38\x01\x57\x96\x41"
+	"\xB2\x94\x10\xB3\xC7\x99\x8D\x6B\xC4\x65\x74\x5E\x5C\x39\x26\x69"
+	"\xD6\x87\x0D\xA2\xC0\x82\xA9\x39\xE3\x7F\xDC\xB8\x2E\xC9\x3E\xDA"
+	"\xC9\x7F\xF3\xAD\x59\x50\xAC\xCF\xBC\x11\x1C\x76\xF1\xA9\x52\x94"
+	"\x44\xE5\x6A\xAF\x68\xC5\x6C\x09\x2C\xD3\x8D\xC3\xBE\xF5\xD2\x0A"
+	"\x93\x99\x26\xED\x4F\x74\xA1\x3E\xDD\xFB\xE1\xA1\xCE\xCC\x48\x94"
+	"\xAF\x94\x28\xC2\xB7\xB8\x88\x3F\xE4\x46\x3A\x4B\xC8\x5B\x1C\xB3"
+	"\xC1",
+	.key_len = 271,
+	.m = "\x54\x85\x9b\x34\x2c\x49\xea\x2a",
+	.c =
+	"\x74\x1b\x55\xac\x47\xb5\x08\x0a\x6e\x2b\x2d\xf7\x94\xb8\x8a\x95"
+	"\xed\xa3\x6b\xc9\x29\xee\xb2\x2c\x80\xc3\x39\x3b\x8c\x62\x45\x72"
+	"\xc2\x7f\x74\x81\x91\x68\x44\x48\x5a\xdc\xa0\x7e\xa7\x0b\x05\x7f"
+	"\x0e\xa0\x6c\xe5\x8f\x19\x4d\xce\x98\x47\x5f\xbd\x5f\xfe\xe5\x34"
+	"\x59\x89\xaf\xf0\xba\x44\xd7\xf1\x1a\x50\x72\xef\x5e\x4a\xb6\xb7"
+	"\x54\x34\xd1\xc4\x83\x09\xdf\x0f\x91\x5f\x7d\x91\x70\x2f\xd4\x13"
+	"\xcc\x5e\xa4\x6c\xc3\x4d\x28\xef\xda\xaf\xec\x14\x92\xfc\xa3\x75"
+	"\x13\xb4\xc1\xa1\x11\xfc\x40\x2f\x4c\x9d\xdf\x16\x76\x11\x20\x6b",
+	.m_size = 8,
+	.c_size = 128,
+	}, {
+#endif
+	.key =
+	"\x30\x82\x02\x0D" /* sequence of 525 bytes */
+	"\x02\x82\x01\x00" /* modulus - integer of 256 bytes */
+	"\xDB\x10\x1A\xC2\xA3\xF1\xDC\xFF\x13\x6B\xED\x44\xDF\xF0\x02\x6D"
+	"\x13\xC7\x88\xDA\x70\x6B\x54\xF1\xE8\x27\xDC\xC3\x0F\x99\x6A\xFA"
+	"\xC6\x67\xFF\x1D\x1E\x3C\x1D\xC1\xB5\x5F\x6C\xC0\xB2\x07\x3A\x6D"
+	"\x41\xE4\x25\x99\xAC\xFC\xD2\x0F\x02\xD3\xD1\x54\x06\x1A\x51\x77"
+	"\xBD\xB6\xBF\xEA\xA7\x5C\x06\xA9\x5D\x69\x84\x45\xD7\xF5\x05\xBA"
+	"\x47\xF0\x1B\xD7\x2B\x24\xEC\xCB\x9B\x1B\x10\x8D\x81\xA0\xBE\xB1"
+	"\x8C\x33\xE4\x36\xB8\x43\xEB\x19\x2A\x81\x8D\xDE\x81\x0A\x99\x48"
+	"\xB6\xF6\xBC\xCD\x49\x34\x3A\x8F\x26\x94\xE3\x28\x82\x1A\x7C\x8F"
+	"\x59\x9F\x45\xE8\x5D\x1A\x45\x76\x04\x56\x05\xA1\xD0\x1B\x8C\x77"
+	"\x6D\xAF\x53\xFA\x71\xE2\x67\xE0\x9A\xFE\x03\xA9\x85\xD2\xC9\xAA"
+	"\xBA\x2A\xBC\xF4\xA0\x08\xF5\x13\x98\x13\x5D\xF0\xD9\x33\x34\x2A"
+	"\x61\xC3\x89\x55\xF0\xAE\x1A\x9C\x22\xEE\x19\x05\x8D\x32\xFE\xEC"
+	"\x9C\x84\xBA\xB7\xF9\x6C\x3A\x4F\x07\xFC\x45\xEB\x12\xE5\x7B\xFD"
+	"\x55\xE6\x29\x69\xD1\xC2\xE8\xB9\x78\x59\xF6\x79\x10\xC6\x4E\xEB"
+	"\x6A\x5E\xB9\x9A\xC7\xC4\x5B\x63\xDA\xA3\x3F\x5E\x92\x7A\x81\x5E"
+	"\xD6\xB0\xE2\x62\x8F\x74\x26\xC2\x0C\xD3\x9A\x17\x47\xE6\x8E\xAB"
+	"\x02\x03\x01\x00\x01" /* public key - integer of 3 bytes */
+	"\x02\x82\x01\x00" /* private key - integer of 256 bytes */
+	"\x52\x41\xF4\xDA\x7B\xB7\x59\x55\xCA\xD4\x2F\x0F\x3A\xCB\xA4\x0D"
+	"\x93\x6C\xCC\x9D\xC1\xB2\xFB\xFD\xAE\x40\x31\xAC\x69\x52\x21\x92"
+	"\xB3\x27\xDF\xEA\xEE\x2C\x82\xBB\xF7\x40\x32\xD5\x14\xC4\x94\x12"
+	"\xEC\xB8\x1F\xCA\x59\xE3\xC1\x78\xF3\x85\xD8\x47\xA5\xD7\x02\x1A"
+	"\x65\x79\x97\x0D\x24\xF4\xF0\x67\x6E\x75\x2D\xBF\x10\x3D\xA8\x7D"
+	"\xEF\x7F\x60\xE4\xE6\x05\x82\x89\x5D\xDF\xC6\xD2\x6C\x07\x91\x33"
+	"\x98\x42\xF0\x02\x00\x25\x38\xC5\x85\x69\x8A\x7D\x2F\x95\x6C\x43"
+	"\x9A\xB8\x81\xE2\xD0\x07\x35\xAA\x05\x41\xC9\x1E\xAF\xE4\x04\x3B"
+	"\x19\xB8\x73\xA2\xAC\x4B\x1E\x66\x48\xD8\x72\x1F\xAC\xF6\xCB\xBC"
+	"\x90\x09\xCA\xEC\x0C\xDC\xF9\x2C\xD7\xEB\xAE\xA3\xA4\x47\xD7\x33"
+	"\x2F\x8A\xCA\xBC\x5E\xF0\x77\xE4\x97\x98\x97\xC7\x10\x91\x7D\x2A"
+	"\xA6\xFF\x46\x83\x97\xDE\xE9\xE2\x17\x03\x06\x14\xE2\xD7\xB1\x1D"
+	"\x77\xAF\x51\x27\x5B\x5E\x69\xB8\x81\xE6\x11\xC5\x43\x23\x81\x04"
+	"\x62\xFF\xE9\x46\xB8\xD8\x44\xDB\xA5\xCC\x31\x54\x34\xCE\x3E\x82"
+	"\xD6\xBF\x7A\x0B\x64\x21\x6D\x88\x7E\x5B\x45\x12\x1E\x63\x8D\x49"
+	"\xA7\x1D\xD9\x1E\x06\xCD\xE8\xBA\x2C\x8C\x69\x32\xEA\xBE\x60\x71",
+	.key_len = 529,
+	.m = "\x54\x85\x9b\x34\x2c\x49\xea\x2a",
+	.c =
+	"\xb2\x97\x76\xb4\xae\x3e\x38\x3c\x7e\x64\x1f\xcc\xa2\x7f\xf6\xbe"
+	"\xcf\x49\xbc\x48\xd3\x6c\x8f\x0a\x0e\xc1\x73\xbd\x7b\x55\x79\x36"
+	"\x0e\xa1\x87\x88\xb9\x2c\x90\xa6\x53\x5e\xe9\xef\xc4\xe2\x4d\xdd"
+	"\xf7\xa6\x69\x82\x3f\x56\xa4\x7b\xfb\x62\xe0\xae\xb8\xd3\x04\xb3"
+	"\xac\x5a\x15\x2a\xe3\x19\x9b\x03\x9a\x0b\x41\xda\x64\xec\x0a\x69"
+	"\xfc\xf2\x10\x92\xf3\xc1\xbf\x84\x7f\xfd\x2c\xae\xc8\xb5\xf6\x41"
+	"\x70\xc5\x47\x03\x8a\xf8\xff\x6f\x3f\xd2\x6f\x09\xb4\x22\xf3\x30"
+	"\xbe\xa9\x85\xcb\x9c\x8d\xf9\x8f\xeb\x32\x91\xa2\x25\x84\x8f\xf5"
+	"\xdc\xc7\x06\x9c\x2d\xe5\x11\x2c\x09\x09\x87\x09\xa9\xf6\x33\x73"
+	"\x90\xf1\x60\xf2\x65\xdd\x30\xa5\x66\xce\x62\x7b\xd0\xf8\x2d\x3d"
+	"\x19\x82\x77\xe3\x0a\x5f\x75\x2f\x8e\xb1\xe5\xe8\x91\x35\x1b\x3b"
+	"\x33\xb7\x66\x92\xd1\xf2\x8e\x6f\xe5\x75\x0c\xad\x36\xfb\x4e\xd0"
+	"\x66\x61\xbd\x49\xfe\xf4\x1a\xa2\x2b\x49\xfe\x03\x4c\x74\x47\x8d"
+	"\x9a\x66\xb2\x49\x46\x4d\x77\xea\x33\x4d\x6b\x3c\xb4\x49\x4a\xc6"
+	"\x7d\x3d\xb5\xb9\x56\x41\x15\x67\x0f\x94\x3c\x93\x65\x27\xe0\x21"
+	"\x5d\x59\xc3\x62\xd5\xa6\xda\x38\x26\x22\x5e\x34\x1c\x94\xaf\x98",
+	.m_size = 8,
+	.c_size = 256,
+	}, {
+	.key =
+	"\x30\x82\x01\x09" /* sequence of 265 bytes */
+	"\x02\x82\x01\x00" /* modulus - integer of 256 bytes */
+	"\xDB\x10\x1A\xC2\xA3\xF1\xDC\xFF\x13\x6B\xED\x44\xDF\xF0\x02\x6D"
+	"\x13\xC7\x88\xDA\x70\x6B\x54\xF1\xE8\x27\xDC\xC3\x0F\x99\x6A\xFA"
+	"\xC6\x67\xFF\x1D\x1E\x3C\x1D\xC1\xB5\x5F\x6C\xC0\xB2\x07\x3A\x6D"
+	"\x41\xE4\x25\x99\xAC\xFC\xD2\x0F\x02\xD3\xD1\x54\x06\x1A\x51\x77"
+	"\xBD\xB6\xBF\xEA\xA7\x5C\x06\xA9\x5D\x69\x84\x45\xD7\xF5\x05\xBA"
+	"\x47\xF0\x1B\xD7\x2B\x24\xEC\xCB\x9B\x1B\x10\x8D\x81\xA0\xBE\xB1"
+	"\x8C\x33\xE4\x36\xB8\x43\xEB\x19\x2A\x81\x8D\xDE\x81\x0A\x99\x48"
+	"\xB6\xF6\xBC\xCD\x49\x34\x3A\x8F\x26\x94\xE3\x28\x82\x1A\x7C\x8F"
+	"\x59\x9F\x45\xE8\x5D\x1A\x45\x76\x04\x56\x05\xA1\xD0\x1B\x8C\x77"
+	"\x6D\xAF\x53\xFA\x71\xE2\x67\xE0\x9A\xFE\x03\xA9\x85\xD2\xC9\xAA"
+	"\xBA\x2A\xBC\xF4\xA0\x08\xF5\x13\x98\x13\x5D\xF0\xD9\x33\x34\x2A"
+	"\x61\xC3\x89\x55\xF0\xAE\x1A\x9C\x22\xEE\x19\x05\x8D\x32\xFE\xEC"
+	"\x9C\x84\xBA\xB7\xF9\x6C\x3A\x4F\x07\xFC\x45\xEB\x12\xE5\x7B\xFD"
+	"\x55\xE6\x29\x69\xD1\xC2\xE8\xB9\x78\x59\xF6\x79\x10\xC6\x4E\xEB"
+	"\x6A\x5E\xB9\x9A\xC7\xC4\x5B\x63\xDA\xA3\x3F\x5E\x92\x7A\x81\x5E"
+	"\xD6\xB0\xE2\x62\x8F\x74\x26\xC2\x0C\xD3\x9A\x17\x47\xE6\x8E\xAB"
+	"\x02\x03\x01\x00\x01", /* public key - integer of 3 bytes */
+	.key_len = 269,
+	.m = "\x54\x85\x9b\x34\x2c\x49\xea\x2a",
+	.c =
+	"\xb2\x97\x76\xb4\xae\x3e\x38\x3c\x7e\x64\x1f\xcc\xa2\x7f\xf6\xbe"
+	"\xcf\x49\xbc\x48\xd3\x6c\x8f\x0a\x0e\xc1\x73\xbd\x7b\x55\x79\x36"
+	"\x0e\xa1\x87\x88\xb9\x2c\x90\xa6\x53\x5e\xe9\xef\xc4\xe2\x4d\xdd"
+	"\xf7\xa6\x69\x82\x3f\x56\xa4\x7b\xfb\x62\xe0\xae\xb8\xd3\x04\xb3"
+	"\xac\x5a\x15\x2a\xe3\x19\x9b\x03\x9a\x0b\x41\xda\x64\xec\x0a\x69"
+	"\xfc\xf2\x10\x92\xf3\xc1\xbf\x84\x7f\xfd\x2c\xae\xc8\xb5\xf6\x41"
+	"\x70\xc5\x47\x03\x8a\xf8\xff\x6f\x3f\xd2\x6f\x09\xb4\x22\xf3\x30"
+	"\xbe\xa9\x85\xcb\x9c\x8d\xf9\x8f\xeb\x32\x91\xa2\x25\x84\x8f\xf5"
+	"\xdc\xc7\x06\x9c\x2d\xe5\x11\x2c\x09\x09\x87\x09\xa9\xf6\x33\x73"
+	"\x90\xf1\x60\xf2\x65\xdd\x30\xa5\x66\xce\x62\x7b\xd0\xf8\x2d\x3d"
+	"\x19\x82\x77\xe3\x0a\x5f\x75\x2f\x8e\xb1\xe5\xe8\x91\x35\x1b\x3b"
+	"\x33\xb7\x66\x92\xd1\xf2\x8e\x6f\xe5\x75\x0c\xad\x36\xfb\x4e\xd0"
+	"\x66\x61\xbd\x49\xfe\xf4\x1a\xa2\x2b\x49\xfe\x03\x4c\x74\x47\x8d"
+	"\x9a\x66\xb2\x49\x46\x4d\x77\xea\x33\x4d\x6b\x3c\xb4\x49\x4a\xc6"
+	"\x7d\x3d\xb5\xb9\x56\x41\x15\x67\x0f\x94\x3c\x93\x65\x27\xe0\x21"
+	"\x5d\x59\xc3\x62\xd5\xa6\xda\x38\x26\x22\x5e\x34\x1c\x94\xaf\x98",
+	.m_size = 8,
+	.c_size = 256,
+	.public_key_vec = true,
+	}
+};
+
+/*
  * MD4 test vectors from RFC1320
  */
 #define MD4_TEST_VECTORS	7
@@ -1822,7 +2027,7 @@ static struct hash_testvec tgr128_tv_template[] = {
 	},
 };
 
-#define GHASH_TEST_VECTORS 5
+#define GHASH_TEST_VECTORS 6
 
 static struct hash_testvec ghash_tv_template[] =
 {
@@ -1875,6 +2080,63 @@ static struct hash_testvec ghash_tv_template[] =
 		.psize	= 20,
 		.digest	= "\xf8\x94\x87\x2a\x4b\x63\x99\x28"
 			  "\x23\xf7\x93\xf7\x19\xf5\x96\xd9",
+	}, {
+		.key	= "\x0a\x1b\x2c\x3d\x4e\x5f\x64\x71"
+			"\x82\x93\xa4\xb5\xc6\xd7\xe8\xf9",
+		.ksize	= 16,
+		.plaintext = "\x56\x6f\x72\x20\x6c\x61\x75\x74"
+			"\x65\x72\x20\x4c\x61\x75\x73\x63"
+			"\x68\x65\x6e\x20\x75\x6e\x64\x20"
+			"\x53\x74\x61\x75\x6e\x65\x6e\x20"
+			"\x73\x65\x69\x20\x73\x74\x69\x6c"
+			"\x6c\x2c\x0a\x64\x75\x20\x6d\x65"
+			"\x69\x6e\x20\x74\x69\x65\x66\x74"
+			"\x69\x65\x66\x65\x73\x20\x4c\x65"
+			"\x62\x65\x6e\x3b\x0a\x64\x61\x73"
+			"\x73\x20\x64\x75\x20\x77\x65\x69"
+			"\xc3\x9f\x74\x20\x77\x61\x73\x20"
+			"\x64\x65\x72\x20\x57\x69\x6e\x64"
+			"\x20\x64\x69\x72\x20\x77\x69\x6c"
+			"\x6c\x2c\x0a\x65\x68\x20\x6e\x6f"
+			"\x63\x68\x20\x64\x69\x65\x20\x42"
+			"\x69\x72\x6b\x65\x6e\x20\x62\x65"
+			"\x62\x65\x6e\x2e\x0a\x0a\x55\x6e"
+			"\x64\x20\x77\x65\x6e\x6e\x20\x64"
+			"\x69\x72\x20\x65\x69\x6e\x6d\x61"
+			"\x6c\x20\x64\x61\x73\x20\x53\x63"
+			"\x68\x77\x65\x69\x67\x65\x6e\x20"
+			"\x73\x70\x72\x61\x63\x68\x2c\x0a"
+			"\x6c\x61\x73\x73\x20\x64\x65\x69"
+			"\x6e\x65\x20\x53\x69\x6e\x6e\x65"
+			"\x20\x62\x65\x73\x69\x65\x67\x65"
+			"\x6e\x2e\x0a\x4a\x65\x64\x65\x6d"
+			"\x20\x48\x61\x75\x63\x68\x65\x20"
+			"\x67\x69\x62\x74\x20\x64\x69\x63"
+			"\x68\x2c\x20\x67\x69\x62\x20\x6e"
+			"\x61\x63\x68\x2c\x0a\x65\x72\x20"
+			"\x77\x69\x72\x64\x20\x64\x69\x63"
+			"\x68\x20\x6c\x69\x65\x62\x65\x6e"
+			"\x20\x75\x6e\x64\x20\x77\x69\x65"
+			"\x67\x65\x6e\x2e\x0a\x0a\x55\x6e"
+			"\x64\x20\x64\x61\x6e\x6e\x20\x6d"
+			"\x65\x69\x6e\x65\x20\x53\x65\x65"
+			"\x6c\x65\x20\x73\x65\x69\x74\x20"
+			"\x77\x65\x69\x74\x2c\x20\x73\x65"
+			"\x69\x20\x77\x65\x69\x74\x2c\x0a"
+			"\x64\x61\x73\x73\x20\x64\x69\x72"
+			"\x20\x64\x61\x73\x20\x4c\x65\x62"
+			"\x65\x6e\x20\x67\x65\x6c\x69\x6e"
+			"\x67\x65\x2c\x0a\x62\x72\x65\x69"
+			"\x74\x65\x20\x64\x69\x63\x68\x20"
+			"\x77\x69\x65\x20\x65\x69\x6e\x20"
+			"\x46\x65\x69\x65\x72\x6b\x6c\x65"
+			"\x69\x64\x0a\xc3\xbc\x62\x65\x72"
+			"\x20\x64\x69\x65\x20\x73\x69\x6e"
+			"\x6e\x65\x6e\x64\x65\x6e\x20\x44"
+			"\x69\x6e\x67\x65\x2e\x2e\x2e\x0a",
+		.psize	= 400,
+		.digest = "\xad\xb1\xc1\xe9\x56\x70\x31\x1d"
+			"\xbb\x5b\xdf\x5e\x70\x72\x1a\x57",
 	},
 };
 
@@ -2969,6 +3231,254 @@ static struct hash_testvec hmac_sha512_tv_template[] = {
 };
 
 /*
+ * Poly1305 test vectors from RFC7539 A.3.
+ */
+
+#define POLY1305_TEST_VECTORS	11
+
+static struct hash_testvec poly1305_tv_template[] = {
+	{ /* Test Vector #1 */
+		.plaintext	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.psize		= 96,
+		.digest		= "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00",
+	}, { /* Test Vector #2 */
+		.plaintext	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x36\xe5\xf6\xb5\xc5\xe0\x60\x70"
+				  "\xf0\xef\xca\x96\x22\x7a\x86\x3e"
+				  "\x41\x6e\x79\x20\x73\x75\x62\x6d"
+				  "\x69\x73\x73\x69\x6f\x6e\x20\x74"
+				  "\x6f\x20\x74\x68\x65\x20\x49\x45"
+				  "\x54\x46\x20\x69\x6e\x74\x65\x6e"
+				  "\x64\x65\x64\x20\x62\x79\x20\x74"
+				  "\x68\x65\x20\x43\x6f\x6e\x74\x72"
+				  "\x69\x62\x75\x74\x6f\x72\x20\x66"
+				  "\x6f\x72\x20\x70\x75\x62\x6c\x69"
+				  "\x63\x61\x74\x69\x6f\x6e\x20\x61"
+				  "\x73\x20\x61\x6c\x6c\x20\x6f\x72"
+				  "\x20\x70\x61\x72\x74\x20\x6f\x66"
+				  "\x20\x61\x6e\x20\x49\x45\x54\x46"
+				  "\x20\x49\x6e\x74\x65\x72\x6e\x65"
+				  "\x74\x2d\x44\x72\x61\x66\x74\x20"
+				  "\x6f\x72\x20\x52\x46\x43\x20\x61"
+				  "\x6e\x64\x20\x61\x6e\x79\x20\x73"
+				  "\x74\x61\x74\x65\x6d\x65\x6e\x74"
+				  "\x20\x6d\x61\x64\x65\x20\x77\x69"
+				  "\x74\x68\x69\x6e\x20\x74\x68\x65"
+				  "\x20\x63\x6f\x6e\x74\x65\x78\x74"
+				  "\x20\x6f\x66\x20\x61\x6e\x20\x49"
+				  "\x45\x54\x46\x20\x61\x63\x74\x69"
+				  "\x76\x69\x74\x79\x20\x69\x73\x20"
+				  "\x63\x6f\x6e\x73\x69\x64\x65\x72"
+				  "\x65\x64\x20\x61\x6e\x20\x22\x49"
+				  "\x45\x54\x46\x20\x43\x6f\x6e\x74"
+				  "\x72\x69\x62\x75\x74\x69\x6f\x6e"
+				  "\x22\x2e\x20\x53\x75\x63\x68\x20"
+				  "\x73\x74\x61\x74\x65\x6d\x65\x6e"
+				  "\x74\x73\x20\x69\x6e\x63\x6c\x75"
+				  "\x64\x65\x20\x6f\x72\x61\x6c\x20"
+				  "\x73\x74\x61\x74\x65\x6d\x65\x6e"
+				  "\x74\x73\x20\x69\x6e\x20\x49\x45"
+				  "\x54\x46\x20\x73\x65\x73\x73\x69"
+				  "\x6f\x6e\x73\x2c\x20\x61\x73\x20"
+				  "\x77\x65\x6c\x6c\x20\x61\x73\x20"
+				  "\x77\x72\x69\x74\x74\x65\x6e\x20"
+				  "\x61\x6e\x64\x20\x65\x6c\x65\x63"
+				  "\x74\x72\x6f\x6e\x69\x63\x20\x63"
+				  "\x6f\x6d\x6d\x75\x6e\x69\x63\x61"
+				  "\x74\x69\x6f\x6e\x73\x20\x6d\x61"
+				  "\x64\x65\x20\x61\x74\x20\x61\x6e"
+				  "\x79\x20\x74\x69\x6d\x65\x20\x6f"
+				  "\x72\x20\x70\x6c\x61\x63\x65\x2c"
+				  "\x20\x77\x68\x69\x63\x68\x20\x61"
+				  "\x72\x65\x20\x61\x64\x64\x72\x65"
+				  "\x73\x73\x65\x64\x20\x74\x6f",
+		.psize		= 407,
+		.digest		= "\x36\xe5\xf6\xb5\xc5\xe0\x60\x70"
+				  "\xf0\xef\xca\x96\x22\x7a\x86\x3e",
+	}, { /* Test Vector #3 */
+		.plaintext	= "\x36\xe5\xf6\xb5\xc5\xe0\x60\x70"
+				  "\xf0\xef\xca\x96\x22\x7a\x86\x3e"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x41\x6e\x79\x20\x73\x75\x62\x6d"
+				  "\x69\x73\x73\x69\x6f\x6e\x20\x74"
+				  "\x6f\x20\x74\x68\x65\x20\x49\x45"
+				  "\x54\x46\x20\x69\x6e\x74\x65\x6e"
+				  "\x64\x65\x64\x20\x62\x79\x20\x74"
+				  "\x68\x65\x20\x43\x6f\x6e\x74\x72"
+				  "\x69\x62\x75\x74\x6f\x72\x20\x66"
+				  "\x6f\x72\x20\x70\x75\x62\x6c\x69"
+				  "\x63\x61\x74\x69\x6f\x6e\x20\x61"
+				  "\x73\x20\x61\x6c\x6c\x20\x6f\x72"
+				  "\x20\x70\x61\x72\x74\x20\x6f\x66"
+				  "\x20\x61\x6e\x20\x49\x45\x54\x46"
+				  "\x20\x49\x6e\x74\x65\x72\x6e\x65"
+				  "\x74\x2d\x44\x72\x61\x66\x74\x20"
+				  "\x6f\x72\x20\x52\x46\x43\x20\x61"
+				  "\x6e\x64\x20\x61\x6e\x79\x20\x73"
+				  "\x74\x61\x74\x65\x6d\x65\x6e\x74"
+				  "\x20\x6d\x61\x64\x65\x20\x77\x69"
+				  "\x74\x68\x69\x6e\x20\x74\x68\x65"
+				  "\x20\x63\x6f\x6e\x74\x65\x78\x74"
+				  "\x20\x6f\x66\x20\x61\x6e\x20\x49"
+				  "\x45\x54\x46\x20\x61\x63\x74\x69"
+				  "\x76\x69\x74\x79\x20\x69\x73\x20"
+				  "\x63\x6f\x6e\x73\x69\x64\x65\x72"
+				  "\x65\x64\x20\x61\x6e\x20\x22\x49"
+				  "\x45\x54\x46\x20\x43\x6f\x6e\x74"
+				  "\x72\x69\x62\x75\x74\x69\x6f\x6e"
+				  "\x22\x2e\x20\x53\x75\x63\x68\x20"
+				  "\x73\x74\x61\x74\x65\x6d\x65\x6e"
+				  "\x74\x73\x20\x69\x6e\x63\x6c\x75"
+				  "\x64\x65\x20\x6f\x72\x61\x6c\x20"
+				  "\x73\x74\x61\x74\x65\x6d\x65\x6e"
+				  "\x74\x73\x20\x69\x6e\x20\x49\x45"
+				  "\x54\x46\x20\x73\x65\x73\x73\x69"
+				  "\x6f\x6e\x73\x2c\x20\x61\x73\x20"
+				  "\x77\x65\x6c\x6c\x20\x61\x73\x20"
+				  "\x77\x72\x69\x74\x74\x65\x6e\x20"
+				  "\x61\x6e\x64\x20\x65\x6c\x65\x63"
+				  "\x74\x72\x6f\x6e\x69\x63\x20\x63"
+				  "\x6f\x6d\x6d\x75\x6e\x69\x63\x61"
+				  "\x74\x69\x6f\x6e\x73\x20\x6d\x61"
+				  "\x64\x65\x20\x61\x74\x20\x61\x6e"
+				  "\x79\x20\x74\x69\x6d\x65\x20\x6f"
+				  "\x72\x20\x70\x6c\x61\x63\x65\x2c"
+				  "\x20\x77\x68\x69\x63\x68\x20\x61"
+				  "\x72\x65\x20\x61\x64\x64\x72\x65"
+				  "\x73\x73\x65\x64\x20\x74\x6f",
+		.psize		= 407,
+		.digest		= "\xf3\x47\x7e\x7c\xd9\x54\x17\xaf"
+				  "\x89\xa6\xb8\x79\x4c\x31\x0c\xf0",
+	}, { /* Test Vector #4 */
+		.plaintext	= "\x1c\x92\x40\xa5\xeb\x55\xd3\x8a"
+				  "\xf3\x33\x88\x86\x04\xf6\xb5\xf0"
+				  "\x47\x39\x17\xc1\x40\x2b\x80\x09"
+				  "\x9d\xca\x5c\xbc\x20\x70\x75\xc0"
+				  "\x27\x54\x77\x61\x73\x20\x62\x72"
+				  "\x69\x6c\x6c\x69\x67\x2c\x20\x61"
+				  "\x6e\x64\x20\x74\x68\x65\x20\x73"
+				  "\x6c\x69\x74\x68\x79\x20\x74\x6f"
+				  "\x76\x65\x73\x0a\x44\x69\x64\x20"
+				  "\x67\x79\x72\x65\x20\x61\x6e\x64"
+				  "\x20\x67\x69\x6d\x62\x6c\x65\x20"
+				  "\x69\x6e\x20\x74\x68\x65\x20\x77"
+				  "\x61\x62\x65\x3a\x0a\x41\x6c\x6c"
+				  "\x20\x6d\x69\x6d\x73\x79\x20\x77"
+				  "\x65\x72\x65\x20\x74\x68\x65\x20"
+				  "\x62\x6f\x72\x6f\x67\x6f\x76\x65"
+				  "\x73\x2c\x0a\x41\x6e\x64\x20\x74"
+				  "\x68\x65\x20\x6d\x6f\x6d\x65\x20"
+				  "\x72\x61\x74\x68\x73\x20\x6f\x75"
+				  "\x74\x67\x72\x61\x62\x65\x2e",
+		.psize		= 159,
+		.digest		= "\x45\x41\x66\x9a\x7e\xaa\xee\x61"
+				  "\xe7\x08\xdc\x7c\xbc\xc5\xeb\x62",
+	}, { /* Test Vector #5 */
+		.plaintext	= "\x02\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff",
+		.psize		= 48,
+		.digest		= "\x03\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00",
+	}, { /* Test Vector #6 */
+		.plaintext	= "\x02\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\x02\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.psize		= 48,
+		.digest		= "\x03\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00",
+	}, { /* Test Vector #7 */
+		.plaintext	= "\x01\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\xf0\xff\xff\xff\xff\xff\xff\xff"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\x11\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.psize		= 80,
+		.digest		= "\x05\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00",
+	}, { /* Test Vector #8 */
+		.plaintext	= "\x01\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\xfb\xfe\xfe\xfe\xfe\xfe\xfe\xfe"
+				  "\xfe\xfe\xfe\xfe\xfe\xfe\xfe\xfe"
+				  "\x01\x01\x01\x01\x01\x01\x01\x01"
+				  "\x01\x01\x01\x01\x01\x01\x01\x01",
+		.psize		= 80,
+		.digest		= "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00",
+	}, { /* Test Vector #9 */
+		.plaintext	= "\x02\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\xfd\xff\xff\xff\xff\xff\xff\xff"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff",
+		.psize		= 48,
+		.digest		= "\xfa\xff\xff\xff\xff\xff\xff\xff"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff",
+	}, { /* Test Vector #10 */
+		.plaintext	= "\x01\x00\x00\x00\x00\x00\x00\x00"
+				  "\x04\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\xe3\x35\x94\xd7\x50\x5e\x43\xb9"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x33\x94\xd7\x50\x5e\x43\x79\xcd"
+				  "\x01\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x01\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.psize		= 96,
+		.digest		= "\x14\x00\x00\x00\x00\x00\x00\x00"
+				  "\x55\x00\x00\x00\x00\x00\x00\x00",
+	}, { /* Test Vector #11 */
+		.plaintext	= "\x01\x00\x00\x00\x00\x00\x00\x00"
+				  "\x04\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\xe3\x35\x94\xd7\x50\x5e\x43\xb9"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x33\x94\xd7\x50\x5e\x43\x79\xcd"
+				  "\x01\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.psize		= 80,
+		.digest		= "\x13\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00",
+	},
+};
+
+/*
  * DES test vectors.
  */
 #define DES_ENC_TEST_VECTORS		11
@@ -3018,7 +3528,7 @@ static struct cipher_testvec des_enc_tv_template[] = {
 			  "\xb4\x99\x26\xf7\x1f\xe1\xd4\x90",
 		.rlen	= 24,
 	}, { /* Weak key */
-		.fail	= 1,
+		.fail	= true,
 		.wk	= 1,
 		.key	= "\x01\x01\x01\x01\x01\x01\x01\x01",
 		.klen	= 8,
@@ -13629,8 +14139,8 @@ static struct cipher_testvec cast6_xts_dec_tv_template[] = {
 #define AES_CTR_3686_DEC_TEST_VECTORS 6
 #define AES_GCM_ENC_TEST_VECTORS 9
 #define AES_GCM_DEC_TEST_VECTORS 8
-#define AES_GCM_4106_ENC_TEST_VECTORS 7
-#define AES_GCM_4106_DEC_TEST_VECTORS 7
+#define AES_GCM_4106_ENC_TEST_VECTORS 23
+#define AES_GCM_4106_DEC_TEST_VECTORS 23
 #define AES_GCM_4543_ENC_TEST_VECTORS 1
 #define AES_GCM_4543_DEC_TEST_VECTORS 2
 #define AES_CCM_ENC_TEST_VECTORS 8
@@ -19789,6 +20299,428 @@ static struct aead_testvec aes_gcm_rfc4106_enc_tv_template[] = {
 			  "\x37\x08\x1C\xCF\xBA\x5D\x71\x46"
 			  "\x80\x72\xB0\x4C\x82\x0D\x60\x3C",
 		.rlen	= 208,
+	}, { /* From draft-mcgrew-gcm-test-01 */
+		.key	= "\x4C\x80\xCD\xEF\xBB\x5D\x10\xDA"
+			  "\x90\x6A\xC7\x3C\x36\x13\xA6\x34"
+			  "\x2E\x44\x3B\x68",
+		.klen	= 20,
+		.iv	= "\x49\x56\xED\x7E\x3B\x24\x4C\xFE",
+		.input	= "\x45\x00\x00\x48\x69\x9A\x00\x00"
+			  "\x80\x11\x4D\xB7\xC0\xA8\x01\x02"
+			  "\xC0\xA8\x01\x01\x0A\x9B\xF1\x56"
+			  "\x38\xD3\x01\x00\x00\x01\x00\x00"
+			  "\x00\x00\x00\x00\x04\x5F\x73\x69"
+			  "\x70\x04\x5F\x75\x64\x70\x03\x73"
+			  "\x69\x70\x09\x63\x79\x62\x65\x72"
+			  "\x63\x69\x74\x79\x02\x64\x6B\x00"
+			  "\x00\x21\x00\x01\x01\x02\x02\x01",
+		.ilen	= 72,
+		.assoc	= "\x00\x00\x43\x21\x87\x65\x43\x21"
+			  "\x00\x00\x00\x00",
+		.alen	= 12,
+		.result	= "\xFE\xCF\x53\x7E\x72\x9D\x5B\x07"
+			  "\xDC\x30\xDF\x52\x8D\xD2\x2B\x76"
+			  "\x8D\x1B\x98\x73\x66\x96\xA6\xFD"
+			  "\x34\x85\x09\xFA\x13\xCE\xAC\x34"
+			  "\xCF\xA2\x43\x6F\x14\xA3\xF3\xCF"
+			  "\x65\x92\x5B\xF1\xF4\xA1\x3C\x5D"
+			  "\x15\xB2\x1E\x18\x84\xF5\xFF\x62"
+			  "\x47\xAE\xAB\xB7\x86\xB9\x3B\xCE"
+			  "\x61\xBC\x17\xD7\x68\xFD\x97\x32"
+			  "\x45\x90\x18\x14\x8F\x6C\xBE\x72"
+			  "\x2F\xD0\x47\x96\x56\x2D\xFD\xB4",
+		.rlen	= 88,
+	}, {
+		.key	= "\xFE\xFF\xE9\x92\x86\x65\x73\x1C"
+			  "\x6D\x6A\x8F\x94\x67\x30\x83\x08"
+			  "\xCA\xFE\xBA\xBE",
+		.klen	= 20,
+		.iv	= "\xFA\xCE\xDB\xAD\xDE\xCA\xF8\x88",
+		.input	= "\x45\x00\x00\x3E\x69\x8F\x00\x00"
+			  "\x80\x11\x4D\xCC\xC0\xA8\x01\x02"
+			  "\xC0\xA8\x01\x01\x0A\x98\x00\x35"
+			  "\x00\x2A\x23\x43\xB2\xD0\x01\x00"
+			  "\x00\x01\x00\x00\x00\x00\x00\x00"
+			  "\x03\x73\x69\x70\x09\x63\x79\x62"
+			  "\x65\x72\x63\x69\x74\x79\x02\x64"
+			  "\x6B\x00\x00\x01\x00\x01\x00\x01",
+		.ilen	= 64,
+		.assoc	= "\x00\x00\xA5\xF8\x00\x00\x00\x0A",
+		.alen	= 8,
+		.result	= "\xDE\xB2\x2C\xD9\xB0\x7C\x72\xC1"
+			  "\x6E\x3A\x65\xBE\xEB\x8D\xF3\x04"
+			  "\xA5\xA5\x89\x7D\x33\xAE\x53\x0F"
+			  "\x1B\xA7\x6D\x5D\x11\x4D\x2A\x5C"
+			  "\x3D\xE8\x18\x27\xC1\x0E\x9A\x4F"
+			  "\x51\x33\x0D\x0E\xEC\x41\x66\x42"
+			  "\xCF\xBB\x85\xA5\xB4\x7E\x48\xA4"
+			  "\xEC\x3B\x9B\xA9\x5D\x91\x8B\xD1"
+			  "\x83\xB7\x0D\x3A\xA8\xBC\x6E\xE4"
+			  "\xC3\x09\xE9\xD8\x5A\x41\xAD\x4A",
+		.rlen	= 80,
+	}, {
+		.key	= "\xAB\xBC\xCD\xDE\xF0\x01\x12\x23"
+			  "\x34\x45\x56\x67\x78\x89\x9A\xAB"
+			  "\xAB\xBC\xCD\xDE\xF0\x01\x12\x23"
+			  "\x34\x45\x56\x67\x78\x89\x9A\xAB"
+			  "\x11\x22\x33\x44",
+		.klen	= 36,
+		.iv	= "\x01\x02\x03\x04\x05\x06\x07\x08",
+		.input	= "\x45\x00\x00\x30\x69\xA6\x40\x00"
+			  "\x80\x06\x26\x90\xC0\xA8\x01\x02"
+			  "\x93\x89\x15\x5E\x0A\x9E\x00\x8B"
+			  "\x2D\xC5\x7E\xE0\x00\x00\x00\x00"
+			  "\x70\x02\x40\x00\x20\xBF\x00\x00"
+			  "\x02\x04\x05\xB4\x01\x01\x04\x02"
+			  "\x01\x02\x02\x01",
+		.ilen	= 52,
+		.assoc	= "\x4A\x2C\xBF\xE3\x00\x00\x00\x02",
+		.alen	= 8,
+		.result	= "\xFF\x42\x5C\x9B\x72\x45\x99\xDF"
+			  "\x7A\x3B\xCD\x51\x01\x94\xE0\x0D"
+			  "\x6A\x78\x10\x7F\x1B\x0B\x1C\xBF"
+			  "\x06\xEF\xAE\x9D\x65\xA5\xD7\x63"
+			  "\x74\x8A\x63\x79\x85\x77\x1D\x34"
+			  "\x7F\x05\x45\x65\x9F\x14\xE9\x9D"
+			  "\xEF\x84\x2D\x8E\xB3\x35\xF4\xEE"
+			  "\xCF\xDB\xF8\x31\x82\x4B\x4C\x49"
+			  "\x15\x95\x6C\x96",
+		.rlen	= 68,
+	}, {
+		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00",
+		.klen	= 20,
+		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.input	= "\x45\x00\x00\x3C\x99\xC5\x00\x00"
+			  "\x80\x01\xCB\x7A\x40\x67\x93\x18"
+			  "\x01\x01\x01\x01\x08\x00\x07\x5C"
+			  "\x02\x00\x44\x00\x61\x62\x63\x64"
+			  "\x65\x66\x67\x68\x69\x6A\x6B\x6C"
+			  "\x6D\x6E\x6F\x70\x71\x72\x73\x74"
+			  "\x75\x76\x77\x61\x62\x63\x64\x65"
+			  "\x66\x67\x68\x69\x01\x02\x02\x01",
+		.ilen	= 64,
+		.assoc	= "\x00\x00\x00\x00\x00\x00\x00\x01",
+		.alen	= 8,
+		.result	= "\x46\x88\xDA\xF2\xF9\x73\xA3\x92"
+			  "\x73\x29\x09\xC3\x31\xD5\x6D\x60"
+			  "\xF6\x94\xAB\xAA\x41\x4B\x5E\x7F"
+			  "\xF5\xFD\xCD\xFF\xF5\xE9\xA2\x84"
+			  "\x45\x64\x76\x49\x27\x19\xFF\xB6"
+			  "\x4D\xE7\xD9\xDC\xA1\xE1\xD8\x94"
+			  "\xBC\x3B\xD5\x78\x73\xED\x4D\x18"
+			  "\x1D\x19\xD4\xD5\xC8\xC1\x8A\xF3"
+			  "\xF8\x21\xD4\x96\xEE\xB0\x96\xE9"
+			  "\x8A\xD2\xB6\x9E\x47\x99\xC7\x1D",
+		.rlen	= 80,
+	}, {
+		.key	= "\x3D\xE0\x98\x74\xB3\x88\xE6\x49"
+			  "\x19\x88\xD0\xC3\x60\x7E\xAE\x1F"
+			  "\x57\x69\x0E\x43",
+		.klen	= 20,
+		.iv	= "\x4E\x28\x00\x00\xA2\xFC\xA1\xA3",
+		.input	= "\x45\x00\x00\x3C\x99\xC3\x00\x00"
+			  "\x80\x01\xCB\x7C\x40\x67\x93\x18"
+			  "\x01\x01\x01\x01\x08\x00\x08\x5C"
+			  "\x02\x00\x43\x00\x61\x62\x63\x64"
+			  "\x65\x66\x67\x68\x69\x6A\x6B\x6C"
+			  "\x6D\x6E\x6F\x70\x71\x72\x73\x74"
+			  "\x75\x76\x77\x61\x62\x63\x64\x65"
+			  "\x66\x67\x68\x69\x01\x02\x02\x01",
+		.ilen	= 64,
+		.assoc	= "\x42\xF6\x7E\x3F\x10\x10\x10\x10"
+			  "\x10\x10\x10\x10",
+		.alen	= 12,
+		.result	= "\xFB\xA2\xCA\xA4\x85\x3C\xF9\xF0"
+			  "\xF2\x2C\xB1\x0D\x86\xDD\x83\xB0"
+			  "\xFE\xC7\x56\x91\xCF\x1A\x04\xB0"
+			  "\x0D\x11\x38\xEC\x9C\x35\x79\x17"
+			  "\x65\xAC\xBD\x87\x01\xAD\x79\x84"
+			  "\x5B\xF9\xFE\x3F\xBA\x48\x7B\xC9"
+			  "\x17\x55\xE6\x66\x2B\x4C\x8D\x0D"
+			  "\x1F\x5E\x22\x73\x95\x30\x32\x0A"
+			  "\xE0\xD7\x31\xCC\x97\x8E\xCA\xFA"
+			  "\xEA\xE8\x8F\x00\xE8\x0D\x6E\x48",
+		.rlen	= 80,
+	}, {
+		.key	= "\x3D\xE0\x98\x74\xB3\x88\xE6\x49"
+			  "\x19\x88\xD0\xC3\x60\x7E\xAE\x1F"
+			  "\x57\x69\x0E\x43",
+		.klen	= 20,
+		.iv	= "\x4E\x28\x00\x00\xA2\xFC\xA1\xA3",
+		.input	= "\x45\x00\x00\x1C\x42\xA2\x00\x00"
+			  "\x80\x01\x44\x1F\x40\x67\x93\xB6"
+			  "\xE0\x00\x00\x02\x0A\x00\xF5\xFF"
+			  "\x01\x02\x02\x01",
+		.ilen	= 28,
+		.assoc	= "\x42\xF6\x7E\x3F\x10\x10\x10\x10"
+			  "\x10\x10\x10\x10",
+		.alen	= 12,
+		.result	= "\xFB\xA2\xCA\x84\x5E\x5D\xF9\xF0"
+			  "\xF2\x2C\x3E\x6E\x86\xDD\x83\x1E"
+			  "\x1F\xC6\x57\x92\xCD\x1A\xF9\x13"
+			  "\x0E\x13\x79\xED\x36\x9F\x07\x1F"
+			  "\x35\xE0\x34\xBE\x95\xF1\x12\xE4"
+			  "\xE7\xD0\x5D\x35",
+		.rlen	= 44,
+	}, {
+		.key	= "\xFE\xFF\xE9\x92\x86\x65\x73\x1C"
+			  "\x6D\x6A\x8F\x94\x67\x30\x83\x08"
+			  "\xFE\xFF\xE9\x92\x86\x65\x73\x1C"
+			  "\xCA\xFE\xBA\xBE",
+		.klen	= 28,
+		.iv	= "\xFA\xCE\xDB\xAD\xDE\xCA\xF8\x88",
+		.input	= "\x45\x00\x00\x28\xA4\xAD\x40\x00"
+			  "\x40\x06\x78\x80\x0A\x01\x03\x8F"
+			  "\x0A\x01\x06\x12\x80\x23\x06\xB8"
+			  "\xCB\x71\x26\x02\xDD\x6B\xB0\x3E"
+			  "\x50\x10\x16\xD0\x75\x68\x00\x01",
+		.ilen	= 40,
+		.assoc	= "\x00\x00\xA5\xF8\x00\x00\x00\x0A",
+		.alen	= 8,
+		.result	= "\xA5\xB1\xF8\x06\x60\x29\xAE\xA4"
+			  "\x0E\x59\x8B\x81\x22\xDE\x02\x42"
+			  "\x09\x38\xB3\xAB\x33\xF8\x28\xE6"
+			  "\x87\xB8\x85\x8B\x5B\xFB\xDB\xD0"
+			  "\x31\x5B\x27\x45\x21\x44\xCC\x77"
+			  "\x95\x45\x7B\x96\x52\x03\x7F\x53"
+			  "\x18\x02\x7B\x5B\x4C\xD7\xA6\x36",
+		.rlen	= 56,
+	}, {
+		.key	= "\xAB\xBC\xCD\xDE\xF0\x01\x12\x23"
+			  "\x34\x45\x56\x67\x78\x89\x9A\xAB"
+			  "\xDE\xCA\xF8\x88",
+		.klen	= 20,
+		.iv	= "\xCA\xFE\xDE\xBA\xCE\xFA\xCE\x74",
+		.input	= "\x45\x00\x00\x49\x33\xBA\x00\x00"
+			  "\x7F\x11\x91\x06\xC3\xFB\x1D\x10"
+			  "\xC2\xB1\xD3\x26\xC0\x28\x31\xCE"
+			  "\x00\x35\xDD\x7B\x80\x03\x02\xD5"
+			  "\x00\x00\x4E\x20\x00\x1E\x8C\x18"
+			  "\xD7\x5B\x81\xDC\x91\xBA\xA0\x47"
+			  "\x6B\x91\xB9\x24\xB2\x80\x38\x9D"
+			  "\x92\xC9\x63\xBA\xC0\x46\xEC\x95"
+			  "\x9B\x62\x66\xC0\x47\x22\xB1\x49"
+			  "\x23\x01\x01\x01",
+		.ilen	= 76,
+		.assoc	= "\x00\x00\x01\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x01",
+		.alen	= 12,
+		.result	= "\x18\xA6\xFD\x42\xF7\x2C\xBF\x4A"
+			  "\xB2\xA2\xEA\x90\x1F\x73\xD8\x14"
+			  "\xE3\xE7\xF2\x43\xD9\x54\x12\xE1"
+			  "\xC3\x49\xC1\xD2\xFB\xEC\x16\x8F"
+			  "\x91\x90\xFE\xEB\xAF\x2C\xB0\x19"
+			  "\x84\xE6\x58\x63\x96\x5D\x74\x72"
+			  "\xB7\x9D\xA3\x45\xE0\xE7\x80\x19"
+			  "\x1F\x0D\x2F\x0E\x0F\x49\x6C\x22"
+			  "\x6F\x21\x27\xB2\x7D\xB3\x57\x24"
+			  "\xE7\x84\x5D\x68\x65\x1F\x57\xE6"
+			  "\x5F\x35\x4F\x75\xFF\x17\x01\x57"
+			  "\x69\x62\x34\x36",
+		.rlen	= 92,
+	}, {
+		.key	= "\xAB\xBC\xCD\xDE\xF0\x01\x12\x23"
+			  "\x34\x45\x56\x67\x78\x89\x9A\xAB"
+			  "\xAB\xBC\xCD\xDE\xF0\x01\x12\x23"
+			  "\x34\x45\x56\x67\x78\x89\x9A\xAB"
+			  "\x73\x61\x6C\x74",
+		.klen	= 36,
+		.iv	= "\x61\x6E\x64\x01\x69\x76\x65\x63",
+		.input	= "\x45\x08\x00\x28\x73\x2C\x00\x00"
+			  "\x40\x06\xE9\xF9\x0A\x01\x06\x12"
+			  "\x0A\x01\x03\x8F\x06\xB8\x80\x23"
+			  "\xDD\x6B\xAF\xBE\xCB\x71\x26\x02"
+			  "\x50\x10\x1F\x64\x6D\x54\x00\x01",
+		.ilen	= 40,
+		.assoc	= "\x17\x40\x5E\x67\x15\x6F\x31\x26"
+			  "\xDD\x0D\xB9\x9B",
+		.alen	= 12,
+		.result	= "\xF2\xD6\x9E\xCD\xBD\x5A\x0D\x5B"
+			  "\x8D\x5E\xF3\x8B\xAD\x4D\xA5\x8D"
+			  "\x1F\x27\x8F\xDE\x98\xEF\x67\x54"
+			  "\x9D\x52\x4A\x30\x18\xD9\xA5\x7F"
+			  "\xF4\xD3\xA3\x1C\xE6\x73\x11\x9E"
+			  "\x45\x16\x26\xC2\x41\x57\x71\xE3"
+			  "\xB7\xEE\xBC\xA6\x14\xC8\x9B\x35",
+		.rlen	= 56,
+	}, {
+		.key	= "\x3D\xE0\x98\x74\xB3\x88\xE6\x49"
+			  "\x19\x88\xD0\xC3\x60\x7E\xAE\x1F"
+			  "\x57\x69\x0E\x43",
+		.klen	= 20,
+		.iv	= "\x4E\x28\x00\x00\xA2\xFC\xA1\xA3",
+		.input	= "\x45\x00\x00\x49\x33\x3E\x00\x00"
+			  "\x7F\x11\x91\x82\xC3\xFB\x1D\x10"
+			  "\xC2\xB1\xD3\x26\xC0\x28\x31\xCE"
+			  "\x00\x35\xCB\x45\x80\x03\x02\x5B"
+			  "\x00\x00\x01\xE0\x00\x1E\x8C\x18"
+			  "\xD6\x57\x59\xD5\x22\x84\xA0\x35"
+			  "\x2C\x71\x47\x5C\x88\x80\x39\x1C"
+			  "\x76\x4D\x6E\x5E\xE0\x49\x6B\x32"
+			  "\x5A\xE2\x70\xC0\x38\x99\x49\x39"
+			  "\x15\x01\x01\x01",
+		.ilen	= 76,
+		.assoc	= "\x42\xF6\x7E\x3F\x10\x10\x10\x10"
+			  "\x10\x10\x10\x10",
+		.alen	= 12,
+		.result	= "\xFB\xA2\xCA\xD1\x2F\xC1\xF9\xF0"
+			  "\x0D\x3C\xEB\xF3\x05\x41\x0D\xB8"
+			  "\x3D\x77\x84\xB6\x07\x32\x3D\x22"
+			  "\x0F\x24\xB0\xA9\x7D\x54\x18\x28"
+			  "\x00\xCA\xDB\x0F\x68\xD9\x9E\xF0"
+			  "\xE0\xC0\xC8\x9A\xE9\xBE\xA8\x88"
+			  "\x4E\x52\xD6\x5B\xC1\xAF\xD0\x74"
+			  "\x0F\x74\x24\x44\x74\x7B\x5B\x39"
+			  "\xAB\x53\x31\x63\xAA\xD4\x55\x0E"
+			  "\xE5\x16\x09\x75\xCD\xB6\x08\xC5"
+			  "\x76\x91\x89\x60\x97\x63\xB8\xE1"
+			  "\x8C\xAA\x81\xE2",
+		.rlen	= 92,
+	}, {
+		.key	= "\xAB\xBC\xCD\xDE\xF0\x01\x12\x23"
+			  "\x34\x45\x56\x67\x78\x89\x9A\xAB"
+			  "\xAB\xBC\xCD\xDE\xF0\x01\x12\x23"
+			  "\x34\x45\x56\x67\x78\x89\x9A\xAB"
+			  "\x73\x61\x6C\x74",
+		.klen	= 36,
+		.iv	= "\x61\x6E\x64\x01\x69\x76\x65\x63",
+		.input	= "\x63\x69\x73\x63\x6F\x01\x72\x75"
+			  "\x6C\x65\x73\x01\x74\x68\x65\x01"
+			  "\x6E\x65\x74\x77\x65\x01\x64\x65"
+			  "\x66\x69\x6E\x65\x01\x74\x68\x65"
+			  "\x74\x65\x63\x68\x6E\x6F\x6C\x6F"
+			  "\x67\x69\x65\x73\x01\x74\x68\x61"
+			  "\x74\x77\x69\x6C\x6C\x01\x64\x65"
+			  "\x66\x69\x6E\x65\x74\x6F\x6D\x6F"
+			  "\x72\x72\x6F\x77\x01\x02\x02\x01",
+		.ilen	= 72,
+		.assoc	= "\x17\x40\x5E\x67\x15\x6F\x31\x26"
+			  "\xDD\x0D\xB9\x9B",
+		.alen	= 12,
+		.result	= "\xD4\xB7\xED\x86\xA1\x77\x7F\x2E"
+			  "\xA1\x3D\x69\x73\xD3\x24\xC6\x9E"
+			  "\x7B\x43\xF8\x26\xFB\x56\x83\x12"
+			  "\x26\x50\x8B\xEB\xD2\xDC\xEB\x18"
+			  "\xD0\xA6\xDF\x10\xE5\x48\x7D\xF0"
+			  "\x74\x11\x3E\x14\xC6\x41\x02\x4E"
+			  "\x3E\x67\x73\xD9\x1A\x62\xEE\x42"
+			  "\x9B\x04\x3A\x10\xE3\xEF\xE6\xB0"
+			  "\x12\xA4\x93\x63\x41\x23\x64\xF8"
+			  "\xC0\xCA\xC5\x87\xF2\x49\xE5\x6B"
+			  "\x11\xE2\x4F\x30\xE4\x4C\xCC\x76",
+		.rlen	= 88,
+	}, {
+		.key	= "\x7D\x77\x3D\x00\xC1\x44\xC5\x25"
+			  "\xAC\x61\x9D\x18\xC8\x4A\x3F\x47"
+			  "\xD9\x66\x42\x67",
+		.klen	= 20,
+		.iv	= "\x43\x45\x7E\x91\x82\x44\x3B\xC6",
+		.input	= "\x01\x02\x02\x01",
+		.ilen	= 4,
+		.assoc	= "\x33\x54\x67\xAE\xFF\xFF\xFF\xFF",
+		.alen	= 8,
+		.result	= "\x43\x7F\x86\x6B\xCB\x3F\x69\x9F"
+			  "\xE9\xB0\x82\x2B\xAC\x96\x1C\x45"
+			  "\x04\xBE\xF2\x70",
+		.rlen	= 20,
+	}, {
+		.key	= "\xAB\xBC\xCD\xDE\xF0\x01\x12\x23"
+			  "\x34\x45\x56\x67\x78\x89\x9A\xAB"
+			  "\xDE\xCA\xF8\x88",
+		.klen	= 20,
+		.iv	= "\xCA\xFE\xDE\xBA\xCE\xFA\xCE\x74",
+		.input	= "\x74\x6F\x01\x62\x65\x01\x6F\x72"
+			  "\x01\x6E\x6F\x74\x01\x74\x6F\x01"
+			  "\x62\x65\x00\x01",
+		.ilen	= 20,
+		.assoc	= "\x00\x00\x01\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x01",
+		.alen	= 12,
+		.result	= "\x29\xC9\xFC\x69\xA1\x97\xD0\x38"
+			  "\xCC\xDD\x14\xE2\xDD\xFC\xAA\x05"
+			  "\x43\x33\x21\x64\x41\x25\x03\x52"
+			  "\x43\x03\xED\x3C\x6C\x5F\x28\x38"
+			  "\x43\xAF\x8C\x3E",
+		.rlen	= 36,
+	}, {
+		.key	= "\x6C\x65\x67\x61\x6C\x69\x7A\x65"
+			  "\x6D\x61\x72\x69\x6A\x75\x61\x6E"
+			  "\x61\x61\x6E\x64\x64\x6F\x69\x74"
+			  "\x62\x65\x66\x6F\x72\x65\x69\x61"
+			  "\x74\x75\x72\x6E",
+		.klen	= 36,
+		.iv	= "\x33\x30\x21\x69\x67\x65\x74\x6D",
+		.input	= "\x45\x00\x00\x30\xDA\x3A\x00\x00"
+			  "\x80\x01\xDF\x3B\xC0\xA8\x00\x05"
+			  "\xC0\xA8\x00\x01\x08\x00\xC6\xCD"
+			  "\x02\x00\x07\x00\x61\x62\x63\x64"
+			  "\x65\x66\x67\x68\x69\x6A\x6B\x6C"
+			  "\x6D\x6E\x6F\x70\x71\x72\x73\x74"
+			  "\x01\x02\x02\x01",
+		.ilen	= 52,
+		.assoc	= "\x79\x6B\x69\x63\xFF\xFF\xFF\xFF"
+			  "\xFF\xFF\xFF\xFF",
+		.alen	= 12,
+		.result	= "\xF9\x7A\xB2\xAA\x35\x6D\x8E\xDC"
+			  "\xE1\x76\x44\xAC\x8C\x78\xE2\x5D"
+			  "\xD2\x4D\xED\xBB\x29\xEB\xF1\xB6"
+			  "\x4A\x27\x4B\x39\xB4\x9C\x3A\x86"
+			  "\x4C\xD3\xD7\x8C\xA4\xAE\x68\xA3"
+			  "\x2B\x42\x45\x8F\xB5\x7D\xBE\x82"
+			  "\x1D\xCC\x63\xB9\xD0\x93\x7B\xA2"
+			  "\x94\x5F\x66\x93\x68\x66\x1A\x32"
+			  "\x9F\xB4\xC0\x53",
+		.rlen	= 68,
+	}, {
+		.key	= "\x3D\xE0\x98\x74\xB3\x88\xE6\x49"
+			  "\x19\x88\xD0\xC3\x60\x7E\xAE\x1F"
+			  "\x57\x69\x0E\x43",
+		.klen	= 20,
+		.iv	= "\x4E\x28\x00\x00\xA2\xFC\xA1\xA3",
+		.input	= "\x45\x00\x00\x30\xDA\x3A\x00\x00"
+			  "\x80\x01\xDF\x3B\xC0\xA8\x00\x05"
+			  "\xC0\xA8\x00\x01\x08\x00\xC6\xCD"
+			  "\x02\x00\x07\x00\x61\x62\x63\x64"
+			  "\x65\x66\x67\x68\x69\x6A\x6B\x6C"
+			  "\x6D\x6E\x6F\x70\x71\x72\x73\x74"
+			  "\x01\x02\x02\x01",
+		.ilen	= 52,
+		.assoc	= "\x3F\x7E\xF6\x42\x10\x10\x10\x10"
+			  "\x10\x10\x10\x10",
+		.alen	= 12,
+		.result	= "\xFB\xA2\xCA\xA8\xC6\xC5\xF9\xF0"
+			  "\xF2\x2C\xA5\x4A\x06\x12\x10\xAD"
+			  "\x3F\x6E\x57\x91\xCF\x1A\xCA\x21"
+			  "\x0D\x11\x7C\xEC\x9C\x35\x79\x17"
+			  "\x65\xAC\xBD\x87\x01\xAD\x79\x84"
+			  "\x5B\xF9\xFE\x3F\xBA\x48\x7B\xC9"
+			  "\x63\x21\x93\x06\x84\xEE\xCA\xDB"
+			  "\x56\x91\x25\x46\xE7\xA9\x5C\x97"
+			  "\x40\xD7\xCB\x05",
+		.rlen	= 68,
+	}, {
+		.key	= "\x4C\x80\xCD\xEF\xBB\x5D\x10\xDA"
+			  "\x90\x6A\xC7\x3C\x36\x13\xA6\x34"
+			  "\x22\x43\x3C\x64",
+		.klen	= 20,
+		.iv	= "\x48\x55\xEC\x7D\x3A\x23\x4B\xFD",
+		.input	= "\x08\x00\xC6\xCD\x02\x00\x07\x00"
+			  "\x61\x62\x63\x64\x65\x66\x67\x68"
+			  "\x69\x6A\x6B\x6C\x6D\x6E\x6F\x70"
+			  "\x71\x72\x73\x74\x01\x02\x02\x01",
+		.ilen	= 32,
+		.assoc	= "\x00\x00\x43\x21\x87\x65\x43\x21"
+			  "\x00\x00\x00\x07",
+		.alen	= 12,
+		.result	= "\x74\x75\x2E\x8A\xEB\x5D\x87\x3C"
+			  "\xD7\xC0\xF4\xAC\xC3\x6C\x4B\xFF"
+			  "\x84\xB7\xD7\xB9\x8F\x0C\xA8\xB6"
+			  "\xAC\xDA\x68\x94\xBC\x61\x90\x69"
+			  "\xEF\x9C\xBC\x28\xFE\x1B\x56\xA7"
+			  "\xC4\xE0\xD5\x8C\x86\xCD\x2B\xC0",
+		.rlen	= 48,
 	}
 };
 
@@ -19964,7 +20896,428 @@ static struct aead_testvec aes_gcm_rfc4106_dec_tv_template[] = {
                           "\xff\xff\xff\xff\xff\xff\xff\xff"
                           "\xff\xff\xff\xff\xff\xff\xff\xff",
                 .rlen   = 192,
-
+	}, {
+		.key	= "\x4C\x80\xCD\xEF\xBB\x5D\x10\xDA"
+			  "\x90\x6A\xC7\x3C\x36\x13\xA6\x34"
+			  "\x2E\x44\x3B\x68",
+		.klen	= 20,
+		.iv	= "\x49\x56\xED\x7E\x3B\x24\x4C\xFE",
+		.result	= "\x45\x00\x00\x48\x69\x9A\x00\x00"
+			  "\x80\x11\x4D\xB7\xC0\xA8\x01\x02"
+			  "\xC0\xA8\x01\x01\x0A\x9B\xF1\x56"
+			  "\x38\xD3\x01\x00\x00\x01\x00\x00"
+			  "\x00\x00\x00\x00\x04\x5F\x73\x69"
+			  "\x70\x04\x5F\x75\x64\x70\x03\x73"
+			  "\x69\x70\x09\x63\x79\x62\x65\x72"
+			  "\x63\x69\x74\x79\x02\x64\x6B\x00"
+			  "\x00\x21\x00\x01\x01\x02\x02\x01",
+		.rlen	= 72,
+		.assoc	= "\x00\x00\x43\x21\x87\x65\x43\x21"
+			  "\x00\x00\x00\x00",
+		.alen	= 12,
+		.input	= "\xFE\xCF\x53\x7E\x72\x9D\x5B\x07"
+			  "\xDC\x30\xDF\x52\x8D\xD2\x2B\x76"
+			  "\x8D\x1B\x98\x73\x66\x96\xA6\xFD"
+			  "\x34\x85\x09\xFA\x13\xCE\xAC\x34"
+			  "\xCF\xA2\x43\x6F\x14\xA3\xF3\xCF"
+			  "\x65\x92\x5B\xF1\xF4\xA1\x3C\x5D"
+			  "\x15\xB2\x1E\x18\x84\xF5\xFF\x62"
+			  "\x47\xAE\xAB\xB7\x86\xB9\x3B\xCE"
+			  "\x61\xBC\x17\xD7\x68\xFD\x97\x32"
+			  "\x45\x90\x18\x14\x8F\x6C\xBE\x72"
+			  "\x2F\xD0\x47\x96\x56\x2D\xFD\xB4",
+		.ilen	= 88,
+	}, {
+		.key	= "\xFE\xFF\xE9\x92\x86\x65\x73\x1C"
+			  "\x6D\x6A\x8F\x94\x67\x30\x83\x08"
+			  "\xCA\xFE\xBA\xBE",
+		.klen	= 20,
+		.iv	= "\xFA\xCE\xDB\xAD\xDE\xCA\xF8\x88",
+		.result	= "\x45\x00\x00\x3E\x69\x8F\x00\x00"
+			  "\x80\x11\x4D\xCC\xC0\xA8\x01\x02"
+			  "\xC0\xA8\x01\x01\x0A\x98\x00\x35"
+			  "\x00\x2A\x23\x43\xB2\xD0\x01\x00"
+			  "\x00\x01\x00\x00\x00\x00\x00\x00"
+			  "\x03\x73\x69\x70\x09\x63\x79\x62"
+			  "\x65\x72\x63\x69\x74\x79\x02\x64"
+			  "\x6B\x00\x00\x01\x00\x01\x00\x01",
+		.rlen	= 64,
+		.assoc	= "\x00\x00\xA5\xF8\x00\x00\x00\x0A",
+		.alen	= 8,
+		.input	= "\xDE\xB2\x2C\xD9\xB0\x7C\x72\xC1"
+			  "\x6E\x3A\x65\xBE\xEB\x8D\xF3\x04"
+			  "\xA5\xA5\x89\x7D\x33\xAE\x53\x0F"
+			  "\x1B\xA7\x6D\x5D\x11\x4D\x2A\x5C"
+			  "\x3D\xE8\x18\x27\xC1\x0E\x9A\x4F"
+			  "\x51\x33\x0D\x0E\xEC\x41\x66\x42"
+			  "\xCF\xBB\x85\xA5\xB4\x7E\x48\xA4"
+			  "\xEC\x3B\x9B\xA9\x5D\x91\x8B\xD1"
+			  "\x83\xB7\x0D\x3A\xA8\xBC\x6E\xE4"
+			  "\xC3\x09\xE9\xD8\x5A\x41\xAD\x4A",
+		.ilen	= 80,
+	}, {
+		.key	= "\xAB\xBC\xCD\xDE\xF0\x01\x12\x23"
+			  "\x34\x45\x56\x67\x78\x89\x9A\xAB"
+			  "\xAB\xBC\xCD\xDE\xF0\x01\x12\x23"
+			  "\x34\x45\x56\x67\x78\x89\x9A\xAB"
+			  "\x11\x22\x33\x44",
+		.klen	= 36,
+		.iv	= "\x01\x02\x03\x04\x05\x06\x07\x08",
+		.result	= "\x45\x00\x00\x30\x69\xA6\x40\x00"
+			  "\x80\x06\x26\x90\xC0\xA8\x01\x02"
+			  "\x93\x89\x15\x5E\x0A\x9E\x00\x8B"
+			  "\x2D\xC5\x7E\xE0\x00\x00\x00\x00"
+			  "\x70\x02\x40\x00\x20\xBF\x00\x00"
+			  "\x02\x04\x05\xB4\x01\x01\x04\x02"
+			  "\x01\x02\x02\x01",
+		.rlen	= 52,
+		.assoc	= "\x4A\x2C\xBF\xE3\x00\x00\x00\x02",
+		.alen	= 8,
+		.input	= "\xFF\x42\x5C\x9B\x72\x45\x99\xDF"
+			  "\x7A\x3B\xCD\x51\x01\x94\xE0\x0D"
+			  "\x6A\x78\x10\x7F\x1B\x0B\x1C\xBF"
+			  "\x06\xEF\xAE\x9D\x65\xA5\xD7\x63"
+			  "\x74\x8A\x63\x79\x85\x77\x1D\x34"
+			  "\x7F\x05\x45\x65\x9F\x14\xE9\x9D"
+			  "\xEF\x84\x2D\x8E\xB3\x35\xF4\xEE"
+			  "\xCF\xDB\xF8\x31\x82\x4B\x4C\x49"
+			  "\x15\x95\x6C\x96",
+		.ilen	= 68,
+	}, {
+		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00",
+		.klen	= 20,
+		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.result	= "\x45\x00\x00\x3C\x99\xC5\x00\x00"
+			  "\x80\x01\xCB\x7A\x40\x67\x93\x18"
+			  "\x01\x01\x01\x01\x08\x00\x07\x5C"
+			  "\x02\x00\x44\x00\x61\x62\x63\x64"
+			  "\x65\x66\x67\x68\x69\x6A\x6B\x6C"
+			  "\x6D\x6E\x6F\x70\x71\x72\x73\x74"
+			  "\x75\x76\x77\x61\x62\x63\x64\x65"
+			  "\x66\x67\x68\x69\x01\x02\x02\x01",
+		.rlen	= 64,
+		.assoc	= "\x00\x00\x00\x00\x00\x00\x00\x01",
+		.alen	= 8,
+		.input	= "\x46\x88\xDA\xF2\xF9\x73\xA3\x92"
+			  "\x73\x29\x09\xC3\x31\xD5\x6D\x60"
+			  "\xF6\x94\xAB\xAA\x41\x4B\x5E\x7F"
+			  "\xF5\xFD\xCD\xFF\xF5\xE9\xA2\x84"
+			  "\x45\x64\x76\x49\x27\x19\xFF\xB6"
+			  "\x4D\xE7\xD9\xDC\xA1\xE1\xD8\x94"
+			  "\xBC\x3B\xD5\x78\x73\xED\x4D\x18"
+			  "\x1D\x19\xD4\xD5\xC8\xC1\x8A\xF3"
+			  "\xF8\x21\xD4\x96\xEE\xB0\x96\xE9"
+			  "\x8A\xD2\xB6\x9E\x47\x99\xC7\x1D",
+		.ilen	= 80,
+	}, {
+		.key	= "\x3D\xE0\x98\x74\xB3\x88\xE6\x49"
+			  "\x19\x88\xD0\xC3\x60\x7E\xAE\x1F"
+			  "\x57\x69\x0E\x43",
+		.klen	= 20,
+		.iv	= "\x4E\x28\x00\x00\xA2\xFC\xA1\xA3",
+		.result	= "\x45\x00\x00\x3C\x99\xC3\x00\x00"
+			  "\x80\x01\xCB\x7C\x40\x67\x93\x18"
+			  "\x01\x01\x01\x01\x08\x00\x08\x5C"
+			  "\x02\x00\x43\x00\x61\x62\x63\x64"
+			  "\x65\x66\x67\x68\x69\x6A\x6B\x6C"
+			  "\x6D\x6E\x6F\x70\x71\x72\x73\x74"
+			  "\x75\x76\x77\x61\x62\x63\x64\x65"
+			  "\x66\x67\x68\x69\x01\x02\x02\x01",
+		.rlen	= 64,
+		.assoc	= "\x42\xF6\x7E\x3F\x10\x10\x10\x10"
+			  "\x10\x10\x10\x10",
+		.alen	= 12,
+		.input	= "\xFB\xA2\xCA\xA4\x85\x3C\xF9\xF0"
+			  "\xF2\x2C\xB1\x0D\x86\xDD\x83\xB0"
+			  "\xFE\xC7\x56\x91\xCF\x1A\x04\xB0"
+			  "\x0D\x11\x38\xEC\x9C\x35\x79\x17"
+			  "\x65\xAC\xBD\x87\x01\xAD\x79\x84"
+			  "\x5B\xF9\xFE\x3F\xBA\x48\x7B\xC9"
+			  "\x17\x55\xE6\x66\x2B\x4C\x8D\x0D"
+			  "\x1F\x5E\x22\x73\x95\x30\x32\x0A"
+			  "\xE0\xD7\x31\xCC\x97\x8E\xCA\xFA"
+			  "\xEA\xE8\x8F\x00\xE8\x0D\x6E\x48",
+		.ilen	= 80,
+	}, {
+		.key	= "\x3D\xE0\x98\x74\xB3\x88\xE6\x49"
+			  "\x19\x88\xD0\xC3\x60\x7E\xAE\x1F"
+			  "\x57\x69\x0E\x43",
+		.klen	= 20,
+		.iv	= "\x4E\x28\x00\x00\xA2\xFC\xA1\xA3",
+		.result	= "\x45\x00\x00\x1C\x42\xA2\x00\x00"
+			  "\x80\x01\x44\x1F\x40\x67\x93\xB6"
+			  "\xE0\x00\x00\x02\x0A\x00\xF5\xFF"
+			  "\x01\x02\x02\x01",
+		.rlen	= 28,
+		.assoc	= "\x42\xF6\x7E\x3F\x10\x10\x10\x10"
+			  "\x10\x10\x10\x10",
+		.alen	= 12,
+		.input	= "\xFB\xA2\xCA\x84\x5E\x5D\xF9\xF0"
+			  "\xF2\x2C\x3E\x6E\x86\xDD\x83\x1E"
+			  "\x1F\xC6\x57\x92\xCD\x1A\xF9\x13"
+			  "\x0E\x13\x79\xED\x36\x9F\x07\x1F"
+			  "\x35\xE0\x34\xBE\x95\xF1\x12\xE4"
+			  "\xE7\xD0\x5D\x35",
+		.ilen	= 44,
+	}, {
+		.key	= "\xFE\xFF\xE9\x92\x86\x65\x73\x1C"
+			  "\x6D\x6A\x8F\x94\x67\x30\x83\x08"
+			  "\xFE\xFF\xE9\x92\x86\x65\x73\x1C"
+			  "\xCA\xFE\xBA\xBE",
+		.klen	= 28,
+		.iv	= "\xFA\xCE\xDB\xAD\xDE\xCA\xF8\x88",
+		.result	= "\x45\x00\x00\x28\xA4\xAD\x40\x00"
+			  "\x40\x06\x78\x80\x0A\x01\x03\x8F"
+			  "\x0A\x01\x06\x12\x80\x23\x06\xB8"
+			  "\xCB\x71\x26\x02\xDD\x6B\xB0\x3E"
+			  "\x50\x10\x16\xD0\x75\x68\x00\x01",
+		.rlen	= 40,
+		.assoc	= "\x00\x00\xA5\xF8\x00\x00\x00\x0A",
+		.alen	= 8,
+		.input	= "\xA5\xB1\xF8\x06\x60\x29\xAE\xA4"
+			  "\x0E\x59\x8B\x81\x22\xDE\x02\x42"
+			  "\x09\x38\xB3\xAB\x33\xF8\x28\xE6"
+			  "\x87\xB8\x85\x8B\x5B\xFB\xDB\xD0"
+			  "\x31\x5B\x27\x45\x21\x44\xCC\x77"
+			  "\x95\x45\x7B\x96\x52\x03\x7F\x53"
+			  "\x18\x02\x7B\x5B\x4C\xD7\xA6\x36",
+		.ilen	= 56,
+	}, {
+		.key	= "\xAB\xBC\xCD\xDE\xF0\x01\x12\x23"
+			  "\x34\x45\x56\x67\x78\x89\x9A\xAB"
+			  "\xDE\xCA\xF8\x88",
+		.klen	= 20,
+		.iv	= "\xCA\xFE\xDE\xBA\xCE\xFA\xCE\x74",
+		.result	= "\x45\x00\x00\x49\x33\xBA\x00\x00"
+			  "\x7F\x11\x91\x06\xC3\xFB\x1D\x10"
+			  "\xC2\xB1\xD3\x26\xC0\x28\x31\xCE"
+			  "\x00\x35\xDD\x7B\x80\x03\x02\xD5"
+			  "\x00\x00\x4E\x20\x00\x1E\x8C\x18"
+			  "\xD7\x5B\x81\xDC\x91\xBA\xA0\x47"
+			  "\x6B\x91\xB9\x24\xB2\x80\x38\x9D"
+			  "\x92\xC9\x63\xBA\xC0\x46\xEC\x95"
+			  "\x9B\x62\x66\xC0\x47\x22\xB1\x49"
+			  "\x23\x01\x01\x01",
+		.rlen	= 76,
+		.assoc	= "\x00\x00\x01\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x01",
+		.alen	= 12,
+		.input	= "\x18\xA6\xFD\x42\xF7\x2C\xBF\x4A"
+			  "\xB2\xA2\xEA\x90\x1F\x73\xD8\x14"
+			  "\xE3\xE7\xF2\x43\xD9\x54\x12\xE1"
+			  "\xC3\x49\xC1\xD2\xFB\xEC\x16\x8F"
+			  "\x91\x90\xFE\xEB\xAF\x2C\xB0\x19"
+			  "\x84\xE6\x58\x63\x96\x5D\x74\x72"
+			  "\xB7\x9D\xA3\x45\xE0\xE7\x80\x19"
+			  "\x1F\x0D\x2F\x0E\x0F\x49\x6C\x22"
+			  "\x6F\x21\x27\xB2\x7D\xB3\x57\x24"
+			  "\xE7\x84\x5D\x68\x65\x1F\x57\xE6"
+			  "\x5F\x35\x4F\x75\xFF\x17\x01\x57"
+			  "\x69\x62\x34\x36",
+		.ilen	= 92,
+	}, {
+		.key	= "\xAB\xBC\xCD\xDE\xF0\x01\x12\x23"
+			  "\x34\x45\x56\x67\x78\x89\x9A\xAB"
+			  "\xAB\xBC\xCD\xDE\xF0\x01\x12\x23"
+			  "\x34\x45\x56\x67\x78\x89\x9A\xAB"
+			  "\x73\x61\x6C\x74",
+		.klen	= 36,
+		.iv	= "\x61\x6E\x64\x01\x69\x76\x65\x63",
+		.result	= "\x45\x08\x00\x28\x73\x2C\x00\x00"
+			  "\x40\x06\xE9\xF9\x0A\x01\x06\x12"
+			  "\x0A\x01\x03\x8F\x06\xB8\x80\x23"
+			  "\xDD\x6B\xAF\xBE\xCB\x71\x26\x02"
+			  "\x50\x10\x1F\x64\x6D\x54\x00\x01",
+		.rlen	= 40,
+		.assoc	= "\x17\x40\x5E\x67\x15\x6F\x31\x26"
+			  "\xDD\x0D\xB9\x9B",
+		.alen	= 12,
+		.input	= "\xF2\xD6\x9E\xCD\xBD\x5A\x0D\x5B"
+			  "\x8D\x5E\xF3\x8B\xAD\x4D\xA5\x8D"
+			  "\x1F\x27\x8F\xDE\x98\xEF\x67\x54"
+			  "\x9D\x52\x4A\x30\x18\xD9\xA5\x7F"
+			  "\xF4\xD3\xA3\x1C\xE6\x73\x11\x9E"
+			  "\x45\x16\x26\xC2\x41\x57\x71\xE3"
+			  "\xB7\xEE\xBC\xA6\x14\xC8\x9B\x35",
+		.ilen	= 56,
+	}, {
+		.key	= "\x3D\xE0\x98\x74\xB3\x88\xE6\x49"
+			  "\x19\x88\xD0\xC3\x60\x7E\xAE\x1F"
+			  "\x57\x69\x0E\x43",
+		.klen	= 20,
+		.iv	= "\x4E\x28\x00\x00\xA2\xFC\xA1\xA3",
+		.result	= "\x45\x00\x00\x49\x33\x3E\x00\x00"
+			  "\x7F\x11\x91\x82\xC3\xFB\x1D\x10"
+			  "\xC2\xB1\xD3\x26\xC0\x28\x31\xCE"
+			  "\x00\x35\xCB\x45\x80\x03\x02\x5B"
+			  "\x00\x00\x01\xE0\x00\x1E\x8C\x18"
+			  "\xD6\x57\x59\xD5\x22\x84\xA0\x35"
+			  "\x2C\x71\x47\x5C\x88\x80\x39\x1C"
+			  "\x76\x4D\x6E\x5E\xE0\x49\x6B\x32"
+			  "\x5A\xE2\x70\xC0\x38\x99\x49\x39"
+			  "\x15\x01\x01\x01",
+		.rlen	= 76,
+		.assoc	= "\x42\xF6\x7E\x3F\x10\x10\x10\x10"
+			  "\x10\x10\x10\x10",
+		.alen	= 12,
+		.input	= "\xFB\xA2\xCA\xD1\x2F\xC1\xF9\xF0"
+			  "\x0D\x3C\xEB\xF3\x05\x41\x0D\xB8"
+			  "\x3D\x77\x84\xB6\x07\x32\x3D\x22"
+			  "\x0F\x24\xB0\xA9\x7D\x54\x18\x28"
+			  "\x00\xCA\xDB\x0F\x68\xD9\x9E\xF0"
+			  "\xE0\xC0\xC8\x9A\xE9\xBE\xA8\x88"
+			  "\x4E\x52\xD6\x5B\xC1\xAF\xD0\x74"
+			  "\x0F\x74\x24\x44\x74\x7B\x5B\x39"
+			  "\xAB\x53\x31\x63\xAA\xD4\x55\x0E"
+			  "\xE5\x16\x09\x75\xCD\xB6\x08\xC5"
+			  "\x76\x91\x89\x60\x97\x63\xB8\xE1"
+			  "\x8C\xAA\x81\xE2",
+		.ilen	= 92,
+	}, {
+		.key	= "\xAB\xBC\xCD\xDE\xF0\x01\x12\x23"
+			  "\x34\x45\x56\x67\x78\x89\x9A\xAB"
+			  "\xAB\xBC\xCD\xDE\xF0\x01\x12\x23"
+			  "\x34\x45\x56\x67\x78\x89\x9A\xAB"
+			  "\x73\x61\x6C\x74",
+		.klen	= 36,
+		.iv	= "\x61\x6E\x64\x01\x69\x76\x65\x63",
+		.result	= "\x63\x69\x73\x63\x6F\x01\x72\x75"
+			  "\x6C\x65\x73\x01\x74\x68\x65\x01"
+			  "\x6E\x65\x74\x77\x65\x01\x64\x65"
+			  "\x66\x69\x6E\x65\x01\x74\x68\x65"
+			  "\x74\x65\x63\x68\x6E\x6F\x6C\x6F"
+			  "\x67\x69\x65\x73\x01\x74\x68\x61"
+			  "\x74\x77\x69\x6C\x6C\x01\x64\x65"
+			  "\x66\x69\x6E\x65\x74\x6F\x6D\x6F"
+			  "\x72\x72\x6F\x77\x01\x02\x02\x01",
+		.rlen	= 72,
+		.assoc	= "\x17\x40\x5E\x67\x15\x6F\x31\x26"
+			  "\xDD\x0D\xB9\x9B",
+		.alen	= 12,
+		.input	= "\xD4\xB7\xED\x86\xA1\x77\x7F\x2E"
+			  "\xA1\x3D\x69\x73\xD3\x24\xC6\x9E"
+			  "\x7B\x43\xF8\x26\xFB\x56\x83\x12"
+			  "\x26\x50\x8B\xEB\xD2\xDC\xEB\x18"
+			  "\xD0\xA6\xDF\x10\xE5\x48\x7D\xF0"
+			  "\x74\x11\x3E\x14\xC6\x41\x02\x4E"
+			  "\x3E\x67\x73\xD9\x1A\x62\xEE\x42"
+			  "\x9B\x04\x3A\x10\xE3\xEF\xE6\xB0"
+			  "\x12\xA4\x93\x63\x41\x23\x64\xF8"
+			  "\xC0\xCA\xC5\x87\xF2\x49\xE5\x6B"
+			  "\x11\xE2\x4F\x30\xE4\x4C\xCC\x76",
+		.ilen	= 88,
+	}, {
+		.key	= "\x7D\x77\x3D\x00\xC1\x44\xC5\x25"
+			  "\xAC\x61\x9D\x18\xC8\x4A\x3F\x47"
+			  "\xD9\x66\x42\x67",
+		.klen	= 20,
+		.iv	= "\x43\x45\x7E\x91\x82\x44\x3B\xC6",
+		.result	= "\x01\x02\x02\x01",
+		.rlen	= 4,
+		.assoc	= "\x33\x54\x67\xAE\xFF\xFF\xFF\xFF",
+		.alen	= 8,
+		.input	= "\x43\x7F\x86\x6B\xCB\x3F\x69\x9F"
+			  "\xE9\xB0\x82\x2B\xAC\x96\x1C\x45"
+			  "\x04\xBE\xF2\x70",
+		.ilen	= 20,
+	}, {
+		.key	= "\xAB\xBC\xCD\xDE\xF0\x01\x12\x23"
+			  "\x34\x45\x56\x67\x78\x89\x9A\xAB"
+			  "\xDE\xCA\xF8\x88",
+		.klen	= 20,
+		.iv	= "\xCA\xFE\xDE\xBA\xCE\xFA\xCE\x74",
+		.result	= "\x74\x6F\x01\x62\x65\x01\x6F\x72"
+			  "\x01\x6E\x6F\x74\x01\x74\x6F\x01"
+			  "\x62\x65\x00\x01",
+		.rlen	= 20,
+		.assoc	= "\x00\x00\x01\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x01",
+		.alen	= 12,
+		.input	= "\x29\xC9\xFC\x69\xA1\x97\xD0\x38"
+			  "\xCC\xDD\x14\xE2\xDD\xFC\xAA\x05"
+			  "\x43\x33\x21\x64\x41\x25\x03\x52"
+			  "\x43\x03\xED\x3C\x6C\x5F\x28\x38"
+			  "\x43\xAF\x8C\x3E",
+		.ilen	= 36,
+	}, {
+		.key	= "\x6C\x65\x67\x61\x6C\x69\x7A\x65"
+			  "\x6D\x61\x72\x69\x6A\x75\x61\x6E"
+			  "\x61\x61\x6E\x64\x64\x6F\x69\x74"
+			  "\x62\x65\x66\x6F\x72\x65\x69\x61"
+			  "\x74\x75\x72\x6E",
+		.klen	= 36,
+		.iv	= "\x33\x30\x21\x69\x67\x65\x74\x6D",
+		.result	= "\x45\x00\x00\x30\xDA\x3A\x00\x00"
+			  "\x80\x01\xDF\x3B\xC0\xA8\x00\x05"
+			  "\xC0\xA8\x00\x01\x08\x00\xC6\xCD"
+			  "\x02\x00\x07\x00\x61\x62\x63\x64"
+			  "\x65\x66\x67\x68\x69\x6A\x6B\x6C"
+			  "\x6D\x6E\x6F\x70\x71\x72\x73\x74"
+			  "\x01\x02\x02\x01",
+		.rlen	= 52,
+		.assoc	= "\x79\x6B\x69\x63\xFF\xFF\xFF\xFF"
+			  "\xFF\xFF\xFF\xFF",
+		.alen	= 12,
+		.input	= "\xF9\x7A\xB2\xAA\x35\x6D\x8E\xDC"
+			  "\xE1\x76\x44\xAC\x8C\x78\xE2\x5D"
+			  "\xD2\x4D\xED\xBB\x29\xEB\xF1\xB6"
+			  "\x4A\x27\x4B\x39\xB4\x9C\x3A\x86"
+			  "\x4C\xD3\xD7\x8C\xA4\xAE\x68\xA3"
+			  "\x2B\x42\x45\x8F\xB5\x7D\xBE\x82"
+			  "\x1D\xCC\x63\xB9\xD0\x93\x7B\xA2"
+			  "\x94\x5F\x66\x93\x68\x66\x1A\x32"
+			  "\x9F\xB4\xC0\x53",
+		.ilen	= 68,
+	}, {
+		.key	= "\x3D\xE0\x98\x74\xB3\x88\xE6\x49"
+			  "\x19\x88\xD0\xC3\x60\x7E\xAE\x1F"
+			  "\x57\x69\x0E\x43",
+		.klen	= 20,
+		.iv	= "\x4E\x28\x00\x00\xA2\xFC\xA1\xA3",
+		.result	= "\x45\x00\x00\x30\xDA\x3A\x00\x00"
+			  "\x80\x01\xDF\x3B\xC0\xA8\x00\x05"
+			  "\xC0\xA8\x00\x01\x08\x00\xC6\xCD"
+			  "\x02\x00\x07\x00\x61\x62\x63\x64"
+			  "\x65\x66\x67\x68\x69\x6A\x6B\x6C"
+			  "\x6D\x6E\x6F\x70\x71\x72\x73\x74"
+			  "\x01\x02\x02\x01",
+		.rlen	= 52,
+		.assoc	= "\x3F\x7E\xF6\x42\x10\x10\x10\x10"
+			  "\x10\x10\x10\x10",
+		.alen	= 12,
+		.input	= "\xFB\xA2\xCA\xA8\xC6\xC5\xF9\xF0"
+			  "\xF2\x2C\xA5\x4A\x06\x12\x10\xAD"
+			  "\x3F\x6E\x57\x91\xCF\x1A\xCA\x21"
+			  "\x0D\x11\x7C\xEC\x9C\x35\x79\x17"
+			  "\x65\xAC\xBD\x87\x01\xAD\x79\x84"
+			  "\x5B\xF9\xFE\x3F\xBA\x48\x7B\xC9"
+			  "\x63\x21\x93\x06\x84\xEE\xCA\xDB"
+			  "\x56\x91\x25\x46\xE7\xA9\x5C\x97"
+			  "\x40\xD7\xCB\x05",
+		.ilen	= 68,
+	}, {
+		.key	= "\x4C\x80\xCD\xEF\xBB\x5D\x10\xDA"
+			  "\x90\x6A\xC7\x3C\x36\x13\xA6\x34"
+			  "\x22\x43\x3C\x64",
+		.klen	= 20,
+		.iv	= "\x48\x55\xEC\x7D\x3A\x23\x4B\xFD",
+		.result	= "\x08\x00\xC6\xCD\x02\x00\x07\x00"
+			  "\x61\x62\x63\x64\x65\x66\x67\x68"
+			  "\x69\x6A\x6B\x6C\x6D\x6E\x6F\x70"
+			  "\x71\x72\x73\x74\x01\x02\x02\x01",
+		.rlen	= 32,
+		.assoc	= "\x00\x00\x43\x21\x87\x65\x43\x21"
+			  "\x00\x00\x00\x07",
+		.alen	= 12,
+		.input	= "\x74\x75\x2E\x8A\xEB\x5D\x87\x3C"
+			  "\xD7\xC0\xF4\xAC\xC3\x6C\x4B\xFF"
+			  "\x84\xB7\xD7\xB9\x8F\x0C\xA8\xB6"
+			  "\xAC\xDA\x68\x94\xBC\x61\x90\x69"
+			  "\xEF\x9C\xBC\x28\xFE\x1B\x56\xA7"
+			  "\xC4\xE0\xD5\x8C\x86\xCD\x2B\xC0",
+		.ilen	= 48,
 	}
 };
 
@@ -19975,8 +21328,9 @@ static struct aead_testvec aes_gcm_rfc4543_enc_tv_template[] = {
 			  "\x22\x43\x3c\x64",
 		.klen	= 20,
 		.iv	= zeroed_string,
-		.assoc	= "\x00\x00\x43\x21\x00\x00\x00\x07",
-		.alen	= 8,
+		.assoc	= "\x00\x00\x43\x21\x00\x00\x00\x07"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.alen	= 16,
 		.input	= "\x45\x00\x00\x30\xda\x3a\x00\x00"
 			  "\x80\x01\xdf\x3b\xc0\xa8\x00\x05"
 			  "\xc0\xa8\x00\x01\x08\x00\xc6\xcd"
@@ -20005,8 +21359,9 @@ static struct aead_testvec aes_gcm_rfc4543_dec_tv_template[] = {
 			  "\x22\x43\x3c\x64",
 		.klen	= 20,
 		.iv	= zeroed_string,
-		.assoc	= "\x00\x00\x43\x21\x00\x00\x00\x07",
-		.alen	= 8,
+		.assoc	= "\x00\x00\x43\x21\x00\x00\x00\x07"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.alen	= 16,
 		.input	= "\x45\x00\x00\x30\xda\x3a\x00\x00"
 			  "\x80\x01\xdf\x3b\xc0\xa8\x00\x05"
 			  "\xc0\xa8\x00\x01\x08\x00\xc6\xcd"
@@ -20031,8 +21386,9 @@ static struct aead_testvec aes_gcm_rfc4543_dec_tv_template[] = {
 			  "\x22\x43\x3c\x64",
 		.klen	= 20,
 		.iv	= zeroed_string,
-		.assoc	= "\x00\x00\x43\x21\x00\x00\x00\x07",
-		.alen	= 8,
+		.assoc	= "\x00\x00\x43\x21\x00\x00\x00\x07"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.alen	= 16,
 		.input	= "\x45\x00\x00\x30\xda\x3a\x00\x00"
 			  "\x80\x01\xdf\x3b\xc0\xa8\x00\x05"
 			  "\xc0\xa8\x00\x01\x08\x00\xc6\xcd"
@@ -20704,6 +22060,454 @@ static struct aead_testvec aes_ccm_rfc4309_dec_tv_template[] = {
 };
 
 /*
+ * ChaCha20-Poly1305 AEAD test vectors from RFC7539 2.8.2./A.5.
+ */
+#define RFC7539_ENC_TEST_VECTORS 2
+#define RFC7539_DEC_TEST_VECTORS 2
+static struct aead_testvec rfc7539_enc_tv_template[] = {
+	{
+		.key	= "\x80\x81\x82\x83\x84\x85\x86\x87"
+			  "\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
+			  "\x90\x91\x92\x93\x94\x95\x96\x97"
+			  "\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f",
+		.klen	= 32,
+		.iv	= "\x07\x00\x00\x00\x40\x41\x42\x43"
+			  "\x44\x45\x46\x47",
+		.assoc	= "\x50\x51\x52\x53\xc0\xc1\xc2\xc3"
+			  "\xc4\xc5\xc6\xc7",
+		.alen	= 12,
+		.input	= "\x4c\x61\x64\x69\x65\x73\x20\x61"
+			  "\x6e\x64\x20\x47\x65\x6e\x74\x6c"
+			  "\x65\x6d\x65\x6e\x20\x6f\x66\x20"
+			  "\x74\x68\x65\x20\x63\x6c\x61\x73"
+			  "\x73\x20\x6f\x66\x20\x27\x39\x39"
+			  "\x3a\x20\x49\x66\x20\x49\x20\x63"
+			  "\x6f\x75\x6c\x64\x20\x6f\x66\x66"
+			  "\x65\x72\x20\x79\x6f\x75\x20\x6f"
+			  "\x6e\x6c\x79\x20\x6f\x6e\x65\x20"
+			  "\x74\x69\x70\x20\x66\x6f\x72\x20"
+			  "\x74\x68\x65\x20\x66\x75\x74\x75"
+			  "\x72\x65\x2c\x20\x73\x75\x6e\x73"
+			  "\x63\x72\x65\x65\x6e\x20\x77\x6f"
+			  "\x75\x6c\x64\x20\x62\x65\x20\x69"
+			  "\x74\x2e",
+		.ilen	= 114,
+		.result	= "\xd3\x1a\x8d\x34\x64\x8e\x60\xdb"
+			  "\x7b\x86\xaf\xbc\x53\xef\x7e\xc2"
+			  "\xa4\xad\xed\x51\x29\x6e\x08\xfe"
+			  "\xa9\xe2\xb5\xa7\x36\xee\x62\xd6"
+			  "\x3d\xbe\xa4\x5e\x8c\xa9\x67\x12"
+			  "\x82\xfa\xfb\x69\xda\x92\x72\x8b"
+			  "\x1a\x71\xde\x0a\x9e\x06\x0b\x29"
+			  "\x05\xd6\xa5\xb6\x7e\xcd\x3b\x36"
+			  "\x92\xdd\xbd\x7f\x2d\x77\x8b\x8c"
+			  "\x98\x03\xae\xe3\x28\x09\x1b\x58"
+			  "\xfa\xb3\x24\xe4\xfa\xd6\x75\x94"
+			  "\x55\x85\x80\x8b\x48\x31\xd7\xbc"
+			  "\x3f\xf4\xde\xf0\x8e\x4b\x7a\x9d"
+			  "\xe5\x76\xd2\x65\x86\xce\xc6\x4b"
+			  "\x61\x16\x1a\xe1\x0b\x59\x4f\x09"
+			  "\xe2\x6a\x7e\x90\x2e\xcb\xd0\x60"
+			  "\x06\x91",
+		.rlen	= 130,
+	}, {
+		.key	= "\x1c\x92\x40\xa5\xeb\x55\xd3\x8a"
+			  "\xf3\x33\x88\x86\x04\xf6\xb5\xf0"
+			  "\x47\x39\x17\xc1\x40\x2b\x80\x09"
+			  "\x9d\xca\x5c\xbc\x20\x70\x75\xc0",
+		.klen	= 32,
+		.iv	= "\x00\x00\x00\x00\x01\x02\x03\x04"
+			  "\x05\x06\x07\x08",
+		.assoc	= "\xf3\x33\x88\x86\x00\x00\x00\x00"
+			  "\x00\x00\x4e\x91",
+		.alen	= 12,
+		.input	= "\x49\x6e\x74\x65\x72\x6e\x65\x74"
+			  "\x2d\x44\x72\x61\x66\x74\x73\x20"
+			  "\x61\x72\x65\x20\x64\x72\x61\x66"
+			  "\x74\x20\x64\x6f\x63\x75\x6d\x65"
+			  "\x6e\x74\x73\x20\x76\x61\x6c\x69"
+			  "\x64\x20\x66\x6f\x72\x20\x61\x20"
+			  "\x6d\x61\x78\x69\x6d\x75\x6d\x20"
+			  "\x6f\x66\x20\x73\x69\x78\x20\x6d"
+			  "\x6f\x6e\x74\x68\x73\x20\x61\x6e"
+			  "\x64\x20\x6d\x61\x79\x20\x62\x65"
+			  "\x20\x75\x70\x64\x61\x74\x65\x64"
+			  "\x2c\x20\x72\x65\x70\x6c\x61\x63"
+			  "\x65\x64\x2c\x20\x6f\x72\x20\x6f"
+			  "\x62\x73\x6f\x6c\x65\x74\x65\x64"
+			  "\x20\x62\x79\x20\x6f\x74\x68\x65"
+			  "\x72\x20\x64\x6f\x63\x75\x6d\x65"
+			  "\x6e\x74\x73\x20\x61\x74\x20\x61"
+			  "\x6e\x79\x20\x74\x69\x6d\x65\x2e"
+			  "\x20\x49\x74\x20\x69\x73\x20\x69"
+			  "\x6e\x61\x70\x70\x72\x6f\x70\x72"
+			  "\x69\x61\x74\x65\x20\x74\x6f\x20"
+			  "\x75\x73\x65\x20\x49\x6e\x74\x65"
+			  "\x72\x6e\x65\x74\x2d\x44\x72\x61"
+			  "\x66\x74\x73\x20\x61\x73\x20\x72"
+			  "\x65\x66\x65\x72\x65\x6e\x63\x65"
+			  "\x20\x6d\x61\x74\x65\x72\x69\x61"
+			  "\x6c\x20\x6f\x72\x20\x74\x6f\x20"
+			  "\x63\x69\x74\x65\x20\x74\x68\x65"
+			  "\x6d\x20\x6f\x74\x68\x65\x72\x20"
+			  "\x74\x68\x61\x6e\x20\x61\x73\x20"
+			  "\x2f\xe2\x80\x9c\x77\x6f\x72\x6b"
+			  "\x20\x69\x6e\x20\x70\x72\x6f\x67"
+			  "\x72\x65\x73\x73\x2e\x2f\xe2\x80"
+			  "\x9d",
+		.ilen	= 265,
+		.result	= "\x64\xa0\x86\x15\x75\x86\x1a\xf4"
+			  "\x60\xf0\x62\xc7\x9b\xe6\x43\xbd"
+			  "\x5e\x80\x5c\xfd\x34\x5c\xf3\x89"
+			  "\xf1\x08\x67\x0a\xc7\x6c\x8c\xb2"
+			  "\x4c\x6c\xfc\x18\x75\x5d\x43\xee"
+			  "\xa0\x9e\xe9\x4e\x38\x2d\x26\xb0"
+			  "\xbd\xb7\xb7\x3c\x32\x1b\x01\x00"
+			  "\xd4\xf0\x3b\x7f\x35\x58\x94\xcf"
+			  "\x33\x2f\x83\x0e\x71\x0b\x97\xce"
+			  "\x98\xc8\xa8\x4a\xbd\x0b\x94\x81"
+			  "\x14\xad\x17\x6e\x00\x8d\x33\xbd"
+			  "\x60\xf9\x82\xb1\xff\x37\xc8\x55"
+			  "\x97\x97\xa0\x6e\xf4\xf0\xef\x61"
+			  "\xc1\x86\x32\x4e\x2b\x35\x06\x38"
+			  "\x36\x06\x90\x7b\x6a\x7c\x02\xb0"
+			  "\xf9\xf6\x15\x7b\x53\xc8\x67\xe4"
+			  "\xb9\x16\x6c\x76\x7b\x80\x4d\x46"
+			  "\xa5\x9b\x52\x16\xcd\xe7\xa4\xe9"
+			  "\x90\x40\xc5\xa4\x04\x33\x22\x5e"
+			  "\xe2\x82\xa1\xb0\xa0\x6c\x52\x3e"
+			  "\xaf\x45\x34\xd7\xf8\x3f\xa1\x15"
+			  "\x5b\x00\x47\x71\x8c\xbc\x54\x6a"
+			  "\x0d\x07\x2b\x04\xb3\x56\x4e\xea"
+			  "\x1b\x42\x22\x73\xf5\x48\x27\x1a"
+			  "\x0b\xb2\x31\x60\x53\xfa\x76\x99"
+			  "\x19\x55\xeb\xd6\x31\x59\x43\x4e"
+			  "\xce\xbb\x4e\x46\x6d\xae\x5a\x10"
+			  "\x73\xa6\x72\x76\x27\x09\x7a\x10"
+			  "\x49\xe6\x17\xd9\x1d\x36\x10\x94"
+			  "\xfa\x68\xf0\xff\x77\x98\x71\x30"
+			  "\x30\x5b\xea\xba\x2e\xda\x04\xdf"
+			  "\x99\x7b\x71\x4d\x6c\x6f\x2c\x29"
+			  "\xa6\xad\x5c\xb4\x02\x2b\x02\x70"
+			  "\x9b\xee\xad\x9d\x67\x89\x0c\xbb"
+			  "\x22\x39\x23\x36\xfe\xa1\x85\x1f"
+			  "\x38",
+		.rlen	= 281,
+	},
+};
+
+static struct aead_testvec rfc7539_dec_tv_template[] = {
+	{
+		.key	= "\x80\x81\x82\x83\x84\x85\x86\x87"
+			  "\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
+			  "\x90\x91\x92\x93\x94\x95\x96\x97"
+			  "\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f",
+		.klen	= 32,
+		.iv	= "\x07\x00\x00\x00\x40\x41\x42\x43"
+			  "\x44\x45\x46\x47",
+		.assoc	= "\x50\x51\x52\x53\xc0\xc1\xc2\xc3"
+			  "\xc4\xc5\xc6\xc7",
+		.alen	= 12,
+		.input	= "\xd3\x1a\x8d\x34\x64\x8e\x60\xdb"
+			  "\x7b\x86\xaf\xbc\x53\xef\x7e\xc2"
+			  "\xa4\xad\xed\x51\x29\x6e\x08\xfe"
+			  "\xa9\xe2\xb5\xa7\x36\xee\x62\xd6"
+			  "\x3d\xbe\xa4\x5e\x8c\xa9\x67\x12"
+			  "\x82\xfa\xfb\x69\xda\x92\x72\x8b"
+			  "\x1a\x71\xde\x0a\x9e\x06\x0b\x29"
+			  "\x05\xd6\xa5\xb6\x7e\xcd\x3b\x36"
+			  "\x92\xdd\xbd\x7f\x2d\x77\x8b\x8c"
+			  "\x98\x03\xae\xe3\x28\x09\x1b\x58"
+			  "\xfa\xb3\x24\xe4\xfa\xd6\x75\x94"
+			  "\x55\x85\x80\x8b\x48\x31\xd7\xbc"
+			  "\x3f\xf4\xde\xf0\x8e\x4b\x7a\x9d"
+			  "\xe5\x76\xd2\x65\x86\xce\xc6\x4b"
+			  "\x61\x16\x1a\xe1\x0b\x59\x4f\x09"
+			  "\xe2\x6a\x7e\x90\x2e\xcb\xd0\x60"
+			  "\x06\x91",
+		.ilen	= 130,
+		.result	= "\x4c\x61\x64\x69\x65\x73\x20\x61"
+			  "\x6e\x64\x20\x47\x65\x6e\x74\x6c"
+			  "\x65\x6d\x65\x6e\x20\x6f\x66\x20"
+			  "\x74\x68\x65\x20\x63\x6c\x61\x73"
+			  "\x73\x20\x6f\x66\x20\x27\x39\x39"
+			  "\x3a\x20\x49\x66\x20\x49\x20\x63"
+			  "\x6f\x75\x6c\x64\x20\x6f\x66\x66"
+			  "\x65\x72\x20\x79\x6f\x75\x20\x6f"
+			  "\x6e\x6c\x79\x20\x6f\x6e\x65\x20"
+			  "\x74\x69\x70\x20\x66\x6f\x72\x20"
+			  "\x74\x68\x65\x20\x66\x75\x74\x75"
+			  "\x72\x65\x2c\x20\x73\x75\x6e\x73"
+			  "\x63\x72\x65\x65\x6e\x20\x77\x6f"
+			  "\x75\x6c\x64\x20\x62\x65\x20\x69"
+			  "\x74\x2e",
+		.rlen	= 114,
+	}, {
+		.key	= "\x1c\x92\x40\xa5\xeb\x55\xd3\x8a"
+			  "\xf3\x33\x88\x86\x04\xf6\xb5\xf0"
+			  "\x47\x39\x17\xc1\x40\x2b\x80\x09"
+			  "\x9d\xca\x5c\xbc\x20\x70\x75\xc0",
+		.klen	= 32,
+		.iv	= "\x00\x00\x00\x00\x01\x02\x03\x04"
+			  "\x05\x06\x07\x08",
+		.assoc	= "\xf3\x33\x88\x86\x00\x00\x00\x00"
+			  "\x00\x00\x4e\x91",
+		.alen	= 12,
+		.input	= "\x64\xa0\x86\x15\x75\x86\x1a\xf4"
+			  "\x60\xf0\x62\xc7\x9b\xe6\x43\xbd"
+			  "\x5e\x80\x5c\xfd\x34\x5c\xf3\x89"
+			  "\xf1\x08\x67\x0a\xc7\x6c\x8c\xb2"
+			  "\x4c\x6c\xfc\x18\x75\x5d\x43\xee"
+			  "\xa0\x9e\xe9\x4e\x38\x2d\x26\xb0"
+			  "\xbd\xb7\xb7\x3c\x32\x1b\x01\x00"
+			  "\xd4\xf0\x3b\x7f\x35\x58\x94\xcf"
+			  "\x33\x2f\x83\x0e\x71\x0b\x97\xce"
+			  "\x98\xc8\xa8\x4a\xbd\x0b\x94\x81"
+			  "\x14\xad\x17\x6e\x00\x8d\x33\xbd"
+			  "\x60\xf9\x82\xb1\xff\x37\xc8\x55"
+			  "\x97\x97\xa0\x6e\xf4\xf0\xef\x61"
+			  "\xc1\x86\x32\x4e\x2b\x35\x06\x38"
+			  "\x36\x06\x90\x7b\x6a\x7c\x02\xb0"
+			  "\xf9\xf6\x15\x7b\x53\xc8\x67\xe4"
+			  "\xb9\x16\x6c\x76\x7b\x80\x4d\x46"
+			  "\xa5\x9b\x52\x16\xcd\xe7\xa4\xe9"
+			  "\x90\x40\xc5\xa4\x04\x33\x22\x5e"
+			  "\xe2\x82\xa1\xb0\xa0\x6c\x52\x3e"
+			  "\xaf\x45\x34\xd7\xf8\x3f\xa1\x15"
+			  "\x5b\x00\x47\x71\x8c\xbc\x54\x6a"
+			  "\x0d\x07\x2b\x04\xb3\x56\x4e\xea"
+			  "\x1b\x42\x22\x73\xf5\x48\x27\x1a"
+			  "\x0b\xb2\x31\x60\x53\xfa\x76\x99"
+			  "\x19\x55\xeb\xd6\x31\x59\x43\x4e"
+			  "\xce\xbb\x4e\x46\x6d\xae\x5a\x10"
+			  "\x73\xa6\x72\x76\x27\x09\x7a\x10"
+			  "\x49\xe6\x17\xd9\x1d\x36\x10\x94"
+			  "\xfa\x68\xf0\xff\x77\x98\x71\x30"
+			  "\x30\x5b\xea\xba\x2e\xda\x04\xdf"
+			  "\x99\x7b\x71\x4d\x6c\x6f\x2c\x29"
+			  "\xa6\xad\x5c\xb4\x02\x2b\x02\x70"
+			  "\x9b\xee\xad\x9d\x67\x89\x0c\xbb"
+			  "\x22\x39\x23\x36\xfe\xa1\x85\x1f"
+			  "\x38",
+		.ilen	= 281,
+		.result	= "\x49\x6e\x74\x65\x72\x6e\x65\x74"
+			  "\x2d\x44\x72\x61\x66\x74\x73\x20"
+			  "\x61\x72\x65\x20\x64\x72\x61\x66"
+			  "\x74\x20\x64\x6f\x63\x75\x6d\x65"
+			  "\x6e\x74\x73\x20\x76\x61\x6c\x69"
+			  "\x64\x20\x66\x6f\x72\x20\x61\x20"
+			  "\x6d\x61\x78\x69\x6d\x75\x6d\x20"
+			  "\x6f\x66\x20\x73\x69\x78\x20\x6d"
+			  "\x6f\x6e\x74\x68\x73\x20\x61\x6e"
+			  "\x64\x20\x6d\x61\x79\x20\x62\x65"
+			  "\x20\x75\x70\x64\x61\x74\x65\x64"
+			  "\x2c\x20\x72\x65\x70\x6c\x61\x63"
+			  "\x65\x64\x2c\x20\x6f\x72\x20\x6f"
+			  "\x62\x73\x6f\x6c\x65\x74\x65\x64"
+			  "\x20\x62\x79\x20\x6f\x74\x68\x65"
+			  "\x72\x20\x64\x6f\x63\x75\x6d\x65"
+			  "\x6e\x74\x73\x20\x61\x74\x20\x61"
+			  "\x6e\x79\x20\x74\x69\x6d\x65\x2e"
+			  "\x20\x49\x74\x20\x69\x73\x20\x69"
+			  "\x6e\x61\x70\x70\x72\x6f\x70\x72"
+			  "\x69\x61\x74\x65\x20\x74\x6f\x20"
+			  "\x75\x73\x65\x20\x49\x6e\x74\x65"
+			  "\x72\x6e\x65\x74\x2d\x44\x72\x61"
+			  "\x66\x74\x73\x20\x61\x73\x20\x72"
+			  "\x65\x66\x65\x72\x65\x6e\x63\x65"
+			  "\x20\x6d\x61\x74\x65\x72\x69\x61"
+			  "\x6c\x20\x6f\x72\x20\x74\x6f\x20"
+			  "\x63\x69\x74\x65\x20\x74\x68\x65"
+			  "\x6d\x20\x6f\x74\x68\x65\x72\x20"
+			  "\x74\x68\x61\x6e\x20\x61\x73\x20"
+			  "\x2f\xe2\x80\x9c\x77\x6f\x72\x6b"
+			  "\x20\x69\x6e\x20\x70\x72\x6f\x67"
+			  "\x72\x65\x73\x73\x2e\x2f\xe2\x80"
+			  "\x9d",
+		.rlen	= 265,
+	},
+};
+
+/*
+ * draft-irtf-cfrg-chacha20-poly1305
+ */
+#define RFC7539ESP_DEC_TEST_VECTORS 1
+#define RFC7539ESP_ENC_TEST_VECTORS 1
+static struct aead_testvec rfc7539esp_enc_tv_template[] = {
+	{
+		.key	= "\x1c\x92\x40\xa5\xeb\x55\xd3\x8a"
+			  "\xf3\x33\x88\x86\x04\xf6\xb5\xf0"
+			  "\x47\x39\x17\xc1\x40\x2b\x80\x09"
+			  "\x9d\xca\x5c\xbc\x20\x70\x75\xc0"
+			  "\x00\x00\x00\x00",
+		.klen	= 36,
+		.iv	= "\x01\x02\x03\x04\x05\x06\x07\x08",
+		.assoc	= "\xf3\x33\x88\x86\x00\x00\x00\x00"
+			  "\x00\x00\x4e\x91",
+		.alen	= 12,
+		.input	= "\x49\x6e\x74\x65\x72\x6e\x65\x74"
+			  "\x2d\x44\x72\x61\x66\x74\x73\x20"
+			  "\x61\x72\x65\x20\x64\x72\x61\x66"
+			  "\x74\x20\x64\x6f\x63\x75\x6d\x65"
+			  "\x6e\x74\x73\x20\x76\x61\x6c\x69"
+			  "\x64\x20\x66\x6f\x72\x20\x61\x20"
+			  "\x6d\x61\x78\x69\x6d\x75\x6d\x20"
+			  "\x6f\x66\x20\x73\x69\x78\x20\x6d"
+			  "\x6f\x6e\x74\x68\x73\x20\x61\x6e"
+			  "\x64\x20\x6d\x61\x79\x20\x62\x65"
+			  "\x20\x75\x70\x64\x61\x74\x65\x64"
+			  "\x2c\x20\x72\x65\x70\x6c\x61\x63"
+			  "\x65\x64\x2c\x20\x6f\x72\x20\x6f"
+			  "\x62\x73\x6f\x6c\x65\x74\x65\x64"
+			  "\x20\x62\x79\x20\x6f\x74\x68\x65"
+			  "\x72\x20\x64\x6f\x63\x75\x6d\x65"
+			  "\x6e\x74\x73\x20\x61\x74\x20\x61"
+			  "\x6e\x79\x20\x74\x69\x6d\x65\x2e"
+			  "\x20\x49\x74\x20\x69\x73\x20\x69"
+			  "\x6e\x61\x70\x70\x72\x6f\x70\x72"
+			  "\x69\x61\x74\x65\x20\x74\x6f\x20"
+			  "\x75\x73\x65\x20\x49\x6e\x74\x65"
+			  "\x72\x6e\x65\x74\x2d\x44\x72\x61"
+			  "\x66\x74\x73\x20\x61\x73\x20\x72"
+			  "\x65\x66\x65\x72\x65\x6e\x63\x65"
+			  "\x20\x6d\x61\x74\x65\x72\x69\x61"
+			  "\x6c\x20\x6f\x72\x20\x74\x6f\x20"
+			  "\x63\x69\x74\x65\x20\x74\x68\x65"
+			  "\x6d\x20\x6f\x74\x68\x65\x72\x20"
+			  "\x74\x68\x61\x6e\x20\x61\x73\x20"
+			  "\x2f\xe2\x80\x9c\x77\x6f\x72\x6b"
+			  "\x20\x69\x6e\x20\x70\x72\x6f\x67"
+			  "\x72\x65\x73\x73\x2e\x2f\xe2\x80"
+			  "\x9d",
+		.ilen	= 265,
+		.result	= "\x64\xa0\x86\x15\x75\x86\x1a\xf4"
+			  "\x60\xf0\x62\xc7\x9b\xe6\x43\xbd"
+			  "\x5e\x80\x5c\xfd\x34\x5c\xf3\x89"
+			  "\xf1\x08\x67\x0a\xc7\x6c\x8c\xb2"
+			  "\x4c\x6c\xfc\x18\x75\x5d\x43\xee"
+			  "\xa0\x9e\xe9\x4e\x38\x2d\x26\xb0"
+			  "\xbd\xb7\xb7\x3c\x32\x1b\x01\x00"
+			  "\xd4\xf0\x3b\x7f\x35\x58\x94\xcf"
+			  "\x33\x2f\x83\x0e\x71\x0b\x97\xce"
+			  "\x98\xc8\xa8\x4a\xbd\x0b\x94\x81"
+			  "\x14\xad\x17\x6e\x00\x8d\x33\xbd"
+			  "\x60\xf9\x82\xb1\xff\x37\xc8\x55"
+			  "\x97\x97\xa0\x6e\xf4\xf0\xef\x61"
+			  "\xc1\x86\x32\x4e\x2b\x35\x06\x38"
+			  "\x36\x06\x90\x7b\x6a\x7c\x02\xb0"
+			  "\xf9\xf6\x15\x7b\x53\xc8\x67\xe4"
+			  "\xb9\x16\x6c\x76\x7b\x80\x4d\x46"
+			  "\xa5\x9b\x52\x16\xcd\xe7\xa4\xe9"
+			  "\x90\x40\xc5\xa4\x04\x33\x22\x5e"
+			  "\xe2\x82\xa1\xb0\xa0\x6c\x52\x3e"
+			  "\xaf\x45\x34\xd7\xf8\x3f\xa1\x15"
+			  "\x5b\x00\x47\x71\x8c\xbc\x54\x6a"
+			  "\x0d\x07\x2b\x04\xb3\x56\x4e\xea"
+			  "\x1b\x42\x22\x73\xf5\x48\x27\x1a"
+			  "\x0b\xb2\x31\x60\x53\xfa\x76\x99"
+			  "\x19\x55\xeb\xd6\x31\x59\x43\x4e"
+			  "\xce\xbb\x4e\x46\x6d\xae\x5a\x10"
+			  "\x73\xa6\x72\x76\x27\x09\x7a\x10"
+			  "\x49\xe6\x17\xd9\x1d\x36\x10\x94"
+			  "\xfa\x68\xf0\xff\x77\x98\x71\x30"
+			  "\x30\x5b\xea\xba\x2e\xda\x04\xdf"
+			  "\x99\x7b\x71\x4d\x6c\x6f\x2c\x29"
+			  "\xa6\xad\x5c\xb4\x02\x2b\x02\x70"
+			  "\x9b\xee\xad\x9d\x67\x89\x0c\xbb"
+			  "\x22\x39\x23\x36\xfe\xa1\x85\x1f"
+			  "\x38",
+		.rlen	= 281,
+	},
+};
+
+static struct aead_testvec rfc7539esp_dec_tv_template[] = {
+	{
+		.key	= "\x1c\x92\x40\xa5\xeb\x55\xd3\x8a"
+			  "\xf3\x33\x88\x86\x04\xf6\xb5\xf0"
+			  "\x47\x39\x17\xc1\x40\x2b\x80\x09"
+			  "\x9d\xca\x5c\xbc\x20\x70\x75\xc0"
+			  "\x00\x00\x00\x00",
+		.klen	= 36,
+		.iv	= "\x01\x02\x03\x04\x05\x06\x07\x08",
+		.assoc	= "\xf3\x33\x88\x86\x00\x00\x00\x00"
+			  "\x00\x00\x4e\x91",
+		.alen	= 12,
+		.input	= "\x64\xa0\x86\x15\x75\x86\x1a\xf4"
+			  "\x60\xf0\x62\xc7\x9b\xe6\x43\xbd"
+			  "\x5e\x80\x5c\xfd\x34\x5c\xf3\x89"
+			  "\xf1\x08\x67\x0a\xc7\x6c\x8c\xb2"
+			  "\x4c\x6c\xfc\x18\x75\x5d\x43\xee"
+			  "\xa0\x9e\xe9\x4e\x38\x2d\x26\xb0"
+			  "\xbd\xb7\xb7\x3c\x32\x1b\x01\x00"
+			  "\xd4\xf0\x3b\x7f\x35\x58\x94\xcf"
+			  "\x33\x2f\x83\x0e\x71\x0b\x97\xce"
+			  "\x98\xc8\xa8\x4a\xbd\x0b\x94\x81"
+			  "\x14\xad\x17\x6e\x00\x8d\x33\xbd"
+			  "\x60\xf9\x82\xb1\xff\x37\xc8\x55"
+			  "\x97\x97\xa0\x6e\xf4\xf0\xef\x61"
+			  "\xc1\x86\x32\x4e\x2b\x35\x06\x38"
+			  "\x36\x06\x90\x7b\x6a\x7c\x02\xb0"
+			  "\xf9\xf6\x15\x7b\x53\xc8\x67\xe4"
+			  "\xb9\x16\x6c\x76\x7b\x80\x4d\x46"
+			  "\xa5\x9b\x52\x16\xcd\xe7\xa4\xe9"
+			  "\x90\x40\xc5\xa4\x04\x33\x22\x5e"
+			  "\xe2\x82\xa1\xb0\xa0\x6c\x52\x3e"
+			  "\xaf\x45\x34\xd7\xf8\x3f\xa1\x15"
+			  "\x5b\x00\x47\x71\x8c\xbc\x54\x6a"
+			  "\x0d\x07\x2b\x04\xb3\x56\x4e\xea"
+			  "\x1b\x42\x22\x73\xf5\x48\x27\x1a"
+			  "\x0b\xb2\x31\x60\x53\xfa\x76\x99"
+			  "\x19\x55\xeb\xd6\x31\x59\x43\x4e"
+			  "\xce\xbb\x4e\x46\x6d\xae\x5a\x10"
+			  "\x73\xa6\x72\x76\x27\x09\x7a\x10"
+			  "\x49\xe6\x17\xd9\x1d\x36\x10\x94"
+			  "\xfa\x68\xf0\xff\x77\x98\x71\x30"
+			  "\x30\x5b\xea\xba\x2e\xda\x04\xdf"
+			  "\x99\x7b\x71\x4d\x6c\x6f\x2c\x29"
+			  "\xa6\xad\x5c\xb4\x02\x2b\x02\x70"
+			  "\x9b\xee\xad\x9d\x67\x89\x0c\xbb"
+			  "\x22\x39\x23\x36\xfe\xa1\x85\x1f"
+			  "\x38",
+		.ilen	= 281,
+		.result	= "\x49\x6e\x74\x65\x72\x6e\x65\x74"
+			  "\x2d\x44\x72\x61\x66\x74\x73\x20"
+			  "\x61\x72\x65\x20\x64\x72\x61\x66"
+			  "\x74\x20\x64\x6f\x63\x75\x6d\x65"
+			  "\x6e\x74\x73\x20\x76\x61\x6c\x69"
+			  "\x64\x20\x66\x6f\x72\x20\x61\x20"
+			  "\x6d\x61\x78\x69\x6d\x75\x6d\x20"
+			  "\x6f\x66\x20\x73\x69\x78\x20\x6d"
+			  "\x6f\x6e\x74\x68\x73\x20\x61\x6e"
+			  "\x64\x20\x6d\x61\x79\x20\x62\x65"
+			  "\x20\x75\x70\x64\x61\x74\x65\x64"
+			  "\x2c\x20\x72\x65\x70\x6c\x61\x63"
+			  "\x65\x64\x2c\x20\x6f\x72\x20\x6f"
+			  "\x62\x73\x6f\x6c\x65\x74\x65\x64"
+			  "\x20\x62\x79\x20\x6f\x74\x68\x65"
+			  "\x72\x20\x64\x6f\x63\x75\x6d\x65"
+			  "\x6e\x74\x73\x20\x61\x74\x20\x61"
+			  "\x6e\x79\x20\x74\x69\x6d\x65\x2e"
+			  "\x20\x49\x74\x20\x69\x73\x20\x69"
+			  "\x6e\x61\x70\x70\x72\x6f\x70\x72"
+			  "\x69\x61\x74\x65\x20\x74\x6f\x20"
+			  "\x75\x73\x65\x20\x49\x6e\x74\x65"
+			  "\x72\x6e\x65\x74\x2d\x44\x72\x61"
+			  "\x66\x74\x73\x20\x61\x73\x20\x72"
+			  "\x65\x66\x65\x72\x65\x6e\x63\x65"
+			  "\x20\x6d\x61\x74\x65\x72\x69\x61"
+			  "\x6c\x20\x6f\x72\x20\x74\x6f\x20"
+			  "\x63\x69\x74\x65\x20\x74\x68\x65"
+			  "\x6d\x20\x6f\x74\x68\x65\x72\x20"
+			  "\x74\x68\x61\x6e\x20\x61\x73\x20"
+			  "\x2f\xe2\x80\x9c\x77\x6f\x72\x6b"
+			  "\x20\x69\x6e\x20\x70\x72\x6f\x67"
+			  "\x72\x65\x73\x73\x2e\x2f\xe2\x80"
+			  "\x9d",
+		.rlen	= 265,
+	},
+};
+
+/*
  * ANSI X9.31 Continuous Pseudo-Random Number Generator (AES mode)
  * test vectors, taken from Appendix B.2.9 and B.2.10:
  *     http://csrc.nist.gov/groups/STM/cavp/documents/rng/RNGVS.pdf
@@ -28370,6 +30174,183 @@ static struct cipher_testvec salsa20_stream_enc_tv_template[] = {
 	},
 };
 
+#define CHACHA20_ENC_TEST_VECTORS 3
+static struct cipher_testvec chacha20_enc_tv_template[] = {
+	{ /* RFC7539 A.2. Test Vector #1 */
+		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.klen	= 32,
+		.iv     = "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.input	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.ilen	= 64,
+		.result	= "\x76\xb8\xe0\xad\xa0\xf1\x3d\x90"
+			  "\x40\x5d\x6a\xe5\x53\x86\xbd\x28"
+			  "\xbd\xd2\x19\xb8\xa0\x8d\xed\x1a"
+			  "\xa8\x36\xef\xcc\x8b\x77\x0d\xc7"
+			  "\xda\x41\x59\x7c\x51\x57\x48\x8d"
+			  "\x77\x24\xe0\x3f\xb8\xd8\x4a\x37"
+			  "\x6a\x43\xb8\xf4\x15\x18\xa1\x1c"
+			  "\xc3\x87\xb6\x69\xb2\xee\x65\x86",
+		.rlen	= 64,
+	}, { /* RFC7539 A.2. Test Vector #2 */
+		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x01",
+		.klen	= 32,
+		.iv     = "\x01\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x02",
+		.input	= "\x41\x6e\x79\x20\x73\x75\x62\x6d"
+			  "\x69\x73\x73\x69\x6f\x6e\x20\x74"
+			  "\x6f\x20\x74\x68\x65\x20\x49\x45"
+			  "\x54\x46\x20\x69\x6e\x74\x65\x6e"
+			  "\x64\x65\x64\x20\x62\x79\x20\x74"
+			  "\x68\x65\x20\x43\x6f\x6e\x74\x72"
+			  "\x69\x62\x75\x74\x6f\x72\x20\x66"
+			  "\x6f\x72\x20\x70\x75\x62\x6c\x69"
+			  "\x63\x61\x74\x69\x6f\x6e\x20\x61"
+			  "\x73\x20\x61\x6c\x6c\x20\x6f\x72"
+			  "\x20\x70\x61\x72\x74\x20\x6f\x66"
+			  "\x20\x61\x6e\x20\x49\x45\x54\x46"
+			  "\x20\x49\x6e\x74\x65\x72\x6e\x65"
+			  "\x74\x2d\x44\x72\x61\x66\x74\x20"
+			  "\x6f\x72\x20\x52\x46\x43\x20\x61"
+			  "\x6e\x64\x20\x61\x6e\x79\x20\x73"
+			  "\x74\x61\x74\x65\x6d\x65\x6e\x74"
+			  "\x20\x6d\x61\x64\x65\x20\x77\x69"
+			  "\x74\x68\x69\x6e\x20\x74\x68\x65"
+			  "\x20\x63\x6f\x6e\x74\x65\x78\x74"
+			  "\x20\x6f\x66\x20\x61\x6e\x20\x49"
+			  "\x45\x54\x46\x20\x61\x63\x74\x69"
+			  "\x76\x69\x74\x79\x20\x69\x73\x20"
+			  "\x63\x6f\x6e\x73\x69\x64\x65\x72"
+			  "\x65\x64\x20\x61\x6e\x20\x22\x49"
+			  "\x45\x54\x46\x20\x43\x6f\x6e\x74"
+			  "\x72\x69\x62\x75\x74\x69\x6f\x6e"
+			  "\x22\x2e\x20\x53\x75\x63\x68\x20"
+			  "\x73\x74\x61\x74\x65\x6d\x65\x6e"
+			  "\x74\x73\x20\x69\x6e\x63\x6c\x75"
+			  "\x64\x65\x20\x6f\x72\x61\x6c\x20"
+			  "\x73\x74\x61\x74\x65\x6d\x65\x6e"
+			  "\x74\x73\x20\x69\x6e\x20\x49\x45"
+			  "\x54\x46\x20\x73\x65\x73\x73\x69"
+			  "\x6f\x6e\x73\x2c\x20\x61\x73\x20"
+			  "\x77\x65\x6c\x6c\x20\x61\x73\x20"
+			  "\x77\x72\x69\x74\x74\x65\x6e\x20"
+			  "\x61\x6e\x64\x20\x65\x6c\x65\x63"
+			  "\x74\x72\x6f\x6e\x69\x63\x20\x63"
+			  "\x6f\x6d\x6d\x75\x6e\x69\x63\x61"
+			  "\x74\x69\x6f\x6e\x73\x20\x6d\x61"
+			  "\x64\x65\x20\x61\x74\x20\x61\x6e"
+			  "\x79\x20\x74\x69\x6d\x65\x20\x6f"
+			  "\x72\x20\x70\x6c\x61\x63\x65\x2c"
+			  "\x20\x77\x68\x69\x63\x68\x20\x61"
+			  "\x72\x65\x20\x61\x64\x64\x72\x65"
+			  "\x73\x73\x65\x64\x20\x74\x6f",
+		.ilen	= 375,
+		.result	= "\xa3\xfb\xf0\x7d\xf3\xfa\x2f\xde"
+			  "\x4f\x37\x6c\xa2\x3e\x82\x73\x70"
+			  "\x41\x60\x5d\x9f\x4f\x4f\x57\xbd"
+			  "\x8c\xff\x2c\x1d\x4b\x79\x55\xec"
+			  "\x2a\x97\x94\x8b\xd3\x72\x29\x15"
+			  "\xc8\xf3\xd3\x37\xf7\xd3\x70\x05"
+			  "\x0e\x9e\x96\xd6\x47\xb7\xc3\x9f"
+			  "\x56\xe0\x31\xca\x5e\xb6\x25\x0d"
+			  "\x40\x42\xe0\x27\x85\xec\xec\xfa"
+			  "\x4b\x4b\xb5\xe8\xea\xd0\x44\x0e"
+			  "\x20\xb6\xe8\xdb\x09\xd8\x81\xa7"
+			  "\xc6\x13\x2f\x42\x0e\x52\x79\x50"
+			  "\x42\xbd\xfa\x77\x73\xd8\xa9\x05"
+			  "\x14\x47\xb3\x29\x1c\xe1\x41\x1c"
+			  "\x68\x04\x65\x55\x2a\xa6\xc4\x05"
+			  "\xb7\x76\x4d\x5e\x87\xbe\xa8\x5a"
+			  "\xd0\x0f\x84\x49\xed\x8f\x72\xd0"
+			  "\xd6\x62\xab\x05\x26\x91\xca\x66"
+			  "\x42\x4b\xc8\x6d\x2d\xf8\x0e\xa4"
+			  "\x1f\x43\xab\xf9\x37\xd3\x25\x9d"
+			  "\xc4\xb2\xd0\xdf\xb4\x8a\x6c\x91"
+			  "\x39\xdd\xd7\xf7\x69\x66\xe9\x28"
+			  "\xe6\x35\x55\x3b\xa7\x6c\x5c\x87"
+			  "\x9d\x7b\x35\xd4\x9e\xb2\xe6\x2b"
+			  "\x08\x71\xcd\xac\x63\x89\x39\xe2"
+			  "\x5e\x8a\x1e\x0e\xf9\xd5\x28\x0f"
+			  "\xa8\xca\x32\x8b\x35\x1c\x3c\x76"
+			  "\x59\x89\xcb\xcf\x3d\xaa\x8b\x6c"
+			  "\xcc\x3a\xaf\x9f\x39\x79\xc9\x2b"
+			  "\x37\x20\xfc\x88\xdc\x95\xed\x84"
+			  "\xa1\xbe\x05\x9c\x64\x99\xb9\xfd"
+			  "\xa2\x36\xe7\xe8\x18\xb0\x4b\x0b"
+			  "\xc3\x9c\x1e\x87\x6b\x19\x3b\xfe"
+			  "\x55\x69\x75\x3f\x88\x12\x8c\xc0"
+			  "\x8a\xaa\x9b\x63\xd1\xa1\x6f\x80"
+			  "\xef\x25\x54\xd7\x18\x9c\x41\x1f"
+			  "\x58\x69\xca\x52\xc5\xb8\x3f\xa3"
+			  "\x6f\xf2\x16\xb9\xc1\xd3\x00\x62"
+			  "\xbe\xbc\xfd\x2d\xc5\xbc\xe0\x91"
+			  "\x19\x34\xfd\xa7\x9a\x86\xf6\xe6"
+			  "\x98\xce\xd7\x59\xc3\xff\x9b\x64"
+			  "\x77\x33\x8f\x3d\xa4\xf9\xcd\x85"
+			  "\x14\xea\x99\x82\xcc\xaf\xb3\x41"
+			  "\xb2\x38\x4d\xd9\x02\xf3\xd1\xab"
+			  "\x7a\xc6\x1d\xd2\x9c\x6f\x21\xba"
+			  "\x5b\x86\x2f\x37\x30\xe3\x7c\xfd"
+			  "\xc4\xfd\x80\x6c\x22\xf2\x21",
+		.rlen	= 375,
+	}, { /* RFC7539 A.2. Test Vector #3 */
+		.key	= "\x1c\x92\x40\xa5\xeb\x55\xd3\x8a"
+			  "\xf3\x33\x88\x86\x04\xf6\xb5\xf0"
+			  "\x47\x39\x17\xc1\x40\x2b\x80\x09"
+			  "\x9d\xca\x5c\xbc\x20\x70\x75\xc0",
+		.klen	= 32,
+		.iv     = "\x2a\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x02",
+		.input	= "\x27\x54\x77\x61\x73\x20\x62\x72"
+			  "\x69\x6c\x6c\x69\x67\x2c\x20\x61"
+			  "\x6e\x64\x20\x74\x68\x65\x20\x73"
+			  "\x6c\x69\x74\x68\x79\x20\x74\x6f"
+			  "\x76\x65\x73\x0a\x44\x69\x64\x20"
+			  "\x67\x79\x72\x65\x20\x61\x6e\x64"
+			  "\x20\x67\x69\x6d\x62\x6c\x65\x20"
+			  "\x69\x6e\x20\x74\x68\x65\x20\x77"
+			  "\x61\x62\x65\x3a\x0a\x41\x6c\x6c"
+			  "\x20\x6d\x69\x6d\x73\x79\x20\x77"
+			  "\x65\x72\x65\x20\x74\x68\x65\x20"
+			  "\x62\x6f\x72\x6f\x67\x6f\x76\x65"
+			  "\x73\x2c\x0a\x41\x6e\x64\x20\x74"
+			  "\x68\x65\x20\x6d\x6f\x6d\x65\x20"
+			  "\x72\x61\x74\x68\x73\x20\x6f\x75"
+			  "\x74\x67\x72\x61\x62\x65\x2e",
+		.ilen	= 127,
+		.result	= "\x62\xe6\x34\x7f\x95\xed\x87\xa4"
+			  "\x5f\xfa\xe7\x42\x6f\x27\xa1\xdf"
+			  "\x5f\xb6\x91\x10\x04\x4c\x0d\x73"
+			  "\x11\x8e\xff\xa9\x5b\x01\xe5\xcf"
+			  "\x16\x6d\x3d\xf2\xd7\x21\xca\xf9"
+			  "\xb2\x1e\x5f\xb1\x4c\x61\x68\x71"
+			  "\xfd\x84\xc5\x4f\x9d\x65\xb2\x83"
+			  "\x19\x6c\x7f\xe4\xf6\x05\x53\xeb"
+			  "\xf3\x9c\x64\x02\xc4\x22\x34\xe3"
+			  "\x2a\x35\x6b\x3e\x76\x43\x12\xa6"
+			  "\x1a\x55\x32\x05\x57\x16\xea\xd6"
+			  "\x96\x25\x68\xf8\x7d\x3f\x3f\x77"
+			  "\x04\xc6\xa8\xd1\xbc\xd1\xbf\x4d"
+			  "\x50\xd6\x15\x4b\x6d\xa7\x31\xb1"
+			  "\x87\xb5\x8d\xfd\x72\x8a\xfa\x36"
+			  "\x75\x7a\x79\x7a\xc1\x88\xd1",
+		.rlen	= 127,
+	},
+};
+
 /*
  * CTS (Cipher Text Stealing) mode tests
  */
@@ -28591,7 +30572,7 @@ struct comp_testvec {
 };
 
 struct pcomp_testvec {
-	void *params;
+	const void *params;
 	unsigned int paramsize;
 	int inlen, outlen;
 	char input[COMP_BUF_SIZE];
@@ -28946,6 +30927,440 @@ static struct hash_testvec michael_mic_tv_template[] = {
 };
 
 /*
+ * CRC32 test vectors
+ */
+#define CRC32_TEST_VECTORS 14
+
+static struct hash_testvec crc32_tv_template[] = {
+	{
+		.key = "\x87\xa9\xcb\xed",
+		.ksize = 4,
+		.psize = 0,
+		.digest = "\x87\xa9\xcb\xed",
+	},
+	{
+		.key = "\xff\xff\xff\xff",
+		.ksize = 4,
+		.plaintext = "\x01\x02\x03\x04\x05\x06\x07\x08"
+			     "\x09\x0a\x0b\x0c\x0d\x0e\x0f\x10"
+			     "\x11\x12\x13\x14\x15\x16\x17\x18"
+			     "\x19\x1a\x1b\x1c\x1d\x1e\x1f\x20"
+			     "\x21\x22\x23\x24\x25\x26\x27\x28",
+		.psize = 40,
+		.digest = "\x3a\xdf\x4b\xb0",
+	},
+	{
+		.key = "\xff\xff\xff\xff",
+		.ksize = 4,
+		.plaintext = "\x29\x2a\x2b\x2c\x2d\x2e\x2f\x30"
+			     "\x31\x32\x33\x34\x35\x36\x37\x38"
+			     "\x39\x3a\x3b\x3c\x3d\x3e\x3f\x40"
+			     "\x41\x42\x43\x44\x45\x46\x47\x48"
+			     "\x49\x4a\x4b\x4c\x4d\x4e\x4f\x50",
+		.psize = 40,
+		.digest = "\xa9\x7a\x7f\x7b",
+	},
+	{
+		.key = "\xff\xff\xff\xff",
+		.ksize = 4,
+		.plaintext = "\x51\x52\x53\x54\x55\x56\x57\x58"
+			     "\x59\x5a\x5b\x5c\x5d\x5e\x5f\x60"
+			     "\x61\x62\x63\x64\x65\x66\x67\x68"
+			     "\x69\x6a\x6b\x6c\x6d\x6e\x6f\x70"
+			     "\x71\x72\x73\x74\x75\x76\x77\x78",
+		.psize = 40,
+		.digest = "\xba\xd3\xf8\x1c",
+	},
+	{
+		.key = "\xff\xff\xff\xff",
+		.ksize = 4,
+		.plaintext = "\x79\x7a\x7b\x7c\x7d\x7e\x7f\x80"
+			     "\x81\x82\x83\x84\x85\x86\x87\x88"
+			     "\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90"
+			     "\x91\x92\x93\x94\x95\x96\x97\x98"
+			     "\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0",
+		.psize = 40,
+		.digest = "\xa8\xa9\xc2\x02",
+	},
+	{
+		.key = "\xff\xff\xff\xff",
+		.ksize = 4,
+		.plaintext = "\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8"
+			     "\xa9\xaa\xab\xac\xad\xae\xaf\xb0"
+			     "\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8"
+			     "\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0"
+			     "\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8",
+		.psize = 40,
+		.digest = "\x27\xf0\x57\xe2",
+	},
+	{
+		.key = "\xff\xff\xff\xff",
+		.ksize = 4,
+		.plaintext = "\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0"
+			     "\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8"
+			     "\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0"
+			     "\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8"
+			     "\xe9\xea\xeb\xec\xed\xee\xef\xf0",
+		.psize = 40,
+		.digest = "\x49\x78\x10\x08",
+	},
+	{
+		.key = "\x80\xea\xd3\xf1",
+		.ksize = 4,
+		.plaintext = "\x29\x2a\x2b\x2c\x2d\x2e\x2f\x30"
+			     "\x31\x32\x33\x34\x35\x36\x37\x38"
+			     "\x39\x3a\x3b\x3c\x3d\x3e\x3f\x40"
+			     "\x41\x42\x43\x44\x45\x46\x47\x48"
+			     "\x49\x4a\x4b\x4c\x4d\x4e\x4f\x50",
+		.psize = 40,
+		.digest = "\x9a\xb1\xdc\xf0",
+	},
+	{
+		.key = "\xf3\x4a\x1d\x5d",
+		.ksize = 4,
+		.plaintext = "\x51\x52\x53\x54\x55\x56\x57\x58"
+			     "\x59\x5a\x5b\x5c\x5d\x5e\x5f\x60"
+			     "\x61\x62\x63\x64\x65\x66\x67\x68"
+			     "\x69\x6a\x6b\x6c\x6d\x6e\x6f\x70"
+			     "\x71\x72\x73\x74\x75\x76\x77\x78",
+		.psize = 40,
+		.digest = "\xb4\x97\xcc\xd4",
+	},
+	{
+		.key = "\x2e\x80\x04\x59",
+		.ksize = 4,
+		.plaintext = "\x79\x7a\x7b\x7c\x7d\x7e\x7f\x80"
+			     "\x81\x82\x83\x84\x85\x86\x87\x88"
+			     "\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90"
+			     "\x91\x92\x93\x94\x95\x96\x97\x98"
+			     "\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0",
+		.psize = 40,
+		.digest = "\x67\x9b\xfa\x79",
+	},
+	{
+		.key = "\xa6\xcc\x19\x85",
+		.ksize = 4,
+		.plaintext = "\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8"
+			     "\xa9\xaa\xab\xac\xad\xae\xaf\xb0"
+			     "\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8"
+			     "\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0"
+			     "\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8",
+		.psize = 40,
+		.digest = "\x24\xb5\x16\xef",
+	},
+	{
+		.key = "\x41\xfc\xfe\x2d",
+		.ksize = 4,
+		.plaintext = "\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0"
+			     "\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8"
+			     "\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0"
+			     "\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8"
+			     "\xe9\xea\xeb\xec\xed\xee\xef\xf0",
+		.psize = 40,
+		.digest = "\x15\x94\x80\x39",
+	},
+	{
+		.key = "\xff\xff\xff\xff",
+		.ksize = 4,
+		.plaintext = "\x01\x02\x03\x04\x05\x06\x07\x08"
+			     "\x09\x0a\x0b\x0c\x0d\x0e\x0f\x10"
+			     "\x11\x12\x13\x14\x15\x16\x17\x18"
+			     "\x19\x1a\x1b\x1c\x1d\x1e\x1f\x20"
+			     "\x21\x22\x23\x24\x25\x26\x27\x28"
+			     "\x29\x2a\x2b\x2c\x2d\x2e\x2f\x30"
+			     "\x31\x32\x33\x34\x35\x36\x37\x38"
+			     "\x39\x3a\x3b\x3c\x3d\x3e\x3f\x40"
+			     "\x41\x42\x43\x44\x45\x46\x47\x48"
+			     "\x49\x4a\x4b\x4c\x4d\x4e\x4f\x50"
+			     "\x51\x52\x53\x54\x55\x56\x57\x58"
+			     "\x59\x5a\x5b\x5c\x5d\x5e\x5f\x60"
+			     "\x61\x62\x63\x64\x65\x66\x67\x68"
+			     "\x69\x6a\x6b\x6c\x6d\x6e\x6f\x70"
+			     "\x71\x72\x73\x74\x75\x76\x77\x78"
+			     "\x79\x7a\x7b\x7c\x7d\x7e\x7f\x80"
+			     "\x81\x82\x83\x84\x85\x86\x87\x88"
+			     "\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90"
+			     "\x91\x92\x93\x94\x95\x96\x97\x98"
+			     "\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0"
+			     "\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8"
+			     "\xa9\xaa\xab\xac\xad\xae\xaf\xb0"
+			     "\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8"
+			     "\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0"
+			     "\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8"
+			     "\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0"
+			     "\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8"
+			     "\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0"
+			     "\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8"
+			     "\xe9\xea\xeb\xec\xed\xee\xef\xf0",
+		.psize = 240,
+		.digest = "\x6c\xc6\x56\xde",
+		.np = 2,
+		.tap = { 31, 209 }
+	}, {
+		.key = "\xff\xff\xff\xff",
+		.ksize = 4,
+		.plaintext =	"\x6e\x05\x79\x10\xa7\x1b\xb2\x49"
+				"\xe0\x54\xeb\x82\x19\x8d\x24\xbb"
+				"\x2f\xc6\x5d\xf4\x68\xff\x96\x0a"
+				"\xa1\x38\xcf\x43\xda\x71\x08\x7c"
+				"\x13\xaa\x1e\xb5\x4c\xe3\x57\xee"
+				"\x85\x1c\x90\x27\xbe\x32\xc9\x60"
+				"\xf7\x6b\x02\x99\x0d\xa4\x3b\xd2"
+				"\x46\xdd\x74\x0b\x7f\x16\xad\x21"
+				"\xb8\x4f\xe6\x5a\xf1\x88\x1f\x93"
+				"\x2a\xc1\x35\xcc\x63\xfa\x6e\x05"
+				"\x9c\x10\xa7\x3e\xd5\x49\xe0\x77"
+				"\x0e\x82\x19\xb0\x24\xbb\x52\xe9"
+				"\x5d\xf4\x8b\x22\x96\x2d\xc4\x38"
+				"\xcf\x66\xfd\x71\x08\x9f\x13\xaa"
+				"\x41\xd8\x4c\xe3\x7a\x11\x85\x1c"
+				"\xb3\x27\xbe\x55\xec\x60\xf7\x8e"
+				"\x02\x99\x30\xc7\x3b\xd2\x69\x00"
+				"\x74\x0b\xa2\x16\xad\x44\xdb\x4f"
+				"\xe6\x7d\x14\x88\x1f\xb6\x2a\xc1"
+				"\x58\xef\x63\xfa\x91\x05\x9c\x33"
+				"\xca\x3e\xd5\x6c\x03\x77\x0e\xa5"
+				"\x19\xb0\x47\xde\x52\xe9\x80\x17"
+				"\x8b\x22\xb9\x2d\xc4\x5b\xf2\x66"
+				"\xfd\x94\x08\x9f\x36\xcd\x41\xd8"
+				"\x6f\x06\x7a\x11\xa8\x1c\xb3\x4a"
+				"\xe1\x55\xec\x83\x1a\x8e\x25\xbc"
+				"\x30\xc7\x5e\xf5\x69\x00\x97\x0b"
+				"\xa2\x39\xd0\x44\xdb\x72\x09\x7d"
+				"\x14\xab\x1f\xb6\x4d\xe4\x58\xef"
+				"\x86\x1d\x91\x28\xbf\x33\xca\x61"
+				"\xf8\x6c\x03\x9a\x0e\xa5\x3c\xd3"
+				"\x47\xde\x75\x0c\x80\x17\xae\x22"
+				"\xb9\x50\xe7\x5b\xf2\x89\x20\x94"
+				"\x2b\xc2\x36\xcd\x64\xfb\x6f\x06"
+				"\x9d\x11\xa8\x3f\xd6\x4a\xe1\x78"
+				"\x0f\x83\x1a\xb1\x25\xbc\x53\xea"
+				"\x5e\xf5\x8c\x00\x97\x2e\xc5\x39"
+				"\xd0\x67\xfe\x72\x09\xa0\x14\xab"
+				"\x42\xd9\x4d\xe4\x7b\x12\x86\x1d"
+				"\xb4\x28\xbf\x56\xed\x61\xf8\x8f"
+				"\x03\x9a\x31\xc8\x3c\xd3\x6a\x01"
+				"\x75\x0c\xa3\x17\xae\x45\xdc\x50"
+				"\xe7\x7e\x15\x89\x20\xb7\x2b\xc2"
+				"\x59\xf0\x64\xfb\x92\x06\x9d\x34"
+				"\xcb\x3f\xd6\x6d\x04\x78\x0f\xa6"
+				"\x1a\xb1\x48\xdf\x53\xea\x81\x18"
+				"\x8c\x23\xba\x2e\xc5\x5c\xf3\x67"
+				"\xfe\x95\x09\xa0\x37\xce\x42\xd9"
+				"\x70\x07\x7b\x12\xa9\x1d\xb4\x4b"
+				"\xe2\x56\xed\x84\x1b\x8f\x26\xbd"
+				"\x31\xc8\x5f\xf6\x6a\x01\x98\x0c"
+				"\xa3\x3a\xd1\x45\xdc\x73\x0a\x7e"
+				"\x15\xac\x20\xb7\x4e\xe5\x59\xf0"
+				"\x87\x1e\x92\x29\xc0\x34\xcb\x62"
+				"\xf9\x6d\x04\x9b\x0f\xa6\x3d\xd4"
+				"\x48\xdf\x76\x0d\x81\x18\xaf\x23"
+				"\xba\x51\xe8\x5c\xf3\x8a\x21\x95"
+				"\x2c\xc3\x37\xce\x65\xfc\x70\x07"
+				"\x9e\x12\xa9\x40\xd7\x4b\xe2\x79"
+				"\x10\x84\x1b\xb2\x26\xbd\x54\xeb"
+				"\x5f\xf6\x8d\x01\x98\x2f\xc6\x3a"
+				"\xd1\x68\xff\x73\x0a\xa1\x15\xac"
+				"\x43\xda\x4e\xe5\x7c\x13\x87\x1e"
+				"\xb5\x29\xc0\x57\xee\x62\xf9\x90"
+				"\x04\x9b\x32\xc9\x3d\xd4\x6b\x02"
+				"\x76\x0d\xa4\x18\xaf\x46\xdd\x51"
+				"\xe8\x7f\x16\x8a\x21\xb8\x2c\xc3"
+				"\x5a\xf1\x65\xfc\x93\x07\x9e\x35"
+				"\xcc\x40\xd7\x6e\x05\x79\x10\xa7"
+				"\x1b\xb2\x49\xe0\x54\xeb\x82\x19"
+				"\x8d\x24\xbb\x2f\xc6\x5d\xf4\x68"
+				"\xff\x96\x0a\xa1\x38\xcf\x43\xda"
+				"\x71\x08\x7c\x13\xaa\x1e\xb5\x4c"
+				"\xe3\x57\xee\x85\x1c\x90\x27\xbe"
+				"\x32\xc9\x60\xf7\x6b\x02\x99\x0d"
+				"\xa4\x3b\xd2\x46\xdd\x74\x0b\x7f"
+				"\x16\xad\x21\xb8\x4f\xe6\x5a\xf1"
+				"\x88\x1f\x93\x2a\xc1\x35\xcc\x63"
+				"\xfa\x6e\x05\x9c\x10\xa7\x3e\xd5"
+				"\x49\xe0\x77\x0e\x82\x19\xb0\x24"
+				"\xbb\x52\xe9\x5d\xf4\x8b\x22\x96"
+				"\x2d\xc4\x38\xcf\x66\xfd\x71\x08"
+				"\x9f\x13\xaa\x41\xd8\x4c\xe3\x7a"
+				"\x11\x85\x1c\xb3\x27\xbe\x55\xec"
+				"\x60\xf7\x8e\x02\x99\x30\xc7\x3b"
+				"\xd2\x69\x00\x74\x0b\xa2\x16\xad"
+				"\x44\xdb\x4f\xe6\x7d\x14\x88\x1f"
+				"\xb6\x2a\xc1\x58\xef\x63\xfa\x91"
+				"\x05\x9c\x33\xca\x3e\xd5\x6c\x03"
+				"\x77\x0e\xa5\x19\xb0\x47\xde\x52"
+				"\xe9\x80\x17\x8b\x22\xb9\x2d\xc4"
+				"\x5b\xf2\x66\xfd\x94\x08\x9f\x36"
+				"\xcd\x41\xd8\x6f\x06\x7a\x11\xa8"
+				"\x1c\xb3\x4a\xe1\x55\xec\x83\x1a"
+				"\x8e\x25\xbc\x30\xc7\x5e\xf5\x69"
+				"\x00\x97\x0b\xa2\x39\xd0\x44\xdb"
+				"\x72\x09\x7d\x14\xab\x1f\xb6\x4d"
+				"\xe4\x58\xef\x86\x1d\x91\x28\xbf"
+				"\x33\xca\x61\xf8\x6c\x03\x9a\x0e"
+				"\xa5\x3c\xd3\x47\xde\x75\x0c\x80"
+				"\x17\xae\x22\xb9\x50\xe7\x5b\xf2"
+				"\x89\x20\x94\x2b\xc2\x36\xcd\x64"
+				"\xfb\x6f\x06\x9d\x11\xa8\x3f\xd6"
+				"\x4a\xe1\x78\x0f\x83\x1a\xb1\x25"
+				"\xbc\x53\xea\x5e\xf5\x8c\x00\x97"
+				"\x2e\xc5\x39\xd0\x67\xfe\x72\x09"
+				"\xa0\x14\xab\x42\xd9\x4d\xe4\x7b"
+				"\x12\x86\x1d\xb4\x28\xbf\x56\xed"
+				"\x61\xf8\x8f\x03\x9a\x31\xc8\x3c"
+				"\xd3\x6a\x01\x75\x0c\xa3\x17\xae"
+				"\x45\xdc\x50\xe7\x7e\x15\x89\x20"
+				"\xb7\x2b\xc2\x59\xf0\x64\xfb\x92"
+				"\x06\x9d\x34\xcb\x3f\xd6\x6d\x04"
+				"\x78\x0f\xa6\x1a\xb1\x48\xdf\x53"
+				"\xea\x81\x18\x8c\x23\xba\x2e\xc5"
+				"\x5c\xf3\x67\xfe\x95\x09\xa0\x37"
+				"\xce\x42\xd9\x70\x07\x7b\x12\xa9"
+				"\x1d\xb4\x4b\xe2\x56\xed\x84\x1b"
+				"\x8f\x26\xbd\x31\xc8\x5f\xf6\x6a"
+				"\x01\x98\x0c\xa3\x3a\xd1\x45\xdc"
+				"\x73\x0a\x7e\x15\xac\x20\xb7\x4e"
+				"\xe5\x59\xf0\x87\x1e\x92\x29\xc0"
+				"\x34\xcb\x62\xf9\x6d\x04\x9b\x0f"
+				"\xa6\x3d\xd4\x48\xdf\x76\x0d\x81"
+				"\x18\xaf\x23\xba\x51\xe8\x5c\xf3"
+				"\x8a\x21\x95\x2c\xc3\x37\xce\x65"
+				"\xfc\x70\x07\x9e\x12\xa9\x40\xd7"
+				"\x4b\xe2\x79\x10\x84\x1b\xb2\x26"
+				"\xbd\x54\xeb\x5f\xf6\x8d\x01\x98"
+				"\x2f\xc6\x3a\xd1\x68\xff\x73\x0a"
+				"\xa1\x15\xac\x43\xda\x4e\xe5\x7c"
+				"\x13\x87\x1e\xb5\x29\xc0\x57\xee"
+				"\x62\xf9\x90\x04\x9b\x32\xc9\x3d"
+				"\xd4\x6b\x02\x76\x0d\xa4\x18\xaf"
+				"\x46\xdd\x51\xe8\x7f\x16\x8a\x21"
+				"\xb8\x2c\xc3\x5a\xf1\x65\xfc\x93"
+				"\x07\x9e\x35\xcc\x40\xd7\x6e\x05"
+				"\x79\x10\xa7\x1b\xb2\x49\xe0\x54"
+				"\xeb\x82\x19\x8d\x24\xbb\x2f\xc6"
+				"\x5d\xf4\x68\xff\x96\x0a\xa1\x38"
+				"\xcf\x43\xda\x71\x08\x7c\x13\xaa"
+				"\x1e\xb5\x4c\xe3\x57\xee\x85\x1c"
+				"\x90\x27\xbe\x32\xc9\x60\xf7\x6b"
+				"\x02\x99\x0d\xa4\x3b\xd2\x46\xdd"
+				"\x74\x0b\x7f\x16\xad\x21\xb8\x4f"
+				"\xe6\x5a\xf1\x88\x1f\x93\x2a\xc1"
+				"\x35\xcc\x63\xfa\x6e\x05\x9c\x10"
+				"\xa7\x3e\xd5\x49\xe0\x77\x0e\x82"
+				"\x19\xb0\x24\xbb\x52\xe9\x5d\xf4"
+				"\x8b\x22\x96\x2d\xc4\x38\xcf\x66"
+				"\xfd\x71\x08\x9f\x13\xaa\x41\xd8"
+				"\x4c\xe3\x7a\x11\x85\x1c\xb3\x27"
+				"\xbe\x55\xec\x60\xf7\x8e\x02\x99"
+				"\x30\xc7\x3b\xd2\x69\x00\x74\x0b"
+				"\xa2\x16\xad\x44\xdb\x4f\xe6\x7d"
+				"\x14\x88\x1f\xb6\x2a\xc1\x58\xef"
+				"\x63\xfa\x91\x05\x9c\x33\xca\x3e"
+				"\xd5\x6c\x03\x77\x0e\xa5\x19\xb0"
+				"\x47\xde\x52\xe9\x80\x17\x8b\x22"
+				"\xb9\x2d\xc4\x5b\xf2\x66\xfd\x94"
+				"\x08\x9f\x36\xcd\x41\xd8\x6f\x06"
+				"\x7a\x11\xa8\x1c\xb3\x4a\xe1\x55"
+				"\xec\x83\x1a\x8e\x25\xbc\x30\xc7"
+				"\x5e\xf5\x69\x00\x97\x0b\xa2\x39"
+				"\xd0\x44\xdb\x72\x09\x7d\x14\xab"
+				"\x1f\xb6\x4d\xe4\x58\xef\x86\x1d"
+				"\x91\x28\xbf\x33\xca\x61\xf8\x6c"
+				"\x03\x9a\x0e\xa5\x3c\xd3\x47\xde"
+				"\x75\x0c\x80\x17\xae\x22\xb9\x50"
+				"\xe7\x5b\xf2\x89\x20\x94\x2b\xc2"
+				"\x36\xcd\x64\xfb\x6f\x06\x9d\x11"
+				"\xa8\x3f\xd6\x4a\xe1\x78\x0f\x83"
+				"\x1a\xb1\x25\xbc\x53\xea\x5e\xf5"
+				"\x8c\x00\x97\x2e\xc5\x39\xd0\x67"
+				"\xfe\x72\x09\xa0\x14\xab\x42\xd9"
+				"\x4d\xe4\x7b\x12\x86\x1d\xb4\x28"
+				"\xbf\x56\xed\x61\xf8\x8f\x03\x9a"
+				"\x31\xc8\x3c\xd3\x6a\x01\x75\x0c"
+				"\xa3\x17\xae\x45\xdc\x50\xe7\x7e"
+				"\x15\x89\x20\xb7\x2b\xc2\x59\xf0"
+				"\x64\xfb\x92\x06\x9d\x34\xcb\x3f"
+				"\xd6\x6d\x04\x78\x0f\xa6\x1a\xb1"
+				"\x48\xdf\x53\xea\x81\x18\x8c\x23"
+				"\xba\x2e\xc5\x5c\xf3\x67\xfe\x95"
+				"\x09\xa0\x37\xce\x42\xd9\x70\x07"
+				"\x7b\x12\xa9\x1d\xb4\x4b\xe2\x56"
+				"\xed\x84\x1b\x8f\x26\xbd\x31\xc8"
+				"\x5f\xf6\x6a\x01\x98\x0c\xa3\x3a"
+				"\xd1\x45\xdc\x73\x0a\x7e\x15\xac"
+				"\x20\xb7\x4e\xe5\x59\xf0\x87\x1e"
+				"\x92\x29\xc0\x34\xcb\x62\xf9\x6d"
+				"\x04\x9b\x0f\xa6\x3d\xd4\x48\xdf"
+				"\x76\x0d\x81\x18\xaf\x23\xba\x51"
+				"\xe8\x5c\xf3\x8a\x21\x95\x2c\xc3"
+				"\x37\xce\x65\xfc\x70\x07\x9e\x12"
+				"\xa9\x40\xd7\x4b\xe2\x79\x10\x84"
+				"\x1b\xb2\x26\xbd\x54\xeb\x5f\xf6"
+				"\x8d\x01\x98\x2f\xc6\x3a\xd1\x68"
+				"\xff\x73\x0a\xa1\x15\xac\x43\xda"
+				"\x4e\xe5\x7c\x13\x87\x1e\xb5\x29"
+				"\xc0\x57\xee\x62\xf9\x90\x04\x9b"
+				"\x32\xc9\x3d\xd4\x6b\x02\x76\x0d"
+				"\xa4\x18\xaf\x46\xdd\x51\xe8\x7f"
+				"\x16\x8a\x21\xb8\x2c\xc3\x5a\xf1"
+				"\x65\xfc\x93\x07\x9e\x35\xcc\x40"
+				"\xd7\x6e\x05\x79\x10\xa7\x1b\xb2"
+				"\x49\xe0\x54\xeb\x82\x19\x8d\x24"
+				"\xbb\x2f\xc6\x5d\xf4\x68\xff\x96"
+				"\x0a\xa1\x38\xcf\x43\xda\x71\x08"
+				"\x7c\x13\xaa\x1e\xb5\x4c\xe3\x57"
+				"\xee\x85\x1c\x90\x27\xbe\x32\xc9"
+				"\x60\xf7\x6b\x02\x99\x0d\xa4\x3b"
+				"\xd2\x46\xdd\x74\x0b\x7f\x16\xad"
+				"\x21\xb8\x4f\xe6\x5a\xf1\x88\x1f"
+				"\x93\x2a\xc1\x35\xcc\x63\xfa\x6e"
+				"\x05\x9c\x10\xa7\x3e\xd5\x49\xe0"
+				"\x77\x0e\x82\x19\xb0\x24\xbb\x52"
+				"\xe9\x5d\xf4\x8b\x22\x96\x2d\xc4"
+				"\x38\xcf\x66\xfd\x71\x08\x9f\x13"
+				"\xaa\x41\xd8\x4c\xe3\x7a\x11\x85"
+				"\x1c\xb3\x27\xbe\x55\xec\x60\xf7"
+				"\x8e\x02\x99\x30\xc7\x3b\xd2\x69"
+				"\x00\x74\x0b\xa2\x16\xad\x44\xdb"
+				"\x4f\xe6\x7d\x14\x88\x1f\xb6\x2a"
+				"\xc1\x58\xef\x63\xfa\x91\x05\x9c"
+				"\x33\xca\x3e\xd5\x6c\x03\x77\x0e"
+				"\xa5\x19\xb0\x47\xde\x52\xe9\x80"
+				"\x17\x8b\x22\xb9\x2d\xc4\x5b\xf2"
+				"\x66\xfd\x94\x08\x9f\x36\xcd\x41"
+				"\xd8\x6f\x06\x7a\x11\xa8\x1c\xb3"
+				"\x4a\xe1\x55\xec\x83\x1a\x8e\x25"
+				"\xbc\x30\xc7\x5e\xf5\x69\x00\x97"
+				"\x0b\xa2\x39\xd0\x44\xdb\x72\x09"
+				"\x7d\x14\xab\x1f\xb6\x4d\xe4\x58"
+				"\xef\x86\x1d\x91\x28\xbf\x33\xca"
+				"\x61\xf8\x6c\x03\x9a\x0e\xa5\x3c"
+				"\xd3\x47\xde\x75\x0c\x80\x17\xae"
+				"\x22\xb9\x50\xe7\x5b\xf2\x89\x20"
+				"\x94\x2b\xc2\x36\xcd\x64\xfb\x6f"
+				"\x06\x9d\x11\xa8\x3f\xd6\x4a\xe1"
+				"\x78\x0f\x83\x1a\xb1\x25\xbc\x53"
+				"\xea\x5e\xf5\x8c\x00\x97\x2e\xc5"
+				"\x39\xd0\x67\xfe\x72\x09\xa0\x14"
+				"\xab\x42\xd9\x4d\xe4\x7b\x12\x86"
+				"\x1d\xb4\x28\xbf\x56\xed\x61\xf8"
+				"\x8f\x03\x9a\x31\xc8\x3c\xd3\x6a"
+				"\x01\x75\x0c\xa3\x17\xae\x45\xdc"
+				"\x50\xe7\x7e\x15\x89\x20\xb7\x2b"
+				"\xc2\x59\xf0\x64\xfb\x92\x06\x9d"
+				"\x34\xcb\x3f\xd6\x6d\x04\x78\x0f"
+				"\xa6\x1a\xb1\x48\xdf\x53\xea\x81"
+				"\x18\x8c\x23\xba\x2e\xc5\x5c\xf3"
+				"\x67\xfe\x95\x09\xa0\x37\xce\x42"
+				"\xd9\x70\x07\x7b\x12\xa9\x1d\xb4"
+				"\x4b\xe2\x56\xed\x84\x1b\x8f\x26"
+				"\xbd\x31\xc8\x5f\xf6\x6a\x01\x98",
+		.psize = 2048,
+		.digest = "\xfb\x3a\x7a\xda",
+	}
+};
+
+/*
  * CRC32C test vectors
  */
 #define CRC32C_TEST_VECTORS 15
diff --git a/crypto/zlib.c b/crypto/zlib.c
index 0eefa9d237ac..d51a30a29e42 100644
--- a/crypto/zlib.c
+++ b/crypto/zlib.c
@@ -78,7 +78,7 @@ static void zlib_exit(struct crypto_tfm *tfm)
 }
 
 
-static int zlib_compress_setup(struct crypto_pcomp *tfm, void *params,
+static int zlib_compress_setup(struct crypto_pcomp *tfm, const void *params,
 			       unsigned int len)
 {
 	struct zlib_ctx *ctx = crypto_tfm_ctx(crypto_pcomp_tfm(tfm));
@@ -209,7 +209,7 @@ static int zlib_compress_final(struct crypto_pcomp *tfm,
 }
 
 
-static int zlib_decompress_setup(struct crypto_pcomp *tfm, void *params,
+static int zlib_decompress_setup(struct crypto_pcomp *tfm, const void *params,
 				 unsigned int len)
 {
 	struct zlib_ctx *ctx = crypto_tfm_ctx(crypto_pcomp_tfm(tfm));
diff --git a/drivers/acpi/acpi_pad.c b/drivers/acpi/acpi_pad.c
index 6bc9cbc01ad6..00b39802d7ec 100644
--- a/drivers/acpi/acpi_pad.c
+++ b/drivers/acpi/acpi_pad.c
@@ -105,7 +105,7 @@ static void round_robin_cpu(unsigned int tsk_index)
 	mutex_lock(&round_robin_lock);
 	cpumask_clear(tmp);
 	for_each_cpu(cpu, pad_busy_cpus)
-		cpumask_or(tmp, tmp, topology_thread_cpumask(cpu));
+		cpumask_or(tmp, tmp, topology_sibling_cpumask(cpu));
 	cpumask_andnot(tmp, cpu_online_mask, tmp);
 	/* avoid HT sibilings if possible */
 	if (cpumask_empty(tmp))
diff --git a/drivers/acpi/apei/erst.c b/drivers/acpi/apei/erst.c
index ed65e9c4b5b0..3670bbab57a3 100644
--- a/drivers/acpi/apei/erst.c
+++ b/drivers/acpi/apei/erst.c
@@ -35,6 +35,7 @@
 #include <linux/nmi.h>
 #include <linux/hardirq.h>
 #include <linux/pstore.h>
+#include <linux/vmalloc.h>
 #include <acpi/apei.h>
 
 #include "apei-internal.h"
diff --git a/drivers/acpi/pci_irq.c b/drivers/acpi/pci_irq.c
index 03e4b6c49c6d..304eccb0ae5c 100644
--- a/drivers/acpi/pci_irq.c
+++ b/drivers/acpi/pci_irq.c
@@ -162,7 +162,7 @@ static int acpi_pci_irq_check_entry(acpi_handle handle, struct pci_dev *dev,
 {
 	int segment = pci_domain_nr(dev->bus);
 	int bus = dev->bus->number;
-	int device = PCI_SLOT(dev->devfn);
+	int device = pci_ari_enabled(dev->bus) ? 0 : PCI_SLOT(dev->devfn);
 	struct acpi_prt_entry *entry;
 
 	if (((prt->address >> 16) & 0xffff) != device ||
diff --git a/drivers/base/topology.c b/drivers/base/topology.c
index 6491f45200a7..8b7d7f8e5851 100644
--- a/drivers/base/topology.c
+++ b/drivers/base/topology.c
@@ -61,7 +61,7 @@ static DEVICE_ATTR_RO(physical_package_id);
 define_id_show_func(core_id);
 static DEVICE_ATTR_RO(core_id);
 
-define_siblings_show_func(thread_siblings, thread_cpumask);
+define_siblings_show_func(thread_siblings, sibling_cpumask);
 static DEVICE_ATTR_RO(thread_siblings);
 static DEVICE_ATTR_RO(thread_siblings_list);
 
diff --git a/drivers/block/pmem.c b/drivers/block/pmem.c
index eabf4a8d0085..095dfaadcaa5 100644
--- a/drivers/block/pmem.c
+++ b/drivers/block/pmem.c
@@ -139,11 +139,11 @@ static struct pmem_device *pmem_alloc(struct device *dev, struct resource *res)
 	}
 
 	/*
-	 * Map the memory as non-cachable, as we can't write back the contents
+	 * Map the memory as write-through, as we can't write back the contents
 	 * of the CPU caches in case of a crash.
 	 */
 	err = -ENOMEM;
-	pmem->virt_addr = ioremap_nocache(pmem->phys_addr, pmem->size);
+	pmem->virt_addr = ioremap_wt(pmem->phys_addr, pmem->size);
 	if (!pmem->virt_addr)
 		goto out_release_region;
 
diff --git a/drivers/bus/mvebu-mbus.c b/drivers/bus/mvebu-mbus.c
index 6f047dcb94c2..c43c3d2baf73 100644
--- a/drivers/bus/mvebu-mbus.c
+++ b/drivers/bus/mvebu-mbus.c
@@ -57,6 +57,7 @@
 #include <linux/of_address.h>
 #include <linux/debugfs.h>
 #include <linux/log2.h>
+#include <linux/memblock.h>
 #include <linux/syscore_ops.h>
 
 /*
@@ -152,13 +153,39 @@ struct mvebu_mbus_state {
 
 static struct mvebu_mbus_state mbus_state;
 
+/*
+ * We provide two variants of the mv_mbus_dram_info() function:
+ *
+ * - The normal one, where the described DRAM ranges may overlap with
+ *   the I/O windows, but for which the DRAM ranges are guaranteed to
+ *   have a power of two size. Such ranges are suitable for the DMA
+ *   masters that only DMA between the RAM and the device, which is
+ *   actually all devices except the crypto engines.
+ *
+ * - The 'nooverlap' one, where the described DRAM ranges are
+ *   guaranteed to not overlap with the I/O windows, but for which the
+ *   DRAM ranges will not have power of two sizes. They will only be
+ *   aligned on a 64 KB boundary, and have a size multiple of 64
+ *   KB. Such ranges are suitable for the DMA masters that DMA between
+ *   the crypto SRAM (which is mapped through an I/O window) and a
+ *   device. This is the case for the crypto engines.
+ */
+
 static struct mbus_dram_target_info mvebu_mbus_dram_info;
+static struct mbus_dram_target_info mvebu_mbus_dram_info_nooverlap;
+
 const struct mbus_dram_target_info *mv_mbus_dram_info(void)
 {
 	return &mvebu_mbus_dram_info;
 }
 EXPORT_SYMBOL_GPL(mv_mbus_dram_info);
 
+const struct mbus_dram_target_info *mv_mbus_dram_info_nooverlap(void)
+{
+	return &mvebu_mbus_dram_info_nooverlap;
+}
+EXPORT_SYMBOL_GPL(mv_mbus_dram_info_nooverlap);
+
 /* Checks whether the given window has remap capability */
 static bool mvebu_mbus_window_is_remappable(struct mvebu_mbus_state *mbus,
 					    const int win)
@@ -576,6 +603,95 @@ static unsigned int armada_xp_mbus_win_remap_offset(int win)
 		return MVEBU_MBUS_NO_REMAP;
 }
 
+/*
+ * Use the memblock information to find the MBus bridge hole in the
+ * physical address space.
+ */
+static void __init
+mvebu_mbus_find_bridge_hole(uint64_t *start, uint64_t *end)
+{
+	struct memblock_region *r;
+	uint64_t s = 0;
+
+	for_each_memblock(memory, r) {
+		/*
+		 * This part of the memory is above 4 GB, so we don't
+		 * care for the MBus bridge hole.
+		 */
+		if (r->base >= 0x100000000ULL)
+			continue;
+
+		/*
+		 * The MBus bridge hole is at the end of the RAM under
+		 * the 4 GB limit.
+		 */
+		if (r->base + r->size > s)
+			s = r->base + r->size;
+	}
+
+	*start = s;
+	*end = 0x100000000ULL;
+}
+
+/*
+ * This function fills in the mvebu_mbus_dram_info_nooverlap data
+ * structure, by looking at the mvebu_mbus_dram_info data, and
+ * removing the parts of it that overlap with I/O windows.
+ */
+static void __init
+mvebu_mbus_setup_cpu_target_nooverlap(struct mvebu_mbus_state *mbus)
+{
+	uint64_t mbus_bridge_base, mbus_bridge_end;
+	int cs_nooverlap = 0;
+	int i;
+
+	mvebu_mbus_find_bridge_hole(&mbus_bridge_base, &mbus_bridge_end);
+
+	for (i = 0; i < mvebu_mbus_dram_info.num_cs; i++) {
+		struct mbus_dram_window *w;
+		u64 base, size, end;
+
+		w = &mvebu_mbus_dram_info.cs[i];
+		base = w->base;
+		size = w->size;
+		end = base + size;
+
+		/*
+		 * The CS is fully enclosed inside the MBus bridge
+		 * area, so ignore it.
+		 */
+		if (base >= mbus_bridge_base && end <= mbus_bridge_end)
+			continue;
+
+		/*
+		 * Beginning of CS overlaps with end of MBus, raise CS
+		 * base address, and shrink its size.
+		 */
+		if (base >= mbus_bridge_base && end > mbus_bridge_end) {
+			size -= mbus_bridge_end - base;
+			base = mbus_bridge_end;
+		}
+
+		/*
+		 * End of CS overlaps with beginning of MBus, shrink
+		 * CS size.
+		 */
+		if (base < mbus_bridge_base && end > mbus_bridge_base)
+			size -= end - mbus_bridge_base;
+
+		w = &mvebu_mbus_dram_info_nooverlap.cs[cs_nooverlap++];
+		w->cs_index = i;
+		w->mbus_attr = 0xf & ~(1 << i);
+		if (mbus->hw_io_coherency)
+			w->mbus_attr |= ATTR_HW_COHERENCY;
+		w->base = base;
+		w->size = size;
+	}
+
+	mvebu_mbus_dram_info_nooverlap.mbus_dram_target_id = TARGET_DDR;
+	mvebu_mbus_dram_info_nooverlap.num_cs = cs_nooverlap;
+}
+
 static void __init
 mvebu_mbus_default_setup_cpu_target(struct mvebu_mbus_state *mbus)
 {
@@ -964,6 +1080,7 @@ static int __init mvebu_mbus_common_init(struct mvebu_mbus_state *mbus,
 		mvebu_mbus_disable_window(mbus, win);
 
 	mbus->soc->setup_cpu_target(mbus);
+	mvebu_mbus_setup_cpu_target_nooverlap(mbus);
 
 	if (is_coherent)
 		writel(UNIT_SYNC_BARRIER_ALL,
diff --git a/drivers/char/hw_random/via-rng.c b/drivers/char/hw_random/via-rng.c
index a3bebef255ad..0c98a9d51a24 100644
--- a/drivers/char/hw_random/via-rng.c
+++ b/drivers/char/hw_random/via-rng.c
@@ -33,7 +33,7 @@
 #include <asm/io.h>
 #include <asm/msr.h>
 #include <asm/cpufeature.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 
 
 
diff --git a/drivers/char/pcmcia/cm4040_cs.c b/drivers/char/pcmcia/cm4040_cs.c
index 8dd48a2be911..fc061f7c2bd1 100644
--- a/drivers/char/pcmcia/cm4040_cs.c
+++ b/drivers/char/pcmcia/cm4040_cs.c
@@ -532,9 +532,8 @@ static int reader_config(struct pcmcia_device *link, int devno)
 
 	fail_rc = pcmcia_enable_device(link);
 	if (fail_rc != 0) {
-		dev_printk(KERN_INFO, &link->dev,
-			   "pcmcia_enable_device failed 0x%x\n",
-			   fail_rc);
+		dev_info(&link->dev, "pcmcia_enable_device failed 0x%x\n",
+			 fail_rc);
 		goto cs_release;
 	}
 
diff --git a/drivers/char/random.c b/drivers/char/random.c
index 9cd6968e2f92..d0da5d852d41 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -409,6 +409,9 @@ static DECLARE_WAIT_QUEUE_HEAD(random_write_wait);
 static DECLARE_WAIT_QUEUE_HEAD(urandom_init_wait);
 static struct fasync_struct *fasync;
 
+static DEFINE_SPINLOCK(random_ready_list_lock);
+static LIST_HEAD(random_ready_list);
+
 /**********************************************************************
  *
  * OS independent entropy store.   Here are the functions which handle
@@ -589,6 +592,22 @@ static void fast_mix(struct fast_pool *f)
 	f->count++;
 }
 
+static void process_random_ready_list(void)
+{
+	unsigned long flags;
+	struct random_ready_callback *rdy, *tmp;
+
+	spin_lock_irqsave(&random_ready_list_lock, flags);
+	list_for_each_entry_safe(rdy, tmp, &random_ready_list, list) {
+		struct module *owner = rdy->owner;
+
+		list_del_init(&rdy->list);
+		rdy->func(rdy);
+		module_put(owner);
+	}
+	spin_unlock_irqrestore(&random_ready_list_lock, flags);
+}
+
 /*
  * Credit (or debit) the entropy store with n bits of entropy.
  * Use credit_entropy_bits_safe() if the value comes from userspace
@@ -660,7 +679,8 @@ retry:
 		r->entropy_total = 0;
 		if (r == &nonblocking_pool) {
 			prandom_reseed_late();
-			wake_up_interruptible(&urandom_init_wait);
+			process_random_ready_list();
+			wake_up_all(&urandom_init_wait);
 			pr_notice("random: %s pool is initialized\n", r->name);
 		}
 	}
@@ -1245,6 +1265,64 @@ void get_random_bytes(void *buf, int nbytes)
 EXPORT_SYMBOL(get_random_bytes);
 
 /*
+ * Add a callback function that will be invoked when the nonblocking
+ * pool is initialised.
+ *
+ * returns: 0 if callback is successfully added
+ *	    -EALREADY if pool is already initialised (callback not called)
+ *	    -ENOENT if module for callback is not alive
+ */
+int add_random_ready_callback(struct random_ready_callback *rdy)
+{
+	struct module *owner;
+	unsigned long flags;
+	int err = -EALREADY;
+
+	if (likely(nonblocking_pool.initialized))
+		return err;
+
+	owner = rdy->owner;
+	if (!try_module_get(owner))
+		return -ENOENT;
+
+	spin_lock_irqsave(&random_ready_list_lock, flags);
+	if (nonblocking_pool.initialized)
+		goto out;
+
+	owner = NULL;
+
+	list_add(&rdy->list, &random_ready_list);
+	err = 0;
+
+out:
+	spin_unlock_irqrestore(&random_ready_list_lock, flags);
+
+	module_put(owner);
+
+	return err;
+}
+EXPORT_SYMBOL(add_random_ready_callback);
+
+/*
+ * Delete a previously registered readiness callback function.
+ */
+void del_random_ready_callback(struct random_ready_callback *rdy)
+{
+	unsigned long flags;
+	struct module *owner = NULL;
+
+	spin_lock_irqsave(&random_ready_list_lock, flags);
+	if (!list_empty(&rdy->list)) {
+		list_del_init(&rdy->list);
+		owner = rdy->owner;
+	}
+	spin_unlock_irqrestore(&random_ready_list_lock, flags);
+
+	module_put(owner);
+}
+EXPORT_SYMBOL(del_random_ready_callback);
+
+/*
  * This function will use the architecture-specific hardware random
  * number generator if it is available.  The arch-specific hw RNG will
  * almost certainly be faster than what we can do in software, but it
diff --git a/drivers/clk/at91/clk-peripheral.c b/drivers/clk/at91/clk-peripheral.c
index 597fed423d7d..df2c1afa52b4 100644
--- a/drivers/clk/at91/clk-peripheral.c
+++ b/drivers/clk/at91/clk-peripheral.c
@@ -29,7 +29,7 @@
 #define PERIPHERAL_RSHIFT_MASK	0x3
 #define PERIPHERAL_RSHIFT(val)	(((val) >> 16) & PERIPHERAL_RSHIFT_MASK)
 
-#define PERIPHERAL_MAX_SHIFT	4
+#define PERIPHERAL_MAX_SHIFT	3
 
 struct clk_peripheral {
 	struct clk_hw hw;
@@ -242,7 +242,7 @@ static long clk_sam9x5_peripheral_round_rate(struct clk_hw *hw,
 		return *parent_rate;
 
 	if (periph->range.max) {
-		for (; shift < PERIPHERAL_MAX_SHIFT; shift++) {
+		for (; shift <= PERIPHERAL_MAX_SHIFT; shift++) {
 			cur_rate = *parent_rate >> shift;
 			if (cur_rate <= periph->range.max)
 				break;
@@ -254,7 +254,7 @@ static long clk_sam9x5_peripheral_round_rate(struct clk_hw *hw,
 
 	best_diff = cur_rate - rate;
 	best_rate = cur_rate;
-	for (; shift < PERIPHERAL_MAX_SHIFT; shift++) {
+	for (; shift <= PERIPHERAL_MAX_SHIFT; shift++) {
 		cur_rate = *parent_rate >> shift;
 		if (cur_rate < rate)
 			cur_diff = rate - cur_rate;
@@ -289,7 +289,7 @@ static int clk_sam9x5_peripheral_set_rate(struct clk_hw *hw,
 	if (periph->range.max && rate > periph->range.max)
 		return -EINVAL;
 
-	for (shift = 0; shift < PERIPHERAL_MAX_SHIFT; shift++) {
+	for (shift = 0; shift <= PERIPHERAL_MAX_SHIFT; shift++) {
 		if (parent_rate >> shift == rate) {
 			periph->auto_div = false;
 			periph->div = shift;
diff --git a/drivers/clk/at91/clk-pll.c b/drivers/clk/at91/clk-pll.c
index 6ec79dbc0840..cbbe40377ad6 100644
--- a/drivers/clk/at91/clk-pll.c
+++ b/drivers/clk/at91/clk-pll.c
@@ -173,8 +173,7 @@ static long clk_pll_get_best_div_mul(struct clk_pll *pll, unsigned long rate,
 	int i = 0;
 
 	/* Check if parent_rate is a valid input rate */
-	if (parent_rate < characteristics->input.min ||
-	    parent_rate > characteristics->input.max)
+	if (parent_rate < characteristics->input.min)
 		return -ERANGE;
 
 	/*
@@ -187,6 +186,15 @@ static long clk_pll_get_best_div_mul(struct clk_pll *pll, unsigned long rate,
 	if (!mindiv)
 		mindiv = 1;
 
+	if (parent_rate > characteristics->input.max) {
+		tmpdiv = DIV_ROUND_UP(parent_rate, characteristics->input.max);
+		if (tmpdiv > PLL_DIV_MAX)
+			return -ERANGE;
+
+		if (tmpdiv > mindiv)
+			mindiv = tmpdiv;
+	}
+
 	/*
 	 * Calculate the maximum divider which is limited by PLL register
 	 * layout (limited by the MUL or DIV field size).
diff --git a/drivers/clk/at91/pmc.h b/drivers/clk/at91/pmc.h
index 69abb08cf146..eb8e5dc9076d 100644
--- a/drivers/clk/at91/pmc.h
+++ b/drivers/clk/at91/pmc.h
@@ -121,7 +121,7 @@ extern void __init of_at91sam9x5_clk_smd_setup(struct device_node *np,
 					       struct at91_pmc *pmc);
 #endif
 
-#if defined(CONFIG_HAVE_AT91_SMD)
+#if defined(CONFIG_HAVE_AT91_H32MX)
 extern void __init of_sama5d4_clk_h32mx_setup(struct device_node *np,
 					      struct at91_pmc *pmc);
 #endif
diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig
index 51d7865fdddb..32164ba3d36a 100644
--- a/drivers/clocksource/Kconfig
+++ b/drivers/clocksource/Kconfig
@@ -106,6 +106,16 @@ config CLKSRC_EFM32
 	  Support to use the timers of EFM32 SoCs as clock source and clock
 	  event device.
 
+config CLKSRC_LPC32XX
+	bool
+	select CLKSRC_MMIO
+	select CLKSRC_OF
+
+config CLKSRC_STM32
+	bool "Clocksource for STM32 SoCs" if !ARCH_STM32
+	depends on OF && ARM && (ARCH_STM32 || COMPILE_TEST)
+	select CLKSRC_MMIO
+
 config ARM_ARCH_TIMER
 	bool
 	select CLKSRC_OF if OF
@@ -139,6 +149,13 @@ config CLKSRC_ARM_GLOBAL_TIMER_SCHED_CLOCK
 	help
 	 Use ARM global timer clock source as sched_clock
 
+config ARMV7M_SYSTICK
+	bool
+	select CLKSRC_OF if OF
+	select CLKSRC_MMIO
+	help
+	  This options enables support for the ARMv7M system timer unit
+
 config ATMEL_PIT
 	select CLKSRC_OF if OF
 	def_bool SOC_AT91SAM9 || SOC_SAMA5
diff --git a/drivers/clocksource/Makefile b/drivers/clocksource/Makefile
index 5b85f6adb258..1831a588b988 100644
--- a/drivers/clocksource/Makefile
+++ b/drivers/clocksource/Makefile
@@ -36,7 +36,9 @@ obj-$(CONFIG_ARCH_NSPIRE)	+= zevio-timer.o
 obj-$(CONFIG_ARCH_BCM_MOBILE)	+= bcm_kona_timer.o
 obj-$(CONFIG_CADENCE_TTC_TIMER)	+= cadence_ttc_timer.o
 obj-$(CONFIG_CLKSRC_EFM32)	+= time-efm32.o
+obj-$(CONFIG_CLKSRC_STM32)	+= timer-stm32.o
 obj-$(CONFIG_CLKSRC_EXYNOS_MCT)	+= exynos_mct.o
+obj-$(CONFIG_CLKSRC_LPC32XX)	+= time-lpc32xx.o
 obj-$(CONFIG_CLKSRC_SAMSUNG_PWM)	+= samsung_pwm_timer.o
 obj-$(CONFIG_FSL_FTM_TIMER)	+= fsl_ftm_timer.o
 obj-$(CONFIG_VF_PIT_TIMER)	+= vf_pit_timer.o
@@ -45,6 +47,7 @@ obj-$(CONFIG_MTK_TIMER)		+= mtk_timer.o
 
 obj-$(CONFIG_ARM_ARCH_TIMER)		+= arm_arch_timer.o
 obj-$(CONFIG_ARM_GLOBAL_TIMER)		+= arm_global_timer.o
+obj-$(CONFIG_ARMV7M_SYSTICK)		+= armv7m_systick.o
 obj-$(CONFIG_CLKSRC_METAG_GENERIC)	+= metag_generic.o
 obj-$(CONFIG_ARCH_HAS_TICK_BROADCAST)	+= dummy_timer.o
 obj-$(CONFIG_ARCH_KEYSTONE)		+= timer-keystone.o
diff --git a/drivers/clocksource/armv7m_systick.c b/drivers/clocksource/armv7m_systick.c
new file mode 100644
index 000000000000..addfd2c64f54
--- /dev/null
+++ b/drivers/clocksource/armv7m_systick.c
@@ -0,0 +1,79 @@
+/*
+ * Copyright (C) Maxime Coquelin 2015
+ * Author:  Maxime Coquelin <mcoquelin.stm32@gmail.com>
+ * License terms:  GNU General Public License (GPL), version 2
+ */
+
+#include <linux/kernel.h>
+#include <linux/clocksource.h>
+#include <linux/clockchips.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/clk.h>
+#include <linux/bitops.h>
+
+#define SYST_CSR	0x00
+#define SYST_RVR	0x04
+#define SYST_CVR	0x08
+#define SYST_CALIB	0x0c
+
+#define SYST_CSR_ENABLE BIT(0)
+
+#define SYSTICK_LOAD_RELOAD_MASK 0x00FFFFFF
+
+static void __init system_timer_of_register(struct device_node *np)
+{
+	struct clk *clk = NULL;
+	void __iomem *base;
+	u32 rate;
+	int ret;
+
+	base = of_iomap(np, 0);
+	if (!base) {
+		pr_warn("system-timer: invalid base address\n");
+		return;
+	}
+
+	ret = of_property_read_u32(np, "clock-frequency", &rate);
+	if (ret) {
+		clk = of_clk_get(np, 0);
+		if (IS_ERR(clk))
+			goto out_unmap;
+
+		ret = clk_prepare_enable(clk);
+		if (ret)
+			goto out_clk_put;
+
+		rate = clk_get_rate(clk);
+		if (!rate)
+			goto out_clk_disable;
+	}
+
+	writel_relaxed(SYSTICK_LOAD_RELOAD_MASK, base + SYST_RVR);
+	writel_relaxed(SYST_CSR_ENABLE, base + SYST_CSR);
+
+	ret = clocksource_mmio_init(base + SYST_CVR, "arm_system_timer", rate,
+			200, 24, clocksource_mmio_readl_down);
+	if (ret) {
+		pr_err("failed to init clocksource (%d)\n", ret);
+		if (clk)
+			goto out_clk_disable;
+		else
+			goto out_unmap;
+	}
+
+	pr_info("ARM System timer initialized as clocksource\n");
+
+	return;
+
+out_clk_disable:
+	clk_disable_unprepare(clk);
+out_clk_put:
+	clk_put(clk);
+out_unmap:
+	iounmap(base);
+	pr_warn("ARM System timer register failed (%d)\n", ret);
+}
+
+CLOCKSOURCE_OF_DECLARE(arm_systick, "arm,armv7m-systick",
+			system_timer_of_register);
diff --git a/drivers/clocksource/asm9260_timer.c b/drivers/clocksource/asm9260_timer.c
index 2c9c993727c8..4c2ba59897e8 100644
--- a/drivers/clocksource/asm9260_timer.c
+++ b/drivers/clocksource/asm9260_timer.c
@@ -178,7 +178,7 @@ static void __init asm9260_timer_init(struct device_node *np)
 	unsigned long rate;
 
 	priv.base = of_io_request_and_map(np, 0, np->name);
-	if (!priv.base)
+	if (IS_ERR(priv.base))
 		panic("%s: unable to map resource", np->name);
 
 	clk = of_clk_get(np, 0);
diff --git a/drivers/clocksource/exynos_mct.c b/drivers/clocksource/exynos_mct.c
index 83564c9cfdbe..935b05936dbd 100644
--- a/drivers/clocksource/exynos_mct.c
+++ b/drivers/clocksource/exynos_mct.c
@@ -209,7 +209,7 @@ static void exynos4_frc_resume(struct clocksource *cs)
 	exynos4_mct_frc_start();
 }
 
-struct clocksource mct_frc = {
+static struct clocksource mct_frc = {
 	.name		= "mct-frc",
 	.rating		= 400,
 	.read		= exynos4_frc_read,
@@ -413,7 +413,7 @@ static inline void exynos4_tick_set_mode(enum clock_event_mode mode,
 	}
 }
 
-static int exynos4_mct_tick_clear(struct mct_clock_event_device *mevt)
+static void exynos4_mct_tick_clear(struct mct_clock_event_device *mevt)
 {
 	struct clock_event_device *evt = &mevt->evt;
 
@@ -426,12 +426,8 @@ static int exynos4_mct_tick_clear(struct mct_clock_event_device *mevt)
 		exynos4_mct_tick_stop(mevt);
 
 	/* Clear the MCT tick interrupt */
-	if (readl_relaxed(reg_base + mevt->base + MCT_L_INT_CSTAT_OFFSET) & 1) {
+	if (readl_relaxed(reg_base + mevt->base + MCT_L_INT_CSTAT_OFFSET) & 1)
 		exynos4_mct_write(0x1, mevt->base + MCT_L_INT_CSTAT_OFFSET);
-		return 1;
-	} else {
-		return 0;
-	}
 }
 
 static irqreturn_t exynos4_mct_tick_isr(int irq, void *dev_id)
@@ -564,18 +560,6 @@ out_irq:
 	free_percpu_irq(mct_irqs[MCT_L0_IRQ], &percpu_mct_tick);
 }
 
-void __init mct_init(void __iomem *base, int irq_g0, int irq_l0, int irq_l1)
-{
-	mct_irqs[MCT_G0_IRQ] = irq_g0;
-	mct_irqs[MCT_L0_IRQ] = irq_l0;
-	mct_irqs[MCT_L1_IRQ] = irq_l1;
-	mct_int_type = MCT_INT_SPI;
-
-	exynos4_timer_resources(NULL, base);
-	exynos4_clocksource_init();
-	exynos4_clockevent_init();
-}
-
 static void __init mct_init_dt(struct device_node *np, unsigned int int_type)
 {
 	u32 nr_irqs, i;
diff --git a/drivers/clocksource/qcom-timer.c b/drivers/clocksource/qcom-timer.c
index 098c542e5c53..cba2d015564c 100644
--- a/drivers/clocksource/qcom-timer.c
+++ b/drivers/clocksource/qcom-timer.c
@@ -40,8 +40,6 @@
 
 #define GPT_HZ 32768
 
-#define MSM_DGT_SHIFT 5
-
 static void __iomem *event_base;
 static void __iomem *sts_base;
 
@@ -232,7 +230,6 @@ err:
 	register_current_timer_delay(&msm_delay_timer);
 }
 
-#ifdef CONFIG_ARCH_QCOM
 static void __init msm_dt_timer_init(struct device_node *np)
 {
 	u32 freq;
@@ -285,59 +282,3 @@ static void __init msm_dt_timer_init(struct device_node *np)
 }
 CLOCKSOURCE_OF_DECLARE(kpss_timer, "qcom,kpss-timer", msm_dt_timer_init);
 CLOCKSOURCE_OF_DECLARE(scss_timer, "qcom,scss-timer", msm_dt_timer_init);
-#else
-
-static int __init msm_timer_map(phys_addr_t addr, u32 event, u32 source,
-				u32 sts)
-{
-	void __iomem *base;
-
-	base = ioremap(addr, SZ_256);
-	if (!base) {
-		pr_err("Failed to map timer base\n");
-		return -ENOMEM;
-	}
-	event_base = base + event;
-	source_base = base + source;
-	if (sts)
-		sts_base = base + sts;
-
-	return 0;
-}
-
-static notrace cycle_t msm_read_timer_count_shift(struct clocksource *cs)
-{
-	/*
-	 * Shift timer count down by a constant due to unreliable lower bits
-	 * on some targets.
-	 */
-	return msm_read_timer_count(cs) >> MSM_DGT_SHIFT;
-}
-
-void __init msm7x01_timer_init(void)
-{
-	struct clocksource *cs = &msm_clocksource;
-
-	if (msm_timer_map(0xc0100000, 0x0, 0x10, 0x0))
-		return;
-	cs->read = msm_read_timer_count_shift;
-	cs->mask = CLOCKSOURCE_MASK((32 - MSM_DGT_SHIFT));
-	/* 600 KHz */
-	msm_timer_init(19200000 >> MSM_DGT_SHIFT, 32 - MSM_DGT_SHIFT, 7,
-			false);
-}
-
-void __init msm7x30_timer_init(void)
-{
-	if (msm_timer_map(0xc0100000, 0x4, 0x24, 0x80))
-		return;
-	msm_timer_init(24576000 / 4, 32, 1, false);
-}
-
-void __init qsd8x50_timer_init(void)
-{
-	if (msm_timer_map(0xAC100000, 0x0, 0x10, 0x34))
-		return;
-	msm_timer_init(19200000 / 4, 32, 7, false);
-}
-#endif
diff --git a/drivers/clocksource/time-lpc32xx.c b/drivers/clocksource/time-lpc32xx.c
new file mode 100644
index 000000000000..a1c06a2bc77c
--- /dev/null
+++ b/drivers/clocksource/time-lpc32xx.c
@@ -0,0 +1,272 @@
+/*
+ * Clocksource driver for NXP LPC32xx/18xx/43xx timer
+ *
+ * Copyright (C) 2015 Joachim Eastwood <manabian@gmail.com>
+ *
+ * Based on:
+ * time-efm32 Copyright (C) 2013 Pengutronix
+ * mach-lpc32xx/timer.c Copyright (C) 2009 - 2010 NXP Semiconductors
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ *
+ */
+
+#define pr_fmt(fmt) "%s: " fmt, __func__
+
+#include <linux/clk.h>
+#include <linux/clockchips.h>
+#include <linux/clocksource.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/kernel.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/sched_clock.h>
+
+#define LPC32XX_TIMER_IR		0x000
+#define  LPC32XX_TIMER_IR_MR0INT	BIT(0)
+#define LPC32XX_TIMER_TCR		0x004
+#define  LPC32XX_TIMER_TCR_CEN		BIT(0)
+#define  LPC32XX_TIMER_TCR_CRST		BIT(1)
+#define LPC32XX_TIMER_TC		0x008
+#define LPC32XX_TIMER_PR		0x00c
+#define LPC32XX_TIMER_MCR		0x014
+#define  LPC32XX_TIMER_MCR_MR0I		BIT(0)
+#define  LPC32XX_TIMER_MCR_MR0R		BIT(1)
+#define  LPC32XX_TIMER_MCR_MR0S		BIT(2)
+#define LPC32XX_TIMER_MR0		0x018
+#define LPC32XX_TIMER_CTCR		0x070
+
+struct lpc32xx_clock_event_ddata {
+	struct clock_event_device evtdev;
+	void __iomem *base;
+};
+
+/* Needed for the sched clock */
+static void __iomem *clocksource_timer_counter;
+
+static u64 notrace lpc32xx_read_sched_clock(void)
+{
+	return readl(clocksource_timer_counter);
+}
+
+static int lpc32xx_clkevt_next_event(unsigned long delta,
+				     struct clock_event_device *evtdev)
+{
+	struct lpc32xx_clock_event_ddata *ddata =
+		container_of(evtdev, struct lpc32xx_clock_event_ddata, evtdev);
+
+	/*
+	 * Place timer in reset and program the delta in the prescale
+	 * register (PR). When the prescale counter matches the value
+	 * in PR the counter register is incremented and the compare
+	 * match will trigger. After setup the timer is released from
+	 * reset and enabled.
+	 */
+	writel_relaxed(LPC32XX_TIMER_TCR_CRST, ddata->base + LPC32XX_TIMER_TCR);
+	writel_relaxed(delta, ddata->base + LPC32XX_TIMER_PR);
+	writel_relaxed(LPC32XX_TIMER_TCR_CEN, ddata->base + LPC32XX_TIMER_TCR);
+
+	return 0;
+}
+
+static int lpc32xx_clkevt_shutdown(struct clock_event_device *evtdev)
+{
+	struct lpc32xx_clock_event_ddata *ddata =
+		container_of(evtdev, struct lpc32xx_clock_event_ddata, evtdev);
+
+	/* Disable the timer */
+	writel_relaxed(0, ddata->base + LPC32XX_TIMER_TCR);
+
+	return 0;
+}
+
+static int lpc32xx_clkevt_oneshot(struct clock_event_device *evtdev)
+{
+	/*
+	 * When using oneshot, we must also disable the timer
+	 * to wait for the first call to set_next_event().
+	 */
+	return lpc32xx_clkevt_shutdown(evtdev);
+}
+
+static irqreturn_t lpc32xx_clock_event_handler(int irq, void *dev_id)
+{
+	struct lpc32xx_clock_event_ddata *ddata = dev_id;
+
+	/* Clear match on channel 0 */
+	writel_relaxed(LPC32XX_TIMER_IR_MR0INT, ddata->base + LPC32XX_TIMER_IR);
+
+	ddata->evtdev.event_handler(&ddata->evtdev);
+
+	return IRQ_HANDLED;
+}
+
+static struct lpc32xx_clock_event_ddata lpc32xx_clk_event_ddata = {
+	.evtdev = {
+		.name			= "lpc3220 clockevent",
+		.features		= CLOCK_EVT_FEAT_ONESHOT,
+		.rating			= 300,
+		.set_next_event		= lpc32xx_clkevt_next_event,
+		.set_state_shutdown	= lpc32xx_clkevt_shutdown,
+		.set_state_oneshot	= lpc32xx_clkevt_oneshot,
+	},
+};
+
+static int __init lpc32xx_clocksource_init(struct device_node *np)
+{
+	void __iomem *base;
+	unsigned long rate;
+	struct clk *clk;
+	int ret;
+
+	clk = of_clk_get_by_name(np, "timerclk");
+	if (IS_ERR(clk)) {
+		pr_err("clock get failed (%lu)\n", PTR_ERR(clk));
+		return PTR_ERR(clk);
+	}
+
+	ret = clk_prepare_enable(clk);
+	if (ret) {
+		pr_err("clock enable failed (%d)\n", ret);
+		goto err_clk_enable;
+	}
+
+	base = of_iomap(np, 0);
+	if (!base) {
+		pr_err("unable to map registers\n");
+		ret = -EADDRNOTAVAIL;
+		goto err_iomap;
+	}
+
+	/*
+	 * Disable and reset timer then set it to free running timer
+	 * mode (CTCR) with no prescaler (PR) or match operations (MCR).
+	 * After setup the timer is released from reset and enabled.
+	 */
+	writel_relaxed(LPC32XX_TIMER_TCR_CRST, base + LPC32XX_TIMER_TCR);
+	writel_relaxed(0, base + LPC32XX_TIMER_PR);
+	writel_relaxed(0, base + LPC32XX_TIMER_MCR);
+	writel_relaxed(0, base + LPC32XX_TIMER_CTCR);
+	writel_relaxed(LPC32XX_TIMER_TCR_CEN, base + LPC32XX_TIMER_TCR);
+
+	rate = clk_get_rate(clk);
+	ret = clocksource_mmio_init(base + LPC32XX_TIMER_TC, "lpc3220 timer",
+				    rate, 300, 32, clocksource_mmio_readl_up);
+	if (ret) {
+		pr_err("failed to init clocksource (%d)\n", ret);
+		goto err_clocksource_init;
+	}
+
+	clocksource_timer_counter = base + LPC32XX_TIMER_TC;
+	sched_clock_register(lpc32xx_read_sched_clock, 32, rate);
+
+	return 0;
+
+err_clocksource_init:
+	iounmap(base);
+err_iomap:
+	clk_disable_unprepare(clk);
+err_clk_enable:
+	clk_put(clk);
+	return ret;
+}
+
+static int __init lpc32xx_clockevent_init(struct device_node *np)
+{
+	void __iomem *base;
+	unsigned long rate;
+	struct clk *clk;
+	int ret, irq;
+
+	clk = of_clk_get_by_name(np, "timerclk");
+	if (IS_ERR(clk)) {
+		pr_err("clock get failed (%lu)\n", PTR_ERR(clk));
+		return PTR_ERR(clk);
+	}
+
+	ret = clk_prepare_enable(clk);
+	if (ret) {
+		pr_err("clock enable failed (%d)\n", ret);
+		goto err_clk_enable;
+	}
+
+	base = of_iomap(np, 0);
+	if (!base) {
+		pr_err("unable to map registers\n");
+		ret = -EADDRNOTAVAIL;
+		goto err_iomap;
+	}
+
+	irq = irq_of_parse_and_map(np, 0);
+	if (!irq) {
+		pr_err("get irq failed\n");
+		ret = -ENOENT;
+		goto err_irq;
+	}
+
+	/*
+	 * Disable timer and clear any pending interrupt (IR) on match
+	 * channel 0 (MR0). Configure a compare match value of 1 on MR0
+	 * and enable interrupt, reset on match and stop on match (MCR).
+	 */
+	writel_relaxed(0, base + LPC32XX_TIMER_TCR);
+	writel_relaxed(0, base + LPC32XX_TIMER_CTCR);
+	writel_relaxed(LPC32XX_TIMER_IR_MR0INT, base + LPC32XX_TIMER_IR);
+	writel_relaxed(1, base + LPC32XX_TIMER_MR0);
+	writel_relaxed(LPC32XX_TIMER_MCR_MR0I | LPC32XX_TIMER_MCR_MR0R |
+		       LPC32XX_TIMER_MCR_MR0S, base + LPC32XX_TIMER_MCR);
+
+	rate = clk_get_rate(clk);
+	lpc32xx_clk_event_ddata.base = base;
+	clockevents_config_and_register(&lpc32xx_clk_event_ddata.evtdev,
+					rate, 1, -1);
+
+	ret = request_irq(irq, lpc32xx_clock_event_handler,
+			  IRQF_TIMER | IRQF_IRQPOLL, "lpc3220 clockevent",
+			  &lpc32xx_clk_event_ddata);
+	if (ret) {
+		pr_err("request irq failed\n");
+		goto err_irq;
+	}
+
+	return 0;
+
+err_irq:
+	iounmap(base);
+err_iomap:
+	clk_disable_unprepare(clk);
+err_clk_enable:
+	clk_put(clk);
+	return ret;
+}
+
+/*
+ * This function asserts that we have exactly one clocksource and one
+ * clock_event_device in the end.
+ */
+static void __init lpc32xx_timer_init(struct device_node *np)
+{
+	static int has_clocksource, has_clockevent;
+	int ret;
+
+	if (!has_clocksource) {
+		ret = lpc32xx_clocksource_init(np);
+		if (!ret) {
+			has_clocksource = 1;
+			return;
+		}
+	}
+
+	if (!has_clockevent) {
+		ret = lpc32xx_clockevent_init(np);
+		if (!ret) {
+			has_clockevent = 1;
+			return;
+		}
+	}
+}
+CLOCKSOURCE_OF_DECLARE(lpc32xx_timer, "nxp,lpc3220-timer", lpc32xx_timer_init);
diff --git a/drivers/clocksource/timer-integrator-ap.c b/drivers/clocksource/timer-integrator-ap.c
index b9efd30513d5..c97d1980c0f8 100644
--- a/drivers/clocksource/timer-integrator-ap.c
+++ b/drivers/clocksource/timer-integrator-ap.c
@@ -166,7 +166,7 @@ static void __init integrator_ap_timer_init_of(struct device_node *node)
 	struct device_node *sec_node;
 
 	base = of_io_request_and_map(node, 0, "integrator-timer");
-	if (!base)
+	if (IS_ERR(base))
 		return;
 
 	clk = of_clk_get(node, 0);
diff --git a/drivers/clocksource/timer-stm32.c b/drivers/clocksource/timer-stm32.c
new file mode 100644
index 000000000000..a97e8b50701c
--- /dev/null
+++ b/drivers/clocksource/timer-stm32.c
@@ -0,0 +1,184 @@
+/*
+ * Copyright (C) Maxime Coquelin 2015
+ * Author:  Maxime Coquelin <mcoquelin.stm32@gmail.com>
+ * License terms:  GNU General Public License (GPL), version 2
+ *
+ * Inspired by time-efm32.c from Uwe Kleine-Koenig
+ */
+
+#include <linux/kernel.h>
+#include <linux/clocksource.h>
+#include <linux/clockchips.h>
+#include <linux/irq.h>
+#include <linux/interrupt.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/clk.h>
+#include <linux/reset.h>
+
+#define TIM_CR1		0x00
+#define TIM_DIER	0x0c
+#define TIM_SR		0x10
+#define TIM_EGR		0x14
+#define TIM_PSC		0x28
+#define TIM_ARR		0x2c
+
+#define TIM_CR1_CEN	BIT(0)
+#define TIM_CR1_OPM	BIT(3)
+#define TIM_CR1_ARPE	BIT(7)
+
+#define TIM_DIER_UIE	BIT(0)
+
+#define TIM_SR_UIF	BIT(0)
+
+#define TIM_EGR_UG	BIT(0)
+
+struct stm32_clock_event_ddata {
+	struct clock_event_device evtdev;
+	unsigned periodic_top;
+	void __iomem *base;
+};
+
+static void stm32_clock_event_set_mode(enum clock_event_mode mode,
+				       struct clock_event_device *evtdev)
+{
+	struct stm32_clock_event_ddata *data =
+		container_of(evtdev, struct stm32_clock_event_ddata, evtdev);
+	void *base = data->base;
+
+	switch (mode) {
+	case CLOCK_EVT_MODE_PERIODIC:
+		writel_relaxed(data->periodic_top, base + TIM_ARR);
+		writel_relaxed(TIM_CR1_ARPE | TIM_CR1_CEN, base + TIM_CR1);
+		break;
+
+	case CLOCK_EVT_MODE_ONESHOT:
+	default:
+		writel_relaxed(0, base + TIM_CR1);
+		break;
+	}
+}
+
+static int stm32_clock_event_set_next_event(unsigned long evt,
+					    struct clock_event_device *evtdev)
+{
+	struct stm32_clock_event_ddata *data =
+		container_of(evtdev, struct stm32_clock_event_ddata, evtdev);
+
+	writel_relaxed(evt, data->base + TIM_ARR);
+	writel_relaxed(TIM_CR1_ARPE | TIM_CR1_OPM | TIM_CR1_CEN,
+		       data->base + TIM_CR1);
+
+	return 0;
+}
+
+static irqreturn_t stm32_clock_event_handler(int irq, void *dev_id)
+{
+	struct stm32_clock_event_ddata *data = dev_id;
+
+	writel_relaxed(0, data->base + TIM_SR);
+
+	data->evtdev.event_handler(&data->evtdev);
+
+	return IRQ_HANDLED;
+}
+
+static struct stm32_clock_event_ddata clock_event_ddata = {
+	.evtdev = {
+		.name = "stm32 clockevent",
+		.features = CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_PERIODIC,
+		.set_mode = stm32_clock_event_set_mode,
+		.set_next_event = stm32_clock_event_set_next_event,
+		.rating = 200,
+	},
+};
+
+static void __init stm32_clockevent_init(struct device_node *np)
+{
+	struct stm32_clock_event_ddata *data = &clock_event_ddata;
+	struct clk *clk;
+	struct reset_control *rstc;
+	unsigned long rate, max_delta;
+	int irq, ret, bits, prescaler = 1;
+
+	clk = of_clk_get(np, 0);
+	if (IS_ERR(clk)) {
+		ret = PTR_ERR(clk);
+		pr_err("failed to get clock for clockevent (%d)\n", ret);
+		goto err_clk_get;
+	}
+
+	ret = clk_prepare_enable(clk);
+	if (ret) {
+		pr_err("failed to enable timer clock for clockevent (%d)\n",
+		       ret);
+		goto err_clk_enable;
+	}
+
+	rate = clk_get_rate(clk);
+
+	rstc = of_reset_control_get(np, NULL);
+	if (!IS_ERR(rstc)) {
+		reset_control_assert(rstc);
+		reset_control_deassert(rstc);
+	}
+
+	data->base = of_iomap(np, 0);
+	if (!data->base) {
+		pr_err("failed to map registers for clockevent\n");
+		goto err_iomap;
+	}
+
+	irq = irq_of_parse_and_map(np, 0);
+	if (!irq) {
+		pr_err("%s: failed to get irq.\n", np->full_name);
+		goto err_get_irq;
+	}
+
+	/* Detect whether the timer is 16 or 32 bits */
+	writel_relaxed(~0U, data->base + TIM_ARR);
+	max_delta = readl_relaxed(data->base + TIM_ARR);
+	if (max_delta == ~0U) {
+		prescaler = 1;
+		bits = 32;
+	} else {
+		prescaler = 1024;
+		bits = 16;
+	}
+	writel_relaxed(0, data->base + TIM_ARR);
+
+	writel_relaxed(prescaler - 1, data->base + TIM_PSC);
+	writel_relaxed(TIM_EGR_UG, data->base + TIM_EGR);
+	writel_relaxed(TIM_DIER_UIE, data->base + TIM_DIER);
+	writel_relaxed(0, data->base + TIM_SR);
+
+	data->periodic_top = DIV_ROUND_CLOSEST(rate, prescaler * HZ);
+
+	clockevents_config_and_register(&data->evtdev,
+					DIV_ROUND_CLOSEST(rate, prescaler),
+					0x1, max_delta);
+
+	ret = request_irq(irq, stm32_clock_event_handler, IRQF_TIMER,
+			"stm32 clockevent", data);
+	if (ret) {
+		pr_err("%s: failed to request irq.\n", np->full_name);
+		goto err_get_irq;
+	}
+
+	pr_info("%s: STM32 clockevent driver initialized (%d bits)\n",
+			np->full_name, bits);
+
+	return;
+
+err_get_irq:
+	iounmap(data->base);
+err_iomap:
+	clk_disable_unprepare(clk);
+err_clk_enable:
+	clk_put(clk);
+err_clk_get:
+	return;
+}
+
+CLOCKSOURCE_OF_DECLARE(stm32, "st,stm32-timer", stm32_clockevent_init);
diff --git a/drivers/clocksource/timer-sun5i.c b/drivers/clocksource/timer-sun5i.c
index 28aa4b7bb602..0ffb4ea7c925 100644
--- a/drivers/clocksource/timer-sun5i.c
+++ b/drivers/clocksource/timer-sun5i.c
@@ -324,7 +324,7 @@ static void __init sun5i_timer_init(struct device_node *node)
 	int irq;
 
 	timer_base = of_io_request_and_map(node, 0, of_node_full_name(node));
-	if (!timer_base)
+	if (IS_ERR(timer_base))
 		panic("Can't map registers");
 
 	irq = irq_of_parse_and_map(node, 0);
diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c
index b0c18ed8d83f..0136dfcdabf0 100644
--- a/drivers/cpufreq/acpi-cpufreq.c
+++ b/drivers/cpufreq/acpi-cpufreq.c
@@ -699,13 +699,14 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	dmi_check_system(sw_any_bug_dmi_table);
 	if (bios_with_sw_any_bug && !policy_is_shared(policy)) {
 		policy->shared_type = CPUFREQ_SHARED_TYPE_ALL;
-		cpumask_copy(policy->cpus, cpu_core_mask(cpu));
+		cpumask_copy(policy->cpus, topology_core_cpumask(cpu));
 	}
 
 	if (check_amd_hwpstate_cpu(cpu) && !acpi_pstate_strict) {
 		cpumask_clear(policy->cpus);
 		cpumask_set_cpu(cpu, policy->cpus);
-		cpumask_copy(data->freqdomain_cpus, cpu_sibling_mask(cpu));
+		cpumask_copy(data->freqdomain_cpus,
+			     topology_sibling_cpumask(cpu));
 		policy->shared_type = CPUFREQ_SHARED_TYPE_HW;
 		pr_info_once(PFX "overriding BIOS provided _PSD data\n");
 	}
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 1da3197425c5..15ada47bb720 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -26,6 +26,7 @@
 #include <linux/fs.h>
 #include <linux/debugfs.h>
 #include <linux/acpi.h>
+#include <linux/vmalloc.h>
 #include <trace/events/power.h>
 
 #include <asm/div64.h>
diff --git a/drivers/cpufreq/p4-clockmod.c b/drivers/cpufreq/p4-clockmod.c
index 529cfd92158f..5dd95dab580d 100644
--- a/drivers/cpufreq/p4-clockmod.c
+++ b/drivers/cpufreq/p4-clockmod.c
@@ -172,7 +172,7 @@ static int cpufreq_p4_cpu_init(struct cpufreq_policy *policy)
 	unsigned int i;
 
 #ifdef CONFIG_SMP
-	cpumask_copy(policy->cpus, cpu_sibling_mask(policy->cpu));
+	cpumask_copy(policy->cpus, topology_sibling_cpumask(policy->cpu));
 #endif
 
 	/* Errata workaround */
diff --git a/drivers/cpufreq/powernow-k8.c b/drivers/cpufreq/powernow-k8.c
index f9ce7e4bf0fe..5c035d04d827 100644
--- a/drivers/cpufreq/powernow-k8.c
+++ b/drivers/cpufreq/powernow-k8.c
@@ -57,13 +57,6 @@ static DEFINE_PER_CPU(struct powernow_k8_data *, powernow_data);
 
 static struct cpufreq_driver cpufreq_amd64_driver;
 
-#ifndef CONFIG_SMP
-static inline const struct cpumask *cpu_core_mask(int cpu)
-{
-	return cpumask_of(0);
-}
-#endif
-
 /* Return a frequency in MHz, given an input fid */
 static u32 find_freq_from_fid(u32 fid)
 {
@@ -620,7 +613,7 @@ static int fill_powernow_table(struct powernow_k8_data *data,
 
 	pr_debug("cfid 0x%x, cvid 0x%x\n", data->currfid, data->currvid);
 	data->powernow_table = powernow_table;
-	if (cpumask_first(cpu_core_mask(data->cpu)) == data->cpu)
+	if (cpumask_first(topology_core_cpumask(data->cpu)) == data->cpu)
 		print_basics(data);
 
 	for (j = 0; j < data->numps; j++)
@@ -784,7 +777,7 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data)
 		CPUFREQ_TABLE_END;
 	data->powernow_table = powernow_table;
 
-	if (cpumask_first(cpu_core_mask(data->cpu)) == data->cpu)
+	if (cpumask_first(topology_core_cpumask(data->cpu)) == data->cpu)
 		print_basics(data);
 
 	/* notify BIOS that we exist */
@@ -1090,7 +1083,7 @@ static int powernowk8_cpu_init(struct cpufreq_policy *pol)
 	if (rc != 0)
 		goto err_out_exit_acpi;
 
-	cpumask_copy(pol->cpus, cpu_core_mask(pol->cpu));
+	cpumask_copy(pol->cpus, topology_core_cpumask(pol->cpu));
 	data->available_cores = pol->cpus;
 
 	/* min/max the cpu is capable of */
diff --git a/drivers/cpufreq/speedstep-ich.c b/drivers/cpufreq/speedstep-ich.c
index e56d632a8b21..37555c6b86a7 100644
--- a/drivers/cpufreq/speedstep-ich.c
+++ b/drivers/cpufreq/speedstep-ich.c
@@ -292,7 +292,7 @@ static int speedstep_cpu_init(struct cpufreq_policy *policy)
 
 	/* only run on CPU to be set, or on its sibling */
 #ifdef CONFIG_SMP
-	cpumask_copy(policy->cpus, cpu_sibling_mask(policy->cpu));
+	cpumask_copy(policy->cpus, topology_sibling_cpumask(policy->cpu));
 #endif
 	policy_cpu = cpumask_any_and(policy->cpus, cpu_online_mask);
 
diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig
index 033c0c86f6ec..4044125fb5d5 100644
--- a/drivers/crypto/Kconfig
+++ b/drivers/crypto/Kconfig
@@ -162,10 +162,10 @@ config CRYPTO_GHASH_S390
 config CRYPTO_DEV_MV_CESA
 	tristate "Marvell's Cryptographic Engine"
 	depends on PLAT_ORION
-	select CRYPTO_ALGAPI
 	select CRYPTO_AES
-	select CRYPTO_BLKCIPHER2
+	select CRYPTO_BLKCIPHER
 	select CRYPTO_HASH
+	select SRAM
 	help
 	  This driver allows you to utilize the Cryptographic Engines and
 	  Security Accelerator (CESA) which can be found on the Marvell Orion
@@ -173,10 +173,27 @@ config CRYPTO_DEV_MV_CESA
 
 	  Currently the driver supports AES in ECB and CBC mode without DMA.
 
+config CRYPTO_DEV_MARVELL_CESA
+	tristate "New Marvell's Cryptographic Engine driver"
+	depends on PLAT_ORION || ARCH_MVEBU
+	select CRYPTO_AES
+	select CRYPTO_DES
+	select CRYPTO_BLKCIPHER
+	select CRYPTO_HASH
+	select SRAM
+	help
+	  This driver allows you to utilize the Cryptographic Engines and
+	  Security Accelerator (CESA) which can be found on the Armada 370.
+	  This driver supports CPU offload through DMA transfers.
+
+	  This driver is aimed at replacing the mv_cesa driver. This will only
+	  happen once it has received proper testing.
+
 config CRYPTO_DEV_NIAGARA2
        tristate "Niagara2 Stream Processing Unit driver"
        select CRYPTO_DES
-       select CRYPTO_ALGAPI
+       select CRYPTO_BLKCIPHER
+       select CRYPTO_HASH
        depends on SPARC64
        help
 	  Each core of a Niagara2 processor contains a Stream
@@ -189,7 +206,6 @@ config CRYPTO_DEV_NIAGARA2
 config CRYPTO_DEV_HIFN_795X
 	tristate "Driver HIFN 795x crypto accelerator chips"
 	select CRYPTO_DES
-	select CRYPTO_ALGAPI
 	select CRYPTO_BLKCIPHER
 	select HW_RANDOM if CRYPTO_DEV_HIFN_795X_RNG
 	depends on PCI
@@ -208,8 +224,10 @@ source drivers/crypto/caam/Kconfig
 
 config CRYPTO_DEV_TALITOS
 	tristate "Talitos Freescale Security Engine (SEC)"
-	select CRYPTO_ALGAPI
+	select CRYPTO_AEAD
 	select CRYPTO_AUTHENC
+	select CRYPTO_BLKCIPHER
+	select CRYPTO_HASH
 	select HW_RANDOM
 	depends on FSL_SOC
 	help
@@ -222,11 +240,29 @@ config CRYPTO_DEV_TALITOS
 	  To compile this driver as a module, choose M here: the module
 	  will be called talitos.
 
+config CRYPTO_DEV_TALITOS1
+	bool "SEC1 (SEC 1.0 and SEC Lite 1.2)"
+	depends on CRYPTO_DEV_TALITOS
+	depends on PPC_8xx || PPC_82xx
+	default y
+	help
+	  Say 'Y' here to use the Freescale Security Engine (SEC) version 1.0
+	  found on MPC82xx or the Freescale Security Engine (SEC Lite)
+	  version 1.2 found on MPC8xx
+
+config CRYPTO_DEV_TALITOS2
+	bool "SEC2+ (SEC version 2.0 or upper)"
+	depends on CRYPTO_DEV_TALITOS
+	default y if !PPC_8xx
+	help
+	  Say 'Y' here to use the Freescale Security Engine (SEC)
+	  version 2 and following as found on MPC83xx, MPC85xx, etc ...
+
 config CRYPTO_DEV_IXP4XX
 	tristate "Driver for IXP4xx crypto hardware acceleration"
 	depends on ARCH_IXP4XX && IXP4XX_QMGR && IXP4XX_NPE
 	select CRYPTO_DES
-	select CRYPTO_ALGAPI
+	select CRYPTO_AEAD
 	select CRYPTO_AUTHENC
 	select CRYPTO_BLKCIPHER
 	help
@@ -236,7 +272,6 @@ config CRYPTO_DEV_PPC4XX
 	tristate "Driver AMCC PPC4xx crypto accelerator"
 	depends on PPC && 4xx
 	select CRYPTO_HASH
-	select CRYPTO_ALGAPI
 	select CRYPTO_BLKCIPHER
 	help
 	  This option allows you to have support for AMCC crypto acceleration.
@@ -257,7 +292,7 @@ config CRYPTO_DEV_OMAP_AES
 	tristate "Support for OMAP AES hw engine"
 	depends on ARCH_OMAP2 || ARCH_OMAP3 || ARCH_OMAP2PLUS
 	select CRYPTO_AES
-	select CRYPTO_BLKCIPHER2
+	select CRYPTO_BLKCIPHER
 	help
 	  OMAP processors have AES module accelerator. Select this if you
 	  want to use the OMAP module for AES algorithms.
@@ -266,7 +301,7 @@ config CRYPTO_DEV_OMAP_DES
 	tristate "Support for OMAP DES3DES hw engine"
 	depends on ARCH_OMAP2PLUS
 	select CRYPTO_DES
-	select CRYPTO_BLKCIPHER2
+	select CRYPTO_BLKCIPHER
 	help
 	  OMAP processors have DES/3DES module accelerator. Select this if you
 	  want to use the OMAP module for DES and 3DES algorithms. Currently
@@ -276,9 +311,10 @@ config CRYPTO_DEV_OMAP_DES
 config CRYPTO_DEV_PICOXCELL
 	tristate "Support for picoXcell IPSEC and Layer2 crypto engines"
 	depends on ARCH_PICOXCELL && HAVE_CLK
+	select CRYPTO_AEAD
 	select CRYPTO_AES
 	select CRYPTO_AUTHENC
-	select CRYPTO_ALGAPI
+	select CRYPTO_BLKCIPHER
 	select CRYPTO_DES
 	select CRYPTO_CBC
 	select CRYPTO_ECB
@@ -304,7 +340,6 @@ config CRYPTO_DEV_S5P
 	tristate "Support for Samsung S5PV210/Exynos crypto accelerator"
 	depends on ARCH_S5PV210 || ARCH_EXYNOS
 	select CRYPTO_AES
-	select CRYPTO_ALGAPI
 	select CRYPTO_BLKCIPHER
 	help
 	  This option allows you to have support for S5P crypto acceleration.
@@ -312,11 +347,13 @@ config CRYPTO_DEV_S5P
 	  algorithms execution.
 
 config CRYPTO_DEV_NX
-	bool "Support for IBM Power7+ in-Nest cryptographic acceleration"
-	depends on PPC64 && IBMVIO && !CPU_LITTLE_ENDIAN
-	default n
+	bool "Support for IBM PowerPC Nest (NX) cryptographic acceleration"
+	depends on PPC64
 	help
-	  Support for Power7+ in-Nest cryptographic acceleration.
+	  This enables support for the NX hardware cryptographic accelerator
+	  coprocessor that is in IBM PowerPC P7+ or later processors.  This
+	  does not actually enable any drivers, it only allows you to select
+	  which acceleration type (encryption and/or compression) to enable.
 
 if CRYPTO_DEV_NX
 	source "drivers/crypto/nx/Kconfig"
@@ -325,7 +362,6 @@ endif
 config CRYPTO_DEV_UX500
 	tristate "Driver for ST-Ericsson UX500 crypto hardware acceleration"
 	depends on ARCH_U8500
-	select CRYPTO_ALGAPI
 	help
 	  Driver for ST-Ericsson UX500 crypto engine.
 
@@ -343,10 +379,7 @@ config CRYPTO_DEV_BFIN_CRC
 config CRYPTO_DEV_ATMEL_AES
 	tristate "Support for Atmel AES hw accelerator"
 	depends on ARCH_AT91
-	select CRYPTO_CBC
-	select CRYPTO_ECB
 	select CRYPTO_AES
-	select CRYPTO_ALGAPI
 	select CRYPTO_BLKCIPHER
 	select AT_HDMAC
 	help
@@ -361,9 +394,6 @@ config CRYPTO_DEV_ATMEL_TDES
 	tristate "Support for Atmel DES/TDES hw accelerator"
 	depends on ARCH_AT91
 	select CRYPTO_DES
-	select CRYPTO_CBC
-	select CRYPTO_ECB
-	select CRYPTO_ALGAPI
 	select CRYPTO_BLKCIPHER
 	help
 	  Some Atmel processors have DES/TDES hw accelerator.
@@ -376,10 +406,7 @@ config CRYPTO_DEV_ATMEL_TDES
 config CRYPTO_DEV_ATMEL_SHA
 	tristate "Support for Atmel SHA hw accelerator"
 	depends on ARCH_AT91
-	select CRYPTO_SHA1
-	select CRYPTO_SHA256
-	select CRYPTO_SHA512
-	select CRYPTO_ALGAPI
+	select CRYPTO_HASH
 	help
 	  Some Atmel processors have SHA1/SHA224/SHA256/SHA384/SHA512
 	  hw accelerator.
@@ -392,7 +419,6 @@ config CRYPTO_DEV_ATMEL_SHA
 config CRYPTO_DEV_CCP
 	bool "Support for AMD Cryptographic Coprocessor"
 	depends on ((X86 && PCI) || (ARM64 && (OF_ADDRESS || ACPI))) && HAS_IOMEM
-	default n
 	help
 	  The AMD Cryptographic Coprocessor provides hardware support
 	  for encryption, hashing and related operations.
@@ -404,13 +430,11 @@ endif
 config CRYPTO_DEV_MXS_DCP
 	tristate "Support for Freescale MXS DCP"
 	depends on ARCH_MXS
-	select CRYPTO_SHA1
-	select CRYPTO_SHA256
 	select CRYPTO_CBC
 	select CRYPTO_ECB
 	select CRYPTO_AES
 	select CRYPTO_BLKCIPHER
-	select CRYPTO_ALGAPI
+	select CRYPTO_HASH
 	help
 	  The Freescale i.MX23/i.MX28 has SHA1/SHA256 and AES128 CBC/ECB
 	  co-processor on the die.
@@ -429,7 +453,6 @@ config CRYPTO_DEV_QCE
 	select CRYPTO_CBC
 	select CRYPTO_XTS
 	select CRYPTO_CTR
-	select CRYPTO_ALGAPI
 	select CRYPTO_BLKCIPHER
 	help
 	  This driver supports Qualcomm crypto engine accelerator
@@ -439,7 +462,6 @@ config CRYPTO_DEV_QCE
 config CRYPTO_DEV_VMX
 	bool "Support for VMX cryptographic acceleration instructions"
 	depends on PPC64
-	default n
 	help
 	  Support for VMX cryptographic acceleration instructions.
 
@@ -449,7 +471,6 @@ config CRYPTO_DEV_IMGTEC_HASH
 	tristate "Imagination Technologies hardware hash accelerator"
 	depends on MIPS || COMPILE_TEST
 	depends on HAS_DMA
-	select CRYPTO_ALGAPI
 	select CRYPTO_MD5
 	select CRYPTO_SHA1
 	select CRYPTO_SHA256
diff --git a/drivers/crypto/Makefile b/drivers/crypto/Makefile
index fb84be7e6be5..e35c07a8da85 100644
--- a/drivers/crypto/Makefile
+++ b/drivers/crypto/Makefile
@@ -9,6 +9,7 @@ obj-$(CONFIG_CRYPTO_DEV_HIFN_795X) += hifn_795x.o
 obj-$(CONFIG_CRYPTO_DEV_IMGTEC_HASH) += img-hash.o
 obj-$(CONFIG_CRYPTO_DEV_IXP4XX) += ixp4xx_crypto.o
 obj-$(CONFIG_CRYPTO_DEV_MV_CESA) += mv_cesa.o
+obj-$(CONFIG_CRYPTO_DEV_MARVELL_CESA) += marvell/
 obj-$(CONFIG_CRYPTO_DEV_MXS_DCP) += mxs-dcp.o
 obj-$(CONFIG_CRYPTO_DEV_NIAGARA2) += n2_crypto.o
 n2_crypto-y := n2_core.o n2_asm.o
diff --git a/drivers/crypto/caam/Kconfig b/drivers/crypto/caam/Kconfig
index e7555ff4cafd..e286e285aa8a 100644
--- a/drivers/crypto/caam/Kconfig
+++ b/drivers/crypto/caam/Kconfig
@@ -45,7 +45,6 @@ config CRYPTO_DEV_FSL_CAAM_RINGSIZE
 config CRYPTO_DEV_FSL_CAAM_INTC
 	bool "Job Ring interrupt coalescing"
 	depends on CRYPTO_DEV_FSL_CAAM_JR
-	default n
 	help
 	  Enable the Job Ring's interrupt coalescing feature.
 
@@ -77,8 +76,9 @@ config CRYPTO_DEV_FSL_CAAM_CRYPTO_API
 	tristate "Register algorithm implementations with the Crypto API"
 	depends on CRYPTO_DEV_FSL_CAAM && CRYPTO_DEV_FSL_CAAM_JR
 	default y
-	select CRYPTO_ALGAPI
+	select CRYPTO_AEAD
 	select CRYPTO_AUTHENC
+	select CRYPTO_BLKCIPHER
 	help
 	  Selecting this will offload crypto for users of the
 	  scatterlist crypto API (such as the linux native IPSec
@@ -115,7 +115,6 @@ config CRYPTO_DEV_FSL_CAAM_RNG_API
 config CRYPTO_DEV_FSL_CAAM_DEBUG
 	bool "Enable debug output in CAAM driver"
 	depends on CRYPTO_DEV_FSL_CAAM
-	default n
 	help
 	  Selecting this will enable printing of various debug
 	  information in the CAAM driver.
diff --git a/drivers/crypto/caam/caamalg.c b/drivers/crypto/caam/caamalg.c
index 29071a156cbe..daca933a82ec 100644
--- a/drivers/crypto/caam/caamalg.c
+++ b/drivers/crypto/caam/caamalg.c
@@ -65,6 +65,10 @@
 /* max IV is max of AES_BLOCK_SIZE, DES3_EDE_BLOCK_SIZE */
 #define CAAM_MAX_IV_LENGTH		16
 
+#define AEAD_DESC_JOB_IO_LEN		(DESC_JOB_IO_LEN + CAAM_CMD_SZ * 2)
+#define GCM_DESC_JOB_IO_LEN		(AEAD_DESC_JOB_IO_LEN + \
+					 CAAM_CMD_SZ * 4)
+
 /* length of descriptors text */
 #define DESC_AEAD_BASE			(4 * CAAM_CMD_SZ)
 #define DESC_AEAD_ENC_LEN		(DESC_AEAD_BASE + 15 * CAAM_CMD_SZ)
@@ -79,18 +83,16 @@
 #define DESC_AEAD_NULL_DEC_LEN		(DESC_AEAD_NULL_BASE + 17 * CAAM_CMD_SZ)
 
 #define DESC_GCM_BASE			(3 * CAAM_CMD_SZ)
-#define DESC_GCM_ENC_LEN		(DESC_GCM_BASE + 23 * CAAM_CMD_SZ)
-#define DESC_GCM_DEC_LEN		(DESC_GCM_BASE + 19 * CAAM_CMD_SZ)
+#define DESC_GCM_ENC_LEN		(DESC_GCM_BASE + 16 * CAAM_CMD_SZ)
+#define DESC_GCM_DEC_LEN		(DESC_GCM_BASE + 12 * CAAM_CMD_SZ)
 
 #define DESC_RFC4106_BASE		(3 * CAAM_CMD_SZ)
-#define DESC_RFC4106_ENC_LEN		(DESC_RFC4106_BASE + 15 * CAAM_CMD_SZ)
-#define DESC_RFC4106_DEC_LEN		(DESC_RFC4106_BASE + 14 * CAAM_CMD_SZ)
-#define DESC_RFC4106_GIVENC_LEN		(DESC_RFC4106_BASE + 21 * CAAM_CMD_SZ)
+#define DESC_RFC4106_ENC_LEN		(DESC_RFC4106_BASE + 10 * CAAM_CMD_SZ)
+#define DESC_RFC4106_DEC_LEN		(DESC_RFC4106_BASE + 10 * CAAM_CMD_SZ)
 
 #define DESC_RFC4543_BASE		(3 * CAAM_CMD_SZ)
-#define DESC_RFC4543_ENC_LEN		(DESC_RFC4543_BASE + 25 * CAAM_CMD_SZ)
-#define DESC_RFC4543_DEC_LEN		(DESC_RFC4543_BASE + 27 * CAAM_CMD_SZ)
-#define DESC_RFC4543_GIVENC_LEN		(DESC_RFC4543_BASE + 30 * CAAM_CMD_SZ)
+#define DESC_RFC4543_ENC_LEN		(DESC_RFC4543_BASE + 11 * CAAM_CMD_SZ)
+#define DESC_RFC4543_DEC_LEN		(DESC_RFC4543_BASE + 12 * CAAM_CMD_SZ)
 
 #define DESC_ABLKCIPHER_BASE		(3 * CAAM_CMD_SZ)
 #define DESC_ABLKCIPHER_ENC_LEN		(DESC_ABLKCIPHER_BASE + \
@@ -98,8 +100,7 @@
 #define DESC_ABLKCIPHER_DEC_LEN		(DESC_ABLKCIPHER_BASE + \
 					 15 * CAAM_CMD_SZ)
 
-#define DESC_MAX_USED_BYTES		(DESC_RFC4543_GIVENC_LEN + \
-					 CAAM_MAX_KEY_SIZE)
+#define DESC_MAX_USED_BYTES		(CAAM_DESC_BYTES_MAX - DESC_JOB_IO_LEN)
 #define DESC_MAX_USED_LEN		(DESC_MAX_USED_BYTES / CAAM_CMD_SZ)
 
 #ifdef DEBUG
@@ -258,7 +259,7 @@ static void init_sh_desc_key_aead(u32 *desc, struct caam_ctx *ctx,
 
 static int aead_null_set_sh_desc(struct crypto_aead *aead)
 {
-	struct aead_tfm *tfm = &aead->base.crt_aead;
+	unsigned int ivsize = crypto_aead_ivsize(aead);
 	struct caam_ctx *ctx = crypto_aead_ctx(aead);
 	struct device *jrdev = ctx->jrdev;
 	bool keys_fit_inline = false;
@@ -273,7 +274,7 @@ static int aead_null_set_sh_desc(struct crypto_aead *aead)
 	    ctx->split_key_pad_len <= CAAM_DESC_BYTES_MAX)
 		keys_fit_inline = true;
 
-	/* aead_encrypt shared descriptor */
+	/* old_aead_encrypt shared descriptor */
 	desc = ctx->sh_desc_enc;
 
 	init_sh_desc(desc, HDR_SHARE_SERIAL);
@@ -362,7 +363,7 @@ static int aead_null_set_sh_desc(struct crypto_aead *aead)
 
 	desc = ctx->sh_desc_dec;
 
-	/* aead_decrypt shared descriptor */
+	/* old_aead_decrypt shared descriptor */
 	init_sh_desc(desc, HDR_SHARE_SERIAL);
 
 	/* Skip if already shared */
@@ -383,7 +384,7 @@ static int aead_null_set_sh_desc(struct crypto_aead *aead)
 
 	/* assoclen + cryptlen = seqinlen - ivsize - authsize */
 	append_math_sub_imm_u32(desc, REG3, SEQINLEN, IMM,
-				ctx->authsize + tfm->ivsize);
+				ctx->authsize + ivsize);
 	/* assoclen = (assoclen + cryptlen) - cryptlen */
 	append_math_sub(desc, REG2, SEQOUTLEN, REG0, CAAM_CMD_SZ);
 	append_math_sub(desc, VARSEQINLEN, REG3, REG2, CAAM_CMD_SZ);
@@ -449,7 +450,7 @@ static int aead_null_set_sh_desc(struct crypto_aead *aead)
 
 static int aead_set_sh_desc(struct crypto_aead *aead)
 {
-	struct aead_tfm *tfm = &aead->base.crt_aead;
+	unsigned int ivsize = crypto_aead_ivsize(aead);
 	struct caam_ctx *ctx = crypto_aead_ctx(aead);
 	struct crypto_tfm *ctfm = crypto_aead_tfm(aead);
 	const char *alg_name = crypto_tfm_alg_name(ctfm);
@@ -496,7 +497,7 @@ static int aead_set_sh_desc(struct crypto_aead *aead)
 	    CAAM_DESC_BYTES_MAX)
 		keys_fit_inline = true;
 
-	/* aead_encrypt shared descriptor */
+	/* old_aead_encrypt shared descriptor */
 	desc = ctx->sh_desc_enc;
 
 	/* Note: Context registers are saved. */
@@ -510,7 +511,7 @@ static int aead_set_sh_desc(struct crypto_aead *aead)
 	append_math_sub_imm_u32(desc, REG3, SEQOUTLEN, IMM, ctx->authsize);
 
 	/* assoclen + cryptlen = seqinlen - ivsize */
-	append_math_sub_imm_u32(desc, REG2, SEQINLEN, IMM, tfm->ivsize);
+	append_math_sub_imm_u32(desc, REG2, SEQINLEN, IMM, ivsize);
 
 	/* assoclen = (assoclen + cryptlen) - cryptlen */
 	append_math_sub(desc, VARSEQINLEN, REG2, REG3, CAAM_CMD_SZ);
@@ -518,7 +519,7 @@ static int aead_set_sh_desc(struct crypto_aead *aead)
 	/* read assoc before reading payload */
 	append_seq_fifo_load(desc, 0, FIFOLD_CLASS_CLASS2 | FIFOLD_TYPE_MSG |
 			     KEY_VLF);
-	aead_append_ld_iv(desc, tfm->ivsize, ctx1_iv_off);
+	aead_append_ld_iv(desc, ivsize, ctx1_iv_off);
 
 	/* Load Counter into CONTEXT1 reg */
 	if (is_rfc3686)
@@ -565,7 +566,7 @@ static int aead_set_sh_desc(struct crypto_aead *aead)
 	    CAAM_DESC_BYTES_MAX)
 		keys_fit_inline = true;
 
-	/* aead_decrypt shared descriptor */
+	/* old_aead_decrypt shared descriptor */
 	desc = ctx->sh_desc_dec;
 
 	/* Note: Context registers are saved. */
@@ -577,7 +578,7 @@ static int aead_set_sh_desc(struct crypto_aead *aead)
 
 	/* assoclen + cryptlen = seqinlen - ivsize - authsize */
 	append_math_sub_imm_u32(desc, REG3, SEQINLEN, IMM,
-				ctx->authsize + tfm->ivsize);
+				ctx->authsize + ivsize);
 	/* assoclen = (assoclen + cryptlen) - cryptlen */
 	append_math_sub(desc, REG2, SEQOUTLEN, REG0, CAAM_CMD_SZ);
 	append_math_sub(desc, VARSEQINLEN, REG3, REG2, CAAM_CMD_SZ);
@@ -586,7 +587,7 @@ static int aead_set_sh_desc(struct crypto_aead *aead)
 	append_seq_fifo_load(desc, 0, FIFOLD_CLASS_CLASS2 | FIFOLD_TYPE_MSG |
 			     KEY_VLF);
 
-	aead_append_ld_iv(desc, tfm->ivsize, ctx1_iv_off);
+	aead_append_ld_iv(desc, ivsize, ctx1_iv_off);
 
 	/* Load Counter into CONTEXT1 reg */
 	if (is_rfc3686)
@@ -645,20 +646,20 @@ static int aead_set_sh_desc(struct crypto_aead *aead)
 	/* Generate IV */
 	geniv = NFIFOENTRY_STYPE_PAD | NFIFOENTRY_DEST_DECO |
 		NFIFOENTRY_DTYPE_MSG | NFIFOENTRY_LC1 |
-		NFIFOENTRY_PTYPE_RND | (tfm->ivsize << NFIFOENTRY_DLEN_SHIFT);
+		NFIFOENTRY_PTYPE_RND | (ivsize << NFIFOENTRY_DLEN_SHIFT);
 	append_load_imm_u32(desc, geniv, LDST_CLASS_IND_CCB |
 			    LDST_SRCDST_WORD_INFO_FIFO | LDST_IMM);
 	append_cmd(desc, CMD_LOAD | DISABLE_AUTO_INFO_FIFO);
 	append_move(desc, MOVE_WAITCOMP |
 		    MOVE_SRC_INFIFO | MOVE_DEST_CLASS1CTX |
 		    (ctx1_iv_off << MOVE_OFFSET_SHIFT) |
-		    (tfm->ivsize << MOVE_LEN_SHIFT));
+		    (ivsize << MOVE_LEN_SHIFT));
 	append_cmd(desc, CMD_LOAD | ENABLE_AUTO_INFO_FIFO);
 
 	/* Copy IV to class 1 context */
 	append_move(desc, MOVE_SRC_CLASS1CTX | MOVE_DEST_OUTFIFO |
 		    (ctx1_iv_off << MOVE_OFFSET_SHIFT) |
-		    (tfm->ivsize << MOVE_LEN_SHIFT));
+		    (ivsize << MOVE_LEN_SHIFT));
 
 	/* Return to encryption */
 	append_operation(desc, ctx->class2_alg_type |
@@ -676,10 +677,10 @@ static int aead_set_sh_desc(struct crypto_aead *aead)
 
 	/* Copy iv from outfifo to class 2 fifo */
 	moveiv = NFIFOENTRY_STYPE_OFIFO | NFIFOENTRY_DEST_CLASS2 |
-		 NFIFOENTRY_DTYPE_MSG | (tfm->ivsize << NFIFOENTRY_DLEN_SHIFT);
+		 NFIFOENTRY_DTYPE_MSG | (ivsize << NFIFOENTRY_DLEN_SHIFT);
 	append_load_imm_u32(desc, moveiv, LDST_CLASS_IND_CCB |
 			    LDST_SRCDST_WORD_INFO_FIFO | LDST_IMM);
-	append_load_imm_u32(desc, tfm->ivsize, LDST_CLASS_2_CCB |
+	append_load_imm_u32(desc, ivsize, LDST_CLASS_2_CCB |
 			    LDST_SRCDST_WORD_DATASZ_REG | LDST_IMM);
 
 	/* Load Counter into CONTEXT1 reg */
@@ -698,7 +699,7 @@ static int aead_set_sh_desc(struct crypto_aead *aead)
 	append_math_add(desc, VARSEQOUTLEN, SEQINLEN, REG0, CAAM_CMD_SZ);
 
 	/* Not need to reload iv */
-	append_seq_fifo_load(desc, tfm->ivsize,
+	append_seq_fifo_load(desc, ivsize,
 			     FIFOLD_CLASS_SKIP);
 
 	/* Will read cryptlen */
@@ -738,7 +739,6 @@ static int aead_setauthsize(struct crypto_aead *authenc,
 
 static int gcm_set_sh_desc(struct crypto_aead *aead)
 {
-	struct aead_tfm *tfm = &aead->base.crt_aead;
 	struct caam_ctx *ctx = crypto_aead_ctx(aead);
 	struct device *jrdev = ctx->jrdev;
 	bool keys_fit_inline = false;
@@ -754,7 +754,7 @@ static int gcm_set_sh_desc(struct crypto_aead *aead)
 	 * Job Descriptor and Shared Descriptor
 	 * must fit into the 64-word Descriptor h/w Buffer
 	 */
-	if (DESC_GCM_ENC_LEN + DESC_JOB_IO_LEN +
+	if (DESC_GCM_ENC_LEN + GCM_DESC_JOB_IO_LEN +
 	    ctx->enckeylen <= CAAM_DESC_BYTES_MAX)
 		keys_fit_inline = true;
 
@@ -777,34 +777,34 @@ static int gcm_set_sh_desc(struct crypto_aead *aead)
 	append_operation(desc, ctx->class1_alg_type |
 			 OP_ALG_AS_INITFINAL | OP_ALG_ENCRYPT);
 
-	/* cryptlen = seqoutlen - authsize */
-	append_math_sub_imm_u32(desc, REG3, SEQOUTLEN, IMM, ctx->authsize);
+	/* if assoclen + cryptlen is ZERO, skip to ICV write */
+	append_math_sub(desc, VARSEQOUTLEN, SEQINLEN, REG0, CAAM_CMD_SZ);
+	zero_assoc_jump_cmd2 = append_jump(desc, JUMP_TEST_ALL |
+						 JUMP_COND_MATH_Z);
 
-	/* assoclen + cryptlen = seqinlen - ivsize */
-	append_math_sub_imm_u32(desc, REG2, SEQINLEN, IMM, tfm->ivsize);
+	/* if assoclen is ZERO, skip reading the assoc data */
+	append_math_add(desc, VARSEQINLEN, ZERO, REG3, CAAM_CMD_SZ);
+	zero_assoc_jump_cmd1 = append_jump(desc, JUMP_TEST_ALL |
+						 JUMP_COND_MATH_Z);
 
-	/* assoclen = (assoclen + cryptlen) - cryptlen */
-	append_math_sub(desc, REG1, REG2, REG3, CAAM_CMD_SZ);
+	append_math_add(desc, VARSEQOUTLEN, ZERO, REG3, CAAM_CMD_SZ);
+
+	/* skip assoc data */
+	append_seq_fifo_store(desc, 0, FIFOST_TYPE_SKIP | FIFOLDST_VLF);
+
+	/* cryptlen = seqinlen - assoclen */
+	append_math_sub(desc, VARSEQOUTLEN, SEQINLEN, REG3, CAAM_CMD_SZ);
 
 	/* if cryptlen is ZERO jump to zero-payload commands */
-	append_math_add(desc, VARSEQOUTLEN, ZERO, REG3, CAAM_CMD_SZ);
 	zero_payload_jump_cmd = append_jump(desc, JUMP_TEST_ALL |
 					    JUMP_COND_MATH_Z);
-	/* read IV */
-	append_seq_fifo_load(desc, tfm->ivsize, FIFOLD_CLASS_CLASS1 |
-			     FIFOLD_TYPE_IV | FIFOLD_TYPE_FLUSH1);
-
-	/* if assoclen is ZERO, skip reading the assoc data */
-	append_math_add(desc, VARSEQINLEN, ZERO, REG1, CAAM_CMD_SZ);
-	zero_assoc_jump_cmd1 = append_jump(desc, JUMP_TEST_ALL |
-					   JUMP_COND_MATH_Z);
 
 	/* read assoc data */
 	append_seq_fifo_load(desc, 0, FIFOLD_CLASS_CLASS1 | FIFOLDST_VLF |
 			     FIFOLD_TYPE_AAD | FIFOLD_TYPE_FLUSH1);
 	set_jump_tgt_here(desc, zero_assoc_jump_cmd1);
 
-	append_math_add(desc, VARSEQINLEN, ZERO, REG3, CAAM_CMD_SZ);
+	append_math_sub(desc, VARSEQINLEN, SEQINLEN, REG0, CAAM_CMD_SZ);
 
 	/* write encrypted data */
 	append_seq_fifo_store(desc, 0, FIFOST_TYPE_MESSAGE_DATA | FIFOLDST_VLF);
@@ -814,31 +814,17 @@ static int gcm_set_sh_desc(struct crypto_aead *aead)
 			     FIFOLD_TYPE_MSG | FIFOLD_TYPE_LAST1);
 
 	/* jump the zero-payload commands */
-	append_jump(desc, JUMP_TEST_ALL | 7);
+	append_jump(desc, JUMP_TEST_ALL | 2);
 
 	/* zero-payload commands */
 	set_jump_tgt_here(desc, zero_payload_jump_cmd);
 
-	/* if assoclen is ZERO, jump to IV reading - is the only input data */
-	append_math_add(desc, VARSEQINLEN, ZERO, REG1, CAAM_CMD_SZ);
-	zero_assoc_jump_cmd2 = append_jump(desc, JUMP_TEST_ALL |
-					   JUMP_COND_MATH_Z);
-	/* read IV */
-	append_seq_fifo_load(desc, tfm->ivsize, FIFOLD_CLASS_CLASS1 |
-			     FIFOLD_TYPE_IV | FIFOLD_TYPE_FLUSH1);
-
 	/* read assoc data */
 	append_seq_fifo_load(desc, 0, FIFOLD_CLASS_CLASS1 | FIFOLDST_VLF |
 			     FIFOLD_TYPE_AAD | FIFOLD_TYPE_LAST1);
 
-	/* jump to ICV writing */
-	append_jump(desc, JUMP_TEST_ALL | 2);
-
-	/* read IV - is the only input data */
+	/* There is no input data */
 	set_jump_tgt_here(desc, zero_assoc_jump_cmd2);
-	append_seq_fifo_load(desc, tfm->ivsize, FIFOLD_CLASS_CLASS1 |
-			     FIFOLD_TYPE_IV | FIFOLD_TYPE_FLUSH1 |
-			     FIFOLD_TYPE_LAST1);
 
 	/* write ICV */
 	append_seq_store(desc, ctx->authsize, LDST_CLASS_1_CCB |
@@ -862,7 +848,7 @@ static int gcm_set_sh_desc(struct crypto_aead *aead)
 	 * must all fit into the 64-word Descriptor h/w Buffer
 	 */
 	keys_fit_inline = false;
-	if (DESC_GCM_DEC_LEN + DESC_JOB_IO_LEN +
+	if (DESC_GCM_DEC_LEN + GCM_DESC_JOB_IO_LEN +
 	    ctx->enckeylen <= CAAM_DESC_BYTES_MAX)
 		keys_fit_inline = true;
 
@@ -886,33 +872,30 @@ static int gcm_set_sh_desc(struct crypto_aead *aead)
 	append_operation(desc, ctx->class1_alg_type |
 			 OP_ALG_AS_INITFINAL | OP_ALG_DECRYPT | OP_ALG_ICV_ON);
 
-	/* assoclen + cryptlen = seqinlen - ivsize - icvsize */
-	append_math_sub_imm_u32(desc, REG3, SEQINLEN, IMM,
-				ctx->authsize + tfm->ivsize);
-
-	/* assoclen = (assoclen + cryptlen) - cryptlen */
-	append_math_sub(desc, REG2, SEQOUTLEN, REG0, CAAM_CMD_SZ);
-	append_math_sub(desc, REG1, REG3, REG2, CAAM_CMD_SZ);
+	/* if assoclen is ZERO, skip reading the assoc data */
+	append_math_add(desc, VARSEQINLEN, ZERO, REG3, CAAM_CMD_SZ);
+	zero_assoc_jump_cmd1 = append_jump(desc, JUMP_TEST_ALL |
+						 JUMP_COND_MATH_Z);
 
-	/* read IV */
-	append_seq_fifo_load(desc, tfm->ivsize, FIFOLD_CLASS_CLASS1 |
-			     FIFOLD_TYPE_IV | FIFOLD_TYPE_FLUSH1);
+	append_math_add(desc, VARSEQOUTLEN, ZERO, REG3, CAAM_CMD_SZ);
 
-	/* jump to zero-payload command if cryptlen is zero */
-	append_math_add(desc, VARSEQOUTLEN, ZERO, REG2, CAAM_CMD_SZ);
-	zero_payload_jump_cmd = append_jump(desc, JUMP_TEST_ALL |
-					    JUMP_COND_MATH_Z);
+	/* skip assoc data */
+	append_seq_fifo_store(desc, 0, FIFOST_TYPE_SKIP | FIFOLDST_VLF);
 
-	append_math_add(desc, VARSEQINLEN, ZERO, REG1, CAAM_CMD_SZ);
-	/* if asoclen is ZERO, skip reading assoc data */
-	zero_assoc_jump_cmd1 = append_jump(desc, JUMP_TEST_ALL |
-					   JUMP_COND_MATH_Z);
 	/* read assoc data */
 	append_seq_fifo_load(desc, 0, FIFOLD_CLASS_CLASS1 | FIFOLDST_VLF |
 			     FIFOLD_TYPE_AAD | FIFOLD_TYPE_FLUSH1);
+
 	set_jump_tgt_here(desc, zero_assoc_jump_cmd1);
 
-	append_math_add(desc, VARSEQINLEN, ZERO, REG2, CAAM_CMD_SZ);
+	/* cryptlen = seqoutlen - assoclen */
+	append_math_sub(desc, VARSEQINLEN, SEQOUTLEN, REG0, CAAM_CMD_SZ);
+
+	/* jump to zero-payload command if cryptlen is zero */
+	zero_payload_jump_cmd = append_jump(desc, JUMP_TEST_ALL |
+					    JUMP_COND_MATH_Z);
+
+	append_math_sub(desc, VARSEQOUTLEN, SEQOUTLEN, REG0, CAAM_CMD_SZ);
 
 	/* store encrypted data */
 	append_seq_fifo_store(desc, 0, FIFOST_TYPE_MESSAGE_DATA | FIFOLDST_VLF);
@@ -921,21 +904,9 @@ static int gcm_set_sh_desc(struct crypto_aead *aead)
 	append_seq_fifo_load(desc, 0, FIFOLD_CLASS_CLASS1 | FIFOLDST_VLF |
 			     FIFOLD_TYPE_MSG | FIFOLD_TYPE_FLUSH1);
 
-	/* jump the zero-payload commands */
-	append_jump(desc, JUMP_TEST_ALL | 4);
-
 	/* zero-payload command */
 	set_jump_tgt_here(desc, zero_payload_jump_cmd);
 
-	/* if assoclen is ZERO, jump to ICV reading */
-	append_math_add(desc, VARSEQINLEN, ZERO, REG1, CAAM_CMD_SZ);
-	zero_assoc_jump_cmd2 = append_jump(desc, JUMP_TEST_ALL |
-					   JUMP_COND_MATH_Z);
-	/* read assoc data */
-	append_seq_fifo_load(desc, 0, FIFOLD_CLASS_CLASS1 | FIFOLDST_VLF |
-			     FIFOLD_TYPE_AAD | FIFOLD_TYPE_FLUSH1);
-	set_jump_tgt_here(desc, zero_assoc_jump_cmd2);
-
 	/* read ICV */
 	append_seq_fifo_load(desc, ctx->authsize, FIFOLD_CLASS_CLASS1 |
 			     FIFOLD_TYPE_ICV | FIFOLD_TYPE_LAST1);
@@ -968,13 +939,11 @@ static int gcm_setauthsize(struct crypto_aead *authenc, unsigned int authsize)
 
 static int rfc4106_set_sh_desc(struct crypto_aead *aead)
 {
-	struct aead_tfm *tfm = &aead->base.crt_aead;
 	struct caam_ctx *ctx = crypto_aead_ctx(aead);
 	struct device *jrdev = ctx->jrdev;
 	bool keys_fit_inline = false;
-	u32 *key_jump_cmd, *move_cmd, *write_iv_cmd;
+	u32 *key_jump_cmd;
 	u32 *desc;
-	u32 geniv;
 
 	if (!ctx->enckeylen || !ctx->authsize)
 		return 0;
@@ -984,7 +953,7 @@ static int rfc4106_set_sh_desc(struct crypto_aead *aead)
 	 * Job Descriptor and Shared Descriptor
 	 * must fit into the 64-word Descriptor h/w Buffer
 	 */
-	if (DESC_RFC4106_ENC_LEN + DESC_JOB_IO_LEN +
+	if (DESC_RFC4106_ENC_LEN + GCM_DESC_JOB_IO_LEN +
 	    ctx->enckeylen <= CAAM_DESC_BYTES_MAX)
 		keys_fit_inline = true;
 
@@ -1007,29 +976,21 @@ static int rfc4106_set_sh_desc(struct crypto_aead *aead)
 	append_operation(desc, ctx->class1_alg_type |
 			 OP_ALG_AS_INITFINAL | OP_ALG_ENCRYPT);
 
-	/* cryptlen = seqoutlen - authsize */
-	append_math_sub_imm_u32(desc, REG3, SEQOUTLEN, IMM, ctx->authsize);
+	append_math_add(desc, VARSEQINLEN, ZERO, REG3, CAAM_CMD_SZ);
 	append_math_add(desc, VARSEQOUTLEN, ZERO, REG3, CAAM_CMD_SZ);
 
-	/* assoclen + cryptlen = seqinlen - ivsize */
-	append_math_sub_imm_u32(desc, REG2, SEQINLEN, IMM, tfm->ivsize);
-
-	/* assoclen = (assoclen + cryptlen) - cryptlen */
-	append_math_sub(desc, VARSEQINLEN, REG2, REG3, CAAM_CMD_SZ);
-
-	/* Read Salt */
-	append_fifo_load_as_imm(desc, (void *)(ctx->key + ctx->enckeylen),
-				4, FIFOLD_CLASS_CLASS1 | FIFOLD_TYPE_IV);
-	/* Read AES-GCM-ESP IV */
-	append_seq_fifo_load(desc, tfm->ivsize, FIFOLD_CLASS_CLASS1 |
-			     FIFOLD_TYPE_IV | FIFOLD_TYPE_FLUSH1);
+	/* Skip assoc data */
+	append_seq_fifo_store(desc, 0, FIFOST_TYPE_SKIP | FIFOLDST_VLF);
 
 	/* Read assoc data */
 	append_seq_fifo_load(desc, 0, FIFOLD_CLASS_CLASS1 | FIFOLDST_VLF |
 			     FIFOLD_TYPE_AAD | FIFOLD_TYPE_FLUSH1);
 
+	/* cryptlen = seqoutlen - assoclen */
+	append_math_sub(desc, VARSEQOUTLEN, SEQINLEN, REG0, CAAM_CMD_SZ);
+
 	/* Will read cryptlen bytes */
-	append_math_add(desc, VARSEQINLEN, ZERO, REG3, CAAM_CMD_SZ);
+	append_math_sub(desc, VARSEQINLEN, SEQINLEN, REG0, CAAM_CMD_SZ);
 
 	/* Write encrypted data */
 	append_seq_fifo_store(desc, 0, FIFOST_TYPE_MESSAGE_DATA | FIFOLDST_VLF);
@@ -1083,30 +1044,21 @@ static int rfc4106_set_sh_desc(struct crypto_aead *aead)
 	append_operation(desc, ctx->class1_alg_type |
 			 OP_ALG_AS_INITFINAL | OP_ALG_DECRYPT | OP_ALG_ICV_ON);
 
-	/* assoclen + cryptlen = seqinlen - ivsize - icvsize */
-	append_math_sub_imm_u32(desc, REG3, SEQINLEN, IMM,
-				ctx->authsize + tfm->ivsize);
-
-	/* assoclen = (assoclen + cryptlen) - cryptlen */
-	append_math_sub(desc, REG2, SEQOUTLEN, REG0, CAAM_CMD_SZ);
-	append_math_sub(desc, VARSEQINLEN, REG3, REG2, CAAM_CMD_SZ);
-
-	/* Will write cryptlen bytes */
-	append_math_sub(desc, VARSEQOUTLEN, SEQOUTLEN, REG0, CAAM_CMD_SZ);
+	append_math_add(desc, VARSEQINLEN, ZERO, REG3, CAAM_CMD_SZ);
+	append_math_add(desc, VARSEQOUTLEN, ZERO, REG3, CAAM_CMD_SZ);
 
-	/* Read Salt */
-	append_fifo_load_as_imm(desc, (void *)(ctx->key + ctx->enckeylen),
-				4, FIFOLD_CLASS_CLASS1 | FIFOLD_TYPE_IV);
-	/* Read AES-GCM-ESP IV */
-	append_seq_fifo_load(desc, tfm->ivsize, FIFOLD_CLASS_CLASS1 |
-			     FIFOLD_TYPE_IV | FIFOLD_TYPE_FLUSH1);
+	/* Skip assoc data */
+	append_seq_fifo_store(desc, 0, FIFOST_TYPE_SKIP | FIFOLDST_VLF);
 
 	/* Read assoc data */
 	append_seq_fifo_load(desc, 0, FIFOLD_CLASS_CLASS1 | FIFOLDST_VLF |
 			     FIFOLD_TYPE_AAD | FIFOLD_TYPE_FLUSH1);
 
+	/* Will write cryptlen bytes */
+	append_math_sub(desc, VARSEQOUTLEN, SEQOUTLEN, REG0, CAAM_CMD_SZ);
+
 	/* Will read cryptlen bytes */
-	append_math_add(desc, VARSEQINLEN, ZERO, REG2, CAAM_CMD_SZ);
+	append_math_sub(desc, VARSEQINLEN, SEQOUTLEN, REG0, CAAM_CMD_SZ);
 
 	/* Store payload data */
 	append_seq_fifo_store(desc, 0, FIFOST_TYPE_MESSAGE_DATA | FIFOLDST_VLF);
@@ -1132,107 +1084,6 @@ static int rfc4106_set_sh_desc(struct crypto_aead *aead)
 		       desc_bytes(desc), 1);
 #endif
 
-	/*
-	 * Job Descriptor and Shared Descriptors
-	 * must all fit into the 64-word Descriptor h/w Buffer
-	 */
-	keys_fit_inline = false;
-	if (DESC_RFC4106_GIVENC_LEN + DESC_JOB_IO_LEN +
-	    ctx->split_key_pad_len + ctx->enckeylen <=
-	    CAAM_DESC_BYTES_MAX)
-		keys_fit_inline = true;
-
-	/* rfc4106_givencrypt shared descriptor */
-	desc = ctx->sh_desc_givenc;
-
-	init_sh_desc(desc, HDR_SHARE_SERIAL);
-
-	/* Skip key loading if it is loaded due to sharing */
-	key_jump_cmd = append_jump(desc, JUMP_JSL | JUMP_TEST_ALL |
-				   JUMP_COND_SHRD);
-	if (keys_fit_inline)
-		append_key_as_imm(desc, (void *)ctx->key, ctx->enckeylen,
-				  ctx->enckeylen, CLASS_1 | KEY_DEST_CLASS_REG);
-	else
-		append_key(desc, ctx->key_dma, ctx->enckeylen,
-			   CLASS_1 | KEY_DEST_CLASS_REG);
-	set_jump_tgt_here(desc, key_jump_cmd);
-
-	/* Generate IV */
-	geniv = NFIFOENTRY_STYPE_PAD | NFIFOENTRY_DEST_DECO |
-		NFIFOENTRY_DTYPE_MSG | NFIFOENTRY_LC1 |
-		NFIFOENTRY_PTYPE_RND | (tfm->ivsize << NFIFOENTRY_DLEN_SHIFT);
-	append_load_imm_u32(desc, geniv, LDST_CLASS_IND_CCB |
-			    LDST_SRCDST_WORD_INFO_FIFO | LDST_IMM);
-	append_cmd(desc, CMD_LOAD | DISABLE_AUTO_INFO_FIFO);
-	move_cmd = append_move(desc, MOVE_SRC_INFIFO | MOVE_DEST_DESCBUF |
-			       (tfm->ivsize << MOVE_LEN_SHIFT));
-	append_cmd(desc, CMD_LOAD | ENABLE_AUTO_INFO_FIFO);
-
-	/* Copy generated IV to OFIFO */
-	write_iv_cmd = append_move(desc, MOVE_SRC_DESCBUF | MOVE_DEST_OUTFIFO |
-				   (tfm->ivsize << MOVE_LEN_SHIFT));
-
-	/* Class 1 operation */
-	append_operation(desc, ctx->class1_alg_type |
-			 OP_ALG_AS_INITFINAL | OP_ALG_ENCRYPT);
-
-	/* ivsize + cryptlen = seqoutlen - authsize */
-	append_math_sub_imm_u32(desc, REG3, SEQOUTLEN, IMM, ctx->authsize);
-
-	/* assoclen = seqinlen - (ivsize + cryptlen) */
-	append_math_sub(desc, VARSEQINLEN, SEQINLEN, REG3, CAAM_CMD_SZ);
-
-	/* Will write ivsize + cryptlen */
-	append_math_add(desc, VARSEQOUTLEN, REG3, REG0, CAAM_CMD_SZ);
-
-	/* Read Salt and generated IV */
-	append_cmd(desc, CMD_FIFO_LOAD | FIFOLD_CLASS_CLASS1 | FIFOLD_TYPE_IV |
-		   FIFOLD_TYPE_FLUSH1 | IMMEDIATE | 12);
-	/* Append Salt */
-	append_data(desc, (void *)(ctx->key + ctx->enckeylen), 4);
-	set_move_tgt_here(desc, move_cmd);
-	set_move_tgt_here(desc, write_iv_cmd);
-	/* Blank commands. Will be overwritten by generated IV. */
-	append_cmd(desc, 0x00000000);
-	append_cmd(desc, 0x00000000);
-	/* End of blank commands */
-
-	/* No need to reload iv */
-	append_seq_fifo_load(desc, tfm->ivsize, FIFOLD_CLASS_SKIP);
-
-	/* Read assoc data */
-	append_seq_fifo_load(desc, 0, FIFOLD_CLASS_CLASS1 | FIFOLDST_VLF |
-			     FIFOLD_TYPE_AAD | FIFOLD_TYPE_FLUSH1);
-
-	/* Will read cryptlen */
-	append_math_add(desc, VARSEQINLEN, SEQINLEN, REG0, CAAM_CMD_SZ);
-
-	/* Store generated IV and encrypted data */
-	append_seq_fifo_store(desc, 0, FIFOST_TYPE_MESSAGE_DATA | FIFOLDST_VLF);
-
-	/* Read payload data */
-	append_seq_fifo_load(desc, 0, FIFOLD_CLASS_CLASS1 | FIFOLDST_VLF |
-			     FIFOLD_TYPE_MSG | FIFOLD_TYPE_LAST1);
-
-	/* Write ICV */
-	append_seq_store(desc, ctx->authsize, LDST_CLASS_1_CCB |
-			 LDST_SRCDST_BYTE_CONTEXT);
-
-	ctx->sh_desc_givenc_dma = dma_map_single(jrdev, desc,
-						 desc_bytes(desc),
-						 DMA_TO_DEVICE);
-	if (dma_mapping_error(jrdev, ctx->sh_desc_givenc_dma)) {
-		dev_err(jrdev, "unable to map shared descriptor\n");
-		return -ENOMEM;
-	}
-#ifdef DEBUG
-	print_hex_dump(KERN_ERR,
-		       "rfc4106 givenc shdesc@"__stringify(__LINE__)": ",
-		       DUMP_PREFIX_ADDRESS, 16, 4, desc,
-		       desc_bytes(desc), 1);
-#endif
-
 	return 0;
 }
 
@@ -1249,14 +1100,12 @@ static int rfc4106_setauthsize(struct crypto_aead *authenc,
 
 static int rfc4543_set_sh_desc(struct crypto_aead *aead)
 {
-	struct aead_tfm *tfm = &aead->base.crt_aead;
 	struct caam_ctx *ctx = crypto_aead_ctx(aead);
 	struct device *jrdev = ctx->jrdev;
 	bool keys_fit_inline = false;
-	u32 *key_jump_cmd, *write_iv_cmd, *write_aad_cmd;
+	u32 *key_jump_cmd;
 	u32 *read_move_cmd, *write_move_cmd;
 	u32 *desc;
-	u32 geniv;
 
 	if (!ctx->enckeylen || !ctx->authsize)
 		return 0;
@@ -1266,7 +1115,7 @@ static int rfc4543_set_sh_desc(struct crypto_aead *aead)
 	 * Job Descriptor and Shared Descriptor
 	 * must fit into the 64-word Descriptor h/w Buffer
 	 */
-	if (DESC_RFC4543_ENC_LEN + DESC_JOB_IO_LEN +
+	if (DESC_RFC4543_ENC_LEN + GCM_DESC_JOB_IO_LEN +
 	    ctx->enckeylen <= CAAM_DESC_BYTES_MAX)
 		keys_fit_inline = true;
 
@@ -1289,48 +1138,8 @@ static int rfc4543_set_sh_desc(struct crypto_aead *aead)
 	append_operation(desc, ctx->class1_alg_type |
 			 OP_ALG_AS_INITFINAL | OP_ALG_ENCRYPT);
 
-	/* Load AES-GMAC ESP IV into Math1 register */
-	append_cmd(desc, CMD_SEQ_LOAD | LDST_SRCDST_WORD_DECO_MATH1 |
-		   LDST_CLASS_DECO | tfm->ivsize);
-
-	/* Wait the DMA transaction to finish */
-	append_jump(desc, JUMP_TEST_ALL | JUMP_COND_CALM |
-		    (1 << JUMP_OFFSET_SHIFT));
-
-	/* Overwrite blank immediate AES-GMAC ESP IV data */
-	write_iv_cmd = append_move(desc, MOVE_SRC_MATH1 | MOVE_DEST_DESCBUF |
-				   (tfm->ivsize << MOVE_LEN_SHIFT));
-
-	/* Overwrite blank immediate AAD data */
-	write_aad_cmd = append_move(desc, MOVE_SRC_MATH1 | MOVE_DEST_DESCBUF |
-				    (tfm->ivsize << MOVE_LEN_SHIFT));
-
-	/* cryptlen = seqoutlen - authsize */
-	append_math_sub_imm_u32(desc, REG3, SEQOUTLEN, IMM, ctx->authsize);
-
-	/* assoclen = (seqinlen - ivsize) - cryptlen */
-	append_math_sub(desc, VARSEQINLEN, SEQINLEN, REG3, CAAM_CMD_SZ);
-
-	/* Read Salt and AES-GMAC ESP IV */
-	append_cmd(desc, CMD_FIFO_LOAD | FIFOLD_CLASS_CLASS1 | IMMEDIATE |
-		   FIFOLD_TYPE_IV | FIFOLD_TYPE_FLUSH1 | (4 + tfm->ivsize));
-	/* Append Salt */
-	append_data(desc, (void *)(ctx->key + ctx->enckeylen), 4);
-	set_move_tgt_here(desc, write_iv_cmd);
-	/* Blank commands. Will be overwritten by AES-GMAC ESP IV. */
-	append_cmd(desc, 0x00000000);
-	append_cmd(desc, 0x00000000);
-	/* End of blank commands */
-
-	/* Read assoc data */
-	append_seq_fifo_load(desc, 0, FIFOLD_CLASS_CLASS1 | FIFOLDST_VLF |
-			     FIFOLD_TYPE_AAD);
-
-	/* Will read cryptlen bytes */
-	append_math_add(desc, VARSEQINLEN, ZERO, REG3, CAAM_CMD_SZ);
-
-	/* Will write cryptlen bytes */
-	append_math_add(desc, VARSEQOUTLEN, ZERO, REG3, CAAM_CMD_SZ);
+	/* assoclen + cryptlen = seqinlen */
+	append_math_sub(desc, REG3, SEQINLEN, REG0, CAAM_CMD_SZ);
 
 	/*
 	 * MOVE_LEN opcode is not available in all SEC HW revisions,
@@ -1342,16 +1151,13 @@ static int rfc4543_set_sh_desc(struct crypto_aead *aead)
 	write_move_cmd = append_move(desc, MOVE_SRC_MATH3 | MOVE_DEST_DESCBUF |
 				     (0x8 << MOVE_LEN_SHIFT));
 
-	/* Authenticate AES-GMAC ESP IV  */
-	append_cmd(desc, CMD_FIFO_LOAD | FIFOLD_CLASS_CLASS1 | IMMEDIATE |
-		   FIFOLD_TYPE_AAD | tfm->ivsize);
-	set_move_tgt_here(desc, write_aad_cmd);
-	/* Blank commands. Will be overwritten by AES-GMAC ESP IV. */
-	append_cmd(desc, 0x00000000);
-	append_cmd(desc, 0x00000000);
-	/* End of blank commands */
+	/* Will read assoclen + cryptlen bytes */
+	append_math_sub(desc, VARSEQINLEN, SEQINLEN, REG0, CAAM_CMD_SZ);
 
-	/* Read and write cryptlen bytes */
+	/* Will write assoclen + cryptlen bytes */
+	append_math_sub(desc, VARSEQOUTLEN, SEQINLEN, REG0, CAAM_CMD_SZ);
+
+	/* Read and write assoclen + cryptlen bytes */
 	aead_append_src_dst(desc, FIFOLD_TYPE_AAD);
 
 	set_move_tgt_here(desc, read_move_cmd);
@@ -1382,7 +1188,7 @@ static int rfc4543_set_sh_desc(struct crypto_aead *aead)
 	 * must all fit into the 64-word Descriptor h/w Buffer
 	 */
 	keys_fit_inline = false;
-	if (DESC_RFC4543_DEC_LEN + DESC_JOB_IO_LEN +
+	if (DESC_RFC4543_DEC_LEN + GCM_DESC_JOB_IO_LEN +
 	    ctx->enckeylen <= CAAM_DESC_BYTES_MAX)
 		keys_fit_inline = true;
 
@@ -1405,28 +1211,8 @@ static int rfc4543_set_sh_desc(struct crypto_aead *aead)
 	append_operation(desc, ctx->class1_alg_type |
 			 OP_ALG_AS_INITFINAL | OP_ALG_DECRYPT | OP_ALG_ICV_ON);
 
-	/* Load AES-GMAC ESP IV into Math1 register */
-	append_cmd(desc, CMD_SEQ_LOAD | LDST_SRCDST_WORD_DECO_MATH1 |
-		   LDST_CLASS_DECO | tfm->ivsize);
-
-	/* Wait the DMA transaction to finish */
-	append_jump(desc, JUMP_TEST_ALL | JUMP_COND_CALM |
-		    (1 << JUMP_OFFSET_SHIFT));
-
-	/* assoclen + cryptlen = (seqinlen - ivsize) - icvsize */
-	append_math_sub_imm_u32(desc, REG3, SEQINLEN, IMM, ctx->authsize);
-
-	/* Overwrite blank immediate AES-GMAC ESP IV data */
-	write_iv_cmd = append_move(desc, MOVE_SRC_MATH1 | MOVE_DEST_DESCBUF |
-				   (tfm->ivsize << MOVE_LEN_SHIFT));
-
-	/* Overwrite blank immediate AAD data */
-	write_aad_cmd = append_move(desc, MOVE_SRC_MATH1 | MOVE_DEST_DESCBUF |
-				    (tfm->ivsize << MOVE_LEN_SHIFT));
-
-	/* assoclen = (assoclen + cryptlen) - cryptlen */
-	append_math_sub(desc, REG2, SEQOUTLEN, REG0, CAAM_CMD_SZ);
-	append_math_sub(desc, VARSEQINLEN, REG3, REG2, CAAM_CMD_SZ);
+	/* assoclen + cryptlen = seqoutlen */
+	append_math_sub(desc, REG3, SEQOUTLEN, REG0, CAAM_CMD_SZ);
 
 	/*
 	 * MOVE_LEN opcode is not available in all SEC HW revisions,
@@ -1438,40 +1224,16 @@ static int rfc4543_set_sh_desc(struct crypto_aead *aead)
 	write_move_cmd = append_move(desc, MOVE_SRC_MATH3 | MOVE_DEST_DESCBUF |
 				     (0x8 << MOVE_LEN_SHIFT));
 
-	/* Read Salt and AES-GMAC ESP IV */
-	append_cmd(desc, CMD_FIFO_LOAD | FIFOLD_CLASS_CLASS1 | IMMEDIATE |
-		   FIFOLD_TYPE_IV | FIFOLD_TYPE_FLUSH1 | (4 + tfm->ivsize));
-	/* Append Salt */
-	append_data(desc, (void *)(ctx->key + ctx->enckeylen), 4);
-	set_move_tgt_here(desc, write_iv_cmd);
-	/* Blank commands. Will be overwritten by AES-GMAC ESP IV. */
-	append_cmd(desc, 0x00000000);
-	append_cmd(desc, 0x00000000);
-	/* End of blank commands */
-
-	/* Read assoc data */
-	append_seq_fifo_load(desc, 0, FIFOLD_CLASS_CLASS1 | FIFOLDST_VLF |
-			     FIFOLD_TYPE_AAD);
-
-	/* Will read cryptlen bytes */
-	append_math_add(desc, VARSEQINLEN, ZERO, REG2, CAAM_CMD_SZ);
+	/* Will read assoclen + cryptlen bytes */
+	append_math_sub(desc, VARSEQINLEN, SEQOUTLEN, REG0, CAAM_CMD_SZ);
 
-	/* Will write cryptlen bytes */
-	append_math_add(desc, VARSEQOUTLEN, ZERO, REG2, CAAM_CMD_SZ);
-
-	/* Authenticate AES-GMAC ESP IV  */
-	append_cmd(desc, CMD_FIFO_LOAD | FIFOLD_CLASS_CLASS1 | IMMEDIATE |
-		   FIFOLD_TYPE_AAD | tfm->ivsize);
-	set_move_tgt_here(desc, write_aad_cmd);
-	/* Blank commands. Will be overwritten by AES-GMAC ESP IV. */
-	append_cmd(desc, 0x00000000);
-	append_cmd(desc, 0x00000000);
-	/* End of blank commands */
+	/* Will write assoclen + cryptlen bytes */
+	append_math_sub(desc, VARSEQOUTLEN, SEQOUTLEN, REG0, CAAM_CMD_SZ);
 
 	/* Store payload data */
 	append_seq_fifo_store(desc, 0, FIFOST_TYPE_MESSAGE_DATA | FIFOLDST_VLF);
 
-	/* In-snoop cryptlen data */
+	/* In-snoop assoclen + cryptlen data */
 	append_seq_fifo_load(desc, 0, FIFOLD_CLASS_BOTH | FIFOLDST_VLF |
 			     FIFOLD_TYPE_AAD | FIFOLD_TYPE_LAST2FLUSH1);
 
@@ -1499,135 +1261,6 @@ static int rfc4543_set_sh_desc(struct crypto_aead *aead)
 		       desc_bytes(desc), 1);
 #endif
 
-	/*
-	 * Job Descriptor and Shared Descriptors
-	 * must all fit into the 64-word Descriptor h/w Buffer
-	 */
-	keys_fit_inline = false;
-	if (DESC_RFC4543_GIVENC_LEN + DESC_JOB_IO_LEN +
-	    ctx->enckeylen <= CAAM_DESC_BYTES_MAX)
-		keys_fit_inline = true;
-
-	/* rfc4543_givencrypt shared descriptor */
-	desc = ctx->sh_desc_givenc;
-
-	init_sh_desc(desc, HDR_SHARE_SERIAL);
-
-	/* Skip key loading if it is loaded due to sharing */
-	key_jump_cmd = append_jump(desc, JUMP_JSL | JUMP_TEST_ALL |
-				   JUMP_COND_SHRD);
-	if (keys_fit_inline)
-		append_key_as_imm(desc, (void *)ctx->key, ctx->enckeylen,
-				  ctx->enckeylen, CLASS_1 | KEY_DEST_CLASS_REG);
-	else
-		append_key(desc, ctx->key_dma, ctx->enckeylen,
-			   CLASS_1 | KEY_DEST_CLASS_REG);
-	set_jump_tgt_here(desc, key_jump_cmd);
-
-	/* Generate IV */
-	geniv = NFIFOENTRY_STYPE_PAD | NFIFOENTRY_DEST_DECO |
-		NFIFOENTRY_DTYPE_MSG | NFIFOENTRY_LC1 |
-		NFIFOENTRY_PTYPE_RND | (tfm->ivsize << NFIFOENTRY_DLEN_SHIFT);
-	append_load_imm_u32(desc, geniv, LDST_CLASS_IND_CCB |
-			    LDST_SRCDST_WORD_INFO_FIFO | LDST_IMM);
-	append_cmd(desc, CMD_LOAD | DISABLE_AUTO_INFO_FIFO);
-	/* Move generated IV to Math1 register */
-	append_move(desc, MOVE_SRC_INFIFO | MOVE_DEST_MATH1 |
-		    (tfm->ivsize << MOVE_LEN_SHIFT));
-	append_cmd(desc, CMD_LOAD | ENABLE_AUTO_INFO_FIFO);
-
-	/* Overwrite blank immediate AES-GMAC IV data */
-	write_iv_cmd = append_move(desc, MOVE_SRC_MATH1 | MOVE_DEST_DESCBUF |
-				   (tfm->ivsize << MOVE_LEN_SHIFT));
-
-	/* Overwrite blank immediate AAD data */
-	write_aad_cmd = append_move(desc, MOVE_SRC_MATH1 | MOVE_DEST_DESCBUF |
-				    (tfm->ivsize << MOVE_LEN_SHIFT));
-
-	/* Copy generated IV to OFIFO */
-	append_move(desc, MOVE_SRC_MATH1 | MOVE_DEST_OUTFIFO |
-		    (tfm->ivsize << MOVE_LEN_SHIFT));
-
-	/* Class 1 operation */
-	append_operation(desc, ctx->class1_alg_type |
-			 OP_ALG_AS_INITFINAL | OP_ALG_ENCRYPT);
-
-	/* ivsize + cryptlen = seqoutlen - authsize */
-	append_math_sub_imm_u32(desc, REG3, SEQOUTLEN, IMM, ctx->authsize);
-
-	/* assoclen = seqinlen - (ivsize + cryptlen) */
-	append_math_sub(desc, VARSEQINLEN, SEQINLEN, REG3, CAAM_CMD_SZ);
-
-	/* Will write ivsize + cryptlen */
-	append_math_add(desc, VARSEQOUTLEN, REG3, REG0, CAAM_CMD_SZ);
-
-	/*
-	 * MOVE_LEN opcode is not available in all SEC HW revisions,
-	 * thus need to do some magic, i.e. self-patch the descriptor
-	 * buffer.
-	 */
-	read_move_cmd = append_move(desc, MOVE_SRC_DESCBUF | MOVE_DEST_MATH3 |
-				    (0x6 << MOVE_LEN_SHIFT));
-	write_move_cmd = append_move(desc, MOVE_SRC_MATH3 | MOVE_DEST_DESCBUF |
-				     (0x8 << MOVE_LEN_SHIFT));
-
-	/* Read Salt and AES-GMAC generated IV */
-	append_cmd(desc, CMD_FIFO_LOAD | FIFOLD_CLASS_CLASS1 | IMMEDIATE |
-		   FIFOLD_TYPE_IV | FIFOLD_TYPE_FLUSH1 | (4 + tfm->ivsize));
-	/* Append Salt */
-	append_data(desc, (void *)(ctx->key + ctx->enckeylen), 4);
-	set_move_tgt_here(desc, write_iv_cmd);
-	/* Blank commands. Will be overwritten by AES-GMAC generated IV. */
-	append_cmd(desc, 0x00000000);
-	append_cmd(desc, 0x00000000);
-	/* End of blank commands */
-
-	/* No need to reload iv */
-	append_seq_fifo_load(desc, tfm->ivsize, FIFOLD_CLASS_SKIP);
-
-	/* Read assoc data */
-	append_seq_fifo_load(desc, 0, FIFOLD_CLASS_CLASS1 | FIFOLDST_VLF |
-			     FIFOLD_TYPE_AAD);
-
-	/* Will read cryptlen */
-	append_math_add(desc, VARSEQINLEN, SEQINLEN, REG0, CAAM_CMD_SZ);
-
-	/* Authenticate AES-GMAC IV  */
-	append_cmd(desc, CMD_FIFO_LOAD | FIFOLD_CLASS_CLASS1 | IMMEDIATE |
-		   FIFOLD_TYPE_AAD | tfm->ivsize);
-	set_move_tgt_here(desc, write_aad_cmd);
-	/* Blank commands. Will be overwritten by AES-GMAC IV. */
-	append_cmd(desc, 0x00000000);
-	append_cmd(desc, 0x00000000);
-	/* End of blank commands */
-
-	/* Read and write cryptlen bytes */
-	aead_append_src_dst(desc, FIFOLD_TYPE_AAD);
-
-	set_move_tgt_here(desc, read_move_cmd);
-	set_move_tgt_here(desc, write_move_cmd);
-	append_cmd(desc, CMD_LOAD | DISABLE_AUTO_INFO_FIFO);
-	/* Move payload data to OFIFO */
-	append_move(desc, MOVE_SRC_INFIFO_CL | MOVE_DEST_OUTFIFO);
-
-	/* Write ICV */
-	append_seq_store(desc, ctx->authsize, LDST_CLASS_1_CCB |
-			 LDST_SRCDST_BYTE_CONTEXT);
-
-	ctx->sh_desc_givenc_dma = dma_map_single(jrdev, desc,
-						 desc_bytes(desc),
-						 DMA_TO_DEVICE);
-	if (dma_mapping_error(jrdev, ctx->sh_desc_givenc_dma)) {
-		dev_err(jrdev, "unable to map shared descriptor\n");
-		return -ENOMEM;
-	}
-#ifdef DEBUG
-	print_hex_dump(KERN_ERR,
-		       "rfc4543 givenc shdesc@"__stringify(__LINE__)": ",
-		       DUMP_PREFIX_ADDRESS, 16, 4, desc,
-		       desc_bytes(desc), 1);
-#endif
-
 	return 0;
 }
 
@@ -2100,7 +1733,7 @@ struct aead_edesc {
 	int sec4_sg_bytes;
 	dma_addr_t sec4_sg_dma;
 	struct sec4_sg_entry *sec4_sg;
-	u32 hw_desc[0];
+	u32 hw_desc[];
 };
 
 /*
@@ -2154,6 +1787,16 @@ static void aead_unmap(struct device *dev,
 		       struct aead_edesc *edesc,
 		       struct aead_request *req)
 {
+	caam_unmap(dev, req->src, req->dst,
+		   edesc->src_nents, edesc->src_chained, edesc->dst_nents,
+		   edesc->dst_chained, 0, 0,
+		   edesc->sec4_sg_dma, edesc->sec4_sg_bytes);
+}
+
+static void old_aead_unmap(struct device *dev,
+			   struct aead_edesc *edesc,
+			   struct aead_request *req)
+{
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
 	int ivsize = crypto_aead_ivsize(aead);
 
@@ -2184,6 +1827,28 @@ static void aead_encrypt_done(struct device *jrdev, u32 *desc, u32 err,
 {
 	struct aead_request *req = context;
 	struct aead_edesc *edesc;
+
+#ifdef DEBUG
+	dev_err(jrdev, "%s %d: err 0x%x\n", __func__, __LINE__, err);
+#endif
+
+	edesc = container_of(desc, struct aead_edesc, hw_desc[0]);
+
+	if (err)
+		caam_jr_strstatus(jrdev, err);
+
+	aead_unmap(jrdev, edesc, req);
+
+	kfree(edesc);
+
+	aead_request_complete(req, err);
+}
+
+static void old_aead_encrypt_done(struct device *jrdev, u32 *desc, u32 err,
+				  void *context)
+{
+	struct aead_request *req = context;
+	struct aead_edesc *edesc;
 #ifdef DEBUG
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
 	struct caam_ctx *ctx = crypto_aead_ctx(aead);
@@ -2198,7 +1863,7 @@ static void aead_encrypt_done(struct device *jrdev, u32 *desc, u32 err,
 	if (err)
 		caam_jr_strstatus(jrdev, err);
 
-	aead_unmap(jrdev, edesc, req);
+	old_aead_unmap(jrdev, edesc, req);
 
 #ifdef DEBUG
 	print_hex_dump(KERN_ERR, "assoc  @"__stringify(__LINE__)": ",
@@ -2223,6 +1888,34 @@ static void aead_decrypt_done(struct device *jrdev, u32 *desc, u32 err,
 {
 	struct aead_request *req = context;
 	struct aead_edesc *edesc;
+
+#ifdef DEBUG
+	dev_err(jrdev, "%s %d: err 0x%x\n", __func__, __LINE__, err);
+#endif
+
+	edesc = container_of(desc, struct aead_edesc, hw_desc[0]);
+
+	if (err)
+		caam_jr_strstatus(jrdev, err);
+
+	aead_unmap(jrdev, edesc, req);
+
+	/*
+	 * verify hw auth check passed else return -EBADMSG
+	 */
+	if ((err & JRSTA_CCBERR_ERRID_MASK) == JRSTA_CCBERR_ERRID_ICVCHK)
+		err = -EBADMSG;
+
+	kfree(edesc);
+
+	aead_request_complete(req, err);
+}
+
+static void old_aead_decrypt_done(struct device *jrdev, u32 *desc, u32 err,
+				  void *context)
+{
+	struct aead_request *req = context;
+	struct aead_edesc *edesc;
 #ifdef DEBUG
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
 	struct caam_ctx *ctx = crypto_aead_ctx(aead);
@@ -2246,7 +1939,7 @@ static void aead_decrypt_done(struct device *jrdev, u32 *desc, u32 err,
 	if (err)
 		caam_jr_strstatus(jrdev, err);
 
-	aead_unmap(jrdev, edesc, req);
+	old_aead_unmap(jrdev, edesc, req);
 
 	/*
 	 * verify hw auth check passed else return -EBADMSG
@@ -2342,10 +2035,10 @@ static void ablkcipher_decrypt_done(struct device *jrdev, u32 *desc, u32 err,
 /*
  * Fill in aead job descriptor
  */
-static void init_aead_job(u32 *sh_desc, dma_addr_t ptr,
-			  struct aead_edesc *edesc,
-			  struct aead_request *req,
-			  bool all_contig, bool encrypt)
+static void old_init_aead_job(u32 *sh_desc, dma_addr_t ptr,
+			      struct aead_edesc *edesc,
+			      struct aead_request *req,
+			      bool all_contig, bool encrypt)
 {
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
 	struct caam_ctx *ctx = crypto_aead_ctx(aead);
@@ -2425,6 +2118,97 @@ static void init_aead_job(u32 *sh_desc, dma_addr_t ptr,
 }
 
 /*
+ * Fill in aead job descriptor
+ */
+static void init_aead_job(struct aead_request *req,
+			  struct aead_edesc *edesc,
+			  bool all_contig, bool encrypt)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct caam_ctx *ctx = crypto_aead_ctx(aead);
+	int authsize = ctx->authsize;
+	u32 *desc = edesc->hw_desc;
+	u32 out_options, in_options;
+	dma_addr_t dst_dma, src_dma;
+	int len, sec4_sg_index = 0;
+	dma_addr_t ptr;
+	u32 *sh_desc;
+
+	sh_desc = encrypt ? ctx->sh_desc_enc : ctx->sh_desc_dec;
+	ptr = encrypt ? ctx->sh_desc_enc_dma : ctx->sh_desc_dec_dma;
+
+	len = desc_len(sh_desc);
+	init_job_desc_shared(desc, ptr, len, HDR_SHARE_DEFER | HDR_REVERSE);
+
+	if (all_contig) {
+		src_dma = sg_dma_address(req->src);
+		in_options = 0;
+	} else {
+		src_dma = edesc->sec4_sg_dma;
+		sec4_sg_index += edesc->src_nents;
+		in_options = LDST_SGF;
+	}
+
+	append_seq_in_ptr(desc, src_dma, req->assoclen + req->cryptlen,
+			  in_options);
+
+	dst_dma = src_dma;
+	out_options = in_options;
+
+	if (unlikely(req->src != req->dst)) {
+		if (!edesc->dst_nents) {
+			dst_dma = sg_dma_address(req->dst);
+		} else {
+			dst_dma = edesc->sec4_sg_dma +
+				  sec4_sg_index *
+				  sizeof(struct sec4_sg_entry);
+			out_options = LDST_SGF;
+		}
+	}
+
+	if (encrypt)
+		append_seq_out_ptr(desc, dst_dma,
+				   req->assoclen + req->cryptlen + authsize,
+				   out_options);
+	else
+		append_seq_out_ptr(desc, dst_dma,
+				   req->assoclen + req->cryptlen - authsize,
+				   out_options);
+
+	/* REG3 = assoclen */
+	append_math_add_imm_u32(desc, REG3, ZERO, IMM, req->assoclen);
+}
+
+static void init_gcm_job(struct aead_request *req,
+			 struct aead_edesc *edesc,
+			 bool all_contig, bool encrypt)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct caam_ctx *ctx = crypto_aead_ctx(aead);
+	unsigned int ivsize = crypto_aead_ivsize(aead);
+	u32 *desc = edesc->hw_desc;
+	bool generic_gcm = (ivsize == 12);
+	unsigned int last;
+
+	init_aead_job(req, edesc, all_contig, encrypt);
+
+	/* BUG This should not be specific to generic GCM. */
+	last = 0;
+	if (encrypt && generic_gcm && !(req->assoclen + req->cryptlen))
+		last = FIFOLD_TYPE_LAST1;
+
+	/* Read GCM IV */
+	append_cmd(desc, CMD_FIFO_LOAD | FIFOLD_CLASS_CLASS1 | IMMEDIATE |
+			 FIFOLD_TYPE_IV | FIFOLD_TYPE_FLUSH1 | 12 | last);
+	/* Append Salt */
+	if (!generic_gcm)
+		append_data(desc, ctx->key + ctx->enckeylen, 4);
+	/* Append IV */
+	append_data(desc, req->iv, ivsize);
+	/* End of blank commands */
+}
+
+/*
  * Fill in aead givencrypt job descriptor
  */
 static void init_aead_giv_job(u32 *sh_desc, dma_addr_t ptr,
@@ -2608,9 +2392,10 @@ static void init_ablkcipher_giv_job(u32 *sh_desc, dma_addr_t ptr,
 /*
  * allocate and map the aead extended descriptor
  */
-static struct aead_edesc *aead_edesc_alloc(struct aead_request *req,
-					   int desc_bytes, bool *all_contig_ptr,
-					   bool encrypt)
+static struct aead_edesc *old_aead_edesc_alloc(struct aead_request *req,
+					       int desc_bytes,
+					       bool *all_contig_ptr,
+					       bool encrypt)
 {
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
 	struct caam_ctx *ctx = crypto_aead_ctx(aead);
@@ -2713,10 +2498,8 @@ static struct aead_edesc *aead_edesc_alloc(struct aead_request *req,
 	sec4_sg_index = 0;
 	if (!all_contig) {
 		if (!is_gcm) {
-			sg_to_sec4_sg(req->assoc,
-				      assoc_nents,
-				      edesc->sec4_sg +
-				      sec4_sg_index, 0);
+			sg_to_sec4_sg_len(req->assoc, req->assoclen,
+					  edesc->sec4_sg + sec4_sg_index);
 			sec4_sg_index += assoc_nents;
 		}
 
@@ -2725,10 +2508,8 @@ static struct aead_edesc *aead_edesc_alloc(struct aead_request *req,
 		sec4_sg_index += 1;
 
 		if (is_gcm) {
-			sg_to_sec4_sg(req->assoc,
-				      assoc_nents,
-				      edesc->sec4_sg +
-				      sec4_sg_index, 0);
+			sg_to_sec4_sg_len(req->assoc, req->assoclen,
+					  edesc->sec4_sg + sec4_sg_index);
 			sec4_sg_index += assoc_nents;
 		}
 
@@ -2752,7 +2533,124 @@ static struct aead_edesc *aead_edesc_alloc(struct aead_request *req,
 	return edesc;
 }
 
-static int aead_encrypt(struct aead_request *req)
+/*
+ * allocate and map the aead extended descriptor
+ */
+static struct aead_edesc *aead_edesc_alloc(struct aead_request *req,
+					   int desc_bytes, bool *all_contig_ptr,
+					   bool encrypt)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct caam_ctx *ctx = crypto_aead_ctx(aead);
+	struct device *jrdev = ctx->jrdev;
+	gfp_t flags = (req->base.flags & (CRYPTO_TFM_REQ_MAY_BACKLOG |
+		       CRYPTO_TFM_REQ_MAY_SLEEP)) ? GFP_KERNEL : GFP_ATOMIC;
+	int src_nents, dst_nents = 0;
+	struct aead_edesc *edesc;
+	int sgc;
+	bool all_contig = true;
+	bool src_chained = false, dst_chained = false;
+	int sec4_sg_index, sec4_sg_len = 0, sec4_sg_bytes;
+	unsigned int authsize = ctx->authsize;
+
+	if (unlikely(req->dst != req->src)) {
+		src_nents = sg_count(req->src, req->assoclen + req->cryptlen,
+				     &src_chained);
+		dst_nents = sg_count(req->dst,
+				     req->assoclen + req->cryptlen +
+					(encrypt ? authsize : (-authsize)),
+				     &dst_chained);
+	} else {
+		src_nents = sg_count(req->src,
+				     req->assoclen + req->cryptlen +
+					(encrypt ? authsize : 0),
+				     &src_chained);
+	}
+
+	/* Check if data are contiguous. */
+	all_contig = !src_nents;
+	if (!all_contig) {
+		src_nents = src_nents ? : 1;
+		sec4_sg_len = src_nents;
+	}
+
+	sec4_sg_len += dst_nents;
+
+	sec4_sg_bytes = sec4_sg_len * sizeof(struct sec4_sg_entry);
+
+	/* allocate space for base edesc and hw desc commands, link tables */
+	edesc = kzalloc(sizeof(struct aead_edesc) + desc_bytes +
+			sec4_sg_bytes, GFP_DMA | flags);
+	if (!edesc) {
+		dev_err(jrdev, "could not allocate extended descriptor\n");
+		return ERR_PTR(-ENOMEM);
+	}
+
+	if (likely(req->src == req->dst)) {
+		sgc = dma_map_sg_chained(jrdev, req->src, src_nents ? : 1,
+					 DMA_BIDIRECTIONAL, src_chained);
+		if (unlikely(!sgc)) {
+			dev_err(jrdev, "unable to map source\n");
+			kfree(edesc);
+			return ERR_PTR(-ENOMEM);
+		}
+	} else {
+		sgc = dma_map_sg_chained(jrdev, req->src, src_nents ? : 1,
+					 DMA_TO_DEVICE, src_chained);
+		if (unlikely(!sgc)) {
+			dev_err(jrdev, "unable to map source\n");
+			kfree(edesc);
+			return ERR_PTR(-ENOMEM);
+		}
+
+		sgc = dma_map_sg_chained(jrdev, req->dst, dst_nents ? : 1,
+					 DMA_FROM_DEVICE, dst_chained);
+		if (unlikely(!sgc)) {
+			dev_err(jrdev, "unable to map destination\n");
+			dma_unmap_sg_chained(jrdev, req->src, src_nents ? : 1,
+					     DMA_TO_DEVICE, src_chained);
+			kfree(edesc);
+			return ERR_PTR(-ENOMEM);
+		}
+	}
+
+	edesc->src_nents = src_nents;
+	edesc->src_chained = src_chained;
+	edesc->dst_nents = dst_nents;
+	edesc->dst_chained = dst_chained;
+	edesc->sec4_sg = (void *)edesc + sizeof(struct aead_edesc) +
+			 desc_bytes;
+	*all_contig_ptr = all_contig;
+
+	sec4_sg_index = 0;
+	if (!all_contig) {
+		sg_to_sec4_sg_last(req->src, src_nents,
+			      edesc->sec4_sg + sec4_sg_index, 0);
+		sec4_sg_index += src_nents;
+	}
+	if (dst_nents) {
+		sg_to_sec4_sg_last(req->dst, dst_nents,
+				   edesc->sec4_sg + sec4_sg_index, 0);
+	}
+
+	if (!sec4_sg_bytes)
+		return edesc;
+
+	edesc->sec4_sg_dma = dma_map_single(jrdev, edesc->sec4_sg,
+					    sec4_sg_bytes, DMA_TO_DEVICE);
+	if (dma_mapping_error(jrdev, edesc->sec4_sg_dma)) {
+		dev_err(jrdev, "unable to map S/G table\n");
+		aead_unmap(jrdev, edesc, req);
+		kfree(edesc);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	edesc->sec4_sg_bytes = sec4_sg_bytes;
+
+	return edesc;
+}
+
+static int gcm_encrypt(struct aead_request *req)
 {
 	struct aead_edesc *edesc;
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
@@ -2763,14 +2661,12 @@ static int aead_encrypt(struct aead_request *req)
 	int ret = 0;
 
 	/* allocate extended descriptor */
-	edesc = aead_edesc_alloc(req, DESC_JOB_IO_LEN *
-				 CAAM_CMD_SZ, &all_contig, true);
+	edesc = aead_edesc_alloc(req, GCM_DESC_JOB_IO_LEN, &all_contig, true);
 	if (IS_ERR(edesc))
 		return PTR_ERR(edesc);
 
 	/* Create and submit job descriptor */
-	init_aead_job(ctx->sh_desc_enc, ctx->sh_desc_enc_dma, edesc, req,
-		      all_contig, true);
+	init_gcm_job(req, edesc, all_contig, true);
 #ifdef DEBUG
 	print_hex_dump(KERN_ERR, "aead jobdesc@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, edesc->hw_desc,
@@ -2789,7 +2685,7 @@ static int aead_encrypt(struct aead_request *req)
 	return ret;
 }
 
-static int aead_decrypt(struct aead_request *req)
+static int old_aead_encrypt(struct aead_request *req)
 {
 	struct aead_edesc *edesc;
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
@@ -2800,8 +2696,80 @@ static int aead_decrypt(struct aead_request *req)
 	int ret = 0;
 
 	/* allocate extended descriptor */
-	edesc = aead_edesc_alloc(req, DESC_JOB_IO_LEN *
-				 CAAM_CMD_SZ, &all_contig, false);
+	edesc = old_aead_edesc_alloc(req, DESC_JOB_IO_LEN *
+				     CAAM_CMD_SZ, &all_contig, true);
+	if (IS_ERR(edesc))
+		return PTR_ERR(edesc);
+
+	/* Create and submit job descriptor */
+	old_init_aead_job(ctx->sh_desc_enc, ctx->sh_desc_enc_dma, edesc, req,
+			  all_contig, true);
+#ifdef DEBUG
+	print_hex_dump(KERN_ERR, "aead jobdesc@"__stringify(__LINE__)": ",
+		       DUMP_PREFIX_ADDRESS, 16, 4, edesc->hw_desc,
+		       desc_bytes(edesc->hw_desc), 1);
+#endif
+
+	desc = edesc->hw_desc;
+	ret = caam_jr_enqueue(jrdev, desc, old_aead_encrypt_done, req);
+	if (!ret) {
+		ret = -EINPROGRESS;
+	} else {
+		old_aead_unmap(jrdev, edesc, req);
+		kfree(edesc);
+	}
+
+	return ret;
+}
+
+static int gcm_decrypt(struct aead_request *req)
+{
+	struct aead_edesc *edesc;
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct caam_ctx *ctx = crypto_aead_ctx(aead);
+	struct device *jrdev = ctx->jrdev;
+	bool all_contig;
+	u32 *desc;
+	int ret = 0;
+
+	/* allocate extended descriptor */
+	edesc = aead_edesc_alloc(req, GCM_DESC_JOB_IO_LEN, &all_contig, false);
+	if (IS_ERR(edesc))
+		return PTR_ERR(edesc);
+
+	/* Create and submit job descriptor*/
+	init_gcm_job(req, edesc, all_contig, false);
+#ifdef DEBUG
+	print_hex_dump(KERN_ERR, "aead jobdesc@"__stringify(__LINE__)": ",
+		       DUMP_PREFIX_ADDRESS, 16, 4, edesc->hw_desc,
+		       desc_bytes(edesc->hw_desc), 1);
+#endif
+
+	desc = edesc->hw_desc;
+	ret = caam_jr_enqueue(jrdev, desc, aead_decrypt_done, req);
+	if (!ret) {
+		ret = -EINPROGRESS;
+	} else {
+		aead_unmap(jrdev, edesc, req);
+		kfree(edesc);
+	}
+
+	return ret;
+}
+
+static int old_aead_decrypt(struct aead_request *req)
+{
+	struct aead_edesc *edesc;
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct caam_ctx *ctx = crypto_aead_ctx(aead);
+	struct device *jrdev = ctx->jrdev;
+	bool all_contig;
+	u32 *desc;
+	int ret = 0;
+
+	/* allocate extended descriptor */
+	edesc = old_aead_edesc_alloc(req, DESC_JOB_IO_LEN *
+				     CAAM_CMD_SZ, &all_contig, false);
 	if (IS_ERR(edesc))
 		return PTR_ERR(edesc);
 
@@ -2812,8 +2780,8 @@ static int aead_decrypt(struct aead_request *req)
 #endif
 
 	/* Create and submit job descriptor*/
-	init_aead_job(ctx->sh_desc_dec,
-		      ctx->sh_desc_dec_dma, edesc, req, all_contig, false);
+	old_init_aead_job(ctx->sh_desc_dec,
+			  ctx->sh_desc_dec_dma, edesc, req, all_contig, false);
 #ifdef DEBUG
 	print_hex_dump(KERN_ERR, "aead jobdesc@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, edesc->hw_desc,
@@ -2821,11 +2789,11 @@ static int aead_decrypt(struct aead_request *req)
 #endif
 
 	desc = edesc->hw_desc;
-	ret = caam_jr_enqueue(jrdev, desc, aead_decrypt_done, req);
+	ret = caam_jr_enqueue(jrdev, desc, old_aead_decrypt_done, req);
 	if (!ret) {
 		ret = -EINPROGRESS;
 	} else {
-		aead_unmap(jrdev, edesc, req);
+		old_aead_unmap(jrdev, edesc, req);
 		kfree(edesc);
 	}
 
@@ -2953,8 +2921,8 @@ static struct aead_edesc *aead_giv_edesc_alloc(struct aead_givcrypt_request
 	sec4_sg_index = 0;
 	if (!(contig & GIV_SRC_CONTIG)) {
 		if (!is_gcm) {
-			sg_to_sec4_sg(req->assoc, assoc_nents,
-				      edesc->sec4_sg + sec4_sg_index, 0);
+			sg_to_sec4_sg_len(req->assoc, req->assoclen,
+					  edesc->sec4_sg + sec4_sg_index);
 			sec4_sg_index += assoc_nents;
 		}
 
@@ -2963,8 +2931,8 @@ static struct aead_edesc *aead_giv_edesc_alloc(struct aead_givcrypt_request
 		sec4_sg_index += 1;
 
 		if (is_gcm) {
-			sg_to_sec4_sg(req->assoc, assoc_nents,
-				      edesc->sec4_sg + sec4_sg_index, 0);
+			sg_to_sec4_sg_len(req->assoc, req->assoclen,
+					  edesc->sec4_sg + sec4_sg_index);
 			sec4_sg_index += assoc_nents;
 		}
 
@@ -2999,7 +2967,7 @@ static struct aead_edesc *aead_giv_edesc_alloc(struct aead_givcrypt_request
 	return edesc;
 }
 
-static int aead_givencrypt(struct aead_givcrypt_request *areq)
+static int old_aead_givencrypt(struct aead_givcrypt_request *areq)
 {
 	struct aead_request *req = &areq->areq;
 	struct aead_edesc *edesc;
@@ -3033,11 +3001,11 @@ static int aead_givencrypt(struct aead_givcrypt_request *areq)
 #endif
 
 	desc = edesc->hw_desc;
-	ret = caam_jr_enqueue(jrdev, desc, aead_encrypt_done, req);
+	ret = caam_jr_enqueue(jrdev, desc, old_aead_encrypt_done, req);
 	if (!ret) {
 		ret = -EINPROGRESS;
 	} else {
-		aead_unmap(jrdev, edesc, req);
+		old_aead_unmap(jrdev, edesc, req);
 		kfree(edesc);
 	}
 
@@ -3046,7 +3014,7 @@ static int aead_givencrypt(struct aead_givcrypt_request *areq)
 
 static int aead_null_givencrypt(struct aead_givcrypt_request *areq)
 {
-	return aead_encrypt(&areq->areq);
+	return old_aead_encrypt(&areq->areq);
 }
 
 /*
@@ -3379,11 +3347,7 @@ struct caam_alg_template {
 	u32 type;
 	union {
 		struct ablkcipher_alg ablkcipher;
-		struct aead_alg aead;
-		struct blkcipher_alg blkcipher;
-		struct cipher_alg cipher;
-		struct compress_alg compress;
-		struct rng_alg rng;
+		struct old_aead_alg aead;
 	} template_u;
 	u32 class1_alg_type;
 	u32 class2_alg_type;
@@ -3400,8 +3364,8 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
 			.givencrypt = aead_null_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = NULL_IV_SIZE,
@@ -3419,8 +3383,8 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
 			.givencrypt = aead_null_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = NULL_IV_SIZE,
@@ -3438,8 +3402,8 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
 			.givencrypt = aead_null_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = NULL_IV_SIZE,
@@ -3458,8 +3422,8 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
 			.givencrypt = aead_null_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = NULL_IV_SIZE,
@@ -3478,8 +3442,8 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
 			.givencrypt = aead_null_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = NULL_IV_SIZE,
@@ -3498,8 +3462,8 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
 			.givencrypt = aead_null_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = NULL_IV_SIZE,
@@ -3518,9 +3482,9 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
+			.givencrypt = old_aead_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = AES_BLOCK_SIZE,
 			.maxauthsize = MD5_DIGEST_SIZE,
@@ -3537,9 +3501,9 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
+			.givencrypt = old_aead_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = AES_BLOCK_SIZE,
 			.maxauthsize = SHA1_DIGEST_SIZE,
@@ -3556,9 +3520,9 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
+			.givencrypt = old_aead_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = AES_BLOCK_SIZE,
 			.maxauthsize = SHA224_DIGEST_SIZE,
@@ -3576,9 +3540,9 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
+			.givencrypt = old_aead_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = AES_BLOCK_SIZE,
 			.maxauthsize = SHA256_DIGEST_SIZE,
@@ -3596,9 +3560,9 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
+			.givencrypt = old_aead_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = AES_BLOCK_SIZE,
 			.maxauthsize = SHA384_DIGEST_SIZE,
@@ -3617,9 +3581,9 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
+			.givencrypt = old_aead_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = AES_BLOCK_SIZE,
 			.maxauthsize = SHA512_DIGEST_SIZE,
@@ -3637,9 +3601,9 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
+			.givencrypt = old_aead_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = DES3_EDE_BLOCK_SIZE,
 			.maxauthsize = MD5_DIGEST_SIZE,
@@ -3656,9 +3620,9 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
+			.givencrypt = old_aead_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = DES3_EDE_BLOCK_SIZE,
 			.maxauthsize = SHA1_DIGEST_SIZE,
@@ -3675,9 +3639,9 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
+			.givencrypt = old_aead_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = DES3_EDE_BLOCK_SIZE,
 			.maxauthsize = SHA224_DIGEST_SIZE,
@@ -3695,9 +3659,9 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
+			.givencrypt = old_aead_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = DES3_EDE_BLOCK_SIZE,
 			.maxauthsize = SHA256_DIGEST_SIZE,
@@ -3715,9 +3679,9 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
+			.givencrypt = old_aead_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = DES3_EDE_BLOCK_SIZE,
 			.maxauthsize = SHA384_DIGEST_SIZE,
@@ -3735,9 +3699,9 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
+			.givencrypt = old_aead_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = DES3_EDE_BLOCK_SIZE,
 			.maxauthsize = SHA512_DIGEST_SIZE,
@@ -3755,9 +3719,9 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
+			.givencrypt = old_aead_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = DES_BLOCK_SIZE,
 			.maxauthsize = MD5_DIGEST_SIZE,
@@ -3774,9 +3738,9 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
+			.givencrypt = old_aead_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = DES_BLOCK_SIZE,
 			.maxauthsize = SHA1_DIGEST_SIZE,
@@ -3793,9 +3757,9 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
+			.givencrypt = old_aead_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = DES_BLOCK_SIZE,
 			.maxauthsize = SHA224_DIGEST_SIZE,
@@ -3813,9 +3777,9 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
+			.givencrypt = old_aead_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = DES_BLOCK_SIZE,
 			.maxauthsize = SHA256_DIGEST_SIZE,
@@ -3833,9 +3797,9 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
+			.givencrypt = old_aead_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = DES_BLOCK_SIZE,
 			.maxauthsize = SHA384_DIGEST_SIZE,
@@ -3853,9 +3817,9 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
+			.givencrypt = old_aead_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = DES_BLOCK_SIZE,
 			.maxauthsize = SHA512_DIGEST_SIZE,
@@ -3873,9 +3837,9 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
+			.givencrypt = old_aead_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = CTR_RFC3686_IV_SIZE,
 			.maxauthsize = MD5_DIGEST_SIZE,
@@ -3892,9 +3856,9 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
+			.givencrypt = old_aead_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = CTR_RFC3686_IV_SIZE,
 			.maxauthsize = SHA1_DIGEST_SIZE,
@@ -3911,9 +3875,9 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
+			.givencrypt = old_aead_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = CTR_RFC3686_IV_SIZE,
 			.maxauthsize = SHA224_DIGEST_SIZE,
@@ -3931,9 +3895,9 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
+			.givencrypt = old_aead_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = CTR_RFC3686_IV_SIZE,
 			.maxauthsize = SHA256_DIGEST_SIZE,
@@ -3951,9 +3915,9 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
+			.givencrypt = old_aead_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = CTR_RFC3686_IV_SIZE,
 			.maxauthsize = SHA384_DIGEST_SIZE,
@@ -3971,9 +3935,9 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
+			.givencrypt = old_aead_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = CTR_RFC3686_IV_SIZE,
 			.maxauthsize = SHA512_DIGEST_SIZE,
@@ -3983,58 +3947,6 @@ static struct caam_alg_template driver_algs[] = {
 				   OP_ALG_AAI_HMAC_PRECOMP,
 		.alg_op = OP_ALG_ALGSEL_SHA512 | OP_ALG_AAI_HMAC,
 	},
-	{
-		.name = "rfc4106(gcm(aes))",
-		.driver_name = "rfc4106-gcm-aes-caam",
-		.blocksize = 1,
-		.type = CRYPTO_ALG_TYPE_AEAD,
-		.template_aead = {
-			.setkey = rfc4106_setkey,
-			.setauthsize = rfc4106_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
-			.geniv = "<built-in>",
-			.ivsize = 8,
-			.maxauthsize = AES_BLOCK_SIZE,
-			},
-		.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_GCM,
-	},
-	{
-		.name = "rfc4543(gcm(aes))",
-		.driver_name = "rfc4543-gcm-aes-caam",
-		.blocksize = 1,
-		.type = CRYPTO_ALG_TYPE_AEAD,
-		.template_aead = {
-			.setkey = rfc4543_setkey,
-			.setauthsize = rfc4543_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
-			.geniv = "<built-in>",
-			.ivsize = 8,
-			.maxauthsize = AES_BLOCK_SIZE,
-			},
-		.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_GCM,
-	},
-	/* Galois Counter Mode */
-	{
-		.name = "gcm(aes)",
-		.driver_name = "gcm-aes-caam",
-		.blocksize = 1,
-		.type = CRYPTO_ALG_TYPE_AEAD,
-		.template_aead = {
-			.setkey = gcm_setkey,
-			.setauthsize = gcm_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = NULL,
-			.geniv = "<built-in>",
-			.ivsize = 12,
-			.maxauthsize = AES_BLOCK_SIZE,
-			},
-		.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_GCM,
-	},
 	/* ablkcipher descriptor */
 	{
 		.name = "cbc(aes)",
@@ -4124,21 +4036,84 @@ static struct caam_alg_template driver_algs[] = {
 	}
 };
 
-struct caam_crypto_alg {
-	struct list_head entry;
+struct caam_alg_entry {
 	int class1_alg_type;
 	int class2_alg_type;
 	int alg_op;
+};
+
+struct caam_aead_alg {
+	struct aead_alg aead;
+	struct caam_alg_entry caam;
+	bool registered;
+};
+
+static struct caam_aead_alg driver_aeads[] = {
+	{
+		.aead = {
+			.base = {
+				.cra_name = "rfc4106(gcm(aes))",
+				.cra_driver_name = "rfc4106-gcm-aes-caam",
+				.cra_blocksize = 1,
+			},
+			.setkey = rfc4106_setkey,
+			.setauthsize = rfc4106_setauthsize,
+			.encrypt = gcm_encrypt,
+			.decrypt = gcm_decrypt,
+			.ivsize = 8,
+			.maxauthsize = AES_BLOCK_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_GCM,
+		},
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "rfc4543(gcm(aes))",
+				.cra_driver_name = "rfc4543-gcm-aes-caam",
+				.cra_blocksize = 1,
+			},
+			.setkey = rfc4543_setkey,
+			.setauthsize = rfc4543_setauthsize,
+			.encrypt = gcm_encrypt,
+			.decrypt = gcm_decrypt,
+			.ivsize = 8,
+			.maxauthsize = AES_BLOCK_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_GCM,
+		},
+	},
+	/* Galois Counter Mode */
+	{
+		.aead = {
+			.base = {
+				.cra_name = "gcm(aes)",
+				.cra_driver_name = "gcm-aes-caam",
+				.cra_blocksize = 1,
+			},
+			.setkey = gcm_setkey,
+			.setauthsize = gcm_setauthsize,
+			.encrypt = gcm_encrypt,
+			.decrypt = gcm_decrypt,
+			.ivsize = 12,
+			.maxauthsize = AES_BLOCK_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_GCM,
+		},
+	},
+};
+
+struct caam_crypto_alg {
 	struct crypto_alg crypto_alg;
+	struct list_head entry;
+	struct caam_alg_entry caam;
 };
 
-static int caam_cra_init(struct crypto_tfm *tfm)
+static int caam_init_common(struct caam_ctx *ctx, struct caam_alg_entry *caam)
 {
-	struct crypto_alg *alg = tfm->__crt_alg;
-	struct caam_crypto_alg *caam_alg =
-		 container_of(alg, struct caam_crypto_alg, crypto_alg);
-	struct caam_ctx *ctx = crypto_tfm_ctx(tfm);
-
 	ctx->jrdev = caam_jr_alloc();
 	if (IS_ERR(ctx->jrdev)) {
 		pr_err("Job Ring Device allocation for transform failed\n");
@@ -4146,17 +4121,35 @@ static int caam_cra_init(struct crypto_tfm *tfm)
 	}
 
 	/* copy descriptor header template value */
-	ctx->class1_alg_type = OP_TYPE_CLASS1_ALG | caam_alg->class1_alg_type;
-	ctx->class2_alg_type = OP_TYPE_CLASS2_ALG | caam_alg->class2_alg_type;
-	ctx->alg_op = OP_TYPE_CLASS2_ALG | caam_alg->alg_op;
+	ctx->class1_alg_type = OP_TYPE_CLASS1_ALG | caam->class1_alg_type;
+	ctx->class2_alg_type = OP_TYPE_CLASS2_ALG | caam->class2_alg_type;
+	ctx->alg_op = OP_TYPE_CLASS2_ALG | caam->alg_op;
 
 	return 0;
 }
 
-static void caam_cra_exit(struct crypto_tfm *tfm)
+static int caam_cra_init(struct crypto_tfm *tfm)
 {
+	struct crypto_alg *alg = tfm->__crt_alg;
+	struct caam_crypto_alg *caam_alg =
+		 container_of(alg, struct caam_crypto_alg, crypto_alg);
 	struct caam_ctx *ctx = crypto_tfm_ctx(tfm);
 
+	return caam_init_common(ctx, &caam_alg->caam);
+}
+
+static int caam_aead_init(struct crypto_aead *tfm)
+{
+	struct aead_alg *alg = crypto_aead_alg(tfm);
+	struct caam_aead_alg *caam_alg =
+		 container_of(alg, struct caam_aead_alg, aead);
+	struct caam_ctx *ctx = crypto_aead_ctx(tfm);
+
+	return caam_init_common(ctx, &caam_alg->caam);
+}
+
+static void caam_exit_common(struct caam_ctx *ctx)
+{
 	if (ctx->sh_desc_enc_dma &&
 	    !dma_mapping_error(ctx->jrdev, ctx->sh_desc_enc_dma))
 		dma_unmap_single(ctx->jrdev, ctx->sh_desc_enc_dma,
@@ -4179,10 +4172,28 @@ static void caam_cra_exit(struct crypto_tfm *tfm)
 	caam_jr_free(ctx->jrdev);
 }
 
+static void caam_cra_exit(struct crypto_tfm *tfm)
+{
+	caam_exit_common(crypto_tfm_ctx(tfm));
+}
+
+static void caam_aead_exit(struct crypto_aead *tfm)
+{
+	caam_exit_common(crypto_aead_ctx(tfm));
+}
+
 static void __exit caam_algapi_exit(void)
 {
 
 	struct caam_crypto_alg *t_alg, *n;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(driver_aeads); i++) {
+		struct caam_aead_alg *t_alg = driver_aeads + i;
+
+		if (t_alg->registered)
+			crypto_unregister_aead(&t_alg->aead);
+	}
 
 	if (!alg_list.next)
 		return;
@@ -4235,13 +4246,26 @@ static struct caam_crypto_alg *caam_alg_alloc(struct caam_alg_template
 		break;
 	}
 
-	t_alg->class1_alg_type = template->class1_alg_type;
-	t_alg->class2_alg_type = template->class2_alg_type;
-	t_alg->alg_op = template->alg_op;
+	t_alg->caam.class1_alg_type = template->class1_alg_type;
+	t_alg->caam.class2_alg_type = template->class2_alg_type;
+	t_alg->caam.alg_op = template->alg_op;
 
 	return t_alg;
 }
 
+static void caam_aead_alg_init(struct caam_aead_alg *t_alg)
+{
+	struct aead_alg *alg = &t_alg->aead;
+
+	alg->base.cra_module = THIS_MODULE;
+	alg->base.cra_priority = CAAM_CRA_PRIORITY;
+	alg->base.cra_ctxsize = sizeof(struct caam_ctx);
+	alg->base.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_KERN_DRIVER_ONLY;
+
+	alg->init = caam_aead_init;
+	alg->exit = caam_aead_exit;
+}
+
 static int __init caam_algapi_init(void)
 {
 	struct device_node *dev_node;
@@ -4249,6 +4273,7 @@ static int __init caam_algapi_init(void)
 	struct device *ctrldev;
 	void *priv;
 	int i = 0, err = 0;
+	bool registered = false;
 
 	dev_node = of_find_compatible_node(NULL, NULL, "fsl,sec-v4.0");
 	if (!dev_node) {
@@ -4295,10 +4320,30 @@ static int __init caam_algapi_init(void)
 			pr_warn("%s alg registration failed\n",
 				t_alg->crypto_alg.cra_driver_name);
 			kfree(t_alg);
-		} else
-			list_add_tail(&t_alg->entry, &alg_list);
+			continue;
+		}
+
+		list_add_tail(&t_alg->entry, &alg_list);
+		registered = true;
 	}
-	if (!list_empty(&alg_list))
+
+	for (i = 0; i < ARRAY_SIZE(driver_aeads); i++) {
+		struct caam_aead_alg *t_alg = driver_aeads + i;
+
+		caam_aead_alg_init(t_alg);
+
+		err = crypto_register_aead(&t_alg->aead);
+		if (err) {
+			pr_warn("%s alg registration failed\n",
+				t_alg->aead.base.cra_driver_name);
+			continue;
+		}
+
+		t_alg->registered = true;
+		registered = true;
+	}
+
+	if (registered)
 		pr_info("caam algorithms registered in /proc/crypto\n");
 
 	return err;
diff --git a/drivers/crypto/caam/caamhash.c b/drivers/crypto/caam/caamhash.c
index ba0532efd3ae..dae1e8099969 100644
--- a/drivers/crypto/caam/caamhash.c
+++ b/drivers/crypto/caam/caamhash.c
@@ -835,17 +835,17 @@ static int ahash_update_ctx(struct ahash_request *req)
 			src_map_to_sec4_sg(jrdev, req->src, src_nents,
 					   edesc->sec4_sg + sec4_sg_src_index,
 					   chained);
-			if (*next_buflen) {
+			if (*next_buflen)
 				scatterwalk_map_and_copy(next_buf, req->src,
 							 to_hash - *buflen,
 							 *next_buflen, 0);
-				state->current_buf = !state->current_buf;
-			}
 		} else {
 			(edesc->sec4_sg + sec4_sg_src_index - 1)->len |=
 							SEC4_SG_LEN_FIN;
 		}
 
+		state->current_buf = !state->current_buf;
+
 		sh_len = desc_len(sh_desc);
 		desc = edesc->hw_desc;
 		init_job_desc_shared(desc, ptr, sh_len, HDR_SHARE_DEFER |
@@ -1268,9 +1268,10 @@ static int ahash_update_no_ctx(struct ahash_request *req)
 			scatterwalk_map_and_copy(next_buf, req->src,
 						 to_hash - *buflen,
 						 *next_buflen, 0);
-			state->current_buf = !state->current_buf;
 		}
 
+		state->current_buf = !state->current_buf;
+
 		sh_len = desc_len(sh_desc);
 		desc = edesc->hw_desc;
 		init_job_desc_shared(desc, ptr, sh_len, HDR_SHARE_DEFER |
@@ -1544,6 +1545,8 @@ static int ahash_init(struct ahash_request *req)
 
 	state->current_buf = 0;
 	state->buf_dma = 0;
+	state->buflen_0 = 0;
+	state->buflen_1 = 0;
 
 	return 0;
 }
diff --git a/drivers/crypto/caam/caamrng.c b/drivers/crypto/caam/caamrng.c
index 26a544b505f1..5095337205b8 100644
--- a/drivers/crypto/caam/caamrng.c
+++ b/drivers/crypto/caam/caamrng.c
@@ -56,7 +56,7 @@
 
 /* Buffer, its dma address and lock */
 struct buf_data {
-	u8 buf[RN_BUF_SIZE];
+	u8 buf[RN_BUF_SIZE] ____cacheline_aligned;
 	dma_addr_t addr;
 	struct completion filled;
 	u32 hw_desc[DESC_JOB_O_LEN];
diff --git a/drivers/crypto/caam/compat.h b/drivers/crypto/caam/compat.h
index acd7743e2603..f57f395db33f 100644
--- a/drivers/crypto/caam/compat.h
+++ b/drivers/crypto/caam/compat.h
@@ -32,7 +32,7 @@
 #include <crypto/des.h>
 #include <crypto/sha.h>
 #include <crypto/md5.h>
-#include <crypto/aead.h>
+#include <crypto/internal/aead.h>
 #include <crypto/authenc.h>
 #include <crypto/scatterwalk.h>
 #include <crypto/internal/skcipher.h>
diff --git a/drivers/crypto/caam/ctrl.c b/drivers/crypto/caam/ctrl.c
index efba4ccd4fac..efacab7539ef 100644
--- a/drivers/crypto/caam/ctrl.c
+++ b/drivers/crypto/caam/ctrl.c
@@ -301,7 +301,7 @@ static int caam_remove(struct platform_device *pdev)
 #endif
 
 	/* Unmap controller region */
-	iounmap(&ctrl);
+	iounmap(ctrl);
 
 	return ret;
 }
@@ -496,7 +496,7 @@ static int caam_probe(struct platform_device *pdev)
 					sizeof(struct platform_device *) * rspec,
 					GFP_KERNEL);
 	if (ctrlpriv->jrpdev == NULL) {
-		iounmap(&ctrl);
+		iounmap(ctrl);
 		return -ENOMEM;
 	}
 
diff --git a/drivers/crypto/caam/regs.h b/drivers/crypto/caam/regs.h
index 378ddc17f60e..672c97489505 100644
--- a/drivers/crypto/caam/regs.h
+++ b/drivers/crypto/caam/regs.h
@@ -83,35 +83,35 @@
 #endif
 #endif
 
+/*
+ * The only users of these wr/rd_reg64 functions is the Job Ring (JR).
+ * The DMA address registers in the JR are a pair of 32-bit registers.
+ * The layout is:
+ *
+ *    base + 0x0000 : most-significant 32 bits
+ *    base + 0x0004 : least-significant 32 bits
+ *
+ * The 32-bit version of this core therefore has to write to base + 0x0004
+ * to set the 32-bit wide DMA address. This seems to be independent of the
+ * endianness of the written/read data.
+ */
+
 #ifndef CONFIG_64BIT
-#ifdef __BIG_ENDIAN
-static inline void wr_reg64(u64 __iomem *reg, u64 data)
-{
-	wr_reg32((u32 __iomem *)reg, (data & 0xffffffff00000000ull) >> 32);
-	wr_reg32((u32 __iomem *)reg + 1, data & 0x00000000ffffffffull);
-}
+#define REG64_MS32(reg) ((u32 __iomem *)(reg))
+#define REG64_LS32(reg) ((u32 __iomem *)(reg) + 1)
 
-static inline u64 rd_reg64(u64 __iomem *reg)
-{
-	return (((u64)rd_reg32((u32 __iomem *)reg)) << 32) |
-		((u64)rd_reg32((u32 __iomem *)reg + 1));
-}
-#else
-#ifdef __LITTLE_ENDIAN
 static inline void wr_reg64(u64 __iomem *reg, u64 data)
 {
-	wr_reg32((u32 __iomem *)reg + 1, (data & 0xffffffff00000000ull) >> 32);
-	wr_reg32((u32 __iomem *)reg, data & 0x00000000ffffffffull);
+	wr_reg32(REG64_MS32(reg), data >> 32);
+	wr_reg32(REG64_LS32(reg), data);
 }
 
 static inline u64 rd_reg64(u64 __iomem *reg)
 {
-	return (((u64)rd_reg32((u32 __iomem *)reg + 1)) << 32) |
-		((u64)rd_reg32((u32 __iomem *)reg));
+	return ((u64)rd_reg32(REG64_MS32(reg)) << 32 |
+		(u64)rd_reg32(REG64_LS32(reg)));
 }
 #endif
-#endif
-#endif
 
 /*
  * jr_outentry
diff --git a/drivers/crypto/caam/sg_sw_sec4.h b/drivers/crypto/caam/sg_sw_sec4.h
index 3b918218aa4c..b68b74cc7b77 100644
--- a/drivers/crypto/caam/sg_sw_sec4.h
+++ b/drivers/crypto/caam/sg_sw_sec4.h
@@ -55,6 +55,21 @@ static inline void sg_to_sec4_sg_last(struct scatterlist *sg, int sg_count,
 	sec4_sg_ptr->len |= SEC4_SG_LEN_FIN;
 }
 
+static inline struct sec4_sg_entry *sg_to_sec4_sg_len(
+	struct scatterlist *sg, unsigned int total,
+	struct sec4_sg_entry *sec4_sg_ptr)
+{
+	do {
+		unsigned int len = min(sg_dma_len(sg), total);
+
+		dma_to_sec4_sg_one(sec4_sg_ptr, sg_dma_address(sg), len, 0);
+		sec4_sg_ptr++;
+		sg = sg_next(sg);
+		total -= len;
+	} while (total);
+	return sec4_sg_ptr - 1;
+}
+
 /* count number of elements in scatterlist */
 static inline int __sg_count(struct scatterlist *sg_list, int nbytes,
 			     bool *chained)
@@ -85,34 +100,41 @@ static inline int sg_count(struct scatterlist *sg_list, int nbytes,
 	return sg_nents;
 }
 
-static int dma_map_sg_chained(struct device *dev, struct scatterlist *sg,
-			      unsigned int nents, enum dma_data_direction dir,
-			      bool chained)
+static inline void dma_unmap_sg_chained(
+	struct device *dev, struct scatterlist *sg, unsigned int nents,
+	enum dma_data_direction dir, bool chained)
 {
 	if (unlikely(chained)) {
 		int i;
 		for (i = 0; i < nents; i++) {
-			dma_map_sg(dev, sg, 1, dir);
+			dma_unmap_sg(dev, sg, 1, dir);
 			sg = sg_next(sg);
 		}
-	} else {
-		dma_map_sg(dev, sg, nents, dir);
+	} else if (nents) {
+		dma_unmap_sg(dev, sg, nents, dir);
 	}
-	return nents;
 }
 
-static int dma_unmap_sg_chained(struct device *dev, struct scatterlist *sg,
-				unsigned int nents, enum dma_data_direction dir,
-				bool chained)
+static inline int dma_map_sg_chained(
+	struct device *dev, struct scatterlist *sg, unsigned int nents,
+	enum dma_data_direction dir, bool chained)
 {
+	struct scatterlist *first = sg;
+
 	if (unlikely(chained)) {
 		int i;
 		for (i = 0; i < nents; i++) {
-			dma_unmap_sg(dev, sg, 1, dir);
+			if (!dma_map_sg(dev, sg, 1, dir)) {
+				dma_unmap_sg_chained(dev, first, i, dir,
+						     chained);
+				nents = 0;
+				break;
+			}
+
 			sg = sg_next(sg);
 		}
-	} else {
-		dma_unmap_sg(dev, sg, nents, dir);
-	}
+	} else
+		nents = dma_map_sg(dev, sg, nents, dir);
+
 	return nents;
 }
diff --git a/drivers/crypto/ccp/Kconfig b/drivers/crypto/ccp/Kconfig
index 7639ffc36c68..ae38f6b6cc10 100644
--- a/drivers/crypto/ccp/Kconfig
+++ b/drivers/crypto/ccp/Kconfig
@@ -13,7 +13,6 @@ config CRYPTO_DEV_CCP_CRYPTO
 	tristate "Encryption and hashing acceleration support"
 	depends on CRYPTO_DEV_CCP_DD
 	default m
-	select CRYPTO_ALGAPI
 	select CRYPTO_HASH
 	select CRYPTO_BLKCIPHER
 	select CRYPTO_AUTHENC
diff --git a/drivers/crypto/ccp/ccp-ops.c b/drivers/crypto/ccp/ccp-ops.c
index 71f2e3c89424..d09c6c4af4aa 100644
--- a/drivers/crypto/ccp/ccp-ops.c
+++ b/drivers/crypto/ccp/ccp-ops.c
@@ -52,8 +52,7 @@ struct ccp_dm_workarea {
 
 struct ccp_sg_workarea {
 	struct scatterlist *sg;
-	unsigned int nents;
-	unsigned int length;
+	int nents;
 
 	struct scatterlist *dma_sg;
 	struct device *dma_dev;
@@ -496,8 +495,10 @@ static int ccp_init_sg_workarea(struct ccp_sg_workarea *wa, struct device *dev,
 	if (!sg)
 		return 0;
 
-	wa->nents = sg_nents(sg);
-	wa->length = sg->length;
+	wa->nents = sg_nents_for_len(sg, len);
+	if (wa->nents < 0)
+		return wa->nents;
+
 	wa->bytes_left = len;
 	wa->sg_used = 0;
 
diff --git a/drivers/crypto/ccp/ccp-platform.c b/drivers/crypto/ccp/ccp-platform.c
index e446781b1892..f2e6de361fd1 100644
--- a/drivers/crypto/ccp/ccp-platform.c
+++ b/drivers/crypto/ccp/ccp-platform.c
@@ -122,8 +122,6 @@ static int ccp_platform_probe(struct platform_device *pdev)
 	}
 	ccp->io_regs = ccp->io_map;
 
-	if (!dev->dma_mask)
-		dev->dma_mask = &dev->coherent_dma_mask;
 	ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(48));
 	if (ret) {
 		dev_err(dev, "dma_set_mask_and_coherent failed (%d)\n", ret);
diff --git a/drivers/crypto/ixp4xx_crypto.c b/drivers/crypto/ixp4xx_crypto.c
index 48f453555f1f..7ba495f75370 100644
--- a/drivers/crypto/ixp4xx_crypto.c
+++ b/drivers/crypto/ixp4xx_crypto.c
@@ -25,7 +25,7 @@
 #include <crypto/aes.h>
 #include <crypto/sha.h>
 #include <crypto/algapi.h>
-#include <crypto/aead.h>
+#include <crypto/internal/aead.h>
 #include <crypto/authenc.h>
 #include <crypto/scatterwalk.h>
 
@@ -575,7 +575,8 @@ static int init_tfm_ablk(struct crypto_tfm *tfm)
 
 static int init_tfm_aead(struct crypto_tfm *tfm)
 {
-	tfm->crt_aead.reqsize = sizeof(struct aead_ctx);
+	crypto_aead_set_reqsize(__crypto_aead_cast(tfm),
+				sizeof(struct aead_ctx));
 	return init_tfm(tfm);
 }
 
@@ -1096,7 +1097,7 @@ static int aead_setup(struct crypto_aead *tfm, unsigned int authsize)
 {
 	struct ixp_ctx *ctx = crypto_aead_ctx(tfm);
 	u32 *flags = &tfm->base.crt_flags;
-	unsigned digest_len = crypto_aead_alg(tfm)->maxauthsize;
+	unsigned digest_len = crypto_aead_maxauthsize(tfm);
 	int ret;
 
 	if (!ctx->enckey_len && !ctx->authkey_len)
@@ -1138,7 +1139,7 @@ out:
 
 static int aead_setauthsize(struct crypto_aead *tfm, unsigned int authsize)
 {
-	int max = crypto_aead_alg(tfm)->maxauthsize >> 2;
+	int max = crypto_aead_maxauthsize(tfm) >> 2;
 
 	if ((authsize>>2) < 1 || (authsize>>2) > max || (authsize & 3))
 		return -EINVAL;
diff --git a/drivers/crypto/marvell/Makefile b/drivers/crypto/marvell/Makefile
new file mode 100644
index 000000000000..0c12b13574dc
--- /dev/null
+++ b/drivers/crypto/marvell/Makefile
@@ -0,0 +1,2 @@
+obj-$(CONFIG_CRYPTO_DEV_MARVELL_CESA) += marvell-cesa.o
+marvell-cesa-objs := cesa.o cipher.o hash.o tdma.o
diff --git a/drivers/crypto/marvell/cesa.c b/drivers/crypto/marvell/cesa.c
new file mode 100644
index 000000000000..a432633bced4
--- /dev/null
+++ b/drivers/crypto/marvell/cesa.c
@@ -0,0 +1,548 @@
+/*
+ * Support for Marvell's Cryptographic Engine and Security Accelerator (CESA)
+ * that can be found on the following platform: Orion, Kirkwood, Armada. This
+ * driver supports the TDMA engine on platforms on which it is available.
+ *
+ * Author: Boris Brezillon <boris.brezillon@free-electrons.com>
+ * Author: Arnaud Ebalard <arno@natisbad.org>
+ *
+ * This work is based on an initial version written by
+ * Sebastian Andrzej Siewior < sebastian at breakpoint dot cc >
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#include <linux/delay.h>
+#include <linux/genalloc.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/kthread.h>
+#include <linux/mbus.h>
+#include <linux/platform_device.h>
+#include <linux/scatterlist.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/clk.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/of_irq.h>
+
+#include "cesa.h"
+
+static int allhwsupport = !IS_ENABLED(CONFIG_CRYPTO_DEV_MV_CESA);
+module_param_named(allhwsupport, allhwsupport, int, 0444);
+MODULE_PARM_DESC(allhwsupport, "Enable support for all hardware (even it if overlaps with the mv_cesa driver)");
+
+struct mv_cesa_dev *cesa_dev;
+
+static void mv_cesa_dequeue_req_unlocked(struct mv_cesa_engine *engine)
+{
+	struct crypto_async_request *req, *backlog;
+	struct mv_cesa_ctx *ctx;
+
+	spin_lock_bh(&cesa_dev->lock);
+	backlog = crypto_get_backlog(&cesa_dev->queue);
+	req = crypto_dequeue_request(&cesa_dev->queue);
+	engine->req = req;
+	spin_unlock_bh(&cesa_dev->lock);
+
+	if (!req)
+		return;
+
+	if (backlog)
+		backlog->complete(backlog, -EINPROGRESS);
+
+	ctx = crypto_tfm_ctx(req->tfm);
+	ctx->ops->prepare(req, engine);
+	ctx->ops->step(req);
+}
+
+static irqreturn_t mv_cesa_int(int irq, void *priv)
+{
+	struct mv_cesa_engine *engine = priv;
+	struct crypto_async_request *req;
+	struct mv_cesa_ctx *ctx;
+	u32 status, mask;
+	irqreturn_t ret = IRQ_NONE;
+
+	while (true) {
+		int res;
+
+		mask = mv_cesa_get_int_mask(engine);
+		status = readl(engine->regs + CESA_SA_INT_STATUS);
+
+		if (!(status & mask))
+			break;
+
+		/*
+		 * TODO: avoid clearing the FPGA_INT_STATUS if this not
+		 * relevant on some platforms.
+		 */
+		writel(~status, engine->regs + CESA_SA_FPGA_INT_STATUS);
+		writel(~status, engine->regs + CESA_SA_INT_STATUS);
+
+		ret = IRQ_HANDLED;
+		spin_lock_bh(&engine->lock);
+		req = engine->req;
+		spin_unlock_bh(&engine->lock);
+		if (req) {
+			ctx = crypto_tfm_ctx(req->tfm);
+			res = ctx->ops->process(req, status & mask);
+			if (res != -EINPROGRESS) {
+				spin_lock_bh(&engine->lock);
+				engine->req = NULL;
+				mv_cesa_dequeue_req_unlocked(engine);
+				spin_unlock_bh(&engine->lock);
+				ctx->ops->cleanup(req);
+				local_bh_disable();
+				req->complete(req, res);
+				local_bh_enable();
+			} else {
+				ctx->ops->step(req);
+			}
+		}
+	}
+
+	return ret;
+}
+
+int mv_cesa_queue_req(struct crypto_async_request *req)
+{
+	int ret;
+	int i;
+
+	spin_lock_bh(&cesa_dev->lock);
+	ret = crypto_enqueue_request(&cesa_dev->queue, req);
+	spin_unlock_bh(&cesa_dev->lock);
+
+	if (ret != -EINPROGRESS)
+		return ret;
+
+	for (i = 0; i < cesa_dev->caps->nengines; i++) {
+		spin_lock_bh(&cesa_dev->engines[i].lock);
+		if (!cesa_dev->engines[i].req)
+			mv_cesa_dequeue_req_unlocked(&cesa_dev->engines[i]);
+		spin_unlock_bh(&cesa_dev->engines[i].lock);
+	}
+
+	return -EINPROGRESS;
+}
+
+static int mv_cesa_add_algs(struct mv_cesa_dev *cesa)
+{
+	int ret;
+	int i, j;
+
+	for (i = 0; i < cesa->caps->ncipher_algs; i++) {
+		ret = crypto_register_alg(cesa->caps->cipher_algs[i]);
+		if (ret)
+			goto err_unregister_crypto;
+	}
+
+	for (i = 0; i < cesa->caps->nahash_algs; i++) {
+		ret = crypto_register_ahash(cesa->caps->ahash_algs[i]);
+		if (ret)
+			goto err_unregister_ahash;
+	}
+
+	return 0;
+
+err_unregister_ahash:
+	for (j = 0; j < i; j++)
+		crypto_unregister_ahash(cesa->caps->ahash_algs[j]);
+	i = cesa->caps->ncipher_algs;
+
+err_unregister_crypto:
+	for (j = 0; j < i; j++)
+		crypto_unregister_alg(cesa->caps->cipher_algs[j]);
+
+	return ret;
+}
+
+static void mv_cesa_remove_algs(struct mv_cesa_dev *cesa)
+{
+	int i;
+
+	for (i = 0; i < cesa->caps->nahash_algs; i++)
+		crypto_unregister_ahash(cesa->caps->ahash_algs[i]);
+
+	for (i = 0; i < cesa->caps->ncipher_algs; i++)
+		crypto_unregister_alg(cesa->caps->cipher_algs[i]);
+}
+
+static struct crypto_alg *orion_cipher_algs[] = {
+	&mv_cesa_ecb_des_alg,
+	&mv_cesa_cbc_des_alg,
+	&mv_cesa_ecb_des3_ede_alg,
+	&mv_cesa_cbc_des3_ede_alg,
+	&mv_cesa_ecb_aes_alg,
+	&mv_cesa_cbc_aes_alg,
+};
+
+static struct ahash_alg *orion_ahash_algs[] = {
+	&mv_md5_alg,
+	&mv_sha1_alg,
+	&mv_ahmac_md5_alg,
+	&mv_ahmac_sha1_alg,
+};
+
+static struct crypto_alg *armada_370_cipher_algs[] = {
+	&mv_cesa_ecb_des_alg,
+	&mv_cesa_cbc_des_alg,
+	&mv_cesa_ecb_des3_ede_alg,
+	&mv_cesa_cbc_des3_ede_alg,
+	&mv_cesa_ecb_aes_alg,
+	&mv_cesa_cbc_aes_alg,
+};
+
+static struct ahash_alg *armada_370_ahash_algs[] = {
+	&mv_md5_alg,
+	&mv_sha1_alg,
+	&mv_sha256_alg,
+	&mv_ahmac_md5_alg,
+	&mv_ahmac_sha1_alg,
+	&mv_ahmac_sha256_alg,
+};
+
+static const struct mv_cesa_caps orion_caps = {
+	.nengines = 1,
+	.cipher_algs = orion_cipher_algs,
+	.ncipher_algs = ARRAY_SIZE(orion_cipher_algs),
+	.ahash_algs = orion_ahash_algs,
+	.nahash_algs = ARRAY_SIZE(orion_ahash_algs),
+	.has_tdma = false,
+};
+
+static const struct mv_cesa_caps kirkwood_caps = {
+	.nengines = 1,
+	.cipher_algs = orion_cipher_algs,
+	.ncipher_algs = ARRAY_SIZE(orion_cipher_algs),
+	.ahash_algs = orion_ahash_algs,
+	.nahash_algs = ARRAY_SIZE(orion_ahash_algs),
+	.has_tdma = true,
+};
+
+static const struct mv_cesa_caps armada_370_caps = {
+	.nengines = 1,
+	.cipher_algs = armada_370_cipher_algs,
+	.ncipher_algs = ARRAY_SIZE(armada_370_cipher_algs),
+	.ahash_algs = armada_370_ahash_algs,
+	.nahash_algs = ARRAY_SIZE(armada_370_ahash_algs),
+	.has_tdma = true,
+};
+
+static const struct mv_cesa_caps armada_xp_caps = {
+	.nengines = 2,
+	.cipher_algs = armada_370_cipher_algs,
+	.ncipher_algs = ARRAY_SIZE(armada_370_cipher_algs),
+	.ahash_algs = armada_370_ahash_algs,
+	.nahash_algs = ARRAY_SIZE(armada_370_ahash_algs),
+	.has_tdma = true,
+};
+
+static const struct of_device_id mv_cesa_of_match_table[] = {
+	{ .compatible = "marvell,orion-crypto", .data = &orion_caps },
+	{ .compatible = "marvell,kirkwood-crypto", .data = &kirkwood_caps },
+	{ .compatible = "marvell,dove-crypto", .data = &kirkwood_caps },
+	{ .compatible = "marvell,armada-370-crypto", .data = &armada_370_caps },
+	{ .compatible = "marvell,armada-xp-crypto", .data = &armada_xp_caps },
+	{ .compatible = "marvell,armada-375-crypto", .data = &armada_xp_caps },
+	{ .compatible = "marvell,armada-38x-crypto", .data = &armada_xp_caps },
+	{}
+};
+MODULE_DEVICE_TABLE(of, mv_cesa_of_match_table);
+
+static void
+mv_cesa_conf_mbus_windows(struct mv_cesa_engine *engine,
+			  const struct mbus_dram_target_info *dram)
+{
+	void __iomem *iobase = engine->regs;
+	int i;
+
+	for (i = 0; i < 4; i++) {
+		writel(0, iobase + CESA_TDMA_WINDOW_CTRL(i));
+		writel(0, iobase + CESA_TDMA_WINDOW_BASE(i));
+	}
+
+	for (i = 0; i < dram->num_cs; i++) {
+		const struct mbus_dram_window *cs = dram->cs + i;
+
+		writel(((cs->size - 1) & 0xffff0000) |
+		       (cs->mbus_attr << 8) |
+		       (dram->mbus_dram_target_id << 4) | 1,
+		       iobase + CESA_TDMA_WINDOW_CTRL(i));
+		writel(cs->base, iobase + CESA_TDMA_WINDOW_BASE(i));
+	}
+}
+
+static int mv_cesa_dev_dma_init(struct mv_cesa_dev *cesa)
+{
+	struct device *dev = cesa->dev;
+	struct mv_cesa_dev_dma *dma;
+
+	if (!cesa->caps->has_tdma)
+		return 0;
+
+	dma = devm_kzalloc(dev, sizeof(*dma), GFP_KERNEL);
+	if (!dma)
+		return -ENOMEM;
+
+	dma->tdma_desc_pool = dmam_pool_create("tdma_desc", dev,
+					sizeof(struct mv_cesa_tdma_desc),
+					16, 0);
+	if (!dma->tdma_desc_pool)
+		return -ENOMEM;
+
+	dma->op_pool = dmam_pool_create("cesa_op", dev,
+					sizeof(struct mv_cesa_op_ctx), 16, 0);
+	if (!dma->op_pool)
+		return -ENOMEM;
+
+	dma->cache_pool = dmam_pool_create("cesa_cache", dev,
+					   CESA_MAX_HASH_BLOCK_SIZE, 1, 0);
+	if (!dma->cache_pool)
+		return -ENOMEM;
+
+	dma->padding_pool = dmam_pool_create("cesa_padding", dev, 72, 1, 0);
+	if (!dma->cache_pool)
+		return -ENOMEM;
+
+	cesa->dma = dma;
+
+	return 0;
+}
+
+static int mv_cesa_get_sram(struct platform_device *pdev, int idx)
+{
+	struct mv_cesa_dev *cesa = platform_get_drvdata(pdev);
+	struct mv_cesa_engine *engine = &cesa->engines[idx];
+	const char *res_name = "sram";
+	struct resource *res;
+
+	engine->pool = of_get_named_gen_pool(cesa->dev->of_node,
+					     "marvell,crypto-srams",
+					     idx);
+	if (engine->pool) {
+		engine->sram = gen_pool_dma_alloc(engine->pool,
+						  cesa->sram_size,
+						  &engine->sram_dma);
+		if (engine->sram)
+			return 0;
+
+		engine->pool = NULL;
+		return -ENOMEM;
+	}
+
+	if (cesa->caps->nengines > 1) {
+		if (!idx)
+			res_name = "sram0";
+		else
+			res_name = "sram1";
+	}
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
+					   res_name);
+	if (!res || resource_size(res) < cesa->sram_size)
+		return -EINVAL;
+
+	engine->sram = devm_ioremap_resource(cesa->dev, res);
+	if (IS_ERR(engine->sram))
+		return PTR_ERR(engine->sram);
+
+	engine->sram_dma = phys_to_dma(cesa->dev,
+				       (phys_addr_t)res->start);
+
+	return 0;
+}
+
+static void mv_cesa_put_sram(struct platform_device *pdev, int idx)
+{
+	struct mv_cesa_dev *cesa = platform_get_drvdata(pdev);
+	struct mv_cesa_engine *engine = &cesa->engines[idx];
+
+	if (!engine->pool)
+		return;
+
+	gen_pool_free(engine->pool, (unsigned long)engine->sram,
+		      cesa->sram_size);
+}
+
+static int mv_cesa_probe(struct platform_device *pdev)
+{
+	const struct mv_cesa_caps *caps = &orion_caps;
+	const struct mbus_dram_target_info *dram;
+	const struct of_device_id *match;
+	struct device *dev = &pdev->dev;
+	struct mv_cesa_dev *cesa;
+	struct mv_cesa_engine *engines;
+	struct resource *res;
+	int irq, ret, i;
+	u32 sram_size;
+
+	if (cesa_dev) {
+		dev_err(&pdev->dev, "Only one CESA device authorized\n");
+		return -EEXIST;
+	}
+
+	if (dev->of_node) {
+		match = of_match_node(mv_cesa_of_match_table, dev->of_node);
+		if (!match || !match->data)
+			return -ENOTSUPP;
+
+		caps = match->data;
+	}
+
+	if ((caps == &orion_caps || caps == &kirkwood_caps) && !allhwsupport)
+		return -ENOTSUPP;
+
+	cesa = devm_kzalloc(dev, sizeof(*cesa), GFP_KERNEL);
+	if (!cesa)
+		return -ENOMEM;
+
+	cesa->caps = caps;
+	cesa->dev = dev;
+
+	sram_size = CESA_SA_DEFAULT_SRAM_SIZE;
+	of_property_read_u32(cesa->dev->of_node, "marvell,crypto-sram-size",
+			     &sram_size);
+	if (sram_size < CESA_SA_MIN_SRAM_SIZE)
+		sram_size = CESA_SA_MIN_SRAM_SIZE;
+
+	cesa->sram_size = sram_size;
+	cesa->engines = devm_kzalloc(dev, caps->nengines * sizeof(*engines),
+				     GFP_KERNEL);
+	if (!cesa->engines)
+		return -ENOMEM;
+
+	spin_lock_init(&cesa->lock);
+	crypto_init_queue(&cesa->queue, 50);
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "regs");
+	cesa->regs = devm_ioremap_resource(dev, res);
+	if (IS_ERR(cesa->regs))
+		return -ENOMEM;
+
+	ret = mv_cesa_dev_dma_init(cesa);
+	if (ret)
+		return ret;
+
+	dram = mv_mbus_dram_info_nooverlap();
+
+	platform_set_drvdata(pdev, cesa);
+
+	for (i = 0; i < caps->nengines; i++) {
+		struct mv_cesa_engine *engine = &cesa->engines[i];
+		char res_name[7];
+
+		engine->id = i;
+		spin_lock_init(&engine->lock);
+
+		ret = mv_cesa_get_sram(pdev, i);
+		if (ret)
+			goto err_cleanup;
+
+		irq = platform_get_irq(pdev, i);
+		if (irq < 0) {
+			ret = irq;
+			goto err_cleanup;
+		}
+
+		/*
+		 * Not all platforms can gate the CESA clocks: do not complain
+		 * if the clock does not exist.
+		 */
+		snprintf(res_name, sizeof(res_name), "cesa%d", i);
+		engine->clk = devm_clk_get(dev, res_name);
+		if (IS_ERR(engine->clk)) {
+			engine->clk = devm_clk_get(dev, NULL);
+			if (IS_ERR(engine->clk))
+				engine->clk = NULL;
+		}
+
+		snprintf(res_name, sizeof(res_name), "cesaz%d", i);
+		engine->zclk = devm_clk_get(dev, res_name);
+		if (IS_ERR(engine->zclk))
+			engine->zclk = NULL;
+
+		ret = clk_prepare_enable(engine->clk);
+		if (ret)
+			goto err_cleanup;
+
+		ret = clk_prepare_enable(engine->zclk);
+		if (ret)
+			goto err_cleanup;
+
+		engine->regs = cesa->regs + CESA_ENGINE_OFF(i);
+
+		if (dram && cesa->caps->has_tdma)
+			mv_cesa_conf_mbus_windows(&cesa->engines[i], dram);
+
+		writel(0, cesa->engines[i].regs + CESA_SA_INT_STATUS);
+		writel(CESA_SA_CFG_STOP_DIG_ERR,
+		       cesa->engines[i].regs + CESA_SA_CFG);
+		writel(engine->sram_dma & CESA_SA_SRAM_MSK,
+		       cesa->engines[i].regs + CESA_SA_DESC_P0);
+
+		ret = devm_request_threaded_irq(dev, irq, NULL, mv_cesa_int,
+						IRQF_ONESHOT,
+						dev_name(&pdev->dev),
+						&cesa->engines[i]);
+		if (ret)
+			goto err_cleanup;
+	}
+
+	cesa_dev = cesa;
+
+	ret = mv_cesa_add_algs(cesa);
+	if (ret) {
+		cesa_dev = NULL;
+		goto err_cleanup;
+	}
+
+	dev_info(dev, "CESA device successfully registered\n");
+
+	return 0;
+
+err_cleanup:
+	for (i = 0; i < caps->nengines; i++) {
+		clk_disable_unprepare(cesa->engines[i].zclk);
+		clk_disable_unprepare(cesa->engines[i].clk);
+		mv_cesa_put_sram(pdev, i);
+	}
+
+	return ret;
+}
+
+static int mv_cesa_remove(struct platform_device *pdev)
+{
+	struct mv_cesa_dev *cesa = platform_get_drvdata(pdev);
+	int i;
+
+	mv_cesa_remove_algs(cesa);
+
+	for (i = 0; i < cesa->caps->nengines; i++) {
+		clk_disable_unprepare(cesa->engines[i].zclk);
+		clk_disable_unprepare(cesa->engines[i].clk);
+		mv_cesa_put_sram(pdev, i);
+	}
+
+	return 0;
+}
+
+static struct platform_driver marvell_cesa = {
+	.probe		= mv_cesa_probe,
+	.remove		= mv_cesa_remove,
+	.driver		= {
+		.owner	= THIS_MODULE,
+		.name	= "marvell-cesa",
+		.of_match_table = mv_cesa_of_match_table,
+	},
+};
+module_platform_driver(marvell_cesa);
+
+MODULE_ALIAS("platform:mv_crypto");
+MODULE_AUTHOR("Boris Brezillon <boris.brezillon@free-electrons.com>");
+MODULE_AUTHOR("Arnaud Ebalard <arno@natisbad.org>");
+MODULE_DESCRIPTION("Support for Marvell's cryptographic engine");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/crypto/marvell/cesa.h b/drivers/crypto/marvell/cesa.h
new file mode 100644
index 000000000000..b60698b30d30
--- /dev/null
+++ b/drivers/crypto/marvell/cesa.h
@@ -0,0 +1,791 @@
+#ifndef __MARVELL_CESA_H__
+#define __MARVELL_CESA_H__
+
+#include <crypto/algapi.h>
+#include <crypto/hash.h>
+#include <crypto/internal/hash.h>
+
+#include <linux/crypto.h>
+#include <linux/dmapool.h>
+
+#define CESA_ENGINE_OFF(i)			(((i) * 0x2000))
+
+#define CESA_TDMA_BYTE_CNT			0x800
+#define CESA_TDMA_SRC_ADDR			0x810
+#define CESA_TDMA_DST_ADDR			0x820
+#define CESA_TDMA_NEXT_ADDR			0x830
+
+#define CESA_TDMA_CONTROL			0x840
+#define CESA_TDMA_DST_BURST			GENMASK(2, 0)
+#define CESA_TDMA_DST_BURST_32B			3
+#define CESA_TDMA_DST_BURST_128B		4
+#define CESA_TDMA_OUT_RD_EN			BIT(4)
+#define CESA_TDMA_SRC_BURST			GENMASK(8, 6)
+#define CESA_TDMA_SRC_BURST_32B			(3 << 6)
+#define CESA_TDMA_SRC_BURST_128B		(4 << 6)
+#define CESA_TDMA_CHAIN				BIT(9)
+#define CESA_TDMA_BYTE_SWAP			BIT(11)
+#define CESA_TDMA_NO_BYTE_SWAP			BIT(11)
+#define CESA_TDMA_EN				BIT(12)
+#define CESA_TDMA_FETCH_ND			BIT(13)
+#define CESA_TDMA_ACT				BIT(14)
+
+#define CESA_TDMA_CUR				0x870
+#define CESA_TDMA_ERROR_CAUSE			0x8c8
+#define CESA_TDMA_ERROR_MSK			0x8cc
+
+#define CESA_TDMA_WINDOW_BASE(x)		(((x) * 0x8) + 0xa00)
+#define CESA_TDMA_WINDOW_CTRL(x)		(((x) * 0x8) + 0xa04)
+
+#define CESA_IVDIG(x)				(0xdd00 + ((x) * 4) +	\
+						 (((x) < 5) ? 0 : 0x14))
+
+#define CESA_SA_CMD				0xde00
+#define CESA_SA_CMD_EN_CESA_SA_ACCL0		BIT(0)
+#define CESA_SA_CMD_EN_CESA_SA_ACCL1		BIT(1)
+#define CESA_SA_CMD_DISABLE_SEC			BIT(2)
+
+#define CESA_SA_DESC_P0				0xde04
+
+#define CESA_SA_DESC_P1				0xde14
+
+#define CESA_SA_CFG				0xde08
+#define CESA_SA_CFG_STOP_DIG_ERR		GENMASK(1, 0)
+#define CESA_SA_CFG_DIG_ERR_CONT		0
+#define CESA_SA_CFG_DIG_ERR_SKIP		1
+#define CESA_SA_CFG_DIG_ERR_STOP		3
+#define CESA_SA_CFG_CH0_W_IDMA			BIT(7)
+#define CESA_SA_CFG_CH1_W_IDMA			BIT(8)
+#define CESA_SA_CFG_ACT_CH0_IDMA		BIT(9)
+#define CESA_SA_CFG_ACT_CH1_IDMA		BIT(10)
+#define CESA_SA_CFG_MULTI_PKT			BIT(11)
+#define CESA_SA_CFG_PARA_DIS			BIT(13)
+
+#define CESA_SA_ACCEL_STATUS			0xde0c
+#define CESA_SA_ST_ACT_0			BIT(0)
+#define CESA_SA_ST_ACT_1			BIT(1)
+
+/*
+ * CESA_SA_FPGA_INT_STATUS looks like a FPGA leftover and is documented only
+ * in Errata 4.12. It looks like that it was part of an IRQ-controller in FPGA
+ * and someone forgot to remove  it while switching to the core and moving to
+ * CESA_SA_INT_STATUS.
+ */
+#define CESA_SA_FPGA_INT_STATUS			0xdd68
+#define CESA_SA_INT_STATUS			0xde20
+#define CESA_SA_INT_AUTH_DONE			BIT(0)
+#define CESA_SA_INT_DES_E_DONE			BIT(1)
+#define CESA_SA_INT_AES_E_DONE			BIT(2)
+#define CESA_SA_INT_AES_D_DONE			BIT(3)
+#define CESA_SA_INT_ENC_DONE			BIT(4)
+#define CESA_SA_INT_ACCEL0_DONE			BIT(5)
+#define CESA_SA_INT_ACCEL1_DONE			BIT(6)
+#define CESA_SA_INT_ACC0_IDMA_DONE		BIT(7)
+#define CESA_SA_INT_ACC1_IDMA_DONE		BIT(8)
+#define CESA_SA_INT_IDMA_DONE			BIT(9)
+#define CESA_SA_INT_IDMA_OWN_ERR		BIT(10)
+
+#define CESA_SA_INT_MSK				0xde24
+
+#define CESA_SA_DESC_CFG_OP_MAC_ONLY		0
+#define CESA_SA_DESC_CFG_OP_CRYPT_ONLY		1
+#define CESA_SA_DESC_CFG_OP_MAC_CRYPT		2
+#define CESA_SA_DESC_CFG_OP_CRYPT_MAC		3
+#define CESA_SA_DESC_CFG_OP_MSK			GENMASK(1, 0)
+#define CESA_SA_DESC_CFG_MACM_SHA256		(1 << 4)
+#define CESA_SA_DESC_CFG_MACM_HMAC_SHA256	(3 << 4)
+#define CESA_SA_DESC_CFG_MACM_MD5		(4 << 4)
+#define CESA_SA_DESC_CFG_MACM_SHA1		(5 << 4)
+#define CESA_SA_DESC_CFG_MACM_HMAC_MD5		(6 << 4)
+#define CESA_SA_DESC_CFG_MACM_HMAC_SHA1		(7 << 4)
+#define CESA_SA_DESC_CFG_MACM_MSK		GENMASK(6, 4)
+#define CESA_SA_DESC_CFG_CRYPTM_DES		(1 << 8)
+#define CESA_SA_DESC_CFG_CRYPTM_3DES		(2 << 8)
+#define CESA_SA_DESC_CFG_CRYPTM_AES		(3 << 8)
+#define CESA_SA_DESC_CFG_CRYPTM_MSK		GENMASK(9, 8)
+#define CESA_SA_DESC_CFG_DIR_ENC		(0 << 12)
+#define CESA_SA_DESC_CFG_DIR_DEC		(1 << 12)
+#define CESA_SA_DESC_CFG_CRYPTCM_ECB		(0 << 16)
+#define CESA_SA_DESC_CFG_CRYPTCM_CBC		(1 << 16)
+#define CESA_SA_DESC_CFG_CRYPTCM_MSK		BIT(16)
+#define CESA_SA_DESC_CFG_3DES_EEE		(0 << 20)
+#define CESA_SA_DESC_CFG_3DES_EDE		(1 << 20)
+#define CESA_SA_DESC_CFG_AES_LEN_128		(0 << 24)
+#define CESA_SA_DESC_CFG_AES_LEN_192		(1 << 24)
+#define CESA_SA_DESC_CFG_AES_LEN_256		(2 << 24)
+#define CESA_SA_DESC_CFG_AES_LEN_MSK		GENMASK(25, 24)
+#define CESA_SA_DESC_CFG_NOT_FRAG		(0 << 30)
+#define CESA_SA_DESC_CFG_FIRST_FRAG		(1 << 30)
+#define CESA_SA_DESC_CFG_LAST_FRAG		(2 << 30)
+#define CESA_SA_DESC_CFG_MID_FRAG		(3 << 30)
+#define CESA_SA_DESC_CFG_FRAG_MSK		GENMASK(31, 30)
+
+/*
+ * /-----------\ 0
+ * | ACCEL CFG |	4 * 8
+ * |-----------| 0x20
+ * | CRYPT KEY |	8 * 4
+ * |-----------| 0x40
+ * |  IV   IN  |	4 * 4
+ * |-----------| 0x40 (inplace)
+ * |  IV BUF   |	4 * 4
+ * |-----------| 0x80
+ * |  DATA IN  |	16 * x (max ->max_req_size)
+ * |-----------| 0x80 (inplace operation)
+ * |  DATA OUT |	16 * x (max ->max_req_size)
+ * \-----------/ SRAM size
+ */
+
+/*
+ * Hashing memory map:
+ * /-----------\ 0
+ * | ACCEL CFG |        4 * 8
+ * |-----------| 0x20
+ * | Inner IV  |        8 * 4
+ * |-----------| 0x40
+ * | Outer IV  |        8 * 4
+ * |-----------| 0x60
+ * | Output BUF|        8 * 4
+ * |-----------| 0x80
+ * |  DATA IN  |        64 * x (max ->max_req_size)
+ * \-----------/ SRAM size
+ */
+
+#define CESA_SA_CFG_SRAM_OFFSET			0x00
+#define CESA_SA_DATA_SRAM_OFFSET		0x80
+
+#define CESA_SA_CRYPT_KEY_SRAM_OFFSET		0x20
+#define CESA_SA_CRYPT_IV_SRAM_OFFSET		0x40
+
+#define CESA_SA_MAC_IIV_SRAM_OFFSET		0x20
+#define CESA_SA_MAC_OIV_SRAM_OFFSET		0x40
+#define CESA_SA_MAC_DIG_SRAM_OFFSET		0x60
+
+#define CESA_SA_DESC_CRYPT_DATA(offset)					\
+	cpu_to_le32((CESA_SA_DATA_SRAM_OFFSET + (offset)) |		\
+		    ((CESA_SA_DATA_SRAM_OFFSET + (offset)) << 16))
+
+#define CESA_SA_DESC_CRYPT_IV(offset)					\
+	cpu_to_le32((CESA_SA_CRYPT_IV_SRAM_OFFSET + (offset)) |	\
+		    ((CESA_SA_CRYPT_IV_SRAM_OFFSET + (offset)) << 16))
+
+#define CESA_SA_DESC_CRYPT_KEY(offset)					\
+	cpu_to_le32(CESA_SA_CRYPT_KEY_SRAM_OFFSET + (offset))
+
+#define CESA_SA_DESC_MAC_DATA(offset)					\
+	cpu_to_le32(CESA_SA_DATA_SRAM_OFFSET + (offset))
+#define CESA_SA_DESC_MAC_DATA_MSK		GENMASK(15, 0)
+
+#define CESA_SA_DESC_MAC_TOTAL_LEN(total_len)	cpu_to_le32((total_len) << 16)
+#define CESA_SA_DESC_MAC_TOTAL_LEN_MSK		GENMASK(31, 16)
+
+#define CESA_SA_DESC_MAC_SRC_TOTAL_LEN_MAX	0xffff
+
+#define CESA_SA_DESC_MAC_DIGEST(offset)					\
+	cpu_to_le32(CESA_SA_MAC_DIG_SRAM_OFFSET + (offset))
+#define CESA_SA_DESC_MAC_DIGEST_MSK		GENMASK(15, 0)
+
+#define CESA_SA_DESC_MAC_FRAG_LEN(frag_len)	cpu_to_le32((frag_len) << 16)
+#define CESA_SA_DESC_MAC_FRAG_LEN_MSK		GENMASK(31, 16)
+
+#define CESA_SA_DESC_MAC_IV(offset)					\
+	cpu_to_le32((CESA_SA_MAC_IIV_SRAM_OFFSET + (offset)) |		\
+		    ((CESA_SA_MAC_OIV_SRAM_OFFSET + (offset)) << 16))
+
+#define CESA_SA_SRAM_SIZE			2048
+#define CESA_SA_SRAM_PAYLOAD_SIZE		(cesa_dev->sram_size - \
+						 CESA_SA_DATA_SRAM_OFFSET)
+
+#define CESA_SA_DEFAULT_SRAM_SIZE		2048
+#define CESA_SA_MIN_SRAM_SIZE			1024
+
+#define CESA_SA_SRAM_MSK			(2048 - 1)
+
+#define CESA_MAX_HASH_BLOCK_SIZE		64
+#define CESA_HASH_BLOCK_SIZE_MSK		(CESA_MAX_HASH_BLOCK_SIZE - 1)
+
+/**
+ * struct mv_cesa_sec_accel_desc - security accelerator descriptor
+ * @config:	engine config
+ * @enc_p:	input and output data pointers for a cipher operation
+ * @enc_len:	cipher operation length
+ * @enc_key_p:	cipher key pointer
+ * @enc_iv:	cipher IV pointers
+ * @mac_src_p:	input pointer and total hash length
+ * @mac_digest:	digest pointer and hash operation length
+ * @mac_iv:	hmac IV pointers
+ *
+ * Structure passed to the CESA engine to describe the crypto operation
+ * to be executed.
+ */
+struct mv_cesa_sec_accel_desc {
+	u32 config;
+	u32 enc_p;
+	u32 enc_len;
+	u32 enc_key_p;
+	u32 enc_iv;
+	u32 mac_src_p;
+	u32 mac_digest;
+	u32 mac_iv;
+};
+
+/**
+ * struct mv_cesa_blkcipher_op_ctx - cipher operation context
+ * @key:	cipher key
+ * @iv:		cipher IV
+ *
+ * Context associated to a cipher operation.
+ */
+struct mv_cesa_blkcipher_op_ctx {
+	u32 key[8];
+	u32 iv[4];
+};
+
+/**
+ * struct mv_cesa_hash_op_ctx - hash or hmac operation context
+ * @key:	cipher key
+ * @iv:		cipher IV
+ *
+ * Context associated to an hash or hmac operation.
+ */
+struct mv_cesa_hash_op_ctx {
+	u32 iv[16];
+	u32 hash[8];
+};
+
+/**
+ * struct mv_cesa_op_ctx - crypto operation context
+ * @desc:	CESA descriptor
+ * @ctx:	context associated to the crypto operation
+ *
+ * Context associated to a crypto operation.
+ */
+struct mv_cesa_op_ctx {
+	struct mv_cesa_sec_accel_desc desc;
+	union {
+		struct mv_cesa_blkcipher_op_ctx blkcipher;
+		struct mv_cesa_hash_op_ctx hash;
+	} ctx;
+};
+
+/* TDMA descriptor flags */
+#define CESA_TDMA_DST_IN_SRAM			BIT(31)
+#define CESA_TDMA_SRC_IN_SRAM			BIT(30)
+#define CESA_TDMA_TYPE_MSK			GENMASK(29, 0)
+#define CESA_TDMA_DUMMY				0
+#define CESA_TDMA_DATA				1
+#define CESA_TDMA_OP				2
+
+/**
+ * struct mv_cesa_tdma_desc - TDMA descriptor
+ * @byte_cnt:	number of bytes to transfer
+ * @src:	DMA address of the source
+ * @dst:	DMA address of the destination
+ * @next_dma:	DMA address of the next TDMA descriptor
+ * @cur_dma:	DMA address of this TDMA descriptor
+ * @next:	pointer to the next TDMA descriptor
+ * @op:		CESA operation attached to this TDMA descriptor
+ * @data:	raw data attached to this TDMA descriptor
+ * @flags:	flags describing the TDMA transfer. See the
+ *		"TDMA descriptor flags" section above
+ *
+ * TDMA descriptor used to create a transfer chain describing a crypto
+ * operation.
+ */
+struct mv_cesa_tdma_desc {
+	u32 byte_cnt;
+	u32 src;
+	u32 dst;
+	u32 next_dma;
+	u32 cur_dma;
+	struct mv_cesa_tdma_desc *next;
+	union {
+		struct mv_cesa_op_ctx *op;
+		void *data;
+	};
+	u32 flags;
+};
+
+/**
+ * struct mv_cesa_sg_dma_iter - scatter-gather iterator
+ * @dir:	transfer direction
+ * @sg:		scatter list
+ * @offset:	current position in the scatter list
+ * @op_offset:	current position in the crypto operation
+ *
+ * Iterator used to iterate over a scatterlist while creating a TDMA chain for
+ * a crypto operation.
+ */
+struct mv_cesa_sg_dma_iter {
+	enum dma_data_direction dir;
+	struct scatterlist *sg;
+	unsigned int offset;
+	unsigned int op_offset;
+};
+
+/**
+ * struct mv_cesa_dma_iter - crypto operation iterator
+ * @len:	the crypto operation length
+ * @offset:	current position in the crypto operation
+ * @op_len:	sub-operation length (the crypto engine can only act on 2kb
+ *		chunks)
+ *
+ * Iterator used to create a TDMA chain for a given crypto operation.
+ */
+struct mv_cesa_dma_iter {
+	unsigned int len;
+	unsigned int offset;
+	unsigned int op_len;
+};
+
+/**
+ * struct mv_cesa_tdma_chain - TDMA chain
+ * @first:	first entry in the TDMA chain
+ * @last:	last entry in the TDMA chain
+ *
+ * Stores a TDMA chain for a specific crypto operation.
+ */
+struct mv_cesa_tdma_chain {
+	struct mv_cesa_tdma_desc *first;
+	struct mv_cesa_tdma_desc *last;
+};
+
+struct mv_cesa_engine;
+
+/**
+ * struct mv_cesa_caps - CESA device capabilities
+ * @engines:		number of engines
+ * @has_tdma:		whether this device has a TDMA block
+ * @cipher_algs:	supported cipher algorithms
+ * @ncipher_algs:	number of supported cipher algorithms
+ * @ahash_algs:		supported hash algorithms
+ * @nahash_algs:	number of supported hash algorithms
+ *
+ * Structure used to describe CESA device capabilities.
+ */
+struct mv_cesa_caps {
+	int nengines;
+	bool has_tdma;
+	struct crypto_alg **cipher_algs;
+	int ncipher_algs;
+	struct ahash_alg **ahash_algs;
+	int nahash_algs;
+};
+
+/**
+ * struct mv_cesa_dev_dma - DMA pools
+ * @tdma_desc_pool:	TDMA desc pool
+ * @op_pool:		crypto operation pool
+ * @cache_pool:		data cache pool (used by hash implementation when the
+ *			hash request is smaller than the hash block size)
+ * @padding_pool:	padding pool (used by hash implementation when hardware
+ *			padding cannot be used)
+ *
+ * Structure containing the different DMA pools used by this driver.
+ */
+struct mv_cesa_dev_dma {
+	struct dma_pool *tdma_desc_pool;
+	struct dma_pool *op_pool;
+	struct dma_pool *cache_pool;
+	struct dma_pool *padding_pool;
+};
+
+/**
+ * struct mv_cesa_dev - CESA device
+ * @caps:	device capabilities
+ * @regs:	device registers
+ * @sram_size:	usable SRAM size
+ * @lock:	device lock
+ * @queue:	crypto request queue
+ * @engines:	array of engines
+ * @dma:	dma pools
+ *
+ * Structure storing CESA device information.
+ */
+struct mv_cesa_dev {
+	const struct mv_cesa_caps *caps;
+	void __iomem *regs;
+	struct device *dev;
+	unsigned int sram_size;
+	spinlock_t lock;
+	struct crypto_queue queue;
+	struct mv_cesa_engine *engines;
+	struct mv_cesa_dev_dma *dma;
+};
+
+/**
+ * struct mv_cesa_engine - CESA engine
+ * @id:			engine id
+ * @regs:		engine registers
+ * @sram:		SRAM memory region
+ * @sram_dma:		DMA address of the SRAM memory region
+ * @lock:		engine lock
+ * @req:		current crypto request
+ * @clk:		engine clk
+ * @zclk:		engine zclk
+ * @max_req_len:	maximum chunk length (useful to create the TDMA chain)
+ * @int_mask:		interrupt mask cache
+ * @pool:		memory pool pointing to the memory region reserved in
+ *			SRAM
+ *
+ * Structure storing CESA engine information.
+ */
+struct mv_cesa_engine {
+	int id;
+	void __iomem *regs;
+	void __iomem *sram;
+	dma_addr_t sram_dma;
+	spinlock_t lock;
+	struct crypto_async_request *req;
+	struct clk *clk;
+	struct clk *zclk;
+	size_t max_req_len;
+	u32 int_mask;
+	struct gen_pool *pool;
+};
+
+/**
+ * struct mv_cesa_req_ops - CESA request operations
+ * @prepare:	prepare a request to be executed on the specified engine
+ * @process:	process a request chunk result (should return 0 if the
+ *		operation, -EINPROGRESS if it needs more steps or an error
+ *		code)
+ * @step:	launch the crypto operation on the next chunk
+ * @cleanup:	cleanup the crypto request (release associated data)
+ */
+struct mv_cesa_req_ops {
+	void (*prepare)(struct crypto_async_request *req,
+			struct mv_cesa_engine *engine);
+	int (*process)(struct crypto_async_request *req, u32 status);
+	void (*step)(struct crypto_async_request *req);
+	void (*cleanup)(struct crypto_async_request *req);
+};
+
+/**
+ * struct mv_cesa_ctx - CESA operation context
+ * @ops:	crypto operations
+ *
+ * Base context structure inherited by operation specific ones.
+ */
+struct mv_cesa_ctx {
+	const struct mv_cesa_req_ops *ops;
+};
+
+/**
+ * struct mv_cesa_hash_ctx - CESA hash operation context
+ * @base:	base context structure
+ *
+ * Hash context structure.
+ */
+struct mv_cesa_hash_ctx {
+	struct mv_cesa_ctx base;
+};
+
+/**
+ * struct mv_cesa_hash_ctx - CESA hmac operation context
+ * @base:	base context structure
+ * @iv:		initialization vectors
+ *
+ * HMAC context structure.
+ */
+struct mv_cesa_hmac_ctx {
+	struct mv_cesa_ctx base;
+	u32 iv[16];
+};
+
+/**
+ * enum mv_cesa_req_type - request type definitions
+ * @CESA_STD_REQ:	standard request
+ * @CESA_DMA_REQ:	DMA request
+ */
+enum mv_cesa_req_type {
+	CESA_STD_REQ,
+	CESA_DMA_REQ,
+};
+
+/**
+ * struct mv_cesa_req - CESA request
+ * @type:	request type
+ * @engine:	engine associated with this request
+ */
+struct mv_cesa_req {
+	enum mv_cesa_req_type type;
+	struct mv_cesa_engine *engine;
+};
+
+/**
+ * struct mv_cesa_tdma_req - CESA TDMA request
+ * @base:	base information
+ * @chain:	TDMA chain
+ */
+struct mv_cesa_tdma_req {
+	struct mv_cesa_req base;
+	struct mv_cesa_tdma_chain chain;
+};
+
+/**
+ * struct mv_cesa_sg_std_iter - CESA scatter-gather iterator for standard
+ *				requests
+ * @iter:	sg mapping iterator
+ * @offset:	current offset in the SG entry mapped in memory
+ */
+struct mv_cesa_sg_std_iter {
+	struct sg_mapping_iter iter;
+	unsigned int offset;
+};
+
+/**
+ * struct mv_cesa_ablkcipher_std_req - cipher standard request
+ * @base:	base information
+ * @op:		operation context
+ * @offset:	current operation offset
+ * @size:	size of the crypto operation
+ */
+struct mv_cesa_ablkcipher_std_req {
+	struct mv_cesa_req base;
+	struct mv_cesa_op_ctx op;
+	unsigned int offset;
+	unsigned int size;
+	bool skip_ctx;
+};
+
+/**
+ * struct mv_cesa_ablkcipher_req - cipher request
+ * @req:	type specific request information
+ * @src_nents:	number of entries in the src sg list
+ * @dst_nents:	number of entries in the dest sg list
+ */
+struct mv_cesa_ablkcipher_req {
+	union {
+		struct mv_cesa_req base;
+		struct mv_cesa_tdma_req dma;
+		struct mv_cesa_ablkcipher_std_req std;
+	} req;
+	int src_nents;
+	int dst_nents;
+};
+
+/**
+ * struct mv_cesa_ahash_std_req - standard hash request
+ * @base:	base information
+ * @offset:	current operation offset
+ */
+struct mv_cesa_ahash_std_req {
+	struct mv_cesa_req base;
+	unsigned int offset;
+};
+
+/**
+ * struct mv_cesa_ahash_dma_req - DMA hash request
+ * @base:		base information
+ * @padding:		padding buffer
+ * @padding_dma:	DMA address of the padding buffer
+ * @cache_dma:		DMA address of the cache buffer
+ */
+struct mv_cesa_ahash_dma_req {
+	struct mv_cesa_tdma_req base;
+	u8 *padding;
+	dma_addr_t padding_dma;
+	dma_addr_t cache_dma;
+};
+
+/**
+ * struct mv_cesa_ahash_req - hash request
+ * @req:		type specific request information
+ * @cache:		cache buffer
+ * @cache_ptr:		write pointer in the cache buffer
+ * @len:		hash total length
+ * @src_nents:		number of entries in the scatterlist
+ * @last_req:		define whether the current operation is the last one
+ *			or not
+ * @state:		hash state
+ */
+struct mv_cesa_ahash_req {
+	union {
+		struct mv_cesa_req base;
+		struct mv_cesa_ahash_dma_req dma;
+		struct mv_cesa_ahash_std_req std;
+	} req;
+	struct mv_cesa_op_ctx op_tmpl;
+	u8 *cache;
+	unsigned int cache_ptr;
+	u64 len;
+	int src_nents;
+	bool last_req;
+	__be32 state[8];
+};
+
+/* CESA functions */
+
+extern struct mv_cesa_dev *cesa_dev;
+
+static inline void mv_cesa_update_op_cfg(struct mv_cesa_op_ctx *op,
+					 u32 cfg, u32 mask)
+{
+	op->desc.config &= cpu_to_le32(~mask);
+	op->desc.config |= cpu_to_le32(cfg);
+}
+
+static inline u32 mv_cesa_get_op_cfg(struct mv_cesa_op_ctx *op)
+{
+	return le32_to_cpu(op->desc.config);
+}
+
+static inline void mv_cesa_set_op_cfg(struct mv_cesa_op_ctx *op, u32 cfg)
+{
+	op->desc.config = cpu_to_le32(cfg);
+}
+
+static inline void mv_cesa_adjust_op(struct mv_cesa_engine *engine,
+				     struct mv_cesa_op_ctx *op)
+{
+	u32 offset = engine->sram_dma & CESA_SA_SRAM_MSK;
+
+	op->desc.enc_p = CESA_SA_DESC_CRYPT_DATA(offset);
+	op->desc.enc_key_p = CESA_SA_DESC_CRYPT_KEY(offset);
+	op->desc.enc_iv = CESA_SA_DESC_CRYPT_IV(offset);
+	op->desc.mac_src_p &= ~CESA_SA_DESC_MAC_DATA_MSK;
+	op->desc.mac_src_p |= CESA_SA_DESC_MAC_DATA(offset);
+	op->desc.mac_digest &= ~CESA_SA_DESC_MAC_DIGEST_MSK;
+	op->desc.mac_digest |= CESA_SA_DESC_MAC_DIGEST(offset);
+	op->desc.mac_iv = CESA_SA_DESC_MAC_IV(offset);
+}
+
+static inline void mv_cesa_set_crypt_op_len(struct mv_cesa_op_ctx *op, int len)
+{
+	op->desc.enc_len = cpu_to_le32(len);
+}
+
+static inline void mv_cesa_set_mac_op_total_len(struct mv_cesa_op_ctx *op,
+						int len)
+{
+	op->desc.mac_src_p &= ~CESA_SA_DESC_MAC_TOTAL_LEN_MSK;
+	op->desc.mac_src_p |= CESA_SA_DESC_MAC_TOTAL_LEN(len);
+}
+
+static inline void mv_cesa_set_mac_op_frag_len(struct mv_cesa_op_ctx *op,
+					       int len)
+{
+	op->desc.mac_digest &= ~CESA_SA_DESC_MAC_FRAG_LEN_MSK;
+	op->desc.mac_digest |= CESA_SA_DESC_MAC_FRAG_LEN(len);
+}
+
+static inline void mv_cesa_set_int_mask(struct mv_cesa_engine *engine,
+					u32 int_mask)
+{
+	if (int_mask == engine->int_mask)
+		return;
+
+	writel(int_mask, engine->regs + CESA_SA_INT_MSK);
+	engine->int_mask = int_mask;
+}
+
+static inline u32 mv_cesa_get_int_mask(struct mv_cesa_engine *engine)
+{
+	return engine->int_mask;
+}
+
+int mv_cesa_queue_req(struct crypto_async_request *req);
+
+/* TDMA functions */
+
+static inline void mv_cesa_req_dma_iter_init(struct mv_cesa_dma_iter *iter,
+					     unsigned int len)
+{
+	iter->len = len;
+	iter->op_len = min(len, CESA_SA_SRAM_PAYLOAD_SIZE);
+	iter->offset = 0;
+}
+
+static inline void mv_cesa_sg_dma_iter_init(struct mv_cesa_sg_dma_iter *iter,
+					    struct scatterlist *sg,
+					    enum dma_data_direction dir)
+{
+	iter->op_offset = 0;
+	iter->offset = 0;
+	iter->sg = sg;
+	iter->dir = dir;
+}
+
+static inline unsigned int
+mv_cesa_req_dma_iter_transfer_len(struct mv_cesa_dma_iter *iter,
+				  struct mv_cesa_sg_dma_iter *sgiter)
+{
+	return min(iter->op_len - sgiter->op_offset,
+		   sg_dma_len(sgiter->sg) - sgiter->offset);
+}
+
+bool mv_cesa_req_dma_iter_next_transfer(struct mv_cesa_dma_iter *chain,
+					struct mv_cesa_sg_dma_iter *sgiter,
+					unsigned int len);
+
+static inline bool mv_cesa_req_dma_iter_next_op(struct mv_cesa_dma_iter *iter)
+{
+	iter->offset += iter->op_len;
+	iter->op_len = min(iter->len - iter->offset,
+			   CESA_SA_SRAM_PAYLOAD_SIZE);
+
+	return iter->op_len;
+}
+
+void mv_cesa_dma_step(struct mv_cesa_tdma_req *dreq);
+
+static inline int mv_cesa_dma_process(struct mv_cesa_tdma_req *dreq,
+				      u32 status)
+{
+	if (!(status & CESA_SA_INT_ACC0_IDMA_DONE))
+		return -EINPROGRESS;
+
+	if (status & CESA_SA_INT_IDMA_OWN_ERR)
+		return -EINVAL;
+
+	return 0;
+}
+
+void mv_cesa_dma_prepare(struct mv_cesa_tdma_req *dreq,
+			 struct mv_cesa_engine *engine);
+
+void mv_cesa_dma_cleanup(struct mv_cesa_tdma_req *dreq);
+
+static inline void
+mv_cesa_tdma_desc_iter_init(struct mv_cesa_tdma_chain *chain)
+{
+	memset(chain, 0, sizeof(*chain));
+}
+
+struct mv_cesa_op_ctx *mv_cesa_dma_add_op(struct mv_cesa_tdma_chain *chain,
+					const struct mv_cesa_op_ctx *op_templ,
+					bool skip_ctx,
+					gfp_t flags);
+
+int mv_cesa_dma_add_data_transfer(struct mv_cesa_tdma_chain *chain,
+				  dma_addr_t dst, dma_addr_t src, u32 size,
+				  u32 flags, gfp_t gfp_flags);
+
+int mv_cesa_dma_add_dummy_launch(struct mv_cesa_tdma_chain *chain,
+				 u32 flags);
+
+int mv_cesa_dma_add_dummy_end(struct mv_cesa_tdma_chain *chain, u32 flags);
+
+int mv_cesa_dma_add_op_transfers(struct mv_cesa_tdma_chain *chain,
+				 struct mv_cesa_dma_iter *dma_iter,
+				 struct mv_cesa_sg_dma_iter *sgiter,
+				 gfp_t gfp_flags);
+
+/* Algorithm definitions */
+
+extern struct ahash_alg mv_md5_alg;
+extern struct ahash_alg mv_sha1_alg;
+extern struct ahash_alg mv_sha256_alg;
+extern struct ahash_alg mv_ahmac_md5_alg;
+extern struct ahash_alg mv_ahmac_sha1_alg;
+extern struct ahash_alg mv_ahmac_sha256_alg;
+
+extern struct crypto_alg mv_cesa_ecb_des_alg;
+extern struct crypto_alg mv_cesa_cbc_des_alg;
+extern struct crypto_alg mv_cesa_ecb_des3_ede_alg;
+extern struct crypto_alg mv_cesa_cbc_des3_ede_alg;
+extern struct crypto_alg mv_cesa_ecb_aes_alg;
+extern struct crypto_alg mv_cesa_cbc_aes_alg;
+
+#endif /* __MARVELL_CESA_H__ */
diff --git a/drivers/crypto/marvell/cipher.c b/drivers/crypto/marvell/cipher.c
new file mode 100644
index 000000000000..0745cf3b9c0e
--- /dev/null
+++ b/drivers/crypto/marvell/cipher.c
@@ -0,0 +1,797 @@
+/*
+ * Cipher algorithms supported by the CESA: DES, 3DES and AES.
+ *
+ * Author: Boris Brezillon <boris.brezillon@free-electrons.com>
+ * Author: Arnaud Ebalard <arno@natisbad.org>
+ *
+ * This work is based on an initial version written by
+ * Sebastian Andrzej Siewior < sebastian at breakpoint dot cc >
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#include <crypto/aes.h>
+#include <crypto/des.h>
+
+#include "cesa.h"
+
+struct mv_cesa_des_ctx {
+	struct mv_cesa_ctx base;
+	u8 key[DES_KEY_SIZE];
+};
+
+struct mv_cesa_des3_ctx {
+	struct mv_cesa_ctx base;
+	u8 key[DES3_EDE_KEY_SIZE];
+};
+
+struct mv_cesa_aes_ctx {
+	struct mv_cesa_ctx base;
+	struct crypto_aes_ctx aes;
+};
+
+struct mv_cesa_ablkcipher_dma_iter {
+	struct mv_cesa_dma_iter base;
+	struct mv_cesa_sg_dma_iter src;
+	struct mv_cesa_sg_dma_iter dst;
+};
+
+static inline void
+mv_cesa_ablkcipher_req_iter_init(struct mv_cesa_ablkcipher_dma_iter *iter,
+				 struct ablkcipher_request *req)
+{
+	mv_cesa_req_dma_iter_init(&iter->base, req->nbytes);
+	mv_cesa_sg_dma_iter_init(&iter->src, req->src, DMA_TO_DEVICE);
+	mv_cesa_sg_dma_iter_init(&iter->dst, req->dst, DMA_FROM_DEVICE);
+}
+
+static inline bool
+mv_cesa_ablkcipher_req_iter_next_op(struct mv_cesa_ablkcipher_dma_iter *iter)
+{
+	iter->src.op_offset = 0;
+	iter->dst.op_offset = 0;
+
+	return mv_cesa_req_dma_iter_next_op(&iter->base);
+}
+
+static inline void
+mv_cesa_ablkcipher_dma_cleanup(struct ablkcipher_request *req)
+{
+	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(req);
+
+	if (req->dst != req->src) {
+		dma_unmap_sg(cesa_dev->dev, req->dst, creq->dst_nents,
+			     DMA_FROM_DEVICE);
+		dma_unmap_sg(cesa_dev->dev, req->src, creq->src_nents,
+			     DMA_TO_DEVICE);
+	} else {
+		dma_unmap_sg(cesa_dev->dev, req->src, creq->src_nents,
+			     DMA_BIDIRECTIONAL);
+	}
+	mv_cesa_dma_cleanup(&creq->req.dma);
+}
+
+static inline void mv_cesa_ablkcipher_cleanup(struct ablkcipher_request *req)
+{
+	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(req);
+
+	if (creq->req.base.type == CESA_DMA_REQ)
+		mv_cesa_ablkcipher_dma_cleanup(req);
+}
+
+static void mv_cesa_ablkcipher_std_step(struct ablkcipher_request *req)
+{
+	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(req);
+	struct mv_cesa_ablkcipher_std_req *sreq = &creq->req.std;
+	struct mv_cesa_engine *engine = sreq->base.engine;
+	size_t  len = min_t(size_t, req->nbytes - sreq->offset,
+			    CESA_SA_SRAM_PAYLOAD_SIZE);
+
+	len = sg_pcopy_to_buffer(req->src, creq->src_nents,
+				 engine->sram + CESA_SA_DATA_SRAM_OFFSET,
+				 len, sreq->offset);
+
+	sreq->size = len;
+	mv_cesa_set_crypt_op_len(&sreq->op, len);
+
+	/* FIXME: only update enc_len field */
+	if (!sreq->skip_ctx) {
+		memcpy(engine->sram, &sreq->op, sizeof(sreq->op));
+		sreq->skip_ctx = true;
+	} else {
+		memcpy(engine->sram, &sreq->op, sizeof(sreq->op.desc));
+	}
+
+	mv_cesa_set_int_mask(engine, CESA_SA_INT_ACCEL0_DONE);
+	writel(CESA_SA_CFG_PARA_DIS, engine->regs + CESA_SA_CFG);
+	writel(CESA_SA_CMD_EN_CESA_SA_ACCL0, engine->regs + CESA_SA_CMD);
+}
+
+static int mv_cesa_ablkcipher_std_process(struct ablkcipher_request *req,
+					  u32 status)
+{
+	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(req);
+	struct mv_cesa_ablkcipher_std_req *sreq = &creq->req.std;
+	struct mv_cesa_engine *engine = sreq->base.engine;
+	size_t len;
+
+	len = sg_pcopy_from_buffer(req->dst, creq->dst_nents,
+				   engine->sram + CESA_SA_DATA_SRAM_OFFSET,
+				   sreq->size, sreq->offset);
+
+	sreq->offset += len;
+	if (sreq->offset < req->nbytes)
+		return -EINPROGRESS;
+
+	return 0;
+}
+
+static int mv_cesa_ablkcipher_process(struct crypto_async_request *req,
+				      u32 status)
+{
+	struct ablkcipher_request *ablkreq = ablkcipher_request_cast(req);
+	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(ablkreq);
+	struct mv_cesa_ablkcipher_std_req *sreq = &creq->req.std;
+	struct mv_cesa_engine *engine = sreq->base.engine;
+	int ret;
+
+	if (creq->req.base.type == CESA_DMA_REQ)
+		ret = mv_cesa_dma_process(&creq->req.dma, status);
+	else
+		ret = mv_cesa_ablkcipher_std_process(ablkreq, status);
+
+	if (ret)
+		return ret;
+
+	memcpy(ablkreq->info, engine->sram + CESA_SA_CRYPT_IV_SRAM_OFFSET,
+	       crypto_ablkcipher_ivsize(crypto_ablkcipher_reqtfm(ablkreq)));
+
+	return 0;
+}
+
+static void mv_cesa_ablkcipher_step(struct crypto_async_request *req)
+{
+	struct ablkcipher_request *ablkreq = ablkcipher_request_cast(req);
+	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(ablkreq);
+
+	if (creq->req.base.type == CESA_DMA_REQ)
+		mv_cesa_dma_step(&creq->req.dma);
+	else
+		mv_cesa_ablkcipher_std_step(ablkreq);
+}
+
+static inline void
+mv_cesa_ablkcipher_dma_prepare(struct ablkcipher_request *req)
+{
+	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(req);
+	struct mv_cesa_tdma_req *dreq = &creq->req.dma;
+
+	mv_cesa_dma_prepare(dreq, dreq->base.engine);
+}
+
+static inline void
+mv_cesa_ablkcipher_std_prepare(struct ablkcipher_request *req)
+{
+	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(req);
+	struct mv_cesa_ablkcipher_std_req *sreq = &creq->req.std;
+	struct mv_cesa_engine *engine = sreq->base.engine;
+
+	sreq->size = 0;
+	sreq->offset = 0;
+	mv_cesa_adjust_op(engine, &sreq->op);
+	memcpy(engine->sram, &sreq->op, sizeof(sreq->op));
+}
+
+static inline void mv_cesa_ablkcipher_prepare(struct crypto_async_request *req,
+					      struct mv_cesa_engine *engine)
+{
+	struct ablkcipher_request *ablkreq = ablkcipher_request_cast(req);
+	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(ablkreq);
+
+	creq->req.base.engine = engine;
+
+	if (creq->req.base.type == CESA_DMA_REQ)
+		mv_cesa_ablkcipher_dma_prepare(ablkreq);
+	else
+		mv_cesa_ablkcipher_std_prepare(ablkreq);
+}
+
+static inline void
+mv_cesa_ablkcipher_req_cleanup(struct crypto_async_request *req)
+{
+	struct ablkcipher_request *ablkreq = ablkcipher_request_cast(req);
+
+	mv_cesa_ablkcipher_cleanup(ablkreq);
+}
+
+static const struct mv_cesa_req_ops mv_cesa_ablkcipher_req_ops = {
+	.step = mv_cesa_ablkcipher_step,
+	.process = mv_cesa_ablkcipher_process,
+	.prepare = mv_cesa_ablkcipher_prepare,
+	.cleanup = mv_cesa_ablkcipher_req_cleanup,
+};
+
+static int mv_cesa_ablkcipher_cra_init(struct crypto_tfm *tfm)
+{
+	struct mv_cesa_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	ctx->base.ops = &mv_cesa_ablkcipher_req_ops;
+
+	tfm->crt_ablkcipher.reqsize = sizeof(struct mv_cesa_ablkcipher_req);
+
+	return 0;
+}
+
+static int mv_cesa_aes_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
+			      unsigned int len)
+{
+	struct crypto_tfm *tfm = crypto_ablkcipher_tfm(cipher);
+	struct mv_cesa_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+	int remaining;
+	int offset;
+	int ret;
+	int i;
+
+	ret = crypto_aes_expand_key(&ctx->aes, key, len);
+	if (ret) {
+		crypto_ablkcipher_set_flags(cipher, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return ret;
+	}
+
+	remaining = (ctx->aes.key_length - 16) / 4;
+	offset = ctx->aes.key_length + 24 - remaining;
+	for (i = 0; i < remaining; i++)
+		ctx->aes.key_dec[4 + i] =
+			cpu_to_le32(ctx->aes.key_enc[offset + i]);
+
+	return 0;
+}
+
+static int mv_cesa_des_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
+			      unsigned int len)
+{
+	struct crypto_tfm *tfm = crypto_ablkcipher_tfm(cipher);
+	struct mv_cesa_des_ctx *ctx = crypto_tfm_ctx(tfm);
+	u32 tmp[DES_EXPKEY_WORDS];
+	int ret;
+
+	if (len != DES_KEY_SIZE) {
+		crypto_ablkcipher_set_flags(cipher, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+
+	ret = des_ekey(tmp, key);
+	if (!ret && (tfm->crt_flags & CRYPTO_TFM_REQ_WEAK_KEY)) {
+		tfm->crt_flags |= CRYPTO_TFM_RES_WEAK_KEY;
+		return -EINVAL;
+	}
+
+	memcpy(ctx->key, key, DES_KEY_SIZE);
+
+	return 0;
+}
+
+static int mv_cesa_des3_ede_setkey(struct crypto_ablkcipher *cipher,
+				   const u8 *key, unsigned int len)
+{
+	struct crypto_tfm *tfm = crypto_ablkcipher_tfm(cipher);
+	struct mv_cesa_des_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	if (len != DES3_EDE_KEY_SIZE) {
+		crypto_ablkcipher_set_flags(cipher, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+
+	memcpy(ctx->key, key, DES3_EDE_KEY_SIZE);
+
+	return 0;
+}
+
+static int mv_cesa_ablkcipher_dma_req_init(struct ablkcipher_request *req,
+				const struct mv_cesa_op_ctx *op_templ)
+{
+	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(req);
+	gfp_t flags = (req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
+		      GFP_KERNEL : GFP_ATOMIC;
+	struct mv_cesa_tdma_req *dreq = &creq->req.dma;
+	struct mv_cesa_ablkcipher_dma_iter iter;
+	struct mv_cesa_tdma_chain chain;
+	bool skip_ctx = false;
+	int ret;
+
+	dreq->base.type = CESA_DMA_REQ;
+	dreq->chain.first = NULL;
+	dreq->chain.last = NULL;
+
+	if (req->src != req->dst) {
+		ret = dma_map_sg(cesa_dev->dev, req->src, creq->src_nents,
+				 DMA_TO_DEVICE);
+		if (!ret)
+			return -ENOMEM;
+
+		ret = dma_map_sg(cesa_dev->dev, req->dst, creq->dst_nents,
+				 DMA_FROM_DEVICE);
+		if (!ret) {
+			ret = -ENOMEM;
+			goto err_unmap_src;
+		}
+	} else {
+		ret = dma_map_sg(cesa_dev->dev, req->src, creq->src_nents,
+				 DMA_BIDIRECTIONAL);
+		if (!ret)
+			return -ENOMEM;
+	}
+
+	mv_cesa_tdma_desc_iter_init(&chain);
+	mv_cesa_ablkcipher_req_iter_init(&iter, req);
+
+	do {
+		struct mv_cesa_op_ctx *op;
+
+		op = mv_cesa_dma_add_op(&chain, op_templ, skip_ctx, flags);
+		if (IS_ERR(op)) {
+			ret = PTR_ERR(op);
+			goto err_free_tdma;
+		}
+		skip_ctx = true;
+
+		mv_cesa_set_crypt_op_len(op, iter.base.op_len);
+
+		/* Add input transfers */
+		ret = mv_cesa_dma_add_op_transfers(&chain, &iter.base,
+						   &iter.src, flags);
+		if (ret)
+			goto err_free_tdma;
+
+		/* Add dummy desc to launch the crypto operation */
+		ret = mv_cesa_dma_add_dummy_launch(&chain, flags);
+		if (ret)
+			goto err_free_tdma;
+
+		/* Add output transfers */
+		ret = mv_cesa_dma_add_op_transfers(&chain, &iter.base,
+						   &iter.dst, flags);
+		if (ret)
+			goto err_free_tdma;
+
+	} while (mv_cesa_ablkcipher_req_iter_next_op(&iter));
+
+	dreq->chain = chain;
+
+	return 0;
+
+err_free_tdma:
+	mv_cesa_dma_cleanup(dreq);
+	if (req->dst != req->src)
+		dma_unmap_sg(cesa_dev->dev, req->dst, creq->dst_nents,
+			     DMA_FROM_DEVICE);
+
+err_unmap_src:
+	dma_unmap_sg(cesa_dev->dev, req->src, creq->src_nents,
+		     req->dst != req->src ? DMA_TO_DEVICE : DMA_BIDIRECTIONAL);
+
+	return ret;
+}
+
+static inline int
+mv_cesa_ablkcipher_std_req_init(struct ablkcipher_request *req,
+				const struct mv_cesa_op_ctx *op_templ)
+{
+	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(req);
+	struct mv_cesa_ablkcipher_std_req *sreq = &creq->req.std;
+
+	sreq->base.type = CESA_STD_REQ;
+	sreq->op = *op_templ;
+	sreq->skip_ctx = false;
+
+	return 0;
+}
+
+static int mv_cesa_ablkcipher_req_init(struct ablkcipher_request *req,
+				       struct mv_cesa_op_ctx *tmpl)
+{
+	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(req);
+	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
+	unsigned int blksize = crypto_ablkcipher_blocksize(tfm);
+	int ret;
+
+	if (!IS_ALIGNED(req->nbytes, blksize))
+		return -EINVAL;
+
+	creq->src_nents = sg_nents_for_len(req->src, req->nbytes);
+	creq->dst_nents = sg_nents_for_len(req->dst, req->nbytes);
+
+	mv_cesa_update_op_cfg(tmpl, CESA_SA_DESC_CFG_OP_CRYPT_ONLY,
+			      CESA_SA_DESC_CFG_OP_MSK);
+
+	/* TODO: add a threshold for DMA usage */
+	if (cesa_dev->caps->has_tdma)
+		ret = mv_cesa_ablkcipher_dma_req_init(req, tmpl);
+	else
+		ret = mv_cesa_ablkcipher_std_req_init(req, tmpl);
+
+	return ret;
+}
+
+static int mv_cesa_des_op(struct ablkcipher_request *req,
+			  struct mv_cesa_op_ctx *tmpl)
+{
+	struct mv_cesa_des_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
+	int ret;
+
+	mv_cesa_update_op_cfg(tmpl, CESA_SA_DESC_CFG_CRYPTM_DES,
+			      CESA_SA_DESC_CFG_CRYPTM_MSK);
+
+	memcpy(tmpl->ctx.blkcipher.key, ctx->key, DES_KEY_SIZE);
+
+	ret = mv_cesa_ablkcipher_req_init(req, tmpl);
+	if (ret)
+		return ret;
+
+	ret = mv_cesa_queue_req(&req->base);
+	if (ret && ret != -EINPROGRESS)
+		mv_cesa_ablkcipher_cleanup(req);
+
+	return ret;
+}
+
+static int mv_cesa_ecb_des_encrypt(struct ablkcipher_request *req)
+{
+	struct mv_cesa_op_ctx tmpl;
+
+	mv_cesa_set_op_cfg(&tmpl,
+			   CESA_SA_DESC_CFG_CRYPTCM_ECB |
+			   CESA_SA_DESC_CFG_DIR_ENC);
+
+	return mv_cesa_des_op(req, &tmpl);
+}
+
+static int mv_cesa_ecb_des_decrypt(struct ablkcipher_request *req)
+{
+	struct mv_cesa_op_ctx tmpl;
+
+	mv_cesa_set_op_cfg(&tmpl,
+			   CESA_SA_DESC_CFG_CRYPTCM_ECB |
+			   CESA_SA_DESC_CFG_DIR_DEC);
+
+	return mv_cesa_des_op(req, &tmpl);
+}
+
+struct crypto_alg mv_cesa_ecb_des_alg = {
+	.cra_name = "ecb(des)",
+	.cra_driver_name = "mv-ecb-des",
+	.cra_priority = 300,
+	.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER |
+		     CRYPTO_ALG_KERN_DRIVER_ONLY | CRYPTO_ALG_ASYNC,
+	.cra_blocksize = DES_BLOCK_SIZE,
+	.cra_ctxsize = sizeof(struct mv_cesa_des_ctx),
+	.cra_alignmask = 0,
+	.cra_type = &crypto_ablkcipher_type,
+	.cra_module = THIS_MODULE,
+	.cra_init = mv_cesa_ablkcipher_cra_init,
+	.cra_u = {
+		.ablkcipher = {
+			.min_keysize = DES_KEY_SIZE,
+			.max_keysize = DES_KEY_SIZE,
+			.setkey = mv_cesa_des_setkey,
+			.encrypt = mv_cesa_ecb_des_encrypt,
+			.decrypt = mv_cesa_ecb_des_decrypt,
+		},
+	},
+};
+
+static int mv_cesa_cbc_des_op(struct ablkcipher_request *req,
+			      struct mv_cesa_op_ctx *tmpl)
+{
+	mv_cesa_update_op_cfg(tmpl, CESA_SA_DESC_CFG_CRYPTCM_CBC,
+			      CESA_SA_DESC_CFG_CRYPTCM_MSK);
+
+	memcpy(tmpl->ctx.blkcipher.iv, req->info, DES_BLOCK_SIZE);
+
+	return mv_cesa_des_op(req, tmpl);
+}
+
+static int mv_cesa_cbc_des_encrypt(struct ablkcipher_request *req)
+{
+	struct mv_cesa_op_ctx tmpl;
+
+	mv_cesa_set_op_cfg(&tmpl, CESA_SA_DESC_CFG_DIR_ENC);
+
+	return mv_cesa_cbc_des_op(req, &tmpl);
+}
+
+static int mv_cesa_cbc_des_decrypt(struct ablkcipher_request *req)
+{
+	struct mv_cesa_op_ctx tmpl;
+
+	mv_cesa_set_op_cfg(&tmpl, CESA_SA_DESC_CFG_DIR_DEC);
+
+	return mv_cesa_cbc_des_op(req, &tmpl);
+}
+
+struct crypto_alg mv_cesa_cbc_des_alg = {
+	.cra_name = "cbc(des)",
+	.cra_driver_name = "mv-cbc-des",
+	.cra_priority = 300,
+	.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER |
+		     CRYPTO_ALG_KERN_DRIVER_ONLY | CRYPTO_ALG_ASYNC,
+	.cra_blocksize = DES_BLOCK_SIZE,
+	.cra_ctxsize = sizeof(struct mv_cesa_des_ctx),
+	.cra_alignmask = 0,
+	.cra_type = &crypto_ablkcipher_type,
+	.cra_module = THIS_MODULE,
+	.cra_init = mv_cesa_ablkcipher_cra_init,
+	.cra_u = {
+		.ablkcipher = {
+			.min_keysize = DES_KEY_SIZE,
+			.max_keysize = DES_KEY_SIZE,
+			.ivsize	     = DES_BLOCK_SIZE,
+			.setkey = mv_cesa_des_setkey,
+			.encrypt = mv_cesa_cbc_des_encrypt,
+			.decrypt = mv_cesa_cbc_des_decrypt,
+		},
+	},
+};
+
+static int mv_cesa_des3_op(struct ablkcipher_request *req,
+			   struct mv_cesa_op_ctx *tmpl)
+{
+	struct mv_cesa_des3_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
+	int ret;
+
+	mv_cesa_update_op_cfg(tmpl, CESA_SA_DESC_CFG_CRYPTM_3DES,
+			      CESA_SA_DESC_CFG_CRYPTM_MSK);
+
+	memcpy(tmpl->ctx.blkcipher.key, ctx->key, DES3_EDE_KEY_SIZE);
+
+	ret = mv_cesa_ablkcipher_req_init(req, tmpl);
+	if (ret)
+		return ret;
+
+	ret = mv_cesa_queue_req(&req->base);
+	if (ret && ret != -EINPROGRESS)
+		mv_cesa_ablkcipher_cleanup(req);
+
+	return ret;
+}
+
+static int mv_cesa_ecb_des3_ede_encrypt(struct ablkcipher_request *req)
+{
+	struct mv_cesa_op_ctx tmpl;
+
+	mv_cesa_set_op_cfg(&tmpl,
+			   CESA_SA_DESC_CFG_CRYPTCM_ECB |
+			   CESA_SA_DESC_CFG_3DES_EDE |
+			   CESA_SA_DESC_CFG_DIR_ENC);
+
+	return mv_cesa_des3_op(req, &tmpl);
+}
+
+static int mv_cesa_ecb_des3_ede_decrypt(struct ablkcipher_request *req)
+{
+	struct mv_cesa_op_ctx tmpl;
+
+	mv_cesa_set_op_cfg(&tmpl,
+			   CESA_SA_DESC_CFG_CRYPTCM_ECB |
+			   CESA_SA_DESC_CFG_3DES_EDE |
+			   CESA_SA_DESC_CFG_DIR_DEC);
+
+	return mv_cesa_des3_op(req, &tmpl);
+}
+
+struct crypto_alg mv_cesa_ecb_des3_ede_alg = {
+	.cra_name = "ecb(des3_ede)",
+	.cra_driver_name = "mv-ecb-des3-ede",
+	.cra_priority = 300,
+	.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER |
+		     CRYPTO_ALG_KERN_DRIVER_ONLY | CRYPTO_ALG_ASYNC,
+	.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+	.cra_ctxsize = sizeof(struct mv_cesa_des3_ctx),
+	.cra_alignmask = 0,
+	.cra_type = &crypto_ablkcipher_type,
+	.cra_module = THIS_MODULE,
+	.cra_init = mv_cesa_ablkcipher_cra_init,
+	.cra_u = {
+		.ablkcipher = {
+			.min_keysize = DES3_EDE_KEY_SIZE,
+			.max_keysize = DES3_EDE_KEY_SIZE,
+			.ivsize	     = DES3_EDE_BLOCK_SIZE,
+			.setkey = mv_cesa_des3_ede_setkey,
+			.encrypt = mv_cesa_ecb_des3_ede_encrypt,
+			.decrypt = mv_cesa_ecb_des3_ede_decrypt,
+		},
+	},
+};
+
+static int mv_cesa_cbc_des3_op(struct ablkcipher_request *req,
+			       struct mv_cesa_op_ctx *tmpl)
+{
+	memcpy(tmpl->ctx.blkcipher.iv, req->info, DES3_EDE_BLOCK_SIZE);
+
+	return mv_cesa_des3_op(req, tmpl);
+}
+
+static int mv_cesa_cbc_des3_ede_encrypt(struct ablkcipher_request *req)
+{
+	struct mv_cesa_op_ctx tmpl;
+
+	mv_cesa_set_op_cfg(&tmpl,
+			   CESA_SA_DESC_CFG_CRYPTCM_CBC |
+			   CESA_SA_DESC_CFG_3DES_EDE |
+			   CESA_SA_DESC_CFG_DIR_ENC);
+
+	return mv_cesa_cbc_des3_op(req, &tmpl);
+}
+
+static int mv_cesa_cbc_des3_ede_decrypt(struct ablkcipher_request *req)
+{
+	struct mv_cesa_op_ctx tmpl;
+
+	mv_cesa_set_op_cfg(&tmpl,
+			   CESA_SA_DESC_CFG_CRYPTCM_CBC |
+			   CESA_SA_DESC_CFG_3DES_EDE |
+			   CESA_SA_DESC_CFG_DIR_DEC);
+
+	return mv_cesa_cbc_des3_op(req, &tmpl);
+}
+
+struct crypto_alg mv_cesa_cbc_des3_ede_alg = {
+	.cra_name = "cbc(des3_ede)",
+	.cra_driver_name = "mv-cbc-des3-ede",
+	.cra_priority = 300,
+	.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER |
+		     CRYPTO_ALG_KERN_DRIVER_ONLY | CRYPTO_ALG_ASYNC,
+	.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+	.cra_ctxsize = sizeof(struct mv_cesa_des3_ctx),
+	.cra_alignmask = 0,
+	.cra_type = &crypto_ablkcipher_type,
+	.cra_module = THIS_MODULE,
+	.cra_init = mv_cesa_ablkcipher_cra_init,
+	.cra_u = {
+		.ablkcipher = {
+			.min_keysize = DES3_EDE_KEY_SIZE,
+			.max_keysize = DES3_EDE_KEY_SIZE,
+			.ivsize	     = DES3_EDE_BLOCK_SIZE,
+			.setkey = mv_cesa_des3_ede_setkey,
+			.encrypt = mv_cesa_cbc_des3_ede_encrypt,
+			.decrypt = mv_cesa_cbc_des3_ede_decrypt,
+		},
+	},
+};
+
+static int mv_cesa_aes_op(struct ablkcipher_request *req,
+			  struct mv_cesa_op_ctx *tmpl)
+{
+	struct mv_cesa_aes_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
+	int ret, i;
+	u32 *key;
+	u32 cfg;
+
+	cfg = CESA_SA_DESC_CFG_CRYPTM_AES;
+
+	if (mv_cesa_get_op_cfg(tmpl) & CESA_SA_DESC_CFG_DIR_DEC)
+		key = ctx->aes.key_dec;
+	else
+		key = ctx->aes.key_enc;
+
+	for (i = 0; i < ctx->aes.key_length / sizeof(u32); i++)
+		tmpl->ctx.blkcipher.key[i] = cpu_to_le32(key[i]);
+
+	if (ctx->aes.key_length == 24)
+		cfg |= CESA_SA_DESC_CFG_AES_LEN_192;
+	else if (ctx->aes.key_length == 32)
+		cfg |= CESA_SA_DESC_CFG_AES_LEN_256;
+
+	mv_cesa_update_op_cfg(tmpl, cfg,
+			      CESA_SA_DESC_CFG_CRYPTM_MSK |
+			      CESA_SA_DESC_CFG_AES_LEN_MSK);
+
+	ret = mv_cesa_ablkcipher_req_init(req, tmpl);
+	if (ret)
+		return ret;
+
+	ret = mv_cesa_queue_req(&req->base);
+	if (ret && ret != -EINPROGRESS)
+		mv_cesa_ablkcipher_cleanup(req);
+
+	return ret;
+}
+
+static int mv_cesa_ecb_aes_encrypt(struct ablkcipher_request *req)
+{
+	struct mv_cesa_op_ctx tmpl;
+
+	mv_cesa_set_op_cfg(&tmpl,
+			   CESA_SA_DESC_CFG_CRYPTCM_ECB |
+			   CESA_SA_DESC_CFG_DIR_ENC);
+
+	return mv_cesa_aes_op(req, &tmpl);
+}
+
+static int mv_cesa_ecb_aes_decrypt(struct ablkcipher_request *req)
+{
+	struct mv_cesa_op_ctx tmpl;
+
+	mv_cesa_set_op_cfg(&tmpl,
+			   CESA_SA_DESC_CFG_CRYPTCM_ECB |
+			   CESA_SA_DESC_CFG_DIR_DEC);
+
+	return mv_cesa_aes_op(req, &tmpl);
+}
+
+struct crypto_alg mv_cesa_ecb_aes_alg = {
+	.cra_name = "ecb(aes)",
+	.cra_driver_name = "mv-ecb-aes",
+	.cra_priority = 300,
+	.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER |
+		     CRYPTO_ALG_KERN_DRIVER_ONLY | CRYPTO_ALG_ASYNC,
+	.cra_blocksize = AES_BLOCK_SIZE,
+	.cra_ctxsize = sizeof(struct mv_cesa_aes_ctx),
+	.cra_alignmask = 0,
+	.cra_type = &crypto_ablkcipher_type,
+	.cra_module = THIS_MODULE,
+	.cra_init = mv_cesa_ablkcipher_cra_init,
+	.cra_u = {
+		.ablkcipher = {
+			.min_keysize = AES_MIN_KEY_SIZE,
+			.max_keysize = AES_MAX_KEY_SIZE,
+			.setkey = mv_cesa_aes_setkey,
+			.encrypt = mv_cesa_ecb_aes_encrypt,
+			.decrypt = mv_cesa_ecb_aes_decrypt,
+		},
+	},
+};
+
+static int mv_cesa_cbc_aes_op(struct ablkcipher_request *req,
+			      struct mv_cesa_op_ctx *tmpl)
+{
+	mv_cesa_update_op_cfg(tmpl, CESA_SA_DESC_CFG_CRYPTCM_CBC,
+			      CESA_SA_DESC_CFG_CRYPTCM_MSK);
+	memcpy(tmpl->ctx.blkcipher.iv, req->info, AES_BLOCK_SIZE);
+
+	return mv_cesa_aes_op(req, tmpl);
+}
+
+static int mv_cesa_cbc_aes_encrypt(struct ablkcipher_request *req)
+{
+	struct mv_cesa_op_ctx tmpl;
+
+	mv_cesa_set_op_cfg(&tmpl, CESA_SA_DESC_CFG_DIR_ENC);
+
+	return mv_cesa_cbc_aes_op(req, &tmpl);
+}
+
+static int mv_cesa_cbc_aes_decrypt(struct ablkcipher_request *req)
+{
+	struct mv_cesa_op_ctx tmpl;
+
+	mv_cesa_set_op_cfg(&tmpl, CESA_SA_DESC_CFG_DIR_DEC);
+
+	return mv_cesa_cbc_aes_op(req, &tmpl);
+}
+
+struct crypto_alg mv_cesa_cbc_aes_alg = {
+	.cra_name = "cbc(aes)",
+	.cra_driver_name = "mv-cbc-aes",
+	.cra_priority = 300,
+	.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER |
+		     CRYPTO_ALG_KERN_DRIVER_ONLY | CRYPTO_ALG_ASYNC,
+	.cra_blocksize = AES_BLOCK_SIZE,
+	.cra_ctxsize = sizeof(struct mv_cesa_aes_ctx),
+	.cra_alignmask = 0,
+	.cra_type = &crypto_ablkcipher_type,
+	.cra_module = THIS_MODULE,
+	.cra_init = mv_cesa_ablkcipher_cra_init,
+	.cra_u = {
+		.ablkcipher = {
+			.min_keysize = AES_MIN_KEY_SIZE,
+			.max_keysize = AES_MAX_KEY_SIZE,
+			.ivsize = AES_BLOCK_SIZE,
+			.setkey = mv_cesa_aes_setkey,
+			.encrypt = mv_cesa_cbc_aes_encrypt,
+			.decrypt = mv_cesa_cbc_aes_decrypt,
+		},
+	},
+};
diff --git a/drivers/crypto/marvell/hash.c b/drivers/crypto/marvell/hash.c
new file mode 100644
index 000000000000..ae9272eb9c1a
--- /dev/null
+++ b/drivers/crypto/marvell/hash.c
@@ -0,0 +1,1441 @@
+/*
+ * Hash algorithms supported by the CESA: MD5, SHA1 and SHA256.
+ *
+ * Author: Boris Brezillon <boris.brezillon@free-electrons.com>
+ * Author: Arnaud Ebalard <arno@natisbad.org>
+ *
+ * This work is based on an initial version written by
+ * Sebastian Andrzej Siewior < sebastian at breakpoint dot cc >
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#include <crypto/md5.h>
+#include <crypto/sha.h>
+
+#include "cesa.h"
+
+struct mv_cesa_ahash_dma_iter {
+	struct mv_cesa_dma_iter base;
+	struct mv_cesa_sg_dma_iter src;
+};
+
+static inline void
+mv_cesa_ahash_req_iter_init(struct mv_cesa_ahash_dma_iter *iter,
+			    struct ahash_request *req)
+{
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+	unsigned int len = req->nbytes;
+
+	if (!creq->last_req)
+		len = (len + creq->cache_ptr) & ~CESA_HASH_BLOCK_SIZE_MSK;
+
+	mv_cesa_req_dma_iter_init(&iter->base, len);
+	mv_cesa_sg_dma_iter_init(&iter->src, req->src, DMA_TO_DEVICE);
+	iter->src.op_offset = creq->cache_ptr;
+}
+
+static inline bool
+mv_cesa_ahash_req_iter_next_op(struct mv_cesa_ahash_dma_iter *iter)
+{
+	iter->src.op_offset = 0;
+
+	return mv_cesa_req_dma_iter_next_op(&iter->base);
+}
+
+static inline int mv_cesa_ahash_dma_alloc_cache(struct mv_cesa_ahash_req *creq,
+						gfp_t flags)
+{
+	struct mv_cesa_ahash_dma_req *dreq = &creq->req.dma;
+
+	creq->cache = dma_pool_alloc(cesa_dev->dma->cache_pool, flags,
+				     &dreq->cache_dma);
+	if (!creq->cache)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static inline int mv_cesa_ahash_std_alloc_cache(struct mv_cesa_ahash_req *creq,
+						gfp_t flags)
+{
+	creq->cache = kzalloc(CESA_MAX_HASH_BLOCK_SIZE, flags);
+	if (!creq->cache)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static int mv_cesa_ahash_alloc_cache(struct ahash_request *req)
+{
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+	gfp_t flags = (req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
+		      GFP_KERNEL : GFP_ATOMIC;
+	int ret;
+
+	if (creq->cache)
+		return 0;
+
+	if (creq->req.base.type == CESA_DMA_REQ)
+		ret = mv_cesa_ahash_dma_alloc_cache(creq, flags);
+	else
+		ret = mv_cesa_ahash_std_alloc_cache(creq, flags);
+
+	return ret;
+}
+
+static inline void mv_cesa_ahash_dma_free_cache(struct mv_cesa_ahash_req *creq)
+{
+	dma_pool_free(cesa_dev->dma->cache_pool, creq->cache,
+		      creq->req.dma.cache_dma);
+}
+
+static inline void mv_cesa_ahash_std_free_cache(struct mv_cesa_ahash_req *creq)
+{
+	kfree(creq->cache);
+}
+
+static void mv_cesa_ahash_free_cache(struct mv_cesa_ahash_req *creq)
+{
+	if (!creq->cache)
+		return;
+
+	if (creq->req.base.type == CESA_DMA_REQ)
+		mv_cesa_ahash_dma_free_cache(creq);
+	else
+		mv_cesa_ahash_std_free_cache(creq);
+
+	creq->cache = NULL;
+}
+
+static int mv_cesa_ahash_dma_alloc_padding(struct mv_cesa_ahash_dma_req *req,
+					   gfp_t flags)
+{
+	if (req->padding)
+		return 0;
+
+	req->padding = dma_pool_alloc(cesa_dev->dma->padding_pool, flags,
+				      &req->padding_dma);
+	if (!req->padding)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void mv_cesa_ahash_dma_free_padding(struct mv_cesa_ahash_dma_req *req)
+{
+	if (!req->padding)
+		return;
+
+	dma_pool_free(cesa_dev->dma->padding_pool, req->padding,
+		      req->padding_dma);
+	req->padding = NULL;
+}
+
+static inline void mv_cesa_ahash_dma_last_cleanup(struct ahash_request *req)
+{
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+
+	mv_cesa_ahash_dma_free_padding(&creq->req.dma);
+}
+
+static inline void mv_cesa_ahash_dma_cleanup(struct ahash_request *req)
+{
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+
+	dma_unmap_sg(cesa_dev->dev, req->src, creq->src_nents, DMA_TO_DEVICE);
+	mv_cesa_dma_cleanup(&creq->req.dma.base);
+}
+
+static inline void mv_cesa_ahash_cleanup(struct ahash_request *req)
+{
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+
+	if (creq->req.base.type == CESA_DMA_REQ)
+		mv_cesa_ahash_dma_cleanup(req);
+}
+
+static void mv_cesa_ahash_last_cleanup(struct ahash_request *req)
+{
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+
+	mv_cesa_ahash_free_cache(creq);
+
+	if (creq->req.base.type == CESA_DMA_REQ)
+		mv_cesa_ahash_dma_last_cleanup(req);
+}
+
+static int mv_cesa_ahash_pad_len(struct mv_cesa_ahash_req *creq)
+{
+	unsigned int index, padlen;
+
+	index = creq->len & CESA_HASH_BLOCK_SIZE_MSK;
+	padlen = (index < 56) ? (56 - index) : (64 + 56 - index);
+
+	return padlen;
+}
+
+static int mv_cesa_ahash_pad_req(struct mv_cesa_ahash_req *creq, u8 *buf)
+{
+	__be64 bits = cpu_to_be64(creq->len << 3);
+	unsigned int index, padlen;
+
+	buf[0] = 0x80;
+	/* Pad out to 56 mod 64 */
+	index = creq->len & CESA_HASH_BLOCK_SIZE_MSK;
+	padlen = mv_cesa_ahash_pad_len(creq);
+	memset(buf + 1, 0, padlen - 1);
+	memcpy(buf + padlen, &bits, sizeof(bits));
+
+	return padlen + 8;
+}
+
+static void mv_cesa_ahash_std_step(struct ahash_request *req)
+{
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+	struct mv_cesa_ahash_std_req *sreq = &creq->req.std;
+	struct mv_cesa_engine *engine = sreq->base.engine;
+	struct mv_cesa_op_ctx *op;
+	unsigned int new_cache_ptr = 0;
+	u32 frag_mode;
+	size_t  len;
+
+	if (creq->cache_ptr)
+		memcpy(engine->sram + CESA_SA_DATA_SRAM_OFFSET, creq->cache,
+		       creq->cache_ptr);
+
+	len = min_t(size_t, req->nbytes + creq->cache_ptr - sreq->offset,
+		    CESA_SA_SRAM_PAYLOAD_SIZE);
+
+	if (!creq->last_req) {
+		new_cache_ptr = len & CESA_HASH_BLOCK_SIZE_MSK;
+		len &= ~CESA_HASH_BLOCK_SIZE_MSK;
+	}
+
+	if (len - creq->cache_ptr)
+		sreq->offset += sg_pcopy_to_buffer(req->src, creq->src_nents,
+						   engine->sram +
+						   CESA_SA_DATA_SRAM_OFFSET +
+						   creq->cache_ptr,
+						   len - creq->cache_ptr,
+						   sreq->offset);
+
+	op = &creq->op_tmpl;
+
+	frag_mode = mv_cesa_get_op_cfg(op) & CESA_SA_DESC_CFG_FRAG_MSK;
+
+	if (creq->last_req && sreq->offset == req->nbytes &&
+	    creq->len <= CESA_SA_DESC_MAC_SRC_TOTAL_LEN_MAX) {
+		if (frag_mode == CESA_SA_DESC_CFG_FIRST_FRAG)
+			frag_mode = CESA_SA_DESC_CFG_NOT_FRAG;
+		else if (frag_mode == CESA_SA_DESC_CFG_MID_FRAG)
+			frag_mode = CESA_SA_DESC_CFG_LAST_FRAG;
+	}
+
+	if (frag_mode == CESA_SA_DESC_CFG_NOT_FRAG ||
+	    frag_mode == CESA_SA_DESC_CFG_LAST_FRAG) {
+		if (len &&
+		    creq->len <= CESA_SA_DESC_MAC_SRC_TOTAL_LEN_MAX) {
+			mv_cesa_set_mac_op_total_len(op, creq->len);
+		} else {
+			int trailerlen = mv_cesa_ahash_pad_len(creq) + 8;
+
+			if (len + trailerlen > CESA_SA_SRAM_PAYLOAD_SIZE) {
+				len &= CESA_HASH_BLOCK_SIZE_MSK;
+				new_cache_ptr = 64 - trailerlen;
+				memcpy(creq->cache,
+				       engine->sram +
+				       CESA_SA_DATA_SRAM_OFFSET + len,
+				       new_cache_ptr);
+			} else {
+				len += mv_cesa_ahash_pad_req(creq,
+						engine->sram + len +
+						CESA_SA_DATA_SRAM_OFFSET);
+			}
+
+			if (frag_mode == CESA_SA_DESC_CFG_LAST_FRAG)
+				frag_mode = CESA_SA_DESC_CFG_MID_FRAG;
+			else
+				frag_mode = CESA_SA_DESC_CFG_FIRST_FRAG;
+		}
+	}
+
+	mv_cesa_set_mac_op_frag_len(op, len);
+	mv_cesa_update_op_cfg(op, frag_mode, CESA_SA_DESC_CFG_FRAG_MSK);
+
+	/* FIXME: only update enc_len field */
+	memcpy(engine->sram, op, sizeof(*op));
+
+	if (frag_mode == CESA_SA_DESC_CFG_FIRST_FRAG)
+		mv_cesa_update_op_cfg(op, CESA_SA_DESC_CFG_MID_FRAG,
+				      CESA_SA_DESC_CFG_FRAG_MSK);
+
+	creq->cache_ptr = new_cache_ptr;
+
+	mv_cesa_set_int_mask(engine, CESA_SA_INT_ACCEL0_DONE);
+	writel(CESA_SA_CFG_PARA_DIS, engine->regs + CESA_SA_CFG);
+	writel(CESA_SA_CMD_EN_CESA_SA_ACCL0, engine->regs + CESA_SA_CMD);
+}
+
+static int mv_cesa_ahash_std_process(struct ahash_request *req, u32 status)
+{
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+	struct mv_cesa_ahash_std_req *sreq = &creq->req.std;
+
+	if (sreq->offset < (req->nbytes - creq->cache_ptr))
+		return -EINPROGRESS;
+
+	return 0;
+}
+
+static inline void mv_cesa_ahash_dma_prepare(struct ahash_request *req)
+{
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+	struct mv_cesa_tdma_req *dreq = &creq->req.dma.base;
+
+	mv_cesa_dma_prepare(dreq, dreq->base.engine);
+}
+
+static void mv_cesa_ahash_std_prepare(struct ahash_request *req)
+{
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+	struct mv_cesa_ahash_std_req *sreq = &creq->req.std;
+	struct mv_cesa_engine *engine = sreq->base.engine;
+
+	sreq->offset = 0;
+	mv_cesa_adjust_op(engine, &creq->op_tmpl);
+	memcpy(engine->sram, &creq->op_tmpl, sizeof(creq->op_tmpl));
+}
+
+static void mv_cesa_ahash_step(struct crypto_async_request *req)
+{
+	struct ahash_request *ahashreq = ahash_request_cast(req);
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(ahashreq);
+
+	if (creq->req.base.type == CESA_DMA_REQ)
+		mv_cesa_dma_step(&creq->req.dma.base);
+	else
+		mv_cesa_ahash_std_step(ahashreq);
+}
+
+static int mv_cesa_ahash_process(struct crypto_async_request *req, u32 status)
+{
+	struct ahash_request *ahashreq = ahash_request_cast(req);
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(ahashreq);
+	struct mv_cesa_engine *engine = creq->req.base.engine;
+	unsigned int digsize;
+	int ret, i;
+
+	if (creq->req.base.type == CESA_DMA_REQ)
+		ret = mv_cesa_dma_process(&creq->req.dma.base, status);
+	else
+		ret = mv_cesa_ahash_std_process(ahashreq, status);
+
+	if (ret == -EINPROGRESS)
+		return ret;
+
+	digsize = crypto_ahash_digestsize(crypto_ahash_reqtfm(ahashreq));
+	for (i = 0; i < digsize / 4; i++)
+		creq->state[i] = readl(engine->regs + CESA_IVDIG(i));
+
+	if (creq->cache_ptr)
+		sg_pcopy_to_buffer(ahashreq->src, creq->src_nents,
+				   creq->cache,
+				   creq->cache_ptr,
+				   ahashreq->nbytes - creq->cache_ptr);
+
+	if (creq->last_req) {
+		for (i = 0; i < digsize / 4; i++) {
+			/*
+			 * Hardware provides MD5 digest in a different
+			 * endianness than SHA-1 and SHA-256 ones.
+			 */
+			if (digsize == MD5_DIGEST_SIZE)
+				creq->state[i] = cpu_to_le32(creq->state[i]);
+			else
+				creq->state[i] = cpu_to_be32(creq->state[i]);
+		}
+
+		memcpy(ahashreq->result, creq->state, digsize);
+	}
+
+	return ret;
+}
+
+static void mv_cesa_ahash_prepare(struct crypto_async_request *req,
+				  struct mv_cesa_engine *engine)
+{
+	struct ahash_request *ahashreq = ahash_request_cast(req);
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(ahashreq);
+	unsigned int digsize;
+	int i;
+
+	creq->req.base.engine = engine;
+
+	if (creq->req.base.type == CESA_DMA_REQ)
+		mv_cesa_ahash_dma_prepare(ahashreq);
+	else
+		mv_cesa_ahash_std_prepare(ahashreq);
+
+	digsize = crypto_ahash_digestsize(crypto_ahash_reqtfm(ahashreq));
+	for (i = 0; i < digsize / 4; i++)
+		writel(creq->state[i],
+		       engine->regs + CESA_IVDIG(i));
+}
+
+static void mv_cesa_ahash_req_cleanup(struct crypto_async_request *req)
+{
+	struct ahash_request *ahashreq = ahash_request_cast(req);
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(ahashreq);
+
+	if (creq->last_req)
+		mv_cesa_ahash_last_cleanup(ahashreq);
+
+	mv_cesa_ahash_cleanup(ahashreq);
+}
+
+static const struct mv_cesa_req_ops mv_cesa_ahash_req_ops = {
+	.step = mv_cesa_ahash_step,
+	.process = mv_cesa_ahash_process,
+	.prepare = mv_cesa_ahash_prepare,
+	.cleanup = mv_cesa_ahash_req_cleanup,
+};
+
+static int mv_cesa_ahash_init(struct ahash_request *req,
+			      struct mv_cesa_op_ctx *tmpl)
+{
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+
+	memset(creq, 0, sizeof(*creq));
+	mv_cesa_update_op_cfg(tmpl,
+			      CESA_SA_DESC_CFG_OP_MAC_ONLY |
+			      CESA_SA_DESC_CFG_FIRST_FRAG,
+			      CESA_SA_DESC_CFG_OP_MSK |
+			      CESA_SA_DESC_CFG_FRAG_MSK);
+	mv_cesa_set_mac_op_total_len(tmpl, 0);
+	mv_cesa_set_mac_op_frag_len(tmpl, 0);
+	creq->op_tmpl = *tmpl;
+	creq->len = 0;
+
+	return 0;
+}
+
+static inline int mv_cesa_ahash_cra_init(struct crypto_tfm *tfm)
+{
+	struct mv_cesa_hash_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	ctx->base.ops = &mv_cesa_ahash_req_ops;
+
+	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
+				 sizeof(struct mv_cesa_ahash_req));
+	return 0;
+}
+
+static int mv_cesa_ahash_cache_req(struct ahash_request *req, bool *cached)
+{
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+	int ret;
+
+	if (((creq->cache_ptr + req->nbytes) & CESA_HASH_BLOCK_SIZE_MSK) &&
+	    !creq->last_req) {
+		ret = mv_cesa_ahash_alloc_cache(req);
+		if (ret)
+			return ret;
+	}
+
+	if (creq->cache_ptr + req->nbytes < 64 && !creq->last_req) {
+		*cached = true;
+
+		if (!req->nbytes)
+			return 0;
+
+		sg_pcopy_to_buffer(req->src, creq->src_nents,
+				   creq->cache + creq->cache_ptr,
+				   req->nbytes, 0);
+
+		creq->cache_ptr += req->nbytes;
+	}
+
+	return 0;
+}
+
+static struct mv_cesa_op_ctx *
+mv_cesa_ahash_dma_add_cache(struct mv_cesa_tdma_chain *chain,
+			    struct mv_cesa_ahash_dma_iter *dma_iter,
+			    struct mv_cesa_ahash_req *creq,
+			    gfp_t flags)
+{
+	struct mv_cesa_ahash_dma_req *ahashdreq = &creq->req.dma;
+	struct mv_cesa_op_ctx *op = NULL;
+	int ret;
+
+	if (!creq->cache_ptr)
+		return NULL;
+
+	ret = mv_cesa_dma_add_data_transfer(chain,
+					    CESA_SA_DATA_SRAM_OFFSET,
+					    ahashdreq->cache_dma,
+					    creq->cache_ptr,
+					    CESA_TDMA_DST_IN_SRAM,
+					    flags);
+	if (ret)
+		return ERR_PTR(ret);
+
+	if (!dma_iter->base.op_len) {
+		op = mv_cesa_dma_add_op(chain, &creq->op_tmpl, false, flags);
+		if (IS_ERR(op))
+			return op;
+
+		mv_cesa_set_mac_op_frag_len(op, creq->cache_ptr);
+
+		/* Add dummy desc to launch crypto operation */
+		ret = mv_cesa_dma_add_dummy_launch(chain, flags);
+		if (ret)
+			return ERR_PTR(ret);
+	}
+
+	return op;
+}
+
+static struct mv_cesa_op_ctx *
+mv_cesa_ahash_dma_add_data(struct mv_cesa_tdma_chain *chain,
+			   struct mv_cesa_ahash_dma_iter *dma_iter,
+			   struct mv_cesa_ahash_req *creq,
+			   gfp_t flags)
+{
+	struct mv_cesa_op_ctx *op;
+	int ret;
+
+	op = mv_cesa_dma_add_op(chain, &creq->op_tmpl, false, flags);
+	if (IS_ERR(op))
+		return op;
+
+	mv_cesa_set_mac_op_frag_len(op, dma_iter->base.op_len);
+
+	if ((mv_cesa_get_op_cfg(&creq->op_tmpl) & CESA_SA_DESC_CFG_FRAG_MSK) ==
+	    CESA_SA_DESC_CFG_FIRST_FRAG)
+		mv_cesa_update_op_cfg(&creq->op_tmpl,
+				      CESA_SA_DESC_CFG_MID_FRAG,
+				      CESA_SA_DESC_CFG_FRAG_MSK);
+
+	/* Add input transfers */
+	ret = mv_cesa_dma_add_op_transfers(chain, &dma_iter->base,
+					   &dma_iter->src, flags);
+	if (ret)
+		return ERR_PTR(ret);
+
+	/* Add dummy desc to launch crypto operation */
+	ret = mv_cesa_dma_add_dummy_launch(chain, flags);
+	if (ret)
+		return ERR_PTR(ret);
+
+	return op;
+}
+
+static struct mv_cesa_op_ctx *
+mv_cesa_ahash_dma_last_req(struct mv_cesa_tdma_chain *chain,
+			   struct mv_cesa_ahash_dma_iter *dma_iter,
+			   struct mv_cesa_ahash_req *creq,
+			   struct mv_cesa_op_ctx *op,
+			   gfp_t flags)
+{
+	struct mv_cesa_ahash_dma_req *ahashdreq = &creq->req.dma;
+	unsigned int len, trailerlen, padoff = 0;
+	int ret;
+
+	if (!creq->last_req)
+		return op;
+
+	if (op && creq->len <= CESA_SA_DESC_MAC_SRC_TOTAL_LEN_MAX) {
+		u32 frag = CESA_SA_DESC_CFG_NOT_FRAG;
+
+		if ((mv_cesa_get_op_cfg(op) & CESA_SA_DESC_CFG_FRAG_MSK) !=
+		    CESA_SA_DESC_CFG_FIRST_FRAG)
+			frag = CESA_SA_DESC_CFG_LAST_FRAG;
+
+		mv_cesa_update_op_cfg(op, frag, CESA_SA_DESC_CFG_FRAG_MSK);
+
+		return op;
+	}
+
+	ret = mv_cesa_ahash_dma_alloc_padding(ahashdreq, flags);
+	if (ret)
+		return ERR_PTR(ret);
+
+	trailerlen = mv_cesa_ahash_pad_req(creq, ahashdreq->padding);
+
+	if (op) {
+		len = min(CESA_SA_SRAM_PAYLOAD_SIZE - dma_iter->base.op_len,
+			  trailerlen);
+		if (len) {
+			ret = mv_cesa_dma_add_data_transfer(chain,
+						CESA_SA_DATA_SRAM_OFFSET +
+						dma_iter->base.op_len,
+						ahashdreq->padding_dma,
+						len, CESA_TDMA_DST_IN_SRAM,
+						flags);
+			if (ret)
+				return ERR_PTR(ret);
+
+			mv_cesa_update_op_cfg(op, CESA_SA_DESC_CFG_MID_FRAG,
+					      CESA_SA_DESC_CFG_FRAG_MSK);
+			mv_cesa_set_mac_op_frag_len(op,
+					dma_iter->base.op_len + len);
+			padoff += len;
+		}
+	}
+
+	if (padoff >= trailerlen)
+		return op;
+
+	if ((mv_cesa_get_op_cfg(&creq->op_tmpl) & CESA_SA_DESC_CFG_FRAG_MSK) !=
+	    CESA_SA_DESC_CFG_FIRST_FRAG)
+		mv_cesa_update_op_cfg(&creq->op_tmpl,
+				      CESA_SA_DESC_CFG_MID_FRAG,
+				      CESA_SA_DESC_CFG_FRAG_MSK);
+
+	op = mv_cesa_dma_add_op(chain, &creq->op_tmpl, false, flags);
+	if (IS_ERR(op))
+		return op;
+
+	mv_cesa_set_mac_op_frag_len(op, trailerlen - padoff);
+
+	ret = mv_cesa_dma_add_data_transfer(chain,
+					    CESA_SA_DATA_SRAM_OFFSET,
+					    ahashdreq->padding_dma +
+					    padoff,
+					    trailerlen - padoff,
+					    CESA_TDMA_DST_IN_SRAM,
+					    flags);
+	if (ret)
+		return ERR_PTR(ret);
+
+	/* Add dummy desc to launch crypto operation */
+	ret = mv_cesa_dma_add_dummy_launch(chain, flags);
+	if (ret)
+		return ERR_PTR(ret);
+
+	return op;
+}
+
+static int mv_cesa_ahash_dma_req_init(struct ahash_request *req)
+{
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+	gfp_t flags = (req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
+		      GFP_KERNEL : GFP_ATOMIC;
+	struct mv_cesa_ahash_dma_req *ahashdreq = &creq->req.dma;
+	struct mv_cesa_tdma_req *dreq = &ahashdreq->base;
+	struct mv_cesa_tdma_chain chain;
+	struct mv_cesa_ahash_dma_iter iter;
+	struct mv_cesa_op_ctx *op = NULL;
+	int ret;
+
+	dreq->chain.first = NULL;
+	dreq->chain.last = NULL;
+
+	if (creq->src_nents) {
+		ret = dma_map_sg(cesa_dev->dev, req->src, creq->src_nents,
+				 DMA_TO_DEVICE);
+		if (!ret) {
+			ret = -ENOMEM;
+			goto err;
+		}
+	}
+
+	mv_cesa_tdma_desc_iter_init(&chain);
+	mv_cesa_ahash_req_iter_init(&iter, req);
+
+	op = mv_cesa_ahash_dma_add_cache(&chain, &iter,
+					 creq, flags);
+	if (IS_ERR(op)) {
+		ret = PTR_ERR(op);
+		goto err_free_tdma;
+	}
+
+	do {
+		if (!iter.base.op_len)
+			break;
+
+		op = mv_cesa_ahash_dma_add_data(&chain, &iter,
+						creq, flags);
+		if (IS_ERR(op)) {
+			ret = PTR_ERR(op);
+			goto err_free_tdma;
+		}
+	} while (mv_cesa_ahash_req_iter_next_op(&iter));
+
+	op = mv_cesa_ahash_dma_last_req(&chain, &iter, creq, op, flags);
+	if (IS_ERR(op)) {
+		ret = PTR_ERR(op);
+		goto err_free_tdma;
+	}
+
+	if (op) {
+		/* Add dummy desc to wait for crypto operation end */
+		ret = mv_cesa_dma_add_dummy_end(&chain, flags);
+		if (ret)
+			goto err_free_tdma;
+	}
+
+	if (!creq->last_req)
+		creq->cache_ptr = req->nbytes + creq->cache_ptr -
+				  iter.base.len;
+	else
+		creq->cache_ptr = 0;
+
+	dreq->chain = chain;
+
+	return 0;
+
+err_free_tdma:
+	mv_cesa_dma_cleanup(dreq);
+	dma_unmap_sg(cesa_dev->dev, req->src, creq->src_nents, DMA_TO_DEVICE);
+
+err:
+	mv_cesa_ahash_last_cleanup(req);
+
+	return ret;
+}
+
+static int mv_cesa_ahash_req_init(struct ahash_request *req, bool *cached)
+{
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+	int ret;
+
+	if (cesa_dev->caps->has_tdma)
+		creq->req.base.type = CESA_DMA_REQ;
+	else
+		creq->req.base.type = CESA_STD_REQ;
+
+	creq->src_nents = sg_nents_for_len(req->src, req->nbytes);
+
+	ret = mv_cesa_ahash_cache_req(req, cached);
+	if (ret)
+		return ret;
+
+	if (*cached)
+		return 0;
+
+	if (creq->req.base.type == CESA_DMA_REQ)
+		ret = mv_cesa_ahash_dma_req_init(req);
+
+	return ret;
+}
+
+static int mv_cesa_ahash_update(struct ahash_request *req)
+{
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+	bool cached = false;
+	int ret;
+
+	creq->len += req->nbytes;
+	ret = mv_cesa_ahash_req_init(req, &cached);
+	if (ret)
+		return ret;
+
+	if (cached)
+		return 0;
+
+	ret = mv_cesa_queue_req(&req->base);
+	if (ret && ret != -EINPROGRESS) {
+		mv_cesa_ahash_cleanup(req);
+		return ret;
+	}
+
+	return ret;
+}
+
+static int mv_cesa_ahash_final(struct ahash_request *req)
+{
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+	struct mv_cesa_op_ctx *tmpl = &creq->op_tmpl;
+	bool cached = false;
+	int ret;
+
+	mv_cesa_set_mac_op_total_len(tmpl, creq->len);
+	creq->last_req = true;
+	req->nbytes = 0;
+
+	ret = mv_cesa_ahash_req_init(req, &cached);
+	if (ret)
+		return ret;
+
+	if (cached)
+		return 0;
+
+	ret = mv_cesa_queue_req(&req->base);
+	if (ret && ret != -EINPROGRESS)
+		mv_cesa_ahash_cleanup(req);
+
+	return ret;
+}
+
+static int mv_cesa_ahash_finup(struct ahash_request *req)
+{
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+	struct mv_cesa_op_ctx *tmpl = &creq->op_tmpl;
+	bool cached = false;
+	int ret;
+
+	creq->len += req->nbytes;
+	mv_cesa_set_mac_op_total_len(tmpl, creq->len);
+	creq->last_req = true;
+
+	ret = mv_cesa_ahash_req_init(req, &cached);
+	if (ret)
+		return ret;
+
+	if (cached)
+		return 0;
+
+	ret = mv_cesa_queue_req(&req->base);
+	if (ret && ret != -EINPROGRESS)
+		mv_cesa_ahash_cleanup(req);
+
+	return ret;
+}
+
+static int mv_cesa_md5_init(struct ahash_request *req)
+{
+	struct mv_cesa_op_ctx tmpl;
+
+	mv_cesa_set_op_cfg(&tmpl, CESA_SA_DESC_CFG_MACM_MD5);
+
+	mv_cesa_ahash_init(req, &tmpl);
+
+	return 0;
+}
+
+static int mv_cesa_md5_export(struct ahash_request *req, void *out)
+{
+	struct md5_state *out_state = out;
+	struct crypto_ahash *ahash = crypto_ahash_reqtfm(req);
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+	unsigned int digsize = crypto_ahash_digestsize(ahash);
+
+	out_state->byte_count = creq->len;
+	memcpy(out_state->hash, creq->state, digsize);
+	memset(out_state->block, 0, sizeof(out_state->block));
+	if (creq->cache)
+		memcpy(out_state->block, creq->cache, creq->cache_ptr);
+
+	return 0;
+}
+
+static int mv_cesa_md5_import(struct ahash_request *req, const void *in)
+{
+	const struct md5_state *in_state = in;
+	struct crypto_ahash *ahash = crypto_ahash_reqtfm(req);
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+	unsigned int digsize = crypto_ahash_digestsize(ahash);
+	unsigned int cache_ptr;
+	int ret;
+
+	creq->len = in_state->byte_count;
+	memcpy(creq->state, in_state->hash, digsize);
+	creq->cache_ptr = 0;
+
+	cache_ptr = creq->len % sizeof(in_state->block);
+	if (!cache_ptr)
+		return 0;
+
+	ret = mv_cesa_ahash_alloc_cache(req);
+	if (ret)
+		return ret;
+
+	memcpy(creq->cache, in_state->block, cache_ptr);
+	creq->cache_ptr = cache_ptr;
+
+	return 0;
+}
+
+static int mv_cesa_md5_digest(struct ahash_request *req)
+{
+	int ret;
+
+	ret = mv_cesa_md5_init(req);
+	if (ret)
+		return ret;
+
+	return mv_cesa_ahash_finup(req);
+}
+
+struct ahash_alg mv_md5_alg = {
+	.init = mv_cesa_md5_init,
+	.update = mv_cesa_ahash_update,
+	.final = mv_cesa_ahash_final,
+	.finup = mv_cesa_ahash_finup,
+	.digest = mv_cesa_md5_digest,
+	.export = mv_cesa_md5_export,
+	.import = mv_cesa_md5_import,
+	.halg = {
+		.digestsize = MD5_DIGEST_SIZE,
+		.base = {
+			.cra_name = "md5",
+			.cra_driver_name = "mv-md5",
+			.cra_priority = 300,
+			.cra_flags = CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = MD5_HMAC_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct mv_cesa_hash_ctx),
+			.cra_init = mv_cesa_ahash_cra_init,
+			.cra_module = THIS_MODULE,
+		 }
+	}
+};
+
+static int mv_cesa_sha1_init(struct ahash_request *req)
+{
+	struct mv_cesa_op_ctx tmpl;
+
+	mv_cesa_set_op_cfg(&tmpl, CESA_SA_DESC_CFG_MACM_SHA1);
+
+	mv_cesa_ahash_init(req, &tmpl);
+
+	return 0;
+}
+
+static int mv_cesa_sha1_export(struct ahash_request *req, void *out)
+{
+	struct sha1_state *out_state = out;
+	struct crypto_ahash *ahash = crypto_ahash_reqtfm(req);
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+	unsigned int digsize = crypto_ahash_digestsize(ahash);
+
+	out_state->count = creq->len;
+	memcpy(out_state->state, creq->state, digsize);
+	memset(out_state->buffer, 0, sizeof(out_state->buffer));
+	if (creq->cache)
+		memcpy(out_state->buffer, creq->cache, creq->cache_ptr);
+
+	return 0;
+}
+
+static int mv_cesa_sha1_import(struct ahash_request *req, const void *in)
+{
+	const struct sha1_state *in_state = in;
+	struct crypto_ahash *ahash = crypto_ahash_reqtfm(req);
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+	unsigned int digsize = crypto_ahash_digestsize(ahash);
+	unsigned int cache_ptr;
+	int ret;
+
+	creq->len = in_state->count;
+	memcpy(creq->state, in_state->state, digsize);
+	creq->cache_ptr = 0;
+
+	cache_ptr = creq->len % SHA1_BLOCK_SIZE;
+	if (!cache_ptr)
+		return 0;
+
+	ret = mv_cesa_ahash_alloc_cache(req);
+	if (ret)
+		return ret;
+
+	memcpy(creq->cache, in_state->buffer, cache_ptr);
+	creq->cache_ptr = cache_ptr;
+
+	return 0;
+}
+
+static int mv_cesa_sha1_digest(struct ahash_request *req)
+{
+	int ret;
+
+	ret = mv_cesa_sha1_init(req);
+	if (ret)
+		return ret;
+
+	return mv_cesa_ahash_finup(req);
+}
+
+struct ahash_alg mv_sha1_alg = {
+	.init = mv_cesa_sha1_init,
+	.update = mv_cesa_ahash_update,
+	.final = mv_cesa_ahash_final,
+	.finup = mv_cesa_ahash_finup,
+	.digest = mv_cesa_sha1_digest,
+	.export = mv_cesa_sha1_export,
+	.import = mv_cesa_sha1_import,
+	.halg = {
+		.digestsize = SHA1_DIGEST_SIZE,
+		.base = {
+			.cra_name = "sha1",
+			.cra_driver_name = "mv-sha1",
+			.cra_priority = 300,
+			.cra_flags = CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = SHA1_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct mv_cesa_hash_ctx),
+			.cra_init = mv_cesa_ahash_cra_init,
+			.cra_module = THIS_MODULE,
+		 }
+	}
+};
+
+static int mv_cesa_sha256_init(struct ahash_request *req)
+{
+	struct mv_cesa_op_ctx tmpl;
+
+	mv_cesa_set_op_cfg(&tmpl, CESA_SA_DESC_CFG_MACM_SHA256);
+
+	mv_cesa_ahash_init(req, &tmpl);
+
+	return 0;
+}
+
+static int mv_cesa_sha256_digest(struct ahash_request *req)
+{
+	int ret;
+
+	ret = mv_cesa_sha256_init(req);
+	if (ret)
+		return ret;
+
+	return mv_cesa_ahash_finup(req);
+}
+
+static int mv_cesa_sha256_export(struct ahash_request *req, void *out)
+{
+	struct sha256_state *out_state = out;
+	struct crypto_ahash *ahash = crypto_ahash_reqtfm(req);
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+	unsigned int ds = crypto_ahash_digestsize(ahash);
+
+	out_state->count = creq->len;
+	memcpy(out_state->state, creq->state, ds);
+	memset(out_state->buf, 0, sizeof(out_state->buf));
+	if (creq->cache)
+		memcpy(out_state->buf, creq->cache, creq->cache_ptr);
+
+	return 0;
+}
+
+static int mv_cesa_sha256_import(struct ahash_request *req, const void *in)
+{
+	const struct sha256_state *in_state = in;
+	struct crypto_ahash *ahash = crypto_ahash_reqtfm(req);
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+	unsigned int digsize = crypto_ahash_digestsize(ahash);
+	unsigned int cache_ptr;
+	int ret;
+
+	creq->len = in_state->count;
+	memcpy(creq->state, in_state->state, digsize);
+	creq->cache_ptr = 0;
+
+	cache_ptr = creq->len % SHA256_BLOCK_SIZE;
+	if (!cache_ptr)
+		return 0;
+
+	ret = mv_cesa_ahash_alloc_cache(req);
+	if (ret)
+		return ret;
+
+	memcpy(creq->cache, in_state->buf, cache_ptr);
+	creq->cache_ptr = cache_ptr;
+
+	return 0;
+}
+
+struct ahash_alg mv_sha256_alg = {
+	.init = mv_cesa_sha256_init,
+	.update = mv_cesa_ahash_update,
+	.final = mv_cesa_ahash_final,
+	.finup = mv_cesa_ahash_finup,
+	.digest = mv_cesa_sha256_digest,
+	.export = mv_cesa_sha256_export,
+	.import = mv_cesa_sha256_import,
+	.halg = {
+		.digestsize = SHA256_DIGEST_SIZE,
+		.base = {
+			.cra_name = "sha256",
+			.cra_driver_name = "mv-sha256",
+			.cra_priority = 300,
+			.cra_flags = CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = SHA256_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct mv_cesa_hash_ctx),
+			.cra_init = mv_cesa_ahash_cra_init,
+			.cra_module = THIS_MODULE,
+		 }
+	}
+};
+
+struct mv_cesa_ahash_result {
+	struct completion completion;
+	int error;
+};
+
+static void mv_cesa_hmac_ahash_complete(struct crypto_async_request *req,
+					int error)
+{
+	struct mv_cesa_ahash_result *result = req->data;
+
+	if (error == -EINPROGRESS)
+		return;
+
+	result->error = error;
+	complete(&result->completion);
+}
+
+static int mv_cesa_ahmac_iv_state_init(struct ahash_request *req, u8 *pad,
+				       void *state, unsigned int blocksize)
+{
+	struct mv_cesa_ahash_result result;
+	struct scatterlist sg;
+	int ret;
+
+	ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+				   mv_cesa_hmac_ahash_complete, &result);
+	sg_init_one(&sg, pad, blocksize);
+	ahash_request_set_crypt(req, &sg, pad, blocksize);
+	init_completion(&result.completion);
+
+	ret = crypto_ahash_init(req);
+	if (ret)
+		return ret;
+
+	ret = crypto_ahash_update(req);
+	if (ret && ret != -EINPROGRESS)
+		return ret;
+
+	wait_for_completion_interruptible(&result.completion);
+	if (result.error)
+		return result.error;
+
+	ret = crypto_ahash_export(req, state);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int mv_cesa_ahmac_pad_init(struct ahash_request *req,
+				  const u8 *key, unsigned int keylen,
+				  u8 *ipad, u8 *opad,
+				  unsigned int blocksize)
+{
+	struct mv_cesa_ahash_result result;
+	struct scatterlist sg;
+	int ret;
+	int i;
+
+	if (keylen <= blocksize) {
+		memcpy(ipad, key, keylen);
+	} else {
+		u8 *keydup = kmemdup(key, keylen, GFP_KERNEL);
+
+		if (!keydup)
+			return -ENOMEM;
+
+		ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+					   mv_cesa_hmac_ahash_complete,
+					   &result);
+		sg_init_one(&sg, keydup, keylen);
+		ahash_request_set_crypt(req, &sg, ipad, keylen);
+		init_completion(&result.completion);
+
+		ret = crypto_ahash_digest(req);
+		if (ret == -EINPROGRESS) {
+			wait_for_completion_interruptible(&result.completion);
+			ret = result.error;
+		}
+
+		/* Set the memory region to 0 to avoid any leak. */
+		memset(keydup, 0, keylen);
+		kfree(keydup);
+
+		if (ret)
+			return ret;
+
+		keylen = crypto_ahash_digestsize(crypto_ahash_reqtfm(req));
+	}
+
+	memset(ipad + keylen, 0, blocksize - keylen);
+	memcpy(opad, ipad, blocksize);
+
+	for (i = 0; i < blocksize; i++) {
+		ipad[i] ^= 0x36;
+		opad[i] ^= 0x5c;
+	}
+
+	return 0;
+}
+
+static int mv_cesa_ahmac_setkey(const char *hash_alg_name,
+				const u8 *key, unsigned int keylen,
+				void *istate, void *ostate)
+{
+	struct ahash_request *req;
+	struct crypto_ahash *tfm;
+	unsigned int blocksize;
+	u8 *ipad = NULL;
+	u8 *opad;
+	int ret;
+
+	tfm = crypto_alloc_ahash(hash_alg_name, CRYPTO_ALG_TYPE_AHASH,
+				 CRYPTO_ALG_TYPE_AHASH_MASK);
+	if (IS_ERR(tfm))
+		return PTR_ERR(tfm);
+
+	req = ahash_request_alloc(tfm, GFP_KERNEL);
+	if (!req) {
+		ret = -ENOMEM;
+		goto free_ahash;
+	}
+
+	crypto_ahash_clear_flags(tfm, ~0);
+
+	blocksize = crypto_tfm_alg_blocksize(crypto_ahash_tfm(tfm));
+
+	ipad = kzalloc(2 * blocksize, GFP_KERNEL);
+	if (!ipad) {
+		ret = -ENOMEM;
+		goto free_req;
+	}
+
+	opad = ipad + blocksize;
+
+	ret = mv_cesa_ahmac_pad_init(req, key, keylen, ipad, opad, blocksize);
+	if (ret)
+		goto free_ipad;
+
+	ret = mv_cesa_ahmac_iv_state_init(req, ipad, istate, blocksize);
+	if (ret)
+		goto free_ipad;
+
+	ret = mv_cesa_ahmac_iv_state_init(req, opad, ostate, blocksize);
+
+free_ipad:
+	kfree(ipad);
+free_req:
+	ahash_request_free(req);
+free_ahash:
+	crypto_free_ahash(tfm);
+
+	return ret;
+}
+
+static int mv_cesa_ahmac_cra_init(struct crypto_tfm *tfm)
+{
+	struct mv_cesa_hmac_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	ctx->base.ops = &mv_cesa_ahash_req_ops;
+
+	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
+				 sizeof(struct mv_cesa_ahash_req));
+	return 0;
+}
+
+static int mv_cesa_ahmac_md5_init(struct ahash_request *req)
+{
+	struct mv_cesa_hmac_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
+	struct mv_cesa_op_ctx tmpl;
+
+	mv_cesa_set_op_cfg(&tmpl, CESA_SA_DESC_CFG_MACM_HMAC_MD5);
+	memcpy(tmpl.ctx.hash.iv, ctx->iv, sizeof(ctx->iv));
+
+	mv_cesa_ahash_init(req, &tmpl);
+
+	return 0;
+}
+
+static int mv_cesa_ahmac_md5_setkey(struct crypto_ahash *tfm, const u8 *key,
+				    unsigned int keylen)
+{
+	struct mv_cesa_hmac_ctx *ctx = crypto_tfm_ctx(crypto_ahash_tfm(tfm));
+	struct md5_state istate, ostate;
+	int ret, i;
+
+	ret = mv_cesa_ahmac_setkey("mv-md5", key, keylen, &istate, &ostate);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < ARRAY_SIZE(istate.hash); i++)
+		ctx->iv[i] = be32_to_cpu(istate.hash[i]);
+
+	for (i = 0; i < ARRAY_SIZE(ostate.hash); i++)
+		ctx->iv[i + 8] = be32_to_cpu(ostate.hash[i]);
+
+	return 0;
+}
+
+static int mv_cesa_ahmac_md5_digest(struct ahash_request *req)
+{
+	int ret;
+
+	ret = mv_cesa_ahmac_md5_init(req);
+	if (ret)
+		return ret;
+
+	return mv_cesa_ahash_finup(req);
+}
+
+struct ahash_alg mv_ahmac_md5_alg = {
+	.init = mv_cesa_ahmac_md5_init,
+	.update = mv_cesa_ahash_update,
+	.final = mv_cesa_ahash_final,
+	.finup = mv_cesa_ahash_finup,
+	.digest = mv_cesa_ahmac_md5_digest,
+	.setkey = mv_cesa_ahmac_md5_setkey,
+	.export = mv_cesa_md5_export,
+	.import = mv_cesa_md5_import,
+	.halg = {
+		.digestsize = MD5_DIGEST_SIZE,
+		.statesize = sizeof(struct md5_state),
+		.base = {
+			.cra_name = "hmac(md5)",
+			.cra_driver_name = "mv-hmac-md5",
+			.cra_priority = 300,
+			.cra_flags = CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = MD5_HMAC_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct mv_cesa_hmac_ctx),
+			.cra_init = mv_cesa_ahmac_cra_init,
+			.cra_module = THIS_MODULE,
+		 }
+	}
+};
+
+static int mv_cesa_ahmac_sha1_init(struct ahash_request *req)
+{
+	struct mv_cesa_hmac_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
+	struct mv_cesa_op_ctx tmpl;
+
+	mv_cesa_set_op_cfg(&tmpl, CESA_SA_DESC_CFG_MACM_HMAC_SHA1);
+	memcpy(tmpl.ctx.hash.iv, ctx->iv, sizeof(ctx->iv));
+
+	mv_cesa_ahash_init(req, &tmpl);
+
+	return 0;
+}
+
+static int mv_cesa_ahmac_sha1_setkey(struct crypto_ahash *tfm, const u8 *key,
+				     unsigned int keylen)
+{
+	struct mv_cesa_hmac_ctx *ctx = crypto_tfm_ctx(crypto_ahash_tfm(tfm));
+	struct sha1_state istate, ostate;
+	int ret, i;
+
+	ret = mv_cesa_ahmac_setkey("mv-sha1", key, keylen, &istate, &ostate);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < ARRAY_SIZE(istate.state); i++)
+		ctx->iv[i] = be32_to_cpu(istate.state[i]);
+
+	for (i = 0; i < ARRAY_SIZE(ostate.state); i++)
+		ctx->iv[i + 8] = be32_to_cpu(ostate.state[i]);
+
+	return 0;
+}
+
+static int mv_cesa_ahmac_sha1_digest(struct ahash_request *req)
+{
+	int ret;
+
+	ret = mv_cesa_ahmac_sha1_init(req);
+	if (ret)
+		return ret;
+
+	return mv_cesa_ahash_finup(req);
+}
+
+struct ahash_alg mv_ahmac_sha1_alg = {
+	.init = mv_cesa_ahmac_sha1_init,
+	.update = mv_cesa_ahash_update,
+	.final = mv_cesa_ahash_final,
+	.finup = mv_cesa_ahash_finup,
+	.digest = mv_cesa_ahmac_sha1_digest,
+	.setkey = mv_cesa_ahmac_sha1_setkey,
+	.export = mv_cesa_sha1_export,
+	.import = mv_cesa_sha1_import,
+	.halg = {
+		.digestsize = SHA1_DIGEST_SIZE,
+		.statesize = sizeof(struct sha1_state),
+		.base = {
+			.cra_name = "hmac(sha1)",
+			.cra_driver_name = "mv-hmac-sha1",
+			.cra_priority = 300,
+			.cra_flags = CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = SHA1_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct mv_cesa_hmac_ctx),
+			.cra_init = mv_cesa_ahmac_cra_init,
+			.cra_module = THIS_MODULE,
+		 }
+	}
+};
+
+static int mv_cesa_ahmac_sha256_setkey(struct crypto_ahash *tfm, const u8 *key,
+				       unsigned int keylen)
+{
+	struct mv_cesa_hmac_ctx *ctx = crypto_tfm_ctx(crypto_ahash_tfm(tfm));
+	struct sha256_state istate, ostate;
+	int ret, i;
+
+	ret = mv_cesa_ahmac_setkey("mv-sha256", key, keylen, &istate, &ostate);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < ARRAY_SIZE(istate.state); i++)
+		ctx->iv[i] = be32_to_cpu(istate.state[i]);
+
+	for (i = 0; i < ARRAY_SIZE(ostate.state); i++)
+		ctx->iv[i + 8] = be32_to_cpu(ostate.state[i]);
+
+	return 0;
+}
+
+static int mv_cesa_ahmac_sha256_init(struct ahash_request *req)
+{
+	struct mv_cesa_hmac_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
+	struct mv_cesa_op_ctx tmpl;
+
+	mv_cesa_set_op_cfg(&tmpl, CESA_SA_DESC_CFG_MACM_HMAC_SHA256);
+	memcpy(tmpl.ctx.hash.iv, ctx->iv, sizeof(ctx->iv));
+
+	mv_cesa_ahash_init(req, &tmpl);
+
+	return 0;
+}
+
+static int mv_cesa_ahmac_sha256_digest(struct ahash_request *req)
+{
+	int ret;
+
+	ret = mv_cesa_ahmac_sha256_init(req);
+	if (ret)
+		return ret;
+
+	return mv_cesa_ahash_finup(req);
+}
+
+struct ahash_alg mv_ahmac_sha256_alg = {
+	.init = mv_cesa_ahmac_sha256_init,
+	.update = mv_cesa_ahash_update,
+	.final = mv_cesa_ahash_final,
+	.finup = mv_cesa_ahash_finup,
+	.digest = mv_cesa_ahmac_sha256_digest,
+	.setkey = mv_cesa_ahmac_sha256_setkey,
+	.export = mv_cesa_sha256_export,
+	.import = mv_cesa_sha256_import,
+	.halg = {
+		.digestsize = SHA256_DIGEST_SIZE,
+		.statesize = sizeof(struct sha256_state),
+		.base = {
+			.cra_name = "hmac(sha256)",
+			.cra_driver_name = "mv-hmac-sha256",
+			.cra_priority = 300,
+			.cra_flags = CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = SHA256_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct mv_cesa_hmac_ctx),
+			.cra_init = mv_cesa_ahmac_cra_init,
+			.cra_module = THIS_MODULE,
+		 }
+	}
+};
diff --git a/drivers/crypto/marvell/tdma.c b/drivers/crypto/marvell/tdma.c
new file mode 100644
index 000000000000..64a366c50174
--- /dev/null
+++ b/drivers/crypto/marvell/tdma.c
@@ -0,0 +1,224 @@
+/*
+ * Provide TDMA helper functions used by cipher and hash algorithm
+ * implementations.
+ *
+ * Author: Boris Brezillon <boris.brezillon@free-electrons.com>
+ * Author: Arnaud Ebalard <arno@natisbad.org>
+ *
+ * This work is based on an initial version written by
+ * Sebastian Andrzej Siewior < sebastian at breakpoint dot cc >
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#include "cesa.h"
+
+bool mv_cesa_req_dma_iter_next_transfer(struct mv_cesa_dma_iter *iter,
+					struct mv_cesa_sg_dma_iter *sgiter,
+					unsigned int len)
+{
+	if (!sgiter->sg)
+		return false;
+
+	sgiter->op_offset += len;
+	sgiter->offset += len;
+	if (sgiter->offset == sg_dma_len(sgiter->sg)) {
+		if (sg_is_last(sgiter->sg))
+			return false;
+		sgiter->offset = 0;
+		sgiter->sg = sg_next(sgiter->sg);
+	}
+
+	if (sgiter->op_offset == iter->op_len)
+		return false;
+
+	return true;
+}
+
+void mv_cesa_dma_step(struct mv_cesa_tdma_req *dreq)
+{
+	struct mv_cesa_engine *engine = dreq->base.engine;
+
+	writel(0, engine->regs + CESA_SA_CFG);
+
+	mv_cesa_set_int_mask(engine, CESA_SA_INT_ACC0_IDMA_DONE);
+	writel(CESA_TDMA_DST_BURST_128B | CESA_TDMA_SRC_BURST_128B |
+	       CESA_TDMA_NO_BYTE_SWAP | CESA_TDMA_EN,
+	       engine->regs + CESA_TDMA_CONTROL);
+
+	writel(CESA_SA_CFG_ACT_CH0_IDMA | CESA_SA_CFG_MULTI_PKT |
+	       CESA_SA_CFG_CH0_W_IDMA | CESA_SA_CFG_PARA_DIS,
+	       engine->regs + CESA_SA_CFG);
+	writel(dreq->chain.first->cur_dma,
+	       engine->regs + CESA_TDMA_NEXT_ADDR);
+	writel(CESA_SA_CMD_EN_CESA_SA_ACCL0, engine->regs + CESA_SA_CMD);
+}
+
+void mv_cesa_dma_cleanup(struct mv_cesa_tdma_req *dreq)
+{
+	struct mv_cesa_tdma_desc *tdma;
+
+	for (tdma = dreq->chain.first; tdma;) {
+		struct mv_cesa_tdma_desc *old_tdma = tdma;
+
+		if (tdma->flags & CESA_TDMA_OP)
+			dma_pool_free(cesa_dev->dma->op_pool, tdma->op,
+				      le32_to_cpu(tdma->src));
+
+		tdma = tdma->next;
+		dma_pool_free(cesa_dev->dma->tdma_desc_pool, old_tdma,
+			      le32_to_cpu(old_tdma->cur_dma));
+	}
+
+	dreq->chain.first = NULL;
+	dreq->chain.last = NULL;
+}
+
+void mv_cesa_dma_prepare(struct mv_cesa_tdma_req *dreq,
+			 struct mv_cesa_engine *engine)
+{
+	struct mv_cesa_tdma_desc *tdma;
+
+	for (tdma = dreq->chain.first; tdma; tdma = tdma->next) {
+		if (tdma->flags & CESA_TDMA_DST_IN_SRAM)
+			tdma->dst = cpu_to_le32(tdma->dst + engine->sram_dma);
+
+		if (tdma->flags & CESA_TDMA_SRC_IN_SRAM)
+			tdma->src = cpu_to_le32(tdma->src + engine->sram_dma);
+
+		if (tdma->flags & CESA_TDMA_OP)
+			mv_cesa_adjust_op(engine, tdma->op);
+	}
+}
+
+static struct mv_cesa_tdma_desc *
+mv_cesa_dma_add_desc(struct mv_cesa_tdma_chain *chain, gfp_t flags)
+{
+	struct mv_cesa_tdma_desc *new_tdma = NULL;
+	dma_addr_t dma_handle;
+
+	new_tdma = dma_pool_alloc(cesa_dev->dma->tdma_desc_pool, flags,
+				  &dma_handle);
+	if (!new_tdma)
+		return ERR_PTR(-ENOMEM);
+
+	memset(new_tdma, 0, sizeof(*new_tdma));
+	new_tdma->cur_dma = cpu_to_le32(dma_handle);
+	if (chain->last) {
+		chain->last->next_dma = new_tdma->cur_dma;
+		chain->last->next = new_tdma;
+	} else {
+		chain->first = new_tdma;
+	}
+
+	chain->last = new_tdma;
+
+	return new_tdma;
+}
+
+struct mv_cesa_op_ctx *mv_cesa_dma_add_op(struct mv_cesa_tdma_chain *chain,
+					const struct mv_cesa_op_ctx *op_templ,
+					bool skip_ctx,
+					gfp_t flags)
+{
+	struct mv_cesa_tdma_desc *tdma;
+	struct mv_cesa_op_ctx *op;
+	dma_addr_t dma_handle;
+
+	tdma = mv_cesa_dma_add_desc(chain, flags);
+	if (IS_ERR(tdma))
+		return ERR_CAST(tdma);
+
+	op = dma_pool_alloc(cesa_dev->dma->op_pool, flags, &dma_handle);
+	if (!op)
+		return ERR_PTR(-ENOMEM);
+
+	*op = *op_templ;
+
+	tdma = chain->last;
+	tdma->op = op;
+	tdma->byte_cnt = (skip_ctx ? sizeof(op->desc) : sizeof(*op)) | BIT(31);
+	tdma->src = dma_handle;
+	tdma->flags = CESA_TDMA_DST_IN_SRAM | CESA_TDMA_OP;
+
+	return op;
+}
+
+int mv_cesa_dma_add_data_transfer(struct mv_cesa_tdma_chain *chain,
+				  dma_addr_t dst, dma_addr_t src, u32 size,
+				  u32 flags, gfp_t gfp_flags)
+{
+	struct mv_cesa_tdma_desc *tdma;
+
+	tdma = mv_cesa_dma_add_desc(chain, gfp_flags);
+	if (IS_ERR(tdma))
+		return PTR_ERR(tdma);
+
+	tdma->byte_cnt = size | BIT(31);
+	tdma->src = src;
+	tdma->dst = dst;
+
+	flags &= (CESA_TDMA_DST_IN_SRAM | CESA_TDMA_SRC_IN_SRAM);
+	tdma->flags = flags | CESA_TDMA_DATA;
+
+	return 0;
+}
+
+int mv_cesa_dma_add_dummy_launch(struct mv_cesa_tdma_chain *chain,
+				 u32 flags)
+{
+	struct mv_cesa_tdma_desc *tdma;
+
+	tdma = mv_cesa_dma_add_desc(chain, flags);
+	if (IS_ERR(tdma))
+		return PTR_ERR(tdma);
+
+	return 0;
+}
+
+int mv_cesa_dma_add_dummy_end(struct mv_cesa_tdma_chain *chain, u32 flags)
+{
+	struct mv_cesa_tdma_desc *tdma;
+
+	tdma = mv_cesa_dma_add_desc(chain, flags);
+	if (IS_ERR(tdma))
+		return PTR_ERR(tdma);
+
+	tdma->byte_cnt = BIT(31);
+
+	return 0;
+}
+
+int mv_cesa_dma_add_op_transfers(struct mv_cesa_tdma_chain *chain,
+				 struct mv_cesa_dma_iter *dma_iter,
+				 struct mv_cesa_sg_dma_iter *sgiter,
+				 gfp_t gfp_flags)
+{
+	u32 flags = sgiter->dir == DMA_TO_DEVICE ?
+		    CESA_TDMA_DST_IN_SRAM : CESA_TDMA_SRC_IN_SRAM;
+	unsigned int len;
+
+	do {
+		dma_addr_t dst, src;
+		int ret;
+
+		len = mv_cesa_req_dma_iter_transfer_len(dma_iter, sgiter);
+		if (sgiter->dir == DMA_TO_DEVICE) {
+			dst = CESA_SA_DATA_SRAM_OFFSET + sgiter->op_offset;
+			src = sg_dma_address(sgiter->sg) + sgiter->offset;
+		} else {
+			dst = sg_dma_address(sgiter->sg) + sgiter->offset;
+			src = CESA_SA_DATA_SRAM_OFFSET + sgiter->op_offset;
+		}
+
+		ret = mv_cesa_dma_add_data_transfer(chain, dst, src, len,
+						    flags, gfp_flags);
+		if (ret)
+			return ret;
+
+	} while (mv_cesa_req_dma_iter_next_transfer(dma_iter, sgiter, len));
+
+	return 0;
+}
diff --git a/drivers/crypto/mv_cesa.c b/drivers/crypto/mv_cesa.c
index f91f15ddee92..5bcd575fa96f 100644
--- a/drivers/crypto/mv_cesa.c
+++ b/drivers/crypto/mv_cesa.c
@@ -9,6 +9,7 @@
 #include <crypto/aes.h>
 #include <crypto/algapi.h>
 #include <linux/crypto.h>
+#include <linux/genalloc.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/kthread.h>
@@ -29,6 +30,8 @@
 #define MAX_HW_HASH_SIZE	0xFFFF
 #define MV_CESA_EXPIRE		500 /* msec */
 
+#define MV_CESA_DEFAULT_SRAM_SIZE	2048
+
 /*
  * STM:
  *   /---------------------------------------\
@@ -83,6 +86,8 @@ struct req_progress {
 struct crypto_priv {
 	void __iomem *reg;
 	void __iomem *sram;
+	struct gen_pool *sram_pool;
+	dma_addr_t sram_dma;
 	int irq;
 	struct clk *clk;
 	struct task_struct *queue_th;
@@ -595,7 +600,7 @@ static int queue_manag(void *data)
 	cpg->eng_st = ENGINE_IDLE;
 	do {
 		struct crypto_async_request *async_req = NULL;
-		struct crypto_async_request *backlog;
+		struct crypto_async_request *backlog = NULL;
 
 		__set_current_state(TASK_INTERRUPTIBLE);
 
@@ -1019,6 +1024,39 @@ static struct ahash_alg mv_hmac_sha1_alg = {
 		 }
 };
 
+static int mv_cesa_get_sram(struct platform_device *pdev,
+			    struct crypto_priv *cp)
+{
+	struct resource *res;
+	u32 sram_size = MV_CESA_DEFAULT_SRAM_SIZE;
+
+	of_property_read_u32(pdev->dev.of_node, "marvell,crypto-sram-size",
+			     &sram_size);
+
+	cp->sram_size = sram_size;
+	cp->sram_pool = of_get_named_gen_pool(pdev->dev.of_node,
+					      "marvell,crypto-srams", 0);
+	if (cp->sram_pool) {
+		cp->sram = gen_pool_dma_alloc(cp->sram_pool, sram_size,
+					      &cp->sram_dma);
+		if (cp->sram)
+			return 0;
+
+		return -ENOMEM;
+	}
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
+					   "sram");
+	if (!res || resource_size(res) < cp->sram_size)
+		return -EINVAL;
+
+	cp->sram = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(cp->sram))
+		return PTR_ERR(cp->sram);
+
+	return 0;
+}
+
 static int mv_probe(struct platform_device *pdev)
 {
 	struct crypto_priv *cp;
@@ -1041,24 +1079,17 @@ static int mv_probe(struct platform_device *pdev)
 
 	spin_lock_init(&cp->lock);
 	crypto_init_queue(&cp->queue, 50);
-	cp->reg = ioremap(res->start, resource_size(res));
-	if (!cp->reg) {
-		ret = -ENOMEM;
+	cp->reg = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(cp->reg)) {
+		ret = PTR_ERR(cp->reg);
 		goto err;
 	}
 
-	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "sram");
-	if (!res) {
-		ret = -ENXIO;
-		goto err_unmap_reg;
-	}
-	cp->sram_size = resource_size(res);
+	ret = mv_cesa_get_sram(pdev, cp);
+	if (ret)
+		goto err;
+
 	cp->max_req_size = cp->sram_size - SRAM_CFG_SPACE;
-	cp->sram = ioremap(res->start, cp->sram_size);
-	if (!cp->sram) {
-		ret = -ENOMEM;
-		goto err_unmap_reg;
-	}
 
 	if (pdev->dev.of_node)
 		irq = irq_of_parse_and_map(pdev->dev.of_node, 0);
@@ -1066,7 +1097,7 @@ static int mv_probe(struct platform_device *pdev)
 		irq = platform_get_irq(pdev, 0);
 	if (irq < 0 || irq == NO_IRQ) {
 		ret = irq;
-		goto err_unmap_sram;
+		goto err;
 	}
 	cp->irq = irq;
 
@@ -1076,7 +1107,7 @@ static int mv_probe(struct platform_device *pdev)
 	cp->queue_th = kthread_run(queue_manag, cp, "mv_crypto");
 	if (IS_ERR(cp->queue_th)) {
 		ret = PTR_ERR(cp->queue_th);
-		goto err_unmap_sram;
+		goto err;
 	}
 
 	ret = request_irq(irq, crypto_int, 0, dev_name(&pdev->dev),
@@ -1134,10 +1165,6 @@ err_irq:
 	}
 err_thread:
 	kthread_stop(cp->queue_th);
-err_unmap_sram:
-	iounmap(cp->sram);
-err_unmap_reg:
-	iounmap(cp->reg);
 err:
 	kfree(cp);
 	cpg = NULL;
@@ -1157,8 +1184,6 @@ static int mv_remove(struct platform_device *pdev)
 	kthread_stop(cp->queue_th);
 	free_irq(cp->irq, cp);
 	memset(cp->sram, 0, cp->sram_size);
-	iounmap(cp->sram);
-	iounmap(cp->reg);
 
 	if (!IS_ERR(cp->clk)) {
 		clk_disable_unprepare(cp->clk);
@@ -1172,6 +1197,8 @@ static int mv_remove(struct platform_device *pdev)
 
 static const struct of_device_id mv_cesa_of_match_table[] = {
 	{ .compatible = "marvell,orion-crypto", },
+	{ .compatible = "marvell,kirkwood-crypto", },
+	{ .compatible = "marvell,dove-crypto", },
 	{}
 };
 MODULE_DEVICE_TABLE(of, mv_cesa_of_match_table);
diff --git a/drivers/crypto/n2_core.c b/drivers/crypto/n2_core.c
index 10a9aeff1666..2e8dab9d4263 100644
--- a/drivers/crypto/n2_core.c
+++ b/drivers/crypto/n2_core.c
@@ -1281,10 +1281,10 @@ static const char md5_zero[MD5_DIGEST_SIZE] = {
 	0xe9, 0x80, 0x09, 0x98, 0xec, 0xf8, 0x42, 0x7e,
 };
 static const u32 md5_init[MD5_HASH_WORDS] = {
-	cpu_to_le32(0x67452301),
-	cpu_to_le32(0xefcdab89),
-	cpu_to_le32(0x98badcfe),
-	cpu_to_le32(0x10325476),
+	cpu_to_le32(MD5_H0),
+	cpu_to_le32(MD5_H1),
+	cpu_to_le32(MD5_H2),
+	cpu_to_le32(MD5_H3),
 };
 static const char sha1_zero[SHA1_DIGEST_SIZE] = {
 	0xda, 0x39, 0xa3, 0xee, 0x5e, 0x6b, 0x4b, 0x0d, 0x32,
diff --git a/drivers/crypto/nx/Kconfig b/drivers/crypto/nx/Kconfig
index f82616621ae1..e421c96c763a 100644
--- a/drivers/crypto/nx/Kconfig
+++ b/drivers/crypto/nx/Kconfig
@@ -1,26 +1,55 @@
+
 config CRYPTO_DEV_NX_ENCRYPT
-	tristate "Encryption acceleration support"
-	depends on PPC64 && IBMVIO
+	tristate "Encryption acceleration support on pSeries platform"
+	depends on PPC_PSERIES && IBMVIO && !CPU_LITTLE_ENDIAN
 	default y
 	select CRYPTO_AES
-	select CRYPTO_CBC
-	select CRYPTO_ECB
 	select CRYPTO_CCM
-	select CRYPTO_GCM
-	select CRYPTO_AUTHENC
-	select CRYPTO_XCBC
-	select CRYPTO_SHA256
-	select CRYPTO_SHA512
 	help
-	  Support for Power7+ in-Nest encryption acceleration. This
-	  module supports acceleration for AES and SHA2 algorithms. If you
-	  choose 'M' here, this module will be called nx_crypto.
+	  Support for PowerPC Nest (NX) encryption acceleration. This
+	  module supports acceleration for AES and SHA2 algorithms on
+	  the pSeries platform.  If you choose 'M' here, this module
+	  will be called nx_crypto.
 
 config CRYPTO_DEV_NX_COMPRESS
 	tristate "Compression acceleration support"
-	depends on PPC64 && IBMVIO
 	default y
 	help
-	  Support for Power7+ in-Nest compression acceleration. This
-	  module supports acceleration for AES and SHA2 algorithms. If you
-	  choose 'M' here, this module will be called nx_compress.
+	  Support for PowerPC Nest (NX) compression acceleration. This
+	  module supports acceleration for compressing memory with the 842
+	  algorithm.  One of the platform drivers must be selected also.
+	  If you choose 'M' here, this module will be called nx_compress.
+
+if CRYPTO_DEV_NX_COMPRESS
+
+config CRYPTO_DEV_NX_COMPRESS_PSERIES
+	tristate "Compression acceleration support on pSeries platform"
+	depends on PPC_PSERIES && IBMVIO
+	default y
+	help
+	  Support for PowerPC Nest (NX) compression acceleration. This
+	  module supports acceleration for compressing memory with the 842
+	  algorithm.  This supports NX hardware on the pSeries platform.
+	  If you choose 'M' here, this module will be called nx_compress_pseries.
+
+config CRYPTO_DEV_NX_COMPRESS_POWERNV
+	tristate "Compression acceleration support on PowerNV platform"
+	depends on PPC_POWERNV
+	default y
+	help
+	  Support for PowerPC Nest (NX) compression acceleration. This
+	  module supports acceleration for compressing memory with the 842
+	  algorithm.  This supports NX hardware on the PowerNV platform.
+	  If you choose 'M' here, this module will be called nx_compress_powernv.
+
+config CRYPTO_DEV_NX_COMPRESS_CRYPTO
+	tristate "Compression acceleration cryptographic interface"
+	select CRYPTO_ALGAPI
+	select 842_DECOMPRESS
+	default y
+	help
+	  Support for PowerPC Nest (NX) accelerators using the cryptographic
+	  API.  If you choose 'M' here, this module will be called
+	  nx_compress_crypto.
+
+endif
diff --git a/drivers/crypto/nx/Makefile b/drivers/crypto/nx/Makefile
index bb770ea45ce9..e1684f5adb11 100644
--- a/drivers/crypto/nx/Makefile
+++ b/drivers/crypto/nx/Makefile
@@ -10,5 +10,12 @@ nx-crypto-objs := nx.o \
 		  nx-sha256.o \
 		  nx-sha512.o
 
-obj-$(CONFIG_CRYPTO_DEV_NX_COMPRESS) += nx-compress.o
+obj-$(CONFIG_CRYPTO_DEV_NX_COMPRESS) += nx-compress.o nx-compress-platform.o
+obj-$(CONFIG_CRYPTO_DEV_NX_COMPRESS_PSERIES) += nx-compress-pseries.o
+obj-$(CONFIG_CRYPTO_DEV_NX_COMPRESS_POWERNV) += nx-compress-powernv.o
+obj-$(CONFIG_CRYPTO_DEV_NX_COMPRESS_CRYPTO) += nx-compress-crypto.o
 nx-compress-objs := nx-842.o
+nx-compress-platform-objs := nx-842-platform.o
+nx-compress-pseries-objs := nx-842-pseries.o
+nx-compress-powernv-objs := nx-842-powernv.o
+nx-compress-crypto-objs := nx-842-crypto.o
diff --git a/drivers/crypto/nx/nx-842-crypto.c b/drivers/crypto/nx/nx-842-crypto.c
new file mode 100644
index 000000000000..d53a1dcd7b4e
--- /dev/null
+++ b/drivers/crypto/nx/nx-842-crypto.c
@@ -0,0 +1,580 @@
+/*
+ * Cryptographic API for the NX-842 hardware compression.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Copyright (C) IBM Corporation, 2011-2015
+ *
+ * Original Authors: Robert Jennings <rcj@linux.vnet.ibm.com>
+ *                   Seth Jennings <sjenning@linux.vnet.ibm.com>
+ *
+ * Rewrite: Dan Streetman <ddstreet@ieee.org>
+ *
+ * This is an interface to the NX-842 compression hardware in PowerPC
+ * processors.  Most of the complexity of this drvier is due to the fact that
+ * the NX-842 compression hardware requires the input and output data buffers
+ * to be specifically aligned, to be a specific multiple in length, and within
+ * specific minimum and maximum lengths.  Those restrictions, provided by the
+ * nx-842 driver via nx842_constraints, mean this driver must use bounce
+ * buffers and headers to correct misaligned in or out buffers, and to split
+ * input buffers that are too large.
+ *
+ * This driver will fall back to software decompression if the hardware
+ * decompression fails, so this driver's decompression should never fail as
+ * long as the provided compressed buffer is valid.  Any compressed buffer
+ * created by this driver will have a header (except ones where the input
+ * perfectly matches the constraints); so users of this driver cannot simply
+ * pass a compressed buffer created by this driver over to the 842 software
+ * decompression library.  Instead, users must use this driver to decompress;
+ * if the hardware fails or is unavailable, the compressed buffer will be
+ * parsed and the header removed, and the raw 842 buffer(s) passed to the 842
+ * software decompression library.
+ *
+ * This does not fall back to software compression, however, since the caller
+ * of this function is specifically requesting hardware compression; if the
+ * hardware compression fails, the caller can fall back to software
+ * compression, and the raw 842 compressed buffer that the software compressor
+ * creates can be passed to this driver for hardware decompression; any
+ * buffer without our specific header magic is assumed to be a raw 842 buffer
+ * and passed directly to the hardware.  Note that the software compression
+ * library will produce a compressed buffer that is incompatible with the
+ * hardware decompressor if the original input buffer length is not a multiple
+ * of 8; if such a compressed buffer is passed to this driver for
+ * decompression, the hardware will reject it and this driver will then pass
+ * it over to the software library for decompression.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/crypto.h>
+#include <linux/vmalloc.h>
+#include <linux/sw842.h>
+#include <linux/ratelimit.h>
+
+#include "nx-842.h"
+
+/* The first 5 bits of this magic are 0x1f, which is an invalid 842 5-bit
+ * template (see lib/842/842.h), so this magic number will never appear at
+ * the start of a raw 842 compressed buffer.  That is important, as any buffer
+ * passed to us without this magic is assumed to be a raw 842 compressed
+ * buffer, and passed directly to the hardware to decompress.
+ */
+#define NX842_CRYPTO_MAGIC	(0xf842)
+#define NX842_CRYPTO_GROUP_MAX	(0x20)
+#define NX842_CRYPTO_HEADER_SIZE(g)				\
+	(sizeof(struct nx842_crypto_header) +			\
+	 sizeof(struct nx842_crypto_header_group) * (g))
+#define NX842_CRYPTO_HEADER_MAX_SIZE				\
+	NX842_CRYPTO_HEADER_SIZE(NX842_CRYPTO_GROUP_MAX)
+
+/* bounce buffer size */
+#define BOUNCE_BUFFER_ORDER	(2)
+#define BOUNCE_BUFFER_SIZE					\
+	((unsigned int)(PAGE_SIZE << BOUNCE_BUFFER_ORDER))
+
+/* try longer on comp because we can fallback to sw decomp if hw is busy */
+#define COMP_BUSY_TIMEOUT	(250) /* ms */
+#define DECOMP_BUSY_TIMEOUT	(50) /* ms */
+
+struct nx842_crypto_header_group {
+	__be16 padding;			/* unused bytes at start of group */
+	__be32 compressed_length;	/* compressed bytes in group */
+	__be32 uncompressed_length;	/* bytes after decompression */
+} __packed;
+
+struct nx842_crypto_header {
+	__be16 magic;		/* NX842_CRYPTO_MAGIC */
+	__be16 ignore;		/* decompressed end bytes to ignore */
+	u8 groups;		/* total groups in this header */
+	struct nx842_crypto_header_group group[];
+} __packed;
+
+struct nx842_crypto_param {
+	u8 *in;
+	unsigned int iremain;
+	u8 *out;
+	unsigned int oremain;
+	unsigned int ototal;
+};
+
+static int update_param(struct nx842_crypto_param *p,
+			unsigned int slen, unsigned int dlen)
+{
+	if (p->iremain < slen)
+		return -EOVERFLOW;
+	if (p->oremain < dlen)
+		return -ENOSPC;
+
+	p->in += slen;
+	p->iremain -= slen;
+	p->out += dlen;
+	p->oremain -= dlen;
+	p->ototal += dlen;
+
+	return 0;
+}
+
+struct nx842_crypto_ctx {
+	u8 *wmem;
+	u8 *sbounce, *dbounce;
+
+	struct nx842_crypto_header header;
+	struct nx842_crypto_header_group group[NX842_CRYPTO_GROUP_MAX];
+};
+
+static int nx842_crypto_init(struct crypto_tfm *tfm)
+{
+	struct nx842_crypto_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	ctx->wmem = kmalloc(nx842_workmem_size(), GFP_KERNEL);
+	ctx->sbounce = (u8 *)__get_free_pages(GFP_KERNEL, BOUNCE_BUFFER_ORDER);
+	ctx->dbounce = (u8 *)__get_free_pages(GFP_KERNEL, BOUNCE_BUFFER_ORDER);
+	if (!ctx->wmem || !ctx->sbounce || !ctx->dbounce) {
+		kfree(ctx->wmem);
+		free_page((unsigned long)ctx->sbounce);
+		free_page((unsigned long)ctx->dbounce);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void nx842_crypto_exit(struct crypto_tfm *tfm)
+{
+	struct nx842_crypto_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	kfree(ctx->wmem);
+	free_page((unsigned long)ctx->sbounce);
+	free_page((unsigned long)ctx->dbounce);
+}
+
+static int read_constraints(struct nx842_constraints *c)
+{
+	int ret;
+
+	ret = nx842_constraints(c);
+	if (ret) {
+		pr_err_ratelimited("could not get nx842 constraints : %d\n",
+				   ret);
+		return ret;
+	}
+
+	/* limit maximum, to always have enough bounce buffer to decompress */
+	if (c->maximum > BOUNCE_BUFFER_SIZE) {
+		c->maximum = BOUNCE_BUFFER_SIZE;
+		pr_info_once("limiting nx842 maximum to %x\n", c->maximum);
+	}
+
+	return 0;
+}
+
+static int nx842_crypto_add_header(struct nx842_crypto_header *hdr, u8 *buf)
+{
+	int s = NX842_CRYPTO_HEADER_SIZE(hdr->groups);
+
+	/* compress should have added space for header */
+	if (s > be16_to_cpu(hdr->group[0].padding)) {
+		pr_err("Internal error: no space for header\n");
+		return -EINVAL;
+	}
+
+	memcpy(buf, hdr, s);
+
+	print_hex_dump_debug("header ", DUMP_PREFIX_OFFSET, 16, 1, buf, s, 0);
+
+	return 0;
+}
+
+static int compress(struct nx842_crypto_ctx *ctx,
+		    struct nx842_crypto_param *p,
+		    struct nx842_crypto_header_group *g,
+		    struct nx842_constraints *c,
+		    u16 *ignore,
+		    unsigned int hdrsize)
+{
+	unsigned int slen = p->iremain, dlen = p->oremain, tmplen;
+	unsigned int adj_slen = slen;
+	u8 *src = p->in, *dst = p->out;
+	int ret, dskip = 0;
+	ktime_t timeout;
+
+	if (p->iremain == 0)
+		return -EOVERFLOW;
+
+	if (p->oremain == 0 || hdrsize + c->minimum > dlen)
+		return -ENOSPC;
+
+	if (slen % c->multiple)
+		adj_slen = round_up(slen, c->multiple);
+	if (slen < c->minimum)
+		adj_slen = c->minimum;
+	if (slen > c->maximum)
+		adj_slen = slen = c->maximum;
+	if (adj_slen > slen || (u64)src % c->alignment) {
+		adj_slen = min(adj_slen, BOUNCE_BUFFER_SIZE);
+		slen = min(slen, BOUNCE_BUFFER_SIZE);
+		if (adj_slen > slen)
+			memset(ctx->sbounce + slen, 0, adj_slen - slen);
+		memcpy(ctx->sbounce, src, slen);
+		src = ctx->sbounce;
+		slen = adj_slen;
+		pr_debug("using comp sbounce buffer, len %x\n", slen);
+	}
+
+	dst += hdrsize;
+	dlen -= hdrsize;
+
+	if ((u64)dst % c->alignment) {
+		dskip = (int)(PTR_ALIGN(dst, c->alignment) - dst);
+		dst += dskip;
+		dlen -= dskip;
+	}
+	if (dlen % c->multiple)
+		dlen = round_down(dlen, c->multiple);
+	if (dlen < c->minimum) {
+nospc:
+		dst = ctx->dbounce;
+		dlen = min(p->oremain, BOUNCE_BUFFER_SIZE);
+		dlen = round_down(dlen, c->multiple);
+		dskip = 0;
+		pr_debug("using comp dbounce buffer, len %x\n", dlen);
+	}
+	if (dlen > c->maximum)
+		dlen = c->maximum;
+
+	tmplen = dlen;
+	timeout = ktime_add_ms(ktime_get(), COMP_BUSY_TIMEOUT);
+	do {
+		dlen = tmplen; /* reset dlen, if we're retrying */
+		ret = nx842_compress(src, slen, dst, &dlen, ctx->wmem);
+		/* possibly we should reduce the slen here, instead of
+		 * retrying with the dbounce buffer?
+		 */
+		if (ret == -ENOSPC && dst != ctx->dbounce)
+			goto nospc;
+	} while (ret == -EBUSY && ktime_before(ktime_get(), timeout));
+	if (ret)
+		return ret;
+
+	dskip += hdrsize;
+
+	if (dst == ctx->dbounce)
+		memcpy(p->out + dskip, dst, dlen);
+
+	g->padding = cpu_to_be16(dskip);
+	g->compressed_length = cpu_to_be32(dlen);
+	g->uncompressed_length = cpu_to_be32(slen);
+
+	if (p->iremain < slen) {
+		*ignore = slen - p->iremain;
+		slen = p->iremain;
+	}
+
+	pr_debug("compress slen %x ignore %x dlen %x padding %x\n",
+		 slen, *ignore, dlen, dskip);
+
+	return update_param(p, slen, dskip + dlen);
+}
+
+static int nx842_crypto_compress(struct crypto_tfm *tfm,
+				 const u8 *src, unsigned int slen,
+				 u8 *dst, unsigned int *dlen)
+{
+	struct nx842_crypto_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct nx842_crypto_header *hdr = &ctx->header;
+	struct nx842_crypto_param p;
+	struct nx842_constraints c;
+	unsigned int groups, hdrsize, h;
+	int ret, n;
+	bool add_header;
+	u16 ignore = 0;
+
+	p.in = (u8 *)src;
+	p.iremain = slen;
+	p.out = dst;
+	p.oremain = *dlen;
+	p.ototal = 0;
+
+	*dlen = 0;
+
+	ret = read_constraints(&c);
+	if (ret)
+		return ret;
+
+	groups = min_t(unsigned int, NX842_CRYPTO_GROUP_MAX,
+		       DIV_ROUND_UP(p.iremain, c.maximum));
+	hdrsize = NX842_CRYPTO_HEADER_SIZE(groups);
+
+	/* skip adding header if the buffers meet all constraints */
+	add_header = (p.iremain % c.multiple	||
+		      p.iremain < c.minimum	||
+		      p.iremain > c.maximum	||
+		      (u64)p.in % c.alignment	||
+		      p.oremain % c.multiple	||
+		      p.oremain < c.minimum	||
+		      p.oremain > c.maximum	||
+		      (u64)p.out % c.alignment);
+
+	hdr->magic = cpu_to_be16(NX842_CRYPTO_MAGIC);
+	hdr->groups = 0;
+	hdr->ignore = 0;
+
+	while (p.iremain > 0) {
+		n = hdr->groups++;
+		if (hdr->groups > NX842_CRYPTO_GROUP_MAX)
+			return -ENOSPC;
+
+		/* header goes before first group */
+		h = !n && add_header ? hdrsize : 0;
+
+		if (ignore)
+			pr_warn("interal error, ignore is set %x\n", ignore);
+
+		ret = compress(ctx, &p, &hdr->group[n], &c, &ignore, h);
+		if (ret)
+			return ret;
+	}
+
+	if (!add_header && hdr->groups > 1) {
+		pr_err("Internal error: No header but multiple groups\n");
+		return -EINVAL;
+	}
+
+	/* ignore indicates the input stream needed to be padded */
+	hdr->ignore = cpu_to_be16(ignore);
+	if (ignore)
+		pr_debug("marked %d bytes as ignore\n", ignore);
+
+	if (add_header)
+		ret = nx842_crypto_add_header(hdr, dst);
+	if (ret)
+		return ret;
+
+	*dlen = p.ototal;
+
+	pr_debug("compress total slen %x dlen %x\n", slen, *dlen);
+
+	return 0;
+}
+
+static int decompress(struct nx842_crypto_ctx *ctx,
+		      struct nx842_crypto_param *p,
+		      struct nx842_crypto_header_group *g,
+		      struct nx842_constraints *c,
+		      u16 ignore,
+		      bool usehw)
+{
+	unsigned int slen = be32_to_cpu(g->compressed_length);
+	unsigned int required_len = be32_to_cpu(g->uncompressed_length);
+	unsigned int dlen = p->oremain, tmplen;
+	unsigned int adj_slen = slen;
+	u8 *src = p->in, *dst = p->out;
+	u16 padding = be16_to_cpu(g->padding);
+	int ret, spadding = 0, dpadding = 0;
+	ktime_t timeout;
+
+	if (!slen || !required_len)
+		return -EINVAL;
+
+	if (p->iremain <= 0 || padding + slen > p->iremain)
+		return -EOVERFLOW;
+
+	if (p->oremain <= 0 || required_len - ignore > p->oremain)
+		return -ENOSPC;
+
+	src += padding;
+
+	if (!usehw)
+		goto usesw;
+
+	if (slen % c->multiple)
+		adj_slen = round_up(slen, c->multiple);
+	if (slen < c->minimum)
+		adj_slen = c->minimum;
+	if (slen > c->maximum)
+		goto usesw;
+	if (slen < adj_slen || (u64)src % c->alignment) {
+		/* we can append padding bytes because the 842 format defines
+		 * an "end" template (see lib/842/842_decompress.c) and will
+		 * ignore any bytes following it.
+		 */
+		if (slen < adj_slen)
+			memset(ctx->sbounce + slen, 0, adj_slen - slen);
+		memcpy(ctx->sbounce, src, slen);
+		src = ctx->sbounce;
+		spadding = adj_slen - slen;
+		slen = adj_slen;
+		pr_debug("using decomp sbounce buffer, len %x\n", slen);
+	}
+
+	if (dlen % c->multiple)
+		dlen = round_down(dlen, c->multiple);
+	if (dlen < required_len || (u64)dst % c->alignment) {
+		dst = ctx->dbounce;
+		dlen = min(required_len, BOUNCE_BUFFER_SIZE);
+		pr_debug("using decomp dbounce buffer, len %x\n", dlen);
+	}
+	if (dlen < c->minimum)
+		goto usesw;
+	if (dlen > c->maximum)
+		dlen = c->maximum;
+
+	tmplen = dlen;
+	timeout = ktime_add_ms(ktime_get(), DECOMP_BUSY_TIMEOUT);
+	do {
+		dlen = tmplen; /* reset dlen, if we're retrying */
+		ret = nx842_decompress(src, slen, dst, &dlen, ctx->wmem);
+	} while (ret == -EBUSY && ktime_before(ktime_get(), timeout));
+	if (ret) {
+usesw:
+		/* reset everything, sw doesn't have constraints */
+		src = p->in + padding;
+		slen = be32_to_cpu(g->compressed_length);
+		spadding = 0;
+		dst = p->out;
+		dlen = p->oremain;
+		dpadding = 0;
+		if (dlen < required_len) { /* have ignore bytes */
+			dst = ctx->dbounce;
+			dlen = BOUNCE_BUFFER_SIZE;
+		}
+		pr_info_ratelimited("using software 842 decompression\n");
+		ret = sw842_decompress(src, slen, dst, &dlen);
+	}
+	if (ret)
+		return ret;
+
+	slen -= spadding;
+
+	dlen -= ignore;
+	if (ignore)
+		pr_debug("ignoring last %x bytes\n", ignore);
+
+	if (dst == ctx->dbounce)
+		memcpy(p->out, dst, dlen);
+
+	pr_debug("decompress slen %x padding %x dlen %x ignore %x\n",
+		 slen, padding, dlen, ignore);
+
+	return update_param(p, slen + padding, dlen);
+}
+
+static int nx842_crypto_decompress(struct crypto_tfm *tfm,
+				   const u8 *src, unsigned int slen,
+				   u8 *dst, unsigned int *dlen)
+{
+	struct nx842_crypto_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct nx842_crypto_header *hdr;
+	struct nx842_crypto_param p;
+	struct nx842_constraints c;
+	int n, ret, hdr_len;
+	u16 ignore = 0;
+	bool usehw = true;
+
+	p.in = (u8 *)src;
+	p.iremain = slen;
+	p.out = dst;
+	p.oremain = *dlen;
+	p.ototal = 0;
+
+	*dlen = 0;
+
+	if (read_constraints(&c))
+		usehw = false;
+
+	hdr = (struct nx842_crypto_header *)src;
+
+	/* If it doesn't start with our header magic number, assume it's a raw
+	 * 842 compressed buffer and pass it directly to the hardware driver
+	 */
+	if (be16_to_cpu(hdr->magic) != NX842_CRYPTO_MAGIC) {
+		struct nx842_crypto_header_group g = {
+			.padding =		0,
+			.compressed_length =	cpu_to_be32(p.iremain),
+			.uncompressed_length =	cpu_to_be32(p.oremain),
+		};
+
+		ret = decompress(ctx, &p, &g, &c, 0, usehw);
+		if (ret)
+			return ret;
+
+		*dlen = p.ototal;
+
+		return 0;
+	}
+
+	if (!hdr->groups) {
+		pr_err("header has no groups\n");
+		return -EINVAL;
+	}
+	if (hdr->groups > NX842_CRYPTO_GROUP_MAX) {
+		pr_err("header has too many groups %x, max %x\n",
+		       hdr->groups, NX842_CRYPTO_GROUP_MAX);
+		return -EINVAL;
+	}
+
+	hdr_len = NX842_CRYPTO_HEADER_SIZE(hdr->groups);
+	if (hdr_len > slen)
+		return -EOVERFLOW;
+
+	memcpy(&ctx->header, src, hdr_len);
+	hdr = &ctx->header;
+
+	for (n = 0; n < hdr->groups; n++) {
+		/* ignore applies to last group */
+		if (n + 1 == hdr->groups)
+			ignore = be16_to_cpu(hdr->ignore);
+
+		ret = decompress(ctx, &p, &hdr->group[n], &c, ignore, usehw);
+		if (ret)
+			return ret;
+	}
+
+	*dlen = p.ototal;
+
+	pr_debug("decompress total slen %x dlen %x\n", slen, *dlen);
+
+	return 0;
+}
+
+static struct crypto_alg alg = {
+	.cra_name		= "842",
+	.cra_driver_name	= "842-nx",
+	.cra_priority		= 300,
+	.cra_flags		= CRYPTO_ALG_TYPE_COMPRESS,
+	.cra_ctxsize		= sizeof(struct nx842_crypto_ctx),
+	.cra_module		= THIS_MODULE,
+	.cra_init		= nx842_crypto_init,
+	.cra_exit		= nx842_crypto_exit,
+	.cra_u			= { .compress = {
+	.coa_compress		= nx842_crypto_compress,
+	.coa_decompress		= nx842_crypto_decompress } }
+};
+
+static int __init nx842_crypto_mod_init(void)
+{
+	return crypto_register_alg(&alg);
+}
+module_init(nx842_crypto_mod_init);
+
+static void __exit nx842_crypto_mod_exit(void)
+{
+	crypto_unregister_alg(&alg);
+}
+module_exit(nx842_crypto_mod_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("IBM PowerPC Nest (NX) 842 Hardware Compression Interface");
+MODULE_ALIAS_CRYPTO("842");
+MODULE_ALIAS_CRYPTO("842-nx");
+MODULE_AUTHOR("Dan Streetman <ddstreet@ieee.org>");
diff --git a/drivers/crypto/nx/nx-842-platform.c b/drivers/crypto/nx/nx-842-platform.c
new file mode 100644
index 000000000000..664f13dd06ed
--- /dev/null
+++ b/drivers/crypto/nx/nx-842-platform.c
@@ -0,0 +1,84 @@
+
+#include "nx-842.h"
+
+/* this is needed, separate from the main nx-842.c driver, because that main
+ * driver loads the platform drivers during its init(), and it expects one
+ * (or none) of the platform drivers to set this pointer to its driver.
+ * That means this pointer can't be in the main nx-842 driver, because it
+ * wouldn't be accessible until after the main driver loaded, which wouldn't
+ * be possible as it's waiting for the platform driver to load.  So place it
+ * here.
+ */
+static struct nx842_driver *driver;
+static DEFINE_SPINLOCK(driver_lock);
+
+struct nx842_driver *nx842_platform_driver(void)
+{
+	return driver;
+}
+EXPORT_SYMBOL_GPL(nx842_platform_driver);
+
+bool nx842_platform_driver_set(struct nx842_driver *_driver)
+{
+	bool ret = false;
+
+	spin_lock(&driver_lock);
+
+	if (!driver) {
+		driver = _driver;
+		ret = true;
+	} else
+		WARN(1, "can't set platform driver, already set to %s\n",
+		     driver->name);
+
+	spin_unlock(&driver_lock);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nx842_platform_driver_set);
+
+/* only call this from the platform driver exit function */
+void nx842_platform_driver_unset(struct nx842_driver *_driver)
+{
+	spin_lock(&driver_lock);
+
+	if (driver == _driver)
+		driver = NULL;
+	else if (driver)
+		WARN(1, "can't unset platform driver %s, currently set to %s\n",
+		     _driver->name, driver->name);
+	else
+		WARN(1, "can't unset platform driver, already unset\n");
+
+	spin_unlock(&driver_lock);
+}
+EXPORT_SYMBOL_GPL(nx842_platform_driver_unset);
+
+bool nx842_platform_driver_get(void)
+{
+	bool ret = false;
+
+	spin_lock(&driver_lock);
+
+	if (driver)
+		ret = try_module_get(driver->owner);
+
+	spin_unlock(&driver_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nx842_platform_driver_get);
+
+void nx842_platform_driver_put(void)
+{
+	spin_lock(&driver_lock);
+
+	if (driver)
+		module_put(driver->owner);
+
+	spin_unlock(&driver_lock);
+}
+EXPORT_SYMBOL_GPL(nx842_platform_driver_put);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Dan Streetman <ddstreet@ieee.org>");
+MODULE_DESCRIPTION("842 H/W Compression platform driver");
diff --git a/drivers/crypto/nx/nx-842-powernv.c b/drivers/crypto/nx/nx-842-powernv.c
new file mode 100644
index 000000000000..33b3b0abf4ae
--- /dev/null
+++ b/drivers/crypto/nx/nx-842-powernv.c
@@ -0,0 +1,637 @@
+/*
+ * Driver for IBM PowerNV 842 compression accelerator
+ *
+ * Copyright (C) 2015 Dan Streetman, IBM Corp
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include "nx-842.h"
+
+#include <linux/timer.h>
+
+#include <asm/prom.h>
+#include <asm/icswx.h>
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Dan Streetman <ddstreet@ieee.org>");
+MODULE_DESCRIPTION("842 H/W Compression driver for IBM PowerNV processors");
+
+#define WORKMEM_ALIGN	(CRB_ALIGN)
+#define CSB_WAIT_MAX	(5000) /* ms */
+
+struct nx842_workmem {
+	/* Below fields must be properly aligned */
+	struct coprocessor_request_block crb; /* CRB_ALIGN align */
+	struct data_descriptor_entry ddl_in[DDL_LEN_MAX]; /* DDE_ALIGN align */
+	struct data_descriptor_entry ddl_out[DDL_LEN_MAX]; /* DDE_ALIGN align */
+	/* Above fields must be properly aligned */
+
+	ktime_t start;
+
+	char padding[WORKMEM_ALIGN]; /* unused, to allow alignment */
+} __packed __aligned(WORKMEM_ALIGN);
+
+struct nx842_coproc {
+	unsigned int chip_id;
+	unsigned int ct;
+	unsigned int ci;
+	struct list_head list;
+};
+
+/* no cpu hotplug on powernv, so this list never changes after init */
+static LIST_HEAD(nx842_coprocs);
+static unsigned int nx842_ct;
+
+/**
+ * setup_indirect_dde - Setup an indirect DDE
+ *
+ * The DDE is setup with the the DDE count, byte count, and address of
+ * first direct DDE in the list.
+ */
+static void setup_indirect_dde(struct data_descriptor_entry *dde,
+			       struct data_descriptor_entry *ddl,
+			       unsigned int dde_count, unsigned int byte_count)
+{
+	dde->flags = 0;
+	dde->count = dde_count;
+	dde->index = 0;
+	dde->length = cpu_to_be32(byte_count);
+	dde->address = cpu_to_be64(nx842_get_pa(ddl));
+}
+
+/**
+ * setup_direct_dde - Setup single DDE from buffer
+ *
+ * The DDE is setup with the buffer and length.  The buffer must be properly
+ * aligned.  The used length is returned.
+ * Returns:
+ *   N    Successfully set up DDE with N bytes
+ */
+static unsigned int setup_direct_dde(struct data_descriptor_entry *dde,
+				     unsigned long pa, unsigned int len)
+{
+	unsigned int l = min_t(unsigned int, len, LEN_ON_PAGE(pa));
+
+	dde->flags = 0;
+	dde->count = 0;
+	dde->index = 0;
+	dde->length = cpu_to_be32(l);
+	dde->address = cpu_to_be64(pa);
+
+	return l;
+}
+
+/**
+ * setup_ddl - Setup DDL from buffer
+ *
+ * Returns:
+ *   0		Successfully set up DDL
+ */
+static int setup_ddl(struct data_descriptor_entry *dde,
+		     struct data_descriptor_entry *ddl,
+		     unsigned char *buf, unsigned int len,
+		     bool in)
+{
+	unsigned long pa = nx842_get_pa(buf);
+	int i, ret, total_len = len;
+
+	if (!IS_ALIGNED(pa, DDE_BUFFER_ALIGN)) {
+		pr_debug("%s buffer pa 0x%lx not 0x%x-byte aligned\n",
+			 in ? "input" : "output", pa, DDE_BUFFER_ALIGN);
+		return -EINVAL;
+	}
+
+	/* only need to check last mult; since buffer must be
+	 * DDE_BUFFER_ALIGN aligned, and that is a multiple of
+	 * DDE_BUFFER_SIZE_MULT, and pre-last page DDE buffers
+	 * are guaranteed a multiple of DDE_BUFFER_SIZE_MULT.
+	 */
+	if (len % DDE_BUFFER_LAST_MULT) {
+		pr_debug("%s buffer len 0x%x not a multiple of 0x%x\n",
+			 in ? "input" : "output", len, DDE_BUFFER_LAST_MULT);
+		if (in)
+			return -EINVAL;
+		len = round_down(len, DDE_BUFFER_LAST_MULT);
+	}
+
+	/* use a single direct DDE */
+	if (len <= LEN_ON_PAGE(pa)) {
+		ret = setup_direct_dde(dde, pa, len);
+		WARN_ON(ret < len);
+		return 0;
+	}
+
+	/* use the DDL */
+	for (i = 0; i < DDL_LEN_MAX && len > 0; i++) {
+		ret = setup_direct_dde(&ddl[i], pa, len);
+		buf += ret;
+		len -= ret;
+		pa = nx842_get_pa(buf);
+	}
+
+	if (len > 0) {
+		pr_debug("0x%x total %s bytes 0x%x too many for DDL.\n",
+			 total_len, in ? "input" : "output", len);
+		if (in)
+			return -EMSGSIZE;
+		total_len -= len;
+	}
+	setup_indirect_dde(dde, ddl, i, total_len);
+
+	return 0;
+}
+
+#define CSB_ERR(csb, msg, ...)					\
+	pr_err("ERROR: " msg " : %02x %02x %02x %02x %08x\n",	\
+	       ##__VA_ARGS__, (csb)->flags,			\
+	       (csb)->cs, (csb)->cc, (csb)->ce,			\
+	       be32_to_cpu((csb)->count))
+
+#define CSB_ERR_ADDR(csb, msg, ...)				\
+	CSB_ERR(csb, msg " at %lx", ##__VA_ARGS__,		\
+		(unsigned long)be64_to_cpu((csb)->address))
+
+/**
+ * wait_for_csb
+ */
+static int wait_for_csb(struct nx842_workmem *wmem,
+			struct coprocessor_status_block *csb)
+{
+	ktime_t start = wmem->start, now = ktime_get();
+	ktime_t timeout = ktime_add_ms(start, CSB_WAIT_MAX);
+
+	while (!(ACCESS_ONCE(csb->flags) & CSB_V)) {
+		cpu_relax();
+		now = ktime_get();
+		if (ktime_after(now, timeout))
+			break;
+	}
+
+	/* hw has updated csb and output buffer */
+	barrier();
+
+	/* check CSB flags */
+	if (!(csb->flags & CSB_V)) {
+		CSB_ERR(csb, "CSB still not valid after %ld us, giving up",
+			(long)ktime_us_delta(now, start));
+		return -ETIMEDOUT;
+	}
+	if (csb->flags & CSB_F) {
+		CSB_ERR(csb, "Invalid CSB format");
+		return -EPROTO;
+	}
+	if (csb->flags & CSB_CH) {
+		CSB_ERR(csb, "Invalid CSB chaining state");
+		return -EPROTO;
+	}
+
+	/* verify CSB completion sequence is 0 */
+	if (csb->cs) {
+		CSB_ERR(csb, "Invalid CSB completion sequence");
+		return -EPROTO;
+	}
+
+	/* check CSB Completion Code */
+	switch (csb->cc) {
+	/* no error */
+	case CSB_CC_SUCCESS:
+		break;
+	case CSB_CC_TPBC_GT_SPBC:
+		/* not an error, but the compressed data is
+		 * larger than the uncompressed data :(
+		 */
+		break;
+
+	/* input data errors */
+	case CSB_CC_OPERAND_OVERLAP:
+		/* input and output buffers overlap */
+		CSB_ERR(csb, "Operand Overlap error");
+		return -EINVAL;
+	case CSB_CC_INVALID_OPERAND:
+		CSB_ERR(csb, "Invalid operand");
+		return -EINVAL;
+	case CSB_CC_NOSPC:
+		/* output buffer too small */
+		return -ENOSPC;
+	case CSB_CC_ABORT:
+		CSB_ERR(csb, "Function aborted");
+		return -EINTR;
+	case CSB_CC_CRC_MISMATCH:
+		CSB_ERR(csb, "CRC mismatch");
+		return -EINVAL;
+	case CSB_CC_TEMPL_INVALID:
+		CSB_ERR(csb, "Compressed data template invalid");
+		return -EINVAL;
+	case CSB_CC_TEMPL_OVERFLOW:
+		CSB_ERR(csb, "Compressed data template shows data past end");
+		return -EINVAL;
+
+	/* these should not happen */
+	case CSB_CC_INVALID_ALIGN:
+		/* setup_ddl should have detected this */
+		CSB_ERR_ADDR(csb, "Invalid alignment");
+		return -EINVAL;
+	case CSB_CC_DATA_LENGTH:
+		/* setup_ddl should have detected this */
+		CSB_ERR(csb, "Invalid data length");
+		return -EINVAL;
+	case CSB_CC_WR_TRANSLATION:
+	case CSB_CC_TRANSLATION:
+	case CSB_CC_TRANSLATION_DUP1:
+	case CSB_CC_TRANSLATION_DUP2:
+	case CSB_CC_TRANSLATION_DUP3:
+	case CSB_CC_TRANSLATION_DUP4:
+	case CSB_CC_TRANSLATION_DUP5:
+	case CSB_CC_TRANSLATION_DUP6:
+		/* should not happen, we use physical addrs */
+		CSB_ERR_ADDR(csb, "Translation error");
+		return -EPROTO;
+	case CSB_CC_WR_PROTECTION:
+	case CSB_CC_PROTECTION:
+	case CSB_CC_PROTECTION_DUP1:
+	case CSB_CC_PROTECTION_DUP2:
+	case CSB_CC_PROTECTION_DUP3:
+	case CSB_CC_PROTECTION_DUP4:
+	case CSB_CC_PROTECTION_DUP5:
+	case CSB_CC_PROTECTION_DUP6:
+		/* should not happen, we use physical addrs */
+		CSB_ERR_ADDR(csb, "Protection error");
+		return -EPROTO;
+	case CSB_CC_PRIVILEGE:
+		/* shouldn't happen, we're in HYP mode */
+		CSB_ERR(csb, "Insufficient Privilege error");
+		return -EPROTO;
+	case CSB_CC_EXCESSIVE_DDE:
+		/* shouldn't happen, setup_ddl doesn't use many dde's */
+		CSB_ERR(csb, "Too many DDEs in DDL");
+		return -EINVAL;
+	case CSB_CC_TRANSPORT:
+		/* shouldn't happen, we setup CRB correctly */
+		CSB_ERR(csb, "Invalid CRB");
+		return -EINVAL;
+	case CSB_CC_SEGMENTED_DDL:
+		/* shouldn't happen, setup_ddl creates DDL right */
+		CSB_ERR(csb, "Segmented DDL error");
+		return -EINVAL;
+	case CSB_CC_DDE_OVERFLOW:
+		/* shouldn't happen, setup_ddl creates DDL right */
+		CSB_ERR(csb, "DDE overflow error");
+		return -EINVAL;
+	case CSB_CC_SESSION:
+		/* should not happen with ICSWX */
+		CSB_ERR(csb, "Session violation error");
+		return -EPROTO;
+	case CSB_CC_CHAIN:
+		/* should not happen, we don't use chained CRBs */
+		CSB_ERR(csb, "Chained CRB error");
+		return -EPROTO;
+	case CSB_CC_SEQUENCE:
+		/* should not happen, we don't use chained CRBs */
+		CSB_ERR(csb, "CRB seqeunce number error");
+		return -EPROTO;
+	case CSB_CC_UNKNOWN_CODE:
+		CSB_ERR(csb, "Unknown subfunction code");
+		return -EPROTO;
+
+	/* hardware errors */
+	case CSB_CC_RD_EXTERNAL:
+	case CSB_CC_RD_EXTERNAL_DUP1:
+	case CSB_CC_RD_EXTERNAL_DUP2:
+	case CSB_CC_RD_EXTERNAL_DUP3:
+		CSB_ERR_ADDR(csb, "Read error outside coprocessor");
+		return -EPROTO;
+	case CSB_CC_WR_EXTERNAL:
+		CSB_ERR_ADDR(csb, "Write error outside coprocessor");
+		return -EPROTO;
+	case CSB_CC_INTERNAL:
+		CSB_ERR(csb, "Internal error in coprocessor");
+		return -EPROTO;
+	case CSB_CC_PROVISION:
+		CSB_ERR(csb, "Storage provision error");
+		return -EPROTO;
+	case CSB_CC_HW:
+		CSB_ERR(csb, "Correctable hardware error");
+		return -EPROTO;
+
+	default:
+		CSB_ERR(csb, "Invalid CC %d", csb->cc);
+		return -EPROTO;
+	}
+
+	/* check Completion Extension state */
+	if (csb->ce & CSB_CE_TERMINATION) {
+		CSB_ERR(csb, "CSB request was terminated");
+		return -EPROTO;
+	}
+	if (csb->ce & CSB_CE_INCOMPLETE) {
+		CSB_ERR(csb, "CSB request not complete");
+		return -EPROTO;
+	}
+	if (!(csb->ce & CSB_CE_TPBC)) {
+		CSB_ERR(csb, "TPBC not provided, unknown target length");
+		return -EPROTO;
+	}
+
+	/* successful completion */
+	pr_debug_ratelimited("Processed %u bytes in %lu us\n", csb->count,
+			     (unsigned long)ktime_us_delta(now, start));
+
+	return 0;
+}
+
+/**
+ * nx842_powernv_function - compress/decompress data using the 842 algorithm
+ *
+ * (De)compression provided by the NX842 coprocessor on IBM PowerNV systems.
+ * This compresses or decompresses the provided input buffer into the provided
+ * output buffer.
+ *
+ * Upon return from this function @outlen contains the length of the
+ * output data.  If there is an error then @outlen will be 0 and an
+ * error will be specified by the return code from this function.
+ *
+ * The @workmem buffer should only be used by one function call at a time.
+ *
+ * @in: input buffer pointer
+ * @inlen: input buffer size
+ * @out: output buffer pointer
+ * @outlenp: output buffer size pointer
+ * @workmem: working memory buffer pointer, size determined by
+ *           nx842_powernv_driver.workmem_size
+ * @fc: function code, see CCW Function Codes in nx-842.h
+ *
+ * Returns:
+ *   0		Success, output of length @outlenp stored in the buffer at @out
+ *   -ENODEV	Hardware unavailable
+ *   -ENOSPC	Output buffer is to small
+ *   -EMSGSIZE	Input buffer too large
+ *   -EINVAL	buffer constraints do not fix nx842_constraints
+ *   -EPROTO	hardware error during operation
+ *   -ETIMEDOUT	hardware did not complete operation in reasonable time
+ *   -EINTR	operation was aborted
+ */
+static int nx842_powernv_function(const unsigned char *in, unsigned int inlen,
+				  unsigned char *out, unsigned int *outlenp,
+				  void *workmem, int fc)
+{
+	struct coprocessor_request_block *crb;
+	struct coprocessor_status_block *csb;
+	struct nx842_workmem *wmem;
+	int ret;
+	u64 csb_addr;
+	u32 ccw;
+	unsigned int outlen = *outlenp;
+
+	wmem = PTR_ALIGN(workmem, WORKMEM_ALIGN);
+
+	*outlenp = 0;
+
+	/* shoudn't happen, we don't load without a coproc */
+	if (!nx842_ct) {
+		pr_err_ratelimited("coprocessor CT is 0");
+		return -ENODEV;
+	}
+
+	crb = &wmem->crb;
+	csb = &crb->csb;
+
+	/* Clear any previous values */
+	memset(crb, 0, sizeof(*crb));
+
+	/* set up DDLs */
+	ret = setup_ddl(&crb->source, wmem->ddl_in,
+			(unsigned char *)in, inlen, true);
+	if (ret)
+		return ret;
+	ret = setup_ddl(&crb->target, wmem->ddl_out,
+			out, outlen, false);
+	if (ret)
+		return ret;
+
+	/* set up CCW */
+	ccw = 0;
+	ccw = SET_FIELD(ccw, CCW_CT, nx842_ct);
+	ccw = SET_FIELD(ccw, CCW_CI_842, 0); /* use 0 for hw auto-selection */
+	ccw = SET_FIELD(ccw, CCW_FC_842, fc);
+
+	/* set up CRB's CSB addr */
+	csb_addr = nx842_get_pa(csb) & CRB_CSB_ADDRESS;
+	csb_addr |= CRB_CSB_AT; /* Addrs are phys */
+	crb->csb_addr = cpu_to_be64(csb_addr);
+
+	wmem->start = ktime_get();
+
+	/* do ICSWX */
+	ret = icswx(cpu_to_be32(ccw), crb);
+
+	pr_debug_ratelimited("icswx CR %x ccw %x crb->ccw %x\n", ret,
+			     (unsigned int)ccw,
+			     (unsigned int)be32_to_cpu(crb->ccw));
+
+	switch (ret) {
+	case ICSWX_INITIATED:
+		ret = wait_for_csb(wmem, csb);
+		break;
+	case ICSWX_BUSY:
+		pr_debug_ratelimited("842 Coprocessor busy\n");
+		ret = -EBUSY;
+		break;
+	case ICSWX_REJECTED:
+		pr_err_ratelimited("ICSWX rejected\n");
+		ret = -EPROTO;
+		break;
+	default:
+		pr_err_ratelimited("Invalid ICSWX return code %x\n", ret);
+		ret = -EPROTO;
+		break;
+	}
+
+	if (!ret)
+		*outlenp = be32_to_cpu(csb->count);
+
+	return ret;
+}
+
+/**
+ * nx842_powernv_compress - Compress data using the 842 algorithm
+ *
+ * Compression provided by the NX842 coprocessor on IBM PowerNV systems.
+ * The input buffer is compressed and the result is stored in the
+ * provided output buffer.
+ *
+ * Upon return from this function @outlen contains the length of the
+ * compressed data.  If there is an error then @outlen will be 0 and an
+ * error will be specified by the return code from this function.
+ *
+ * @in: input buffer pointer
+ * @inlen: input buffer size
+ * @out: output buffer pointer
+ * @outlenp: output buffer size pointer
+ * @workmem: working memory buffer pointer, size determined by
+ *           nx842_powernv_driver.workmem_size
+ *
+ * Returns: see @nx842_powernv_function()
+ */
+static int nx842_powernv_compress(const unsigned char *in, unsigned int inlen,
+				  unsigned char *out, unsigned int *outlenp,
+				  void *wmem)
+{
+	return nx842_powernv_function(in, inlen, out, outlenp,
+				      wmem, CCW_FC_842_COMP_NOCRC);
+}
+
+/**
+ * nx842_powernv_decompress - Decompress data using the 842 algorithm
+ *
+ * Decompression provided by the NX842 coprocessor on IBM PowerNV systems.
+ * The input buffer is decompressed and the result is stored in the
+ * provided output buffer.
+ *
+ * Upon return from this function @outlen contains the length of the
+ * decompressed data.  If there is an error then @outlen will be 0 and an
+ * error will be specified by the return code from this function.
+ *
+ * @in: input buffer pointer
+ * @inlen: input buffer size
+ * @out: output buffer pointer
+ * @outlenp: output buffer size pointer
+ * @workmem: working memory buffer pointer, size determined by
+ *           nx842_powernv_driver.workmem_size
+ *
+ * Returns: see @nx842_powernv_function()
+ */
+static int nx842_powernv_decompress(const unsigned char *in, unsigned int inlen,
+				    unsigned char *out, unsigned int *outlenp,
+				    void *wmem)
+{
+	return nx842_powernv_function(in, inlen, out, outlenp,
+				      wmem, CCW_FC_842_DECOMP_NOCRC);
+}
+
+static int __init nx842_powernv_probe(struct device_node *dn)
+{
+	struct nx842_coproc *coproc;
+	struct property *ct_prop, *ci_prop;
+	unsigned int ct, ci;
+	int chip_id;
+
+	chip_id = of_get_ibm_chip_id(dn);
+	if (chip_id < 0) {
+		pr_err("ibm,chip-id missing\n");
+		return -EINVAL;
+	}
+	ct_prop = of_find_property(dn, "ibm,842-coprocessor-type", NULL);
+	if (!ct_prop) {
+		pr_err("ibm,842-coprocessor-type missing\n");
+		return -EINVAL;
+	}
+	ct = be32_to_cpu(*(unsigned int *)ct_prop->value);
+	ci_prop = of_find_property(dn, "ibm,842-coprocessor-instance", NULL);
+	if (!ci_prop) {
+		pr_err("ibm,842-coprocessor-instance missing\n");
+		return -EINVAL;
+	}
+	ci = be32_to_cpu(*(unsigned int *)ci_prop->value);
+
+	coproc = kmalloc(sizeof(*coproc), GFP_KERNEL);
+	if (!coproc)
+		return -ENOMEM;
+
+	coproc->chip_id = chip_id;
+	coproc->ct = ct;
+	coproc->ci = ci;
+	INIT_LIST_HEAD(&coproc->list);
+	list_add(&coproc->list, &nx842_coprocs);
+
+	pr_info("coprocessor found on chip %d, CT %d CI %d\n", chip_id, ct, ci);
+
+	if (!nx842_ct)
+		nx842_ct = ct;
+	else if (nx842_ct != ct)
+		pr_err("NX842 chip %d, CT %d != first found CT %d\n",
+		       chip_id, ct, nx842_ct);
+
+	return 0;
+}
+
+static struct nx842_constraints nx842_powernv_constraints = {
+	.alignment =	DDE_BUFFER_ALIGN,
+	.multiple =	DDE_BUFFER_LAST_MULT,
+	.minimum =	DDE_BUFFER_LAST_MULT,
+	.maximum =	(DDL_LEN_MAX - 1) * PAGE_SIZE,
+};
+
+static struct nx842_driver nx842_powernv_driver = {
+	.name =		KBUILD_MODNAME,
+	.owner =	THIS_MODULE,
+	.workmem_size =	sizeof(struct nx842_workmem),
+	.constraints =	&nx842_powernv_constraints,
+	.compress =	nx842_powernv_compress,
+	.decompress =	nx842_powernv_decompress,
+};
+
+static __init int nx842_powernv_init(void)
+{
+	struct device_node *dn;
+
+	/* verify workmem size/align restrictions */
+	BUILD_BUG_ON(WORKMEM_ALIGN % CRB_ALIGN);
+	BUILD_BUG_ON(CRB_ALIGN % DDE_ALIGN);
+	BUILD_BUG_ON(CRB_SIZE % DDE_ALIGN);
+	/* verify buffer size/align restrictions */
+	BUILD_BUG_ON(PAGE_SIZE % DDE_BUFFER_ALIGN);
+	BUILD_BUG_ON(DDE_BUFFER_ALIGN % DDE_BUFFER_SIZE_MULT);
+	BUILD_BUG_ON(DDE_BUFFER_SIZE_MULT % DDE_BUFFER_LAST_MULT);
+
+	pr_info("loading\n");
+
+	for_each_compatible_node(dn, NULL, "ibm,power-nx")
+		nx842_powernv_probe(dn);
+
+	if (!nx842_ct) {
+		pr_err("no coprocessors found\n");
+		return -ENODEV;
+	}
+
+	if (!nx842_platform_driver_set(&nx842_powernv_driver)) {
+		struct nx842_coproc *coproc, *n;
+
+		list_for_each_entry_safe(coproc, n, &nx842_coprocs, list) {
+			list_del(&coproc->list);
+			kfree(coproc);
+		}
+
+		return -EEXIST;
+	}
+
+	pr_info("loaded\n");
+
+	return 0;
+}
+module_init(nx842_powernv_init);
+
+static void __exit nx842_powernv_exit(void)
+{
+	struct nx842_coproc *coproc, *n;
+
+	nx842_platform_driver_unset(&nx842_powernv_driver);
+
+	list_for_each_entry_safe(coproc, n, &nx842_coprocs, list) {
+		list_del(&coproc->list);
+		kfree(coproc);
+	}
+
+	pr_info("unloaded\n");
+}
+module_exit(nx842_powernv_exit);
diff --git a/drivers/crypto/nx/nx-842-pseries.c b/drivers/crypto/nx/nx-842-pseries.c
new file mode 100644
index 000000000000..3040a6091bf2
--- /dev/null
+++ b/drivers/crypto/nx/nx-842-pseries.c
@@ -0,0 +1,1140 @@
+/*
+ * Driver for IBM Power 842 compression accelerator
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ *
+ * Copyright (C) IBM Corporation, 2012
+ *
+ * Authors: Robert Jennings <rcj@linux.vnet.ibm.com>
+ *          Seth Jennings <sjenning@linux.vnet.ibm.com>
+ */
+
+#include <asm/vio.h>
+
+#include "nx-842.h"
+#include "nx_csbcpb.h" /* struct nx_csbcpb */
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Robert Jennings <rcj@linux.vnet.ibm.com>");
+MODULE_DESCRIPTION("842 H/W Compression driver for IBM Power processors");
+
+static struct nx842_constraints nx842_pseries_constraints = {
+	.alignment =	DDE_BUFFER_ALIGN,
+	.multiple =	DDE_BUFFER_LAST_MULT,
+	.minimum =	DDE_BUFFER_LAST_MULT,
+	.maximum =	PAGE_SIZE, /* dynamic, max_sync_size */
+};
+
+static int check_constraints(unsigned long buf, unsigned int *len, bool in)
+{
+	if (!IS_ALIGNED(buf, nx842_pseries_constraints.alignment)) {
+		pr_debug("%s buffer 0x%lx not aligned to 0x%x\n",
+			 in ? "input" : "output", buf,
+			 nx842_pseries_constraints.alignment);
+		return -EINVAL;
+	}
+	if (*len % nx842_pseries_constraints.multiple) {
+		pr_debug("%s buffer len 0x%x not multiple of 0x%x\n",
+			 in ? "input" : "output", *len,
+			 nx842_pseries_constraints.multiple);
+		if (in)
+			return -EINVAL;
+		*len = round_down(*len, nx842_pseries_constraints.multiple);
+	}
+	if (*len < nx842_pseries_constraints.minimum) {
+		pr_debug("%s buffer len 0x%x under minimum 0x%x\n",
+			 in ? "input" : "output", *len,
+			 nx842_pseries_constraints.minimum);
+		return -EINVAL;
+	}
+	if (*len > nx842_pseries_constraints.maximum) {
+		pr_debug("%s buffer len 0x%x over maximum 0x%x\n",
+			 in ? "input" : "output", *len,
+			 nx842_pseries_constraints.maximum);
+		if (in)
+			return -EINVAL;
+		*len = nx842_pseries_constraints.maximum;
+	}
+	return 0;
+}
+
+/* I assume we need to align the CSB? */
+#define WORKMEM_ALIGN	(256)
+
+struct nx842_workmem {
+	/* scatterlist */
+	char slin[4096];
+	char slout[4096];
+	/* coprocessor status/parameter block */
+	struct nx_csbcpb csbcpb;
+
+	char padding[WORKMEM_ALIGN];
+} __aligned(WORKMEM_ALIGN);
+
+/* Macros for fields within nx_csbcpb */
+/* Check the valid bit within the csbcpb valid field */
+#define NX842_CSBCBP_VALID_CHK(x) (x & BIT_MASK(7))
+
+/* CE macros operate on the completion_extension field bits in the csbcpb.
+ * CE0 0=full completion, 1=partial completion
+ * CE1 0=CE0 indicates completion, 1=termination (output may be modified)
+ * CE2 0=processed_bytes is source bytes, 1=processed_bytes is target bytes */
+#define NX842_CSBCPB_CE0(x)	(x & BIT_MASK(7))
+#define NX842_CSBCPB_CE1(x)	(x & BIT_MASK(6))
+#define NX842_CSBCPB_CE2(x)	(x & BIT_MASK(5))
+
+/* The NX unit accepts data only on 4K page boundaries */
+#define NX842_HW_PAGE_SIZE	(4096)
+#define NX842_HW_PAGE_MASK	(~(NX842_HW_PAGE_SIZE-1))
+
+enum nx842_status {
+	UNAVAILABLE,
+	AVAILABLE
+};
+
+struct ibm_nx842_counters {
+	atomic64_t comp_complete;
+	atomic64_t comp_failed;
+	atomic64_t decomp_complete;
+	atomic64_t decomp_failed;
+	atomic64_t swdecomp;
+	atomic64_t comp_times[32];
+	atomic64_t decomp_times[32];
+};
+
+static struct nx842_devdata {
+	struct vio_dev *vdev;
+	struct device *dev;
+	struct ibm_nx842_counters *counters;
+	unsigned int max_sg_len;
+	unsigned int max_sync_size;
+	unsigned int max_sync_sg;
+	enum nx842_status status;
+} __rcu *devdata;
+static DEFINE_SPINLOCK(devdata_mutex);
+
+#define NX842_COUNTER_INC(_x) \
+static inline void nx842_inc_##_x( \
+	const struct nx842_devdata *dev) { \
+	if (dev) \
+		atomic64_inc(&dev->counters->_x); \
+}
+NX842_COUNTER_INC(comp_complete);
+NX842_COUNTER_INC(comp_failed);
+NX842_COUNTER_INC(decomp_complete);
+NX842_COUNTER_INC(decomp_failed);
+NX842_COUNTER_INC(swdecomp);
+
+#define NX842_HIST_SLOTS 16
+
+static void ibm_nx842_incr_hist(atomic64_t *times, unsigned int time)
+{
+	int bucket = fls(time);
+
+	if (bucket)
+		bucket = min((NX842_HIST_SLOTS - 1), bucket - 1);
+
+	atomic64_inc(&times[bucket]);
+}
+
+/* NX unit operation flags */
+#define NX842_OP_COMPRESS	0x0
+#define NX842_OP_CRC		0x1
+#define NX842_OP_DECOMPRESS	0x2
+#define NX842_OP_COMPRESS_CRC   (NX842_OP_COMPRESS | NX842_OP_CRC)
+#define NX842_OP_DECOMPRESS_CRC (NX842_OP_DECOMPRESS | NX842_OP_CRC)
+#define NX842_OP_ASYNC		(1<<23)
+#define NX842_OP_NOTIFY		(1<<22)
+#define NX842_OP_NOTIFY_INT(x)	((x & 0xff)<<8)
+
+static unsigned long nx842_get_desired_dma(struct vio_dev *viodev)
+{
+	/* No use of DMA mappings within the driver. */
+	return 0;
+}
+
+struct nx842_slentry {
+	__be64 ptr; /* Real address (use __pa()) */
+	__be64 len;
+};
+
+/* pHyp scatterlist entry */
+struct nx842_scatterlist {
+	int entry_nr; /* number of slentries */
+	struct nx842_slentry *entries; /* ptr to array of slentries */
+};
+
+/* Does not include sizeof(entry_nr) in the size */
+static inline unsigned long nx842_get_scatterlist_size(
+				struct nx842_scatterlist *sl)
+{
+	return sl->entry_nr * sizeof(struct nx842_slentry);
+}
+
+static int nx842_build_scatterlist(unsigned long buf, int len,
+			struct nx842_scatterlist *sl)
+{
+	unsigned long entrylen;
+	struct nx842_slentry *entry;
+
+	sl->entry_nr = 0;
+
+	entry = sl->entries;
+	while (len) {
+		entry->ptr = cpu_to_be64(nx842_get_pa((void *)buf));
+		entrylen = min_t(int, len,
+				 LEN_ON_SIZE(buf, NX842_HW_PAGE_SIZE));
+		entry->len = cpu_to_be64(entrylen);
+
+		len -= entrylen;
+		buf += entrylen;
+
+		sl->entry_nr++;
+		entry++;
+	}
+
+	return 0;
+}
+
+static int nx842_validate_result(struct device *dev,
+	struct cop_status_block *csb)
+{
+	/* The csb must be valid after returning from vio_h_cop_sync */
+	if (!NX842_CSBCBP_VALID_CHK(csb->valid)) {
+		dev_err(dev, "%s: cspcbp not valid upon completion.\n",
+				__func__);
+		dev_dbg(dev, "valid:0x%02x cs:0x%02x cc:0x%02x ce:0x%02x\n",
+				csb->valid,
+				csb->crb_seq_number,
+				csb->completion_code,
+				csb->completion_extension);
+		dev_dbg(dev, "processed_bytes:%d address:0x%016lx\n",
+				be32_to_cpu(csb->processed_byte_count),
+				(unsigned long)be64_to_cpu(csb->address));
+		return -EIO;
+	}
+
+	/* Check return values from the hardware in the CSB */
+	switch (csb->completion_code) {
+	case 0:	/* Completed without error */
+		break;
+	case 64: /* Target bytes > Source bytes during compression */
+	case 13: /* Output buffer too small */
+		dev_dbg(dev, "%s: Compression output larger than input\n",
+					__func__);
+		return -ENOSPC;
+	case 66: /* Input data contains an illegal template field */
+	case 67: /* Template indicates data past the end of the input stream */
+		dev_dbg(dev, "%s: Bad data for decompression (code:%d)\n",
+					__func__, csb->completion_code);
+		return -EINVAL;
+	default:
+		dev_dbg(dev, "%s: Unspecified error (code:%d)\n",
+					__func__, csb->completion_code);
+		return -EIO;
+	}
+
+	/* Hardware sanity check */
+	if (!NX842_CSBCPB_CE2(csb->completion_extension)) {
+		dev_err(dev, "%s: No error returned by hardware, but "
+				"data returned is unusable, contact support.\n"
+				"(Additional info: csbcbp->processed bytes "
+				"does not specify processed bytes for the "
+				"target buffer.)\n", __func__);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+/**
+ * nx842_pseries_compress - Compress data using the 842 algorithm
+ *
+ * Compression provide by the NX842 coprocessor on IBM Power systems.
+ * The input buffer is compressed and the result is stored in the
+ * provided output buffer.
+ *
+ * Upon return from this function @outlen contains the length of the
+ * compressed data.  If there is an error then @outlen will be 0 and an
+ * error will be specified by the return code from this function.
+ *
+ * @in: Pointer to input buffer
+ * @inlen: Length of input buffer
+ * @out: Pointer to output buffer
+ * @outlen: Length of output buffer
+ * @wrkmem: ptr to buffer for working memory, size determined by
+ *          nx842_pseries_driver.workmem_size
+ *
+ * Returns:
+ *   0		Success, output of length @outlen stored in the buffer at @out
+ *   -ENOMEM	Unable to allocate internal buffers
+ *   -ENOSPC	Output buffer is to small
+ *   -EIO	Internal error
+ *   -ENODEV	Hardware unavailable
+ */
+static int nx842_pseries_compress(const unsigned char *in, unsigned int inlen,
+				  unsigned char *out, unsigned int *outlen,
+				  void *wmem)
+{
+	struct nx842_devdata *local_devdata;
+	struct device *dev = NULL;
+	struct nx842_workmem *workmem;
+	struct nx842_scatterlist slin, slout;
+	struct nx_csbcpb *csbcpb;
+	int ret = 0, max_sync_size;
+	unsigned long inbuf, outbuf;
+	struct vio_pfo_op op = {
+		.done = NULL,
+		.handle = 0,
+		.timeout = 0,
+	};
+	unsigned long start = get_tb();
+
+	inbuf = (unsigned long)in;
+	if (check_constraints(inbuf, &inlen, true))
+		return -EINVAL;
+
+	outbuf = (unsigned long)out;
+	if (check_constraints(outbuf, outlen, false))
+		return -EINVAL;
+
+	rcu_read_lock();
+	local_devdata = rcu_dereference(devdata);
+	if (!local_devdata || !local_devdata->dev) {
+		rcu_read_unlock();
+		return -ENODEV;
+	}
+	max_sync_size = local_devdata->max_sync_size;
+	dev = local_devdata->dev;
+
+	/* Init scatterlist */
+	workmem = PTR_ALIGN(wmem, WORKMEM_ALIGN);
+	slin.entries = (struct nx842_slentry *)workmem->slin;
+	slout.entries = (struct nx842_slentry *)workmem->slout;
+
+	/* Init operation */
+	op.flags = NX842_OP_COMPRESS;
+	csbcpb = &workmem->csbcpb;
+	memset(csbcpb, 0, sizeof(*csbcpb));
+	op.csbcpb = nx842_get_pa(csbcpb);
+
+	if ((inbuf & NX842_HW_PAGE_MASK) ==
+	    ((inbuf + inlen - 1) & NX842_HW_PAGE_MASK)) {
+		/* Create direct DDE */
+		op.in = nx842_get_pa((void *)inbuf);
+		op.inlen = inlen;
+	} else {
+		/* Create indirect DDE (scatterlist) */
+		nx842_build_scatterlist(inbuf, inlen, &slin);
+		op.in = nx842_get_pa(slin.entries);
+		op.inlen = -nx842_get_scatterlist_size(&slin);
+	}
+
+	if ((outbuf & NX842_HW_PAGE_MASK) ==
+	    ((outbuf + *outlen - 1) & NX842_HW_PAGE_MASK)) {
+		/* Create direct DDE */
+		op.out = nx842_get_pa((void *)outbuf);
+		op.outlen = *outlen;
+	} else {
+		/* Create indirect DDE (scatterlist) */
+		nx842_build_scatterlist(outbuf, *outlen, &slout);
+		op.out = nx842_get_pa(slout.entries);
+		op.outlen = -nx842_get_scatterlist_size(&slout);
+	}
+
+	dev_dbg(dev, "%s: op.in %lx op.inlen %ld op.out %lx op.outlen %ld\n",
+		__func__, (unsigned long)op.in, (long)op.inlen,
+		(unsigned long)op.out, (long)op.outlen);
+
+	/* Send request to pHyp */
+	ret = vio_h_cop_sync(local_devdata->vdev, &op);
+
+	/* Check for pHyp error */
+	if (ret) {
+		dev_dbg(dev, "%s: vio_h_cop_sync error (ret=%d, hret=%ld)\n",
+			__func__, ret, op.hcall_err);
+		ret = -EIO;
+		goto unlock;
+	}
+
+	/* Check for hardware error */
+	ret = nx842_validate_result(dev, &csbcpb->csb);
+	if (ret)
+		goto unlock;
+
+	*outlen = be32_to_cpu(csbcpb->csb.processed_byte_count);
+	dev_dbg(dev, "%s: processed_bytes=%d\n", __func__, *outlen);
+
+unlock:
+	if (ret)
+		nx842_inc_comp_failed(local_devdata);
+	else {
+		nx842_inc_comp_complete(local_devdata);
+		ibm_nx842_incr_hist(local_devdata->counters->comp_times,
+			(get_tb() - start) / tb_ticks_per_usec);
+	}
+	rcu_read_unlock();
+	return ret;
+}
+
+/**
+ * nx842_pseries_decompress - Decompress data using the 842 algorithm
+ *
+ * Decompression provide by the NX842 coprocessor on IBM Power systems.
+ * The input buffer is decompressed and the result is stored in the
+ * provided output buffer.  The size allocated to the output buffer is
+ * provided by the caller of this function in @outlen.  Upon return from
+ * this function @outlen contains the length of the decompressed data.
+ * If there is an error then @outlen will be 0 and an error will be
+ * specified by the return code from this function.
+ *
+ * @in: Pointer to input buffer
+ * @inlen: Length of input buffer
+ * @out: Pointer to output buffer
+ * @outlen: Length of output buffer
+ * @wrkmem: ptr to buffer for working memory, size determined by
+ *          nx842_pseries_driver.workmem_size
+ *
+ * Returns:
+ *   0		Success, output of length @outlen stored in the buffer at @out
+ *   -ENODEV	Hardware decompression device is unavailable
+ *   -ENOMEM	Unable to allocate internal buffers
+ *   -ENOSPC	Output buffer is to small
+ *   -EINVAL	Bad input data encountered when attempting decompress
+ *   -EIO	Internal error
+ */
+static int nx842_pseries_decompress(const unsigned char *in, unsigned int inlen,
+				    unsigned char *out, unsigned int *outlen,
+				    void *wmem)
+{
+	struct nx842_devdata *local_devdata;
+	struct device *dev = NULL;
+	struct nx842_workmem *workmem;
+	struct nx842_scatterlist slin, slout;
+	struct nx_csbcpb *csbcpb;
+	int ret = 0, max_sync_size;
+	unsigned long inbuf, outbuf;
+	struct vio_pfo_op op = {
+		.done = NULL,
+		.handle = 0,
+		.timeout = 0,
+	};
+	unsigned long start = get_tb();
+
+	/* Ensure page alignment and size */
+	inbuf = (unsigned long)in;
+	if (check_constraints(inbuf, &inlen, true))
+		return -EINVAL;
+
+	outbuf = (unsigned long)out;
+	if (check_constraints(outbuf, outlen, false))
+		return -EINVAL;
+
+	rcu_read_lock();
+	local_devdata = rcu_dereference(devdata);
+	if (!local_devdata || !local_devdata->dev) {
+		rcu_read_unlock();
+		return -ENODEV;
+	}
+	max_sync_size = local_devdata->max_sync_size;
+	dev = local_devdata->dev;
+
+	workmem = PTR_ALIGN(wmem, WORKMEM_ALIGN);
+
+	/* Init scatterlist */
+	slin.entries = (struct nx842_slentry *)workmem->slin;
+	slout.entries = (struct nx842_slentry *)workmem->slout;
+
+	/* Init operation */
+	op.flags = NX842_OP_DECOMPRESS;
+	csbcpb = &workmem->csbcpb;
+	memset(csbcpb, 0, sizeof(*csbcpb));
+	op.csbcpb = nx842_get_pa(csbcpb);
+
+	if ((inbuf & NX842_HW_PAGE_MASK) ==
+	    ((inbuf + inlen - 1) & NX842_HW_PAGE_MASK)) {
+		/* Create direct DDE */
+		op.in = nx842_get_pa((void *)inbuf);
+		op.inlen = inlen;
+	} else {
+		/* Create indirect DDE (scatterlist) */
+		nx842_build_scatterlist(inbuf, inlen, &slin);
+		op.in = nx842_get_pa(slin.entries);
+		op.inlen = -nx842_get_scatterlist_size(&slin);
+	}
+
+	if ((outbuf & NX842_HW_PAGE_MASK) ==
+	    ((outbuf + *outlen - 1) & NX842_HW_PAGE_MASK)) {
+		/* Create direct DDE */
+		op.out = nx842_get_pa((void *)outbuf);
+		op.outlen = *outlen;
+	} else {
+		/* Create indirect DDE (scatterlist) */
+		nx842_build_scatterlist(outbuf, *outlen, &slout);
+		op.out = nx842_get_pa(slout.entries);
+		op.outlen = -nx842_get_scatterlist_size(&slout);
+	}
+
+	dev_dbg(dev, "%s: op.in %lx op.inlen %ld op.out %lx op.outlen %ld\n",
+		__func__, (unsigned long)op.in, (long)op.inlen,
+		(unsigned long)op.out, (long)op.outlen);
+
+	/* Send request to pHyp */
+	ret = vio_h_cop_sync(local_devdata->vdev, &op);
+
+	/* Check for pHyp error */
+	if (ret) {
+		dev_dbg(dev, "%s: vio_h_cop_sync error (ret=%d, hret=%ld)\n",
+			__func__, ret, op.hcall_err);
+		goto unlock;
+	}
+
+	/* Check for hardware error */
+	ret = nx842_validate_result(dev, &csbcpb->csb);
+	if (ret)
+		goto unlock;
+
+	*outlen = be32_to_cpu(csbcpb->csb.processed_byte_count);
+
+unlock:
+	if (ret)
+		/* decompress fail */
+		nx842_inc_decomp_failed(local_devdata);
+	else {
+		nx842_inc_decomp_complete(local_devdata);
+		ibm_nx842_incr_hist(local_devdata->counters->decomp_times,
+			(get_tb() - start) / tb_ticks_per_usec);
+	}
+
+	rcu_read_unlock();
+	return ret;
+}
+
+/**
+ * nx842_OF_set_defaults -- Set default (disabled) values for devdata
+ *
+ * @devdata - struct nx842_devdata to update
+ *
+ * Returns:
+ *  0 on success
+ *  -ENOENT if @devdata ptr is NULL
+ */
+static int nx842_OF_set_defaults(struct nx842_devdata *devdata)
+{
+	if (devdata) {
+		devdata->max_sync_size = 0;
+		devdata->max_sync_sg = 0;
+		devdata->max_sg_len = 0;
+		devdata->status = UNAVAILABLE;
+		return 0;
+	} else
+		return -ENOENT;
+}
+
+/**
+ * nx842_OF_upd_status -- Update the device info from OF status prop
+ *
+ * The status property indicates if the accelerator is enabled.  If the
+ * device is in the OF tree it indicates that the hardware is present.
+ * The status field indicates if the device is enabled when the status
+ * is 'okay'.  Otherwise the device driver will be disabled.
+ *
+ * @devdata - struct nx842_devdata to update
+ * @prop - struct property point containing the maxsyncop for the update
+ *
+ * Returns:
+ *  0 - Device is available
+ *  -EINVAL - Device is not available
+ */
+static int nx842_OF_upd_status(struct nx842_devdata *devdata,
+					struct property *prop) {
+	int ret = 0;
+	const char *status = (const char *)prop->value;
+
+	if (!strncmp(status, "okay", (size_t)prop->length)) {
+		devdata->status = AVAILABLE;
+	} else {
+		dev_info(devdata->dev, "%s: status '%s' is not 'okay'\n",
+				__func__, status);
+		devdata->status = UNAVAILABLE;
+	}
+
+	return ret;
+}
+
+/**
+ * nx842_OF_upd_maxsglen -- Update the device info from OF maxsglen prop
+ *
+ * Definition of the 'ibm,max-sg-len' OF property:
+ *  This field indicates the maximum byte length of a scatter list
+ *  for the platform facility. It is a single cell encoded as with encode-int.
+ *
+ * Example:
+ *  # od -x ibm,max-sg-len
+ *  0000000 0000 0ff0
+ *
+ *  In this example, the maximum byte length of a scatter list is
+ *  0x0ff0 (4,080).
+ *
+ * @devdata - struct nx842_devdata to update
+ * @prop - struct property point containing the maxsyncop for the update
+ *
+ * Returns:
+ *  0 on success
+ *  -EINVAL on failure
+ */
+static int nx842_OF_upd_maxsglen(struct nx842_devdata *devdata,
+					struct property *prop) {
+	int ret = 0;
+	const unsigned int maxsglen = of_read_number(prop->value, 1);
+
+	if (prop->length != sizeof(maxsglen)) {
+		dev_err(devdata->dev, "%s: unexpected format for ibm,max-sg-len property\n", __func__);
+		dev_dbg(devdata->dev, "%s: ibm,max-sg-len is %d bytes long, expected %lu bytes\n", __func__,
+				prop->length, sizeof(maxsglen));
+		ret = -EINVAL;
+	} else {
+		devdata->max_sg_len = min_t(unsigned int,
+					    maxsglen, NX842_HW_PAGE_SIZE);
+	}
+
+	return ret;
+}
+
+/**
+ * nx842_OF_upd_maxsyncop -- Update the device info from OF maxsyncop prop
+ *
+ * Definition of the 'ibm,max-sync-cop' OF property:
+ *  Two series of cells.  The first series of cells represents the maximums
+ *  that can be synchronously compressed. The second series of cells
+ *  represents the maximums that can be synchronously decompressed.
+ *  1. The first cell in each series contains the count of the number of
+ *     data length, scatter list elements pairs that follow – each being
+ *     of the form
+ *    a. One cell data byte length
+ *    b. One cell total number of scatter list elements
+ *
+ * Example:
+ *  # od -x ibm,max-sync-cop
+ *  0000000 0000 0001 0000 1000 0000 01fe 0000 0001
+ *  0000020 0000 1000 0000 01fe
+ *
+ *  In this example, compression supports 0x1000 (4,096) data byte length
+ *  and 0x1fe (510) total scatter list elements.  Decompression supports
+ *  0x1000 (4,096) data byte length and 0x1f3 (510) total scatter list
+ *  elements.
+ *
+ * @devdata - struct nx842_devdata to update
+ * @prop - struct property point containing the maxsyncop for the update
+ *
+ * Returns:
+ *  0 on success
+ *  -EINVAL on failure
+ */
+static int nx842_OF_upd_maxsyncop(struct nx842_devdata *devdata,
+					struct property *prop) {
+	int ret = 0;
+	unsigned int comp_data_limit, decomp_data_limit;
+	unsigned int comp_sg_limit, decomp_sg_limit;
+	const struct maxsynccop_t {
+		__be32 comp_elements;
+		__be32 comp_data_limit;
+		__be32 comp_sg_limit;
+		__be32 decomp_elements;
+		__be32 decomp_data_limit;
+		__be32 decomp_sg_limit;
+	} *maxsynccop;
+
+	if (prop->length != sizeof(*maxsynccop)) {
+		dev_err(devdata->dev, "%s: unexpected format for ibm,max-sync-cop property\n", __func__);
+		dev_dbg(devdata->dev, "%s: ibm,max-sync-cop is %d bytes long, expected %lu bytes\n", __func__, prop->length,
+				sizeof(*maxsynccop));
+		ret = -EINVAL;
+		goto out;
+	}
+
+	maxsynccop = (const struct maxsynccop_t *)prop->value;
+	comp_data_limit = be32_to_cpu(maxsynccop->comp_data_limit);
+	comp_sg_limit = be32_to_cpu(maxsynccop->comp_sg_limit);
+	decomp_data_limit = be32_to_cpu(maxsynccop->decomp_data_limit);
+	decomp_sg_limit = be32_to_cpu(maxsynccop->decomp_sg_limit);
+
+	/* Use one limit rather than separate limits for compression and
+	 * decompression. Set a maximum for this so as not to exceed the
+	 * size that the header can support and round the value down to
+	 * the hardware page size (4K) */
+	devdata->max_sync_size = min(comp_data_limit, decomp_data_limit);
+
+	devdata->max_sync_size = min_t(unsigned int, devdata->max_sync_size,
+					65536);
+
+	if (devdata->max_sync_size < 4096) {
+		dev_err(devdata->dev, "%s: hardware max data size (%u) is "
+				"less than the driver minimum, unable to use "
+				"the hardware device\n",
+				__func__, devdata->max_sync_size);
+		ret = -EINVAL;
+		goto out;
+	}
+
+	nx842_pseries_constraints.maximum = devdata->max_sync_size;
+
+	devdata->max_sync_sg = min(comp_sg_limit, decomp_sg_limit);
+	if (devdata->max_sync_sg < 1) {
+		dev_err(devdata->dev, "%s: hardware max sg size (%u) is "
+				"less than the driver minimum, unable to use "
+				"the hardware device\n",
+				__func__, devdata->max_sync_sg);
+		ret = -EINVAL;
+		goto out;
+	}
+
+out:
+	return ret;
+}
+
+/**
+ *
+ * nx842_OF_upd -- Handle OF properties updates for the device.
+ *
+ * Set all properties from the OF tree.  Optionally, a new property
+ * can be provided by the @new_prop pointer to overwrite an existing value.
+ * The device will remain disabled until all values are valid, this function
+ * will return an error for updates unless all values are valid.
+ *
+ * @new_prop: If not NULL, this property is being updated.  If NULL, update
+ *  all properties from the current values in the OF tree.
+ *
+ * Returns:
+ *  0 - Success
+ *  -ENOMEM - Could not allocate memory for new devdata structure
+ *  -EINVAL - property value not found, new_prop is not a recognized
+ *	property for the device or property value is not valid.
+ *  -ENODEV - Device is not available
+ */
+static int nx842_OF_upd(struct property *new_prop)
+{
+	struct nx842_devdata *old_devdata = NULL;
+	struct nx842_devdata *new_devdata = NULL;
+	struct device_node *of_node = NULL;
+	struct property *status = NULL;
+	struct property *maxsglen = NULL;
+	struct property *maxsyncop = NULL;
+	int ret = 0;
+	unsigned long flags;
+
+	spin_lock_irqsave(&devdata_mutex, flags);
+	old_devdata = rcu_dereference_check(devdata,
+			lockdep_is_held(&devdata_mutex));
+	if (old_devdata)
+		of_node = old_devdata->dev->of_node;
+
+	if (!old_devdata || !of_node) {
+		pr_err("%s: device is not available\n", __func__);
+		spin_unlock_irqrestore(&devdata_mutex, flags);
+		return -ENODEV;
+	}
+
+	new_devdata = kzalloc(sizeof(*new_devdata), GFP_NOFS);
+	if (!new_devdata) {
+		dev_err(old_devdata->dev, "%s: Could not allocate memory for device data\n", __func__);
+		ret = -ENOMEM;
+		goto error_out;
+	}
+
+	memcpy(new_devdata, old_devdata, sizeof(*old_devdata));
+	new_devdata->counters = old_devdata->counters;
+
+	/* Set ptrs for existing properties */
+	status = of_find_property(of_node, "status", NULL);
+	maxsglen = of_find_property(of_node, "ibm,max-sg-len", NULL);
+	maxsyncop = of_find_property(of_node, "ibm,max-sync-cop", NULL);
+	if (!status || !maxsglen || !maxsyncop) {
+		dev_err(old_devdata->dev, "%s: Could not locate device properties\n", __func__);
+		ret = -EINVAL;
+		goto error_out;
+	}
+
+	/*
+	 * If this is a property update, there are only certain properties that
+	 * we care about. Bail if it isn't in the below list
+	 */
+	if (new_prop && (strncmp(new_prop->name, "status", new_prop->length) ||
+		         strncmp(new_prop->name, "ibm,max-sg-len", new_prop->length) ||
+		         strncmp(new_prop->name, "ibm,max-sync-cop", new_prop->length)))
+		goto out;
+
+	/* Perform property updates */
+	ret = nx842_OF_upd_status(new_devdata, status);
+	if (ret)
+		goto error_out;
+
+	ret = nx842_OF_upd_maxsglen(new_devdata, maxsglen);
+	if (ret)
+		goto error_out;
+
+	ret = nx842_OF_upd_maxsyncop(new_devdata, maxsyncop);
+	if (ret)
+		goto error_out;
+
+out:
+	dev_info(old_devdata->dev, "%s: max_sync_size new:%u old:%u\n",
+			__func__, new_devdata->max_sync_size,
+			old_devdata->max_sync_size);
+	dev_info(old_devdata->dev, "%s: max_sync_sg new:%u old:%u\n",
+			__func__, new_devdata->max_sync_sg,
+			old_devdata->max_sync_sg);
+	dev_info(old_devdata->dev, "%s: max_sg_len new:%u old:%u\n",
+			__func__, new_devdata->max_sg_len,
+			old_devdata->max_sg_len);
+
+	rcu_assign_pointer(devdata, new_devdata);
+	spin_unlock_irqrestore(&devdata_mutex, flags);
+	synchronize_rcu();
+	dev_set_drvdata(new_devdata->dev, new_devdata);
+	kfree(old_devdata);
+	return 0;
+
+error_out:
+	if (new_devdata) {
+		dev_info(old_devdata->dev, "%s: device disabled\n", __func__);
+		nx842_OF_set_defaults(new_devdata);
+		rcu_assign_pointer(devdata, new_devdata);
+		spin_unlock_irqrestore(&devdata_mutex, flags);
+		synchronize_rcu();
+		dev_set_drvdata(new_devdata->dev, new_devdata);
+		kfree(old_devdata);
+	} else {
+		dev_err(old_devdata->dev, "%s: could not update driver from hardware\n", __func__);
+		spin_unlock_irqrestore(&devdata_mutex, flags);
+	}
+
+	if (!ret)
+		ret = -EINVAL;
+	return ret;
+}
+
+/**
+ * nx842_OF_notifier - Process updates to OF properties for the device
+ *
+ * @np: notifier block
+ * @action: notifier action
+ * @update: struct pSeries_reconfig_prop_update pointer if action is
+ *	PSERIES_UPDATE_PROPERTY
+ *
+ * Returns:
+ *	NOTIFY_OK on success
+ *	NOTIFY_BAD encoded with error number on failure, use
+ *		notifier_to_errno() to decode this value
+ */
+static int nx842_OF_notifier(struct notifier_block *np, unsigned long action,
+			     void *data)
+{
+	struct of_reconfig_data *upd = data;
+	struct nx842_devdata *local_devdata;
+	struct device_node *node = NULL;
+
+	rcu_read_lock();
+	local_devdata = rcu_dereference(devdata);
+	if (local_devdata)
+		node = local_devdata->dev->of_node;
+
+	if (local_devdata &&
+			action == OF_RECONFIG_UPDATE_PROPERTY &&
+			!strcmp(upd->dn->name, node->name)) {
+		rcu_read_unlock();
+		nx842_OF_upd(upd->prop);
+	} else
+		rcu_read_unlock();
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block nx842_of_nb = {
+	.notifier_call = nx842_OF_notifier,
+};
+
+#define nx842_counter_read(_name)					\
+static ssize_t nx842_##_name##_show(struct device *dev,		\
+		struct device_attribute *attr,				\
+		char *buf) {						\
+	struct nx842_devdata *local_devdata;			\
+	int p = 0;							\
+	rcu_read_lock();						\
+	local_devdata = rcu_dereference(devdata);			\
+	if (local_devdata)						\
+		p = snprintf(buf, PAGE_SIZE, "%ld\n",			\
+		       atomic64_read(&local_devdata->counters->_name));	\
+	rcu_read_unlock();						\
+	return p;							\
+}
+
+#define NX842DEV_COUNTER_ATTR_RO(_name)					\
+	nx842_counter_read(_name);					\
+	static struct device_attribute dev_attr_##_name = __ATTR(_name,	\
+						0444,			\
+						nx842_##_name##_show,\
+						NULL);
+
+NX842DEV_COUNTER_ATTR_RO(comp_complete);
+NX842DEV_COUNTER_ATTR_RO(comp_failed);
+NX842DEV_COUNTER_ATTR_RO(decomp_complete);
+NX842DEV_COUNTER_ATTR_RO(decomp_failed);
+NX842DEV_COUNTER_ATTR_RO(swdecomp);
+
+static ssize_t nx842_timehist_show(struct device *,
+		struct device_attribute *, char *);
+
+static struct device_attribute dev_attr_comp_times = __ATTR(comp_times, 0444,
+		nx842_timehist_show, NULL);
+static struct device_attribute dev_attr_decomp_times = __ATTR(decomp_times,
+		0444, nx842_timehist_show, NULL);
+
+static ssize_t nx842_timehist_show(struct device *dev,
+		struct device_attribute *attr, char *buf) {
+	char *p = buf;
+	struct nx842_devdata *local_devdata;
+	atomic64_t *times;
+	int bytes_remain = PAGE_SIZE;
+	int bytes;
+	int i;
+
+	rcu_read_lock();
+	local_devdata = rcu_dereference(devdata);
+	if (!local_devdata) {
+		rcu_read_unlock();
+		return 0;
+	}
+
+	if (attr == &dev_attr_comp_times)
+		times = local_devdata->counters->comp_times;
+	else if (attr == &dev_attr_decomp_times)
+		times = local_devdata->counters->decomp_times;
+	else {
+		rcu_read_unlock();
+		return 0;
+	}
+
+	for (i = 0; i < (NX842_HIST_SLOTS - 2); i++) {
+		bytes = snprintf(p, bytes_remain, "%u-%uus:\t%ld\n",
+			       i ? (2<<(i-1)) : 0, (2<<i)-1,
+			       atomic64_read(&times[i]));
+		bytes_remain -= bytes;
+		p += bytes;
+	}
+	/* The last bucket holds everything over
+	 * 2<<(NX842_HIST_SLOTS - 2) us */
+	bytes = snprintf(p, bytes_remain, "%uus - :\t%ld\n",
+			2<<(NX842_HIST_SLOTS - 2),
+			atomic64_read(&times[(NX842_HIST_SLOTS - 1)]));
+	p += bytes;
+
+	rcu_read_unlock();
+	return p - buf;
+}
+
+static struct attribute *nx842_sysfs_entries[] = {
+	&dev_attr_comp_complete.attr,
+	&dev_attr_comp_failed.attr,
+	&dev_attr_decomp_complete.attr,
+	&dev_attr_decomp_failed.attr,
+	&dev_attr_swdecomp.attr,
+	&dev_attr_comp_times.attr,
+	&dev_attr_decomp_times.attr,
+	NULL,
+};
+
+static struct attribute_group nx842_attribute_group = {
+	.name = NULL,		/* put in device directory */
+	.attrs = nx842_sysfs_entries,
+};
+
+static struct nx842_driver nx842_pseries_driver = {
+	.name =		KBUILD_MODNAME,
+	.owner =	THIS_MODULE,
+	.workmem_size =	sizeof(struct nx842_workmem),
+	.constraints =	&nx842_pseries_constraints,
+	.compress =	nx842_pseries_compress,
+	.decompress =	nx842_pseries_decompress,
+};
+
+static int __init nx842_probe(struct vio_dev *viodev,
+				  const struct vio_device_id *id)
+{
+	struct nx842_devdata *old_devdata, *new_devdata = NULL;
+	unsigned long flags;
+	int ret = 0;
+
+	spin_lock_irqsave(&devdata_mutex, flags);
+	old_devdata = rcu_dereference_check(devdata,
+			lockdep_is_held(&devdata_mutex));
+
+	if (old_devdata && old_devdata->vdev != NULL) {
+		dev_err(&viodev->dev, "%s: Attempt to register more than one instance of the hardware\n", __func__);
+		ret = -1;
+		goto error_unlock;
+	}
+
+	dev_set_drvdata(&viodev->dev, NULL);
+
+	new_devdata = kzalloc(sizeof(*new_devdata), GFP_NOFS);
+	if (!new_devdata) {
+		dev_err(&viodev->dev, "%s: Could not allocate memory for device data\n", __func__);
+		ret = -ENOMEM;
+		goto error_unlock;
+	}
+
+	new_devdata->counters = kzalloc(sizeof(*new_devdata->counters),
+			GFP_NOFS);
+	if (!new_devdata->counters) {
+		dev_err(&viodev->dev, "%s: Could not allocate memory for performance counters\n", __func__);
+		ret = -ENOMEM;
+		goto error_unlock;
+	}
+
+	new_devdata->vdev = viodev;
+	new_devdata->dev = &viodev->dev;
+	nx842_OF_set_defaults(new_devdata);
+
+	rcu_assign_pointer(devdata, new_devdata);
+	spin_unlock_irqrestore(&devdata_mutex, flags);
+	synchronize_rcu();
+	kfree(old_devdata);
+
+	of_reconfig_notifier_register(&nx842_of_nb);
+
+	ret = nx842_OF_upd(NULL);
+	if (ret && ret != -ENODEV) {
+		dev_err(&viodev->dev, "could not parse device tree. %d\n", ret);
+		ret = -1;
+		goto error;
+	}
+
+	rcu_read_lock();
+	dev_set_drvdata(&viodev->dev, rcu_dereference(devdata));
+	rcu_read_unlock();
+
+	if (sysfs_create_group(&viodev->dev.kobj, &nx842_attribute_group)) {
+		dev_err(&viodev->dev, "could not create sysfs device attributes\n");
+		ret = -1;
+		goto error;
+	}
+
+	return 0;
+
+error_unlock:
+	spin_unlock_irqrestore(&devdata_mutex, flags);
+	if (new_devdata)
+		kfree(new_devdata->counters);
+	kfree(new_devdata);
+error:
+	return ret;
+}
+
+static int __exit nx842_remove(struct vio_dev *viodev)
+{
+	struct nx842_devdata *old_devdata;
+	unsigned long flags;
+
+	pr_info("Removing IBM Power 842 compression device\n");
+	sysfs_remove_group(&viodev->dev.kobj, &nx842_attribute_group);
+
+	spin_lock_irqsave(&devdata_mutex, flags);
+	old_devdata = rcu_dereference_check(devdata,
+			lockdep_is_held(&devdata_mutex));
+	of_reconfig_notifier_unregister(&nx842_of_nb);
+	RCU_INIT_POINTER(devdata, NULL);
+	spin_unlock_irqrestore(&devdata_mutex, flags);
+	synchronize_rcu();
+	dev_set_drvdata(&viodev->dev, NULL);
+	if (old_devdata)
+		kfree(old_devdata->counters);
+	kfree(old_devdata);
+
+	return 0;
+}
+
+static struct vio_device_id nx842_vio_driver_ids[] = {
+	{"ibm,compression-v1", "ibm,compression"},
+	{"", ""},
+};
+
+static struct vio_driver nx842_vio_driver = {
+	.name = KBUILD_MODNAME,
+	.probe = nx842_probe,
+	.remove = __exit_p(nx842_remove),
+	.get_desired_dma = nx842_get_desired_dma,
+	.id_table = nx842_vio_driver_ids,
+};
+
+static int __init nx842_init(void)
+{
+	struct nx842_devdata *new_devdata;
+	int ret;
+
+	pr_info("Registering IBM Power 842 compression driver\n");
+
+	if (!of_find_compatible_node(NULL, NULL, "ibm,compression"))
+		return -ENODEV;
+
+	RCU_INIT_POINTER(devdata, NULL);
+	new_devdata = kzalloc(sizeof(*new_devdata), GFP_KERNEL);
+	if (!new_devdata) {
+		pr_err("Could not allocate memory for device data\n");
+		return -ENOMEM;
+	}
+	new_devdata->status = UNAVAILABLE;
+	RCU_INIT_POINTER(devdata, new_devdata);
+
+	ret = vio_register_driver(&nx842_vio_driver);
+	if (ret) {
+		pr_err("Could not register VIO driver %d\n", ret);
+
+		kfree(new_devdata);
+		return ret;
+	}
+
+	if (!nx842_platform_driver_set(&nx842_pseries_driver)) {
+		vio_unregister_driver(&nx842_vio_driver);
+		kfree(new_devdata);
+		return -EEXIST;
+	}
+
+	return 0;
+}
+
+module_init(nx842_init);
+
+static void __exit nx842_exit(void)
+{
+	struct nx842_devdata *old_devdata;
+	unsigned long flags;
+
+	pr_info("Exiting IBM Power 842 compression driver\n");
+	nx842_platform_driver_unset(&nx842_pseries_driver);
+	spin_lock_irqsave(&devdata_mutex, flags);
+	old_devdata = rcu_dereference_check(devdata,
+			lockdep_is_held(&devdata_mutex));
+	RCU_INIT_POINTER(devdata, NULL);
+	spin_unlock_irqrestore(&devdata_mutex, flags);
+	synchronize_rcu();
+	if (old_devdata && old_devdata->dev)
+		dev_set_drvdata(old_devdata->dev, NULL);
+	kfree(old_devdata);
+	vio_unregister_driver(&nx842_vio_driver);
+}
+
+module_exit(nx842_exit);
+
diff --git a/drivers/crypto/nx/nx-842.c b/drivers/crypto/nx/nx-842.c
index 887196e9b50c..6e5e0d60d0c8 100644
--- a/drivers/crypto/nx/nx-842.c
+++ b/drivers/crypto/nx/nx-842.c
@@ -1,5 +1,10 @@
 /*
- * Driver for IBM Power 842 compression accelerator
+ * Driver frontend for IBM Power 842 compression accelerator
+ *
+ * Copyright (C) 2015 Dan Streetman, IBM Corp
+ *
+ * Designer of the Power data compression engine:
+ *   Bulent Abali <abali@us.ibm.com>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -10,1594 +15,89 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
- *
- * Copyright (C) IBM Corporation, 2012
- *
- * Authors: Robert Jennings <rcj@linux.vnet.ibm.com>
- *          Seth Jennings <sjenning@linux.vnet.ibm.com>
  */
 
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/nx842.h>
-#include <linux/of.h>
-#include <linux/slab.h>
-
-#include <asm/page.h>
-#include <asm/vio.h>
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
-#include "nx_csbcpb.h" /* struct nx_csbcpb */
+#include "nx-842.h"
 
-#define MODULE_NAME "nx-compress"
 MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Robert Jennings <rcj@linux.vnet.ibm.com>");
+MODULE_AUTHOR("Dan Streetman <ddstreet@ieee.org>");
 MODULE_DESCRIPTION("842 H/W Compression driver for IBM Power processors");
 
-#define SHIFT_4K 12
-#define SHIFT_64K 16
-#define SIZE_4K (1UL << SHIFT_4K)
-#define SIZE_64K (1UL << SHIFT_64K)
-
-/* IO buffer must be 128 byte aligned */
-#define IO_BUFFER_ALIGN 128
-
-struct nx842_header {
-	int blocks_nr; /* number of compressed blocks */
-	int offset; /* offset of the first block (from beginning of header) */
-	int sizes[0]; /* size of compressed blocks */
-};
-
-static inline int nx842_header_size(const struct nx842_header *hdr)
-{
-	return sizeof(struct nx842_header) +
-			hdr->blocks_nr * sizeof(hdr->sizes[0]);
-}
-
-/* Macros for fields within nx_csbcpb */
-/* Check the valid bit within the csbcpb valid field */
-#define NX842_CSBCBP_VALID_CHK(x) (x & BIT_MASK(7))
-
-/* CE macros operate on the completion_extension field bits in the csbcpb.
- * CE0 0=full completion, 1=partial completion
- * CE1 0=CE0 indicates completion, 1=termination (output may be modified)
- * CE2 0=processed_bytes is source bytes, 1=processed_bytes is target bytes */
-#define NX842_CSBCPB_CE0(x)	(x & BIT_MASK(7))
-#define NX842_CSBCPB_CE1(x)	(x & BIT_MASK(6))
-#define NX842_CSBCPB_CE2(x)	(x & BIT_MASK(5))
-
-/* The NX unit accepts data only on 4K page boundaries */
-#define NX842_HW_PAGE_SHIFT	SHIFT_4K
-#define NX842_HW_PAGE_SIZE	(ASM_CONST(1) << NX842_HW_PAGE_SHIFT)
-#define NX842_HW_PAGE_MASK	(~(NX842_HW_PAGE_SIZE-1))
-
-enum nx842_status {
-	UNAVAILABLE,
-	AVAILABLE
-};
-
-struct ibm_nx842_counters {
-	atomic64_t comp_complete;
-	atomic64_t comp_failed;
-	atomic64_t decomp_complete;
-	atomic64_t decomp_failed;
-	atomic64_t swdecomp;
-	atomic64_t comp_times[32];
-	atomic64_t decomp_times[32];
-};
-
-static struct nx842_devdata {
-	struct vio_dev *vdev;
-	struct device *dev;
-	struct ibm_nx842_counters *counters;
-	unsigned int max_sg_len;
-	unsigned int max_sync_size;
-	unsigned int max_sync_sg;
-	enum nx842_status status;
-} __rcu *devdata;
-static DEFINE_SPINLOCK(devdata_mutex);
-
-#define NX842_COUNTER_INC(_x) \
-static inline void nx842_inc_##_x( \
-	const struct nx842_devdata *dev) { \
-	if (dev) \
-		atomic64_inc(&dev->counters->_x); \
-}
-NX842_COUNTER_INC(comp_complete);
-NX842_COUNTER_INC(comp_failed);
-NX842_COUNTER_INC(decomp_complete);
-NX842_COUNTER_INC(decomp_failed);
-NX842_COUNTER_INC(swdecomp);
-
-#define NX842_HIST_SLOTS 16
-
-static void ibm_nx842_incr_hist(atomic64_t *times, unsigned int time)
-{
-	int bucket = fls(time);
-
-	if (bucket)
-		bucket = min((NX842_HIST_SLOTS - 1), bucket - 1);
-
-	atomic64_inc(&times[bucket]);
-}
-
-/* NX unit operation flags */
-#define NX842_OP_COMPRESS	0x0
-#define NX842_OP_CRC		0x1
-#define NX842_OP_DECOMPRESS	0x2
-#define NX842_OP_COMPRESS_CRC   (NX842_OP_COMPRESS | NX842_OP_CRC)
-#define NX842_OP_DECOMPRESS_CRC (NX842_OP_DECOMPRESS | NX842_OP_CRC)
-#define NX842_OP_ASYNC		(1<<23)
-#define NX842_OP_NOTIFY		(1<<22)
-#define NX842_OP_NOTIFY_INT(x)	((x & 0xff)<<8)
-
-static unsigned long nx842_get_desired_dma(struct vio_dev *viodev)
-{
-	/* No use of DMA mappings within the driver. */
-	return 0;
-}
-
-struct nx842_slentry {
-	unsigned long ptr; /* Real address (use __pa()) */
-	unsigned long len;
-};
-
-/* pHyp scatterlist entry */
-struct nx842_scatterlist {
-	int entry_nr; /* number of slentries */
-	struct nx842_slentry *entries; /* ptr to array of slentries */
-};
-
-/* Does not include sizeof(entry_nr) in the size */
-static inline unsigned long nx842_get_scatterlist_size(
-				struct nx842_scatterlist *sl)
-{
-	return sl->entry_nr * sizeof(struct nx842_slentry);
-}
-
-static inline unsigned long nx842_get_pa(void *addr)
-{
-	if (is_vmalloc_addr(addr))
-		return page_to_phys(vmalloc_to_page(addr))
-		       + offset_in_page(addr);
-	else
-		return __pa(addr);
-}
-
-static int nx842_build_scatterlist(unsigned long buf, int len,
-			struct nx842_scatterlist *sl)
-{
-	unsigned long nextpage;
-	struct nx842_slentry *entry;
-
-	sl->entry_nr = 0;
-
-	entry = sl->entries;
-	while (len) {
-		entry->ptr = nx842_get_pa((void *)buf);
-		nextpage = ALIGN(buf + 1, NX842_HW_PAGE_SIZE);
-		if (nextpage < buf + len) {
-			/* we aren't at the end yet */
-			if (IS_ALIGNED(buf, NX842_HW_PAGE_SIZE))
-				/* we are in the middle (or beginning) */
-				entry->len = NX842_HW_PAGE_SIZE;
-			else
-				/* we are at the beginning */
-				entry->len = nextpage - buf;
-		} else {
-			/* at the end */
-			entry->len = len;
-		}
-
-		len -= entry->len;
-		buf += entry->len;
-		sl->entry_nr++;
-		entry++;
-	}
-
-	return 0;
-}
-
-/*
- * Working memory for software decompression
- */
-struct sw842_fifo {
-	union {
-		char f8[256][8];
-		char f4[512][4];
-	};
-	char f2[256][2];
-	unsigned char f84_full;
-	unsigned char f2_full;
-	unsigned char f8_count;
-	unsigned char f2_count;
-	unsigned int f4_count;
-};
-
-/*
- * Working memory for crypto API
+/**
+ * nx842_constraints
+ *
+ * This provides the driver's constraints.  Different nx842 implementations
+ * may have varying requirements.  The constraints are:
+ *   @alignment:	All buffers should be aligned to this
+ *   @multiple:		All buffer lengths should be a multiple of this
+ *   @minimum:		Buffer lengths must not be less than this amount
+ *   @maximum:		Buffer lengths must not be more than this amount
+ *
+ * The constraints apply to all buffers and lengths, both input and output,
+ * for both compression and decompression, except for the minimum which
+ * only applies to compression input and decompression output; the
+ * compressed data can be less than the minimum constraint.  It can be
+ * assumed that compressed data will always adhere to the multiple
+ * constraint.
+ *
+ * The driver may succeed even if these constraints are violated;
+ * however the driver can return failure or suffer reduced performance
+ * if any constraint is not met.
  */
-struct nx842_workmem {
-	char bounce[PAGE_SIZE]; /* bounce buffer for decompression input */
-	union {
-		/* hardware working memory */
-		struct {
-			/* scatterlist */
-			char slin[SIZE_4K];
-			char slout[SIZE_4K];
-			/* coprocessor status/parameter block */
-			struct nx_csbcpb csbcpb;
-		};
-		/* software working memory */
-		struct sw842_fifo swfifo; /* software decompression fifo */
-	};
-};
-
-int nx842_get_workmem_size(void)
-{
-	return sizeof(struct nx842_workmem) + NX842_HW_PAGE_SIZE;
-}
-EXPORT_SYMBOL_GPL(nx842_get_workmem_size);
-
-int nx842_get_workmem_size_aligned(void)
-{
-	return sizeof(struct nx842_workmem);
-}
-EXPORT_SYMBOL_GPL(nx842_get_workmem_size_aligned);
-
-static int nx842_validate_result(struct device *dev,
-	struct cop_status_block *csb)
+int nx842_constraints(struct nx842_constraints *c)
 {
-	/* The csb must be valid after returning from vio_h_cop_sync */
-	if (!NX842_CSBCBP_VALID_CHK(csb->valid)) {
-		dev_err(dev, "%s: cspcbp not valid upon completion.\n",
-				__func__);
-		dev_dbg(dev, "valid:0x%02x cs:0x%02x cc:0x%02x ce:0x%02x\n",
-				csb->valid,
-				csb->crb_seq_number,
-				csb->completion_code,
-				csb->completion_extension);
-		dev_dbg(dev, "processed_bytes:%d address:0x%016lx\n",
-				csb->processed_byte_count,
-				(unsigned long)csb->address);
-		return -EIO;
-	}
-
-	/* Check return values from the hardware in the CSB */
-	switch (csb->completion_code) {
-	case 0:	/* Completed without error */
-		break;
-	case 64: /* Target bytes > Source bytes during compression */
-	case 13: /* Output buffer too small */
-		dev_dbg(dev, "%s: Compression output larger than input\n",
-					__func__);
-		return -ENOSPC;
-	case 66: /* Input data contains an illegal template field */
-	case 67: /* Template indicates data past the end of the input stream */
-		dev_dbg(dev, "%s: Bad data for decompression (code:%d)\n",
-					__func__, csb->completion_code);
-		return -EINVAL;
-	default:
-		dev_dbg(dev, "%s: Unspecified error (code:%d)\n",
-					__func__, csb->completion_code);
-		return -EIO;
-	}
-
-	/* Hardware sanity check */
-	if (!NX842_CSBCPB_CE2(csb->completion_extension)) {
-		dev_err(dev, "%s: No error returned by hardware, but "
-				"data returned is unusable, contact support.\n"
-				"(Additional info: csbcbp->processed bytes "
-				"does not specify processed bytes for the "
-				"target buffer.)\n", __func__);
-		return -EIO;
-	}
-
+	memcpy(c, nx842_platform_driver()->constraints, sizeof(*c));
 	return 0;
 }
+EXPORT_SYMBOL_GPL(nx842_constraints);
 
 /**
- * nx842_compress - Compress data using the 842 algorithm
- *
- * Compression provide by the NX842 coprocessor on IBM Power systems.
- * The input buffer is compressed and the result is stored in the
- * provided output buffer.
- *
- * Upon return from this function @outlen contains the length of the
- * compressed data.  If there is an error then @outlen will be 0 and an
- * error will be specified by the return code from this function.
- *
- * @in: Pointer to input buffer, must be page aligned
- * @inlen: Length of input buffer, must be PAGE_SIZE
- * @out: Pointer to output buffer
- * @outlen: Length of output buffer
- * @wrkmem: ptr to buffer for working memory, size determined by
- *          nx842_get_workmem_size()
+ * nx842_workmem_size
  *
- * Returns:
- *   0		Success, output of length @outlen stored in the buffer at @out
- *   -ENOMEM	Unable to allocate internal buffers
- *   -ENOSPC	Output buffer is to small
- *   -EMSGSIZE	XXX Difficult to describe this limitation
- *   -EIO	Internal error
- *   -ENODEV	Hardware unavailable
+ * Get the amount of working memory the driver requires.
  */
-int nx842_compress(const unsigned char *in, unsigned int inlen,
-		       unsigned char *out, unsigned int *outlen, void *wmem)
+size_t nx842_workmem_size(void)
 {
-	struct nx842_header *hdr;
-	struct nx842_devdata *local_devdata;
-	struct device *dev = NULL;
-	struct nx842_workmem *workmem;
-	struct nx842_scatterlist slin, slout;
-	struct nx_csbcpb *csbcpb;
-	int ret = 0, max_sync_size, i, bytesleft, size, hdrsize;
-	unsigned long inbuf, outbuf, padding;
-	struct vio_pfo_op op = {
-		.done = NULL,
-		.handle = 0,
-		.timeout = 0,
-	};
-	unsigned long start_time = get_tb();
-
-	/*
-	 * Make sure input buffer is 64k page aligned.  This is assumed since
-	 * this driver is designed for page compression only (for now).  This
-	 * is very nice since we can now use direct DDE(s) for the input and
-	 * the alignment is guaranteed.
-	*/
-	inbuf = (unsigned long)in;
-	if (!IS_ALIGNED(inbuf, PAGE_SIZE) || inlen != PAGE_SIZE)
-		return -EINVAL;
-
-	rcu_read_lock();
-	local_devdata = rcu_dereference(devdata);
-	if (!local_devdata || !local_devdata->dev) {
-		rcu_read_unlock();
-		return -ENODEV;
-	}
-	max_sync_size = local_devdata->max_sync_size;
-	dev = local_devdata->dev;
-
-	/* Create the header */
-	hdr = (struct nx842_header *)out;
-	hdr->blocks_nr = PAGE_SIZE / max_sync_size;
-	hdrsize = nx842_header_size(hdr);
-	outbuf = (unsigned long)out + hdrsize;
-	bytesleft = *outlen - hdrsize;
-
-	/* Init scatterlist */
-	workmem = (struct nx842_workmem *)ALIGN((unsigned long)wmem,
-		NX842_HW_PAGE_SIZE);
-	slin.entries = (struct nx842_slentry *)workmem->slin;
-	slout.entries = (struct nx842_slentry *)workmem->slout;
-
-	/* Init operation */
-	op.flags = NX842_OP_COMPRESS;
-	csbcpb = &workmem->csbcpb;
-	memset(csbcpb, 0, sizeof(*csbcpb));
-	op.csbcpb = nx842_get_pa(csbcpb);
-	op.out = nx842_get_pa(slout.entries);
-
-	for (i = 0; i < hdr->blocks_nr; i++) {
-		/*
-		 * Aligning the output blocks to 128 bytes does waste space,
-		 * but it prevents the need for bounce buffers and memory
-		 * copies.  It also simplifies the code a lot.  In the worst
-		 * case (64k page, 4k max_sync_size), you lose up to
-		 * (128*16)/64k = ~3% the compression factor. For 64k
-		 * max_sync_size, the loss would be at most 128/64k = ~0.2%.
-		 */
-		padding = ALIGN(outbuf, IO_BUFFER_ALIGN) - outbuf;
-		outbuf += padding;
-		bytesleft -= padding;
-		if (i == 0)
-			/* save offset into first block in header */
-			hdr->offset = padding + hdrsize;
-
-		if (bytesleft <= 0) {
-			ret = -ENOSPC;
-			goto unlock;
-		}
-
-		/*
-		 * NOTE: If the default max_sync_size is changed from 4k
-		 * to 64k, remove the "likely" case below, since a
-		 * scatterlist will always be needed.
-		 */
-		if (likely(max_sync_size == NX842_HW_PAGE_SIZE)) {
-			/* Create direct DDE */
-			op.in = nx842_get_pa((void *)inbuf);
-			op.inlen = max_sync_size;
-
-		} else {
-			/* Create indirect DDE (scatterlist) */
-			nx842_build_scatterlist(inbuf, max_sync_size, &slin);
-			op.in = nx842_get_pa(slin.entries);
-			op.inlen = -nx842_get_scatterlist_size(&slin);
-		}
-
-		/*
-		 * If max_sync_size != NX842_HW_PAGE_SIZE, an indirect
-		 * DDE is required for the outbuf.
-		 * If max_sync_size == NX842_HW_PAGE_SIZE, outbuf must
-		 * also be page aligned (1 in 128/4k=32 chance) in order
-		 * to use a direct DDE.
-		 * This is unlikely, just use an indirect DDE always.
-		 */
-		nx842_build_scatterlist(outbuf,
-			min(bytesleft, max_sync_size), &slout);
-		/* op.out set before loop */
-		op.outlen = -nx842_get_scatterlist_size(&slout);
-
-		/* Send request to pHyp */
-		ret = vio_h_cop_sync(local_devdata->vdev, &op);
-
-		/* Check for pHyp error */
-		if (ret) {
-			dev_dbg(dev, "%s: vio_h_cop_sync error (ret=%d, hret=%ld)\n",
-				__func__, ret, op.hcall_err);
-			ret = -EIO;
-			goto unlock;
-		}
-
-		/* Check for hardware error */
-		ret = nx842_validate_result(dev, &csbcpb->csb);
-		if (ret && ret != -ENOSPC)
-			goto unlock;
-
-		/* Handle incompressible data */
-		if (unlikely(ret == -ENOSPC)) {
-			if (bytesleft < max_sync_size) {
-				/*
-				 * Not enough space left in the output buffer
-				 * to store uncompressed block
-				 */
-				goto unlock;
-			} else {
-				/* Store incompressible block */
-				memcpy((void *)outbuf, (void *)inbuf,
-					max_sync_size);
-				hdr->sizes[i] = -max_sync_size;
-				outbuf += max_sync_size;
-				bytesleft -= max_sync_size;
-				/* Reset ret, incompressible data handled */
-				ret = 0;
-			}
-		} else {
-			/* Normal case, compression was successful */
-			size = csbcpb->csb.processed_byte_count;
-			dev_dbg(dev, "%s: processed_bytes=%d\n",
-				__func__, size);
-			hdr->sizes[i] = size;
-			outbuf += size;
-			bytesleft -= size;
-		}
-
-		inbuf += max_sync_size;
-	}
-
-	*outlen = (unsigned int)(outbuf - (unsigned long)out);
-
-unlock:
-	if (ret)
-		nx842_inc_comp_failed(local_devdata);
-	else {
-		nx842_inc_comp_complete(local_devdata);
-		ibm_nx842_incr_hist(local_devdata->counters->comp_times,
-			(get_tb() - start_time) / tb_ticks_per_usec);
-	}
-	rcu_read_unlock();
-	return ret;
+	return nx842_platform_driver()->workmem_size;
 }
-EXPORT_SYMBOL_GPL(nx842_compress);
-
-static int sw842_decompress(const unsigned char *, int, unsigned char *, int *,
-			const void *);
+EXPORT_SYMBOL_GPL(nx842_workmem_size);
 
-/**
- * nx842_decompress - Decompress data using the 842 algorithm
- *
- * Decompression provide by the NX842 coprocessor on IBM Power systems.
- * The input buffer is decompressed and the result is stored in the
- * provided output buffer.  The size allocated to the output buffer is
- * provided by the caller of this function in @outlen.  Upon return from
- * this function @outlen contains the length of the decompressed data.
- * If there is an error then @outlen will be 0 and an error will be
- * specified by the return code from this function.
- *
- * @in: Pointer to input buffer, will use bounce buffer if not 128 byte
- *      aligned
- * @inlen: Length of input buffer
- * @out: Pointer to output buffer, must be page aligned
- * @outlen: Length of output buffer, must be PAGE_SIZE
- * @wrkmem: ptr to buffer for working memory, size determined by
- *          nx842_get_workmem_size()
- *
- * Returns:
- *   0		Success, output of length @outlen stored in the buffer at @out
- *   -ENODEV	Hardware decompression device is unavailable
- *   -ENOMEM	Unable to allocate internal buffers
- *   -ENOSPC	Output buffer is to small
- *   -EINVAL	Bad input data encountered when attempting decompress
- *   -EIO	Internal error
- */
-int nx842_decompress(const unsigned char *in, unsigned int inlen,
-			 unsigned char *out, unsigned int *outlen, void *wmem)
+int nx842_compress(const unsigned char *in, unsigned int ilen,
+		   unsigned char *out, unsigned int *olen, void *wmem)
 {
-	struct nx842_header *hdr;
-	struct nx842_devdata *local_devdata;
-	struct device *dev = NULL;
-	struct nx842_workmem *workmem;
-	struct nx842_scatterlist slin, slout;
-	struct nx_csbcpb *csbcpb;
-	int ret = 0, i, size, max_sync_size;
-	unsigned long inbuf, outbuf;
-	struct vio_pfo_op op = {
-		.done = NULL,
-		.handle = 0,
-		.timeout = 0,
-	};
-	unsigned long start_time = get_tb();
-
-	/* Ensure page alignment and size */
-	outbuf = (unsigned long)out;
-	if (!IS_ALIGNED(outbuf, PAGE_SIZE) || *outlen != PAGE_SIZE)
-		return -EINVAL;
-
-	rcu_read_lock();
-	local_devdata = rcu_dereference(devdata);
-	if (local_devdata)
-		dev = local_devdata->dev;
-
-	/* Get header */
-	hdr = (struct nx842_header *)in;
-
-	workmem = (struct nx842_workmem *)ALIGN((unsigned long)wmem,
-		NX842_HW_PAGE_SIZE);
-
-	inbuf = (unsigned long)in + hdr->offset;
-	if (likely(!IS_ALIGNED(inbuf, IO_BUFFER_ALIGN))) {
-		/* Copy block(s) into bounce buffer for alignment */
-		memcpy(workmem->bounce, in + hdr->offset, inlen - hdr->offset);
-		inbuf = (unsigned long)workmem->bounce;
-	}
-
-	/* Init scatterlist */
-	slin.entries = (struct nx842_slentry *)workmem->slin;
-	slout.entries = (struct nx842_slentry *)workmem->slout;
-
-	/* Init operation */
-	op.flags = NX842_OP_DECOMPRESS;
-	csbcpb = &workmem->csbcpb;
-	memset(csbcpb, 0, sizeof(*csbcpb));
-	op.csbcpb = nx842_get_pa(csbcpb);
-
-	/*
-	 * max_sync_size may have changed since compression,
-	 * so we can't read it from the device info. We need
-	 * to derive it from hdr->blocks_nr.
-	 */
-	max_sync_size = PAGE_SIZE / hdr->blocks_nr;
-
-	for (i = 0; i < hdr->blocks_nr; i++) {
-		/* Skip padding */
-		inbuf = ALIGN(inbuf, IO_BUFFER_ALIGN);
-
-		if (hdr->sizes[i] < 0) {
-			/* Negative sizes indicate uncompressed data blocks */
-			size = abs(hdr->sizes[i]);
-			memcpy((void *)outbuf, (void *)inbuf, size);
-			outbuf += size;
-			inbuf += size;
-			continue;
-		}
-
-		if (!dev)
-			goto sw;
-
-		/*
-		 * The better the compression, the more likely the "likely"
-		 * case becomes.
-		 */
-		if (likely((inbuf & NX842_HW_PAGE_MASK) ==
-			((inbuf + hdr->sizes[i] - 1) & NX842_HW_PAGE_MASK))) {
-			/* Create direct DDE */
-			op.in = nx842_get_pa((void *)inbuf);
-			op.inlen = hdr->sizes[i];
-		} else {
-			/* Create indirect DDE (scatterlist) */
-			nx842_build_scatterlist(inbuf, hdr->sizes[i] , &slin);
-			op.in = nx842_get_pa(slin.entries);
-			op.inlen = -nx842_get_scatterlist_size(&slin);
-		}
-
-		/*
-		 * NOTE: If the default max_sync_size is changed from 4k
-		 * to 64k, remove the "likely" case below, since a
-		 * scatterlist will always be needed.
-		 */
-		if (likely(max_sync_size == NX842_HW_PAGE_SIZE)) {
-			/* Create direct DDE */
-			op.out = nx842_get_pa((void *)outbuf);
-			op.outlen = max_sync_size;
-		} else {
-			/* Create indirect DDE (scatterlist) */
-			nx842_build_scatterlist(outbuf, max_sync_size, &slout);
-			op.out = nx842_get_pa(slout.entries);
-			op.outlen = -nx842_get_scatterlist_size(&slout);
-		}
-
-		/* Send request to pHyp */
-		ret = vio_h_cop_sync(local_devdata->vdev, &op);
-
-		/* Check for pHyp error */
-		if (ret) {
-			dev_dbg(dev, "%s: vio_h_cop_sync error (ret=%d, hret=%ld)\n",
-				__func__, ret, op.hcall_err);
-			dev = NULL;
-			goto sw;
-		}
-
-		/* Check for hardware error */
-		ret = nx842_validate_result(dev, &csbcpb->csb);
-		if (ret) {
-			dev = NULL;
-			goto sw;
-		}
-
-		/* HW decompression success */
-		inbuf += hdr->sizes[i];
-		outbuf += csbcpb->csb.processed_byte_count;
-		continue;
-
-sw:
-		/* software decompression */
-		size = max_sync_size;
-		ret = sw842_decompress(
-			(unsigned char *)inbuf, hdr->sizes[i],
-			(unsigned char *)outbuf, &size, wmem);
-		if (ret)
-			pr_debug("%s: sw842_decompress failed with %d\n",
-				__func__, ret);
-
-		if (ret) {
-			if (ret != -ENOSPC && ret != -EINVAL &&
-					ret != -EMSGSIZE)
-				ret = -EIO;
-			goto unlock;
-		}
-
-		/* SW decompression success */
-		inbuf += hdr->sizes[i];
-		outbuf += size;
-	}
-
-	*outlen = (unsigned int)(outbuf - (unsigned long)out);
-
-unlock:
-	if (ret)
-		/* decompress fail */
-		nx842_inc_decomp_failed(local_devdata);
-	else {
-		if (!dev)
-			/* software decompress */
-			nx842_inc_swdecomp(local_devdata);
-		nx842_inc_decomp_complete(local_devdata);
-		ibm_nx842_incr_hist(local_devdata->counters->decomp_times,
-			(get_tb() - start_time) / tb_ticks_per_usec);
-	}
-
-	rcu_read_unlock();
-	return ret;
+	return nx842_platform_driver()->compress(in, ilen, out, olen, wmem);
 }
-EXPORT_SYMBOL_GPL(nx842_decompress);
+EXPORT_SYMBOL_GPL(nx842_compress);
 
-/**
- * nx842_OF_set_defaults -- Set default (disabled) values for devdata
- *
- * @devdata - struct nx842_devdata to update
- *
- * Returns:
- *  0 on success
- *  -ENOENT if @devdata ptr is NULL
- */
-static int nx842_OF_set_defaults(struct nx842_devdata *devdata)
+int nx842_decompress(const unsigned char *in, unsigned int ilen,
+		     unsigned char *out, unsigned int *olen, void *wmem)
 {
-	if (devdata) {
-		devdata->max_sync_size = 0;
-		devdata->max_sync_sg = 0;
-		devdata->max_sg_len = 0;
-		devdata->status = UNAVAILABLE;
-		return 0;
-	} else
-		return -ENOENT;
-}
-
-/**
- * nx842_OF_upd_status -- Update the device info from OF status prop
- *
- * The status property indicates if the accelerator is enabled.  If the
- * device is in the OF tree it indicates that the hardware is present.
- * The status field indicates if the device is enabled when the status
- * is 'okay'.  Otherwise the device driver will be disabled.
- *
- * @devdata - struct nx842_devdata to update
- * @prop - struct property point containing the maxsyncop for the update
- *
- * Returns:
- *  0 - Device is available
- *  -EINVAL - Device is not available
- */
-static int nx842_OF_upd_status(struct nx842_devdata *devdata,
-					struct property *prop) {
-	int ret = 0;
-	const char *status = (const char *)prop->value;
-
-	if (!strncmp(status, "okay", (size_t)prop->length)) {
-		devdata->status = AVAILABLE;
-	} else {
-		dev_info(devdata->dev, "%s: status '%s' is not 'okay'\n",
-				__func__, status);
-		devdata->status = UNAVAILABLE;
-	}
-
-	return ret;
-}
-
-/**
- * nx842_OF_upd_maxsglen -- Update the device info from OF maxsglen prop
- *
- * Definition of the 'ibm,max-sg-len' OF property:
- *  This field indicates the maximum byte length of a scatter list
- *  for the platform facility. It is a single cell encoded as with encode-int.
- *
- * Example:
- *  # od -x ibm,max-sg-len
- *  0000000 0000 0ff0
- *
- *  In this example, the maximum byte length of a scatter list is
- *  0x0ff0 (4,080).
- *
- * @devdata - struct nx842_devdata to update
- * @prop - struct property point containing the maxsyncop for the update
- *
- * Returns:
- *  0 on success
- *  -EINVAL on failure
- */
-static int nx842_OF_upd_maxsglen(struct nx842_devdata *devdata,
-					struct property *prop) {
-	int ret = 0;
-	const int *maxsglen = prop->value;
-
-	if (prop->length != sizeof(*maxsglen)) {
-		dev_err(devdata->dev, "%s: unexpected format for ibm,max-sg-len property\n", __func__);
-		dev_dbg(devdata->dev, "%s: ibm,max-sg-len is %d bytes long, expected %lu bytes\n", __func__,
-				prop->length, sizeof(*maxsglen));
-		ret = -EINVAL;
-	} else {
-		devdata->max_sg_len = (unsigned int)min(*maxsglen,
-				(int)NX842_HW_PAGE_SIZE);
-	}
-
-	return ret;
-}
-
-/**
- * nx842_OF_upd_maxsyncop -- Update the device info from OF maxsyncop prop
- *
- * Definition of the 'ibm,max-sync-cop' OF property:
- *  Two series of cells.  The first series of cells represents the maximums
- *  that can be synchronously compressed. The second series of cells
- *  represents the maximums that can be synchronously decompressed.
- *  1. The first cell in each series contains the count of the number of
- *     data length, scatter list elements pairs that follow – each being
- *     of the form
- *    a. One cell data byte length
- *    b. One cell total number of scatter list elements
- *
- * Example:
- *  # od -x ibm,max-sync-cop
- *  0000000 0000 0001 0000 1000 0000 01fe 0000 0001
- *  0000020 0000 1000 0000 01fe
- *
- *  In this example, compression supports 0x1000 (4,096) data byte length
- *  and 0x1fe (510) total scatter list elements.  Decompression supports
- *  0x1000 (4,096) data byte length and 0x1f3 (510) total scatter list
- *  elements.
- *
- * @devdata - struct nx842_devdata to update
- * @prop - struct property point containing the maxsyncop for the update
- *
- * Returns:
- *  0 on success
- *  -EINVAL on failure
- */
-static int nx842_OF_upd_maxsyncop(struct nx842_devdata *devdata,
-					struct property *prop) {
-	int ret = 0;
-	const struct maxsynccop_t {
-		int comp_elements;
-		int comp_data_limit;
-		int comp_sg_limit;
-		int decomp_elements;
-		int decomp_data_limit;
-		int decomp_sg_limit;
-	} *maxsynccop;
-
-	if (prop->length != sizeof(*maxsynccop)) {
-		dev_err(devdata->dev, "%s: unexpected format for ibm,max-sync-cop property\n", __func__);
-		dev_dbg(devdata->dev, "%s: ibm,max-sync-cop is %d bytes long, expected %lu bytes\n", __func__, prop->length,
-				sizeof(*maxsynccop));
-		ret = -EINVAL;
-		goto out;
-	}
-
-	maxsynccop = (const struct maxsynccop_t *)prop->value;
-
-	/* Use one limit rather than separate limits for compression and
-	 * decompression. Set a maximum for this so as not to exceed the
-	 * size that the header can support and round the value down to
-	 * the hardware page size (4K) */
-	devdata->max_sync_size =
-			(unsigned int)min(maxsynccop->comp_data_limit,
-					maxsynccop->decomp_data_limit);
-
-	devdata->max_sync_size = min_t(unsigned int, devdata->max_sync_size,
-					SIZE_64K);
-
-	if (devdata->max_sync_size < SIZE_4K) {
-		dev_err(devdata->dev, "%s: hardware max data size (%u) is "
-				"less than the driver minimum, unable to use "
-				"the hardware device\n",
-				__func__, devdata->max_sync_size);
-		ret = -EINVAL;
-		goto out;
-	}
-
-	devdata->max_sync_sg = (unsigned int)min(maxsynccop->comp_sg_limit,
-						maxsynccop->decomp_sg_limit);
-	if (devdata->max_sync_sg < 1) {
-		dev_err(devdata->dev, "%s: hardware max sg size (%u) is "
-				"less than the driver minimum, unable to use "
-				"the hardware device\n",
-				__func__, devdata->max_sync_sg);
-		ret = -EINVAL;
-		goto out;
-	}
-
-out:
-	return ret;
+	return nx842_platform_driver()->decompress(in, ilen, out, olen, wmem);
 }
+EXPORT_SYMBOL_GPL(nx842_decompress);
 
-/**
- *
- * nx842_OF_upd -- Handle OF properties updates for the device.
- *
- * Set all properties from the OF tree.  Optionally, a new property
- * can be provided by the @new_prop pointer to overwrite an existing value.
- * The device will remain disabled until all values are valid, this function
- * will return an error for updates unless all values are valid.
- *
- * @new_prop: If not NULL, this property is being updated.  If NULL, update
- *  all properties from the current values in the OF tree.
- *
- * Returns:
- *  0 - Success
- *  -ENOMEM - Could not allocate memory for new devdata structure
- *  -EINVAL - property value not found, new_prop is not a recognized
- *	property for the device or property value is not valid.
- *  -ENODEV - Device is not available
- */
-static int nx842_OF_upd(struct property *new_prop)
+static __init int nx842_init(void)
 {
-	struct nx842_devdata *old_devdata = NULL;
-	struct nx842_devdata *new_devdata = NULL;
-	struct device_node *of_node = NULL;
-	struct property *status = NULL;
-	struct property *maxsglen = NULL;
-	struct property *maxsyncop = NULL;
-	int ret = 0;
-	unsigned long flags;
-
-	spin_lock_irqsave(&devdata_mutex, flags);
-	old_devdata = rcu_dereference_check(devdata,
-			lockdep_is_held(&devdata_mutex));
-	if (old_devdata)
-		of_node = old_devdata->dev->of_node;
+	request_module("nx-compress-powernv");
+	request_module("nx-compress-pseries");
 
-	if (!old_devdata || !of_node) {
-		pr_err("%s: device is not available\n", __func__);
-		spin_unlock_irqrestore(&devdata_mutex, flags);
-		return -ENODEV;
-	}
-
-	new_devdata = kzalloc(sizeof(*new_devdata), GFP_NOFS);
-	if (!new_devdata) {
-		dev_err(old_devdata->dev, "%s: Could not allocate memory for device data\n", __func__);
-		ret = -ENOMEM;
-		goto error_out;
-	}
-
-	memcpy(new_devdata, old_devdata, sizeof(*old_devdata));
-	new_devdata->counters = old_devdata->counters;
-
-	/* Set ptrs for existing properties */
-	status = of_find_property(of_node, "status", NULL);
-	maxsglen = of_find_property(of_node, "ibm,max-sg-len", NULL);
-	maxsyncop = of_find_property(of_node, "ibm,max-sync-cop", NULL);
-	if (!status || !maxsglen || !maxsyncop) {
-		dev_err(old_devdata->dev, "%s: Could not locate device properties\n", __func__);
-		ret = -EINVAL;
-		goto error_out;
-	}
-
-	/*
-	 * If this is a property update, there are only certain properties that
-	 * we care about. Bail if it isn't in the below list
+	/* we prevent loading if there's no platform driver, and we get the
+	 * module that set it so it won't unload, so we don't need to check
+	 * if it's set in any of the above functions
 	 */
-	if (new_prop && (strncmp(new_prop->name, "status", new_prop->length) ||
-		         strncmp(new_prop->name, "ibm,max-sg-len", new_prop->length) ||
-		         strncmp(new_prop->name, "ibm,max-sync-cop", new_prop->length)))
-		goto out;
-
-	/* Perform property updates */
-	ret = nx842_OF_upd_status(new_devdata, status);
-	if (ret)
-		goto error_out;
-
-	ret = nx842_OF_upd_maxsglen(new_devdata, maxsglen);
-	if (ret)
-		goto error_out;
-
-	ret = nx842_OF_upd_maxsyncop(new_devdata, maxsyncop);
-	if (ret)
-		goto error_out;
-
-out:
-	dev_info(old_devdata->dev, "%s: max_sync_size new:%u old:%u\n",
-			__func__, new_devdata->max_sync_size,
-			old_devdata->max_sync_size);
-	dev_info(old_devdata->dev, "%s: max_sync_sg new:%u old:%u\n",
-			__func__, new_devdata->max_sync_sg,
-			old_devdata->max_sync_sg);
-	dev_info(old_devdata->dev, "%s: max_sg_len new:%u old:%u\n",
-			__func__, new_devdata->max_sg_len,
-			old_devdata->max_sg_len);
-
-	rcu_assign_pointer(devdata, new_devdata);
-	spin_unlock_irqrestore(&devdata_mutex, flags);
-	synchronize_rcu();
-	dev_set_drvdata(new_devdata->dev, new_devdata);
-	kfree(old_devdata);
-	return 0;
-
-error_out:
-	if (new_devdata) {
-		dev_info(old_devdata->dev, "%s: device disabled\n", __func__);
-		nx842_OF_set_defaults(new_devdata);
-		rcu_assign_pointer(devdata, new_devdata);
-		spin_unlock_irqrestore(&devdata_mutex, flags);
-		synchronize_rcu();
-		dev_set_drvdata(new_devdata->dev, new_devdata);
-		kfree(old_devdata);
-	} else {
-		dev_err(old_devdata->dev, "%s: could not update driver from hardware\n", __func__);
-		spin_unlock_irqrestore(&devdata_mutex, flags);
-	}
-
-	if (!ret)
-		ret = -EINVAL;
-	return ret;
-}
-
-/**
- * nx842_OF_notifier - Process updates to OF properties for the device
- *
- * @np: notifier block
- * @action: notifier action
- * @update: struct pSeries_reconfig_prop_update pointer if action is
- *	PSERIES_UPDATE_PROPERTY
- *
- * Returns:
- *	NOTIFY_OK on success
- *	NOTIFY_BAD encoded with error number on failure, use
- *		notifier_to_errno() to decode this value
- */
-static int nx842_OF_notifier(struct notifier_block *np, unsigned long action,
-			     void *data)
-{
-	struct of_reconfig_data *upd = data;
-	struct nx842_devdata *local_devdata;
-	struct device_node *node = NULL;
-
-	rcu_read_lock();
-	local_devdata = rcu_dereference(devdata);
-	if (local_devdata)
-		node = local_devdata->dev->of_node;
-
-	if (local_devdata &&
-			action == OF_RECONFIG_UPDATE_PROPERTY &&
-			!strcmp(upd->dn->name, node->name)) {
-		rcu_read_unlock();
-		nx842_OF_upd(upd->prop);
-	} else
-		rcu_read_unlock();
-
-	return NOTIFY_OK;
-}
-
-static struct notifier_block nx842_of_nb = {
-	.notifier_call = nx842_OF_notifier,
-};
-
-#define nx842_counter_read(_name)					\
-static ssize_t nx842_##_name##_show(struct device *dev,		\
-		struct device_attribute *attr,				\
-		char *buf) {						\
-	struct nx842_devdata *local_devdata;			\
-	int p = 0;							\
-	rcu_read_lock();						\
-	local_devdata = rcu_dereference(devdata);			\
-	if (local_devdata)						\
-		p = snprintf(buf, PAGE_SIZE, "%ld\n",			\
-		       atomic64_read(&local_devdata->counters->_name));	\
-	rcu_read_unlock();						\
-	return p;							\
-}
-
-#define NX842DEV_COUNTER_ATTR_RO(_name)					\
-	nx842_counter_read(_name);					\
-	static struct device_attribute dev_attr_##_name = __ATTR(_name,	\
-						0444,			\
-						nx842_##_name##_show,\
-						NULL);
-
-NX842DEV_COUNTER_ATTR_RO(comp_complete);
-NX842DEV_COUNTER_ATTR_RO(comp_failed);
-NX842DEV_COUNTER_ATTR_RO(decomp_complete);
-NX842DEV_COUNTER_ATTR_RO(decomp_failed);
-NX842DEV_COUNTER_ATTR_RO(swdecomp);
-
-static ssize_t nx842_timehist_show(struct device *,
-		struct device_attribute *, char *);
-
-static struct device_attribute dev_attr_comp_times = __ATTR(comp_times, 0444,
-		nx842_timehist_show, NULL);
-static struct device_attribute dev_attr_decomp_times = __ATTR(decomp_times,
-		0444, nx842_timehist_show, NULL);
-
-static ssize_t nx842_timehist_show(struct device *dev,
-		struct device_attribute *attr, char *buf) {
-	char *p = buf;
-	struct nx842_devdata *local_devdata;
-	atomic64_t *times;
-	int bytes_remain = PAGE_SIZE;
-	int bytes;
-	int i;
-
-	rcu_read_lock();
-	local_devdata = rcu_dereference(devdata);
-	if (!local_devdata) {
-		rcu_read_unlock();
-		return 0;
-	}
-
-	if (attr == &dev_attr_comp_times)
-		times = local_devdata->counters->comp_times;
-	else if (attr == &dev_attr_decomp_times)
-		times = local_devdata->counters->decomp_times;
-	else {
-		rcu_read_unlock();
-		return 0;
-	}
-
-	for (i = 0; i < (NX842_HIST_SLOTS - 2); i++) {
-		bytes = snprintf(p, bytes_remain, "%u-%uus:\t%ld\n",
-			       i ? (2<<(i-1)) : 0, (2<<i)-1,
-			       atomic64_read(&times[i]));
-		bytes_remain -= bytes;
-		p += bytes;
-	}
-	/* The last bucket holds everything over
-	 * 2<<(NX842_HIST_SLOTS - 2) us */
-	bytes = snprintf(p, bytes_remain, "%uus - :\t%ld\n",
-			2<<(NX842_HIST_SLOTS - 2),
-			atomic64_read(&times[(NX842_HIST_SLOTS - 1)]));
-	p += bytes;
-
-	rcu_read_unlock();
-	return p - buf;
-}
-
-static struct attribute *nx842_sysfs_entries[] = {
-	&dev_attr_comp_complete.attr,
-	&dev_attr_comp_failed.attr,
-	&dev_attr_decomp_complete.attr,
-	&dev_attr_decomp_failed.attr,
-	&dev_attr_swdecomp.attr,
-	&dev_attr_comp_times.attr,
-	&dev_attr_decomp_times.attr,
-	NULL,
-};
-
-static struct attribute_group nx842_attribute_group = {
-	.name = NULL,		/* put in device directory */
-	.attrs = nx842_sysfs_entries,
-};
-
-static int __init nx842_probe(struct vio_dev *viodev,
-				  const struct vio_device_id *id)
-{
-	struct nx842_devdata *old_devdata, *new_devdata = NULL;
-	unsigned long flags;
-	int ret = 0;
-
-	spin_lock_irqsave(&devdata_mutex, flags);
-	old_devdata = rcu_dereference_check(devdata,
-			lockdep_is_held(&devdata_mutex));
-
-	if (old_devdata && old_devdata->vdev != NULL) {
-		dev_err(&viodev->dev, "%s: Attempt to register more than one instance of the hardware\n", __func__);
-		ret = -1;
-		goto error_unlock;
-	}
-
-	dev_set_drvdata(&viodev->dev, NULL);
-
-	new_devdata = kzalloc(sizeof(*new_devdata), GFP_NOFS);
-	if (!new_devdata) {
-		dev_err(&viodev->dev, "%s: Could not allocate memory for device data\n", __func__);
-		ret = -ENOMEM;
-		goto error_unlock;
-	}
-
-	new_devdata->counters = kzalloc(sizeof(*new_devdata->counters),
-			GFP_NOFS);
-	if (!new_devdata->counters) {
-		dev_err(&viodev->dev, "%s: Could not allocate memory for performance counters\n", __func__);
-		ret = -ENOMEM;
-		goto error_unlock;
-	}
-
-	new_devdata->vdev = viodev;
-	new_devdata->dev = &viodev->dev;
-	nx842_OF_set_defaults(new_devdata);
-
-	rcu_assign_pointer(devdata, new_devdata);
-	spin_unlock_irqrestore(&devdata_mutex, flags);
-	synchronize_rcu();
-	kfree(old_devdata);
-
-	of_reconfig_notifier_register(&nx842_of_nb);
-
-	ret = nx842_OF_upd(NULL);
-	if (ret && ret != -ENODEV) {
-		dev_err(&viodev->dev, "could not parse device tree. %d\n", ret);
-		ret = -1;
-		goto error;
-	}
-
-	rcu_read_lock();
-	dev_set_drvdata(&viodev->dev, rcu_dereference(devdata));
-	rcu_read_unlock();
-
-	if (sysfs_create_group(&viodev->dev.kobj, &nx842_attribute_group)) {
-		dev_err(&viodev->dev, "could not create sysfs device attributes\n");
-		ret = -1;
-		goto error;
+	if (!nx842_platform_driver_get()) {
+		pr_err("no nx842 driver found.\n");
+		return -ENODEV;
 	}
 
 	return 0;
-
-error_unlock:
-	spin_unlock_irqrestore(&devdata_mutex, flags);
-	if (new_devdata)
-		kfree(new_devdata->counters);
-	kfree(new_devdata);
-error:
-	return ret;
-}
-
-static int __exit nx842_remove(struct vio_dev *viodev)
-{
-	struct nx842_devdata *old_devdata;
-	unsigned long flags;
-
-	pr_info("Removing IBM Power 842 compression device\n");
-	sysfs_remove_group(&viodev->dev.kobj, &nx842_attribute_group);
-
-	spin_lock_irqsave(&devdata_mutex, flags);
-	old_devdata = rcu_dereference_check(devdata,
-			lockdep_is_held(&devdata_mutex));
-	of_reconfig_notifier_unregister(&nx842_of_nb);
-	RCU_INIT_POINTER(devdata, NULL);
-	spin_unlock_irqrestore(&devdata_mutex, flags);
-	synchronize_rcu();
-	dev_set_drvdata(&viodev->dev, NULL);
-	if (old_devdata)
-		kfree(old_devdata->counters);
-	kfree(old_devdata);
-	return 0;
-}
-
-static struct vio_device_id nx842_driver_ids[] = {
-	{"ibm,compression-v1", "ibm,compression"},
-	{"", ""},
-};
-
-static struct vio_driver nx842_driver = {
-	.name = MODULE_NAME,
-	.probe = nx842_probe,
-	.remove = __exit_p(nx842_remove),
-	.get_desired_dma = nx842_get_desired_dma,
-	.id_table = nx842_driver_ids,
-};
-
-static int __init nx842_init(void)
-{
-	struct nx842_devdata *new_devdata;
-	pr_info("Registering IBM Power 842 compression driver\n");
-
-	RCU_INIT_POINTER(devdata, NULL);
-	new_devdata = kzalloc(sizeof(*new_devdata), GFP_KERNEL);
-	if (!new_devdata) {
-		pr_err("Could not allocate memory for device data\n");
-		return -ENOMEM;
-	}
-	new_devdata->status = UNAVAILABLE;
-	RCU_INIT_POINTER(devdata, new_devdata);
-
-	return vio_register_driver(&nx842_driver);
 }
-
 module_init(nx842_init);
 
 static void __exit nx842_exit(void)
 {
-	struct nx842_devdata *old_devdata;
-	unsigned long flags;
-
-	pr_info("Exiting IBM Power 842 compression driver\n");
-	spin_lock_irqsave(&devdata_mutex, flags);
-	old_devdata = rcu_dereference_check(devdata,
-			lockdep_is_held(&devdata_mutex));
-	RCU_INIT_POINTER(devdata, NULL);
-	spin_unlock_irqrestore(&devdata_mutex, flags);
-	synchronize_rcu();
-	if (old_devdata)
-		dev_set_drvdata(old_devdata->dev, NULL);
-	kfree(old_devdata);
-	vio_unregister_driver(&nx842_driver);
+	nx842_platform_driver_put();
 }
-
 module_exit(nx842_exit);
-
-/*********************************
- * 842 software decompressor
-*********************************/
-typedef int (*sw842_template_op)(const char **, int *, unsigned char **,
-						struct sw842_fifo *);
-
-static int sw842_data8(const char **, int *, unsigned char **,
-						struct sw842_fifo *);
-static int sw842_data4(const char **, int *, unsigned char **,
-						struct sw842_fifo *);
-static int sw842_data2(const char **, int *, unsigned char **,
-						struct sw842_fifo *);
-static int sw842_ptr8(const char **, int *, unsigned char **,
-						struct sw842_fifo *);
-static int sw842_ptr4(const char **, int *, unsigned char **,
-						struct sw842_fifo *);
-static int sw842_ptr2(const char **, int *, unsigned char **,
-						struct sw842_fifo *);
-
-/* special templates */
-#define SW842_TMPL_REPEAT 0x1B
-#define SW842_TMPL_ZEROS 0x1C
-#define SW842_TMPL_EOF 0x1E
-
-static sw842_template_op sw842_tmpl_ops[26][4] = {
-	{ sw842_data8, NULL}, /* 0 (00000) */
-	{ sw842_data4, sw842_data2, sw842_ptr2,  NULL},
-	{ sw842_data4, sw842_ptr2,  sw842_data2, NULL},
-	{ sw842_data4, sw842_ptr2,  sw842_ptr2,  NULL},
-	{ sw842_data4, sw842_ptr4,  NULL},
-	{ sw842_data2, sw842_ptr2,  sw842_data4, NULL},
-	{ sw842_data2, sw842_ptr2,  sw842_data2, sw842_ptr2},
-	{ sw842_data2, sw842_ptr2,  sw842_ptr2,  sw842_data2},
-	{ sw842_data2, sw842_ptr2,  sw842_ptr2,  sw842_ptr2,},
-	{ sw842_data2, sw842_ptr2,  sw842_ptr4,  NULL},
-	{ sw842_ptr2,  sw842_data2, sw842_data4, NULL}, /* 10 (01010) */
-	{ sw842_ptr2,  sw842_data4, sw842_ptr2,  NULL},
-	{ sw842_ptr2,  sw842_data2, sw842_ptr2,  sw842_data2},
-	{ sw842_ptr2,  sw842_data2, sw842_ptr2,  sw842_ptr2},
-	{ sw842_ptr2,  sw842_data2, sw842_ptr4,  NULL},
-	{ sw842_ptr2,  sw842_ptr2,  sw842_data4, NULL},
-	{ sw842_ptr2,  sw842_ptr2,  sw842_data2, sw842_ptr2},
-	{ sw842_ptr2,  sw842_ptr2,  sw842_ptr2,  sw842_data2},
-	{ sw842_ptr2,  sw842_ptr2,  sw842_ptr2,  sw842_ptr2},
-	{ sw842_ptr2,  sw842_ptr2,  sw842_ptr4,  NULL},
-	{ sw842_ptr4,  sw842_data4, NULL}, /* 20 (10100) */
-	{ sw842_ptr4,  sw842_data2, sw842_ptr2,  NULL},
-	{ sw842_ptr4,  sw842_ptr2,  sw842_data2, NULL},
-	{ sw842_ptr4,  sw842_ptr2,  sw842_ptr2,  NULL},
-	{ sw842_ptr4,  sw842_ptr4,  NULL},
-	{ sw842_ptr8,  NULL}
-};
-
-/* Software decompress helpers */
-
-static uint8_t sw842_get_byte(const char *buf, int bit)
-{
-	uint8_t tmpl;
-	uint16_t tmp;
-	tmp = htons(*(uint16_t *)(buf));
-	tmp = (uint16_t)(tmp << bit);
-	tmp = ntohs(tmp);
-	memcpy(&tmpl, &tmp, 1);
-	return tmpl;
-}
-
-static uint8_t sw842_get_template(const char **buf, int *bit)
-{
-	uint8_t byte;
-	byte = sw842_get_byte(*buf, *bit);
-	byte = byte >> 3;
-	byte &= 0x1F;
-	*buf += (*bit + 5) / 8;
-	*bit = (*bit + 5) % 8;
-	return byte;
-}
-
-/* repeat_count happens to be 5-bit too (like the template) */
-static uint8_t sw842_get_repeat_count(const char **buf, int *bit)
-{
-	uint8_t byte;
-	byte = sw842_get_byte(*buf, *bit);
-	byte = byte >> 2;
-	byte &= 0x3F;
-	*buf += (*bit + 6) / 8;
-	*bit = (*bit + 6) % 8;
-	return byte;
-}
-
-static uint8_t sw842_get_ptr2(const char **buf, int *bit)
-{
-	uint8_t ptr;
-	ptr = sw842_get_byte(*buf, *bit);
-	(*buf)++;
-	return ptr;
-}
-
-static uint16_t sw842_get_ptr4(const char **buf, int *bit,
-		struct sw842_fifo *fifo)
-{
-	uint16_t ptr;
-	ptr = htons(*(uint16_t *)(*buf));
-	ptr = (uint16_t)(ptr << *bit);
-	ptr = ptr >> 7;
-	ptr &= 0x01FF;
-	*buf += (*bit + 9) / 8;
-	*bit = (*bit + 9) % 8;
-	return ptr;
-}
-
-static uint8_t sw842_get_ptr8(const char **buf, int *bit,
-		struct sw842_fifo *fifo)
-{
-	return sw842_get_ptr2(buf, bit);
-}
-
-/* Software decompress template ops */
-
-static int sw842_data8(const char **inbuf, int *inbit,
-		unsigned char **outbuf, struct sw842_fifo *fifo)
-{
-	int ret;
-
-	ret = sw842_data4(inbuf, inbit, outbuf, fifo);
-	if (ret)
-		return ret;
-	ret = sw842_data4(inbuf, inbit, outbuf, fifo);
-	return ret;
-}
-
-static int sw842_data4(const char **inbuf, int *inbit,
-		unsigned char **outbuf, struct sw842_fifo *fifo)
-{
-	int ret;
-
-	ret = sw842_data2(inbuf, inbit, outbuf, fifo);
-	if (ret)
-		return ret;
-	ret = sw842_data2(inbuf, inbit, outbuf, fifo);
-	return ret;
-}
-
-static int sw842_data2(const char **inbuf, int *inbit,
-		unsigned char **outbuf, struct sw842_fifo *fifo)
-{
-	**outbuf = sw842_get_byte(*inbuf, *inbit);
-	(*inbuf)++;
-	(*outbuf)++;
-	**outbuf = sw842_get_byte(*inbuf, *inbit);
-	(*inbuf)++;
-	(*outbuf)++;
-	return 0;
-}
-
-static int sw842_ptr8(const char **inbuf, int *inbit,
-		unsigned char **outbuf, struct sw842_fifo *fifo)
-{
-	uint8_t ptr;
-	ptr = sw842_get_ptr8(inbuf, inbit, fifo);
-	if (!fifo->f84_full && (ptr >= fifo->f8_count))
-		return 1;
-	memcpy(*outbuf, fifo->f8[ptr], 8);
-	*outbuf += 8;
-	return 0;
-}
-
-static int sw842_ptr4(const char **inbuf, int *inbit,
-		unsigned char **outbuf, struct sw842_fifo *fifo)
-{
-	uint16_t ptr;
-	ptr = sw842_get_ptr4(inbuf, inbit, fifo);
-	if (!fifo->f84_full && (ptr >= fifo->f4_count))
-		return 1;
-	memcpy(*outbuf, fifo->f4[ptr], 4);
-	*outbuf += 4;
-	return 0;
-}
-
-static int sw842_ptr2(const char **inbuf, int *inbit,
-		unsigned char **outbuf, struct sw842_fifo *fifo)
-{
-	uint8_t ptr;
-	ptr = sw842_get_ptr2(inbuf, inbit);
-	if (!fifo->f2_full && (ptr >= fifo->f2_count))
-		return 1;
-	memcpy(*outbuf, fifo->f2[ptr], 2);
-	*outbuf += 2;
-	return 0;
-}
-
-static void sw842_copy_to_fifo(const char *buf, struct sw842_fifo *fifo)
-{
-	unsigned char initial_f2count = fifo->f2_count;
-
-	memcpy(fifo->f8[fifo->f8_count], buf, 8);
-	fifo->f4_count += 2;
-	fifo->f8_count += 1;
-
-	if (!fifo->f84_full && fifo->f4_count >= 512) {
-		fifo->f84_full = 1;
-		fifo->f4_count /= 512;
-	}
-
-	memcpy(fifo->f2[fifo->f2_count++], buf, 2);
-	memcpy(fifo->f2[fifo->f2_count++], buf + 2, 2);
-	memcpy(fifo->f2[fifo->f2_count++], buf + 4, 2);
-	memcpy(fifo->f2[fifo->f2_count++], buf + 6, 2);
-	if (fifo->f2_count < initial_f2count)
-		fifo->f2_full = 1;
-}
-
-static int sw842_decompress(const unsigned char *src, int srclen,
-			unsigned char *dst, int *destlen,
-			const void *wrkmem)
-{
-	uint8_t tmpl;
-	const char *inbuf;
-	int inbit = 0;
-	unsigned char *outbuf, *outbuf_end, *origbuf, *prevbuf;
-	const char *inbuf_end;
-	sw842_template_op op;
-	int opindex;
-	int i, repeat_count;
-	struct sw842_fifo *fifo;
-	int ret = 0;
-
-	fifo = &((struct nx842_workmem *)(wrkmem))->swfifo;
-	memset(fifo, 0, sizeof(*fifo));
-
-	origbuf = NULL;
-	inbuf = src;
-	inbuf_end = src + srclen;
-	outbuf = dst;
-	outbuf_end = dst + *destlen;
-
-	while ((tmpl = sw842_get_template(&inbuf, &inbit)) != SW842_TMPL_EOF) {
-		if (inbuf >= inbuf_end) {
-			ret = -EINVAL;
-			goto out;
-		}
-
-		opindex = 0;
-		prevbuf = origbuf;
-		origbuf = outbuf;
-		switch (tmpl) {
-		case SW842_TMPL_REPEAT:
-			if (prevbuf == NULL) {
-				ret = -EINVAL;
-				goto out;
-			}
-
-			repeat_count = sw842_get_repeat_count(&inbuf,
-								&inbit) + 1;
-
-			/* Did the repeat count advance past the end of input */
-			if (inbuf > inbuf_end) {
-				ret = -EINVAL;
-				goto out;
-			}
-
-			for (i = 0; i < repeat_count; i++) {
-				/* Would this overflow the output buffer */
-				if ((outbuf + 8) > outbuf_end) {
-					ret = -ENOSPC;
-					goto out;
-				}
-
-				memcpy(outbuf, prevbuf, 8);
-				sw842_copy_to_fifo(outbuf, fifo);
-				outbuf += 8;
-			}
-			break;
-
-		case SW842_TMPL_ZEROS:
-			/* Would this overflow the output buffer */
-			if ((outbuf + 8) > outbuf_end) {
-				ret = -ENOSPC;
-				goto out;
-			}
-
-			memset(outbuf, 0, 8);
-			sw842_copy_to_fifo(outbuf, fifo);
-			outbuf += 8;
-			break;
-
-		default:
-			if (tmpl > 25) {
-				ret = -EINVAL;
-				goto out;
-			}
-
-			/* Does this go past the end of the input buffer */
-			if ((inbuf + 2) > inbuf_end) {
-				ret = -EINVAL;
-				goto out;
-			}
-
-			/* Would this overflow the output buffer */
-			if ((outbuf + 8) > outbuf_end) {
-				ret = -ENOSPC;
-				goto out;
-			}
-
-			while (opindex < 4 &&
-				(op = sw842_tmpl_ops[tmpl][opindex++])
-					!= NULL) {
-				ret = (*op)(&inbuf, &inbit, &outbuf, fifo);
-				if (ret) {
-					ret = -EINVAL;
-					goto out;
-				}
-				sw842_copy_to_fifo(origbuf, fifo);
-			}
-		}
-	}
-
-out:
-	if (!ret)
-		*destlen = (unsigned int)(outbuf - dst);
-	else
-		*destlen = 0;
-
-	return ret;
-}
diff --git a/drivers/crypto/nx/nx-842.h b/drivers/crypto/nx/nx-842.h
new file mode 100644
index 000000000000..ac0ea79d0f8b
--- /dev/null
+++ b/drivers/crypto/nx/nx-842.h
@@ -0,0 +1,144 @@
+
+#ifndef __NX_842_H__
+#define __NX_842_H__
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/sw842.h>
+#include <linux/of.h>
+#include <linux/slab.h>
+#include <linux/io.h>
+#include <linux/mm.h>
+#include <linux/ratelimit.h>
+
+/* Restrictions on Data Descriptor List (DDL) and Entry (DDE) buffers
+ *
+ * From NX P8 workbook, sec 4.9.1 "842 details"
+ *   Each DDE buffer is 128 byte aligned
+ *   Each DDE buffer size is a multiple of 32 bytes (except the last)
+ *   The last DDE buffer size is a multiple of 8 bytes
+ */
+#define DDE_BUFFER_ALIGN	(128)
+#define DDE_BUFFER_SIZE_MULT	(32)
+#define DDE_BUFFER_LAST_MULT	(8)
+
+/* Arbitrary DDL length limit
+ * Allows max buffer size of MAX-1 to MAX pages
+ * (depending on alignment)
+ */
+#define DDL_LEN_MAX		(17)
+
+/* CCW 842 CI/FC masks
+ * NX P8 workbook, section 4.3.1, figure 4-6
+ * "CI/FC Boundary by NX CT type"
+ */
+#define CCW_CI_842		(0x00003ff8)
+#define CCW_FC_842		(0x00000007)
+
+/* CCW Function Codes (FC) for 842
+ * NX P8 workbook, section 4.9, table 4-28
+ * "Function Code Definitions for 842 Memory Compression"
+ */
+#define CCW_FC_842_COMP_NOCRC	(0)
+#define CCW_FC_842_COMP_CRC	(1)
+#define CCW_FC_842_DECOMP_NOCRC	(2)
+#define CCW_FC_842_DECOMP_CRC	(3)
+#define CCW_FC_842_MOVE		(4)
+
+/* CSB CC Error Types for 842
+ * NX P8 workbook, section 4.10.3, table 4-30
+ * "Reported Error Types Summary Table"
+ */
+/* These are all duplicates of existing codes defined in icswx.h. */
+#define CSB_CC_TRANSLATION_DUP1	(80)
+#define CSB_CC_TRANSLATION_DUP2	(82)
+#define CSB_CC_TRANSLATION_DUP3	(84)
+#define CSB_CC_TRANSLATION_DUP4	(86)
+#define CSB_CC_TRANSLATION_DUP5	(92)
+#define CSB_CC_TRANSLATION_DUP6	(94)
+#define CSB_CC_PROTECTION_DUP1	(81)
+#define CSB_CC_PROTECTION_DUP2	(83)
+#define CSB_CC_PROTECTION_DUP3	(85)
+#define CSB_CC_PROTECTION_DUP4	(87)
+#define CSB_CC_PROTECTION_DUP5	(93)
+#define CSB_CC_PROTECTION_DUP6	(95)
+#define CSB_CC_RD_EXTERNAL_DUP1	(89)
+#define CSB_CC_RD_EXTERNAL_DUP2	(90)
+#define CSB_CC_RD_EXTERNAL_DUP3	(91)
+/* These are specific to NX */
+/* 842 codes */
+#define CSB_CC_TPBC_GT_SPBC	(64) /* no error, but >1 comp ratio */
+#define CSB_CC_CRC_MISMATCH	(65) /* decomp crc mismatch */
+#define CSB_CC_TEMPL_INVALID	(66) /* decomp invalid template value */
+#define CSB_CC_TEMPL_OVERFLOW	(67) /* decomp template shows data after end */
+/* sym crypt codes */
+#define CSB_CC_DECRYPT_OVERFLOW	(64)
+/* asym crypt codes */
+#define CSB_CC_MINV_OVERFLOW	(128)
+/* These are reserved for hypervisor use */
+#define CSB_CC_HYP_RESERVE_START	(240)
+#define CSB_CC_HYP_RESERVE_END		(253)
+#define CSB_CC_HYP_NO_HW		(254)
+#define CSB_CC_HYP_HANG_ABORTED		(255)
+
+/* CCB Completion Modes (CM) for 842
+ * NX P8 workbook, section 4.3, figure 4-5
+ * "CRB Details - Normal Cop_Req (CL=00, C=1)"
+ */
+#define CCB_CM_EXTRA_WRITE	(CCB_CM0_ALL_COMPLETIONS & CCB_CM12_STORE)
+#define CCB_CM_INTERRUPT	(CCB_CM0_ALL_COMPLETIONS & CCB_CM12_INTERRUPT)
+
+#define LEN_ON_SIZE(pa, size)	((size) - ((pa) & ((size) - 1)))
+#define LEN_ON_PAGE(pa)		LEN_ON_SIZE(pa, PAGE_SIZE)
+
+static inline unsigned long nx842_get_pa(void *addr)
+{
+	if (!is_vmalloc_addr(addr))
+		return __pa(addr);
+
+	return page_to_phys(vmalloc_to_page(addr)) + offset_in_page(addr);
+}
+
+/* Get/Set bit fields */
+#define MASK_LSH(m)		(__builtin_ffsl(m) - 1)
+#define GET_FIELD(v, m)		(((v) & (m)) >> MASK_LSH(m))
+#define SET_FIELD(v, m, val)	(((v) & ~(m)) | (((val) << MASK_LSH(m)) & (m)))
+
+struct nx842_constraints {
+	int alignment;
+	int multiple;
+	int minimum;
+	int maximum;
+};
+
+struct nx842_driver {
+	char *name;
+	struct module *owner;
+	size_t workmem_size;
+
+	struct nx842_constraints *constraints;
+
+	int (*compress)(const unsigned char *in, unsigned int in_len,
+			unsigned char *out, unsigned int *out_len,
+			void *wrkmem);
+	int (*decompress)(const unsigned char *in, unsigned int in_len,
+			  unsigned char *out, unsigned int *out_len,
+			  void *wrkmem);
+};
+
+struct nx842_driver *nx842_platform_driver(void);
+bool nx842_platform_driver_set(struct nx842_driver *driver);
+void nx842_platform_driver_unset(struct nx842_driver *driver);
+bool nx842_platform_driver_get(void);
+void nx842_platform_driver_put(void);
+
+size_t nx842_workmem_size(void);
+
+int nx842_constraints(struct nx842_constraints *constraints);
+
+int nx842_compress(const unsigned char *in, unsigned int in_len,
+		   unsigned char *out, unsigned int *out_len, void *wrkmem);
+int nx842_decompress(const unsigned char *in, unsigned int in_len,
+		     unsigned char *out, unsigned int *out_len, void *wrkmem);
+
+#endif /* __NX_842_H__ */
diff --git a/drivers/crypto/nx/nx-aes-gcm.c b/drivers/crypto/nx/nx-aes-gcm.c
index 88c562434bc0..08ac6d48688c 100644
--- a/drivers/crypto/nx/nx-aes-gcm.c
+++ b/drivers/crypto/nx/nx-aes-gcm.c
@@ -93,17 +93,6 @@ out:
 	return rc;
 }
 
-static int gcm_aes_nx_setauthsize(struct crypto_aead *tfm,
-				  unsigned int authsize)
-{
-	if (authsize > crypto_aead_alg(tfm)->maxauthsize)
-		return -EINVAL;
-
-	crypto_aead_crt(tfm)->authsize = authsize;
-
-	return 0;
-}
-
 static int gcm4106_aes_nx_setauthsize(struct crypto_aead *tfm,
 				      unsigned int authsize)
 {
@@ -116,8 +105,6 @@ static int gcm4106_aes_nx_setauthsize(struct crypto_aead *tfm,
 		return -EINVAL;
 	}
 
-	crypto_aead_crt(tfm)->authsize = authsize;
-
 	return 0;
 }
 
@@ -134,7 +121,7 @@ static int nx_gca(struct nx_crypto_ctx  *nx_ctx,
 	unsigned int max_sg_len;
 
 	if (nbytes <= AES_BLOCK_SIZE) {
-		scatterwalk_start(&walk, req->assoc);
+		scatterwalk_start(&walk, req->src);
 		scatterwalk_copychunks(out, &walk, nbytes, SCATTERWALK_FROM_SG);
 		scatterwalk_done(&walk, SCATTERWALK_FROM_SG, 0);
 		return 0;
@@ -159,7 +146,7 @@ static int nx_gca(struct nx_crypto_ctx  *nx_ctx,
 				   NX_PAGE_SIZE * (max_sg_len - 1));
 
 		nx_sg = nx_walk_and_build(nx_ctx->in_sg, max_sg_len,
-					  req->assoc, processed, &to_process);
+					  req->src, processed, &to_process);
 
 		if ((to_process + processed) < nbytes)
 			NX_CPB_FDM(csbcpb_aead) |= NX_FDM_INTERMEDIATE;
@@ -225,7 +212,7 @@ static int gmac(struct aead_request *req, struct blkcipher_desc *desc)
 				   NX_PAGE_SIZE * (max_sg_len - 1));
 
 		nx_sg = nx_walk_and_build(nx_ctx->in_sg, max_sg_len,
-					  req->assoc, processed, &to_process);
+					  req->src, processed, &to_process);
 
 		if ((to_process + processed) < nbytes)
 			NX_CPB_FDM(csbcpb) |= NX_FDM_INTERMEDIATE;
@@ -377,7 +364,8 @@ static int gcm_aes_nx_crypt(struct aead_request *req, int enc)
 		csbcpb->cpb.aes_gcm.bit_length_data = nbytes * 8;
 		desc.tfm = (struct crypto_blkcipher *) req->base.tfm;
 		rc = nx_build_sg_lists(nx_ctx, &desc, req->dst,
-				       req->src, &to_process, processed,
+				       req->src, &to_process,
+				       processed + req->assoclen,
 				       csbcpb->cpb.aes_gcm.iv_or_cnt);
 
 		if (rc)
@@ -412,17 +400,19 @@ static int gcm_aes_nx_crypt(struct aead_request *req, int enc)
 mac:
 	if (enc) {
 		/* copy out the auth tag */
-		scatterwalk_map_and_copy(csbcpb->cpb.aes_gcm.out_pat_or_mac,
-				 req->dst, nbytes,
-				 crypto_aead_authsize(crypto_aead_reqtfm(req)),
-				 SCATTERWALK_TO_SG);
+		scatterwalk_map_and_copy(
+			csbcpb->cpb.aes_gcm.out_pat_or_mac,
+			req->dst, req->assoclen + nbytes,
+			crypto_aead_authsize(crypto_aead_reqtfm(req)),
+			SCATTERWALK_TO_SG);
 	} else {
 		u8 *itag = nx_ctx->priv.gcm.iauth_tag;
 		u8 *otag = csbcpb->cpb.aes_gcm.out_pat_or_mac;
 
-		scatterwalk_map_and_copy(itag, req->src, nbytes,
-				 crypto_aead_authsize(crypto_aead_reqtfm(req)),
-				 SCATTERWALK_FROM_SG);
+		scatterwalk_map_and_copy(
+			itag, req->src, req->assoclen + nbytes,
+			crypto_aead_authsize(crypto_aead_reqtfm(req)),
+			SCATTERWALK_FROM_SG);
 		rc = memcmp(itag, otag,
 			    crypto_aead_authsize(crypto_aead_reqtfm(req))) ?
 		     -EBADMSG : 0;
@@ -481,45 +471,39 @@ static int gcm4106_aes_nx_decrypt(struct aead_request *req)
  * during encrypt/decrypt doesn't solve this problem, because it calls
  * blkcipher_walk_done under the covers, which doesn't use walk->blocksize,
  * but instead uses this tfm->blocksize. */
-struct crypto_alg nx_gcm_aes_alg = {
-	.cra_name        = "gcm(aes)",
-	.cra_driver_name = "gcm-aes-nx",
-	.cra_priority    = 300,
-	.cra_flags       = CRYPTO_ALG_TYPE_AEAD,
-	.cra_blocksize   = 1,
-	.cra_ctxsize     = sizeof(struct nx_crypto_ctx),
-	.cra_type        = &crypto_aead_type,
-	.cra_module      = THIS_MODULE,
-	.cra_init        = nx_crypto_ctx_aes_gcm_init,
-	.cra_exit        = nx_crypto_ctx_exit,
-	.cra_aead = {
-		.ivsize      = AES_BLOCK_SIZE,
-		.maxauthsize = AES_BLOCK_SIZE,
-		.setkey      = gcm_aes_nx_set_key,
-		.setauthsize = gcm_aes_nx_setauthsize,
-		.encrypt     = gcm_aes_nx_encrypt,
-		.decrypt     = gcm_aes_nx_decrypt,
-	}
+struct aead_alg nx_gcm_aes_alg = {
+	.base = {
+		.cra_name        = "gcm(aes)",
+		.cra_driver_name = "gcm-aes-nx",
+		.cra_priority    = 300,
+		.cra_blocksize   = 1,
+		.cra_ctxsize     = sizeof(struct nx_crypto_ctx),
+		.cra_module      = THIS_MODULE,
+	},
+	.init        = nx_crypto_ctx_aes_gcm_init,
+	.exit        = nx_crypto_ctx_aead_exit,
+	.ivsize      = 12,
+	.maxauthsize = AES_BLOCK_SIZE,
+	.setkey      = gcm_aes_nx_set_key,
+	.encrypt     = gcm_aes_nx_encrypt,
+	.decrypt     = gcm_aes_nx_decrypt,
 };
 
-struct crypto_alg nx_gcm4106_aes_alg = {
-	.cra_name        = "rfc4106(gcm(aes))",
-	.cra_driver_name = "rfc4106-gcm-aes-nx",
-	.cra_priority    = 300,
-	.cra_flags       = CRYPTO_ALG_TYPE_AEAD,
-	.cra_blocksize   = 1,
-	.cra_ctxsize     = sizeof(struct nx_crypto_ctx),
-	.cra_type        = &crypto_nivaead_type,
-	.cra_module      = THIS_MODULE,
-	.cra_init        = nx_crypto_ctx_aes_gcm_init,
-	.cra_exit        = nx_crypto_ctx_exit,
-	.cra_aead = {
-		.ivsize      = 8,
-		.maxauthsize = AES_BLOCK_SIZE,
-		.geniv       = "seqiv",
-		.setkey      = gcm4106_aes_nx_set_key,
-		.setauthsize = gcm4106_aes_nx_setauthsize,
-		.encrypt     = gcm4106_aes_nx_encrypt,
-		.decrypt     = gcm4106_aes_nx_decrypt,
-	}
+struct aead_alg nx_gcm4106_aes_alg = {
+	.base = {
+		.cra_name        = "rfc4106(gcm(aes))",
+		.cra_driver_name = "rfc4106-gcm-aes-nx",
+		.cra_priority    = 300,
+		.cra_blocksize   = 1,
+		.cra_ctxsize     = sizeof(struct nx_crypto_ctx),
+		.cra_module      = THIS_MODULE,
+	},
+	.init        = nx_crypto_ctx_aes_gcm_init,
+	.exit        = nx_crypto_ctx_aead_exit,
+	.ivsize      = 8,
+	.maxauthsize = AES_BLOCK_SIZE,
+	.setkey      = gcm4106_aes_nx_set_key,
+	.setauthsize = gcm4106_aes_nx_setauthsize,
+	.encrypt     = gcm4106_aes_nx_encrypt,
+	.decrypt     = gcm4106_aes_nx_decrypt,
 };
diff --git a/drivers/crypto/nx/nx-sha256.c b/drivers/crypto/nx/nx-sha256.c
index 23621da624c3..4e91bdb83c59 100644
--- a/drivers/crypto/nx/nx-sha256.c
+++ b/drivers/crypto/nx/nx-sha256.c
@@ -33,8 +33,9 @@ static int nx_sha256_init(struct shash_desc *desc)
 {
 	struct sha256_state *sctx = shash_desc_ctx(desc);
 	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(&desc->tfm->base);
+	struct nx_sg *out_sg;
 	int len;
-	int rc;
+	u32 max_sg_len;
 
 	nx_ctx_init(nx_ctx, HCOP_FC_SHA);
 
@@ -44,15 +45,18 @@ static int nx_sha256_init(struct shash_desc *desc)
 
 	NX_CPB_SET_DIGEST_SIZE(nx_ctx->csbcpb, NX_DS_SHA256);
 
+	max_sg_len = min_t(u64, nx_ctx->ap->sglen,
+			nx_driver.of.max_sg_len/sizeof(struct nx_sg));
+	max_sg_len = min_t(u64, max_sg_len,
+			nx_ctx->ap->databytelen/NX_PAGE_SIZE);
+
 	len = SHA256_DIGEST_SIZE;
-	rc = nx_sha_build_sg_list(nx_ctx, nx_ctx->out_sg,
-				  &nx_ctx->op.outlen,
-				  &len,
-				  (u8 *) sctx->state,
-				  NX_DS_SHA256);
+	out_sg = nx_build_sg_list(nx_ctx->out_sg, (u8 *)sctx->state,
+				  &len, max_sg_len);
+	nx_ctx->op.outlen = (nx_ctx->out_sg - out_sg) * sizeof(struct nx_sg);
 
-	if (rc)
-		goto out;
+	if (len != SHA256_DIGEST_SIZE)
+		return -EINVAL;
 
 	sctx->state[0] = __cpu_to_be32(SHA256_H0);
 	sctx->state[1] = __cpu_to_be32(SHA256_H1);
@@ -64,7 +68,6 @@ static int nx_sha256_init(struct shash_desc *desc)
 	sctx->state[7] = __cpu_to_be32(SHA256_H7);
 	sctx->count = 0;
 
-out:
 	return 0;
 }
 
@@ -74,10 +77,12 @@ static int nx_sha256_update(struct shash_desc *desc, const u8 *data,
 	struct sha256_state *sctx = shash_desc_ctx(desc);
 	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(&desc->tfm->base);
 	struct nx_csbcpb *csbcpb = (struct nx_csbcpb *)nx_ctx->csbcpb;
+	struct nx_sg *in_sg;
 	u64 to_process = 0, leftover, total;
 	unsigned long irq_flags;
 	int rc = 0;
 	int data_len;
+	u32 max_sg_len;
 	u64 buf_len = (sctx->count % SHA256_BLOCK_SIZE);
 
 	spin_lock_irqsave(&nx_ctx->lock, irq_flags);
@@ -97,6 +102,12 @@ static int nx_sha256_update(struct shash_desc *desc, const u8 *data,
 	NX_CPB_FDM(csbcpb) |= NX_FDM_INTERMEDIATE;
 	NX_CPB_FDM(csbcpb) |= NX_FDM_CONTINUATION;
 
+	in_sg = nx_ctx->in_sg;
+	max_sg_len = min_t(u64, nx_ctx->ap->sglen,
+			nx_driver.of.max_sg_len/sizeof(struct nx_sg));
+	max_sg_len = min_t(u64, max_sg_len,
+			nx_ctx->ap->databytelen/NX_PAGE_SIZE);
+
 	do {
 		/*
 		 * to_process: the SHA256_BLOCK_SIZE data chunk to process in
@@ -108,25 +119,22 @@ static int nx_sha256_update(struct shash_desc *desc, const u8 *data,
 
 		if (buf_len) {
 			data_len = buf_len;
-			rc = nx_sha_build_sg_list(nx_ctx, nx_ctx->in_sg,
-						  &nx_ctx->op.inlen,
-						  &data_len,
-						  (u8 *) sctx->buf,
-						  NX_DS_SHA256);
+			in_sg = nx_build_sg_list(nx_ctx->in_sg,
+						 (u8 *) sctx->buf,
+						 &data_len,
+						 max_sg_len);
 
-			if (rc || data_len != buf_len)
+			if (data_len != buf_len) {
+				rc = -EINVAL;
 				goto out;
+			}
 		}
 
 		data_len = to_process - buf_len;
-		rc = nx_sha_build_sg_list(nx_ctx, nx_ctx->in_sg,
-					  &nx_ctx->op.inlen,
-					  &data_len,
-					  (u8 *) data,
-					  NX_DS_SHA256);
+		in_sg = nx_build_sg_list(in_sg, (u8 *) data,
+					 &data_len, max_sg_len);
 
-		if (rc)
-			goto out;
+		nx_ctx->op.inlen = (nx_ctx->in_sg - in_sg) * sizeof(struct nx_sg);
 
 		to_process = (data_len + buf_len);
 		leftover = total - to_process;
@@ -173,12 +181,19 @@ static int nx_sha256_final(struct shash_desc *desc, u8 *out)
 	struct sha256_state *sctx = shash_desc_ctx(desc);
 	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(&desc->tfm->base);
 	struct nx_csbcpb *csbcpb = (struct nx_csbcpb *)nx_ctx->csbcpb;
+	struct nx_sg *in_sg, *out_sg;
 	unsigned long irq_flags;
-	int rc;
+	u32 max_sg_len;
+	int rc = 0;
 	int len;
 
 	spin_lock_irqsave(&nx_ctx->lock, irq_flags);
 
+	max_sg_len = min_t(u64, nx_ctx->ap->sglen,
+			nx_driver.of.max_sg_len/sizeof(struct nx_sg));
+	max_sg_len = min_t(u64, max_sg_len,
+			nx_ctx->ap->databytelen/NX_PAGE_SIZE);
+
 	/* final is represented by continuing the operation and indicating that
 	 * this is not an intermediate operation */
 	if (sctx->count >= SHA256_BLOCK_SIZE) {
@@ -195,25 +210,24 @@ static int nx_sha256_final(struct shash_desc *desc, u8 *out)
 	csbcpb->cpb.sha256.message_bit_length = (u64) (sctx->count * 8);
 
 	len = sctx->count & (SHA256_BLOCK_SIZE - 1);
-	rc = nx_sha_build_sg_list(nx_ctx, nx_ctx->in_sg,
-				  &nx_ctx->op.inlen,
-				  &len,
-				  (u8 *) sctx->buf,
-				  NX_DS_SHA256);
+	in_sg = nx_build_sg_list(nx_ctx->in_sg, (u8 *) sctx->buf,
+				 &len, max_sg_len);
 
-	if (rc || len != (sctx->count & (SHA256_BLOCK_SIZE - 1)))
+	if (len != (sctx->count & (SHA256_BLOCK_SIZE - 1))) {
+		rc = -EINVAL;
 		goto out;
+	}
 
 	len = SHA256_DIGEST_SIZE;
-	rc = nx_sha_build_sg_list(nx_ctx, nx_ctx->out_sg,
-				  &nx_ctx->op.outlen,
-				  &len,
-				  out,
-				  NX_DS_SHA256);
+	out_sg = nx_build_sg_list(nx_ctx->out_sg, out, &len, max_sg_len);
 
-	if (rc || len != SHA256_DIGEST_SIZE)
+	if (len != SHA256_DIGEST_SIZE) {
+		rc = -EINVAL;
 		goto out;
+	}
 
+	nx_ctx->op.inlen = (nx_ctx->in_sg - in_sg) * sizeof(struct nx_sg);
+	nx_ctx->op.outlen = (nx_ctx->out_sg - out_sg) * sizeof(struct nx_sg);
 	if (!nx_ctx->op.outlen) {
 		rc = -EINVAL;
 		goto out;
diff --git a/drivers/crypto/nx/nx-sha512.c b/drivers/crypto/nx/nx-sha512.c
index b3adf1022673..e6a58d2ee628 100644
--- a/drivers/crypto/nx/nx-sha512.c
+++ b/drivers/crypto/nx/nx-sha512.c
@@ -32,8 +32,9 @@ static int nx_sha512_init(struct shash_desc *desc)
 {
 	struct sha512_state *sctx = shash_desc_ctx(desc);
 	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(&desc->tfm->base);
+	struct nx_sg *out_sg;
 	int len;
-	int rc;
+	u32 max_sg_len;
 
 	nx_ctx_init(nx_ctx, HCOP_FC_SHA);
 
@@ -43,15 +44,18 @@ static int nx_sha512_init(struct shash_desc *desc)
 
 	NX_CPB_SET_DIGEST_SIZE(nx_ctx->csbcpb, NX_DS_SHA512);
 
+	max_sg_len = min_t(u64, nx_ctx->ap->sglen,
+			nx_driver.of.max_sg_len/sizeof(struct nx_sg));
+	max_sg_len = min_t(u64, max_sg_len,
+			nx_ctx->ap->databytelen/NX_PAGE_SIZE);
+
 	len = SHA512_DIGEST_SIZE;
-	rc = nx_sha_build_sg_list(nx_ctx, nx_ctx->out_sg,
-				  &nx_ctx->op.outlen,
-				  &len,
-				  (u8 *)sctx->state,
-				  NX_DS_SHA512);
+	out_sg = nx_build_sg_list(nx_ctx->out_sg, (u8 *)sctx->state,
+				  &len, max_sg_len);
+	nx_ctx->op.outlen = (nx_ctx->out_sg - out_sg) * sizeof(struct nx_sg);
 
-	if (rc || len != SHA512_DIGEST_SIZE)
-		goto out;
+	if (len != SHA512_DIGEST_SIZE)
+		return -EINVAL;
 
 	sctx->state[0] = __cpu_to_be64(SHA512_H0);
 	sctx->state[1] = __cpu_to_be64(SHA512_H1);
@@ -63,7 +67,6 @@ static int nx_sha512_init(struct shash_desc *desc)
 	sctx->state[7] = __cpu_to_be64(SHA512_H7);
 	sctx->count[0] = 0;
 
-out:
 	return 0;
 }
 
@@ -73,10 +76,12 @@ static int nx_sha512_update(struct shash_desc *desc, const u8 *data,
 	struct sha512_state *sctx = shash_desc_ctx(desc);
 	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(&desc->tfm->base);
 	struct nx_csbcpb *csbcpb = (struct nx_csbcpb *)nx_ctx->csbcpb;
+	struct nx_sg *in_sg;
 	u64 to_process, leftover = 0, total;
 	unsigned long irq_flags;
 	int rc = 0;
 	int data_len;
+	u32 max_sg_len;
 	u64 buf_len = (sctx->count[0] % SHA512_BLOCK_SIZE);
 
 	spin_lock_irqsave(&nx_ctx->lock, irq_flags);
@@ -96,6 +101,12 @@ static int nx_sha512_update(struct shash_desc *desc, const u8 *data,
 	NX_CPB_FDM(csbcpb) |= NX_FDM_INTERMEDIATE;
 	NX_CPB_FDM(csbcpb) |= NX_FDM_CONTINUATION;
 
+	in_sg = nx_ctx->in_sg;
+	max_sg_len = min_t(u64, nx_ctx->ap->sglen,
+			nx_driver.of.max_sg_len/sizeof(struct nx_sg));
+	max_sg_len = min_t(u64, max_sg_len,
+			nx_ctx->ap->databytelen/NX_PAGE_SIZE);
+
 	do {
 		/*
 		 * to_process: the SHA512_BLOCK_SIZE data chunk to process in
@@ -108,25 +119,26 @@ static int nx_sha512_update(struct shash_desc *desc, const u8 *data,
 
 		if (buf_len) {
 			data_len = buf_len;
-			rc = nx_sha_build_sg_list(nx_ctx, nx_ctx->in_sg,
-						  &nx_ctx->op.inlen,
-						  &data_len,
-						  (u8 *) sctx->buf,
-						  NX_DS_SHA512);
+			in_sg = nx_build_sg_list(nx_ctx->in_sg,
+						 (u8 *) sctx->buf,
+						 &data_len, max_sg_len);
 
-			if (rc || data_len != buf_len)
+			if (data_len != buf_len) {
+				rc = -EINVAL;
 				goto out;
+			}
 		}
 
 		data_len = to_process - buf_len;
-		rc = nx_sha_build_sg_list(nx_ctx, nx_ctx->in_sg,
-					  &nx_ctx->op.inlen,
-					  &data_len,
-					  (u8 *) data,
-					  NX_DS_SHA512);
+		in_sg = nx_build_sg_list(in_sg, (u8 *) data,
+					 &data_len, max_sg_len);
 
-		if (rc || data_len != (to_process - buf_len))
+		nx_ctx->op.inlen = (nx_ctx->in_sg - in_sg) * sizeof(struct nx_sg);
+
+		if (data_len != (to_process - buf_len)) {
+			rc = -EINVAL;
 			goto out;
+		}
 
 		to_process = (data_len + buf_len);
 		leftover = total - to_process;
@@ -172,13 +184,20 @@ static int nx_sha512_final(struct shash_desc *desc, u8 *out)
 	struct sha512_state *sctx = shash_desc_ctx(desc);
 	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(&desc->tfm->base);
 	struct nx_csbcpb *csbcpb = (struct nx_csbcpb *)nx_ctx->csbcpb;
+	struct nx_sg *in_sg, *out_sg;
+	u32 max_sg_len;
 	u64 count0;
 	unsigned long irq_flags;
-	int rc;
+	int rc = 0;
 	int len;
 
 	spin_lock_irqsave(&nx_ctx->lock, irq_flags);
 
+	max_sg_len = min_t(u64, nx_ctx->ap->sglen,
+			nx_driver.of.max_sg_len/sizeof(struct nx_sg));
+	max_sg_len = min_t(u64, max_sg_len,
+			nx_ctx->ap->databytelen/NX_PAGE_SIZE);
+
 	/* final is represented by continuing the operation and indicating that
 	 * this is not an intermediate operation */
 	if (sctx->count[0] >= SHA512_BLOCK_SIZE) {
@@ -200,24 +219,20 @@ static int nx_sha512_final(struct shash_desc *desc, u8 *out)
 	csbcpb->cpb.sha512.message_bit_length_lo = count0;
 
 	len = sctx->count[0] & (SHA512_BLOCK_SIZE - 1);
-	rc = nx_sha_build_sg_list(nx_ctx, nx_ctx->in_sg,
-				  &nx_ctx->op.inlen,
-				  &len,
-				  (u8 *)sctx->buf,
-				  NX_DS_SHA512);
+	in_sg = nx_build_sg_list(nx_ctx->in_sg, sctx->buf, &len,
+				 max_sg_len);
 
-	if (rc || len != (sctx->count[0] & (SHA512_BLOCK_SIZE - 1)))
+	if (len != (sctx->count[0] & (SHA512_BLOCK_SIZE - 1))) {
+		rc = -EINVAL;
 		goto out;
+	}
 
 	len = SHA512_DIGEST_SIZE;
-	rc = nx_sha_build_sg_list(nx_ctx, nx_ctx->out_sg,
-				  &nx_ctx->op.outlen,
-				  &len,
-				  out,
-				  NX_DS_SHA512);
+	out_sg = nx_build_sg_list(nx_ctx->out_sg, out, &len,
+				 max_sg_len);
 
-	if (rc)
-		goto out;
+	nx_ctx->op.inlen = (nx_ctx->in_sg - in_sg) * sizeof(struct nx_sg);
+	nx_ctx->op.outlen = (nx_ctx->out_sg - out_sg) * sizeof(struct nx_sg);
 
 	if (!nx_ctx->op.outlen) {
 		rc = -EINVAL;
diff --git a/drivers/crypto/nx/nx.c b/drivers/crypto/nx/nx.c
index 1da6dc59d0dd..f6198f29a4a8 100644
--- a/drivers/crypto/nx/nx.c
+++ b/drivers/crypto/nx/nx.c
@@ -19,8 +19,8 @@
  * Author: Kent Yoder <yoder1@us.ibm.com>
  */
 
+#include <crypto/internal/aead.h>
 #include <crypto/internal/hash.h>
-#include <crypto/hash.h>
 #include <crypto/aes.h>
 #include <crypto/sha.h>
 #include <crypto/algapi.h>
@@ -29,10 +29,10 @@
 #include <linux/moduleparam.h>
 #include <linux/types.h>
 #include <linux/mm.h>
-#include <linux/crypto.h>
 #include <linux/scatterlist.h>
 #include <linux/device.h>
 #include <linux/of.h>
+#include <linux/types.h>
 #include <asm/hvcall.h>
 #include <asm/vio.h>
 
@@ -215,8 +215,15 @@ struct nx_sg *nx_walk_and_build(struct nx_sg       *nx_dst,
  * @delta:  is the amount we need to crop in order to bound the list.
  *
  */
-static long int trim_sg_list(struct nx_sg *sg, struct nx_sg *end, unsigned int delta)
+static long int trim_sg_list(struct nx_sg *sg,
+			     struct nx_sg *end,
+			     unsigned int delta,
+			     unsigned int *nbytes)
 {
+	long int oplen;
+	long int data_back;
+	unsigned int is_delta = delta;
+
 	while (delta && end > sg) {
 		struct nx_sg *last = end - 1;
 
@@ -228,54 +235,20 @@ static long int trim_sg_list(struct nx_sg *sg, struct nx_sg *end, unsigned int d
 			delta -= last->len;
 		}
 	}
-	return (sg - end) * sizeof(struct nx_sg);
-}
 
-/**
- * nx_sha_build_sg_list - walk and build sg list to sha modes
- *			  using right bounds and limits.
- * @nx_ctx: NX crypto context for the lists we're building
- * @nx_sg: current sg list in or out list
- * @op_len: current op_len to be used in order to build a sg list
- * @nbytes:  number or bytes to be processed
- * @offset: buf offset
- * @mode: SHA256 or SHA512
- */
-int nx_sha_build_sg_list(struct nx_crypto_ctx *nx_ctx,
-			  struct nx_sg 	      *nx_in_outsg,
-			  s64		      *op_len,
-			  unsigned int        *nbytes,
-			  u8 		      *offset,
-			  u32		      mode)
-{
-	unsigned int delta = 0;
-	unsigned int total = *nbytes;
-	struct nx_sg *nx_insg = nx_in_outsg;
-	unsigned int max_sg_len;
-
-	max_sg_len = min_t(u64, nx_ctx->ap->sglen,
-			nx_driver.of.max_sg_len/sizeof(struct nx_sg));
-	max_sg_len = min_t(u64, max_sg_len,
-			nx_ctx->ap->databytelen/NX_PAGE_SIZE);
-
-	*nbytes = min_t(u64, *nbytes, nx_ctx->ap->databytelen);
-	nx_insg = nx_build_sg_list(nx_insg, offset, nbytes, max_sg_len);
-
-	switch (mode) {
-	case NX_DS_SHA256:
-		if (*nbytes < total)
-			delta = *nbytes - (*nbytes & ~(SHA256_BLOCK_SIZE - 1));
-		break;
-	case NX_DS_SHA512:
-		if (*nbytes < total)
-			delta = *nbytes - (*nbytes & ~(SHA512_BLOCK_SIZE - 1));
-		break;
-	default:
-		return -EINVAL;
+	/* There are cases where we need to crop list in order to make it
+	 * a block size multiple, but we also need to align data. In order to
+	 * that we need to calculate how much we need to put back to be
+	 * processed
+	 */
+	oplen = (sg - end) * sizeof(struct nx_sg);
+	if (is_delta) {
+		data_back = (abs(oplen) / AES_BLOCK_SIZE) *  sg->len;
+		data_back = *nbytes - (data_back & ~(AES_BLOCK_SIZE - 1));
+		*nbytes -= data_back;
 	}
-	*op_len = trim_sg_list(nx_in_outsg, nx_insg, delta);
 
-	return 0;
+	return oplen;
 }
 
 /**
@@ -330,8 +303,8 @@ int nx_build_sg_lists(struct nx_crypto_ctx  *nx_ctx,
 	/* these lengths should be negative, which will indicate to phyp that
 	 * the input and output parameters are scatterlists, not linear
 	 * buffers */
-	nx_ctx->op.inlen = trim_sg_list(nx_ctx->in_sg, nx_insg, delta);
-	nx_ctx->op.outlen = trim_sg_list(nx_ctx->out_sg, nx_outsg, delta);
+	nx_ctx->op.inlen = trim_sg_list(nx_ctx->in_sg, nx_insg, delta, nbytes);
+	nx_ctx->op.outlen = trim_sg_list(nx_ctx->out_sg, nx_outsg, delta, nbytes);
 
 	return 0;
 }
@@ -426,6 +399,13 @@ static void nx_of_update_msc(struct device   *dev,
 				goto next_loop;
 			}
 
+			if (!trip->sglen || trip->databytelen < NX_PAGE_SIZE) {
+				dev_warn(dev, "bogus sglen/databytelen: "
+					 "%u/%u (ignored)\n", trip->sglen,
+					 trip->databytelen);
+				goto next_loop;
+			}
+
 			switch (trip->keybitlen) {
 			case 128:
 			case 160:
@@ -518,6 +498,72 @@ static void nx_of_init(struct device *dev, struct nx_of *props)
 		nx_of_update_msc(dev, p, props);
 }
 
+static bool nx_check_prop(struct device *dev, u32 fc, u32 mode, int slot)
+{
+	struct alg_props *props = &nx_driver.of.ap[fc][mode][slot];
+
+	if (!props->sglen || props->databytelen < NX_PAGE_SIZE) {
+		if (dev)
+			dev_warn(dev, "bogus sglen/databytelen for %u/%u/%u: "
+				 "%u/%u (ignored)\n", fc, mode, slot,
+				 props->sglen, props->databytelen);
+		return false;
+	}
+
+	return true;
+}
+
+static bool nx_check_props(struct device *dev, u32 fc, u32 mode)
+{
+	int i;
+
+	for (i = 0; i < 3; i++)
+		if (!nx_check_prop(dev, fc, mode, i))
+			return false;
+
+	return true;
+}
+
+static int nx_register_alg(struct crypto_alg *alg, u32 fc, u32 mode)
+{
+	return nx_check_props(&nx_driver.viodev->dev, fc, mode) ?
+	       crypto_register_alg(alg) : 0;
+}
+
+static int nx_register_aead(struct aead_alg *alg, u32 fc, u32 mode)
+{
+	return nx_check_props(&nx_driver.viodev->dev, fc, mode) ?
+	       crypto_register_aead(alg) : 0;
+}
+
+static int nx_register_shash(struct shash_alg *alg, u32 fc, u32 mode, int slot)
+{
+	return (slot >= 0 ? nx_check_prop(&nx_driver.viodev->dev,
+					  fc, mode, slot) :
+			    nx_check_props(&nx_driver.viodev->dev, fc, mode)) ?
+	       crypto_register_shash(alg) : 0;
+}
+
+static void nx_unregister_alg(struct crypto_alg *alg, u32 fc, u32 mode)
+{
+	if (nx_check_props(NULL, fc, mode))
+		crypto_unregister_alg(alg);
+}
+
+static void nx_unregister_aead(struct aead_alg *alg, u32 fc, u32 mode)
+{
+	if (nx_check_props(NULL, fc, mode))
+		crypto_unregister_aead(alg);
+}
+
+static void nx_unregister_shash(struct shash_alg *alg, u32 fc, u32 mode,
+				int slot)
+{
+	if (slot >= 0 ? nx_check_prop(NULL, fc, mode, slot) :
+			nx_check_props(NULL, fc, mode))
+		crypto_unregister_shash(alg);
+}
+
 /**
  * nx_register_algs - register algorithms with the crypto API
  *
@@ -542,72 +588,77 @@ static int nx_register_algs(void)
 
 	nx_driver.of.status = NX_OKAY;
 
-	rc = crypto_register_alg(&nx_ecb_aes_alg);
+	rc = nx_register_alg(&nx_ecb_aes_alg, NX_FC_AES, NX_MODE_AES_ECB);
 	if (rc)
 		goto out;
 
-	rc = crypto_register_alg(&nx_cbc_aes_alg);
+	rc = nx_register_alg(&nx_cbc_aes_alg, NX_FC_AES, NX_MODE_AES_CBC);
 	if (rc)
 		goto out_unreg_ecb;
 
-	rc = crypto_register_alg(&nx_ctr_aes_alg);
+	rc = nx_register_alg(&nx_ctr_aes_alg, NX_FC_AES, NX_MODE_AES_CTR);
 	if (rc)
 		goto out_unreg_cbc;
 
-	rc = crypto_register_alg(&nx_ctr3686_aes_alg);
+	rc = nx_register_alg(&nx_ctr3686_aes_alg, NX_FC_AES, NX_MODE_AES_CTR);
 	if (rc)
 		goto out_unreg_ctr;
 
-	rc = crypto_register_alg(&nx_gcm_aes_alg);
+	rc = nx_register_aead(&nx_gcm_aes_alg, NX_FC_AES, NX_MODE_AES_GCM);
 	if (rc)
 		goto out_unreg_ctr3686;
 
-	rc = crypto_register_alg(&nx_gcm4106_aes_alg);
+	rc = nx_register_aead(&nx_gcm4106_aes_alg, NX_FC_AES, NX_MODE_AES_GCM);
 	if (rc)
 		goto out_unreg_gcm;
 
-	rc = crypto_register_alg(&nx_ccm_aes_alg);
+	rc = nx_register_alg(&nx_ccm_aes_alg, NX_FC_AES, NX_MODE_AES_CCM);
 	if (rc)
 		goto out_unreg_gcm4106;
 
-	rc = crypto_register_alg(&nx_ccm4309_aes_alg);
+	rc = nx_register_alg(&nx_ccm4309_aes_alg, NX_FC_AES, NX_MODE_AES_CCM);
 	if (rc)
 		goto out_unreg_ccm;
 
-	rc = crypto_register_shash(&nx_shash_sha256_alg);
+	rc = nx_register_shash(&nx_shash_sha256_alg, NX_FC_SHA, NX_MODE_SHA,
+			       NX_PROPS_SHA256);
 	if (rc)
 		goto out_unreg_ccm4309;
 
-	rc = crypto_register_shash(&nx_shash_sha512_alg);
+	rc = nx_register_shash(&nx_shash_sha512_alg, NX_FC_SHA, NX_MODE_SHA,
+			       NX_PROPS_SHA512);
 	if (rc)
 		goto out_unreg_s256;
 
-	rc = crypto_register_shash(&nx_shash_aes_xcbc_alg);
+	rc = nx_register_shash(&nx_shash_aes_xcbc_alg,
+			       NX_FC_AES, NX_MODE_AES_XCBC_MAC, -1);
 	if (rc)
 		goto out_unreg_s512;
 
 	goto out;
 
 out_unreg_s512:
-	crypto_unregister_shash(&nx_shash_sha512_alg);
+	nx_unregister_shash(&nx_shash_sha512_alg, NX_FC_SHA, NX_MODE_SHA,
+			    NX_PROPS_SHA512);
 out_unreg_s256:
-	crypto_unregister_shash(&nx_shash_sha256_alg);
+	nx_unregister_shash(&nx_shash_sha256_alg, NX_FC_SHA, NX_MODE_SHA,
+			    NX_PROPS_SHA256);
 out_unreg_ccm4309:
-	crypto_unregister_alg(&nx_ccm4309_aes_alg);
+	nx_unregister_alg(&nx_ccm4309_aes_alg, NX_FC_AES, NX_MODE_AES_CCM);
 out_unreg_ccm:
-	crypto_unregister_alg(&nx_ccm_aes_alg);
+	nx_unregister_alg(&nx_ccm_aes_alg, NX_FC_AES, NX_MODE_AES_CCM);
 out_unreg_gcm4106:
-	crypto_unregister_alg(&nx_gcm4106_aes_alg);
+	nx_unregister_aead(&nx_gcm4106_aes_alg, NX_FC_AES, NX_MODE_AES_GCM);
 out_unreg_gcm:
-	crypto_unregister_alg(&nx_gcm_aes_alg);
+	nx_unregister_aead(&nx_gcm_aes_alg, NX_FC_AES, NX_MODE_AES_GCM);
 out_unreg_ctr3686:
-	crypto_unregister_alg(&nx_ctr3686_aes_alg);
+	nx_unregister_alg(&nx_ctr3686_aes_alg, NX_FC_AES, NX_MODE_AES_CTR);
 out_unreg_ctr:
-	crypto_unregister_alg(&nx_ctr_aes_alg);
+	nx_unregister_alg(&nx_ctr_aes_alg, NX_FC_AES, NX_MODE_AES_CTR);
 out_unreg_cbc:
-	crypto_unregister_alg(&nx_cbc_aes_alg);
+	nx_unregister_alg(&nx_cbc_aes_alg, NX_FC_AES, NX_MODE_AES_CBC);
 out_unreg_ecb:
-	crypto_unregister_alg(&nx_ecb_aes_alg);
+	nx_unregister_alg(&nx_ecb_aes_alg, NX_FC_AES, NX_MODE_AES_ECB);
 out:
 	return rc;
 }
@@ -666,9 +717,9 @@ int nx_crypto_ctx_aes_ccm_init(struct crypto_tfm *tfm)
 				  NX_MODE_AES_CCM);
 }
 
-int nx_crypto_ctx_aes_gcm_init(struct crypto_tfm *tfm)
+int nx_crypto_ctx_aes_gcm_init(struct crypto_aead *tfm)
 {
-	return nx_crypto_ctx_init(crypto_tfm_ctx(tfm), NX_FC_AES,
+	return nx_crypto_ctx_init(crypto_aead_ctx(tfm), NX_FC_AES,
 				  NX_MODE_AES_GCM);
 }
 
@@ -720,6 +771,13 @@ void nx_crypto_ctx_exit(struct crypto_tfm *tfm)
 	nx_ctx->out_sg = NULL;
 }
 
+void nx_crypto_ctx_aead_exit(struct crypto_aead *tfm)
+{
+	struct nx_crypto_ctx *nx_ctx = crypto_aead_ctx(tfm);
+
+	kzfree(nx_ctx->kmem);
+}
+
 static int nx_probe(struct vio_dev *viodev, const struct vio_device_id *id)
 {
 	dev_dbg(&viodev->dev, "driver probed: %s resource id: 0x%x\n",
@@ -746,17 +804,24 @@ static int nx_remove(struct vio_dev *viodev)
 	if (nx_driver.of.status == NX_OKAY) {
 		NX_DEBUGFS_FINI(&nx_driver);
 
-		crypto_unregister_alg(&nx_ccm_aes_alg);
-		crypto_unregister_alg(&nx_ccm4309_aes_alg);
-		crypto_unregister_alg(&nx_gcm_aes_alg);
-		crypto_unregister_alg(&nx_gcm4106_aes_alg);
-		crypto_unregister_alg(&nx_ctr_aes_alg);
-		crypto_unregister_alg(&nx_ctr3686_aes_alg);
-		crypto_unregister_alg(&nx_cbc_aes_alg);
-		crypto_unregister_alg(&nx_ecb_aes_alg);
-		crypto_unregister_shash(&nx_shash_sha256_alg);
-		crypto_unregister_shash(&nx_shash_sha512_alg);
-		crypto_unregister_shash(&nx_shash_aes_xcbc_alg);
+		nx_unregister_shash(&nx_shash_aes_xcbc_alg,
+				    NX_FC_AES, NX_MODE_AES_XCBC_MAC, -1);
+		nx_unregister_shash(&nx_shash_sha512_alg,
+				    NX_FC_SHA, NX_MODE_SHA, NX_PROPS_SHA256);
+		nx_unregister_shash(&nx_shash_sha256_alg,
+				    NX_FC_SHA, NX_MODE_SHA, NX_PROPS_SHA512);
+		nx_unregister_alg(&nx_ccm4309_aes_alg,
+				  NX_FC_AES, NX_MODE_AES_CCM);
+		nx_unregister_alg(&nx_ccm_aes_alg, NX_FC_AES, NX_MODE_AES_CCM);
+		nx_unregister_aead(&nx_gcm4106_aes_alg,
+				   NX_FC_AES, NX_MODE_AES_GCM);
+		nx_unregister_aead(&nx_gcm_aes_alg,
+				   NX_FC_AES, NX_MODE_AES_GCM);
+		nx_unregister_alg(&nx_ctr3686_aes_alg,
+				  NX_FC_AES, NX_MODE_AES_CTR);
+		nx_unregister_alg(&nx_ctr_aes_alg, NX_FC_AES, NX_MODE_AES_CTR);
+		nx_unregister_alg(&nx_cbc_aes_alg, NX_FC_AES, NX_MODE_AES_CBC);
+		nx_unregister_alg(&nx_ecb_aes_alg, NX_FC_AES, NX_MODE_AES_ECB);
 	}
 
 	return 0;
diff --git a/drivers/crypto/nx/nx.h b/drivers/crypto/nx/nx.h
index 6c9ecaaead52..de3ea8738146 100644
--- a/drivers/crypto/nx/nx.h
+++ b/drivers/crypto/nx/nx.h
@@ -143,18 +143,17 @@ struct nx_crypto_ctx {
 
 /* prototypes */
 int nx_crypto_ctx_aes_ccm_init(struct crypto_tfm *tfm);
-int nx_crypto_ctx_aes_gcm_init(struct crypto_tfm *tfm);
+int nx_crypto_ctx_aes_gcm_init(struct crypto_aead *tfm);
 int nx_crypto_ctx_aes_xcbc_init(struct crypto_tfm *tfm);
 int nx_crypto_ctx_aes_ctr_init(struct crypto_tfm *tfm);
 int nx_crypto_ctx_aes_cbc_init(struct crypto_tfm *tfm);
 int nx_crypto_ctx_aes_ecb_init(struct crypto_tfm *tfm);
 int nx_crypto_ctx_sha_init(struct crypto_tfm *tfm);
 void nx_crypto_ctx_exit(struct crypto_tfm *tfm);
+void nx_crypto_ctx_aead_exit(struct crypto_aead *tfm);
 void nx_ctx_init(struct nx_crypto_ctx *nx_ctx, unsigned int function);
 int nx_hcall_sync(struct nx_crypto_ctx *ctx, struct vio_pfo_op *op,
 		  u32 may_sleep);
-int nx_sha_build_sg_list(struct nx_crypto_ctx *, struct nx_sg *,
-			 s64 *, unsigned int *, u8 *, u32);
 struct nx_sg *nx_build_sg_list(struct nx_sg *, u8 *, unsigned int *, u32);
 int nx_build_sg_lists(struct nx_crypto_ctx *, struct blkcipher_desc *,
 		      struct scatterlist *, struct scatterlist *, unsigned int *,
@@ -178,8 +177,8 @@ void nx_debugfs_fini(struct nx_crypto_driver *);
 
 extern struct crypto_alg nx_cbc_aes_alg;
 extern struct crypto_alg nx_ecb_aes_alg;
-extern struct crypto_alg nx_gcm_aes_alg;
-extern struct crypto_alg nx_gcm4106_aes_alg;
+extern struct aead_alg nx_gcm_aes_alg;
+extern struct aead_alg nx_gcm4106_aes_alg;
 extern struct crypto_alg nx_ctr_aes_alg;
 extern struct crypto_alg nx_ctr3686_aes_alg;
 extern struct crypto_alg nx_ccm_aes_alg;
diff --git a/drivers/crypto/omap-sham.c b/drivers/crypto/omap-sham.c
index 4d63e0d4da9a..b2024c95a3cf 100644
--- a/drivers/crypto/omap-sham.c
+++ b/drivers/crypto/omap-sham.c
@@ -362,7 +362,13 @@ static void omap_sham_copy_ready_hash(struct ahash_request *req)
 
 static int omap_sham_hw_init(struct omap_sham_dev *dd)
 {
-	pm_runtime_get_sync(dd->dev);
+	int err;
+
+	err = pm_runtime_get_sync(dd->dev);
+	if (err < 0) {
+		dev_err(dd->dev, "failed to get sync: %d\n", err);
+		return err;
+	}
 
 	if (!test_bit(FLAGS_INIT, &dd->flags)) {
 		set_bit(FLAGS_INIT, &dd->flags);
@@ -1793,6 +1799,10 @@ static const struct of_device_id omap_sham_of_match[] = {
 		.data		= &omap_sham_pdata_omap2,
 	},
 	{
+		.compatible	= "ti,omap3-sham",
+		.data		= &omap_sham_pdata_omap2,
+	},
+	{
 		.compatible	= "ti,omap4-sham",
 		.data		= &omap_sham_pdata_omap4,
 	},
@@ -1947,7 +1957,13 @@ static int omap_sham_probe(struct platform_device *pdev)
 
 	pm_runtime_enable(dev);
 	pm_runtime_irq_safe(dev);
-	pm_runtime_get_sync(dev);
+
+	err = pm_runtime_get_sync(dev);
+	if (err < 0) {
+		dev_err(dev, "failed to get sync: %d\n", err);
+		goto err_pm;
+	}
+
 	rev = omap_sham_read(dd, SHA_REG_REV(dd));
 	pm_runtime_put_sync(&pdev->dev);
 
@@ -1977,6 +1993,7 @@ err_algs:
 		for (j = dd->pdata->algs_info[i].registered - 1; j >= 0; j--)
 			crypto_unregister_ahash(
 					&dd->pdata->algs_info[i].algs_list[j]);
+err_pm:
 	pm_runtime_disable(dev);
 	if (dd->dma_lch)
 		dma_release_channel(dd->dma_lch);
@@ -2019,7 +2036,11 @@ static int omap_sham_suspend(struct device *dev)
 
 static int omap_sham_resume(struct device *dev)
 {
-	pm_runtime_get_sync(dev);
+	int err = pm_runtime_get_sync(dev);
+	if (err < 0) {
+		dev_err(dev, "failed to get sync: %d\n", err);
+		return err;
+	}
 	return 0;
 }
 #endif
diff --git a/drivers/crypto/padlock-aes.c b/drivers/crypto/padlock-aes.c
index c178ed8c3908..da2d6777bd09 100644
--- a/drivers/crypto/padlock-aes.c
+++ b/drivers/crypto/padlock-aes.c
@@ -22,7 +22,7 @@
 #include <asm/cpu_device_id.h>
 #include <asm/byteorder.h>
 #include <asm/processor.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 
 /*
  * Number of data blocks actually fetched for each xcrypt insn.
diff --git a/drivers/crypto/padlock-sha.c b/drivers/crypto/padlock-sha.c
index 95f7d27ce491..4e154c9b9206 100644
--- a/drivers/crypto/padlock-sha.c
+++ b/drivers/crypto/padlock-sha.c
@@ -23,7 +23,7 @@
 #include <linux/kernel.h>
 #include <linux/scatterlist.h>
 #include <asm/cpu_device_id.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 
 struct padlock_sha_desc {
 	struct shash_desc fallback;
diff --git a/drivers/crypto/picoxcell_crypto.c b/drivers/crypto/picoxcell_crypto.c
index 5da5b98b8f29..4f56f3681abd 100644
--- a/drivers/crypto/picoxcell_crypto.c
+++ b/drivers/crypto/picoxcell_crypto.c
@@ -15,7 +15,7 @@
  * along with this program; if not, write to the Free Software
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
-#include <crypto/aead.h>
+#include <crypto/internal/aead.h>
 #include <crypto/aes.h>
 #include <crypto/algapi.h>
 #include <crypto/authenc.h>
@@ -40,6 +40,7 @@
 #include <linux/rtnetlink.h>
 #include <linux/scatterlist.h>
 #include <linux/sched.h>
+#include <linux/sizes.h>
 #include <linux/slab.h>
 #include <linux/timer.h>
 
@@ -261,18 +262,9 @@ static unsigned spacc_load_ctx(struct spacc_generic_ctx *ctx,
 }
 
 /* Count the number of scatterlist entries in a scatterlist. */
-static int sg_count(struct scatterlist *sg_list, int nbytes)
+static inline int sg_count(struct scatterlist *sg_list, int nbytes)
 {
-	struct scatterlist *sg = sg_list;
-	int sg_nents = 0;
-
-	while (nbytes > 0) {
-		++sg_nents;
-		nbytes -= sg->length;
-		sg = sg_next(sg);
-	}
-
-	return sg_nents;
+	return sg_nents_for_len(sg_list, nbytes);
 }
 
 static inline void ddt_set(struct spacc_ddt *ddt, dma_addr_t phys, size_t len)
@@ -326,6 +318,7 @@ static int spacc_aead_make_ddts(struct spacc_req *req, u8 *giv)
 	struct spacc_ddt *src_ddt, *dst_ddt;
 	unsigned ivsize = crypto_aead_ivsize(crypto_aead_reqtfm(areq));
 	unsigned nents = sg_count(areq->src, areq->cryptlen);
+	unsigned total;
 	dma_addr_t iv_addr;
 	struct scatterlist *cur;
 	int i, dst_ents, src_ents, assoc_ents;
@@ -369,11 +362,18 @@ static int spacc_aead_make_ddts(struct spacc_req *req, u8 *giv)
 	 * Map the associated data. For decryption we don't copy the
 	 * associated data.
 	 */
+	total = areq->assoclen;
 	for_each_sg(areq->assoc, cur, assoc_ents, i) {
-		ddt_set(src_ddt++, sg_dma_address(cur), sg_dma_len(cur));
+		unsigned len = sg_dma_len(cur);
+
+		if (len > total)
+			len = total;
+
+		total -= len;
+
+		ddt_set(src_ddt++, sg_dma_address(cur), len);
 		if (req->is_encrypt)
-			ddt_set(dst_ddt++, sg_dma_address(cur),
-				sg_dma_len(cur));
+			ddt_set(dst_ddt++, sg_dma_address(cur), len);
 	}
 	ddt_set(src_ddt++, iv_addr, ivsize);
 
@@ -790,7 +790,8 @@ static int spacc_aead_cra_init(struct crypto_tfm *tfm)
 
 	get_random_bytes(ctx->salt, sizeof(ctx->salt));
 
-	tfm->crt_aead.reqsize = sizeof(struct spacc_req);
+	crypto_aead_set_reqsize(__crypto_aead_cast(tfm),
+				sizeof(struct spacc_req));
 
 	return 0;
 }
@@ -1754,15 +1755,15 @@ static int spacc_probe(struct platform_device *pdev)
 		return PTR_ERR(engine->clk);
 	}
 
-	if (clk_enable(engine->clk)) {
-		dev_info(&pdev->dev, "unable to enable clk\n");
+	if (clk_prepare_enable(engine->clk)) {
+		dev_info(&pdev->dev, "unable to prepare/enable clk\n");
 		clk_put(engine->clk);
 		return -EIO;
 	}
 
 	err = device_create_file(&pdev->dev, &dev_attr_stat_irq_thresh);
 	if (err) {
-		clk_disable(engine->clk);
+		clk_disable_unprepare(engine->clk);
 		clk_put(engine->clk);
 		return err;
 	}
@@ -1830,7 +1831,7 @@ static int spacc_remove(struct platform_device *pdev)
 		crypto_unregister_alg(&alg->alg);
 	}
 
-	clk_disable(engine->clk);
+	clk_disable_unprepare(engine->clk);
 	clk_put(engine->clk);
 
 	return 0;
diff --git a/drivers/crypto/qat/Kconfig b/drivers/crypto/qat/Kconfig
index 49bede2a9f77..6fdb9e8b22a7 100644
--- a/drivers/crypto/qat/Kconfig
+++ b/drivers/crypto/qat/Kconfig
@@ -2,9 +2,8 @@ config CRYPTO_DEV_QAT
 	tristate
 	select CRYPTO_AEAD
 	select CRYPTO_AUTHENC
-	select CRYPTO_ALGAPI
-	select CRYPTO_AES
-	select CRYPTO_CBC
+	select CRYPTO_BLKCIPHER
+	select CRYPTO_HMAC
 	select CRYPTO_SHA1
 	select CRYPTO_SHA256
 	select CRYPTO_SHA512
@@ -13,7 +12,6 @@ config CRYPTO_DEV_QAT
 config CRYPTO_DEV_QAT_DH895xCC
 	tristate "Support for Intel(R) DH895xCC"
 	depends on X86 && PCI
-	default n
 	select CRYPTO_DEV_QAT
 	help
 	  Support for Intel(R) DH895xcc with Intel(R) QuickAssist Technology
diff --git a/drivers/crypto/qat/qat_common/adf_accel_devices.h b/drivers/crypto/qat/qat_common/adf_accel_devices.h
index f22ce7169fa5..5fe902967620 100644
--- a/drivers/crypto/qat/qat_common/adf_accel_devices.h
+++ b/drivers/crypto/qat/qat_common/adf_accel_devices.h
@@ -48,7 +48,6 @@
 #define ADF_ACCEL_DEVICES_H_
 #include <linux/module.h>
 #include <linux/list.h>
-#include <linux/proc_fs.h>
 #include <linux/io.h>
 #include "adf_cfg_common.h"
 
diff --git a/drivers/crypto/qat/qat_common/adf_cfg_user.h b/drivers/crypto/qat/qat_common/adf_cfg_user.h
index 0c38a155a865..ef5988afd4c6 100644
--- a/drivers/crypto/qat/qat_common/adf_cfg_user.h
+++ b/drivers/crypto/qat/qat_common/adf_cfg_user.h
@@ -54,14 +54,6 @@ struct adf_user_cfg_key_val {
 	char key[ADF_CFG_MAX_KEY_LEN_IN_BYTES];
 	char val[ADF_CFG_MAX_VAL_LEN_IN_BYTES];
 	union {
-		char *user_val_ptr;
-		uint64_t padding1;
-	};
-	union {
-		struct adf_user_cfg_key_val *prev;
-		uint64_t padding2;
-	};
-	union {
 		struct adf_user_cfg_key_val *next;
 		uint64_t padding3;
 	};
@@ -75,10 +67,6 @@ struct adf_user_cfg_section {
 		uint64_t padding1;
 	};
 	union {
-		struct adf_user_cfg_section *prev;
-		uint64_t padding2;
-	};
-	union {
 		struct adf_user_cfg_section *next;
 		uint64_t padding3;
 	};
diff --git a/drivers/crypto/qat/qat_common/adf_common_drv.h b/drivers/crypto/qat/qat_common/adf_common_drv.h
index 0666ee6a3360..27e16c09230b 100644
--- a/drivers/crypto/qat/qat_common/adf_common_drv.h
+++ b/drivers/crypto/qat/qat_common/adf_common_drv.h
@@ -53,6 +53,13 @@
 #include "icp_qat_fw_loader_handle.h"
 #include "icp_qat_hal.h"
 
+#define ADF_MAJOR_VERSION	0
+#define ADF_MINOR_VERSION	1
+#define ADF_BUILD_VERSION	3
+#define ADF_DRV_VERSION		__stringify(ADF_MAJOR_VERSION) "." \
+				__stringify(ADF_MINOR_VERSION) "." \
+				__stringify(ADF_BUILD_VERSION)
+
 #define ADF_STATUS_RESTARTING 0
 #define ADF_STATUS_STARTING 1
 #define ADF_STATUS_CONFIGURED 2
diff --git a/drivers/crypto/qat/qat_common/adf_ctl_drv.c b/drivers/crypto/qat/qat_common/adf_ctl_drv.c
index cb5f066e93a6..e056b9e9bf8a 100644
--- a/drivers/crypto/qat/qat_common/adf_ctl_drv.c
+++ b/drivers/crypto/qat/qat_common/adf_ctl_drv.c
@@ -504,3 +504,4 @@ MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Intel");
 MODULE_DESCRIPTION("Intel(R) QuickAssist Technology");
 MODULE_ALIAS_CRYPTO("intel_qat");
+MODULE_VERSION(ADF_DRV_VERSION);
diff --git a/drivers/crypto/qat/qat_common/qat_algs.c b/drivers/crypto/qat/qat_common/qat_algs.c
index 1dc5b0a17cf7..067402c7c2a9 100644
--- a/drivers/crypto/qat/qat_common/qat_algs.c
+++ b/drivers/crypto/qat/qat_common/qat_algs.c
@@ -47,7 +47,7 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/crypto.h>
-#include <crypto/aead.h>
+#include <crypto/internal/aead.h>
 #include <crypto/aes.h>
 #include <crypto/sha.h>
 #include <crypto/hash.h>
@@ -653,7 +653,7 @@ static void qat_alg_free_bufl(struct qat_crypto_instance *inst,
 }
 
 static int qat_alg_sgl_to_bufl(struct qat_crypto_instance *inst,
-			       struct scatterlist *assoc,
+			       struct scatterlist *assoc, int assoclen,
 			       struct scatterlist *sgl,
 			       struct scatterlist *sglout, uint8_t *iv,
 			       uint8_t ivlen,
@@ -685,15 +685,21 @@ static int qat_alg_sgl_to_bufl(struct qat_crypto_instance *inst,
 	for_each_sg(assoc, sg, assoc_n, i) {
 		if (!sg->length)
 			continue;
-		bufl->bufers[bufs].addr = dma_map_single(dev,
-							 sg_virt(sg),
-							 sg->length,
-							 DMA_BIDIRECTIONAL);
-		bufl->bufers[bufs].len = sg->length;
+
+		if (!(assoclen > 0))
+			break;
+
+		bufl->bufers[bufs].addr =
+			dma_map_single(dev, sg_virt(sg),
+				       min_t(int, assoclen, sg->length),
+				       DMA_BIDIRECTIONAL);
+		bufl->bufers[bufs].len = min_t(int, assoclen, sg->length);
 		if (unlikely(dma_mapping_error(dev, bufl->bufers[bufs].addr)))
 			goto err;
 		bufs++;
+		assoclen -= sg->length;
 	}
+
 	if (ivlen) {
 		bufl->bufers[bufs].addr = dma_map_single(dev, iv, ivlen,
 							 DMA_BIDIRECTIONAL);
@@ -845,8 +851,9 @@ static int qat_alg_aead_dec(struct aead_request *areq)
 	int digst_size = crypto_aead_crt(aead_tfm)->authsize;
 	int ret, ctr = 0;
 
-	ret = qat_alg_sgl_to_bufl(ctx->inst, areq->assoc, areq->src, areq->dst,
-				  areq->iv, AES_BLOCK_SIZE, qat_req);
+	ret = qat_alg_sgl_to_bufl(ctx->inst, areq->assoc, areq->assoclen,
+				  areq->src, areq->dst, areq->iv,
+				  AES_BLOCK_SIZE, qat_req);
 	if (unlikely(ret))
 		return ret;
 
@@ -889,8 +896,9 @@ static int qat_alg_aead_enc_internal(struct aead_request *areq, uint8_t *iv,
 	struct icp_qat_fw_la_bulk_req *msg;
 	int ret, ctr = 0;
 
-	ret = qat_alg_sgl_to_bufl(ctx->inst, areq->assoc, areq->src, areq->dst,
-				  iv, AES_BLOCK_SIZE, qat_req);
+	ret = qat_alg_sgl_to_bufl(ctx->inst, areq->assoc, areq->assoclen,
+				  areq->src, areq->dst, iv, AES_BLOCK_SIZE,
+				  qat_req);
 	if (unlikely(ret))
 		return ret;
 
@@ -1017,7 +1025,7 @@ static int qat_alg_ablkcipher_encrypt(struct ablkcipher_request *req)
 	struct icp_qat_fw_la_bulk_req *msg;
 	int ret, ctr = 0;
 
-	ret = qat_alg_sgl_to_bufl(ctx->inst, NULL, req->src, req->dst,
+	ret = qat_alg_sgl_to_bufl(ctx->inst, NULL, 0, req->src, req->dst,
 				  NULL, 0, qat_req);
 	if (unlikely(ret))
 		return ret;
@@ -1055,7 +1063,7 @@ static int qat_alg_ablkcipher_decrypt(struct ablkcipher_request *req)
 	struct icp_qat_fw_la_bulk_req *msg;
 	int ret, ctr = 0;
 
-	ret = qat_alg_sgl_to_bufl(ctx->inst, NULL, req->src, req->dst,
+	ret = qat_alg_sgl_to_bufl(ctx->inst, NULL, 0, req->src, req->dst,
 				  NULL, 0, qat_req);
 	if (unlikely(ret))
 		return ret;
@@ -1094,8 +1102,9 @@ static int qat_alg_aead_init(struct crypto_tfm *tfm,
 		return -EFAULT;
 	spin_lock_init(&ctx->lock);
 	ctx->qat_hash_alg = hash;
-	tfm->crt_aead.reqsize = sizeof(struct aead_request) +
-				sizeof(struct qat_crypto_request);
+	crypto_aead_set_reqsize(__crypto_aead_cast(tfm),
+		sizeof(struct aead_request) +
+		sizeof(struct qat_crypto_request));
 	ctx->tfm = tfm;
 	return 0;
 }
diff --git a/drivers/crypto/qat/qat_dh895xcc/adf_drv.c b/drivers/crypto/qat/qat_dh895xcc/adf_drv.c
index 9decea2779c6..1bde45b7a3c5 100644
--- a/drivers/crypto/qat/qat_dh895xcc/adf_drv.c
+++ b/drivers/crypto/qat/qat_dh895xcc/adf_drv.c
@@ -300,6 +300,8 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (ret)
 		goto out_err;
 
+	pcie_set_readrq(pdev, 1024);
+
 	/* enable PCI device */
 	if (pci_enable_device(pdev)) {
 		ret = -EFAULT;
@@ -417,5 +419,6 @@ module_exit(adfdrv_release);
 
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Intel");
-MODULE_FIRMWARE("qat_895xcc.bin");
+MODULE_FIRMWARE(ADF_DH895XCC_FW);
 MODULE_DESCRIPTION("Intel(R) QuickAssist Technology");
+MODULE_VERSION(ADF_DRV_VERSION);
diff --git a/drivers/crypto/sahara.c b/drivers/crypto/sahara.c
index 6be377f6b9e7..397a500b3d8a 100644
--- a/drivers/crypto/sahara.c
+++ b/drivers/crypto/sahara.c
@@ -1578,8 +1578,12 @@ static int sahara_probe(struct platform_device *pdev)
 
 	init_completion(&dev->dma_completion);
 
-	clk_prepare_enable(dev->clk_ipg);
-	clk_prepare_enable(dev->clk_ahb);
+	err = clk_prepare_enable(dev->clk_ipg);
+	if (err)
+		goto err_link;
+	err = clk_prepare_enable(dev->clk_ahb);
+	if (err)
+		goto clk_ipg_disable;
 
 	version = sahara_read(dev, SAHARA_REG_VERSION);
 	if (of_device_is_compatible(pdev->dev.of_node, "fsl,imx27-sahara")) {
@@ -1619,10 +1623,11 @@ err_algs:
 	dma_free_coherent(&pdev->dev,
 			  SAHARA_MAX_HW_LINK * sizeof(struct sahara_hw_link),
 			  dev->hw_link[0], dev->hw_phys_link[0]);
-	clk_disable_unprepare(dev->clk_ipg);
-	clk_disable_unprepare(dev->clk_ahb);
 	kthread_stop(dev->kthread);
 	dev_ptr = NULL;
+	clk_disable_unprepare(dev->clk_ahb);
+clk_ipg_disable:
+	clk_disable_unprepare(dev->clk_ipg);
 err_link:
 	dma_free_coherent(&pdev->dev,
 			  2 * AES_KEYSIZE_128,
diff --git a/drivers/crypto/talitos.c b/drivers/crypto/talitos.c
index 857414afa29a..83aca95a95bc 100644
--- a/drivers/crypto/talitos.c
+++ b/drivers/crypto/talitos.c
@@ -46,7 +46,7 @@
 #include <crypto/des.h>
 #include <crypto/sha.h>
 #include <crypto/md5.h>
-#include <crypto/aead.h>
+#include <crypto/internal/aead.h>
 #include <crypto/authenc.h>
 #include <crypto/skcipher.h>
 #include <crypto/hash.h>
@@ -55,49 +55,92 @@
 
 #include "talitos.h"
 
-static void to_talitos_ptr(struct talitos_ptr *talitos_ptr, dma_addr_t dma_addr)
+static void to_talitos_ptr(struct talitos_ptr *ptr, dma_addr_t dma_addr,
+			   bool is_sec1)
 {
-	talitos_ptr->ptr = cpu_to_be32(lower_32_bits(dma_addr));
-	talitos_ptr->eptr = upper_32_bits(dma_addr);
+	ptr->ptr = cpu_to_be32(lower_32_bits(dma_addr));
+	if (!is_sec1)
+		ptr->eptr = upper_32_bits(dma_addr);
+}
+
+static void to_talitos_ptr_len(struct talitos_ptr *ptr, unsigned int len,
+			       bool is_sec1)
+{
+	if (is_sec1) {
+		ptr->res = 0;
+		ptr->len1 = cpu_to_be16(len);
+	} else {
+		ptr->len = cpu_to_be16(len);
+	}
+}
+
+static unsigned short from_talitos_ptr_len(struct talitos_ptr *ptr,
+					   bool is_sec1)
+{
+	if (is_sec1)
+		return be16_to_cpu(ptr->len1);
+	else
+		return be16_to_cpu(ptr->len);
+}
+
+static void to_talitos_ptr_extent_clear(struct talitos_ptr *ptr, bool is_sec1)
+{
+	if (!is_sec1)
+		ptr->j_extent = 0;
 }
 
 /*
  * map virtual single (contiguous) pointer to h/w descriptor pointer
  */
 static void map_single_talitos_ptr(struct device *dev,
-				   struct talitos_ptr *talitos_ptr,
-				   unsigned short len, void *data,
-				   unsigned char extent,
+				   struct talitos_ptr *ptr,
+				   unsigned int len, void *data,
 				   enum dma_data_direction dir)
 {
 	dma_addr_t dma_addr = dma_map_single(dev, data, len, dir);
+	struct talitos_private *priv = dev_get_drvdata(dev);
+	bool is_sec1 = has_ftr_sec1(priv);
 
-	talitos_ptr->len = cpu_to_be16(len);
-	to_talitos_ptr(talitos_ptr, dma_addr);
-	talitos_ptr->j_extent = extent;
+	to_talitos_ptr_len(ptr, len, is_sec1);
+	to_talitos_ptr(ptr, dma_addr, is_sec1);
+	to_talitos_ptr_extent_clear(ptr, is_sec1);
 }
 
 /*
  * unmap bus single (contiguous) h/w descriptor pointer
  */
 static void unmap_single_talitos_ptr(struct device *dev,
-				     struct talitos_ptr *talitos_ptr,
+				     struct talitos_ptr *ptr,
 				     enum dma_data_direction dir)
 {
-	dma_unmap_single(dev, be32_to_cpu(talitos_ptr->ptr),
-			 be16_to_cpu(talitos_ptr->len), dir);
+	struct talitos_private *priv = dev_get_drvdata(dev);
+	bool is_sec1 = has_ftr_sec1(priv);
+
+	dma_unmap_single(dev, be32_to_cpu(ptr->ptr),
+			 from_talitos_ptr_len(ptr, is_sec1), dir);
 }
 
 static int reset_channel(struct device *dev, int ch)
 {
 	struct talitos_private *priv = dev_get_drvdata(dev);
 	unsigned int timeout = TALITOS_TIMEOUT;
+	bool is_sec1 = has_ftr_sec1(priv);
 
-	setbits32(priv->chan[ch].reg + TALITOS_CCCR, TALITOS_CCCR_RESET);
+	if (is_sec1) {
+		setbits32(priv->chan[ch].reg + TALITOS_CCCR_LO,
+			  TALITOS1_CCCR_LO_RESET);
 
-	while ((in_be32(priv->chan[ch].reg + TALITOS_CCCR) & TALITOS_CCCR_RESET)
-	       && --timeout)
-		cpu_relax();
+		while ((in_be32(priv->chan[ch].reg + TALITOS_CCCR_LO) &
+			TALITOS1_CCCR_LO_RESET) && --timeout)
+			cpu_relax();
+	} else {
+		setbits32(priv->chan[ch].reg + TALITOS_CCCR,
+			  TALITOS2_CCCR_RESET);
+
+		while ((in_be32(priv->chan[ch].reg + TALITOS_CCCR) &
+			TALITOS2_CCCR_RESET) && --timeout)
+			cpu_relax();
+	}
 
 	if (timeout == 0) {
 		dev_err(dev, "failed to reset channel %d\n", ch);
@@ -120,11 +163,12 @@ static int reset_device(struct device *dev)
 {
 	struct talitos_private *priv = dev_get_drvdata(dev);
 	unsigned int timeout = TALITOS_TIMEOUT;
-	u32 mcr = TALITOS_MCR_SWR;
+	bool is_sec1 = has_ftr_sec1(priv);
+	u32 mcr = is_sec1 ? TALITOS1_MCR_SWR : TALITOS2_MCR_SWR;
 
 	setbits32(priv->reg + TALITOS_MCR, mcr);
 
-	while ((in_be32(priv->reg + TALITOS_MCR) & TALITOS_MCR_SWR)
+	while ((in_be32(priv->reg + TALITOS_MCR) & mcr)
 	       && --timeout)
 		cpu_relax();
 
@@ -148,6 +192,7 @@ static int init_device(struct device *dev)
 {
 	struct talitos_private *priv = dev_get_drvdata(dev);
 	int ch, err;
+	bool is_sec1 = has_ftr_sec1(priv);
 
 	/*
 	 * Master reset
@@ -171,12 +216,19 @@ static int init_device(struct device *dev)
 	}
 
 	/* enable channel done and error interrupts */
-	setbits32(priv->reg + TALITOS_IMR, TALITOS_IMR_INIT);
-	setbits32(priv->reg + TALITOS_IMR_LO, TALITOS_IMR_LO_INIT);
+	if (is_sec1) {
+		clrbits32(priv->reg + TALITOS_IMR, TALITOS1_IMR_INIT);
+		clrbits32(priv->reg + TALITOS_IMR_LO, TALITOS1_IMR_LO_INIT);
+		/* disable parity error check in DEU (erroneous? test vect.) */
+		setbits32(priv->reg_deu + TALITOS_EUICR, TALITOS1_DEUICR_KPE);
+	} else {
+		setbits32(priv->reg + TALITOS_IMR, TALITOS2_IMR_INIT);
+		setbits32(priv->reg + TALITOS_IMR_LO, TALITOS2_IMR_LO_INIT);
+	}
 
 	/* disable integrity check error interrupts (use writeback instead) */
 	if (priv->features & TALITOS_FTR_HW_AUTH_CHECK)
-		setbits32(priv->reg + TALITOS_MDEUICR_LO,
+		setbits32(priv->reg_mdeu + TALITOS_EUICR_LO,
 		          TALITOS_MDEUICR_LO_ICE);
 
 	return 0;
@@ -204,6 +256,7 @@ int talitos_submit(struct device *dev, int ch, struct talitos_desc *desc,
 	struct talitos_request *request;
 	unsigned long flags;
 	int head;
+	bool is_sec1 = has_ftr_sec1(priv);
 
 	spin_lock_irqsave(&priv->chan[ch].head_lock, flags);
 
@@ -217,8 +270,17 @@ int talitos_submit(struct device *dev, int ch, struct talitos_desc *desc,
 	request = &priv->chan[ch].fifo[head];
 
 	/* map descriptor and save caller data */
-	request->dma_desc = dma_map_single(dev, desc, sizeof(*desc),
-					   DMA_BIDIRECTIONAL);
+	if (is_sec1) {
+		desc->hdr1 = desc->hdr;
+		desc->next_desc = 0;
+		request->dma_desc = dma_map_single(dev, &desc->hdr1,
+						   TALITOS_DESC_SIZE,
+						   DMA_BIDIRECTIONAL);
+	} else {
+		request->dma_desc = dma_map_single(dev, desc,
+						   TALITOS_DESC_SIZE,
+						   DMA_BIDIRECTIONAL);
+	}
 	request->callback = callback;
 	request->context = context;
 
@@ -250,16 +312,21 @@ static void flush_channel(struct device *dev, int ch, int error, int reset_ch)
 	struct talitos_request *request, saved_req;
 	unsigned long flags;
 	int tail, status;
+	bool is_sec1 = has_ftr_sec1(priv);
 
 	spin_lock_irqsave(&priv->chan[ch].tail_lock, flags);
 
 	tail = priv->chan[ch].tail;
 	while (priv->chan[ch].fifo[tail].desc) {
+		__be32 hdr;
+
 		request = &priv->chan[ch].fifo[tail];
 
 		/* descriptors with their done bits set don't get the error */
 		rmb();
-		if ((request->desc->hdr & DESC_HDR_DONE) == DESC_HDR_DONE)
+		hdr = is_sec1 ? request->desc->hdr1 : request->desc->hdr;
+
+		if ((hdr & DESC_HDR_DONE) == DESC_HDR_DONE)
 			status = 0;
 		else
 			if (!error)
@@ -268,7 +335,7 @@ static void flush_channel(struct device *dev, int ch, int error, int reset_ch)
 				status = error;
 
 		dma_unmap_single(dev, request->dma_desc,
-				 sizeof(struct talitos_desc),
+				 TALITOS_DESC_SIZE,
 				 DMA_BIDIRECTIONAL);
 
 		/* copy entries so we can call callback outside lock */
@@ -302,8 +369,37 @@ static void flush_channel(struct device *dev, int ch, int error, int reset_ch)
 /*
  * process completed requests for channels that have done status
  */
-#define DEF_TALITOS_DONE(name, ch_done_mask)				\
-static void talitos_done_##name(unsigned long data)			\
+#define DEF_TALITOS1_DONE(name, ch_done_mask)				\
+static void talitos1_done_##name(unsigned long data)			\
+{									\
+	struct device *dev = (struct device *)data;			\
+	struct talitos_private *priv = dev_get_drvdata(dev);		\
+	unsigned long flags;						\
+									\
+	if (ch_done_mask & 0x10000000)					\
+		flush_channel(dev, 0, 0, 0);			\
+	if (priv->num_channels == 1)					\
+		goto out;						\
+	if (ch_done_mask & 0x40000000)					\
+		flush_channel(dev, 1, 0, 0);			\
+	if (ch_done_mask & 0x00010000)					\
+		flush_channel(dev, 2, 0, 0);			\
+	if (ch_done_mask & 0x00040000)					\
+		flush_channel(dev, 3, 0, 0);			\
+									\
+out:									\
+	/* At this point, all completed channels have been processed */	\
+	/* Unmask done interrupts for channels completed later on. */	\
+	spin_lock_irqsave(&priv->reg_lock, flags);			\
+	clrbits32(priv->reg + TALITOS_IMR, ch_done_mask);		\
+	clrbits32(priv->reg + TALITOS_IMR_LO, TALITOS1_IMR_LO_INIT);	\
+	spin_unlock_irqrestore(&priv->reg_lock, flags);			\
+}
+
+DEF_TALITOS1_DONE(4ch, TALITOS1_ISR_4CHDONE)
+
+#define DEF_TALITOS2_DONE(name, ch_done_mask)				\
+static void talitos2_done_##name(unsigned long data)			\
 {									\
 	struct device *dev = (struct device *)data;			\
 	struct talitos_private *priv = dev_get_drvdata(dev);		\
@@ -325,12 +421,13 @@ out:									\
 	/* Unmask done interrupts for channels completed later on. */	\
 	spin_lock_irqsave(&priv->reg_lock, flags);			\
 	setbits32(priv->reg + TALITOS_IMR, ch_done_mask);		\
-	setbits32(priv->reg + TALITOS_IMR_LO, TALITOS_IMR_LO_INIT);	\
+	setbits32(priv->reg + TALITOS_IMR_LO, TALITOS2_IMR_LO_INIT);	\
 	spin_unlock_irqrestore(&priv->reg_lock, flags);			\
 }
-DEF_TALITOS_DONE(4ch, TALITOS_ISR_4CHDONE)
-DEF_TALITOS_DONE(ch0_2, TALITOS_ISR_CH_0_2_DONE)
-DEF_TALITOS_DONE(ch1_3, TALITOS_ISR_CH_1_3_DONE)
+
+DEF_TALITOS2_DONE(4ch, TALITOS2_ISR_4CHDONE)
+DEF_TALITOS2_DONE(ch0_2, TALITOS2_ISR_CH_0_2_DONE)
+DEF_TALITOS2_DONE(ch1_3, TALITOS2_ISR_CH_1_3_DONE)
 
 /*
  * locate current (offending) descriptor
@@ -377,44 +474,44 @@ static void report_eu_error(struct device *dev, int ch, u32 desc_hdr)
 	switch (desc_hdr & DESC_HDR_SEL0_MASK) {
 	case DESC_HDR_SEL0_AFEU:
 		dev_err(dev, "AFEUISR 0x%08x_%08x\n",
-			in_be32(priv->reg + TALITOS_AFEUISR),
-			in_be32(priv->reg + TALITOS_AFEUISR_LO));
+			in_be32(priv->reg_afeu + TALITOS_EUISR),
+			in_be32(priv->reg_afeu + TALITOS_EUISR_LO));
 		break;
 	case DESC_HDR_SEL0_DEU:
 		dev_err(dev, "DEUISR 0x%08x_%08x\n",
-			in_be32(priv->reg + TALITOS_DEUISR),
-			in_be32(priv->reg + TALITOS_DEUISR_LO));
+			in_be32(priv->reg_deu + TALITOS_EUISR),
+			in_be32(priv->reg_deu + TALITOS_EUISR_LO));
 		break;
 	case DESC_HDR_SEL0_MDEUA:
 	case DESC_HDR_SEL0_MDEUB:
 		dev_err(dev, "MDEUISR 0x%08x_%08x\n",
-			in_be32(priv->reg + TALITOS_MDEUISR),
-			in_be32(priv->reg + TALITOS_MDEUISR_LO));
+			in_be32(priv->reg_mdeu + TALITOS_EUISR),
+			in_be32(priv->reg_mdeu + TALITOS_EUISR_LO));
 		break;
 	case DESC_HDR_SEL0_RNG:
 		dev_err(dev, "RNGUISR 0x%08x_%08x\n",
-			in_be32(priv->reg + TALITOS_RNGUISR),
-			in_be32(priv->reg + TALITOS_RNGUISR_LO));
+			in_be32(priv->reg_rngu + TALITOS_ISR),
+			in_be32(priv->reg_rngu + TALITOS_ISR_LO));
 		break;
 	case DESC_HDR_SEL0_PKEU:
 		dev_err(dev, "PKEUISR 0x%08x_%08x\n",
-			in_be32(priv->reg + TALITOS_PKEUISR),
-			in_be32(priv->reg + TALITOS_PKEUISR_LO));
+			in_be32(priv->reg_pkeu + TALITOS_EUISR),
+			in_be32(priv->reg_pkeu + TALITOS_EUISR_LO));
 		break;
 	case DESC_HDR_SEL0_AESU:
 		dev_err(dev, "AESUISR 0x%08x_%08x\n",
-			in_be32(priv->reg + TALITOS_AESUISR),
-			in_be32(priv->reg + TALITOS_AESUISR_LO));
+			in_be32(priv->reg_aesu + TALITOS_EUISR),
+			in_be32(priv->reg_aesu + TALITOS_EUISR_LO));
 		break;
 	case DESC_HDR_SEL0_CRCU:
 		dev_err(dev, "CRCUISR 0x%08x_%08x\n",
-			in_be32(priv->reg + TALITOS_CRCUISR),
-			in_be32(priv->reg + TALITOS_CRCUISR_LO));
+			in_be32(priv->reg_crcu + TALITOS_EUISR),
+			in_be32(priv->reg_crcu + TALITOS_EUISR_LO));
 		break;
 	case DESC_HDR_SEL0_KEU:
 		dev_err(dev, "KEUISR 0x%08x_%08x\n",
-			in_be32(priv->reg + TALITOS_KEUISR),
-			in_be32(priv->reg + TALITOS_KEUISR_LO));
+			in_be32(priv->reg_pkeu + TALITOS_EUISR),
+			in_be32(priv->reg_pkeu + TALITOS_EUISR_LO));
 		break;
 	}
 
@@ -422,13 +519,13 @@ static void report_eu_error(struct device *dev, int ch, u32 desc_hdr)
 	case DESC_HDR_SEL1_MDEUA:
 	case DESC_HDR_SEL1_MDEUB:
 		dev_err(dev, "MDEUISR 0x%08x_%08x\n",
-			in_be32(priv->reg + TALITOS_MDEUISR),
-			in_be32(priv->reg + TALITOS_MDEUISR_LO));
+			in_be32(priv->reg_mdeu + TALITOS_EUISR),
+			in_be32(priv->reg_mdeu + TALITOS_EUISR_LO));
 		break;
 	case DESC_HDR_SEL1_CRCU:
 		dev_err(dev, "CRCUISR 0x%08x_%08x\n",
-			in_be32(priv->reg + TALITOS_CRCUISR),
-			in_be32(priv->reg + TALITOS_CRCUISR_LO));
+			in_be32(priv->reg_crcu + TALITOS_EUISR),
+			in_be32(priv->reg_crcu + TALITOS_EUISR_LO));
 		break;
 	}
 
@@ -445,17 +542,24 @@ static void talitos_error(struct device *dev, u32 isr, u32 isr_lo)
 {
 	struct talitos_private *priv = dev_get_drvdata(dev);
 	unsigned int timeout = TALITOS_TIMEOUT;
-	int ch, error, reset_dev = 0, reset_ch = 0;
-	u32 v, v_lo;
+	int ch, error, reset_dev = 0;
+	u32 v_lo;
+	bool is_sec1 = has_ftr_sec1(priv);
+	int reset_ch = is_sec1 ? 1 : 0; /* only SEC2 supports continuation */
 
 	for (ch = 0; ch < priv->num_channels; ch++) {
 		/* skip channels without errors */
-		if (!(isr & (1 << (ch * 2 + 1))))
-			continue;
+		if (is_sec1) {
+			/* bits 29, 31, 17, 19 */
+			if (!(isr & (1 << (29 + (ch & 1) * 2 - (ch & 2) * 6))))
+				continue;
+		} else {
+			if (!(isr & (1 << (ch * 2 + 1))))
+				continue;
+		}
 
 		error = -EINVAL;
 
-		v = in_be32(priv->chan[ch].reg + TALITOS_CCPSR);
 		v_lo = in_be32(priv->chan[ch].reg + TALITOS_CCPSR_LO);
 
 		if (v_lo & TALITOS_CCPSR_LO_DOF) {
@@ -471,23 +575,28 @@ static void talitos_error(struct device *dev, u32 isr, u32 isr_lo)
 		if (v_lo & TALITOS_CCPSR_LO_MDTE)
 			dev_err(dev, "master data transfer error\n");
 		if (v_lo & TALITOS_CCPSR_LO_SGDLZ)
-			dev_err(dev, "s/g data length zero error\n");
+			dev_err(dev, is_sec1 ? "pointeur not complete error\n"
+					     : "s/g data length zero error\n");
 		if (v_lo & TALITOS_CCPSR_LO_FPZ)
-			dev_err(dev, "fetch pointer zero error\n");
+			dev_err(dev, is_sec1 ? "parity error\n"
+					     : "fetch pointer zero error\n");
 		if (v_lo & TALITOS_CCPSR_LO_IDH)
 			dev_err(dev, "illegal descriptor header error\n");
 		if (v_lo & TALITOS_CCPSR_LO_IEU)
-			dev_err(dev, "invalid execution unit error\n");
+			dev_err(dev, is_sec1 ? "static assignment error\n"
+					     : "invalid exec unit error\n");
 		if (v_lo & TALITOS_CCPSR_LO_EU)
 			report_eu_error(dev, ch, current_desc_hdr(dev, ch));
-		if (v_lo & TALITOS_CCPSR_LO_GB)
-			dev_err(dev, "gather boundary error\n");
-		if (v_lo & TALITOS_CCPSR_LO_GRL)
-			dev_err(dev, "gather return/length error\n");
-		if (v_lo & TALITOS_CCPSR_LO_SB)
-			dev_err(dev, "scatter boundary error\n");
-		if (v_lo & TALITOS_CCPSR_LO_SRL)
-			dev_err(dev, "scatter return/length error\n");
+		if (!is_sec1) {
+			if (v_lo & TALITOS_CCPSR_LO_GB)
+				dev_err(dev, "gather boundary error\n");
+			if (v_lo & TALITOS_CCPSR_LO_GRL)
+				dev_err(dev, "gather return/length error\n");
+			if (v_lo & TALITOS_CCPSR_LO_SB)
+				dev_err(dev, "scatter boundary error\n");
+			if (v_lo & TALITOS_CCPSR_LO_SRL)
+				dev_err(dev, "scatter return/length error\n");
+		}
 
 		flush_channel(dev, ch, error, reset_ch);
 
@@ -495,10 +604,10 @@ static void talitos_error(struct device *dev, u32 isr, u32 isr_lo)
 			reset_channel(dev, ch);
 		} else {
 			setbits32(priv->chan[ch].reg + TALITOS_CCCR,
-				  TALITOS_CCCR_CONT);
+				  TALITOS2_CCCR_CONT);
 			setbits32(priv->chan[ch].reg + TALITOS_CCCR_LO, 0);
 			while ((in_be32(priv->chan[ch].reg + TALITOS_CCCR) &
-			       TALITOS_CCCR_CONT) && --timeout)
+			       TALITOS2_CCCR_CONT) && --timeout)
 				cpu_relax();
 			if (timeout == 0) {
 				dev_err(dev, "failed to restart channel %d\n",
@@ -507,9 +616,14 @@ static void talitos_error(struct device *dev, u32 isr, u32 isr_lo)
 			}
 		}
 	}
-	if (reset_dev || isr & ~TALITOS_ISR_4CHERR || isr_lo) {
-		dev_err(dev, "done overflow, internal time out, or rngu error: "
-		        "ISR 0x%08x_%08x\n", isr, isr_lo);
+	if (reset_dev || (is_sec1 && isr & ~TALITOS1_ISR_4CHERR) ||
+	    (!is_sec1 && isr & ~TALITOS2_ISR_4CHERR) || isr_lo) {
+		if (is_sec1 && (isr_lo & TALITOS1_ISR_TEA_ERR))
+			dev_err(dev, "TEA error: ISR 0x%08x_%08x\n",
+				isr, isr_lo);
+		else
+			dev_err(dev, "done overflow, internal time out, or "
+				"rngu error: ISR 0x%08x_%08x\n", isr, isr_lo);
 
 		/* purge request queues */
 		for (ch = 0; ch < priv->num_channels; ch++)
@@ -520,8 +634,43 @@ static void talitos_error(struct device *dev, u32 isr, u32 isr_lo)
 	}
 }
 
-#define DEF_TALITOS_INTERRUPT(name, ch_done_mask, ch_err_mask, tlet)	       \
-static irqreturn_t talitos_interrupt_##name(int irq, void *data)	       \
+#define DEF_TALITOS1_INTERRUPT(name, ch_done_mask, ch_err_mask, tlet)	       \
+static irqreturn_t talitos1_interrupt_##name(int irq, void *data)	       \
+{									       \
+	struct device *dev = data;					       \
+	struct talitos_private *priv = dev_get_drvdata(dev);		       \
+	u32 isr, isr_lo;						       \
+	unsigned long flags;						       \
+									       \
+	spin_lock_irqsave(&priv->reg_lock, flags);			       \
+	isr = in_be32(priv->reg + TALITOS_ISR);				       \
+	isr_lo = in_be32(priv->reg + TALITOS_ISR_LO);			       \
+	/* Acknowledge interrupt */					       \
+	out_be32(priv->reg + TALITOS_ICR, isr & (ch_done_mask | ch_err_mask)); \
+	out_be32(priv->reg + TALITOS_ICR_LO, isr_lo);			       \
+									       \
+	if (unlikely(isr & ch_err_mask || isr_lo & TALITOS1_IMR_LO_INIT)) {    \
+		spin_unlock_irqrestore(&priv->reg_lock, flags);		       \
+		talitos_error(dev, isr & ch_err_mask, isr_lo);		       \
+	}								       \
+	else {								       \
+		if (likely(isr & ch_done_mask)) {			       \
+			/* mask further done interrupts. */		       \
+			setbits32(priv->reg + TALITOS_IMR, ch_done_mask);      \
+			/* done_task will unmask done interrupts at exit */    \
+			tasklet_schedule(&priv->done_task[tlet]);	       \
+		}							       \
+		spin_unlock_irqrestore(&priv->reg_lock, flags);		       \
+	}								       \
+									       \
+	return (isr & (ch_done_mask | ch_err_mask) || isr_lo) ? IRQ_HANDLED :  \
+								IRQ_NONE;      \
+}
+
+DEF_TALITOS1_INTERRUPT(4ch, TALITOS1_ISR_4CHDONE, TALITOS1_ISR_4CHERR, 0)
+
+#define DEF_TALITOS2_INTERRUPT(name, ch_done_mask, ch_err_mask, tlet)	       \
+static irqreturn_t talitos2_interrupt_##name(int irq, void *data)	       \
 {									       \
 	struct device *dev = data;					       \
 	struct talitos_private *priv = dev_get_drvdata(dev);		       \
@@ -552,9 +701,12 @@ static irqreturn_t talitos_interrupt_##name(int irq, void *data)	       \
 	return (isr & (ch_done_mask | ch_err_mask) || isr_lo) ? IRQ_HANDLED :  \
 								IRQ_NONE;      \
 }
-DEF_TALITOS_INTERRUPT(4ch, TALITOS_ISR_4CHDONE, TALITOS_ISR_4CHERR, 0)
-DEF_TALITOS_INTERRUPT(ch0_2, TALITOS_ISR_CH_0_2_DONE, TALITOS_ISR_CH_0_2_ERR, 0)
-DEF_TALITOS_INTERRUPT(ch1_3, TALITOS_ISR_CH_1_3_DONE, TALITOS_ISR_CH_1_3_ERR, 1)
+
+DEF_TALITOS2_INTERRUPT(4ch, TALITOS2_ISR_4CHDONE, TALITOS2_ISR_4CHERR, 0)
+DEF_TALITOS2_INTERRUPT(ch0_2, TALITOS2_ISR_CH_0_2_DONE, TALITOS2_ISR_CH_0_2_ERR,
+		       0)
+DEF_TALITOS2_INTERRUPT(ch1_3, TALITOS2_ISR_CH_1_3_DONE, TALITOS2_ISR_CH_1_3_ERR,
+		       1)
 
 /*
  * hwrng
@@ -567,7 +719,7 @@ static int talitos_rng_data_present(struct hwrng *rng, int wait)
 	int i;
 
 	for (i = 0; i < 20; i++) {
-		ofl = in_be32(priv->reg + TALITOS_RNGUSR_LO) &
+		ofl = in_be32(priv->reg_rngu + TALITOS_EUSR_LO) &
 		      TALITOS_RNGUSR_LO_OFL;
 		if (ofl || !wait)
 			break;
@@ -583,8 +735,8 @@ static int talitos_rng_data_read(struct hwrng *rng, u32 *data)
 	struct talitos_private *priv = dev_get_drvdata(dev);
 
 	/* rng fifo requires 64-bit accesses */
-	*data = in_be32(priv->reg + TALITOS_RNGU_FIFO);
-	*data = in_be32(priv->reg + TALITOS_RNGU_FIFO_LO);
+	*data = in_be32(priv->reg_rngu + TALITOS_EU_FIFO);
+	*data = in_be32(priv->reg_rngu + TALITOS_EU_FIFO_LO);
 
 	return sizeof(u32);
 }
@@ -595,8 +747,9 @@ static int talitos_rng_init(struct hwrng *rng)
 	struct talitos_private *priv = dev_get_drvdata(dev);
 	unsigned int timeout = TALITOS_TIMEOUT;
 
-	setbits32(priv->reg + TALITOS_RNGURCR_LO, TALITOS_RNGURCR_LO_SR);
-	while (!(in_be32(priv->reg + TALITOS_RNGUSR_LO) & TALITOS_RNGUSR_LO_RD)
+	setbits32(priv->reg_rngu + TALITOS_EURCR_LO, TALITOS_RNGURCR_LO_SR);
+	while (!(in_be32(priv->reg_rngu + TALITOS_EUSR_LO)
+		 & TALITOS_RNGUSR_LO_RD)
 	       && --timeout)
 		cpu_relax();
 	if (timeout == 0) {
@@ -605,7 +758,7 @@ static int talitos_rng_init(struct hwrng *rng)
 	}
 
 	/* start generating */
-	setbits32(priv->reg + TALITOS_RNGUDSR_LO, 0);
+	setbits32(priv->reg_rngu + TALITOS_EUDSR_LO, 0);
 
 	return 0;
 }
@@ -661,7 +814,7 @@ struct talitos_ahash_req_ctx {
 	unsigned int first;
 	unsigned int last;
 	unsigned int to_hash_later;
-	u64 nbuf;
+	unsigned int nbuf;
 	struct scatterlist bufsl[2];
 	struct scatterlist *psrc;
 };
@@ -712,9 +865,10 @@ badkey:
  * @dst_chained: whether dst is chained or not
  * @iv_dma: dma address of iv for checking continuity and link table
  * @dma_len: length of dma mapped link_tbl space
- * @dma_link_tbl: bus physical address of link_tbl
+ * @dma_link_tbl: bus physical address of link_tbl/buf
  * @desc: h/w descriptor
- * @link_tbl: input and output h/w link tables (if {src,dst}_nents > 1)
+ * @link_tbl: input and output h/w link tables (if {src,dst}_nents > 1) (SEC2)
+ * @buf: input and output buffeur (if {src,dst}_nents > 1) (SEC1)
  *
  * if decrypting (with authcheck), or either one of src_nents or dst_nents
  * is greater than 1, an integrity check value is concatenated to the end
@@ -731,7 +885,10 @@ struct talitos_edesc {
 	int dma_len;
 	dma_addr_t dma_link_tbl;
 	struct talitos_desc desc;
-	struct talitos_ptr link_tbl[0];
+	union {
+		struct talitos_ptr link_tbl[0];
+		u8 buf[0];
+	};
 };
 
 static int talitos_map_sg(struct device *dev, struct scatterlist *sg,
@@ -907,8 +1064,8 @@ static int sg_to_link_tbl(struct scatterlist *sg, int sg_count,
 {
 	int n_sg = sg_count;
 
-	while (n_sg--) {
-		to_talitos_ptr(link_tbl_ptr, sg_dma_address(sg));
+	while (sg && n_sg--) {
+		to_talitos_ptr(link_tbl_ptr, sg_dma_address(sg), 0);
 		link_tbl_ptr->len = cpu_to_be16(sg_dma_len(sg));
 		link_tbl_ptr->j_extent = 0;
 		link_tbl_ptr++;
@@ -925,7 +1082,8 @@ static int sg_to_link_tbl(struct scatterlist *sg, int sg_count,
 		sg_count--;
 		link_tbl_ptr--;
 	}
-	be16_add_cpu(&link_tbl_ptr->len, cryptlen);
+	link_tbl_ptr->len = cpu_to_be16(be16_to_cpu(link_tbl_ptr->len)
+					+ cryptlen);
 
 	/* tag end of link table */
 	link_tbl_ptr->j_extent = DESC_PTR_LNKTBL_RETURN;
@@ -953,7 +1111,7 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq,
 
 	/* hmac key */
 	map_single_talitos_ptr(dev, &desc->ptr[0], ctx->authkeylen, &ctx->key,
-			       0, DMA_TO_DEVICE);
+			       DMA_TO_DEVICE);
 
 	/* hmac data */
 	desc->ptr[1].len = cpu_to_be16(areq->assoclen + ivsize);
@@ -962,7 +1120,7 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq,
 		struct talitos_ptr *tbl_ptr = &edesc->link_tbl[tbl_off];
 
 		to_talitos_ptr(&desc->ptr[1], edesc->dma_link_tbl + tbl_off *
-			       sizeof(struct talitos_ptr));
+			       sizeof(struct talitos_ptr), 0);
 		desc->ptr[1].j_extent = DESC_PTR_LNKTBL_JUMP;
 
 		/* assoc_nents - 1 entries for assoc, 1 for IV */
@@ -973,7 +1131,7 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq,
 		tbl_ptr += sg_count - 1;
 		tbl_ptr->j_extent = 0;
 		tbl_ptr++;
-		to_talitos_ptr(tbl_ptr, edesc->iv_dma);
+		to_talitos_ptr(tbl_ptr, edesc->iv_dma, 0);
 		tbl_ptr->len = cpu_to_be16(ivsize);
 		tbl_ptr->j_extent = DESC_PTR_LNKTBL_RETURN;
 
@@ -982,14 +1140,14 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq,
 	} else {
 		if (areq->assoclen)
 			to_talitos_ptr(&desc->ptr[1],
-				       sg_dma_address(areq->assoc));
+				       sg_dma_address(areq->assoc), 0);
 		else
-			to_talitos_ptr(&desc->ptr[1], edesc->iv_dma);
+			to_talitos_ptr(&desc->ptr[1], edesc->iv_dma, 0);
 		desc->ptr[1].j_extent = 0;
 	}
 
 	/* cipher iv */
-	to_talitos_ptr(&desc->ptr[2], edesc->iv_dma);
+	to_talitos_ptr(&desc->ptr[2], edesc->iv_dma, 0);
 	desc->ptr[2].len = cpu_to_be16(ivsize);
 	desc->ptr[2].j_extent = 0;
 	/* Sync needed for the aead_givencrypt case */
@@ -997,7 +1155,7 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq,
 
 	/* cipher key */
 	map_single_talitos_ptr(dev, &desc->ptr[3], ctx->enckeylen,
-			       (char *)&ctx->key + ctx->authkeylen, 0,
+			       (char *)&ctx->key + ctx->authkeylen,
 			       DMA_TO_DEVICE);
 
 	/*
@@ -1015,7 +1173,7 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq,
 				  edesc->src_chained);
 
 	if (sg_count == 1) {
-		to_talitos_ptr(&desc->ptr[4], sg_dma_address(areq->src));
+		to_talitos_ptr(&desc->ptr[4], sg_dma_address(areq->src), 0);
 	} else {
 		sg_link_tbl_len = cryptlen;
 
@@ -1026,14 +1184,14 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq,
 					  &edesc->link_tbl[0]);
 		if (sg_count > 1) {
 			desc->ptr[4].j_extent |= DESC_PTR_LNKTBL_JUMP;
-			to_talitos_ptr(&desc->ptr[4], edesc->dma_link_tbl);
+			to_talitos_ptr(&desc->ptr[4], edesc->dma_link_tbl, 0);
 			dma_sync_single_for_device(dev, edesc->dma_link_tbl,
 						   edesc->dma_len,
 						   DMA_BIDIRECTIONAL);
 		} else {
 			/* Only one segment now, so no link tbl needed */
 			to_talitos_ptr(&desc->ptr[4],
-				       sg_dma_address(areq->src));
+				       sg_dma_address(areq->src), 0);
 		}
 	}
 
@@ -1047,13 +1205,13 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq,
 					  DMA_FROM_DEVICE, edesc->dst_chained);
 
 	if (sg_count == 1) {
-		to_talitos_ptr(&desc->ptr[5], sg_dma_address(areq->dst));
+		to_talitos_ptr(&desc->ptr[5], sg_dma_address(areq->dst), 0);
 	} else {
 		int tbl_off = edesc->src_nents + 1;
 		struct talitos_ptr *tbl_ptr = &edesc->link_tbl[tbl_off];
 
 		to_talitos_ptr(&desc->ptr[5], edesc->dma_link_tbl +
-			       tbl_off * sizeof(struct talitos_ptr));
+			       tbl_off * sizeof(struct talitos_ptr), 0);
 		sg_count = sg_to_link_tbl(areq->dst, sg_count, cryptlen,
 					  tbl_ptr);
 
@@ -1068,14 +1226,14 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq,
 		to_talitos_ptr(tbl_ptr, edesc->dma_link_tbl +
 			       (tbl_off + edesc->dst_nents + 1 +
 				edesc->assoc_nents) *
-			       sizeof(struct talitos_ptr));
+			       sizeof(struct talitos_ptr), 0);
 		desc->ptr[5].j_extent |= DESC_PTR_LNKTBL_JUMP;
 		dma_sync_single_for_device(ctx->dev, edesc->dma_link_tbl,
 					   edesc->dma_len, DMA_BIDIRECTIONAL);
 	}
 
 	/* iv out */
-	map_single_talitos_ptr(dev, &desc->ptr[6], ivsize, ctx->iv, 0,
+	map_single_talitos_ptr(dev, &desc->ptr[6], ivsize, ctx->iv,
 			       DMA_FROM_DEVICE);
 
 	ret = talitos_submit(dev, ctx->ch, desc, callback, areq);
@@ -1095,7 +1253,7 @@ static int sg_count(struct scatterlist *sg_list, int nbytes, bool *chained)
 	int sg_nents = 0;
 
 	*chained = false;
-	while (nbytes > 0) {
+	while (nbytes > 0 && sg) {
 		sg_nents++;
 		nbytes -= sg->length;
 		if (!sg_is_last(sg) && (sg + 1)->length == 0)
@@ -1128,8 +1286,11 @@ static struct talitos_edesc *talitos_edesc_alloc(struct device *dev,
 	dma_addr_t iv_dma = 0;
 	gfp_t flags = cryptoflags & CRYPTO_TFM_REQ_MAY_SLEEP ? GFP_KERNEL :
 		      GFP_ATOMIC;
+	struct talitos_private *priv = dev_get_drvdata(dev);
+	bool is_sec1 = has_ftr_sec1(priv);
+	int max_len = is_sec1 ? TALITOS1_MAX_DATA_LEN : TALITOS2_MAX_DATA_LEN;
 
-	if (cryptlen + authsize > TALITOS_MAX_DATA_LEN) {
+	if (cryptlen + authsize > max_len) {
 		dev_err(dev, "length exceeds h/w max limit\n");
 		return ERR_PTR(-EINVAL);
 	}
@@ -1173,8 +1334,12 @@ static struct talitos_edesc *talitos_edesc_alloc(struct device *dev,
 	 */
 	alloc_len = sizeof(struct talitos_edesc);
 	if (assoc_nents || src_nents || dst_nents) {
-		dma_len = (src_nents + dst_nents + 2 + assoc_nents) *
-			  sizeof(struct talitos_ptr) + authsize;
+		if (is_sec1)
+			dma_len = (src_nents ? cryptlen : 0) +
+				  (dst_nents ? cryptlen : 0);
+		else
+			dma_len = (src_nents + dst_nents + 2 + assoc_nents) *
+				  sizeof(struct talitos_ptr) + authsize;
 		alloc_len += dma_len;
 	} else {
 		dma_len = 0;
@@ -1327,16 +1492,43 @@ static int ablkcipher_setkey(struct crypto_ablkcipher *cipher,
 	return 0;
 }
 
+static void unmap_sg_talitos_ptr(struct device *dev, struct scatterlist *src,
+				 struct scatterlist *dst, unsigned int len,
+				 struct talitos_edesc *edesc)
+{
+	struct talitos_private *priv = dev_get_drvdata(dev);
+	bool is_sec1 = has_ftr_sec1(priv);
+
+	if (is_sec1) {
+		if (!edesc->src_nents) {
+			dma_unmap_sg(dev, src, 1,
+				     dst != src ? DMA_TO_DEVICE
+						: DMA_BIDIRECTIONAL);
+		}
+		if (dst && edesc->dst_nents) {
+			dma_sync_single_for_device(dev,
+						   edesc->dma_link_tbl + len,
+						   len, DMA_FROM_DEVICE);
+			sg_copy_from_buffer(dst, edesc->dst_nents ? : 1,
+					    edesc->buf + len, len);
+		} else if (dst && dst != src) {
+			dma_unmap_sg(dev, dst, 1, DMA_FROM_DEVICE);
+		}
+	} else {
+		talitos_sg_unmap(dev, edesc, src, dst);
+	}
+}
+
 static void common_nonsnoop_unmap(struct device *dev,
 				  struct talitos_edesc *edesc,
 				  struct ablkcipher_request *areq)
 {
 	unmap_single_talitos_ptr(dev, &edesc->desc.ptr[5], DMA_FROM_DEVICE);
+
+	unmap_sg_talitos_ptr(dev, areq->src, areq->dst, areq->nbytes, edesc);
 	unmap_single_talitos_ptr(dev, &edesc->desc.ptr[2], DMA_TO_DEVICE);
 	unmap_single_talitos_ptr(dev, &edesc->desc.ptr[1], DMA_TO_DEVICE);
 
-	talitos_sg_unmap(dev, edesc, areq->src, areq->dst);
-
 	if (edesc->dma_len)
 		dma_unmap_single(dev, edesc->dma_link_tbl, edesc->dma_len,
 				 DMA_BIDIRECTIONAL);
@@ -1358,6 +1550,102 @@ static void ablkcipher_done(struct device *dev,
 	areq->base.complete(&areq->base, err);
 }
 
+int map_sg_in_talitos_ptr(struct device *dev, struct scatterlist *src,
+			  unsigned int len, struct talitos_edesc *edesc,
+			  enum dma_data_direction dir, struct talitos_ptr *ptr)
+{
+	int sg_count;
+	struct talitos_private *priv = dev_get_drvdata(dev);
+	bool is_sec1 = has_ftr_sec1(priv);
+
+	to_talitos_ptr_len(ptr, len, is_sec1);
+
+	if (is_sec1) {
+		sg_count = edesc->src_nents ? : 1;
+
+		if (sg_count == 1) {
+			dma_map_sg(dev, src, 1, dir);
+			to_talitos_ptr(ptr, sg_dma_address(src), is_sec1);
+		} else {
+			sg_copy_to_buffer(src, sg_count, edesc->buf, len);
+			to_talitos_ptr(ptr, edesc->dma_link_tbl, is_sec1);
+			dma_sync_single_for_device(dev, edesc->dma_link_tbl,
+						   len, DMA_TO_DEVICE);
+		}
+	} else {
+		to_talitos_ptr_extent_clear(ptr, is_sec1);
+
+		sg_count = talitos_map_sg(dev, src, edesc->src_nents ? : 1, dir,
+					  edesc->src_chained);
+
+		if (sg_count == 1) {
+			to_talitos_ptr(ptr, sg_dma_address(src), is_sec1);
+		} else {
+			sg_count = sg_to_link_tbl(src, sg_count, len,
+						  &edesc->link_tbl[0]);
+			if (sg_count > 1) {
+				to_talitos_ptr(ptr, edesc->dma_link_tbl, 0);
+				ptr->j_extent |= DESC_PTR_LNKTBL_JUMP;
+				dma_sync_single_for_device(dev,
+							   edesc->dma_link_tbl,
+							   edesc->dma_len,
+							   DMA_BIDIRECTIONAL);
+			} else {
+				/* Only one segment now, so no link tbl needed*/
+				to_talitos_ptr(ptr, sg_dma_address(src),
+					       is_sec1);
+			}
+		}
+	}
+	return sg_count;
+}
+
+void map_sg_out_talitos_ptr(struct device *dev, struct scatterlist *dst,
+			    unsigned int len, struct talitos_edesc *edesc,
+			    enum dma_data_direction dir,
+			    struct talitos_ptr *ptr, int sg_count)
+{
+	struct talitos_private *priv = dev_get_drvdata(dev);
+	bool is_sec1 = has_ftr_sec1(priv);
+
+	if (dir != DMA_NONE)
+		sg_count = talitos_map_sg(dev, dst, edesc->dst_nents ? : 1,
+					  dir, edesc->dst_chained);
+
+	to_talitos_ptr_len(ptr, len, is_sec1);
+
+	if (is_sec1) {
+		if (sg_count == 1) {
+			if (dir != DMA_NONE)
+				dma_map_sg(dev, dst, 1, dir);
+			to_talitos_ptr(ptr, sg_dma_address(dst), is_sec1);
+		} else {
+			to_talitos_ptr(ptr, edesc->dma_link_tbl + len, is_sec1);
+			dma_sync_single_for_device(dev,
+						   edesc->dma_link_tbl + len,
+						   len, DMA_FROM_DEVICE);
+		}
+	} else {
+		to_talitos_ptr_extent_clear(ptr, is_sec1);
+
+		if (sg_count == 1) {
+			to_talitos_ptr(ptr, sg_dma_address(dst), is_sec1);
+		} else {
+			struct talitos_ptr *link_tbl_ptr =
+				&edesc->link_tbl[edesc->src_nents + 1];
+
+			to_talitos_ptr(ptr, edesc->dma_link_tbl +
+					    (edesc->src_nents + 1) *
+					     sizeof(struct talitos_ptr), 0);
+			ptr->j_extent |= DESC_PTR_LNKTBL_JUMP;
+			sg_to_link_tbl(dst, sg_count, len, link_tbl_ptr);
+			dma_sync_single_for_device(dev, edesc->dma_link_tbl,
+						   edesc->dma_len,
+						   DMA_BIDIRECTIONAL);
+		}
+	}
+}
+
 static int common_nonsnoop(struct talitos_edesc *edesc,
 			   struct ablkcipher_request *areq,
 			   void (*callback) (struct device *dev,
@@ -1371,83 +1659,41 @@ static int common_nonsnoop(struct talitos_edesc *edesc,
 	unsigned int cryptlen = areq->nbytes;
 	unsigned int ivsize = crypto_ablkcipher_ivsize(cipher);
 	int sg_count, ret;
+	struct talitos_private *priv = dev_get_drvdata(dev);
+	bool is_sec1 = has_ftr_sec1(priv);
 
 	/* first DWORD empty */
-	desc->ptr[0].len = 0;
-	to_talitos_ptr(&desc->ptr[0], 0);
-	desc->ptr[0].j_extent = 0;
+	desc->ptr[0] = zero_entry;
 
 	/* cipher iv */
-	to_talitos_ptr(&desc->ptr[1], edesc->iv_dma);
-	desc->ptr[1].len = cpu_to_be16(ivsize);
-	desc->ptr[1].j_extent = 0;
+	to_talitos_ptr(&desc->ptr[1], edesc->iv_dma, is_sec1);
+	to_talitos_ptr_len(&desc->ptr[1], ivsize, is_sec1);
+	to_talitos_ptr_extent_clear(&desc->ptr[1], is_sec1);
 
 	/* cipher key */
 	map_single_talitos_ptr(dev, &desc->ptr[2], ctx->keylen,
-			       (char *)&ctx->key, 0, DMA_TO_DEVICE);
+			       (char *)&ctx->key, DMA_TO_DEVICE);
 
 	/*
 	 * cipher in
 	 */
-	desc->ptr[3].len = cpu_to_be16(cryptlen);
-	desc->ptr[3].j_extent = 0;
-
-	sg_count = talitos_map_sg(dev, areq->src, edesc->src_nents ? : 1,
-				  (areq->src == areq->dst) ? DMA_BIDIRECTIONAL
-							   : DMA_TO_DEVICE,
-				  edesc->src_chained);
-
-	if (sg_count == 1) {
-		to_talitos_ptr(&desc->ptr[3], sg_dma_address(areq->src));
-	} else {
-		sg_count = sg_to_link_tbl(areq->src, sg_count, cryptlen,
-					  &edesc->link_tbl[0]);
-		if (sg_count > 1) {
-			to_talitos_ptr(&desc->ptr[3], edesc->dma_link_tbl);
-			desc->ptr[3].j_extent |= DESC_PTR_LNKTBL_JUMP;
-			dma_sync_single_for_device(dev, edesc->dma_link_tbl,
-						   edesc->dma_len,
-						   DMA_BIDIRECTIONAL);
-		} else {
-			/* Only one segment now, so no link tbl needed */
-			to_talitos_ptr(&desc->ptr[3],
-				       sg_dma_address(areq->src));
-		}
-	}
+	sg_count = map_sg_in_talitos_ptr(dev, areq->src, cryptlen, edesc,
+					 (areq->src == areq->dst) ?
+					  DMA_BIDIRECTIONAL : DMA_TO_DEVICE,
+					  &desc->ptr[3]);
 
 	/* cipher out */
-	desc->ptr[4].len = cpu_to_be16(cryptlen);
-	desc->ptr[4].j_extent = 0;
-
-	if (areq->src != areq->dst)
-		sg_count = talitos_map_sg(dev, areq->dst,
-					  edesc->dst_nents ? : 1,
-					  DMA_FROM_DEVICE, edesc->dst_chained);
-
-	if (sg_count == 1) {
-		to_talitos_ptr(&desc->ptr[4], sg_dma_address(areq->dst));
-	} else {
-		struct talitos_ptr *link_tbl_ptr =
-			&edesc->link_tbl[edesc->src_nents + 1];
-
-		to_talitos_ptr(&desc->ptr[4], edesc->dma_link_tbl +
-					      (edesc->src_nents + 1) *
-					      sizeof(struct talitos_ptr));
-		desc->ptr[4].j_extent |= DESC_PTR_LNKTBL_JUMP;
-		sg_count = sg_to_link_tbl(areq->dst, sg_count, cryptlen,
-					  link_tbl_ptr);
-		dma_sync_single_for_device(ctx->dev, edesc->dma_link_tbl,
-					   edesc->dma_len, DMA_BIDIRECTIONAL);
-	}
+	map_sg_out_talitos_ptr(dev, areq->dst, cryptlen, edesc,
+			       (areq->src == areq->dst) ? DMA_NONE
+							: DMA_FROM_DEVICE,
+			       &desc->ptr[4], sg_count);
 
 	/* iv out */
-	map_single_talitos_ptr(dev, &desc->ptr[5], ivsize, ctx->iv, 0,
+	map_single_talitos_ptr(dev, &desc->ptr[5], ivsize, ctx->iv,
 			       DMA_FROM_DEVICE);
 
 	/* last DWORD empty */
-	desc->ptr[6].len = 0;
-	to_talitos_ptr(&desc->ptr[6], 0);
-	desc->ptr[6].j_extent = 0;
+	desc->ptr[6] = zero_entry;
 
 	ret = talitos_submit(dev, ctx->ch, desc, callback, areq);
 	if (ret != -EINPROGRESS) {
@@ -1507,20 +1753,22 @@ static void common_nonsnoop_hash_unmap(struct device *dev,
 				       struct ahash_request *areq)
 {
 	struct talitos_ahash_req_ctx *req_ctx = ahash_request_ctx(areq);
+	struct talitos_private *priv = dev_get_drvdata(dev);
+	bool is_sec1 = has_ftr_sec1(priv);
 
 	unmap_single_talitos_ptr(dev, &edesc->desc.ptr[5], DMA_FROM_DEVICE);
 
+	unmap_sg_talitos_ptr(dev, req_ctx->psrc, NULL, 0, edesc);
+
 	/* When using hashctx-in, must unmap it. */
-	if (edesc->desc.ptr[1].len)
+	if (from_talitos_ptr_len(&edesc->desc.ptr[1], is_sec1))
 		unmap_single_talitos_ptr(dev, &edesc->desc.ptr[1],
 					 DMA_TO_DEVICE);
 
-	if (edesc->desc.ptr[2].len)
+	if (from_talitos_ptr_len(&edesc->desc.ptr[2], is_sec1))
 		unmap_single_talitos_ptr(dev, &edesc->desc.ptr[2],
 					 DMA_TO_DEVICE);
 
-	talitos_sg_unmap(dev, edesc, req_ctx->psrc, NULL);
-
 	if (edesc->dma_len)
 		dma_unmap_single(dev, edesc->dma_link_tbl, edesc->dma_len,
 				 DMA_BIDIRECTIONAL);
@@ -1548,6 +1796,27 @@ static void ahash_done(struct device *dev,
 	areq->base.complete(&areq->base, err);
 }
 
+/*
+ * SEC1 doesn't like hashing of 0 sized message, so we do the padding
+ * ourself and submit a padded block
+ */
+void talitos_handle_buggy_hash(struct talitos_ctx *ctx,
+			       struct talitos_edesc *edesc,
+			       struct talitos_ptr *ptr)
+{
+	static u8 padded_hash[64] = {
+		0x80, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+		0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+		0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+		0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+	};
+
+	pr_err_once("Bug in SEC1, padding ourself\n");
+	edesc->desc.hdr &= ~DESC_HDR_MODE0_MDEU_PAD;
+	map_single_talitos_ptr(ctx->dev, ptr, sizeof(padded_hash),
+			       (char *)padded_hash, DMA_TO_DEVICE);
+}
+
 static int common_nonsnoop_hash(struct talitos_edesc *edesc,
 				struct ahash_request *areq, unsigned int length,
 				void (*callback) (struct device *dev,
@@ -1559,7 +1828,9 @@ static int common_nonsnoop_hash(struct talitos_edesc *edesc,
 	struct talitos_ahash_req_ctx *req_ctx = ahash_request_ctx(areq);
 	struct device *dev = ctx->dev;
 	struct talitos_desc *desc = &edesc->desc;
-	int sg_count, ret;
+	int ret;
+	struct talitos_private *priv = dev_get_drvdata(dev);
+	bool is_sec1 = has_ftr_sec1(priv);
 
 	/* first DWORD empty */
 	desc->ptr[0] = zero_entry;
@@ -1568,7 +1839,7 @@ static int common_nonsnoop_hash(struct talitos_edesc *edesc,
 	if (!req_ctx->first || req_ctx->swinit) {
 		map_single_talitos_ptr(dev, &desc->ptr[1],
 				       req_ctx->hw_context_size,
-				       (char *)req_ctx->hw_context, 0,
+				       (char *)req_ctx->hw_context,
 				       DMA_TO_DEVICE);
 		req_ctx->swinit = 0;
 	} else {
@@ -1580,38 +1851,15 @@ static int common_nonsnoop_hash(struct talitos_edesc *edesc,
 	/* HMAC key */
 	if (ctx->keylen)
 		map_single_talitos_ptr(dev, &desc->ptr[2], ctx->keylen,
-				       (char *)&ctx->key, 0, DMA_TO_DEVICE);
+				       (char *)&ctx->key, DMA_TO_DEVICE);
 	else
 		desc->ptr[2] = zero_entry;
 
 	/*
 	 * data in
 	 */
-	desc->ptr[3].len = cpu_to_be16(length);
-	desc->ptr[3].j_extent = 0;
-
-	sg_count = talitos_map_sg(dev, req_ctx->psrc,
-				  edesc->src_nents ? : 1,
-				  DMA_TO_DEVICE, edesc->src_chained);
-
-	if (sg_count == 1) {
-		to_talitos_ptr(&desc->ptr[3], sg_dma_address(req_ctx->psrc));
-	} else {
-		sg_count = sg_to_link_tbl(req_ctx->psrc, sg_count, length,
-					  &edesc->link_tbl[0]);
-		if (sg_count > 1) {
-			desc->ptr[3].j_extent |= DESC_PTR_LNKTBL_JUMP;
-			to_talitos_ptr(&desc->ptr[3], edesc->dma_link_tbl);
-			dma_sync_single_for_device(ctx->dev,
-						   edesc->dma_link_tbl,
-						   edesc->dma_len,
-						   DMA_BIDIRECTIONAL);
-		} else {
-			/* Only one segment now, so no link tbl needed */
-			to_talitos_ptr(&desc->ptr[3],
-				       sg_dma_address(req_ctx->psrc));
-		}
-	}
+	map_sg_in_talitos_ptr(dev, req_ctx->psrc, length, edesc,
+			      DMA_TO_DEVICE, &desc->ptr[3]);
 
 	/* fifth DWORD empty */
 	desc->ptr[4] = zero_entry;
@@ -1620,15 +1868,18 @@ static int common_nonsnoop_hash(struct talitos_edesc *edesc,
 	if (req_ctx->last)
 		map_single_talitos_ptr(dev, &desc->ptr[5],
 				       crypto_ahash_digestsize(tfm),
-				       areq->result, 0, DMA_FROM_DEVICE);
+				       areq->result, DMA_FROM_DEVICE);
 	else
 		map_single_talitos_ptr(dev, &desc->ptr[5],
 				       req_ctx->hw_context_size,
-				       req_ctx->hw_context, 0, DMA_FROM_DEVICE);
+				       req_ctx->hw_context, DMA_FROM_DEVICE);
 
 	/* last DWORD empty */
 	desc->ptr[6] = zero_entry;
 
+	if (is_sec1 && from_talitos_ptr_len(&desc->ptr[3], true) == 0)
+		talitos_handle_buggy_hash(ctx, edesc, &desc->ptr[3]);
+
 	ret = talitos_submit(dev, ctx->ch, desc, callback, areq);
 	if (ret != -EINPROGRESS) {
 		common_nonsnoop_hash_unmap(dev, edesc, areq);
@@ -2561,6 +2812,7 @@ static struct talitos_crypto_alg *talitos_alg_alloc(struct device *dev,
 		break;
 	default:
 		dev_err(dev, "unknown algorithm type %d\n", t_alg->algt.type);
+		kfree(t_alg);
 		return ERR_PTR(-EINVAL);
 	}
 
@@ -2581,29 +2833,35 @@ static int talitos_probe_irq(struct platform_device *ofdev)
 	struct device_node *np = ofdev->dev.of_node;
 	struct talitos_private *priv = dev_get_drvdata(dev);
 	int err;
+	bool is_sec1 = has_ftr_sec1(priv);
 
 	priv->irq[0] = irq_of_parse_and_map(np, 0);
 	if (!priv->irq[0]) {
 		dev_err(dev, "failed to map irq\n");
 		return -EINVAL;
 	}
+	if (is_sec1) {
+		err = request_irq(priv->irq[0], talitos1_interrupt_4ch, 0,
+				  dev_driver_string(dev), dev);
+		goto primary_out;
+	}
 
 	priv->irq[1] = irq_of_parse_and_map(np, 1);
 
 	/* get the primary irq line */
 	if (!priv->irq[1]) {
-		err = request_irq(priv->irq[0], talitos_interrupt_4ch, 0,
+		err = request_irq(priv->irq[0], talitos2_interrupt_4ch, 0,
 				  dev_driver_string(dev), dev);
 		goto primary_out;
 	}
 
-	err = request_irq(priv->irq[0], talitos_interrupt_ch0_2, 0,
+	err = request_irq(priv->irq[0], talitos2_interrupt_ch0_2, 0,
 			  dev_driver_string(dev), dev);
 	if (err)
 		goto primary_out;
 
 	/* get the secondary irq line */
-	err = request_irq(priv->irq[1], talitos_interrupt_ch1_3, 0,
+	err = request_irq(priv->irq[1], talitos2_interrupt_ch1_3, 0,
 			  dev_driver_string(dev), dev);
 	if (err) {
 		dev_err(dev, "failed to request secondary irq\n");
@@ -2630,6 +2888,7 @@ static int talitos_probe(struct platform_device *ofdev)
 	struct talitos_private *priv;
 	const unsigned int *prop;
 	int i, err;
+	int stride;
 
 	priv = kzalloc(sizeof(struct talitos_private), GFP_KERNEL);
 	if (!priv)
@@ -2643,20 +2902,6 @@ static int talitos_probe(struct platform_device *ofdev)
 
 	spin_lock_init(&priv->reg_lock);
 
-	err = talitos_probe_irq(ofdev);
-	if (err)
-		goto err_out;
-
-	if (!priv->irq[1]) {
-		tasklet_init(&priv->done_task[0], talitos_done_4ch,
-			     (unsigned long)dev);
-	} else {
-		tasklet_init(&priv->done_task[0], talitos_done_ch0_2,
-			     (unsigned long)dev);
-		tasklet_init(&priv->done_task[1], talitos_done_ch1_3,
-			     (unsigned long)dev);
-	}
-
 	priv->reg = of_iomap(np, 0);
 	if (!priv->reg) {
 		dev_err(dev, "failed to of_iomap\n");
@@ -2696,6 +2941,53 @@ static int talitos_probe(struct platform_device *ofdev)
 				  TALITOS_FTR_SHA224_HWINIT |
 				  TALITOS_FTR_HMAC_OK;
 
+	if (of_device_is_compatible(np, "fsl,sec1.0"))
+		priv->features |= TALITOS_FTR_SEC1;
+
+	if (of_device_is_compatible(np, "fsl,sec1.2")) {
+		priv->reg_deu = priv->reg + TALITOS12_DEU;
+		priv->reg_aesu = priv->reg + TALITOS12_AESU;
+		priv->reg_mdeu = priv->reg + TALITOS12_MDEU;
+		stride = TALITOS1_CH_STRIDE;
+	} else if (of_device_is_compatible(np, "fsl,sec1.0")) {
+		priv->reg_deu = priv->reg + TALITOS10_DEU;
+		priv->reg_aesu = priv->reg + TALITOS10_AESU;
+		priv->reg_mdeu = priv->reg + TALITOS10_MDEU;
+		priv->reg_afeu = priv->reg + TALITOS10_AFEU;
+		priv->reg_rngu = priv->reg + TALITOS10_RNGU;
+		priv->reg_pkeu = priv->reg + TALITOS10_PKEU;
+		stride = TALITOS1_CH_STRIDE;
+	} else {
+		priv->reg_deu = priv->reg + TALITOS2_DEU;
+		priv->reg_aesu = priv->reg + TALITOS2_AESU;
+		priv->reg_mdeu = priv->reg + TALITOS2_MDEU;
+		priv->reg_afeu = priv->reg + TALITOS2_AFEU;
+		priv->reg_rngu = priv->reg + TALITOS2_RNGU;
+		priv->reg_pkeu = priv->reg + TALITOS2_PKEU;
+		priv->reg_keu = priv->reg + TALITOS2_KEU;
+		priv->reg_crcu = priv->reg + TALITOS2_CRCU;
+		stride = TALITOS2_CH_STRIDE;
+	}
+
+	err = talitos_probe_irq(ofdev);
+	if (err)
+		goto err_out;
+
+	if (of_device_is_compatible(np, "fsl,sec1.0")) {
+		tasklet_init(&priv->done_task[0], talitos1_done_4ch,
+			     (unsigned long)dev);
+	} else {
+		if (!priv->irq[1]) {
+			tasklet_init(&priv->done_task[0], talitos2_done_4ch,
+				     (unsigned long)dev);
+		} else {
+			tasklet_init(&priv->done_task[0], talitos2_done_ch0_2,
+				     (unsigned long)dev);
+			tasklet_init(&priv->done_task[1], talitos2_done_ch1_3,
+				     (unsigned long)dev);
+		}
+	}
+
 	priv->chan = kzalloc(sizeof(struct talitos_channel) *
 			     priv->num_channels, GFP_KERNEL);
 	if (!priv->chan) {
@@ -2707,7 +2999,7 @@ static int talitos_probe(struct platform_device *ofdev)
 	priv->fifo_len = roundup_pow_of_two(priv->chfifo_len);
 
 	for (i = 0; i < priv->num_channels; i++) {
-		priv->chan[i].reg = priv->reg + TALITOS_CH_STRIDE * (i + 1);
+		priv->chan[i].reg = priv->reg + stride * (i + 1);
 		if (!priv->irq[1] || !(i & 1))
 			priv->chan[i].reg += TALITOS_CH_BASE_OFFSET;
 
@@ -2794,9 +3086,16 @@ err_out:
 }
 
 static const struct of_device_id talitos_match[] = {
+#ifdef CONFIG_CRYPTO_DEV_TALITOS1
+	{
+		.compatible = "fsl,sec1.0",
+	},
+#endif
+#ifdef CONFIG_CRYPTO_DEV_TALITOS2
 	{
 		.compatible = "fsl,sec2.0",
 	},
+#endif
 	{},
 };
 MODULE_DEVICE_TABLE(of, talitos_match);
diff --git a/drivers/crypto/talitos.h b/drivers/crypto/talitos.h
index 61a14054aa39..314daf55e7f7 100644
--- a/drivers/crypto/talitos.h
+++ b/drivers/crypto/talitos.h
@@ -29,7 +29,8 @@
  */
 
 #define TALITOS_TIMEOUT 100000
-#define TALITOS_MAX_DATA_LEN 65535
+#define TALITOS1_MAX_DATA_LEN 32768
+#define TALITOS2_MAX_DATA_LEN 65535
 
 #define DESC_TYPE(desc_hdr) ((be32_to_cpu(desc_hdr) >> 3) & 0x1f)
 #define PRIMARY_EU(desc_hdr) ((be32_to_cpu(desc_hdr) >> 28) & 0xf)
@@ -37,9 +38,17 @@
 
 /* descriptor pointer entry */
 struct talitos_ptr {
-	__be16 len;     /* length */
-	u8 j_extent;    /* jump to sg link table and/or extent */
-	u8 eptr;        /* extended address */
+	union {
+		struct {		/* SEC2 format */
+			__be16 len;     /* length */
+			u8 j_extent;    /* jump to sg link table and/or extent*/
+			u8 eptr;        /* extended address */
+		};
+		struct {			/* SEC1 format */
+			__be16 res;
+			__be16 len1;	/* length */
+		};
+	};
 	__be32 ptr;     /* address */
 };
 
@@ -53,10 +62,16 @@ static const struct talitos_ptr zero_entry = {
 /* descriptor */
 struct talitos_desc {
 	__be32 hdr;                     /* header high bits */
-	__be32 hdr_lo;                  /* header low bits */
+	union {
+		__be32 hdr_lo;		/* header low bits */
+		__be32 hdr1;		/* header for SEC1 */
+	};
 	struct talitos_ptr ptr[7];      /* ptr/len pair array */
+	__be32 next_desc;		/* next descriptor (SEC1) */
 };
 
+#define TALITOS_DESC_SIZE	(sizeof(struct talitos_desc) - sizeof(__be32))
+
 /**
  * talitos_request - descriptor submission request
  * @desc: descriptor pointer (kernel virtual)
@@ -97,6 +112,14 @@ struct talitos_private {
 	struct device *dev;
 	struct platform_device *ofdev;
 	void __iomem *reg;
+	void __iomem *reg_deu;
+	void __iomem *reg_aesu;
+	void __iomem *reg_mdeu;
+	void __iomem *reg_afeu;
+	void __iomem *reg_rngu;
+	void __iomem *reg_pkeu;
+	void __iomem *reg_keu;
+	void __iomem *reg_crcu;
 	int irq[2];
 
 	/* SEC global registers lock  */
@@ -144,49 +167,80 @@ extern int talitos_submit(struct device *dev, int ch, struct talitos_desc *desc,
 #define TALITOS_FTR_HW_AUTH_CHECK 0x00000002
 #define TALITOS_FTR_SHA224_HWINIT 0x00000004
 #define TALITOS_FTR_HMAC_OK 0x00000008
+#define TALITOS_FTR_SEC1 0x00000010
+
+/*
+ * If both CONFIG_CRYPTO_DEV_TALITOS1 and CONFIG_CRYPTO_DEV_TALITOS2 are
+ * defined, we check the features which are set according to the device tree.
+ * Otherwise, we answer true or false directly
+ */
+static inline bool has_ftr_sec1(struct talitos_private *priv)
+{
+#if defined(CONFIG_CRYPTO_DEV_TALITOS1) && defined(CONFIG_CRYPTO_DEV_TALITOS2)
+	return priv->features & TALITOS_FTR_SEC1 ? true : false;
+#elif defined(CONFIG_CRYPTO_DEV_TALITOS1)
+	return true;
+#else
+	return false;
+#endif
+}
 
 /*
  * TALITOS_xxx_LO addresses point to the low data bits (32-63) of the register
  */
 
+#define ISR1_FORMAT(x)			(((x) << 28) | ((x) << 16))
+#define ISR2_FORMAT(x)			(((x) << 4) | (x))
+
 /* global register offset addresses */
 #define TALITOS_MCR			0x1030  /* master control register */
 #define   TALITOS_MCR_RCA0		(1 << 15) /* remap channel 0 */
 #define   TALITOS_MCR_RCA1		(1 << 14) /* remap channel 1 */
 #define   TALITOS_MCR_RCA2		(1 << 13) /* remap channel 2 */
 #define   TALITOS_MCR_RCA3		(1 << 12) /* remap channel 3 */
-#define   TALITOS_MCR_SWR		0x1     /* s/w reset */
+#define   TALITOS1_MCR_SWR		0x1000000     /* s/w reset */
+#define   TALITOS2_MCR_SWR		0x1     /* s/w reset */
 #define TALITOS_MCR_LO			0x1034
 #define TALITOS_IMR			0x1008  /* interrupt mask register */
-#define   TALITOS_IMR_INIT		0x100ff /* enable channel IRQs */
-#define   TALITOS_IMR_DONE		0x00055 /* done IRQs */
+/* enable channel IRQs */
+#define   TALITOS1_IMR_INIT		ISR1_FORMAT(0xf)
+#define   TALITOS1_IMR_DONE		ISR1_FORMAT(0x5) /* done IRQs */
+/* enable channel IRQs */
+#define   TALITOS2_IMR_INIT		(ISR2_FORMAT(0xf) | 0x10000)
+#define   TALITOS2_IMR_DONE		ISR1_FORMAT(0x5) /* done IRQs */
 #define TALITOS_IMR_LO			0x100C
-#define   TALITOS_IMR_LO_INIT		0x20000 /* allow RNGU error IRQs */
+#define   TALITOS1_IMR_LO_INIT		0x2000000 /* allow RNGU error IRQs */
+#define   TALITOS2_IMR_LO_INIT		0x20000 /* allow RNGU error IRQs */
 #define TALITOS_ISR			0x1010  /* interrupt status register */
-#define   TALITOS_ISR_4CHERR		0xaa    /* 4 channel errors mask */
-#define   TALITOS_ISR_4CHDONE		0x55    /* 4 channel done mask */
-#define   TALITOS_ISR_CH_0_2_ERR	0x22    /* channels 0, 2 errors mask */
-#define   TALITOS_ISR_CH_0_2_DONE	0x11    /* channels 0, 2 done mask */
-#define   TALITOS_ISR_CH_1_3_ERR	0x88    /* channels 1, 3 errors mask */
-#define   TALITOS_ISR_CH_1_3_DONE	0x44    /* channels 1, 3 done mask */
+#define   TALITOS1_ISR_4CHERR		ISR1_FORMAT(0xa) /* 4 ch errors mask */
+#define   TALITOS1_ISR_4CHDONE		ISR1_FORMAT(0x5) /* 4 ch done mask */
+#define   TALITOS1_ISR_TEA_ERR		0x00000040
+#define   TALITOS2_ISR_4CHERR		ISR2_FORMAT(0xa) /* 4 ch errors mask */
+#define   TALITOS2_ISR_4CHDONE		ISR2_FORMAT(0x5) /* 4 ch done mask */
+#define   TALITOS2_ISR_CH_0_2_ERR	ISR2_FORMAT(0x2) /* ch 0, 2 err mask */
+#define   TALITOS2_ISR_CH_0_2_DONE	ISR2_FORMAT(0x1) /* ch 0, 2 done mask */
+#define   TALITOS2_ISR_CH_1_3_ERR	ISR2_FORMAT(0x8) /* ch 1, 3 err mask */
+#define   TALITOS2_ISR_CH_1_3_DONE	ISR2_FORMAT(0x4) /* ch 1, 3 done mask */
 #define TALITOS_ISR_LO			0x1014
 #define TALITOS_ICR			0x1018  /* interrupt clear register */
 #define TALITOS_ICR_LO			0x101C
 
 /* channel register address stride */
 #define TALITOS_CH_BASE_OFFSET		0x1000	/* default channel map base */
-#define TALITOS_CH_STRIDE		0x100
+#define TALITOS1_CH_STRIDE		0x1000
+#define TALITOS2_CH_STRIDE		0x100
 
 /* channel configuration register  */
 #define TALITOS_CCCR			0x8
-#define   TALITOS_CCCR_CONT		0x2    /* channel continue */
-#define   TALITOS_CCCR_RESET		0x1    /* channel reset */
+#define   TALITOS2_CCCR_CONT		0x2    /* channel continue on SEC2 */
+#define   TALITOS2_CCCR_RESET		0x1    /* channel reset on SEC2 */
 #define TALITOS_CCCR_LO			0xc
 #define   TALITOS_CCCR_LO_IWSE		0x80   /* chan. ICCR writeback enab. */
 #define   TALITOS_CCCR_LO_EAE		0x20   /* extended address enable */
 #define   TALITOS_CCCR_LO_CDWE		0x10   /* chan. done writeback enab. */
 #define   TALITOS_CCCR_LO_NT		0x4    /* notification type */
 #define   TALITOS_CCCR_LO_CDIE		0x2    /* channel done IRQ enable */
+#define   TALITOS1_CCCR_LO_RESET	0x1    /* channel reset on SEC1 */
 
 /* CCPSR: channel pointer status register */
 #define TALITOS_CCPSR			0x10
@@ -224,37 +278,48 @@ extern int talitos_submit(struct device *dev, int ch, struct talitos_desc *desc,
 #define TALITOS_SCATTER			0xe0
 #define TALITOS_SCATTER_LO		0xe4
 
+/* execution unit registers base */
+#define TALITOS2_DEU			0x2000
+#define TALITOS2_AESU			0x4000
+#define TALITOS2_MDEU			0x6000
+#define TALITOS2_AFEU			0x8000
+#define TALITOS2_RNGU			0xa000
+#define TALITOS2_PKEU			0xc000
+#define TALITOS2_KEU			0xe000
+#define TALITOS2_CRCU			0xf000
+
+#define TALITOS12_AESU			0x4000
+#define TALITOS12_DEU			0x5000
+#define TALITOS12_MDEU			0x6000
+
+#define TALITOS10_AFEU			0x8000
+#define TALITOS10_DEU			0xa000
+#define TALITOS10_MDEU			0xc000
+#define TALITOS10_RNGU			0xe000
+#define TALITOS10_PKEU			0x10000
+#define TALITOS10_AESU			0x12000
+
 /* execution unit interrupt status registers */
-#define TALITOS_DEUISR			0x2030 /* DES unit */
-#define TALITOS_DEUISR_LO		0x2034
-#define TALITOS_AESUISR			0x4030 /* AES unit */
-#define TALITOS_AESUISR_LO		0x4034
-#define TALITOS_MDEUISR			0x6030 /* message digest unit */
-#define TALITOS_MDEUISR_LO		0x6034
-#define TALITOS_MDEUICR			0x6038 /* interrupt control */
-#define TALITOS_MDEUICR_LO		0x603c
+#define TALITOS_EUDSR			0x10	/* data size */
+#define TALITOS_EUDSR_LO		0x14
+#define TALITOS_EURCR			0x18 /* reset control*/
+#define TALITOS_EURCR_LO		0x1c
+#define TALITOS_EUSR			0x28 /* rng status */
+#define TALITOS_EUSR_LO			0x2c
+#define TALITOS_EUISR			0x30
+#define TALITOS_EUISR_LO		0x34
+#define TALITOS_EUICR			0x38 /* int. control */
+#define TALITOS_EUICR_LO		0x3c
+#define TALITOS_EU_FIFO			0x800 /* output FIFO */
+#define TALITOS_EU_FIFO_LO		0x804 /* output FIFO */
+/* DES unit */
+#define   TALITOS1_DEUICR_KPE		0x00200000 /* Key Parity Error */
+/* message digest unit */
 #define   TALITOS_MDEUICR_LO_ICE	0x4000 /* integrity check IRQ enable */
-#define TALITOS_AFEUISR			0x8030 /* arc4 unit */
-#define TALITOS_AFEUISR_LO		0x8034
-#define TALITOS_RNGUISR			0xa030 /* random number unit */
-#define TALITOS_RNGUISR_LO		0xa034
-#define TALITOS_RNGUSR			0xa028 /* rng status */
-#define TALITOS_RNGUSR_LO		0xa02c
+/* random number unit */
 #define   TALITOS_RNGUSR_LO_RD		0x1	/* reset done */
 #define   TALITOS_RNGUSR_LO_OFL		0xff0000/* output FIFO length */
-#define TALITOS_RNGUDSR			0xa010	/* data size */
-#define TALITOS_RNGUDSR_LO		0xa014
-#define TALITOS_RNGU_FIFO		0xa800	/* output FIFO */
-#define TALITOS_RNGU_FIFO_LO		0xa804	/* output FIFO */
-#define TALITOS_RNGURCR			0xa018	/* reset control */
-#define TALITOS_RNGURCR_LO		0xa01c
 #define   TALITOS_RNGURCR_LO_SR		0x1	/* software reset */
-#define TALITOS_PKEUISR			0xc030 /* public key unit */
-#define TALITOS_PKEUISR_LO		0xc034
-#define TALITOS_KEUISR			0xe030 /* kasumi unit */
-#define TALITOS_KEUISR_LO		0xe034
-#define TALITOS_CRCUISR			0xf030 /* cyclic redundancy check unit*/
-#define TALITOS_CRCUISR_LO		0xf034
 
 #define TALITOS_MDEU_CONTEXT_SIZE_MD5_SHA1_SHA256	0x28
 #define TALITOS_MDEU_CONTEXT_SIZE_SHA384_SHA512		0x48
diff --git a/drivers/crypto/ux500/Kconfig b/drivers/crypto/ux500/Kconfig
index b35e5c4b025a..30796441b0a6 100644
--- a/drivers/crypto/ux500/Kconfig
+++ b/drivers/crypto/ux500/Kconfig
@@ -7,6 +7,8 @@
 config CRYPTO_DEV_UX500_CRYP
 	tristate "UX500 crypto driver for CRYP block"
 	depends on CRYPTO_DEV_UX500
+	select CRYPTO_ALGAPI
+	select CRYPTO_BLKCIPHER
 	select CRYPTO_DES
 	help
         This selects the crypto driver for the UX500_CRYP hardware. It supports
@@ -16,7 +18,6 @@ config CRYPTO_DEV_UX500_HASH
         tristate "UX500 crypto driver for HASH block"
         depends on CRYPTO_DEV_UX500
         select CRYPTO_HASH
-        select CRYPTO_HMAC
         help
           This selects the hash driver for the UX500_HASH hardware.
           Depends on UX500/STM DMA if running in DMA mode.
@@ -24,7 +25,6 @@ config CRYPTO_DEV_UX500_HASH
 config CRYPTO_DEV_UX500_DEBUG
 	bool "Activate ux500 platform debug-mode for crypto and hash block"
 	depends on CRYPTO_DEV_UX500_CRYP || CRYPTO_DEV_UX500_HASH
-	default n
 	help
 	  Say Y if you want to add debug prints to ux500_hash and
 	  ux500_cryp devices.
diff --git a/drivers/crypto/vmx/Kconfig b/drivers/crypto/vmx/Kconfig
index 771babf16aa0..89d8208d9851 100644
--- a/drivers/crypto/vmx/Kconfig
+++ b/drivers/crypto/vmx/Kconfig
@@ -1,6 +1,6 @@
 config CRYPTO_DEV_VMX_ENCRYPT
 	tristate "Encryption acceleration support on P8 CPU"
-	depends on PPC64 && CRYPTO_DEV_VMX
+	depends on CRYPTO_DEV_VMX
 	default y
 	help
 	  Support for VMX cryptographic acceleration instructions on Power8 CPU.
diff --git a/drivers/crypto/vmx/Makefile b/drivers/crypto/vmx/Makefile
index c699c6e6c82e..d28ab96a2475 100644
--- a/drivers/crypto/vmx/Makefile
+++ b/drivers/crypto/vmx/Makefile
@@ -4,7 +4,7 @@ vmx-crypto-objs := vmx.o aesp8-ppc.o ghashp8-ppc.o aes.o aes_cbc.o aes_ctr.o gha
 ifeq ($(CONFIG_CPU_LITTLE_ENDIAN),y)
 TARGET := linux-ppc64le
 else
-TARGET := linux-pcc64
+TARGET := linux-ppc64
 endif
 
 quiet_cmd_perl = PERL $@
diff --git a/drivers/crypto/vmx/aes.c b/drivers/crypto/vmx/aes.c
index ab300ea19434..e79e567e43aa 100644
--- a/drivers/crypto/vmx/aes.c
+++ b/drivers/crypto/vmx/aes.c
@@ -30,110 +30,118 @@
 #include "aesp8-ppc.h"
 
 struct p8_aes_ctx {
-    struct crypto_cipher *fallback;
-    struct aes_key enc_key;
-    struct aes_key dec_key;
+	struct crypto_cipher *fallback;
+	struct aes_key enc_key;
+	struct aes_key dec_key;
 };
 
 static int p8_aes_init(struct crypto_tfm *tfm)
 {
-    const char *alg;
-    struct crypto_cipher *fallback;
-    struct p8_aes_ctx *ctx = crypto_tfm_ctx(tfm);
-
-    if (!(alg = crypto_tfm_alg_name(tfm))) {
-        printk(KERN_ERR "Failed to get algorithm name.\n");
-        return -ENOENT;
-    }
-
-    fallback = crypto_alloc_cipher(alg, 0 ,CRYPTO_ALG_NEED_FALLBACK);
-    if (IS_ERR(fallback)) {
-        printk(KERN_ERR "Failed to allocate transformation for '%s': %ld\n",
-                alg, PTR_ERR(fallback));
-        return PTR_ERR(fallback);
-    }
-    printk(KERN_INFO "Using '%s' as fallback implementation.\n",
-            crypto_tfm_alg_driver_name((struct crypto_tfm *) fallback));
-
-    crypto_cipher_set_flags(fallback,
-            crypto_cipher_get_flags((struct crypto_cipher *) tfm));
-    ctx->fallback = fallback;
-
-    return 0;
+	const char *alg;
+	struct crypto_cipher *fallback;
+	struct p8_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	if (!(alg = crypto_tfm_alg_name(tfm))) {
+		printk(KERN_ERR "Failed to get algorithm name.\n");
+		return -ENOENT;
+	}
+
+	fallback = crypto_alloc_cipher(alg, 0, CRYPTO_ALG_NEED_FALLBACK);
+	if (IS_ERR(fallback)) {
+		printk(KERN_ERR
+		       "Failed to allocate transformation for '%s': %ld\n",
+		       alg, PTR_ERR(fallback));
+		return PTR_ERR(fallback);
+	}
+	printk(KERN_INFO "Using '%s' as fallback implementation.\n",
+	       crypto_tfm_alg_driver_name((struct crypto_tfm *) fallback));
+
+	crypto_cipher_set_flags(fallback,
+				crypto_cipher_get_flags((struct
+							 crypto_cipher *)
+							tfm));
+	ctx->fallback = fallback;
+
+	return 0;
 }
 
 static void p8_aes_exit(struct crypto_tfm *tfm)
 {
-    struct p8_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct p8_aes_ctx *ctx = crypto_tfm_ctx(tfm);
 
-    if (ctx->fallback) {
-        crypto_free_cipher(ctx->fallback);
-        ctx->fallback = NULL;
-    }
+	if (ctx->fallback) {
+		crypto_free_cipher(ctx->fallback);
+		ctx->fallback = NULL;
+	}
 }
 
 static int p8_aes_setkey(struct crypto_tfm *tfm, const u8 *key,
-    unsigned int keylen)
+			 unsigned int keylen)
 {
-    int ret;
-    struct p8_aes_ctx *ctx = crypto_tfm_ctx(tfm);
-
-    pagefault_disable();
-    enable_kernel_altivec();
-    ret = aes_p8_set_encrypt_key(key, keylen * 8, &ctx->enc_key);
-    ret += aes_p8_set_decrypt_key(key, keylen * 8, &ctx->dec_key);
-    pagefault_enable();
-    
-    ret += crypto_cipher_setkey(ctx->fallback, key, keylen);
-    return ret;
+	int ret;
+	struct p8_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	preempt_disable();
+	pagefault_disable();
+	enable_kernel_altivec();
+	ret = aes_p8_set_encrypt_key(key, keylen * 8, &ctx->enc_key);
+	ret += aes_p8_set_decrypt_key(key, keylen * 8, &ctx->dec_key);
+	pagefault_enable();
+	preempt_enable();
+
+	ret += crypto_cipher_setkey(ctx->fallback, key, keylen);
+	return ret;
 }
 
 static void p8_aes_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
 {
-    struct p8_aes_ctx *ctx = crypto_tfm_ctx(tfm);
-
-    if (in_interrupt()) {
-        crypto_cipher_encrypt_one(ctx->fallback, dst, src);
-    } else {
-        pagefault_disable();
-        enable_kernel_altivec();
-        aes_p8_encrypt(src, dst, &ctx->enc_key);
-        pagefault_enable();
-    }
+	struct p8_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	if (in_interrupt()) {
+		crypto_cipher_encrypt_one(ctx->fallback, dst, src);
+	} else {
+		preempt_disable();
+		pagefault_disable();
+		enable_kernel_altivec();
+		aes_p8_encrypt(src, dst, &ctx->enc_key);
+		pagefault_enable();
+		preempt_enable();
+	}
 }
 
 static void p8_aes_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
 {
-    struct p8_aes_ctx *ctx = crypto_tfm_ctx(tfm);
-
-    if (in_interrupt()) {
-        crypto_cipher_decrypt_one(ctx->fallback, dst, src);
-    } else {
-        pagefault_disable();
-        enable_kernel_altivec();
-        aes_p8_decrypt(src, dst, &ctx->dec_key);
-        pagefault_enable();
-    }
+	struct p8_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	if (in_interrupt()) {
+		crypto_cipher_decrypt_one(ctx->fallback, dst, src);
+	} else {
+		preempt_disable();
+		pagefault_disable();
+		enable_kernel_altivec();
+		aes_p8_decrypt(src, dst, &ctx->dec_key);
+		pagefault_enable();
+		preempt_enable();
+	}
 }
 
 struct crypto_alg p8_aes_alg = {
-    .cra_name = "aes",
-    .cra_driver_name = "p8_aes",
-    .cra_module = THIS_MODULE,
-    .cra_priority = 1000,
-    .cra_type = NULL,
-    .cra_flags = CRYPTO_ALG_TYPE_CIPHER | CRYPTO_ALG_NEED_FALLBACK,
-    .cra_alignmask = 0,
-    .cra_blocksize = AES_BLOCK_SIZE,
-    .cra_ctxsize = sizeof(struct p8_aes_ctx),
-    .cra_init = p8_aes_init,
-    .cra_exit = p8_aes_exit,
-    .cra_cipher = {
-        .cia_min_keysize = AES_MIN_KEY_SIZE,
-        .cia_max_keysize = AES_MAX_KEY_SIZE,
-        .cia_setkey = p8_aes_setkey,
-        .cia_encrypt = p8_aes_encrypt,
-        .cia_decrypt = p8_aes_decrypt,
-    },
+	.cra_name = "aes",
+	.cra_driver_name = "p8_aes",
+	.cra_module = THIS_MODULE,
+	.cra_priority = 1000,
+	.cra_type = NULL,
+	.cra_flags = CRYPTO_ALG_TYPE_CIPHER | CRYPTO_ALG_NEED_FALLBACK,
+	.cra_alignmask = 0,
+	.cra_blocksize = AES_BLOCK_SIZE,
+	.cra_ctxsize = sizeof(struct p8_aes_ctx),
+	.cra_init = p8_aes_init,
+	.cra_exit = p8_aes_exit,
+	.cra_cipher = {
+		       .cia_min_keysize = AES_MIN_KEY_SIZE,
+		       .cia_max_keysize = AES_MAX_KEY_SIZE,
+		       .cia_setkey = p8_aes_setkey,
+		       .cia_encrypt = p8_aes_encrypt,
+		       .cia_decrypt = p8_aes_decrypt,
+	},
 };
-
diff --git a/drivers/crypto/vmx/aes_cbc.c b/drivers/crypto/vmx/aes_cbc.c
index 1a559b7dddb5..7299995c78ec 100644
--- a/drivers/crypto/vmx/aes_cbc.c
+++ b/drivers/crypto/vmx/aes_cbc.c
@@ -31,154 +31,168 @@
 #include "aesp8-ppc.h"
 
 struct p8_aes_cbc_ctx {
-    struct crypto_blkcipher *fallback;
-    struct aes_key enc_key;
-    struct aes_key dec_key;
+	struct crypto_blkcipher *fallback;
+	struct aes_key enc_key;
+	struct aes_key dec_key;
 };
 
 static int p8_aes_cbc_init(struct crypto_tfm *tfm)
 {
-    const char *alg;
-    struct crypto_blkcipher *fallback;
-    struct p8_aes_cbc_ctx *ctx = crypto_tfm_ctx(tfm);
-
-    if (!(alg = crypto_tfm_alg_name(tfm))) {
-        printk(KERN_ERR "Failed to get algorithm name.\n");
-        return -ENOENT;
-    }
-
-    fallback = crypto_alloc_blkcipher(alg, 0 ,CRYPTO_ALG_NEED_FALLBACK);
-    if (IS_ERR(fallback)) {
-        printk(KERN_ERR "Failed to allocate transformation for '%s': %ld\n",
-                alg, PTR_ERR(fallback));
-        return PTR_ERR(fallback);
-    }
-    printk(KERN_INFO "Using '%s' as fallback implementation.\n",
-            crypto_tfm_alg_driver_name((struct crypto_tfm *) fallback));
-
-    crypto_blkcipher_set_flags(fallback,
-            crypto_blkcipher_get_flags((struct crypto_blkcipher *) tfm));
-    ctx->fallback = fallback;
-
-    return 0;
+	const char *alg;
+	struct crypto_blkcipher *fallback;
+	struct p8_aes_cbc_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	if (!(alg = crypto_tfm_alg_name(tfm))) {
+		printk(KERN_ERR "Failed to get algorithm name.\n");
+		return -ENOENT;
+	}
+
+	fallback =
+	    crypto_alloc_blkcipher(alg, 0, CRYPTO_ALG_NEED_FALLBACK);
+	if (IS_ERR(fallback)) {
+		printk(KERN_ERR
+		       "Failed to allocate transformation for '%s': %ld\n",
+		       alg, PTR_ERR(fallback));
+		return PTR_ERR(fallback);
+	}
+	printk(KERN_INFO "Using '%s' as fallback implementation.\n",
+	       crypto_tfm_alg_driver_name((struct crypto_tfm *) fallback));
+
+	crypto_blkcipher_set_flags(
+		fallback,
+		crypto_blkcipher_get_flags((struct crypto_blkcipher *)tfm));
+	ctx->fallback = fallback;
+
+	return 0;
 }
 
 static void p8_aes_cbc_exit(struct crypto_tfm *tfm)
 {
-    struct p8_aes_cbc_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct p8_aes_cbc_ctx *ctx = crypto_tfm_ctx(tfm);
 
-    if (ctx->fallback) {
-        crypto_free_blkcipher(ctx->fallback);
-        ctx->fallback = NULL;
-    }
+	if (ctx->fallback) {
+		crypto_free_blkcipher(ctx->fallback);
+		ctx->fallback = NULL;
+	}
 }
 
 static int p8_aes_cbc_setkey(struct crypto_tfm *tfm, const u8 *key,
-    unsigned int keylen)
+			     unsigned int keylen)
 {
-    int ret;
-    struct p8_aes_cbc_ctx *ctx = crypto_tfm_ctx(tfm);
-
-    pagefault_disable();
-    enable_kernel_altivec();
-    ret = aes_p8_set_encrypt_key(key, keylen * 8, &ctx->enc_key);
-    ret += aes_p8_set_decrypt_key(key, keylen * 8, &ctx->dec_key);
-    pagefault_enable();
-
-    ret += crypto_blkcipher_setkey(ctx->fallback, key, keylen);
-    return ret;
+	int ret;
+	struct p8_aes_cbc_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	preempt_disable();
+	pagefault_disable();
+	enable_kernel_altivec();
+	ret = aes_p8_set_encrypt_key(key, keylen * 8, &ctx->enc_key);
+	ret += aes_p8_set_decrypt_key(key, keylen * 8, &ctx->dec_key);
+	pagefault_enable();
+	preempt_enable();
+
+	ret += crypto_blkcipher_setkey(ctx->fallback, key, keylen);
+	return ret;
 }
 
 static int p8_aes_cbc_encrypt(struct blkcipher_desc *desc,
-    struct scatterlist *dst, struct scatterlist *src,
-    unsigned int nbytes)
+			      struct scatterlist *dst,
+			      struct scatterlist *src, unsigned int nbytes)
 {
-    int ret;
-    struct blkcipher_walk walk;
-    struct p8_aes_cbc_ctx *ctx = crypto_tfm_ctx(
-            crypto_blkcipher_tfm(desc->tfm));
-    struct blkcipher_desc fallback_desc = {
-        .tfm = ctx->fallback,
-        .info = desc->info,
-        .flags = desc->flags
-    };
-
-    if (in_interrupt()) {
-        ret = crypto_blkcipher_encrypt(&fallback_desc, dst, src, nbytes);
-    } else {
-        pagefault_disable();
-        enable_kernel_altivec();
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-        ret = blkcipher_walk_virt(desc, &walk);
-        while ((nbytes = walk.nbytes)) {
-			aes_p8_cbc_encrypt(walk.src.virt.addr, walk.dst.virt.addr,
-				nbytes & AES_BLOCK_MASK, &ctx->enc_key, walk.iv, 1);
+	int ret;
+	struct blkcipher_walk walk;
+	struct p8_aes_cbc_ctx *ctx =
+		crypto_tfm_ctx(crypto_blkcipher_tfm(desc->tfm));
+	struct blkcipher_desc fallback_desc = {
+		.tfm = ctx->fallback,
+		.info = desc->info,
+		.flags = desc->flags
+	};
+
+	if (in_interrupt()) {
+		ret = crypto_blkcipher_encrypt(&fallback_desc, dst, src,
+					       nbytes);
+	} else {
+		preempt_disable();
+		pagefault_disable();
+		enable_kernel_altivec();
+
+		blkcipher_walk_init(&walk, dst, src, nbytes);
+		ret = blkcipher_walk_virt(desc, &walk);
+		while ((nbytes = walk.nbytes)) {
+			aes_p8_cbc_encrypt(walk.src.virt.addr,
+					   walk.dst.virt.addr,
+					   nbytes & AES_BLOCK_MASK,
+					   &ctx->enc_key, walk.iv, 1);
 			nbytes &= AES_BLOCK_SIZE - 1;
 			ret = blkcipher_walk_done(desc, &walk, nbytes);
-	}
+		}
 
-        pagefault_enable();
-    }
+		pagefault_enable();
+		preempt_enable();
+	}
 
-    return ret;
+	return ret;
 }
 
 static int p8_aes_cbc_decrypt(struct blkcipher_desc *desc,
-    struct scatterlist *dst, struct scatterlist *src,
-    unsigned int nbytes)
+			      struct scatterlist *dst,
+			      struct scatterlist *src, unsigned int nbytes)
 {
-    int ret;
-    struct blkcipher_walk walk;
-    struct p8_aes_cbc_ctx *ctx = crypto_tfm_ctx(
-            crypto_blkcipher_tfm(desc->tfm));
-    struct blkcipher_desc fallback_desc = {
-        .tfm = ctx->fallback,
-        .info = desc->info,
-        .flags = desc->flags
-    };
-
-    if (in_interrupt()) {
-        ret = crypto_blkcipher_decrypt(&fallback_desc, dst, src, nbytes);
-    } else {
-        pagefault_disable();
-        enable_kernel_altivec();
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-        ret = blkcipher_walk_virt(desc, &walk);
-        while ((nbytes = walk.nbytes)) {
-			aes_p8_cbc_encrypt(walk.src.virt.addr, walk.dst.virt.addr,
-				nbytes & AES_BLOCK_MASK, &ctx->dec_key, walk.iv, 0);
+	int ret;
+	struct blkcipher_walk walk;
+	struct p8_aes_cbc_ctx *ctx =
+		crypto_tfm_ctx(crypto_blkcipher_tfm(desc->tfm));
+	struct blkcipher_desc fallback_desc = {
+		.tfm = ctx->fallback,
+		.info = desc->info,
+		.flags = desc->flags
+	};
+
+	if (in_interrupt()) {
+		ret = crypto_blkcipher_decrypt(&fallback_desc, dst, src,
+					       nbytes);
+	} else {
+		preempt_disable();
+		pagefault_disable();
+		enable_kernel_altivec();
+
+		blkcipher_walk_init(&walk, dst, src, nbytes);
+		ret = blkcipher_walk_virt(desc, &walk);
+		while ((nbytes = walk.nbytes)) {
+			aes_p8_cbc_encrypt(walk.src.virt.addr,
+					   walk.dst.virt.addr,
+					   nbytes & AES_BLOCK_MASK,
+					   &ctx->dec_key, walk.iv, 0);
 			nbytes &= AES_BLOCK_SIZE - 1;
 			ret = blkcipher_walk_done(desc, &walk, nbytes);
 		}
 
-        pagefault_enable();
-    }
+		pagefault_enable();
+		preempt_enable();
+	}
 
-    return ret;
+	return ret;
 }
 
 
 struct crypto_alg p8_aes_cbc_alg = {
-    .cra_name = "cbc(aes)",
-    .cra_driver_name = "p8_aes_cbc",
-    .cra_module = THIS_MODULE,
-    .cra_priority = 1000,
-    .cra_type = &crypto_blkcipher_type,
-    .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | CRYPTO_ALG_NEED_FALLBACK,
-    .cra_alignmask = 0,
-    .cra_blocksize = AES_BLOCK_SIZE,
-    .cra_ctxsize = sizeof(struct p8_aes_cbc_ctx),
-    .cra_init = p8_aes_cbc_init,
-    .cra_exit = p8_aes_cbc_exit,
-    .cra_blkcipher = {
-        .ivsize = 0,
-        .min_keysize = AES_MIN_KEY_SIZE,
-        .max_keysize = AES_MAX_KEY_SIZE,
-        .setkey = p8_aes_cbc_setkey,
-        .encrypt = p8_aes_cbc_encrypt,
-        .decrypt = p8_aes_cbc_decrypt,
-    },
+	.cra_name = "cbc(aes)",
+	.cra_driver_name = "p8_aes_cbc",
+	.cra_module = THIS_MODULE,
+	.cra_priority = 1000,
+	.cra_type = &crypto_blkcipher_type,
+	.cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | CRYPTO_ALG_NEED_FALLBACK,
+	.cra_alignmask = 0,
+	.cra_blocksize = AES_BLOCK_SIZE,
+	.cra_ctxsize = sizeof(struct p8_aes_cbc_ctx),
+	.cra_init = p8_aes_cbc_init,
+	.cra_exit = p8_aes_cbc_exit,
+	.cra_blkcipher = {
+			  .ivsize = 0,
+			  .min_keysize = AES_MIN_KEY_SIZE,
+			  .max_keysize = AES_MAX_KEY_SIZE,
+			  .setkey = p8_aes_cbc_setkey,
+			  .encrypt = p8_aes_cbc_encrypt,
+			  .decrypt = p8_aes_cbc_decrypt,
+	},
 };
-
diff --git a/drivers/crypto/vmx/aes_ctr.c b/drivers/crypto/vmx/aes_ctr.c
index 96dbee4bf4a6..7adae42a7b79 100644
--- a/drivers/crypto/vmx/aes_ctr.c
+++ b/drivers/crypto/vmx/aes_ctr.c
@@ -30,138 +30,147 @@
 #include "aesp8-ppc.h"
 
 struct p8_aes_ctr_ctx {
-    struct crypto_blkcipher *fallback;
-    struct aes_key enc_key;
+	struct crypto_blkcipher *fallback;
+	struct aes_key enc_key;
 };
 
 static int p8_aes_ctr_init(struct crypto_tfm *tfm)
 {
-    const char *alg;
-    struct crypto_blkcipher *fallback;
-    struct p8_aes_ctr_ctx *ctx = crypto_tfm_ctx(tfm);
-
-    if (!(alg = crypto_tfm_alg_name(tfm))) {
-        printk(KERN_ERR "Failed to get algorithm name.\n");
-        return -ENOENT;
-    }
-
-    fallback = crypto_alloc_blkcipher(alg, 0 ,CRYPTO_ALG_NEED_FALLBACK);
-    if (IS_ERR(fallback)) {
-        printk(KERN_ERR "Failed to allocate transformation for '%s': %ld\n",
-                alg, PTR_ERR(fallback));
-        return PTR_ERR(fallback);
-    }
-    printk(KERN_INFO "Using '%s' as fallback implementation.\n",
-            crypto_tfm_alg_driver_name((struct crypto_tfm *) fallback));
-
-    crypto_blkcipher_set_flags(fallback,
-            crypto_blkcipher_get_flags((struct crypto_blkcipher *) tfm));
-    ctx->fallback = fallback;
-
-    return 0;
+	const char *alg;
+	struct crypto_blkcipher *fallback;
+	struct p8_aes_ctr_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	if (!(alg = crypto_tfm_alg_name(tfm))) {
+		printk(KERN_ERR "Failed to get algorithm name.\n");
+		return -ENOENT;
+	}
+
+	fallback =
+	    crypto_alloc_blkcipher(alg, 0, CRYPTO_ALG_NEED_FALLBACK);
+	if (IS_ERR(fallback)) {
+		printk(KERN_ERR
+		       "Failed to allocate transformation for '%s': %ld\n",
+		       alg, PTR_ERR(fallback));
+		return PTR_ERR(fallback);
+	}
+	printk(KERN_INFO "Using '%s' as fallback implementation.\n",
+	       crypto_tfm_alg_driver_name((struct crypto_tfm *) fallback));
+
+	crypto_blkcipher_set_flags(
+		fallback,
+		crypto_blkcipher_get_flags((struct crypto_blkcipher *)tfm));
+	ctx->fallback = fallback;
+
+	return 0;
 }
 
 static void p8_aes_ctr_exit(struct crypto_tfm *tfm)
 {
-    struct p8_aes_ctr_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct p8_aes_ctr_ctx *ctx = crypto_tfm_ctx(tfm);
 
-    if (ctx->fallback) {
-        crypto_free_blkcipher(ctx->fallback);
-        ctx->fallback = NULL;
-    }
+	if (ctx->fallback) {
+		crypto_free_blkcipher(ctx->fallback);
+		ctx->fallback = NULL;
+	}
 }
 
 static int p8_aes_ctr_setkey(struct crypto_tfm *tfm, const u8 *key,
-    unsigned int keylen)
+			     unsigned int keylen)
 {
-    int ret;
-    struct p8_aes_ctr_ctx *ctx = crypto_tfm_ctx(tfm);
+	int ret;
+	struct p8_aes_ctr_ctx *ctx = crypto_tfm_ctx(tfm);
 
-    pagefault_disable();
-    enable_kernel_altivec();
-    ret = aes_p8_set_encrypt_key(key, keylen * 8, &ctx->enc_key);
-    pagefault_enable();
+	pagefault_disable();
+	enable_kernel_altivec();
+	ret = aes_p8_set_encrypt_key(key, keylen * 8, &ctx->enc_key);
+	pagefault_enable();
 
-    ret += crypto_blkcipher_setkey(ctx->fallback, key, keylen);
-    return ret;
+	ret += crypto_blkcipher_setkey(ctx->fallback, key, keylen);
+	return ret;
 }
 
 static void p8_aes_ctr_final(struct p8_aes_ctr_ctx *ctx,
-                struct blkcipher_walk *walk)
+			     struct blkcipher_walk *walk)
 {
-    u8 *ctrblk = walk->iv;
-    u8 keystream[AES_BLOCK_SIZE];
-    u8 *src = walk->src.virt.addr;
-    u8 *dst = walk->dst.virt.addr;
-    unsigned int nbytes = walk->nbytes;
-
-    pagefault_disable();
-    enable_kernel_altivec();
-    aes_p8_encrypt(ctrblk, keystream, &ctx->enc_key);
-    pagefault_enable();
-
-    crypto_xor(keystream, src, nbytes);
-    memcpy(dst, keystream, nbytes);
-    crypto_inc(ctrblk, AES_BLOCK_SIZE);
+	u8 *ctrblk = walk->iv;
+	u8 keystream[AES_BLOCK_SIZE];
+	u8 *src = walk->src.virt.addr;
+	u8 *dst = walk->dst.virt.addr;
+	unsigned int nbytes = walk->nbytes;
+
+	pagefault_disable();
+	enable_kernel_altivec();
+	aes_p8_encrypt(ctrblk, keystream, &ctx->enc_key);
+	pagefault_enable();
+
+	crypto_xor(keystream, src, nbytes);
+	memcpy(dst, keystream, nbytes);
+	crypto_inc(ctrblk, AES_BLOCK_SIZE);
 }
 
 static int p8_aes_ctr_crypt(struct blkcipher_desc *desc,
-    struct scatterlist *dst, struct scatterlist *src,
-    unsigned int nbytes)
+			    struct scatterlist *dst,
+			    struct scatterlist *src, unsigned int nbytes)
 {
-    int ret;
-    struct blkcipher_walk walk;
-    struct p8_aes_ctr_ctx *ctx = crypto_tfm_ctx(
-            crypto_blkcipher_tfm(desc->tfm));
-    struct blkcipher_desc fallback_desc = {
-        .tfm = ctx->fallback,
-        .info = desc->info,
-        .flags = desc->flags
-    };
-
-    if (in_interrupt()) {
-        ret = crypto_blkcipher_encrypt(&fallback_desc, dst, src, nbytes);
-    } else {
-        blkcipher_walk_init(&walk, dst, src, nbytes);
-        ret = blkcipher_walk_virt_block(desc, &walk, AES_BLOCK_SIZE);
-        while ((nbytes = walk.nbytes) >= AES_BLOCK_SIZE) {
-            pagefault_disable();
-            enable_kernel_altivec();
-            aes_p8_ctr32_encrypt_blocks(walk.src.virt.addr, walk.dst.virt.addr,
-                (nbytes & AES_BLOCK_MASK)/AES_BLOCK_SIZE, &ctx->enc_key, walk.iv);
-            pagefault_enable();
-
-            crypto_inc(walk.iv, AES_BLOCK_SIZE);
-            nbytes &= AES_BLOCK_SIZE - 1;
-            ret = blkcipher_walk_done(desc, &walk, nbytes);
-        }
-        if (walk.nbytes) {
-            p8_aes_ctr_final(ctx, &walk);
-            ret = blkcipher_walk_done(desc, &walk, 0);
-        }
-    }
-
-    return ret;
+	int ret;
+	struct blkcipher_walk walk;
+	struct p8_aes_ctr_ctx *ctx =
+		crypto_tfm_ctx(crypto_blkcipher_tfm(desc->tfm));
+	struct blkcipher_desc fallback_desc = {
+		.tfm = ctx->fallback,
+		.info = desc->info,
+		.flags = desc->flags
+	};
+
+	if (in_interrupt()) {
+		ret = crypto_blkcipher_encrypt(&fallback_desc, dst, src,
+					       nbytes);
+	} else {
+		blkcipher_walk_init(&walk, dst, src, nbytes);
+		ret = blkcipher_walk_virt_block(desc, &walk, AES_BLOCK_SIZE);
+		while ((nbytes = walk.nbytes) >= AES_BLOCK_SIZE) {
+			pagefault_disable();
+			enable_kernel_altivec();
+			aes_p8_ctr32_encrypt_blocks(walk.src.virt.addr,
+						    walk.dst.virt.addr,
+						    (nbytes &
+						     AES_BLOCK_MASK) /
+						    AES_BLOCK_SIZE,
+						    &ctx->enc_key,
+						    walk.iv);
+			pagefault_enable();
+
+			crypto_inc(walk.iv, AES_BLOCK_SIZE);
+			nbytes &= AES_BLOCK_SIZE - 1;
+			ret = blkcipher_walk_done(desc, &walk, nbytes);
+		}
+		if (walk.nbytes) {
+			p8_aes_ctr_final(ctx, &walk);
+			ret = blkcipher_walk_done(desc, &walk, 0);
+		}
+	}
+
+	return ret;
 }
 
 struct crypto_alg p8_aes_ctr_alg = {
-    .cra_name = "ctr(aes)",
-    .cra_driver_name = "p8_aes_ctr",
-    .cra_module = THIS_MODULE,
-    .cra_priority = 1000,
-    .cra_type = &crypto_blkcipher_type,
-    .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | CRYPTO_ALG_NEED_FALLBACK,
-    .cra_alignmask = 0,
-    .cra_blocksize = 1,
-    .cra_ctxsize = sizeof(struct p8_aes_ctr_ctx),
-    .cra_init = p8_aes_ctr_init,
-    .cra_exit = p8_aes_ctr_exit,
-    .cra_blkcipher = {
-        .ivsize = 0,
-        .min_keysize = AES_MIN_KEY_SIZE,
-        .max_keysize = AES_MAX_KEY_SIZE,
-        .setkey = p8_aes_ctr_setkey,
-        .encrypt = p8_aes_ctr_crypt,
-        .decrypt = p8_aes_ctr_crypt,
-    },
+	.cra_name = "ctr(aes)",
+	.cra_driver_name = "p8_aes_ctr",
+	.cra_module = THIS_MODULE,
+	.cra_priority = 1000,
+	.cra_type = &crypto_blkcipher_type,
+	.cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | CRYPTO_ALG_NEED_FALLBACK,
+	.cra_alignmask = 0,
+	.cra_blocksize = 1,
+	.cra_ctxsize = sizeof(struct p8_aes_ctr_ctx),
+	.cra_init = p8_aes_ctr_init,
+	.cra_exit = p8_aes_ctr_exit,
+	.cra_blkcipher = {
+			  .ivsize = 0,
+			  .min_keysize = AES_MIN_KEY_SIZE,
+			  .max_keysize = AES_MAX_KEY_SIZE,
+			  .setkey = p8_aes_ctr_setkey,
+			  .encrypt = p8_aes_ctr_crypt,
+			  .decrypt = p8_aes_ctr_crypt,
+	},
 };
diff --git a/drivers/crypto/vmx/aesp8-ppc.h b/drivers/crypto/vmx/aesp8-ppc.h
index e963945a83e1..4cd34ee54a94 100644
--- a/drivers/crypto/vmx/aesp8-ppc.h
+++ b/drivers/crypto/vmx/aesp8-ppc.h
@@ -4,17 +4,18 @@
 #define AES_BLOCK_MASK  (~(AES_BLOCK_SIZE-1))
 
 struct aes_key {
-    u8 key[AES_MAX_KEYLENGTH];
-    int rounds;
+	u8 key[AES_MAX_KEYLENGTH];
+	int rounds;
 };
 
 int aes_p8_set_encrypt_key(const u8 *userKey, const int bits,
-        struct aes_key *key);
+			   struct aes_key *key);
 int aes_p8_set_decrypt_key(const u8 *userKey, const int bits,
-        struct aes_key *key);
+			   struct aes_key *key);
 void aes_p8_encrypt(const u8 *in, u8 *out, const struct aes_key *key);
-void aes_p8_decrypt(const u8 *in, u8 *out,const struct aes_key *key);
+void aes_p8_decrypt(const u8 *in, u8 *out, const struct aes_key *key);
 void aes_p8_cbc_encrypt(const u8 *in, u8 *out, size_t len,
-		const struct aes_key *key, u8 *iv, const int enc);
+			const struct aes_key *key, u8 *iv, const int enc);
 void aes_p8_ctr32_encrypt_blocks(const u8 *in, u8 *out,
-        size_t len, const struct aes_key *key, const u8 *iv);
+				 size_t len, const struct aes_key *key,
+				 const u8 *iv);
diff --git a/drivers/crypto/vmx/ghash.c b/drivers/crypto/vmx/ghash.c
index d0ffe277af5c..b5e29002b666 100644
--- a/drivers/crypto/vmx/ghash.c
+++ b/drivers/crypto/vmx/ghash.c
@@ -39,176 +39,188 @@
 void gcm_init_p8(u128 htable[16], const u64 Xi[2]);
 void gcm_gmult_p8(u64 Xi[2], const u128 htable[16]);
 void gcm_ghash_p8(u64 Xi[2], const u128 htable[16],
-        const u8 *in,size_t len);
+		  const u8 *in, size_t len);
 
 struct p8_ghash_ctx {
-    u128 htable[16];
-    struct crypto_shash *fallback;
+	u128 htable[16];
+	struct crypto_shash *fallback;
 };
 
 struct p8_ghash_desc_ctx {
-    u64 shash[2];
-    u8 buffer[GHASH_DIGEST_SIZE];
-    int bytes;
-    struct shash_desc fallback_desc;
+	u64 shash[2];
+	u8 buffer[GHASH_DIGEST_SIZE];
+	int bytes;
+	struct shash_desc fallback_desc;
 };
 
 static int p8_ghash_init_tfm(struct crypto_tfm *tfm)
 {
-    const char *alg;
-    struct crypto_shash *fallback;
-    struct crypto_shash *shash_tfm = __crypto_shash_cast(tfm);
-    struct p8_ghash_ctx *ctx = crypto_tfm_ctx(tfm);
-
-    if (!(alg = crypto_tfm_alg_name(tfm))) {
-        printk(KERN_ERR "Failed to get algorithm name.\n");
-        return -ENOENT;
-    }
-
-    fallback = crypto_alloc_shash(alg, 0 ,CRYPTO_ALG_NEED_FALLBACK);
-    if (IS_ERR(fallback)) {
-        printk(KERN_ERR "Failed to allocate transformation for '%s': %ld\n",
-                alg, PTR_ERR(fallback));
-        return PTR_ERR(fallback);
-    }
-    printk(KERN_INFO "Using '%s' as fallback implementation.\n",
-            crypto_tfm_alg_driver_name(crypto_shash_tfm(fallback)));
-
-    crypto_shash_set_flags(fallback,
-            crypto_shash_get_flags((struct crypto_shash *) tfm));
-    ctx->fallback = fallback;
-
-    shash_tfm->descsize = sizeof(struct p8_ghash_desc_ctx)
-        + crypto_shash_descsize(fallback);
-
-    return 0;
+	const char *alg;
+	struct crypto_shash *fallback;
+	struct crypto_shash *shash_tfm = __crypto_shash_cast(tfm);
+	struct p8_ghash_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	if (!(alg = crypto_tfm_alg_name(tfm))) {
+		printk(KERN_ERR "Failed to get algorithm name.\n");
+		return -ENOENT;
+	}
+
+	fallback = crypto_alloc_shash(alg, 0, CRYPTO_ALG_NEED_FALLBACK);
+	if (IS_ERR(fallback)) {
+		printk(KERN_ERR
+		       "Failed to allocate transformation for '%s': %ld\n",
+		       alg, PTR_ERR(fallback));
+		return PTR_ERR(fallback);
+	}
+	printk(KERN_INFO "Using '%s' as fallback implementation.\n",
+	       crypto_tfm_alg_driver_name(crypto_shash_tfm(fallback)));
+
+	crypto_shash_set_flags(fallback,
+			       crypto_shash_get_flags((struct crypto_shash
+						       *) tfm));
+	ctx->fallback = fallback;
+
+	shash_tfm->descsize = sizeof(struct p8_ghash_desc_ctx)
+	    + crypto_shash_descsize(fallback);
+
+	return 0;
 }
 
 static void p8_ghash_exit_tfm(struct crypto_tfm *tfm)
 {
-    struct p8_ghash_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct p8_ghash_ctx *ctx = crypto_tfm_ctx(tfm);
 
-    if (ctx->fallback) {
-        crypto_free_shash(ctx->fallback);
-        ctx->fallback = NULL;
-    }
+	if (ctx->fallback) {
+		crypto_free_shash(ctx->fallback);
+		ctx->fallback = NULL;
+	}
 }
 
 static int p8_ghash_init(struct shash_desc *desc)
 {
-    struct p8_ghash_ctx *ctx = crypto_tfm_ctx(crypto_shash_tfm(desc->tfm));
-    struct p8_ghash_desc_ctx *dctx = shash_desc_ctx(desc);
-
-    dctx->bytes = 0;
-    memset(dctx->shash, 0, GHASH_DIGEST_SIZE);
-    dctx->fallback_desc.tfm = ctx->fallback;
-    dctx->fallback_desc.flags = desc->flags;
-    return crypto_shash_init(&dctx->fallback_desc);
+	struct p8_ghash_ctx *ctx = crypto_tfm_ctx(crypto_shash_tfm(desc->tfm));
+	struct p8_ghash_desc_ctx *dctx = shash_desc_ctx(desc);
+
+	dctx->bytes = 0;
+	memset(dctx->shash, 0, GHASH_DIGEST_SIZE);
+	dctx->fallback_desc.tfm = ctx->fallback;
+	dctx->fallback_desc.flags = desc->flags;
+	return crypto_shash_init(&dctx->fallback_desc);
 }
 
 static int p8_ghash_setkey(struct crypto_shash *tfm, const u8 *key,
-    unsigned int keylen)
+			   unsigned int keylen)
 {
-    struct p8_ghash_ctx *ctx = crypto_tfm_ctx(crypto_shash_tfm(tfm));
-
-    if (keylen != GHASH_KEY_LEN)
-        return -EINVAL;
-
-    pagefault_disable();
-    enable_kernel_altivec();
-    enable_kernel_fp();
-    gcm_init_p8(ctx->htable, (const u64 *) key);
-    pagefault_enable();
-    return crypto_shash_setkey(ctx->fallback, key, keylen);
+	struct p8_ghash_ctx *ctx = crypto_tfm_ctx(crypto_shash_tfm(tfm));
+
+	if (keylen != GHASH_KEY_LEN)
+		return -EINVAL;
+
+	preempt_disable();
+	pagefault_disable();
+	enable_kernel_altivec();
+	enable_kernel_fp();
+	gcm_init_p8(ctx->htable, (const u64 *) key);
+	pagefault_enable();
+	preempt_enable();
+	return crypto_shash_setkey(ctx->fallback, key, keylen);
 }
 
 static int p8_ghash_update(struct shash_desc *desc,
-        const u8 *src, unsigned int srclen)
+			   const u8 *src, unsigned int srclen)
 {
-    unsigned int len;
-    struct p8_ghash_ctx *ctx = crypto_tfm_ctx(crypto_shash_tfm(desc->tfm));
-    struct p8_ghash_desc_ctx *dctx = shash_desc_ctx(desc);
-
-    if (IN_INTERRUPT) {
-        return crypto_shash_update(&dctx->fallback_desc, src, srclen);
-    } else {
-        if (dctx->bytes) {
-            if (dctx->bytes + srclen < GHASH_DIGEST_SIZE) {
-                memcpy(dctx->buffer + dctx->bytes, src, srclen);
-                dctx->bytes += srclen;
-                return 0;
-            }
-            memcpy(dctx->buffer + dctx->bytes, src,
-                    GHASH_DIGEST_SIZE - dctx->bytes);
-            pagefault_disable();
-            enable_kernel_altivec();
-            enable_kernel_fp();
-            gcm_ghash_p8(dctx->shash, ctx->htable, dctx->buffer,
-                    GHASH_DIGEST_SIZE);
-            pagefault_enable();
-            src += GHASH_DIGEST_SIZE - dctx->bytes;
-            srclen -= GHASH_DIGEST_SIZE - dctx->bytes;
-            dctx->bytes = 0;
-        }
-        len = srclen & ~(GHASH_DIGEST_SIZE - 1);
-        if (len) {
-            pagefault_disable();
-            enable_kernel_altivec();
-            enable_kernel_fp();
-            gcm_ghash_p8(dctx->shash, ctx->htable, src, len);
-            pagefault_enable();
-            src += len;
-            srclen -= len;
-        }
-        if (srclen) {
-            memcpy(dctx->buffer, src, srclen);
-            dctx->bytes = srclen;
-        }
-        return 0;
-    }
+	unsigned int len;
+	struct p8_ghash_ctx *ctx = crypto_tfm_ctx(crypto_shash_tfm(desc->tfm));
+	struct p8_ghash_desc_ctx *dctx = shash_desc_ctx(desc);
+
+	if (IN_INTERRUPT) {
+		return crypto_shash_update(&dctx->fallback_desc, src,
+					   srclen);
+	} else {
+		if (dctx->bytes) {
+			if (dctx->bytes + srclen < GHASH_DIGEST_SIZE) {
+				memcpy(dctx->buffer + dctx->bytes, src,
+				       srclen);
+				dctx->bytes += srclen;
+				return 0;
+			}
+			memcpy(dctx->buffer + dctx->bytes, src,
+			       GHASH_DIGEST_SIZE - dctx->bytes);
+			preempt_disable();
+			pagefault_disable();
+			enable_kernel_altivec();
+			enable_kernel_fp();
+			gcm_ghash_p8(dctx->shash, ctx->htable,
+				     dctx->buffer, GHASH_DIGEST_SIZE);
+			pagefault_enable();
+			preempt_enable();
+			src += GHASH_DIGEST_SIZE - dctx->bytes;
+			srclen -= GHASH_DIGEST_SIZE - dctx->bytes;
+			dctx->bytes = 0;
+		}
+		len = srclen & ~(GHASH_DIGEST_SIZE - 1);
+		if (len) {
+			preempt_disable();
+			pagefault_disable();
+			enable_kernel_altivec();
+			enable_kernel_fp();
+			gcm_ghash_p8(dctx->shash, ctx->htable, src, len);
+			pagefault_enable();
+			preempt_enable();
+			src += len;
+			srclen -= len;
+		}
+		if (srclen) {
+			memcpy(dctx->buffer, src, srclen);
+			dctx->bytes = srclen;
+		}
+		return 0;
+	}
 }
 
 static int p8_ghash_final(struct shash_desc *desc, u8 *out)
 {
-    int i;
-    struct p8_ghash_ctx *ctx = crypto_tfm_ctx(crypto_shash_tfm(desc->tfm));
-    struct p8_ghash_desc_ctx *dctx = shash_desc_ctx(desc);
-
-    if (IN_INTERRUPT) {
-        return crypto_shash_final(&dctx->fallback_desc, out);
-    } else {
-        if (dctx->bytes) {
-            for (i = dctx->bytes; i < GHASH_DIGEST_SIZE; i++)
-                dctx->buffer[i] = 0;
-            pagefault_disable();
-            enable_kernel_altivec();
-            enable_kernel_fp();
-            gcm_ghash_p8(dctx->shash, ctx->htable, dctx->buffer,
-                    GHASH_DIGEST_SIZE);
-            pagefault_enable();
-            dctx->bytes = 0;
-        }
-        memcpy(out, dctx->shash, GHASH_DIGEST_SIZE);
-        return 0;
-    }
+	int i;
+	struct p8_ghash_ctx *ctx = crypto_tfm_ctx(crypto_shash_tfm(desc->tfm));
+	struct p8_ghash_desc_ctx *dctx = shash_desc_ctx(desc);
+
+	if (IN_INTERRUPT) {
+		return crypto_shash_final(&dctx->fallback_desc, out);
+	} else {
+		if (dctx->bytes) {
+			for (i = dctx->bytes; i < GHASH_DIGEST_SIZE; i++)
+				dctx->buffer[i] = 0;
+			preempt_disable();
+			pagefault_disable();
+			enable_kernel_altivec();
+			enable_kernel_fp();
+			gcm_ghash_p8(dctx->shash, ctx->htable,
+				     dctx->buffer, GHASH_DIGEST_SIZE);
+			pagefault_enable();
+			preempt_enable();
+			dctx->bytes = 0;
+		}
+		memcpy(out, dctx->shash, GHASH_DIGEST_SIZE);
+		return 0;
+	}
 }
 
 struct shash_alg p8_ghash_alg = {
-    .digestsize = GHASH_DIGEST_SIZE,
-    .init       = p8_ghash_init,
-    .update     = p8_ghash_update,
-    .final      = p8_ghash_final,
-    .setkey     = p8_ghash_setkey,
-    .descsize   = sizeof(struct p8_ghash_desc_ctx),
-    .base       = {
-        .cra_name = "ghash",
-        .cra_driver_name = "p8_ghash",
-        .cra_priority = 1000,
-        .cra_flags = CRYPTO_ALG_TYPE_SHASH | CRYPTO_ALG_NEED_FALLBACK,
-        .cra_blocksize = GHASH_BLOCK_SIZE,
-        .cra_ctxsize = sizeof(struct p8_ghash_ctx),
-        .cra_module = THIS_MODULE,
-        .cra_init = p8_ghash_init_tfm,
-        .cra_exit = p8_ghash_exit_tfm,
-    },
+	.digestsize = GHASH_DIGEST_SIZE,
+	.init = p8_ghash_init,
+	.update = p8_ghash_update,
+	.final = p8_ghash_final,
+	.setkey = p8_ghash_setkey,
+	.descsize = sizeof(struct p8_ghash_desc_ctx),
+	.base = {
+		 .cra_name = "ghash",
+		 .cra_driver_name = "p8_ghash",
+		 .cra_priority = 1000,
+		 .cra_flags = CRYPTO_ALG_TYPE_SHASH | CRYPTO_ALG_NEED_FALLBACK,
+		 .cra_blocksize = GHASH_BLOCK_SIZE,
+		 .cra_ctxsize = sizeof(struct p8_ghash_ctx),
+		 .cra_module = THIS_MODULE,
+		 .cra_init = p8_ghash_init_tfm,
+		 .cra_exit = p8_ghash_exit_tfm,
+	},
 };
diff --git a/drivers/crypto/vmx/vmx.c b/drivers/crypto/vmx/vmx.c
index 44d8d5cfe40d..e163d5770438 100644
--- a/drivers/crypto/vmx/vmx.c
+++ b/drivers/crypto/vmx/vmx.c
@@ -32,57 +32,57 @@ extern struct crypto_alg p8_aes_alg;
 extern struct crypto_alg p8_aes_cbc_alg;
 extern struct crypto_alg p8_aes_ctr_alg;
 static struct crypto_alg *algs[] = {
-    &p8_aes_alg,
-    &p8_aes_cbc_alg,
-    &p8_aes_ctr_alg,
-    NULL,
+	&p8_aes_alg,
+	&p8_aes_cbc_alg,
+	&p8_aes_ctr_alg,
+	NULL,
 };
 
 int __init p8_init(void)
 {
-    int ret = 0;
-    struct crypto_alg **alg_it;
+	int ret = 0;
+	struct crypto_alg **alg_it;
 
-    if (!(cur_cpu_spec->cpu_user_features2 & PPC_FEATURE2_VEC_CRYPTO))
-        return -ENODEV;
+	if (!(cur_cpu_spec->cpu_user_features2 & PPC_FEATURE2_VEC_CRYPTO))
+		return -ENODEV;
 
-    for (alg_it = algs; *alg_it; alg_it++) {
-        ret = crypto_register_alg(*alg_it);
-        printk(KERN_INFO "crypto_register_alg '%s' = %d\n",
-                (*alg_it)->cra_name, ret);
-        if (ret) {
-            for (alg_it--; alg_it >= algs; alg_it--)
-                crypto_unregister_alg(*alg_it);
-            break;
-        }
-    }
-    if (ret)
-        return ret;
+	for (alg_it = algs; *alg_it; alg_it++) {
+		ret = crypto_register_alg(*alg_it);
+		printk(KERN_INFO "crypto_register_alg '%s' = %d\n",
+		       (*alg_it)->cra_name, ret);
+		if (ret) {
+			for (alg_it--; alg_it >= algs; alg_it--)
+				crypto_unregister_alg(*alg_it);
+			break;
+		}
+	}
+	if (ret)
+		return ret;
 
-    ret = crypto_register_shash(&p8_ghash_alg);
-    if (ret) {
-        for (alg_it = algs; *alg_it; alg_it++)
-            crypto_unregister_alg(*alg_it);
-    }
-    return ret;
+	ret = crypto_register_shash(&p8_ghash_alg);
+	if (ret) {
+		for (alg_it = algs; *alg_it; alg_it++)
+			crypto_unregister_alg(*alg_it);
+	}
+	return ret;
 }
 
 void __exit p8_exit(void)
 {
-    struct crypto_alg **alg_it;
+	struct crypto_alg **alg_it;
 
-    for (alg_it = algs; *alg_it; alg_it++) {
-        printk(KERN_INFO "Removing '%s'\n", (*alg_it)->cra_name);
-        crypto_unregister_alg(*alg_it);
-    }
-    crypto_unregister_shash(&p8_ghash_alg);
+	for (alg_it = algs; *alg_it; alg_it++) {
+		printk(KERN_INFO "Removing '%s'\n", (*alg_it)->cra_name);
+		crypto_unregister_alg(*alg_it);
+	}
+	crypto_unregister_shash(&p8_ghash_alg);
 }
 
 module_init(p8_init);
 module_exit(p8_exit);
 
 MODULE_AUTHOR("Marcelo Cerri<mhcerri@br.ibm.com>");
-MODULE_DESCRIPTION("IBM VMX cryptogaphic acceleration instructions support on Power 8");
+MODULE_DESCRIPTION("IBM VMX cryptographic acceleration instructions "
+		   "support on Power 8");
 MODULE_LICENSE("GPL");
 MODULE_VERSION("1.0.0");
-
diff --git a/drivers/dma/mic_x100_dma.c b/drivers/dma/mic_x100_dma.c
index 6de2e677be04..74d9db05a5ad 100644
--- a/drivers/dma/mic_x100_dma.c
+++ b/drivers/dma/mic_x100_dma.c
@@ -22,6 +22,7 @@
 #include <linux/module.h>
 #include <linux/io.h>
 #include <linux/seq_file.h>
+#include <linux/vmalloc.h>
 
 #include "mic_x100_dma.h"
 
diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig
index 8de4da5c9ab6..54071c148340 100644
--- a/drivers/firmware/efi/Kconfig
+++ b/drivers/firmware/efi/Kconfig
@@ -18,6 +18,11 @@ config EFI_VARS
 	  Subsequent efibootmgr releases may be found at:
 	  <http://github.com/vathpela/efibootmgr>
 
+config EFI_ESRT
+	bool
+	depends on EFI && !IA64
+	default y
+
 config EFI_VARS_PSTORE
 	tristate "Register efivars backend for pstore"
 	depends on EFI_VARS && PSTORE
diff --git a/drivers/firmware/efi/Makefile b/drivers/firmware/efi/Makefile
index d8be608a9f3b..6fd3da938717 100644
--- a/drivers/firmware/efi/Makefile
+++ b/drivers/firmware/efi/Makefile
@@ -3,6 +3,7 @@
 #
 obj-$(CONFIG_EFI)			+= efi.o vars.o reboot.o
 obj-$(CONFIG_EFI_VARS)			+= efivars.o
+obj-$(CONFIG_EFI_ESRT)			+= esrt.o
 obj-$(CONFIG_EFI_VARS_PSTORE)		+= efi-pstore.o
 obj-$(CONFIG_UEFI_CPER)			+= cper.o
 obj-$(CONFIG_EFI_RUNTIME_MAP)		+= runtime-map.o
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 3061bb8629dc..ca617f40574a 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -39,6 +39,7 @@ struct efi __read_mostly efi = {
 	.fw_vendor  = EFI_INVALID_TABLE_ADDR,
 	.runtime    = EFI_INVALID_TABLE_ADDR,
 	.config_table  = EFI_INVALID_TABLE_ADDR,
+	.esrt       = EFI_INVALID_TABLE_ADDR,
 };
 EXPORT_SYMBOL(efi);
 
@@ -64,7 +65,7 @@ static int __init parse_efi_cmdline(char *str)
 }
 early_param("efi", parse_efi_cmdline);
 
-static struct kobject *efi_kobj;
+struct kobject *efi_kobj;
 static struct kobject *efivars_kobj;
 
 /*
@@ -85,10 +86,15 @@ static ssize_t systab_show(struct kobject *kobj,
 		str += sprintf(str, "ACPI20=0x%lx\n", efi.acpi20);
 	if (efi.acpi != EFI_INVALID_TABLE_ADDR)
 		str += sprintf(str, "ACPI=0x%lx\n", efi.acpi);
-	if (efi.smbios != EFI_INVALID_TABLE_ADDR)
-		str += sprintf(str, "SMBIOS=0x%lx\n", efi.smbios);
+	/*
+	 * If both SMBIOS and SMBIOS3 entry points are implemented, the
+	 * SMBIOS3 entry point shall be preferred, so we list it first to
+	 * let applications stop parsing after the first match.
+	 */
 	if (efi.smbios3 != EFI_INVALID_TABLE_ADDR)
 		str += sprintf(str, "SMBIOS3=0x%lx\n", efi.smbios3);
+	if (efi.smbios != EFI_INVALID_TABLE_ADDR)
+		str += sprintf(str, "SMBIOS=0x%lx\n", efi.smbios);
 	if (efi.hcdp != EFI_INVALID_TABLE_ADDR)
 		str += sprintf(str, "HCDP=0x%lx\n", efi.hcdp);
 	if (efi.boot_info != EFI_INVALID_TABLE_ADDR)
@@ -232,6 +238,84 @@ err_put:
 
 subsys_initcall(efisubsys_init);
 
+/*
+ * Find the efi memory descriptor for a given physical address.  Given a
+ * physicall address, determine if it exists within an EFI Memory Map entry,
+ * and if so, populate the supplied memory descriptor with the appropriate
+ * data.
+ */
+int __init efi_mem_desc_lookup(u64 phys_addr, efi_memory_desc_t *out_md)
+{
+	struct efi_memory_map *map = efi.memmap;
+	void *p, *e;
+
+	if (!efi_enabled(EFI_MEMMAP)) {
+		pr_err_once("EFI_MEMMAP is not enabled.\n");
+		return -EINVAL;
+	}
+
+	if (!map) {
+		pr_err_once("efi.memmap is not set.\n");
+		return -EINVAL;
+	}
+	if (!out_md) {
+		pr_err_once("out_md is null.\n");
+		return -EINVAL;
+        }
+	if (WARN_ON_ONCE(!map->phys_map))
+		return -EINVAL;
+	if (WARN_ON_ONCE(map->nr_map == 0) || WARN_ON_ONCE(map->desc_size == 0))
+		return -EINVAL;
+
+	e = map->phys_map + map->nr_map * map->desc_size;
+	for (p = map->phys_map; p < e; p += map->desc_size) {
+		efi_memory_desc_t *md;
+		u64 size;
+		u64 end;
+
+		/*
+		 * If a driver calls this after efi_free_boot_services,
+		 * ->map will be NULL, and the target may also not be mapped.
+		 * So just always get our own virtual map on the CPU.
+		 *
+		 */
+		md = early_memremap((phys_addr_t)p, sizeof (*md));
+		if (!md) {
+			pr_err_once("early_memremap(%p, %zu) failed.\n",
+				    p, sizeof (*md));
+			return -ENOMEM;
+		}
+
+		if (!(md->attribute & EFI_MEMORY_RUNTIME) &&
+		    md->type != EFI_BOOT_SERVICES_DATA &&
+		    md->type != EFI_RUNTIME_SERVICES_DATA) {
+			early_memunmap(md, sizeof (*md));
+			continue;
+		}
+
+		size = md->num_pages << EFI_PAGE_SHIFT;
+		end = md->phys_addr + size;
+		if (phys_addr >= md->phys_addr && phys_addr < end) {
+			memcpy(out_md, md, sizeof(*out_md));
+			early_memunmap(md, sizeof (*md));
+			return 0;
+		}
+
+		early_memunmap(md, sizeof (*md));
+	}
+	pr_err_once("requested map not found.\n");
+	return -ENOENT;
+}
+
+/*
+ * Calculate the highest address of an efi memory descriptor.
+ */
+u64 __init efi_mem_desc_end(efi_memory_desc_t *md)
+{
+	u64 size = md->num_pages << EFI_PAGE_SHIFT;
+	u64 end = md->phys_addr + size;
+	return end;
+}
 
 /*
  * We can't ioremap data in EFI boot services RAM, because we've already mapped
@@ -274,6 +358,7 @@ static __initdata efi_config_table_type_t common_tables[] = {
 	{SMBIOS_TABLE_GUID, "SMBIOS", &efi.smbios},
 	{SMBIOS3_TABLE_GUID, "SMBIOS 3.0", &efi.smbios3},
 	{UGA_IO_PROTOCOL_GUID, "UGA", &efi.uga},
+	{EFI_SYSTEM_RESOURCE_TABLE_GUID, "ESRT", &efi.esrt},
 	{NULL_GUID, NULL, NULL},
 };
 
diff --git a/drivers/firmware/efi/efivars.c b/drivers/firmware/efi/efivars.c
index 7b2e0496e0c0..756eca8c4cf8 100644
--- a/drivers/firmware/efi/efivars.c
+++ b/drivers/firmware/efi/efivars.c
@@ -535,7 +535,7 @@ static ssize_t efivar_delete(struct file *filp, struct kobject *kobj,
  * efivar_create_sysfs_entry - create a new entry in sysfs
  * @new_var: efivar entry to create
  *
- * Returns 1 on failure, 0 on success
+ * Returns 0 on success, negative error code on failure
  */
 static int
 efivar_create_sysfs_entry(struct efivar_entry *new_var)
@@ -544,6 +544,7 @@ efivar_create_sysfs_entry(struct efivar_entry *new_var)
 	char *short_name;
 	unsigned long variable_name_size;
 	efi_char16_t *variable_name;
+	int ret;
 
 	variable_name = new_var->var.VariableName;
 	variable_name_size = ucs2_strlen(variable_name) * sizeof(efi_char16_t);
@@ -558,7 +559,7 @@ efivar_create_sysfs_entry(struct efivar_entry *new_var)
 	short_name = kzalloc(short_name_size, GFP_KERNEL);
 
 	if (!short_name)
-		return 1;
+		return -ENOMEM;
 
 	/* Convert Unicode to normal chars (assume top bits are 0),
 	   ala UTF-8 */
@@ -574,11 +575,11 @@ efivar_create_sysfs_entry(struct efivar_entry *new_var)
 
 	new_var->kobj.kset = efivars_kset;
 
-	i = kobject_init_and_add(&new_var->kobj, &efivar_ktype,
+	ret = kobject_init_and_add(&new_var->kobj, &efivar_ktype,
 				   NULL, "%s", short_name);
 	kfree(short_name);
-	if (i)
-		return 1;
+	if (ret)
+		return ret;
 
 	kobject_uevent(&new_var->kobj, KOBJ_ADD);
 	efivar_entry_add(new_var, &efivar_sysfs_list);
diff --git a/drivers/firmware/efi/esrt.c b/drivers/firmware/efi/esrt.c
new file mode 100644
index 000000000000..a5b95d61ae71
--- /dev/null
+++ b/drivers/firmware/efi/esrt.c
@@ -0,0 +1,471 @@
+/*
+ * esrt.c
+ *
+ * This module exports EFI System Resource Table (ESRT) entries into userspace
+ * through the sysfs file system. The ESRT provides a read-only catalog of
+ * system components for which the system accepts firmware upgrades via UEFI's
+ * "Capsule Update" feature. This module allows userland utilities to evaluate
+ * what firmware updates can be applied to this system, and potentially arrange
+ * for those updates to occur.
+ *
+ * Data is currently found below /sys/firmware/efi/esrt/...
+ */
+#define pr_fmt(fmt) "esrt: " fmt
+
+#include <linux/capability.h>
+#include <linux/device.h>
+#include <linux/efi.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/kobject.h>
+#include <linux/list.h>
+#include <linux/memblock.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+
+#include <asm/io.h>
+#include <asm/early_ioremap.h>
+
+struct efi_system_resource_entry_v1 {
+	efi_guid_t	fw_class;
+	u32		fw_type;
+	u32		fw_version;
+	u32		lowest_supported_fw_version;
+	u32		capsule_flags;
+	u32		last_attempt_version;
+	u32		last_attempt_status;
+};
+
+/*
+ * _count and _version are what they seem like.  _max is actually just
+ * accounting info for the firmware when creating the table; it should never
+ * have been exposed to us.  To wit, the spec says:
+ * The maximum number of resource array entries that can be within the
+ * table without reallocating the table, must not be zero.
+ * Since there's no guidance about what that means in terms of memory layout,
+ * it means nothing to us.
+ */
+struct efi_system_resource_table {
+	u32	fw_resource_count;
+	u32	fw_resource_count_max;
+	u64	fw_resource_version;
+	u8	entries[];
+};
+
+static phys_addr_t esrt_data;
+static size_t esrt_data_size;
+
+static struct efi_system_resource_table *esrt;
+
+struct esre_entry {
+	union {
+		struct efi_system_resource_entry_v1 *esre1;
+	} esre;
+
+	struct kobject kobj;
+	struct list_head list;
+};
+
+/* global list of esre_entry. */
+static LIST_HEAD(entry_list);
+
+/* entry attribute */
+struct esre_attribute {
+	struct attribute attr;
+	ssize_t (*show)(struct esre_entry *entry, char *buf);
+	ssize_t (*store)(struct esre_entry *entry,
+			 const char *buf, size_t count);
+};
+
+static struct esre_entry *to_entry(struct kobject *kobj)
+{
+	return container_of(kobj, struct esre_entry, kobj);
+}
+
+static struct esre_attribute *to_attr(struct attribute *attr)
+{
+	return container_of(attr, struct esre_attribute, attr);
+}
+
+static ssize_t esre_attr_show(struct kobject *kobj,
+			      struct attribute *_attr, char *buf)
+{
+	struct esre_entry *entry = to_entry(kobj);
+	struct esre_attribute *attr = to_attr(_attr);
+
+	/* Don't tell normal users what firmware versions we've got... */
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
+	return attr->show(entry, buf);
+}
+
+static const struct sysfs_ops esre_attr_ops = {
+	.show = esre_attr_show,
+};
+
+/* Generic ESRT Entry ("ESRE") support. */
+static ssize_t esre_fw_class_show(struct esre_entry *entry, char *buf)
+{
+	char *str = buf;
+
+	efi_guid_to_str(&entry->esre.esre1->fw_class, str);
+	str += strlen(str);
+	str += sprintf(str, "\n");
+
+	return str - buf;
+}
+
+static struct esre_attribute esre_fw_class = __ATTR(fw_class, 0400,
+	esre_fw_class_show, NULL);
+
+#define esre_attr_decl(name, size, fmt) \
+static ssize_t esre_##name##_show(struct esre_entry *entry, char *buf) \
+{ \
+	return sprintf(buf, fmt "\n", \
+		       le##size##_to_cpu(entry->esre.esre1->name)); \
+} \
+\
+static struct esre_attribute esre_##name = __ATTR(name, 0400, \
+	esre_##name##_show, NULL)
+
+esre_attr_decl(fw_type, 32, "%u");
+esre_attr_decl(fw_version, 32, "%u");
+esre_attr_decl(lowest_supported_fw_version, 32, "%u");
+esre_attr_decl(capsule_flags, 32, "0x%x");
+esre_attr_decl(last_attempt_version, 32, "%u");
+esre_attr_decl(last_attempt_status, 32, "%u");
+
+static struct attribute *esre1_attrs[] = {
+	&esre_fw_class.attr,
+	&esre_fw_type.attr,
+	&esre_fw_version.attr,
+	&esre_lowest_supported_fw_version.attr,
+	&esre_capsule_flags.attr,
+	&esre_last_attempt_version.attr,
+	&esre_last_attempt_status.attr,
+	NULL
+};
+static void esre_release(struct kobject *kobj)
+{
+	struct esre_entry *entry = to_entry(kobj);
+
+	list_del(&entry->list);
+	kfree(entry);
+}
+
+static struct kobj_type esre1_ktype = {
+	.release = esre_release,
+	.sysfs_ops = &esre_attr_ops,
+	.default_attrs = esre1_attrs,
+};
+
+
+static struct kobject *esrt_kobj;
+static struct kset *esrt_kset;
+
+static int esre_create_sysfs_entry(void *esre, int entry_num)
+{
+	struct esre_entry *entry;
+	char name[20];
+
+	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry)
+		return -ENOMEM;
+
+	sprintf(name, "entry%d", entry_num);
+
+	entry->kobj.kset = esrt_kset;
+
+	if (esrt->fw_resource_version == 1) {
+		int rc = 0;
+
+		entry->esre.esre1 = esre;
+		rc = kobject_init_and_add(&entry->kobj, &esre1_ktype, NULL,
+					  "%s", name);
+		if (rc) {
+			kfree(entry);
+			return rc;
+		}
+	}
+
+	list_add_tail(&entry->list, &entry_list);
+	return 0;
+}
+
+/* support for displaying ESRT fields at the top level */
+#define esrt_attr_decl(name, size, fmt) \
+static ssize_t esrt_##name##_show(struct kobject *kobj, \
+				  struct kobj_attribute *attr, char *buf)\
+{ \
+	return sprintf(buf, fmt "\n", le##size##_to_cpu(esrt->name)); \
+} \
+\
+static struct kobj_attribute esrt_##name = __ATTR(name, 0400, \
+	esrt_##name##_show, NULL)
+
+esrt_attr_decl(fw_resource_count, 32, "%u");
+esrt_attr_decl(fw_resource_count_max, 32, "%u");
+esrt_attr_decl(fw_resource_version, 64, "%llu");
+
+static struct attribute *esrt_attrs[] = {
+	&esrt_fw_resource_count.attr,
+	&esrt_fw_resource_count_max.attr,
+	&esrt_fw_resource_version.attr,
+	NULL,
+};
+
+static inline int esrt_table_exists(void)
+{
+	if (!efi_enabled(EFI_CONFIG_TABLES))
+		return 0;
+	if (efi.esrt == EFI_INVALID_TABLE_ADDR)
+		return 0;
+	return 1;
+}
+
+static umode_t esrt_attr_is_visible(struct kobject *kobj,
+				    struct attribute *attr, int n)
+{
+	if (!esrt_table_exists())
+		return 0;
+	return attr->mode;
+}
+
+static struct attribute_group esrt_attr_group = {
+	.attrs = esrt_attrs,
+	.is_visible = esrt_attr_is_visible,
+};
+
+/*
+ * remap the table, copy it to kmalloced pages, and unmap it.
+ */
+void __init efi_esrt_init(void)
+{
+	void *va;
+	struct efi_system_resource_table tmpesrt;
+	struct efi_system_resource_entry_v1 *v1_entries;
+	size_t size, max, entry_size, entries_size;
+	efi_memory_desc_t md;
+	int rc;
+	phys_addr_t end;
+
+	pr_debug("esrt-init: loading.\n");
+	if (!esrt_table_exists())
+		return;
+
+	rc = efi_mem_desc_lookup(efi.esrt, &md);
+	if (rc < 0) {
+		pr_err("ESRT header is not in the memory map.\n");
+		return;
+	}
+
+	max = efi_mem_desc_end(&md);
+	if (max < efi.esrt) {
+		pr_err("EFI memory descriptor is invalid. (esrt: %p max: %p)\n",
+		       (void *)efi.esrt, (void *)max);
+		return;
+	}
+
+	size = sizeof(*esrt);
+	max -= efi.esrt;
+
+	if (max < size) {
+		pr_err("ESRT header doen't fit on single memory map entry. (size: %zu max: %zu)\n",
+		       size, max);
+		return;
+	}
+
+	va = early_memremap(efi.esrt, size);
+	if (!va) {
+		pr_err("early_memremap(%p, %zu) failed.\n", (void *)efi.esrt,
+		       size);
+		return;
+	}
+
+	memcpy(&tmpesrt, va, sizeof(tmpesrt));
+
+	if (tmpesrt.fw_resource_version == 1) {
+		entry_size = sizeof (*v1_entries);
+	} else {
+		pr_err("Unsupported ESRT version %lld.\n",
+		       tmpesrt.fw_resource_version);
+		return;
+	}
+
+	if (tmpesrt.fw_resource_count > 0 && max - size < entry_size) {
+		pr_err("ESRT memory map entry can only hold the header. (max: %zu size: %zu)\n",
+		       max - size, entry_size);
+		goto err_memunmap;
+	}
+
+	/*
+	 * The format doesn't really give us any boundary to test here,
+	 * so I'm making up 128 as the max number of individually updatable
+	 * components we support.
+	 * 128 should be pretty excessive, but there's still some chance
+	 * somebody will do that someday and we'll need to raise this.
+	 */
+	if (tmpesrt.fw_resource_count > 128) {
+		pr_err("ESRT says fw_resource_count has very large value %d.\n",
+		       tmpesrt.fw_resource_count);
+		goto err_memunmap;
+	}
+
+	/*
+	 * We know it can't be larger than N * sizeof() here, and N is limited
+	 * by the previous test to a small number, so there's no overflow.
+	 */
+	entries_size = tmpesrt.fw_resource_count * entry_size;
+	if (max < size + entries_size) {
+		pr_err("ESRT does not fit on single memory map entry (size: %zu max: %zu)\n",
+		       size, max);
+		goto err_memunmap;
+	}
+
+	/* remap it with our (plausible) new pages */
+	early_memunmap(va, size);
+	size += entries_size;
+	va = early_memremap(efi.esrt, size);
+	if (!va) {
+		pr_err("early_memremap(%p, %zu) failed.\n", (void *)efi.esrt,
+		       size);
+		return;
+	}
+
+	esrt_data = (phys_addr_t)efi.esrt;
+	esrt_data_size = size;
+
+	end = esrt_data + size;
+	pr_info("Reserving ESRT space from %pa to %pa.\n", &esrt_data, &end);
+	memblock_reserve(esrt_data, esrt_data_size);
+
+	pr_debug("esrt-init: loaded.\n");
+err_memunmap:
+	early_memunmap(va, size);
+}
+
+static int __init register_entries(void)
+{
+	struct efi_system_resource_entry_v1 *v1_entries = (void *)esrt->entries;
+	int i, rc;
+
+	if (!esrt_table_exists())
+		return 0;
+
+	for (i = 0; i < le32_to_cpu(esrt->fw_resource_count); i++) {
+		void *esre = NULL;
+		if (esrt->fw_resource_version == 1) {
+			esre = &v1_entries[i];
+		} else {
+			pr_err("Unsupported ESRT version %lld.\n",
+			       esrt->fw_resource_version);
+			return -EINVAL;
+		}
+
+		rc = esre_create_sysfs_entry(esre, i);
+		if (rc < 0) {
+			pr_err("ESRT entry creation failed with error %d.\n",
+			       rc);
+			return rc;
+		}
+	}
+	return 0;
+}
+
+static void cleanup_entry_list(void)
+{
+	struct esre_entry *entry, *next;
+
+	list_for_each_entry_safe(entry, next, &entry_list, list) {
+		kobject_put(&entry->kobj);
+	}
+}
+
+static int __init esrt_sysfs_init(void)
+{
+	int error;
+	struct efi_system_resource_table __iomem *ioesrt;
+
+	pr_debug("esrt-sysfs: loading.\n");
+	if (!esrt_data || !esrt_data_size)
+		return -ENOSYS;
+
+	ioesrt = ioremap(esrt_data, esrt_data_size);
+	if (!ioesrt) {
+		pr_err("ioremap(%pa, %zu) failed.\n", &esrt_data,
+		       esrt_data_size);
+		return -ENOMEM;
+	}
+
+	esrt = kmalloc(esrt_data_size, GFP_KERNEL);
+	if (!esrt) {
+		pr_err("kmalloc failed. (wanted %zu bytes)\n", esrt_data_size);
+		iounmap(ioesrt);
+		return -ENOMEM;
+	}
+
+	memcpy_fromio(esrt, ioesrt, esrt_data_size);
+
+	esrt_kobj = kobject_create_and_add("esrt", efi_kobj);
+	if (!esrt_kobj) {
+		pr_err("Firmware table registration failed.\n");
+		error = -ENOMEM;
+		goto err;
+	}
+
+	error = sysfs_create_group(esrt_kobj, &esrt_attr_group);
+	if (error) {
+		pr_err("Sysfs attribute export failed with error %d.\n",
+		       error);
+		goto err_remove_esrt;
+	}
+
+	esrt_kset = kset_create_and_add("entries", NULL, esrt_kobj);
+	if (!esrt_kset) {
+		pr_err("kset creation failed.\n");
+		error = -ENOMEM;
+		goto err_remove_group;
+	}
+
+	error = register_entries();
+	if (error)
+		goto err_cleanup_list;
+
+	memblock_remove(esrt_data, esrt_data_size);
+
+	pr_debug("esrt-sysfs: loaded.\n");
+
+	return 0;
+err_cleanup_list:
+	cleanup_entry_list();
+	kset_unregister(esrt_kset);
+err_remove_group:
+	sysfs_remove_group(esrt_kobj, &esrt_attr_group);
+err_remove_esrt:
+	kobject_put(esrt_kobj);
+err:
+	kfree(esrt);
+	esrt = NULL;
+	return error;
+}
+
+static void __exit esrt_sysfs_exit(void)
+{
+	pr_debug("esrt-sysfs: unloading.\n");
+	cleanup_entry_list();
+	kset_unregister(esrt_kset);
+	sysfs_remove_group(esrt_kobj, &esrt_attr_group);
+	kfree(esrt);
+	esrt = NULL;
+	kobject_del(esrt_kobj);
+	kobject_put(esrt_kobj);
+}
+
+module_init(esrt_sysfs_init);
+module_exit(esrt_sysfs_exit);
+
+MODULE_AUTHOR("Peter Jones <pjones@redhat.com>");
+MODULE_DESCRIPTION("EFI System Resource Table support");
+MODULE_LICENSE("GPL");
diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index caefe806db5e..8f1fe739c985 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -126,6 +126,14 @@ config GPIO_BCM_KONA
 	help
 	  Turn on GPIO support for Broadcom "Kona" chips.
 
+config GPIO_BRCMSTB
+	tristate "BRCMSTB GPIO support"
+	default y if ARCH_BRCMSTB
+	depends on OF_GPIO && (ARCH_BRCMSTB || COMPILE_TEST)
+	select GPIO_GENERIC
+	help
+	  Say yes here to enable GPIO support for Broadcom STB (BCM7XXX) SoCs.
+
 config GPIO_CLPS711X
 	tristate "CLPS711X GPIO support"
 	depends on ARCH_CLPS711X || COMPILE_TEST
@@ -159,6 +167,14 @@ config GPIO_EP93XX
 	depends on ARCH_EP93XX
 	select GPIO_GENERIC
 
+config GPIO_ETRAXFS
+	bool "Axis ETRAX FS General I/O"
+	depends on CRIS || COMPILE_TEST
+	depends on OF
+	select GPIO_GENERIC
+	help
+	  Say yes here to support the GPIO controller on Axis ETRAX FS SoCs.
+
 config GPIO_F7188X
 	tristate "F71869, F71869A, F71882FG and F71889F GPIO support"
 	depends on X86
@@ -230,6 +246,14 @@ config GPIO_LOONGSON
 	help
 	  driver for GPIO functionality on Loongson-2F/3A/3B processors.
 
+config GPIO_LPC18XX
+	bool "NXP LPC18XX/43XX GPIO support"
+	default y if ARCH_LPC18XX
+	depends on OF_GPIO && (ARCH_LPC18XX || COMPILE_TEST)
+	help
+	  Select this option to enable GPIO driver for
+	  NXP LPC18XX/43XX devices.
+
 config GPIO_LYNXPOINT
 	tristate "Intel Lynxpoint GPIO support"
 	depends on ACPI && X86
@@ -308,7 +332,7 @@ config GPIO_OCTEON
 	  family of SOCs.
 
 config GPIO_OMAP
-	bool "TI OMAP GPIO support" if COMPILE_TEST && !ARCH_OMAP2PLUS
+	tristate "TI OMAP GPIO support" if ARCH_OMAP2PLUS || COMPILE_TEST
 	default y if ARCH_OMAP
 	depends on ARM
 	select GENERIC_IRQ_CHIP
@@ -488,6 +512,17 @@ config GPIO_XILINX
 	help
 	  Say yes here to support the Xilinx FPGA GPIO device
 
+config GPIO_XLP
+	tristate "Netlogic XLP GPIO support"
+	depends on CPU_XLP
+	select GPIOLIB_IRQCHIP
+	help
+	  This driver provides support for GPIO interface on Netlogic XLP MIPS64
+	  SoCs. Currently supported XLP variants are XLP8XX, XLP3XX, XLP2XX,
+	  XLP9XX and XLP5XX.
+
+	  If unsure, say N.
+
 config GPIO_XTENSA
 	bool "Xtensa GPIO32 support"
 	depends on XTENSA
@@ -505,7 +540,7 @@ config GPIO_ZEVIO
 
 config GPIO_ZYNQ
 	tristate "Xilinx Zynq GPIO support"
-	depends on ARCH_ZYNQ
+	depends on ARCH_ZYNQ || ARCH_ZYNQMP
 	select GPIOLIB_IRQCHIP
 	help
 	  Say yes here to support Xilinx Zynq GPIO controller.
diff --git a/drivers/gpio/Makefile b/drivers/gpio/Makefile
index f71bb971329c..f82cd678ce08 100644
--- a/drivers/gpio/Makefile
+++ b/drivers/gpio/Makefile
@@ -21,6 +21,7 @@ obj-$(CONFIG_GPIO_ALTERA)  	+= gpio-altera.o
 obj-$(CONFIG_GPIO_AMD8111)	+= gpio-amd8111.o
 obj-$(CONFIG_GPIO_ARIZONA)	+= gpio-arizona.o
 obj-$(CONFIG_GPIO_BCM_KONA)	+= gpio-bcm-kona.o
+obj-$(CONFIG_GPIO_BRCMSTB)	+= gpio-brcmstb.o
 obj-$(CONFIG_GPIO_BT8XX)	+= gpio-bt8xx.o
 obj-$(CONFIG_GPIO_CLPS711X)	+= gpio-clps711x.o
 obj-$(CONFIG_GPIO_CS5535)	+= gpio-cs5535.o
@@ -32,6 +33,7 @@ obj-$(CONFIG_GPIO_DLN2)		+= gpio-dln2.o
 obj-$(CONFIG_GPIO_DWAPB)	+= gpio-dwapb.o
 obj-$(CONFIG_GPIO_EM)		+= gpio-em.o
 obj-$(CONFIG_GPIO_EP93XX)	+= gpio-ep93xx.o
+obj-$(CONFIG_GPIO_ETRAXFS)	+= gpio-etraxfs.o
 obj-$(CONFIG_GPIO_F7188X)	+= gpio-f7188x.o
 obj-$(CONFIG_GPIO_GE_FPGA)	+= gpio-ge.o
 obj-$(CONFIG_GPIO_GRGPIO)	+= gpio-grgpio.o
@@ -44,6 +46,7 @@ obj-$(CONFIG_ARCH_KS8695)	+= gpio-ks8695.o
 obj-$(CONFIG_GPIO_INTEL_MID)	+= gpio-intel-mid.o
 obj-$(CONFIG_GPIO_LOONGSON)	+= gpio-loongson.o
 obj-$(CONFIG_GPIO_LP3943)	+= gpio-lp3943.o
+obj-$(CONFIG_GPIO_LPC18XX)	+= gpio-lpc18xx.o
 obj-$(CONFIG_ARCH_LPC32XX)	+= gpio-lpc32xx.o
 obj-$(CONFIG_GPIO_LYNXPOINT)	+= gpio-lynxpoint.o
 obj-$(CONFIG_GPIO_MAX730X)	+= gpio-max730x.o
@@ -109,6 +112,7 @@ obj-$(CONFIG_GPIO_WM8994)	+= gpio-wm8994.o
 obj-$(CONFIG_GPIO_XGENE)	+= gpio-xgene.o
 obj-$(CONFIG_GPIO_XGENE_SB)	+= gpio-xgene-sb.o
 obj-$(CONFIG_GPIO_XILINX)	+= gpio-xilinx.o
+obj-$(CONFIG_GPIO_XLP)		+= gpio-xlp.o
 obj-$(CONFIG_GPIO_XTENSA)	+= gpio-xtensa.o
 obj-$(CONFIG_GPIO_ZEVIO)	+= gpio-zevio.o
 obj-$(CONFIG_GPIO_ZYNQ)		+= gpio-zynq.o
diff --git a/drivers/gpio/gpio-altera.c b/drivers/gpio/gpio-altera.c
index 449fb46cb8a0..0f3d336d6303 100644
--- a/drivers/gpio/gpio-altera.c
+++ b/drivers/gpio/gpio-altera.c
@@ -107,7 +107,8 @@ static int altera_gpio_irq_set_type(struct irq_data *d,
 	return -EINVAL;
 }
 
-static unsigned int altera_gpio_irq_startup(struct irq_data *d) {
+static unsigned int altera_gpio_irq_startup(struct irq_data *d)
+{
 	altera_gpio_irq_unmask(d);
 
 	return 0;
diff --git a/drivers/gpio/gpio-bcm-kona.c b/drivers/gpio/gpio-bcm-kona.c
index b164ce837b43..a6e79225886d 100644
--- a/drivers/gpio/gpio-bcm-kona.c
+++ b/drivers/gpio/gpio-bcm-kona.c
@@ -122,6 +122,16 @@ static void bcm_kona_gpio_unlock_gpio(struct bcm_kona_gpio *kona_gpio,
 	spin_unlock_irqrestore(&kona_gpio->lock, flags);
 }
 
+static int bcm_kona_gpio_get_dir(struct gpio_chip *chip, unsigned gpio)
+{
+	struct bcm_kona_gpio *kona_gpio = to_kona_gpio(chip);
+	void __iomem *reg_base = kona_gpio->reg_base;
+	u32 val;
+
+	val = readl(reg_base + GPIO_CONTROL(gpio)) & GPIO_GPCTR0_IOTR_MASK;
+	return val ? GPIOF_DIR_IN : GPIOF_DIR_OUT;
+}
+
 static void bcm_kona_gpio_set(struct gpio_chip *chip, unsigned gpio, int value)
 {
 	struct bcm_kona_gpio *kona_gpio;
@@ -135,12 +145,8 @@ static void bcm_kona_gpio_set(struct gpio_chip *chip, unsigned gpio, int value)
 	reg_base = kona_gpio->reg_base;
 	spin_lock_irqsave(&kona_gpio->lock, flags);
 
-	/* determine the GPIO pin direction */
-	val = readl(reg_base + GPIO_CONTROL(gpio));
-	val &= GPIO_GPCTR0_IOTR_MASK;
-
 	/* this function only applies to output pin */
-	if (GPIO_GPCTR0_IOTR_CMD_INPUT == val)
+	if (bcm_kona_gpio_get_dir(chip, gpio) == GPIOF_DIR_IN)
 		goto out;
 
 	reg_offset = value ? GPIO_OUT_SET(bank_id) : GPIO_OUT_CLEAR(bank_id);
@@ -166,13 +172,12 @@ static int bcm_kona_gpio_get(struct gpio_chip *chip, unsigned gpio)
 	reg_base = kona_gpio->reg_base;
 	spin_lock_irqsave(&kona_gpio->lock, flags);
 
-	/* determine the GPIO pin direction */
-	val = readl(reg_base + GPIO_CONTROL(gpio));
-	val &= GPIO_GPCTR0_IOTR_MASK;
+	if (bcm_kona_gpio_get_dir(chip, gpio) == GPIOF_DIR_IN)
+		reg_offset = GPIO_IN_STATUS(bank_id);
+	else
+		reg_offset = GPIO_OUT_STATUS(bank_id);
 
 	/* read the GPIO bank status */
-	reg_offset = (GPIO_GPCTR0_IOTR_CMD_INPUT == val) ?
-	    GPIO_IN_STATUS(bank_id) : GPIO_OUT_STATUS(bank_id);
 	val = readl(reg_base + reg_offset);
 
 	spin_unlock_irqrestore(&kona_gpio->lock, flags);
@@ -310,6 +315,7 @@ static struct gpio_chip template_chip = {
 	.owner = THIS_MODULE,
 	.request = bcm_kona_gpio_request,
 	.free = bcm_kona_gpio_free,
+	.get_direction = bcm_kona_gpio_get_dir,
 	.direction_input = bcm_kona_gpio_direction_input,
 	.get = bcm_kona_gpio_get,
 	.direction_output = bcm_kona_gpio_direction_output,
diff --git a/drivers/gpio/gpio-brcmstb.c b/drivers/gpio/gpio-brcmstb.c
new file mode 100644
index 000000000000..7a3cb1fa0a76
--- /dev/null
+++ b/drivers/gpio/gpio-brcmstb.c
@@ -0,0 +1,252 @@
+/*
+ * Copyright (C) 2015 Broadcom Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/bitops.h>
+#include <linux/gpio/driver.h>
+#include <linux/of_device.h>
+#include <linux/of_irq.h>
+#include <linux/module.h>
+#include <linux/basic_mmio_gpio.h>
+
+#define GIO_BANK_SIZE           0x20
+#define GIO_ODEN(bank)          (((bank) * GIO_BANK_SIZE) + 0x00)
+#define GIO_DATA(bank)          (((bank) * GIO_BANK_SIZE) + 0x04)
+#define GIO_IODIR(bank)         (((bank) * GIO_BANK_SIZE) + 0x08)
+#define GIO_EC(bank)            (((bank) * GIO_BANK_SIZE) + 0x0c)
+#define GIO_EI(bank)            (((bank) * GIO_BANK_SIZE) + 0x10)
+#define GIO_MASK(bank)          (((bank) * GIO_BANK_SIZE) + 0x14)
+#define GIO_LEVEL(bank)         (((bank) * GIO_BANK_SIZE) + 0x18)
+#define GIO_STAT(bank)          (((bank) * GIO_BANK_SIZE) + 0x1c)
+
+struct brcmstb_gpio_bank {
+	struct list_head node;
+	int id;
+	struct bgpio_chip bgc;
+	struct brcmstb_gpio_priv *parent_priv;
+	u32 width;
+};
+
+struct brcmstb_gpio_priv {
+	struct list_head bank_list;
+	void __iomem *reg_base;
+	int num_banks;
+	struct platform_device *pdev;
+	int gpio_base;
+};
+
+#define MAX_GPIO_PER_BANK           32
+#define GPIO_BANK(gpio)         ((gpio) >> 5)
+/* assumes MAX_GPIO_PER_BANK is a multiple of 2 */
+#define GPIO_BIT(gpio)          ((gpio) & (MAX_GPIO_PER_BANK - 1))
+
+static inline struct brcmstb_gpio_bank *
+brcmstb_gpio_gc_to_bank(struct gpio_chip *gc)
+{
+	struct bgpio_chip *bgc = to_bgpio_chip(gc);
+	return container_of(bgc, struct brcmstb_gpio_bank, bgc);
+}
+
+static inline struct brcmstb_gpio_priv *
+brcmstb_gpio_gc_to_priv(struct gpio_chip *gc)
+{
+	struct brcmstb_gpio_bank *bank = brcmstb_gpio_gc_to_bank(gc);
+	return bank->parent_priv;
+}
+
+/* Make sure that the number of banks matches up between properties */
+static int brcmstb_gpio_sanity_check_banks(struct device *dev,
+		struct device_node *np, struct resource *res)
+{
+	int res_num_banks = resource_size(res) / GIO_BANK_SIZE;
+	int num_banks =
+		of_property_count_u32_elems(np, "brcm,gpio-bank-widths");
+
+	if (res_num_banks != num_banks) {
+		dev_err(dev, "Mismatch in banks: res had %d, bank-widths had %d\n",
+				res_num_banks, num_banks);
+		return -EINVAL;
+	} else {
+		return 0;
+	}
+}
+
+static int brcmstb_gpio_remove(struct platform_device *pdev)
+{
+	struct brcmstb_gpio_priv *priv = platform_get_drvdata(pdev);
+	struct list_head *pos;
+	struct brcmstb_gpio_bank *bank;
+	int ret = 0;
+
+	list_for_each(pos, &priv->bank_list) {
+		bank = list_entry(pos, struct brcmstb_gpio_bank, node);
+		ret = bgpio_remove(&bank->bgc);
+		if (ret)
+			dev_err(&pdev->dev, "gpiochip_remove fail in cleanup");
+	}
+	return ret;
+}
+
+static int brcmstb_gpio_of_xlate(struct gpio_chip *gc,
+		const struct of_phandle_args *gpiospec, u32 *flags)
+{
+	struct brcmstb_gpio_priv *priv = brcmstb_gpio_gc_to_priv(gc);
+	struct brcmstb_gpio_bank *bank = brcmstb_gpio_gc_to_bank(gc);
+	int offset;
+
+	if (gc->of_gpio_n_cells != 2) {
+		WARN_ON(1);
+		return -EINVAL;
+	}
+
+	if (WARN_ON(gpiospec->args_count < gc->of_gpio_n_cells))
+		return -EINVAL;
+
+	offset = gpiospec->args[0] - (gc->base - priv->gpio_base);
+	if (offset >= gc->ngpio)
+		return -EINVAL;
+
+	if (unlikely(offset >= bank->width)) {
+		dev_warn_ratelimited(&priv->pdev->dev,
+			"Received request for invalid GPIO offset %d\n",
+			gpiospec->args[0]);
+	}
+
+	if (flags)
+		*flags = gpiospec->args[1];
+
+	return offset;
+}
+
+static int brcmstb_gpio_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
+	void __iomem *reg_base;
+	struct brcmstb_gpio_priv *priv;
+	struct resource *res;
+	struct property *prop;
+	const __be32 *p;
+	u32 bank_width;
+	int err;
+	static int gpio_base;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	reg_base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(reg_base))
+		return PTR_ERR(reg_base);
+
+	priv->gpio_base = gpio_base;
+	priv->reg_base = reg_base;
+	priv->pdev = pdev;
+
+	INIT_LIST_HEAD(&priv->bank_list);
+	if (brcmstb_gpio_sanity_check_banks(dev, np, res))
+		return -EINVAL;
+
+	of_property_for_each_u32(np, "brcm,gpio-bank-widths", prop, p,
+			bank_width) {
+		struct brcmstb_gpio_bank *bank;
+		struct bgpio_chip *bgc;
+		struct gpio_chip *gc;
+
+		bank = devm_kzalloc(dev, sizeof(*bank), GFP_KERNEL);
+		if (!bank) {
+			err = -ENOMEM;
+			goto fail;
+		}
+
+		bank->parent_priv = priv;
+		bank->id = priv->num_banks;
+		if (bank_width <= 0 || bank_width > MAX_GPIO_PER_BANK) {
+			dev_err(dev, "Invalid bank width %d\n", bank_width);
+			goto fail;
+		} else {
+			bank->width = bank_width;
+		}
+
+		/*
+		 * Regs are 4 bytes wide, have data reg, no set/clear regs,
+		 * and direction bits have 0 = output and 1 = input
+		 */
+		bgc = &bank->bgc;
+		err = bgpio_init(bgc, dev, 4,
+				reg_base + GIO_DATA(bank->id),
+				NULL, NULL, NULL,
+				reg_base + GIO_IODIR(bank->id), 0);
+		if (err) {
+			dev_err(dev, "bgpio_init() failed\n");
+			goto fail;
+		}
+
+		gc = &bgc->gc;
+		gc->of_node = np;
+		gc->owner = THIS_MODULE;
+		gc->label = np->full_name;
+		gc->base = gpio_base;
+		gc->of_gpio_n_cells = 2;
+		gc->of_xlate = brcmstb_gpio_of_xlate;
+		/* not all ngpio lines are valid, will use bank width later */
+		gc->ngpio = MAX_GPIO_PER_BANK;
+
+		err = gpiochip_add(gc);
+		if (err) {
+			dev_err(dev, "Could not add gpiochip for bank %d\n",
+					bank->id);
+			goto fail;
+		}
+		gpio_base += gc->ngpio;
+		dev_dbg(dev, "bank=%d, base=%d, ngpio=%d, width=%d\n", bank->id,
+			gc->base, gc->ngpio, bank->width);
+
+		/* Everything looks good, so add bank to list */
+		list_add(&bank->node, &priv->bank_list);
+
+		priv->num_banks++;
+	}
+
+	dev_info(dev, "Registered %d banks (GPIO(s): %d-%d)\n",
+			priv->num_banks, priv->gpio_base, gpio_base - 1);
+
+	platform_set_drvdata(pdev, priv);
+
+	return 0;
+
+fail:
+	(void) brcmstb_gpio_remove(pdev);
+	return err;
+}
+
+static const struct of_device_id brcmstb_gpio_of_match[] = {
+	{ .compatible = "brcm,brcmstb-gpio" },
+	{},
+};
+
+MODULE_DEVICE_TABLE(of, brcmstb_gpio_of_match);
+
+static struct platform_driver brcmstb_gpio_driver = {
+	.driver = {
+		.name = "brcmstb-gpio",
+		.of_match_table = brcmstb_gpio_of_match,
+	},
+	.probe = brcmstb_gpio_probe,
+	.remove = brcmstb_gpio_remove,
+};
+module_platform_driver(brcmstb_gpio_driver);
+
+MODULE_AUTHOR("Gregory Fong");
+MODULE_DESCRIPTION("Driver for Broadcom BRCMSTB SoC UPG GPIO");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/gpio/gpio-crystalcove.c b/drivers/gpio/gpio-crystalcove.c
index 91a7ffe83135..fddd204dc9b6 100644
--- a/drivers/gpio/gpio-crystalcove.c
+++ b/drivers/gpio/gpio-crystalcove.c
@@ -16,6 +16,7 @@
  */
 
 #include <linux/interrupt.h>
+#include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/gpio.h>
 #include <linux/seq_file.h>
@@ -94,9 +95,8 @@ static inline int to_reg(int gpio, enum ctrl_register reg_type)
 {
 	int reg;
 
-	if (gpio == 94) {
+	if (gpio == 94)
 		return GPIOPANELCTL;
-	}
 
 	if (reg_type == CTRL_IN) {
 		if (gpio < 8)
@@ -255,6 +255,7 @@ static struct irq_chip crystalcove_irqchip = {
 	.irq_set_type		= crystalcove_irq_type,
 	.irq_bus_lock		= crystalcove_bus_lock,
 	.irq_bus_sync_unlock	= crystalcove_bus_sync_unlock,
+	.flags			= IRQCHIP_SKIP_SET_WAKE,
 };
 
 static irqreturn_t crystalcove_gpio_irq_handler(int irq, void *data)
diff --git a/drivers/gpio/gpio-dln2.c b/drivers/gpio/gpio-dln2.c
index dbdb4de82c6d..6685712c15cf 100644
--- a/drivers/gpio/gpio-dln2.c
+++ b/drivers/gpio/gpio-dln2.c
@@ -466,7 +466,6 @@ static int dln2_gpio_probe(struct platform_device *pdev)
 	dln2->gpio.owner = THIS_MODULE;
 	dln2->gpio.base = -1;
 	dln2->gpio.ngpio = pins;
-	dln2->gpio.exported = true;
 	dln2->gpio.can_sleep = true;
 	dln2->gpio.irq_not_threaded = true;
 	dln2->gpio.set = dln2_gpio_set;
diff --git a/drivers/gpio/gpio-etraxfs.c b/drivers/gpio/gpio-etraxfs.c
new file mode 100644
index 000000000000..28071f4a5672
--- /dev/null
+++ b/drivers/gpio/gpio-etraxfs.c
@@ -0,0 +1,176 @@
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/gpio.h>
+#include <linux/of_gpio.h>
+#include <linux/io.h>
+#include <linux/platform_device.h>
+#include <linux/basic_mmio_gpio.h>
+
+#define ETRAX_FS_rw_pa_dout	0
+#define ETRAX_FS_r_pa_din	4
+#define ETRAX_FS_rw_pa_oe	8
+#define ETRAX_FS_rw_intr_cfg	12
+#define ETRAX_FS_rw_intr_mask	16
+#define ETRAX_FS_rw_ack_intr	20
+#define ETRAX_FS_r_intr		24
+#define ETRAX_FS_rw_pb_dout	32
+#define ETRAX_FS_r_pb_din	36
+#define ETRAX_FS_rw_pb_oe	40
+#define ETRAX_FS_rw_pc_dout	48
+#define ETRAX_FS_r_pc_din	52
+#define ETRAX_FS_rw_pc_oe	56
+#define ETRAX_FS_rw_pd_dout	64
+#define ETRAX_FS_r_pd_din	68
+#define ETRAX_FS_rw_pd_oe	72
+#define ETRAX_FS_rw_pe_dout	80
+#define ETRAX_FS_r_pe_din	84
+#define ETRAX_FS_rw_pe_oe	88
+
+struct etraxfs_gpio_port {
+	const char *label;
+	unsigned int oe;
+	unsigned int dout;
+	unsigned int din;
+	unsigned int ngpio;
+};
+
+struct etraxfs_gpio_info {
+	unsigned int num_ports;
+	const struct etraxfs_gpio_port *ports;
+};
+
+static const struct etraxfs_gpio_port etraxfs_gpio_etraxfs_ports[] = {
+	{
+		.label	= "A",
+		.ngpio	= 8,
+		.oe	= ETRAX_FS_rw_pa_oe,
+		.dout	= ETRAX_FS_rw_pa_dout,
+		.din	= ETRAX_FS_r_pa_din,
+	},
+	{
+		.label	= "B",
+		.ngpio	= 18,
+		.oe	= ETRAX_FS_rw_pb_oe,
+		.dout	= ETRAX_FS_rw_pb_dout,
+		.din	= ETRAX_FS_r_pb_din,
+	},
+	{
+		.label	= "C",
+		.ngpio	= 18,
+		.oe	= ETRAX_FS_rw_pc_oe,
+		.dout	= ETRAX_FS_rw_pc_dout,
+		.din	= ETRAX_FS_r_pc_din,
+	},
+	{
+		.label	= "D",
+		.ngpio	= 18,
+		.oe	= ETRAX_FS_rw_pd_oe,
+		.dout	= ETRAX_FS_rw_pd_dout,
+		.din	= ETRAX_FS_r_pd_din,
+	},
+	{
+		.label	= "E",
+		.ngpio	= 18,
+		.oe	= ETRAX_FS_rw_pe_oe,
+		.dout	= ETRAX_FS_rw_pe_dout,
+		.din	= ETRAX_FS_r_pe_din,
+	},
+};
+
+static const struct etraxfs_gpio_info etraxfs_gpio_etraxfs = {
+	.num_ports = ARRAY_SIZE(etraxfs_gpio_etraxfs_ports),
+	.ports = etraxfs_gpio_etraxfs_ports,
+};
+
+static int etraxfs_gpio_of_xlate(struct gpio_chip *gc,
+			       const struct of_phandle_args *gpiospec,
+			       u32 *flags)
+{
+	/*
+	 * Port numbers are A to E, and the properties are integers, so we
+	 * specify them as 0xA - 0xE.
+	 */
+	if (gc->label[0] - 'A' + 0xA != gpiospec->args[2])
+		return -EINVAL;
+
+	return of_gpio_simple_xlate(gc, gpiospec, flags);
+}
+
+static const struct of_device_id etraxfs_gpio_of_table[] = {
+	{
+		.compatible = "axis,etraxfs-gio",
+		.data = &etraxfs_gpio_etraxfs,
+	},
+	{},
+};
+
+static int etraxfs_gpio_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	const struct etraxfs_gpio_info *info;
+	const struct of_device_id *match;
+	struct bgpio_chip *chips;
+	struct resource *res;
+	void __iomem *regs;
+	int ret;
+	int i;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	regs = devm_ioremap_resource(dev, res);
+	if (!regs)
+		return -ENOMEM;
+
+	match = of_match_node(etraxfs_gpio_of_table, dev->of_node);
+	if (!match)
+		return -EINVAL;
+
+	info = match->data;
+
+	chips = devm_kzalloc(dev, sizeof(*chips) * info->num_ports, GFP_KERNEL);
+	if (!chips)
+		return -ENOMEM;
+
+	for (i = 0; i < info->num_ports; i++) {
+		struct bgpio_chip *bgc = &chips[i];
+		const struct etraxfs_gpio_port *port = &info->ports[i];
+
+		ret = bgpio_init(bgc, dev, 4,
+				 regs + port->din,	/* dat */
+				 regs + port->dout,	/* set */
+				 NULL,			/* clr */
+				 regs + port->oe,	/* dirout */
+				 NULL,			/* dirin */
+				 BGPIOF_UNREADABLE_REG_SET);
+		if (ret)
+			return ret;
+
+		bgc->gc.ngpio = port->ngpio;
+		bgc->gc.label = port->label;
+
+		bgc->gc.of_node = dev->of_node;
+		bgc->gc.of_gpio_n_cells = 3;
+		bgc->gc.of_xlate = etraxfs_gpio_of_xlate;
+
+		ret = gpiochip_add(&bgc->gc);
+		if (ret)
+			dev_err(dev, "Unable to register port %s\n",
+				bgc->gc.label);
+	}
+
+	return 0;
+}
+
+static struct platform_driver etraxfs_gpio_driver = {
+	.driver = {
+		.name		= "etraxfs-gpio",
+		.of_match_table = of_match_ptr(etraxfs_gpio_of_table),
+	},
+	.probe	= etraxfs_gpio_probe,
+};
+
+static int __init etraxfs_gpio_init(void)
+{
+	return platform_driver_register(&etraxfs_gpio_driver);
+}
+
+device_initcall(etraxfs_gpio_init);
diff --git a/drivers/gpio/gpio-f7188x.c b/drivers/gpio/gpio-f7188x.c
index dbda8433c4f7..5e3c4fa67d82 100644
--- a/drivers/gpio/gpio-f7188x.c
+++ b/drivers/gpio/gpio-f7188x.c
@@ -172,7 +172,7 @@ static struct f7188x_gpio_bank f71869a_gpio_bank[] = {
 };
 
 static struct f7188x_gpio_bank f71882_gpio_bank[] = {
-	F7188X_GPIO_BANK(0 , 8, 0xF0),
+	F7188X_GPIO_BANK(0, 8, 0xF0),
 	F7188X_GPIO_BANK(10, 8, 0xE0),
 	F7188X_GPIO_BANK(20, 8, 0xD0),
 	F7188X_GPIO_BANK(30, 4, 0xC0),
@@ -180,7 +180,7 @@ static struct f7188x_gpio_bank f71882_gpio_bank[] = {
 };
 
 static struct f7188x_gpio_bank f71889_gpio_bank[] = {
-	F7188X_GPIO_BANK(0 , 7, 0xF0),
+	F7188X_GPIO_BANK(0, 7, 0xF0),
 	F7188X_GPIO_BANK(10, 7, 0xE0),
 	F7188X_GPIO_BANK(20, 8, 0xD0),
 	F7188X_GPIO_BANK(30, 8, 0xC0),
diff --git a/drivers/gpio/gpio-generic.c b/drivers/gpio/gpio-generic.c
index b92a690f5765..9bda3727fac1 100644
--- a/drivers/gpio/gpio-generic.c
+++ b/drivers/gpio/gpio-generic.c
@@ -135,6 +135,17 @@ static unsigned long bgpio_pin2mask_be(struct bgpio_chip *bgc,
 	return 1 << (bgc->bits - 1 - pin);
 }
 
+static int bgpio_get_set(struct gpio_chip *gc, unsigned int gpio)
+{
+	struct bgpio_chip *bgc = to_bgpio_chip(gc);
+	unsigned long pinmask = bgc->pin2mask(bgc, gpio);
+
+	if (bgc->dir & pinmask)
+		return bgc->read_reg(bgc->reg_set) & pinmask;
+	else
+		return bgc->read_reg(bgc->reg_dat) & pinmask;
+}
+
 static int bgpio_get(struct gpio_chip *gc, unsigned int gpio)
 {
 	struct bgpio_chip *bgc = to_bgpio_chip(gc);
@@ -416,7 +427,8 @@ static int bgpio_setup_accessors(struct device *dev,
 static int bgpio_setup_io(struct bgpio_chip *bgc,
 			  void __iomem *dat,
 			  void __iomem *set,
-			  void __iomem *clr)
+			  void __iomem *clr,
+			  unsigned long flags)
 {
 
 	bgc->reg_dat = dat;
@@ -437,7 +449,11 @@ static int bgpio_setup_io(struct bgpio_chip *bgc,
 		bgc->gc.set_multiple = bgpio_set_multiple;
 	}
 
-	bgc->gc.get = bgpio_get;
+	if (!(flags & BGPIOF_UNREADABLE_REG_SET) &&
+	    (flags & BGPIOF_READ_OUTPUT_REG_SET))
+		bgc->gc.get = bgpio_get_set;
+	else
+		bgc->gc.get = bgpio_get;
 
 	return 0;
 }
@@ -500,7 +516,7 @@ int bgpio_init(struct bgpio_chip *bgc, struct device *dev,
 	bgc->gc.ngpio = bgc->bits;
 	bgc->gc.request = bgpio_request;
 
-	ret = bgpio_setup_io(bgc, dat, set, clr);
+	ret = bgpio_setup_io(bgc, dat, set, clr, flags);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpio/gpio-it8761e.c b/drivers/gpio/gpio-it8761e.c
index dadfc245cf09..30a8f24c92c5 100644
--- a/drivers/gpio/gpio-it8761e.c
+++ b/drivers/gpio/gpio-it8761e.c
@@ -123,7 +123,7 @@ static void it8761e_gpio_set(struct gpio_chip *gc,
 
 	curr_vals = inb(reg);
 	if (val)
-		outb(curr_vals | (1 << bit) , reg);
+		outb(curr_vals | (1 << bit), reg);
 	else
 		outb(curr_vals & ~(1 << bit), reg);
 
diff --git a/drivers/gpio/gpio-lpc18xx.c b/drivers/gpio/gpio-lpc18xx.c
new file mode 100644
index 000000000000..eb68603136b0
--- /dev/null
+++ b/drivers/gpio/gpio-lpc18xx.c
@@ -0,0 +1,180 @@
+/*
+ * GPIO driver for NXP LPC18xx/43xx.
+ *
+ * Copyright (C) 2015 Joachim Eastwood <manabian@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/clk.h>
+#include <linux/gpio/driver.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_gpio.h>
+#include <linux/pinctrl/consumer.h>
+#include <linux/platform_device.h>
+
+/* LPC18xx GPIO register offsets */
+#define LPC18XX_REG_DIR(n)	(0x2000 + n * sizeof(u32))
+
+#define LPC18XX_MAX_PORTS	8
+#define LPC18XX_PINS_PER_PORT	32
+
+struct lpc18xx_gpio_chip {
+	struct gpio_chip gpio;
+	void __iomem *base;
+	struct clk *clk;
+	spinlock_t lock;
+};
+
+static inline struct lpc18xx_gpio_chip *to_lpc18xx_gpio(struct gpio_chip *chip)
+{
+	return container_of(chip, struct lpc18xx_gpio_chip, gpio);
+}
+
+static int lpc18xx_gpio_request(struct gpio_chip *chip, unsigned offset)
+{
+	return pinctrl_request_gpio(offset);
+}
+
+static void lpc18xx_gpio_free(struct gpio_chip *chip, unsigned offset)
+{
+	pinctrl_free_gpio(offset);
+}
+
+static void lpc18xx_gpio_set(struct gpio_chip *chip, unsigned offset, int value)
+{
+	struct lpc18xx_gpio_chip *gc = to_lpc18xx_gpio(chip);
+	writeb(value ? 1 : 0, gc->base + offset);
+}
+
+static int lpc18xx_gpio_get(struct gpio_chip *chip, unsigned offset)
+{
+	struct lpc18xx_gpio_chip *gc = to_lpc18xx_gpio(chip);
+	return !!readb(gc->base + offset);
+}
+
+static int lpc18xx_gpio_direction(struct gpio_chip *chip, unsigned offset,
+				  bool out)
+{
+	struct lpc18xx_gpio_chip *gc = to_lpc18xx_gpio(chip);
+	unsigned long flags;
+	u32 port, pin, dir;
+
+	port = offset / LPC18XX_PINS_PER_PORT;
+	pin  = offset % LPC18XX_PINS_PER_PORT;
+
+	spin_lock_irqsave(&gc->lock, flags);
+	dir = readl(gc->base + LPC18XX_REG_DIR(port));
+	if (out)
+		dir |= BIT(pin);
+	else
+		dir &= ~BIT(pin);
+	writel(dir, gc->base + LPC18XX_REG_DIR(port));
+	spin_unlock_irqrestore(&gc->lock, flags);
+
+	return 0;
+}
+
+static int lpc18xx_gpio_direction_input(struct gpio_chip *chip,
+					unsigned offset)
+{
+	return lpc18xx_gpio_direction(chip, offset, false);
+}
+
+static int lpc18xx_gpio_direction_output(struct gpio_chip *chip,
+					 unsigned offset, int value)
+{
+	lpc18xx_gpio_set(chip, offset, value);
+	return lpc18xx_gpio_direction(chip, offset, true);
+}
+
+static struct gpio_chip lpc18xx_chip = {
+	.label			= "lpc18xx/43xx-gpio",
+	.request		= lpc18xx_gpio_request,
+	.free			= lpc18xx_gpio_free,
+	.direction_input	= lpc18xx_gpio_direction_input,
+	.direction_output	= lpc18xx_gpio_direction_output,
+	.set			= lpc18xx_gpio_set,
+	.get			= lpc18xx_gpio_get,
+	.ngpio			= LPC18XX_MAX_PORTS * LPC18XX_PINS_PER_PORT,
+	.owner			= THIS_MODULE,
+};
+
+static int lpc18xx_gpio_probe(struct platform_device *pdev)
+{
+	struct lpc18xx_gpio_chip *gc;
+	struct resource *res;
+	int ret;
+
+	gc = devm_kzalloc(&pdev->dev, sizeof(*gc), GFP_KERNEL);
+	if (!gc)
+		return -ENOMEM;
+
+	gc->gpio = lpc18xx_chip;
+	platform_set_drvdata(pdev, gc);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	gc->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(gc->base))
+		return PTR_ERR(gc->base);
+
+	gc->clk = devm_clk_get(&pdev->dev, NULL);
+	if (IS_ERR(gc->clk)) {
+		dev_err(&pdev->dev, "input clock not found\n");
+		return PTR_ERR(gc->clk);
+	}
+
+	ret = clk_prepare_enable(gc->clk);
+	if (ret) {
+		dev_err(&pdev->dev, "unable to enable clock\n");
+		return ret;
+	}
+
+	spin_lock_init(&gc->lock);
+
+	gc->gpio.dev = &pdev->dev;
+
+	ret = gpiochip_add(&gc->gpio);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to add gpio chip\n");
+		clk_disable_unprepare(gc->clk);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int lpc18xx_gpio_remove(struct platform_device *pdev)
+{
+	struct lpc18xx_gpio_chip *gc = platform_get_drvdata(pdev);
+
+	gpiochip_remove(&gc->gpio);
+	clk_disable_unprepare(gc->clk);
+
+	return 0;
+}
+
+static const struct of_device_id lpc18xx_gpio_match[] = {
+	{ .compatible = "nxp,lpc1850-gpio" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, lpc18xx_gpio_match);
+
+static struct platform_driver lpc18xx_gpio_driver = {
+	.probe	= lpc18xx_gpio_probe,
+	.remove	= lpc18xx_gpio_remove,
+	.driver	= {
+		.name		= "lpc18xx-gpio",
+		.of_match_table	= lpc18xx_gpio_match,
+	},
+};
+module_platform_driver(lpc18xx_gpio_driver);
+
+MODULE_AUTHOR("Joachim Eastwood <manabian@gmail.com>");
+MODULE_DESCRIPTION("GPIO driver for LPC18xx/43xx");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/gpio/gpio-lynxpoint.c b/drivers/gpio/gpio-lynxpoint.c
index 127c755b38dc..153af464c7a7 100644
--- a/drivers/gpio/gpio-lynxpoint.c
+++ b/drivers/gpio/gpio-lynxpoint.c
@@ -72,7 +72,7 @@ struct lp_gpio {
  *
  * per gpio specific registers consist of two 32bit registers per gpio
  * (LP_CONFIG1 and LP_CONFIG2), with 94 gpios there's a total of
- * 188 config registes.
+ * 188 config registers.
  *
  * A simplified view of the register layout look like this:
  *
diff --git a/drivers/gpio/gpio-max732x.c b/drivers/gpio/gpio-max732x.c
index 0fa4543c5e02..aed4ca9338bc 100644
--- a/drivers/gpio/gpio-max732x.c
+++ b/drivers/gpio/gpio-max732x.c
@@ -429,6 +429,14 @@ static int max732x_irq_set_type(struct irq_data *d, unsigned int type)
 	return 0;
 }
 
+static int max732x_irq_set_wake(struct irq_data *data, unsigned int on)
+{
+	struct max732x_chip *chip = irq_data_get_irq_chip_data(data);
+
+	irq_set_irq_wake(chip->client->irq, on);
+	return 0;
+}
+
 static struct irq_chip max732x_irq_chip = {
 	.name			= "max732x",
 	.irq_mask		= max732x_irq_mask,
@@ -436,6 +444,7 @@ static struct irq_chip max732x_irq_chip = {
 	.irq_bus_lock		= max732x_irq_bus_lock,
 	.irq_bus_sync_unlock	= max732x_irq_bus_sync_unlock,
 	.irq_set_type		= max732x_irq_set_type,
+	.irq_set_wake		= max732x_irq_set_wake,
 };
 
 static uint8_t max732x_irq_pending(struct max732x_chip *chip)
@@ -507,12 +516,10 @@ static int max732x_irq_setup(struct max732x_chip *chip,
 		chip->irq_features = has_irq;
 		mutex_init(&chip->irq_lock);
 
-		ret = devm_request_threaded_irq(&client->dev,
-					client->irq,
-					NULL,
-					max732x_irq_handler,
-					IRQF_TRIGGER_FALLING | IRQF_ONESHOT,
-					dev_name(&client->dev), chip);
+		ret = devm_request_threaded_irq(&client->dev, client->irq,
+				NULL, max732x_irq_handler, IRQF_ONESHOT |
+				IRQF_TRIGGER_FALLING | IRQF_SHARED,
+				dev_name(&client->dev), chip);
 		if (ret) {
 			dev_err(&client->dev, "failed to request irq %d\n",
 				client->irq);
@@ -521,7 +528,7 @@ static int max732x_irq_setup(struct max732x_chip *chip,
 		ret =  gpiochip_irqchip_add(&chip->gpio_chip,
 					    &max732x_irq_chip,
 					    irq_base,
-					    handle_edge_irq,
+					    handle_simple_irq,
 					    IRQ_TYPE_NONE);
 		if (ret) {
 			dev_err(&client->dev,
diff --git a/drivers/gpio/gpio-moxart.c b/drivers/gpio/gpio-moxart.c
index c3ab46e595da..abd8676ce2b6 100644
--- a/drivers/gpio/gpio-moxart.c
+++ b/drivers/gpio/gpio-moxart.c
@@ -39,17 +39,6 @@ static void moxart_gpio_free(struct gpio_chip *chip, unsigned offset)
 	pinctrl_free_gpio(offset);
 }
 
-static int moxart_gpio_get(struct gpio_chip *chip, unsigned offset)
-{
-	struct bgpio_chip *bgc = to_bgpio_chip(chip);
-	u32 ret = bgc->read_reg(bgc->reg_dir);
-
-	if (ret & BIT(offset))
-		return !!(bgc->read_reg(bgc->reg_set) & BIT(offset));
-	else
-		return !!(bgc->read_reg(bgc->reg_dat) & BIT(offset));
-}
-
 static int moxart_gpio_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -68,8 +57,9 @@ static int moxart_gpio_probe(struct platform_device *pdev)
 		return PTR_ERR(base);
 
 	ret = bgpio_init(bgc, dev, 4, base + GPIO_DATA_IN,
-		    base + GPIO_DATA_OUT, NULL,
-		    base + GPIO_PIN_DIRECTION, NULL, 0);
+			 base + GPIO_DATA_OUT, NULL,
+			 base + GPIO_PIN_DIRECTION, NULL,
+			 BGPIOF_READ_OUTPUT_REG_SET);
 	if (ret) {
 		dev_err(&pdev->dev, "bgpio_init failed\n");
 		return ret;
@@ -78,7 +68,6 @@ static int moxart_gpio_probe(struct platform_device *pdev)
 	bgc->gc.label = "moxart-gpio";
 	bgc->gc.request = moxart_gpio_request;
 	bgc->gc.free = moxart_gpio_free;
-	bgc->gc.get = moxart_gpio_get;
 	bgc->data = bgc->read_reg(bgc->reg_set);
 	bgc->gc.base = 0;
 	bgc->gc.ngpio = 32;
diff --git a/drivers/gpio/gpio-mxc.c b/drivers/gpio/gpio-mxc.c
index 9f7446a7ac64..ec1eb1b7250f 100644
--- a/drivers/gpio/gpio-mxc.c
+++ b/drivers/gpio/gpio-mxc.c
@@ -131,7 +131,7 @@ static struct mxc_gpio_hwdata *mxc_gpio_hwdata;
 #define GPIO_INT_FALL_EDGE	(mxc_gpio_hwdata->fall_edge)
 #define GPIO_INT_BOTH_EDGES	0x4
 
-static struct platform_device_id mxc_gpio_devtype[] = {
+static const struct platform_device_id mxc_gpio_devtype[] = {
 	{
 		.name = "imx1-gpio",
 		.driver_data = IMX1_GPIO,
@@ -437,20 +437,20 @@ static int mxc_gpio_probe(struct platform_device *pdev)
 		irq_set_chained_handler(port->irq, mx2_gpio_irq_handler);
 	} else {
 		/* setup one handler for each entry */
-		irq_set_chained_handler(port->irq, mx3_gpio_irq_handler);
-		irq_set_handler_data(port->irq, port);
-		if (port->irq_high > 0) {
+		irq_set_chained_handler_and_data(port->irq,
+						 mx3_gpio_irq_handler, port);
+		if (port->irq_high > 0)
 			/* setup handler for GPIO 16 to 31 */
-			irq_set_chained_handler(port->irq_high,
-						mx3_gpio_irq_handler);
-			irq_set_handler_data(port->irq_high, port);
-		}
+			irq_set_chained_handler_and_data(port->irq_high,
+							 mx3_gpio_irq_handler,
+							 port);
 	}
 
 	err = bgpio_init(&port->bgc, &pdev->dev, 4,
 			 port->base + GPIO_PSR,
 			 port->base + GPIO_DR, NULL,
-			 port->base + GPIO_GDIR, NULL, 0);
+			 port->base + GPIO_GDIR, NULL,
+			 BGPIOF_READ_OUTPUT_REG_SET);
 	if (err)
 		goto out_bgio;
 
diff --git a/drivers/gpio/gpio-mxs.c b/drivers/gpio/gpio-mxs.c
index 84cbda6acdda..551d15d7c369 100644
--- a/drivers/gpio/gpio-mxs.c
+++ b/drivers/gpio/gpio-mxs.c
@@ -239,7 +239,7 @@ static int mxs_gpio_get_direction(struct gpio_chip *gc, unsigned offset)
 	return !(dir & mask);
 }
 
-static struct platform_device_id mxs_gpio_ids[] = {
+static const struct platform_device_id mxs_gpio_ids[] = {
 	{
 		.name = "imx23-gpio",
 		.driver_data = IMX23_GPIO,
@@ -320,8 +320,8 @@ static int mxs_gpio_probe(struct platform_device *pdev)
 	mxs_gpio_init_gc(port, irq_base);
 
 	/* setup one handler for each entry */
-	irq_set_chained_handler(port->irq, mxs_gpio_irq_handler);
-	irq_set_handler_data(port->irq, port);
+	irq_set_chained_handler_and_data(port->irq, mxs_gpio_irq_handler,
+					 port);
 
 	err = bgpio_init(&port->bgc, &pdev->dev, 4,
 			 port->base + PINCTRL_DIN(port),
diff --git a/drivers/gpio/gpio-omap.c b/drivers/gpio/gpio-omap.c
index b232397ad7ec..b0c57d505be7 100644
--- a/drivers/gpio/gpio-omap.c
+++ b/drivers/gpio/gpio-omap.c
@@ -488,9 +488,6 @@ static int omap_gpio_irq_type(struct irq_data *d, unsigned type)
 	unsigned long flags;
 	unsigned offset = d->hwirq;
 
-	if (!BANK_USED(bank))
-		pm_runtime_get_sync(bank->dev);
-
 	if (type & ~IRQ_TYPE_SENSE_MASK)
 		return -EINVAL;
 
@@ -498,12 +495,18 @@ static int omap_gpio_irq_type(struct irq_data *d, unsigned type)
 		(type & (IRQ_TYPE_LEVEL_LOW|IRQ_TYPE_LEVEL_HIGH)))
 		return -EINVAL;
 
+	if (!BANK_USED(bank))
+		pm_runtime_get_sync(bank->dev);
+
 	spin_lock_irqsave(&bank->lock, flags);
 	retval = omap_set_gpio_triggering(bank, offset, type);
+	if (retval)
+		goto error;
 	omap_gpio_init_irq(bank, offset);
 	if (!omap_gpio_is_input(bank, offset)) {
 		spin_unlock_irqrestore(&bank->lock, flags);
-		return -EINVAL;
+		retval = -EINVAL;
+		goto error;
 	}
 	spin_unlock_irqrestore(&bank->lock, flags);
 
@@ -512,6 +515,11 @@ static int omap_gpio_irq_type(struct irq_data *d, unsigned type)
 	else if (type & (IRQ_TYPE_EDGE_FALLING | IRQ_TYPE_EDGE_RISING))
 		__irq_set_handler_locked(d->irq, handle_edge_irq);
 
+	return 0;
+
+error:
+	if (!BANK_USED(bank))
+		pm_runtime_put(bank->dev);
 	return retval;
 }
 
@@ -638,15 +646,6 @@ static int omap_set_gpio_wakeup(struct gpio_bank *bank, unsigned offset,
 	return 0;
 }
 
-static void omap_reset_gpio(struct gpio_bank *bank, unsigned offset)
-{
-	omap_set_gpio_direction(bank, offset, 1);
-	omap_set_gpio_irqenable(bank, offset, 0);
-	omap_clear_gpio_irqstatus(bank, offset);
-	omap_set_gpio_triggering(bank, offset, IRQ_TYPE_NONE);
-	omap_clear_gpio_debounce(bank, offset);
-}
-
 /* Use disable_irq_wake() and enable_irq_wake() functions from drivers */
 static int omap_gpio_wake_enable(struct irq_data *d, unsigned int enable)
 {
@@ -669,14 +668,7 @@ static int omap_gpio_request(struct gpio_chip *chip, unsigned offset)
 		pm_runtime_get_sync(bank->dev);
 
 	spin_lock_irqsave(&bank->lock, flags);
-	/* Set trigger to none. You need to enable the desired trigger with
-	 * request_irq() or set_irq_type(). Only do this if the IRQ line has
-	 * not already been requested.
-	 */
-	if (!LINE_USED(bank->irq_usage, offset)) {
-		omap_set_gpio_triggering(bank, offset, IRQ_TYPE_NONE);
-		omap_enable_gpio_module(bank, offset);
-	}
+	omap_enable_gpio_module(bank, offset);
 	bank->mod_usage |= BIT(offset);
 	spin_unlock_irqrestore(&bank->lock, flags);
 
@@ -690,8 +682,11 @@ static void omap_gpio_free(struct gpio_chip *chip, unsigned offset)
 
 	spin_lock_irqsave(&bank->lock, flags);
 	bank->mod_usage &= ~(BIT(offset));
+	if (!LINE_USED(bank->irq_usage, offset)) {
+		omap_set_gpio_direction(bank, offset, 1);
+		omap_clear_gpio_debounce(bank, offset);
+	}
 	omap_disable_gpio_module(bank, offset);
-	omap_reset_gpio(bank, offset);
 	spin_unlock_irqrestore(&bank->lock, flags);
 
 	/*
@@ -795,11 +790,23 @@ static unsigned int omap_gpio_irq_startup(struct irq_data *d)
 		pm_runtime_get_sync(bank->dev);
 
 	spin_lock_irqsave(&bank->lock, flags);
-	omap_gpio_init_irq(bank, offset);
+
+	if (!LINE_USED(bank->mod_usage, offset))
+		omap_set_gpio_direction(bank, offset, 1);
+	else if (!omap_gpio_is_input(bank, offset))
+		goto err;
+	omap_enable_gpio_module(bank, offset);
+	bank->irq_usage |= BIT(offset);
+
 	spin_unlock_irqrestore(&bank->lock, flags);
 	omap_gpio_unmask_irq(d);
 
 	return 0;
+err:
+	spin_unlock_irqrestore(&bank->lock, flags);
+	if (!BANK_USED(bank))
+		pm_runtime_put(bank->dev);
+	return -EINVAL;
 }
 
 static void omap_gpio_irq_shutdown(struct irq_data *d)
@@ -810,8 +817,12 @@ static void omap_gpio_irq_shutdown(struct irq_data *d)
 
 	spin_lock_irqsave(&bank->lock, flags);
 	bank->irq_usage &= ~(BIT(offset));
+	omap_set_gpio_irqenable(bank, offset, 0);
+	omap_clear_gpio_irqstatus(bank, offset);
+	omap_set_gpio_triggering(bank, offset, IRQ_TYPE_NONE);
+	if (!LINE_USED(bank->mod_usage, offset))
+		omap_clear_gpio_debounce(bank, offset);
 	omap_disable_gpio_module(bank, offset);
-	omap_reset_gpio(bank, offset);
 	spin_unlock_irqrestore(&bank->lock, flags);
 
 	/*
@@ -1233,6 +1244,17 @@ static int omap_gpio_probe(struct platform_device *pdev)
 	return 0;
 }
 
+static int omap_gpio_remove(struct platform_device *pdev)
+{
+	struct gpio_bank *bank = platform_get_drvdata(pdev);
+
+	list_del(&bank->node);
+	gpiochip_remove(&bank->chip);
+	pm_runtime_disable(bank->dev);
+
+	return 0;
+}
+
 #ifdef CONFIG_ARCH_OMAP2PLUS
 
 #if defined(CONFIG_PM)
@@ -1418,6 +1440,7 @@ static int omap_gpio_runtime_resume(struct device *dev)
 }
 #endif /* CONFIG_PM */
 
+#if IS_BUILTIN(CONFIG_GPIO_OMAP)
 void omap2_gpio_prepare_for_idle(int pwr_mode)
 {
 	struct gpio_bank *bank;
@@ -1443,6 +1466,7 @@ void omap2_gpio_resume_after_idle(void)
 		pm_runtime_get_sync(bank->dev);
 	}
 }
+#endif
 
 #if defined(CONFIG_PM)
 static void omap_gpio_init_context(struct gpio_bank *p)
@@ -1598,6 +1622,7 @@ MODULE_DEVICE_TABLE(of, omap_gpio_match);
 
 static struct platform_driver omap_gpio_driver = {
 	.probe		= omap_gpio_probe,
+	.remove		= omap_gpio_remove,
 	.driver		= {
 		.name	= "omap_gpio",
 		.pm	= &gpio_pm_ops,
@@ -1615,3 +1640,13 @@ static int __init omap_gpio_drv_reg(void)
 	return platform_driver_register(&omap_gpio_driver);
 }
 postcore_initcall(omap_gpio_drv_reg);
+
+static void __exit omap_gpio_exit(void)
+{
+	platform_driver_unregister(&omap_gpio_driver);
+}
+module_exit(omap_gpio_exit);
+
+MODULE_DESCRIPTION("omap gpio driver");
+MODULE_ALIAS("platform:gpio-omap");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c
index e2da64abbccd..d233eb3b8132 100644
--- a/drivers/gpio/gpio-pca953x.c
+++ b/drivers/gpio/gpio-pca953x.c
@@ -443,12 +443,13 @@ static struct irq_chip pca953x_irq_chip = {
 	.irq_set_type		= pca953x_irq_set_type,
 };
 
-static u8 pca953x_irq_pending(struct pca953x_chip *chip, u8 *pending)
+static bool pca953x_irq_pending(struct pca953x_chip *chip, u8 *pending)
 {
 	u8 cur_stat[MAX_BANK];
 	u8 old_stat[MAX_BANK];
-	u8 pendings = 0;
-	u8 trigger[MAX_BANK], triggers = 0;
+	bool pending_seen = false;
+	bool trigger_seen = false;
+	u8 trigger[MAX_BANK];
 	int ret, i, offset = 0;
 
 	switch (chip->chip_type) {
@@ -461,7 +462,7 @@ static u8 pca953x_irq_pending(struct pca953x_chip *chip, u8 *pending)
 	}
 	ret = pca953x_read_regs(chip, offset, cur_stat);
 	if (ret)
-		return 0;
+		return false;
 
 	/* Remove output pins from the equation */
 	for (i = 0; i < NBANK(chip); i++)
@@ -471,11 +472,12 @@ static u8 pca953x_irq_pending(struct pca953x_chip *chip, u8 *pending)
 
 	for (i = 0; i < NBANK(chip); i++) {
 		trigger[i] = (cur_stat[i] ^ old_stat[i]) & chip->irq_mask[i];
-		triggers += trigger[i];
+		if (trigger[i])
+			trigger_seen = true;
 	}
 
-	if (!triggers)
-		return 0;
+	if (!trigger_seen)
+		return false;
 
 	memcpy(chip->irq_stat, cur_stat, NBANK(chip));
 
@@ -483,10 +485,11 @@ static u8 pca953x_irq_pending(struct pca953x_chip *chip, u8 *pending)
 		pending[i] = (old_stat[i] & chip->irq_trig_fall[i]) |
 			(cur_stat[i] & chip->irq_trig_raise[i]);
 		pending[i] &= trigger[i];
-		pendings += pending[i];
+		if (pending[i])
+			pending_seen = true;
 	}
 
-	return pendings;
+	return pending_seen;
 }
 
 static irqreturn_t pca953x_irq_handler(int irq, void *devid)
@@ -630,7 +633,7 @@ static int device_pca957x_init(struct pca953x_chip *chip, u32 invert)
 		memset(val, 0, NBANK(chip));
 	pca953x_write_regs(chip, PCA957X_INVRT, val);
 
-	/* To enable register 6, 7 to controll pull up and pull down */
+	/* To enable register 6, 7 to control pull up and pull down */
 	memset(val, 0x02, NBANK(chip));
 	pca953x_write_regs(chip, PCA957X_BKEN, val);
 
diff --git a/drivers/gpio/gpio-pcf857x.c b/drivers/gpio/gpio-pcf857x.c
index 945f0cda8529..404f3c61ef9b 100644
--- a/drivers/gpio/gpio-pcf857x.c
+++ b/drivers/gpio/gpio-pcf857x.c
@@ -91,6 +91,8 @@ struct pcf857x {
 	spinlock_t		slock;		/* protect irq demux */
 	unsigned		out;		/* software latch */
 	unsigned		status;		/* current status */
+	unsigned int		irq_parent;
+	unsigned		irq_enabled;	/* enabled irqs */
 
 	int (*write)(struct i2c_client *client, unsigned data);
 	int (*read)(struct i2c_client *client);
@@ -194,7 +196,7 @@ static irqreturn_t pcf857x_irq(int irq, void *data)
 	 * interrupt source, just to avoid bad irqs
 	 */
 
-	change = (gpio->status ^ status);
+	change = (gpio->status ^ status) & gpio->irq_enabled;
 	for_each_set_bit(i, &change, gpio->chip.ngpio)
 		handle_nested_irq(irq_find_mapping(gpio->chip.irqdomain, i));
 	gpio->status = status;
@@ -209,29 +211,62 @@ static irqreturn_t pcf857x_irq(int irq, void *data)
  */
 static void noop(struct irq_data *data) { }
 
-static unsigned int noop_ret(struct irq_data *data)
+static int pcf857x_irq_set_wake(struct irq_data *data, unsigned int on)
 {
-	return 0;
+	struct pcf857x *gpio = irq_data_get_irq_chip_data(data);
+
+	int error = 0;
+
+	if (gpio->irq_parent) {
+		error = irq_set_irq_wake(gpio->irq_parent, on);
+		if (error) {
+			dev_dbg(&gpio->client->dev,
+				"irq %u doesn't support irq_set_wake\n",
+				gpio->irq_parent);
+			gpio->irq_parent = 0;
+		}
+	}
+	return error;
 }
 
-static int pcf857x_irq_set_wake(struct irq_data *data, unsigned int on)
+static void pcf857x_irq_enable(struct irq_data *data)
 {
 	struct pcf857x *gpio = irq_data_get_irq_chip_data(data);
 
-	irq_set_irq_wake(gpio->client->irq, on);
-	return 0;
+	gpio->irq_enabled |= (1 << data->hwirq);
+}
+
+static void pcf857x_irq_disable(struct irq_data *data)
+{
+	struct pcf857x *gpio = irq_data_get_irq_chip_data(data);
+
+	gpio->irq_enabled &= ~(1 << data->hwirq);
+}
+
+static void pcf857x_irq_bus_lock(struct irq_data *data)
+{
+	struct pcf857x *gpio = irq_data_get_irq_chip_data(data);
+
+	mutex_lock(&gpio->lock);
+}
+
+static void pcf857x_irq_bus_sync_unlock(struct irq_data *data)
+{
+	struct pcf857x *gpio = irq_data_get_irq_chip_data(data);
+
+	mutex_unlock(&gpio->lock);
 }
 
 static struct irq_chip pcf857x_irq_chip = {
 	.name		= "pcf857x",
-	.irq_startup	= noop_ret,
-	.irq_shutdown	= noop,
-	.irq_enable	= noop,
-	.irq_disable	= noop,
+	.irq_enable	= pcf857x_irq_enable,
+	.irq_disable	= pcf857x_irq_disable,
 	.irq_ack	= noop,
 	.irq_mask	= noop,
 	.irq_unmask	= noop,
 	.irq_set_wake	= pcf857x_irq_set_wake,
+	.irq_bus_lock		= pcf857x_irq_bus_lock,
+	.irq_bus_sync_unlock	= pcf857x_irq_bus_sync_unlock,
 };
 
 /*-------------------------------------------------------------------------*/
@@ -364,6 +399,7 @@ static int pcf857x_probe(struct i2c_client *client,
 
 		gpiochip_set_chained_irqchip(&gpio->chip, &pcf857x_irq_chip,
 					     client->irq, NULL);
+		gpio->irq_parent = client->irq;
 	}
 
 	/* Let platform code set up the GPIOs and their users.
diff --git a/drivers/gpio/gpio-rcar.c b/drivers/gpio/gpio-rcar.c
index fd3977465948..1e14a6c74ed1 100644
--- a/drivers/gpio/gpio-rcar.c
+++ b/drivers/gpio/gpio-rcar.c
@@ -177,8 +177,17 @@ static int gpio_rcar_irq_set_wake(struct irq_data *d, unsigned int on)
 	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
 	struct gpio_rcar_priv *p = container_of(gc, struct gpio_rcar_priv,
 						gpio_chip);
-
-	irq_set_irq_wake(p->irq_parent, on);
+	int error;
+
+	if (p->irq_parent) {
+		error = irq_set_irq_wake(p->irq_parent, on);
+		if (error) {
+			dev_dbg(&p->pdev->dev,
+				"irq %u doesn't support irq_set_wake\n",
+				p->irq_parent);
+			p->irq_parent = 0;
+		}
+	}
 
 	if (!p->clk)
 		return 0;
diff --git a/drivers/gpio/gpio-stp-xway.c b/drivers/gpio/gpio-stp-xway.c
index 202361eb7279..81bdbe7ba2a4 100644
--- a/drivers/gpio/gpio-stp-xway.c
+++ b/drivers/gpio/gpio-stp-xway.c
@@ -58,7 +58,7 @@
 #define XWAY_STP_ADSL_MASK	0x3
 
 /* 2 groups of 3 bits can be driven by the phys */
-#define XWAY_STP_PHY_MASK	0x3
+#define XWAY_STP_PHY_MASK	0x7
 #define XWAY_STP_PHY1_SHIFT	27
 #define XWAY_STP_PHY2_SHIFT	15
 
@@ -200,7 +200,7 @@ static int xway_stp_hw_init(struct xway_stp *chip)
 static int xway_stp_probe(struct platform_device *pdev)
 {
 	struct resource *res;
-	const __be32 *shadow, *groups, *dsl, *phy;
+	u32 shadow, groups, dsl, phy;
 	struct xway_stp *chip;
 	struct clk *clk;
 	int ret = 0;
@@ -223,33 +223,28 @@ static int xway_stp_probe(struct platform_device *pdev)
 	chip->gc.owner = THIS_MODULE;
 
 	/* store the shadow value if one was passed by the devicetree */
-	shadow = of_get_property(pdev->dev.of_node, "lantiq,shadow", NULL);
-	if (shadow)
-		chip->shadow = be32_to_cpu(*shadow);
+	if (!of_property_read_u32(pdev->dev.of_node, "lantiq,shadow", &shadow))
+		chip->shadow = shadow;
 
 	/* find out which gpio groups should be enabled */
-	groups = of_get_property(pdev->dev.of_node, "lantiq,groups", NULL);
-	if (groups)
-		chip->groups = be32_to_cpu(*groups) & XWAY_STP_GROUP_MASK;
+	if (!of_property_read_u32(pdev->dev.of_node, "lantiq,groups", &groups))
+		chip->groups = groups & XWAY_STP_GROUP_MASK;
 	else
 		chip->groups = XWAY_STP_GROUP0;
 	chip->gc.ngpio = fls(chip->groups) * 8;
 
 	/* find out which gpios are controlled by the dsl core */
-	dsl = of_get_property(pdev->dev.of_node, "lantiq,dsl", NULL);
-	if (dsl)
-		chip->dsl = be32_to_cpu(*dsl) & XWAY_STP_ADSL_MASK;
+	if (!of_property_read_u32(pdev->dev.of_node, "lantiq,dsl", &dsl))
+		chip->dsl = dsl & XWAY_STP_ADSL_MASK;
 
 	/* find out which gpios are controlled by the phys */
 	if (of_machine_is_compatible("lantiq,ar9") ||
 			of_machine_is_compatible("lantiq,gr9") ||
 			of_machine_is_compatible("lantiq,vr9")) {
-		phy = of_get_property(pdev->dev.of_node, "lantiq,phy1", NULL);
-		if (phy)
-			chip->phy1 = be32_to_cpu(*phy) & XWAY_STP_PHY_MASK;
-		phy = of_get_property(pdev->dev.of_node, "lantiq,phy2", NULL);
-		if (phy)
-			chip->phy2 = be32_to_cpu(*phy) & XWAY_STP_PHY_MASK;
+		if (!of_property_read_u32(pdev->dev.of_node, "lantiq,phy1", &phy))
+			chip->phy1 = phy & XWAY_STP_PHY_MASK;
+		if (!of_property_read_u32(pdev->dev.of_node, "lantiq,phy2", &phy))
+			chip->phy2 = phy & XWAY_STP_PHY_MASK;
 	}
 
 	/* check which edge trigger we should use, default to a falling edge */
diff --git a/drivers/gpio/gpio-tb10x.c b/drivers/gpio/gpio-tb10x.c
index 46b89614aa91..12c99d969b98 100644
--- a/drivers/gpio/gpio-tb10x.c
+++ b/drivers/gpio/gpio-tb10x.c
@@ -292,7 +292,6 @@ static int tb10x_gpio_remove(struct platform_device *pdev)
 					BIT(tb10x_gpio->gc.ngpio) - 1, 0, 0);
 		kfree(tb10x_gpio->domain->gc);
 		irq_domain_remove(tb10x_gpio->domain);
-		free_irq(tb10x_gpio->irq, tb10x_gpio);
 	}
 	gpiochip_remove(&tb10x_gpio->gc);
 
diff --git a/drivers/gpio/gpio-tegra.c b/drivers/gpio/gpio-tegra.c
index 1741981d53c8..9b25c90f725c 100644
--- a/drivers/gpio/gpio-tegra.c
+++ b/drivers/gpio/gpio-tegra.c
@@ -288,7 +288,7 @@ static void tegra_gpio_irq_handler(unsigned int irq, struct irq_desc *desc)
 			tegra_gpio_writel(1 << pin, GPIO_INT_CLR(gpio));
 
 			/* if gpio is edge triggered, clear condition
-			 * before executing the hander so that we don't
+			 * before executing the handler so that we don't
 			 * miss edges
 			 */
 			if (lvl & (0x100 << pin)) {
@@ -515,8 +515,8 @@ static int tegra_gpio_probe(struct platform_device *pdev)
 	for (i = 0; i < tegra_gpio_bank_count; i++) {
 		bank = &tegra_gpio_banks[i];
 
-		irq_set_chained_handler(bank->irq, tegra_gpio_irq_handler);
-		irq_set_handler_data(bank->irq, bank);
+		irq_set_chained_handler_and_data(bank->irq,
+						 tegra_gpio_irq_handler, bank);
 
 		for (j = 0; j < 4; j++)
 			spin_lock_init(&bank->lvl_lock[j]);
diff --git a/drivers/gpio/gpio-ts5500.c b/drivers/gpio/gpio-ts5500.c
index 92fbabd82879..b29a102d136b 100644
--- a/drivers/gpio/gpio-ts5500.c
+++ b/drivers/gpio/gpio-ts5500.c
@@ -440,7 +440,7 @@ static int ts5500_dio_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static struct platform_device_id ts5500_dio_ids[] = {
+static const struct platform_device_id ts5500_dio_ids[] = {
 	{ "ts5500-dio1", TS5500_DIO1 },
 	{ "ts5500-dio2", TS5500_DIO2 },
 	{ "ts5500-dio-lcd", TS5500_LCD },
diff --git a/drivers/gpio/gpio-xgene-sb.c b/drivers/gpio/gpio-xgene-sb.c
index fb9d29a5d584..d57068b9083e 100644
--- a/drivers/gpio/gpio-xgene-sb.c
+++ b/drivers/gpio/gpio-xgene-sb.c
@@ -25,8 +25,11 @@
 #include <linux/of_gpio.h>
 #include <linux/gpio.h>
 #include <linux/gpio/driver.h>
+#include <linux/acpi.h>
 #include <linux/basic_mmio_gpio.h>
 
+#include "gpiolib.h"
+
 #define XGENE_MAX_GPIO_DS		22
 #define XGENE_MAX_GPIO_DS_IRQ		6
 
@@ -112,7 +115,6 @@ static int xgene_gpio_sb_probe(struct platform_device *pdev)
 				   GFP_KERNEL);
 	if (!priv->irq)
 		return -ENOMEM;
-	memset(priv->irq, 0, sizeof(u32) * XGENE_MAX_GPIO_DS);
 
 	for (i = 0; i < priv->nirq; i++) {
 		priv->irq[default_lines[i]] = platform_get_irq(pdev, i);
@@ -129,6 +131,11 @@ static int xgene_gpio_sb_probe(struct platform_device *pdev)
 	else
 		dev_info(&pdev->dev, "X-Gene GPIO Standby driver registered\n");
 
+	if (priv->nirq > 0) {
+		/* Register interrupt handlers for gpio signaled acpi events */
+		acpi_gpiochip_request_interrupts(&priv->bgc.gc);
+	}
+
 	return ret;
 }
 
@@ -136,6 +143,10 @@ static int xgene_gpio_sb_remove(struct platform_device *pdev)
 {
 	struct xgene_gpio_sb *priv = platform_get_drvdata(pdev);
 
+	if (priv->nirq > 0) {
+		acpi_gpiochip_free_interrupts(&priv->bgc.gc);
+	}
+
 	return bgpio_remove(&priv->bgc);
 }
 
@@ -145,10 +156,19 @@ static const struct of_device_id xgene_gpio_sb_of_match[] = {
 };
 MODULE_DEVICE_TABLE(of, xgene_gpio_sb_of_match);
 
+#ifdef CONFIG_ACPI
+static const struct acpi_device_id xgene_gpio_sb_acpi_match[] = {
+	{"APMC0D15", 0},
+	{},
+};
+MODULE_DEVICE_TABLE(acpi, xgene_gpio_sb_acpi_match);
+#endif
+
 static struct platform_driver xgene_gpio_sb_driver = {
 	.driver = {
 		   .name = "xgene-gpio-sb",
 		   .of_match_table = xgene_gpio_sb_of_match,
+		   .acpi_match_table = ACPI_PTR(xgene_gpio_sb_acpi_match),
 		   },
 	.probe = xgene_gpio_sb_probe,
 	.remove = xgene_gpio_sb_remove,
diff --git a/drivers/gpio/gpio-xilinx.c b/drivers/gpio/gpio-xilinx.c
index 61243d177740..77fe5d3cb105 100644
--- a/drivers/gpio/gpio-xilinx.c
+++ b/drivers/gpio/gpio-xilinx.c
@@ -41,10 +41,10 @@
 /**
  * struct xgpio_instance - Stores information about GPIO device
  * @mmchip: OF GPIO chip for memory mapped banks
+ * @gpio_width: GPIO width for every channel
  * @gpio_state: GPIO state shadow register
  * @gpio_dir: GPIO direction shadow register
  * @gpio_lock: Lock used for synchronization
- * @inited: True if the port has been inited
  */
 struct xgpio_instance {
 	struct of_mm_gpio_chip mmchip;
@@ -231,6 +231,8 @@ static void xgpio_save_regs(struct of_mm_gpio_chip *mm_gc)
  * @pdev: pointer to the platform device
  *
  * This function remove gpiochips and frees all the allocated resources.
+ *
+ * Return: 0 always
  */
 static int xgpio_remove(struct platform_device *pdev)
 {
diff --git a/drivers/gpio/gpio-xlp.c b/drivers/gpio/gpio-xlp.c
new file mode 100644
index 000000000000..9bdab7203d65
--- /dev/null
+++ b/drivers/gpio/gpio-xlp.c
@@ -0,0 +1,427 @@
+/*
+ * Copyright (C) 2003-2015 Broadcom Corporation
+ * All Rights Reserved
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/gpio.h>
+#include <linux/platform_device.h>
+#include <linux/of_device.h>
+#include <linux/module.h>
+#include <linux/irq.h>
+#include <linux/interrupt.h>
+
+/*
+ * XLP GPIO has multiple 32 bit registers for each feature where each register
+ * controls 32 pins. So, pins up to 64 require 2 32-bit registers and up to 96
+ * require 3 32-bit registers for each feature.
+ * Here we only define offset of the first register for each feature. Offset of
+ * the registers for pins greater than 32 can be calculated as following(Use
+ * GPIO_INT_STAT as example):
+ *
+ * offset = (gpio / XLP_GPIO_REGSZ) * 4;
+ * reg_addr = addr + offset;
+ *
+ * where addr is base address of the that feature register and gpio is the pin.
+ */
+#define GPIO_OUTPUT_EN		0x00
+#define GPIO_PADDRV		0x08
+#define GPIO_INT_EN00		0x18
+#define GPIO_INT_EN10		0x20
+#define GPIO_INT_EN20		0x28
+#define GPIO_INT_EN30		0x30
+#define GPIO_INT_POL		0x38
+#define GPIO_INT_TYPE		0x40
+#define GPIO_INT_STAT		0x48
+
+#define GPIO_9XX_BYTESWAP	0X00
+#define GPIO_9XX_CTRL		0X04
+#define GPIO_9XX_OUTPUT_EN	0x14
+#define GPIO_9XX_PADDRV		0x24
+/*
+ * Only for 4 interrupt enable reg are defined for now,
+ * total reg available are 12.
+ */
+#define GPIO_9XX_INT_EN00	0x44
+#define GPIO_9XX_INT_EN10	0x54
+#define GPIO_9XX_INT_EN20	0x64
+#define GPIO_9XX_INT_EN30	0x74
+#define GPIO_9XX_INT_POL	0x104
+#define GPIO_9XX_INT_TYPE	0x114
+#define GPIO_9XX_INT_STAT	0x124
+
+#define GPIO_3XX_INT_EN00	0x18
+#define GPIO_3XX_INT_EN10	0x20
+#define GPIO_3XX_INT_EN20	0x28
+#define GPIO_3XX_INT_EN30	0x30
+#define GPIO_3XX_INT_POL	0x78
+#define GPIO_3XX_INT_TYPE	0x80
+#define GPIO_3XX_INT_STAT	0x88
+
+/* Interrupt type register mask */
+#define XLP_GPIO_IRQ_TYPE_LVL	0x0
+#define XLP_GPIO_IRQ_TYPE_EDGE	0x1
+
+/* Interrupt polarity register mask */
+#define XLP_GPIO_IRQ_POL_HIGH	0x0
+#define XLP_GPIO_IRQ_POL_LOW	0x1
+
+#define XLP_GPIO_REGSZ		32
+#define XLP_GPIO_IRQ_BASE	768
+#define XLP_MAX_NR_GPIO		96
+
+/* XLP variants supported by this driver */
+enum {
+	XLP_GPIO_VARIANT_XLP832 = 1,
+	XLP_GPIO_VARIANT_XLP316,
+	XLP_GPIO_VARIANT_XLP208,
+	XLP_GPIO_VARIANT_XLP980,
+	XLP_GPIO_VARIANT_XLP532
+};
+
+struct xlp_gpio_priv {
+	struct gpio_chip chip;
+	DECLARE_BITMAP(gpio_enabled_mask, XLP_MAX_NR_GPIO);
+	void __iomem *gpio_intr_en;	/* pointer to first intr enable reg */
+	void __iomem *gpio_intr_stat;	/* pointer to first intr status reg */
+	void __iomem *gpio_intr_type;	/* pointer to first intr type reg */
+	void __iomem *gpio_intr_pol;	/* pointer to first intr polarity reg */
+	void __iomem *gpio_out_en;	/* pointer to first output enable reg */
+	void __iomem *gpio_paddrv;	/* pointer to first pad drive reg */
+	spinlock_t lock;
+};
+
+static struct xlp_gpio_priv *gpio_chip_to_xlp_priv(struct gpio_chip *gc)
+{
+	return container_of(gc, struct xlp_gpio_priv, chip);
+}
+
+static int xlp_gpio_get_reg(void __iomem *addr, unsigned gpio)
+{
+	u32 pos, regset;
+
+	pos = gpio % XLP_GPIO_REGSZ;
+	regset = (gpio / XLP_GPIO_REGSZ) * 4;
+	return !!(readl(addr + regset) & BIT(pos));
+}
+
+static void xlp_gpio_set_reg(void __iomem *addr, unsigned gpio, int state)
+{
+	u32 value, pos, regset;
+
+	pos = gpio % XLP_GPIO_REGSZ;
+	regset = (gpio / XLP_GPIO_REGSZ) * 4;
+	value = readl(addr + regset);
+
+	if (state)
+		value |= BIT(pos);
+	else
+		value &= ~BIT(pos);
+
+	writel(value, addr + regset);
+}
+
+static void xlp_gpio_irq_disable(struct irq_data *d)
+{
+	struct gpio_chip *gc  = irq_data_get_irq_chip_data(d);
+	struct xlp_gpio_priv *priv = gpio_chip_to_xlp_priv(gc);
+	unsigned long flags;
+
+	spin_lock_irqsave(&priv->lock, flags);
+	xlp_gpio_set_reg(priv->gpio_intr_en, d->hwirq, 0x0);
+	__clear_bit(d->hwirq, priv->gpio_enabled_mask);
+	spin_unlock_irqrestore(&priv->lock, flags);
+}
+
+static void xlp_gpio_irq_mask_ack(struct irq_data *d)
+{
+	struct gpio_chip *gc  = irq_data_get_irq_chip_data(d);
+	struct xlp_gpio_priv *priv = gpio_chip_to_xlp_priv(gc);
+	unsigned long flags;
+
+	spin_lock_irqsave(&priv->lock, flags);
+	xlp_gpio_set_reg(priv->gpio_intr_en, d->hwirq, 0x0);
+	xlp_gpio_set_reg(priv->gpio_intr_stat, d->hwirq, 0x1);
+	__clear_bit(d->hwirq, priv->gpio_enabled_mask);
+	spin_unlock_irqrestore(&priv->lock, flags);
+}
+
+static void xlp_gpio_irq_unmask(struct irq_data *d)
+{
+	struct gpio_chip *gc  = irq_data_get_irq_chip_data(d);
+	struct xlp_gpio_priv *priv = gpio_chip_to_xlp_priv(gc);
+	unsigned long flags;
+
+	spin_lock_irqsave(&priv->lock, flags);
+	xlp_gpio_set_reg(priv->gpio_intr_en, d->hwirq, 0x1);
+	__set_bit(d->hwirq, priv->gpio_enabled_mask);
+	spin_unlock_irqrestore(&priv->lock, flags);
+}
+
+static int xlp_gpio_set_irq_type(struct irq_data *d, unsigned int type)
+{
+	struct gpio_chip *gc  = irq_data_get_irq_chip_data(d);
+	struct xlp_gpio_priv *priv = gpio_chip_to_xlp_priv(gc);
+	int pol, irq_type;
+
+	switch (type) {
+	case IRQ_TYPE_EDGE_RISING:
+		irq_type = XLP_GPIO_IRQ_TYPE_EDGE;
+		pol = XLP_GPIO_IRQ_POL_HIGH;
+		break;
+	case IRQ_TYPE_EDGE_FALLING:
+		irq_type = XLP_GPIO_IRQ_TYPE_EDGE;
+		pol = XLP_GPIO_IRQ_POL_LOW;
+		break;
+	case IRQ_TYPE_LEVEL_HIGH:
+		irq_type = XLP_GPIO_IRQ_TYPE_LVL;
+		pol = XLP_GPIO_IRQ_POL_HIGH;
+		break;
+	case IRQ_TYPE_LEVEL_LOW:
+		irq_type = XLP_GPIO_IRQ_TYPE_LVL;
+		pol = XLP_GPIO_IRQ_POL_LOW;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	xlp_gpio_set_reg(priv->gpio_intr_type, d->hwirq, irq_type);
+	xlp_gpio_set_reg(priv->gpio_intr_pol, d->hwirq, pol);
+
+	return 0;
+}
+
+static struct irq_chip xlp_gpio_irq_chip = {
+	.name		= "XLP-GPIO",
+	.irq_mask_ack	= xlp_gpio_irq_mask_ack,
+	.irq_disable	= xlp_gpio_irq_disable,
+	.irq_set_type	= xlp_gpio_set_irq_type,
+	.irq_unmask	= xlp_gpio_irq_unmask,
+	.flags		= IRQCHIP_ONESHOT_SAFE,
+};
+
+static irqreturn_t xlp_gpio_generic_handler(int irq, void *data)
+{
+	struct xlp_gpio_priv *priv = data;
+	int gpio, regoff;
+	u32 gpio_stat;
+
+	regoff = -1;
+	gpio_stat = 0;
+	for_each_set_bit(gpio, priv->gpio_enabled_mask, XLP_MAX_NR_GPIO) {
+		if (regoff != gpio / XLP_GPIO_REGSZ) {
+			regoff = gpio / XLP_GPIO_REGSZ;
+			gpio_stat = readl(priv->gpio_intr_stat + regoff * 4);
+		}
+		if (gpio_stat & BIT(gpio % XLP_GPIO_REGSZ))
+			generic_handle_irq(irq_find_mapping(
+						priv->chip.irqdomain, gpio));
+	}
+
+	return IRQ_HANDLED;
+}
+
+static int xlp_gpio_dir_output(struct gpio_chip *gc, unsigned gpio, int state)
+{
+	struct xlp_gpio_priv *priv = gpio_chip_to_xlp_priv(gc);
+
+	BUG_ON(gpio >= gc->ngpio);
+	xlp_gpio_set_reg(priv->gpio_out_en, gpio, 0x1);
+
+	return 0;
+}
+
+static int xlp_gpio_dir_input(struct gpio_chip *gc, unsigned gpio)
+{
+	struct xlp_gpio_priv *priv = gpio_chip_to_xlp_priv(gc);
+
+	BUG_ON(gpio >= gc->ngpio);
+	xlp_gpio_set_reg(priv->gpio_out_en, gpio, 0x0);
+
+	return 0;
+}
+
+static int xlp_gpio_get(struct gpio_chip *gc, unsigned gpio)
+{
+	struct xlp_gpio_priv *priv = gpio_chip_to_xlp_priv(gc);
+
+	BUG_ON(gpio >= gc->ngpio);
+	return xlp_gpio_get_reg(priv->gpio_paddrv, gpio);
+}
+
+static void xlp_gpio_set(struct gpio_chip *gc, unsigned gpio, int state)
+{
+	struct xlp_gpio_priv *priv = gpio_chip_to_xlp_priv(gc);
+
+	BUG_ON(gpio >= gc->ngpio);
+	xlp_gpio_set_reg(priv->gpio_paddrv, gpio, state);
+}
+
+static const struct of_device_id xlp_gpio_of_ids[] = {
+	{
+		.compatible = "netlogic,xlp832-gpio",
+		.data	    = (void *)XLP_GPIO_VARIANT_XLP832,
+	},
+	{
+		.compatible = "netlogic,xlp316-gpio",
+		.data	    = (void *)XLP_GPIO_VARIANT_XLP316,
+	},
+	{
+		.compatible = "netlogic,xlp208-gpio",
+		.data	    = (void *)XLP_GPIO_VARIANT_XLP208,
+	},
+	{
+		.compatible = "netlogic,xlp980-gpio",
+		.data	    = (void *)XLP_GPIO_VARIANT_XLP980,
+	},
+	{
+		.compatible = "netlogic,xlp532-gpio",
+		.data	    = (void *)XLP_GPIO_VARIANT_XLP532,
+	},
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, xlp_gpio_of_ids);
+
+static int xlp_gpio_probe(struct platform_device *pdev)
+{
+	struct gpio_chip *gc;
+	struct resource *iores;
+	struct xlp_gpio_priv *priv;
+	const struct of_device_id *of_id;
+	void __iomem *gpio_base;
+	int irq_base, irq, err;
+	int ngpio;
+	u32 soc_type;
+
+	iores = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!iores)
+		return -ENODEV;
+
+	priv = devm_kzalloc(&pdev->dev,	sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	gpio_base = devm_ioremap_resource(&pdev->dev, iores);
+	if (IS_ERR(gpio_base))
+		return PTR_ERR(gpio_base);
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return irq;
+
+	of_id = of_match_device(xlp_gpio_of_ids, &pdev->dev);
+	if (!of_id) {
+		dev_err(&pdev->dev, "Failed to get soc type!\n");
+		return -ENODEV;
+	}
+
+	soc_type = (uintptr_t) of_id->data;
+
+	switch (soc_type) {
+	case XLP_GPIO_VARIANT_XLP832:
+		priv->gpio_out_en = gpio_base + GPIO_OUTPUT_EN;
+		priv->gpio_paddrv = gpio_base + GPIO_PADDRV;
+		priv->gpio_intr_stat = gpio_base + GPIO_INT_STAT;
+		priv->gpio_intr_type = gpio_base + GPIO_INT_TYPE;
+		priv->gpio_intr_pol = gpio_base + GPIO_INT_POL;
+		priv->gpio_intr_en = gpio_base + GPIO_INT_EN00;
+		ngpio = 41;
+		break;
+	case XLP_GPIO_VARIANT_XLP208:
+	case XLP_GPIO_VARIANT_XLP316:
+		priv->gpio_out_en = gpio_base + GPIO_OUTPUT_EN;
+		priv->gpio_paddrv = gpio_base + GPIO_PADDRV;
+		priv->gpio_intr_stat = gpio_base + GPIO_3XX_INT_STAT;
+		priv->gpio_intr_type = gpio_base + GPIO_3XX_INT_TYPE;
+		priv->gpio_intr_pol = gpio_base + GPIO_3XX_INT_POL;
+		priv->gpio_intr_en = gpio_base + GPIO_3XX_INT_EN00;
+
+		ngpio = (soc_type == XLP_GPIO_VARIANT_XLP208) ? 42 : 57;
+		break;
+	case XLP_GPIO_VARIANT_XLP980:
+	case XLP_GPIO_VARIANT_XLP532:
+		priv->gpio_out_en = gpio_base + GPIO_9XX_OUTPUT_EN;
+		priv->gpio_paddrv = gpio_base + GPIO_9XX_PADDRV;
+		priv->gpio_intr_stat = gpio_base + GPIO_9XX_INT_STAT;
+		priv->gpio_intr_type = gpio_base + GPIO_9XX_INT_TYPE;
+		priv->gpio_intr_pol = gpio_base + GPIO_9XX_INT_POL;
+		priv->gpio_intr_en = gpio_base + GPIO_9XX_INT_EN00;
+
+		ngpio = (soc_type == XLP_GPIO_VARIANT_XLP980) ? 66 : 67;
+		break;
+	default:
+		dev_err(&pdev->dev, "Unknown Processor type!\n");
+		return -ENODEV;
+	}
+
+	bitmap_zero(priv->gpio_enabled_mask, XLP_MAX_NR_GPIO);
+
+	gc = &priv->chip;
+
+	gc->owner = THIS_MODULE;
+	gc->label = dev_name(&pdev->dev);
+	gc->base = 0;
+	gc->dev = &pdev->dev;
+	gc->ngpio = ngpio;
+	gc->of_node = pdev->dev.of_node;
+	gc->direction_output = xlp_gpio_dir_output;
+	gc->direction_input = xlp_gpio_dir_input;
+	gc->set = xlp_gpio_set;
+	gc->get = xlp_gpio_get;
+
+	spin_lock_init(&priv->lock);
+
+	err = devm_request_irq(&pdev->dev, irq, xlp_gpio_generic_handler,
+			IRQ_TYPE_NONE, pdev->name, priv);
+	if (err)
+		return err;
+
+	irq_base = irq_alloc_descs(-1, XLP_GPIO_IRQ_BASE, gc->ngpio, 0);
+	if (irq_base < 0) {
+		dev_err(&pdev->dev, "Failed to allocate IRQ numbers\n");
+		return err;
+	}
+
+	err = gpiochip_add(gc);
+	if (err < 0)
+		goto out_free_desc;
+
+	err = gpiochip_irqchip_add(gc, &xlp_gpio_irq_chip, irq_base,
+				handle_level_irq, IRQ_TYPE_NONE);
+	if (err) {
+		dev_err(&pdev->dev, "Could not connect irqchip to gpiochip!\n");
+		goto out_gpio_remove;
+	}
+
+	dev_info(&pdev->dev, "registered %d GPIOs\n", gc->ngpio);
+
+	return 0;
+
+out_gpio_remove:
+	gpiochip_remove(gc);
+out_free_desc:
+	irq_free_descs(irq_base, gc->ngpio);
+	return err;
+}
+
+static struct platform_driver xlp_gpio_driver = {
+	.driver		= {
+		.name	= "xlp-gpio",
+		.of_match_table = xlp_gpio_of_ids,
+	},
+	.probe		= xlp_gpio_probe,
+};
+module_platform_driver(xlp_gpio_driver);
+
+MODULE_AUTHOR("Kamlakant Patel <kamlakant.patel@broadcom.com>");
+MODULE_AUTHOR("Ganesan Ramalingam <ganesanr@broadcom.com>");
+MODULE_DESCRIPTION("Netlogic XLP GPIO Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/gpio/gpio-zynq.c b/drivers/gpio/gpio-zynq.c
index 184c4b1b2558..2e87c4b8da26 100644
--- a/drivers/gpio/gpio-zynq.c
+++ b/drivers/gpio/gpio-zynq.c
@@ -18,34 +18,47 @@
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
+#include <linux/of.h>
 
 #define DRIVER_NAME "zynq-gpio"
 
 /* Maximum banks */
 #define ZYNQ_GPIO_MAX_BANK	4
+#define ZYNQMP_GPIO_MAX_BANK	6
 
 #define ZYNQ_GPIO_BANK0_NGPIO	32
 #define ZYNQ_GPIO_BANK1_NGPIO	22
 #define ZYNQ_GPIO_BANK2_NGPIO	32
 #define ZYNQ_GPIO_BANK3_NGPIO	32
 
-#define ZYNQ_GPIO_NR_GPIOS	(ZYNQ_GPIO_BANK0_NGPIO + \
-				 ZYNQ_GPIO_BANK1_NGPIO + \
-				 ZYNQ_GPIO_BANK2_NGPIO + \
-				 ZYNQ_GPIO_BANK3_NGPIO)
-
-#define ZYNQ_GPIO_BANK0_PIN_MIN	0
-#define ZYNQ_GPIO_BANK0_PIN_MAX	(ZYNQ_GPIO_BANK0_PIN_MIN + \
-					ZYNQ_GPIO_BANK0_NGPIO - 1)
-#define ZYNQ_GPIO_BANK1_PIN_MIN	(ZYNQ_GPIO_BANK0_PIN_MAX + 1)
-#define ZYNQ_GPIO_BANK1_PIN_MAX	(ZYNQ_GPIO_BANK1_PIN_MIN + \
-					ZYNQ_GPIO_BANK1_NGPIO - 1)
-#define ZYNQ_GPIO_BANK2_PIN_MIN	(ZYNQ_GPIO_BANK1_PIN_MAX + 1)
-#define ZYNQ_GPIO_BANK2_PIN_MAX	(ZYNQ_GPIO_BANK2_PIN_MIN + \
-					ZYNQ_GPIO_BANK2_NGPIO - 1)
-#define ZYNQ_GPIO_BANK3_PIN_MIN	(ZYNQ_GPIO_BANK2_PIN_MAX + 1)
-#define ZYNQ_GPIO_BANK3_PIN_MAX	(ZYNQ_GPIO_BANK3_PIN_MIN + \
-					ZYNQ_GPIO_BANK3_NGPIO - 1)
+#define ZYNQMP_GPIO_BANK0_NGPIO 26
+#define ZYNQMP_GPIO_BANK1_NGPIO 26
+#define ZYNQMP_GPIO_BANK2_NGPIO 26
+#define ZYNQMP_GPIO_BANK3_NGPIO 32
+#define ZYNQMP_GPIO_BANK4_NGPIO 32
+#define ZYNQMP_GPIO_BANK5_NGPIO 32
+
+#define	ZYNQ_GPIO_NR_GPIOS	118
+#define	ZYNQMP_GPIO_NR_GPIOS	174
+
+#define ZYNQ_GPIO_BANK0_PIN_MIN(str)	0
+#define ZYNQ_GPIO_BANK0_PIN_MAX(str)	(ZYNQ_GPIO_BANK0_PIN_MIN(str) + \
+					ZYNQ##str##_GPIO_BANK0_NGPIO - 1)
+#define ZYNQ_GPIO_BANK1_PIN_MIN(str)	(ZYNQ_GPIO_BANK0_PIN_MAX(str) + 1)
+#define ZYNQ_GPIO_BANK1_PIN_MAX(str)	(ZYNQ_GPIO_BANK1_PIN_MIN(str) + \
+					ZYNQ##str##_GPIO_BANK1_NGPIO - 1)
+#define ZYNQ_GPIO_BANK2_PIN_MIN(str)	(ZYNQ_GPIO_BANK1_PIN_MAX(str) + 1)
+#define ZYNQ_GPIO_BANK2_PIN_MAX(str)	(ZYNQ_GPIO_BANK2_PIN_MIN(str) + \
+					ZYNQ##str##_GPIO_BANK2_NGPIO - 1)
+#define ZYNQ_GPIO_BANK3_PIN_MIN(str)	(ZYNQ_GPIO_BANK2_PIN_MAX(str) + 1)
+#define ZYNQ_GPIO_BANK3_PIN_MAX(str)	(ZYNQ_GPIO_BANK3_PIN_MIN(str) + \
+					ZYNQ##str##_GPIO_BANK3_NGPIO - 1)
+#define ZYNQ_GPIO_BANK4_PIN_MIN(str)	(ZYNQ_GPIO_BANK3_PIN_MAX(str) + 1)
+#define ZYNQ_GPIO_BANK4_PIN_MAX(str)	(ZYNQ_GPIO_BANK4_PIN_MIN(str) + \
+					ZYNQ##str##_GPIO_BANK4_NGPIO - 1)
+#define ZYNQ_GPIO_BANK5_PIN_MIN(str)	(ZYNQ_GPIO_BANK4_PIN_MAX(str) + 1)
+#define ZYNQ_GPIO_BANK5_PIN_MAX(str)	(ZYNQ_GPIO_BANK5_PIN_MIN(str) + \
+					ZYNQ##str##_GPIO_BANK5_NGPIO - 1)
 
 
 /* Register offsets for the GPIO device */
@@ -89,12 +102,30 @@
  * @base_addr:	base address of the GPIO device
  * @clk:	clock resource for this controller
  * @irq:	interrupt for the GPIO device
+ * @p_data:	pointer to platform data
  */
 struct zynq_gpio {
 	struct gpio_chip chip;
 	void __iomem *base_addr;
 	struct clk *clk;
 	int irq;
+	const struct zynq_platform_data *p_data;
+};
+
+/**
+ * struct zynq_platform_data -  zynq gpio platform data structure
+ * @label:	string to store in gpio->label
+ * @ngpio:	max number of gpio pins
+ * @max_bank:	maximum number of gpio banks
+ * @bank_min:	this array represents bank's min pin
+ * @bank_max:	this array represents bank's max pin
+*/
+struct zynq_platform_data {
+	const char *label;
+	u16 ngpio;
+	int max_bank;
+	int bank_min[ZYNQMP_GPIO_MAX_BANK];
+	int bank_max[ZYNQMP_GPIO_MAX_BANK];
 };
 
 static struct irq_chip zynq_gpio_level_irqchip;
@@ -112,39 +143,26 @@ static struct irq_chip zynq_gpio_edge_irqchip;
  */
 static inline void zynq_gpio_get_bank_pin(unsigned int pin_num,
 					  unsigned int *bank_num,
-					  unsigned int *bank_pin_num)
+					  unsigned int *bank_pin_num,
+					  struct zynq_gpio *gpio)
 {
-	switch (pin_num) {
-	case ZYNQ_GPIO_BANK0_PIN_MIN ... ZYNQ_GPIO_BANK0_PIN_MAX:
-		*bank_num = 0;
-		*bank_pin_num = pin_num;
-		break;
-	case ZYNQ_GPIO_BANK1_PIN_MIN ... ZYNQ_GPIO_BANK1_PIN_MAX:
-		*bank_num = 1;
-		*bank_pin_num = pin_num - ZYNQ_GPIO_BANK1_PIN_MIN;
-		break;
-	case ZYNQ_GPIO_BANK2_PIN_MIN ... ZYNQ_GPIO_BANK2_PIN_MAX:
-		*bank_num = 2;
-		*bank_pin_num = pin_num - ZYNQ_GPIO_BANK2_PIN_MIN;
-		break;
-	case ZYNQ_GPIO_BANK3_PIN_MIN ... ZYNQ_GPIO_BANK3_PIN_MAX:
-		*bank_num = 3;
-		*bank_pin_num = pin_num - ZYNQ_GPIO_BANK3_PIN_MIN;
-		break;
-	default:
-		WARN(true, "invalid GPIO pin number: %u", pin_num);
-		*bank_num = 0;
-		*bank_pin_num = 0;
-		break;
+	int bank;
+
+	for (bank = 0; bank < gpio->p_data->max_bank; bank++) {
+		if ((pin_num >= gpio->p_data->bank_min[bank]) &&
+			(pin_num <= gpio->p_data->bank_max[bank])) {
+				*bank_num = bank;
+				*bank_pin_num = pin_num -
+						gpio->p_data->bank_min[bank];
+				return;
+		}
 	}
-}
 
-static const unsigned int zynq_gpio_bank_offset[] = {
-	ZYNQ_GPIO_BANK0_PIN_MIN,
-	ZYNQ_GPIO_BANK1_PIN_MIN,
-	ZYNQ_GPIO_BANK2_PIN_MIN,
-	ZYNQ_GPIO_BANK3_PIN_MIN,
-};
+	/* default */
+	WARN(true, "invalid GPIO pin number: %u", pin_num);
+	*bank_num = 0;
+	*bank_pin_num = 0;
+}
 
 /**
  * zynq_gpio_get_value - Get the state of the specified pin of GPIO device
@@ -161,7 +179,7 @@ static int zynq_gpio_get_value(struct gpio_chip *chip, unsigned int pin)
 	unsigned int bank_num, bank_pin_num;
 	struct zynq_gpio *gpio = container_of(chip, struct zynq_gpio, chip);
 
-	zynq_gpio_get_bank_pin(pin, &bank_num, &bank_pin_num);
+	zynq_gpio_get_bank_pin(pin, &bank_num, &bank_pin_num, gpio);
 
 	data = readl_relaxed(gpio->base_addr +
 			     ZYNQ_GPIO_DATA_RO_OFFSET(bank_num));
@@ -185,7 +203,7 @@ static void zynq_gpio_set_value(struct gpio_chip *chip, unsigned int pin,
 	unsigned int reg_offset, bank_num, bank_pin_num;
 	struct zynq_gpio *gpio = container_of(chip, struct zynq_gpio, chip);
 
-	zynq_gpio_get_bank_pin(pin, &bank_num, &bank_pin_num);
+	zynq_gpio_get_bank_pin(pin, &bank_num, &bank_pin_num, gpio);
 
 	if (bank_pin_num >= ZYNQ_GPIO_MID_PIN_NUM) {
 		/* only 16 data bits in bit maskable reg */
@@ -222,7 +240,7 @@ static int zynq_gpio_dir_in(struct gpio_chip *chip, unsigned int pin)
 	unsigned int bank_num, bank_pin_num;
 	struct zynq_gpio *gpio = container_of(chip, struct zynq_gpio, chip);
 
-	zynq_gpio_get_bank_pin(pin, &bank_num, &bank_pin_num);
+	zynq_gpio_get_bank_pin(pin, &bank_num, &bank_pin_num, gpio);
 
 	/* bank 0 pins 7 and 8 are special and cannot be used as inputs */
 	if (bank_num == 0 && (bank_pin_num == 7 || bank_pin_num == 8))
@@ -255,7 +273,7 @@ static int zynq_gpio_dir_out(struct gpio_chip *chip, unsigned int pin,
 	unsigned int bank_num, bank_pin_num;
 	struct zynq_gpio *gpio = container_of(chip, struct zynq_gpio, chip);
 
-	zynq_gpio_get_bank_pin(pin, &bank_num, &bank_pin_num);
+	zynq_gpio_get_bank_pin(pin, &bank_num, &bank_pin_num, gpio);
 
 	/* set the GPIO pin as output */
 	reg = readl_relaxed(gpio->base_addr + ZYNQ_GPIO_DIRM_OFFSET(bank_num));
@@ -286,7 +304,7 @@ static void zynq_gpio_irq_mask(struct irq_data *irq_data)
 	struct zynq_gpio *gpio = irq_data_get_irq_chip_data(irq_data);
 
 	device_pin_num = irq_data->hwirq;
-	zynq_gpio_get_bank_pin(device_pin_num, &bank_num, &bank_pin_num);
+	zynq_gpio_get_bank_pin(device_pin_num, &bank_num, &bank_pin_num, gpio);
 	writel_relaxed(BIT(bank_pin_num),
 		       gpio->base_addr + ZYNQ_GPIO_INTDIS_OFFSET(bank_num));
 }
@@ -306,7 +324,7 @@ static void zynq_gpio_irq_unmask(struct irq_data *irq_data)
 	struct zynq_gpio *gpio = irq_data_get_irq_chip_data(irq_data);
 
 	device_pin_num = irq_data->hwirq;
-	zynq_gpio_get_bank_pin(device_pin_num, &bank_num, &bank_pin_num);
+	zynq_gpio_get_bank_pin(device_pin_num, &bank_num, &bank_pin_num, gpio);
 	writel_relaxed(BIT(bank_pin_num),
 		       gpio->base_addr + ZYNQ_GPIO_INTEN_OFFSET(bank_num));
 }
@@ -325,7 +343,7 @@ static void zynq_gpio_irq_ack(struct irq_data *irq_data)
 	struct zynq_gpio *gpio = irq_data_get_irq_chip_data(irq_data);
 
 	device_pin_num = irq_data->hwirq;
-	zynq_gpio_get_bank_pin(device_pin_num, &bank_num, &bank_pin_num);
+	zynq_gpio_get_bank_pin(device_pin_num, &bank_num, &bank_pin_num, gpio);
 	writel_relaxed(BIT(bank_pin_num),
 		       gpio->base_addr + ZYNQ_GPIO_INTSTS_OFFSET(bank_num));
 }
@@ -335,7 +353,7 @@ static void zynq_gpio_irq_ack(struct irq_data *irq_data)
  * @irq_data:	irq data containing irq number of gpio pin for the interrupt
  *		to enable
  *
- * Clears the INTSTS bit and unmasks the given interrrupt.
+ * Clears the INTSTS bit and unmasks the given interrupt.
  */
 static void zynq_gpio_irq_enable(struct irq_data *irq_data)
 {
@@ -375,7 +393,7 @@ static int zynq_gpio_set_irq_type(struct irq_data *irq_data, unsigned int type)
 	struct zynq_gpio *gpio = irq_data_get_irq_chip_data(irq_data);
 
 	device_pin_num = irq_data->hwirq;
-	zynq_gpio_get_bank_pin(device_pin_num, &bank_num, &bank_pin_num);
+	zynq_gpio_get_bank_pin(device_pin_num, &bank_num, &bank_pin_num, gpio);
 
 	int_type = readl_relaxed(gpio->base_addr +
 				 ZYNQ_GPIO_INTTYPE_OFFSET(bank_num));
@@ -470,7 +488,7 @@ static void zynq_gpio_handle_bank_irq(struct zynq_gpio *gpio,
 				      unsigned int bank_num,
 				      unsigned long pending)
 {
-	unsigned int bank_offset = zynq_gpio_bank_offset[bank_num];
+	unsigned int bank_offset = gpio->p_data->bank_min[bank_num];
 	struct irq_domain *irqdomain = gpio->chip.irqdomain;
 	int offset;
 
@@ -505,7 +523,7 @@ static void zynq_gpio_irqhandler(unsigned int irq, struct irq_desc *desc)
 
 	chained_irq_enter(irqchip, desc);
 
-	for (bank_num = 0; bank_num < ZYNQ_GPIO_MAX_BANK; bank_num++) {
+	for (bank_num = 0; bank_num < gpio->p_data->max_bank; bank_num++) {
 		int_sts = readl_relaxed(gpio->base_addr +
 					ZYNQ_GPIO_INTSTS_OFFSET(bank_num));
 		int_enb = readl_relaxed(gpio->base_addr +
@@ -582,6 +600,46 @@ static const struct dev_pm_ops zynq_gpio_dev_pm_ops = {
 			zynq_gpio_runtime_resume, NULL)
 };
 
+static const struct zynq_platform_data zynqmp_gpio_def = {
+	.label = "zynqmp_gpio",
+	.ngpio = ZYNQMP_GPIO_NR_GPIOS,
+	.max_bank = ZYNQMP_GPIO_MAX_BANK,
+	.bank_min[0] = ZYNQ_GPIO_BANK0_PIN_MIN(MP),
+	.bank_max[0] = ZYNQ_GPIO_BANK0_PIN_MAX(MP),
+	.bank_min[1] = ZYNQ_GPIO_BANK1_PIN_MIN(MP),
+	.bank_max[1] = ZYNQ_GPIO_BANK1_PIN_MAX(MP),
+	.bank_min[2] = ZYNQ_GPIO_BANK2_PIN_MIN(MP),
+	.bank_max[2] = ZYNQ_GPIO_BANK2_PIN_MAX(MP),
+	.bank_min[3] = ZYNQ_GPIO_BANK3_PIN_MIN(MP),
+	.bank_max[3] = ZYNQ_GPIO_BANK3_PIN_MAX(MP),
+	.bank_min[4] = ZYNQ_GPIO_BANK4_PIN_MIN(MP),
+	.bank_max[4] = ZYNQ_GPIO_BANK4_PIN_MAX(MP),
+	.bank_min[5] = ZYNQ_GPIO_BANK5_PIN_MIN(MP),
+	.bank_max[5] = ZYNQ_GPIO_BANK5_PIN_MAX(MP),
+};
+
+static const struct zynq_platform_data zynq_gpio_def = {
+	.label = "zynq_gpio",
+	.ngpio = ZYNQ_GPIO_NR_GPIOS,
+	.max_bank = ZYNQ_GPIO_MAX_BANK,
+	.bank_min[0] = ZYNQ_GPIO_BANK0_PIN_MIN(),
+	.bank_max[0] = ZYNQ_GPIO_BANK0_PIN_MAX(),
+	.bank_min[1] = ZYNQ_GPIO_BANK1_PIN_MIN(),
+	.bank_max[1] = ZYNQ_GPIO_BANK1_PIN_MAX(),
+	.bank_min[2] = ZYNQ_GPIO_BANK2_PIN_MIN(),
+	.bank_max[2] = ZYNQ_GPIO_BANK2_PIN_MAX(),
+	.bank_min[3] = ZYNQ_GPIO_BANK3_PIN_MIN(),
+	.bank_max[3] = ZYNQ_GPIO_BANK3_PIN_MAX(),
+};
+
+static const struct of_device_id zynq_gpio_of_match[] = {
+	{ .compatible = "xlnx,zynq-gpio-1.0", .data = (void *)&zynq_gpio_def },
+	{ .compatible = "xlnx,zynqmp-gpio-1.0",
+					.data = (void *)&zynqmp_gpio_def },
+	{ /* end of table */ }
+};
+MODULE_DEVICE_TABLE(of, zynq_gpio_of_match);
+
 /**
  * zynq_gpio_probe - Initialization method for a zynq_gpio device
  * @pdev:	platform device instance
@@ -599,11 +657,18 @@ static int zynq_gpio_probe(struct platform_device *pdev)
 	struct zynq_gpio *gpio;
 	struct gpio_chip *chip;
 	struct resource *res;
+	const struct of_device_id *match;
 
 	gpio = devm_kzalloc(&pdev->dev, sizeof(*gpio), GFP_KERNEL);
 	if (!gpio)
 		return -ENOMEM;
 
+	match = of_match_node(zynq_gpio_of_match, pdev->dev.of_node);
+	if (!match) {
+		dev_err(&pdev->dev, "of_match_node() failed\n");
+		return -EINVAL;
+	}
+	gpio->p_data = match->data;
 	platform_set_drvdata(pdev, gpio);
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
@@ -619,7 +684,7 @@ static int zynq_gpio_probe(struct platform_device *pdev)
 
 	/* configure the gpio chip */
 	chip = &gpio->chip;
-	chip->label = "zynq_gpio";
+	chip->label = gpio->p_data->label;
 	chip->owner = THIS_MODULE;
 	chip->dev = &pdev->dev;
 	chip->get = zynq_gpio_get_value;
@@ -629,7 +694,7 @@ static int zynq_gpio_probe(struct platform_device *pdev)
 	chip->direction_input = zynq_gpio_dir_in;
 	chip->direction_output = zynq_gpio_dir_out;
 	chip->base = -1;
-	chip->ngpio = ZYNQ_GPIO_NR_GPIOS;
+	chip->ngpio = gpio->p_data->ngpio;
 
 	/* Enable GPIO clock */
 	gpio->clk = devm_clk_get(&pdev->dev, NULL);
@@ -651,7 +716,7 @@ static int zynq_gpio_probe(struct platform_device *pdev)
 	}
 
 	/* disable interrupts for all banks */
-	for (bank_num = 0; bank_num < ZYNQ_GPIO_MAX_BANK; bank_num++)
+	for (bank_num = 0; bank_num < gpio->p_data->max_bank; bank_num++)
 		writel_relaxed(ZYNQ_GPIO_IXR_DISABLE_ALL, gpio->base_addr +
 			       ZYNQ_GPIO_INTDIS_OFFSET(bank_num));
 
@@ -695,12 +760,6 @@ static int zynq_gpio_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static struct of_device_id zynq_gpio_of_match[] = {
-	{ .compatible = "xlnx,zynq-gpio-1.0", },
-	{ /* end of table */ }
-};
-MODULE_DEVICE_TABLE(of, zynq_gpio_of_match);
-
 static struct platform_driver zynq_gpio_driver = {
 	.driver	= {
 		.name = DRIVER_NAME,
diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c
index 725d16138b74..533fe5dbe6f8 100644
--- a/drivers/gpio/gpiolib-acpi.c
+++ b/drivers/gpio/gpiolib-acpi.c
@@ -114,10 +114,11 @@ static inline int acpi_gpiochip_pin_to_gpio_offset(struct gpio_chip *chip,
  * @path:	ACPI GPIO controller full path name, (e.g. "\\_SB.GPO1")
  * @pin:	ACPI GPIO pin number (0-based, controller-relative)
  *
- * Returns GPIO descriptor to use with Linux generic GPIO API, or ERR_PTR
- * error value
+ * Return: GPIO descriptor to use with Linux generic GPIO API, or ERR_PTR
+ * error value. Specifically returns %-EPROBE_DEFER if the referenced GPIO
+ * controller does not have gpiochip registered at the moment. This is to
+ * support probe deferral.
  */
-
 static struct gpio_desc *acpi_get_gpiod(char *path, int pin)
 {
 	struct gpio_chip *chip;
@@ -131,7 +132,7 @@ static struct gpio_desc *acpi_get_gpiod(char *path, int pin)
 
 	chip = gpiochip_find(handle, acpi_gpiochip_find);
 	if (!chip)
-		return ERR_PTR(-ENODEV);
+		return ERR_PTR(-EPROBE_DEFER);
 
 	offset = acpi_gpiochip_pin_to_gpio_offset(chip, pin);
 	if (offset < 0)
@@ -307,6 +308,7 @@ void acpi_gpiochip_request_interrupts(struct gpio_chip *chip)
 	acpi_walk_resources(handle, "_AEI",
 			    acpi_gpiochip_request_interrupt, acpi_gpio);
 }
+EXPORT_SYMBOL_GPL(acpi_gpiochip_request_interrupts);
 
 /**
  * acpi_gpiochip_free_interrupts() - Free GPIO ACPI event interrupts.
@@ -346,6 +348,7 @@ void acpi_gpiochip_free_interrupts(struct gpio_chip *chip)
 		kfree(event);
 	}
 }
+EXPORT_SYMBOL_GPL(acpi_gpiochip_free_interrupts);
 
 int acpi_dev_add_driver_gpios(struct acpi_device *adev,
 			      const struct acpi_gpio_mapping *gpios)
@@ -514,6 +517,35 @@ struct gpio_desc *acpi_get_gpiod_by_index(struct acpi_device *adev,
 	return lookup.desc ? lookup.desc : ERR_PTR(-ENOENT);
 }
 
+/**
+ * acpi_dev_gpio_irq_get() - Find GpioInt and translate it to Linux IRQ number
+ * @adev: pointer to a ACPI device to get IRQ from
+ * @index: index of GpioInt resource (starting from %0)
+ *
+ * If the device has one or more GpioInt resources, this function can be
+ * used to translate from the GPIO offset in the resource to the Linux IRQ
+ * number.
+ *
+ * Return: Linux IRQ number (>%0) on success, negative errno on failure.
+ */
+int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index)
+{
+	int idx, i;
+
+	for (i = 0, idx = 0; idx <= index; i++) {
+		struct acpi_gpio_info info;
+		struct gpio_desc *desc;
+
+		desc = acpi_get_gpiod_by_index(adev, NULL, i, &info);
+		if (IS_ERR(desc))
+			break;
+		if (info.gpioint && idx++ == index)
+			return gpiod_to_irq(desc);
+	}
+	return -ENOENT;
+}
+EXPORT_SYMBOL_GPL(acpi_dev_gpio_irq_get);
+
 static acpi_status
 acpi_gpio_adr_space_handler(u32 function, acpi_physical_address address,
 			    u32 bits, u64 *value, void *handler_context,
diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c
index a6c67c6b4680..9a0ec48a4737 100644
--- a/drivers/gpio/gpiolib-of.c
+++ b/drivers/gpio/gpiolib-of.c
@@ -242,7 +242,7 @@ int of_gpio_simple_xlate(struct gpio_chip *gc,
 {
 	/*
 	 * We're discouraging gpio_cells < 2, since that way you'll have to
-	 * write your own xlate function (that will have to retrive the GPIO
+	 * write your own xlate function (that will have to retrieve the GPIO
 	 * number and the flags from a single gpio cell -- this is possible,
 	 * but not recommended).
 	 */
diff --git a/drivers/gpio/gpiolib-sysfs.c b/drivers/gpio/gpiolib-sysfs.c
index af3bc7a8033b..b57ed8e55ab5 100644
--- a/drivers/gpio/gpiolib-sysfs.c
+++ b/drivers/gpio/gpiolib-sysfs.c
@@ -6,14 +6,29 @@
 #include <linux/gpio/driver.h>
 #include <linux/interrupt.h>
 #include <linux/kdev_t.h>
+#include <linux/slab.h>
 
 #include "gpiolib.h"
 
-static DEFINE_IDR(dirent_idr);
+#define GPIO_IRQF_TRIGGER_FALLING	BIT(0)
+#define GPIO_IRQF_TRIGGER_RISING	BIT(1)
+#define GPIO_IRQF_TRIGGER_BOTH		(GPIO_IRQF_TRIGGER_FALLING | \
+					 GPIO_IRQF_TRIGGER_RISING)
 
+struct gpiod_data {
+	struct gpio_desc *desc;
+
+	struct mutex mutex;
+	struct kernfs_node *value_kn;
+	int irq;
+	unsigned char irq_flags;
 
-/* lock protects against unexport_gpio() being called while
- * sysfs files are active.
+	bool direction_can_change;
+};
+
+/*
+ * Lock to serialise gpiod export and unexport, and prevent re-export of
+ * gpiod whose chip is being unregistered.
  */
 static DEFINE_MUTEX(sysfs_lock);
 
@@ -38,38 +53,35 @@ static DEFINE_MUTEX(sysfs_lock);
  *        /edge configuration
  */
 
-static ssize_t gpio_direction_show(struct device *dev,
+static ssize_t direction_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct gpio_desc	*desc = dev_get_drvdata(dev);
+	struct gpiod_data *data = dev_get_drvdata(dev);
+	struct gpio_desc *desc = data->desc;
 	ssize_t			status;
 
-	mutex_lock(&sysfs_lock);
+	mutex_lock(&data->mutex);
 
-	if (!test_bit(FLAG_EXPORT, &desc->flags)) {
-		status = -EIO;
-	} else {
-		gpiod_get_direction(desc);
-		status = sprintf(buf, "%s\n",
+	gpiod_get_direction(desc);
+	status = sprintf(buf, "%s\n",
 			test_bit(FLAG_IS_OUT, &desc->flags)
 				? "out" : "in");
-	}
 
-	mutex_unlock(&sysfs_lock);
+	mutex_unlock(&data->mutex);
+
 	return status;
 }
 
-static ssize_t gpio_direction_store(struct device *dev,
+static ssize_t direction_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t size)
 {
-	struct gpio_desc	*desc = dev_get_drvdata(dev);
+	struct gpiod_data *data = dev_get_drvdata(dev);
+	struct gpio_desc *desc = data->desc;
 	ssize_t			status;
 
-	mutex_lock(&sysfs_lock);
+	mutex_lock(&data->mutex);
 
-	if (!test_bit(FLAG_EXPORT, &desc->flags))
-		status = -EIO;
-	else if (sysfs_streq(buf, "high"))
+	if (sysfs_streq(buf, "high"))
 		status = gpiod_direction_output_raw(desc, 1);
 	else if (sysfs_streq(buf, "out") || sysfs_streq(buf, "low"))
 		status = gpiod_direction_output_raw(desc, 0);
@@ -78,43 +90,40 @@ static ssize_t gpio_direction_store(struct device *dev,
 	else
 		status = -EINVAL;
 
-	mutex_unlock(&sysfs_lock);
+	mutex_unlock(&data->mutex);
+
 	return status ? : size;
 }
+static DEVICE_ATTR_RW(direction);
 
-static /* const */ DEVICE_ATTR(direction, 0644,
-		gpio_direction_show, gpio_direction_store);
-
-static ssize_t gpio_value_show(struct device *dev,
+static ssize_t value_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct gpio_desc	*desc = dev_get_drvdata(dev);
+	struct gpiod_data *data = dev_get_drvdata(dev);
+	struct gpio_desc *desc = data->desc;
 	ssize_t			status;
 
-	mutex_lock(&sysfs_lock);
+	mutex_lock(&data->mutex);
 
-	if (!test_bit(FLAG_EXPORT, &desc->flags))
-		status = -EIO;
-	else
-		status = sprintf(buf, "%d\n", gpiod_get_value_cansleep(desc));
+	status = sprintf(buf, "%d\n", gpiod_get_value_cansleep(desc));
+
+	mutex_unlock(&data->mutex);
 
-	mutex_unlock(&sysfs_lock);
 	return status;
 }
 
-static ssize_t gpio_value_store(struct device *dev,
+static ssize_t value_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t size)
 {
-	struct gpio_desc	*desc = dev_get_drvdata(dev);
+	struct gpiod_data *data = dev_get_drvdata(dev);
+	struct gpio_desc *desc = data->desc;
 	ssize_t			status;
 
-	mutex_lock(&sysfs_lock);
+	mutex_lock(&data->mutex);
 
-	if (!test_bit(FLAG_EXPORT, &desc->flags))
-		status = -EIO;
-	else if (!test_bit(FLAG_IS_OUT, &desc->flags))
+	if (!test_bit(FLAG_IS_OUT, &desc->flags)) {
 		status = -EPERM;
-	else {
+	} else {
 		long		value;
 
 		status = kstrtol(buf, 0, &value);
@@ -124,172 +133,168 @@ static ssize_t gpio_value_store(struct device *dev,
 		}
 	}
 
-	mutex_unlock(&sysfs_lock);
+	mutex_unlock(&data->mutex);
+
 	return status;
 }
-
-static DEVICE_ATTR(value, 0644,
-		gpio_value_show, gpio_value_store);
+static DEVICE_ATTR_RW(value);
 
 static irqreturn_t gpio_sysfs_irq(int irq, void *priv)
 {
-	struct kernfs_node	*value_sd = priv;
+	struct gpiod_data *data = priv;
+
+	sysfs_notify_dirent(data->value_kn);
 
-	sysfs_notify_dirent(value_sd);
 	return IRQ_HANDLED;
 }
 
-static int gpio_setup_irq(struct gpio_desc *desc, struct device *dev,
-		unsigned long gpio_flags)
+/* Caller holds gpiod-data mutex. */
+static int gpio_sysfs_request_irq(struct device *dev, unsigned char flags)
 {
-	struct kernfs_node	*value_sd;
+	struct gpiod_data	*data = dev_get_drvdata(dev);
+	struct gpio_desc	*desc = data->desc;
 	unsigned long		irq_flags;
-	int			ret, irq, id;
+	int			ret;
 
-	if ((desc->flags & GPIO_TRIGGER_MASK) == gpio_flags)
-		return 0;
-
-	irq = gpiod_to_irq(desc);
-	if (irq < 0)
+	data->irq = gpiod_to_irq(desc);
+	if (data->irq < 0)
 		return -EIO;
 
-	id = desc->flags >> ID_SHIFT;
-	value_sd = idr_find(&dirent_idr, id);
-	if (value_sd)
-		free_irq(irq, value_sd);
-
-	desc->flags &= ~GPIO_TRIGGER_MASK;
-
-	if (!gpio_flags) {
-		gpiochip_unlock_as_irq(desc->chip, gpio_chip_hwgpio(desc));
-		ret = 0;
-		goto free_id;
-	}
+	data->value_kn = sysfs_get_dirent(dev->kobj.sd, "value");
+	if (!data->value_kn)
+		return -ENODEV;
 
 	irq_flags = IRQF_SHARED;
-	if (test_bit(FLAG_TRIG_FALL, &gpio_flags))
+	if (flags & GPIO_IRQF_TRIGGER_FALLING)
 		irq_flags |= test_bit(FLAG_ACTIVE_LOW, &desc->flags) ?
 			IRQF_TRIGGER_RISING : IRQF_TRIGGER_FALLING;
-	if (test_bit(FLAG_TRIG_RISE, &gpio_flags))
+	if (flags & GPIO_IRQF_TRIGGER_RISING)
 		irq_flags |= test_bit(FLAG_ACTIVE_LOW, &desc->flags) ?
 			IRQF_TRIGGER_FALLING : IRQF_TRIGGER_RISING;
 
-	if (!value_sd) {
-		value_sd = sysfs_get_dirent(dev->kobj.sd, "value");
-		if (!value_sd) {
-			ret = -ENODEV;
-			goto err_out;
-		}
-
-		ret = idr_alloc(&dirent_idr, value_sd, 1, 0, GFP_KERNEL);
-		if (ret < 0)
-			goto free_sd;
-		id = ret;
-
-		desc->flags &= GPIO_FLAGS_MASK;
-		desc->flags |= (unsigned long)id << ID_SHIFT;
-
-		if (desc->flags >> ID_SHIFT != id) {
-			ret = -ERANGE;
-			goto free_id;
-		}
-	}
+	/*
+	 * FIXME: This should be done in the irq_request_resources callback
+	 *        when the irq is requested, but a few drivers currently fail
+	 *        to do so.
+	 *
+	 *        Remove this redundant call (along with the corresponding
+	 *        unlock) when those drivers have been fixed.
+	 */
+	ret = gpiochip_lock_as_irq(desc->chip, gpio_chip_hwgpio(desc));
+	if (ret < 0)
+		goto err_put_kn;
 
-	ret = request_any_context_irq(irq, gpio_sysfs_irq, irq_flags,
-				"gpiolib", value_sd);
+	ret = request_any_context_irq(data->irq, gpio_sysfs_irq, irq_flags,
+				"gpiolib", data);
 	if (ret < 0)
-		goto free_id;
+		goto err_unlock;
 
-	ret = gpiochip_lock_as_irq(desc->chip, gpio_chip_hwgpio(desc));
-	if (ret < 0) {
-		gpiod_warn(desc, "failed to flag the GPIO for IRQ\n");
-		goto free_id;
-	}
+	data->irq_flags = flags;
 
-	desc->flags |= gpio_flags;
 	return 0;
 
-free_id:
-	idr_remove(&dirent_idr, id);
-	desc->flags &= GPIO_FLAGS_MASK;
-free_sd:
-	if (value_sd)
-		sysfs_put(value_sd);
-err_out:
+err_unlock:
+	gpiochip_unlock_as_irq(desc->chip, gpio_chip_hwgpio(desc));
+err_put_kn:
+	sysfs_put(data->value_kn);
+
 	return ret;
 }
 
+/*
+ * Caller holds gpiod-data mutex (unless called after class-device
+ * deregistration).
+ */
+static void gpio_sysfs_free_irq(struct device *dev)
+{
+	struct gpiod_data *data = dev_get_drvdata(dev);
+	struct gpio_desc *desc = data->desc;
+
+	data->irq_flags = 0;
+	free_irq(data->irq, data);
+	gpiochip_unlock_as_irq(desc->chip, gpio_chip_hwgpio(desc));
+	sysfs_put(data->value_kn);
+}
+
 static const struct {
 	const char *name;
-	unsigned long flags;
+	unsigned char flags;
 } trigger_types[] = {
 	{ "none",    0 },
-	{ "falling", BIT(FLAG_TRIG_FALL) },
-	{ "rising",  BIT(FLAG_TRIG_RISE) },
-	{ "both",    BIT(FLAG_TRIG_FALL) | BIT(FLAG_TRIG_RISE) },
+	{ "falling", GPIO_IRQF_TRIGGER_FALLING },
+	{ "rising",  GPIO_IRQF_TRIGGER_RISING },
+	{ "both",    GPIO_IRQF_TRIGGER_BOTH },
 };
 
-static ssize_t gpio_edge_show(struct device *dev,
+static ssize_t edge_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	const struct gpio_desc	*desc = dev_get_drvdata(dev);
-	ssize_t			status;
+	struct gpiod_data *data = dev_get_drvdata(dev);
+	ssize_t	status = 0;
+	int i;
 
-	mutex_lock(&sysfs_lock);
-
-	if (!test_bit(FLAG_EXPORT, &desc->flags))
-		status = -EIO;
-	else {
-		int i;
+	mutex_lock(&data->mutex);
 
-		status = 0;
-		for (i = 0; i < ARRAY_SIZE(trigger_types); i++)
-			if ((desc->flags & GPIO_TRIGGER_MASK)
-					== trigger_types[i].flags) {
-				status = sprintf(buf, "%s\n",
-						 trigger_types[i].name);
-				break;
-			}
+	for (i = 0; i < ARRAY_SIZE(trigger_types); i++) {
+		if (data->irq_flags == trigger_types[i].flags) {
+			status = sprintf(buf, "%s\n", trigger_types[i].name);
+			break;
+		}
 	}
 
-	mutex_unlock(&sysfs_lock);
+	mutex_unlock(&data->mutex);
+
 	return status;
 }
 
-static ssize_t gpio_edge_store(struct device *dev,
+static ssize_t edge_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t size)
 {
-	struct gpio_desc	*desc = dev_get_drvdata(dev);
-	ssize_t			status;
-	int			i;
+	struct gpiod_data *data = dev_get_drvdata(dev);
+	unsigned char flags;
+	ssize_t	status = size;
+	int i;
 
-	for (i = 0; i < ARRAY_SIZE(trigger_types); i++)
+	for (i = 0; i < ARRAY_SIZE(trigger_types); i++) {
 		if (sysfs_streq(trigger_types[i].name, buf))
-			goto found;
-	return -EINVAL;
+			break;
+	}
 
-found:
-	mutex_lock(&sysfs_lock);
+	if (i == ARRAY_SIZE(trigger_types))
+		return -EINVAL;
 
-	if (!test_bit(FLAG_EXPORT, &desc->flags))
-		status = -EIO;
-	else {
-		status = gpio_setup_irq(desc, dev, trigger_types[i].flags);
+	flags = trigger_types[i].flags;
+
+	mutex_lock(&data->mutex);
+
+	if (flags == data->irq_flags) {
+		status = size;
+		goto out_unlock;
+	}
+
+	if (data->irq_flags)
+		gpio_sysfs_free_irq(dev);
+
+	if (flags) {
+		status = gpio_sysfs_request_irq(dev, flags);
 		if (!status)
 			status = size;
 	}
 
-	mutex_unlock(&sysfs_lock);
+out_unlock:
+	mutex_unlock(&data->mutex);
 
 	return status;
 }
+static DEVICE_ATTR_RW(edge);
 
-static DEVICE_ATTR(edge, 0644, gpio_edge_show, gpio_edge_store);
-
-static int sysfs_set_active_low(struct gpio_desc *desc, struct device *dev,
-				int value)
+/* Caller holds gpiod-data mutex. */
+static int gpio_sysfs_set_active_low(struct device *dev, int value)
 {
+	struct gpiod_data	*data = dev_get_drvdata(dev);
+	struct gpio_desc	*desc = data->desc;
 	int			status = 0;
+	unsigned int		flags = data->irq_flags;
 
 	if (!!test_bit(FLAG_ACTIVE_LOW, &desc->flags) == !!value)
 		return 0;
@@ -300,69 +305,59 @@ static int sysfs_set_active_low(struct gpio_desc *desc, struct device *dev,
 		clear_bit(FLAG_ACTIVE_LOW, &desc->flags);
 
 	/* reconfigure poll(2) support if enabled on one edge only */
-	if (dev != NULL && (!!test_bit(FLAG_TRIG_RISE, &desc->flags) ^
-				!!test_bit(FLAG_TRIG_FALL, &desc->flags))) {
-		unsigned long trigger_flags = desc->flags & GPIO_TRIGGER_MASK;
-
-		gpio_setup_irq(desc, dev, 0);
-		status = gpio_setup_irq(desc, dev, trigger_flags);
+	if (flags == GPIO_IRQF_TRIGGER_FALLING ||
+					flags == GPIO_IRQF_TRIGGER_RISING) {
+		gpio_sysfs_free_irq(dev);
+		status = gpio_sysfs_request_irq(dev, flags);
 	}
 
 	return status;
 }
 
-static ssize_t gpio_active_low_show(struct device *dev,
+static ssize_t active_low_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	const struct gpio_desc	*desc = dev_get_drvdata(dev);
+	struct gpiod_data *data = dev_get_drvdata(dev);
+	struct gpio_desc *desc = data->desc;
 	ssize_t			status;
 
-	mutex_lock(&sysfs_lock);
+	mutex_lock(&data->mutex);
 
-	if (!test_bit(FLAG_EXPORT, &desc->flags))
-		status = -EIO;
-	else
-		status = sprintf(buf, "%d\n",
+	status = sprintf(buf, "%d\n",
 				!!test_bit(FLAG_ACTIVE_LOW, &desc->flags));
 
-	mutex_unlock(&sysfs_lock);
+	mutex_unlock(&data->mutex);
 
 	return status;
 }
 
-static ssize_t gpio_active_low_store(struct device *dev,
+static ssize_t active_low_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t size)
 {
-	struct gpio_desc	*desc = dev_get_drvdata(dev);
+	struct gpiod_data	*data = dev_get_drvdata(dev);
 	ssize_t			status;
+	long			value;
 
-	mutex_lock(&sysfs_lock);
+	mutex_lock(&data->mutex);
 
-	if (!test_bit(FLAG_EXPORT, &desc->flags)) {
-		status = -EIO;
-	} else {
-		long		value;
+	status = kstrtol(buf, 0, &value);
+	if (status == 0)
+		status = gpio_sysfs_set_active_low(dev, value);
 
-		status = kstrtol(buf, 0, &value);
-		if (status == 0)
-			status = sysfs_set_active_low(desc, dev, value != 0);
-	}
-
-	mutex_unlock(&sysfs_lock);
+	mutex_unlock(&data->mutex);
 
 	return status ? : size;
 }
-
-static DEVICE_ATTR(active_low, 0644,
-		gpio_active_low_show, gpio_active_low_store);
+static DEVICE_ATTR_RW(active_low);
 
 static umode_t gpio_is_visible(struct kobject *kobj, struct attribute *attr,
 			       int n)
 {
 	struct device *dev = container_of(kobj, struct device, kobj);
-	struct gpio_desc *desc = dev_get_drvdata(dev);
+	struct gpiod_data *data = dev_get_drvdata(dev);
+	struct gpio_desc *desc = data->desc;
 	umode_t mode = attr->mode;
-	bool show_direction = test_bit(FLAG_SYSFS_DIR, &desc->flags);
+	bool show_direction = data->direction_can_change;
 
 	if (attr == &dev_attr_direction.attr) {
 		if (!show_direction)
@@ -402,32 +397,32 @@ static const struct attribute_group *gpio_groups[] = {
  *   /ngpio ... matching gpio_chip.ngpio
  */
 
-static ssize_t chip_base_show(struct device *dev,
+static ssize_t base_show(struct device *dev,
 			       struct device_attribute *attr, char *buf)
 {
 	const struct gpio_chip	*chip = dev_get_drvdata(dev);
 
 	return sprintf(buf, "%d\n", chip->base);
 }
-static DEVICE_ATTR(base, 0444, chip_base_show, NULL);
+static DEVICE_ATTR_RO(base);
 
-static ssize_t chip_label_show(struct device *dev,
+static ssize_t label_show(struct device *dev,
 			       struct device_attribute *attr, char *buf)
 {
 	const struct gpio_chip	*chip = dev_get_drvdata(dev);
 
 	return sprintf(buf, "%s\n", chip->label ? : "");
 }
-static DEVICE_ATTR(label, 0444, chip_label_show, NULL);
+static DEVICE_ATTR_RO(label);
 
-static ssize_t chip_ngpio_show(struct device *dev,
+static ssize_t ngpio_show(struct device *dev,
 			       struct device_attribute *attr, char *buf)
 {
 	const struct gpio_chip	*chip = dev_get_drvdata(dev);
 
 	return sprintf(buf, "%u\n", chip->ngpio);
 }
-static DEVICE_ATTR(ngpio, 0444, chip_ngpio_show, NULL);
+static DEVICE_ATTR_RO(ngpio);
 
 static struct attribute *gpiochip_attrs[] = {
 	&dev_attr_base.attr,
@@ -552,6 +547,7 @@ static struct class gpio_class = {
 int gpiod_export(struct gpio_desc *desc, bool direction_may_change)
 {
 	struct gpio_chip	*chip;
+	struct gpiod_data	*data;
 	unsigned long		flags;
 	int			status;
 	const char		*ioname = NULL;
@@ -574,9 +570,9 @@ int gpiod_export(struct gpio_desc *desc, bool direction_may_change)
 	mutex_lock(&sysfs_lock);
 
 	/* check if chip is being removed */
-	if (!chip || !chip->exported) {
+	if (!chip || !chip->cdev) {
 		status = -ENODEV;
-		goto fail_unlock;
+		goto err_unlock;
 	}
 
 	spin_lock_irqsave(&gpio_lock, flags);
@@ -588,43 +584,54 @@ int gpiod_export(struct gpio_desc *desc, bool direction_may_change)
 				test_bit(FLAG_REQUESTED, &desc->flags),
 				test_bit(FLAG_EXPORT, &desc->flags));
 		status = -EPERM;
-		goto fail_unlock;
+		goto err_unlock;
 	}
+	spin_unlock_irqrestore(&gpio_lock, flags);
 
-	if (desc->chip->direction_input && desc->chip->direction_output &&
-			direction_may_change) {
-		set_bit(FLAG_SYSFS_DIR, &desc->flags);
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data) {
+		status = -ENOMEM;
+		goto err_unlock;
 	}
 
-	spin_unlock_irqrestore(&gpio_lock, flags);
+	data->desc = desc;
+	mutex_init(&data->mutex);
+	if (chip->direction_input && chip->direction_output)
+		data->direction_can_change = direction_may_change;
+	else
+		data->direction_can_change = false;
 
 	offset = gpio_chip_hwgpio(desc);
-	if (desc->chip->names && desc->chip->names[offset])
-		ioname = desc->chip->names[offset];
+	if (chip->names && chip->names[offset])
+		ioname = chip->names[offset];
 
-	dev = device_create_with_groups(&gpio_class, desc->chip->dev,
-					MKDEV(0, 0), desc, gpio_groups,
+	dev = device_create_with_groups(&gpio_class, chip->dev,
+					MKDEV(0, 0), data, gpio_groups,
 					ioname ? ioname : "gpio%u",
 					desc_to_gpio(desc));
 	if (IS_ERR(dev)) {
 		status = PTR_ERR(dev);
-		goto fail_unlock;
+		goto err_free_data;
 	}
 
 	set_bit(FLAG_EXPORT, &desc->flags);
 	mutex_unlock(&sysfs_lock);
 	return 0;
 
-fail_unlock:
+err_free_data:
+	kfree(data);
+err_unlock:
 	mutex_unlock(&sysfs_lock);
 	gpiod_dbg(desc, "%s: status %d\n", __func__, status);
 	return status;
 }
 EXPORT_SYMBOL_GPL(gpiod_export);
 
-static int match_export(struct device *dev, const void *data)
+static int match_export(struct device *dev, const void *desc)
 {
-	return dev_get_drvdata(dev) == data;
+	struct gpiod_data *data = dev_get_drvdata(dev);
+
+	return data->desc == desc;
 }
 
 /**
@@ -641,82 +648,26 @@ static int match_export(struct device *dev, const void *data)
 int gpiod_export_link(struct device *dev, const char *name,
 		      struct gpio_desc *desc)
 {
-	int			status = -EINVAL;
+	struct device *cdev;
+	int ret;
 
 	if (!desc) {
 		pr_warn("%s: invalid GPIO\n", __func__);
 		return -EINVAL;
 	}
 
-	mutex_lock(&sysfs_lock);
-
-	if (test_bit(FLAG_EXPORT, &desc->flags)) {
-		struct device *tdev;
-
-		tdev = class_find_device(&gpio_class, NULL, desc, match_export);
-		if (tdev != NULL) {
-			status = sysfs_create_link(&dev->kobj, &tdev->kobj,
-						name);
-			put_device(tdev);
-		} else {
-			status = -ENODEV;
-		}
-	}
-
-	mutex_unlock(&sysfs_lock);
+	cdev = class_find_device(&gpio_class, NULL, desc, match_export);
+	if (!cdev)
+		return -ENODEV;
 
-	if (status)
-		gpiod_dbg(desc, "%s: status %d\n", __func__, status);
+	ret = sysfs_create_link(&dev->kobj, &cdev->kobj, name);
+	put_device(cdev);
 
-	return status;
+	return ret;
 }
 EXPORT_SYMBOL_GPL(gpiod_export_link);
 
 /**
- * gpiod_sysfs_set_active_low - set the polarity of gpio sysfs value
- * @gpio: gpio to change
- * @value: non-zero to use active low, i.e. inverted values
- *
- * Set the polarity of /sys/class/gpio/gpioN/value sysfs attribute.
- * The GPIO does not have to be exported yet.  If poll(2) support has
- * been enabled for either rising or falling edge, it will be
- * reconfigured to follow the new polarity.
- *
- * Returns zero on success, else an error.
- */
-int gpiod_sysfs_set_active_low(struct gpio_desc *desc, int value)
-{
-	struct device		*dev = NULL;
-	int			status = -EINVAL;
-
-	if (!desc) {
-		pr_warn("%s: invalid GPIO\n", __func__);
-		return -EINVAL;
-	}
-
-	mutex_lock(&sysfs_lock);
-
-	if (test_bit(FLAG_EXPORT, &desc->flags)) {
-		dev = class_find_device(&gpio_class, NULL, desc, match_export);
-		if (dev == NULL) {
-			status = -ENODEV;
-			goto unlock;
-		}
-	}
-
-	status = sysfs_set_active_low(desc, dev, value);
-	put_device(dev);
-unlock:
-	mutex_unlock(&sysfs_lock);
-
-	if (status)
-		gpiod_dbg(desc, "%s: status %d\n", __func__, status);
-
-	return status;
-}
-EXPORT_SYMBOL_GPL(gpiod_sysfs_set_active_low);
-
-/**
  * gpiod_unexport - reverse effect of gpio_export()
  * @gpio: gpio to make unavailable
  *
@@ -724,8 +675,8 @@ EXPORT_SYMBOL_GPL(gpiod_sysfs_set_active_low);
  */
 void gpiod_unexport(struct gpio_desc *desc)
 {
-	int			status = 0;
-	struct device		*dev = NULL;
+	struct gpiod_data *data;
+	struct device *dev;
 
 	if (!desc) {
 		pr_warn("%s: invalid GPIO\n", __func__);
@@ -734,82 +685,79 @@ void gpiod_unexport(struct gpio_desc *desc)
 
 	mutex_lock(&sysfs_lock);
 
-	if (test_bit(FLAG_EXPORT, &desc->flags)) {
+	if (!test_bit(FLAG_EXPORT, &desc->flags))
+		goto err_unlock;
 
-		dev = class_find_device(&gpio_class, NULL, desc, match_export);
-		if (dev) {
-			gpio_setup_irq(desc, dev, 0);
-			clear_bit(FLAG_SYSFS_DIR, &desc->flags);
-			clear_bit(FLAG_EXPORT, &desc->flags);
-		} else
-			status = -ENODEV;
-	}
+	dev = class_find_device(&gpio_class, NULL, desc, match_export);
+	if (!dev)
+		goto err_unlock;
+
+	data = dev_get_drvdata(dev);
+
+	clear_bit(FLAG_EXPORT, &desc->flags);
+
+	device_unregister(dev);
+
+	/*
+	 * Release irq after deregistration to prevent race with edge_store.
+	 */
+	if (data->irq_flags)
+		gpio_sysfs_free_irq(dev);
 
 	mutex_unlock(&sysfs_lock);
 
-	if (dev) {
-		device_unregister(dev);
-		put_device(dev);
-	}
+	put_device(dev);
+	kfree(data);
 
-	if (status)
-		gpiod_dbg(desc, "%s: status %d\n", __func__, status);
+	return;
+
+err_unlock:
+	mutex_unlock(&sysfs_lock);
 }
 EXPORT_SYMBOL_GPL(gpiod_unexport);
 
-int gpiochip_export(struct gpio_chip *chip)
+int gpiochip_sysfs_register(struct gpio_chip *chip)
 {
-	int		status;
 	struct device	*dev;
 
-	/* Many systems register gpio chips for SOC support very early,
+	/*
+	 * Many systems add gpio chips for SOC support very early,
 	 * before driver model support is available.  In those cases we
-	 * export this later, in gpiolib_sysfs_init() ... here we just
+	 * register later, in gpiolib_sysfs_init() ... here we just
 	 * verify that _some_ field of gpio_class got initialized.
 	 */
 	if (!gpio_class.p)
 		return 0;
 
 	/* use chip->base for the ID; it's already known to be unique */
-	mutex_lock(&sysfs_lock);
 	dev = device_create_with_groups(&gpio_class, chip->dev, MKDEV(0, 0),
 					chip, gpiochip_groups,
 					"gpiochip%d", chip->base);
 	if (IS_ERR(dev))
-		status = PTR_ERR(dev);
-	else
-		status = 0;
-	chip->exported = (status == 0);
-	mutex_unlock(&sysfs_lock);
+		return PTR_ERR(dev);
 
-	if (status)
-		chip_dbg(chip, "%s: status %d\n", __func__, status);
+	mutex_lock(&sysfs_lock);
+	chip->cdev = dev;
+	mutex_unlock(&sysfs_lock);
 
-	return status;
+	return 0;
 }
 
-void gpiochip_unexport(struct gpio_chip *chip)
+void gpiochip_sysfs_unregister(struct gpio_chip *chip)
 {
-	int			status;
-	struct device		*dev;
 	struct gpio_desc *desc;
 	unsigned int i;
 
+	if (!chip->cdev)
+		return;
+
+	device_unregister(chip->cdev);
+
+	/* prevent further gpiod exports */
 	mutex_lock(&sysfs_lock);
-	dev = class_find_device(&gpio_class, NULL, chip, match_export);
-	if (dev) {
-		put_device(dev);
-		device_unregister(dev);
-		/* prevent further gpiod exports */
-		chip->exported = false;
-		status = 0;
-	} else
-		status = -ENODEV;
+	chip->cdev = NULL;
 	mutex_unlock(&sysfs_lock);
 
-	if (status)
-		chip_dbg(chip, "%s: status %d\n", __func__, status);
-
 	/* unregister gpiod class devices owned by sysfs */
 	for (i = 0; i < chip->ngpio; i++) {
 		desc = &chip->desc[i];
@@ -836,19 +784,20 @@ static int __init gpiolib_sysfs_init(void)
 	 */
 	spin_lock_irqsave(&gpio_lock, flags);
 	list_for_each_entry(chip, &gpio_chips, list) {
-		if (chip->exported)
+		if (chip->cdev)
 			continue;
 
 		/*
-		 * TODO we yield gpio_lock here because gpiochip_export()
-		 * acquires a mutex. This is unsafe and needs to be fixed.
+		 * TODO we yield gpio_lock here because
+		 * gpiochip_sysfs_register() acquires a mutex. This is unsafe
+		 * and needs to be fixed.
 		 *
 		 * Also it would be nice to use gpiochip_find() here so we
 		 * can keep gpio_chips local to gpiolib.c, but the yield of
 		 * gpio_lock prevents us from doing this.
 		 */
 		spin_unlock_irqrestore(&gpio_lock, flags);
-		status = gpiochip_export(chip);
+		status = gpiochip_sysfs_register(chip);
 		spin_lock_irqsave(&gpio_lock, flags);
 	}
 	spin_unlock_irqrestore(&gpio_lock, flags);
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 6bc612b8a49f..be42ab368a80 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -290,7 +290,7 @@ int gpiochip_add(struct gpio_chip *chip)
 	of_gpiochip_add(chip);
 	acpi_gpiochip_add(chip);
 
-	status = gpiochip_export(chip);
+	status = gpiochip_sysfs_register(chip);
 	if (status)
 		goto err_remove_chip;
 
@@ -327,10 +327,12 @@ EXPORT_SYMBOL_GPL(gpiochip_add);
  */
 void gpiochip_remove(struct gpio_chip *chip)
 {
+	struct gpio_desc *desc;
 	unsigned long	flags;
 	unsigned	id;
+	bool		requested = false;
 
-	gpiochip_unexport(chip);
+	gpiochip_sysfs_unregister(chip);
 
 	gpiochip_irqchip_remove(chip);
 
@@ -341,15 +343,17 @@ void gpiochip_remove(struct gpio_chip *chip)
 
 	spin_lock_irqsave(&gpio_lock, flags);
 	for (id = 0; id < chip->ngpio; id++) {
-		if (test_bit(FLAG_REQUESTED, &chip->desc[id].flags))
-			dev_crit(chip->dev, "REMOVING GPIOCHIP WITH GPIOS STILL REQUESTED\n");
+		desc = &chip->desc[id];
+		desc->chip = NULL;
+		if (test_bit(FLAG_REQUESTED, &desc->flags))
+			requested = true;
 	}
-	for (id = 0; id < chip->ngpio; id++)
-		chip->desc[id].chip = NULL;
-
 	list_del(&chip->list);
 	spin_unlock_irqrestore(&gpio_lock, flags);
 
+	if (requested)
+		dev_crit(chip->dev, "REMOVING GPIOCHIP WITH GPIOS STILL REQUESTED\n");
+
 	kfree(chip->desc);
 	chip->desc = NULL;
 }
@@ -441,6 +445,8 @@ void gpiochip_set_chained_irqchip(struct gpio_chip *gpiochip,
 		 */
 		irq_set_handler_data(parent_irq, gpiochip);
 		irq_set_chained_handler(parent_irq, parent_handler);
+
+		gpiochip->irq_parent = parent_irq;
 	}
 
 	/* Set the parent IRQ for all affected IRQs */
@@ -549,6 +555,11 @@ static void gpiochip_irqchip_remove(struct gpio_chip *gpiochip)
 
 	acpi_gpiochip_free_interrupts(gpiochip);
 
+	if (gpiochip->irq_parent) {
+		irq_set_chained_handler(gpiochip->irq_parent, NULL);
+		irq_set_handler_data(gpiochip->irq_parent, NULL);
+	}
+
 	/* Remove all IRQ mappings and delete the domain */
 	if (gpiochip->irqdomain) {
 		for (offset = 0; offset < gpiochip->ngpio; offset++)
@@ -608,7 +619,7 @@ int gpiochip_irqchip_add(struct gpio_chip *gpiochip,
 	of_node = gpiochip->dev->of_node;
 #ifdef CONFIG_OF_GPIO
 	/*
-	 * If the gpiochip has an assigned OF node this takes precendence
+	 * If the gpiochip has an assigned OF node this takes precedence
 	 * FIXME: get rid of this and use gpiochip->dev->of_node everywhere
 	 */
 	if (gpiochip->of_node)
@@ -1211,7 +1222,7 @@ EXPORT_SYMBOL_GPL(gpiod_get_value);
 /*
  *  _gpio_set_open_drain_value() - Set the open drain gpio's value.
  * @desc: gpio descriptor whose state need to be set.
- * @value: Non-zero for setting it HIGH otherise it will set to LOW.
+ * @value: Non-zero for setting it HIGH otherwise it will set to LOW.
  */
 static void _gpio_set_open_drain_value(struct gpio_desc *desc, bool value)
 {
@@ -1238,7 +1249,7 @@ static void _gpio_set_open_drain_value(struct gpio_desc *desc, bool value)
 /*
  *  _gpio_set_open_source_value() - Set the open source gpio's value.
  * @desc: gpio descriptor whose state need to be set.
- * @value: Non-zero for setting it HIGH otherise it will set to LOW.
+ * @value: Non-zero for setting it HIGH otherwise it will set to LOW.
  */
 static void _gpio_set_open_source_value(struct gpio_desc *desc, bool value)
 {
@@ -1300,17 +1311,16 @@ static void gpio_chip_set_multiple(struct gpio_chip *chip,
 				continue;
 			}
 			/* set outputs if the corresponding mask bit is set */
-			if (__test_and_clear_bit(i, mask)) {
+			if (__test_and_clear_bit(i, mask))
 				chip->set(chip, i, test_bit(i, bits));
-			}
 		}
 	}
 }
 
-static void gpiod_set_array_priv(bool raw, bool can_sleep,
-				 unsigned int array_size,
-				 struct gpio_desc **desc_array,
-				 int *value_array)
+static void gpiod_set_array_value_priv(bool raw, bool can_sleep,
+				       unsigned int array_size,
+				       struct gpio_desc **desc_array,
+				       int *value_array)
 {
 	int i = 0;
 
@@ -1320,9 +1330,9 @@ static void gpiod_set_array_priv(bool raw, bool can_sleep,
 		unsigned long bits[BITS_TO_LONGS(chip->ngpio)];
 		int count = 0;
 
-		if (!can_sleep) {
+		if (!can_sleep)
 			WARN_ON(chip->can_sleep);
-		}
+
 		memset(mask, 0, sizeof(mask));
 		do {
 			struct gpio_desc *desc = desc_array[i];
@@ -1337,24 +1347,22 @@ static void gpiod_set_array_priv(bool raw, bool can_sleep,
 			 * open drain and open source outputs are set individually
 			 */
 			if (test_bit(FLAG_OPEN_DRAIN, &desc->flags)) {
-				_gpio_set_open_drain_value(desc,value);
+				_gpio_set_open_drain_value(desc, value);
 			} else if (test_bit(FLAG_OPEN_SOURCE, &desc->flags)) {
 				_gpio_set_open_source_value(desc, value);
 			} else {
 				__set_bit(hwgpio, mask);
-				if (value) {
+				if (value)
 					__set_bit(hwgpio, bits);
-				} else {
+				else
 					__clear_bit(hwgpio, bits);
-				}
 				count++;
 			}
 			i++;
 		} while ((i < array_size) && (desc_array[i]->chip == chip));
 		/* push collected bits to outputs */
-		if (count != 0) {
+		if (count != 0)
 			gpio_chip_set_multiple(chip, mask, bits);
-		}
 	}
 }
 
@@ -1403,7 +1411,7 @@ void gpiod_set_value(struct gpio_desc *desc, int value)
 EXPORT_SYMBOL_GPL(gpiod_set_value);
 
 /**
- * gpiod_set_raw_array() - assign values to an array of GPIOs
+ * gpiod_set_raw_array_value() - assign values to an array of GPIOs
  * @array_size: number of elements in the descriptor / value arrays
  * @desc_array: array of GPIO descriptors whose values will be assigned
  * @value_array: array of values to assign
@@ -1414,17 +1422,18 @@ EXPORT_SYMBOL_GPL(gpiod_set_value);
  * This function should be called from contexts where we cannot sleep, and will
  * complain if the GPIO chip functions potentially sleep.
  */
-void gpiod_set_raw_array(unsigned int array_size,
+void gpiod_set_raw_array_value(unsigned int array_size,
 			 struct gpio_desc **desc_array, int *value_array)
 {
 	if (!desc_array)
 		return;
-	gpiod_set_array_priv(true, false, array_size, desc_array, value_array);
+	gpiod_set_array_value_priv(true, false, array_size, desc_array,
+				   value_array);
 }
-EXPORT_SYMBOL_GPL(gpiod_set_raw_array);
+EXPORT_SYMBOL_GPL(gpiod_set_raw_array_value);
 
 /**
- * gpiod_set_array() - assign values to an array of GPIOs
+ * gpiod_set_array_value() - assign values to an array of GPIOs
  * @array_size: number of elements in the descriptor / value arrays
  * @desc_array: array of GPIO descriptors whose values will be assigned
  * @value_array: array of values to assign
@@ -1435,14 +1444,15 @@ EXPORT_SYMBOL_GPL(gpiod_set_raw_array);
  * This function should be called from contexts where we cannot sleep, and will
  * complain if the GPIO chip functions potentially sleep.
  */
-void gpiod_set_array(unsigned int array_size,
-		     struct gpio_desc **desc_array, int *value_array)
+void gpiod_set_array_value(unsigned int array_size,
+			   struct gpio_desc **desc_array, int *value_array)
 {
 	if (!desc_array)
 		return;
-	gpiod_set_array_priv(false, false, array_size, desc_array, value_array);
+	gpiod_set_array_value_priv(false, false, array_size, desc_array,
+				   value_array);
 }
-EXPORT_SYMBOL_GPL(gpiod_set_array);
+EXPORT_SYMBOL_GPL(gpiod_set_array_value);
 
 /**
  * gpiod_cansleep() - report whether gpio value access may sleep
@@ -1604,7 +1614,7 @@ void gpiod_set_value_cansleep(struct gpio_desc *desc, int value)
 EXPORT_SYMBOL_GPL(gpiod_set_value_cansleep);
 
 /**
- * gpiod_set_raw_array_cansleep() - assign values to an array of GPIOs
+ * gpiod_set_raw_array_value_cansleep() - assign values to an array of GPIOs
  * @array_size: number of elements in the descriptor / value arrays
  * @desc_array: array of GPIO descriptors whose values will be assigned
  * @value_array: array of values to assign
@@ -1614,19 +1624,20 @@ EXPORT_SYMBOL_GPL(gpiod_set_value_cansleep);
  *
  * This function is to be called from contexts that can sleep.
  */
-void gpiod_set_raw_array_cansleep(unsigned int array_size,
-				  struct gpio_desc **desc_array,
-				  int *value_array)
+void gpiod_set_raw_array_value_cansleep(unsigned int array_size,
+					struct gpio_desc **desc_array,
+					int *value_array)
 {
 	might_sleep_if(extra_checks);
 	if (!desc_array)
 		return;
-	gpiod_set_array_priv(true, true, array_size, desc_array, value_array);
+	gpiod_set_array_value_priv(true, true, array_size, desc_array,
+				   value_array);
 }
-EXPORT_SYMBOL_GPL(gpiod_set_raw_array_cansleep);
+EXPORT_SYMBOL_GPL(gpiod_set_raw_array_value_cansleep);
 
 /**
- * gpiod_set_array_cansleep() - assign values to an array of GPIOs
+ * gpiod_set_array_value_cansleep() - assign values to an array of GPIOs
  * @array_size: number of elements in the descriptor / value arrays
  * @desc_array: array of GPIO descriptors whose values will be assigned
  * @value_array: array of values to assign
@@ -1636,16 +1647,17 @@ EXPORT_SYMBOL_GPL(gpiod_set_raw_array_cansleep);
  *
  * This function is to be called from contexts that can sleep.
  */
-void gpiod_set_array_cansleep(unsigned int array_size,
-			      struct gpio_desc **desc_array,
-			      int *value_array)
+void gpiod_set_array_value_cansleep(unsigned int array_size,
+				    struct gpio_desc **desc_array,
+				    int *value_array)
 {
 	might_sleep_if(extra_checks);
 	if (!desc_array)
 		return;
-	gpiod_set_array_priv(false, true, array_size, desc_array, value_array);
+	gpiod_set_array_value_priv(false, true, array_size, desc_array,
+				   value_array);
 }
-EXPORT_SYMBOL_GPL(gpiod_set_array_cansleep);
+EXPORT_SYMBOL_GPL(gpiod_set_array_value_cansleep);
 
 /**
  * gpiod_add_lookup_table() - register GPIO device consumers
@@ -1880,7 +1892,7 @@ EXPORT_SYMBOL_GPL(gpiod_count);
  *
  * Return the GPIO descriptor corresponding to the function con_id of device
  * dev, -ENOENT if no GPIO has been assigned to the requested function, or
- * another IS_ERR() code if an error occured while trying to acquire the GPIO.
+ * another IS_ERR() code if an error occurred while trying to acquire the GPIO.
  */
 struct gpio_desc *__must_check __gpiod_get(struct device *dev, const char *con_id,
 					 enum gpiod_flags flags)
@@ -1960,7 +1972,7 @@ static int gpiod_configure_flags(struct gpio_desc *desc, const char *con_id,
  *
  * Return a valid GPIO descriptor, -ENOENT if no GPIO has been assigned to the
  * requested function and/or index, or another IS_ERR() code if an error
- * occured while trying to acquire the GPIO.
+ * occurred while trying to acquire the GPIO.
  */
 struct gpio_desc *__must_check __gpiod_get_index(struct device *dev,
 					       const char *con_id,
@@ -2118,13 +2130,15 @@ int gpiod_hog(struct gpio_desc *desc, const char *name,
 
 	local_desc = gpiochip_request_own_desc(chip, hwnum, name);
 	if (IS_ERR(local_desc)) {
-		pr_debug("requesting own GPIO %s failed\n", name);
+		pr_err("requesting hog GPIO %s (chip %s, offset %d) failed\n",
+		       name, chip->label, hwnum);
 		return PTR_ERR(local_desc);
 	}
 
 	status = gpiod_configure_flags(desc, name, lflags, dflags);
 	if (status < 0) {
-		pr_debug("setup of GPIO %s failed\n", name);
+		pr_err("setup of hog GPIO %s (chip %s, offset %d) failed\n",
+		       name, chip->label, hwnum);
 		gpiochip_free_own_desc(desc);
 		return status;
 	}
diff --git a/drivers/gpio/gpiolib.h b/drivers/gpio/gpiolib.h
index 594b1798c0e7..bf343004b008 100644
--- a/drivers/gpio/gpiolib.h
+++ b/drivers/gpio/gpiolib.h
@@ -83,20 +83,12 @@ struct gpio_desc {
 #define FLAG_IS_OUT	1
 #define FLAG_EXPORT	2	/* protected by sysfs_lock */
 #define FLAG_SYSFS	3	/* exported via /sys/class/gpio/control */
-#define FLAG_TRIG_FALL	4	/* trigger on falling edge */
-#define FLAG_TRIG_RISE	5	/* trigger on rising edge */
 #define FLAG_ACTIVE_LOW	6	/* value has active low */
 #define FLAG_OPEN_DRAIN	7	/* Gpio is open drain type */
 #define FLAG_OPEN_SOURCE 8	/* Gpio is open source type */
 #define FLAG_USED_AS_IRQ 9	/* GPIO is connected to an IRQ */
-#define FLAG_SYSFS_DIR	10	/* show sysfs direction attribute */
 #define FLAG_IS_HOGGED	11	/* GPIO is hogged */
 
-#define ID_SHIFT	16	/* add new flags before this one */
-
-#define GPIO_FLAGS_MASK		((1 << ID_SHIFT) - 1)
-#define GPIO_TRIGGER_MASK	(BIT(FLAG_TRIG_FALL) | BIT(FLAG_TRIG_RISE))
-
 	const char		*label;
 };
 
@@ -151,17 +143,17 @@ static int __maybe_unused gpio_chip_hwgpio(const struct gpio_desc *desc)
 
 #ifdef CONFIG_GPIO_SYSFS
 
-int gpiochip_export(struct gpio_chip *chip);
-void gpiochip_unexport(struct gpio_chip *chip);
+int gpiochip_sysfs_register(struct gpio_chip *chip);
+void gpiochip_sysfs_unregister(struct gpio_chip *chip);
 
 #else
 
-static inline int gpiochip_export(struct gpio_chip *chip)
+static inline int gpiochip_sysfs_register(struct gpio_chip *chip)
 {
 	return 0;
 }
 
-static inline void gpiochip_unexport(struct gpio_chip *chip)
+static inline void gpiochip_sysfs_unregister(struct gpio_chip *chip)
 {
 }
 
diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c
index 266dcd6cdf3b..0a957828b3bd 100644
--- a/drivers/gpu/drm/drm_ioctl.c
+++ b/drivers/gpu/drm/drm_ioctl.c
@@ -36,9 +36,6 @@
 
 #include <linux/pci.h>
 #include <linux/export.h>
-#ifdef CONFIG_X86
-#include <asm/mtrr.h>
-#endif
 
 static int drm_version(struct drm_device *dev, void *data,
 		       struct drm_file *file_priv);
@@ -197,16 +194,7 @@ static int drm_getmap(struct drm_device *dev, void *data,
 	map->type = r_list->map->type;
 	map->flags = r_list->map->flags;
 	map->handle = (void *)(unsigned long) r_list->user_token;
-
-#ifdef CONFIG_X86
-	/*
-	 * There appears to be exactly one user of the mtrr index: dritest.
-	 * It's easy enough to keep it working on non-PAT systems.
-	 */
-	map->mtrr = phys_wc_to_mtrr_index(r_list->map->mtrr);
-#else
-	map->mtrr = -1;
-#endif
+	map->mtrr = arch_phys_wc_index(r_list->map->mtrr);
 
 	mutex_unlock(&dev->struct_mutex);
 
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 851b585987f9..2d0995e7afc3 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2656,6 +2656,9 @@ void i915_gem_reset(struct drm_device *dev)
 void
 i915_gem_retire_requests_ring(struct intel_engine_cs *ring)
 {
+	if (list_empty(&ring->request_list))
+		return;
+
 	WARN_ON(i915_verify_lists(ring->dev));
 
 	/* Retire requests first as we use it above for the early return.
@@ -3000,8 +3003,8 @@ int i915_vma_unbind(struct i915_vma *vma)
 		} else if (vma->ggtt_view.pages) {
 			sg_free_table(vma->ggtt_view.pages);
 			kfree(vma->ggtt_view.pages);
-			vma->ggtt_view.pages = NULL;
 		}
+		vma->ggtt_view.pages = NULL;
 	}
 
 	drm_mm_remove_node(&vma->node);
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index a3190e793ed4..cc552a4c1f3b 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -32,6 +32,7 @@
 #include "i915_trace.h"
 #include "intel_drv.h"
 #include <linux/dma_remapping.h>
+#include <linux/uaccess.h>
 
 #define  __EXEC_OBJECT_HAS_PIN (1<<31)
 #define  __EXEC_OBJECT_HAS_FENCE (1<<30)
@@ -465,7 +466,7 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj,
 	}
 
 	/* We can't wait for rendering with pagefaults disabled */
-	if (obj->active && in_atomic())
+	if (obj->active && pagefault_disabled())
 		return -EFAULT;
 
 	if (use_cpu_reloc(obj))
diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c
index 6e84df9369a6..ad4b9010dfb0 100644
--- a/drivers/gpu/drm/mgag200/mgag200_mode.c
+++ b/drivers/gpu/drm/mgag200/mgag200_mode.c
@@ -1526,6 +1526,11 @@ static int mga_vga_mode_valid(struct drm_connector *connector,
 		return MODE_BANDWIDTH;
 	}
 
+	if ((mode->hdisplay % 8) != 0 || (mode->hsync_start % 8) != 0 ||
+	    (mode->hsync_end % 8) != 0 || (mode->htotal % 8) != 0) {
+		return MODE_H_ILLEGAL;
+	}
+
 	if (mode->crtc_hdisplay > 2048 || mode->crtc_hsync_start > 4096 ||
 	    mode->crtc_hsync_end > 4096 || mode->crtc_htotal > 4096 ||
 	    mode->crtc_vdisplay > 2048 || mode->crtc_vsync_start > 4096 ||
diff --git a/drivers/gpu/drm/radeon/atombios.h b/drivers/gpu/drm/radeon/atombios.h
index 92be50c39ffd..ab89eed9ddd9 100644
--- a/drivers/gpu/drm/radeon/atombios.h
+++ b/drivers/gpu/drm/radeon/atombios.h
@@ -7944,8 +7944,8 @@ typedef struct {
 typedef struct {
   AMD_ACPI_DESCRIPTION_HEADER SHeader;
   UCHAR TableUUID[16];    //0x24
-  ULONG VBIOSImageOffset; //0x34. Offset to the first GOP_VBIOS_CONTENT block from the beginning of the stucture.
-  ULONG Lib1ImageOffset;  //0x38. Offset to the first GOP_LIB1_CONTENT block from the beginning of the stucture.
+  ULONG VBIOSImageOffset; //0x34. Offset to the first GOP_VBIOS_CONTENT block from the beginning of the structure.
+  ULONG Lib1ImageOffset;  //0x38. Offset to the first GOP_LIB1_CONTENT block from the beginning of the structure.
   ULONG Reserved[4];      //0x3C
 }UEFI_ACPI_VFCT;
 
diff --git a/drivers/gpu/drm/radeon/radeon_dp_mst.c b/drivers/gpu/drm/radeon/radeon_dp_mst.c
index 2b98ed3e684d..257b10be5cda 100644
--- a/drivers/gpu/drm/radeon/radeon_dp_mst.c
+++ b/drivers/gpu/drm/radeon/radeon_dp_mst.c
@@ -663,12 +663,17 @@ int
 radeon_dp_mst_probe(struct radeon_connector *radeon_connector)
 {
 	struct radeon_connector_atom_dig *dig_connector = radeon_connector->con_priv;
+	struct drm_device *dev = radeon_connector->base.dev;
+	struct radeon_device *rdev = dev->dev_private;
 	int ret;
 	u8 msg[1];
 
 	if (!radeon_mst)
 		return 0;
 
+	if (!ASIC_IS_DCE5(rdev))
+		return 0;
+
 	if (dig_connector->dpcd[DP_DPCD_REV] < 0x12)
 		return 0;
 
diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c
index 7b2a7335cc5d..b0acf50d9558 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_kms.c
@@ -576,6 +576,9 @@ static int radeon_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 		if (radeon_get_allowed_info_register(rdev, *value, value))
 			return -EINVAL;
 		break;
+	case RADEON_INFO_VA_UNMAP_WORKING:
+		*value = true;
+		break;
 	default:
 		DRM_DEBUG_KMS("Invalid request %d\n", info->request);
 		return -EINVAL;
diff --git a/drivers/gpu/ipu-v3/ipu-common.c b/drivers/gpu/ipu-v3/ipu-common.c
index 67bab5c36056..6d2f39d36e44 100644
--- a/drivers/gpu/ipu-v3/ipu-common.c
+++ b/drivers/gpu/ipu-v3/ipu-common.c
@@ -1119,10 +1119,9 @@ static int ipu_irq_init(struct ipu_soc *ipu)
 		ct->regs.mask = IPU_INT_CTRL(i / 32);
 	}
 
-	irq_set_chained_handler(ipu->irq_sync, ipu_irq_handler);
-	irq_set_handler_data(ipu->irq_sync, ipu);
-	irq_set_chained_handler(ipu->irq_err, ipu_err_irq_handler);
-	irq_set_handler_data(ipu->irq_err, ipu);
+	irq_set_chained_handler_and_data(ipu->irq_sync, ipu_irq_handler, ipu);
+	irq_set_chained_handler_and_data(ipu->irq_err, ipu_err_irq_handler,
+					 ipu);
 
 	return 0;
 }
@@ -1131,10 +1130,8 @@ static void ipu_irq_exit(struct ipu_soc *ipu)
 {
 	int i, irq;
 
-	irq_set_chained_handler(ipu->irq_err, NULL);
-	irq_set_handler_data(ipu->irq_err, NULL);
-	irq_set_chained_handler(ipu->irq_sync, NULL);
-	irq_set_handler_data(ipu->irq_sync, NULL);
+	irq_set_chained_handler_and_data(ipu->irq_err, NULL, NULL);
+	irq_set_chained_handler_and_data(ipu->irq_sync, NULL, NULL);
 
 	/* TODO: remove irq_domain_generic_chips */
 
diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig
index 15338afdf7f9..cc4c6649d195 100644
--- a/drivers/hid/Kconfig
+++ b/drivers/hid/Kconfig
@@ -634,7 +634,12 @@ config HID_PLANTRONICS
 	tristate "Plantronics USB HID Driver"
 	depends on HID
 	---help---
-	Provides HID support for Plantronics telephony devices.
+	  Provides HID support for Plantronics USB audio devices.
+	  Correctly maps vendor unique volume up/down HID usages to
+	  KEY_VOLUMEUP and KEY_VOLUMEDOWN events and prevents core mapping
+	  of other vendor unique HID usages to random mouse events.
+
+	  Say M here if you may ever plug in a Plantronics USB audio device.
 
 config HID_PRIMAX
 	tristate "Primax non-fully HID-compliant devices"
diff --git a/drivers/hid/Makefile b/drivers/hid/Makefile
index e4a21dfd7ef3..2f8a41dc3cc8 100644
--- a/drivers/hid/Makefile
+++ b/drivers/hid/Makefile
@@ -24,7 +24,7 @@ obj-$(CONFIG_HID_A4TECH)	+= hid-a4tech.o
 obj-$(CONFIG_HID_ACRUX)		+= hid-axff.o
 obj-$(CONFIG_HID_APPLE)		+= hid-apple.o
 obj-$(CONFIG_HID_APPLEIR)	+= hid-appleir.o
-obj-$(CONFIG_HID_AUREAL)        += hid-aureal.o
+obj-$(CONFIG_HID_AUREAL)	+= hid-aureal.o
 obj-$(CONFIG_HID_BELKIN)	+= hid-belkin.o
 obj-$(CONFIG_HID_BETOP_FF)	+= hid-betopff.o
 obj-$(CONFIG_HID_CHERRY)	+= hid-cherry.o
@@ -46,12 +46,12 @@ obj-$(CONFIG_HID_ICADE)		+= hid-icade.o
 obj-$(CONFIG_HID_KENSINGTON)	+= hid-kensington.o
 obj-$(CONFIG_HID_KEYTOUCH)	+= hid-keytouch.o
 obj-$(CONFIG_HID_KYE)		+= hid-kye.o
-obj-$(CONFIG_HID_LCPOWER)       += hid-lcpower.o
+obj-$(CONFIG_HID_LCPOWER)	+= hid-lcpower.o
 obj-$(CONFIG_HID_LENOVO)	+= hid-lenovo.o
 obj-$(CONFIG_HID_LOGITECH)	+= hid-logitech.o
 obj-$(CONFIG_HID_LOGITECH_DJ)	+= hid-logitech-dj.o
 obj-$(CONFIG_HID_LOGITECH_HIDPP)	+= hid-logitech-hidpp.o
-obj-$(CONFIG_HID_MAGICMOUSE)    += hid-magicmouse.o
+obj-$(CONFIG_HID_MAGICMOUSE)	+= hid-magicmouse.o
 obj-$(CONFIG_HID_MICROSOFT)	+= hid-microsoft.o
 obj-$(CONFIG_HID_MONTEREY)	+= hid-monterey.o
 obj-$(CONFIG_HID_MULTITOUCH)	+= hid-multitouch.o
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index 722a925795a2..157c62775053 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -706,7 +706,8 @@ static void hid_scan_collection(struct hid_parser *parser, unsigned type)
 
 	if (hid->vendor == USB_VENDOR_ID_MICROSOFT &&
 	    (hid->product == USB_DEVICE_ID_MS_TYPE_COVER_3 ||
-	     hid->product == USB_DEVICE_ID_MS_TYPE_COVER_3_JP) &&
+	     hid->product == USB_DEVICE_ID_MS_TYPE_COVER_3_JP ||
+	     hid->product == USB_DEVICE_ID_MS_POWER_COVER) &&
 	    hid->group == HID_GROUP_MULTITOUCH)
 		hid->group = HID_GROUP_GENERIC;
 
@@ -1061,13 +1062,13 @@ static u32 s32ton(__s32 value, unsigned n)
  * Search linux-kernel and linux-usb-devel archives for "hid-core extract".
  */
 
-static __u32 extract(const struct hid_device *hid, __u8 *report,
+__u32 hid_field_extract(const struct hid_device *hid, __u8 *report,
 		     unsigned offset, unsigned n)
 {
 	u64 x;
 
 	if (n > 32)
-		hid_warn(hid, "extract() called with n (%d) > 32! (%s)\n",
+		hid_warn(hid, "hid_field_extract() called with n (%d) > 32! (%s)\n",
 			 n, current->comm);
 
 	report += offset >> 3;  /* adjust byte index */
@@ -1076,6 +1077,7 @@ static __u32 extract(const struct hid_device *hid, __u8 *report,
 	x = (x >> offset) & ((1ULL << n) - 1);  /* extract bit field */
 	return (u32) x;
 }
+EXPORT_SYMBOL_GPL(hid_field_extract);
 
 /*
  * "implement" : set bits in a little endian bit stream.
@@ -1221,9 +1223,9 @@ static void hid_input_field(struct hid_device *hid, struct hid_field *field,
 	for (n = 0; n < count; n++) {
 
 		value[n] = min < 0 ?
-			snto32(extract(hid, data, offset + n * size, size),
-			       size) :
-			extract(hid, data, offset + n * size, size);
+			snto32(hid_field_extract(hid, data, offset + n * size,
+			       size), size) :
+			hid_field_extract(hid, data, offset + n * size, size);
 
 		/* Ignore report if ErrorRollOver */
 		if (!(field->flags & HID_MAIN_ITEM_VARIABLE) &&
@@ -1851,6 +1853,7 @@ static const struct hid_device_id hid_have_special_driver[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_TPKBD) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_CUSBKBD) },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_CBTKBD) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_TPPRODOCK) },
 #endif
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_MX3000_RECEIVER) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_S510_RECEIVER) },
@@ -1901,6 +1904,7 @@ static const struct hid_device_id hid_have_special_driver[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_OFFICE_KB) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_3) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_3_JP) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_POWER_COVER) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MONTEREY, USB_DEVICE_ID_GENIUS_KB29E) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MSI, USB_DEVICE_ID_MSI_GT683R_LED_PANEL) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_NTRIG, USB_DEVICE_ID_NTRIG_TOUCH_SCREEN) },
@@ -1959,9 +1963,12 @@ static const struct hid_device_id hid_have_special_driver[] = {
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_SMK, USB_DEVICE_ID_SMK_PS3_BDREMOTE) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_BUZZ_CONTROLLER) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_WIRELESS_BUZZ_CONTROLLER) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_MOTION_CONTROLLER) },
+	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_MOTION_CONTROLLER) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_NAVIGATION_CONTROLLER) },
+	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_NAVIGATION_CONTROLLER) },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_PS3_BDREMOTE) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_PS3_CONTROLLER) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_NAVIGATION_CONTROLLER) },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_PS3_CONTROLLER) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_PS4_CONTROLLER) },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_PS4_CONTROLLER) },
@@ -1997,6 +2004,7 @@ static const struct hid_device_id hid_have_special_driver[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_WISEGROUP_LTD, USB_DEVICE_ID_SUPER_JOY_BOX_3_PRO) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_WISEGROUP_LTD, USB_DEVICE_ID_SUPER_DUAL_BOX_PRO) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_WISEGROUP_LTD, USB_DEVICE_ID_SUPER_JOY_BOX_5_PRO) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_PLAYDOTCOM, USB_DEVICE_ID_PLAYDOTCOM_EMS_USBII) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_WALTOP, USB_DEVICE_ID_WALTOP_SLIM_TABLET_5_8_INCH) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_WALTOP, USB_DEVICE_ID_WALTOP_SLIM_TABLET_12_1_INCH) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_WALTOP, USB_DEVICE_ID_WALTOP_Q_PAD) },
@@ -2265,14 +2273,6 @@ static const struct hid_device_id hid_ignore_list[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_GENERAL_TOUCH, 0x0001) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_GENERAL_TOUCH, 0x0002) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_GENERAL_TOUCH, 0x0004) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_GLAB, USB_DEVICE_ID_4_PHIDGETSERVO_30) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_GLAB, USB_DEVICE_ID_1_PHIDGETSERVO_30) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_GLAB, USB_DEVICE_ID_0_0_4_IF_KIT) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_GLAB, USB_DEVICE_ID_0_16_16_IF_KIT) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_GLAB, USB_DEVICE_ID_8_8_8_IF_KIT) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_GLAB, USB_DEVICE_ID_0_8_7_IF_KIT) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_GLAB, USB_DEVICE_ID_0_8_8_IF_KIT) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_GLAB, USB_DEVICE_ID_PHIDGET_MOTORCONTROL) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_GOTOP, USB_DEVICE_ID_SUPER_Q2) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_GOTOP, USB_DEVICE_ID_GOGOPEN) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_GOTOP, USB_DEVICE_ID_PENPOWER) },
@@ -2399,14 +2399,6 @@ static const struct hid_device_id hid_ignore_list[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_WTP) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_DPAD) },
 #endif
-	{ HID_USB_DEVICE(USB_VENDOR_ID_VERNIER, USB_DEVICE_ID_VERNIER_LABPRO) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_VERNIER, USB_DEVICE_ID_VERNIER_GOTEMP) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_VERNIER, USB_DEVICE_ID_VERNIER_SKIP) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_VERNIER, USB_DEVICE_ID_VERNIER_CYCLOPS) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_VERNIER, USB_DEVICE_ID_VERNIER_LCSPEC) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_WISEGROUP, USB_DEVICE_ID_4_PHIDGETSERVO_20) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_WISEGROUP, USB_DEVICE_ID_1_PHIDGETSERVO_20) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_WISEGROUP, USB_DEVICE_ID_8_8_4_IF_KIT) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_YEALINK, USB_DEVICE_ID_YEALINK_P1K_P4K_B2K) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_RISO_KAGAKU, USB_DEVICE_ID_RI_KA_WEBMAIL) },
 	{ }
diff --git a/drivers/hid/hid-cypress.c b/drivers/hid/hid-cypress.c
index c4ef3bc726e3..1b764d1745f3 100644
--- a/drivers/hid/hid-cypress.c
+++ b/drivers/hid/hid-cypress.c
@@ -41,13 +41,9 @@ static __u8 *cp_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 
 	for (i = 0; i < *rsize - 4; i++)
 		if (rdesc[i] == 0x29 && rdesc[i + 2] == 0x19) {
-			__u8 tmp;
-
 			rdesc[i] = 0x19;
 			rdesc[i + 2] = 0x29;
-			tmp = rdesc[i + 3];
-			rdesc[i + 3] = rdesc[i + 1];
-			rdesc[i + 1] = tmp;
+			swap(rdesc[i + 3], rdesc[i + 1]);
 		}
 	return rdesc;
 }
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 7ce93d927f62..b04b0820d816 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -227,6 +227,7 @@
 #define USB_DEVICE_ID_CHICONY_TACTICAL_PAD	0x0418
 #define USB_DEVICE_ID_CHICONY_MULTI_TOUCH	0xb19d
 #define USB_DEVICE_ID_CHICONY_WIRELESS	0x0618
+#define USB_DEVICE_ID_CHICONY_PIXART_USB_OPTICAL_MOUSE	0x1053
 #define USB_DEVICE_ID_CHICONY_WIRELESS2	0x1123
 #define USB_DEVICE_ID_CHICONY_AK1D	0x1125
 
@@ -363,16 +364,6 @@
 #define USB_DEVICE_ID_GENERAL_TOUCH_WIN8_PIT_010A 0x010a
 #define USB_DEVICE_ID_GENERAL_TOUCH_WIN8_PIT_E100 0xe100
 
-#define USB_VENDOR_ID_GLAB		0x06c2
-#define USB_DEVICE_ID_4_PHIDGETSERVO_30	0x0038
-#define USB_DEVICE_ID_1_PHIDGETSERVO_30	0x0039
-#define USB_DEVICE_ID_0_0_4_IF_KIT	0x0040
-#define USB_DEVICE_ID_0_16_16_IF_KIT	0x0044
-#define USB_DEVICE_ID_8_8_8_IF_KIT	0x0045
-#define USB_DEVICE_ID_0_8_7_IF_KIT	0x0051
-#define USB_DEVICE_ID_0_8_8_IF_KIT	0x0053
-#define USB_DEVICE_ID_PHIDGET_MOTORCONTROL	0x0058
-
 #define USB_VENDOR_ID_GOODTOUCH		0x1aad
 #define USB_DEVICE_ID_GOODTOUCH_000f	0x000f
 
@@ -586,6 +577,7 @@
 #define USB_DEVICE_ID_LENOVO_TPKBD	0x6009
 #define USB_DEVICE_ID_LENOVO_CUSBKBD	0x6047
 #define USB_DEVICE_ID_LENOVO_CBTKBD	0x6048
+#define USB_DEVICE_ID_LENOVO_TPPRODOCK	0x6067
 
 #define USB_VENDOR_ID_LG		0x1fd2
 #define USB_DEVICE_ID_LG_MULTITOUCH	0x0064
@@ -673,6 +665,7 @@
 #define USB_DEVICE_ID_MS_TYPE_COVER_2    0x07a9
 #define USB_DEVICE_ID_MS_TYPE_COVER_3    0x07dc
 #define USB_DEVICE_ID_MS_TYPE_COVER_3_JP 0x07dd
+#define USB_DEVICE_ID_MS_POWER_COVER     0x07da
 
 #define USB_VENDOR_ID_MOJO		0x8282
 #define USB_DEVICE_ID_RETRO_ADAPTER	0x3201
@@ -852,6 +845,7 @@
 #define USB_DEVICE_ID_SONY_PS3_BDREMOTE		0x0306
 #define USB_DEVICE_ID_SONY_PS3_CONTROLLER	0x0268
 #define USB_DEVICE_ID_SONY_PS4_CONTROLLER	0x05c4
+#define USB_DEVICE_ID_SONY_MOTION_CONTROLLER	0x03d5
 #define USB_DEVICE_ID_SONY_NAVIGATION_CONTROLLER	0x042f
 #define USB_DEVICE_ID_SONY_BUZZ_CONTROLLER		0x0002
 #define USB_DEVICE_ID_SONY_WIRELESS_BUZZ_CONTROLLER	0x1000
@@ -958,13 +952,6 @@
 #define USB_DEVICE_ID_VELLEMAN_K8061_FIRST	0x8061
 #define USB_DEVICE_ID_VELLEMAN_K8061_LAST	0x8068
 
-#define USB_VENDOR_ID_VERNIER		0x08f7
-#define USB_DEVICE_ID_VERNIER_LABPRO	0x0001
-#define USB_DEVICE_ID_VERNIER_GOTEMP	0x0002
-#define USB_DEVICE_ID_VERNIER_SKIP	0x0003
-#define USB_DEVICE_ID_VERNIER_CYCLOPS	0x0004
-#define USB_DEVICE_ID_VERNIER_LCSPEC	0x0006
-
 #define USB_VENDOR_ID_VTL		0x0306
 #define USB_DEVICE_ID_VTL_MULTITOUCH_FF3F	0xff3f
 
@@ -983,9 +970,6 @@
 
 #define USB_VENDOR_ID_WISEGROUP		0x0925
 #define USB_DEVICE_ID_SMARTJOY_PLUS	0x0005
-#define USB_DEVICE_ID_1_PHIDGETSERVO_20	0x8101
-#define USB_DEVICE_ID_4_PHIDGETSERVO_20	0x8104
-#define USB_DEVICE_ID_8_8_4_IF_KIT	0x8201
 #define USB_DEVICE_ID_SUPER_JOY_BOX_3	0x8888
 #define USB_DEVICE_ID_QUAD_USB_JOYPAD	0x8800
 #define USB_DEVICE_ID_DUAL_USB_JOYPAD	0x8866
@@ -1039,4 +1023,11 @@
 #define USB_VENDOR_ID_RISO_KAGAKU	0x1294	/* Riso Kagaku Corp. */
 #define USB_DEVICE_ID_RI_KA_WEBMAIL	0x1320	/* Webmail Notifier */
 
+#define USB_VENDOR_ID_MULTIPLE_1781	0x1781
+#define USB_DEVICE_ID_RAPHNET_4NES4SNES_OLD	0x0a8d
+
+#define USB_VENDOR_ID_DRACAL_RAPHNET	0x289b
+#define USB_DEVICE_ID_RAPHNET_2NES2SNES	0x0002
+#define USB_DEVICE_ID_RAPHNET_4NES4SNES	0x0003
+
 #endif
diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c
index 008e89bf6f3c..3511bbaba505 100644
--- a/drivers/hid/hid-input.c
+++ b/drivers/hid/hid-input.c
@@ -1157,7 +1157,8 @@ void hidinput_hid_event(struct hid_device *hid, struct hid_field *field, struct
 		return;
 
 	/* report the usage code as scancode if the key status has changed */
-	if (usage->type == EV_KEY && !!test_bit(usage->code, input->key) != value)
+	if (usage->type == EV_KEY &&
+	    (!test_bit(usage->code, input->key)) == value)
 		input_event(input, EV_MSC, MSC_SCAN, usage->hid);
 
 	input_event(input, usage->type, usage->code, value);
diff --git a/drivers/hid/hid-lenovo.c b/drivers/hid/hid-lenovo.c
index c4c3f0952521..4f59bffd0205 100644
--- a/drivers/hid/hid-lenovo.c
+++ b/drivers/hid/hid-lenovo.c
@@ -43,6 +43,35 @@ struct lenovo_drvdata_cptkbd {
 
 #define map_key_clear(c) hid_map_usage_clear(hi, usage, bit, max, EV_KEY, (c))
 
+static const __u8 lenovo_pro_dock_need_fixup_collection[] = {
+	0x05, 0x88,		/* Usage Page (Vendor Usage Page 0x88)	*/
+	0x09, 0x01,		/* Usage (Vendor Usage 0x01)		*/
+	0xa1, 0x01,		/* Collection (Application)		*/
+	0x85, 0x04,		/*  Report ID (4)			*/
+	0x19, 0x00,		/*  Usage Minimum (0)			*/
+	0x2a, 0xff, 0xff,	/*  Usage Maximum (65535)		*/
+};
+
+static __u8 *lenovo_report_fixup(struct hid_device *hdev, __u8 *rdesc,
+		unsigned int *rsize)
+{
+	switch (hdev->product) {
+	case USB_DEVICE_ID_LENOVO_TPPRODOCK:
+		/* the fixups that need to be done:
+		 *   - get a reasonable usage max for the vendor collection
+		 *     0x8801 from the report ID 4
+		 */
+		if (*rsize >= 153 &&
+		    memcmp(&rdesc[140], lenovo_pro_dock_need_fixup_collection,
+			  sizeof(lenovo_pro_dock_need_fixup_collection)) == 0) {
+			rdesc[151] = 0x01;
+			rdesc[152] = 0x00;
+		}
+		break;
+	}
+	return rdesc;
+}
+
 static int lenovo_input_mapping_tpkbd(struct hid_device *hdev,
 		struct hid_input *hi, struct hid_field *field,
 		struct hid_usage *usage, unsigned long **bit, int *max)
@@ -599,7 +628,8 @@ static int lenovo_probe_tpkbd(struct hid_device *hdev)
 				    GFP_KERNEL);
 	if (data_pointer == NULL) {
 		hid_err(hdev, "Could not allocate memory for driver data\n");
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto err;
 	}
 
 	// set same default values as windows driver
@@ -610,7 +640,8 @@ static int lenovo_probe_tpkbd(struct hid_device *hdev)
 	name_micmute = devm_kzalloc(&hdev->dev, name_sz, GFP_KERNEL);
 	if (name_mute == NULL || name_micmute == NULL) {
 		hid_err(hdev, "Could not allocate memory for led data\n");
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto err;
 	}
 	snprintf(name_mute, name_sz, "%s:amber:mute", dev_name(dev));
 	snprintf(name_micmute, name_sz, "%s:amber:micmute", dev_name(dev));
@@ -634,6 +665,9 @@ static int lenovo_probe_tpkbd(struct hid_device *hdev)
 	lenovo_features_set_tpkbd(hdev);
 
 	return 0;
+err:
+	sysfs_remove_group(&hdev->dev.kobj, &lenovo_attr_group_tpkbd);
+	return ret;
 }
 
 static int lenovo_probe_cptkbd(struct hid_device *hdev)
@@ -762,10 +796,29 @@ static void lenovo_remove(struct hid_device *hdev)
 	hid_hw_stop(hdev);
 }
 
+static void lenovo_input_configured(struct hid_device *hdev,
+		struct hid_input *hi)
+{
+	switch (hdev->product) {
+		case USB_DEVICE_ID_LENOVO_TPKBD:
+		case USB_DEVICE_ID_LENOVO_CUSBKBD:
+		case USB_DEVICE_ID_LENOVO_CBTKBD:
+			if (test_bit(EV_REL, hi->input->evbit)) {
+				/* set only for trackpoint device */
+				__set_bit(INPUT_PROP_POINTER, hi->input->propbit);
+				__set_bit(INPUT_PROP_POINTING_STICK,
+						hi->input->propbit);
+			}
+			break;
+	}
+}
+
+
 static const struct hid_device_id lenovo_devices[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_TPKBD) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_CUSBKBD) },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_CBTKBD) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_TPPRODOCK) },
 	{ }
 };
 
@@ -774,10 +827,12 @@ MODULE_DEVICE_TABLE(hid, lenovo_devices);
 static struct hid_driver lenovo_driver = {
 	.name = "lenovo",
 	.id_table = lenovo_devices,
+	.input_configured = lenovo_input_configured,
 	.input_mapping = lenovo_input_mapping,
 	.probe = lenovo_probe,
 	.remove = lenovo_remove,
 	.raw_event = lenovo_raw_event,
+	.report_fixup = lenovo_report_fixup,
 };
 module_hid_driver(lenovo_driver);
 
diff --git a/drivers/hid/hid-lg.c b/drivers/hid/hid-lg.c
index b86c18e651ed..429340d809b5 100644
--- a/drivers/hid/hid-lg.c
+++ b/drivers/hid/hid-lg.c
@@ -700,7 +700,8 @@ static int lg_probe(struct hid_device *hdev, const struct hid_device_id *id)
 			/* insert a little delay of 10 jiffies ~ 40ms */
 			wait_queue_head_t wait;
 			init_waitqueue_head (&wait);
-			wait_event_interruptible_timeout(wait, 0, 10);
+			wait_event_interruptible_timeout(wait, 0,
+							 msecs_to_jiffies(40));
 
 			/* Select random Address */
 			buf[1] = 0xB2;
@@ -712,13 +713,16 @@ static int lg_probe(struct hid_device *hdev, const struct hid_device_id *id)
 	}
 
 	if (drv_data->quirks & LG_FF)
-		lgff_init(hdev);
-	if (drv_data->quirks & LG_FF2)
-		lg2ff_init(hdev);
-	if (drv_data->quirks & LG_FF3)
-		lg3ff_init(hdev);
-	if (drv_data->quirks & LG_FF4)
-		lg4ff_init(hdev);
+		ret = lgff_init(hdev);
+	else if (drv_data->quirks & LG_FF2)
+		ret = lg2ff_init(hdev);
+	else if (drv_data->quirks & LG_FF3)
+		ret = lg3ff_init(hdev);
+	else if (drv_data->quirks & LG_FF4)
+		ret = lg4ff_init(hdev);
+
+	if (ret)
+		goto err_free;
 
 	return 0;
 err_free:
@@ -731,8 +735,8 @@ static void lg_remove(struct hid_device *hdev)
 	struct lg_drv_data *drv_data = hid_get_drvdata(hdev);
 	if (drv_data->quirks & LG_FF4)
 		lg4ff_deinit(hdev);
-
-	hid_hw_stop(hdev);
+	else
+		hid_hw_stop(hdev);
 	kfree(drv_data);
 }
 
diff --git a/drivers/hid/hid-lg4ff.c b/drivers/hid/hid-lg4ff.c
index 1232210b1cc5..02cec83caac3 100644
--- a/drivers/hid/hid-lg4ff.c
+++ b/drivers/hid/hid-lg4ff.c
@@ -68,26 +68,32 @@
 #define LG4FF_FFEX_REV_MAJ 0x21
 #define LG4FF_FFEX_REV_MIN 0x00
 
-static void hid_lg4ff_set_range_dfp(struct hid_device *hid, u16 range);
-static void hid_lg4ff_set_range_g25(struct hid_device *hid, u16 range);
-
-struct lg4ff_device_entry {
-	__u32 product_id;
-	__u16 range;
-	__u16 min_range;
-	__u16 max_range;
+static void lg4ff_set_range_dfp(struct hid_device *hid, u16 range);
+static void lg4ff_set_range_g25(struct hid_device *hid, u16 range);
+
+struct lg4ff_wheel_data {
+	const u32 product_id;
+	u16 range;
+	const u16 min_range;
+	const u16 max_range;
 #ifdef CONFIG_LEDS_CLASS
-	__u8  led_state;
+	u8  led_state;
 	struct led_classdev *led[5];
 #endif
-	u32 alternate_modes;
-	const char *real_tag;
-	const char *real_name;
-	u16 real_product_id;
-	struct list_head list;
+	const u32 alternate_modes;
+	const char * const real_tag;
+	const char * const real_name;
+	const u16 real_product_id;
+
 	void (*set_range)(struct hid_device *hid, u16 range);
 };
 
+struct lg4ff_device_entry {
+	spinlock_t report_lock; /* Protect output HID report */
+	struct hid_report *report;
+	struct lg4ff_wheel_data wdata;
+};
+
 static const signed short lg4ff_wheel_effects[] = {
 	FF_CONSTANT,
 	FF_AUTOCENTER,
@@ -95,16 +101,16 @@ static const signed short lg4ff_wheel_effects[] = {
 };
 
 struct lg4ff_wheel {
-	const __u32 product_id;
+	const u32 product_id;
 	const signed short *ff_effects;
-	const __u16 min_range;
-	const __u16 max_range;
+	const u16 min_range;
+	const u16 max_range;
 	void (*set_range)(struct hid_device *hid, u16 range);
 };
 
 struct lg4ff_compat_mode_switch {
-	const __u8 cmd_count;	/* Number of commands to send */
-	const __u8 cmd[];
+	const u8 cmd_count;	/* Number of commands to send */
+	const u8 cmd[];
 };
 
 struct lg4ff_wheel_ident_info {
@@ -134,10 +140,10 @@ struct lg4ff_alternate_mode {
 static const struct lg4ff_wheel lg4ff_devices[] = {
 	{USB_DEVICE_ID_LOGITECH_WHEEL,       lg4ff_wheel_effects, 40, 270, NULL},
 	{USB_DEVICE_ID_LOGITECH_MOMO_WHEEL,  lg4ff_wheel_effects, 40, 270, NULL},
-	{USB_DEVICE_ID_LOGITECH_DFP_WHEEL,   lg4ff_wheel_effects, 40, 900, hid_lg4ff_set_range_dfp},
-	{USB_DEVICE_ID_LOGITECH_G25_WHEEL,   lg4ff_wheel_effects, 40, 900, hid_lg4ff_set_range_g25},
-	{USB_DEVICE_ID_LOGITECH_DFGT_WHEEL,  lg4ff_wheel_effects, 40, 900, hid_lg4ff_set_range_g25},
-	{USB_DEVICE_ID_LOGITECH_G27_WHEEL,   lg4ff_wheel_effects, 40, 900, hid_lg4ff_set_range_g25},
+	{USB_DEVICE_ID_LOGITECH_DFP_WHEEL,   lg4ff_wheel_effects, 40, 900, lg4ff_set_range_dfp},
+	{USB_DEVICE_ID_LOGITECH_G25_WHEEL,   lg4ff_wheel_effects, 40, 900, lg4ff_set_range_g25},
+	{USB_DEVICE_ID_LOGITECH_DFGT_WHEEL,  lg4ff_wheel_effects, 40, 900, lg4ff_set_range_g25},
+	{USB_DEVICE_ID_LOGITECH_G27_WHEEL,   lg4ff_wheel_effects, 40, 900, lg4ff_set_range_g25},
 	{USB_DEVICE_ID_LOGITECH_MOMO_WHEEL2, lg4ff_wheel_effects, 40, 270, NULL},
 	{USB_DEVICE_ID_LOGITECH_WII_WHEEL,   lg4ff_wheel_effects, 40, 270, NULL}
 };
@@ -245,10 +251,10 @@ static const struct lg4ff_compat_mode_switch lg4ff_mode_switch_ext16_g25 = {
 };
 
 /* Recalculates X axis value accordingly to currently selected range */
-static __s32 lg4ff_adjust_dfp_x_axis(__s32 value, __u16 range)
+static s32 lg4ff_adjust_dfp_x_axis(s32 value, u16 range)
 {
-	__u16 max_range;
-	__s32 new_value;
+	u16 max_range;
+	s32 new_value;
 
 	if (range == 900)
 		return value;
@@ -269,21 +275,21 @@ static __s32 lg4ff_adjust_dfp_x_axis(__s32 value, __u16 range)
 }
 
 int lg4ff_adjust_input_event(struct hid_device *hid, struct hid_field *field,
-			     struct hid_usage *usage, __s32 value, struct lg_drv_data *drv_data)
+			     struct hid_usage *usage, s32 value, struct lg_drv_data *drv_data)
 {
 	struct lg4ff_device_entry *entry = drv_data->device_props;
-	__s32 new_value = 0;
+	s32 new_value = 0;
 
 	if (!entry) {
 		hid_err(hid, "Device properties not found");
 		return 0;
 	}
 
-	switch (entry->product_id) {
+	switch (entry->wdata.product_id) {
 	case USB_DEVICE_ID_LOGITECH_DFP_WHEEL:
 		switch (usage->code) {
 		case ABS_X:
-			new_value = lg4ff_adjust_dfp_x_axis(value, entry->range);
+			new_value = lg4ff_adjust_dfp_x_axis(value, entry->wdata.range);
 			input_event(field->hidinput->input, usage->type, usage->code, new_value);
 			return 1;
 		default:
@@ -294,14 +300,56 @@ int lg4ff_adjust_input_event(struct hid_device *hid, struct hid_field *field,
 	}
 }
 
-static int hid_lg4ff_play(struct input_dev *dev, void *data, struct ff_effect *effect)
+static void lg4ff_init_wheel_data(struct lg4ff_wheel_data * const wdata, const struct lg4ff_wheel *wheel,
+				  const struct lg4ff_multimode_wheel *mmode_wheel,
+				  const u16 real_product_id)
+{
+	u32 alternate_modes = 0;
+	const char *real_tag = NULL;
+	const char *real_name = NULL;
+
+	if (mmode_wheel) {
+		alternate_modes = mmode_wheel->alternate_modes;
+		real_tag = mmode_wheel->real_tag;
+		real_name = mmode_wheel->real_name;
+	}
+
+	{
+		struct lg4ff_wheel_data t_wdata =  { .product_id = wheel->product_id,
+						     .real_product_id = real_product_id,
+						     .min_range = wheel->min_range,
+						     .max_range = wheel->max_range,
+						     .set_range = wheel->set_range,
+						     .alternate_modes = alternate_modes,
+						     .real_tag = real_tag,
+						     .real_name = real_name };
+
+		memcpy(wdata, &t_wdata, sizeof(t_wdata));
+	}
+}
+
+static int lg4ff_play(struct input_dev *dev, void *data, struct ff_effect *effect)
 {
 	struct hid_device *hid = input_get_drvdata(dev);
-	struct list_head *report_list = &hid->report_enum[HID_OUTPUT_REPORT].report_list;
-	struct hid_report *report = list_entry(report_list->next, struct hid_report, list);
-	__s32 *value = report->field[0]->value;
+	struct lg4ff_device_entry *entry;
+	struct lg_drv_data *drv_data;
+	unsigned long flags;
+	s32 *value;
 	int x;
 
+	drv_data = hid_get_drvdata(hid);
+	if (!drv_data) {
+		hid_err(hid, "Private driver data not found!\n");
+		return -EINVAL;
+	}
+
+	entry = drv_data->device_props;
+	if (!entry) {
+		hid_err(hid, "Device properties not found!\n");
+		return -EINVAL;
+	}
+	value = entry->report->field[0]->value;
+
 #define CLAMP(x) do { if (x < 0) x = 0; else if (x > 0xff) x = 0xff; } while (0)
 
 	switch (effect->type) {
@@ -309,6 +357,7 @@ static int hid_lg4ff_play(struct input_dev *dev, void *data, struct ff_effect *e
 		x = effect->u.ramp.start_level + 0x80;	/* 0x80 is no force */
 		CLAMP(x);
 
+		spin_lock_irqsave(&entry->report_lock, flags);
 		if (x == 0x80) {
 			/* De-activate force in slot-1*/
 			value[0] = 0x13;
@@ -319,7 +368,8 @@ static int hid_lg4ff_play(struct input_dev *dev, void *data, struct ff_effect *e
 			value[5] = 0x00;
 			value[6] = 0x00;
 
-			hid_hw_request(hid, report, HID_REQ_SET_REPORT);
+			hid_hw_request(hid, entry->report, HID_REQ_SET_REPORT);
+			spin_unlock_irqrestore(&entry->report_lock, flags);
 			return 0;
 		}
 
@@ -331,7 +381,8 @@ static int hid_lg4ff_play(struct input_dev *dev, void *data, struct ff_effect *e
 		value[5] = 0x00;
 		value[6] = 0x00;
 
-		hid_hw_request(hid, report, HID_REQ_SET_REPORT);
+		hid_hw_request(hid, entry->report, HID_REQ_SET_REPORT);
+		spin_unlock_irqrestore(&entry->report_lock, flags);
 		break;
 	}
 	return 0;
@@ -339,15 +390,16 @@ static int hid_lg4ff_play(struct input_dev *dev, void *data, struct ff_effect *e
 
 /* Sends default autocentering command compatible with
  * all wheels except Formula Force EX */
-static void hid_lg4ff_set_autocenter_default(struct input_dev *dev, u16 magnitude)
+static void lg4ff_set_autocenter_default(struct input_dev *dev, u16 magnitude)
 {
 	struct hid_device *hid = input_get_drvdata(dev);
 	struct list_head *report_list = &hid->report_enum[HID_OUTPUT_REPORT].report_list;
 	struct hid_report *report = list_entry(report_list->next, struct hid_report, list);
-	__s32 *value = report->field[0]->value;
-	__u32 expand_a, expand_b;
+	s32 *value = report->field[0]->value;
+	u32 expand_a, expand_b;
 	struct lg4ff_device_entry *entry;
 	struct lg_drv_data *drv_data;
+	unsigned long flags;
 
 	drv_data = hid_get_drvdata(hid);
 	if (!drv_data) {
@@ -360,8 +412,10 @@ static void hid_lg4ff_set_autocenter_default(struct input_dev *dev, u16 magnitud
 		hid_err(hid, "Device properties not found!\n");
 		return;
 	}
+	value = entry->report->field[0]->value;
 
 	/* De-activate Auto-Center */
+	spin_lock_irqsave(&entry->report_lock, flags);
 	if (magnitude == 0) {
 		value[0] = 0xf5;
 		value[1] = 0x00;
@@ -371,7 +425,8 @@ static void hid_lg4ff_set_autocenter_default(struct input_dev *dev, u16 magnitud
 		value[5] = 0x00;
 		value[6] = 0x00;
 
-		hid_hw_request(hid, report, HID_REQ_SET_REPORT);
+		hid_hw_request(hid, entry->report, HID_REQ_SET_REPORT);
+		spin_unlock_irqrestore(&entry->report_lock, flags);
 		return;
 	}
 
@@ -384,7 +439,7 @@ static void hid_lg4ff_set_autocenter_default(struct input_dev *dev, u16 magnitud
 	}
 
 	/* Adjust for non-MOMO wheels */
-	switch (entry->product_id) {
+	switch (entry->wdata.product_id) {
 	case USB_DEVICE_ID_LOGITECH_MOMO_WHEEL:
 	case USB_DEVICE_ID_LOGITECH_MOMO_WHEEL2:
 		break;
@@ -401,7 +456,7 @@ static void hid_lg4ff_set_autocenter_default(struct input_dev *dev, u16 magnitud
 	value[5] = 0x00;
 	value[6] = 0x00;
 
-	hid_hw_request(hid, report, HID_REQ_SET_REPORT);
+	hid_hw_request(hid, entry->report, HID_REQ_SET_REPORT);
 
 	/* Activate Auto-Center */
 	value[0] = 0x14;
@@ -412,18 +467,34 @@ static void hid_lg4ff_set_autocenter_default(struct input_dev *dev, u16 magnitud
 	value[5] = 0x00;
 	value[6] = 0x00;
 
-	hid_hw_request(hid, report, HID_REQ_SET_REPORT);
+	hid_hw_request(hid, entry->report, HID_REQ_SET_REPORT);
+	spin_unlock_irqrestore(&entry->report_lock, flags);
 }
 
 /* Sends autocentering command compatible with Formula Force EX */
-static void hid_lg4ff_set_autocenter_ffex(struct input_dev *dev, u16 magnitude)
+static void lg4ff_set_autocenter_ffex(struct input_dev *dev, u16 magnitude)
 {
 	struct hid_device *hid = input_get_drvdata(dev);
-	struct list_head *report_list = &hid->report_enum[HID_OUTPUT_REPORT].report_list;
-	struct hid_report *report = list_entry(report_list->next, struct hid_report, list);
-	__s32 *value = report->field[0]->value;
+	struct lg4ff_device_entry *entry;
+	struct lg_drv_data *drv_data;
+	unsigned long flags;
+	s32 *value;
 	magnitude = magnitude * 90 / 65535;
 
+	drv_data = hid_get_drvdata(hid);
+	if (!drv_data) {
+		hid_err(hid, "Private driver data not found!\n");
+		return;
+	}
+
+	entry = drv_data->device_props;
+	if (!entry) {
+		hid_err(hid, "Device properties not found!\n");
+		return;
+	}
+	value = entry->report->field[0]->value;
+
+	spin_lock_irqsave(&entry->report_lock, flags);
 	value[0] = 0xfe;
 	value[1] = 0x03;
 	value[2] = magnitude >> 14;
@@ -432,18 +503,33 @@ static void hid_lg4ff_set_autocenter_ffex(struct input_dev *dev, u16 magnitude)
 	value[5] = 0x00;
 	value[6] = 0x00;
 
-	hid_hw_request(hid, report, HID_REQ_SET_REPORT);
+	hid_hw_request(hid, entry->report, HID_REQ_SET_REPORT);
+	spin_unlock_irqrestore(&entry->report_lock, flags);
 }
 
 /* Sends command to set range compatible with G25/G27/Driving Force GT */
-static void hid_lg4ff_set_range_g25(struct hid_device *hid, u16 range)
+static void lg4ff_set_range_g25(struct hid_device *hid, u16 range)
 {
-	struct list_head *report_list = &hid->report_enum[HID_OUTPUT_REPORT].report_list;
-	struct hid_report *report = list_entry(report_list->next, struct hid_report, list);
-	__s32 *value = report->field[0]->value;
+	struct lg4ff_device_entry *entry;
+	struct lg_drv_data *drv_data;
+	unsigned long flags;
+	s32 *value;
 
+	drv_data = hid_get_drvdata(hid);
+	if (!drv_data) {
+		hid_err(hid, "Private driver data not found!\n");
+		return;
+	}
+
+	entry = drv_data->device_props;
+	if (!entry) {
+		hid_err(hid, "Device properties not found!\n");
+		return;
+	}
+	value = entry->report->field[0]->value;
 	dbg_hid("G25/G27/DFGT: setting range to %u\n", range);
 
+	spin_lock_irqsave(&entry->report_lock, flags);
 	value[0] = 0xf8;
 	value[1] = 0x81;
 	value[2] = range & 0x00ff;
@@ -452,20 +538,35 @@ static void hid_lg4ff_set_range_g25(struct hid_device *hid, u16 range)
 	value[5] = 0x00;
 	value[6] = 0x00;
 
-	hid_hw_request(hid, report, HID_REQ_SET_REPORT);
+	hid_hw_request(hid, entry->report, HID_REQ_SET_REPORT);
+	spin_unlock_irqrestore(&entry->report_lock, flags);
 }
 
 /* Sends commands to set range compatible with Driving Force Pro wheel */
-static void hid_lg4ff_set_range_dfp(struct hid_device *hid, __u16 range)
+static void lg4ff_set_range_dfp(struct hid_device *hid, u16 range)
 {
-	struct list_head *report_list = &hid->report_enum[HID_OUTPUT_REPORT].report_list;
-	struct hid_report *report = list_entry(report_list->next, struct hid_report, list);
+	struct lg4ff_device_entry *entry;
+	struct lg_drv_data *drv_data;
+	unsigned long flags;
 	int start_left, start_right, full_range;
-	__s32 *value = report->field[0]->value;
+	s32 *value;
+
+	drv_data = hid_get_drvdata(hid);
+	if (!drv_data) {
+		hid_err(hid, "Private driver data not found!\n");
+		return;
+	}
 
+	entry = drv_data->device_props;
+	if (!entry) {
+		hid_err(hid, "Device properties not found!\n");
+		return;
+	}
+	value = entry->report->field[0]->value;
 	dbg_hid("Driving Force Pro: setting range to %u\n", range);
 
 	/* Prepare "coarse" limit command */
+	spin_lock_irqsave(&entry->report_lock, flags);
 	value[0] = 0xf8;
 	value[1] = 0x00;	/* Set later */
 	value[2] = 0x00;
@@ -475,13 +576,13 @@ static void hid_lg4ff_set_range_dfp(struct hid_device *hid, __u16 range)
 	value[6] = 0x00;
 
 	if (range > 200) {
-		report->field[0]->value[1] = 0x03;
+		value[1] = 0x03;
 		full_range = 900;
 	} else {
-		report->field[0]->value[1] = 0x02;
+		value[1] = 0x02;
 		full_range = 200;
 	}
-	hid_hw_request(hid, report, HID_REQ_SET_REPORT);
+	hid_hw_request(hid, entry->report, HID_REQ_SET_REPORT);
 
 	/* Prepare "fine" limit command */
 	value[0] = 0x81;
@@ -493,7 +594,8 @@ static void hid_lg4ff_set_range_dfp(struct hid_device *hid, __u16 range)
 	value[6] = 0x00;
 
 	if (range == 200 || range == 900) {	/* Do not apply any fine limit */
-		hid_hw_request(hid, report, HID_REQ_SET_REPORT);
+		hid_hw_request(hid, entry->report, HID_REQ_SET_REPORT);
+		spin_unlock_irqrestore(&entry->report_lock, flags);
 		return;
 	}
 
@@ -507,7 +609,8 @@ static void hid_lg4ff_set_range_dfp(struct hid_device *hid, __u16 range)
 	value[5] = (start_right & 0xe) << 4 | (start_left & 0xe);
 	value[6] = 0xff;
 
-	hid_hw_request(hid, report, HID_REQ_SET_REPORT);
+	hid_hw_request(hid, entry->report, HID_REQ_SET_REPORT);
+	spin_unlock_irqrestore(&entry->report_lock, flags);
 }
 
 static const struct lg4ff_compat_mode_switch *lg4ff_get_mode_switch_command(const u16 real_product_id, const u16 target_product_id)
@@ -569,19 +672,35 @@ static const struct lg4ff_compat_mode_switch *lg4ff_get_mode_switch_command(cons
 
 static int lg4ff_switch_compatibility_mode(struct hid_device *hid, const struct lg4ff_compat_mode_switch *s)
 {
-	struct list_head *report_list = &hid->report_enum[HID_OUTPUT_REPORT].report_list;
-	struct hid_report *report = list_entry(report_list->next, struct hid_report, list);
-	__s32 *value = report->field[0]->value;
+	struct lg4ff_device_entry *entry;
+	struct lg_drv_data *drv_data;
+	unsigned long flags;
+	s32 *value;
 	u8 i;
 
+	drv_data = hid_get_drvdata(hid);
+	if (!drv_data) {
+		hid_err(hid, "Private driver data not found!\n");
+		return -EINVAL;
+	}
+
+	entry = drv_data->device_props;
+	if (!entry) {
+		hid_err(hid, "Device properties not found!\n");
+		return -EINVAL;
+	}
+	value = entry->report->field[0]->value;
+
+	spin_lock_irqsave(&entry->report_lock, flags);
 	for (i = 0; i < s->cmd_count; i++) {
 		u8 j;
 
 		for (j = 0; j < 7; j++)
 			value[j] = s->cmd[j + (7*i)];
 
-		hid_hw_request(hid, report, HID_REQ_SET_REPORT);
+		hid_hw_request(hid, entry->report, HID_REQ_SET_REPORT);
 	}
+	spin_unlock_irqrestore(&entry->report_lock, flags);
 	hid_hw_wait(hid);
 	return 0;
 }
@@ -606,23 +725,23 @@ static ssize_t lg4ff_alternate_modes_show(struct device *dev, struct device_attr
 		return 0;
 	}
 
-	if (!entry->real_name) {
+	if (!entry->wdata.real_name) {
 		hid_err(hid, "NULL pointer to string\n");
 		return 0;
 	}
 
 	for (i = 0; i < LG4FF_MODE_MAX_IDX; i++) {
-		if (entry->alternate_modes & BIT(i)) {
+		if (entry->wdata.alternate_modes & BIT(i)) {
 			/* Print tag and full name */
 			count += scnprintf(buf + count, PAGE_SIZE - count, "%s: %s",
 					   lg4ff_alternate_modes[i].tag,
-					   !lg4ff_alternate_modes[i].product_id ? entry->real_name : lg4ff_alternate_modes[i].name);
+					   !lg4ff_alternate_modes[i].product_id ? entry->wdata.real_name : lg4ff_alternate_modes[i].name);
 			if (count >= PAGE_SIZE - 1)
 				return count;
 
 			/* Mark the currently active mode with an asterisk */
-			if (lg4ff_alternate_modes[i].product_id == entry->product_id ||
-			    (lg4ff_alternate_modes[i].product_id == 0 && entry->product_id == entry->real_product_id))
+			if (lg4ff_alternate_modes[i].product_id == entry->wdata.product_id ||
+			    (lg4ff_alternate_modes[i].product_id == 0 && entry->wdata.product_id == entry->wdata.real_product_id))
 				count += scnprintf(buf + count, PAGE_SIZE - count, " *\n");
 			else
 				count += scnprintf(buf + count, PAGE_SIZE - count, "\n");
@@ -675,10 +794,10 @@ static ssize_t lg4ff_alternate_modes_store(struct device *dev, struct device_att
 		const u16 mode_product_id = lg4ff_alternate_modes[i].product_id;
 		const char *tag = lg4ff_alternate_modes[i].tag;
 
-		if (entry->alternate_modes & BIT(i)) {
+		if (entry->wdata.alternate_modes & BIT(i)) {
 			if (!strcmp(tag, lbuf)) {
 				if (!mode_product_id)
-					target_product_id = entry->real_product_id;
+					target_product_id = entry->wdata.real_product_id;
 				else
 					target_product_id = mode_product_id;
 				break;
@@ -693,24 +812,24 @@ static ssize_t lg4ff_alternate_modes_store(struct device *dev, struct device_att
 	}
 	kfree(lbuf); /* Not needed anymore */
 
-	if (target_product_id == entry->product_id) /* Nothing to do */
+	if (target_product_id == entry->wdata.product_id) /* Nothing to do */
 		return count;
 
 	/* Automatic switching has to be disabled for the switch to DF-EX mode to work correctly */
 	if (target_product_id == USB_DEVICE_ID_LOGITECH_WHEEL && !lg4ff_no_autoswitch) {
 		hid_info(hid, "\"%s\" cannot be switched to \"DF-EX\" mode. Load the \"hid_logitech\" module with \"lg4ff_no_autoswitch=1\" parameter set and try again\n",
-			 entry->real_name);
+			 entry->wdata.real_name);
 		return -EINVAL;
 	}
 
 	/* Take care of hardware limitations */
-	if ((entry->real_product_id == USB_DEVICE_ID_LOGITECH_DFP_WHEEL || entry->real_product_id == USB_DEVICE_ID_LOGITECH_G25_WHEEL) &&
-	    entry->product_id > target_product_id) {
-		hid_info(hid, "\"%s\" cannot be switched back into \"%s\" mode\n", entry->real_name, lg4ff_alternate_modes[i].name);
+	if ((entry->wdata.real_product_id == USB_DEVICE_ID_LOGITECH_DFP_WHEEL || entry->wdata.real_product_id == USB_DEVICE_ID_LOGITECH_G25_WHEEL) &&
+	    entry->wdata.product_id > target_product_id) {
+		hid_info(hid, "\"%s\" cannot be switched back into \"%s\" mode\n", entry->wdata.real_name, lg4ff_alternate_modes[i].name);
 		return -EINVAL;
 	}
 
-	s = lg4ff_get_mode_switch_command(entry->real_product_id, target_product_id);
+	s = lg4ff_get_mode_switch_command(entry->wdata.real_product_id, target_product_id);
 	if (!s) {
 		hid_err(hid, "Invalid target product ID %X\n", target_product_id);
 		return -EINVAL;
@@ -721,9 +840,9 @@ static ssize_t lg4ff_alternate_modes_store(struct device *dev, struct device_att
 }
 static DEVICE_ATTR(alternate_modes, S_IRUSR | S_IWUSR | S_IRGRP | S_IWGRP | S_IROTH, lg4ff_alternate_modes_show, lg4ff_alternate_modes_store);
 
-/* Read current range and display it in terminal */
-static ssize_t range_show(struct device *dev, struct device_attribute *attr,
-			  char *buf)
+/* Export the currently set range of the wheel */
+static ssize_t lg4ff_range_show(struct device *dev, struct device_attribute *attr,
+				char *buf)
 {
 	struct hid_device *hid = to_hid_device(dev);
 	struct lg4ff_device_entry *entry;
@@ -742,19 +861,19 @@ static ssize_t range_show(struct device *dev, struct device_attribute *attr,
 		return 0;
 	}
 
-	count = scnprintf(buf, PAGE_SIZE, "%u\n", entry->range);
+	count = scnprintf(buf, PAGE_SIZE, "%u\n", entry->wdata.range);
 	return count;
 }
 
 /* Set range to user specified value, call appropriate function
  * according to the type of the wheel */
-static ssize_t range_store(struct device *dev, struct device_attribute *attr,
-			   const char *buf, size_t count)
+static ssize_t lg4ff_range_store(struct device *dev, struct device_attribute *attr,
+				 const char *buf, size_t count)
 {
 	struct hid_device *hid = to_hid_device(dev);
 	struct lg4ff_device_entry *entry;
 	struct lg_drv_data *drv_data;
-	__u16 range = simple_strtoul(buf, NULL, 10);
+	u16 range = simple_strtoul(buf, NULL, 10);
 
 	drv_data = hid_get_drvdata(hid);
 	if (!drv_data) {
@@ -769,18 +888,18 @@ static ssize_t range_store(struct device *dev, struct device_attribute *attr,
 	}
 
 	if (range == 0)
-		range = entry->max_range;
+		range = entry->wdata.max_range;
 
 	/* Check if the wheel supports range setting
 	 * and that the range is within limits for the wheel */
-	if (entry->set_range != NULL && range >= entry->min_range && range <= entry->max_range) {
-		entry->set_range(hid, range);
-		entry->range = range;
+	if (entry->wdata.set_range && range >= entry->wdata.min_range && range <= entry->wdata.max_range) {
+		entry->wdata.set_range(hid, range);
+		entry->wdata.range = range;
 	}
 
 	return count;
 }
-static DEVICE_ATTR_RW(range);
+static DEVICE_ATTR(range, S_IRUSR | S_IWUSR | S_IRGRP | S_IWGRP | S_IROTH, lg4ff_range_show, lg4ff_range_store);
 
 static ssize_t lg4ff_real_id_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
@@ -801,12 +920,12 @@ static ssize_t lg4ff_real_id_show(struct device *dev, struct device_attribute *a
 		return 0;
 	}
 
-	if (!entry->real_tag || !entry->real_name) {
+	if (!entry->wdata.real_tag || !entry->wdata.real_name) {
 		hid_err(hid, "NULL pointer to string\n");
 		return 0;
 	}
 
-	count = scnprintf(buf, PAGE_SIZE, "%s: %s\n", entry->real_tag, entry->real_name);
+	count = scnprintf(buf, PAGE_SIZE, "%s: %s\n", entry->wdata.real_tag, entry->wdata.real_name);
 	return count;
 }
 
@@ -818,12 +937,27 @@ static ssize_t lg4ff_real_id_store(struct device *dev, struct device_attribute *
 static DEVICE_ATTR(real_id, S_IRUGO, lg4ff_real_id_show, lg4ff_real_id_store);
 
 #ifdef CONFIG_LEDS_CLASS
-static void lg4ff_set_leds(struct hid_device *hid, __u8 leds)
+static void lg4ff_set_leds(struct hid_device *hid, u8 leds)
 {
-	struct list_head *report_list = &hid->report_enum[HID_OUTPUT_REPORT].report_list;
-	struct hid_report *report = list_entry(report_list->next, struct hid_report, list);
-	__s32 *value = report->field[0]->value;
+	struct lg_drv_data *drv_data;
+	struct lg4ff_device_entry *entry;
+	unsigned long flags;
+	s32 *value;
+
+	drv_data = hid_get_drvdata(hid);
+	if (!drv_data) {
+		hid_err(hid, "Private driver data not found!\n");
+		return;
+	}
+
+	entry = drv_data->device_props;
+	if (!entry) {
+		hid_err(hid, "Device properties not found!\n");
+		return;
+	}
+	value = entry->report->field[0]->value;
 
+	spin_lock_irqsave(&entry->report_lock, flags);
 	value[0] = 0xf8;
 	value[1] = 0x12;
 	value[2] = leds;
@@ -831,7 +965,8 @@ static void lg4ff_set_leds(struct hid_device *hid, __u8 leds)
 	value[4] = 0x00;
 	value[5] = 0x00;
 	value[6] = 0x00;
-	hid_hw_request(hid, report, HID_REQ_SET_REPORT);
+	hid_hw_request(hid, entry->report, HID_REQ_SET_REPORT);
+	spin_unlock_irqrestore(&entry->report_lock, flags);
 }
 
 static void lg4ff_led_set_brightness(struct led_classdev *led_cdev,
@@ -848,7 +983,7 @@ static void lg4ff_led_set_brightness(struct led_classdev *led_cdev,
 		return;
 	}
 
-	entry = (struct lg4ff_device_entry *)drv_data->device_props;
+	entry = drv_data->device_props;
 
 	if (!entry) {
 		hid_err(hid, "Device properties not found.");
@@ -856,15 +991,15 @@ static void lg4ff_led_set_brightness(struct led_classdev *led_cdev,
 	}
 
 	for (i = 0; i < 5; i++) {
-		if (led_cdev != entry->led[i])
+		if (led_cdev != entry->wdata.led[i])
 			continue;
-		state = (entry->led_state >> i) & 1;
+		state = (entry->wdata.led_state >> i) & 1;
 		if (value == LED_OFF && state) {
-			entry->led_state &= ~(1 << i);
-			lg4ff_set_leds(hid, entry->led_state);
+			entry->wdata.led_state &= ~(1 << i);
+			lg4ff_set_leds(hid, entry->wdata.led_state);
 		} else if (value != LED_OFF && !state) {
-			entry->led_state |= 1 << i;
-			lg4ff_set_leds(hid, entry->led_state);
+			entry->wdata.led_state |= 1 << i;
+			lg4ff_set_leds(hid, entry->wdata.led_state);
 		}
 		break;
 	}
@@ -883,7 +1018,7 @@ static enum led_brightness lg4ff_led_get_brightness(struct led_classdev *led_cde
 		return LED_OFF;
 	}
 
-	entry = (struct lg4ff_device_entry *)drv_data->device_props;
+	entry = drv_data->device_props;
 
 	if (!entry) {
 		hid_err(hid, "Device properties not found.");
@@ -891,8 +1026,8 @@ static enum led_brightness lg4ff_led_get_brightness(struct led_classdev *led_cde
 	}
 
 	for (i = 0; i < 5; i++)
-		if (led_cdev == entry->led[i]) {
-			value = (entry->led_state >> i) & 1;
+		if (led_cdev == entry->wdata.led[i]) {
+			value = (entry->wdata.led_state >> i) & 1;
 			break;
 		}
 
@@ -991,8 +1126,11 @@ int lg4ff_init(struct hid_device *hid)
 {
 	struct hid_input *hidinput = list_entry(hid->inputs.next, struct hid_input, list);
 	struct input_dev *dev = hidinput->input;
+	struct list_head *report_list = &hid->report_enum[HID_OUTPUT_REPORT].report_list;
+	struct hid_report *report = list_entry(report_list->next, struct hid_report, list);
 	const struct usb_device_descriptor *udesc = &(hid_to_usb_dev(hid)->descriptor);
 	const u16 bcdDevice = le16_to_cpu(udesc->bcdDevice);
+	const struct lg4ff_multimode_wheel *mmode_wheel = NULL;
 	struct lg4ff_device_entry *entry;
 	struct lg_drv_data *drv_data;
 	int error, i, j;
@@ -1003,6 +1141,18 @@ int lg4ff_init(struct hid_device *hid)
 	if (!hid_validate_values(hid, HID_OUTPUT_REPORT, 0, 0, 7))
 		return -1;
 
+	drv_data = hid_get_drvdata(hid);
+	if (!drv_data) {
+		hid_err(hid, "Cannot add device, private driver data not allocated\n");
+		return -1;
+	}
+	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry)
+		return -ENOMEM;
+	spin_lock_init(&entry->report_lock);
+	entry->report = report;
+	drv_data->device_props = entry;
+
 	/* Check if a multimode wheel has been connected and
 	 * handle it appropriately */
 	mmode_ret = lg4ff_handle_multimode_wheel(hid, &real_product_id, bcdDevice);
@@ -1012,6 +1162,11 @@ int lg4ff_init(struct hid_device *hid)
 	 */
 	if (mmode_ret == LG4FF_MMODE_SWITCHED)
 		return 0;
+	else if (mmode_ret < 0) {
+		hid_err(hid, "Unable to switch device mode during initialization, errno %d\n", mmode_ret);
+		error = mmode_ret;
+		goto err_init;
+	}
 
 	/* Check what wheel has been connected */
 	for (i = 0; i < ARRAY_SIZE(lg4ff_devices); i++) {
@@ -1022,9 +1177,11 @@ int lg4ff_init(struct hid_device *hid)
 	}
 
 	if (i == ARRAY_SIZE(lg4ff_devices)) {
-		hid_err(hid, "Device is not supported by lg4ff driver. If you think it should be, consider reporting a bug to"
-			     "LKML, Simon Wood <simon@mungewell.org> or Michal Maly <madcatxster@gmail.com>\n");
-		return -1;
+		hid_err(hid, "This device is flagged to be handled by the lg4ff module but this module does not know how to handle it. "
+			     "Please report this as a bug to LKML, Simon Wood <simon@mungewell.org> or "
+			     "Michal Maly <madcatxster@devoid-pointer.net>\n");
+		error = -1;
+		goto err_init;
 	}
 
 	if (mmode_ret == LG4FF_MMODE_IS_MULTIMODE) {
@@ -1035,7 +1192,8 @@ int lg4ff_init(struct hid_device *hid)
 
 		if (mmode_idx == ARRAY_SIZE(lg4ff_multimode_wheels)) {
 			hid_err(hid, "Device product ID %X is not listed as a multimode wheel", real_product_id);
-			return -1;
+			error = -1;
+			goto err_init;
 		}
 	}
 
@@ -1043,37 +1201,17 @@ int lg4ff_init(struct hid_device *hid)
 	for (j = 0; lg4ff_devices[i].ff_effects[j] >= 0; j++)
 		set_bit(lg4ff_devices[i].ff_effects[j], dev->ffbit);
 
-	error = input_ff_create_memless(dev, NULL, hid_lg4ff_play);
+	error = input_ff_create_memless(dev, NULL, lg4ff_play);
 
 	if (error)
-		return error;
-
-	/* Get private driver data */
-	drv_data = hid_get_drvdata(hid);
-	if (!drv_data) {
-		hid_err(hid, "Cannot add device, private driver data not allocated\n");
-		return -1;
-	}
+		goto err_init;
 
 	/* Initialize device properties */
-	entry = kzalloc(sizeof(struct lg4ff_device_entry), GFP_KERNEL);
-	if (!entry) {
-		hid_err(hid, "Cannot add device, insufficient memory to allocate device properties.\n");
-		return -ENOMEM;
-	}
-	drv_data->device_props = entry;
-
-	entry->product_id = lg4ff_devices[i].product_id;
-	entry->real_product_id = real_product_id;
-	entry->min_range = lg4ff_devices[i].min_range;
-	entry->max_range = lg4ff_devices[i].max_range;
-	entry->set_range = lg4ff_devices[i].set_range;
 	if (mmode_ret == LG4FF_MMODE_IS_MULTIMODE) {
 		BUG_ON(mmode_idx == -1);
-		entry->alternate_modes = lg4ff_multimode_wheels[mmode_idx].alternate_modes;
-		entry->real_tag = lg4ff_multimode_wheels[mmode_idx].real_tag;
-		entry->real_name = lg4ff_multimode_wheels[mmode_idx].real_name;
+		mmode_wheel = &lg4ff_multimode_wheels[mmode_idx];
 	}
+	lg4ff_init_wheel_data(&entry->wdata, &lg4ff_devices[i], mmode_wheel, real_product_id);
 
 	/* Check if autocentering is available and
 	 * set the centering force to zero by default */
@@ -1081,9 +1219,9 @@ int lg4ff_init(struct hid_device *hid)
 		/* Formula Force EX expects different autocentering command */
 		if ((bcdDevice >> 8) == LG4FF_FFEX_REV_MAJ &&
 		    (bcdDevice & 0xff) == LG4FF_FFEX_REV_MIN)
-			dev->ff->set_autocenter = hid_lg4ff_set_autocenter_ffex;
+			dev->ff->set_autocenter = lg4ff_set_autocenter_ffex;
 		else
-			dev->ff->set_autocenter = hid_lg4ff_set_autocenter_default;
+			dev->ff->set_autocenter = lg4ff_set_autocenter_default;
 
 		dev->ff->set_autocenter(dev, 0);
 	}
@@ -1091,27 +1229,27 @@ int lg4ff_init(struct hid_device *hid)
 	/* Create sysfs interface */
 	error = device_create_file(&hid->dev, &dev_attr_range);
 	if (error)
-		return error;
+		hid_warn(hid, "Unable to create sysfs interface for \"range\", errno %d\n", error);
 	if (mmode_ret == LG4FF_MMODE_IS_MULTIMODE) {
 		error = device_create_file(&hid->dev, &dev_attr_real_id);
 		if (error)
-			return error;
+			hid_warn(hid, "Unable to create sysfs interface for \"real_id\", errno %d\n", error);
 		error = device_create_file(&hid->dev, &dev_attr_alternate_modes);
 		if (error)
-			return error;
+			hid_warn(hid, "Unable to create sysfs interface for \"alternate_modes\", errno %d\n", error);
 	}
 	dbg_hid("sysfs interface created\n");
 
 	/* Set the maximum range to start with */
-	entry->range = entry->max_range;
-	if (entry->set_range != NULL)
-		entry->set_range(hid, entry->range);
+	entry->wdata.range = entry->wdata.max_range;
+	if (entry->wdata.set_range)
+		entry->wdata.set_range(hid, entry->wdata.range);
 
 #ifdef CONFIG_LEDS_CLASS
 	/* register led subsystem - G27 only */
-	entry->led_state = 0;
+	entry->wdata.led_state = 0;
 	for (j = 0; j < 5; j++)
-		entry->led[j] = NULL;
+		entry->wdata.led[j] = NULL;
 
 	if (lg4ff_devices[i].product_id == USB_DEVICE_ID_LOGITECH_G27_WHEEL) {
 		struct led_classdev *led;
@@ -1126,7 +1264,7 @@ int lg4ff_init(struct hid_device *hid)
 			led = kzalloc(sizeof(struct led_classdev)+name_sz, GFP_KERNEL);
 			if (!led) {
 				hid_err(hid, "can't allocate memory for LED %d\n", j);
-				goto err;
+				goto err_leds;
 			}
 
 			name = (void *)(&led[1]);
@@ -1137,16 +1275,16 @@ int lg4ff_init(struct hid_device *hid)
 			led->brightness_get = lg4ff_led_get_brightness;
 			led->brightness_set = lg4ff_led_set_brightness;
 
-			entry->led[j] = led;
+			entry->wdata.led[j] = led;
 			error = led_classdev_register(&hid->dev, led);
 
 			if (error) {
 				hid_err(hid, "failed to register LED %d. Aborting.\n", j);
-err:
+err_leds:
 				/* Deregister LEDs (if any) */
 				for (j = 0; j < 5; j++) {
-					led = entry->led[j];
-					entry->led[j] = NULL;
+					led = entry->wdata.led[j];
+					entry->wdata.led[j] = NULL;
 					if (!led)
 						continue;
 					led_classdev_unregister(led);
@@ -1160,6 +1298,11 @@ out:
 #endif
 	hid_info(hid, "Force feedback support for Logitech Gaming Wheels\n");
 	return 0;
+
+err_init:
+	drv_data->device_props = NULL;
+	kfree(entry);
+	return error;
 }
 
 int lg4ff_deinit(struct hid_device *hid)
@@ -1176,14 +1319,13 @@ int lg4ff_deinit(struct hid_device *hid)
 	if (!entry)
 		goto out; /* Nothing more to do */
 
-	device_remove_file(&hid->dev, &dev_attr_range);
-
 	/* Multimode devices will have at least the "MODE_NATIVE" bit set */
-	if (entry->alternate_modes) {
+	if (entry->wdata.alternate_modes) {
 		device_remove_file(&hid->dev, &dev_attr_real_id);
 		device_remove_file(&hid->dev, &dev_attr_alternate_modes);
 	}
 
+	device_remove_file(&hid->dev, &dev_attr_range);
 #ifdef CONFIG_LEDS_CLASS
 	{
 		int j;
@@ -1192,8 +1334,8 @@ int lg4ff_deinit(struct hid_device *hid)
 		/* Deregister LEDs (if any) */
 		for (j = 0; j < 5; j++) {
 
-			led = entry->led[j];
-			entry->led[j] = NULL;
+			led = entry->wdata.led[j];
+			entry->wdata.led[j] = NULL;
 			if (!led)
 				continue;
 			led_classdev_unregister(led);
@@ -1201,10 +1343,10 @@ int lg4ff_deinit(struct hid_device *hid)
 		}
 	}
 #endif
+	hid_hw_stop(hid);
+	drv_data->device_props = NULL;
 
-	/* Deallocate memory */
 	kfree(entry);
-
 out:
 	dbg_hid("Device successfully unregistered\n");
 	return 0;
diff --git a/drivers/hid/hid-lg4ff.h b/drivers/hid/hid-lg4ff.h
index 5b6a5086c47f..66201af44da3 100644
--- a/drivers/hid/hid-lg4ff.h
+++ b/drivers/hid/hid-lg4ff.h
@@ -5,12 +5,12 @@
 extern int lg4ff_no_autoswitch; /* From hid-lg.c */
 
 int lg4ff_adjust_input_event(struct hid_device *hid, struct hid_field *field,
-			     struct hid_usage *usage, __s32 value, struct lg_drv_data *drv_data);
+			     struct hid_usage *usage, s32 value, struct lg_drv_data *drv_data);
 int lg4ff_init(struct hid_device *hdev);
 int lg4ff_deinit(struct hid_device *hdev);
 #else
 static inline int lg4ff_adjust_input_event(struct hid_device *hid, struct hid_field *field,
-					   struct hid_usage *usage, __s32 value, struct lg_drv_data *drv_data) { return 0; }
+					   struct hid_usage *usage, s32 value, struct lg_drv_data *drv_data) { return 0; }
 static inline int lg4ff_init(struct hid_device *hdev) { return -1; }
 static inline int lg4ff_deinit(struct hid_device *hdev) { return -1; }
 #endif
diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c
index 5fd530acf747..484196459305 100644
--- a/drivers/hid/hid-logitech-hidpp.c
+++ b/drivers/hid/hid-logitech-hidpp.c
@@ -40,8 +40,9 @@ MODULE_PARM_DESC(disable_raw_mode,
 #define HIDPP_REPORT_LONG_LENGTH		20
 
 #define HIDPP_QUIRK_CLASS_WTP			BIT(0)
+#define HIDPP_QUIRK_CLASS_M560			BIT(1)
 
-/* bits 1..20 are reserved for classes */
+/* bits 2..20 are reserved for classes */
 #define HIDPP_QUIRK_DELAYED_INIT		BIT(21)
 #define HIDPP_QUIRK_WTP_PHYSICAL_BUTTONS	BIT(22)
 
@@ -930,6 +931,207 @@ static int wtp_connect(struct hid_device *hdev, bool connected)
 			true, true);
 }
 
+/* ------------------------------------------------------------------------- */
+/* Logitech M560 devices                                                     */
+/* ------------------------------------------------------------------------- */
+
+/*
+ * Logitech M560 protocol overview
+ *
+ * The Logitech M560 mouse, is designed for windows 8. When the middle and/or
+ * the sides buttons are pressed, it sends some keyboard keys events
+ * instead of buttons ones.
+ * To complicate things further, the middle button keys sequence
+ * is different from the odd press and the even press.
+ *
+ * forward button -> Super_R
+ * backward button -> Super_L+'d' (press only)
+ * middle button -> 1st time: Alt_L+SuperL+XF86TouchpadOff (press only)
+ *                  2nd time: left-click (press only)
+ * NB: press-only means that when the button is pressed, the
+ * KeyPress/ButtonPress and KeyRelease/ButtonRelease events are generated
+ * together sequentially; instead when the button is released, no event is
+ * generated !
+ *
+ * With the command
+ *	10<xx>0a 3500af03 (where <xx> is the mouse id),
+ * the mouse reacts differently:
+ * - it never sends a keyboard key event
+ * - for the three mouse button it sends:
+ *	middle button               press   11<xx>0a 3500af00...
+ *	side 1 button (forward)     press   11<xx>0a 3500b000...
+ *	side 2 button (backward)    press   11<xx>0a 3500ae00...
+ *	middle/side1/side2 button   release 11<xx>0a 35000000...
+ */
+
+static const u8 m560_config_parameter[] = {0x00, 0xaf, 0x03};
+
+struct m560_private_data {
+	struct input_dev *input;
+};
+
+/* how buttons are mapped in the report */
+#define M560_MOUSE_BTN_LEFT		0x01
+#define M560_MOUSE_BTN_RIGHT		0x02
+#define M560_MOUSE_BTN_WHEEL_LEFT	0x08
+#define M560_MOUSE_BTN_WHEEL_RIGHT	0x10
+
+#define M560_SUB_ID			0x0a
+#define M560_BUTTON_MODE_REGISTER	0x35
+
+static int m560_send_config_command(struct hid_device *hdev, bool connected)
+{
+	struct hidpp_report response;
+	struct hidpp_device *hidpp_dev;
+
+	hidpp_dev = hid_get_drvdata(hdev);
+
+	if (!connected)
+		return -ENODEV;
+
+	return hidpp_send_rap_command_sync(
+		hidpp_dev,
+		REPORT_ID_HIDPP_SHORT,
+		M560_SUB_ID,
+		M560_BUTTON_MODE_REGISTER,
+		(u8 *)m560_config_parameter,
+		sizeof(m560_config_parameter),
+		&response
+	);
+}
+
+static int m560_allocate(struct hid_device *hdev)
+{
+	struct hidpp_device *hidpp = hid_get_drvdata(hdev);
+	struct m560_private_data *d;
+
+	d = devm_kzalloc(&hdev->dev, sizeof(struct m560_private_data),
+			GFP_KERNEL);
+	if (!d)
+		return -ENOMEM;
+
+	hidpp->private_data = d;
+
+	return 0;
+};
+
+static int m560_raw_event(struct hid_device *hdev, u8 *data, int size)
+{
+	struct hidpp_device *hidpp = hid_get_drvdata(hdev);
+	struct m560_private_data *mydata = hidpp->private_data;
+
+	/* sanity check */
+	if (!mydata || !mydata->input) {
+		hid_err(hdev, "error in parameter\n");
+		return -EINVAL;
+	}
+
+	if (size < 7) {
+		hid_err(hdev, "error in report\n");
+		return 0;
+	}
+
+	if (data[0] == REPORT_ID_HIDPP_LONG &&
+	    data[2] == M560_SUB_ID && data[6] == 0x00) {
+		/*
+		 * m560 mouse report for middle, forward and backward button
+		 *
+		 * data[0] = 0x11
+		 * data[1] = device-id
+		 * data[2] = 0x0a
+		 * data[5] = 0xaf -> middle
+		 *	     0xb0 -> forward
+		 *	     0xae -> backward
+		 *	     0x00 -> release all
+		 * data[6] = 0x00
+		 */
+
+		switch (data[5]) {
+		case 0xaf:
+			input_report_key(mydata->input, BTN_MIDDLE, 1);
+			break;
+		case 0xb0:
+			input_report_key(mydata->input, BTN_FORWARD, 1);
+			break;
+		case 0xae:
+			input_report_key(mydata->input, BTN_BACK, 1);
+			break;
+		case 0x00:
+			input_report_key(mydata->input, BTN_BACK, 0);
+			input_report_key(mydata->input, BTN_FORWARD, 0);
+			input_report_key(mydata->input, BTN_MIDDLE, 0);
+			break;
+		default:
+			hid_err(hdev, "error in report\n");
+			return 0;
+		}
+		input_sync(mydata->input);
+
+	} else if (data[0] == 0x02) {
+		/*
+		 * Logitech M560 mouse report
+		 *
+		 * data[0] = type (0x02)
+		 * data[1..2] = buttons
+		 * data[3..5] = xy
+		 * data[6] = wheel
+		 */
+
+		int v;
+
+		input_report_key(mydata->input, BTN_LEFT,
+			!!(data[1] & M560_MOUSE_BTN_LEFT));
+		input_report_key(mydata->input, BTN_RIGHT,
+			!!(data[1] & M560_MOUSE_BTN_RIGHT));
+
+		if (data[1] & M560_MOUSE_BTN_WHEEL_LEFT)
+			input_report_rel(mydata->input, REL_HWHEEL, -1);
+		else if (data[1] & M560_MOUSE_BTN_WHEEL_RIGHT)
+			input_report_rel(mydata->input, REL_HWHEEL, 1);
+
+		v = hid_snto32(hid_field_extract(hdev, data+3, 0, 12), 12);
+		input_report_rel(mydata->input, REL_X, v);
+
+		v = hid_snto32(hid_field_extract(hdev, data+3, 12, 12), 12);
+		input_report_rel(mydata->input, REL_Y, v);
+
+		v = hid_snto32(data[6], 8);
+		input_report_rel(mydata->input, REL_WHEEL, v);
+
+		input_sync(mydata->input);
+	}
+
+	return 1;
+}
+
+static void m560_populate_input(struct hidpp_device *hidpp,
+		struct input_dev *input_dev, bool origin_is_hid_core)
+{
+	struct m560_private_data *mydata = hidpp->private_data;
+
+	mydata->input = input_dev;
+
+	__set_bit(EV_KEY, mydata->input->evbit);
+	__set_bit(BTN_MIDDLE, mydata->input->keybit);
+	__set_bit(BTN_RIGHT, mydata->input->keybit);
+	__set_bit(BTN_LEFT, mydata->input->keybit);
+	__set_bit(BTN_BACK, mydata->input->keybit);
+	__set_bit(BTN_FORWARD, mydata->input->keybit);
+
+	__set_bit(EV_REL, mydata->input->evbit);
+	__set_bit(REL_X, mydata->input->relbit);
+	__set_bit(REL_Y, mydata->input->relbit);
+	__set_bit(REL_WHEEL, mydata->input->relbit);
+	__set_bit(REL_HWHEEL, mydata->input->relbit);
+}
+
+static int m560_input_mapping(struct hid_device *hdev, struct hid_input *hi,
+		struct hid_field *field, struct hid_usage *usage,
+		unsigned long **bit, int *max)
+{
+	return -1;
+}
+
 /* -------------------------------------------------------------------------- */
 /* Generic HID++ devices                                                      */
 /* -------------------------------------------------------------------------- */
@@ -942,6 +1144,9 @@ static int hidpp_input_mapping(struct hid_device *hdev, struct hid_input *hi,
 
 	if (hidpp->quirks & HIDPP_QUIRK_CLASS_WTP)
 		return wtp_input_mapping(hdev, hi, field, usage, bit, max);
+	else if (hidpp->quirks & HIDPP_QUIRK_CLASS_M560 &&
+			field->application != HID_GD_MOUSE)
+		return m560_input_mapping(hdev, hi, field, usage, bit, max);
 
 	return 0;
 }
@@ -951,6 +1156,8 @@ static void hidpp_populate_input(struct hidpp_device *hidpp,
 {
 	if (hidpp->quirks & HIDPP_QUIRK_CLASS_WTP)
 		wtp_populate_input(hidpp, input, origin_is_hid_core);
+	else if (hidpp->quirks & HIDPP_QUIRK_CLASS_M560)
+		m560_populate_input(hidpp, input, origin_is_hid_core);
 }
 
 static void hidpp_input_configured(struct hid_device *hdev,
@@ -1038,6 +1245,8 @@ static int hidpp_raw_event(struct hid_device *hdev, struct hid_report *report,
 
 	if (hidpp->quirks & HIDPP_QUIRK_CLASS_WTP)
 		return wtp_raw_event(hdev, data, size);
+	else if (hidpp->quirks & HIDPP_QUIRK_CLASS_M560)
+		return m560_raw_event(hdev, data, size);
 
 	return 0;
 }
@@ -1115,6 +1324,10 @@ static void hidpp_connect_event(struct hidpp_device *hidpp)
 		ret = wtp_connect(hdev, connected);
 		if (ret)
 			return;
+	} else if (hidpp->quirks & HIDPP_QUIRK_CLASS_M560) {
+		ret = m560_send_config_command(hdev, connected);
+		if (ret)
+			return;
 	}
 
 	if (!connected || hidpp->delayed_input)
@@ -1190,7 +1403,11 @@ static int hidpp_probe(struct hid_device *hdev, const struct hid_device_id *id)
 	if (hidpp->quirks & HIDPP_QUIRK_CLASS_WTP) {
 		ret = wtp_allocate(hdev, id);
 		if (ret)
-			goto wtp_allocate_fail;
+			goto allocate_fail;
+	} else if (hidpp->quirks & HIDPP_QUIRK_CLASS_M560) {
+		ret = m560_allocate(hdev);
+		if (ret)
+			goto allocate_fail;
 	}
 
 	INIT_WORK(&hidpp->work, delayed_work_cb);
@@ -1253,7 +1470,7 @@ hid_hw_start_fail:
 hid_parse_fail:
 	cancel_work_sync(&hidpp->work);
 	mutex_destroy(&hidpp->send_mutex);
-wtp_allocate_fail:
+allocate_fail:
 	hid_set_drvdata(hdev, NULL);
 	return ret;
 }
@@ -1281,6 +1498,10 @@ static const struct hid_device_id hidpp_devices[] = {
 	  HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH,
 		USB_DEVICE_ID_LOGITECH_T651),
 	  .driver_data = HIDPP_QUIRK_CLASS_WTP },
+	{ /* Mouse logitech M560 */
+	  HID_DEVICE(BUS_USB, HID_GROUP_LOGITECH_DJ_DEVICE,
+		USB_VENDOR_ID_LOGITECH, 0x402d),
+	  .driver_data = HIDPP_QUIRK_DELAYED_INIT | HIDPP_QUIRK_CLASS_M560 },
 
 	{ HID_DEVICE(BUS_USB, HID_GROUP_LOGITECH_DJ_DEVICE,
 		USB_VENDOR_ID_LOGITECH, HID_ANY_ID)},
diff --git a/drivers/hid/hid-microsoft.c b/drivers/hid/hid-microsoft.c
index af935eb198c9..32a596f554af 100644
--- a/drivers/hid/hid-microsoft.c
+++ b/drivers/hid/hid-microsoft.c
@@ -280,6 +280,8 @@ static const struct hid_device_id ms_devices[] = {
 		.driver_data = MS_HIDINPUT },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_3_JP),
 		.driver_data = MS_HIDINPUT },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_POWER_COVER),
+		.driver_data = MS_HIDINPUT },
 
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_PRESENTER_8K_BT),
 		.driver_data = MS_PRESENTER },
diff --git a/drivers/hid/hid-plantronics.c b/drivers/hid/hid-plantronics.c
index 2180e0789b76..febb21ee190e 100644
--- a/drivers/hid/hid-plantronics.c
+++ b/drivers/hid/hid-plantronics.c
@@ -2,7 +2,7 @@
  *  Plantronics USB HID Driver
  *
  *  Copyright (c) 2014 JD Cole <jd.cole@plantronics.com>
- *  Copyright (c) 2014 Terry Junge <terry.junge@plantronics.com>
+ *  Copyright (c) 2015 Terry Junge <terry.junge@plantronics.com>
  */
 
 /*
@@ -17,23 +17,138 @@
 #include <linux/hid.h>
 #include <linux/module.h>
 
+#define PLT_HID_1_0_PAGE	0xffa00000
+#define PLT_HID_2_0_PAGE	0xffa20000
+
+#define PLT_BASIC_TELEPHONY	0x0003
+#define PLT_BASIC_EXCEPTION	0x0005
+
+#define PLT_VOL_UP		0x00b1
+#define PLT_VOL_DOWN		0x00b2
+
+#define PLT1_VOL_UP		(PLT_HID_1_0_PAGE | PLT_VOL_UP)
+#define PLT1_VOL_DOWN		(PLT_HID_1_0_PAGE | PLT_VOL_DOWN)
+#define PLT2_VOL_UP		(PLT_HID_2_0_PAGE | PLT_VOL_UP)
+#define PLT2_VOL_DOWN		(PLT_HID_2_0_PAGE | PLT_VOL_DOWN)
+
+#define PLT_DA60		0xda60
+#define PLT_BT300_MIN		0x0413
+#define PLT_BT300_MAX		0x0418
+
+
+#define PLT_ALLOW_CONSUMER (field->application == HID_CP_CONSUMERCONTROL && \
+			    (usage->hid & HID_USAGE_PAGE) == HID_UP_CONSUMER)
+
 static int plantronics_input_mapping(struct hid_device *hdev,
 				     struct hid_input *hi,
 				     struct hid_field *field,
 				     struct hid_usage *usage,
 				     unsigned long **bit, int *max)
 {
-	if (field->application == HID_CP_CONSUMERCONTROL
-	    && (usage->hid & HID_USAGE_PAGE) == HID_UP_CONSUMER) {
-		hid_dbg(hdev, "usage: %08x (appl: %08x) - defaulted\n",
-			 usage->hid, field->application);
-		return 0;
+	unsigned short mapped_key;
+	unsigned long plt_type = (unsigned long)hid_get_drvdata(hdev);
+
+	/* handle volume up/down mapping */
+	/* non-standard types or multi-HID interfaces - plt_type is PID */
+	if (!(plt_type & HID_USAGE_PAGE)) {
+		switch (plt_type) {
+		case PLT_DA60:
+			if (PLT_ALLOW_CONSUMER)
+				goto defaulted;
+			goto ignored;
+		default:
+			if (PLT_ALLOW_CONSUMER)
+				goto defaulted;
+		}
+	}
+	/* handle standard types - plt_type is 0xffa0uuuu or 0xffa2uuuu */
+	/* 'basic telephony compliant' - allow default consumer page map */
+	else if ((plt_type & HID_USAGE) >= PLT_BASIC_TELEPHONY &&
+		 (plt_type & HID_USAGE) != PLT_BASIC_EXCEPTION) {
+		if (PLT_ALLOW_CONSUMER)
+			goto defaulted;
+	}
+	/* not 'basic telephony' - apply legacy mapping */
+	/* only map if the field is in the device's primary vendor page */
+	else if (!((field->application ^ plt_type) & HID_USAGE_PAGE)) {
+		switch (usage->hid) {
+		case PLT1_VOL_UP:
+		case PLT2_VOL_UP:
+			mapped_key = KEY_VOLUMEUP;
+			goto mapped;
+		case PLT1_VOL_DOWN:
+		case PLT2_VOL_DOWN:
+			mapped_key = KEY_VOLUMEDOWN;
+			goto mapped;
+		}
 	}
 
-	hid_dbg(hdev, "usage: %08x (appl: %08x) - ignored\n",
-		usage->hid, field->application);
+/*
+ * Future mapping of call control or other usages,
+ * if and when keys are defined would go here
+ * otherwise, ignore everything else that was not mapped
+ */
 
+ignored:
 	return -1;
+
+defaulted:
+	hid_dbg(hdev, "usage: %08x (appl: %08x) - defaulted\n",
+		usage->hid, field->application);
+	return 0;
+
+mapped:
+	hid_map_usage_clear(hi, usage, bit, max, EV_KEY, mapped_key);
+	hid_dbg(hdev, "usage: %08x (appl: %08x) - mapped to key %d\n",
+		usage->hid, field->application, mapped_key);
+	return 1;
+}
+
+static unsigned long plantronics_device_type(struct hid_device *hdev)
+{
+	unsigned i, col_page;
+	unsigned long plt_type = hdev->product;
+
+	/* multi-HID interfaces? - plt_type is PID */
+	if (plt_type >= PLT_BT300_MIN && plt_type <= PLT_BT300_MAX)
+		goto exit;
+
+	/* determine primary vendor page */
+	for (i = 0; i < hdev->maxcollection; i++) {
+		col_page = hdev->collection[i].usage & HID_USAGE_PAGE;
+		if (col_page == PLT_HID_2_0_PAGE) {
+			plt_type = hdev->collection[i].usage;
+			break;
+		}
+		if (col_page == PLT_HID_1_0_PAGE)
+			plt_type = hdev->collection[i].usage;
+	}
+
+exit:
+	hid_dbg(hdev, "plt_type decoded as: %08lx\n", plt_type);
+	return plt_type;
+}
+
+static int plantronics_probe(struct hid_device *hdev,
+			     const struct hid_device_id *id)
+{
+	int ret;
+
+	ret = hid_parse(hdev);
+	if (ret) {
+		hid_err(hdev, "parse failed\n");
+		goto err;
+	}
+
+	hid_set_drvdata(hdev, (void *)plantronics_device_type(hdev));
+
+	ret = hid_hw_start(hdev, HID_CONNECT_DEFAULT |
+		HID_CONNECT_HIDINPUT_FORCE | HID_CONNECT_HIDDEV_FORCE);
+	if (ret)
+		hid_err(hdev, "hw start failed\n");
+
+err:
+	return ret;
 }
 
 static const struct hid_device_id plantronics_devices[] = {
@@ -46,6 +161,7 @@ static struct hid_driver plantronics_driver = {
 	.name = "plantronics",
 	.id_table = plantronics_devices,
 	.input_mapping = plantronics_input_mapping,
+	.probe = plantronics_probe,
 };
 module_hid_driver(plantronics_driver);
 
diff --git a/drivers/hid/hid-prodikeys.c b/drivers/hid/hid-prodikeys.c
index 91fab975063c..e3e98ccf137b 100644
--- a/drivers/hid/hid-prodikeys.c
+++ b/drivers/hid/hid-prodikeys.c
@@ -395,11 +395,10 @@ static int pcmidi_handle_report4(struct pcmidi_snd *pm, u8 *data)
 
 	/* break keys */
 	for (bit_index = 0; bit_index < 24; bit_index++) {
-		key = pm->last_key[bit_index];
 		if (!((0x01 << bit_index) & bit_mask)) {
 			input_event(pm->input_ep82, EV_KEY,
 				pm->last_key[bit_index], 0);
-				pm->last_key[bit_index] = 0;
+			pm->last_key[bit_index] = 0;
 		}
 	}
 
diff --git a/drivers/hid/hid-rmi.c b/drivers/hid/hid-rmi.c
index 368ffdf2c0a3..4cf80bb276dc 100644
--- a/drivers/hid/hid-rmi.c
+++ b/drivers/hid/hid-rmi.c
@@ -29,9 +29,9 @@
 #define RMI_SET_RMI_MODE_REPORT_ID	0x0f /* Feature Report */
 
 /* flags */
-#define RMI_READ_REQUEST_PENDING	BIT(0)
-#define RMI_READ_DATA_PENDING		BIT(1)
-#define RMI_STARTED			BIT(2)
+#define RMI_READ_REQUEST_PENDING	0
+#define RMI_READ_DATA_PENDING		1
+#define RMI_STARTED			2
 
 /* device flags */
 #define RMI_DEVICE			BIT(0)
@@ -1013,6 +1013,7 @@ static int rmi_populate_f30(struct hid_device *hdev)
 
 static int rmi_populate(struct hid_device *hdev)
 {
+	struct rmi_data *data = hid_get_drvdata(hdev);
 	int ret;
 
 	ret = rmi_scan_pdt(hdev);
@@ -1033,9 +1034,11 @@ static int rmi_populate(struct hid_device *hdev)
 		return ret;
 	}
 
-	ret = rmi_populate_f30(hdev);
-	if (ret)
-		hid_warn(hdev, "Error while initializing F30 (%d).\n", ret);
+	if (!(data->device_flags & RMI_DEVICE_HAS_PHYS_BUTTONS)) {
+		ret = rmi_populate_f30(hdev);
+		if (ret)
+			hid_warn(hdev, "Error while initializing F30 (%d).\n", ret);
+	}
 
 	return 0;
 }
diff --git a/drivers/hid/hid-sjoy.c b/drivers/hid/hid-sjoy.c
index 37845eccddb5..36b6470af947 100644
--- a/drivers/hid/hid-sjoy.c
+++ b/drivers/hid/hid-sjoy.c
@@ -166,6 +166,9 @@ static const struct hid_device_id sjoy_devices[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_WISEGROUP, USB_DEVICE_ID_DUAL_USB_JOYPAD),
 		.driver_data = HID_QUIRK_MULTI_INPUT |
 			       HID_QUIRK_SKIP_OUTPUT_REPORTS },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_PLAYDOTCOM, USB_DEVICE_ID_PLAYDOTCOM_EMS_USBII),
+		.driver_data = HID_QUIRK_MULTI_INPUT |
+			       HID_QUIRK_SKIP_OUTPUT_REPORTS },
 	{ }
 };
 MODULE_DEVICE_TABLE(hid, sjoy_devices);
diff --git a/drivers/hid/hid-sony.c b/drivers/hid/hid-sony.c
index 6ca96cebb44c..ed2f008f8403 100644
--- a/drivers/hid/hid-sony.c
+++ b/drivers/hid/hid-sony.c
@@ -46,20 +46,37 @@
 #define PS3REMOTE                 BIT(4)
 #define DUALSHOCK4_CONTROLLER_USB BIT(5)
 #define DUALSHOCK4_CONTROLLER_BT  BIT(6)
+#define MOTION_CONTROLLER_USB     BIT(7)
+#define MOTION_CONTROLLER_BT      BIT(8)
+#define NAVIGATION_CONTROLLER_USB BIT(9)
+#define NAVIGATION_CONTROLLER_BT  BIT(10)
 
 #define SIXAXIS_CONTROLLER (SIXAXIS_CONTROLLER_USB | SIXAXIS_CONTROLLER_BT)
+#define MOTION_CONTROLLER (MOTION_CONTROLLER_USB | MOTION_CONTROLLER_BT)
+#define NAVIGATION_CONTROLLER (NAVIGATION_CONTROLLER_USB |\
+				NAVIGATION_CONTROLLER_BT)
 #define DUALSHOCK4_CONTROLLER (DUALSHOCK4_CONTROLLER_USB |\
 				DUALSHOCK4_CONTROLLER_BT)
 #define SONY_LED_SUPPORT (SIXAXIS_CONTROLLER | BUZZ_CONTROLLER |\
-				DUALSHOCK4_CONTROLLER)
-#define SONY_BATTERY_SUPPORT (SIXAXIS_CONTROLLER | DUALSHOCK4_CONTROLLER)
-#define SONY_FF_SUPPORT (SIXAXIS_CONTROLLER | DUALSHOCK4_CONTROLLER)
+				DUALSHOCK4_CONTROLLER | MOTION_CONTROLLER |\
+				NAVIGATION_CONTROLLER)
+#define SONY_BATTERY_SUPPORT (SIXAXIS_CONTROLLER | DUALSHOCK4_CONTROLLER |\
+				MOTION_CONTROLLER_BT | NAVIGATION_CONTROLLER)
+#define SONY_FF_SUPPORT (SIXAXIS_CONTROLLER | DUALSHOCK4_CONTROLLER |\
+				MOTION_CONTROLLER)
 
 #define MAX_LEDS 4
 
+/*
+ * The Sixaxis reports both digital and analog values for each button on the
+ * controller except for Start, Select and the PS button.  The controller ends
+ * up reporting 27 axes which causes them to spill over into the multi-touch
+ * axis values.  Additionally, the controller only has 20 actual, physical axes
+ * so there are several unused axes in between the used ones.
+ */
 static __u8 sixaxis_rdesc[] = {
 	0x05, 0x01,         /*  Usage Page (Desktop),               */
-	0x09, 0x04,         /*  Usage (Joystik),                    */
+	0x09, 0x04,         /*  Usage (Joystick),                   */
 	0xA1, 0x01,         /*  Collection (Application),           */
 	0xA1, 0x02,         /*      Collection (Logical),           */
 	0x85, 0x01,         /*          Report ID (1),              */
@@ -134,6 +151,186 @@ static __u8 sixaxis_rdesc[] = {
 	0xC0                /*  End Collection                      */
 };
 
+/* PS/3 Motion controller */
+static __u8 motion_rdesc[] = {
+	0x05, 0x01,         /*  Usage Page (Desktop),               */
+	0x09, 0x04,         /*  Usage (Joystick),                   */
+	0xA1, 0x01,         /*  Collection (Application),           */
+	0xA1, 0x02,         /*      Collection (Logical),           */
+	0x85, 0x01,         /*          Report ID (1),              */
+	0x75, 0x01,         /*          Report Size (1),            */
+	0x95, 0x15,         /*          Report Count (21),          */
+	0x15, 0x00,         /*          Logical Minimum (0),        */
+	0x25, 0x01,         /*          Logical Maximum (1),        */
+	0x35, 0x00,         /*          Physical Minimum (0),       */
+	0x45, 0x01,         /*          Physical Maximum (1),       */
+	0x05, 0x09,         /*          Usage Page (Button),        */
+	0x19, 0x01,         /*          Usage Minimum (01h),        */
+	0x29, 0x15,         /*          Usage Maximum (15h),        */
+	0x81, 0x02,         /*          Input (Variable),           * Buttons */
+	0x95, 0x0B,         /*          Report Count (11),          */
+	0x06, 0x00, 0xFF,   /*          Usage Page (FF00h),         */
+	0x81, 0x03,         /*          Input (Constant, Variable), * Padding */
+	0x15, 0x00,         /*          Logical Minimum (0),        */
+	0x26, 0xFF, 0x00,   /*          Logical Maximum (255),      */
+	0x05, 0x01,         /*          Usage Page (Desktop),       */
+	0xA1, 0x00,         /*          Collection (Physical),      */
+	0x75, 0x08,         /*              Report Size (8),        */
+	0x95, 0x01,         /*              Report Count (1),       */
+	0x35, 0x00,         /*              Physical Minimum (0),   */
+	0x46, 0xFF, 0x00,   /*              Physical Maximum (255), */
+	0x09, 0x30,         /*              Usage (X),              */
+	0x81, 0x02,         /*              Input (Variable),       * Trigger */
+	0xC0,               /*          End Collection,             */
+	0x06, 0x00, 0xFF,   /*          Usage Page (FF00h),         */
+	0x75, 0x08,         /*          Report Size (8),            */
+	0x95, 0x07,         /*          Report Count (7),           * skip 7 bytes */
+	0x81, 0x02,         /*          Input (Variable),           */
+	0x05, 0x01,         /*          Usage Page (Desktop),       */
+	0x75, 0x10,         /*          Report Size (16),           */
+	0x46, 0xFF, 0xFF,   /*          Physical Maximum (65535),   */
+	0x27, 0xFF, 0xFF, 0x00, 0x00, /*      Logical Maximum (65535),    */
+	0x95, 0x03,         /*          Report Count (3),           * 3x Accels */
+	0x09, 0x33,         /*              Usage (rX),             */
+	0x09, 0x34,         /*              Usage (rY),             */
+	0x09, 0x35,         /*              Usage (rZ),             */
+	0x81, 0x02,         /*          Input (Variable),           */
+	0x06, 0x00, 0xFF,   /*          Usage Page (FF00h),         */
+	0x95, 0x03,         /*          Report Count (3),           * Skip Accels 2nd frame */
+	0x81, 0x02,         /*          Input (Variable),           */
+	0x05, 0x01,         /*          Usage Page (Desktop),       */
+	0x09, 0x01,         /*          Usage (Pointer),            */
+	0x95, 0x03,         /*          Report Count (3),           * 3x Gyros */
+	0x81, 0x02,         /*          Input (Variable),           */
+	0x06, 0x00, 0xFF,   /*          Usage Page (FF00h),         */
+	0x95, 0x03,         /*          Report Count (3),           * Skip Gyros 2nd frame */
+	0x81, 0x02,         /*          Input (Variable),           */
+	0x75, 0x0C,         /*          Report Size (12),           */
+	0x46, 0xFF, 0x0F,   /*          Physical Maximum (4095),    */
+	0x26, 0xFF, 0x0F,   /*          Logical Maximum (4095),     */
+	0x95, 0x04,         /*          Report Count (4),           * Skip Temp and Magnetometers */
+	0x81, 0x02,         /*          Input (Variable),           */
+	0x75, 0x08,         /*          Report Size (8),            */
+	0x46, 0xFF, 0x00,   /*          Physical Maximum (255),     */
+	0x26, 0xFF, 0x00,   /*          Logical Maximum (255),      */
+	0x95, 0x06,         /*          Report Count (6),           * Skip Timestamp and Extension Bytes */
+	0x81, 0x02,         /*          Input (Variable),           */
+	0x75, 0x08,         /*          Report Size (8),            */
+	0x95, 0x30,         /*          Report Count (48),          */
+	0x09, 0x01,         /*          Usage (Pointer),            */
+	0x91, 0x02,         /*          Output (Variable),          */
+	0x75, 0x08,         /*          Report Size (8),            */
+	0x95, 0x30,         /*          Report Count (48),          */
+	0x09, 0x01,         /*          Usage (Pointer),            */
+	0xB1, 0x02,         /*          Feature (Variable),         */
+	0xC0,               /*      End Collection,                 */
+	0xA1, 0x02,         /*      Collection (Logical),           */
+	0x85, 0x02,         /*          Report ID (2),              */
+	0x75, 0x08,         /*          Report Size (8),            */
+	0x95, 0x30,         /*          Report Count (48),          */
+	0x09, 0x01,         /*          Usage (Pointer),            */
+	0xB1, 0x02,         /*          Feature (Variable),         */
+	0xC0,               /*      End Collection,                 */
+	0xA1, 0x02,         /*      Collection (Logical),           */
+	0x85, 0xEE,         /*          Report ID (238),            */
+	0x75, 0x08,         /*          Report Size (8),            */
+	0x95, 0x30,         /*          Report Count (48),          */
+	0x09, 0x01,         /*          Usage (Pointer),            */
+	0xB1, 0x02,         /*          Feature (Variable),         */
+	0xC0,               /*      End Collection,                 */
+	0xA1, 0x02,         /*      Collection (Logical),           */
+	0x85, 0xEF,         /*          Report ID (239),            */
+	0x75, 0x08,         /*          Report Size (8),            */
+	0x95, 0x30,         /*          Report Count (48),          */
+	0x09, 0x01,         /*          Usage (Pointer),            */
+	0xB1, 0x02,         /*          Feature (Variable),         */
+	0xC0,               /*      End Collection,                 */
+	0xC0                /*  End Collection                      */
+};
+
+/* PS/3 Navigation controller */
+static __u8 navigation_rdesc[] = {
+	0x05, 0x01,         /*  Usage Page (Desktop),               */
+	0x09, 0x04,         /*  Usage (Joystik),                    */
+	0xA1, 0x01,         /*  Collection (Application),           */
+	0xA1, 0x02,         /*      Collection (Logical),           */
+	0x85, 0x01,         /*          Report ID (1),              */
+	0x75, 0x08,         /*          Report Size (8),            */
+	0x95, 0x01,         /*          Report Count (1),           */
+	0x15, 0x00,         /*          Logical Minimum (0),        */
+	0x26, 0xFF, 0x00,   /*          Logical Maximum (255),      */
+	0x81, 0x03,         /*          Input (Constant, Variable), */
+	0x75, 0x01,         /*          Report Size (1),            */
+	0x95, 0x13,         /*          Report Count (19),          */
+	0x15, 0x00,         /*          Logical Minimum (0),        */
+	0x25, 0x01,         /*          Logical Maximum (1),        */
+	0x35, 0x00,         /*          Physical Minimum (0),       */
+	0x45, 0x01,         /*          Physical Maximum (1),       */
+	0x05, 0x09,         /*          Usage Page (Button),        */
+	0x19, 0x01,         /*          Usage Minimum (01h),        */
+	0x29, 0x13,         /*          Usage Maximum (13h),        */
+	0x81, 0x02,         /*          Input (Variable),           */
+	0x75, 0x01,         /*          Report Size (1),            */
+	0x95, 0x0D,         /*          Report Count (13),          */
+	0x06, 0x00, 0xFF,   /*          Usage Page (FF00h),         */
+	0x81, 0x03,         /*          Input (Constant, Variable), */
+	0x15, 0x00,         /*          Logical Minimum (0),        */
+	0x26, 0xFF, 0x00,   /*          Logical Maximum (255),      */
+	0x05, 0x01,         /*          Usage Page (Desktop),       */
+	0x09, 0x01,         /*          Usage (Pointer),            */
+	0xA1, 0x00,         /*          Collection (Physical),      */
+	0x75, 0x08,         /*              Report Size (8),        */
+	0x95, 0x02,         /*              Report Count (2),       */
+	0x35, 0x00,         /*              Physical Minimum (0),   */
+	0x46, 0xFF, 0x00,   /*              Physical Maximum (255), */
+	0x09, 0x30,         /*              Usage (X),              */
+	0x09, 0x31,         /*              Usage (Y),              */
+	0x81, 0x02,         /*              Input (Variable),       */
+	0xC0,               /*          End Collection,             */
+	0x06, 0x00, 0xFF,   /*          Usage Page (FF00h),         */
+	0x95, 0x06,         /*          Report Count (6),           */
+	0x81, 0x03,         /*          Input (Constant, Variable), */
+	0x05, 0x01,         /*          Usage Page (Desktop),       */
+	0x75, 0x08,         /*          Report Size (8),            */
+	0x95, 0x05,         /*          Report Count (5),           */
+	0x09, 0x01,         /*          Usage (Pointer),            */
+	0x81, 0x02,         /*          Input (Variable),           */
+	0x06, 0x00, 0xFF,   /*          Usage Page (FF00h),         */
+	0x95, 0x20,         /*          Report Count (26),          */
+	0x81, 0x02,         /*          Input (Variable),           */
+	0x75, 0x08,         /*          Report Size (8),            */
+	0x95, 0x30,         /*          Report Count (48),          */
+	0x09, 0x01,         /*          Usage (Pointer),            */
+	0x91, 0x02,         /*          Output (Variable),          */
+	0x75, 0x08,         /*          Report Size (8),            */
+	0x95, 0x30,         /*          Report Count (48),          */
+	0x09, 0x01,         /*          Usage (Pointer),            */
+	0xB1, 0x02,         /*          Feature (Variable),         */
+	0xC0,               /*      End Collection,                 */
+	0xA1, 0x02,         /*      Collection (Logical),           */
+	0x85, 0x02,         /*          Report ID (2),              */
+	0x75, 0x08,         /*          Report Size (8),            */
+	0x95, 0x30,         /*          Report Count (48),          */
+	0x09, 0x01,         /*          Usage (Pointer),            */
+	0xB1, 0x02,         /*          Feature (Variable),         */
+	0xC0,               /*      End Collection,                 */
+	0xA1, 0x02,         /*      Collection (Logical),           */
+	0x85, 0xEE,         /*          Report ID (238),            */
+	0x75, 0x08,         /*          Report Size (8),            */
+	0x95, 0x30,         /*          Report Count (48),          */
+	0x09, 0x01,         /*          Usage (Pointer),            */
+	0xB1, 0x02,         /*          Feature (Variable),         */
+	0xC0,               /*      End Collection,                 */
+	0xA1, 0x02,         /*      Collection (Logical),           */
+	0x85, 0xEF,         /*          Report ID (239),            */
+	0x75, 0x08,         /*          Report Size (8),            */
+	0x95, 0x30,         /*          Report Count (48),          */
+	0x09, 0x01,         /*          Usage (Pointer),            */
+	0xB1, 0x02,         /*          Feature (Variable),         */
+	0xC0,               /*      End Collection,                 */
+	0xC0                /*  End Collection                      */
+};
+
 /*
  * The default descriptor doesn't provide mapping for the accelerometers
  * or orientation sensors.  This fixed descriptor maps the accelerometers
@@ -798,12 +995,20 @@ union sixaxis_output_report_01 {
 	__u8 buf[36];
 };
 
+struct motion_output_report_02 {
+	u8 type, zero;
+	u8 r, g, b;
+	u8 zero2;
+	u8 rumble;
+};
+
 #define DS4_REPORT_0x02_SIZE 37
 #define DS4_REPORT_0x05_SIZE 32
 #define DS4_REPORT_0x11_SIZE 78
 #define DS4_REPORT_0x81_SIZE 7
 #define SIXAXIS_REPORT_0xF2_SIZE 17
 #define SIXAXIS_REPORT_0xF5_SIZE 8
+#define MOTION_REPORT_0x02_SIZE 49
 
 static DEFINE_SPINLOCK(sony_dev_list_lock);
 static LIST_HEAD(sony_device_list);
@@ -844,6 +1049,20 @@ static __u8 *sixaxis_fixup(struct hid_device *hdev, __u8 *rdesc,
 	return sixaxis_rdesc;
 }
 
+static u8 *motion_fixup(struct hid_device *hdev, u8 *rdesc,
+			     unsigned int *rsize)
+{
+	*rsize = sizeof(motion_rdesc);
+	return motion_rdesc;
+}
+
+static u8 *navigation_fixup(struct hid_device *hdev, u8 *rdesc,
+			     unsigned int *rsize)
+{
+	*rsize = sizeof(navigation_rdesc);
+	return navigation_rdesc;
+}
+
 static __u8 *ps3remote_fixup(struct hid_device *hdev, __u8 *rdesc,
 			     unsigned int *rsize)
 {
@@ -924,6 +1143,12 @@ static __u8 *sony_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 	if (sc->quirks & SIXAXIS_CONTROLLER)
 		return sixaxis_fixup(hdev, rdesc, rsize);
 
+	if (sc->quirks & MOTION_CONTROLLER)
+		return motion_fixup(hdev, rdesc, rsize);
+
+	if (sc->quirks & NAVIGATION_CONTROLLER)
+		return navigation_fixup(hdev, rdesc, rsize);
+
 	if (sc->quirks & PS3REMOTE)
 		return ps3remote_fixup(hdev, rdesc, rsize);
 
@@ -934,6 +1159,7 @@ static void sixaxis_parse_report(struct sony_sc *sc, __u8 *rd, int size)
 {
 	static const __u8 sixaxis_battery_capacity[] = { 0, 1, 25, 50, 75, 100 };
 	unsigned long flags;
+	int offset;
 	__u8 cable_state, battery_capacity, battery_charging;
 
 	/*
@@ -942,12 +1168,14 @@ static void sixaxis_parse_report(struct sony_sc *sc, __u8 *rd, int size)
 	 * It does not report the actual level while charging so it
 	 * is set to 100% while charging is in progress.
 	 */
-	if (rd[30] >= 0xee) {
+	offset = (sc->quirks & MOTION_CONTROLLER) ? 12 : 30;
+
+	if (rd[offset] >= 0xee) {
 		battery_capacity = 100;
-		battery_charging = !(rd[30] & 0x01);
+		battery_charging = !(rd[offset] & 0x01);
 		cable_state = 1;
 	} else {
-		__u8 index = rd[30] <= 5 ? rd[30] : 5;
+		__u8 index = rd[offset] <= 5 ? rd[offset] : 5;
 		battery_capacity = sixaxis_battery_capacity[index];
 		battery_charging = 0;
 		cable_state = 0;
@@ -1048,6 +1276,11 @@ static int sony_raw_event(struct hid_device *hdev, struct hid_report *report,
 		swap(rd[47], rd[48]);
 
 		sixaxis_parse_report(sc, rd, size);
+	} else if ((sc->quirks & MOTION_CONTROLLER_BT) && rd[0] == 0x01 && size == 49) {
+		sixaxis_parse_report(sc, rd, size);
+	} else if ((sc->quirks & NAVIGATION_CONTROLLER) && rd[0] == 0x01 &&
+			size == 49) {
+		sixaxis_parse_report(sc, rd, size);
 	} else if (((sc->quirks & DUALSHOCK4_CONTROLLER_USB) && rd[0] == 0x01 &&
 			size == 64) || ((sc->quirks & DUALSHOCK4_CONTROLLER_BT)
 			&& rd[0] == 0x11 && size == 78)) {
@@ -1208,7 +1441,7 @@ static int dualshock4_set_operational_bt(struct hid_device *hdev)
 	return ret;
 }
 
-static void sixaxis_set_leds_from_id(int id, __u8 values[MAX_LEDS])
+static void sixaxis_set_leds_from_id(struct sony_sc *sc)
 {
 	static const __u8 sixaxis_leds[10][4] = {
 				{ 0x01, 0x00, 0x00, 0x00 },
@@ -1223,16 +1456,18 @@ static void sixaxis_set_leds_from_id(int id, __u8 values[MAX_LEDS])
 				{ 0x01, 0x01, 0x01, 0x01 }
 	};
 
-	BUG_ON(MAX_LEDS < ARRAY_SIZE(sixaxis_leds[0]));
+	int id = sc->device_id;
+
+	BUILD_BUG_ON(MAX_LEDS < ARRAY_SIZE(sixaxis_leds[0]));
 
 	if (id < 0)
 		return;
 
 	id %= 10;
-	memcpy(values, sixaxis_leds[id], sizeof(sixaxis_leds[id]));
+	memcpy(sc->led_state, sixaxis_leds[id], sizeof(sixaxis_leds[id]));
 }
 
-static void dualshock4_set_leds_from_id(int id, __u8 values[MAX_LEDS])
+static void dualshock4_set_leds_from_id(struct sony_sc *sc)
 {
 	/* The first 4 color/index entries match what the PS4 assigns */
 	static const __u8 color_code[7][3] = {
@@ -1245,46 +1480,44 @@ static void dualshock4_set_leds_from_id(int id, __u8 values[MAX_LEDS])
 			/* White  */	{ 0x01, 0x01, 0x01 }
 	};
 
-	BUG_ON(MAX_LEDS < ARRAY_SIZE(color_code[0]));
+	int id = sc->device_id;
+
+	BUILD_BUG_ON(MAX_LEDS < ARRAY_SIZE(color_code[0]));
 
 	if (id < 0)
 		return;
 
 	id %= 7;
-	memcpy(values, color_code[id], sizeof(color_code[id]));
+	memcpy(sc->led_state, color_code[id], sizeof(color_code[id]));
 }
 
-static void buzz_set_leds(struct hid_device *hdev, const __u8 *leds)
+static void buzz_set_leds(struct sony_sc *sc)
 {
+	struct hid_device *hdev = sc->hdev;
 	struct list_head *report_list =
 		&hdev->report_enum[HID_OUTPUT_REPORT].report_list;
 	struct hid_report *report = list_entry(report_list->next,
 		struct hid_report, list);
 	__s32 *value = report->field[0]->value;
 
+	BUILD_BUG_ON(MAX_LEDS < 4);
+
 	value[0] = 0x00;
-	value[1] = leds[0] ? 0xff : 0x00;
-	value[2] = leds[1] ? 0xff : 0x00;
-	value[3] = leds[2] ? 0xff : 0x00;
-	value[4] = leds[3] ? 0xff : 0x00;
+	value[1] = sc->led_state[0] ? 0xff : 0x00;
+	value[2] = sc->led_state[1] ? 0xff : 0x00;
+	value[3] = sc->led_state[2] ? 0xff : 0x00;
+	value[4] = sc->led_state[3] ? 0xff : 0x00;
 	value[5] = 0x00;
 	value[6] = 0x00;
 	hid_hw_request(hdev, report, HID_REQ_SET_REPORT);
 }
 
-static void sony_set_leds(struct sony_sc *sc, const __u8 *leds, int count)
+static void sony_set_leds(struct sony_sc *sc)
 {
-	int n;
-
-	BUG_ON(count > MAX_LEDS);
-
-	if (sc->quirks & BUZZ_CONTROLLER && count == 4) {
-		buzz_set_leds(sc->hdev, leds);
-	} else {
-		for (n = 0; n < count; n++)
-			sc->led_state[n] = leds[n];
+	if (!(sc->quirks & BUZZ_CONTROLLER))
 		schedule_work(&sc->state_worker);
-	}
+	else
+		buzz_set_leds(sc);
 }
 
 static void sony_led_set_brightness(struct led_classdev *led,
@@ -1324,8 +1557,7 @@ static void sony_led_set_brightness(struct led_classdev *led,
 			drv_data->led_delay_on[n] = 0;
 			drv_data->led_delay_off[n] = 0;
 
-			sony_set_leds(drv_data, drv_data->led_state,
-					drv_data->led_count);
+			sony_set_leds(drv_data);
 			break;
 		}
 	}
@@ -1431,7 +1663,6 @@ static int sony_leds_init(struct sony_sc *sc)
 	const char *name_fmt;
 	static const char * const ds4_name_str[] = { "red", "green", "blue",
 						  "global" };
-	__u8 initial_values[MAX_LEDS] = { 0 };
 	__u8 max_brightness[MAX_LEDS] = { [0 ... (MAX_LEDS - 1)] = 1 };
 	__u8 use_hw_blink[MAX_LEDS] = { 0 };
 
@@ -1446,16 +1677,31 @@ static int sony_leds_init(struct sony_sc *sc)
 		if (!hid_validate_values(hdev, HID_OUTPUT_REPORT, 0, 0, 7))
 			return -ENODEV;
 	} else if (sc->quirks & DUALSHOCK4_CONTROLLER) {
-		dualshock4_set_leds_from_id(sc->device_id, initial_values);
-		initial_values[3] = 1;
+		dualshock4_set_leds_from_id(sc);
+		sc->led_state[3] = 1;
 		sc->led_count = 4;
 		memset(max_brightness, 255, 3);
 		use_hw_blink[3] = 1;
 		use_ds4_names = 1;
 		name_len = 0;
 		name_fmt = "%s:%s";
+	} else if (sc->quirks & MOTION_CONTROLLER) {
+		sc->led_count = 3;
+		memset(max_brightness, 255, 3);
+		use_ds4_names = 1;
+		name_len = 0;
+		name_fmt = "%s:%s";
+	} else if (sc->quirks & NAVIGATION_CONTROLLER) {
+		static const __u8 navigation_leds[4] = {0x01, 0x00, 0x00, 0x00};
+
+		memcpy(sc->led_state, navigation_leds, sizeof(navigation_leds));
+		sc->led_count = 1;
+		memset(use_hw_blink, 1, 4);
+		use_ds4_names = 0;
+		name_len = strlen("::sony#");
+		name_fmt = "%s::sony%d";
 	} else {
-		sixaxis_set_leds_from_id(sc->device_id, initial_values);
+		sixaxis_set_leds_from_id(sc);
 		sc->led_count = 4;
 		memset(use_hw_blink, 1, 4);
 		use_ds4_names = 0;
@@ -1468,7 +1714,7 @@ static int sony_leds_init(struct sony_sc *sc)
 	 * only relevant if the driver is loaded after somebody actively set the
 	 * LEDs to on
 	 */
-	sony_set_leds(sc, initial_values, sc->led_count);
+	sony_set_leds(sc);
 
 	name_sz = strlen(dev_name(&hdev->dev)) + name_len + 1;
 
@@ -1491,7 +1737,7 @@ static int sony_leds_init(struct sony_sc *sc)
 		else
 			snprintf(name, name_sz, name_fmt, dev_name(&hdev->dev), n + 1);
 		led->name = name;
-		led->brightness = initial_values[n];
+		led->brightness = sc->led_state[n];
 		led->max_brightness = max_brightness[n];
 		led->brightness_get = sony_led_get_brightness;
 		led->brightness_set = sony_led_set_brightness;
@@ -1622,9 +1868,31 @@ static void dualshock4_state_worker(struct work_struct *work)
 				HID_OUTPUT_REPORT, HID_REQ_SET_REPORT);
 }
 
+static void motion_state_worker(struct work_struct *work)
+{
+	struct sony_sc *sc = container_of(work, struct sony_sc, state_worker);
+	struct hid_device *hdev = sc->hdev;
+	struct motion_output_report_02 *report =
+		(struct motion_output_report_02 *)sc->output_report_dmabuf;
+
+	memset(report, 0, MOTION_REPORT_0x02_SIZE);
+
+	report->type = 0x02; /* set leds */
+	report->r = sc->led_state[0];
+	report->g = sc->led_state[1];
+	report->b = sc->led_state[2];
+
+#ifdef CONFIG_SONY_FF
+	report->rumble = max(sc->right, sc->left);
+#endif
+
+	hid_hw_output_report(hdev, (__u8 *)report, MOTION_REPORT_0x02_SIZE);
+}
+
 static int sony_allocate_output_report(struct sony_sc *sc)
 {
-	if (sc->quirks & SIXAXIS_CONTROLLER)
+	if ((sc->quirks & SIXAXIS_CONTROLLER) ||
+			(sc->quirks & NAVIGATION_CONTROLLER))
 		sc->output_report_dmabuf =
 			kmalloc(sizeof(union sixaxis_output_report_01),
 				GFP_KERNEL);
@@ -1634,6 +1902,9 @@ static int sony_allocate_output_report(struct sony_sc *sc)
 	else if (sc->quirks & DUALSHOCK4_CONTROLLER_USB)
 		sc->output_report_dmabuf = kmalloc(DS4_REPORT_0x05_SIZE,
 						GFP_KERNEL);
+	else if (sc->quirks & MOTION_CONTROLLER)
+		sc->output_report_dmabuf = kmalloc(MOTION_REPORT_0x02_SIZE,
+						GFP_KERNEL);
 	else
 		return 0;
 
@@ -1839,6 +2110,8 @@ static int sony_check_add(struct sony_sc *sc)
 	int n, ret;
 
 	if ((sc->quirks & DUALSHOCK4_CONTROLLER_BT) ||
+	    (sc->quirks & MOTION_CONTROLLER_BT) ||
+	    (sc->quirks & NAVIGATION_CONTROLLER_BT) ||
 	    (sc->quirks & SIXAXIS_CONTROLLER_BT)) {
 		/*
 		 * sony_get_bt_devaddr() attempts to parse the Bluetooth MAC
@@ -1871,7 +2144,8 @@ static int sony_check_add(struct sony_sc *sc)
 		}
 
 		memcpy(sc->mac_address, &buf[1], sizeof(sc->mac_address));
-	} else if (sc->quirks & SIXAXIS_CONTROLLER_USB) {
+	} else if ((sc->quirks & SIXAXIS_CONTROLLER_USB) ||
+			(sc->quirks & NAVIGATION_CONTROLLER_USB)) {
 		buf = kmalloc(SIXAXIS_REPORT_0xF2_SIZE, GFP_KERNEL);
 		if (!buf)
 			return -ENOMEM;
@@ -1993,19 +2267,20 @@ static int sony_probe(struct hid_device *hdev, const struct hid_device_id *id)
 		return ret;
 	}
 
-	ret = sony_allocate_output_report(sc);
+	ret = sony_set_device_id(sc);
 	if (ret < 0) {
-		hid_err(hdev, "failed to allocate the output report buffer\n");
+		hid_err(hdev, "failed to allocate the device id\n");
 		goto err_stop;
 	}
 
-	ret = sony_set_device_id(sc);
+	ret = sony_allocate_output_report(sc);
 	if (ret < 0) {
-		hid_err(hdev, "failed to allocate the device id\n");
+		hid_err(hdev, "failed to allocate the output report buffer\n");
 		goto err_stop;
 	}
 
-	if (sc->quirks & SIXAXIS_CONTROLLER_USB) {
+	if ((sc->quirks & SIXAXIS_CONTROLLER_USB) ||
+			(sc->quirks & NAVIGATION_CONTROLLER_USB)) {
 		/*
 		 * The Sony Sixaxis does not handle HID Output Reports on the
 		 * Interrupt EP like it could, so we need to force HID Output
@@ -2020,7 +2295,8 @@ static int sony_probe(struct hid_device *hdev, const struct hid_device_id *id)
 		hdev->quirks |= HID_QUIRK_SKIP_OUTPUT_REPORT_ID;
 		ret = sixaxis_set_operational_usb(hdev);
 		sony_init_work(sc, sixaxis_state_worker);
-	} else if (sc->quirks & SIXAXIS_CONTROLLER_BT) {
+	} else if ((sc->quirks & SIXAXIS_CONTROLLER_BT) ||
+			(sc->quirks & NAVIGATION_CONTROLLER_BT)) {
 		/*
 		 * The Sixaxis wants output reports sent on the ctrl endpoint
 		 * when connected via Bluetooth.
@@ -2043,6 +2319,8 @@ static int sony_probe(struct hid_device *hdev, const struct hid_device_id *id)
 		}
 
 		sony_init_work(sc, dualshock4_state_worker);
+	} else if (sc->quirks & MOTION_CONTROLLER) {
+		sony_init_work(sc, motion_state_worker);
 	} else {
 		ret = 0;
 	}
@@ -2122,7 +2400,13 @@ static const struct hid_device_id sony_devices[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_PS3_CONTROLLER),
 		.driver_data = SIXAXIS_CONTROLLER_USB },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_NAVIGATION_CONTROLLER),
-		.driver_data = SIXAXIS_CONTROLLER_USB },
+		.driver_data = NAVIGATION_CONTROLLER_USB },
+	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_NAVIGATION_CONTROLLER),
+		.driver_data = NAVIGATION_CONTROLLER_BT },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_MOTION_CONTROLLER),
+		.driver_data = MOTION_CONTROLLER_USB },
+	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_MOTION_CONTROLLER),
+		.driver_data = MOTION_CONTROLLER_BT },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_PS3_CONTROLLER),
 		.driver_data = SIXAXIS_CONTROLLER_BT },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_VAIO_VGX_MOUSE),
diff --git a/drivers/hid/i2c-hid/i2c-hid.c b/drivers/hid/i2c-hid/i2c-hid.c
index 92d6cdf02460..f77469d4edfb 100644
--- a/drivers/hid/i2c-hid/i2c-hid.c
+++ b/drivers/hid/i2c-hid/i2c-hid.c
@@ -42,9 +42,9 @@
 #include <linux/i2c/i2c-hid.h>
 
 /* flags */
-#define I2C_HID_STARTED		(1 << 0)
-#define I2C_HID_RESET_PENDING	(1 << 1)
-#define I2C_HID_READ_PENDING	(1 << 2)
+#define I2C_HID_STARTED		0
+#define I2C_HID_RESET_PENDING	1
+#define I2C_HID_READ_PENDING	2
 
 #define I2C_HID_PWR_ON		0x00
 #define I2C_HID_PWR_SLEEP	0x01
@@ -1019,7 +1019,6 @@ static int i2c_hid_probe(struct i2c_client *client,
 	hid->driver_data = client;
 	hid->ll_driver = &i2c_hid_ll_driver;
 	hid->dev.parent = &client->dev;
-	ACPI_COMPANION_SET(&hid->dev, ACPI_COMPANION(&client->dev));
 	hid->bus = BUS_I2C;
 	hid->version = le16_to_cpu(ihid->hdesc.bcdVersion);
 	hid->vendor = le16_to_cpu(ihid->hdesc.wVendorID);
diff --git a/drivers/hid/usbhid/hid-quirks.c b/drivers/hid/usbhid/hid-quirks.c
index 4696895eb708..53e7de7cb9e2 100644
--- a/drivers/hid/usbhid/hid-quirks.c
+++ b/drivers/hid/usbhid/hid-quirks.c
@@ -52,7 +52,6 @@ static const struct hid_blacklist {
 	{ USB_VENDOR_ID_ETURBOTOUCH, USB_DEVICE_ID_ETURBOTOUCH_2968, HID_QUIRK_MULTI_INPUT },
 	{ USB_VENDOR_ID_GREENASIA, USB_DEVICE_ID_GREENASIA_DUAL_USB_JOYPAD, HID_QUIRK_MULTI_INPUT },
 	{ USB_VENDOR_ID_PANTHERLORD, USB_DEVICE_ID_PANTHERLORD_TWIN_USB_JOYSTICK, HID_QUIRK_MULTI_INPUT | HID_QUIRK_SKIP_OUTPUT_REPORTS },
-	{ USB_VENDOR_ID_PLAYDOTCOM, USB_DEVICE_ID_PLAYDOTCOM_EMS_USBII, HID_QUIRK_MULTI_INPUT },
 	{ USB_VENDOR_ID_TOUCHPACK, USB_DEVICE_ID_TOUCHPACK_RTS, HID_QUIRK_MULTI_INPUT },
 
 	{ USB_VENDOR_ID_AIREN, USB_DEVICE_ID_AIREN_SLIMPLUS, HID_QUIRK_NOGET },
@@ -70,6 +69,7 @@ static const struct hid_blacklist {
 	{ USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_PRO_PEDALS, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_3AXIS_5BUTTON_STICK, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_AXIS_295, HID_QUIRK_NOGET },
+	{ USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_CHICONY_PIXART_USB_OPTICAL_MOUSE, HID_QUIRK_ALWAYS_POLL },
 	{ USB_VENDOR_ID_DMI, USB_DEVICE_ID_DMI_ENC, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ELAN_TOUCHSCREEN, HID_QUIRK_ALWAYS_POLL },
 	{ USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ELAN_TOUCHSCREEN_009B, HID_QUIRK_ALWAYS_POLL },
@@ -89,6 +89,7 @@ static const struct hid_blacklist {
 	{ USB_VENDOR_ID_MGE, USB_DEVICE_ID_MGE_UPS, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_3, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_3_JP, HID_QUIRK_NO_INIT_REPORTS },
+	{ USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_POWER_COVER, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_MSI, USB_DEVICE_ID_MSI_GT683R_LED_PANEL, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_NEXIO, USB_DEVICE_ID_NEXIO_MULTITOUCH_PTI0750, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_NOVATEK, USB_DEVICE_ID_NOVATEK_MOUSE, HID_QUIRK_NO_INIT_REPORTS },
@@ -141,6 +142,9 @@ static const struct hid_blacklist {
 	{ USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_QUAD_HD, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_TP_V103, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_HOLTEK_ALT, USB_DEVICE_ID_HOLTEK_ALT_KEYBOARD_A096, HID_QUIRK_NO_INIT_INPUT_REPORTS },
+	{ USB_VENDOR_ID_MULTIPLE_1781, USB_DEVICE_ID_RAPHNET_4NES4SNES_OLD, HID_QUIRK_MULTI_INPUT },
+	{ USB_VENDOR_ID_DRACAL_RAPHNET, USB_DEVICE_ID_RAPHNET_2NES2SNES, HID_QUIRK_MULTI_INPUT },
+	{ USB_VENDOR_ID_DRACAL_RAPHNET, USB_DEVICE_ID_RAPHNET_4NES4SNES, HID_QUIRK_MULTI_INPUT },
 
 	{ 0, 0 }
 };
diff --git a/drivers/hid/wacom.h b/drivers/hid/wacom.h
index 024f4d89d579..a533787a6d85 100644
--- a/drivers/hid/wacom.h
+++ b/drivers/hid/wacom.h
@@ -134,8 +134,10 @@ static inline void wacom_schedule_work(struct wacom_wac *wacom_wac)
 extern const struct hid_device_id wacom_ids[];
 
 void wacom_wac_irq(struct wacom_wac *wacom_wac, size_t len);
-void wacom_setup_device_quirks(struct wacom_features *features);
-int wacom_setup_pentouch_input_capabilities(struct input_dev *input_dev,
+void wacom_setup_device_quirks(struct wacom *wacom);
+int wacom_setup_pen_input_capabilities(struct input_dev *input_dev,
+				   struct wacom_wac *wacom_wac);
+int wacom_setup_touch_input_capabilities(struct input_dev *input_dev,
 				   struct wacom_wac *wacom_wac);
 int wacom_setup_pad_input_capabilities(struct input_dev *input_dev,
 				       struct wacom_wac *wacom_wac);
diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c
index e8607d096138..4c0ffca97bef 100644
--- a/drivers/hid/wacom_sys.c
+++ b/drivers/hid/wacom_sys.c
@@ -35,7 +35,11 @@ static int wacom_get_report(struct hid_device *hdev, u8 type, u8 *buf,
 	do {
 		retval = hid_hw_raw_request(hdev, buf[0], buf, size, type,
 				HID_REQ_GET_REPORT);
-	} while ((retval == -ETIMEDOUT || retval == -EPIPE) && --retries);
+	} while ((retval == -ETIMEDOUT || retval == -EAGAIN) && --retries);
+
+	if (retval < 0)
+		hid_err(hdev, "wacom_get_report: ran out of retries "
+			"(last error = %d)\n", retval);
 
 	return retval;
 }
@@ -48,7 +52,11 @@ static int wacom_set_report(struct hid_device *hdev, u8 type, u8 *buf,
 	do {
 		retval = hid_hw_raw_request(hdev, buf[0], buf, size, type,
 				HID_REQ_SET_REPORT);
-	} while ((retval == -ETIMEDOUT || retval == -EPIPE) && --retries);
+	} while ((retval == -ETIMEDOUT || retval == -EAGAIN) && --retries);
+
+	if (retval < 0)
+		hid_err(hdev, "wacom_set_report: ran out of retries "
+			"(last error = %d)\n", retval);
 
 	return retval;
 }
@@ -117,9 +125,16 @@ static void wacom_feature_mapping(struct hid_device *hdev,
 				break;
 			data[0] = field->report->id;
 			ret = wacom_get_report(hdev, HID_FEATURE_REPORT,
-						data, 2, 0);
-			if (ret == 2)
+						data, 2, WAC_CMD_RETRIES);
+			if (ret == 2) {
 				features->touch_max = data[1];
+			} else {
+				features->touch_max = 16;
+				hid_warn(hdev, "wacom_feature_mapping: "
+					 "could not get HID_DG_CONTACTMAX, "
+					 "defaulting to %d\n",
+					  features->touch_max);
+			}
 			kfree(data);
 		}
 		break;
@@ -181,7 +196,11 @@ static void wacom_usage_mapping(struct hid_device *hdev,
 	* X/Y values and some cases of invalid Digitizer X/Y
 	* values commonly reported.
 	*/
-	if (!pen && !finger)
+	if (pen)
+		features->device_type |= WACOM_DEVICETYPE_PEN;
+	else if (finger)
+		features->device_type |= WACOM_DEVICETYPE_TOUCH;
+	else
 		return;
 
 	/*
@@ -198,14 +217,11 @@ static void wacom_usage_mapping(struct hid_device *hdev,
 	case HID_GD_X:
 		features->x_max = field->logical_maximum;
 		if (finger) {
-			features->device_type = BTN_TOOL_FINGER;
 			features->x_phy = field->physical_maximum;
 			if (features->type != BAMBOO_PT) {
 				features->unit = field->unit;
 				features->unitExpo = field->unit_exponent;
 			}
-		} else {
-			features->device_type = BTN_TOOL_PEN;
 		}
 		break;
 	case HID_GD_Y:
@@ -237,7 +253,7 @@ static void wacom_post_parse_hid(struct hid_device *hdev,
 	if (features->type == HID_GENERIC) {
 		/* Any last-minute generic device setup */
 		if (features->touch_max > 1) {
-			input_mt_init_slots(wacom_wac->input, wacom_wac->features.touch_max,
+			input_mt_init_slots(wacom_wac->touch_input, wacom_wac->features.touch_max,
 				    INPUT_MT_DIRECT);
 		}
 	}
@@ -395,7 +411,7 @@ static int wacom_query_tablet_data(struct hid_device *hdev,
 	if (features->type == HID_GENERIC)
 		return wacom_hid_set_device_mode(hdev);
 
-	if (features->device_type == BTN_TOOL_FINGER) {
+	if (features->device_type & WACOM_DEVICETYPE_TOUCH) {
 		if (features->type > TABLETPC) {
 			/* MT Tablet PC touch */
 			return wacom_set_device_mode(hdev, 3, 4, 4);
@@ -409,7 +425,7 @@ static int wacom_query_tablet_data(struct hid_device *hdev,
 		else if (features->type == BAMBOO_PAD) {
 			return wacom_set_device_mode(hdev, 2, 2, 2);
 		}
-	} else if (features->device_type == BTN_TOOL_PEN) {
+	} else if (features->device_type & WACOM_DEVICETYPE_PEN) {
 		if (features->type <= BAMBOO_PT && features->type != WIRELESS) {
 			return wacom_set_device_mode(hdev, 2, 2, 2);
 		}
@@ -425,7 +441,6 @@ static void wacom_retrieve_hid_descriptor(struct hid_device *hdev,
 	struct usb_interface *intf = wacom->intf;
 
 	/* default features */
-	features->device_type = BTN_TOOL_PEN;
 	features->x_fuzz = 4;
 	features->y_fuzz = 4;
 	features->pressure_fuzz = 0;
@@ -439,17 +454,13 @@ static void wacom_retrieve_hid_descriptor(struct hid_device *hdev,
 	 */
 	if (features->type == WIRELESS) {
 		if (intf->cur_altsetting->desc.bInterfaceNumber == 0) {
-			features->device_type = 0;
+			features->device_type = WACOM_DEVICETYPE_NONE;
 		} else if (intf->cur_altsetting->desc.bInterfaceNumber == 2) {
-			features->device_type = BTN_TOOL_FINGER;
+			features->device_type |= WACOM_DEVICETYPE_TOUCH;
 			features->pktlen = WACOM_PKGLEN_BBTOUCH3;
 		}
 	}
 
-	/* only devices that support touch need to retrieve the info */
-	if (features->type < BAMBOO_PT)
-		return;
-
 	wacom_parse_hid(hdev, features);
 }
 
@@ -527,9 +538,9 @@ static int wacom_add_shared_data(struct hid_device *hdev)
 
 	wacom_wac->shared = &data->shared;
 
-	if (wacom_wac->features.device_type == BTN_TOOL_FINGER)
+	if (wacom_wac->features.device_type & WACOM_DEVICETYPE_TOUCH)
 		wacom_wac->shared->touch = hdev;
-	else if (wacom_wac->features.device_type == BTN_TOOL_PEN)
+	else if (wacom_wac->features.device_type & WACOM_DEVICETYPE_PEN)
 		wacom_wac->shared->pen = hdev;
 
 out:
@@ -848,6 +859,9 @@ static int wacom_initialize_leds(struct wacom *wacom)
 {
 	int error;
 
+	if (!(wacom->wacom_wac.features.device_type & WACOM_DEVICETYPE_PAD))
+		return 0;
+
 	/* Initialize default values */
 	switch (wacom->wacom_wac.features.type) {
 	case INTUOS4S:
@@ -881,17 +895,14 @@ static int wacom_initialize_leds(struct wacom *wacom)
 	case INTUOSPS:
 	case INTUOSPM:
 	case INTUOSPL:
-		if (wacom->wacom_wac.features.device_type == BTN_TOOL_PEN) {
-			wacom->led.select[0] = 0;
-			wacom->led.select[1] = 0;
-			wacom->led.llv = 32;
-			wacom->led.hlv = 0;
-			wacom->led.img_lum = 0;
-
-			error = sysfs_create_group(&wacom->hdev->dev.kobj,
-						  &intuos5_led_attr_group);
-		} else
-			return 0;
+		wacom->led.select[0] = 0;
+		wacom->led.select[1] = 0;
+		wacom->led.llv = 32;
+		wacom->led.hlv = 0;
+		wacom->led.img_lum = 0;
+
+		error = sysfs_create_group(&wacom->hdev->dev.kobj,
+					  &intuos5_led_attr_group);
 		break;
 
 	default:
@@ -914,6 +925,9 @@ static void wacom_destroy_leds(struct wacom *wacom)
 	if (!wacom->led_initialized)
 		return;
 
+	if (!(wacom->wacom_wac.features.device_type & WACOM_DEVICETYPE_PAD))
+		return;
+
 	wacom->led_initialized = false;
 
 	switch (wacom->wacom_wac.features.type) {
@@ -937,9 +951,8 @@ static void wacom_destroy_leds(struct wacom *wacom)
 	case INTUOSPS:
 	case INTUOSPM:
 	case INTUOSPL:
-		if (wacom->wacom_wac.features.device_type == BTN_TOOL_PEN)
-			sysfs_remove_group(&wacom->hdev->dev.kobj,
-					   &intuos5_led_attr_group);
+		sysfs_remove_group(&wacom->hdev->dev.kobj,
+				   &intuos5_led_attr_group);
 		break;
 	}
 }
@@ -1117,7 +1130,7 @@ static struct input_dev *wacom_allocate_input(struct wacom *wacom)
 	if (!input_dev)
 		return NULL;
 
-	input_dev->name = wacom_wac->name;
+	input_dev->name = wacom_wac->pen_name;
 	input_dev->phys = hdev->phys;
 	input_dev->dev.parent = &hdev->dev;
 	input_dev->open = wacom_open;
@@ -1136,27 +1149,33 @@ static void wacom_free_inputs(struct wacom *wacom)
 {
 	struct wacom_wac *wacom_wac = &(wacom->wacom_wac);
 
-	if (wacom_wac->input)
-		input_free_device(wacom_wac->input);
+	if (wacom_wac->pen_input)
+		input_free_device(wacom_wac->pen_input);
+	if (wacom_wac->touch_input)
+		input_free_device(wacom_wac->touch_input);
 	if (wacom_wac->pad_input)
 		input_free_device(wacom_wac->pad_input);
-	wacom_wac->input = NULL;
+	wacom_wac->pen_input = NULL;
+	wacom_wac->touch_input = NULL;
 	wacom_wac->pad_input = NULL;
 }
 
 static int wacom_allocate_inputs(struct wacom *wacom)
 {
-	struct input_dev *input_dev, *pad_input_dev;
+	struct input_dev *pen_input_dev, *touch_input_dev, *pad_input_dev;
 	struct wacom_wac *wacom_wac = &(wacom->wacom_wac);
 
-	input_dev = wacom_allocate_input(wacom);
+	pen_input_dev = wacom_allocate_input(wacom);
+	touch_input_dev = wacom_allocate_input(wacom);
 	pad_input_dev = wacom_allocate_input(wacom);
-	if (!input_dev || !pad_input_dev) {
+	if (!pen_input_dev || !touch_input_dev || !pad_input_dev) {
 		wacom_free_inputs(wacom);
 		return -ENOMEM;
 	}
 
-	wacom_wac->input = input_dev;
+	wacom_wac->pen_input = pen_input_dev;
+	wacom_wac->touch_input = touch_input_dev;
+	wacom_wac->touch_input->name = wacom_wac->touch_name;
 	wacom_wac->pad_input = pad_input_dev;
 	wacom_wac->pad_input->name = wacom_wac->pad_name;
 
@@ -1165,11 +1184,17 @@ static int wacom_allocate_inputs(struct wacom *wacom)
 
 static void wacom_clean_inputs(struct wacom *wacom)
 {
-	if (wacom->wacom_wac.input) {
-		if (wacom->wacom_wac.input_registered)
-			input_unregister_device(wacom->wacom_wac.input);
+	if (wacom->wacom_wac.pen_input) {
+		if (wacom->wacom_wac.pen_registered)
+			input_unregister_device(wacom->wacom_wac.pen_input);
 		else
-			input_free_device(wacom->wacom_wac.input);
+			input_free_device(wacom->wacom_wac.pen_input);
+	}
+	if (wacom->wacom_wac.touch_input) {
+		if (wacom->wacom_wac.touch_registered)
+			input_unregister_device(wacom->wacom_wac.touch_input);
+		else
+			input_free_device(wacom->wacom_wac.touch_input);
 	}
 	if (wacom->wacom_wac.pad_input) {
 		if (wacom->wacom_wac.pad_registered)
@@ -1177,29 +1202,49 @@ static void wacom_clean_inputs(struct wacom *wacom)
 		else
 			input_free_device(wacom->wacom_wac.pad_input);
 	}
-	wacom->wacom_wac.input = NULL;
+	wacom->wacom_wac.pen_input = NULL;
+	wacom->wacom_wac.touch_input = NULL;
 	wacom->wacom_wac.pad_input = NULL;
 	wacom_destroy_leds(wacom);
 }
 
 static int wacom_register_inputs(struct wacom *wacom)
 {
-	struct input_dev *input_dev, *pad_input_dev;
+	struct input_dev *pen_input_dev, *touch_input_dev, *pad_input_dev;
 	struct wacom_wac *wacom_wac = &(wacom->wacom_wac);
-	int error;
+	int error = 0;
 
-	input_dev = wacom_wac->input;
+	pen_input_dev = wacom_wac->pen_input;
+	touch_input_dev = wacom_wac->touch_input;
 	pad_input_dev = wacom_wac->pad_input;
 
-	if (!input_dev || !pad_input_dev)
+	if (!pen_input_dev || !touch_input_dev || !pad_input_dev)
 		return -EINVAL;
 
-	error = wacom_setup_pentouch_input_capabilities(input_dev, wacom_wac);
-	if (!error) {
-		error = input_register_device(input_dev);
+	error = wacom_setup_pen_input_capabilities(pen_input_dev, wacom_wac);
+	if (error) {
+		/* no pen in use on this interface */
+		input_free_device(pen_input_dev);
+		wacom_wac->pen_input = NULL;
+		pen_input_dev = NULL;
+	} else {
+		error = input_register_device(pen_input_dev);
+		if (error)
+			goto fail_register_pen_input;
+		wacom_wac->pen_registered = true;
+	}
+
+	error = wacom_setup_touch_input_capabilities(touch_input_dev, wacom_wac);
+	if (error) {
+		/* no touch in use on this interface */
+		input_free_device(touch_input_dev);
+		wacom_wac->touch_input = NULL;
+		touch_input_dev = NULL;
+	} else {
+		error = input_register_device(touch_input_dev);
 		if (error)
-			return error;
-		wacom_wac->input_registered = true;
+			goto fail_register_touch_input;
+		wacom_wac->touch_registered = true;
 	}
 
 	error = wacom_setup_pad_input_capabilities(pad_input_dev, wacom_wac);
@@ -1226,9 +1271,14 @@ fail_leds:
 	pad_input_dev = NULL;
 	wacom_wac->pad_registered = false;
 fail_register_pad_input:
-	input_unregister_device(input_dev);
-	wacom_wac->input = NULL;
-	wacom_wac->input_registered = false;
+	input_unregister_device(touch_input_dev);
+	wacom_wac->touch_input = NULL;
+	wacom_wac->touch_registered = false;
+fail_register_touch_input:
+	input_unregister_device(pen_input_dev);
+	wacom_wac->pen_input = NULL;
+	wacom_wac->pen_registered = false;
+fail_register_pen_input:
 	return error;
 }
 
@@ -1285,8 +1335,11 @@ static void wacom_wireless_work(struct work_struct *work)
 		/* Stylus interface */
 		wacom_wac1->features =
 			*((struct wacom_features *)id->driver_data);
-		wacom_wac1->features.device_type = BTN_TOOL_PEN;
-		snprintf(wacom_wac1->name, WACOM_NAME_MAX, "%s (WL) Pen",
+		wacom_wac1->features.device_type |= WACOM_DEVICETYPE_PEN;
+		if (wacom_wac1->features.type != INTUOSHT &&
+		    wacom_wac1->features.type != BAMBOO_PT)
+			wacom_wac1->features.device_type |= WACOM_DEVICETYPE_PAD;
+		snprintf(wacom_wac1->pen_name, WACOM_NAME_MAX, "%s (WL) Pen",
 			 wacom_wac1->features.name);
 		snprintf(wacom_wac1->pad_name, WACOM_NAME_MAX, "%s (WL) Pad",
 			 wacom_wac1->features.name);
@@ -1304,16 +1357,16 @@ static void wacom_wireless_work(struct work_struct *work)
 			wacom_wac2->features =
 				*((struct wacom_features *)id->driver_data);
 			wacom_wac2->features.pktlen = WACOM_PKGLEN_BBTOUCH3;
-			wacom_wac2->features.device_type = BTN_TOOL_FINGER;
 			wacom_wac2->features.x_max = wacom_wac2->features.y_max = 4096;
-			if (wacom_wac2->features.touch_max)
-				snprintf(wacom_wac2->name, WACOM_NAME_MAX,
-					 "%s (WL) Finger",wacom_wac2->features.name);
-			else
-				snprintf(wacom_wac2->name, WACOM_NAME_MAX,
-					 "%s (WL) Pad",wacom_wac2->features.name);
+			snprintf(wacom_wac2->touch_name, WACOM_NAME_MAX,
+				 "%s (WL) Finger",wacom_wac2->features.name);
 			snprintf(wacom_wac2->pad_name, WACOM_NAME_MAX,
-				 "%s (WL) Pad", wacom_wac2->features.name);
+				 "%s (WL) Pad",wacom_wac2->features.name);
+			if (wacom_wac1->features.touch_max)
+				wacom_wac2->features.device_type |= WACOM_DEVICETYPE_TOUCH;
+			if (wacom_wac1->features.type == INTUOSHT ||
+			    wacom_wac1->features.type == BAMBOO_PT)
+				wacom_wac2->features.device_type |= WACOM_DEVICETYPE_PAD;
 			wacom_wac2->pid = wacom_wac->pid;
 			error = wacom_allocate_inputs(wacom2) ||
 				wacom_register_inputs(wacom2);
@@ -1322,7 +1375,7 @@ static void wacom_wireless_work(struct work_struct *work)
 
 			if (wacom_wac1->features.type == INTUOSHT &&
 			    wacom_wac1->features.touch_max)
-				wacom_wac->shared->touch_input = wacom_wac2->input;
+				wacom_wac->shared->touch_input = wacom_wac2->touch_input;
 		}
 
 		error = wacom_initialize_battery(wacom);
@@ -1369,6 +1422,12 @@ static void wacom_set_default_phy(struct wacom_features *features)
 
 static void wacom_calculate_res(struct wacom_features *features)
 {
+	/* set unit to "100th of a mm" for devices not reported by HID */
+	if (!features->unit) {
+		features->unit = 0x11;
+		features->unitExpo = -3;
+	}
+
 	features->x_resolution = wacom_calc_hid_res(features->x_max,
 						    features->x_phy,
 						    features->unit,
@@ -1396,6 +1455,49 @@ static size_t wacom_compute_pktlen(struct hid_device *hdev)
 	return size;
 }
 
+static void wacom_update_name(struct wacom *wacom)
+{
+	struct wacom_wac *wacom_wac = &wacom->wacom_wac;
+	struct wacom_features *features = &wacom_wac->features;
+	char name[WACOM_NAME_MAX];
+
+	/* Generic devices name unspecified */
+	if ((features->type == HID_GENERIC) && !strcmp("Wacom HID", features->name)) {
+		if (strstr(wacom->hdev->name, "Wacom") ||
+		    strstr(wacom->hdev->name, "wacom") ||
+		    strstr(wacom->hdev->name, "WACOM")) {
+			/* name is in HID descriptor, use it */
+			strlcpy(name, wacom->hdev->name, sizeof(name));
+
+			/* strip out excess whitespaces */
+			while (1) {
+				char *gap = strstr(name, "  ");
+				if (gap == NULL)
+					break;
+				/* shift everything including the terminator */
+				memmove(gap, gap+1, strlen(gap));
+			}
+			/* get rid of trailing whitespace */
+			if (name[strlen(name)-1] == ' ')
+				name[strlen(name)-1] = '\0';
+		} else {
+			/* no meaningful name retrieved. use product ID */
+			snprintf(name, sizeof(name),
+				 "%s %X", features->name, wacom->hdev->product);
+		}
+	} else {
+		strlcpy(name, features->name, sizeof(name));
+	}
+
+	/* Append the device type to the name */
+	snprintf(wacom_wac->pen_name, sizeof(wacom_wac->pen_name),
+		"%s Pen", name);
+	snprintf(wacom_wac->touch_name, sizeof(wacom_wac->touch_name),
+		"%s Finger", name);
+	snprintf(wacom_wac->pad_name, sizeof(wacom_wac->pad_name),
+		"%s Pad", name);
+}
+
 static int wacom_probe(struct hid_device *hdev,
 		const struct hid_device_id *id)
 {
@@ -1474,64 +1576,25 @@ static int wacom_probe(struct hid_device *hdev,
 
 	/* Retrieve the physical and logical size for touch devices */
 	wacom_retrieve_hid_descriptor(hdev, features);
+	wacom_setup_device_quirks(wacom);
 
-	/*
-	 * Intuos5 has no useful data about its touch interface in its
-	 * HID descriptor. If this is the touch interface (PacketSize
-	 * of WACOM_PKGLEN_BBTOUCH3), override the table values.
-	 */
-	if (features->type >= INTUOS5S && features->type <= INTUOSHT) {
-		if (features->pktlen == WACOM_PKGLEN_BBTOUCH3) {
-			features->device_type = BTN_TOOL_FINGER;
+	if (features->device_type == WACOM_DEVICETYPE_NONE &&
+	    features->type != WIRELESS) {
+		error = features->type == HID_GENERIC ? -ENODEV : 0;
 
-			features->x_max = 4096;
-			features->y_max = 4096;
-		} else {
-			features->device_type = BTN_TOOL_PEN;
-		}
-	}
+		dev_warn(&hdev->dev, "Unknown device_type for '%s'. %s.",
+			 hdev->name,
+			 error ? "Ignoring" : "Assuming pen");
 
-	/*
-	 * Same thing for Bamboo 3rd gen.
-	 */
-	if ((features->type == BAMBOO_PT) &&
-	    (features->pktlen == WACOM_PKGLEN_BBTOUCH3) &&
-	    (features->device_type == BTN_TOOL_PEN)) {
-		features->device_type = BTN_TOOL_FINGER;
+		if (error)
+			goto fail_shared_data;
 
-		features->x_max = 4096;
-		features->y_max = 4096;
+		features->device_type |= WACOM_DEVICETYPE_PEN;
 	}
 
-	/*
-	 * Same thing for Bamboo PAD
-	 */
-	if (features->type == BAMBOO_PAD)
-		features->device_type = BTN_TOOL_FINGER;
-
-	if (hdev->bus == BUS_BLUETOOTH)
-		features->quirks |= WACOM_QUIRK_BATTERY;
-
-	wacom_setup_device_quirks(features);
-
-	/* set unit to "100th of a mm" for devices not reported by HID */
-	if (!features->unit) {
-		features->unit = 0x11;
-		features->unitExpo = -3;
-	}
 	wacom_calculate_res(features);
 
-	strlcpy(wacom_wac->name, features->name, sizeof(wacom_wac->name));
-	snprintf(wacom_wac->pad_name, sizeof(wacom_wac->pad_name),
-		"%s Pad", features->name);
-
-	/* Append the device type to the name */
-	if (features->device_type != BTN_TOOL_FINGER)
-		strlcat(wacom_wac->name, " Pen", WACOM_NAME_MAX);
-	else if (features->touch_max)
-		strlcat(wacom_wac->name, " Finger", WACOM_NAME_MAX);
-	else
-		strlcat(wacom_wac->name, " Pad", WACOM_NAME_MAX);
+	wacom_update_name(wacom);
 
 	error = wacom_add_shared_data(hdev);
 	if (error)
@@ -1574,9 +1637,9 @@ static int wacom_probe(struct hid_device *hdev,
 	if (features->quirks & WACOM_QUIRK_MONITOR)
 		error = hid_hw_open(hdev);
 
-	if (wacom_wac->features.type == INTUOSHT && wacom_wac->features.touch_max) {
-		if (wacom_wac->features.device_type == BTN_TOOL_FINGER)
-			wacom_wac->shared->touch_input = wacom_wac->input;
+	if (wacom_wac->features.type == INTUOSHT && 
+	    wacom_wac->features.device_type & WACOM_DEVICETYPE_TOUCH) {
+			wacom_wac->shared->touch_input = wacom_wac->touch_input;
 	}
 
 	return 0;
diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c
index adf959dcfa5d..232da89f4e88 100644
--- a/drivers/hid/wacom_wac.c
+++ b/drivers/hid/wacom_wac.c
@@ -69,7 +69,7 @@ static void wacom_notify_battery(struct wacom_wac *wacom_wac,
 static int wacom_penpartner_irq(struct wacom_wac *wacom)
 {
 	unsigned char *data = wacom->data;
-	struct input_dev *input = wacom->input;
+	struct input_dev *input = wacom->pen_input;
 
 	switch (data[0]) {
 	case 1:
@@ -114,7 +114,7 @@ static int wacom_pl_irq(struct wacom_wac *wacom)
 {
 	struct wacom_features *features = &wacom->features;
 	unsigned char *data = wacom->data;
-	struct input_dev *input = wacom->input;
+	struct input_dev *input = wacom->pen_input;
 	int prox, pressure;
 
 	if (data[0] != WACOM_REPORT_PENABLED) {
@@ -186,7 +186,7 @@ static int wacom_pl_irq(struct wacom_wac *wacom)
 static int wacom_ptu_irq(struct wacom_wac *wacom)
 {
 	unsigned char *data = wacom->data;
-	struct input_dev *input = wacom->input;
+	struct input_dev *input = wacom->pen_input;
 
 	if (data[0] != WACOM_REPORT_PENABLED) {
 		dev_dbg(input->dev.parent,
@@ -215,7 +215,7 @@ static int wacom_ptu_irq(struct wacom_wac *wacom)
 static int wacom_dtu_irq(struct wacom_wac *wacom)
 {
 	unsigned char *data = wacom->data;
-	struct input_dev *input = wacom->input;
+	struct input_dev *input = wacom->pen_input;
 	int prox = data[1] & 0x20;
 
 	dev_dbg(input->dev.parent,
@@ -245,7 +245,7 @@ static int wacom_dtu_irq(struct wacom_wac *wacom)
 static int wacom_dtus_irq(struct wacom_wac *wacom)
 {
 	char *data = wacom->data;
-	struct input_dev *input = wacom->input;
+	struct input_dev *input = wacom->pen_input;
 	unsigned short prox, pressure = 0;
 
 	if (data[0] != WACOM_REPORT_DTUS && data[0] != WACOM_REPORT_DTUSPAD) {
@@ -297,7 +297,7 @@ static int wacom_graphire_irq(struct wacom_wac *wacom)
 {
 	struct wacom_features *features = &wacom->features;
 	unsigned char *data = wacom->data;
-	struct input_dev *input = wacom->input;
+	struct input_dev *input = wacom->pen_input;
 	struct input_dev *pad_input = wacom->pad_input;
 	int battery_capacity, ps_connected;
 	int prox;
@@ -464,7 +464,7 @@ static int wacom_intuos_inout(struct wacom_wac *wacom)
 {
 	struct wacom_features *features = &wacom->features;
 	unsigned char *data = wacom->data;
-	struct input_dev *input = wacom->input;
+	struct input_dev *input = wacom->pen_input;
 	int idx = 0;
 
 	/* tool number */
@@ -649,7 +649,7 @@ static void wacom_intuos_general(struct wacom_wac *wacom)
 {
 	struct wacom_features *features = &wacom->features;
 	unsigned char *data = wacom->data;
-	struct input_dev *input = wacom->input;
+	struct input_dev *input = wacom->pen_input;
 	unsigned int t;
 
 	/* general pen packet */
@@ -681,7 +681,7 @@ static int wacom_intuos_irq(struct wacom_wac *wacom)
 {
 	struct wacom_features *features = &wacom->features;
 	unsigned char *data = wacom->data;
-	struct input_dev *input = wacom->input;
+	struct input_dev *input = wacom->pen_input;
 	unsigned int t;
 	int idx = 0, result;
 
@@ -1025,7 +1025,7 @@ static void wacom_intuos_bt_process_data(struct wacom_wac *wacom,
 	memcpy(wacom->data, data, 10);
 	wacom_intuos_irq(wacom);
 
-	input_sync(wacom->input);
+	input_sync(wacom->pen_input);
 	if (wacom->pad_input)
 		input_sync(wacom->pad_input);
 }
@@ -1057,7 +1057,7 @@ static int wacom_intuos_bt_irq(struct wacom_wac *wacom, size_t len)
 				     ps_connected);
 		break;
 	default:
-		dev_dbg(wacom->input->dev.parent,
+		dev_dbg(wacom->pen_input->dev.parent,
 				"Unknown report: %d,%d size:%zu\n",
 				data[0], data[1], len);
 		return 0;
@@ -1067,7 +1067,7 @@ static int wacom_intuos_bt_irq(struct wacom_wac *wacom, size_t len)
 
 static int wacom_wac_finger_count_touches(struct wacom_wac *wacom)
 {
-	struct input_dev *input = wacom->input;
+	struct input_dev *input = wacom->touch_input;
 	unsigned touch_max = wacom->features.touch_max;
 	int count = 0;
 	int i;
@@ -1075,9 +1075,8 @@ static int wacom_wac_finger_count_touches(struct wacom_wac *wacom)
 	if (!touch_max)
 		return 0;
 
-	/* non-HID_GENERIC single touch input doesn't call this routine */
-	if ((touch_max == 1) && (wacom->features.type == HID_GENERIC))
-		return wacom->hid_data.tipswitch &&
+	if (touch_max == 1)
+		return test_bit(BTN_TOUCH, input->key) &&
 		       !wacom->shared->stylus_in_proximity;
 
 	for (i = 0; i < input->mt->num_slots; i++) {
@@ -1092,7 +1091,7 @@ static int wacom_wac_finger_count_touches(struct wacom_wac *wacom)
 
 static int wacom_24hdt_irq(struct wacom_wac *wacom)
 {
-	struct input_dev *input = wacom->input;
+	struct input_dev *input = wacom->touch_input;
 	unsigned char *data = wacom->data;
 	int i;
 	int current_num_contacts = data[61];
@@ -1160,7 +1159,7 @@ static int wacom_24hdt_irq(struct wacom_wac *wacom)
 
 static int wacom_mt_touch(struct wacom_wac *wacom)
 {
-	struct input_dev *input = wacom->input;
+	struct input_dev *input = wacom->touch_input;
 	unsigned char *data = wacom->data;
 	int i;
 	int current_num_contacts = data[2];
@@ -1211,7 +1210,7 @@ static int wacom_mt_touch(struct wacom_wac *wacom)
 
 static int wacom_tpc_mt_touch(struct wacom_wac *wacom)
 {
-	struct input_dev *input = wacom->input;
+	struct input_dev *input = wacom->touch_input;
 	unsigned char *data = wacom->data;
 	int i;
 
@@ -1240,7 +1239,7 @@ static int wacom_tpc_mt_touch(struct wacom_wac *wacom)
 static int wacom_tpc_single_touch(struct wacom_wac *wacom, size_t len)
 {
 	unsigned char *data = wacom->data;
-	struct input_dev *input = wacom->input;
+	struct input_dev *input = wacom->touch_input;
 	bool prox = !wacom->shared->stylus_in_proximity;
 	int x = 0, y = 0;
 
@@ -1276,7 +1275,7 @@ static int wacom_tpc_single_touch(struct wacom_wac *wacom, size_t len)
 static int wacom_tpc_pen(struct wacom_wac *wacom)
 {
 	unsigned char *data = wacom->data;
-	struct input_dev *input = wacom->input;
+	struct input_dev *input = wacom->pen_input;
 	bool prox = data[1] & 0x20;
 
 	if (!wacom->shared->stylus_in_proximity) /* first in prox */
@@ -1305,8 +1304,12 @@ static int wacom_tpc_irq(struct wacom_wac *wacom, size_t len)
 {
 	unsigned char *data = wacom->data;
 
-	dev_dbg(wacom->input->dev.parent,
-		"%s: received report #%d\n", __func__, data[0]);
+	if (wacom->pen_input)
+		dev_dbg(wacom->pen_input->dev.parent,
+			"%s: received report #%d\n", __func__, data[0]);
+	else if (wacom->touch_input)
+		dev_dbg(wacom->touch_input->dev.parent,
+			"%s: received report #%d\n", __func__, data[0]);
 
 	switch (len) {
 	case WACOM_PKGLEN_TPC1FG:
@@ -1338,11 +1341,9 @@ static int wacom_tpc_irq(struct wacom_wac *wacom, size_t len)
 	return 0;
 }
 
-static void wacom_map_usage(struct wacom *wacom, struct hid_usage *usage,
+static void wacom_map_usage(struct input_dev *input, struct hid_usage *usage,
 		struct hid_field *field, __u8 type, __u16 code, int fuzz)
 {
-	struct wacom_wac *wacom_wac = &wacom->wacom_wac;
-	struct input_dev *input = wacom_wac->input;
 	int fmin = field->logical_minimum;
 	int fmax = field->logical_maximum;
 
@@ -1370,36 +1371,38 @@ static void wacom_wac_pen_usage_mapping(struct hid_device *hdev,
 		struct hid_field *field, struct hid_usage *usage)
 {
 	struct wacom *wacom = hid_get_drvdata(hdev);
+	struct wacom_wac *wacom_wac = &wacom->wacom_wac;
+	struct input_dev *input = wacom_wac->pen_input;
 
 	switch (usage->hid) {
 	case HID_GD_X:
-		wacom_map_usage(wacom, usage, field, EV_ABS, ABS_X, 4);
+		wacom_map_usage(input, usage, field, EV_ABS, ABS_X, 4);
 		break;
 	case HID_GD_Y:
-		wacom_map_usage(wacom, usage, field, EV_ABS, ABS_Y, 4);
+		wacom_map_usage(input, usage, field, EV_ABS, ABS_Y, 4);
 		break;
 	case HID_DG_TIPPRESSURE:
-		wacom_map_usage(wacom, usage, field, EV_ABS, ABS_PRESSURE, 0);
+		wacom_map_usage(input, usage, field, EV_ABS, ABS_PRESSURE, 0);
 		break;
 	case HID_DG_INRANGE:
-		wacom_map_usage(wacom, usage, field, EV_KEY, BTN_TOOL_PEN, 0);
+		wacom_map_usage(input, usage, field, EV_KEY, BTN_TOOL_PEN, 0);
 		break;
 	case HID_DG_INVERT:
-		wacom_map_usage(wacom, usage, field, EV_KEY,
+		wacom_map_usage(input, usage, field, EV_KEY,
 				BTN_TOOL_RUBBER, 0);
 		break;
 	case HID_DG_ERASER:
 	case HID_DG_TIPSWITCH:
-		wacom_map_usage(wacom, usage, field, EV_KEY, BTN_TOUCH, 0);
+		wacom_map_usage(input, usage, field, EV_KEY, BTN_TOUCH, 0);
 		break;
 	case HID_DG_BARRELSWITCH:
-		wacom_map_usage(wacom, usage, field, EV_KEY, BTN_STYLUS, 0);
+		wacom_map_usage(input, usage, field, EV_KEY, BTN_STYLUS, 0);
 		break;
 	case HID_DG_BARRELSWITCH2:
-		wacom_map_usage(wacom, usage, field, EV_KEY, BTN_STYLUS2, 0);
+		wacom_map_usage(input, usage, field, EV_KEY, BTN_STYLUS2, 0);
 		break;
 	case HID_DG_TOOLSERIALNUMBER:
-		wacom_map_usage(wacom, usage, field, EV_MSC, MSC_SERIAL, 0);
+		wacom_map_usage(input, usage, field, EV_MSC, MSC_SERIAL, 0);
 		break;
 	}
 }
@@ -1409,7 +1412,7 @@ static int wacom_wac_pen_event(struct hid_device *hdev, struct hid_field *field,
 {
 	struct wacom *wacom = hid_get_drvdata(hdev);
 	struct wacom_wac *wacom_wac = &wacom->wacom_wac;
-	struct input_dev *input = wacom_wac->input;
+	struct input_dev *input = wacom_wac->pen_input;
 
 	/* checking which Tool / tip switch to send */
 	switch (usage->hid) {
@@ -1439,7 +1442,7 @@ static void wacom_wac_pen_report(struct hid_device *hdev,
 {
 	struct wacom *wacom = hid_get_drvdata(hdev);
 	struct wacom_wac *wacom_wac = &wacom->wacom_wac;
-	struct input_dev *input = wacom_wac->input;
+	struct input_dev *input = wacom_wac->pen_input;
 	bool prox = wacom_wac->hid_data.inrange_state;
 
 	if (!wacom_wac->shared->stylus_in_proximity) /* first in prox */
@@ -1468,23 +1471,24 @@ static void wacom_wac_finger_usage_mapping(struct hid_device *hdev,
 	struct wacom *wacom = hid_get_drvdata(hdev);
 	struct wacom_wac *wacom_wac = &wacom->wacom_wac;
 	struct wacom_features *features = &wacom_wac->features;
+	struct input_dev *input = wacom_wac->touch_input;
 	unsigned touch_max = wacom_wac->features.touch_max;
 
 	switch (usage->hid) {
 	case HID_GD_X:
 		features->last_slot_field = usage->hid;
 		if (touch_max == 1)
-			wacom_map_usage(wacom, usage, field, EV_ABS, ABS_X, 4);
+			wacom_map_usage(input, usage, field, EV_ABS, ABS_X, 4);
 		else
-			wacom_map_usage(wacom, usage, field, EV_ABS,
+			wacom_map_usage(input, usage, field, EV_ABS,
 					ABS_MT_POSITION_X, 4);
 		break;
 	case HID_GD_Y:
 		features->last_slot_field = usage->hid;
 		if (touch_max == 1)
-			wacom_map_usage(wacom, usage, field, EV_ABS, ABS_Y, 4);
+			wacom_map_usage(input, usage, field, EV_ABS, ABS_Y, 4);
 		else
-			wacom_map_usage(wacom, usage, field, EV_ABS,
+			wacom_map_usage(input, usage, field, EV_ABS,
 					ABS_MT_POSITION_Y, 4);
 		break;
 	case HID_DG_CONTACTID:
@@ -1498,7 +1502,7 @@ static void wacom_wac_finger_usage_mapping(struct hid_device *hdev,
 		break;
 	case HID_DG_TIPSWITCH:
 		features->last_slot_field = usage->hid;
-		wacom_map_usage(wacom, usage, field, EV_KEY, BTN_TOUCH, 0);
+		wacom_map_usage(input, usage, field, EV_KEY, BTN_TOUCH, 0);
 		break;
 	}
 }
@@ -1554,7 +1558,7 @@ static int wacom_wac_finger_event(struct hid_device *hdev,
 
 	if (usage->usage_index + 1 == field->report_count) {
 		if (usage->hid == wacom_wac->features.last_slot_field)
-			wacom_wac_finger_slot(wacom_wac, wacom_wac->input);
+			wacom_wac_finger_slot(wacom_wac, wacom_wac->touch_input);
 	}
 
 	return 0;
@@ -1565,7 +1569,7 @@ static void wacom_wac_finger_report(struct hid_device *hdev,
 {
 	struct wacom *wacom = hid_get_drvdata(hdev);
 	struct wacom_wac *wacom_wac = &wacom->wacom_wac;
-	struct input_dev *input = wacom_wac->input;
+	struct input_dev *input = wacom_wac->touch_input;
 	unsigned touch_max = wacom_wac->features.touch_max;
 
 	if (touch_max > 1)
@@ -1582,10 +1586,10 @@ void wacom_wac_usage_mapping(struct hid_device *hdev,
 {
 	struct wacom *wacom = hid_get_drvdata(hdev);
 	struct wacom_wac *wacom_wac = &wacom->wacom_wac;
-	struct input_dev *input = wacom_wac->input;
 
 	/* currently, only direct devices have proper hid report descriptors */
-	__set_bit(INPUT_PROP_DIRECT, input->propbit);
+	__set_bit(INPUT_PROP_DIRECT, wacom_wac->pen_input->propbit);
+	__set_bit(INPUT_PROP_DIRECT, wacom_wac->touch_input->propbit);
 
 	if (WACOM_PEN_FIELD(field))
 		return wacom_wac_pen_usage_mapping(hdev, field, usage);
@@ -1630,7 +1634,7 @@ void wacom_wac_report(struct hid_device *hdev, struct hid_report *report)
 static int wacom_bpt_touch(struct wacom_wac *wacom)
 {
 	struct wacom_features *features = &wacom->features;
-	struct input_dev *input = wacom->input;
+	struct input_dev *input = wacom->touch_input;
 	struct input_dev *pad_input = wacom->pad_input;
 	unsigned char *data = wacom->data;
 	int i;
@@ -1678,7 +1682,7 @@ static int wacom_bpt_touch(struct wacom_wac *wacom)
 static void wacom_bpt3_touch_msg(struct wacom_wac *wacom, unsigned char *data)
 {
 	struct wacom_features *features = &wacom->features;
-	struct input_dev *input = wacom->input;
+	struct input_dev *input = wacom->touch_input;
 	bool touch = data[1] & 0x80;
 	int slot = input_mt_get_slot_by_key(input, data[0]);
 
@@ -1736,7 +1740,6 @@ static void wacom_bpt3_button_msg(struct wacom_wac *wacom, unsigned char *data)
 
 static int wacom_bpt3_touch(struct wacom_wac *wacom)
 {
-	struct input_dev *input = wacom->input;
 	unsigned char *data = wacom->data;
 	int count = data[1] & 0x07;
 	int i;
@@ -1755,8 +1758,12 @@ static int wacom_bpt3_touch(struct wacom_wac *wacom)
 			wacom_bpt3_button_msg(wacom, data + offset);
 
 	}
-	input_mt_sync_frame(input);
-	wacom->shared->touch_down = wacom_wac_finger_count_touches(wacom);
+
+	/* only update the touch if we actually have a touchpad */
+	if (wacom->touch_registered) {
+		input_mt_sync_frame(wacom->touch_input);
+		wacom->shared->touch_down = wacom_wac_finger_count_touches(wacom);
+	}
 
 	return 1;
 }
@@ -1764,7 +1771,7 @@ static int wacom_bpt3_touch(struct wacom_wac *wacom)
 static int wacom_bpt_pen(struct wacom_wac *wacom)
 {
 	struct wacom_features *features = &wacom->features;
-	struct input_dev *input = wacom->input;
+	struct input_dev *input = wacom->pen_input;
 	unsigned char *data = wacom->data;
 	int prox = 0, x = 0, y = 0, p = 0, d = 0, pen = 0, btn1 = 0, btn2 = 0;
 
@@ -1873,7 +1880,7 @@ static void wacom_bamboo_pad_pen_event(struct wacom_wac *wacom,
 static int wacom_bamboo_pad_touch_event(struct wacom_wac *wacom,
 		unsigned char *data)
 {
-	struct input_dev *input = wacom->input;
+	struct input_dev *input = wacom->touch_input;
 	unsigned char *finger_data, prefix;
 	unsigned id;
 	int x, y;
@@ -2117,7 +2124,10 @@ void wacom_wac_irq(struct wacom_wac *wacom_wac, size_t len)
 	}
 
 	if (sync) {
-		input_sync(wacom_wac->input);
+		if (wacom_wac->pen_input)
+			input_sync(wacom_wac->pen_input);
+		if (wacom_wac->touch_input)
+			input_sync(wacom_wac->touch_input);
 		if (wacom_wac->pad_input)
 			input_sync(wacom_wac->pad_input);
 	}
@@ -2125,7 +2135,7 @@ void wacom_wac_irq(struct wacom_wac *wacom_wac, size_t len)
 
 static void wacom_setup_cintiq(struct wacom_wac *wacom_wac)
 {
-	struct input_dev *input_dev = wacom_wac->input;
+	struct input_dev *input_dev = wacom_wac->pen_input;
 
 	input_set_capability(input_dev, EV_MSC, MSC_SERIAL);
 
@@ -2148,7 +2158,7 @@ static void wacom_setup_cintiq(struct wacom_wac *wacom_wac)
 
 static void wacom_setup_intuos(struct wacom_wac *wacom_wac)
 {
-	struct input_dev *input_dev = wacom_wac->input;
+	struct input_dev *input_dev = wacom_wac->pen_input;
 
 	input_set_capability(input_dev, EV_REL, REL_WHEEL);
 
@@ -2167,15 +2177,57 @@ static void wacom_setup_intuos(struct wacom_wac *wacom_wac)
 	input_set_abs_params(input_dev, ABS_THROTTLE, -1023, 1023, 0, 0);
 }
 
-void wacom_setup_device_quirks(struct wacom_features *features)
+void wacom_setup_device_quirks(struct wacom *wacom)
 {
+	struct wacom_features *features = &wacom->wacom_wac.features;
+
+	/* The pen and pad share the same interface on most devices */
+	if (features->type == GRAPHIRE_BT || features->type == WACOM_G4 ||
+	    features->type == DTUS || features->type == WACOM_MO ||
+	    (features->type >= INTUOS3S && features->type <= WACOM_13HD && 
+	     features->type != INTUOSHT)) {
+		if (features->device_type & WACOM_DEVICETYPE_PEN)
+			features->device_type |= WACOM_DEVICETYPE_PAD;
+	}
 
 	/* touch device found but size is not defined. use default */
-	if (features->device_type == BTN_TOOL_FINGER && !features->x_max) {
+	if (features->device_type & WACOM_DEVICETYPE_TOUCH && !features->x_max) {
 		features->x_max = 1023;
 		features->y_max = 1023;
 	}
 
+	/*
+	 * Intuos5/Pro and Bamboo 3rd gen have no useful data about its
+	 * touch interface in its HID descriptor. If this is the touch
+	 * interface (PacketSize of WACOM_PKGLEN_BBTOUCH3), override the
+	 * tablet values.
+	 */
+	if ((features->type >= INTUOS5S && features->type <= INTUOSHT) ||
+		(features->type == BAMBOO_PT)) {
+		if (features->pktlen == WACOM_PKGLEN_BBTOUCH3) {
+			if (features->touch_max)
+				features->device_type |= WACOM_DEVICETYPE_TOUCH;
+			if (features->type == BAMBOO_PT || features->type == INTUOSHT)
+				features->device_type |= WACOM_DEVICETYPE_PAD;
+
+			features->x_max = 4096;
+			features->y_max = 4096;
+		}
+	}
+
+	/*
+	 * Raw Wacom-mode pen and touch events both come from interface
+	 * 0, whose HID descriptor has an application usage of 0xFF0D
+	 * (i.e., WACOM_VENDORDEFINED_PEN). We route pen packets back
+	 * out through the HID_GENERIC device created for interface 1,
+	 * so rewrite this one to be of type BTN_TOOL_FINGER.
+	 */
+	if (features->type == BAMBOO_PAD)
+		features->device_type |= WACOM_DEVICETYPE_TOUCH;
+
+	if (wacom->hdev->bus == BUS_BLUETOOTH)
+		features->quirks |= WACOM_QUIRK_BATTERY;
+
 	/* quirk for bamboo touch with 2 low res touches */
 	if (features->type == BAMBOO_PT &&
 	    features->pktlen == WACOM_PKGLEN_BBTOUCH) {
@@ -2192,61 +2244,23 @@ void wacom_setup_device_quirks(struct wacom_features *features)
 		features->quirks |= WACOM_QUIRK_NO_INPUT;
 
 		/* must be monitor interface if no device_type set */
-		if (!features->device_type) {
+		if (features->device_type == WACOM_DEVICETYPE_NONE) {
 			features->quirks |= WACOM_QUIRK_MONITOR;
 			features->quirks |= WACOM_QUIRK_BATTERY;
 		}
 	}
 }
 
-static void wacom_abs_set_axis(struct input_dev *input_dev,
-			       struct wacom_wac *wacom_wac)
-{
-	struct wacom_features *features = &wacom_wac->features;
-
-	if (features->device_type == BTN_TOOL_PEN) {
-		input_set_abs_params(input_dev, ABS_X, features->x_min,
-				     features->x_max, features->x_fuzz, 0);
-		input_set_abs_params(input_dev, ABS_Y, features->y_min,
-				     features->y_max, features->y_fuzz, 0);
-		input_set_abs_params(input_dev, ABS_PRESSURE, 0,
-			features->pressure_max, features->pressure_fuzz, 0);
-
-		/* penabled devices have fixed resolution for each model */
-		input_abs_set_res(input_dev, ABS_X, features->x_resolution);
-		input_abs_set_res(input_dev, ABS_Y, features->y_resolution);
-	} else {
-		if (features->touch_max == 1) {
-			input_set_abs_params(input_dev, ABS_X, 0,
-				features->x_max, features->x_fuzz, 0);
-			input_set_abs_params(input_dev, ABS_Y, 0,
-				features->y_max, features->y_fuzz, 0);
-			input_abs_set_res(input_dev, ABS_X,
-					  features->x_resolution);
-			input_abs_set_res(input_dev, ABS_Y,
-					  features->y_resolution);
-		}
-
-		if (features->touch_max > 1) {
-			input_set_abs_params(input_dev, ABS_MT_POSITION_X, 0,
-				features->x_max, features->x_fuzz, 0);
-			input_set_abs_params(input_dev, ABS_MT_POSITION_Y, 0,
-				features->y_max, features->y_fuzz, 0);
-			input_abs_set_res(input_dev, ABS_MT_POSITION_X,
-					  features->x_resolution);
-			input_abs_set_res(input_dev, ABS_MT_POSITION_Y,
-					  features->y_resolution);
-		}
-	}
-}
-
-int wacom_setup_pentouch_input_capabilities(struct input_dev *input_dev,
+int wacom_setup_pen_input_capabilities(struct input_dev *input_dev,
 				   struct wacom_wac *wacom_wac)
 {
 	struct wacom_features *features = &wacom_wac->features;
 
 	input_dev->evbit[0] |= BIT_MASK(EV_KEY) | BIT_MASK(EV_ABS);
 
+	if (!(features->device_type & WACOM_DEVICETYPE_PEN))
+		return -ENODEV;
+
 	if (features->type == HID_GENERIC)
 		/* setup has already been done */
 		return 0;
@@ -2254,7 +2268,17 @@ int wacom_setup_pentouch_input_capabilities(struct input_dev *input_dev,
 	__set_bit(BTN_TOUCH, input_dev->keybit);
 	__set_bit(ABS_MISC, input_dev->absbit);
 
-	wacom_abs_set_axis(input_dev, wacom_wac);
+	input_set_abs_params(input_dev, ABS_X, features->x_min,
+			     features->x_max, features->x_fuzz, 0);
+	input_set_abs_params(input_dev, ABS_Y, features->y_min,
+			     features->y_max, features->y_fuzz, 0);
+	input_set_abs_params(input_dev, ABS_PRESSURE, 0,
+		features->pressure_max, features->pressure_fuzz, 0);
+
+	/* penabled devices have fixed resolution for each model */
+	input_abs_set_res(input_dev, ABS_X, features->x_resolution);
+	input_abs_set_res(input_dev, ABS_Y, features->y_resolution);
+
 
 	switch (features->type) {
 	case GRAPHIRE_BT:
@@ -2323,53 +2347,25 @@ int wacom_setup_pentouch_input_capabilities(struct input_dev *input_dev,
 	case INTUOSPS:
 		__set_bit(INPUT_PROP_POINTER, input_dev->propbit);
 
-		if (features->device_type == BTN_TOOL_PEN) {
-			input_set_abs_params(input_dev, ABS_DISTANCE, 0,
-					      features->distance_max,
-					      0, 0);
-
-			input_set_abs_params(input_dev, ABS_Z, -900, 899, 0, 0);
-			input_abs_set_res(input_dev, ABS_Z, 287);
+		input_set_abs_params(input_dev, ABS_DISTANCE, 0,
+				      features->distance_max,
+				      0, 0);
 
-			wacom_setup_intuos(wacom_wac);
-		} else if (features->device_type == BTN_TOOL_FINGER) {
-			__clear_bit(ABS_MISC, input_dev->absbit);
+		input_set_abs_params(input_dev, ABS_Z, -900, 899, 0, 0);
+		input_abs_set_res(input_dev, ABS_Z, 287);
 
-			input_set_abs_params(input_dev, ABS_MT_TOUCH_MAJOR,
-			                     0, features->x_max, 0, 0);
-			input_set_abs_params(input_dev, ABS_MT_TOUCH_MINOR,
-			                     0, features->y_max, 0, 0);
-			input_mt_init_slots(input_dev, features->touch_max, INPUT_MT_POINTER);
-		}
+		wacom_setup_intuos(wacom_wac);
 		break;
 
 	case WACOM_24HDT:
-		if (features->device_type == BTN_TOOL_FINGER) {
-			input_set_abs_params(input_dev, ABS_MT_TOUCH_MAJOR, 0, features->x_max, 0, 0);
-			input_set_abs_params(input_dev, ABS_MT_WIDTH_MAJOR, 0, features->x_max, 0, 0);
-			input_set_abs_params(input_dev, ABS_MT_WIDTH_MINOR, 0, features->y_max, 0, 0);
-			input_set_abs_params(input_dev, ABS_MT_ORIENTATION, 0, 1, 0, 0);
-		}
-		/* fall through */
-
 	case WACOM_27QHDT:
 	case MTSCREEN:
 	case MTTPC:
 	case MTTPC_B:
 	case TABLETPC2FG:
-		if (features->device_type == BTN_TOOL_FINGER && features->touch_max > 1)
-			input_mt_init_slots(input_dev, features->touch_max, INPUT_MT_DIRECT);
-		/* fall through */
-
 	case TABLETPC:
 	case TABLETPCE:
 		__clear_bit(ABS_MISC, input_dev->absbit);
-
-		__set_bit(INPUT_PROP_DIRECT, input_dev->propbit);
-
-		if (features->device_type != BTN_TOOL_PEN)
-			break;  /* no need to process stylus stuff */
-
 		/* fall through */
 
 	case DTUS:
@@ -2397,50 +2393,114 @@ int wacom_setup_pentouch_input_capabilities(struct input_dev *input_dev,
 		break;
 
 	case INTUOSHT:
-		if (features->touch_max &&
-		    features->device_type == BTN_TOOL_FINGER) {
-			input_dev->evbit[0] |= BIT_MASK(EV_SW);
-			__set_bit(SW_MUTE_DEVICE, input_dev->swbit);
-		}
-		/* fall through */
-
 	case BAMBOO_PT:
 		__clear_bit(ABS_MISC, input_dev->absbit);
 
-		if (features->device_type == BTN_TOOL_FINGER) {
+		__set_bit(INPUT_PROP_POINTER, input_dev->propbit);
+		__set_bit(BTN_TOOL_RUBBER, input_dev->keybit);
+		__set_bit(BTN_TOOL_PEN, input_dev->keybit);
+		__set_bit(BTN_STYLUS, input_dev->keybit);
+		__set_bit(BTN_STYLUS2, input_dev->keybit);
+		input_set_abs_params(input_dev, ABS_DISTANCE, 0,
+				      features->distance_max,
+				      0, 0);
+		break;
+	case BAMBOO_PAD:
+		__clear_bit(ABS_MISC, input_dev->absbit);
+		break;
+	}
+	return 0;
+}
 
-			if (features->touch_max) {
-				if (features->pktlen == WACOM_PKGLEN_BBTOUCH3) {
-					input_set_abs_params(input_dev,
-						     ABS_MT_TOUCH_MAJOR,
-						     0, features->x_max, 0, 0);
-					input_set_abs_params(input_dev,
-						     ABS_MT_TOUCH_MINOR,
-						     0, features->y_max, 0, 0);
-				}
-				input_mt_init_slots(input_dev, features->touch_max, INPUT_MT_POINTER);
-			} else {
-				/* buttons/keys only interface */
-				__clear_bit(ABS_X, input_dev->absbit);
-				__clear_bit(ABS_Y, input_dev->absbit);
-				__clear_bit(BTN_TOUCH, input_dev->keybit);
+int wacom_setup_touch_input_capabilities(struct input_dev *input_dev,
+					 struct wacom_wac *wacom_wac)
+{
+	struct wacom_features *features = &wacom_wac->features;
 
-				/* PAD is setup by wacom_setup_pad_input_capabilities later */
-				return 1;
-			}
-		} else if (features->device_type == BTN_TOOL_PEN) {
-			__set_bit(INPUT_PROP_POINTER, input_dev->propbit);
-			__set_bit(BTN_TOOL_RUBBER, input_dev->keybit);
-			__set_bit(BTN_TOOL_PEN, input_dev->keybit);
-			__set_bit(BTN_STYLUS, input_dev->keybit);
-			__set_bit(BTN_STYLUS2, input_dev->keybit);
-			input_set_abs_params(input_dev, ABS_DISTANCE, 0,
-					      features->distance_max,
-					      0, 0);
+	input_dev->evbit[0] |= BIT_MASK(EV_KEY) | BIT_MASK(EV_ABS);
+
+	if (!(features->device_type & WACOM_DEVICETYPE_TOUCH))
+		return -ENODEV;
+
+	if (features->type == HID_GENERIC)
+		/* setup has already been done */
+		return 0;
+
+	__set_bit(BTN_TOUCH, input_dev->keybit);
+
+	if (features->touch_max == 1) {
+		input_set_abs_params(input_dev, ABS_X, 0,
+			features->x_max, features->x_fuzz, 0);
+		input_set_abs_params(input_dev, ABS_Y, 0,
+			features->y_max, features->y_fuzz, 0);
+		input_abs_set_res(input_dev, ABS_X,
+				  features->x_resolution);
+		input_abs_set_res(input_dev, ABS_Y,
+				  features->y_resolution);
+	}
+	else if (features->touch_max > 1) {
+		input_set_abs_params(input_dev, ABS_MT_POSITION_X, 0,
+			features->x_max, features->x_fuzz, 0);
+		input_set_abs_params(input_dev, ABS_MT_POSITION_Y, 0,
+			features->y_max, features->y_fuzz, 0);
+		input_abs_set_res(input_dev, ABS_MT_POSITION_X,
+				  features->x_resolution);
+		input_abs_set_res(input_dev, ABS_MT_POSITION_Y,
+				  features->y_resolution);
+	}
+
+	switch (features->type) {
+	case INTUOS5:
+	case INTUOS5L:
+	case INTUOSPM:
+	case INTUOSPL:
+	case INTUOS5S:
+	case INTUOSPS:
+		__set_bit(INPUT_PROP_POINTER, input_dev->propbit);
+
+		input_set_abs_params(input_dev, ABS_MT_TOUCH_MAJOR, 0, features->x_max, 0, 0);
+		input_set_abs_params(input_dev, ABS_MT_TOUCH_MINOR, 0, features->y_max, 0, 0);
+		input_mt_init_slots(input_dev, features->touch_max, INPUT_MT_POINTER);
+		break;
+
+	case WACOM_24HDT:
+		input_set_abs_params(input_dev, ABS_MT_TOUCH_MAJOR, 0, features->x_max, 0, 0);
+		input_set_abs_params(input_dev, ABS_MT_WIDTH_MAJOR, 0, features->x_max, 0, 0);
+		input_set_abs_params(input_dev, ABS_MT_WIDTH_MINOR, 0, features->y_max, 0, 0);
+		input_set_abs_params(input_dev, ABS_MT_ORIENTATION, 0, 1, 0, 0);
+		/* fall through */
+
+	case WACOM_27QHDT:
+	case MTSCREEN:
+	case MTTPC:
+	case MTTPC_B:
+	case TABLETPC2FG:
+		input_mt_init_slots(input_dev, features->touch_max, INPUT_MT_DIRECT);
+		/*fall through */
+
+	case TABLETPC:
+	case TABLETPCE:
+		__set_bit(INPUT_PROP_DIRECT, input_dev->propbit);
+		break;
+
+	case INTUOSHT:
+		input_dev->evbit[0] |= BIT_MASK(EV_SW);
+		__set_bit(SW_MUTE_DEVICE, input_dev->swbit);
+		/* fall through */
+
+	case BAMBOO_PT:
+		if (features->pktlen == WACOM_PKGLEN_BBTOUCH3) {
+			input_set_abs_params(input_dev,
+				     ABS_MT_TOUCH_MAJOR,
+				     0, features->x_max, 0, 0);
+			input_set_abs_params(input_dev,
+				     ABS_MT_TOUCH_MINOR,
+				     0, features->y_max, 0, 0);
 		}
+		input_mt_init_slots(input_dev, features->touch_max, INPUT_MT_POINTER);
 		break;
+
 	case BAMBOO_PAD:
-		__clear_bit(ABS_MISC, input_dev->absbit);
 		input_mt_init_slots(input_dev, features->touch_max,
 				    INPUT_MT_POINTER);
 		__set_bit(BTN_LEFT, input_dev->keybit);
@@ -2456,6 +2516,9 @@ int wacom_setup_pad_input_capabilities(struct input_dev *input_dev,
 	struct wacom_features *features = &wacom_wac->features;
 	int i;
 
+	if (!(features->device_type & WACOM_DEVICETYPE_PAD))
+		return -ENODEV;
+
 	input_dev->evbit[0] |= BIT_MASK(EV_KEY) | BIT_MASK(EV_ABS);
 
 	/* kept for making legacy xf86-input-wacom working with the wheels */
@@ -2592,10 +2655,6 @@ int wacom_setup_pad_input_capabilities(struct input_dev *input_dev,
 
 	case INTUOS5S:
 	case INTUOSPS:
-		/* touch interface does not have the pad device */
-		if (features->device_type != BTN_TOOL_PEN)
-			return -ENODEV;
-
 		for (i = 0; i < 7; i++)
 			__set_bit(BTN_0 + i, input_dev->keybit);
 
@@ -2637,12 +2696,6 @@ int wacom_setup_pad_input_capabilities(struct input_dev *input_dev,
 
 	case INTUOSHT:
 	case BAMBOO_PT:
-		/* pad device is on the touch interface */
-		if ((features->device_type != BTN_TOOL_FINGER) ||
-		    /* Bamboo Pen only tablet does not have pad */
-		    ((features->type == BAMBOO_PT) && !features->touch_max))
-			return -ENODEV;
-
 		__clear_bit(ABS_MISC, input_dev->absbit);
 
 		__set_bit(BTN_LEFT, input_dev->keybit);
@@ -2922,6 +2975,9 @@ static const struct wacom_features wacom_features_0x32F =
 	{ "Wacom DTU1031X", 22472, 12728, 511, 0,
 	  DTUSX, WACOM_INTUOS_RES, WACOM_INTUOS_RES,
 	  WACOM_DTU_OFFSET, WACOM_DTU_OFFSET };
+static const struct wacom_features wacom_features_0x336 =
+	{ "Wacom DTU1141", 23472, 13203, 1023, 0,
+	  DTUS, WACOM_INTUOS_RES, WACOM_INTUOS_RES };
 static const struct wacom_features wacom_features_0x57 =
 	{ "Wacom DTK2241", 95640, 54060, 2047, 63,
 	  DTK, WACOM_INTUOS3_RES, WACOM_INTUOS3_RES,
@@ -3275,6 +3331,7 @@ const struct hid_device_id wacom_ids[] = {
 	{ USB_DEVICE_WACOM(0x32F) },
 	{ USB_DEVICE_WACOM(0x333) },
 	{ USB_DEVICE_WACOM(0x335) },
+	{ USB_DEVICE_WACOM(0x336) },
 	{ USB_DEVICE_WACOM(0x4001) },
 	{ USB_DEVICE_WACOM(0x4004) },
 	{ USB_DEVICE_WACOM(0x5000) },
diff --git a/drivers/hid/wacom_wac.h b/drivers/hid/wacom_wac.h
index 4700ac994a3b..2978c303909d 100644
--- a/drivers/hid/wacom_wac.h
+++ b/drivers/hid/wacom_wac.h
@@ -18,10 +18,7 @@
 #define WACOM_NAME_MAX		64
 
 /* packet length for individual models */
-#define WACOM_PKGLEN_PENPRTN	 7
-#define WACOM_PKGLEN_GRAPHIRE	 8
 #define WACOM_PKGLEN_BBFUN	 9
-#define WACOM_PKGLEN_INTUOS	10
 #define WACOM_PKGLEN_TPC1FG	 5
 #define WACOM_PKGLEN_TPC1FG_B	10
 #define WACOM_PKGLEN_TPC2FG	14
@@ -29,9 +26,6 @@
 #define WACOM_PKGLEN_BBTOUCH3	64
 #define WACOM_PKGLEN_BBPEN	10
 #define WACOM_PKGLEN_WIRELESS	32
-#define WACOM_PKGLEN_MTOUCH	62
-#define WACOM_PKGLEN_MTTPC	40
-#define WACOM_PKGLEN_DTUS	68
 #define WACOM_PKGLEN_PENABLED	 8
 #define WACOM_PKGLEN_BPAD_TOUCH	32
 #define WACOM_PKGLEN_BPAD_TOUCH_USB	64
@@ -78,10 +72,20 @@
 #define WACOM_QUIRK_MONITOR		0x0004
 #define WACOM_QUIRK_BATTERY		0x0008
 
+/* device types */
+#define WACOM_DEVICETYPE_NONE           0x0000
+#define WACOM_DEVICETYPE_PEN            0x0001
+#define WACOM_DEVICETYPE_TOUCH          0x0002
+#define WACOM_DEVICETYPE_PAD            0x0004
+
+#define WACOM_VENDORDEFINED_PEN		0xff0d0001
+
 #define WACOM_PEN_FIELD(f)	(((f)->logical == HID_DG_STYLUS) || \
 				 ((f)->physical == HID_DG_STYLUS) || \
 				 ((f)->physical == HID_DG_PEN) || \
-				 ((f)->application == HID_DG_PEN))
+				 ((f)->application == HID_DG_PEN) || \
+				 ((f)->application == HID_DG_DIGITIZER) || \
+				 ((f)->application == WACOM_VENDORDEFINED_PEN))
 #define WACOM_FINGER_FIELD(f)	(((f)->logical == HID_DG_FINGER) || \
 				 ((f)->physical == HID_DG_FINGER) || \
 				 ((f)->application == HID_DG_TOUCHSCREEN))
@@ -192,7 +196,8 @@ struct hid_data {
 };
 
 struct wacom_wac {
-	char name[WACOM_NAME_MAX];
+	char pen_name[WACOM_NAME_MAX];
+	char touch_name[WACOM_NAME_MAX];
 	char pad_name[WACOM_NAME_MAX];
 	char bat_name[WACOM_NAME_MAX];
 	char ac_name[WACOM_NAME_MAX];
@@ -203,9 +208,11 @@ struct wacom_wac {
 	bool reporting_data;
 	struct wacom_features features;
 	struct wacom_shared *shared;
-	struct input_dev *input;
+	struct input_dev *pen_input;
+	struct input_dev *touch_input;
 	struct input_dev *pad_input;
-	bool input_registered;
+	bool pen_registered;
+	bool touch_registered;
 	bool pad_registered;
 	int pid;
 	int battery_capacity;
diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig
index 25d9e72627e9..54075a07d2a1 100644
--- a/drivers/hwmon/Kconfig
+++ b/drivers/hwmon/Kconfig
@@ -509,7 +509,7 @@ config SENSORS_G762
 
 config SENSORS_GPIO_FAN
 	tristate "GPIO fan"
-	depends on GPIOLIB
+	depends on GPIOLIB || COMPILE_TEST
 	depends on THERMAL || THERMAL=n
 	help
 	  If you say yes here you get support for fans connected to GPIO lines.
@@ -1106,8 +1106,8 @@ config SENSORS_NTC_THERMISTOR
 	  send notifications about the temperature.
 
 	  Currently, this driver supports
-	  NCP15WB473, NCP18WB473, NCP21WB473, NCP03WB473, and NCP15WL333
-	  from Murata and B57330V2103 from EPCOS.
+	  NCP15WB473, NCP18WB473, NCP21WB473, NCP03WB473, NCP15WL333,
+	  and NCP03WF104 from Murata and B57330V2103 from EPCOS.
 
 	  This driver can also be built as a module.  If so, the module
 	  will be called ntc-thermistor.
@@ -1186,7 +1186,7 @@ config SENSORS_PWM_FAN
 
 config SENSORS_SHT15
 	tristate "Sensiron humidity and temperature sensors. SHT15 and compat."
-	depends on GPIOLIB
+	depends on GPIOLIB || COMPILE_TEST
 	help
 	  If you say yes here you get support for the Sensiron SHT10, SHT11,
 	  SHT15, SHT71, SHT75 humidity and temperature sensors.
@@ -1452,6 +1452,16 @@ config SENSORS_INA2XX
 	  This driver can also be built as a module.  If so, the module
 	  will be called ina2xx.
 
+config SENSORS_TC74
+	tristate "Microchip TC74"
+	depends on I2C
+	help
+	  If you say yes here you get support for Microchip TC74 single
+	  input temperature sensor chips.
+
+	  This driver can also be built as a module.  If so, the module
+	  will be called tc74.
+
 config SENSORS_THMC50
 	tristate "Texas Instruments THMC50 / Analog Devices ADM1022"
 	depends on I2C
diff --git a/drivers/hwmon/Makefile b/drivers/hwmon/Makefile
index b4a40f17e2aa..ab904027f074 100644
--- a/drivers/hwmon/Makefile
+++ b/drivers/hwmon/Makefile
@@ -140,6 +140,7 @@ obj-$(CONFIG_SENSORS_SMSC47B397)+= smsc47b397.o
 obj-$(CONFIG_SENSORS_SMSC47M1)	+= smsc47m1.o
 obj-$(CONFIG_SENSORS_SMSC47M192)+= smsc47m192.o
 obj-$(CONFIG_SENSORS_AMC6821)	+= amc6821.o
+obj-$(CONFIG_SENSORS_TC74)	+= tc74.o
 obj-$(CONFIG_SENSORS_THMC50)	+= thmc50.o
 obj-$(CONFIG_SENSORS_TMP102)	+= tmp102.o
 obj-$(CONFIG_SENSORS_TMP103)	+= tmp103.o
diff --git a/drivers/hwmon/atxp1.c b/drivers/hwmon/atxp1.c
index 4c829bb2f9db..f2f2f2fc755a 100644
--- a/drivers/hwmon/atxp1.c
+++ b/drivers/hwmon/atxp1.c
@@ -12,10 +12,9 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
+ * The ATXP1 can reside on I2C addresses 0x37 or 0x4e. The chip is
+ * not auto-detected by the driver and must be instantiated explicitly.
+ * See Documentation/i2c/instantiating-devices for more information.
  */
 
 #include <linux/kernel.h>
@@ -43,8 +42,6 @@ MODULE_AUTHOR("Sebastian Witt <se.witt@gmx.net>");
 #define ATXP1_VIDMASK	0x1f
 #define ATXP1_GPIO1MASK	0x0f
 
-static const unsigned short normal_i2c[] = { 0x37, 0x4e, I2C_CLIENT_END };
-
 struct atxp1_data {
 	struct i2c_client *client;
 	struct mutex update_lock;
@@ -259,48 +256,6 @@ static struct attribute *atxp1_attrs[] = {
 };
 ATTRIBUTE_GROUPS(atxp1);
 
-/* Return 0 if detection is successful, -ENODEV otherwise */
-static int atxp1_detect(struct i2c_client *new_client,
-			struct i2c_board_info *info)
-{
-	struct i2c_adapter *adapter = new_client->adapter;
-
-	u8 temp;
-
-	if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_BYTE_DATA))
-		return -ENODEV;
-
-	/* Detect ATXP1, checking if vendor ID registers are all zero */
-	if (!((i2c_smbus_read_byte_data(new_client, 0x3e) == 0) &&
-	     (i2c_smbus_read_byte_data(new_client, 0x3f) == 0) &&
-	     (i2c_smbus_read_byte_data(new_client, 0xfe) == 0) &&
-	     (i2c_smbus_read_byte_data(new_client, 0xff) == 0)))
-		return -ENODEV;
-
-	/*
-	 * No vendor ID, now checking if registers 0x10,0x11 (non-existent)
-	 * showing the same as register 0x00
-	 */
-	temp = i2c_smbus_read_byte_data(new_client, 0x00);
-
-	if (!((i2c_smbus_read_byte_data(new_client, 0x10) == temp) &&
-	      (i2c_smbus_read_byte_data(new_client, 0x11) == temp)))
-		return -ENODEV;
-
-	/* Get VRM */
-	temp = vid_which_vrm();
-
-	if ((temp != 90) && (temp != 91)) {
-		dev_err(&adapter->dev, "atxp1: Not supporting VRM %d.%d\n",
-				temp / 10, temp % 10);
-		return -ENODEV;
-	}
-
-	strlcpy(info->type, "atxp1", I2C_NAME_SIZE);
-
-	return 0;
-}
-
 static int atxp1_probe(struct i2c_client *client,
 		       const struct i2c_device_id *id)
 {
@@ -314,6 +269,11 @@ static int atxp1_probe(struct i2c_client *client,
 
 	/* Get VRM */
 	data->vrm = vid_which_vrm();
+	if (data->vrm != 90 && data->vrm != 91) {
+		dev_err(dev, "atxp1: Not supporting VRM %d.%d\n",
+			data->vrm / 10, data->vrm % 10);
+		return -ENODEV;
+	}
 
 	data->client = client;
 	mutex_init(&data->update_lock);
@@ -342,8 +302,6 @@ static struct i2c_driver atxp1_driver = {
 	},
 	.probe		= atxp1_probe,
 	.id_table	= atxp1_id,
-	.detect		= atxp1_detect,
-	.address_list	= normal_i2c,
 };
 
 module_i2c_driver(atxp1_driver);
diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c
index ed303ba3a593..3e03379e7c5d 100644
--- a/drivers/hwmon/coretemp.c
+++ b/drivers/hwmon/coretemp.c
@@ -63,7 +63,8 @@ MODULE_PARM_DESC(tjmax, "TjMax value in degrees Celsius");
 #define TO_ATTR_NO(cpu)		(TO_CORE_ID(cpu) + BASE_SYSFS_ATTR_NO)
 
 #ifdef CONFIG_SMP
-#define for_each_sibling(i, cpu)	for_each_cpu(i, cpu_sibling_mask(cpu))
+#define for_each_sibling(i, cpu) \
+	for_each_cpu(i, topology_sibling_cpumask(cpu))
 #else
 #define for_each_sibling(i, cpu)	for (i = 0; false; )
 #endif
diff --git a/drivers/hwmon/max197.c b/drivers/hwmon/max197.c
index cb0dcfda958c..07628569547a 100644
--- a/drivers/hwmon/max197.c
+++ b/drivers/hwmon/max197.c
@@ -324,7 +324,7 @@ static int max197_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static struct platform_device_id max197_device_ids[] = {
+static const struct platform_device_id max197_device_ids[] = {
 	{ "max197", max197 },
 	{ "max199", max199 },
 	{ }
diff --git a/drivers/hwmon/ntc_thermistor.c b/drivers/hwmon/ntc_thermistor.c
index 68800115876b..dc0b76c5e302 100644
--- a/drivers/hwmon/ntc_thermistor.c
+++ b/drivers/hwmon/ntc_thermistor.c
@@ -53,6 +53,7 @@ static const struct platform_device_id ntc_thermistor_id[] = {
 	{ "ncp03wb473", TYPE_NCPXXWB473 },
 	{ "ncp15wl333", TYPE_NCPXXWL333 },
 	{ "b57330v2103", TYPE_B57330V2103},
+	{ "ncp03wf104", TYPE_NCPXXWF104 },
 	{ },
 };
 
@@ -135,6 +136,43 @@ static const struct ntc_compensation ncpXXwl333[] = {
 	{ .temp_c	= 125, .ohm	= 707 },
 };
 
+static const struct ntc_compensation ncpXXwf104[] = {
+	{ .temp_c	= -40, .ohm	= 4397119 },
+	{ .temp_c	= -35, .ohm	= 3088599 },
+	{ .temp_c	= -30, .ohm	= 2197225 },
+	{ .temp_c	= -25, .ohm	= 1581881 },
+	{ .temp_c	= -20, .ohm	= 1151037 },
+	{ .temp_c	= -15, .ohm	= 846579 },
+	{ .temp_c	= -10, .ohm	= 628988 },
+	{ .temp_c	= -5, .ohm	= 471632 },
+	{ .temp_c	= 0, .ohm	= 357012 },
+	{ .temp_c	= 5, .ohm	= 272500 },
+	{ .temp_c	= 10, .ohm	= 209710 },
+	{ .temp_c	= 15, .ohm	= 162651 },
+	{ .temp_c	= 20, .ohm	= 127080 },
+	{ .temp_c	= 25, .ohm	= 100000 },
+	{ .temp_c	= 30, .ohm	= 79222 },
+	{ .temp_c	= 35, .ohm	= 63167 },
+	{ .temp_c	= 40, .ohm	= 50677 },
+	{ .temp_c	= 45, .ohm	= 40904 },
+	{ .temp_c	= 50, .ohm	= 33195 },
+	{ .temp_c	= 55, .ohm	= 27091 },
+	{ .temp_c	= 60, .ohm	= 22224 },
+	{ .temp_c	= 65, .ohm	= 18323 },
+	{ .temp_c	= 70, .ohm	= 15184 },
+	{ .temp_c	= 75, .ohm	= 12635 },
+	{ .temp_c	= 80, .ohm	= 10566 },
+	{ .temp_c	= 85, .ohm	= 8873 },
+	{ .temp_c	= 90, .ohm	= 7481 },
+	{ .temp_c	= 95, .ohm	= 6337 },
+	{ .temp_c	= 100, .ohm	= 5384 },
+	{ .temp_c	= 105, .ohm	= 4594 },
+	{ .temp_c	= 110, .ohm	= 3934 },
+	{ .temp_c	= 115, .ohm	= 3380 },
+	{ .temp_c	= 120, .ohm	= 2916 },
+	{ .temp_c	= 125, .ohm	= 2522 },
+};
+
 /*
  * The following compensation table is from the specification of EPCOS NTC
  * Thermistors Datasheet
@@ -190,20 +228,21 @@ struct ntc_data {
 static int ntc_adc_iio_read(struct ntc_thermistor_platform_data *pdata)
 {
 	struct iio_channel *channel = pdata->chan;
-	s64 result;
-	int val, ret;
+	int raw, uv, ret;
 
-	ret = iio_read_channel_raw(channel, &val);
+	ret = iio_read_channel_raw(channel, &raw);
 	if (ret < 0) {
 		pr_err("read channel() error: %d\n", ret);
 		return ret;
 	}
 
-	/* unit: mV */
-	result = pdata->pullup_uv * (s64) val;
-	result >>= 12;
+	ret = iio_convert_raw_to_processed(channel, raw, &uv, 1000);
+	if (ret < 0) {
+		/* Assume 12 bit ADC with vref at pullup_uv */
+		uv = (pdata->pullup_uv * (s64)raw) >> 12;
+	}
 
-	return (int)result;
+	return uv;
 }
 
 static const struct of_device_id ntc_match[] = {
@@ -219,6 +258,8 @@ static const struct of_device_id ntc_match[] = {
 		.data = &ntc_thermistor_id[4] },
 	{ .compatible = "epcos,b57330v2103",
 		.data = &ntc_thermistor_id[5]},
+	{ .compatible = "murata,ncp03wf104",
+		.data = &ntc_thermistor_id[6] },
 
 	/* Usage of vendor name "ntc" is deprecated */
 	{ .compatible = "ntc,ncp15wb473",
@@ -309,30 +350,27 @@ static inline u64 div64_u64_safe(u64 dividend, u64 divisor)
 static int get_ohm_of_thermistor(struct ntc_data *data, unsigned int uv)
 {
 	struct ntc_thermistor_platform_data *pdata = data->pdata;
-	u64 mv = uv / 1000;
-	u64 pmv = pdata->pullup_uv / 1000;
+	u32 puv = pdata->pullup_uv;
 	u64 n, puo, pdo;
 	puo = pdata->pullup_ohm;
 	pdo = pdata->pulldown_ohm;
 
-	if (mv == 0) {
-		if (pdata->connect == NTC_CONNECTED_POSITIVE)
-			return INT_MAX;
-		return 0;
-	}
-	if (mv >= pmv)
+	if (uv == 0)
+		return (pdata->connect == NTC_CONNECTED_POSITIVE) ?
+			INT_MAX : 0;
+	if (uv >= puv)
 		return (pdata->connect == NTC_CONNECTED_POSITIVE) ?
 			0 : INT_MAX;
 
 	if (pdata->connect == NTC_CONNECTED_POSITIVE && puo == 0)
-		n = div64_u64_safe(pdo * (pmv - mv), mv);
+		n = div_u64(pdo * (puv - uv), uv);
 	else if (pdata->connect == NTC_CONNECTED_GROUND && pdo == 0)
-		n = div64_u64_safe(puo * mv, pmv - mv);
+		n = div_u64(puo * uv, puv - uv);
 	else if (pdata->connect == NTC_CONNECTED_POSITIVE)
-		n = div64_u64_safe(pdo * puo * (pmv - mv),
-				puo * mv - pdo * (pmv - mv));
+		n = div64_u64_safe(pdo * puo * (puv - uv),
+				puo * uv - pdo * (puv - uv));
 	else
-		n = div64_u64_safe(pdo * puo * mv, pdo * (pmv - mv) - puo * mv);
+		n = div64_u64_safe(pdo * puo * uv, pdo * (puv - uv) - puo * uv);
 
 	if (n > INT_MAX)
 		n = INT_MAX;
@@ -567,6 +605,10 @@ static int ntc_thermistor_probe(struct platform_device *pdev)
 		data->comp = b57330v2103;
 		data->n_comp = ARRAY_SIZE(b57330v2103);
 		break;
+	case TYPE_NCPXXWF104:
+		data->comp = ncpXXwf104;
+		data->n_comp = ARRAY_SIZE(ncpXXwf104);
+		break;
 	default:
 		dev_err(&pdev->dev, "Unknown device type: %lu(%s)\n",
 				pdev_id->driver_data, pdev_id->name);
diff --git a/drivers/hwmon/sht15.c b/drivers/hwmon/sht15.c
index d4f0935daaa1..497a7f822a12 100644
--- a/drivers/hwmon/sht15.c
+++ b/drivers/hwmon/sht15.c
@@ -1074,7 +1074,7 @@ static int sht15_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static struct platform_device_id sht15_device_ids[] = {
+static const struct platform_device_id sht15_device_ids[] = {
 	{ "sht10", sht10 },
 	{ "sht11", sht11 },
 	{ "sht15", sht15 },
diff --git a/drivers/hwmon/tc74.c b/drivers/hwmon/tc74.c
new file mode 100644
index 000000000000..d95165158800
--- /dev/null
+++ b/drivers/hwmon/tc74.c
@@ -0,0 +1,177 @@
+/*
+ * An hwmon driver for the Microchip TC74
+ *
+ * Copyright 2015 Maciej Szmigiero <mail@maciej.szmigiero.name>
+ *
+ * Based on ad7414.c:
+ *	Copyright 2006 Stefan Roese, DENX Software Engineering
+ *	Copyright 2008 Sean MacLennan, PIKA Technologies
+ *	Copyright 2008 Frank Edelhaeuser, Spansion Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/bitops.h>
+#include <linux/err.h>
+#include <linux/hwmon.h>
+#include <linux/hwmon-sysfs.h>
+#include <linux/i2c.h>
+#include <linux/jiffies.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/sysfs.h>
+
+/* TC74 registers */
+#define TC74_REG_TEMP		0x00
+#define TC74_REG_CONFIG		0x01
+
+struct tc74_data {
+	struct i2c_client	*client;
+	struct mutex		lock;	/* atomic read data updates */
+	bool			valid;	/* validity of fields below */
+	unsigned long		next_update;	/* In jiffies */
+	s8			temp_input;	/* Temp value in dC */
+};
+
+static int tc74_update_device(struct device *dev)
+{
+	struct tc74_data *data = dev_get_drvdata(dev);
+	struct i2c_client *client = data->client;
+	int ret;
+
+	ret = mutex_lock_interruptible(&data->lock);
+	if (ret)
+		return ret;
+
+	if (time_after(jiffies, data->next_update) || !data->valid) {
+		s32 value;
+
+		value = i2c_smbus_read_byte_data(client, TC74_REG_CONFIG);
+		if (value < 0) {
+			dev_dbg(&client->dev, "TC74_REG_CONFIG read err %d\n",
+				(int)value);
+
+			ret = value;
+			goto ret_unlock;
+		}
+
+		if (!(value & BIT(6))) {
+			/* not ready yet */
+
+			ret = -EAGAIN;
+			goto ret_unlock;
+		}
+
+		value = i2c_smbus_read_byte_data(client, TC74_REG_TEMP);
+		if (value < 0) {
+			dev_dbg(&client->dev, "TC74_REG_TEMP read err %d\n",
+				(int)value);
+
+			ret = value;
+			goto ret_unlock;
+		}
+
+		data->temp_input = value;
+		data->next_update = jiffies + HZ / 4;
+		data->valid = true;
+	}
+
+ret_unlock:
+	mutex_unlock(&data->lock);
+
+	return ret;
+}
+
+static ssize_t show_temp_input(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	struct tc74_data *data = dev_get_drvdata(dev);
+	int ret;
+
+	ret = tc74_update_device(dev);
+	if (ret)
+		return ret;
+
+	return sprintf(buf, "%d\n", data->temp_input * 1000);
+}
+static SENSOR_DEVICE_ATTR(temp1_input, S_IRUGO, show_temp_input, NULL, 0);
+
+static struct attribute *tc74_attrs[] = {
+	&sensor_dev_attr_temp1_input.dev_attr.attr,
+	NULL
+};
+
+ATTRIBUTE_GROUPS(tc74);
+
+static int tc74_probe(struct i2c_client *client,
+		      const struct i2c_device_id *dev_id)
+{
+	struct device *dev = &client->dev;
+	struct tc74_data *data;
+	struct device *hwmon_dev;
+	s32 conf;
+
+	if (!i2c_check_functionality(client->adapter, I2C_FUNC_SMBUS_BYTE_DATA))
+		return -EOPNOTSUPP;
+
+	data = devm_kzalloc(dev, sizeof(struct tc74_data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->client = client;
+	mutex_init(&data->lock);
+
+	/* Make sure the chip is powered up. */
+	conf = i2c_smbus_read_byte_data(client, TC74_REG_CONFIG);
+	if (conf < 0) {
+		dev_err(dev, "unable to read config register\n");
+
+		return conf;
+	}
+
+	if (conf & 0x3f) {
+		dev_err(dev, "invalid config register value\n");
+
+		return -ENODEV;
+	}
+
+	if (conf & BIT(7)) {
+		s32 ret;
+
+		conf &= ~BIT(7);
+
+		ret = i2c_smbus_write_byte_data(client, TC74_REG_CONFIG, conf);
+		if (ret)
+			dev_warn(dev, "unable to disable STANDBY\n");
+	}
+
+	hwmon_dev = devm_hwmon_device_register_with_groups(dev,
+							   client->name,
+							   data, tc74_groups);
+	return PTR_ERR_OR_ZERO(hwmon_dev);
+}
+
+static const struct i2c_device_id tc74_id[] = {
+	{ "tc74", 0 },
+	{}
+};
+MODULE_DEVICE_TABLE(i2c, tc74_id);
+
+static struct i2c_driver tc74_driver = {
+	.driver = {
+		.name	= "tc74",
+	},
+	.probe	= tc74_probe,
+	.id_table = tc74_id,
+};
+
+module_i2c_driver(tc74_driver);
+
+MODULE_AUTHOR("Maciej Szmigiero <mail@maciej.szmigiero.name>");
+
+MODULE_DESCRIPTION("TC74 driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/i2c/busses/i2c-piix4.c b/drivers/i2c/busses/i2c-piix4.c
index 67cbec6796a0..630bce68bf38 100644
--- a/drivers/i2c/busses/i2c-piix4.c
+++ b/drivers/i2c/busses/i2c-piix4.c
@@ -245,7 +245,7 @@ static int piix4_setup_sb800(struct pci_dev *PIIX4_dev,
 	     PIIX4_dev->device == PCI_DEVICE_ID_AMD_HUDSON2_SMBUS &&
 	     PIIX4_dev->revision >= 0x41) ||
 	    (PIIX4_dev->vendor == PCI_VENDOR_ID_AMD &&
-	     PIIX4_dev->device == 0x790b &&
+	     PIIX4_dev->device == PCI_DEVICE_ID_AMD_KERNCZ_SMBUS &&
 	     PIIX4_dev->revision >= 0x49))
 		smb_en = 0x00;
 	else
@@ -545,7 +545,7 @@ static const struct pci_device_id piix4_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_IXP400_SMBUS) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_SBX00_SMBUS) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_HUDSON2_SMBUS) },
-	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, 0x790b) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_KERNCZ_SMBUS) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_SERVERWORKS,
 		     PCI_DEVICE_ID_SERVERWORKS_OSB4) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_SERVERWORKS,
diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c
index 987c124432c5..fc2ee8213fb6 100644
--- a/drivers/i2c/i2c-core.c
+++ b/drivers/i2c/i2c-core.c
@@ -107,7 +107,7 @@ static int acpi_i2c_add_resource(struct acpi_resource *ares, void *data)
 			if (sb->access_mode == ACPI_I2C_10BIT_MODE)
 				info->flags |= I2C_CLIENT_TEN;
 		}
-	} else if (info->irq < 0) {
+	} else if (!info->irq) {
 		struct resource r;
 
 		if (acpi_dev_resource_interrupt(ares, 0, &r))
@@ -134,7 +134,6 @@ static acpi_status acpi_i2c_add_device(acpi_handle handle, u32 level,
 
 	memset(&info, 0, sizeof(info));
 	info.fwnode = acpi_fwnode_handle(adev);
-	info.irq = -1;
 
 	INIT_LIST_HEAD(&resource_list);
 	ret = acpi_dev_get_resources(adev, &resource_list,
@@ -632,8 +631,13 @@ static int i2c_device_probe(struct device *dev)
 	if (!client)
 		return 0;
 
-	if (!client->irq && dev->of_node) {
-		int irq = of_irq_get(dev->of_node, 0);
+	if (!client->irq) {
+		int irq = -ENOENT;
+
+		if (dev->of_node)
+			irq = of_irq_get(dev->of_node, 0);
+		else if (ACPI_COMPANION(dev))
+			irq = acpi_dev_gpio_irq_get(ACPI_COMPANION(dev), 0);
 
 		if (irq == -EPROBE_DEFER)
 			return irq;
diff --git a/drivers/infiniband/hw/ipath/Kconfig b/drivers/infiniband/hw/ipath/Kconfig
index 1d9bb115cbf6..8fe54ff00580 100644
--- a/drivers/infiniband/hw/ipath/Kconfig
+++ b/drivers/infiniband/hw/ipath/Kconfig
@@ -9,3 +9,6 @@ config INFINIBAND_IPATH
 	as IP-over-InfiniBand as well as with userspace applications
 	(in conjunction with InfiniBand userspace access).
 	For QLogic PCIe QLE based cards, use the QIB driver instead.
+
+	If you have this hardware you will need to boot with PAT disabled
+	on your x86-64 systems, use the nopat kernel parameter.
diff --git a/drivers/infiniband/hw/ipath/ipath_driver.c b/drivers/infiniband/hw/ipath/ipath_driver.c
index bd0caedafe99..2d7e503d13cb 100644
--- a/drivers/infiniband/hw/ipath/ipath_driver.c
+++ b/drivers/infiniband/hw/ipath/ipath_driver.c
@@ -42,6 +42,9 @@
 #include <linux/bitmap.h>
 #include <linux/slab.h>
 #include <linux/module.h>
+#ifdef CONFIG_X86_64
+#include <asm/pat.h>
+#endif
 
 #include "ipath_kernel.h"
 #include "ipath_verbs.h"
@@ -395,6 +398,14 @@ static int ipath_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	unsigned long long addr;
 	u32 bar0 = 0, bar1 = 0;
 
+#ifdef CONFIG_X86_64
+	if (WARN(pat_enabled(),
+		 "ipath needs PAT disabled, boot with nopat kernel parameter\n")) {
+		ret = -ENODEV;
+		goto bail;
+	}
+#endif
+
 	dd = ipath_alloc_devdata(pdev);
 	if (IS_ERR(dd)) {
 		ret = PTR_ERR(dd);
@@ -542,6 +553,7 @@ static int ipath_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	dd->ipath_kregbase = __ioremap(addr, len,
 		(_PAGE_NO_CACHE|_PAGE_WRITETHRU));
 #else
+	/* XXX: split this properly to enable on PAT */
 	dd->ipath_kregbase = ioremap_nocache(addr, len);
 #endif
 
@@ -587,12 +599,8 @@ static int ipath_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	ret = ipath_enable_wc(dd);
 
-	if (ret) {
-		ipath_dev_err(dd, "Write combining not enabled "
-			      "(err %d): performance may be poor\n",
-			      -ret);
+	if (ret)
 		ret = 0;
-	}
 
 	ipath_verify_pioperf(dd);
 
diff --git a/drivers/infiniband/hw/ipath/ipath_kernel.h b/drivers/infiniband/hw/ipath/ipath_kernel.h
index e08db7020cd4..f0f947122779 100644
--- a/drivers/infiniband/hw/ipath/ipath_kernel.h
+++ b/drivers/infiniband/hw/ipath/ipath_kernel.h
@@ -463,9 +463,7 @@ struct ipath_devdata {
 	/* offset in HT config space of slave/primary interface block */
 	u8 ipath_ht_slave_off;
 	/* for write combining settings */
-	unsigned long ipath_wc_cookie;
-	unsigned long ipath_wc_base;
-	unsigned long ipath_wc_len;
+	int wc_cookie;
 	/* ref count for each pkey */
 	atomic_t ipath_pkeyrefs[4];
 	/* shadow copy of struct page *'s for exp tid pages */
diff --git a/drivers/infiniband/hw/ipath/ipath_wc_x86_64.c b/drivers/infiniband/hw/ipath/ipath_wc_x86_64.c
index 4ad0b932df1f..7b6e4c843e19 100644
--- a/drivers/infiniband/hw/ipath/ipath_wc_x86_64.c
+++ b/drivers/infiniband/hw/ipath/ipath_wc_x86_64.c
@@ -37,7 +37,6 @@
  */
 
 #include <linux/pci.h>
-#include <asm/mtrr.h>
 #include <asm/processor.h>
 
 #include "ipath_kernel.h"
@@ -122,27 +121,14 @@ int ipath_enable_wc(struct ipath_devdata *dd)
 	}
 
 	if (!ret) {
-		int cookie;
-		ipath_cdbg(VERBOSE, "Setting mtrr for chip to WC "
-			   "(addr %llx, len=0x%llx)\n",
-			   (unsigned long long) pioaddr,
-			   (unsigned long long) piolen);
-		cookie = mtrr_add(pioaddr, piolen, MTRR_TYPE_WRCOMB, 0);
-		if (cookie < 0) {
-			{
-				dev_info(&dd->pcidev->dev,
-					 "mtrr_add()  WC for PIO bufs "
-					 "failed (%d)\n",
-					 cookie);
-				ret = -EINVAL;
-			}
-		} else {
-			ipath_cdbg(VERBOSE, "Set mtrr for chip to WC, "
-				   "cookie is %d\n", cookie);
-			dd->ipath_wc_cookie = cookie;
-			dd->ipath_wc_base = (unsigned long) pioaddr;
-			dd->ipath_wc_len = (unsigned long) piolen;
-		}
+		dd->wc_cookie = arch_phys_wc_add(pioaddr, piolen);
+		if (dd->wc_cookie < 0) {
+			ipath_dev_err(dd, "Seting mtrr failed on PIO buffers\n");
+			ret = -ENODEV;
+		} else if (dd->wc_cookie == 0)
+			ipath_cdbg(VERBOSE, "Set mtrr for chip to WC not needed\n");
+		else
+			ipath_cdbg(VERBOSE, "Set mtrr for chip to WC\n");
 	}
 
 	return ret;
@@ -154,16 +140,5 @@ int ipath_enable_wc(struct ipath_devdata *dd)
  */
 void ipath_disable_wc(struct ipath_devdata *dd)
 {
-	if (dd->ipath_wc_cookie) {
-		int r;
-		ipath_cdbg(VERBOSE, "undoing WCCOMB on pio buffers\n");
-		r = mtrr_del(dd->ipath_wc_cookie, dd->ipath_wc_base,
-			     dd->ipath_wc_len);
-		if (r < 0)
-			dev_info(&dd->pcidev->dev,
-				 "mtrr_del(%lx, %lx, %lx) failed: %d\n",
-				 dd->ipath_wc_cookie, dd->ipath_wc_base,
-				 dd->ipath_wc_len, r);
-		dd->ipath_wc_cookie = 0; /* even on failure */
-	}
+	arch_phys_wc_del(dd->wc_cookie);
 }
diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index 3f40319a55da..575a072d765f 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -65,6 +65,8 @@ static int
 isert_rdma_accept(struct isert_conn *isert_conn);
 struct rdma_cm_id *isert_setup_id(struct isert_np *isert_np);
 
+static void isert_release_work(struct work_struct *work);
+
 static inline bool
 isert_prot_cmd(struct isert_conn *conn, struct se_cmd *cmd)
 {
@@ -648,6 +650,7 @@ isert_init_conn(struct isert_conn *isert_conn)
 	mutex_init(&isert_conn->mutex);
 	spin_lock_init(&isert_conn->pool_lock);
 	INIT_LIST_HEAD(&isert_conn->fr_pool);
+	INIT_WORK(&isert_conn->release_work, isert_release_work);
 }
 
 static void
@@ -925,6 +928,7 @@ isert_disconnected_handler(struct rdma_cm_id *cma_id,
 {
 	struct isert_np *isert_np = cma_id->context;
 	struct isert_conn *isert_conn;
+	bool terminating = false;
 
 	if (isert_np->np_cm_id == cma_id)
 		return isert_np_cma_handler(cma_id->context, event);
@@ -932,12 +936,25 @@ isert_disconnected_handler(struct rdma_cm_id *cma_id,
 	isert_conn = cma_id->qp->qp_context;
 
 	mutex_lock(&isert_conn->mutex);
+	terminating = (isert_conn->state == ISER_CONN_TERMINATING);
 	isert_conn_terminate(isert_conn);
 	mutex_unlock(&isert_conn->mutex);
 
 	isert_info("conn %p completing wait\n", isert_conn);
 	complete(&isert_conn->wait);
 
+	if (terminating)
+		goto out;
+
+	mutex_lock(&isert_np->np_accept_mutex);
+	if (!list_empty(&isert_conn->accept_node)) {
+		list_del_init(&isert_conn->accept_node);
+		isert_put_conn(isert_conn);
+		queue_work(isert_release_wq, &isert_conn->release_work);
+	}
+	mutex_unlock(&isert_np->np_accept_mutex);
+
+out:
 	return 0;
 }
 
@@ -2380,7 +2397,6 @@ isert_build_rdma_wr(struct isert_conn *isert_conn, struct isert_cmd *isert_cmd,
 	page_off = offset % PAGE_SIZE;
 
 	send_wr->sg_list = ib_sge;
-	send_wr->num_sge = sg_nents;
 	send_wr->wr_id = (uintptr_t)&isert_cmd->tx_desc;
 	/*
 	 * Perform mapping of TCM scatterlist memory ib_sge dma_addr.
@@ -2400,14 +2416,17 @@ isert_build_rdma_wr(struct isert_conn *isert_conn, struct isert_cmd *isert_cmd,
 			  ib_sge->addr, ib_sge->length, ib_sge->lkey);
 		page_off = 0;
 		data_left -= ib_sge->length;
+		if (!data_left)
+			break;
 		ib_sge++;
 		isert_dbg("Incrementing ib_sge pointer to %p\n", ib_sge);
 	}
 
+	send_wr->num_sge = ++i;
 	isert_dbg("Set outgoing sg_list: %p num_sg: %u from TCM SGLs\n",
 		  send_wr->sg_list, send_wr->num_sge);
 
-	return sg_nents;
+	return send_wr->num_sge;
 }
 
 static int
@@ -3366,7 +3385,6 @@ static void isert_wait_conn(struct iscsi_conn *conn)
 	isert_wait4flush(isert_conn);
 	isert_wait4logout(isert_conn);
 
-	INIT_WORK(&isert_conn->release_work, isert_release_work);
 	queue_work(isert_release_wq, &isert_conn->release_work);
 }
 
@@ -3374,6 +3392,7 @@ static void isert_free_conn(struct iscsi_conn *conn)
 {
 	struct isert_conn *isert_conn = conn->context;
 
+	isert_wait4flush(isert_conn);
 	isert_put_conn(isert_conn);
 }
 
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index e1c7e9e51045..fffea87a014f 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -34,6 +34,7 @@
 #include <linux/irq.h>
 #include <linux/msi.h>
 #include <linux/dma-contiguous.h>
+#include <linux/irqdomain.h>
 #include <asm/irq_remapping.h>
 #include <asm/io_apic.h>
 #include <asm/apic.h>
@@ -3852,6 +3853,21 @@ union irte {
 	} fields;
 };
 
+struct irq_2_irte {
+	u16 devid; /* Device ID for IRTE table */
+	u16 index; /* Index into IRTE table*/
+};
+
+struct amd_ir_data {
+	struct irq_2_irte			irq_2_irte;
+	union irte				irte_entry;
+	union {
+		struct msi_msg			msi_entry;
+	};
+};
+
+static struct irq_chip amd_ir_chip;
+
 #define DTE_IRQ_PHYS_ADDR_MASK	(((1ULL << 45)-1) << 6)
 #define DTE_IRQ_REMAP_INTCTL    (2ULL << 60)
 #define DTE_IRQ_TABLE_LEN       (8ULL << 1)
@@ -3945,7 +3961,7 @@ out_unlock:
 	return table;
 }
 
-static int alloc_irq_index(struct irq_cfg *cfg, u16 devid, int count)
+static int alloc_irq_index(u16 devid, int count)
 {
 	struct irq_remap_table *table;
 	unsigned long flags;
@@ -3967,18 +3983,10 @@ static int alloc_irq_index(struct irq_cfg *cfg, u16 devid, int count)
 			c = 0;
 
 		if (c == count)	{
-			struct irq_2_irte *irte_info;
-
 			for (; c != 0; --c)
 				table->table[index - c + 1] = IRTE_ALLOCATED;
 
 			index -= count - 1;
-
-			cfg->remapped	      = 1;
-			irte_info             = &cfg->irq_2_irte;
-			irte_info->devid      = devid;
-			irte_info->index      = index;
-
 			goto out;
 		}
 	}
@@ -3991,22 +3999,6 @@ out:
 	return index;
 }
 
-static int get_irte(u16 devid, int index, union irte *irte)
-{
-	struct irq_remap_table *table;
-	unsigned long flags;
-
-	table = get_irq_table(devid, false);
-	if (!table)
-		return -ENOMEM;
-
-	spin_lock_irqsave(&table->lock, flags);
-	irte->val = table->table[index];
-	spin_unlock_irqrestore(&table->lock, flags);
-
-	return 0;
-}
-
 static int modify_irte(u16 devid, int index, union irte irte)
 {
 	struct irq_remap_table *table;
@@ -4053,243 +4045,316 @@ static void free_irte(u16 devid, int index)
 	iommu_completion_wait(iommu);
 }
 
-static int setup_ioapic_entry(int irq, struct IO_APIC_route_entry *entry,
-			      unsigned int destination, int vector,
-			      struct io_apic_irq_attr *attr)
+static int get_devid(struct irq_alloc_info *info)
 {
-	struct irq_remap_table *table;
-	struct irq_2_irte *irte_info;
-	struct irq_cfg *cfg;
-	union irte irte;
-	int ioapic_id;
-	int index;
-	int devid;
-	int ret;
-
-	cfg = irq_cfg(irq);
-	if (!cfg)
-		return -EINVAL;
-
-	irte_info = &cfg->irq_2_irte;
-	ioapic_id = mpc_ioapic_id(attr->ioapic);
-	devid     = get_ioapic_devid(ioapic_id);
-
-	if (devid < 0)
-		return devid;
-
-	table = get_irq_table(devid, true);
-	if (table == NULL)
-		return -ENOMEM;
-
-	index = attr->ioapic_pin;
+	int devid = -1;
 
-	/* Setup IRQ remapping info */
-	cfg->remapped	      = 1;
-	irte_info->devid      = devid;
-	irte_info->index      = index;
+	switch (info->type) {
+	case X86_IRQ_ALLOC_TYPE_IOAPIC:
+		devid     = get_ioapic_devid(info->ioapic_id);
+		break;
+	case X86_IRQ_ALLOC_TYPE_HPET:
+		devid     = get_hpet_devid(info->hpet_id);
+		break;
+	case X86_IRQ_ALLOC_TYPE_MSI:
+	case X86_IRQ_ALLOC_TYPE_MSIX:
+		devid = get_device_id(&info->msi_dev->dev);
+		break;
+	default:
+		BUG_ON(1);
+		break;
+	}
 
-	/* Setup IRTE for IOMMU */
-	irte.val		= 0;
-	irte.fields.vector      = vector;
-	irte.fields.int_type    = apic->irq_delivery_mode;
-	irte.fields.destination = destination;
-	irte.fields.dm          = apic->irq_dest_mode;
-	irte.fields.valid       = 1;
-
-	ret = modify_irte(devid, index, irte);
-	if (ret)
-		return ret;
+	return devid;
+}
 
-	/* Setup IOAPIC entry */
-	memset(entry, 0, sizeof(*entry));
+static struct irq_domain *get_ir_irq_domain(struct irq_alloc_info *info)
+{
+	struct amd_iommu *iommu;
+	int devid;
 
-	entry->vector        = index;
-	entry->mask          = 0;
-	entry->trigger       = attr->trigger;
-	entry->polarity      = attr->polarity;
+	if (!info)
+		return NULL;
 
-	/*
-	 * Mask level triggered irqs.
-	 */
-	if (attr->trigger)
-		entry->mask = 1;
+	devid = get_devid(info);
+	if (devid >= 0) {
+		iommu = amd_iommu_rlookup_table[devid];
+		if (iommu)
+			return iommu->ir_domain;
+	}
 
-	return 0;
+	return NULL;
 }
 
-static int set_affinity(struct irq_data *data, const struct cpumask *mask,
-			bool force)
+static struct irq_domain *get_irq_domain(struct irq_alloc_info *info)
 {
-	struct irq_2_irte *irte_info;
-	unsigned int dest, irq;
-	struct irq_cfg *cfg;
-	union irte irte;
-	int err;
-
-	if (!config_enabled(CONFIG_SMP))
-		return -1;
-
-	cfg       = irqd_cfg(data);
-	irq       = data->irq;
-	irte_info = &cfg->irq_2_irte;
+	struct amd_iommu *iommu;
+	int devid;
 
-	if (!cpumask_intersects(mask, cpu_online_mask))
-		return -EINVAL;
+	if (!info)
+		return NULL;
 
-	if (get_irte(irte_info->devid, irte_info->index, &irte))
-		return -EBUSY;
+	switch (info->type) {
+	case X86_IRQ_ALLOC_TYPE_MSI:
+	case X86_IRQ_ALLOC_TYPE_MSIX:
+		devid = get_device_id(&info->msi_dev->dev);
+		if (devid >= 0) {
+			iommu = amd_iommu_rlookup_table[devid];
+			if (iommu)
+				return iommu->msi_domain;
+		}
+		break;
+	default:
+		break;
+	}
 
-	if (assign_irq_vector(irq, cfg, mask))
-		return -EBUSY;
+	return NULL;
+}
 
-	err = apic->cpu_mask_to_apicid_and(cfg->domain, mask, &dest);
-	if (err) {
-		if (assign_irq_vector(irq, cfg, data->affinity))
-			pr_err("AMD-Vi: Failed to recover vector for irq %d\n", irq);
-		return err;
-	}
+struct irq_remap_ops amd_iommu_irq_ops = {
+	.prepare		= amd_iommu_prepare,
+	.enable			= amd_iommu_enable,
+	.disable		= amd_iommu_disable,
+	.reenable		= amd_iommu_reenable,
+	.enable_faulting	= amd_iommu_enable_faulting,
+	.get_ir_irq_domain	= get_ir_irq_domain,
+	.get_irq_domain		= get_irq_domain,
+};
 
-	irte.fields.vector      = cfg->vector;
-	irte.fields.destination = dest;
+static void irq_remapping_prepare_irte(struct amd_ir_data *data,
+				       struct irq_cfg *irq_cfg,
+				       struct irq_alloc_info *info,
+				       int devid, int index, int sub_handle)
+{
+	struct irq_2_irte *irte_info = &data->irq_2_irte;
+	struct msi_msg *msg = &data->msi_entry;
+	union irte *irte = &data->irte_entry;
+	struct IO_APIC_route_entry *entry;
 
-	modify_irte(irte_info->devid, irte_info->index, irte);
+	data->irq_2_irte.devid = devid;
+	data->irq_2_irte.index = index + sub_handle;
 
-	if (cfg->move_in_progress)
-		send_cleanup_vector(cfg);
+	/* Setup IRTE for IOMMU */
+	irte->val = 0;
+	irte->fields.vector      = irq_cfg->vector;
+	irte->fields.int_type    = apic->irq_delivery_mode;
+	irte->fields.destination = irq_cfg->dest_apicid;
+	irte->fields.dm          = apic->irq_dest_mode;
+	irte->fields.valid       = 1;
+
+	switch (info->type) {
+	case X86_IRQ_ALLOC_TYPE_IOAPIC:
+		/* Setup IOAPIC entry */
+		entry = info->ioapic_entry;
+		info->ioapic_entry = NULL;
+		memset(entry, 0, sizeof(*entry));
+		entry->vector        = index;
+		entry->mask          = 0;
+		entry->trigger       = info->ioapic_trigger;
+		entry->polarity      = info->ioapic_polarity;
+		/* Mask level triggered irqs. */
+		if (info->ioapic_trigger)
+			entry->mask = 1;
+		break;
 
-	cpumask_copy(data->affinity, mask);
+	case X86_IRQ_ALLOC_TYPE_HPET:
+	case X86_IRQ_ALLOC_TYPE_MSI:
+	case X86_IRQ_ALLOC_TYPE_MSIX:
+		msg->address_hi = MSI_ADDR_BASE_HI;
+		msg->address_lo = MSI_ADDR_BASE_LO;
+		msg->data = irte_info->index;
+		break;
 
-	return 0;
+	default:
+		BUG_ON(1);
+		break;
+	}
 }
 
-static int free_irq(int irq)
+static int irq_remapping_alloc(struct irq_domain *domain, unsigned int virq,
+			       unsigned int nr_irqs, void *arg)
 {
-	struct irq_2_irte *irte_info;
+	struct irq_alloc_info *info = arg;
+	struct irq_data *irq_data;
+	struct amd_ir_data *data;
 	struct irq_cfg *cfg;
+	int i, ret, devid;
+	int index = -1;
 
-	cfg = irq_cfg(irq);
-	if (!cfg)
+	if (!info)
+		return -EINVAL;
+	if (nr_irqs > 1 && info->type != X86_IRQ_ALLOC_TYPE_MSI &&
+	    info->type != X86_IRQ_ALLOC_TYPE_MSIX)
 		return -EINVAL;
 
-	irte_info = &cfg->irq_2_irte;
-
-	free_irte(irte_info->devid, irte_info->index);
+	/*
+	 * With IRQ remapping enabled, don't need contiguous CPU vectors
+	 * to support multiple MSI interrupts.
+	 */
+	if (info->type == X86_IRQ_ALLOC_TYPE_MSI)
+		info->flags &= ~X86_IRQ_ALLOC_CONTIGUOUS_VECTORS;
 
-	return 0;
-}
+	devid = get_devid(info);
+	if (devid < 0)
+		return -EINVAL;
 
-static void compose_msi_msg(struct pci_dev *pdev,
-			    unsigned int irq, unsigned int dest,
-			    struct msi_msg *msg, u8 hpet_id)
-{
-	struct irq_2_irte *irte_info;
-	struct irq_cfg *cfg;
-	union irte irte;
+	ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, arg);
+	if (ret < 0)
+		return ret;
 
-	cfg = irq_cfg(irq);
-	if (!cfg)
-		return;
+	ret = -ENOMEM;
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		goto out_free_parent;
 
-	irte_info = &cfg->irq_2_irte;
+	if (info->type == X86_IRQ_ALLOC_TYPE_IOAPIC) {
+		if (get_irq_table(devid, true))
+			index = info->ioapic_pin;
+		else
+			ret = -ENOMEM;
+	} else {
+		index = alloc_irq_index(devid, nr_irqs);
+	}
+	if (index < 0) {
+		pr_warn("Failed to allocate IRTE\n");
+		kfree(data);
+		goto out_free_parent;
+	}
 
-	irte.val		= 0;
-	irte.fields.vector	= cfg->vector;
-	irte.fields.int_type    = apic->irq_delivery_mode;
-	irte.fields.destination	= dest;
-	irte.fields.dm		= apic->irq_dest_mode;
-	irte.fields.valid	= 1;
+	for (i = 0; i < nr_irqs; i++) {
+		irq_data = irq_domain_get_irq_data(domain, virq + i);
+		cfg = irqd_cfg(irq_data);
+		if (!irq_data || !cfg) {
+			ret = -EINVAL;
+			goto out_free_data;
+		}
 
-	modify_irte(irte_info->devid, irte_info->index, irte);
+		if (i > 0) {
+			data = kzalloc(sizeof(*data), GFP_KERNEL);
+			if (!data)
+				goto out_free_data;
+		}
+		irq_data->hwirq = (devid << 16) + i;
+		irq_data->chip_data = data;
+		irq_data->chip = &amd_ir_chip;
+		irq_remapping_prepare_irte(data, cfg, info, devid, index, i);
+		irq_set_status_flags(virq + i, IRQ_MOVE_PCNTXT);
+	}
+	return 0;
 
-	msg->address_hi = MSI_ADDR_BASE_HI;
-	msg->address_lo = MSI_ADDR_BASE_LO;
-	msg->data       = irte_info->index;
+out_free_data:
+	for (i--; i >= 0; i--) {
+		irq_data = irq_domain_get_irq_data(domain, virq + i);
+		if (irq_data)
+			kfree(irq_data->chip_data);
+	}
+	for (i = 0; i < nr_irqs; i++)
+		free_irte(devid, index + i);
+out_free_parent:
+	irq_domain_free_irqs_common(domain, virq, nr_irqs);
+	return ret;
 }
 
-static int msi_alloc_irq(struct pci_dev *pdev, int irq, int nvec)
+static void irq_remapping_free(struct irq_domain *domain, unsigned int virq,
+			       unsigned int nr_irqs)
 {
-	struct irq_cfg *cfg;
-	int index;
-	u16 devid;
-
-	if (!pdev)
-		return -EINVAL;
+	struct irq_2_irte *irte_info;
+	struct irq_data *irq_data;
+	struct amd_ir_data *data;
+	int i;
 
-	cfg = irq_cfg(irq);
-	if (!cfg)
-		return -EINVAL;
+	for (i = 0; i < nr_irqs; i++) {
+		irq_data = irq_domain_get_irq_data(domain, virq  + i);
+		if (irq_data && irq_data->chip_data) {
+			data = irq_data->chip_data;
+			irte_info = &data->irq_2_irte;
+			free_irte(irte_info->devid, irte_info->index);
+			kfree(data);
+		}
+	}
+	irq_domain_free_irqs_common(domain, virq, nr_irqs);
+}
 
-	devid = get_device_id(&pdev->dev);
-	index = alloc_irq_index(cfg, devid, nvec);
+static void irq_remapping_activate(struct irq_domain *domain,
+				   struct irq_data *irq_data)
+{
+	struct amd_ir_data *data = irq_data->chip_data;
+	struct irq_2_irte *irte_info = &data->irq_2_irte;
 
-	return index < 0 ? MAX_IRQS_PER_TABLE : index;
+	modify_irte(irte_info->devid, irte_info->index, data->irte_entry);
 }
 
-static int msi_setup_irq(struct pci_dev *pdev, unsigned int irq,
-			 int index, int offset)
+static void irq_remapping_deactivate(struct irq_domain *domain,
+				     struct irq_data *irq_data)
 {
-	struct irq_2_irte *irte_info;
-	struct irq_cfg *cfg;
-	u16 devid;
+	struct amd_ir_data *data = irq_data->chip_data;
+	struct irq_2_irte *irte_info = &data->irq_2_irte;
+	union irte entry;
 
-	if (!pdev)
-		return -EINVAL;
+	entry.val = 0;
+	modify_irte(irte_info->devid, irte_info->index, data->irte_entry);
+}
 
-	cfg = irq_cfg(irq);
-	if (!cfg)
-		return -EINVAL;
+static struct irq_domain_ops amd_ir_domain_ops = {
+	.alloc = irq_remapping_alloc,
+	.free = irq_remapping_free,
+	.activate = irq_remapping_activate,
+	.deactivate = irq_remapping_deactivate,
+};
 
-	if (index >= MAX_IRQS_PER_TABLE)
-		return 0;
+static int amd_ir_set_affinity(struct irq_data *data,
+			       const struct cpumask *mask, bool force)
+{
+	struct amd_ir_data *ir_data = data->chip_data;
+	struct irq_2_irte *irte_info = &ir_data->irq_2_irte;
+	struct irq_cfg *cfg = irqd_cfg(data);
+	struct irq_data *parent = data->parent_data;
+	int ret;
 
-	devid		= get_device_id(&pdev->dev);
-	irte_info	= &cfg->irq_2_irte;
+	ret = parent->chip->irq_set_affinity(parent, mask, force);
+	if (ret < 0 || ret == IRQ_SET_MASK_OK_DONE)
+		return ret;
 
-	cfg->remapped	      = 1;
-	irte_info->devid      = devid;
-	irte_info->index      = index + offset;
+	/*
+	 * Atomically updates the IRTE with the new destination, vector
+	 * and flushes the interrupt entry cache.
+	 */
+	ir_data->irte_entry.fields.vector = cfg->vector;
+	ir_data->irte_entry.fields.destination = cfg->dest_apicid;
+	modify_irte(irte_info->devid, irte_info->index, ir_data->irte_entry);
 
-	return 0;
+	/*
+	 * After this point, all the interrupts will start arriving
+	 * at the new destination. So, time to cleanup the previous
+	 * vector allocation.
+	 */
+	send_cleanup_vector(cfg);
+
+	return IRQ_SET_MASK_OK_DONE;
 }
 
-static int alloc_hpet_msi(unsigned int irq, unsigned int id)
+static void ir_compose_msi_msg(struct irq_data *irq_data, struct msi_msg *msg)
 {
-	struct irq_2_irte *irte_info;
-	struct irq_cfg *cfg;
-	int index, devid;
+	struct amd_ir_data *ir_data = irq_data->chip_data;
 
-	cfg = irq_cfg(irq);
-	if (!cfg)
-		return -EINVAL;
+	*msg = ir_data->msi_entry;
+}
 
-	irte_info = &cfg->irq_2_irte;
-	devid     = get_hpet_devid(id);
-	if (devid < 0)
-		return devid;
+static struct irq_chip amd_ir_chip = {
+	.irq_ack = ir_ack_apic_edge,
+	.irq_set_affinity = amd_ir_set_affinity,
+	.irq_compose_msi_msg = ir_compose_msi_msg,
+};
 
-	index = alloc_irq_index(cfg, devid, 1);
-	if (index < 0)
-		return index;
+int amd_iommu_create_irq_domain(struct amd_iommu *iommu)
+{
+	iommu->ir_domain = irq_domain_add_tree(NULL, &amd_ir_domain_ops, iommu);
+	if (!iommu->ir_domain)
+		return -ENOMEM;
 
-	cfg->remapped	      = 1;
-	irte_info->devid      = devid;
-	irte_info->index      = index;
+	iommu->ir_domain->parent = arch_get_ir_parent_domain();
+	iommu->msi_domain = arch_create_msi_irq_domain(iommu->ir_domain);
 
 	return 0;
 }
-
-struct irq_remap_ops amd_iommu_irq_ops = {
-	.prepare		= amd_iommu_prepare,
-	.enable			= amd_iommu_enable,
-	.disable		= amd_iommu_disable,
-	.reenable		= amd_iommu_reenable,
-	.enable_faulting	= amd_iommu_enable_faulting,
-	.setup_ioapic_entry	= setup_ioapic_entry,
-	.set_affinity		= set_affinity,
-	.free_irq		= free_irq,
-	.compose_msi_msg	= compose_msi_msg,
-	.msi_alloc_irq		= msi_alloc_irq,
-	.msi_setup_irq		= msi_setup_irq,
-	.alloc_hpet_msi		= alloc_hpet_msi,
-};
 #endif
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index 450ef5001a65..c17df04d7a7f 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -1124,6 +1124,10 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h)
 	if (ret)
 		return ret;
 
+	ret = amd_iommu_create_irq_domain(iommu);
+	if (ret)
+		return ret;
+
 	/*
 	 * Make sure IOMMU is not considered to translate itself. The IVRS
 	 * table tells us so, but this is a lie!
diff --git a/drivers/iommu/amd_iommu_proto.h b/drivers/iommu/amd_iommu_proto.h
index 72b0fd455e24..0a21142d3639 100644
--- a/drivers/iommu/amd_iommu_proto.h
+++ b/drivers/iommu/amd_iommu_proto.h
@@ -62,6 +62,15 @@ extern u8 amd_iommu_pc_get_max_counters(u16 devid);
 extern int amd_iommu_pc_get_set_reg_val(u16 devid, u8 bank, u8 cntr, u8 fxn,
 				    u64 *value, bool is_write);
 
+#ifdef CONFIG_IRQ_REMAP
+extern int amd_iommu_create_irq_domain(struct amd_iommu *iommu);
+#else
+static inline int amd_iommu_create_irq_domain(struct amd_iommu *iommu)
+{
+	return 0;
+}
+#endif
+
 #define PPR_SUCCESS			0x0
 #define PPR_INVALID			0x1
 #define PPR_FAILURE			0xf
diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h
index 05030e523771..6533e874c9d7 100644
--- a/drivers/iommu/amd_iommu_types.h
+++ b/drivers/iommu/amd_iommu_types.h
@@ -398,6 +398,7 @@ struct amd_iommu_fault {
 
 
 struct iommu_domain;
+struct irq_domain;
 
 /*
  * This structure contains generic data for  IOMMU protection domains
@@ -579,6 +580,10 @@ struct amd_iommu {
 	/* The maximum PC banks and counters/bank (PCSup=1) */
 	u8 max_banks;
 	u8 max_counters;
+#ifdef CONFIG_IRQ_REMAP
+	struct irq_domain *ir_domain;
+	struct irq_domain *msi_domain;
+#endif
 };
 
 struct devid_map {
diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index 9847613085e1..536f2d8ea41a 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -1087,8 +1087,8 @@ static void free_iommu(struct intel_iommu *iommu)
 
 	if (iommu->irq) {
 		free_irq(iommu->irq, iommu);
-		irq_set_handler_data(iommu->irq, NULL);
 		dmar_free_hwirq(iommu->irq);
+		iommu->irq = 0;
 	}
 
 	if (iommu->qi) {
@@ -1642,23 +1642,14 @@ int dmar_set_interrupt(struct intel_iommu *iommu)
 	if (iommu->irq)
 		return 0;
 
-	irq = dmar_alloc_hwirq();
-	if (irq <= 0) {
+	irq = dmar_alloc_hwirq(iommu->seq_id, iommu->node, iommu);
+	if (irq > 0) {
+		iommu->irq = irq;
+	} else {
 		pr_err("IOMMU: no free vectors\n");
 		return -EINVAL;
 	}
 
-	irq_set_handler_data(irq, iommu);
-	iommu->irq = irq;
-
-	ret = arch_setup_dmar_msi(irq);
-	if (ret) {
-		irq_set_handler_data(irq, NULL);
-		iommu->irq = 0;
-		dmar_free_hwirq(irq);
-		return ret;
-	}
-
 	ret = request_irq(irq, dmar_fault, IRQF_NO_THREAD, iommu->name, iommu);
 	if (ret)
 		pr_err("IOMMU: can't request irq\n");
diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c
index 5709ae9c3e77..80f1d1486247 100644
--- a/drivers/iommu/intel_irq_remapping.c
+++ b/drivers/iommu/intel_irq_remapping.c
@@ -8,6 +8,7 @@
 #include <linux/irq.h>
 #include <linux/intel-iommu.h>
 #include <linux/acpi.h>
+#include <linux/irqdomain.h>
 #include <asm/io_apic.h>
 #include <asm/smp.h>
 #include <asm/cpu.h>
@@ -17,6 +18,11 @@
 
 #include "irq_remapping.h"
 
+enum irq_mode {
+	IRQ_REMAPPING,
+	IRQ_POSTING,
+};
+
 struct ioapic_scope {
 	struct intel_iommu *iommu;
 	unsigned int id;
@@ -31,6 +37,22 @@ struct hpet_scope {
 	unsigned int devfn;
 };
 
+struct irq_2_iommu {
+	struct intel_iommu *iommu;
+	u16 irte_index;
+	u16 sub_handle;
+	u8  irte_mask;
+	enum irq_mode mode;
+};
+
+struct intel_ir_data {
+	struct irq_2_iommu			irq_2_iommu;
+	struct irte				irte_entry;
+	union {
+		struct msi_msg			msi_entry;
+	};
+};
+
 #define IR_X2APIC_MODE(mode) (mode ? (1 << 11) : 0)
 #define IRTE_DEST(dest) ((eim_mode) ? dest : dest << 8)
 
@@ -50,43 +72,14 @@ static struct hpet_scope ir_hpet[MAX_HPET_TBS];
  * the dmar_global_lock.
  */
 static DEFINE_RAW_SPINLOCK(irq_2_ir_lock);
+static struct irq_domain_ops intel_ir_domain_ops;
 
 static int __init parse_ioapics_under_ir(void);
 
-static struct irq_2_iommu *irq_2_iommu(unsigned int irq)
-{
-	struct irq_cfg *cfg = irq_cfg(irq);
-	return cfg ? &cfg->irq_2_iommu : NULL;
-}
-
-static int get_irte(int irq, struct irte *entry)
-{
-	struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
-	unsigned long flags;
-	int index;
-
-	if (!entry || !irq_iommu)
-		return -1;
-
-	raw_spin_lock_irqsave(&irq_2_ir_lock, flags);
-
-	if (unlikely(!irq_iommu->iommu)) {
-		raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
-		return -1;
-	}
-
-	index = irq_iommu->irte_index + irq_iommu->sub_handle;
-	*entry = *(irq_iommu->iommu->ir_table->base + index);
-
-	raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
-	return 0;
-}
-
-static int alloc_irte(struct intel_iommu *iommu, int irq, u16 count)
+static int alloc_irte(struct intel_iommu *iommu, int irq,
+		      struct irq_2_iommu *irq_iommu, u16 count)
 {
 	struct ir_table *table = iommu->ir_table;
-	struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
-	struct irq_cfg *cfg = irq_cfg(irq);
 	unsigned int mask = 0;
 	unsigned long flags;
 	int index;
@@ -113,11 +106,11 @@ static int alloc_irte(struct intel_iommu *iommu, int irq, u16 count)
 	if (index < 0) {
 		pr_warn("IR%d: can't allocate an IRTE\n", iommu->seq_id);
 	} else {
-		cfg->remapped = 1;
 		irq_iommu->iommu = iommu;
 		irq_iommu->irte_index =  index;
 		irq_iommu->sub_handle = 0;
 		irq_iommu->irte_mask = mask;
+		irq_iommu->mode = IRQ_REMAPPING;
 	}
 	raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
 
@@ -135,47 +128,9 @@ static int qi_flush_iec(struct intel_iommu *iommu, int index, int mask)
 	return qi_submit_sync(&desc, iommu);
 }
 
-static int map_irq_to_irte_handle(int irq, u16 *sub_handle)
-{
-	struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
-	unsigned long flags;
-	int index;
-
-	if (!irq_iommu)
-		return -1;
-
-	raw_spin_lock_irqsave(&irq_2_ir_lock, flags);
-	*sub_handle = irq_iommu->sub_handle;
-	index = irq_iommu->irte_index;
-	raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
-	return index;
-}
-
-static int set_irte_irq(int irq, struct intel_iommu *iommu, u16 index, u16 subhandle)
+static int modify_irte(struct irq_2_iommu *irq_iommu,
+		       struct irte *irte_modified)
 {
-	struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
-	struct irq_cfg *cfg = irq_cfg(irq);
-	unsigned long flags;
-
-	if (!irq_iommu)
-		return -1;
-
-	raw_spin_lock_irqsave(&irq_2_ir_lock, flags);
-
-	cfg->remapped = 1;
-	irq_iommu->iommu = iommu;
-	irq_iommu->irte_index = index;
-	irq_iommu->sub_handle = subhandle;
-	irq_iommu->irte_mask = 0;
-
-	raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
-
-	return 0;
-}
-
-static int modify_irte(int irq, struct irte *irte_modified)
-{
-	struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
 	struct intel_iommu *iommu;
 	unsigned long flags;
 	struct irte *irte;
@@ -196,6 +151,9 @@ static int modify_irte(int irq, struct irte *irte_modified)
 	__iommu_flush_cache(iommu, irte, sizeof(*irte));
 
 	rc = qi_flush_iec(iommu, index, 0);
+
+	/* Update iommu mode according to the IRTE mode */
+	irq_iommu->mode = irte->pst ? IRQ_POSTING : IRQ_REMAPPING;
 	raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
 
 	return rc;
@@ -242,7 +200,7 @@ static int clear_entries(struct irq_2_iommu *irq_iommu)
 		return 0;
 
 	iommu = irq_iommu->iommu;
-	index = irq_iommu->irte_index + irq_iommu->sub_handle;
+	index = irq_iommu->irte_index;
 
 	start = iommu->ir_table->base + index;
 	end = start + (1 << irq_iommu->irte_mask);
@@ -257,29 +215,6 @@ static int clear_entries(struct irq_2_iommu *irq_iommu)
 	return qi_flush_iec(iommu, index, irq_iommu->irte_mask);
 }
 
-static int free_irte(int irq)
-{
-	struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
-	unsigned long flags;
-	int rc;
-
-	if (!irq_iommu)
-		return -1;
-
-	raw_spin_lock_irqsave(&irq_2_ir_lock, flags);
-
-	rc = clear_entries(irq_iommu);
-
-	irq_iommu->iommu = NULL;
-	irq_iommu->irte_index = 0;
-	irq_iommu->sub_handle = 0;
-	irq_iommu->irte_mask = 0;
-
-	raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
-
-	return rc;
-}
-
 /*
  * source validation type
  */
@@ -488,7 +423,6 @@ static int intel_setup_irq_remapping(struct intel_iommu *iommu)
 
 	pages = alloc_pages_node(iommu->node, GFP_KERNEL | __GFP_ZERO,
 				 INTR_REMAP_PAGE_ORDER);
-
 	if (!pages) {
 		pr_err("IR%d: failed to allocate pages of order %d\n",
 		       iommu->seq_id, INTR_REMAP_PAGE_ORDER);
@@ -502,11 +436,23 @@ static int intel_setup_irq_remapping(struct intel_iommu *iommu)
 		goto out_free_pages;
 	}
 
+	iommu->ir_domain = irq_domain_add_hierarchy(arch_get_ir_parent_domain(),
+						    0, INTR_REMAP_TABLE_ENTRIES,
+						    NULL, &intel_ir_domain_ops,
+						    iommu);
+	if (!iommu->ir_domain) {
+		pr_err("IR%d: failed to allocate irqdomain\n", iommu->seq_id);
+		goto out_free_bitmap;
+	}
+	iommu->ir_msi_domain = arch_create_msi_irq_domain(iommu->ir_domain);
+
 	ir_table->base = page_address(pages);
 	ir_table->bitmap = bitmap;
 	iommu->ir_table = ir_table;
 	return 0;
 
+out_free_bitmap:
+	kfree(bitmap);
 out_free_pages:
 	__free_pages(pages, INTR_REMAP_PAGE_ORDER);
 out_free_table:
@@ -517,6 +463,14 @@ out_free_table:
 static void intel_teardown_irq_remapping(struct intel_iommu *iommu)
 {
 	if (iommu && iommu->ir_table) {
+		if (iommu->ir_msi_domain) {
+			irq_domain_remove(iommu->ir_msi_domain);
+			iommu->ir_msi_domain = NULL;
+		}
+		if (iommu->ir_domain) {
+			irq_domain_remove(iommu->ir_domain);
+			iommu->ir_domain = NULL;
+		}
 		free_pages((unsigned long)iommu->ir_table->base,
 			   INTR_REMAP_PAGE_ORDER);
 		kfree(iommu->ir_table->bitmap);
@@ -627,6 +581,26 @@ error:
 	return -ENODEV;
 }
 
+/*
+ * Set Posted-Interrupts capability.
+ */
+static inline void set_irq_posting_cap(void)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu;
+
+	if (!disable_irq_post) {
+		intel_irq_remap_ops.capability |= 1 << IRQ_POSTING_CAP;
+
+		for_each_iommu(iommu, drhd)
+			if (!cap_pi_support(iommu->cap)) {
+				intel_irq_remap_ops.capability &=
+						~(1 << IRQ_POSTING_CAP);
+				break;
+			}
+	}
+}
+
 static int __init intel_enable_irq_remapping(void)
 {
 	struct dmar_drhd_unit *drhd;
@@ -702,12 +676,7 @@ static int __init intel_enable_irq_remapping(void)
 
 	irq_remapping_enabled = 1;
 
-	/*
-	 * VT-d has a different layout for IO-APIC entries when
-	 * interrupt remapping is enabled. So it needs a special routine
-	 * to print IO-APIC entries for debugging purposes too.
-	 */
-	x86_io_apic_ops.print_entries = intel_ir_io_apic_print_entries;
+	set_irq_posting_cap();
 
 	pr_info("Enabled IRQ remapping in %s mode\n", eim ? "x2apic" : "xapic");
 
@@ -909,6 +878,12 @@ static void disable_irq_remapping(void)
 
 		iommu_disable_irq_remapping(iommu);
 	}
+
+	/*
+	 * Clear Posted-Interrupts capability.
+	 */
+	if (!disable_irq_post)
+		intel_irq_remap_ops.capability &= ~(1 << IRQ_POSTING_CAP);
 }
 
 static int reenable_irq_remapping(int eim)
@@ -936,6 +911,8 @@ static int reenable_irq_remapping(int eim)
 	if (!setup)
 		goto error;
 
+	set_irq_posting_cap();
+
 	return 0;
 
 error:
@@ -945,8 +922,7 @@ error:
 	return -1;
 }
 
-static void prepare_irte(struct irte *irte, int vector,
-			 unsigned int dest)
+static void prepare_irte(struct irte *irte, int vector, unsigned int dest)
 {
 	memset(irte, 0, sizeof(*irte));
 
@@ -966,76 +942,63 @@ static void prepare_irte(struct irte *irte, int vector,
 	irte->redir_hint = 1;
 }
 
-static int intel_setup_ioapic_entry(int irq,
-				    struct IO_APIC_route_entry *route_entry,
-				    unsigned int destination, int vector,
-				    struct io_apic_irq_attr *attr)
+static struct irq_domain *intel_get_ir_irq_domain(struct irq_alloc_info *info)
 {
-	int ioapic_id = mpc_ioapic_id(attr->ioapic);
-	struct intel_iommu *iommu;
-	struct IR_IO_APIC_route_entry *entry;
-	struct irte irte;
-	int index;
-
-	down_read(&dmar_global_lock);
-	iommu = map_ioapic_to_ir(ioapic_id);
-	if (!iommu) {
-		pr_warn("No mapping iommu for ioapic %d\n", ioapic_id);
-		index = -ENODEV;
-	} else {
-		index = alloc_irte(iommu, irq, 1);
-		if (index < 0) {
-			pr_warn("Failed to allocate IRTE for ioapic %d\n",
-				ioapic_id);
-			index = -ENOMEM;
-		}
-	}
-	up_read(&dmar_global_lock);
-	if (index < 0)
-		return index;
-
-	prepare_irte(&irte, vector, destination);
+	struct intel_iommu *iommu = NULL;
 
-	/* Set source-id of interrupt request */
-	set_ioapic_sid(&irte, ioapic_id);
+	if (!info)
+		return NULL;
 
-	modify_irte(irq, &irte);
+	switch (info->type) {
+	case X86_IRQ_ALLOC_TYPE_IOAPIC:
+		iommu = map_ioapic_to_ir(info->ioapic_id);
+		break;
+	case X86_IRQ_ALLOC_TYPE_HPET:
+		iommu = map_hpet_to_ir(info->hpet_id);
+		break;
+	case X86_IRQ_ALLOC_TYPE_MSI:
+	case X86_IRQ_ALLOC_TYPE_MSIX:
+		iommu = map_dev_to_ir(info->msi_dev);
+		break;
+	default:
+		BUG_ON(1);
+		break;
+	}
 
-	apic_printk(APIC_VERBOSE, KERN_DEBUG "IOAPIC[%d]: "
-		"Set IRTE entry (P:%d FPD:%d Dst_Mode:%d "
-		"Redir_hint:%d Trig_Mode:%d Dlvry_Mode:%X "
-		"Avail:%X Vector:%02X Dest:%08X "
-		"SID:%04X SQ:%X SVT:%X)\n",
-		attr->ioapic, irte.present, irte.fpd, irte.dst_mode,
-		irte.redir_hint, irte.trigger_mode, irte.dlvry_mode,
-		irte.avail, irte.vector, irte.dest_id,
-		irte.sid, irte.sq, irte.svt);
+	return iommu ? iommu->ir_domain : NULL;
+}
 
-	entry = (struct IR_IO_APIC_route_entry *)route_entry;
-	memset(entry, 0, sizeof(*entry));
+static struct irq_domain *intel_get_irq_domain(struct irq_alloc_info *info)
+{
+	struct intel_iommu *iommu;
 
-	entry->index2	= (index >> 15) & 0x1;
-	entry->zero	= 0;
-	entry->format	= 1;
-	entry->index	= (index & 0x7fff);
-	/*
-	 * IO-APIC RTE will be configured with virtual vector.
-	 * irq handler will do the explicit EOI to the io-apic.
-	 */
-	entry->vector	= attr->ioapic_pin;
-	entry->mask	= 0;			/* enable IRQ */
-	entry->trigger	= attr->trigger;
-	entry->polarity	= attr->polarity;
+	if (!info)
+		return NULL;
 
-	/* Mask level triggered irqs.
-	 * Use IRQ_DELAYED_DISABLE for edge triggered irqs.
-	 */
-	if (attr->trigger)
-		entry->mask = 1;
+	switch (info->type) {
+	case X86_IRQ_ALLOC_TYPE_MSI:
+	case X86_IRQ_ALLOC_TYPE_MSIX:
+		iommu = map_dev_to_ir(info->msi_dev);
+		if (iommu)
+			return iommu->ir_msi_domain;
+		break;
+	default:
+		break;
+	}
 
-	return 0;
+	return NULL;
 }
 
+struct irq_remap_ops intel_irq_remap_ops = {
+	.prepare		= intel_prepare_irq_remapping,
+	.enable			= intel_enable_irq_remapping,
+	.disable		= disable_irq_remapping,
+	.reenable		= reenable_irq_remapping,
+	.enable_faulting	= enable_drhd_fault_handling,
+	.get_ir_irq_domain	= intel_get_ir_irq_domain,
+	.get_irq_domain		= intel_get_irq_domain,
+};
+
 /*
  * Migrate the IO-APIC irq in the presence of intr-remapping.
  *
@@ -1051,170 +1014,282 @@ static int intel_setup_ioapic_entry(int irq,
  * is used to migrate MSI irq's in the presence of interrupt-remapping.
  */
 static int
-intel_ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask,
-			  bool force)
+intel_ir_set_affinity(struct irq_data *data, const struct cpumask *mask,
+		      bool force)
 {
+	struct intel_ir_data *ir_data = data->chip_data;
+	struct irte *irte = &ir_data->irte_entry;
 	struct irq_cfg *cfg = irqd_cfg(data);
-	unsigned int dest, irq = data->irq;
-	struct irte irte;
-	int err;
-
-	if (!config_enabled(CONFIG_SMP))
-		return -EINVAL;
-
-	if (!cpumask_intersects(mask, cpu_online_mask))
-		return -EINVAL;
-
-	if (get_irte(irq, &irte))
-		return -EBUSY;
-
-	err = assign_irq_vector(irq, cfg, mask);
-	if (err)
-		return err;
-
-	err = apic->cpu_mask_to_apicid_and(cfg->domain, mask, &dest);
-	if (err) {
-		if (assign_irq_vector(irq, cfg, data->affinity))
-			pr_err("Failed to recover vector for irq %d\n", irq);
-		return err;
-	}
+	struct irq_data *parent = data->parent_data;
+	int ret;
 
-	irte.vector = cfg->vector;
-	irte.dest_id = IRTE_DEST(dest);
+	ret = parent->chip->irq_set_affinity(parent, mask, force);
+	if (ret < 0 || ret == IRQ_SET_MASK_OK_DONE)
+		return ret;
 
 	/*
 	 * Atomically updates the IRTE with the new destination, vector
 	 * and flushes the interrupt entry cache.
 	 */
-	modify_irte(irq, &irte);
+	irte->vector = cfg->vector;
+	irte->dest_id = IRTE_DEST(cfg->dest_apicid);
+
+	/* Update the hardware only if the interrupt is in remapped mode. */
+	if (ir_data->irq_2_iommu.mode == IRQ_REMAPPING)
+		modify_irte(&ir_data->irq_2_iommu, irte);
 
 	/*
 	 * After this point, all the interrupts will start arriving
 	 * at the new destination. So, time to cleanup the previous
 	 * vector allocation.
 	 */
-	if (cfg->move_in_progress)
-		send_cleanup_vector(cfg);
+	send_cleanup_vector(cfg);
 
-	cpumask_copy(data->affinity, mask);
-	return 0;
+	return IRQ_SET_MASK_OK_DONE;
 }
 
-static void intel_compose_msi_msg(struct pci_dev *pdev,
-				  unsigned int irq, unsigned int dest,
-				  struct msi_msg *msg, u8 hpet_id)
+static void intel_ir_compose_msi_msg(struct irq_data *irq_data,
+				     struct msi_msg *msg)
 {
-	struct irq_cfg *cfg;
-	struct irte irte;
-	u16 sub_handle = 0;
-	int ir_index;
+	struct intel_ir_data *ir_data = irq_data->chip_data;
 
-	cfg = irq_cfg(irq);
+	*msg = ir_data->msi_entry;
+}
 
-	ir_index = map_irq_to_irte_handle(irq, &sub_handle);
-	BUG_ON(ir_index == -1);
+static int intel_ir_set_vcpu_affinity(struct irq_data *data, void *info)
+{
+	struct intel_ir_data *ir_data = data->chip_data;
+	struct vcpu_data *vcpu_pi_info = info;
 
-	prepare_irte(&irte, cfg->vector, dest);
+	/* stop posting interrupts, back to remapping mode */
+	if (!vcpu_pi_info) {
+		modify_irte(&ir_data->irq_2_iommu, &ir_data->irte_entry);
+	} else {
+		struct irte irte_pi;
 
-	/* Set source-id of interrupt request */
-	if (pdev)
-		set_msi_sid(&irte, pdev);
-	else
-		set_hpet_sid(&irte, hpet_id);
+		/*
+		 * We are not caching the posted interrupt entry. We
+		 * copy the data from the remapped entry and modify
+		 * the fields which are relevant for posted mode. The
+		 * cached remapped entry is used for switching back to
+		 * remapped mode.
+		 */
+		memset(&irte_pi, 0, sizeof(irte_pi));
+		dmar_copy_shared_irte(&irte_pi, &ir_data->irte_entry);
+
+		/* Update the posted mode fields */
+		irte_pi.p_pst = 1;
+		irte_pi.p_urgent = 0;
+		irte_pi.p_vector = vcpu_pi_info->vector;
+		irte_pi.pda_l = (vcpu_pi_info->pi_desc_addr >>
+				(32 - PDA_LOW_BIT)) & ~(-1UL << PDA_LOW_BIT);
+		irte_pi.pda_h = (vcpu_pi_info->pi_desc_addr >> 32) &
+				~(-1UL << PDA_HIGH_BIT);
+
+		modify_irte(&ir_data->irq_2_iommu, &irte_pi);
+	}
 
-	modify_irte(irq, &irte);
+	return 0;
+}
+
+static struct irq_chip intel_ir_chip = {
+	.irq_ack = ir_ack_apic_edge,
+	.irq_set_affinity = intel_ir_set_affinity,
+	.irq_compose_msi_msg = intel_ir_compose_msi_msg,
+	.irq_set_vcpu_affinity = intel_ir_set_vcpu_affinity,
+};
 
-	msg->address_hi = MSI_ADDR_BASE_HI;
-	msg->data = sub_handle;
-	msg->address_lo = MSI_ADDR_BASE_LO | MSI_ADDR_IR_EXT_INT |
-			  MSI_ADDR_IR_SHV |
-			  MSI_ADDR_IR_INDEX1(ir_index) |
-			  MSI_ADDR_IR_INDEX2(ir_index);
+static void intel_irq_remapping_prepare_irte(struct intel_ir_data *data,
+					     struct irq_cfg *irq_cfg,
+					     struct irq_alloc_info *info,
+					     int index, int sub_handle)
+{
+	struct IR_IO_APIC_route_entry *entry;
+	struct irte *irte = &data->irte_entry;
+	struct msi_msg *msg = &data->msi_entry;
+
+	prepare_irte(irte, irq_cfg->vector, irq_cfg->dest_apicid);
+	switch (info->type) {
+	case X86_IRQ_ALLOC_TYPE_IOAPIC:
+		/* Set source-id of interrupt request */
+		set_ioapic_sid(irte, info->ioapic_id);
+		apic_printk(APIC_VERBOSE, KERN_DEBUG "IOAPIC[%d]: Set IRTE entry (P:%d FPD:%d Dst_Mode:%d Redir_hint:%d Trig_Mode:%d Dlvry_Mode:%X Avail:%X Vector:%02X Dest:%08X SID:%04X SQ:%X SVT:%X)\n",
+			info->ioapic_id, irte->present, irte->fpd,
+			irte->dst_mode, irte->redir_hint,
+			irte->trigger_mode, irte->dlvry_mode,
+			irte->avail, irte->vector, irte->dest_id,
+			irte->sid, irte->sq, irte->svt);
+
+		entry = (struct IR_IO_APIC_route_entry *)info->ioapic_entry;
+		info->ioapic_entry = NULL;
+		memset(entry, 0, sizeof(*entry));
+		entry->index2	= (index >> 15) & 0x1;
+		entry->zero	= 0;
+		entry->format	= 1;
+		entry->index	= (index & 0x7fff);
+		/*
+		 * IO-APIC RTE will be configured with virtual vector.
+		 * irq handler will do the explicit EOI to the io-apic.
+		 */
+		entry->vector	= info->ioapic_pin;
+		entry->mask	= 0;			/* enable IRQ */
+		entry->trigger	= info->ioapic_trigger;
+		entry->polarity	= info->ioapic_polarity;
+		if (info->ioapic_trigger)
+			entry->mask = 1; /* Mask level triggered irqs. */
+		break;
+
+	case X86_IRQ_ALLOC_TYPE_HPET:
+	case X86_IRQ_ALLOC_TYPE_MSI:
+	case X86_IRQ_ALLOC_TYPE_MSIX:
+		if (info->type == X86_IRQ_ALLOC_TYPE_HPET)
+			set_hpet_sid(irte, info->hpet_id);
+		else
+			set_msi_sid(irte, info->msi_dev);
+
+		msg->address_hi = MSI_ADDR_BASE_HI;
+		msg->data = sub_handle;
+		msg->address_lo = MSI_ADDR_BASE_LO | MSI_ADDR_IR_EXT_INT |
+				  MSI_ADDR_IR_SHV |
+				  MSI_ADDR_IR_INDEX1(index) |
+				  MSI_ADDR_IR_INDEX2(index);
+		break;
+
+	default:
+		BUG_ON(1);
+		break;
+	}
 }
 
-/*
- * Map the PCI dev to the corresponding remapping hardware unit
- * and allocate 'nvec' consecutive interrupt-remapping table entries
- * in it.
- */
-static int intel_msi_alloc_irq(struct pci_dev *dev, int irq, int nvec)
+static void intel_free_irq_resources(struct irq_domain *domain,
+				     unsigned int virq, unsigned int nr_irqs)
 {
-	struct intel_iommu *iommu;
-	int index;
+	struct irq_data *irq_data;
+	struct intel_ir_data *data;
+	struct irq_2_iommu *irq_iommu;
+	unsigned long flags;
+	int i;
 
-	down_read(&dmar_global_lock);
-	iommu = map_dev_to_ir(dev);
-	if (!iommu) {
-		printk(KERN_ERR
-		       "Unable to map PCI %s to iommu\n", pci_name(dev));
-		index = -ENOENT;
-	} else {
-		index = alloc_irte(iommu, irq, nvec);
-		if (index < 0) {
-			printk(KERN_ERR
-			       "Unable to allocate %d IRTE for PCI %s\n",
-			       nvec, pci_name(dev));
-			index = -ENOSPC;
+	for (i = 0; i < nr_irqs; i++) {
+		irq_data = irq_domain_get_irq_data(domain, virq  + i);
+		if (irq_data && irq_data->chip_data) {
+			data = irq_data->chip_data;
+			irq_iommu = &data->irq_2_iommu;
+			raw_spin_lock_irqsave(&irq_2_ir_lock, flags);
+			clear_entries(irq_iommu);
+			raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
+			irq_domain_reset_irq_data(irq_data);
+			kfree(data);
 		}
 	}
-	up_read(&dmar_global_lock);
-
-	return index;
 }
 
-static int intel_msi_setup_irq(struct pci_dev *pdev, unsigned int irq,
-			       int index, int sub_handle)
+static int intel_irq_remapping_alloc(struct irq_domain *domain,
+				     unsigned int virq, unsigned int nr_irqs,
+				     void *arg)
 {
-	struct intel_iommu *iommu;
-	int ret = -ENOENT;
+	struct intel_iommu *iommu = domain->host_data;
+	struct irq_alloc_info *info = arg;
+	struct intel_ir_data *data, *ird;
+	struct irq_data *irq_data;
+	struct irq_cfg *irq_cfg;
+	int i, ret, index;
+
+	if (!info || !iommu)
+		return -EINVAL;
+	if (nr_irqs > 1 && info->type != X86_IRQ_ALLOC_TYPE_MSI &&
+	    info->type != X86_IRQ_ALLOC_TYPE_MSIX)
+		return -EINVAL;
+
+	/*
+	 * With IRQ remapping enabled, don't need contiguous CPU vectors
+	 * to support multiple MSI interrupts.
+	 */
+	if (info->type == X86_IRQ_ALLOC_TYPE_MSI)
+		info->flags &= ~X86_IRQ_ALLOC_CONTIGUOUS_VECTORS;
+
+	ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, arg);
+	if (ret < 0)
+		return ret;
+
+	ret = -ENOMEM;
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		goto out_free_parent;
 
 	down_read(&dmar_global_lock);
-	iommu = map_dev_to_ir(pdev);
-	if (iommu) {
-		/*
-		 * setup the mapping between the irq and the IRTE
-		 * base index, the sub_handle pointing to the
-		 * appropriate interrupt remap table entry.
-		 */
-		set_irte_irq(irq, iommu, index, sub_handle);
-		ret = 0;
-	}
+	index = alloc_irte(iommu, virq, &data->irq_2_iommu, nr_irqs);
 	up_read(&dmar_global_lock);
+	if (index < 0) {
+		pr_warn("Failed to allocate IRTE\n");
+		kfree(data);
+		goto out_free_parent;
+	}
 
+	for (i = 0; i < nr_irqs; i++) {
+		irq_data = irq_domain_get_irq_data(domain, virq + i);
+		irq_cfg = irqd_cfg(irq_data);
+		if (!irq_data || !irq_cfg) {
+			ret = -EINVAL;
+			goto out_free_data;
+		}
+
+		if (i > 0) {
+			ird = kzalloc(sizeof(*ird), GFP_KERNEL);
+			if (!ird)
+				goto out_free_data;
+			/* Initialize the common data */
+			ird->irq_2_iommu = data->irq_2_iommu;
+			ird->irq_2_iommu.sub_handle = i;
+		} else {
+			ird = data;
+		}
+
+		irq_data->hwirq = (index << 16) + i;
+		irq_data->chip_data = ird;
+		irq_data->chip = &intel_ir_chip;
+		intel_irq_remapping_prepare_irte(ird, irq_cfg, info, index, i);
+		irq_set_status_flags(virq + i, IRQ_MOVE_PCNTXT);
+	}
+	return 0;
+
+out_free_data:
+	intel_free_irq_resources(domain, virq, i);
+out_free_parent:
+	irq_domain_free_irqs_common(domain, virq, nr_irqs);
 	return ret;
 }
 
-static int intel_alloc_hpet_msi(unsigned int irq, unsigned int id)
+static void intel_irq_remapping_free(struct irq_domain *domain,
+				     unsigned int virq, unsigned int nr_irqs)
 {
-	int ret = -1;
-	struct intel_iommu *iommu;
-	int index;
+	intel_free_irq_resources(domain, virq, nr_irqs);
+	irq_domain_free_irqs_common(domain, virq, nr_irqs);
+}
 
-	down_read(&dmar_global_lock);
-	iommu = map_hpet_to_ir(id);
-	if (iommu) {
-		index = alloc_irte(iommu, irq, 1);
-		if (index >= 0)
-			ret = 0;
-	}
-	up_read(&dmar_global_lock);
+static void intel_irq_remapping_activate(struct irq_domain *domain,
+					 struct irq_data *irq_data)
+{
+	struct intel_ir_data *data = irq_data->chip_data;
 
-	return ret;
+	modify_irte(&data->irq_2_iommu, &data->irte_entry);
 }
 
-struct irq_remap_ops intel_irq_remap_ops = {
-	.prepare		= intel_prepare_irq_remapping,
-	.enable			= intel_enable_irq_remapping,
-	.disable		= disable_irq_remapping,
-	.reenable		= reenable_irq_remapping,
-	.enable_faulting	= enable_drhd_fault_handling,
-	.setup_ioapic_entry	= intel_setup_ioapic_entry,
-	.set_affinity		= intel_ioapic_set_affinity,
-	.free_irq		= free_irte,
-	.compose_msi_msg	= intel_compose_msi_msg,
-	.msi_alloc_irq		= intel_msi_alloc_irq,
-	.msi_setup_irq		= intel_msi_setup_irq,
-	.alloc_hpet_msi		= intel_alloc_hpet_msi,
+static void intel_irq_remapping_deactivate(struct irq_domain *domain,
+					   struct irq_data *irq_data)
+{
+	struct intel_ir_data *data = irq_data->chip_data;
+	struct irte entry;
+
+	memset(&entry, 0, sizeof(entry));
+	modify_irte(&data->irq_2_iommu, &entry);
+}
+
+static struct irq_domain_ops intel_ir_domain_ops = {
+	.alloc = intel_irq_remapping_alloc,
+	.free = intel_irq_remapping_free,
+	.activate = intel_irq_remapping_activate,
+	.deactivate = intel_irq_remapping_deactivate,
 };
 
 /*
@@ -1280,6 +1355,9 @@ int dmar_ir_hotplug(struct dmar_drhd_unit *dmaru, bool insert)
 		return -EINVAL;
 	if (!ecap_ir_support(iommu->ecap))
 		return 0;
+	if (irq_remapping_cap(IRQ_POSTING_CAP) &&
+	    !cap_pi_support(iommu->cap))
+		return -EBUSY;
 
 	if (insert) {
 		if (!iommu->ir_table)
diff --git a/drivers/iommu/irq_remapping.c b/drivers/iommu/irq_remapping.c
index 390079ee1350..2d9993062ded 100644
--- a/drivers/iommu/irq_remapping.c
+++ b/drivers/iommu/irq_remapping.c
@@ -6,6 +6,7 @@
 #include <linux/msi.h>
 #include <linux/irq.h>
 #include <linux/pci.h>
+#include <linux/irqdomain.h>
 
 #include <asm/hw_irq.h>
 #include <asm/irq_remapping.h>
@@ -21,21 +22,11 @@ int irq_remap_broken;
 int disable_sourceid_checking;
 int no_x2apic_optout;
 
+int disable_irq_post = 1;
+
 static int disable_irq_remap;
 static struct irq_remap_ops *remap_ops;
 
-static int msi_alloc_remapped_irq(struct pci_dev *pdev, int irq, int nvec);
-static int msi_setup_remapped_irq(struct pci_dev *pdev, unsigned int irq,
-				  int index, int sub_handle);
-static int set_remapped_irq_affinity(struct irq_data *data,
-				     const struct cpumask *mask,
-				     bool force);
-
-static bool irq_remapped(struct irq_cfg *cfg)
-{
-	return (cfg->remapped == 1);
-}
-
 static void irq_remapping_disable_io_apic(void)
 {
 	/*
@@ -49,117 +40,9 @@ static void irq_remapping_disable_io_apic(void)
 		disconnect_bsp_APIC(0);
 }
 
-static int do_setup_msi_irqs(struct pci_dev *dev, int nvec)
-{
-	int ret, sub_handle, nvec_pow2, index = 0;
-	unsigned int irq;
-	struct msi_desc *msidesc;
-
-	msidesc = list_entry(dev->msi_list.next, struct msi_desc, list);
-
-	irq = irq_alloc_hwirqs(nvec, dev_to_node(&dev->dev));
-	if (irq == 0)
-		return -ENOSPC;
-
-	nvec_pow2 = __roundup_pow_of_two(nvec);
-	for (sub_handle = 0; sub_handle < nvec; sub_handle++) {
-		if (!sub_handle) {
-			index = msi_alloc_remapped_irq(dev, irq, nvec_pow2);
-			if (index < 0) {
-				ret = index;
-				goto error;
-			}
-		} else {
-			ret = msi_setup_remapped_irq(dev, irq + sub_handle,
-						     index, sub_handle);
-			if (ret < 0)
-				goto error;
-		}
-		ret = setup_msi_irq(dev, msidesc, irq, sub_handle);
-		if (ret < 0)
-			goto error;
-	}
-	return 0;
-
-error:
-	irq_free_hwirqs(irq, nvec);
-
-	/*
-	 * Restore altered MSI descriptor fields and prevent just destroyed
-	 * IRQs from tearing down again in default_teardown_msi_irqs()
-	 */
-	msidesc->irq = 0;
-
-	return ret;
-}
-
-static int do_setup_msix_irqs(struct pci_dev *dev, int nvec)
-{
-	int node, ret, sub_handle, index = 0;
-	struct msi_desc *msidesc;
-	unsigned int irq;
-
-	node		= dev_to_node(&dev->dev);
-	sub_handle	= 0;
-
-	list_for_each_entry(msidesc, &dev->msi_list, list) {
-
-		irq = irq_alloc_hwirq(node);
-		if (irq == 0)
-			return -1;
-
-		if (sub_handle == 0)
-			ret = index = msi_alloc_remapped_irq(dev, irq, nvec);
-		else
-			ret = msi_setup_remapped_irq(dev, irq, index, sub_handle);
-
-		if (ret < 0)
-			goto error;
-
-		ret = setup_msi_irq(dev, msidesc, irq, 0);
-		if (ret < 0)
-			goto error;
-
-		sub_handle += 1;
-		irq        += 1;
-	}
-
-	return 0;
-
-error:
-	irq_free_hwirq(irq);
-	return ret;
-}
-
-static int irq_remapping_setup_msi_irqs(struct pci_dev *dev,
-					int nvec, int type)
-{
-	if (type == PCI_CAP_ID_MSI)
-		return do_setup_msi_irqs(dev, nvec);
-	else
-		return do_setup_msix_irqs(dev, nvec);
-}
-
-static void eoi_ioapic_pin_remapped(int apic, int pin, int vector)
-{
-	/*
-	 * Intr-remapping uses pin number as the virtual vector
-	 * in the RTE. Actual vector is programmed in
-	 * intr-remapping table entry. Hence for the io-apic
-	 * EOI we use the pin number.
-	 */
-	io_apic_eoi(apic, pin);
-}
-
 static void __init irq_remapping_modify_x86_ops(void)
 {
 	x86_io_apic_ops.disable		= irq_remapping_disable_io_apic;
-	x86_io_apic_ops.set_affinity	= set_remapped_irq_affinity;
-	x86_io_apic_ops.setup_entry	= setup_ioapic_remapped_entry;
-	x86_io_apic_ops.eoi_ioapic_pin	= eoi_ioapic_pin_remapped;
-	x86_msi.setup_msi_irqs		= irq_remapping_setup_msi_irqs;
-	x86_msi.setup_hpet_msi		= setup_hpet_msi_remapped;
-	x86_msi.compose_msi_msg		= compose_remapped_msi_msg;
 }
 
 static __init int setup_nointremap(char *str)
@@ -198,6 +81,15 @@ void set_irq_remapping_broken(void)
 	irq_remap_broken = 1;
 }
 
+bool irq_remapping_cap(enum irq_remap_cap cap)
+{
+	if (!remap_ops || disable_irq_post)
+		return 0;
+
+	return (remap_ops->capability & (1 << cap));
+}
+EXPORT_SYMBOL_GPL(irq_remapping_cap);
+
 int __init irq_remapping_prepare(void)
 {
 	if (disable_irq_remap)
@@ -254,113 +146,48 @@ int __init irq_remap_enable_fault_handling(void)
 	return remap_ops->enable_faulting();
 }
 
-int setup_ioapic_remapped_entry(int irq,
-				struct IO_APIC_route_entry *entry,
-				unsigned int destination, int vector,
-				struct io_apic_irq_attr *attr)
-{
-	if (!remap_ops->setup_ioapic_entry)
-		return -ENODEV;
-
-	return remap_ops->setup_ioapic_entry(irq, entry, destination,
-					     vector, attr);
-}
-
-static int set_remapped_irq_affinity(struct irq_data *data,
-				     const struct cpumask *mask, bool force)
-{
-	if (!config_enabled(CONFIG_SMP) || !remap_ops->set_affinity)
-		return 0;
-
-	return remap_ops->set_affinity(data, mask, force);
-}
-
-void free_remapped_irq(int irq)
-{
-	struct irq_cfg *cfg = irq_cfg(irq);
-
-	if (irq_remapped(cfg) && remap_ops->free_irq)
-		remap_ops->free_irq(irq);
-}
-
-void compose_remapped_msi_msg(struct pci_dev *pdev,
-			      unsigned int irq, unsigned int dest,
-			      struct msi_msg *msg, u8 hpet_id)
-{
-	struct irq_cfg *cfg = irq_cfg(irq);
-
-	if (!irq_remapped(cfg))
-		native_compose_msi_msg(pdev, irq, dest, msg, hpet_id);
-	else if (remap_ops->compose_msi_msg)
-		remap_ops->compose_msi_msg(pdev, irq, dest, msg, hpet_id);
-}
-
-static int msi_alloc_remapped_irq(struct pci_dev *pdev, int irq, int nvec)
-{
-	if (!remap_ops->msi_alloc_irq)
-		return -ENODEV;
-
-	return remap_ops->msi_alloc_irq(pdev, irq, nvec);
-}
-
-static int msi_setup_remapped_irq(struct pci_dev *pdev, unsigned int irq,
-				  int index, int sub_handle)
-{
-	if (!remap_ops->msi_setup_irq)
-		return -ENODEV;
-
-	return remap_ops->msi_setup_irq(pdev, irq, index, sub_handle);
-}
-
-int setup_hpet_msi_remapped(unsigned int irq, unsigned int id)
-{
-	int ret;
-
-	if (!remap_ops->alloc_hpet_msi)
-		return -ENODEV;
-
-	ret = remap_ops->alloc_hpet_msi(irq, id);
-	if (ret)
-		return -EINVAL;
-
-	return default_setup_hpet_msi(irq, id);
-}
-
 void panic_if_irq_remap(const char *msg)
 {
 	if (irq_remapping_enabled)
 		panic(msg);
 }
 
-static void ir_ack_apic_edge(struct irq_data *data)
+void ir_ack_apic_edge(struct irq_data *data)
 {
 	ack_APIC_irq();
 }
 
-static void ir_ack_apic_level(struct irq_data *data)
+/**
+ * irq_remapping_get_ir_irq_domain - Get the irqdomain associated with the IOMMU
+ *				     device serving request @info
+ * @info: interrupt allocation information, used to identify the IOMMU device
+ *
+ * It's used to get parent irqdomain for HPET and IOAPIC irqdomains.
+ * Returns pointer to IRQ domain, or NULL on failure.
+ */
+struct irq_domain *
+irq_remapping_get_ir_irq_domain(struct irq_alloc_info *info)
 {
-	ack_APIC_irq();
-	eoi_ioapic_irq(data->irq, irqd_cfg(data));
-}
+	if (!remap_ops || !remap_ops->get_ir_irq_domain)
+		return NULL;
 
-static void ir_print_prefix(struct irq_data *data, struct seq_file *p)
-{
-	seq_printf(p, " IR-%s", data->chip->name);
+	return remap_ops->get_ir_irq_domain(info);
 }
 
-void irq_remap_modify_chip_defaults(struct irq_chip *chip)
+/**
+ * irq_remapping_get_irq_domain - Get the irqdomain serving the request @info
+ * @info: interrupt allocation information, used to identify the IOMMU device
+ *
+ * There will be one PCI MSI/MSIX irqdomain associated with each interrupt
+ * remapping device, so this interface is used to retrieve the PCI MSI/MSIX
+ * irqdomain serving request @info.
+ * Returns pointer to IRQ domain, or NULL on failure.
+ */
+struct irq_domain *
+irq_remapping_get_irq_domain(struct irq_alloc_info *info)
 {
-	chip->irq_print_chip = ir_print_prefix;
-	chip->irq_ack = ir_ack_apic_edge;
-	chip->irq_eoi = ir_ack_apic_level;
-	chip->irq_set_affinity = x86_io_apic_ops.set_affinity;
-}
+	if (!remap_ops || !remap_ops->get_irq_domain)
+		return NULL;
 
-bool setup_remapped_irq(int irq, struct irq_cfg *cfg, struct irq_chip *chip)
-{
-	if (!irq_remapped(cfg))
-		return false;
-	irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
-	irq_remap_modify_chip_defaults(chip);
-	return true;
+	return remap_ops->get_irq_domain(info);
 }
diff --git a/drivers/iommu/irq_remapping.h b/drivers/iommu/irq_remapping.h
index 7c70cc29ffe6..039c7af7b190 100644
--- a/drivers/iommu/irq_remapping.h
+++ b/drivers/iommu/irq_remapping.h
@@ -24,19 +24,22 @@
 
 #ifdef CONFIG_IRQ_REMAP
 
-struct IO_APIC_route_entry;
-struct io_apic_irq_attr;
 struct irq_data;
-struct cpumask;
-struct pci_dev;
 struct msi_msg;
+struct irq_domain;
+struct irq_alloc_info;
 
 extern int irq_remap_broken;
 extern int disable_sourceid_checking;
 extern int no_x2apic_optout;
 extern int irq_remapping_enabled;
 
+extern int disable_irq_post;
+
 struct irq_remap_ops {
+	/* The supported capabilities */
+	int capability;
+
 	/* Initializes hardware and makes it ready for remapping interrupts */
 	int  (*prepare)(void);
 
@@ -52,40 +55,23 @@ struct irq_remap_ops {
 	/* Enable fault handling */
 	int  (*enable_faulting)(void);
 
-	/* IO-APIC setup routine */
-	int (*setup_ioapic_entry)(int irq, struct IO_APIC_route_entry *,
-				  unsigned int, int,
-				  struct io_apic_irq_attr *);
-
-	/* Set the CPU affinity of a remapped interrupt */
-	int (*set_affinity)(struct irq_data *data, const struct cpumask *mask,
-			    bool force);
-
-	/* Free an IRQ */
-	int (*free_irq)(int);
+	/* Get the irqdomain associated the IOMMU device */
+	struct irq_domain *(*get_ir_irq_domain)(struct irq_alloc_info *);
 
-	/* Create MSI msg to use for interrupt remapping */
-	void (*compose_msi_msg)(struct pci_dev *,
-				unsigned int, unsigned int,
-				struct msi_msg *, u8);
-
-	/* Allocate remapping resources for MSI */
-	int (*msi_alloc_irq)(struct pci_dev *, int, int);
-
-	/* Setup the remapped MSI irq */
-	int (*msi_setup_irq)(struct pci_dev *, unsigned int, int, int);
-
-	/* Setup interrupt remapping for an HPET MSI */
-	int (*alloc_hpet_msi)(unsigned int, unsigned int);
+	/* Get the MSI irqdomain associated with the IOMMU device */
+	struct irq_domain *(*get_irq_domain)(struct irq_alloc_info *);
 };
 
 extern struct irq_remap_ops intel_irq_remap_ops;
 extern struct irq_remap_ops amd_iommu_irq_ops;
 
+extern void ir_ack_apic_edge(struct irq_data *data);
+
 #else  /* CONFIG_IRQ_REMAP */
 
 #define irq_remapping_enabled 0
 #define irq_remap_broken      0
+#define disable_irq_post      1
 
 #endif /* CONFIG_IRQ_REMAP */
 
diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig
index 6de62a96e79c..99b9a9792975 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -30,6 +30,7 @@ config ARM_GIC_V3_ITS
 config ARM_NVIC
 	bool
 	select IRQ_DOMAIN
+	select IRQ_DOMAIN_HIERARCHY
 	select GENERIC_IRQ_CHIP
 
 config ARM_VIC
diff --git a/drivers/irqchip/exynos-combiner.c b/drivers/irqchip/exynos-combiner.c
index 5945223b73fa..5c82e3bdafdf 100644
--- a/drivers/irqchip/exynos-combiner.c
+++ b/drivers/irqchip/exynos-combiner.c
@@ -13,6 +13,7 @@
 #include <linux/init.h>
 #include <linux/io.h>
 #include <linux/slab.h>
+#include <linux/syscore_ops.h>
 #include <linux/irqdomain.h>
 #include <linux/irqchip/chained_irq.h>
 #include <linux/interrupt.h>
@@ -34,9 +35,14 @@ struct combiner_chip_data {
 	unsigned int irq_mask;
 	void __iomem *base;
 	unsigned int parent_irq;
+#ifdef CONFIG_PM
+	u32 pm_save;
+#endif
 };
 
+static struct combiner_chip_data *combiner_data;
 static struct irq_domain *combiner_irq_domain;
+static unsigned int max_nr = 20;
 
 static inline void __iomem *combiner_base(struct irq_data *data)
 {
@@ -164,18 +170,16 @@ static int combiner_irq_domain_map(struct irq_domain *d, unsigned int irq,
 	return 0;
 }
 
-static struct irq_domain_ops combiner_irq_domain_ops = {
+static const struct irq_domain_ops combiner_irq_domain_ops = {
 	.xlate	= combiner_irq_domain_xlate,
 	.map	= combiner_irq_domain_map,
 };
 
 static void __init combiner_init(void __iomem *combiner_base,
-				 struct device_node *np,
-				 unsigned int max_nr)
+				 struct device_node *np)
 {
 	int i, irq;
 	unsigned int nr_irq;
-	struct combiner_chip_data *combiner_data;
 
 	nr_irq = max_nr * IRQ_IN_COMBINER;
 
@@ -201,11 +205,59 @@ static void __init combiner_init(void __iomem *combiner_base,
 	}
 }
 
+#ifdef CONFIG_PM
+
+/**
+ * combiner_suspend - save interrupt combiner state before suspend
+ *
+ * Save the interrupt enable set register for all combiner groups since
+ * the state is lost when the system enters into a sleep state.
+ *
+ */
+static int combiner_suspend(void)
+{
+	int i;
+
+	for (i = 0; i < max_nr; i++)
+		combiner_data[i].pm_save =
+			__raw_readl(combiner_data[i].base + COMBINER_ENABLE_SET);
+
+	return 0;
+}
+
+/**
+ * combiner_resume - restore interrupt combiner state after resume
+ *
+ * Restore the interrupt enable set register for all combiner groups since
+ * the state is lost when the system enters into a sleep state on suspend.
+ *
+ */
+static void combiner_resume(void)
+{
+	int i;
+
+	for (i = 0; i < max_nr; i++) {
+		__raw_writel(combiner_data[i].irq_mask,
+			     combiner_data[i].base + COMBINER_ENABLE_CLEAR);
+		__raw_writel(combiner_data[i].pm_save,
+			     combiner_data[i].base + COMBINER_ENABLE_SET);
+	}
+}
+
+#else
+#define combiner_suspend	NULL
+#define combiner_resume		NULL
+#endif
+
+static struct syscore_ops combiner_syscore_ops = {
+	.suspend	= combiner_suspend,
+	.resume		= combiner_resume,
+};
+
 static int __init combiner_of_init(struct device_node *np,
 				   struct device_node *parent)
 {
 	void __iomem *combiner_base;
-	unsigned int max_nr = 20;
 
 	combiner_base = of_iomap(np, 0);
 	if (!combiner_base) {
@@ -219,7 +271,9 @@ static int __init combiner_of_init(struct device_node *np,
 			__func__, max_nr);
 	}
 
-	combiner_init(combiner_base, np, max_nr);
+	combiner_init(combiner_base, np);
+
+	register_syscore_ops(&combiner_syscore_ops);
 
 	return 0;
 }
diff --git a/drivers/irqchip/irq-armada-370-xp.c b/drivers/irqchip/irq-armada-370-xp.c
index daccc8bdbb42..0d3b0fe2f175 100644
--- a/drivers/irqchip/irq-armada-370-xp.c
+++ b/drivers/irqchip/irq-armada-370-xp.c
@@ -409,7 +409,7 @@ static struct notifier_block mpic_cascaded_cpu_notifier = {
 };
 #endif /* CONFIG_SMP */
 
-static struct irq_domain_ops armada_370_xp_mpic_irq_ops = {
+static const struct irq_domain_ops armada_370_xp_mpic_irq_ops = {
 	.map = armada_370_xp_mpic_irq_map,
 	.xlate = irq_domain_xlate_onecell,
 };
diff --git a/drivers/irqchip/irq-atmel-aic5.c b/drivers/irqchip/irq-atmel-aic5.c
index a2e8c3f876cb..459bf4429d36 100644
--- a/drivers/irqchip/irq-atmel-aic5.c
+++ b/drivers/irqchip/irq-atmel-aic5.c
@@ -339,6 +339,15 @@ static int __init aic5_of_init(struct device_node *node,
 	return 0;
 }
 
+#define NR_SAMA5D2_IRQS		77
+
+static int __init sama5d2_aic5_of_init(struct device_node *node,
+				       struct device_node *parent)
+{
+	return aic5_of_init(node, parent, NR_SAMA5D2_IRQS);
+}
+IRQCHIP_DECLARE(sama5d2_aic5, "atmel,sama5d2-aic", sama5d2_aic5_of_init);
+
 #define NR_SAMA5D3_IRQS		48
 
 static int __init sama5d3_aic5_of_init(struct device_node *node,
diff --git a/drivers/irqchip/irq-bcm2835.c b/drivers/irqchip/irq-bcm2835.c
index 5916d6cdafa1..e68c3b60a681 100644
--- a/drivers/irqchip/irq-bcm2835.c
+++ b/drivers/irqchip/irq-bcm2835.c
@@ -135,7 +135,7 @@ static int armctrl_xlate(struct irq_domain *d, struct device_node *ctrlr,
 	return 0;
 }
 
-static struct irq_domain_ops armctrl_ops = {
+static const struct irq_domain_ops armctrl_ops = {
 	.xlate = armctrl_xlate
 };
 
diff --git a/drivers/irqchip/irq-gic-common.c b/drivers/irqchip/irq-gic-common.c
index ad96ebb0c7ab..9448e391cb71 100644
--- a/drivers/irqchip/irq-gic-common.c
+++ b/drivers/irqchip/irq-gic-common.c
@@ -24,11 +24,8 @@
 int gic_configure_irq(unsigned int irq, unsigned int type,
 		       void __iomem *base, void (*sync_access)(void))
 {
-	u32 enablemask = 1 << (irq % 32);
-	u32 enableoff = (irq / 32) * 4;
 	u32 confmask = 0x2 << ((irq % 16) * 2);
 	u32 confoff = (irq / 16) * 4;
-	bool enabled = false;
 	u32 val, oldval;
 	int ret = 0;
 
@@ -43,17 +40,6 @@ int gic_configure_irq(unsigned int irq, unsigned int type,
 		val |= confmask;
 
 	/*
-	 * As recommended by the spec, disable the interrupt before changing
-	 * the configuration
-	 */
-	if (readl_relaxed(base + GIC_DIST_ENABLE_SET + enableoff) & enablemask) {
-		writel_relaxed(enablemask, base + GIC_DIST_ENABLE_CLEAR + enableoff);
-		if (sync_access)
-			sync_access();
-		enabled = true;
-	}
-
-	/*
 	 * Write back the new configuration, and possibly re-enable
 	 * the interrupt. If we tried to write a new configuration and failed,
 	 * return an error.
@@ -62,9 +48,6 @@ int gic_configure_irq(unsigned int irq, unsigned int type,
 	if (readl_relaxed(base + GIC_DIST_CONFIG + confoff) != val && val != oldval)
 		ret = -EINVAL;
 
-	if (enabled)
-		writel_relaxed(enablemask, base + GIC_DIST_ENABLE_SET + enableoff);
-
 	if (sync_access)
 		sync_access();
 
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index 49875adb6b44..c52f7ba205b4 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -658,6 +658,7 @@ static struct irq_chip gic_chip = {
 	.irq_set_affinity	= gic_set_affinity,
 	.irq_get_irqchip_state	= gic_irq_get_irqchip_state,
 	.irq_set_irqchip_state	= gic_irq_set_irqchip_state,
+	.flags			= IRQCHIP_SET_TYPE_MASKED,
 };
 
 #define GIC_ID_NR		(1U << gic_data.rdists.id_bits)
diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index 01999d74bd3a..8d7e1c8b6d56 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -324,6 +324,7 @@ static struct irq_chip gic_chip = {
 #endif
 	.irq_get_irqchip_state	= gic_irq_get_irqchip_state,
 	.irq_set_irqchip_state	= gic_irq_set_irqchip_state,
+	.flags			= IRQCHIP_SET_TYPE_MASKED,
 };
 
 void __init gic_cascade_irq(unsigned int gic_nr, unsigned int irq)
diff --git a/drivers/irqchip/irq-hip04.c b/drivers/irqchip/irq-hip04.c
index 7d6ffb5de84f..0cae45d10695 100644
--- a/drivers/irqchip/irq-hip04.c
+++ b/drivers/irqchip/irq-hip04.c
@@ -202,6 +202,7 @@ static struct irq_chip hip04_irq_chip = {
 #ifdef CONFIG_SMP
 	.irq_set_affinity	= hip04_irq_set_affinity,
 #endif
+	.flags			= IRQCHIP_SET_TYPE_MASKED,
 };
 
 static u16 hip04_get_cpumask(struct hip04_irq_data *intc)
diff --git a/drivers/irqchip/irq-keystone.c b/drivers/irqchip/irq-keystone.c
index 78e8b3ce5252..81e3cf5b9a1f 100644
--- a/drivers/irqchip/irq-keystone.c
+++ b/drivers/irqchip/irq-keystone.c
@@ -131,7 +131,7 @@ static int keystone_irq_map(struct irq_domain *h, unsigned int virq,
 	return 0;
 }
 
-static struct irq_domain_ops keystone_irq_ops = {
+static const struct irq_domain_ops keystone_irq_ops = {
 	.map	= keystone_irq_map,
 	.xlate	= irq_domain_xlate_onecell,
 };
@@ -184,8 +184,7 @@ static int keystone_irq_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, kirq);
 
-	irq_set_chained_handler(kirq->irq, keystone_irq_handler);
-	irq_set_handler_data(kirq->irq, kirq);
+	irq_set_chained_handler_and_data(kirq->irq, keystone_irq_handler, kirq);
 
 	/* clear all source bits */
 	keystone_irq_writel(kirq, ~0x0);
diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c
index 269c2354c431..4400edd1a6c7 100644
--- a/drivers/irqchip/irq-mips-gic.c
+++ b/drivers/irqchip/irq-mips-gic.c
@@ -746,7 +746,7 @@ static int gic_irq_domain_xlate(struct irq_domain *d, struct device_node *ctrlr,
 	return 0;
 }
 
-static struct irq_domain_ops gic_irq_domain_ops = {
+static const struct irq_domain_ops gic_irq_domain_ops = {
 	.map = gic_irq_domain_map,
 	.xlate = gic_irq_domain_xlate,
 };
diff --git a/drivers/irqchip/irq-mtk-sysirq.c b/drivers/irqchip/irq-mtk-sysirq.c
index eaf0a710e98a..15c13039bba2 100644
--- a/drivers/irqchip/irq-mtk-sysirq.c
+++ b/drivers/irqchip/irq-mtk-sysirq.c
@@ -111,7 +111,7 @@ static int mtk_sysirq_domain_alloc(struct irq_domain *domain, unsigned int virq,
 	return irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, &gic_data);
 }
 
-static struct irq_domain_ops sysirq_domain_ops = {
+static const struct irq_domain_ops sysirq_domain_ops = {
 	.xlate = mtk_sysirq_domain_xlate,
 	.alloc = mtk_sysirq_domain_alloc,
 	.free = irq_domain_free_irqs_common,
@@ -144,7 +144,7 @@ static int __init mtk_sysirq_of_init(struct device_node *node,
 	chip_data->intpol_base = ioremap(res.start, size);
 	if (!chip_data->intpol_base) {
 		pr_err("mtk_sysirq: unable to map sysirq register\n");
-		ret = PTR_ERR(chip_data->intpol_base);
+		ret = -ENXIO;
 		goto out_free;
 	}
 
diff --git a/drivers/irqchip/irq-mxs.c b/drivers/irqchip/irq-mxs.c
index e4acf1e3f8e3..04bf97b289cf 100644
--- a/drivers/irqchip/irq-mxs.c
+++ b/drivers/irqchip/irq-mxs.c
@@ -90,7 +90,7 @@ static int icoll_irq_domain_map(struct irq_domain *d, unsigned int virq,
 	return 0;
 }
 
-static struct irq_domain_ops icoll_irq_domain_ops = {
+static const struct irq_domain_ops icoll_irq_domain_ops = {
 	.map = icoll_irq_domain_map,
 	.xlate = irq_domain_xlate_onecell,
 };
diff --git a/drivers/irqchip/irq-nvic.c b/drivers/irqchip/irq-nvic.c
index 4ff0805fca01..5fac9100f6cb 100644
--- a/drivers/irqchip/irq-nvic.c
+++ b/drivers/irqchip/irq-nvic.c
@@ -49,6 +49,31 @@ nvic_handle_irq(irq_hw_number_t hwirq, struct pt_regs *regs)
 	handle_IRQ(irq, regs);
 }
 
+static int nvic_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
+				unsigned int nr_irqs, void *arg)
+{
+	int i, ret;
+	irq_hw_number_t hwirq;
+	unsigned int type = IRQ_TYPE_NONE;
+	struct of_phandle_args *irq_data = arg;
+
+	ret = irq_domain_xlate_onecell(domain, irq_data->np, irq_data->args,
+				   irq_data->args_count, &hwirq, &type);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < nr_irqs; i++)
+		irq_map_generic_chip(domain, virq + i, hwirq + i);
+
+	return 0;
+}
+
+static const struct irq_domain_ops nvic_irq_domain_ops = {
+	.xlate = irq_domain_xlate_onecell,
+	.alloc = nvic_irq_domain_alloc,
+	.free = irq_domain_free_irqs_top,
+};
+
 static int __init nvic_of_init(struct device_node *node,
 			       struct device_node *parent)
 {
@@ -70,7 +95,8 @@ static int __init nvic_of_init(struct device_node *node,
 		irqs = NVIC_MAX_IRQ;
 
 	nvic_irq_domain =
-		irq_domain_add_linear(node, irqs, &irq_generic_chip_ops, NULL);
+		irq_domain_add_linear(node, irqs, &nvic_irq_domain_ops, NULL);
+
 	if (!nvic_irq_domain) {
 		pr_warn("Failed to allocate irq domain\n");
 		return -ENOMEM;
diff --git a/drivers/irqchip/irq-renesas-intc-irqpin.c b/drivers/irqchip/irq-renesas-intc-irqpin.c
index 9a0767b9c89d..0670ab4e3897 100644
--- a/drivers/irqchip/irq-renesas-intc-irqpin.c
+++ b/drivers/irqchip/irq-renesas-intc-irqpin.c
@@ -347,7 +347,7 @@ static int intc_irqpin_irq_domain_map(struct irq_domain *h, unsigned int virq,
 	return 0;
 }
 
-static struct irq_domain_ops intc_irqpin_irq_domain_ops = {
+static const struct irq_domain_ops intc_irqpin_irq_domain_ops = {
 	.map	= intc_irqpin_irq_domain_map,
 	.xlate  = irq_domain_xlate_twocell,
 };
diff --git a/drivers/irqchip/irq-renesas-irqc.c b/drivers/irqchip/irq-renesas-irqc.c
index cdf80b7794cd..778bd076aeea 100644
--- a/drivers/irqchip/irq-renesas-irqc.c
+++ b/drivers/irqchip/irq-renesas-irqc.c
@@ -29,7 +29,6 @@
 #include <linux/err.h>
 #include <linux/slab.h>
 #include <linux/module.h>
-#include <linux/platform_data/irq-renesas-irqc.h>
 #include <linux/pm_runtime.h>
 
 #define IRQC_IRQ_MAX	32	/* maximum 32 interrupts per driver instance */
@@ -62,7 +61,6 @@ struct irqc_priv {
 	void __iomem *iomem;
 	void __iomem *cpu_int_base;
 	struct irqc_irq irq[IRQC_IRQ_MAX];
-	struct renesas_irqc_config config;
 	unsigned int number_of_irqs;
 	struct platform_device *pdev;
 	struct irq_chip irq_chip;
@@ -168,14 +166,13 @@ static int irqc_irq_domain_map(struct irq_domain *h, unsigned int virq,
 	return 0;
 }
 
-static struct irq_domain_ops irqc_irq_domain_ops = {
+static const struct irq_domain_ops irqc_irq_domain_ops = {
 	.map	= irqc_irq_domain_map,
 	.xlate  = irq_domain_xlate_twocell,
 };
 
 static int irqc_probe(struct platform_device *pdev)
 {
-	struct renesas_irqc_config *pdata = pdev->dev.platform_data;
 	struct irqc_priv *p;
 	struct resource *io;
 	struct resource *irq;
@@ -191,10 +188,6 @@ static int irqc_probe(struct platform_device *pdev)
 		goto err0;
 	}
 
-	/* deal with driver instance configuration */
-	if (pdata)
-		memcpy(&p->config, pdata, sizeof(*pdata));
-
 	p->pdev = pdev;
 	platform_set_drvdata(pdev, p);
 
@@ -251,8 +244,7 @@ static int irqc_probe(struct platform_device *pdev)
 	irq_chip->flags	= IRQCHIP_MASK_ON_SUSPEND;
 
 	p->irq_domain = irq_domain_add_simple(pdev->dev.of_node,
-					      p->number_of_irqs,
-					      p->config.irq_base,
+					      p->number_of_irqs, 0,
 					      &irqc_irq_domain_ops, p);
 	if (!p->irq_domain) {
 		ret = -ENXIO;
@@ -272,13 +264,6 @@ static int irqc_probe(struct platform_device *pdev)
 
 	dev_info(&pdev->dev, "driving %d irqs\n", p->number_of_irqs);
 
-	/* warn in case of mismatch if irq base is specified */
-	if (p->config.irq_base) {
-		if (p->config.irq_base != p->irq[0].domain_irq)
-			dev_warn(&pdev->dev, "irq base mismatch (%d/%d)\n",
-				 p->config.irq_base, p->irq[0].domain_irq);
-	}
-
 	return 0;
 err3:
 	while (--k >= 0)
diff --git a/drivers/irqchip/irq-s3c24xx.c b/drivers/irqchip/irq-s3c24xx.c
index c8d373fcd823..e96717f45ea1 100644
--- a/drivers/irqchip/irq-s3c24xx.c
+++ b/drivers/irqchip/irq-s3c24xx.c
@@ -502,7 +502,7 @@ err:
 	return -EINVAL;
 }
 
-static struct irq_domain_ops s3c24xx_irq_ops = {
+static const struct irq_domain_ops s3c24xx_irq_ops = {
 	.map = s3c24xx_irq_map,
 	.xlate = irq_domain_xlate_twocell,
 };
@@ -1228,7 +1228,7 @@ static int s3c24xx_irq_xlate_of(struct irq_domain *d, struct device_node *n,
 	return 0;
 }
 
-static struct irq_domain_ops s3c24xx_irq_ops_of = {
+static const struct irq_domain_ops s3c24xx_irq_ops_of = {
 	.map = s3c24xx_irq_map_of,
 	.xlate = s3c24xx_irq_xlate_of,
 };
diff --git a/drivers/irqchip/irq-sun4i.c b/drivers/irqchip/irq-sun4i.c
index 64155b686081..83d6aa6464ee 100644
--- a/drivers/irqchip/irq-sun4i.c
+++ b/drivers/irqchip/irq-sun4i.c
@@ -89,7 +89,7 @@ static int sun4i_irq_map(struct irq_domain *d, unsigned int virq,
 	return 0;
 }
 
-static struct irq_domain_ops sun4i_irq_ops = {
+static const struct irq_domain_ops sun4i_irq_ops = {
 	.map = sun4i_irq_map,
 	.xlate = irq_domain_xlate_onecell,
 };
diff --git a/drivers/irqchip/irq-versatile-fpga.c b/drivers/irqchip/irq-versatile-fpga.c
index 1ab451729a5c..888111b76ea0 100644
--- a/drivers/irqchip/irq-versatile-fpga.c
+++ b/drivers/irqchip/irq-versatile-fpga.c
@@ -132,7 +132,7 @@ static int fpga_irqdomain_map(struct irq_domain *d, unsigned int irq,
 	return 0;
 }
 
-static struct irq_domain_ops fpga_irqdomain_ops = {
+static const struct irq_domain_ops fpga_irqdomain_ops = {
 	.map = fpga_irqdomain_map,
 	.xlate = irq_domain_xlate_onetwocell,
 };
diff --git a/drivers/irqchip/irq-vf610-mscm-ir.c b/drivers/irqchip/irq-vf610-mscm-ir.c
index 9521057d4744..f5c01cbcc73a 100644
--- a/drivers/irqchip/irq-vf610-mscm-ir.c
+++ b/drivers/irqchip/irq-vf610-mscm-ir.c
@@ -47,6 +47,7 @@ struct vf610_mscm_ir_chip_data {
 	void __iomem *mscm_ir_base;
 	u16 cpu_mask;
 	u16 saved_irsprc[MSCM_IRSPRC_NUM];
+	bool is_nvic;
 };
 
 static struct vf610_mscm_ir_chip_data *mscm_ir_data;
@@ -101,7 +102,7 @@ static void vf610_mscm_ir_enable(struct irq_data *data)
 	writew_relaxed(chip_data->cpu_mask,
 		       chip_data->mscm_ir_base + MSCM_IRSPRC(hwirq));
 
-	irq_chip_unmask_parent(data);
+	irq_chip_enable_parent(data);
 }
 
 static void vf610_mscm_ir_disable(struct irq_data *data)
@@ -111,7 +112,7 @@ static void vf610_mscm_ir_disable(struct irq_data *data)
 
 	writew_relaxed(0x0, chip_data->mscm_ir_base + MSCM_IRSPRC(hwirq));
 
-	irq_chip_mask_parent(data);
+	irq_chip_disable_parent(data);
 }
 
 static struct irq_chip vf610_mscm_ir_irq_chip = {
@@ -143,10 +144,17 @@ static int vf610_mscm_ir_domain_alloc(struct irq_domain *domain, unsigned int vi
 					      domain->host_data);
 
 	gic_data.np = domain->parent->of_node;
-	gic_data.args_count = 3;
-	gic_data.args[0] = GIC_SPI;
-	gic_data.args[1] = irq_data->args[0];
-	gic_data.args[2] = irq_data->args[1];
+
+	if (mscm_ir_data->is_nvic) {
+		gic_data.args_count = 1;
+		gic_data.args[0] = irq_data->args[0];
+	} else {
+		gic_data.args_count = 3;
+		gic_data.args[0] = GIC_SPI;
+		gic_data.args[1] = irq_data->args[0];
+		gic_data.args[2] = irq_data->args[1];
+	}
+
 	return irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, &gic_data);
 }
 
@@ -174,10 +182,9 @@ static int __init vf610_mscm_ir_of_init(struct device_node *node,
 		return -ENOMEM;
 
 	mscm_ir_data->mscm_ir_base = of_io_request_and_map(node, 0, "mscm-ir");
-
-	if (!mscm_ir_data->mscm_ir_base) {
+	if (IS_ERR(mscm_ir_data->mscm_ir_base)) {
 		pr_err("vf610_mscm_ir: unable to map mscm register\n");
-		ret = -ENOMEM;
+		ret = PTR_ERR(mscm_ir_data->mscm_ir_base);
 		goto out_free;
 	}
 
@@ -199,6 +206,9 @@ static int __init vf610_mscm_ir_of_init(struct device_node *node,
 		goto out_unmap;
 	}
 
+	if (of_device_is_compatible(domain->parent->of_node, "arm,armv7m-nvic"))
+		mscm_ir_data->is_nvic = true;
+
 	cpu_pm_register_notifier(&mscm_ir_notifier_block);
 
 	return 0;
diff --git a/drivers/irqchip/irq-vic.c b/drivers/irqchip/irq-vic.c
index 54089debf2dc..d4ce331ea4a0 100644
--- a/drivers/irqchip/irq-vic.c
+++ b/drivers/irqchip/irq-vic.c
@@ -256,7 +256,7 @@ static void __exception_irq_entry vic_handle_irq(struct pt_regs *regs)
 	} while (handled);
 }
 
-static struct irq_domain_ops vic_irqdomain_ops = {
+static const struct irq_domain_ops vic_irqdomain_ops = {
 	.map = vic_irqdomain_map,
 	.xlate = irq_domain_xlate_onetwocell,
 };
diff --git a/drivers/irqchip/irq-vt8500.c b/drivers/irqchip/irq-vt8500.c
index b7af816f2769..0b297009b856 100644
--- a/drivers/irqchip/irq-vt8500.c
+++ b/drivers/irqchip/irq-vt8500.c
@@ -173,7 +173,7 @@ static int vt8500_irq_map(struct irq_domain *h, unsigned int virq,
 	return 0;
 }
 
-static struct irq_domain_ops vt8500_irq_domain_ops = {
+static const struct irq_domain_ops vt8500_irq_domain_ops = {
 	.map = vt8500_irq_map,
 	.xlate = irq_domain_xlate_onecell,
 };
diff --git a/drivers/irqchip/spear-shirq.c b/drivers/irqchip/spear-shirq.c
index 9c145a7cb056..a45121546caf 100644
--- a/drivers/irqchip/spear-shirq.c
+++ b/drivers/irqchip/spear-shirq.c
@@ -207,8 +207,7 @@ static void __init spear_shirq_register(struct spear_shirq *shirq,
 	if (!shirq->irq_chip)
 		return;
 
-	irq_set_chained_handler(parent_irq, shirq_handler);
-	irq_set_handler_data(parent_irq, shirq);
+	irq_set_chained_handler_and_data(parent_irq, shirq_handler, shirq);
 
 	for (i = 0; i < shirq->nr_irqs; i++) {
 		irq_set_chip_and_handler(shirq->virq_base + i,
diff --git a/drivers/isdn/i4l/isdn_net.c b/drivers/isdn/i4l/isdn_net.c
index 546b7e81161d..aa5dd5668528 100644
--- a/drivers/isdn/i4l/isdn_net.c
+++ b/drivers/isdn/i4l/isdn_net.c
@@ -58,7 +58,7 @@
  * About SOFTNET:
  * Most of the changes were pretty obvious and basically done by HE already.
  *
- * One problem of the isdn net device code is that is uses struct net_device
+ * One problem of the isdn net device code is that it uses struct net_device
  * for masters and slaves. However, only master interface are registered to
  * the network layer, and therefore, it only makes sense to call netif_*
  * functions on them.
diff --git a/drivers/lguest/interrupts_and_traps.c b/drivers/lguest/interrupts_and_traps.c
index 5e7559be222a..eb934b0242e0 100644
--- a/drivers/lguest/interrupts_and_traps.c
+++ b/drivers/lguest/interrupts_and_traps.c
@@ -20,7 +20,7 @@
 #include "lg.h"
 
 /* Allow Guests to use a non-128 (ie. non-Linux) syscall trap. */
-static unsigned int syscall_vector = SYSCALL_VECTOR;
+static unsigned int syscall_vector = IA32_SYSCALL_VECTOR;
 module_param(syscall_vector, uint, 0444);
 
 /* The address of the interrupt handler is split into two bits: */
@@ -333,8 +333,8 @@ void set_interrupt(struct lg_cpu *cpu, unsigned int irq)
  */
 static bool could_be_syscall(unsigned int num)
 {
-	/* Normal Linux SYSCALL_VECTOR or reserved vector? */
-	return num == SYSCALL_VECTOR || num == syscall_vector;
+	/* Normal Linux IA32_SYSCALL_VECTOR or reserved vector? */
+	return num == IA32_SYSCALL_VECTOR || num == syscall_vector;
 }
 
 /* The syscall vector it wants must be unused by Host. */
@@ -351,7 +351,7 @@ bool check_syscall_vector(struct lguest *lg)
 int init_interrupts(void)
 {
 	/* If they want some strange system call vector, reserve it now */
-	if (syscall_vector != SYSCALL_VECTOR) {
+	if (syscall_vector != IA32_SYSCALL_VECTOR) {
 		if (test_bit(syscall_vector, used_vectors) ||
 		    vector_used_by_percpu_irq(syscall_vector)) {
 			printk(KERN_ERR "lg: couldn't reserve syscall %u\n",
@@ -366,7 +366,7 @@ int init_interrupts(void)
 
 void free_interrupts(void)
 {
-	if (syscall_vector != SYSCALL_VECTOR)
+	if (syscall_vector != IA32_SYSCALL_VECTOR)
 		clear_bit(syscall_vector, used_vectors);
 }
 
diff --git a/drivers/lguest/x86/core.c b/drivers/lguest/x86/core.c
index 30f2aef69d78..6a4cd771a2be 100644
--- a/drivers/lguest/x86/core.c
+++ b/drivers/lguest/x86/core.c
@@ -46,7 +46,7 @@
 #include <asm/setup.h>
 #include <asm/lguest.h>
 #include <asm/uaccess.h>
-#include <asm/i387.h>
+#include <asm/fpu/internal.h>
 #include <asm/tlbflush.h>
 #include "../lg.h"
 
@@ -251,7 +251,7 @@ void lguest_arch_run_guest(struct lg_cpu *cpu)
 	 * we set it now, so we can trap and pass that trap to the Guest if it
 	 * uses the FPU.
 	 */
-	if (cpu->ts && user_has_fpu())
+	if (cpu->ts && fpregs_active())
 		stts();
 
 	/*
@@ -283,7 +283,7 @@ void lguest_arch_run_guest(struct lg_cpu *cpu)
 		wrmsr(MSR_IA32_SYSENTER_CS, __KERNEL_CS, 0);
 
 	/* Clear the host TS bit if it was set above. */
-	if (cpu->ts && user_has_fpu())
+	if (cpu->ts && fpregs_active())
 		clts();
 
 	/*
@@ -297,12 +297,12 @@ void lguest_arch_run_guest(struct lg_cpu *cpu)
 	/*
 	 * Similarly, if we took a trap because the Guest used the FPU,
 	 * we have to restore the FPU it expects to see.
-	 * math_state_restore() may sleep and we may even move off to
+	 * fpu__restore() may sleep and we may even move off to
 	 * a different CPU. So all the critical stuff should be done
 	 * before this.
 	 */
-	else if (cpu->regs->trapnum == 7 && !user_has_fpu())
-		math_state_restore();
+	else if (cpu->regs->trapnum == 7 && !fpregs_active())
+		fpu__restore(&current->thread.fpu);
 }
 
 /*H:130
diff --git a/drivers/media/Kconfig b/drivers/media/Kconfig
index 3ef0f90b128f..157099243d61 100644
--- a/drivers/media/Kconfig
+++ b/drivers/media/Kconfig
@@ -97,6 +97,7 @@ config MEDIA_CONTROLLER
 config MEDIA_CONTROLLER_DVB
 	bool "Enable Media controller for DVB"
 	depends on MEDIA_CONTROLLER
+	depends on BROKEN
 	---help---
 	  Enable the media controller API support for DVB.
 
diff --git a/drivers/media/pci/cx25821/cx25821-medusa-reg.h b/drivers/media/pci/cx25821/cx25821-medusa-reg.h
index c98ac946b277..2e10643a86b7 100644
--- a/drivers/media/pci/cx25821/cx25821-medusa-reg.h
+++ b/drivers/media/pci/cx25821/cx25821-medusa-reg.h
@@ -84,9 +84,9 @@
 #define	ABIST_BIN4_VGA3				0x01D4
 #define	ABIST_BIN5_VGA4				0x01D8
 #define	ABIST_BIN6_VGA5				0x01DC
-#define	ABIST_BIN7_VGA6				0x0x1E0
-#define	ABIST_CLAMP_A				0x0x1E4
-#define	ABIST_CLAMP_B				0x0x1E8
+#define	ABIST_BIN7_VGA6				0x01E0
+#define	ABIST_CLAMP_A				0x01E4
+#define	ABIST_CLAMP_B				0x01E8
 #define	ABIST_CLAMP_C				0x01EC
 #define	ABIST_CLAMP_D				0x01F0
 #define	ABIST_CLAMP_E				0x01F4
diff --git a/drivers/media/pci/ivtv/Kconfig b/drivers/media/pci/ivtv/Kconfig
index dd6ee57e3a4c..6e5867c57305 100644
--- a/drivers/media/pci/ivtv/Kconfig
+++ b/drivers/media/pci/ivtv/Kconfig
@@ -57,5 +57,8 @@ config VIDEO_FB_IVTV
 	  This is used in the Hauppauge PVR-350 card. There is a driver
 	  homepage at <http://www.ivtvdriver.org>.
 
+	  In order to use this module, you will need to boot with PAT disabled
+	  on x86 systems, using the nopat kernel parameter.
+
 	  To compile this driver as a module, choose M here: the
 	  module will be called ivtvfb.
diff --git a/drivers/media/pci/ivtv/ivtvfb.c b/drivers/media/pci/ivtv/ivtvfb.c
index 9ff1230192e8..4cb365d4ffdc 100644
--- a/drivers/media/pci/ivtv/ivtvfb.c
+++ b/drivers/media/pci/ivtv/ivtvfb.c
@@ -44,8 +44,8 @@
 #include <linux/ivtvfb.h>
 #include <linux/slab.h>
 
-#ifdef CONFIG_MTRR
-#include <asm/mtrr.h>
+#ifdef CONFIG_X86_64
+#include <asm/pat.h>
 #endif
 
 #include "ivtv-driver.h"
@@ -155,12 +155,11 @@ struct osd_info {
 	/* Buffer size */
 	u32 video_buffer_size;
 
-#ifdef CONFIG_MTRR
 	/* video_base rounded down as required by hardware MTRRs */
 	unsigned long fb_start_aligned_physaddr;
 	/* video_base rounded up as required by hardware MTRRs */
 	unsigned long fb_end_aligned_physaddr;
-#endif
+	int wc_cookie;
 
 	/* Store the buffer offset */
 	int set_osd_coords_x;
@@ -1099,6 +1098,8 @@ static int ivtvfb_init_vidmode(struct ivtv *itv)
 static int ivtvfb_init_io(struct ivtv *itv)
 {
 	struct osd_info *oi = itv->osd_info;
+	/* Find the largest power of two that maps the whole buffer */
+	int size_shift = 31;
 
 	mutex_lock(&itv->serialize_lock);
 	if (ivtv_init_on_first_open(itv)) {
@@ -1132,29 +1133,16 @@ static int ivtvfb_init_io(struct ivtv *itv)
 			oi->video_pbase, oi->video_vbase,
 			oi->video_buffer_size / 1024);
 
-#ifdef CONFIG_MTRR
-	{
-		/* Find the largest power of two that maps the whole buffer */
-		int size_shift = 31;
-
-		while (!(oi->video_buffer_size & (1 << size_shift))) {
-			size_shift--;
-		}
-		size_shift++;
-		oi->fb_start_aligned_physaddr = oi->video_pbase & ~((1 << size_shift) - 1);
-		oi->fb_end_aligned_physaddr = oi->video_pbase + oi->video_buffer_size;
-		oi->fb_end_aligned_physaddr += (1 << size_shift) - 1;
-		oi->fb_end_aligned_physaddr &= ~((1 << size_shift) - 1);
-		if (mtrr_add(oi->fb_start_aligned_physaddr,
-			oi->fb_end_aligned_physaddr - oi->fb_start_aligned_physaddr,
-			     MTRR_TYPE_WRCOMB, 1) < 0) {
-			IVTVFB_INFO("disabled mttr\n");
-			oi->fb_start_aligned_physaddr = 0;
-			oi->fb_end_aligned_physaddr = 0;
-		}
-	}
-#endif
-
+	while (!(oi->video_buffer_size & (1 << size_shift)))
+		size_shift--;
+	size_shift++;
+	oi->fb_start_aligned_physaddr = oi->video_pbase & ~((1 << size_shift) - 1);
+	oi->fb_end_aligned_physaddr = oi->video_pbase + oi->video_buffer_size;
+	oi->fb_end_aligned_physaddr += (1 << size_shift) - 1;
+	oi->fb_end_aligned_physaddr &= ~((1 << size_shift) - 1);
+	oi->wc_cookie = arch_phys_wc_add(oi->fb_start_aligned_physaddr,
+					 oi->fb_end_aligned_physaddr -
+					 oi->fb_start_aligned_physaddr);
 	/* Blank the entire osd. */
 	memset_io(oi->video_vbase, 0, oi->video_buffer_size);
 
@@ -1172,14 +1160,7 @@ static void ivtvfb_release_buffers (struct ivtv *itv)
 
 	/* Release pseudo palette */
 	kfree(oi->ivtvfb_info.pseudo_palette);
-
-#ifdef CONFIG_MTRR
-	if (oi->fb_end_aligned_physaddr) {
-		mtrr_del(-1, oi->fb_start_aligned_physaddr,
-			oi->fb_end_aligned_physaddr - oi->fb_start_aligned_physaddr);
-	}
-#endif
-
+	arch_phys_wc_del(oi->wc_cookie);
 	kfree(oi);
 	itv->osd_info = NULL;
 }
@@ -1284,6 +1265,13 @@ static int __init ivtvfb_init(void)
 	int registered = 0;
 	int err;
 
+#ifdef CONFIG_X86_64
+	if (WARN(pat_enabled(),
+		 "ivtvfb needs PAT disabled, boot with nopat kernel parameter\n")) {
+		return -ENODEV;
+	}
+#endif
+
 	if (ivtvfb_card_id < -1 || ivtvfb_card_id >= IVTV_MAX_CARDS) {
 		printk(KERN_ERR "ivtvfb:  ivtvfb_card_id parameter is out of range (valid range: -1 - %d)\n",
 		     IVTV_MAX_CARDS - 1);
diff --git a/drivers/mfd/ucb1x00-core.c b/drivers/mfd/ucb1x00-core.c
index 58ea9fdd3a15..3591550598ad 100644
--- a/drivers/mfd/ucb1x00-core.c
+++ b/drivers/mfd/ucb1x00-core.c
@@ -566,8 +566,7 @@ static int ucb1x00_probe(struct mcp *mcp)
 	}
 
 	irq_set_irq_type(ucb->irq, IRQ_TYPE_EDGE_RISING);
-	irq_set_handler_data(ucb->irq, ucb);
-	irq_set_chained_handler(ucb->irq, ucb1x00_irq);
+	irq_set_chained_handler_and_data(ucb->irq, ucb1x00_irq, ucb);
 
 	if (pdata && pdata->gpio_base) {
 		ucb->gpio.label = dev_name(&ucb->dev);
diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
index 60f7141a6b02..c9c3d20b784b 100644
--- a/drivers/mmc/card/block.c
+++ b/drivers/mmc/card/block.c
@@ -913,6 +913,9 @@ static int mmc_blk_cmd_recovery(struct mmc_card *card, struct request *req,
 		if (!err)
 			break;
 
+		/* Re-tune if needed */
+		mmc_retune_recheck(card->host);
+
 		prev_cmd_status_valid = false;
 		pr_err("%s: error %d sending status command, %sing\n",
 		       req->rq_disk->disk_name, err, retry ? "retry" : "abort");
@@ -1204,6 +1207,7 @@ static int mmc_blk_err_check(struct mmc_card *card,
 						    mmc_active);
 	struct mmc_blk_request *brq = &mq_mrq->brq;
 	struct request *req = mq_mrq->req;
+	int need_retune = card->host->need_retune;
 	int ecc_err = 0, gen_err = 0;
 
 	/*
@@ -1271,6 +1275,12 @@ static int mmc_blk_err_check(struct mmc_card *card,
 	}
 
 	if (brq->data.error) {
+		if (need_retune && !brq->retune_retry_done) {
+			pr_info("%s: retrying because a re-tune was needed\n",
+				req->rq_disk->disk_name);
+			brq->retune_retry_done = 1;
+			return MMC_BLK_RETRY;
+		}
 		pr_err("%s: error %d transferring data, sector %u, nr %u, cmd response %#x, card status %#x\n",
 		       req->rq_disk->disk_name, brq->data.error,
 		       (unsigned)blk_rq_pos(req),
@@ -1830,7 +1840,7 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *rqc)
 	struct mmc_blk_data *md = mq->data;
 	struct mmc_card *card = md->queue.card;
 	struct mmc_blk_request *brq = &mq->mqrq_cur->brq;
-	int ret = 1, disable_multi = 0, retry = 0, type;
+	int ret = 1, disable_multi = 0, retry = 0, type, retune_retry_done = 0;
 	enum mmc_blk_status status;
 	struct mmc_queue_req *mq_rq;
 	struct request *req = rqc;
@@ -1910,10 +1920,13 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *rqc)
 			break;
 		case MMC_BLK_CMD_ERR:
 			ret = mmc_blk_cmd_err(md, card, brq, req, ret);
-			if (!mmc_blk_reset(md, card->host, type))
-				break;
-			goto cmd_abort;
+			if (mmc_blk_reset(md, card->host, type))
+				goto cmd_abort;
+			if (!ret)
+				goto start_new_req;
+			break;
 		case MMC_BLK_RETRY:
+			retune_retry_done = brq->retune_retry_done;
 			if (retry++ < 5)
 				break;
 			/* Fall through */
@@ -1976,6 +1989,7 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *rqc)
 				mmc_start_req(card->host,
 						&mq_rq->mmc_active, NULL);
 			}
+			mq_rq->brq.retune_retry_done = retune_retry_done;
 		}
 	} while (ret);
 
@@ -2217,7 +2231,8 @@ static struct mmc_blk_data *mmc_blk_alloc(struct mmc_card *card)
 		 * The CSD capacity field is in units of read_blkbits.
 		 * set_capacity takes units of 512 bytes.
 		 */
-		size = card->csd.capacity << (card->csd.read_blkbits - 9);
+		size = (typeof(sector_t))card->csd.capacity
+			<< (card->csd.read_blkbits - 9);
 	}
 
 	return mmc_blk_alloc_req(card, &card->dev, size, false, NULL,
diff --git a/drivers/mmc/card/mmc_test.c b/drivers/mmc/card/mmc_test.c
index 53b741398b93..b78cf5d403a3 100644
--- a/drivers/mmc/card/mmc_test.c
+++ b/drivers/mmc/card/mmc_test.c
@@ -268,8 +268,6 @@ static int mmc_test_wait_busy(struct mmc_test_card *test)
 static int mmc_test_buffer_transfer(struct mmc_test_card *test,
 	u8 *buffer, unsigned addr, unsigned blksz, int write)
 {
-	int ret;
-
 	struct mmc_request mrq = {0};
 	struct mmc_command cmd = {0};
 	struct mmc_command stop = {0};
@@ -292,11 +290,7 @@ static int mmc_test_buffer_transfer(struct mmc_test_card *test,
 	if (data.error)
 		return data.error;
 
-	ret = mmc_test_wait_busy(test);
-	if (ret)
-		return ret;
-
-	return 0;
+	return mmc_test_wait_busy(test);
 }
 
 static void mmc_test_free_mem(struct mmc_test_mem *mem)
@@ -826,9 +820,7 @@ static int mmc_test_nonblock_transfer(struct mmc_test_card *test,
 				mmc_test_nonblock_reset(&mrq1, &cmd1,
 							&stop1, &data1);
 		}
-		done_areq = cur_areq;
-		cur_areq = other_areq;
-		other_areq = done_areq;
+		swap(cur_areq, other_areq);
 		dev_addr += blocks;
 	}
 
@@ -994,11 +986,7 @@ static int mmc_test_basic_write(struct mmc_test_card *test)
 
 	sg_init_one(&sg, test->buffer, 512);
 
-	ret = mmc_test_simple_transfer(test, &sg, 1, 0, 1, 512, 1);
-	if (ret)
-		return ret;
-
-	return 0;
+	return mmc_test_simple_transfer(test, &sg, 1, 0, 1, 512, 1);
 }
 
 static int mmc_test_basic_read(struct mmc_test_card *test)
@@ -1012,44 +1000,29 @@ static int mmc_test_basic_read(struct mmc_test_card *test)
 
 	sg_init_one(&sg, test->buffer, 512);
 
-	ret = mmc_test_simple_transfer(test, &sg, 1, 0, 1, 512, 0);
-	if (ret)
-		return ret;
-
-	return 0;
+	return mmc_test_simple_transfer(test, &sg, 1, 0, 1, 512, 0);
 }
 
 static int mmc_test_verify_write(struct mmc_test_card *test)
 {
-	int ret;
 	struct scatterlist sg;
 
 	sg_init_one(&sg, test->buffer, 512);
 
-	ret = mmc_test_transfer(test, &sg, 1, 0, 1, 512, 1);
-	if (ret)
-		return ret;
-
-	return 0;
+	return mmc_test_transfer(test, &sg, 1, 0, 1, 512, 1);
 }
 
 static int mmc_test_verify_read(struct mmc_test_card *test)
 {
-	int ret;
 	struct scatterlist sg;
 
 	sg_init_one(&sg, test->buffer, 512);
 
-	ret = mmc_test_transfer(test, &sg, 1, 0, 1, 512, 0);
-	if (ret)
-		return ret;
-
-	return 0;
+	return mmc_test_transfer(test, &sg, 1, 0, 1, 512, 0);
 }
 
 static int mmc_test_multi_write(struct mmc_test_card *test)
 {
-	int ret;
 	unsigned int size;
 	struct scatterlist sg;
 
@@ -1066,16 +1039,11 @@ static int mmc_test_multi_write(struct mmc_test_card *test)
 
 	sg_init_one(&sg, test->buffer, size);
 
-	ret = mmc_test_transfer(test, &sg, 1, 0, size/512, 512, 1);
-	if (ret)
-		return ret;
-
-	return 0;
+	return mmc_test_transfer(test, &sg, 1, 0, size/512, 512, 1);
 }
 
 static int mmc_test_multi_read(struct mmc_test_card *test)
 {
-	int ret;
 	unsigned int size;
 	struct scatterlist sg;
 
@@ -1092,11 +1060,7 @@ static int mmc_test_multi_read(struct mmc_test_card *test)
 
 	sg_init_one(&sg, test->buffer, size);
 
-	ret = mmc_test_transfer(test, &sg, 1, 0, size/512, 512, 0);
-	if (ret)
-		return ret;
-
-	return 0;
+	return mmc_test_transfer(test, &sg, 1, 0, size/512, 512, 0);
 }
 
 static int mmc_test_pow2_write(struct mmc_test_card *test)
@@ -1263,11 +1227,7 @@ static int mmc_test_xfersize_write(struct mmc_test_card *test)
 	if (ret)
 		return ret;
 
-	ret = mmc_test_broken_transfer(test, 1, 512, 1);
-	if (ret)
-		return ret;
-
-	return 0;
+	return mmc_test_broken_transfer(test, 1, 512, 1);
 }
 
 static int mmc_test_xfersize_read(struct mmc_test_card *test)
@@ -1278,11 +1238,7 @@ static int mmc_test_xfersize_read(struct mmc_test_card *test)
 	if (ret)
 		return ret;
 
-	ret = mmc_test_broken_transfer(test, 1, 512, 0);
-	if (ret)
-		return ret;
-
-	return 0;
+	return mmc_test_broken_transfer(test, 1, 512, 0);
 }
 
 static int mmc_test_multi_xfersize_write(struct mmc_test_card *test)
@@ -1296,11 +1252,7 @@ static int mmc_test_multi_xfersize_write(struct mmc_test_card *test)
 	if (ret)
 		return ret;
 
-	ret = mmc_test_broken_transfer(test, 2, 512, 1);
-	if (ret)
-		return ret;
-
-	return 0;
+	return mmc_test_broken_transfer(test, 2, 512, 1);
 }
 
 static int mmc_test_multi_xfersize_read(struct mmc_test_card *test)
@@ -1314,48 +1266,33 @@ static int mmc_test_multi_xfersize_read(struct mmc_test_card *test)
 	if (ret)
 		return ret;
 
-	ret = mmc_test_broken_transfer(test, 2, 512, 0);
-	if (ret)
-		return ret;
-
-	return 0;
+	return mmc_test_broken_transfer(test, 2, 512, 0);
 }
 
 #ifdef CONFIG_HIGHMEM
 
 static int mmc_test_write_high(struct mmc_test_card *test)
 {
-	int ret;
 	struct scatterlist sg;
 
 	sg_init_table(&sg, 1);
 	sg_set_page(&sg, test->highmem, 512, 0);
 
-	ret = mmc_test_transfer(test, &sg, 1, 0, 1, 512, 1);
-	if (ret)
-		return ret;
-
-	return 0;
+	return mmc_test_transfer(test, &sg, 1, 0, 1, 512, 1);
 }
 
 static int mmc_test_read_high(struct mmc_test_card *test)
 {
-	int ret;
 	struct scatterlist sg;
 
 	sg_init_table(&sg, 1);
 	sg_set_page(&sg, test->highmem, 512, 0);
 
-	ret = mmc_test_transfer(test, &sg, 1, 0, 1, 512, 0);
-	if (ret)
-		return ret;
-
-	return 0;
+	return mmc_test_transfer(test, &sg, 1, 0, 1, 512, 0);
 }
 
 static int mmc_test_multi_write_high(struct mmc_test_card *test)
 {
-	int ret;
 	unsigned int size;
 	struct scatterlist sg;
 
@@ -1373,16 +1310,11 @@ static int mmc_test_multi_write_high(struct mmc_test_card *test)
 	sg_init_table(&sg, 1);
 	sg_set_page(&sg, test->highmem, size, 0);
 
-	ret = mmc_test_transfer(test, &sg, 1, 0, size/512, 512, 1);
-	if (ret)
-		return ret;
-
-	return 0;
+	return mmc_test_transfer(test, &sg, 1, 0, size/512, 512, 1);
 }
 
 static int mmc_test_multi_read_high(struct mmc_test_card *test)
 {
-	int ret;
 	unsigned int size;
 	struct scatterlist sg;
 
@@ -1400,11 +1332,7 @@ static int mmc_test_multi_read_high(struct mmc_test_card *test)
 	sg_init_table(&sg, 1);
 	sg_set_page(&sg, test->highmem, size, 0);
 
-	ret = mmc_test_transfer(test, &sg, 1, 0, size/512, 512, 0);
-	if (ret)
-		return ret;
-
-	return 0;
+	return mmc_test_transfer(test, &sg, 1, 0, size/512, 512, 0);
 }
 
 #else
diff --git a/drivers/mmc/card/queue.c b/drivers/mmc/card/queue.c
index 8efa3684aef8..b5a2b145d89f 100644
--- a/drivers/mmc/card/queue.c
+++ b/drivers/mmc/card/queue.c
@@ -56,7 +56,6 @@ static int mmc_queue_thread(void *d)
 	down(&mq->thread_sem);
 	do {
 		struct request *req = NULL;
-		struct mmc_queue_req *tmp;
 		unsigned int cmd_flags = 0;
 
 		spin_lock_irq(q->queue_lock);
@@ -69,6 +68,7 @@ static int mmc_queue_thread(void *d)
 			set_current_state(TASK_RUNNING);
 			cmd_flags = req ? req->cmd_flags : 0;
 			mq->issue_fn(mq, req);
+			cond_resched();
 			if (mq->flags & MMC_QUEUE_NEW_REQUEST) {
 				mq->flags &= ~MMC_QUEUE_NEW_REQUEST;
 				continue; /* fetch again */
@@ -86,9 +86,7 @@ static int mmc_queue_thread(void *d)
 
 			mq->mqrq_prev->brq.mrq.data = NULL;
 			mq->mqrq_prev->req = NULL;
-			tmp = mq->mqrq_prev;
-			mq->mqrq_prev = mq->mqrq_cur;
-			mq->mqrq_cur = tmp;
+			swap(mq->mqrq_prev, mq->mqrq_cur);
 		} else {
 			if (kthread_should_stop()) {
 				set_current_state(TASK_RUNNING);
diff --git a/drivers/mmc/card/queue.h b/drivers/mmc/card/queue.h
index 99e6521e6169..36cddab57d77 100644
--- a/drivers/mmc/card/queue.h
+++ b/drivers/mmc/card/queue.h
@@ -12,6 +12,7 @@ struct mmc_blk_request {
 	struct mmc_command	cmd;
 	struct mmc_command	stop;
 	struct mmc_data		data;
+	int			retune_retry_done;
 };
 
 enum mmc_packed_type {
diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index 92e7671426eb..9ad73f30f744 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -133,6 +133,12 @@ void mmc_request_done(struct mmc_host *host, struct mmc_request *mrq)
 	struct mmc_command *cmd = mrq->cmd;
 	int err = cmd->error;
 
+	/* Flag re-tuning needed on CRC errors */
+	if (err == -EILSEQ || (mrq->sbc && mrq->sbc->error == -EILSEQ) ||
+	    (mrq->data && mrq->data->error == -EILSEQ) ||
+	    (mrq->stop && mrq->stop->error == -EILSEQ))
+		mmc_retune_needed(host);
+
 	if (err && cmd->retries && mmc_host_is_spi(host)) {
 		if (cmd->resp[0] & R1_SPI_ILLEGAL_COMMAND)
 			cmd->retries = 0;
@@ -186,12 +192,29 @@ void mmc_request_done(struct mmc_host *host, struct mmc_request *mrq)
 
 EXPORT_SYMBOL(mmc_request_done);
 
+static void __mmc_start_request(struct mmc_host *host, struct mmc_request *mrq)
+{
+	int err;
+
+	/* Assumes host controller has been runtime resumed by mmc_claim_host */
+	err = mmc_retune(host);
+	if (err) {
+		mrq->cmd->error = err;
+		mmc_request_done(host, mrq);
+		return;
+	}
+
+	host->ops->request(host, mrq);
+}
+
 static int mmc_start_request(struct mmc_host *host, struct mmc_request *mrq)
 {
 #ifdef CONFIG_MMC_DEBUG
 	unsigned int i, sz;
 	struct scatterlist *sg;
 #endif
+	mmc_retune_hold(host);
+
 	if (mmc_card_removed(host->card))
 		return -ENOMEDIUM;
 
@@ -252,7 +275,7 @@ static int mmc_start_request(struct mmc_host *host, struct mmc_request *mrq)
 	}
 	mmc_host_clk_hold(host);
 	led_trigger_event(host->led, LED_FULL);
-	host->ops->request(host, mrq);
+	__mmc_start_request(host, mrq);
 
 	return 0;
 }
@@ -301,12 +324,15 @@ void mmc_start_bkops(struct mmc_card *card, bool from_exception)
 		use_busy_signal = false;
 	}
 
+	mmc_retune_hold(card->host);
+
 	err = __mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
 			EXT_CSD_BKOPS_START, 1, timeout,
 			use_busy_signal, true, false);
 	if (err) {
 		pr_warn("%s: Error %d starting bkops\n",
 			mmc_hostname(card->host), err);
+		mmc_retune_release(card->host);
 		goto out;
 	}
 
@@ -317,6 +343,8 @@ void mmc_start_bkops(struct mmc_card *card, bool from_exception)
 	 */
 	if (!use_busy_signal)
 		mmc_card_set_doing_bkops(card);
+	else
+		mmc_retune_release(card->host);
 out:
 	mmc_release_host(card->host);
 }
@@ -417,22 +445,22 @@ static int mmc_wait_for_data_req_done(struct mmc_host *host,
 							    host->areq);
 				break; /* return err */
 			} else {
+				mmc_retune_recheck(host);
 				pr_info("%s: req failed (CMD%u): %d, retrying...\n",
 					mmc_hostname(host),
 					cmd->opcode, cmd->error);
 				cmd->retries--;
 				cmd->error = 0;
-				host->ops->request(host, mrq);
+				__mmc_start_request(host, mrq);
 				continue; /* wait for done/new event again */
 			}
 		} else if (context_info->is_new_req) {
 			context_info->is_new_req = false;
-			if (!next_req) {
-				err = MMC_BLK_NEW_REQUEST;
-				break; /* return err */
-			}
+			if (!next_req)
+				return MMC_BLK_NEW_REQUEST;
 		}
 	}
+	mmc_retune_release(host);
 	return err;
 }
 
@@ -467,12 +495,16 @@ static void mmc_wait_for_req_done(struct mmc_host *host,
 		    mmc_card_removed(host->card))
 			break;
 
+		mmc_retune_recheck(host);
+
 		pr_debug("%s: req failed (CMD%u): %d, retrying...\n",
 			 mmc_hostname(host), cmd->opcode, cmd->error);
 		cmd->retries--;
 		cmd->error = 0;
-		host->ops->request(host, mrq);
+		__mmc_start_request(host, mrq);
 	}
+
+	mmc_retune_release(host);
 }
 
 /**
@@ -728,6 +760,7 @@ int mmc_stop_bkops(struct mmc_card *card)
 	 */
 	if (!err || (err == -EINVAL)) {
 		mmc_card_clr_doing_bkops(card);
+		mmc_retune_release(card->host);
 		err = 0;
 	}
 
@@ -1109,6 +1142,8 @@ int mmc_execute_tuning(struct mmc_card *card)
 
 	if (err)
 		pr_err("%s: tuning execution failed\n", mmc_hostname(host));
+	else
+		mmc_retune_enable(host);
 
 	return err;
 }
@@ -1140,6 +1175,8 @@ void mmc_set_bus_width(struct mmc_host *host, unsigned int width)
  */
 void mmc_set_initial_state(struct mmc_host *host)
 {
+	mmc_retune_disable(host);
+
 	if (mmc_host_is_spi(host))
 		host->ios.chip_select = MMC_CS_HIGH;
 	else
@@ -1147,6 +1184,7 @@ void mmc_set_initial_state(struct mmc_host *host)
 	host->ios.bus_mode = MMC_BUSMODE_PUSHPULL;
 	host->ios.bus_width = MMC_BUS_WIDTH_1;
 	host->ios.timing = MMC_TIMING_LEGACY;
+	host->ios.drv_type = 0;
 
 	mmc_set_ios(host);
 }
@@ -1551,8 +1589,8 @@ int mmc_set_signal_voltage(struct mmc_host *host, int signal_voltage, u32 ocr)
 		goto power_cycle;
 	}
 
-	/* Keep clock gated for at least 5 ms */
-	mmc_delay(5);
+	/* Keep clock gated for at least 10 ms, though spec only says 5 ms */
+	mmc_delay(10);
 	host->ios.clock = clock;
 	mmc_set_ios(host);
 
@@ -1601,6 +1639,44 @@ void mmc_set_driver_type(struct mmc_host *host, unsigned int drv_type)
 	mmc_host_clk_release(host);
 }
 
+int mmc_select_drive_strength(struct mmc_card *card, unsigned int max_dtr,
+			      int card_drv_type, int *drv_type)
+{
+	struct mmc_host *host = card->host;
+	int host_drv_type = SD_DRIVER_TYPE_B;
+	int drive_strength;
+
+	*drv_type = 0;
+
+	if (!host->ops->select_drive_strength)
+		return 0;
+
+	/* Use SD definition of driver strength for hosts */
+	if (host->caps & MMC_CAP_DRIVER_TYPE_A)
+		host_drv_type |= SD_DRIVER_TYPE_A;
+
+	if (host->caps & MMC_CAP_DRIVER_TYPE_C)
+		host_drv_type |= SD_DRIVER_TYPE_C;
+
+	if (host->caps & MMC_CAP_DRIVER_TYPE_D)
+		host_drv_type |= SD_DRIVER_TYPE_D;
+
+	/*
+	 * The drive strength that the hardware can support
+	 * depends on the board design.  Pass the appropriate
+	 * information and let the hardware specific code
+	 * return what is possible given the options
+	 */
+	mmc_host_clk_hold(host);
+	drive_strength = host->ops->select_drive_strength(card, max_dtr,
+							  host_drv_type,
+							  card_drv_type,
+							  drv_type);
+	mmc_host_clk_release(host);
+
+	return drive_strength;
+}
+
 /*
  * Apply power to the MMC stack.  This is a two-stage process.
  * First, we enable power to the card without the clock running.
@@ -1970,6 +2046,8 @@ static int mmc_do_erase(struct mmc_card *card, unsigned int from,
 	unsigned long timeout;
 	int err;
 
+	mmc_retune_hold(card->host);
+
 	/*
 	 * qty is used to calculate the erase timeout which depends on how many
 	 * erase groups (or allocation units in SD terminology) are affected.
@@ -2073,6 +2151,7 @@ static int mmc_do_erase(struct mmc_card *card, unsigned int from,
 	} while (!(cmd.resp[0] & R1_READY_FOR_DATA) ||
 		 (R1_CURRENT_STATE(cmd.resp[0]) == R1_STATE_PRG));
 out:
+	mmc_retune_release(card->host);
 	return err;
 }
 
@@ -2331,7 +2410,8 @@ int mmc_hw_reset(struct mmc_host *host)
 	ret = host->bus_ops->reset(host);
 	mmc_bus_put(host);
 
-	pr_warn("%s: tried to reset card\n", mmc_hostname(host));
+	if (ret != -EOPNOTSUPP)
+		pr_warn("%s: tried to reset card\n", mmc_hostname(host));
 
 	return ret;
 }
diff --git a/drivers/mmc/core/core.h b/drivers/mmc/core/core.h
index cfba3c05aab1..1a22a82209b2 100644
--- a/drivers/mmc/core/core.h
+++ b/drivers/mmc/core/core.h
@@ -50,6 +50,8 @@ int mmc_set_signal_voltage(struct mmc_host *host, int signal_voltage, u32 ocr);
 int __mmc_set_signal_voltage(struct mmc_host *host, int signal_voltage);
 void mmc_set_timing(struct mmc_host *host, unsigned int timing);
 void mmc_set_driver_type(struct mmc_host *host, unsigned int drv_type);
+int mmc_select_drive_strength(struct mmc_card *card, unsigned int max_dtr,
+			      int card_drv_type, int *drv_type);
 void mmc_power_up(struct mmc_host *host, u32 ocr);
 void mmc_power_off(struct mmc_host *host);
 void mmc_power_cycle(struct mmc_host *host, u32 ocr);
@@ -88,6 +90,8 @@ void mmc_remove_card_debugfs(struct mmc_card *card);
 void mmc_init_context_info(struct mmc_host *host);
 
 int mmc_execute_tuning(struct mmc_card *card);
+int mmc_hs200_to_hs400(struct mmc_card *card);
+int mmc_hs400_to_hs200(struct mmc_card *card);
 
 #endif
 
diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c
index 8be0df758e68..99a9c9011c50 100644
--- a/drivers/mmc/core/host.c
+++ b/drivers/mmc/core/host.c
@@ -301,6 +301,90 @@ static inline void mmc_host_clk_sysfs_init(struct mmc_host *host)
 
 #endif
 
+void mmc_retune_enable(struct mmc_host *host)
+{
+	host->can_retune = 1;
+	if (host->retune_period)
+		mod_timer(&host->retune_timer,
+			  jiffies + host->retune_period * HZ);
+}
+
+void mmc_retune_disable(struct mmc_host *host)
+{
+	host->can_retune = 0;
+	del_timer_sync(&host->retune_timer);
+	host->retune_now = 0;
+	host->need_retune = 0;
+}
+
+void mmc_retune_timer_stop(struct mmc_host *host)
+{
+	del_timer_sync(&host->retune_timer);
+}
+EXPORT_SYMBOL(mmc_retune_timer_stop);
+
+void mmc_retune_hold(struct mmc_host *host)
+{
+	if (!host->hold_retune)
+		host->retune_now = 1;
+	host->hold_retune += 1;
+}
+
+void mmc_retune_release(struct mmc_host *host)
+{
+	if (host->hold_retune)
+		host->hold_retune -= 1;
+	else
+		WARN_ON(1);
+}
+
+int mmc_retune(struct mmc_host *host)
+{
+	bool return_to_hs400 = false;
+	int err;
+
+	if (host->retune_now)
+		host->retune_now = 0;
+	else
+		return 0;
+
+	if (!host->need_retune || host->doing_retune || !host->card)
+		return 0;
+
+	host->need_retune = 0;
+
+	host->doing_retune = 1;
+
+	if (host->ios.timing == MMC_TIMING_MMC_HS400) {
+		err = mmc_hs400_to_hs200(host->card);
+		if (err)
+			goto out;
+
+		return_to_hs400 = true;
+
+		if (host->ops->prepare_hs400_tuning)
+			host->ops->prepare_hs400_tuning(host, &host->ios);
+	}
+
+	err = mmc_execute_tuning(host->card);
+	if (err)
+		goto out;
+
+	if (return_to_hs400)
+		err = mmc_hs200_to_hs400(host->card);
+out:
+	host->doing_retune = 0;
+
+	return err;
+}
+
+static void mmc_retune_timer(unsigned long data)
+{
+	struct mmc_host *host = (struct mmc_host *)data;
+
+	mmc_retune_needed(host);
+}
+
 /**
  *	mmc_of_parse() - parse host's device-tree node
  *	@host: host whose node should be parsed.
@@ -400,6 +484,9 @@ int mmc_of_parse(struct mmc_host *host)
 	else if (ret != -ENOENT)
 		return ret;
 
+	if (of_property_read_bool(np, "disable-wp"))
+		host->caps2 |= MMC_CAP2_NO_WRITE_PROTECT;
+
 	/* See the comment on CD inversion above */
 	if (ro_cap_invert ^ ro_gpio_invert)
 		host->caps2 |= MMC_CAP2_RO_ACTIVE_HIGH;
@@ -504,6 +591,7 @@ struct mmc_host *mmc_alloc_host(int extra, struct device *dev)
 #ifdef CONFIG_PM
 	host->pm_notify.notifier_call = mmc_pm_notify;
 #endif
+	setup_timer(&host->retune_timer, mmc_retune_timer, (unsigned long)host);
 
 	/*
 	 * By default, hosts do not support SGIO or large requests.
diff --git a/drivers/mmc/core/host.h b/drivers/mmc/core/host.h
index f2ab9e578126..992bf5397633 100644
--- a/drivers/mmc/core/host.h
+++ b/drivers/mmc/core/host.h
@@ -15,5 +15,11 @@
 int mmc_register_host_class(void);
 void mmc_unregister_host_class(void);
 
+void mmc_retune_enable(struct mmc_host *host);
+void mmc_retune_disable(struct mmc_host *host);
+void mmc_retune_hold(struct mmc_host *host);
+void mmc_retune_release(struct mmc_host *host);
+int mmc_retune(struct mmc_host *host);
+
 #endif
 
diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index f36c76f8b232..e726903170a8 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -21,6 +21,7 @@
 #include <linux/mmc/mmc.h>
 
 #include "core.h"
+#include "host.h"
 #include "bus.h"
 #include "mmc_ops.h"
 #include "sd_ops.h"
@@ -266,8 +267,10 @@ static void mmc_manage_enhanced_area(struct mmc_card *card, u8 *ext_csd)
 			 * calculate the enhanced data area offset, in bytes
 			 */
 			card->ext_csd.enhanced_area_offset =
-				(ext_csd[139] << 24) + (ext_csd[138] << 16) +
-				(ext_csd[137] << 8) + ext_csd[136];
+				(((unsigned long long)ext_csd[139]) << 24) +
+				(((unsigned long long)ext_csd[138]) << 16) +
+				(((unsigned long long)ext_csd[137]) << 8) +
+				(((unsigned long long)ext_csd[136]));
 			if (mmc_card_blockaddr(card))
 				card->ext_csd.enhanced_area_offset <<= 9;
 			/*
@@ -434,6 +437,7 @@ static int mmc_decode_ext_csd(struct mmc_card *card, u8 *ext_csd)
 	card->ext_csd.raw_trim_mult =
 		ext_csd[EXT_CSD_TRIM_MULT];
 	card->ext_csd.raw_partition_support = ext_csd[EXT_CSD_PARTITION_SUPPORT];
+	card->ext_csd.raw_driver_strength = ext_csd[EXT_CSD_DRIVER_STRENGTH];
 	if (card->ext_csd.rev >= 4) {
 		if (ext_csd[EXT_CSD_PARTITION_SETTING_COMPLETED] &
 		    EXT_CSD_PART_SETTING_COMPLETED)
@@ -1040,6 +1044,7 @@ static int mmc_select_hs400(struct mmc_card *card)
 {
 	struct mmc_host *host = card->host;
 	int err = 0;
+	u8 val;
 
 	/*
 	 * HS400 mode requires 8-bit bus width
@@ -1055,8 +1060,10 @@ static int mmc_select_hs400(struct mmc_card *card)
 	mmc_set_timing(card->host, MMC_TIMING_MMC_HS);
 	mmc_set_bus_speed(card);
 
+	val = EXT_CSD_TIMING_HS |
+	      card->drive_strength << EXT_CSD_DRV_STR_SHIFT;
 	err = __mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
-			   EXT_CSD_HS_TIMING, EXT_CSD_TIMING_HS,
+			   EXT_CSD_HS_TIMING, val,
 			   card->ext_csd.generic_cmd6_time,
 			   true, true, true);
 	if (err) {
@@ -1075,8 +1082,10 @@ static int mmc_select_hs400(struct mmc_card *card)
 		return err;
 	}
 
+	val = EXT_CSD_TIMING_HS400 |
+	      card->drive_strength << EXT_CSD_DRV_STR_SHIFT;
 	err = __mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
-			   EXT_CSD_HS_TIMING, EXT_CSD_TIMING_HS400,
+			   EXT_CSD_HS_TIMING, val,
 			   card->ext_csd.generic_cmd6_time,
 			   true, true, true);
 	if (err) {
@@ -1091,6 +1100,115 @@ static int mmc_select_hs400(struct mmc_card *card)
 	return 0;
 }
 
+int mmc_hs200_to_hs400(struct mmc_card *card)
+{
+	return mmc_select_hs400(card);
+}
+
+/* Caller must hold re-tuning */
+static int mmc_switch_status(struct mmc_card *card)
+{
+	u32 status;
+	int err;
+
+	err = mmc_send_status(card, &status);
+	if (err)
+		return err;
+
+	return mmc_switch_status_error(card->host, status);
+}
+
+int mmc_hs400_to_hs200(struct mmc_card *card)
+{
+	struct mmc_host *host = card->host;
+	bool send_status = true;
+	unsigned int max_dtr;
+	int err;
+	u8 val;
+
+	if (host->caps & MMC_CAP_WAIT_WHILE_BUSY)
+		send_status = false;
+
+	/* Reduce frequency to HS */
+	max_dtr = card->ext_csd.hs_max_dtr;
+	mmc_set_clock(host, max_dtr);
+
+	/* Switch HS400 to HS DDR */
+	val = EXT_CSD_TIMING_HS |
+	      card->drive_strength << EXT_CSD_DRV_STR_SHIFT;
+	err = __mmc_switch(card, EXT_CSD_CMD_SET_NORMAL, EXT_CSD_HS_TIMING,
+			   val, card->ext_csd.generic_cmd6_time,
+			   true, send_status, true);
+	if (err)
+		goto out_err;
+
+	mmc_set_timing(host, MMC_TIMING_MMC_DDR52);
+
+	if (!send_status) {
+		err = mmc_switch_status(card);
+		if (err)
+			goto out_err;
+	}
+
+	/* Switch HS DDR to HS */
+	err = __mmc_switch(card, EXT_CSD_CMD_SET_NORMAL, EXT_CSD_BUS_WIDTH,
+			   EXT_CSD_BUS_WIDTH_8, card->ext_csd.generic_cmd6_time,
+			   true, send_status, true);
+	if (err)
+		goto out_err;
+
+	mmc_set_timing(host, MMC_TIMING_MMC_HS);
+
+	if (!send_status) {
+		err = mmc_switch_status(card);
+		if (err)
+			goto out_err;
+	}
+
+	/* Switch HS to HS200 */
+	val = EXT_CSD_TIMING_HS200 |
+	      card->drive_strength << EXT_CSD_DRV_STR_SHIFT;
+	err = __mmc_switch(card, EXT_CSD_CMD_SET_NORMAL, EXT_CSD_HS_TIMING,
+			   val, card->ext_csd.generic_cmd6_time, true,
+			   send_status, true);
+	if (err)
+		goto out_err;
+
+	mmc_set_timing(host, MMC_TIMING_MMC_HS200);
+
+	if (!send_status) {
+		err = mmc_switch_status(card);
+		if (err)
+			goto out_err;
+	}
+
+	mmc_set_bus_speed(card);
+
+	return 0;
+
+out_err:
+	pr_err("%s: %s failed, error %d\n", mmc_hostname(card->host),
+	       __func__, err);
+	return err;
+}
+
+static void mmc_select_driver_type(struct mmc_card *card)
+{
+	int card_drv_type, drive_strength, drv_type;
+
+	card_drv_type = card->ext_csd.raw_driver_strength |
+			mmc_driver_type_mask(0);
+
+	drive_strength = mmc_select_drive_strength(card,
+						   card->ext_csd.hs200_max_dtr,
+						   card_drv_type, &drv_type);
+
+	card->drive_strength = drive_strength;
+
+	if (drv_type)
+		mmc_set_driver_type(card->host, drv_type);
+}
+
 /*
  * For device supporting HS200 mode, the following sequence
  * should be done before executing the tuning process.
@@ -1102,6 +1220,7 @@ static int mmc_select_hs200(struct mmc_card *card)
 {
 	struct mmc_host *host = card->host;
 	int err = -EINVAL;
+	u8 val;
 
 	if (card->mmc_avail_type & EXT_CSD_CARD_TYPE_HS200_1_2V)
 		err = __mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_120);
@@ -1113,14 +1232,18 @@ static int mmc_select_hs200(struct mmc_card *card)
 	if (err)
 		goto err;
 
+	mmc_select_driver_type(card);
+
 	/*
 	 * Set the bus width(4 or 8) with host's support and
 	 * switch to HS200 mode if bus width is set successfully.
 	 */
 	err = mmc_select_bus_width(card);
 	if (!IS_ERR_VALUE(err)) {
+		val = EXT_CSD_TIMING_HS200 |
+		      card->drive_strength << EXT_CSD_DRV_STR_SHIFT;
 		err = __mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
-				   EXT_CSD_HS_TIMING, EXT_CSD_TIMING_HS200,
+				   EXT_CSD_HS_TIMING, val,
 				   card->ext_csd.generic_cmd6_time,
 				   true, true, true);
 		if (!err)
@@ -1511,9 +1634,12 @@ static int mmc_sleep(struct mmc_host *host)
 	unsigned int timeout_ms = DIV_ROUND_UP(card->ext_csd.sa_timeout, 10000);
 	int err;
 
+	/* Re-tuning can't be done once the card is deselected */
+	mmc_retune_hold(host);
+
 	err = mmc_deselect_cards(host);
 	if (err)
-		return err;
+		goto out_release;
 
 	cmd.opcode = MMC_SLEEP_AWAKE;
 	cmd.arg = card->rca << 16;
@@ -1534,7 +1660,7 @@ static int mmc_sleep(struct mmc_host *host)
 
 	err = mmc_wait_for_cmd(host, &cmd, 0);
 	if (err)
-		return err;
+		goto out_release;
 
 	/*
 	 * If the host does not wait while the card signals busy, then we will
@@ -1545,6 +1671,8 @@ static int mmc_sleep(struct mmc_host *host)
 	if (!cmd.busy_timeout || !(host->caps & MMC_CAP_WAIT_WHILE_BUSY))
 		mmc_delay(timeout_ms);
 
+out_release:
+	mmc_retune_release(host);
 	return err;
 }
 
@@ -1782,17 +1910,6 @@ static int mmc_runtime_resume(struct mmc_host *host)
 	return 0;
 }
 
-static int mmc_power_restore(struct mmc_host *host)
-{
-	int ret;
-
-	mmc_claim_host(host);
-	ret = mmc_init_card(host, host->card->ocr, host->card);
-	mmc_release_host(host);
-
-	return ret;
-}
-
 int mmc_can_reset(struct mmc_card *card)
 {
 	u8 rst_n_function;
@@ -1830,7 +1947,7 @@ static int mmc_reset(struct mmc_host *host)
 	mmc_set_initial_state(host);
 	mmc_host_clk_release(host);
 
-	return mmc_power_restore(host);
+	return mmc_init_card(host, card->ocr, card);
 }
 
 static const struct mmc_bus_ops mmc_ops = {
@@ -1840,7 +1957,6 @@ static const struct mmc_bus_ops mmc_ops = {
 	.resume = mmc_resume,
 	.runtime_suspend = mmc_runtime_suspend,
 	.runtime_resume = mmc_runtime_resume,
-	.power_restore = mmc_power_restore,
 	.alive = mmc_alive,
 	.shutdown = mmc_shutdown,
 	.reset = mmc_reset,
diff --git a/drivers/mmc/core/mmc_ops.c b/drivers/mmc/core/mmc_ops.c
index 0ea042dc7443..0e9ae1c276c8 100644
--- a/drivers/mmc/core/mmc_ops.c
+++ b/drivers/mmc/core/mmc_ops.c
@@ -19,6 +19,7 @@
 #include <linux/mmc/mmc.h>
 
 #include "core.h"
+#include "host.h"
 #include "mmc_ops.h"
 
 #define MMC_OPS_TIMEOUT_MS	(10 * 60 * 1000) /* 10 minute timeout */
@@ -449,6 +450,21 @@ int mmc_spi_set_crc(struct mmc_host *host, int use_crc)
 	return err;
 }
 
+int mmc_switch_status_error(struct mmc_host *host, u32 status)
+{
+	if (mmc_host_is_spi(host)) {
+		if (status & R1_SPI_ILLEGAL_COMMAND)
+			return -EBADMSG;
+	} else {
+		if (status & 0xFDFFA000)
+			pr_warn("%s: unexpected status %#x after switch\n",
+				mmc_hostname(host), status);
+		if (status & R1_SWITCH_ERROR)
+			return -EBADMSG;
+	}
+	return 0;
+}
+
 /**
  *	__mmc_switch - modify EXT_CSD register
  *	@card: the MMC card associated with the data transfer
@@ -474,6 +490,8 @@ int __mmc_switch(struct mmc_card *card, u8 set, u8 index, u8 value,
 	u32 status = 0;
 	bool use_r1b_resp = use_busy_signal;
 
+	mmc_retune_hold(host);
+
 	/*
 	 * If the cmd timeout and the max_busy_timeout of the host are both
 	 * specified, let's validate them. A failure means we need to prevent
@@ -506,11 +524,11 @@ int __mmc_switch(struct mmc_card *card, u8 set, u8 index, u8 value,
 
 	err = mmc_wait_for_cmd(host, &cmd, MMC_CMD_RETRIES);
 	if (err)
-		return err;
+		goto out;
 
 	/* No need to check card status in case of unblocking command */
 	if (!use_busy_signal)
-		return 0;
+		goto out;
 
 	/*
 	 * CRC errors shall only be ignored in cases were CMD13 is used to poll
@@ -529,7 +547,7 @@ int __mmc_switch(struct mmc_card *card, u8 set, u8 index, u8 value,
 		if (send_status) {
 			err = __mmc_send_status(card, &status, ignore_crc);
 			if (err)
-				return err;
+				goto out;
 		}
 		if ((host->caps & MMC_CAP_WAIT_WHILE_BUSY) && use_r1b_resp)
 			break;
@@ -543,29 +561,23 @@ int __mmc_switch(struct mmc_card *card, u8 set, u8 index, u8 value,
 		 */
 		if (!send_status) {
 			mmc_delay(timeout_ms);
-			return 0;
+			goto out;
 		}
 
 		/* Timeout if the device never leaves the program state. */
 		if (time_after(jiffies, timeout)) {
 			pr_err("%s: Card stuck in programming state! %s\n",
 				mmc_hostname(host), __func__);
-			return -ETIMEDOUT;
+			err = -ETIMEDOUT;
+			goto out;
 		}
 	} while (R1_CURRENT_STATE(status) == R1_STATE_PRG);
 
-	if (mmc_host_is_spi(host)) {
-		if (status & R1_SPI_ILLEGAL_COMMAND)
-			return -EBADMSG;
-	} else {
-		if (status & 0xFDFFA000)
-			pr_warn("%s: unexpected status %#x after switch\n",
-				mmc_hostname(host), status);
-		if (status & R1_SWITCH_ERROR)
-			return -EBADMSG;
-	}
+	err = mmc_switch_status_error(host, status);
+out:
+	mmc_retune_release(host);
 
-	return 0;
+	return err;
 }
 EXPORT_SYMBOL_GPL(__mmc_switch);
 
diff --git a/drivers/mmc/core/mmc_ops.h b/drivers/mmc/core/mmc_ops.h
index 6f4b00ed93de..f498f9ae21f0 100644
--- a/drivers/mmc/core/mmc_ops.h
+++ b/drivers/mmc/core/mmc_ops.h
@@ -27,6 +27,7 @@ int mmc_spi_set_crc(struct mmc_host *host, int use_crc);
 int mmc_bus_test(struct mmc_card *card, u8 bus_width);
 int mmc_send_hpi_cmd(struct mmc_card *card, u32 *status);
 int mmc_can_ext_csd(struct mmc_card *card);
+int mmc_switch_status_error(struct mmc_host *host, u32 status);
 
 #endif
 
diff --git a/drivers/mmc/core/sd.c b/drivers/mmc/core/sd.c
index 31a9ef256d06..4e7366ab187f 100644
--- a/drivers/mmc/core/sd.c
+++ b/drivers/mmc/core/sd.c
@@ -386,64 +386,31 @@ out:
 
 static int sd_select_driver_type(struct mmc_card *card, u8 *status)
 {
-	int host_drv_type = SD_DRIVER_TYPE_B;
-	int card_drv_type = SD_DRIVER_TYPE_B;
-	int drive_strength;
+	int card_drv_type, drive_strength, drv_type;
 	int err;
 
-	/*
-	 * If the host doesn't support any of the Driver Types A,C or D,
-	 * or there is no board specific handler then default Driver
-	 * Type B is used.
-	 */
-	if (!(card->host->caps & (MMC_CAP_DRIVER_TYPE_A | MMC_CAP_DRIVER_TYPE_C
-	    | MMC_CAP_DRIVER_TYPE_D)))
-		return 0;
-
-	if (!card->host->ops->select_drive_strength)
-		return 0;
-
-	if (card->host->caps & MMC_CAP_DRIVER_TYPE_A)
-		host_drv_type |= SD_DRIVER_TYPE_A;
-
-	if (card->host->caps & MMC_CAP_DRIVER_TYPE_C)
-		host_drv_type |= SD_DRIVER_TYPE_C;
-
-	if (card->host->caps & MMC_CAP_DRIVER_TYPE_D)
-		host_drv_type |= SD_DRIVER_TYPE_D;
-
-	if (card->sw_caps.sd3_drv_type & SD_DRIVER_TYPE_A)
-		card_drv_type |= SD_DRIVER_TYPE_A;
-
-	if (card->sw_caps.sd3_drv_type & SD_DRIVER_TYPE_C)
-		card_drv_type |= SD_DRIVER_TYPE_C;
+	card->drive_strength = 0;
 
-	if (card->sw_caps.sd3_drv_type & SD_DRIVER_TYPE_D)
-		card_drv_type |= SD_DRIVER_TYPE_D;
+	card_drv_type = card->sw_caps.sd3_drv_type | SD_DRIVER_TYPE_B;
 
-	/*
-	 * The drive strength that the hardware can support
-	 * depends on the board design.  Pass the appropriate
-	 * information and let the hardware specific code
-	 * return what is possible given the options
-	 */
-	mmc_host_clk_hold(card->host);
-	drive_strength = card->host->ops->select_drive_strength(
-		card->sw_caps.uhs_max_dtr,
-		host_drv_type, card_drv_type);
-	mmc_host_clk_release(card->host);
-
-	err = mmc_sd_switch(card, 1, 2, drive_strength, status);
-	if (err)
-		return err;
+	drive_strength = mmc_select_drive_strength(card,
+						   card->sw_caps.uhs_max_dtr,
+						   card_drv_type, &drv_type);
 
-	if ((status[15] & 0xF) != drive_strength) {
-		pr_warn("%s: Problem setting drive strength!\n",
-			mmc_hostname(card->host));
-		return 0;
+	if (drive_strength) {
+		err = mmc_sd_switch(card, 1, 2, drive_strength, status);
+		if (err)
+			return err;
+		if ((status[15] & 0xF) != drive_strength) {
+			pr_warn("%s: Problem setting drive strength!\n",
+				mmc_hostname(card->host));
+			return 0;
+		}
+		card->drive_strength = drive_strength;
 	}
 
-	mmc_set_driver_type(card->host, drive_strength);
+	if (drv_type)
+		mmc_set_driver_type(card->host, drv_type);
 
 	return 0;
 }
@@ -804,6 +771,28 @@ int mmc_sd_get_csd(struct mmc_host *host, struct mmc_card *card)
 	return 0;
 }
 
+static int mmc_sd_get_ro(struct mmc_host *host)
+{
+	int ro;
+
+	/*
+	 * Some systems don't feature a write-protect pin and don't need one.
+	 * E.g. because they only have micro-SD card slot. For those systems
+	 * assume that the SD card is always read-write.
+	 */
+	if (host->caps2 & MMC_CAP2_NO_WRITE_PROTECT)
+		return 0;
+
+	if (!host->ops->get_ro)
+		return -1;
+
+	mmc_host_clk_hold(host);
+	ro = host->ops->get_ro(host);
+	mmc_host_clk_release(host);
+
+	return ro;
+}
+
 int mmc_sd_setup_card(struct mmc_host *host, struct mmc_card *card,
 	bool reinit)
 {
@@ -855,13 +844,7 @@ int mmc_sd_setup_card(struct mmc_host *host, struct mmc_card *card,
 	 * Check if read-only switch is active.
 	 */
 	if (!reinit) {
-		int ro = -1;
-
-		if (host->ops->get_ro) {
-			mmc_host_clk_hold(card->host);
-			ro = host->ops->get_ro(host);
-			mmc_host_clk_release(card->host);
-		}
+		int ro = mmc_sd_get_ro(host);
 
 		if (ro < 0) {
 			pr_warn("%s: host does not support reading read-only switch, assuming write-enable\n",
@@ -1181,21 +1164,10 @@ static int mmc_sd_runtime_resume(struct mmc_host *host)
 	return 0;
 }
 
-static int mmc_sd_power_restore(struct mmc_host *host)
-{
-	int ret;
-
-	mmc_claim_host(host);
-	ret = mmc_sd_init_card(host, host->card->ocr, host->card);
-	mmc_release_host(host);
-
-	return ret;
-}
-
 static int mmc_sd_reset(struct mmc_host *host)
 {
 	mmc_power_cycle(host, host->card->ocr);
-	return mmc_sd_power_restore(host);
+	return mmc_sd_init_card(host, host->card->ocr, host->card);
 }
 
 static const struct mmc_bus_ops mmc_sd_ops = {
@@ -1205,7 +1177,6 @@ static const struct mmc_bus_ops mmc_sd_ops = {
 	.runtime_resume = mmc_sd_runtime_resume,
 	.suspend = mmc_sd_suspend,
 	.resume = mmc_sd_resume,
-	.power_restore = mmc_sd_power_restore,
 	.alive = mmc_sd_alive,
 	.shutdown = mmc_sd_suspend,
 	.reset = mmc_sd_reset,
diff --git a/drivers/mmc/core/sdio.c b/drivers/mmc/core/sdio.c
index 5bc6c7dbbd60..b91abedcfdca 100644
--- a/drivers/mmc/core/sdio.c
+++ b/drivers/mmc/core/sdio.c
@@ -402,69 +402,38 @@ static unsigned char host_drive_to_sdio_drive(int host_strength)
 
 static void sdio_select_driver_type(struct mmc_card *card)
 {
-	int host_drv_type = SD_DRIVER_TYPE_B;
-	int card_drv_type = SD_DRIVER_TYPE_B;
-	int drive_strength;
+	int card_drv_type, drive_strength, drv_type;
 	unsigned char card_strength;
 	int err;
 
-	/*
-	 * If the host doesn't support any of the Driver Types A,C or D,
-	 * or there is no board specific handler then default Driver
-	 * Type B is used.
-	 */
-	if (!(card->host->caps &
-		(MMC_CAP_DRIVER_TYPE_A |
-		 MMC_CAP_DRIVER_TYPE_C |
-		 MMC_CAP_DRIVER_TYPE_D)))
-		return;
-
-	if (!card->host->ops->select_drive_strength)
-		return;
-
-	if (card->host->caps & MMC_CAP_DRIVER_TYPE_A)
-		host_drv_type |= SD_DRIVER_TYPE_A;
-
-	if (card->host->caps & MMC_CAP_DRIVER_TYPE_C)
-		host_drv_type |= SD_DRIVER_TYPE_C;
+	card->drive_strength = 0;
 
-	if (card->host->caps & MMC_CAP_DRIVER_TYPE_D)
-		host_drv_type |= SD_DRIVER_TYPE_D;
+	card_drv_type = card->sw_caps.sd3_drv_type | SD_DRIVER_TYPE_B;
 
-	if (card->sw_caps.sd3_drv_type & SD_DRIVER_TYPE_A)
-		card_drv_type |= SD_DRIVER_TYPE_A;
-
-	if (card->sw_caps.sd3_drv_type & SD_DRIVER_TYPE_C)
-		card_drv_type |= SD_DRIVER_TYPE_C;
-
-	if (card->sw_caps.sd3_drv_type & SD_DRIVER_TYPE_D)
-		card_drv_type |= SD_DRIVER_TYPE_D;
-
-	/*
-	 * The drive strength that the hardware can support
-	 * depends on the board design.  Pass the appropriate
-	 * information and let the hardware specific code
-	 * return what is possible given the options
-	 */
-	drive_strength = card->host->ops->select_drive_strength(
-		card->sw_caps.uhs_max_dtr,
-		host_drv_type, card_drv_type);
+	drive_strength = mmc_select_drive_strength(card,
+						   card->sw_caps.uhs_max_dtr,
+						   card_drv_type, &drv_type);
 
-	/* if error just use default for drive strength B */
-	err = mmc_io_rw_direct(card, 0, 0, SDIO_CCCR_DRIVE_STRENGTH, 0,
-		&card_strength);
-	if (err)
-		return;
+	if (drive_strength) {
+		/* if error just use default for drive strength B */
+		err = mmc_io_rw_direct(card, 0, 0, SDIO_CCCR_DRIVE_STRENGTH, 0,
+				       &card_strength);
+		if (err)
+			return;
 
-	card_strength &= ~(SDIO_DRIVE_DTSx_MASK<<SDIO_DRIVE_DTSx_SHIFT);
-	card_strength |= host_drive_to_sdio_drive(drive_strength);
+		card_strength &= ~(SDIO_DRIVE_DTSx_MASK<<SDIO_DRIVE_DTSx_SHIFT);
+		card_strength |= host_drive_to_sdio_drive(drive_strength);
 
-	err = mmc_io_rw_direct(card, 1, 0, SDIO_CCCR_DRIVE_STRENGTH,
-		card_strength, NULL);
+		/* if error default to drive strength B */
+		err = mmc_io_rw_direct(card, 1, 0, SDIO_CCCR_DRIVE_STRENGTH,
+				       card_strength, NULL);
+		if (err)
+			return;
+		card->drive_strength = drive_strength;
+	}
 
-	/* if error default to drive strength B */
-	if (!err)
-		mmc_set_driver_type(card->host, drive_strength);
+	if (drv_type)
+		mmc_set_driver_type(card->host, drv_type);
 }
 
 
@@ -934,8 +903,12 @@ static int mmc_sdio_suspend(struct mmc_host *host)
 		mmc_release_host(host);
 	}
 
-	if (!mmc_card_keep_power(host))
+	if (!mmc_card_keep_power(host)) {
 		mmc_power_off(host);
+	} else if (host->retune_period) {
+		mmc_retune_timer_stop(host);
+		mmc_retune_needed(host);
+	}
 
 	return 0;
 }
@@ -1056,6 +1029,12 @@ static int mmc_sdio_runtime_resume(struct mmc_host *host)
 	return mmc_sdio_power_restore(host);
 }
 
+static int mmc_sdio_reset(struct mmc_host *host)
+{
+	mmc_power_cycle(host, host->card->ocr);
+	return mmc_sdio_power_restore(host);
+}
+
 static const struct mmc_bus_ops mmc_sdio_ops = {
 	.remove = mmc_sdio_remove,
 	.detect = mmc_sdio_detect,
@@ -1066,6 +1045,7 @@ static const struct mmc_bus_ops mmc_sdio_ops = {
 	.runtime_resume = mmc_sdio_runtime_resume,
 	.power_restore = mmc_sdio_power_restore,
 	.alive = mmc_sdio_alive,
+	.reset = mmc_sdio_reset,
 };
 
 
diff --git a/drivers/mmc/core/sdio_bus.c b/drivers/mmc/core/sdio_bus.c
index bee02e644d62..7e327a6dd53d 100644
--- a/drivers/mmc/core/sdio_bus.c
+++ b/drivers/mmc/core/sdio_bus.c
@@ -137,6 +137,10 @@ static int sdio_bus_probe(struct device *dev)
 	if (!id)
 		return -ENODEV;
 
+	ret = dev_pm_domain_attach(dev, false);
+	if (ret == -EPROBE_DEFER)
+		return ret;
+
 	/* Unbound SDIO functions are always suspended.
 	 * During probe, the function is set active and the usage count
 	 * is incremented.  If the driver supports runtime PM,
@@ -166,6 +170,7 @@ static int sdio_bus_probe(struct device *dev)
 disable_runtimepm:
 	if (func->card->host->caps & MMC_CAP_POWER_OFF_CARD)
 		pm_runtime_put_noidle(dev);
+	dev_pm_domain_detach(dev, false);
 	return ret;
 }
 
@@ -197,6 +202,8 @@ static int sdio_bus_remove(struct device *dev)
 	if (func->card->host->caps & MMC_CAP_POWER_OFF_CARD)
 		pm_runtime_put_sync(dev);
 
+	dev_pm_domain_detach(dev, false);
+
 	return ret;
 }
 
@@ -316,10 +323,8 @@ int sdio_add_func(struct sdio_func *func)
 	sdio_set_of_node(func);
 	sdio_acpi_set_handle(func);
 	ret = device_add(&func->dev);
-	if (ret == 0) {
+	if (ret == 0)
 		sdio_func_set_present(func);
-		dev_pm_domain_attach(&func->dev, false);
-	}
 
 	return ret;
 }
@@ -335,7 +340,6 @@ void sdio_remove_func(struct sdio_func *func)
 	if (!sdio_func_present(func))
 		return;
 
-	dev_pm_domain_detach(&func->dev, false);
 	device_del(&func->dev);
 	of_node_put(func->dev.of_node);
 	put_device(&func->dev);
diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig
index b1f837e749fe..fd9a58e216a5 100644
--- a/drivers/mmc/host/Kconfig
+++ b/drivers/mmc/host/Kconfig
@@ -219,6 +219,7 @@ config MMC_SDHCI_SIRF
 	tristate "SDHCI support on CSR SiRFprimaII and SiRFmarco SoCs"
 	depends on ARCH_SIRF
 	depends on MMC_SDHCI_PLTFM
+	select MMC_SDHCI_IO_ACCESSORS
 	help
 	  This selects the SDHCI support for SiRF System-on-Chip devices.
 
@@ -775,3 +776,11 @@ config MMC_TOSHIBA_PCI
 	tristate "Toshiba Type A SD/MMC Card Interface Driver"
 	depends on PCI
 	help
+
+config MMC_MTK
+	tristate "MediaTek SD/MMC Card Interface support"
+	help
+	  This selects the MediaTek(R) Secure digital and Multimedia card Interface.
+	  If you have a machine with a integrated SD/MMC card reader, say Y or M here.
+	  This is needed if support for any SD/SDIO/MMC devices is required.
+	  If unsure, say N.
diff --git a/drivers/mmc/host/Makefile b/drivers/mmc/host/Makefile
index e3ab5b968651..e928d61c5f4b 100644
--- a/drivers/mmc/host/Makefile
+++ b/drivers/mmc/host/Makefile
@@ -20,6 +20,7 @@ obj-$(CONFIG_MMC_SDHCI_F_SDH30)	+= sdhci_f_sdh30.o
 obj-$(CONFIG_MMC_SDHCI_SPEAR)	+= sdhci-spear.o
 obj-$(CONFIG_MMC_WBSD)		+= wbsd.o
 obj-$(CONFIG_MMC_AU1X)		+= au1xmmc.o
+obj-$(CONFIG_MMC_MTK)		+= mtk-sd.o
 obj-$(CONFIG_MMC_OMAP)		+= omap.o
 obj-$(CONFIG_MMC_OMAP_HS)	+= omap_hsmmc.o
 obj-$(CONFIG_MMC_ATMELMCI)	+= atmel-mci.o
diff --git a/drivers/mmc/host/davinci_mmc.c b/drivers/mmc/host/davinci_mmc.c
index 1625f908dc70..ea2a2ebc6b91 100644
--- a/drivers/mmc/host/davinci_mmc.c
+++ b/drivers/mmc/host/davinci_mmc.c
@@ -1161,7 +1161,7 @@ static void __init init_mmcsd_host(struct mmc_davinci_host *host)
 	mmc_davinci_reset_ctrl(host, 0);
 }
 
-static struct platform_device_id davinci_mmc_devtype[] = {
+static const struct platform_device_id davinci_mmc_devtype[] = {
 	{
 		.name	= "dm6441-mmc",
 		.driver_data = MMC_CTLR_VERSION_1,
diff --git a/drivers/mmc/host/dw_mmc-exynos.c b/drivers/mmc/host/dw_mmc-exynos.c
index e761eb1b1441..1e75309898b7 100644
--- a/drivers/mmc/host/dw_mmc-exynos.c
+++ b/drivers/mmc/host/dw_mmc-exynos.c
@@ -556,4 +556,4 @@ module_platform_driver(dw_mci_exynos_pltfm_driver);
 MODULE_DESCRIPTION("Samsung Specific DW-MSHC Driver Extension");
 MODULE_AUTHOR("Thomas Abraham <thomas.ab@samsung.com");
 MODULE_LICENSE("GPL v2");
-MODULE_ALIAS("platform:dwmmc-exynos");
+MODULE_ALIAS("platform:dwmmc_exynos");
diff --git a/drivers/mmc/host/dw_mmc-k3.c b/drivers/mmc/host/dw_mmc-k3.c
index 650f9cc3f7a6..63c2e2ed1288 100644
--- a/drivers/mmc/host/dw_mmc-k3.c
+++ b/drivers/mmc/host/dw_mmc-k3.c
@@ -8,16 +8,30 @@
  * (at your option) any later version.
  */
 
-#include <linux/module.h>
-#include <linux/platform_device.h>
 #include <linux/clk.h>
+#include <linux/mfd/syscon.h>
 #include <linux/mmc/host.h>
 #include <linux/mmc/dw_mmc.h>
+#include <linux/module.h>
 #include <linux/of_address.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/regulator/consumer.h>
 
 #include "dw_mmc.h"
 #include "dw_mmc-pltfm.h"
 
+/*
+ * hi6220 sd only support io voltage 1.8v and 3v
+ * Also need config AO_SCTRL_SEL18 accordingly
+ */
+#define AO_SCTRL_SEL18		BIT(10)
+#define AO_SCTRL_CTRL3		0x40C
+
+struct k3_priv {
+	struct regmap	*reg;
+};
+
 static void dw_mci_k3_set_ios(struct dw_mci *host, struct mmc_ios *ios)
 {
 	int ret;
@@ -33,8 +47,93 @@ static const struct dw_mci_drv_data k3_drv_data = {
 	.set_ios		= dw_mci_k3_set_ios,
 };
 
+static int dw_mci_hi6220_parse_dt(struct dw_mci *host)
+{
+	struct k3_priv *priv;
+
+	priv = devm_kzalloc(host->dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->reg = syscon_regmap_lookup_by_phandle(host->dev->of_node,
+					 "hisilicon,peripheral-syscon");
+	if (IS_ERR(priv->reg))
+		priv->reg = NULL;
+
+	host->priv = priv;
+	return 0;
+}
+
+static int dw_mci_hi6220_switch_voltage(struct mmc_host *mmc, struct mmc_ios *ios)
+{
+	struct dw_mci_slot *slot = mmc_priv(mmc);
+	struct k3_priv *priv;
+	struct dw_mci *host;
+	int min_uv, max_uv;
+	int ret;
+
+	host = slot->host;
+	priv = host->priv;
+
+	if (!priv || !priv->reg)
+		return 0;
+
+	if (ios->signal_voltage == MMC_SIGNAL_VOLTAGE_330) {
+		ret = regmap_update_bits(priv->reg, AO_SCTRL_CTRL3,
+					 AO_SCTRL_SEL18, 0);
+		min_uv = 3000000;
+		max_uv = 3000000;
+	} else if (ios->signal_voltage == MMC_SIGNAL_VOLTAGE_180) {
+		ret = regmap_update_bits(priv->reg, AO_SCTRL_CTRL3,
+					 AO_SCTRL_SEL18, AO_SCTRL_SEL18);
+		min_uv = 1800000;
+		max_uv = 1800000;
+	} else {
+		dev_dbg(host->dev, "voltage not supported\n");
+		return -EINVAL;
+	}
+
+	if (ret) {
+		dev_dbg(host->dev, "switch voltage failed\n");
+		return ret;
+	}
+
+	if (IS_ERR_OR_NULL(mmc->supply.vqmmc))
+		return 0;
+
+	ret = regulator_set_voltage(mmc->supply.vqmmc, min_uv, max_uv);
+	if (ret) {
+		dev_dbg(host->dev, "Regulator set error %d: %d - %d\n",
+				 ret, min_uv, max_uv);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void dw_mci_hi6220_set_ios(struct dw_mci *host, struct mmc_ios *ios)
+{
+	int ret;
+	unsigned int clock;
+
+	clock = (ios->clock <= 25000000) ? 25000000 : ios->clock;
+
+	ret = clk_set_rate(host->biu_clk, clock);
+	if (ret)
+		dev_warn(host->dev, "failed to set rate %uHz\n", clock);
+
+	host->bus_hz = clk_get_rate(host->biu_clk);
+}
+
+static const struct dw_mci_drv_data hi6220_data = {
+	.switch_voltage		= dw_mci_hi6220_switch_voltage,
+	.set_ios		= dw_mci_hi6220_set_ios,
+	.parse_dt		= dw_mci_hi6220_parse_dt,
+};
+
 static const struct of_device_id dw_mci_k3_match[] = {
 	{ .compatible = "hisilicon,hi4511-dw-mshc", .data = &k3_drv_data, },
+	{ .compatible = "hisilicon,hi6220-dw-mshc", .data = &hi6220_data, },
 	{},
 };
 MODULE_DEVICE_TABLE(of, dw_mci_k3_match);
@@ -94,4 +193,4 @@ module_platform_driver(dw_mci_k3_pltfm_driver);
 
 MODULE_DESCRIPTION("K3 Specific DW-MSHC Driver Extension");
 MODULE_LICENSE("GPL v2");
-MODULE_ALIAS("platform:dwmmc-k3");
+MODULE_ALIAS("platform:dwmmc_k3");
diff --git a/drivers/mmc/host/dw_mmc-rockchip.c b/drivers/mmc/host/dw_mmc-rockchip.c
index dbf166f94f1b..de15121bba7d 100644
--- a/drivers/mmc/host/dw_mmc-rockchip.c
+++ b/drivers/mmc/host/dw_mmc-rockchip.c
@@ -153,5 +153,5 @@ module_platform_driver(dw_mci_rockchip_pltfm_driver);
 
 MODULE_AUTHOR("Addy Ke <addy.ke@rock-chips.com>");
 MODULE_DESCRIPTION("Rockchip Specific DW-MSHC Driver Extension");
-MODULE_ALIAS("platform:dwmmc-rockchip");
+MODULE_ALIAS("platform:dwmmc_rockchip");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c
index 5f5adafb253a..40e9d8e45f25 100644
--- a/drivers/mmc/host/dw_mmc.c
+++ b/drivers/mmc/host/dw_mmc.c
@@ -1236,11 +1236,15 @@ static int dw_mci_switch_voltage(struct mmc_host *mmc, struct mmc_ios *ios)
 {
 	struct dw_mci_slot *slot = mmc_priv(mmc);
 	struct dw_mci *host = slot->host;
+	const struct dw_mci_drv_data *drv_data = host->drv_data;
 	u32 uhs;
 	u32 v18 = SDMMC_UHS_18V << slot->id;
 	int min_uv, max_uv;
 	int ret;
 
+	if (drv_data && drv_data->switch_voltage)
+		return drv_data->switch_voltage(mmc, ios);
+
 	/*
 	 * Program the voltage.  Note that some instances of dw_mmc may use
 	 * the UHS_REG for this.  For other instances (like exynos) the UHS_REG
@@ -1278,10 +1282,7 @@ static int dw_mci_get_ro(struct mmc_host *mmc)
 	int gpio_ro = mmc_gpio_get_ro(mmc);
 
 	/* Use platform get_ro function, else try on board write protect */
-	if ((slot->quirks & DW_MCI_SLOT_QUIRK_NO_WRITE_PROTECT) ||
-			(slot->host->quirks & DW_MCI_QUIRK_NO_WRITE_PROTECT))
-		read_only = 0;
-	else if (!IS_ERR_VALUE(gpio_ro))
+	if (!IS_ERR_VALUE(gpio_ro))
 		read_only = gpio_ro;
 	else
 		read_only =
@@ -2280,9 +2281,10 @@ static irqreturn_t dw_mci_interrupt(int irq, void *dev_id)
 }
 
 #ifdef CONFIG_OF
-/* given a slot id, find out the device node representing that slot */
-static struct device_node *dw_mci_of_find_slot_node(struct device *dev, u8 slot)
+/* given a slot, find out the device node representing that slot */
+static struct device_node *dw_mci_of_find_slot_node(struct dw_mci_slot *slot)
 {
+	struct device *dev = slot->mmc->parent;
 	struct device_node *np;
 	const __be32 *addr;
 	int len;
@@ -2294,42 +2296,28 @@ static struct device_node *dw_mci_of_find_slot_node(struct device *dev, u8 slot)
 		addr = of_get_property(np, "reg", &len);
 		if (!addr || (len < sizeof(int)))
 			continue;
-		if (be32_to_cpup(addr) == slot)
+		if (be32_to_cpup(addr) == slot->id)
 			return np;
 	}
 	return NULL;
 }
 
-static struct dw_mci_of_slot_quirks {
-	char *quirk;
-	int id;
-} of_slot_quirks[] = {
-	{
-		.quirk	= "disable-wp",
-		.id	= DW_MCI_SLOT_QUIRK_NO_WRITE_PROTECT,
-	},
-};
-
-static int dw_mci_of_get_slot_quirks(struct device *dev, u8 slot)
+static void dw_mci_slot_of_parse(struct dw_mci_slot *slot)
 {
-	struct device_node *np = dw_mci_of_find_slot_node(dev, slot);
-	int quirks = 0;
-	int idx;
+	struct device_node *np = dw_mci_of_find_slot_node(slot);
 
-	/* get quirks */
-	for (idx = 0; idx < ARRAY_SIZE(of_slot_quirks); idx++)
-		if (of_get_property(np, of_slot_quirks[idx].quirk, NULL)) {
-			dev_warn(dev, "Slot quirk %s is deprecated\n",
-					of_slot_quirks[idx].quirk);
-			quirks |= of_slot_quirks[idx].id;
-		}
+	if (!np)
+		return;
 
-	return quirks;
+	if (of_property_read_bool(np, "disable-wp")) {
+		slot->mmc->caps2 |= MMC_CAP2_NO_WRITE_PROTECT;
+		dev_warn(slot->mmc->parent,
+			"Slot quirk 'disable-wp' is deprecated\n");
+	}
 }
 #else /* CONFIG_OF */
-static int dw_mci_of_get_slot_quirks(struct device *dev, u8 slot)
+static void dw_mci_slot_of_parse(struct dw_mci_slot *slot)
 {
-	return 0;
 }
 #endif /* CONFIG_OF */
 
@@ -2352,8 +2340,6 @@ static int dw_mci_init_slot(struct dw_mci *host, unsigned int id)
 	slot->host = host;
 	host->slot[id] = slot;
 
-	slot->quirks = dw_mci_of_get_slot_quirks(host->dev, slot->id);
-
 	mmc->ops = &dw_mci_ops;
 	if (of_property_read_u32_array(host->dev->of_node,
 				       "clock-freq-min-max", freq, 2)) {
@@ -2391,6 +2377,8 @@ static int dw_mci_init_slot(struct dw_mci *host, unsigned int id)
 	if (host->pdata->caps2)
 		mmc->caps2 = host->pdata->caps2;
 
+	dw_mci_slot_of_parse(slot);
+
 	ret = mmc_of_parse(mmc);
 	if (ret)
 		goto err_host_allocated;
@@ -2618,9 +2606,6 @@ static struct dw_mci_of_quirks {
 	{
 		.quirk	= "broken-cd",
 		.id	= DW_MCI_QUIRK_BROKEN_CARD_DETECTION,
-	}, {
-		.quirk	= "disable-wp",
-		.id	= DW_MCI_QUIRK_NO_WRITE_PROTECT,
 	},
 };
 
@@ -2941,15 +2926,15 @@ void dw_mci_remove(struct dw_mci *host)
 {
 	int i;
 
-	mci_writel(host, RINTSTS, 0xFFFFFFFF);
-	mci_writel(host, INTMASK, 0); /* disable all mmc interrupt first */
-
 	for (i = 0; i < host->num_slots; i++) {
 		dev_dbg(host->dev, "remove slot %d\n", i);
 		if (host->slot[i])
 			dw_mci_cleanup_slot(host->slot[i], i);
 	}
 
+	mci_writel(host, RINTSTS, 0xFFFFFFFF);
+	mci_writel(host, INTMASK, 0); /* disable all mmc interrupt first */
+
 	/* disable clock to CIU */
 	mci_writel(host, CLKENA, 0);
 	mci_writel(host, CLKSRC, 0);
diff --git a/drivers/mmc/host/dw_mmc.h b/drivers/mmc/host/dw_mmc.h
index f45ab91de339..8ce4674730a6 100644
--- a/drivers/mmc/host/dw_mmc.h
+++ b/drivers/mmc/host/dw_mmc.h
@@ -227,7 +227,6 @@ extern int dw_mci_resume(struct dw_mci *host);
  * struct dw_mci_slot - MMC slot state
  * @mmc: The mmc_host representing this slot.
  * @host: The MMC controller this slot is using.
- * @quirks: Slot-level quirks (DW_MCI_SLOT_QUIRK_XXX)
  * @ctype: Card type for this slot.
  * @mrq: mmc_request currently being processed or waiting to be
  *	processed, or NULL when the slot is idle.
@@ -245,8 +244,6 @@ struct dw_mci_slot {
 	struct mmc_host		*mmc;
 	struct dw_mci		*host;
 
-	int			quirks;
-
 	u32			ctype;
 
 	struct mmc_request	*mrq;
@@ -287,5 +284,7 @@ struct dw_mci_drv_data {
 	int		(*execute_tuning)(struct dw_mci_slot *slot);
 	int		(*prepare_hs400_tuning)(struct dw_mci *host,
 						struct mmc_ios *ios);
+	int		(*switch_voltage)(struct mmc_host *mmc,
+					  struct mmc_ios *ios);
 };
 #endif /* _DW_MMC_H_ */
diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c
new file mode 100644
index 000000000000..7153500dd007
--- /dev/null
+++ b/drivers/mmc/host/mtk-sd.c
@@ -0,0 +1,1462 @@
+/*
+ * Copyright (c) 2014-2015 MediaTek Inc.
+ * Author: Chaotian.Jing <chaotian.jing@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/module.h>
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/dma-mapping.h>
+#include <linux/ioport.h>
+#include <linux/irq.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/of_gpio.h>
+#include <linux/pinctrl/consumer.h>
+#include <linux/platform_device.h>
+#include <linux/pm.h>
+#include <linux/pm_runtime.h>
+#include <linux/regulator/consumer.h>
+#include <linux/spinlock.h>
+
+#include <linux/mmc/card.h>
+#include <linux/mmc/core.h>
+#include <linux/mmc/host.h>
+#include <linux/mmc/mmc.h>
+#include <linux/mmc/sd.h>
+#include <linux/mmc/sdio.h>
+
+#define MAX_BD_NUM          1024
+
+/*--------------------------------------------------------------------------*/
+/* Common Definition                                                        */
+/*--------------------------------------------------------------------------*/
+#define MSDC_BUS_1BITS          0x0
+#define MSDC_BUS_4BITS          0x1
+#define MSDC_BUS_8BITS          0x2
+
+#define MSDC_BURST_64B          0x6
+
+/*--------------------------------------------------------------------------*/
+/* Register Offset                                                          */
+/*--------------------------------------------------------------------------*/
+#define MSDC_CFG         0x0
+#define MSDC_IOCON       0x04
+#define MSDC_PS          0x08
+#define MSDC_INT         0x0c
+#define MSDC_INTEN       0x10
+#define MSDC_FIFOCS      0x14
+#define SDC_CFG          0x30
+#define SDC_CMD          0x34
+#define SDC_ARG          0x38
+#define SDC_STS          0x3c
+#define SDC_RESP0        0x40
+#define SDC_RESP1        0x44
+#define SDC_RESP2        0x48
+#define SDC_RESP3        0x4c
+#define SDC_BLK_NUM      0x50
+#define SDC_ACMD_RESP    0x80
+#define MSDC_DMA_SA      0x90
+#define MSDC_DMA_CTRL    0x98
+#define MSDC_DMA_CFG     0x9c
+#define MSDC_PATCH_BIT   0xb0
+#define MSDC_PATCH_BIT1  0xb4
+#define MSDC_PAD_TUNE    0xec
+
+/*--------------------------------------------------------------------------*/
+/* Register Mask                                                            */
+/*--------------------------------------------------------------------------*/
+
+/* MSDC_CFG mask */
+#define MSDC_CFG_MODE           (0x1 << 0)	/* RW */
+#define MSDC_CFG_CKPDN          (0x1 << 1)	/* RW */
+#define MSDC_CFG_RST            (0x1 << 2)	/* RW */
+#define MSDC_CFG_PIO            (0x1 << 3)	/* RW */
+#define MSDC_CFG_CKDRVEN        (0x1 << 4)	/* RW */
+#define MSDC_CFG_BV18SDT        (0x1 << 5)	/* RW */
+#define MSDC_CFG_BV18PSS        (0x1 << 6)	/* R  */
+#define MSDC_CFG_CKSTB          (0x1 << 7)	/* R  */
+#define MSDC_CFG_CKDIV          (0xff << 8)	/* RW */
+#define MSDC_CFG_CKMOD          (0x3 << 16)	/* RW */
+
+/* MSDC_IOCON mask */
+#define MSDC_IOCON_SDR104CKS    (0x1 << 0)	/* RW */
+#define MSDC_IOCON_RSPL         (0x1 << 1)	/* RW */
+#define MSDC_IOCON_DSPL         (0x1 << 2)	/* RW */
+#define MSDC_IOCON_DDLSEL       (0x1 << 3)	/* RW */
+#define MSDC_IOCON_DDR50CKD     (0x1 << 4)	/* RW */
+#define MSDC_IOCON_DSPLSEL      (0x1 << 5)	/* RW */
+#define MSDC_IOCON_W_DSPL       (0x1 << 8)	/* RW */
+#define MSDC_IOCON_D0SPL        (0x1 << 16)	/* RW */
+#define MSDC_IOCON_D1SPL        (0x1 << 17)	/* RW */
+#define MSDC_IOCON_D2SPL        (0x1 << 18)	/* RW */
+#define MSDC_IOCON_D3SPL        (0x1 << 19)	/* RW */
+#define MSDC_IOCON_D4SPL        (0x1 << 20)	/* RW */
+#define MSDC_IOCON_D5SPL        (0x1 << 21)	/* RW */
+#define MSDC_IOCON_D6SPL        (0x1 << 22)	/* RW */
+#define MSDC_IOCON_D7SPL        (0x1 << 23)	/* RW */
+#define MSDC_IOCON_RISCSZ       (0x3 << 24)	/* RW */
+
+/* MSDC_PS mask */
+#define MSDC_PS_CDEN            (0x1 << 0)	/* RW */
+#define MSDC_PS_CDSTS           (0x1 << 1)	/* R  */
+#define MSDC_PS_CDDEBOUNCE      (0xf << 12)	/* RW */
+#define MSDC_PS_DAT             (0xff << 16)	/* R  */
+#define MSDC_PS_CMD             (0x1 << 24)	/* R  */
+#define MSDC_PS_WP              (0x1 << 31)	/* R  */
+
+/* MSDC_INT mask */
+#define MSDC_INT_MMCIRQ         (0x1 << 0)	/* W1C */
+#define MSDC_INT_CDSC           (0x1 << 1)	/* W1C */
+#define MSDC_INT_ACMDRDY        (0x1 << 3)	/* W1C */
+#define MSDC_INT_ACMDTMO        (0x1 << 4)	/* W1C */
+#define MSDC_INT_ACMDCRCERR     (0x1 << 5)	/* W1C */
+#define MSDC_INT_DMAQ_EMPTY     (0x1 << 6)	/* W1C */
+#define MSDC_INT_SDIOIRQ        (0x1 << 7)	/* W1C */
+#define MSDC_INT_CMDRDY         (0x1 << 8)	/* W1C */
+#define MSDC_INT_CMDTMO         (0x1 << 9)	/* W1C */
+#define MSDC_INT_RSPCRCERR      (0x1 << 10)	/* W1C */
+#define MSDC_INT_CSTA           (0x1 << 11)	/* R */
+#define MSDC_INT_XFER_COMPL     (0x1 << 12)	/* W1C */
+#define MSDC_INT_DXFER_DONE     (0x1 << 13)	/* W1C */
+#define MSDC_INT_DATTMO         (0x1 << 14)	/* W1C */
+#define MSDC_INT_DATCRCERR      (0x1 << 15)	/* W1C */
+#define MSDC_INT_ACMD19_DONE    (0x1 << 16)	/* W1C */
+#define MSDC_INT_DMA_BDCSERR    (0x1 << 17)	/* W1C */
+#define MSDC_INT_DMA_GPDCSERR   (0x1 << 18)	/* W1C */
+#define MSDC_INT_DMA_PROTECT    (0x1 << 19)	/* W1C */
+
+/* MSDC_INTEN mask */
+#define MSDC_INTEN_MMCIRQ       (0x1 << 0)	/* RW */
+#define MSDC_INTEN_CDSC         (0x1 << 1)	/* RW */
+#define MSDC_INTEN_ACMDRDY      (0x1 << 3)	/* RW */
+#define MSDC_INTEN_ACMDTMO      (0x1 << 4)	/* RW */
+#define MSDC_INTEN_ACMDCRCERR   (0x1 << 5)	/* RW */
+#define MSDC_INTEN_DMAQ_EMPTY   (0x1 << 6)	/* RW */
+#define MSDC_INTEN_SDIOIRQ      (0x1 << 7)	/* RW */
+#define MSDC_INTEN_CMDRDY       (0x1 << 8)	/* RW */
+#define MSDC_INTEN_CMDTMO       (0x1 << 9)	/* RW */
+#define MSDC_INTEN_RSPCRCERR    (0x1 << 10)	/* RW */
+#define MSDC_INTEN_CSTA         (0x1 << 11)	/* RW */
+#define MSDC_INTEN_XFER_COMPL   (0x1 << 12)	/* RW */
+#define MSDC_INTEN_DXFER_DONE   (0x1 << 13)	/* RW */
+#define MSDC_INTEN_DATTMO       (0x1 << 14)	/* RW */
+#define MSDC_INTEN_DATCRCERR    (0x1 << 15)	/* RW */
+#define MSDC_INTEN_ACMD19_DONE  (0x1 << 16)	/* RW */
+#define MSDC_INTEN_DMA_BDCSERR  (0x1 << 17)	/* RW */
+#define MSDC_INTEN_DMA_GPDCSERR (0x1 << 18)	/* RW */
+#define MSDC_INTEN_DMA_PROTECT  (0x1 << 19)	/* RW */
+
+/* MSDC_FIFOCS mask */
+#define MSDC_FIFOCS_RXCNT       (0xff << 0)	/* R */
+#define MSDC_FIFOCS_TXCNT       (0xff << 16)	/* R */
+#define MSDC_FIFOCS_CLR         (0x1 << 31)	/* RW */
+
+/* SDC_CFG mask */
+#define SDC_CFG_SDIOINTWKUP     (0x1 << 0)	/* RW */
+#define SDC_CFG_INSWKUP         (0x1 << 1)	/* RW */
+#define SDC_CFG_BUSWIDTH        (0x3 << 16)	/* RW */
+#define SDC_CFG_SDIO            (0x1 << 19)	/* RW */
+#define SDC_CFG_SDIOIDE         (0x1 << 20)	/* RW */
+#define SDC_CFG_INTATGAP        (0x1 << 21)	/* RW */
+#define SDC_CFG_DTOC            (0xff << 24)	/* RW */
+
+/* SDC_STS mask */
+#define SDC_STS_SDCBUSY         (0x1 << 0)	/* RW */
+#define SDC_STS_CMDBUSY         (0x1 << 1)	/* RW */
+#define SDC_STS_SWR_COMPL       (0x1 << 31)	/* RW */
+
+/* MSDC_DMA_CTRL mask */
+#define MSDC_DMA_CTRL_START     (0x1 << 0)	/* W */
+#define MSDC_DMA_CTRL_STOP      (0x1 << 1)	/* W */
+#define MSDC_DMA_CTRL_RESUME    (0x1 << 2)	/* W */
+#define MSDC_DMA_CTRL_MODE      (0x1 << 8)	/* RW */
+#define MSDC_DMA_CTRL_LASTBUF   (0x1 << 10)	/* RW */
+#define MSDC_DMA_CTRL_BRUSTSZ   (0x7 << 12)	/* RW */
+
+/* MSDC_DMA_CFG mask */
+#define MSDC_DMA_CFG_STS        (0x1 << 0)	/* R */
+#define MSDC_DMA_CFG_DECSEN     (0x1 << 1)	/* RW */
+#define MSDC_DMA_CFG_AHBHPROT2  (0x2 << 8)	/* RW */
+#define MSDC_DMA_CFG_ACTIVEEN   (0x2 << 12)	/* RW */
+#define MSDC_DMA_CFG_CS12B16B   (0x1 << 16)	/* RW */
+
+/* MSDC_PATCH_BIT mask */
+#define MSDC_PATCH_BIT_ODDSUPP    (0x1 <<  1)	/* RW */
+#define MSDC_INT_DAT_LATCH_CK_SEL (0x7 <<  7)
+#define MSDC_CKGEN_MSDC_DLY_SEL   (0x1f << 10)
+#define MSDC_PATCH_BIT_IODSSEL    (0x1 << 16)	/* RW */
+#define MSDC_PATCH_BIT_IOINTSEL   (0x1 << 17)	/* RW */
+#define MSDC_PATCH_BIT_BUSYDLY    (0xf << 18)	/* RW */
+#define MSDC_PATCH_BIT_WDOD       (0xf << 22)	/* RW */
+#define MSDC_PATCH_BIT_IDRTSEL    (0x1 << 26)	/* RW */
+#define MSDC_PATCH_BIT_CMDFSEL    (0x1 << 27)	/* RW */
+#define MSDC_PATCH_BIT_INTDLSEL   (0x1 << 28)	/* RW */
+#define MSDC_PATCH_BIT_SPCPUSH    (0x1 << 29)	/* RW */
+#define MSDC_PATCH_BIT_DECRCTMO   (0x1 << 30)	/* RW */
+
+#define REQ_CMD_EIO  (0x1 << 0)
+#define REQ_CMD_TMO  (0x1 << 1)
+#define REQ_DAT_ERR  (0x1 << 2)
+#define REQ_STOP_EIO (0x1 << 3)
+#define REQ_STOP_TMO (0x1 << 4)
+#define REQ_CMD_BUSY (0x1 << 5)
+
+#define MSDC_PREPARE_FLAG (0x1 << 0)
+#define MSDC_ASYNC_FLAG (0x1 << 1)
+#define MSDC_MMAP_FLAG (0x1 << 2)
+
+#define MTK_MMC_AUTOSUSPEND_DELAY	50
+#define CMD_TIMEOUT         (HZ/10 * 5)	/* 100ms x5 */
+#define DAT_TIMEOUT         (HZ    * 5)	/* 1000ms x5 */
+
+/*--------------------------------------------------------------------------*/
+/* Descriptor Structure                                                     */
+/*--------------------------------------------------------------------------*/
+struct mt_gpdma_desc {
+	u32 gpd_info;
+#define GPDMA_DESC_HWO		(0x1 << 0)
+#define GPDMA_DESC_BDP		(0x1 << 1)
+#define GPDMA_DESC_CHECKSUM	(0xff << 8) /* bit8 ~ bit15 */
+#define GPDMA_DESC_INT		(0x1 << 16)
+	u32 next;
+	u32 ptr;
+	u32 gpd_data_len;
+#define GPDMA_DESC_BUFLEN	(0xffff) /* bit0 ~ bit15 */
+#define GPDMA_DESC_EXTLEN	(0xff << 16) /* bit16 ~ bit23 */
+	u32 arg;
+	u32 blknum;
+	u32 cmd;
+};
+
+struct mt_bdma_desc {
+	u32 bd_info;
+#define BDMA_DESC_EOL		(0x1 << 0)
+#define BDMA_DESC_CHECKSUM	(0xff << 8) /* bit8 ~ bit15 */
+#define BDMA_DESC_BLKPAD	(0x1 << 17)
+#define BDMA_DESC_DWPAD		(0x1 << 18)
+	u32 next;
+	u32 ptr;
+	u32 bd_data_len;
+#define BDMA_DESC_BUFLEN	(0xffff) /* bit0 ~ bit15 */
+};
+
+struct msdc_dma {
+	struct scatterlist *sg;	/* I/O scatter list */
+	struct mt_gpdma_desc *gpd;		/* pointer to gpd array */
+	struct mt_bdma_desc *bd;		/* pointer to bd array */
+	dma_addr_t gpd_addr;	/* the physical address of gpd array */
+	dma_addr_t bd_addr;	/* the physical address of bd array */
+};
+
+struct msdc_save_para {
+	u32 msdc_cfg;
+	u32 iocon;
+	u32 sdc_cfg;
+	u32 pad_tune;
+	u32 patch_bit0;
+	u32 patch_bit1;
+};
+
+struct msdc_host {
+	struct device *dev;
+	struct mmc_host *mmc;	/* mmc structure */
+	int cmd_rsp;
+
+	spinlock_t lock;
+	struct mmc_request *mrq;
+	struct mmc_command *cmd;
+	struct mmc_data *data;
+	int error;
+
+	void __iomem *base;		/* host base address */
+
+	struct msdc_dma dma;	/* dma channel */
+	u64 dma_mask;
+
+	u32 timeout_ns;		/* data timeout ns */
+	u32 timeout_clks;	/* data timeout clks */
+
+	struct pinctrl *pinctrl;
+	struct pinctrl_state *pins_default;
+	struct pinctrl_state *pins_uhs;
+	struct delayed_work req_timeout;
+	int irq;		/* host interrupt */
+
+	struct clk *src_clk;	/* msdc source clock */
+	struct clk *h_clk;      /* msdc h_clk */
+	u32 mclk;		/* mmc subsystem clock frequency */
+	u32 src_clk_freq;	/* source clock frequency */
+	u32 sclk;		/* SD/MS bus clock frequency */
+	bool ddr;
+	bool vqmmc_enabled;
+	struct msdc_save_para save_para; /* used when gate HCLK */
+};
+
+static void sdr_set_bits(void __iomem *reg, u32 bs)
+{
+	u32 val = readl(reg);
+
+	val |= bs;
+	writel(val, reg);
+}
+
+static void sdr_clr_bits(void __iomem *reg, u32 bs)
+{
+	u32 val = readl(reg);
+
+	val &= ~bs;
+	writel(val, reg);
+}
+
+static void sdr_set_field(void __iomem *reg, u32 field, u32 val)
+{
+	unsigned int tv = readl(reg);
+
+	tv &= ~field;
+	tv |= ((val) << (ffs((unsigned int)field) - 1));
+	writel(tv, reg);
+}
+
+static void sdr_get_field(void __iomem *reg, u32 field, u32 *val)
+{
+	unsigned int tv = readl(reg);
+
+	*val = ((tv & field) >> (ffs((unsigned int)field) - 1));
+}
+
+static void msdc_reset_hw(struct msdc_host *host)
+{
+	u32 val;
+
+	sdr_set_bits(host->base + MSDC_CFG, MSDC_CFG_RST);
+	while (readl(host->base + MSDC_CFG) & MSDC_CFG_RST)
+		cpu_relax();
+
+	sdr_set_bits(host->base + MSDC_FIFOCS, MSDC_FIFOCS_CLR);
+	while (readl(host->base + MSDC_FIFOCS) & MSDC_FIFOCS_CLR)
+		cpu_relax();
+
+	val = readl(host->base + MSDC_INT);
+	writel(val, host->base + MSDC_INT);
+}
+
+static void msdc_cmd_next(struct msdc_host *host,
+		struct mmc_request *mrq, struct mmc_command *cmd);
+
+static u32 data_ints_mask = MSDC_INTEN_XFER_COMPL | MSDC_INTEN_DATTMO |
+			MSDC_INTEN_DATCRCERR | MSDC_INTEN_DMA_BDCSERR |
+			MSDC_INTEN_DMA_GPDCSERR | MSDC_INTEN_DMA_PROTECT;
+
+static u8 msdc_dma_calcs(u8 *buf, u32 len)
+{
+	u32 i, sum = 0;
+
+	for (i = 0; i < len; i++)
+		sum += buf[i];
+	return 0xff - (u8) sum;
+}
+
+static inline void msdc_dma_setup(struct msdc_host *host, struct msdc_dma *dma,
+		struct mmc_data *data)
+{
+	unsigned int j, dma_len;
+	dma_addr_t dma_address;
+	u32 dma_ctrl;
+	struct scatterlist *sg;
+	struct mt_gpdma_desc *gpd;
+	struct mt_bdma_desc *bd;
+
+	sg = data->sg;
+
+	gpd = dma->gpd;
+	bd = dma->bd;
+
+	/* modify gpd */
+	gpd->gpd_info |= GPDMA_DESC_HWO;
+	gpd->gpd_info |= GPDMA_DESC_BDP;
+	/* need to clear first. use these bits to calc checksum */
+	gpd->gpd_info &= ~GPDMA_DESC_CHECKSUM;
+	gpd->gpd_info |= msdc_dma_calcs((u8 *) gpd, 16) << 8;
+
+	/* modify bd */
+	for_each_sg(data->sg, sg, data->sg_count, j) {
+		dma_address = sg_dma_address(sg);
+		dma_len = sg_dma_len(sg);
+
+		/* init bd */
+		bd[j].bd_info &= ~BDMA_DESC_BLKPAD;
+		bd[j].bd_info &= ~BDMA_DESC_DWPAD;
+		bd[j].ptr = (u32)dma_address;
+		bd[j].bd_data_len &= ~BDMA_DESC_BUFLEN;
+		bd[j].bd_data_len |= (dma_len & BDMA_DESC_BUFLEN);
+
+		if (j == data->sg_count - 1) /* the last bd */
+			bd[j].bd_info |= BDMA_DESC_EOL;
+		else
+			bd[j].bd_info &= ~BDMA_DESC_EOL;
+
+		/* checksume need to clear first */
+		bd[j].bd_info &= ~BDMA_DESC_CHECKSUM;
+		bd[j].bd_info |= msdc_dma_calcs((u8 *)(&bd[j]), 16) << 8;
+	}
+
+	sdr_set_field(host->base + MSDC_DMA_CFG, MSDC_DMA_CFG_DECSEN, 1);
+	dma_ctrl = readl_relaxed(host->base + MSDC_DMA_CTRL);
+	dma_ctrl &= ~(MSDC_DMA_CTRL_BRUSTSZ | MSDC_DMA_CTRL_MODE);
+	dma_ctrl |= (MSDC_BURST_64B << 12 | 1 << 8);
+	writel_relaxed(dma_ctrl, host->base + MSDC_DMA_CTRL);
+	writel((u32)dma->gpd_addr, host->base + MSDC_DMA_SA);
+}
+
+static void msdc_prepare_data(struct msdc_host *host, struct mmc_request *mrq)
+{
+	struct mmc_data *data = mrq->data;
+
+	if (!(data->host_cookie & MSDC_PREPARE_FLAG)) {
+		bool read = (data->flags & MMC_DATA_READ) != 0;
+
+		data->host_cookie |= MSDC_PREPARE_FLAG;
+		data->sg_count = dma_map_sg(host->dev, data->sg, data->sg_len,
+					   read ? DMA_FROM_DEVICE : DMA_TO_DEVICE);
+	}
+}
+
+static void msdc_unprepare_data(struct msdc_host *host, struct mmc_request *mrq)
+{
+	struct mmc_data *data = mrq->data;
+
+	if (data->host_cookie & MSDC_ASYNC_FLAG)
+		return;
+
+	if (data->host_cookie & MSDC_PREPARE_FLAG) {
+		bool read = (data->flags & MMC_DATA_READ) != 0;
+
+		dma_unmap_sg(host->dev, data->sg, data->sg_len,
+			     read ? DMA_FROM_DEVICE : DMA_TO_DEVICE);
+		data->host_cookie &= ~MSDC_PREPARE_FLAG;
+	}
+}
+
+/* clock control primitives */
+static void msdc_set_timeout(struct msdc_host *host, u32 ns, u32 clks)
+{
+	u32 timeout, clk_ns;
+	u32 mode = 0;
+
+	host->timeout_ns = ns;
+	host->timeout_clks = clks;
+	if (host->sclk == 0) {
+		timeout = 0;
+	} else {
+		clk_ns  = 1000000000UL / host->sclk;
+		timeout = (ns + clk_ns - 1) / clk_ns + clks;
+		/* in 1048576 sclk cycle unit */
+		timeout = (timeout + (0x1 << 20) - 1) >> 20;
+		sdr_get_field(host->base + MSDC_CFG, MSDC_CFG_CKMOD, &mode);
+		/*DDR mode will double the clk cycles for data timeout */
+		timeout = mode >= 2 ? timeout * 2 : timeout;
+		timeout = timeout > 1 ? timeout - 1 : 0;
+		timeout = timeout > 255 ? 255 : timeout;
+	}
+	sdr_set_field(host->base + SDC_CFG, SDC_CFG_DTOC, timeout);
+}
+
+static void msdc_gate_clock(struct msdc_host *host)
+{
+	clk_disable_unprepare(host->src_clk);
+	clk_disable_unprepare(host->h_clk);
+}
+
+static void msdc_ungate_clock(struct msdc_host *host)
+{
+	clk_prepare_enable(host->h_clk);
+	clk_prepare_enable(host->src_clk);
+	while (!(readl(host->base + MSDC_CFG) & MSDC_CFG_CKSTB))
+		cpu_relax();
+}
+
+static void msdc_set_mclk(struct msdc_host *host, int ddr, u32 hz)
+{
+	u32 mode;
+	u32 flags;
+	u32 div;
+	u32 sclk;
+
+	if (!hz) {
+		dev_dbg(host->dev, "set mclk to 0\n");
+		host->mclk = 0;
+		sdr_clr_bits(host->base + MSDC_CFG, MSDC_CFG_CKPDN);
+		return;
+	}
+
+	flags = readl(host->base + MSDC_INTEN);
+	sdr_clr_bits(host->base + MSDC_INTEN, flags);
+	if (ddr) { /* may need to modify later */
+		mode = 0x2; /* ddr mode and use divisor */
+		if (hz >= (host->src_clk_freq >> 2)) {
+			div = 0; /* mean div = 1/4 */
+			sclk = host->src_clk_freq >> 2; /* sclk = clk / 4 */
+		} else {
+			div = (host->src_clk_freq + ((hz << 2) - 1)) / (hz << 2);
+			sclk = (host->src_clk_freq >> 2) / div;
+			div = (div >> 1);
+		}
+	} else if (hz >= host->src_clk_freq) {
+		mode = 0x1; /* no divisor */
+		div = 0;
+		sclk = host->src_clk_freq;
+	} else {
+		mode = 0x0; /* use divisor */
+		if (hz >= (host->src_clk_freq >> 1)) {
+			div = 0; /* mean div = 1/2 */
+			sclk = host->src_clk_freq >> 1; /* sclk = clk / 2 */
+		} else {
+			div = (host->src_clk_freq + ((hz << 2) - 1)) / (hz << 2);
+			sclk = (host->src_clk_freq >> 2) / div;
+		}
+	}
+	sdr_set_field(host->base + MSDC_CFG, MSDC_CFG_CKMOD | MSDC_CFG_CKDIV,
+			(mode << 8) | (div % 0xff));
+	sdr_set_bits(host->base + MSDC_CFG, MSDC_CFG_CKPDN);
+	while (!(readl(host->base + MSDC_CFG) & MSDC_CFG_CKSTB))
+		cpu_relax();
+	host->sclk = sclk;
+	host->mclk = hz;
+	host->ddr = ddr;
+	/* need because clk changed. */
+	msdc_set_timeout(host, host->timeout_ns, host->timeout_clks);
+	sdr_set_bits(host->base + MSDC_INTEN, flags);
+
+	dev_dbg(host->dev, "sclk: %d, ddr: %d\n", host->sclk, ddr);
+}
+
+static inline u32 msdc_cmd_find_resp(struct msdc_host *host,
+		struct mmc_request *mrq, struct mmc_command *cmd)
+{
+	u32 resp;
+
+	switch (mmc_resp_type(cmd)) {
+		/* Actually, R1, R5, R6, R7 are the same */
+	case MMC_RSP_R1:
+		resp = 0x1;
+		break;
+	case MMC_RSP_R1B:
+		resp = 0x7;
+		break;
+	case MMC_RSP_R2:
+		resp = 0x2;
+		break;
+	case MMC_RSP_R3:
+		resp = 0x3;
+		break;
+	case MMC_RSP_NONE:
+	default:
+		resp = 0x0;
+		break;
+	}
+
+	return resp;
+}
+
+static inline u32 msdc_cmd_prepare_raw_cmd(struct msdc_host *host,
+		struct mmc_request *mrq, struct mmc_command *cmd)
+{
+	/* rawcmd :
+	 * vol_swt << 30 | auto_cmd << 28 | blklen << 16 | go_irq << 15 |
+	 * stop << 14 | rw << 13 | dtype << 11 | rsptyp << 7 | brk << 6 | opcode
+	 */
+	u32 opcode = cmd->opcode;
+	u32 resp = msdc_cmd_find_resp(host, mrq, cmd);
+	u32 rawcmd = (opcode & 0x3f) | ((resp & 0x7) << 7);
+
+	host->cmd_rsp = resp;
+
+	if ((opcode == SD_IO_RW_DIRECT && cmd->flags == (unsigned int) -1) ||
+	    opcode == MMC_STOP_TRANSMISSION)
+		rawcmd |= (0x1 << 14);
+	else if (opcode == SD_SWITCH_VOLTAGE)
+		rawcmd |= (0x1 << 30);
+	else if (opcode == SD_APP_SEND_SCR ||
+		 opcode == SD_APP_SEND_NUM_WR_BLKS ||
+		 (opcode == SD_SWITCH && mmc_cmd_type(cmd) == MMC_CMD_ADTC) ||
+		 (opcode == SD_APP_SD_STATUS && mmc_cmd_type(cmd) == MMC_CMD_ADTC) ||
+		 (opcode == MMC_SEND_EXT_CSD && mmc_cmd_type(cmd) == MMC_CMD_ADTC))
+		rawcmd |= (0x1 << 11);
+
+	if (cmd->data) {
+		struct mmc_data *data = cmd->data;
+
+		if (mmc_op_multi(opcode)) {
+			if (mmc_card_mmc(host->mmc->card) && mrq->sbc &&
+			    !(mrq->sbc->arg & 0xFFFF0000))
+				rawcmd |= 0x2 << 28; /* AutoCMD23 */
+		}
+
+		rawcmd |= ((data->blksz & 0xFFF) << 16);
+		if (data->flags & MMC_DATA_WRITE)
+			rawcmd |= (0x1 << 13);
+		if (data->blocks > 1)
+			rawcmd |= (0x2 << 11);
+		else
+			rawcmd |= (0x1 << 11);
+		/* Always use dma mode */
+		sdr_clr_bits(host->base + MSDC_CFG, MSDC_CFG_PIO);
+
+		if (host->timeout_ns != data->timeout_ns ||
+		    host->timeout_clks != data->timeout_clks)
+			msdc_set_timeout(host, data->timeout_ns,
+					data->timeout_clks);
+
+		writel(data->blocks, host->base + SDC_BLK_NUM);
+	}
+	return rawcmd;
+}
+
+static void msdc_start_data(struct msdc_host *host, struct mmc_request *mrq,
+			    struct mmc_command *cmd, struct mmc_data *data)
+{
+	bool read;
+
+	WARN_ON(host->data);
+	host->data = data;
+	read = data->flags & MMC_DATA_READ;
+
+	mod_delayed_work(system_wq, &host->req_timeout, DAT_TIMEOUT);
+	msdc_dma_setup(host, &host->dma, data);
+	sdr_set_bits(host->base + MSDC_INTEN, data_ints_mask);
+	sdr_set_field(host->base + MSDC_DMA_CTRL, MSDC_DMA_CTRL_START, 1);
+	dev_dbg(host->dev, "DMA start\n");
+	dev_dbg(host->dev, "%s: cmd=%d DMA data: %d blocks; read=%d\n",
+			__func__, cmd->opcode, data->blocks, read);
+}
+
+static int msdc_auto_cmd_done(struct msdc_host *host, int events,
+		struct mmc_command *cmd)
+{
+	u32 *rsp = cmd->resp;
+
+	rsp[0] = readl(host->base + SDC_ACMD_RESP);
+
+	if (events & MSDC_INT_ACMDRDY) {
+		cmd->error = 0;
+	} else {
+		msdc_reset_hw(host);
+		if (events & MSDC_INT_ACMDCRCERR) {
+			cmd->error = -EILSEQ;
+			host->error |= REQ_STOP_EIO;
+		} else if (events & MSDC_INT_ACMDTMO) {
+			cmd->error = -ETIMEDOUT;
+			host->error |= REQ_STOP_TMO;
+		}
+		dev_err(host->dev,
+			"%s: AUTO_CMD%d arg=%08X; rsp %08X; cmd_error=%d\n",
+			__func__, cmd->opcode, cmd->arg, rsp[0], cmd->error);
+	}
+	return cmd->error;
+}
+
+static void msdc_track_cmd_data(struct msdc_host *host,
+				struct mmc_command *cmd, struct mmc_data *data)
+{
+	if (host->error)
+		dev_dbg(host->dev, "%s: cmd=%d arg=%08X; host->error=0x%08X\n",
+			__func__, cmd->opcode, cmd->arg, host->error);
+}
+
+static void msdc_request_done(struct msdc_host *host, struct mmc_request *mrq)
+{
+	unsigned long flags;
+	bool ret;
+
+	ret = cancel_delayed_work(&host->req_timeout);
+	if (!ret) {
+		/* delay work already running */
+		return;
+	}
+	spin_lock_irqsave(&host->lock, flags);
+	host->mrq = NULL;
+	spin_unlock_irqrestore(&host->lock, flags);
+
+	msdc_track_cmd_data(host, mrq->cmd, mrq->data);
+	if (mrq->data)
+		msdc_unprepare_data(host, mrq);
+	mmc_request_done(host->mmc, mrq);
+
+	pm_runtime_mark_last_busy(host->dev);
+	pm_runtime_put_autosuspend(host->dev);
+}
+
+/* returns true if command is fully handled; returns false otherwise */
+static bool msdc_cmd_done(struct msdc_host *host, int events,
+			  struct mmc_request *mrq, struct mmc_command *cmd)
+{
+	bool done = false;
+	bool sbc_error;
+	unsigned long flags;
+	u32 *rsp = cmd->resp;
+
+	if (mrq->sbc && cmd == mrq->cmd &&
+	    (events & (MSDC_INT_ACMDRDY | MSDC_INT_ACMDCRCERR
+				   | MSDC_INT_ACMDTMO)))
+		msdc_auto_cmd_done(host, events, mrq->sbc);
+
+	sbc_error = mrq->sbc && mrq->sbc->error;
+
+	if (!sbc_error && !(events & (MSDC_INT_CMDRDY
+					| MSDC_INT_RSPCRCERR
+					| MSDC_INT_CMDTMO)))
+		return done;
+
+	spin_lock_irqsave(&host->lock, flags);
+	done = !host->cmd;
+	host->cmd = NULL;
+	spin_unlock_irqrestore(&host->lock, flags);
+
+	if (done)
+		return true;
+
+	sdr_clr_bits(host->base + MSDC_INTEN, MSDC_INTEN_CMDRDY |
+			MSDC_INTEN_RSPCRCERR | MSDC_INTEN_CMDTMO |
+			MSDC_INTEN_ACMDRDY | MSDC_INTEN_ACMDCRCERR |
+			MSDC_INTEN_ACMDTMO);
+	writel(cmd->arg, host->base + SDC_ARG);
+
+	if (cmd->flags & MMC_RSP_PRESENT) {
+		if (cmd->flags & MMC_RSP_136) {
+			rsp[0] = readl(host->base + SDC_RESP3);
+			rsp[1] = readl(host->base + SDC_RESP2);
+			rsp[2] = readl(host->base + SDC_RESP1);
+			rsp[3] = readl(host->base + SDC_RESP0);
+		} else {
+			rsp[0] = readl(host->base + SDC_RESP0);
+		}
+	}
+
+	if (!sbc_error && !(events & MSDC_INT_CMDRDY)) {
+		msdc_reset_hw(host);
+		if (events & MSDC_INT_RSPCRCERR) {
+			cmd->error = -EILSEQ;
+			host->error |= REQ_CMD_EIO;
+		} else if (events & MSDC_INT_CMDTMO) {
+			cmd->error = -ETIMEDOUT;
+			host->error |= REQ_CMD_TMO;
+		}
+	}
+	if (cmd->error)
+		dev_dbg(host->dev,
+				"%s: cmd=%d arg=%08X; rsp %08X; cmd_error=%d\n",
+				__func__, cmd->opcode, cmd->arg, rsp[0],
+				cmd->error);
+
+	msdc_cmd_next(host, mrq, cmd);
+	return true;
+}
+
+/* It is the core layer's responsibility to ensure card status
+ * is correct before issue a request. but host design do below
+ * checks recommended.
+ */
+static inline bool msdc_cmd_is_ready(struct msdc_host *host,
+		struct mmc_request *mrq, struct mmc_command *cmd)
+{
+	/* The max busy time we can endure is 20ms */
+	unsigned long tmo = jiffies + msecs_to_jiffies(20);
+
+	while ((readl(host->base + SDC_STS) & SDC_STS_CMDBUSY) &&
+			time_before(jiffies, tmo))
+		cpu_relax();
+	if (readl(host->base + SDC_STS) & SDC_STS_CMDBUSY) {
+		dev_err(host->dev, "CMD bus busy detected\n");
+		host->error |= REQ_CMD_BUSY;
+		msdc_cmd_done(host, MSDC_INT_CMDTMO, mrq, cmd);
+		return false;
+	}
+
+	if (mmc_resp_type(cmd) == MMC_RSP_R1B || cmd->data) {
+		tmo = jiffies + msecs_to_jiffies(20);
+		/* R1B or with data, should check SDCBUSY */
+		while ((readl(host->base + SDC_STS) & SDC_STS_SDCBUSY) &&
+				time_before(jiffies, tmo))
+			cpu_relax();
+		if (readl(host->base + SDC_STS) & SDC_STS_SDCBUSY) {
+			dev_err(host->dev, "Controller busy detected\n");
+			host->error |= REQ_CMD_BUSY;
+			msdc_cmd_done(host, MSDC_INT_CMDTMO, mrq, cmd);
+			return false;
+		}
+	}
+	return true;
+}
+
+static void msdc_start_command(struct msdc_host *host,
+		struct mmc_request *mrq, struct mmc_command *cmd)
+{
+	u32 rawcmd;
+
+	WARN_ON(host->cmd);
+	host->cmd = cmd;
+
+	if (!msdc_cmd_is_ready(host, mrq, cmd))
+		return;
+
+	if ((readl(host->base + MSDC_FIFOCS) & MSDC_FIFOCS_TXCNT) >> 16 ||
+	    readl(host->base + MSDC_FIFOCS) & MSDC_FIFOCS_RXCNT) {
+		dev_err(host->dev, "TX/RX FIFO non-empty before start of IO. Reset\n");
+		msdc_reset_hw(host);
+	}
+
+	cmd->error = 0;
+	rawcmd = msdc_cmd_prepare_raw_cmd(host, mrq, cmd);
+	mod_delayed_work(system_wq, &host->req_timeout, DAT_TIMEOUT);
+
+	sdr_set_bits(host->base + MSDC_INTEN, MSDC_INTEN_CMDRDY |
+			MSDC_INTEN_RSPCRCERR | MSDC_INTEN_CMDTMO |
+			MSDC_INTEN_ACMDRDY | MSDC_INTEN_ACMDCRCERR |
+			MSDC_INTEN_ACMDTMO);
+	writel(cmd->arg, host->base + SDC_ARG);
+	writel(rawcmd, host->base + SDC_CMD);
+}
+
+static void msdc_cmd_next(struct msdc_host *host,
+		struct mmc_request *mrq, struct mmc_command *cmd)
+{
+	if (cmd->error || (mrq->sbc && mrq->sbc->error))
+		msdc_request_done(host, mrq);
+	else if (cmd == mrq->sbc)
+		msdc_start_command(host, mrq, mrq->cmd);
+	else if (!cmd->data)
+		msdc_request_done(host, mrq);
+	else
+		msdc_start_data(host, mrq, cmd, cmd->data);
+}
+
+static void msdc_ops_request(struct mmc_host *mmc, struct mmc_request *mrq)
+{
+	struct msdc_host *host = mmc_priv(mmc);
+
+	host->error = 0;
+	WARN_ON(host->mrq);
+	host->mrq = mrq;
+
+	pm_runtime_get_sync(host->dev);
+
+	if (mrq->data)
+		msdc_prepare_data(host, mrq);
+
+	/* if SBC is required, we have HW option and SW option.
+	 * if HW option is enabled, and SBC does not have "special" flags,
+	 * use HW option,  otherwise use SW option
+	 */
+	if (mrq->sbc && (!mmc_card_mmc(mmc->card) ||
+	    (mrq->sbc->arg & 0xFFFF0000)))
+		msdc_start_command(host, mrq, mrq->sbc);
+	else
+		msdc_start_command(host, mrq, mrq->cmd);
+}
+
+static void msdc_pre_req(struct mmc_host *mmc, struct mmc_request *mrq,
+		bool is_first_req)
+{
+	struct msdc_host *host = mmc_priv(mmc);
+	struct mmc_data *data = mrq->data;
+
+	if (!data)
+		return;
+
+	msdc_prepare_data(host, mrq);
+	data->host_cookie |= MSDC_ASYNC_FLAG;
+}
+
+static void msdc_post_req(struct mmc_host *mmc, struct mmc_request *mrq,
+		int err)
+{
+	struct msdc_host *host = mmc_priv(mmc);
+	struct mmc_data *data;
+
+	data = mrq->data;
+	if (!data)
+		return;
+	if (data->host_cookie) {
+		data->host_cookie &= ~MSDC_ASYNC_FLAG;
+		msdc_unprepare_data(host, mrq);
+	}
+}
+
+static void msdc_data_xfer_next(struct msdc_host *host,
+				struct mmc_request *mrq, struct mmc_data *data)
+{
+	if (mmc_op_multi(mrq->cmd->opcode) && mrq->stop && !mrq->stop->error &&
+	    (!data->bytes_xfered || !mrq->sbc))
+		msdc_start_command(host, mrq, mrq->stop);
+	else
+		msdc_request_done(host, mrq);
+}
+
+static bool msdc_data_xfer_done(struct msdc_host *host, u32 events,
+				struct mmc_request *mrq, struct mmc_data *data)
+{
+	struct mmc_command *stop = data->stop;
+	unsigned long flags;
+	bool done;
+	unsigned int check_data = events &
+	    (MSDC_INT_XFER_COMPL | MSDC_INT_DATCRCERR | MSDC_INT_DATTMO
+	     | MSDC_INT_DMA_BDCSERR | MSDC_INT_DMA_GPDCSERR
+	     | MSDC_INT_DMA_PROTECT);
+
+	spin_lock_irqsave(&host->lock, flags);
+	done = !host->data;
+	if (check_data)
+		host->data = NULL;
+	spin_unlock_irqrestore(&host->lock, flags);
+
+	if (done)
+		return true;
+
+	if (check_data || (stop && stop->error)) {
+		dev_dbg(host->dev, "DMA status: 0x%8X\n",
+				readl(host->base + MSDC_DMA_CFG));
+		sdr_set_field(host->base + MSDC_DMA_CTRL, MSDC_DMA_CTRL_STOP,
+				1);
+		while (readl(host->base + MSDC_DMA_CFG) & MSDC_DMA_CFG_STS)
+			cpu_relax();
+		sdr_clr_bits(host->base + MSDC_INTEN, data_ints_mask);
+		dev_dbg(host->dev, "DMA stop\n");
+
+		if ((events & MSDC_INT_XFER_COMPL) && (!stop || !stop->error)) {
+			data->bytes_xfered = data->blocks * data->blksz;
+		} else {
+			dev_err(host->dev, "interrupt events: %x\n", events);
+			msdc_reset_hw(host);
+			host->error |= REQ_DAT_ERR;
+			data->bytes_xfered = 0;
+
+			if (events & MSDC_INT_DATTMO)
+				data->error = -ETIMEDOUT;
+
+			dev_err(host->dev, "%s: cmd=%d; blocks=%d",
+				__func__, mrq->cmd->opcode, data->blocks);
+			dev_err(host->dev, "data_error=%d xfer_size=%d\n",
+					(int)data->error, data->bytes_xfered);
+		}
+
+		msdc_data_xfer_next(host, mrq, data);
+		done = true;
+	}
+	return done;
+}
+
+static void msdc_set_buswidth(struct msdc_host *host, u32 width)
+{
+	u32 val = readl(host->base + SDC_CFG);
+
+	val &= ~SDC_CFG_BUSWIDTH;
+
+	switch (width) {
+	default:
+	case MMC_BUS_WIDTH_1:
+		val |= (MSDC_BUS_1BITS << 16);
+		break;
+	case MMC_BUS_WIDTH_4:
+		val |= (MSDC_BUS_4BITS << 16);
+		break;
+	case MMC_BUS_WIDTH_8:
+		val |= (MSDC_BUS_8BITS << 16);
+		break;
+	}
+
+	writel(val, host->base + SDC_CFG);
+	dev_dbg(host->dev, "Bus Width = %d", width);
+}
+
+static int msdc_ops_switch_volt(struct mmc_host *mmc, struct mmc_ios *ios)
+{
+	struct msdc_host *host = mmc_priv(mmc);
+	int min_uv, max_uv;
+	int ret = 0;
+
+	if (!IS_ERR(mmc->supply.vqmmc)) {
+		if (ios->signal_voltage == MMC_SIGNAL_VOLTAGE_330) {
+			min_uv = 3300000;
+			max_uv = 3300000;
+		} else if (ios->signal_voltage == MMC_SIGNAL_VOLTAGE_180) {
+			min_uv = 1800000;
+			max_uv = 1800000;
+		} else {
+			dev_err(host->dev, "Unsupported signal voltage!\n");
+			return -EINVAL;
+		}
+
+		ret = regulator_set_voltage(mmc->supply.vqmmc, min_uv, max_uv);
+		if (ret) {
+			dev_err(host->dev,
+					"Regulator set error %d: %d - %d\n",
+					ret, min_uv, max_uv);
+		} else {
+			/* Apply different pinctrl settings for different signal voltage */
+			if (ios->signal_voltage == MMC_SIGNAL_VOLTAGE_180)
+				pinctrl_select_state(host->pinctrl, host->pins_uhs);
+			else
+				pinctrl_select_state(host->pinctrl, host->pins_default);
+		}
+	}
+	return ret;
+}
+
+static int msdc_card_busy(struct mmc_host *mmc)
+{
+	struct msdc_host *host = mmc_priv(mmc);
+	u32 status = readl(host->base + MSDC_PS);
+
+	/* check if any pin between dat[0:3] is low */
+	if (((status >> 16) & 0xf) != 0xf)
+		return 1;
+
+	return 0;
+}
+
+static void msdc_request_timeout(struct work_struct *work)
+{
+	struct msdc_host *host = container_of(work, struct msdc_host,
+			req_timeout.work);
+
+	/* simulate HW timeout status */
+	dev_err(host->dev, "%s: aborting cmd/data/mrq\n", __func__);
+	if (host->mrq) {
+		dev_err(host->dev, "%s: aborting mrq=%p cmd=%d\n", __func__,
+				host->mrq, host->mrq->cmd->opcode);
+		if (host->cmd) {
+			dev_err(host->dev, "%s: aborting cmd=%d\n",
+					__func__, host->cmd->opcode);
+			msdc_cmd_done(host, MSDC_INT_CMDTMO, host->mrq,
+					host->cmd);
+		} else if (host->data) {
+			dev_err(host->dev, "%s: abort data: cmd%d; %d blocks\n",
+					__func__, host->mrq->cmd->opcode,
+					host->data->blocks);
+			msdc_data_xfer_done(host, MSDC_INT_DATTMO, host->mrq,
+					host->data);
+		}
+	}
+}
+
+static irqreturn_t msdc_irq(int irq, void *dev_id)
+{
+	struct msdc_host *host = (struct msdc_host *) dev_id;
+
+	while (true) {
+		unsigned long flags;
+		struct mmc_request *mrq;
+		struct mmc_command *cmd;
+		struct mmc_data *data;
+		u32 events, event_mask;
+
+		spin_lock_irqsave(&host->lock, flags);
+		events = readl(host->base + MSDC_INT);
+		event_mask = readl(host->base + MSDC_INTEN);
+		/* clear interrupts */
+		writel(events & event_mask, host->base + MSDC_INT);
+
+		mrq = host->mrq;
+		cmd = host->cmd;
+		data = host->data;
+		spin_unlock_irqrestore(&host->lock, flags);
+
+		if (!(events & event_mask))
+			break;
+
+		if (!mrq) {
+			dev_err(host->dev,
+				"%s: MRQ=NULL; events=%08X; event_mask=%08X\n",
+				__func__, events, event_mask);
+			WARN_ON(1);
+			break;
+		}
+
+		dev_dbg(host->dev, "%s: events=%08X\n", __func__, events);
+
+		if (cmd)
+			msdc_cmd_done(host, events, mrq, cmd);
+		else if (data)
+			msdc_data_xfer_done(host, events, mrq, data);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static void msdc_init_hw(struct msdc_host *host)
+{
+	u32 val;
+
+	/* Configure to MMC/SD mode, clock free running */
+	sdr_set_bits(host->base + MSDC_CFG, MSDC_CFG_MODE | MSDC_CFG_CKPDN);
+
+	/* Reset */
+	msdc_reset_hw(host);
+
+	/* Disable card detection */
+	sdr_clr_bits(host->base + MSDC_PS, MSDC_PS_CDEN);
+
+	/* Disable and clear all interrupts */
+	writel(0, host->base + MSDC_INTEN);
+	val = readl(host->base + MSDC_INT);
+	writel(val, host->base + MSDC_INT);
+
+	writel(0, host->base + MSDC_PAD_TUNE);
+	writel(0, host->base + MSDC_IOCON);
+	sdr_set_field(host->base + MSDC_IOCON, MSDC_IOCON_DDLSEL, 1);
+	writel(0x403c004f, host->base + MSDC_PATCH_BIT);
+	sdr_set_field(host->base + MSDC_PATCH_BIT, MSDC_CKGEN_MSDC_DLY_SEL, 1);
+	writel(0xffff0089, host->base + MSDC_PATCH_BIT1);
+	/* Configure to enable SDIO mode.
+	 * it's must otherwise sdio cmd5 failed
+	 */
+	sdr_set_bits(host->base + SDC_CFG, SDC_CFG_SDIO);
+
+	/* disable detect SDIO device interrupt function */
+	sdr_clr_bits(host->base + SDC_CFG, SDC_CFG_SDIOIDE);
+
+	/* Configure to default data timeout */
+	sdr_set_field(host->base + SDC_CFG, SDC_CFG_DTOC, 3);
+
+	dev_dbg(host->dev, "init hardware done!");
+}
+
+static void msdc_deinit_hw(struct msdc_host *host)
+{
+	u32 val;
+	/* Disable and clear all interrupts */
+	writel(0, host->base + MSDC_INTEN);
+
+	val = readl(host->base + MSDC_INT);
+	writel(val, host->base + MSDC_INT);
+}
+
+/* init gpd and bd list in msdc_drv_probe */
+static void msdc_init_gpd_bd(struct msdc_host *host, struct msdc_dma *dma)
+{
+	struct mt_gpdma_desc *gpd = dma->gpd;
+	struct mt_bdma_desc *bd = dma->bd;
+	int i;
+
+	memset(gpd, 0, sizeof(struct mt_gpdma_desc));
+
+	gpd->gpd_info = GPDMA_DESC_BDP; /* hwo, cs, bd pointer */
+	gpd->ptr = (u32)dma->bd_addr; /* physical address */
+
+	memset(bd, 0, sizeof(struct mt_bdma_desc) * MAX_BD_NUM);
+	for (i = 0; i < (MAX_BD_NUM - 1); i++)
+		bd[i].next = (u32)dma->bd_addr + sizeof(*bd) * (i + 1);
+}
+
+static void msdc_ops_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
+{
+	struct msdc_host *host = mmc_priv(mmc);
+	int ret;
+	u32 ddr = 0;
+
+	pm_runtime_get_sync(host->dev);
+
+	if (ios->timing == MMC_TIMING_UHS_DDR50 ||
+	    ios->timing == MMC_TIMING_MMC_DDR52)
+		ddr = 1;
+
+	msdc_set_buswidth(host, ios->bus_width);
+
+	/* Suspend/Resume will do power off/on */
+	switch (ios->power_mode) {
+	case MMC_POWER_UP:
+		if (!IS_ERR(mmc->supply.vmmc)) {
+			ret = mmc_regulator_set_ocr(mmc, mmc->supply.vmmc,
+					ios->vdd);
+			if (ret) {
+				dev_err(host->dev, "Failed to set vmmc power!\n");
+				goto end;
+			}
+		}
+		break;
+	case MMC_POWER_ON:
+		if (!IS_ERR(mmc->supply.vqmmc) && !host->vqmmc_enabled) {
+			ret = regulator_enable(mmc->supply.vqmmc);
+			if (ret)
+				dev_err(host->dev, "Failed to set vqmmc power!\n");
+			else
+				host->vqmmc_enabled = true;
+		}
+		break;
+	case MMC_POWER_OFF:
+		if (!IS_ERR(mmc->supply.vmmc))
+			mmc_regulator_set_ocr(mmc, mmc->supply.vmmc, 0);
+
+		if (!IS_ERR(mmc->supply.vqmmc) && host->vqmmc_enabled) {
+			regulator_disable(mmc->supply.vqmmc);
+			host->vqmmc_enabled = false;
+		}
+		break;
+	default:
+		break;
+	}
+
+	if (host->mclk != ios->clock || host->ddr != ddr)
+		msdc_set_mclk(host, ddr, ios->clock);
+
+end:
+	pm_runtime_mark_last_busy(host->dev);
+	pm_runtime_put_autosuspend(host->dev);
+}
+
+static struct mmc_host_ops mt_msdc_ops = {
+	.post_req = msdc_post_req,
+	.pre_req = msdc_pre_req,
+	.request = msdc_ops_request,
+	.set_ios = msdc_ops_set_ios,
+	.start_signal_voltage_switch = msdc_ops_switch_volt,
+	.card_busy = msdc_card_busy,
+};
+
+static int msdc_drv_probe(struct platform_device *pdev)
+{
+	struct mmc_host *mmc;
+	struct msdc_host *host;
+	struct resource *res;
+	int ret;
+
+	if (!pdev->dev.of_node) {
+		dev_err(&pdev->dev, "No DT found\n");
+		return -EINVAL;
+	}
+	/* Allocate MMC host for this device */
+	mmc = mmc_alloc_host(sizeof(struct msdc_host), &pdev->dev);
+	if (!mmc)
+		return -ENOMEM;
+
+	host = mmc_priv(mmc);
+	ret = mmc_of_parse(mmc);
+	if (ret)
+		goto host_free;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	host->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(host->base)) {
+		ret = PTR_ERR(host->base);
+		goto host_free;
+	}
+
+	ret = mmc_regulator_get_supply(mmc);
+	if (ret == -EPROBE_DEFER)
+		goto host_free;
+
+	host->src_clk = devm_clk_get(&pdev->dev, "source");
+	if (IS_ERR(host->src_clk)) {
+		ret = PTR_ERR(host->src_clk);
+		goto host_free;
+	}
+
+	host->h_clk = devm_clk_get(&pdev->dev, "hclk");
+	if (IS_ERR(host->h_clk)) {
+		ret = PTR_ERR(host->h_clk);
+		goto host_free;
+	}
+
+	host->irq = platform_get_irq(pdev, 0);
+	if (host->irq < 0) {
+		ret = -EINVAL;
+		goto host_free;
+	}
+
+	host->pinctrl = devm_pinctrl_get(&pdev->dev);
+	if (IS_ERR(host->pinctrl)) {
+		ret = PTR_ERR(host->pinctrl);
+		dev_err(&pdev->dev, "Cannot find pinctrl!\n");
+		goto host_free;
+	}
+
+	host->pins_default = pinctrl_lookup_state(host->pinctrl, "default");
+	if (IS_ERR(host->pins_default)) {
+		ret = PTR_ERR(host->pins_default);
+		dev_err(&pdev->dev, "Cannot find pinctrl default!\n");
+		goto host_free;
+	}
+
+	host->pins_uhs = pinctrl_lookup_state(host->pinctrl, "state_uhs");
+	if (IS_ERR(host->pins_uhs)) {
+		ret = PTR_ERR(host->pins_uhs);
+		dev_err(&pdev->dev, "Cannot find pinctrl uhs!\n");
+		goto host_free;
+	}
+
+	host->dev = &pdev->dev;
+	host->mmc = mmc;
+	host->src_clk_freq = clk_get_rate(host->src_clk);
+	/* Set host parameters to mmc */
+	mmc->ops = &mt_msdc_ops;
+	mmc->f_min = host->src_clk_freq / (4 * 255);
+
+	mmc->caps |= MMC_CAP_ERASE | MMC_CAP_CMD23;
+	/* MMC core transfer sizes tunable parameters */
+	mmc->max_segs = MAX_BD_NUM;
+	mmc->max_seg_size = BDMA_DESC_BUFLEN;
+	mmc->max_blk_size = 2048;
+	mmc->max_req_size = 512 * 1024;
+	mmc->max_blk_count = mmc->max_req_size / 512;
+	host->dma_mask = DMA_BIT_MASK(32);
+	mmc_dev(mmc)->dma_mask = &host->dma_mask;
+
+	host->timeout_clks = 3 * 1048576;
+	host->dma.gpd = dma_alloc_coherent(&pdev->dev,
+				sizeof(struct mt_gpdma_desc),
+				&host->dma.gpd_addr, GFP_KERNEL);
+	host->dma.bd = dma_alloc_coherent(&pdev->dev,
+				MAX_BD_NUM * sizeof(struct mt_bdma_desc),
+				&host->dma.bd_addr, GFP_KERNEL);
+	if (!host->dma.gpd || !host->dma.bd) {
+		ret = -ENOMEM;
+		goto release_mem;
+	}
+	msdc_init_gpd_bd(host, &host->dma);
+	INIT_DELAYED_WORK(&host->req_timeout, msdc_request_timeout);
+	spin_lock_init(&host->lock);
+
+	platform_set_drvdata(pdev, mmc);
+	msdc_ungate_clock(host);
+	msdc_init_hw(host);
+
+	ret = devm_request_irq(&pdev->dev, host->irq, msdc_irq,
+		IRQF_TRIGGER_LOW | IRQF_ONESHOT, pdev->name, host);
+	if (ret)
+		goto release;
+
+	pm_runtime_set_active(host->dev);
+	pm_runtime_set_autosuspend_delay(host->dev, MTK_MMC_AUTOSUSPEND_DELAY);
+	pm_runtime_use_autosuspend(host->dev);
+	pm_runtime_enable(host->dev);
+	ret = mmc_add_host(mmc);
+
+	if (ret)
+		goto end;
+
+	return 0;
+end:
+	pm_runtime_disable(host->dev);
+release:
+	platform_set_drvdata(pdev, NULL);
+	msdc_deinit_hw(host);
+	msdc_gate_clock(host);
+release_mem:
+	if (host->dma.gpd)
+		dma_free_coherent(&pdev->dev,
+			sizeof(struct mt_gpdma_desc),
+			host->dma.gpd, host->dma.gpd_addr);
+	if (host->dma.bd)
+		dma_free_coherent(&pdev->dev,
+			MAX_BD_NUM * sizeof(struct mt_bdma_desc),
+			host->dma.bd, host->dma.bd_addr);
+host_free:
+	mmc_free_host(mmc);
+
+	return ret;
+}
+
+static int msdc_drv_remove(struct platform_device *pdev)
+{
+	struct mmc_host *mmc;
+	struct msdc_host *host;
+
+	mmc = platform_get_drvdata(pdev);
+	host = mmc_priv(mmc);
+
+	pm_runtime_get_sync(host->dev);
+
+	platform_set_drvdata(pdev, NULL);
+	mmc_remove_host(host->mmc);
+	msdc_deinit_hw(host);
+	msdc_gate_clock(host);
+
+	pm_runtime_disable(host->dev);
+	pm_runtime_put_noidle(host->dev);
+	dma_free_coherent(&pdev->dev,
+			sizeof(struct mt_gpdma_desc),
+			host->dma.gpd, host->dma.gpd_addr);
+	dma_free_coherent(&pdev->dev, MAX_BD_NUM * sizeof(struct mt_bdma_desc),
+			host->dma.bd, host->dma.bd_addr);
+
+	mmc_free_host(host->mmc);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM
+static void msdc_save_reg(struct msdc_host *host)
+{
+	host->save_para.msdc_cfg = readl(host->base + MSDC_CFG);
+	host->save_para.iocon = readl(host->base + MSDC_IOCON);
+	host->save_para.sdc_cfg = readl(host->base + SDC_CFG);
+	host->save_para.pad_tune = readl(host->base + MSDC_PAD_TUNE);
+	host->save_para.patch_bit0 = readl(host->base + MSDC_PATCH_BIT);
+	host->save_para.patch_bit1 = readl(host->base + MSDC_PATCH_BIT1);
+}
+
+static void msdc_restore_reg(struct msdc_host *host)
+{
+	writel(host->save_para.msdc_cfg, host->base + MSDC_CFG);
+	writel(host->save_para.iocon, host->base + MSDC_IOCON);
+	writel(host->save_para.sdc_cfg, host->base + SDC_CFG);
+	writel(host->save_para.pad_tune, host->base + MSDC_PAD_TUNE);
+	writel(host->save_para.patch_bit0, host->base + MSDC_PATCH_BIT);
+	writel(host->save_para.patch_bit1, host->base + MSDC_PATCH_BIT1);
+}
+
+static int msdc_runtime_suspend(struct device *dev)
+{
+	struct mmc_host *mmc = dev_get_drvdata(dev);
+	struct msdc_host *host = mmc_priv(mmc);
+
+	msdc_save_reg(host);
+	msdc_gate_clock(host);
+	return 0;
+}
+
+static int msdc_runtime_resume(struct device *dev)
+{
+	struct mmc_host *mmc = dev_get_drvdata(dev);
+	struct msdc_host *host = mmc_priv(mmc);
+
+	msdc_ungate_clock(host);
+	msdc_restore_reg(host);
+	return 0;
+}
+#endif
+
+static const struct dev_pm_ops msdc_dev_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
+	SET_RUNTIME_PM_OPS(msdc_runtime_suspend, msdc_runtime_resume, NULL)
+};
+
+static const struct of_device_id msdc_of_ids[] = {
+	{   .compatible = "mediatek,mt8135-mmc", },
+	{}
+};
+
+static struct platform_driver mt_msdc_driver = {
+	.probe = msdc_drv_probe,
+	.remove = msdc_drv_remove,
+	.driver = {
+		.name = "mtk-msdc",
+		.of_match_table = msdc_of_ids,
+		.pm = &msdc_dev_pm_ops,
+	},
+};
+
+module_platform_driver(mt_msdc_driver);
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("MediaTek SD/MMC Card Driver");
diff --git a/drivers/mmc/host/mxcmmc.c b/drivers/mmc/host/mxcmmc.c
index 317d709f7550..d110f9e98c4b 100644
--- a/drivers/mmc/host/mxcmmc.c
+++ b/drivers/mmc/host/mxcmmc.c
@@ -605,11 +605,7 @@ static int mxcmci_push(struct mxcmci_host *host, void *_buf, int bytes)
 		mxcmci_writel(host, cpu_to_le32(tmp), MMC_REG_BUFFER_ACCESS);
 	}
 
-	stat = mxcmci_poll_status(host, STATUS_BUF_WRITE_RDY);
-	if (stat)
-		return stat;
-
-	return 0;
+	return mxcmci_poll_status(host, STATUS_BUF_WRITE_RDY);
 }
 
 static int mxcmci_transfer_data(struct mxcmci_host *host)
diff --git a/drivers/mmc/host/mxs-mmc.c b/drivers/mmc/host/mxs-mmc.c
index a82411a2c024..d839147e591d 100644
--- a/drivers/mmc/host/mxs-mmc.c
+++ b/drivers/mmc/host/mxs-mmc.c
@@ -549,7 +549,7 @@ static const struct mmc_host_ops mxs_mmc_ops = {
 	.enable_sdio_irq = mxs_mmc_enable_sdio_irq,
 };
 
-static struct platform_device_id mxs_ssp_ids[] = {
+static const struct platform_device_id mxs_ssp_ids[] = {
 	{
 		.name = "imx23-mmc",
 		.driver_data = IMX23_SSP,
diff --git a/drivers/mmc/host/rtsx_pci_sdmmc.c b/drivers/mmc/host/rtsx_pci_sdmmc.c
index 1d3d6c4bfdc6..93137483ecde 100644
--- a/drivers/mmc/host/rtsx_pci_sdmmc.c
+++ b/drivers/mmc/host/rtsx_pci_sdmmc.c
@@ -1474,7 +1474,7 @@ static int rtsx_pci_sdmmc_drv_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static struct platform_device_id rtsx_pci_sdmmc_ids[] = {
+static const struct platform_device_id rtsx_pci_sdmmc_ids[] = {
 	{
 		.name = DRV_NAME_RTSX_PCI_SDMMC,
 	}, {
diff --git a/drivers/mmc/host/rtsx_usb_sdmmc.c b/drivers/mmc/host/rtsx_usb_sdmmc.c
index 88af827e086b..6c71fc9f76c7 100644
--- a/drivers/mmc/host/rtsx_usb_sdmmc.c
+++ b/drivers/mmc/host/rtsx_usb_sdmmc.c
@@ -1439,7 +1439,7 @@ static int rtsx_usb_sdmmc_drv_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static struct platform_device_id rtsx_usb_sdmmc_ids[] = {
+static const struct platform_device_id rtsx_usb_sdmmc_ids[] = {
 	{
 		.name = "rtsx_usb_sdmmc",
 	}, {
diff --git a/drivers/mmc/host/s3cmci.c b/drivers/mmc/host/s3cmci.c
index 94cddf381ba3..6291d5042ef2 100644
--- a/drivers/mmc/host/s3cmci.c
+++ b/drivers/mmc/host/s3cmci.c
@@ -1856,7 +1856,7 @@ static int s3cmci_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static struct platform_device_id s3cmci_driver_ids[] = {
+static const struct platform_device_id s3cmci_driver_ids[] = {
 	{
 		.name	= "s3c2410-sdi",
 		.driver_data	= 0,
diff --git a/drivers/mmc/host/sdhci-bcm2835.c b/drivers/mmc/host/sdhci-bcm2835.c
index 0ef0343c603a..1c65d4690e70 100644
--- a/drivers/mmc/host/sdhci-bcm2835.c
+++ b/drivers/mmc/host/sdhci-bcm2835.c
@@ -172,9 +172,19 @@ static int bcm2835_sdhci_probe(struct platform_device *pdev)
 		ret = PTR_ERR(pltfm_host->clk);
 		goto err;
 	}
+	ret = clk_prepare_enable(pltfm_host->clk);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to enable host clk\n");
+		goto err;
+	}
 
-	return sdhci_add_host(host);
+	ret = sdhci_add_host(host);
+	if (ret)
+		goto err_clk;
 
+	return 0;
+err_clk:
+	clk_disable_unprepare(pltfm_host->clk);
 err:
 	sdhci_pltfm_free(pdev);
 	return ret;
diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c
index 82f512d87cb8..faf0cb910c96 100644
--- a/drivers/mmc/host/sdhci-esdhc-imx.c
+++ b/drivers/mmc/host/sdhci-esdhc-imx.c
@@ -4,7 +4,7 @@
  * derived from the OF-version.
  *
  * Copyright (c) 2010 Pengutronix e.K.
- *   Author: Wolfram Sang <w.sang@pengutronix.de>
+ *   Author: Wolfram Sang <kernel@pengutronix.de>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -112,6 +112,14 @@
 #define ESDHC_FLAG_STD_TUNING		BIT(5)
 /* The IP has SDHCI_CAPABILITIES_1 register */
 #define ESDHC_FLAG_HAVE_CAP1		BIT(6)
+/*
+ * The IP has errata ERR004536
+ * uSDHC: ADMA Length Mismatch Error occurs if the AHB read access is slow,
+ * when reading data from the card
+ */
+#define ESDHC_FLAG_ERR004536		BIT(7)
+/* The IP supports HS200 mode */
+#define ESDHC_FLAG_HS200		BIT(8)
 
 struct esdhc_soc_data {
 	u32 flags;
@@ -139,7 +147,13 @@ static struct esdhc_soc_data usdhc_imx6q_data = {
 
 static struct esdhc_soc_data usdhc_imx6sl_data = {
 	.flags = ESDHC_FLAG_USDHC | ESDHC_FLAG_STD_TUNING
-			| ESDHC_FLAG_HAVE_CAP1,
+			| ESDHC_FLAG_HAVE_CAP1 | ESDHC_FLAG_ERR004536
+			| ESDHC_FLAG_HS200,
+};
+
+static struct esdhc_soc_data usdhc_imx6sx_data = {
+	.flags = ESDHC_FLAG_USDHC | ESDHC_FLAG_STD_TUNING
+			| ESDHC_FLAG_HAVE_CAP1 | ESDHC_FLAG_HS200,
 };
 
 struct pltfm_imx_data {
@@ -161,7 +175,7 @@ struct pltfm_imx_data {
 	u32 is_ddr;
 };
 
-static struct platform_device_id imx_esdhc_devtype[] = {
+static const struct platform_device_id imx_esdhc_devtype[] = {
 	{
 		.name = "sdhci-esdhc-imx25",
 		.driver_data = (kernel_ulong_t) &esdhc_imx25_data,
@@ -182,6 +196,7 @@ static const struct of_device_id imx_esdhc_dt_ids[] = {
 	{ .compatible = "fsl,imx35-esdhc", .data = &esdhc_imx35_data, },
 	{ .compatible = "fsl,imx51-esdhc", .data = &esdhc_imx51_data, },
 	{ .compatible = "fsl,imx53-esdhc", .data = &esdhc_imx53_data, },
+	{ .compatible = "fsl,imx6sx-usdhc", .data = &usdhc_imx6sx_data, },
 	{ .compatible = "fsl,imx6sl-usdhc", .data = &usdhc_imx6sl_data, },
 	{ .compatible = "fsl,imx6q-usdhc", .data = &usdhc_imx6q_data, },
 	{ /* sentinel */ }
@@ -298,7 +313,7 @@ static void esdhc_writel_le(struct sdhci_host *host, u32 val, int reg)
 	u32 data;
 
 	if (unlikely(reg == SDHCI_INT_ENABLE || reg == SDHCI_SIGNAL_ENABLE)) {
-		if (val & SDHCI_INT_CARD_INT) {
+		if ((val & SDHCI_INT_CARD_INT) && !esdhc_is_usdhc(imx_data)) {
 			/*
 			 * Clear and then set D3CD bit to avoid missing the
 			 * card interrupt.  This is a eSDHC controller problem
@@ -313,6 +328,11 @@ static void esdhc_writel_le(struct sdhci_host *host, u32 val, int reg)
 			data |= ESDHC_CTRL_D3CD;
 			writel(data, host->ioaddr + SDHCI_HOST_CONTROL);
 		}
+
+		if (val & SDHCI_INT_ADMA_ERROR) {
+			val &= ~SDHCI_INT_ADMA_ERROR;
+			val |= ESDHC_INT_VENDOR_SPEC_DMA_ERR;
+		}
 	}
 
 	if (unlikely((imx_data->socdata->flags & ESDHC_FLAG_MULTIBLK_NO_INT)
@@ -333,13 +353,6 @@ static void esdhc_writel_le(struct sdhci_host *host, u32 val, int reg)
 			}
 	}
 
-	if (unlikely(reg == SDHCI_INT_ENABLE || reg == SDHCI_SIGNAL_ENABLE)) {
-		if (val & SDHCI_INT_ADMA_ERROR) {
-			val &= ~SDHCI_INT_ADMA_ERROR;
-			val |= ESDHC_INT_VENDOR_SPEC_DMA_ERR;
-		}
-	}
-
 	writel(val, host->ioaddr + reg);
 }
 
@@ -903,7 +916,8 @@ sdhci_esdhc_imx_probe_dt(struct platform_device *pdev,
 
 	mmc_of_parse_voltage(np, &host->ocr_mask);
 
-	return 0;
+	/* call to generic mmc_of_parse to support additional capabilities */
+	return mmc_of_parse(host->mmc);
 }
 #else
 static inline int
@@ -924,6 +938,7 @@ static int sdhci_esdhc_imx_probe(struct platform_device *pdev)
 	struct esdhc_platform_data *boarddata;
 	int err;
 	struct pltfm_imx_data *imx_data;
+	bool dt = true;
 
 	host = sdhci_pltfm_init(pdev, &sdhci_esdhc_imx_pdata, 0);
 	if (IS_ERR(host))
@@ -991,6 +1006,16 @@ static int sdhci_esdhc_imx_probe(struct platform_device *pdev)
 		writel(0x08100810, host->ioaddr + ESDHC_WTMK_LVL);
 		host->quirks2 |= SDHCI_QUIRK2_PRESET_VALUE_BROKEN;
 		host->mmc->caps |= MMC_CAP_1_8V_DDR;
+
+		if (!(imx_data->socdata->flags & ESDHC_FLAG_HS200))
+			host->quirks2 |= SDHCI_QUIRK2_BROKEN_HS200;
+
+		/*
+		* errata ESDHC_FLAG_ERR004536 fix for MX6Q TO1.2 and MX6DL
+		* TO1.1, it's harmless for MX6SL
+		*/
+		writel(readl(host->ioaddr + 0x6c) | BIT(7),
+			host->ioaddr + 0x6c);
 	}
 
 	if (imx_data->socdata->flags & ESDHC_FLAG_MAN_TUNING)
@@ -1002,6 +1027,9 @@ static int sdhci_esdhc_imx_probe(struct platform_device *pdev)
 			ESDHC_STD_TUNING_EN | ESDHC_TUNING_START_TAP,
 			host->ioaddr + ESDHC_TUNING_CTRL);
 
+	if (imx_data->socdata->flags & ESDHC_FLAG_ERR004536)
+		host->quirks |= SDHCI_QUIRK_BROKEN_ADMA;
+
 	boarddata = &imx_data->boarddata;
 	if (sdhci_esdhc_imx_probe_dt(pdev, host, boarddata) < 0) {
 		if (!host->mmc->parent->platform_data) {
@@ -1011,11 +1039,44 @@ static int sdhci_esdhc_imx_probe(struct platform_device *pdev)
 		}
 		imx_data->boarddata = *((struct esdhc_platform_data *)
 					host->mmc->parent->platform_data);
+		dt = false;
+	}
+	/* write_protect */
+	if (boarddata->wp_type == ESDHC_WP_GPIO && !dt) {
+		err = mmc_gpio_request_ro(host->mmc, boarddata->wp_gpio);
+		if (err) {
+			dev_err(mmc_dev(host->mmc),
+				"failed to request write-protect gpio!\n");
+			goto disable_clk;
+		}
+		host->mmc->caps2 |= MMC_CAP2_RO_ACTIVE_HIGH;
 	}
 
 	/* card_detect */
-	if (boarddata->cd_type == ESDHC_CD_CONTROLLER)
+	switch (boarddata->cd_type) {
+	case ESDHC_CD_GPIO:
+		if (dt)
+			break;
+		err = mmc_gpio_request_cd(host->mmc, boarddata->cd_gpio, 0);
+		if (err) {
+			dev_err(mmc_dev(host->mmc),
+				"failed to request card-detect gpio!\n");
+			goto disable_clk;
+		}
+		/* fall through */
+
+	case ESDHC_CD_CONTROLLER:
+		/* we have a working card_detect back */
 		host->quirks &= ~SDHCI_QUIRK_BROKEN_CARD_DETECTION;
+		break;
+
+	case ESDHC_CD_PERMANENT:
+		host->mmc->caps |= MMC_CAP_NONREMOVABLE;
+		break;
+
+	case ESDHC_CD_NONE:
+		break;
+	}
 
 	switch (boarddata->max_bus_width) {
 	case 8:
@@ -1048,11 +1109,6 @@ static int sdhci_esdhc_imx_probe(struct platform_device *pdev)
 		host->quirks2 |= SDHCI_QUIRK2_NO_1_8_V;
 	}
 
-	/* call to generic mmc_of_parse to support additional capabilities */
-	err = mmc_of_parse(host->mmc);
-	if (err)
-		goto disable_clk;
-
 	err = sdhci_add_host(host);
 	if (err)
 		goto disable_clk;
@@ -1151,5 +1207,5 @@ static struct platform_driver sdhci_esdhc_imx_driver = {
 module_platform_driver(sdhci_esdhc_imx_driver);
 
 MODULE_DESCRIPTION("SDHCI driver for Freescale i.MX eSDHC");
-MODULE_AUTHOR("Wolfram Sang <w.sang@pengutronix.de>");
+MODULE_AUTHOR("Wolfram Sang <kernel@pengutronix.de>");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/mmc/host/sdhci-of-arasan.c b/drivers/mmc/host/sdhci-of-arasan.c
index 6287d426c96b..21c0c08dfe54 100644
--- a/drivers/mmc/host/sdhci-of-arasan.c
+++ b/drivers/mmc/host/sdhci-of-arasan.c
@@ -20,6 +20,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/of_device.h>
 #include "sdhci-pltfm.h"
 
 #define SDHCI_ARASAN_CLK_CTRL_OFFSET	0x2c
@@ -168,6 +169,11 @@ static int sdhci_arasan_probe(struct platform_device *pdev)
 		goto clk_disable_all;
 	}
 
+	if (of_device_is_compatible(pdev->dev.of_node, "arasan,sdhci-4.9a")) {
+		host->quirks |= SDHCI_QUIRK_NO_HISPD_BIT;
+		host->quirks2 |= SDHCI_QUIRK2_HOST_NO_CMD23;
+	}
+
 	sdhci_get_of_property(pdev);
 	pltfm_host = sdhci_priv(host);
 	pltfm_host->priv = sdhci_arasan;
@@ -208,6 +214,7 @@ static int sdhci_arasan_remove(struct platform_device *pdev)
 
 static const struct of_device_id sdhci_arasan_of_match[] = {
 	{ .compatible = "arasan,sdhci-8.9a" },
+	{ .compatible = "arasan,sdhci-4.9a" },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, sdhci_arasan_of_match);
diff --git a/drivers/mmc/host/sdhci-of-esdhc.c b/drivers/mmc/host/sdhci-of-esdhc.c
index 22e9111b11ff..797be7549a15 100644
--- a/drivers/mmc/host/sdhci-of-esdhc.c
+++ b/drivers/mmc/host/sdhci-of-esdhc.c
@@ -199,7 +199,7 @@ static unsigned int esdhc_of_get_min_clock(struct sdhci_host *host)
 
 static void esdhc_of_set_clock(struct sdhci_host *host, unsigned int clock)
 {
-	int pre_div = 2;
+	int pre_div = 1;
 	int div = 1;
 	u32 temp;
 
@@ -229,7 +229,7 @@ static void esdhc_of_set_clock(struct sdhci_host *host, unsigned int clock)
 
 	dev_dbg(mmc_dev(host->mmc), "desired SD clock: %d, actual: %d\n",
 		clock, host->max_clk / pre_div / div);
-
+	host->mmc->actual_clock = host->max_clk / pre_div / div;
 	pre_div >>= 1;
 	div--;
 
@@ -361,6 +361,13 @@ static int sdhci_esdhc_probe(struct platform_device *pdev)
 	sdhci_get_of_property(pdev);
 
 	np = pdev->dev.of_node;
+	if (of_device_is_compatible(np, "fsl,p5040-esdhc") ||
+	    of_device_is_compatible(np, "fsl,p5020-esdhc") ||
+	    of_device_is_compatible(np, "fsl,p4080-esdhc") ||
+	    of_device_is_compatible(np, "fsl,p1020-esdhc") ||
+	    of_device_is_compatible(np, "fsl,t1040-esdhc"))
+		host->quirks &= ~SDHCI_QUIRK_BROKEN_CARD_DETECTION;
+
 	if (of_device_is_compatible(np, "fsl,p2020-esdhc")) {
 		/*
 		 * Freescale messed up with P2020 as it has a non-standard
diff --git a/drivers/mmc/host/sdhci-pci-data.c b/drivers/mmc/host/sdhci-pci-data.c
index a611217769f5..56fddc622a54 100644
--- a/drivers/mmc/host/sdhci-pci-data.c
+++ b/drivers/mmc/host/sdhci-pci-data.c
@@ -3,3 +3,6 @@
 
 struct sdhci_pci_data *(*sdhci_pci_get_data)(struct pci_dev *pdev, int slotno);
 EXPORT_SYMBOL_GPL(sdhci_pci_get_data);
+
+int sdhci_pci_spt_drive_strength;
+EXPORT_SYMBOL_GPL(sdhci_pci_spt_drive_strength);
diff --git a/drivers/mmc/host/sdhci-pci.c b/drivers/mmc/host/sdhci-pci.c
index 7a3fc16d0a6c..94f54d2772e8 100644
--- a/drivers/mmc/host/sdhci-pci.c
+++ b/drivers/mmc/host/sdhci-pci.c
@@ -20,6 +20,7 @@
 #include <linux/slab.h>
 #include <linux/device.h>
 #include <linux/mmc/host.h>
+#include <linux/mmc/mmc.h>
 #include <linux/scatterlist.h>
 #include <linux/io.h>
 #include <linux/gpio.h>
@@ -266,6 +267,69 @@ static void sdhci_pci_int_hw_reset(struct sdhci_host *host)
 	usleep_range(300, 1000);
 }
 
+static int spt_select_drive_strength(struct sdhci_host *host,
+				     struct mmc_card *card,
+				     unsigned int max_dtr,
+				     int host_drv, int card_drv, int *drv_type)
+{
+	int drive_strength;
+
+	if (sdhci_pci_spt_drive_strength > 0)
+		drive_strength = sdhci_pci_spt_drive_strength & 0xf;
+	else
+		drive_strength = 1; /* 33-ohm */
+
+	if ((mmc_driver_type_mask(drive_strength) & card_drv) == 0)
+		drive_strength = 0; /* Default 50-ohm */
+
+	return drive_strength;
+}
+
+/* Try to read the drive strength from the card */
+static void spt_read_drive_strength(struct sdhci_host *host)
+{
+	u32 val, i, t;
+	u16 m;
+
+	if (sdhci_pci_spt_drive_strength)
+		return;
+
+	sdhci_pci_spt_drive_strength = -1;
+
+	m = sdhci_readw(host, SDHCI_HOST_CONTROL2) & 0x7;
+	if (m != 3 && m != 5)
+		return;
+	val = sdhci_readl(host, SDHCI_PRESENT_STATE);
+	if (val & 0x3)
+		return;
+	sdhci_writel(host, 0x007f0023, SDHCI_INT_ENABLE);
+	sdhci_writel(host, 0, SDHCI_SIGNAL_ENABLE);
+	sdhci_writew(host, 0x10, SDHCI_TRANSFER_MODE);
+	sdhci_writeb(host, 0xe, SDHCI_TIMEOUT_CONTROL);
+	sdhci_writew(host, 512, SDHCI_BLOCK_SIZE);
+	sdhci_writew(host, 1, SDHCI_BLOCK_COUNT);
+	sdhci_writel(host, 0, SDHCI_ARGUMENT);
+	sdhci_writew(host, 0x83b, SDHCI_COMMAND);
+	for (i = 0; i < 1000; i++) {
+		val = sdhci_readl(host, SDHCI_INT_STATUS);
+		if (val & 0xffff8000)
+			return;
+		if (val & 0x20)
+			break;
+		udelay(1);
+	}
+	val = sdhci_readl(host, SDHCI_PRESENT_STATE);
+	if (!(val & 0x800))
+		return;
+	for (i = 0; i < 47; i++)
+		val = sdhci_readl(host, SDHCI_BUFFER);
+	t = val & 0xf00;
+	if (t != 0x200 && t != 0x300)
+		return;
+
+	sdhci_pci_spt_drive_strength = 0x10 | ((val >> 12) & 0xf);
+}
+
 static int byt_emmc_probe_slot(struct sdhci_pci_slot *slot)
 {
 	slot->host->mmc->caps |= MMC_CAP_8_BIT_DATA | MMC_CAP_NONREMOVABLE |
@@ -276,6 +340,10 @@ static int byt_emmc_probe_slot(struct sdhci_pci_slot *slot)
 	slot->hw_reset = sdhci_pci_int_hw_reset;
 	if (slot->chip->pdev->device == PCI_DEVICE_ID_INTEL_BSW_EMMC)
 		slot->host->timeout_clk = 1000; /* 1000 kHz i.e. 1 MHz */
+	if (slot->chip->pdev->device == PCI_DEVICE_ID_INTEL_SPT_EMMC) {
+		spt_read_drive_strength(slot->host);
+		slot->select_drive_strength = spt_select_drive_strength;
+	}
 	return 0;
 }
 
@@ -302,6 +370,7 @@ static const struct sdhci_pci_fixes sdhci_intel_byt_emmc = {
 	.probe_slot	= byt_emmc_probe_slot,
 	.quirks		= SDHCI_QUIRK_NO_ENDATTR_IN_NOPDESC,
 	.quirks2	= SDHCI_QUIRK2_PRESET_VALUE_BROKEN |
+			  SDHCI_QUIRK2_CAPS_BIT63_FOR_HS400 |
 			  SDHCI_QUIRK2_STOP_WITH_TC,
 };
 
@@ -655,14 +724,37 @@ static const struct sdhci_pci_fixes sdhci_rtsx = {
 	.probe_slot	= rtsx_probe_slot,
 };
 
+/*AMD chipset generation*/
+enum amd_chipset_gen {
+	AMD_CHIPSET_BEFORE_ML,
+	AMD_CHIPSET_CZ,
+	AMD_CHIPSET_NL,
+	AMD_CHIPSET_UNKNOWN,
+};
+
 static int amd_probe(struct sdhci_pci_chip *chip)
 {
 	struct pci_dev	*smbus_dev;
+	enum amd_chipset_gen gen;
 
 	smbus_dev = pci_get_device(PCI_VENDOR_ID_AMD,
 			PCI_DEVICE_ID_AMD_HUDSON2_SMBUS, NULL);
+	if (smbus_dev) {
+		gen = AMD_CHIPSET_BEFORE_ML;
+	} else {
+		smbus_dev = pci_get_device(PCI_VENDOR_ID_AMD,
+				PCI_DEVICE_ID_AMD_KERNCZ_SMBUS, NULL);
+		if (smbus_dev) {
+			if (smbus_dev->revision < 0x51)
+				gen = AMD_CHIPSET_CZ;
+			else
+				gen = AMD_CHIPSET_NL;
+		} else {
+			gen = AMD_CHIPSET_UNKNOWN;
+		}
+	}
 
-	if (smbus_dev && (smbus_dev->revision < 0x51)) {
+	if ((gen == AMD_CHIPSET_BEFORE_ML) || (gen == AMD_CHIPSET_CZ)) {
 		chip->quirks2 |= SDHCI_QUIRK2_CLEAR_TRANSFERMODE_REG_BEFORE_CMD;
 		chip->quirks2 |= SDHCI_QUIRK2_BROKEN_HS200;
 	}
@@ -1203,6 +1295,20 @@ static void sdhci_pci_hw_reset(struct sdhci_host *host)
 		slot->hw_reset(host);
 }
 
+static int sdhci_pci_select_drive_strength(struct sdhci_host *host,
+					   struct mmc_card *card,
+					   unsigned int max_dtr, int host_drv,
+					   int card_drv, int *drv_type)
+{
+	struct sdhci_pci_slot *slot = sdhci_priv(host);
+
+	if (!slot->select_drive_strength)
+		return 0;
+
+	return slot->select_drive_strength(host, card, max_dtr, host_drv,
+					   card_drv, drv_type);
+}
+
 static const struct sdhci_ops sdhci_pci_ops = {
 	.set_clock	= sdhci_set_clock,
 	.enable_dma	= sdhci_pci_enable_dma,
@@ -1210,6 +1316,7 @@ static const struct sdhci_ops sdhci_pci_ops = {
 	.reset		= sdhci_reset,
 	.set_uhs_signaling = sdhci_set_uhs_signaling,
 	.hw_reset		= sdhci_pci_hw_reset,
+	.select_drive_strength	= sdhci_pci_select_drive_strength,
 };
 
 /*****************************************************************************\
diff --git a/drivers/mmc/host/sdhci-pci.h b/drivers/mmc/host/sdhci-pci.h
index 1ec684d06d54..541f1cad5247 100644
--- a/drivers/mmc/host/sdhci-pci.h
+++ b/drivers/mmc/host/sdhci-pci.h
@@ -72,6 +72,10 @@ struct sdhci_pci_slot {
 	bool			cd_override_level;
 
 	void (*hw_reset)(struct sdhci_host *host);
+	int (*select_drive_strength)(struct sdhci_host *host,
+				     struct mmc_card *card,
+				     unsigned int max_dtr, int host_drv,
+				     int card_drv, int *drv_type);
 };
 
 struct sdhci_pci_chip {
diff --git a/drivers/mmc/host/sdhci-pxav2.c b/drivers/mmc/host/sdhci-pxav2.c
index f98008b5ea77..beffd8615489 100644
--- a/drivers/mmc/host/sdhci-pxav2.c
+++ b/drivers/mmc/host/sdhci-pxav2.c
@@ -252,9 +252,7 @@ static int sdhci_pxav2_remove(struct platform_device *pdev)
 static struct platform_driver sdhci_pxav2_driver = {
 	.driver		= {
 		.name	= "sdhci-pxav2",
-#ifdef CONFIG_OF
-		.of_match_table = sdhci_pxav2_of_match,
-#endif
+		.of_match_table = of_match_ptr(sdhci_pxav2_of_match),
 		.pm	= SDHCI_PLTFM_PMOPS,
 	},
 	.probe		= sdhci_pxav2_probe,
diff --git a/drivers/mmc/host/sdhci-pxav3.c b/drivers/mmc/host/sdhci-pxav3.c
index b5103a247bc1..9cd5fc62f130 100644
--- a/drivers/mmc/host/sdhci-pxav3.c
+++ b/drivers/mmc/host/sdhci-pxav3.c
@@ -457,12 +457,8 @@ static int sdhci_pxav3_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, host);
 
-	if (host->mmc->pm_caps & MMC_PM_KEEP_POWER) {
+	if (host->mmc->pm_caps & MMC_PM_WAKE_SDIO_IRQ)
 		device_init_wakeup(&pdev->dev, 1);
-		host->mmc->pm_flags |= MMC_PM_WAKE_SDIO_IRQ;
-	} else {
-		device_init_wakeup(&pdev->dev, 0);
-	}
 
 	pm_runtime_put_autosuspend(&pdev->dev);
 
@@ -578,9 +574,7 @@ static const struct dev_pm_ops sdhci_pxav3_pmops = {
 static struct platform_driver sdhci_pxav3_driver = {
 	.driver		= {
 		.name	= "sdhci-pxav3",
-#ifdef CONFIG_OF
-		.of_match_table = sdhci_pxav3_of_match,
-#endif
+		.of_match_table = of_match_ptr(sdhci_pxav3_of_match),
 		.pm	= SDHCI_PXAV3_PMOPS,
 	},
 	.probe		= sdhci_pxav3_probe,
diff --git a/drivers/mmc/host/sdhci-s3c.c b/drivers/mmc/host/sdhci-s3c.c
index c6d2dd7317c1..70c724bc6fc7 100644
--- a/drivers/mmc/host/sdhci-s3c.c
+++ b/drivers/mmc/host/sdhci-s3c.c
@@ -736,7 +736,7 @@ static struct sdhci_s3c_drv_data exynos4_sdhci_drv_data = {
 #define EXYNOS4_SDHCI_DRV_DATA ((kernel_ulong_t)NULL)
 #endif
 
-static struct platform_device_id sdhci_s3c_driver_ids[] = {
+static const struct platform_device_id sdhci_s3c_driver_ids[] = {
 	{
 		.name		= "s3c-sdhci",
 		.driver_data	= (kernel_ulong_t)NULL,
diff --git a/drivers/mmc/host/sdhci-sirf.c b/drivers/mmc/host/sdhci-sirf.c
index 32848eb7ad80..0110bae25b7e 100644
--- a/drivers/mmc/host/sdhci-sirf.c
+++ b/drivers/mmc/host/sdhci-sirf.c
@@ -17,7 +17,7 @@
 
 #define SDHCI_CLK_DELAY_SETTING 0x4C
 #define SDHCI_SIRF_8BITBUS BIT(3)
-#define SIRF_TUNING_COUNT 128
+#define SIRF_TUNING_COUNT 16384
 
 struct sdhci_sirf_priv {
 	int gpio_cd;
@@ -43,10 +43,43 @@ static void sdhci_sirf_set_bus_width(struct sdhci_host *host, int width)
 	sdhci_writeb(host, ctrl, SDHCI_HOST_CONTROL);
 }
 
+static u32 sdhci_sirf_readl_le(struct sdhci_host *host, int reg)
+{
+	u32 val = readl(host->ioaddr + reg);
+
+	if (unlikely((reg == SDHCI_CAPABILITIES_1) &&
+			(host->mmc->caps & MMC_CAP_UHS_SDR50))) {
+		/* fake CAP_1 register */
+		val = SDHCI_SUPPORT_SDR50 | SDHCI_USE_SDR50_TUNING;
+	}
+
+	if (unlikely(reg == SDHCI_SLOT_INT_STATUS)) {
+		u32 prss = val;
+		/* fake chips as V3.0 host conreoller */
+		prss &= ~(0xFF << 16);
+		val = prss | (SDHCI_SPEC_300 << 16);
+	}
+	return val;
+}
+
+static u16 sdhci_sirf_readw_le(struct sdhci_host *host, int reg)
+{
+	u16 ret = 0;
+
+	ret = readw(host->ioaddr + reg);
+
+	if (unlikely(reg == SDHCI_HOST_VERSION)) {
+		ret = readw(host->ioaddr + SDHCI_HOST_VERSION);
+		ret |= SDHCI_SPEC_300;
+	}
+
+	return ret;
+}
+
 static int sdhci_sirf_execute_tuning(struct sdhci_host *host, u32 opcode)
 {
 	int tuning_seq_cnt = 3;
-	u8 phase, tuned_phases[SIRF_TUNING_COUNT];
+	int phase;
 	u8 tuned_phase_cnt = 0;
 	int rc = 0, longest_range = 0;
 	int start = -1, end = 0, tuning_value = -1, range = 0;
@@ -58,6 +91,7 @@ static int sdhci_sirf_execute_tuning(struct sdhci_host *host, u32 opcode)
 
 retry:
 	phase = 0;
+	tuned_phase_cnt = 0;
 	do {
 		sdhci_writel(host,
 			clock_setting | phase,
@@ -65,7 +99,7 @@ retry:
 
 		if (!mmc_send_tuning(mmc)) {
 			/* Tuning is successful at this tuning point */
-			tuned_phases[tuned_phase_cnt++] = phase;
+			tuned_phase_cnt++;
 			dev_dbg(mmc_dev(mmc), "%s: Found good phase = %d\n",
 				 mmc_hostname(mmc), phase);
 			if (start == -1)
@@ -85,7 +119,7 @@ retry:
 			start = -1;
 			end = range = 0;
 		}
-	} while (++phase < ARRAY_SIZE(tuned_phases));
+	} while (++phase < SIRF_TUNING_COUNT);
 
 	if (tuned_phase_cnt && tuning_value > 0) {
 		/*
@@ -112,6 +146,8 @@ retry:
 }
 
 static struct sdhci_ops sdhci_sirf_ops = {
+	.read_l = sdhci_sirf_readl_le,
+	.read_w = sdhci_sirf_readw_le,
 	.platform_execute_tuning = sdhci_sirf_execute_tuning,
 	.set_clock = sdhci_set_clock,
 	.get_max_clock	= sdhci_pltfm_clk_get_max_clock,
diff --git a/drivers/mmc/host/sdhci-st.c b/drivers/mmc/host/sdhci-st.c
index 682f2bb0f4bf..969c2b0d57fd 100644
--- a/drivers/mmc/host/sdhci-st.c
+++ b/drivers/mmc/host/sdhci-st.c
@@ -509,4 +509,4 @@ module_platform_driver(sdhci_st_driver);
 MODULE_DESCRIPTION("SDHCI driver for STMicroelectronics SoCs");
 MODULE_AUTHOR("Giuseppe Cavallaro <peppe.cavallaro@st.com>");
 MODULE_LICENSE("GPL v2");
-MODULE_ALIAS("platform:st-sdhci");
+MODULE_ALIAS("platform:sdhci-st");
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index c80287a02735..bc1445238fb3 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -52,7 +52,6 @@ static void sdhci_finish_data(struct sdhci_host *);
 
 static void sdhci_finish_command(struct sdhci_host *);
 static int sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode);
-static void sdhci_tuning_timer(unsigned long data);
 static void sdhci_enable_preset_value(struct sdhci_host *host, bool enable);
 static int sdhci_pre_dma_transfer(struct sdhci_host *host,
 					struct mmc_data *data,
@@ -254,17 +253,6 @@ static void sdhci_init(struct sdhci_host *host, int soft)
 static void sdhci_reinit(struct sdhci_host *host)
 {
 	sdhci_init(host, 0);
-	/*
-	 * Retuning stuffs are affected by different cards inserted and only
-	 * applicable to UHS-I cards. So reset these fields to their initial
-	 * value when card is removed.
-	 */
-	if (host->flags & SDHCI_USING_RETUNING_TIMER) {
-		host->flags &= ~SDHCI_USING_RETUNING_TIMER;
-
-		del_timer_sync(&host->tuning_timer);
-		host->flags &= ~SDHCI_NEEDS_RETUNING;
-	}
 	sdhci_enable_card_detection(host);
 }
 
@@ -328,8 +316,7 @@ static void sdhci_read_block_pio(struct sdhci_host *host)
 	local_irq_save(flags);
 
 	while (blksize) {
-		if (!sg_miter_next(&host->sg_miter))
-			BUG();
+		BUG_ON(!sg_miter_next(&host->sg_miter));
 
 		len = min(host->sg_miter.length, blksize);
 
@@ -374,8 +361,7 @@ static void sdhci_write_block_pio(struct sdhci_host *host)
 	local_irq_save(flags);
 
 	while (blksize) {
-		if (!sg_miter_next(&host->sg_miter))
-			BUG();
+		BUG_ON(!sg_miter_next(&host->sg_miter));
 
 		len = min(host->sg_miter.length, blksize);
 
@@ -848,7 +834,7 @@ static void sdhci_prepare_data(struct sdhci_host *host, struct mmc_command *cmd)
 			int sg_cnt;
 
 			sg_cnt = sdhci_pre_dma_transfer(host, data, NULL);
-			if (sg_cnt == 0) {
+			if (sg_cnt <= 0) {
 				/*
 				 * This only happens when someone fed
 				 * us an invalid request.
@@ -1353,7 +1339,6 @@ static void sdhci_request(struct mmc_host *mmc, struct mmc_request *mrq)
 	struct sdhci_host *host;
 	int present;
 	unsigned long flags;
-	u32 tuning_opcode;
 
 	host = mmc_priv(mmc);
 
@@ -1387,39 +1372,6 @@ static void sdhci_request(struct mmc_host *mmc, struct mmc_request *mrq)
 		host->mrq->cmd->error = -ENOMEDIUM;
 		tasklet_schedule(&host->finish_tasklet);
 	} else {
-		u32 present_state;
-
-		present_state = sdhci_readl(host, SDHCI_PRESENT_STATE);
-		/*
-		 * Check if the re-tuning timer has already expired and there
-		 * is no on-going data transfer and DAT0 is not busy. If so,
-		 * we need to execute tuning procedure before sending command.
-		 */
-		if ((host->flags & SDHCI_NEEDS_RETUNING) &&
-		    !(present_state & (SDHCI_DOING_WRITE | SDHCI_DOING_READ)) &&
-		    (present_state & SDHCI_DATA_0_LVL_MASK)) {
-			if (mmc->card) {
-				/* eMMC uses cmd21 but sd and sdio use cmd19 */
-				tuning_opcode =
-					mmc->card->type == MMC_TYPE_MMC ?
-					MMC_SEND_TUNING_BLOCK_HS200 :
-					MMC_SEND_TUNING_BLOCK;
-
-				/* Here we need to set the host->mrq to NULL,
-				 * in case the pending finish_tasklet
-				 * finishes it incorrectly.
-				 */
-				host->mrq = NULL;
-
-				spin_unlock_irqrestore(&host->lock, flags);
-				sdhci_execute_tuning(mmc, tuning_opcode);
-				spin_lock_irqsave(&host->lock, flags);
-
-				/* Restore original mmc_request structure */
-				host->mrq = mrq;
-			}
-		}
-
 		if (mrq->sbc && !(host->flags & SDHCI_AUTO_CMD23))
 			sdhci_send_command(host, mrq->sbc);
 		else
@@ -1562,8 +1514,17 @@ static void sdhci_do_set_ios(struct sdhci_host *host, struct mmc_ios *ios)
 			ctrl_2 &= ~SDHCI_CTRL_DRV_TYPE_MASK;
 			if (ios->drv_type == MMC_SET_DRIVER_TYPE_A)
 				ctrl_2 |= SDHCI_CTRL_DRV_TYPE_A;
+			else if (ios->drv_type == MMC_SET_DRIVER_TYPE_B)
+				ctrl_2 |= SDHCI_CTRL_DRV_TYPE_B;
 			else if (ios->drv_type == MMC_SET_DRIVER_TYPE_C)
 				ctrl_2 |= SDHCI_CTRL_DRV_TYPE_C;
+			else if (ios->drv_type == MMC_SET_DRIVER_TYPE_D)
+				ctrl_2 |= SDHCI_CTRL_DRV_TYPE_D;
+			else {
+				pr_warn("%s: invalid driver type, default to "
+					"driver type B\n", mmc_hostname(mmc));
+				ctrl_2 |= SDHCI_CTRL_DRV_TYPE_B;
+			}
 
 			sdhci_writew(host, ctrl_2, SDHCI_HOST_CONTROL2);
 		} else {
@@ -2065,23 +2026,18 @@ static int sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode)
 	}
 
 out:
-	host->flags &= ~SDHCI_NEEDS_RETUNING;
-
 	if (tuning_count) {
-		host->flags |= SDHCI_USING_RETUNING_TIMER;
-		mod_timer(&host->tuning_timer, jiffies + tuning_count * HZ);
+		/*
+		 * In case tuning fails, host controllers which support
+		 * re-tuning can try tuning again at a later time, when the
+		 * re-tuning timer expires.  So for these controllers, we
+		 * return 0. Since there might be other controllers who do not
+		 * have this capability, we return error for them.
+		 */
+		err = 0;
 	}
 
-	/*
-	 * In case tuning fails, host controllers which support re-tuning can
-	 * try tuning again at a later time, when the re-tuning timer expires.
-	 * So for these controllers, we return 0. Since there might be other
-	 * controllers who do not have this capability, we return error for
-	 * them. SDHCI_USING_RETUNING_TIMER means the host is currently using
-	 * a retuning timer to do the retuning for the card.
-	 */
-	if (err && (host->flags & SDHCI_USING_RETUNING_TIMER))
-		err = 0;
+	host->mmc->retune_period = err ? 0 : tuning_count;
 
 	sdhci_writel(host, host->ier, SDHCI_INT_ENABLE);
 	sdhci_writel(host, host->ier, SDHCI_SIGNAL_ENABLE);
@@ -2092,6 +2048,18 @@ out_unlock:
 	return err;
 }
 
+static int sdhci_select_drive_strength(struct mmc_card *card,
+				       unsigned int max_dtr, int host_drv,
+				       int card_drv, int *drv_type)
+{
+	struct sdhci_host *host = mmc_priv(card->host);
+
+	if (!host->ops->select_drive_strength)
+		return 0;
+
+	return host->ops->select_drive_strength(host, card, max_dtr, host_drv,
+						card_drv, drv_type);
+}
 
 static void sdhci_enable_preset_value(struct sdhci_host *host, bool enable)
 {
@@ -2236,6 +2204,7 @@ static const struct mmc_host_ops sdhci_ops = {
 	.start_signal_voltage_switch	= sdhci_start_signal_voltage_switch,
 	.prepare_hs400_tuning		= sdhci_prepare_hs400_tuning,
 	.execute_tuning			= sdhci_execute_tuning,
+	.select_drive_strength		= sdhci_select_drive_strength,
 	.card_event			= sdhci_card_event,
 	.card_busy	= sdhci_card_busy,
 };
@@ -2337,20 +2306,6 @@ static void sdhci_timeout_timer(unsigned long data)
 	spin_unlock_irqrestore(&host->lock, flags);
 }
 
-static void sdhci_tuning_timer(unsigned long data)
-{
-	struct sdhci_host *host;
-	unsigned long flags;
-
-	host = (struct sdhci_host *)data;
-
-	spin_lock_irqsave(&host->lock, flags);
-
-	host->flags |= SDHCI_NEEDS_RETUNING;
-
-	spin_unlock_irqrestore(&host->lock, flags);
-}
-
 /*****************************************************************************\
  *                                                                           *
  * Interrupt handling                                                        *
@@ -2728,11 +2683,8 @@ int sdhci_suspend_host(struct sdhci_host *host)
 {
 	sdhci_disable_card_detection(host);
 
-	/* Disable tuning since we are suspending */
-	if (host->flags & SDHCI_USING_RETUNING_TIMER) {
-		del_timer_sync(&host->tuning_timer);
-		host->flags &= ~SDHCI_NEEDS_RETUNING;
-	}
+	mmc_retune_timer_stop(host->mmc);
+	mmc_retune_needed(host->mmc);
 
 	if (!device_may_wakeup(mmc_dev(host->mmc))) {
 		host->ier = 0;
@@ -2782,10 +2734,6 @@ int sdhci_resume_host(struct sdhci_host *host)
 
 	sdhci_enable_card_detection(host);
 
-	/* Set the re-tuning expiration flag */
-	if (host->flags & SDHCI_USING_RETUNING_TIMER)
-		host->flags |= SDHCI_NEEDS_RETUNING;
-
 	return ret;
 }
 
@@ -2822,11 +2770,8 @@ int sdhci_runtime_suspend_host(struct sdhci_host *host)
 {
 	unsigned long flags;
 
-	/* Disable tuning since we are suspending */
-	if (host->flags & SDHCI_USING_RETUNING_TIMER) {
-		del_timer_sync(&host->tuning_timer);
-		host->flags &= ~SDHCI_NEEDS_RETUNING;
-	}
+	mmc_retune_timer_stop(host->mmc);
+	mmc_retune_needed(host->mmc);
 
 	spin_lock_irqsave(&host->lock, flags);
 	host->ier &= SDHCI_INT_CARD_INT;
@@ -2869,10 +2814,6 @@ int sdhci_runtime_resume_host(struct sdhci_host *host)
 		spin_unlock_irqrestore(&host->lock, flags);
 	}
 
-	/* Set the re-tuning expiration flag */
-	if (host->flags & SDHCI_USING_RETUNING_TIMER)
-		host->flags |= SDHCI_NEEDS_RETUNING;
-
 	spin_lock_irqsave(&host->lock, flags);
 
 	host->runtime_suspended = false;
@@ -3315,13 +3256,14 @@ int sdhci_add_host(struct sdhci_host *host)
 				   SDHCI_MAX_CURRENT_MULTIPLIER;
 	}
 
-	/* If OCR set by external regulators, use it instead */
+	/* If OCR set by host, use it instead. */
+	if (host->ocr_mask)
+		ocr_avail = host->ocr_mask;
+
+	/* If OCR set by external regulators, give it highest prio. */
 	if (mmc->ocr_avail)
 		ocr_avail = mmc->ocr_avail;
 
-	if (host->ocr_mask)
-		ocr_avail &= host->ocr_mask;
-
 	mmc->ocr_avail = ocr_avail;
 	mmc->ocr_avail_sdio = ocr_avail;
 	if (host->ocr_avail_sdio)
@@ -3408,13 +3350,6 @@ int sdhci_add_host(struct sdhci_host *host)
 
 	init_waitqueue_head(&host->buf_ready_int);
 
-	if (host->version >= SDHCI_SPEC_300) {
-		/* Initialize re-tuning timer */
-		init_timer(&host->tuning_timer);
-		host->tuning_timer.data = (unsigned long)host;
-		host->tuning_timer.function = sdhci_tuning_timer;
-	}
-
 	sdhci_init(host, 0);
 
 	ret = request_threaded_irq(host->irq, sdhci_irq, sdhci_thread_irq,
diff --git a/drivers/mmc/host/sdhci.h b/drivers/mmc/host/sdhci.h
index e639b7f435e5..5521d29368e4 100644
--- a/drivers/mmc/host/sdhci.h
+++ b/drivers/mmc/host/sdhci.h
@@ -432,13 +432,11 @@ struct sdhci_host {
 #define SDHCI_REQ_USE_DMA	(1<<2)	/* Use DMA for this req. */
 #define SDHCI_DEVICE_DEAD	(1<<3)	/* Device unresponsive */
 #define SDHCI_SDR50_NEEDS_TUNING (1<<4)	/* SDR50 needs tuning */
-#define SDHCI_NEEDS_RETUNING	(1<<5)	/* Host needs retuning */
 #define SDHCI_AUTO_CMD12	(1<<6)	/* Auto CMD12 support */
 #define SDHCI_AUTO_CMD23	(1<<7)	/* Auto CMD23 support */
 #define SDHCI_PV_ENABLED	(1<<8)	/* Preset value enabled */
 #define SDHCI_SDIO_IRQ_ENABLED	(1<<9)	/* SDIO irq enabled */
 #define SDHCI_SDR104_NEEDS_TUNING (1<<10)	/* SDR104/HS200 needs tuning */
-#define SDHCI_USING_RETUNING_TIMER (1<<11)	/* Host is using a retuning timer for the card */
 #define SDHCI_USE_64_BIT_DMA	(1<<12)	/* Use 64-bit DMA */
 #define SDHCI_HS400_TUNING	(1<<13)	/* Tuning for HS400 */
 
@@ -504,7 +502,6 @@ struct sdhci_host {
 	unsigned int		tuning_count;	/* Timer count for re-tuning */
 	unsigned int		tuning_mode;	/* Re-tuning mode supported by host */
 #define SDHCI_TUNING_MODE_1	0
-	struct timer_list	tuning_timer;	/* Timer for tuning */
 
 	struct sdhci_host_next	next_data;
 	unsigned long private[0] ____cacheline_aligned;
@@ -541,6 +538,10 @@ struct sdhci_ops {
 	void	(*platform_init)(struct sdhci_host *host);
 	void    (*card_event)(struct sdhci_host *host);
 	void	(*voltage_switch)(struct sdhci_host *host);
+	int	(*select_drive_strength)(struct sdhci_host *host,
+					 struct mmc_card *card,
+					 unsigned int max_dtr, int host_drv,
+					 int card_drv, int *drv_type);
 };
 
 #ifdef CONFIG_MMC_SDHCI_IO_ACCESSORS
diff --git a/drivers/mmc/host/sdhci_f_sdh30.c b/drivers/mmc/host/sdhci_f_sdh30.c
index 2fe8b91481b3..983b8b32ef96 100644
--- a/drivers/mmc/host/sdhci_f_sdh30.c
+++ b/drivers/mmc/host/sdhci_f_sdh30.c
@@ -49,7 +49,7 @@ struct f_sdhost_priv {
 	struct device *dev;
 };
 
-void sdhci_f_sdh30_soft_voltage_switch(struct sdhci_host *host)
+static void sdhci_f_sdh30_soft_voltage_switch(struct sdhci_host *host)
 {
 	struct f_sdhost_priv *priv = sdhci_priv(host);
 	u32 ctrl = 0;
@@ -77,12 +77,12 @@ void sdhci_f_sdh30_soft_voltage_switch(struct sdhci_host *host)
 	sdhci_writel(host, ctrl, F_SDH30_TUNING_SETTING);
 }
 
-unsigned int sdhci_f_sdh30_get_min_clock(struct sdhci_host *host)
+static unsigned int sdhci_f_sdh30_get_min_clock(struct sdhci_host *host)
 {
 	return F_SDH30_MIN_CLOCK;
 }
 
-void sdhci_f_sdh30_reset(struct sdhci_host *host, u8 mask)
+static void sdhci_f_sdh30_reset(struct sdhci_host *host, u8 mask)
 {
 	if (sdhci_readw(host, SDHCI_CLOCK_CONTROL) == 0)
 		sdhci_writew(host, 0xBC01, SDHCI_CLOCK_CONTROL);
@@ -114,8 +114,7 @@ static int sdhci_f_sdh30_probe(struct platform_device *pdev)
 		return irq;
 	}
 
-	host = sdhci_alloc_host(dev, sizeof(struct sdhci_host) +
-						sizeof(struct f_sdhost_priv));
+	host = sdhci_alloc_host(dev, sizeof(struct f_sdhost_priv));
 	if (IS_ERR(host))
 		return PTR_ERR(host);
 
diff --git a/drivers/mmc/host/sh_mmcif.c b/drivers/mmc/host/sh_mmcif.c
index 7eff087cf515..5a1fdd405b1a 100644
--- a/drivers/mmc/host/sh_mmcif.c
+++ b/drivers/mmc/host/sh_mmcif.c
@@ -57,6 +57,7 @@
 #include <linux/mmc/slot-gpio.h>
 #include <linux/mod_devicetable.h>
 #include <linux/mutex.h>
+#include <linux/of_device.h>
 #include <linux/pagemap.h>
 #include <linux/platform_device.h>
 #include <linux/pm_qos.h>
@@ -205,14 +206,14 @@
 #define CLKDEV_MMC_DATA		20000000 /* 20MHz */
 #define CLKDEV_INIT		400000   /* 400 KHz */
 
-enum mmcif_state {
+enum sh_mmcif_state {
 	STATE_IDLE,
 	STATE_REQUEST,
 	STATE_IOS,
 	STATE_TIMEOUT,
 };
 
-enum mmcif_wait_for {
+enum sh_mmcif_wait_for {
 	MMCIF_WAIT_FOR_REQUEST,
 	MMCIF_WAIT_FOR_CMD,
 	MMCIF_WAIT_FOR_MREAD,
@@ -224,12 +225,14 @@ enum mmcif_wait_for {
 	MMCIF_WAIT_FOR_STOP,
 };
 
+/*
+ * difference for each SoC
+ */
 struct sh_mmcif_host {
 	struct mmc_host *mmc;
 	struct mmc_request *mrq;
 	struct platform_device *pd;
-	struct clk *hclk;
-	unsigned int clk;
+	struct clk *clk;
 	int bus_width;
 	unsigned char timing;
 	bool sd_error;
@@ -238,8 +241,8 @@ struct sh_mmcif_host {
 	void __iomem *addr;
 	u32 *pio_ptr;
 	spinlock_t lock;		/* protect sh_mmcif_host::state */
-	enum mmcif_state state;
-	enum mmcif_wait_for wait_for;
+	enum sh_mmcif_state state;
+	enum sh_mmcif_wait_for wait_for;
 	struct delayed_work timeout_work;
 	size_t blocksize;
 	int sg_idx;
@@ -249,6 +252,7 @@ struct sh_mmcif_host {
 	bool ccs_enable;		/* Command Completion Signal support */
 	bool clk_ctrl2_enable;
 	struct mutex thread_lock;
+	u32 clkdiv_map;         /* see CE_CLK_CTRL::CLKDIV */
 
 	/* DMA support */
 	struct dma_chan		*chan_rx;
@@ -257,6 +261,14 @@ struct sh_mmcif_host {
 	bool			dma_active;
 };
 
+static const struct of_device_id sh_mmcif_of_match[] = {
+	{ .compatible = "renesas,sh-mmcif" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, sh_mmcif_of_match);
+
+#define sh_mmcif_host_to_dev(host) (&host->pd->dev)
+
 static inline void sh_mmcif_bitset(struct sh_mmcif_host *host,
 					unsigned int reg, u32 val)
 {
@@ -269,15 +281,16 @@ static inline void sh_mmcif_bitclr(struct sh_mmcif_host *host,
 	writel(~val & readl(host->addr + reg), host->addr + reg);
 }
 
-static void mmcif_dma_complete(void *arg)
+static void sh_mmcif_dma_complete(void *arg)
 {
 	struct sh_mmcif_host *host = arg;
 	struct mmc_request *mrq = host->mrq;
+	struct device *dev = sh_mmcif_host_to_dev(host);
 
-	dev_dbg(&host->pd->dev, "Command completed\n");
+	dev_dbg(dev, "Command completed\n");
 
 	if (WARN(!mrq || !mrq->data, "%s: NULL data in DMA completion!\n",
-		 dev_name(&host->pd->dev)))
+		 dev_name(dev)))
 		return;
 
 	complete(&host->dma_complete);
@@ -289,6 +302,7 @@ static void sh_mmcif_start_dma_rx(struct sh_mmcif_host *host)
 	struct scatterlist *sg = data->sg;
 	struct dma_async_tx_descriptor *desc = NULL;
 	struct dma_chan *chan = host->chan_rx;
+	struct device *dev = sh_mmcif_host_to_dev(host);
 	dma_cookie_t cookie = -EINVAL;
 	int ret;
 
@@ -301,13 +315,13 @@ static void sh_mmcif_start_dma_rx(struct sh_mmcif_host *host)
 	}
 
 	if (desc) {
-		desc->callback = mmcif_dma_complete;
+		desc->callback = sh_mmcif_dma_complete;
 		desc->callback_param = host;
 		cookie = dmaengine_submit(desc);
 		sh_mmcif_bitset(host, MMCIF_CE_BUF_ACC, BUF_ACC_DMAREN);
 		dma_async_issue_pending(chan);
 	}
-	dev_dbg(&host->pd->dev, "%s(): mapped %d -> %d, cookie %d\n",
+	dev_dbg(dev, "%s(): mapped %d -> %d, cookie %d\n",
 		__func__, data->sg_len, ret, cookie);
 
 	if (!desc) {
@@ -323,12 +337,12 @@ static void sh_mmcif_start_dma_rx(struct sh_mmcif_host *host)
 			host->chan_tx = NULL;
 			dma_release_channel(chan);
 		}
-		dev_warn(&host->pd->dev,
+		dev_warn(dev,
 			 "DMA failed: %d, falling back to PIO\n", ret);
 		sh_mmcif_bitclr(host, MMCIF_CE_BUF_ACC, BUF_ACC_DMAREN | BUF_ACC_DMAWEN);
 	}
 
-	dev_dbg(&host->pd->dev, "%s(): desc %p, cookie %d, sg[%d]\n", __func__,
+	dev_dbg(dev, "%s(): desc %p, cookie %d, sg[%d]\n", __func__,
 		desc, cookie, data->sg_len);
 }
 
@@ -338,6 +352,7 @@ static void sh_mmcif_start_dma_tx(struct sh_mmcif_host *host)
 	struct scatterlist *sg = data->sg;
 	struct dma_async_tx_descriptor *desc = NULL;
 	struct dma_chan *chan = host->chan_tx;
+	struct device *dev = sh_mmcif_host_to_dev(host);
 	dma_cookie_t cookie = -EINVAL;
 	int ret;
 
@@ -350,13 +365,13 @@ static void sh_mmcif_start_dma_tx(struct sh_mmcif_host *host)
 	}
 
 	if (desc) {
-		desc->callback = mmcif_dma_complete;
+		desc->callback = sh_mmcif_dma_complete;
 		desc->callback_param = host;
 		cookie = dmaengine_submit(desc);
 		sh_mmcif_bitset(host, MMCIF_CE_BUF_ACC, BUF_ACC_DMAWEN);
 		dma_async_issue_pending(chan);
 	}
-	dev_dbg(&host->pd->dev, "%s(): mapped %d -> %d, cookie %d\n",
+	dev_dbg(dev, "%s(): mapped %d -> %d, cookie %d\n",
 		__func__, data->sg_len, ret, cookie);
 
 	if (!desc) {
@@ -372,12 +387,12 @@ static void sh_mmcif_start_dma_tx(struct sh_mmcif_host *host)
 			host->chan_rx = NULL;
 			dma_release_channel(chan);
 		}
-		dev_warn(&host->pd->dev,
+		dev_warn(dev,
 			 "DMA failed: %d, falling back to PIO\n", ret);
 		sh_mmcif_bitclr(host, MMCIF_CE_BUF_ACC, BUF_ACC_DMAREN | BUF_ACC_DMAWEN);
 	}
 
-	dev_dbg(&host->pd->dev, "%s(): desc %p, cookie %d\n", __func__,
+	dev_dbg(dev, "%s(): desc %p, cookie %d\n", __func__,
 		desc, cookie);
 }
 
@@ -390,6 +405,7 @@ sh_mmcif_request_dma_one(struct sh_mmcif_host *host,
 	struct dma_chan *chan;
 	void *slave_data = NULL;
 	struct resource *res;
+	struct device *dev = sh_mmcif_host_to_dev(host);
 	dma_cap_mask_t mask;
 	int ret;
 
@@ -402,10 +418,10 @@ sh_mmcif_request_dma_one(struct sh_mmcif_host *host,
 			(void *)pdata->slave_id_rx;
 
 	chan = dma_request_slave_channel_compat(mask, shdma_chan_filter,
-				slave_data, &host->pd->dev,
+				slave_data, dev,
 				direction == DMA_MEM_TO_DEV ? "tx" : "rx");
 
-	dev_dbg(&host->pd->dev, "%s: %s: got channel %p\n", __func__,
+	dev_dbg(dev, "%s: %s: got channel %p\n", __func__,
 		direction == DMA_MEM_TO_DEV ? "TX" : "RX", chan);
 
 	if (!chan)
@@ -435,12 +451,13 @@ sh_mmcif_request_dma_one(struct sh_mmcif_host *host,
 static void sh_mmcif_request_dma(struct sh_mmcif_host *host,
 				 struct sh_mmcif_plat_data *pdata)
 {
+	struct device *dev = sh_mmcif_host_to_dev(host);
 	host->dma_active = false;
 
 	if (pdata) {
 		if (pdata->slave_id_tx <= 0 || pdata->slave_id_rx <= 0)
 			return;
-	} else if (!host->pd->dev.of_node) {
+	} else if (!dev->of_node) {
 		return;
 	}
 
@@ -476,21 +493,59 @@ static void sh_mmcif_release_dma(struct sh_mmcif_host *host)
 
 static void sh_mmcif_clock_control(struct sh_mmcif_host *host, unsigned int clk)
 {
-	struct sh_mmcif_plat_data *p = host->pd->dev.platform_data;
+	struct device *dev = sh_mmcif_host_to_dev(host);
+	struct sh_mmcif_plat_data *p = dev->platform_data;
 	bool sup_pclk = p ? p->sup_pclk : false;
+	unsigned int current_clk = clk_get_rate(host->clk);
+	unsigned int clkdiv;
 
 	sh_mmcif_bitclr(host, MMCIF_CE_CLK_CTRL, CLK_ENABLE);
 	sh_mmcif_bitclr(host, MMCIF_CE_CLK_CTRL, CLK_CLEAR);
 
 	if (!clk)
 		return;
-	if (sup_pclk && clk == host->clk)
-		sh_mmcif_bitset(host, MMCIF_CE_CLK_CTRL, CLK_SUP_PCLK);
-	else
-		sh_mmcif_bitset(host, MMCIF_CE_CLK_CTRL, CLK_CLEAR &
-				((fls(DIV_ROUND_UP(host->clk,
-						   clk) - 1) - 1) << 16));
 
+	if (host->clkdiv_map) {
+		unsigned int freq, best_freq, myclk, div, diff_min, diff;
+		int i;
+
+		clkdiv = 0;
+		diff_min = ~0;
+		best_freq = 0;
+		for (i = 31; i >= 0; i--) {
+			if (!((1 << i) & host->clkdiv_map))
+				continue;
+
+			/*
+			 * clk = parent_freq / div
+			 * -> parent_freq = clk x div
+			 */
+
+			div = 1 << (i + 1);
+			freq = clk_round_rate(host->clk, clk * div);
+			myclk = freq / div;
+			diff = (myclk > clk) ? myclk - clk : clk - myclk;
+
+			if (diff <= diff_min) {
+				best_freq = freq;
+				clkdiv = i;
+				diff_min = diff;
+			}
+		}
+
+		dev_dbg(dev, "clk %u/%u (%u, 0x%x)\n",
+			(best_freq / (1 << (clkdiv + 1))), clk,
+			best_freq, clkdiv);
+
+		clk_set_rate(host->clk, best_freq);
+		clkdiv = clkdiv << 16;
+	} else if (sup_pclk && clk == current_clk) {
+		clkdiv = CLK_SUP_PCLK;
+	} else {
+		clkdiv = (fls(DIV_ROUND_UP(current_clk, clk) - 1) - 1) << 16;
+	}
+
+	sh_mmcif_bitset(host, MMCIF_CE_CLK_CTRL, CLK_CLEAR & clkdiv);
 	sh_mmcif_bitset(host, MMCIF_CE_CLK_CTRL, CLK_ENABLE);
 }
 
@@ -514,6 +569,7 @@ static void sh_mmcif_sync_reset(struct sh_mmcif_host *host)
 
 static int sh_mmcif_error_manage(struct sh_mmcif_host *host)
 {
+	struct device *dev = sh_mmcif_host_to_dev(host);
 	u32 state1, state2;
 	int ret, timeout;
 
@@ -521,8 +577,8 @@ static int sh_mmcif_error_manage(struct sh_mmcif_host *host)
 
 	state1 = sh_mmcif_readl(host->addr, MMCIF_CE_HOST_STS1);
 	state2 = sh_mmcif_readl(host->addr, MMCIF_CE_HOST_STS2);
-	dev_dbg(&host->pd->dev, "ERR HOST_STS1 = %08x\n", state1);
-	dev_dbg(&host->pd->dev, "ERR HOST_STS2 = %08x\n", state2);
+	dev_dbg(dev, "ERR HOST_STS1 = %08x\n", state1);
+	dev_dbg(dev, "ERR HOST_STS2 = %08x\n", state2);
 
 	if (state1 & STS1_CMDSEQ) {
 		sh_mmcif_bitset(host, MMCIF_CE_CMD_CTRL, CMD_CTRL_BREAK);
@@ -534,25 +590,25 @@ static int sh_mmcif_error_manage(struct sh_mmcif_host *host)
 			mdelay(1);
 		}
 		if (!timeout) {
-			dev_err(&host->pd->dev,
+			dev_err(dev,
 				"Forced end of command sequence timeout err\n");
 			return -EIO;
 		}
 		sh_mmcif_sync_reset(host);
-		dev_dbg(&host->pd->dev, "Forced end of command sequence\n");
+		dev_dbg(dev, "Forced end of command sequence\n");
 		return -EIO;
 	}
 
 	if (state2 & STS2_CRC_ERR) {
-		dev_err(&host->pd->dev, " CRC error: state %u, wait %u\n",
+		dev_err(dev, " CRC error: state %u, wait %u\n",
 			host->state, host->wait_for);
 		ret = -EIO;
 	} else if (state2 & STS2_TIMEOUT_ERR) {
-		dev_err(&host->pd->dev, " Timeout: state %u, wait %u\n",
+		dev_err(dev, " Timeout: state %u, wait %u\n",
 			host->state, host->wait_for);
 		ret = -ETIMEDOUT;
 	} else {
-		dev_dbg(&host->pd->dev, " End/Index error: state %u, wait %u\n",
+		dev_dbg(dev, " End/Index error: state %u, wait %u\n",
 			host->state, host->wait_for);
 		ret = -EIO;
 	}
@@ -593,13 +649,14 @@ static void sh_mmcif_single_read(struct sh_mmcif_host *host,
 
 static bool sh_mmcif_read_block(struct sh_mmcif_host *host)
 {
+	struct device *dev = sh_mmcif_host_to_dev(host);
 	struct mmc_data *data = host->mrq->data;
 	u32 *p = sg_virt(data->sg);
 	int i;
 
 	if (host->sd_error) {
 		data->error = sh_mmcif_error_manage(host);
-		dev_dbg(&host->pd->dev, "%s(): %d\n", __func__, data->error);
+		dev_dbg(dev, "%s(): %d\n", __func__, data->error);
 		return false;
 	}
 
@@ -634,13 +691,14 @@ static void sh_mmcif_multi_read(struct sh_mmcif_host *host,
 
 static bool sh_mmcif_mread_block(struct sh_mmcif_host *host)
 {
+	struct device *dev = sh_mmcif_host_to_dev(host);
 	struct mmc_data *data = host->mrq->data;
 	u32 *p = host->pio_ptr;
 	int i;
 
 	if (host->sd_error) {
 		data->error = sh_mmcif_error_manage(host);
-		dev_dbg(&host->pd->dev, "%s(): %d\n", __func__, data->error);
+		dev_dbg(dev, "%s(): %d\n", __func__, data->error);
 		return false;
 	}
 
@@ -671,13 +729,14 @@ static void sh_mmcif_single_write(struct sh_mmcif_host *host,
 
 static bool sh_mmcif_write_block(struct sh_mmcif_host *host)
 {
+	struct device *dev = sh_mmcif_host_to_dev(host);
 	struct mmc_data *data = host->mrq->data;
 	u32 *p = sg_virt(data->sg);
 	int i;
 
 	if (host->sd_error) {
 		data->error = sh_mmcif_error_manage(host);
-		dev_dbg(&host->pd->dev, "%s(): %d\n", __func__, data->error);
+		dev_dbg(dev, "%s(): %d\n", __func__, data->error);
 		return false;
 	}
 
@@ -712,13 +771,14 @@ static void sh_mmcif_multi_write(struct sh_mmcif_host *host,
 
 static bool sh_mmcif_mwrite_block(struct sh_mmcif_host *host)
 {
+	struct device *dev = sh_mmcif_host_to_dev(host);
 	struct mmc_data *data = host->mrq->data;
 	u32 *p = host->pio_ptr;
 	int i;
 
 	if (host->sd_error) {
 		data->error = sh_mmcif_error_manage(host);
-		dev_dbg(&host->pd->dev, "%s(): %d\n", __func__, data->error);
+		dev_dbg(dev, "%s(): %d\n", __func__, data->error);
 		return false;
 	}
 
@@ -756,6 +816,7 @@ static void sh_mmcif_get_cmd12response(struct sh_mmcif_host *host,
 static u32 sh_mmcif_set_cmd(struct sh_mmcif_host *host,
 			    struct mmc_request *mrq)
 {
+	struct device *dev = sh_mmcif_host_to_dev(host);
 	struct mmc_data *data = mrq->data;
 	struct mmc_command *cmd = mrq->cmd;
 	u32 opc = cmd->opcode;
@@ -775,7 +836,7 @@ static u32 sh_mmcif_set_cmd(struct sh_mmcif_host *host,
 		tmp |= CMD_SET_RTYP_17B;
 		break;
 	default:
-		dev_err(&host->pd->dev, "Unsupported response type.\n");
+		dev_err(dev, "Unsupported response type.\n");
 		break;
 	}
 	switch (opc) {
@@ -803,7 +864,7 @@ static u32 sh_mmcif_set_cmd(struct sh_mmcif_host *host,
 			tmp |= CMD_SET_DATW_8;
 			break;
 		default:
-			dev_err(&host->pd->dev, "Unsupported bus width.\n");
+			dev_err(dev, "Unsupported bus width.\n");
 			break;
 		}
 		switch (host->timing) {
@@ -846,6 +907,8 @@ static u32 sh_mmcif_set_cmd(struct sh_mmcif_host *host,
 static int sh_mmcif_data_trans(struct sh_mmcif_host *host,
 			       struct mmc_request *mrq, u32 opc)
 {
+	struct device *dev = sh_mmcif_host_to_dev(host);
+
 	switch (opc) {
 	case MMC_READ_MULTIPLE_BLOCK:
 		sh_mmcif_multi_read(host, mrq);
@@ -861,7 +924,7 @@ static int sh_mmcif_data_trans(struct sh_mmcif_host *host,
 		sh_mmcif_single_read(host, mrq);
 		return 0;
 	default:
-		dev_err(&host->pd->dev, "Unsupported CMD%d\n", opc);
+		dev_err(dev, "Unsupported CMD%d\n", opc);
 		return -EINVAL;
 	}
 }
@@ -918,6 +981,8 @@ static void sh_mmcif_start_cmd(struct sh_mmcif_host *host,
 static void sh_mmcif_stop_cmd(struct sh_mmcif_host *host,
 			      struct mmc_request *mrq)
 {
+	struct device *dev = sh_mmcif_host_to_dev(host);
+
 	switch (mrq->cmd->opcode) {
 	case MMC_READ_MULTIPLE_BLOCK:
 		sh_mmcif_bitset(host, MMCIF_CE_INT_MASK, MASK_MCMD12DRE);
@@ -926,7 +991,7 @@ static void sh_mmcif_stop_cmd(struct sh_mmcif_host *host,
 		sh_mmcif_bitset(host, MMCIF_CE_INT_MASK, MASK_MCMD12RBE);
 		break;
 	default:
-		dev_err(&host->pd->dev, "unsupported stop cmd\n");
+		dev_err(dev, "unsupported stop cmd\n");
 		mrq->stop->error = sh_mmcif_error_manage(host);
 		return;
 	}
@@ -937,11 +1002,13 @@ static void sh_mmcif_stop_cmd(struct sh_mmcif_host *host,
 static void sh_mmcif_request(struct mmc_host *mmc, struct mmc_request *mrq)
 {
 	struct sh_mmcif_host *host = mmc_priv(mmc);
+	struct device *dev = sh_mmcif_host_to_dev(host);
 	unsigned long flags;
 
 	spin_lock_irqsave(&host->lock, flags);
 	if (host->state != STATE_IDLE) {
-		dev_dbg(&host->pd->dev, "%s() rejected, state %u\n", __func__, host->state);
+		dev_dbg(dev, "%s() rejected, state %u\n",
+			__func__, host->state);
 		spin_unlock_irqrestore(&host->lock, flags);
 		mrq->cmd->error = -EAGAIN;
 		mmc_request_done(mmc, mrq);
@@ -972,17 +1039,37 @@ static void sh_mmcif_request(struct mmc_host *mmc, struct mmc_request *mrq)
 	sh_mmcif_start_cmd(host, mrq);
 }
 
-static int sh_mmcif_clk_update(struct sh_mmcif_host *host)
+static void sh_mmcif_clk_setup(struct sh_mmcif_host *host)
 {
-	int ret = clk_prepare_enable(host->hclk);
+	struct device *dev = sh_mmcif_host_to_dev(host);
+
+	if (host->mmc->f_max) {
+		unsigned int f_max, f_min = 0, f_min_old;
+
+		f_max = host->mmc->f_max;
+		for (f_min_old = f_max; f_min_old > 2;) {
+			f_min = clk_round_rate(host->clk, f_min_old / 2);
+			if (f_min == f_min_old)
+				break;
+			f_min_old = f_min;
+		}
+
+		/*
+		 * This driver assumes this SoC is R-Car Gen2 or later
+		 */
+		host->clkdiv_map = 0x3ff;
+
+		host->mmc->f_max = f_max / (1 << ffs(host->clkdiv_map));
+		host->mmc->f_min = f_min / (1 << fls(host->clkdiv_map));
+	} else {
+		unsigned int clk = clk_get_rate(host->clk);
 
-	if (!ret) {
-		host->clk = clk_get_rate(host->hclk);
-		host->mmc->f_max = host->clk / 2;
-		host->mmc->f_min = host->clk / 512;
+		host->mmc->f_max = clk / 2;
+		host->mmc->f_min = clk / 512;
 	}
 
-	return ret;
+	dev_dbg(dev, "clk max/min = %d/%d\n",
+		host->mmc->f_max, host->mmc->f_min);
 }
 
 static void sh_mmcif_set_power(struct sh_mmcif_host *host, struct mmc_ios *ios)
@@ -998,11 +1085,13 @@ static void sh_mmcif_set_power(struct sh_mmcif_host *host, struct mmc_ios *ios)
 static void sh_mmcif_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 {
 	struct sh_mmcif_host *host = mmc_priv(mmc);
+	struct device *dev = sh_mmcif_host_to_dev(host);
 	unsigned long flags;
 
 	spin_lock_irqsave(&host->lock, flags);
 	if (host->state != STATE_IDLE) {
-		dev_dbg(&host->pd->dev, "%s() rejected, state %u\n", __func__, host->state);
+		dev_dbg(dev, "%s() rejected, state %u\n",
+			__func__, host->state);
 		spin_unlock_irqrestore(&host->lock, flags);
 		return;
 	}
@@ -1013,7 +1102,7 @@ static void sh_mmcif_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 	if (ios->power_mode == MMC_POWER_UP) {
 		if (!host->card_present) {
 			/* See if we also get DMA */
-			sh_mmcif_request_dma(host, host->pd->dev.platform_data);
+			sh_mmcif_request_dma(host, dev->platform_data);
 			host->card_present = true;
 		}
 		sh_mmcif_set_power(host, ios);
@@ -1027,8 +1116,8 @@ static void sh_mmcif_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 			}
 		}
 		if (host->power) {
-			pm_runtime_put_sync(&host->pd->dev);
-			clk_disable_unprepare(host->hclk);
+			pm_runtime_put_sync(dev);
+			clk_disable_unprepare(host->clk);
 			host->power = false;
 			if (ios->power_mode == MMC_POWER_OFF)
 				sh_mmcif_set_power(host, ios);
@@ -1039,8 +1128,9 @@ static void sh_mmcif_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 
 	if (ios->clock) {
 		if (!host->power) {
-			sh_mmcif_clk_update(host);
-			pm_runtime_get_sync(&host->pd->dev);
+			clk_prepare_enable(host->clk);
+
+			pm_runtime_get_sync(dev);
 			host->power = true;
 			sh_mmcif_sync_reset(host);
 		}
@@ -1055,7 +1145,8 @@ static void sh_mmcif_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 static int sh_mmcif_get_cd(struct mmc_host *mmc)
 {
 	struct sh_mmcif_host *host = mmc_priv(mmc);
-	struct sh_mmcif_plat_data *p = host->pd->dev.platform_data;
+	struct device *dev = sh_mmcif_host_to_dev(host);
+	struct sh_mmcif_plat_data *p = dev->platform_data;
 	int ret = mmc_gpio_get_cd(mmc);
 
 	if (ret >= 0)
@@ -1077,6 +1168,7 @@ static bool sh_mmcif_end_cmd(struct sh_mmcif_host *host)
 {
 	struct mmc_command *cmd = host->mrq->cmd;
 	struct mmc_data *data = host->mrq->data;
+	struct device *dev = sh_mmcif_host_to_dev(host);
 	long time;
 
 	if (host->sd_error) {
@@ -1090,7 +1182,7 @@ static bool sh_mmcif_end_cmd(struct sh_mmcif_host *host)
 			cmd->error = sh_mmcif_error_manage(host);
 			break;
 		}
-		dev_dbg(&host->pd->dev, "CMD%d error %d\n",
+		dev_dbg(dev, "CMD%d error %d\n",
 			cmd->opcode, cmd->error);
 		host->sd_error = false;
 		return false;
@@ -1170,6 +1262,7 @@ static irqreturn_t sh_mmcif_irqt(int irq, void *dev_id)
 {
 	struct sh_mmcif_host *host = dev_id;
 	struct mmc_request *mrq;
+	struct device *dev = sh_mmcif_host_to_dev(host);
 	bool wait = false;
 	unsigned long flags;
 	int wait_work;
@@ -1184,7 +1277,7 @@ static irqreturn_t sh_mmcif_irqt(int irq, void *dev_id)
 
 	mrq = host->mrq;
 	if (!mrq) {
-		dev_dbg(&host->pd->dev, "IRQ thread state %u, wait %u: NULL mrq!\n",
+		dev_dbg(dev, "IRQ thread state %u, wait %u: NULL mrq!\n",
 			host->state, host->wait_for);
 		mutex_unlock(&host->thread_lock);
 		return IRQ_HANDLED;
@@ -1222,7 +1315,7 @@ static irqreturn_t sh_mmcif_irqt(int irq, void *dev_id)
 	case MMCIF_WAIT_FOR_STOP:
 		if (host->sd_error) {
 			mrq->stop->error = sh_mmcif_error_manage(host);
-			dev_dbg(&host->pd->dev, "%s(): %d\n", __func__, mrq->stop->error);
+			dev_dbg(dev, "%s(): %d\n", __func__, mrq->stop->error);
 			break;
 		}
 		sh_mmcif_get_cmd12response(host, mrq->stop);
@@ -1232,7 +1325,7 @@ static irqreturn_t sh_mmcif_irqt(int irq, void *dev_id)
 	case MMCIF_WAIT_FOR_WRITE_END:
 		if (host->sd_error) {
 			mrq->data->error = sh_mmcif_error_manage(host);
-			dev_dbg(&host->pd->dev, "%s(): %d\n", __func__, mrq->data->error);
+			dev_dbg(dev, "%s(): %d\n", __func__, mrq->data->error);
 		}
 		break;
 	default:
@@ -1275,6 +1368,7 @@ static irqreturn_t sh_mmcif_irqt(int irq, void *dev_id)
 static irqreturn_t sh_mmcif_intr(int irq, void *dev_id)
 {
 	struct sh_mmcif_host *host = dev_id;
+	struct device *dev = sh_mmcif_host_to_dev(host);
 	u32 state, mask;
 
 	state = sh_mmcif_readl(host->addr, MMCIF_CE_INT);
@@ -1286,32 +1380,33 @@ static irqreturn_t sh_mmcif_intr(int irq, void *dev_id)
 	sh_mmcif_bitclr(host, MMCIF_CE_INT_MASK, state & MASK_CLEAN);
 
 	if (state & ~MASK_CLEAN)
-		dev_dbg(&host->pd->dev, "IRQ state = 0x%08x incompletely cleared\n",
+		dev_dbg(dev, "IRQ state = 0x%08x incompletely cleared\n",
 			state);
 
 	if (state & INT_ERR_STS || state & ~INT_ALL) {
 		host->sd_error = true;
-		dev_dbg(&host->pd->dev, "int err state = 0x%08x\n", state);
+		dev_dbg(dev, "int err state = 0x%08x\n", state);
 	}
 	if (state & ~(INT_CMD12RBE | INT_CMD12CRE)) {
 		if (!host->mrq)
-			dev_dbg(&host->pd->dev, "NULL IRQ state = 0x%08x\n", state);
+			dev_dbg(dev, "NULL IRQ state = 0x%08x\n", state);
 		if (!host->dma_active)
 			return IRQ_WAKE_THREAD;
 		else if (host->sd_error)
-			mmcif_dma_complete(host);
+			sh_mmcif_dma_complete(host);
 	} else {
-		dev_dbg(&host->pd->dev, "Unexpected IRQ 0x%x\n", state);
+		dev_dbg(dev, "Unexpected IRQ 0x%x\n", state);
 	}
 
 	return IRQ_HANDLED;
 }
 
-static void mmcif_timeout_work(struct work_struct *work)
+static void sh_mmcif_timeout_work(struct work_struct *work)
 {
 	struct delayed_work *d = container_of(work, struct delayed_work, work);
 	struct sh_mmcif_host *host = container_of(d, struct sh_mmcif_host, timeout_work);
 	struct mmc_request *mrq = host->mrq;
+	struct device *dev = sh_mmcif_host_to_dev(host);
 	unsigned long flags;
 
 	if (host->dying)
@@ -1324,7 +1419,7 @@ static void mmcif_timeout_work(struct work_struct *work)
 		return;
 	}
 
-	dev_err(&host->pd->dev, "Timeout waiting for %u on CMD%u\n",
+	dev_err(dev, "Timeout waiting for %u on CMD%u\n",
 		host->wait_for, mrq->cmd->opcode);
 
 	host->state = STATE_TIMEOUT;
@@ -1361,7 +1456,8 @@ static void mmcif_timeout_work(struct work_struct *work)
 
 static void sh_mmcif_init_ocr(struct sh_mmcif_host *host)
 {
-	struct sh_mmcif_plat_data *pd = host->pd->dev.platform_data;
+	struct device *dev = sh_mmcif_host_to_dev(host);
+	struct sh_mmcif_plat_data *pd = dev->platform_data;
 	struct mmc_host *mmc = host->mmc;
 
 	mmc_regulator_get_supply(mmc);
@@ -1380,7 +1476,8 @@ static int sh_mmcif_probe(struct platform_device *pdev)
 	int ret = 0, irq[2];
 	struct mmc_host *mmc;
 	struct sh_mmcif_host *host;
-	struct sh_mmcif_plat_data *pd = pdev->dev.platform_data;
+	struct device *dev = &pdev->dev;
+	struct sh_mmcif_plat_data *pd = dev->platform_data;
 	struct resource *res;
 	void __iomem *reg;
 	const char *name;
@@ -1388,16 +1485,16 @@ static int sh_mmcif_probe(struct platform_device *pdev)
 	irq[0] = platform_get_irq(pdev, 0);
 	irq[1] = platform_get_irq(pdev, 1);
 	if (irq[0] < 0) {
-		dev_err(&pdev->dev, "Get irq error\n");
+		dev_err(dev, "Get irq error\n");
 		return -ENXIO;
 	}
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	reg = devm_ioremap_resource(&pdev->dev, res);
+	reg = devm_ioremap_resource(dev, res);
 	if (IS_ERR(reg))
 		return PTR_ERR(reg);
 
-	mmc = mmc_alloc_host(sizeof(struct sh_mmcif_host), &pdev->dev);
+	mmc = mmc_alloc_host(sizeof(struct sh_mmcif_host), dev);
 	if (!mmc)
 		return -ENOMEM;
 
@@ -1430,41 +1527,44 @@ static int sh_mmcif_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, host);
 
-	pm_runtime_enable(&pdev->dev);
+	pm_runtime_enable(dev);
 	host->power = false;
 
-	host->hclk = devm_clk_get(&pdev->dev, NULL);
-	if (IS_ERR(host->hclk)) {
-		ret = PTR_ERR(host->hclk);
-		dev_err(&pdev->dev, "cannot get clock: %d\n", ret);
+	host->clk = devm_clk_get(dev, NULL);
+	if (IS_ERR(host->clk)) {
+		ret = PTR_ERR(host->clk);
+		dev_err(dev, "cannot get clock: %d\n", ret);
 		goto err_pm;
 	}
-	ret = sh_mmcif_clk_update(host);
+
+	ret = clk_prepare_enable(host->clk);
 	if (ret < 0)
 		goto err_pm;
 
-	ret = pm_runtime_resume(&pdev->dev);
+	sh_mmcif_clk_setup(host);
+
+	ret = pm_runtime_resume(dev);
 	if (ret < 0)
 		goto err_clk;
 
-	INIT_DELAYED_WORK(&host->timeout_work, mmcif_timeout_work);
+	INIT_DELAYED_WORK(&host->timeout_work, sh_mmcif_timeout_work);
 
 	sh_mmcif_sync_reset(host);
 	sh_mmcif_writel(host->addr, MMCIF_CE_INT_MASK, MASK_ALL);
 
-	name = irq[1] < 0 ? dev_name(&pdev->dev) : "sh_mmc:error";
-	ret = devm_request_threaded_irq(&pdev->dev, irq[0], sh_mmcif_intr,
+	name = irq[1] < 0 ? dev_name(dev) : "sh_mmc:error";
+	ret = devm_request_threaded_irq(dev, irq[0], sh_mmcif_intr,
 					sh_mmcif_irqt, 0, name, host);
 	if (ret) {
-		dev_err(&pdev->dev, "request_irq error (%s)\n", name);
+		dev_err(dev, "request_irq error (%s)\n", name);
 		goto err_clk;
 	}
 	if (irq[1] >= 0) {
-		ret = devm_request_threaded_irq(&pdev->dev, irq[1],
+		ret = devm_request_threaded_irq(dev, irq[1],
 						sh_mmcif_intr, sh_mmcif_irqt,
 						0, "sh_mmc:int", host);
 		if (ret) {
-			dev_err(&pdev->dev, "request_irq error (sh_mmc:int)\n");
+			dev_err(dev, "request_irq error (sh_mmc:int)\n");
 			goto err_clk;
 		}
 	}
@@ -1481,19 +1581,19 @@ static int sh_mmcif_probe(struct platform_device *pdev)
 	if (ret < 0)
 		goto err_clk;
 
-	dev_pm_qos_expose_latency_limit(&pdev->dev, 100);
+	dev_pm_qos_expose_latency_limit(dev, 100);
 
-	dev_info(&pdev->dev, "Chip version 0x%04x, clock rate %luMHz\n",
+	dev_info(dev, "Chip version 0x%04x, clock rate %luMHz\n",
 		 sh_mmcif_readl(host->addr, MMCIF_CE_VERSION) & 0xffff,
-		 clk_get_rate(host->hclk) / 1000000UL);
+		 clk_get_rate(host->clk) / 1000000UL);
 
-	clk_disable_unprepare(host->hclk);
+	clk_disable_unprepare(host->clk);
 	return ret;
 
 err_clk:
-	clk_disable_unprepare(host->hclk);
+	clk_disable_unprepare(host->clk);
 err_pm:
-	pm_runtime_disable(&pdev->dev);
+	pm_runtime_disable(dev);
 err_host:
 	mmc_free_host(mmc);
 	return ret;
@@ -1504,7 +1604,7 @@ static int sh_mmcif_remove(struct platform_device *pdev)
 	struct sh_mmcif_host *host = platform_get_drvdata(pdev);
 
 	host->dying = true;
-	clk_prepare_enable(host->hclk);
+	clk_prepare_enable(host->clk);
 	pm_runtime_get_sync(&pdev->dev);
 
 	dev_pm_qos_hide_latency_limit(&pdev->dev);
@@ -1519,7 +1619,7 @@ static int sh_mmcif_remove(struct platform_device *pdev)
 	 */
 	cancel_delayed_work_sync(&host->timeout_work);
 
-	clk_disable_unprepare(host->hclk);
+	clk_disable_unprepare(host->clk);
 	mmc_free_host(host->mmc);
 	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
@@ -1543,12 +1643,6 @@ static int sh_mmcif_resume(struct device *dev)
 }
 #endif
 
-static const struct of_device_id mmcif_of_match[] = {
-	{ .compatible = "renesas,sh-mmcif" },
-	{ }
-};
-MODULE_DEVICE_TABLE(of, mmcif_of_match);
-
 static const struct dev_pm_ops sh_mmcif_dev_pm_ops = {
 	SET_SYSTEM_SLEEP_PM_OPS(sh_mmcif_suspend, sh_mmcif_resume)
 };
@@ -1559,7 +1653,7 @@ static struct platform_driver sh_mmcif_driver = {
 	.driver		= {
 		.name	= DRIVER_NAME,
 		.pm	= &sh_mmcif_dev_pm_ops,
-		.of_match_table = mmcif_of_match,
+		.of_match_table = sh_mmcif_of_match,
 	},
 };
 
diff --git a/drivers/mmc/host/tmio_mmc.c b/drivers/mmc/host/tmio_mmc.c
index f746df493892..e897e7fc3b14 100644
--- a/drivers/mmc/host/tmio_mmc.c
+++ b/drivers/mmc/host/tmio_mmc.c
@@ -85,8 +85,10 @@ static int tmio_mmc_probe(struct platform_device *pdev)
 	}
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res)
-		return -EINVAL;
+	if (!res) {
+		ret = -EINVAL;
+		goto cell_disable;
+	}
 
 	pdata->flags |= TMIO_MMC_HAVE_HIGH_REG;
 
@@ -101,7 +103,8 @@ static int tmio_mmc_probe(struct platform_device *pdev)
 	if (ret)
 		goto host_free;
 
-	ret = request_irq(irq, tmio_mmc_irq, IRQF_TRIGGER_FALLING,
+	ret = devm_request_irq(&pdev->dev, irq, tmio_mmc_irq,
+				IRQF_TRIGGER_FALLING,
 				dev_name(&pdev->dev), host);
 	if (ret)
 		goto host_remove;
@@ -129,7 +132,6 @@ static int tmio_mmc_remove(struct platform_device *pdev)
 
 	if (mmc) {
 		struct tmio_mmc_host *host = mmc_priv(mmc);
-		free_irq(platform_get_irq(pdev, 0), host);
 		tmio_mmc_host_remove(host);
 		if (cell->disable)
 			cell->disable(pdev);
diff --git a/drivers/mmc/host/tmio_mmc_pio.c b/drivers/mmc/host/tmio_mmc_pio.c
index dba7e1c19dd7..e3dcf31a8bd6 100644
--- a/drivers/mmc/host/tmio_mmc_pio.c
+++ b/drivers/mmc/host/tmio_mmc_pio.c
@@ -1108,7 +1108,8 @@ int tmio_mmc_host_probe(struct tmio_mmc_host *_host,
 	if (ret < 0)
 		goto host_free;
 
-	_host->ctl = ioremap(res_ctl->start, resource_size(res_ctl));
+	_host->ctl = devm_ioremap(&pdev->dev,
+				  res_ctl->start, resource_size(res_ctl));
 	if (!_host->ctl) {
 		ret = -ENOMEM;
 		goto host_free;
@@ -1230,8 +1231,6 @@ void tmio_mmc_host_remove(struct tmio_mmc_host *host)
 
 	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
-
-	iounmap(host->ctl);
 }
 EXPORT_SYMBOL(tmio_mmc_host_remove);
 
diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index 4b00545a3ace..65944dd8bf6b 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -1304,7 +1304,7 @@ static unsigned int efx_wanted_parallelism(struct efx_nic *efx)
 			if (!cpumask_test_cpu(cpu, thread_mask)) {
 				++count;
 				cpumask_or(thread_mask, thread_mask,
-					   topology_thread_cpumask(cpu));
+					   topology_sibling_cpumask(cpu));
 			}
 		}
 
diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c
index 3dc1f68b322d..6ce973187225 100644
--- a/drivers/net/ethernet/sun/cassini.c
+++ b/drivers/net/ethernet/sun/cassini.c
@@ -3058,7 +3058,6 @@ static void cas_init_mac(struct cas *cp)
 	/* setup core arbitration weight register */
 	writel(CAWR_RR_DIS, cp->regs + REG_CAWR);
 
-	/* XXX Use pci_dma_burst_advice() */
 #if !defined(CONFIG_SPARC64) && !defined(CONFIG_ALPHA)
 	/* set the infinite burst register for chips that don't have
 	 * pci issues.
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index ea091bc5ff09..1e09243d5449 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -28,6 +28,7 @@
 #include <linux/slab.h>
 #include <linux/netdevice.h>
 #include <linux/if_ether.h>
+#include <linux/vmalloc.h>
 #include <asm/sync_bitops.h>
 
 #include "hyperv_net.h"
diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index 9118cea91882..35a482d526d9 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -27,6 +27,7 @@
 #include <linux/netdevice.h>
 #include <linux/if_vlan.h>
 #include <linux/nls.h>
+#include <linux/vmalloc.h>
 
 #include "hyperv_net.h"
 
diff --git a/drivers/net/phy/mdio-mux-gpio.c b/drivers/net/phy/mdio-mux-gpio.c
index 66edd99bc302..7ddb1ab70891 100644
--- a/drivers/net/phy/mdio-mux-gpio.c
+++ b/drivers/net/phy/mdio-mux-gpio.c
@@ -35,7 +35,8 @@ static int mdio_mux_gpio_switch_fn(int current_child, int desired_child,
 	for (n = 0; n < s->gpios->ndescs; n++)
 		values[n] = (desired_child >> n) & 1;
 
-	gpiod_set_array_cansleep(s->gpios->ndescs, s->gpios->desc, values);
+	gpiod_set_array_value_cansleep(s->gpios->ndescs, s->gpios->desc,
+				       values);
 
 	return 0;
 }
diff --git a/drivers/ntb/ntb_hw.c b/drivers/ntb/ntb_hw.c
index 15f9b7c9e4d3..3f6738612f45 100644
--- a/drivers/ntb/ntb_hw.c
+++ b/drivers/ntb/ntb_hw.c
@@ -1313,8 +1313,6 @@ static int ntb_setup_intx(struct ntb_device *ndev)
 	struct pci_dev *pdev = ndev->pdev;
 	int rc;
 
-	pci_msi_off(pdev);
-
 	/* Verify intx is enabled */
 	pci_intx(pdev, 1);
 
diff --git a/drivers/of/address.c b/drivers/of/address.c
index 78a7dcbec7d8..6906a3f61bd8 100644
--- a/drivers/of/address.c
+++ b/drivers/of/address.c
@@ -765,7 +765,7 @@ unsigned long __weak pci_address_to_pio(phys_addr_t address)
 	spin_lock(&io_range_lock);
 	list_for_each_entry(res, &io_range_list, list) {
 		if (address >= res->start && address < res->start + res->size) {
-			addr = res->start - address + offset;
+			addr = address - res->start + offset;
 			break;
 		}
 		offset += res->size;
diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig
index 7a8f1c5e65af..73de4efcbe6e 100644
--- a/drivers/pci/Kconfig
+++ b/drivers/pci/Kconfig
@@ -1,6 +1,10 @@
 #
 # PCI configuration
 #
+config PCI_BUS_ADDR_T_64BIT
+	def_bool y if (ARCH_DMA_ADDR_T_64BIT || 64BIT)
+	depends on PCI
+
 config PCI_MSI
 	bool "Message Signaled Interrupts (MSI and MSI-X)"
 	depends on PCI
diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c
index 90fa3a78fb7c..6fbd3f2b5992 100644
--- a/drivers/pci/bus.c
+++ b/drivers/pci/bus.c
@@ -92,11 +92,11 @@ void pci_bus_remove_resources(struct pci_bus *bus)
 }
 
 static struct pci_bus_region pci_32_bit = {0, 0xffffffffULL};
-#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
+#ifdef CONFIG_PCI_BUS_ADDR_T_64BIT
 static struct pci_bus_region pci_64_bit = {0,
-				(dma_addr_t) 0xffffffffffffffffULL};
-static struct pci_bus_region pci_high = {(dma_addr_t) 0x100000000ULL,
-				(dma_addr_t) 0xffffffffffffffffULL};
+				(pci_bus_addr_t) 0xffffffffffffffffULL};
+static struct pci_bus_region pci_high = {(pci_bus_addr_t) 0x100000000ULL,
+				(pci_bus_addr_t) 0xffffffffffffffffULL};
 #endif
 
 /*
@@ -200,7 +200,7 @@ int pci_bus_alloc_resource(struct pci_bus *bus, struct resource *res,
 					  resource_size_t),
 		void *alignf_data)
 {
-#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
+#ifdef CONFIG_PCI_BUS_ADDR_T_64BIT
 	int rc;
 
 	if (res->flags & IORESOURCE_MEM_64) {
diff --git a/drivers/pci/host/Kconfig b/drivers/pci/host/Kconfig
index 1dfb567b3522..c132bddc03f3 100644
--- a/drivers/pci/host/Kconfig
+++ b/drivers/pci/host/Kconfig
@@ -89,11 +89,20 @@ config PCI_XGENE
 	depends on ARCH_XGENE
 	depends on OF
 	select PCIEPORTBUS
+	select PCI_MSI_IRQ_DOMAIN if PCI_MSI
 	help
 	  Say Y here if you want internal PCI support on APM X-Gene SoC.
 	  There are 5 internal PCIe ports available. Each port is GEN3 capable
 	  and have varied lanes from x1 to x8.
 
+config PCI_XGENE_MSI
+	bool "X-Gene v1 PCIe MSI feature"
+	depends on PCI_XGENE && PCI_MSI
+	default y
+	help
+	  Say Y here if you want PCIe MSI support for the APM X-Gene v1 SoC.
+	  This MSI driver supports 5 PCIe ports on the APM X-Gene v1 SoC.
+
 config PCI_LAYERSCAPE
 	bool "Freescale Layerscape PCIe controller"
 	depends on OF && ARM
@@ -125,4 +134,15 @@ config PCIE_IPROC_PLATFORM
 	  Say Y here if you want to use the Broadcom iProc PCIe controller
 	  through the generic platform bus interface
 
+config PCIE_IPROC_BCMA
+	bool "Broadcom iProc PCIe BCMA bus driver"
+	depends on ARCH_BCM_IPROC || (ARM && COMPILE_TEST)
+	select PCIE_IPROC
+	select BCMA
+	select PCI_DOMAINS
+	default ARCH_BCM_5301X
+	help
+	  Say Y here if you want to use the Broadcom iProc PCIe controller
+	  through the BCMA bus interface
+
 endmenu
diff --git a/drivers/pci/host/Makefile b/drivers/pci/host/Makefile
index f733b4e27642..140d66f796e4 100644
--- a/drivers/pci/host/Makefile
+++ b/drivers/pci/host/Makefile
@@ -11,7 +11,9 @@ obj-$(CONFIG_PCIE_SPEAR13XX) += pcie-spear13xx.o
 obj-$(CONFIG_PCI_KEYSTONE) += pci-keystone-dw.o pci-keystone.o
 obj-$(CONFIG_PCIE_XILINX) += pcie-xilinx.o
 obj-$(CONFIG_PCI_XGENE) += pci-xgene.o
+obj-$(CONFIG_PCI_XGENE_MSI) += pci-xgene-msi.o
 obj-$(CONFIG_PCI_LAYERSCAPE) += pci-layerscape.o
 obj-$(CONFIG_PCI_VERSATILE) += pci-versatile.o
 obj-$(CONFIG_PCIE_IPROC) += pcie-iproc.o
 obj-$(CONFIG_PCIE_IPROC_PLATFORM) += pcie-iproc-platform.o
+obj-$(CONFIG_PCIE_IPROC_BCMA) += pcie-iproc-bcma.o
diff --git a/drivers/pci/host/pci-dra7xx.c b/drivers/pci/host/pci-dra7xx.c
index 2d57e19a2cd4..80db09e47800 100644
--- a/drivers/pci/host/pci-dra7xx.c
+++ b/drivers/pci/host/pci-dra7xx.c
@@ -93,9 +93,9 @@ static int dra7xx_pcie_link_up(struct pcie_port *pp)
 
 static int dra7xx_pcie_establish_link(struct pcie_port *pp)
 {
-	u32 reg;
-	unsigned int retries = 1000;
 	struct dra7xx_pcie *dra7xx = to_dra7xx_pcie(pp);
+	u32 reg;
+	unsigned int retries;
 
 	if (dw_pcie_link_up(pp)) {
 		dev_err(pp->dev, "link is already up\n");
@@ -106,19 +106,14 @@ static int dra7xx_pcie_establish_link(struct pcie_port *pp)
 	reg |= LTSSM_EN;
 	dra7xx_pcie_writel(dra7xx, PCIECTRL_DRA7XX_CONF_DEVICE_CMD, reg);
 
-	while (retries--) {
-		reg = dra7xx_pcie_readl(dra7xx,	PCIECTRL_DRA7XX_CONF_PHY_CS);
-		if (reg & LINK_UP)
-			break;
+	for (retries = 0; retries < 1000; retries++) {
+		if (dw_pcie_link_up(pp))
+			return 0;
 		usleep_range(10, 20);
 	}
 
-	if (retries == 0) {
-		dev_err(pp->dev, "link is not up\n");
-		return -ETIMEDOUT;
-	}
-
-	return 0;
+	dev_err(pp->dev, "link is not up\n");
+	return -EINVAL;
 }
 
 static void dra7xx_pcie_enable_interrupts(struct pcie_port *pp)
diff --git a/drivers/pci/host/pci-exynos.c b/drivers/pci/host/pci-exynos.c
index c139237e0e52..f9f468d9a819 100644
--- a/drivers/pci/host/pci-exynos.c
+++ b/drivers/pci/host/pci-exynos.c
@@ -316,9 +316,9 @@ static void exynos_pcie_assert_reset(struct pcie_port *pp)
 
 static int exynos_pcie_establish_link(struct pcie_port *pp)
 {
-	u32 val;
-	int count = 0;
 	struct exynos_pcie *exynos_pcie = to_exynos_pcie(pp);
+	u32 val;
+	unsigned int retries;
 
 	if (dw_pcie_link_up(pp)) {
 		dev_err(pp->dev, "Link already up\n");
@@ -357,27 +357,23 @@ static int exynos_pcie_establish_link(struct pcie_port *pp)
 			  PCIE_APP_LTSSM_ENABLE);
 
 	/* check if the link is up or not */
-	while (!dw_pcie_link_up(pp)) {
-		mdelay(100);
-		count++;
-		if (count == 10) {
-			while (exynos_phy_readl(exynos_pcie,
-						PCIE_PHY_PLL_LOCKED) == 0) {
-				val = exynos_blk_readl(exynos_pcie,
-						       PCIE_PHY_PLL_LOCKED);
-				dev_info(pp->dev, "PLL Locked: 0x%x\n", val);
-			}
-			/* power off phy */
-			exynos_pcie_power_off_phy(pp);
-
-			dev_err(pp->dev, "PCIe Link Fail\n");
-			return -EINVAL;
+	for (retries = 0; retries < 10; retries++) {
+		if (dw_pcie_link_up(pp)) {
+			dev_info(pp->dev, "Link up\n");
+			return 0;
 		}
+		mdelay(100);
 	}
 
-	dev_info(pp->dev, "Link up\n");
+	while (exynos_phy_readl(exynos_pcie, PCIE_PHY_PLL_LOCKED) == 0) {
+		val = exynos_blk_readl(exynos_pcie, PCIE_PHY_PLL_LOCKED);
+		dev_info(pp->dev, "PLL Locked: 0x%x\n", val);
+	}
+	/* power off phy */
+	exynos_pcie_power_off_phy(pp);
 
-	return 0;
+	dev_err(pp->dev, "PCIe Link Fail\n");
+	return -EINVAL;
 }
 
 static void exynos_pcie_clear_irq_pulse(struct pcie_port *pp)
diff --git a/drivers/pci/host/pci-imx6.c b/drivers/pci/host/pci-imx6.c
index fdb95367721e..233a196c6e66 100644
--- a/drivers/pci/host/pci-imx6.c
+++ b/drivers/pci/host/pci-imx6.c
@@ -47,6 +47,8 @@ struct imx6_pcie {
 #define PCIE_RC_LCR_MAX_LINK_SPEEDS_GEN2	0x2
 #define PCIE_RC_LCR_MAX_LINK_SPEEDS_MASK	0xf
 
+#define PCIE_RC_LCSR				0x80
+
 /* PCIe Port Logic registers (memory-mapped) */
 #define PL_OFFSET 0x700
 #define PCIE_PL_PFLR (PL_OFFSET + 0x08)
@@ -335,21 +337,36 @@ static void imx6_pcie_init_phy(struct pcie_port *pp)
 
 static int imx6_pcie_wait_for_link(struct pcie_port *pp)
 {
-	int count = 200;
+	unsigned int retries;
 
-	while (!dw_pcie_link_up(pp)) {
+	for (retries = 0; retries < 200; retries++) {
+		if (dw_pcie_link_up(pp))
+			return 0;
 		usleep_range(100, 1000);
-		if (--count)
-			continue;
-
-		dev_err(pp->dev, "phy link never came up\n");
-		dev_dbg(pp->dev, "DEBUG_R0: 0x%08x, DEBUG_R1: 0x%08x\n",
-			readl(pp->dbi_base + PCIE_PHY_DEBUG_R0),
-			readl(pp->dbi_base + PCIE_PHY_DEBUG_R1));
-		return -EINVAL;
 	}
 
-	return 0;
+	dev_err(pp->dev, "phy link never came up\n");
+	dev_dbg(pp->dev, "DEBUG_R0: 0x%08x, DEBUG_R1: 0x%08x\n",
+		readl(pp->dbi_base + PCIE_PHY_DEBUG_R0),
+		readl(pp->dbi_base + PCIE_PHY_DEBUG_R1));
+	return -EINVAL;
+}
+
+static int imx6_pcie_wait_for_speed_change(struct pcie_port *pp)
+{
+	u32 tmp;
+	unsigned int retries;
+
+	for (retries = 0; retries < 200; retries++) {
+		tmp = readl(pp->dbi_base + PCIE_LINK_WIDTH_SPEED_CONTROL);
+		/* Test if the speed change finished. */
+		if (!(tmp & PORT_LOGIC_SPEED_CHANGE))
+			return 0;
+		usleep_range(100, 1000);
+	}
+
+	dev_err(pp->dev, "Speed change timeout\n");
+	return -EINVAL;
 }
 
 static irqreturn_t imx6_pcie_msi_handler(int irq, void *arg)
@@ -359,11 +376,11 @@ static irqreturn_t imx6_pcie_msi_handler(int irq, void *arg)
 	return dw_handle_msi_irq(pp);
 }
 
-static int imx6_pcie_start_link(struct pcie_port *pp)
+static int imx6_pcie_establish_link(struct pcie_port *pp)
 {
 	struct imx6_pcie *imx6_pcie = to_imx6_pcie(pp);
-	uint32_t tmp;
-	int ret, count;
+	u32 tmp;
+	int ret;
 
 	/*
 	 * Force Gen1 operation when starting the link.  In case the link is
@@ -397,29 +414,22 @@ static int imx6_pcie_start_link(struct pcie_port *pp)
 	tmp |= PORT_LOGIC_SPEED_CHANGE;
 	writel(tmp, pp->dbi_base + PCIE_LINK_WIDTH_SPEED_CONTROL);
 
-	count = 200;
-	while (count--) {
-		tmp = readl(pp->dbi_base + PCIE_LINK_WIDTH_SPEED_CONTROL);
-		/* Test if the speed change finished. */
-		if (!(tmp & PORT_LOGIC_SPEED_CHANGE))
-			break;
-		usleep_range(100, 1000);
+	ret = imx6_pcie_wait_for_speed_change(pp);
+	if (ret) {
+		dev_err(pp->dev, "Failed to bring link up!\n");
+		return ret;
 	}
 
 	/* Make sure link training is finished as well! */
-	if (count)
-		ret = imx6_pcie_wait_for_link(pp);
-	else
-		ret = -EINVAL;
-
+	ret = imx6_pcie_wait_for_link(pp);
 	if (ret) {
 		dev_err(pp->dev, "Failed to bring link up!\n");
-	} else {
-		tmp = readl(pp->dbi_base + 0x80);
-		dev_dbg(pp->dev, "Link up, Gen=%i\n", (tmp >> 16) & 0xf);
+		return ret;
 	}
 
-	return ret;
+	tmp = readl(pp->dbi_base + PCIE_RC_LCSR);
+	dev_dbg(pp->dev, "Link up, Gen=%i\n", (tmp >> 16) & 0xf);
+	return 0;
 }
 
 static void imx6_pcie_host_init(struct pcie_port *pp)
@@ -432,7 +442,7 @@ static void imx6_pcie_host_init(struct pcie_port *pp)
 
 	dw_pcie_setup_rc(pp);
 
-	imx6_pcie_start_link(pp);
+	imx6_pcie_establish_link(pp);
 
 	if (IS_ENABLED(CONFIG_PCI_MSI))
 		dw_pcie_msi_init(pp);
@@ -440,19 +450,19 @@ static void imx6_pcie_host_init(struct pcie_port *pp)
 
 static void imx6_pcie_reset_phy(struct pcie_port *pp)
 {
-	uint32_t temp;
+	u32 tmp;
 
-	pcie_phy_read(pp->dbi_base, PHY_RX_OVRD_IN_LO, &temp);
-	temp |= (PHY_RX_OVRD_IN_LO_RX_DATA_EN |
-		 PHY_RX_OVRD_IN_LO_RX_PLL_EN);
-	pcie_phy_write(pp->dbi_base, PHY_RX_OVRD_IN_LO, temp);
+	pcie_phy_read(pp->dbi_base, PHY_RX_OVRD_IN_LO, &tmp);
+	tmp |= (PHY_RX_OVRD_IN_LO_RX_DATA_EN |
+		PHY_RX_OVRD_IN_LO_RX_PLL_EN);
+	pcie_phy_write(pp->dbi_base, PHY_RX_OVRD_IN_LO, tmp);
 
 	usleep_range(2000, 3000);
 
-	pcie_phy_read(pp->dbi_base, PHY_RX_OVRD_IN_LO, &temp);
-	temp &= ~(PHY_RX_OVRD_IN_LO_RX_DATA_EN |
+	pcie_phy_read(pp->dbi_base, PHY_RX_OVRD_IN_LO, &tmp);
+	tmp &= ~(PHY_RX_OVRD_IN_LO_RX_DATA_EN |
 		  PHY_RX_OVRD_IN_LO_RX_PLL_EN);
-	pcie_phy_write(pp->dbi_base, PHY_RX_OVRD_IN_LO, temp);
+	pcie_phy_write(pp->dbi_base, PHY_RX_OVRD_IN_LO, tmp);
 }
 
 static int imx6_pcie_link_up(struct pcie_port *pp)
diff --git a/drivers/pci/host/pci-keystone.c b/drivers/pci/host/pci-keystone.c
index 75333b0c4f0a..b75d684aefcd 100644
--- a/drivers/pci/host/pci-keystone.c
+++ b/drivers/pci/host/pci-keystone.c
@@ -88,7 +88,7 @@ DECLARE_PCI_FIXUP_ENABLE(PCI_ANY_ID, PCI_ANY_ID, quirk_limit_mrrs);
 static int ks_pcie_establish_link(struct keystone_pcie *ks_pcie)
 {
 	struct pcie_port *pp = &ks_pcie->pp;
-	int count = 200;
+	unsigned int retries;
 
 	dw_pcie_setup_rc(pp);
 
@@ -99,17 +99,15 @@ static int ks_pcie_establish_link(struct keystone_pcie *ks_pcie)
 
 	ks_dw_pcie_initiate_link_train(ks_pcie);
 	/* check if the link is up or not */
-	while (!dw_pcie_link_up(pp)) {
+	for (retries = 0; retries < 200; retries++) {
+		if (dw_pcie_link_up(pp))
+			return 0;
 		usleep_range(100, 1000);
-		if (--count) {
-			ks_dw_pcie_initiate_link_train(ks_pcie);
-			continue;
-		}
-		dev_err(pp->dev, "phy link never came up\n");
-		return -EINVAL;
+		ks_dw_pcie_initiate_link_train(ks_pcie);
 	}
 
-	return 0;
+	dev_err(pp->dev, "phy link never came up\n");
+	return -EINVAL;
 }
 
 static void ks_pcie_msi_irq_handler(unsigned int irq, struct irq_desc *desc)
diff --git a/drivers/pci/host/pci-layerscape.c b/drivers/pci/host/pci-layerscape.c
index 4a6e62f67579..b2328ea13dcf 100644
--- a/drivers/pci/host/pci-layerscape.c
+++ b/drivers/pci/host/pci-layerscape.c
@@ -62,22 +62,27 @@ static int ls_pcie_link_up(struct pcie_port *pp)
 	return 1;
 }
 
+static int ls_pcie_establish_link(struct pcie_port *pp)
+{
+	unsigned int retries;
+
+	for (retries = 0; retries < 200; retries++) {
+		if (dw_pcie_link_up(pp))
+			return 0;
+		usleep_range(100, 1000);
+	}
+
+	dev_err(pp->dev, "phy link never came up\n");
+	return -EINVAL;
+}
+
 static void ls_pcie_host_init(struct pcie_port *pp)
 {
 	struct ls_pcie *pcie = to_ls_pcie(pp);
-	int count = 0;
 	u32 val;
 
 	dw_pcie_setup_rc(pp);
-
-	while (!ls_pcie_link_up(pp)) {
-		usleep_range(100, 1000);
-		count++;
-		if (count >= 200) {
-			dev_err(pp->dev, "phy link never came up\n");
-			return;
-		}
-	}
+	ls_pcie_establish_link(pp);
 
 	/*
 	 * LS1021A Workaround for internal TKT228622
diff --git a/drivers/pci/host/pci-mvebu.c b/drivers/pci/host/pci-mvebu.c
index 1ab863551920..70aa09556ec5 100644
--- a/drivers/pci/host/pci-mvebu.c
+++ b/drivers/pci/host/pci-mvebu.c
@@ -751,21 +751,6 @@ static int mvebu_pcie_setup(int nr, struct pci_sys_data *sys)
 	return 1;
 }
 
-static struct pci_bus *mvebu_pcie_scan_bus(int nr, struct pci_sys_data *sys)
-{
-	struct mvebu_pcie *pcie = sys_to_pcie(sys);
-	struct pci_bus *bus;
-
-	bus = pci_create_root_bus(&pcie->pdev->dev, sys->busnr,
-				  &mvebu_pcie_ops, sys, &sys->resources);
-	if (!bus)
-		return NULL;
-
-	pci_scan_child_bus(bus);
-
-	return bus;
-}
-
 static resource_size_t mvebu_pcie_align_resource(struct pci_dev *dev,
 						 const struct resource *res,
 						 resource_size_t start,
@@ -809,12 +794,11 @@ static void mvebu_pcie_enable(struct mvebu_pcie *pcie)
 	hw.nr_controllers = 1;
 	hw.private_data   = (void **)&pcie;
 	hw.setup          = mvebu_pcie_setup;
-	hw.scan           = mvebu_pcie_scan_bus;
 	hw.map_irq        = of_irq_parse_and_map_pci;
 	hw.ops            = &mvebu_pcie_ops;
 	hw.align_resource = mvebu_pcie_align_resource;
 
-	pci_common_init(&hw);
+	pci_common_init_dev(&pcie->pdev->dev, &hw);
 }
 
 /*
diff --git a/drivers/pci/host/pci-tegra.c b/drivers/pci/host/pci-tegra.c
index 00e92720d7f7..10c05718dbfd 100644
--- a/drivers/pci/host/pci-tegra.c
+++ b/drivers/pci/host/pci-tegra.c
@@ -630,21 +630,6 @@ static int tegra_pcie_map_irq(const struct pci_dev *pdev, u8 slot, u8 pin)
 	return irq;
 }
 
-static struct pci_bus *tegra_pcie_scan_bus(int nr, struct pci_sys_data *sys)
-{
-	struct tegra_pcie *pcie = sys_to_pcie(sys);
-	struct pci_bus *bus;
-
-	bus = pci_create_root_bus(pcie->dev, sys->busnr, &tegra_pcie_ops, sys,
-				  &sys->resources);
-	if (!bus)
-		return NULL;
-
-	pci_scan_child_bus(bus);
-
-	return bus;
-}
-
 static irqreturn_t tegra_pcie_isr(int irq, void *arg)
 {
 	const char *err_msg[] = {
@@ -1831,7 +1816,6 @@ static int tegra_pcie_enable(struct tegra_pcie *pcie)
 	hw.private_data = (void **)&pcie;
 	hw.setup = tegra_pcie_setup;
 	hw.map_irq = tegra_pcie_map_irq;
-	hw.scan = tegra_pcie_scan_bus;
 	hw.ops = &tegra_pcie_ops;
 
 	pci_common_init_dev(pcie->dev, &hw);
diff --git a/drivers/pci/host/pci-xgene-msi.c b/drivers/pci/host/pci-xgene-msi.c
new file mode 100644
index 000000000000..2d31d4d6fd08
--- /dev/null
+++ b/drivers/pci/host/pci-xgene-msi.c
@@ -0,0 +1,596 @@
+/*
+ * APM X-Gene MSI Driver
+ *
+ * Copyright (c) 2014, Applied Micro Circuits Corporation
+ * Author: Tanmay Inamdar <tinamdar@apm.com>
+ *	   Duc Dang <dhdang@apm.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+#include <linux/cpu.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/msi.h>
+#include <linux/of_irq.h>
+#include <linux/irqchip/chained_irq.h>
+#include <linux/pci.h>
+#include <linux/platform_device.h>
+#include <linux/of_pci.h>
+
+#define MSI_IR0			0x000000
+#define MSI_INT0		0x800000
+#define IDX_PER_GROUP		8
+#define IRQS_PER_IDX		16
+#define NR_HW_IRQS		16
+#define NR_MSI_VEC		(IDX_PER_GROUP * IRQS_PER_IDX * NR_HW_IRQS)
+
+struct xgene_msi_group {
+	struct xgene_msi	*msi;
+	int			gic_irq;
+	u32			msi_grp;
+};
+
+struct xgene_msi {
+	struct device_node	*node;
+	struct msi_controller	mchip;
+	struct irq_domain	*domain;
+	u64			msi_addr;
+	void __iomem		*msi_regs;
+	unsigned long		*bitmap;
+	struct mutex		bitmap_lock;
+	struct xgene_msi_group	*msi_groups;
+	int			num_cpus;
+};
+
+/* Global data */
+static struct xgene_msi xgene_msi_ctrl;
+
+static struct irq_chip xgene_msi_top_irq_chip = {
+	.name		= "X-Gene1 MSI",
+	.irq_enable	= pci_msi_unmask_irq,
+	.irq_disable	= pci_msi_mask_irq,
+	.irq_mask	= pci_msi_mask_irq,
+	.irq_unmask	= pci_msi_unmask_irq,
+};
+
+static struct  msi_domain_info xgene_msi_domain_info = {
+	.flags	= (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS |
+		  MSI_FLAG_PCI_MSIX),
+	.chip	= &xgene_msi_top_irq_chip,
+};
+
+/*
+ * X-Gene v1 has 16 groups of MSI termination registers MSInIRx, where
+ * n is group number (0..F), x is index of registers in each group (0..7)
+ * The register layout is as follows:
+ * MSI0IR0			base_addr
+ * MSI0IR1			base_addr +  0x10000
+ * ...				...
+ * MSI0IR6			base_addr +  0x60000
+ * MSI0IR7			base_addr +  0x70000
+ * MSI1IR0			base_addr +  0x80000
+ * MSI1IR1			base_addr +  0x90000
+ * ...				...
+ * MSI1IR7			base_addr +  0xF0000
+ * MSI2IR0			base_addr + 0x100000
+ * ...				...
+ * MSIFIR0			base_addr + 0x780000
+ * MSIFIR1			base_addr + 0x790000
+ * ...				...
+ * MSIFIR7			base_addr + 0x7F0000
+ * MSIINT0			base_addr + 0x800000
+ * MSIINT1			base_addr + 0x810000
+ * ...				...
+ * MSIINTF			base_addr + 0x8F0000
+ *
+ * Each index register supports 16 MSI vectors (0..15) to generate interrupt.
+ * There are total 16 GIC IRQs assigned for these 16 groups of MSI termination
+ * registers.
+ *
+ * Each MSI termination group has 1 MSIINTn register (n is 0..15) to indicate
+ * the MSI pending status caused by 1 of its 8 index registers.
+ */
+
+/* MSInIRx read helper */
+static u32 xgene_msi_ir_read(struct xgene_msi *msi,
+				    u32 msi_grp, u32 msir_idx)
+{
+	return readl_relaxed(msi->msi_regs + MSI_IR0 +
+			      (msi_grp << 19) + (msir_idx << 16));
+}
+
+/* MSIINTn read helper */
+static u32 xgene_msi_int_read(struct xgene_msi *msi, u32 msi_grp)
+{
+	return readl_relaxed(msi->msi_regs + MSI_INT0 + (msi_grp << 16));
+}
+
+/*
+ * With 2048 MSI vectors supported, the MSI message can be constructed using
+ * following scheme:
+ * - Divide into 8 256-vector groups
+ *		Group 0: 0-255
+ *		Group 1: 256-511
+ *		Group 2: 512-767
+ *		...
+ *		Group 7: 1792-2047
+ * - Each 256-vector group is divided into 16 16-vector groups
+ *	As an example: 16 16-vector groups for 256-vector group 0-255 is
+ *		Group 0: 0-15
+ *		Group 1: 16-32
+ *		...
+ *		Group 15: 240-255
+ * - The termination address of MSI vector in 256-vector group n and 16-vector
+ *   group x is the address of MSIxIRn
+ * - The data for MSI vector in 16-vector group x is x
+ */
+static u32 hwirq_to_reg_set(unsigned long hwirq)
+{
+	return (hwirq / (NR_HW_IRQS * IRQS_PER_IDX));
+}
+
+static u32 hwirq_to_group(unsigned long hwirq)
+{
+	return (hwirq % NR_HW_IRQS);
+}
+
+static u32 hwirq_to_msi_data(unsigned long hwirq)
+{
+	return ((hwirq / NR_HW_IRQS) % IRQS_PER_IDX);
+}
+
+static void xgene_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
+{
+	struct xgene_msi *msi = irq_data_get_irq_chip_data(data);
+	u32 reg_set = hwirq_to_reg_set(data->hwirq);
+	u32 group = hwirq_to_group(data->hwirq);
+	u64 target_addr = msi->msi_addr + (((8 * group) + reg_set) << 16);
+
+	msg->address_hi = upper_32_bits(target_addr);
+	msg->address_lo = lower_32_bits(target_addr);
+	msg->data = hwirq_to_msi_data(data->hwirq);
+}
+
+/*
+ * X-Gene v1 only has 16 MSI GIC IRQs for 2048 MSI vectors.  To maintain
+ * the expected behaviour of .set_affinity for each MSI interrupt, the 16
+ * MSI GIC IRQs are statically allocated to 8 X-Gene v1 cores (2 GIC IRQs
+ * for each core).  The MSI vector is moved fom 1 MSI GIC IRQ to another
+ * MSI GIC IRQ to steer its MSI interrupt to correct X-Gene v1 core.  As a
+ * consequence, the total MSI vectors that X-Gene v1 supports will be
+ * reduced to 256 (2048/8) vectors.
+ */
+static int hwirq_to_cpu(unsigned long hwirq)
+{
+	return (hwirq % xgene_msi_ctrl.num_cpus);
+}
+
+static unsigned long hwirq_to_canonical_hwirq(unsigned long hwirq)
+{
+	return (hwirq - hwirq_to_cpu(hwirq));
+}
+
+static int xgene_msi_set_affinity(struct irq_data *irqdata,
+				  const struct cpumask *mask, bool force)
+{
+	int target_cpu = cpumask_first(mask);
+	int curr_cpu;
+
+	curr_cpu = hwirq_to_cpu(irqdata->hwirq);
+	if (curr_cpu == target_cpu)
+		return IRQ_SET_MASK_OK_DONE;
+
+	/* Update MSI number to target the new CPU */
+	irqdata->hwirq = hwirq_to_canonical_hwirq(irqdata->hwirq) + target_cpu;
+
+	return IRQ_SET_MASK_OK;
+}
+
+static struct irq_chip xgene_msi_bottom_irq_chip = {
+	.name			= "MSI",
+	.irq_set_affinity       = xgene_msi_set_affinity,
+	.irq_compose_msi_msg	= xgene_compose_msi_msg,
+};
+
+static int xgene_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
+				  unsigned int nr_irqs, void *args)
+{
+	struct xgene_msi *msi = domain->host_data;
+	int msi_irq;
+
+	mutex_lock(&msi->bitmap_lock);
+
+	msi_irq = bitmap_find_next_zero_area(msi->bitmap, NR_MSI_VEC, 0,
+					     msi->num_cpus, 0);
+	if (msi_irq < NR_MSI_VEC)
+		bitmap_set(msi->bitmap, msi_irq, msi->num_cpus);
+	else
+		msi_irq = -ENOSPC;
+
+	mutex_unlock(&msi->bitmap_lock);
+
+	if (msi_irq < 0)
+		return msi_irq;
+
+	irq_domain_set_info(domain, virq, msi_irq,
+			    &xgene_msi_bottom_irq_chip, domain->host_data,
+			    handle_simple_irq, NULL, NULL);
+	set_irq_flags(virq, IRQF_VALID);
+
+	return 0;
+}
+
+static void xgene_irq_domain_free(struct irq_domain *domain,
+				  unsigned int virq, unsigned int nr_irqs)
+{
+	struct irq_data *d = irq_domain_get_irq_data(domain, virq);
+	struct xgene_msi *msi = irq_data_get_irq_chip_data(d);
+	u32 hwirq;
+
+	mutex_lock(&msi->bitmap_lock);
+
+	hwirq = hwirq_to_canonical_hwirq(d->hwirq);
+	bitmap_clear(msi->bitmap, hwirq, msi->num_cpus);
+
+	mutex_unlock(&msi->bitmap_lock);
+
+	irq_domain_free_irqs_parent(domain, virq, nr_irqs);
+}
+
+static const struct irq_domain_ops msi_domain_ops = {
+	.alloc  = xgene_irq_domain_alloc,
+	.free   = xgene_irq_domain_free,
+};
+
+static int xgene_allocate_domains(struct xgene_msi *msi)
+{
+	msi->domain = irq_domain_add_linear(NULL, NR_MSI_VEC,
+					    &msi_domain_ops, msi);
+	if (!msi->domain)
+		return -ENOMEM;
+
+	msi->mchip.domain = pci_msi_create_irq_domain(msi->mchip.of_node,
+						      &xgene_msi_domain_info,
+						      msi->domain);
+
+	if (!msi->mchip.domain) {
+		irq_domain_remove(msi->domain);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void xgene_free_domains(struct xgene_msi *msi)
+{
+	if (msi->mchip.domain)
+		irq_domain_remove(msi->mchip.domain);
+	if (msi->domain)
+		irq_domain_remove(msi->domain);
+}
+
+static int xgene_msi_init_allocator(struct xgene_msi *xgene_msi)
+{
+	int size = BITS_TO_LONGS(NR_MSI_VEC) * sizeof(long);
+
+	xgene_msi->bitmap = kzalloc(size, GFP_KERNEL);
+	if (!xgene_msi->bitmap)
+		return -ENOMEM;
+
+	mutex_init(&xgene_msi->bitmap_lock);
+
+	xgene_msi->msi_groups = kcalloc(NR_HW_IRQS,
+					sizeof(struct xgene_msi_group),
+					GFP_KERNEL);
+	if (!xgene_msi->msi_groups)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void xgene_msi_isr(unsigned int irq, struct irq_desc *desc)
+{
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+	struct xgene_msi_group *msi_groups;
+	struct xgene_msi *xgene_msi;
+	unsigned int virq;
+	int msir_index, msir_val, hw_irq;
+	u32 intr_index, grp_select, msi_grp;
+
+	chained_irq_enter(chip, desc);
+
+	msi_groups = irq_desc_get_handler_data(desc);
+	xgene_msi = msi_groups->msi;
+	msi_grp = msi_groups->msi_grp;
+
+	/*
+	 * MSIINTn (n is 0..F) indicates if there is a pending MSI interrupt
+	 * If bit x of this register is set (x is 0..7), one or more interupts
+	 * corresponding to MSInIRx is set.
+	 */
+	grp_select = xgene_msi_int_read(xgene_msi, msi_grp);
+	while (grp_select) {
+		msir_index = ffs(grp_select) - 1;
+		/*
+		 * Calculate MSInIRx address to read to check for interrupts
+		 * (refer to termination address and data assignment
+		 * described in xgene_compose_msi_msg() )
+		 */
+		msir_val = xgene_msi_ir_read(xgene_msi, msi_grp, msir_index);
+		while (msir_val) {
+			intr_index = ffs(msir_val) - 1;
+			/*
+			 * Calculate MSI vector number (refer to the termination
+			 * address and data assignment described in
+			 * xgene_compose_msi_msg function)
+			 */
+			hw_irq = (((msir_index * IRQS_PER_IDX) + intr_index) *
+				 NR_HW_IRQS) + msi_grp;
+			/*
+			 * As we have multiple hw_irq that maps to single MSI,
+			 * always look up the virq using the hw_irq as seen from
+			 * CPU0
+			 */
+			hw_irq = hwirq_to_canonical_hwirq(hw_irq);
+			virq = irq_find_mapping(xgene_msi->domain, hw_irq);
+			WARN_ON(!virq);
+			if (virq != 0)
+				generic_handle_irq(virq);
+			msir_val &= ~(1 << intr_index);
+		}
+		grp_select &= ~(1 << msir_index);
+
+		if (!grp_select) {
+			/*
+			 * We handled all interrupts happened in this group,
+			 * resample this group MSI_INTx register in case
+			 * something else has been made pending in the meantime
+			 */
+			grp_select = xgene_msi_int_read(xgene_msi, msi_grp);
+		}
+	}
+
+	chained_irq_exit(chip, desc);
+}
+
+static int xgene_msi_remove(struct platform_device *pdev)
+{
+	int virq, i;
+	struct xgene_msi *msi = platform_get_drvdata(pdev);
+
+	for (i = 0; i < NR_HW_IRQS; i++) {
+		virq = msi->msi_groups[i].gic_irq;
+		if (virq != 0) {
+			irq_set_chained_handler(virq, NULL);
+			irq_set_handler_data(virq, NULL);
+		}
+	}
+	kfree(msi->msi_groups);
+
+	kfree(msi->bitmap);
+	msi->bitmap = NULL;
+
+	xgene_free_domains(msi);
+
+	return 0;
+}
+
+static int xgene_msi_hwirq_alloc(unsigned int cpu)
+{
+	struct xgene_msi *msi = &xgene_msi_ctrl;
+	struct xgene_msi_group *msi_group;
+	cpumask_var_t mask;
+	int i;
+	int err;
+
+	for (i = cpu; i < NR_HW_IRQS; i += msi->num_cpus) {
+		msi_group = &msi->msi_groups[i];
+		if (!msi_group->gic_irq)
+			continue;
+
+		irq_set_chained_handler(msi_group->gic_irq,
+					xgene_msi_isr);
+		err = irq_set_handler_data(msi_group->gic_irq, msi_group);
+		if (err) {
+			pr_err("failed to register GIC IRQ handler\n");
+			return -EINVAL;
+		}
+		/*
+		 * Statically allocate MSI GIC IRQs to each CPU core.
+		 * With 8-core X-Gene v1, 2 MSI GIC IRQs are allocated
+		 * to each core.
+		 */
+		if (alloc_cpumask_var(&mask, GFP_KERNEL)) {
+			cpumask_clear(mask);
+			cpumask_set_cpu(cpu, mask);
+			err = irq_set_affinity(msi_group->gic_irq, mask);
+			if (err)
+				pr_err("failed to set affinity for GIC IRQ");
+			free_cpumask_var(mask);
+		} else {
+			pr_err("failed to alloc CPU mask for affinity\n");
+			err = -EINVAL;
+		}
+
+		if (err) {
+			irq_set_chained_handler(msi_group->gic_irq, NULL);
+			irq_set_handler_data(msi_group->gic_irq, NULL);
+			return err;
+		}
+	}
+
+	return 0;
+}
+
+static void xgene_msi_hwirq_free(unsigned int cpu)
+{
+	struct xgene_msi *msi = &xgene_msi_ctrl;
+	struct xgene_msi_group *msi_group;
+	int i;
+
+	for (i = cpu; i < NR_HW_IRQS; i += msi->num_cpus) {
+		msi_group = &msi->msi_groups[i];
+		if (!msi_group->gic_irq)
+			continue;
+
+		irq_set_chained_handler(msi_group->gic_irq, NULL);
+		irq_set_handler_data(msi_group->gic_irq, NULL);
+	}
+}
+
+static int xgene_msi_cpu_callback(struct notifier_block *nfb,
+				  unsigned long action, void *hcpu)
+{
+	unsigned cpu = (unsigned long)hcpu;
+
+	switch (action) {
+	case CPU_ONLINE:
+	case CPU_ONLINE_FROZEN:
+		xgene_msi_hwirq_alloc(cpu);
+		break;
+	case CPU_DEAD:
+	case CPU_DEAD_FROZEN:
+		xgene_msi_hwirq_free(cpu);
+		break;
+	default:
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block xgene_msi_cpu_notifier = {
+	.notifier_call = xgene_msi_cpu_callback,
+};
+
+static const struct of_device_id xgene_msi_match_table[] = {
+	{.compatible = "apm,xgene1-msi"},
+	{},
+};
+
+static int xgene_msi_probe(struct platform_device *pdev)
+{
+	struct resource *res;
+	int rc, irq_index;
+	struct xgene_msi *xgene_msi;
+	unsigned int cpu;
+	int virt_msir;
+	u32 msi_val, msi_idx;
+
+	xgene_msi = &xgene_msi_ctrl;
+
+	platform_set_drvdata(pdev, xgene_msi);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	xgene_msi->msi_regs = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(xgene_msi->msi_regs)) {
+		dev_err(&pdev->dev, "no reg space\n");
+		rc = -EINVAL;
+		goto error;
+	}
+	xgene_msi->msi_addr = res->start;
+
+	xgene_msi->num_cpus = num_possible_cpus();
+
+	rc = xgene_msi_init_allocator(xgene_msi);
+	if (rc) {
+		dev_err(&pdev->dev, "Error allocating MSI bitmap\n");
+		goto error;
+	}
+
+	rc = xgene_allocate_domains(xgene_msi);
+	if (rc) {
+		dev_err(&pdev->dev, "Failed to allocate MSI domain\n");
+		goto error;
+	}
+
+	for (irq_index = 0; irq_index < NR_HW_IRQS; irq_index++) {
+		virt_msir = platform_get_irq(pdev, irq_index);
+		if (virt_msir < 0) {
+			dev_err(&pdev->dev, "Cannot translate IRQ index %d\n",
+				irq_index);
+			rc = -EINVAL;
+			goto error;
+		}
+		xgene_msi->msi_groups[irq_index].gic_irq = virt_msir;
+		xgene_msi->msi_groups[irq_index].msi_grp = irq_index;
+		xgene_msi->msi_groups[irq_index].msi = xgene_msi;
+	}
+
+	/*
+	 * MSInIRx registers are read-to-clear; before registering
+	 * interrupt handlers, read all of them to clear spurious
+	 * interrupts that may occur before the driver is probed.
+	 */
+	for (irq_index = 0; irq_index < NR_HW_IRQS; irq_index++) {
+		for (msi_idx = 0; msi_idx < IDX_PER_GROUP; msi_idx++)
+			msi_val = xgene_msi_ir_read(xgene_msi, irq_index,
+						    msi_idx);
+		/* Read MSIINTn to confirm */
+		msi_val = xgene_msi_int_read(xgene_msi, irq_index);
+		if (msi_val) {
+			dev_err(&pdev->dev, "Failed to clear spurious IRQ\n");
+			rc = -EINVAL;
+			goto error;
+		}
+	}
+
+	cpu_notifier_register_begin();
+
+	for_each_online_cpu(cpu)
+		if (xgene_msi_hwirq_alloc(cpu)) {
+			dev_err(&pdev->dev, "failed to register MSI handlers\n");
+			cpu_notifier_register_done();
+			goto error;
+		}
+
+	rc = __register_hotcpu_notifier(&xgene_msi_cpu_notifier);
+	if (rc) {
+		dev_err(&pdev->dev, "failed to add CPU MSI notifier\n");
+		cpu_notifier_register_done();
+		goto error;
+	}
+
+	cpu_notifier_register_done();
+
+	xgene_msi->mchip.of_node = pdev->dev.of_node;
+	rc = of_pci_msi_chip_add(&xgene_msi->mchip);
+	if (rc) {
+		dev_err(&pdev->dev, "failed to add MSI controller chip\n");
+		goto error_notifier;
+	}
+
+	dev_info(&pdev->dev, "APM X-Gene PCIe MSI driver loaded\n");
+
+	return 0;
+
+error_notifier:
+	unregister_hotcpu_notifier(&xgene_msi_cpu_notifier);
+error:
+	xgene_msi_remove(pdev);
+	return rc;
+}
+
+static struct platform_driver xgene_msi_driver = {
+	.driver = {
+		.name = "xgene-msi",
+		.owner = THIS_MODULE,
+		.of_match_table = xgene_msi_match_table,
+	},
+	.probe = xgene_msi_probe,
+	.remove = xgene_msi_remove,
+};
+
+static int __init xgene_pcie_msi_init(void)
+{
+	return platform_driver_register(&xgene_msi_driver);
+}
+subsys_initcall(xgene_pcie_msi_init);
diff --git a/drivers/pci/host/pci-xgene.c b/drivers/pci/host/pci-xgene.c
index ee082c0366ec..a9dfb70d623a 100644
--- a/drivers/pci/host/pci-xgene.c
+++ b/drivers/pci/host/pci-xgene.c
@@ -59,6 +59,12 @@
 #define SZ_1T				(SZ_1G*1024ULL)
 #define PIPE_PHY_RATE_RD(src)		((0xc000 & (u32)(src)) >> 0xe)
 
+#define ROOT_CAP_AND_CTRL		0x5C
+
+/* PCIe IP version */
+#define XGENE_PCIE_IP_VER_UNKN		0
+#define XGENE_PCIE_IP_VER_1		1
+
 struct xgene_pcie_port {
 	struct device_node	*node;
 	struct device		*dev;
@@ -67,6 +73,7 @@ struct xgene_pcie_port {
 	void __iomem		*cfg_base;
 	unsigned long		cfg_addr;
 	bool			link_up;
+	u32			version;
 };
 
 static inline u32 pcie_bar_low_val(u32 addr, u32 flags)
@@ -130,9 +137,7 @@ static bool xgene_pcie_hide_rc_bars(struct pci_bus *bus, int offset)
 static void __iomem *xgene_pcie_map_bus(struct pci_bus *bus, unsigned int devfn,
 			      int offset)
 {
-	struct xgene_pcie_port *port = bus->sysdata;
-
-	if ((pci_is_root_bus(bus) && devfn != 0) || !port->link_up ||
+	if ((pci_is_root_bus(bus) && devfn != 0) ||
 	    xgene_pcie_hide_rc_bars(bus, offset))
 		return NULL;
 
@@ -140,9 +145,37 @@ static void __iomem *xgene_pcie_map_bus(struct pci_bus *bus, unsigned int devfn,
 	return xgene_pcie_get_cfg_base(bus) + offset;
 }
 
+static int xgene_pcie_config_read32(struct pci_bus *bus, unsigned int devfn,
+				    int where, int size, u32 *val)
+{
+	struct xgene_pcie_port *port = bus->sysdata;
+
+	if (pci_generic_config_read32(bus, devfn, where & ~0x3, 4, val) !=
+	    PCIBIOS_SUCCESSFUL)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
+	/*
+	 * The v1 controller has a bug in its Configuration Request
+	 * Retry Status (CRS) logic: when CRS is enabled and we read the
+	 * Vendor and Device ID of a non-existent device, the controller
+	 * fabricates return data of 0xFFFF0001 ("device exists but is not
+	 * ready") instead of 0xFFFFFFFF ("device does not exist").  This
+	 * causes the PCI core to retry the read until it times out.
+	 * Avoid this by not claiming to support CRS.
+	 */
+	if (pci_is_root_bus(bus) && (port->version == XGENE_PCIE_IP_VER_1) &&
+	    ((where & ~0x3) == ROOT_CAP_AND_CTRL))
+		*val &= ~(PCI_EXP_RTCAP_CRSVIS << 16);
+
+	if (size <= 2)
+		*val = (*val >> (8 * (where & 3))) & ((1 << (size * 8)) - 1);
+
+	return PCIBIOS_SUCCESSFUL;
+}
+
 static struct pci_ops xgene_pcie_ops = {
 	.map_bus = xgene_pcie_map_bus,
-	.read = pci_generic_config_read32,
+	.read = xgene_pcie_config_read32,
 	.write = pci_generic_config_write32,
 };
 
@@ -468,6 +501,23 @@ static int xgene_pcie_setup(struct xgene_pcie_port *port,
 	return 0;
 }
 
+static int xgene_pcie_msi_enable(struct pci_bus *bus)
+{
+	struct device_node *msi_node;
+
+	msi_node = of_parse_phandle(bus->dev.of_node,
+					"msi-parent", 0);
+	if (!msi_node)
+		return -ENODEV;
+
+	bus->msi = of_pci_find_msi_chip_by_node(msi_node);
+	if (!bus->msi)
+		return -ENODEV;
+
+	bus->msi->dev = &bus->dev;
+	return 0;
+}
+
 static int xgene_pcie_probe_bridge(struct platform_device *pdev)
 {
 	struct device_node *dn = pdev->dev.of_node;
@@ -483,6 +533,10 @@ static int xgene_pcie_probe_bridge(struct platform_device *pdev)
 	port->node = of_node_get(pdev->dev.of_node);
 	port->dev = &pdev->dev;
 
+	port->version = XGENE_PCIE_IP_VER_UNKN;
+	if (of_device_is_compatible(port->node, "apm,xgene-pcie"))
+		port->version = XGENE_PCIE_IP_VER_1;
+
 	ret = xgene_pcie_map_reg(port, pdev);
 	if (ret)
 		return ret;
@@ -504,6 +558,10 @@ static int xgene_pcie_probe_bridge(struct platform_device *pdev)
 	if (!bus)
 		return -ENOMEM;
 
+	if (IS_ENABLED(CONFIG_PCI_MSI))
+		if (xgene_pcie_msi_enable(bus))
+			dev_info(port->dev, "failed to enable MSI\n");
+
 	pci_scan_child_bus(bus);
 	pci_assign_unassigned_bus_resources(bus);
 	pci_bus_add_devices(bus);
diff --git a/drivers/pci/host/pcie-designware.c b/drivers/pci/host/pcie-designware.c
index 2e9f84fdd9ce..69486be7181e 100644
--- a/drivers/pci/host/pcie-designware.c
+++ b/drivers/pci/host/pcie-designware.c
@@ -31,6 +31,7 @@
 #define PORT_LINK_MODE_1_LANES		(0x1 << 16)
 #define PORT_LINK_MODE_2_LANES		(0x3 << 16)
 #define PORT_LINK_MODE_4_LANES		(0x7 << 16)
+#define PORT_LINK_MODE_8_LANES		(0xf << 16)
 
 #define PCIE_LINK_WIDTH_SPEED_CONTROL	0x80C
 #define PORT_LOGIC_SPEED_CHANGE		(0x1 << 17)
@@ -38,6 +39,7 @@
 #define PORT_LOGIC_LINK_WIDTH_1_LANES	(0x1 << 8)
 #define PORT_LOGIC_LINK_WIDTH_2_LANES	(0x2 << 8)
 #define PORT_LOGIC_LINK_WIDTH_4_LANES	(0x4 << 8)
+#define PORT_LOGIC_LINK_WIDTH_8_LANES	(0x8 << 8)
 
 #define PCIE_MSI_ADDR_LO		0x820
 #define PCIE_MSI_ADDR_HI		0x824
@@ -150,6 +152,21 @@ static int dw_pcie_wr_own_conf(struct pcie_port *pp, int where, int size,
 	return ret;
 }
 
+static void dw_pcie_prog_outbound_atu(struct pcie_port *pp, int index,
+		int type, u64 cpu_addr, u64 pci_addr, u32 size)
+{
+	dw_pcie_writel_rc(pp, PCIE_ATU_REGION_OUTBOUND | index,
+			  PCIE_ATU_VIEWPORT);
+	dw_pcie_writel_rc(pp, lower_32_bits(cpu_addr), PCIE_ATU_LOWER_BASE);
+	dw_pcie_writel_rc(pp, upper_32_bits(cpu_addr), PCIE_ATU_UPPER_BASE);
+	dw_pcie_writel_rc(pp, lower_32_bits(cpu_addr + size - 1),
+			  PCIE_ATU_LIMIT);
+	dw_pcie_writel_rc(pp, lower_32_bits(pci_addr), PCIE_ATU_LOWER_TARGET);
+	dw_pcie_writel_rc(pp, upper_32_bits(pci_addr), PCIE_ATU_UPPER_TARGET);
+	dw_pcie_writel_rc(pp, type, PCIE_ATU_CR1);
+	dw_pcie_writel_rc(pp, PCIE_ATU_ENABLE, PCIE_ATU_CR2);
+}
+
 static struct irq_chip dw_msi_irq_chip = {
 	.name = "PCI-MSI",
 	.irq_enable = pci_msi_unmask_irq,
@@ -493,6 +510,11 @@ int dw_pcie_host_init(struct pcie_port *pp)
 	if (pp->ops->host_init)
 		pp->ops->host_init(pp);
 
+	if (!pp->ops->rd_other_conf)
+		dw_pcie_prog_outbound_atu(pp, PCIE_ATU_REGION_INDEX1,
+					  PCIE_ATU_TYPE_MEM, pp->mem_mod_base,
+					  pp->mem_bus_addr, pp->mem_size);
+
 	dw_pcie_wr_own_conf(pp, PCI_BASE_ADDRESS_0, 4, 0);
 
 	/* program correct class for RC */
@@ -515,115 +537,73 @@ int dw_pcie_host_init(struct pcie_port *pp)
 	return 0;
 }
 
-static void dw_pcie_prog_viewport_cfg0(struct pcie_port *pp, u32 busdev)
-{
-	/* Program viewport 0 : OUTBOUND : CFG0 */
-	dw_pcie_writel_rc(pp, PCIE_ATU_REGION_OUTBOUND | PCIE_ATU_REGION_INDEX0,
-			  PCIE_ATU_VIEWPORT);
-	dw_pcie_writel_rc(pp, pp->cfg0_mod_base, PCIE_ATU_LOWER_BASE);
-	dw_pcie_writel_rc(pp, (pp->cfg0_mod_base >> 32), PCIE_ATU_UPPER_BASE);
-	dw_pcie_writel_rc(pp, pp->cfg0_mod_base + pp->cfg0_size - 1,
-			  PCIE_ATU_LIMIT);
-	dw_pcie_writel_rc(pp, busdev, PCIE_ATU_LOWER_TARGET);
-	dw_pcie_writel_rc(pp, 0, PCIE_ATU_UPPER_TARGET);
-	dw_pcie_writel_rc(pp, PCIE_ATU_TYPE_CFG0, PCIE_ATU_CR1);
-	dw_pcie_writel_rc(pp, PCIE_ATU_ENABLE, PCIE_ATU_CR2);
-}
-
-static void dw_pcie_prog_viewport_cfg1(struct pcie_port *pp, u32 busdev)
-{
-	/* Program viewport 1 : OUTBOUND : CFG1 */
-	dw_pcie_writel_rc(pp, PCIE_ATU_REGION_OUTBOUND | PCIE_ATU_REGION_INDEX1,
-			  PCIE_ATU_VIEWPORT);
-	dw_pcie_writel_rc(pp, PCIE_ATU_TYPE_CFG1, PCIE_ATU_CR1);
-	dw_pcie_writel_rc(pp, pp->cfg1_mod_base, PCIE_ATU_LOWER_BASE);
-	dw_pcie_writel_rc(pp, (pp->cfg1_mod_base >> 32), PCIE_ATU_UPPER_BASE);
-	dw_pcie_writel_rc(pp, pp->cfg1_mod_base + pp->cfg1_size - 1,
-			  PCIE_ATU_LIMIT);
-	dw_pcie_writel_rc(pp, busdev, PCIE_ATU_LOWER_TARGET);
-	dw_pcie_writel_rc(pp, 0, PCIE_ATU_UPPER_TARGET);
-	dw_pcie_writel_rc(pp, PCIE_ATU_ENABLE, PCIE_ATU_CR2);
-}
-
-static void dw_pcie_prog_viewport_mem_outbound(struct pcie_port *pp)
-{
-	/* Program viewport 0 : OUTBOUND : MEM */
-	dw_pcie_writel_rc(pp, PCIE_ATU_REGION_OUTBOUND | PCIE_ATU_REGION_INDEX0,
-			  PCIE_ATU_VIEWPORT);
-	dw_pcie_writel_rc(pp, PCIE_ATU_TYPE_MEM, PCIE_ATU_CR1);
-	dw_pcie_writel_rc(pp, pp->mem_mod_base, PCIE_ATU_LOWER_BASE);
-	dw_pcie_writel_rc(pp, (pp->mem_mod_base >> 32), PCIE_ATU_UPPER_BASE);
-	dw_pcie_writel_rc(pp, pp->mem_mod_base + pp->mem_size - 1,
-			  PCIE_ATU_LIMIT);
-	dw_pcie_writel_rc(pp, pp->mem_bus_addr, PCIE_ATU_LOWER_TARGET);
-	dw_pcie_writel_rc(pp, upper_32_bits(pp->mem_bus_addr),
-			  PCIE_ATU_UPPER_TARGET);
-	dw_pcie_writel_rc(pp, PCIE_ATU_ENABLE, PCIE_ATU_CR2);
-}
-
-static void dw_pcie_prog_viewport_io_outbound(struct pcie_port *pp)
-{
-	/* Program viewport 1 : OUTBOUND : IO */
-	dw_pcie_writel_rc(pp, PCIE_ATU_REGION_OUTBOUND | PCIE_ATU_REGION_INDEX1,
-			  PCIE_ATU_VIEWPORT);
-	dw_pcie_writel_rc(pp, PCIE_ATU_TYPE_IO, PCIE_ATU_CR1);
-	dw_pcie_writel_rc(pp, pp->io_mod_base, PCIE_ATU_LOWER_BASE);
-	dw_pcie_writel_rc(pp, (pp->io_mod_base >> 32), PCIE_ATU_UPPER_BASE);
-	dw_pcie_writel_rc(pp, pp->io_mod_base + pp->io_size - 1,
-			  PCIE_ATU_LIMIT);
-	dw_pcie_writel_rc(pp, pp->io_bus_addr, PCIE_ATU_LOWER_TARGET);
-	dw_pcie_writel_rc(pp, upper_32_bits(pp->io_bus_addr),
-			  PCIE_ATU_UPPER_TARGET);
-	dw_pcie_writel_rc(pp, PCIE_ATU_ENABLE, PCIE_ATU_CR2);
-}
-
 static int dw_pcie_rd_other_conf(struct pcie_port *pp, struct pci_bus *bus,
 		u32 devfn, int where, int size, u32 *val)
 {
-	int ret = PCIBIOS_SUCCESSFUL;
-	u32 address, busdev;
+	int ret, type;
+	u32 address, busdev, cfg_size;
+	u64 cpu_addr;
+	void __iomem *va_cfg_base;
 
 	busdev = PCIE_ATU_BUS(bus->number) | PCIE_ATU_DEV(PCI_SLOT(devfn)) |
 		 PCIE_ATU_FUNC(PCI_FUNC(devfn));
 	address = where & ~0x3;
 
 	if (bus->parent->number == pp->root_bus_nr) {
-		dw_pcie_prog_viewport_cfg0(pp, busdev);
-		ret = dw_pcie_cfg_read(pp->va_cfg0_base + address, where, size,
-				val);
-		dw_pcie_prog_viewport_mem_outbound(pp);
+		type = PCIE_ATU_TYPE_CFG0;
+		cpu_addr = pp->cfg0_mod_base;
+		cfg_size = pp->cfg0_size;
+		va_cfg_base = pp->va_cfg0_base;
 	} else {
-		dw_pcie_prog_viewport_cfg1(pp, busdev);
-		ret = dw_pcie_cfg_read(pp->va_cfg1_base + address, where, size,
-				val);
-		dw_pcie_prog_viewport_io_outbound(pp);
+		type = PCIE_ATU_TYPE_CFG1;
+		cpu_addr = pp->cfg1_mod_base;
+		cfg_size = pp->cfg1_size;
+		va_cfg_base = pp->va_cfg1_base;
 	}
 
+	dw_pcie_prog_outbound_atu(pp, PCIE_ATU_REGION_INDEX0,
+				  type, cpu_addr,
+				  busdev, cfg_size);
+	ret = dw_pcie_cfg_read(va_cfg_base + address, where, size, val);
+	dw_pcie_prog_outbound_atu(pp, PCIE_ATU_REGION_INDEX0,
+				  PCIE_ATU_TYPE_IO, pp->io_mod_base,
+				  pp->io_bus_addr, pp->io_size);
+
 	return ret;
 }
 
 static int dw_pcie_wr_other_conf(struct pcie_port *pp, struct pci_bus *bus,
 		u32 devfn, int where, int size, u32 val)
 {
-	int ret = PCIBIOS_SUCCESSFUL;
-	u32 address, busdev;
+	int ret, type;
+	u32 address, busdev, cfg_size;
+	u64 cpu_addr;
+	void __iomem *va_cfg_base;
 
 	busdev = PCIE_ATU_BUS(bus->number) | PCIE_ATU_DEV(PCI_SLOT(devfn)) |
 		 PCIE_ATU_FUNC(PCI_FUNC(devfn));
 	address = where & ~0x3;
 
 	if (bus->parent->number == pp->root_bus_nr) {
-		dw_pcie_prog_viewport_cfg0(pp, busdev);
-		ret = dw_pcie_cfg_write(pp->va_cfg0_base + address, where, size,
-				val);
-		dw_pcie_prog_viewport_mem_outbound(pp);
+		type = PCIE_ATU_TYPE_CFG0;
+		cpu_addr = pp->cfg0_mod_base;
+		cfg_size = pp->cfg0_size;
+		va_cfg_base = pp->va_cfg0_base;
 	} else {
-		dw_pcie_prog_viewport_cfg1(pp, busdev);
-		ret = dw_pcie_cfg_write(pp->va_cfg1_base + address, where, size,
-				val);
-		dw_pcie_prog_viewport_io_outbound(pp);
+		type = PCIE_ATU_TYPE_CFG1;
+		cpu_addr = pp->cfg1_mod_base;
+		cfg_size = pp->cfg1_size;
+		va_cfg_base = pp->va_cfg1_base;
 	}
 
+	dw_pcie_prog_outbound_atu(pp, PCIE_ATU_REGION_INDEX0,
+				  type, cpu_addr,
+				  busdev, cfg_size);
+	ret = dw_pcie_cfg_write(va_cfg_base + address, where, size, val);
+	dw_pcie_prog_outbound_atu(pp, PCIE_ATU_REGION_INDEX0,
+				  PCIE_ATU_TYPE_IO, pp->io_mod_base,
+				  pp->io_bus_addr, pp->io_size);
+
 	return ret;
 }
 
@@ -728,13 +708,11 @@ static struct pci_bus *dw_pcie_scan_bus(int nr, struct pci_sys_data *sys)
 	struct pcie_port *pp = sys_to_pcie(sys);
 
 	pp->root_bus_nr = sys->busnr;
-	bus = pci_create_root_bus(pp->dev, sys->busnr,
+	bus = pci_scan_root_bus(pp->dev, sys->busnr,
 				  &dw_pcie_ops, sys, &sys->resources);
 	if (!bus)
 		return NULL;
 
-	pci_scan_child_bus(bus);
-
 	if (bus && pp->ops->scan_bus)
 		pp->ops->scan_bus(pp);
 
@@ -778,6 +756,9 @@ void dw_pcie_setup_rc(struct pcie_port *pp)
 	case 4:
 		val |= PORT_LINK_MODE_4_LANES;
 		break;
+	case 8:
+		val |= PORT_LINK_MODE_8_LANES;
+		break;
 	}
 	dw_pcie_writel_rc(pp, val, PCIE_PORT_LINK_CONTROL);
 
@@ -794,6 +775,9 @@ void dw_pcie_setup_rc(struct pcie_port *pp)
 	case 4:
 		val |= PORT_LOGIC_LINK_WIDTH_4_LANES;
 		break;
+	case 8:
+		val |= PORT_LOGIC_LINK_WIDTH_8_LANES;
+		break;
 	}
 	dw_pcie_writel_rc(pp, val, PCIE_LINK_WIDTH_SPEED_CONTROL);
 
diff --git a/drivers/pci/host/pcie-iproc-bcma.c b/drivers/pci/host/pcie-iproc-bcma.c
new file mode 100644
index 000000000000..96a7d999fd5e
--- /dev/null
+++ b/drivers/pci/host/pcie-iproc-bcma.c
@@ -0,0 +1,110 @@
+/*
+ * Copyright (C) 2015 Broadcom Corporation
+ * Copyright (C) 2015 Hauke Mehrtens <hauke@hauke-m.de>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/phy/phy.h>
+#include <linux/bcma/bcma.h>
+#include <linux/ioport.h>
+
+#include "pcie-iproc.h"
+
+
+/* NS: CLASS field is R/O, and set to wrong 0x200 value */
+static void bcma_pcie2_fixup_class(struct pci_dev *dev)
+{
+	dev->class = PCI_CLASS_BRIDGE_PCI << 8;
+}
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0x8011, bcma_pcie2_fixup_class);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0x8012, bcma_pcie2_fixup_class);
+
+static int iproc_pcie_bcma_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+{
+	struct pci_sys_data *sys = dev->sysdata;
+	struct iproc_pcie *pcie = sys->private_data;
+	struct bcma_device *bdev = container_of(pcie->dev, struct bcma_device, dev);
+
+	return bcma_core_irq(bdev, 5);
+}
+
+static int iproc_pcie_bcma_probe(struct bcma_device *bdev)
+{
+	struct iproc_pcie *pcie;
+	LIST_HEAD(res);
+	struct resource res_mem;
+	int ret;
+
+	pcie = devm_kzalloc(&bdev->dev, sizeof(*pcie), GFP_KERNEL);
+	if (!pcie)
+		return -ENOMEM;
+
+	pcie->dev = &bdev->dev;
+	bcma_set_drvdata(bdev, pcie);
+
+	pcie->base = bdev->io_addr;
+
+	res_mem.start = bdev->addr_s[0];
+	res_mem.end = bdev->addr_s[0] + SZ_128M - 1;
+	res_mem.name = "PCIe MEM space";
+	res_mem.flags = IORESOURCE_MEM;
+	pci_add_resource(&res, &res_mem);
+
+	pcie->map_irq = iproc_pcie_bcma_map_irq;
+
+	ret = iproc_pcie_setup(pcie, &res);
+	if (ret)
+		dev_err(pcie->dev, "PCIe controller setup failed\n");
+
+	pci_free_resource_list(&res);
+
+	return ret;
+}
+
+static void iproc_pcie_bcma_remove(struct bcma_device *bdev)
+{
+	struct iproc_pcie *pcie = bcma_get_drvdata(bdev);
+
+	iproc_pcie_remove(pcie);
+}
+
+static const struct bcma_device_id iproc_pcie_bcma_table[] = {
+	BCMA_CORE(BCMA_MANUF_BCM, BCMA_CORE_NS_PCIEG2, BCMA_ANY_REV, BCMA_ANY_CLASS),
+	{},
+};
+MODULE_DEVICE_TABLE(bcma, iproc_pcie_bcma_table);
+
+static struct bcma_driver iproc_pcie_bcma_driver = {
+	.name		= KBUILD_MODNAME,
+	.id_table	= iproc_pcie_bcma_table,
+	.probe		= iproc_pcie_bcma_probe,
+	.remove		= iproc_pcie_bcma_remove,
+};
+
+static int __init iproc_pcie_bcma_init(void)
+{
+	return bcma_driver_register(&iproc_pcie_bcma_driver);
+}
+module_init(iproc_pcie_bcma_init);
+
+static void __exit iproc_pcie_bcma_exit(void)
+{
+	bcma_driver_unregister(&iproc_pcie_bcma_driver);
+}
+module_exit(iproc_pcie_bcma_exit);
+
+MODULE_AUTHOR("Hauke Mehrtens");
+MODULE_DESCRIPTION("Broadcom iProc PCIe BCMA driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/pci/host/pcie-iproc-platform.c b/drivers/pci/host/pcie-iproc-platform.c
index afad6c21fcfa..9aedc8eb2c6e 100644
--- a/drivers/pci/host/pcie-iproc-platform.c
+++ b/drivers/pci/host/pcie-iproc-platform.c
@@ -69,15 +69,15 @@ static int iproc_pcie_pltfm_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	pcie->resources = &res;
+	pcie->map_irq = of_irq_parse_and_map_pci;
 
-	ret = iproc_pcie_setup(pcie);
-	if (ret) {
+	ret = iproc_pcie_setup(pcie, &res);
+	if (ret)
 		dev_err(pcie->dev, "PCIe controller setup failed\n");
-		return ret;
-	}
 
-	return 0;
+	pci_free_resource_list(&res);
+
+	return ret;
 }
 
 static int iproc_pcie_pltfm_remove(struct platform_device *pdev)
diff --git a/drivers/pci/host/pcie-iproc.c b/drivers/pci/host/pcie-iproc.c
index 329e1b54528b..d77481ea553e 100644
--- a/drivers/pci/host/pcie-iproc.c
+++ b/drivers/pci/host/pcie-iproc.c
@@ -183,7 +183,7 @@ static void iproc_pcie_enable(struct iproc_pcie *pcie)
 	writel(SYS_RC_INTX_MASK, pcie->base + SYS_RC_INTX_EN);
 }
 
-int iproc_pcie_setup(struct iproc_pcie *pcie)
+int iproc_pcie_setup(struct iproc_pcie *pcie, struct list_head *res)
 {
 	int ret;
 	struct pci_bus *bus;
@@ -211,7 +211,7 @@ int iproc_pcie_setup(struct iproc_pcie *pcie)
 	pcie->sysdata.private_data = pcie;
 
 	bus = pci_create_root_bus(pcie->dev, 0, &iproc_pcie_ops,
-				  &pcie->sysdata, pcie->resources);
+				  &pcie->sysdata, res);
 	if (!bus) {
 		dev_err(pcie->dev, "unable to create PCI root bus\n");
 		ret = -ENOMEM;
@@ -229,7 +229,7 @@ int iproc_pcie_setup(struct iproc_pcie *pcie)
 
 	pci_scan_child_bus(bus);
 	pci_assign_unassigned_bus_resources(bus);
-	pci_fixup_irqs(pci_common_swizzle, of_irq_parse_and_map_pci);
+	pci_fixup_irqs(pci_common_swizzle, pcie->map_irq);
 	pci_bus_add_devices(bus);
 
 	return 0;
diff --git a/drivers/pci/host/pcie-iproc.h b/drivers/pci/host/pcie-iproc.h
index e28075ed1856..ba0a108309cc 100644
--- a/drivers/pci/host/pcie-iproc.h
+++ b/drivers/pci/host/pcie-iproc.h
@@ -29,14 +29,14 @@
 struct iproc_pcie {
 	struct device *dev;
 	void __iomem *base;
-	struct list_head *resources;
 	struct pci_sys_data sysdata;
 	struct pci_bus *root_bus;
 	struct phy *phy;
 	int irqs[IPROC_PCIE_MAX_NUM_IRQS];
+	int (*map_irq)(const struct pci_dev *, u8, u8);
 };
 
-int iproc_pcie_setup(struct iproc_pcie *pcie);
+int iproc_pcie_setup(struct iproc_pcie *pcie, struct list_head *res);
 int iproc_pcie_remove(struct iproc_pcie *pcie);
 
 #endif /* _PCIE_IPROC_H */
diff --git a/drivers/pci/host/pcie-spear13xx.c b/drivers/pci/host/pcie-spear13xx.c
index 020d78890719..dfec4281bd50 100644
--- a/drivers/pci/host/pcie-spear13xx.c
+++ b/drivers/pci/host/pcie-spear13xx.c
@@ -146,10 +146,10 @@ struct pcie_app_reg {
 static int spear13xx_pcie_establish_link(struct pcie_port *pp)
 {
 	u32 val;
-	int count = 0;
 	struct spear13xx_pcie *spear13xx_pcie = to_spear13xx_pcie(pp);
 	struct pcie_app_reg *app_reg = spear13xx_pcie->app_base;
 	u32 exp_cap_off = EXP_CAP_ID_OFFSET;
+	unsigned int retries;
 
 	if (dw_pcie_link_up(pp)) {
 		dev_err(pp->dev, "link already up\n");
@@ -201,17 +201,16 @@ static int spear13xx_pcie_establish_link(struct pcie_port *pp)
 			&app_reg->app_ctrl_0);
 
 	/* check if the link is up or not */
-	while (!dw_pcie_link_up(pp)) {
-		mdelay(100);
-		count++;
-		if (count == 10) {
-			dev_err(pp->dev, "link Fail\n");
-			return -EINVAL;
+	for (retries = 0; retries < 10; retries++) {
+		if (dw_pcie_link_up(pp)) {
+			dev_info(pp->dev, "link up\n");
+			return 0;
 		}
+		mdelay(100);
 	}
-	dev_info(pp->dev, "link up\n");
 
-	return 0;
+	dev_err(pp->dev, "link Fail\n");
+	return -EINVAL;
 }
 
 static irqreturn_t spear13xx_pcie_irq_handler(int irq, void *arg)
diff --git a/drivers/pci/hotplug/Makefile b/drivers/pci/hotplug/Makefile
index 4a9aa08b08f1..b616e7588ff4 100644
--- a/drivers/pci/hotplug/Makefile
+++ b/drivers/pci/hotplug/Makefile
@@ -61,9 +61,6 @@ pciehp-objs		:=	pciehp_core.o	\
 				pciehp_ctrl.o	\
 				pciehp_pci.o	\
 				pciehp_hpc.o
-ifdef CONFIG_ACPI
-pciehp-objs		+=	pciehp_acpi.o
-endif
 
 shpchp-objs		:=	shpchp_core.o	\
 				shpchp_ctrl.o	\
diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c
index bcb90e4888dd..ff538568a617 100644
--- a/drivers/pci/hotplug/acpiphp_glue.c
+++ b/drivers/pci/hotplug/acpiphp_glue.c
@@ -632,15 +632,14 @@ static void trim_stale_devices(struct pci_dev *dev)
 {
 	struct acpi_device *adev = ACPI_COMPANION(&dev->dev);
 	struct pci_bus *bus = dev->subordinate;
-	bool alive = false;
+	bool alive = dev->ignore_hotplug;
 
 	if (adev) {
 		acpi_status status;
 		unsigned long long sta;
 
 		status = acpi_evaluate_integer(adev->handle, "_STA", NULL, &sta);
-		alive = (ACPI_SUCCESS(status) && device_status_valid(sta))
-			|| dev->ignore_hotplug;
+		alive = alive || (ACPI_SUCCESS(status) && device_status_valid(sta));
 	}
 	if (!alive)
 		alive = pci_device_is_present(dev);
diff --git a/drivers/pci/hotplug/pciehp.h b/drivers/pci/hotplug/pciehp.h
index b11521953485..57cd1327346f 100644
--- a/drivers/pci/hotplug/pciehp.h
+++ b/drivers/pci/hotplug/pciehp.h
@@ -132,11 +132,7 @@ struct controller {
 
 int pciehp_sysfs_enable_slot(struct slot *slot);
 int pciehp_sysfs_disable_slot(struct slot *slot);
-u8 pciehp_handle_attention_button(struct slot *p_slot);
-u8 pciehp_handle_switch_change(struct slot *p_slot);
-u8 pciehp_handle_presence_change(struct slot *p_slot);
-u8 pciehp_handle_power_fault(struct slot *p_slot);
-void pciehp_handle_linkstate_change(struct slot *p_slot);
+void pciehp_queue_interrupt_event(struct slot *slot, u32 event_type);
 int pciehp_configure_device(struct slot *p_slot);
 int pciehp_unconfigure_device(struct slot *p_slot);
 void pciehp_queue_pushbutton_work(struct work_struct *work);
@@ -167,21 +163,4 @@ static inline const char *slot_name(struct slot *slot)
 	return hotplug_slot_name(slot->hotplug_slot);
 }
 
-#ifdef CONFIG_ACPI
-#include <linux/pci-acpi.h>
-
-void __init pciehp_acpi_slot_detection_init(void);
-int pciehp_acpi_slot_detection_check(struct pci_dev *dev);
-
-static inline void pciehp_firmware_init(void)
-{
-	pciehp_acpi_slot_detection_init();
-}
-#else
-#define pciehp_firmware_init()				do {} while (0)
-static inline int pciehp_acpi_slot_detection_check(struct pci_dev *dev)
-{
-	return 0;
-}
-#endif				/* CONFIG_ACPI */
 #endif				/* _PCIEHP_H */
diff --git a/drivers/pci/hotplug/pciehp_acpi.c b/drivers/pci/hotplug/pciehp_acpi.c
deleted file mode 100644
index 93cc9266e8cb..000000000000
--- a/drivers/pci/hotplug/pciehp_acpi.c
+++ /dev/null
@@ -1,137 +0,0 @@
-/*
- * ACPI related functions for PCI Express Hot Plug driver.
- *
- * Copyright (C) 2008 Kenji Kaneshige
- * Copyright (C) 2008 Fujitsu Limited.
- *
- * All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or (at
- * your option) any later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
- * NON INFRINGEMENT.  See the GNU General Public License for more
- * details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-
-#include <linux/acpi.h>
-#include <linux/pci.h>
-#include <linux/pci_hotplug.h>
-#include <linux/slab.h>
-#include <linux/module.h>
-#include "pciehp.h"
-
-#define PCIEHP_DETECT_PCIE	(0)
-#define PCIEHP_DETECT_ACPI	(1)
-#define PCIEHP_DETECT_AUTO	(2)
-#define PCIEHP_DETECT_DEFAULT	PCIEHP_DETECT_AUTO
-
-struct dummy_slot {
-	u32 number;
-	struct list_head list;
-};
-
-static int slot_detection_mode;
-static char *pciehp_detect_mode;
-module_param(pciehp_detect_mode, charp, 0444);
-MODULE_PARM_DESC(pciehp_detect_mode,
-	 "Slot detection mode: pcie, acpi, auto\n"
-	 "  pcie          - Use PCIe based slot detection\n"
-	 "  acpi          - Use ACPI for slot detection\n"
-	 "  auto(default) - Auto select mode. Use acpi option if duplicate\n"
-	 "                  slot ids are found. Otherwise, use pcie option\n");
-
-int pciehp_acpi_slot_detection_check(struct pci_dev *dev)
-{
-	if (slot_detection_mode != PCIEHP_DETECT_ACPI)
-		return 0;
-	if (acpi_pci_detect_ejectable(ACPI_HANDLE(&dev->dev)))
-		return 0;
-	return -ENODEV;
-}
-
-static int __init parse_detect_mode(void)
-{
-	if (!pciehp_detect_mode)
-		return PCIEHP_DETECT_DEFAULT;
-	if (!strcmp(pciehp_detect_mode, "pcie"))
-		return PCIEHP_DETECT_PCIE;
-	if (!strcmp(pciehp_detect_mode, "acpi"))
-		return PCIEHP_DETECT_ACPI;
-	if (!strcmp(pciehp_detect_mode, "auto"))
-		return PCIEHP_DETECT_AUTO;
-	warn("bad specifier '%s' for pciehp_detect_mode. Use default\n",
-	     pciehp_detect_mode);
-	return PCIEHP_DETECT_DEFAULT;
-}
-
-static int __initdata dup_slot_id;
-static int __initdata acpi_slot_detected;
-static struct list_head __initdata dummy_slots = LIST_HEAD_INIT(dummy_slots);
-
-/* Dummy driver for duplicate name detection */
-static int __init dummy_probe(struct pcie_device *dev)
-{
-	u32 slot_cap;
-	acpi_handle handle;
-	struct dummy_slot *slot, *tmp;
-	struct pci_dev *pdev = dev->port;
-
-	pcie_capability_read_dword(pdev, PCI_EXP_SLTCAP, &slot_cap);
-	slot = kzalloc(sizeof(*slot), GFP_KERNEL);
-	if (!slot)
-		return -ENOMEM;
-	slot->number = (slot_cap & PCI_EXP_SLTCAP_PSN) >> 19;
-	list_for_each_entry(tmp, &dummy_slots, list) {
-		if (tmp->number == slot->number)
-			dup_slot_id++;
-	}
-	list_add_tail(&slot->list, &dummy_slots);
-	handle = ACPI_HANDLE(&pdev->dev);
-	if (!acpi_slot_detected && acpi_pci_detect_ejectable(handle))
-		acpi_slot_detected = 1;
-	return -ENODEV;         /* dummy driver always returns error */
-}
-
-static struct pcie_port_service_driver __initdata dummy_driver = {
-	.name		= "pciehp_dummy",
-	.port_type	= PCIE_ANY_PORT,
-	.service	= PCIE_PORT_SERVICE_HP,
-	.probe		= dummy_probe,
-};
-
-static int __init select_detection_mode(void)
-{
-	struct dummy_slot *slot, *tmp;
-
-	if (pcie_port_service_register(&dummy_driver))
-		return PCIEHP_DETECT_ACPI;
-	pcie_port_service_unregister(&dummy_driver);
-	list_for_each_entry_safe(slot, tmp, &dummy_slots, list) {
-		list_del(&slot->list);
-		kfree(slot);
-	}
-	if (acpi_slot_detected && dup_slot_id)
-		return PCIEHP_DETECT_ACPI;
-	return PCIEHP_DETECT_PCIE;
-}
-
-void __init pciehp_acpi_slot_detection_init(void)
-{
-	slot_detection_mode = parse_detect_mode();
-	if (slot_detection_mode != PCIEHP_DETECT_AUTO)
-		goto out;
-	slot_detection_mode = select_detection_mode();
-out:
-	if (slot_detection_mode == PCIEHP_DETECT_ACPI)
-		info("Using ACPI for slot detection.\n");
-}
diff --git a/drivers/pci/hotplug/pciehp_core.c b/drivers/pci/hotplug/pciehp_core.c
index 07aa722bb12c..612b21a14df5 100644
--- a/drivers/pci/hotplug/pciehp_core.c
+++ b/drivers/pci/hotplug/pciehp_core.c
@@ -77,11 +77,6 @@ static int reset_slot		(struct hotplug_slot *slot, int probe);
  */
 static void release_slot(struct hotplug_slot *hotplug_slot)
 {
-	struct slot *slot = hotplug_slot->private;
-
-	ctrl_dbg(slot->ctrl, "%s: physical_slot = %s\n",
-		 __func__, hotplug_slot_name(hotplug_slot));
-
 	kfree(hotplug_slot->ops);
 	kfree(hotplug_slot->info);
 	kfree(hotplug_slot);
@@ -129,14 +124,10 @@ static int init_slot(struct controller *ctrl)
 	slot->hotplug_slot = hotplug;
 	snprintf(name, SLOT_NAME_SIZE, "%u", PSN(ctrl));
 
-	ctrl_dbg(ctrl, "Registering domain:bus:dev=%04x:%02x:00 sun=%x\n",
-		 pci_domain_nr(ctrl->pcie->port->subordinate),
-		 ctrl->pcie->port->subordinate->number, PSN(ctrl));
 	retval = pci_hp_register(hotplug,
 				 ctrl->pcie->port->subordinate, 0, name);
 	if (retval)
-		ctrl_err(ctrl,
-			 "pci_hp_register failed with error %d\n", retval);
+		ctrl_err(ctrl, "pci_hp_register failed: error %d\n", retval);
 out:
 	if (retval) {
 		kfree(ops);
@@ -158,9 +149,6 @@ static int set_attention_status(struct hotplug_slot *hotplug_slot, u8 status)
 {
 	struct slot *slot = hotplug_slot->private;
 
-	ctrl_dbg(slot->ctrl, "%s: physical_slot = %s\n",
-		  __func__, slot_name(slot));
-
 	pciehp_set_attention_status(slot, status);
 	return 0;
 }
@@ -170,9 +158,6 @@ static int enable_slot(struct hotplug_slot *hotplug_slot)
 {
 	struct slot *slot = hotplug_slot->private;
 
-	ctrl_dbg(slot->ctrl, "%s: physical_slot = %s\n",
-		 __func__, slot_name(slot));
-
 	return pciehp_sysfs_enable_slot(slot);
 }
 
@@ -181,9 +166,6 @@ static int disable_slot(struct hotplug_slot *hotplug_slot)
 {
 	struct slot *slot = hotplug_slot->private;
 
-	ctrl_dbg(slot->ctrl, "%s: physical_slot = %s\n",
-		  __func__, slot_name(slot));
-
 	return pciehp_sysfs_disable_slot(slot);
 }
 
@@ -191,9 +173,6 @@ static int get_power_status(struct hotplug_slot *hotplug_slot, u8 *value)
 {
 	struct slot *slot = hotplug_slot->private;
 
-	ctrl_dbg(slot->ctrl, "%s: physical_slot = %s\n",
-		  __func__, slot_name(slot));
-
 	pciehp_get_power_status(slot, value);
 	return 0;
 }
@@ -202,9 +181,6 @@ static int get_attention_status(struct hotplug_slot *hotplug_slot, u8 *value)
 {
 	struct slot *slot = hotplug_slot->private;
 
-	ctrl_dbg(slot->ctrl, "%s: physical_slot = %s\n",
-		  __func__, slot_name(slot));
-
 	pciehp_get_attention_status(slot, value);
 	return 0;
 }
@@ -213,9 +189,6 @@ static int get_latch_status(struct hotplug_slot *hotplug_slot, u8 *value)
 {
 	struct slot *slot = hotplug_slot->private;
 
-	ctrl_dbg(slot->ctrl, "%s: physical_slot = %s\n",
-		 __func__, slot_name(slot));
-
 	pciehp_get_latch_status(slot, value);
 	return 0;
 }
@@ -224,9 +197,6 @@ static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value)
 {
 	struct slot *slot = hotplug_slot->private;
 
-	ctrl_dbg(slot->ctrl, "%s: physical_slot = %s\n",
-		 __func__, slot_name(slot));
-
 	pciehp_get_adapter_status(slot, value);
 	return 0;
 }
@@ -235,9 +205,6 @@ static int reset_slot(struct hotplug_slot *hotplug_slot, int probe)
 {
 	struct slot *slot = hotplug_slot->private;
 
-	ctrl_dbg(slot->ctrl, "%s: physical_slot = %s\n",
-		 __func__, slot_name(slot));
-
 	return pciehp_reset_slot(slot, probe);
 }
 
@@ -248,24 +215,21 @@ static int pciehp_probe(struct pcie_device *dev)
 	struct slot *slot;
 	u8 occupied, poweron;
 
-	if (pciehp_force)
-		dev_info(&dev->device,
-			 "Bypassing BIOS check for pciehp use on %s\n",
-			 pci_name(dev->port));
-	else if (pciehp_acpi_slot_detection_check(dev->port))
-		goto err_out_none;
+	/* If this is not a "hotplug" service, we have no business here. */
+	if (dev->service != PCIE_PORT_SERVICE_HP)
+		return -ENODEV;
 
 	if (!dev->port->subordinate) {
 		/* Can happen if we run out of bus numbers during probe */
 		dev_err(&dev->device,
 			"Hotplug bridge without secondary bus, ignoring\n");
-		goto err_out_none;
+		return -ENODEV;
 	}
 
 	ctrl = pcie_init(dev);
 	if (!ctrl) {
 		dev_err(&dev->device, "Controller initialization failed\n");
-		goto err_out_none;
+		return -ENODEV;
 	}
 	set_service_data(dev, ctrl);
 
@@ -275,14 +239,14 @@ static int pciehp_probe(struct pcie_device *dev)
 		if (rc == -EBUSY)
 			ctrl_warn(ctrl, "Slot already registered by another hotplug driver\n");
 		else
-			ctrl_err(ctrl, "Slot initialization failed\n");
+			ctrl_err(ctrl, "Slot initialization failed (%d)\n", rc);
 		goto err_out_release_ctlr;
 	}
 
 	/* Enable events after we have setup the data structures */
 	rc = pcie_init_notification(ctrl);
 	if (rc) {
-		ctrl_err(ctrl, "Notification initialization failed\n");
+		ctrl_err(ctrl, "Notification initialization failed (%d)\n", rc);
 		goto err_out_free_ctrl_slot;
 	}
 
@@ -305,7 +269,6 @@ err_out_free_ctrl_slot:
 	cleanup_slot(ctrl);
 err_out_release_ctlr:
 	pciehp_release_ctrl(ctrl);
-err_out_none:
 	return -ENODEV;
 }
 
@@ -366,7 +329,6 @@ static int __init pcied_init(void)
 {
 	int retval = 0;
 
-	pciehp_firmware_init();
 	retval = pcie_port_service_register(&hpdriver_portdrv);
 	dbg("pcie_port_service_register = %d\n", retval);
 	info(DRIVER_DESC " version: " DRIVER_VERSION "\n");
diff --git a/drivers/pci/hotplug/pciehp_ctrl.c b/drivers/pci/hotplug/pciehp_ctrl.c
index f052e951b23e..f3796124ad7c 100644
--- a/drivers/pci/hotplug/pciehp_ctrl.c
+++ b/drivers/pci/hotplug/pciehp_ctrl.c
@@ -37,138 +37,20 @@
 
 static void interrupt_event_handler(struct work_struct *work);
 
-static int queue_interrupt_event(struct slot *p_slot, u32 event_type)
+void pciehp_queue_interrupt_event(struct slot *p_slot, u32 event_type)
 {
 	struct event_info *info;
 
 	info = kmalloc(sizeof(*info), GFP_ATOMIC);
-	if (!info)
-		return -ENOMEM;
+	if (!info) {
+		ctrl_err(p_slot->ctrl, "dropped event %d (ENOMEM)\n", event_type);
+		return;
+	}
 
+	INIT_WORK(&info->work, interrupt_event_handler);
 	info->event_type = event_type;
 	info->p_slot = p_slot;
-	INIT_WORK(&info->work, interrupt_event_handler);
-
 	queue_work(p_slot->wq, &info->work);
-
-	return 0;
-}
-
-u8 pciehp_handle_attention_button(struct slot *p_slot)
-{
-	u32 event_type;
-	struct controller *ctrl = p_slot->ctrl;
-
-	/* Attention Button Change */
-	ctrl_dbg(ctrl, "Attention button interrupt received\n");
-
-	/*
-	 *  Button pressed - See if need to TAKE ACTION!!!
-	 */
-	ctrl_info(ctrl, "Button pressed on Slot(%s)\n", slot_name(p_slot));
-	event_type = INT_BUTTON_PRESS;
-
-	queue_interrupt_event(p_slot, event_type);
-
-	return 0;
-}
-
-u8 pciehp_handle_switch_change(struct slot *p_slot)
-{
-	u8 getstatus;
-	u32 event_type;
-	struct controller *ctrl = p_slot->ctrl;
-
-	/* Switch Change */
-	ctrl_dbg(ctrl, "Switch interrupt received\n");
-
-	pciehp_get_latch_status(p_slot, &getstatus);
-	if (getstatus) {
-		/*
-		 * Switch opened
-		 */
-		ctrl_info(ctrl, "Latch open on Slot(%s)\n", slot_name(p_slot));
-		event_type = INT_SWITCH_OPEN;
-	} else {
-		/*
-		 *  Switch closed
-		 */
-		ctrl_info(ctrl, "Latch close on Slot(%s)\n", slot_name(p_slot));
-		event_type = INT_SWITCH_CLOSE;
-	}
-
-	queue_interrupt_event(p_slot, event_type);
-
-	return 1;
-}
-
-u8 pciehp_handle_presence_change(struct slot *p_slot)
-{
-	u32 event_type;
-	u8 presence_save;
-	struct controller *ctrl = p_slot->ctrl;
-
-	/* Presence Change */
-	ctrl_dbg(ctrl, "Presence/Notify input change\n");
-
-	/* Switch is open, assume a presence change
-	 * Save the presence state
-	 */
-	pciehp_get_adapter_status(p_slot, &presence_save);
-	if (presence_save) {
-		/*
-		 * Card Present
-		 */
-		ctrl_info(ctrl, "Card present on Slot(%s)\n", slot_name(p_slot));
-		event_type = INT_PRESENCE_ON;
-	} else {
-		/*
-		 * Not Present
-		 */
-		ctrl_info(ctrl, "Card not present on Slot(%s)\n",
-			  slot_name(p_slot));
-		event_type = INT_PRESENCE_OFF;
-	}
-
-	queue_interrupt_event(p_slot, event_type);
-
-	return 1;
-}
-
-u8 pciehp_handle_power_fault(struct slot *p_slot)
-{
-	u32 event_type;
-	struct controller *ctrl = p_slot->ctrl;
-
-	/* power fault */
-	ctrl_dbg(ctrl, "Power fault interrupt received\n");
-	ctrl_err(ctrl, "Power fault on slot %s\n", slot_name(p_slot));
-	event_type = INT_POWER_FAULT;
-	ctrl_info(ctrl, "Power fault bit %x set\n", 0);
-	queue_interrupt_event(p_slot, event_type);
-
-	return 1;
-}
-
-void pciehp_handle_linkstate_change(struct slot *p_slot)
-{
-	u32 event_type;
-	struct controller *ctrl = p_slot->ctrl;
-
-	/* Link Status Change */
-	ctrl_dbg(ctrl, "Data Link Layer State change\n");
-
-	if (pciehp_check_link_active(ctrl)) {
-		ctrl_info(ctrl, "slot(%s): Link Up event\n",
-			  slot_name(p_slot));
-		event_type = INT_LINK_UP;
-	} else {
-		ctrl_info(ctrl, "slot(%s): Link Down event\n",
-			  slot_name(p_slot));
-		event_type = INT_LINK_DOWN;
-	}
-
-	queue_interrupt_event(p_slot, event_type);
 }
 
 /* The following routines constitute the bulk of the
@@ -298,10 +180,6 @@ static void pciehp_power_thread(struct work_struct *work)
 
 	switch (info->req) {
 	case DISABLE_REQ:
-		ctrl_dbg(p_slot->ctrl,
-			 "Disabling domain:bus:device=%04x:%02x:00\n",
-			 pci_domain_nr(p_slot->ctrl->pcie->port->subordinate),
-			 p_slot->ctrl->pcie->port->subordinate->number);
 		mutex_lock(&p_slot->hotplug_lock);
 		pciehp_disable_slot(p_slot);
 		mutex_unlock(&p_slot->hotplug_lock);
@@ -310,10 +188,6 @@ static void pciehp_power_thread(struct work_struct *work)
 		mutex_unlock(&p_slot->lock);
 		break;
 	case ENABLE_REQ:
-		ctrl_dbg(p_slot->ctrl,
-			 "Enabling domain:bus:device=%04x:%02x:00\n",
-			 pci_domain_nr(p_slot->ctrl->pcie->port->subordinate),
-			 p_slot->ctrl->pcie->port->subordinate->number);
 		mutex_lock(&p_slot->hotplug_lock);
 		ret = pciehp_enable_slot(p_slot);
 		mutex_unlock(&p_slot->hotplug_lock);
@@ -416,7 +290,7 @@ static void handle_button_press_event(struct slot *p_slot)
 		ctrl_info(ctrl, "Button ignore on Slot(%s)\n", slot_name(p_slot));
 		break;
 	default:
-		ctrl_warn(ctrl, "Not a valid state\n");
+		ctrl_warn(ctrl, "ignoring invalid state %#x\n", p_slot->state);
 		break;
 	}
 }
@@ -507,8 +381,8 @@ static void handle_link_event(struct slot *p_slot, u32 event)
 		}
 		break;
 	default:
-		ctrl_err(ctrl, "Not a valid state on slot(%s)\n",
-			 slot_name(p_slot));
+		ctrl_err(ctrl, "ignoring invalid state %#x on slot(%s)\n",
+			 p_slot->state, slot_name(p_slot));
 		kfree(info);
 		break;
 	}
@@ -532,7 +406,6 @@ static void interrupt_event_handler(struct work_struct *work)
 		pciehp_green_led_off(p_slot);
 		break;
 	case INT_PRESENCE_ON:
-		ctrl_dbg(ctrl, "Surprise Insertion\n");
 		handle_surprise_event(p_slot);
 		break;
 	case INT_PRESENCE_OFF:
@@ -540,7 +413,6 @@ static void interrupt_event_handler(struct work_struct *work)
 		 * Regardless of surprise capability, we need to
 		 * definitely remove a card that has been pulled out!
 		 */
-		ctrl_dbg(ctrl, "Surprise Removal\n");
 		handle_surprise_event(p_slot);
 		break;
 	case INT_LINK_UP:
@@ -647,8 +519,8 @@ int pciehp_sysfs_enable_slot(struct slot *p_slot)
 			  slot_name(p_slot));
 		break;
 	default:
-		ctrl_err(ctrl, "Not a valid state on slot %s\n",
-			 slot_name(p_slot));
+		ctrl_err(ctrl, "invalid state %#x on slot %s\n",
+			 p_slot->state, slot_name(p_slot));
 		break;
 	}
 	mutex_unlock(&p_slot->lock);
@@ -682,8 +554,8 @@ int pciehp_sysfs_disable_slot(struct slot *p_slot)
 			  slot_name(p_slot));
 		break;
 	default:
-		ctrl_err(ctrl, "Not a valid state on slot %s\n",
-			 slot_name(p_slot));
+		ctrl_err(ctrl, "invalid state %#x on slot %s\n",
+			 p_slot->state, slot_name(p_slot));
 		break;
 	}
 	mutex_unlock(&p_slot->lock);
diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c
index 0ebf754fc177..2913f7e68a10 100644
--- a/drivers/pci/hotplug/pciehp_hpc.c
+++ b/drivers/pci/hotplug/pciehp_hpc.c
@@ -176,20 +176,17 @@ static void pcie_wait_cmd(struct controller *ctrl)
 			  jiffies_to_msecs(jiffies - ctrl->cmd_started));
 }
 
-/**
- * pcie_write_cmd - Issue controller command
- * @ctrl: controller to which the command is issued
- * @cmd:  command value written to slot control register
- * @mask: bitmask of slot control register to be modified
- */
-static void pcie_write_cmd(struct controller *ctrl, u16 cmd, u16 mask)
+static void pcie_do_write_cmd(struct controller *ctrl, u16 cmd,
+			      u16 mask, bool wait)
 {
 	struct pci_dev *pdev = ctrl_dev(ctrl);
 	u16 slot_ctrl;
 
 	mutex_lock(&ctrl->ctrl_lock);
 
-	/* Wait for any previous command that might still be in progress */
+	/*
+	 * Always wait for any previous command that might still be in progress
+	 */
 	pcie_wait_cmd(ctrl);
 
 	pcie_capability_read_word(pdev, PCI_EXP_SLTCTL, &slot_ctrl);
@@ -201,9 +198,33 @@ static void pcie_write_cmd(struct controller *ctrl, u16 cmd, u16 mask)
 	ctrl->cmd_started = jiffies;
 	ctrl->slot_ctrl = slot_ctrl;
 
+	/*
+	 * Optionally wait for the hardware to be ready for a new command,
+	 * indicating completion of the above issued command.
+	 */
+	if (wait)
+		pcie_wait_cmd(ctrl);
+
 	mutex_unlock(&ctrl->ctrl_lock);
 }
 
+/**
+ * pcie_write_cmd - Issue controller command
+ * @ctrl: controller to which the command is issued
+ * @cmd:  command value written to slot control register
+ * @mask: bitmask of slot control register to be modified
+ */
+static void pcie_write_cmd(struct controller *ctrl, u16 cmd, u16 mask)
+{
+	pcie_do_write_cmd(ctrl, cmd, mask, true);
+}
+
+/* Same as above without waiting for the hardware to latch */
+static void pcie_write_cmd_nowait(struct controller *ctrl, u16 cmd, u16 mask)
+{
+	pcie_do_write_cmd(ctrl, cmd, mask, false);
+}
+
 bool pciehp_check_link_active(struct controller *ctrl)
 {
 	struct pci_dev *pdev = ctrl_dev(ctrl);
@@ -291,7 +312,8 @@ int pciehp_check_link_status(struct controller *ctrl)
 	ctrl_dbg(ctrl, "%s: lnk_status = %x\n", __func__, lnk_status);
 	if ((lnk_status & PCI_EXP_LNKSTA_LT) ||
 	    !(lnk_status & PCI_EXP_LNKSTA_NLW)) {
-		ctrl_err(ctrl, "Link Training Error occurs\n");
+		ctrl_err(ctrl, "link training error: status %#06x\n",
+			 lnk_status);
 		return -1;
 	}
 
@@ -422,7 +444,7 @@ void pciehp_set_attention_status(struct slot *slot, u8 value)
 	default:
 		return;
 	}
-	pcie_write_cmd(ctrl, slot_cmd, PCI_EXP_SLTCTL_AIC);
+	pcie_write_cmd_nowait(ctrl, slot_cmd, PCI_EXP_SLTCTL_AIC);
 	ctrl_dbg(ctrl, "%s: SLOTCTRL %x write cmd %x\n", __func__,
 		 pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL, slot_cmd);
 }
@@ -434,7 +456,8 @@ void pciehp_green_led_on(struct slot *slot)
 	if (!PWR_LED(ctrl))
 		return;
 
-	pcie_write_cmd(ctrl, PCI_EXP_SLTCTL_PWR_IND_ON, PCI_EXP_SLTCTL_PIC);
+	pcie_write_cmd_nowait(ctrl, PCI_EXP_SLTCTL_PWR_IND_ON,
+			      PCI_EXP_SLTCTL_PIC);
 	ctrl_dbg(ctrl, "%s: SLOTCTRL %x write cmd %x\n", __func__,
 		 pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL,
 		 PCI_EXP_SLTCTL_PWR_IND_ON);
@@ -447,7 +470,8 @@ void pciehp_green_led_off(struct slot *slot)
 	if (!PWR_LED(ctrl))
 		return;
 
-	pcie_write_cmd(ctrl, PCI_EXP_SLTCTL_PWR_IND_OFF, PCI_EXP_SLTCTL_PIC);
+	pcie_write_cmd_nowait(ctrl, PCI_EXP_SLTCTL_PWR_IND_OFF,
+			      PCI_EXP_SLTCTL_PIC);
 	ctrl_dbg(ctrl, "%s: SLOTCTRL %x write cmd %x\n", __func__,
 		 pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL,
 		 PCI_EXP_SLTCTL_PWR_IND_OFF);
@@ -460,7 +484,8 @@ void pciehp_green_led_blink(struct slot *slot)
 	if (!PWR_LED(ctrl))
 		return;
 
-	pcie_write_cmd(ctrl, PCI_EXP_SLTCTL_PWR_IND_BLINK, PCI_EXP_SLTCTL_PIC);
+	pcie_write_cmd_nowait(ctrl, PCI_EXP_SLTCTL_PWR_IND_BLINK,
+			      PCI_EXP_SLTCTL_PIC);
 	ctrl_dbg(ctrl, "%s: SLOTCTRL %x write cmd %x\n", __func__,
 		 pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL,
 		 PCI_EXP_SLTCTL_PWR_IND_BLINK);
@@ -510,6 +535,8 @@ static irqreturn_t pcie_isr(int irq, void *dev_id)
 	struct pci_dev *dev;
 	struct slot *slot = ctrl->slot;
 	u16 detected, intr_loc;
+	u8 open, present;
+	bool link;
 
 	/*
 	 * In order to guarantee that all interrupt events are
@@ -532,7 +559,7 @@ static irqreturn_t pcie_isr(int irq, void *dev_id)
 						   intr_loc);
 	} while (detected);
 
-	ctrl_dbg(ctrl, "%s: intr_loc %x\n", __func__, intr_loc);
+	ctrl_dbg(ctrl, "pending interrupts %#06x from Slot Status\n", intr_loc);
 
 	/* Check Command Complete Interrupt Pending */
 	if (intr_loc & PCI_EXP_SLTSTA_CC) {
@@ -555,25 +582,44 @@ static irqreturn_t pcie_isr(int irq, void *dev_id)
 		return IRQ_HANDLED;
 
 	/* Check MRL Sensor Changed */
-	if (intr_loc & PCI_EXP_SLTSTA_MRLSC)
-		pciehp_handle_switch_change(slot);
+	if (intr_loc & PCI_EXP_SLTSTA_MRLSC) {
+		pciehp_get_latch_status(slot, &open);
+		ctrl_info(ctrl, "Latch %s on Slot(%s)\n",
+			  open ? "open" : "close", slot_name(slot));
+		pciehp_queue_interrupt_event(slot, open ? INT_SWITCH_OPEN :
+					     INT_SWITCH_CLOSE);
+	}
 
 	/* Check Attention Button Pressed */
-	if (intr_loc & PCI_EXP_SLTSTA_ABP)
-		pciehp_handle_attention_button(slot);
+	if (intr_loc & PCI_EXP_SLTSTA_ABP) {
+		ctrl_info(ctrl, "Button pressed on Slot(%s)\n",
+			  slot_name(slot));
+		pciehp_queue_interrupt_event(slot, INT_BUTTON_PRESS);
+	}
 
 	/* Check Presence Detect Changed */
-	if (intr_loc & PCI_EXP_SLTSTA_PDC)
-		pciehp_handle_presence_change(slot);
+	if (intr_loc & PCI_EXP_SLTSTA_PDC) {
+		pciehp_get_adapter_status(slot, &present);
+		ctrl_info(ctrl, "Card %spresent on Slot(%s)\n",
+			  present ? "" : "not ", slot_name(slot));
+		pciehp_queue_interrupt_event(slot, present ? INT_PRESENCE_ON :
+					     INT_PRESENCE_OFF);
+	}
 
 	/* Check Power Fault Detected */
 	if ((intr_loc & PCI_EXP_SLTSTA_PFD) && !ctrl->power_fault_detected) {
 		ctrl->power_fault_detected = 1;
-		pciehp_handle_power_fault(slot);
+		ctrl_err(ctrl, "Power fault on slot %s\n", slot_name(slot));
+		pciehp_queue_interrupt_event(slot, INT_POWER_FAULT);
 	}
 
-	if (intr_loc & PCI_EXP_SLTSTA_DLLSC)
-		pciehp_handle_linkstate_change(slot);
+	if (intr_loc & PCI_EXP_SLTSTA_DLLSC) {
+		link = pciehp_check_link_active(ctrl);
+		ctrl_info(ctrl, "slot(%s): Link %s event\n",
+			  slot_name(slot), link ? "Up" : "Down");
+		pciehp_queue_interrupt_event(slot, link ? INT_LINK_UP :
+					     INT_LINK_DOWN);
+	}
 
 	return IRQ_HANDLED;
 }
@@ -613,7 +659,7 @@ void pcie_enable_notification(struct controller *ctrl)
 		PCI_EXP_SLTCTL_HPIE | PCI_EXP_SLTCTL_CCIE |
 		PCI_EXP_SLTCTL_DLLSCE);
 
-	pcie_write_cmd(ctrl, cmd, mask);
+	pcie_write_cmd_nowait(ctrl, cmd, mask);
 	ctrl_dbg(ctrl, "%s: SLOTCTRL %x write cmd %x\n", __func__,
 		 pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL, cmd);
 }
@@ -664,7 +710,7 @@ int pciehp_reset_slot(struct slot *slot, int probe)
 	pci_reset_bridge_secondary_bus(ctrl->pcie->port);
 
 	pcie_capability_write_word(pdev, PCI_EXP_SLTSTA, stat_mask);
-	pcie_write_cmd(ctrl, ctrl_mask, ctrl_mask);
+	pcie_write_cmd_nowait(ctrl, ctrl_mask, ctrl_mask);
 	ctrl_dbg(ctrl, "%s: SLOTCTRL %x write cmd %x\n", __func__,
 		 pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL, ctrl_mask);
 	if (pciehp_poll_mode)
@@ -724,48 +770,13 @@ static void pcie_cleanup_slot(struct controller *ctrl)
 
 static inline void dbg_ctrl(struct controller *ctrl)
 {
-	int i;
-	u16 reg16;
 	struct pci_dev *pdev = ctrl->pcie->port;
+	u16 reg16;
 
 	if (!pciehp_debug)
 		return;
 
-	ctrl_info(ctrl, "Hotplug Controller:\n");
-	ctrl_info(ctrl, "  Seg/Bus/Dev/Func/IRQ : %s IRQ %d\n",
-		  pci_name(pdev), pdev->irq);
-	ctrl_info(ctrl, "  Vendor ID            : 0x%04x\n", pdev->vendor);
-	ctrl_info(ctrl, "  Device ID            : 0x%04x\n", pdev->device);
-	ctrl_info(ctrl, "  Subsystem ID         : 0x%04x\n",
-		  pdev->subsystem_device);
-	ctrl_info(ctrl, "  Subsystem Vendor ID  : 0x%04x\n",
-		  pdev->subsystem_vendor);
-	ctrl_info(ctrl, "  PCIe Cap offset      : 0x%02x\n",
-		  pci_pcie_cap(pdev));
-	for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) {
-		if (!pci_resource_len(pdev, i))
-			continue;
-		ctrl_info(ctrl, "  PCI resource [%d]     : %pR\n",
-			  i, &pdev->resource[i]);
-	}
 	ctrl_info(ctrl, "Slot Capabilities      : 0x%08x\n", ctrl->slot_cap);
-	ctrl_info(ctrl, "  Physical Slot Number : %d\n", PSN(ctrl));
-	ctrl_info(ctrl, "  Attention Button     : %3s\n",
-		  ATTN_BUTTN(ctrl) ? "yes" : "no");
-	ctrl_info(ctrl, "  Power Controller     : %3s\n",
-		  POWER_CTRL(ctrl) ? "yes" : "no");
-	ctrl_info(ctrl, "  MRL Sensor           : %3s\n",
-		  MRL_SENS(ctrl)   ? "yes" : "no");
-	ctrl_info(ctrl, "  Attention Indicator  : %3s\n",
-		  ATTN_LED(ctrl)   ? "yes" : "no");
-	ctrl_info(ctrl, "  Power Indicator      : %3s\n",
-		  PWR_LED(ctrl)    ? "yes" : "no");
-	ctrl_info(ctrl, "  Hot-Plug Surprise    : %3s\n",
-		  HP_SUPR_RM(ctrl) ? "yes" : "no");
-	ctrl_info(ctrl, "  EMI Present          : %3s\n",
-		  EMI(ctrl)        ? "yes" : "no");
-	ctrl_info(ctrl, "  Command Completed    : %3s\n",
-		  NO_CMD_CMPL(ctrl) ? "no" : "yes");
 	pcie_capability_read_word(pdev, PCI_EXP_SLTSTA, &reg16);
 	ctrl_info(ctrl, "Slot Status            : 0x%04x\n", reg16);
 	pcie_capability_read_word(pdev, PCI_EXP_SLTCTL, &reg16);
@@ -794,10 +805,8 @@ struct controller *pcie_init(struct pcie_device *dev)
 
 	/* Check if Data Link Layer Link Active Reporting is implemented */
 	pcie_capability_read_dword(pdev, PCI_EXP_LNKCAP, &link_cap);
-	if (link_cap & PCI_EXP_LNKCAP_DLLLARC) {
-		ctrl_dbg(ctrl, "Link Active Reporting supported\n");
+	if (link_cap & PCI_EXP_LNKCAP_DLLLARC)
 		ctrl->link_active_reporting = 1;
-	}
 
 	/* Clear all remaining event bits in Slot Status register */
 	pcie_capability_write_word(pdev, PCI_EXP_SLTSTA,
@@ -805,13 +814,15 @@ struct controller *pcie_init(struct pcie_device *dev)
 		PCI_EXP_SLTSTA_MRLSC | PCI_EXP_SLTSTA_PDC |
 		PCI_EXP_SLTSTA_CC | PCI_EXP_SLTSTA_DLLSC);
 
-	ctrl_info(ctrl, "Slot #%d AttnBtn%c AttnInd%c PwrInd%c PwrCtrl%c MRL%c Interlock%c NoCompl%c LLActRep%c\n",
+	ctrl_info(ctrl, "Slot #%d AttnBtn%c PwrCtrl%c MRL%c AttnInd%c PwrInd%c HotPlug%c Surprise%c Interlock%c NoCompl%c LLActRep%c\n",
 		(slot_cap & PCI_EXP_SLTCAP_PSN) >> 19,
 		FLAG(slot_cap, PCI_EXP_SLTCAP_ABP),
-		FLAG(slot_cap, PCI_EXP_SLTCAP_AIP),
-		FLAG(slot_cap, PCI_EXP_SLTCAP_PIP),
 		FLAG(slot_cap, PCI_EXP_SLTCAP_PCP),
 		FLAG(slot_cap, PCI_EXP_SLTCAP_MRLSP),
+		FLAG(slot_cap, PCI_EXP_SLTCAP_AIP),
+		FLAG(slot_cap, PCI_EXP_SLTCAP_PIP),
+		FLAG(slot_cap, PCI_EXP_SLTCAP_HPC),
+		FLAG(slot_cap, PCI_EXP_SLTCAP_HPS),
 		FLAG(slot_cap, PCI_EXP_SLTCAP_EIP),
 		FLAG(slot_cap, PCI_EXP_SLTCAP_NCCS),
 		FLAG(link_cap, PCI_EXP_LNKCAP_DLLLARC));
diff --git a/drivers/pci/htirq.c b/drivers/pci/htirq.c
index a94dd2c4183a..7eb4109a3df4 100644
--- a/drivers/pci/htirq.c
+++ b/drivers/pci/htirq.c
@@ -23,20 +23,11 @@
  */
 static DEFINE_SPINLOCK(ht_irq_lock);
 
-struct ht_irq_cfg {
-	struct pci_dev *dev;
-	 /* Update callback used to cope with buggy hardware */
-	ht_irq_update_t *update;
-	unsigned pos;
-	unsigned idx;
-	struct ht_irq_msg msg;
-};
-
-
 void write_ht_irq_msg(unsigned int irq, struct ht_irq_msg *msg)
 {
 	struct ht_irq_cfg *cfg = irq_get_handler_data(irq);
 	unsigned long flags;
+
 	spin_lock_irqsave(&ht_irq_lock, flags);
 	if (cfg->msg.address_lo != msg->address_lo) {
 		pci_write_config_byte(cfg->dev, cfg->pos + 2, cfg->idx);
@@ -55,6 +46,7 @@ void write_ht_irq_msg(unsigned int irq, struct ht_irq_msg *msg)
 void fetch_ht_irq_msg(unsigned int irq, struct ht_irq_msg *msg)
 {
 	struct ht_irq_cfg *cfg = irq_get_handler_data(irq);
+
 	*msg = cfg->msg;
 }
 
@@ -86,7 +78,6 @@ void unmask_ht_irq(struct irq_data *data)
  */
 int __ht_create_irq(struct pci_dev *dev, int idx, ht_irq_update_t *update)
 {
-	struct ht_irq_cfg *cfg;
 	int max_irq, pos, irq;
 	unsigned long flags;
 	u32 data;
@@ -105,29 +96,9 @@ int __ht_create_irq(struct pci_dev *dev, int idx, ht_irq_update_t *update)
 	if (idx > max_irq)
 		return -EINVAL;
 
-	cfg = kmalloc(sizeof(*cfg), GFP_KERNEL);
-	if (!cfg)
-		return -ENOMEM;
-
-	cfg->dev = dev;
-	cfg->update = update;
-	cfg->pos = pos;
-	cfg->idx = 0x10 + (idx * 2);
-	/* Initialize msg to a value that will never match the first write. */
-	cfg->msg.address_lo = 0xffffffff;
-	cfg->msg.address_hi = 0xffffffff;
-
-	irq = irq_alloc_hwirq(dev_to_node(&dev->dev));
-	if (!irq) {
-		kfree(cfg);
-		return -EBUSY;
-	}
-	irq_set_handler_data(irq, cfg);
-
-	if (arch_setup_ht_irq(irq, dev) < 0) {
-		ht_destroy_irq(irq);
-		return -EBUSY;
-	}
+	irq = arch_setup_ht_irq(idx, pos, dev, update);
+	if (irq > 0)
+		dev_dbg(&dev->dev, "irq %d for HT\n", irq);
 
 	return irq;
 }
@@ -158,13 +129,6 @@ EXPORT_SYMBOL(ht_create_irq);
  */
 void ht_destroy_irq(unsigned int irq)
 {
-	struct ht_irq_cfg *cfg;
-
-	cfg = irq_get_handler_data(irq);
-	irq_set_chip(irq, NULL);
-	irq_set_handler_data(irq, NULL);
-	irq_free_hwirq(irq);
-
-	kfree(cfg);
+	arch_teardown_ht_irq(irq);
 }
 EXPORT_SYMBOL(ht_destroy_irq);
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index c3e7dfcf9ff5..f66be868ad21 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -185,27 +185,6 @@ void __weak arch_restore_msi_irqs(struct pci_dev *dev)
 	return default_restore_msi_irqs(dev);
 }
 
-static void msi_set_enable(struct pci_dev *dev, int enable)
-{
-	u16 control;
-
-	pci_read_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, &control);
-	control &= ~PCI_MSI_FLAGS_ENABLE;
-	if (enable)
-		control |= PCI_MSI_FLAGS_ENABLE;
-	pci_write_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, control);
-}
-
-static void msix_clear_and_set_ctrl(struct pci_dev *dev, u16 clear, u16 set)
-{
-	u16 ctrl;
-
-	pci_read_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, &ctrl);
-	ctrl &= ~clear;
-	ctrl |= set;
-	pci_write_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, ctrl);
-}
-
 static inline __attribute_const__ u32 msi_mask(unsigned x)
 {
 	/* Don't shift by >= width of type */
@@ -452,7 +431,7 @@ static void __pci_restore_msi_state(struct pci_dev *dev)
 	entry = irq_get_msi_desc(dev->irq);
 
 	pci_intx_for_msi(dev, 0);
-	msi_set_enable(dev, 0);
+	pci_msi_set_enable(dev, 0);
 	arch_restore_msi_irqs(dev);
 
 	pci_read_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, &control);
@@ -473,14 +452,14 @@ static void __pci_restore_msix_state(struct pci_dev *dev)
 
 	/* route the table */
 	pci_intx_for_msi(dev, 0);
-	msix_clear_and_set_ctrl(dev, 0,
+	pci_msix_clear_and_set_ctrl(dev, 0,
 				PCI_MSIX_FLAGS_ENABLE | PCI_MSIX_FLAGS_MASKALL);
 
 	arch_restore_msi_irqs(dev);
 	list_for_each_entry(entry, &dev->msi_list, list)
 		msix_mask_irq(entry, entry->masked);
 
-	msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_MASKALL, 0);
+	pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_MASKALL, 0);
 }
 
 void pci_restore_msi_state(struct pci_dev *dev)
@@ -647,7 +626,7 @@ static int msi_capability_init(struct pci_dev *dev, int nvec)
 	int ret;
 	unsigned mask;
 
-	msi_set_enable(dev, 0);	/* Disable MSI during set up */
+	pci_msi_set_enable(dev, 0);	/* Disable MSI during set up */
 
 	entry = msi_setup_entry(dev, nvec);
 	if (!entry)
@@ -683,7 +662,7 @@ static int msi_capability_init(struct pci_dev *dev, int nvec)
 
 	/* Set MSI enabled bits	 */
 	pci_intx_for_msi(dev, 0);
-	msi_set_enable(dev, 1);
+	pci_msi_set_enable(dev, 1);
 	dev->msi_enabled = 1;
 
 	dev->irq = entry->irq;
@@ -775,7 +754,7 @@ static int msix_capability_init(struct pci_dev *dev,
 	void __iomem *base;
 
 	/* Ensure MSI-X is disabled while it is set up */
-	msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_ENABLE, 0);
+	pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_ENABLE, 0);
 
 	pci_read_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, &control);
 	/* Request & Map MSI-X table region */
@@ -801,7 +780,7 @@ static int msix_capability_init(struct pci_dev *dev,
 	 * MSI-X registers.  We need to mask all the vectors to prevent
 	 * interrupts coming in before they're fully set up.
 	 */
-	msix_clear_and_set_ctrl(dev, 0,
+	pci_msix_clear_and_set_ctrl(dev, 0,
 				PCI_MSIX_FLAGS_MASKALL | PCI_MSIX_FLAGS_ENABLE);
 
 	msix_program_entries(dev, entries);
@@ -814,7 +793,7 @@ static int msix_capability_init(struct pci_dev *dev,
 	pci_intx_for_msi(dev, 0);
 	dev->msix_enabled = 1;
 
-	msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_MASKALL, 0);
+	pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_MASKALL, 0);
 
 	return 0;
 
@@ -919,7 +898,7 @@ void pci_msi_shutdown(struct pci_dev *dev)
 	BUG_ON(list_empty(&dev->msi_list));
 	desc = list_first_entry(&dev->msi_list, struct msi_desc, list);
 
-	msi_set_enable(dev, 0);
+	pci_msi_set_enable(dev, 0);
 	pci_intx_for_msi(dev, 1);
 	dev->msi_enabled = 0;
 
@@ -1027,7 +1006,7 @@ void pci_msix_shutdown(struct pci_dev *dev)
 		__pci_msix_desc_mask_irq(entry, 1);
 	}
 
-	msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_ENABLE, 0);
+	pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_ENABLE, 0);
 	pci_intx_for_msi(dev, 1);
 	dev->msix_enabled = 0;
 }
@@ -1062,18 +1041,6 @@ EXPORT_SYMBOL(pci_msi_enabled);
 void pci_msi_init_pci_dev(struct pci_dev *dev)
 {
 	INIT_LIST_HEAD(&dev->msi_list);
-
-	/* Disable the msi hardware to avoid screaming interrupts
-	 * during boot.  This is the power on reset default so
-	 * usually this should be a noop.
-	 */
-	dev->msi_cap = pci_find_capability(dev, PCI_CAP_ID_MSI);
-	if (dev->msi_cap)
-		msi_set_enable(dev, 0);
-
-	dev->msix_cap = pci_find_capability(dev, PCI_CAP_ID_MSIX);
-	if (dev->msix_cap)
-		msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_ENABLE, 0);
 }
 
 /**
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index acc4b6ef78c4..0008c950452c 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -3101,39 +3101,6 @@ bool pci_check_and_unmask_intx(struct pci_dev *dev)
 }
 EXPORT_SYMBOL_GPL(pci_check_and_unmask_intx);
 
-/**
- * pci_msi_off - disables any MSI or MSI-X capabilities
- * @dev: the PCI device to operate on
- *
- * If you want to use MSI, see pci_enable_msi() and friends.
- * This is a lower-level primitive that allows us to disable
- * MSI operation at the device level.
- */
-void pci_msi_off(struct pci_dev *dev)
-{
-	int pos;
-	u16 control;
-
-	/*
-	 * This looks like it could go in msi.c, but we need it even when
-	 * CONFIG_PCI_MSI=n.  For the same reason, we can't use
-	 * dev->msi_cap or dev->msix_cap here.
-	 */
-	pos = pci_find_capability(dev, PCI_CAP_ID_MSI);
-	if (pos) {
-		pci_read_config_word(dev, pos + PCI_MSI_FLAGS, &control);
-		control &= ~PCI_MSI_FLAGS_ENABLE;
-		pci_write_config_word(dev, pos + PCI_MSI_FLAGS, control);
-	}
-	pos = pci_find_capability(dev, PCI_CAP_ID_MSIX);
-	if (pos) {
-		pci_read_config_word(dev, pos + PCI_MSIX_FLAGS, &control);
-		control &= ~PCI_MSIX_FLAGS_ENABLE;
-		pci_write_config_word(dev, pos + PCI_MSIX_FLAGS, control);
-	}
-}
-EXPORT_SYMBOL_GPL(pci_msi_off);
-
 int pci_set_dma_max_seg_size(struct pci_dev *dev, unsigned int size)
 {
 	return dma_set_max_seg_size(&dev->dev, size);
@@ -4324,6 +4291,17 @@ bool pci_device_is_present(struct pci_dev *pdev)
 }
 EXPORT_SYMBOL_GPL(pci_device_is_present);
 
+void pci_ignore_hotplug(struct pci_dev *dev)
+{
+	struct pci_dev *bridge = dev->bus->self;
+
+	dev->ignore_hotplug = 1;
+	/* Propagate the "ignore hotplug" setting to the parent bridge. */
+	if (bridge)
+		bridge->ignore_hotplug = 1;
+}
+EXPORT_SYMBOL_GPL(pci_ignore_hotplug);
+
 #define RESOURCE_ALIGNMENT_PARAM_SIZE COMMAND_LINE_SIZE
 static char resource_alignment_param[RESOURCE_ALIGNMENT_PARAM_SIZE] = {0};
 static DEFINE_SPINLOCK(resource_alignment_lock);
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 9bd762c237ab..4ff0ff1c4088 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -146,6 +146,27 @@ static inline void pci_no_msi(void) { }
 static inline void pci_msi_init_pci_dev(struct pci_dev *dev) { }
 #endif
 
+static inline void pci_msi_set_enable(struct pci_dev *dev, int enable)
+{
+	u16 control;
+
+	pci_read_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, &control);
+	control &= ~PCI_MSI_FLAGS_ENABLE;
+	if (enable)
+		control |= PCI_MSI_FLAGS_ENABLE;
+	pci_write_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, control);
+}
+
+static inline void pci_msix_clear_and_set_ctrl(struct pci_dev *dev, u16 clear, u16 set)
+{
+	u16 ctrl;
+
+	pci_read_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, &ctrl);
+	ctrl &= ~clear;
+	ctrl |= set;
+	pci_write_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, ctrl);
+}
+
 void pci_realloc_get_opt(char *);
 
 static inline int pci_no_d1d2(struct pci_dev *dev)
@@ -216,17 +237,6 @@ void __pci_bus_assign_resources(const struct pci_bus *bus,
 				struct list_head *fail_head);
 bool pci_bus_clip_resource(struct pci_dev *dev, int idx);
 
-/**
- * pci_ari_enabled - query ARI forwarding status
- * @bus: the PCI bus
- *
- * Returns 1 if ARI forwarding is enabled, or 0 if not enabled;
- */
-static inline int pci_ari_enabled(struct pci_bus *bus)
-{
-	return bus->self && bus->self->ari_enabled;
-}
-
 void pci_reassigndev_resource_alignment(struct pci_dev *dev);
 void pci_disable_bridge_window(struct pci_dev *dev);
 
diff --git a/drivers/pci/pcie/aer/aerdrv_core.c b/drivers/pci/pcie/aer/aerdrv_core.c
index 5653ea94547f..9803e3d039fe 100644
--- a/drivers/pci/pcie/aer/aerdrv_core.c
+++ b/drivers/pci/pcie/aer/aerdrv_core.c
@@ -425,8 +425,7 @@ static pci_ers_result_t reset_link(struct pci_dev *dev)
 
 	if (driver && driver->reset_link) {
 		status = driver->reset_link(udev);
-	} else if (pci_pcie_type(udev) == PCI_EXP_TYPE_DOWNSTREAM ||
-		pci_pcie_type(udev) == PCI_EXP_TYPE_ROOT_PORT) {
+	} else if (udev->has_secondary_link) {
 		status = default_reset_link(udev);
 	} else {
 		dev_printk(KERN_DEBUG, &dev->dev,
diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c
index 7d4fcdc512aa..317e3558a35e 100644
--- a/drivers/pci/pcie/aspm.c
+++ b/drivers/pci/pcie/aspm.c
@@ -127,15 +127,12 @@ static void pcie_set_clkpm_nocheck(struct pcie_link_state *link, int enable)
 {
 	struct pci_dev *child;
 	struct pci_bus *linkbus = link->pdev->subordinate;
+	u32 val = enable ? PCI_EXP_LNKCTL_CLKREQ_EN : 0;
 
-	list_for_each_entry(child, &linkbus->devices, bus_list) {
-		if (enable)
-			pcie_capability_set_word(child, PCI_EXP_LNKCTL,
-						 PCI_EXP_LNKCTL_CLKREQ_EN);
-		else
-			pcie_capability_clear_word(child, PCI_EXP_LNKCTL,
-						   PCI_EXP_LNKCTL_CLKREQ_EN);
-	}
+	list_for_each_entry(child, &linkbus->devices, bus_list)
+		pcie_capability_clear_and_set_word(child, PCI_EXP_LNKCTL,
+						   PCI_EXP_LNKCTL_CLKREQ_EN,
+						   val);
 	link->clkpm_enabled = !!enable;
 }
 
@@ -525,7 +522,7 @@ static struct pcie_link_state *alloc_pcie_link_state(struct pci_dev *pdev)
 	INIT_LIST_HEAD(&link->children);
 	INIT_LIST_HEAD(&link->link);
 	link->pdev = pdev;
-	if (pci_pcie_type(pdev) == PCI_EXP_TYPE_DOWNSTREAM) {
+	if (pci_pcie_type(pdev) != PCI_EXP_TYPE_ROOT_PORT) {
 		struct pcie_link_state *parent;
 		parent = pdev->bus->parent->self->link_state;
 		if (!parent) {
@@ -559,10 +556,15 @@ void pcie_aspm_init_link_state(struct pci_dev *pdev)
 	if (!aspm_support_enabled)
 		return;
 
-	if (!pci_is_pcie(pdev) || pdev->link_state)
+	if (pdev->link_state)
 		return;
-	if (pci_pcie_type(pdev) != PCI_EXP_TYPE_ROOT_PORT &&
-	    pci_pcie_type(pdev) != PCI_EXP_TYPE_DOWNSTREAM)
+
+	/*
+	 * We allocate pcie_link_state for the component on the upstream
+	 * end of a Link, so there's nothing to do unless this device has a
+	 * Link on its secondary side.
+	 */
+	if (!pdev->has_secondary_link)
 		return;
 
 	/* VIA has a strange chipset, root port is under a bridge */
@@ -675,10 +677,7 @@ void pcie_aspm_pm_state_change(struct pci_dev *pdev)
 {
 	struct pcie_link_state *link = pdev->link_state;
 
-	if (aspm_disabled || !pci_is_pcie(pdev) || !link)
-		return;
-	if ((pci_pcie_type(pdev) != PCI_EXP_TYPE_ROOT_PORT) &&
-	    (pci_pcie_type(pdev) != PCI_EXP_TYPE_DOWNSTREAM))
+	if (aspm_disabled || !link)
 		return;
 	/*
 	 * Devices changed PM state, we should recheck if latency
@@ -696,16 +695,12 @@ void pcie_aspm_powersave_config_link(struct pci_dev *pdev)
 {
 	struct pcie_link_state *link = pdev->link_state;
 
-	if (aspm_disabled || !pci_is_pcie(pdev) || !link)
+	if (aspm_disabled || !link)
 		return;
 
 	if (aspm_policy != POLICY_POWERSAVE)
 		return;
 
-	if ((pci_pcie_type(pdev) != PCI_EXP_TYPE_ROOT_PORT) &&
-	    (pci_pcie_type(pdev) != PCI_EXP_TYPE_DOWNSTREAM))
-		return;
-
 	down_read(&pci_bus_sem);
 	mutex_lock(&aspm_lock);
 	pcie_config_aspm_path(link);
@@ -714,8 +709,7 @@ void pcie_aspm_powersave_config_link(struct pci_dev *pdev)
 	up_read(&pci_bus_sem);
 }
 
-static void __pci_disable_link_state(struct pci_dev *pdev, int state, bool sem,
-				     bool force)
+static void __pci_disable_link_state(struct pci_dev *pdev, int state, bool sem)
 {
 	struct pci_dev *parent = pdev->bus->self;
 	struct pcie_link_state *link;
@@ -723,8 +717,7 @@ static void __pci_disable_link_state(struct pci_dev *pdev, int state, bool sem,
 	if (!pci_is_pcie(pdev))
 		return;
 
-	if (pci_pcie_type(pdev) == PCI_EXP_TYPE_ROOT_PORT ||
-	    pci_pcie_type(pdev) == PCI_EXP_TYPE_DOWNSTREAM)
+	if (pdev->has_secondary_link)
 		parent = pdev;
 	if (!parent || !parent->link_state)
 		return;
@@ -737,7 +730,7 @@ static void __pci_disable_link_state(struct pci_dev *pdev, int state, bool sem,
 	 * a similar mechanism using "PciASPMOptOut", which is also
 	 * ignored in this situation.
 	 */
-	if (aspm_disabled && !force) {
+	if (aspm_disabled) {
 		dev_warn(&pdev->dev, "can't disable ASPM; OS doesn't have ASPM control\n");
 		return;
 	}
@@ -763,7 +756,7 @@ static void __pci_disable_link_state(struct pci_dev *pdev, int state, bool sem,
 
 void pci_disable_link_state_locked(struct pci_dev *pdev, int state)
 {
-	__pci_disable_link_state(pdev, state, false, false);
+	__pci_disable_link_state(pdev, state, false);
 }
 EXPORT_SYMBOL(pci_disable_link_state_locked);
 
@@ -778,7 +771,7 @@ EXPORT_SYMBOL(pci_disable_link_state_locked);
  */
 void pci_disable_link_state(struct pci_dev *pdev, int state)
 {
-	__pci_disable_link_state(pdev, state, true, false);
+	__pci_disable_link_state(pdev, state, true);
 }
 EXPORT_SYMBOL(pci_disable_link_state);
 
@@ -907,9 +900,7 @@ void pcie_aspm_create_sysfs_dev_files(struct pci_dev *pdev)
 {
 	struct pcie_link_state *link_state = pdev->link_state;
 
-	if (!pci_is_pcie(pdev) ||
-	    (pci_pcie_type(pdev) != PCI_EXP_TYPE_ROOT_PORT &&
-	     pci_pcie_type(pdev) != PCI_EXP_TYPE_DOWNSTREAM) || !link_state)
+	if (!link_state)
 		return;
 
 	if (link_state->aspm_support)
@@ -924,9 +915,7 @@ void pcie_aspm_remove_sysfs_dev_files(struct pci_dev *pdev)
 {
 	struct pcie_link_state *link_state = pdev->link_state;
 
-	if (!pci_is_pcie(pdev) ||
-	    (pci_pcie_type(pdev) != PCI_EXP_TYPE_ROOT_PORT &&
-	     pci_pcie_type(pdev) != PCI_EXP_TYPE_DOWNSTREAM) || !link_state)
+	if (!link_state)
 		return;
 
 	if (link_state->aspm_support)
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 6675a7a1b9fc..cefd636681b6 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -254,8 +254,8 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type,
 	}
 
 	if (res->flags & IORESOURCE_MEM_64) {
-		if ((sizeof(dma_addr_t) < 8 || sizeof(resource_size_t) < 8) &&
-		    sz64 > 0x100000000ULL) {
+		if ((sizeof(pci_bus_addr_t) < 8 || sizeof(resource_size_t) < 8)
+		    && sz64 > 0x100000000ULL) {
 			res->flags |= IORESOURCE_UNSET | IORESOURCE_DISABLED;
 			res->start = 0;
 			res->end = 0;
@@ -264,7 +264,7 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type,
 			goto out;
 		}
 
-		if ((sizeof(dma_addr_t) < 8) && l) {
+		if ((sizeof(pci_bus_addr_t) < 8) && l) {
 			/* Above 32-bit boundary; try to reallocate */
 			res->flags |= IORESOURCE_UNSET;
 			res->start = 0;
@@ -399,7 +399,7 @@ static void pci_read_bridge_mmio_pref(struct pci_bus *child)
 	struct pci_dev *dev = child->self;
 	u16 mem_base_lo, mem_limit_lo;
 	u64 base64, limit64;
-	dma_addr_t base, limit;
+	pci_bus_addr_t base, limit;
 	struct pci_bus_region region;
 	struct resource *res;
 
@@ -426,8 +426,8 @@ static void pci_read_bridge_mmio_pref(struct pci_bus *child)
 		}
 	}
 
-	base = (dma_addr_t) base64;
-	limit = (dma_addr_t) limit64;
+	base = (pci_bus_addr_t) base64;
+	limit = (pci_bus_addr_t) limit64;
 
 	if (base != base64) {
 		dev_err(&dev->dev, "can't handle bridge window above 4GB (bus address %#010llx)\n",
@@ -973,6 +973,8 @@ void set_pcie_port_type(struct pci_dev *pdev)
 {
 	int pos;
 	u16 reg16;
+	int type;
+	struct pci_dev *parent;
 
 	pos = pci_find_capability(pdev, PCI_CAP_ID_EXP);
 	if (!pos)
@@ -982,6 +984,22 @@ void set_pcie_port_type(struct pci_dev *pdev)
 	pdev->pcie_flags_reg = reg16;
 	pci_read_config_word(pdev, pos + PCI_EXP_DEVCAP, &reg16);
 	pdev->pcie_mpss = reg16 & PCI_EXP_DEVCAP_PAYLOAD;
+
+	/*
+	 * A Root Port is always the upstream end of a Link.  No PCIe
+	 * component has two Links.  Two Links are connected by a Switch
+	 * that has a Port on each Link and internal logic to connect the
+	 * two Ports.
+	 */
+	type = pci_pcie_type(pdev);
+	if (type == PCI_EXP_TYPE_ROOT_PORT)
+		pdev->has_secondary_link = 1;
+	else if (type == PCI_EXP_TYPE_UPSTREAM ||
+		 type == PCI_EXP_TYPE_DOWNSTREAM) {
+		parent = pci_upstream_bridge(pdev);
+		if (!parent->has_secondary_link)
+			pdev->has_secondary_link = 1;
+	}
 }
 
 void set_pcie_hotplug_bridge(struct pci_dev *pdev)
@@ -1085,6 +1103,22 @@ int pci_cfg_space_size(struct pci_dev *dev)
 
 #define LEGACY_IO_RESOURCE	(IORESOURCE_IO | IORESOURCE_PCI_FIXED)
 
+static void pci_msi_setup_pci_dev(struct pci_dev *dev)
+{
+	/*
+	 * Disable the MSI hardware to avoid screaming interrupts
+	 * during boot.  This is the power on reset default so
+	 * usually this should be a noop.
+	 */
+	dev->msi_cap = pci_find_capability(dev, PCI_CAP_ID_MSI);
+	if (dev->msi_cap)
+		pci_msi_set_enable(dev, 0);
+
+	dev->msix_cap = pci_find_capability(dev, PCI_CAP_ID_MSIX);
+	if (dev->msix_cap)
+		pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_ENABLE, 0);
+}
+
 /**
  * pci_setup_device - fill in class and map information of a device
  * @dev: the device structure to fill
@@ -1140,6 +1174,8 @@ int pci_setup_device(struct pci_dev *dev)
 	/* "Unknown power state" */
 	dev->current_state = PCI_UNKNOWN;
 
+	pci_msi_setup_pci_dev(dev);
+
 	/* Early fixups, before probing the BARs */
 	pci_fixup_device(pci_fixup_early, dev);
 	/* device class may be changed after fixup */
@@ -1611,7 +1647,7 @@ static int only_one_child(struct pci_bus *bus)
 		return 0;
 	if (pci_pcie_type(parent) == PCI_EXP_TYPE_ROOT_PORT)
 		return 1;
-	if (pci_pcie_type(parent) == PCI_EXP_TYPE_DOWNSTREAM &&
+	if (parent->has_secondary_link &&
 	    !pci_has_flag(PCI_SCAN_ALL_PCIE_DEVS))
 		return 1;
 	return 0;
@@ -2094,25 +2130,6 @@ struct pci_bus *pci_scan_root_bus(struct device *parent, int bus,
 }
 EXPORT_SYMBOL(pci_scan_root_bus);
 
-/* Deprecated; use pci_scan_root_bus() instead */
-struct pci_bus *pci_scan_bus_parented(struct device *parent,
-		int bus, struct pci_ops *ops, void *sysdata)
-{
-	LIST_HEAD(resources);
-	struct pci_bus *b;
-
-	pci_add_resource(&resources, &ioport_resource);
-	pci_add_resource(&resources, &iomem_resource);
-	pci_add_resource(&resources, &busn_resource);
-	b = pci_create_root_bus(parent, bus, ops, sysdata, &resources);
-	if (b)
-		pci_scan_child_bus(b);
-	else
-		pci_free_resource_list(&resources);
-	return b;
-}
-EXPORT_SYMBOL(pci_scan_bus_parented);
-
 struct pci_bus *pci_scan_bus(int bus, struct pci_ops *ops,
 					void *sysdata)
 {
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index c6dc1dfd25d5..e9fd0e90fa3b 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -819,13 +819,6 @@ static void quirk_amd_ioapic(struct pci_dev *dev)
 	}
 }
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD,	PCI_DEVICE_ID_AMD_VIPER_7410,	quirk_amd_ioapic);
-
-static void quirk_ioapic_rmw(struct pci_dev *dev)
-{
-	if (dev->devfn == 0 && dev->bus->number == 0)
-		sis_apic_bug = 1;
-}
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_SI,	PCI_ANY_ID,			quirk_ioapic_rmw);
 #endif /* CONFIG_X86_IO_APIC */
 
 /*
@@ -1600,7 +1593,6 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_EESSC,	quirk_a
 
 static void quirk_pcie_mch(struct pci_dev *pdev)
 {
-	pci_msi_off(pdev);
 	pdev->no_msi = 1;
 }
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_E7520_MCH,	quirk_pcie_mch);
@@ -1614,7 +1606,6 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_E7525_MCH,	quir
  */
 static void quirk_pcie_pxh(struct pci_dev *dev)
 {
-	pci_msi_off(dev);
 	dev->no_msi = 1;
 	dev_warn(&dev->dev, "PXH quirk detected; SHPC device MSI disabled\n");
 }
@@ -3572,6 +3563,8 @@ static void quirk_dma_func1_alias(struct pci_dev *dev)
  * SKUs this function is not present, making this a ghost requester.
  * https://bugzilla.kernel.org/show_bug.cgi?id=42679
  */
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x9120,
+			 quirk_dma_func1_alias);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x9123,
 			 quirk_dma_func1_alias);
 /* https://bugzilla.kernel.org/show_bug.cgi?id=42679#c14 */
@@ -3740,6 +3733,8 @@ static const u16 pci_quirk_intel_pch_acs_ids[] = {
 	/* Wellsburg (X99) PCH */
 	0x8d10, 0x8d11, 0x8d12, 0x8d13, 0x8d14, 0x8d15, 0x8d16, 0x8d17,
 	0x8d18, 0x8d19, 0x8d1a, 0x8d1b, 0x8d1c, 0x8d1d, 0x8d1e,
+	/* Lynx Point (9 series) PCH */
+	0x8c90, 0x8c92, 0x8c94, 0x8c96, 0x8c98, 0x8c9a, 0x8c9c, 0x8c9e,
 };
 
 static bool pci_quirk_intel_pch_acs_match(struct pci_dev *dev)
diff --git a/drivers/pci/vc.c b/drivers/pci/vc.c
index 7e1304d2e389..dfbab61a1b47 100644
--- a/drivers/pci/vc.c
+++ b/drivers/pci/vc.c
@@ -108,8 +108,7 @@ static void pci_vc_enable(struct pci_dev *dev, int pos, int res)
 	struct pci_dev *link = NULL;
 
 	/* Enable VCs from the downstream device */
-	if (pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT ||
-	    pci_pcie_type(dev) == PCI_EXP_TYPE_DOWNSTREAM)
+	if (!dev->has_secondary_link)
 		return;
 
 	ctrl_pos = pos + PCI_VC_RES_CTRL + (res * PCI_CAP_VC_PER_VC_SIZEOF);
diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c
index 7cfd2db02deb..240f38872085 100644
--- a/drivers/pci/xen-pcifront.c
+++ b/drivers/pci/xen-pcifront.c
@@ -446,9 +446,15 @@ static int pcifront_scan_root(struct pcifront_device *pdev,
 				 unsigned int domain, unsigned int bus)
 {
 	struct pci_bus *b;
+	LIST_HEAD(resources);
 	struct pcifront_sd *sd = NULL;
 	struct pci_bus_entry *bus_entry = NULL;
 	int err = 0;
+	static struct resource busn_res = {
+		.start = 0,
+		.end = 255,
+		.flags = IORESOURCE_BUS,
+	};
 
 #ifndef CONFIG_PCI_DOMAINS
 	if (domain != 0) {
@@ -470,17 +476,21 @@ static int pcifront_scan_root(struct pcifront_device *pdev,
 		err = -ENOMEM;
 		goto err_out;
 	}
+	pci_add_resource(&resources, &ioport_resource);
+	pci_add_resource(&resources, &iomem_resource);
+	pci_add_resource(&resources, &busn_res);
 	pcifront_init_sd(sd, domain, bus, pdev);
 
 	pci_lock_rescan_remove();
 
-	b = pci_scan_bus_parented(&pdev->xdev->dev, bus,
-				  &pcifront_bus_ops, sd);
+	b = pci_scan_root_bus(&pdev->xdev->dev, bus,
+				  &pcifront_bus_ops, sd, &resources);
 	if (!b) {
 		dev_err(&pdev->xdev->dev,
 			"Error creating PCI Frontend Bus!\n");
 		err = -ENOMEM;
 		pci_unlock_rescan_remove();
+		pci_free_resource_list(&resources);
 		goto err_out;
 	}
 
@@ -488,7 +498,7 @@ static int pcifront_scan_root(struct pcifront_device *pdev,
 
 	list_add(&bus_entry->list, &pdev->root_buses);
 
-	/* pci_scan_bus_parented skips devices which do not have a have
+	/* pci_scan_root_bus skips devices which do not have a
 	* devfn==0. The pcifront_scan_bus enumerates all devfn. */
 	err = pcifront_scan_bus(pdev, domain, bus, b);
 
diff --git a/drivers/pcmcia/cistpl.c b/drivers/pcmcia/cistpl.c
index 64d0515b76bd..55ef7d1fd8da 100644
--- a/drivers/pcmcia/cistpl.c
+++ b/drivers/pcmcia/cistpl.c
@@ -94,8 +94,7 @@ static void __iomem *set_cis_map(struct pcmcia_socket *s,
 		mem->res = pcmcia_find_mem_region(0, s->map_size,
 						s->map_size, 0, s);
 		if (mem->res == NULL) {
-			dev_printk(KERN_NOTICE, &s->dev,
-				   "cs: unable to map card memory!\n");
+			dev_notice(&s->dev, "cs: unable to map card memory!\n");
 			return NULL;
 		}
 		s->cis_virt = NULL;
@@ -381,8 +380,7 @@ int verify_cis_cache(struct pcmcia_socket *s)
 
 	buf = kmalloc(256, GFP_KERNEL);
 	if (buf == NULL) {
-		dev_printk(KERN_WARNING, &s->dev,
-			   "no memory for verifying CIS\n");
+		dev_warn(&s->dev, "no memory for verifying CIS\n");
 		return -ENOMEM;
 	}
 	mutex_lock(&s->ops_mutex);
@@ -414,14 +412,14 @@ int pcmcia_replace_cis(struct pcmcia_socket *s,
 		       const u8 *data, const size_t len)
 {
 	if (len > CISTPL_MAX_CIS_SIZE) {
-		dev_printk(KERN_WARNING, &s->dev, "replacement CIS too big\n");
+		dev_warn(&s->dev, "replacement CIS too big\n");
 		return -EINVAL;
 	}
 	mutex_lock(&s->ops_mutex);
 	kfree(s->fake_cis);
 	s->fake_cis = kmalloc(len, GFP_KERNEL);
 	if (s->fake_cis == NULL) {
-		dev_printk(KERN_WARNING, &s->dev, "no memory to replace CIS\n");
+		dev_warn(&s->dev, "no memory to replace CIS\n");
 		mutex_unlock(&s->ops_mutex);
 		return -ENOMEM;
 	}
@@ -434,17 +432,17 @@ int pcmcia_replace_cis(struct pcmcia_socket *s,
 
 /* The high-level CIS tuple services */
 
-typedef struct tuple_flags {
+struct tuple_flags {
 	u_int		link_space:4;
 	u_int		has_link:1;
 	u_int		mfc_fn:3;
 	u_int		space:4;
-} tuple_flags;
+};
 
-#define LINK_SPACE(f)	(((tuple_flags *)(&(f)))->link_space)
-#define HAS_LINK(f)	(((tuple_flags *)(&(f)))->has_link)
-#define MFC_FN(f)	(((tuple_flags *)(&(f)))->mfc_fn)
-#define SPACE(f)	(((tuple_flags *)(&(f)))->space)
+#define LINK_SPACE(f)	(((struct tuple_flags *)(&(f)))->link_space)
+#define HAS_LINK(f)	(((struct tuple_flags *)(&(f)))->has_link)
+#define MFC_FN(f)	(((struct tuple_flags *)(&(f)))->mfc_fn)
+#define SPACE(f)	(((struct tuple_flags *)(&(f)))->space)
 
 int pccard_get_first_tuple(struct pcmcia_socket *s, unsigned int function,
 			tuple_t *tuple)
@@ -1451,26 +1449,16 @@ int pccard_validate_cis(struct pcmcia_socket *s, unsigned int *info)
 done:
 	/* invalidate CIS cache on failure */
 	if (!dev_ok || !ident_ok || !count) {
-#if defined(CONFIG_MTD_PCMCIA_ANONYMOUS)
-		/* Set up as an anonymous card. If we don't have anonymous
-		   memory support then just error the card as there is no
-		   point trying to second guess.
-
-		   Note: some cards have just a device entry, it may be
-		   worth extending support to cover these in future */
-		if (!dev_ok || !ident_ok) {
-			dev_info(&s->dev, "no CIS, assuming an anonymous memory card.\n");
-			pcmcia_replace_cis(s, "\xFF", 1);
-			count = 1;
-			ret = 0;
-		} else
-#endif
-		{
-			mutex_lock(&s->ops_mutex);
-			destroy_cis_cache(s);
-			mutex_unlock(&s->ops_mutex);
+		mutex_lock(&s->ops_mutex);
+		destroy_cis_cache(s);
+		mutex_unlock(&s->ops_mutex);
+		/* We differentiate between dev_ok, ident_ok and count
+		   failures to allow for an override for anonymous cards
+		   in ds.c */
+		if (!dev_ok || !ident_ok)
 			ret = -EIO;
-		}
+		else
+			ret = -EFAULT;
 	}
 
 	if (info)
diff --git a/drivers/pcmcia/cs.c b/drivers/pcmcia/cs.c
index 5292db69c426..8007bfda720a 100644
--- a/drivers/pcmcia/cs.c
+++ b/drivers/pcmcia/cs.c
@@ -177,8 +177,8 @@ int pcmcia_register_socket(struct pcmcia_socket *socket)
 
 	wait_for_completion(&socket->thread_done);
 	if (!socket->thread) {
-		dev_printk(KERN_WARNING, &socket->dev,
-			   "PCMCIA: warning: socket thread did not start\n");
+		dev_warn(&socket->dev,
+			 "PCMCIA: warning: socket thread did not start\n");
 		return -EIO;
 	}
 
@@ -275,7 +275,7 @@ static int socket_reset(struct pcmcia_socket *skt)
 		msleep(unreset_check * 10);
 	}
 
-	dev_printk(KERN_ERR, &skt->dev, "time out after reset.\n");
+	dev_err(&skt->dev, "time out after reset\n");
 	return -ETIMEDOUT;
 }
 
@@ -325,8 +325,8 @@ static void socket_shutdown(struct pcmcia_socket *s)
 
 	s->ops->get_status(s, &status);
 	if (status & SS_POWERON) {
-		dev_printk(KERN_ERR, &s->dev,
-			   "*** DANGER *** unable to remove socket power\n");
+		dev_err(&s->dev,
+			"*** DANGER *** unable to remove socket power\n");
 	}
 
 	s->state &= ~SOCKET_INUSE;
@@ -356,15 +356,13 @@ static int socket_setup(struct pcmcia_socket *skt, int initial_delay)
 	}
 
 	if (status & SS_PENDING) {
-		dev_printk(KERN_ERR, &skt->dev,
-			   "voltage interrogation timed out.\n");
+		dev_err(&skt->dev, "voltage interrogation timed out\n");
 		return -ETIMEDOUT;
 	}
 
 	if (status & SS_CARDBUS) {
 		if (!(skt->features & SS_CAP_CARDBUS)) {
-			dev_printk(KERN_ERR, &skt->dev,
-				"cardbus cards are not supported.\n");
+			dev_err(&skt->dev, "cardbus cards are not supported\n");
 			return -EINVAL;
 		}
 		skt->state |= SOCKET_CARDBUS;
@@ -379,7 +377,7 @@ static int socket_setup(struct pcmcia_socket *skt, int initial_delay)
 	else if (!(status & SS_XVCARD))
 		skt->socket.Vcc = skt->socket.Vpp = 50;
 	else {
-		dev_printk(KERN_ERR, &skt->dev, "unsupported voltage key.\n");
+		dev_err(&skt->dev, "unsupported voltage key\n");
 		return -EIO;
 	}
 
@@ -396,7 +394,7 @@ static int socket_setup(struct pcmcia_socket *skt, int initial_delay)
 
 	skt->ops->get_status(skt, &status);
 	if (!(status & SS_POWERON)) {
-		dev_printk(KERN_ERR, &skt->dev, "unable to apply power.\n");
+		dev_err(&skt->dev, "unable to apply power\n");
 		return -EIO;
 	}
 
@@ -429,8 +427,7 @@ static int socket_insert(struct pcmcia_socket *skt)
 	if (ret == 0) {
 		skt->state |= SOCKET_PRESENT;
 
-		dev_printk(KERN_NOTICE, &skt->dev,
-			   "pccard: %s card inserted into slot %d\n",
+		dev_notice(&skt->dev, "pccard: %s card inserted into slot %d\n",
 			   (skt->state & SOCKET_CARDBUS) ? "CardBus" : "PCMCIA",
 			   skt->sock);
 
@@ -558,8 +555,7 @@ static int socket_resume(struct pcmcia_socket *skt)
 
 static void socket_remove(struct pcmcia_socket *skt)
 {
-	dev_printk(KERN_NOTICE, &skt->dev,
-		   "pccard: card ejected from slot %d\n", skt->sock);
+	dev_notice(&skt->dev, "pccard: card ejected from slot %d\n", skt->sock);
 	socket_shutdown(skt);
 }
 
@@ -605,8 +601,7 @@ static int pccardd(void *__skt)
 	/* register with the device core */
 	ret = device_register(&skt->dev);
 	if (ret) {
-		dev_printk(KERN_WARNING, &skt->dev,
-			   "PCMCIA: unable to register socket\n");
+		dev_warn(&skt->dev, "PCMCIA: unable to register socket\n");
 		skt->thread = NULL;
 		complete(&skt->thread_done);
 		return 0;
diff --git a/drivers/pcmcia/ds.c b/drivers/pcmcia/ds.c
index d3baf0bfca9f..0decee6c556e 100644
--- a/drivers/pcmcia/ds.c
+++ b/drivers/pcmcia/ds.c
@@ -81,8 +81,8 @@ static void pcmcia_check_driver(struct pcmcia_driver *p_drv)
 
 
 struct pcmcia_dynid {
-	struct list_head 		node;
-	struct pcmcia_device_id 	id;
+	struct list_head		node;
+	struct pcmcia_device_id		id;
 };
 
 /**
@@ -284,8 +284,8 @@ static int pcmcia_device_probe(struct device *dev)
 		dev_dbg(dev, "base %x, regs %x", p_dev->config_base,
 			p_dev->config_regs);
 	} else {
-		dev_printk(KERN_INFO, dev,
-			   "pcmcia: could not parse base and rmask0 of CIS\n");
+		dev_info(dev,
+			 "pcmcia: could not parse base and rmask0 of CIS\n");
 		p_dev->config_base = 0;
 		p_dev->config_regs = 0;
 	}
@@ -382,15 +382,15 @@ static int pcmcia_device_remove(struct device *dev)
 
 	/* check for proper unloading */
 	if (p_dev->_irq || p_dev->_io || p_dev->_locked)
-		dev_printk(KERN_INFO, dev,
-			"pcmcia: driver %s did not release config properly\n",
-			p_drv->name);
+		dev_info(dev,
+			 "pcmcia: driver %s did not release config properly\n",
+			 p_drv->name);
 
 	for (i = 0; i < MAX_WIN; i++)
 		if (p_dev->_win & CLIENT_WIN_REQ(i))
-			dev_printk(KERN_INFO, dev,
-			  "pcmcia: driver %s did not release window properly\n",
-			   p_drv->name);
+			dev_info(dev,
+				 "pcmcia: driver %s did not release window properly\n",
+				 p_drv->name);
 
 	/* references from pcmcia_probe_device */
 	pcmcia_put_dev(p_dev);
@@ -566,7 +566,7 @@ static struct pcmcia_device *pcmcia_device_add(struct pcmcia_socket *s,
 			c->io[i].name = p_dev->devname;
 			c->io[i].flags = IORESOURCE_IO;
 		}
-		for (i = 0; i< MAX_WIN; i++) {
+		for (i = 0; i < MAX_WIN; i++) {
 			c->mem[i].name = p_dev->devname;
 			c->mem[i].flags = IORESOURCE_MEM;
 		}
@@ -578,8 +578,7 @@ static struct pcmcia_device *pcmcia_device_add(struct pcmcia_socket *s,
 
 	mutex_unlock(&s->ops_mutex);
 
-	dev_printk(KERN_NOTICE, &p_dev->dev,
-		   "pcmcia: registering new device %s (IRQ: %d)\n",
+	dev_notice(&p_dev->dev, "pcmcia: registering new device %s (IRQ: %d)\n",
 		   p_dev->devname, p_dev->irq);
 
 	pcmcia_device_query(p_dev);
@@ -634,8 +633,24 @@ static int pcmcia_card_add(struct pcmcia_socket *s)
 
 	ret = pccard_validate_cis(s, &no_chains);
 	if (ret || !no_chains) {
-		dev_dbg(&s->dev, "invalid CIS or invalid resources\n");
-		return -ENODEV;
+#if defined(CONFIG_MTD_PCMCIA_ANONYMOUS)
+		/* Set up as an anonymous card. If we don't have anonymous
+		   memory support then just error the card as there is no
+		   point trying to second guess.
+
+		   Note: some cards have just a device entry, it may be
+		   worth extending support to cover these in future */
+		if (ret == -EIO) {
+			dev_info(&s->dev, "no CIS, assuming an anonymous memory card.\n");
+			pcmcia_replace_cis(s, "\xFF", 1);
+			no_chains = 1;
+			ret = 0;
+		} else
+#endif
+		{
+			dev_dbg(&s->dev, "invalid CIS or invalid resources\n");
+			return -ENODEV;
+		}
 	}
 
 	if (!pccard_read_tuple(s, BIND_FN_ALL, CISTPL_LONGLINK_MFC, &mfc))
@@ -651,7 +666,7 @@ static int pcmcia_card_add(struct pcmcia_socket *s)
 }
 
 
-static int pcmcia_requery_callback(struct device *dev, void * _data)
+static int pcmcia_requery_callback(struct device *dev, void *_data)
 {
 	struct pcmcia_device *p_dev = to_pcmcia_dev(dev);
 	if (!p_dev->dev.driver) {
@@ -729,7 +744,7 @@ static void pcmcia_requery(struct pcmcia_socket *s)
  * the one provided by the card is broken. The firmware files reside in
  * /lib/firmware/ in userspace.
  */
-static int pcmcia_load_firmware(struct pcmcia_device *dev, char * filename)
+static int pcmcia_load_firmware(struct pcmcia_device *dev, char *filename)
 {
 	struct pcmcia_socket *s = dev->socket;
 	const struct firmware *fw;
@@ -745,16 +760,14 @@ static int pcmcia_load_firmware(struct pcmcia_device *dev, char * filename)
 	if (request_firmware(&fw, filename, &dev->dev) == 0) {
 		if (fw->size >= CISTPL_MAX_CIS_SIZE) {
 			ret = -EINVAL;
-			dev_printk(KERN_ERR, &dev->dev,
-				   "pcmcia: CIS override is too big\n");
+			dev_err(&dev->dev, "pcmcia: CIS override is too big\n");
 			goto release;
 		}
 
 		if (!pcmcia_replace_cis(s, fw->data, fw->size))
 			ret = 0;
 		else {
-			dev_printk(KERN_ERR, &dev->dev,
-				   "pcmcia: CIS override failed\n");
+			dev_err(&dev->dev, "pcmcia: CIS override failed\n");
 			goto release;
 		}
 
@@ -781,7 +794,8 @@ static int pcmcia_load_firmware(struct pcmcia_device *dev, char * filename)
 
 #else /* !CONFIG_PCMCIA_LOAD_CIS */
 
-static inline int pcmcia_load_firmware(struct pcmcia_device *dev, char * filename)
+static inline int pcmcia_load_firmware(struct pcmcia_device *dev,
+				       char *filename)
 {
 	return -ENODEV;
 }
@@ -1148,10 +1162,9 @@ static int pcmcia_dev_suspend(struct device *dev, pm_message_t state)
 	if (p_drv->suspend) {
 		ret = p_drv->suspend(p_dev);
 		if (ret) {
-			dev_printk(KERN_ERR, dev,
-				   "pcmcia: device %s (driver %s) did "
-				   "not want to go to sleep (%d)\n",
-				   p_dev->devname, p_drv->name, ret);
+			dev_err(dev,
+				"pcmcia: device %s (driver %s) did not want to go to sleep (%d)\n",
+				p_dev->devname, p_drv->name, ret);
 			mutex_lock(&p_dev->socket->ops_mutex);
 			p_dev->suspended = 0;
 			mutex_unlock(&p_dev->socket->ops_mutex);
@@ -1206,7 +1219,7 @@ static int pcmcia_dev_resume(struct device *dev)
 }
 
 
-static int pcmcia_bus_suspend_callback(struct device *dev, void * _data)
+static int pcmcia_bus_suspend_callback(struct device *dev, void *_data)
 {
 	struct pcmcia_socket *skt = _data;
 	struct pcmcia_device *p_dev = to_pcmcia_dev(dev);
@@ -1217,7 +1230,7 @@ static int pcmcia_bus_suspend_callback(struct device *dev, void * _data)
 	return runtime_suspend(dev);
 }
 
-static int pcmcia_bus_resume_callback(struct device *dev, void * _data)
+static int pcmcia_bus_resume_callback(struct device *dev, void *_data)
 {
 	struct pcmcia_socket *skt = _data;
 	struct pcmcia_device *p_dev = to_pcmcia_dev(dev);
@@ -1342,14 +1355,13 @@ static int pcmcia_bus_add_socket(struct device *dev,
 
 	socket = pcmcia_get_socket(socket);
 	if (!socket) {
-		dev_printk(KERN_ERR, dev,
-			   "PCMCIA obtaining reference to socket failed\n");
+		dev_err(dev, "PCMCIA obtaining reference to socket failed\n");
 		return -ENODEV;
 	}
 
 	ret = sysfs_create_bin_file(&dev->kobj, &pccard_cis_attr);
 	if (ret) {
-		dev_printk(KERN_ERR, dev, "PCMCIA registration failed\n");
+		dev_err(dev, "PCMCIA registration failed\n");
 		pcmcia_put_socket(socket);
 		return ret;
 	}
@@ -1361,7 +1373,7 @@ static int pcmcia_bus_add_socket(struct device *dev,
 
 	ret = pccard_register_pcmcia(socket, &pcmcia_bus_callback);
 	if (ret) {
-		dev_printk(KERN_ERR, dev, "PCMCIA registration failed\n");
+		dev_err(dev, "PCMCIA registration failed\n");
 		pcmcia_put_socket(socket);
 		return ret;
 	}
diff --git a/drivers/pcmcia/electra_cf.c b/drivers/pcmcia/electra_cf.c
index 7f9950d324df..61cf61ac621e 100644
--- a/drivers/pcmcia/electra_cf.c
+++ b/drivers/pcmcia/electra_cf.c
@@ -48,14 +48,14 @@ struct electra_cf_socket {
 
 	struct platform_device	*ofdev;
 	unsigned long		mem_phys;
-	void __iomem *		mem_base;
+	void __iomem		*mem_base;
 	unsigned long		mem_size;
-	void __iomem *		io_virt;
+	void __iomem		*io_virt;
 	unsigned int		io_base;
 	unsigned int		io_size;
 	u_int			irq;
 	struct resource		iomem;
-	void __iomem *		gpio_base;
+	void __iomem		*gpio_base;
 	int			gpio_detect;
 	int			gpio_vsense;
 	int			gpio_3v;
@@ -202,7 +202,7 @@ static int electra_cf_probe(struct platform_device *ofdev)
 	if (err)
 		return -EINVAL;
 
-	cf = kzalloc(sizeof *cf, GFP_KERNEL);
+	cf = kzalloc(sizeof(*cf), GFP_KERNEL);
 	if (!cf)
 		return -ENOMEM;
 
@@ -216,8 +216,10 @@ static int electra_cf_probe(struct platform_device *ofdev)
 	cf->io_size = PAGE_ALIGN(resource_size(&io));
 
 	area = __get_vm_area(cf->io_size, 0, PHB_IO_BASE, PHB_IO_END);
-	if (area == NULL)
-		return -ENOMEM;
+	if (area == NULL) {
+		status = -ENOMEM;
+		goto fail1;
+	}
 
 	cf->io_virt = (void __iomem *)(area->addr);
 
@@ -320,7 +322,8 @@ fail1:
 		iounmap(cf->mem_base);
 	if (cf->gpio_base)
 		iounmap(cf->gpio_base);
-	device_init_wakeup(&ofdev->dev, 0);
+	if (area)
+		device_init_wakeup(&ofdev->dev, 0);
 	kfree(cf);
 	return status;
 
@@ -369,5 +372,5 @@ static struct platform_driver electra_cf_driver = {
 module_platform_driver(electra_cf_driver);
 
 MODULE_LICENSE("GPL");
-MODULE_AUTHOR ("Olof Johansson <olof@lixom.net>");
+MODULE_AUTHOR("Olof Johansson <olof@lixom.net>");
 MODULE_DESCRIPTION("PA Semi Electra CF driver");
diff --git a/drivers/pcmcia/i82365.c b/drivers/pcmcia/i82365.c
index a2c138719bac..eb0d80a429e4 100644
--- a/drivers/pcmcia/i82365.c
+++ b/drivers/pcmcia/i82365.c
@@ -132,14 +132,14 @@ module_param(recov_time, int, 0444);
 
 /*====================================================================*/
 
-typedef struct cirrus_state_t {
+struct cirrus_state {
     u_char		misc1, misc2;
     u_char		timer[6];
-} cirrus_state_t;
+};
 
-typedef struct vg46x_state_t {
+struct vg46x_state {
     u_char		ctl, ema;
-} vg46x_state_t;
+};
 
 struct i82365_socket {
     u_short		type, flags;
@@ -149,8 +149,8 @@ struct i82365_socket {
     u_short		psock;
     u_char		cs_irq, intr;
     union {
-	cirrus_state_t		cirrus;
-	vg46x_state_t		vg46x;
+	struct cirrus_state		cirrus;
+	struct vg46x_state		vg46x;
     } state;
 };
 
@@ -173,11 +173,11 @@ static struct timer_list poll_timer;
 /*====================================================================*/
 
 /* These definitions must match the pcic table! */
-typedef enum pcic_id {
+enum pcic_id {
     IS_I82365A, IS_I82365B, IS_I82365DF,
     IS_IBM, IS_RF5Cx96, IS_VLSI, IS_VG468, IS_VG469,
     IS_PD6710, IS_PD672X, IS_VT83C469,
-} pcic_id;
+};
 
 /* Flags for classifying groups of controllers */
 #define IS_VADEM	0x0001
@@ -189,12 +189,12 @@ typedef enum pcic_id {
 #define IS_REGISTERED	0x2000
 #define IS_ALIVE	0x8000
 
-typedef struct pcic_t {
+struct pcic {
     char		*name;
     u_short		flags;
-} pcic_t;
+};
 
-static pcic_t pcic[] = {
+static struct pcic pcic[] = {
     { "Intel i82365sl A step", 0 },
     { "Intel i82365sl B step", 0 },
     { "Intel i82365sl DF", IS_DF_PWR },
@@ -208,7 +208,7 @@ static pcic_t pcic[] = {
     { "VIA VT83C469", IS_CIRRUS|IS_VIA },
 };
 
-#define PCIC_COUNT	(sizeof(pcic)/sizeof(pcic_t))
+#define PCIC_COUNT	ARRAY_SIZE(pcic)
 
 /*====================================================================*/
 
@@ -294,7 +294,7 @@ static void i365_set_pair(u_short sock, u_short reg, u_short data)
 static void cirrus_get_state(u_short s)
 {
     int i;
-    cirrus_state_t *p = &socket[s].state.cirrus;
+    struct cirrus_state *p = &socket[s].state.cirrus;
     p->misc1 = i365_get(s, PD67_MISC_CTL_1);
     p->misc1 &= (PD67_MC1_MEDIA_ENA | PD67_MC1_INPACK_ENA);
     p->misc2 = i365_get(s, PD67_MISC_CTL_2);
@@ -306,7 +306,7 @@ static void cirrus_set_state(u_short s)
 {
     int i;
     u_char misc;
-    cirrus_state_t *p = &socket[s].state.cirrus;
+    struct cirrus_state *p = &socket[s].state.cirrus;
 
     misc = i365_get(s, PD67_MISC_CTL_2);
     i365_set(s, PD67_MISC_CTL_2, p->misc2);
@@ -321,7 +321,7 @@ static void cirrus_set_state(u_short s)
 static u_int __init cirrus_set_opts(u_short s, char *buf)
 {
     struct i82365_socket *t = &socket[s];
-    cirrus_state_t *p = &socket[s].state.cirrus;
+    struct cirrus_state *p = &socket[s].state.cirrus;
     u_int mask = 0xffff;
 
     if (has_ring == -1) has_ring = 1;
@@ -377,7 +377,7 @@ static u_int __init cirrus_set_opts(u_short s, char *buf)
 
 static void vg46x_get_state(u_short s)
 {
-    vg46x_state_t *p = &socket[s].state.vg46x;
+    struct vg46x_state *p = &socket[s].state.vg46x;
     p->ctl = i365_get(s, VG468_CTL);
     if (socket[s].type == IS_VG469)
 	p->ema = i365_get(s, VG469_EXT_MODE);
@@ -385,7 +385,7 @@ static void vg46x_get_state(u_short s)
 
 static void vg46x_set_state(u_short s)
 {
-    vg46x_state_t *p = &socket[s].state.vg46x;
+    struct vg46x_state *p = &socket[s].state.vg46x;
     i365_set(s, VG468_CTL, p->ctl);
     if (socket[s].type == IS_VG469)
 	i365_set(s, VG469_EXT_MODE, p->ema);
@@ -393,7 +393,7 @@ static void vg46x_set_state(u_short s)
 
 static u_int __init vg46x_set_opts(u_short s, char *buf)
 {
-    vg46x_state_t *p = &socket[s].state.vg46x;
+    struct vg46x_state *p = &socket[s].state.vg46x;
     
     flip(p->ctl, VG468_CTL_ASYNC, async_clock);
     flip(p->ema, VG469_MODE_CABLE, cable_mode);
@@ -1285,13 +1285,6 @@ static int __init init_i82365(void)
 	    ret = pcmcia_register_socket(&socket[i].socket);
 	    if (!ret)
 		    socket[i].flags |= IS_REGISTERED;
-
-#if 0 /* driver model ordering issue */
-	   class_device_create_file(&socket[i].socket.dev,
-			   	    &class_device_attr_info);
-	   class_device_create_file(&socket[i].socket.dev,
-			   	    &class_device_attr_exca);
-#endif
     }
 
     /* Finally, schedule a polling interrupt */
diff --git a/drivers/pcmcia/m32r_cfc.c b/drivers/pcmcia/m32r_cfc.c
index 0075bd7162ed..70b089430fcc 100644
--- a/drivers/pcmcia/m32r_cfc.c
+++ b/drivers/pcmcia/m32r_cfc.c
@@ -754,13 +754,6 @@ static int __init init_m32r_pcc(void)
 		ret = pcmcia_register_socket(&socket[i].socket);
 		if (!ret)
 			socket[i].flags |= IS_REGISTERED;
-
-#if 0	/* driver model ordering issue */
-		class_device_create_file(&socket[i].socket.dev,
-					 &class_device_attr_info);
-		class_device_create_file(&socket[i].socket.dev,
-					 &class_device_attr_exca);
-#endif
 	}
 
 	/* Finally, schedule a polling interrupt */
diff --git a/drivers/pcmcia/m32r_pcc.c b/drivers/pcmcia/m32r_pcc.c
index a77e571b08b8..eb126b98ed8a 100644
--- a/drivers/pcmcia/m32r_pcc.c
+++ b/drivers/pcmcia/m32r_pcc.c
@@ -716,13 +716,6 @@ static int __init init_m32r_pcc(void)
 		ret = pcmcia_register_socket(&socket[i].socket);
 		if (!ret)
 			socket[i].flags |= IS_REGISTERED;
-
-#if 0	/* driver model ordering issue */
-		class_device_create_file(&socket[i].socket.dev,
-					 &class_device_attr_info);
-		class_device_create_file(&socket[i].socket.dev,
-					 &class_device_attr_exca);
-#endif
 	}
 
 	/* Finally, schedule a polling interrupt */
diff --git a/drivers/pcmcia/pcmcia_cis.c b/drivers/pcmcia/pcmcia_cis.c
index e2c92415b892..1c05d74e850d 100644
--- a/drivers/pcmcia/pcmcia_cis.c
+++ b/drivers/pcmcia/pcmcia_cis.c
@@ -44,7 +44,7 @@ int pccard_read_tuple(struct pcmcia_socket *s, unsigned int function,
 
 	buf = kmalloc(256, GFP_KERNEL);
 	if (buf == NULL) {
-		dev_printk(KERN_WARNING, &s->dev, "no memory to read tuple\n");
+		dev_warn(&s->dev, "no memory to read tuple\n");
 		return -ENOMEM;
 	}
 	tuple.DesiredTuple = code;
@@ -94,7 +94,7 @@ int pccard_loop_tuple(struct pcmcia_socket *s, unsigned int function,
 
 	buf = kzalloc(256, GFP_KERNEL);
 	if (buf == NULL) {
-		dev_printk(KERN_WARNING, &s->dev, "no memory to read tuple\n");
+		dev_warn(&s->dev, "no memory to read tuple\n");
 		return -ENOMEM;
 	}
 
diff --git a/drivers/pcmcia/pcmcia_resource.c b/drivers/pcmcia/pcmcia_resource.c
index e8c19def1b0f..34aad895a239 100644
--- a/drivers/pcmcia/pcmcia_resource.c
+++ b/drivers/pcmcia/pcmcia_resource.c
@@ -508,8 +508,7 @@ int pcmcia_enable_device(struct pcmcia_device *p_dev)
 	s->socket.Vpp = p_dev->vpp;
 	if (s->ops->set_socket(s, &s->socket)) {
 		mutex_unlock(&s->ops_mutex);
-		dev_printk(KERN_WARNING, &p_dev->dev,
-			   "Unable to set socket state\n");
+		dev_warn(&p_dev->dev, "Unable to set socket state\n");
 		return -EINVAL;
 	}
 
@@ -736,13 +735,11 @@ __pcmcia_request_exclusive_irq(struct pcmcia_device *p_dev,
 	ret = request_irq(p_dev->irq, handler, 0, p_dev->devname, p_dev->priv);
 	if (ret) {
 		ret = pcmcia_request_irq(p_dev, handler);
-		dev_printk(KERN_WARNING, &p_dev->dev, "pcmcia: "
-			"request for exclusive IRQ could not be fulfilled.\n");
-		dev_printk(KERN_WARNING, &p_dev->dev, "pcmcia: the driver "
-			"needs updating to supported shared IRQ lines.\n");
+		dev_warn(&p_dev->dev, "pcmcia: request for exclusive IRQ could not be fulfilled\n");
+		dev_warn(&p_dev->dev, "pcmcia: the driver needs updating to supported shared IRQ lines\n");
 	}
 	if (ret)
-		dev_printk(KERN_INFO, &p_dev->dev, "request_irq() failed\n");
+		dev_info(&p_dev->dev, "request_irq() failed\n");
 	else
 		p_dev->_irq = 1;
 
diff --git a/drivers/pcmcia/rsrc_nonstatic.c b/drivers/pcmcia/rsrc_nonstatic.c
index 065704c605d5..5ef7b46a2578 100644
--- a/drivers/pcmcia/rsrc_nonstatic.c
+++ b/drivers/pcmcia/rsrc_nonstatic.c
@@ -191,15 +191,13 @@ static void do_io_probe(struct pcmcia_socket *s, unsigned int base,
 	int any;
 	u_char *b, hole, most;
 
-	dev_printk(KERN_INFO, &s->dev, "cs: IO port probe %#x-%#x:",
-		base, base+num-1);
+	dev_info(&s->dev, "cs: IO port probe %#x-%#x:", base, base+num-1);
 
 	/* First, what does a floating port look like? */
 	b = kzalloc(256, GFP_KERNEL);
 	if (!b) {
-		printk("\n");
-		dev_printk(KERN_ERR, &s->dev,
-			"do_io_probe: unable to kmalloc 256 bytes");
+		pr_cont("\n");
+		dev_err(&s->dev, "do_io_probe: unable to kmalloc 256 bytes\n");
 		return;
 	}
 	for (i = base, most = 0; i < base+num; i += 8) {
@@ -223,7 +221,7 @@ static void do_io_probe(struct pcmcia_socket *s, unsigned int base,
 		res = claim_region(s, i, 8, IORESOURCE_IO, "PCMCIA ioprobe");
 		if (!res) {
 			if (!any)
-				printk(" excluding");
+				pr_cont(" excluding");
 			if (!bad)
 				bad = any = i;
 			continue;
@@ -234,13 +232,13 @@ static void do_io_probe(struct pcmcia_socket *s, unsigned int base,
 		free_region(res);
 		if (j < 8) {
 			if (!any)
-				printk(" excluding");
+				pr_cont(" excluding");
 			if (!bad)
 				bad = any = i;
 		} else {
 			if (bad) {
 				sub_interval(&s_data->io_db, bad, i-bad);
-				printk(" %#x-%#x", bad, i-1);
+				pr_cont(" %#x-%#x", bad, i-1);
 				bad = 0;
 			}
 		}
@@ -248,15 +246,15 @@ static void do_io_probe(struct pcmcia_socket *s, unsigned int base,
 	if (bad) {
 		if ((num > 16) && (bad == base) && (i == base+num)) {
 			sub_interval(&s_data->io_db, bad, i-bad);
-			printk(" nothing: probe failed.\n");
+			pr_cont(" nothing: probe failed.\n");
 			return;
 		} else {
 			sub_interval(&s_data->io_db, bad, i-bad);
-			printk(" %#x-%#x", bad, i-1);
+			pr_cont(" %#x-%#x", bad, i-1);
 		}
 	}
 
-	printk(any ? "\n" : " clean.\n");
+	pr_cont("%s\n", !any ? " clean" : "");
 }
 #endif
 
@@ -413,8 +411,8 @@ static int do_mem_probe(struct pcmcia_socket *s, u_long base, u_long num,
 	struct socket_data *s_data = s->resource_data;
 	u_long i, j, bad, fail, step;
 
-	dev_printk(KERN_INFO, &s->dev, "cs: memory probe 0x%06lx-0x%06lx:",
-		base, base+num-1);
+	dev_info(&s->dev, "cs: memory probe 0x%06lx-0x%06lx:",
+		 base, base+num-1);
 	bad = fail = 0;
 	step = (num < 0x20000) ? 0x2000 : ((num>>4) & ~0x1fff);
 	/* don't allow too large steps */
@@ -438,13 +436,13 @@ static int do_mem_probe(struct pcmcia_socket *s, u_long base, u_long num,
 		}
 		if (i != j) {
 			if (!bad)
-				printk(" excluding");
-			printk(" %#05lx-%#05lx", i, j-1);
+				pr_cont(" excluding");
+			pr_cont(" %#05lx-%#05lx", i, j-1);
 			sub_interval(&s_data->mem_db, i, j-i);
 			bad += j-i;
 		}
 	}
-	printk(bad ? "\n" : " clean.\n");
+	pr_cont("%s\n", !bad ? " clean" : "");
 	return num - bad;
 }
 
@@ -495,7 +493,7 @@ static int validate_mem(struct pcmcia_socket *s, unsigned int probe_mask)
 			return 0;
 		if (s_data->mem_db_valid.next != &s_data->mem_db_valid)
 			return 0;
-		dev_printk(KERN_NOTICE, &s->dev,
+		dev_notice(&s->dev,
 			   "cs: warning: no high memory space available!\n");
 		return -ENODEV;
 	}
@@ -975,9 +973,9 @@ static int nonstatic_autoadd_resources(struct pcmcia_socket *s)
 			if (res == &ioport_resource)
 				continue;
 
-			dev_printk(KERN_INFO, &s->cb_dev->dev,
-				   "pcmcia: parent PCI bridge window: %pR\n",
-				   res);
+			dev_info(&s->cb_dev->dev,
+				 "pcmcia: parent PCI bridge window: %pR\n",
+				 res);
 			if (!adjust_io(s, ADD_MANAGED_RESOURCE, res->start, res->end))
 				done |= IORESOURCE_IO;
 
@@ -990,9 +988,9 @@ static int nonstatic_autoadd_resources(struct pcmcia_socket *s)
 			if (res == &iomem_resource)
 				continue;
 
-			dev_printk(KERN_INFO, &s->cb_dev->dev,
-				   "pcmcia: parent PCI bridge window: %pR\n",
-				   res);
+			dev_info(&s->cb_dev->dev,
+				 "pcmcia: parent PCI bridge window: %pR\n",
+				 res);
 			if (!adjust_memory(s, ADD_MANAGED_RESOURCE, res->start, res->end))
 				done |= IORESOURCE_MEM;
 		}
diff --git a/drivers/pcmcia/ti113x.h b/drivers/pcmcia/ti113x.h
index a71789486cdf..5cb670e037a0 100644
--- a/drivers/pcmcia/ti113x.h
+++ b/drivers/pcmcia/ti113x.h
@@ -372,8 +372,8 @@ static void ti12xx_irqroute_func0(struct yenta_socket *socket)
 
 	mfunc = mfunc_old = config_readl(socket, TI122X_MFUNC);
 	devctl = config_readb(socket, TI113X_DEVICE_CONTROL);
-	dev_printk(KERN_INFO, &socket->dev->dev,
-		   "TI: mfunc 0x%08x, devctl 0x%02x\n", mfunc, devctl);
+	dev_info(&socket->dev->dev, "TI: mfunc 0x%08x, devctl 0x%02x\n",
+		 mfunc, devctl);
 
 	/* make sure PCI interrupts are enabled before probing */
 	ti_init(socket);
@@ -387,8 +387,8 @@ static void ti12xx_irqroute_func0(struct yenta_socket *socket)
 	 * We're here which means PCI interrupts are _not_ delivered. try to
 	 * find the right setting (all serial or parallel)
 	 */
-	dev_printk(KERN_INFO, &socket->dev->dev,
-		   "TI: probing PCI interrupt failed, trying to fix\n");
+	dev_info(&socket->dev->dev,
+		 "TI: probing PCI interrupt failed, trying to fix\n");
 
 	/* for serial PCI make sure MFUNC3 is set to IRQSER */
 	if ((devctl & TI113X_DCR_IMODE_MASK) == TI12XX_DCR_IMODE_ALL_SERIAL) {
@@ -412,8 +412,8 @@ static void ti12xx_irqroute_func0(struct yenta_socket *socket)
 
 				pci_irq_status = yenta_probe_cb_irq(socket);
 				if (pci_irq_status == 1) {
-					dev_printk(KERN_INFO, &socket->dev->dev,
-					    "TI: all-serial interrupts ok\n");
+					dev_info(&socket->dev->dev,
+						 "TI: all-serial interrupts ok\n");
 					mfunc_old = mfunc;
 					goto out;
 				}
@@ -428,8 +428,8 @@ static void ti12xx_irqroute_func0(struct yenta_socket *socket)
 		}
 
 		/* serial PCI interrupts not working fall back to parallel */
-		dev_printk(KERN_INFO, &socket->dev->dev,
-			   "TI: falling back to parallel PCI interrupts\n");
+		dev_info(&socket->dev->dev,
+			 "TI: falling back to parallel PCI interrupts\n");
 		devctl &= ~TI113X_DCR_IMODE_MASK;
 		devctl |= TI113X_DCR_IMODE_SERIAL; /* serial ISA could be right */
 		config_writeb(socket, TI113X_DEVICE_CONTROL, devctl);
@@ -460,8 +460,7 @@ static void ti12xx_irqroute_func0(struct yenta_socket *socket)
 	pci_irq_status = yenta_probe_cb_irq(socket);
 	if (pci_irq_status == 1) {
 		mfunc_old = mfunc;
-		dev_printk(KERN_INFO, &socket->dev->dev,
-			   "TI: parallel PCI interrupts ok\n");
+		dev_info(&socket->dev->dev, "TI: parallel PCI interrupts ok\n");
 	} else {
 		/* not working, back to old value */
 		mfunc = mfunc_old;
@@ -473,9 +472,8 @@ static void ti12xx_irqroute_func0(struct yenta_socket *socket)
 out:
 	if (pci_irq_status < 1) {
 		socket->cb_irq = 0;
-		dev_printk(KERN_INFO, &socket->dev->dev,
-			   "Yenta TI: no PCI interrupts. Fish. "
-			   "Please report.\n");
+		dev_info(&socket->dev->dev,
+			 "Yenta TI: no PCI interrupts. Fish. Please report.\n");
 	}
 }
 
@@ -547,9 +545,8 @@ static void ti12xx_irqroute_func1(struct yenta_socket *socket)
 
 	mfunc = mfunc_old = config_readl(socket, TI122X_MFUNC);
 	devctl = config_readb(socket, TI113X_DEVICE_CONTROL);
-	dev_printk(KERN_INFO, &socket->dev->dev,
-		   "TI: mfunc 0x%08x, devctl 0x%02x\n",
-		   mfunc, devctl);
+	dev_info(&socket->dev->dev, "TI: mfunc 0x%08x, devctl 0x%02x\n",
+		 mfunc, devctl);
 
 	/* if IRQs are configured as tied, align irq of func1 with func0 */
 	sysctl = config_readl(socket, TI113X_SYSTEM_CONTROL);
@@ -568,8 +565,8 @@ static void ti12xx_irqroute_func1(struct yenta_socket *socket)
 	 * We're here which means PCI interrupts are _not_ delivered. try to
 	 * find the right setting
 	 */
-	dev_printk(KERN_INFO, &socket->dev->dev,
-		   "TI: probing PCI interrupt failed, trying to fix\n");
+	dev_info(&socket->dev->dev,
+		 "TI: probing PCI interrupt failed, trying to fix\n");
 
 	/* if all serial: set INTRTIE, probe again */
 	if ((devctl & TI113X_DCR_IMODE_MASK) == TI12XX_DCR_IMODE_ALL_SERIAL) {
@@ -578,8 +575,8 @@ static void ti12xx_irqroute_func1(struct yenta_socket *socket)
 		if (ti12xx_tie_interrupts(socket, &old_irq)) {
 			pci_irq_status = yenta_probe_cb_irq(socket);
 			if (pci_irq_status == 1) {
-				dev_printk(KERN_INFO, &socket->dev->dev,
-					"TI: all-serial interrupts, tied ok\n");
+				dev_info(&socket->dev->dev,
+					 "TI: all-serial interrupts, tied ok\n");
 				goto out;
 			}
 
@@ -616,8 +613,8 @@ static void ti12xx_irqroute_func1(struct yenta_socket *socket)
 
 			pci_irq_status = yenta_probe_cb_irq(socket);
 			if (pci_irq_status == 1) {
-				dev_printk(KERN_INFO, &socket->dev->dev,
-					   "TI: parallel PCI interrupts ok\n");
+				dev_info(&socket->dev->dev,
+					 "TI: parallel PCI interrupts ok\n");
 				goto out;
 			}
 
@@ -632,8 +629,8 @@ static void ti12xx_irqroute_func1(struct yenta_socket *socket)
 		if (ti12xx_tie_interrupts(socket, &old_irq)) {
 			pci_irq_status = yenta_probe_cb_irq(socket);
 			if (pci_irq_status == 1) {
-				dev_printk(KERN_INFO, &socket->dev->dev,
-				    "TI: parallel PCI interrupts, tied ok\n");
+				dev_info(&socket->dev->dev,
+					 "TI: parallel PCI interrupts, tied ok\n");
 				goto out;
 			}
 
@@ -644,8 +641,8 @@ static void ti12xx_irqroute_func1(struct yenta_socket *socket)
 out:
 	if (pci_irq_status < 1) {
 		socket->cb_irq = 0;
-		dev_printk(KERN_INFO, &socket->dev->dev,
-			   "TI: no PCI interrupts. Fish. Please report.\n");
+		dev_info(&socket->dev->dev,
+			 "TI: no PCI interrupts. Fish. Please report.\n");
 	}
 }
 
@@ -849,13 +846,12 @@ static int ti12xx_override(struct yenta_socket *socket)
 	/* make sure that memory burst is active */
 	val_orig = val = config_readl(socket, TI113X_SYSTEM_CONTROL);
 	if (disable_clkrun && PCI_FUNC(socket->dev->devfn) == 0) {
-		dev_printk(KERN_INFO, &socket->dev->dev,
-			   "Disabling CLKRUN feature\n");
+		dev_info(&socket->dev->dev, "Disabling CLKRUN feature\n");
 		val |= TI113X_SCR_KEEPCLK;
 	}
 	if (!(val & TI122X_SCR_MRBURSTUP)) {
-		dev_printk(KERN_INFO, &socket->dev->dev,
-			   "Enabling burst memory read transactions\n");
+		dev_info(&socket->dev->dev,
+			 "Enabling burst memory read transactions\n");
 		val |= TI122X_SCR_MRBURSTUP;
 	}
 	if (val_orig != val)
@@ -866,12 +862,10 @@ static int ti12xx_override(struct yenta_socket *socket)
 	 * CSC interrupts to PCI rather than INTVAL.
 	 */
 	val = config_readb(socket, TI1250_DIAGNOSTIC);
-	dev_printk(KERN_INFO, &socket->dev->dev,
-		   "Using %s to route CSC interrupts to PCI\n",
-		   (val & TI1250_DIAG_PCI_CSC) ? "CSCINT" : "INTVAL");
-	dev_printk(KERN_INFO, &socket->dev->dev,
-		   "Routing CardBus interrupts to %s\n",
-		   (val & TI1250_DIAG_PCI_IREQ) ? "PCI" : "ISA");
+	dev_info(&socket->dev->dev, "Using %s to route CSC interrupts to PCI\n",
+		 (val & TI1250_DIAG_PCI_CSC) ? "CSCINT" : "INTVAL");
+	dev_info(&socket->dev->dev, "Routing CardBus interrupts to %s\n",
+		 (val & TI1250_DIAG_PCI_IREQ) ? "PCI" : "ISA");
 
 	/* do irqrouting, depending on function */
 	if (PCI_FUNC(socket->dev->devfn) == 0)
@@ -896,9 +890,9 @@ static int ti1250_override(struct yenta_socket *socket)
 		diag |= TI1250_DIAG_PCI_CSC | TI1250_DIAG_PCI_IREQ;
 
 	if (diag != old) {
-		dev_printk(KERN_INFO, &socket->dev->dev,
-			   "adjusting diagnostic: %02x -> %02x\n",
-			   old, diag);
+		dev_info(&socket->dev->dev,
+			 "adjusting diagnostic: %02x -> %02x\n",
+			 old, diag);
 		config_writeb(socket, TI1250_DIAGNOSTIC, diag);
 	}
 
@@ -963,9 +957,9 @@ static void ene_tune_bridge(struct pcmcia_socket *sock, struct pci_bus *bus)
 		/* default to clear TLTEnable bit, old behaviour */
 		test_c9 &= ~ENE_TEST_C9_TLTENABLE;
 
-	dev_printk(KERN_INFO, &socket->dev->dev,
-		   "EnE: chaning testregister 0xC9, %02x -> %02x\n",
-		   old_c9, test_c9);
+	dev_info(&socket->dev->dev,
+		 "EnE: changing testregister 0xC9, %02x -> %02x\n",
+		 old_c9, test_c9);
 	config_writeb(socket, ENE_TEST_C9, test_c9);
 }
 
diff --git a/drivers/pcmcia/topic.h b/drivers/pcmcia/topic.h
index 615a45a8fe86..582688fe7505 100644
--- a/drivers/pcmcia/topic.h
+++ b/drivers/pcmcia/topic.h
@@ -104,6 +104,9 @@
 #define TOPIC_EXCA_IF_CONTROL		0x3e	/* 8 bit */
 #define TOPIC_EXCA_IFC_33V_ENA		0x01
 
+#define TOPIC_PCI_CFG_PPBCN		0x3e	/* 16-bit */
+#define TOPIC_PCI_CFG_PPBCN_WBEN	0x0400
+
 static void topic97_zoom_video(struct pcmcia_socket *sock, int onoff)
 {
 	struct yenta_socket *socket = container_of(sock, struct yenta_socket, socket);
@@ -138,6 +141,7 @@ static int topic97_override(struct yenta_socket *socket)
 static int topic95_override(struct yenta_socket *socket)
 {
 	u8 fctrl;
+	u16 ppbcn;
 
 	/* enable 3.3V support for 16bit cards */
 	fctrl = exca_readb(socket, TOPIC_EXCA_IF_CONTROL);
@@ -146,6 +150,18 @@ static int topic95_override(struct yenta_socket *socket)
 	/* tell yenta to use exca registers to power 16bit cards */
 	socket->flags |= YENTA_16BIT_POWER_EXCA | YENTA_16BIT_POWER_DF;
 
+	/* Disable write buffers to prevent lockups under load with numerous
+	   Cardbus cards, observed on Tecra 500CDT and reported elsewhere on the
+	   net.  This is not a power-on default according to the datasheet
+	   but some BIOSes seem to set it. */
+	if (pci_read_config_word(socket->dev, TOPIC_PCI_CFG_PPBCN, &ppbcn) == 0
+	    && socket->dev->revision <= 7
+	    && (ppbcn & TOPIC_PCI_CFG_PPBCN_WBEN)) {
+		ppbcn &= ~TOPIC_PCI_CFG_PPBCN_WBEN;
+		pci_write_config_word(socket->dev, TOPIC_PCI_CFG_PPBCN, ppbcn);
+		dev_info(&socket->dev->dev, "Disabled ToPIC95 Cardbus write buffers.\n");
+	}
+
 	return 0;
 }
 
diff --git a/drivers/pcmcia/vrc4171_card.c b/drivers/pcmcia/vrc4171_card.c
index 21973d55a055..1e5fa211fb70 100644
--- a/drivers/pcmcia/vrc4171_card.c
+++ b/drivers/pcmcia/vrc4171_card.c
@@ -84,32 +84,32 @@ MODULE_LICENSE("GPL");
 #define IO_MAX_MAPS	2
 #define MEM_MAX_MAPS	5
 
-typedef enum {
+enum vrc4171_slot {
 	SLOT_PROBE = 0,
 	SLOT_NOPROBE_IO,
 	SLOT_NOPROBE_MEM,
 	SLOT_NOPROBE_ALL,
 	SLOT_INITIALIZED,
-} vrc4171_slot_t;
+};
 
-typedef enum {
+enum vrc4171_slotb {
 	SLOTB_IS_NONE,
 	SLOTB_IS_PCCARD,
 	SLOTB_IS_CF,
 	SLOTB_IS_FLASHROM,
-} vrc4171_slotb_t;
+};
 
-typedef struct vrc4171_socket {
-	vrc4171_slot_t slot;
+struct vrc4171_socket {
+	enum vrc4171_slot slot;
 	struct pcmcia_socket pcmcia_socket;
 	char name[24];
 	int csc_irq;
 	int io_irq;
 	spinlock_t lock;
-} vrc4171_socket_t;
+};
 
-static vrc4171_socket_t vrc4171_sockets[CARD_MAX_SLOTS];
-static vrc4171_slotb_t vrc4171_slotb = SLOTB_IS_NONE;
+static struct vrc4171_socket vrc4171_sockets[CARD_MAX_SLOTS];
+static enum vrc4171_slotb vrc4171_slotb = SLOTB_IS_NONE;
 static char vrc4171_card_name[] = "NEC VRC4171 Card Controller";
 static unsigned int vrc4171_irq;
 static uint16_t vrc4171_irq_mask = 0xdeb8;
@@ -141,7 +141,7 @@ static inline uint16_t vrc4171_get_irq_status(void)
 	return inw(INTERRUPT_STATUS);
 }
 
-static inline void vrc4171_set_multifunction_pin(vrc4171_slotb_t config)
+static inline void vrc4171_set_multifunction_pin(enum vrc4171_slotb config)
 {
 	uint16_t config1;
 
@@ -234,7 +234,7 @@ static inline int search_nonuse_irq(void)
 
 static int pccard_init(struct pcmcia_socket *sock)
 {
-	vrc4171_socket_t *socket;
+	struct vrc4171_socket *socket;
 	unsigned int slot;
 
 	sock->features |= SS_CAP_PCCARD | SS_CAP_PAGE_REGS;
@@ -317,7 +317,7 @@ static inline uint8_t set_Vcc_value(u_char Vcc)
 
 static int pccard_set_socket(struct pcmcia_socket *sock, socket_state_t *state)
 {
-	vrc4171_socket_t *socket;
+	struct vrc4171_socket *socket;
 	unsigned int slot;
 	uint8_t voltage, power, control, cscint;
 
@@ -517,7 +517,7 @@ static inline unsigned int get_events(int slot)
 
 static irqreturn_t pccard_interrupt(int irq, void *dev_id)
 {
-	vrc4171_socket_t *socket;
+	struct vrc4171_socket *socket;
 	unsigned int events;
 	irqreturn_t retval = IRQ_NONE;
 	uint16_t status;
@@ -567,7 +567,7 @@ static inline void reserve_using_irq(int slot)
 
 static int vrc4171_add_sockets(void)
 {
-	vrc4171_socket_t *socket;
+	struct vrc4171_socket *socket;
 	int slot, retval;
 
 	for (slot = 0; slot < CARD_MAX_SLOTS; slot++) {
@@ -617,7 +617,7 @@ static int vrc4171_add_sockets(void)
 
 static void vrc4171_remove_sockets(void)
 {
-	vrc4171_socket_t *socket;
+	struct vrc4171_socket *socket;
 	int slot;
 
 	for (slot = 0; slot < CARD_MAX_SLOTS; slot++) {
diff --git a/drivers/pcmcia/yenta_socket.c b/drivers/pcmcia/yenta_socket.c
index 965bd8491233..5d6d9b1549bc 100644
--- a/drivers/pcmcia/yenta_socket.c
+++ b/drivers/pcmcia/yenta_socket.c
@@ -712,10 +712,9 @@ static int yenta_allocate_res(struct yenta_socket *socket, int nr, unsigned type
 		pcibios_bus_to_resource(dev->bus, res, &region);
 		if (pci_claim_resource(dev, PCI_BRIDGE_RESOURCES + nr) == 0)
 			return 0;
-		dev_printk(KERN_INFO, &dev->dev,
-			   "Preassigned resource %d busy or not available, "
-			   "reconfiguring...\n",
-			   nr);
+		dev_info(&dev->dev,
+			 "Preassigned resource %d busy or not available, reconfiguring...\n",
+			 nr);
 	}
 
 	if (type & IORESOURCE_IO) {
@@ -738,9 +737,9 @@ static int yenta_allocate_res(struct yenta_socket *socket, int nr, unsigned type
 			return 1;
 	}
 
-	dev_printk(KERN_INFO, &dev->dev,
-		   "no resource of type %x available, trying to continue...\n",
-		   type);
+	dev_info(&dev->dev,
+		 "no resource of type %x available, trying to continue...\n",
+		 type);
 	res->start = res->end = res->flags = 0;
 	return 0;
 }
@@ -802,13 +801,13 @@ static void yenta_close(struct pci_dev *dev)
 	else
 		del_timer_sync(&sock->poll_timer);
 
-	if (sock->base)
-		iounmap(sock->base);
+	iounmap(sock->base);
 	yenta_free_resources(sock);
 
 	pci_release_regions(dev);
 	pci_disable_device(dev);
 	pci_set_drvdata(dev, NULL);
+	kfree(sock);
 }
 
 
@@ -979,8 +978,8 @@ static int yenta_probe_cb_irq(struct yenta_socket *socket)
 	socket->probe_status = 0;
 
 	if (request_irq(socket->cb_irq, yenta_probe_handler, IRQF_SHARED, "yenta", socket)) {
-		dev_printk(KERN_WARNING, &socket->dev->dev,
-			   "request_irq() in yenta_probe_cb_irq() failed!\n");
+		dev_warn(&socket->dev->dev,
+			 "request_irq() in yenta_probe_cb_irq() failed!\n");
 		return -1;
 	}
 
@@ -1019,9 +1018,8 @@ static void yenta_get_socket_capabilities(struct yenta_socket *socket, u32 isa_i
 	else
 		socket->socket.irq_mask = 0;
 
-	dev_printk(KERN_INFO, &socket->dev->dev,
-		   "ISA IRQ mask 0x%04x, PCI irq %d\n",
-		   socket->socket.irq_mask, socket->cb_irq);
+	dev_info(&socket->dev->dev, "ISA IRQ mask 0x%04x, PCI irq %d\n",
+		 socket->socket.irq_mask, socket->cb_irq);
 }
 
 /*
@@ -1111,9 +1109,9 @@ static void yenta_fixup_parent_bridge(struct pci_bus *cardbus_bridge)
 
 	/* Show that the wanted subordinate number is not possible: */
 	if (cardbus_bridge->busn_res.end > upper_limit)
-		dev_printk(KERN_WARNING, &cardbus_bridge->dev,
-			   "Upper limit for fixing this "
-			   "bridge's parent bridge: #%02x\n", upper_limit);
+		dev_warn(&cardbus_bridge->dev,
+			 "Upper limit for fixing this bridge's parent bridge: #%02x\n",
+			 upper_limit);
 
 	/* If we have room to increase the bridge's subordinate number, */
 	if (bridge_to_fix->busn_res.end < upper_limit) {
@@ -1122,11 +1120,11 @@ static void yenta_fixup_parent_bridge(struct pci_bus *cardbus_bridge)
 		unsigned char subordinate_to_assign =
 			min_t(int, cardbus_bridge->busn_res.end, upper_limit);
 
-		dev_printk(KERN_INFO, &bridge_to_fix->dev,
-			   "Raising subordinate bus# of parent "
-			   "bus (#%02x) from #%02x to #%02x\n",
-			   bridge_to_fix->number,
-			   (int)bridge_to_fix->busn_res.end, subordinate_to_assign);
+		dev_info(&bridge_to_fix->dev,
+			 "Raising subordinate bus# of parent bus (#%02x) from #%02x to #%02x\n",
+			 bridge_to_fix->number,
+			 (int)bridge_to_fix->busn_res.end,
+			 subordinate_to_assign);
 
 		/* Save the new subordinate in the bus struct of the bridge */
 		bridge_to_fix->busn_res.end = subordinate_to_assign;
@@ -1153,8 +1151,7 @@ static int yenta_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	 * Bail out if so.
 	 */
 	if (!dev->subordinate) {
-		dev_printk(KERN_ERR, &dev->dev, "no bus associated! "
-			   "(try 'pci=assign-busses')\n");
+		dev_err(&dev->dev, "no bus associated! (try 'pci=assign-busses')\n");
 		return -ENODEV;
 	}
 
@@ -1189,7 +1186,7 @@ static int yenta_probe(struct pci_dev *dev, const struct pci_device_id *id)
 		goto disable;
 
 	if (!pci_resource_start(dev, 0)) {
-		dev_printk(KERN_ERR, &dev->dev, "No cardbus resource!\n");
+		dev_err(&dev->dev, "No cardbus resource!\n");
 		ret = -ENODEV;
 		goto release;
 	}
@@ -1208,8 +1205,8 @@ static int yenta_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	 * report the subsystem vendor and device for help debugging
 	 * the irq stuff...
 	 */
-	dev_printk(KERN_INFO, &dev->dev, "CardBus bridge found [%04x:%04x]\n",
-		   dev->subsystem_vendor, dev->subsystem_device);
+	dev_info(&dev->dev, "CardBus bridge found [%04x:%04x]\n",
+		 dev->subsystem_vendor, dev->subsystem_device);
 
 	yenta_config_init(socket);
 
@@ -1239,12 +1236,10 @@ static int yenta_probe(struct pci_dev *dev, const struct pci_device_id *id)
 		setup_timer(&socket->poll_timer, yenta_interrupt_wrapper,
 			    (unsigned long)socket);
 		mod_timer(&socket->poll_timer, jiffies + HZ);
-		dev_printk(KERN_INFO, &dev->dev,
-			   "no PCI IRQ, CardBus support disabled for this "
-			   "socket.\n");
-		dev_printk(KERN_INFO, &dev->dev,
-			   "check your BIOS CardBus, BIOS IRQ or ACPI "
-			   "settings.\n");
+		dev_info(&dev->dev,
+			 "no PCI IRQ, CardBus support disabled for this socket.\n");
+		dev_info(&dev->dev,
+			 "check your BIOS CardBus, BIOS IRQ or ACPI settings.\n");
 	} else {
 		socket->socket.features |= SS_CAP_CARDBUS;
 	}
@@ -1252,32 +1247,41 @@ static int yenta_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	/* Figure out what the dang thing can do for the PCMCIA layer... */
 	yenta_interrogate(socket);
 	yenta_get_socket_capabilities(socket, isa_interrupts);
-	dev_printk(KERN_INFO, &dev->dev,
-		   "Socket status: %08x\n", cb_readl(socket, CB_SOCKET_STATE));
+	dev_info(&dev->dev, "Socket status: %08x\n",
+		 cb_readl(socket, CB_SOCKET_STATE));
 
 	yenta_fixup_parent_bridge(dev->subordinate);
 
 	/* Register it with the pcmcia layer.. */
 	ret = pcmcia_register_socket(&socket->socket);
-	if (ret == 0) {
-		/* Add the yenta register attributes */
-		ret = device_create_file(&dev->dev, &dev_attr_yenta_registers);
-		if (ret == 0)
-			goto out;
-
-		/* error path... */
-		pcmcia_unregister_socket(&socket->socket);
-	}
+	if (ret)
+		goto free_irq;
+
+	/* Add the yenta register attributes */
+	ret = device_create_file(&dev->dev, &dev_attr_yenta_registers);
+	if (ret)
+		goto unregister_socket;
 
+	return ret;
+
+	/* error path... */
+ unregister_socket:
+	pcmcia_unregister_socket(&socket->socket);
+ free_irq:
+	if (socket->cb_irq)
+		free_irq(socket->cb_irq, socket);
+	else
+		del_timer_sync(&socket->poll_timer);
  unmap:
 	iounmap(socket->base);
+	yenta_free_resources(socket);
  release:
 	pci_release_regions(dev);
  disable:
 	pci_disable_device(dev);
  free:
+	pci_set_drvdata(dev, NULL);
 	kfree(socket);
- out:
 	return ret;
 }
 
diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig
index 909133c6ffb7..7137a077b9a6 100644
--- a/drivers/platform/x86/Kconfig
+++ b/drivers/platform/x86/Kconfig
@@ -670,7 +670,7 @@ config TOSHIBA_HAPS
 	depends on ACPI
 	---help---
 	  This driver adds support for the built-in accelerometer
-	  found on recent Toshiba laptops equiped with HID TOS620A
+	  found on recent Toshiba laptops equipped with HID TOS620A
 	  device.
 
 	  This driver receives ACPI notify events 0x80 when the sensor
@@ -679,7 +679,7 @@ config TOSHIBA_HAPS
 	  been stabilized.
 
 	  Also provides sysfs entries to get/set the desired protection
-	  level and reseting the HDD protection interface.
+	  level and resetting the HDD protection interface.
 
 	  If you have a recent Toshiba laptop with a built-in accelerometer
 	  device, say Y.
diff --git a/drivers/power/reset/ltc2952-poweroff.c b/drivers/power/reset/ltc2952-poweroff.c
index 1e08195551fe..5f855f99bdfc 100644
--- a/drivers/power/reset/ltc2952-poweroff.c
+++ b/drivers/power/reset/ltc2952-poweroff.c
@@ -158,7 +158,6 @@ static irqreturn_t ltc2952_poweroff_handler(int irq, void *dev_id)
 			      HRTIMER_MODE_REL);
 	} else {
 		hrtimer_cancel(&data->timer_trigger);
-		/* omitting return value check, timer should have been valid */
 	}
 	return IRQ_HANDLED;
 }
diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c
index ba34c7d89042..3a7769fe53de 100644
--- a/drivers/pwm/core.c
+++ b/drivers/pwm/core.c
@@ -223,13 +223,16 @@ void *pwm_get_chip_data(struct pwm_device *pwm)
 EXPORT_SYMBOL_GPL(pwm_get_chip_data);
 
 /**
- * pwmchip_add() - register a new PWM chip
+ * pwmchip_add_with_polarity() - register a new PWM chip
  * @chip: the PWM chip to add
+ * @polarity: initial polarity of PWM channels
  *
  * Register a new PWM chip. If chip->base < 0 then a dynamically assigned base
- * will be used.
+ * will be used. The initial polarity for all channels is specified by the
+ * @polarity parameter.
  */
-int pwmchip_add(struct pwm_chip *chip)
+int pwmchip_add_with_polarity(struct pwm_chip *chip,
+			      enum pwm_polarity polarity)
 {
 	struct pwm_device *pwm;
 	unsigned int i;
@@ -259,6 +262,7 @@ int pwmchip_add(struct pwm_chip *chip)
 		pwm->chip = chip;
 		pwm->pwm = chip->base + i;
 		pwm->hwpwm = i;
+		pwm->polarity = polarity;
 
 		radix_tree_insert(&pwm_tree, pwm->pwm, pwm);
 	}
@@ -279,6 +283,19 @@ out:
 	mutex_unlock(&pwm_lock);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(pwmchip_add_with_polarity);
+
+/**
+ * pwmchip_add() - register a new PWM chip
+ * @chip: the PWM chip to add
+ *
+ * Register a new PWM chip. If chip->base < 0 then a dynamically assigned base
+ * will be used. The initial polarity for all channels is normal.
+ */
+int pwmchip_add(struct pwm_chip *chip)
+{
+	return pwmchip_add_with_polarity(chip, PWM_POLARITY_NORMAL);
+}
 EXPORT_SYMBOL_GPL(pwmchip_add);
 
 /**
@@ -586,6 +603,23 @@ void pwm_add_table(struct pwm_lookup *table, size_t num)
 }
 
 /**
+ * pwm_remove_table() - unregister PWM device consumers
+ * @table: array of consumers to unregister
+ * @num: number of consumers in table
+ */
+void pwm_remove_table(struct pwm_lookup *table, size_t num)
+{
+	mutex_lock(&pwm_lookup_lock);
+
+	while (num--) {
+		list_del(&table->list);
+		table++;
+	}
+
+	mutex_unlock(&pwm_lookup_lock);
+}
+
+/**
  * pwm_get() - look up and request a PWM device
  * @dev: device for PWM consumer
  * @con_id: consumer name
diff --git a/drivers/pwm/pwm-atmel.c b/drivers/pwm/pwm-atmel.c
index d3c22de9ee47..a947c9095d9d 100644
--- a/drivers/pwm/pwm-atmel.c
+++ b/drivers/pwm/pwm-atmel.c
@@ -8,9 +8,11 @@
  */
 
 #include <linux/clk.h>
+#include <linux/delay.h>
 #include <linux/err.h>
 #include <linux/io.h>
 #include <linux/module.h>
+#include <linux/mutex.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
@@ -21,6 +23,7 @@
 #define PWM_ENA			0x04
 #define PWM_DIS			0x08
 #define PWM_SR			0x0C
+#define PWM_ISR			0x1C
 /* Bit field in SR */
 #define PWM_SR_ALL_CH_ON	0x0F
 
@@ -60,6 +63,9 @@ struct atmel_pwm_chip {
 	struct clk *clk;
 	void __iomem *base;
 
+	unsigned int updated_pwms;
+	struct mutex isr_lock; /* ISR is cleared when read, ensure only one thread does that */
+
 	void (*config)(struct pwm_chip *chip, struct pwm_device *pwm,
 		       unsigned long dty, unsigned long prd);
 };
@@ -144,6 +150,10 @@ static int atmel_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm,
 	val = (val & ~PWM_CMR_CPRE_MSK) | (pres & PWM_CMR_CPRE_MSK);
 	atmel_pwm_ch_writel(atmel_pwm, pwm->hwpwm, PWM_CMR, val);
 	atmel_pwm->config(chip, pwm, dty, prd);
+	mutex_lock(&atmel_pwm->isr_lock);
+	atmel_pwm->updated_pwms |= atmel_pwm_readl(atmel_pwm, PWM_ISR);
+	atmel_pwm->updated_pwms &= ~(1 << pwm->hwpwm);
+	mutex_unlock(&atmel_pwm->isr_lock);
 
 	clk_disable(atmel_pwm->clk);
 	return ret;
@@ -155,24 +165,25 @@ static void atmel_pwm_config_v1(struct pwm_chip *chip, struct pwm_device *pwm,
 	struct atmel_pwm_chip *atmel_pwm = to_atmel_pwm_chip(chip);
 	unsigned int val;
 
-	if (test_bit(PWMF_ENABLED, &pwm->flags)) {
-		/*
-		 * If the PWM channel is enabled, using the update register,
-		 * it needs to set bit 10 of CMR to 0
-		 */
-		atmel_pwm_ch_writel(atmel_pwm, pwm->hwpwm, PWMV1_CUPD, dty);
 
-		val = atmel_pwm_ch_readl(atmel_pwm, pwm->hwpwm, PWM_CMR);
-		val &= ~PWM_CMR_UPD_CDTY;
-		atmel_pwm_ch_writel(atmel_pwm, pwm->hwpwm, PWM_CMR, val);
-	} else {
-		/*
-		 * If the PWM channel is disabled, write value to duty and
-		 * period registers directly.
-		 */
-		atmel_pwm_ch_writel(atmel_pwm, pwm->hwpwm, PWMV1_CDTY, dty);
-		atmel_pwm_ch_writel(atmel_pwm, pwm->hwpwm, PWMV1_CPRD, prd);
-	}
+	atmel_pwm_ch_writel(atmel_pwm, pwm->hwpwm, PWMV1_CUPD, dty);
+
+	val = atmel_pwm_ch_readl(atmel_pwm, pwm->hwpwm, PWM_CMR);
+	val &= ~PWM_CMR_UPD_CDTY;
+	atmel_pwm_ch_writel(atmel_pwm, pwm->hwpwm, PWM_CMR, val);
+
+	/*
+	 * If the PWM channel is enabled, only update CDTY by using the update
+	 * register, it needs to set bit 10 of CMR to 0
+	 */
+	if (test_bit(PWMF_ENABLED, &pwm->flags))
+		return;
+	/*
+	 * If the PWM channel is disabled, write value to duty and period
+	 * registers directly.
+	 */
+	atmel_pwm_ch_writel(atmel_pwm, pwm->hwpwm, PWMV1_CDTY, dty);
+	atmel_pwm_ch_writel(atmel_pwm, pwm->hwpwm, PWMV1_CPRD, prd);
 }
 
 static void atmel_pwm_config_v2(struct pwm_chip *chip, struct pwm_device *pwm,
@@ -242,7 +253,22 @@ static int atmel_pwm_enable(struct pwm_chip *chip, struct pwm_device *pwm)
 static void atmel_pwm_disable(struct pwm_chip *chip, struct pwm_device *pwm)
 {
 	struct atmel_pwm_chip *atmel_pwm = to_atmel_pwm_chip(chip);
+	unsigned long timeout = jiffies + 2 * HZ;
+
+	/*
+	 * Wait for at least a complete period to have passed before disabling a
+	 * channel to be sure that CDTY has been updated
+	 */
+	mutex_lock(&atmel_pwm->isr_lock);
+	atmel_pwm->updated_pwms |= atmel_pwm_readl(atmel_pwm, PWM_ISR);
+
+	while (!(atmel_pwm->updated_pwms & (1 << pwm->hwpwm)) &&
+	       time_before(jiffies, timeout)) {
+		usleep_range(10, 100);
+		atmel_pwm->updated_pwms |= atmel_pwm_readl(atmel_pwm, PWM_ISR);
+	}
 
+	mutex_unlock(&atmel_pwm->isr_lock);
 	atmel_pwm_writel(atmel_pwm, PWM_DIS, 1 << pwm->hwpwm);
 
 	clk_disable(atmel_pwm->clk);
@@ -357,6 +383,8 @@ static int atmel_pwm_probe(struct platform_device *pdev)
 	atmel_pwm->chip.npwm = 4;
 	atmel_pwm->chip.can_sleep = true;
 	atmel_pwm->config = data->config;
+	atmel_pwm->updated_pwms = 0;
+	mutex_init(&atmel_pwm->isr_lock);
 
 	ret = pwmchip_add(&atmel_pwm->chip);
 	if (ret < 0) {
@@ -378,6 +406,7 @@ static int atmel_pwm_remove(struct platform_device *pdev)
 	struct atmel_pwm_chip *atmel_pwm = platform_get_drvdata(pdev);
 
 	clk_unprepare(atmel_pwm->clk);
+	mutex_destroy(&atmel_pwm->isr_lock);
 
 	return pwmchip_remove(&atmel_pwm->chip);
 }
diff --git a/drivers/pwm/pwm-bcm-kona.c b/drivers/pwm/pwm-bcm-kona.c
index 02bc048892a9..7af8fea2dc5b 100644
--- a/drivers/pwm/pwm-bcm-kona.c
+++ b/drivers/pwm/pwm-bcm-kona.c
@@ -266,18 +266,15 @@ static int kona_pwmc_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	/* Set smooth mode, push/pull, and normal polarity for all channels */
-	for (chan = 0; chan < kp->chip.npwm; chan++) {
-		value |= (1 << PWM_CONTROL_SMOOTH_SHIFT(chan));
+	/* Set push/pull for all channels */
+	for (chan = 0; chan < kp->chip.npwm; chan++)
 		value |= (1 << PWM_CONTROL_TYPE_SHIFT(chan));
-		value |= (1 << PWM_CONTROL_POLARITY_SHIFT(chan));
-	}
 
 	writel(value, kp->base + PWM_CONTROL_OFFSET);
 
 	clk_disable_unprepare(kp->clk);
 
-	ret = pwmchip_add(&kp->chip);
+	ret = pwmchip_add_with_polarity(&kp->chip, PWM_POLARITY_INVERSED);
 	if (ret < 0)
 		dev_err(&pdev->dev, "failed to add PWM chip: %d\n", ret);
 
diff --git a/drivers/pwm/pwm-lpss-pci.c b/drivers/pwm/pwm-lpss-pci.c
index cf20d2beacdd..45042c1b2046 100644
--- a/drivers/pwm/pwm-lpss-pci.c
+++ b/drivers/pwm/pwm-lpss-pci.c
@@ -44,8 +44,10 @@ static void pwm_lpss_remove_pci(struct pci_dev *pdev)
 }
 
 static const struct pci_device_id pwm_lpss_pci_ids[] = {
+	{ PCI_VDEVICE(INTEL, 0x0ac8), (unsigned long)&pwm_lpss_bsw_info},
 	{ PCI_VDEVICE(INTEL, 0x0f08), (unsigned long)&pwm_lpss_byt_info},
 	{ PCI_VDEVICE(INTEL, 0x0f09), (unsigned long)&pwm_lpss_byt_info},
+	{ PCI_VDEVICE(INTEL, 0x1ac8), (unsigned long)&pwm_lpss_bsw_info},
 	{ PCI_VDEVICE(INTEL, 0x2288), (unsigned long)&pwm_lpss_bsw_info},
 	{ PCI_VDEVICE(INTEL, 0x2289), (unsigned long)&pwm_lpss_bsw_info},
 	{ },
diff --git a/drivers/pwm/pwm-samsung.c b/drivers/pwm/pwm-samsung.c
index ff201e1b9219..ada2d326dc3e 100644
--- a/drivers/pwm/pwm-samsung.c
+++ b/drivers/pwm/pwm-samsung.c
@@ -456,6 +456,7 @@ static const struct of_device_id samsung_pwm_matches[] = {
 	{ .compatible = "samsung,exynos4210-pwm", .data = &s5p64x0_variant },
 	{},
 };
+MODULE_DEVICE_TABLE(of, samsung_pwm_matches);
 
 static int pwm_samsung_parse_dt(struct samsung_pwm_chip *chip)
 {
diff --git a/drivers/rapidio/rio-scan.c b/drivers/rapidio/rio-scan.c
index 47a1b2ea76c4..d6a126c17c03 100644
--- a/drivers/rapidio/rio-scan.c
+++ b/drivers/rapidio/rio-scan.c
@@ -83,7 +83,7 @@ static u16 rio_destid_alloc(struct rio_net *net)
  * @destid: destID to reserve
  *
  * Tries to reserve the specified destID.
- * Returns 0 if successfull.
+ * Returns 0 if successful.
  */
 static int rio_destid_reserve(struct rio_net *net, u16 destid)
 {
diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig
index b021bcb88537..b94c217a09ae 100644
--- a/drivers/scsi/Kconfig
+++ b/drivers/scsi/Kconfig
@@ -52,7 +52,7 @@ config SCSI_MQ_DEFAULT
 	  This option enables the new blk-mq based I/O path for SCSI
 	  devices by default.  With the option the scsi_mod.use_blk_mq
 	  module/boot option defaults to Y, without it to N, but it can
-	  still be overriden either way.
+	  still be overridden either way.
 
 	  If unsure say N.
 
diff --git a/drivers/scsi/fnic/fnic_debugfs.c b/drivers/scsi/fnic/fnic_debugfs.c
index 5980c10c734d..d6498fabe628 100644
--- a/drivers/scsi/fnic/fnic_debugfs.c
+++ b/drivers/scsi/fnic/fnic_debugfs.c
@@ -18,6 +18,7 @@
 #include <linux/module.h>
 #include <linux/errno.h>
 #include <linux/debugfs.h>
+#include <linux/vmalloc.h>
 #include "fnic.h"
 
 static struct dentry *fnic_trace_debugfs_root;
diff --git a/drivers/scsi/fnic/fnic_trace.c b/drivers/scsi/fnic/fnic_trace.c
index 65a9bde26974..4e15c4bf0795 100644
--- a/drivers/scsi/fnic/fnic_trace.c
+++ b/drivers/scsi/fnic/fnic_trace.c
@@ -21,6 +21,7 @@
 #include <linux/spinlock.h>
 #include <linux/kallsyms.h>
 #include <linux/time.h>
+#include <linux/vmalloc.h>
 #include "fnic_io.h"
 #include "fnic.h"
 
diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c
index 513edcb0c2da..25aa9b98d53a 100644
--- a/drivers/scsi/lpfc/lpfc_debugfs.c
+++ b/drivers/scsi/lpfc/lpfc_debugfs.c
@@ -710,7 +710,7 @@ lpfc_debugfs_slow_ring_trc(struct lpfc_hba *phba, char *fmt,
  * returns a pointer to that log in the private_data field in @file.
  *
  * Returns:
- * This function returns zero if successful. On error it will return an negative
+ * This function returns zero if successful. On error it will return a negative
  * error value.
  **/
 static int
@@ -760,7 +760,7 @@ out:
  * returns a pointer to that log in the private_data field in @file.
  *
  * Returns:
- * This function returns zero if successful. On error it will return an negative
+ * This function returns zero if successful. On error it will return a negative
  * error value.
  **/
 static int
@@ -810,7 +810,7 @@ out:
  * returns a pointer to that log in the private_data field in @file.
  *
  * Returns:
- * This function returns zero if successful. On error it will return an negative
+ * This function returns zero if successful. On error it will return a negative
  * error value.
  **/
 static int
@@ -852,7 +852,7 @@ out:
  * returns a pointer to that log in the private_data field in @file.
  *
  * Returns:
- * This function returns zero if successful. On error it will return an negative
+ * This function returns zero if successful. On error it will return a negative
  * error value.
  **/
 static int
@@ -894,7 +894,7 @@ out:
  * returns a pointer to that log in the private_data field in @file.
  *
  * Returns:
- * This function returns zero if successful. On error it will return an negative
+ * This function returns zero if successful. On error it will return a negative
  * error value.
  **/
 static int
@@ -1115,7 +1115,7 @@ lpfc_debugfs_dif_err_release(struct inode *inode, struct file *file)
  * returns a pointer to that log in the private_data field in @file.
  *
  * Returns:
- * This function returns zero if successful. On error it will return an negative
+ * This function returns zero if successful. On error it will return a negative
  * error value.
  **/
 static int
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index 890637fdd61e..4c3fc0eb8b30 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -4747,7 +4747,7 @@ fail_ready_state:
 
 /**
  * megasas_release_mfi -	Reverses the FW initialization
- * @intance:			Adapter soft state
+ * @instance:			Adapter soft state
  */
 static void megasas_release_mfi(struct megasas_instance *instance)
 {
diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c
index 5a0800d19970..dba4de04de3c 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fusion.c
+++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c
@@ -2334,7 +2334,7 @@ megasas_issue_dcmd_fusion(struct megasas_instance *instance,
 
 /**
  * megasas_release_fusion -	Reverses the FW initialization
- * @intance:			Adapter soft state
+ * @instance:			Adapter soft state
  */
 void
 megasas_release_fusion(struct megasas_instance *instance)
diff --git a/drivers/scsi/qla4xxx/ql4_83xx.c b/drivers/scsi/qla4xxx/ql4_83xx.c
index 556c1525f881..5d4f8e67fb25 100644
--- a/drivers/scsi/qla4xxx/ql4_83xx.c
+++ b/drivers/scsi/qla4xxx/ql4_83xx.c
@@ -828,7 +828,7 @@ void qla4_83xx_read_reset_template(struct scsi_qla_host *ha)
 	ret_val = qla4_83xx_flash_read_u32(ha, addr, p_buff,
 					   tmplt_hdr_def_size);
 	if (ret_val != QLA_SUCCESS) {
-		ql4_printk(KERN_ERR, ha, "%s: Failed to read reset tempelate\n",
+		ql4_printk(KERN_ERR, ha, "%s: Failed to read reset template\n",
 			   __func__);
 		goto exit_read_template_error;
 	}
diff --git a/drivers/scsi/qla4xxx/ql4_bsg.c b/drivers/scsi/qla4xxx/ql4_bsg.c
index 9f92cbf96477..415ee5eb3fc7 100644
--- a/drivers/scsi/qla4xxx/ql4_bsg.c
+++ b/drivers/scsi/qla4xxx/ql4_bsg.c
@@ -571,7 +571,7 @@ static int qla4_83xx_pre_loopback_config(struct scsi_qla_host *ha,
 
 	if ((config & ENABLE_INTERNAL_LOOPBACK) ||
 	    (config & ENABLE_EXTERNAL_LOOPBACK)) {
-		ql4_printk(KERN_INFO, ha, "%s: Loopback diagnostics already in progress. Invalid requiest\n",
+		ql4_printk(KERN_INFO, ha, "%s: Loopback diagnostics already in progress. Invalid request\n",
 			   __func__);
 		goto exit_pre_loopback_config;
 	}
diff --git a/drivers/staging/lustre/lustre/include/linux/lustre_compat25.h b/drivers/staging/lustre/lustre/include/linux/lustre_compat25.h
index 3925db160650..513c81f43d6e 100644
--- a/drivers/staging/lustre/lustre/include/linux/lustre_compat25.h
+++ b/drivers/staging/lustre/lustre/include/linux/lustre_compat25.h
@@ -189,22 +189,7 @@ static inline int ll_quota_off(struct super_block *sb, int off, int remount)
 #endif
 
 
-
-/*
- * After 3.1, kernel's nameidata.intent.open.flags is different
- * with lustre's lookup_intent.it_flags, as lustre's it_flags'
- * lower bits equal to FMODE_xxx while kernel doesn't transliterate
- * lower bits of nameidata.intent.open.flags to FMODE_xxx.
- * */
 #include <linux/version.h>
-static inline int ll_namei_to_lookup_intent_flag(int flag)
-{
-#if LINUX_VERSION_CODE >= KERNEL_VERSION(3, 1, 0)
-	flag = (flag & ~O_ACCMODE) | OPEN_FMODE(flag);
-#endif
-	return flag;
-}
-
 #include <linux/fs.h>
 
 # define ll_umode_t	umode_t
diff --git a/drivers/staging/lustre/lustre/libcfs/linux/linux-cpu.c b/drivers/staging/lustre/lustre/libcfs/linux/linux-cpu.c
index cc3ab351943e..f9262243f935 100644
--- a/drivers/staging/lustre/lustre/libcfs/linux/linux-cpu.c
+++ b/drivers/staging/lustre/lustre/libcfs/linux/linux-cpu.c
@@ -87,7 +87,7 @@ static void cfs_cpu_core_siblings(int cpu, cpumask_t *mask)
 /* return cpumask of HTs in the same core */
 static void cfs_cpu_ht_siblings(int cpu, cpumask_t *mask)
 {
-	cpumask_copy(mask, topology_thread_cpumask(cpu));
+	cpumask_copy(mask, topology_sibling_cpumask(cpu));
 }
 
 static void cfs_node_to_cpumask(int node, cpumask_t *mask)
diff --git a/drivers/staging/lustre/lustre/llite/llite_internal.h b/drivers/staging/lustre/lustre/llite/llite_internal.h
index 5f918e3c4683..528af9011653 100644
--- a/drivers/staging/lustre/lustre/llite/llite_internal.h
+++ b/drivers/staging/lustre/lustre/llite/llite_internal.h
@@ -57,12 +57,6 @@
 #define VM_FAULT_RETRY 0
 #endif
 
-/* Kernel 3.1 kills LOOKUP_CONTINUE, LOOKUP_PARENT is equivalent to it.
- * seem kernel commit 49084c3bb2055c401f3493c13edae14d49128ca0 */
-#ifndef LOOKUP_CONTINUE
-#define LOOKUP_CONTINUE LOOKUP_PARENT
-#endif
-
 /** Only used on client-side for indicating the tail of dir hash/offset. */
 #define LL_DIR_END_OFF	  0x7fffffffffffffffULL
 #define LL_DIR_END_OFF_32BIT    0x7fffffffUL
diff --git a/drivers/staging/lustre/lustre/llite/symlink.c b/drivers/staging/lustre/lustre/llite/symlink.c
index 3711e671a4df..69b203651905 100644
--- a/drivers/staging/lustre/lustre/llite/symlink.c
+++ b/drivers/staging/lustre/lustre/llite/symlink.c
@@ -118,7 +118,7 @@ failed:
 	return rc;
 }
 
-static void *ll_follow_link(struct dentry *dentry, struct nameidata *nd)
+static const char *ll_follow_link(struct dentry *dentry, void **cookie)
 {
 	struct inode *inode = d_inode(dentry);
 	struct ptlrpc_request *request = NULL;
@@ -126,32 +126,22 @@ static void *ll_follow_link(struct dentry *dentry, struct nameidata *nd)
 	char *symname = NULL;
 
 	CDEBUG(D_VFSTRACE, "VFS Op\n");
-	/* Limit the recursive symlink depth to 5 instead of default
-	 * 8 links when kernel has 4k stack to prevent stack overflow.
-	 * For 8k stacks we need to limit it to 7 for local servers. */
-	if (THREAD_SIZE < 8192 && current->link_count >= 6) {
-		rc = -ELOOP;
-	} else if (THREAD_SIZE == 8192 && current->link_count >= 8) {
-		rc = -ELOOP;
-	} else {
-		ll_inode_size_lock(inode);
-		rc = ll_readlink_internal(inode, &request, &symname);
-		ll_inode_size_unlock(inode);
-	}
+	ll_inode_size_lock(inode);
+	rc = ll_readlink_internal(inode, &request, &symname);
+	ll_inode_size_unlock(inode);
 	if (rc) {
 		ptlrpc_req_finished(request);
-		request = NULL;
-		symname = ERR_PTR(rc);
+		return ERR_PTR(rc);
 	}
 
-	nd_set_link(nd, symname);
 	/* symname may contain a pointer to the request message buffer,
 	 * we delay request releasing until ll_put_link then.
 	 */
-	return request;
+	*cookie = request;
+	return symname;
 }
 
-static void ll_put_link(struct dentry *dentry, struct nameidata *nd, void *cookie)
+static void ll_put_link(struct inode *unused, void *cookie)
 {
 	ptlrpc_req_finished(cookie);
 }
diff --git a/drivers/staging/lustre/lustre/ptlrpc/service.c b/drivers/staging/lustre/lustre/ptlrpc/service.c
index 8e61421515cb..344189ac5698 100644
--- a/drivers/staging/lustre/lustre/ptlrpc/service.c
+++ b/drivers/staging/lustre/lustre/ptlrpc/service.c
@@ -557,7 +557,7 @@ ptlrpc_server_nthreads_check(struct ptlrpc_service *svc,
 		 * there are.
 		 */
 		/* weight is # of HTs */
-		if (cpumask_weight(topology_thread_cpumask(0)) > 1) {
+		if (cpumask_weight(topology_sibling_cpumask(0)) > 1) {
 			/* depress thread factor for hyper-thread */
 			factor = factor - (factor >> 1) + (factor >> 3);
 		}
@@ -2768,7 +2768,7 @@ int ptlrpc_hr_init(void)
 
 	init_waitqueue_head(&ptlrpc_hr.hr_waitq);
 
-	weight = cpumask_weight(topology_thread_cpumask(0));
+	weight = cpumask_weight(topology_sibling_cpumask(0));
 
 	cfs_percpt_for_each(hrp, i, ptlrpc_hr.hr_partitions) {
 		hrp->hrp_cpt = i;
diff --git a/drivers/tty/serial/serial_mctrl_gpio.c b/drivers/tty/serial/serial_mctrl_gpio.c
index 0ec756c62bcf..d7b846d41630 100644
--- a/drivers/tty/serial/serial_mctrl_gpio.c
+++ b/drivers/tty/serial/serial_mctrl_gpio.c
@@ -55,7 +55,7 @@ void mctrl_gpio_set(struct mctrl_gpios *gpios, unsigned int mctrl)
 			value_array[count] = !!(mctrl & mctrl_gpios_desc[i].mctrl);
 			count++;
 		}
-	gpiod_set_array(count, desc_array, value_array);
+	gpiod_set_array_value(count, desc_array, value_array);
 }
 EXPORT_SYMBOL_GPL(mctrl_gpio_set);
 
diff --git a/drivers/usb/misc/ldusb.c b/drivers/usb/misc/ldusb.c
index 82503a7ff6c8..cce22ff1c2eb 100644
--- a/drivers/usb/misc/ldusb.c
+++ b/drivers/usb/misc/ldusb.c
@@ -69,12 +69,6 @@
 #define USB_DEVICE_ID_LD_HYBRID		0x2090	/* USB Product ID of Automotive Hybrid */
 #define USB_DEVICE_ID_LD_HEATCONTROL	0x20A0	/* USB Product ID of Heat control */
 
-#define USB_VENDOR_ID_VERNIER		0x08f7
-#define USB_DEVICE_ID_VERNIER_GOTEMP	0x0002
-#define USB_DEVICE_ID_VERNIER_SKIP	0x0003
-#define USB_DEVICE_ID_VERNIER_CYCLOPS	0x0004
-#define USB_DEVICE_ID_VERNIER_LCSPEC	0x0006
-
 #ifdef CONFIG_USB_DYNAMIC_MINORS
 #define USB_LD_MINOR_BASE	0
 #else
@@ -115,10 +109,6 @@ static const struct usb_device_id ld_usb_table[] = {
 	{ USB_DEVICE(USB_VENDOR_ID_LD, USB_DEVICE_ID_LD_MCT) },
 	{ USB_DEVICE(USB_VENDOR_ID_LD, USB_DEVICE_ID_LD_HYBRID) },
 	{ USB_DEVICE(USB_VENDOR_ID_LD, USB_DEVICE_ID_LD_HEATCONTROL) },
-	{ USB_DEVICE(USB_VENDOR_ID_VERNIER, USB_DEVICE_ID_VERNIER_GOTEMP) },
-	{ USB_DEVICE(USB_VENDOR_ID_VERNIER, USB_DEVICE_ID_VERNIER_SKIP) },
-	{ USB_DEVICE(USB_VENDOR_ID_VERNIER, USB_DEVICE_ID_VERNIER_CYCLOPS) },
-	{ USB_DEVICE(USB_VENDOR_ID_VERNIER, USB_DEVICE_ID_VERNIER_LCSPEC) },
 	{ }					/* Terminating entry */
 };
 MODULE_DEVICE_TABLE(usb, ld_usb_table);
diff --git a/drivers/usb/serial/Kconfig b/drivers/usb/serial/Kconfig
index b7cf1982d1d9..56ecb8b5115d 100644
--- a/drivers/usb/serial/Kconfig
+++ b/drivers/usb/serial/Kconfig
@@ -171,7 +171,7 @@ config USB_SERIAL_FTDI_SIO
 	---help---
 	  Say Y here if you want to use a FTDI SIO single port USB to serial
 	  converter device. The implementation I have is called the USC-1000.
-	  This driver has also be tested with the 245 and 232 devices.
+	  This driver has also been tested with the 245 and 232 devices.
 
 	  See <http://ftdi-usb-sio.sourceforge.net/> for more
 	  information on this driver and the device.
diff --git a/drivers/video/fbdev/amifb.c b/drivers/video/fbdev/amifb.c
index 35f7900a0573..ee3a703acf23 100644
--- a/drivers/video/fbdev/amifb.c
+++ b/drivers/video/fbdev/amifb.c
@@ -3705,8 +3705,8 @@ default_chipset:
 	 * access the videomem with writethrough cache
 	 */
 	info->fix.smem_start = (u_long)ZTWO_PADDR(videomemory);
-	videomemory = (u_long)ioremap_writethrough(info->fix.smem_start,
-						   info->fix.smem_len);
+	videomemory = (u_long)ioremap_wt(info->fix.smem_start,
+					 info->fix.smem_len);
 	if (!videomemory) {
 		dev_warn(&pdev->dev,
 			 "Unable to map videomem cached writethrough\n");
diff --git a/drivers/video/fbdev/atafb.c b/drivers/video/fbdev/atafb.c
index cb9ee2556850..d6ce613e12ad 100644
--- a/drivers/video/fbdev/atafb.c
+++ b/drivers/video/fbdev/atafb.c
@@ -3185,8 +3185,7 @@ int __init atafb_init(void)
 		/* Map the video memory (physical address given) to somewhere
 		 * in the kernel address space.
 		 */
-		external_screen_base = ioremap_writethrough(external_addr,
-						     external_len);
+		external_screen_base = ioremap_wt(external_addr, external_len);
 		if (external_vgaiobase)
 			external_vgaiobase =
 			  (unsigned long)ioremap(external_vgaiobase, 0x10000);
diff --git a/drivers/video/fbdev/hpfb.c b/drivers/video/fbdev/hpfb.c
index a1b7e5fa9b09..9476d196f510 100644
--- a/drivers/video/fbdev/hpfb.c
+++ b/drivers/video/fbdev/hpfb.c
@@ -241,8 +241,8 @@ static int hpfb_init_one(unsigned long phys_base, unsigned long virt_base)
 	fb_info.fix.line_length = fb_width;
 	fb_height = (in_8(fb_regs + HPFB_FBHMSB) << 8) | in_8(fb_regs + HPFB_FBHLSB);
 	fb_info.fix.smem_len = fb_width * fb_height;
-	fb_start = (unsigned long)ioremap_writethrough(fb_info.fix.smem_start,
-						       fb_info.fix.smem_len);
+	fb_start = (unsigned long)ioremap_wt(fb_info.fix.smem_start,
+					     fb_info.fix.smem_len);
 	hpfb_defined.xres = (in_8(fb_regs + HPFB_DWMSB) << 8) | in_8(fb_regs + HPFB_DWLSB);
 	hpfb_defined.yres = (in_8(fb_regs + HPFB_DHMSB) << 8) | in_8(fb_regs + HPFB_DHLSB);
 	hpfb_defined.xres_virtual = hpfb_defined.xres;
diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c
index eba1b7ac7294..5447b8186332 100644
--- a/drivers/virtio/virtio_pci_common.c
+++ b/drivers/virtio/virtio_pci_common.c
@@ -502,9 +502,6 @@ static int virtio_pci_probe(struct pci_dev *pci_dev,
 	INIT_LIST_HEAD(&vp_dev->virtqueues);
 	spin_lock_init(&vp_dev->lock);
 
-	/* Disable MSI/MSIX to bring device to a known good state. */
-	pci_msi_off(pci_dev);
-
 	/* enable the device */
 	rc = pci_enable_device(pci_dev);
 	if (rc)
diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h
index fb9ffcb43277..0923f2cf3c80 100644
--- a/fs/9p/v9fs.h
+++ b/fs/9p/v9fs.h
@@ -149,8 +149,6 @@ extern int v9fs_vfs_unlink(struct inode *i, struct dentry *d);
 extern int v9fs_vfs_rmdir(struct inode *i, struct dentry *d);
 extern int v9fs_vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 			struct inode *new_dir, struct dentry *new_dentry);
-extern void v9fs_vfs_put_link(struct dentry *dentry, struct nameidata *nd,
-			void *p);
 extern struct inode *v9fs_inode_from_fid(struct v9fs_session_info *v9ses,
 					 struct p9_fid *fid,
 					 struct super_block *sb, int new);
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 703342e309f5..510040b04c96 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -1224,100 +1224,43 @@ ino_t v9fs_qid2ino(struct p9_qid *qid)
 }
 
 /**
- * v9fs_readlink - read a symlink's location (internal version)
+ * v9fs_vfs_follow_link - follow a symlink path
  * @dentry: dentry for symlink
- * @buffer: buffer to load symlink location into
- * @buflen: length of buffer
- *
+ * @cookie: place to pass the data to put_link()
  */
 
-static int v9fs_readlink(struct dentry *dentry, char *buffer, int buflen)
+static const char *v9fs_vfs_follow_link(struct dentry *dentry, void **cookie)
 {
-	int retval;
-
-	struct v9fs_session_info *v9ses;
-	struct p9_fid *fid;
+	struct v9fs_session_info *v9ses = v9fs_dentry2v9ses(dentry);
+	struct p9_fid *fid = v9fs_fid_lookup(dentry);
 	struct p9_wstat *st;
+	char *res;
+
+	p9_debug(P9_DEBUG_VFS, "%pd\n", dentry);
 
-	p9_debug(P9_DEBUG_VFS, " %pd\n", dentry);
-	retval = -EPERM;
-	v9ses = v9fs_dentry2v9ses(dentry);
-	fid = v9fs_fid_lookup(dentry);
 	if (IS_ERR(fid))
-		return PTR_ERR(fid);
+		return ERR_CAST(fid);
 
 	if (!v9fs_proto_dotu(v9ses))
-		return -EBADF;
+		return ERR_PTR(-EBADF);
 
 	st = p9_client_stat(fid);
 	if (IS_ERR(st))
-		return PTR_ERR(st);
+		return ERR_CAST(st);
 
 	if (!(st->mode & P9_DMSYMLINK)) {
-		retval = -EINVAL;
-		goto done;
+		p9stat_free(st);
+		kfree(st);
+		return ERR_PTR(-EINVAL);
 	}
+	res = st->extension;
+	st->extension = NULL;
+	if (strlen(res) >= PATH_MAX)
+		res[PATH_MAX - 1] = '\0';
 
-	/* copy extension buffer into buffer */
-	retval = min(strlen(st->extension)+1, (size_t)buflen);
-	memcpy(buffer, st->extension, retval);
-
-	p9_debug(P9_DEBUG_VFS, "%pd -> %s (%.*s)\n",
-		 dentry, st->extension, buflen, buffer);
-
-done:
 	p9stat_free(st);
 	kfree(st);
-	return retval;
-}
-
-/**
- * v9fs_vfs_follow_link - follow a symlink path
- * @dentry: dentry for symlink
- * @nd: nameidata
- *
- */
-
-static void *v9fs_vfs_follow_link(struct dentry *dentry, struct nameidata *nd)
-{
-	int len = 0;
-	char *link = __getname();
-
-	p9_debug(P9_DEBUG_VFS, "%pd\n", dentry);
-
-	if (!link)
-		link = ERR_PTR(-ENOMEM);
-	else {
-		len = v9fs_readlink(dentry, link, PATH_MAX);
-
-		if (len < 0) {
-			__putname(link);
-			link = ERR_PTR(len);
-		} else
-			link[min(len, PATH_MAX-1)] = 0;
-	}
-	nd_set_link(nd, link);
-
-	return NULL;
-}
-
-/**
- * v9fs_vfs_put_link - release a symlink path
- * @dentry: dentry for symlink
- * @nd: nameidata
- * @p: unused
- *
- */
-
-void
-v9fs_vfs_put_link(struct dentry *dentry, struct nameidata *nd, void *p)
-{
-	char *s = nd_get_link(nd);
-
-	p9_debug(P9_DEBUG_VFS, " %pd %s\n",
-		 dentry, IS_ERR(s) ? "<error>" : s);
-	if (!IS_ERR(s))
-		__putname(s);
+	return *cookie = res;
 }
 
 /**
@@ -1370,6 +1313,8 @@ v9fs_vfs_symlink(struct inode *dir, struct dentry *dentry, const char *symname)
 	return v9fs_vfs_mkspecial(dir, dentry, P9_DMSYMLINK, symname);
 }
 
+#define U32_MAX_DIGITS 10
+
 /**
  * v9fs_vfs_link - create a hardlink
  * @old_dentry: dentry for file to link to
@@ -1383,7 +1328,7 @@ v9fs_vfs_link(struct dentry *old_dentry, struct inode *dir,
 	      struct dentry *dentry)
 {
 	int retval;
-	char *name;
+	char name[1 + U32_MAX_DIGITS + 2]; /* sign + number + \n + \0 */
 	struct p9_fid *oldfid;
 
 	p9_debug(P9_DEBUG_VFS, " %lu,%pd,%pd\n",
@@ -1393,20 +1338,12 @@ v9fs_vfs_link(struct dentry *old_dentry, struct inode *dir,
 	if (IS_ERR(oldfid))
 		return PTR_ERR(oldfid);
 
-	name = __getname();
-	if (unlikely(!name)) {
-		retval = -ENOMEM;
-		goto clunk_fid;
-	}
-
 	sprintf(name, "%d\n", oldfid->fid);
 	retval = v9fs_vfs_mkspecial(dir, dentry, P9_DMLINK, name);
-	__putname(name);
 	if (!retval) {
 		v9fs_refresh_inode(oldfid, d_inode(old_dentry));
 		v9fs_invalidate_inode_attr(dir);
 	}
-clunk_fid:
 	p9_client_clunk(oldfid);
 	return retval;
 }
@@ -1425,7 +1362,7 @@ v9fs_vfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rde
 {
 	struct v9fs_session_info *v9ses = v9fs_inode2v9ses(dir);
 	int retval;
-	char *name;
+	char name[2 + U32_MAX_DIGITS + 1 + U32_MAX_DIGITS + 1];
 	u32 perm;
 
 	p9_debug(P9_DEBUG_VFS, " %lu,%pd mode: %hx MAJOR: %u MINOR: %u\n",
@@ -1435,26 +1372,16 @@ v9fs_vfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rde
 	if (!new_valid_dev(rdev))
 		return -EINVAL;
 
-	name = __getname();
-	if (!name)
-		return -ENOMEM;
 	/* build extension */
 	if (S_ISBLK(mode))
 		sprintf(name, "b %u %u", MAJOR(rdev), MINOR(rdev));
 	else if (S_ISCHR(mode))
 		sprintf(name, "c %u %u", MAJOR(rdev), MINOR(rdev));
-	else if (S_ISFIFO(mode))
-		*name = 0;
-	else if (S_ISSOCK(mode))
+	else
 		*name = 0;
-	else {
-		__putname(name);
-		return -EINVAL;
-	}
 
 	perm = unixmode2p9mode(v9ses, mode);
 	retval = v9fs_vfs_mkspecial(dir, dentry, perm, name);
-	__putname(name);
 
 	return retval;
 }
@@ -1530,7 +1457,7 @@ static const struct inode_operations v9fs_file_inode_operations = {
 static const struct inode_operations v9fs_symlink_inode_operations = {
 	.readlink = generic_readlink,
 	.follow_link = v9fs_vfs_follow_link,
-	.put_link = v9fs_vfs_put_link,
+	.put_link = kfree_put_link,
 	.getattr = v9fs_vfs_getattr,
 	.setattr = v9fs_vfs_setattr,
 };
diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c
index 9861c7c951a6..09e4433717b8 100644
--- a/fs/9p/vfs_inode_dotl.c
+++ b/fs/9p/vfs_inode_dotl.c
@@ -905,41 +905,24 @@ error:
 /**
  * v9fs_vfs_follow_link_dotl - follow a symlink path
  * @dentry: dentry for symlink
- * @nd: nameidata
- *
+ * @cookie: place to pass the data to put_link()
  */
 
-static void *
-v9fs_vfs_follow_link_dotl(struct dentry *dentry, struct nameidata *nd)
+static const char *
+v9fs_vfs_follow_link_dotl(struct dentry *dentry, void **cookie)
 {
-	int retval;
-	struct p9_fid *fid;
-	char *link = __getname();
+	struct p9_fid *fid = v9fs_fid_lookup(dentry);
 	char *target;
+	int retval;
 
 	p9_debug(P9_DEBUG_VFS, "%pd\n", dentry);
 
-	if (!link) {
-		link = ERR_PTR(-ENOMEM);
-		goto ndset;
-	}
-	fid = v9fs_fid_lookup(dentry);
-	if (IS_ERR(fid)) {
-		__putname(link);
-		link = ERR_CAST(fid);
-		goto ndset;
-	}
+	if (IS_ERR(fid))
+		return ERR_CAST(fid);
 	retval = p9_client_readlink(fid, &target);
-	if (!retval) {
-		strcpy(link, target);
-		kfree(target);
-		goto ndset;
-	}
-	__putname(link);
-	link = ERR_PTR(retval);
-ndset:
-	nd_set_link(nd, link);
-	return NULL;
+	if (retval)
+		return ERR_PTR(retval);
+	return *cookie = target;
 }
 
 int v9fs_refresh_inode_dotl(struct p9_fid *fid, struct inode *inode)
@@ -1006,7 +989,7 @@ const struct inode_operations v9fs_file_inode_operations_dotl = {
 const struct inode_operations v9fs_symlink_inode_operations_dotl = {
 	.readlink = generic_readlink,
 	.follow_link = v9fs_vfs_follow_link_dotl,
-	.put_link = v9fs_vfs_put_link,
+	.put_link = kfree_put_link,
 	.getattr = v9fs_vfs_getattr_dotl,
 	.setattr = v9fs_vfs_setattr_dotl,
 	.setxattr = generic_setxattr,
diff --git a/fs/autofs4/symlink.c b/fs/autofs4/symlink.c
index de58cc7b8076..da0c33481bc0 100644
--- a/fs/autofs4/symlink.c
+++ b/fs/autofs4/symlink.c
@@ -12,14 +12,13 @@
 
 #include "autofs_i.h"
 
-static void *autofs4_follow_link(struct dentry *dentry, struct nameidata *nd)
+static const char *autofs4_follow_link(struct dentry *dentry, void **cookie)
 {
 	struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
 	struct autofs_info *ino = autofs4_dentry_ino(dentry);
 	if (ino && !autofs4_oz_mode(sbi))
 		ino->last_used = jiffies;
-	nd_set_link(nd, d_inode(dentry)->i_private);
-	return NULL;
+	return d_inode(dentry)->i_private;
 }
 
 const struct inode_operations autofs4_symlink_inode_operations = {
diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c
index 7943533c3868..46aedacfa6a8 100644
--- a/fs/befs/linuxvfs.c
+++ b/fs/befs/linuxvfs.c
@@ -42,8 +42,7 @@ static struct inode *befs_iget(struct super_block *, unsigned long);
 static struct inode *befs_alloc_inode(struct super_block *sb);
 static void befs_destroy_inode(struct inode *inode);
 static void befs_destroy_inodecache(void);
-static void *befs_follow_link(struct dentry *, struct nameidata *);
-static void *befs_fast_follow_link(struct dentry *, struct nameidata *);
+static const char *befs_follow_link(struct dentry *, void **);
 static int befs_utf2nls(struct super_block *sb, const char *in, int in_len,
 			char **out, int *out_len);
 static int befs_nls2utf(struct super_block *sb, const char *in, int in_len,
@@ -80,11 +79,6 @@ static const struct address_space_operations befs_aops = {
 	.bmap		= befs_bmap,
 };
 
-static const struct inode_operations befs_fast_symlink_inode_operations = {
-	.readlink	= generic_readlink,
-	.follow_link	= befs_fast_follow_link,
-};
-
 static const struct inode_operations befs_symlink_inode_operations = {
 	.readlink	= generic_readlink,
 	.follow_link	= befs_follow_link,
@@ -403,10 +397,12 @@ static struct inode *befs_iget(struct super_block *sb, unsigned long ino)
 		inode->i_op = &befs_dir_inode_operations;
 		inode->i_fop = &befs_dir_operations;
 	} else if (S_ISLNK(inode->i_mode)) {
-		if (befs_ino->i_flags & BEFS_LONG_SYMLINK)
+		if (befs_ino->i_flags & BEFS_LONG_SYMLINK) {
 			inode->i_op = &befs_symlink_inode_operations;
-		else
-			inode->i_op = &befs_fast_symlink_inode_operations;
+		} else {
+			inode->i_link = befs_ino->i_data.symlink;
+			inode->i_op = &simple_symlink_inode_operations;
+		}
 	} else {
 		befs_error(sb, "Inode %lu is not a regular file, "
 			   "directory or symlink. THAT IS WRONG! BeFS has no "
@@ -467,8 +463,8 @@ befs_destroy_inodecache(void)
  * The data stream become link name. Unless the LONG_SYMLINK
  * flag is set.
  */
-static void *
-befs_follow_link(struct dentry *dentry, struct nameidata *nd)
+static const char *
+befs_follow_link(struct dentry *dentry, void **cookie)
 {
 	struct super_block *sb = dentry->d_sb;
 	struct befs_inode_info *befs_ino = BEFS_I(d_inode(dentry));
@@ -478,33 +474,20 @@ befs_follow_link(struct dentry *dentry, struct nameidata *nd)
 
 	if (len == 0) {
 		befs_error(sb, "Long symlink with illegal length");
-		link = ERR_PTR(-EIO);
-	} else {
-		befs_debug(sb, "Follow long symlink");
-
-		link = kmalloc(len, GFP_NOFS);
-		if (!link) {
-			link = ERR_PTR(-ENOMEM);
-		} else if (befs_read_lsymlink(sb, data, link, len) != len) {
-			kfree(link);
-			befs_error(sb, "Failed to read entire long symlink");
-			link = ERR_PTR(-EIO);
-		} else {
-			link[len - 1] = '\0';
-		}
+		return ERR_PTR(-EIO);
 	}
-	nd_set_link(nd, link);
-	return NULL;
-}
-
-
-static void *
-befs_fast_follow_link(struct dentry *dentry, struct nameidata *nd)
-{
-	struct befs_inode_info *befs_ino = BEFS_I(d_inode(dentry));
+	befs_debug(sb, "Follow long symlink");
 
-	nd_set_link(nd, befs_ino->i_data.symlink);
-	return NULL;
+	link = kmalloc(len, GFP_NOFS);
+	if (!link)
+		return ERR_PTR(-ENOMEM);
+	if (befs_read_lsymlink(sb, data, link, len) != len) {
+		kfree(link);
+		befs_error(sb, "Failed to read entire long symlink");
+		return ERR_PTR(-EIO);
+	}
+	link[len - 1] = '\0';
+	return *cookie = link;
 }
 
 /*
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index e876e1944519..571acd88606c 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -6,7 +6,6 @@
 #include <linux/string.h>
 #include <linux/uaccess.h>
 #include <linux/kernel.h>
-#include <linux/namei.h>
 #include <linux/writeback.h>
 #include <linux/vmalloc.h>
 #include <linux/posix_acl.h>
@@ -819,6 +818,7 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
 			else
 				kfree(sym); /* lost a race */
 		}
+		inode->i_link = ci->i_symlink;
 		break;
 	case S_IFDIR:
 		inode->i_op = &ceph_dir_iops;
@@ -1691,16 +1691,9 @@ retry:
 /*
  * symlinks
  */
-static void *ceph_sym_follow_link(struct dentry *dentry, struct nameidata *nd)
-{
-	struct ceph_inode_info *ci = ceph_inode(d_inode(dentry));
-	nd_set_link(nd, ci->i_symlink);
-	return NULL;
-}
-
 static const struct inode_operations ceph_symlink_iops = {
 	.readlink = generic_readlink,
-	.follow_link = ceph_sym_follow_link,
+	.follow_link = simple_follow_link,
 	.setattr = ceph_setattr,
 	.getattr = ceph_getattr,
 	.setxattr = ceph_setxattr,
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index 252f5c15806b..a782b22904e4 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -120,7 +120,7 @@ extern struct vfsmount *cifs_dfs_d_automount(struct path *path);
 #endif
 
 /* Functions related to symlinks */
-extern void *cifs_follow_link(struct dentry *direntry, struct nameidata *nd);
+extern const char *cifs_follow_link(struct dentry *direntry, void **cookie);
 extern int cifs_readlink(struct dentry *direntry, char __user *buffer,
 			 int buflen);
 extern int cifs_symlink(struct inode *inode, struct dentry *direntry,
diff --git a/fs/cifs/link.c b/fs/cifs/link.c
index e6c707cc62b3..e3548f73bdea 100644
--- a/fs/cifs/link.c
+++ b/fs/cifs/link.c
@@ -626,8 +626,8 @@ cifs_hl_exit:
 	return rc;
 }
 
-void *
-cifs_follow_link(struct dentry *direntry, struct nameidata *nd)
+const char *
+cifs_follow_link(struct dentry *direntry, void **cookie)
 {
 	struct inode *inode = d_inode(direntry);
 	int rc = -ENOMEM;
@@ -643,16 +643,18 @@ cifs_follow_link(struct dentry *direntry, struct nameidata *nd)
 
 	tlink = cifs_sb_tlink(cifs_sb);
 	if (IS_ERR(tlink)) {
-		rc = PTR_ERR(tlink);
-		tlink = NULL;
-		goto out;
+		free_xid(xid);
+		return ERR_CAST(tlink);
 	}
 	tcon = tlink_tcon(tlink);
 	server = tcon->ses->server;
 
 	full_path = build_path_from_dentry(direntry);
-	if (!full_path)
-		goto out;
+	if (!full_path) {
+		free_xid(xid);
+		cifs_put_tlink(tlink);
+		return ERR_PTR(-ENOMEM);
+	}
 
 	cifs_dbg(FYI, "Full path: %s inode = 0x%p\n", full_path, inode);
 
@@ -670,17 +672,13 @@ cifs_follow_link(struct dentry *direntry, struct nameidata *nd)
 						&target_path, cifs_sb);
 
 	kfree(full_path);
-out:
+	free_xid(xid);
+	cifs_put_tlink(tlink);
 	if (rc != 0) {
 		kfree(target_path);
-		target_path = ERR_PTR(rc);
+		return ERR_PTR(rc);
 	}
-
-	free_xid(xid);
-	if (tlink)
-		cifs_put_tlink(tlink);
-	nd_set_link(nd, target_path);
-	return NULL;
+	return *cookie = target_path;
 }
 
 int
diff --git a/fs/configfs/symlink.c b/fs/configfs/symlink.c
index cc9f2546ea4a..ec5c8325b503 100644
--- a/fs/configfs/symlink.c
+++ b/fs/configfs/symlink.c
@@ -279,36 +279,27 @@ static int configfs_getlink(struct dentry *dentry, char * path)
 
 }
 
-static void *configfs_follow_link(struct dentry *dentry, struct nameidata *nd)
+static const char *configfs_follow_link(struct dentry *dentry, void **cookie)
 {
-	int error = -ENOMEM;
 	unsigned long page = get_zeroed_page(GFP_KERNEL);
+	int error;
 
-	if (page) {
-		error = configfs_getlink(dentry, (char *)page);
-		if (!error) {
-			nd_set_link(nd, (char *)page);
-			return (void *)page;
-		}
-	}
-
-	nd_set_link(nd, ERR_PTR(error));
-	return NULL;
-}
+	if (!page)
+		return ERR_PTR(-ENOMEM);
 
-static void configfs_put_link(struct dentry *dentry, struct nameidata *nd,
-			      void *cookie)
-{
-	if (cookie) {
-		unsigned long page = (unsigned long)cookie;
-		free_page(page);
+	error = configfs_getlink(dentry, (char *)page);
+	if (!error) {
+		return *cookie = (void *)page;
 	}
+
+	free_page(page);
+	return ERR_PTR(error);
 }
 
 const struct inode_operations configfs_symlink_inode_operations = {
 	.follow_link = configfs_follow_link,
 	.readlink = generic_readlink,
-	.put_link = configfs_put_link,
+	.put_link = free_page_put_link,
 	.setattr = configfs_setattr,
 };
 
diff --git a/fs/dcache.c b/fs/dcache.c
index 37b5afdaf698..592c4b582495 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -322,17 +322,17 @@ static void dentry_free(struct dentry *dentry)
 }
 
 /**
- * dentry_rcuwalk_barrier - invalidate in-progress rcu-walk lookups
+ * dentry_rcuwalk_invalidate - invalidate in-progress rcu-walk lookups
  * @dentry: the target dentry
  * After this call, in-progress rcu-walk path lookup will fail. This
  * should be called after unhashing, and after changing d_inode (if
  * the dentry has not already been unhashed).
  */
-static inline void dentry_rcuwalk_barrier(struct dentry *dentry)
+static inline void dentry_rcuwalk_invalidate(struct dentry *dentry)
 {
-	assert_spin_locked(&dentry->d_lock);
-	/* Go through a barrier */
-	write_seqcount_barrier(&dentry->d_seq);
+	lockdep_assert_held(&dentry->d_lock);
+	/* Go through am invalidation barrier */
+	write_seqcount_invalidate(&dentry->d_seq);
 }
 
 /*
@@ -372,7 +372,7 @@ static void dentry_unlink_inode(struct dentry * dentry)
 	struct inode *inode = dentry->d_inode;
 	__d_clear_type_and_inode(dentry);
 	hlist_del_init(&dentry->d_u.d_alias);
-	dentry_rcuwalk_barrier(dentry);
+	dentry_rcuwalk_invalidate(dentry);
 	spin_unlock(&dentry->d_lock);
 	spin_unlock(&inode->i_lock);
 	if (!inode->i_nlink)
@@ -494,7 +494,7 @@ void __d_drop(struct dentry *dentry)
 		__hlist_bl_del(&dentry->d_hash);
 		dentry->d_hash.pprev = NULL;
 		hlist_bl_unlock(b);
-		dentry_rcuwalk_barrier(dentry);
+		dentry_rcuwalk_invalidate(dentry);
 	}
 }
 EXPORT_SYMBOL(__d_drop);
@@ -1752,7 +1752,7 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode)
 	if (inode)
 		hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry);
 	__d_set_inode_and_type(dentry, inode, add_flags);
-	dentry_rcuwalk_barrier(dentry);
+	dentry_rcuwalk_invalidate(dentry);
 	spin_unlock(&dentry->d_lock);
 	fsnotify_d_instantiate(dentry, inode);
 }
diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c
index 830a7e76f5c6..284f9aa0028b 100644
--- a/fs/debugfs/file.c
+++ b/fs/debugfs/file.c
@@ -17,7 +17,6 @@
 #include <linux/fs.h>
 #include <linux/seq_file.h>
 #include <linux/pagemap.h>
-#include <linux/namei.h>
 #include <linux/debugfs.h>
 #include <linux/io.h>
 #include <linux/slab.h>
@@ -43,17 +42,6 @@ const struct file_operations debugfs_file_operations = {
 	.llseek =	noop_llseek,
 };
 
-static void *debugfs_follow_link(struct dentry *dentry, struct nameidata *nd)
-{
-	nd_set_link(nd, d_inode(dentry)->i_private);
-	return NULL;
-}
-
-const struct inode_operations debugfs_link_operations = {
-	.readlink       = generic_readlink,
-	.follow_link    = debugfs_follow_link,
-};
-
 static int debugfs_u8_set(void *data, u64 val)
 {
 	*(u8 *)data = val;
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index c1e7ffb0dab6..7eaec88ea970 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -174,7 +174,7 @@ static void debugfs_evict_inode(struct inode *inode)
 	truncate_inode_pages_final(&inode->i_data);
 	clear_inode(inode);
 	if (S_ISLNK(inode->i_mode))
-		kfree(inode->i_private);
+		kfree(inode->i_link);
 }
 
 static const struct super_operations debugfs_super_operations = {
@@ -511,8 +511,8 @@ struct dentry *debugfs_create_symlink(const char *name, struct dentry *parent,
 		return failed_creating(dentry);
 	}
 	inode->i_mode = S_IFLNK | S_IRWXUGO;
-	inode->i_op = &debugfs_link_operations;
-	inode->i_private = link;
+	inode->i_op = &simple_symlink_inode_operations;
+	inode->i_link = link;
 	d_instantiate(dentry, inode);
 	return end_creating(dentry);
 }
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index fc850b55db67..3c4db1172d22 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -170,7 +170,6 @@ out_unlock:
  * @directory_inode: inode of the new file's dentry's parent in ecryptfs
  * @ecryptfs_dentry: New file's dentry in ecryptfs
  * @mode: The mode of the new file
- * @nd: nameidata of ecryptfs' parent's dentry & vfsmount
  *
  * Creates the underlying file and the eCryptfs inode which will link to
  * it. It will also update the eCryptfs directory inode to mimic the
@@ -384,7 +383,7 @@ static int ecryptfs_lookup_interpose(struct dentry *dentry,
  * ecryptfs_lookup
  * @ecryptfs_dir_inode: The eCryptfs directory inode
  * @ecryptfs_dentry: The eCryptfs dentry that we are looking up
- * @ecryptfs_nd: nameidata; may be NULL
+ * @flags: lookup flags
  *
  * Find a file on disk. If the file does not exist, then we'll add it to the
  * dentry cache and continue on to read it from the disk.
@@ -675,18 +674,16 @@ out:
 	return rc ? ERR_PTR(rc) : buf;
 }
 
-static void *ecryptfs_follow_link(struct dentry *dentry, struct nameidata *nd)
+static const char *ecryptfs_follow_link(struct dentry *dentry, void **cookie)
 {
 	size_t len;
 	char *buf = ecryptfs_readlink_lower(dentry, &len);
 	if (IS_ERR(buf))
-		goto out;
+		return buf;
 	fsstack_copy_attr_atime(d_inode(dentry),
 				d_inode(ecryptfs_dentry_to_lower(dentry)));
 	buf[len] = '\0';
-out:
-	nd_set_link(nd, buf);
-	return NULL;
+	return *cookie = buf;
 }
 
 /**
diff --git a/fs/exofs/Kbuild b/fs/exofs/Kbuild
index b47c7b8dc275..a364fd0965ec 100644
--- a/fs/exofs/Kbuild
+++ b/fs/exofs/Kbuild
@@ -16,5 +16,5 @@
 libore-y := ore.o ore_raid.o
 obj-$(CONFIG_ORE) += libore.o
 
-exofs-y := inode.o file.o symlink.o namei.o dir.o super.o sys.o
+exofs-y := inode.o file.o namei.o dir.o super.o sys.o
 obj-$(CONFIG_EXOFS_FS) += exofs.o
diff --git a/fs/exofs/exofs.h b/fs/exofs/exofs.h
index ad9cac670a47..2e86086bc940 100644
--- a/fs/exofs/exofs.h
+++ b/fs/exofs/exofs.h
@@ -207,10 +207,6 @@ extern const struct address_space_operations exofs_aops;
 extern const struct inode_operations exofs_dir_inode_operations;
 extern const struct inode_operations exofs_special_inode_operations;
 
-/* symlink.c         */
-extern const struct inode_operations exofs_symlink_inode_operations;
-extern const struct inode_operations exofs_fast_symlink_inode_operations;
-
 /* exofs_init_comps will initialize an ore_components device array
  * pointing to a single ore_comp struct, and a round-robin view
  * of the device table.
diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c
index 786e4cc8c889..73c64daa0f55 100644
--- a/fs/exofs/inode.c
+++ b/fs/exofs/inode.c
@@ -1222,10 +1222,11 @@ struct inode *exofs_iget(struct super_block *sb, unsigned long ino)
 		inode->i_fop = &exofs_dir_operations;
 		inode->i_mapping->a_ops = &exofs_aops;
 	} else if (S_ISLNK(inode->i_mode)) {
-		if (exofs_inode_is_fast_symlink(inode))
-			inode->i_op = &exofs_fast_symlink_inode_operations;
-		else {
-			inode->i_op = &exofs_symlink_inode_operations;
+		if (exofs_inode_is_fast_symlink(inode)) {
+			inode->i_op = &simple_symlink_inode_operations;
+			inode->i_link = (char *)oi->i_data;
+		} else {
+			inode->i_op = &page_symlink_inode_operations;
 			inode->i_mapping->a_ops = &exofs_aops;
 		}
 	} else {
diff --git a/fs/exofs/namei.c b/fs/exofs/namei.c
index 5ae25e431191..09a6bb1ad63c 100644
--- a/fs/exofs/namei.c
+++ b/fs/exofs/namei.c
@@ -113,7 +113,7 @@ static int exofs_symlink(struct inode *dir, struct dentry *dentry,
 	oi = exofs_i(inode);
 	if (l > sizeof(oi->i_data)) {
 		/* slow symlink */
-		inode->i_op = &exofs_symlink_inode_operations;
+		inode->i_op = &page_symlink_inode_operations;
 		inode->i_mapping->a_ops = &exofs_aops;
 		memset(oi->i_data, 0, sizeof(oi->i_data));
 
@@ -122,7 +122,8 @@ static int exofs_symlink(struct inode *dir, struct dentry *dentry,
 			goto out_fail;
 	} else {
 		/* fast symlink */
-		inode->i_op = &exofs_fast_symlink_inode_operations;
+		inode->i_op = &simple_symlink_inode_operations;
+		inode->i_link = (char *)oi->i_data;
 		memcpy(oi->i_data, symname, l);
 		inode->i_size = l-1;
 	}
diff --git a/fs/exofs/symlink.c b/fs/exofs/symlink.c
deleted file mode 100644
index 6f6f3a4c1365..000000000000
--- a/fs/exofs/symlink.c
+++ /dev/null
@@ -1,55 +0,0 @@
-/*
- * Copyright (C) 2005, 2006
- * Avishay Traeger (avishay@gmail.com)
- * Copyright (C) 2008, 2009
- * Boaz Harrosh <ooo@electrozaur.com>
- *
- * Copyrights for code taken from ext2:
- *     Copyright (C) 1992, 1993, 1994, 1995
- *     Remy Card (card@masi.ibp.fr)
- *     Laboratoire MASI - Institut Blaise Pascal
- *     Universite Pierre et Marie Curie (Paris VI)
- *     from
- *     linux/fs/minix/inode.c
- *     Copyright (C) 1991, 1992  Linus Torvalds
- *
- * This file is part of exofs.
- *
- * exofs is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation.  Since it is based on ext2, and the only
- * valid version of GPL for the Linux kernel is version 2, the only valid
- * version of GPL for exofs is version 2.
- *
- * exofs is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with exofs; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
- */
-
-#include <linux/namei.h>
-
-#include "exofs.h"
-
-static void *exofs_follow_link(struct dentry *dentry, struct nameidata *nd)
-{
-	struct exofs_i_info *oi = exofs_i(d_inode(dentry));
-
-	nd_set_link(nd, (char *)oi->i_data);
-	return NULL;
-}
-
-const struct inode_operations exofs_symlink_inode_operations = {
-	.readlink	= generic_readlink,
-	.follow_link	= page_follow_link_light,
-	.put_link	= page_put_link,
-};
-
-const struct inode_operations exofs_fast_symlink_inode_operations = {
-	.readlink	= generic_readlink,
-	.follow_link	= exofs_follow_link,
-};
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index f460ae36d5b7..5c09776d347f 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -1403,6 +1403,7 @@ struct inode *ext2_iget (struct super_block *sb, unsigned long ino)
 			inode->i_mapping->a_ops = &ext2_aops;
 	} else if (S_ISLNK(inode->i_mode)) {
 		if (ext2_inode_is_fast_symlink(inode)) {
+			inode->i_link = (char *)ei->i_data;
 			inode->i_op = &ext2_fast_symlink_inode_operations;
 			nd_terminate_link(ei->i_data, inode->i_size,
 				sizeof(ei->i_data) - 1);
diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c
index 3e074a9ccbe6..13ec54a99c96 100644
--- a/fs/ext2/namei.c
+++ b/fs/ext2/namei.c
@@ -189,7 +189,8 @@ static int ext2_symlink (struct inode * dir, struct dentry * dentry,
 	} else {
 		/* fast symlink */
 		inode->i_op = &ext2_fast_symlink_inode_operations;
-		memcpy((char*)(EXT2_I(inode)->i_data),symname,l);
+		inode->i_link = (char*)EXT2_I(inode)->i_data;
+		memcpy(inode->i_link, symname, l);
 		inode->i_size = l-1;
 	}
 	mark_inode_dirty(inode);
diff --git a/fs/ext2/symlink.c b/fs/ext2/symlink.c
index 20608f17c2e5..ae17179f3810 100644
--- a/fs/ext2/symlink.c
+++ b/fs/ext2/symlink.c
@@ -19,14 +19,6 @@
 
 #include "ext2.h"
 #include "xattr.h"
-#include <linux/namei.h>
-
-static void *ext2_follow_link(struct dentry *dentry, struct nameidata *nd)
-{
-	struct ext2_inode_info *ei = EXT2_I(d_inode(dentry));
-	nd_set_link(nd, (char *)ei->i_data);
-	return NULL;
-}
 
 const struct inode_operations ext2_symlink_inode_operations = {
 	.readlink	= generic_readlink,
@@ -43,7 +35,7 @@ const struct inode_operations ext2_symlink_inode_operations = {
  
 const struct inode_operations ext2_fast_symlink_inode_operations = {
 	.readlink	= generic_readlink,
-	.follow_link	= ext2_follow_link,
+	.follow_link	= simple_follow_link,
 	.setattr	= ext2_setattr,
 #ifdef CONFIG_EXT2_FS_XATTR
 	.setxattr	= generic_setxattr,
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index 2ee2dc4351d1..6c7e5468a2f8 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -2999,6 +2999,7 @@ struct inode *ext3_iget(struct super_block *sb, unsigned long ino)
 			inode->i_op = &ext3_fast_symlink_inode_operations;
 			nd_terminate_link(ei->i_data, inode->i_size,
 				sizeof(ei->i_data) - 1);
+			inode->i_link = (char *)ei->i_data;
 		} else {
 			inode->i_op = &ext3_symlink_inode_operations;
 			ext3_set_aops(inode);
diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c
index 4264b9bd0002..c9e767cd4b67 100644
--- a/fs/ext3/namei.c
+++ b/fs/ext3/namei.c
@@ -2308,7 +2308,8 @@ retry:
 		}
 	} else {
 		inode->i_op = &ext3_fast_symlink_inode_operations;
-		memcpy((char*)&EXT3_I(inode)->i_data,symname,l);
+		inode->i_link = (char*)&EXT3_I(inode)->i_data;
+		memcpy(inode->i_link, symname, l);
 		inode->i_size = l-1;
 	}
 	EXT3_I(inode)->i_disksize = inode->i_size;
diff --git a/fs/ext3/symlink.c b/fs/ext3/symlink.c
index ea96df3c58db..c08c59094ae6 100644
--- a/fs/ext3/symlink.c
+++ b/fs/ext3/symlink.c
@@ -17,17 +17,9 @@
  *  ext3 symlink handling code
  */
 
-#include <linux/namei.h>
 #include "ext3.h"
 #include "xattr.h"
 
-static void * ext3_follow_link(struct dentry *dentry, struct nameidata *nd)
-{
-	struct ext3_inode_info *ei = EXT3_I(d_inode(dentry));
-	nd_set_link(nd, (char*)ei->i_data);
-	return NULL;
-}
-
 const struct inode_operations ext3_symlink_inode_operations = {
 	.readlink	= generic_readlink,
 	.follow_link	= page_follow_link_light,
@@ -43,7 +35,7 @@ const struct inode_operations ext3_symlink_inode_operations = {
 
 const struct inode_operations ext3_fast_symlink_inode_operations = {
 	.readlink	= generic_readlink,
-	.follow_link	= ext3_follow_link,
+	.follow_link	= simple_follow_link,
 	.setattr	= ext3_setattr,
 #ifdef CONFIG_EXT3_FS_XATTR
 	.setxattr	= generic_setxattr,
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 9a83f149ac85..0a3b72d1d458 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -2847,6 +2847,7 @@ extern int ext4_mpage_readpages(struct address_space *mapping,
 				unsigned nr_pages);
 
 /* symlink.c */
+extern const struct inode_operations ext4_encrypted_symlink_inode_operations;
 extern const struct inode_operations ext4_symlink_inode_operations;
 extern const struct inode_operations ext4_fast_symlink_inode_operations;
 
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 0554b0b5957b..5168c9b56880 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -4213,8 +4213,11 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 		inode->i_op = &ext4_dir_inode_operations;
 		inode->i_fop = &ext4_dir_operations;
 	} else if (S_ISLNK(inode->i_mode)) {
-		if (ext4_inode_is_fast_symlink(inode) &&
-		    !ext4_encrypted_inode(inode)) {
+		if (ext4_encrypted_inode(inode)) {
+			inode->i_op = &ext4_encrypted_symlink_inode_operations;
+			ext4_set_aops(inode);
+		} else if (ext4_inode_is_fast_symlink(inode)) {
+			inode->i_link = (char *)ei->i_data;
 			inode->i_op = &ext4_fast_symlink_inode_operations;
 			nd_terminate_link(ei->i_data, inode->i_size,
 				sizeof(ei->i_data) - 1);
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 814f3beb4369..5fdb9f6aa869 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -3206,10 +3206,12 @@ static int ext4_symlink(struct inode *dir,
 			goto err_drop_inode;
 		sd->len = cpu_to_le16(ostr.len);
 		disk_link.name = (char *) sd;
+		inode->i_op = &ext4_encrypted_symlink_inode_operations;
 	}
 
 	if ((disk_link.len > EXT4_N_BLOCKS * 4)) {
-		inode->i_op = &ext4_symlink_inode_operations;
+		if (!encryption_required)
+			inode->i_op = &ext4_symlink_inode_operations;
 		ext4_set_aops(inode);
 		/*
 		 * We cannot call page_symlink() with transaction started
@@ -3249,9 +3251,10 @@ static int ext4_symlink(struct inode *dir,
 	} else {
 		/* clear the extent format for fast symlink */
 		ext4_clear_inode_flag(inode, EXT4_INODE_EXTENTS);
-		inode->i_op = encryption_required ?
-			&ext4_symlink_inode_operations :
-			&ext4_fast_symlink_inode_operations;
+		if (!encryption_required) {
+			inode->i_op = &ext4_fast_symlink_inode_operations;
+			inode->i_link = (char *)&EXT4_I(inode)->i_data;
+		}
 		memcpy((char *)&EXT4_I(inode)->i_data, disk_link.name,
 		       disk_link.len);
 		inode->i_size = disk_link.len - 1;
diff --git a/fs/ext4/symlink.c b/fs/ext4/symlink.c
index 187b78920314..ba5bd18a9825 100644
--- a/fs/ext4/symlink.c
+++ b/fs/ext4/symlink.c
@@ -23,7 +23,7 @@
 #include "xattr.h"
 
 #ifdef CONFIG_EXT4_FS_ENCRYPTION
-static void *ext4_follow_link(struct dentry *dentry, struct nameidata *nd)
+static const char *ext4_follow_link(struct dentry *dentry, void **cookie)
 {
 	struct page *cpage = NULL;
 	char *caddr, *paddr = NULL;
@@ -35,12 +35,9 @@ static void *ext4_follow_link(struct dentry *dentry, struct nameidata *nd)
 	int res;
 	u32 plen, max_size = inode->i_sb->s_blocksize;
 
-	if (!ext4_encrypted_inode(inode))
-		return page_follow_link_light(dentry, nd);
-
 	ctx = ext4_get_fname_crypto_ctx(inode, inode->i_sb->s_blocksize);
 	if (IS_ERR(ctx))
-		return ctx;
+		return ERR_CAST(ctx);
 
 	if (ext4_inode_is_fast_symlink(inode)) {
 		caddr = (char *) EXT4_I(inode)->i_data;
@@ -49,7 +46,7 @@ static void *ext4_follow_link(struct dentry *dentry, struct nameidata *nd)
 		cpage = read_mapping_page(inode->i_mapping, 0, NULL);
 		if (IS_ERR(cpage)) {
 			ext4_put_fname_crypto_ctx(&ctx);
-			return cpage;
+			return ERR_CAST(cpage);
 		}
 		caddr = kmap(cpage);
 		caddr[size] = 0;
@@ -80,13 +77,12 @@ static void *ext4_follow_link(struct dentry *dentry, struct nameidata *nd)
 	/* Null-terminate the name */
 	if (res <= plen)
 		paddr[res] = '\0';
-	nd_set_link(nd, paddr);
 	ext4_put_fname_crypto_ctx(&ctx);
 	if (cpage) {
 		kunmap(cpage);
 		page_cache_release(cpage);
 	}
-	return NULL;
+	return *cookie = paddr;
 errout:
 	ext4_put_fname_crypto_ctx(&ctx);
 	if (cpage) {
@@ -97,36 +93,22 @@ errout:
 	return ERR_PTR(res);
 }
 
-static void ext4_put_link(struct dentry *dentry, struct nameidata *nd,
-			  void *cookie)
-{
-	struct page *page = cookie;
-
-	if (!page) {
-		kfree(nd_get_link(nd));
-	} else {
-		kunmap(page);
-		page_cache_release(page);
-	}
-}
+const struct inode_operations ext4_encrypted_symlink_inode_operations = {
+	.readlink	= generic_readlink,
+	.follow_link    = ext4_follow_link,
+	.put_link       = kfree_put_link,
+	.setattr	= ext4_setattr,
+	.setxattr	= generic_setxattr,
+	.getxattr	= generic_getxattr,
+	.listxattr	= ext4_listxattr,
+	.removexattr	= generic_removexattr,
+};
 #endif
 
-static void *ext4_follow_fast_link(struct dentry *dentry, struct nameidata *nd)
-{
-	struct ext4_inode_info *ei = EXT4_I(d_inode(dentry));
-	nd_set_link(nd, (char *) ei->i_data);
-	return NULL;
-}
-
 const struct inode_operations ext4_symlink_inode_operations = {
 	.readlink	= generic_readlink,
-#ifdef CONFIG_EXT4_FS_ENCRYPTION
-	.follow_link    = ext4_follow_link,
-	.put_link       = ext4_put_link,
-#else
 	.follow_link	= page_follow_link_light,
 	.put_link	= page_put_link,
-#endif
 	.setattr	= ext4_setattr,
 	.setxattr	= generic_setxattr,
 	.getxattr	= generic_getxattr,
@@ -136,7 +118,7 @@ const struct inode_operations ext4_symlink_inode_operations = {
 
 const struct inode_operations ext4_fast_symlink_inode_operations = {
 	.readlink	= generic_readlink,
-	.follow_link    = ext4_follow_fast_link,
+	.follow_link    = simple_follow_link,
 	.setattr	= ext4_setattr,
 	.setxattr	= generic_setxattr,
 	.getxattr	= generic_getxattr,
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index 658e8079aaf9..71765d062914 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -296,19 +296,15 @@ fail:
 	return err;
 }
 
-static void *f2fs_follow_link(struct dentry *dentry, struct nameidata *nd)
+static const char *f2fs_follow_link(struct dentry *dentry, void **cookie)
 {
-	struct page *page = page_follow_link_light(dentry, nd);
-
-	if (IS_ERR_OR_NULL(page))
-		return page;
-
-	/* this is broken symlink case */
-	if (*nd_get_link(nd) == 0) {
-		page_put_link(dentry, nd, page);
-		return ERR_PTR(-ENOENT);
+	const char *link = page_follow_link_light(dentry, cookie);
+	if (!IS_ERR(link) && !*link) {
+		/* this is broken symlink case */
+		page_put_link(NULL, *cookie);
+		link = ERR_PTR(-ENOENT);
 	}
-	return page;
+	return link;
 }
 
 static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
diff --git a/fs/freevxfs/vxfs_extern.h b/fs/freevxfs/vxfs_extern.h
index 881aa3d217f0..e3dcb4467d92 100644
--- a/fs/freevxfs/vxfs_extern.h
+++ b/fs/freevxfs/vxfs_extern.h
@@ -50,9 +50,6 @@ extern daddr_t			vxfs_bmap1(struct inode *, long);
 /* vxfs_fshead.c */
 extern int			vxfs_read_fshead(struct super_block *);
 
-/* vxfs_immed.c */
-extern const struct inode_operations vxfs_immed_symlink_iops;
-
 /* vxfs_inode.c */
 extern const struct address_space_operations vxfs_immed_aops;
 extern struct kmem_cache	*vxfs_inode_cachep;
diff --git a/fs/freevxfs/vxfs_immed.c b/fs/freevxfs/vxfs_immed.c
index 8b9229e2ca5c..cb84f0fcc72a 100644
--- a/fs/freevxfs/vxfs_immed.c
+++ b/fs/freevxfs/vxfs_immed.c
@@ -32,29 +32,15 @@
  */
 #include <linux/fs.h>
 #include <linux/pagemap.h>
-#include <linux/namei.h>
 
 #include "vxfs.h"
 #include "vxfs_extern.h"
 #include "vxfs_inode.h"
 
 
-static void *	vxfs_immed_follow_link(struct dentry *, struct nameidata *);
-
 static int	vxfs_immed_readpage(struct file *, struct page *);
 
 /*
- * Inode operations for immed symlinks.
- *
- * Unliked all other operations we do not go through the pagecache,
- * but do all work directly on the inode.
- */
-const struct inode_operations vxfs_immed_symlink_iops = {
-	.readlink =		generic_readlink,
-	.follow_link =		vxfs_immed_follow_link,
-};
-
-/*
  * Address space operations for immed files and directories.
  */
 const struct address_space_operations vxfs_immed_aops = {
@@ -62,26 +48,6 @@ const struct address_space_operations vxfs_immed_aops = {
 };
 
 /**
- * vxfs_immed_follow_link - follow immed symlink
- * @dp:		dentry for the link
- * @np:		pathname lookup data for the current path walk
- *
- * Description:
- *   vxfs_immed_follow_link restarts the pathname lookup with
- *   the data obtained from @dp.
- *
- * Returns:
- *   Zero on success, else a negative error code.
- */
-static void *
-vxfs_immed_follow_link(struct dentry *dp, struct nameidata *np)
-{
-	struct vxfs_inode_info		*vip = VXFS_INO(d_inode(dp));
-	nd_set_link(np, vip->vii_immed.vi_immed);
-	return NULL;
-}
-
-/**
  * vxfs_immed_readpage - read part of an immed inode into pagecache
  * @file:	file context (unused)
  * @page:	page frame to fill in.
diff --git a/fs/freevxfs/vxfs_inode.c b/fs/freevxfs/vxfs_inode.c
index 363e3ae25f6b..ef73ed674a27 100644
--- a/fs/freevxfs/vxfs_inode.c
+++ b/fs/freevxfs/vxfs_inode.c
@@ -35,6 +35,7 @@
 #include <linux/pagemap.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>
+#include <linux/namei.h>
 
 #include "vxfs.h"
 #include "vxfs_inode.h"
@@ -327,8 +328,10 @@ vxfs_iget(struct super_block *sbp, ino_t ino)
 			ip->i_op = &page_symlink_inode_operations;
 			ip->i_mapping->a_ops = &vxfs_aops;
 		} else {
-			ip->i_op = &vxfs_immed_symlink_iops;
-			vip->vii_immed.vi_immed[ip->i_size] = '\0';
+			ip->i_op = &simple_symlink_inode_operations;
+			ip->i_link = vip->vii_immed.vi_immed;
+			nd_terminate_link(ip->i_link, ip->i_size,
+					  sizeof(vip->vii_immed.vi_immed) - 1);
 		}
 	} else
 		init_special_inode(ip, ip->i_mode, old_decode_dev(vip->vii_rdev));
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 0572bca49f15..5e2e08712d3b 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -1365,7 +1365,7 @@ static int fuse_readdir(struct file *file, struct dir_context *ctx)
 	return err;
 }
 
-static char *read_link(struct dentry *dentry)
+static const char *fuse_follow_link(struct dentry *dentry, void **cookie)
 {
 	struct inode *inode = d_inode(dentry);
 	struct fuse_conn *fc = get_fuse_conn(inode);
@@ -1389,28 +1389,12 @@ static char *read_link(struct dentry *dentry)
 		link = ERR_PTR(ret);
 	} else {
 		link[ret] = '\0';
+		*cookie = link;
 	}
 	fuse_invalidate_atime(inode);
 	return link;
 }
 
-static void free_link(char *link)
-{
-	if (!IS_ERR(link))
-		free_page((unsigned long) link);
-}
-
-static void *fuse_follow_link(struct dentry *dentry, struct nameidata *nd)
-{
-	nd_set_link(nd, read_link(dentry));
-	return NULL;
-}
-
-static void fuse_put_link(struct dentry *dentry, struct nameidata *nd, void *c)
-{
-	free_link(nd_get_link(nd));
-}
-
 static int fuse_dir_open(struct inode *inode, struct file *file)
 {
 	return fuse_open_common(inode, file, true);
@@ -1926,7 +1910,7 @@ static const struct inode_operations fuse_common_inode_operations = {
 static const struct inode_operations fuse_symlink_inode_operations = {
 	.setattr	= fuse_setattr,
 	.follow_link	= fuse_follow_link,
-	.put_link	= fuse_put_link,
+	.put_link	= free_page_put_link,
 	.readlink	= generic_readlink,
 	.getattr	= fuse_getattr,
 	.setxattr	= fuse_setxattr,
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 1b3ca7a2e3fc..3a1461de1551 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -1548,7 +1548,7 @@ out:
  * Returns: 0 on success or error code
  */
 
-static void *gfs2_follow_link(struct dentry *dentry, struct nameidata *nd)
+static const char *gfs2_follow_link(struct dentry *dentry, void **cookie)
 {
 	struct gfs2_inode *ip = GFS2_I(d_inode(dentry));
 	struct gfs2_holder i_gh;
@@ -1561,8 +1561,7 @@ static void *gfs2_follow_link(struct dentry *dentry, struct nameidata *nd)
 	error = gfs2_glock_nq(&i_gh);
 	if (error) {
 		gfs2_holder_uninit(&i_gh);
-		nd_set_link(nd, ERR_PTR(error));
-		return NULL;
+		return ERR_PTR(error);
 	}
 
 	size = (unsigned int)i_size_read(&ip->i_inode);
@@ -1586,8 +1585,9 @@ static void *gfs2_follow_link(struct dentry *dentry, struct nameidata *nd)
 	brelse(dibh);
 out:
 	gfs2_glock_dq_uninit(&i_gh);
-	nd_set_link(nd, buf);
-	return NULL;
+	if (!IS_ERR(buf))
+		*cookie = buf;
+	return buf;
 }
 
 /**
diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index 07d8d8f52faf..059597b23f67 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -892,7 +892,7 @@ static const struct inode_operations hostfs_dir_iops = {
 	.setattr	= hostfs_setattr,
 };
 
-static void *hostfs_follow_link(struct dentry *dentry, struct nameidata *nd)
+static const char *hostfs_follow_link(struct dentry *dentry, void **cookie)
 {
 	char *link = __getname();
 	if (link) {
@@ -906,21 +906,18 @@ static void *hostfs_follow_link(struct dentry *dentry, struct nameidata *nd)
 		}
 		if (err < 0) {
 			__putname(link);
-			link = ERR_PTR(err);
+			return ERR_PTR(err);
 		}
 	} else {
-		link = ERR_PTR(-ENOMEM);
+		return ERR_PTR(-ENOMEM);
 	}
 
-	nd_set_link(nd, link);
-	return NULL;
+	return *cookie = link;
 }
 
-static void hostfs_put_link(struct dentry *dentry, struct nameidata *nd, void *cookie)
+static void hostfs_put_link(struct inode *unused, void *cookie)
 {
-	char *s = nd_get_link(nd);
-	if (!IS_ERR(s))
-		__putname(s);
+	__putname(cookie);
 }
 
 static const struct inode_operations hostfs_link_iops = {
diff --git a/fs/hppfs/hppfs.c b/fs/hppfs/hppfs.c
index fa2bd5366ecf..2867837909a9 100644
--- a/fs/hppfs/hppfs.c
+++ b/fs/hppfs/hppfs.c
@@ -642,20 +642,19 @@ static int hppfs_readlink(struct dentry *dentry, char __user *buffer,
 						    buflen);
 }
 
-static void *hppfs_follow_link(struct dentry *dentry, struct nameidata *nd)
+static const char *hppfs_follow_link(struct dentry *dentry, void **cookie)
 {
 	struct dentry *proc_dentry = HPPFS_I(d_inode(dentry))->proc_dentry;
 
-	return d_inode(proc_dentry)->i_op->follow_link(proc_dentry, nd);
+	return d_inode(proc_dentry)->i_op->follow_link(proc_dentry, cookie);
 }
 
-static void hppfs_put_link(struct dentry *dentry, struct nameidata *nd,
-			   void *cookie)
+static void hppfs_put_link(struct inode *inode, void *cookie)
 {
-	struct dentry *proc_dentry = HPPFS_I(d_inode(dentry))->proc_dentry;
+	struct inode *proc_inode = d_inode(HPPFS_I(inode)->proc_dentry);
 
-	if (d_inode(proc_dentry)->i_op->put_link)
-		d_inode(proc_dentry)->i_op->put_link(proc_dentry, nd, cookie);
+	if (proc_inode->i_op->put_link)
+		proc_inode->i_op->put_link(proc_inode, cookie);
 }
 
 static const struct inode_operations hppfs_dir_iops = {
diff --git a/fs/inode.c b/fs/inode.c
index ea37cd17b53f..e8d62688ed91 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -152,6 +152,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
 	inode->i_pipe = NULL;
 	inode->i_bdev = NULL;
 	inode->i_cdev = NULL;
+	inode->i_link = NULL;
 	inode->i_rdev = 0;
 	inode->dirtied_when = 0;
 
@@ -1584,36 +1585,47 @@ static int update_time(struct inode *inode, struct timespec *time, int flags)
  *	This function automatically handles read only file systems and media,
  *	as well as the "noatime" flag and inode specific "noatime" markers.
  */
-void touch_atime(const struct path *path)
+bool atime_needs_update(const struct path *path, struct inode *inode)
 {
 	struct vfsmount *mnt = path->mnt;
-	struct inode *inode = d_inode(path->dentry);
 	struct timespec now;
 
 	if (inode->i_flags & S_NOATIME)
-		return;
+		return false;
 	if (IS_NOATIME(inode))
-		return;
+		return false;
 	if ((inode->i_sb->s_flags & MS_NODIRATIME) && S_ISDIR(inode->i_mode))
-		return;
+		return false;
 
 	if (mnt->mnt_flags & MNT_NOATIME)
-		return;
+		return false;
 	if ((mnt->mnt_flags & MNT_NODIRATIME) && S_ISDIR(inode->i_mode))
-		return;
+		return false;
 
 	now = current_fs_time(inode->i_sb);
 
 	if (!relatime_need_update(mnt, inode, now))
-		return;
+		return false;
 
 	if (timespec_equal(&inode->i_atime, &now))
+		return false;
+
+	return true;
+}
+
+void touch_atime(const struct path *path)
+{
+	struct vfsmount *mnt = path->mnt;
+	struct inode *inode = d_inode(path->dentry);
+	struct timespec now;
+
+	if (!atime_needs_update(path, inode))
 		return;
 
 	if (!sb_start_write_trylock(inode->i_sb))
 		return;
 
-	if (__mnt_want_write(mnt))
+	if (__mnt_want_write(mnt) != 0)
 		goto skip_update;
 	/*
 	 * File systems can error out when updating inodes if they need to
@@ -1624,6 +1636,7 @@ void touch_atime(const struct path *path)
 	 * We may also fail on filesystems that have the ability to make parts
 	 * of the fs read only, e.g. subvolumes in Btrfs.
 	 */
+	now = current_fs_time(inode->i_sb);
 	update_time(inode, &now, S_ATIME);
 	__mnt_drop_write(mnt);
 skip_update:
diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c
index 1ba5c97943b8..81180022923f 100644
--- a/fs/jffs2/dir.c
+++ b/fs/jffs2/dir.c
@@ -354,6 +354,7 @@ static int jffs2_symlink (struct inode *dir_i, struct dentry *dentry, const char
 		ret = -ENOMEM;
 		goto fail;
 	}
+	inode->i_link = f->target;
 
 	jffs2_dbg(1, "%s(): symlink's target '%s' cached\n",
 		  __func__, (char *)f->target);
diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c
index fe5ea080b4ec..60d86e8fba6e 100644
--- a/fs/jffs2/fs.c
+++ b/fs/jffs2/fs.c
@@ -294,6 +294,7 @@ struct inode *jffs2_iget(struct super_block *sb, unsigned long ino)
 
 	case S_IFLNK:
 		inode->i_op = &jffs2_symlink_inode_operations;
+		inode->i_link = f->target;
 		break;
 
 	case S_IFDIR:
diff --git a/fs/jffs2/symlink.c b/fs/jffs2/symlink.c
index 1fefa25d0fa5..8ce2f240125b 100644
--- a/fs/jffs2/symlink.c
+++ b/fs/jffs2/symlink.c
@@ -9,58 +9,15 @@
  *
  */
 
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/kernel.h>
-#include <linux/fs.h>
-#include <linux/namei.h>
 #include "nodelist.h"
 
-static void *jffs2_follow_link(struct dentry *dentry, struct nameidata *nd);
-
 const struct inode_operations jffs2_symlink_inode_operations =
 {
 	.readlink =	generic_readlink,
-	.follow_link =	jffs2_follow_link,
+	.follow_link =	simple_follow_link,
 	.setattr =	jffs2_setattr,
 	.setxattr =	jffs2_setxattr,
 	.getxattr =	jffs2_getxattr,
 	.listxattr =	jffs2_listxattr,
 	.removexattr =	jffs2_removexattr
 };
-
-static void *jffs2_follow_link(struct dentry *dentry, struct nameidata *nd)
-{
-	struct jffs2_inode_info *f = JFFS2_INODE_INFO(d_inode(dentry));
-	char *p = (char *)f->target;
-
-	/*
-	 * We don't acquire the f->sem mutex here since the only data we
-	 * use is f->target.
-	 *
-	 * 1. If we are here the inode has already built and f->target has
-	 * to point to the target path.
-	 * 2. Nobody uses f->target (if the inode is symlink's inode). The
-	 * exception is inode freeing function which frees f->target. But
-	 * it can't be called while we are here and before VFS has
-	 * stopped using our f->target string which we provide by means of
-	 * nd_set_link() call.
-	 */
-
-	if (!p) {
-		pr_err("%s(): can't find symlink target\n", __func__);
-		p = ERR_PTR(-EIO);
-	}
-	jffs2_dbg(1, "%s(): target path is '%s'\n",
-		  __func__, (char *)f->target);
-
-	nd_set_link(nd, p);
-
-	/*
-	 * We will unlock the f->sem mutex but VFS will use the f->target string. This is safe
-	 * since the only way that may cause f->target to be changed is iput() operation.
-	 * But VFS will not use f->target after iput() has been called.
-	 */
-	return NULL;
-}
-
diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c
index 070dc4b33544..6f1cb2b5ee28 100644
--- a/fs/jfs/inode.c
+++ b/fs/jfs/inode.c
@@ -63,11 +63,12 @@ struct inode *jfs_iget(struct super_block *sb, unsigned long ino)
 			inode->i_mapping->a_ops = &jfs_aops;
 		} else {
 			inode->i_op = &jfs_fast_symlink_inode_operations;
+			inode->i_link = JFS_IP(inode)->i_inline;
 			/*
 			 * The inline data should be null-terminated, but
 			 * don't let on-disk corruption crash the kernel
 			 */
-			JFS_IP(inode)->i_inline[inode->i_size] = '\0';
+			inode->i_link[inode->i_size] = '\0';
 		}
 	} else {
 		inode->i_op = &jfs_file_inode_operations;
diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c
index 66db7bc0ed10..e33be921aa41 100644
--- a/fs/jfs/namei.c
+++ b/fs/jfs/namei.c
@@ -880,7 +880,6 @@ static int jfs_symlink(struct inode *dip, struct dentry *dentry,
 	int ssize;		/* source pathname size */
 	struct btstack btstack;
 	struct inode *ip = d_inode(dentry);
-	unchar *i_fastsymlink;
 	s64 xlen = 0;
 	int bmask = 0, xsize;
 	s64 xaddr;
@@ -946,8 +945,8 @@ static int jfs_symlink(struct inode *dip, struct dentry *dentry,
 	if (ssize <= IDATASIZE) {
 		ip->i_op = &jfs_fast_symlink_inode_operations;
 
-		i_fastsymlink = JFS_IP(ip)->i_inline;
-		memcpy(i_fastsymlink, name, ssize);
+		ip->i_link = JFS_IP(ip)->i_inline;
+		memcpy(ip->i_link, name, ssize);
 		ip->i_size = ssize - 1;
 
 		/*
diff --git a/fs/jfs/symlink.c b/fs/jfs/symlink.c
index 80f42bcc4ef1..5929e2363cb8 100644
--- a/fs/jfs/symlink.c
+++ b/fs/jfs/symlink.c
@@ -17,21 +17,13 @@
  */
 
 #include <linux/fs.h>
-#include <linux/namei.h>
 #include "jfs_incore.h"
 #include "jfs_inode.h"
 #include "jfs_xattr.h"
 
-static void *jfs_follow_link(struct dentry *dentry, struct nameidata *nd)
-{
-	char *s = JFS_IP(d_inode(dentry))->i_inline;
-	nd_set_link(nd, s);
-	return NULL;
-}
-
 const struct inode_operations jfs_fast_symlink_inode_operations = {
 	.readlink	= generic_readlink,
-	.follow_link	= jfs_follow_link,
+	.follow_link	= simple_follow_link,
 	.setattr	= jfs_setattr,
 	.setxattr	= jfs_setxattr,
 	.getxattr	= jfs_getxattr,
diff --git a/fs/kernfs/symlink.c b/fs/kernfs/symlink.c
index 8a198898e39a..db272528ab5b 100644
--- a/fs/kernfs/symlink.c
+++ b/fs/kernfs/symlink.c
@@ -112,25 +112,18 @@ static int kernfs_getlink(struct dentry *dentry, char *path)
 	return error;
 }
 
-static void *kernfs_iop_follow_link(struct dentry *dentry, struct nameidata *nd)
+static const char *kernfs_iop_follow_link(struct dentry *dentry, void **cookie)
 {
 	int error = -ENOMEM;
 	unsigned long page = get_zeroed_page(GFP_KERNEL);
-	if (page) {
-		error = kernfs_getlink(dentry, (char *) page);
-		if (error < 0)
-			free_page((unsigned long)page);
-	}
-	nd_set_link(nd, error ? ERR_PTR(error) : (char *)page);
-	return NULL;
-}
-
-static void kernfs_iop_put_link(struct dentry *dentry, struct nameidata *nd,
-				void *cookie)
-{
-	char *page = nd_get_link(nd);
-	if (!IS_ERR(page))
+	if (!page)
+		return ERR_PTR(-ENOMEM);
+	error = kernfs_getlink(dentry, (char *)page);
+	if (unlikely(error < 0)) {
 		free_page((unsigned long)page);
+		return ERR_PTR(error);
+	}
+	return *cookie = (char *)page;
 }
 
 const struct inode_operations kernfs_symlink_iops = {
@@ -140,7 +133,7 @@ const struct inode_operations kernfs_symlink_iops = {
 	.listxattr	= kernfs_iop_listxattr,
 	.readlink	= generic_readlink,
 	.follow_link	= kernfs_iop_follow_link,
-	.put_link	= kernfs_iop_put_link,
+	.put_link	= free_page_put_link,
 	.setattr	= kernfs_iop_setattr,
 	.getattr	= kernfs_iop_getattr,
 	.permission	= kernfs_iop_permission,
diff --git a/fs/libfs.c b/fs/libfs.c
index cb1fb4b9b637..65e1feca8b98 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -1024,15 +1024,18 @@ int noop_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 }
 EXPORT_SYMBOL(noop_fsync);
 
-void kfree_put_link(struct dentry *dentry, struct nameidata *nd,
-				void *cookie)
+void kfree_put_link(struct inode *unused, void *cookie)
 {
-	char *s = nd_get_link(nd);
-	if (!IS_ERR(s))
-		kfree(s);
+	kfree(cookie);
 }
 EXPORT_SYMBOL(kfree_put_link);
 
+void free_page_put_link(struct inode *unused, void *cookie)
+{
+	free_page((unsigned long) cookie);
+}
+EXPORT_SYMBOL(free_page_put_link);
+
 /*
  * nop .set_page_dirty method so that people can use .page_mkwrite on
  * anon inodes.
@@ -1093,3 +1096,15 @@ simple_nosetlease(struct file *filp, long arg, struct file_lock **flp,
 	return -EINVAL;
 }
 EXPORT_SYMBOL(simple_nosetlease);
+
+const char *simple_follow_link(struct dentry *dentry, void **cookie)
+{
+	return d_inode(dentry)->i_link;
+}
+EXPORT_SYMBOL(simple_follow_link);
+
+const struct inode_operations simple_symlink_inode_operations = {
+	.follow_link = simple_follow_link,
+	.readlink = generic_readlink
+};
+EXPORT_SYMBOL(simple_symlink_inode_operations);
diff --git a/fs/logfs/dir.c b/fs/logfs/dir.c
index 4cf38f118549..f9b45d46d4c4 100644
--- a/fs/logfs/dir.c
+++ b/fs/logfs/dir.c
@@ -779,6 +779,7 @@ fail:
 const struct inode_operations logfs_symlink_iops = {
 	.readlink	= generic_readlink,
 	.follow_link	= page_follow_link_light,
+	.put_link	= page_put_link,
 };
 
 const struct inode_operations logfs_dir_iops = {
diff --git a/fs/mount.h b/fs/mount.h
index 6a61c2b3e385..b5b8082bfa42 100644
--- a/fs/mount.h
+++ b/fs/mount.h
@@ -88,6 +88,7 @@ static inline int is_mounted(struct vfsmount *mnt)
 extern struct mount *__lookup_mnt(struct vfsmount *, struct dentry *);
 extern struct mount *__lookup_mnt_last(struct vfsmount *, struct dentry *);
 
+extern int __legitimize_mnt(struct vfsmount *, unsigned);
 extern bool legitimize_mnt(struct vfsmount *, unsigned);
 
 extern void __detach_mounts(struct dentry *dentry);
diff --git a/fs/namei.c b/fs/namei.c
index fe30d3be43a8..2dad0eaf91d3 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -492,6 +492,7 @@ void path_put(const struct path *path)
 }
 EXPORT_SYMBOL(path_put);
 
+#define EMBEDDED_LEVELS 2
 struct nameidata {
 	struct path	path;
 	struct qstr	last;
@@ -501,10 +502,139 @@ struct nameidata {
 	unsigned	seq, m_seq;
 	int		last_type;
 	unsigned	depth;
-	struct file	*base;
-	char *saved_names[MAX_NESTED_LINKS + 1];
+	int		total_link_count;
+	struct saved {
+		struct path link;
+		void *cookie;
+		const char *name;
+		struct inode *inode;
+		unsigned seq;
+	} *stack, internal[EMBEDDED_LEVELS];
+	struct filename	*name;
+	struct nameidata *saved;
+	unsigned	root_seq;
+	int		dfd;
 };
 
+static void set_nameidata(struct nameidata *p, int dfd, struct filename *name)
+{
+	struct nameidata *old = current->nameidata;
+	p->stack = p->internal;
+	p->dfd = dfd;
+	p->name = name;
+	p->total_link_count = old ? old->total_link_count : 0;
+	p->saved = old;
+	current->nameidata = p;
+}
+
+static void restore_nameidata(void)
+{
+	struct nameidata *now = current->nameidata, *old = now->saved;
+
+	current->nameidata = old;
+	if (old)
+		old->total_link_count = now->total_link_count;
+	if (now->stack != now->internal) {
+		kfree(now->stack);
+		now->stack = now->internal;
+	}
+}
+
+static int __nd_alloc_stack(struct nameidata *nd)
+{
+	struct saved *p;
+
+	if (nd->flags & LOOKUP_RCU) {
+		p= kmalloc(MAXSYMLINKS * sizeof(struct saved),
+				  GFP_ATOMIC);
+		if (unlikely(!p))
+			return -ECHILD;
+	} else {
+		p= kmalloc(MAXSYMLINKS * sizeof(struct saved),
+				  GFP_KERNEL);
+		if (unlikely(!p))
+			return -ENOMEM;
+	}
+	memcpy(p, nd->internal, sizeof(nd->internal));
+	nd->stack = p;
+	return 0;
+}
+
+static inline int nd_alloc_stack(struct nameidata *nd)
+{
+	if (likely(nd->depth != EMBEDDED_LEVELS))
+		return 0;
+	if (likely(nd->stack != nd->internal))
+		return 0;
+	return __nd_alloc_stack(nd);
+}
+
+static void drop_links(struct nameidata *nd)
+{
+	int i = nd->depth;
+	while (i--) {
+		struct saved *last = nd->stack + i;
+		struct inode *inode = last->inode;
+		if (last->cookie && inode->i_op->put_link) {
+			inode->i_op->put_link(inode, last->cookie);
+			last->cookie = NULL;
+		}
+	}
+}
+
+static void terminate_walk(struct nameidata *nd)
+{
+	drop_links(nd);
+	if (!(nd->flags & LOOKUP_RCU)) {
+		int i;
+		path_put(&nd->path);
+		for (i = 0; i < nd->depth; i++)
+			path_put(&nd->stack[i].link);
+		if (nd->root.mnt && !(nd->flags & LOOKUP_ROOT)) {
+			path_put(&nd->root);
+			nd->root.mnt = NULL;
+		}
+	} else {
+		nd->flags &= ~LOOKUP_RCU;
+		if (!(nd->flags & LOOKUP_ROOT))
+			nd->root.mnt = NULL;
+		rcu_read_unlock();
+	}
+	nd->depth = 0;
+}
+
+/* path_put is needed afterwards regardless of success or failure */
+static bool legitimize_path(struct nameidata *nd,
+			    struct path *path, unsigned seq)
+{
+	int res = __legitimize_mnt(path->mnt, nd->m_seq);
+	if (unlikely(res)) {
+		if (res > 0)
+			path->mnt = NULL;
+		path->dentry = NULL;
+		return false;
+	}
+	if (unlikely(!lockref_get_not_dead(&path->dentry->d_lockref))) {
+		path->dentry = NULL;
+		return false;
+	}
+	return !read_seqcount_retry(&path->dentry->d_seq, seq);
+}
+
+static bool legitimize_links(struct nameidata *nd)
+{
+	int i;
+	for (i = 0; i < nd->depth; i++) {
+		struct saved *last = nd->stack + i;
+		if (unlikely(!legitimize_path(nd, &last->link, last->seq))) {
+			drop_links(nd);
+			nd->depth = i + 1;
+			return false;
+		}
+	}
+	return true;
+}
+
 /*
  * Path walking has 2 modes, rcu-walk and ref-walk (see
  * Documentation/filesystems/path-lookup.txt).  In situations when we can't
@@ -520,35 +650,28 @@ struct nameidata {
  * unlazy_walk - try to switch to ref-walk mode.
  * @nd: nameidata pathwalk data
  * @dentry: child of nd->path.dentry or NULL
+ * @seq: seq number to check dentry against
  * Returns: 0 on success, -ECHILD on failure
  *
  * unlazy_walk attempts to legitimize the current nd->path, nd->root and dentry
  * for ref-walk mode.  @dentry must be a path found by a do_lookup call on
  * @nd or NULL.  Must be called from rcu-walk context.
+ * Nothing should touch nameidata between unlazy_walk() failure and
+ * terminate_walk().
  */
-static int unlazy_walk(struct nameidata *nd, struct dentry *dentry)
+static int unlazy_walk(struct nameidata *nd, struct dentry *dentry, unsigned seq)
 {
-	struct fs_struct *fs = current->fs;
 	struct dentry *parent = nd->path.dentry;
 
 	BUG_ON(!(nd->flags & LOOKUP_RCU));
 
-	/*
-	 * After legitimizing the bastards, terminate_walk()
-	 * will do the right thing for non-RCU mode, and all our
-	 * subsequent exit cases should rcu_read_unlock()
-	 * before returning.  Do vfsmount first; if dentry
-	 * can't be legitimized, just set nd->path.dentry to NULL
-	 * and rely on dput(NULL) being a no-op.
-	 */
-	if (!legitimize_mnt(nd->path.mnt, nd->m_seq))
-		return -ECHILD;
 	nd->flags &= ~LOOKUP_RCU;
-
-	if (!lockref_get_not_dead(&parent->d_lockref)) {
-		nd->path.dentry = NULL;	
-		goto out;
-	}
+	if (unlikely(!legitimize_links(nd)))
+		goto out2;
+	if (unlikely(!legitimize_mnt(nd->path.mnt, nd->m_seq)))
+		goto out2;
+	if (unlikely(!lockref_get_not_dead(&parent->d_lockref)))
+		goto out1;
 
 	/*
 	 * For a negative lookup, the lookup sequence point is the parents
@@ -568,7 +691,7 @@ static int unlazy_walk(struct nameidata *nd, struct dentry *dentry)
 	} else {
 		if (!lockref_get_not_dead(&dentry->d_lockref))
 			goto out;
-		if (read_seqcount_retry(&dentry->d_seq, nd->seq))
+		if (read_seqcount_retry(&dentry->d_seq, seq))
 			goto drop_dentry;
 	}
 
@@ -577,22 +700,24 @@ static int unlazy_walk(struct nameidata *nd, struct dentry *dentry)
 	 * still valid and get it if required.
 	 */
 	if (nd->root.mnt && !(nd->flags & LOOKUP_ROOT)) {
-		spin_lock(&fs->lock);
-		if (nd->root.mnt != fs->root.mnt || nd->root.dentry != fs->root.dentry)
-			goto unlock_and_drop_dentry;
-		path_get(&nd->root);
-		spin_unlock(&fs->lock);
+		if (unlikely(!legitimize_path(nd, &nd->root, nd->root_seq))) {
+			rcu_read_unlock();
+			dput(dentry);
+			return -ECHILD;
+		}
 	}
 
 	rcu_read_unlock();
 	return 0;
 
-unlock_and_drop_dentry:
-	spin_unlock(&fs->lock);
 drop_dentry:
 	rcu_read_unlock();
 	dput(dentry);
 	goto drop_root_mnt;
+out2:
+	nd->path.mnt = NULL;
+out1:
+	nd->path.dentry = NULL;
 out:
 	rcu_read_unlock();
 drop_root_mnt:
@@ -601,6 +726,24 @@ drop_root_mnt:
 	return -ECHILD;
 }
 
+static int unlazy_link(struct nameidata *nd, struct path *link, unsigned seq)
+{
+	if (unlikely(!legitimize_path(nd, link, seq))) {
+		drop_links(nd);
+		nd->depth = 0;
+		nd->flags &= ~LOOKUP_RCU;
+		nd->path.mnt = NULL;
+		nd->path.dentry = NULL;
+		if (!(nd->flags & LOOKUP_ROOT))
+			nd->root.mnt = NULL;
+		rcu_read_unlock();
+	} else if (likely(unlazy_walk(nd, NULL, 0)) == 0) {
+		return 0;
+	}
+	path_put(link);
+	return -ECHILD;
+}
+
 static inline int d_revalidate(struct dentry *dentry, unsigned int flags)
 {
 	return dentry->d_op->d_revalidate(dentry, flags);
@@ -622,26 +765,10 @@ static int complete_walk(struct nameidata *nd)
 	int status;
 
 	if (nd->flags & LOOKUP_RCU) {
-		nd->flags &= ~LOOKUP_RCU;
 		if (!(nd->flags & LOOKUP_ROOT))
 			nd->root.mnt = NULL;
-
-		if (!legitimize_mnt(nd->path.mnt, nd->m_seq)) {
-			rcu_read_unlock();
-			return -ECHILD;
-		}
-		if (unlikely(!lockref_get_not_dead(&dentry->d_lockref))) {
-			rcu_read_unlock();
-			mntput(nd->path.mnt);
+		if (unlikely(unlazy_walk(nd, NULL, 0)))
 			return -ECHILD;
-		}
-		if (read_seqcount_retry(&dentry->d_seq, nd->seq)) {
-			rcu_read_unlock();
-			dput(dentry);
-			mntput(nd->path.mnt);
-			return -ECHILD;
-		}
-		rcu_read_unlock();
 	}
 
 	if (likely(!(nd->flags & LOOKUP_JUMPED)))
@@ -657,28 +784,25 @@ static int complete_walk(struct nameidata *nd)
 	if (!status)
 		status = -ESTALE;
 
-	path_put(&nd->path);
 	return status;
 }
 
-static __always_inline void set_root(struct nameidata *nd)
+static void set_root(struct nameidata *nd)
 {
 	get_fs_root(current->fs, &nd->root);
 }
 
-static int link_path_walk(const char *, struct nameidata *);
-
-static __always_inline unsigned set_root_rcu(struct nameidata *nd)
+static unsigned set_root_rcu(struct nameidata *nd)
 {
 	struct fs_struct *fs = current->fs;
-	unsigned seq, res;
+	unsigned seq;
 
 	do {
 		seq = read_seqcount_begin(&fs->seq);
 		nd->root = fs->root;
-		res = __read_seqcount_begin(&nd->root.dentry->d_seq);
+		nd->root_seq = __read_seqcount_begin(&nd->root.dentry->d_seq);
 	} while (read_seqcount_retry(&fs->seq, seq));
-	return res;
+	return nd->root_seq;
 }
 
 static void path_put_conditional(struct path *path, struct nameidata *nd)
@@ -704,8 +828,9 @@ static inline void path_to_nameidata(const struct path *path,
  * Helper to directly jump to a known parsed path from ->follow_link,
  * caller must have taken a reference to path beforehand.
  */
-void nd_jump_link(struct nameidata *nd, struct path *path)
+void nd_jump_link(struct path *path)
 {
+	struct nameidata *nd = current->nameidata;
 	path_put(&nd->path);
 
 	nd->path = *path;
@@ -713,24 +838,14 @@ void nd_jump_link(struct nameidata *nd, struct path *path)
 	nd->flags |= LOOKUP_JUMPED;
 }
 
-void nd_set_link(struct nameidata *nd, char *path)
-{
-	nd->saved_names[nd->depth] = path;
-}
-EXPORT_SYMBOL(nd_set_link);
-
-char *nd_get_link(struct nameidata *nd)
-{
-	return nd->saved_names[nd->depth];
-}
-EXPORT_SYMBOL(nd_get_link);
-
-static inline void put_link(struct nameidata *nd, struct path *link, void *cookie)
+static inline void put_link(struct nameidata *nd)
 {
-	struct inode *inode = link->dentry->d_inode;
-	if (inode->i_op->put_link)
-		inode->i_op->put_link(link->dentry, nd, cookie);
-	path_put(link);
+	struct saved *last = nd->stack + --nd->depth;
+	struct inode *inode = last->inode;
+	if (last->cookie && inode->i_op->put_link)
+		inode->i_op->put_link(inode, last->cookie);
+	if (!(nd->flags & LOOKUP_RCU))
+		path_put(&last->link);
 }
 
 int sysctl_protected_symlinks __read_mostly = 0;
@@ -738,7 +853,6 @@ int sysctl_protected_hardlinks __read_mostly = 0;
 
 /**
  * may_follow_link - Check symlink following for unsafe situations
- * @link: The path of the symlink
  * @nd: nameidata pathwalk data
  *
  * In the case of the sysctl_protected_symlinks sysctl being enabled,
@@ -752,7 +866,7 @@ int sysctl_protected_hardlinks __read_mostly = 0;
  *
  * Returns 0 if following the symlink is allowed, -ve on error.
  */
-static inline int may_follow_link(struct path *link, struct nameidata *nd)
+static inline int may_follow_link(struct nameidata *nd)
 {
 	const struct inode *inode;
 	const struct inode *parent;
@@ -761,7 +875,7 @@ static inline int may_follow_link(struct path *link, struct nameidata *nd)
 		return 0;
 
 	/* Allowed if owner and follower match. */
-	inode = link->dentry->d_inode;
+	inode = nd->stack[0].inode;
 	if (uid_eq(current_cred()->fsuid, inode->i_uid))
 		return 0;
 
@@ -774,9 +888,10 @@ static inline int may_follow_link(struct path *link, struct nameidata *nd)
 	if (uid_eq(parent->i_uid, inode->i_uid))
 		return 0;
 
-	audit_log_link_denied("follow_link", link);
-	path_put_conditional(link, nd);
-	path_put(&nd->path);
+	if (nd->flags & LOOKUP_RCU)
+		return -ECHILD;
+
+	audit_log_link_denied("follow_link", &nd->stack[0].link);
 	return -EACCES;
 }
 
@@ -849,82 +964,68 @@ static int may_linkat(struct path *link)
 	return -EPERM;
 }
 
-static __always_inline int
-follow_link(struct path *link, struct nameidata *nd, void **p)
+static __always_inline
+const char *get_link(struct nameidata *nd)
 {
-	struct dentry *dentry = link->dentry;
+	struct saved *last = nd->stack + nd->depth - 1;
+	struct dentry *dentry = last->link.dentry;
+	struct inode *inode = last->inode;
 	int error;
-	char *s;
+	const char *res;
 
-	BUG_ON(nd->flags & LOOKUP_RCU);
-
-	if (link->mnt == nd->path.mnt)
-		mntget(link->mnt);
-
-	error = -ELOOP;
-	if (unlikely(current->total_link_count >= 40))
-		goto out_put_nd_path;
-
-	cond_resched();
-	current->total_link_count++;
-
-	touch_atime(link);
-	nd_set_link(nd, NULL);
+	if (!(nd->flags & LOOKUP_RCU)) {
+		touch_atime(&last->link);
+		cond_resched();
+	} else if (atime_needs_update(&last->link, inode)) {
+		if (unlikely(unlazy_walk(nd, NULL, 0)))
+			return ERR_PTR(-ECHILD);
+		touch_atime(&last->link);
+	}
 
-	error = security_inode_follow_link(link->dentry, nd);
-	if (error)
-		goto out_put_nd_path;
+	error = security_inode_follow_link(dentry, inode,
+					   nd->flags & LOOKUP_RCU);
+	if (unlikely(error))
+		return ERR_PTR(error);
 
 	nd->last_type = LAST_BIND;
-	*p = dentry->d_inode->i_op->follow_link(dentry, nd);
-	error = PTR_ERR(*p);
-	if (IS_ERR(*p))
-		goto out_put_nd_path;
-
-	error = 0;
-	s = nd_get_link(nd);
-	if (s) {
-		if (unlikely(IS_ERR(s))) {
-			path_put(&nd->path);
-			put_link(nd, link, *p);
-			return PTR_ERR(s);
+	res = inode->i_link;
+	if (!res) {
+		if (nd->flags & LOOKUP_RCU) {
+			if (unlikely(unlazy_walk(nd, NULL, 0)))
+				return ERR_PTR(-ECHILD);
 		}
-		if (*s == '/') {
+		res = inode->i_op->follow_link(dentry, &last->cookie);
+		if (IS_ERR_OR_NULL(res)) {
+			last->cookie = NULL;
+			return res;
+		}
+	}
+	if (*res == '/') {
+		if (nd->flags & LOOKUP_RCU) {
+			struct dentry *d;
+			if (!nd->root.mnt)
+				set_root_rcu(nd);
+			nd->path = nd->root;
+			d = nd->path.dentry;
+			nd->inode = d->d_inode;
+			nd->seq = nd->root_seq;
+			if (unlikely(read_seqcount_retry(&d->d_seq, nd->seq)))
+				return ERR_PTR(-ECHILD);
+		} else {
 			if (!nd->root.mnt)
 				set_root(nd);
 			path_put(&nd->path);
 			nd->path = nd->root;
 			path_get(&nd->root);
-			nd->flags |= LOOKUP_JUMPED;
+			nd->inode = nd->path.dentry->d_inode;
 		}
-		nd->inode = nd->path.dentry->d_inode;
-		error = link_path_walk(s, nd);
-		if (unlikely(error))
-			put_link(nd, link, *p);
+		nd->flags |= LOOKUP_JUMPED;
+		while (unlikely(*++res == '/'))
+			;
 	}
-
-	return error;
-
-out_put_nd_path:
-	*p = NULL;
-	path_put(&nd->path);
-	path_put(link);
-	return error;
-}
-
-static int follow_up_rcu(struct path *path)
-{
-	struct mount *mnt = real_mount(path->mnt);
-	struct mount *parent;
-	struct dentry *mountpoint;
-
-	parent = mnt->mnt_parent;
-	if (&parent->mnt == path->mnt)
-		return 0;
-	mountpoint = mnt->mnt_mountpoint;
-	path->dentry = mountpoint;
-	path->mnt = &parent->mnt;
-	return 1;
+	if (!*res)
+		res = NULL;
+	return res;
 }
 
 /*
@@ -965,7 +1066,7 @@ EXPORT_SYMBOL(follow_up);
  * - return -EISDIR to tell follow_managed() to stop and return the path we
  *   were called with.
  */
-static int follow_automount(struct path *path, unsigned flags,
+static int follow_automount(struct path *path, struct nameidata *nd,
 			    bool *need_mntput)
 {
 	struct vfsmount *mnt;
@@ -985,13 +1086,13 @@ static int follow_automount(struct path *path, unsigned flags,
 	 * as being automount points.  These will need the attentions
 	 * of the daemon to instantiate them before they can be used.
 	 */
-	if (!(flags & (LOOKUP_PARENT | LOOKUP_DIRECTORY |
-		     LOOKUP_OPEN | LOOKUP_CREATE | LOOKUP_AUTOMOUNT)) &&
+	if (!(nd->flags & (LOOKUP_PARENT | LOOKUP_DIRECTORY |
+			   LOOKUP_OPEN | LOOKUP_CREATE | LOOKUP_AUTOMOUNT)) &&
 	    path->dentry->d_inode)
 		return -EISDIR;
 
-	current->total_link_count++;
-	if (current->total_link_count >= 40)
+	nd->total_link_count++;
+	if (nd->total_link_count >= 40)
 		return -ELOOP;
 
 	mnt = path->dentry->d_op->d_automount(path);
@@ -1005,7 +1106,7 @@ static int follow_automount(struct path *path, unsigned flags,
 		 * the path being looked up; if it wasn't then the remainder of
 		 * the path is inaccessible and we should say so.
 		 */
-		if (PTR_ERR(mnt) == -EISDIR && (flags & LOOKUP_PARENT))
+		if (PTR_ERR(mnt) == -EISDIR && (nd->flags & LOOKUP_PARENT))
 			return -EREMOTE;
 		return PTR_ERR(mnt);
 	}
@@ -1045,7 +1146,7 @@ static int follow_automount(struct path *path, unsigned flags,
  *
  * Serialization is taken care of in namespace.c
  */
-static int follow_managed(struct path *path, unsigned flags)
+static int follow_managed(struct path *path, struct nameidata *nd)
 {
 	struct vfsmount *mnt = path->mnt; /* held by caller, must be left alone */
 	unsigned managed;
@@ -1089,7 +1190,7 @@ static int follow_managed(struct path *path, unsigned flags)
 
 		/* Handle an automount point */
 		if (managed & DCACHE_NEED_AUTOMOUNT) {
-			ret = follow_automount(path, flags, &need_mntput);
+			ret = follow_automount(path, nd, &need_mntput);
 			if (ret < 0)
 				break;
 			continue;
@@ -1103,7 +1204,11 @@ static int follow_managed(struct path *path, unsigned flags)
 		mntput(path->mnt);
 	if (ret == -EISDIR)
 		ret = 0;
-	return ret < 0 ? ret : need_mntput;
+	if (need_mntput)
+		nd->flags |= LOOKUP_JUMPED;
+	if (unlikely(ret < 0))
+		path_put_conditional(path, nd);
+	return ret;
 }
 
 int follow_down_one(struct path *path)
@@ -1133,7 +1238,7 @@ static inline int managed_dentry_rcu(struct dentry *dentry)
  * we meet a managed dentry that would need blocking.
  */
 static bool __follow_mount_rcu(struct nameidata *nd, struct path *path,
-			       struct inode **inode)
+			       struct inode **inode, unsigned *seqp)
 {
 	for (;;) {
 		struct mount *mounted;
@@ -1160,7 +1265,7 @@ static bool __follow_mount_rcu(struct nameidata *nd, struct path *path,
 		path->mnt = &mounted->mnt;
 		path->dentry = mounted->mnt.mnt_root;
 		nd->flags |= LOOKUP_JUMPED;
-		nd->seq = read_seqcount_begin(&path->dentry->d_seq);
+		*seqp = read_seqcount_begin(&path->dentry->d_seq);
 		/*
 		 * Update the inode too. We don't need to re-check the
 		 * dentry sequence number here after this d_inode read,
@@ -1179,10 +1284,8 @@ static int follow_dotdot_rcu(struct nameidata *nd)
 		set_root_rcu(nd);
 
 	while (1) {
-		if (nd->path.dentry == nd->root.dentry &&
-		    nd->path.mnt == nd->root.mnt) {
+		if (path_equal(&nd->path, &nd->root))
 			break;
-		}
 		if (nd->path.dentry != nd->path.mnt->mnt_root) {
 			struct dentry *old = nd->path.dentry;
 			struct dentry *parent = old->d_parent;
@@ -1190,38 +1293,42 @@ static int follow_dotdot_rcu(struct nameidata *nd)
 
 			inode = parent->d_inode;
 			seq = read_seqcount_begin(&parent->d_seq);
-			if (read_seqcount_retry(&old->d_seq, nd->seq))
-				goto failed;
+			if (unlikely(read_seqcount_retry(&old->d_seq, nd->seq)))
+				return -ECHILD;
 			nd->path.dentry = parent;
 			nd->seq = seq;
 			break;
+		} else {
+			struct mount *mnt = real_mount(nd->path.mnt);
+			struct mount *mparent = mnt->mnt_parent;
+			struct dentry *mountpoint = mnt->mnt_mountpoint;
+			struct inode *inode2 = mountpoint->d_inode;
+			unsigned seq = read_seqcount_begin(&mountpoint->d_seq);
+			if (unlikely(read_seqretry(&mount_lock, nd->m_seq)))
+				return -ECHILD;
+			if (&mparent->mnt == nd->path.mnt)
+				break;
+			/* we know that mountpoint was pinned */
+			nd->path.dentry = mountpoint;
+			nd->path.mnt = &mparent->mnt;
+			inode = inode2;
+			nd->seq = seq;
 		}
-		if (!follow_up_rcu(&nd->path))
-			break;
-		inode = nd->path.dentry->d_inode;
-		nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
 	}
-	while (d_mountpoint(nd->path.dentry)) {
+	while (unlikely(d_mountpoint(nd->path.dentry))) {
 		struct mount *mounted;
 		mounted = __lookup_mnt(nd->path.mnt, nd->path.dentry);
+		if (unlikely(read_seqretry(&mount_lock, nd->m_seq)))
+			return -ECHILD;
 		if (!mounted)
 			break;
 		nd->path.mnt = &mounted->mnt;
 		nd->path.dentry = mounted->mnt.mnt_root;
 		inode = nd->path.dentry->d_inode;
 		nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
-		if (read_seqretry(&mount_lock, nd->m_seq))
-			goto failed;
 	}
 	nd->inode = inode;
 	return 0;
-
-failed:
-	nd->flags &= ~LOOKUP_RCU;
-	if (!(nd->flags & LOOKUP_ROOT))
-		nd->root.mnt = NULL;
-	rcu_read_unlock();
-	return -ECHILD;
 }
 
 /*
@@ -1400,7 +1507,8 @@ static struct dentry *__lookup_hash(struct qstr *name,
  *  It _is_ time-critical.
  */
 static int lookup_fast(struct nameidata *nd,
-		       struct path *path, struct inode **inode)
+		       struct path *path, struct inode **inode,
+		       unsigned *seqp)
 {
 	struct vfsmount *mnt = nd->path.mnt;
 	struct dentry *dentry, *parent = nd->path.dentry;
@@ -1424,7 +1532,7 @@ static int lookup_fast(struct nameidata *nd,
 		 * This sequence count validates that the inode matches
 		 * the dentry name information from lookup.
 		 */
-		*inode = dentry->d_inode;
+		*inode = d_backing_inode(dentry);
 		negative = d_is_negative(dentry);
 		if (read_seqcount_retry(&dentry->d_seq, seq))
 			return -ECHILD;
@@ -1440,8 +1548,8 @@ static int lookup_fast(struct nameidata *nd,
 		 */
 		if (__read_seqcount_retry(&parent->d_seq, nd->seq))
 			return -ECHILD;
-		nd->seq = seq;
 
+		*seqp = seq;
 		if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE)) {
 			status = d_revalidate(dentry, nd->flags);
 			if (unlikely(status <= 0)) {
@@ -1452,10 +1560,10 @@ static int lookup_fast(struct nameidata *nd,
 		}
 		path->mnt = mnt;
 		path->dentry = dentry;
-		if (likely(__follow_mount_rcu(nd, path, inode)))
+		if (likely(__follow_mount_rcu(nd, path, inode, seqp)))
 			return 0;
 unlazy:
-		if (unlazy_walk(nd, dentry))
+		if (unlazy_walk(nd, dentry, seq))
 			return -ECHILD;
 	} else {
 		dentry = __d_lookup(parent, &nd->last);
@@ -1482,15 +1590,10 @@ unlazy:
 	}
 	path->mnt = mnt;
 	path->dentry = dentry;
-	err = follow_managed(path, nd->flags);
-	if (unlikely(err < 0)) {
-		path_put_conditional(path, nd);
-		return err;
-	}
-	if (err)
-		nd->flags |= LOOKUP_JUMPED;
-	*inode = path->dentry->d_inode;
-	return 0;
+	err = follow_managed(path, nd);
+	if (likely(!err))
+		*inode = d_backing_inode(path->dentry);
+	return err;
 
 need_lookup:
 	return 1;
@@ -1500,7 +1603,6 @@ need_lookup:
 static int lookup_slow(struct nameidata *nd, struct path *path)
 {
 	struct dentry *dentry, *parent;
-	int err;
 
 	parent = nd->path.dentry;
 	BUG_ON(nd->inode != parent->d_inode);
@@ -1512,14 +1614,7 @@ static int lookup_slow(struct nameidata *nd, struct path *path)
 		return PTR_ERR(dentry);
 	path->mnt = nd->path.mnt;
 	path->dentry = dentry;
-	err = follow_managed(path, nd->flags);
-	if (unlikely(err < 0)) {
-		path_put_conditional(path, nd);
-		return err;
-	}
-	if (err)
-		nd->flags |= LOOKUP_JUMPED;
-	return 0;
+	return follow_managed(path, nd);
 }
 
 static inline int may_lookup(struct nameidata *nd)
@@ -1528,7 +1623,7 @@ static inline int may_lookup(struct nameidata *nd)
 		int err = inode_permission(nd->inode, MAY_EXEC|MAY_NOT_BLOCK);
 		if (err != -ECHILD)
 			return err;
-		if (unlazy_walk(nd, NULL))
+		if (unlazy_walk(nd, NULL, 0))
 			return -ECHILD;
 	}
 	return inode_permission(nd->inode, MAY_EXEC);
@@ -1538,24 +1633,45 @@ static inline int handle_dots(struct nameidata *nd, int type)
 {
 	if (type == LAST_DOTDOT) {
 		if (nd->flags & LOOKUP_RCU) {
-			if (follow_dotdot_rcu(nd))
-				return -ECHILD;
+			return follow_dotdot_rcu(nd);
 		} else
 			follow_dotdot(nd);
 	}
 	return 0;
 }
 
-static void terminate_walk(struct nameidata *nd)
+static int pick_link(struct nameidata *nd, struct path *link,
+		     struct inode *inode, unsigned seq)
 {
+	int error;
+	struct saved *last;
+	if (unlikely(nd->total_link_count++ >= MAXSYMLINKS)) {
+		path_to_nameidata(link, nd);
+		return -ELOOP;
+	}
 	if (!(nd->flags & LOOKUP_RCU)) {
-		path_put(&nd->path);
-	} else {
-		nd->flags &= ~LOOKUP_RCU;
-		if (!(nd->flags & LOOKUP_ROOT))
-			nd->root.mnt = NULL;
-		rcu_read_unlock();
+		if (link->mnt == nd->path.mnt)
+			mntget(link->mnt);
+	}
+	error = nd_alloc_stack(nd);
+	if (unlikely(error)) {
+		if (error == -ECHILD) {
+			if (unlikely(unlazy_link(nd, link, seq)))
+				return -ECHILD;
+			error = nd_alloc_stack(nd);
+		}
+		if (error) {
+			path_put(link);
+			return error;
+		}
 	}
+
+	last = nd->stack + nd->depth++;
+	last->link = *link;
+	last->cookie = NULL;
+	last->inode = inode;
+	last->seq = seq;
+	return 1;
 }
 
 /*
@@ -1564,98 +1680,68 @@ static void terminate_walk(struct nameidata *nd)
  * so we keep a cache of "no, this doesn't need follow_link"
  * for the common case.
  */
-static inline int should_follow_link(struct dentry *dentry, int follow)
+static inline int should_follow_link(struct nameidata *nd, struct path *link,
+				     int follow,
+				     struct inode *inode, unsigned seq)
 {
-	return unlikely(d_is_symlink(dentry)) ? follow : 0;
+	if (likely(!d_is_symlink(link->dentry)))
+		return 0;
+	if (!follow)
+		return 0;
+	return pick_link(nd, link, inode, seq);
 }
 
-static inline int walk_component(struct nameidata *nd, struct path *path,
-		int follow)
+enum {WALK_GET = 1, WALK_PUT = 2};
+
+static int walk_component(struct nameidata *nd, int flags)
 {
+	struct path path;
 	struct inode *inode;
+	unsigned seq;
 	int err;
 	/*
 	 * "." and ".." are special - ".." especially so because it has
 	 * to be able to know about the current root directory and
 	 * parent relationships.
 	 */
-	if (unlikely(nd->last_type != LAST_NORM))
-		return handle_dots(nd, nd->last_type);
-	err = lookup_fast(nd, path, &inode);
+	if (unlikely(nd->last_type != LAST_NORM)) {
+		err = handle_dots(nd, nd->last_type);
+		if (flags & WALK_PUT)
+			put_link(nd);
+		return err;
+	}
+	err = lookup_fast(nd, &path, &inode, &seq);
 	if (unlikely(err)) {
 		if (err < 0)
-			goto out_err;
+			return err;
 
-		err = lookup_slow(nd, path);
+		err = lookup_slow(nd, &path);
 		if (err < 0)
-			goto out_err;
+			return err;
 
-		inode = path->dentry->d_inode;
+		inode = d_backing_inode(path.dentry);
+		seq = 0;	/* we are already out of RCU mode */
 		err = -ENOENT;
-		if (d_is_negative(path->dentry))
+		if (d_is_negative(path.dentry))
 			goto out_path_put;
 	}
 
-	if (should_follow_link(path->dentry, follow)) {
-		if (nd->flags & LOOKUP_RCU) {
-			if (unlikely(nd->path.mnt != path->mnt ||
-				     unlazy_walk(nd, path->dentry))) {
-				err = -ECHILD;
-				goto out_err;
-			}
-		}
-		BUG_ON(inode != path->dentry->d_inode);
-		return 1;
-	}
-	path_to_nameidata(path, nd);
+	if (flags & WALK_PUT)
+		put_link(nd);
+	err = should_follow_link(nd, &path, flags & WALK_GET, inode, seq);
+	if (unlikely(err))
+		return err;
+	path_to_nameidata(&path, nd);
 	nd->inode = inode;
+	nd->seq = seq;
 	return 0;
 
 out_path_put:
-	path_to_nameidata(path, nd);
-out_err:
-	terminate_walk(nd);
+	path_to_nameidata(&path, nd);
 	return err;
 }
 
 /*
- * This limits recursive symlink follows to 8, while
- * limiting consecutive symlinks to 40.
- *
- * Without that kind of total limit, nasty chains of consecutive
- * symlinks can cause almost arbitrarily long lookups.
- */
-static inline int nested_symlink(struct path *path, struct nameidata *nd)
-{
-	int res;
-
-	if (unlikely(current->link_count >= MAX_NESTED_LINKS)) {
-		path_put_conditional(path, nd);
-		path_put(&nd->path);
-		return -ELOOP;
-	}
-	BUG_ON(nd->depth >= MAX_NESTED_LINKS);
-
-	nd->depth++;
-	current->link_count++;
-
-	do {
-		struct path link = *path;
-		void *cookie;
-
-		res = follow_link(&link, nd, &cookie);
-		if (res)
-			break;
-		res = walk_component(nd, path, LOOKUP_FOLLOW);
-		put_link(nd, &link, cookie);
-	} while (res > 0);
-
-	current->link_count--;
-	nd->depth--;
-	return res;
-}
-
-/*
  * We can do the critical dentry name comparison and hashing
  * operations one word at a time, but we are limited to:
  *
@@ -1781,9 +1867,8 @@ static inline u64 hash_name(const char *name)
  */
 static int link_path_walk(const char *name, struct nameidata *nd)
 {
-	struct path next;
 	int err;
-	
+
 	while (*name=='/')
 		name++;
 	if (!*name)
@@ -1796,7 +1881,7 @@ static int link_path_walk(const char *name, struct nameidata *nd)
 
 		err = may_lookup(nd);
  		if (err)
-			break;
+			return err;
 
 		hash_len = hash_name(name);
 
@@ -1818,7 +1903,7 @@ static int link_path_walk(const char *name, struct nameidata *nd)
 				struct qstr this = { { .hash_len = hash_len }, .name = name };
 				err = parent->d_op->d_hash(parent, &this);
 				if (err < 0)
-					break;
+					return err;
 				hash_len = this.hash_len;
 				name = this.name;
 			}
@@ -1830,7 +1915,7 @@ static int link_path_walk(const char *name, struct nameidata *nd)
 
 		name += hashlen_len(hash_len);
 		if (!*name)
-			return 0;
+			goto OK;
 		/*
 		 * If it wasn't NUL, we know it was '/'. Skip that
 		 * slash, and continue until no more slashes.
@@ -1838,57 +1923,73 @@ static int link_path_walk(const char *name, struct nameidata *nd)
 		do {
 			name++;
 		} while (unlikely(*name == '/'));
-		if (!*name)
-			return 0;
-
-		err = walk_component(nd, &next, LOOKUP_FOLLOW);
+		if (unlikely(!*name)) {
+OK:
+			/* pathname body, done */
+			if (!nd->depth)
+				return 0;
+			name = nd->stack[nd->depth - 1].name;
+			/* trailing symlink, done */
+			if (!name)
+				return 0;
+			/* last component of nested symlink */
+			err = walk_component(nd, WALK_GET | WALK_PUT);
+		} else {
+			err = walk_component(nd, WALK_GET);
+		}
 		if (err < 0)
 			return err;
 
 		if (err) {
-			err = nested_symlink(&next, nd);
-			if (err)
-				return err;
-		}
-		if (!d_can_lookup(nd->path.dentry)) {
-			err = -ENOTDIR; 
-			break;
+			const char *s = get_link(nd);
+
+			if (unlikely(IS_ERR(s)))
+				return PTR_ERR(s);
+			err = 0;
+			if (unlikely(!s)) {
+				/* jumped */
+				put_link(nd);
+			} else {
+				nd->stack[nd->depth - 1].name = name;
+				name = s;
+				continue;
+			}
 		}
+		if (unlikely(!d_can_lookup(nd->path.dentry)))
+			return -ENOTDIR;
 	}
-	terminate_walk(nd);
-	return err;
 }
 
-static int path_init(int dfd, const struct filename *name, unsigned int flags,
-		     struct nameidata *nd)
+static const char *path_init(struct nameidata *nd, unsigned flags)
 {
 	int retval = 0;
-	const char *s = name->name;
+	const char *s = nd->name->name;
 
 	nd->last_type = LAST_ROOT; /* if there are only slashes... */
 	nd->flags = flags | LOOKUP_JUMPED | LOOKUP_PARENT;
 	nd->depth = 0;
-	nd->base = NULL;
+	nd->total_link_count = 0;
 	if (flags & LOOKUP_ROOT) {
 		struct dentry *root = nd->root.dentry;
 		struct inode *inode = root->d_inode;
 		if (*s) {
 			if (!d_can_lookup(root))
-				return -ENOTDIR;
+				return ERR_PTR(-ENOTDIR);
 			retval = inode_permission(inode, MAY_EXEC);
 			if (retval)
-				return retval;
+				return ERR_PTR(retval);
 		}
 		nd->path = nd->root;
 		nd->inode = inode;
 		if (flags & LOOKUP_RCU) {
 			rcu_read_lock();
 			nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
+			nd->root_seq = nd->seq;
 			nd->m_seq = read_seqbegin(&mount_lock);
 		} else {
 			path_get(&nd->path);
 		}
-		goto done;
+		return s;
 	}
 
 	nd->root.mnt = NULL;
@@ -1903,7 +2004,7 @@ static int path_init(int dfd, const struct filename *name, unsigned int flags,
 			path_get(&nd->root);
 		}
 		nd->path = nd->root;
-	} else if (dfd == AT_FDCWD) {
+	} else if (nd->dfd == AT_FDCWD) {
 		if (flags & LOOKUP_RCU) {
 			struct fs_struct *fs = current->fs;
 			unsigned seq;
@@ -1920,180 +2021,205 @@ static int path_init(int dfd, const struct filename *name, unsigned int flags,
 		}
 	} else {
 		/* Caller must check execute permissions on the starting path component */
-		struct fd f = fdget_raw(dfd);
+		struct fd f = fdget_raw(nd->dfd);
 		struct dentry *dentry;
 
 		if (!f.file)
-			return -EBADF;
+			return ERR_PTR(-EBADF);
 
 		dentry = f.file->f_path.dentry;
 
 		if (*s) {
 			if (!d_can_lookup(dentry)) {
 				fdput(f);
-				return -ENOTDIR;
+				return ERR_PTR(-ENOTDIR);
 			}
 		}
 
 		nd->path = f.file->f_path;
 		if (flags & LOOKUP_RCU) {
-			if (f.flags & FDPUT_FPUT)
-				nd->base = f.file;
-			nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
 			rcu_read_lock();
+			nd->inode = nd->path.dentry->d_inode;
+			nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
 		} else {
 			path_get(&nd->path);
-			fdput(f);
+			nd->inode = nd->path.dentry->d_inode;
 		}
+		fdput(f);
+		return s;
 	}
 
 	nd->inode = nd->path.dentry->d_inode;
 	if (!(flags & LOOKUP_RCU))
-		goto done;
+		return s;
 	if (likely(!read_seqcount_retry(&nd->path.dentry->d_seq, nd->seq)))
-		goto done;
+		return s;
 	if (!(nd->flags & LOOKUP_ROOT))
 		nd->root.mnt = NULL;
 	rcu_read_unlock();
-	return -ECHILD;
-done:
-	current->total_link_count = 0;
-	return link_path_walk(s, nd);
+	return ERR_PTR(-ECHILD);
 }
 
-static void path_cleanup(struct nameidata *nd)
+static const char *trailing_symlink(struct nameidata *nd)
 {
-	if (nd->root.mnt && !(nd->flags & LOOKUP_ROOT)) {
-		path_put(&nd->root);
-		nd->root.mnt = NULL;
-	}
-	if (unlikely(nd->base))
-		fput(nd->base);
+	const char *s;
+	int error = may_follow_link(nd);
+	if (unlikely(error))
+		return ERR_PTR(error);
+	nd->flags |= LOOKUP_PARENT;
+	nd->stack[0].name = NULL;
+	s = get_link(nd);
+	return s ? s : "";
 }
 
-static inline int lookup_last(struct nameidata *nd, struct path *path)
+static inline int lookup_last(struct nameidata *nd)
 {
 	if (nd->last_type == LAST_NORM && nd->last.name[nd->last.len])
 		nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
 
 	nd->flags &= ~LOOKUP_PARENT;
-	return walk_component(nd, path, nd->flags & LOOKUP_FOLLOW);
+	return walk_component(nd,
+			nd->flags & LOOKUP_FOLLOW
+				? nd->depth
+					? WALK_PUT | WALK_GET
+					: WALK_GET
+				: 0);
 }
 
 /* Returns 0 and nd will be valid on success; Retuns error, otherwise. */
-static int path_lookupat(int dfd, const struct filename *name,
-				unsigned int flags, struct nameidata *nd)
+static int path_lookupat(struct nameidata *nd, unsigned flags, struct path *path)
 {
-	struct path path;
+	const char *s = path_init(nd, flags);
 	int err;
 
-	/*
-	 * Path walking is largely split up into 2 different synchronisation
-	 * schemes, rcu-walk and ref-walk (explained in
-	 * Documentation/filesystems/path-lookup.txt). These share much of the
-	 * path walk code, but some things particularly setup, cleanup, and
-	 * following mounts are sufficiently divergent that functions are
-	 * duplicated. Typically there is a function foo(), and its RCU
-	 * analogue, foo_rcu().
-	 *
-	 * -ECHILD is the error number of choice (just to avoid clashes) that
-	 * is returned if some aspect of an rcu-walk fails. Such an error must
-	 * be handled by restarting a traditional ref-walk (which will always
-	 * be able to complete).
-	 */
-	err = path_init(dfd, name, flags, nd);
-	if (!err && !(flags & LOOKUP_PARENT)) {
-		err = lookup_last(nd, &path);
-		while (err > 0) {
-			void *cookie;
-			struct path link = path;
-			err = may_follow_link(&link, nd);
-			if (unlikely(err))
-				break;
-			nd->flags |= LOOKUP_PARENT;
-			err = follow_link(&link, nd, &cookie);
-			if (err)
-				break;
-			err = lookup_last(nd, &path);
-			put_link(nd, &link, cookie);
+	if (IS_ERR(s))
+		return PTR_ERR(s);
+	while (!(err = link_path_walk(s, nd))
+		&& ((err = lookup_last(nd)) > 0)) {
+		s = trailing_symlink(nd);
+		if (IS_ERR(s)) {
+			err = PTR_ERR(s);
+			break;
 		}
 	}
-
 	if (!err)
 		err = complete_walk(nd);
 
-	if (!err && nd->flags & LOOKUP_DIRECTORY) {
-		if (!d_can_lookup(nd->path.dentry)) {
-			path_put(&nd->path);
+	if (!err && nd->flags & LOOKUP_DIRECTORY)
+		if (!d_can_lookup(nd->path.dentry))
 			err = -ENOTDIR;
-		}
+	if (!err) {
+		*path = nd->path;
+		nd->path.mnt = NULL;
+		nd->path.dentry = NULL;
 	}
-
-	path_cleanup(nd);
+	terminate_walk(nd);
 	return err;
 }
 
-static int filename_lookup(int dfd, struct filename *name,
-				unsigned int flags, struct nameidata *nd)
+static int filename_lookup(int dfd, struct filename *name, unsigned flags,
+			   struct path *path, struct path *root)
 {
-	int retval = path_lookupat(dfd, name, flags | LOOKUP_RCU, nd);
+	int retval;
+	struct nameidata nd;
+	if (IS_ERR(name))
+		return PTR_ERR(name);
+	if (unlikely(root)) {
+		nd.root = *root;
+		flags |= LOOKUP_ROOT;
+	}
+	set_nameidata(&nd, dfd, name);
+	retval = path_lookupat(&nd, flags | LOOKUP_RCU, path);
 	if (unlikely(retval == -ECHILD))
-		retval = path_lookupat(dfd, name, flags, nd);
+		retval = path_lookupat(&nd, flags, path);
 	if (unlikely(retval == -ESTALE))
-		retval = path_lookupat(dfd, name, flags | LOOKUP_REVAL, nd);
+		retval = path_lookupat(&nd, flags | LOOKUP_REVAL, path);
 
 	if (likely(!retval))
-		audit_inode(name, nd->path.dentry, flags & LOOKUP_PARENT);
+		audit_inode(name, path->dentry, flags & LOOKUP_PARENT);
+	restore_nameidata();
+	putname(name);
 	return retval;
 }
 
+/* Returns 0 and nd will be valid on success; Retuns error, otherwise. */
+static int path_parentat(struct nameidata *nd, unsigned flags,
+				struct path *parent)
+{
+	const char *s = path_init(nd, flags);
+	int err;
+	if (IS_ERR(s))
+		return PTR_ERR(s);
+	err = link_path_walk(s, nd);
+	if (!err)
+		err = complete_walk(nd);
+	if (!err) {
+		*parent = nd->path;
+		nd->path.mnt = NULL;
+		nd->path.dentry = NULL;
+	}
+	terminate_walk(nd);
+	return err;
+}
+
+static struct filename *filename_parentat(int dfd, struct filename *name,
+				unsigned int flags, struct path *parent,
+				struct qstr *last, int *type)
+{
+	int retval;
+	struct nameidata nd;
+
+	if (IS_ERR(name))
+		return name;
+	set_nameidata(&nd, dfd, name);
+	retval = path_parentat(&nd, flags | LOOKUP_RCU, parent);
+	if (unlikely(retval == -ECHILD))
+		retval = path_parentat(&nd, flags, parent);
+	if (unlikely(retval == -ESTALE))
+		retval = path_parentat(&nd, flags | LOOKUP_REVAL, parent);
+	if (likely(!retval)) {
+		*last = nd.last;
+		*type = nd.last_type;
+		audit_inode(name, parent->dentry, LOOKUP_PARENT);
+	} else {
+		putname(name);
+		name = ERR_PTR(retval);
+	}
+	restore_nameidata();
+	return name;
+}
+
 /* does lookup, returns the object with parent locked */
 struct dentry *kern_path_locked(const char *name, struct path *path)
 {
-	struct filename *filename = getname_kernel(name);
-	struct nameidata nd;
+	struct filename *filename;
 	struct dentry *d;
-	int err;
+	struct qstr last;
+	int type;
 
+	filename = filename_parentat(AT_FDCWD, getname_kernel(name), 0, path,
+				    &last, &type);
 	if (IS_ERR(filename))
 		return ERR_CAST(filename);
-
-	err = filename_lookup(AT_FDCWD, filename, LOOKUP_PARENT, &nd);
-	if (err) {
-		d = ERR_PTR(err);
-		goto out;
-	}
-	if (nd.last_type != LAST_NORM) {
-		path_put(&nd.path);
-		d = ERR_PTR(-EINVAL);
-		goto out;
+	if (unlikely(type != LAST_NORM)) {
+		path_put(path);
+		putname(filename);
+		return ERR_PTR(-EINVAL);
 	}
-	mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
-	d = __lookup_hash(&nd.last, nd.path.dentry, 0);
+	mutex_lock_nested(&path->dentry->d_inode->i_mutex, I_MUTEX_PARENT);
+	d = __lookup_hash(&last, path->dentry, 0);
 	if (IS_ERR(d)) {
-		mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
-		path_put(&nd.path);
-		goto out;
+		mutex_unlock(&path->dentry->d_inode->i_mutex);
+		path_put(path);
 	}
-	*path = nd.path;
-out:
 	putname(filename);
 	return d;
 }
 
 int kern_path(const char *name, unsigned int flags, struct path *path)
 {
-	struct nameidata nd;
-	struct filename *filename = getname_kernel(name);
-	int res = PTR_ERR(filename);
-
-	if (!IS_ERR(filename)) {
-		res = filename_lookup(AT_FDCWD, filename, flags, &nd);
-		putname(filename);
-		if (!res)
-			*path = nd.path;
-	}
-	return res;
+	return filename_lookup(AT_FDCWD, getname_kernel(name),
+			       flags, path, NULL);
 }
 EXPORT_SYMBOL(kern_path);
 
@@ -2109,36 +2235,13 @@ int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt,
 		    const char *name, unsigned int flags,
 		    struct path *path)
 {
-	struct filename *filename = getname_kernel(name);
-	int err = PTR_ERR(filename);
-
-	BUG_ON(flags & LOOKUP_PARENT);
-
-	/* the first argument of filename_lookup() is ignored with LOOKUP_ROOT */
-	if (!IS_ERR(filename)) {
-		struct nameidata nd;
-		nd.root.dentry = dentry;
-		nd.root.mnt = mnt;
-		err = filename_lookup(AT_FDCWD, filename,
-				      flags | LOOKUP_ROOT, &nd);
-		if (!err)
-			*path = nd.path;
-		putname(filename);
-	}
-	return err;
+	struct path root = {.mnt = mnt, .dentry = dentry};
+	/* the first argument of filename_lookup() is ignored with root */
+	return filename_lookup(AT_FDCWD, getname_kernel(name),
+			       flags , path, &root);
 }
 EXPORT_SYMBOL(vfs_path_lookup);
 
-/*
- * Restricted form of lookup. Doesn't follow links, single-component only,
- * needs parent already locked. Doesn't follow mounts.
- * SMP-safe.
- */
-static struct dentry *lookup_hash(struct nameidata *nd)
-{
-	return __lookup_hash(&nd->last, nd->path.dentry, nd->flags);
-}
-
 /**
  * lookup_one_len - filesystem helper to lookup single pathname component
  * @name:	pathname component to lookup
@@ -2193,27 +2296,10 @@ EXPORT_SYMBOL(lookup_one_len);
 int user_path_at_empty(int dfd, const char __user *name, unsigned flags,
 		 struct path *path, int *empty)
 {
-	struct nameidata nd;
-	struct filename *tmp = getname_flags(name, flags, empty);
-	int err = PTR_ERR(tmp);
-	if (!IS_ERR(tmp)) {
-
-		BUG_ON(flags & LOOKUP_PARENT);
-
-		err = filename_lookup(dfd, tmp, flags, &nd);
-		putname(tmp);
-		if (!err)
-			*path = nd.path;
-	}
-	return err;
-}
-
-int user_path_at(int dfd, const char __user *name, unsigned flags,
-		 struct path *path)
-{
-	return user_path_at_empty(dfd, name, flags, path, NULL);
+	return filename_lookup(dfd, getname_flags(name, flags, empty),
+			       flags, path, NULL);
 }
-EXPORT_SYMBOL(user_path_at);
+EXPORT_SYMBOL(user_path_at_empty);
 
 /*
  * NB: most callers don't do anything directly with the reference to the
@@ -2221,26 +2307,16 @@ EXPORT_SYMBOL(user_path_at);
  *     allocated by getname. So we must hold the reference to it until all
  *     path-walking is complete.
  */
-static struct filename *
-user_path_parent(int dfd, const char __user *path, struct nameidata *nd,
+static inline struct filename *
+user_path_parent(int dfd, const char __user *path,
+		 struct path *parent,
+		 struct qstr *last,
+		 int *type,
 		 unsigned int flags)
 {
-	struct filename *s = getname(path);
-	int error;
-
 	/* only LOOKUP_REVAL is allowed in extra flags */
-	flags &= LOOKUP_REVAL;
-
-	if (IS_ERR(s))
-		return s;
-
-	error = filename_lookup(dfd, s, flags | LOOKUP_PARENT, nd);
-	if (error) {
-		putname(s);
-		return ERR_PTR(error);
-	}
-
-	return s;
+	return filename_parentat(dfd, getname(path), flags & LOOKUP_REVAL,
+				 parent, last, type);
 }
 
 /**
@@ -2279,10 +2355,8 @@ mountpoint_last(struct nameidata *nd, struct path *path)
 
 	/* If we're in rcuwalk, drop out of it to handle last component */
 	if (nd->flags & LOOKUP_RCU) {
-		if (unlazy_walk(nd, NULL)) {
-			error = -ECHILD;
-			goto out;
-		}
+		if (unlazy_walk(nd, NULL, 0))
+			return -ECHILD;
 	}
 
 	nd->flags &= ~LOOKUP_PARENT;
@@ -2290,7 +2364,7 @@ mountpoint_last(struct nameidata *nd, struct path *path)
 	if (unlikely(nd->last_type != LAST_NORM)) {
 		error = handle_dots(nd, nd->last_type);
 		if (error)
-			goto out;
+			return error;
 		dentry = dget(nd->path.dentry);
 		goto done;
 	}
@@ -2305,74 +2379,60 @@ mountpoint_last(struct nameidata *nd, struct path *path)
 		 */
 		dentry = d_alloc(dir, &nd->last);
 		if (!dentry) {
-			error = -ENOMEM;
 			mutex_unlock(&dir->d_inode->i_mutex);
-			goto out;
+			return -ENOMEM;
 		}
 		dentry = lookup_real(dir->d_inode, dentry, nd->flags);
-		error = PTR_ERR(dentry);
 		if (IS_ERR(dentry)) {
 			mutex_unlock(&dir->d_inode->i_mutex);
-			goto out;
+			return PTR_ERR(dentry);
 		}
 	}
 	mutex_unlock(&dir->d_inode->i_mutex);
 
 done:
 	if (d_is_negative(dentry)) {
-		error = -ENOENT;
 		dput(dentry);
-		goto out;
+		return -ENOENT;
 	}
+	if (nd->depth)
+		put_link(nd);
 	path->dentry = dentry;
 	path->mnt = nd->path.mnt;
-	if (should_follow_link(dentry, nd->flags & LOOKUP_FOLLOW))
-		return 1;
+	error = should_follow_link(nd, path, nd->flags & LOOKUP_FOLLOW,
+				   d_backing_inode(dentry), 0);
+	if (unlikely(error))
+		return error;
 	mntget(path->mnt);
 	follow_mount(path);
-	error = 0;
-out:
-	terminate_walk(nd);
-	return error;
+	return 0;
 }
 
 /**
  * path_mountpoint - look up a path to be umounted
- * @dfd:	directory file descriptor to start walk from
- * @name:	full pathname to walk
- * @path:	pointer to container for result
+ * @nameidata:	lookup context
  * @flags:	lookup flags
+ * @path:	pointer to container for result
  *
  * Look up the given name, but don't attempt to revalidate the last component.
  * Returns 0 and "path" will be valid on success; Returns error otherwise.
  */
 static int
-path_mountpoint(int dfd, const struct filename *name, struct path *path,
-		unsigned int flags)
+path_mountpoint(struct nameidata *nd, unsigned flags, struct path *path)
 {
-	struct nameidata nd;
+	const char *s = path_init(nd, flags);
 	int err;
-
-	err = path_init(dfd, name, flags, &nd);
-	if (unlikely(err))
-		goto out;
-
-	err = mountpoint_last(&nd, path);
-	while (err > 0) {
-		void *cookie;
-		struct path link = *path;
-		err = may_follow_link(&link, &nd);
-		if (unlikely(err))
-			break;
-		nd.flags |= LOOKUP_PARENT;
-		err = follow_link(&link, &nd, &cookie);
-		if (err)
+	if (IS_ERR(s))
+		return PTR_ERR(s);
+	while (!(err = link_path_walk(s, nd)) &&
+		(err = mountpoint_last(nd, path)) > 0) {
+		s = trailing_symlink(nd);
+		if (IS_ERR(s)) {
+			err = PTR_ERR(s);
 			break;
-		err = mountpoint_last(&nd, path);
-		put_link(&nd, &link, cookie);
+		}
 	}
-out:
-	path_cleanup(&nd);
+	terminate_walk(nd);
 	return err;
 }
 
@@ -2380,16 +2440,19 @@ static int
 filename_mountpoint(int dfd, struct filename *name, struct path *path,
 			unsigned int flags)
 {
+	struct nameidata nd;
 	int error;
 	if (IS_ERR(name))
 		return PTR_ERR(name);
-	error = path_mountpoint(dfd, name, path, flags | LOOKUP_RCU);
+	set_nameidata(&nd, dfd, name);
+	error = path_mountpoint(&nd, flags | LOOKUP_RCU, path);
 	if (unlikely(error == -ECHILD))
-		error = path_mountpoint(dfd, name, path, flags);
+		error = path_mountpoint(&nd, flags, path);
 	if (unlikely(error == -ESTALE))
-		error = path_mountpoint(dfd, name, path, flags | LOOKUP_REVAL);
+		error = path_mountpoint(&nd, flags | LOOKUP_REVAL, path);
 	if (likely(!error))
 		audit_inode(name, path->dentry, 0);
+	restore_nameidata();
 	putname(name);
 	return error;
 }
@@ -2456,7 +2519,7 @@ EXPORT_SYMBOL(__check_sticky);
  */
 static int may_delete(struct inode *dir, struct dentry *victim, bool isdir)
 {
-	struct inode *inode = victim->d_inode;
+	struct inode *inode = d_backing_inode(victim);
 	int error;
 
 	if (d_is_negative(victim))
@@ -2922,18 +2985,19 @@ out_dput:
 /*
  * Handle the last step of open()
  */
-static int do_last(struct nameidata *nd, struct path *path,
+static int do_last(struct nameidata *nd,
 		   struct file *file, const struct open_flags *op,
-		   int *opened, struct filename *name)
+		   int *opened)
 {
 	struct dentry *dir = nd->path.dentry;
 	int open_flag = op->open_flag;
 	bool will_truncate = (open_flag & O_TRUNC) != 0;
 	bool got_write = false;
 	int acc_mode = op->acc_mode;
+	unsigned seq;
 	struct inode *inode;
-	bool symlink_ok = false;
 	struct path save_parent = { .dentry = NULL, .mnt = NULL };
+	struct path path;
 	bool retried = false;
 	int error;
 
@@ -2942,7 +3006,7 @@ static int do_last(struct nameidata *nd, struct path *path,
 
 	if (nd->last_type != LAST_NORM) {
 		error = handle_dots(nd, nd->last_type);
-		if (error)
+		if (unlikely(error))
 			return error;
 		goto finish_open;
 	}
@@ -2950,15 +3014,13 @@ static int do_last(struct nameidata *nd, struct path *path,
 	if (!(open_flag & O_CREAT)) {
 		if (nd->last.name[nd->last.len])
 			nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
-		if (open_flag & O_PATH && !(nd->flags & LOOKUP_FOLLOW))
-			symlink_ok = true;
 		/* we _can_ be in RCU mode here */
-		error = lookup_fast(nd, path, &inode);
+		error = lookup_fast(nd, &path, &inode, &seq);
 		if (likely(!error))
 			goto finish_lookup;
 
 		if (error < 0)
-			goto out;
+			return error;
 
 		BUG_ON(nd->inode != dir->d_inode);
 	} else {
@@ -2972,11 +3034,10 @@ static int do_last(struct nameidata *nd, struct path *path,
 		if (error)
 			return error;
 
-		audit_inode(name, dir, LOOKUP_PARENT);
-		error = -EISDIR;
+		audit_inode(nd->name, dir, LOOKUP_PARENT);
 		/* trailing slashes? */
-		if (nd->last.name[nd->last.len])
-			goto out;
+		if (unlikely(nd->last.name[nd->last.len]))
+			return -EISDIR;
 	}
 
 retry_lookup:
@@ -2991,7 +3052,7 @@ retry_lookup:
 		 */
 	}
 	mutex_lock(&dir->d_inode->i_mutex);
-	error = lookup_open(nd, path, file, op, got_write, opened);
+	error = lookup_open(nd, &path, file, op, got_write, opened);
 	mutex_unlock(&dir->d_inode->i_mutex);
 
 	if (error <= 0) {
@@ -3002,7 +3063,7 @@ retry_lookup:
 		    !S_ISREG(file_inode(file)->i_mode))
 			will_truncate = false;
 
-		audit_inode(name, file->f_path.dentry, 0);
+		audit_inode(nd->name, file->f_path.dentry, 0);
 		goto opened;
 	}
 
@@ -3011,15 +3072,15 @@ retry_lookup:
 		open_flag &= ~O_TRUNC;
 		will_truncate = false;
 		acc_mode = MAY_OPEN;
-		path_to_nameidata(path, nd);
+		path_to_nameidata(&path, nd);
 		goto finish_open_created;
 	}
 
 	/*
 	 * create/update audit record if it already exists.
 	 */
-	if (d_is_positive(path->dentry))
-		audit_inode(name, path->dentry, 0);
+	if (d_is_positive(path.dentry))
+		audit_inode(nd->name, path.dentry, 0);
 
 	/*
 	 * If atomic_open() acquired write access it is dropped now due to
@@ -3031,47 +3092,45 @@ retry_lookup:
 		got_write = false;
 	}
 
-	error = -EEXIST;
-	if ((open_flag & (O_EXCL | O_CREAT)) == (O_EXCL | O_CREAT))
-		goto exit_dput;
-
-	error = follow_managed(path, nd->flags);
-	if (error < 0)
-		goto exit_dput;
+	if (unlikely((open_flag & (O_EXCL | O_CREAT)) == (O_EXCL | O_CREAT))) {
+		path_to_nameidata(&path, nd);
+		return -EEXIST;
+	}
 
-	if (error)
-		nd->flags |= LOOKUP_JUMPED;
+	error = follow_managed(&path, nd);
+	if (unlikely(error < 0))
+		return error;
 
 	BUG_ON(nd->flags & LOOKUP_RCU);
-	inode = path->dentry->d_inode;
-	error = -ENOENT;
-	if (d_is_negative(path->dentry)) {
-		path_to_nameidata(path, nd);
-		goto out;
+	inode = d_backing_inode(path.dentry);
+	seq = 0;	/* out of RCU mode, so the value doesn't matter */
+	if (unlikely(d_is_negative(path.dentry))) {
+		path_to_nameidata(&path, nd);
+		return -ENOENT;
 	}
 finish_lookup:
-	/* we _can_ be in RCU mode here */
-	if (should_follow_link(path->dentry, !symlink_ok)) {
-		if (nd->flags & LOOKUP_RCU) {
-			if (unlikely(nd->path.mnt != path->mnt ||
-				     unlazy_walk(nd, path->dentry))) {
-				error = -ECHILD;
-				goto out;
-			}
-		}
-		BUG_ON(inode != path->dentry->d_inode);
-		return 1;
+	if (nd->depth)
+		put_link(nd);
+	error = should_follow_link(nd, &path, nd->flags & LOOKUP_FOLLOW,
+				   inode, seq);
+	if (unlikely(error))
+		return error;
+
+	if (unlikely(d_is_symlink(path.dentry)) && !(open_flag & O_PATH)) {
+		path_to_nameidata(&path, nd);
+		return -ELOOP;
 	}
 
-	if ((nd->flags & LOOKUP_RCU) || nd->path.mnt != path->mnt) {
-		path_to_nameidata(path, nd);
+	if ((nd->flags & LOOKUP_RCU) || nd->path.mnt != path.mnt) {
+		path_to_nameidata(&path, nd);
 	} else {
 		save_parent.dentry = nd->path.dentry;
-		save_parent.mnt = mntget(path->mnt);
-		nd->path.dentry = path->dentry;
+		save_parent.mnt = mntget(path.mnt);
+		nd->path.dentry = path.dentry;
 
 	}
 	nd->inode = inode;
+	nd->seq = seq;
 	/* Why this, you ask?  _Now_ we might have grown LOOKUP_JUMPED... */
 finish_open:
 	error = complete_walk(nd);
@@ -3079,7 +3138,7 @@ finish_open:
 		path_put(&save_parent);
 		return error;
 	}
-	audit_inode(name, nd->path.dentry, 0);
+	audit_inode(nd->name, nd->path.dentry, 0);
 	error = -EISDIR;
 	if ((open_flag & O_CREAT) && d_is_dir(nd->path.dentry))
 		goto out;
@@ -3126,12 +3185,8 @@ out:
 	if (got_write)
 		mnt_drop_write(nd->path.mnt);
 	path_put(&save_parent);
-	terminate_walk(nd);
 	return error;
 
-exit_dput:
-	path_put_conditional(path, nd);
-	goto out;
 exit_fput:
 	fput(file);
 	goto out;
@@ -3155,50 +3210,46 @@ stale_open:
 	goto retry_lookup;
 }
 
-static int do_tmpfile(int dfd, struct filename *pathname,
-		struct nameidata *nd, int flags,
+static int do_tmpfile(struct nameidata *nd, unsigned flags,
 		const struct open_flags *op,
 		struct file *file, int *opened)
 {
 	static const struct qstr name = QSTR_INIT("/", 1);
-	struct dentry *dentry, *child;
+	struct dentry *child;
 	struct inode *dir;
-	int error = path_lookupat(dfd, pathname,
-				  flags | LOOKUP_DIRECTORY, nd);
+	struct path path;
+	int error = path_lookupat(nd, flags | LOOKUP_DIRECTORY, &path);
 	if (unlikely(error))
 		return error;
-	error = mnt_want_write(nd->path.mnt);
+	error = mnt_want_write(path.mnt);
 	if (unlikely(error))
 		goto out;
+	dir = path.dentry->d_inode;
 	/* we want directory to be writable */
-	error = inode_permission(nd->inode, MAY_WRITE | MAY_EXEC);
+	error = inode_permission(dir, MAY_WRITE | MAY_EXEC);
 	if (error)
 		goto out2;
-	dentry = nd->path.dentry;
-	dir = dentry->d_inode;
 	if (!dir->i_op->tmpfile) {
 		error = -EOPNOTSUPP;
 		goto out2;
 	}
-	child = d_alloc(dentry, &name);
+	child = d_alloc(path.dentry, &name);
 	if (unlikely(!child)) {
 		error = -ENOMEM;
 		goto out2;
 	}
-	nd->flags &= ~LOOKUP_DIRECTORY;
-	nd->flags |= op->intent;
-	dput(nd->path.dentry);
-	nd->path.dentry = child;
-	error = dir->i_op->tmpfile(dir, nd->path.dentry, op->mode);
+	dput(path.dentry);
+	path.dentry = child;
+	error = dir->i_op->tmpfile(dir, child, op->mode);
 	if (error)
 		goto out2;
-	audit_inode(pathname, nd->path.dentry, 0);
+	audit_inode(nd->name, child, 0);
 	/* Don't check for other permissions, the inode was just created */
-	error = may_open(&nd->path, MAY_OPEN, op->open_flag);
+	error = may_open(&path, MAY_OPEN, op->open_flag);
 	if (error)
 		goto out2;
-	file->f_path.mnt = nd->path.mnt;
-	error = finish_open(file, nd->path.dentry, NULL, opened);
+	file->f_path.mnt = path.mnt;
+	error = finish_open(file, child, NULL, opened);
 	if (error)
 		goto out2;
 	error = open_check_o_direct(file);
@@ -3211,17 +3262,17 @@ static int do_tmpfile(int dfd, struct filename *pathname,
 		spin_unlock(&inode->i_lock);
 	}
 out2:
-	mnt_drop_write(nd->path.mnt);
+	mnt_drop_write(path.mnt);
 out:
-	path_put(&nd->path);
+	path_put(&path);
 	return error;
 }
 
-static struct file *path_openat(int dfd, struct filename *pathname,
-		struct nameidata *nd, const struct open_flags *op, int flags)
+static struct file *path_openat(struct nameidata *nd,
+			const struct open_flags *op, unsigned flags)
 {
+	const char *s;
 	struct file *file;
-	struct path path;
 	int opened = 0;
 	int error;
 
@@ -3232,37 +3283,25 @@ static struct file *path_openat(int dfd, struct filename *pathname,
 	file->f_flags = op->open_flag;
 
 	if (unlikely(file->f_flags & __O_TMPFILE)) {
-		error = do_tmpfile(dfd, pathname, nd, flags, op, file, &opened);
+		error = do_tmpfile(nd, flags, op, file, &opened);
 		goto out2;
 	}
 
-	error = path_init(dfd, pathname, flags, nd);
-	if (unlikely(error))
-		goto out;
-
-	error = do_last(nd, &path, file, op, &opened, pathname);
-	while (unlikely(error > 0)) { /* trailing symlink */
-		struct path link = path;
-		void *cookie;
-		if (!(nd->flags & LOOKUP_FOLLOW)) {
-			path_put_conditional(&path, nd);
-			path_put(&nd->path);
-			error = -ELOOP;
-			break;
-		}
-		error = may_follow_link(&link, nd);
-		if (unlikely(error))
-			break;
-		nd->flags |= LOOKUP_PARENT;
+	s = path_init(nd, flags);
+	if (IS_ERR(s)) {
+		put_filp(file);
+		return ERR_CAST(s);
+	}
+	while (!(error = link_path_walk(s, nd)) &&
+		(error = do_last(nd, file, op, &opened)) > 0) {
 		nd->flags &= ~(LOOKUP_OPEN|LOOKUP_CREATE|LOOKUP_EXCL);
-		error = follow_link(&link, nd, &cookie);
-		if (unlikely(error))
+		s = trailing_symlink(nd);
+		if (IS_ERR(s)) {
+			error = PTR_ERR(s);
 			break;
-		error = do_last(nd, &path, file, op, &opened, pathname);
-		put_link(nd, &link, cookie);
+		}
 	}
-out:
-	path_cleanup(nd);
+	terminate_walk(nd);
 out2:
 	if (!(opened & FILE_OPENED)) {
 		BUG_ON(!error);
@@ -3287,11 +3326,13 @@ struct file *do_filp_open(int dfd, struct filename *pathname,
 	int flags = op->lookup_flags;
 	struct file *filp;
 
-	filp = path_openat(dfd, pathname, &nd, op, flags | LOOKUP_RCU);
+	set_nameidata(&nd, dfd, pathname);
+	filp = path_openat(&nd, op, flags | LOOKUP_RCU);
 	if (unlikely(filp == ERR_PTR(-ECHILD)))
-		filp = path_openat(dfd, pathname, &nd, op, flags);
+		filp = path_openat(&nd, op, flags);
 	if (unlikely(filp == ERR_PTR(-ESTALE)))
-		filp = path_openat(dfd, pathname, &nd, op, flags | LOOKUP_REVAL);
+		filp = path_openat(&nd, op, flags | LOOKUP_REVAL);
+	restore_nameidata();
 	return filp;
 }
 
@@ -3313,11 +3354,13 @@ struct file *do_file_open_root(struct dentry *dentry, struct vfsmount *mnt,
 	if (unlikely(IS_ERR(filename)))
 		return ERR_CAST(filename);
 
-	file = path_openat(-1, filename, &nd, op, flags | LOOKUP_RCU);
+	set_nameidata(&nd, -1, filename);
+	file = path_openat(&nd, op, flags | LOOKUP_RCU);
 	if (unlikely(file == ERR_PTR(-ECHILD)))
-		file = path_openat(-1, filename, &nd, op, flags);
+		file = path_openat(&nd, op, flags);
 	if (unlikely(file == ERR_PTR(-ESTALE)))
-		file = path_openat(-1, filename, &nd, op, flags | LOOKUP_REVAL);
+		file = path_openat(&nd, op, flags | LOOKUP_REVAL);
+	restore_nameidata();
 	putname(filename);
 	return file;
 }
@@ -3326,7 +3369,8 @@ static struct dentry *filename_create(int dfd, struct filename *name,
 				struct path *path, unsigned int lookup_flags)
 {
 	struct dentry *dentry = ERR_PTR(-EEXIST);
-	struct nameidata nd;
+	struct qstr last;
+	int type;
 	int err2;
 	int error;
 	bool is_dir = (lookup_flags & LOOKUP_DIRECTORY);
@@ -3337,26 +3381,25 @@ static struct dentry *filename_create(int dfd, struct filename *name,
 	 */
 	lookup_flags &= LOOKUP_REVAL;
 
-	error = filename_lookup(dfd, name, LOOKUP_PARENT|lookup_flags, &nd);
-	if (error)
-		return ERR_PTR(error);
+	name = filename_parentat(dfd, name, lookup_flags, path, &last, &type);
+	if (IS_ERR(name))
+		return ERR_CAST(name);
 
 	/*
 	 * Yucky last component or no last component at all?
 	 * (foo/., foo/.., /////)
 	 */
-	if (nd.last_type != LAST_NORM)
+	if (unlikely(type != LAST_NORM))
 		goto out;
-	nd.flags &= ~LOOKUP_PARENT;
-	nd.flags |= LOOKUP_CREATE | LOOKUP_EXCL;
 
 	/* don't fail immediately if it's r/o, at least try to report other errors */
-	err2 = mnt_want_write(nd.path.mnt);
+	err2 = mnt_want_write(path->mnt);
 	/*
 	 * Do the final lookup.
 	 */
-	mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
-	dentry = lookup_hash(&nd);
+	lookup_flags |= LOOKUP_CREATE | LOOKUP_EXCL;
+	mutex_lock_nested(&path->dentry->d_inode->i_mutex, I_MUTEX_PARENT);
+	dentry = __lookup_hash(&last, path->dentry, lookup_flags);
 	if (IS_ERR(dentry))
 		goto unlock;
 
@@ -3370,7 +3413,7 @@ static struct dentry *filename_create(int dfd, struct filename *name,
 	 * all is fine. Let's be bastards - you had / on the end, you've
 	 * been asking for (non-existent) directory. -ENOENT for you.
 	 */
-	if (unlikely(!is_dir && nd.last.name[nd.last.len])) {
+	if (unlikely(!is_dir && last.name[last.len])) {
 		error = -ENOENT;
 		goto fail;
 	}
@@ -3378,31 +3421,26 @@ static struct dentry *filename_create(int dfd, struct filename *name,
 		error = err2;
 		goto fail;
 	}
-	*path = nd.path;
+	putname(name);
 	return dentry;
 fail:
 	dput(dentry);
 	dentry = ERR_PTR(error);
 unlock:
-	mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
+	mutex_unlock(&path->dentry->d_inode->i_mutex);
 	if (!err2)
-		mnt_drop_write(nd.path.mnt);
+		mnt_drop_write(path->mnt);
 out:
-	path_put(&nd.path);
+	path_put(path);
+	putname(name);
 	return dentry;
 }
 
 struct dentry *kern_path_create(int dfd, const char *pathname,
 				struct path *path, unsigned int lookup_flags)
 {
-	struct filename *filename = getname_kernel(pathname);
-	struct dentry *res;
-
-	if (IS_ERR(filename))
-		return ERR_CAST(filename);
-	res = filename_create(dfd, filename, path, lookup_flags);
-	putname(filename);
-	return res;
+	return filename_create(dfd, getname_kernel(pathname),
+				path, lookup_flags);
 }
 EXPORT_SYMBOL(kern_path_create);
 
@@ -3415,16 +3453,10 @@ void done_path_create(struct path *path, struct dentry *dentry)
 }
 EXPORT_SYMBOL(done_path_create);
 
-struct dentry *user_path_create(int dfd, const char __user *pathname,
+inline struct dentry *user_path_create(int dfd, const char __user *pathname,
 				struct path *path, unsigned int lookup_flags)
 {
-	struct filename *tmp = getname(pathname);
-	struct dentry *res;
-	if (IS_ERR(tmp))
-		return ERR_CAST(tmp);
-	res = filename_create(dfd, tmp, path, lookup_flags);
-	putname(tmp);
-	return res;
+	return filename_create(dfd, getname(pathname), path, lookup_flags);
 }
 EXPORT_SYMBOL(user_path_create);
 
@@ -3645,14 +3677,17 @@ static long do_rmdir(int dfd, const char __user *pathname)
 	int error = 0;
 	struct filename *name;
 	struct dentry *dentry;
-	struct nameidata nd;
+	struct path path;
+	struct qstr last;
+	int type;
 	unsigned int lookup_flags = 0;
 retry:
-	name = user_path_parent(dfd, pathname, &nd, lookup_flags);
+	name = user_path_parent(dfd, pathname,
+				&path, &last, &type, lookup_flags);
 	if (IS_ERR(name))
 		return PTR_ERR(name);
 
-	switch(nd.last_type) {
+	switch (type) {
 	case LAST_DOTDOT:
 		error = -ENOTEMPTY;
 		goto exit1;
@@ -3664,13 +3699,12 @@ retry:
 		goto exit1;
 	}
 
-	nd.flags &= ~LOOKUP_PARENT;
-	error = mnt_want_write(nd.path.mnt);
+	error = mnt_want_write(path.mnt);
 	if (error)
 		goto exit1;
 
-	mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
-	dentry = lookup_hash(&nd);
+	mutex_lock_nested(&path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
+	dentry = __lookup_hash(&last, path.dentry, lookup_flags);
 	error = PTR_ERR(dentry);
 	if (IS_ERR(dentry))
 		goto exit2;
@@ -3678,17 +3712,17 @@ retry:
 		error = -ENOENT;
 		goto exit3;
 	}
-	error = security_path_rmdir(&nd.path, dentry);
+	error = security_path_rmdir(&path, dentry);
 	if (error)
 		goto exit3;
-	error = vfs_rmdir(nd.path.dentry->d_inode, dentry);
+	error = vfs_rmdir(path.dentry->d_inode, dentry);
 exit3:
 	dput(dentry);
 exit2:
-	mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
-	mnt_drop_write(nd.path.mnt);
+	mutex_unlock(&path.dentry->d_inode->i_mutex);
+	mnt_drop_write(path.mnt);
 exit1:
-	path_put(&nd.path);
+	path_put(&path);
 	putname(name);
 	if (retry_estale(error, lookup_flags)) {
 		lookup_flags |= LOOKUP_REVAL;
@@ -3771,43 +3805,45 @@ static long do_unlinkat(int dfd, const char __user *pathname)
 	int error;
 	struct filename *name;
 	struct dentry *dentry;
-	struct nameidata nd;
+	struct path path;
+	struct qstr last;
+	int type;
 	struct inode *inode = NULL;
 	struct inode *delegated_inode = NULL;
 	unsigned int lookup_flags = 0;
 retry:
-	name = user_path_parent(dfd, pathname, &nd, lookup_flags);
+	name = user_path_parent(dfd, pathname,
+				&path, &last, &type, lookup_flags);
 	if (IS_ERR(name))
 		return PTR_ERR(name);
 
 	error = -EISDIR;
-	if (nd.last_type != LAST_NORM)
+	if (type != LAST_NORM)
 		goto exit1;
 
-	nd.flags &= ~LOOKUP_PARENT;
-	error = mnt_want_write(nd.path.mnt);
+	error = mnt_want_write(path.mnt);
 	if (error)
 		goto exit1;
 retry_deleg:
-	mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
-	dentry = lookup_hash(&nd);
+	mutex_lock_nested(&path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
+	dentry = __lookup_hash(&last, path.dentry, lookup_flags);
 	error = PTR_ERR(dentry);
 	if (!IS_ERR(dentry)) {
 		/* Why not before? Because we want correct error value */
-		if (nd.last.name[nd.last.len])
+		if (last.name[last.len])
 			goto slashes;
 		inode = dentry->d_inode;
 		if (d_is_negative(dentry))
 			goto slashes;
 		ihold(inode);
-		error = security_path_unlink(&nd.path, dentry);
+		error = security_path_unlink(&path, dentry);
 		if (error)
 			goto exit2;
-		error = vfs_unlink(nd.path.dentry->d_inode, dentry, &delegated_inode);
+		error = vfs_unlink(path.dentry->d_inode, dentry, &delegated_inode);
 exit2:
 		dput(dentry);
 	}
-	mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
+	mutex_unlock(&path.dentry->d_inode->i_mutex);
 	if (inode)
 		iput(inode);	/* truncate the inode here */
 	inode = NULL;
@@ -3816,9 +3852,9 @@ exit2:
 		if (!error)
 			goto retry_deleg;
 	}
-	mnt_drop_write(nd.path.mnt);
+	mnt_drop_write(path.mnt);
 exit1:
-	path_put(&nd.path);
+	path_put(&path);
 	putname(name);
 	if (retry_estale(error, lookup_flags)) {
 		lookup_flags |= LOOKUP_REVAL;
@@ -4248,14 +4284,15 @@ EXPORT_SYMBOL(vfs_rename);
 SYSCALL_DEFINE5(renameat2, int, olddfd, const char __user *, oldname,
 		int, newdfd, const char __user *, newname, unsigned int, flags)
 {
-	struct dentry *old_dir, *new_dir;
 	struct dentry *old_dentry, *new_dentry;
 	struct dentry *trap;
-	struct nameidata oldnd, newnd;
+	struct path old_path, new_path;
+	struct qstr old_last, new_last;
+	int old_type, new_type;
 	struct inode *delegated_inode = NULL;
 	struct filename *from;
 	struct filename *to;
-	unsigned int lookup_flags = 0;
+	unsigned int lookup_flags = 0, target_flags = LOOKUP_RENAME_TARGET;
 	bool should_retry = false;
 	int error;
 
@@ -4269,47 +4306,45 @@ SYSCALL_DEFINE5(renameat2, int, olddfd, const char __user *, oldname,
 	if ((flags & RENAME_WHITEOUT) && !capable(CAP_MKNOD))
 		return -EPERM;
 
+	if (flags & RENAME_EXCHANGE)
+		target_flags = 0;
+
 retry:
-	from = user_path_parent(olddfd, oldname, &oldnd, lookup_flags);
+	from = user_path_parent(olddfd, oldname,
+				&old_path, &old_last, &old_type, lookup_flags);
 	if (IS_ERR(from)) {
 		error = PTR_ERR(from);
 		goto exit;
 	}
 
-	to = user_path_parent(newdfd, newname, &newnd, lookup_flags);
+	to = user_path_parent(newdfd, newname,
+				&new_path, &new_last, &new_type, lookup_flags);
 	if (IS_ERR(to)) {
 		error = PTR_ERR(to);
 		goto exit1;
 	}
 
 	error = -EXDEV;
-	if (oldnd.path.mnt != newnd.path.mnt)
+	if (old_path.mnt != new_path.mnt)
 		goto exit2;
 
-	old_dir = oldnd.path.dentry;
 	error = -EBUSY;
-	if (oldnd.last_type != LAST_NORM)
+	if (old_type != LAST_NORM)
 		goto exit2;
 
-	new_dir = newnd.path.dentry;
 	if (flags & RENAME_NOREPLACE)
 		error = -EEXIST;
-	if (newnd.last_type != LAST_NORM)
+	if (new_type != LAST_NORM)
 		goto exit2;
 
-	error = mnt_want_write(oldnd.path.mnt);
+	error = mnt_want_write(old_path.mnt);
 	if (error)
 		goto exit2;
 
-	oldnd.flags &= ~LOOKUP_PARENT;
-	newnd.flags &= ~LOOKUP_PARENT;
-	if (!(flags & RENAME_EXCHANGE))
-		newnd.flags |= LOOKUP_RENAME_TARGET;
-
 retry_deleg:
-	trap = lock_rename(new_dir, old_dir);
+	trap = lock_rename(new_path.dentry, old_path.dentry);
 
-	old_dentry = lookup_hash(&oldnd);
+	old_dentry = __lookup_hash(&old_last, old_path.dentry, lookup_flags);
 	error = PTR_ERR(old_dentry);
 	if (IS_ERR(old_dentry))
 		goto exit3;
@@ -4317,7 +4352,7 @@ retry_deleg:
 	error = -ENOENT;
 	if (d_is_negative(old_dentry))
 		goto exit4;
-	new_dentry = lookup_hash(&newnd);
+	new_dentry = __lookup_hash(&new_last, new_path.dentry, lookup_flags | target_flags);
 	error = PTR_ERR(new_dentry);
 	if (IS_ERR(new_dentry))
 		goto exit4;
@@ -4331,16 +4366,16 @@ retry_deleg:
 
 		if (!d_is_dir(new_dentry)) {
 			error = -ENOTDIR;
-			if (newnd.last.name[newnd.last.len])
+			if (new_last.name[new_last.len])
 				goto exit5;
 		}
 	}
 	/* unless the source is a directory trailing slashes give -ENOTDIR */
 	if (!d_is_dir(old_dentry)) {
 		error = -ENOTDIR;
-		if (oldnd.last.name[oldnd.last.len])
+		if (old_last.name[old_last.len])
 			goto exit5;
-		if (!(flags & RENAME_EXCHANGE) && newnd.last.name[newnd.last.len])
+		if (!(flags & RENAME_EXCHANGE) && new_last.name[new_last.len])
 			goto exit5;
 	}
 	/* source should not be ancestor of target */
@@ -4353,32 +4388,32 @@ retry_deleg:
 	if (new_dentry == trap)
 		goto exit5;
 
-	error = security_path_rename(&oldnd.path, old_dentry,
-				     &newnd.path, new_dentry, flags);
+	error = security_path_rename(&old_path, old_dentry,
+				     &new_path, new_dentry, flags);
 	if (error)
 		goto exit5;
-	error = vfs_rename(old_dir->d_inode, old_dentry,
-			   new_dir->d_inode, new_dentry,
+	error = vfs_rename(old_path.dentry->d_inode, old_dentry,
+			   new_path.dentry->d_inode, new_dentry,
 			   &delegated_inode, flags);
 exit5:
 	dput(new_dentry);
 exit4:
 	dput(old_dentry);
 exit3:
-	unlock_rename(new_dir, old_dir);
+	unlock_rename(new_path.dentry, old_path.dentry);
 	if (delegated_inode) {
 		error = break_deleg_wait(&delegated_inode);
 		if (!error)
 			goto retry_deleg;
 	}
-	mnt_drop_write(oldnd.path.mnt);
+	mnt_drop_write(old_path.mnt);
 exit2:
 	if (retry_estale(error, lookup_flags))
 		should_retry = true;
-	path_put(&newnd.path);
+	path_put(&new_path);
 	putname(to);
 exit1:
-	path_put(&oldnd.path);
+	path_put(&old_path);
 	putname(from);
 	if (should_retry) {
 		should_retry = false;
@@ -4437,18 +4472,19 @@ EXPORT_SYMBOL(readlink_copy);
  */
 int generic_readlink(struct dentry *dentry, char __user *buffer, int buflen)
 {
-	struct nameidata nd;
 	void *cookie;
+	struct inode *inode = d_inode(dentry);
+	const char *link = inode->i_link;
 	int res;
 
-	nd.depth = 0;
-	cookie = dentry->d_inode->i_op->follow_link(dentry, &nd);
-	if (IS_ERR(cookie))
-		return PTR_ERR(cookie);
-
-	res = readlink_copy(buffer, buflen, nd_get_link(&nd));
-	if (dentry->d_inode->i_op->put_link)
-		dentry->d_inode->i_op->put_link(dentry, &nd, cookie);
+	if (!link) {
+		link = inode->i_op->follow_link(dentry, &cookie);
+		if (IS_ERR(link))
+			return PTR_ERR(link);
+	}
+	res = readlink_copy(buffer, buflen, link);
+	if (inode->i_op->put_link)
+		inode->i_op->put_link(inode, cookie);
 	return res;
 }
 EXPORT_SYMBOL(generic_readlink);
@@ -4480,22 +4516,21 @@ int page_readlink(struct dentry *dentry, char __user *buffer, int buflen)
 }
 EXPORT_SYMBOL(page_readlink);
 
-void *page_follow_link_light(struct dentry *dentry, struct nameidata *nd)
+const char *page_follow_link_light(struct dentry *dentry, void **cookie)
 {
 	struct page *page = NULL;
-	nd_set_link(nd, page_getlink(dentry, &page));
-	return page;
+	char *res = page_getlink(dentry, &page);
+	if (!IS_ERR(res))
+		*cookie = page;
+	return res;
 }
 EXPORT_SYMBOL(page_follow_link_light);
 
-void page_put_link(struct dentry *dentry, struct nameidata *nd, void *cookie)
+void page_put_link(struct inode *unused, void *cookie)
 {
 	struct page *page = cookie;
-
-	if (page) {
-		kunmap(page);
-		page_cache_release(page);
-	}
+	kunmap(page);
+	page_cache_release(page);
 }
 EXPORT_SYMBOL(page_put_link);
 
diff --git a/fs/namespace.c b/fs/namespace.c
index 1b9e11167bae..9c1c43d0d4f1 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -590,24 +590,35 @@ static void delayed_free_vfsmnt(struct rcu_head *head)
 }
 
 /* call under rcu_read_lock */
-bool legitimize_mnt(struct vfsmount *bastard, unsigned seq)
+int __legitimize_mnt(struct vfsmount *bastard, unsigned seq)
 {
 	struct mount *mnt;
 	if (read_seqretry(&mount_lock, seq))
-		return false;
+		return 1;
 	if (bastard == NULL)
-		return true;
+		return 0;
 	mnt = real_mount(bastard);
 	mnt_add_count(mnt, 1);
 	if (likely(!read_seqretry(&mount_lock, seq)))
-		return true;
+		return 0;
 	if (bastard->mnt_flags & MNT_SYNC_UMOUNT) {
 		mnt_add_count(mnt, -1);
-		return false;
+		return 1;
+	}
+	return -1;
+}
+
+/* call under rcu_read_lock */
+bool legitimize_mnt(struct vfsmount *bastard, unsigned seq)
+{
+	int res = __legitimize_mnt(bastard, seq);
+	if (likely(!res))
+		return true;
+	if (unlikely(res < 0)) {
+		rcu_read_unlock();
+		mntput(bastard);
+		rcu_read_lock();
 	}
-	rcu_read_unlock();
-	mntput(bastard);
-	rcu_read_lock();
 	return false;
 }
 
diff --git a/fs/nfs/symlink.c b/fs/nfs/symlink.c
index 2d56200655fe..b6de433da5db 100644
--- a/fs/nfs/symlink.c
+++ b/fs/nfs/symlink.c
@@ -20,7 +20,6 @@
 #include <linux/stat.h>
 #include <linux/mm.h>
 #include <linux/string.h>
-#include <linux/namei.h>
 
 /* Symlink caching in the page cache is even more simplistic
  * and straight-forward than readdir caching.
@@ -43,7 +42,7 @@ error:
 	return -EIO;
 }
 
-static void *nfs_follow_link(struct dentry *dentry, struct nameidata *nd)
+static const char *nfs_follow_link(struct dentry *dentry, void **cookie)
 {
 	struct inode *inode = d_inode(dentry);
 	struct page *page;
@@ -51,19 +50,13 @@ static void *nfs_follow_link(struct dentry *dentry, struct nameidata *nd)
 
 	err = ERR_PTR(nfs_revalidate_mapping(inode, inode->i_mapping));
 	if (err)
-		goto read_failed;
+		return err;
 	page = read_cache_page(&inode->i_data, 0,
 				(filler_t *)nfs_symlink_filler, inode);
-	if (IS_ERR(page)) {
-		err = page;
-		goto read_failed;
-	}
-	nd_set_link(nd, kmap(page));
-	return page;
-
-read_failed:
-	nd_set_link(nd, err);
-	return NULL;
+	if (IS_ERR(page))
+		return ERR_CAST(page);
+	*cookie = page;
+	return kmap(page);
 }
 
 /*
diff --git a/fs/ntfs/namei.c b/fs/ntfs/namei.c
index 0f35b80d17fe..443abecf01b7 100644
--- a/fs/ntfs/namei.c
+++ b/fs/ntfs/namei.c
@@ -35,7 +35,7 @@
  * ntfs_lookup - find the inode represented by a dentry in a directory inode
  * @dir_ino:	directory inode in which to look for the inode
  * @dent:	dentry representing the inode to look for
- * @nd:		lookup nameidata
+ * @flags:	lookup flags
  *
  * In short, ntfs_lookup() looks for the inode represented by the dentry @dent
  * in the directory inode @dir_ino and if found attaches the inode to the
diff --git a/fs/open.c b/fs/open.c
index 98e5a52dc68c..e0250bdcc440 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -367,7 +367,7 @@ retry:
 	if (res)
 		goto out;
 
-	inode = path.dentry->d_inode;
+	inode = d_backing_inode(path.dentry);
 
 	if ((mode & MAY_EXEC) && S_ISREG(inode->i_mode)) {
 		/*
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index 04f124884687..308379b2d0b2 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -140,11 +140,12 @@ struct ovl_link_data {
 	void *cookie;
 };
 
-static void *ovl_follow_link(struct dentry *dentry, struct nameidata *nd)
+static const char *ovl_follow_link(struct dentry *dentry, void **cookie)
 {
-	void *ret;
 	struct dentry *realdentry;
 	struct inode *realinode;
+	struct ovl_link_data *data = NULL;
+	const char *ret;
 
 	realdentry = ovl_dentry_real(dentry);
 	realinode = realdentry->d_inode;
@@ -152,28 +153,28 @@ static void *ovl_follow_link(struct dentry *dentry, struct nameidata *nd)
 	if (WARN_ON(!realinode->i_op->follow_link))
 		return ERR_PTR(-EPERM);
 
-	ret = realinode->i_op->follow_link(realdentry, nd);
-	if (IS_ERR(ret))
-		return ret;
-
 	if (realinode->i_op->put_link) {
-		struct ovl_link_data *data;
-
 		data = kmalloc(sizeof(struct ovl_link_data), GFP_KERNEL);
-		if (!data) {
-			realinode->i_op->put_link(realdentry, nd, ret);
+		if (!data)
 			return ERR_PTR(-ENOMEM);
-		}
 		data->realdentry = realdentry;
-		data->cookie = ret;
+	}
 
-		return data;
-	} else {
-		return NULL;
+	ret = realinode->i_op->follow_link(realdentry, cookie);
+	if (IS_ERR_OR_NULL(ret)) {
+		kfree(data);
+		return ret;
 	}
+
+	if (data)
+		data->cookie = *cookie;
+
+	*cookie = data;
+
+	return ret;
 }
 
-static void ovl_put_link(struct dentry *dentry, struct nameidata *nd, void *c)
+static void ovl_put_link(struct inode *unused, void *c)
 {
 	struct inode *realinode;
 	struct ovl_link_data *data = c;
@@ -182,7 +183,7 @@ static void ovl_put_link(struct dentry *dentry, struct nameidata *nd, void *c)
 		return;
 
 	realinode = data->realdentry->d_inode;
-	realinode->i_op->put_link(data->realdentry, nd, data->cookie);
+	realinode->i_op->put_link(realinode, data->cookie);
 	kfree(data);
 }
 
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 093ca14f5701..286a422f440e 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1380,7 +1380,7 @@ static int proc_exe_link(struct dentry *dentry, struct path *exe_path)
 		return -ENOENT;
 }
 
-static void *proc_pid_follow_link(struct dentry *dentry, struct nameidata *nd)
+static const char *proc_pid_follow_link(struct dentry *dentry, void **cookie)
 {
 	struct inode *inode = d_inode(dentry);
 	struct path path;
@@ -1394,7 +1394,7 @@ static void *proc_pid_follow_link(struct dentry *dentry, struct nameidata *nd)
 	if (error)
 		goto out;
 
-	nd_jump_link(nd, &path);
+	nd_jump_link(&path);
 	return NULL;
 out:
 	return ERR_PTR(error);
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 8272aaba1bb0..afe232b9df6e 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -23,7 +23,6 @@
 #include <linux/slab.h>
 #include <linux/mount.h>
 #include <linux/magic.h>
-#include <linux/namei.h>
 
 #include <asm/uaccess.h>
 
@@ -394,16 +393,16 @@ static const struct file_operations proc_reg_file_ops_no_compat = {
 };
 #endif
 
-static void *proc_follow_link(struct dentry *dentry, struct nameidata *nd)
+static const char *proc_follow_link(struct dentry *dentry, void **cookie)
 {
 	struct proc_dir_entry *pde = PDE(d_inode(dentry));
 	if (unlikely(!use_pde(pde)))
 		return ERR_PTR(-EINVAL);
-	nd_set_link(nd, pde->data);
-	return pde;
+	*cookie = pde;
+	return pde->data;
 }
 
-static void proc_put_link(struct dentry *dentry, struct nameidata *nd, void *p)
+static void proc_put_link(struct inode *unused, void *p)
 {
 	unuse_pde(p);
 }
diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
index e512642dbbdc..f6e8354b8cea 100644
--- a/fs/proc/namespaces.c
+++ b/fs/proc/namespaces.c
@@ -30,7 +30,7 @@ static const struct proc_ns_operations *ns_entries[] = {
 	&mntns_operations,
 };
 
-static void *proc_ns_follow_link(struct dentry *dentry, struct nameidata *nd)
+static const char *proc_ns_follow_link(struct dentry *dentry, void **cookie)
 {
 	struct inode *inode = d_inode(dentry);
 	const struct proc_ns_operations *ns_ops = PROC_I(inode)->ns_ops;
@@ -45,7 +45,7 @@ static void *proc_ns_follow_link(struct dentry *dentry, struct nameidata *nd)
 	if (ptrace_may_access(task, PTRACE_MODE_READ)) {
 		error = ns_get_path(&ns_path, task, ns_ops);
 		if (!error)
-			nd_jump_link(nd, &ns_path);
+			nd_jump_link(&ns_path);
 	}
 	put_task_struct(task);
 	return error;
diff --git a/fs/proc/self.c b/fs/proc/self.c
index 6195b4a7c3b1..113b8d061fc0 100644
--- a/fs/proc/self.c
+++ b/fs/proc/self.c
@@ -1,5 +1,4 @@
 #include <linux/sched.h>
-#include <linux/namei.h>
 #include <linux/slab.h>
 #include <linux/pid_namespace.h>
 #include "internal.h"
@@ -19,21 +18,20 @@ static int proc_self_readlink(struct dentry *dentry, char __user *buffer,
 	return readlink_copy(buffer, buflen, tmp);
 }
 
-static void *proc_self_follow_link(struct dentry *dentry, struct nameidata *nd)
+static const char *proc_self_follow_link(struct dentry *dentry, void **cookie)
 {
 	struct pid_namespace *ns = dentry->d_sb->s_fs_info;
 	pid_t tgid = task_tgid_nr_ns(current, ns);
-	char *name = ERR_PTR(-ENOENT);
-	if (tgid) {
-		/* 11 for max length of signed int in decimal + NULL term */
-		name = kmalloc(12, GFP_KERNEL);
-		if (!name)
-			name = ERR_PTR(-ENOMEM);
-		else
-			sprintf(name, "%d", tgid);
-	}
-	nd_set_link(nd, name);
-	return NULL;
+	char *name;
+
+	if (!tgid)
+		return ERR_PTR(-ENOENT);
+	/* 11 for max length of signed int in decimal + NULL term */
+	name = kmalloc(12, GFP_KERNEL);
+	if (!name)
+		return ERR_PTR(-ENOMEM);
+	sprintf(name, "%d", tgid);
+	return *cookie = name;
 }
 
 static const struct inode_operations proc_self_inode_operations = {
diff --git a/fs/proc/thread_self.c b/fs/proc/thread_self.c
index a8371993b4fb..947b0f4fd0a1 100644
--- a/fs/proc/thread_self.c
+++ b/fs/proc/thread_self.c
@@ -1,5 +1,4 @@
 #include <linux/sched.h>
-#include <linux/namei.h>
 #include <linux/slab.h>
 #include <linux/pid_namespace.h>
 #include "internal.h"
@@ -20,21 +19,20 @@ static int proc_thread_self_readlink(struct dentry *dentry, char __user *buffer,
 	return readlink_copy(buffer, buflen, tmp);
 }
 
-static void *proc_thread_self_follow_link(struct dentry *dentry, struct nameidata *nd)
+static const char *proc_thread_self_follow_link(struct dentry *dentry, void **cookie)
 {
 	struct pid_namespace *ns = dentry->d_sb->s_fs_info;
 	pid_t tgid = task_tgid_nr_ns(current, ns);
 	pid_t pid = task_pid_nr_ns(current, ns);
-	char *name = ERR_PTR(-ENOENT);
-	if (pid) {
-		name = kmalloc(PROC_NUMBUF + 6 + PROC_NUMBUF, GFP_KERNEL);
-		if (!name)
-			name = ERR_PTR(-ENOMEM);
-		else
-			sprintf(name, "%d/task/%d", tgid, pid);
-	}
-	nd_set_link(nd, name);
-	return NULL;
+	char *name;
+
+	if (!pid)
+		return ERR_PTR(-ENOENT);
+	name = kmalloc(PROC_NUMBUF + 6 + PROC_NUMBUF, GFP_KERNEL);
+	if (!name)
+		return ERR_PTR(-ENOMEM);
+	sprintf(name, "%d/task/%d", tgid, pid);
+	return *cookie = name;
 }
 
 static const struct inode_operations proc_thread_self_inode_operations = {
diff --git a/fs/select.c b/fs/select.c
index f684c750e08a..015547330e88 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -189,7 +189,7 @@ static int __pollwake(wait_queue_t *wait, unsigned mode, int sync, void *key)
 	 * doesn't imply write barrier and the users expect write
 	 * barrier semantics on wakeup functions.  The following
 	 * smp_wmb() is equivalent to smp_wmb() in try_to_wake_up()
-	 * and is paired with set_mb() in poll_schedule_timeout.
+	 * and is paired with smp_store_mb() in poll_schedule_timeout.
 	 */
 	smp_wmb();
 	pwq->triggered = 1;
@@ -244,7 +244,7 @@ int poll_schedule_timeout(struct poll_wqueues *pwq, int state,
 	/*
 	 * Prepare for the next iteration.
 	 *
-	 * The following set_mb() serves two purposes.  First, it's
+	 * The following smp_store_mb() serves two purposes.  First, it's
 	 * the counterpart rmb of the wmb in pollwake() such that data
 	 * written before wake up is always visible after wake up.
 	 * Second, the full barrier guarantees that triggered clearing
@@ -252,7 +252,7 @@ int poll_schedule_timeout(struct poll_wqueues *pwq, int state,
 	 * this problem doesn't exist for the first iteration as
 	 * add_wait_queue() has full barrier semantics.
 	 */
-	set_mb(pwq->triggered, 0);
+	smp_store_mb(pwq->triggered, 0);
 
 	return rc;
 }
diff --git a/fs/sysv/Makefile b/fs/sysv/Makefile
index 3591f9d7a48a..7a75e70a4b61 100644
--- a/fs/sysv/Makefile
+++ b/fs/sysv/Makefile
@@ -5,4 +5,4 @@
 obj-$(CONFIG_SYSV_FS) += sysv.o
 
 sysv-objs := ialloc.o balloc.o inode.o itree.o file.o dir.o \
-	     namei.o super.o symlink.o
+	     namei.o super.o
diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c
index 88956309cc86..590ad9206e3f 100644
--- a/fs/sysv/inode.c
+++ b/fs/sysv/inode.c
@@ -166,8 +166,9 @@ void sysv_set_inode(struct inode *inode, dev_t rdev)
 			inode->i_op = &sysv_symlink_inode_operations;
 			inode->i_mapping->a_ops = &sysv_aops;
 		} else {
-			inode->i_op = &sysv_fast_symlink_inode_operations;
-			nd_terminate_link(SYSV_I(inode)->i_data, inode->i_size,
+			inode->i_op = &simple_symlink_inode_operations;
+			inode->i_link = (char *)SYSV_I(inode)->i_data;
+			nd_terminate_link(inode->i_link, inode->i_size,
 				sizeof(SYSV_I(inode)->i_data) - 1);
 		}
 	} else
diff --git a/fs/sysv/symlink.c b/fs/sysv/symlink.c
deleted file mode 100644
index d3fa0d703314..000000000000
--- a/fs/sysv/symlink.c
+++ /dev/null
@@ -1,20 +0,0 @@
-/*
- *  linux/fs/sysv/symlink.c
- *
- *  Handling of System V filesystem fast symlinks extensions.
- *  Aug 2001, Christoph Hellwig (hch@infradead.org)
- */
-
-#include "sysv.h"
-#include <linux/namei.h>
-
-static void *sysv_follow_link(struct dentry *dentry, struct nameidata *nd)
-{
-	nd_set_link(nd, (char *)SYSV_I(d_inode(dentry))->i_data);
-	return NULL;
-}
-
-const struct inode_operations sysv_fast_symlink_inode_operations = {
-	.readlink	= generic_readlink,
-	.follow_link	= sysv_follow_link,
-};
diff --git a/fs/sysv/sysv.h b/fs/sysv/sysv.h
index 69d488986cce..2c13525131cd 100644
--- a/fs/sysv/sysv.h
+++ b/fs/sysv/sysv.h
@@ -161,7 +161,6 @@ extern ino_t sysv_inode_by_name(struct dentry *);
 
 extern const struct inode_operations sysv_file_inode_operations;
 extern const struct inode_operations sysv_dir_inode_operations;
-extern const struct inode_operations sysv_fast_symlink_inode_operations;
 extern const struct file_operations sysv_file_operations;
 extern const struct file_operations sysv_dir_operations;
 extern const struct address_space_operations sysv_aops;
diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c
index 27060fc855d4..5c27c66c224a 100644
--- a/fs/ubifs/dir.c
+++ b/fs/ubifs/dir.c
@@ -889,6 +889,7 @@ static int ubifs_symlink(struct inode *dir, struct dentry *dentry,
 
 	memcpy(ui->data, symname, len);
 	((char *)ui->data)[len] = '\0';
+	inode->i_link = ui->data;
 	/*
 	 * The terminating zero byte is not written to the flash media and it
 	 * is put just to make later in-memory string processing simpler. Thus,
diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index 35efc103c39c..a3dfe2ae79f2 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -51,7 +51,6 @@
 
 #include "ubifs.h"
 #include <linux/mount.h>
-#include <linux/namei.h>
 #include <linux/slab.h>
 
 static int read_block(struct inode *inode, void *addr, unsigned int block,
@@ -1300,14 +1299,6 @@ static void ubifs_invalidatepage(struct page *page, unsigned int offset,
 	ClearPageChecked(page);
 }
 
-static void *ubifs_follow_link(struct dentry *dentry, struct nameidata *nd)
-{
-	struct ubifs_inode *ui = ubifs_inode(d_inode(dentry));
-
-	nd_set_link(nd, ui->data);
-	return NULL;
-}
-
 int ubifs_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 {
 	struct inode *inode = file->f_mapping->host;
@@ -1570,7 +1561,7 @@ const struct inode_operations ubifs_file_inode_operations = {
 
 const struct inode_operations ubifs_symlink_inode_operations = {
 	.readlink    = generic_readlink,
-	.follow_link = ubifs_follow_link,
+	.follow_link = simple_follow_link,
 	.setattr     = ubifs_setattr,
 	.getattr     = ubifs_getattr,
 	.setxattr    = ubifs_setxattr,
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index 75e6f04bb795..20f5dbd7c6a8 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -195,6 +195,7 @@ struct inode *ubifs_iget(struct super_block *sb, unsigned long inum)
 		}
 		memcpy(ui->data, ino->data, ui->data_len);
 		((char *)ui->data)[ui->data_len] = '\0';
+		inode->i_link = ui->data;
 		break;
 	case S_IFBLK:
 	case S_IFCHR:
diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c
index be7d42c7d938..99aaf5c9bf4d 100644
--- a/fs/ufs/inode.c
+++ b/fs/ufs/inode.c
@@ -572,9 +572,10 @@ static void ufs_set_inode_ops(struct inode *inode)
 		inode->i_fop = &ufs_dir_operations;
 		inode->i_mapping->a_ops = &ufs_aops;
 	} else if (S_ISLNK(inode->i_mode)) {
-		if (!inode->i_blocks)
+		if (!inode->i_blocks) {
 			inode->i_op = &ufs_fast_symlink_inode_operations;
-		else {
+			inode->i_link = (char *)UFS_I(inode)->i_u1.i_symlink;
+		} else {
 			inode->i_op = &ufs_symlink_inode_operations;
 			inode->i_mapping->a_ops = &ufs_aops;
 		}
diff --git a/fs/ufs/namei.c b/fs/ufs/namei.c
index e491a93a7e9a..f773deb1d2e3 100644
--- a/fs/ufs/namei.c
+++ b/fs/ufs/namei.c
@@ -144,7 +144,8 @@ static int ufs_symlink (struct inode * dir, struct dentry * dentry,
 	} else {
 		/* fast symlink */
 		inode->i_op = &ufs_fast_symlink_inode_operations;
-		memcpy(UFS_I(inode)->i_u1.i_symlink, symname, l);
+		inode->i_link = (char *)UFS_I(inode)->i_u1.i_symlink;
+		memcpy(inode->i_link, symname, l);
 		inode->i_size = l-1;
 	}
 	mark_inode_dirty(inode);
diff --git a/fs/ufs/symlink.c b/fs/ufs/symlink.c
index 5b537e2fdda3..874480bb43e9 100644
--- a/fs/ufs/symlink.c
+++ b/fs/ufs/symlink.c
@@ -25,23 +25,12 @@
  *  ext2 symlink handling code
  */
 
-#include <linux/fs.h>
-#include <linux/namei.h>
-
 #include "ufs_fs.h"
 #include "ufs.h"
 
-
-static void *ufs_follow_link(struct dentry *dentry, struct nameidata *nd)
-{
-	struct ufs_inode_info *p = UFS_I(d_inode(dentry));
-	nd_set_link(nd, (char*)p->i_u1.i_symlink);
-	return NULL;
-}
-
 const struct inode_operations ufs_fast_symlink_inode_operations = {
 	.readlink	= generic_readlink,
-	.follow_link	= ufs_follow_link,
+	.follow_link	= simple_follow_link,
 	.setattr	= ufs_setattr,
 };
 
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index f4cd7204e236..7f51f39f8acc 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -41,7 +41,6 @@
 
 #include <linux/capability.h>
 #include <linux/xattr.h>
-#include <linux/namei.h>
 #include <linux/posix_acl.h>
 #include <linux/security.h>
 #include <linux/fiemap.h>
@@ -414,10 +413,10 @@ xfs_vn_rename(
  * we need to be very careful about how much stack we use.
  * uio is kmalloced for this reason...
  */
-STATIC void *
+STATIC const char *
 xfs_vn_follow_link(
 	struct dentry		*dentry,
-	struct nameidata	*nd)
+	void			**cookie)
 {
 	char			*link;
 	int			error = -ENOMEM;
@@ -430,14 +429,12 @@ xfs_vn_follow_link(
 	if (unlikely(error))
 		goto out_kfree;
 
-	nd_set_link(nd, link);
-	return NULL;
+	return *cookie = link;
 
  out_kfree:
 	kfree(link);
  out_err:
-	nd_set_link(nd, ERR_PTR(error));
-	return NULL;
+	return ERR_PTR(error);
 }
 
 STATIC int
diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h
index f5c40b0fadc2..e6a83d712ef6 100644
--- a/include/asm-generic/barrier.h
+++ b/include/asm-generic/barrier.h
@@ -66,8 +66,8 @@
 #define smp_read_barrier_depends()	do { } while (0)
 #endif
 
-#ifndef set_mb
-#define set_mb(var, value)  do { (var) = (value); mb(); } while (0)
+#ifndef smp_store_mb
+#define smp_store_mb(var, value)  do { WRITE_ONCE(var, value); mb(); } while (0)
 #endif
 
 #ifndef smp_mb__before_atomic
diff --git a/include/asm-generic/cmpxchg.h b/include/asm-generic/cmpxchg.h
index 811fb1e9b061..3766ab34aa45 100644
--- a/include/asm-generic/cmpxchg.h
+++ b/include/asm-generic/cmpxchg.h
@@ -86,9 +86,6 @@ unsigned long __xchg(unsigned long x, volatile void *ptr, int size)
 
 /*
  * Atomic compare and exchange.
- *
- * Do not define __HAVE_ARCH_CMPXCHG because we want to use it to check whether
- * a cmpxchg primitive faster than repeated local irq save/restore exists.
  */
 #include <asm-generic/cmpxchg-local.h>
 
diff --git a/include/asm-generic/futex.h b/include/asm-generic/futex.h
index b59b5a52637e..e56272c919b5 100644
--- a/include/asm-generic/futex.h
+++ b/include/asm-generic/futex.h
@@ -8,8 +8,7 @@
 #ifndef CONFIG_SMP
 /*
  * The following implementation only for uniprocessor machines.
- * For UP, it's relies on the fact that pagefault_disable() also disables
- * preemption to ensure mutual exclusion.
+ * It relies on preempt_disable() ensuring mutual exclusion.
  *
  */
 
@@ -38,6 +37,7 @@ futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
 		oparg = 1 << oparg;
 
+	preempt_disable();
 	pagefault_disable();
 
 	ret = -EFAULT;
@@ -72,6 +72,7 @@ futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 
 out_pagefault_enable:
 	pagefault_enable();
+	preempt_enable();
 
 	if (ret == 0) {
 		switch (cmp) {
@@ -106,6 +107,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 {
 	u32 val;
 
+	preempt_disable();
 	if (unlikely(get_user(val, uaddr) != 0))
 		return -EFAULT;
 
@@ -113,6 +115,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 		return -EFAULT;
 
 	*uval = val;
+	preempt_enable();
 
 	return 0;
 }
diff --git a/include/asm-generic/gpio.h b/include/asm-generic/gpio.h
index 9bb0d11729c9..40ec1433f05d 100644
--- a/include/asm-generic/gpio.h
+++ b/include/asm-generic/gpio.h
@@ -128,11 +128,6 @@ static inline int gpio_export_link(struct device *dev, const char *name,
 	return gpiod_export_link(dev, name, gpio_to_desc(gpio));
 }
 
-static inline int gpio_sysfs_set_active_low(unsigned gpio, int value)
-{
-	return gpiod_sysfs_set_active_low(gpio_to_desc(gpio), value);
-}
-
 static inline void gpio_unexport(unsigned gpio)
 {
 	gpiod_unexport(gpio_to_desc(gpio));
diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h
index 9db042304df3..f56094cfdeff 100644
--- a/include/asm-generic/io.h
+++ b/include/asm-generic/io.h
@@ -769,6 +769,14 @@ static inline void __iomem *ioremap_nocache(phys_addr_t offset, size_t size)
 }
 #endif
 
+#ifndef ioremap_uc
+#define ioremap_uc ioremap_uc
+static inline void __iomem *ioremap_uc(phys_addr_t offset, size_t size)
+{
+	return ioremap_nocache(offset, size);
+}
+#endif
+
 #ifndef ioremap_wc
 #define ioremap_wc ioremap_wc
 static inline void __iomem *ioremap_wc(phys_addr_t offset, size_t size)
@@ -777,8 +785,17 @@ static inline void __iomem *ioremap_wc(phys_addr_t offset, size_t size)
 }
 #endif
 
+#ifndef ioremap_wt
+#define ioremap_wt ioremap_wt
+static inline void __iomem *ioremap_wt(phys_addr_t offset, size_t size)
+{
+	return ioremap_nocache(offset, size);
+}
+#endif
+
 #ifndef iounmap
 #define iounmap iounmap
+
 static inline void iounmap(void __iomem *addr)
 {
 }
diff --git a/include/asm-generic/iomap.h b/include/asm-generic/iomap.h
index 1b41011643a5..d8f8622fa044 100644
--- a/include/asm-generic/iomap.h
+++ b/include/asm-generic/iomap.h
@@ -66,6 +66,10 @@ extern void ioport_unmap(void __iomem *);
 #define ioremap_wc ioremap_nocache
 #endif
 
+#ifndef ARCH_HAS_IOREMAP_WT
+#define ioremap_wt ioremap_nocache
+#endif
+
 #ifdef CONFIG_PCI
 /* Destroy a virtual mapping cookie for a PCI BAR (memory or IO) */
 struct pci_dev;
diff --git a/include/asm-generic/pci.h b/include/asm-generic/pci.h
index e80a0495e5b0..f24bc519bf31 100644
--- a/include/asm-generic/pci.h
+++ b/include/asm-generic/pci.h
@@ -6,19 +6,6 @@
 #ifndef _ASM_GENERIC_PCI_H
 #define _ASM_GENERIC_PCI_H
 
-static inline struct resource *
-pcibios_select_root(struct pci_dev *pdev, struct resource *res)
-{
-	struct resource *root = NULL;
-
-	if (res->flags & IORESOURCE_IO)
-		root = &ioport_resource;
-	if (res->flags & IORESOURCE_MEM)
-		root = &iomem_resource;
-
-	return root;
-}
-
 #ifndef HAVE_ARCH_PCI_GET_LEGACY_IDE_IRQ
 static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
 {
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 39f1d6a2b04d..bd910ceaccfa 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -262,6 +262,10 @@ static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b)
 #define pgprot_writecombine pgprot_noncached
 #endif
 
+#ifndef pgprot_writethrough
+#define pgprot_writethrough pgprot_noncached
+#endif
+
 #ifndef pgprot_device
 #define pgprot_device pgprot_noncached
 #endif
diff --git a/include/asm-generic/preempt.h b/include/asm-generic/preempt.h
index eb6f9e6c3075..d0a7a4753db2 100644
--- a/include/asm-generic/preempt.h
+++ b/include/asm-generic/preempt.h
@@ -79,11 +79,8 @@ static __always_inline bool should_resched(void)
 #ifdef CONFIG_PREEMPT
 extern asmlinkage void preempt_schedule(void);
 #define __preempt_schedule() preempt_schedule()
-
-#ifdef CONFIG_CONTEXT_TRACKING
-extern asmlinkage void preempt_schedule_context(void);
-#define __preempt_schedule_context() preempt_schedule_context()
-#endif
+extern asmlinkage void preempt_schedule_notrace(void);
+#define __preempt_schedule_notrace() preempt_schedule_notrace()
 #endif /* CONFIG_PREEMPT */
 
 #endif /* __ASM_PREEMPT_H */
diff --git a/include/asm-generic/qspinlock.h b/include/asm-generic/qspinlock.h
new file mode 100644
index 000000000000..83bfb87f5bf1
--- /dev/null
+++ b/include/asm-generic/qspinlock.h
@@ -0,0 +1,139 @@
+/*
+ * Queued spinlock
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * (C) Copyright 2013-2015 Hewlett-Packard Development Company, L.P.
+ *
+ * Authors: Waiman Long <waiman.long@hp.com>
+ */
+#ifndef __ASM_GENERIC_QSPINLOCK_H
+#define __ASM_GENERIC_QSPINLOCK_H
+
+#include <asm-generic/qspinlock_types.h>
+
+/**
+ * queued_spin_is_locked - is the spinlock locked?
+ * @lock: Pointer to queued spinlock structure
+ * Return: 1 if it is locked, 0 otherwise
+ */
+static __always_inline int queued_spin_is_locked(struct qspinlock *lock)
+{
+	return atomic_read(&lock->val);
+}
+
+/**
+ * queued_spin_value_unlocked - is the spinlock structure unlocked?
+ * @lock: queued spinlock structure
+ * Return: 1 if it is unlocked, 0 otherwise
+ *
+ * N.B. Whenever there are tasks waiting for the lock, it is considered
+ *      locked wrt the lockref code to avoid lock stealing by the lockref
+ *      code and change things underneath the lock. This also allows some
+ *      optimizations to be applied without conflict with lockref.
+ */
+static __always_inline int queued_spin_value_unlocked(struct qspinlock lock)
+{
+	return !atomic_read(&lock.val);
+}
+
+/**
+ * queued_spin_is_contended - check if the lock is contended
+ * @lock : Pointer to queued spinlock structure
+ * Return: 1 if lock contended, 0 otherwise
+ */
+static __always_inline int queued_spin_is_contended(struct qspinlock *lock)
+{
+	return atomic_read(&lock->val) & ~_Q_LOCKED_MASK;
+}
+/**
+ * queued_spin_trylock - try to acquire the queued spinlock
+ * @lock : Pointer to queued spinlock structure
+ * Return: 1 if lock acquired, 0 if failed
+ */
+static __always_inline int queued_spin_trylock(struct qspinlock *lock)
+{
+	if (!atomic_read(&lock->val) &&
+	   (atomic_cmpxchg(&lock->val, 0, _Q_LOCKED_VAL) == 0))
+		return 1;
+	return 0;
+}
+
+extern void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
+
+/**
+ * queued_spin_lock - acquire a queued spinlock
+ * @lock: Pointer to queued spinlock structure
+ */
+static __always_inline void queued_spin_lock(struct qspinlock *lock)
+{
+	u32 val;
+
+	val = atomic_cmpxchg(&lock->val, 0, _Q_LOCKED_VAL);
+	if (likely(val == 0))
+		return;
+	queued_spin_lock_slowpath(lock, val);
+}
+
+#ifndef queued_spin_unlock
+/**
+ * queued_spin_unlock - release a queued spinlock
+ * @lock : Pointer to queued spinlock structure
+ */
+static __always_inline void queued_spin_unlock(struct qspinlock *lock)
+{
+	/*
+	 * smp_mb__before_atomic() in order to guarantee release semantics
+	 */
+	smp_mb__before_atomic_dec();
+	atomic_sub(_Q_LOCKED_VAL, &lock->val);
+}
+#endif
+
+/**
+ * queued_spin_unlock_wait - wait until current lock holder releases the lock
+ * @lock : Pointer to queued spinlock structure
+ *
+ * There is a very slight possibility of live-lock if the lockers keep coming
+ * and the waiter is just unfortunate enough to not see any unlock state.
+ */
+static inline void queued_spin_unlock_wait(struct qspinlock *lock)
+{
+	while (atomic_read(&lock->val) & _Q_LOCKED_MASK)
+		cpu_relax();
+}
+
+#ifndef virt_queued_spin_lock
+static __always_inline bool virt_queued_spin_lock(struct qspinlock *lock)
+{
+	return false;
+}
+#endif
+
+/*
+ * Initializier
+ */
+#define	__ARCH_SPIN_LOCK_UNLOCKED	{ ATOMIC_INIT(0) }
+
+/*
+ * Remapping spinlock architecture specific functions to the corresponding
+ * queued spinlock functions.
+ */
+#define arch_spin_is_locked(l)		queued_spin_is_locked(l)
+#define arch_spin_is_contended(l)	queued_spin_is_contended(l)
+#define arch_spin_value_unlocked(l)	queued_spin_value_unlocked(l)
+#define arch_spin_lock(l)		queued_spin_lock(l)
+#define arch_spin_trylock(l)		queued_spin_trylock(l)
+#define arch_spin_unlock(l)		queued_spin_unlock(l)
+#define arch_spin_lock_flags(l, f)	queued_spin_lock(l)
+#define arch_spin_unlock_wait(l)	queued_spin_unlock_wait(l)
+
+#endif /* __ASM_GENERIC_QSPINLOCK_H */
diff --git a/include/asm-generic/qspinlock_types.h b/include/asm-generic/qspinlock_types.h
new file mode 100644
index 000000000000..85f888e86761
--- /dev/null
+++ b/include/asm-generic/qspinlock_types.h
@@ -0,0 +1,79 @@
+/*
+ * Queued spinlock
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * (C) Copyright 2013-2015 Hewlett-Packard Development Company, L.P.
+ *
+ * Authors: Waiman Long <waiman.long@hp.com>
+ */
+#ifndef __ASM_GENERIC_QSPINLOCK_TYPES_H
+#define __ASM_GENERIC_QSPINLOCK_TYPES_H
+
+/*
+ * Including atomic.h with PARAVIRT on will cause compilation errors because
+ * of recursive header file incluson via paravirt_types.h. So don't include
+ * it if PARAVIRT is on.
+ */
+#ifndef CONFIG_PARAVIRT
+#include <linux/types.h>
+#include <linux/atomic.h>
+#endif
+
+typedef struct qspinlock {
+	atomic_t	val;
+} arch_spinlock_t;
+
+/*
+ * Bitfields in the atomic value:
+ *
+ * When NR_CPUS < 16K
+ *  0- 7: locked byte
+ *     8: pending
+ *  9-15: not used
+ * 16-17: tail index
+ * 18-31: tail cpu (+1)
+ *
+ * When NR_CPUS >= 16K
+ *  0- 7: locked byte
+ *     8: pending
+ *  9-10: tail index
+ * 11-31: tail cpu (+1)
+ */
+#define	_Q_SET_MASK(type)	(((1U << _Q_ ## type ## _BITS) - 1)\
+				      << _Q_ ## type ## _OFFSET)
+#define _Q_LOCKED_OFFSET	0
+#define _Q_LOCKED_BITS		8
+#define _Q_LOCKED_MASK		_Q_SET_MASK(LOCKED)
+
+#define _Q_PENDING_OFFSET	(_Q_LOCKED_OFFSET + _Q_LOCKED_BITS)
+#if CONFIG_NR_CPUS < (1U << 14)
+#define _Q_PENDING_BITS		8
+#else
+#define _Q_PENDING_BITS		1
+#endif
+#define _Q_PENDING_MASK		_Q_SET_MASK(PENDING)
+
+#define _Q_TAIL_IDX_OFFSET	(_Q_PENDING_OFFSET + _Q_PENDING_BITS)
+#define _Q_TAIL_IDX_BITS	2
+#define _Q_TAIL_IDX_MASK	_Q_SET_MASK(TAIL_IDX)
+
+#define _Q_TAIL_CPU_OFFSET	(_Q_TAIL_IDX_OFFSET + _Q_TAIL_IDX_BITS)
+#define _Q_TAIL_CPU_BITS	(32 - _Q_TAIL_CPU_OFFSET)
+#define _Q_TAIL_CPU_MASK	_Q_SET_MASK(TAIL_CPU)
+
+#define _Q_TAIL_OFFSET		_Q_TAIL_IDX_OFFSET
+#define _Q_TAIL_MASK		(_Q_TAIL_IDX_MASK | _Q_TAIL_CPU_MASK)
+
+#define _Q_LOCKED_VAL		(1U << _Q_LOCKED_OFFSET)
+#define _Q_PENDING_VAL		(1U << _Q_PENDING_OFFSET)
+
+#endif /* __ASM_GENERIC_QSPINLOCK_TYPES_H */
diff --git a/include/crypto/aead.h b/include/crypto/aead.h
index 94b19be67574..7169ad04acc0 100644
--- a/include/crypto/aead.h
+++ b/include/crypto/aead.h
@@ -18,6 +18,65 @@
 #include <linux/slab.h>
 
 /**
+ * DOC: Authenticated Encryption With Associated Data (AEAD) Cipher API
+ *
+ * The AEAD cipher API is used with the ciphers of type CRYPTO_ALG_TYPE_AEAD
+ * (listed as type "aead" in /proc/crypto)
+ *
+ * The most prominent examples for this type of encryption is GCM and CCM.
+ * However, the kernel supports other types of AEAD ciphers which are defined
+ * with the following cipher string:
+ *
+ *	authenc(keyed message digest, block cipher)
+ *
+ * For example: authenc(hmac(sha256), cbc(aes))
+ *
+ * The example code provided for the asynchronous block cipher operation
+ * applies here as well. Naturally all *ablkcipher* symbols must be exchanged
+ * the *aead* pendants discussed in the following. In addition, for the AEAD
+ * operation, the aead_request_set_assoc function must be used to set the
+ * pointer to the associated data memory location before performing the
+ * encryption or decryption operation. In case of an encryption, the associated
+ * data memory is filled during the encryption operation. For decryption, the
+ * associated data memory must contain data that is used to verify the integrity
+ * of the decrypted data. Another deviation from the asynchronous block cipher
+ * operation is that the caller should explicitly check for -EBADMSG of the
+ * crypto_aead_decrypt. That error indicates an authentication error, i.e.
+ * a breach in the integrity of the message. In essence, that -EBADMSG error
+ * code is the key bonus an AEAD cipher has over "standard" block chaining
+ * modes.
+ */
+
+/**
+ *	struct aead_request - AEAD request
+ *	@base: Common attributes for async crypto requests
+ *	@old: Boolean whether the old or new AEAD API is used
+ *	@assoclen: Length in bytes of associated data for authentication
+ *	@cryptlen: Length of data to be encrypted or decrypted
+ *	@iv: Initialisation vector
+ *	@assoc: Associated data
+ *	@src: Source data
+ *	@dst: Destination data
+ *	@__ctx: Start of private context data
+ */
+struct aead_request {
+	struct crypto_async_request base;
+
+	bool old;
+
+	unsigned int assoclen;
+	unsigned int cryptlen;
+
+	u8 *iv;
+
+	struct scatterlist *assoc;
+	struct scatterlist *src;
+	struct scatterlist *dst;
+
+	void *__ctx[] CRYPTO_MINALIGN_ATTR;
+};
+
+/**
  *	struct aead_givcrypt_request - AEAD request with IV generation
  *	@seq: Sequence number for IV generation
  *	@giv: Space for generated IV
@@ -30,6 +89,474 @@ struct aead_givcrypt_request {
 	struct aead_request areq;
 };
 
+/**
+ * struct aead_alg - AEAD cipher definition
+ * @maxauthsize: Set the maximum authentication tag size supported by the
+ *		 transformation. A transformation may support smaller tag sizes.
+ *		 As the authentication tag is a message digest to ensure the
+ *		 integrity of the encrypted data, a consumer typically wants the
+ *		 largest authentication tag possible as defined by this
+ *		 variable.
+ * @setauthsize: Set authentication size for the AEAD transformation. This
+ *		 function is used to specify the consumer requested size of the
+ * 		 authentication tag to be either generated by the transformation
+ *		 during encryption or the size of the authentication tag to be
+ *		 supplied during the decryption operation. This function is also
+ *		 responsible for checking the authentication tag size for
+ *		 validity.
+ * @setkey: see struct ablkcipher_alg
+ * @encrypt: see struct ablkcipher_alg
+ * @decrypt: see struct ablkcipher_alg
+ * @geniv: see struct ablkcipher_alg
+ * @ivsize: see struct ablkcipher_alg
+ * @init: Initialize the cryptographic transformation object. This function
+ *	  is used to initialize the cryptographic transformation object.
+ *	  This function is called only once at the instantiation time, right
+ *	  after the transformation context was allocated. In case the
+ *	  cryptographic hardware has some special requirements which need to
+ *	  be handled by software, this function shall check for the precise
+ *	  requirement of the transformation and put any software fallbacks
+ *	  in place.
+ * @exit: Deinitialize the cryptographic transformation object. This is a
+ *	  counterpart to @init, used to remove various changes set in
+ *	  @init.
+ *
+ * All fields except @ivsize is mandatory and must be filled.
+ */
+struct aead_alg {
+	int (*setkey)(struct crypto_aead *tfm, const u8 *key,
+	              unsigned int keylen);
+	int (*setauthsize)(struct crypto_aead *tfm, unsigned int authsize);
+	int (*encrypt)(struct aead_request *req);
+	int (*decrypt)(struct aead_request *req);
+	int (*init)(struct crypto_aead *tfm);
+	void (*exit)(struct crypto_aead *tfm);
+
+	const char *geniv;
+
+	unsigned int ivsize;
+	unsigned int maxauthsize;
+
+	struct crypto_alg base;
+};
+
+struct crypto_aead {
+	int (*setkey)(struct crypto_aead *tfm, const u8 *key,
+	              unsigned int keylen);
+	int (*setauthsize)(struct crypto_aead *tfm, unsigned int authsize);
+	int (*encrypt)(struct aead_request *req);
+	int (*decrypt)(struct aead_request *req);
+	int (*givencrypt)(struct aead_givcrypt_request *req);
+	int (*givdecrypt)(struct aead_givcrypt_request *req);
+
+	struct crypto_aead *child;
+
+	unsigned int authsize;
+	unsigned int reqsize;
+
+	struct crypto_tfm base;
+};
+
+static inline struct crypto_aead *__crypto_aead_cast(struct crypto_tfm *tfm)
+{
+	return container_of(tfm, struct crypto_aead, base);
+}
+
+/**
+ * crypto_alloc_aead() - allocate AEAD cipher handle
+ * @alg_name: is the cra_name / name or cra_driver_name / driver name of the
+ *	     AEAD cipher
+ * @type: specifies the type of the cipher
+ * @mask: specifies the mask for the cipher
+ *
+ * Allocate a cipher handle for an AEAD. The returned struct
+ * crypto_aead is the cipher handle that is required for any subsequent
+ * API invocation for that AEAD.
+ *
+ * Return: allocated cipher handle in case of success; IS_ERR() is true in case
+ *	   of an error, PTR_ERR() returns the error code.
+ */
+struct crypto_aead *crypto_alloc_aead(const char *alg_name, u32 type, u32 mask);
+
+static inline struct crypto_tfm *crypto_aead_tfm(struct crypto_aead *tfm)
+{
+	return &tfm->base;
+}
+
+/**
+ * crypto_free_aead() - zeroize and free aead handle
+ * @tfm: cipher handle to be freed
+ */
+static inline void crypto_free_aead(struct crypto_aead *tfm)
+{
+	crypto_destroy_tfm(tfm, crypto_aead_tfm(tfm));
+}
+
+static inline struct crypto_aead *crypto_aead_crt(struct crypto_aead *tfm)
+{
+	return tfm;
+}
+
+static inline struct old_aead_alg *crypto_old_aead_alg(struct crypto_aead *tfm)
+{
+	return &crypto_aead_tfm(tfm)->__crt_alg->cra_aead;
+}
+
+static inline struct aead_alg *crypto_aead_alg(struct crypto_aead *tfm)
+{
+	return container_of(crypto_aead_tfm(tfm)->__crt_alg,
+			    struct aead_alg, base);
+}
+
+static inline unsigned int crypto_aead_alg_ivsize(struct aead_alg *alg)
+{
+	return alg->base.cra_aead.encrypt ? alg->base.cra_aead.ivsize :
+					    alg->ivsize;
+}
+
+/**
+ * crypto_aead_ivsize() - obtain IV size
+ * @tfm: cipher handle
+ *
+ * The size of the IV for the aead referenced by the cipher handle is
+ * returned. This IV size may be zero if the cipher does not need an IV.
+ *
+ * Return: IV size in bytes
+ */
+static inline unsigned int crypto_aead_ivsize(struct crypto_aead *tfm)
+{
+	return crypto_aead_alg_ivsize(crypto_aead_alg(tfm));
+}
+
+/**
+ * crypto_aead_authsize() - obtain maximum authentication data size
+ * @tfm: cipher handle
+ *
+ * The maximum size of the authentication data for the AEAD cipher referenced
+ * by the AEAD cipher handle is returned. The authentication data size may be
+ * zero if the cipher implements a hard-coded maximum.
+ *
+ * The authentication data may also be known as "tag value".
+ *
+ * Return: authentication data size / tag size in bytes
+ */
+static inline unsigned int crypto_aead_authsize(struct crypto_aead *tfm)
+{
+	return tfm->authsize;
+}
+
+/**
+ * crypto_aead_blocksize() - obtain block size of cipher
+ * @tfm: cipher handle
+ *
+ * The block size for the AEAD referenced with the cipher handle is returned.
+ * The caller may use that information to allocate appropriate memory for the
+ * data returned by the encryption or decryption operation
+ *
+ * Return: block size of cipher
+ */
+static inline unsigned int crypto_aead_blocksize(struct crypto_aead *tfm)
+{
+	return crypto_tfm_alg_blocksize(crypto_aead_tfm(tfm));
+}
+
+static inline unsigned int crypto_aead_alignmask(struct crypto_aead *tfm)
+{
+	return crypto_tfm_alg_alignmask(crypto_aead_tfm(tfm));
+}
+
+static inline u32 crypto_aead_get_flags(struct crypto_aead *tfm)
+{
+	return crypto_tfm_get_flags(crypto_aead_tfm(tfm));
+}
+
+static inline void crypto_aead_set_flags(struct crypto_aead *tfm, u32 flags)
+{
+	crypto_tfm_set_flags(crypto_aead_tfm(tfm), flags);
+}
+
+static inline void crypto_aead_clear_flags(struct crypto_aead *tfm, u32 flags)
+{
+	crypto_tfm_clear_flags(crypto_aead_tfm(tfm), flags);
+}
+
+/**
+ * crypto_aead_setkey() - set key for cipher
+ * @tfm: cipher handle
+ * @key: buffer holding the key
+ * @keylen: length of the key in bytes
+ *
+ * The caller provided key is set for the AEAD referenced by the cipher
+ * handle.
+ *
+ * Note, the key length determines the cipher type. Many block ciphers implement
+ * different cipher modes depending on the key size, such as AES-128 vs AES-192
+ * vs. AES-256. When providing a 16 byte key for an AES cipher handle, AES-128
+ * is performed.
+ *
+ * Return: 0 if the setting of the key was successful; < 0 if an error occurred
+ */
+int crypto_aead_setkey(struct crypto_aead *tfm,
+		       const u8 *key, unsigned int keylen);
+
+/**
+ * crypto_aead_setauthsize() - set authentication data size
+ * @tfm: cipher handle
+ * @authsize: size of the authentication data / tag in bytes
+ *
+ * Set the authentication data size / tag size. AEAD requires an authentication
+ * tag (or MAC) in addition to the associated data.
+ *
+ * Return: 0 if the setting of the key was successful; < 0 if an error occurred
+ */
+int crypto_aead_setauthsize(struct crypto_aead *tfm, unsigned int authsize);
+
+static inline struct crypto_aead *crypto_aead_reqtfm(struct aead_request *req)
+{
+	return __crypto_aead_cast(req->base.tfm);
+}
+
+/**
+ * crypto_aead_encrypt() - encrypt plaintext
+ * @req: reference to the aead_request handle that holds all information
+ *	 needed to perform the cipher operation
+ *
+ * Encrypt plaintext data using the aead_request handle. That data structure
+ * and how it is filled with data is discussed with the aead_request_*
+ * functions.
+ *
+ * IMPORTANT NOTE The encryption operation creates the authentication data /
+ *		  tag. That data is concatenated with the created ciphertext.
+ *		  The ciphertext memory size is therefore the given number of
+ *		  block cipher blocks + the size defined by the
+ *		  crypto_aead_setauthsize invocation. The caller must ensure
+ *		  that sufficient memory is available for the ciphertext and
+ *		  the authentication tag.
+ *
+ * Return: 0 if the cipher operation was successful; < 0 if an error occurred
+ */
+static inline int crypto_aead_encrypt(struct aead_request *req)
+{
+	return crypto_aead_reqtfm(req)->encrypt(req);
+}
+
+/**
+ * crypto_aead_decrypt() - decrypt ciphertext
+ * @req: reference to the ablkcipher_request handle that holds all information
+ *	 needed to perform the cipher operation
+ *
+ * Decrypt ciphertext data using the aead_request handle. That data structure
+ * and how it is filled with data is discussed with the aead_request_*
+ * functions.
+ *
+ * IMPORTANT NOTE The caller must concatenate the ciphertext followed by the
+ *		  authentication data / tag. That authentication data / tag
+ *		  must have the size defined by the crypto_aead_setauthsize
+ *		  invocation.
+ *
+ *
+ * Return: 0 if the cipher operation was successful; -EBADMSG: The AEAD
+ *	   cipher operation performs the authentication of the data during the
+ *	   decryption operation. Therefore, the function returns this error if
+ *	   the authentication of the ciphertext was unsuccessful (i.e. the
+ *	   integrity of the ciphertext or the associated data was violated);
+ *	   < 0 if an error occurred.
+ */
+static inline int crypto_aead_decrypt(struct aead_request *req)
+{
+	if (req->cryptlen < crypto_aead_authsize(crypto_aead_reqtfm(req)))
+		return -EINVAL;
+
+	return crypto_aead_reqtfm(req)->decrypt(req);
+}
+
+/**
+ * DOC: Asynchronous AEAD Request Handle
+ *
+ * The aead_request data structure contains all pointers to data required for
+ * the AEAD cipher operation. This includes the cipher handle (which can be
+ * used by multiple aead_request instances), pointer to plaintext and
+ * ciphertext, asynchronous callback function, etc. It acts as a handle to the
+ * aead_request_* API calls in a similar way as AEAD handle to the
+ * crypto_aead_* API calls.
+ */
+
+/**
+ * crypto_aead_reqsize() - obtain size of the request data structure
+ * @tfm: cipher handle
+ *
+ * Return: number of bytes
+ */
+unsigned int crypto_aead_reqsize(struct crypto_aead *tfm);
+
+/**
+ * aead_request_set_tfm() - update cipher handle reference in request
+ * @req: request handle to be modified
+ * @tfm: cipher handle that shall be added to the request handle
+ *
+ * Allow the caller to replace the existing aead handle in the request
+ * data structure with a different one.
+ */
+static inline void aead_request_set_tfm(struct aead_request *req,
+					struct crypto_aead *tfm)
+{
+	req->base.tfm = crypto_aead_tfm(tfm->child);
+}
+
+/**
+ * aead_request_alloc() - allocate request data structure
+ * @tfm: cipher handle to be registered with the request
+ * @gfp: memory allocation flag that is handed to kmalloc by the API call.
+ *
+ * Allocate the request data structure that must be used with the AEAD
+ * encrypt and decrypt API calls. During the allocation, the provided aead
+ * handle is registered in the request data structure.
+ *
+ * Return: allocated request handle in case of success; IS_ERR() is true in case
+ *	   of an error, PTR_ERR() returns the error code.
+ */
+static inline struct aead_request *aead_request_alloc(struct crypto_aead *tfm,
+						      gfp_t gfp)
+{
+	struct aead_request *req;
+
+	req = kmalloc(sizeof(*req) + crypto_aead_reqsize(tfm), gfp);
+
+	if (likely(req))
+		aead_request_set_tfm(req, tfm);
+
+	return req;
+}
+
+/**
+ * aead_request_free() - zeroize and free request data structure
+ * @req: request data structure cipher handle to be freed
+ */
+static inline void aead_request_free(struct aead_request *req)
+{
+	kzfree(req);
+}
+
+/**
+ * aead_request_set_callback() - set asynchronous callback function
+ * @req: request handle
+ * @flags: specify zero or an ORing of the flags
+ *	   CRYPTO_TFM_REQ_MAY_BACKLOG the request queue may back log and
+ *	   increase the wait queue beyond the initial maximum size;
+ *	   CRYPTO_TFM_REQ_MAY_SLEEP the request processing may sleep
+ * @compl: callback function pointer to be registered with the request handle
+ * @data: The data pointer refers to memory that is not used by the kernel
+ *	  crypto API, but provided to the callback function for it to use. Here,
+ *	  the caller can provide a reference to memory the callback function can
+ *	  operate on. As the callback function is invoked asynchronously to the
+ *	  related functionality, it may need to access data structures of the
+ *	  related functionality which can be referenced using this pointer. The
+ *	  callback function can access the memory via the "data" field in the
+ *	  crypto_async_request data structure provided to the callback function.
+ *
+ * Setting the callback function that is triggered once the cipher operation
+ * completes
+ *
+ * The callback function is registered with the aead_request handle and
+ * must comply with the following template
+ *
+ *	void callback_function(struct crypto_async_request *req, int error)
+ */
+static inline void aead_request_set_callback(struct aead_request *req,
+					     u32 flags,
+					     crypto_completion_t compl,
+					     void *data)
+{
+	req->base.complete = compl;
+	req->base.data = data;
+	req->base.flags = flags;
+}
+
+/**
+ * aead_request_set_crypt - set data buffers
+ * @req: request handle
+ * @src: source scatter / gather list
+ * @dst: destination scatter / gather list
+ * @cryptlen: number of bytes to process from @src
+ * @iv: IV for the cipher operation which must comply with the IV size defined
+ *      by crypto_aead_ivsize()
+ *
+ * Setting the source data and destination data scatter / gather lists which
+ * hold the associated data concatenated with the plaintext or ciphertext. See
+ * below for the authentication tag.
+ *
+ * For encryption, the source is treated as the plaintext and the
+ * destination is the ciphertext. For a decryption operation, the use is
+ * reversed - the source is the ciphertext and the destination is the plaintext.
+ *
+ * For both src/dst the layout is associated data, plain/cipher text,
+ * authentication tag.
+ *
+ * The content of the AD in the destination buffer after processing
+ * will either be untouched, or it will contain a copy of the AD
+ * from the source buffer.  In order to ensure that it always has
+ * a copy of the AD, the user must copy the AD over either before
+ * or after processing.  Of course this is not relevant if the user
+ * is doing in-place processing where src == dst.
+ *
+ * IMPORTANT NOTE AEAD requires an authentication tag (MAC). For decryption,
+ *		  the caller must concatenate the ciphertext followed by the
+ *		  authentication tag and provide the entire data stream to the
+ *		  decryption operation (i.e. the data length used for the
+ *		  initialization of the scatterlist and the data length for the
+ *		  decryption operation is identical). For encryption, however,
+ *		  the authentication tag is created while encrypting the data.
+ *		  The destination buffer must hold sufficient space for the
+ *		  ciphertext and the authentication tag while the encryption
+ *		  invocation must only point to the plaintext data size. The
+ *		  following code snippet illustrates the memory usage
+ *		  buffer = kmalloc(ptbuflen + (enc ? authsize : 0));
+ *		  sg_init_one(&sg, buffer, ptbuflen + (enc ? authsize : 0));
+ *		  aead_request_set_crypt(req, &sg, &sg, ptbuflen, iv);
+ */
+static inline void aead_request_set_crypt(struct aead_request *req,
+					  struct scatterlist *src,
+					  struct scatterlist *dst,
+					  unsigned int cryptlen, u8 *iv)
+{
+	req->src = src;
+	req->dst = dst;
+	req->cryptlen = cryptlen;
+	req->iv = iv;
+}
+
+/**
+ * aead_request_set_assoc() - set the associated data scatter / gather list
+ * @req: request handle
+ * @assoc: associated data scatter / gather list
+ * @assoclen: number of bytes to process from @assoc
+ *
+ * Obsolete, do not use.
+ */
+static inline void aead_request_set_assoc(struct aead_request *req,
+					  struct scatterlist *assoc,
+					  unsigned int assoclen)
+{
+	req->assoc = assoc;
+	req->assoclen = assoclen;
+	req->old = true;
+}
+
+/**
+ * aead_request_set_ad - set associated data information
+ * @req: request handle
+ * @assoclen: number of bytes in associated data
+ *
+ * Setting the AD information.  This function sets the length of
+ * the associated data.
+ */
+static inline void aead_request_set_ad(struct aead_request *req,
+				       unsigned int assoclen)
+{
+	req->assoclen = assoclen;
+	req->old = false;
+}
+
 static inline struct crypto_aead *aead_givcrypt_reqtfm(
 	struct aead_givcrypt_request *req)
 {
@@ -38,14 +565,12 @@ static inline struct crypto_aead *aead_givcrypt_reqtfm(
 
 static inline int crypto_aead_givencrypt(struct aead_givcrypt_request *req)
 {
-	struct aead_tfm *crt = crypto_aead_crt(aead_givcrypt_reqtfm(req));
-	return crt->givencrypt(req);
+	return aead_givcrypt_reqtfm(req)->givencrypt(req);
 };
 
 static inline int crypto_aead_givdecrypt(struct aead_givcrypt_request *req)
 {
-	struct aead_tfm *crt = crypto_aead_crt(aead_givcrypt_reqtfm(req));
-	return crt->givdecrypt(req);
+	return aead_givcrypt_reqtfm(req)->givdecrypt(req);
 };
 
 static inline void aead_givcrypt_set_tfm(struct aead_givcrypt_request *req,
diff --git a/include/crypto/akcipher.h b/include/crypto/akcipher.h
new file mode 100644
index 000000000000..69d163e39101
--- /dev/null
+++ b/include/crypto/akcipher.h
@@ -0,0 +1,340 @@
+/*
+ * Public Key Encryption
+ *
+ * Copyright (c) 2015, Intel Corporation
+ * Authors: Tadeusz Struk <tadeusz.struk@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ */
+#ifndef _CRYPTO_AKCIPHER_H
+#define _CRYPTO_AKCIPHER_H
+#include <linux/crypto.h>
+
+/**
+ * struct akcipher_request - public key request
+ *
+ * @base:	Common attributes for async crypto requests
+ * @src:	Pointer to memory containing the input parameters
+ *		The format of the parameter(s) is expeted to be Octet String
+ * @dst:	Pointer to memory whare the result will be stored
+ * @src_len:	Size of the input parameter
+ * @dst_len:	Size of the output buffer. It needs to be at leaset
+ *		as big as the expected result depending	on the operation
+ *		After operation it will be updated with the acctual size of the
+ *		result. In case of error, where the dst_len was insufficient,
+ *		it will be updated to the size required for the operation.
+ * @__ctx:	Start of private context data
+ */
+struct akcipher_request {
+	struct crypto_async_request base;
+	void *src;
+	void *dst;
+	unsigned int src_len;
+	unsigned int dst_len;
+	void *__ctx[] CRYPTO_MINALIGN_ATTR;
+};
+
+/**
+ * struct crypto_akcipher - user-instantiated objects which encapsulate
+ * algorithms and core processing logic
+ *
+ * @base:	Common crypto API algorithm data structure
+ */
+struct crypto_akcipher {
+	struct crypto_tfm base;
+};
+
+/**
+ * struct akcipher_alg - generic public key algorithm
+ *
+ * @sign:	Function performs a sign operation as defined by public key
+ *		algorithm. In case of error, where the dst_len was insufficient,
+ *		the req->dst_len will be updated to the size required for the
+ *		operation
+ * @verify:	Function performs a sign operation as defined by public key
+ *		algorithm. In case of error, where the dst_len was insufficient,
+ *		the req->dst_len will be updated to the size required for the
+ *		operation
+ * @encrypt:	Function performs an encrytp operation as defined by public key
+ *		algorithm. In case of error, where the dst_len was insufficient,
+ *		the req->dst_len will be updated to the size required for the
+ *		operation
+ * @decrypt:	Function performs a decrypt operation as defined by public key
+ *		algorithm. In case of error, where the dst_len was insufficient,
+ *		the req->dst_len will be updated to the size required for the
+ *		operation
+ * @setkey:	Function invokes the algorithm specific set key function, which
+ *		knows how to decode and interpret the BER encoded key
+ * @init:	Initialize the cryptographic transformation object.
+ *		This function is used to initialize the cryptographic
+ *		transformation object. This function is called only once at
+ *		the instantiation time, right after the transformation context
+ *		was allocated. In case the cryptographic hardware has some
+ *		special requirements which need to be handled by software, this
+ *		function shall check for the precise requirement of the
+ *		transformation and put any software fallbacks in place.
+ * @exit:	Deinitialize the cryptographic transformation object. This is a
+ *		counterpart to @init, used to remove various changes set in
+ *		@init.
+ *
+ * @reqsize:	Request context size required by algorithm implementation
+ * @base:	Common crypto API algorithm data structure
+ */
+struct akcipher_alg {
+	int (*sign)(struct akcipher_request *req);
+	int (*verify)(struct akcipher_request *req);
+	int (*encrypt)(struct akcipher_request *req);
+	int (*decrypt)(struct akcipher_request *req);
+	int (*setkey)(struct crypto_akcipher *tfm, const void *key,
+		      unsigned int keylen);
+	int (*init)(struct crypto_akcipher *tfm);
+	void (*exit)(struct crypto_akcipher *tfm);
+
+	unsigned int reqsize;
+	struct crypto_alg base;
+};
+
+/**
+ * DOC: Generic Public Key API
+ *
+ * The Public Key API is used with the algorithms of type
+ * CRYPTO_ALG_TYPE_AKCIPHER (listed as type "akcipher" in /proc/crypto)
+ */
+
+/**
+ * crypto_alloc_akcipher() -- allocate AKCIPHER tfm handle
+ * @alg_name: is the cra_name / name or cra_driver_name / driver name of the
+ *	      public key algorithm e.g. "rsa"
+ * @type: specifies the type of the algorithm
+ * @mask: specifies the mask for the algorithm
+ *
+ * Allocate a handle for public key algorithm. The returned struct
+ * crypto_akcipher is the handle that is required for any subsequent
+ * API invocation for the public key operations.
+ *
+ * Return: allocated handle in case of success; IS_ERR() is true in case
+ *	   of an error, PTR_ERR() returns the error code.
+ */
+struct crypto_akcipher *crypto_alloc_akcipher(const char *alg_name, u32 type,
+					      u32 mask);
+
+static inline struct crypto_tfm *crypto_akcipher_tfm(
+	struct crypto_akcipher *tfm)
+{
+	return &tfm->base;
+}
+
+static inline struct akcipher_alg *__crypto_akcipher_alg(struct crypto_alg *alg)
+{
+	return container_of(alg, struct akcipher_alg, base);
+}
+
+static inline struct crypto_akcipher *__crypto_akcipher_tfm(
+	struct crypto_tfm *tfm)
+{
+	return container_of(tfm, struct crypto_akcipher, base);
+}
+
+static inline struct akcipher_alg *crypto_akcipher_alg(
+	struct crypto_akcipher *tfm)
+{
+	return __crypto_akcipher_alg(crypto_akcipher_tfm(tfm)->__crt_alg);
+}
+
+static inline unsigned int crypto_akcipher_reqsize(struct crypto_akcipher *tfm)
+{
+	return crypto_akcipher_alg(tfm)->reqsize;
+}
+
+static inline void akcipher_request_set_tfm(struct akcipher_request *req,
+					    struct crypto_akcipher *tfm)
+{
+	req->base.tfm = crypto_akcipher_tfm(tfm);
+}
+
+static inline struct crypto_akcipher *crypto_akcipher_reqtfm(
+	struct akcipher_request *req)
+{
+	return __crypto_akcipher_tfm(req->base.tfm);
+}
+
+/**
+ * crypto_free_akcipher() -- free AKCIPHER tfm handle
+ *
+ * @tfm: AKCIPHER tfm handle allocated with crypto_alloc_akcipher()
+ */
+static inline void crypto_free_akcipher(struct crypto_akcipher *tfm)
+{
+	crypto_destroy_tfm(tfm, crypto_akcipher_tfm(tfm));
+}
+
+/**
+ * akcipher_request_alloc() -- allocates public key request
+ *
+ * @tfm:	AKCIPHER tfm handle allocated with crypto_alloc_akcipher()
+ * @gfp:	allocation flags
+ *
+ * Return: allocated handle in case of success or NULL in case of an error.
+ */
+static inline struct akcipher_request *akcipher_request_alloc(
+	struct crypto_akcipher *tfm, gfp_t gfp)
+{
+	struct akcipher_request *req;
+
+	req = kmalloc(sizeof(*req) + crypto_akcipher_reqsize(tfm), gfp);
+	if (likely(req))
+		akcipher_request_set_tfm(req, tfm);
+
+	return req;
+}
+
+/**
+ * akcipher_request_free() -- zeroize and free public key request
+ *
+ * @req:	request to free
+ */
+static inline void akcipher_request_free(struct akcipher_request *req)
+{
+	kzfree(req);
+}
+
+/**
+ * akcipher_request_set_callback() -- Sets an asynchronous callback.
+ *
+ * Callback will be called when an asynchronous operation on a given
+ * request is finished.
+ *
+ * @req:	request that the callback will be set for
+ * @flgs:	specify for instance if the operation may backlog
+ * @cmlp:	callback which will be called
+ * @data:	private data used by the caller
+ */
+static inline void akcipher_request_set_callback(struct akcipher_request *req,
+						 u32 flgs,
+						 crypto_completion_t cmpl,
+						 void *data)
+{
+	req->base.complete = cmpl;
+	req->base.data = data;
+	req->base.flags = flgs;
+}
+
+/**
+ * akcipher_request_set_crypt() -- Sets reqest parameters
+ *
+ * Sets parameters required by crypto operation
+ *
+ * @req:	public key request
+ * @src:	ptr to input parameter
+ * @dst:	ptr of output parameter
+ * @src_len:	size of the input buffer
+ * @dst_len:	size of the output buffer. It will be updated by the
+ *		implementation to reflect the acctual size of the result
+ */
+static inline void akcipher_request_set_crypt(struct akcipher_request *req,
+					      void *src, void *dst,
+					      unsigned int src_len,
+					      unsigned int dst_len)
+{
+	req->src = src;
+	req->dst = dst;
+	req->src_len = src_len;
+	req->dst_len = dst_len;
+}
+
+/**
+ * crypto_akcipher_encrypt() -- Invoke public key encrypt operation
+ *
+ * Function invokes the specific public key encrypt operation for a given
+ * public key algorithm
+ *
+ * @req:	asymmetric key request
+ *
+ * Return: zero on success; error code in case of error
+ */
+static inline int crypto_akcipher_encrypt(struct akcipher_request *req)
+{
+	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
+	struct akcipher_alg *alg = crypto_akcipher_alg(tfm);
+
+	return alg->encrypt(req);
+}
+
+/**
+ * crypto_akcipher_decrypt() -- Invoke public key decrypt operation
+ *
+ * Function invokes the specific public key decrypt operation for a given
+ * public key algorithm
+ *
+ * @req:	asymmetric key request
+ *
+ * Return: zero on success; error code in case of error
+ */
+static inline int crypto_akcipher_decrypt(struct akcipher_request *req)
+{
+	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
+	struct akcipher_alg *alg = crypto_akcipher_alg(tfm);
+
+	return alg->decrypt(req);
+}
+
+/**
+ * crypto_akcipher_sign() -- Invoke public key sign operation
+ *
+ * Function invokes the specific public key sign operation for a given
+ * public key algorithm
+ *
+ * @req:	asymmetric key request
+ *
+ * Return: zero on success; error code in case of error
+ */
+static inline int crypto_akcipher_sign(struct akcipher_request *req)
+{
+	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
+	struct akcipher_alg *alg = crypto_akcipher_alg(tfm);
+
+	return alg->sign(req);
+}
+
+/**
+ * crypto_akcipher_verify() -- Invoke public key verify operation
+ *
+ * Function invokes the specific public key verify operation for a given
+ * public key algorithm
+ *
+ * @req:	asymmetric key request
+ *
+ * Return: zero on success; error code in case of error
+ */
+static inline int crypto_akcipher_verify(struct akcipher_request *req)
+{
+	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
+	struct akcipher_alg *alg = crypto_akcipher_alg(tfm);
+
+	return alg->verify(req);
+}
+
+/**
+ * crypto_akcipher_setkey() -- Invoke public key setkey operation
+ *
+ * Function invokes the algorithm specific set key function, which knows
+ * how to decode and interpret the encoded key
+ *
+ * @tfm:	tfm handle
+ * @key:	BER encoded private or public key
+ * @keylen:	length of the key
+ *
+ * Return: zero on success; error code in case of error
+ */
+static inline int crypto_akcipher_setkey(struct crypto_akcipher *tfm, void *key,
+					 unsigned int keylen)
+{
+	struct akcipher_alg *alg = crypto_akcipher_alg(tfm);
+
+	return alg->setkey(tfm, key, keylen);
+}
+#endif
diff --git a/include/crypto/algapi.h b/include/crypto/algapi.h
index 0ecb7688af71..d4ebf6e9af6a 100644
--- a/include/crypto/algapi.h
+++ b/include/crypto/algapi.h
@@ -17,6 +17,7 @@
 #include <linux/kernel.h>
 #include <linux/skbuff.h>
 
+struct crypto_aead;
 struct module;
 struct rtattr;
 struct seq_file;
@@ -126,7 +127,6 @@ struct ablkcipher_walk {
 };
 
 extern const struct crypto_type crypto_ablkcipher_type;
-extern const struct crypto_type crypto_aead_type;
 extern const struct crypto_type crypto_blkcipher_type;
 
 void crypto_mod_put(struct crypto_alg *alg);
@@ -144,6 +144,8 @@ int crypto_init_spawn(struct crypto_spawn *spawn, struct crypto_alg *alg,
 int crypto_init_spawn2(struct crypto_spawn *spawn, struct crypto_alg *alg,
 		       struct crypto_instance *inst,
 		       const struct crypto_type *frontend);
+int crypto_grab_spawn(struct crypto_spawn *spawn, const char *name,
+		      u32 type, u32 mask);
 
 void crypto_drop_spawn(struct crypto_spawn *spawn);
 struct crypto_tfm *crypto_spawn_tfm(struct crypto_spawn *spawn, u32 type,
@@ -239,22 +241,6 @@ static inline void *crypto_ablkcipher_ctx_aligned(struct crypto_ablkcipher *tfm)
 	return crypto_tfm_ctx_aligned(&tfm->base);
 }
 
-static inline struct aead_alg *crypto_aead_alg(struct crypto_aead *tfm)
-{
-	return &crypto_aead_tfm(tfm)->__crt_alg->cra_aead;
-}
-
-static inline void *crypto_aead_ctx(struct crypto_aead *tfm)
-{
-	return crypto_tfm_ctx(&tfm->base);
-}
-
-static inline struct crypto_instance *crypto_aead_alg_instance(
-	struct crypto_aead *aead)
-{
-	return crypto_tfm_alg_instance(&aead->base);
-}
-
 static inline struct crypto_blkcipher *crypto_spawn_blkcipher(
 	struct crypto_spawn *spawn)
 {
@@ -363,21 +349,6 @@ static inline int ablkcipher_tfm_in_queue(struct crypto_queue *queue,
 	return crypto_tfm_in_queue(queue, crypto_ablkcipher_tfm(tfm));
 }
 
-static inline void *aead_request_ctx(struct aead_request *req)
-{
-	return req->__ctx;
-}
-
-static inline void aead_request_complete(struct aead_request *req, int err)
-{
-	req->base.complete(&req->base, err);
-}
-
-static inline u32 aead_request_flags(struct aead_request *req)
-{
-	return req->base.flags;
-}
-
 static inline struct crypto_alg *crypto_get_attr_alg(struct rtattr **tb,
 						     u32 type, u32 mask)
 {
diff --git a/include/crypto/compress.h b/include/crypto/compress.h
index 86163ef24219..5b67af834d83 100644
--- a/include/crypto/compress.h
+++ b/include/crypto/compress.h
@@ -55,14 +55,14 @@ struct crypto_pcomp {
 };
 
 struct pcomp_alg {
-	int (*compress_setup)(struct crypto_pcomp *tfm, void *params,
+	int (*compress_setup)(struct crypto_pcomp *tfm, const void *params,
 			      unsigned int len);
 	int (*compress_init)(struct crypto_pcomp *tfm);
 	int (*compress_update)(struct crypto_pcomp *tfm,
 			       struct comp_request *req);
 	int (*compress_final)(struct crypto_pcomp *tfm,
 			      struct comp_request *req);
-	int (*decompress_setup)(struct crypto_pcomp *tfm, void *params,
+	int (*decompress_setup)(struct crypto_pcomp *tfm, const void *params,
 				unsigned int len);
 	int (*decompress_init)(struct crypto_pcomp *tfm);
 	int (*decompress_update)(struct crypto_pcomp *tfm,
@@ -97,7 +97,7 @@ static inline struct pcomp_alg *crypto_pcomp_alg(struct crypto_pcomp *tfm)
 }
 
 static inline int crypto_compress_setup(struct crypto_pcomp *tfm,
-					void *params, unsigned int len)
+					const void *params, unsigned int len)
 {
 	return crypto_pcomp_alg(tfm)->compress_setup(tfm, params, len);
 }
@@ -120,7 +120,7 @@ static inline int crypto_compress_final(struct crypto_pcomp *tfm,
 }
 
 static inline int crypto_decompress_setup(struct crypto_pcomp *tfm,
-					  void *params, unsigned int len)
+					  const void *params, unsigned int len)
 {
 	return crypto_pcomp_alg(tfm)->decompress_setup(tfm, params, len);
 }
diff --git a/include/crypto/cryptd.h b/include/crypto/cryptd.h
index ba98918bbd9b..1547f540c920 100644
--- a/include/crypto/cryptd.h
+++ b/include/crypto/cryptd.h
@@ -14,6 +14,7 @@
 
 #include <linux/crypto.h>
 #include <linux/kernel.h>
+#include <crypto/aead.h>
 #include <crypto/hash.h>
 
 struct cryptd_ablkcipher {
diff --git a/include/crypto/drbg.h b/include/crypto/drbg.h
index 5186f750c713..9756c70899d8 100644
--- a/include/crypto/drbg.h
+++ b/include/crypto/drbg.h
@@ -49,8 +49,9 @@
 #include <crypto/internal/rng.h>
 #include <crypto/rng.h>
 #include <linux/fips.h>
-#include <linux/spinlock.h>
+#include <linux/mutex.h>
 #include <linux/list.h>
+#include <linux/workqueue.h>
 
 /*
  * Concatenation Helper and string operation helper
@@ -104,12 +105,13 @@ struct drbg_test_data {
 };
 
 struct drbg_state {
-	spinlock_t drbg_lock;	/* lock around DRBG */
+	struct mutex drbg_mutex;	/* lock around DRBG */
 	unsigned char *V;	/* internal state 10.1.1.1 1a) */
 	/* hash: static value 10.1.1.1 1b) hmac / ctr: key */
 	unsigned char *C;
 	/* Number of RNG requests since last reseed -- 10.1.1.1 1c) */
 	size_t reseed_ctr;
+	size_t reseed_threshold;
 	 /* some memory the DRBG can use for its operation */
 	unsigned char *scratchpad;
 	void *priv_data;	/* Cipher handle */
@@ -119,9 +121,12 @@ struct drbg_state {
 	bool fips_primed;	/* Continuous test primed? */
 	unsigned char *prev;	/* FIPS 140-2 continuous test value */
 #endif
+	struct work_struct seed_work;	/* asynchronous seeding support */
+	struct crypto_rng *jent;
 	const struct drbg_state_ops *d_ops;
 	const struct drbg_core *core;
-	struct drbg_test_data *test_data;
+	struct drbg_string test_data;
+	struct random_ready_callback random_ready;
 };
 
 static inline __u8 drbg_statelen(struct drbg_state *drbg)
@@ -177,19 +182,8 @@ static inline size_t drbg_max_requests(struct drbg_state *drbg)
 }
 
 /*
- * kernel crypto API input data structure for DRBG generate in case dlen
- * is set to 0
- */
-struct drbg_gen {
-	unsigned char *outbuf;	/* output buffer for random numbers */
-	unsigned int outlen;	/* size of output buffer */
-	struct drbg_string *addtl;	/* additional information string */
-	struct drbg_test_data *test_data;	/* test data */
-};
-
-/*
  * This is a wrapper to the kernel crypto API function of
- * crypto_rng_get_bytes() to allow the caller to provide additional data.
+ * crypto_rng_generate() to allow the caller to provide additional data.
  *
  * @drng DRBG handle -- see crypto_rng_get_bytes
  * @outbuf output buffer -- see crypto_rng_get_bytes
@@ -204,21 +198,15 @@ static inline int crypto_drbg_get_bytes_addtl(struct crypto_rng *drng,
 			unsigned char *outbuf, unsigned int outlen,
 			struct drbg_string *addtl)
 {
-	int ret;
-	struct drbg_gen genbuf;
-	genbuf.outbuf = outbuf;
-	genbuf.outlen = outlen;
-	genbuf.addtl = addtl;
-	genbuf.test_data = NULL;
-	ret = crypto_rng_get_bytes(drng, (u8 *)&genbuf, 0);
-	return ret;
+	return crypto_rng_generate(drng, addtl->buf, addtl->len,
+				   outbuf, outlen);
 }
 
 /*
  * TEST code
  *
  * This is a wrapper to the kernel crypto API function of
- * crypto_rng_get_bytes() to allow the caller to provide additional data and
+ * crypto_rng_generate() to allow the caller to provide additional data and
  * allow furnishing of test_data
  *
  * @drng DRBG handle -- see crypto_rng_get_bytes
@@ -236,14 +224,10 @@ static inline int crypto_drbg_get_bytes_addtl_test(struct crypto_rng *drng,
 			struct drbg_string *addtl,
 			struct drbg_test_data *test_data)
 {
-	int ret;
-	struct drbg_gen genbuf;
-	genbuf.outbuf = outbuf;
-	genbuf.outlen = outlen;
-	genbuf.addtl = addtl;
-	genbuf.test_data = test_data;
-	ret = crypto_rng_get_bytes(drng, (u8 *)&genbuf, 0);
-	return ret;
+	crypto_rng_set_entropy(drng, test_data->testentropy->buf,
+			       test_data->testentropy->len);
+	return crypto_rng_generate(drng, addtl->buf, addtl->len,
+				   outbuf, outlen);
 }
 
 /*
@@ -264,14 +248,9 @@ static inline int crypto_drbg_reset_test(struct crypto_rng *drng,
 					 struct drbg_string *pers,
 					 struct drbg_test_data *test_data)
 {
-	int ret;
-	struct drbg_gen genbuf;
-	genbuf.outbuf = NULL;
-	genbuf.outlen = 0;
-	genbuf.addtl = pers;
-	genbuf.test_data = test_data;
-	ret = crypto_rng_reset(drng, (u8 *)&genbuf, 0);
-	return ret;
+	crypto_rng_set_entropy(drng, test_data->testentropy->buf,
+			       test_data->testentropy->len);
+	return crypto_rng_reset(drng, pers->buf, pers->len);
 }
 
 /* DRBG type flags */
diff --git a/include/crypto/hash.h b/include/crypto/hash.h
index 98abda9ed3aa..57c8a6ee33c2 100644
--- a/include/crypto/hash.h
+++ b/include/crypto/hash.h
@@ -66,7 +66,7 @@ struct ahash_request {
 /**
  * struct ahash_alg - asynchronous message digest definition
  * @init: Initialize the transformation context. Intended only to initialize the
- *	  state of the HASH transformation at the begining. This shall fill in
+ *	  state of the HASH transformation at the beginning. This shall fill in
  *	  the internal structures used during the entire duration of the whole
  *	  transformation. No data processing happens at this point.
  * @update: Push a chunk of data into the driver for transformation. This
diff --git a/include/crypto/internal/aead.h b/include/crypto/internal/aead.h
index 2eba340230a7..4b2547186519 100644
--- a/include/crypto/internal/aead.h
+++ b/include/crypto/internal/aead.h
@@ -15,16 +15,75 @@
 
 #include <crypto/aead.h>
 #include <crypto/algapi.h>
+#include <linux/stddef.h>
 #include <linux/types.h>
 
 struct rtattr;
 
+struct aead_instance {
+	union {
+		struct {
+			char head[offsetof(struct aead_alg, base)];
+			struct crypto_instance base;
+		} s;
+		struct aead_alg alg;
+	};
+};
+
 struct crypto_aead_spawn {
 	struct crypto_spawn base;
 };
 
+extern const struct crypto_type crypto_aead_type;
 extern const struct crypto_type crypto_nivaead_type;
 
+static inline void *crypto_aead_ctx(struct crypto_aead *tfm)
+{
+	return crypto_tfm_ctx(&tfm->base);
+}
+
+static inline struct crypto_instance *crypto_aead_alg_instance(
+	struct crypto_aead *aead)
+{
+	return crypto_tfm_alg_instance(&aead->base);
+}
+
+static inline struct crypto_instance *aead_crypto_instance(
+	struct aead_instance *inst)
+{
+	return container_of(&inst->alg.base, struct crypto_instance, alg);
+}
+
+static inline struct aead_instance *aead_instance(struct crypto_instance *inst)
+{
+	return container_of(&inst->alg, struct aead_instance, alg.base);
+}
+
+static inline struct aead_instance *aead_alg_instance(struct crypto_aead *aead)
+{
+	return aead_instance(crypto_aead_alg_instance(aead));
+}
+
+static inline void *aead_instance_ctx(struct aead_instance *inst)
+{
+	return crypto_instance_ctx(aead_crypto_instance(inst));
+}
+
+static inline void *aead_request_ctx(struct aead_request *req)
+{
+	return req->__ctx;
+}
+
+static inline void aead_request_complete(struct aead_request *req, int err)
+{
+	req->base.complete(&req->base, err);
+}
+
+static inline u32 aead_request_flags(struct aead_request *req)
+{
+	return req->base.flags;
+}
+
 static inline void crypto_set_aead_spawn(
 	struct crypto_aead_spawn *spawn, struct crypto_instance *inst)
 {
@@ -47,24 +106,27 @@ static inline struct crypto_alg *crypto_aead_spawn_alg(
 	return spawn->base.alg;
 }
 
+static inline struct aead_alg *crypto_spawn_aead_alg(
+	struct crypto_aead_spawn *spawn)
+{
+	return container_of(spawn->base.alg, struct aead_alg, base);
+}
+
 static inline struct crypto_aead *crypto_spawn_aead(
 	struct crypto_aead_spawn *spawn)
 {
-	return __crypto_aead_cast(
-		crypto_spawn_tfm(&spawn->base, CRYPTO_ALG_TYPE_AEAD,
-				 CRYPTO_ALG_TYPE_MASK));
+	return crypto_spawn_tfm2(&spawn->base);
 }
 
-struct crypto_instance *aead_geniv_alloc(struct crypto_template *tmpl,
-					 struct rtattr **tb, u32 type,
-					 u32 mask);
-void aead_geniv_free(struct crypto_instance *inst);
+struct aead_instance *aead_geniv_alloc(struct crypto_template *tmpl,
+				       struct rtattr **tb, u32 type, u32 mask);
+void aead_geniv_free(struct aead_instance *inst);
 int aead_geniv_init(struct crypto_tfm *tfm);
 void aead_geniv_exit(struct crypto_tfm *tfm);
 
 static inline struct crypto_aead *aead_geniv_base(struct crypto_aead *geniv)
 {
-	return crypto_aead_crt(geniv)->base;
+	return geniv->child;
 }
 
 static inline void *aead_givcrypt_reqctx(struct aead_givcrypt_request *req)
@@ -78,5 +140,29 @@ static inline void aead_givcrypt_complete(struct aead_givcrypt_request *req,
 	aead_request_complete(&req->areq, err);
 }
 
+static inline void crypto_aead_set_reqsize(struct crypto_aead *aead,
+					   unsigned int reqsize)
+{
+	crypto_aead_crt(aead)->reqsize = reqsize;
+}
+
+static inline unsigned int crypto_aead_alg_maxauthsize(struct aead_alg *alg)
+{
+	return alg->base.cra_aead.encrypt ? alg->base.cra_aead.maxauthsize :
+					    alg->maxauthsize;
+}
+
+static inline unsigned int crypto_aead_maxauthsize(struct crypto_aead *aead)
+{
+	return crypto_aead_alg_maxauthsize(crypto_aead_alg(aead));
+}
+
+int crypto_register_aead(struct aead_alg *alg);
+void crypto_unregister_aead(struct aead_alg *alg);
+int crypto_register_aeads(struct aead_alg *algs, int count);
+void crypto_unregister_aeads(struct aead_alg *algs, int count);
+int aead_register_instance(struct crypto_template *tmpl,
+			   struct aead_instance *inst);
+
 #endif	/* _CRYPTO_INTERNAL_AEAD_H */
 
diff --git a/include/crypto/internal/akcipher.h b/include/crypto/internal/akcipher.h
new file mode 100644
index 000000000000..9a2bda15e454
--- /dev/null
+++ b/include/crypto/internal/akcipher.h
@@ -0,0 +1,60 @@
+/*
+ * Public Key Encryption
+ *
+ * Copyright (c) 2015, Intel Corporation
+ * Authors: Tadeusz Struk <tadeusz.struk@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ */
+#ifndef _CRYPTO_AKCIPHER_INT_H
+#define _CRYPTO_AKCIPHER_INT_H
+#include <crypto/akcipher.h>
+
+/*
+ * Transform internal helpers.
+ */
+static inline void *akcipher_request_ctx(struct akcipher_request *req)
+{
+	return req->__ctx;
+}
+
+static inline void *akcipher_tfm_ctx(struct crypto_akcipher *tfm)
+{
+	return tfm->base.__crt_ctx;
+}
+
+static inline void akcipher_request_complete(struct akcipher_request *req,
+					     int err)
+{
+	req->base.complete(&req->base, err);
+}
+
+static inline const char *akcipher_alg_name(struct crypto_akcipher *tfm)
+{
+	return crypto_akcipher_tfm(tfm)->__crt_alg->cra_name;
+}
+
+/**
+ * crypto_register_akcipher() -- Register public key algorithm
+ *
+ * Function registers an implementation of a public key verify algorithm
+ *
+ * @alg:	algorithm definition
+ *
+ * Return: zero on success; error code in case of error
+ */
+int crypto_register_akcipher(struct akcipher_alg *alg);
+
+/**
+ * crypto_unregister_akcipher() -- Unregister public key algorithm
+ *
+ * Function unregisters an implementation of a public key verify algorithm
+ *
+ * @alg:	algorithm definition
+ */
+void crypto_unregister_akcipher(struct akcipher_alg *alg);
+#endif
diff --git a/include/crypto/internal/geniv.h b/include/crypto/internal/geniv.h
new file mode 100644
index 000000000000..9ca9b871aba5
--- /dev/null
+++ b/include/crypto/internal/geniv.h
@@ -0,0 +1,24 @@
+/*
+ * geniv: IV generation
+ *
+ * Copyright (c) 2015 Herbert Xu <herbert@gondor.apana.org.au>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ */
+
+#ifndef _CRYPTO_INTERNAL_GENIV_H
+#define _CRYPTO_INTERNAL_GENIV_H
+
+#include <crypto/internal/aead.h>
+#include <linux/spinlock.h>
+
+struct aead_geniv_ctx {
+	spinlock_t lock;
+	struct crypto_aead *child;
+};
+
+#endif	/* _CRYPTO_INTERNAL_GENIV_H */
diff --git a/include/crypto/internal/rng.h b/include/crypto/internal/rng.h
index 896973369573..a52ef3483dd7 100644
--- a/include/crypto/internal/rng.h
+++ b/include/crypto/internal/rng.h
@@ -2,6 +2,7 @@
  * RNG: Random Number Generator  algorithms under the crypto API
  *
  * Copyright (c) 2008 Neil Horman <nhorman@tuxdriver.com>
+ * Copyright (c) 2015 Herbert Xu <herbert@gondor.apana.org.au>
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms of the GNU General Public License as published by the Free
@@ -16,11 +17,29 @@
 #include <crypto/algapi.h>
 #include <crypto/rng.h>
 
-extern const struct crypto_type crypto_rng_type;
+int crypto_register_rng(struct rng_alg *alg);
+void crypto_unregister_rng(struct rng_alg *alg);
+int crypto_register_rngs(struct rng_alg *algs, int count);
+void crypto_unregister_rngs(struct rng_alg *algs, int count);
+
+#if defined(CONFIG_CRYPTO_RNG) || defined(CONFIG_CRYPTO_RNG_MODULE)
+int crypto_del_default_rng(void);
+#else
+static inline int crypto_del_default_rng(void)
+{
+	return 0;
+}
+#endif
 
 static inline void *crypto_rng_ctx(struct crypto_rng *tfm)
 {
 	return crypto_tfm_ctx(&tfm->base);
 }
 
+static inline void crypto_rng_set_entropy(struct crypto_rng *tfm,
+					  const u8 *data, unsigned int len)
+{
+	crypto_rng_alg(tfm)->set_ent(tfm, data, len);
+}
+
 #endif
diff --git a/include/crypto/internal/rsa.h b/include/crypto/internal/rsa.h
new file mode 100644
index 000000000000..a8c86365439f
--- /dev/null
+++ b/include/crypto/internal/rsa.h
@@ -0,0 +1,27 @@
+/*
+ * RSA internal helpers
+ *
+ * Copyright (c) 2015, Intel Corporation
+ * Authors: Tadeusz Struk <tadeusz.struk@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ */
+#ifndef _RSA_HELPER_
+#define _RSA_HELPER_
+#include <linux/mpi.h>
+
+struct rsa_key {
+	MPI n;
+	MPI e;
+	MPI d;
+};
+
+int rsa_parse_key(struct rsa_key *rsa_key, const void *key,
+		  unsigned int key_len);
+
+void rsa_free_key(struct rsa_key *rsa_key);
+#endif
diff --git a/include/crypto/md5.h b/include/crypto/md5.h
index 65f299b08b0d..146af825eedb 100644
--- a/include/crypto/md5.h
+++ b/include/crypto/md5.h
@@ -8,6 +8,11 @@
 #define MD5_BLOCK_WORDS		16
 #define MD5_HASH_WORDS		4
 
+#define MD5_H0	0x67452301UL
+#define MD5_H1	0xefcdab89UL
+#define MD5_H2	0x98badcfeUL
+#define MD5_H3	0x10325476UL
+
 struct md5_state {
 	u32 hash[MD5_HASH_WORDS];
 	u32 block[MD5_BLOCK_WORDS];
diff --git a/include/crypto/null.h b/include/crypto/null.h
index b7c864cc70df..06dc30d9f56e 100644
--- a/include/crypto/null.h
+++ b/include/crypto/null.h
@@ -8,4 +8,7 @@
 #define NULL_DIGEST_SIZE	0
 #define NULL_IV_SIZE		0
 
+struct crypto_blkcipher *crypto_get_default_null_skcipher(void);
+void crypto_put_default_null_skcipher(void);
+
 #endif
diff --git a/include/crypto/rng.h b/include/crypto/rng.h
index 6e28ea5be9f1..b95ede354a66 100644
--- a/include/crypto/rng.h
+++ b/include/crypto/rng.h
@@ -2,6 +2,7 @@
  * RNG: Random Number Generator  algorithms under the crypto API
  *
  * Copyright (c) 2008 Neil Horman <nhorman@tuxdriver.com>
+ * Copyright (c) 2015 Herbert Xu <herbert@gondor.apana.org.au>
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms of the GNU General Public License as published by the Free
@@ -15,6 +16,50 @@
 
 #include <linux/crypto.h>
 
+struct crypto_rng;
+
+/**
+ * struct rng_alg - random number generator definition
+ *
+ * @generate:	The function defined by this variable obtains a
+ *		random number. The random number generator transform
+ *		must generate the random number out of the context
+ *		provided with this call, plus any additional data
+ *		if provided to the call.
+ * @seed:	Seed or reseed the random number generator.  With the
+ *		invocation of this function call, the random number
+ *		generator shall become ready for generation.  If the
+ *		random number generator requires a seed for setting
+ *		up a new state, the seed must be provided by the
+ *		consumer while invoking this function. The required
+ *		size of the seed is defined with @seedsize .
+ * @set_ent:	Set entropy that would otherwise be obtained from
+ *		entropy source.  Internal use only.
+ * @seedsize:	The seed size required for a random number generator
+ *		initialization defined with this variable. Some
+ *		random number generators does not require a seed
+ *		as the seeding is implemented internally without
+ *		the need of support by the consumer. In this case,
+ *		the seed size is set to zero.
+ * @base:	Common crypto API algorithm data structure.
+ */
+struct rng_alg {
+	int (*generate)(struct crypto_rng *tfm,
+			const u8 *src, unsigned int slen,
+			u8 *dst, unsigned int dlen);
+	int (*seed)(struct crypto_rng *tfm, const u8 *seed, unsigned int slen);
+	void (*set_ent)(struct crypto_rng *tfm, const u8 *data,
+			unsigned int len);
+
+	unsigned int seedsize;
+
+	struct crypto_alg base;
+};
+
+struct crypto_rng {
+	struct crypto_tfm base;
+};
+
 extern struct crypto_rng *crypto_default_rng;
 
 int crypto_get_default_rng(void);
@@ -27,11 +72,6 @@ void crypto_put_default_rng(void);
  * CRYPTO_ALG_TYPE_RNG (listed as type "rng" in /proc/crypto)
  */
 
-static inline struct crypto_rng *__crypto_rng_cast(struct crypto_tfm *tfm)
-{
-	return (struct crypto_rng *)tfm;
-}
-
 /**
  * crypto_alloc_rng() -- allocate RNG handle
  * @alg_name: is the cra_name / name or cra_driver_name / driver name of the
@@ -52,15 +92,7 @@ static inline struct crypto_rng *__crypto_rng_cast(struct crypto_tfm *tfm)
  * Return: allocated cipher handle in case of success; IS_ERR() is true in case
  *	   of an error, PTR_ERR() returns the error code.
  */
-static inline struct crypto_rng *crypto_alloc_rng(const char *alg_name,
-						  u32 type, u32 mask)
-{
-	type &= ~CRYPTO_ALG_TYPE_MASK;
-	type |= CRYPTO_ALG_TYPE_RNG;
-	mask |= CRYPTO_ALG_TYPE_MASK;
-
-	return __crypto_rng_cast(crypto_alloc_base(alg_name, type, mask));
-}
+struct crypto_rng *crypto_alloc_rng(const char *alg_name, u32 type, u32 mask);
 
 static inline struct crypto_tfm *crypto_rng_tfm(struct crypto_rng *tfm)
 {
@@ -77,12 +109,8 @@ static inline struct crypto_tfm *crypto_rng_tfm(struct crypto_rng *tfm)
  */
 static inline struct rng_alg *crypto_rng_alg(struct crypto_rng *tfm)
 {
-	return &crypto_rng_tfm(tfm)->__crt_alg->cra_rng;
-}
-
-static inline struct rng_tfm *crypto_rng_crt(struct crypto_rng *tfm)
-{
-	return &crypto_rng_tfm(tfm)->crt_rng;
+	return container_of(crypto_rng_tfm(tfm)->__crt_alg,
+			    struct rng_alg, base);
 }
 
 /**
@@ -91,7 +119,28 @@ static inline struct rng_tfm *crypto_rng_crt(struct crypto_rng *tfm)
  */
 static inline void crypto_free_rng(struct crypto_rng *tfm)
 {
-	crypto_free_tfm(crypto_rng_tfm(tfm));
+	crypto_destroy_tfm(tfm, crypto_rng_tfm(tfm));
+}
+
+/**
+ * crypto_rng_generate() - get random number
+ * @tfm: cipher handle
+ * @src: Input buffer holding additional data, may be NULL
+ * @slen: Length of additional data
+ * @dst: output buffer holding the random numbers
+ * @dlen: length of the output buffer
+ *
+ * This function fills the caller-allocated buffer with random
+ * numbers using the random number generator referenced by the
+ * cipher handle.
+ *
+ * Return: 0 function was successful; < 0 if an error occurred
+ */
+static inline int crypto_rng_generate(struct crypto_rng *tfm,
+				      const u8 *src, unsigned int slen,
+				      u8 *dst, unsigned int dlen)
+{
+	return crypto_rng_alg(tfm)->generate(tfm, src, slen, dst, dlen);
 }
 
 /**
@@ -108,7 +157,7 @@ static inline void crypto_free_rng(struct crypto_rng *tfm)
 static inline int crypto_rng_get_bytes(struct crypto_rng *tfm,
 				       u8 *rdata, unsigned int dlen)
 {
-	return crypto_rng_crt(tfm)->rng_gen_random(tfm, rdata, dlen);
+	return crypto_rng_generate(tfm, NULL, 0, rdata, dlen);
 }
 
 /**
@@ -128,11 +177,8 @@ static inline int crypto_rng_get_bytes(struct crypto_rng *tfm,
  *
  * Return: 0 if the setting of the key was successful; < 0 if an error occurred
  */
-static inline int crypto_rng_reset(struct crypto_rng *tfm,
-				   u8 *seed, unsigned int slen)
-{
-	return crypto_rng_crt(tfm)->rng_reset(tfm, seed, slen);
-}
+int crypto_rng_reset(struct crypto_rng *tfm, const u8 *seed,
+		     unsigned int slen);
 
 /**
  * crypto_rng_seedsize() - obtain seed size of RNG
diff --git a/include/crypto/scatterwalk.h b/include/crypto/scatterwalk.h
index 20e4226a2e14..96670e7e7c14 100644
--- a/include/crypto/scatterwalk.h
+++ b/include/crypto/scatterwalk.h
@@ -102,4 +102,8 @@ void scatterwalk_map_and_copy(void *buf, struct scatterlist *sg,
 
 int scatterwalk_bytes_sglen(struct scatterlist *sg, int num_bytes);
 
+struct scatterlist *scatterwalk_ffwd(struct scatterlist dst[2],
+				     struct scatterlist *src,
+				     unsigned int len);
+
 #endif  /* _CRYPTO_SCATTERWALK_H */
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 400b86453ed7..c187817471fb 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -710,6 +710,8 @@ static inline void acpi_dev_remove_driver_gpios(struct acpi_device *adev)
 	if (adev)
 		adev->driver_gpios = NULL;
 }
+
+int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index);
 #else
 static inline int acpi_dev_add_driver_gpios(struct acpi_device *adev,
 			      const struct acpi_gpio_mapping *gpios)
@@ -717,6 +719,11 @@ static inline int acpi_dev_add_driver_gpios(struct acpi_device *adev,
 	return -ENXIO;
 }
 static inline void acpi_dev_remove_driver_gpios(struct acpi_device *adev) {}
+
+static inline int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index)
+{
+	return -ENXIO;
+}
 #endif
 
 /* Device properties */
diff --git a/include/linux/alarmtimer.h b/include/linux/alarmtimer.h
index a899402a5a0e..52f3b7da4f2d 100644
--- a/include/linux/alarmtimer.h
+++ b/include/linux/alarmtimer.h
@@ -43,8 +43,8 @@ struct alarm {
 
 void alarm_init(struct alarm *alarm, enum alarmtimer_type type,
 		enum alarmtimer_restart (*function)(struct alarm *, ktime_t));
-int alarm_start(struct alarm *alarm, ktime_t start);
-int alarm_start_relative(struct alarm *alarm, ktime_t start);
+void alarm_start(struct alarm *alarm, ktime_t start);
+void alarm_start_relative(struct alarm *alarm, ktime_t start);
 void alarm_restart(struct alarm *alarm);
 int alarm_try_to_cancel(struct alarm *alarm);
 int alarm_cancel(struct alarm *alarm);
diff --git a/include/linux/basic_mmio_gpio.h b/include/linux/basic_mmio_gpio.h
index 0e97856b2cff..14eea946e640 100644
--- a/include/linux/basic_mmio_gpio.h
+++ b/include/linux/basic_mmio_gpio.h
@@ -74,5 +74,6 @@ int bgpio_init(struct bgpio_chip *bgc, struct device *dev,
 #define BGPIOF_UNREADABLE_REG_SET	BIT(1) /* reg_set is unreadable */
 #define BGPIOF_UNREADABLE_REG_DIR	BIT(2) /* reg_dir is unreadable */
 #define BGPIOF_BIG_ENDIAN_BYTE_ORDER	BIT(3)
+#define BGPIOF_READ_OUTPUT_REG_SET     BIT(4) /* reg_set stores output value */
 
 #endif /* __BASIC_MMIO_GPIO_H */
diff --git a/include/linux/bottom_half.h b/include/linux/bottom_half.h
index 86c12c93e3cf..8fdcb783197d 100644
--- a/include/linux/bottom_half.h
+++ b/include/linux/bottom_half.h
@@ -2,7 +2,6 @@
 #define _LINUX_BH_H
 
 #include <linux/preempt.h>
-#include <linux/preempt_mask.h>
 
 #ifdef CONFIG_TRACE_IRQFLAGS
 extern void __local_bh_disable_ip(unsigned long ip, unsigned int cnt);
diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h
index 96c280b2c263..597a1e836f22 100644
--- a/include/linux/clockchips.h
+++ b/include/linux/clockchips.h
@@ -37,12 +37,15 @@ enum clock_event_mode {
  *		reached from DETACHED or SHUTDOWN.
  * ONESHOT:	Device is programmed to generate event only once. Can be reached
  *		from DETACHED or SHUTDOWN.
+ * ONESHOT_STOPPED: Device was programmed in ONESHOT mode and is temporarily
+ *		    stopped.
  */
 enum clock_event_state {
 	CLOCK_EVT_STATE_DETACHED,
 	CLOCK_EVT_STATE_SHUTDOWN,
 	CLOCK_EVT_STATE_PERIODIC,
 	CLOCK_EVT_STATE_ONESHOT,
+	CLOCK_EVT_STATE_ONESHOT_STOPPED,
 };
 
 /*
@@ -84,12 +87,13 @@ enum clock_event_state {
  * @mult:		nanosecond to cycles multiplier
  * @shift:		nanoseconds to cycles divisor (power of two)
  * @mode:		operating mode, relevant only to ->set_mode(), OBSOLETE
- * @state:		current state of the device, assigned by the core code
+ * @state_use_accessors:current state of the device, assigned by the core code
  * @features:		features
  * @retries:		number of forced programming retries
  * @set_mode:		legacy set mode function, only for modes <= CLOCK_EVT_MODE_RESUME.
  * @set_state_periodic:	switch state to periodic, if !set_mode
  * @set_state_oneshot:	switch state to oneshot, if !set_mode
+ * @set_state_oneshot_stopped: switch state to oneshot_stopped, if !set_mode
  * @set_state_shutdown:	switch state to shutdown, if !set_mode
  * @tick_resume:	resume clkevt device, if !set_mode
  * @broadcast:		function to broadcast events
@@ -113,7 +117,7 @@ struct clock_event_device {
 	u32			mult;
 	u32			shift;
 	enum clock_event_mode	mode;
-	enum clock_event_state	state;
+	enum clock_event_state	state_use_accessors;
 	unsigned int		features;
 	unsigned long		retries;
 
@@ -121,11 +125,12 @@ struct clock_event_device {
 	 * State transition callback(s): Only one of the two groups should be
 	 * defined:
 	 * - set_mode(), only for modes <= CLOCK_EVT_MODE_RESUME.
-	 * - set_state_{shutdown|periodic|oneshot}(), tick_resume().
+	 * - set_state_{shutdown|periodic|oneshot|oneshot_stopped}(), tick_resume().
 	 */
 	void			(*set_mode)(enum clock_event_mode mode, struct clock_event_device *);
 	int			(*set_state_periodic)(struct clock_event_device *);
 	int			(*set_state_oneshot)(struct clock_event_device *);
+	int			(*set_state_oneshot_stopped)(struct clock_event_device *);
 	int			(*set_state_shutdown)(struct clock_event_device *);
 	int			(*tick_resume)(struct clock_event_device *);
 
@@ -144,6 +149,32 @@ struct clock_event_device {
 	struct module		*owner;
 } ____cacheline_aligned;
 
+/* Helpers to verify state of a clockevent device */
+static inline bool clockevent_state_detached(struct clock_event_device *dev)
+{
+	return dev->state_use_accessors == CLOCK_EVT_STATE_DETACHED;
+}
+
+static inline bool clockevent_state_shutdown(struct clock_event_device *dev)
+{
+	return dev->state_use_accessors == CLOCK_EVT_STATE_SHUTDOWN;
+}
+
+static inline bool clockevent_state_periodic(struct clock_event_device *dev)
+{
+	return dev->state_use_accessors == CLOCK_EVT_STATE_PERIODIC;
+}
+
+static inline bool clockevent_state_oneshot(struct clock_event_device *dev)
+{
+	return dev->state_use_accessors == CLOCK_EVT_STATE_ONESHOT;
+}
+
+static inline bool clockevent_state_oneshot_stopped(struct clock_event_device *dev)
+{
+	return dev->state_use_accessors == CLOCK_EVT_STATE_ONESHOT_STOPPED;
+}
+
 /*
  * Calculate a multiplication factor for scaled math, which is used to convert
  * nanoseconds based values to clock ticks:
diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h
index d27d0152271f..278dd279a7a8 100644
--- a/include/linux/clocksource.h
+++ b/include/linux/clocksource.h
@@ -181,7 +181,6 @@ static inline s64 clocksource_cyc2ns(cycle_t cycles, u32 mult, u32 shift)
 
 extern int clocksource_unregister(struct clocksource*);
 extern void clocksource_touch_watchdog(void);
-extern struct clocksource* clocksource_get_next(void);
 extern void clocksource_change_rating(struct clocksource *cs, int rating);
 extern void clocksource_suspend(void);
 extern void clocksource_resume(void);
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 867722591be2..05be2352fef8 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -250,7 +250,23 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
 	({ union { typeof(x) __val; char __c[1]; } __u; __read_once_size(&(x), __u.__c, sizeof(x)); __u.__val; })
 
 #define WRITE_ONCE(x, val) \
-	({ typeof(x) __val = (val); __write_once_size(&(x), &__val, sizeof(__val)); __val; })
+	({ union { typeof(x) __val; char __c[1]; } __u = { .__val = (val) }; __write_once_size(&(x), __u.__c, sizeof(x)); __u.__val; })
+
+/**
+ * READ_ONCE_CTRL - Read a value heading a control dependency
+ * @x: The value to be read, heading the control dependency
+ *
+ * Control dependencies are tricky.  See Documentation/memory-barriers.txt
+ * for important information on how to use them.  Note that in many cases,
+ * use of smp_load_acquire() will be much simpler.  Control dependencies
+ * should be avoided except on the hottest of hotpaths.
+ */
+#define READ_ONCE_CTRL(x) \
+({ \
+	typeof(x) __val = READ_ONCE(x); \
+	smp_read_barrier_depends(); /* Enforce control dependency. */ \
+	__val; \
+})
 
 #endif /* __KERNEL__ */
 
@@ -450,7 +466,7 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
  * with an explicit memory barrier or atomic instruction that provides the
  * required ordering.
  *
- * If possible use READ_ONCE/ASSIGN_ONCE instead.
+ * If possible use READ_ONCE()/WRITE_ONCE() instead.
  */
 #define __ACCESS_ONCE(x) ({ \
 	 __maybe_unused typeof(x) __var = (__force typeof(x)) 0; \
diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h
index 2821838256b4..b96bd299966f 100644
--- a/include/linux/context_tracking.h
+++ b/include/linux/context_tracking.h
@@ -14,8 +14,6 @@ extern void context_tracking_enter(enum ctx_state state);
 extern void context_tracking_exit(enum ctx_state state);
 extern void context_tracking_user_enter(void);
 extern void context_tracking_user_exit(void);
-extern void __context_tracking_task_switch(struct task_struct *prev,
-					   struct task_struct *next);
 
 static inline void user_enter(void)
 {
@@ -51,19 +49,11 @@ static inline void exception_exit(enum ctx_state prev_ctx)
 	}
 }
 
-static inline void context_tracking_task_switch(struct task_struct *prev,
-						struct task_struct *next)
-{
-	if (context_tracking_is_enabled())
-		__context_tracking_task_switch(prev, next);
-}
 #else
 static inline void user_enter(void) { }
 static inline void user_exit(void) { }
 static inline enum ctx_state exception_enter(void) { return 0; }
 static inline void exception_exit(enum ctx_state prev_ctx) { }
-static inline void context_tracking_task_switch(struct task_struct *prev,
-						struct task_struct *next) { }
 #endif /* !CONFIG_CONTEXT_TRACKING */
 
 
diff --git a/include/linux/context_tracking_state.h b/include/linux/context_tracking_state.h
index 6b7b96a32b75..678ecdf90cf6 100644
--- a/include/linux/context_tracking_state.h
+++ b/include/linux/context_tracking_state.h
@@ -12,6 +12,7 @@ struct context_tracking {
 	 * may be further optimized using static keys.
 	 */
 	bool active;
+	int recursion;
 	enum ctx_state {
 		CONTEXT_KERNEL = 0,
 		CONTEXT_USER,
diff --git a/include/linux/crc-itu-t.h b/include/linux/crc-itu-t.h
index 84920f3cc83e..a9953c762eee 100644
--- a/include/linux/crc-itu-t.h
+++ b/include/linux/crc-itu-t.h
@@ -3,7 +3,7 @@
  *
  * Implements the standard CRC ITU-T V.41:
  *   Width 16
- *   Poly  0x0x1021 (x^16 + x^12 + x^15 + 1)
+ *   Poly  0x1021 (x^16 + x^12 + x^15 + 1)
  *   Init  0
  *
  * This source code is licensed under the GNU General Public License,
diff --git a/include/linux/crypto.h b/include/linux/crypto.h
index 10df5d2d093a..81ef938b0a8e 100644
--- a/include/linux/crypto.h
+++ b/include/linux/crypto.h
@@ -53,6 +53,7 @@
 #define CRYPTO_ALG_TYPE_SHASH		0x00000009
 #define CRYPTO_ALG_TYPE_AHASH		0x0000000a
 #define CRYPTO_ALG_TYPE_RNG		0x0000000c
+#define CRYPTO_ALG_TYPE_AKCIPHER	0x0000000d
 #define CRYPTO_ALG_TYPE_PCOMPRESS	0x0000000f
 
 #define CRYPTO_ALG_TYPE_HASH_MASK	0x0000000e
@@ -101,6 +102,12 @@
 #define CRYPTO_ALG_INTERNAL		0x00002000
 
 /*
+ * Temporary flag used to prevent legacy AEAD implementations from
+ * being used by user-space.
+ */
+#define CRYPTO_ALG_AEAD_NEW		0x00004000
+
+/*
  * Transform masks and values (for crt_flags).
  */
 #define CRYPTO_TFM_REQ_MASK		0x000fff00
@@ -138,9 +145,9 @@ struct crypto_async_request;
 struct crypto_aead;
 struct crypto_blkcipher;
 struct crypto_hash;
-struct crypto_rng;
 struct crypto_tfm;
 struct crypto_type;
+struct aead_request;
 struct aead_givcrypt_request;
 struct skcipher_givcrypt_request;
 
@@ -175,32 +182,6 @@ struct ablkcipher_request {
 	void *__ctx[] CRYPTO_MINALIGN_ATTR;
 };
 
-/**
- *	struct aead_request - AEAD request
- *	@base: Common attributes for async crypto requests
- *	@assoclen: Length in bytes of associated data for authentication
- *	@cryptlen: Length of data to be encrypted or decrypted
- *	@iv: Initialisation vector
- *	@assoc: Associated data
- *	@src: Source data
- *	@dst: Destination data
- *	@__ctx: Start of private context data
- */
-struct aead_request {
-	struct crypto_async_request base;
-
-	unsigned int assoclen;
-	unsigned int cryptlen;
-
-	u8 *iv;
-
-	struct scatterlist *assoc;
-	struct scatterlist *src;
-	struct scatterlist *dst;
-
-	void *__ctx[] CRYPTO_MINALIGN_ATTR;
-};
-
 struct blkcipher_desc {
 	struct crypto_blkcipher *tfm;
 	void *info;
@@ -294,7 +275,7 @@ struct ablkcipher_alg {
 };
 
 /**
- * struct aead_alg - AEAD cipher definition
+ * struct old_aead_alg - AEAD cipher definition
  * @maxauthsize: Set the maximum authentication tag size supported by the
  *		 transformation. A transformation may support smaller tag sizes.
  *		 As the authentication tag is a message digest to ensure the
@@ -319,7 +300,7 @@ struct ablkcipher_alg {
  * All fields except @givencrypt , @givdecrypt , @geniv and @ivsize are
  * mandatory and must be filled.
  */
-struct aead_alg {
+struct old_aead_alg {
 	int (*setkey)(struct crypto_aead *tfm, const u8 *key,
 	              unsigned int keylen);
 	int (*setauthsize)(struct crypto_aead *tfm, unsigned int authsize);
@@ -426,40 +407,12 @@ struct compress_alg {
 			      unsigned int slen, u8 *dst, unsigned int *dlen);
 };
 
-/**
- * struct rng_alg - random number generator definition
- * @rng_make_random: The function defined by this variable obtains a random
- *		     number. The random number generator transform must generate
- *		     the random number out of the context provided with this
- *		     call.
- * @rng_reset: Reset of the random number generator by clearing the entire state.
- *	       With the invocation of this function call, the random number
- *             generator shall completely reinitialize its state. If the random
- *	       number generator requires a seed for setting up a new state,
- *	       the seed must be provided by the consumer while invoking this
- *	       function. The required size of the seed is defined with
- *	       @seedsize .
- * @seedsize: The seed size required for a random number generator
- *	      initialization defined with this variable. Some random number
- *	      generators like the SP800-90A DRBG does not require a seed as the
- *	      seeding is implemented internally without the need of support by
- *	      the consumer. In this case, the seed size is set to zero.
- */
-struct rng_alg {
-	int (*rng_make_random)(struct crypto_rng *tfm, u8 *rdata,
-			       unsigned int dlen);
-	int (*rng_reset)(struct crypto_rng *tfm, u8 *seed, unsigned int slen);
-
-	unsigned int seedsize;
-};
-
 
 #define cra_ablkcipher	cra_u.ablkcipher
 #define cra_aead	cra_u.aead
 #define cra_blkcipher	cra_u.blkcipher
 #define cra_cipher	cra_u.cipher
 #define cra_compress	cra_u.compress
-#define cra_rng		cra_u.rng
 
 /**
  * struct crypto_alg - definition of a cryptograpic cipher algorithm
@@ -505,7 +458,7 @@ struct rng_alg {
  *		     transformation algorithm.
  * @cra_type: Type of the cryptographic transformation. This is a pointer to
  *	      struct crypto_type, which implements callbacks common for all
- *	      trasnformation types. There are multiple options:
+ *	      transformation types. There are multiple options:
  *	      &crypto_blkcipher_type, &crypto_ablkcipher_type,
  *	      &crypto_ahash_type, &crypto_aead_type, &crypto_rng_type.
  *	      This field might be empty. In that case, there are no common
@@ -555,11 +508,10 @@ struct crypto_alg {
 
 	union {
 		struct ablkcipher_alg ablkcipher;
-		struct aead_alg aead;
+		struct old_aead_alg aead;
 		struct blkcipher_alg blkcipher;
 		struct cipher_alg cipher;
 		struct compress_alg compress;
-		struct rng_alg rng;
 	} cra_u;
 
 	int (*cra_init)(struct crypto_tfm *tfm);
@@ -567,7 +519,7 @@ struct crypto_alg {
 	void (*cra_destroy)(struct crypto_alg *alg);
 	
 	struct module *cra_module;
-};
+} CRYPTO_MINALIGN_ATTR;
 
 /*
  * Algorithm registration interface.
@@ -602,21 +554,6 @@ struct ablkcipher_tfm {
 	unsigned int reqsize;
 };
 
-struct aead_tfm {
-	int (*setkey)(struct crypto_aead *tfm, const u8 *key,
-	              unsigned int keylen);
-	int (*encrypt)(struct aead_request *req);
-	int (*decrypt)(struct aead_request *req);
-	int (*givencrypt)(struct aead_givcrypt_request *req);
-	int (*givdecrypt)(struct aead_givcrypt_request *req);
-
-	struct crypto_aead *base;
-
-	unsigned int ivsize;
-	unsigned int authsize;
-	unsigned int reqsize;
-};
-
 struct blkcipher_tfm {
 	void *iv;
 	int (*setkey)(struct crypto_tfm *tfm, const u8 *key,
@@ -655,19 +592,11 @@ struct compress_tfm {
 	                      u8 *dst, unsigned int *dlen);
 };
 
-struct rng_tfm {
-	int (*rng_gen_random)(struct crypto_rng *tfm, u8 *rdata,
-			      unsigned int dlen);
-	int (*rng_reset)(struct crypto_rng *tfm, u8 *seed, unsigned int slen);
-};
-
 #define crt_ablkcipher	crt_u.ablkcipher
-#define crt_aead	crt_u.aead
 #define crt_blkcipher	crt_u.blkcipher
 #define crt_cipher	crt_u.cipher
 #define crt_hash	crt_u.hash
 #define crt_compress	crt_u.compress
-#define crt_rng		crt_u.rng
 
 struct crypto_tfm {
 
@@ -675,12 +604,10 @@ struct crypto_tfm {
 	
 	union {
 		struct ablkcipher_tfm ablkcipher;
-		struct aead_tfm aead;
 		struct blkcipher_tfm blkcipher;
 		struct cipher_tfm cipher;
 		struct hash_tfm hash;
 		struct compress_tfm compress;
-		struct rng_tfm rng;
 	} crt_u;
 
 	void (*exit)(struct crypto_tfm *tfm);
@@ -694,10 +621,6 @@ struct crypto_ablkcipher {
 	struct crypto_tfm base;
 };
 
-struct crypto_aead {
-	struct crypto_tfm base;
-};
-
 struct crypto_blkcipher {
 	struct crypto_tfm base;
 };
@@ -714,10 +637,6 @@ struct crypto_hash {
 	struct crypto_tfm base;
 };
 
-struct crypto_rng {
-	struct crypto_tfm base;
-};
-
 enum {
 	CRYPTOA_UNSPEC,
 	CRYPTOA_ALG,
@@ -1194,400 +1113,6 @@ static inline void ablkcipher_request_set_crypt(
 }
 
 /**
- * DOC: Authenticated Encryption With Associated Data (AEAD) Cipher API
- *
- * The AEAD cipher API is used with the ciphers of type CRYPTO_ALG_TYPE_AEAD
- * (listed as type "aead" in /proc/crypto)
- *
- * The most prominent examples for this type of encryption is GCM and CCM.
- * However, the kernel supports other types of AEAD ciphers which are defined
- * with the following cipher string:
- *
- *	authenc(keyed message digest, block cipher)
- *
- * For example: authenc(hmac(sha256), cbc(aes))
- *
- * The example code provided for the asynchronous block cipher operation
- * applies here as well. Naturally all *ablkcipher* symbols must be exchanged
- * the *aead* pendants discussed in the following. In addtion, for the AEAD
- * operation, the aead_request_set_assoc function must be used to set the
- * pointer to the associated data memory location before performing the
- * encryption or decryption operation. In case of an encryption, the associated
- * data memory is filled during the encryption operation. For decryption, the
- * associated data memory must contain data that is used to verify the integrity
- * of the decrypted data. Another deviation from the asynchronous block cipher
- * operation is that the caller should explicitly check for -EBADMSG of the
- * crypto_aead_decrypt. That error indicates an authentication error, i.e.
- * a breach in the integrity of the message. In essence, that -EBADMSG error
- * code is the key bonus an AEAD cipher has over "standard" block chaining
- * modes.
- */
-
-static inline struct crypto_aead *__crypto_aead_cast(struct crypto_tfm *tfm)
-{
-	return (struct crypto_aead *)tfm;
-}
-
-/**
- * crypto_alloc_aead() - allocate AEAD cipher handle
- * @alg_name: is the cra_name / name or cra_driver_name / driver name of the
- *	     AEAD cipher
- * @type: specifies the type of the cipher
- * @mask: specifies the mask for the cipher
- *
- * Allocate a cipher handle for an AEAD. The returned struct
- * crypto_aead is the cipher handle that is required for any subsequent
- * API invocation for that AEAD.
- *
- * Return: allocated cipher handle in case of success; IS_ERR() is true in case
- *	   of an error, PTR_ERR() returns the error code.
- */
-struct crypto_aead *crypto_alloc_aead(const char *alg_name, u32 type, u32 mask);
-
-static inline struct crypto_tfm *crypto_aead_tfm(struct crypto_aead *tfm)
-{
-	return &tfm->base;
-}
-
-/**
- * crypto_free_aead() - zeroize and free aead handle
- * @tfm: cipher handle to be freed
- */
-static inline void crypto_free_aead(struct crypto_aead *tfm)
-{
-	crypto_free_tfm(crypto_aead_tfm(tfm));
-}
-
-static inline struct aead_tfm *crypto_aead_crt(struct crypto_aead *tfm)
-{
-	return &crypto_aead_tfm(tfm)->crt_aead;
-}
-
-/**
- * crypto_aead_ivsize() - obtain IV size
- * @tfm: cipher handle
- *
- * The size of the IV for the aead referenced by the cipher handle is
- * returned. This IV size may be zero if the cipher does not need an IV.
- *
- * Return: IV size in bytes
- */
-static inline unsigned int crypto_aead_ivsize(struct crypto_aead *tfm)
-{
-	return crypto_aead_crt(tfm)->ivsize;
-}
-
-/**
- * crypto_aead_authsize() - obtain maximum authentication data size
- * @tfm: cipher handle
- *
- * The maximum size of the authentication data for the AEAD cipher referenced
- * by the AEAD cipher handle is returned. The authentication data size may be
- * zero if the cipher implements a hard-coded maximum.
- *
- * The authentication data may also be known as "tag value".
- *
- * Return: authentication data size / tag size in bytes
- */
-static inline unsigned int crypto_aead_authsize(struct crypto_aead *tfm)
-{
-	return crypto_aead_crt(tfm)->authsize;
-}
-
-/**
- * crypto_aead_blocksize() - obtain block size of cipher
- * @tfm: cipher handle
- *
- * The block size for the AEAD referenced with the cipher handle is returned.
- * The caller may use that information to allocate appropriate memory for the
- * data returned by the encryption or decryption operation
- *
- * Return: block size of cipher
- */
-static inline unsigned int crypto_aead_blocksize(struct crypto_aead *tfm)
-{
-	return crypto_tfm_alg_blocksize(crypto_aead_tfm(tfm));
-}
-
-static inline unsigned int crypto_aead_alignmask(struct crypto_aead *tfm)
-{
-	return crypto_tfm_alg_alignmask(crypto_aead_tfm(tfm));
-}
-
-static inline u32 crypto_aead_get_flags(struct crypto_aead *tfm)
-{
-	return crypto_tfm_get_flags(crypto_aead_tfm(tfm));
-}
-
-static inline void crypto_aead_set_flags(struct crypto_aead *tfm, u32 flags)
-{
-	crypto_tfm_set_flags(crypto_aead_tfm(tfm), flags);
-}
-
-static inline void crypto_aead_clear_flags(struct crypto_aead *tfm, u32 flags)
-{
-	crypto_tfm_clear_flags(crypto_aead_tfm(tfm), flags);
-}
-
-/**
- * crypto_aead_setkey() - set key for cipher
- * @tfm: cipher handle
- * @key: buffer holding the key
- * @keylen: length of the key in bytes
- *
- * The caller provided key is set for the AEAD referenced by the cipher
- * handle.
- *
- * Note, the key length determines the cipher type. Many block ciphers implement
- * different cipher modes depending on the key size, such as AES-128 vs AES-192
- * vs. AES-256. When providing a 16 byte key for an AES cipher handle, AES-128
- * is performed.
- *
- * Return: 0 if the setting of the key was successful; < 0 if an error occurred
- */
-static inline int crypto_aead_setkey(struct crypto_aead *tfm, const u8 *key,
-				     unsigned int keylen)
-{
-	struct aead_tfm *crt = crypto_aead_crt(tfm);
-
-	return crt->setkey(crt->base, key, keylen);
-}
-
-/**
- * crypto_aead_setauthsize() - set authentication data size
- * @tfm: cipher handle
- * @authsize: size of the authentication data / tag in bytes
- *
- * Set the authentication data size / tag size. AEAD requires an authentication
- * tag (or MAC) in addition to the associated data.
- *
- * Return: 0 if the setting of the key was successful; < 0 if an error occurred
- */
-int crypto_aead_setauthsize(struct crypto_aead *tfm, unsigned int authsize);
-
-static inline struct crypto_aead *crypto_aead_reqtfm(struct aead_request *req)
-{
-	return __crypto_aead_cast(req->base.tfm);
-}
-
-/**
- * crypto_aead_encrypt() - encrypt plaintext
- * @req: reference to the aead_request handle that holds all information
- *	 needed to perform the cipher operation
- *
- * Encrypt plaintext data using the aead_request handle. That data structure
- * and how it is filled with data is discussed with the aead_request_*
- * functions.
- *
- * IMPORTANT NOTE The encryption operation creates the authentication data /
- *		  tag. That data is concatenated with the created ciphertext.
- *		  The ciphertext memory size is therefore the given number of
- *		  block cipher blocks + the size defined by the
- *		  crypto_aead_setauthsize invocation. The caller must ensure
- *		  that sufficient memory is available for the ciphertext and
- *		  the authentication tag.
- *
- * Return: 0 if the cipher operation was successful; < 0 if an error occurred
- */
-static inline int crypto_aead_encrypt(struct aead_request *req)
-{
-	return crypto_aead_crt(crypto_aead_reqtfm(req))->encrypt(req);
-}
-
-/**
- * crypto_aead_decrypt() - decrypt ciphertext
- * @req: reference to the ablkcipher_request handle that holds all information
- *	 needed to perform the cipher operation
- *
- * Decrypt ciphertext data using the aead_request handle. That data structure
- * and how it is filled with data is discussed with the aead_request_*
- * functions.
- *
- * IMPORTANT NOTE The caller must concatenate the ciphertext followed by the
- *		  authentication data / tag. That authentication data / tag
- *		  must have the size defined by the crypto_aead_setauthsize
- *		  invocation.
- *
- *
- * Return: 0 if the cipher operation was successful; -EBADMSG: The AEAD
- *	   cipher operation performs the authentication of the data during the
- *	   decryption operation. Therefore, the function returns this error if
- *	   the authentication of the ciphertext was unsuccessful (i.e. the
- *	   integrity of the ciphertext or the associated data was violated);
- *	   < 0 if an error occurred.
- */
-static inline int crypto_aead_decrypt(struct aead_request *req)
-{
-	if (req->cryptlen < crypto_aead_authsize(crypto_aead_reqtfm(req)))
-		return -EINVAL;
-
-	return crypto_aead_crt(crypto_aead_reqtfm(req))->decrypt(req);
-}
-
-/**
- * DOC: Asynchronous AEAD Request Handle
- *
- * The aead_request data structure contains all pointers to data required for
- * the AEAD cipher operation. This includes the cipher handle (which can be
- * used by multiple aead_request instances), pointer to plaintext and
- * ciphertext, asynchronous callback function, etc. It acts as a handle to the
- * aead_request_* API calls in a similar way as AEAD handle to the
- * crypto_aead_* API calls.
- */
-
-/**
- * crypto_aead_reqsize() - obtain size of the request data structure
- * @tfm: cipher handle
- *
- * Return: number of bytes
- */
-static inline unsigned int crypto_aead_reqsize(struct crypto_aead *tfm)
-{
-	return crypto_aead_crt(tfm)->reqsize;
-}
-
-/**
- * aead_request_set_tfm() - update cipher handle reference in request
- * @req: request handle to be modified
- * @tfm: cipher handle that shall be added to the request handle
- *
- * Allow the caller to replace the existing aead handle in the request
- * data structure with a different one.
- */
-static inline void aead_request_set_tfm(struct aead_request *req,
-					struct crypto_aead *tfm)
-{
-	req->base.tfm = crypto_aead_tfm(crypto_aead_crt(tfm)->base);
-}
-
-/**
- * aead_request_alloc() - allocate request data structure
- * @tfm: cipher handle to be registered with the request
- * @gfp: memory allocation flag that is handed to kmalloc by the API call.
- *
- * Allocate the request data structure that must be used with the AEAD
- * encrypt and decrypt API calls. During the allocation, the provided aead
- * handle is registered in the request data structure.
- *
- * Return: allocated request handle in case of success; IS_ERR() is true in case
- *	   of an error, PTR_ERR() returns the error code.
- */
-static inline struct aead_request *aead_request_alloc(struct crypto_aead *tfm,
-						      gfp_t gfp)
-{
-	struct aead_request *req;
-
-	req = kmalloc(sizeof(*req) + crypto_aead_reqsize(tfm), gfp);
-
-	if (likely(req))
-		aead_request_set_tfm(req, tfm);
-
-	return req;
-}
-
-/**
- * aead_request_free() - zeroize and free request data structure
- * @req: request data structure cipher handle to be freed
- */
-static inline void aead_request_free(struct aead_request *req)
-{
-	kzfree(req);
-}
-
-/**
- * aead_request_set_callback() - set asynchronous callback function
- * @req: request handle
- * @flags: specify zero or an ORing of the flags
- *	   CRYPTO_TFM_REQ_MAY_BACKLOG the request queue may back log and
- *	   increase the wait queue beyond the initial maximum size;
- *	   CRYPTO_TFM_REQ_MAY_SLEEP the request processing may sleep
- * @compl: callback function pointer to be registered with the request handle
- * @data: The data pointer refers to memory that is not used by the kernel
- *	  crypto API, but provided to the callback function for it to use. Here,
- *	  the caller can provide a reference to memory the callback function can
- *	  operate on. As the callback function is invoked asynchronously to the
- *	  related functionality, it may need to access data structures of the
- *	  related functionality which can be referenced using this pointer. The
- *	  callback function can access the memory via the "data" field in the
- *	  crypto_async_request data structure provided to the callback function.
- *
- * Setting the callback function that is triggered once the cipher operation
- * completes
- *
- * The callback function is registered with the aead_request handle and
- * must comply with the following template
- *
- *	void callback_function(struct crypto_async_request *req, int error)
- */
-static inline void aead_request_set_callback(struct aead_request *req,
-					     u32 flags,
-					     crypto_completion_t compl,
-					     void *data)
-{
-	req->base.complete = compl;
-	req->base.data = data;
-	req->base.flags = flags;
-}
-
-/**
- * aead_request_set_crypt - set data buffers
- * @req: request handle
- * @src: source scatter / gather list
- * @dst: destination scatter / gather list
- * @cryptlen: number of bytes to process from @src
- * @iv: IV for the cipher operation which must comply with the IV size defined
- *      by crypto_aead_ivsize()
- *
- * Setting the source data and destination data scatter / gather lists.
- *
- * For encryption, the source is treated as the plaintext and the
- * destination is the ciphertext. For a decryption operation, the use is
- * reversed - the source is the ciphertext and the destination is the plaintext.
- *
- * IMPORTANT NOTE AEAD requires an authentication tag (MAC). For decryption,
- *		  the caller must concatenate the ciphertext followed by the
- *		  authentication tag and provide the entire data stream to the
- *		  decryption operation (i.e. the data length used for the
- *		  initialization of the scatterlist and the data length for the
- *		  decryption operation is identical). For encryption, however,
- *		  the authentication tag is created while encrypting the data.
- *		  The destination buffer must hold sufficient space for the
- *		  ciphertext and the authentication tag while the encryption
- *		  invocation must only point to the plaintext data size. The
- *		  following code snippet illustrates the memory usage
- *		  buffer = kmalloc(ptbuflen + (enc ? authsize : 0));
- *		  sg_init_one(&sg, buffer, ptbuflen + (enc ? authsize : 0));
- *		  aead_request_set_crypt(req, &sg, &sg, ptbuflen, iv);
- */
-static inline void aead_request_set_crypt(struct aead_request *req,
-					  struct scatterlist *src,
-					  struct scatterlist *dst,
-					  unsigned int cryptlen, u8 *iv)
-{
-	req->src = src;
-	req->dst = dst;
-	req->cryptlen = cryptlen;
-	req->iv = iv;
-}
-
-/**
- * aead_request_set_assoc() - set the associated data scatter / gather list
- * @req: request handle
- * @assoc: associated data scatter / gather list
- * @assoclen: number of bytes to process from @assoc
- *
- * For encryption, the memory is filled with the associated data. For
- * decryption, the memory must point to the associated data.
- */
-static inline void aead_request_set_assoc(struct aead_request *req,
-					  struct scatterlist *assoc,
-					  unsigned int assoclen)
-{
-	req->assoc = assoc;
-	req->assoclen = assoclen;
-}
-
-/**
  * DOC: Synchronous Block Cipher API
  *
  * The synchronous block cipher API is used with the ciphers of type
diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h
index cb25af461054..420311bcee38 100644
--- a/include/linux/debugfs.h
+++ b/include/linux/debugfs.h
@@ -45,7 +45,6 @@ extern struct dentry *arch_debugfs_dir;
 
 /* declared over in file.c */
 extern const struct file_operations debugfs_file_operations;
-extern const struct inode_operations debugfs_link_operations;
 
 struct dentry *debugfs_create_file(const char *name, umode_t mode,
 				   struct dentry *parent, void *data,
diff --git a/include/linux/dmar.h b/include/linux/dmar.h
index 30624954dec5..e9bc9292bd3a 100644
--- a/include/linux/dmar.h
+++ b/include/linux/dmar.h
@@ -185,33 +185,85 @@ static inline int dmar_device_remove(void *handle)
 
 struct irte {
 	union {
+		/* Shared between remapped and posted mode*/
 		struct {
-			__u64	present 	: 1,
-				fpd		: 1,
-				dst_mode	: 1,
-				redir_hint	: 1,
-				trigger_mode	: 1,
-				dlvry_mode	: 3,
-				avail		: 4,
-				__reserved_1	: 4,
-				vector		: 8,
-				__reserved_2	: 8,
-				dest_id		: 32;
+			__u64	present		: 1,  /*  0      */
+				fpd		: 1,  /*  1      */
+				__res0		: 6,  /*  2 -  6 */
+				avail		: 4,  /*  8 - 11 */
+				__res1		: 3,  /* 12 - 14 */
+				pst		: 1,  /* 15      */
+				vector		: 8,  /* 16 - 23 */
+				__res2		: 40; /* 24 - 63 */
+		};
+
+		/* Remapped mode */
+		struct {
+			__u64	r_present	: 1,  /*  0      */
+				r_fpd		: 1,  /*  1      */
+				dst_mode	: 1,  /*  2      */
+				redir_hint	: 1,  /*  3      */
+				trigger_mode	: 1,  /*  4      */
+				dlvry_mode	: 3,  /*  5 -  7 */
+				r_avail		: 4,  /*  8 - 11 */
+				r_res0		: 4,  /* 12 - 15 */
+				r_vector	: 8,  /* 16 - 23 */
+				r_res1		: 8,  /* 24 - 31 */
+				dest_id		: 32; /* 32 - 63 */
+		};
+
+		/* Posted mode */
+		struct {
+			__u64	p_present	: 1,  /*  0      */
+				p_fpd		: 1,  /*  1      */
+				p_res0		: 6,  /*  2 -  7 */
+				p_avail		: 4,  /*  8 - 11 */
+				p_res1		: 2,  /* 12 - 13 */
+				p_urgent	: 1,  /* 14      */
+				p_pst		: 1,  /* 15      */
+				p_vector	: 8,  /* 16 - 23 */
+				p_res2		: 14, /* 24 - 37 */
+				pda_l		: 26; /* 38 - 63 */
 		};
 		__u64 low;
 	};
 
 	union {
+		/* Shared between remapped and posted mode*/
 		struct {
-			__u64	sid		: 16,
-				sq		: 2,
-				svt		: 2,
-				__reserved_3	: 44;
+			__u64	sid		: 16,  /* 64 - 79  */
+				sq		: 2,   /* 80 - 81  */
+				svt		: 2,   /* 82 - 83  */
+				__res3		: 44;  /* 84 - 127 */
+		};
+
+		/* Posted mode*/
+		struct {
+			__u64	p_sid		: 16,  /* 64 - 79  */
+				p_sq		: 2,   /* 80 - 81  */
+				p_svt		: 2,   /* 82 - 83  */
+				p_res3		: 12,  /* 84 - 95  */
+				pda_h		: 32;  /* 96 - 127 */
 		};
 		__u64 high;
 	};
 };
 
+static inline void dmar_copy_shared_irte(struct irte *dst, struct irte *src)
+{
+	dst->present	= src->present;
+	dst->fpd	= src->fpd;
+	dst->avail	= src->avail;
+	dst->pst	= src->pst;
+	dst->vector	= src->vector;
+	dst->sid	= src->sid;
+	dst->sq		= src->sq;
+	dst->svt	= src->svt;
+}
+
+#define PDA_LOW_BIT    26
+#define PDA_HIGH_BIT   32
+
 enum {
 	IRQ_REMAP_XAPIC_MODE,
 	IRQ_REMAP_X2APIC_MODE,
@@ -227,6 +279,7 @@ extern void dmar_msi_read(int irq, struct msi_msg *msg);
 extern void dmar_msi_write(int irq, struct msi_msg *msg);
 extern int dmar_set_interrupt(struct intel_iommu *iommu);
 extern irqreturn_t dmar_fault(int irq, void *dev_id);
-extern int arch_setup_dmar_msi(unsigned int irq);
+extern int dmar_alloc_hwirq(int id, int node, void *arg);
+extern void dmar_free_hwirq(int irq);
 
 #endif /* __DMAR_H__ */
diff --git a/include/linux/efi.h b/include/linux/efi.h
index af5be0368dec..2092965afca3 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -583,6 +583,9 @@ void efi_native_runtime_setup(void);
 #define EFI_FILE_INFO_ID \
     EFI_GUID(  0x9576e92, 0x6d3f, 0x11d2, 0x8e, 0x39, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b )
 
+#define EFI_SYSTEM_RESOURCE_TABLE_GUID \
+    EFI_GUID(  0xb122a263, 0x3661, 0x4f68, 0x99, 0x29, 0x78, 0xf8, 0xb0, 0xd6, 0x21, 0x80 )
+
 #define EFI_FILE_SYSTEM_GUID \
     EFI_GUID(  0x964e5b22, 0x6459, 0x11d2, 0x8e, 0x39, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b )
 
@@ -823,6 +826,7 @@ extern struct efi {
 	unsigned long fw_vendor;	/* fw_vendor */
 	unsigned long runtime;		/* runtime table */
 	unsigned long config_table;	/* config tables */
+	unsigned long esrt;		/* ESRT table */
 	efi_get_time_t *get_time;
 	efi_set_time_t *set_time;
 	efi_get_wakeup_time_t *get_wakeup_time;
@@ -875,6 +879,11 @@ static inline efi_status_t efi_query_variable_store(u32 attributes, unsigned lon
 #endif
 extern void __iomem *efi_lookup_mapped_addr(u64 phys_addr);
 extern int efi_config_init(efi_config_table_type_t *arch_tables);
+#ifdef CONFIG_EFI_ESRT
+extern void __init efi_esrt_init(void);
+#else
+static inline void efi_esrt_init(void) { }
+#endif
 extern int efi_config_parse_tables(void *config_tables, int count, int sz,
 				   efi_config_table_type_t *arch_tables);
 extern u64 efi_get_iobase (void);
@@ -882,12 +891,15 @@ extern u32 efi_mem_type (unsigned long phys_addr);
 extern u64 efi_mem_attributes (unsigned long phys_addr);
 extern u64 efi_mem_attribute (unsigned long phys_addr, unsigned long size);
 extern int __init efi_uart_console_only (void);
+extern u64 efi_mem_desc_end(efi_memory_desc_t *md);
+extern int efi_mem_desc_lookup(u64 phys_addr, efi_memory_desc_t *out_md);
 extern void efi_initialize_iomem_resources(struct resource *code_resource,
 		struct resource *data_resource, struct resource *bss_resource);
 extern void efi_get_time(struct timespec *now);
 extern void efi_reserve_boot_services(void);
 extern int efi_get_fdt_params(struct efi_fdt_params *params, int verbose);
 extern struct efi_memory_map memmap;
+extern struct kobject *efi_kobj;
 
 extern int efi_reboot_quirk_mode;
 extern bool efi_poweroff_required(void);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 35ec87e490b1..b577e801b4af 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -38,7 +38,6 @@ struct backing_dev_info;
 struct export_operations;
 struct hd_geometry;
 struct iovec;
-struct nameidata;
 struct kiocb;
 struct kobject;
 struct pipe_inode_info;
@@ -656,6 +655,7 @@ struct inode {
 		struct pipe_inode_info	*i_pipe;
 		struct block_device	*i_bdev;
 		struct cdev		*i_cdev;
+		char			*i_link;
 	};
 
 	__u32			i_generation;
@@ -1607,12 +1607,12 @@ struct file_operations {
 
 struct inode_operations {
 	struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int);
-	void * (*follow_link) (struct dentry *, struct nameidata *);
+	const char * (*follow_link) (struct dentry *, void **);
 	int (*permission) (struct inode *, int);
 	struct posix_acl * (*get_acl)(struct inode *, int);
 
 	int (*readlink) (struct dentry *, char __user *,int);
-	void (*put_link) (struct dentry *, struct nameidata *, void *);
+	void (*put_link) (struct inode *, void *);
 
 	int (*create) (struct inode *,struct dentry *, umode_t, bool);
 	int (*link) (struct dentry *,struct inode *,struct dentry *);
@@ -1879,6 +1879,7 @@ enum file_time_flags {
 	S_VERSION = 8,
 };
 
+extern bool atime_needs_update(const struct path *, struct inode *);
 extern void touch_atime(const struct path *);
 static inline void file_accessed(struct file *file)
 {
@@ -2704,13 +2705,14 @@ extern const struct file_operations generic_ro_fops;
 
 extern int readlink_copy(char __user *, int, const char *);
 extern int page_readlink(struct dentry *, char __user *, int);
-extern void *page_follow_link_light(struct dentry *, struct nameidata *);
-extern void page_put_link(struct dentry *, struct nameidata *, void *);
+extern const char *page_follow_link_light(struct dentry *, void **);
+extern void page_put_link(struct inode *, void *);
 extern int __page_symlink(struct inode *inode, const char *symname, int len,
 		int nofs);
 extern int page_symlink(struct inode *inode, const char *symname, int len);
 extern const struct inode_operations page_symlink_inode_operations;
-extern void kfree_put_link(struct dentry *, struct nameidata *, void *);
+extern void kfree_put_link(struct inode *, void *);
+extern void free_page_put_link(struct inode *, void *);
 extern int generic_readlink(struct dentry *, char __user *, int);
 extern void generic_fillattr(struct inode *, struct kstat *);
 int vfs_getattr_nosec(struct path *path, struct kstat *stat);
@@ -2721,6 +2723,8 @@ void __inode_sub_bytes(struct inode *inode, loff_t bytes);
 void inode_sub_bytes(struct inode *inode, loff_t bytes);
 loff_t inode_get_bytes(struct inode *inode);
 void inode_set_bytes(struct inode *inode, loff_t bytes);
+const char *simple_follow_link(struct dentry *, void **);
+extern const struct inode_operations simple_symlink_inode_operations;
 
 extern int iterate_dir(struct file *, struct dir_context *);
 
diff --git a/include/linux/gpio.h b/include/linux/gpio.h
index ab81339a8590..d12b5d566e4b 100644
--- a/include/linux/gpio.h
+++ b/include/linux/gpio.h
@@ -196,13 +196,6 @@ static inline int gpio_export_link(struct device *dev, const char *name,
 	return -EINVAL;
 }
 
-static inline int gpio_sysfs_set_active_low(unsigned gpio, int value)
-{
-	/* GPIO can never have been requested */
-	WARN_ON(1);
-	return -EINVAL;
-}
-
 static inline void gpio_unexport(unsigned gpio)
 {
 	/* GPIO can never have been exported */
diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h
index 3a7c9ffd5ab9..fd098169fe87 100644
--- a/include/linux/gpio/consumer.h
+++ b/include/linux/gpio/consumer.h
@@ -100,24 +100,25 @@ int gpiod_direction_output_raw(struct gpio_desc *desc, int value);
 /* Value get/set from non-sleeping context */
 int gpiod_get_value(const struct gpio_desc *desc);
 void gpiod_set_value(struct gpio_desc *desc, int value);
-void gpiod_set_array(unsigned int array_size,
-		     struct gpio_desc **desc_array, int *value_array);
+void gpiod_set_array_value(unsigned int array_size,
+			   struct gpio_desc **desc_array, int *value_array);
 int gpiod_get_raw_value(const struct gpio_desc *desc);
 void gpiod_set_raw_value(struct gpio_desc *desc, int value);
-void gpiod_set_raw_array(unsigned int array_size,
-			 struct gpio_desc **desc_array, int *value_array);
+void gpiod_set_raw_array_value(unsigned int array_size,
+			       struct gpio_desc **desc_array,
+			       int *value_array);
 
 /* Value get/set from sleeping context */
 int gpiod_get_value_cansleep(const struct gpio_desc *desc);
 void gpiod_set_value_cansleep(struct gpio_desc *desc, int value);
-void gpiod_set_array_cansleep(unsigned int array_size,
-			      struct gpio_desc **desc_array,
-			      int *value_array);
+void gpiod_set_array_value_cansleep(unsigned int array_size,
+				    struct gpio_desc **desc_array,
+				    int *value_array);
 int gpiod_get_raw_value_cansleep(const struct gpio_desc *desc);
 void gpiod_set_raw_value_cansleep(struct gpio_desc *desc, int value);
-void gpiod_set_raw_array_cansleep(unsigned int array_size,
-				  struct gpio_desc **desc_array,
-				  int *value_array);
+void gpiod_set_raw_array_value_cansleep(unsigned int array_size,
+					struct gpio_desc **desc_array,
+					int *value_array);
 
 int gpiod_set_debounce(struct gpio_desc *desc, unsigned debounce);
 
@@ -304,9 +305,9 @@ static inline void gpiod_set_value(struct gpio_desc *desc, int value)
 	/* GPIO can never have been requested */
 	WARN_ON(1);
 }
-static inline void gpiod_set_array(unsigned int array_size,
-				   struct gpio_desc **desc_array,
-				   int *value_array)
+static inline void gpiod_set_array_value(unsigned int array_size,
+					 struct gpio_desc **desc_array,
+					 int *value_array)
 {
 	/* GPIO can never have been requested */
 	WARN_ON(1);
@@ -322,9 +323,9 @@ static inline void gpiod_set_raw_value(struct gpio_desc *desc, int value)
 	/* GPIO can never have been requested */
 	WARN_ON(1);
 }
-static inline void gpiod_set_raw_array(unsigned int array_size,
-				       struct gpio_desc **desc_array,
-				       int *value_array)
+static inline void gpiod_set_raw_array_value(unsigned int array_size,
+					     struct gpio_desc **desc_array,
+					     int *value_array)
 {
 	/* GPIO can never have been requested */
 	WARN_ON(1);
@@ -341,7 +342,7 @@ static inline void gpiod_set_value_cansleep(struct gpio_desc *desc, int value)
 	/* GPIO can never have been requested */
 	WARN_ON(1);
 }
-static inline void gpiod_set_array_cansleep(unsigned int array_size,
+static inline void gpiod_set_array_value_cansleep(unsigned int array_size,
 					    struct gpio_desc **desc_array,
 					    int *value_array)
 {
@@ -360,7 +361,7 @@ static inline void gpiod_set_raw_value_cansleep(struct gpio_desc *desc,
 	/* GPIO can never have been requested */
 	WARN_ON(1);
 }
-static inline void gpiod_set_raw_array_cansleep(unsigned int array_size,
+static inline void gpiod_set_raw_array_value_cansleep(unsigned int array_size,
 						struct gpio_desc **desc_array,
 						int *value_array)
 {
@@ -449,7 +450,6 @@ static inline int desc_to_gpio(const struct gpio_desc *desc)
 int gpiod_export(struct gpio_desc *desc, bool direction_may_change);
 int gpiod_export_link(struct device *dev, const char *name,
 		      struct gpio_desc *desc);
-int gpiod_sysfs_set_active_low(struct gpio_desc *desc, int value);
 void gpiod_unexport(struct gpio_desc *desc);
 
 #else  /* CONFIG_GPIOLIB && CONFIG_GPIO_SYSFS */
@@ -466,11 +466,6 @@ static inline int gpiod_export_link(struct device *dev, const char *name,
 	return -ENOSYS;
 }
 
-static inline int gpiod_sysfs_set_active_low(struct gpio_desc *desc, int value)
-{
-	return -ENOSYS;
-}
-
 static inline void gpiod_unexport(struct gpio_desc *desc)
 {
 }
diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index f1b36593ec9f..cc7ec129b329 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -20,6 +20,7 @@ struct seq_file;
  * struct gpio_chip - abstract a GPIO controller
  * @label: for diagnostics
  * @dev: optional device providing the GPIOs
+ * @cdev: class device used by sysfs interface (may be NULL)
  * @owner: helps prevent removal of modules exporting active GPIOs
  * @list: links gpio_chips together for traversal
  * @request: optional hook for chip-specific activation, such as
@@ -41,8 +42,12 @@ struct seq_file;
  * @dbg_show: optional routine to show contents in debugfs; default code
  *	will be used when this is omitted, but custom code can show extra
  *	state (such as pullup/pulldown configuration).
- * @base: identifies the first GPIO number handled by this chip; or, if
- *	negative during registration, requests dynamic ID allocation.
+ * @base: identifies the first GPIO number handled by this chip;
+ *	or, if negative during registration, requests dynamic ID allocation.
+ *	DEPRECATION: providing anything non-negative and nailing the base
+ *	base offset of GPIO chips is deprecated. Please pass -1 as base to
+ *	let gpiolib select the chip base in all possible cases. We want to
+ *	get rid of the static GPIO number space in the long run.
  * @ngpio: the number of GPIOs handled by this controller; the last GPIO
  *	handled is (base + ngpio - 1).
  * @desc: array of ngpio descriptors. Private.
@@ -57,7 +62,6 @@ struct seq_file;
  *	implies that if the chip supports IRQs, these IRQs need to be threaded
  *	as the chip access may sleep when e.g. reading out the IRQ status
  *	registers.
- * @exported: flags if the gpiochip is exported for use from sysfs. Private.
  * @irq_not_threaded: flag must be set if @can_sleep is set but the
  *	IRQs don't need to be threaded
  *
@@ -74,6 +78,7 @@ struct seq_file;
 struct gpio_chip {
 	const char		*label;
 	struct device		*dev;
+	struct device		*cdev;
 	struct module		*owner;
 	struct list_head        list;
 
@@ -109,7 +114,6 @@ struct gpio_chip {
 	const char		*const *names;
 	bool			can_sleep;
 	bool			irq_not_threaded;
-	bool			exported;
 
 #ifdef CONFIG_GPIOLIB_IRQCHIP
 	/*
@@ -121,6 +125,7 @@ struct gpio_chip {
 	unsigned int		irq_base;
 	irq_flow_handler_t	irq_handler;
 	unsigned int		irq_default_type;
+	int			irq_parent;
 #endif
 
 #if defined(CONFIG_OF_GPIO)
diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h
index f4af03404b97..dfd59d6bc6f0 100644
--- a/include/linux/hardirq.h
+++ b/include/linux/hardirq.h
@@ -1,7 +1,7 @@
 #ifndef LINUX_HARDIRQ_H
 #define LINUX_HARDIRQ_H
 
-#include <linux/preempt_mask.h>
+#include <linux/preempt.h>
 #include <linux/lockdep.h>
 #include <linux/ftrace_irq.h>
 #include <linux/vtime.h>
diff --git a/include/linux/hid.h b/include/linux/hid.h
index 176b43670e5d..f17980de2662 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -815,6 +815,8 @@ void hid_disconnect(struct hid_device *hid);
 const struct hid_device_id *hid_match_id(struct hid_device *hdev,
 					 const struct hid_device_id *id);
 s32 hid_snto32(__u32 value, unsigned n);
+__u32 hid_field_extract(const struct hid_device *hid, __u8 *report,
+		     unsigned offset, unsigned n);
 
 /**
  * hid_device_io_start - enable HID input during probe, remove
diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index 9286a46b7d69..6aefcd0031a6 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -65,6 +65,7 @@ static inline void kunmap(struct page *page)
 
 static inline void *kmap_atomic(struct page *page)
 {
+	preempt_disable();
 	pagefault_disable();
 	return page_address(page);
 }
@@ -73,6 +74,7 @@ static inline void *kmap_atomic(struct page *page)
 static inline void __kunmap_atomic(void *addr)
 {
 	pagefault_enable();
+	preempt_enable();
 }
 
 #define kmap_atomic_pfn(pfn)	kmap_atomic(pfn_to_page(pfn))
diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 05f6df1fdf5b..76dd4f0da5ca 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -53,34 +53,25 @@ enum hrtimer_restart {
  *
  * 0x00		inactive
  * 0x01		enqueued into rbtree
- * 0x02		callback function running
- * 0x04		timer is migrated to another cpu
  *
- * Special cases:
- * 0x03		callback function running and enqueued
- *		(was requeued on another CPU)
- * 0x05		timer was migrated on CPU hotunplug
+ * The callback state is not part of the timer->state because clearing it would
+ * mean touching the timer after the callback, this makes it impossible to free
+ * the timer from the callback function.
  *
- * The "callback function running and enqueued" status is only possible on
- * SMP. It happens for example when a posix timer expired and the callback
+ * Therefore we track the callback state in:
+ *
+ *	timer->base->cpu_base->running == timer
+ *
+ * On SMP it is possible to have a "callback function running and enqueued"
+ * status. It happens for example when a posix timer expired and the callback
  * queued a signal. Between dropping the lock which protects the posix timer
  * and reacquiring the base lock of the hrtimer, another CPU can deliver the
- * signal and rearm the timer. We have to preserve the callback running state,
- * as otherwise the timer could be removed before the softirq code finishes the
- * the handling of the timer.
- *
- * The HRTIMER_STATE_ENQUEUED bit is always or'ed to the current state
- * to preserve the HRTIMER_STATE_CALLBACK in the above scenario. This
- * also affects HRTIMER_STATE_MIGRATE where the preservation is not
- * necessary. HRTIMER_STATE_MIGRATE is cleared after the timer is
- * enqueued on the new cpu.
+ * signal and rearm the timer.
  *
  * All state transitions are protected by cpu_base->lock.
  */
 #define HRTIMER_STATE_INACTIVE	0x00
 #define HRTIMER_STATE_ENQUEUED	0x01
-#define HRTIMER_STATE_CALLBACK	0x02
-#define HRTIMER_STATE_MIGRATE	0x04
 
 /**
  * struct hrtimer - the basic hrtimer structure
@@ -130,6 +121,12 @@ struct hrtimer_sleeper {
 	struct task_struct *task;
 };
 
+#ifdef CONFIG_64BIT
+# define HRTIMER_CLOCK_BASE_ALIGN	64
+#else
+# define HRTIMER_CLOCK_BASE_ALIGN	32
+#endif
+
 /**
  * struct hrtimer_clock_base - the timer base for a specific clock
  * @cpu_base:		per cpu clock base
@@ -137,9 +134,7 @@ struct hrtimer_sleeper {
  *			timer to a base on another cpu.
  * @clockid:		clock id for per_cpu support
  * @active:		red black tree root node for the active timers
- * @resolution:		the resolution of the clock, in nanoseconds
  * @get_time:		function to retrieve the current time of the clock
- * @softirq_time:	the time when running the hrtimer queue in the softirq
  * @offset:		offset of this clock to the monotonic base
  */
 struct hrtimer_clock_base {
@@ -147,11 +142,9 @@ struct hrtimer_clock_base {
 	int			index;
 	clockid_t		clockid;
 	struct timerqueue_head	active;
-	ktime_t			resolution;
 	ktime_t			(*get_time)(void);
-	ktime_t			softirq_time;
 	ktime_t			offset;
-};
+} __attribute__((__aligned__(HRTIMER_CLOCK_BASE_ALIGN)));
 
 enum  hrtimer_base_type {
 	HRTIMER_BASE_MONOTONIC,
@@ -165,11 +158,16 @@ enum  hrtimer_base_type {
  * struct hrtimer_cpu_base - the per cpu clock bases
  * @lock:		lock protecting the base and associated clock bases
  *			and timers
+ * @seq:		seqcount around __run_hrtimer
+ * @running:		pointer to the currently running hrtimer
  * @cpu:		cpu number
  * @active_bases:	Bitfield to mark bases with active timers
- * @clock_was_set:	Indicates that clock was set from irq context.
+ * @clock_was_set_seq:	Sequence counter of clock was set events
+ * @migration_enabled:	The migration of hrtimers to other cpus is enabled
+ * @nohz_active:	The nohz functionality is enabled
  * @expires_next:	absolute time of the next event which was scheduled
  *			via clock_set_next_event()
+ * @next_timer:		Pointer to the first expiring timer
  * @in_hrtirq:		hrtimer_interrupt() is currently executing
  * @hres_active:	State of high resolution mode
  * @hang_detected:	The last hrtimer interrupt detected a hang
@@ -178,27 +176,38 @@ enum  hrtimer_base_type {
  * @nr_hangs:		Total number of hrtimer interrupt hangs
  * @max_hang_time:	Maximum time spent in hrtimer_interrupt
  * @clock_base:		array of clock bases for this cpu
+ *
+ * Note: next_timer is just an optimization for __remove_hrtimer().
+ *	 Do not dereference the pointer because it is not reliable on
+ *	 cross cpu removals.
  */
 struct hrtimer_cpu_base {
 	raw_spinlock_t			lock;
+	seqcount_t			seq;
+	struct hrtimer			*running;
 	unsigned int			cpu;
 	unsigned int			active_bases;
-	unsigned int			clock_was_set;
+	unsigned int			clock_was_set_seq;
+	bool				migration_enabled;
+	bool				nohz_active;
 #ifdef CONFIG_HIGH_RES_TIMERS
+	unsigned int			in_hrtirq	: 1,
+					hres_active	: 1,
+					hang_detected	: 1;
 	ktime_t				expires_next;
-	int				in_hrtirq;
-	int				hres_active;
-	int				hang_detected;
-	unsigned long			nr_events;
-	unsigned long			nr_retries;
-	unsigned long			nr_hangs;
-	ktime_t				max_hang_time;
+	struct hrtimer			*next_timer;
+	unsigned int			nr_events;
+	unsigned int			nr_retries;
+	unsigned int			nr_hangs;
+	unsigned int			max_hang_time;
 #endif
 	struct hrtimer_clock_base	clock_base[HRTIMER_MAX_CLOCK_BASES];
-};
+} ____cacheline_aligned;
 
 static inline void hrtimer_set_expires(struct hrtimer *timer, ktime_t time)
 {
+	BUILD_BUG_ON(sizeof(struct hrtimer_clock_base) > HRTIMER_CLOCK_BASE_ALIGN);
+
 	timer->node.expires = time;
 	timer->_softexpires = time;
 }
@@ -262,19 +271,16 @@ static inline ktime_t hrtimer_expires_remaining(const struct hrtimer *timer)
 	return ktime_sub(timer->node.expires, timer->base->get_time());
 }
 
-#ifdef CONFIG_HIGH_RES_TIMERS
-struct clock_event_device;
-
-extern void hrtimer_interrupt(struct clock_event_device *dev);
-
-/*
- * In high resolution mode the time reference must be read accurate
- */
 static inline ktime_t hrtimer_cb_get_time(struct hrtimer *timer)
 {
 	return timer->base->get_time();
 }
 
+#ifdef CONFIG_HIGH_RES_TIMERS
+struct clock_event_device;
+
+extern void hrtimer_interrupt(struct clock_event_device *dev);
+
 static inline int hrtimer_is_hres_active(struct hrtimer *timer)
 {
 	return timer->base->cpu_base->hres_active;
@@ -295,21 +301,16 @@ extern void hrtimer_peek_ahead_timers(void);
 
 extern void clock_was_set_delayed(void);
 
+extern unsigned int hrtimer_resolution;
+
 #else
 
 # define MONOTONIC_RES_NSEC	LOW_RES_NSEC
 # define KTIME_MONOTONIC_RES	KTIME_LOW_RES
 
-static inline void hrtimer_peek_ahead_timers(void) { }
+#define hrtimer_resolution	(unsigned int)LOW_RES_NSEC
 
-/*
- * In non high resolution mode the time reference is taken from
- * the base softirq time variable.
- */
-static inline ktime_t hrtimer_cb_get_time(struct hrtimer *timer)
-{
-	return timer->base->softirq_time;
-}
+static inline void hrtimer_peek_ahead_timers(void) { }
 
 static inline int hrtimer_is_hres_active(struct hrtimer *timer)
 {
@@ -353,49 +354,47 @@ static inline void destroy_hrtimer_on_stack(struct hrtimer *timer) { }
 #endif
 
 /* Basic timer operations: */
-extern int hrtimer_start(struct hrtimer *timer, ktime_t tim,
-			 const enum hrtimer_mode mode);
-extern int hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
+extern void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
 			unsigned long range_ns, const enum hrtimer_mode mode);
-extern int
-__hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
-			 unsigned long delta_ns,
-			 const enum hrtimer_mode mode, int wakeup);
+
+/**
+ * hrtimer_start - (re)start an hrtimer on the current CPU
+ * @timer:	the timer to be added
+ * @tim:	expiry time
+ * @mode:	expiry mode: absolute (HRTIMER_MODE_ABS) or
+ *		relative (HRTIMER_MODE_REL)
+ */
+static inline void hrtimer_start(struct hrtimer *timer, ktime_t tim,
+				 const enum hrtimer_mode mode)
+{
+	hrtimer_start_range_ns(timer, tim, 0, mode);
+}
 
 extern int hrtimer_cancel(struct hrtimer *timer);
 extern int hrtimer_try_to_cancel(struct hrtimer *timer);
 
-static inline int hrtimer_start_expires(struct hrtimer *timer,
-						enum hrtimer_mode mode)
+static inline void hrtimer_start_expires(struct hrtimer *timer,
+					 enum hrtimer_mode mode)
 {
 	unsigned long delta;
 	ktime_t soft, hard;
 	soft = hrtimer_get_softexpires(timer);
 	hard = hrtimer_get_expires(timer);
 	delta = ktime_to_ns(ktime_sub(hard, soft));
-	return hrtimer_start_range_ns(timer, soft, delta, mode);
+	hrtimer_start_range_ns(timer, soft, delta, mode);
 }
 
-static inline int hrtimer_restart(struct hrtimer *timer)
+static inline void hrtimer_restart(struct hrtimer *timer)
 {
-	return hrtimer_start_expires(timer, HRTIMER_MODE_ABS);
+	hrtimer_start_expires(timer, HRTIMER_MODE_ABS);
 }
 
 /* Query timers: */
 extern ktime_t hrtimer_get_remaining(const struct hrtimer *timer);
-extern int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp);
 
-extern ktime_t hrtimer_get_next_event(void);
+extern u64 hrtimer_get_next_event(void);
 
-/*
- * A timer is active, when it is enqueued into the rbtree or the
- * callback function is running or it's in the state of being migrated
- * to another cpu.
- */
-static inline int hrtimer_active(const struct hrtimer *timer)
-{
-	return timer->state != HRTIMER_STATE_INACTIVE;
-}
+extern bool hrtimer_active(const struct hrtimer *timer);
 
 /*
  * Helper function to check, whether the timer is on one of the queues
@@ -411,14 +410,29 @@ static inline int hrtimer_is_queued(struct hrtimer *timer)
  */
 static inline int hrtimer_callback_running(struct hrtimer *timer)
 {
-	return timer->state & HRTIMER_STATE_CALLBACK;
+	return timer->base->cpu_base->running == timer;
 }
 
 /* Forward a hrtimer so it expires after now: */
 extern u64
 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval);
 
-/* Forward a hrtimer so it expires after the hrtimer's current now */
+/**
+ * hrtimer_forward_now - forward the timer expiry so it expires after now
+ * @timer:	hrtimer to forward
+ * @interval:	the interval to forward
+ *
+ * Forward the timer expiry so it will expire after the current time
+ * of the hrtimer clock base. Returns the number of overruns.
+ *
+ * Can be safely called from the callback function of @timer. If
+ * called from other contexts @timer must neither be enqueued nor
+ * running the callback and the caller needs to take care of
+ * serialization.
+ *
+ * Note: This only updates the timer expiry value and does not requeue
+ * the timer.
+ */
 static inline u64 hrtimer_forward_now(struct hrtimer *timer,
 				      ktime_t interval)
 {
@@ -443,7 +457,6 @@ extern int schedule_hrtimeout(ktime_t *expires, const enum hrtimer_mode mode);
 
 /* Soft interrupt function to run the hrtimer queues: */
 extern void hrtimer_run_queues(void);
-extern void hrtimer_run_pending(void);
 
 /* Bootup initialization: */
 extern void __init hrtimers_init(void);
diff --git a/include/linux/htirq.h b/include/linux/htirq.h
index 70a1dbbf2093..d4a527e58434 100644
--- a/include/linux/htirq.h
+++ b/include/linux/htirq.h
@@ -1,24 +1,38 @@
 #ifndef LINUX_HTIRQ_H
 #define LINUX_HTIRQ_H
 
+struct pci_dev;
+struct irq_data;
+
 struct ht_irq_msg {
 	u32	address_lo;	/* low 32 bits of the ht irq message */
 	u32	address_hi;	/* high 32 bits of the it irq message */
 };
 
+typedef void (ht_irq_update_t)(struct pci_dev *dev, int irq,
+			       struct ht_irq_msg *msg);
+
+struct ht_irq_cfg {
+	struct pci_dev *dev;
+	 /* Update callback used to cope with buggy hardware */
+	ht_irq_update_t *update;
+	unsigned pos;
+	unsigned idx;
+	struct ht_irq_msg msg;
+};
+
 /* Helper functions.. */
 void fetch_ht_irq_msg(unsigned int irq, struct ht_irq_msg *msg);
 void write_ht_irq_msg(unsigned int irq, struct ht_irq_msg *msg);
-struct irq_data;
 void mask_ht_irq(struct irq_data *data);
 void unmask_ht_irq(struct irq_data *data);
 
 /* The arch hook for getting things started */
-int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev);
+int arch_setup_ht_irq(int idx, int pos, struct pci_dev *dev,
+		      ht_irq_update_t *update);
+void arch_teardown_ht_irq(unsigned int irq);
 
 /* For drivers of buggy hardware */
-typedef void (ht_irq_update_t)(struct pci_dev *dev, int irq,
-			       struct ht_irq_msg *msg);
 int __ht_create_irq(struct pci_dev *dev, int idx, ht_irq_update_t *update);
 
 #endif /* LINUX_HTIRQ_H */
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 696d22312b31..bb9b075f0eb0 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -50,9 +50,8 @@ extern struct fs_struct init_fs;
 	.cpu_timers	= INIT_CPU_TIMERS(sig.cpu_timers),		\
 	.rlim		= INIT_RLIMITS,					\
 	.cputimer	= { 						\
-		.cputime = INIT_CPUTIME,				\
-		.running = 0,						\
-		.lock = __RAW_SPIN_LOCK_UNLOCKED(sig.cputimer.lock),	\
+		.cputime_atomic	= INIT_CPUTIME_ATOMIC,			\
+		.running	= 0,					\
 	},								\
 	.cred_guard_mutex =						\
 		 __MUTEX_INITIALIZER(sig.cred_guard_mutex),		\
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index a240e61a7700..3665cb331ca1 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -87,6 +87,7 @@ static inline void dmar_writeq(void __iomem *addr, u64 val)
 /*
  * Decoding Capability Register
  */
+#define cap_pi_support(c)	(((c) >> 59) & 1)
 #define cap_read_drain(c)	(((c) >> 55) & 1)
 #define cap_write_drain(c)	(((c) >> 54) & 1)
 #define cap_max_amask_val(c)	(((c) >> 48) & 0x3f)
@@ -299,6 +300,8 @@ struct q_inval {
 
 #define INTR_REMAP_TABLE_ENTRIES	65536
 
+struct irq_domain;
+
 struct ir_table {
 	struct irte *base;
 	unsigned long *bitmap;
@@ -348,6 +351,8 @@ struct intel_iommu {
 
 #ifdef CONFIG_IRQ_REMAP
 	struct ir_table *ir_table;	/* Interrupt remapping info */
+	struct irq_domain *ir_domain;
+	struct irq_domain *ir_msi_domain;
 #endif
 	struct device	*iommu_dev; /* IOMMU-sysfs device */
 	int		node;
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 950ae4501826..be7e75c945e9 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -413,7 +413,8 @@ enum
 	BLOCK_IOPOLL_SOFTIRQ,
 	TASKLET_SOFTIRQ,
 	SCHED_SOFTIRQ,
-	HRTIMER_SOFTIRQ,
+	HRTIMER_SOFTIRQ, /* Unused, but kept as tools rely on the
+			    numbering. Sigh! */
 	RCU_SOFTIRQ,    /* Preferable RCU should always be the last softirq */
 
 	NR_SOFTIRQS
@@ -592,10 +593,10 @@ tasklet_hrtimer_init(struct tasklet_hrtimer *ttimer,
 		     clockid_t which_clock, enum hrtimer_mode mode);
 
 static inline
-int tasklet_hrtimer_start(struct tasklet_hrtimer *ttimer, ktime_t time,
-			  const enum hrtimer_mode mode)
+void tasklet_hrtimer_start(struct tasklet_hrtimer *ttimer, ktime_t time,
+			   const enum hrtimer_mode mode)
 {
-	return hrtimer_start(&ttimer->timer, time, mode);
+	hrtimer_start(&ttimer->timer, time, mode);
 }
 
 static inline
diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h
index 657fab4efab3..c27dde7215b5 100644
--- a/include/linux/io-mapping.h
+++ b/include/linux/io-mapping.h
@@ -141,6 +141,7 @@ static inline void __iomem *
 io_mapping_map_atomic_wc(struct io_mapping *mapping,
 			 unsigned long offset)
 {
+	preempt_disable();
 	pagefault_disable();
 	return ((char __force __iomem *) mapping) + offset;
 }
@@ -149,6 +150,7 @@ static inline void
 io_mapping_unmap_atomic(void __iomem *vaddr)
 {
 	pagefault_enable();
+	preempt_enable();
 }
 
 /* Non-atomic map/unmap */
diff --git a/include/linux/io.h b/include/linux/io.h
index 986f2bffea1e..fb5a99800e77 100644
--- a/include/linux/io.h
+++ b/include/linux/io.h
@@ -19,6 +19,7 @@
 #define _LINUX_IO_H
 
 #include <linux/types.h>
+#include <linux/init.h>
 #include <asm/io.h>
 #include <asm/page.h>
 
@@ -111,6 +112,13 @@ static inline void arch_phys_wc_del(int handle)
 }
 
 #define arch_phys_wc_add arch_phys_wc_add
+#ifndef arch_phys_wc_index
+static inline int arch_phys_wc_index(int handle)
+{
+	return -1;
+}
+#define arch_phys_wc_index arch_phys_wc_index
+#endif
 #endif
 
 #endif /* _LINUX_IO_H */
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 62c6901cab55..812149160d3b 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -126,13 +126,21 @@ struct msi_desc;
 struct irq_domain;
 
 /**
- * struct irq_data - per irq and irq chip data passed down to chip functions
+ * struct irq_common_data - per irq data shared by all irqchips
+ * @state_use_accessors: status information for irq chip functions.
+ *			Use accessor functions to deal with it
+ */
+struct irq_common_data {
+	unsigned int		state_use_accessors;
+};
+
+/**
+ * struct irq_data - per irq chip data passed down to chip functions
  * @mask:		precomputed bitmask for accessing the chip registers
  * @irq:		interrupt number
  * @hwirq:		hardware interrupt number, local to the interrupt domain
  * @node:		node index useful for balancing
- * @state_use_accessors: status information for irq chip functions.
- *			Use accessor functions to deal with it
+ * @common:		point to data shared by all irqchips
  * @chip:		low level interrupt hardware access
  * @domain:		Interrupt translation domain; responsible for mapping
  *			between hwirq number and linux irq number.
@@ -153,7 +161,7 @@ struct irq_data {
 	unsigned int		irq;
 	unsigned long		hwirq;
 	unsigned int		node;
-	unsigned int		state_use_accessors;
+	struct irq_common_data	*common;
 	struct irq_chip		*chip;
 	struct irq_domain	*domain;
 #ifdef	CONFIG_IRQ_DOMAIN_HIERARCHY
@@ -166,7 +174,7 @@ struct irq_data {
 };
 
 /*
- * Bit masks for irq_data.state
+ * Bit masks for irq_common_data.state_use_accessors
  *
  * IRQD_TRIGGER_MASK		- Mask for the trigger type bits
  * IRQD_SETAFFINITY_PENDING	- Affinity setting is pending
@@ -198,34 +206,36 @@ enum {
 	IRQD_WAKEUP_ARMED		= (1 << 19),
 };
 
+#define __irqd_to_state(d)		((d)->common->state_use_accessors)
+
 static inline bool irqd_is_setaffinity_pending(struct irq_data *d)
 {
-	return d->state_use_accessors & IRQD_SETAFFINITY_PENDING;
+	return __irqd_to_state(d) & IRQD_SETAFFINITY_PENDING;
 }
 
 static inline bool irqd_is_per_cpu(struct irq_data *d)
 {
-	return d->state_use_accessors & IRQD_PER_CPU;
+	return __irqd_to_state(d) & IRQD_PER_CPU;
 }
 
 static inline bool irqd_can_balance(struct irq_data *d)
 {
-	return !(d->state_use_accessors & (IRQD_PER_CPU | IRQD_NO_BALANCING));
+	return !(__irqd_to_state(d) & (IRQD_PER_CPU | IRQD_NO_BALANCING));
 }
 
 static inline bool irqd_affinity_was_set(struct irq_data *d)
 {
-	return d->state_use_accessors & IRQD_AFFINITY_SET;
+	return __irqd_to_state(d) & IRQD_AFFINITY_SET;
 }
 
 static inline void irqd_mark_affinity_was_set(struct irq_data *d)
 {
-	d->state_use_accessors |= IRQD_AFFINITY_SET;
+	__irqd_to_state(d) |= IRQD_AFFINITY_SET;
 }
 
 static inline u32 irqd_get_trigger_type(struct irq_data *d)
 {
-	return d->state_use_accessors & IRQD_TRIGGER_MASK;
+	return __irqd_to_state(d) & IRQD_TRIGGER_MASK;
 }
 
 /*
@@ -233,43 +243,43 @@ static inline u32 irqd_get_trigger_type(struct irq_data *d)
  */
 static inline void irqd_set_trigger_type(struct irq_data *d, u32 type)
 {
-	d->state_use_accessors &= ~IRQD_TRIGGER_MASK;
-	d->state_use_accessors |= type & IRQD_TRIGGER_MASK;
+	__irqd_to_state(d) &= ~IRQD_TRIGGER_MASK;
+	__irqd_to_state(d) |= type & IRQD_TRIGGER_MASK;
 }
 
 static inline bool irqd_is_level_type(struct irq_data *d)
 {
-	return d->state_use_accessors & IRQD_LEVEL;
+	return __irqd_to_state(d) & IRQD_LEVEL;
 }
 
 static inline bool irqd_is_wakeup_set(struct irq_data *d)
 {
-	return d->state_use_accessors & IRQD_WAKEUP_STATE;
+	return __irqd_to_state(d) & IRQD_WAKEUP_STATE;
 }
 
 static inline bool irqd_can_move_in_process_context(struct irq_data *d)
 {
-	return d->state_use_accessors & IRQD_MOVE_PCNTXT;
+	return __irqd_to_state(d) & IRQD_MOVE_PCNTXT;
 }
 
 static inline bool irqd_irq_disabled(struct irq_data *d)
 {
-	return d->state_use_accessors & IRQD_IRQ_DISABLED;
+	return __irqd_to_state(d) & IRQD_IRQ_DISABLED;
 }
 
 static inline bool irqd_irq_masked(struct irq_data *d)
 {
-	return d->state_use_accessors & IRQD_IRQ_MASKED;
+	return __irqd_to_state(d) & IRQD_IRQ_MASKED;
 }
 
 static inline bool irqd_irq_inprogress(struct irq_data *d)
 {
-	return d->state_use_accessors & IRQD_IRQ_INPROGRESS;
+	return __irqd_to_state(d) & IRQD_IRQ_INPROGRESS;
 }
 
 static inline bool irqd_is_wakeup_armed(struct irq_data *d)
 {
-	return d->state_use_accessors & IRQD_WAKEUP_ARMED;
+	return __irqd_to_state(d) & IRQD_WAKEUP_ARMED;
 }
 
 
@@ -280,12 +290,12 @@ static inline bool irqd_is_wakeup_armed(struct irq_data *d)
  */
 static inline void irqd_set_chained_irq_inprogress(struct irq_data *d)
 {
-	d->state_use_accessors |= IRQD_IRQ_INPROGRESS;
+	__irqd_to_state(d) |= IRQD_IRQ_INPROGRESS;
 }
 
 static inline void irqd_clr_chained_irq_inprogress(struct irq_data *d)
 {
-	d->state_use_accessors &= ~IRQD_IRQ_INPROGRESS;
+	__irqd_to_state(d) &= ~IRQD_IRQ_INPROGRESS;
 }
 
 static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d)
@@ -327,6 +337,7 @@ static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d)
  * @irq_write_msi_msg:	optional to write message content for MSI
  * @irq_get_irqchip_state:	return the internal state of an interrupt
  * @irq_set_irqchip_state:	set the internal state of a interrupt
+ * @irq_set_vcpu_affinity:	optional to target a vCPU in a virtual machine
  * @flags:		chip specific flags
  */
 struct irq_chip {
@@ -369,6 +380,8 @@ struct irq_chip {
 	int		(*irq_get_irqchip_state)(struct irq_data *data, enum irqchip_irq_state which, bool *state);
 	int		(*irq_set_irqchip_state)(struct irq_data *data, enum irqchip_irq_state which, bool state);
 
+	int		(*irq_set_vcpu_affinity)(struct irq_data *data, void *vcpu_info);
+
 	unsigned long	flags;
 };
 
@@ -422,6 +435,7 @@ extern void irq_cpu_online(void);
 extern void irq_cpu_offline(void);
 extern int irq_set_affinity_locked(struct irq_data *data,
 				   const struct cpumask *cpumask, bool force);
+extern int irq_set_vcpu_affinity(unsigned int irq, void *vcpu_info);
 
 #if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_PENDING_IRQ)
 void irq_move_irq(struct irq_data *data);
@@ -458,6 +472,8 @@ extern void handle_nested_irq(unsigned int irq);
 
 extern int irq_chip_compose_msi_msg(struct irq_data *data, struct msi_msg *msg);
 #ifdef	CONFIG_IRQ_DOMAIN_HIERARCHY
+extern void irq_chip_enable_parent(struct irq_data *data);
+extern void irq_chip_disable_parent(struct irq_data *data);
 extern void irq_chip_ack_parent(struct irq_data *data);
 extern int irq_chip_retrigger_hierarchy(struct irq_data *data);
 extern void irq_chip_mask_parent(struct irq_data *data);
@@ -467,6 +483,8 @@ extern int irq_chip_set_affinity_parent(struct irq_data *data,
 					const struct cpumask *dest,
 					bool force);
 extern int irq_chip_set_wake_parent(struct irq_data *data, unsigned int on);
+extern int irq_chip_set_vcpu_affinity_parent(struct irq_data *data,
+					     void *vcpu_info);
 #endif
 
 /* Handling of unhandled and spurious interrupts: */
@@ -517,6 +535,15 @@ irq_set_chained_handler(unsigned int irq, irq_flow_handler_t handle)
 	__irq_set_handler(irq, handle, 1, NULL);
 }
 
+/*
+ * Set a highlevel chained flow handler and its data for a given IRQ.
+ * (a chained handler is automatically enabled and set to
+ *  IRQ_NOREQUEST, IRQ_NOPROBE, and IRQ_NOTHREAD)
+ */
+void
+irq_set_chained_handler_and_data(unsigned int irq, irq_flow_handler_t handle,
+				 void *data);
+
 void irq_modify_status(unsigned int irq, unsigned long clr, unsigned long set);
 
 static inline void irq_set_status_flags(unsigned int irq, unsigned long set)
@@ -624,6 +651,23 @@ static inline u32 irq_get_trigger_type(unsigned int irq)
 	return d ? irqd_get_trigger_type(d) : 0;
 }
 
+static inline int irq_data_get_node(struct irq_data *d)
+{
+	return d->node;
+}
+
+static inline struct cpumask *irq_get_affinity_mask(int irq)
+{
+	struct irq_data *d = irq_get_irq_data(irq);
+
+	return d ? d->affinity : NULL;
+}
+
+static inline struct cpumask *irq_data_get_affinity_mask(struct irq_data *d)
+{
+	return d->affinity;
+}
+
 unsigned int arch_dynirq_lower_bound(unsigned int from);
 
 int __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node,
diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
index dd1109fb241e..c52d1480f272 100644
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -17,7 +17,7 @@ struct pt_regs;
 
 /**
  * struct irq_desc - interrupt descriptor
- * @irq_data:		per irq and chip data passed down to chip functions
+ * @irq_common_data:	per irq and chip data passed down to chip functions
  * @kstat_irqs:		irq stats per cpu
  * @handle_irq:		highlevel irq-events handler
  * @preflow_handler:	handler called before the flow handler (currently used by sparc)
@@ -47,6 +47,7 @@ struct pt_regs;
  * @name:		flow handler name for /proc/interrupts output
  */
 struct irq_desc {
+	struct irq_common_data	irq_common_data;
 	struct irq_data		irq_data;
 	unsigned int __percpu	*kstat_irqs;
 	irq_flow_handler_t	handle_irq;
@@ -93,6 +94,15 @@ struct irq_desc {
 extern struct irq_desc irq_desc[NR_IRQS];
 #endif
 
+static inline struct irq_desc *irq_data_to_desc(struct irq_data *data)
+{
+#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY
+	return irq_to_desc(data->irq);
+#else
+	return container_of(data, struct irq_desc, irq_data);
+#endif
+}
+
 static inline struct irq_data *irq_desc_get_irq_data(struct irq_desc *desc)
 {
 	return &desc->irq_data;
diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h
index 676d7306a360..744ac0ec98eb 100644
--- a/include/linux/irqdomain.h
+++ b/include/linux/irqdomain.h
@@ -258,6 +258,10 @@ int irq_domain_xlate_onetwocell(struct irq_domain *d, struct device_node *ctrlr,
 /* V2 interfaces to support hierarchy IRQ domains. */
 extern struct irq_data *irq_domain_get_irq_data(struct irq_domain *domain,
 						unsigned int virq);
+extern void irq_domain_set_info(struct irq_domain *domain, unsigned int virq,
+				irq_hw_number_t hwirq, struct irq_chip *chip,
+				void *chip_data, irq_flow_handler_t handler,
+				void *handler_data, const char *handler_name);
 #ifdef	CONFIG_IRQ_DOMAIN_HIERARCHY
 extern struct irq_domain *irq_domain_add_hierarchy(struct irq_domain *parent,
 			unsigned int flags, unsigned int size,
@@ -281,10 +285,6 @@ extern int irq_domain_set_hwirq_and_chip(struct irq_domain *domain,
 					 irq_hw_number_t hwirq,
 					 struct irq_chip *chip,
 					 void *chip_data);
-extern void irq_domain_set_info(struct irq_domain *domain, unsigned int virq,
-				irq_hw_number_t hwirq, struct irq_chip *chip,
-				void *chip_data, irq_flow_handler_t handler,
-				void *handler_data, const char *handler_name);
 extern void irq_domain_reset_irq_data(struct irq_data *irq_data);
 extern void irq_domain_free_irqs_common(struct irq_domain *domain,
 					unsigned int virq,
diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h
index c367cbdf73ab..535fd3bb1ba8 100644
--- a/include/linux/jiffies.h
+++ b/include/linux/jiffies.h
@@ -7,6 +7,7 @@
 #include <linux/time.h>
 #include <linux/timex.h>
 #include <asm/param.h>			/* for HZ */
+#include <generated/timeconst.h>
 
 /*
  * The following defines establish the engineering parameters of the PLL
@@ -288,8 +289,133 @@ static inline u64 jiffies_to_nsecs(const unsigned long j)
 	return (u64)jiffies_to_usecs(j) * NSEC_PER_USEC;
 }
 
-extern unsigned long msecs_to_jiffies(const unsigned int m);
-extern unsigned long usecs_to_jiffies(const unsigned int u);
+extern unsigned long __msecs_to_jiffies(const unsigned int m);
+#if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ)
+/*
+ * HZ is equal to or smaller than 1000, and 1000 is a nice round
+ * multiple of HZ, divide with the factor between them, but round
+ * upwards:
+ */
+static inline unsigned long _msecs_to_jiffies(const unsigned int m)
+{
+	return (m + (MSEC_PER_SEC / HZ) - 1) / (MSEC_PER_SEC / HZ);
+}
+#elif HZ > MSEC_PER_SEC && !(HZ % MSEC_PER_SEC)
+/*
+ * HZ is larger than 1000, and HZ is a nice round multiple of 1000 -
+ * simply multiply with the factor between them.
+ *
+ * But first make sure the multiplication result cannot overflow:
+ */
+static inline unsigned long _msecs_to_jiffies(const unsigned int m)
+{
+	if (m > jiffies_to_msecs(MAX_JIFFY_OFFSET))
+		return MAX_JIFFY_OFFSET;
+	return m * (HZ / MSEC_PER_SEC);
+}
+#else
+/*
+ * Generic case - multiply, round and divide. But first check that if
+ * we are doing a net multiplication, that we wouldn't overflow:
+ */
+static inline unsigned long _msecs_to_jiffies(const unsigned int m)
+{
+	if (HZ > MSEC_PER_SEC && m > jiffies_to_msecs(MAX_JIFFY_OFFSET))
+		return MAX_JIFFY_OFFSET;
+
+	return (MSEC_TO_HZ_MUL32 * m + MSEC_TO_HZ_ADJ32) >> MSEC_TO_HZ_SHR32;
+}
+#endif
+/**
+ * msecs_to_jiffies: - convert milliseconds to jiffies
+ * @m:	time in milliseconds
+ *
+ * conversion is done as follows:
+ *
+ * - negative values mean 'infinite timeout' (MAX_JIFFY_OFFSET)
+ *
+ * - 'too large' values [that would result in larger than
+ *   MAX_JIFFY_OFFSET values] mean 'infinite timeout' too.
+ *
+ * - all other values are converted to jiffies by either multiplying
+ *   the input value by a factor or dividing it with a factor and
+ *   handling any 32-bit overflows.
+ *   for the details see __msecs_to_jiffies()
+ *
+ * msecs_to_jiffies() checks for the passed in value being a constant
+ * via __builtin_constant_p() allowing gcc to eliminate most of the
+ * code, __msecs_to_jiffies() is called if the value passed does not
+ * allow constant folding and the actual conversion must be done at
+ * runtime.
+ * the HZ range specific helpers _msecs_to_jiffies() are called both
+ * directly here and from __msecs_to_jiffies() in the case where
+ * constant folding is not possible.
+ */
+static inline unsigned long msecs_to_jiffies(const unsigned int m)
+{
+	if (__builtin_constant_p(m)) {
+		if ((int)m < 0)
+			return MAX_JIFFY_OFFSET;
+		return _msecs_to_jiffies(m);
+	} else {
+		return __msecs_to_jiffies(m);
+	}
+}
+
+extern unsigned long __usecs_to_jiffies(const unsigned int u);
+#if HZ <= USEC_PER_SEC && !(USEC_PER_SEC % HZ)
+static inline unsigned long _usecs_to_jiffies(const unsigned int u)
+{
+	return (u + (USEC_PER_SEC / HZ) - 1) / (USEC_PER_SEC / HZ);
+}
+#elif HZ > USEC_PER_SEC && !(HZ % USEC_PER_SEC)
+static inline unsigned long _usecs_to_jiffies(const unsigned int u)
+{
+	return u * (HZ / USEC_PER_SEC);
+}
+static inline unsigned long _usecs_to_jiffies(const unsigned int u)
+{
+#else
+static inline unsigned long _usecs_to_jiffies(const unsigned int u)
+{
+	return (USEC_TO_HZ_MUL32 * u + USEC_TO_HZ_ADJ32)
+		>> USEC_TO_HZ_SHR32;
+}
+#endif
+
+/**
+ * usecs_to_jiffies: - convert microseconds to jiffies
+ * @u:	time in microseconds
+ *
+ * conversion is done as follows:
+ *
+ * - 'too large' values [that would result in larger than
+ *   MAX_JIFFY_OFFSET values] mean 'infinite timeout' too.
+ *
+ * - all other values are converted to jiffies by either multiplying
+ *   the input value by a factor or dividing it with a factor and
+ *   handling any 32-bit overflows as for msecs_to_jiffies.
+ *
+ * usecs_to_jiffies() checks for the passed in value being a constant
+ * via __builtin_constant_p() allowing gcc to eliminate most of the
+ * code, __usecs_to_jiffies() is called if the value passed does not
+ * allow constant folding and the actual conversion must be done at
+ * runtime.
+ * the HZ range specific helpers _usecs_to_jiffies() are called both
+ * directly here and from __msecs_to_jiffies() in the case where
+ * constant folding is not possible.
+ */
+static inline unsigned long usecs_to_jiffies(const unsigned int u)
+{
+	if (__builtin_constant_p(u)) {
+		if (u > jiffies_to_usecs(MAX_JIFFY_OFFSET))
+			return MAX_JIFFY_OFFSET;
+		return _usecs_to_jiffies(u);
+	} else {
+		return __usecs_to_jiffies(u);
+	}
+}
+
 extern unsigned long timespec_to_jiffies(const struct timespec *value);
 extern void jiffies_to_timespec(const unsigned long jiffies,
 				struct timespec *value);
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 3a5b48e52a9e..060dd7b61c6d 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -244,7 +244,8 @@ static inline u32 reciprocal_scale(u32 val, u32 ep_ro)
 
 #if defined(CONFIG_MMU) && \
 	(defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_DEBUG_ATOMIC_SLEEP))
-void might_fault(void);
+#define might_fault() __might_fault(__FILE__, __LINE__)
+void __might_fault(const char *file, int line);
 #else
 static inline void might_fault(void) { }
 #endif
diff --git a/include/linux/lglock.h b/include/linux/lglock.h
index 0081f000e34b..c92ebd100d9b 100644
--- a/include/linux/lglock.h
+++ b/include/linux/lglock.h
@@ -52,10 +52,15 @@ struct lglock {
 	static struct lglock name = { .lock = &name ## _lock }
 
 void lg_lock_init(struct lglock *lg, char *name);
+
 void lg_local_lock(struct lglock *lg);
 void lg_local_unlock(struct lglock *lg);
 void lg_local_lock_cpu(struct lglock *lg, int cpu);
 void lg_local_unlock_cpu(struct lglock *lg, int cpu);
+
+void lg_double_lock(struct lglock *lg, int cpu1, int cpu2);
+void lg_double_unlock(struct lglock *lg, int cpu1, int cpu2);
+
 void lg_global_lock(struct lglock *lg);
 void lg_global_unlock(struct lglock *lg);
 
diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h
index ee6dbb39a809..31db7a05dd36 100644
--- a/include/linux/livepatch.h
+++ b/include/linux/livepatch.h
@@ -99,7 +99,7 @@ struct klp_object {
 	struct klp_func *funcs;
 
 	/* internal */
-	struct kobject *kobj;
+	struct kobject kobj;
 	struct module *mod;
 	enum klp_state state;
 };
@@ -123,6 +123,12 @@ struct klp_patch {
 	enum klp_state state;
 };
 
+#define klp_for_each_object(patch, obj) \
+	for (obj = patch->objs; obj->funcs; obj++)
+
+#define klp_for_each_func(obj, func) \
+	for (func = obj->funcs; func->old_name; func++)
+
 int klp_register_patch(struct klp_patch *);
 int klp_unregister_patch(struct klp_patch *);
 int klp_enable_patch(struct klp_patch *);
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 066ba4157541..2722111591a3 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -130,8 +130,8 @@ enum bounce_type {
 };
 
 struct lock_class_stats {
-	unsigned long			contention_point[4];
-	unsigned long			contending_point[4];
+	unsigned long			contention_point[LOCKSTAT_POINTS];
+	unsigned long			contending_point[LOCKSTAT_POINTS];
 	struct lock_time		read_waittime;
 	struct lock_time		write_waittime;
 	struct lock_time		read_holdtime;
diff --git a/include/linux/mbus.h b/include/linux/mbus.h
index 611b69fa8594..1f7bc630d225 100644
--- a/include/linux/mbus.h
+++ b/include/linux/mbus.h
@@ -54,11 +54,16 @@ struct mbus_dram_target_info
  */
 #ifdef CONFIG_PLAT_ORION
 extern const struct mbus_dram_target_info *mv_mbus_dram_info(void);
+extern const struct mbus_dram_target_info *mv_mbus_dram_info_nooverlap(void);
 #else
 static inline const struct mbus_dram_target_info *mv_mbus_dram_info(void)
 {
 	return NULL;
 }
+static inline const struct mbus_dram_target_info *mv_mbus_dram_info_nooverlap(void)
+{
+	return NULL;
+}
 #endif
 
 int mvebu_mbus_save_cpu_target(u32 *store_addr);
diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h
index 19f0175c0afa..4d3776d25925 100644
--- a/include/linux/mmc/card.h
+++ b/include/linux/mmc/card.h
@@ -97,6 +97,7 @@ struct mmc_ext_csd {
 	u8			raw_erased_mem_count;	/* 181 */
 	u8			raw_ext_csd_structure;	/* 194 */
 	u8			raw_card_type;		/* 196 */
+	u8			raw_driver_strength;	/* 197 */
 	u8			out_of_int_time;	/* 198 */
 	u8			raw_pwr_cl_52_195;	/* 200 */
 	u8			raw_pwr_cl_26_195;	/* 201 */
@@ -305,6 +306,7 @@ struct mmc_card {
 
 	unsigned int		sd_bus_speed;	/* Bus Speed Mode set for the card */
 	unsigned int		mmc_avail_type;	/* supported device type by both host and card */
+	unsigned int		drive_strength;	/* for UHS-I, HS200 or HS400 */
 
 	struct dentry		*debugfs_root;
 	struct mmc_part	part[MMC_NUM_PHY_PARTITION]; /* physical partitions */
diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h
index de722d4e9d61..258daf914c6d 100644
--- a/include/linux/mmc/core.h
+++ b/include/linux/mmc/core.h
@@ -121,6 +121,7 @@ struct mmc_data {
 	struct mmc_request	*mrq;		/* associated request */
 
 	unsigned int		sg_len;		/* size of scatter list */
+	int			sg_count;	/* mapped sg entries */
 	struct scatterlist	*sg;		/* I/O scatter list */
 	s32			host_cookie;	/* host private data */
 };
diff --git a/include/linux/mmc/dw_mmc.h b/include/linux/mmc/dw_mmc.h
index 12111993a317..5be97676f1fa 100644
--- a/include/linux/mmc/dw_mmc.h
+++ b/include/linux/mmc/dw_mmc.h
@@ -226,12 +226,6 @@ struct dw_mci_dma_ops {
 #define DW_MCI_QUIRK_HIGHSPEED			BIT(2)
 /* Unreliable card detection */
 #define DW_MCI_QUIRK_BROKEN_CARD_DETECTION	BIT(3)
-/* No write protect */
-#define DW_MCI_QUIRK_NO_WRITE_PROTECT		BIT(4)
-
-/* Slot level quirks */
-/* This slot has no write protect */
-#define DW_MCI_SLOT_QUIRK_NO_WRITE_PROTECT	BIT(0)
 
 struct dma_pdata;
 
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index b5bedaec6223..1369e54faeb7 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -12,6 +12,7 @@
 
 #include <linux/leds.h>
 #include <linux/mutex.h>
+#include <linux/timer.h>
 #include <linux/sched.h>
 #include <linux/device.h>
 #include <linux/fault-inject.h>
@@ -131,7 +132,9 @@ struct mmc_host_ops {
 
 	/* Prepare HS400 target operating frequency depending host driver */
 	int	(*prepare_hs400_tuning)(struct mmc_host *host, struct mmc_ios *ios);
-	int	(*select_drive_strength)(unsigned int max_dtr, int host_drv, int card_drv);
+	int	(*select_drive_strength)(struct mmc_card *card,
+					 unsigned int max_dtr, int host_drv,
+					 int card_drv, int *drv_type);
 	void	(*hw_reset)(struct mmc_host *host);
 	void	(*card_event)(struct mmc_host *host);
 
@@ -285,6 +288,7 @@ struct mmc_host {
 				 MMC_CAP2_HS400_1_2V)
 #define MMC_CAP2_HSX00_1_2V	(MMC_CAP2_HS200_1_2V_SDR | MMC_CAP2_HS400_1_2V)
 #define MMC_CAP2_SDIO_IRQ_NOTHREAD (1 << 17)
+#define MMC_CAP2_NO_WRITE_PROTECT (1 << 18)	/* No physical write protect pin, assume that card is always read-write */
 
 	mmc_pm_flag_t		pm_caps;	/* supported pm features */
 
@@ -321,10 +325,18 @@ struct mmc_host {
 #ifdef CONFIG_MMC_DEBUG
 	unsigned int		removed:1;	/* host is being removed */
 #endif
+	unsigned int		can_retune:1;	/* re-tuning can be used */
+	unsigned int		doing_retune:1;	/* re-tuning in progress */
+	unsigned int		retune_now:1;	/* do re-tuning at next req */
 
 	int			rescan_disable;	/* disable card detection */
 	int			rescan_entered;	/* used with nonremovable devices */
 
+	int			need_retune;	/* re-tuning is needed */
+	int			hold_retune;	/* hold off re-tuning */
+	unsigned int		retune_period;	/* re-tuning period in secs */
+	struct timer_list	retune_timer;	/* for periodic re-tuning */
+
 	bool			trigger_card_event; /* card_event necessary */
 
 	struct mmc_card		*card;		/* device attached to this host */
@@ -513,4 +525,18 @@ static inline bool mmc_card_hs400(struct mmc_card *card)
 	return card->host->ios.timing == MMC_TIMING_MMC_HS400;
 }
 
+void mmc_retune_timer_stop(struct mmc_host *host);
+
+static inline void mmc_retune_needed(struct mmc_host *host)
+{
+	if (host->can_retune)
+		host->need_retune = 1;
+}
+
+static inline void mmc_retune_recheck(struct mmc_host *host)
+{
+	if (host->hold_retune <= 1)
+		host->retune_now = 1;
+}
+
 #endif /* LINUX_MMC_HOST_H */
diff --git a/include/linux/mmc/mmc.h b/include/linux/mmc/mmc.h
index 124f562118b8..15f2c4a0a62c 100644
--- a/include/linux/mmc/mmc.h
+++ b/include/linux/mmc/mmc.h
@@ -302,6 +302,7 @@ struct _mmc_csd {
 #define EXT_CSD_REV			192	/* RO */
 #define EXT_CSD_STRUCTURE		194	/* RO */
 #define EXT_CSD_CARD_TYPE		196	/* RO */
+#define EXT_CSD_DRIVER_STRENGTH		197	/* RO */
 #define EXT_CSD_OUT_OF_INTERRUPT_TIME	198	/* RO */
 #define EXT_CSD_PART_SWITCH_TIME        199     /* RO */
 #define EXT_CSD_PWR_CL_52_195		200	/* RO */
@@ -390,6 +391,7 @@ struct _mmc_csd {
 #define EXT_CSD_TIMING_HS	1	/* High speed */
 #define EXT_CSD_TIMING_HS200	2	/* HS200 */
 #define EXT_CSD_TIMING_HS400	3	/* HS400 */
+#define EXT_CSD_DRV_STR_SHIFT	4	/* Driver Strength shift */
 
 #define EXT_CSD_SEC_ER_EN	BIT(0)
 #define EXT_CSD_SEC_BD_BLK_EN	BIT(2)
@@ -441,4 +443,6 @@ struct _mmc_csd {
 #define MMC_SWITCH_MODE_CLEAR_BITS	0x02	/* Clear bits which are 1 in value */
 #define MMC_SWITCH_MODE_WRITE_BYTE	0x03	/* Set target to value */
 
+#define mmc_driver_type_mask(n)		(1 << (n))
+
 #endif /* LINUX_MMC_MMC_H */
diff --git a/include/linux/mmc/sdhci-pci-data.h b/include/linux/mmc/sdhci-pci-data.h
index 8959604a13d3..fda15b6d4135 100644
--- a/include/linux/mmc/sdhci-pci-data.h
+++ b/include/linux/mmc/sdhci-pci-data.h
@@ -15,4 +15,6 @@ struct sdhci_pci_data {
 extern struct sdhci_pci_data *(*sdhci_pci_get_data)(struct pci_dev *pdev,
 				int slotno);
 
+extern int sdhci_pci_spt_drive_strength;
+
 #endif
diff --git a/include/linux/module.h b/include/linux/module.h
index c883b86ea964..1e5436042eb0 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -655,4 +655,16 @@ static inline void module_bug_finalize(const Elf_Ehdr *hdr,
 static inline void module_bug_cleanup(struct module *mod) {}
 #endif	/* CONFIG_GENERIC_BUG */
 
+#ifdef CONFIG_MODULE_SIG
+static inline bool module_sig_ok(struct module *module)
+{
+	return module->sig_ok;
+}
+#else	/* !CONFIG_MODULE_SIG */
+static inline bool module_sig_ok(struct module *module)
+{
+	return true;
+}
+#endif	/* CONFIG_MODULE_SIG */
+
 #endif /* _LINUX_MODULE_H */
diff --git a/include/linux/mpi.h b/include/linux/mpi.h
index 5af1b81def49..641b7d6fd096 100644
--- a/include/linux/mpi.h
+++ b/include/linux/mpi.h
@@ -81,6 +81,8 @@ MPI mpi_read_from_buffer(const void *buffer, unsigned *ret_nread);
 int mpi_fromstr(MPI val, const char *str);
 u32 mpi_get_keyid(MPI a, u32 *keyid);
 void *mpi_get_buffer(MPI a, unsigned *nbytes, int *sign);
+int mpi_read_buffer(MPI a, uint8_t *buf, unsigned buf_len, unsigned *nbytes,
+		    int *sign);
 void *mpi_get_secure_buffer(MPI a, unsigned *nbytes, int *sign);
 int mpi_set_buffer(MPI a, const void *buffer, unsigned nbytes, int sign);
 
@@ -142,4 +144,17 @@ int mpi_rshift(MPI x, MPI a, unsigned n);
 /*-- mpi-inv.c --*/
 int mpi_invm(MPI x, MPI u, MPI v);
 
+/* inline functions */
+
+/**
+ * mpi_get_size() - returns max size required to store the number
+ *
+ * @a:	A multi precision integer for which we want to allocate a bufer
+ *
+ * Return: size required to store the number
+ */
+static inline unsigned int mpi_get_size(MPI a)
+{
+	return a->nlimbs * BYTES_PER_MPI_LIMB;
+}
 #endif /*G10_MPI_H */
diff --git a/include/linux/namei.h b/include/linux/namei.h
index c8990779f0c3..d8c6334cd150 100644
--- a/include/linux/namei.h
+++ b/include/linux/namei.h
@@ -1,16 +1,15 @@
 #ifndef _LINUX_NAMEI_H
 #define _LINUX_NAMEI_H
 
-#include <linux/dcache.h>
-#include <linux/errno.h>
-#include <linux/linkage.h>
+#include <linux/kernel.h>
 #include <linux/path.h>
-
-struct vfsmount;
-struct nameidata;
+#include <linux/fcntl.h>
+#include <linux/errno.h>
 
 enum { MAX_NESTED_LINKS = 8 };
 
+#define MAXSYMLINKS 40
+
 /*
  * Type of the last component on LOOKUP_PARENT
  */
@@ -45,13 +44,29 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND};
 #define LOOKUP_ROOT		0x2000
 #define LOOKUP_EMPTY		0x4000
 
-extern int user_path_at(int, const char __user *, unsigned, struct path *);
 extern int user_path_at_empty(int, const char __user *, unsigned, struct path *, int *empty);
 
-#define user_path(name, path) user_path_at(AT_FDCWD, name, LOOKUP_FOLLOW, path)
-#define user_lpath(name, path) user_path_at(AT_FDCWD, name, 0, path)
-#define user_path_dir(name, path) \
-	user_path_at(AT_FDCWD, name, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, path)
+static inline int user_path_at(int dfd, const char __user *name, unsigned flags,
+		 struct path *path)
+{
+	return user_path_at_empty(dfd, name, flags, path, NULL);
+}
+
+static inline int user_path(const char __user *name, struct path *path)
+{
+	return user_path_at_empty(AT_FDCWD, name, LOOKUP_FOLLOW, path, NULL);
+}
+
+static inline int user_lpath(const char __user *name, struct path *path)
+{
+	return user_path_at_empty(AT_FDCWD, name, 0, path, NULL);
+}
+
+static inline int user_path_dir(const char __user *name, struct path *path)
+{
+	return user_path_at_empty(AT_FDCWD, name,
+				  LOOKUP_FOLLOW | LOOKUP_DIRECTORY, path, NULL);
+}
 
 extern int kern_path(const char *, unsigned, struct path *);
 
@@ -70,9 +85,7 @@ extern int follow_up(struct path *);
 extern struct dentry *lock_rename(struct dentry *, struct dentry *);
 extern void unlock_rename(struct dentry *, struct dentry *);
 
-extern void nd_jump_link(struct nameidata *nd, struct path *path);
-extern void nd_set_link(struct nameidata *nd, char *path);
-extern char *nd_get_link(struct nameidata *nd);
+extern void nd_jump_link(struct path *path);
 
 static inline void nd_terminate_link(void *name, size_t len, size_t maxlen)
 {
diff --git a/include/linux/netfilter_bridge/ebtables.h b/include/linux/netfilter_bridge/ebtables.h
index f1bd3962e6b6..8ca6d6464ea3 100644
--- a/include/linux/netfilter_bridge/ebtables.h
+++ b/include/linux/netfilter_bridge/ebtables.h
@@ -6,7 +6,7 @@
  *
  *  ebtables.c,v 2.0, April, 2002
  *
- *  This code is stongly inspired on the iptables code which is
+ *  This code is strongly inspired by the iptables code which is
  *  Copyright (C) 1999 Paul `Rusty' Russell & Michael J. Neuling
  */
 #ifndef __LINUX_BRIDGE_EFF_H
diff --git a/include/linux/nx842.h b/include/linux/nx842.h
deleted file mode 100644
index a4d324c6406a..000000000000
--- a/include/linux/nx842.h
+++ /dev/null
@@ -1,11 +0,0 @@
-#ifndef __NX842_H__
-#define __NX842_H__
-
-int nx842_get_workmem_size(void);
-int nx842_get_workmem_size_aligned(void);
-int nx842_compress(const unsigned char *in, unsigned int in_len,
-		unsigned char *out, unsigned int *out_len, void *wrkmem);
-int nx842_decompress(const unsigned char *in, unsigned int in_len,
-		unsigned char *out, unsigned int *out_len, void *wrkmem);
-
-#endif
diff --git a/include/linux/osq_lock.h b/include/linux/osq_lock.h
index 3a6490e81b28..703ea5c30a33 100644
--- a/include/linux/osq_lock.h
+++ b/include/linux/osq_lock.h
@@ -32,4 +32,9 @@ static inline void osq_lock_init(struct optimistic_spin_queue *lock)
 extern bool osq_lock(struct optimistic_spin_queue *lock);
 extern void osq_unlock(struct optimistic_spin_queue *lock);
 
+static inline bool osq_is_locked(struct optimistic_spin_queue *lock)
+{
+	return atomic_read(&lock->tail) != OSQ_UNLOCKED_VAL;
+}
+
 #endif
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 353db8dc4c6e..8a0321a8fb59 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -355,6 +355,7 @@ struct pci_dev {
 	unsigned int	broken_intx_masking:1;
 	unsigned int	io_window_1k:1;	/* Intel P2P bridge 1K I/O windows */
 	unsigned int	irq_managed:1;
+	unsigned int	has_secondary_link:1;
 	pci_dev_flags_t dev_flags;
 	atomic_t	enable_cnt;	/* pci_enable_device has been called */
 
@@ -577,9 +578,15 @@ int raw_pci_read(unsigned int domain, unsigned int bus, unsigned int devfn,
 int raw_pci_write(unsigned int domain, unsigned int bus, unsigned int devfn,
 		  int reg, int len, u32 val);
 
+#ifdef CONFIG_PCI_BUS_ADDR_T_64BIT
+typedef u64 pci_bus_addr_t;
+#else
+typedef u32 pci_bus_addr_t;
+#endif
+
 struct pci_bus_region {
-	dma_addr_t start;
-	dma_addr_t end;
+	pci_bus_addr_t start;
+	pci_bus_addr_t end;
 };
 
 struct pci_dynids {
@@ -773,8 +780,6 @@ void pcibios_bus_to_resource(struct pci_bus *bus, struct resource *res,
 void pcibios_scan_specific_bus(int busn);
 struct pci_bus *pci_find_bus(int domain, int busnr);
 void pci_bus_add_devices(const struct pci_bus *bus);
-struct pci_bus *pci_scan_bus_parented(struct device *parent, int bus,
-				      struct pci_ops *ops, void *sysdata);
 struct pci_bus *pci_scan_bus(int bus, struct pci_ops *ops, void *sysdata);
 struct pci_bus *pci_create_root_bus(struct device *parent, int bus,
 				    struct pci_ops *ops, void *sysdata,
@@ -974,7 +979,6 @@ void pci_intx(struct pci_dev *dev, int enable);
 bool pci_intx_mask_supported(struct pci_dev *dev);
 bool pci_check_and_mask_intx(struct pci_dev *dev);
 bool pci_check_and_unmask_intx(struct pci_dev *dev);
-void pci_msi_off(struct pci_dev *dev);
 int pci_set_dma_max_seg_size(struct pci_dev *dev, unsigned int size);
 int pci_set_dma_seg_boundary(struct pci_dev *dev, unsigned long mask);
 int pci_wait_for_pending(struct pci_dev *dev, int pos, u16 mask);
@@ -1006,6 +1010,7 @@ int __must_check pci_assign_resource(struct pci_dev *dev, int i);
 int __must_check pci_reassign_resource(struct pci_dev *dev, int i, resource_size_t add_size, resource_size_t align);
 int pci_select_bars(struct pci_dev *dev, unsigned long flags);
 bool pci_device_is_present(struct pci_dev *pdev);
+void pci_ignore_hotplug(struct pci_dev *dev);
 
 /* ROM control related routines */
 int pci_enable_rom(struct pci_dev *pdev);
@@ -1043,11 +1048,6 @@ bool pci_dev_run_wake(struct pci_dev *dev);
 bool pci_check_pme_status(struct pci_dev *dev);
 void pci_pme_wakeup_bus(struct pci_bus *bus);
 
-static inline void pci_ignore_hotplug(struct pci_dev *dev)
-{
-	dev->ignore_hotplug = 1;
-}
-
 static inline int pci_enable_wake(struct pci_dev *dev, pci_power_t state,
 				  bool enable)
 {
@@ -1128,7 +1128,7 @@ int __must_check pci_bus_alloc_resource(struct pci_bus *bus,
 
 int pci_remap_iospace(const struct resource *res, phys_addr_t phys_addr);
 
-static inline dma_addr_t pci_bus_address(struct pci_dev *pdev, int bar)
+static inline pci_bus_addr_t pci_bus_address(struct pci_dev *pdev, int bar)
 {
 	struct pci_bus_region region;
 
@@ -1197,15 +1197,6 @@ int pci_set_vga_state(struct pci_dev *pdev, bool decode,
 #define	pci_pool_alloc(pool, flags, handle) dma_pool_alloc(pool, flags, handle)
 #define	pci_pool_free(pool, vaddr, addr) dma_pool_free(pool, vaddr, addr)
 
-enum pci_dma_burst_strategy {
-	PCI_DMA_BURST_INFINITY,	/* make bursts as large as possible,
-				   strategy_parameter is N/A */
-	PCI_DMA_BURST_BOUNDARY, /* disconnect at every strategy_parameter
-				   byte boundaries */
-	PCI_DMA_BURST_MULTIPLE, /* disconnect at some multiple of
-				   strategy_parameter byte boundaries */
-};
-
 struct msix_entry {
 	u32	vector;	/* kernel uses to write allocated vector */
 	u16	entry;	/* driver uses to specify entry, OS writes */
@@ -1430,8 +1421,6 @@ static inline int pci_request_regions(struct pci_dev *dev, const char *res_name)
 { return -EIO; }
 static inline void pci_release_regions(struct pci_dev *dev) { }
 
-#define pci_dma_burst_advice(pdev, strat, strategy_parameter) do { } while (0)
-
 static inline void pci_block_cfg_access(struct pci_dev *dev) { }
 static inline int pci_block_cfg_access_in_atomic(struct pci_dev *dev)
 { return 0; }
@@ -1905,4 +1894,15 @@ static inline bool pci_is_dev_assigned(struct pci_dev *pdev)
 {
 	return (pdev->dev_flags & PCI_DEV_FLAGS_ASSIGNED) == PCI_DEV_FLAGS_ASSIGNED;
 }
+
+/**
+ * pci_ari_enabled - query ARI forwarding status
+ * @bus: the PCI bus
+ *
+ * Returns true if ARI forwarding is enabled.
+ */
+static inline bool pci_ari_enabled(struct pci_bus *bus)
+{
+	return bus->self && bus->self->ari_enabled;
+}
 #endif /* LINUX_PCI_H */
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 2f7b9a40f627..cb63a7b522ef 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -579,6 +579,7 @@
 #define PCI_DEVICE_ID_AMD_HUDSON2_SATA_IDE	0x7800
 #define PCI_DEVICE_ID_AMD_HUDSON2_SMBUS		0x780b
 #define PCI_DEVICE_ID_AMD_HUDSON2_IDE		0x780c
+#define PCI_DEVICE_ID_AMD_KERNCZ_SMBUS  0x790b
 
 #define PCI_VENDOR_ID_TRIDENT		0x1023
 #define PCI_DEVICE_ID_TRIDENT_4DWAVE_DX	0x2000
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index d8a82a89f35a..1b82d44b0a02 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -120,7 +120,7 @@ struct hw_perf_event {
 		};
 		struct { /* intel_cqm */
 			int			cqm_state;
-			int			cqm_rmid;
+			u32			cqm_rmid;
 			struct list_head	cqm_events_entry;
 			struct list_head	cqm_groups_entry;
 			struct list_head	cqm_group_entry;
@@ -562,8 +562,12 @@ struct perf_cpu_context {
 	struct perf_event_context	*task_ctx;
 	int				active_oncpu;
 	int				exclusive;
+
+	raw_spinlock_t			hrtimer_lock;
 	struct hrtimer			hrtimer;
 	ktime_t				hrtimer_interval;
+	unsigned int			hrtimer_active;
+
 	struct pmu			*unique_pmu;
 	struct perf_cgroup		*cgrp;
 };
@@ -730,6 +734,22 @@ extern int perf_event_overflow(struct perf_event *event,
 				 struct perf_sample_data *data,
 				 struct pt_regs *regs);
 
+extern void perf_event_output(struct perf_event *event,
+				struct perf_sample_data *data,
+				struct pt_regs *regs);
+
+extern void
+perf_event_header__init_id(struct perf_event_header *header,
+			   struct perf_sample_data *data,
+			   struct perf_event *event);
+extern void
+perf_event__output_id_sample(struct perf_event *event,
+			     struct perf_output_handle *handle,
+			     struct perf_sample_data *sample);
+
+extern void
+perf_log_lost_samples(struct perf_event *event, u64 lost);
+
 static inline bool is_sampling_event(struct perf_event *event)
 {
 	return event->attr.sample_period != 0;
@@ -794,11 +814,33 @@ perf_sw_event_sched(u32 event_id, u64 nr, u64 addr)
 
 extern struct static_key_deferred perf_sched_events;
 
+static __always_inline bool
+perf_sw_migrate_enabled(void)
+{
+	if (static_key_false(&perf_swevent_enabled[PERF_COUNT_SW_CPU_MIGRATIONS]))
+		return true;
+	return false;
+}
+
+static inline void perf_event_task_migrate(struct task_struct *task)
+{
+	if (perf_sw_migrate_enabled())
+		task->sched_migrated = 1;
+}
+
 static inline void perf_event_task_sched_in(struct task_struct *prev,
 					    struct task_struct *task)
 {
 	if (static_key_false(&perf_sched_events.key))
 		__perf_event_task_sched_in(prev, task);
+
+	if (perf_sw_migrate_enabled() && task->sched_migrated) {
+		struct pt_regs *regs = this_cpu_ptr(&__perf_regs[0]);
+
+		perf_fetch_caller_regs(regs);
+		___perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS, 1, regs, 0);
+		task->sched_migrated = 0;
+	}
 }
 
 static inline void perf_event_task_sched_out(struct task_struct *prev,
@@ -921,6 +963,8 @@ perf_aux_output_skip(struct perf_output_handle *handle,
 static inline void *
 perf_get_aux(struct perf_output_handle *handle)				{ return NULL; }
 static inline void
+perf_event_task_migrate(struct task_struct *task)			{ }
+static inline void
 perf_event_task_sched_in(struct task_struct *prev,
 			 struct task_struct *task)			{ }
 static inline void
diff --git a/include/linux/platform_data/gpio-omap.h b/include/linux/platform_data/gpio-omap.h
index 5d50b25a73d7..cb2618147c34 100644
--- a/include/linux/platform_data/gpio-omap.h
+++ b/include/linux/platform_data/gpio-omap.h
@@ -208,9 +208,17 @@ struct omap_gpio_platform_data {
 	int (*get_context_loss_count)(struct device *dev);
 };
 
+#if IS_BUILTIN(CONFIG_GPIO_OMAP)
 extern void omap2_gpio_prepare_for_idle(int off_mode);
 extern void omap2_gpio_resume_after_idle(void);
-extern void omap_set_gpio_debounce(int gpio, int enable);
-extern void omap_set_gpio_debounce_time(int gpio, int enable);
+#else
+static inline void omap2_gpio_prepare_for_idle(int off_mode)
+{
+}
+
+static inline void omap2_gpio_resume_after_idle(void)
+{
+}
+#endif
 
 #endif
diff --git a/include/linux/platform_data/irq-renesas-irqc.h b/include/linux/platform_data/irq-renesas-irqc.h
deleted file mode 100644
index 3ae17b3e00ed..000000000000
--- a/include/linux/platform_data/irq-renesas-irqc.h
+++ /dev/null
@@ -1,27 +0,0 @@
-/*
- * Renesas IRQC Driver
- *
- *  Copyright (C) 2013 Magnus Damm
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- */
-
-#ifndef __IRQ_RENESAS_IRQC_H__
-#define __IRQ_RENESAS_IRQC_H__
-
-struct renesas_irqc_config {
-	unsigned int irq_base;
-};
-
-#endif /* __IRQ_RENESAS_IRQC_H__ */
diff --git a/include/linux/platform_data/ntc_thermistor.h b/include/linux/platform_data/ntc_thermistor.h
index 0a6de4ca4930..aed170588b74 100644
--- a/include/linux/platform_data/ntc_thermistor.h
+++ b/include/linux/platform_data/ntc_thermistor.h
@@ -27,6 +27,7 @@ enum ntc_thermistor_type {
 	TYPE_NCPXXWB473,
 	TYPE_NCPXXWL333,
 	TYPE_B57330V2103,
+	TYPE_NCPXXWF104,
 };
 
 struct ntc_thermistor_platform_data {
diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index de83b4eb1642..0f1534acaf60 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -10,13 +10,117 @@
 #include <linux/list.h>
 
 /*
- * We use the MSB mostly because its available; see <linux/preempt_mask.h> for
- * the other bits -- can't include that header due to inclusion hell.
+ * We put the hardirq and softirq counter into the preemption
+ * counter. The bitmask has the following meaning:
+ *
+ * - bits 0-7 are the preemption count (max preemption depth: 256)
+ * - bits 8-15 are the softirq count (max # of softirqs: 256)
+ *
+ * The hardirq count could in theory be the same as the number of
+ * interrupts in the system, but we run all interrupt handlers with
+ * interrupts disabled, so we cannot have nesting interrupts. Though
+ * there are a few palaeontologic drivers which reenable interrupts in
+ * the handler, so we need more than one bit here.
+ *
+ *         PREEMPT_MASK:	0x000000ff
+ *         SOFTIRQ_MASK:	0x0000ff00
+ *         HARDIRQ_MASK:	0x000f0000
+ *             NMI_MASK:	0x00100000
+ *       PREEMPT_ACTIVE:	0x00200000
+ * PREEMPT_NEED_RESCHED:	0x80000000
  */
+#define PREEMPT_BITS	8
+#define SOFTIRQ_BITS	8
+#define HARDIRQ_BITS	4
+#define NMI_BITS	1
+
+#define PREEMPT_SHIFT	0
+#define SOFTIRQ_SHIFT	(PREEMPT_SHIFT + PREEMPT_BITS)
+#define HARDIRQ_SHIFT	(SOFTIRQ_SHIFT + SOFTIRQ_BITS)
+#define NMI_SHIFT	(HARDIRQ_SHIFT + HARDIRQ_BITS)
+
+#define __IRQ_MASK(x)	((1UL << (x))-1)
+
+#define PREEMPT_MASK	(__IRQ_MASK(PREEMPT_BITS) << PREEMPT_SHIFT)
+#define SOFTIRQ_MASK	(__IRQ_MASK(SOFTIRQ_BITS) << SOFTIRQ_SHIFT)
+#define HARDIRQ_MASK	(__IRQ_MASK(HARDIRQ_BITS) << HARDIRQ_SHIFT)
+#define NMI_MASK	(__IRQ_MASK(NMI_BITS)     << NMI_SHIFT)
+
+#define PREEMPT_OFFSET	(1UL << PREEMPT_SHIFT)
+#define SOFTIRQ_OFFSET	(1UL << SOFTIRQ_SHIFT)
+#define HARDIRQ_OFFSET	(1UL << HARDIRQ_SHIFT)
+#define NMI_OFFSET	(1UL << NMI_SHIFT)
+
+#define SOFTIRQ_DISABLE_OFFSET	(2 * SOFTIRQ_OFFSET)
+
+#define PREEMPT_ACTIVE_BITS	1
+#define PREEMPT_ACTIVE_SHIFT	(NMI_SHIFT + NMI_BITS)
+#define PREEMPT_ACTIVE	(__IRQ_MASK(PREEMPT_ACTIVE_BITS) << PREEMPT_ACTIVE_SHIFT)
+
+/* We use the MSB mostly because its available */
 #define PREEMPT_NEED_RESCHED	0x80000000
 
+/* preempt_count() and related functions, depends on PREEMPT_NEED_RESCHED */
 #include <asm/preempt.h>
 
+#define hardirq_count()	(preempt_count() & HARDIRQ_MASK)
+#define softirq_count()	(preempt_count() & SOFTIRQ_MASK)
+#define irq_count()	(preempt_count() & (HARDIRQ_MASK | SOFTIRQ_MASK \
+				 | NMI_MASK))
+
+/*
+ * Are we doing bottom half or hardware interrupt processing?
+ * Are we in a softirq context? Interrupt context?
+ * in_softirq - Are we currently processing softirq or have bh disabled?
+ * in_serving_softirq - Are we currently processing softirq?
+ */
+#define in_irq()		(hardirq_count())
+#define in_softirq()		(softirq_count())
+#define in_interrupt()		(irq_count())
+#define in_serving_softirq()	(softirq_count() & SOFTIRQ_OFFSET)
+
+/*
+ * Are we in NMI context?
+ */
+#define in_nmi()	(preempt_count() & NMI_MASK)
+
+#if defined(CONFIG_PREEMPT_COUNT)
+# define PREEMPT_DISABLE_OFFSET 1
+#else
+# define PREEMPT_DISABLE_OFFSET 0
+#endif
+
+/*
+ * The preempt_count offset needed for things like:
+ *
+ *  spin_lock_bh()
+ *
+ * Which need to disable both preemption (CONFIG_PREEMPT_COUNT) and
+ * softirqs, such that unlock sequences of:
+ *
+ *  spin_unlock();
+ *  local_bh_enable();
+ *
+ * Work as expected.
+ */
+#define SOFTIRQ_LOCK_OFFSET (SOFTIRQ_DISABLE_OFFSET + PREEMPT_DISABLE_OFFSET)
+
+/*
+ * Are we running in atomic context?  WARNING: this macro cannot
+ * always detect atomic context; in particular, it cannot know about
+ * held spinlocks in non-preemptible kernels.  Thus it should not be
+ * used in the general case to determine whether sleeping is possible.
+ * Do not use in_atomic() in driver code.
+ */
+#define in_atomic()	(preempt_count() != 0)
+
+/*
+ * Check whether we were atomic before we did preempt_disable():
+ * (used by the scheduler)
+ */
+#define in_atomic_preempt_off() \
+		((preempt_count() & ~PREEMPT_ACTIVE) != PREEMPT_DISABLE_OFFSET)
+
 #if defined(CONFIG_DEBUG_PREEMPT) || defined(CONFIG_PREEMPT_TRACER)
 extern void preempt_count_add(int val);
 extern void preempt_count_sub(int val);
@@ -33,6 +137,18 @@ extern void preempt_count_sub(int val);
 #define preempt_count_inc() preempt_count_add(1)
 #define preempt_count_dec() preempt_count_sub(1)
 
+#define preempt_active_enter() \
+do { \
+	preempt_count_add(PREEMPT_ACTIVE + PREEMPT_DISABLE_OFFSET); \
+	barrier(); \
+} while (0)
+
+#define preempt_active_exit() \
+do { \
+	barrier(); \
+	preempt_count_sub(PREEMPT_ACTIVE + PREEMPT_DISABLE_OFFSET); \
+} while (0)
+
 #ifdef CONFIG_PREEMPT_COUNT
 
 #define preempt_disable() \
@@ -49,6 +165,8 @@ do { \
 
 #define preempt_enable_no_resched() sched_preempt_enable_no_resched()
 
+#define preemptible()	(preempt_count() == 0 && !irqs_disabled())
+
 #ifdef CONFIG_PREEMPT
 #define preempt_enable() \
 do { \
@@ -57,52 +175,46 @@ do { \
 		__preempt_schedule(); \
 } while (0)
 
+#define preempt_enable_notrace() \
+do { \
+	barrier(); \
+	if (unlikely(__preempt_count_dec_and_test())) \
+		__preempt_schedule_notrace(); \
+} while (0)
+
 #define preempt_check_resched() \
 do { \
 	if (should_resched()) \
 		__preempt_schedule(); \
 } while (0)
 
-#else
+#else /* !CONFIG_PREEMPT */
 #define preempt_enable() \
 do { \
 	barrier(); \
 	preempt_count_dec(); \
 } while (0)
-#define preempt_check_resched() do { } while (0)
-#endif
-
-#define preempt_disable_notrace() \
-do { \
-	__preempt_count_inc(); \
-	barrier(); \
-} while (0)
 
-#define preempt_enable_no_resched_notrace() \
+#define preempt_enable_notrace() \
 do { \
 	barrier(); \
 	__preempt_count_dec(); \
 } while (0)
 
-#ifdef CONFIG_PREEMPT
-
-#ifndef CONFIG_CONTEXT_TRACKING
-#define __preempt_schedule_context() __preempt_schedule()
-#endif
+#define preempt_check_resched() do { } while (0)
+#endif /* CONFIG_PREEMPT */
 
-#define preempt_enable_notrace() \
+#define preempt_disable_notrace() \
 do { \
+	__preempt_count_inc(); \
 	barrier(); \
-	if (unlikely(__preempt_count_dec_and_test())) \
-		__preempt_schedule_context(); \
 } while (0)
-#else
-#define preempt_enable_notrace() \
+
+#define preempt_enable_no_resched_notrace() \
 do { \
 	barrier(); \
 	__preempt_count_dec(); \
 } while (0)
-#endif
 
 #else /* !CONFIG_PREEMPT_COUNT */
 
@@ -121,6 +233,7 @@ do { \
 #define preempt_disable_notrace()		barrier()
 #define preempt_enable_no_resched_notrace()	barrier()
 #define preempt_enable_notrace()		barrier()
+#define preemptible()				0
 
 #endif /* CONFIG_PREEMPT_COUNT */
 
diff --git a/include/linux/preempt_mask.h b/include/linux/preempt_mask.h
deleted file mode 100644
index dbeec4d4a3be..000000000000
--- a/include/linux/preempt_mask.h
+++ /dev/null
@@ -1,117 +0,0 @@
-#ifndef LINUX_PREEMPT_MASK_H
-#define LINUX_PREEMPT_MASK_H
-
-#include <linux/preempt.h>
-
-/*
- * We put the hardirq and softirq counter into the preemption
- * counter. The bitmask has the following meaning:
- *
- * - bits 0-7 are the preemption count (max preemption depth: 256)
- * - bits 8-15 are the softirq count (max # of softirqs: 256)
- *
- * The hardirq count could in theory be the same as the number of
- * interrupts in the system, but we run all interrupt handlers with
- * interrupts disabled, so we cannot have nesting interrupts. Though
- * there are a few palaeontologic drivers which reenable interrupts in
- * the handler, so we need more than one bit here.
- *
- * PREEMPT_MASK:	0x000000ff
- * SOFTIRQ_MASK:	0x0000ff00
- * HARDIRQ_MASK:	0x000f0000
- *     NMI_MASK:	0x00100000
- * PREEMPT_ACTIVE:	0x00200000
- */
-#define PREEMPT_BITS	8
-#define SOFTIRQ_BITS	8
-#define HARDIRQ_BITS	4
-#define NMI_BITS	1
-
-#define PREEMPT_SHIFT	0
-#define SOFTIRQ_SHIFT	(PREEMPT_SHIFT + PREEMPT_BITS)
-#define HARDIRQ_SHIFT	(SOFTIRQ_SHIFT + SOFTIRQ_BITS)
-#define NMI_SHIFT	(HARDIRQ_SHIFT + HARDIRQ_BITS)
-
-#define __IRQ_MASK(x)	((1UL << (x))-1)
-
-#define PREEMPT_MASK	(__IRQ_MASK(PREEMPT_BITS) << PREEMPT_SHIFT)
-#define SOFTIRQ_MASK	(__IRQ_MASK(SOFTIRQ_BITS) << SOFTIRQ_SHIFT)
-#define HARDIRQ_MASK	(__IRQ_MASK(HARDIRQ_BITS) << HARDIRQ_SHIFT)
-#define NMI_MASK	(__IRQ_MASK(NMI_BITS)     << NMI_SHIFT)
-
-#define PREEMPT_OFFSET	(1UL << PREEMPT_SHIFT)
-#define SOFTIRQ_OFFSET	(1UL << SOFTIRQ_SHIFT)
-#define HARDIRQ_OFFSET	(1UL << HARDIRQ_SHIFT)
-#define NMI_OFFSET	(1UL << NMI_SHIFT)
-
-#define SOFTIRQ_DISABLE_OFFSET	(2 * SOFTIRQ_OFFSET)
-
-#define PREEMPT_ACTIVE_BITS	1
-#define PREEMPT_ACTIVE_SHIFT	(NMI_SHIFT + NMI_BITS)
-#define PREEMPT_ACTIVE	(__IRQ_MASK(PREEMPT_ACTIVE_BITS) << PREEMPT_ACTIVE_SHIFT)
-
-#define hardirq_count()	(preempt_count() & HARDIRQ_MASK)
-#define softirq_count()	(preempt_count() & SOFTIRQ_MASK)
-#define irq_count()	(preempt_count() & (HARDIRQ_MASK | SOFTIRQ_MASK \
-				 | NMI_MASK))
-
-/*
- * Are we doing bottom half or hardware interrupt processing?
- * Are we in a softirq context? Interrupt context?
- * in_softirq - Are we currently processing softirq or have bh disabled?
- * in_serving_softirq - Are we currently processing softirq?
- */
-#define in_irq()		(hardirq_count())
-#define in_softirq()		(softirq_count())
-#define in_interrupt()		(irq_count())
-#define in_serving_softirq()	(softirq_count() & SOFTIRQ_OFFSET)
-
-/*
- * Are we in NMI context?
- */
-#define in_nmi()	(preempt_count() & NMI_MASK)
-
-#if defined(CONFIG_PREEMPT_COUNT)
-# define PREEMPT_CHECK_OFFSET 1
-#else
-# define PREEMPT_CHECK_OFFSET 0
-#endif
-
-/*
- * The preempt_count offset needed for things like:
- *
- *  spin_lock_bh()
- *
- * Which need to disable both preemption (CONFIG_PREEMPT_COUNT) and
- * softirqs, such that unlock sequences of:
- *
- *  spin_unlock();
- *  local_bh_enable();
- *
- * Work as expected.
- */
-#define SOFTIRQ_LOCK_OFFSET (SOFTIRQ_DISABLE_OFFSET + PREEMPT_CHECK_OFFSET)
-
-/*
- * Are we running in atomic context?  WARNING: this macro cannot
- * always detect atomic context; in particular, it cannot know about
- * held spinlocks in non-preemptible kernels.  Thus it should not be
- * used in the general case to determine whether sleeping is possible.
- * Do not use in_atomic() in driver code.
- */
-#define in_atomic()	((preempt_count() & ~PREEMPT_ACTIVE) != 0)
-
-/*
- * Check whether we were atomic before we did preempt_disable():
- * (used by the scheduler, *after* releasing the kernel lock)
- */
-#define in_atomic_preempt_off() \
-		((preempt_count() & ~PREEMPT_ACTIVE) != PREEMPT_CHECK_OFFSET)
-
-#ifdef CONFIG_PREEMPT_COUNT
-# define preemptible()	(preempt_count() == 0 && !irqs_disabled())
-#else
-# define preemptible()	0
-#endif
-
-#endif /* LINUX_PREEMPT_MASK_H */
diff --git a/include/linux/pwm.h b/include/linux/pwm.h
index e90628cac8fa..36262d08a9da 100644
--- a/include/linux/pwm.h
+++ b/include/linux/pwm.h
@@ -182,6 +182,8 @@ struct pwm_chip {
 int pwm_set_chip_data(struct pwm_device *pwm, void *data);
 void *pwm_get_chip_data(struct pwm_device *pwm);
 
+int pwmchip_add_with_polarity(struct pwm_chip *chip,
+			      enum pwm_polarity polarity);
 int pwmchip_add(struct pwm_chip *chip);
 int pwmchip_remove(struct pwm_chip *chip);
 struct pwm_device *pwm_request_from_chip(struct pwm_chip *chip,
@@ -217,6 +219,11 @@ static inline int pwmchip_add(struct pwm_chip *chip)
 	return -EINVAL;
 }
 
+static inline int pwmchip_add_inversed(struct pwm_chip *chip)
+{
+	return -EINVAL;
+}
+
 static inline int pwmchip_remove(struct pwm_chip *chip)
 {
 	return -EINVAL;
@@ -290,10 +297,15 @@ struct pwm_lookup {
 
 #if IS_ENABLED(CONFIG_PWM)
 void pwm_add_table(struct pwm_lookup *table, size_t num);
+void pwm_remove_table(struct pwm_lookup *table, size_t num);
 #else
 static inline void pwm_add_table(struct pwm_lookup *table, size_t num)
 {
 }
+
+static inline void pwm_remove_table(struct pwm_lookup *table, size_t num)
+{
+}
 #endif
 
 #ifdef CONFIG_PWM_SYSFS
diff --git a/include/linux/random.h b/include/linux/random.h
index b05856e16b75..e651874df2c9 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -6,14 +6,23 @@
 #ifndef _LINUX_RANDOM_H
 #define _LINUX_RANDOM_H
 
+#include <linux/list.h>
 #include <uapi/linux/random.h>
 
+struct random_ready_callback {
+	struct list_head list;
+	void (*func)(struct random_ready_callback *rdy);
+	struct module *owner;
+};
+
 extern void add_device_randomness(const void *, unsigned int);
 extern void add_input_randomness(unsigned int type, unsigned int code,
 				 unsigned int value);
 extern void add_interrupt_randomness(int irq, int irq_flags);
 
 extern void get_random_bytes(void *buf, int nbytes);
+extern int add_random_ready_callback(struct random_ready_callback *rdy);
+extern void del_random_ready_callback(struct random_ready_callback *rdy);
 extern void get_random_bytes_arch(void *buf, int nbytes);
 void generate_random_uuid(unsigned char uuid_out[16]);
 extern int random_int_secret_init(void);
diff --git a/include/linux/rculist.h b/include/linux/rculist.h
index a18b16f1dc0e..17c6b1f84a77 100644
--- a/include/linux/rculist.h
+++ b/include/linux/rculist.h
@@ -29,8 +29,8 @@
  */
 static inline void INIT_LIST_HEAD_RCU(struct list_head *list)
 {
-	ACCESS_ONCE(list->next) = list;
-	ACCESS_ONCE(list->prev) = list;
+	WRITE_ONCE(list->next, list);
+	WRITE_ONCE(list->prev, list);
 }
 
 /*
@@ -288,7 +288,7 @@ static inline void list_splice_init_rcu(struct list_head *list,
 #define list_first_or_null_rcu(ptr, type, member) \
 ({ \
 	struct list_head *__ptr = (ptr); \
-	struct list_head *__next = ACCESS_ONCE(__ptr->next); \
+	struct list_head *__next = READ_ONCE(__ptr->next); \
 	likely(__ptr != __next) ? list_entry_rcu(__next, type, member) : NULL; \
 })
 
@@ -549,8 +549,8 @@ static inline void hlist_add_behind_rcu(struct hlist_node *n,
  */
 #define hlist_for_each_entry_from_rcu(pos, member)			\
 	for (; pos;							\
-	     pos = hlist_entry_safe(rcu_dereference((pos)->member.next),\
-			typeof(*(pos)), member))
+	     pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(	\
+			&(pos)->member)), typeof(*(pos)), member))
 
 #endif	/* __KERNEL__ */
 #endif
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 573a5afd5ed8..33a056bb886f 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -44,6 +44,8 @@
 #include <linux/debugobjects.h>
 #include <linux/bug.h>
 #include <linux/compiler.h>
+#include <linux/ktime.h>
+
 #include <asm/barrier.h>
 
 extern int rcu_expedited; /* for sysctl */
@@ -292,10 +294,6 @@ void rcu_sched_qs(void);
 void rcu_bh_qs(void);
 void rcu_check_callbacks(int user);
 struct notifier_block;
-void rcu_idle_enter(void);
-void rcu_idle_exit(void);
-void rcu_irq_enter(void);
-void rcu_irq_exit(void);
 int rcu_cpu_notify(struct notifier_block *self,
 		   unsigned long action, void *hcpu);
 
@@ -364,8 +362,8 @@ extern struct srcu_struct tasks_rcu_exit_srcu;
 #define rcu_note_voluntary_context_switch(t) \
 	do { \
 		rcu_all_qs(); \
-		if (ACCESS_ONCE((t)->rcu_tasks_holdout)) \
-			ACCESS_ONCE((t)->rcu_tasks_holdout) = false; \
+		if (READ_ONCE((t)->rcu_tasks_holdout)) \
+			WRITE_ONCE((t)->rcu_tasks_holdout, false); \
 	} while (0)
 #else /* #ifdef CONFIG_TASKS_RCU */
 #define TASKS_RCU(x) do { } while (0)
@@ -609,7 +607,7 @@ static inline void rcu_preempt_sleep_check(void)
 
 #define __rcu_access_pointer(p, space) \
 ({ \
-	typeof(*p) *_________p1 = (typeof(*p) *__force)ACCESS_ONCE(p); \
+	typeof(*p) *_________p1 = (typeof(*p) *__force)READ_ONCE(p); \
 	rcu_dereference_sparse(p, space); \
 	((typeof(*p) __force __kernel *)(_________p1)); \
 })
@@ -628,21 +626,6 @@ static inline void rcu_preempt_sleep_check(void)
 	((typeof(*p) __force __kernel *)(p)); \
 })
 
-#define __rcu_access_index(p, space) \
-({ \
-	typeof(p) _________p1 = ACCESS_ONCE(p); \
-	rcu_dereference_sparse(p, space); \
-	(_________p1); \
-})
-#define __rcu_dereference_index_check(p, c) \
-({ \
-	/* Dependency order vs. p above. */ \
-	typeof(p) _________p1 = lockless_dereference(p); \
-	rcu_lockdep_assert(c, \
-			   "suspicious rcu_dereference_index_check() usage"); \
-	(_________p1); \
-})
-
 /**
  * RCU_INITIALIZER() - statically initialize an RCU-protected global variable
  * @v: The value to statically initialize with.
@@ -659,7 +642,7 @@ static inline void rcu_preempt_sleep_check(void)
  */
 #define lockless_dereference(p) \
 ({ \
-	typeof(p) _________p1 = ACCESS_ONCE(p); \
+	typeof(p) _________p1 = READ_ONCE(p); \
 	smp_read_barrier_depends(); /* Dependency order vs. p above. */ \
 	(_________p1); \
 })
@@ -702,7 +685,7 @@ static inline void rcu_preempt_sleep_check(void)
  * @p: The pointer to read
  *
  * Return the value of the specified RCU-protected pointer, but omit the
- * smp_read_barrier_depends() and keep the ACCESS_ONCE().  This is useful
+ * smp_read_barrier_depends() and keep the READ_ONCE().  This is useful
  * when the value of this pointer is accessed, but the pointer is not
  * dereferenced, for example, when testing an RCU-protected pointer against
  * NULL.  Although rcu_access_pointer() may also be used in cases where
@@ -787,47 +770,12 @@ static inline void rcu_preempt_sleep_check(void)
 #define rcu_dereference_raw_notrace(p) __rcu_dereference_check((p), 1, __rcu)
 
 /**
- * rcu_access_index() - fetch RCU index with no dereferencing
- * @p: The index to read
- *
- * Return the value of the specified RCU-protected index, but omit the
- * smp_read_barrier_depends() and keep the ACCESS_ONCE().  This is useful
- * when the value of this index is accessed, but the index is not
- * dereferenced, for example, when testing an RCU-protected index against
- * -1.  Although rcu_access_index() may also be used in cases where
- * update-side locks prevent the value of the index from changing, you
- * should instead use rcu_dereference_index_protected() for this use case.
- */
-#define rcu_access_index(p) __rcu_access_index((p), __rcu)
-
-/**
- * rcu_dereference_index_check() - rcu_dereference for indices with debug checking
- * @p: The pointer to read, prior to dereferencing
- * @c: The conditions under which the dereference will take place
- *
- * Similar to rcu_dereference_check(), but omits the sparse checking.
- * This allows rcu_dereference_index_check() to be used on integers,
- * which can then be used as array indices.  Attempting to use
- * rcu_dereference_check() on an integer will give compiler warnings
- * because the sparse address-space mechanism relies on dereferencing
- * the RCU-protected pointer.  Dereferencing integers is not something
- * that even gcc will put up with.
- *
- * Note that this function does not implicitly check for RCU read-side
- * critical sections.  If this function gains lots of uses, it might
- * make sense to provide versions for each flavor of RCU, but it does
- * not make sense as of early 2010.
- */
-#define rcu_dereference_index_check(p, c) \
-	__rcu_dereference_index_check((p), (c))
-
-/**
  * rcu_dereference_protected() - fetch RCU pointer when updates prevented
  * @p: The pointer to read, prior to dereferencing
  * @c: The conditions under which the dereference will take place
  *
  * Return the value of the specified RCU-protected pointer, but omit
- * both the smp_read_barrier_depends() and the ACCESS_ONCE().  This
+ * both the smp_read_barrier_depends() and the READ_ONCE().  This
  * is useful in cases where update-side locks prevent the value of the
  * pointer from changing.  Please note that this primitive does -not-
  * prevent the compiler from repeating this reference or combining it
@@ -1153,13 +1101,13 @@ static inline notrace void rcu_read_unlock_sched_notrace(void)
 #define kfree_rcu(ptr, rcu_head)					\
 	__kfree_rcu(&((ptr)->rcu_head), offsetof(typeof(*(ptr)), rcu_head))
 
-#if defined(CONFIG_TINY_RCU) || defined(CONFIG_RCU_NOCB_CPU_ALL)
-static inline int rcu_needs_cpu(unsigned long *delta_jiffies)
+#ifdef CONFIG_TINY_RCU
+static inline int rcu_needs_cpu(u64 basemono, u64 *nextevt)
 {
-	*delta_jiffies = ULONG_MAX;
+	*nextevt = KTIME_MAX;
 	return 0;
 }
-#endif /* #if defined(CONFIG_TINY_RCU) || defined(CONFIG_RCU_NOCB_CPU_ALL) */
+#endif /* #ifdef CONFIG_TINY_RCU */
 
 #if defined(CONFIG_RCU_NOCB_CPU_ALL)
 static inline bool rcu_is_nocb_cpu(int cpu) { return true; }
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 937edaeb150d..3df6c1ec4e25 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -159,6 +159,22 @@ static inline void rcu_cpu_stall_reset(void)
 {
 }
 
+static inline void rcu_idle_enter(void)
+{
+}
+
+static inline void rcu_idle_exit(void)
+{
+}
+
+static inline void rcu_irq_enter(void)
+{
+}
+
+static inline void rcu_irq_exit(void)
+{
+}
+
 static inline void exit_rcu(void)
 {
 }
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index d2e583a6aaca..456879143f89 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -31,9 +31,7 @@
 #define __LINUX_RCUTREE_H
 
 void rcu_note_context_switch(void);
-#ifndef CONFIG_RCU_NOCB_CPU_ALL
-int rcu_needs_cpu(unsigned long *delta_jiffies);
-#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */
+int rcu_needs_cpu(u64 basem, u64 *nextevt);
 void rcu_cpu_stall_reset(void);
 
 /*
@@ -93,6 +91,11 @@ void rcu_force_quiescent_state(void);
 void rcu_bh_force_quiescent_state(void);
 void rcu_sched_force_quiescent_state(void);
 
+void rcu_idle_enter(void);
+void rcu_idle_exit(void);
+void rcu_irq_enter(void);
+void rcu_irq_exit(void);
+
 void exit_rcu(void);
 
 void rcu_scheduler_starting(void);
diff --git a/include/linux/rio.h b/include/linux/rio.h
index 6bda06f21930..cde976e86b48 100644
--- a/include/linux/rio.h
+++ b/include/linux/rio.h
@@ -298,7 +298,7 @@ struct rio_id_table {
  * struct rio_net - RIO network info
  * @node: Node in global list of RIO networks
  * @devices: List of devices in this network
- * @switches: List of switches in this netowrk
+ * @switches: List of switches in this network
  * @mports: List of master ports accessing this network
  * @hport: Default port for accessing this network
  * @id: RIO network ID
diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h
index ed8f9e70df9b..a0edb992c9c3 100644
--- a/include/linux/scatterlist.h
+++ b/include/linux/scatterlist.h
@@ -221,6 +221,7 @@ static inline void *sg_virt(struct scatterlist *sg)
 }
 
 int sg_nents(struct scatterlist *sg);
+int sg_nents_for_len(struct scatterlist *sg, u64 len);
 struct scatterlist *sg_next(struct scatterlist *);
 struct scatterlist *sg_last(struct scatterlist *s, unsigned int);
 void sg_init_table(struct scatterlist *, unsigned int);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 26a2e6122734..6633e83e608a 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -25,7 +25,7 @@ struct sched_param {
 #include <linux/errno.h>
 #include <linux/nodemask.h>
 #include <linux/mm_types.h>
-#include <linux/preempt_mask.h>
+#include <linux/preempt.h>
 
 #include <asm/page.h>
 #include <asm/ptrace.h>
@@ -132,6 +132,7 @@ struct fs_struct;
 struct perf_event_context;
 struct blk_plug;
 struct filename;
+struct nameidata;
 
 #define VMACACHE_BITS 2
 #define VMACACHE_SIZE (1U << VMACACHE_BITS)
@@ -173,7 +174,12 @@ extern unsigned long nr_iowait_cpu(int cpu);
 extern void get_iowait_load(unsigned long *nr_waiters, unsigned long *load);
 
 extern void calc_global_load(unsigned long ticks);
+
+#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
 extern void update_cpu_load_nohz(void);
+#else
+static inline void update_cpu_load_nohz(void) { }
+#endif
 
 extern unsigned long get_parent_ip(unsigned long addr);
 
@@ -213,9 +219,10 @@ print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq);
 #define TASK_WAKEKILL		128
 #define TASK_WAKING		256
 #define TASK_PARKED		512
-#define TASK_STATE_MAX		1024
+#define TASK_NOLOAD		1024
+#define TASK_STATE_MAX		2048
 
-#define TASK_STATE_TO_CHAR_STR "RSDTtXZxKWP"
+#define TASK_STATE_TO_CHAR_STR "RSDTtXZxKWPN"
 
 extern char ___assert_task_state[1 - 2*!!(
 		sizeof(TASK_STATE_TO_CHAR_STR)-1 != ilog2(TASK_STATE_MAX)+1)];
@@ -225,6 +232,8 @@ extern char ___assert_task_state[1 - 2*!!(
 #define TASK_STOPPED		(TASK_WAKEKILL | __TASK_STOPPED)
 #define TASK_TRACED		(TASK_WAKEKILL | __TASK_TRACED)
 
+#define TASK_IDLE		(TASK_UNINTERRUPTIBLE | TASK_NOLOAD)
+
 /* Convenience macros for the sake of wake_up */
 #define TASK_NORMAL		(TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE)
 #define TASK_ALL		(TASK_NORMAL | __TASK_STOPPED | __TASK_TRACED)
@@ -240,7 +249,8 @@ extern char ___assert_task_state[1 - 2*!!(
 			((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0)
 #define task_contributes_to_load(task)	\
 				((task->state & TASK_UNINTERRUPTIBLE) != 0 && \
-				 (task->flags & PF_FROZEN) == 0)
+				 (task->flags & PF_FROZEN) == 0 && \
+				 (task->state & TASK_NOLOAD) == 0)
 
 #ifdef CONFIG_DEBUG_ATOMIC_SLEEP
 
@@ -252,7 +262,7 @@ extern char ___assert_task_state[1 - 2*!!(
 #define set_task_state(tsk, state_value)			\
 	do {							\
 		(tsk)->task_state_change = _THIS_IP_;		\
-		set_mb((tsk)->state, (state_value));		\
+		smp_store_mb((tsk)->state, (state_value));		\
 	} while (0)
 
 /*
@@ -274,7 +284,7 @@ extern char ___assert_task_state[1 - 2*!!(
 #define set_current_state(state_value)				\
 	do {							\
 		current->task_state_change = _THIS_IP_;		\
-		set_mb(current->state, (state_value));		\
+		smp_store_mb(current->state, (state_value));		\
 	} while (0)
 
 #else
@@ -282,7 +292,7 @@ extern char ___assert_task_state[1 - 2*!!(
 #define __set_task_state(tsk, state_value)		\
 	do { (tsk)->state = (state_value); } while (0)
 #define set_task_state(tsk, state_value)		\
-	set_mb((tsk)->state, (state_value))
+	smp_store_mb((tsk)->state, (state_value))
 
 /*
  * set_current_state() includes a barrier so that the write of current->state
@@ -298,7 +308,7 @@ extern char ___assert_task_state[1 - 2*!!(
 #define __set_current_state(state_value)		\
 	do { current->state = (state_value); } while (0)
 #define set_current_state(state_value)			\
-	set_mb(current->state, (state_value))
+	smp_store_mb(current->state, (state_value))
 
 #endif
 
@@ -335,14 +345,10 @@ extern int runqueue_is_locked(int cpu);
 #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
 extern void nohz_balance_enter_idle(int cpu);
 extern void set_cpu_sd_state_idle(void);
-extern int get_nohz_timer_target(int pinned);
+extern int get_nohz_timer_target(void);
 #else
 static inline void nohz_balance_enter_idle(int cpu) { }
 static inline void set_cpu_sd_state_idle(void) { }
-static inline int get_nohz_timer_target(int pinned)
-{
-	return smp_processor_id();
-}
 #endif
 
 /*
@@ -567,6 +573,23 @@ struct task_cputime {
 		.sum_exec_runtime = 0,				\
 	}
 
+/*
+ * This is the atomic variant of task_cputime, which can be used for
+ * storing and updating task_cputime statistics without locking.
+ */
+struct task_cputime_atomic {
+	atomic64_t utime;
+	atomic64_t stime;
+	atomic64_t sum_exec_runtime;
+};
+
+#define INIT_CPUTIME_ATOMIC \
+	(struct task_cputime_atomic) {				\
+		.utime = ATOMIC64_INIT(0),			\
+		.stime = ATOMIC64_INIT(0),			\
+		.sum_exec_runtime = ATOMIC64_INIT(0),		\
+	}
+
 #ifdef CONFIG_PREEMPT_COUNT
 #define PREEMPT_DISABLED	(1 + PREEMPT_ENABLED)
 #else
@@ -584,18 +607,16 @@ struct task_cputime {
 
 /**
  * struct thread_group_cputimer - thread group interval timer counts
- * @cputime:		thread group interval timers.
+ * @cputime_atomic:	atomic thread group interval timers.
  * @running:		non-zero when there are timers running and
  * 			@cputime receives updates.
- * @lock:		lock for fields in this struct.
  *
  * This structure contains the version of task_cputime, above, that is
  * used for thread group CPU timer calculations.
  */
 struct thread_group_cputimer {
-	struct task_cputime cputime;
+	struct task_cputime_atomic cputime_atomic;
 	int running;
-	raw_spinlock_t lock;
 };
 
 #include <linux/rwsem.h>
@@ -900,6 +921,50 @@ enum cpu_idle_type {
 #define SCHED_CAPACITY_SCALE	(1L << SCHED_CAPACITY_SHIFT)
 
 /*
+ * Wake-queues are lists of tasks with a pending wakeup, whose
+ * callers have already marked the task as woken internally,
+ * and can thus carry on. A common use case is being able to
+ * do the wakeups once the corresponding user lock as been
+ * released.
+ *
+ * We hold reference to each task in the list across the wakeup,
+ * thus guaranteeing that the memory is still valid by the time
+ * the actual wakeups are performed in wake_up_q().
+ *
+ * One per task suffices, because there's never a need for a task to be
+ * in two wake queues simultaneously; it is forbidden to abandon a task
+ * in a wake queue (a call to wake_up_q() _must_ follow), so if a task is
+ * already in a wake queue, the wakeup will happen soon and the second
+ * waker can just skip it.
+ *
+ * The WAKE_Q macro declares and initializes the list head.
+ * wake_up_q() does NOT reinitialize the list; it's expected to be
+ * called near the end of a function, where the fact that the queue is
+ * not used again will be easy to see by inspection.
+ *
+ * Note that this can cause spurious wakeups. schedule() callers
+ * must ensure the call is done inside a loop, confirming that the
+ * wakeup condition has in fact occurred.
+ */
+struct wake_q_node {
+	struct wake_q_node *next;
+};
+
+struct wake_q_head {
+	struct wake_q_node *first;
+	struct wake_q_node **lastp;
+};
+
+#define WAKE_Q_TAIL ((struct wake_q_node *) 0x01)
+
+#define WAKE_Q(name)					\
+	struct wake_q_head name = { WAKE_Q_TAIL, &name.first }
+
+extern void wake_q_add(struct wake_q_head *head,
+		       struct task_struct *task);
+extern void wake_up_q(struct wake_q_head *head);
+
+/*
  * sched-domains (multiprocessor balancing) declarations:
  */
 #ifdef CONFIG_SMP
@@ -1334,8 +1399,6 @@ struct task_struct {
 	int rcu_read_lock_nesting;
 	union rcu_special rcu_read_unlock_special;
 	struct list_head rcu_node_entry;
-#endif /* #ifdef CONFIG_PREEMPT_RCU */
-#ifdef CONFIG_PREEMPT_RCU
 	struct rcu_node *rcu_blocked_node;
 #endif /* #ifdef CONFIG_PREEMPT_RCU */
 #ifdef CONFIG_TASKS_RCU
@@ -1356,9 +1419,6 @@ struct task_struct {
 #endif
 
 	struct mm_struct *mm, *active_mm;
-#ifdef CONFIG_COMPAT_BRK
-	unsigned brk_randomized:1;
-#endif
 	/* per-thread vma caching */
 	u32 vmacache_seqnum;
 	struct vm_area_struct *vmacache[VMACACHE_SIZE];
@@ -1369,7 +1429,7 @@ struct task_struct {
 	int exit_state;
 	int exit_code, exit_signal;
 	int pdeath_signal;  /*  The signal sent when the parent dies  */
-	unsigned int jobctl;	/* JOBCTL_*, siglock protected */
+	unsigned long jobctl;	/* JOBCTL_*, siglock protected */
 
 	/* Used for emulating ABI behavior of previous Linux versions */
 	unsigned int personality;
@@ -1381,10 +1441,14 @@ struct task_struct {
 	/* Revert to default priority/policy when forking */
 	unsigned sched_reset_on_fork:1;
 	unsigned sched_contributes_to_load:1;
+	unsigned sched_migrated:1;
 
 #ifdef CONFIG_MEMCG_KMEM
 	unsigned memcg_kmem_skip_account:1;
 #endif
+#ifdef CONFIG_COMPAT_BRK
+	unsigned brk_randomized:1;
+#endif
 
 	unsigned long atomic_flags; /* Flags needing atomic access. */
 
@@ -1461,7 +1525,7 @@ struct task_struct {
 				       it with task_lock())
 				     - initialized normally by setup_new_exec */
 /* file system info */
-	int link_count, total_link_count;
+	struct nameidata *nameidata;
 #ifdef CONFIG_SYSVIPC
 /* ipc stuff */
 	struct sysv_sem sysvsem;
@@ -1511,6 +1575,8 @@ struct task_struct {
 	/* Protection of the PI data structures: */
 	raw_spinlock_t pi_lock;
 
+	struct wake_q_node wake_q;
+
 #ifdef CONFIG_RT_MUTEXES
 	/* PI waiters blocked on a rt_mutex held by this task */
 	struct rb_root pi_waiters;
@@ -1724,6 +1790,7 @@ struct task_struct {
 #ifdef CONFIG_DEBUG_ATOMIC_SLEEP
 	unsigned long	task_state_change;
 #endif
+	int pagefault_disabled;
 };
 
 /* Future-safe accessor for struct task_struct's cpus_allowed. */
@@ -2077,22 +2144,22 @@ TASK_PFA_CLEAR(SPREAD_SLAB, spread_slab)
 #define JOBCTL_TRAPPING_BIT	21	/* switching to TRACED */
 #define JOBCTL_LISTENING_BIT	22	/* ptracer is listening for events */
 
-#define JOBCTL_STOP_DEQUEUED	(1 << JOBCTL_STOP_DEQUEUED_BIT)
-#define JOBCTL_STOP_PENDING	(1 << JOBCTL_STOP_PENDING_BIT)
-#define JOBCTL_STOP_CONSUME	(1 << JOBCTL_STOP_CONSUME_BIT)
-#define JOBCTL_TRAP_STOP	(1 << JOBCTL_TRAP_STOP_BIT)
-#define JOBCTL_TRAP_NOTIFY	(1 << JOBCTL_TRAP_NOTIFY_BIT)
-#define JOBCTL_TRAPPING		(1 << JOBCTL_TRAPPING_BIT)
-#define JOBCTL_LISTENING	(1 << JOBCTL_LISTENING_BIT)
+#define JOBCTL_STOP_DEQUEUED	(1UL << JOBCTL_STOP_DEQUEUED_BIT)
+#define JOBCTL_STOP_PENDING	(1UL << JOBCTL_STOP_PENDING_BIT)
+#define JOBCTL_STOP_CONSUME	(1UL << JOBCTL_STOP_CONSUME_BIT)
+#define JOBCTL_TRAP_STOP	(1UL << JOBCTL_TRAP_STOP_BIT)
+#define JOBCTL_TRAP_NOTIFY	(1UL << JOBCTL_TRAP_NOTIFY_BIT)
+#define JOBCTL_TRAPPING		(1UL << JOBCTL_TRAPPING_BIT)
+#define JOBCTL_LISTENING	(1UL << JOBCTL_LISTENING_BIT)
 
 #define JOBCTL_TRAP_MASK	(JOBCTL_TRAP_STOP | JOBCTL_TRAP_NOTIFY)
 #define JOBCTL_PENDING_MASK	(JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK)
 
 extern bool task_set_jobctl_pending(struct task_struct *task,
-				    unsigned int mask);
+				    unsigned long mask);
 extern void task_clear_jobctl_trapping(struct task_struct *task);
 extern void task_clear_jobctl_pending(struct task_struct *task,
-				      unsigned int mask);
+				      unsigned long mask);
 
 static inline void rcu_copy_process(struct task_struct *p)
 {
@@ -2532,6 +2599,9 @@ static inline unsigned long wait_task_inactive(struct task_struct *p,
 }
 #endif
 
+#define tasklist_empty() \
+	list_empty(&init_task.tasks)
+
 #define next_task(p) \
 	list_entry_rcu((p)->tasks.next, struct task_struct, tasks)
 
@@ -2962,11 +3032,6 @@ static __always_inline bool need_resched(void)
 void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times);
 void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times);
 
-static inline void thread_group_cputime_init(struct signal_struct *sig)
-{
-	raw_spin_lock_init(&sig->cputimer.lock);
-}
-
 /*
  * Reevaluate whether the task has signals pending delivery.
  * Wake the task if so.
@@ -3080,13 +3145,13 @@ static inline void mm_update_next_owner(struct mm_struct *mm)
 static inline unsigned long task_rlimit(const struct task_struct *tsk,
 		unsigned int limit)
 {
-	return ACCESS_ONCE(tsk->signal->rlim[limit].rlim_cur);
+	return READ_ONCE(tsk->signal->rlim[limit].rlim_cur);
 }
 
 static inline unsigned long task_rlimit_max(const struct task_struct *tsk,
 		unsigned int limit)
 {
-	return ACCESS_ONCE(tsk->signal->rlim[limit].rlim_max);
+	return READ_ONCE(tsk->signal->rlim[limit].rlim_max);
 }
 
 static inline unsigned long rlimit(unsigned int limit)
diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index 596a0e007c62..c9e4731cf10b 100644
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -57,24 +57,12 @@ extern unsigned int sysctl_numa_balancing_scan_size;
 extern unsigned int sysctl_sched_migration_cost;
 extern unsigned int sysctl_sched_nr_migrate;
 extern unsigned int sysctl_sched_time_avg;
-extern unsigned int sysctl_timer_migration;
 extern unsigned int sysctl_sched_shares_window;
 
 int sched_proc_update_handler(struct ctl_table *table, int write,
 		void __user *buffer, size_t *length,
 		loff_t *ppos);
 #endif
-#ifdef CONFIG_SCHED_DEBUG
-static inline unsigned int get_sysctl_timer_migration(void)
-{
-	return sysctl_timer_migration;
-}
-#else
-static inline unsigned int get_sysctl_timer_migration(void)
-{
-	return 1;
-}
-#endif
 
 /*
  *  control realtime throttling:
diff --git a/include/linux/security.h b/include/linux/security.h
index 18264ea9e314..52febde52479 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -43,7 +43,6 @@ struct file;
 struct vfsmount;
 struct path;
 struct qstr;
-struct nameidata;
 struct iattr;
 struct fown_struct;
 struct file_operations;
@@ -477,7 +476,8 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts)
  * @inode_follow_link:
  *	Check permission to follow a symbolic link when looking up a pathname.
  *	@dentry contains the dentry structure for the link.
- *	@nd contains the nameidata structure for the parent directory.
+ *	@inode contains the inode, which itself is not stable in RCU-walk
+ *	@rcu indicates whether we are in RCU-walk mode.
  *	Return 0 if permission is granted.
  * @inode_permission:
  *	Check permission before accessing an inode.  This hook is called by the
@@ -1553,7 +1553,8 @@ struct security_operations {
 	int (*inode_rename) (struct inode *old_dir, struct dentry *old_dentry,
 			     struct inode *new_dir, struct dentry *new_dentry);
 	int (*inode_readlink) (struct dentry *dentry);
-	int (*inode_follow_link) (struct dentry *dentry, struct nameidata *nd);
+	int (*inode_follow_link) (struct dentry *dentry, struct inode *inode,
+				  bool rcu);
 	int (*inode_permission) (struct inode *inode, int mask);
 	int (*inode_setattr)	(struct dentry *dentry, struct iattr *attr);
 	int (*inode_getattr) (const struct path *path);
@@ -1839,7 +1840,8 @@ int security_inode_rename(struct inode *old_dir, struct dentry *old_dentry,
 			  struct inode *new_dir, struct dentry *new_dentry,
 			  unsigned int flags);
 int security_inode_readlink(struct dentry *dentry);
-int security_inode_follow_link(struct dentry *dentry, struct nameidata *nd);
+int security_inode_follow_link(struct dentry *dentry, struct inode *inode,
+			       bool rcu);
 int security_inode_permission(struct inode *inode, int mask);
 int security_inode_setattr(struct dentry *dentry, struct iattr *attr);
 int security_inode_getattr(const struct path *path);
@@ -2242,7 +2244,8 @@ static inline int security_inode_readlink(struct dentry *dentry)
 }
 
 static inline int security_inode_follow_link(struct dentry *dentry,
-					      struct nameidata *nd)
+					     struct inode *inode,
+					     bool rcu)
 {
 	return 0;
 }
diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index 5f68d0a391ce..486e685a226a 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -233,6 +233,47 @@ static inline void raw_write_seqcount_end(seqcount_t *s)
 	s->sequence++;
 }
 
+/**
+ * raw_write_seqcount_barrier - do a seq write barrier
+ * @s: pointer to seqcount_t
+ *
+ * This can be used to provide an ordering guarantee instead of the
+ * usual consistency guarantee. It is one wmb cheaper, because we can
+ * collapse the two back-to-back wmb()s.
+ *
+ *      seqcount_t seq;
+ *      bool X = true, Y = false;
+ *
+ *      void read(void)
+ *      {
+ *              bool x, y;
+ *
+ *              do {
+ *                      int s = read_seqcount_begin(&seq);
+ *
+ *                      x = X; y = Y;
+ *
+ *              } while (read_seqcount_retry(&seq, s));
+ *
+ *              BUG_ON(!x && !y);
+ *      }
+ *
+ *      void write(void)
+ *      {
+ *              Y = true;
+ *
+ *              raw_write_seqcount_barrier(seq);
+ *
+ *              X = false;
+ *      }
+ */
+static inline void raw_write_seqcount_barrier(seqcount_t *s)
+{
+	s->sequence++;
+	smp_wmb();
+	s->sequence++;
+}
+
 /*
  * raw_write_seqcount_latch - redirect readers to even/odd copy
  * @s: pointer to seqcount_t
@@ -266,13 +307,13 @@ static inline void write_seqcount_end(seqcount_t *s)
 }
 
 /**
- * write_seqcount_barrier - invalidate in-progress read-side seq operations
+ * write_seqcount_invalidate - invalidate in-progress read-side seq operations
  * @s: pointer to seqcount_t
  *
- * After write_seqcount_barrier, no read-side seq operations will complete
+ * After write_seqcount_invalidate, no read-side seq operations will complete
  * successfully and see data older than this.
  */
-static inline void write_seqcount_barrier(seqcount_t *s)
+static inline void write_seqcount_invalidate(seqcount_t *s)
 {
 	smp_wmb();
 	s->sequence+=2;
diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index 3e18379dfa6f..0063b24b4f36 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -120,7 +120,7 @@ do {								\
 /*
  * Despite its name it doesn't necessarily has to be a full barrier.
  * It should only guarantee that a STORE before the critical section
- * can not be reordered with a LOAD inside this section.
+ * can not be reordered with LOADs and STOREs inside this section.
  * spin_lock() is the one-way barrier, this LOAD can not escape out
  * of the region. So the default implementation simply ensures that
  * a STORE can not move into the critical section, smp_wmb() should
diff --git a/include/linux/sw842.h b/include/linux/sw842.h
new file mode 100644
index 000000000000..109ba041c2ae
--- /dev/null
+++ b/include/linux/sw842.h
@@ -0,0 +1,12 @@
+#ifndef __SW842_H__
+#define __SW842_H__
+
+#define SW842_MEM_COMPRESS	(0xf000)
+
+int sw842_compress(const u8 *src, unsigned int srclen,
+		   u8 *dst, unsigned int *destlen, void *wmem);
+
+int sw842_decompress(const u8 *src, unsigned int srclen,
+		     u8 *dst, unsigned int *destlen);
+
+#endif
diff --git a/include/linux/tick.h b/include/linux/tick.h
index ec6e8bc992bf..3741ba1a652c 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -138,6 +138,12 @@ static inline bool tick_nohz_full_cpu(int cpu)
 	return cpumask_test_cpu(cpu, tick_nohz_full_mask);
 }
 
+static inline void tick_nohz_full_add_cpus_to(struct cpumask *mask)
+{
+	if (tick_nohz_full_enabled())
+		cpumask_or(mask, mask, tick_nohz_full_mask);
+}
+
 extern void __tick_nohz_full_check(void);
 extern void tick_nohz_full_kick(void);
 extern void tick_nohz_full_kick_cpu(int cpu);
@@ -146,6 +152,7 @@ extern void __tick_nohz_task_switch(struct task_struct *tsk);
 #else
 static inline bool tick_nohz_full_enabled(void) { return false; }
 static inline bool tick_nohz_full_cpu(int cpu) { return false; }
+static inline void tick_nohz_full_add_cpus_to(struct cpumask *mask) { }
 static inline void __tick_nohz_full_check(void) { }
 static inline void tick_nohz_full_kick_cpu(int cpu) { }
 static inline void tick_nohz_full_kick(void) { }
diff --git a/include/linux/time64.h b/include/linux/time64.h
index a3831478d9cf..77b5df2acd2a 100644
--- a/include/linux/time64.h
+++ b/include/linux/time64.h
@@ -2,6 +2,7 @@
 #define _LINUX_TIME64_H
 
 #include <uapi/linux/time.h>
+#include <linux/math64.h>
 
 typedef __s64 time64_t;
 
@@ -28,6 +29,7 @@ struct timespec64 {
 #define FSEC_PER_SEC	1000000000000000LL
 
 /* Located here for timespec[64]_valid_strict */
+#define TIME64_MAX			((s64)~((u64)1 << 63))
 #define KTIME_MAX			((s64)~((u64)1 << 63))
 #define KTIME_SEC_MAX			(KTIME_MAX / NSEC_PER_SEC)
 
diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h
index fb86963859c7..25247220b4b7 100644
--- a/include/linux/timekeeper_internal.h
+++ b/include/linux/timekeeper_internal.h
@@ -49,6 +49,8 @@ struct tk_read_base {
  * @offs_boot:		Offset clock monotonic -> clock boottime
  * @offs_tai:		Offset clock monotonic -> clock tai
  * @tai_offset:		The current UTC to TAI offset in seconds
+ * @clock_was_set_seq:	The sequence number of clock was set events
+ * @next_leap_ktime:	CLOCK_MONOTONIC time value of a pending leap-second
  * @raw_time:		Monotonic raw base time in timespec64 format
  * @cycle_interval:	Number of clock cycles in one NTP interval
  * @xtime_interval:	Number of clock shifted nano seconds in one NTP
@@ -60,6 +62,9 @@ struct tk_read_base {
  *			shifted nano seconds.
  * @ntp_error_shift:	Shift conversion between clock shifted nano seconds and
  *			ntp shifted nano seconds.
+ * @last_warning:	Warning ratelimiter (DEBUG_TIMEKEEPING)
+ * @underflow_seen:	Underflow warning flag (DEBUG_TIMEKEEPING)
+ * @overflow_seen:	Overflow warning flag (DEBUG_TIMEKEEPING)
  *
  * Note: For timespec(64) based interfaces wall_to_monotonic is what
  * we need to add to xtime (or xtime corrected for sub jiffie times)
@@ -85,6 +90,8 @@ struct timekeeper {
 	ktime_t			offs_boot;
 	ktime_t			offs_tai;
 	s32			tai_offset;
+	unsigned int		clock_was_set_seq;
+	ktime_t			next_leap_ktime;
 	struct timespec64	raw_time;
 
 	/* The following members are for timekeeping internal use */
@@ -104,6 +111,18 @@ struct timekeeper {
 	s64			ntp_error;
 	u32			ntp_error_shift;
 	u32			ntp_err_mult;
+#ifdef CONFIG_DEBUG_TIMEKEEPING
+	long			last_warning;
+	/*
+	 * These simple flag variables are managed
+	 * without locks, which is racy, but they are
+	 * ok since we don't really care about being
+	 * super precise about how many events were
+	 * seen, just that a problem was observed.
+	 */
+	int			underflow_seen;
+	int			overflow_seen;
+#endif
 };
 
 #ifdef CONFIG_GENERIC_TIME_VSYSCALL
diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h
index 99176af216af..3aa72e648650 100644
--- a/include/linux/timekeeping.h
+++ b/include/linux/timekeeping.h
@@ -163,6 +163,7 @@ extern ktime_t ktime_get(void);
 extern ktime_t ktime_get_with_offset(enum tk_offsets offs);
 extern ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs);
 extern ktime_t ktime_get_raw(void);
+extern u32 ktime_get_resolution_ns(void);
 
 /**
  * ktime_get_real - get the real (wall-) time in ktime_t format
@@ -266,7 +267,6 @@ extern int persistent_clock_is_local;
 
 extern void read_persistent_clock(struct timespec *ts);
 extern void read_persistent_clock64(struct timespec64 *ts);
-extern void read_boot_clock(struct timespec *ts);
 extern void read_boot_clock64(struct timespec64 *ts);
 extern int update_persistent_clock(struct timespec now);
 extern int update_persistent_clock64(struct timespec64 now);
diff --git a/include/linux/timer.h b/include/linux/timer.h
index 8c5a197e1587..61aa61dc410c 100644
--- a/include/linux/timer.h
+++ b/include/linux/timer.h
@@ -14,27 +14,23 @@ struct timer_list {
 	 * All fields that change during normal runtime grouped to the
 	 * same cacheline
 	 */
-	struct list_head entry;
-	unsigned long expires;
-	struct tvec_base *base;
-
-	void (*function)(unsigned long);
-	unsigned long data;
-
-	int slack;
+	struct hlist_node	entry;
+	unsigned long		expires;
+	void			(*function)(unsigned long);
+	unsigned long		data;
+	u32			flags;
+	int			slack;
 
 #ifdef CONFIG_TIMER_STATS
-	int start_pid;
-	void *start_site;
-	char start_comm[16];
+	int			start_pid;
+	void			*start_site;
+	char			start_comm[16];
 #endif
 #ifdef CONFIG_LOCKDEP
-	struct lockdep_map lockdep_map;
+	struct lockdep_map	lockdep_map;
 #endif
 };
 
-extern struct tvec_base boot_tvec_bases;
-
 #ifdef CONFIG_LOCKDEP
 /*
  * NB: because we have to copy the lockdep_map, setting the lockdep_map key
@@ -49,9 +45,6 @@ extern struct tvec_base boot_tvec_bases;
 #endif
 
 /*
- * Note that all tvec_bases are at least 4 byte aligned and lower two bits
- * of base in timer_list is guaranteed to be zero. Use them for flags.
- *
  * A deferrable timer will work normally when the system is busy, but
  * will not cause a CPU to come out of idle just to service it; instead,
  * the timer will be serviced when the CPU eventually wakes up with a
@@ -65,17 +58,18 @@ extern struct tvec_base boot_tvec_bases;
  * workqueue locking issues. It's not meant for executing random crap
  * with interrupts disabled. Abuse is monitored!
  */
-#define TIMER_DEFERRABLE		0x1LU
-#define TIMER_IRQSAFE			0x2LU
-
-#define TIMER_FLAG_MASK			0x3LU
+#define TIMER_CPUMASK		0x0007FFFF
+#define TIMER_MIGRATING		0x00080000
+#define TIMER_BASEMASK		(TIMER_CPUMASK | TIMER_MIGRATING)
+#define TIMER_DEFERRABLE	0x00100000
+#define TIMER_IRQSAFE		0x00200000
 
 #define __TIMER_INITIALIZER(_function, _expires, _data, _flags) { \
-		.entry = { .prev = TIMER_ENTRY_STATIC },	\
+		.entry = { .next = TIMER_ENTRY_STATIC },	\
 		.function = (_function),			\
 		.expires = (_expires),				\
 		.data = (_data),				\
-		.base = (void *)((unsigned long)&boot_tvec_bases + (_flags)), \
+		.flags = (_flags),				\
 		.slack = -1,					\
 		__TIMER_LOCKDEP_MAP_INITIALIZER(		\
 			__FILE__ ":" __stringify(__LINE__))	\
@@ -168,7 +162,7 @@ static inline void init_timer_on_stack_key(struct timer_list *timer,
  */
 static inline int timer_pending(const struct timer_list * timer)
 {
-	return timer->entry.next != NULL;
+	return timer->entry.pprev != NULL;
 }
 
 extern void add_timer_on(struct timer_list *timer, int cpu);
@@ -188,26 +182,16 @@ extern void set_timer_slack(struct timer_list *time, int slack_hz);
 #define NEXT_TIMER_MAX_DELTA	((1UL << 30) - 1)
 
 /*
- * Return when the next timer-wheel timeout occurs (in absolute jiffies),
- * locks the timer base and does the comparison against the given
- * jiffie.
- */
-extern unsigned long get_next_timer_interrupt(unsigned long now);
-
-/*
  * Timer-statistics info:
  */
 #ifdef CONFIG_TIMER_STATS
 
 extern int timer_stats_active;
 
-#define TIMER_STATS_FLAG_DEFERRABLE	0x1
-
 extern void init_timer_stats(void);
 
 extern void timer_stats_update_stats(void *timer, pid_t pid, void *startf,
-				     void *timerf, char *comm,
-				     unsigned int timer_flag);
+				     void *timerf, char *comm, u32 flags);
 
 extern void __timer_stats_timer_set_start_info(struct timer_list *timer,
 					       void *addr);
@@ -254,6 +238,15 @@ extern void run_local_timers(void);
 struct hrtimer;
 extern enum hrtimer_restart it_real_fn(struct hrtimer *);
 
+#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
+#include <linux/sysctl.h>
+
+extern unsigned int sysctl_timer_migration;
+int timer_migration_handler(struct ctl_table *table, int write,
+			    void __user *buffer, size_t *lenp,
+			    loff_t *ppos);
+#endif
+
 unsigned long __round_jiffies(unsigned long j, int cpu);
 unsigned long __round_jiffies_relative(unsigned long j, int cpu);
 unsigned long round_jiffies(unsigned long j);
diff --git a/include/linux/timerqueue.h b/include/linux/timerqueue.h
index a520fd70a59f..7eec17ad7fa1 100644
--- a/include/linux/timerqueue.h
+++ b/include/linux/timerqueue.h
@@ -16,10 +16,10 @@ struct timerqueue_head {
 };
 
 
-extern void timerqueue_add(struct timerqueue_head *head,
-				struct timerqueue_node *node);
-extern void timerqueue_del(struct timerqueue_head *head,
-				struct timerqueue_node *node);
+extern bool timerqueue_add(struct timerqueue_head *head,
+			   struct timerqueue_node *node);
+extern bool timerqueue_del(struct timerqueue_head *head,
+			   struct timerqueue_node *node);
 extern struct timerqueue_node *timerqueue_iterate_next(
 						struct timerqueue_node *node);
 
diff --git a/include/linux/topology.h b/include/linux/topology.h
index 909b6e43b694..73ddad1e0fa3 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -191,8 +191,8 @@ static inline int cpu_to_mem(int cpu)
 #ifndef topology_core_id
 #define topology_core_id(cpu)			((void)(cpu), 0)
 #endif
-#ifndef topology_thread_cpumask
-#define topology_thread_cpumask(cpu)		cpumask_of(cpu)
+#ifndef topology_sibling_cpumask
+#define topology_sibling_cpumask(cpu)		cpumask_of(cpu)
 #endif
 #ifndef topology_core_cpumask
 #define topology_core_cpumask(cpu)		cpumask_of(cpu)
@@ -201,7 +201,7 @@ static inline int cpu_to_mem(int cpu)
 #ifdef CONFIG_SCHED_SMT
 static inline const struct cpumask *cpu_smt_mask(int cpu)
 {
-	return topology_thread_cpumask(cpu);
+	return topology_sibling_cpumask(cpu);
 }
 #endif
 
diff --git a/include/linux/types.h b/include/linux/types.h
index 59698be03490..8715287c3b1f 100644
--- a/include/linux/types.h
+++ b/include/linux/types.h
@@ -139,12 +139,20 @@ typedef unsigned long blkcnt_t;
  */
 #define pgoff_t unsigned long
 
-/* A dma_addr_t can hold any valid DMA or bus address for the platform */
+/*
+ * A dma_addr_t can hold any valid DMA address, i.e., any address returned
+ * by the DMA API.
+ *
+ * If the DMA API only uses 32-bit addresses, dma_addr_t need only be 32
+ * bits wide.  Bus addresses, e.g., PCI BARs, may be wider than 32 bits,
+ * but drivers do memory-mapped I/O to ioremapped kernel virtual addresses,
+ * so they don't care about the size of the actual bus addresses.
+ */
 #ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
 typedef u64 dma_addr_t;
 #else
 typedef u32 dma_addr_t;
-#endif /* dma_addr_t */
+#endif
 
 typedef unsigned __bitwise__ gfp_t;
 typedef unsigned __bitwise__ fmode_t;
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index ecd3319dac33..ae572c138607 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -1,21 +1,30 @@
 #ifndef __LINUX_UACCESS_H__
 #define __LINUX_UACCESS_H__
 
-#include <linux/preempt.h>
+#include <linux/sched.h>
 #include <asm/uaccess.h>
 
+static __always_inline void pagefault_disabled_inc(void)
+{
+	current->pagefault_disabled++;
+}
+
+static __always_inline void pagefault_disabled_dec(void)
+{
+	current->pagefault_disabled--;
+	WARN_ON(current->pagefault_disabled < 0);
+}
+
 /*
- * These routines enable/disable the pagefault handler in that
- * it will not take any locks and go straight to the fixup table.
+ * These routines enable/disable the pagefault handler. If disabled, it will
+ * not take any locks and go straight to the fixup table.
  *
- * They have great resemblance to the preempt_disable/enable calls
- * and in fact they are identical; this is because currently there is
- * no other way to make the pagefault handlers do this. So we do
- * disable preemption but we don't necessarily care about that.
+ * User access methods will not sleep when called from a pagefault_disabled()
+ * environment.
  */
 static inline void pagefault_disable(void)
 {
-	preempt_count_inc();
+	pagefault_disabled_inc();
 	/*
 	 * make sure to have issued the store before a pagefault
 	 * can hit.
@@ -25,18 +34,31 @@ static inline void pagefault_disable(void)
 
 static inline void pagefault_enable(void)
 {
-#ifndef CONFIG_PREEMPT
 	/*
 	 * make sure to issue those last loads/stores before enabling
 	 * the pagefault handler again.
 	 */
 	barrier();
-	preempt_count_dec();
-#else
-	preempt_enable();
-#endif
+	pagefault_disabled_dec();
 }
 
+/*
+ * Is the pagefault handler disabled? If so, user access methods will not sleep.
+ */
+#define pagefault_disabled() (current->pagefault_disabled != 0)
+
+/*
+ * The pagefault handler is in general disabled by pagefault_disable() or
+ * when in irq context (via in_atomic()).
+ *
+ * This function should only be used by the fault handlers. Other users should
+ * stick to pagefault_disabled().
+ * Please NEVER use preempt_disable() to disable the fault handler. With
+ * !CONFIG_PREEMPT_COUNT, this is like a NOP. So the handler won't be disabled.
+ * in_atomic() will report different values based on !CONFIG_PREEMPT_COUNT.
+ */
+#define faulthandler_disabled() (pagefault_disabled() || in_atomic())
+
 #ifndef ARCH_HAS_NOCACHE_UACCESS
 
 static inline unsigned long __copy_from_user_inatomic_nocache(void *to,
diff --git a/include/linux/wait.h b/include/linux/wait.h
index 2db83349865b..d69ac4ecc88b 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -969,7 +969,7 @@ extern int bit_wait_io_timeout(struct wait_bit_key *);
  * on that signal.
  */
 static inline int
-wait_on_bit(void *word, int bit, unsigned mode)
+wait_on_bit(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
 	if (!test_bit(bit, word))
@@ -994,7 +994,7 @@ wait_on_bit(void *word, int bit, unsigned mode)
  * on that signal.
  */
 static inline int
-wait_on_bit_io(void *word, int bit, unsigned mode)
+wait_on_bit_io(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
 	if (!test_bit(bit, word))
@@ -1020,7 +1020,8 @@ wait_on_bit_io(void *word, int bit, unsigned mode)
  * received a signal and the mode permitted wakeup on that signal.
  */
 static inline int
-wait_on_bit_timeout(void *word, int bit, unsigned mode, unsigned long timeout)
+wait_on_bit_timeout(unsigned long *word, int bit, unsigned mode,
+		    unsigned long timeout)
 {
 	might_sleep();
 	if (!test_bit(bit, word))
@@ -1047,7 +1048,8 @@ wait_on_bit_timeout(void *word, int bit, unsigned mode, unsigned long timeout)
  * on that signal.
  */
 static inline int
-wait_on_bit_action(void *word, int bit, wait_bit_action_f *action, unsigned mode)
+wait_on_bit_action(unsigned long *word, int bit, wait_bit_action_f *action,
+		   unsigned mode)
 {
 	might_sleep();
 	if (!test_bit(bit, word))
@@ -1075,7 +1077,7 @@ wait_on_bit_action(void *word, int bit, wait_bit_action_f *action, unsigned mode
  * the @mode allows that signal to wake the process.
  */
 static inline int
-wait_on_bit_lock(void *word, int bit, unsigned mode)
+wait_on_bit_lock(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
 	if (!test_and_set_bit(bit, word))
@@ -1099,7 +1101,7 @@ wait_on_bit_lock(void *word, int bit, unsigned mode)
  * the @mode allows that signal to wake the process.
  */
 static inline int
-wait_on_bit_lock_io(void *word, int bit, unsigned mode)
+wait_on_bit_lock_io(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
 	if (!test_and_set_bit(bit, word))
@@ -1125,7 +1127,8 @@ wait_on_bit_lock_io(void *word, int bit, unsigned mode)
  * the @mode allows that signal to wake the process.
  */
 static inline int
-wait_on_bit_lock_action(void *word, int bit, wait_bit_action_f *action, unsigned mode)
+wait_on_bit_lock_action(unsigned long *word, int bit, wait_bit_action_f *action,
+			unsigned mode)
 {
 	might_sleep();
 	if (!test_and_set_bit(bit, word))
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 36ac102c97c7..f0ee97eec24d 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -168,6 +168,7 @@ struct xfrm_state {
 	struct xfrm_algo	*ealg;
 	struct xfrm_algo	*calg;
 	struct xfrm_algo_aead	*aead;
+	const char		*geniv;
 
 	/* Data for encapsulator */
 	struct xfrm_encap_tmpl	*encap;
@@ -1314,6 +1315,7 @@ static inline int xfrm_id_proto_match(u8 proto, u8 userproto)
  * xfrm algorithm information
  */
 struct xfrm_algo_aead_info {
+	char *geniv;
 	u16 icv_truncbits;
 };
 
@@ -1323,6 +1325,7 @@ struct xfrm_algo_auth_info {
 };
 
 struct xfrm_algo_encr_info {
+	char *geniv;
 	u16 blockbits;
 	u16 defkeybits;
 };
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 30fedaf3e56a..d57a575fe31f 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -147,7 +147,8 @@ TRACE_EVENT(sched_switch,
 		  __print_flags(__entry->prev_state & (TASK_STATE_MAX-1), "|",
 				{ 1, "S"} , { 2, "D" }, { 4, "T" }, { 8, "t" },
 				{ 16, "Z" }, { 32, "X" }, { 64, "x" },
-				{ 128, "K" }, { 256, "W" }, { 512, "P" }) : "R",
+				{ 128, "K" }, { 256, "W" }, { 512, "P" },
+				{ 1024, "N" }) : "R",
 		__entry->prev_state & TASK_STATE_MAX ? "+" : "",
 		__entry->next_comm, __entry->next_pid, __entry->next_prio)
 );
diff --git a/include/trace/events/timer.h b/include/trace/events/timer.h
index 68c2c2000f02..073b9ac245ba 100644
--- a/include/trace/events/timer.h
+++ b/include/trace/events/timer.h
@@ -43,15 +43,18 @@ DEFINE_EVENT(timer_class, timer_init,
  */
 TRACE_EVENT(timer_start,
 
-	TP_PROTO(struct timer_list *timer, unsigned long expires),
+	TP_PROTO(struct timer_list *timer,
+		unsigned long expires,
+		unsigned int flags),
 
-	TP_ARGS(timer, expires),
+	TP_ARGS(timer, expires, flags),
 
 	TP_STRUCT__entry(
 		__field( void *,	timer		)
 		__field( void *,	function	)
 		__field( unsigned long,	expires		)
 		__field( unsigned long,	now		)
+		__field( unsigned int,	flags		)
 	),
 
 	TP_fast_assign(
@@ -59,11 +62,12 @@ TRACE_EVENT(timer_start,
 		__entry->function	= timer->function;
 		__entry->expires	= expires;
 		__entry->now		= jiffies;
+		__entry->flags		= flags;
 	),
 
-	TP_printk("timer=%p function=%pf expires=%lu [timeout=%ld]",
+	TP_printk("timer=%p function=%pf expires=%lu [timeout=%ld] flags=0x%08x",
 		  __entry->timer, __entry->function, __entry->expires,
-		  (long)__entry->expires - __entry->now)
+		  (long)__entry->expires - __entry->now, __entry->flags)
 );
 
 /**
diff --git a/include/uapi/drm/radeon_drm.h b/include/uapi/drm/radeon_drm.h
index 871e73f99a4d..94d44ab2fda1 100644
--- a/include/uapi/drm/radeon_drm.h
+++ b/include/uapi/drm/radeon_drm.h
@@ -1038,6 +1038,7 @@ struct drm_radeon_cs {
 #define RADEON_INFO_CURRENT_GPU_SCLK	0x22
 #define RADEON_INFO_CURRENT_GPU_MCLK	0x23
 #define RADEON_INFO_READ_REG		0x24
+#define RADEON_INFO_VA_UNMAP_WORKING	0x25
 
 struct drm_radeon_info {
 	uint32_t		request;
diff --git a/include/linux/cryptouser.h b/include/uapi/linux/cryptouser.h
index 4abf2ea6a887..2e67bb64c1da 100644
--- a/include/linux/cryptouser.h
+++ b/include/uapi/linux/cryptouser.h
@@ -25,6 +25,7 @@ enum {
 	CRYPTO_MSG_DELALG,
 	CRYPTO_MSG_UPDATEALG,
 	CRYPTO_MSG_GETALG,
+	CRYPTO_MSG_DELRNG,
 	__CRYPTO_MSG_MAX
 };
 #define CRYPTO_MSG_MAX (__CRYPTO_MSG_MAX - 1)
@@ -43,6 +44,7 @@ enum crypto_attr_type_t {
 	CRYPTOCFGA_REPORT_COMPRESS,	/* struct crypto_report_comp */
 	CRYPTOCFGA_REPORT_RNG,		/* struct crypto_report_rng */
 	CRYPTOCFGA_REPORT_CIPHER,	/* struct crypto_report_cipher */
+	CRYPTOCFGA_REPORT_AKCIPHER,	/* struct crypto_report_akcipher */
 	__CRYPTOCFGA_MAX
 
 #define CRYPTOCFGA_MAX (__CRYPTOCFGA_MAX - 1)
@@ -101,5 +103,9 @@ struct crypto_report_rng {
 	unsigned int seedsize;
 };
 
+struct crypto_report_akcipher {
+	char type[CRYPTO_MAX_NAME];
+};
+
 #define CRYPTO_REPORT_MAXSIZE (sizeof(struct crypto_user_alg) + \
 			       sizeof(struct crypto_report_blkcipher))
diff --git a/include/uapi/linux/netfilter_bridge/ebtables.h b/include/uapi/linux/netfilter_bridge/ebtables.h
index 773dfe8924c7..fd2ee501726d 100644
--- a/include/uapi/linux/netfilter_bridge/ebtables.h
+++ b/include/uapi/linux/netfilter_bridge/ebtables.h
@@ -6,7 +6,7 @@
  *
  *  ebtables.c,v 2.0, April, 2002
  *
- *  This code is stongly inspired on the iptables code which is
+ *  This code is strongly inspired by the iptables code which is
  *  Copyright (C) 1999 Paul `Rusty' Russell & Michael J. Neuling
  */
 
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 309211b3eb67..d97f84c080da 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -167,6 +167,7 @@ enum perf_branch_sample_type_shift {
 	PERF_SAMPLE_BRANCH_COND_SHIFT		= 10, /* conditional branches */
 
 	PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT	= 11, /* call/ret stack */
+	PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT	= 12, /* indirect jumps */
 
 	PERF_SAMPLE_BRANCH_MAX_SHIFT		/* non-ABI */
 };
@@ -186,6 +187,7 @@ enum perf_branch_sample_type {
 	PERF_SAMPLE_BRANCH_COND		= 1U << PERF_SAMPLE_BRANCH_COND_SHIFT,
 
 	PERF_SAMPLE_BRANCH_CALL_STACK	= 1U << PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT,
+	PERF_SAMPLE_BRANCH_IND_JUMP	= 1U << PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT,
 
 	PERF_SAMPLE_BRANCH_MAX		= 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT,
 };
@@ -564,6 +566,10 @@ struct perf_event_mmap_page {
 #define PERF_RECORD_MISC_GUEST_USER		(5 << 0)
 
 /*
+ * Indicates that /proc/PID/maps parsing are truncated by time out.
+ */
+#define PERF_RECORD_MISC_PROC_MAP_PARSE_TIMEOUT	(1 << 12)
+/*
  * PERF_RECORD_MISC_MMAP_DATA and PERF_RECORD_MISC_COMM_EXEC are used on
  * different events so can reuse the same bit position.
  */
@@ -800,6 +806,18 @@ enum perf_event_type {
 	 */
 	PERF_RECORD_ITRACE_START		= 12,
 
+	/*
+	 * Records the dropped/lost sample number.
+	 *
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *
+	 *	u64				lost;
+	 *	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_LOST_SAMPLES		= 13,
+
 	PERF_RECORD_MAX,			/* non-ABI */
 };
 
diff --git a/init/Kconfig b/init/Kconfig
index dc24dec60232..b999fa381bf9 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -465,13 +465,9 @@ endmenu # "CPU/Task time and stats accounting"
 
 menu "RCU Subsystem"
 
-choice
-	prompt "RCU Implementation"
-	default TREE_RCU
-
 config TREE_RCU
-	bool "Tree-based hierarchical RCU"
-	depends on !PREEMPT && SMP
+	bool
+	default y if !PREEMPT && SMP
 	help
 	  This option selects the RCU implementation that is
 	  designed for very large SMP system with hundreds or
@@ -479,8 +475,8 @@ config TREE_RCU
 	  smaller systems.
 
 config PREEMPT_RCU
-	bool "Preemptible tree-based hierarchical RCU"
-	depends on PREEMPT
+	bool
+	default y if PREEMPT
 	help
 	  This option selects the RCU implementation that is
 	  designed for very large SMP systems with hundreds or
@@ -491,15 +487,28 @@ config PREEMPT_RCU
 	  Select this option if you are unsure.
 
 config TINY_RCU
-	bool "UP-only small-memory-footprint RCU"
-	depends on !PREEMPT && !SMP
+	bool
+	default y if !PREEMPT && !SMP
 	help
 	  This option selects the RCU implementation that is
 	  designed for UP systems from which real-time response
 	  is not required.  This option greatly reduces the
 	  memory footprint of RCU.
 
-endchoice
+config RCU_EXPERT
+	bool "Make expert-level adjustments to RCU configuration"
+	default n
+	help
+	  This option needs to be enabled if you wish to make
+	  expert-level adjustments to RCU configuration.  By default,
+	  no such adjustments can be made, which has the often-beneficial
+	  side-effect of preventing "make oldconfig" from asking you all
+	  sorts of detailed questions about how you would like numerous
+	  obscure RCU options to be set up.
+
+	  Say Y if you need to make expert-level adjustments to RCU.
+
+	  Say N if you are unsure.
 
 config SRCU
 	bool
@@ -509,7 +518,7 @@ config SRCU
 	  sections.
 
 config TASKS_RCU
-	bool "Task_based RCU implementation using voluntary context switch"
+	bool
 	default n
 	select SRCU
 	help
@@ -517,8 +526,6 @@ config TASKS_RCU
 	  only voluntary context switch (not preemption!), idle, and
 	  user-mode execution as quiescent states.
 
-	  If unsure, say N.
-
 config RCU_STALL_COMMON
 	def_bool ( TREE_RCU || PREEMPT_RCU || RCU_TRACE )
 	help
@@ -531,9 +538,7 @@ config CONTEXT_TRACKING
        bool
 
 config RCU_USER_QS
-	bool "Consider userspace as in RCU extended quiescent state"
-	depends on HAVE_CONTEXT_TRACKING && SMP
-	select CONTEXT_TRACKING
+	bool
 	help
 	  This option sets hooks on kernel / userspace boundaries and
 	  puts RCU in extended quiescent state when the CPU runs in
@@ -541,12 +546,6 @@ config RCU_USER_QS
 	  excluded from the global RCU state machine and thus doesn't
 	  try to keep the timer tick on for RCU.
 
-	  Unless you want to hack and help the development of the full
-	  dynticks mode, you shouldn't enable this option.  It also
-	  adds unnecessary overhead.
-
-	  If unsure say N
-
 config CONTEXT_TRACKING_FORCE
 	bool "Force context tracking"
 	depends on CONTEXT_TRACKING
@@ -578,7 +577,7 @@ config RCU_FANOUT
 	int "Tree-based hierarchical RCU fanout value"
 	range 2 64 if 64BIT
 	range 2 32 if !64BIT
-	depends on TREE_RCU || PREEMPT_RCU
+	depends on (TREE_RCU || PREEMPT_RCU) && RCU_EXPERT
 	default 64 if 64BIT
 	default 32 if !64BIT
 	help
@@ -596,9 +595,9 @@ config RCU_FANOUT
 
 config RCU_FANOUT_LEAF
 	int "Tree-based hierarchical RCU leaf-level fanout value"
-	range 2 RCU_FANOUT if 64BIT
-	range 2 RCU_FANOUT if !64BIT
-	depends on TREE_RCU || PREEMPT_RCU
+	range 2 64 if 64BIT
+	range 2 32 if !64BIT
+	depends on (TREE_RCU || PREEMPT_RCU) && RCU_EXPERT
 	default 16
 	help
 	  This option controls the leaf-level fanout of hierarchical
@@ -621,23 +620,9 @@ config RCU_FANOUT_LEAF
 
 	  Take the default if unsure.
 
-config RCU_FANOUT_EXACT
-	bool "Disable tree-based hierarchical RCU auto-balancing"
-	depends on TREE_RCU || PREEMPT_RCU
-	default n
-	help
-	  This option forces use of the exact RCU_FANOUT value specified,
-	  regardless of imbalances in the hierarchy.  This is useful for
-	  testing RCU itself, and might one day be useful on systems with
-	  strong NUMA behavior.
-
-	  Without RCU_FANOUT_EXACT, the code will balance the hierarchy.
-
-	  Say N if unsure.
-
 config RCU_FAST_NO_HZ
 	bool "Accelerate last non-dyntick-idle CPU's grace periods"
-	depends on NO_HZ_COMMON && SMP
+	depends on NO_HZ_COMMON && SMP && RCU_EXPERT
 	default n
 	help
 	  This option permits CPUs to enter dynticks-idle state even if
@@ -663,7 +648,7 @@ config TREE_RCU_TRACE
 
 config RCU_BOOST
 	bool "Enable RCU priority boosting"
-	depends on RT_MUTEXES && PREEMPT_RCU
+	depends on RT_MUTEXES && PREEMPT_RCU && RCU_EXPERT
 	default n
 	help
 	  This option boosts the priority of preempted RCU readers that
@@ -680,6 +665,7 @@ config RCU_KTHREAD_PRIO
 	range 0 99 if !RCU_BOOST
 	default 1 if RCU_BOOST
 	default 0 if !RCU_BOOST
+	depends on RCU_EXPERT
 	help
 	  This option specifies the SCHED_FIFO priority value that will be
 	  assigned to the rcuc/n and rcub/n threads and is also the value
@@ -1637,7 +1623,7 @@ config PERF_EVENTS
 config DEBUG_PERF_USE_VMALLOC
 	default n
 	bool "Debug: use vmalloc to back perf mmap() buffers"
-	depends on PERF_EVENTS && DEBUG_KERNEL
+	depends on PERF_EVENTS && DEBUG_KERNEL && !PPC
 	select PERF_USE_VMALLOC
 	help
 	 Use vmalloc memory to back perf mmap() buffers.
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index 3aaea7ffd077..a24ba9fe5bb8 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -47,8 +47,7 @@
 #define RECV		1
 
 #define STATE_NONE	0
-#define STATE_PENDING	1
-#define STATE_READY	2
+#define STATE_READY	1
 
 struct posix_msg_tree_node {
 	struct rb_node		rb_node;
@@ -571,15 +570,12 @@ static int wq_sleep(struct mqueue_inode_info *info, int sr,
 	wq_add(info, sr, ewp);
 
 	for (;;) {
-		set_current_state(TASK_INTERRUPTIBLE);
+		__set_current_state(TASK_INTERRUPTIBLE);
 
 		spin_unlock(&info->lock);
 		time = schedule_hrtimeout_range_clock(timeout, 0,
 			HRTIMER_MODE_ABS, CLOCK_REALTIME);
 
-		while (ewp->state == STATE_PENDING)
-			cpu_relax();
-
 		if (ewp->state == STATE_READY) {
 			retval = 0;
 			goto out;
@@ -907,11 +903,15 @@ out_name:
  * list of waiting receivers. A sender checks that list before adding the new
  * message into the message array. If there is a waiting receiver, then it
  * bypasses the message array and directly hands the message over to the
- * receiver.
- * The receiver accepts the message and returns without grabbing the queue
- * spinlock. Therefore an intermediate STATE_PENDING state and memory barriers
- * are necessary. The same algorithm is used for sysv semaphores, see
- * ipc/sem.c for more details.
+ * receiver. The receiver accepts the message and returns without grabbing the
+ * queue spinlock:
+ *
+ * - Set pointer to message.
+ * - Queue the receiver task for later wakeup (without the info->lock).
+ * - Update its state to STATE_READY. Now the receiver can continue.
+ * - Wake up the process after the lock is dropped. Should the process wake up
+ *   before this wakeup (due to a timeout or a signal) it will either see
+ *   STATE_READY and continue or acquire the lock to check the state again.
  *
  * The same algorithm is used for senders.
  */
@@ -919,21 +919,29 @@ out_name:
 /* pipelined_send() - send a message directly to the task waiting in
  * sys_mq_timedreceive() (without inserting message into a queue).
  */
-static inline void pipelined_send(struct mqueue_inode_info *info,
+static inline void pipelined_send(struct wake_q_head *wake_q,
+				  struct mqueue_inode_info *info,
 				  struct msg_msg *message,
 				  struct ext_wait_queue *receiver)
 {
 	receiver->msg = message;
 	list_del(&receiver->list);
-	receiver->state = STATE_PENDING;
-	wake_up_process(receiver->task);
-	smp_wmb();
+	wake_q_add(wake_q, receiver->task);
+	/*
+	 * Rely on the implicit cmpxchg barrier from wake_q_add such
+	 * that we can ensure that updating receiver->state is the last
+	 * write operation: As once set, the receiver can continue,
+	 * and if we don't have the reference count from the wake_q,
+	 * yet, at that point we can later have a use-after-free
+	 * condition and bogus wakeup.
+	 */
 	receiver->state = STATE_READY;
 }
 
 /* pipelined_receive() - if there is task waiting in sys_mq_timedsend()
  * gets its message and put to the queue (we have one free place for sure). */
-static inline void pipelined_receive(struct mqueue_inode_info *info)
+static inline void pipelined_receive(struct wake_q_head *wake_q,
+				     struct mqueue_inode_info *info)
 {
 	struct ext_wait_queue *sender = wq_get_first_waiter(info, SEND);
 
@@ -944,10 +952,9 @@ static inline void pipelined_receive(struct mqueue_inode_info *info)
 	}
 	if (msg_insert(sender->msg, info))
 		return;
+
 	list_del(&sender->list);
-	sender->state = STATE_PENDING;
-	wake_up_process(sender->task);
-	smp_wmb();
+	wake_q_add(wake_q, sender->task);
 	sender->state = STATE_READY;
 }
 
@@ -965,6 +972,7 @@ SYSCALL_DEFINE5(mq_timedsend, mqd_t, mqdes, const char __user *, u_msg_ptr,
 	struct timespec ts;
 	struct posix_msg_tree_node *new_leaf = NULL;
 	int ret = 0;
+	WAKE_Q(wake_q);
 
 	if (u_abs_timeout) {
 		int res = prepare_timeout(u_abs_timeout, &expires, &ts);
@@ -1049,7 +1057,7 @@ SYSCALL_DEFINE5(mq_timedsend, mqd_t, mqdes, const char __user *, u_msg_ptr,
 	} else {
 		receiver = wq_get_first_waiter(info, RECV);
 		if (receiver) {
-			pipelined_send(info, msg_ptr, receiver);
+			pipelined_send(&wake_q, info, msg_ptr, receiver);
 		} else {
 			/* adds message to the queue */
 			ret = msg_insert(msg_ptr, info);
@@ -1062,6 +1070,7 @@ SYSCALL_DEFINE5(mq_timedsend, mqd_t, mqdes, const char __user *, u_msg_ptr,
 	}
 out_unlock:
 	spin_unlock(&info->lock);
+	wake_up_q(&wake_q);
 out_free:
 	if (ret)
 		free_msg(msg_ptr);
@@ -1149,14 +1158,17 @@ SYSCALL_DEFINE5(mq_timedreceive, mqd_t, mqdes, char __user *, u_msg_ptr,
 			msg_ptr = wait.msg;
 		}
 	} else {
+		WAKE_Q(wake_q);
+
 		msg_ptr = msg_get(info);
 
 		inode->i_atime = inode->i_mtime = inode->i_ctime =
 				CURRENT_TIME;
 
 		/* There is now free space in queue. */
-		pipelined_receive(info);
+		pipelined_receive(&wake_q, info);
 		spin_unlock(&info->lock);
+		wake_up_q(&wake_q);
 		ret = 0;
 	}
 	if (ret == 0) {
diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks
index 08561f1acd13..ebdb0043203a 100644
--- a/kernel/Kconfig.locks
+++ b/kernel/Kconfig.locks
@@ -235,9 +235,16 @@ config LOCK_SPIN_ON_OWNER
        def_bool y
        depends on MUTEX_SPIN_ON_OWNER || RWSEM_SPIN_ON_OWNER
 
-config ARCH_USE_QUEUE_RWLOCK
+config ARCH_USE_QUEUED_SPINLOCKS
 	bool
 
-config QUEUE_RWLOCK
-	def_bool y if ARCH_USE_QUEUE_RWLOCK
+config QUEUED_SPINLOCKS
+	def_bool y if ARCH_USE_QUEUED_SPINLOCKS
+	depends on SMP
+
+config ARCH_USE_QUEUED_RWLOCKS
+	bool
+
+config QUEUED_RWLOCKS
+	def_bool y if ARCH_USE_QUEUED_RWLOCKS
 	depends on SMP
diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c
index 72d59a1a6eb6..0a495ab35bc7 100644
--- a/kernel/context_tracking.c
+++ b/kernel/context_tracking.c
@@ -30,12 +30,23 @@ EXPORT_SYMBOL_GPL(context_tracking_enabled);
 DEFINE_PER_CPU(struct context_tracking, context_tracking);
 EXPORT_SYMBOL_GPL(context_tracking);
 
-void context_tracking_cpu_set(int cpu)
+static bool context_tracking_recursion_enter(void)
 {
-	if (!per_cpu(context_tracking.active, cpu)) {
-		per_cpu(context_tracking.active, cpu) = true;
-		static_key_slow_inc(&context_tracking_enabled);
-	}
+	int recursion;
+
+	recursion = __this_cpu_inc_return(context_tracking.recursion);
+	if (recursion == 1)
+		return true;
+
+	WARN_ONCE((recursion < 1), "Invalid context tracking recursion value %d\n", recursion);
+	__this_cpu_dec(context_tracking.recursion);
+
+	return false;
+}
+
+static void context_tracking_recursion_exit(void)
+{
+	__this_cpu_dec(context_tracking.recursion);
 }
 
 /**
@@ -75,6 +86,9 @@ void context_tracking_enter(enum ctx_state state)
 	WARN_ON_ONCE(!current->mm);
 
 	local_irq_save(flags);
+	if (!context_tracking_recursion_enter())
+		goto out_irq_restore;
+
 	if ( __this_cpu_read(context_tracking.state) != state) {
 		if (__this_cpu_read(context_tracking.active)) {
 			/*
@@ -105,6 +119,8 @@ void context_tracking_enter(enum ctx_state state)
 		 */
 		__this_cpu_write(context_tracking.state, state);
 	}
+	context_tracking_recursion_exit();
+out_irq_restore:
 	local_irq_restore(flags);
 }
 NOKPROBE_SYMBOL(context_tracking_enter);
@@ -139,6 +155,9 @@ void context_tracking_exit(enum ctx_state state)
 		return;
 
 	local_irq_save(flags);
+	if (!context_tracking_recursion_enter())
+		goto out_irq_restore;
+
 	if (__this_cpu_read(context_tracking.state) == state) {
 		if (__this_cpu_read(context_tracking.active)) {
 			/*
@@ -153,6 +172,8 @@ void context_tracking_exit(enum ctx_state state)
 		}
 		__this_cpu_write(context_tracking.state, CONTEXT_KERNEL);
 	}
+	context_tracking_recursion_exit();
+out_irq_restore:
 	local_irq_restore(flags);
 }
 NOKPROBE_SYMBOL(context_tracking_exit);
@@ -164,24 +185,26 @@ void context_tracking_user_exit(void)
 }
 NOKPROBE_SYMBOL(context_tracking_user_exit);
 
-/**
- * __context_tracking_task_switch - context switch the syscall callbacks
- * @prev: the task that is being switched out
- * @next: the task that is being switched in
- *
- * The context tracking uses the syscall slow path to implement its user-kernel
- * boundaries probes on syscalls. This way it doesn't impact the syscall fast
- * path on CPUs that don't do context tracking.
- *
- * But we need to clear the flag on the previous task because it may later
- * migrate to some CPU that doesn't do the context tracking. As such the TIF
- * flag may not be desired there.
- */
-void __context_tracking_task_switch(struct task_struct *prev,
-				    struct task_struct *next)
+void __init context_tracking_cpu_set(int cpu)
 {
-	clear_tsk_thread_flag(prev, TIF_NOHZ);
-	set_tsk_thread_flag(next, TIF_NOHZ);
+	static __initdata bool initialized = false;
+
+	if (!per_cpu(context_tracking.active, cpu)) {
+		per_cpu(context_tracking.active, cpu) = true;
+		static_key_slow_inc(&context_tracking_enabled);
+	}
+
+	if (initialized)
+		return;
+
+	/*
+	 * Set TIF_NOHZ to init/0 and let it propagate to all tasks through fork
+	 * This assumes that init is the only task at this early boot stage.
+	 */
+	set_tsk_thread_flag(&init_task, TIF_NOHZ);
+	WARN_ON_ONCE(!tasklist_empty());
+
+	initialized = true;
 }
 
 #ifdef CONFIG_CONTEXT_TRACKING_FORCE
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 94bbe4695232..9c9c9fab16cc 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -398,7 +398,6 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 	err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu));
 	if (err) {
 		/* CPU didn't die: tell everyone.  Can't complain. */
-		smpboot_unpark_threads(cpu);
 		cpu_notify_nofail(CPU_DOWN_FAILED | mod, hcpu);
 		goto out_release;
 	}
@@ -463,6 +462,7 @@ static int smpboot_thread_call(struct notifier_block *nfb,
 
 	switch (action & ~CPU_TASKS_FROZEN) {
 
+	case CPU_DOWN_FAILED:
 	case CPU_ONLINE:
 		smpboot_unpark_threads(cpu);
 		break;
@@ -479,7 +479,7 @@ static struct notifier_block smpboot_thread_notifier = {
 	.priority = CPU_PRI_SMPBOOT,
 };
 
-void __cpuinit smpboot_thread_init(void)
+void smpboot_thread_init(void)
 {
 	register_cpu_notifier(&smpboot_thread_notifier);
 }
diff --git a/kernel/events/core.c b/kernel/events/core.c
index eddf1ed4155e..8e13f3e54ec3 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -51,9 +51,11 @@
 
 static struct workqueue_struct *perf_wq;
 
+typedef int (*remote_function_f)(void *);
+
 struct remote_function_call {
 	struct task_struct	*p;
-	int			(*func)(void *info);
+	remote_function_f	func;
 	void			*info;
 	int			ret;
 };
@@ -86,7 +88,7 @@ static void remote_function(void *data)
  *	    -EAGAIN - when the process moved away
  */
 static int
-task_function_call(struct task_struct *p, int (*func) (void *info), void *info)
+task_function_call(struct task_struct *p, remote_function_f func, void *info)
 {
 	struct remote_function_call data = {
 		.p	= p,
@@ -110,7 +112,7 @@ task_function_call(struct task_struct *p, int (*func) (void *info), void *info)
  *
  * returns: @func return value or -ENXIO when the cpu is offline
  */
-static int cpu_function_call(int cpu, int (*func) (void *info), void *info)
+static int cpu_function_call(int cpu, remote_function_f func, void *info)
 {
 	struct remote_function_call data = {
 		.p	= NULL,
@@ -747,62 +749,31 @@ perf_cgroup_mark_enabled(struct perf_event *event,
 /*
  * function must be called with interrupts disbled
  */
-static enum hrtimer_restart perf_cpu_hrtimer_handler(struct hrtimer *hr)
+static enum hrtimer_restart perf_mux_hrtimer_handler(struct hrtimer *hr)
 {
 	struct perf_cpu_context *cpuctx;
-	enum hrtimer_restart ret = HRTIMER_NORESTART;
 	int rotations = 0;
 
 	WARN_ON(!irqs_disabled());
 
 	cpuctx = container_of(hr, struct perf_cpu_context, hrtimer);
-
 	rotations = perf_rotate_context(cpuctx);
 
-	/*
-	 * arm timer if needed
-	 */
-	if (rotations) {
+	raw_spin_lock(&cpuctx->hrtimer_lock);
+	if (rotations)
 		hrtimer_forward_now(hr, cpuctx->hrtimer_interval);
-		ret = HRTIMER_RESTART;
-	}
-
-	return ret;
-}
-
-/* CPU is going down */
-void perf_cpu_hrtimer_cancel(int cpu)
-{
-	struct perf_cpu_context *cpuctx;
-	struct pmu *pmu;
-	unsigned long flags;
-
-	if (WARN_ON(cpu != smp_processor_id()))
-		return;
-
-	local_irq_save(flags);
-
-	rcu_read_lock();
-
-	list_for_each_entry_rcu(pmu, &pmus, entry) {
-		cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
-
-		if (pmu->task_ctx_nr == perf_sw_context)
-			continue;
-
-		hrtimer_cancel(&cpuctx->hrtimer);
-	}
-
-	rcu_read_unlock();
+	else
+		cpuctx->hrtimer_active = 0;
+	raw_spin_unlock(&cpuctx->hrtimer_lock);
 
-	local_irq_restore(flags);
+	return rotations ? HRTIMER_RESTART : HRTIMER_NORESTART;
 }
 
-static void __perf_cpu_hrtimer_init(struct perf_cpu_context *cpuctx, int cpu)
+static void __perf_mux_hrtimer_init(struct perf_cpu_context *cpuctx, int cpu)
 {
-	struct hrtimer *hr = &cpuctx->hrtimer;
+	struct hrtimer *timer = &cpuctx->hrtimer;
 	struct pmu *pmu = cpuctx->ctx.pmu;
-	int timer;
+	u64 interval;
 
 	/* no multiplexing needed for SW PMU */
 	if (pmu->task_ctx_nr == perf_sw_context)
@@ -812,31 +783,36 @@ static void __perf_cpu_hrtimer_init(struct perf_cpu_context *cpuctx, int cpu)
 	 * check default is sane, if not set then force to
 	 * default interval (1/tick)
 	 */
-	timer = pmu->hrtimer_interval_ms;
-	if (timer < 1)
-		timer = pmu->hrtimer_interval_ms = PERF_CPU_HRTIMER;
+	interval = pmu->hrtimer_interval_ms;
+	if (interval < 1)
+		interval = pmu->hrtimer_interval_ms = PERF_CPU_HRTIMER;
 
-	cpuctx->hrtimer_interval = ns_to_ktime(NSEC_PER_MSEC * timer);
+	cpuctx->hrtimer_interval = ns_to_ktime(NSEC_PER_MSEC * interval);
 
-	hrtimer_init(hr, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED);
-	hr->function = perf_cpu_hrtimer_handler;
+	raw_spin_lock_init(&cpuctx->hrtimer_lock);
+	hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED);
+	timer->function = perf_mux_hrtimer_handler;
 }
 
-static void perf_cpu_hrtimer_restart(struct perf_cpu_context *cpuctx)
+static int perf_mux_hrtimer_restart(struct perf_cpu_context *cpuctx)
 {
-	struct hrtimer *hr = &cpuctx->hrtimer;
+	struct hrtimer *timer = &cpuctx->hrtimer;
 	struct pmu *pmu = cpuctx->ctx.pmu;
+	unsigned long flags;
 
 	/* not for SW PMU */
 	if (pmu->task_ctx_nr == perf_sw_context)
-		return;
+		return 0;
 
-	if (hrtimer_active(hr))
-		return;
+	raw_spin_lock_irqsave(&cpuctx->hrtimer_lock, flags);
+	if (!cpuctx->hrtimer_active) {
+		cpuctx->hrtimer_active = 1;
+		hrtimer_forward_now(timer, cpuctx->hrtimer_interval);
+		hrtimer_start_expires(timer, HRTIMER_MODE_ABS_PINNED);
+	}
+	raw_spin_unlock_irqrestore(&cpuctx->hrtimer_lock, flags);
 
-	if (!hrtimer_callback_running(hr))
-		__hrtimer_start_range_ns(hr, cpuctx->hrtimer_interval,
-					 0, HRTIMER_MODE_REL_PINNED, 0);
+	return 0;
 }
 
 void perf_pmu_disable(struct pmu *pmu)
@@ -1935,7 +1911,7 @@ group_sched_in(struct perf_event *group_event,
 
 	if (event_sched_in(group_event, cpuctx, ctx)) {
 		pmu->cancel_txn(pmu);
-		perf_cpu_hrtimer_restart(cpuctx);
+		perf_mux_hrtimer_restart(cpuctx);
 		return -EAGAIN;
 	}
 
@@ -1982,7 +1958,7 @@ group_error:
 
 	pmu->cancel_txn(pmu);
 
-	perf_cpu_hrtimer_restart(cpuctx);
+	perf_mux_hrtimer_restart(cpuctx);
 
 	return -EAGAIN;
 }
@@ -2255,7 +2231,7 @@ static int __perf_event_enable(void *info)
 		 */
 		if (leader != event) {
 			group_sched_out(leader, cpuctx, ctx);
-			perf_cpu_hrtimer_restart(cpuctx);
+			perf_mux_hrtimer_restart(cpuctx);
 		}
 		if (leader->attr.pinned) {
 			update_group_times(leader);
@@ -4331,20 +4307,20 @@ static void ring_buffer_attach(struct perf_event *event,
 		WARN_ON_ONCE(event->rcu_pending);
 
 		old_rb = event->rb;
-		event->rcu_batches = get_state_synchronize_rcu();
-		event->rcu_pending = 1;
-
 		spin_lock_irqsave(&old_rb->event_lock, flags);
 		list_del_rcu(&event->rb_entry);
 		spin_unlock_irqrestore(&old_rb->event_lock, flags);
-	}
 
-	if (event->rcu_pending && rb) {
-		cond_synchronize_rcu(event->rcu_batches);
-		event->rcu_pending = 0;
+		event->rcu_batches = get_state_synchronize_rcu();
+		event->rcu_pending = 1;
 	}
 
 	if (rb) {
+		if (event->rcu_pending) {
+			cond_synchronize_rcu(event->rcu_batches);
+			event->rcu_pending = 0;
+		}
+
 		spin_lock_irqsave(&rb->event_lock, flags);
 		list_add_rcu(&event->rb_entry, &rb->event_list);
 		spin_unlock_irqrestore(&rb->event_lock, flags);
@@ -5381,9 +5357,9 @@ void perf_prepare_sample(struct perf_event_header *header,
 	}
 }
 
-static void perf_event_output(struct perf_event *event,
-				struct perf_sample_data *data,
-				struct pt_regs *regs)
+void perf_event_output(struct perf_event *event,
+			struct perf_sample_data *data,
+			struct pt_regs *regs)
 {
 	struct perf_output_handle handle;
 	struct perf_event_header header;
@@ -5975,6 +5951,39 @@ void perf_event_aux_event(struct perf_event *event, unsigned long head,
 }
 
 /*
+ * Lost/dropped samples logging
+ */
+void perf_log_lost_samples(struct perf_event *event, u64 lost)
+{
+	struct perf_output_handle handle;
+	struct perf_sample_data sample;
+	int ret;
+
+	struct {
+		struct perf_event_header	header;
+		u64				lost;
+	} lost_samples_event = {
+		.header = {
+			.type = PERF_RECORD_LOST_SAMPLES,
+			.misc = 0,
+			.size = sizeof(lost_samples_event),
+		},
+		.lost		= lost,
+	};
+
+	perf_event_header__init_id(&lost_samples_event.header, &sample, event);
+
+	ret = perf_output_begin(&handle, event,
+				lost_samples_event.header.size);
+	if (ret)
+		return;
+
+	perf_output_put(&handle, lost_samples_event);
+	perf_event__output_id_sample(event, &handle, &sample);
+	perf_output_end(&handle);
+}
+
+/*
  * IRQ throttle logging
  */
 
@@ -6864,9 +6873,8 @@ static void perf_swevent_start_hrtimer(struct perf_event *event)
 	} else {
 		period = max_t(u64, 10000, hwc->sample_period);
 	}
-	__hrtimer_start_range_ns(&hwc->hrtimer,
-				ns_to_ktime(period), 0,
-				HRTIMER_MODE_REL_PINNED, 0);
+	hrtimer_start(&hwc->hrtimer, ns_to_ktime(period),
+		      HRTIMER_MODE_REL_PINNED);
 }
 
 static void perf_swevent_cancel_hrtimer(struct perf_event *event)
@@ -7167,6 +7175,8 @@ perf_event_mux_interval_ms_show(struct device *dev,
 	return snprintf(page, PAGE_SIZE-1, "%d\n", pmu->hrtimer_interval_ms);
 }
 
+static DEFINE_MUTEX(mux_interval_mutex);
+
 static ssize_t
 perf_event_mux_interval_ms_store(struct device *dev,
 				 struct device_attribute *attr,
@@ -7186,17 +7196,21 @@ perf_event_mux_interval_ms_store(struct device *dev,
 	if (timer == pmu->hrtimer_interval_ms)
 		return count;
 
+	mutex_lock(&mux_interval_mutex);
 	pmu->hrtimer_interval_ms = timer;
 
 	/* update all cpuctx for this PMU */
-	for_each_possible_cpu(cpu) {
+	get_online_cpus();
+	for_each_online_cpu(cpu) {
 		struct perf_cpu_context *cpuctx;
 		cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
 		cpuctx->hrtimer_interval = ns_to_ktime(NSEC_PER_MSEC * timer);
 
-		if (hrtimer_active(&cpuctx->hrtimer))
-			hrtimer_forward_now(&cpuctx->hrtimer, cpuctx->hrtimer_interval);
+		cpu_function_call(cpu,
+			(remote_function_f)perf_mux_hrtimer_restart, cpuctx);
 	}
+	put_online_cpus();
+	mutex_unlock(&mux_interval_mutex);
 
 	return count;
 }
@@ -7301,7 +7315,7 @@ skip_type:
 		lockdep_set_class(&cpuctx->ctx.lock, &cpuctx_lock);
 		cpuctx->ctx.pmu = pmu;
 
-		__perf_cpu_hrtimer_init(cpuctx, cpu);
+		__perf_mux_hrtimer_init(cpuctx, cpu);
 
 		cpuctx->unique_pmu = pmu;
 	}
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index 9f6ce9ba4a04..2deb24c7a40d 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -72,15 +72,6 @@ static inline bool rb_has_aux(struct ring_buffer *rb)
 void perf_event_aux_event(struct perf_event *event, unsigned long head,
 			  unsigned long size, u64 flags);
 
-extern void
-perf_event_header__init_id(struct perf_event_header *header,
-			   struct perf_sample_data *data,
-			   struct perf_event *event);
-extern void
-perf_event__output_id_sample(struct perf_event *event,
-			     struct perf_output_handle *handle,
-			     struct perf_sample_data *sample);
-
 extern struct page *
 perf_mmap_to_page(struct ring_buffer *rb, unsigned long pgoff);
 
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 725c416085e3..96472824a752 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -141,7 +141,7 @@ int perf_output_begin(struct perf_output_handle *handle,
 	perf_output_get_handle(handle);
 
 	do {
-		tail = ACCESS_ONCE(rb->user_page->data_tail);
+		tail = READ_ONCE_CTRL(rb->user_page->data_tail);
 		offset = head = local_read(&rb->head);
 		if (!rb->overwrite &&
 		    unlikely(CIRC_SPACE(head, tail, perf_data_size(rb)) < size))
diff --git a/kernel/fork.c b/kernel/fork.c
index 03c1eaaa6ef5..0bb88b555550 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1091,10 +1091,7 @@ static void posix_cpu_timers_init_group(struct signal_struct *sig)
 {
 	unsigned long cpu_limit;
 
-	/* Thread group counters. */
-	thread_group_cputime_init(sig);
-
-	cpu_limit = ACCESS_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur);
+	cpu_limit = READ_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur);
 	if (cpu_limit != RLIM_INFINITY) {
 		sig->cputime_expires.prof_exp = secs_to_cputime(cpu_limit);
 		sig->cputimer.running = 1;
@@ -1396,6 +1393,9 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	p->hardirq_context = 0;
 	p->softirq_context = 0;
 #endif
+
+	p->pagefault_disabled = 0;
+
 #ifdef CONFIG_LOCKDEP
 	p->lockdep_depth = 0; /* no locks held yet */
 	p->curr_chain_key = 0;
diff --git a/kernel/futex.c b/kernel/futex.c
index 2579e407ff67..ea6ca0bca525 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1090,9 +1090,11 @@ static void __unqueue_futex(struct futex_q *q)
 
 /*
  * The hash bucket lock must be held when this is called.
- * Afterwards, the futex_q must not be accessed.
+ * Afterwards, the futex_q must not be accessed. Callers
+ * must ensure to later call wake_up_q() for the actual
+ * wakeups to occur.
  */
-static void wake_futex(struct futex_q *q)
+static void mark_wake_futex(struct wake_q_head *wake_q, struct futex_q *q)
 {
 	struct task_struct *p = q->task;
 
@@ -1100,14 +1102,10 @@ static void wake_futex(struct futex_q *q)
 		return;
 
 	/*
-	 * We set q->lock_ptr = NULL _before_ we wake up the task. If
-	 * a non-futex wake up happens on another CPU then the task
-	 * might exit and p would dereference a non-existing task
-	 * struct. Prevent this by holding a reference on p across the
-	 * wake up.
+	 * Queue the task for later wakeup for after we've released
+	 * the hb->lock. wake_q_add() grabs reference to p.
 	 */
-	get_task_struct(p);
-
+	wake_q_add(wake_q, p);
 	__unqueue_futex(q);
 	/*
 	 * The waiting task can free the futex_q as soon as
@@ -1117,9 +1115,6 @@ static void wake_futex(struct futex_q *q)
 	 */
 	smp_wmb();
 	q->lock_ptr = NULL;
-
-	wake_up_state(p, TASK_NORMAL);
-	put_task_struct(p);
 }
 
 static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this)
@@ -1217,6 +1212,7 @@ futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset)
 	struct futex_q *this, *next;
 	union futex_key key = FUTEX_KEY_INIT;
 	int ret;
+	WAKE_Q(wake_q);
 
 	if (!bitset)
 		return -EINVAL;
@@ -1244,13 +1240,14 @@ futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset)
 			if (!(this->bitset & bitset))
 				continue;
 
-			wake_futex(this);
+			mark_wake_futex(&wake_q, this);
 			if (++ret >= nr_wake)
 				break;
 		}
 	}
 
 	spin_unlock(&hb->lock);
+	wake_up_q(&wake_q);
 out_put_key:
 	put_futex_key(&key);
 out:
@@ -1269,6 +1266,7 @@ futex_wake_op(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2,
 	struct futex_hash_bucket *hb1, *hb2;
 	struct futex_q *this, *next;
 	int ret, op_ret;
+	WAKE_Q(wake_q);
 
 retry:
 	ret = get_futex_key(uaddr1, flags & FLAGS_SHARED, &key1, VERIFY_READ);
@@ -1320,7 +1318,7 @@ retry_private:
 				ret = -EINVAL;
 				goto out_unlock;
 			}
-			wake_futex(this);
+			mark_wake_futex(&wake_q, this);
 			if (++ret >= nr_wake)
 				break;
 		}
@@ -1334,7 +1332,7 @@ retry_private:
 					ret = -EINVAL;
 					goto out_unlock;
 				}
-				wake_futex(this);
+				mark_wake_futex(&wake_q, this);
 				if (++op_ret >= nr_wake2)
 					break;
 			}
@@ -1344,6 +1342,7 @@ retry_private:
 
 out_unlock:
 	double_unlock_hb(hb1, hb2);
+	wake_up_q(&wake_q);
 out_put_keys:
 	put_futex_key(&key2);
 out_put_key1:
@@ -1503,6 +1502,7 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags,
 	struct futex_pi_state *pi_state = NULL;
 	struct futex_hash_bucket *hb1, *hb2;
 	struct futex_q *this, *next;
+	WAKE_Q(wake_q);
 
 	if (requeue_pi) {
 		/*
@@ -1679,7 +1679,7 @@ retry_private:
 		 * woken by futex_unlock_pi().
 		 */
 		if (++task_count <= nr_wake && !requeue_pi) {
-			wake_futex(this);
+			mark_wake_futex(&wake_q, this);
 			continue;
 		}
 
@@ -1719,6 +1719,7 @@ retry_private:
 out_unlock:
 	free_pi_state(pi_state);
 	double_unlock_hb(hb1, hb2);
+	wake_up_q(&wake_q);
 	hb_waiters_dec(hb2);
 
 	/*
@@ -2055,7 +2056,7 @@ static void futex_wait_queue_me(struct futex_hash_bucket *hb, struct futex_q *q,
 {
 	/*
 	 * The task state is guaranteed to be set before another task can
-	 * wake it. set_current_state() is implemented using set_mb() and
+	 * wake it. set_current_state() is implemented using smp_store_mb() and
 	 * queue_me() calls spin_unlock() upon completion, both serializing
 	 * access to the hash list and forcing another memory barrier.
 	 */
@@ -2063,11 +2064,8 @@ static void futex_wait_queue_me(struct futex_hash_bucket *hb, struct futex_q *q,
 	queue_me(q, hb);
 
 	/* Arm the timer */
-	if (timeout) {
+	if (timeout)
 		hrtimer_start_expires(&timeout->timer, HRTIMER_MODE_ABS);
-		if (!hrtimer_active(&timeout->timer))
-			timeout->task = NULL;
-	}
 
 	/*
 	 * If we have been removed from the hash list, then another task
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index eb9a4ea394ab..27f4332c7f84 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -719,15 +719,9 @@ void handle_percpu_devid_irq(unsigned int irq, struct irq_desc *desc)
 }
 
 void
-__irq_set_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
-		  const char *name)
+__irq_do_set_handler(struct irq_desc *desc, irq_flow_handler_t handle,
+		     int is_chained, const char *name)
 {
-	unsigned long flags;
-	struct irq_desc *desc = irq_get_desc_buslock(irq, &flags, 0);
-
-	if (!desc)
-		return;
-
 	if (!handle) {
 		handle = handle_bad_irq;
 	} else {
@@ -749,13 +743,13 @@ __irq_set_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
 			 * right away.
 			 */
 			if (WARN_ON(is_chained))
-				goto out;
+				return;
 			/* Try the parent */
 			irq_data = irq_data->parent_data;
 		}
 #endif
 		if (WARN_ON(!irq_data || irq_data->chip == &no_irq_chip))
-			goto out;
+			return;
 	}
 
 	/* Uninstall? */
@@ -774,12 +768,41 @@ __irq_set_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
 		irq_settings_set_nothread(desc);
 		irq_startup(desc, true);
 	}
-out:
+}
+
+void
+__irq_set_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
+		  const char *name)
+{
+	unsigned long flags;
+	struct irq_desc *desc = irq_get_desc_buslock(irq, &flags, 0);
+
+	if (!desc)
+		return;
+
+	__irq_do_set_handler(desc, handle, is_chained, name);
 	irq_put_desc_busunlock(desc, flags);
 }
 EXPORT_SYMBOL_GPL(__irq_set_handler);
 
 void
+irq_set_chained_handler_and_data(unsigned int irq, irq_flow_handler_t handle,
+				 void *data)
+{
+	unsigned long flags;
+	struct irq_desc *desc = irq_get_desc_buslock(irq, &flags, 0);
+
+	if (!desc)
+		return;
+
+	__irq_do_set_handler(desc, handle, 1, NULL);
+	desc->irq_data.handler_data = data;
+
+	irq_put_desc_busunlock(desc, flags);
+}
+EXPORT_SYMBOL_GPL(irq_set_chained_handler_and_data);
+
+void
 irq_set_chip_and_handler_name(unsigned int irq, struct irq_chip *chip,
 			      irq_flow_handler_t handle, const char *name)
 {
@@ -876,6 +899,34 @@ void irq_cpu_offline(void)
 
 #ifdef	CONFIG_IRQ_DOMAIN_HIERARCHY
 /**
+ * irq_chip_enable_parent - Enable the parent interrupt (defaults to unmask if
+ * NULL)
+ * @data:	Pointer to interrupt specific data
+ */
+void irq_chip_enable_parent(struct irq_data *data)
+{
+	data = data->parent_data;
+	if (data->chip->irq_enable)
+		data->chip->irq_enable(data);
+	else
+		data->chip->irq_unmask(data);
+}
+
+/**
+ * irq_chip_disable_parent - Disable the parent interrupt (defaults to mask if
+ * NULL)
+ * @data:	Pointer to interrupt specific data
+ */
+void irq_chip_disable_parent(struct irq_data *data)
+{
+	data = data->parent_data;
+	if (data->chip->irq_disable)
+		data->chip->irq_disable(data);
+	else
+		data->chip->irq_mask(data);
+}
+
+/**
  * irq_chip_ack_parent - Acknowledge the parent interrupt
  * @data:	Pointer to interrupt specific data
  */
@@ -950,6 +1001,20 @@ int irq_chip_retrigger_hierarchy(struct irq_data *data)
 }
 
 /**
+ * irq_chip_set_vcpu_affinity_parent - Set vcpu affinity on the parent interrupt
+ * @data:	Pointer to interrupt specific data
+ * @dest:	The vcpu affinity information
+ */
+int irq_chip_set_vcpu_affinity_parent(struct irq_data *data, void *vcpu_info)
+{
+	data = data->parent_data;
+	if (data->chip->irq_set_vcpu_affinity)
+		return data->chip->irq_set_vcpu_affinity(data, vcpu_info);
+
+	return -ENOSYS;
+}
+
+/**
  * irq_chip_set_wake_parent - Set/reset wake-up on the parent interrupt
  * @data:	Pointer to interrupt specific data
  * @on:		Whether to set or reset the wake-up capability of this irq
diff --git a/kernel/irq/devres.c b/kernel/irq/devres.c
index d5d0f7345c54..74d90a754268 100644
--- a/kernel/irq/devres.c
+++ b/kernel/irq/devres.c
@@ -104,7 +104,7 @@ int devm_request_any_context_irq(struct device *dev, unsigned int irq,
 		return -ENOMEM;
 
 	rc = request_any_context_irq(irq, handler, irqflags, devname, dev_id);
-	if (rc) {
+	if (rc < 0) {
 		devres_free(dr);
 		return rc;
 	}
@@ -113,7 +113,7 @@ int devm_request_any_context_irq(struct device *dev, unsigned int irq,
 	dr->dev_id = dev_id;
 	devres_add(dev, dr);
 
-	return 0;
+	return rc;
 }
 EXPORT_SYMBOL(devm_request_any_context_irq);
 
diff --git a/kernel/irq/dummychip.c b/kernel/irq/dummychip.c
index 2feb6feca0cc..326a67f2410b 100644
--- a/kernel/irq/dummychip.c
+++ b/kernel/irq/dummychip.c
@@ -42,6 +42,7 @@ struct irq_chip no_irq_chip = {
 	.irq_enable	= noop,
 	.irq_disable	= noop,
 	.irq_ack	= ack_bad,
+	.flags		= IRQCHIP_SKIP_SET_WAKE,
 };
 
 /*
diff --git a/kernel/irq/generic-chip.c b/kernel/irq/generic-chip.c
index 61024e8abdef..15b370daf234 100644
--- a/kernel/irq/generic-chip.c
+++ b/kernel/irq/generic-chip.c
@@ -360,7 +360,7 @@ static struct lock_class_key irq_nested_lock_class;
 int irq_map_generic_chip(struct irq_domain *d, unsigned int virq,
 			 irq_hw_number_t hw_irq)
 {
-	struct irq_data *data = irq_get_irq_data(virq);
+	struct irq_data *data = irq_domain_get_irq_data(d, virq);
 	struct irq_domain_chip_generic *dgc = d->gc;
 	struct irq_chip_generic *gc;
 	struct irq_chip_type *ct;
@@ -405,8 +405,7 @@ int irq_map_generic_chip(struct irq_domain *d, unsigned int virq,
 	else
 		data->mask = 1 << idx;
 
-	irq_set_chip_and_handler(virq, chip, ct->handler);
-	irq_set_chip_data(virq, gc);
+	irq_domain_set_info(d, virq, hw_irq, chip, gc, ct->handler, NULL, NULL);
 	irq_modify_status(virq, dgc->irq_flags_to_clear, dgc->irq_flags_to_set);
 	return 0;
 }
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index df553b0af936..4834ee828c41 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -59,8 +59,6 @@ enum {
 #include "debug.h"
 #include "settings.h"
 
-#define irq_data_to_desc(data)	container_of(data, struct irq_desc, irq_data)
-
 extern int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
 		unsigned long flags);
 extern void __disable_irq(struct irq_desc *desc, unsigned int irq);
@@ -170,27 +168,27 @@ irq_put_desc_unlock(struct irq_desc *desc, unsigned long flags)
  */
 static inline void irqd_set_move_pending(struct irq_data *d)
 {
-	d->state_use_accessors |= IRQD_SETAFFINITY_PENDING;
+	__irqd_to_state(d) |= IRQD_SETAFFINITY_PENDING;
 }
 
 static inline void irqd_clr_move_pending(struct irq_data *d)
 {
-	d->state_use_accessors &= ~IRQD_SETAFFINITY_PENDING;
+	__irqd_to_state(d) &= ~IRQD_SETAFFINITY_PENDING;
 }
 
 static inline void irqd_clear(struct irq_data *d, unsigned int mask)
 {
-	d->state_use_accessors &= ~mask;
+	__irqd_to_state(d) &= ~mask;
 }
 
 static inline void irqd_set(struct irq_data *d, unsigned int mask)
 {
-	d->state_use_accessors |= mask;
+	__irqd_to_state(d) |= mask;
 }
 
 static inline bool irqd_has_set(struct irq_data *d, unsigned int mask)
 {
-	return d->state_use_accessors & mask;
+	return __irqd_to_state(d) & mask;
 }
 
 static inline void kstat_incr_irqs_this_cpu(unsigned int irq, struct irq_desc *desc)
@@ -199,6 +197,11 @@ static inline void kstat_incr_irqs_this_cpu(unsigned int irq, struct irq_desc *d
 	__this_cpu_inc(kstat.irqs_sum);
 }
 
+static inline int irq_desc_get_node(struct irq_desc *desc)
+{
+	return irq_data_get_node(&desc->irq_data);
+}
+
 #ifdef CONFIG_PM_SLEEP
 bool irq_pm_check_wakeup(struct irq_desc *desc);
 void irq_pm_install_action(struct irq_desc *desc, struct irqaction *action);
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 99793b9b6d23..4afc457613dd 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -59,16 +59,10 @@ static void desc_smp_init(struct irq_desc *desc, int node)
 #endif
 }
 
-static inline int desc_node(struct irq_desc *desc)
-{
-	return desc->irq_data.node;
-}
-
 #else
 static inline int
 alloc_masks(struct irq_desc *desc, gfp_t gfp, int node) { return 0; }
 static inline void desc_smp_init(struct irq_desc *desc, int node) { }
-static inline int desc_node(struct irq_desc *desc) { return 0; }
 #endif
 
 static void desc_set_defaults(unsigned int irq, struct irq_desc *desc, int node,
@@ -76,6 +70,7 @@ static void desc_set_defaults(unsigned int irq, struct irq_desc *desc, int node,
 {
 	int cpu;
 
+	desc->irq_data.common = &desc->irq_common_data;
 	desc->irq_data.irq = irq;
 	desc->irq_data.chip = &no_irq_chip;
 	desc->irq_data.chip_data = NULL;
@@ -299,7 +294,7 @@ static void free_desc(unsigned int irq)
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&desc->lock, flags);
-	desc_set_defaults(irq, desc, desc_node(desc), NULL);
+	desc_set_defaults(irq, desc, irq_desc_get_node(desc), NULL);
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 }
 
@@ -619,7 +614,7 @@ unsigned int kstat_irqs(unsigned int irq)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	int cpu;
-	int sum = 0;
+	unsigned int sum = 0;
 
 	if (!desc || !desc->kstat_irqs)
 		return 0;
@@ -639,7 +634,7 @@ unsigned int kstat_irqs(unsigned int irq)
  */
 unsigned int kstat_irqs_usr(unsigned int irq)
 {
-	int sum;
+	unsigned int sum;
 
 	irq_lock_sparse();
 	sum = kstat_irqs(irq);
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 7fac311057b8..8c3577fef78c 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -830,10 +830,12 @@ static struct irq_data *irq_domain_insert_irq_data(struct irq_domain *domain,
 {
 	struct irq_data *irq_data;
 
-	irq_data = kzalloc_node(sizeof(*irq_data), GFP_KERNEL, child->node);
+	irq_data = kzalloc_node(sizeof(*irq_data), GFP_KERNEL,
+				irq_data_get_node(child));
 	if (irq_data) {
 		child->parent_data = irq_data;
 		irq_data->irq = child->irq;
+		irq_data->common = child->common;
 		irq_data->node = child->node;
 		irq_data->domain = domain;
 	}
@@ -1232,6 +1234,27 @@ struct irq_data *irq_domain_get_irq_data(struct irq_domain *domain,
 	return (irq_data && irq_data->domain == domain) ? irq_data : NULL;
 }
 
+/**
+ * irq_domain_set_info - Set the complete data for a @virq in @domain
+ * @domain:		Interrupt domain to match
+ * @virq:		IRQ number
+ * @hwirq:		The hardware interrupt number
+ * @chip:		The associated interrupt chip
+ * @chip_data:		The associated interrupt chip data
+ * @handler:		The interrupt flow handler
+ * @handler_data:	The interrupt flow handler data
+ * @handler_name:	The interrupt handler name
+ */
+void irq_domain_set_info(struct irq_domain *domain, unsigned int virq,
+			 irq_hw_number_t hwirq, struct irq_chip *chip,
+			 void *chip_data, irq_flow_handler_t handler,
+			 void *handler_data, const char *handler_name)
+{
+	irq_set_chip_and_handler_name(virq, chip, handler, handler_name);
+	irq_set_chip_data(virq, chip_data);
+	irq_set_handler_data(virq, handler_data);
+}
+
 static void irq_domain_check_hierarchy(struct irq_domain *domain)
 {
 }
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index e68932bb308e..f9744853b656 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -256,6 +256,37 @@ int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m)
 }
 EXPORT_SYMBOL_GPL(irq_set_affinity_hint);
 
+/**
+ *	irq_set_vcpu_affinity - Set vcpu affinity for the interrupt
+ *	@irq: interrupt number to set affinity
+ *	@vcpu_info: vCPU specific data
+ *
+ *	This function uses the vCPU specific data to set the vCPU
+ *	affinity for an irq. The vCPU specific data is passed from
+ *	outside, such as KVM. One example code path is as below:
+ *	KVM -> IOMMU -> irq_set_vcpu_affinity().
+ */
+int irq_set_vcpu_affinity(unsigned int irq, void *vcpu_info)
+{
+	unsigned long flags;
+	struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0);
+	struct irq_data *data;
+	struct irq_chip *chip;
+	int ret = -ENOSYS;
+
+	if (!desc)
+		return -EINVAL;
+
+	data = irq_desc_get_irq_data(desc);
+	chip = irq_data_get_irq_chip(data);
+	if (chip && chip->irq_set_vcpu_affinity)
+		ret = chip->irq_set_vcpu_affinity(data, vcpu_info);
+	irq_put_desc_unlock(desc, flags);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(irq_set_vcpu_affinity);
+
 static void irq_affinity_notify(struct work_struct *work)
 {
 	struct irq_affinity_notify *notify =
@@ -332,7 +363,7 @@ static int
 setup_affinity(unsigned int irq, struct irq_desc *desc, struct cpumask *mask)
 {
 	struct cpumask *set = irq_default_affinity;
-	int node = desc->irq_data.node;
+	int node = irq_desc_get_node(desc);
 
 	/* Excludes PER_CPU and NO_BALANCE interrupts */
 	if (!irq_can_set_affinity(irq))
diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c
index ca3f4aaff707..37ddb7bda651 100644
--- a/kernel/irq/migration.c
+++ b/kernel/irq/migration.c
@@ -7,21 +7,21 @@
 void irq_move_masked_irq(struct irq_data *idata)
 {
 	struct irq_desc *desc = irq_data_to_desc(idata);
-	struct irq_chip *chip = idata->chip;
+	struct irq_chip *chip = desc->irq_data.chip;
 
 	if (likely(!irqd_is_setaffinity_pending(&desc->irq_data)))
 		return;
 
+	irqd_clr_move_pending(&desc->irq_data);
+
 	/*
 	 * Paranoia: cpu-local interrupts shouldn't be calling in here anyway.
 	 */
-	if (!irqd_can_balance(&desc->irq_data)) {
+	if (irqd_is_per_cpu(&desc->irq_data)) {
 		WARN_ON(1);
 		return;
 	}
 
-	irqd_clr_move_pending(&desc->irq_data);
-
 	if (unlikely(cpumask_empty(desc->pending_mask)))
 		return;
 
@@ -52,6 +52,13 @@ void irq_move_irq(struct irq_data *idata)
 {
 	bool masked;
 
+	/*
+	 * Get top level irq_data when CONFIG_IRQ_DOMAIN_HIERARCHY is enabled,
+	 * and it should be optimized away when CONFIG_IRQ_DOMAIN_HIERARCHY is
+	 * disabled. So we avoid an "#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY" here.
+	 */
+	idata = irq_desc_get_irq_data(irq_data_to_desc(idata));
+
 	if (likely(!irqd_is_setaffinity_pending(idata)))
 		return;
 
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index 474de5cb394d..7bf1f1bbb7fa 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -124,7 +124,7 @@ static void msi_domain_free(struct irq_domain *domain, unsigned int virq,
 	irq_domain_free_irqs_top(domain, virq, nr_irqs);
 }
 
-static struct irq_domain_ops msi_domain_ops = {
+static const struct irq_domain_ops msi_domain_ops = {
 	.alloc		= msi_domain_alloc,
 	.free		= msi_domain_free,
 	.activate	= msi_domain_activate,
diff --git a/kernel/irq/pm.c b/kernel/irq/pm.c
index 5204a6d1b985..d22786a6dbde 100644
--- a/kernel/irq/pm.c
+++ b/kernel/irq/pm.c
@@ -123,6 +123,8 @@ void suspend_device_irqs(void)
 		unsigned long flags;
 		bool sync;
 
+		if (irq_settings_is_nested_thread(desc))
+			continue;
 		raw_spin_lock_irqsave(&desc->lock, flags);
 		sync = suspend_device_irq(desc, irq);
 		raw_spin_unlock_irqrestore(&desc->lock, flags);
@@ -163,6 +165,8 @@ static void resume_irqs(bool want_early)
 
 		if (!is_early && want_early)
 			continue;
+		if (irq_settings_is_nested_thread(desc))
+			continue;
 
 		raw_spin_lock_irqsave(&desc->lock, flags);
 		resume_irq(desc, irq);
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index df2f4642d1e7..0e97c142ce40 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -241,7 +241,7 @@ static int irq_node_proc_show(struct seq_file *m, void *v)
 {
 	struct irq_desc *desc = irq_to_desc((long) m->private);
 
-	seq_printf(m, "%d\n", desc->irq_data.node);
+	seq_printf(m, "%d\n", irq_desc_get_node(desc));
 	return 0;
 }
 
diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c
index 284e2691e380..c40ebcca0495 100644
--- a/kernel/livepatch/core.c
+++ b/kernel/livepatch/core.c
@@ -128,7 +128,7 @@ static bool klp_is_patch_registered(struct klp_patch *patch)
 
 static bool klp_initialized(void)
 {
-	return klp_root_kobj;
+	return !!klp_root_kobj;
 }
 
 struct klp_find_arg {
@@ -179,7 +179,9 @@ static int klp_find_object_symbol(const char *objname, const char *name,
 		.count = 0
 	};
 
+	mutex_lock(&module_mutex);
 	kallsyms_on_each_symbol(klp_find_callback, &args);
+	mutex_unlock(&module_mutex);
 
 	if (args.count == 0)
 		pr_err("symbol '%s' not found in symbol table\n", name);
@@ -219,13 +221,19 @@ static int klp_verify_vmlinux_symbol(const char *name, unsigned long addr)
 		.name = name,
 		.addr = addr,
 	};
+	int ret;
 
-	if (kallsyms_on_each_symbol(klp_verify_callback, &args))
-		return 0;
+	mutex_lock(&module_mutex);
+	ret = kallsyms_on_each_symbol(klp_verify_callback, &args);
+	mutex_unlock(&module_mutex);
 
-	pr_err("symbol '%s' not found at specified address 0x%016lx, kernel mismatch?\n",
-		name, addr);
-	return -EINVAL;
+	if (!ret) {
+		pr_err("symbol '%s' not found at specified address 0x%016lx, kernel mismatch?\n",
+			name, addr);
+		return -EINVAL;
+	}
+
+	return 0;
 }
 
 static int klp_find_verify_func_addr(struct klp_object *obj,
@@ -234,8 +242,9 @@ static int klp_find_verify_func_addr(struct klp_object *obj,
 	int ret;
 
 #if defined(CONFIG_RANDOMIZE_BASE)
-	/* KASLR is enabled, disregard old_addr from user */
-	func->old_addr = 0;
+	/* If KASLR has been enabled, adjust old_addr accordingly */
+	if (kaslr_enabled() && func->old_addr)
+		func->old_addr += kaslr_offset();
 #endif
 
 	if (!func->old_addr || klp_is_module(obj))
@@ -422,7 +431,7 @@ static void klp_disable_object(struct klp_object *obj)
 {
 	struct klp_func *func;
 
-	for (func = obj->funcs; func->old_name; func++)
+	klp_for_each_func(obj, func)
 		if (func->state == KLP_ENABLED)
 			klp_disable_func(func);
 
@@ -440,7 +449,7 @@ static int klp_enable_object(struct klp_object *obj)
 	if (WARN_ON(!klp_is_object_loaded(obj)))
 		return -EINVAL;
 
-	for (func = obj->funcs; func->old_name; func++) {
+	klp_for_each_func(obj, func) {
 		ret = klp_enable_func(func);
 		if (ret) {
 			klp_disable_object(obj);
@@ -463,7 +472,7 @@ static int __klp_disable_patch(struct klp_patch *patch)
 
 	pr_notice("disabling patch '%s'\n", patch->mod->name);
 
-	for (obj = patch->objs; obj->funcs; obj++) {
+	klp_for_each_object(patch, obj) {
 		if (obj->state == KLP_ENABLED)
 			klp_disable_object(obj);
 	}
@@ -523,7 +532,7 @@ static int __klp_enable_patch(struct klp_patch *patch)
 
 	pr_notice("enabling patch '%s'\n", patch->mod->name);
 
-	for (obj = patch->objs; obj->funcs; obj++) {
+	klp_for_each_object(patch, obj) {
 		if (!klp_is_object_loaded(obj))
 			continue;
 
@@ -651,6 +660,15 @@ static struct kobj_type klp_ktype_patch = {
 	.default_attrs = klp_patch_attrs,
 };
 
+static void klp_kobj_release_object(struct kobject *kobj)
+{
+}
+
+static struct kobj_type klp_ktype_object = {
+	.release = klp_kobj_release_object,
+	.sysfs_ops = &kobj_sysfs_ops,
+};
+
 static void klp_kobj_release_func(struct kobject *kobj)
 {
 }
@@ -680,7 +698,7 @@ static void klp_free_object_loaded(struct klp_object *obj)
 
 	obj->mod = NULL;
 
-	for (func = obj->funcs; func->old_name; func++)
+	klp_for_each_func(obj, func)
 		func->old_addr = 0;
 }
 
@@ -695,7 +713,7 @@ static void klp_free_objects_limited(struct klp_patch *patch,
 
 	for (obj = patch->objs; obj->funcs && obj != limit; obj++) {
 		klp_free_funcs_limited(obj, NULL);
-		kobject_put(obj->kobj);
+		kobject_put(&obj->kobj);
 	}
 }
 
@@ -713,7 +731,7 @@ static int klp_init_func(struct klp_object *obj, struct klp_func *func)
 	func->state = KLP_DISABLED;
 
 	return kobject_init_and_add(&func->kobj, &klp_ktype_func,
-				    obj->kobj, "%s", func->old_name);
+				    &obj->kobj, "%s", func->old_name);
 }
 
 /* parts of the initialization that is done only when the object is loaded */
@@ -729,7 +747,7 @@ static int klp_init_object_loaded(struct klp_patch *patch,
 			return ret;
 	}
 
-	for (func = obj->funcs; func->old_name; func++) {
+	klp_for_each_func(obj, func) {
 		ret = klp_find_verify_func_addr(obj, func);
 		if (ret)
 			return ret;
@@ -753,11 +771,12 @@ static int klp_init_object(struct klp_patch *patch, struct klp_object *obj)
 	klp_find_object_module(obj);
 
 	name = klp_is_module(obj) ? obj->name : "vmlinux";
-	obj->kobj = kobject_create_and_add(name, &patch->kobj);
-	if (!obj->kobj)
-		return -ENOMEM;
+	ret = kobject_init_and_add(&obj->kobj, &klp_ktype_object,
+				   &patch->kobj, "%s", name);
+	if (ret)
+		return ret;
 
-	for (func = obj->funcs; func->old_name; func++) {
+	klp_for_each_func(obj, func) {
 		ret = klp_init_func(obj, func);
 		if (ret)
 			goto free;
@@ -773,7 +792,7 @@ static int klp_init_object(struct klp_patch *patch, struct klp_object *obj)
 
 free:
 	klp_free_funcs_limited(obj, func);
-	kobject_put(obj->kobj);
+	kobject_put(&obj->kobj);
 	return ret;
 }
 
@@ -794,7 +813,7 @@ static int klp_init_patch(struct klp_patch *patch)
 	if (ret)
 		goto unlock;
 
-	for (obj = patch->objs; obj->funcs; obj++) {
+	klp_for_each_object(patch, obj) {
 		ret = klp_init_object(patch, obj);
 		if (ret)
 			goto free;
@@ -883,7 +902,7 @@ int klp_register_patch(struct klp_patch *patch)
 }
 EXPORT_SYMBOL_GPL(klp_register_patch);
 
-static void klp_module_notify_coming(struct klp_patch *patch,
+static int klp_module_notify_coming(struct klp_patch *patch,
 				     struct klp_object *obj)
 {
 	struct module *pmod = patch->mod;
@@ -891,22 +910,23 @@ static void klp_module_notify_coming(struct klp_patch *patch,
 	int ret;
 
 	ret = klp_init_object_loaded(patch, obj);
-	if (ret)
-		goto err;
+	if (ret) {
+		pr_warn("failed to initialize patch '%s' for module '%s' (%d)\n",
+			pmod->name, mod->name, ret);
+		return ret;
+	}
 
 	if (patch->state == KLP_DISABLED)
-		return;
+		return 0;
 
 	pr_notice("applying patch '%s' to loading module '%s'\n",
 		  pmod->name, mod->name);
 
 	ret = klp_enable_object(obj);
-	if (!ret)
-		return;
-
-err:
-	pr_warn("failed to apply patch '%s' to module '%s' (%d)\n",
-		pmod->name, mod->name, ret);
+	if (ret)
+		pr_warn("failed to apply patch '%s' to module '%s' (%d)\n",
+			pmod->name, mod->name, ret);
+	return ret;
 }
 
 static void klp_module_notify_going(struct klp_patch *patch,
@@ -930,6 +950,7 @@ disabled:
 static int klp_module_notify(struct notifier_block *nb, unsigned long action,
 			     void *data)
 {
+	int ret;
 	struct module *mod = data;
 	struct klp_patch *patch;
 	struct klp_object *obj;
@@ -949,13 +970,18 @@ static int klp_module_notify(struct notifier_block *nb, unsigned long action,
 		mod->klp_alive = false;
 
 	list_for_each_entry(patch, &klp_patches, list) {
-		for (obj = patch->objs; obj->funcs; obj++) {
+		klp_for_each_object(patch, obj) {
 			if (!klp_is_module(obj) || strcmp(obj->name, mod->name))
 				continue;
 
 			if (action == MODULE_STATE_COMING) {
 				obj->mod = mod;
-				klp_module_notify_coming(patch, obj);
+				ret = klp_module_notify_coming(patch, obj);
+				if (ret) {
+					obj->mod = NULL;
+					pr_warn("patch '%s' is in an inconsistent state!\n",
+						patch->mod->name);
+				}
 			} else /* MODULE_STATE_GOING */
 				klp_module_notify_going(patch, obj);
 
@@ -973,7 +999,7 @@ static struct notifier_block klp_module_nb = {
 	.priority = INT_MIN+1, /* called late but before ftrace notifier */
 };
 
-static int klp_init(void)
+static int __init klp_init(void)
 {
 	int ret;
 
diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile
index de7a416cca2a..7dd5c9918e4c 100644
--- a/kernel/locking/Makefile
+++ b/kernel/locking/Makefile
@@ -17,6 +17,7 @@ obj-$(CONFIG_SMP) += spinlock.o
 obj-$(CONFIG_LOCK_SPIN_ON_OWNER) += osq_lock.o
 obj-$(CONFIG_SMP) += lglock.o
 obj-$(CONFIG_PROVE_LOCKING) += spinlock.o
+obj-$(CONFIG_QUEUED_SPINLOCKS) += qspinlock.o
 obj-$(CONFIG_RT_MUTEXES) += rtmutex.o
 obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o
 obj-$(CONFIG_RT_MUTEX_TESTER) += rtmutex-tester.o
@@ -25,5 +26,5 @@ obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.o
 obj-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o
 obj-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem-xadd.o
 obj-$(CONFIG_PERCPU_RWSEM) += percpu-rwsem.o
-obj-$(CONFIG_QUEUE_RWLOCK) += qrwlock.o
+obj-$(CONFIG_QUEUED_RWLOCKS) += qrwlock.o
 obj-$(CONFIG_LOCK_TORTURE_TEST) += locktorture.o
diff --git a/kernel/locking/lglock.c b/kernel/locking/lglock.c
index 86ae2aebf004..951cfcd10b4a 100644
--- a/kernel/locking/lglock.c
+++ b/kernel/locking/lglock.c
@@ -60,6 +60,28 @@ void lg_local_unlock_cpu(struct lglock *lg, int cpu)
 }
 EXPORT_SYMBOL(lg_local_unlock_cpu);
 
+void lg_double_lock(struct lglock *lg, int cpu1, int cpu2)
+{
+	BUG_ON(cpu1 == cpu2);
+
+	/* lock in cpu order, just like lg_global_lock */
+	if (cpu2 < cpu1)
+		swap(cpu1, cpu2);
+
+	preempt_disable();
+	lock_acquire_shared(&lg->lock_dep_map, 0, 0, NULL, _RET_IP_);
+	arch_spin_lock(per_cpu_ptr(lg->lock, cpu1));
+	arch_spin_lock(per_cpu_ptr(lg->lock, cpu2));
+}
+
+void lg_double_unlock(struct lglock *lg, int cpu1, int cpu2)
+{
+	lock_release(&lg->lock_dep_map, 1, _RET_IP_);
+	arch_spin_unlock(per_cpu_ptr(lg->lock, cpu1));
+	arch_spin_unlock(per_cpu_ptr(lg->lock, cpu2));
+	preempt_enable();
+}
+
 void lg_global_lock(struct lglock *lg)
 {
 	int i;
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index aaeae885d9af..456614136f1a 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -4067,8 +4067,7 @@ void __init lockdep_info(void)
 
 #ifdef CONFIG_DEBUG_LOCKDEP
 	if (lockdep_init_error) {
-		printk("WARNING: lockdep init error! lock-%s was acquired"
-			"before lockdep_init\n", lock_init_error);
+		printk("WARNING: lockdep init error: lock '%s' was acquired before lockdep_init().\n", lock_init_error);
 		printk("Call stack leading to lockdep invocation was:\n");
 		print_stack_trace(&lockdep_init_trace, 0);
 	}
diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c
index ec8cce259779..32244186f1f2 100644
--- a/kernel/locking/locktorture.c
+++ b/kernel/locking/locktorture.c
@@ -122,12 +122,12 @@ static int torture_lock_busted_write_lock(void)
 
 static void torture_lock_busted_write_delay(struct torture_random_state *trsp)
 {
-	const unsigned long longdelay_us = 100;
+	const unsigned long longdelay_ms = 100;
 
 	/* We want a long delay occasionally to force massive contention.  */
 	if (!(torture_random(trsp) %
-	      (cxt.nrealwriters_stress * 2000 * longdelay_us)))
-		mdelay(longdelay_us);
+	      (cxt.nrealwriters_stress * 2000 * longdelay_ms)))
+		mdelay(longdelay_ms);
 #ifdef CONFIG_PREEMPT
 	if (!(torture_random(trsp) % (cxt.nrealwriters_stress * 20000)))
 		preempt_schedule();  /* Allow test to be preempted. */
@@ -160,14 +160,14 @@ static int torture_spin_lock_write_lock(void) __acquires(torture_spinlock)
 static void torture_spin_lock_write_delay(struct torture_random_state *trsp)
 {
 	const unsigned long shortdelay_us = 2;
-	const unsigned long longdelay_us = 100;
+	const unsigned long longdelay_ms = 100;
 
 	/* We want a short delay mostly to emulate likely code, and
 	 * we want a long delay occasionally to force massive contention.
 	 */
 	if (!(torture_random(trsp) %
-	      (cxt.nrealwriters_stress * 2000 * longdelay_us)))
-		mdelay(longdelay_us);
+	      (cxt.nrealwriters_stress * 2000 * longdelay_ms)))
+		mdelay(longdelay_ms);
 	if (!(torture_random(trsp) %
 	      (cxt.nrealwriters_stress * 2 * shortdelay_us)))
 		udelay(shortdelay_us);
@@ -309,7 +309,7 @@ static int torture_rwlock_read_lock_irq(void) __acquires(torture_rwlock)
 static void torture_rwlock_read_unlock_irq(void)
 __releases(torture_rwlock)
 {
-	write_unlock_irqrestore(&torture_rwlock, cxt.cur_ops->flags);
+	read_unlock_irqrestore(&torture_rwlock, cxt.cur_ops->flags);
 }
 
 static struct lock_torture_ops rw_lock_irq_ops = {
diff --git a/kernel/locking/mcs_spinlock.h b/kernel/locking/mcs_spinlock.h
index 75e114bdf3f2..fd91aaa4554c 100644
--- a/kernel/locking/mcs_spinlock.h
+++ b/kernel/locking/mcs_spinlock.h
@@ -17,6 +17,7 @@
 struct mcs_spinlock {
 	struct mcs_spinlock *next;
 	int locked; /* 1 if lock acquired */
+	int count;  /* nesting count, see qspinlock.c */
 };
 
 #ifndef arch_mcs_spin_lock_contended
diff --git a/kernel/locking/qrwlock.c b/kernel/locking/qrwlock.c
index f956ede7f90d..6c5da483966b 100644
--- a/kernel/locking/qrwlock.c
+++ b/kernel/locking/qrwlock.c
@@ -1,5 +1,5 @@
 /*
- * Queue read/write lock
+ * Queued read/write locks
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -22,6 +22,26 @@
 #include <linux/hardirq.h>
 #include <asm/qrwlock.h>
 
+/*
+ * This internal data structure is used for optimizing access to some of
+ * the subfields within the atomic_t cnts.
+ */
+struct __qrwlock {
+	union {
+		atomic_t cnts;
+		struct {
+#ifdef __LITTLE_ENDIAN
+			u8 wmode;	/* Writer mode   */
+			u8 rcnts[3];	/* Reader counts */
+#else
+			u8 rcnts[3];	/* Reader counts */
+			u8 wmode;	/* Writer mode   */
+#endif
+		};
+	};
+	arch_spinlock_t	lock;
+};
+
 /**
  * rspin_until_writer_unlock - inc reader count & spin until writer is gone
  * @lock  : Pointer to queue rwlock structure
@@ -107,10 +127,10 @@ void queue_write_lock_slowpath(struct qrwlock *lock)
 	 * or wait for a previous writer to go away.
 	 */
 	for (;;) {
-		cnts = atomic_read(&lock->cnts);
-		if (!(cnts & _QW_WMASK) &&
-		    (atomic_cmpxchg(&lock->cnts, cnts,
-				    cnts | _QW_WAITING) == cnts))
+		struct __qrwlock *l = (struct __qrwlock *)lock;
+
+		if (!READ_ONCE(l->wmode) &&
+		   (cmpxchg(&l->wmode, 0, _QW_WAITING) == 0))
 			break;
 
 		cpu_relax_lowlatency();
diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
new file mode 100644
index 000000000000..38c49202d532
--- /dev/null
+++ b/kernel/locking/qspinlock.c
@@ -0,0 +1,473 @@
+/*
+ * Queued spinlock
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * (C) Copyright 2013-2015 Hewlett-Packard Development Company, L.P.
+ * (C) Copyright 2013-2014 Red Hat, Inc.
+ * (C) Copyright 2015 Intel Corp.
+ *
+ * Authors: Waiman Long <waiman.long@hp.com>
+ *          Peter Zijlstra <peterz@infradead.org>
+ */
+
+#ifndef _GEN_PV_LOCK_SLOWPATH
+
+#include <linux/smp.h>
+#include <linux/bug.h>
+#include <linux/cpumask.h>
+#include <linux/percpu.h>
+#include <linux/hardirq.h>
+#include <linux/mutex.h>
+#include <asm/byteorder.h>
+#include <asm/qspinlock.h>
+
+/*
+ * The basic principle of a queue-based spinlock can best be understood
+ * by studying a classic queue-based spinlock implementation called the
+ * MCS lock. The paper below provides a good description for this kind
+ * of lock.
+ *
+ * http://www.cise.ufl.edu/tr/DOC/REP-1992-71.pdf
+ *
+ * This queued spinlock implementation is based on the MCS lock, however to make
+ * it fit the 4 bytes we assume spinlock_t to be, and preserve its existing
+ * API, we must modify it somehow.
+ *
+ * In particular; where the traditional MCS lock consists of a tail pointer
+ * (8 bytes) and needs the next pointer (another 8 bytes) of its own node to
+ * unlock the next pending (next->locked), we compress both these: {tail,
+ * next->locked} into a single u32 value.
+ *
+ * Since a spinlock disables recursion of its own context and there is a limit
+ * to the contexts that can nest; namely: task, softirq, hardirq, nmi. As there
+ * are at most 4 nesting levels, it can be encoded by a 2-bit number. Now
+ * we can encode the tail by combining the 2-bit nesting level with the cpu
+ * number. With one byte for the lock value and 3 bytes for the tail, only a
+ * 32-bit word is now needed. Even though we only need 1 bit for the lock,
+ * we extend it to a full byte to achieve better performance for architectures
+ * that support atomic byte write.
+ *
+ * We also change the first spinner to spin on the lock bit instead of its
+ * node; whereby avoiding the need to carry a node from lock to unlock, and
+ * preserving existing lock API. This also makes the unlock code simpler and
+ * faster.
+ *
+ * N.B. The current implementation only supports architectures that allow
+ *      atomic operations on smaller 8-bit and 16-bit data types.
+ *
+ */
+
+#include "mcs_spinlock.h"
+
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+#define MAX_NODES	8
+#else
+#define MAX_NODES	4
+#endif
+
+/*
+ * Per-CPU queue node structures; we can never have more than 4 nested
+ * contexts: task, softirq, hardirq, nmi.
+ *
+ * Exactly fits one 64-byte cacheline on a 64-bit architecture.
+ *
+ * PV doubles the storage and uses the second cacheline for PV state.
+ */
+static DEFINE_PER_CPU_ALIGNED(struct mcs_spinlock, mcs_nodes[MAX_NODES]);
+
+/*
+ * We must be able to distinguish between no-tail and the tail at 0:0,
+ * therefore increment the cpu number by one.
+ */
+
+static inline u32 encode_tail(int cpu, int idx)
+{
+	u32 tail;
+
+#ifdef CONFIG_DEBUG_SPINLOCK
+	BUG_ON(idx > 3);
+#endif
+	tail  = (cpu + 1) << _Q_TAIL_CPU_OFFSET;
+	tail |= idx << _Q_TAIL_IDX_OFFSET; /* assume < 4 */
+
+	return tail;
+}
+
+static inline struct mcs_spinlock *decode_tail(u32 tail)
+{
+	int cpu = (tail >> _Q_TAIL_CPU_OFFSET) - 1;
+	int idx = (tail &  _Q_TAIL_IDX_MASK) >> _Q_TAIL_IDX_OFFSET;
+
+	return per_cpu_ptr(&mcs_nodes[idx], cpu);
+}
+
+#define _Q_LOCKED_PENDING_MASK (_Q_LOCKED_MASK | _Q_PENDING_MASK)
+
+/*
+ * By using the whole 2nd least significant byte for the pending bit, we
+ * can allow better optimization of the lock acquisition for the pending
+ * bit holder.
+ *
+ * This internal structure is also used by the set_locked function which
+ * is not restricted to _Q_PENDING_BITS == 8.
+ */
+struct __qspinlock {
+	union {
+		atomic_t val;
+#ifdef __LITTLE_ENDIAN
+		struct {
+			u8	locked;
+			u8	pending;
+		};
+		struct {
+			u16	locked_pending;
+			u16	tail;
+		};
+#else
+		struct {
+			u16	tail;
+			u16	locked_pending;
+		};
+		struct {
+			u8	reserved[2];
+			u8	pending;
+			u8	locked;
+		};
+#endif
+	};
+};
+
+#if _Q_PENDING_BITS == 8
+/**
+ * clear_pending_set_locked - take ownership and clear the pending bit.
+ * @lock: Pointer to queued spinlock structure
+ *
+ * *,1,0 -> *,0,1
+ *
+ * Lock stealing is not allowed if this function is used.
+ */
+static __always_inline void clear_pending_set_locked(struct qspinlock *lock)
+{
+	struct __qspinlock *l = (void *)lock;
+
+	WRITE_ONCE(l->locked_pending, _Q_LOCKED_VAL);
+}
+
+/*
+ * xchg_tail - Put in the new queue tail code word & retrieve previous one
+ * @lock : Pointer to queued spinlock structure
+ * @tail : The new queue tail code word
+ * Return: The previous queue tail code word
+ *
+ * xchg(lock, tail)
+ *
+ * p,*,* -> n,*,* ; prev = xchg(lock, node)
+ */
+static __always_inline u32 xchg_tail(struct qspinlock *lock, u32 tail)
+{
+	struct __qspinlock *l = (void *)lock;
+
+	return (u32)xchg(&l->tail, tail >> _Q_TAIL_OFFSET) << _Q_TAIL_OFFSET;
+}
+
+#else /* _Q_PENDING_BITS == 8 */
+
+/**
+ * clear_pending_set_locked - take ownership and clear the pending bit.
+ * @lock: Pointer to queued spinlock structure
+ *
+ * *,1,0 -> *,0,1
+ */
+static __always_inline void clear_pending_set_locked(struct qspinlock *lock)
+{
+	atomic_add(-_Q_PENDING_VAL + _Q_LOCKED_VAL, &lock->val);
+}
+
+/**
+ * xchg_tail - Put in the new queue tail code word & retrieve previous one
+ * @lock : Pointer to queued spinlock structure
+ * @tail : The new queue tail code word
+ * Return: The previous queue tail code word
+ *
+ * xchg(lock, tail)
+ *
+ * p,*,* -> n,*,* ; prev = xchg(lock, node)
+ */
+static __always_inline u32 xchg_tail(struct qspinlock *lock, u32 tail)
+{
+	u32 old, new, val = atomic_read(&lock->val);
+
+	for (;;) {
+		new = (val & _Q_LOCKED_PENDING_MASK) | tail;
+		old = atomic_cmpxchg(&lock->val, val, new);
+		if (old == val)
+			break;
+
+		val = old;
+	}
+	return old;
+}
+#endif /* _Q_PENDING_BITS == 8 */
+
+/**
+ * set_locked - Set the lock bit and own the lock
+ * @lock: Pointer to queued spinlock structure
+ *
+ * *,*,0 -> *,0,1
+ */
+static __always_inline void set_locked(struct qspinlock *lock)
+{
+	struct __qspinlock *l = (void *)lock;
+
+	WRITE_ONCE(l->locked, _Q_LOCKED_VAL);
+}
+
+
+/*
+ * Generate the native code for queued_spin_unlock_slowpath(); provide NOPs for
+ * all the PV callbacks.
+ */
+
+static __always_inline void __pv_init_node(struct mcs_spinlock *node) { }
+static __always_inline void __pv_wait_node(struct mcs_spinlock *node) { }
+static __always_inline void __pv_kick_node(struct mcs_spinlock *node) { }
+
+static __always_inline void __pv_wait_head(struct qspinlock *lock,
+					   struct mcs_spinlock *node) { }
+
+#define pv_enabled()		false
+
+#define pv_init_node		__pv_init_node
+#define pv_wait_node		__pv_wait_node
+#define pv_kick_node		__pv_kick_node
+#define pv_wait_head		__pv_wait_head
+
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+#define queued_spin_lock_slowpath	native_queued_spin_lock_slowpath
+#endif
+
+#endif /* _GEN_PV_LOCK_SLOWPATH */
+
+/**
+ * queued_spin_lock_slowpath - acquire the queued spinlock
+ * @lock: Pointer to queued spinlock structure
+ * @val: Current value of the queued spinlock 32-bit word
+ *
+ * (queue tail, pending bit, lock value)
+ *
+ *              fast     :    slow                                  :    unlock
+ *                       :                                          :
+ * uncontended  (0,0,0) -:--> (0,0,1) ------------------------------:--> (*,*,0)
+ *                       :       | ^--------.------.             /  :
+ *                       :       v           \      \            |  :
+ * pending               :    (0,1,1) +--> (0,1,0)   \           |  :
+ *                       :       | ^--'              |           |  :
+ *                       :       v                   |           |  :
+ * uncontended           :    (n,x,y) +--> (n,0,0) --'           |  :
+ *   queue               :       | ^--'                          |  :
+ *                       :       v                               |  :
+ * contended             :    (*,x,y) +--> (*,0,0) ---> (*,0,1) -'  :
+ *   queue               :         ^--'                             :
+ */
+void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
+{
+	struct mcs_spinlock *prev, *next, *node;
+	u32 new, old, tail;
+	int idx;
+
+	BUILD_BUG_ON(CONFIG_NR_CPUS >= (1U << _Q_TAIL_CPU_BITS));
+
+	if (pv_enabled())
+		goto queue;
+
+	if (virt_queued_spin_lock(lock))
+		return;
+
+	/*
+	 * wait for in-progress pending->locked hand-overs
+	 *
+	 * 0,1,0 -> 0,0,1
+	 */
+	if (val == _Q_PENDING_VAL) {
+		while ((val = atomic_read(&lock->val)) == _Q_PENDING_VAL)
+			cpu_relax();
+	}
+
+	/*
+	 * trylock || pending
+	 *
+	 * 0,0,0 -> 0,0,1 ; trylock
+	 * 0,0,1 -> 0,1,1 ; pending
+	 */
+	for (;;) {
+		/*
+		 * If we observe any contention; queue.
+		 */
+		if (val & ~_Q_LOCKED_MASK)
+			goto queue;
+
+		new = _Q_LOCKED_VAL;
+		if (val == new)
+			new |= _Q_PENDING_VAL;
+
+		old = atomic_cmpxchg(&lock->val, val, new);
+		if (old == val)
+			break;
+
+		val = old;
+	}
+
+	/*
+	 * we won the trylock
+	 */
+	if (new == _Q_LOCKED_VAL)
+		return;
+
+	/*
+	 * we're pending, wait for the owner to go away.
+	 *
+	 * *,1,1 -> *,1,0
+	 *
+	 * this wait loop must be a load-acquire such that we match the
+	 * store-release that clears the locked bit and create lock
+	 * sequentiality; this is because not all clear_pending_set_locked()
+	 * implementations imply full barriers.
+	 */
+	while ((val = smp_load_acquire(&lock->val.counter)) & _Q_LOCKED_MASK)
+		cpu_relax();
+
+	/*
+	 * take ownership and clear the pending bit.
+	 *
+	 * *,1,0 -> *,0,1
+	 */
+	clear_pending_set_locked(lock);
+	return;
+
+	/*
+	 * End of pending bit optimistic spinning and beginning of MCS
+	 * queuing.
+	 */
+queue:
+	node = this_cpu_ptr(&mcs_nodes[0]);
+	idx = node->count++;
+	tail = encode_tail(smp_processor_id(), idx);
+
+	node += idx;
+	node->locked = 0;
+	node->next = NULL;
+	pv_init_node(node);
+
+	/*
+	 * We touched a (possibly) cold cacheline in the per-cpu queue node;
+	 * attempt the trylock once more in the hope someone let go while we
+	 * weren't watching.
+	 */
+	if (queued_spin_trylock(lock))
+		goto release;
+
+	/*
+	 * We have already touched the queueing cacheline; don't bother with
+	 * pending stuff.
+	 *
+	 * p,*,* -> n,*,*
+	 */
+	old = xchg_tail(lock, tail);
+
+	/*
+	 * if there was a previous node; link it and wait until reaching the
+	 * head of the waitqueue.
+	 */
+	if (old & _Q_TAIL_MASK) {
+		prev = decode_tail(old);
+		WRITE_ONCE(prev->next, node);
+
+		pv_wait_node(node);
+		arch_mcs_spin_lock_contended(&node->locked);
+	}
+
+	/*
+	 * we're at the head of the waitqueue, wait for the owner & pending to
+	 * go away.
+	 *
+	 * *,x,y -> *,0,0
+	 *
+	 * this wait loop must use a load-acquire such that we match the
+	 * store-release that clears the locked bit and create lock
+	 * sequentiality; this is because the set_locked() function below
+	 * does not imply a full barrier.
+	 *
+	 */
+	pv_wait_head(lock, node);
+	while ((val = smp_load_acquire(&lock->val.counter)) & _Q_LOCKED_PENDING_MASK)
+		cpu_relax();
+
+	/*
+	 * claim the lock:
+	 *
+	 * n,0,0 -> 0,0,1 : lock, uncontended
+	 * *,0,0 -> *,0,1 : lock, contended
+	 *
+	 * If the queue head is the only one in the queue (lock value == tail),
+	 * clear the tail code and grab the lock. Otherwise, we only need
+	 * to grab the lock.
+	 */
+	for (;;) {
+		if (val != tail) {
+			set_locked(lock);
+			break;
+		}
+		old = atomic_cmpxchg(&lock->val, val, _Q_LOCKED_VAL);
+		if (old == val)
+			goto release;	/* No contention */
+
+		val = old;
+	}
+
+	/*
+	 * contended path; wait for next, release.
+	 */
+	while (!(next = READ_ONCE(node->next)))
+		cpu_relax();
+
+	arch_mcs_spin_unlock_contended(&next->locked);
+	pv_kick_node(next);
+
+release:
+	/*
+	 * release the node
+	 */
+	this_cpu_dec(mcs_nodes[0].count);
+}
+EXPORT_SYMBOL(queued_spin_lock_slowpath);
+
+/*
+ * Generate the paravirt code for queued_spin_unlock_slowpath().
+ */
+#if !defined(_GEN_PV_LOCK_SLOWPATH) && defined(CONFIG_PARAVIRT_SPINLOCKS)
+#define _GEN_PV_LOCK_SLOWPATH
+
+#undef  pv_enabled
+#define pv_enabled()	true
+
+#undef pv_init_node
+#undef pv_wait_node
+#undef pv_kick_node
+#undef pv_wait_head
+
+#undef  queued_spin_lock_slowpath
+#define queued_spin_lock_slowpath	__pv_queued_spin_lock_slowpath
+
+#include "qspinlock_paravirt.h"
+#include "qspinlock.c"
+
+#endif
diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h
new file mode 100644
index 000000000000..04ab18151cc8
--- /dev/null
+++ b/kernel/locking/qspinlock_paravirt.h
@@ -0,0 +1,325 @@
+#ifndef _GEN_PV_LOCK_SLOWPATH
+#error "do not include this file"
+#endif
+
+#include <linux/hash.h>
+#include <linux/bootmem.h>
+
+/*
+ * Implement paravirt qspinlocks; the general idea is to halt the vcpus instead
+ * of spinning them.
+ *
+ * This relies on the architecture to provide two paravirt hypercalls:
+ *
+ *   pv_wait(u8 *ptr, u8 val) -- suspends the vcpu if *ptr == val
+ *   pv_kick(cpu)             -- wakes a suspended vcpu
+ *
+ * Using these we implement __pv_queued_spin_lock_slowpath() and
+ * __pv_queued_spin_unlock() to replace native_queued_spin_lock_slowpath() and
+ * native_queued_spin_unlock().
+ */
+
+#define _Q_SLOW_VAL	(3U << _Q_LOCKED_OFFSET)
+
+enum vcpu_state {
+	vcpu_running = 0,
+	vcpu_halted,
+};
+
+struct pv_node {
+	struct mcs_spinlock	mcs;
+	struct mcs_spinlock	__res[3];
+
+	int			cpu;
+	u8			state;
+};
+
+/*
+ * Lock and MCS node addresses hash table for fast lookup
+ *
+ * Hashing is done on a per-cacheline basis to minimize the need to access
+ * more than one cacheline.
+ *
+ * Dynamically allocate a hash table big enough to hold at least 4X the
+ * number of possible cpus in the system. Allocation is done on page
+ * granularity. So the minimum number of hash buckets should be at least
+ * 256 (64-bit) or 512 (32-bit) to fully utilize a 4k page.
+ *
+ * Since we should not be holding locks from NMI context (very rare indeed) the
+ * max load factor is 0.75, which is around the point where open addressing
+ * breaks down.
+ *
+ */
+struct pv_hash_entry {
+	struct qspinlock *lock;
+	struct pv_node   *node;
+};
+
+#define PV_HE_PER_LINE	(SMP_CACHE_BYTES / sizeof(struct pv_hash_entry))
+#define PV_HE_MIN	(PAGE_SIZE / sizeof(struct pv_hash_entry))
+
+static struct pv_hash_entry *pv_lock_hash;
+static unsigned int pv_lock_hash_bits __read_mostly;
+
+/*
+ * Allocate memory for the PV qspinlock hash buckets
+ *
+ * This function should be called from the paravirt spinlock initialization
+ * routine.
+ */
+void __init __pv_init_lock_hash(void)
+{
+	int pv_hash_size = ALIGN(4 * num_possible_cpus(), PV_HE_PER_LINE);
+
+	if (pv_hash_size < PV_HE_MIN)
+		pv_hash_size = PV_HE_MIN;
+
+	/*
+	 * Allocate space from bootmem which should be page-size aligned
+	 * and hence cacheline aligned.
+	 */
+	pv_lock_hash = alloc_large_system_hash("PV qspinlock",
+					       sizeof(struct pv_hash_entry),
+					       pv_hash_size, 0, HASH_EARLY,
+					       &pv_lock_hash_bits, NULL,
+					       pv_hash_size, pv_hash_size);
+}
+
+#define for_each_hash_entry(he, offset, hash)						\
+	for (hash &= ~(PV_HE_PER_LINE - 1), he = &pv_lock_hash[hash], offset = 0;	\
+	     offset < (1 << pv_lock_hash_bits);						\
+	     offset++, he = &pv_lock_hash[(hash + offset) & ((1 << pv_lock_hash_bits) - 1)])
+
+static struct qspinlock **pv_hash(struct qspinlock *lock, struct pv_node *node)
+{
+	unsigned long offset, hash = hash_ptr(lock, pv_lock_hash_bits);
+	struct pv_hash_entry *he;
+
+	for_each_hash_entry(he, offset, hash) {
+		if (!cmpxchg(&he->lock, NULL, lock)) {
+			WRITE_ONCE(he->node, node);
+			return &he->lock;
+		}
+	}
+	/*
+	 * Hard assume there is a free entry for us.
+	 *
+	 * This is guaranteed by ensuring every blocked lock only ever consumes
+	 * a single entry, and since we only have 4 nesting levels per CPU
+	 * and allocated 4*nr_possible_cpus(), this must be so.
+	 *
+	 * The single entry is guaranteed by having the lock owner unhash
+	 * before it releases.
+	 */
+	BUG();
+}
+
+static struct pv_node *pv_unhash(struct qspinlock *lock)
+{
+	unsigned long offset, hash = hash_ptr(lock, pv_lock_hash_bits);
+	struct pv_hash_entry *he;
+	struct pv_node *node;
+
+	for_each_hash_entry(he, offset, hash) {
+		if (READ_ONCE(he->lock) == lock) {
+			node = READ_ONCE(he->node);
+			WRITE_ONCE(he->lock, NULL);
+			return node;
+		}
+	}
+	/*
+	 * Hard assume we'll find an entry.
+	 *
+	 * This guarantees a limited lookup time and is itself guaranteed by
+	 * having the lock owner do the unhash -- IFF the unlock sees the
+	 * SLOW flag, there MUST be a hash entry.
+	 */
+	BUG();
+}
+
+/*
+ * Initialize the PV part of the mcs_spinlock node.
+ */
+static void pv_init_node(struct mcs_spinlock *node)
+{
+	struct pv_node *pn = (struct pv_node *)node;
+
+	BUILD_BUG_ON(sizeof(struct pv_node) > 5*sizeof(struct mcs_spinlock));
+
+	pn->cpu = smp_processor_id();
+	pn->state = vcpu_running;
+}
+
+/*
+ * Wait for node->locked to become true, halt the vcpu after a short spin.
+ * pv_kick_node() is used to wake the vcpu again.
+ */
+static void pv_wait_node(struct mcs_spinlock *node)
+{
+	struct pv_node *pn = (struct pv_node *)node;
+	int loop;
+
+	for (;;) {
+		for (loop = SPIN_THRESHOLD; loop; loop--) {
+			if (READ_ONCE(node->locked))
+				return;
+			cpu_relax();
+		}
+
+		/*
+		 * Order pn->state vs pn->locked thusly:
+		 *
+		 * [S] pn->state = vcpu_halted	  [S] next->locked = 1
+		 *     MB			      MB
+		 * [L] pn->locked		[RmW] pn->state = vcpu_running
+		 *
+		 * Matches the xchg() from pv_kick_node().
+		 */
+		smp_store_mb(pn->state, vcpu_halted);
+
+		if (!READ_ONCE(node->locked))
+			pv_wait(&pn->state, vcpu_halted);
+
+		/*
+		 * Reset the vCPU state to avoid unncessary CPU kicking
+		 */
+		WRITE_ONCE(pn->state, vcpu_running);
+
+		/*
+		 * If the locked flag is still not set after wakeup, it is a
+		 * spurious wakeup and the vCPU should wait again. However,
+		 * there is a pretty high overhead for CPU halting and kicking.
+		 * So it is better to spin for a while in the hope that the
+		 * MCS lock will be released soon.
+		 */
+	}
+	/*
+	 * By now our node->locked should be 1 and our caller will not actually
+	 * spin-wait for it. We do however rely on our caller to do a
+	 * load-acquire for us.
+	 */
+}
+
+/*
+ * Called after setting next->locked = 1, used to wake those stuck in
+ * pv_wait_node().
+ */
+static void pv_kick_node(struct mcs_spinlock *node)
+{
+	struct pv_node *pn = (struct pv_node *)node;
+
+	/*
+	 * Note that because node->locked is already set, this actual
+	 * mcs_spinlock entry could be re-used already.
+	 *
+	 * This should be fine however, kicking people for no reason is
+	 * harmless.
+	 *
+	 * See the comment in pv_wait_node().
+	 */
+	if (xchg(&pn->state, vcpu_running) == vcpu_halted)
+		pv_kick(pn->cpu);
+}
+
+/*
+ * Wait for l->locked to become clear; halt the vcpu after a short spin.
+ * __pv_queued_spin_unlock() will wake us.
+ */
+static void pv_wait_head(struct qspinlock *lock, struct mcs_spinlock *node)
+{
+	struct pv_node *pn = (struct pv_node *)node;
+	struct __qspinlock *l = (void *)lock;
+	struct qspinlock **lp = NULL;
+	int loop;
+
+	for (;;) {
+		for (loop = SPIN_THRESHOLD; loop; loop--) {
+			if (!READ_ONCE(l->locked))
+				return;
+			cpu_relax();
+		}
+
+		WRITE_ONCE(pn->state, vcpu_halted);
+		if (!lp) { /* ONCE */
+			lp = pv_hash(lock, pn);
+			/*
+			 * lp must be set before setting _Q_SLOW_VAL
+			 *
+			 * [S] lp = lock                [RmW] l = l->locked = 0
+			 *     MB                             MB
+			 * [S] l->locked = _Q_SLOW_VAL  [L]   lp
+			 *
+			 * Matches the cmpxchg() in __pv_queued_spin_unlock().
+			 */
+			if (!cmpxchg(&l->locked, _Q_LOCKED_VAL, _Q_SLOW_VAL)) {
+				/*
+				 * The lock is free and _Q_SLOW_VAL has never
+				 * been set. Therefore we need to unhash before
+				 * getting the lock.
+				 */
+				WRITE_ONCE(*lp, NULL);
+				return;
+			}
+		}
+		pv_wait(&l->locked, _Q_SLOW_VAL);
+
+		/*
+		 * The unlocker should have freed the lock before kicking the
+		 * CPU. So if the lock is still not free, it is a spurious
+		 * wakeup and so the vCPU should wait again after spinning for
+		 * a while.
+		 */
+	}
+
+	/*
+	 * Lock is unlocked now; the caller will acquire it without waiting.
+	 * As with pv_wait_node() we rely on the caller to do a load-acquire
+	 * for us.
+	 */
+}
+
+/*
+ * PV version of the unlock function to be used in stead of
+ * queued_spin_unlock().
+ */
+__visible void __pv_queued_spin_unlock(struct qspinlock *lock)
+{
+	struct __qspinlock *l = (void *)lock;
+	struct pv_node *node;
+
+	/*
+	 * We must not unlock if SLOW, because in that case we must first
+	 * unhash. Otherwise it would be possible to have multiple @lock
+	 * entries, which would be BAD.
+	 */
+	if (likely(cmpxchg(&l->locked, _Q_LOCKED_VAL, 0) == _Q_LOCKED_VAL))
+		return;
+
+	/*
+	 * Since the above failed to release, this must be the SLOW path.
+	 * Therefore start by looking up the blocked node and unhashing it.
+	 */
+	node = pv_unhash(lock);
+
+	/*
+	 * Now that we have a reference to the (likely) blocked pv_node,
+	 * release the lock.
+	 */
+	smp_store_release(&l->locked, 0);
+
+	/*
+	 * At this point the memory pointed at by lock can be freed/reused,
+	 * however we can still use the pv_node to kick the CPU.
+	 */
+	if (READ_ONCE(node->state) == vcpu_halted)
+		pv_kick(node->cpu);
+}
+/*
+ * Include the architecture specific callee-save thunk of the
+ * __pv_queued_spin_unlock(). This thunk is put together with
+ * __pv_queued_spin_unlock() near the top of the file to make sure
+ * that the callee-save thunk and the real unlock function are close
+ * to each other sharing consecutive instruction cachelines.
+ */
+#include <asm/qspinlock_paravirt.h>
+
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index b025295f4966..36573e96a477 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -70,10 +70,10 @@ static void fixup_rt_mutex_waiters(struct rt_mutex *lock)
 }
 
 /*
- * We can speed up the acquire/release, if the architecture
- * supports cmpxchg and if there's no debugging state to be set up
+ * We can speed up the acquire/release, if there's no debugging state to be
+ * set up.
  */
-#if defined(__HAVE_ARCH_CMPXCHG) && !defined(CONFIG_DEBUG_RT_MUTEXES)
+#ifndef CONFIG_DEBUG_RT_MUTEXES
 # define rt_mutex_cmpxchg(l,c,n)	(cmpxchg(&l->owner, c, n) == c)
 static inline void mark_rt_mutex_waiters(struct rt_mutex *lock)
 {
@@ -1182,11 +1182,8 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
 	set_current_state(state);
 
 	/* Setup the timer, when timeout != NULL */
-	if (unlikely(timeout)) {
+	if (unlikely(timeout))
 		hrtimer_start_expires(&timeout->timer, HRTIMER_MODE_ABS);
-		if (!hrtimer_active(&timeout->timer))
-			timeout->task = NULL;
-	}
 
 	ret = task_blocks_on_rt_mutex(lock, &waiter, current, chwalk);
 
@@ -1443,10 +1440,17 @@ EXPORT_SYMBOL_GPL(rt_mutex_timed_lock);
  *
  * @lock:	the rt_mutex to be locked
  *
+ * This function can only be called in thread context. It's safe to
+ * call it from atomic regions, but not from hard interrupt or soft
+ * interrupt context.
+ *
  * Returns 1 on success and 0 on contention
  */
 int __sched rt_mutex_trylock(struct rt_mutex *lock)
 {
+	if (WARN_ON(in_irq() || in_nmi() || in_serving_softirq()))
+		return 0;
+
 	return rt_mutex_fasttrylock(lock, rt_mutex_slowtrylock);
 }
 EXPORT_SYMBOL_GPL(rt_mutex_trylock);
diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
index 3417d0172a5d..0f189714e457 100644
--- a/kernel/locking/rwsem-xadd.c
+++ b/kernel/locking/rwsem-xadd.c
@@ -409,11 +409,24 @@ done:
 	return taken;
 }
 
+/*
+ * Return true if the rwsem has active spinner
+ */
+static inline bool rwsem_has_spinner(struct rw_semaphore *sem)
+{
+	return osq_is_locked(&sem->osq);
+}
+
 #else
 static bool rwsem_optimistic_spin(struct rw_semaphore *sem)
 {
 	return false;
 }
+
+static inline bool rwsem_has_spinner(struct rw_semaphore *sem)
+{
+	return false;
+}
 #endif
 
 /*
@@ -496,7 +509,38 @@ struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem)
 {
 	unsigned long flags;
 
+	/*
+	 * If a spinner is present, it is not necessary to do the wakeup.
+	 * Try to do wakeup only if the trylock succeeds to minimize
+	 * spinlock contention which may introduce too much delay in the
+	 * unlock operation.
+	 *
+	 *    spinning writer		up_write/up_read caller
+	 *    ---------------		-----------------------
+	 * [S]   osq_unlock()		[L]   osq
+	 *	 MB			      RMB
+	 * [RmW] rwsem_try_write_lock() [RmW] spin_trylock(wait_lock)
+	 *
+	 * Here, it is important to make sure that there won't be a missed
+	 * wakeup while the rwsem is free and the only spinning writer goes
+	 * to sleep without taking the rwsem. Even when the spinning writer
+	 * is just going to break out of the waiting loop, it will still do
+	 * a trylock in rwsem_down_write_failed() before sleeping. IOW, if
+	 * rwsem_has_spinner() is true, it will guarantee at least one
+	 * trylock attempt on the rwsem later on.
+	 */
+	if (rwsem_has_spinner(sem)) {
+		/*
+		 * The smp_rmb() here is to make sure that the spinner
+		 * state is consulted before reading the wait_lock.
+		 */
+		smp_rmb();
+		if (!raw_spin_trylock_irqsave(&sem->wait_lock, flags))
+			return sem;
+		goto locked;
+	}
 	raw_spin_lock_irqsave(&sem->wait_lock, flags);
+locked:
 
 	/* do nothing if list empty */
 	if (!list_empty(&sem->wait_list))
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 8dbe27611ec3..59e32684c23b 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -241,6 +241,7 @@ rcu_torture_free(struct rcu_torture *p)
 struct rcu_torture_ops {
 	int ttype;
 	void (*init)(void);
+	void (*cleanup)(void);
 	int (*readlock)(void);
 	void (*read_delay)(struct torture_random_state *rrsp);
 	void (*readunlock)(int idx);
@@ -477,10 +478,12 @@ static struct rcu_torture_ops rcu_busted_ops = {
  */
 
 DEFINE_STATIC_SRCU(srcu_ctl);
+static struct srcu_struct srcu_ctld;
+static struct srcu_struct *srcu_ctlp = &srcu_ctl;
 
-static int srcu_torture_read_lock(void) __acquires(&srcu_ctl)
+static int srcu_torture_read_lock(void) __acquires(srcu_ctlp)
 {
-	return srcu_read_lock(&srcu_ctl);
+	return srcu_read_lock(srcu_ctlp);
 }
 
 static void srcu_read_delay(struct torture_random_state *rrsp)
@@ -499,49 +502,49 @@ static void srcu_read_delay(struct torture_random_state *rrsp)
 		rcu_read_delay(rrsp);
 }
 
-static void srcu_torture_read_unlock(int idx) __releases(&srcu_ctl)
+static void srcu_torture_read_unlock(int idx) __releases(srcu_ctlp)
 {
-	srcu_read_unlock(&srcu_ctl, idx);
+	srcu_read_unlock(srcu_ctlp, idx);
 }
 
 static unsigned long srcu_torture_completed(void)
 {
-	return srcu_batches_completed(&srcu_ctl);
+	return srcu_batches_completed(srcu_ctlp);
 }
 
 static void srcu_torture_deferred_free(struct rcu_torture *rp)
 {
-	call_srcu(&srcu_ctl, &rp->rtort_rcu, rcu_torture_cb);
+	call_srcu(srcu_ctlp, &rp->rtort_rcu, rcu_torture_cb);
 }
 
 static void srcu_torture_synchronize(void)
 {
-	synchronize_srcu(&srcu_ctl);
+	synchronize_srcu(srcu_ctlp);
 }
 
 static void srcu_torture_call(struct rcu_head *head,
 			      void (*func)(struct rcu_head *head))
 {
-	call_srcu(&srcu_ctl, head, func);
+	call_srcu(srcu_ctlp, head, func);
 }
 
 static void srcu_torture_barrier(void)
 {
-	srcu_barrier(&srcu_ctl);
+	srcu_barrier(srcu_ctlp);
 }
 
 static void srcu_torture_stats(void)
 {
 	int cpu;
-	int idx = srcu_ctl.completed & 0x1;
+	int idx = srcu_ctlp->completed & 0x1;
 
 	pr_alert("%s%s per-CPU(idx=%d):",
 		 torture_type, TORTURE_FLAG, idx);
 	for_each_possible_cpu(cpu) {
 		long c0, c1;
 
-		c0 = (long)per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[!idx];
-		c1 = (long)per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[idx];
+		c0 = (long)per_cpu_ptr(srcu_ctlp->per_cpu_ref, cpu)->c[!idx];
+		c1 = (long)per_cpu_ptr(srcu_ctlp->per_cpu_ref, cpu)->c[idx];
 		pr_cont(" %d(%ld,%ld)", cpu, c0, c1);
 	}
 	pr_cont("\n");
@@ -549,7 +552,7 @@ static void srcu_torture_stats(void)
 
 static void srcu_torture_synchronize_expedited(void)
 {
-	synchronize_srcu_expedited(&srcu_ctl);
+	synchronize_srcu_expedited(srcu_ctlp);
 }
 
 static struct rcu_torture_ops srcu_ops = {
@@ -569,6 +572,38 @@ static struct rcu_torture_ops srcu_ops = {
 	.name		= "srcu"
 };
 
+static void srcu_torture_init(void)
+{
+	rcu_sync_torture_init();
+	WARN_ON(init_srcu_struct(&srcu_ctld));
+	srcu_ctlp = &srcu_ctld;
+}
+
+static void srcu_torture_cleanup(void)
+{
+	cleanup_srcu_struct(&srcu_ctld);
+	srcu_ctlp = &srcu_ctl; /* In case of a later rcutorture run. */
+}
+
+/* As above, but dynamically allocated. */
+static struct rcu_torture_ops srcud_ops = {
+	.ttype		= SRCU_FLAVOR,
+	.init		= srcu_torture_init,
+	.cleanup	= srcu_torture_cleanup,
+	.readlock	= srcu_torture_read_lock,
+	.read_delay	= srcu_read_delay,
+	.readunlock	= srcu_torture_read_unlock,
+	.started	= NULL,
+	.completed	= srcu_torture_completed,
+	.deferred_free	= srcu_torture_deferred_free,
+	.sync		= srcu_torture_synchronize,
+	.exp_sync	= srcu_torture_synchronize_expedited,
+	.call		= srcu_torture_call,
+	.cb_barrier	= srcu_torture_barrier,
+	.stats		= srcu_torture_stats,
+	.name		= "srcud"
+};
+
 /*
  * Definitions for sched torture testing.
  */
@@ -672,8 +707,8 @@ static void rcu_torture_boost_cb(struct rcu_head *head)
 	struct rcu_boost_inflight *rbip =
 		container_of(head, struct rcu_boost_inflight, rcu);
 
-	smp_mb(); /* Ensure RCU-core accesses precede clearing ->inflight */
-	rbip->inflight = 0;
+	/* Ensure RCU-core accesses precede clearing ->inflight */
+	smp_store_release(&rbip->inflight, 0);
 }
 
 static int rcu_torture_boost(void *arg)
@@ -710,9 +745,9 @@ static int rcu_torture_boost(void *arg)
 		call_rcu_time = jiffies;
 		while (ULONG_CMP_LT(jiffies, endtime)) {
 			/* If we don't have a callback in flight, post one. */
-			if (!rbi.inflight) {
-				smp_mb(); /* RCU core before ->inflight = 1. */
-				rbi.inflight = 1;
+			if (!smp_load_acquire(&rbi.inflight)) {
+				/* RCU core before ->inflight = 1. */
+				smp_store_release(&rbi.inflight, 1);
 				call_rcu(&rbi.rcu, rcu_torture_boost_cb);
 				if (jiffies - call_rcu_time >
 					 test_boost_duration * HZ - HZ / 2) {
@@ -751,11 +786,10 @@ checkwait:	stutter_wait("rcu_torture_boost");
 	} while (!torture_must_stop());
 
 	/* Clean up and exit. */
-	while (!kthread_should_stop() || rbi.inflight) {
+	while (!kthread_should_stop() || smp_load_acquire(&rbi.inflight)) {
 		torture_shutdown_absorb("rcu_torture_boost");
 		schedule_timeout_uninterruptible(1);
 	}
-	smp_mb(); /* order accesses to ->inflight before stack-frame death. */
 	destroy_rcu_head_on_stack(&rbi.rcu);
 	torture_kthread_stopping("rcu_torture_boost");
 	return 0;
@@ -1054,7 +1088,7 @@ static void rcu_torture_timer(unsigned long unused)
 	p = rcu_dereference_check(rcu_torture_current,
 				  rcu_read_lock_bh_held() ||
 				  rcu_read_lock_sched_held() ||
-				  srcu_read_lock_held(&srcu_ctl));
+				  srcu_read_lock_held(srcu_ctlp));
 	if (p == NULL) {
 		/* Leave because rcu_torture_writer is not yet underway */
 		cur_ops->readunlock(idx);
@@ -1128,7 +1162,7 @@ rcu_torture_reader(void *arg)
 		p = rcu_dereference_check(rcu_torture_current,
 					  rcu_read_lock_bh_held() ||
 					  rcu_read_lock_sched_held() ||
-					  srcu_read_lock_held(&srcu_ctl));
+					  srcu_read_lock_held(srcu_ctlp));
 		if (p == NULL) {
 			/* Wait for rcu_torture_writer to get underway */
 			cur_ops->readunlock(idx);
@@ -1413,12 +1447,15 @@ static int rcu_torture_barrier_cbs(void *arg)
 	do {
 		wait_event(barrier_cbs_wq[myid],
 			   (newphase =
-			    ACCESS_ONCE(barrier_phase)) != lastphase ||
+			    smp_load_acquire(&barrier_phase)) != lastphase ||
 			   torture_must_stop());
 		lastphase = newphase;
-		smp_mb(); /* ensure barrier_phase load before ->call(). */
 		if (torture_must_stop())
 			break;
+		/*
+		 * The above smp_load_acquire() ensures barrier_phase load
+		 * is ordered before the folloiwng ->call().
+		 */
 		cur_ops->call(&rcu, rcu_torture_barrier_cbf);
 		if (atomic_dec_and_test(&barrier_cbs_count))
 			wake_up(&barrier_wq);
@@ -1439,8 +1476,8 @@ static int rcu_torture_barrier(void *arg)
 	do {
 		atomic_set(&barrier_cbs_invoked, 0);
 		atomic_set(&barrier_cbs_count, n_barrier_cbs);
-		smp_mb(); /* Ensure barrier_phase after prior assignments. */
-		barrier_phase = !barrier_phase;
+		/* Ensure barrier_phase ordered after prior assignments. */
+		smp_store_release(&barrier_phase, !barrier_phase);
 		for (i = 0; i < n_barrier_cbs; i++)
 			wake_up(&barrier_cbs_wq[i]);
 		wait_event(barrier_wq,
@@ -1588,10 +1625,14 @@ rcu_torture_cleanup(void)
 			rcutorture_booster_cleanup(i);
 	}
 
-	/* Wait for all RCU callbacks to fire.  */
-
+	/*
+	 * Wait for all RCU callbacks to fire, then do flavor-specific
+	 * cleanup operations.
+	 */
 	if (cur_ops->cb_barrier != NULL)
 		cur_ops->cb_barrier();
+	if (cur_ops->cleanup != NULL)
+		cur_ops->cleanup();
 
 	rcu_torture_stats_print();  /* -After- the stats thread is stopped! */
 
@@ -1668,8 +1709,8 @@ rcu_torture_init(void)
 	int cpu;
 	int firsterr = 0;
 	static struct rcu_torture_ops *torture_ops[] = {
-		&rcu_ops, &rcu_bh_ops, &rcu_busted_ops, &srcu_ops, &sched_ops,
-		RCUTORTURE_TASKS_OPS
+		&rcu_ops, &rcu_bh_ops, &rcu_busted_ops, &srcu_ops, &srcud_ops,
+		&sched_ops, RCUTORTURE_TASKS_OPS
 	};
 
 	if (!torture_init_begin(torture_type, verbose, &torture_runnable))
@@ -1701,7 +1742,7 @@ rcu_torture_init(void)
 	if (nreaders >= 0) {
 		nrealreaders = nreaders;
 	} else {
-		nrealreaders = num_online_cpus() - 1;
+		nrealreaders = num_online_cpus() - 2 - nreaders;
 		if (nrealreaders <= 0)
 			nrealreaders = 1;
 	}
diff --git a/kernel/rcu/srcu.c b/kernel/rcu/srcu.c
index cad76e76b4e7..fb33d35ee0b7 100644
--- a/kernel/rcu/srcu.c
+++ b/kernel/rcu/srcu.c
@@ -151,7 +151,7 @@ static unsigned long srcu_readers_seq_idx(struct srcu_struct *sp, int idx)
 	unsigned long t;
 
 	for_each_possible_cpu(cpu) {
-		t = ACCESS_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->seq[idx]);
+		t = READ_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->seq[idx]);
 		sum += t;
 	}
 	return sum;
@@ -168,7 +168,7 @@ static unsigned long srcu_readers_active_idx(struct srcu_struct *sp, int idx)
 	unsigned long t;
 
 	for_each_possible_cpu(cpu) {
-		t = ACCESS_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[idx]);
+		t = READ_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[idx]);
 		sum += t;
 	}
 	return sum;
@@ -265,8 +265,8 @@ static int srcu_readers_active(struct srcu_struct *sp)
 	unsigned long sum = 0;
 
 	for_each_possible_cpu(cpu) {
-		sum += ACCESS_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[0]);
-		sum += ACCESS_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[1]);
+		sum += READ_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[0]);
+		sum += READ_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[1]);
 	}
 	return sum;
 }
@@ -296,7 +296,7 @@ int __srcu_read_lock(struct srcu_struct *sp)
 {
 	int idx;
 
-	idx = ACCESS_ONCE(sp->completed) & 0x1;
+	idx = READ_ONCE(sp->completed) & 0x1;
 	preempt_disable();
 	__this_cpu_inc(sp->per_cpu_ref->c[idx]);
 	smp_mb(); /* B */  /* Avoid leaking the critical section. */
diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c
index 069742d61c68..591af0cb7b9f 100644
--- a/kernel/rcu/tiny.c
+++ b/kernel/rcu/tiny.c
@@ -49,39 +49,6 @@ static void __call_rcu(struct rcu_head *head,
 
 #include "tiny_plugin.h"
 
-/*
- * Enter idle, which is an extended quiescent state if we have fully
- * entered that mode.
- */
-void rcu_idle_enter(void)
-{
-}
-EXPORT_SYMBOL_GPL(rcu_idle_enter);
-
-/*
- * Exit an interrupt handler towards idle.
- */
-void rcu_irq_exit(void)
-{
-}
-EXPORT_SYMBOL_GPL(rcu_irq_exit);
-
-/*
- * Exit idle, so that we are no longer in an extended quiescent state.
- */
-void rcu_idle_exit(void)
-{
-}
-EXPORT_SYMBOL_GPL(rcu_idle_exit);
-
-/*
- * Enter an interrupt handler, moving away from idle.
- */
-void rcu_irq_enter(void)
-{
-}
-EXPORT_SYMBOL_GPL(rcu_irq_enter);
-
 #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE)
 
 /*
@@ -170,6 +137,11 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
 
 	/* Move the ready-to-invoke callbacks to a local list. */
 	local_irq_save(flags);
+	if (rcp->donetail == &rcp->rcucblist) {
+		/* No callbacks ready, so just leave. */
+		local_irq_restore(flags);
+		return;
+	}
 	RCU_TRACE(trace_rcu_batch_start(rcp->name, 0, rcp->qlen, -1));
 	list = rcp->rcucblist;
 	rcp->rcucblist = *rcp->donetail;
diff --git a/kernel/rcu/tiny_plugin.h b/kernel/rcu/tiny_plugin.h
index f94e209a10d6..e492a5253e0f 100644
--- a/kernel/rcu/tiny_plugin.h
+++ b/kernel/rcu/tiny_plugin.h
@@ -144,16 +144,17 @@ static void check_cpu_stall(struct rcu_ctrlblk *rcp)
 		return;
 	rcp->ticks_this_gp++;
 	j = jiffies;
-	js = ACCESS_ONCE(rcp->jiffies_stall);
+	js = READ_ONCE(rcp->jiffies_stall);
 	if (rcp->rcucblist && ULONG_CMP_GE(j, js)) {
 		pr_err("INFO: %s stall on CPU (%lu ticks this GP) idle=%llx (t=%lu jiffies q=%ld)\n",
 		       rcp->name, rcp->ticks_this_gp, DYNTICK_TASK_EXIT_IDLE,
 		       jiffies - rcp->gp_start, rcp->qlen);
 		dump_stack();
-		ACCESS_ONCE(rcp->jiffies_stall) = jiffies +
-			3 * rcu_jiffies_till_stall_check() + 3;
+		WRITE_ONCE(rcp->jiffies_stall,
+			   jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
 	} else if (ULONG_CMP_GE(j, js)) {
-		ACCESS_ONCE(rcp->jiffies_stall) = jiffies + rcu_jiffies_till_stall_check();
+		WRITE_ONCE(rcp->jiffies_stall,
+			   jiffies + rcu_jiffies_till_stall_check());
 	}
 }
 
@@ -161,7 +162,8 @@ static void reset_cpu_stall_ticks(struct rcu_ctrlblk *rcp)
 {
 	rcp->ticks_this_gp = 0;
 	rcp->gp_start = jiffies;
-	ACCESS_ONCE(rcp->jiffies_stall) = jiffies + rcu_jiffies_till_stall_check();
+	WRITE_ONCE(rcp->jiffies_stall,
+		   jiffies + rcu_jiffies_till_stall_check());
 }
 
 static void check_cpu_stalls(void)
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 8cf7304b2867..add042926a66 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -91,7 +91,7 @@ static const char *tp_##sname##_varname __used __tracepoint_string = sname##_var
 
 #define RCU_STATE_INITIALIZER(sname, sabbr, cr) \
 DEFINE_RCU_TPS(sname) \
-DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_data, sname##_data); \
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_data, sname##_data); \
 struct rcu_state sname##_state = { \
 	.level = { &sname##_state.node[0] }, \
 	.rda = &sname##_data, \
@@ -110,11 +110,18 @@ struct rcu_state sname##_state = { \
 RCU_STATE_INITIALIZER(rcu_sched, 's', call_rcu_sched);
 RCU_STATE_INITIALIZER(rcu_bh, 'b', call_rcu_bh);
 
-static struct rcu_state *rcu_state_p;
+static struct rcu_state *const rcu_state_p;
+static struct rcu_data __percpu *const rcu_data_p;
 LIST_HEAD(rcu_struct_flavors);
 
-/* Increase (but not decrease) the CONFIG_RCU_FANOUT_LEAF at boot time. */
-static int rcu_fanout_leaf = CONFIG_RCU_FANOUT_LEAF;
+/* Dump rcu_node combining tree at boot to verify correct setup. */
+static bool dump_tree;
+module_param(dump_tree, bool, 0444);
+/* Control rcu_node-tree auto-balancing at boot time. */
+static bool rcu_fanout_exact;
+module_param(rcu_fanout_exact, bool, 0444);
+/* Increase (but not decrease) the RCU_FANOUT_LEAF at boot time. */
+static int rcu_fanout_leaf = RCU_FANOUT_LEAF;
 module_param(rcu_fanout_leaf, int, 0444);
 int rcu_num_lvls __read_mostly = RCU_NUM_LVLS;
 static int num_rcu_lvl[] = {  /* Number of rcu_nodes at specified level. */
@@ -159,17 +166,46 @@ static void invoke_rcu_core(void);
 static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp);
 
 /* rcuc/rcub kthread realtime priority */
+#ifdef CONFIG_RCU_KTHREAD_PRIO
 static int kthread_prio = CONFIG_RCU_KTHREAD_PRIO;
+#else /* #ifdef CONFIG_RCU_KTHREAD_PRIO */
+static int kthread_prio = IS_ENABLED(CONFIG_RCU_BOOST) ? 1 : 0;
+#endif /* #else #ifdef CONFIG_RCU_KTHREAD_PRIO */
 module_param(kthread_prio, int, 0644);
 
 /* Delay in jiffies for grace-period initialization delays, debug only. */
+
+#ifdef CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT
+static int gp_preinit_delay = CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT_DELAY;
+module_param(gp_preinit_delay, int, 0644);
+#else /* #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT */
+static const int gp_preinit_delay;
+#endif /* #else #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT */
+
 #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_INIT
 static int gp_init_delay = CONFIG_RCU_TORTURE_TEST_SLOW_INIT_DELAY;
 module_param(gp_init_delay, int, 0644);
 #else /* #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_INIT */
 static const int gp_init_delay;
 #endif /* #else #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_INIT */
-#define PER_RCU_NODE_PERIOD 10	/* Number of grace periods between delays. */
+
+#ifdef CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP
+static int gp_cleanup_delay = CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP_DELAY;
+module_param(gp_cleanup_delay, int, 0644);
+#else /* #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP */
+static const int gp_cleanup_delay;
+#endif /* #else #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP */
+
+/*
+ * Number of grace periods between delays, normalized by the duration of
+ * the delay.  The longer the the delay, the more the grace periods between
+ * each delay.  The reason for this normalization is that it means that,
+ * for non-zero delays, the overall slowdown of grace periods is constant
+ * regardless of the duration of the delay.  This arrangement balances
+ * the need for long delays to increase some race probabilities with the
+ * need for fast grace periods to increase other race probabilities.
+ */
+#define PER_RCU_NODE_PERIOD 3	/* Number of grace periods between delays. */
 
 /*
  * Track the rcutorture test sequence number and the update version
@@ -191,17 +227,17 @@ unsigned long rcutorture_vernum;
  */
 unsigned long rcu_rnp_online_cpus(struct rcu_node *rnp)
 {
-	return ACCESS_ONCE(rnp->qsmaskinitnext);
+	return READ_ONCE(rnp->qsmaskinitnext);
 }
 
 /*
- * Return true if an RCU grace period is in progress.  The ACCESS_ONCE()s
+ * Return true if an RCU grace period is in progress.  The READ_ONCE()s
  * permit this function to be invoked without holding the root rcu_node
  * structure's ->lock, but of course results can be subject to change.
  */
 static int rcu_gp_in_progress(struct rcu_state *rsp)
 {
-	return ACCESS_ONCE(rsp->completed) != ACCESS_ONCE(rsp->gpnum);
+	return READ_ONCE(rsp->completed) != READ_ONCE(rsp->gpnum);
 }
 
 /*
@@ -278,8 +314,8 @@ static void rcu_momentary_dyntick_idle(void)
 		if (!(resched_mask & rsp->flavor_mask))
 			continue;
 		smp_mb(); /* rcu_sched_qs_mask before cond_resched_completed. */
-		if (ACCESS_ONCE(rdp->mynode->completed) !=
-		    ACCESS_ONCE(rdp->cond_resched_completed))
+		if (READ_ONCE(rdp->mynode->completed) !=
+		    READ_ONCE(rdp->cond_resched_completed))
 			continue;
 
 		/*
@@ -491,9 +527,9 @@ void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
 		break;
 	}
 	if (rsp != NULL) {
-		*flags = ACCESS_ONCE(rsp->gp_flags);
-		*gpnum = ACCESS_ONCE(rsp->gpnum);
-		*completed = ACCESS_ONCE(rsp->completed);
+		*flags = READ_ONCE(rsp->gp_flags);
+		*gpnum = READ_ONCE(rsp->gpnum);
+		*completed = READ_ONCE(rsp->completed);
 		return;
 	}
 	*flags = 0;
@@ -539,10 +575,10 @@ static struct rcu_node *rcu_get_root(struct rcu_state *rsp)
 static int rcu_future_needs_gp(struct rcu_state *rsp)
 {
 	struct rcu_node *rnp = rcu_get_root(rsp);
-	int idx = (ACCESS_ONCE(rnp->completed) + 1) & 0x1;
+	int idx = (READ_ONCE(rnp->completed) + 1) & 0x1;
 	int *fp = &rnp->need_future_gp[idx];
 
-	return ACCESS_ONCE(*fp);
+	return READ_ONCE(*fp);
 }
 
 /*
@@ -565,7 +601,7 @@ cpu_needs_another_gp(struct rcu_state *rsp, struct rcu_data *rdp)
 		return 1;  /* Yes, this CPU has newly registered callbacks. */
 	for (i = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++)
 		if (rdp->nxttail[i - 1] != rdp->nxttail[i] &&
-		    ULONG_CMP_LT(ACCESS_ONCE(rsp->completed),
+		    ULONG_CMP_LT(READ_ONCE(rsp->completed),
 				 rdp->nxtcompleted[i]))
 			return 1;  /* Yes, CBs for future grace period. */
 	return 0; /* No grace period needed. */
@@ -585,7 +621,8 @@ static void rcu_eqs_enter_common(long long oldval, bool user)
 	struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
 
 	trace_rcu_dyntick(TPS("Start"), oldval, rdtp->dynticks_nesting);
-	if (!user && !is_idle_task(current)) {
+	if (IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
+	    !user && !is_idle_task(current)) {
 		struct task_struct *idle __maybe_unused =
 			idle_task(smp_processor_id());
 
@@ -604,7 +641,8 @@ static void rcu_eqs_enter_common(long long oldval, bool user)
 	smp_mb__before_atomic();  /* See above. */
 	atomic_inc(&rdtp->dynticks);
 	smp_mb__after_atomic();  /* Force ordering with next sojourn. */
-	WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1);
+	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
+		     atomic_read(&rdtp->dynticks) & 0x1);
 	rcu_dynticks_task_enter();
 
 	/*
@@ -630,7 +668,8 @@ static void rcu_eqs_enter(bool user)
 
 	rdtp = this_cpu_ptr(&rcu_dynticks);
 	oldval = rdtp->dynticks_nesting;
-	WARN_ON_ONCE((oldval & DYNTICK_TASK_NEST_MASK) == 0);
+	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
+		     (oldval & DYNTICK_TASK_NEST_MASK) == 0);
 	if ((oldval & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE) {
 		rdtp->dynticks_nesting = 0;
 		rcu_eqs_enter_common(oldval, user);
@@ -703,7 +742,8 @@ void rcu_irq_exit(void)
 	rdtp = this_cpu_ptr(&rcu_dynticks);
 	oldval = rdtp->dynticks_nesting;
 	rdtp->dynticks_nesting--;
-	WARN_ON_ONCE(rdtp->dynticks_nesting < 0);
+	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
+		     rdtp->dynticks_nesting < 0);
 	if (rdtp->dynticks_nesting)
 		trace_rcu_dyntick(TPS("--="), oldval, rdtp->dynticks_nesting);
 	else
@@ -728,10 +768,12 @@ static void rcu_eqs_exit_common(long long oldval, int user)
 	atomic_inc(&rdtp->dynticks);
 	/* CPUs seeing atomic_inc() must see later RCU read-side crit sects */
 	smp_mb__after_atomic();  /* See above. */
-	WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1));
+	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
+		     !(atomic_read(&rdtp->dynticks) & 0x1));
 	rcu_cleanup_after_idle();
 	trace_rcu_dyntick(TPS("End"), oldval, rdtp->dynticks_nesting);
-	if (!user && !is_idle_task(current)) {
+	if (IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
+	    !user && !is_idle_task(current)) {
 		struct task_struct *idle __maybe_unused =
 			idle_task(smp_processor_id());
 
@@ -755,7 +797,7 @@ static void rcu_eqs_exit(bool user)
 
 	rdtp = this_cpu_ptr(&rcu_dynticks);
 	oldval = rdtp->dynticks_nesting;
-	WARN_ON_ONCE(oldval < 0);
+	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && oldval < 0);
 	if (oldval & DYNTICK_TASK_NEST_MASK) {
 		rdtp->dynticks_nesting += DYNTICK_TASK_NEST_VALUE;
 	} else {
@@ -828,7 +870,8 @@ void rcu_irq_enter(void)
 	rdtp = this_cpu_ptr(&rcu_dynticks);
 	oldval = rdtp->dynticks_nesting;
 	rdtp->dynticks_nesting++;
-	WARN_ON_ONCE(rdtp->dynticks_nesting == 0);
+	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
+		     rdtp->dynticks_nesting == 0);
 	if (oldval)
 		trace_rcu_dyntick(TPS("++="), oldval, rdtp->dynticks_nesting);
 	else
@@ -1011,9 +1054,9 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp,
 		trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti"));
 		return 1;
 	} else {
-		if (ULONG_CMP_LT(ACCESS_ONCE(rdp->gpnum) + ULONG_MAX / 4,
+		if (ULONG_CMP_LT(READ_ONCE(rdp->gpnum) + ULONG_MAX / 4,
 				 rdp->mynode->gpnum))
-			ACCESS_ONCE(rdp->gpwrap) = true;
+			WRITE_ONCE(rdp->gpwrap, true);
 		return 0;
 	}
 }
@@ -1093,12 +1136,12 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp,
 	if (ULONG_CMP_GE(jiffies,
 			 rdp->rsp->gp_start + jiffies_till_sched_qs) ||
 	    ULONG_CMP_GE(jiffies, rdp->rsp->jiffies_resched)) {
-		if (!(ACCESS_ONCE(*rcrmp) & rdp->rsp->flavor_mask)) {
-			ACCESS_ONCE(rdp->cond_resched_completed) =
-				ACCESS_ONCE(rdp->mynode->completed);
+		if (!(READ_ONCE(*rcrmp) & rdp->rsp->flavor_mask)) {
+			WRITE_ONCE(rdp->cond_resched_completed,
+				   READ_ONCE(rdp->mynode->completed));
 			smp_mb(); /* ->cond_resched_completed before *rcrmp. */
-			ACCESS_ONCE(*rcrmp) =
-				ACCESS_ONCE(*rcrmp) + rdp->rsp->flavor_mask;
+			WRITE_ONCE(*rcrmp,
+				   READ_ONCE(*rcrmp) + rdp->rsp->flavor_mask);
 			resched_cpu(rdp->cpu);  /* Force CPU into scheduler. */
 			rdp->rsp->jiffies_resched += 5; /* Enable beating. */
 		} else if (ULONG_CMP_GE(jiffies, rdp->rsp->jiffies_resched)) {
@@ -1119,9 +1162,9 @@ static void record_gp_stall_check_time(struct rcu_state *rsp)
 	rsp->gp_start = j;
 	smp_wmb(); /* Record start time before stall time. */
 	j1 = rcu_jiffies_till_stall_check();
-	ACCESS_ONCE(rsp->jiffies_stall) = j + j1;
+	WRITE_ONCE(rsp->jiffies_stall, j + j1);
 	rsp->jiffies_resched = j + j1 / 2;
-	rsp->n_force_qs_gpstart = ACCESS_ONCE(rsp->n_force_qs);
+	rsp->n_force_qs_gpstart = READ_ONCE(rsp->n_force_qs);
 }
 
 /*
@@ -1133,10 +1176,11 @@ static void rcu_check_gp_kthread_starvation(struct rcu_state *rsp)
 	unsigned long j;
 
 	j = jiffies;
-	gpa = ACCESS_ONCE(rsp->gp_activity);
+	gpa = READ_ONCE(rsp->gp_activity);
 	if (j - gpa > 2 * HZ)
-		pr_err("%s kthread starved for %ld jiffies!\n",
-		       rsp->name, j - gpa);
+		pr_err("%s kthread starved for %ld jiffies! g%lu c%lu f%#x\n",
+		       rsp->name, j - gpa,
+		       rsp->gpnum, rsp->completed, rsp->gp_flags);
 }
 
 /*
@@ -1173,12 +1217,13 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum)
 	/* Only let one CPU complain about others per time interval. */
 
 	raw_spin_lock_irqsave(&rnp->lock, flags);
-	delta = jiffies - ACCESS_ONCE(rsp->jiffies_stall);
+	delta = jiffies - READ_ONCE(rsp->jiffies_stall);
 	if (delta < RCU_STALL_RAT_DELAY || !rcu_gp_in_progress(rsp)) {
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 		return;
 	}
-	ACCESS_ONCE(rsp->jiffies_stall) = jiffies + 3 * rcu_jiffies_till_stall_check() + 3;
+	WRITE_ONCE(rsp->jiffies_stall,
+		   jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 
 	/*
@@ -1212,12 +1257,12 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum)
 	if (ndetected) {
 		rcu_dump_cpu_stacks(rsp);
 	} else {
-		if (ACCESS_ONCE(rsp->gpnum) != gpnum ||
-		    ACCESS_ONCE(rsp->completed) == gpnum) {
+		if (READ_ONCE(rsp->gpnum) != gpnum ||
+		    READ_ONCE(rsp->completed) == gpnum) {
 			pr_err("INFO: Stall ended before state dump start\n");
 		} else {
 			j = jiffies;
-			gpa = ACCESS_ONCE(rsp->gp_activity);
+			gpa = READ_ONCE(rsp->gp_activity);
 			pr_err("All QSes seen, last %s kthread activity %ld (%ld-%ld), jiffies_till_next_fqs=%ld, root ->qsmask %#lx\n",
 			       rsp->name, j - gpa, j, gpa,
 			       jiffies_till_next_fqs,
@@ -1262,9 +1307,9 @@ static void print_cpu_stall(struct rcu_state *rsp)
 	rcu_dump_cpu_stacks(rsp);
 
 	raw_spin_lock_irqsave(&rnp->lock, flags);
-	if (ULONG_CMP_GE(jiffies, ACCESS_ONCE(rsp->jiffies_stall)))
-		ACCESS_ONCE(rsp->jiffies_stall) = jiffies +
-				     3 * rcu_jiffies_till_stall_check() + 3;
+	if (ULONG_CMP_GE(jiffies, READ_ONCE(rsp->jiffies_stall)))
+		WRITE_ONCE(rsp->jiffies_stall,
+			   jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 
 	/*
@@ -1307,20 +1352,20 @@ static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
 	 * Given this check, comparisons of jiffies, rsp->jiffies_stall,
 	 * and rsp->gp_start suffice to forestall false positives.
 	 */
-	gpnum = ACCESS_ONCE(rsp->gpnum);
+	gpnum = READ_ONCE(rsp->gpnum);
 	smp_rmb(); /* Pick up ->gpnum first... */
-	js = ACCESS_ONCE(rsp->jiffies_stall);
+	js = READ_ONCE(rsp->jiffies_stall);
 	smp_rmb(); /* ...then ->jiffies_stall before the rest... */
-	gps = ACCESS_ONCE(rsp->gp_start);
+	gps = READ_ONCE(rsp->gp_start);
 	smp_rmb(); /* ...and finally ->gp_start before ->completed. */
-	completed = ACCESS_ONCE(rsp->completed);
+	completed = READ_ONCE(rsp->completed);
 	if (ULONG_CMP_GE(completed, gpnum) ||
 	    ULONG_CMP_LT(j, js) ||
 	    ULONG_CMP_GE(gps, js))
 		return; /* No stall or GP completed since entering function. */
 	rnp = rdp->mynode;
 	if (rcu_gp_in_progress(rsp) &&
-	    (ACCESS_ONCE(rnp->qsmask) & rdp->grpmask)) {
+	    (READ_ONCE(rnp->qsmask) & rdp->grpmask)) {
 
 		/* We haven't checked in, so go dump stack. */
 		print_cpu_stall(rsp);
@@ -1347,7 +1392,7 @@ void rcu_cpu_stall_reset(void)
 	struct rcu_state *rsp;
 
 	for_each_rcu_flavor(rsp)
-		ACCESS_ONCE(rsp->jiffies_stall) = jiffies + ULONG_MAX / 2;
+		WRITE_ONCE(rsp->jiffies_stall, jiffies + ULONG_MAX / 2);
 }
 
 /*
@@ -1457,7 +1502,7 @@ rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp,
 	 * doing some extra useless work.
 	 */
 	if (rnp->gpnum != rnp->completed ||
-	    ACCESS_ONCE(rnp_root->gpnum) != ACCESS_ONCE(rnp_root->completed)) {
+	    READ_ONCE(rnp_root->gpnum) != READ_ONCE(rnp_root->completed)) {
 		rnp->need_future_gp[c & 0x1]++;
 		trace_rcu_future_gp(rnp, rdp, c, TPS("Startedleaf"));
 		goto out;
@@ -1542,7 +1587,7 @@ static int rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp)
 static void rcu_gp_kthread_wake(struct rcu_state *rsp)
 {
 	if (current == rsp->gp_kthread ||
-	    !ACCESS_ONCE(rsp->gp_flags) ||
+	    !READ_ONCE(rsp->gp_flags) ||
 	    !rsp->gp_kthread)
 		return;
 	wake_up(&rsp->gp_wq);
@@ -1677,7 +1722,7 @@ static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp,
 
 	/* Handle the ends of any preceding grace periods first. */
 	if (rdp->completed == rnp->completed &&
-	    !unlikely(ACCESS_ONCE(rdp->gpwrap))) {
+	    !unlikely(READ_ONCE(rdp->gpwrap))) {
 
 		/* No grace period end, so just accelerate recent callbacks. */
 		ret = rcu_accelerate_cbs(rsp, rnp, rdp);
@@ -1692,7 +1737,7 @@ static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp,
 		trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuend"));
 	}
 
-	if (rdp->gpnum != rnp->gpnum || unlikely(ACCESS_ONCE(rdp->gpwrap))) {
+	if (rdp->gpnum != rnp->gpnum || unlikely(READ_ONCE(rdp->gpwrap))) {
 		/*
 		 * If the current grace period is waiting for this CPU,
 		 * set up to detect a quiescent state, otherwise don't
@@ -1704,7 +1749,7 @@ static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp,
 		rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr);
 		rdp->qs_pending = !!(rnp->qsmask & rdp->grpmask);
 		zero_cpu_stall_ticks(rdp);
-		ACCESS_ONCE(rdp->gpwrap) = false;
+		WRITE_ONCE(rdp->gpwrap, false);
 	}
 	return ret;
 }
@@ -1717,9 +1762,9 @@ static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp)
 
 	local_irq_save(flags);
 	rnp = rdp->mynode;
-	if ((rdp->gpnum == ACCESS_ONCE(rnp->gpnum) &&
-	     rdp->completed == ACCESS_ONCE(rnp->completed) &&
-	     !unlikely(ACCESS_ONCE(rdp->gpwrap))) || /* w/out lock. */
+	if ((rdp->gpnum == READ_ONCE(rnp->gpnum) &&
+	     rdp->completed == READ_ONCE(rnp->completed) &&
+	     !unlikely(READ_ONCE(rdp->gpwrap))) || /* w/out lock. */
 	    !raw_spin_trylock(&rnp->lock)) { /* irqs already off, so later. */
 		local_irq_restore(flags);
 		return;
@@ -1731,6 +1776,13 @@ static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp)
 		rcu_gp_kthread_wake(rsp);
 }
 
+static void rcu_gp_slow(struct rcu_state *rsp, int delay)
+{
+	if (delay > 0 &&
+	    !(rsp->gpnum % (rcu_num_nodes * PER_RCU_NODE_PERIOD * delay)))
+		schedule_timeout_uninterruptible(delay);
+}
+
 /*
  * Initialize a new grace period.  Return 0 if no grace period required.
  */
@@ -1740,15 +1792,15 @@ static int rcu_gp_init(struct rcu_state *rsp)
 	struct rcu_data *rdp;
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
-	ACCESS_ONCE(rsp->gp_activity) = jiffies;
+	WRITE_ONCE(rsp->gp_activity, jiffies);
 	raw_spin_lock_irq(&rnp->lock);
 	smp_mb__after_unlock_lock();
-	if (!ACCESS_ONCE(rsp->gp_flags)) {
+	if (!READ_ONCE(rsp->gp_flags)) {
 		/* Spurious wakeup, tell caller to go back to sleep.  */
 		raw_spin_unlock_irq(&rnp->lock);
 		return 0;
 	}
-	ACCESS_ONCE(rsp->gp_flags) = 0; /* Clear all flags: New grace period. */
+	WRITE_ONCE(rsp->gp_flags, 0); /* Clear all flags: New grace period. */
 
 	if (WARN_ON_ONCE(rcu_gp_in_progress(rsp))) {
 		/*
@@ -1773,6 +1825,7 @@ static int rcu_gp_init(struct rcu_state *rsp)
 	 * will handle subsequent offline CPUs.
 	 */
 	rcu_for_each_leaf_node(rsp, rnp) {
+		rcu_gp_slow(rsp, gp_preinit_delay);
 		raw_spin_lock_irq(&rnp->lock);
 		smp_mb__after_unlock_lock();
 		if (rnp->qsmaskinit == rnp->qsmaskinitnext &&
@@ -1829,14 +1882,15 @@ static int rcu_gp_init(struct rcu_state *rsp)
 	 * process finishes, because this kthread handles both.
 	 */
 	rcu_for_each_node_breadth_first(rsp, rnp) {
+		rcu_gp_slow(rsp, gp_init_delay);
 		raw_spin_lock_irq(&rnp->lock);
 		smp_mb__after_unlock_lock();
 		rdp = this_cpu_ptr(rsp->rda);
 		rcu_preempt_check_blocked_tasks(rnp);
 		rnp->qsmask = rnp->qsmaskinit;
-		ACCESS_ONCE(rnp->gpnum) = rsp->gpnum;
+		WRITE_ONCE(rnp->gpnum, rsp->gpnum);
 		if (WARN_ON_ONCE(rnp->completed != rsp->completed))
-			ACCESS_ONCE(rnp->completed) = rsp->completed;
+			WRITE_ONCE(rnp->completed, rsp->completed);
 		if (rnp == rdp->mynode)
 			(void)__note_gp_changes(rsp, rnp, rdp);
 		rcu_preempt_boost_start_gp(rnp);
@@ -1845,10 +1899,7 @@ static int rcu_gp_init(struct rcu_state *rsp)
 					    rnp->grphi, rnp->qsmask);
 		raw_spin_unlock_irq(&rnp->lock);
 		cond_resched_rcu_qs();
-		ACCESS_ONCE(rsp->gp_activity) = jiffies;
-		if (gp_init_delay > 0 &&
-		    !(rsp->gpnum % (rcu_num_nodes * PER_RCU_NODE_PERIOD)))
-			schedule_timeout_uninterruptible(gp_init_delay);
+		WRITE_ONCE(rsp->gp_activity, jiffies);
 	}
 
 	return 1;
@@ -1864,7 +1915,7 @@ static int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in)
 	unsigned long maxj;
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
-	ACCESS_ONCE(rsp->gp_activity) = jiffies;
+	WRITE_ONCE(rsp->gp_activity, jiffies);
 	rsp->n_force_qs++;
 	if (fqs_state == RCU_SAVE_DYNTICK) {
 		/* Collect dyntick-idle snapshots. */
@@ -1882,11 +1933,11 @@ static int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in)
 		force_qs_rnp(rsp, rcu_implicit_dynticks_qs, &isidle, &maxj);
 	}
 	/* Clear flag to prevent immediate re-entry. */
-	if (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
+	if (READ_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
 		raw_spin_lock_irq(&rnp->lock);
 		smp_mb__after_unlock_lock();
-		ACCESS_ONCE(rsp->gp_flags) =
-			ACCESS_ONCE(rsp->gp_flags) & ~RCU_GP_FLAG_FQS;
+		WRITE_ONCE(rsp->gp_flags,
+			   READ_ONCE(rsp->gp_flags) & ~RCU_GP_FLAG_FQS);
 		raw_spin_unlock_irq(&rnp->lock);
 	}
 	return fqs_state;
@@ -1903,7 +1954,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 	struct rcu_data *rdp;
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
-	ACCESS_ONCE(rsp->gp_activity) = jiffies;
+	WRITE_ONCE(rsp->gp_activity, jiffies);
 	raw_spin_lock_irq(&rnp->lock);
 	smp_mb__after_unlock_lock();
 	gp_duration = jiffies - rsp->gp_start;
@@ -1934,7 +1985,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 		smp_mb__after_unlock_lock();
 		WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp));
 		WARN_ON_ONCE(rnp->qsmask);
-		ACCESS_ONCE(rnp->completed) = rsp->gpnum;
+		WRITE_ONCE(rnp->completed, rsp->gpnum);
 		rdp = this_cpu_ptr(rsp->rda);
 		if (rnp == rdp->mynode)
 			needgp = __note_gp_changes(rsp, rnp, rdp) || needgp;
@@ -1942,7 +1993,8 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 		nocb += rcu_future_gp_cleanup(rsp, rnp);
 		raw_spin_unlock_irq(&rnp->lock);
 		cond_resched_rcu_qs();
-		ACCESS_ONCE(rsp->gp_activity) = jiffies;
+		WRITE_ONCE(rsp->gp_activity, jiffies);
+		rcu_gp_slow(rsp, gp_cleanup_delay);
 	}
 	rnp = rcu_get_root(rsp);
 	raw_spin_lock_irq(&rnp->lock);
@@ -1950,16 +2002,16 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 	rcu_nocb_gp_set(rnp, nocb);
 
 	/* Declare grace period done. */
-	ACCESS_ONCE(rsp->completed) = rsp->gpnum;
+	WRITE_ONCE(rsp->completed, rsp->gpnum);
 	trace_rcu_grace_period(rsp->name, rsp->completed, TPS("end"));
 	rsp->fqs_state = RCU_GP_IDLE;
 	rdp = this_cpu_ptr(rsp->rda);
 	/* Advance CBs to reduce false positives below. */
 	needgp = rcu_advance_cbs(rsp, rnp, rdp) || needgp;
 	if (needgp || cpu_needs_another_gp(rsp, rdp)) {
-		ACCESS_ONCE(rsp->gp_flags) = RCU_GP_FLAG_INIT;
+		WRITE_ONCE(rsp->gp_flags, RCU_GP_FLAG_INIT);
 		trace_rcu_grace_period(rsp->name,
-				       ACCESS_ONCE(rsp->gpnum),
+				       READ_ONCE(rsp->gpnum),
 				       TPS("newreq"));
 	}
 	raw_spin_unlock_irq(&rnp->lock);
@@ -1983,20 +2035,20 @@ static int __noreturn rcu_gp_kthread(void *arg)
 		/* Handle grace-period start. */
 		for (;;) {
 			trace_rcu_grace_period(rsp->name,
-					       ACCESS_ONCE(rsp->gpnum),
+					       READ_ONCE(rsp->gpnum),
 					       TPS("reqwait"));
 			rsp->gp_state = RCU_GP_WAIT_GPS;
 			wait_event_interruptible(rsp->gp_wq,
-						 ACCESS_ONCE(rsp->gp_flags) &
+						 READ_ONCE(rsp->gp_flags) &
 						 RCU_GP_FLAG_INIT);
 			/* Locking provides needed memory barrier. */
 			if (rcu_gp_init(rsp))
 				break;
 			cond_resched_rcu_qs();
-			ACCESS_ONCE(rsp->gp_activity) = jiffies;
+			WRITE_ONCE(rsp->gp_activity, jiffies);
 			WARN_ON(signal_pending(current));
 			trace_rcu_grace_period(rsp->name,
-					       ACCESS_ONCE(rsp->gpnum),
+					       READ_ONCE(rsp->gpnum),
 					       TPS("reqwaitsig"));
 		}
 
@@ -2012,39 +2064,39 @@ static int __noreturn rcu_gp_kthread(void *arg)
 			if (!ret)
 				rsp->jiffies_force_qs = jiffies + j;
 			trace_rcu_grace_period(rsp->name,
-					       ACCESS_ONCE(rsp->gpnum),
+					       READ_ONCE(rsp->gpnum),
 					       TPS("fqswait"));
 			rsp->gp_state = RCU_GP_WAIT_FQS;
 			ret = wait_event_interruptible_timeout(rsp->gp_wq,
-					((gf = ACCESS_ONCE(rsp->gp_flags)) &
+					((gf = READ_ONCE(rsp->gp_flags)) &
 					 RCU_GP_FLAG_FQS) ||
-					(!ACCESS_ONCE(rnp->qsmask) &&
+					(!READ_ONCE(rnp->qsmask) &&
 					 !rcu_preempt_blocked_readers_cgp(rnp)),
 					j);
 			/* Locking provides needed memory barriers. */
 			/* If grace period done, leave loop. */
-			if (!ACCESS_ONCE(rnp->qsmask) &&
+			if (!READ_ONCE(rnp->qsmask) &&
 			    !rcu_preempt_blocked_readers_cgp(rnp))
 				break;
 			/* If time for quiescent-state forcing, do it. */
 			if (ULONG_CMP_GE(jiffies, rsp->jiffies_force_qs) ||
 			    (gf & RCU_GP_FLAG_FQS)) {
 				trace_rcu_grace_period(rsp->name,
-						       ACCESS_ONCE(rsp->gpnum),
+						       READ_ONCE(rsp->gpnum),
 						       TPS("fqsstart"));
 				fqs_state = rcu_gp_fqs(rsp, fqs_state);
 				trace_rcu_grace_period(rsp->name,
-						       ACCESS_ONCE(rsp->gpnum),
+						       READ_ONCE(rsp->gpnum),
 						       TPS("fqsend"));
 				cond_resched_rcu_qs();
-				ACCESS_ONCE(rsp->gp_activity) = jiffies;
+				WRITE_ONCE(rsp->gp_activity, jiffies);
 			} else {
 				/* Deal with stray signal. */
 				cond_resched_rcu_qs();
-				ACCESS_ONCE(rsp->gp_activity) = jiffies;
+				WRITE_ONCE(rsp->gp_activity, jiffies);
 				WARN_ON(signal_pending(current));
 				trace_rcu_grace_period(rsp->name,
-						       ACCESS_ONCE(rsp->gpnum),
+						       READ_ONCE(rsp->gpnum),
 						       TPS("fqswaitsig"));
 			}
 			j = jiffies_till_next_fqs;
@@ -2086,8 +2138,8 @@ rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp,
 		 */
 		return false;
 	}
-	ACCESS_ONCE(rsp->gp_flags) = RCU_GP_FLAG_INIT;
-	trace_rcu_grace_period(rsp->name, ACCESS_ONCE(rsp->gpnum),
+	WRITE_ONCE(rsp->gp_flags, RCU_GP_FLAG_INIT);
+	trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gpnum),
 			       TPS("newreq"));
 
 	/*
@@ -2137,6 +2189,7 @@ static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags)
 	__releases(rcu_get_root(rsp)->lock)
 {
 	WARN_ON_ONCE(!rcu_gp_in_progress(rsp));
+	WRITE_ONCE(rsp->gp_flags, READ_ONCE(rsp->gp_flags) | RCU_GP_FLAG_FQS);
 	raw_spin_unlock_irqrestore(&rcu_get_root(rsp)->lock, flags);
 	rcu_gp_kthread_wake(rsp);
 }
@@ -2334,8 +2387,6 @@ rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp)
 	rcu_report_qs_rdp(rdp->cpu, rsp, rdp);
 }
 
-#ifdef CONFIG_HOTPLUG_CPU
-
 /*
  * Send the specified CPU's RCU callbacks to the orphanage.  The
  * specified CPU must be offline, and the caller must hold the
@@ -2346,7 +2397,7 @@ rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp,
 			  struct rcu_node *rnp, struct rcu_data *rdp)
 {
 	/* No-CBs CPUs do not have orphanable callbacks. */
-	if (rcu_is_nocb_cpu(rdp->cpu))
+	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) || rcu_is_nocb_cpu(rdp->cpu))
 		return;
 
 	/*
@@ -2359,7 +2410,7 @@ rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp,
 		rsp->qlen += rdp->qlen;
 		rdp->n_cbs_orphaned += rdp->qlen;
 		rdp->qlen_lazy = 0;
-		ACCESS_ONCE(rdp->qlen) = 0;
+		WRITE_ONCE(rdp->qlen, 0);
 	}
 
 	/*
@@ -2405,7 +2456,8 @@ static void rcu_adopt_orphan_cbs(struct rcu_state *rsp, unsigned long flags)
 	struct rcu_data *rdp = raw_cpu_ptr(rsp->rda);
 
 	/* No-CBs CPUs are handled specially. */
-	if (rcu_nocb_adopt_orphan_cbs(rsp, rdp, flags))
+	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) ||
+	    rcu_nocb_adopt_orphan_cbs(rsp, rdp, flags))
 		return;
 
 	/* Do the accounting first. */
@@ -2452,6 +2504,9 @@ static void rcu_cleanup_dying_cpu(struct rcu_state *rsp)
 	RCU_TRACE(struct rcu_data *rdp = this_cpu_ptr(rsp->rda));
 	RCU_TRACE(struct rcu_node *rnp = rdp->mynode);
 
+	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
+		return;
+
 	RCU_TRACE(mask = rdp->grpmask);
 	trace_rcu_grace_period(rsp->name,
 			       rnp->gpnum + 1 - !!(rnp->qsmask & mask),
@@ -2480,7 +2535,8 @@ static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf)
 	long mask;
 	struct rcu_node *rnp = rnp_leaf;
 
-	if (rnp->qsmaskinit || rcu_preempt_has_tasks(rnp))
+	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) ||
+	    rnp->qsmaskinit || rcu_preempt_has_tasks(rnp))
 		return;
 	for (;;) {
 		mask = rnp->grpmask;
@@ -2511,6 +2567,9 @@ static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp)
 	struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
 	struct rcu_node *rnp = rdp->mynode;  /* Outgoing CPU's rdp & rnp. */
 
+	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
+		return;
+
 	/* Remove outgoing CPU from mask in the leaf rcu_node structure. */
 	mask = rdp->grpmask;
 	raw_spin_lock_irqsave(&rnp->lock, flags);
@@ -2532,6 +2591,9 @@ static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp)
 	struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
 	struct rcu_node *rnp = rdp->mynode;  /* Outgoing CPU's rdp & rnp. */
 
+	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
+		return;
+
 	/* Adjust any no-longer-needed kthreads. */
 	rcu_boost_kthread_setaffinity(rnp, -1);
 
@@ -2546,26 +2608,6 @@ static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp)
 		  cpu, rdp->qlen, rdp->nxtlist);
 }
 
-#else /* #ifdef CONFIG_HOTPLUG_CPU */
-
-static void rcu_cleanup_dying_cpu(struct rcu_state *rsp)
-{
-}
-
-static void __maybe_unused rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf)
-{
-}
-
-static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp)
-{
-}
-
-static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp)
-{
-}
-
-#endif /* #else #ifdef CONFIG_HOTPLUG_CPU */
-
 /*
  * Invoke any RCU callbacks that have made it to the end of their grace
  * period.  Thottle as specified by rdp->blimit.
@@ -2580,7 +2622,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
 	/* If no callbacks are ready, just return. */
 	if (!cpu_has_callbacks_ready_to_invoke(rdp)) {
 		trace_rcu_batch_start(rsp->name, rdp->qlen_lazy, rdp->qlen, 0);
-		trace_rcu_batch_end(rsp->name, 0, !!ACCESS_ONCE(rdp->nxtlist),
+		trace_rcu_batch_end(rsp->name, 0, !!READ_ONCE(rdp->nxtlist),
 				    need_resched(), is_idle_task(current),
 				    rcu_is_callbacks_kthread());
 		return;
@@ -2636,7 +2678,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
 	}
 	smp_mb(); /* List handling before counting for rcu_barrier(). */
 	rdp->qlen_lazy -= count_lazy;
-	ACCESS_ONCE(rdp->qlen) = rdp->qlen - count;
+	WRITE_ONCE(rdp->qlen, rdp->qlen - count);
 	rdp->n_cbs_invoked += count;
 
 	/* Reinstate batch limit if we have worked down the excess. */
@@ -2730,10 +2772,6 @@ static void force_qs_rnp(struct rcu_state *rsp,
 		mask = 0;
 		raw_spin_lock_irqsave(&rnp->lock, flags);
 		smp_mb__after_unlock_lock();
-		if (!rcu_gp_in_progress(rsp)) {
-			raw_spin_unlock_irqrestore(&rnp->lock, flags);
-			return;
-		}
 		if (rnp->qsmask == 0) {
 			if (rcu_state_p == &rcu_sched_state ||
 			    rsp != rcu_state_p ||
@@ -2763,8 +2801,6 @@ static void force_qs_rnp(struct rcu_state *rsp,
 		bit = 1;
 		for (; cpu <= rnp->grphi; cpu++, bit <<= 1) {
 			if ((rnp->qsmask & bit) != 0) {
-				if ((rnp->qsmaskinit & bit) == 0)
-					*isidle = false; /* Pending hotplug. */
 				if (f(per_cpu_ptr(rsp->rda, cpu), isidle, maxj))
 					mask |= bit;
 			}
@@ -2793,7 +2829,7 @@ static void force_quiescent_state(struct rcu_state *rsp)
 	/* Funnel through hierarchy to reduce memory contention. */
 	rnp = __this_cpu_read(rsp->rda->mynode);
 	for (; rnp != NULL; rnp = rnp->parent) {
-		ret = (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) ||
+		ret = (READ_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) ||
 		      !raw_spin_trylock(&rnp->fqslock);
 		if (rnp_old != NULL)
 			raw_spin_unlock(&rnp_old->fqslock);
@@ -2809,13 +2845,12 @@ static void force_quiescent_state(struct rcu_state *rsp)
 	raw_spin_lock_irqsave(&rnp_old->lock, flags);
 	smp_mb__after_unlock_lock();
 	raw_spin_unlock(&rnp_old->fqslock);
-	if (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
+	if (READ_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
 		rsp->n_force_qs_lh++;
 		raw_spin_unlock_irqrestore(&rnp_old->lock, flags);
 		return;  /* Someone beat us to it. */
 	}
-	ACCESS_ONCE(rsp->gp_flags) =
-		ACCESS_ONCE(rsp->gp_flags) | RCU_GP_FLAG_FQS;
+	WRITE_ONCE(rsp->gp_flags, READ_ONCE(rsp->gp_flags) | RCU_GP_FLAG_FQS);
 	raw_spin_unlock_irqrestore(&rnp_old->lock, flags);
 	rcu_gp_kthread_wake(rsp);
 }
@@ -2881,7 +2916,7 @@ static void rcu_process_callbacks(struct softirq_action *unused)
  */
 static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp)
 {
-	if (unlikely(!ACCESS_ONCE(rcu_scheduler_fully_active)))
+	if (unlikely(!READ_ONCE(rcu_scheduler_fully_active)))
 		return;
 	if (likely(!rsp->boost)) {
 		rcu_do_batch(rsp, rdp);
@@ -2972,7 +3007,7 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
 	WARN_ON_ONCE((unsigned long)head & 0x1); /* Misaligned rcu_head! */
 	if (debug_rcu_head_queue(head)) {
 		/* Probable double call_rcu(), so leak the callback. */
-		ACCESS_ONCE(head->func) = rcu_leak_callback;
+		WRITE_ONCE(head->func, rcu_leak_callback);
 		WARN_ONCE(1, "__call_rcu(): Leaked duplicate callback\n");
 		return;
 	}
@@ -3011,7 +3046,7 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
 		if (!likely(rdp->nxtlist))
 			init_default_callback_list(rdp);
 	}
-	ACCESS_ONCE(rdp->qlen) = rdp->qlen + 1;
+	WRITE_ONCE(rdp->qlen, rdp->qlen + 1);
 	if (lazy)
 		rdp->qlen_lazy++;
 	else
@@ -3287,7 +3322,7 @@ void synchronize_sched_expedited(void)
 	if (ULONG_CMP_GE((ulong)atomic_long_read(&rsp->expedited_start),
 			 (ulong)atomic_long_read(&rsp->expedited_done) +
 			 ULONG_MAX / 8)) {
-		synchronize_sched();
+		wait_rcu_gp(call_rcu_sched);
 		atomic_long_inc(&rsp->expedited_wrap);
 		return;
 	}
@@ -3450,14 +3485,14 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
 	}
 
 	/* Has another RCU grace period completed?  */
-	if (ACCESS_ONCE(rnp->completed) != rdp->completed) { /* outside lock */
+	if (READ_ONCE(rnp->completed) != rdp->completed) { /* outside lock */
 		rdp->n_rp_gp_completed++;
 		return 1;
 	}
 
 	/* Has a new RCU grace period started? */
-	if (ACCESS_ONCE(rnp->gpnum) != rdp->gpnum ||
-	    unlikely(ACCESS_ONCE(rdp->gpwrap))) { /* outside lock */
+	if (READ_ONCE(rnp->gpnum) != rdp->gpnum ||
+	    unlikely(READ_ONCE(rdp->gpwrap))) { /* outside lock */
 		rdp->n_rp_gp_started++;
 		return 1;
 	}
@@ -3493,7 +3528,7 @@ static int rcu_pending(void)
  * non-NULL, store an indication of whether all callbacks are lazy.
  * (If there are no callbacks, all of them are deemed to be lazy.)
  */
-static int __maybe_unused rcu_cpu_has_callbacks(bool *all_lazy)
+static bool __maybe_unused rcu_cpu_has_callbacks(bool *all_lazy)
 {
 	bool al = true;
 	bool hc = false;
@@ -3564,7 +3599,7 @@ static void _rcu_barrier(struct rcu_state *rsp)
 {
 	int cpu;
 	struct rcu_data *rdp;
-	unsigned long snap = ACCESS_ONCE(rsp->n_barrier_done);
+	unsigned long snap = READ_ONCE(rsp->n_barrier_done);
 	unsigned long snap_done;
 
 	_rcu_barrier_trace(rsp, "Begin", -1, snap);
@@ -3606,10 +3641,10 @@ static void _rcu_barrier(struct rcu_state *rsp)
 
 	/*
 	 * Increment ->n_barrier_done to avoid duplicate work.  Use
-	 * ACCESS_ONCE() to prevent the compiler from speculating
+	 * WRITE_ONCE() to prevent the compiler from speculating
 	 * the increment to precede the early-exit check.
 	 */
-	ACCESS_ONCE(rsp->n_barrier_done) = rsp->n_barrier_done + 1;
+	WRITE_ONCE(rsp->n_barrier_done, rsp->n_barrier_done + 1);
 	WARN_ON_ONCE((rsp->n_barrier_done & 0x1) != 1);
 	_rcu_barrier_trace(rsp, "Inc1", -1, rsp->n_barrier_done);
 	smp_mb(); /* Order ->n_barrier_done increment with below mechanism. */
@@ -3645,7 +3680,7 @@ static void _rcu_barrier(struct rcu_state *rsp)
 				__call_rcu(&rdp->barrier_head,
 					   rcu_barrier_callback, rsp, cpu, 0);
 			}
-		} else if (ACCESS_ONCE(rdp->qlen)) {
+		} else if (READ_ONCE(rdp->qlen)) {
 			_rcu_barrier_trace(rsp, "OnlineQ", cpu,
 					   rsp->n_barrier_done);
 			smp_call_function_single(cpu, rcu_barrier_func, rsp, 1);
@@ -3665,7 +3700,7 @@ static void _rcu_barrier(struct rcu_state *rsp)
 
 	/* Increment ->n_barrier_done to prevent duplicate work. */
 	smp_mb(); /* Keep increment after above mechanism. */
-	ACCESS_ONCE(rsp->n_barrier_done) = rsp->n_barrier_done + 1;
+	WRITE_ONCE(rsp->n_barrier_done, rsp->n_barrier_done + 1);
 	WARN_ON_ONCE((rsp->n_barrier_done & 0x1) != 0);
 	_rcu_barrier_trace(rsp, "Inc2", -1, rsp->n_barrier_done);
 	smp_mb(); /* Keep increment before caller's subsequent code. */
@@ -3780,7 +3815,7 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
 	rdp->gpnum = rnp->completed; /* Make CPU later note any new GP. */
 	rdp->completed = rnp->completed;
 	rdp->passed_quiesce = false;
-	rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr);
+	rdp->rcu_qs_ctr_snap = per_cpu(rcu_qs_ctr, cpu);
 	rdp->qs_pending = false;
 	trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuonl"));
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
@@ -3924,16 +3959,16 @@ void rcu_scheduler_starting(void)
 
 /*
  * Compute the per-level fanout, either using the exact fanout specified
- * or balancing the tree, depending on CONFIG_RCU_FANOUT_EXACT.
+ * or balancing the tree, depending on the rcu_fanout_exact boot parameter.
  */
 static void __init rcu_init_levelspread(struct rcu_state *rsp)
 {
 	int i;
 
-	if (IS_ENABLED(CONFIG_RCU_FANOUT_EXACT)) {
+	if (rcu_fanout_exact) {
 		rsp->levelspread[rcu_num_lvls - 1] = rcu_fanout_leaf;
 		for (i = rcu_num_lvls - 2; i >= 0; i--)
-			rsp->levelspread[i] = CONFIG_RCU_FANOUT;
+			rsp->levelspread[i] = RCU_FANOUT;
 	} else {
 		int ccur;
 		int cprv;
@@ -3971,9 +4006,9 @@ static void __init rcu_init_one(struct rcu_state *rsp,
 
 	BUILD_BUG_ON(MAX_RCU_LVLS > ARRAY_SIZE(buf));  /* Fix buf[] init! */
 
-	/* Silence gcc 4.8 warning about array index out of range. */
-	if (rcu_num_lvls > RCU_NUM_LVLS)
-		panic("rcu_init_one: rcu_num_lvls overflow");
+	/* Silence gcc 4.8 false positive about array index out of range. */
+	if (rcu_num_lvls <= 0 || rcu_num_lvls > RCU_NUM_LVLS)
+		panic("rcu_init_one: rcu_num_lvls out of range");
 
 	/* Initialize the level-tracking arrays. */
 
@@ -4059,7 +4094,7 @@ static void __init rcu_init_geometry(void)
 		jiffies_till_next_fqs = d;
 
 	/* If the compile-time values are accurate, just leave. */
-	if (rcu_fanout_leaf == CONFIG_RCU_FANOUT_LEAF &&
+	if (rcu_fanout_leaf == RCU_FANOUT_LEAF &&
 	    nr_cpu_ids == NR_CPUS)
 		return;
 	pr_info("RCU: Adjusting geometry for rcu_fanout_leaf=%d, nr_cpu_ids=%d\n",
@@ -4073,7 +4108,7 @@ static void __init rcu_init_geometry(void)
 	rcu_capacity[0] = 1;
 	rcu_capacity[1] = rcu_fanout_leaf;
 	for (i = 2; i <= MAX_RCU_LVLS; i++)
-		rcu_capacity[i] = rcu_capacity[i - 1] * CONFIG_RCU_FANOUT;
+		rcu_capacity[i] = rcu_capacity[i - 1] * RCU_FANOUT;
 
 	/*
 	 * The boot-time rcu_fanout_leaf parameter is only permitted
@@ -4083,7 +4118,7 @@ static void __init rcu_init_geometry(void)
 	 * the configured number of CPUs.  Complain and fall back to the
 	 * compile-time values if these limits are exceeded.
 	 */
-	if (rcu_fanout_leaf < CONFIG_RCU_FANOUT_LEAF ||
+	if (rcu_fanout_leaf < RCU_FANOUT_LEAF ||
 	    rcu_fanout_leaf > sizeof(unsigned long) * 8 ||
 	    n > rcu_capacity[MAX_RCU_LVLS]) {
 		WARN_ON(1);
@@ -4109,6 +4144,28 @@ static void __init rcu_init_geometry(void)
 	rcu_num_nodes -= n;
 }
 
+/*
+ * Dump out the structure of the rcu_node combining tree associated
+ * with the rcu_state structure referenced by rsp.
+ */
+static void __init rcu_dump_rcu_node_tree(struct rcu_state *rsp)
+{
+	int level = 0;
+	struct rcu_node *rnp;
+
+	pr_info("rcu_node tree layout dump\n");
+	pr_info(" ");
+	rcu_for_each_node_breadth_first(rsp, rnp) {
+		if (rnp->level != level) {
+			pr_cont("\n");
+			pr_info(" ");
+			level = rnp->level;
+		}
+		pr_cont("%d:%d ^%d  ", rnp->grplo, rnp->grphi, rnp->grpnum);
+	}
+	pr_cont("\n");
+}
+
 void __init rcu_init(void)
 {
 	int cpu;
@@ -4119,6 +4176,8 @@ void __init rcu_init(void)
 	rcu_init_geometry();
 	rcu_init_one(&rcu_bh_state, &rcu_bh_data);
 	rcu_init_one(&rcu_sched_state, &rcu_sched_data);
+	if (dump_tree)
+		rcu_dump_rcu_node_tree(&rcu_sched_state);
 	__rcu_init_preempt();
 	open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
 
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index a69d3dab2ec4..4adb7ca0bf47 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -35,11 +35,33 @@
  * In practice, this did work well going from three levels to four.
  * Of course, your mileage may vary.
  */
+
 #define MAX_RCU_LVLS 4
-#define RCU_FANOUT_1	      (CONFIG_RCU_FANOUT_LEAF)
-#define RCU_FANOUT_2	      (RCU_FANOUT_1 * CONFIG_RCU_FANOUT)
-#define RCU_FANOUT_3	      (RCU_FANOUT_2 * CONFIG_RCU_FANOUT)
-#define RCU_FANOUT_4	      (RCU_FANOUT_3 * CONFIG_RCU_FANOUT)
+
+#ifdef CONFIG_RCU_FANOUT
+#define RCU_FANOUT CONFIG_RCU_FANOUT
+#else /* #ifdef CONFIG_RCU_FANOUT */
+# ifdef CONFIG_64BIT
+# define RCU_FANOUT 64
+# else
+# define RCU_FANOUT 32
+# endif
+#endif /* #else #ifdef CONFIG_RCU_FANOUT */
+
+#ifdef CONFIG_RCU_FANOUT_LEAF
+#define RCU_FANOUT_LEAF CONFIG_RCU_FANOUT_LEAF
+#else /* #ifdef CONFIG_RCU_FANOUT_LEAF */
+# ifdef CONFIG_64BIT
+# define RCU_FANOUT_LEAF 64
+# else
+# define RCU_FANOUT_LEAF 32
+# endif
+#endif /* #else #ifdef CONFIG_RCU_FANOUT_LEAF */
+
+#define RCU_FANOUT_1	      (RCU_FANOUT_LEAF)
+#define RCU_FANOUT_2	      (RCU_FANOUT_1 * RCU_FANOUT)
+#define RCU_FANOUT_3	      (RCU_FANOUT_2 * RCU_FANOUT)
+#define RCU_FANOUT_4	      (RCU_FANOUT_3 * RCU_FANOUT)
 
 #if NR_CPUS <= RCU_FANOUT_1
 #  define RCU_NUM_LVLS	      1
@@ -170,7 +192,6 @@ struct rcu_node {
 				/*  if there is no such task.  If there */
 				/*  is no current expedited grace period, */
 				/*  then there can cannot be any such task. */
-#ifdef CONFIG_RCU_BOOST
 	struct list_head *boost_tasks;
 				/* Pointer to first task that needs to be */
 				/*  priority boosted, or NULL if no priority */
@@ -208,7 +229,6 @@ struct rcu_node {
 	unsigned long n_balk_nos;
 				/* Refused to boost: not sure why, though. */
 				/*  This can happen due to race conditions. */
-#endif /* #ifdef CONFIG_RCU_BOOST */
 #ifdef CONFIG_RCU_NOCB_CPU
 	wait_queue_head_t nocb_gp_wq[2];
 				/* Place for rcu_nocb_kthread() to wait GP. */
@@ -519,14 +539,11 @@ extern struct list_head rcu_struct_flavors;
  * RCU implementation internal declarations:
  */
 extern struct rcu_state rcu_sched_state;
-DECLARE_PER_CPU(struct rcu_data, rcu_sched_data);
 
 extern struct rcu_state rcu_bh_state;
-DECLARE_PER_CPU(struct rcu_data, rcu_bh_data);
 
 #ifdef CONFIG_PREEMPT_RCU
 extern struct rcu_state rcu_preempt_state;
-DECLARE_PER_CPU(struct rcu_data, rcu_preempt_data);
 #endif /* #ifdef CONFIG_PREEMPT_RCU */
 
 #ifdef CONFIG_RCU_BOOST
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 8c0ec0f5a027..013485fb2b06 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -43,7 +43,17 @@ DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_status);
 DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_loops);
 DEFINE_PER_CPU(char, rcu_cpu_has_work);
 
-#endif /* #ifdef CONFIG_RCU_BOOST */
+#else /* #ifdef CONFIG_RCU_BOOST */
+
+/*
+ * Some architectures do not define rt_mutexes, but if !CONFIG_RCU_BOOST,
+ * all uses are in dead code.  Provide a definition to keep the compiler
+ * happy, but add WARN_ON_ONCE() to complain if used in the wrong place.
+ * This probably needs to be excluded from -rt builds.
+ */
+#define rt_mutex_owner(a) ({ WARN_ON_ONCE(1); NULL; })
+
+#endif /* #else #ifdef CONFIG_RCU_BOOST */
 
 #ifdef CONFIG_RCU_NOCB_CPU
 static cpumask_var_t rcu_nocb_mask; /* CPUs to have callbacks offloaded. */
@@ -60,11 +70,11 @@ static void __init rcu_bootup_announce_oddness(void)
 {
 	if (IS_ENABLED(CONFIG_RCU_TRACE))
 		pr_info("\tRCU debugfs-based tracing is enabled.\n");
-	if ((IS_ENABLED(CONFIG_64BIT) && CONFIG_RCU_FANOUT != 64) ||
-	    (!IS_ENABLED(CONFIG_64BIT) && CONFIG_RCU_FANOUT != 32))
+	if ((IS_ENABLED(CONFIG_64BIT) && RCU_FANOUT != 64) ||
+	    (!IS_ENABLED(CONFIG_64BIT) && RCU_FANOUT != 32))
 		pr_info("\tCONFIG_RCU_FANOUT set to non-default value of %d\n",
-		       CONFIG_RCU_FANOUT);
-	if (IS_ENABLED(CONFIG_RCU_FANOUT_EXACT))
+		       RCU_FANOUT);
+	if (rcu_fanout_exact)
 		pr_info("\tHierarchical RCU autobalancing is disabled.\n");
 	if (IS_ENABLED(CONFIG_RCU_FAST_NO_HZ))
 		pr_info("\tRCU dyntick-idle grace-period acceleration is enabled.\n");
@@ -76,10 +86,10 @@ static void __init rcu_bootup_announce_oddness(void)
 		pr_info("\tAdditional per-CPU info printed with stalls.\n");
 	if (NUM_RCU_LVL_4 != 0)
 		pr_info("\tFour-level hierarchy is enabled.\n");
-	if (CONFIG_RCU_FANOUT_LEAF != 16)
+	if (RCU_FANOUT_LEAF != 16)
 		pr_info("\tBuild-time adjustment of leaf fanout to %d.\n",
-			CONFIG_RCU_FANOUT_LEAF);
-	if (rcu_fanout_leaf != CONFIG_RCU_FANOUT_LEAF)
+			RCU_FANOUT_LEAF);
+	if (rcu_fanout_leaf != RCU_FANOUT_LEAF)
 		pr_info("\tBoot-time adjustment of leaf fanout to %d.\n", rcu_fanout_leaf);
 	if (nr_cpu_ids != NR_CPUS)
 		pr_info("\tRCU restricting CPUs from NR_CPUS=%d to nr_cpu_ids=%d.\n", NR_CPUS, nr_cpu_ids);
@@ -90,7 +100,8 @@ static void __init rcu_bootup_announce_oddness(void)
 #ifdef CONFIG_PREEMPT_RCU
 
 RCU_STATE_INITIALIZER(rcu_preempt, 'p', call_rcu);
-static struct rcu_state *rcu_state_p = &rcu_preempt_state;
+static struct rcu_state *const rcu_state_p = &rcu_preempt_state;
+static struct rcu_data __percpu *const rcu_data_p = &rcu_preempt_data;
 
 static int rcu_preempted_readers_exp(struct rcu_node *rnp);
 static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
@@ -116,11 +127,11 @@ static void __init rcu_bootup_announce(void)
  */
 static void rcu_preempt_qs(void)
 {
-	if (!__this_cpu_read(rcu_preempt_data.passed_quiesce)) {
+	if (!__this_cpu_read(rcu_data_p->passed_quiesce)) {
 		trace_rcu_grace_period(TPS("rcu_preempt"),
-				       __this_cpu_read(rcu_preempt_data.gpnum),
+				       __this_cpu_read(rcu_data_p->gpnum),
 				       TPS("cpuqs"));
-		__this_cpu_write(rcu_preempt_data.passed_quiesce, 1);
+		__this_cpu_write(rcu_data_p->passed_quiesce, 1);
 		barrier(); /* Coordinate with rcu_preempt_check_callbacks(). */
 		current->rcu_read_unlock_special.b.need_qs = false;
 	}
@@ -150,7 +161,7 @@ static void rcu_preempt_note_context_switch(void)
 	    !t->rcu_read_unlock_special.b.blocked) {
 
 		/* Possibly blocking in an RCU read-side critical section. */
-		rdp = this_cpu_ptr(rcu_preempt_state.rda);
+		rdp = this_cpu_ptr(rcu_state_p->rda);
 		rnp = rdp->mynode;
 		raw_spin_lock_irqsave(&rnp->lock, flags);
 		smp_mb__after_unlock_lock();
@@ -180,10 +191,9 @@ static void rcu_preempt_note_context_switch(void)
 		if ((rnp->qsmask & rdp->grpmask) && rnp->gp_tasks != NULL) {
 			list_add(&t->rcu_node_entry, rnp->gp_tasks->prev);
 			rnp->gp_tasks = &t->rcu_node_entry;
-#ifdef CONFIG_RCU_BOOST
-			if (rnp->boost_tasks != NULL)
+			if (IS_ENABLED(CONFIG_RCU_BOOST) &&
+			    rnp->boost_tasks != NULL)
 				rnp->boost_tasks = rnp->gp_tasks;
-#endif /* #ifdef CONFIG_RCU_BOOST */
 		} else {
 			list_add(&t->rcu_node_entry, &rnp->blkd_tasks);
 			if (rnp->qsmask & rdp->grpmask)
@@ -263,9 +273,7 @@ void rcu_read_unlock_special(struct task_struct *t)
 	bool empty_exp_now;
 	unsigned long flags;
 	struct list_head *np;
-#ifdef CONFIG_RCU_BOOST
 	bool drop_boost_mutex = false;
-#endif /* #ifdef CONFIG_RCU_BOOST */
 	struct rcu_node *rnp;
 	union rcu_special special;
 
@@ -307,9 +315,11 @@ void rcu_read_unlock_special(struct task_struct *t)
 		t->rcu_read_unlock_special.b.blocked = false;
 
 		/*
-		 * Remove this task from the list it blocked on.  The
-		 * task can migrate while we acquire the lock, but at
-		 * most one time.  So at most two passes through loop.
+		 * Remove this task from the list it blocked on.  The task
+		 * now remains queued on the rcu_node corresponding to
+		 * the CPU it first blocked on, so the first attempt to
+		 * acquire the task's rcu_node's ->lock will succeed.
+		 * Keep the loop and add a WARN_ON() out of sheer paranoia.
 		 */
 		for (;;) {
 			rnp = t->rcu_blocked_node;
@@ -317,6 +327,7 @@ void rcu_read_unlock_special(struct task_struct *t)
 			smp_mb__after_unlock_lock();
 			if (rnp == t->rcu_blocked_node)
 				break;
+			WARN_ON_ONCE(1);
 			raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
 		}
 		empty_norm = !rcu_preempt_blocked_readers_cgp(rnp);
@@ -331,12 +342,12 @@ void rcu_read_unlock_special(struct task_struct *t)
 			rnp->gp_tasks = np;
 		if (&t->rcu_node_entry == rnp->exp_tasks)
 			rnp->exp_tasks = np;
-#ifdef CONFIG_RCU_BOOST
-		if (&t->rcu_node_entry == rnp->boost_tasks)
-			rnp->boost_tasks = np;
-		/* Snapshot ->boost_mtx ownership with rcu_node lock held. */
-		drop_boost_mutex = rt_mutex_owner(&rnp->boost_mtx) == t;
-#endif /* #ifdef CONFIG_RCU_BOOST */
+		if (IS_ENABLED(CONFIG_RCU_BOOST)) {
+			if (&t->rcu_node_entry == rnp->boost_tasks)
+				rnp->boost_tasks = np;
+			/* Snapshot ->boost_mtx ownership w/rnp->lock held. */
+			drop_boost_mutex = rt_mutex_owner(&rnp->boost_mtx) == t;
+		}
 
 		/*
 		 * If this was the last task on the current list, and if
@@ -353,24 +364,21 @@ void rcu_read_unlock_special(struct task_struct *t)
 							 rnp->grplo,
 							 rnp->grphi,
 							 !!rnp->gp_tasks);
-			rcu_report_unblock_qs_rnp(&rcu_preempt_state,
-						  rnp, flags);
+			rcu_report_unblock_qs_rnp(rcu_state_p, rnp, flags);
 		} else {
 			raw_spin_unlock_irqrestore(&rnp->lock, flags);
 		}
 
-#ifdef CONFIG_RCU_BOOST
 		/* Unboost if we were boosted. */
-		if (drop_boost_mutex)
+		if (IS_ENABLED(CONFIG_RCU_BOOST) && drop_boost_mutex)
 			rt_mutex_unlock(&rnp->boost_mtx);
-#endif /* #ifdef CONFIG_RCU_BOOST */
 
 		/*
 		 * If this was the last task on the expedited lists,
 		 * then we need to report up the rcu_node hierarchy.
 		 */
 		if (!empty_exp && empty_exp_now)
-			rcu_report_exp_rnp(&rcu_preempt_state, rnp, true);
+			rcu_report_exp_rnp(rcu_state_p, rnp, true);
 	} else {
 		local_irq_restore(flags);
 	}
@@ -390,7 +398,7 @@ static void rcu_print_detail_task_stall_rnp(struct rcu_node *rnp)
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 		return;
 	}
-	t = list_entry(rnp->gp_tasks,
+	t = list_entry(rnp->gp_tasks->prev,
 		       struct task_struct, rcu_node_entry);
 	list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry)
 		sched_show_task(t);
@@ -447,7 +455,7 @@ static int rcu_print_task_stall(struct rcu_node *rnp)
 	if (!rcu_preempt_blocked_readers_cgp(rnp))
 		return 0;
 	rcu_print_task_stall_begin(rnp);
-	t = list_entry(rnp->gp_tasks,
+	t = list_entry(rnp->gp_tasks->prev,
 		       struct task_struct, rcu_node_entry);
 	list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) {
 		pr_cont(" P%d", t->pid);
@@ -491,8 +499,8 @@ static void rcu_preempt_check_callbacks(void)
 		return;
 	}
 	if (t->rcu_read_lock_nesting > 0 &&
-	    __this_cpu_read(rcu_preempt_data.qs_pending) &&
-	    !__this_cpu_read(rcu_preempt_data.passed_quiesce))
+	    __this_cpu_read(rcu_data_p->qs_pending) &&
+	    !__this_cpu_read(rcu_data_p->passed_quiesce))
 		t->rcu_read_unlock_special.b.need_qs = true;
 }
 
@@ -500,7 +508,7 @@ static void rcu_preempt_check_callbacks(void)
 
 static void rcu_preempt_do_callbacks(void)
 {
-	rcu_do_batch(&rcu_preempt_state, this_cpu_ptr(&rcu_preempt_data));
+	rcu_do_batch(rcu_state_p, this_cpu_ptr(rcu_data_p));
 }
 
 #endif /* #ifdef CONFIG_RCU_BOOST */
@@ -510,7 +518,7 @@ static void rcu_preempt_do_callbacks(void)
  */
 void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
 {
-	__call_rcu(head, func, &rcu_preempt_state, -1, 0);
+	__call_rcu(head, func, rcu_state_p, -1, 0);
 }
 EXPORT_SYMBOL_GPL(call_rcu);
 
@@ -570,7 +578,7 @@ static int rcu_preempted_readers_exp(struct rcu_node *rnp)
 static int sync_rcu_preempt_exp_done(struct rcu_node *rnp)
 {
 	return !rcu_preempted_readers_exp(rnp) &&
-	       ACCESS_ONCE(rnp->expmask) == 0;
+	       READ_ONCE(rnp->expmask) == 0;
 }
 
 /*
@@ -711,12 +719,12 @@ sync_rcu_preempt_exp_init2(struct rcu_state *rsp, struct rcu_node *rnp)
 void synchronize_rcu_expedited(void)
 {
 	struct rcu_node *rnp;
-	struct rcu_state *rsp = &rcu_preempt_state;
+	struct rcu_state *rsp = rcu_state_p;
 	unsigned long snap;
 	int trycount = 0;
 
 	smp_mb(); /* Caller's modifications seen first by other CPUs. */
-	snap = ACCESS_ONCE(sync_rcu_preempt_exp_count) + 1;
+	snap = READ_ONCE(sync_rcu_preempt_exp_count) + 1;
 	smp_mb(); /* Above access cannot bleed into critical section. */
 
 	/*
@@ -740,7 +748,7 @@ void synchronize_rcu_expedited(void)
 	 */
 	while (!mutex_trylock(&sync_rcu_preempt_exp_mutex)) {
 		if (ULONG_CMP_LT(snap,
-		    ACCESS_ONCE(sync_rcu_preempt_exp_count))) {
+		    READ_ONCE(sync_rcu_preempt_exp_count))) {
 			put_online_cpus();
 			goto mb_ret; /* Others did our work for us. */
 		}
@@ -752,7 +760,7 @@ void synchronize_rcu_expedited(void)
 			return;
 		}
 	}
-	if (ULONG_CMP_LT(snap, ACCESS_ONCE(sync_rcu_preempt_exp_count))) {
+	if (ULONG_CMP_LT(snap, READ_ONCE(sync_rcu_preempt_exp_count))) {
 		put_online_cpus();
 		goto unlock_mb_ret; /* Others did our work for us. */
 	}
@@ -780,8 +788,7 @@ void synchronize_rcu_expedited(void)
 
 	/* Clean up and exit. */
 	smp_mb(); /* ensure expedited GP seen before counter increment. */
-	ACCESS_ONCE(sync_rcu_preempt_exp_count) =
-					sync_rcu_preempt_exp_count + 1;
+	WRITE_ONCE(sync_rcu_preempt_exp_count, sync_rcu_preempt_exp_count + 1);
 unlock_mb_ret:
 	mutex_unlock(&sync_rcu_preempt_exp_mutex);
 mb_ret:
@@ -799,7 +806,7 @@ EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
  */
 void rcu_barrier(void)
 {
-	_rcu_barrier(&rcu_preempt_state);
+	_rcu_barrier(rcu_state_p);
 }
 EXPORT_SYMBOL_GPL(rcu_barrier);
 
@@ -808,7 +815,7 @@ EXPORT_SYMBOL_GPL(rcu_barrier);
  */
 static void __init __rcu_init_preempt(void)
 {
-	rcu_init_one(&rcu_preempt_state, &rcu_preempt_data);
+	rcu_init_one(rcu_state_p, rcu_data_p);
 }
 
 /*
@@ -831,7 +838,8 @@ void exit_rcu(void)
 
 #else /* #ifdef CONFIG_PREEMPT_RCU */
 
-static struct rcu_state *rcu_state_p = &rcu_sched_state;
+static struct rcu_state *const rcu_state_p = &rcu_sched_state;
+static struct rcu_data __percpu *const rcu_data_p = &rcu_sched_data;
 
 /*
  * Tell them what RCU they are running.
@@ -994,8 +1002,8 @@ static int rcu_boost(struct rcu_node *rnp)
 	struct task_struct *t;
 	struct list_head *tb;
 
-	if (ACCESS_ONCE(rnp->exp_tasks) == NULL &&
-	    ACCESS_ONCE(rnp->boost_tasks) == NULL)
+	if (READ_ONCE(rnp->exp_tasks) == NULL &&
+	    READ_ONCE(rnp->boost_tasks) == NULL)
 		return 0;  /* Nothing left to boost. */
 
 	raw_spin_lock_irqsave(&rnp->lock, flags);
@@ -1048,8 +1056,8 @@ static int rcu_boost(struct rcu_node *rnp)
 	rt_mutex_lock(&rnp->boost_mtx);
 	rt_mutex_unlock(&rnp->boost_mtx);  /* Then keep lockdep happy. */
 
-	return ACCESS_ONCE(rnp->exp_tasks) != NULL ||
-	       ACCESS_ONCE(rnp->boost_tasks) != NULL;
+	return READ_ONCE(rnp->exp_tasks) != NULL ||
+	       READ_ONCE(rnp->boost_tasks) != NULL;
 }
 
 /*
@@ -1173,7 +1181,7 @@ static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
 	struct sched_param sp;
 	struct task_struct *t;
 
-	if (&rcu_preempt_state != rsp)
+	if (rcu_state_p != rsp)
 		return 0;
 
 	if (!rcu_scheduler_fully_active || rcu_rnp_online_cpus(rnp) == 0)
@@ -1367,13 +1375,12 @@ static void rcu_prepare_kthreads(int cpu)
  * Because we not have RCU_FAST_NO_HZ, just check whether this CPU needs
  * any flavor of RCU.
  */
-#ifndef CONFIG_RCU_NOCB_CPU_ALL
-int rcu_needs_cpu(unsigned long *delta_jiffies)
+int rcu_needs_cpu(u64 basemono, u64 *nextevt)
 {
-	*delta_jiffies = ULONG_MAX;
-	return rcu_cpu_has_callbacks(NULL);
+	*nextevt = KTIME_MAX;
+	return IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL)
+	       ? 0 : rcu_cpu_has_callbacks(NULL);
 }
-#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */
 
 /*
  * Because we do not have RCU_FAST_NO_HZ, don't bother cleaning up
@@ -1432,8 +1439,6 @@ module_param(rcu_idle_gp_delay, int, 0644);
 static int rcu_idle_lazy_gp_delay = RCU_IDLE_LAZY_GP_DELAY;
 module_param(rcu_idle_lazy_gp_delay, int, 0644);
 
-extern int tick_nohz_active;
-
 /*
  * Try to advance callbacks for all flavors of RCU on the current CPU, but
  * only if it has been awhile since the last time we did so.  Afterwards,
@@ -1462,7 +1467,7 @@ static bool __maybe_unused rcu_try_advance_all_cbs(void)
 		 * callbacks not yet ready to invoke.
 		 */
 		if ((rdp->completed != rnp->completed ||
-		     unlikely(ACCESS_ONCE(rdp->gpwrap))) &&
+		     unlikely(READ_ONCE(rdp->gpwrap))) &&
 		    rdp->nxttail[RCU_DONE_TAIL] != rdp->nxttail[RCU_NEXT_TAIL])
 			note_gp_changes(rsp, rdp);
 
@@ -1480,17 +1485,22 @@ static bool __maybe_unused rcu_try_advance_all_cbs(void)
  *
  * The caller must have disabled interrupts.
  */
-#ifndef CONFIG_RCU_NOCB_CPU_ALL
-int rcu_needs_cpu(unsigned long *dj)
+int rcu_needs_cpu(u64 basemono, u64 *nextevt)
 {
 	struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
+	unsigned long dj;
+
+	if (IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL)) {
+		*nextevt = KTIME_MAX;
+		return 0;
+	}
 
 	/* Snapshot to detect later posting of non-lazy callback. */
 	rdtp->nonlazy_posted_snap = rdtp->nonlazy_posted;
 
 	/* If no callbacks, RCU doesn't need the CPU. */
 	if (!rcu_cpu_has_callbacks(&rdtp->all_lazy)) {
-		*dj = ULONG_MAX;
+		*nextevt = KTIME_MAX;
 		return 0;
 	}
 
@@ -1504,14 +1514,14 @@ int rcu_needs_cpu(unsigned long *dj)
 
 	/* Request timer delay depending on laziness, and round. */
 	if (!rdtp->all_lazy) {
-		*dj = round_up(rcu_idle_gp_delay + jiffies,
+		dj = round_up(rcu_idle_gp_delay + jiffies,
 			       rcu_idle_gp_delay) - jiffies;
 	} else {
-		*dj = round_jiffies(rcu_idle_lazy_gp_delay + jiffies) - jiffies;
+		dj = round_jiffies(rcu_idle_lazy_gp_delay + jiffies) - jiffies;
 	}
+	*nextevt = basemono + dj * TICK_NSEC;
 	return 0;
 }
-#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */
 
 /*
  * Prepare a CPU for idle from an RCU perspective.  The first major task
@@ -1525,7 +1535,6 @@ int rcu_needs_cpu(unsigned long *dj)
  */
 static void rcu_prepare_for_idle(void)
 {
-#ifndef CONFIG_RCU_NOCB_CPU_ALL
 	bool needwake;
 	struct rcu_data *rdp;
 	struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
@@ -1533,8 +1542,11 @@ static void rcu_prepare_for_idle(void)
 	struct rcu_state *rsp;
 	int tne;
 
+	if (IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL))
+		return;
+
 	/* Handle nohz enablement switches conservatively. */
-	tne = ACCESS_ONCE(tick_nohz_active);
+	tne = READ_ONCE(tick_nohz_active);
 	if (tne != rdtp->tick_nohz_enabled_snap) {
 		if (rcu_cpu_has_callbacks(NULL))
 			invoke_rcu_core(); /* force nohz to see update. */
@@ -1580,7 +1592,6 @@ static void rcu_prepare_for_idle(void)
 		if (needwake)
 			rcu_gp_kthread_wake(rsp);
 	}
-#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */
 }
 
 /*
@@ -1590,12 +1601,11 @@ static void rcu_prepare_for_idle(void)
  */
 static void rcu_cleanup_after_idle(void)
 {
-#ifndef CONFIG_RCU_NOCB_CPU_ALL
-	if (rcu_is_nocb_cpu(smp_processor_id()))
+	if (IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL) ||
+	    rcu_is_nocb_cpu(smp_processor_id()))
 		return;
 	if (rcu_try_advance_all_cbs())
 		invoke_rcu_core();
-#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */
 }
 
 /*
@@ -1760,7 +1770,7 @@ static void print_cpu_stall_info(struct rcu_state *rsp, int cpu)
 	       atomic_read(&rdtp->dynticks) & 0xfff,
 	       rdtp->dynticks_nesting, rdtp->dynticks_nmi_nesting,
 	       rdp->softirq_snap, kstat_softirqs_cpu(RCU_SOFTIRQ, cpu),
-	       ACCESS_ONCE(rsp->n_force_qs) - rsp->n_force_qs_gpstart,
+	       READ_ONCE(rsp->n_force_qs) - rsp->n_force_qs_gpstart,
 	       fast_no_hz);
 }
 
@@ -1898,11 +1908,11 @@ static void wake_nocb_leader(struct rcu_data *rdp, bool force)
 {
 	struct rcu_data *rdp_leader = rdp->nocb_leader;
 
-	if (!ACCESS_ONCE(rdp_leader->nocb_kthread))
+	if (!READ_ONCE(rdp_leader->nocb_kthread))
 		return;
-	if (ACCESS_ONCE(rdp_leader->nocb_leader_sleep) || force) {
+	if (READ_ONCE(rdp_leader->nocb_leader_sleep) || force) {
 		/* Prior smp_mb__after_atomic() orders against prior enqueue. */
-		ACCESS_ONCE(rdp_leader->nocb_leader_sleep) = false;
+		WRITE_ONCE(rdp_leader->nocb_leader_sleep, false);
 		wake_up(&rdp_leader->nocb_wq);
 	}
 }
@@ -1934,14 +1944,14 @@ static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu)
 	ret = atomic_long_read(&rdp->nocb_q_count);
 
 #ifdef CONFIG_PROVE_RCU
-	rhp = ACCESS_ONCE(rdp->nocb_head);
+	rhp = READ_ONCE(rdp->nocb_head);
 	if (!rhp)
-		rhp = ACCESS_ONCE(rdp->nocb_gp_head);
+		rhp = READ_ONCE(rdp->nocb_gp_head);
 	if (!rhp)
-		rhp = ACCESS_ONCE(rdp->nocb_follower_head);
+		rhp = READ_ONCE(rdp->nocb_follower_head);
 
 	/* Having no rcuo kthread but CBs after scheduler starts is bad! */
-	if (!ACCESS_ONCE(rdp->nocb_kthread) && rhp &&
+	if (!READ_ONCE(rdp->nocb_kthread) && rhp &&
 	    rcu_scheduler_fully_active) {
 		/* RCU callback enqueued before CPU first came online??? */
 		pr_err("RCU: Never-onlined no-CBs CPU %d has CB %p\n",
@@ -1975,12 +1985,12 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp,
 	atomic_long_add(rhcount, &rdp->nocb_q_count);
 	/* rcu_barrier() relies on ->nocb_q_count add before xchg. */
 	old_rhpp = xchg(&rdp->nocb_tail, rhtp);
-	ACCESS_ONCE(*old_rhpp) = rhp;
+	WRITE_ONCE(*old_rhpp, rhp);
 	atomic_long_add(rhcount_lazy, &rdp->nocb_q_count_lazy);
 	smp_mb__after_atomic(); /* Store *old_rhpp before _wake test. */
 
 	/* If we are not being polled and there is a kthread, awaken it ... */
-	t = ACCESS_ONCE(rdp->nocb_kthread);
+	t = READ_ONCE(rdp->nocb_kthread);
 	if (rcu_nocb_poll || !t) {
 		trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
 				    TPS("WakeNotPoll"));
@@ -2118,7 +2128,7 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp)
 	for (;;) {
 		wait_event_interruptible(
 			rnp->nocb_gp_wq[c & 0x1],
-			(d = ULONG_CMP_GE(ACCESS_ONCE(rnp->completed), c)));
+			(d = ULONG_CMP_GE(READ_ONCE(rnp->completed), c)));
 		if (likely(d))
 			break;
 		WARN_ON(signal_pending(current));
@@ -2145,7 +2155,7 @@ wait_again:
 	if (!rcu_nocb_poll) {
 		trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu, "Sleep");
 		wait_event_interruptible(my_rdp->nocb_wq,
-				!ACCESS_ONCE(my_rdp->nocb_leader_sleep));
+				!READ_ONCE(my_rdp->nocb_leader_sleep));
 		/* Memory barrier handled by smp_mb() calls below and repoll. */
 	} else if (firsttime) {
 		firsttime = false; /* Don't drown trace log with "Poll"! */
@@ -2159,12 +2169,12 @@ wait_again:
 	 */
 	gotcbs = false;
 	for (rdp = my_rdp; rdp; rdp = rdp->nocb_next_follower) {
-		rdp->nocb_gp_head = ACCESS_ONCE(rdp->nocb_head);
+		rdp->nocb_gp_head = READ_ONCE(rdp->nocb_head);
 		if (!rdp->nocb_gp_head)
 			continue;  /* No CBs here, try next follower. */
 
 		/* Move callbacks to wait-for-GP list, which is empty. */
-		ACCESS_ONCE(rdp->nocb_head) = NULL;
+		WRITE_ONCE(rdp->nocb_head, NULL);
 		rdp->nocb_gp_tail = xchg(&rdp->nocb_tail, &rdp->nocb_head);
 		gotcbs = true;
 	}
@@ -2184,7 +2194,7 @@ wait_again:
 		my_rdp->nocb_leader_sleep = true;
 		smp_mb();  /* Ensure _sleep true before scan. */
 		for (rdp = my_rdp; rdp; rdp = rdp->nocb_next_follower)
-			if (ACCESS_ONCE(rdp->nocb_head)) {
+			if (READ_ONCE(rdp->nocb_head)) {
 				/* Found CB, so short-circuit next wait. */
 				my_rdp->nocb_leader_sleep = false;
 				break;
@@ -2205,7 +2215,7 @@ wait_again:
 
 	/* Each pass through the following loop wakes a follower, if needed. */
 	for (rdp = my_rdp; rdp; rdp = rdp->nocb_next_follower) {
-		if (ACCESS_ONCE(rdp->nocb_head))
+		if (READ_ONCE(rdp->nocb_head))
 			my_rdp->nocb_leader_sleep = false;/* No need to sleep.*/
 		if (!rdp->nocb_gp_head)
 			continue; /* No CBs, so no need to wake follower. */
@@ -2241,7 +2251,7 @@ static void nocb_follower_wait(struct rcu_data *rdp)
 			trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
 					    "FollowerSleep");
 			wait_event_interruptible(rdp->nocb_wq,
-						 ACCESS_ONCE(rdp->nocb_follower_head));
+						 READ_ONCE(rdp->nocb_follower_head));
 		} else if (firsttime) {
 			/* Don't drown trace log with "Poll"! */
 			firsttime = false;
@@ -2282,10 +2292,10 @@ static int rcu_nocb_kthread(void *arg)
 			nocb_follower_wait(rdp);
 
 		/* Pull the ready-to-invoke callbacks onto local list. */
-		list = ACCESS_ONCE(rdp->nocb_follower_head);
+		list = READ_ONCE(rdp->nocb_follower_head);
 		BUG_ON(!list);
 		trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, "WokeNonEmpty");
-		ACCESS_ONCE(rdp->nocb_follower_head) = NULL;
+		WRITE_ONCE(rdp->nocb_follower_head, NULL);
 		tail = xchg(&rdp->nocb_follower_tail, &rdp->nocb_follower_head);
 
 		/* Each pass through the following loop invokes a callback. */
@@ -2324,7 +2334,7 @@ static int rcu_nocb_kthread(void *arg)
 /* Is a deferred wakeup of rcu_nocb_kthread() required? */
 static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp)
 {
-	return ACCESS_ONCE(rdp->nocb_defer_wakeup);
+	return READ_ONCE(rdp->nocb_defer_wakeup);
 }
 
 /* Do a deferred wakeup of rcu_nocb_kthread(). */
@@ -2334,8 +2344,8 @@ static void do_nocb_deferred_wakeup(struct rcu_data *rdp)
 
 	if (!rcu_nocb_need_deferred_wakeup(rdp))
 		return;
-	ndw = ACCESS_ONCE(rdp->nocb_defer_wakeup);
-	ACCESS_ONCE(rdp->nocb_defer_wakeup) = RCU_NOGP_WAKE_NOT;
+	ndw = READ_ONCE(rdp->nocb_defer_wakeup);
+	WRITE_ONCE(rdp->nocb_defer_wakeup, RCU_NOGP_WAKE_NOT);
 	wake_nocb_leader(rdp, ndw == RCU_NOGP_WAKE_FORCE);
 	trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("DeferredWake"));
 }
@@ -2448,7 +2458,7 @@ static void rcu_spawn_one_nocb_kthread(struct rcu_state *rsp, int cpu)
 	t = kthread_run(rcu_nocb_kthread, rdp_spawn,
 			"rcuo%c/%d", rsp->abbr, cpu);
 	BUG_ON(IS_ERR(t));
-	ACCESS_ONCE(rdp_spawn->nocb_kthread) = t;
+	WRITE_ONCE(rdp_spawn->nocb_kthread, t);
 }
 
 /*
@@ -2663,7 +2673,7 @@ static void rcu_sysidle_enter(int irq)
 
 	/* Record start of fully idle period. */
 	j = jiffies;
-	ACCESS_ONCE(rdtp->dynticks_idle_jiffies) = j;
+	WRITE_ONCE(rdtp->dynticks_idle_jiffies, j);
 	smp_mb__before_atomic();
 	atomic_inc(&rdtp->dynticks_idle);
 	smp_mb__after_atomic();
@@ -2681,7 +2691,7 @@ static void rcu_sysidle_enter(int irq)
  */
 void rcu_sysidle_force_exit(void)
 {
-	int oldstate = ACCESS_ONCE(full_sysidle_state);
+	int oldstate = READ_ONCE(full_sysidle_state);
 	int newoldstate;
 
 	/*
@@ -2794,7 +2804,7 @@ static void rcu_sysidle_check_cpu(struct rcu_data *rdp, bool *isidle,
 	smp_mb(); /* Read counters before timestamps. */
 
 	/* Pick up timestamps. */
-	j = ACCESS_ONCE(rdtp->dynticks_idle_jiffies);
+	j = READ_ONCE(rdtp->dynticks_idle_jiffies);
 	/* If this CPU entered idle more recently, update maxj timestamp. */
 	if (ULONG_CMP_LT(*maxj, j))
 		*maxj = j;
@@ -2831,11 +2841,11 @@ static unsigned long rcu_sysidle_delay(void)
 static void rcu_sysidle(unsigned long j)
 {
 	/* Check the current state. */
-	switch (ACCESS_ONCE(full_sysidle_state)) {
+	switch (READ_ONCE(full_sysidle_state)) {
 	case RCU_SYSIDLE_NOT:
 
 		/* First time all are idle, so note a short idle period. */
-		ACCESS_ONCE(full_sysidle_state) = RCU_SYSIDLE_SHORT;
+		WRITE_ONCE(full_sysidle_state, RCU_SYSIDLE_SHORT);
 		break;
 
 	case RCU_SYSIDLE_SHORT:
@@ -2873,7 +2883,7 @@ static void rcu_sysidle_cancel(void)
 {
 	smp_mb();
 	if (full_sysidle_state > RCU_SYSIDLE_SHORT)
-		ACCESS_ONCE(full_sysidle_state) = RCU_SYSIDLE_NOT;
+		WRITE_ONCE(full_sysidle_state, RCU_SYSIDLE_NOT);
 }
 
 /*
@@ -2925,7 +2935,7 @@ static void rcu_sysidle_cb(struct rcu_head *rhp)
 	smp_mb();  /* grace period precedes setting inuse. */
 
 	rshp = container_of(rhp, struct rcu_sysidle_head, rh);
-	ACCESS_ONCE(rshp->inuse) = 0;
+	WRITE_ONCE(rshp->inuse, 0);
 }
 
 /*
@@ -2936,7 +2946,7 @@ static void rcu_sysidle_cb(struct rcu_head *rhp)
 bool rcu_sys_is_idle(void)
 {
 	static struct rcu_sysidle_head rsh;
-	int rss = ACCESS_ONCE(full_sysidle_state);
+	int rss = READ_ONCE(full_sysidle_state);
 
 	if (WARN_ON_ONCE(smp_processor_id() != tick_do_timer_cpu))
 		return false;
@@ -2964,7 +2974,7 @@ bool rcu_sys_is_idle(void)
 			}
 			rcu_sysidle_report(rcu_state_p, isidle, maxj, false);
 			oldrss = rss;
-			rss = ACCESS_ONCE(full_sysidle_state);
+			rss = READ_ONCE(full_sysidle_state);
 		}
 	}
 
@@ -3048,10 +3058,10 @@ static bool rcu_nohz_full_cpu(struct rcu_state *rsp)
 #ifdef CONFIG_NO_HZ_FULL
 	if (tick_nohz_full_cpu(smp_processor_id()) &&
 	    (!rcu_gp_in_progress(rsp) ||
-	     ULONG_CMP_LT(jiffies, ACCESS_ONCE(rsp->gp_start) + HZ)))
-		return 1;
+	     ULONG_CMP_LT(jiffies, READ_ONCE(rsp->gp_start) + HZ)))
+		return true;
 #endif /* #ifdef CONFIG_NO_HZ_FULL */
-	return 0;
+	return false;
 }
 
 /*
@@ -3077,7 +3087,7 @@ static void rcu_bind_gp_kthread(void)
 static void rcu_dynticks_task_enter(void)
 {
 #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL)
-	ACCESS_ONCE(current->rcu_tasks_idle_cpu) = smp_processor_id();
+	WRITE_ONCE(current->rcu_tasks_idle_cpu, smp_processor_id());
 #endif /* #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) */
 }
 
@@ -3085,6 +3095,6 @@ static void rcu_dynticks_task_enter(void)
 static void rcu_dynticks_task_exit(void)
 {
 #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL)
-	ACCESS_ONCE(current->rcu_tasks_idle_cpu) = -1;
+	WRITE_ONCE(current->rcu_tasks_idle_cpu, -1);
 #endif /* #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) */
 }
diff --git a/kernel/rcu/tree_trace.c b/kernel/rcu/tree_trace.c
index f92361efd0f5..3ea7ffc7d5c4 100644
--- a/kernel/rcu/tree_trace.c
+++ b/kernel/rcu/tree_trace.c
@@ -277,7 +277,7 @@ static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp)
 	seq_printf(m, "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu oqlen=%ld/%ld\n",
 		   rsp->n_force_qs, rsp->n_force_qs_ngp,
 		   rsp->n_force_qs - rsp->n_force_qs_ngp,
-		   ACCESS_ONCE(rsp->n_force_qs_lh), rsp->qlen_lazy, rsp->qlen);
+		   READ_ONCE(rsp->n_force_qs_lh), rsp->qlen_lazy, rsp->qlen);
 	for (rnp = &rsp->node[0]; rnp - &rsp->node[0] < rcu_num_nodes; rnp++) {
 		if (rnp->level != level) {
 			seq_puts(m, "\n");
@@ -323,8 +323,8 @@ static void show_one_rcugp(struct seq_file *m, struct rcu_state *rsp)
 	struct rcu_node *rnp = &rsp->node[0];
 
 	raw_spin_lock_irqsave(&rnp->lock, flags);
-	completed = ACCESS_ONCE(rsp->completed);
-	gpnum = ACCESS_ONCE(rsp->gpnum);
+	completed = READ_ONCE(rsp->completed);
+	gpnum = READ_ONCE(rsp->gpnum);
 	if (completed == gpnum)
 		gpage = 0;
 	else
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 1f133350da01..afaecb7a799a 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -150,14 +150,14 @@ void __rcu_read_unlock(void)
 		barrier();  /* critical section before exit code. */
 		t->rcu_read_lock_nesting = INT_MIN;
 		barrier();  /* assign before ->rcu_read_unlock_special load */
-		if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special.s)))
+		if (unlikely(READ_ONCE(t->rcu_read_unlock_special.s)))
 			rcu_read_unlock_special(t);
 		barrier();  /* ->rcu_read_unlock_special load before assign */
 		t->rcu_read_lock_nesting = 0;
 	}
 #ifdef CONFIG_PROVE_LOCKING
 	{
-		int rrln = ACCESS_ONCE(t->rcu_read_lock_nesting);
+		int rrln = READ_ONCE(t->rcu_read_lock_nesting);
 
 		WARN_ON_ONCE(rrln < 0 && rrln > INT_MIN / 2);
 	}
@@ -389,17 +389,17 @@ module_param(rcu_cpu_stall_timeout, int, 0644);
 
 int rcu_jiffies_till_stall_check(void)
 {
-	int till_stall_check = ACCESS_ONCE(rcu_cpu_stall_timeout);
+	int till_stall_check = READ_ONCE(rcu_cpu_stall_timeout);
 
 	/*
 	 * Limit check must be consistent with the Kconfig limits
 	 * for CONFIG_RCU_CPU_STALL_TIMEOUT.
 	 */
 	if (till_stall_check < 3) {
-		ACCESS_ONCE(rcu_cpu_stall_timeout) = 3;
+		WRITE_ONCE(rcu_cpu_stall_timeout, 3);
 		till_stall_check = 3;
 	} else if (till_stall_check > 300) {
-		ACCESS_ONCE(rcu_cpu_stall_timeout) = 300;
+		WRITE_ONCE(rcu_cpu_stall_timeout, 300);
 		till_stall_check = 300;
 	}
 	return till_stall_check * HZ + RCU_STALL_DELAY_DELTA;
@@ -550,12 +550,12 @@ static void check_holdout_task(struct task_struct *t,
 {
 	int cpu;
 
-	if (!ACCESS_ONCE(t->rcu_tasks_holdout) ||
-	    t->rcu_tasks_nvcsw != ACCESS_ONCE(t->nvcsw) ||
-	    !ACCESS_ONCE(t->on_rq) ||
+	if (!READ_ONCE(t->rcu_tasks_holdout) ||
+	    t->rcu_tasks_nvcsw != READ_ONCE(t->nvcsw) ||
+	    !READ_ONCE(t->on_rq) ||
 	    (IS_ENABLED(CONFIG_NO_HZ_FULL) &&
 	     !is_idle_task(t) && t->rcu_tasks_idle_cpu >= 0)) {
-		ACCESS_ONCE(t->rcu_tasks_holdout) = false;
+		WRITE_ONCE(t->rcu_tasks_holdout, false);
 		list_del_init(&t->rcu_tasks_holdout_list);
 		put_task_struct(t);
 		return;
@@ -639,11 +639,11 @@ static int __noreturn rcu_tasks_kthread(void *arg)
 		 */
 		rcu_read_lock();
 		for_each_process_thread(g, t) {
-			if (t != current && ACCESS_ONCE(t->on_rq) &&
+			if (t != current && READ_ONCE(t->on_rq) &&
 			    !is_idle_task(t)) {
 				get_task_struct(t);
-				t->rcu_tasks_nvcsw = ACCESS_ONCE(t->nvcsw);
-				ACCESS_ONCE(t->rcu_tasks_holdout) = true;
+				t->rcu_tasks_nvcsw = READ_ONCE(t->nvcsw);
+				WRITE_ONCE(t->rcu_tasks_holdout, true);
 				list_add(&t->rcu_tasks_holdout_list,
 					 &rcu_tasks_holdouts);
 			}
@@ -672,7 +672,7 @@ static int __noreturn rcu_tasks_kthread(void *arg)
 			struct task_struct *t1;
 
 			schedule_timeout_interruptible(HZ);
-			rtst = ACCESS_ONCE(rcu_task_stall_timeout);
+			rtst = READ_ONCE(rcu_task_stall_timeout);
 			needreport = rtst > 0 &&
 				     time_after(jiffies, lastreport + rtst);
 			if (needreport)
@@ -728,7 +728,7 @@ static void rcu_spawn_tasks_kthread(void)
 	static struct task_struct *rcu_tasks_kthread_ptr;
 	struct task_struct *t;
 
-	if (ACCESS_ONCE(rcu_tasks_kthread_ptr)) {
+	if (READ_ONCE(rcu_tasks_kthread_ptr)) {
 		smp_mb(); /* Ensure caller sees full kthread. */
 		return;
 	}
@@ -740,7 +740,7 @@ static void rcu_spawn_tasks_kthread(void)
 	t = kthread_run(rcu_tasks_kthread, NULL, "rcu_tasks_kthread");
 	BUG_ON(IS_ERR(t));
 	smp_mb(); /* Ensure others see full kthread. */
-	ACCESS_ONCE(rcu_tasks_kthread_ptr) = t;
+	WRITE_ONCE(rcu_tasks_kthread_ptr, t);
 	mutex_unlock(&rcu_tasks_kthread_mutex);
 }
 
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index 46be87024875..67687973ce80 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -11,7 +11,7 @@ ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
 CFLAGS_core.o := $(PROFILING) -fno-omit-frame-pointer
 endif
 
-obj-y += core.o proc.o clock.o cputime.o
+obj-y += core.o loadavg.o clock.o cputime.o
 obj-y += idle_task.o fair.o rt.o deadline.o stop_task.o
 obj-y += wait.o completion.o idle.o
 obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o
diff --git a/kernel/sched/auto_group.c b/kernel/sched/auto_group.c
index eae160dd669d..750ed601ddf7 100644
--- a/kernel/sched/auto_group.c
+++ b/kernel/sched/auto_group.c
@@ -1,5 +1,3 @@
-#ifdef CONFIG_SCHED_AUTOGROUP
-
 #include "sched.h"
 
 #include <linux/proc_fs.h>
@@ -141,7 +139,7 @@ autogroup_move_group(struct task_struct *p, struct autogroup *ag)
 
 	p->signal->autogroup = autogroup_kref_get(ag);
 
-	if (!ACCESS_ONCE(sysctl_sched_autogroup_enabled))
+	if (!READ_ONCE(sysctl_sched_autogroup_enabled))
 		goto out;
 
 	for_each_thread(p, t)
@@ -249,5 +247,3 @@ int autogroup_path(struct task_group *tg, char *buf, int buflen)
 	return snprintf(buf, buflen, "%s-%ld", "/autogroup", tg->autogroup->id);
 }
 #endif /* CONFIG_SCHED_DEBUG */
-
-#endif /* CONFIG_SCHED_AUTOGROUP */
diff --git a/kernel/sched/auto_group.h b/kernel/sched/auto_group.h
index 8bd047142816..890c95f2587a 100644
--- a/kernel/sched/auto_group.h
+++ b/kernel/sched/auto_group.h
@@ -29,7 +29,7 @@ extern bool task_wants_autogroup(struct task_struct *p, struct task_group *tg);
 static inline struct task_group *
 autogroup_task_group(struct task_struct *p, struct task_group *tg)
 {
-	int enabled = ACCESS_ONCE(sysctl_sched_autogroup_enabled);
+	int enabled = READ_ONCE(sysctl_sched_autogroup_enabled);
 
 	if (enabled && task_wants_autogroup(p, tg))
 		return p->signal->autogroup->tg;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 123673291ffb..c86935a7f1f8 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -90,26 +90,6 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/sched.h>
 
-void start_bandwidth_timer(struct hrtimer *period_timer, ktime_t period)
-{
-	unsigned long delta;
-	ktime_t soft, hard, now;
-
-	for (;;) {
-		if (hrtimer_active(period_timer))
-			break;
-
-		now = hrtimer_cb_get_time(period_timer);
-		hrtimer_forward(period_timer, now, period);
-
-		soft = hrtimer_get_softexpires(period_timer);
-		hard = hrtimer_get_expires(period_timer);
-		delta = ktime_to_ns(ktime_sub(hard, soft));
-		__hrtimer_start_range_ns(period_timer, soft, delta,
-					 HRTIMER_MODE_ABS_PINNED, 0);
-	}
-}
-
 DEFINE_MUTEX(sched_domains_mutex);
 DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
 
@@ -355,12 +335,11 @@ static enum hrtimer_restart hrtick(struct hrtimer *timer)
 
 #ifdef CONFIG_SMP
 
-static int __hrtick_restart(struct rq *rq)
+static void __hrtick_restart(struct rq *rq)
 {
 	struct hrtimer *timer = &rq->hrtick_timer;
-	ktime_t time = hrtimer_get_softexpires(timer);
 
-	return __hrtimer_start_range_ns(timer, time, 0, HRTIMER_MODE_ABS_PINNED, 0);
+	hrtimer_start_expires(timer, HRTIMER_MODE_ABS_PINNED);
 }
 
 /*
@@ -440,8 +419,8 @@ void hrtick_start(struct rq *rq, u64 delay)
 	 * doesn't make sense. Rely on vruntime for fairness.
 	 */
 	delay = max_t(u64, delay, 10000LL);
-	__hrtimer_start_range_ns(&rq->hrtick_timer, ns_to_ktime(delay), 0,
-			HRTIMER_MODE_REL_PINNED, 0);
+	hrtimer_start(&rq->hrtick_timer, ns_to_ktime(delay),
+		      HRTIMER_MODE_REL_PINNED);
 }
 
 static inline void init_hrtick(void)
@@ -511,7 +490,7 @@ static bool set_nr_and_not_polling(struct task_struct *p)
 static bool set_nr_if_polling(struct task_struct *p)
 {
 	struct thread_info *ti = task_thread_info(p);
-	typeof(ti->flags) old, val = ACCESS_ONCE(ti->flags);
+	typeof(ti->flags) old, val = READ_ONCE(ti->flags);
 
 	for (;;) {
 		if (!(val & _TIF_POLLING_NRFLAG))
@@ -541,6 +520,52 @@ static bool set_nr_if_polling(struct task_struct *p)
 #endif
 #endif
 
+void wake_q_add(struct wake_q_head *head, struct task_struct *task)
+{
+	struct wake_q_node *node = &task->wake_q;
+
+	/*
+	 * Atomically grab the task, if ->wake_q is !nil already it means
+	 * its already queued (either by us or someone else) and will get the
+	 * wakeup due to that.
+	 *
+	 * This cmpxchg() implies a full barrier, which pairs with the write
+	 * barrier implied by the wakeup in wake_up_list().
+	 */
+	if (cmpxchg(&node->next, NULL, WAKE_Q_TAIL))
+		return;
+
+	get_task_struct(task);
+
+	/*
+	 * The head is context local, there can be no concurrency.
+	 */
+	*head->lastp = node;
+	head->lastp = &node->next;
+}
+
+void wake_up_q(struct wake_q_head *head)
+{
+	struct wake_q_node *node = head->first;
+
+	while (node != WAKE_Q_TAIL) {
+		struct task_struct *task;
+
+		task = container_of(node, struct task_struct, wake_q);
+		BUG_ON(!task);
+		/* task can safely be re-inserted now */
+		node = node->next;
+		task->wake_q.next = NULL;
+
+		/*
+		 * wake_up_process() implies a wmb() to pair with the queueing
+		 * in wake_q_add() so as not to miss wakeups.
+		 */
+		wake_up_process(task);
+		put_task_struct(task);
+	}
+}
+
 /*
  * resched_curr - mark rq's current task 'to be rescheduled now'.
  *
@@ -593,13 +618,12 @@ void resched_cpu(int cpu)
  * selecting an idle cpu will add more delays to the timers than intended
  * (as that cpu's timer base may not be uptodate wrt jiffies etc).
  */
-int get_nohz_timer_target(int pinned)
+int get_nohz_timer_target(void)
 {
-	int cpu = smp_processor_id();
-	int i;
+	int i, cpu = smp_processor_id();
 	struct sched_domain *sd;
 
-	if (pinned || !get_sysctl_timer_migration() || !idle_cpu(cpu))
+	if (!idle_cpu(cpu))
 		return cpu;
 
 	rcu_read_lock();
@@ -1049,7 +1073,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 		if (p->sched_class->migrate_task_rq)
 			p->sched_class->migrate_task_rq(p, new_cpu);
 		p->se.nr_migrations++;
-		perf_sw_event_sched(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 0);
+		perf_event_task_migrate(p);
 	}
 
 	__set_task_cpu(p, new_cpu);
@@ -2105,12 +2129,15 @@ void wake_up_new_task(struct task_struct *p)
 
 #ifdef CONFIG_PREEMPT_NOTIFIERS
 
+static struct static_key preempt_notifier_key = STATIC_KEY_INIT_FALSE;
+
 /**
  * preempt_notifier_register - tell me when current is being preempted & rescheduled
  * @notifier: notifier struct to register
  */
 void preempt_notifier_register(struct preempt_notifier *notifier)
 {
+	static_key_slow_inc(&preempt_notifier_key);
 	hlist_add_head(&notifier->link, &current->preempt_notifiers);
 }
 EXPORT_SYMBOL_GPL(preempt_notifier_register);
@@ -2119,15 +2146,16 @@ EXPORT_SYMBOL_GPL(preempt_notifier_register);
  * preempt_notifier_unregister - no longer interested in preemption notifications
  * @notifier: notifier struct to unregister
  *
- * This is safe to call from within a preemption notifier.
+ * This is *not* safe to call from within a preemption notifier.
  */
 void preempt_notifier_unregister(struct preempt_notifier *notifier)
 {
 	hlist_del(&notifier->link);
+	static_key_slow_dec(&preempt_notifier_key);
 }
 EXPORT_SYMBOL_GPL(preempt_notifier_unregister);
 
-static void fire_sched_in_preempt_notifiers(struct task_struct *curr)
+static void __fire_sched_in_preempt_notifiers(struct task_struct *curr)
 {
 	struct preempt_notifier *notifier;
 
@@ -2135,9 +2163,15 @@ static void fire_sched_in_preempt_notifiers(struct task_struct *curr)
 		notifier->ops->sched_in(notifier, raw_smp_processor_id());
 }
 
+static __always_inline void fire_sched_in_preempt_notifiers(struct task_struct *curr)
+{
+	if (static_key_false(&preempt_notifier_key))
+		__fire_sched_in_preempt_notifiers(curr);
+}
+
 static void
-fire_sched_out_preempt_notifiers(struct task_struct *curr,
-				 struct task_struct *next)
+__fire_sched_out_preempt_notifiers(struct task_struct *curr,
+				   struct task_struct *next)
 {
 	struct preempt_notifier *notifier;
 
@@ -2145,13 +2179,21 @@ fire_sched_out_preempt_notifiers(struct task_struct *curr,
 		notifier->ops->sched_out(notifier, next);
 }
 
+static __always_inline void
+fire_sched_out_preempt_notifiers(struct task_struct *curr,
+				 struct task_struct *next)
+{
+	if (static_key_false(&preempt_notifier_key))
+		__fire_sched_out_preempt_notifiers(curr, next);
+}
+
 #else /* !CONFIG_PREEMPT_NOTIFIERS */
 
-static void fire_sched_in_preempt_notifiers(struct task_struct *curr)
+static inline void fire_sched_in_preempt_notifiers(struct task_struct *curr)
 {
 }
 
-static void
+static inline void
 fire_sched_out_preempt_notifiers(struct task_struct *curr,
 				 struct task_struct *next)
 {
@@ -2332,7 +2374,6 @@ context_switch(struct rq *rq, struct task_struct *prev,
 	 */
 	spin_release(&rq->lock.dep_map, 1, _THIS_IP_);
 
-	context_tracking_task_switch(prev, next);
 	/* Here we just switch the register state and the stack. */
 	switch_to(prev, next, prev);
 	barrier();
@@ -2397,9 +2438,9 @@ unsigned long nr_iowait_cpu(int cpu)
 
 void get_iowait_load(unsigned long *nr_waiters, unsigned long *load)
 {
-	struct rq *this = this_rq();
-	*nr_waiters = atomic_read(&this->nr_iowait);
-	*load = this->cpu_load[0];
+	struct rq *rq = this_rq();
+	*nr_waiters = atomic_read(&rq->nr_iowait);
+	*load = rq->load.weight;
 }
 
 #ifdef CONFIG_SMP
@@ -2497,6 +2538,7 @@ void scheduler_tick(void)
 	update_rq_clock(rq);
 	curr->sched_class->task_tick(rq, curr, 0);
 	update_cpu_load_active(rq);
+	calc_global_load_tick(rq);
 	raw_spin_unlock(&rq->lock);
 
 	perf_event_task_tick();
@@ -2525,7 +2567,7 @@ void scheduler_tick(void)
 u64 scheduler_tick_max_deferment(void)
 {
 	struct rq *rq = this_rq();
-	unsigned long next, now = ACCESS_ONCE(jiffies);
+	unsigned long next, now = READ_ONCE(jiffies);
 
 	next = rq->last_sched_tick + HZ;
 
@@ -2726,9 +2768,7 @@ again:
  *          - return from syscall or exception to user-space
  *          - return from interrupt-handler to user-space
  *
- * WARNING: all callers must re-check need_resched() afterward and reschedule
- * accordingly in case an event triggered the need for rescheduling (such as
- * an interrupt waking up a task) while preemption was disabled in __schedule().
+ * WARNING: must be called with preemption disabled!
  */
 static void __sched __schedule(void)
 {
@@ -2737,7 +2777,6 @@ static void __sched __schedule(void)
 	struct rq *rq;
 	int cpu;
 
-	preempt_disable();
 	cpu = smp_processor_id();
 	rq = cpu_rq(cpu);
 	rcu_note_context_switch();
@@ -2801,8 +2840,6 @@ static void __sched __schedule(void)
 		raw_spin_unlock_irq(&rq->lock);
 
 	post_schedule(rq);
-
-	sched_preempt_enable_no_resched();
 }
 
 static inline void sched_submit_work(struct task_struct *tsk)
@@ -2823,7 +2860,9 @@ asmlinkage __visible void __sched schedule(void)
 
 	sched_submit_work(tsk);
 	do {
+		preempt_disable();
 		__schedule();
+		sched_preempt_enable_no_resched();
 	} while (need_resched());
 }
 EXPORT_SYMBOL(schedule);
@@ -2862,15 +2901,14 @@ void __sched schedule_preempt_disabled(void)
 static void __sched notrace preempt_schedule_common(void)
 {
 	do {
-		__preempt_count_add(PREEMPT_ACTIVE);
+		preempt_active_enter();
 		__schedule();
-		__preempt_count_sub(PREEMPT_ACTIVE);
+		preempt_active_exit();
 
 		/*
 		 * Check again in case we missed a preemption opportunity
 		 * between schedule and now.
 		 */
-		barrier();
 	} while (need_resched());
 }
 
@@ -2894,9 +2932,8 @@ asmlinkage __visible void __sched notrace preempt_schedule(void)
 NOKPROBE_SYMBOL(preempt_schedule);
 EXPORT_SYMBOL(preempt_schedule);
 
-#ifdef CONFIG_CONTEXT_TRACKING
 /**
- * preempt_schedule_context - preempt_schedule called by tracing
+ * preempt_schedule_notrace - preempt_schedule called by tracing
  *
  * The tracing infrastructure uses preempt_enable_notrace to prevent
  * recursion and tracing preempt enabling caused by the tracing
@@ -2909,7 +2946,7 @@ EXPORT_SYMBOL(preempt_schedule);
  * instead of preempt_schedule() to exit user context if needed before
  * calling the scheduler.
  */
-asmlinkage __visible void __sched notrace preempt_schedule_context(void)
+asmlinkage __visible void __sched notrace preempt_schedule_notrace(void)
 {
 	enum ctx_state prev_ctx;
 
@@ -2917,7 +2954,13 @@ asmlinkage __visible void __sched notrace preempt_schedule_context(void)
 		return;
 
 	do {
-		__preempt_count_add(PREEMPT_ACTIVE);
+		/*
+		 * Use raw __prempt_count() ops that don't call function.
+		 * We can't call functions before disabling preemption which
+		 * disarm preemption tracing recursions.
+		 */
+		__preempt_count_add(PREEMPT_ACTIVE + PREEMPT_DISABLE_OFFSET);
+		barrier();
 		/*
 		 * Needs preempt disabled in case user_exit() is traced
 		 * and the tracer calls preempt_enable_notrace() causing
@@ -2927,12 +2970,11 @@ asmlinkage __visible void __sched notrace preempt_schedule_context(void)
 		__schedule();
 		exception_exit(prev_ctx);
 
-		__preempt_count_sub(PREEMPT_ACTIVE);
 		barrier();
+		__preempt_count_sub(PREEMPT_ACTIVE + PREEMPT_DISABLE_OFFSET);
 	} while (need_resched());
 }
-EXPORT_SYMBOL_GPL(preempt_schedule_context);
-#endif /* CONFIG_CONTEXT_TRACKING */
+EXPORT_SYMBOL_GPL(preempt_schedule_notrace);
 
 #endif /* CONFIG_PREEMPT */
 
@@ -2952,17 +2994,11 @@ asmlinkage __visible void __sched preempt_schedule_irq(void)
 	prev_state = exception_enter();
 
 	do {
-		__preempt_count_add(PREEMPT_ACTIVE);
+		preempt_active_enter();
 		local_irq_enable();
 		__schedule();
 		local_irq_disable();
-		__preempt_count_sub(PREEMPT_ACTIVE);
-
-		/*
-		 * Check again in case we missed a preemption opportunity
-		 * between schedule and now.
-		 */
-		barrier();
+		preempt_active_exit();
 	} while (need_resched());
 
 	exception_exit(prev_state);
@@ -3040,7 +3076,6 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 		if (!dl_prio(p->normal_prio) ||
 		    (pi_task && dl_entity_preempt(&pi_task->dl, &p->dl))) {
 			p->dl.dl_boosted = 1;
-			p->dl.dl_throttled = 0;
 			enqueue_flag = ENQUEUE_REPLENISH;
 		} else
 			p->dl.dl_boosted = 0;
@@ -5314,7 +5349,7 @@ static struct notifier_block migration_notifier = {
 	.priority = CPU_PRI_MIGRATION,
 };
 
-static void __cpuinit set_cpu_rq_start_time(void)
+static void set_cpu_rq_start_time(void)
 {
 	int cpu = smp_processor_id();
 	struct rq *rq = cpu_rq(cpu);
@@ -7032,6 +7067,9 @@ void __init sched_init_smp(void)
 	alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL);
 	alloc_cpumask_var(&fallback_doms, GFP_KERNEL);
 
+	/* nohz_full won't take effect without isolating the cpus. */
+	tick_nohz_full_add_cpus_to(cpu_isolated_map);
+
 	sched_init_numa();
 
 	/*
@@ -7068,8 +7106,6 @@ void __init sched_init_smp(void)
 }
 #endif /* CONFIG_SMP */
 
-const_debug unsigned int sysctl_timer_migration = 1;
-
 int in_sched_functions(unsigned long addr)
 {
 	return in_lock_functions(addr) ||
@@ -7734,11 +7770,11 @@ static long sched_group_rt_runtime(struct task_group *tg)
 	return rt_runtime_us;
 }
 
-static int sched_group_set_rt_period(struct task_group *tg, long rt_period_us)
+static int sched_group_set_rt_period(struct task_group *tg, u64 rt_period_us)
 {
 	u64 rt_runtime, rt_period;
 
-	rt_period = (u64)rt_period_us * NSEC_PER_USEC;
+	rt_period = rt_period_us * NSEC_PER_USEC;
 	rt_runtime = tg->rt_bandwidth.rt_runtime;
 
 	return tg_set_rt_bandwidth(tg, rt_period, rt_runtime);
@@ -8105,10 +8141,8 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota)
 
 	__refill_cfs_bandwidth_runtime(cfs_b);
 	/* restart the period timer (if active) to handle new period expiry */
-	if (runtime_enabled && cfs_b->timer_active) {
-		/* force a reprogram */
-		__start_cfs_bandwidth(cfs_b, true);
-	}
+	if (runtime_enabled)
+		start_cfs_bandwidth(cfs_b);
 	raw_spin_unlock_irq(&cfs_b->lock);
 
 	for_each_online_cpu(i) {
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 8394b1ee600c..f5a64ffad176 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -567,7 +567,7 @@ static void cputime_advance(cputime_t *counter, cputime_t new)
 {
 	cputime_t old;
 
-	while (new > (old = ACCESS_ONCE(*counter)))
+	while (new > (old = READ_ONCE(*counter)))
 		cmpxchg_cputime(counter, old, new);
 }
 
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 5e95145088fd..eac20c557a55 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -503,8 +503,6 @@ static int start_dl_timer(struct sched_dl_entity *dl_se, bool boosted)
 	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
 	struct rq *rq = rq_of_dl_rq(dl_rq);
 	ktime_t now, act;
-	ktime_t soft, hard;
-	unsigned long range;
 	s64 delta;
 
 	if (boosted)
@@ -527,15 +525,9 @@ static int start_dl_timer(struct sched_dl_entity *dl_se, bool boosted)
 	if (ktime_us_delta(act, now) < 0)
 		return 0;
 
-	hrtimer_set_expires(&dl_se->dl_timer, act);
+	hrtimer_start(&dl_se->dl_timer, act, HRTIMER_MODE_ABS);
 
-	soft = hrtimer_get_softexpires(&dl_se->dl_timer);
-	hard = hrtimer_get_expires(&dl_se->dl_timer);
-	range = ktime_to_ns(ktime_sub(hard, soft));
-	__hrtimer_start_range_ns(&dl_se->dl_timer, soft,
-				 range, HRTIMER_MODE_ABS, 0);
-
-	return hrtimer_active(&dl_se->dl_timer);
+	return 1;
 }
 
 /*
@@ -640,7 +632,7 @@ void init_dl_task_timer(struct sched_dl_entity *dl_se)
 }
 
 static
-int dl_runtime_exceeded(struct rq *rq, struct sched_dl_entity *dl_se)
+int dl_runtime_exceeded(struct sched_dl_entity *dl_se)
 {
 	return (dl_se->runtime <= 0);
 }
@@ -684,7 +676,7 @@ static void update_curr_dl(struct rq *rq)
 	sched_rt_avg_update(rq, delta_exec);
 
 	dl_se->runtime -= dl_se->dl_yielded ? 0 : delta_exec;
-	if (dl_runtime_exceeded(rq, dl_se)) {
+	if (dl_runtime_exceeded(dl_se)) {
 		dl_se->dl_throttled = 1;
 		__dequeue_task_dl(rq, curr, 0);
 		if (unlikely(!start_dl_timer(dl_se, curr->dl.dl_boosted)))
@@ -995,7 +987,7 @@ select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags)
 	rq = cpu_rq(cpu);
 
 	rcu_read_lock();
-	curr = ACCESS_ONCE(rq->curr); /* unlocked access */
+	curr = READ_ONCE(rq->curr); /* unlocked access */
 
 	/*
 	 * If we are dealing with a -deadline task, we must
@@ -1012,7 +1004,9 @@ select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags)
 	    (p->nr_cpus_allowed > 1)) {
 		int target = find_later_rq(p);
 
-		if (target != -1)
+		if (target != -1 &&
+				dl_time_before(p->dl.deadline,
+					cpu_rq(target)->dl.earliest_dl.curr))
 			cpu = target;
 	}
 	rcu_read_unlock();
@@ -1230,6 +1224,32 @@ next_node:
 	return NULL;
 }
 
+/*
+ * Return the earliest pushable rq's task, which is suitable to be executed
+ * on the CPU, NULL otherwise:
+ */
+static struct task_struct *pick_earliest_pushable_dl_task(struct rq *rq, int cpu)
+{
+	struct rb_node *next_node = rq->dl.pushable_dl_tasks_leftmost;
+	struct task_struct *p = NULL;
+
+	if (!has_pushable_dl_tasks(rq))
+		return NULL;
+
+next_node:
+	if (next_node) {
+		p = rb_entry(next_node, struct task_struct, pushable_dl_tasks);
+
+		if (pick_dl_task(rq, p, cpu))
+			return p;
+
+		next_node = rb_next(next_node);
+		goto next_node;
+	}
+
+	return NULL;
+}
+
 static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask_dl);
 
 static int find_later_rq(struct task_struct *task)
@@ -1333,6 +1353,17 @@ static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq)
 
 		later_rq = cpu_rq(cpu);
 
+		if (!dl_time_before(task->dl.deadline,
+					later_rq->dl.earliest_dl.curr)) {
+			/*
+			 * Target rq has tasks of equal or earlier deadline,
+			 * retrying does not release any lock and is unlikely
+			 * to yield a different result.
+			 */
+			later_rq = NULL;
+			break;
+		}
+
 		/* Retry if something changed. */
 		if (double_lock_balance(rq, later_rq)) {
 			if (unlikely(task_rq(task) != rq ||
@@ -1514,7 +1545,7 @@ static int pull_dl_task(struct rq *this_rq)
 		if (src_rq->dl.dl_nr_running <= 1)
 			goto skip;
 
-		p = pick_next_earliest_dl_task(src_rq, this_cpu);
+		p = pick_earliest_pushable_dl_task(src_rq, this_cpu);
 
 		/*
 		 * We found a task to be pulled if:
@@ -1659,7 +1690,7 @@ static void rq_offline_dl(struct rq *rq)
 	cpudl_clear_freecpu(&rq->rd->cpudl, rq->cpu);
 }
 
-void init_sched_dl_class(void)
+void __init init_sched_dl_class(void)
 {
 	unsigned int i;
 
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index a245c1fc6f0a..315c68e015d9 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -132,12 +132,14 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
 		p->prio);
 #ifdef CONFIG_SCHEDSTATS
 	SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld",
-		SPLIT_NS(p->se.vruntime),
+		SPLIT_NS(p->se.statistics.wait_sum),
 		SPLIT_NS(p->se.sum_exec_runtime),
 		SPLIT_NS(p->se.statistics.sum_sleep_runtime));
 #else
-	SEQ_printf(m, "%15Ld %15Ld %15Ld.%06ld %15Ld.%06ld %15Ld.%06ld",
-		0LL, 0LL, 0LL, 0L, 0LL, 0L, 0LL, 0L);
+	SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld",
+		0LL, 0L,
+		SPLIT_NS(p->se.sum_exec_runtime),
+		0LL, 0L);
 #endif
 #ifdef CONFIG_NUMA_BALANCING
 	SEQ_printf(m, " %d", task_node(p));
@@ -156,7 +158,7 @@ static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu)
 	SEQ_printf(m,
 	"\nrunnable tasks:\n"
 	"            task   PID         tree-key  switches  prio"
-	"     exec-runtime         sum-exec        sum-sleep\n"
+	"     wait-time             sum-exec        sum-sleep\n"
 	"------------------------------------------------------"
 	"----------------------------------------------------\n");
 
@@ -230,8 +232,6 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 #endif
 #endif
 #ifdef CONFIG_CFS_BANDWIDTH
-	SEQ_printf(m, "  .%-30s: %d\n", "tg->cfs_bandwidth.timer_active",
-			cfs_rq->tg->cfs_bandwidth.timer_active);
 	SEQ_printf(m, "  .%-30s: %d\n", "throttled",
 			cfs_rq->throttled);
 	SEQ_printf(m, "  .%-30s: %d\n", "throttle_count",
@@ -582,6 +582,7 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
 	nr_switches = p->nvcsw + p->nivcsw;
 
 #ifdef CONFIG_SCHEDSTATS
+	PN(se.statistics.sum_sleep_runtime);
 	PN(se.statistics.wait_start);
 	PN(se.statistics.sleep_start);
 	PN(se.statistics.block_start);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index c2980e8733bc..40a7fcbf491e 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -141,9 +141,9 @@ static inline void update_load_set(struct load_weight *lw, unsigned long w)
  *
  * This idea comes from the SD scheduler of Con Kolivas:
  */
-static int get_update_sysctl_factor(void)
+static unsigned int get_update_sysctl_factor(void)
 {
-	unsigned int cpus = min_t(int, num_online_cpus(), 8);
+	unsigned int cpus = min_t(unsigned int, num_online_cpus(), 8);
 	unsigned int factor;
 
 	switch (sysctl_sched_tunable_scaling) {
@@ -576,7 +576,7 @@ int sched_proc_update_handler(struct ctl_table *table, int write,
 		loff_t *ppos)
 {
 	int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
-	int factor = get_update_sysctl_factor();
+	unsigned int factor = get_update_sysctl_factor();
 
 	if (ret || !write)
 		return ret;
@@ -834,7 +834,7 @@ static unsigned int task_nr_scan_windows(struct task_struct *p)
 
 static unsigned int task_scan_min(struct task_struct *p)
 {
-	unsigned int scan_size = ACCESS_ONCE(sysctl_numa_balancing_scan_size);
+	unsigned int scan_size = READ_ONCE(sysctl_numa_balancing_scan_size);
 	unsigned int scan, floor;
 	unsigned int windows = 1;
 
@@ -1198,11 +1198,9 @@ static void task_numa_assign(struct task_numa_env *env,
 static bool load_too_imbalanced(long src_load, long dst_load,
 				struct task_numa_env *env)
 {
+	long imb, old_imb;
+	long orig_src_load, orig_dst_load;
 	long src_capacity, dst_capacity;
-	long orig_src_load;
-	long load_a, load_b;
-	long moved_load;
-	long imb;
 
 	/*
 	 * The load is corrected for the CPU capacity available on each node.
@@ -1215,39 +1213,30 @@ static bool load_too_imbalanced(long src_load, long dst_load,
 	dst_capacity = env->dst_stats.compute_capacity;
 
 	/* We care about the slope of the imbalance, not the direction. */
-	load_a = dst_load;
-	load_b = src_load;
-	if (load_a < load_b)
-		swap(load_a, load_b);
+	if (dst_load < src_load)
+		swap(dst_load, src_load);
 
 	/* Is the difference below the threshold? */
-	imb = load_a * src_capacity * 100 -
-		load_b * dst_capacity * env->imbalance_pct;
+	imb = dst_load * src_capacity * 100 -
+	      src_load * dst_capacity * env->imbalance_pct;
 	if (imb <= 0)
 		return false;
 
 	/*
 	 * The imbalance is above the allowed threshold.
-	 * Allow a move that brings us closer to a balanced situation,
-	 * without moving things past the point of balance.
+	 * Compare it with the old imbalance.
 	 */
 	orig_src_load = env->src_stats.load;
+	orig_dst_load = env->dst_stats.load;
 
-	/*
-	 * In a task swap, there will be one load moving from src to dst,
-	 * and another moving back. This is the net sum of both moves.
-	 * A simple task move will always have a positive value.
-	 * Allow the move if it brings the system closer to a balanced
-	 * situation, without crossing over the balance point.
-	 */
-	moved_load = orig_src_load - src_load;
+	if (orig_dst_load < orig_src_load)
+		swap(orig_dst_load, orig_src_load);
 
-	if (moved_load > 0)
-		/* Moving src -> dst. Did we overshoot balance? */
-		return src_load * dst_capacity < dst_load * src_capacity;
-	else
-		/* Moving dst -> src. Did we overshoot balance? */
-		return dst_load * src_capacity < src_load * dst_capacity;
+	old_imb = orig_dst_load * src_capacity * 100 -
+		  orig_src_load * dst_capacity * env->imbalance_pct;
+
+	/* Would this change make things worse? */
+	return (imb > old_imb);
 }
 
 /*
@@ -1409,6 +1398,30 @@ static void task_numa_find_cpu(struct task_numa_env *env,
 	}
 }
 
+/* Only move tasks to a NUMA node less busy than the current node. */
+static bool numa_has_capacity(struct task_numa_env *env)
+{
+	struct numa_stats *src = &env->src_stats;
+	struct numa_stats *dst = &env->dst_stats;
+
+	if (src->has_free_capacity && !dst->has_free_capacity)
+		return false;
+
+	/*
+	 * Only consider a task move if the source has a higher load
+	 * than the destination, corrected for CPU capacity on each node.
+	 *
+	 *      src->load                dst->load
+	 * --------------------- vs ---------------------
+	 * src->compute_capacity    dst->compute_capacity
+	 */
+	if (src->load * dst->compute_capacity >
+	    dst->load * src->compute_capacity)
+		return true;
+
+	return false;
+}
+
 static int task_numa_migrate(struct task_struct *p)
 {
 	struct task_numa_env env = {
@@ -1463,7 +1476,8 @@ static int task_numa_migrate(struct task_struct *p)
 	update_numa_stats(&env.dst_stats, env.dst_nid);
 
 	/* Try to find a spot on the preferred nid. */
-	task_numa_find_cpu(&env, taskimp, groupimp);
+	if (numa_has_capacity(&env))
+		task_numa_find_cpu(&env, taskimp, groupimp);
 
 	/*
 	 * Look at other nodes in these cases:
@@ -1494,7 +1508,8 @@ static int task_numa_migrate(struct task_struct *p)
 			env.dist = dist;
 			env.dst_nid = nid;
 			update_numa_stats(&env.dst_stats, env.dst_nid);
-			task_numa_find_cpu(&env, taskimp, groupimp);
+			if (numa_has_capacity(&env))
+				task_numa_find_cpu(&env, taskimp, groupimp);
 		}
 	}
 
@@ -1794,7 +1809,12 @@ static void task_numa_placement(struct task_struct *p)
 	u64 runtime, period;
 	spinlock_t *group_lock = NULL;
 
-	seq = ACCESS_ONCE(p->mm->numa_scan_seq);
+	/*
+	 * The p->mm->numa_scan_seq field gets updated without
+	 * exclusive access. Use READ_ONCE() here to ensure
+	 * that the field is read in a single access:
+	 */
+	seq = READ_ONCE(p->mm->numa_scan_seq);
 	if (p->numa_scan_seq == seq)
 		return;
 	p->numa_scan_seq = seq;
@@ -1938,7 +1958,7 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags,
 	}
 
 	rcu_read_lock();
-	tsk = ACCESS_ONCE(cpu_rq(cpu)->curr);
+	tsk = READ_ONCE(cpu_rq(cpu)->curr);
 
 	if (!cpupid_match_pid(tsk, cpupid))
 		goto no_join;
@@ -2107,7 +2127,15 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags)
 
 static void reset_ptenuma_scan(struct task_struct *p)
 {
-	ACCESS_ONCE(p->mm->numa_scan_seq)++;
+	/*
+	 * We only did a read acquisition of the mmap sem, so
+	 * p->mm->numa_scan_seq is written to without exclusive access
+	 * and the update is not guaranteed to be atomic. That's not
+	 * much of an issue though, since this is just used for
+	 * statistical sampling. Use READ_ONCE/WRITE_ONCE, which are not
+	 * expensive, to avoid any form of compiler optimizations:
+	 */
+	WRITE_ONCE(p->mm->numa_scan_seq, READ_ONCE(p->mm->numa_scan_seq) + 1);
 	p->mm->numa_scan_offset = 0;
 }
 
@@ -3476,16 +3504,7 @@ static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq)
 	if (cfs_b->quota == RUNTIME_INF)
 		amount = min_amount;
 	else {
-		/*
-		 * If the bandwidth pool has become inactive, then at least one
-		 * period must have elapsed since the last consumption.
-		 * Refresh the global state and ensure bandwidth timer becomes
-		 * active.
-		 */
-		if (!cfs_b->timer_active) {
-			__refill_cfs_bandwidth_runtime(cfs_b);
-			__start_cfs_bandwidth(cfs_b, false);
-		}
+		start_cfs_bandwidth(cfs_b);
 
 		if (cfs_b->runtime > 0) {
 			amount = min(cfs_b->runtime, min_amount);
@@ -3634,6 +3653,7 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq)
 	struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
 	struct sched_entity *se;
 	long task_delta, dequeue = 1;
+	bool empty;
 
 	se = cfs_rq->tg->se[cpu_of(rq_of(cfs_rq))];
 
@@ -3663,13 +3683,21 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq)
 	cfs_rq->throttled = 1;
 	cfs_rq->throttled_clock = rq_clock(rq);
 	raw_spin_lock(&cfs_b->lock);
+	empty = list_empty(&cfs_rq->throttled_list);
+
 	/*
 	 * Add to the _head_ of the list, so that an already-started
 	 * distribute_cfs_runtime will not see us
 	 */
 	list_add_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq);
-	if (!cfs_b->timer_active)
-		__start_cfs_bandwidth(cfs_b, false);
+
+	/*
+	 * If we're the first throttled task, make sure the bandwidth
+	 * timer is running.
+	 */
+	if (empty)
+		start_cfs_bandwidth(cfs_b);
+
 	raw_spin_unlock(&cfs_b->lock);
 }
 
@@ -3784,13 +3812,6 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun)
 	if (cfs_b->idle && !throttled)
 		goto out_deactivate;
 
-	/*
-	 * if we have relooped after returning idle once, we need to update our
-	 * status as actually running, so that other cpus doing
-	 * __start_cfs_bandwidth will stop trying to cancel us.
-	 */
-	cfs_b->timer_active = 1;
-
 	__refill_cfs_bandwidth_runtime(cfs_b);
 
 	if (!throttled) {
@@ -3835,7 +3856,6 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun)
 	return 0;
 
 out_deactivate:
-	cfs_b->timer_active = 0;
 	return 1;
 }
 
@@ -3850,7 +3870,7 @@ static const u64 cfs_bandwidth_slack_period = 5 * NSEC_PER_MSEC;
  * Are we near the end of the current quota period?
  *
  * Requires cfs_b->lock for hrtimer_expires_remaining to be safe against the
- * hrtimer base being cleared by __hrtimer_start_range_ns. In the case of
+ * hrtimer base being cleared by hrtimer_start. In the case of
  * migrate_hrtimers, base is never cleared, so we are fine.
  */
 static int runtime_refresh_within(struct cfs_bandwidth *cfs_b, u64 min_expire)
@@ -3878,8 +3898,9 @@ static void start_cfs_slack_bandwidth(struct cfs_bandwidth *cfs_b)
 	if (runtime_refresh_within(cfs_b, min_left))
 		return;
 
-	start_bandwidth_timer(&cfs_b->slack_timer,
-				ns_to_ktime(cfs_bandwidth_slack_period));
+	hrtimer_start(&cfs_b->slack_timer,
+			ns_to_ktime(cfs_bandwidth_slack_period),
+			HRTIMER_MODE_REL);
 }
 
 /* we know any runtime found here is valid as update_curr() precedes return */
@@ -3999,6 +4020,7 @@ static enum hrtimer_restart sched_cfs_slack_timer(struct hrtimer *timer)
 {
 	struct cfs_bandwidth *cfs_b =
 		container_of(timer, struct cfs_bandwidth, slack_timer);
+
 	do_sched_cfs_slack_timer(cfs_b);
 
 	return HRTIMER_NORESTART;
@@ -4008,20 +4030,19 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
 {
 	struct cfs_bandwidth *cfs_b =
 		container_of(timer, struct cfs_bandwidth, period_timer);
-	ktime_t now;
 	int overrun;
 	int idle = 0;
 
 	raw_spin_lock(&cfs_b->lock);
 	for (;;) {
-		now = hrtimer_cb_get_time(timer);
-		overrun = hrtimer_forward(timer, now, cfs_b->period);
-
+		overrun = hrtimer_forward_now(timer, cfs_b->period);
 		if (!overrun)
 			break;
 
 		idle = do_sched_cfs_period_timer(cfs_b, overrun);
 	}
+	if (idle)
+		cfs_b->period_active = 0;
 	raw_spin_unlock(&cfs_b->lock);
 
 	return idle ? HRTIMER_NORESTART : HRTIMER_RESTART;
@@ -4035,7 +4056,7 @@ void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
 	cfs_b->period = ns_to_ktime(default_cfs_period());
 
 	INIT_LIST_HEAD(&cfs_b->throttled_cfs_rq);
-	hrtimer_init(&cfs_b->period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	hrtimer_init(&cfs_b->period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED);
 	cfs_b->period_timer.function = sched_cfs_period_timer;
 	hrtimer_init(&cfs_b->slack_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	cfs_b->slack_timer.function = sched_cfs_slack_timer;
@@ -4047,28 +4068,15 @@ static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq)
 	INIT_LIST_HEAD(&cfs_rq->throttled_list);
 }
 
-/* requires cfs_b->lock, may release to reprogram timer */
-void __start_cfs_bandwidth(struct cfs_bandwidth *cfs_b, bool force)
+void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
 {
-	/*
-	 * The timer may be active because we're trying to set a new bandwidth
-	 * period or because we're racing with the tear-down path
-	 * (timer_active==0 becomes visible before the hrtimer call-back
-	 * terminates).  In either case we ensure that it's re-programmed
-	 */
-	while (unlikely(hrtimer_active(&cfs_b->period_timer)) &&
-	       hrtimer_try_to_cancel(&cfs_b->period_timer) < 0) {
-		/* bounce the lock to allow do_sched_cfs_period_timer to run */
-		raw_spin_unlock(&cfs_b->lock);
-		cpu_relax();
-		raw_spin_lock(&cfs_b->lock);
-		/* if someone else restarted the timer then we're done */
-		if (!force && cfs_b->timer_active)
-			return;
-	}
+	lockdep_assert_held(&cfs_b->lock);
 
-	cfs_b->timer_active = 1;
-	start_bandwidth_timer(&cfs_b->period_timer, cfs_b->period);
+	if (!cfs_b->period_active) {
+		cfs_b->period_active = 1;
+		hrtimer_forward_now(&cfs_b->period_timer, cfs_b->period);
+		hrtimer_start_expires(&cfs_b->period_timer, HRTIMER_MODE_ABS_PINNED);
+	}
 }
 
 static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
@@ -4323,6 +4331,189 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 }
 
 #ifdef CONFIG_SMP
+
+/*
+ * per rq 'load' arrray crap; XXX kill this.
+ */
+
+/*
+ * The exact cpuload at various idx values, calculated at every tick would be
+ * load = (2^idx - 1) / 2^idx * load + 1 / 2^idx * cur_load
+ *
+ * If a cpu misses updates for n-1 ticks (as it was idle) and update gets called
+ * on nth tick when cpu may be busy, then we have:
+ * load = ((2^idx - 1) / 2^idx)^(n-1) * load
+ * load = (2^idx - 1) / 2^idx) * load + 1 / 2^idx * cur_load
+ *
+ * decay_load_missed() below does efficient calculation of
+ * load = ((2^idx - 1) / 2^idx)^(n-1) * load
+ * avoiding 0..n-1 loop doing load = ((2^idx - 1) / 2^idx) * load
+ *
+ * The calculation is approximated on a 128 point scale.
+ * degrade_zero_ticks is the number of ticks after which load at any
+ * particular idx is approximated to be zero.
+ * degrade_factor is a precomputed table, a row for each load idx.
+ * Each column corresponds to degradation factor for a power of two ticks,
+ * based on 128 point scale.
+ * Example:
+ * row 2, col 3 (=12) says that the degradation at load idx 2 after
+ * 8 ticks is 12/128 (which is an approximation of exact factor 3^8/4^8).
+ *
+ * With this power of 2 load factors, we can degrade the load n times
+ * by looking at 1 bits in n and doing as many mult/shift instead of
+ * n mult/shifts needed by the exact degradation.
+ */
+#define DEGRADE_SHIFT		7
+static const unsigned char
+		degrade_zero_ticks[CPU_LOAD_IDX_MAX] = {0, 8, 32, 64, 128};
+static const unsigned char
+		degrade_factor[CPU_LOAD_IDX_MAX][DEGRADE_SHIFT + 1] = {
+					{0, 0, 0, 0, 0, 0, 0, 0},
+					{64, 32, 8, 0, 0, 0, 0, 0},
+					{96, 72, 40, 12, 1, 0, 0},
+					{112, 98, 75, 43, 15, 1, 0},
+					{120, 112, 98, 76, 45, 16, 2} };
+
+/*
+ * Update cpu_load for any missed ticks, due to tickless idle. The backlog
+ * would be when CPU is idle and so we just decay the old load without
+ * adding any new load.
+ */
+static unsigned long
+decay_load_missed(unsigned long load, unsigned long missed_updates, int idx)
+{
+	int j = 0;
+
+	if (!missed_updates)
+		return load;
+
+	if (missed_updates >= degrade_zero_ticks[idx])
+		return 0;
+
+	if (idx == 1)
+		return load >> missed_updates;
+
+	while (missed_updates) {
+		if (missed_updates % 2)
+			load = (load * degrade_factor[idx][j]) >> DEGRADE_SHIFT;
+
+		missed_updates >>= 1;
+		j++;
+	}
+	return load;
+}
+
+/*
+ * Update rq->cpu_load[] statistics. This function is usually called every
+ * scheduler tick (TICK_NSEC). With tickless idle this will not be called
+ * every tick. We fix it up based on jiffies.
+ */
+static void __update_cpu_load(struct rq *this_rq, unsigned long this_load,
+			      unsigned long pending_updates)
+{
+	int i, scale;
+
+	this_rq->nr_load_updates++;
+
+	/* Update our load: */
+	this_rq->cpu_load[0] = this_load; /* Fasttrack for idx 0 */
+	for (i = 1, scale = 2; i < CPU_LOAD_IDX_MAX; i++, scale += scale) {
+		unsigned long old_load, new_load;
+
+		/* scale is effectively 1 << i now, and >> i divides by scale */
+
+		old_load = this_rq->cpu_load[i];
+		old_load = decay_load_missed(old_load, pending_updates - 1, i);
+		new_load = this_load;
+		/*
+		 * Round up the averaging division if load is increasing. This
+		 * prevents us from getting stuck on 9 if the load is 10, for
+		 * example.
+		 */
+		if (new_load > old_load)
+			new_load += scale - 1;
+
+		this_rq->cpu_load[i] = (old_load * (scale - 1) + new_load) >> i;
+	}
+
+	sched_avg_update(this_rq);
+}
+
+#ifdef CONFIG_NO_HZ_COMMON
+/*
+ * There is no sane way to deal with nohz on smp when using jiffies because the
+ * cpu doing the jiffies update might drift wrt the cpu doing the jiffy reading
+ * causing off-by-one errors in observed deltas; {0,2} instead of {1,1}.
+ *
+ * Therefore we cannot use the delta approach from the regular tick since that
+ * would seriously skew the load calculation. However we'll make do for those
+ * updates happening while idle (nohz_idle_balance) or coming out of idle
+ * (tick_nohz_idle_exit).
+ *
+ * This means we might still be one tick off for nohz periods.
+ */
+
+/*
+ * Called from nohz_idle_balance() to update the load ratings before doing the
+ * idle balance.
+ */
+static void update_idle_cpu_load(struct rq *this_rq)
+{
+	unsigned long curr_jiffies = READ_ONCE(jiffies);
+	unsigned long load = this_rq->cfs.runnable_load_avg;
+	unsigned long pending_updates;
+
+	/*
+	 * bail if there's load or we're actually up-to-date.
+	 */
+	if (load || curr_jiffies == this_rq->last_load_update_tick)
+		return;
+
+	pending_updates = curr_jiffies - this_rq->last_load_update_tick;
+	this_rq->last_load_update_tick = curr_jiffies;
+
+	__update_cpu_load(this_rq, load, pending_updates);
+}
+
+/*
+ * Called from tick_nohz_idle_exit() -- try and fix up the ticks we missed.
+ */
+void update_cpu_load_nohz(void)
+{
+	struct rq *this_rq = this_rq();
+	unsigned long curr_jiffies = READ_ONCE(jiffies);
+	unsigned long pending_updates;
+
+	if (curr_jiffies == this_rq->last_load_update_tick)
+		return;
+
+	raw_spin_lock(&this_rq->lock);
+	pending_updates = curr_jiffies - this_rq->last_load_update_tick;
+	if (pending_updates) {
+		this_rq->last_load_update_tick = curr_jiffies;
+		/*
+		 * We were idle, this means load 0, the current load might be
+		 * !0 due to remote wakeups and the sort.
+		 */
+		__update_cpu_load(this_rq, 0, pending_updates);
+	}
+	raw_spin_unlock(&this_rq->lock);
+}
+#endif /* CONFIG_NO_HZ */
+
+/*
+ * Called from scheduler_tick()
+ */
+void update_cpu_load_active(struct rq *this_rq)
+{
+	unsigned long load = this_rq->cfs.runnable_load_avg;
+	/*
+	 * See the mess around update_idle_cpu_load() / update_cpu_load_nohz().
+	 */
+	this_rq->last_load_update_tick = jiffies;
+	__update_cpu_load(this_rq, load, 1);
+}
+
 /* Used instead of source_load when we know the type == 0 */
 static unsigned long weighted_cpuload(const int cpu)
 {
@@ -4375,7 +4566,7 @@ static unsigned long capacity_orig_of(int cpu)
 static unsigned long cpu_avg_load_per_task(int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
-	unsigned long nr_running = ACCESS_ONCE(rq->cfs.h_nr_running);
+	unsigned long nr_running = READ_ONCE(rq->cfs.h_nr_running);
 	unsigned long load_avg = rq->cfs.runnable_load_avg;
 
 	if (nr_running)
@@ -5126,18 +5317,21 @@ again:
 		 * entity, update_curr() will update its vruntime, otherwise
 		 * forget we've ever seen it.
 		 */
-		if (curr && curr->on_rq)
-			update_curr(cfs_rq);
-		else
-			curr = NULL;
+		if (curr) {
+			if (curr->on_rq)
+				update_curr(cfs_rq);
+			else
+				curr = NULL;
 
-		/*
-		 * This call to check_cfs_rq_runtime() will do the throttle and
-		 * dequeue its entity in the parent(s). Therefore the 'simple'
-		 * nr_running test will indeed be correct.
-		 */
-		if (unlikely(check_cfs_rq_runtime(cfs_rq)))
-			goto simple;
+			/*
+			 * This call to check_cfs_rq_runtime() will do the
+			 * throttle and dequeue its entity in the parent(s).
+			 * Therefore the 'simple' nr_running test will indeed
+			 * be correct.
+			 */
+			if (unlikely(check_cfs_rq_runtime(cfs_rq)))
+				goto simple;
+		}
 
 		se = pick_next_entity(cfs_rq, curr);
 		cfs_rq = group_cfs_rq(se);
@@ -5467,10 +5661,15 @@ static int task_hot(struct task_struct *p, struct lb_env *env)
 }
 
 #ifdef CONFIG_NUMA_BALANCING
-/* Returns true if the destination node has incurred more faults */
+/*
+ * Returns true if the destination node is the preferred node.
+ * Needs to match fbq_classify_rq(): if there is a runnable task
+ * that is not on its preferred node, we should identify it.
+ */
 static bool migrate_improves_locality(struct task_struct *p, struct lb_env *env)
 {
 	struct numa_group *numa_group = rcu_dereference(p->numa_group);
+	unsigned long src_faults, dst_faults;
 	int src_nid, dst_nid;
 
 	if (!sched_feat(NUMA_FAVOUR_HIGHER) || !p->numa_faults ||
@@ -5484,29 +5683,30 @@ static bool migrate_improves_locality(struct task_struct *p, struct lb_env *env)
 	if (src_nid == dst_nid)
 		return false;
 
-	if (numa_group) {
-		/* Task is already in the group's interleave set. */
-		if (node_isset(src_nid, numa_group->active_nodes))
-			return false;
-
-		/* Task is moving into the group's interleave set. */
-		if (node_isset(dst_nid, numa_group->active_nodes))
-			return true;
-
-		return group_faults(p, dst_nid) > group_faults(p, src_nid);
-	}
-
 	/* Encourage migration to the preferred node. */
 	if (dst_nid == p->numa_preferred_nid)
 		return true;
 
-	return task_faults(p, dst_nid) > task_faults(p, src_nid);
+	/* Migrating away from the preferred node is bad. */
+	if (src_nid == p->numa_preferred_nid)
+		return false;
+
+	if (numa_group) {
+		src_faults = group_faults(p, src_nid);
+		dst_faults = group_faults(p, dst_nid);
+	} else {
+		src_faults = task_faults(p, src_nid);
+		dst_faults = task_faults(p, dst_nid);
+	}
+
+	return dst_faults > src_faults;
 }
 
 
 static bool migrate_degrades_locality(struct task_struct *p, struct lb_env *env)
 {
 	struct numa_group *numa_group = rcu_dereference(p->numa_group);
+	unsigned long src_faults, dst_faults;
 	int src_nid, dst_nid;
 
 	if (!sched_feat(NUMA) || !sched_feat(NUMA_RESIST_LOWER))
@@ -5521,23 +5721,23 @@ static bool migrate_degrades_locality(struct task_struct *p, struct lb_env *env)
 	if (src_nid == dst_nid)
 		return false;
 
-	if (numa_group) {
-		/* Task is moving within/into the group's interleave set. */
-		if (node_isset(dst_nid, numa_group->active_nodes))
-			return false;
+	/* Migrating away from the preferred node is bad. */
+	if (src_nid == p->numa_preferred_nid)
+		return true;
 
-		/* Task is moving out of the group's interleave set. */
-		if (node_isset(src_nid, numa_group->active_nodes))
-			return true;
+	/* Encourage migration to the preferred node. */
+	if (dst_nid == p->numa_preferred_nid)
+		return false;
 
-		return group_faults(p, dst_nid) < group_faults(p, src_nid);
+	if (numa_group) {
+		src_faults = group_faults(p, src_nid);
+		dst_faults = group_faults(p, dst_nid);
+	} else {
+		src_faults = task_faults(p, src_nid);
+		dst_faults = task_faults(p, dst_nid);
 	}
 
-	/* Migrating away from the preferred node is always bad. */
-	if (src_nid == p->numa_preferred_nid)
-		return true;
-
-	return task_faults(p, dst_nid) < task_faults(p, src_nid);
+	return dst_faults < src_faults;
 }
 
 #else
@@ -6037,8 +6237,8 @@ static unsigned long scale_rt_capacity(int cpu)
 	 * Since we're reading these variables without serialization make sure
 	 * we read them once before doing sanity checks on them.
 	 */
-	age_stamp = ACCESS_ONCE(rq->age_stamp);
-	avg = ACCESS_ONCE(rq->rt_avg);
+	age_stamp = READ_ONCE(rq->age_stamp);
+	avg = READ_ONCE(rq->rt_avg);
 	delta = __rq_clock_broken(rq) - age_stamp;
 
 	if (unlikely(delta < 0))
diff --git a/kernel/sched/proc.c b/kernel/sched/loadavg.c
index 8ecd552fe4f2..ef7159012cf3 100644
--- a/kernel/sched/proc.c
+++ b/kernel/sched/loadavg.c
@@ -1,7 +1,9 @@
 /*
- *  kernel/sched/proc.c
+ * kernel/sched/loadavg.c
  *
- *  Kernel load calculations, forked from sched/core.c
+ * This file contains the magic bits required to compute the global loadavg
+ * figure. Its a silly number but people think its important. We go through
+ * great pains to make it work on big machines and tickless kernels.
  */
 
 #include <linux/export.h>
@@ -81,7 +83,7 @@ long calc_load_fold_active(struct rq *this_rq)
 	long nr_active, delta = 0;
 
 	nr_active = this_rq->nr_running;
-	nr_active += (long) this_rq->nr_uninterruptible;
+	nr_active += (long)this_rq->nr_uninterruptible;
 
 	if (nr_active != this_rq->calc_load_active) {
 		delta = nr_active - this_rq->calc_load_active;
@@ -186,6 +188,7 @@ void calc_load_enter_idle(void)
 	delta = calc_load_fold_active(this_rq);
 	if (delta) {
 		int idx = calc_load_write_idx();
+
 		atomic_long_add(delta, &calc_load_idle[idx]);
 	}
 }
@@ -241,18 +244,20 @@ fixed_power_int(unsigned long x, unsigned int frac_bits, unsigned int n)
 {
 	unsigned long result = 1UL << frac_bits;
 
-	if (n) for (;;) {
-		if (n & 1) {
-			result *= x;
-			result += 1UL << (frac_bits - 1);
-			result >>= frac_bits;
+	if (n) {
+		for (;;) {
+			if (n & 1) {
+				result *= x;
+				result += 1UL << (frac_bits - 1);
+				result >>= frac_bits;
+			}
+			n >>= 1;
+			if (!n)
+				break;
+			x *= x;
+			x += 1UL << (frac_bits - 1);
+			x >>= frac_bits;
 		}
-		n >>= 1;
-		if (!n)
-			break;
-		x *= x;
-		x += 1UL << (frac_bits - 1);
-		x >>= frac_bits;
 	}
 
 	return result;
@@ -285,7 +290,6 @@ static unsigned long
 calc_load_n(unsigned long load, unsigned long exp,
 	    unsigned long active, unsigned int n)
 {
-
 	return calc_load(load, fixed_power_int(exp, FSHIFT, n), active);
 }
 
@@ -339,6 +343,8 @@ static inline void calc_global_nohz(void) { }
 /*
  * calc_load - update the avenrun load estimates 10 ticks after the
  * CPUs have updated calc_load_tasks.
+ *
+ * Called from the global timer code.
  */
 void calc_global_load(unsigned long ticks)
 {
@@ -370,10 +376,10 @@ void calc_global_load(unsigned long ticks)
 }
 
 /*
- * Called from update_cpu_load() to periodically update this CPU's
+ * Called from scheduler_tick() to periodically update this CPU's
  * active count.
  */
-static void calc_load_account_active(struct rq *this_rq)
+void calc_global_load_tick(struct rq *this_rq)
 {
 	long delta;
 
@@ -386,199 +392,3 @@ static void calc_load_account_active(struct rq *this_rq)
 
 	this_rq->calc_load_update += LOAD_FREQ;
 }
-
-/*
- * End of global load-average stuff
- */
-
-/*
- * The exact cpuload at various idx values, calculated at every tick would be
- * load = (2^idx - 1) / 2^idx * load + 1 / 2^idx * cur_load
- *
- * If a cpu misses updates for n-1 ticks (as it was idle) and update gets called
- * on nth tick when cpu may be busy, then we have:
- * load = ((2^idx - 1) / 2^idx)^(n-1) * load
- * load = (2^idx - 1) / 2^idx) * load + 1 / 2^idx * cur_load
- *
- * decay_load_missed() below does efficient calculation of
- * load = ((2^idx - 1) / 2^idx)^(n-1) * load
- * avoiding 0..n-1 loop doing load = ((2^idx - 1) / 2^idx) * load
- *
- * The calculation is approximated on a 128 point scale.
- * degrade_zero_ticks is the number of ticks after which load at any
- * particular idx is approximated to be zero.
- * degrade_factor is a precomputed table, a row for each load idx.
- * Each column corresponds to degradation factor for a power of two ticks,
- * based on 128 point scale.
- * Example:
- * row 2, col 3 (=12) says that the degradation at load idx 2 after
- * 8 ticks is 12/128 (which is an approximation of exact factor 3^8/4^8).
- *
- * With this power of 2 load factors, we can degrade the load n times
- * by looking at 1 bits in n and doing as many mult/shift instead of
- * n mult/shifts needed by the exact degradation.
- */
-#define DEGRADE_SHIFT		7
-static const unsigned char
-		degrade_zero_ticks[CPU_LOAD_IDX_MAX] = {0, 8, 32, 64, 128};
-static const unsigned char
-		degrade_factor[CPU_LOAD_IDX_MAX][DEGRADE_SHIFT + 1] = {
-					{0, 0, 0, 0, 0, 0, 0, 0},
-					{64, 32, 8, 0, 0, 0, 0, 0},
-					{96, 72, 40, 12, 1, 0, 0},
-					{112, 98, 75, 43, 15, 1, 0},
-					{120, 112, 98, 76, 45, 16, 2} };
-
-/*
- * Update cpu_load for any missed ticks, due to tickless idle. The backlog
- * would be when CPU is idle and so we just decay the old load without
- * adding any new load.
- */
-static unsigned long
-decay_load_missed(unsigned long load, unsigned long missed_updates, int idx)
-{
-	int j = 0;
-
-	if (!missed_updates)
-		return load;
-
-	if (missed_updates >= degrade_zero_ticks[idx])
-		return 0;
-
-	if (idx == 1)
-		return load >> missed_updates;
-
-	while (missed_updates) {
-		if (missed_updates % 2)
-			load = (load * degrade_factor[idx][j]) >> DEGRADE_SHIFT;
-
-		missed_updates >>= 1;
-		j++;
-	}
-	return load;
-}
-
-/*
- * Update rq->cpu_load[] statistics. This function is usually called every
- * scheduler tick (TICK_NSEC). With tickless idle this will not be called
- * every tick. We fix it up based on jiffies.
- */
-static void __update_cpu_load(struct rq *this_rq, unsigned long this_load,
-			      unsigned long pending_updates)
-{
-	int i, scale;
-
-	this_rq->nr_load_updates++;
-
-	/* Update our load: */
-	this_rq->cpu_load[0] = this_load; /* Fasttrack for idx 0 */
-	for (i = 1, scale = 2; i < CPU_LOAD_IDX_MAX; i++, scale += scale) {
-		unsigned long old_load, new_load;
-
-		/* scale is effectively 1 << i now, and >> i divides by scale */
-
-		old_load = this_rq->cpu_load[i];
-		old_load = decay_load_missed(old_load, pending_updates - 1, i);
-		new_load = this_load;
-		/*
-		 * Round up the averaging division if load is increasing. This
-		 * prevents us from getting stuck on 9 if the load is 10, for
-		 * example.
-		 */
-		if (new_load > old_load)
-			new_load += scale - 1;
-
-		this_rq->cpu_load[i] = (old_load * (scale - 1) + new_load) >> i;
-	}
-
-	sched_avg_update(this_rq);
-}
-
-#ifdef CONFIG_SMP
-static inline unsigned long get_rq_runnable_load(struct rq *rq)
-{
-	return rq->cfs.runnable_load_avg;
-}
-#else
-static inline unsigned long get_rq_runnable_load(struct rq *rq)
-{
-	return rq->load.weight;
-}
-#endif
-
-#ifdef CONFIG_NO_HZ_COMMON
-/*
- * There is no sane way to deal with nohz on smp when using jiffies because the
- * cpu doing the jiffies update might drift wrt the cpu doing the jiffy reading
- * causing off-by-one errors in observed deltas; {0,2} instead of {1,1}.
- *
- * Therefore we cannot use the delta approach from the regular tick since that
- * would seriously skew the load calculation. However we'll make do for those
- * updates happening while idle (nohz_idle_balance) or coming out of idle
- * (tick_nohz_idle_exit).
- *
- * This means we might still be one tick off for nohz periods.
- */
-
-/*
- * Called from nohz_idle_balance() to update the load ratings before doing the
- * idle balance.
- */
-void update_idle_cpu_load(struct rq *this_rq)
-{
-	unsigned long curr_jiffies = ACCESS_ONCE(jiffies);
-	unsigned long load = get_rq_runnable_load(this_rq);
-	unsigned long pending_updates;
-
-	/*
-	 * bail if there's load or we're actually up-to-date.
-	 */
-	if (load || curr_jiffies == this_rq->last_load_update_tick)
-		return;
-
-	pending_updates = curr_jiffies - this_rq->last_load_update_tick;
-	this_rq->last_load_update_tick = curr_jiffies;
-
-	__update_cpu_load(this_rq, load, pending_updates);
-}
-
-/*
- * Called from tick_nohz_idle_exit() -- try and fix up the ticks we missed.
- */
-void update_cpu_load_nohz(void)
-{
-	struct rq *this_rq = this_rq();
-	unsigned long curr_jiffies = ACCESS_ONCE(jiffies);
-	unsigned long pending_updates;
-
-	if (curr_jiffies == this_rq->last_load_update_tick)
-		return;
-
-	raw_spin_lock(&this_rq->lock);
-	pending_updates = curr_jiffies - this_rq->last_load_update_tick;
-	if (pending_updates) {
-		this_rq->last_load_update_tick = curr_jiffies;
-		/*
-		 * We were idle, this means load 0, the current load might be
-		 * !0 due to remote wakeups and the sort.
-		 */
-		__update_cpu_load(this_rq, 0, pending_updates);
-	}
-	raw_spin_unlock(&this_rq->lock);
-}
-#endif /* CONFIG_NO_HZ */
-
-/*
- * Called from scheduler_tick()
- */
-void update_cpu_load_active(struct rq *this_rq)
-{
-	unsigned long load = get_rq_runnable_load(this_rq);
-	/*
-	 * See the mess around update_idle_cpu_load() / update_cpu_load_nohz().
-	 */
-	this_rq->last_load_update_tick = jiffies;
-	__update_cpu_load(this_rq, load, 1);
-
-	calc_load_account_active(this_rq);
-}
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 575da76a3874..7d7093c51f8d 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -18,19 +18,22 @@ static enum hrtimer_restart sched_rt_period_timer(struct hrtimer *timer)
 {
 	struct rt_bandwidth *rt_b =
 		container_of(timer, struct rt_bandwidth, rt_period_timer);
-	ktime_t now;
-	int overrun;
 	int idle = 0;
+	int overrun;
 
+	raw_spin_lock(&rt_b->rt_runtime_lock);
 	for (;;) {
-		now = hrtimer_cb_get_time(timer);
-		overrun = hrtimer_forward(timer, now, rt_b->rt_period);
-
+		overrun = hrtimer_forward_now(timer, rt_b->rt_period);
 		if (!overrun)
 			break;
 
+		raw_spin_unlock(&rt_b->rt_runtime_lock);
 		idle = do_sched_rt_period_timer(rt_b, overrun);
+		raw_spin_lock(&rt_b->rt_runtime_lock);
 	}
+	if (idle)
+		rt_b->rt_period_active = 0;
+	raw_spin_unlock(&rt_b->rt_runtime_lock);
 
 	return idle ? HRTIMER_NORESTART : HRTIMER_RESTART;
 }
@@ -52,11 +55,12 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
 	if (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF)
 		return;
 
-	if (hrtimer_active(&rt_b->rt_period_timer))
-		return;
-
 	raw_spin_lock(&rt_b->rt_runtime_lock);
-	start_bandwidth_timer(&rt_b->rt_period_timer, rt_b->rt_period);
+	if (!rt_b->rt_period_active) {
+		rt_b->rt_period_active = 1;
+		hrtimer_forward_now(&rt_b->rt_period_timer, rt_b->rt_period);
+		hrtimer_start_expires(&rt_b->rt_period_timer, HRTIMER_MODE_ABS_PINNED);
+	}
 	raw_spin_unlock(&rt_b->rt_runtime_lock);
 }
 
@@ -1323,7 +1327,7 @@ select_task_rq_rt(struct task_struct *p, int cpu, int sd_flag, int flags)
 	rq = cpu_rq(cpu);
 
 	rcu_read_lock();
-	curr = ACCESS_ONCE(rq->curr); /* unlocked access */
+	curr = READ_ONCE(rq->curr); /* unlocked access */
 
 	/*
 	 * If the current task on @p's runqueue is an RT task, then
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index e0e129993958..aea7c1f393cb 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -26,8 +26,14 @@ extern __read_mostly int scheduler_running;
 extern unsigned long calc_load_update;
 extern atomic_long_t calc_load_tasks;
 
+extern void calc_global_load_tick(struct rq *this_rq);
 extern long calc_load_fold_active(struct rq *this_rq);
+
+#ifdef CONFIG_SMP
 extern void update_cpu_load_active(struct rq *this_rq);
+#else
+static inline void update_cpu_load_active(struct rq *this_rq) { }
+#endif
 
 /*
  * Helpers for converting nanosecond timing to jiffy resolution
@@ -131,6 +137,7 @@ struct rt_bandwidth {
 	ktime_t			rt_period;
 	u64			rt_runtime;
 	struct hrtimer		rt_period_timer;
+	unsigned int		rt_period_active;
 };
 
 void __dl_clear_params(struct task_struct *p);
@@ -215,7 +222,7 @@ struct cfs_bandwidth {
 	s64 hierarchical_quota;
 	u64 runtime_expires;
 
-	int idle, timer_active;
+	int idle, period_active;
 	struct hrtimer period_timer, slack_timer;
 	struct list_head throttled_cfs_rq;
 
@@ -306,7 +313,7 @@ extern void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b);
 extern int sched_group_set_shares(struct task_group *tg, unsigned long shares);
 
 extern void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b);
-extern void __start_cfs_bandwidth(struct cfs_bandwidth *cfs_b, bool force);
+extern void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b);
 extern void unthrottle_cfs_rq(struct cfs_rq *cfs_rq);
 
 extern void free_rt_sched_group(struct task_group *tg);
@@ -707,7 +714,7 @@ DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
 
 static inline u64 __rq_clock_broken(struct rq *rq)
 {
-	return ACCESS_ONCE(rq->clock);
+	return READ_ONCE(rq->clock);
 }
 
 static inline u64 rq_clock(struct rq *rq)
@@ -1284,7 +1291,6 @@ extern void update_max_interval(void);
 extern void init_sched_dl_class(void);
 extern void init_sched_rt_class(void);
 extern void init_sched_fair_class(void);
-extern void init_sched_dl_class(void);
 
 extern void resched_curr(struct rq *rq);
 extern void resched_cpu(int cpu);
@@ -1298,8 +1304,6 @@ extern void init_dl_task_timer(struct sched_dl_entity *dl_se);
 
 unsigned long to_ratio(u64 period, u64 runtime);
 
-extern void update_idle_cpu_load(struct rq *this_rq);
-
 extern void init_task_runnable_average(struct task_struct *p);
 
 static inline void add_nr_running(struct rq *rq, unsigned count)
@@ -1406,8 +1410,6 @@ static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta) { }
 static inline void sched_avg_update(struct rq *rq) { }
 #endif
 
-extern void start_bandwidth_timer(struct hrtimer *period_timer, ktime_t period);
-
 /*
  * __task_rq_lock - lock the rq @p resides on.
  */
diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
index 4ab704339656..077ebbd5e10f 100644
--- a/kernel/sched/stats.h
+++ b/kernel/sched/stats.h
@@ -174,7 +174,8 @@ static inline bool cputimer_running(struct task_struct *tsk)
 {
 	struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
 
-	if (!cputimer->running)
+	/* Check if cputimer isn't running. This is accessed without locking. */
+	if (!READ_ONCE(cputimer->running))
 		return false;
 
 	/*
@@ -215,9 +216,7 @@ static inline void account_group_user_time(struct task_struct *tsk,
 	if (!cputimer_running(tsk))
 		return;
 
-	raw_spin_lock(&cputimer->lock);
-	cputimer->cputime.utime += cputime;
-	raw_spin_unlock(&cputimer->lock);
+	atomic64_add(cputime, &cputimer->cputime_atomic.utime);
 }
 
 /**
@@ -238,9 +237,7 @@ static inline void account_group_system_time(struct task_struct *tsk,
 	if (!cputimer_running(tsk))
 		return;
 
-	raw_spin_lock(&cputimer->lock);
-	cputimer->cputime.stime += cputime;
-	raw_spin_unlock(&cputimer->lock);
+	atomic64_add(cputime, &cputimer->cputime_atomic.stime);
 }
 
 /**
@@ -261,7 +258,5 @@ static inline void account_group_exec_runtime(struct task_struct *tsk,
 	if (!cputimer_running(tsk))
 		return;
 
-	raw_spin_lock(&cputimer->lock);
-	cputimer->cputime.sum_exec_runtime += ns;
-	raw_spin_unlock(&cputimer->lock);
+	atomic64_add(ns, &cputimer->cputime_atomic.sum_exec_runtime);
 }
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 852143a79f36..052e02672d12 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -341,7 +341,7 @@ long wait_woken(wait_queue_t *wait, unsigned mode, long timeout)
 	 * condition being true _OR_ WQ_FLAG_WOKEN such that we will not miss
 	 * an event.
 	 */
-	set_mb(wait->flags, wait->flags & ~WQ_FLAG_WOKEN); /* B */
+	smp_store_mb(wait->flags, wait->flags & ~WQ_FLAG_WOKEN); /* B */
 
 	return timeout;
 }
@@ -354,7 +354,7 @@ int woken_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key)
 	 * doesn't imply write barrier and the users expects write
 	 * barrier semantics on wakeup functions.  The following
 	 * smp_wmb() is equivalent to smp_wmb() in try_to_wake_up()
-	 * and is paired with set_mb() in wait_woken().
+	 * and is paired with smp_store_mb() in wait_woken().
 	 */
 	smp_wmb(); /* C */
 	wait->flags |= WQ_FLAG_WOKEN;
@@ -601,7 +601,7 @@ EXPORT_SYMBOL(bit_wait_io);
 
 __sched int bit_wait_timeout(struct wait_bit_key *word)
 {
-	unsigned long now = ACCESS_ONCE(jiffies);
+	unsigned long now = READ_ONCE(jiffies);
 	if (signal_pending_state(current->state, current))
 		return 1;
 	if (time_after_eq(now, word->timeout))
@@ -613,7 +613,7 @@ EXPORT_SYMBOL_GPL(bit_wait_timeout);
 
 __sched int bit_wait_io_timeout(struct wait_bit_key *word)
 {
-	unsigned long now = ACCESS_ONCE(jiffies);
+	unsigned long now = READ_ONCE(jiffies);
 	if (signal_pending_state(current->state, current))
 		return 1;
 	if (time_after_eq(now, word->timeout))
diff --git a/kernel/signal.c b/kernel/signal.c
index d51c5ddd855c..f19833b5db3c 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -245,7 +245,7 @@ static inline void print_dropped_signal(int sig)
  * RETURNS:
  * %true if @mask is set, %false if made noop because @task was dying.
  */
-bool task_set_jobctl_pending(struct task_struct *task, unsigned int mask)
+bool task_set_jobctl_pending(struct task_struct *task, unsigned long mask)
 {
 	BUG_ON(mask & ~(JOBCTL_PENDING_MASK | JOBCTL_STOP_CONSUME |
 			JOBCTL_STOP_SIGMASK | JOBCTL_TRAPPING));
@@ -297,7 +297,7 @@ void task_clear_jobctl_trapping(struct task_struct *task)
  * CONTEXT:
  * Must be called with @task->sighand->siglock held.
  */
-void task_clear_jobctl_pending(struct task_struct *task, unsigned int mask)
+void task_clear_jobctl_pending(struct task_struct *task, unsigned long mask)
 {
 	BUG_ON(mask & ~JOBCTL_PENDING_MASK);
 
@@ -2000,7 +2000,7 @@ static bool do_signal_stop(int signr)
 	struct signal_struct *sig = current->signal;
 
 	if (!(current->jobctl & JOBCTL_STOP_PENDING)) {
-		unsigned int gstop = JOBCTL_STOP_PENDING | JOBCTL_STOP_CONSUME;
+		unsigned long gstop = JOBCTL_STOP_PENDING | JOBCTL_STOP_CONSUME;
 		struct task_struct *t;
 
 		/* signr will be recorded in task->jobctl for retries */
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index 695f0c6cd169..fd643d8c4b42 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -211,25 +211,6 @@ static int multi_cpu_stop(void *data)
 	return err;
 }
 
-struct irq_cpu_stop_queue_work_info {
-	int cpu1;
-	int cpu2;
-	struct cpu_stop_work *work1;
-	struct cpu_stop_work *work2;
-};
-
-/*
- * This function is always run with irqs and preemption disabled.
- * This guarantees that both work1 and work2 get queued, before
- * our local migrate thread gets the chance to preempt us.
- */
-static void irq_cpu_stop_queue_work(void *arg)
-{
-	struct irq_cpu_stop_queue_work_info *info = arg;
-	cpu_stop_queue_work(info->cpu1, info->work1);
-	cpu_stop_queue_work(info->cpu2, info->work2);
-}
-
 /**
  * stop_two_cpus - stops two cpus
  * @cpu1: the cpu to stop
@@ -245,7 +226,6 @@ int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void *
 {
 	struct cpu_stop_done done;
 	struct cpu_stop_work work1, work2;
-	struct irq_cpu_stop_queue_work_info call_args;
 	struct multi_stop_data msdata;
 
 	preempt_disable();
@@ -262,13 +242,6 @@ int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void *
 		.done = &done
 	};
 
-	call_args = (struct irq_cpu_stop_queue_work_info){
-		.cpu1 = cpu1,
-		.cpu2 = cpu2,
-		.work1 = &work1,
-		.work2 = &work2,
-	};
-
 	cpu_stop_init_done(&done, 2);
 	set_state(&msdata, MULTI_STOP_PREPARE);
 
@@ -285,16 +258,11 @@ int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void *
 		return -ENOENT;
 	}
 
-	lg_local_lock(&stop_cpus_lock);
-	/*
-	 * Queuing needs to be done by the lowest numbered CPU, to ensure
-	 * that works are always queued in the same order on every CPU.
-	 * This prevents deadlocks.
-	 */
-	smp_call_function_single(min(cpu1, cpu2),
-				 &irq_cpu_stop_queue_work,
-				 &call_args, 1);
-	lg_local_unlock(&stop_cpus_lock);
+	lg_double_lock(&stop_cpus_lock, cpu1, cpu2);
+	cpu_stop_queue_work(cpu1, &work1);
+	cpu_stop_queue_work(cpu2, &work2);
+	lg_double_unlock(&stop_cpus_lock, cpu1, cpu2);
+
 	preempt_enable();
 
 	wait_for_completion(&done.completion);
diff --git a/kernel/sys.c b/kernel/sys.c
index a4e372b798a5..8571296b7ddb 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -92,10 +92,10 @@
 # define SET_TSC_CTL(a)		(-EINVAL)
 #endif
 #ifndef MPX_ENABLE_MANAGEMENT
-# define MPX_ENABLE_MANAGEMENT(a)	(-EINVAL)
+# define MPX_ENABLE_MANAGEMENT()	(-EINVAL)
 #endif
 #ifndef MPX_DISABLE_MANAGEMENT
-# define MPX_DISABLE_MANAGEMENT(a)	(-EINVAL)
+# define MPX_DISABLE_MANAGEMENT()	(-EINVAL)
 #endif
 #ifndef GET_FP_MODE
 # define GET_FP_MODE(a)		(-EINVAL)
@@ -2230,12 +2230,12 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 	case PR_MPX_ENABLE_MANAGEMENT:
 		if (arg2 || arg3 || arg4 || arg5)
 			return -EINVAL;
-		error = MPX_ENABLE_MANAGEMENT(me);
+		error = MPX_ENABLE_MANAGEMENT();
 		break;
 	case PR_MPX_DISABLE_MANAGEMENT:
 		if (arg2 || arg3 || arg4 || arg5)
 			return -EINVAL;
-		error = MPX_DISABLE_MANAGEMENT(me);
+		error = MPX_DISABLE_MANAGEMENT();
 		break;
 	case PR_SET_FP_MODE:
 		error = SET_FP_MODE(me, arg2);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 2082b1a88fb9..b13e9d2de302 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -349,15 +349,6 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
-	{
-		.procname	= "timer_migration",
-		.data		= &sysctl_timer_migration,
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
-		.extra2		= &one,
-	},
 #endif /* CONFIG_SMP */
 #ifdef CONFIG_NUMA_BALANCING
 	{
@@ -1132,6 +1123,15 @@ static struct ctl_table kern_table[] = {
 		.extra1		= &zero,
 		.extra2		= &one,
 	},
+#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
+	{
+		.procname	= "timer_migration",
+		.data		= &sysctl_timer_migration,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= timer_migration_handler,
+	},
+#endif
 	{ }
 };
 
diff --git a/kernel/time/Makefile b/kernel/time/Makefile
index 01f0312419b3..ffc4cc3dcd47 100644
--- a/kernel/time/Makefile
+++ b/kernel/time/Makefile
@@ -13,19 +13,4 @@ obj-$(CONFIG_TIMER_STATS)			+= timer_stats.o
 obj-$(CONFIG_DEBUG_FS)				+= timekeeping_debug.o
 obj-$(CONFIG_TEST_UDELAY)			+= test_udelay.o
 
-$(obj)/time.o: $(obj)/timeconst.h
-
-quiet_cmd_hzfile = HZFILE  $@
-      cmd_hzfile = echo "hz=$(CONFIG_HZ)" > $@
-
-targets += hz.bc
-$(obj)/hz.bc: $(objtree)/include/config/hz.h FORCE
-	$(call if_changed,hzfile)
-
-quiet_cmd_bc  = BC      $@
-      cmd_bc  = bc -q $(filter-out FORCE,$^) > $@
-
-targets += timeconst.h
-$(obj)/timeconst.h: $(obj)/hz.bc $(src)/timeconst.bc FORCE
-	$(call if_changed,bc)
-
+$(obj)/time.o: $(objtree)/include/config/
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index 1b001ed1edb9..7fbba635a549 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -317,19 +317,16 @@ EXPORT_SYMBOL_GPL(alarm_init);
  * @alarm: ptr to alarm to set
  * @start: time to run the alarm
  */
-int alarm_start(struct alarm *alarm, ktime_t start)
+void alarm_start(struct alarm *alarm, ktime_t start)
 {
 	struct alarm_base *base = &alarm_bases[alarm->type];
 	unsigned long flags;
-	int ret;
 
 	spin_lock_irqsave(&base->lock, flags);
 	alarm->node.expires = start;
 	alarmtimer_enqueue(base, alarm);
-	ret = hrtimer_start(&alarm->timer, alarm->node.expires,
-				HRTIMER_MODE_ABS);
+	hrtimer_start(&alarm->timer, alarm->node.expires, HRTIMER_MODE_ABS);
 	spin_unlock_irqrestore(&base->lock, flags);
-	return ret;
 }
 EXPORT_SYMBOL_GPL(alarm_start);
 
@@ -338,12 +335,12 @@ EXPORT_SYMBOL_GPL(alarm_start);
  * @alarm: ptr to alarm to set
  * @start: time relative to now to run the alarm
  */
-int alarm_start_relative(struct alarm *alarm, ktime_t start)
+void alarm_start_relative(struct alarm *alarm, ktime_t start)
 {
 	struct alarm_base *base = &alarm_bases[alarm->type];
 
 	start = ktime_add(start, base->gettime());
-	return alarm_start(alarm, start);
+	alarm_start(alarm, start);
 }
 EXPORT_SYMBOL_GPL(alarm_start_relative);
 
@@ -495,12 +492,12 @@ static enum alarmtimer_restart alarm_handle_timer(struct alarm *alarm,
  */
 static int alarm_clock_getres(const clockid_t which_clock, struct timespec *tp)
 {
-	clockid_t baseid = alarm_bases[clock2alarm(which_clock)].base_clockid;
-
 	if (!alarmtimer_get_rtcdev())
 		return -EINVAL;
 
-	return hrtimer_get_res(baseid, tp);
+	tp->tv_sec = 0;
+	tp->tv_nsec = hrtimer_resolution;
+	return 0;
 }
 
 /**
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 637a09461c1d..08ccc3da3ca0 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -94,8 +94,8 @@ u64 clockevent_delta2ns(unsigned long latch, struct clock_event_device *evt)
 }
 EXPORT_SYMBOL_GPL(clockevent_delta2ns);
 
-static int __clockevents_set_state(struct clock_event_device *dev,
-				   enum clock_event_state state)
+static int __clockevents_switch_state(struct clock_event_device *dev,
+				      enum clock_event_state state)
 {
 	/* Transition with legacy set_mode() callback */
 	if (dev->set_mode) {
@@ -134,32 +134,44 @@ static int __clockevents_set_state(struct clock_event_device *dev,
 			return -ENOSYS;
 		return dev->set_state_oneshot(dev);
 
+	case CLOCK_EVT_STATE_ONESHOT_STOPPED:
+		/* Core internal bug */
+		if (WARN_ONCE(!clockevent_state_oneshot(dev),
+			      "Current state: %d\n",
+			      clockevent_get_state(dev)))
+			return -EINVAL;
+
+		if (dev->set_state_oneshot_stopped)
+			return dev->set_state_oneshot_stopped(dev);
+		else
+			return -ENOSYS;
+
 	default:
 		return -ENOSYS;
 	}
 }
 
 /**
- * clockevents_set_state - set the operating state of a clock event device
+ * clockevents_switch_state - set the operating state of a clock event device
  * @dev:	device to modify
  * @state:	new state
  *
  * Must be called with interrupts disabled !
  */
-void clockevents_set_state(struct clock_event_device *dev,
-			   enum clock_event_state state)
+void clockevents_switch_state(struct clock_event_device *dev,
+			      enum clock_event_state state)
 {
-	if (dev->state != state) {
-		if (__clockevents_set_state(dev, state))
+	if (clockevent_get_state(dev) != state) {
+		if (__clockevents_switch_state(dev, state))
 			return;
 
-		dev->state = state;
+		clockevent_set_state(dev, state);
 
 		/*
 		 * A nsec2cyc multiplicator of 0 is invalid and we'd crash
 		 * on it, so fix it up and emit a warning:
 		 */
-		if (state == CLOCK_EVT_STATE_ONESHOT) {
+		if (clockevent_state_oneshot(dev)) {
 			if (unlikely(!dev->mult)) {
 				dev->mult = 1;
 				WARN_ON(1);
@@ -174,7 +186,7 @@ void clockevents_set_state(struct clock_event_device *dev,
  */
 void clockevents_shutdown(struct clock_event_device *dev)
 {
-	clockevents_set_state(dev, CLOCK_EVT_STATE_SHUTDOWN);
+	clockevents_switch_state(dev, CLOCK_EVT_STATE_SHUTDOWN);
 	dev->next_event.tv64 = KTIME_MAX;
 }
 
@@ -248,7 +260,7 @@ static int clockevents_program_min_delta(struct clock_event_device *dev)
 		delta = dev->min_delta_ns;
 		dev->next_event = ktime_add_ns(ktime_get(), delta);
 
-		if (dev->state == CLOCK_EVT_STATE_SHUTDOWN)
+		if (clockevent_state_shutdown(dev))
 			return 0;
 
 		dev->retries++;
@@ -285,7 +297,7 @@ static int clockevents_program_min_delta(struct clock_event_device *dev)
 	delta = dev->min_delta_ns;
 	dev->next_event = ktime_add_ns(ktime_get(), delta);
 
-	if (dev->state == CLOCK_EVT_STATE_SHUTDOWN)
+	if (clockevent_state_shutdown(dev))
 		return 0;
 
 	dev->retries++;
@@ -317,9 +329,13 @@ int clockevents_program_event(struct clock_event_device *dev, ktime_t expires,
 
 	dev->next_event = expires;
 
-	if (dev->state == CLOCK_EVT_STATE_SHUTDOWN)
+	if (clockevent_state_shutdown(dev))
 		return 0;
 
+	/* We must be in ONESHOT state here */
+	WARN_ONCE(!clockevent_state_oneshot(dev), "Current state: %d\n",
+		  clockevent_get_state(dev));
+
 	/* Shortcut for clockevent devices that can deal with ktime. */
 	if (dev->features & CLOCK_EVT_FEAT_KTIME)
 		return dev->set_next_ktime(expires, dev);
@@ -362,7 +378,7 @@ static int clockevents_replace(struct clock_event_device *ced)
 	struct clock_event_device *dev, *newdev = NULL;
 
 	list_for_each_entry(dev, &clockevent_devices, list) {
-		if (dev == ced || dev->state != CLOCK_EVT_STATE_DETACHED)
+		if (dev == ced || !clockevent_state_detached(dev))
 			continue;
 
 		if (!tick_check_replacement(newdev, dev))
@@ -388,7 +404,7 @@ static int clockevents_replace(struct clock_event_device *ced)
 static int __clockevents_try_unbind(struct clock_event_device *ced, int cpu)
 {
 	/* Fast track. Device is unused */
-	if (ced->state == CLOCK_EVT_STATE_DETACHED) {
+	if (clockevent_state_detached(ced)) {
 		list_del_init(&ced->list);
 		return 0;
 	}
@@ -445,7 +461,8 @@ static int clockevents_sanity_check(struct clock_event_device *dev)
 	if (dev->set_mode) {
 		/* We shouldn't be supporting new modes now */
 		WARN_ON(dev->set_state_periodic || dev->set_state_oneshot ||
-			dev->set_state_shutdown || dev->tick_resume);
+			dev->set_state_shutdown || dev->tick_resume ||
+			dev->set_state_oneshot_stopped);
 
 		BUG_ON(dev->mode != CLOCK_EVT_MODE_UNUSED);
 		return 0;
@@ -480,7 +497,7 @@ void clockevents_register_device(struct clock_event_device *dev)
 	BUG_ON(clockevents_sanity_check(dev));
 
 	/* Initialize state to DETACHED */
-	dev->state = CLOCK_EVT_STATE_DETACHED;
+	clockevent_set_state(dev, CLOCK_EVT_STATE_DETACHED);
 
 	if (!dev->cpumask) {
 		WARN_ON(num_possible_cpus() > 1);
@@ -545,11 +562,11 @@ int __clockevents_update_freq(struct clock_event_device *dev, u32 freq)
 {
 	clockevents_config(dev, freq);
 
-	if (dev->state == CLOCK_EVT_STATE_ONESHOT)
+	if (clockevent_state_oneshot(dev))
 		return clockevents_program_event(dev, dev->next_event, false);
 
-	if (dev->state == CLOCK_EVT_STATE_PERIODIC)
-		return __clockevents_set_state(dev, CLOCK_EVT_STATE_PERIODIC);
+	if (clockevent_state_periodic(dev))
+		return __clockevents_switch_state(dev, CLOCK_EVT_STATE_PERIODIC);
 
 	return 0;
 }
@@ -603,13 +620,13 @@ void clockevents_exchange_device(struct clock_event_device *old,
 	 */
 	if (old) {
 		module_put(old->owner);
-		clockevents_set_state(old, CLOCK_EVT_STATE_DETACHED);
+		clockevents_switch_state(old, CLOCK_EVT_STATE_DETACHED);
 		list_del(&old->list);
 		list_add(&old->list, &clockevents_released);
 	}
 
 	if (new) {
-		BUG_ON(new->state != CLOCK_EVT_STATE_DETACHED);
+		BUG_ON(!clockevent_state_detached(new));
 		clockevents_shutdown(new);
 	}
 }
@@ -622,7 +639,7 @@ void clockevents_suspend(void)
 	struct clock_event_device *dev;
 
 	list_for_each_entry_reverse(dev, &clockevent_devices, list)
-		if (dev->suspend)
+		if (dev->suspend && !clockevent_state_detached(dev))
 			dev->suspend(dev);
 }
 
@@ -634,7 +651,7 @@ void clockevents_resume(void)
 	struct clock_event_device *dev;
 
 	list_for_each_entry(dev, &clockevent_devices, list)
-		if (dev->resume)
+		if (dev->resume && !clockevent_state_detached(dev))
 			dev->resume(dev);
 }
 
@@ -665,7 +682,7 @@ void tick_cleanup_dead_cpu(int cpu)
 		if (cpumask_test_cpu(cpu, dev->cpumask) &&
 		    cpumask_weight(dev->cpumask) == 1 &&
 		    !tick_is_broadcast_device(dev)) {
-			BUG_ON(dev->state != CLOCK_EVT_STATE_DETACHED);
+			BUG_ON(!clockevent_state_detached(dev));
 			list_del(&dev->list);
 		}
 	}
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 15facb1b9c60..841b72f720e8 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -23,6 +23,8 @@
  *   o Allow clocksource drivers to be unregistered
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/device.h>
 #include <linux/clocksource.h>
 #include <linux/init.h>
@@ -216,10 +218,11 @@ static void clocksource_watchdog(unsigned long data)
 
 		/* Check the deviation from the watchdog clocksource. */
 		if ((abs(cs_nsec - wd_nsec) > WATCHDOG_THRESHOLD)) {
-			pr_warn("timekeeping watchdog: Marking clocksource '%s' as unstable, because the skew is too large:\n", cs->name);
-			pr_warn("	'%s' wd_now: %llx wd_last: %llx mask: %llx\n",
+			pr_warn("timekeeping watchdog: Marking clocksource '%s' as unstable because the skew is too large:\n",
+				cs->name);
+			pr_warn("                      '%s' wd_now: %llx wd_last: %llx mask: %llx\n",
 				watchdog->name, wdnow, wdlast, watchdog->mask);
-			pr_warn("	'%s' cs_now: %llx cs_last: %llx mask: %llx\n",
+			pr_warn("                      '%s' cs_now: %llx cs_last: %llx mask: %llx\n",
 				cs->name, csnow, cslast, cs->mask);
 			__clocksource_unstable(cs);
 			continue;
@@ -567,9 +570,8 @@ static void __clocksource_select(bool skipcur)
 		 */
 		if (!(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES) && oneshot) {
 			/* Override clocksource cannot be used. */
-			printk(KERN_WARNING "Override clocksource %s is not "
-			       "HRT compatible. Cannot switch while in "
-			       "HRT/NOHZ mode\n", cs->name);
+			pr_warn("Override clocksource %s is not HRT compatible - cannot switch while in HRT/NOHZ mode\n",
+				cs->name);
 			override_name[0] = 0;
 		} else
 			/* Override clocksource can be used. */
@@ -708,8 +710,8 @@ void __clocksource_update_freq_scale(struct clocksource *cs, u32 scale, u32 freq
 
 	clocksource_update_max_deferment(cs);
 
-	pr_info("clocksource %s: mask: 0x%llx max_cycles: 0x%llx, max_idle_ns: %lld ns\n",
-			cs->name, cs->mask, cs->max_cycles, cs->max_idle_ns);
+	pr_info("%s: mask: 0x%llx max_cycles: 0x%llx, max_idle_ns: %lld ns\n",
+		cs->name, cs->mask, cs->max_cycles, cs->max_idle_ns);
 }
 EXPORT_SYMBOL_GPL(__clocksource_update_freq_scale);
 
@@ -1008,12 +1010,10 @@ __setup("clocksource=", boot_override_clocksource);
 static int __init boot_override_clock(char* str)
 {
 	if (!strcmp(str, "pmtmr")) {
-		printk("Warning: clock=pmtmr is deprecated. "
-			"Use clocksource=acpi_pm.\n");
+		pr_warn("clock=pmtmr is deprecated - use clocksource=acpi_pm\n");
 		return boot_override_clocksource("acpi_pm");
 	}
-	printk("Warning! clock= boot option is deprecated. "
-		"Use clocksource=xyz\n");
+	pr_warn("clock= boot option is deprecated - use clocksource=xyz\n");
 	return boot_override_clocksource(str);
 }
 
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 93ef7190bdea..5c7ae4b641c4 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -66,33 +66,29 @@
  */
 DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
 {
-
 	.lock = __RAW_SPIN_LOCK_UNLOCKED(hrtimer_bases.lock),
+	.seq = SEQCNT_ZERO(hrtimer_bases.seq),
 	.clock_base =
 	{
 		{
 			.index = HRTIMER_BASE_MONOTONIC,
 			.clockid = CLOCK_MONOTONIC,
 			.get_time = &ktime_get,
-			.resolution = KTIME_LOW_RES,
 		},
 		{
 			.index = HRTIMER_BASE_REALTIME,
 			.clockid = CLOCK_REALTIME,
 			.get_time = &ktime_get_real,
-			.resolution = KTIME_LOW_RES,
 		},
 		{
 			.index = HRTIMER_BASE_BOOTTIME,
 			.clockid = CLOCK_BOOTTIME,
 			.get_time = &ktime_get_boottime,
-			.resolution = KTIME_LOW_RES,
 		},
 		{
 			.index = HRTIMER_BASE_TAI,
 			.clockid = CLOCK_TAI,
 			.get_time = &ktime_get_clocktai,
-			.resolution = KTIME_LOW_RES,
 		},
 	}
 };
@@ -109,27 +105,6 @@ static inline int hrtimer_clockid_to_base(clockid_t clock_id)
 	return hrtimer_clock_to_base_table[clock_id];
 }
 
-
-/*
- * Get the coarse grained time at the softirq based on xtime and
- * wall_to_monotonic.
- */
-static void hrtimer_get_softirq_time(struct hrtimer_cpu_base *base)
-{
-	ktime_t xtim, mono, boot, tai;
-	ktime_t off_real, off_boot, off_tai;
-
-	mono = ktime_get_update_offsets_tick(&off_real, &off_boot, &off_tai);
-	boot = ktime_add(mono, off_boot);
-	xtim = ktime_add(mono, off_real);
-	tai = ktime_add(mono, off_tai);
-
-	base->clock_base[HRTIMER_BASE_REALTIME].softirq_time = xtim;
-	base->clock_base[HRTIMER_BASE_MONOTONIC].softirq_time = mono;
-	base->clock_base[HRTIMER_BASE_BOOTTIME].softirq_time = boot;
-	base->clock_base[HRTIMER_BASE_TAI].softirq_time = tai;
-}
-
 /*
  * Functions and macros which are different for UP/SMP systems are kept in a
  * single place
@@ -137,6 +112,18 @@ static void hrtimer_get_softirq_time(struct hrtimer_cpu_base *base)
 #ifdef CONFIG_SMP
 
 /*
+ * We require the migration_base for lock_hrtimer_base()/switch_hrtimer_base()
+ * such that hrtimer_callback_running() can unconditionally dereference
+ * timer->base->cpu_base
+ */
+static struct hrtimer_cpu_base migration_cpu_base = {
+	.seq = SEQCNT_ZERO(migration_cpu_base),
+	.clock_base = { { .cpu_base = &migration_cpu_base, }, },
+};
+
+#define migration_base	migration_cpu_base.clock_base[0]
+
+/*
  * We are using hashed locking: holding per_cpu(hrtimer_bases)[n].lock
  * means that all timers which are tied to this base via timer->base are
  * locked, and the base itself is locked too.
@@ -145,8 +132,8 @@ static void hrtimer_get_softirq_time(struct hrtimer_cpu_base *base)
  * be found on the lists/queues.
  *
  * When the timer's base is locked, and the timer removed from list, it is
- * possible to set timer->base = NULL and drop the lock: the timer remains
- * locked.
+ * possible to set timer->base = &migration_base and drop the lock: the timer
+ * remains locked.
  */
 static
 struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer,
@@ -156,7 +143,7 @@ struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer,
 
 	for (;;) {
 		base = timer->base;
-		if (likely(base != NULL)) {
+		if (likely(base != &migration_base)) {
 			raw_spin_lock_irqsave(&base->cpu_base->lock, *flags);
 			if (likely(base == timer->base))
 				return base;
@@ -190,6 +177,24 @@ hrtimer_check_target(struct hrtimer *timer, struct hrtimer_clock_base *new_base)
 #endif
 }
 
+#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
+static inline
+struct hrtimer_cpu_base *get_target_base(struct hrtimer_cpu_base *base,
+					 int pinned)
+{
+	if (pinned || !base->migration_enabled)
+		return this_cpu_ptr(&hrtimer_bases);
+	return &per_cpu(hrtimer_bases, get_nohz_timer_target());
+}
+#else
+static inline
+struct hrtimer_cpu_base *get_target_base(struct hrtimer_cpu_base *base,
+					 int pinned)
+{
+	return this_cpu_ptr(&hrtimer_bases);
+}
+#endif
+
 /*
  * Switch the timer base to the current CPU when possible.
  */
@@ -197,14 +202,13 @@ static inline struct hrtimer_clock_base *
 switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_clock_base *base,
 		    int pinned)
 {
+	struct hrtimer_cpu_base *new_cpu_base, *this_base;
 	struct hrtimer_clock_base *new_base;
-	struct hrtimer_cpu_base *new_cpu_base;
-	int this_cpu = smp_processor_id();
-	int cpu = get_nohz_timer_target(pinned);
 	int basenum = base->index;
 
+	this_base = this_cpu_ptr(&hrtimer_bases);
+	new_cpu_base = get_target_base(this_base, pinned);
 again:
-	new_cpu_base = &per_cpu(hrtimer_bases, cpu);
 	new_base = &new_cpu_base->clock_base[basenum];
 
 	if (base != new_base) {
@@ -220,22 +224,24 @@ again:
 		if (unlikely(hrtimer_callback_running(timer)))
 			return base;
 
-		/* See the comment in lock_timer_base() */
-		timer->base = NULL;
+		/* See the comment in lock_hrtimer_base() */
+		timer->base = &migration_base;
 		raw_spin_unlock(&base->cpu_base->lock);
 		raw_spin_lock(&new_base->cpu_base->lock);
 
-		if (cpu != this_cpu && hrtimer_check_target(timer, new_base)) {
-			cpu = this_cpu;
+		if (new_cpu_base != this_base &&
+		    hrtimer_check_target(timer, new_base)) {
 			raw_spin_unlock(&new_base->cpu_base->lock);
 			raw_spin_lock(&base->cpu_base->lock);
+			new_cpu_base = this_base;
 			timer->base = base;
 			goto again;
 		}
 		timer->base = new_base;
 	} else {
-		if (cpu != this_cpu && hrtimer_check_target(timer, new_base)) {
-			cpu = this_cpu;
+		if (new_cpu_base != this_base &&
+		    hrtimer_check_target(timer, new_base)) {
+			new_cpu_base = this_base;
 			goto again;
 		}
 	}
@@ -443,24 +449,35 @@ static inline void debug_deactivate(struct hrtimer *timer)
 }
 
 #if defined(CONFIG_NO_HZ_COMMON) || defined(CONFIG_HIGH_RES_TIMERS)
+static inline void hrtimer_update_next_timer(struct hrtimer_cpu_base *cpu_base,
+					     struct hrtimer *timer)
+{
+#ifdef CONFIG_HIGH_RES_TIMERS
+	cpu_base->next_timer = timer;
+#endif
+}
+
 static ktime_t __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base)
 {
 	struct hrtimer_clock_base *base = cpu_base->clock_base;
 	ktime_t expires, expires_next = { .tv64 = KTIME_MAX };
-	int i;
+	unsigned int active = cpu_base->active_bases;
 
-	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++, base++) {
+	hrtimer_update_next_timer(cpu_base, NULL);
+	for (; active; base++, active >>= 1) {
 		struct timerqueue_node *next;
 		struct hrtimer *timer;
 
-		next = timerqueue_getnext(&base->active);
-		if (!next)
+		if (!(active & 0x01))
 			continue;
 
+		next = timerqueue_getnext(&base->active);
 		timer = container_of(next, struct hrtimer, node);
 		expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
-		if (expires.tv64 < expires_next.tv64)
+		if (expires.tv64 < expires_next.tv64) {
 			expires_next = expires;
+			hrtimer_update_next_timer(cpu_base, timer);
+		}
 	}
 	/*
 	 * clock_was_set() might have changed base->offset of any of
@@ -473,6 +490,16 @@ static ktime_t __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base)
 }
 #endif
 
+static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base)
+{
+	ktime_t *offs_real = &base->clock_base[HRTIMER_BASE_REALTIME].offset;
+	ktime_t *offs_boot = &base->clock_base[HRTIMER_BASE_BOOTTIME].offset;
+	ktime_t *offs_tai = &base->clock_base[HRTIMER_BASE_TAI].offset;
+
+	return ktime_get_update_offsets_now(&base->clock_was_set_seq,
+					    offs_real, offs_boot, offs_tai);
+}
+
 /* High resolution timer related functions */
 #ifdef CONFIG_HIGH_RES_TIMERS
 
@@ -480,6 +507,8 @@ static ktime_t __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base)
  * High resolution timer enabled ?
  */
 static int hrtimer_hres_enabled __read_mostly  = 1;
+unsigned int hrtimer_resolution __read_mostly = LOW_RES_NSEC;
+EXPORT_SYMBOL_GPL(hrtimer_resolution);
 
 /*
  * Enable / Disable high resolution mode
@@ -508,9 +537,14 @@ static inline int hrtimer_is_hres_enabled(void)
 /*
  * Is the high resolution mode active ?
  */
+static inline int __hrtimer_hres_active(struct hrtimer_cpu_base *cpu_base)
+{
+	return cpu_base->hres_active;
+}
+
 static inline int hrtimer_hres_active(void)
 {
-	return __this_cpu_read(hrtimer_bases.hres_active);
+	return __hrtimer_hres_active(this_cpu_ptr(&hrtimer_bases));
 }
 
 /*
@@ -521,7 +555,12 @@ static inline int hrtimer_hres_active(void)
 static void
 hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal)
 {
-	ktime_t expires_next = __hrtimer_get_next_event(cpu_base);
+	ktime_t expires_next;
+
+	if (!cpu_base->hres_active)
+		return;
+
+	expires_next = __hrtimer_get_next_event(cpu_base);
 
 	if (skip_equal && expires_next.tv64 == cpu_base->expires_next.tv64)
 		return;
@@ -545,63 +584,53 @@ hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal)
 	if (cpu_base->hang_detected)
 		return;
 
-	if (cpu_base->expires_next.tv64 != KTIME_MAX)
-		tick_program_event(cpu_base->expires_next, 1);
+	tick_program_event(cpu_base->expires_next, 1);
 }
 
 /*
- * Shared reprogramming for clock_realtime and clock_monotonic
- *
  * When a timer is enqueued and expires earlier than the already enqueued
  * timers, we have to check, whether it expires earlier than the timer for
  * which the clock event device was armed.
  *
- * Note, that in case the state has HRTIMER_STATE_CALLBACK set, no reprogramming
- * and no expiry check happens. The timer gets enqueued into the rbtree. The
- * reprogramming and expiry check is done in the hrtimer_interrupt or in the
- * softirq.
- *
  * Called with interrupts disabled and base->cpu_base.lock held
  */
-static int hrtimer_reprogram(struct hrtimer *timer,
-			     struct hrtimer_clock_base *base)
+static void hrtimer_reprogram(struct hrtimer *timer,
+			      struct hrtimer_clock_base *base)
 {
 	struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
 	ktime_t expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
-	int res;
 
 	WARN_ON_ONCE(hrtimer_get_expires_tv64(timer) < 0);
 
 	/*
-	 * When the callback is running, we do not reprogram the clock event
-	 * device. The timer callback is either running on a different CPU or
-	 * the callback is executed in the hrtimer_interrupt context. The
-	 * reprogramming is handled either by the softirq, which called the
-	 * callback or at the end of the hrtimer_interrupt.
+	 * If the timer is not on the current cpu, we cannot reprogram
+	 * the other cpus clock event device.
 	 */
-	if (hrtimer_callback_running(timer))
-		return 0;
+	if (base->cpu_base != cpu_base)
+		return;
+
+	/*
+	 * If the hrtimer interrupt is running, then it will
+	 * reevaluate the clock bases and reprogram the clock event
+	 * device. The callbacks are always executed in hard interrupt
+	 * context so we don't need an extra check for a running
+	 * callback.
+	 */
+	if (cpu_base->in_hrtirq)
+		return;
 
 	/*
 	 * CLOCK_REALTIME timer might be requested with an absolute
-	 * expiry time which is less than base->offset. Nothing wrong
-	 * about that, just avoid to call into the tick code, which
-	 * has now objections against negative expiry values.
+	 * expiry time which is less than base->offset. Set it to 0.
 	 */
 	if (expires.tv64 < 0)
-		return -ETIME;
+		expires.tv64 = 0;
 
 	if (expires.tv64 >= cpu_base->expires_next.tv64)
-		return 0;
+		return;
 
-	/*
-	 * When the target cpu of the timer is currently executing
-	 * hrtimer_interrupt(), then we do not touch the clock event
-	 * device. hrtimer_interrupt() will reevaluate all clock bases
-	 * before reprogramming the device.
-	 */
-	if (cpu_base->in_hrtirq)
-		return 0;
+	/* Update the pointer to the next expiring timer */
+	cpu_base->next_timer = timer;
 
 	/*
 	 * If a hang was detected in the last timer interrupt then we
@@ -610,15 +639,14 @@ static int hrtimer_reprogram(struct hrtimer *timer,
 	 * to make progress.
 	 */
 	if (cpu_base->hang_detected)
-		return 0;
+		return;
 
 	/*
-	 * Clockevents returns -ETIME, when the event was in the past.
+	 * Program the timer hardware. We enforce the expiry for
+	 * events which are already in the past.
 	 */
-	res = tick_program_event(expires, 0);
-	if (!IS_ERR_VALUE(res))
-		cpu_base->expires_next = expires;
-	return res;
+	cpu_base->expires_next = expires;
+	tick_program_event(expires, 1);
 }
 
 /*
@@ -630,15 +658,6 @@ static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base)
 	base->hres_active = 0;
 }
 
-static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base)
-{
-	ktime_t *offs_real = &base->clock_base[HRTIMER_BASE_REALTIME].offset;
-	ktime_t *offs_boot = &base->clock_base[HRTIMER_BASE_BOOTTIME].offset;
-	ktime_t *offs_tai = &base->clock_base[HRTIMER_BASE_TAI].offset;
-
-	return ktime_get_update_offsets_now(offs_real, offs_boot, offs_tai);
-}
-
 /*
  * Retrigger next event is called after clock was set
  *
@@ -648,7 +667,7 @@ static void retrigger_next_event(void *arg)
 {
 	struct hrtimer_cpu_base *base = this_cpu_ptr(&hrtimer_bases);
 
-	if (!hrtimer_hres_active())
+	if (!base->hres_active)
 		return;
 
 	raw_spin_lock(&base->lock);
@@ -662,29 +681,19 @@ static void retrigger_next_event(void *arg)
  */
 static int hrtimer_switch_to_hres(void)
 {
-	int i, cpu = smp_processor_id();
-	struct hrtimer_cpu_base *base = &per_cpu(hrtimer_bases, cpu);
-	unsigned long flags;
-
-	if (base->hres_active)
-		return 1;
-
-	local_irq_save(flags);
+	struct hrtimer_cpu_base *base = this_cpu_ptr(&hrtimer_bases);
 
 	if (tick_init_highres()) {
-		local_irq_restore(flags);
 		printk(KERN_WARNING "Could not switch to high resolution "
-				    "mode on CPU %d\n", cpu);
+				    "mode on CPU %d\n", base->cpu);
 		return 0;
 	}
 	base->hres_active = 1;
-	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++)
-		base->clock_base[i].resolution = KTIME_HIGH_RES;
+	hrtimer_resolution = HIGH_RES_NSEC;
 
 	tick_setup_sched_timer();
 	/* "Retrigger" the interrupt to get things going */
 	retrigger_next_event(NULL);
-	local_irq_restore(flags);
 	return 1;
 }
 
@@ -706,6 +715,7 @@ void clock_was_set_delayed(void)
 
 #else
 
+static inline int __hrtimer_hres_active(struct hrtimer_cpu_base *b) { return 0; }
 static inline int hrtimer_hres_active(void) { return 0; }
 static inline int hrtimer_is_hres_enabled(void) { return 0; }
 static inline int hrtimer_switch_to_hres(void) { return 0; }
@@ -803,6 +813,14 @@ void unlock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags)
  *
  * Forward the timer expiry so it will expire in the future.
  * Returns the number of overruns.
+ *
+ * Can be safely called from the callback function of @timer. If
+ * called from other contexts @timer must neither be enqueued nor
+ * running the callback and the caller needs to take care of
+ * serialization.
+ *
+ * Note: This only updates the timer expiry value and does not requeue
+ * the timer.
  */
 u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval)
 {
@@ -814,8 +832,11 @@ u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval)
 	if (delta.tv64 < 0)
 		return 0;
 
-	if (interval.tv64 < timer->base->resolution.tv64)
-		interval.tv64 = timer->base->resolution.tv64;
+	if (WARN_ON(timer->state & HRTIMER_STATE_ENQUEUED))
+		return 0;
+
+	if (interval.tv64 < hrtimer_resolution)
+		interval.tv64 = hrtimer_resolution;
 
 	if (unlikely(delta.tv64 >= interval.tv64)) {
 		s64 incr = ktime_to_ns(interval);
@@ -849,16 +870,11 @@ static int enqueue_hrtimer(struct hrtimer *timer,
 {
 	debug_activate(timer);
 
-	timerqueue_add(&base->active, &timer->node);
 	base->cpu_base->active_bases |= 1 << base->index;
 
-	/*
-	 * HRTIMER_STATE_ENQUEUED is or'ed to the current state to preserve the
-	 * state of a possibly running callback.
-	 */
-	timer->state |= HRTIMER_STATE_ENQUEUED;
+	timer->state = HRTIMER_STATE_ENQUEUED;
 
-	return (&timer->node == base->active.next);
+	return timerqueue_add(&base->active, &timer->node);
 }
 
 /*
@@ -875,39 +891,38 @@ static void __remove_hrtimer(struct hrtimer *timer,
 			     struct hrtimer_clock_base *base,
 			     unsigned long newstate, int reprogram)
 {
-	struct timerqueue_node *next_timer;
-	if (!(timer->state & HRTIMER_STATE_ENQUEUED))
-		goto out;
+	struct hrtimer_cpu_base *cpu_base = base->cpu_base;
+	unsigned int state = timer->state;
+
+	timer->state = newstate;
+	if (!(state & HRTIMER_STATE_ENQUEUED))
+		return;
+
+	if (!timerqueue_del(&base->active, &timer->node))
+		cpu_base->active_bases &= ~(1 << base->index);
 
-	next_timer = timerqueue_getnext(&base->active);
-	timerqueue_del(&base->active, &timer->node);
-	if (&timer->node == next_timer) {
 #ifdef CONFIG_HIGH_RES_TIMERS
-		/* Reprogram the clock event device. if enabled */
-		if (reprogram && hrtimer_hres_active()) {
-			ktime_t expires;
-
-			expires = ktime_sub(hrtimer_get_expires(timer),
-					    base->offset);
-			if (base->cpu_base->expires_next.tv64 == expires.tv64)
-				hrtimer_force_reprogram(base->cpu_base, 1);
-		}
+	/*
+	 * Note: If reprogram is false we do not update
+	 * cpu_base->next_timer. This happens when we remove the first
+	 * timer on a remote cpu. No harm as we never dereference
+	 * cpu_base->next_timer. So the worst thing what can happen is
+	 * an superflous call to hrtimer_force_reprogram() on the
+	 * remote cpu later on if the same timer gets enqueued again.
+	 */
+	if (reprogram && timer == cpu_base->next_timer)
+		hrtimer_force_reprogram(cpu_base, 1);
 #endif
-	}
-	if (!timerqueue_getnext(&base->active))
-		base->cpu_base->active_bases &= ~(1 << base->index);
-out:
-	timer->state = newstate;
 }
 
 /*
  * remove hrtimer, called with base lock held
  */
 static inline int
-remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base)
+remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, bool restart)
 {
 	if (hrtimer_is_queued(timer)) {
-		unsigned long state;
+		unsigned long state = timer->state;
 		int reprogram;
 
 		/*
@@ -921,30 +936,35 @@ remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base)
 		debug_deactivate(timer);
 		timer_stats_hrtimer_clear_start_info(timer);
 		reprogram = base->cpu_base == this_cpu_ptr(&hrtimer_bases);
-		/*
-		 * We must preserve the CALLBACK state flag here,
-		 * otherwise we could move the timer base in
-		 * switch_hrtimer_base.
-		 */
-		state = timer->state & HRTIMER_STATE_CALLBACK;
+
+		if (!restart)
+			state = HRTIMER_STATE_INACTIVE;
+
 		__remove_hrtimer(timer, base, state, reprogram);
 		return 1;
 	}
 	return 0;
 }
 
-int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
-		unsigned long delta_ns, const enum hrtimer_mode mode,
-		int wakeup)
+/**
+ * hrtimer_start_range_ns - (re)start an hrtimer on the current CPU
+ * @timer:	the timer to be added
+ * @tim:	expiry time
+ * @delta_ns:	"slack" range for the timer
+ * @mode:	expiry mode: absolute (HRTIMER_MODE_ABS) or
+ *		relative (HRTIMER_MODE_REL)
+ */
+void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
+			    unsigned long delta_ns, const enum hrtimer_mode mode)
 {
 	struct hrtimer_clock_base *base, *new_base;
 	unsigned long flags;
-	int ret, leftmost;
+	int leftmost;
 
 	base = lock_hrtimer_base(timer, &flags);
 
 	/* Remove an active timer from the queue: */
-	ret = remove_hrtimer(timer, base);
+	remove_hrtimer(timer, base, true);
 
 	if (mode & HRTIMER_MODE_REL) {
 		tim = ktime_add_safe(tim, base->get_time());
@@ -956,7 +976,7 @@ int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
 		 * timeouts. This will go away with the GTOD framework.
 		 */
 #ifdef CONFIG_TIME_LOW_RES
-		tim = ktime_add_safe(tim, base->resolution);
+		tim = ktime_add_safe(tim, ktime_set(0, hrtimer_resolution));
 #endif
 	}
 
@@ -968,85 +988,25 @@ int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
 	timer_stats_hrtimer_set_start_info(timer);
 
 	leftmost = enqueue_hrtimer(timer, new_base);
-
-	if (!leftmost) {
-		unlock_hrtimer_base(timer, &flags);
-		return ret;
-	}
+	if (!leftmost)
+		goto unlock;
 
 	if (!hrtimer_is_hres_active(timer)) {
 		/*
 		 * Kick to reschedule the next tick to handle the new timer
 		 * on dynticks target.
 		 */
-		wake_up_nohz_cpu(new_base->cpu_base->cpu);
-	} else if (new_base->cpu_base == this_cpu_ptr(&hrtimer_bases) &&
-			hrtimer_reprogram(timer, new_base)) {
-		/*
-		 * Only allow reprogramming if the new base is on this CPU.
-		 * (it might still be on another CPU if the timer was pending)
-		 *
-		 * XXX send_remote_softirq() ?
-		 */
-		if (wakeup) {
-			/*
-			 * We need to drop cpu_base->lock to avoid a
-			 * lock ordering issue vs. rq->lock.
-			 */
-			raw_spin_unlock(&new_base->cpu_base->lock);
-			raise_softirq_irqoff(HRTIMER_SOFTIRQ);
-			local_irq_restore(flags);
-			return ret;
-		} else {
-			__raise_softirq_irqoff(HRTIMER_SOFTIRQ);
-		}
+		if (new_base->cpu_base->nohz_active)
+			wake_up_nohz_cpu(new_base->cpu_base->cpu);
+	} else {
+		hrtimer_reprogram(timer, new_base);
 	}
-
+unlock:
 	unlock_hrtimer_base(timer, &flags);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(__hrtimer_start_range_ns);
-
-/**
- * hrtimer_start_range_ns - (re)start an hrtimer on the current CPU
- * @timer:	the timer to be added
- * @tim:	expiry time
- * @delta_ns:	"slack" range for the timer
- * @mode:	expiry mode: absolute (HRTIMER_MODE_ABS) or
- *		relative (HRTIMER_MODE_REL)
- *
- * Returns:
- *  0 on success
- *  1 when the timer was active
- */
-int hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
-		unsigned long delta_ns, const enum hrtimer_mode mode)
-{
-	return __hrtimer_start_range_ns(timer, tim, delta_ns, mode, 1);
 }
 EXPORT_SYMBOL_GPL(hrtimer_start_range_ns);
 
 /**
- * hrtimer_start - (re)start an hrtimer on the current CPU
- * @timer:	the timer to be added
- * @tim:	expiry time
- * @mode:	expiry mode: absolute (HRTIMER_MODE_ABS) or
- *		relative (HRTIMER_MODE_REL)
- *
- * Returns:
- *  0 on success
- *  1 when the timer was active
- */
-int
-hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode)
-{
-	return __hrtimer_start_range_ns(timer, tim, 0, mode, 1);
-}
-EXPORT_SYMBOL_GPL(hrtimer_start);
-
-
-/**
  * hrtimer_try_to_cancel - try to deactivate a timer
  * @timer:	hrtimer to stop
  *
@@ -1062,10 +1022,19 @@ int hrtimer_try_to_cancel(struct hrtimer *timer)
 	unsigned long flags;
 	int ret = -1;
 
+	/*
+	 * Check lockless first. If the timer is not active (neither
+	 * enqueued nor running the callback, nothing to do here.  The
+	 * base lock does not serialize against a concurrent enqueue,
+	 * so we can avoid taking it.
+	 */
+	if (!hrtimer_active(timer))
+		return 0;
+
 	base = lock_hrtimer_base(timer, &flags);
 
 	if (!hrtimer_callback_running(timer))
-		ret = remove_hrtimer(timer, base);
+		ret = remove_hrtimer(timer, base, false);
 
 	unlock_hrtimer_base(timer, &flags);
 
@@ -1115,26 +1084,22 @@ EXPORT_SYMBOL_GPL(hrtimer_get_remaining);
 /**
  * hrtimer_get_next_event - get the time until next expiry event
  *
- * Returns the delta to the next expiry event or KTIME_MAX if no timer
- * is pending.
+ * Returns the next expiry time or KTIME_MAX if no timer is pending.
  */
-ktime_t hrtimer_get_next_event(void)
+u64 hrtimer_get_next_event(void)
 {
 	struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
-	ktime_t mindelta = { .tv64 = KTIME_MAX };
+	u64 expires = KTIME_MAX;
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&cpu_base->lock, flags);
 
-	if (!hrtimer_hres_active())
-		mindelta = ktime_sub(__hrtimer_get_next_event(cpu_base),
-				     ktime_get());
+	if (!__hrtimer_hres_active(cpu_base))
+		expires = __hrtimer_get_next_event(cpu_base).tv64;
 
 	raw_spin_unlock_irqrestore(&cpu_base->lock, flags);
 
-	if (mindelta.tv64 < 0)
-		mindelta.tv64 = 0;
-	return mindelta;
+	return expires;
 }
 #endif
 
@@ -1176,37 +1141,73 @@ void hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
 }
 EXPORT_SYMBOL_GPL(hrtimer_init);
 
-/**
- * hrtimer_get_res - get the timer resolution for a clock
- * @which_clock: which clock to query
- * @tp:		 pointer to timespec variable to store the resolution
+/*
+ * A timer is active, when it is enqueued into the rbtree or the
+ * callback function is running or it's in the state of being migrated
+ * to another cpu.
  *
- * Store the resolution of the clock selected by @which_clock in the
- * variable pointed to by @tp.
+ * It is important for this function to not return a false negative.
  */
-int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp)
+bool hrtimer_active(const struct hrtimer *timer)
 {
 	struct hrtimer_cpu_base *cpu_base;
-	int base = hrtimer_clockid_to_base(which_clock);
+	unsigned int seq;
 
-	cpu_base = raw_cpu_ptr(&hrtimer_bases);
-	*tp = ktime_to_timespec(cpu_base->clock_base[base].resolution);
+	do {
+		cpu_base = READ_ONCE(timer->base->cpu_base);
+		seq = raw_read_seqcount_begin(&cpu_base->seq);
 
-	return 0;
+		if (timer->state != HRTIMER_STATE_INACTIVE ||
+		    cpu_base->running == timer)
+			return true;
+
+	} while (read_seqcount_retry(&cpu_base->seq, seq) ||
+		 cpu_base != READ_ONCE(timer->base->cpu_base));
+
+	return false;
 }
-EXPORT_SYMBOL_GPL(hrtimer_get_res);
+EXPORT_SYMBOL_GPL(hrtimer_active);
 
-static void __run_hrtimer(struct hrtimer *timer, ktime_t *now)
+/*
+ * The write_seqcount_barrier()s in __run_hrtimer() split the thing into 3
+ * distinct sections:
+ *
+ *  - queued:	the timer is queued
+ *  - callback:	the timer is being ran
+ *  - post:	the timer is inactive or (re)queued
+ *
+ * On the read side we ensure we observe timer->state and cpu_base->running
+ * from the same section, if anything changed while we looked at it, we retry.
+ * This includes timer->base changing because sequence numbers alone are
+ * insufficient for that.
+ *
+ * The sequence numbers are required because otherwise we could still observe
+ * a false negative if the read side got smeared over multiple consequtive
+ * __run_hrtimer() invocations.
+ */
+
+static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base,
+			  struct hrtimer_clock_base *base,
+			  struct hrtimer *timer, ktime_t *now)
 {
-	struct hrtimer_clock_base *base = timer->base;
-	struct hrtimer_cpu_base *cpu_base = base->cpu_base;
 	enum hrtimer_restart (*fn)(struct hrtimer *);
 	int restart;
 
-	WARN_ON(!irqs_disabled());
+	lockdep_assert_held(&cpu_base->lock);
 
 	debug_deactivate(timer);
-	__remove_hrtimer(timer, base, HRTIMER_STATE_CALLBACK, 0);
+	cpu_base->running = timer;
+
+	/*
+	 * Separate the ->running assignment from the ->state assignment.
+	 *
+	 * As with a regular write barrier, this ensures the read side in
+	 * hrtimer_active() cannot observe cpu_base->running == NULL &&
+	 * timer->state == INACTIVE.
+	 */
+	raw_write_seqcount_barrier(&cpu_base->seq);
+
+	__remove_hrtimer(timer, base, HRTIMER_STATE_INACTIVE, 0);
 	timer_stats_account_hrtimer(timer);
 	fn = timer->function;
 
@@ -1222,58 +1223,43 @@ static void __run_hrtimer(struct hrtimer *timer, ktime_t *now)
 	raw_spin_lock(&cpu_base->lock);
 
 	/*
-	 * Note: We clear the CALLBACK bit after enqueue_hrtimer and
+	 * Note: We clear the running state after enqueue_hrtimer and
 	 * we do not reprogramm the event hardware. Happens either in
 	 * hrtimer_start_range_ns() or in hrtimer_interrupt()
+	 *
+	 * Note: Because we dropped the cpu_base->lock above,
+	 * hrtimer_start_range_ns() can have popped in and enqueued the timer
+	 * for us already.
 	 */
-	if (restart != HRTIMER_NORESTART) {
-		BUG_ON(timer->state != HRTIMER_STATE_CALLBACK);
+	if (restart != HRTIMER_NORESTART &&
+	    !(timer->state & HRTIMER_STATE_ENQUEUED))
 		enqueue_hrtimer(timer, base);
-	}
 
-	WARN_ON_ONCE(!(timer->state & HRTIMER_STATE_CALLBACK));
+	/*
+	 * Separate the ->running assignment from the ->state assignment.
+	 *
+	 * As with a regular write barrier, this ensures the read side in
+	 * hrtimer_active() cannot observe cpu_base->running == NULL &&
+	 * timer->state == INACTIVE.
+	 */
+	raw_write_seqcount_barrier(&cpu_base->seq);
 
-	timer->state &= ~HRTIMER_STATE_CALLBACK;
+	WARN_ON_ONCE(cpu_base->running != timer);
+	cpu_base->running = NULL;
 }
 
-#ifdef CONFIG_HIGH_RES_TIMERS
-
-/*
- * High resolution timer interrupt
- * Called with interrupts disabled
- */
-void hrtimer_interrupt(struct clock_event_device *dev)
+static void __hrtimer_run_queues(struct hrtimer_cpu_base *cpu_base, ktime_t now)
 {
-	struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
-	ktime_t expires_next, now, entry_time, delta;
-	int i, retries = 0;
-
-	BUG_ON(!cpu_base->hres_active);
-	cpu_base->nr_events++;
-	dev->next_event.tv64 = KTIME_MAX;
-
-	raw_spin_lock(&cpu_base->lock);
-	entry_time = now = hrtimer_update_base(cpu_base);
-retry:
-	cpu_base->in_hrtirq = 1;
-	/*
-	 * We set expires_next to KTIME_MAX here with cpu_base->lock
-	 * held to prevent that a timer is enqueued in our queue via
-	 * the migration code. This does not affect enqueueing of
-	 * timers which run their callback and need to be requeued on
-	 * this CPU.
-	 */
-	cpu_base->expires_next.tv64 = KTIME_MAX;
+	struct hrtimer_clock_base *base = cpu_base->clock_base;
+	unsigned int active = cpu_base->active_bases;
 
-	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
-		struct hrtimer_clock_base *base;
+	for (; active; base++, active >>= 1) {
 		struct timerqueue_node *node;
 		ktime_t basenow;
 
-		if (!(cpu_base->active_bases & (1 << i)))
+		if (!(active & 0x01))
 			continue;
 
-		base = cpu_base->clock_base + i;
 		basenow = ktime_add(now, base->offset);
 
 		while ((node = timerqueue_getnext(&base->active))) {
@@ -1296,9 +1282,42 @@ retry:
 			if (basenow.tv64 < hrtimer_get_softexpires_tv64(timer))
 				break;
 
-			__run_hrtimer(timer, &basenow);
+			__run_hrtimer(cpu_base, base, timer, &basenow);
 		}
 	}
+}
+
+#ifdef CONFIG_HIGH_RES_TIMERS
+
+/*
+ * High resolution timer interrupt
+ * Called with interrupts disabled
+ */
+void hrtimer_interrupt(struct clock_event_device *dev)
+{
+	struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
+	ktime_t expires_next, now, entry_time, delta;
+	int retries = 0;
+
+	BUG_ON(!cpu_base->hres_active);
+	cpu_base->nr_events++;
+	dev->next_event.tv64 = KTIME_MAX;
+
+	raw_spin_lock(&cpu_base->lock);
+	entry_time = now = hrtimer_update_base(cpu_base);
+retry:
+	cpu_base->in_hrtirq = 1;
+	/*
+	 * We set expires_next to KTIME_MAX here with cpu_base->lock
+	 * held to prevent that a timer is enqueued in our queue via
+	 * the migration code. This does not affect enqueueing of
+	 * timers which run their callback and need to be requeued on
+	 * this CPU.
+	 */
+	cpu_base->expires_next.tv64 = KTIME_MAX;
+
+	__hrtimer_run_queues(cpu_base, now);
+
 	/* Reevaluate the clock bases for the next expiry */
 	expires_next = __hrtimer_get_next_event(cpu_base);
 	/*
@@ -1310,8 +1329,7 @@ retry:
 	raw_spin_unlock(&cpu_base->lock);
 
 	/* Reprogramming necessary ? */
-	if (expires_next.tv64 == KTIME_MAX ||
-	    !tick_program_event(expires_next, 0)) {
+	if (!tick_program_event(expires_next, 0)) {
 		cpu_base->hang_detected = 0;
 		return;
 	}
@@ -1344,8 +1362,8 @@ retry:
 	cpu_base->hang_detected = 1;
 	raw_spin_unlock(&cpu_base->lock);
 	delta = ktime_sub(now, entry_time);
-	if (delta.tv64 > cpu_base->max_hang_time.tv64)
-		cpu_base->max_hang_time = delta;
+	if ((unsigned int)delta.tv64 > cpu_base->max_hang_time)
+		cpu_base->max_hang_time = (unsigned int) delta.tv64;
 	/*
 	 * Limit it to a sensible value as we enforce a longer
 	 * delay. Give the CPU at least 100ms to catch up.
@@ -1363,7 +1381,7 @@ retry:
  * local version of hrtimer_peek_ahead_timers() called with interrupts
  * disabled.
  */
-static void __hrtimer_peek_ahead_timers(void)
+static inline void __hrtimer_peek_ahead_timers(void)
 {
 	struct tick_device *td;
 
@@ -1375,29 +1393,6 @@ static void __hrtimer_peek_ahead_timers(void)
 		hrtimer_interrupt(td->evtdev);
 }
 
-/**
- * hrtimer_peek_ahead_timers -- run soft-expired timers now
- *
- * hrtimer_peek_ahead_timers will peek at the timer queue of
- * the current cpu and check if there are any timers for which
- * the soft expires time has passed. If any such timers exist,
- * they are run immediately and then removed from the timer queue.
- *
- */
-void hrtimer_peek_ahead_timers(void)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);
-	__hrtimer_peek_ahead_timers();
-	local_irq_restore(flags);
-}
-
-static void run_hrtimer_softirq(struct softirq_action *h)
-{
-	hrtimer_peek_ahead_timers();
-}
-
 #else /* CONFIG_HIGH_RES_TIMERS */
 
 static inline void __hrtimer_peek_ahead_timers(void) { }
@@ -1405,66 +1400,32 @@ static inline void __hrtimer_peek_ahead_timers(void) { }
 #endif	/* !CONFIG_HIGH_RES_TIMERS */
 
 /*
- * Called from timer softirq every jiffy, expire hrtimers:
- *
- * For HRT its the fall back code to run the softirq in the timer
- * softirq context in case the hrtimer initialization failed or has
- * not been done yet.
+ * Called from run_local_timers in hardirq context every jiffy
  */
-void hrtimer_run_pending(void)
+void hrtimer_run_queues(void)
 {
-	if (hrtimer_hres_active())
+	struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
+	ktime_t now;
+
+	if (__hrtimer_hres_active(cpu_base))
 		return;
 
 	/*
-	 * This _is_ ugly: We have to check in the softirq context,
-	 * whether we can switch to highres and / or nohz mode. The
-	 * clocksource switch happens in the timer interrupt with
-	 * xtime_lock held. Notification from there only sets the
-	 * check bit in the tick_oneshot code, otherwise we might
-	 * deadlock vs. xtime_lock.
+	 * This _is_ ugly: We have to check periodically, whether we
+	 * can switch to highres and / or nohz mode. The clocksource
+	 * switch happens with xtime_lock held. Notification from
+	 * there only sets the check bit in the tick_oneshot code,
+	 * otherwise we might deadlock vs. xtime_lock.
 	 */
-	if (tick_check_oneshot_change(!hrtimer_is_hres_enabled()))
+	if (tick_check_oneshot_change(!hrtimer_is_hres_enabled())) {
 		hrtimer_switch_to_hres();
-}
-
-/*
- * Called from hardirq context every jiffy
- */
-void hrtimer_run_queues(void)
-{
-	struct timerqueue_node *node;
-	struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
-	struct hrtimer_clock_base *base;
-	int index, gettime = 1;
-
-	if (hrtimer_hres_active())
 		return;
-
-	for (index = 0; index < HRTIMER_MAX_CLOCK_BASES; index++) {
-		base = &cpu_base->clock_base[index];
-		if (!timerqueue_getnext(&base->active))
-			continue;
-
-		if (gettime) {
-			hrtimer_get_softirq_time(cpu_base);
-			gettime = 0;
-		}
-
-		raw_spin_lock(&cpu_base->lock);
-
-		while ((node = timerqueue_getnext(&base->active))) {
-			struct hrtimer *timer;
-
-			timer = container_of(node, struct hrtimer, node);
-			if (base->softirq_time.tv64 <=
-					hrtimer_get_expires_tv64(timer))
-				break;
-
-			__run_hrtimer(timer, &base->softirq_time);
-		}
-		raw_spin_unlock(&cpu_base->lock);
 	}
+
+	raw_spin_lock(&cpu_base->lock);
+	now = hrtimer_update_base(cpu_base);
+	__hrtimer_run_queues(cpu_base, now);
+	raw_spin_unlock(&cpu_base->lock);
 }
 
 /*
@@ -1497,8 +1458,6 @@ static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mod
 	do {
 		set_current_state(TASK_INTERRUPTIBLE);
 		hrtimer_start_expires(&t->timer, mode);
-		if (!hrtimer_active(&t->timer))
-			t->task = NULL;
 
 		if (likely(t->task))
 			freezable_schedule();
@@ -1642,11 +1601,11 @@ static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base,
 		debug_deactivate(timer);
 
 		/*
-		 * Mark it as STATE_MIGRATE not INACTIVE otherwise the
+		 * Mark it as ENQUEUED not INACTIVE otherwise the
 		 * timer could be seen as !active and just vanish away
 		 * under us on another CPU
 		 */
-		__remove_hrtimer(timer, old_base, HRTIMER_STATE_MIGRATE, 0);
+		__remove_hrtimer(timer, old_base, HRTIMER_STATE_ENQUEUED, 0);
 		timer->base = new_base;
 		/*
 		 * Enqueue the timers on the new cpu. This does not
@@ -1657,9 +1616,6 @@ static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base,
 		 * event device.
 		 */
 		enqueue_hrtimer(timer, new_base);
-
-		/* Clear the migration state bit */
-		timer->state &= ~HRTIMER_STATE_MIGRATE;
 	}
 }
 
@@ -1731,9 +1687,6 @@ void __init hrtimers_init(void)
 	hrtimer_cpu_notify(&hrtimers_nb, (unsigned long)CPU_UP_PREPARE,
 			  (void *)(long)smp_processor_id());
 	register_cpu_notifier(&hrtimers_nb);
-#ifdef CONFIG_HIGH_RES_TIMERS
-	open_softirq(HRTIMER_SOFTIRQ, run_hrtimer_softirq);
-#endif
 }
 
 /**
@@ -1772,8 +1725,6 @@ schedule_hrtimeout_range_clock(ktime_t *expires, unsigned long delta,
 	hrtimer_init_sleeper(&t, current);
 
 	hrtimer_start_expires(&t.timer, mode);
-	if (!hrtimer_active(&t.timer))
-		t.task = NULL;
 
 	if (likely(t.task))
 		schedule();
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 7a681003001c..fb4d98c7fd43 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -35,6 +35,7 @@ unsigned long			tick_nsec;
 static u64			tick_length;
 static u64			tick_length_base;
 
+#define SECS_PER_DAY		86400
 #define MAX_TICKADJ		500LL		/* usecs */
 #define MAX_TICKADJ_SCALED \
 	(((MAX_TICKADJ * NSEC_PER_USEC) << NTP_SCALE_SHIFT) / NTP_INTERVAL_FREQ)
@@ -76,6 +77,9 @@ static long			time_adjust;
 /* constant (boot-param configurable) NTP tick adjustment (upscaled)	*/
 static s64			ntp_tick_adj;
 
+/* second value of the next pending leapsecond, or TIME64_MAX if no leap */
+static time64_t			ntp_next_leap_sec = TIME64_MAX;
+
 #ifdef CONFIG_NTP_PPS
 
 /*
@@ -349,6 +353,7 @@ void ntp_clear(void)
 	tick_length	= tick_length_base;
 	time_offset	= 0;
 
+	ntp_next_leap_sec = TIME64_MAX;
 	/* Clear PPS state variables */
 	pps_clear();
 }
@@ -359,6 +364,21 @@ u64 ntp_tick_length(void)
 	return tick_length;
 }
 
+/**
+ * ntp_get_next_leap - Returns the next leapsecond in CLOCK_REALTIME ktime_t
+ *
+ * Provides the time of the next leapsecond against CLOCK_REALTIME in
+ * a ktime_t format. Returns KTIME_MAX if no leapsecond is pending.
+ */
+ktime_t ntp_get_next_leap(void)
+{
+	ktime_t ret;
+
+	if ((time_state == TIME_INS) && (time_status & STA_INS))
+		return ktime_set(ntp_next_leap_sec, 0);
+	ret.tv64 = KTIME_MAX;
+	return ret;
+}
 
 /*
  * this routine handles the overflow of the microsecond field
@@ -382,15 +402,21 @@ int second_overflow(unsigned long secs)
 	 */
 	switch (time_state) {
 	case TIME_OK:
-		if (time_status & STA_INS)
+		if (time_status & STA_INS) {
 			time_state = TIME_INS;
-		else if (time_status & STA_DEL)
+			ntp_next_leap_sec = secs + SECS_PER_DAY -
+						(secs % SECS_PER_DAY);
+		} else if (time_status & STA_DEL) {
 			time_state = TIME_DEL;
+			ntp_next_leap_sec = secs + SECS_PER_DAY -
+						 ((secs+1) % SECS_PER_DAY);
+		}
 		break;
 	case TIME_INS:
-		if (!(time_status & STA_INS))
+		if (!(time_status & STA_INS)) {
+			ntp_next_leap_sec = TIME64_MAX;
 			time_state = TIME_OK;
-		else if (secs % 86400 == 0) {
+		} else if (secs % SECS_PER_DAY == 0) {
 			leap = -1;
 			time_state = TIME_OOP;
 			printk(KERN_NOTICE
@@ -398,19 +424,21 @@ int second_overflow(unsigned long secs)
 		}
 		break;
 	case TIME_DEL:
-		if (!(time_status & STA_DEL))
+		if (!(time_status & STA_DEL)) {
+			ntp_next_leap_sec = TIME64_MAX;
 			time_state = TIME_OK;
-		else if ((secs + 1) % 86400 == 0) {
+		} else if ((secs + 1) % SECS_PER_DAY == 0) {
 			leap = 1;
+			ntp_next_leap_sec = TIME64_MAX;
 			time_state = TIME_WAIT;
 			printk(KERN_NOTICE
 				"Clock: deleting leap second 23:59:59 UTC\n");
 		}
 		break;
 	case TIME_OOP:
+		ntp_next_leap_sec = TIME64_MAX;
 		time_state = TIME_WAIT;
 		break;
-
 	case TIME_WAIT:
 		if (!(time_status & (STA_INS | STA_DEL)))
 			time_state = TIME_OK;
@@ -547,6 +575,7 @@ static inline void process_adj_status(struct timex *txc, struct timespec64 *ts)
 	if ((time_status & STA_PLL) && !(txc->status & STA_PLL)) {
 		time_state = TIME_OK;
 		time_status = STA_UNSYNC;
+		ntp_next_leap_sec = TIME64_MAX;
 		/* restart PPS frequency calibration */
 		pps_reset_freq_interval();
 	}
@@ -711,6 +740,24 @@ int __do_adjtimex(struct timex *txc, struct timespec64 *ts, s32 *time_tai)
 	if (!(time_status & STA_NANO))
 		txc->time.tv_usec /= NSEC_PER_USEC;
 
+	/* Handle leapsec adjustments */
+	if (unlikely(ts->tv_sec >= ntp_next_leap_sec)) {
+		if ((time_state == TIME_INS) && (time_status & STA_INS)) {
+			result = TIME_OOP;
+			txc->tai++;
+			txc->time.tv_sec--;
+		}
+		if ((time_state == TIME_DEL) && (time_status & STA_DEL)) {
+			result = TIME_WAIT;
+			txc->tai--;
+			txc->time.tv_sec++;
+		}
+		if ((time_state == TIME_OOP) &&
+					(ts->tv_sec == ntp_next_leap_sec)) {
+			result = TIME_WAIT;
+		}
+	}
+
 	return result;
 }
 
diff --git a/kernel/time/ntp_internal.h b/kernel/time/ntp_internal.h
index bbd102ad9df7..65430504ca26 100644
--- a/kernel/time/ntp_internal.h
+++ b/kernel/time/ntp_internal.h
@@ -5,6 +5,7 @@ extern void ntp_init(void);
 extern void ntp_clear(void);
 /* Returns how long ticks are at present, in ns / 2^NTP_SCALE_SHIFT. */
 extern u64 ntp_tick_length(void);
+extern ktime_t ntp_get_next_leap(void);
 extern int second_overflow(unsigned long secs);
 extern int ntp_validate_timex(struct timex *);
 extern int __do_adjtimex(struct timex *, struct timespec64 *, s32 *);
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 0075da74abf0..892e3dae0aac 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -196,39 +196,62 @@ static int cpu_clock_sample(const clockid_t which_clock, struct task_struct *p,
 	return 0;
 }
 
-static void update_gt_cputime(struct task_cputime *a, struct task_cputime *b)
+/*
+ * Set cputime to sum_cputime if sum_cputime > cputime. Use cmpxchg
+ * to avoid race conditions with concurrent updates to cputime.
+ */
+static inline void __update_gt_cputime(atomic64_t *cputime, u64 sum_cputime)
 {
-	if (b->utime > a->utime)
-		a->utime = b->utime;
+	u64 curr_cputime;
+retry:
+	curr_cputime = atomic64_read(cputime);
+	if (sum_cputime > curr_cputime) {
+		if (atomic64_cmpxchg(cputime, curr_cputime, sum_cputime) != curr_cputime)
+			goto retry;
+	}
+}
 
-	if (b->stime > a->stime)
-		a->stime = b->stime;
+static void update_gt_cputime(struct task_cputime_atomic *cputime_atomic, struct task_cputime *sum)
+{
+	__update_gt_cputime(&cputime_atomic->utime, sum->utime);
+	__update_gt_cputime(&cputime_atomic->stime, sum->stime);
+	__update_gt_cputime(&cputime_atomic->sum_exec_runtime, sum->sum_exec_runtime);
+}
 
-	if (b->sum_exec_runtime > a->sum_exec_runtime)
-		a->sum_exec_runtime = b->sum_exec_runtime;
+/* Sample task_cputime_atomic values in "atomic_timers", store results in "times". */
+static inline void sample_cputime_atomic(struct task_cputime *times,
+					 struct task_cputime_atomic *atomic_times)
+{
+	times->utime = atomic64_read(&atomic_times->utime);
+	times->stime = atomic64_read(&atomic_times->stime);
+	times->sum_exec_runtime = atomic64_read(&atomic_times->sum_exec_runtime);
 }
 
 void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times)
 {
 	struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
 	struct task_cputime sum;
-	unsigned long flags;
 
-	if (!cputimer->running) {
+	/* Check if cputimer isn't running. This is accessed without locking. */
+	if (!READ_ONCE(cputimer->running)) {
 		/*
 		 * The POSIX timer interface allows for absolute time expiry
 		 * values through the TIMER_ABSTIME flag, therefore we have
-		 * to synchronize the timer to the clock every time we start
-		 * it.
+		 * to synchronize the timer to the clock every time we start it.
 		 */
 		thread_group_cputime(tsk, &sum);
-		raw_spin_lock_irqsave(&cputimer->lock, flags);
-		cputimer->running = 1;
-		update_gt_cputime(&cputimer->cputime, &sum);
-	} else
-		raw_spin_lock_irqsave(&cputimer->lock, flags);
-	*times = cputimer->cputime;
-	raw_spin_unlock_irqrestore(&cputimer->lock, flags);
+		update_gt_cputime(&cputimer->cputime_atomic, &sum);
+
+		/*
+		 * We're setting cputimer->running without a lock. Ensure
+		 * this only gets written to in one operation. We set
+		 * running after update_gt_cputime() as a small optimization,
+		 * but barriers are not required because update_gt_cputime()
+		 * can handle concurrent updates.
+		 */
+		WRITE_ONCE(cputimer->running, 1);
+	}
+	sample_cputime_atomic(times, &cputimer->cputime_atomic);
 }
 
 /*
@@ -582,7 +605,8 @@ bool posix_cpu_timers_can_stop_tick(struct task_struct *tsk)
 	if (!task_cputime_zero(&tsk->cputime_expires))
 		return false;
 
-	if (tsk->signal->cputimer.running)
+	/* Check if cputimer is running. This is accessed without locking. */
+	if (READ_ONCE(tsk->signal->cputimer.running))
 		return false;
 
 	return true;
@@ -852,10 +876,10 @@ static void check_thread_timers(struct task_struct *tsk,
 	/*
 	 * Check for the special case thread timers.
 	 */
-	soft = ACCESS_ONCE(sig->rlim[RLIMIT_RTTIME].rlim_cur);
+	soft = READ_ONCE(sig->rlim[RLIMIT_RTTIME].rlim_cur);
 	if (soft != RLIM_INFINITY) {
 		unsigned long hard =
-			ACCESS_ONCE(sig->rlim[RLIMIT_RTTIME].rlim_max);
+			READ_ONCE(sig->rlim[RLIMIT_RTTIME].rlim_max);
 
 		if (hard != RLIM_INFINITY &&
 		    tsk->rt.timeout > DIV_ROUND_UP(hard, USEC_PER_SEC/HZ)) {
@@ -882,14 +906,12 @@ static void check_thread_timers(struct task_struct *tsk,
 	}
 }
 
-static void stop_process_timers(struct signal_struct *sig)
+static inline void stop_process_timers(struct signal_struct *sig)
 {
 	struct thread_group_cputimer *cputimer = &sig->cputimer;
-	unsigned long flags;
 
-	raw_spin_lock_irqsave(&cputimer->lock, flags);
-	cputimer->running = 0;
-	raw_spin_unlock_irqrestore(&cputimer->lock, flags);
+	/* Turn off cputimer->running. This is done without locking. */
+	WRITE_ONCE(cputimer->running, 0);
 }
 
 static u32 onecputick;
@@ -958,11 +980,11 @@ static void check_process_timers(struct task_struct *tsk,
 			 SIGPROF);
 	check_cpu_itimer(tsk, &sig->it[CPUCLOCK_VIRT], &virt_expires, utime,
 			 SIGVTALRM);
-	soft = ACCESS_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur);
+	soft = READ_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur);
 	if (soft != RLIM_INFINITY) {
 		unsigned long psecs = cputime_to_secs(ptime);
 		unsigned long hard =
-			ACCESS_ONCE(sig->rlim[RLIMIT_CPU].rlim_max);
+			READ_ONCE(sig->rlim[RLIMIT_CPU].rlim_max);
 		cputime_t x;
 		if (psecs >= hard) {
 			/*
@@ -1111,12 +1133,11 @@ static inline int fastpath_timer_check(struct task_struct *tsk)
 	}
 
 	sig = tsk->signal;
-	if (sig->cputimer.running) {
+	/* Check if cputimer is running. This is accessed without locking. */
+	if (READ_ONCE(sig->cputimer.running)) {
 		struct task_cputime group_sample;
 
-		raw_spin_lock(&sig->cputimer.lock);
-		group_sample = sig->cputimer.cputime;
-		raw_spin_unlock(&sig->cputimer.lock);
+		sample_cputime_atomic(&group_sample, &sig->cputimer.cputime_atomic);
 
 		if (task_cputime_expired(&group_sample, &sig->cputime_expires))
 			return 1;
@@ -1157,7 +1178,7 @@ void run_posix_cpu_timers(struct task_struct *tsk)
 	 * If there are any active process wide timers (POSIX 1.b, itimers,
 	 * RLIMIT_CPU) cputimer must be running.
 	 */
-	if (tsk->signal->cputimer.running)
+	if (READ_ONCE(tsk->signal->cputimer.running))
 		check_process_timers(tsk, &firing);
 
 	/*
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index 31ea01f42e1f..31d11ac9fa47 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -272,13 +272,20 @@ static int posix_get_tai(clockid_t which_clock, struct timespec *tp)
 	return 0;
 }
 
+static int posix_get_hrtimer_res(clockid_t which_clock, struct timespec *tp)
+{
+	tp->tv_sec = 0;
+	tp->tv_nsec = hrtimer_resolution;
+	return 0;
+}
+
 /*
  * Initialize everything, well, just everything in Posix clocks/timers ;)
  */
 static __init int init_posix_timers(void)
 {
 	struct k_clock clock_realtime = {
-		.clock_getres	= hrtimer_get_res,
+		.clock_getres	= posix_get_hrtimer_res,
 		.clock_get	= posix_clock_realtime_get,
 		.clock_set	= posix_clock_realtime_set,
 		.clock_adj	= posix_clock_realtime_adj,
@@ -290,7 +297,7 @@ static __init int init_posix_timers(void)
 		.timer_del	= common_timer_del,
 	};
 	struct k_clock clock_monotonic = {
-		.clock_getres	= hrtimer_get_res,
+		.clock_getres	= posix_get_hrtimer_res,
 		.clock_get	= posix_ktime_get_ts,
 		.nsleep		= common_nsleep,
 		.nsleep_restart	= hrtimer_nanosleep_restart,
@@ -300,7 +307,7 @@ static __init int init_posix_timers(void)
 		.timer_del	= common_timer_del,
 	};
 	struct k_clock clock_monotonic_raw = {
-		.clock_getres	= hrtimer_get_res,
+		.clock_getres	= posix_get_hrtimer_res,
 		.clock_get	= posix_get_monotonic_raw,
 	};
 	struct k_clock clock_realtime_coarse = {
@@ -312,7 +319,7 @@ static __init int init_posix_timers(void)
 		.clock_get	= posix_get_monotonic_coarse,
 	};
 	struct k_clock clock_tai = {
-		.clock_getres	= hrtimer_get_res,
+		.clock_getres	= posix_get_hrtimer_res,
 		.clock_get	= posix_get_tai,
 		.nsleep		= common_nsleep,
 		.nsleep_restart	= hrtimer_nanosleep_restart,
@@ -322,7 +329,7 @@ static __init int init_posix_timers(void)
 		.timer_del	= common_timer_del,
 	};
 	struct k_clock clock_boottime = {
-		.clock_getres	= hrtimer_get_res,
+		.clock_getres	= posix_get_hrtimer_res,
 		.clock_get	= posix_get_boottime,
 		.nsleep		= common_nsleep,
 		.nsleep_restart	= hrtimer_nanosleep_restart,
diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c
index 6aac4beedbbe..3e7db49a2381 100644
--- a/kernel/time/tick-broadcast-hrtimer.c
+++ b/kernel/time/tick-broadcast-hrtimer.c
@@ -22,6 +22,7 @@ static void bc_set_mode(enum clock_event_mode mode,
 			struct clock_event_device *bc)
 {
 	switch (mode) {
+	case CLOCK_EVT_MODE_UNUSED:
 	case CLOCK_EVT_MODE_SHUTDOWN:
 		/*
 		 * Note, we cannot cancel the timer here as we might
@@ -66,9 +67,11 @@ static int bc_set_next(ktime_t expires, struct clock_event_device *bc)
 	 * hrtimer_{start/cancel} functions call into tracing,
 	 * calls to these functions must be bound within RCU_NONIDLE.
 	 */
-	RCU_NONIDLE(bc_moved = (hrtimer_try_to_cancel(&bctimer) >= 0) ?
-		!hrtimer_start(&bctimer, expires, HRTIMER_MODE_ABS_PINNED) :
-			0);
+	RCU_NONIDLE({
+			bc_moved = hrtimer_try_to_cancel(&bctimer) >= 0;
+			if (bc_moved)
+				hrtimer_start(&bctimer, expires,
+					      HRTIMER_MODE_ABS_PINNED);});
 	if (bc_moved) {
 		/* Bind the "device" to the cpu */
 		bc->bound_on = smp_processor_id();
@@ -99,10 +102,13 @@ static enum hrtimer_restart bc_handler(struct hrtimer *t)
 {
 	ce_broadcast_hrtimer.event_handler(&ce_broadcast_hrtimer);
 
-	if (ce_broadcast_hrtimer.next_event.tv64 == KTIME_MAX)
+	switch (ce_broadcast_hrtimer.mode) {
+	case CLOCK_EVT_MODE_ONESHOT:
+		if (ce_broadcast_hrtimer.next_event.tv64 != KTIME_MAX)
+			return HRTIMER_RESTART;
+	default:
 		return HRTIMER_NORESTART;
-
-	return HRTIMER_RESTART;
+	}
 }
 
 void tick_setup_hrtimer_broadcast(void)
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 7e8ca4f448a8..d39f32cdd1b5 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -255,18 +255,18 @@ int tick_receive_broadcast(void)
 /*
  * Broadcast the event to the cpus, which are set in the mask (mangled).
  */
-static void tick_do_broadcast(struct cpumask *mask)
+static bool tick_do_broadcast(struct cpumask *mask)
 {
 	int cpu = smp_processor_id();
 	struct tick_device *td;
+	bool local = false;
 
 	/*
 	 * Check, if the current cpu is in the mask
 	 */
 	if (cpumask_test_cpu(cpu, mask)) {
 		cpumask_clear_cpu(cpu, mask);
-		td = &per_cpu(tick_cpu_device, cpu);
-		td->evtdev->event_handler(td->evtdev);
+		local = true;
 	}
 
 	if (!cpumask_empty(mask)) {
@@ -279,16 +279,17 @@ static void tick_do_broadcast(struct cpumask *mask)
 		td = &per_cpu(tick_cpu_device, cpumask_first(mask));
 		td->evtdev->broadcast(mask);
 	}
+	return local;
 }
 
 /*
  * Periodic broadcast:
  * - invoke the broadcast handlers
  */
-static void tick_do_periodic_broadcast(void)
+static bool tick_do_periodic_broadcast(void)
 {
 	cpumask_and(tmpmask, cpu_online_mask, tick_broadcast_mask);
-	tick_do_broadcast(tmpmask);
+	return tick_do_broadcast(tmpmask);
 }
 
 /*
@@ -296,34 +297,26 @@ static void tick_do_periodic_broadcast(void)
  */
 static void tick_handle_periodic_broadcast(struct clock_event_device *dev)
 {
-	ktime_t next;
+	struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
+	bool bc_local;
 
 	raw_spin_lock(&tick_broadcast_lock);
+	bc_local = tick_do_periodic_broadcast();
 
-	tick_do_periodic_broadcast();
+	if (clockevent_state_oneshot(dev)) {
+		ktime_t next = ktime_add(dev->next_event, tick_period);
 
-	/*
-	 * The device is in periodic mode. No reprogramming necessary:
-	 */
-	if (dev->state == CLOCK_EVT_STATE_PERIODIC)
-		goto unlock;
+		clockevents_program_event(dev, next, true);
+	}
+	raw_spin_unlock(&tick_broadcast_lock);
 
 	/*
-	 * Setup the next period for devices, which do not have
-	 * periodic mode. We read dev->next_event first and add to it
-	 * when the event already expired. clockevents_program_event()
-	 * sets dev->next_event only when the event is really
-	 * programmed to the device.
+	 * We run the handler of the local cpu after dropping
+	 * tick_broadcast_lock because the handler might deadlock when
+	 * trying to switch to oneshot mode.
 	 */
-	for (next = dev->next_event; ;) {
-		next = ktime_add(next, tick_period);
-
-		if (!clockevents_program_event(dev, next, false))
-			goto unlock;
-		tick_do_periodic_broadcast();
-	}
-unlock:
-	raw_spin_unlock(&tick_broadcast_lock);
+	if (bc_local)
+		td->evtdev->event_handler(td->evtdev);
 }
 
 /**
@@ -532,23 +525,19 @@ static void tick_broadcast_set_affinity(struct clock_event_device *bc,
 	irq_set_affinity(bc->irq, bc->cpumask);
 }
 
-static int tick_broadcast_set_event(struct clock_event_device *bc, int cpu,
-				    ktime_t expires, int force)
+static void tick_broadcast_set_event(struct clock_event_device *bc, int cpu,
+				     ktime_t expires)
 {
-	int ret;
-
-	if (bc->state != CLOCK_EVT_STATE_ONESHOT)
-		clockevents_set_state(bc, CLOCK_EVT_STATE_ONESHOT);
+	if (!clockevent_state_oneshot(bc))
+		clockevents_switch_state(bc, CLOCK_EVT_STATE_ONESHOT);
 
-	ret = clockevents_program_event(bc, expires, force);
-	if (!ret)
-		tick_broadcast_set_affinity(bc, cpumask_of(cpu));
-	return ret;
+	clockevents_program_event(bc, expires, 1);
+	tick_broadcast_set_affinity(bc, cpumask_of(cpu));
 }
 
 static void tick_resume_broadcast_oneshot(struct clock_event_device *bc)
 {
-	clockevents_set_state(bc, CLOCK_EVT_STATE_ONESHOT);
+	clockevents_switch_state(bc, CLOCK_EVT_STATE_ONESHOT);
 }
 
 /*
@@ -566,7 +555,7 @@ void tick_check_oneshot_broadcast_this_cpu(void)
 		 * switched over, leave the device alone.
 		 */
 		if (td->mode == TICKDEV_MODE_ONESHOT) {
-			clockevents_set_state(td->evtdev,
+			clockevents_switch_state(td->evtdev,
 					      CLOCK_EVT_STATE_ONESHOT);
 		}
 	}
@@ -580,9 +569,9 @@ static void tick_handle_oneshot_broadcast(struct clock_event_device *dev)
 	struct tick_device *td;
 	ktime_t now, next_event;
 	int cpu, next_cpu = 0;
+	bool bc_local;
 
 	raw_spin_lock(&tick_broadcast_lock);
-again:
 	dev->next_event.tv64 = KTIME_MAX;
 	next_event.tv64 = KTIME_MAX;
 	cpumask_clear(tmpmask);
@@ -624,7 +613,7 @@ again:
 	/*
 	 * Wakeup the cpus which have an expired event.
 	 */
-	tick_do_broadcast(tmpmask);
+	bc_local = tick_do_broadcast(tmpmask);
 
 	/*
 	 * Two reasons for reprogram:
@@ -636,15 +625,15 @@ again:
 	 * - There are pending events on sleeping CPUs which were not
 	 * in the event mask
 	 */
-	if (next_event.tv64 != KTIME_MAX) {
-		/*
-		 * Rearm the broadcast device. If event expired,
-		 * repeat the above
-		 */
-		if (tick_broadcast_set_event(dev, next_cpu, next_event, 0))
-			goto again;
-	}
+	if (next_event.tv64 != KTIME_MAX)
+		tick_broadcast_set_event(dev, next_cpu, next_event);
+
 	raw_spin_unlock(&tick_broadcast_lock);
+
+	if (bc_local) {
+		td = this_cpu_ptr(&tick_cpu_device);
+		td->evtdev->event_handler(td->evtdev);
+	}
 }
 
 static int broadcast_needs_cpu(struct clock_event_device *bc, int cpu)
@@ -670,7 +659,7 @@ static void broadcast_shutdown_local(struct clock_event_device *bc,
 		if (dev->next_event.tv64 < bc->next_event.tv64)
 			return;
 	}
-	clockevents_set_state(dev, CLOCK_EVT_STATE_SHUTDOWN);
+	clockevents_switch_state(dev, CLOCK_EVT_STATE_SHUTDOWN);
 }
 
 /**
@@ -726,7 +715,7 @@ int tick_broadcast_oneshot_control(enum tick_broadcast_state state)
 			 */
 			if (!cpumask_test_cpu(cpu, tick_broadcast_force_mask) &&
 			    dev->next_event.tv64 < bc->next_event.tv64)
-				tick_broadcast_set_event(bc, cpu, dev->next_event, 1);
+				tick_broadcast_set_event(bc, cpu, dev->next_event);
 		}
 		/*
 		 * If the current CPU owns the hrtimer broadcast
@@ -740,7 +729,7 @@ int tick_broadcast_oneshot_control(enum tick_broadcast_state state)
 			cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask);
 	} else {
 		if (cpumask_test_and_clear_cpu(cpu, tick_broadcast_oneshot_mask)) {
-			clockevents_set_state(dev, CLOCK_EVT_STATE_ONESHOT);
+			clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT);
 			/*
 			 * The cpu which was handling the broadcast
 			 * timer marked this cpu in the broadcast
@@ -842,7 +831,7 @@ void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
 
 	/* Set it up only once ! */
 	if (bc->event_handler != tick_handle_oneshot_broadcast) {
-		int was_periodic = bc->state == CLOCK_EVT_STATE_PERIODIC;
+		int was_periodic = clockevent_state_periodic(bc);
 
 		bc->event_handler = tick_handle_oneshot_broadcast;
 
@@ -858,10 +847,10 @@ void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
 			   tick_broadcast_oneshot_mask, tmpmask);
 
 		if (was_periodic && !cpumask_empty(tmpmask)) {
-			clockevents_set_state(bc, CLOCK_EVT_STATE_ONESHOT);
+			clockevents_switch_state(bc, CLOCK_EVT_STATE_ONESHOT);
 			tick_broadcast_init_next_event(tmpmask,
 						       tick_next_period);
-			tick_broadcast_set_event(bc, cpu, tick_next_period, 1);
+			tick_broadcast_set_event(bc, cpu, tick_next_period);
 		} else
 			bc->next_event.tv64 = KTIME_MAX;
 	} else {
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 51508465153c..76446cb5dfe1 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -103,7 +103,17 @@ void tick_handle_periodic(struct clock_event_device *dev)
 
 	tick_periodic(cpu);
 
-	if (dev->state != CLOCK_EVT_STATE_ONESHOT)
+#if defined(CONFIG_HIGH_RES_TIMERS) || defined(CONFIG_NO_HZ_COMMON)
+	/*
+	 * The cpu might have transitioned to HIGHRES or NOHZ mode via
+	 * update_process_times() -> run_local_timers() ->
+	 * hrtimer_run_queues().
+	 */
+	if (dev->event_handler != tick_handle_periodic)
+		return;
+#endif
+
+	if (!clockevent_state_oneshot(dev))
 		return;
 	for (;;) {
 		/*
@@ -141,7 +151,7 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast)
 
 	if ((dev->features & CLOCK_EVT_FEAT_PERIODIC) &&
 	    !tick_broadcast_oneshot_active()) {
-		clockevents_set_state(dev, CLOCK_EVT_STATE_PERIODIC);
+		clockevents_switch_state(dev, CLOCK_EVT_STATE_PERIODIC);
 	} else {
 		unsigned long seq;
 		ktime_t next;
@@ -151,7 +161,7 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast)
 			next = tick_next_period;
 		} while (read_seqretry(&jiffies_lock, seq));
 
-		clockevents_set_state(dev, CLOCK_EVT_STATE_ONESHOT);
+		clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT);
 
 		for (;;) {
 			if (!clockevents_program_event(dev, next, false))
@@ -368,7 +378,7 @@ void tick_shutdown(unsigned int cpu)
 		 * Prevent that the clock events layer tries to call
 		 * the set mode function!
 		 */
-		dev->state = CLOCK_EVT_STATE_DETACHED;
+		clockevent_set_state(dev, CLOCK_EVT_STATE_DETACHED);
 		dev->mode = CLOCK_EVT_MODE_UNUSED;
 		clockevents_exchange_device(dev, NULL);
 		dev->event_handler = clockevents_handle_noop;
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index b64fdd8054c5..966a5a6fdd0a 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -36,11 +36,22 @@ static inline int tick_device_is_functional(struct clock_event_device *dev)
 	return !(dev->features & CLOCK_EVT_FEAT_DUMMY);
 }
 
+static inline enum clock_event_state clockevent_get_state(struct clock_event_device *dev)
+{
+	return dev->state_use_accessors;
+}
+
+static inline void clockevent_set_state(struct clock_event_device *dev,
+					enum clock_event_state state)
+{
+	dev->state_use_accessors = state;
+}
+
 extern void clockevents_shutdown(struct clock_event_device *dev);
 extern void clockevents_exchange_device(struct clock_event_device *old,
 					struct clock_event_device *new);
-extern void clockevents_set_state(struct clock_event_device *dev,
-				 enum clock_event_state state);
+extern void clockevents_switch_state(struct clock_event_device *dev,
+				     enum clock_event_state state);
 extern int clockevents_program_event(struct clock_event_device *dev,
 				     ktime_t expires, bool force);
 extern void clockevents_handle_noop(struct clock_event_device *dev);
@@ -137,3 +148,19 @@ extern void tick_nohz_init(void);
 # else
 static inline void tick_nohz_init(void) { }
 #endif
+
+#ifdef CONFIG_NO_HZ_COMMON
+extern unsigned long tick_nohz_active;
+#else
+#define tick_nohz_active (0)
+#endif
+
+#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
+extern void timers_update_migration(bool update_nohz);
+#else
+static inline void timers_update_migration(bool update_nohz) { }
+#endif
+
+DECLARE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases);
+
+extern u64 get_next_timer_interrupt(unsigned long basej, u64 basem);
diff --git a/kernel/time/tick-oneshot.c b/kernel/time/tick-oneshot.c
index 67a64b1670bf..b51344652330 100644
--- a/kernel/time/tick-oneshot.c
+++ b/kernel/time/tick-oneshot.c
@@ -28,6 +28,22 @@ int tick_program_event(ktime_t expires, int force)
 {
 	struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev);
 
+	if (unlikely(expires.tv64 == KTIME_MAX)) {
+		/*
+		 * We don't need the clock event device any more, stop it.
+		 */
+		clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT_STOPPED);
+		return 0;
+	}
+
+	if (unlikely(clockevent_state_oneshot_stopped(dev))) {
+		/*
+		 * We need the clock event again, configure it in ONESHOT mode
+		 * before using it.
+		 */
+		clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT);
+	}
+
 	return clockevents_program_event(dev, expires, force);
 }
 
@@ -38,7 +54,7 @@ void tick_resume_oneshot(void)
 {
 	struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev);
 
-	clockevents_set_state(dev, CLOCK_EVT_STATE_ONESHOT);
+	clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT);
 	clockevents_program_event(dev, ktime_get(), true);
 }
 
@@ -50,7 +66,7 @@ void tick_setup_oneshot(struct clock_event_device *newdev,
 			ktime_t next_event)
 {
 	newdev->event_handler = handler;
-	clockevents_set_state(newdev, CLOCK_EVT_STATE_ONESHOT);
+	clockevents_switch_state(newdev, CLOCK_EVT_STATE_ONESHOT);
 	clockevents_program_event(newdev, next_event, true);
 }
 
@@ -81,7 +97,7 @@ int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *))
 
 	td->mode = TICKDEV_MODE_ONESHOT;
 	dev->event_handler = handler;
-	clockevents_set_state(dev, CLOCK_EVT_STATE_ONESHOT);
+	clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT);
 	tick_broadcast_switch_to_oneshot();
 	return 0;
 }
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 914259128145..c792429e98c6 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -399,7 +399,7 @@ void __init tick_nohz_init(void)
  * NO HZ enabled ?
  */
 static int tick_nohz_enabled __read_mostly  = 1;
-int tick_nohz_active  __read_mostly;
+unsigned long tick_nohz_active  __read_mostly;
 /*
  * Enable / Disable tickless mode
  */
@@ -565,156 +565,144 @@ u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time)
 }
 EXPORT_SYMBOL_GPL(get_cpu_iowait_time_us);
 
+static void tick_nohz_restart(struct tick_sched *ts, ktime_t now)
+{
+	hrtimer_cancel(&ts->sched_timer);
+	hrtimer_set_expires(&ts->sched_timer, ts->last_tick);
+
+	/* Forward the time to expire in the future */
+	hrtimer_forward(&ts->sched_timer, now, tick_period);
+
+	if (ts->nohz_mode == NOHZ_MODE_HIGHRES)
+		hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS_PINNED);
+	else
+		tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1);
+}
+
 static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
 					 ktime_t now, int cpu)
 {
-	unsigned long seq, last_jiffies, next_jiffies, delta_jiffies;
-	ktime_t last_update, expires, ret = { .tv64 = 0 };
-	unsigned long rcu_delta_jiffies;
 	struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev);
-	u64 time_delta;
-
-	time_delta = timekeeping_max_deferment();
+	u64 basemono, next_tick, next_tmr, next_rcu, delta, expires;
+	unsigned long seq, basejiff;
+	ktime_t	tick;
 
 	/* Read jiffies and the time when jiffies were updated last */
 	do {
 		seq = read_seqbegin(&jiffies_lock);
-		last_update = last_jiffies_update;
-		last_jiffies = jiffies;
+		basemono = last_jiffies_update.tv64;
+		basejiff = jiffies;
 	} while (read_seqretry(&jiffies_lock, seq));
+	ts->last_jiffies = basejiff;
 
-	if (rcu_needs_cpu(&rcu_delta_jiffies) ||
+	if (rcu_needs_cpu(basemono, &next_rcu) ||
 	    arch_needs_cpu() || irq_work_needs_cpu()) {
-		next_jiffies = last_jiffies + 1;
-		delta_jiffies = 1;
+		next_tick = basemono + TICK_NSEC;
 	} else {
-		/* Get the next timer wheel timer */
-		next_jiffies = get_next_timer_interrupt(last_jiffies);
-		delta_jiffies = next_jiffies - last_jiffies;
-		if (rcu_delta_jiffies < delta_jiffies) {
-			next_jiffies = last_jiffies + rcu_delta_jiffies;
-			delta_jiffies = rcu_delta_jiffies;
-		}
+		/*
+		 * Get the next pending timer. If high resolution
+		 * timers are enabled this only takes the timer wheel
+		 * timers into account. If high resolution timers are
+		 * disabled this also looks at the next expiring
+		 * hrtimer.
+		 */
+		next_tmr = get_next_timer_interrupt(basejiff, basemono);
+		ts->next_timer = next_tmr;
+		/* Take the next rcu event into account */
+		next_tick = next_rcu < next_tmr ? next_rcu : next_tmr;
 	}
 
 	/*
-	 * Do not stop the tick, if we are only one off (or less)
-	 * or if the cpu is required for RCU:
+	 * If the tick is due in the next period, keep it ticking or
+	 * restart it proper.
 	 */
-	if (!ts->tick_stopped && delta_jiffies <= 1)
-		goto out;
-
-	/* Schedule the tick, if we are at least one jiffie off */
-	if ((long)delta_jiffies >= 1) {
-
-		/*
-		 * If this cpu is the one which updates jiffies, then
-		 * give up the assignment and let it be taken by the
-		 * cpu which runs the tick timer next, which might be
-		 * this cpu as well. If we don't drop this here the
-		 * jiffies might be stale and do_timer() never
-		 * invoked. Keep track of the fact that it was the one
-		 * which had the do_timer() duty last. If this cpu is
-		 * the one which had the do_timer() duty last, we
-		 * limit the sleep time to the timekeeping
-		 * max_deferement value which we retrieved
-		 * above. Otherwise we can sleep as long as we want.
-		 */
-		if (cpu == tick_do_timer_cpu) {
-			tick_do_timer_cpu = TICK_DO_TIMER_NONE;
-			ts->do_timer_last = 1;
-		} else if (tick_do_timer_cpu != TICK_DO_TIMER_NONE) {
-			time_delta = KTIME_MAX;
-			ts->do_timer_last = 0;
-		} else if (!ts->do_timer_last) {
-			time_delta = KTIME_MAX;
+	delta = next_tick - basemono;
+	if (delta <= (u64)TICK_NSEC) {
+		tick.tv64 = 0;
+		if (!ts->tick_stopped)
+			goto out;
+		if (delta == 0) {
+			/* Tick is stopped, but required now. Enforce it */
+			tick_nohz_restart(ts, now);
+			goto out;
 		}
+	}
+
+	/*
+	 * If this cpu is the one which updates jiffies, then give up
+	 * the assignment and let it be taken by the cpu which runs
+	 * the tick timer next, which might be this cpu as well. If we
+	 * don't drop this here the jiffies might be stale and
+	 * do_timer() never invoked. Keep track of the fact that it
+	 * was the one which had the do_timer() duty last. If this cpu
+	 * is the one which had the do_timer() duty last, we limit the
+	 * sleep time to the timekeeping max_deferement value.
+	 * Otherwise we can sleep as long as we want.
+	 */
+	delta = timekeeping_max_deferment();
+	if (cpu == tick_do_timer_cpu) {
+		tick_do_timer_cpu = TICK_DO_TIMER_NONE;
+		ts->do_timer_last = 1;
+	} else if (tick_do_timer_cpu != TICK_DO_TIMER_NONE) {
+		delta = KTIME_MAX;
+		ts->do_timer_last = 0;
+	} else if (!ts->do_timer_last) {
+		delta = KTIME_MAX;
+	}
 
 #ifdef CONFIG_NO_HZ_FULL
-		if (!ts->inidle) {
-			time_delta = min(time_delta,
-					 scheduler_tick_max_deferment());
-		}
+	/* Limit the tick delta to the maximum scheduler deferment */
+	if (!ts->inidle)
+		delta = min(delta, scheduler_tick_max_deferment());
 #endif
 
-		/*
-		 * calculate the expiry time for the next timer wheel
-		 * timer. delta_jiffies >= NEXT_TIMER_MAX_DELTA signals
-		 * that there is no timer pending or at least extremely
-		 * far into the future (12 days for HZ=1000). In this
-		 * case we set the expiry to the end of time.
-		 */
-		if (likely(delta_jiffies < NEXT_TIMER_MAX_DELTA)) {
-			/*
-			 * Calculate the time delta for the next timer event.
-			 * If the time delta exceeds the maximum time delta
-			 * permitted by the current clocksource then adjust
-			 * the time delta accordingly to ensure the
-			 * clocksource does not wrap.
-			 */
-			time_delta = min_t(u64, time_delta,
-					   tick_period.tv64 * delta_jiffies);
-		}
-
-		if (time_delta < KTIME_MAX)
-			expires = ktime_add_ns(last_update, time_delta);
-		else
-			expires.tv64 = KTIME_MAX;
-
-		/* Skip reprogram of event if its not changed */
-		if (ts->tick_stopped && ktime_equal(expires, dev->next_event))
-			goto out;
+	/* Calculate the next expiry time */
+	if (delta < (KTIME_MAX - basemono))
+		expires = basemono + delta;
+	else
+		expires = KTIME_MAX;
 
-		ret = expires;
+	expires = min_t(u64, expires, next_tick);
+	tick.tv64 = expires;
 
-		/*
-		 * nohz_stop_sched_tick can be called several times before
-		 * the nohz_restart_sched_tick is called. This happens when
-		 * interrupts arrive which do not cause a reschedule. In the
-		 * first call we save the current tick time, so we can restart
-		 * the scheduler tick in nohz_restart_sched_tick.
-		 */
-		if (!ts->tick_stopped) {
-			nohz_balance_enter_idle(cpu);
-			calc_load_enter_idle();
+	/* Skip reprogram of event if its not changed */
+	if (ts->tick_stopped && (expires == dev->next_event.tv64))
+		goto out;
 
-			ts->last_tick = hrtimer_get_expires(&ts->sched_timer);
-			ts->tick_stopped = 1;
-			trace_tick_stop(1, " ");
-		}
+	/*
+	 * nohz_stop_sched_tick can be called several times before
+	 * the nohz_restart_sched_tick is called. This happens when
+	 * interrupts arrive which do not cause a reschedule. In the
+	 * first call we save the current tick time, so we can restart
+	 * the scheduler tick in nohz_restart_sched_tick.
+	 */
+	if (!ts->tick_stopped) {
+		nohz_balance_enter_idle(cpu);
+		calc_load_enter_idle();
 
-		/*
-		 * If the expiration time == KTIME_MAX, then
-		 * in this case we simply stop the tick timer.
-		 */
-		 if (unlikely(expires.tv64 == KTIME_MAX)) {
-			if (ts->nohz_mode == NOHZ_MODE_HIGHRES)
-				hrtimer_cancel(&ts->sched_timer);
-			goto out;
-		}
+		ts->last_tick = hrtimer_get_expires(&ts->sched_timer);
+		ts->tick_stopped = 1;
+		trace_tick_stop(1, " ");
+	}
 
-		if (ts->nohz_mode == NOHZ_MODE_HIGHRES) {
-			hrtimer_start(&ts->sched_timer, expires,
-				      HRTIMER_MODE_ABS_PINNED);
-			/* Check, if the timer was already in the past */
-			if (hrtimer_active(&ts->sched_timer))
-				goto out;
-		} else if (!tick_program_event(expires, 0))
-				goto out;
-		/*
-		 * We are past the event already. So we crossed a
-		 * jiffie boundary. Update jiffies and raise the
-		 * softirq.
-		 */
-		tick_do_update_jiffies64(ktime_get());
+	/*
+	 * If the expiration time == KTIME_MAX, then we simply stop
+	 * the tick timer.
+	 */
+	if (unlikely(expires == KTIME_MAX)) {
+		if (ts->nohz_mode == NOHZ_MODE_HIGHRES)
+			hrtimer_cancel(&ts->sched_timer);
+		goto out;
 	}
-	raise_softirq_irqoff(TIMER_SOFTIRQ);
+
+	if (ts->nohz_mode == NOHZ_MODE_HIGHRES)
+		hrtimer_start(&ts->sched_timer, tick, HRTIMER_MODE_ABS_PINNED);
+	else
+		tick_program_event(tick, 1);
 out:
-	ts->next_jiffies = next_jiffies;
-	ts->last_jiffies = last_jiffies;
+	/* Update the estimated sleep length */
 	ts->sleep_length = ktime_sub(dev->next_event, now);
-
-	return ret;
+	return tick;
 }
 
 static void tick_nohz_full_stop_tick(struct tick_sched *ts)
@@ -876,32 +864,6 @@ ktime_t tick_nohz_get_sleep_length(void)
 	return ts->sleep_length;
 }
 
-static void tick_nohz_restart(struct tick_sched *ts, ktime_t now)
-{
-	hrtimer_cancel(&ts->sched_timer);
-	hrtimer_set_expires(&ts->sched_timer, ts->last_tick);
-
-	while (1) {
-		/* Forward the time to expire in the future */
-		hrtimer_forward(&ts->sched_timer, now, tick_period);
-
-		if (ts->nohz_mode == NOHZ_MODE_HIGHRES) {
-			hrtimer_start_expires(&ts->sched_timer,
-					      HRTIMER_MODE_ABS_PINNED);
-			/* Check, if the timer was already in the past */
-			if (hrtimer_active(&ts->sched_timer))
-				break;
-		} else {
-			if (!tick_program_event(
-				hrtimer_get_expires(&ts->sched_timer), 0))
-				break;
-		}
-		/* Reread time and update jiffies */
-		now = ktime_get();
-		tick_do_update_jiffies64(now);
-	}
-}
-
 static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now)
 {
 	/* Update jiffies first */
@@ -972,12 +934,6 @@ void tick_nohz_idle_exit(void)
 	local_irq_enable();
 }
 
-static int tick_nohz_reprogram(struct tick_sched *ts, ktime_t now)
-{
-	hrtimer_forward(&ts->sched_timer, now, tick_period);
-	return tick_program_event(hrtimer_get_expires(&ts->sched_timer), 0);
-}
-
 /*
  * The nohz low res interrupt handler
  */
@@ -996,10 +952,18 @@ static void tick_nohz_handler(struct clock_event_device *dev)
 	if (unlikely(ts->tick_stopped))
 		return;
 
-	while (tick_nohz_reprogram(ts, now)) {
-		now = ktime_get();
-		tick_do_update_jiffies64(now);
-	}
+	hrtimer_forward(&ts->sched_timer, now, tick_period);
+	tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1);
+}
+
+static inline void tick_nohz_activate(struct tick_sched *ts, int mode)
+{
+	if (!tick_nohz_enabled)
+		return;
+	ts->nohz_mode = mode;
+	/* One update is enough */
+	if (!test_and_set_bit(0, &tick_nohz_active))
+		timers_update_migration(true);
 }
 
 /**
@@ -1013,13 +977,8 @@ static void tick_nohz_switch_to_nohz(void)
 	if (!tick_nohz_enabled)
 		return;
 
-	local_irq_disable();
-	if (tick_switch_to_oneshot(tick_nohz_handler)) {
-		local_irq_enable();
+	if (tick_switch_to_oneshot(tick_nohz_handler))
 		return;
-	}
-	tick_nohz_active = 1;
-	ts->nohz_mode = NOHZ_MODE_LOWRES;
 
 	/*
 	 * Recycle the hrtimer in ts, so we can share the
@@ -1029,13 +988,10 @@ static void tick_nohz_switch_to_nohz(void)
 	/* Get the next period */
 	next = tick_init_jiffy_update();
 
-	for (;;) {
-		hrtimer_set_expires(&ts->sched_timer, next);
-		if (!tick_program_event(next, 0))
-			break;
-		next = ktime_add(next, tick_period);
-	}
-	local_irq_enable();
+	hrtimer_forward_now(&ts->sched_timer, tick_period);
+	hrtimer_set_expires(&ts->sched_timer, next);
+	tick_program_event(next, 1);
+	tick_nohz_activate(ts, NOHZ_MODE_LOWRES);
 }
 
 /*
@@ -1087,6 +1043,7 @@ static inline void tick_nohz_irq_enter(void)
 
 static inline void tick_nohz_switch_to_nohz(void) { }
 static inline void tick_nohz_irq_enter(void) { }
+static inline void tick_nohz_activate(struct tick_sched *ts, int mode) { }
 
 #endif /* CONFIG_NO_HZ_COMMON */
 
@@ -1167,22 +1124,9 @@ void tick_setup_sched_timer(void)
 		hrtimer_add_expires_ns(&ts->sched_timer, offset);
 	}
 
-	for (;;) {
-		hrtimer_forward(&ts->sched_timer, now, tick_period);
-		hrtimer_start_expires(&ts->sched_timer,
-				      HRTIMER_MODE_ABS_PINNED);
-		/* Check, if the timer was already in the past */
-		if (hrtimer_active(&ts->sched_timer))
-			break;
-		now = ktime_get();
-	}
-
-#ifdef CONFIG_NO_HZ_COMMON
-	if (tick_nohz_enabled) {
-		ts->nohz_mode = NOHZ_MODE_HIGHRES;
-		tick_nohz_active = 1;
-	}
-#endif
+	hrtimer_forward(&ts->sched_timer, now, tick_period);
+	hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS_PINNED);
+	tick_nohz_activate(ts, NOHZ_MODE_HIGHRES);
 }
 #endif /* HIGH_RES_TIMERS */
 
@@ -1227,7 +1171,7 @@ void tick_oneshot_notify(void)
  * Called cyclic from the hrtimer softirq (driven by the timer
  * softirq) allow_nohz signals, that we can switch into low-res nohz
  * mode, because high resolution timers are disabled (either compile
- * or runtime).
+ * or runtime). Called with interrupts disabled.
  */
 int tick_check_oneshot_change(int allow_nohz)
 {
diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h
index 28b5da3e1a17..42fdf4958bcc 100644
--- a/kernel/time/tick-sched.h
+++ b/kernel/time/tick-sched.h
@@ -57,7 +57,7 @@ struct tick_sched {
 	ktime_t				iowait_sleeptime;
 	ktime_t				sleep_length;
 	unsigned long			last_jiffies;
-	unsigned long			next_jiffies;
+	u64				next_timer;
 	ktime_t				idle_expires;
 	int				do_timer_last;
 };
diff --git a/kernel/time/time.c b/kernel/time/time.c
index 2c85b7724af4..85d5bb1d67eb 100644
--- a/kernel/time/time.c
+++ b/kernel/time/time.c
@@ -41,7 +41,7 @@
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
 
-#include "timeconst.h"
+#include <generated/timeconst.h>
 #include "timekeeping.h"
 
 /*
@@ -173,6 +173,10 @@ int do_sys_settimeofday(const struct timespec *tv, const struct timezone *tz)
 		return error;
 
 	if (tz) {
+		/* Verify we're witin the +-15 hrs range */
+		if (tz->tz_minuteswest > 15*60 || tz->tz_minuteswest < -15*60)
+			return -EINVAL;
+
 		sys_tz = *tz;
 		update_vsyscall_tz();
 		if (firsttime) {
@@ -483,9 +487,11 @@ struct timespec64 ns_to_timespec64(const s64 nsec)
 }
 EXPORT_SYMBOL(ns_to_timespec64);
 #endif
-/*
- * When we convert to jiffies then we interpret incoming values
- * the following way:
+/**
+ * msecs_to_jiffies: - convert milliseconds to jiffies
+ * @m:	time in milliseconds
+ *
+ * conversion is done as follows:
  *
  * - negative values mean 'infinite timeout' (MAX_JIFFY_OFFSET)
  *
@@ -493,66 +499,36 @@ EXPORT_SYMBOL(ns_to_timespec64);
  *   MAX_JIFFY_OFFSET values] mean 'infinite timeout' too.
  *
  * - all other values are converted to jiffies by either multiplying
- *   the input value by a factor or dividing it with a factor
- *
- * We must also be careful about 32-bit overflows.
+ *   the input value by a factor or dividing it with a factor and
+ *   handling any 32-bit overflows.
+ *   for the details see __msecs_to_jiffies()
+ *
+ * msecs_to_jiffies() checks for the passed in value being a constant
+ * via __builtin_constant_p() allowing gcc to eliminate most of the
+ * code, __msecs_to_jiffies() is called if the value passed does not
+ * allow constant folding and the actual conversion must be done at
+ * runtime.
+ * the _msecs_to_jiffies helpers are the HZ dependent conversion
+ * routines found in include/linux/jiffies.h
  */
-unsigned long msecs_to_jiffies(const unsigned int m)
+unsigned long __msecs_to_jiffies(const unsigned int m)
 {
 	/*
 	 * Negative value, means infinite timeout:
 	 */
 	if ((int)m < 0)
 		return MAX_JIFFY_OFFSET;
-
-#if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ)
-	/*
-	 * HZ is equal to or smaller than 1000, and 1000 is a nice
-	 * round multiple of HZ, divide with the factor between them,
-	 * but round upwards:
-	 */
-	return (m + (MSEC_PER_SEC / HZ) - 1) / (MSEC_PER_SEC / HZ);
-#elif HZ > MSEC_PER_SEC && !(HZ % MSEC_PER_SEC)
-	/*
-	 * HZ is larger than 1000, and HZ is a nice round multiple of
-	 * 1000 - simply multiply with the factor between them.
-	 *
-	 * But first make sure the multiplication result cannot
-	 * overflow:
-	 */
-	if (m > jiffies_to_msecs(MAX_JIFFY_OFFSET))
-		return MAX_JIFFY_OFFSET;
-
-	return m * (HZ / MSEC_PER_SEC);
-#else
-	/*
-	 * Generic case - multiply, round and divide. But first
-	 * check that if we are doing a net multiplication, that
-	 * we wouldn't overflow:
-	 */
-	if (HZ > MSEC_PER_SEC && m > jiffies_to_msecs(MAX_JIFFY_OFFSET))
-		return MAX_JIFFY_OFFSET;
-
-	return (MSEC_TO_HZ_MUL32 * m + MSEC_TO_HZ_ADJ32)
-		>> MSEC_TO_HZ_SHR32;
-#endif
+	return _msecs_to_jiffies(m);
 }
-EXPORT_SYMBOL(msecs_to_jiffies);
+EXPORT_SYMBOL(__msecs_to_jiffies);
 
-unsigned long usecs_to_jiffies(const unsigned int u)
+unsigned long __usecs_to_jiffies(const unsigned int u)
 {
 	if (u > jiffies_to_usecs(MAX_JIFFY_OFFSET))
 		return MAX_JIFFY_OFFSET;
-#if HZ <= USEC_PER_SEC && !(USEC_PER_SEC % HZ)
-	return (u + (USEC_PER_SEC / HZ) - 1) / (USEC_PER_SEC / HZ);
-#elif HZ > USEC_PER_SEC && !(HZ % USEC_PER_SEC)
-	return u * (HZ / USEC_PER_SEC);
-#else
-	return (USEC_TO_HZ_MUL32 * u + USEC_TO_HZ_ADJ32)
-		>> USEC_TO_HZ_SHR32;
-#endif
+	return _usecs_to_jiffies(u);
 }
-EXPORT_SYMBOL(usecs_to_jiffies);
+EXPORT_SYMBOL(__usecs_to_jiffies);
 
 /*
  * The TICK_NSEC - 1 rounds up the value to the next resolution.  Note
diff --git a/kernel/time/timeconst.bc b/kernel/time/timeconst.bc
index 511bdf2cafda..c7388dee8635 100644
--- a/kernel/time/timeconst.bc
+++ b/kernel/time/timeconst.bc
@@ -50,7 +50,7 @@ define timeconst(hz) {
 	print "#include <linux/types.h>\n\n"
 
 	print "#if HZ != ", hz, "\n"
-	print "#error \qkernel/timeconst.h has the wrong HZ value!\q\n"
+	print "#error \qinclude/generated/timeconst.h has the wrong HZ value!\q\n"
 	print "#endif\n\n"
 
 	if (hz < 2) {
@@ -105,4 +105,5 @@ define timeconst(hz) {
 	halt
 }
 
+hz = read();
 timeconst(hz)
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 946acb72179f..30b7a409bf1e 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -118,18 +118,6 @@ static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta)
 
 #ifdef CONFIG_DEBUG_TIMEKEEPING
 #define WARNING_FREQ (HZ*300) /* 5 minute rate-limiting */
-/*
- * These simple flag variables are managed
- * without locks, which is racy, but ok since
- * we don't really care about being super
- * precise about how many events were seen,
- * just that a problem was observed.
- */
-static int timekeeping_underflow_seen;
-static int timekeeping_overflow_seen;
-
-/* last_warning is only modified under the timekeeping lock */
-static long timekeeping_last_warning;
 
 static void timekeeping_check_update(struct timekeeper *tk, cycle_t offset)
 {
@@ -149,29 +137,30 @@ static void timekeeping_check_update(struct timekeeper *tk, cycle_t offset)
 		}
 	}
 
-	if (timekeeping_underflow_seen) {
-		if (jiffies - timekeeping_last_warning > WARNING_FREQ) {
+	if (tk->underflow_seen) {
+		if (jiffies - tk->last_warning > WARNING_FREQ) {
 			printk_deferred("WARNING: Underflow in clocksource '%s' observed, time update ignored.\n", name);
 			printk_deferred("         Please report this, consider using a different clocksource, if possible.\n");
 			printk_deferred("         Your kernel is probably still fine.\n");
-			timekeeping_last_warning = jiffies;
+			tk->last_warning = jiffies;
 		}
-		timekeeping_underflow_seen = 0;
+		tk->underflow_seen = 0;
 	}
 
-	if (timekeeping_overflow_seen) {
-		if (jiffies - timekeeping_last_warning > WARNING_FREQ) {
+	if (tk->overflow_seen) {
+		if (jiffies - tk->last_warning > WARNING_FREQ) {
 			printk_deferred("WARNING: Overflow in clocksource '%s' observed, time update capped.\n", name);
 			printk_deferred("         Please report this, consider using a different clocksource, if possible.\n");
 			printk_deferred("         Your kernel is probably still fine.\n");
-			timekeeping_last_warning = jiffies;
+			tk->last_warning = jiffies;
 		}
-		timekeeping_overflow_seen = 0;
+		tk->overflow_seen = 0;
 	}
 }
 
 static inline cycle_t timekeeping_get_delta(struct tk_read_base *tkr)
 {
+	struct timekeeper *tk = &tk_core.timekeeper;
 	cycle_t now, last, mask, max, delta;
 	unsigned int seq;
 
@@ -197,13 +186,13 @@ static inline cycle_t timekeeping_get_delta(struct tk_read_base *tkr)
 	 * mask-relative negative values.
 	 */
 	if (unlikely((~delta & mask) < (mask >> 3))) {
-		timekeeping_underflow_seen = 1;
+		tk->underflow_seen = 1;
 		delta = 0;
 	}
 
 	/* Cap delta value to the max_cycles values to avoid mult overflows */
 	if (unlikely(delta > max)) {
-		timekeeping_overflow_seen = 1;
+		tk->overflow_seen = 1;
 		delta = tkr->clock->max_cycles;
 	}
 
@@ -551,6 +540,17 @@ int pvclock_gtod_unregister_notifier(struct notifier_block *nb)
 EXPORT_SYMBOL_GPL(pvclock_gtod_unregister_notifier);
 
 /*
+ * tk_update_leap_state - helper to update the next_leap_ktime
+ */
+static inline void tk_update_leap_state(struct timekeeper *tk)
+{
+	tk->next_leap_ktime = ntp_get_next_leap();
+	if (tk->next_leap_ktime.tv64 != KTIME_MAX)
+		/* Convert to monotonic time */
+		tk->next_leap_ktime = ktime_sub(tk->next_leap_ktime, tk->offs_real);
+}
+
+/*
  * Update the ktime_t based scalar nsec members of the timekeeper
  */
 static inline void tk_update_ktime_data(struct timekeeper *tk)
@@ -591,17 +591,25 @@ static void timekeeping_update(struct timekeeper *tk, unsigned int action)
 		ntp_clear();
 	}
 
+	tk_update_leap_state(tk);
 	tk_update_ktime_data(tk);
 
 	update_vsyscall(tk);
 	update_pvclock_gtod(tk, action & TK_CLOCK_WAS_SET);
 
+	update_fast_timekeeper(&tk->tkr_mono, &tk_fast_mono);
+	update_fast_timekeeper(&tk->tkr_raw,  &tk_fast_raw);
+
+	if (action & TK_CLOCK_WAS_SET)
+		tk->clock_was_set_seq++;
+	/*
+	 * The mirroring of the data to the shadow-timekeeper needs
+	 * to happen last here to ensure we don't over-write the
+	 * timekeeper structure on the next update with stale data
+	 */
 	if (action & TK_MIRROR)
 		memcpy(&shadow_timekeeper, &tk_core.timekeeper,
 		       sizeof(tk_core.timekeeper));
-
-	update_fast_timekeeper(&tk->tkr_mono, &tk_fast_mono);
-	update_fast_timekeeper(&tk->tkr_raw,  &tk_fast_raw);
 }
 
 /**
@@ -699,6 +707,23 @@ ktime_t ktime_get(void)
 }
 EXPORT_SYMBOL_GPL(ktime_get);
 
+u32 ktime_get_resolution_ns(void)
+{
+	struct timekeeper *tk = &tk_core.timekeeper;
+	unsigned int seq;
+	u32 nsecs;
+
+	WARN_ON(timekeeping_suspended);
+
+	do {
+		seq = read_seqcount_begin(&tk_core.seq);
+		nsecs = tk->tkr_mono.mult >> tk->tkr_mono.shift;
+	} while (read_seqcount_retry(&tk_core.seq, seq));
+
+	return nsecs;
+}
+EXPORT_SYMBOL_GPL(ktime_get_resolution_ns);
+
 static ktime_t *offsets[TK_OFFS_MAX] = {
 	[TK_OFFS_REAL]	= &tk_core.timekeeper.offs_real,
 	[TK_OFFS_BOOT]	= &tk_core.timekeeper.offs_boot,
@@ -1179,28 +1204,20 @@ void __weak read_persistent_clock64(struct timespec64 *ts64)
 }
 
 /**
- * read_boot_clock -  Return time of the system start.
+ * read_boot_clock64 -  Return time of the system start.
  *
  * Weak dummy function for arches that do not yet support it.
  * Function to read the exact time the system has been started.
- * Returns a timespec with tv_sec=0 and tv_nsec=0 if unsupported.
+ * Returns a timespec64 with tv_sec=0 and tv_nsec=0 if unsupported.
  *
  *  XXX - Do be sure to remove it once all arches implement it.
  */
-void __weak read_boot_clock(struct timespec *ts)
+void __weak read_boot_clock64(struct timespec64 *ts)
 {
 	ts->tv_sec = 0;
 	ts->tv_nsec = 0;
 }
 
-void __weak read_boot_clock64(struct timespec64 *ts64)
-{
-	struct timespec ts;
-
-	read_boot_clock(&ts);
-	*ts64 = timespec_to_timespec64(ts);
-}
-
 /* Flag for if timekeeping_resume() has injected sleeptime */
 static bool sleeptime_injected;
 
@@ -1836,8 +1853,9 @@ void update_wall_time(void)
 	 * memcpy under the tk_core.seq against one before we start
 	 * updating.
 	 */
+	timekeeping_update(tk, clock_set);
 	memcpy(real_tk, tk, sizeof(*tk));
-	timekeeping_update(real_tk, clock_set);
+	/* The memcpy must come last. Do not put anything here! */
 	write_seqcount_end(&tk_core.seq);
 out:
 	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
@@ -1926,47 +1944,20 @@ void do_timer(unsigned long ticks)
 }
 
 /**
- * ktime_get_update_offsets_tick - hrtimer helper
- * @offs_real:	pointer to storage for monotonic -> realtime offset
- * @offs_boot:	pointer to storage for monotonic -> boottime offset
- * @offs_tai:	pointer to storage for monotonic -> clock tai offset
- *
- * Returns monotonic time at last tick and various offsets
- */
-ktime_t ktime_get_update_offsets_tick(ktime_t *offs_real, ktime_t *offs_boot,
-							ktime_t *offs_tai)
-{
-	struct timekeeper *tk = &tk_core.timekeeper;
-	unsigned int seq;
-	ktime_t base;
-	u64 nsecs;
-
-	do {
-		seq = read_seqcount_begin(&tk_core.seq);
-
-		base = tk->tkr_mono.base;
-		nsecs = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift;
-
-		*offs_real = tk->offs_real;
-		*offs_boot = tk->offs_boot;
-		*offs_tai = tk->offs_tai;
-	} while (read_seqcount_retry(&tk_core.seq, seq));
-
-	return ktime_add_ns(base, nsecs);
-}
-
-#ifdef CONFIG_HIGH_RES_TIMERS
-/**
  * ktime_get_update_offsets_now - hrtimer helper
+ * @cwsseq:	pointer to check and store the clock was set sequence number
  * @offs_real:	pointer to storage for monotonic -> realtime offset
  * @offs_boot:	pointer to storage for monotonic -> boottime offset
  * @offs_tai:	pointer to storage for monotonic -> clock tai offset
  *
- * Returns current monotonic time and updates the offsets
+ * Returns current monotonic time and updates the offsets if the
+ * sequence number in @cwsseq and timekeeper.clock_was_set_seq are
+ * different.
+ *
  * Called from hrtimer_interrupt() or retrigger_next_event()
  */
-ktime_t ktime_get_update_offsets_now(ktime_t *offs_real, ktime_t *offs_boot,
-							ktime_t *offs_tai)
+ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real,
+				     ktime_t *offs_boot, ktime_t *offs_tai)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
 	unsigned int seq;
@@ -1978,15 +1969,23 @@ ktime_t ktime_get_update_offsets_now(ktime_t *offs_real, ktime_t *offs_boot,
 
 		base = tk->tkr_mono.base;
 		nsecs = timekeeping_get_ns(&tk->tkr_mono);
+		base = ktime_add_ns(base, nsecs);
+
+		if (*cwsseq != tk->clock_was_set_seq) {
+			*cwsseq = tk->clock_was_set_seq;
+			*offs_real = tk->offs_real;
+			*offs_boot = tk->offs_boot;
+			*offs_tai = tk->offs_tai;
+		}
+
+		/* Handle leapsecond insertion adjustments */
+		if (unlikely(base.tv64 >= tk->next_leap_ktime.tv64))
+			*offs_real = ktime_sub(tk->offs_real, ktime_set(1, 0));
 
-		*offs_real = tk->offs_real;
-		*offs_boot = tk->offs_boot;
-		*offs_tai = tk->offs_tai;
 	} while (read_seqcount_retry(&tk_core.seq, seq));
 
-	return ktime_add_ns(base, nsecs);
+	return base;
 }
-#endif
 
 /**
  * do_adjtimex() - Accessor function to NTP __do_adjtimex function
@@ -2027,6 +2026,8 @@ int do_adjtimex(struct timex *txc)
 		__timekeeping_set_tai_offset(tk, tai);
 		timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET);
 	}
+	tk_update_leap_state(tk);
+
 	write_seqcount_end(&tk_core.seq);
 	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
 
diff --git a/kernel/time/timekeeping.h b/kernel/time/timekeeping.h
index ead8794b9a4e..704f595ce83f 100644
--- a/kernel/time/timekeeping.h
+++ b/kernel/time/timekeeping.h
@@ -3,19 +3,16 @@
 /*
  * Internal interfaces for kernel/time/
  */
-extern ktime_t ktime_get_update_offsets_tick(ktime_t *offs_real,
-						ktime_t *offs_boot,
-						ktime_t *offs_tai);
-extern ktime_t ktime_get_update_offsets_now(ktime_t *offs_real,
-						ktime_t *offs_boot,
-						ktime_t *offs_tai);
+extern ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq,
+					    ktime_t *offs_real,
+					    ktime_t *offs_boot,
+					    ktime_t *offs_tai);
 
 extern int timekeeping_valid_for_hres(void);
 extern u64 timekeeping_max_deferment(void);
 extern int timekeeping_inject_offset(struct timespec *ts);
 extern s32 timekeeping_get_tai_offset(void);
 extern void timekeeping_set_tai_offset(s32 tai_offset);
-extern void timekeeping_clocktai(struct timespec *ts);
 extern int timekeeping_suspend(void);
 extern void timekeeping_resume(void);
 
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 2ece3aa5069c..520499dd85af 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -49,6 +49,8 @@
 #include <asm/timex.h>
 #include <asm/io.h>
 
+#include "tick-internal.h"
+
 #define CREATE_TRACE_POINTS
 #include <trace/events/timer.h>
 
@@ -68,11 +70,11 @@ EXPORT_SYMBOL(jiffies_64);
 #define MAX_TVAL ((unsigned long)((1ULL << (TVR_BITS + 4*TVN_BITS)) - 1))
 
 struct tvec {
-	struct list_head vec[TVN_SIZE];
+	struct hlist_head vec[TVN_SIZE];
 };
 
 struct tvec_root {
-	struct list_head vec[TVR_SIZE];
+	struct hlist_head vec[TVR_SIZE];
 };
 
 struct tvec_base {
@@ -83,6 +85,8 @@ struct tvec_base {
 	unsigned long active_timers;
 	unsigned long all_timers;
 	int cpu;
+	bool migration_enabled;
+	bool nohz_active;
 	struct tvec_root tv1;
 	struct tvec tv2;
 	struct tvec tv3;
@@ -90,43 +94,60 @@ struct tvec_base {
 	struct tvec tv5;
 } ____cacheline_aligned;
 
-/*
- * __TIMER_INITIALIZER() needs to set ->base to a valid pointer (because we've
- * made NULL special, hint: lock_timer_base()) and we cannot get a compile time
- * pointer to per-cpu entries because we don't know where we'll map the section,
- * even for the boot cpu.
- *
- * And so we use boot_tvec_bases for boot CPU and per-cpu __tvec_bases for the
- * rest of them.
- */
-struct tvec_base boot_tvec_bases;
-EXPORT_SYMBOL(boot_tvec_bases);
 
-static DEFINE_PER_CPU(struct tvec_base *, tvec_bases) = &boot_tvec_bases;
+static DEFINE_PER_CPU(struct tvec_base, tvec_bases);
+
+#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
+unsigned int sysctl_timer_migration = 1;
 
-/* Functions below help us manage 'deferrable' flag */
-static inline unsigned int tbase_get_deferrable(struct tvec_base *base)
+void timers_update_migration(bool update_nohz)
 {
-	return ((unsigned int)(unsigned long)base & TIMER_DEFERRABLE);
+	bool on = sysctl_timer_migration && tick_nohz_active;
+	unsigned int cpu;
+
+	/* Avoid the loop, if nothing to update */
+	if (this_cpu_read(tvec_bases.migration_enabled) == on)
+		return;
+
+	for_each_possible_cpu(cpu) {
+		per_cpu(tvec_bases.migration_enabled, cpu) = on;
+		per_cpu(hrtimer_bases.migration_enabled, cpu) = on;
+		if (!update_nohz)
+			continue;
+		per_cpu(tvec_bases.nohz_active, cpu) = true;
+		per_cpu(hrtimer_bases.nohz_active, cpu) = true;
+	}
 }
 
-static inline unsigned int tbase_get_irqsafe(struct tvec_base *base)
+int timer_migration_handler(struct ctl_table *table, int write,
+			    void __user *buffer, size_t *lenp,
+			    loff_t *ppos)
 {
-	return ((unsigned int)(unsigned long)base & TIMER_IRQSAFE);
+	static DEFINE_MUTEX(mutex);
+	int ret;
+
+	mutex_lock(&mutex);
+	ret = proc_dointvec(table, write, buffer, lenp, ppos);
+	if (!ret && write)
+		timers_update_migration(false);
+	mutex_unlock(&mutex);
+	return ret;
 }
 
-static inline struct tvec_base *tbase_get_base(struct tvec_base *base)
+static inline struct tvec_base *get_target_base(struct tvec_base *base,
+						int pinned)
 {
-	return ((struct tvec_base *)((unsigned long)base & ~TIMER_FLAG_MASK));
+	if (pinned || !base->migration_enabled)
+		return this_cpu_ptr(&tvec_bases);
+	return per_cpu_ptr(&tvec_bases, get_nohz_timer_target());
 }
-
-static inline void
-timer_set_base(struct timer_list *timer, struct tvec_base *new_base)
+#else
+static inline struct tvec_base *get_target_base(struct tvec_base *base,
+						int pinned)
 {
-	unsigned long flags = (unsigned long)timer->base & TIMER_FLAG_MASK;
-
-	timer->base = (struct tvec_base *)((unsigned long)(new_base) | flags);
+	return this_cpu_ptr(&tvec_bases);
 }
+#endif
 
 static unsigned long round_jiffies_common(unsigned long j, int cpu,
 		bool force_up)
@@ -349,26 +370,12 @@ void set_timer_slack(struct timer_list *timer, int slack_hz)
 }
 EXPORT_SYMBOL_GPL(set_timer_slack);
 
-/*
- * If the list is empty, catch up ->timer_jiffies to the current time.
- * The caller must hold the tvec_base lock.  Returns true if the list
- * was empty and therefore ->timer_jiffies was updated.
- */
-static bool catchup_timer_jiffies(struct tvec_base *base)
-{
-	if (!base->all_timers) {
-		base->timer_jiffies = jiffies;
-		return true;
-	}
-	return false;
-}
-
 static void
 __internal_add_timer(struct tvec_base *base, struct timer_list *timer)
 {
 	unsigned long expires = timer->expires;
 	unsigned long idx = expires - base->timer_jiffies;
-	struct list_head *vec;
+	struct hlist_head *vec;
 
 	if (idx < TVR_SIZE) {
 		int i = expires & TVR_MASK;
@@ -401,25 +408,25 @@ __internal_add_timer(struct tvec_base *base, struct timer_list *timer)
 		i = (expires >> (TVR_BITS + 3 * TVN_BITS)) & TVN_MASK;
 		vec = base->tv5.vec + i;
 	}
-	/*
-	 * Timers are FIFO:
-	 */
-	list_add_tail(&timer->entry, vec);
+
+	hlist_add_head(&timer->entry, vec);
 }
 
 static void internal_add_timer(struct tvec_base *base, struct timer_list *timer)
 {
-	(void)catchup_timer_jiffies(base);
+	/* Advance base->jiffies, if the base is empty */
+	if (!base->all_timers++)
+		base->timer_jiffies = jiffies;
+
 	__internal_add_timer(base, timer);
 	/*
 	 * Update base->active_timers and base->next_timer
 	 */
-	if (!tbase_get_deferrable(timer->base)) {
+	if (!(timer->flags & TIMER_DEFERRABLE)) {
 		if (!base->active_timers++ ||
 		    time_before(timer->expires, base->next_timer))
 			base->next_timer = timer->expires;
 	}
-	base->all_timers++;
 
 	/*
 	 * Check whether the other CPU is in dynticks mode and needs
@@ -434,8 +441,11 @@ static void internal_add_timer(struct tvec_base *base, struct timer_list *timer)
 	 * require special care against races with idle_cpu(), lets deal
 	 * with that later.
 	 */
-	if (!tbase_get_deferrable(base) || tick_nohz_full_cpu(base->cpu))
-		wake_up_nohz_cpu(base->cpu);
+	if (base->nohz_active) {
+		if (!(timer->flags & TIMER_DEFERRABLE) ||
+		    tick_nohz_full_cpu(base->cpu))
+			wake_up_nohz_cpu(base->cpu);
+	}
 }
 
 #ifdef CONFIG_TIMER_STATS
@@ -451,15 +461,12 @@ void __timer_stats_timer_set_start_info(struct timer_list *timer, void *addr)
 
 static void timer_stats_account_timer(struct timer_list *timer)
 {
-	unsigned int flag = 0;
-
 	if (likely(!timer->start_site))
 		return;
-	if (unlikely(tbase_get_deferrable(timer->base)))
-		flag |= TIMER_STATS_FLAG_DEFERRABLE;
 
 	timer_stats_update_stats(timer, timer->start_pid, timer->start_site,
-				 timer->function, timer->start_comm, flag);
+				 timer->function, timer->start_comm,
+				 timer->flags);
 }
 
 #else
@@ -516,8 +523,8 @@ static int timer_fixup_activate(void *addr, enum debug_obj_state state)
 		 * statically initialized. We just make sure that it
 		 * is tracked in the object tracker.
 		 */
-		if (timer->entry.next == NULL &&
-		    timer->entry.prev == TIMER_ENTRY_STATIC) {
+		if (timer->entry.pprev == NULL &&
+		    timer->entry.next == TIMER_ENTRY_STATIC) {
 			debug_object_init(timer, &timer_debug_descr);
 			debug_object_activate(timer, &timer_debug_descr);
 			return 0;
@@ -563,7 +570,7 @@ static int timer_fixup_assert_init(void *addr, enum debug_obj_state state)
 
 	switch (state) {
 	case ODEBUG_STATE_NOTAVAILABLE:
-		if (timer->entry.prev == TIMER_ENTRY_STATIC) {
+		if (timer->entry.next == TIMER_ENTRY_STATIC) {
 			/*
 			 * This is not really a fixup. The timer was
 			 * statically initialized. We just make sure that it
@@ -648,7 +655,7 @@ static inline void
 debug_activate(struct timer_list *timer, unsigned long expires)
 {
 	debug_timer_activate(timer);
-	trace_timer_start(timer, expires);
+	trace_timer_start(timer, expires, timer->flags);
 }
 
 static inline void debug_deactivate(struct timer_list *timer)
@@ -665,10 +672,8 @@ static inline void debug_assert_init(struct timer_list *timer)
 static void do_init_timer(struct timer_list *timer, unsigned int flags,
 			  const char *name, struct lock_class_key *key)
 {
-	struct tvec_base *base = raw_cpu_read(tvec_bases);
-
-	timer->entry.next = NULL;
-	timer->base = (void *)((unsigned long)base | flags);
+	timer->entry.pprev = NULL;
+	timer->flags = flags | raw_smp_processor_id();
 	timer->slack = -1;
 #ifdef CONFIG_TIMER_STATS
 	timer->start_site = NULL;
@@ -699,24 +704,23 @@ EXPORT_SYMBOL(init_timer_key);
 
 static inline void detach_timer(struct timer_list *timer, bool clear_pending)
 {
-	struct list_head *entry = &timer->entry;
+	struct hlist_node *entry = &timer->entry;
 
 	debug_deactivate(timer);
 
-	__list_del(entry->prev, entry->next);
+	__hlist_del(entry);
 	if (clear_pending)
-		entry->next = NULL;
-	entry->prev = LIST_POISON2;
+		entry->pprev = NULL;
+	entry->next = LIST_POISON2;
 }
 
 static inline void
 detach_expired_timer(struct timer_list *timer, struct tvec_base *base)
 {
 	detach_timer(timer, true);
-	if (!tbase_get_deferrable(timer->base))
+	if (!(timer->flags & TIMER_DEFERRABLE))
 		base->active_timers--;
 	base->all_timers--;
-	(void)catchup_timer_jiffies(base);
 }
 
 static int detach_if_pending(struct timer_list *timer, struct tvec_base *base,
@@ -726,13 +730,14 @@ static int detach_if_pending(struct timer_list *timer, struct tvec_base *base,
 		return 0;
 
 	detach_timer(timer, clear_pending);
-	if (!tbase_get_deferrable(timer->base)) {
+	if (!(timer->flags & TIMER_DEFERRABLE)) {
 		base->active_timers--;
 		if (timer->expires == base->next_timer)
 			base->next_timer = base->timer_jiffies;
 	}
-	base->all_timers--;
-	(void)catchup_timer_jiffies(base);
+	/* If this was the last timer, advance base->jiffies */
+	if (!--base->all_timers)
+		base->timer_jiffies = jiffies;
 	return 1;
 }
 
@@ -744,24 +749,22 @@ static int detach_if_pending(struct timer_list *timer, struct tvec_base *base,
  * So __run_timers/migrate_timers can safely modify all timers which could
  * be found on ->tvX lists.
  *
- * When the timer's base is locked, and the timer removed from list, it is
- * possible to set timer->base = NULL and drop the lock: the timer remains
- * locked.
+ * When the timer's base is locked and removed from the list, the
+ * TIMER_MIGRATING flag is set, FIXME
  */
 static struct tvec_base *lock_timer_base(struct timer_list *timer,
 					unsigned long *flags)
 	__acquires(timer->base->lock)
 {
-	struct tvec_base *base;
-
 	for (;;) {
-		struct tvec_base *prelock_base = timer->base;
-		base = tbase_get_base(prelock_base);
-		if (likely(base != NULL)) {
+		u32 tf = timer->flags;
+		struct tvec_base *base;
+
+		if (!(tf & TIMER_MIGRATING)) {
+			base = per_cpu_ptr(&tvec_bases, tf & TIMER_CPUMASK);
 			spin_lock_irqsave(&base->lock, *flags);
-			if (likely(prelock_base == timer->base))
+			if (timer->flags == tf)
 				return base;
-			/* The timer has migrated to another CPU */
 			spin_unlock_irqrestore(&base->lock, *flags);
 		}
 		cpu_relax();
@@ -770,11 +773,11 @@ static struct tvec_base *lock_timer_base(struct timer_list *timer,
 
 static inline int
 __mod_timer(struct timer_list *timer, unsigned long expires,
-						bool pending_only, int pinned)
+	    bool pending_only, int pinned)
 {
 	struct tvec_base *base, *new_base;
 	unsigned long flags;
-	int ret = 0 , cpu;
+	int ret = 0;
 
 	timer_stats_timer_set_start_info(timer);
 	BUG_ON(!timer->function);
@@ -787,8 +790,7 @@ __mod_timer(struct timer_list *timer, unsigned long expires,
 
 	debug_activate(timer, expires);
 
-	cpu = get_nohz_timer_target(pinned);
-	new_base = per_cpu(tvec_bases, cpu);
+	new_base = get_target_base(base, pinned);
 
 	if (base != new_base) {
 		/*
@@ -800,11 +802,13 @@ __mod_timer(struct timer_list *timer, unsigned long expires,
 		 */
 		if (likely(base->running_timer != timer)) {
 			/* See the comment in lock_timer_base() */
-			timer_set_base(timer, NULL);
+			timer->flags |= TIMER_MIGRATING;
+
 			spin_unlock(&base->lock);
 			base = new_base;
 			spin_lock(&base->lock);
-			timer_set_base(timer, base);
+			timer->flags &= ~TIMER_BASEMASK;
+			timer->flags |= base->cpu;
 		}
 	}
 
@@ -966,13 +970,13 @@ EXPORT_SYMBOL(add_timer);
  */
 void add_timer_on(struct timer_list *timer, int cpu)
 {
-	struct tvec_base *base = per_cpu(tvec_bases, cpu);
+	struct tvec_base *base = per_cpu_ptr(&tvec_bases, cpu);
 	unsigned long flags;
 
 	timer_stats_timer_set_start_info(timer);
 	BUG_ON(timer_pending(timer) || !timer->function);
 	spin_lock_irqsave(&base->lock, flags);
-	timer_set_base(timer, base);
+	timer->flags = (timer->flags & ~TIMER_BASEMASK) | cpu;
 	debug_activate(timer, timer->expires);
 	internal_add_timer(base, timer);
 	spin_unlock_irqrestore(&base->lock, flags);
@@ -1037,8 +1041,6 @@ int try_to_del_timer_sync(struct timer_list *timer)
 EXPORT_SYMBOL(try_to_del_timer_sync);
 
 #ifdef CONFIG_SMP
-static DEFINE_PER_CPU(struct tvec_base, __tvec_bases);
-
 /**
  * del_timer_sync - deactivate a timer and wait for the handler to finish.
  * @timer: the timer to be deactivated
@@ -1093,7 +1095,7 @@ int del_timer_sync(struct timer_list *timer)
 	 * don't use it in hardirq context, because it
 	 * could lead to deadlock.
 	 */
-	WARN_ON(in_irq() && !tbase_get_irqsafe(timer->base));
+	WARN_ON(in_irq() && !(timer->flags & TIMER_IRQSAFE));
 	for (;;) {
 		int ret = try_to_del_timer_sync(timer);
 		if (ret >= 0)
@@ -1107,17 +1109,17 @@ EXPORT_SYMBOL(del_timer_sync);
 static int cascade(struct tvec_base *base, struct tvec *tv, int index)
 {
 	/* cascade all the timers from tv up one level */
-	struct timer_list *timer, *tmp;
-	struct list_head tv_list;
+	struct timer_list *timer;
+	struct hlist_node *tmp;
+	struct hlist_head tv_list;
 
-	list_replace_init(tv->vec + index, &tv_list);
+	hlist_move_list(tv->vec + index, &tv_list);
 
 	/*
 	 * We are removing _all_ timers from the list, so we
 	 * don't have to detach them individually.
 	 */
-	list_for_each_entry_safe(timer, tmp, &tv_list, entry) {
-		BUG_ON(tbase_get_base(timer->base) != base);
+	hlist_for_each_entry_safe(timer, tmp, &tv_list, entry) {
 		/* No accounting, while moving them */
 		__internal_add_timer(base, timer);
 	}
@@ -1182,14 +1184,18 @@ static inline void __run_timers(struct tvec_base *base)
 	struct timer_list *timer;
 
 	spin_lock_irq(&base->lock);
-	if (catchup_timer_jiffies(base)) {
-		spin_unlock_irq(&base->lock);
-		return;
-	}
+
 	while (time_after_eq(jiffies, base->timer_jiffies)) {
-		struct list_head work_list;
-		struct list_head *head = &work_list;
-		int index = base->timer_jiffies & TVR_MASK;
+		struct hlist_head work_list;
+		struct hlist_head *head = &work_list;
+		int index;
+
+		if (!base->all_timers) {
+			base->timer_jiffies = jiffies;
+			break;
+		}
+
+		index = base->timer_jiffies & TVR_MASK;
 
 		/*
 		 * Cascade timers:
@@ -1200,16 +1206,16 @@ static inline void __run_timers(struct tvec_base *base)
 					!cascade(base, &base->tv4, INDEX(2)))
 			cascade(base, &base->tv5, INDEX(3));
 		++base->timer_jiffies;
-		list_replace_init(base->tv1.vec + index, head);
-		while (!list_empty(head)) {
+		hlist_move_list(base->tv1.vec + index, head);
+		while (!hlist_empty(head)) {
 			void (*fn)(unsigned long);
 			unsigned long data;
 			bool irqsafe;
 
-			timer = list_first_entry(head, struct timer_list,entry);
+			timer = hlist_entry(head->first, struct timer_list, entry);
 			fn = timer->function;
 			data = timer->data;
-			irqsafe = tbase_get_irqsafe(timer->base);
+			irqsafe = timer->flags & TIMER_IRQSAFE;
 
 			timer_stats_account_timer(timer);
 
@@ -1248,8 +1254,8 @@ static unsigned long __next_timer_interrupt(struct tvec_base *base)
 	/* Look for timer events in tv1. */
 	index = slot = timer_jiffies & TVR_MASK;
 	do {
-		list_for_each_entry(nte, base->tv1.vec + slot, entry) {
-			if (tbase_get_deferrable(nte->base))
+		hlist_for_each_entry(nte, base->tv1.vec + slot, entry) {
+			if (nte->flags & TIMER_DEFERRABLE)
 				continue;
 
 			found = 1;
@@ -1279,8 +1285,8 @@ cascade:
 
 		index = slot = timer_jiffies & TVN_MASK;
 		do {
-			list_for_each_entry(nte, varp->vec + slot, entry) {
-				if (tbase_get_deferrable(nte->base))
+			hlist_for_each_entry(nte, varp->vec + slot, entry) {
+				if (nte->flags & TIMER_DEFERRABLE)
 					continue;
 
 				found = 1;
@@ -1311,54 +1317,48 @@ cascade:
  * Check, if the next hrtimer event is before the next timer wheel
  * event:
  */
-static unsigned long cmp_next_hrtimer_event(unsigned long now,
-					    unsigned long expires)
+static u64 cmp_next_hrtimer_event(u64 basem, u64 expires)
 {
-	ktime_t hr_delta = hrtimer_get_next_event();
-	struct timespec tsdelta;
-	unsigned long delta;
-
-	if (hr_delta.tv64 == KTIME_MAX)
-		return expires;
+	u64 nextevt = hrtimer_get_next_event();
 
 	/*
-	 * Expired timer available, let it expire in the next tick
+	 * If high resolution timers are enabled
+	 * hrtimer_get_next_event() returns KTIME_MAX.
 	 */
-	if (hr_delta.tv64 <= 0)
-		return now + 1;
-
-	tsdelta = ktime_to_timespec(hr_delta);
-	delta = timespec_to_jiffies(&tsdelta);
+	if (expires <= nextevt)
+		return expires;
 
 	/*
-	 * Limit the delta to the max value, which is checked in
-	 * tick_nohz_stop_sched_tick():
+	 * If the next timer is already expired, return the tick base
+	 * time so the tick is fired immediately.
 	 */
-	if (delta > NEXT_TIMER_MAX_DELTA)
-		delta = NEXT_TIMER_MAX_DELTA;
+	if (nextevt <= basem)
+		return basem;
 
 	/*
-	 * Take rounding errors in to account and make sure, that it
-	 * expires in the next tick. Otherwise we go into an endless
-	 * ping pong due to tick_nohz_stop_sched_tick() retriggering
-	 * the timer softirq
+	 * Round up to the next jiffie. High resolution timers are
+	 * off, so the hrtimers are expired in the tick and we need to
+	 * make sure that this tick really expires the timer to avoid
+	 * a ping pong of the nohz stop code.
+	 *
+	 * Use DIV_ROUND_UP_ULL to prevent gcc calling __divdi3
 	 */
-	if (delta < 1)
-		delta = 1;
-	now += delta;
-	if (time_before(now, expires))
-		return now;
-	return expires;
+	return DIV_ROUND_UP_ULL(nextevt, TICK_NSEC) * TICK_NSEC;
 }
 
 /**
- * get_next_timer_interrupt - return the jiffy of the next pending timer
- * @now: current time (in jiffies)
+ * get_next_timer_interrupt - return the time (clock mono) of the next timer
+ * @basej:	base time jiffies
+ * @basem:	base time clock monotonic
+ *
+ * Returns the tick aligned clock monotonic time of the next pending
+ * timer or KTIME_MAX if no timer is pending.
  */
-unsigned long get_next_timer_interrupt(unsigned long now)
+u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
 {
-	struct tvec_base *base = __this_cpu_read(tvec_bases);
-	unsigned long expires = now + NEXT_TIMER_MAX_DELTA;
+	struct tvec_base *base = this_cpu_ptr(&tvec_bases);
+	u64 expires = KTIME_MAX;
+	unsigned long nextevt;
 
 	/*
 	 * Pretend that there is no timer pending if the cpu is offline.
@@ -1371,14 +1371,15 @@ unsigned long get_next_timer_interrupt(unsigned long now)
 	if (base->active_timers) {
 		if (time_before_eq(base->next_timer, base->timer_jiffies))
 			base->next_timer = __next_timer_interrupt(base);
-		expires = base->next_timer;
+		nextevt = base->next_timer;
+		if (time_before_eq(nextevt, basej))
+			expires = basem;
+		else
+			expires = basem + (nextevt - basej) * TICK_NSEC;
 	}
 	spin_unlock(&base->lock);
 
-	if (time_before_eq(expires, now))
-		return now;
-
-	return cmp_next_hrtimer_event(now, expires);
+	return cmp_next_hrtimer_event(basem, expires);
 }
 #endif
 
@@ -1407,9 +1408,7 @@ void update_process_times(int user_tick)
  */
 static void run_timer_softirq(struct softirq_action *h)
 {
-	struct tvec_base *base = __this_cpu_read(tvec_bases);
-
-	hrtimer_run_pending();
+	struct tvec_base *base = this_cpu_ptr(&tvec_bases);
 
 	if (time_after_eq(jiffies, base->timer_jiffies))
 		__run_timers(base);
@@ -1545,15 +1544,16 @@ signed long __sched schedule_timeout_uninterruptible(signed long timeout)
 EXPORT_SYMBOL(schedule_timeout_uninterruptible);
 
 #ifdef CONFIG_HOTPLUG_CPU
-static void migrate_timer_list(struct tvec_base *new_base, struct list_head *head)
+static void migrate_timer_list(struct tvec_base *new_base, struct hlist_head *head)
 {
 	struct timer_list *timer;
+	int cpu = new_base->cpu;
 
-	while (!list_empty(head)) {
-		timer = list_first_entry(head, struct timer_list, entry);
+	while (!hlist_empty(head)) {
+		timer = hlist_entry(head->first, struct timer_list, entry);
 		/* We ignore the accounting on the dying cpu */
 		detach_timer(timer, false);
-		timer_set_base(timer, new_base);
+		timer->flags = (timer->flags & ~TIMER_BASEMASK) | cpu;
 		internal_add_timer(new_base, timer);
 	}
 }
@@ -1565,8 +1565,8 @@ static void migrate_timers(int cpu)
 	int i;
 
 	BUG_ON(cpu_online(cpu));
-	old_base = per_cpu(tvec_bases, cpu);
-	new_base = get_cpu_var(tvec_bases);
+	old_base = per_cpu_ptr(&tvec_bases, cpu);
+	new_base = this_cpu_ptr(&tvec_bases);
 	/*
 	 * The caller is globally serialized and nobody else
 	 * takes two locks at once, deadlock is not possible.
@@ -1590,7 +1590,6 @@ static void migrate_timers(int cpu)
 
 	spin_unlock(&old_base->lock);
 	spin_unlock_irq(&new_base->lock);
-	put_cpu_var(tvec_bases);
 }
 
 static int timer_cpu_notify(struct notifier_block *self,
@@ -1616,52 +1615,27 @@ static inline void timer_register_cpu_notifier(void)
 static inline void timer_register_cpu_notifier(void) { }
 #endif /* CONFIG_HOTPLUG_CPU */
 
-static void __init init_timer_cpu(struct tvec_base *base, int cpu)
+static void __init init_timer_cpu(int cpu)
 {
-	int j;
-
-	BUG_ON(base != tbase_get_base(base));
+	struct tvec_base *base = per_cpu_ptr(&tvec_bases, cpu);
 
 	base->cpu = cpu;
-	per_cpu(tvec_bases, cpu) = base;
 	spin_lock_init(&base->lock);
 
-	for (j = 0; j < TVN_SIZE; j++) {
-		INIT_LIST_HEAD(base->tv5.vec + j);
-		INIT_LIST_HEAD(base->tv4.vec + j);
-		INIT_LIST_HEAD(base->tv3.vec + j);
-		INIT_LIST_HEAD(base->tv2.vec + j);
-	}
-	for (j = 0; j < TVR_SIZE; j++)
-		INIT_LIST_HEAD(base->tv1.vec + j);
-
 	base->timer_jiffies = jiffies;
 	base->next_timer = base->timer_jiffies;
 }
 
 static void __init init_timer_cpus(void)
 {
-	struct tvec_base *base;
-	int local_cpu = smp_processor_id();
 	int cpu;
 
-	for_each_possible_cpu(cpu) {
-		if (cpu == local_cpu)
-			base = &boot_tvec_bases;
-#ifdef CONFIG_SMP
-		else
-			base = per_cpu_ptr(&__tvec_bases, cpu);
-#endif
-
-		init_timer_cpu(base, cpu);
-	}
+	for_each_possible_cpu(cpu)
+		init_timer_cpu(cpu);
 }
 
 void __init init_timers(void)
 {
-	/* ensure there are enough low bits for flags in timer->base pointer */
-	BUILD_BUG_ON(__alignof__(struct tvec_base) & TIMER_FLAG_MASK);
-
 	init_timer_cpus();
 	init_timer_stats();
 	timer_register_cpu_notifier();
@@ -1697,14 +1671,14 @@ unsigned long msleep_interruptible(unsigned int msecs)
 
 EXPORT_SYMBOL(msleep_interruptible);
 
-static int __sched do_usleep_range(unsigned long min, unsigned long max)
+static void __sched do_usleep_range(unsigned long min, unsigned long max)
 {
 	ktime_t kmin;
 	unsigned long delta;
 
 	kmin = ktime_set(0, min * NSEC_PER_USEC);
 	delta = (max - min) * NSEC_PER_USEC;
-	return schedule_hrtimeout_range(&kmin, delta, HRTIMER_MODE_REL);
+	schedule_hrtimeout_range(&kmin, delta, HRTIMER_MODE_REL);
 }
 
 /**
@@ -1712,7 +1686,7 @@ static int __sched do_usleep_range(unsigned long min, unsigned long max)
  * @min: Minimum time in usecs to sleep
  * @max: Maximum time in usecs to sleep
  */
-void usleep_range(unsigned long min, unsigned long max)
+void __sched usleep_range(unsigned long min, unsigned long max)
 {
 	__set_current_state(TASK_UNINTERRUPTIBLE);
 	do_usleep_range(min, max);
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index e878c2e0ba45..a4536e1e3e2a 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -29,19 +29,24 @@ struct timer_list_iter {
 
 typedef void (*print_fn_t)(struct seq_file *m, unsigned int *classes);
 
-DECLARE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases);
-
 /*
  * This allows printing both to /proc/timer_list and
  * to the console (on SysRq-Q):
  */
-#define SEQ_printf(m, x...)			\
- do {						\
-	if (m)					\
-		seq_printf(m, x);		\
-	else					\
-		printk(x);			\
- } while (0)
+__printf(2, 3)
+static void SEQ_printf(struct seq_file *m, const char *fmt, ...)
+{
+	va_list args;
+
+	va_start(args, fmt);
+
+	if (m)
+		seq_vprintf(m, fmt, args);
+	else
+		vprintk(fmt, args);
+
+	va_end(args);
+}
 
 static void print_name_offset(struct seq_file *m, void *sym)
 {
@@ -120,10 +125,10 @@ static void
 print_base(struct seq_file *m, struct hrtimer_clock_base *base, u64 now)
 {
 	SEQ_printf(m, "  .base:       %pK\n", base);
-	SEQ_printf(m, "  .index:      %d\n",
-			base->index);
-	SEQ_printf(m, "  .resolution: %Lu nsecs\n",
-			(unsigned long long)ktime_to_ns(base->resolution));
+	SEQ_printf(m, "  .index:      %d\n", base->index);
+
+	SEQ_printf(m, "  .resolution: %u nsecs\n", (unsigned) hrtimer_resolution);
+
 	SEQ_printf(m,   "  .get_time:   ");
 	print_name_offset(m, base->get_time);
 	SEQ_printf(m,   "\n");
@@ -158,7 +163,7 @@ static void print_cpu(struct seq_file *m, int cpu, u64 now)
 	P(nr_events);
 	P(nr_retries);
 	P(nr_hangs);
-	P_ns(max_hang_time);
+	P(max_hang_time);
 #endif
 #undef P
 #undef P_ns
@@ -184,7 +189,7 @@ static void print_cpu(struct seq_file *m, int cpu, u64 now)
 		P_ns(idle_sleeptime);
 		P_ns(iowait_sleeptime);
 		P(last_jiffies);
-		P(next_jiffies);
+		P(next_timer);
 		P_ns(idle_expires);
 		SEQ_printf(m, "jiffies: %Lu\n",
 			   (unsigned long long)jiffies);
@@ -251,6 +256,12 @@ print_tickdevice(struct seq_file *m, struct tick_device *td, int cpu)
 			SEQ_printf(m, "\n");
 		}
 
+		if (dev->set_state_oneshot_stopped) {
+			SEQ_printf(m, " oneshot stopped: ");
+			print_name_offset(m, dev->set_state_oneshot_stopped);
+			SEQ_printf(m, "\n");
+		}
+
 		if (dev->tick_resume) {
 			SEQ_printf(m, " resume:   ");
 			print_name_offset(m, dev->tick_resume);
@@ -269,11 +280,11 @@ static void timer_list_show_tickdevices_header(struct seq_file *m)
 {
 #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
 	print_tickdevice(m, tick_get_broadcast_device(), -1);
-	SEQ_printf(m, "tick_broadcast_mask: %08lx\n",
-		   cpumask_bits(tick_get_broadcast_mask())[0]);
+	SEQ_printf(m, "tick_broadcast_mask: %*pb\n",
+		   cpumask_pr_args(tick_get_broadcast_mask()));
 #ifdef CONFIG_TICK_ONESHOT
-	SEQ_printf(m, "tick_broadcast_oneshot_mask: %08lx\n",
-		   cpumask_bits(tick_get_broadcast_oneshot_mask())[0]);
+	SEQ_printf(m, "tick_broadcast_oneshot_mask: %*pb\n",
+		   cpumask_pr_args(tick_get_broadcast_oneshot_mask()));
 #endif
 	SEQ_printf(m, "\n");
 #endif
@@ -282,7 +293,7 @@ static void timer_list_show_tickdevices_header(struct seq_file *m)
 
 static inline void timer_list_header(struct seq_file *m, u64 now)
 {
-	SEQ_printf(m, "Timer List Version: v0.7\n");
+	SEQ_printf(m, "Timer List Version: v0.8\n");
 	SEQ_printf(m, "HRTIMER_MAX_CLOCK_BASES: %d\n", HRTIMER_MAX_CLOCK_BASES);
 	SEQ_printf(m, "now at %Ld nsecs\n", (unsigned long long)now);
 	SEQ_printf(m, "\n");
diff --git a/kernel/time/timer_stats.c b/kernel/time/timer_stats.c
index 1fb08f21302e..1adecb4b87c8 100644
--- a/kernel/time/timer_stats.c
+++ b/kernel/time/timer_stats.c
@@ -68,7 +68,7 @@ struct entry {
 	 * Number of timeout events:
 	 */
 	unsigned long		count;
-	unsigned int		timer_flag;
+	u32			flags;
 
 	/*
 	 * We save the command-line string to preserve
@@ -227,13 +227,13 @@ static struct entry *tstat_lookup(struct entry *entry, char *comm)
  * @startf:	pointer to the function which did the timer setup
  * @timerf:	pointer to the timer callback function of the timer
  * @comm:	name of the process which set up the timer
+ * @tflags:	The flags field of the timer
  *
  * When the timer is already registered, then the event counter is
  * incremented. Otherwise the timer is registered in a free slot.
  */
 void timer_stats_update_stats(void *timer, pid_t pid, void *startf,
-			      void *timerf, char *comm,
-			      unsigned int timer_flag)
+			      void *timerf, char *comm, u32 tflags)
 {
 	/*
 	 * It doesn't matter which lock we take:
@@ -251,7 +251,7 @@ void timer_stats_update_stats(void *timer, pid_t pid, void *startf,
 	input.start_func = startf;
 	input.expire_func = timerf;
 	input.pid = pid;
-	input.timer_flag = timer_flag;
+	input.flags = tflags;
 
 	raw_spin_lock_irqsave(lock, flags);
 	if (!timer_stats_active)
@@ -306,7 +306,7 @@ static int tstats_show(struct seq_file *m, void *v)
 
 	for (i = 0; i < nr_entries; i++) {
 		entry = entries + i;
-		if (entry->timer_flag & TIMER_STATS_FLAG_DEFERRABLE) {
+		if (entry->flags & TIMER_DEFERRABLE) {
 			seq_printf(m, "%4luD, %5d %-16s ",
 				entry->count, entry->pid, entry->comm);
 		} else {
diff --git a/kernel/torture.c b/kernel/torture.c
index dd70993c266c..3e4840633d3e 100644
--- a/kernel/torture.c
+++ b/kernel/torture.c
@@ -409,7 +409,7 @@ static void (*torture_shutdown_hook)(void);
  */
 void torture_shutdown_absorb(const char *title)
 {
-	while (ACCESS_ONCE(fullstop) == FULLSTOP_SHUTDOWN) {
+	while (READ_ONCE(fullstop) == FULLSTOP_SHUTDOWN) {
 		pr_notice("torture thread %s parking due to system shutdown\n",
 			  title);
 		schedule_timeout_uninterruptible(MAX_SCHEDULE_TIMEOUT);
@@ -480,9 +480,9 @@ static int torture_shutdown_notify(struct notifier_block *unused1,
 				   unsigned long unused2, void *unused3)
 {
 	mutex_lock(&fullstop_mutex);
-	if (ACCESS_ONCE(fullstop) == FULLSTOP_DONTSTOP) {
+	if (READ_ONCE(fullstop) == FULLSTOP_DONTSTOP) {
 		VERBOSE_TOROUT_STRING("Unscheduled system shutdown detected");
-		ACCESS_ONCE(fullstop) = FULLSTOP_SHUTDOWN;
+		WRITE_ONCE(fullstop, FULLSTOP_SHUTDOWN);
 	} else {
 		pr_warn("Concurrent rmmod and shutdown illegal!\n");
 	}
@@ -523,13 +523,13 @@ static int stutter;
  */
 void stutter_wait(const char *title)
 {
-	while (ACCESS_ONCE(stutter_pause_test) ||
-	       (torture_runnable && !ACCESS_ONCE(*torture_runnable))) {
+	while (READ_ONCE(stutter_pause_test) ||
+	       (torture_runnable && !READ_ONCE(*torture_runnable))) {
 		if (stutter_pause_test)
-			if (ACCESS_ONCE(stutter_pause_test) == 1)
+			if (READ_ONCE(stutter_pause_test) == 1)
 				schedule_timeout_interruptible(1);
 			else
-				while (ACCESS_ONCE(stutter_pause_test))
+				while (READ_ONCE(stutter_pause_test))
 					cond_resched();
 		else
 			schedule_timeout_interruptible(round_jiffies_relative(HZ));
@@ -549,14 +549,14 @@ static int torture_stutter(void *arg)
 		if (!torture_must_stop()) {
 			if (stutter > 1) {
 				schedule_timeout_interruptible(stutter - 1);
-				ACCESS_ONCE(stutter_pause_test) = 2;
+				WRITE_ONCE(stutter_pause_test, 2);
 			}
 			schedule_timeout_interruptible(1);
-			ACCESS_ONCE(stutter_pause_test) = 1;
+			WRITE_ONCE(stutter_pause_test, 1);
 		}
 		if (!torture_must_stop())
 			schedule_timeout_interruptible(stutter);
-		ACCESS_ONCE(stutter_pause_test) = 0;
+		WRITE_ONCE(stutter_pause_test, 0);
 		torture_shutdown_absorb("torture_stutter");
 	} while (!torture_must_stop());
 	torture_kthread_stopping("torture_stutter");
@@ -642,13 +642,13 @@ EXPORT_SYMBOL_GPL(torture_init_end);
 bool torture_cleanup_begin(void)
 {
 	mutex_lock(&fullstop_mutex);
-	if (ACCESS_ONCE(fullstop) == FULLSTOP_SHUTDOWN) {
+	if (READ_ONCE(fullstop) == FULLSTOP_SHUTDOWN) {
 		pr_warn("Concurrent rmmod and shutdown illegal!\n");
 		mutex_unlock(&fullstop_mutex);
 		schedule_timeout_uninterruptible(10);
 		return true;
 	}
-	ACCESS_ONCE(fullstop) = FULLSTOP_RMMOD;
+	WRITE_ONCE(fullstop, FULLSTOP_RMMOD);
 	mutex_unlock(&fullstop_mutex);
 	torture_shutdown_cleanup();
 	torture_shuffle_cleanup();
@@ -681,7 +681,7 @@ EXPORT_SYMBOL_GPL(torture_must_stop);
  */
 bool torture_must_stop_irq(void)
 {
-	return ACCESS_ONCE(fullstop) != FULLSTOP_DONTSTOP;
+	return READ_ONCE(fullstop) != FULLSTOP_DONTSTOP;
 }
 EXPORT_SYMBOL_GPL(torture_must_stop_irq);
 
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index ced69da0ff55..7f2e97ce71a7 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -1369,19 +1369,26 @@ static int check_preds(struct filter_parse_state *ps)
 {
 	int n_normal_preds = 0, n_logical_preds = 0;
 	struct postfix_elt *elt;
+	int cnt = 0;
 
 	list_for_each_entry(elt, &ps->postfix, list) {
-		if (elt->op == OP_NONE)
+		if (elt->op == OP_NONE) {
+			cnt++;
 			continue;
+		}
 
 		if (elt->op == OP_AND || elt->op == OP_OR) {
 			n_logical_preds++;
+			cnt--;
 			continue;
 		}
+		if (elt->op != OP_NOT)
+			cnt--;
 		n_normal_preds++;
+		WARN_ON_ONCE(cnt < 0);
 	}
 
-	if (!n_normal_preds || n_logical_preds >= n_normal_preds) {
+	if (cnt != 1 || !n_normal_preds || n_logical_preds >= n_normal_preds) {
 		parse_error(ps, FILT_ERR_INVALID_FILTER, 0);
 		return -EINVAL;
 	}
diff --git a/lib/842/842.h b/lib/842/842.h
new file mode 100644
index 000000000000..7c200030acf7
--- /dev/null
+++ b/lib/842/842.h
@@ -0,0 +1,127 @@
+
+#ifndef __842_H__
+#define __842_H__
+
+/* The 842 compressed format is made up of multiple blocks, each of
+ * which have the format:
+ *
+ * <template>[arg1][arg2][arg3][arg4]
+ *
+ * where there are between 0 and 4 template args, depending on the specific
+ * template operation.  For normal operations, each arg is either a specific
+ * number of data bytes to add to the output buffer, or an index pointing
+ * to a previously-written number of data bytes to copy to the output buffer.
+ *
+ * The template code is a 5-bit value.  This code indicates what to do with
+ * the following data.  Template codes from 0 to 0x19 should use the template
+ * table, the static "decomp_ops" table used in decompress.  For each template
+ * (table row), there are between 1 and 4 actions; each action corresponds to
+ * an arg following the template code bits.  Each action is either a "data"
+ * type action, or a "index" type action, and each action results in 2, 4, or 8
+ * bytes being written to the output buffer.  Each template (i.e. all actions
+ * in the table row) will add up to 8 bytes being written to the output buffer.
+ * Any row with less than 4 actions is padded with noop actions, indicated by
+ * N0 (for which there is no corresponding arg in the compressed data buffer).
+ *
+ * "Data" actions, indicated in the table by D2, D4, and D8, mean that the
+ * corresponding arg is 2, 4, or 8 bytes, respectively, in the compressed data
+ * buffer should be copied directly to the output buffer.
+ *
+ * "Index" actions, indicated in the table by I2, I4, and I8, mean the
+ * corresponding arg is an index parameter that points to, respectively, a 2,
+ * 4, or 8 byte value already in the output buffer, that should be copied to
+ * the end of the output buffer.  Essentially, the index points to a position
+ * in a ring buffer that contains the last N bytes of output buffer data.
+ * The number of bits for each index's arg are: 8 bits for I2, 9 bits for I4,
+ * and 8 bits for I8.  Since each index points to a 2, 4, or 8 byte section,
+ * this means that I2 can reference 512 bytes ((2^8 bits = 256) * 2 bytes), I4
+ * can reference 2048 bytes ((2^9 = 512) * 4 bytes), and I8 can reference 2048
+ * bytes ((2^8 = 256) * 8 bytes).  Think of it as a kind-of ring buffer for
+ * each of I2, I4, and I8 that are updated for each byte written to the output
+ * buffer.  In this implementation, the output buffer is directly used for each
+ * index; there is no additional memory required.  Note that the index is into
+ * a ring buffer, not a sliding window; for example, if there have been 260
+ * bytes written to the output buffer, an I2 index of 0 would index to byte 256
+ * in the output buffer, while an I2 index of 16 would index to byte 16 in the
+ * output buffer.
+ *
+ * There are also 3 special template codes; 0x1b for "repeat", 0x1c for
+ * "zeros", and 0x1e for "end".  The "repeat" operation is followed by a 6 bit
+ * arg N indicating how many times to repeat.  The last 8 bytes written to the
+ * output buffer are written again to the output buffer, N + 1 times.  The
+ * "zeros" operation, which has no arg bits, writes 8 zeros to the output
+ * buffer.  The "end" operation, which also has no arg bits, signals the end
+ * of the compressed data.  There may be some number of padding (don't care,
+ * but usually 0) bits after the "end" operation bits, to fill the buffer
+ * length to a specific byte multiple (usually a multiple of 8, 16, or 32
+ * bytes).
+ *
+ * This software implementation also uses one of the undefined template values,
+ * 0x1d as a special "short data" template code, to represent less than 8 bytes
+ * of uncompressed data.  It is followed by a 3 bit arg N indicating how many
+ * data bytes will follow, and then N bytes of data, which should be copied to
+ * the output buffer.  This allows the software 842 compressor to accept input
+ * buffers that are not an exact multiple of 8 bytes long.  However, those
+ * compressed buffers containing this sw-only template will be rejected by
+ * the 842 hardware decompressor, and must be decompressed with this software
+ * library.  The 842 software compression module includes a parameter to
+ * disable using this sw-only "short data" template, and instead simply
+ * reject any input buffer that is not a multiple of 8 bytes long.
+ *
+ * After all actions for each operation code are processed, another template
+ * code is in the next 5 bits.  The decompression ends once the "end" template
+ * code is detected.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/bitops.h>
+#include <asm/unaligned.h>
+
+#include <linux/sw842.h>
+
+/* special templates */
+#define OP_REPEAT	(0x1B)
+#define OP_ZEROS	(0x1C)
+#define OP_END		(0x1E)
+
+/* sw only template - this is not in the hw design; it's used only by this
+ * software compressor and decompressor, to allow input buffers that aren't
+ * a multiple of 8.
+ */
+#define OP_SHORT_DATA	(0x1D)
+
+/* additional bits of each op param */
+#define OP_BITS		(5)
+#define REPEAT_BITS	(6)
+#define SHORT_DATA_BITS	(3)
+#define I2_BITS		(8)
+#define I4_BITS		(9)
+#define I8_BITS		(8)
+
+#define REPEAT_BITS_MAX		(0x3f)
+#define SHORT_DATA_BITS_MAX	(0x7)
+
+/* Arbitrary values used to indicate action */
+#define OP_ACTION	(0x70)
+#define OP_ACTION_INDEX	(0x10)
+#define OP_ACTION_DATA	(0x20)
+#define OP_ACTION_NOOP	(0x40)
+#define OP_AMOUNT	(0x0f)
+#define OP_AMOUNT_0	(0x00)
+#define OP_AMOUNT_2	(0x02)
+#define OP_AMOUNT_4	(0x04)
+#define OP_AMOUNT_8	(0x08)
+
+#define D2		(OP_ACTION_DATA  | OP_AMOUNT_2)
+#define D4		(OP_ACTION_DATA  | OP_AMOUNT_4)
+#define D8		(OP_ACTION_DATA  | OP_AMOUNT_8)
+#define I2		(OP_ACTION_INDEX | OP_AMOUNT_2)
+#define I4		(OP_ACTION_INDEX | OP_AMOUNT_4)
+#define I8		(OP_ACTION_INDEX | OP_AMOUNT_8)
+#define N0		(OP_ACTION_NOOP  | OP_AMOUNT_0)
+
+/* the max of the regular templates - not including the special templates */
+#define OPS_MAX		(0x1a)
+
+#endif
diff --git a/lib/842/842_compress.c b/lib/842/842_compress.c
new file mode 100644
index 000000000000..7ce68948e68c
--- /dev/null
+++ b/lib/842/842_compress.c
@@ -0,0 +1,626 @@
+/*
+ * 842 Software Compression
+ *
+ * Copyright (C) 2015 Dan Streetman, IBM Corp
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * See 842.h for details of the 842 compressed format.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#define MODULE_NAME "842_compress"
+
+#include <linux/hashtable.h>
+
+#include "842.h"
+#include "842_debugfs.h"
+
+#define SW842_HASHTABLE8_BITS	(10)
+#define SW842_HASHTABLE4_BITS	(11)
+#define SW842_HASHTABLE2_BITS	(10)
+
+/* By default, we allow compressing input buffers of any length, but we must
+ * use the non-standard "short data" template so the decompressor can correctly
+ * reproduce the uncompressed data buffer at the right length.  However the
+ * hardware 842 compressor will not recognize the "short data" template, and
+ * will fail to decompress any compressed buffer containing it (I have no idea
+ * why anyone would want to use software to compress and hardware to decompress
+ * but that's beside the point).  This parameter forces the compression
+ * function to simply reject any input buffer that isn't a multiple of 8 bytes
+ * long, instead of using the "short data" template, so that all compressed
+ * buffers produced by this function will be decompressable by the 842 hardware
+ * decompressor.  Unless you have a specific need for that, leave this disabled
+ * so that any length buffer can be compressed.
+ */
+static bool sw842_strict;
+module_param_named(strict, sw842_strict, bool, 0644);
+
+static u8 comp_ops[OPS_MAX][5] = { /* params size in bits */
+	{ I8, N0, N0, N0, 0x19 }, /* 8 */
+	{ I4, I4, N0, N0, 0x18 }, /* 18 */
+	{ I4, I2, I2, N0, 0x17 }, /* 25 */
+	{ I2, I2, I4, N0, 0x13 }, /* 25 */
+	{ I2, I2, I2, I2, 0x12 }, /* 32 */
+	{ I4, I2, D2, N0, 0x16 }, /* 33 */
+	{ I4, D2, I2, N0, 0x15 }, /* 33 */
+	{ I2, D2, I4, N0, 0x0e }, /* 33 */
+	{ D2, I2, I4, N0, 0x09 }, /* 33 */
+	{ I2, I2, I2, D2, 0x11 }, /* 40 */
+	{ I2, I2, D2, I2, 0x10 }, /* 40 */
+	{ I2, D2, I2, I2, 0x0d }, /* 40 */
+	{ D2, I2, I2, I2, 0x08 }, /* 40 */
+	{ I4, D4, N0, N0, 0x14 }, /* 41 */
+	{ D4, I4, N0, N0, 0x04 }, /* 41 */
+	{ I2, I2, D4, N0, 0x0f }, /* 48 */
+	{ I2, D2, I2, D2, 0x0c }, /* 48 */
+	{ I2, D4, I2, N0, 0x0b }, /* 48 */
+	{ D2, I2, I2, D2, 0x07 }, /* 48 */
+	{ D2, I2, D2, I2, 0x06 }, /* 48 */
+	{ D4, I2, I2, N0, 0x03 }, /* 48 */
+	{ I2, D2, D4, N0, 0x0a }, /* 56 */
+	{ D2, I2, D4, N0, 0x05 }, /* 56 */
+	{ D4, I2, D2, N0, 0x02 }, /* 56 */
+	{ D4, D2, I2, N0, 0x01 }, /* 56 */
+	{ D8, N0, N0, N0, 0x00 }, /* 64 */
+};
+
+struct sw842_hlist_node8 {
+	struct hlist_node node;
+	u64 data;
+	u8 index;
+};
+
+struct sw842_hlist_node4 {
+	struct hlist_node node;
+	u32 data;
+	u16 index;
+};
+
+struct sw842_hlist_node2 {
+	struct hlist_node node;
+	u16 data;
+	u8 index;
+};
+
+#define INDEX_NOT_FOUND		(-1)
+#define INDEX_NOT_CHECKED	(-2)
+
+struct sw842_param {
+	u8 *in;
+	u8 *instart;
+	u64 ilen;
+	u8 *out;
+	u64 olen;
+	u8 bit;
+	u64 data8[1];
+	u32 data4[2];
+	u16 data2[4];
+	int index8[1];
+	int index4[2];
+	int index2[4];
+	DECLARE_HASHTABLE(htable8, SW842_HASHTABLE8_BITS);
+	DECLARE_HASHTABLE(htable4, SW842_HASHTABLE4_BITS);
+	DECLARE_HASHTABLE(htable2, SW842_HASHTABLE2_BITS);
+	struct sw842_hlist_node8 node8[1 << I8_BITS];
+	struct sw842_hlist_node4 node4[1 << I4_BITS];
+	struct sw842_hlist_node2 node2[1 << I2_BITS];
+};
+
+#define get_input_data(p, o, b)						\
+	be##b##_to_cpu(get_unaligned((__be##b *)((p)->in + (o))))
+
+#define init_hashtable_nodes(p, b)	do {			\
+	int _i;							\
+	hash_init((p)->htable##b);				\
+	for (_i = 0; _i < ARRAY_SIZE((p)->node##b); _i++) {	\
+		(p)->node##b[_i].index = _i;			\
+		(p)->node##b[_i].data = 0;			\
+		INIT_HLIST_NODE(&(p)->node##b[_i].node);	\
+	}							\
+} while (0)
+
+#define find_index(p, b, n)	({					\
+	struct sw842_hlist_node##b *_n;					\
+	p->index##b[n] = INDEX_NOT_FOUND;				\
+	hash_for_each_possible(p->htable##b, _n, node, p->data##b[n]) {	\
+		if (p->data##b[n] == _n->data) {			\
+			p->index##b[n] = _n->index;			\
+			break;						\
+		}							\
+	}								\
+	p->index##b[n] >= 0;						\
+})
+
+#define check_index(p, b, n)			\
+	((p)->index##b[n] == INDEX_NOT_CHECKED	\
+	 ? find_index(p, b, n)			\
+	 : (p)->index##b[n] >= 0)
+
+#define replace_hash(p, b, i, d)	do {				\
+	struct sw842_hlist_node##b *_n = &(p)->node##b[(i)+(d)];	\
+	hash_del(&_n->node);						\
+	_n->data = (p)->data##b[d];					\
+	pr_debug("add hash index%x %x pos %x data %lx\n", b,		\
+		 (unsigned int)_n->index,				\
+		 (unsigned int)((p)->in - (p)->instart),		\
+		 (unsigned long)_n->data);				\
+	hash_add((p)->htable##b, &_n->node, _n->data);			\
+} while (0)
+
+static u8 bmask[8] = { 0x00, 0x80, 0xc0, 0xe0, 0xf0, 0xf8, 0xfc, 0xfe };
+
+static int add_bits(struct sw842_param *p, u64 d, u8 n);
+
+static int __split_add_bits(struct sw842_param *p, u64 d, u8 n, u8 s)
+{
+	int ret;
+
+	if (n <= s)
+		return -EINVAL;
+
+	ret = add_bits(p, d >> s, n - s);
+	if (ret)
+		return ret;
+	return add_bits(p, d & GENMASK_ULL(s - 1, 0), s);
+}
+
+static int add_bits(struct sw842_param *p, u64 d, u8 n)
+{
+	int b = p->bit, bits = b + n, s = round_up(bits, 8) - bits;
+	u64 o;
+	u8 *out = p->out;
+
+	pr_debug("add %u bits %lx\n", (unsigned char)n, (unsigned long)d);
+
+	if (n > 64)
+		return -EINVAL;
+
+	/* split this up if writing to > 8 bytes (i.e. n == 64 && p->bit > 0),
+	 * or if we're at the end of the output buffer and would write past end
+	 */
+	if (bits > 64)
+		return __split_add_bits(p, d, n, 32);
+	else if (p->olen < 8 && bits > 32 && bits <= 56)
+		return __split_add_bits(p, d, n, 16);
+	else if (p->olen < 4 && bits > 16 && bits <= 24)
+		return __split_add_bits(p, d, n, 8);
+
+	if (DIV_ROUND_UP(bits, 8) > p->olen)
+		return -ENOSPC;
+
+	o = *out & bmask[b];
+	d <<= s;
+
+	if (bits <= 8)
+		*out = o | d;
+	else if (bits <= 16)
+		put_unaligned(cpu_to_be16(o << 8 | d), (__be16 *)out);
+	else if (bits <= 24)
+		put_unaligned(cpu_to_be32(o << 24 | d << 8), (__be32 *)out);
+	else if (bits <= 32)
+		put_unaligned(cpu_to_be32(o << 24 | d), (__be32 *)out);
+	else if (bits <= 40)
+		put_unaligned(cpu_to_be64(o << 56 | d << 24), (__be64 *)out);
+	else if (bits <= 48)
+		put_unaligned(cpu_to_be64(o << 56 | d << 16), (__be64 *)out);
+	else if (bits <= 56)
+		put_unaligned(cpu_to_be64(o << 56 | d << 8), (__be64 *)out);
+	else
+		put_unaligned(cpu_to_be64(o << 56 | d), (__be64 *)out);
+
+	p->bit += n;
+
+	if (p->bit > 7) {
+		p->out += p->bit / 8;
+		p->olen -= p->bit / 8;
+		p->bit %= 8;
+	}
+
+	return 0;
+}
+
+static int add_template(struct sw842_param *p, u8 c)
+{
+	int ret, i, b = 0;
+	u8 *t = comp_ops[c];
+	bool inv = false;
+
+	if (c >= OPS_MAX)
+		return -EINVAL;
+
+	pr_debug("template %x\n", t[4]);
+
+	ret = add_bits(p, t[4], OP_BITS);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < 4; i++) {
+		pr_debug("op %x\n", t[i]);
+
+		switch (t[i] & OP_AMOUNT) {
+		case OP_AMOUNT_8:
+			if (b)
+				inv = true;
+			else if (t[i] & OP_ACTION_INDEX)
+				ret = add_bits(p, p->index8[0], I8_BITS);
+			else if (t[i] & OP_ACTION_DATA)
+				ret = add_bits(p, p->data8[0], 64);
+			else
+				inv = true;
+			break;
+		case OP_AMOUNT_4:
+			if (b == 2 && t[i] & OP_ACTION_DATA)
+				ret = add_bits(p, get_input_data(p, 2, 32), 32);
+			else if (b != 0 && b != 4)
+				inv = true;
+			else if (t[i] & OP_ACTION_INDEX)
+				ret = add_bits(p, p->index4[b >> 2], I4_BITS);
+			else if (t[i] & OP_ACTION_DATA)
+				ret = add_bits(p, p->data4[b >> 2], 32);
+			else
+				inv = true;
+			break;
+		case OP_AMOUNT_2:
+			if (b != 0 && b != 2 && b != 4 && b != 6)
+				inv = true;
+			if (t[i] & OP_ACTION_INDEX)
+				ret = add_bits(p, p->index2[b >> 1], I2_BITS);
+			else if (t[i] & OP_ACTION_DATA)
+				ret = add_bits(p, p->data2[b >> 1], 16);
+			else
+				inv = true;
+			break;
+		case OP_AMOUNT_0:
+			inv = (b != 8) || !(t[i] & OP_ACTION_NOOP);
+			break;
+		default:
+			inv = true;
+			break;
+		}
+
+		if (ret)
+			return ret;
+
+		if (inv) {
+			pr_err("Invalid templ %x op %d : %x %x %x %x\n",
+			       c, i, t[0], t[1], t[2], t[3]);
+			return -EINVAL;
+		}
+
+		b += t[i] & OP_AMOUNT;
+	}
+
+	if (b != 8) {
+		pr_err("Invalid template %x len %x : %x %x %x %x\n",
+		       c, b, t[0], t[1], t[2], t[3]);
+		return -EINVAL;
+	}
+
+	if (sw842_template_counts)
+		atomic_inc(&template_count[t[4]]);
+
+	return 0;
+}
+
+static int add_repeat_template(struct sw842_param *p, u8 r)
+{
+	int ret;
+
+	/* repeat param is 0-based */
+	if (!r || --r > REPEAT_BITS_MAX)
+		return -EINVAL;
+
+	ret = add_bits(p, OP_REPEAT, OP_BITS);
+	if (ret)
+		return ret;
+
+	ret = add_bits(p, r, REPEAT_BITS);
+	if (ret)
+		return ret;
+
+	if (sw842_template_counts)
+		atomic_inc(&template_repeat_count);
+
+	return 0;
+}
+
+static int add_short_data_template(struct sw842_param *p, u8 b)
+{
+	int ret, i;
+
+	if (!b || b > SHORT_DATA_BITS_MAX)
+		return -EINVAL;
+
+	ret = add_bits(p, OP_SHORT_DATA, OP_BITS);
+	if (ret)
+		return ret;
+
+	ret = add_bits(p, b, SHORT_DATA_BITS);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < b; i++) {
+		ret = add_bits(p, p->in[i], 8);
+		if (ret)
+			return ret;
+	}
+
+	if (sw842_template_counts)
+		atomic_inc(&template_short_data_count);
+
+	return 0;
+}
+
+static int add_zeros_template(struct sw842_param *p)
+{
+	int ret = add_bits(p, OP_ZEROS, OP_BITS);
+
+	if (ret)
+		return ret;
+
+	if (sw842_template_counts)
+		atomic_inc(&template_zeros_count);
+
+	return 0;
+}
+
+static int add_end_template(struct sw842_param *p)
+{
+	int ret = add_bits(p, OP_END, OP_BITS);
+
+	if (ret)
+		return ret;
+
+	if (sw842_template_counts)
+		atomic_inc(&template_end_count);
+
+	return 0;
+}
+
+static bool check_template(struct sw842_param *p, u8 c)
+{
+	u8 *t = comp_ops[c];
+	int i, match, b = 0;
+
+	if (c >= OPS_MAX)
+		return false;
+
+	for (i = 0; i < 4; i++) {
+		if (t[i] & OP_ACTION_INDEX) {
+			if (t[i] & OP_AMOUNT_2)
+				match = check_index(p, 2, b >> 1);
+			else if (t[i] & OP_AMOUNT_4)
+				match = check_index(p, 4, b >> 2);
+			else if (t[i] & OP_AMOUNT_8)
+				match = check_index(p, 8, 0);
+			else
+				return false;
+			if (!match)
+				return false;
+		}
+
+		b += t[i] & OP_AMOUNT;
+	}
+
+	return true;
+}
+
+static void get_next_data(struct sw842_param *p)
+{
+	p->data8[0] = get_input_data(p, 0, 64);
+	p->data4[0] = get_input_data(p, 0, 32);
+	p->data4[1] = get_input_data(p, 4, 32);
+	p->data2[0] = get_input_data(p, 0, 16);
+	p->data2[1] = get_input_data(p, 2, 16);
+	p->data2[2] = get_input_data(p, 4, 16);
+	p->data2[3] = get_input_data(p, 6, 16);
+}
+
+/* update the hashtable entries.
+ * only call this after finding/adding the current template
+ * the dataN fields for the current 8 byte block must be already updated
+ */
+static void update_hashtables(struct sw842_param *p)
+{
+	u64 pos = p->in - p->instart;
+	u64 n8 = (pos >> 3) % (1 << I8_BITS);
+	u64 n4 = (pos >> 2) % (1 << I4_BITS);
+	u64 n2 = (pos >> 1) % (1 << I2_BITS);
+
+	replace_hash(p, 8, n8, 0);
+	replace_hash(p, 4, n4, 0);
+	replace_hash(p, 4, n4, 1);
+	replace_hash(p, 2, n2, 0);
+	replace_hash(p, 2, n2, 1);
+	replace_hash(p, 2, n2, 2);
+	replace_hash(p, 2, n2, 3);
+}
+
+/* find the next template to use, and add it
+ * the p->dataN fields must already be set for the current 8 byte block
+ */
+static int process_next(struct sw842_param *p)
+{
+	int ret, i;
+
+	p->index8[0] = INDEX_NOT_CHECKED;
+	p->index4[0] = INDEX_NOT_CHECKED;
+	p->index4[1] = INDEX_NOT_CHECKED;
+	p->index2[0] = INDEX_NOT_CHECKED;
+	p->index2[1] = INDEX_NOT_CHECKED;
+	p->index2[2] = INDEX_NOT_CHECKED;
+	p->index2[3] = INDEX_NOT_CHECKED;
+
+	/* check up to OPS_MAX - 1; last op is our fallback */
+	for (i = 0; i < OPS_MAX - 1; i++) {
+		if (check_template(p, i))
+			break;
+	}
+
+	ret = add_template(p, i);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+/**
+ * sw842_compress
+ *
+ * Compress the uncompressed buffer of length @ilen at @in to the output buffer
+ * @out, using no more than @olen bytes, using the 842 compression format.
+ *
+ * Returns: 0 on success, error on failure.  The @olen parameter
+ * will contain the number of output bytes written on success, or
+ * 0 on error.
+ */
+int sw842_compress(const u8 *in, unsigned int ilen,
+		   u8 *out, unsigned int *olen, void *wmem)
+{
+	struct sw842_param *p = (struct sw842_param *)wmem;
+	int ret;
+	u64 last, next, pad, total;
+	u8 repeat_count = 0;
+
+	BUILD_BUG_ON(sizeof(*p) > SW842_MEM_COMPRESS);
+
+	init_hashtable_nodes(p, 8);
+	init_hashtable_nodes(p, 4);
+	init_hashtable_nodes(p, 2);
+
+	p->in = (u8 *)in;
+	p->instart = p->in;
+	p->ilen = ilen;
+	p->out = out;
+	p->olen = *olen;
+	p->bit = 0;
+
+	total = p->olen;
+
+	*olen = 0;
+
+	/* if using strict mode, we can only compress a multiple of 8 */
+	if (sw842_strict && (ilen % 8)) {
+		pr_err("Using strict mode, can't compress len %d\n", ilen);
+		return -EINVAL;
+	}
+
+	/* let's compress at least 8 bytes, mkay? */
+	if (unlikely(ilen < 8))
+		goto skip_comp;
+
+	/* make initial 'last' different so we don't match the first time */
+	last = ~get_unaligned((u64 *)p->in);
+
+	while (p->ilen > 7) {
+		next = get_unaligned((u64 *)p->in);
+
+		/* must get the next data, as we need to update the hashtable
+		 * entries with the new data every time
+		 */
+		get_next_data(p);
+
+		/* we don't care about endianness in last or next;
+		 * we're just comparing 8 bytes to another 8 bytes,
+		 * they're both the same endianness
+		 */
+		if (next == last) {
+			/* repeat count bits are 0-based, so we stop at +1 */
+			if (++repeat_count <= REPEAT_BITS_MAX)
+				goto repeat;
+		}
+		if (repeat_count) {
+			ret = add_repeat_template(p, repeat_count);
+			repeat_count = 0;
+			if (next == last) /* reached max repeat bits */
+				goto repeat;
+		}
+
+		if (next == 0)
+			ret = add_zeros_template(p);
+		else
+			ret = process_next(p);
+
+		if (ret)
+			return ret;
+
+repeat:
+		last = next;
+		update_hashtables(p);
+		p->in += 8;
+		p->ilen -= 8;
+	}
+
+	if (repeat_count) {
+		ret = add_repeat_template(p, repeat_count);
+		if (ret)
+			return ret;
+	}
+
+skip_comp:
+	if (p->ilen > 0) {
+		ret = add_short_data_template(p, p->ilen);
+		if (ret)
+			return ret;
+
+		p->in += p->ilen;
+		p->ilen = 0;
+	}
+
+	ret = add_end_template(p);
+	if (ret)
+		return ret;
+
+	if (p->bit) {
+		p->out++;
+		p->olen--;
+		p->bit = 0;
+	}
+
+	/* pad compressed length to multiple of 8 */
+	pad = (8 - ((total - p->olen) % 8)) % 8;
+	if (pad) {
+		if (pad > p->olen) /* we were so close! */
+			return -ENOSPC;
+		memset(p->out, 0, pad);
+		p->out += pad;
+		p->olen -= pad;
+	}
+
+	if (unlikely((total - p->olen) > UINT_MAX))
+		return -ENOSPC;
+
+	*olen = total - p->olen;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(sw842_compress);
+
+static int __init sw842_init(void)
+{
+	if (sw842_template_counts)
+		sw842_debugfs_create();
+
+	return 0;
+}
+module_init(sw842_init);
+
+static void __exit sw842_exit(void)
+{
+	if (sw842_template_counts)
+		sw842_debugfs_remove();
+}
+module_exit(sw842_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Software 842 Compressor");
+MODULE_AUTHOR("Dan Streetman <ddstreet@ieee.org>");
diff --git a/lib/842/842_debugfs.h b/lib/842/842_debugfs.h
new file mode 100644
index 000000000000..e7f3bffaf255
--- /dev/null
+++ b/lib/842/842_debugfs.h
@@ -0,0 +1,52 @@
+
+#ifndef __842_DEBUGFS_H__
+#define __842_DEBUGFS_H__
+
+#include <linux/debugfs.h>
+
+static bool sw842_template_counts;
+module_param_named(template_counts, sw842_template_counts, bool, 0444);
+
+static atomic_t template_count[OPS_MAX], template_repeat_count,
+	template_zeros_count, template_short_data_count, template_end_count;
+
+static struct dentry *sw842_debugfs_root;
+
+static int __init sw842_debugfs_create(void)
+{
+	umode_t m = S_IRUGO | S_IWUSR;
+	int i;
+
+	if (!debugfs_initialized())
+		return -ENODEV;
+
+	sw842_debugfs_root = debugfs_create_dir(MODULE_NAME, NULL);
+	if (IS_ERR(sw842_debugfs_root))
+		return PTR_ERR(sw842_debugfs_root);
+
+	for (i = 0; i < ARRAY_SIZE(template_count); i++) {
+		char name[32];
+
+		snprintf(name, 32, "template_%02x", i);
+		debugfs_create_atomic_t(name, m, sw842_debugfs_root,
+					&template_count[i]);
+	}
+	debugfs_create_atomic_t("template_repeat", m, sw842_debugfs_root,
+				&template_repeat_count);
+	debugfs_create_atomic_t("template_zeros", m, sw842_debugfs_root,
+				&template_zeros_count);
+	debugfs_create_atomic_t("template_short_data", m, sw842_debugfs_root,
+				&template_short_data_count);
+	debugfs_create_atomic_t("template_end", m, sw842_debugfs_root,
+				&template_end_count);
+
+	return 0;
+}
+
+static void __exit sw842_debugfs_remove(void)
+{
+	if (sw842_debugfs_root && !IS_ERR(sw842_debugfs_root))
+		debugfs_remove_recursive(sw842_debugfs_root);
+}
+
+#endif
diff --git a/lib/842/842_decompress.c b/lib/842/842_decompress.c
new file mode 100644
index 000000000000..5446ff0c9ba0
--- /dev/null
+++ b/lib/842/842_decompress.c
@@ -0,0 +1,405 @@
+/*
+ * 842 Software Decompression
+ *
+ * Copyright (C) 2015 Dan Streetman, IBM Corp
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * See 842.h for details of the 842 compressed format.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#define MODULE_NAME "842_decompress"
+
+#include "842.h"
+#include "842_debugfs.h"
+
+/* rolling fifo sizes */
+#define I2_FIFO_SIZE	(2 * (1 << I2_BITS))
+#define I4_FIFO_SIZE	(4 * (1 << I4_BITS))
+#define I8_FIFO_SIZE	(8 * (1 << I8_BITS))
+
+static u8 decomp_ops[OPS_MAX][4] = {
+	{ D8, N0, N0, N0 },
+	{ D4, D2, I2, N0 },
+	{ D4, I2, D2, N0 },
+	{ D4, I2, I2, N0 },
+	{ D4, I4, N0, N0 },
+	{ D2, I2, D4, N0 },
+	{ D2, I2, D2, I2 },
+	{ D2, I2, I2, D2 },
+	{ D2, I2, I2, I2 },
+	{ D2, I2, I4, N0 },
+	{ I2, D2, D4, N0 },
+	{ I2, D4, I2, N0 },
+	{ I2, D2, I2, D2 },
+	{ I2, D2, I2, I2 },
+	{ I2, D2, I4, N0 },
+	{ I2, I2, D4, N0 },
+	{ I2, I2, D2, I2 },
+	{ I2, I2, I2, D2 },
+	{ I2, I2, I2, I2 },
+	{ I2, I2, I4, N0 },
+	{ I4, D4, N0, N0 },
+	{ I4, D2, I2, N0 },
+	{ I4, I2, D2, N0 },
+	{ I4, I2, I2, N0 },
+	{ I4, I4, N0, N0 },
+	{ I8, N0, N0, N0 }
+};
+
+struct sw842_param {
+	u8 *in;
+	u8 bit;
+	u64 ilen;
+	u8 *out;
+	u8 *ostart;
+	u64 olen;
+};
+
+#define beN_to_cpu(d, s)					\
+	((s) == 2 ? be16_to_cpu(get_unaligned((__be16 *)d)) :	\
+	 (s) == 4 ? be32_to_cpu(get_unaligned((__be32 *)d)) :	\
+	 (s) == 8 ? be64_to_cpu(get_unaligned((__be64 *)d)) :	\
+	 WARN(1, "pr_debug param err invalid size %x\n", s))
+
+static int next_bits(struct sw842_param *p, u64 *d, u8 n);
+
+static int __split_next_bits(struct sw842_param *p, u64 *d, u8 n, u8 s)
+{
+	u64 tmp = 0;
+	int ret;
+
+	if (n <= s) {
+		pr_debug("split_next_bits invalid n %u s %u\n", n, s);
+		return -EINVAL;
+	}
+
+	ret = next_bits(p, &tmp, n - s);
+	if (ret)
+		return ret;
+	ret = next_bits(p, d, s);
+	if (ret)
+		return ret;
+	*d |= tmp << s;
+	return 0;
+}
+
+static int next_bits(struct sw842_param *p, u64 *d, u8 n)
+{
+	u8 *in = p->in, b = p->bit, bits = b + n;
+
+	if (n > 64) {
+		pr_debug("next_bits invalid n %u\n", n);
+		return -EINVAL;
+	}
+
+	/* split this up if reading > 8 bytes, or if we're at the end of
+	 * the input buffer and would read past the end
+	 */
+	if (bits > 64)
+		return __split_next_bits(p, d, n, 32);
+	else if (p->ilen < 8 && bits > 32 && bits <= 56)
+		return __split_next_bits(p, d, n, 16);
+	else if (p->ilen < 4 && bits > 16 && bits <= 24)
+		return __split_next_bits(p, d, n, 8);
+
+	if (DIV_ROUND_UP(bits, 8) > p->ilen)
+		return -EOVERFLOW;
+
+	if (bits <= 8)
+		*d = *in >> (8 - bits);
+	else if (bits <= 16)
+		*d = be16_to_cpu(get_unaligned((__be16 *)in)) >> (16 - bits);
+	else if (bits <= 32)
+		*d = be32_to_cpu(get_unaligned((__be32 *)in)) >> (32 - bits);
+	else
+		*d = be64_to_cpu(get_unaligned((__be64 *)in)) >> (64 - bits);
+
+	*d &= GENMASK_ULL(n - 1, 0);
+
+	p->bit += n;
+
+	if (p->bit > 7) {
+		p->in += p->bit / 8;
+		p->ilen -= p->bit / 8;
+		p->bit %= 8;
+	}
+
+	return 0;
+}
+
+static int do_data(struct sw842_param *p, u8 n)
+{
+	u64 v;
+	int ret;
+
+	if (n > p->olen)
+		return -ENOSPC;
+
+	ret = next_bits(p, &v, n * 8);
+	if (ret)
+		return ret;
+
+	switch (n) {
+	case 2:
+		put_unaligned(cpu_to_be16((u16)v), (__be16 *)p->out);
+		break;
+	case 4:
+		put_unaligned(cpu_to_be32((u32)v), (__be32 *)p->out);
+		break;
+	case 8:
+		put_unaligned(cpu_to_be64((u64)v), (__be64 *)p->out);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	p->out += n;
+	p->olen -= n;
+
+	return 0;
+}
+
+static int __do_index(struct sw842_param *p, u8 size, u8 bits, u64 fsize)
+{
+	u64 index, offset, total = round_down(p->out - p->ostart, 8);
+	int ret;
+
+	ret = next_bits(p, &index, bits);
+	if (ret)
+		return ret;
+
+	offset = index * size;
+
+	/* a ring buffer of fsize is used; correct the offset */
+	if (total > fsize) {
+		/* this is where the current fifo is */
+		u64 section = round_down(total, fsize);
+		/* the current pos in the fifo */
+		u64 pos = total - section;
+
+		/* if the offset is past/at the pos, we need to
+		 * go back to the last fifo section
+		 */
+		if (offset >= pos)
+			section -= fsize;
+
+		offset += section;
+	}
+
+	if (offset + size > total) {
+		pr_debug("index%x %lx points past end %lx\n", size,
+			 (unsigned long)offset, (unsigned long)total);
+		return -EINVAL;
+	}
+
+	pr_debug("index%x to %lx off %lx adjoff %lx tot %lx data %lx\n",
+		 size, (unsigned long)index, (unsigned long)(index * size),
+		 (unsigned long)offset, (unsigned long)total,
+		 (unsigned long)beN_to_cpu(&p->ostart[offset], size));
+
+	memcpy(p->out, &p->ostart[offset], size);
+	p->out += size;
+	p->olen -= size;
+
+	return 0;
+}
+
+static int do_index(struct sw842_param *p, u8 n)
+{
+	switch (n) {
+	case 2:
+		return __do_index(p, 2, I2_BITS, I2_FIFO_SIZE);
+	case 4:
+		return __do_index(p, 4, I4_BITS, I4_FIFO_SIZE);
+	case 8:
+		return __do_index(p, 8, I8_BITS, I8_FIFO_SIZE);
+	default:
+		return -EINVAL;
+	}
+}
+
+static int do_op(struct sw842_param *p, u8 o)
+{
+	int i, ret = 0;
+
+	if (o >= OPS_MAX)
+		return -EINVAL;
+
+	for (i = 0; i < 4; i++) {
+		u8 op = decomp_ops[o][i];
+
+		pr_debug("op is %x\n", op);
+
+		switch (op & OP_ACTION) {
+		case OP_ACTION_DATA:
+			ret = do_data(p, op & OP_AMOUNT);
+			break;
+		case OP_ACTION_INDEX:
+			ret = do_index(p, op & OP_AMOUNT);
+			break;
+		case OP_ACTION_NOOP:
+			break;
+		default:
+			pr_err("Interal error, invalid op %x\n", op);
+			return -EINVAL;
+		}
+
+		if (ret)
+			return ret;
+	}
+
+	if (sw842_template_counts)
+		atomic_inc(&template_count[o]);
+
+	return 0;
+}
+
+/**
+ * sw842_decompress
+ *
+ * Decompress the 842-compressed buffer of length @ilen at @in
+ * to the output buffer @out, using no more than @olen bytes.
+ *
+ * The compressed buffer must be only a single 842-compressed buffer,
+ * with the standard format described in the comments in 842.h
+ * Processing will stop when the 842 "END" template is detected,
+ * not the end of the buffer.
+ *
+ * Returns: 0 on success, error on failure.  The @olen parameter
+ * will contain the number of output bytes written on success, or
+ * 0 on error.
+ */
+int sw842_decompress(const u8 *in, unsigned int ilen,
+		     u8 *out, unsigned int *olen)
+{
+	struct sw842_param p;
+	int ret;
+	u64 op, rep, tmp, bytes, total;
+
+	p.in = (u8 *)in;
+	p.bit = 0;
+	p.ilen = ilen;
+	p.out = out;
+	p.ostart = out;
+	p.olen = *olen;
+
+	total = p.olen;
+
+	*olen = 0;
+
+	do {
+		ret = next_bits(&p, &op, OP_BITS);
+		if (ret)
+			return ret;
+
+		pr_debug("template is %lx\n", (unsigned long)op);
+
+		switch (op) {
+		case OP_REPEAT:
+			ret = next_bits(&p, &rep, REPEAT_BITS);
+			if (ret)
+				return ret;
+
+			if (p.out == out) /* no previous bytes */
+				return -EINVAL;
+
+			/* copy rep + 1 */
+			rep++;
+
+			if (rep * 8 > p.olen)
+				return -ENOSPC;
+
+			while (rep-- > 0) {
+				memcpy(p.out, p.out - 8, 8);
+				p.out += 8;
+				p.olen -= 8;
+			}
+
+			if (sw842_template_counts)
+				atomic_inc(&template_repeat_count);
+
+			break;
+		case OP_ZEROS:
+			if (8 > p.olen)
+				return -ENOSPC;
+
+			memset(p.out, 0, 8);
+			p.out += 8;
+			p.olen -= 8;
+
+			if (sw842_template_counts)
+				atomic_inc(&template_zeros_count);
+
+			break;
+		case OP_SHORT_DATA:
+			ret = next_bits(&p, &bytes, SHORT_DATA_BITS);
+			if (ret)
+				return ret;
+
+			if (!bytes || bytes > SHORT_DATA_BITS_MAX)
+				return -EINVAL;
+
+			while (bytes-- > 0) {
+				ret = next_bits(&p, &tmp, 8);
+				if (ret)
+					return ret;
+				*p.out = (u8)tmp;
+				p.out++;
+				p.olen--;
+			}
+
+			if (sw842_template_counts)
+				atomic_inc(&template_short_data_count);
+
+			break;
+		case OP_END:
+			if (sw842_template_counts)
+				atomic_inc(&template_end_count);
+
+			break;
+		default: /* use template */
+			ret = do_op(&p, op);
+			if (ret)
+				return ret;
+			break;
+		}
+	} while (op != OP_END);
+
+	if (unlikely((total - p.olen) > UINT_MAX))
+		return -ENOSPC;
+
+	*olen = total - p.olen;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(sw842_decompress);
+
+static int __init sw842_init(void)
+{
+	if (sw842_template_counts)
+		sw842_debugfs_create();
+
+	return 0;
+}
+module_init(sw842_init);
+
+static void __exit sw842_exit(void)
+{
+	if (sw842_template_counts)
+		sw842_debugfs_remove();
+}
+module_exit(sw842_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Software 842 Decompressor");
+MODULE_AUTHOR("Dan Streetman <ddstreet@ieee.org>");
diff --git a/lib/842/Makefile b/lib/842/Makefile
new file mode 100644
index 000000000000..5d24c0baff2e
--- /dev/null
+++ b/lib/842/Makefile
@@ -0,0 +1,2 @@
+obj-$(CONFIG_842_COMPRESS) += 842_compress.o
+obj-$(CONFIG_842_DECOMPRESS) += 842_decompress.o
diff --git a/lib/Kconfig b/lib/Kconfig
index 601965a948e8..34e332b8d326 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -212,6 +212,12 @@ config RANDOM32_SELFTEST
 #
 # compression support is select'ed if needed
 #
+config 842_COMPRESS
+	tristate
+
+config 842_DECOMPRESS
+	tristate
+
 config ZLIB_INFLATE
 	tristate
 
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index ba2b0c87e65b..b908048f8d6a 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1233,6 +1233,7 @@ config RCU_TORTURE_TEST
 	depends on DEBUG_KERNEL
 	select TORTURE_TEST
 	select SRCU
+	select TASKS_RCU
 	default n
 	help
 	  This option provides a kernel module that runs torture tests
@@ -1261,12 +1262,38 @@ config RCU_TORTURE_TEST_RUNNABLE
 	  Say N here if you want the RCU torture tests to start only
 	  after being manually enabled via /proc.
 
+config RCU_TORTURE_TEST_SLOW_PREINIT
+	bool "Slow down RCU grace-period pre-initialization to expose races"
+	depends on RCU_TORTURE_TEST
+	help
+	  This option delays grace-period pre-initialization (the
+	  propagation of CPU-hotplug changes up the rcu_node combining
+	  tree) for a few jiffies between initializing each pair of
+	  consecutive rcu_node structures.  This helps to expose races
+	  involving grace-period pre-initialization, in other words, it
+	  makes your kernel less stable.  It can also greatly increase
+	  grace-period latency, especially on systems with large numbers
+	  of CPUs.  This is useful when torture-testing RCU, but in
+	  almost no other circumstance.
+
+	  Say Y here if you want your system to crash and hang more often.
+	  Say N if you want a sane system.
+
+config RCU_TORTURE_TEST_SLOW_PREINIT_DELAY
+	int "How much to slow down RCU grace-period pre-initialization"
+	range 0 5
+	default 3
+	depends on RCU_TORTURE_TEST_SLOW_PREINIT
+	help
+	  This option specifies the number of jiffies to wait between
+	  each rcu_node structure pre-initialization step.
+
 config RCU_TORTURE_TEST_SLOW_INIT
 	bool "Slow down RCU grace-period initialization to expose races"
 	depends on RCU_TORTURE_TEST
 	help
-	  This option makes grace-period initialization block for a
-	  few jiffies between initializing each pair of consecutive
+	  This option delays grace-period initialization for a few
+	  jiffies between initializing each pair of consecutive
 	  rcu_node structures.	This helps to expose races involving
 	  grace-period initialization, in other words, it makes your
 	  kernel less stable.  It can also greatly increase grace-period
@@ -1286,6 +1313,30 @@ config RCU_TORTURE_TEST_SLOW_INIT_DELAY
 	  This option specifies the number of jiffies to wait between
 	  each rcu_node structure initialization.
 
+config RCU_TORTURE_TEST_SLOW_CLEANUP
+	bool "Slow down RCU grace-period cleanup to expose races"
+	depends on RCU_TORTURE_TEST
+	help
+	  This option delays grace-period cleanup for a few jiffies
+	  between cleaning up each pair of consecutive rcu_node
+	  structures.  This helps to expose races involving grace-period
+	  cleanup, in other words, it makes your kernel less stable.
+	  It can also greatly increase grace-period latency, especially
+	  on systems with large numbers of CPUs.  This is useful when
+	  torture-testing RCU, but in almost no other circumstance.
+
+	  Say Y here if you want your system to crash and hang more often.
+	  Say N if you want a sane system.
+
+config RCU_TORTURE_TEST_SLOW_CLEANUP_DELAY
+	int "How much to slow down RCU grace-period cleanup"
+	range 0 5
+	default 3
+	depends on RCU_TORTURE_TEST_SLOW_CLEANUP
+	help
+	  This option specifies the number of jiffies to wait between
+	  each rcu_node structure cleanup operation.
+
 config RCU_CPU_STALL_TIMEOUT
 	int "RCU CPU stall timeout in seconds"
 	depends on RCU_STALL_COMMON
@@ -1322,6 +1373,17 @@ config RCU_TRACE
 	  Say Y here if you want to enable RCU tracing
 	  Say N if you are unsure.
 
+config RCU_EQS_DEBUG
+	bool "Use this when adding any sort of NO_HZ support to your arch"
+	depends on DEBUG_KERNEL
+	help
+	  This option provides consistency checks in RCU's handling of
+	  NO_HZ.  These checks have proven quite helpful in detecting
+	  bugs in arch-specific NO_HZ code.
+
+	  Say N here if you need ultimate kernel/user switch latencies
+	  Say Y if you are unsure
+
 endmenu # "RCU Debugging"
 
 config DEBUG_BLOCK_EXT_DEVT
diff --git a/lib/Makefile b/lib/Makefile
index 6c37933336a0..ff37c8c2f7b2 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -78,6 +78,8 @@ obj-$(CONFIG_LIBCRC32C)	+= libcrc32c.o
 obj-$(CONFIG_CRC8)	+= crc8.o
 obj-$(CONFIG_GENERIC_ALLOCATOR) += genalloc.o
 
+obj-$(CONFIG_842_COMPRESS) += 842/
+obj-$(CONFIG_842_DECOMPRESS) += 842/
 obj-$(CONFIG_ZLIB_INFLATE) += zlib_inflate/
 obj-$(CONFIG_ZLIB_DEFLATE) += zlib_deflate/
 obj-$(CONFIG_REED_SOLOMON) += reed_solomon/
diff --git a/lib/cpu_rmap.c b/lib/cpu_rmap.c
index 4f134d8907a7..f610b2a10b3e 100644
--- a/lib/cpu_rmap.c
+++ b/lib/cpu_rmap.c
@@ -191,7 +191,7 @@ int cpu_rmap_update(struct cpu_rmap *rmap, u16 index,
 	/* Update distances based on topology */
 	for_each_cpu(cpu, update_mask) {
 		if (cpu_rmap_copy_neigh(rmap, cpu,
-					topology_thread_cpumask(cpu), 1))
+					topology_sibling_cpumask(cpu), 1))
 			continue;
 		if (cpu_rmap_copy_neigh(rmap, cpu,
 					topology_core_cpumask(cpu), 2))
diff --git a/lib/cpumask.c b/lib/cpumask.c
index 5f627084f2e9..5a70f6196f57 100644
--- a/lib/cpumask.c
+++ b/lib/cpumask.c
@@ -16,11 +16,10 @@
 int cpumask_next_and(int n, const struct cpumask *src1p,
 		     const struct cpumask *src2p)
 {
-	struct cpumask tmp;
-
-	if (cpumask_and(&tmp, src1p, src2p))
-		return cpumask_next(n, &tmp);
-	return nr_cpu_ids;
+	while ((n = cpumask_next(n, src1p)) < nr_cpu_ids)
+		if (cpumask_test_cpu(n, src2p))
+			break;
+	return n;
 }
 EXPORT_SYMBOL(cpumask_next_and);
 
diff --git a/lib/crc-itu-t.c b/lib/crc-itu-t.c
index a63472b82416..b3219d0abfb4 100644
--- a/lib/crc-itu-t.c
+++ b/lib/crc-itu-t.c
@@ -9,7 +9,7 @@
 #include <linux/module.h>
 #include <linux/crc-itu-t.h>
 
-/** CRC table for the CRC ITU-T V.41 0x0x1021 (x^16 + x^12 + x^15 + 1) */
+/** CRC table for the CRC ITU-T V.41 0x1021 (x^16 + x^12 + x^15 + 1) */
 const u16 crc_itu_t_table[256] = {
 	0x0000, 0x1021, 0x2042, 0x3063, 0x4084, 0x50a5, 0x60c6, 0x70e7,
 	0x8108, 0x9129, 0xa14a, 0xb16b, 0xc18c, 0xd1ad, 0xe1ce, 0xf1ef,
diff --git a/lib/mpi/mpicoder.c b/lib/mpi/mpicoder.c
index 4cc6442733f4..bc0a1da8afba 100644
--- a/lib/mpi/mpicoder.c
+++ b/lib/mpi/mpicoder.c
@@ -128,28 +128,36 @@ leave:
 }
 EXPORT_SYMBOL_GPL(mpi_read_from_buffer);
 
-/****************
- * Return an allocated buffer with the MPI (msb first).
- * NBYTES receives the length of this buffer. Caller must free the
- * return string (This function does return a 0 byte buffer with NBYTES
- * set to zero if the value of A is zero. If sign is not NULL, it will
- * be set to the sign of the A.
+/**
+ * mpi_read_buffer() - read MPI to a bufer provided by user (msb first)
+ *
+ * @a:		a multi precision integer
+ * @buf:	bufer to which the output will be written to. Needs to be at
+ *		leaset mpi_get_size(a) long.
+ * @buf_len:	size of the buf.
+ * @nbytes:	receives the actual length of the data written.
+ * @sign:	if not NULL, it will be set to the sign of a.
+ *
+ * Return:	0 on success or error code in case of error
  */
-void *mpi_get_buffer(MPI a, unsigned *nbytes, int *sign)
+int mpi_read_buffer(MPI a, uint8_t *buf, unsigned buf_len, unsigned *nbytes,
+		    int *sign)
 {
-	uint8_t *p, *buffer;
+	uint8_t *p;
 	mpi_limb_t alimb;
+	unsigned int n = mpi_get_size(a);
 	int i;
-	unsigned int n;
+
+	if (buf_len < n || !buf)
+		return -EINVAL;
 
 	if (sign)
 		*sign = a->sign;
-	*nbytes = n = a->nlimbs * BYTES_PER_MPI_LIMB;
-	if (!n)
-		n++;		/* avoid zero length allocation */
-	p = buffer = kmalloc(n, GFP_KERNEL);
-	if (!p)
-		return NULL;
+
+	if (nbytes)
+		*nbytes = n;
+
+	p = buf;
 
 	for (i = a->nlimbs - 1; i >= 0; i--) {
 		alimb = a->d[i];
@@ -171,15 +179,56 @@ void *mpi_get_buffer(MPI a, unsigned *nbytes, int *sign)
 #error please implement for this limb size.
 #endif
 	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mpi_read_buffer);
+
+/*
+ * mpi_get_buffer() - Returns an allocated buffer with the MPI (msb first).
+ * Caller must free the return string.
+ * This function does return a 0 byte buffer with nbytes set to zero if the
+ * value of A is zero.
+ *
+ * @a:		a multi precision integer.
+ * @nbytes:	receives the length of this buffer.
+ * @sign:	if not NULL, it will be set to the sign of the a.
+ *
+ * Return:	Pointer to MPI buffer or NULL on error
+ */
+void *mpi_get_buffer(MPI a, unsigned *nbytes, int *sign)
+{
+	uint8_t *buf, *p;
+	unsigned int n;
+	int ret;
+
+	if (!nbytes)
+		return NULL;
+
+	n = mpi_get_size(a);
+
+	if (!n)
+		n++;
+
+	buf = kmalloc(n, GFP_KERNEL);
+
+	if (!buf)
+		return NULL;
+
+	ret = mpi_read_buffer(a, buf, n, nbytes, sign);
+
+	if (ret) {
+		kfree(buf);
+		return NULL;
+	}
 
 	/* this is sub-optimal but we need to do the shift operation
 	 * because the caller has to free the returned buffer */
-	for (p = buffer; !*p && *nbytes; p++, --*nbytes)
+	for (p = buf; !*p && *nbytes; p++, --*nbytes)
 		;
-	if (p != buffer)
-		memmove(buffer, p, *nbytes);
+	if (p != buf)
+		memmove(buf, p, *nbytes);
 
-	return buffer;
+	return buf;
 }
 EXPORT_SYMBOL_GPL(mpi_get_buffer);
 
diff --git a/lib/mpi/mpiutil.c b/lib/mpi/mpiutil.c
index bf076d281d40..314f4dfa603e 100644
--- a/lib/mpi/mpiutil.c
+++ b/lib/mpi/mpiutil.c
@@ -69,7 +69,7 @@ void mpi_free_limb_space(mpi_ptr_t a)
 	if (!a)
 		return;
 
-	kfree(a);
+	kzfree(a);
 }
 
 void mpi_assign_limb_space(MPI a, mpi_ptr_t ap, unsigned nlimbs)
@@ -95,7 +95,7 @@ int mpi_resize(MPI a, unsigned nlimbs)
 		if (!p)
 			return -ENOMEM;
 		memcpy(p, a->d, a->alloced * sizeof(mpi_limb_t));
-		kfree(a->d);
+		kzfree(a->d);
 		a->d = p;
 	} else {
 		a->d = kzalloc(nlimbs * sizeof(mpi_limb_t), GFP_KERNEL);
@@ -112,7 +112,7 @@ void mpi_free(MPI a)
 		return;
 
 	if (a->flags & 4)
-		kfree(a->d);
+		kzfree(a->d);
 	else
 		mpi_free_limb_space(a->d);
 
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 3d2aa27b845b..061550de77bc 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -33,7 +33,7 @@
 #include <linux/string.h>
 #include <linux/bitops.h>
 #include <linux/rcupdate.h>
-#include <linux/preempt_mask.h>		/* in_interrupt() */
+#include <linux/preempt.h>		/* in_interrupt() */
 
 
 /*
diff --git a/lib/raid6/x86.h b/lib/raid6/x86.h
index b7595484a815..8fe9d9662abb 100644
--- a/lib/raid6/x86.h
+++ b/lib/raid6/x86.h
@@ -23,7 +23,7 @@
 
 #ifdef __KERNEL__ /* Real code */
 
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 
 #else /* Dummy code for user space testing */
 
diff --git a/lib/scatterlist.c b/lib/scatterlist.c
index c9f2e8c6ccc9..99fbc2f238c4 100644
--- a/lib/scatterlist.c
+++ b/lib/scatterlist.c
@@ -56,6 +56,38 @@ int sg_nents(struct scatterlist *sg)
 }
 EXPORT_SYMBOL(sg_nents);
 
+/**
+ * sg_nents_for_len - return total count of entries in scatterlist
+ *                    needed to satisfy the supplied length
+ * @sg:		The scatterlist
+ * @len:	The total required length
+ *
+ * Description:
+ * Determines the number of entries in sg that are required to meet
+ * the supplied length, taking into acount chaining as well
+ *
+ * Returns:
+ *   the number of sg entries needed, negative error on failure
+ *
+ **/
+int sg_nents_for_len(struct scatterlist *sg, u64 len)
+{
+	int nents;
+	u64 total;
+
+	if (!len)
+		return 0;
+
+	for (nents = 0, total = 0; sg; sg = sg_next(sg)) {
+		nents++;
+		total += sg->length;
+		if (total >= len)
+			return nents;
+	}
+
+	return -EINVAL;
+}
+EXPORT_SYMBOL(sg_nents_for_len);
 
 /**
  * sg_last - return the last scatterlist entry in a list
diff --git a/lib/strnlen_user.c b/lib/strnlen_user.c
index fe9a32591c24..3a5f2b366d84 100644
--- a/lib/strnlen_user.c
+++ b/lib/strnlen_user.c
@@ -85,7 +85,8 @@ static inline long do_strnlen_user(const char __user *src, unsigned long count,
  * @str: The string to measure.
  * @count: Maximum count (including NUL character)
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Get the size of a NUL-terminated string in user space.
  *
@@ -121,7 +122,8 @@ EXPORT_SYMBOL(strnlen_user);
  * strlen_user: - Get the size of a user string INCLUDING final NUL.
  * @str: The string to measure.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Get the size of a NUL-terminated string in user space.
  *
diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index 3c365ab6cf5f..42e192decbfd 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -656,7 +656,7 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 		 */
 		phys_addr_t paddr = map_single(hwdev, 0, size, DMA_FROM_DEVICE);
 		if (paddr == SWIOTLB_MAP_ERROR)
-			return NULL;
+			goto err_warn;
 
 		ret = phys_to_virt(paddr);
 		dev_addr = phys_to_dma(hwdev, paddr);
@@ -670,7 +670,7 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 			/* DMA_TO_DEVICE to avoid memcpy in unmap_single */
 			swiotlb_tbl_unmap_single(hwdev, paddr,
 						 size, DMA_TO_DEVICE);
-			return NULL;
+			goto err_warn;
 		}
 	}
 
@@ -678,6 +678,13 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 	memset(ret, 0, size);
 
 	return ret;
+
+err_warn:
+	pr_warn("swiotlb: coherent allocation failed for device %s size=%zu\n",
+		dev_name(hwdev), size);
+	dump_stack();
+
+	return NULL;
 }
 EXPORT_SYMBOL(swiotlb_alloc_coherent);
 
diff --git a/lib/timerqueue.c b/lib/timerqueue.c
index a382e4a32609..782ae8ca2c06 100644
--- a/lib/timerqueue.c
+++ b/lib/timerqueue.c
@@ -36,7 +36,7 @@
  * Adds the timer node to the timerqueue, sorted by the
  * node's expires value.
  */
-void timerqueue_add(struct timerqueue_head *head, struct timerqueue_node *node)
+bool timerqueue_add(struct timerqueue_head *head, struct timerqueue_node *node)
 {
 	struct rb_node **p = &head->head.rb_node;
 	struct rb_node *parent = NULL;
@@ -56,8 +56,11 @@ void timerqueue_add(struct timerqueue_head *head, struct timerqueue_node *node)
 	rb_link_node(&node->node, parent, p);
 	rb_insert_color(&node->node, &head->head);
 
-	if (!head->next || node->expires.tv64 < head->next->expires.tv64)
+	if (!head->next || node->expires.tv64 < head->next->expires.tv64) {
 		head->next = node;
+		return true;
+	}
+	return false;
 }
 EXPORT_SYMBOL_GPL(timerqueue_add);
 
@@ -69,7 +72,7 @@ EXPORT_SYMBOL_GPL(timerqueue_add);
  *
  * Removes the timer node from the timerqueue.
  */
-void timerqueue_del(struct timerqueue_head *head, struct timerqueue_node *node)
+bool timerqueue_del(struct timerqueue_head *head, struct timerqueue_node *node)
 {
 	WARN_ON_ONCE(RB_EMPTY_NODE(&node->node));
 
@@ -82,6 +85,7 @@ void timerqueue_del(struct timerqueue_head *head, struct timerqueue_node *node)
 	}
 	rb_erase(&node->node, &head->head);
 	RB_CLEAR_NODE(&node->node);
+	return head->next != NULL;
 }
 EXPORT_SYMBOL_GPL(timerqueue_del);
 
diff --git a/mm/memory.c b/mm/memory.c
index 22e037e3364e..17734c3c1183 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3737,7 +3737,7 @@ void print_vma_addr(char *prefix, unsigned long ip)
 }
 
 #if defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_DEBUG_ATOMIC_SLEEP)
-void might_fault(void)
+void __might_fault(const char *file, int line)
 {
 	/*
 	 * Some code (nfs/sunrpc) uses socket ops on kernel memory while
@@ -3747,21 +3747,15 @@ void might_fault(void)
 	 */
 	if (segment_eq(get_fs(), KERNEL_DS))
 		return;
-
-	/*
-	 * it would be nicer only to annotate paths which are not under
-	 * pagefault_disable, however that requires a larger audit and
-	 * providing helpers like get_user_atomic.
-	 */
-	if (in_atomic())
+	if (pagefault_disabled())
 		return;
-
-	__might_sleep(__FILE__, __LINE__, 0);
-
+	__might_sleep(file, line, 0);
+#if defined(CONFIG_DEBUG_ATOMIC_SLEEP)
 	if (current->mm)
 		might_lock_read(&current->mm->mmap_sem);
+#endif
 }
-EXPORT_SYMBOL(might_fault);
+EXPORT_SYMBOL(__might_fault);
 #endif
 
 #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS)
diff --git a/mm/shmem.c b/mm/shmem.c
index de981370fbc5..3759099d8ce4 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2451,6 +2451,7 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s
 			return -ENOMEM;
 		}
 		inode->i_op = &shmem_short_symlink_operations;
+		inode->i_link = info->symlink;
 	} else {
 		error = shmem_getpage(inode, 0, &page, SGP_WRITE, NULL);
 		if (error) {
@@ -2474,30 +2475,23 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s
 	return 0;
 }
 
-static void *shmem_follow_short_symlink(struct dentry *dentry, struct nameidata *nd)
-{
-	nd_set_link(nd, SHMEM_I(d_inode(dentry))->symlink);
-	return NULL;
-}
-
-static void *shmem_follow_link(struct dentry *dentry, struct nameidata *nd)
+static const char *shmem_follow_link(struct dentry *dentry, void **cookie)
 {
 	struct page *page = NULL;
 	int error = shmem_getpage(d_inode(dentry), 0, &page, SGP_READ, NULL);
-	nd_set_link(nd, error ? ERR_PTR(error) : kmap(page));
-	if (page)
-		unlock_page(page);
-	return page;
+	if (error)
+		return ERR_PTR(error);
+	unlock_page(page);
+	*cookie = page;
+	return kmap(page);
 }
 
-static void shmem_put_link(struct dentry *dentry, struct nameidata *nd, void *cookie)
+static void shmem_put_link(struct inode *unused, void *cookie)
 {
-	if (!IS_ERR(nd_get_link(nd))) {
-		struct page *page = cookie;
-		kunmap(page);
-		mark_page_accessed(page);
-		page_cache_release(page);
-	}
+	struct page *page = cookie;
+	kunmap(page);
+	mark_page_accessed(page);
+	page_cache_release(page);
 }
 
 #ifdef CONFIG_TMPFS_XATTR
@@ -2642,7 +2636,7 @@ static ssize_t shmem_listxattr(struct dentry *dentry, char *buffer, size_t size)
 
 static const struct inode_operations shmem_short_symlink_operations = {
 	.readlink	= generic_readlink,
-	.follow_link	= shmem_follow_short_symlink,
+	.follow_link	= simple_follow_link,
 #ifdef CONFIG_TMPFS_XATTR
 	.setxattr	= shmem_setxattr,
 	.getxattr	= shmem_getxattr,
@@ -3401,7 +3395,13 @@ int shmem_zero_setup(struct vm_area_struct *vma)
 	struct file *file;
 	loff_t size = vma->vm_end - vma->vm_start;
 
-	file = shmem_file_setup("dev/zero", size, vma->vm_flags);
+	/*
+	 * Cloning a new file under mmap_sem leads to a lock ordering conflict
+	 * between XFS directory reading and selinux: since this file is only
+	 * accessible to the user through its mapping, use S_PRIVATE flag to
+	 * bypass file security, in the same way as shmem_kernel_file_setup().
+	 */
+	file = __shmem_file_setup("dev/zero", size, vma->vm_flags, S_PRIVATE);
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index 91180a7fc943..c2cabbe6fa58 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -6,7 +6,7 @@
  *
  *  ebtables.c,v 2.0, July, 2002
  *
- *  This code is stongly inspired on the iptables code which is
+ *  This code is strongly inspired by the iptables code which is
  *  Copyright (C) 1999 Paul `Rusty' Russell & Michael J. Neuling
  *
  *  This program is free software; you can redistribute it and/or
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 508155b283dd..54817d365366 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -2212,8 +2212,6 @@ static void spin(struct pktgen_dev *pkt_dev, ktime_t spin_until)
 		do {
 			set_current_state(TASK_INTERRUPTIBLE);
 			hrtimer_start_expires(&t.timer, HRTIMER_MODE_ABS);
-			if (!hrtimer_active(&t.timer))
-				t.task = NULL;
 
 			if (likely(t.task))
 				schedule();
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 30b544f025ac..477937465a20 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -49,7 +49,7 @@ static void *esp_alloc_tmp(struct crypto_aead *aead, int nfrags, int seqhilen)
 		len = ALIGN(len, crypto_tfm_ctx_alignment());
 	}
 
-	len += sizeof(struct aead_givcrypt_request) + crypto_aead_reqsize(aead);
+	len += sizeof(struct aead_request) + crypto_aead_reqsize(aead);
 	len = ALIGN(len, __alignof__(struct scatterlist));
 
 	len += sizeof(struct scatterlist) * nfrags;
@@ -68,17 +68,6 @@ static inline u8 *esp_tmp_iv(struct crypto_aead *aead, void *tmp, int seqhilen)
 			 crypto_aead_alignmask(aead) + 1) : tmp + seqhilen;
 }
 
-static inline struct aead_givcrypt_request *esp_tmp_givreq(
-	struct crypto_aead *aead, u8 *iv)
-{
-	struct aead_givcrypt_request *req;
-
-	req = (void *)PTR_ALIGN(iv + crypto_aead_ivsize(aead),
-				crypto_tfm_ctx_alignment());
-	aead_givcrypt_set_tfm(req, aead);
-	return req;
-}
-
 static inline struct aead_request *esp_tmp_req(struct crypto_aead *aead, u8 *iv)
 {
 	struct aead_request *req;
@@ -97,14 +86,6 @@ static inline struct scatterlist *esp_req_sg(struct crypto_aead *aead,
 			     __alignof__(struct scatterlist));
 }
 
-static inline struct scatterlist *esp_givreq_sg(
-	struct crypto_aead *aead, struct aead_givcrypt_request *req)
-{
-	return (void *)ALIGN((unsigned long)(req + 1) +
-			     crypto_aead_reqsize(aead),
-			     __alignof__(struct scatterlist));
-}
-
 static void esp_output_done(struct crypto_async_request *base, int err)
 {
 	struct sk_buff *skb = base->data;
@@ -113,14 +94,37 @@ static void esp_output_done(struct crypto_async_request *base, int err)
 	xfrm_output_resume(skb, err);
 }
 
+/* Move ESP header back into place. */
+static void esp_restore_header(struct sk_buff *skb, unsigned int offset)
+{
+	struct ip_esp_hdr *esph = (void *)(skb->data + offset);
+	void *tmp = ESP_SKB_CB(skb)->tmp;
+	__be32 *seqhi = esp_tmp_seqhi(tmp);
+
+	esph->seq_no = esph->spi;
+	esph->spi = *seqhi;
+}
+
+static void esp_output_restore_header(struct sk_buff *skb)
+{
+	esp_restore_header(skb, skb_transport_offset(skb) - sizeof(__be32));
+}
+
+static void esp_output_done_esn(struct crypto_async_request *base, int err)
+{
+	struct sk_buff *skb = base->data;
+
+	esp_output_restore_header(skb);
+	esp_output_done(base, err);
+}
+
 static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 {
 	int err;
 	struct ip_esp_hdr *esph;
 	struct crypto_aead *aead;
-	struct aead_givcrypt_request *req;
+	struct aead_request *req;
 	struct scatterlist *sg;
-	struct scatterlist *asg;
 	struct sk_buff *trailer;
 	void *tmp;
 	u8 *iv;
@@ -129,17 +133,19 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 	int clen;
 	int alen;
 	int plen;
+	int ivlen;
 	int tfclen;
 	int nfrags;
 	int assoclen;
-	int sglists;
 	int seqhilen;
 	__be32 *seqhi;
+	__be64 seqno;
 
 	/* skb is pure payload to encrypt */
 
 	aead = x->data;
 	alen = crypto_aead_authsize(aead);
+	ivlen = crypto_aead_ivsize(aead);
 
 	tfclen = 0;
 	if (x->tfcpad) {
@@ -160,16 +166,14 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 	nfrags = err;
 
 	assoclen = sizeof(*esph);
-	sglists = 1;
 	seqhilen = 0;
 
 	if (x->props.flags & XFRM_STATE_ESN) {
-		sglists += 2;
 		seqhilen += sizeof(__be32);
 		assoclen += seqhilen;
 	}
 
-	tmp = esp_alloc_tmp(aead, nfrags + sglists, seqhilen);
+	tmp = esp_alloc_tmp(aead, nfrags, seqhilen);
 	if (!tmp) {
 		err = -ENOMEM;
 		goto error;
@@ -177,9 +181,8 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 
 	seqhi = esp_tmp_seqhi(tmp);
 	iv = esp_tmp_iv(aead, tmp, seqhilen);
-	req = esp_tmp_givreq(aead, iv);
-	asg = esp_givreq_sg(aead, req);
-	sg = asg + sglists;
+	req = esp_tmp_req(aead, iv);
+	sg = esp_req_sg(aead, req);
 
 	/* Fill padding... */
 	tail = skb_tail_pointer(trailer);
@@ -235,37 +238,53 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 		*skb_mac_header(skb) = IPPROTO_UDP;
 	}
 
-	esph->spi = x->id.spi;
 	esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low);
 
+	aead_request_set_callback(req, 0, esp_output_done, skb);
+
+	/* For ESN we move the header forward by 4 bytes to
+	 * accomodate the high bits.  We will move it back after
+	 * encryption.
+	 */
+	if ((x->props.flags & XFRM_STATE_ESN)) {
+		esph = (void *)(skb_transport_header(skb) - sizeof(__be32));
+		*seqhi = esph->spi;
+		esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.hi);
+		aead_request_set_callback(req, 0, esp_output_done_esn, skb);
+	}
+
+	esph->spi = x->id.spi;
+
 	sg_init_table(sg, nfrags);
 	skb_to_sgvec(skb, sg,
-		     esph->enc_data + crypto_aead_ivsize(aead) - skb->data,
-		     clen + alen);
+		     (unsigned char *)esph - skb->data,
+		     assoclen + ivlen + clen + alen);
 
-	if ((x->props.flags & XFRM_STATE_ESN)) {
-		sg_init_table(asg, 3);
-		sg_set_buf(asg, &esph->spi, sizeof(__be32));
-		*seqhi = htonl(XFRM_SKB_CB(skb)->seq.output.hi);
-		sg_set_buf(asg + 1, seqhi, seqhilen);
-		sg_set_buf(asg + 2, &esph->seq_no, sizeof(__be32));
-	} else
-		sg_init_one(asg, esph, sizeof(*esph));
-
-	aead_givcrypt_set_callback(req, 0, esp_output_done, skb);
-	aead_givcrypt_set_crypt(req, sg, sg, clen, iv);
-	aead_givcrypt_set_assoc(req, asg, assoclen);
-	aead_givcrypt_set_giv(req, esph->enc_data,
-			      XFRM_SKB_CB(skb)->seq.output.low +
-			      ((u64)XFRM_SKB_CB(skb)->seq.output.hi << 32));
+	aead_request_set_crypt(req, sg, sg, ivlen + clen, iv);
+	aead_request_set_ad(req, assoclen);
+
+	seqno = cpu_to_be64(XFRM_SKB_CB(skb)->seq.output.low +
+			    ((u64)XFRM_SKB_CB(skb)->seq.output.hi << 32));
+
+	memset(iv, 0, ivlen);
+	memcpy(iv + ivlen - min(ivlen, 8), (u8 *)&seqno + 8 - min(ivlen, 8),
+	       min(ivlen, 8));
 
 	ESP_SKB_CB(skb)->tmp = tmp;
-	err = crypto_aead_givencrypt(req);
-	if (err == -EINPROGRESS)
+	err = crypto_aead_encrypt(req);
+
+	switch (err) {
+	case -EINPROGRESS:
 		goto error;
 
-	if (err == -EBUSY)
+	case -EBUSY:
 		err = NET_XMIT_DROP;
+		break;
+
+	case 0:
+		if ((x->props.flags & XFRM_STATE_ESN))
+			esp_output_restore_header(skb);
+	}
 
 	kfree(tmp);
 
@@ -364,6 +383,20 @@ static void esp_input_done(struct crypto_async_request *base, int err)
 	xfrm_input_resume(skb, esp_input_done2(skb, err));
 }
 
+static void esp_input_restore_header(struct sk_buff *skb)
+{
+	esp_restore_header(skb, 0);
+	__skb_pull(skb, 4);
+}
+
+static void esp_input_done_esn(struct crypto_async_request *base, int err)
+{
+	struct sk_buff *skb = base->data;
+
+	esp_input_restore_header(skb);
+	esp_input_done(base, err);
+}
+
 /*
  * Note: detecting truncated vs. non-truncated authentication data is very
  * expensive, so we only support truncated data, which is the recommended
@@ -375,19 +408,18 @@ static int esp_input(struct xfrm_state *x, struct sk_buff *skb)
 	struct crypto_aead *aead = x->data;
 	struct aead_request *req;
 	struct sk_buff *trailer;
-	int elen = skb->len - sizeof(*esph) - crypto_aead_ivsize(aead);
+	int ivlen = crypto_aead_ivsize(aead);
+	int elen = skb->len - sizeof(*esph) - ivlen;
 	int nfrags;
 	int assoclen;
-	int sglists;
 	int seqhilen;
 	__be32 *seqhi;
 	void *tmp;
 	u8 *iv;
 	struct scatterlist *sg;
-	struct scatterlist *asg;
 	int err = -EINVAL;
 
-	if (!pskb_may_pull(skb, sizeof(*esph) + crypto_aead_ivsize(aead)))
+	if (!pskb_may_pull(skb, sizeof(*esph) + ivlen))
 		goto out;
 
 	if (elen <= 0)
@@ -400,17 +432,15 @@ static int esp_input(struct xfrm_state *x, struct sk_buff *skb)
 	nfrags = err;
 
 	assoclen = sizeof(*esph);
-	sglists = 1;
 	seqhilen = 0;
 
 	if (x->props.flags & XFRM_STATE_ESN) {
-		sglists += 2;
 		seqhilen += sizeof(__be32);
 		assoclen += seqhilen;
 	}
 
 	err = -ENOMEM;
-	tmp = esp_alloc_tmp(aead, nfrags + sglists, seqhilen);
+	tmp = esp_alloc_tmp(aead, nfrags, seqhilen);
 	if (!tmp)
 		goto out;
 
@@ -418,36 +448,39 @@ static int esp_input(struct xfrm_state *x, struct sk_buff *skb)
 	seqhi = esp_tmp_seqhi(tmp);
 	iv = esp_tmp_iv(aead, tmp, seqhilen);
 	req = esp_tmp_req(aead, iv);
-	asg = esp_req_sg(aead, req);
-	sg = asg + sglists;
+	sg = esp_req_sg(aead, req);
 
 	skb->ip_summed = CHECKSUM_NONE;
 
 	esph = (struct ip_esp_hdr *)skb->data;
 
-	/* Get ivec. This can be wrong, check against another impls. */
-	iv = esph->enc_data;
-
-	sg_init_table(sg, nfrags);
-	skb_to_sgvec(skb, sg, sizeof(*esph) + crypto_aead_ivsize(aead), elen);
+	aead_request_set_callback(req, 0, esp_input_done, skb);
 
+	/* For ESN we move the header forward by 4 bytes to
+	 * accomodate the high bits.  We will move it back after
+	 * decryption.
+	 */
 	if ((x->props.flags & XFRM_STATE_ESN)) {
-		sg_init_table(asg, 3);
-		sg_set_buf(asg, &esph->spi, sizeof(__be32));
-		*seqhi = XFRM_SKB_CB(skb)->seq.input.hi;
-		sg_set_buf(asg + 1, seqhi, seqhilen);
-		sg_set_buf(asg + 2, &esph->seq_no, sizeof(__be32));
-	} else
-		sg_init_one(asg, esph, sizeof(*esph));
+		esph = (void *)skb_push(skb, 4);
+		*seqhi = esph->spi;
+		esph->spi = esph->seq_no;
+		esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.input.hi);
+		aead_request_set_callback(req, 0, esp_input_done_esn, skb);
+	}
 
-	aead_request_set_callback(req, 0, esp_input_done, skb);
-	aead_request_set_crypt(req, sg, sg, elen, iv);
-	aead_request_set_assoc(req, asg, assoclen);
+	sg_init_table(sg, nfrags);
+	skb_to_sgvec(skb, sg, 0, skb->len);
+
+	aead_request_set_crypt(req, sg, sg, elen + ivlen, iv);
+	aead_request_set_ad(req, assoclen);
 
 	err = crypto_aead_decrypt(req);
 	if (err == -EINPROGRESS)
 		goto out;
 
+	if ((x->props.flags & XFRM_STATE_ESN))
+		esp_input_restore_header(skb);
+
 	err = esp_input_done2(skb, err);
 
 out:
@@ -519,10 +552,16 @@ static void esp_destroy(struct xfrm_state *x)
 
 static int esp_init_aead(struct xfrm_state *x)
 {
+	char aead_name[CRYPTO_MAX_ALG_NAME];
 	struct crypto_aead *aead;
 	int err;
 
-	aead = crypto_alloc_aead(x->aead->alg_name, 0, 0);
+	err = -ENAMETOOLONG;
+	if (snprintf(aead_name, CRYPTO_MAX_ALG_NAME, "%s(%s)",
+		     x->geniv, x->aead->alg_name) >= CRYPTO_MAX_ALG_NAME)
+		goto error;
+
+	aead = crypto_alloc_aead(aead_name, 0, 0);
 	err = PTR_ERR(aead);
 	if (IS_ERR(aead))
 		goto error;
@@ -561,15 +600,19 @@ static int esp_init_authenc(struct xfrm_state *x)
 
 	if ((x->props.flags & XFRM_STATE_ESN)) {
 		if (snprintf(authenc_name, CRYPTO_MAX_ALG_NAME,
-			     "authencesn(%s,%s)",
+			     "%s%sauthencesn(%s,%s)%s",
+			     x->geniv ?: "", x->geniv ? "(" : "",
 			     x->aalg ? x->aalg->alg_name : "digest_null",
-			     x->ealg->alg_name) >= CRYPTO_MAX_ALG_NAME)
+			     x->ealg->alg_name,
+			     x->geniv ? ")" : "") >= CRYPTO_MAX_ALG_NAME)
 			goto error;
 	} else {
 		if (snprintf(authenc_name, CRYPTO_MAX_ALG_NAME,
-			     "authenc(%s,%s)",
+			     "%s%sauthenc(%s,%s)%s",
+			     x->geniv ?: "", x->geniv ? "(" : "",
 			     x->aalg ? x->aalg->alg_name : "digest_null",
-			     x->ealg->alg_name) >= CRYPTO_MAX_ALG_NAME)
+			     x->ealg->alg_name,
+			     x->geniv ? ")" : "") >= CRYPTO_MAX_ALG_NAME)
 			goto error;
 	}
 
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 7c07ce36aae2..060a60b2f8a6 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -76,7 +76,7 @@ static void *esp_alloc_tmp(struct crypto_aead *aead, int nfrags, int seqihlen)
 		len = ALIGN(len, crypto_tfm_ctx_alignment());
 	}
 
-	len += sizeof(struct aead_givcrypt_request) + crypto_aead_reqsize(aead);
+	len += sizeof(struct aead_request) + crypto_aead_reqsize(aead);
 	len = ALIGN(len, __alignof__(struct scatterlist));
 
 	len += sizeof(struct scatterlist) * nfrags;
@@ -96,17 +96,6 @@ static inline u8 *esp_tmp_iv(struct crypto_aead *aead, void *tmp, int seqhilen)
 			 crypto_aead_alignmask(aead) + 1) : tmp + seqhilen;
 }
 
-static inline struct aead_givcrypt_request *esp_tmp_givreq(
-	struct crypto_aead *aead, u8 *iv)
-{
-	struct aead_givcrypt_request *req;
-
-	req = (void *)PTR_ALIGN(iv + crypto_aead_ivsize(aead),
-				crypto_tfm_ctx_alignment());
-	aead_givcrypt_set_tfm(req, aead);
-	return req;
-}
-
 static inline struct aead_request *esp_tmp_req(struct crypto_aead *aead, u8 *iv)
 {
 	struct aead_request *req;
@@ -125,14 +114,6 @@ static inline struct scatterlist *esp_req_sg(struct crypto_aead *aead,
 			     __alignof__(struct scatterlist));
 }
 
-static inline struct scatterlist *esp_givreq_sg(
-	struct crypto_aead *aead, struct aead_givcrypt_request *req)
-{
-	return (void *)ALIGN((unsigned long)(req + 1) +
-			     crypto_aead_reqsize(aead),
-			     __alignof__(struct scatterlist));
-}
-
 static void esp_output_done(struct crypto_async_request *base, int err)
 {
 	struct sk_buff *skb = base->data;
@@ -141,32 +122,57 @@ static void esp_output_done(struct crypto_async_request *base, int err)
 	xfrm_output_resume(skb, err);
 }
 
+/* Move ESP header back into place. */
+static void esp_restore_header(struct sk_buff *skb, unsigned int offset)
+{
+	struct ip_esp_hdr *esph = (void *)(skb->data + offset);
+	void *tmp = ESP_SKB_CB(skb)->tmp;
+	__be32 *seqhi = esp_tmp_seqhi(tmp);
+
+	esph->seq_no = esph->spi;
+	esph->spi = *seqhi;
+}
+
+static void esp_output_restore_header(struct sk_buff *skb)
+{
+	esp_restore_header(skb, skb_transport_offset(skb) - sizeof(__be32));
+}
+
+static void esp_output_done_esn(struct crypto_async_request *base, int err)
+{
+	struct sk_buff *skb = base->data;
+
+	esp_output_restore_header(skb);
+	esp_output_done(base, err);
+}
+
 static int esp6_output(struct xfrm_state *x, struct sk_buff *skb)
 {
 	int err;
 	struct ip_esp_hdr *esph;
 	struct crypto_aead *aead;
-	struct aead_givcrypt_request *req;
+	struct aead_request *req;
 	struct scatterlist *sg;
-	struct scatterlist *asg;
 	struct sk_buff *trailer;
 	void *tmp;
 	int blksize;
 	int clen;
 	int alen;
 	int plen;
+	int ivlen;
 	int tfclen;
 	int nfrags;
 	int assoclen;
-	int sglists;
 	int seqhilen;
 	u8 *iv;
 	u8 *tail;
 	__be32 *seqhi;
+	__be64 seqno;
 
 	/* skb is pure payload to encrypt */
 	aead = x->data;
 	alen = crypto_aead_authsize(aead);
+	ivlen = crypto_aead_ivsize(aead);
 
 	tfclen = 0;
 	if (x->tfcpad) {
@@ -187,16 +193,14 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb)
 	nfrags = err;
 
 	assoclen = sizeof(*esph);
-	sglists = 1;
 	seqhilen = 0;
 
 	if (x->props.flags & XFRM_STATE_ESN) {
-		sglists += 2;
 		seqhilen += sizeof(__be32);
 		assoclen += seqhilen;
 	}
 
-	tmp = esp_alloc_tmp(aead, nfrags + sglists, seqhilen);
+	tmp = esp_alloc_tmp(aead, nfrags, seqhilen);
 	if (!tmp) {
 		err = -ENOMEM;
 		goto error;
@@ -204,9 +208,8 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb)
 
 	seqhi = esp_tmp_seqhi(tmp);
 	iv = esp_tmp_iv(aead, tmp, seqhilen);
-	req = esp_tmp_givreq(aead, iv);
-	asg = esp_givreq_sg(aead, req);
-	sg = asg + sglists;
+	req = esp_tmp_req(aead, iv);
+	sg = esp_req_sg(aead, req);
 
 	/* Fill padding... */
 	tail = skb_tail_pointer(trailer);
@@ -227,37 +230,53 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb)
 	esph = ip_esp_hdr(skb);
 	*skb_mac_header(skb) = IPPROTO_ESP;
 
-	esph->spi = x->id.spi;
 	esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low);
 
+	aead_request_set_callback(req, 0, esp_output_done, skb);
+
+	/* For ESN we move the header forward by 4 bytes to
+	 * accomodate the high bits.  We will move it back after
+	 * encryption.
+	 */
+	if ((x->props.flags & XFRM_STATE_ESN)) {
+		esph = (void *)(skb_transport_header(skb) - sizeof(__be32));
+		*seqhi = esph->spi;
+		esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.hi);
+		aead_request_set_callback(req, 0, esp_output_done_esn, skb);
+	}
+
+	esph->spi = x->id.spi;
+
 	sg_init_table(sg, nfrags);
 	skb_to_sgvec(skb, sg,
-		     esph->enc_data + crypto_aead_ivsize(aead) - skb->data,
-		     clen + alen);
+		     (unsigned char *)esph - skb->data,
+		     assoclen + ivlen + clen + alen);
 
-	if ((x->props.flags & XFRM_STATE_ESN)) {
-		sg_init_table(asg, 3);
-		sg_set_buf(asg, &esph->spi, sizeof(__be32));
-		*seqhi = htonl(XFRM_SKB_CB(skb)->seq.output.hi);
-		sg_set_buf(asg + 1, seqhi, seqhilen);
-		sg_set_buf(asg + 2, &esph->seq_no, sizeof(__be32));
-	} else
-		sg_init_one(asg, esph, sizeof(*esph));
-
-	aead_givcrypt_set_callback(req, 0, esp_output_done, skb);
-	aead_givcrypt_set_crypt(req, sg, sg, clen, iv);
-	aead_givcrypt_set_assoc(req, asg, assoclen);
-	aead_givcrypt_set_giv(req, esph->enc_data,
-			      XFRM_SKB_CB(skb)->seq.output.low +
-			      ((u64)XFRM_SKB_CB(skb)->seq.output.hi << 32));
+	aead_request_set_crypt(req, sg, sg, ivlen + clen, iv);
+	aead_request_set_ad(req, assoclen);
+
+	seqno = cpu_to_be64(XFRM_SKB_CB(skb)->seq.output.low +
+			    ((u64)XFRM_SKB_CB(skb)->seq.output.hi << 32));
+
+	memset(iv, 0, ivlen);
+	memcpy(iv + ivlen - min(ivlen, 8), (u8 *)&seqno + 8 - min(ivlen, 8),
+	       min(ivlen, 8));
 
 	ESP_SKB_CB(skb)->tmp = tmp;
-	err = crypto_aead_givencrypt(req);
-	if (err == -EINPROGRESS)
+	err = crypto_aead_encrypt(req);
+
+	switch (err) {
+	case -EINPROGRESS:
 		goto error;
 
-	if (err == -EBUSY)
+	case -EBUSY:
 		err = NET_XMIT_DROP;
+		break;
+
+	case 0:
+		if ((x->props.flags & XFRM_STATE_ESN))
+			esp_output_restore_header(skb);
+	}
 
 	kfree(tmp);
 
@@ -318,25 +337,38 @@ static void esp_input_done(struct crypto_async_request *base, int err)
 	xfrm_input_resume(skb, esp_input_done2(skb, err));
 }
 
+static void esp_input_restore_header(struct sk_buff *skb)
+{
+	esp_restore_header(skb, 0);
+	__skb_pull(skb, 4);
+}
+
+static void esp_input_done_esn(struct crypto_async_request *base, int err)
+{
+	struct sk_buff *skb = base->data;
+
+	esp_input_restore_header(skb);
+	esp_input_done(base, err);
+}
+
 static int esp6_input(struct xfrm_state *x, struct sk_buff *skb)
 {
 	struct ip_esp_hdr *esph;
 	struct crypto_aead *aead = x->data;
 	struct aead_request *req;
 	struct sk_buff *trailer;
-	int elen = skb->len - sizeof(*esph) - crypto_aead_ivsize(aead);
+	int ivlen = crypto_aead_ivsize(aead);
+	int elen = skb->len - sizeof(*esph) - ivlen;
 	int nfrags;
 	int assoclen;
-	int sglists;
 	int seqhilen;
 	int ret = 0;
 	void *tmp;
 	__be32 *seqhi;
 	u8 *iv;
 	struct scatterlist *sg;
-	struct scatterlist *asg;
 
-	if (!pskb_may_pull(skb, sizeof(*esph) + crypto_aead_ivsize(aead))) {
+	if (!pskb_may_pull(skb, sizeof(*esph) + ivlen)) {
 		ret = -EINVAL;
 		goto out;
 	}
@@ -355,16 +387,14 @@ static int esp6_input(struct xfrm_state *x, struct sk_buff *skb)
 	ret = -ENOMEM;
 
 	assoclen = sizeof(*esph);
-	sglists = 1;
 	seqhilen = 0;
 
 	if (x->props.flags & XFRM_STATE_ESN) {
-		sglists += 2;
 		seqhilen += sizeof(__be32);
 		assoclen += seqhilen;
 	}
 
-	tmp = esp_alloc_tmp(aead, nfrags + sglists, seqhilen);
+	tmp = esp_alloc_tmp(aead, nfrags, seqhilen);
 	if (!tmp)
 		goto out;
 
@@ -372,36 +402,39 @@ static int esp6_input(struct xfrm_state *x, struct sk_buff *skb)
 	seqhi = esp_tmp_seqhi(tmp);
 	iv = esp_tmp_iv(aead, tmp, seqhilen);
 	req = esp_tmp_req(aead, iv);
-	asg = esp_req_sg(aead, req);
-	sg = asg + sglists;
+	sg = esp_req_sg(aead, req);
 
 	skb->ip_summed = CHECKSUM_NONE;
 
 	esph = (struct ip_esp_hdr *)skb->data;
 
-	/* Get ivec. This can be wrong, check against another impls. */
-	iv = esph->enc_data;
-
-	sg_init_table(sg, nfrags);
-	skb_to_sgvec(skb, sg, sizeof(*esph) + crypto_aead_ivsize(aead), elen);
+	aead_request_set_callback(req, 0, esp_input_done, skb);
 
+	/* For ESN we move the header forward by 4 bytes to
+	 * accomodate the high bits.  We will move it back after
+	 * decryption.
+	 */
 	if ((x->props.flags & XFRM_STATE_ESN)) {
-		sg_init_table(asg, 3);
-		sg_set_buf(asg, &esph->spi, sizeof(__be32));
-		*seqhi = XFRM_SKB_CB(skb)->seq.input.hi;
-		sg_set_buf(asg + 1, seqhi, seqhilen);
-		sg_set_buf(asg + 2, &esph->seq_no, sizeof(__be32));
-	} else
-		sg_init_one(asg, esph, sizeof(*esph));
+		esph = (void *)skb_push(skb, 4);
+		*seqhi = esph->spi;
+		esph->spi = esph->seq_no;
+		esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.input.hi);
+		aead_request_set_callback(req, 0, esp_input_done_esn, skb);
+	}
 
-	aead_request_set_callback(req, 0, esp_input_done, skb);
-	aead_request_set_crypt(req, sg, sg, elen, iv);
-	aead_request_set_assoc(req, asg, assoclen);
+	sg_init_table(sg, nfrags);
+	skb_to_sgvec(skb, sg, 0, skb->len);
+
+	aead_request_set_crypt(req, sg, sg, elen + ivlen, iv);
+	aead_request_set_ad(req, assoclen);
 
 	ret = crypto_aead_decrypt(req);
 	if (ret == -EINPROGRESS)
 		goto out;
 
+	if ((x->props.flags & XFRM_STATE_ESN))
+		esp_input_restore_header(skb);
+
 	ret = esp_input_done2(skb, ret);
 
 out:
@@ -461,10 +494,16 @@ static void esp6_destroy(struct xfrm_state *x)
 
 static int esp_init_aead(struct xfrm_state *x)
 {
+	char aead_name[CRYPTO_MAX_ALG_NAME];
 	struct crypto_aead *aead;
 	int err;
 
-	aead = crypto_alloc_aead(x->aead->alg_name, 0, 0);
+	err = -ENAMETOOLONG;
+	if (snprintf(aead_name, CRYPTO_MAX_ALG_NAME, "%s(%s)",
+		     x->geniv, x->aead->alg_name) >= CRYPTO_MAX_ALG_NAME)
+		goto error;
+
+	aead = crypto_alloc_aead(aead_name, 0, 0);
 	err = PTR_ERR(aead);
 	if (IS_ERR(aead))
 		goto error;
@@ -503,15 +542,19 @@ static int esp_init_authenc(struct xfrm_state *x)
 
 	if ((x->props.flags & XFRM_STATE_ESN)) {
 		if (snprintf(authenc_name, CRYPTO_MAX_ALG_NAME,
-			     "authencesn(%s,%s)",
+			     "%s%sauthencesn(%s,%s)%s",
+			     x->geniv ?: "", x->geniv ? "(" : "",
 			     x->aalg ? x->aalg->alg_name : "digest_null",
-			     x->ealg->alg_name) >= CRYPTO_MAX_ALG_NAME)
+			     x->ealg->alg_name,
+			     x->geniv ? ")" : "") >= CRYPTO_MAX_ALG_NAME)
 			goto error;
 	} else {
 		if (snprintf(authenc_name, CRYPTO_MAX_ALG_NAME,
-			     "authenc(%s,%s)",
+			     "%s%sauthenc(%s,%s)%s",
+			     x->geniv ?: "", x->geniv ? "(" : "",
 			     x->aalg ? x->aalg->alg_name : "digest_null",
-			     x->ealg->alg_name) >= CRYPTO_MAX_ALG_NAME)
+			     x->ealg->alg_name,
+			     x->geniv ? ")" : "") >= CRYPTO_MAX_ALG_NAME)
 			goto error;
 	}
 
diff --git a/net/key/af_key.c b/net/key/af_key.c
index f0d52d721b3a..3c5b8ce38ef4 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -1190,6 +1190,7 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct net *net,
 				memcpy(x->ealg->alg_key, key+1, keysize);
 			}
 			x->props.ealgo = sa->sadb_sa_encrypt;
+			x->geniv = a->uinfo.encr.geniv;
 		}
 	}
 	/* x->algo.flags = sa->sadb_sa_flags; */
diff --git a/net/mac80211/aes_ccm.c b/net/mac80211/aes_ccm.c
index 208df7c0b6ea..7663c28ba353 100644
--- a/net/mac80211/aes_ccm.c
+++ b/net/mac80211/aes_ccm.c
@@ -11,9 +11,8 @@
 
 #include <linux/kernel.h>
 #include <linux/types.h>
-#include <linux/crypto.h>
 #include <linux/err.h>
-#include <crypto/aes.h>
+#include <crypto/aead.h>
 
 #include <net/mac80211.h>
 #include "key.h"
@@ -23,7 +22,7 @@ void ieee80211_aes_ccm_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad,
 			       u8 *data, size_t data_len, u8 *mic,
 			       size_t mic_len)
 {
-	struct scatterlist assoc, pt, ct[2];
+	struct scatterlist sg[3];
 
 	char aead_req_data[sizeof(struct aead_request) +
 			   crypto_aead_reqsize(tfm)]
@@ -32,15 +31,14 @@ void ieee80211_aes_ccm_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad,
 
 	memset(aead_req, 0, sizeof(aead_req_data));
 
-	sg_init_one(&pt, data, data_len);
-	sg_init_one(&assoc, &aad[2], be16_to_cpup((__be16 *)aad));
-	sg_init_table(ct, 2);
-	sg_set_buf(&ct[0], data, data_len);
-	sg_set_buf(&ct[1], mic, mic_len);
+	sg_init_table(sg, 3);
+	sg_set_buf(&sg[0], &aad[2], be16_to_cpup((__be16 *)aad));
+	sg_set_buf(&sg[1], data, data_len);
+	sg_set_buf(&sg[2], mic, mic_len);
 
 	aead_request_set_tfm(aead_req, tfm);
-	aead_request_set_assoc(aead_req, &assoc, assoc.length);
-	aead_request_set_crypt(aead_req, &pt, ct, data_len, b_0);
+	aead_request_set_crypt(aead_req, sg, sg, data_len, b_0);
+	aead_request_set_ad(aead_req, sg[0].length);
 
 	crypto_aead_encrypt(aead_req);
 }
@@ -49,7 +47,7 @@ int ieee80211_aes_ccm_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad,
 			      u8 *data, size_t data_len, u8 *mic,
 			      size_t mic_len)
 {
-	struct scatterlist assoc, pt, ct[2];
+	struct scatterlist sg[3];
 	char aead_req_data[sizeof(struct aead_request) +
 			   crypto_aead_reqsize(tfm)]
 		__aligned(__alignof__(struct aead_request));
@@ -60,15 +58,14 @@ int ieee80211_aes_ccm_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad,
 
 	memset(aead_req, 0, sizeof(aead_req_data));
 
-	sg_init_one(&pt, data, data_len);
-	sg_init_one(&assoc, &aad[2], be16_to_cpup((__be16 *)aad));
-	sg_init_table(ct, 2);
-	sg_set_buf(&ct[0], data, data_len);
-	sg_set_buf(&ct[1], mic, mic_len);
+	sg_init_table(sg, 3);
+	sg_set_buf(&sg[0], &aad[2], be16_to_cpup((__be16 *)aad));
+	sg_set_buf(&sg[1], data, data_len);
+	sg_set_buf(&sg[2], mic, mic_len);
 
 	aead_request_set_tfm(aead_req, tfm);
-	aead_request_set_assoc(aead_req, &assoc, assoc.length);
-	aead_request_set_crypt(aead_req, ct, &pt, data_len + mic_len, b_0);
+	aead_request_set_crypt(aead_req, sg, sg, data_len + mic_len, b_0);
+	aead_request_set_ad(aead_req, sg[0].length);
 
 	return crypto_aead_decrypt(aead_req);
 }
diff --git a/net/mac80211/aes_gcm.c b/net/mac80211/aes_gcm.c
index fd278bbe1b0d..3afe361fd27c 100644
--- a/net/mac80211/aes_gcm.c
+++ b/net/mac80211/aes_gcm.c
@@ -8,9 +8,8 @@
 
 #include <linux/kernel.h>
 #include <linux/types.h>
-#include <linux/crypto.h>
 #include <linux/err.h>
-#include <crypto/aes.h>
+#include <crypto/aead.h>
 
 #include <net/mac80211.h>
 #include "key.h"
@@ -19,7 +18,7 @@
 void ieee80211_aes_gcm_encrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad,
 			       u8 *data, size_t data_len, u8 *mic)
 {
-	struct scatterlist assoc, pt, ct[2];
+	struct scatterlist sg[3];
 
 	char aead_req_data[sizeof(struct aead_request) +
 			   crypto_aead_reqsize(tfm)]
@@ -28,15 +27,14 @@ void ieee80211_aes_gcm_encrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad,
 
 	memset(aead_req, 0, sizeof(aead_req_data));
 
-	sg_init_one(&pt, data, data_len);
-	sg_init_one(&assoc, &aad[2], be16_to_cpup((__be16 *)aad));
-	sg_init_table(ct, 2);
-	sg_set_buf(&ct[0], data, data_len);
-	sg_set_buf(&ct[1], mic, IEEE80211_GCMP_MIC_LEN);
+	sg_init_table(sg, 3);
+	sg_set_buf(&sg[0], &aad[2], be16_to_cpup((__be16 *)aad));
+	sg_set_buf(&sg[1], data, data_len);
+	sg_set_buf(&sg[2], mic, IEEE80211_GCMP_MIC_LEN);
 
 	aead_request_set_tfm(aead_req, tfm);
-	aead_request_set_assoc(aead_req, &assoc, assoc.length);
-	aead_request_set_crypt(aead_req, &pt, ct, data_len, j_0);
+	aead_request_set_crypt(aead_req, sg, sg, data_len, j_0);
+	aead_request_set_ad(aead_req, sg[0].length);
 
 	crypto_aead_encrypt(aead_req);
 }
@@ -44,7 +42,7 @@ void ieee80211_aes_gcm_encrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad,
 int ieee80211_aes_gcm_decrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad,
 			      u8 *data, size_t data_len, u8 *mic)
 {
-	struct scatterlist assoc, pt, ct[2];
+	struct scatterlist sg[3];
 	char aead_req_data[sizeof(struct aead_request) +
 			   crypto_aead_reqsize(tfm)]
 		__aligned(__alignof__(struct aead_request));
@@ -55,16 +53,15 @@ int ieee80211_aes_gcm_decrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad,
 
 	memset(aead_req, 0, sizeof(aead_req_data));
 
-	sg_init_one(&pt, data, data_len);
-	sg_init_one(&assoc, &aad[2], be16_to_cpup((__be16 *)aad));
-	sg_init_table(ct, 2);
-	sg_set_buf(&ct[0], data, data_len);
-	sg_set_buf(&ct[1], mic, IEEE80211_GCMP_MIC_LEN);
+	sg_init_table(sg, 3);
+	sg_set_buf(&sg[0], &aad[2], be16_to_cpup((__be16 *)aad));
+	sg_set_buf(&sg[1], data, data_len);
+	sg_set_buf(&sg[2], mic, IEEE80211_GCMP_MIC_LEN);
 
 	aead_request_set_tfm(aead_req, tfm);
-	aead_request_set_assoc(aead_req, &assoc, assoc.length);
-	aead_request_set_crypt(aead_req, ct, &pt,
+	aead_request_set_crypt(aead_req, sg, sg,
 			       data_len + IEEE80211_GCMP_MIC_LEN, j_0);
+	aead_request_set_ad(aead_req, sg[0].length);
 
 	return crypto_aead_decrypt(aead_req);
 }
diff --git a/net/mac80211/aes_gmac.c b/net/mac80211/aes_gmac.c
index f1321b7d6506..3ddd927aaf30 100644
--- a/net/mac80211/aes_gmac.c
+++ b/net/mac80211/aes_gmac.c
@@ -9,8 +9,8 @@
 
 #include <linux/kernel.h>
 #include <linux/types.h>
-#include <linux/crypto.h>
 #include <linux/err.h>
+#include <crypto/aead.h>
 #include <crypto/aes.h>
 
 #include <net/mac80211.h>
@@ -24,7 +24,7 @@
 int ieee80211_aes_gmac(struct crypto_aead *tfm, const u8 *aad, u8 *nonce,
 		       const u8 *data, size_t data_len, u8 *mic)
 {
-	struct scatterlist sg[3], ct[1];
+	struct scatterlist sg[4];
 	char aead_req_data[sizeof(struct aead_request) +
 			   crypto_aead_reqsize(tfm)]
 		__aligned(__alignof__(struct aead_request));
@@ -37,21 +37,19 @@ int ieee80211_aes_gmac(struct crypto_aead *tfm, const u8 *aad, u8 *nonce,
 	memset(aead_req, 0, sizeof(aead_req_data));
 
 	memset(zero, 0, GMAC_MIC_LEN);
-	sg_init_table(sg, 3);
+	sg_init_table(sg, 4);
 	sg_set_buf(&sg[0], aad, AAD_LEN);
 	sg_set_buf(&sg[1], data, data_len - GMAC_MIC_LEN);
 	sg_set_buf(&sg[2], zero, GMAC_MIC_LEN);
+	sg_set_buf(&sg[3], mic, GMAC_MIC_LEN);
 
 	memcpy(iv, nonce, GMAC_NONCE_LEN);
 	memset(iv + GMAC_NONCE_LEN, 0, sizeof(iv) - GMAC_NONCE_LEN);
 	iv[AES_BLOCK_SIZE - 1] = 0x01;
 
-	sg_init_table(ct, 1);
-	sg_set_buf(&ct[0], mic, GMAC_MIC_LEN);
-
 	aead_request_set_tfm(aead_req, tfm);
-	aead_request_set_assoc(aead_req, sg, AAD_LEN + data_len);
-	aead_request_set_crypt(aead_req, NULL, ct, 0, iv);
+	aead_request_set_crypt(aead_req, sg, sg, 0, iv);
+	aead_request_set_ad(aead_req, AAD_LEN + data_len);
 
 	crypto_aead_encrypt(aead_req);
 
diff --git a/net/mac802154/llsec.c b/net/mac802154/llsec.c
index 5b2be12832e6..985e9394e2af 100644
--- a/net/mac802154/llsec.c
+++ b/net/mac802154/llsec.c
@@ -17,8 +17,9 @@
 #include <linux/err.h>
 #include <linux/bug.h>
 #include <linux/completion.h>
+#include <linux/crypto.h>
 #include <linux/ieee802154.h>
-#include <crypto/algapi.h>
+#include <crypto/aead.h>
 
 #include "ieee802154_i.h"
 #include "llsec.h"
@@ -649,7 +650,7 @@ llsec_do_encrypt_auth(struct sk_buff *skb, const struct mac802154_llsec *sec,
 	u8 iv[16];
 	unsigned char *data;
 	int authlen, assoclen, datalen, rc;
-	struct scatterlist src, assoc[2], dst[2];
+	struct scatterlist sg;
 	struct aead_request *req;
 
 	authlen = ieee802154_sechdr_authtag_len(&hdr->sec);
@@ -659,30 +660,23 @@ llsec_do_encrypt_auth(struct sk_buff *skb, const struct mac802154_llsec *sec,
 	if (!req)
 		return -ENOMEM;
 
-	sg_init_table(assoc, 2);
-	sg_set_buf(&assoc[0], skb_mac_header(skb), skb->mac_len);
 	assoclen = skb->mac_len;
 
 	data = skb_mac_header(skb) + skb->mac_len;
 	datalen = skb_tail_pointer(skb) - data;
 
-	if (hdr->sec.level & IEEE802154_SCF_SECLEVEL_ENC) {
-		sg_set_buf(&assoc[1], data, 0);
-	} else {
-		sg_set_buf(&assoc[1], data, datalen);
+	skb_put(skb, authlen);
+
+	sg_init_one(&sg, skb_mac_header(skb), assoclen + datalen + authlen);
+
+	if (!(hdr->sec.level & IEEE802154_SCF_SECLEVEL_ENC)) {
 		assoclen += datalen;
 		datalen = 0;
 	}
 
-	sg_init_one(&src, data, datalen);
-
-	sg_init_table(dst, 2);
-	sg_set_buf(&dst[0], data, datalen);
-	sg_set_buf(&dst[1], skb_put(skb, authlen), authlen);
-
 	aead_request_set_callback(req, 0, NULL, NULL);
-	aead_request_set_assoc(req, assoc, assoclen);
-	aead_request_set_crypt(req, &src, dst, datalen, iv);
+	aead_request_set_crypt(req, &sg, &sg, datalen, iv);
+	aead_request_set_ad(req, assoclen);
 
 	rc = crypto_aead_encrypt(req);
 
@@ -858,7 +852,7 @@ llsec_do_decrypt_auth(struct sk_buff *skb, const struct mac802154_llsec *sec,
 	u8 iv[16];
 	unsigned char *data;
 	int authlen, datalen, assoclen, rc;
-	struct scatterlist src, assoc[2];
+	struct scatterlist sg;
 	struct aead_request *req;
 
 	authlen = ieee802154_sechdr_authtag_len(&hdr->sec);
@@ -868,27 +862,21 @@ llsec_do_decrypt_auth(struct sk_buff *skb, const struct mac802154_llsec *sec,
 	if (!req)
 		return -ENOMEM;
 
-	sg_init_table(assoc, 2);
-	sg_set_buf(&assoc[0], skb_mac_header(skb), skb->mac_len);
 	assoclen = skb->mac_len;
 
 	data = skb_mac_header(skb) + skb->mac_len;
 	datalen = skb_tail_pointer(skb) - data;
 
-	if (hdr->sec.level & IEEE802154_SCF_SECLEVEL_ENC) {
-		sg_set_buf(&assoc[1], data, 0);
-	} else {
-		sg_set_buf(&assoc[1], data, datalen - authlen);
+	sg_init_one(&sg, skb_mac_header(skb), assoclen + datalen);
+
+	if (!(hdr->sec.level & IEEE802154_SCF_SECLEVEL_ENC)) {
 		assoclen += datalen - authlen;
-		data += datalen - authlen;
 		datalen = authlen;
 	}
 
-	sg_init_one(&src, data, datalen);
-
 	aead_request_set_callback(req, 0, NULL, NULL);
-	aead_request_set_assoc(req, assoc, assoclen);
-	aead_request_set_crypt(req, &src, &src, datalen, iv);
+	aead_request_set_crypt(req, &sg, &sg, datalen, iv);
+	aead_request_set_ad(req, assoclen);
 
 	rc = crypto_aead_decrypt(req);
 
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 1e1c89e51a11..73a123daa2cc 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1885,13 +1885,10 @@ EXPORT_SYMBOL(tcf_destroy_chain);
 #ifdef CONFIG_PROC_FS
 static int psched_show(struct seq_file *seq, void *v)
 {
-	struct timespec ts;
-
-	hrtimer_get_res(CLOCK_MONOTONIC, &ts);
 	seq_printf(seq, "%08x %08x %08x %08x\n",
 		   (u32)NSEC_PER_USEC, (u32)PSCHED_TICKS2NS(1),
 		   1000000,
-		   (u32)NSEC_PER_SEC/(u32)ktime_to_ns(timespec_to_ktime(ts)));
+		   (u32)NSEC_PER_SEC / hrtimer_resolution);
 
 	return 0;
 }
diff --git a/net/xfrm/xfrm_algo.c b/net/xfrm/xfrm_algo.c
index 12e82a5e4ad5..42f7c76cf853 100644
--- a/net/xfrm/xfrm_algo.c
+++ b/net/xfrm/xfrm_algo.c
@@ -31,6 +31,7 @@ static struct xfrm_algo_desc aead_list[] = {
 
 	.uinfo = {
 		.aead = {
+			.geniv = "seqniv",
 			.icv_truncbits = 64,
 		}
 	},
@@ -49,6 +50,7 @@ static struct xfrm_algo_desc aead_list[] = {
 
 	.uinfo = {
 		.aead = {
+			.geniv = "seqniv",
 			.icv_truncbits = 96,
 		}
 	},
@@ -67,6 +69,7 @@ static struct xfrm_algo_desc aead_list[] = {
 
 	.uinfo = {
 		.aead = {
+			.geniv = "seqniv",
 			.icv_truncbits = 128,
 		}
 	},
@@ -85,6 +88,7 @@ static struct xfrm_algo_desc aead_list[] = {
 
 	.uinfo = {
 		.aead = {
+			.geniv = "seqniv",
 			.icv_truncbits = 64,
 		}
 	},
@@ -103,6 +107,7 @@ static struct xfrm_algo_desc aead_list[] = {
 
 	.uinfo = {
 		.aead = {
+			.geniv = "seqniv",
 			.icv_truncbits = 96,
 		}
 	},
@@ -121,6 +126,7 @@ static struct xfrm_algo_desc aead_list[] = {
 
 	.uinfo = {
 		.aead = {
+			.geniv = "seqniv",
 			.icv_truncbits = 128,
 		}
 	},
@@ -139,6 +145,7 @@ static struct xfrm_algo_desc aead_list[] = {
 
 	.uinfo = {
 		.aead = {
+			.geniv = "seqiv",
 			.icv_truncbits = 128,
 		}
 	},
@@ -152,6 +159,18 @@ static struct xfrm_algo_desc aead_list[] = {
 		.sadb_alg_maxbits = 256
 	}
 },
+{
+	.name = "rfc7539esp(chacha20,poly1305)",
+
+	.uinfo = {
+		.aead = {
+			.geniv = "seqniv",
+			.icv_truncbits = 128,
+		}
+	},
+
+	.pfkey_supported = 0,
+},
 };
 
 static struct xfrm_algo_desc aalg_list[] = {
@@ -353,6 +372,7 @@ static struct xfrm_algo_desc ealg_list[] = {
 
 	.uinfo = {
 		.encr = {
+			.geniv = "echainiv",
 			.blockbits = 64,
 			.defkeybits = 64,
 		}
@@ -373,6 +393,7 @@ static struct xfrm_algo_desc ealg_list[] = {
 
 	.uinfo = {
 		.encr = {
+			.geniv = "echainiv",
 			.blockbits = 64,
 			.defkeybits = 192,
 		}
@@ -393,6 +414,7 @@ static struct xfrm_algo_desc ealg_list[] = {
 
 	.uinfo = {
 		.encr = {
+			.geniv = "echainiv",
 			.blockbits = 64,
 			.defkeybits = 128,
 		}
@@ -413,6 +435,7 @@ static struct xfrm_algo_desc ealg_list[] = {
 
 	.uinfo = {
 		.encr = {
+			.geniv = "echainiv",
 			.blockbits = 64,
 			.defkeybits = 128,
 		}
@@ -433,6 +456,7 @@ static struct xfrm_algo_desc ealg_list[] = {
 
 	.uinfo = {
 		.encr = {
+			.geniv = "echainiv",
 			.blockbits = 128,
 			.defkeybits = 128,
 		}
@@ -453,6 +477,7 @@ static struct xfrm_algo_desc ealg_list[] = {
 
 	.uinfo = {
 		.encr = {
+			.geniv = "echainiv",
 			.blockbits = 128,
 			.defkeybits = 128,
 		}
@@ -473,6 +498,7 @@ static struct xfrm_algo_desc ealg_list[] = {
 
 	.uinfo = {
 		.encr = {
+			.geniv = "echainiv",
 			.blockbits = 128,
 			.defkeybits = 128,
 		}
@@ -493,6 +519,7 @@ static struct xfrm_algo_desc ealg_list[] = {
 
 	.uinfo = {
 		.encr = {
+			.geniv = "echainiv",
 			.blockbits = 128,
 			.defkeybits = 128,
 		}
@@ -512,6 +539,7 @@ static struct xfrm_algo_desc ealg_list[] = {
 
 	.uinfo = {
 		.encr = {
+			.geniv = "seqiv",
 			.blockbits = 128,
 			.defkeybits = 160, /* 128-bit key + 32-bit nonce */
 		}
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 2091664295ba..bd16c6c7e1e7 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -289,6 +289,31 @@ static int attach_one_algo(struct xfrm_algo **algpp, u8 *props,
 	return 0;
 }
 
+static int attach_crypt(struct xfrm_state *x, struct nlattr *rta)
+{
+	struct xfrm_algo *p, *ualg;
+	struct xfrm_algo_desc *algo;
+
+	if (!rta)
+		return 0;
+
+	ualg = nla_data(rta);
+
+	algo = xfrm_ealg_get_byname(ualg->alg_name, 1);
+	if (!algo)
+		return -ENOSYS;
+	x->props.ealgo = algo->desc.sadb_alg_id;
+
+	p = kmemdup(ualg, xfrm_alg_len(ualg), GFP_KERNEL);
+	if (!p)
+		return -ENOMEM;
+
+	strcpy(p->alg_name, algo->name);
+	x->ealg = p;
+	x->geniv = algo->uinfo.encr.geniv;
+	return 0;
+}
+
 static int attach_auth(struct xfrm_algo_auth **algpp, u8 *props,
 		       struct nlattr *rta)
 {
@@ -349,8 +374,7 @@ static int attach_auth_trunc(struct xfrm_algo_auth **algpp, u8 *props,
 	return 0;
 }
 
-static int attach_aead(struct xfrm_algo_aead **algpp, u8 *props,
-		       struct nlattr *rta)
+static int attach_aead(struct xfrm_state *x, struct nlattr *rta)
 {
 	struct xfrm_algo_aead *p, *ualg;
 	struct xfrm_algo_desc *algo;
@@ -363,14 +387,15 @@ static int attach_aead(struct xfrm_algo_aead **algpp, u8 *props,
 	algo = xfrm_aead_get_byname(ualg->alg_name, ualg->alg_icv_len, 1);
 	if (!algo)
 		return -ENOSYS;
-	*props = algo->desc.sadb_alg_id;
+	x->props.ealgo = algo->desc.sadb_alg_id;
 
 	p = kmemdup(ualg, aead_len(ualg), GFP_KERNEL);
 	if (!p)
 		return -ENOMEM;
 
 	strcpy(p->alg_name, algo->name);
-	*algpp = p;
+	x->aead = p;
+	x->geniv = algo->uinfo.aead.geniv;
 	return 0;
 }
 
@@ -515,8 +540,7 @@ static struct xfrm_state *xfrm_state_construct(struct net *net,
 	if (attrs[XFRMA_SA_EXTRA_FLAGS])
 		x->props.extra_flags = nla_get_u32(attrs[XFRMA_SA_EXTRA_FLAGS]);
 
-	if ((err = attach_aead(&x->aead, &x->props.ealgo,
-			       attrs[XFRMA_ALG_AEAD])))
+	if ((err = attach_aead(x, attrs[XFRMA_ALG_AEAD])))
 		goto error;
 	if ((err = attach_auth_trunc(&x->aalg, &x->props.aalgo,
 				     attrs[XFRMA_ALG_AUTH_TRUNC])))
@@ -526,9 +550,7 @@ static struct xfrm_state *xfrm_state_construct(struct net *net,
 				       attrs[XFRMA_ALG_AUTH])))
 			goto error;
 	}
-	if ((err = attach_one_algo(&x->ealg, &x->props.ealgo,
-				   xfrm_ealg_get_byname,
-				   attrs[XFRMA_ALG_CRYPT])))
+	if ((err = attach_crypt(x, attrs[XFRMA_ALG_CRYPT])))
 		goto error;
 	if ((err = attach_one_algo(&x->calg, &x->props.calgo,
 				   xfrm_calg_get_byname,
diff --git a/scripts/checksyscalls.sh b/scripts/checksyscalls.sh
index 5b3add31f9f1..2c9082ba6137 100755
--- a/scripts/checksyscalls.sh
+++ b/scripts/checksyscalls.sh
@@ -212,5 +212,5 @@ EOF
     )
 }
 
-(ignore_list && syscall_list $(dirname $0)/../arch/x86/syscalls/syscall_32.tbl) | \
+(ignore_list && syscall_list $(dirname $0)/../arch/x86/entry/syscalls/syscall_32.tbl) | \
 $* -E -x c - > /dev/null
diff --git a/security/capability.c b/security/capability.c
index 0d03fcc489a4..7d3f38fe02ba 100644
--- a/security/capability.c
+++ b/security/capability.c
@@ -209,8 +209,8 @@ static int cap_inode_readlink(struct dentry *dentry)
 	return 0;
 }
 
-static int cap_inode_follow_link(struct dentry *dentry,
-				 struct nameidata *nameidata)
+static int cap_inode_follow_link(struct dentry *dentry, struct inode *inode,
+				 bool rcu)
 {
 	return 0;
 }
diff --git a/security/security.c b/security/security.c
index 8e9b1f4b9b45..04c8feca081a 100644
--- a/security/security.c
+++ b/security/security.c
@@ -581,11 +581,12 @@ int security_inode_readlink(struct dentry *dentry)
 	return security_ops->inode_readlink(dentry);
 }
 
-int security_inode_follow_link(struct dentry *dentry, struct nameidata *nd)
+int security_inode_follow_link(struct dentry *dentry, struct inode *inode,
+			       bool rcu)
 {
-	if (unlikely(IS_PRIVATE(d_backing_inode(dentry))))
+	if (unlikely(IS_PRIVATE(inode)))
 		return 0;
-	return security_ops->inode_follow_link(dentry, nd);
+	return security_ops->inode_follow_link(dentry, inode, rcu);
 }
 
 int security_inode_permission(struct inode *inode, int mask)
diff --git a/security/selinux/avc.c b/security/selinux/avc.c
index 3c17dda9571d..0b122b1421a9 100644
--- a/security/selinux/avc.c
+++ b/security/selinux/avc.c
@@ -761,7 +761,23 @@ int avc_has_perm(u32 ssid, u32 tsid, u16 tclass,
 
 	rc = avc_has_perm_noaudit(ssid, tsid, tclass, requested, 0, &avd);
 
-	rc2 = avc_audit(ssid, tsid, tclass, requested, &avd, rc, auditdata);
+	rc2 = avc_audit(ssid, tsid, tclass, requested, &avd, rc, auditdata, 0);
+	if (rc2)
+		return rc2;
+	return rc;
+}
+
+int avc_has_perm_flags(u32 ssid, u32 tsid, u16 tclass,
+		       u32 requested, struct common_audit_data *auditdata,
+		       int flags)
+{
+	struct av_decision avd;
+	int rc, rc2;
+
+	rc = avc_has_perm_noaudit(ssid, tsid, tclass, requested, 0, &avd);
+
+	rc2 = avc_audit(ssid, tsid, tclass, requested, &avd, rc,
+			auditdata, flags);
 	if (rc2)
 		return rc2;
 	return rc;
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 7dade28affba..ffa5a642629a 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -1564,7 +1564,7 @@ static int cred_has_capability(const struct cred *cred,
 
 	rc = avc_has_perm_noaudit(sid, sid, sclass, av, 0, &avd);
 	if (audit == SECURITY_CAP_AUDIT) {
-		int rc2 = avc_audit(sid, sid, sclass, av, &avd, rc, &ad);
+		int rc2 = avc_audit(sid, sid, sclass, av, &avd, rc, &ad, 0);
 		if (rc2)
 			return rc2;
 	}
@@ -2861,11 +2861,23 @@ static int selinux_inode_readlink(struct dentry *dentry)
 	return dentry_has_perm(cred, dentry, FILE__READ);
 }
 
-static int selinux_inode_follow_link(struct dentry *dentry, struct nameidata *nameidata)
+static int selinux_inode_follow_link(struct dentry *dentry, struct inode *inode,
+				     bool rcu)
 {
 	const struct cred *cred = current_cred();
+	struct common_audit_data ad;
+	struct inode_security_struct *isec;
+	u32 sid;
 
-	return dentry_has_perm(cred, dentry, FILE__READ);
+	validate_creds(cred);
+
+	ad.type = LSM_AUDIT_DATA_DENTRY;
+	ad.u.dentry = dentry;
+	sid = cred_sid(cred);
+	isec = inode->i_security;
+
+	return avc_has_perm_flags(sid, isec->sid, isec->sclass, FILE__READ, &ad,
+				  rcu ? MAY_NOT_BLOCK : 0);
 }
 
 static noinline int audit_inode_permission(struct inode *inode,
diff --git a/security/selinux/include/avc.h b/security/selinux/include/avc.h
index ddf8eec03f21..5973c327c54e 100644
--- a/security/selinux/include/avc.h
+++ b/security/selinux/include/avc.h
@@ -130,7 +130,8 @@ static inline int avc_audit(u32 ssid, u32 tsid,
 			    u16 tclass, u32 requested,
 			    struct av_decision *avd,
 			    int result,
-			    struct common_audit_data *a)
+			    struct common_audit_data *a,
+			    int flags)
 {
 	u32 audited, denied;
 	audited = avc_audit_required(requested, avd, result, 0, &denied);
@@ -138,7 +139,7 @@ static inline int avc_audit(u32 ssid, u32 tsid,
 		return 0;
 	return slow_avc_audit(ssid, tsid, tclass,
 			      requested, audited, denied, result,
-			      a, 0);
+			      a, flags);
 }
 
 #define AVC_STRICT 1 /* Ignore permissive mode. */
@@ -150,6 +151,10 @@ int avc_has_perm_noaudit(u32 ssid, u32 tsid,
 int avc_has_perm(u32 ssid, u32 tsid,
 		 u16 tclass, u32 requested,
 		 struct common_audit_data *auditdata);
+int avc_has_perm_flags(u32 ssid, u32 tsid,
+		       u16 tclass, u32 requested,
+		       struct common_audit_data *auditdata,
+		       int flags);
 
 u32 avc_policy_seqno(void);
 
diff --git a/sound/core/hrtimer.c b/sound/core/hrtimer.c
index 886be7da989d..f845ecf7e172 100644
--- a/sound/core/hrtimer.c
+++ b/sound/core/hrtimer.c
@@ -121,16 +121,9 @@ static struct snd_timer *mytimer;
 static int __init snd_hrtimer_init(void)
 {
 	struct snd_timer *timer;
-	struct timespec tp;
 	int err;
 
-	hrtimer_get_res(CLOCK_MONOTONIC, &tp);
-	if (tp.tv_sec > 0 || !tp.tv_nsec) {
-		pr_err("snd-hrtimer: Invalid resolution %u.%09u",
-			   (unsigned)tp.tv_sec, (unsigned)tp.tv_nsec);
-		return -EINVAL;
-	}
-	resolution = tp.tv_nsec;
+	resolution = hrtimer_resolution;
 
 	/* Create a new timer and set up the fields */
 	err = snd_timer_global_new("hrtimer", SNDRV_TIMER_GLOBAL_HRTIMER,
diff --git a/sound/drivers/pcsp/pcsp.c b/sound/drivers/pcsp/pcsp.c
index d9647bd84d0f..27e25bb78c97 100644
--- a/sound/drivers/pcsp/pcsp.c
+++ b/sound/drivers/pcsp/pcsp.c
@@ -42,16 +42,13 @@ struct snd_pcsp pcsp_chip;
 static int snd_pcsp_create(struct snd_card *card)
 {
 	static struct snd_device_ops ops = { };
-	struct timespec tp;
-	int err;
-	int div, min_div, order;
-
-	hrtimer_get_res(CLOCK_MONOTONIC, &tp);
+	unsigned int resolution = hrtimer_resolution;
+	int err, div, min_div, order;
 
 	if (!nopcm) {
-		if (tp.tv_sec || tp.tv_nsec > PCSP_MAX_PERIOD_NS) {
+		if (resolution > PCSP_MAX_PERIOD_NS) {
 			printk(KERN_ERR "PCSP: Timer resolution is not sufficient "
-				"(%linS)\n", tp.tv_nsec);
+				"(%unS)\n", resolution);
 			printk(KERN_ERR "PCSP: Make sure you have HPET and ACPI "
 				"enabled.\n");
 			printk(KERN_ERR "PCSP: Turned into nopcm mode.\n");
@@ -59,13 +56,13 @@ static int snd_pcsp_create(struct snd_card *card)
 		}
 	}
 
-	if (loops_per_jiffy >= PCSP_MIN_LPJ && tp.tv_nsec <= PCSP_MIN_PERIOD_NS)
+	if (loops_per_jiffy >= PCSP_MIN_LPJ && resolution <= PCSP_MIN_PERIOD_NS)
 		min_div = MIN_DIV;
 	else
 		min_div = MAX_DIV;
 #if PCSP_DEBUG
-	printk(KERN_DEBUG "PCSP: lpj=%li, min_div=%i, res=%li\n",
-	       loops_per_jiffy, min_div, tp.tv_nsec);
+	printk(KERN_DEBUG "PCSP: lpj=%li, min_div=%i, res=%u\n",
+	       loops_per_jiffy, min_div, resolution);
 #endif
 
 	div = MAX_DIV / min_div;
diff --git a/sound/mips/Kconfig b/sound/mips/Kconfig
index d2f615ab177a..2153d31fb663 100644
--- a/sound/mips/Kconfig
+++ b/sound/mips/Kconfig
@@ -12,12 +12,14 @@ if SND_MIPS
 config SND_SGI_O2
 	tristate "SGI O2 Audio"
 	depends on SGI_IP32
+	select SND_PCM
         help
                 Sound support for the SGI O2 Workstation. 
 
 config SND_SGI_HAL2
         tristate "SGI HAL2 Audio"
         depends on SGI_HAS_HAL2
+	select SND_PCM
         help
                 Sound support for the SGI Indy and Indigo2 Workstation.
 
diff --git a/sound/pci/asihpi/hpioctl.c b/sound/pci/asihpi/hpioctl.c
index 6610bd096fc9..d17937b92331 100644
--- a/sound/pci/asihpi/hpioctl.c
+++ b/sound/pci/asihpi/hpioctl.c
@@ -32,6 +32,7 @@
 #include <linux/pci.h>
 #include <linux/stringify.h>
 #include <linux/module.h>
+#include <linux/vmalloc.h>
 
 #ifdef MODULE_FIRMWARE
 MODULE_FIRMWARE("asihpi/dsp5000.bin");
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index a244ba706317..b6db25b23dd3 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -1879,7 +1879,9 @@ static int azx_probe_continue(struct azx *chip)
 #endif
 	}
 
+#ifdef CONFIG_SND_HDA_I915
  skip_i915:
+#endif
 	err = azx_first_init(chip);
 	if (err < 0)
 		goto out_free;
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 0320cb523d9e..6d010452c1f5 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -4515,6 +4515,8 @@ enum {
 	ALC288_FIXUP_DELL_HEADSET_MODE,
 	ALC288_FIXUP_DELL1_MIC_NO_PRESENCE,
 	ALC288_FIXUP_DELL_XPS_13_GPIO6,
+	ALC292_FIXUP_DELL_E7X,
+	ALC292_FIXUP_DISABLE_AAMIX,
 };
 
 static const struct hda_fixup alc269_fixups[] = {
@@ -5037,6 +5039,16 @@ static const struct hda_fixup alc269_fixups[] = {
 		.chained = true,
 		.chain_id = ALC288_FIXUP_DELL1_MIC_NO_PRESENCE
 	},
+	[ALC292_FIXUP_DISABLE_AAMIX] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc_fixup_disable_aamix,
+	},
+	[ALC292_FIXUP_DELL_E7X] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc_fixup_dell_xps13,
+		.chained = true,
+		.chain_id = ALC292_FIXUP_DISABLE_AAMIX
+	},
 };
 
 static const struct snd_pci_quirk alc269_fixup_tbl[] = {
@@ -5049,6 +5061,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1025, 0x0775, "Acer Aspire E1-572", ALC271_FIXUP_HP_GATE_MIC_JACK_E1_572),
 	SND_PCI_QUIRK(0x1025, 0x079b, "Acer Aspire V5-573G", ALC282_FIXUP_ASPIRE_V5_PINS),
 	SND_PCI_QUIRK(0x1028, 0x0470, "Dell M101z", ALC269_FIXUP_DELL_M101Z),
+	SND_PCI_QUIRK(0x1028, 0x05ca, "Dell Latitude E7240", ALC292_FIXUP_DELL_E7X),
+	SND_PCI_QUIRK(0x1028, 0x05cb, "Dell Latitude E7440", ALC292_FIXUP_DELL_E7X),
 	SND_PCI_QUIRK(0x1028, 0x05da, "Dell Vostro 5460", ALC290_FIXUP_SUBWOOFER),
 	SND_PCI_QUIRK(0x1028, 0x05f4, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x05f5, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
@@ -5058,6 +5072,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1028, 0x0638, "Dell Inspiron 5439", ALC290_FIXUP_MONO_SPEAKERS_HSJACK),
 	SND_PCI_QUIRK(0x1028, 0x064a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x064b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x1028, 0x0665, "Dell XPS 13", ALC292_FIXUP_DELL_E7X),
 	SND_PCI_QUIRK(0x1028, 0x06c7, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x06d9, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x06da, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
@@ -5637,8 +5652,7 @@ static int patch_alc269(struct hda_codec *codec)
 
 	spec = codec->spec;
 	spec->gen.shared_mic_vref_pin = 0x18;
-	if (codec->core.vendor_id != 0x10ec0292)
-		codec->power_save_node = 1;
+	codec->power_save_node = 1;
 
 	snd_hda_pick_fixup(codec, alc269_fixup_models,
 		       alc269_fixup_tbl, alc269_fixups);
diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c
index 6833c74ed6ff..6c66d7e16439 100644
--- a/sound/pci/hda/patch_sigmatel.c
+++ b/sound/pci/hda/patch_sigmatel.c
@@ -100,6 +100,7 @@ enum {
 	STAC_HP_ENVY_BASS,
 	STAC_HP_BNB13_EQ,
 	STAC_HP_ENVY_TS_BASS,
+	STAC_HP_ENVY_TS_DAC_BIND,
 	STAC_92HD83XXX_GPIO10_EAPD,
 	STAC_92HD83XXX_MODELS
 };
@@ -2171,6 +2172,22 @@ static void stac92hd83xxx_fixup_gpio10_eapd(struct hda_codec *codec,
 	spec->eapd_switch = 0;
 }
 
+static void hp_envy_ts_fixup_dac_bind(struct hda_codec *codec,
+					    const struct hda_fixup *fix,
+					    int action)
+{
+	struct sigmatel_spec *spec = codec->spec;
+	static hda_nid_t preferred_pairs[] = {
+		0xd, 0x13,
+		0
+	};
+
+	if (action != HDA_FIXUP_ACT_PRE_PROBE)
+		return;
+
+	spec->gen.preferred_dacs = preferred_pairs;
+}
+
 static const struct hda_verb hp_bnb13_eq_verbs[] = {
 	/* 44.1KHz base */
 	{ 0x22, 0x7A6, 0x3E },
@@ -2686,6 +2703,12 @@ static const struct hda_fixup stac92hd83xxx_fixups[] = {
 			{}
 		},
 	},
+	[STAC_HP_ENVY_TS_DAC_BIND] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = hp_envy_ts_fixup_dac_bind,
+		.chained = true,
+		.chain_id = STAC_HP_ENVY_TS_BASS,
+	},
 	[STAC_92HD83XXX_GPIO10_EAPD] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = stac92hd83xxx_fixup_gpio10_eapd,
@@ -2764,6 +2787,8 @@ static const struct snd_pci_quirk stac92hd83xxx_fixup_tbl[] = {
 			  "HP bNB13", STAC_HP_BNB13_EQ),
 	SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x190e,
 			  "HP ENVY TS", STAC_HP_ENVY_TS_BASS),
+	SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x1967,
+			  "HP ENVY TS", STAC_HP_ENVY_TS_DAC_BIND),
 	SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x1940,
 			  "HP bNB13", STAC_HP_BNB13_EQ),
 	SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x1941,
diff --git a/tools/Makefile b/tools/Makefile
index 9a617adc6675..b35102721cbb 100644
--- a/tools/Makefile
+++ b/tools/Makefile
@@ -1,3 +1,8 @@
+# Some of the tools (perf) use same make variables
+# as in kernel build.
+export srctree=
+export objtree=
+
 include scripts/Makefile.include
 
 help:
@@ -47,11 +52,16 @@ cgroup firewire hv guest usb virtio vm net: FORCE
 liblockdep: FORCE
 	$(call descend,lib/lockdep)
 
-libapikfs: FORCE
+libapi: FORCE
 	$(call descend,lib/api)
 
-perf: libapikfs FORCE
-	$(call descend,$@)
+# The perf build does not follow the descend function setup,
+# invoking it via it's own make rule.
+PERF_O   = $(if $(O),$(O)/tools/perf,)
+
+perf: FORCE
+	$(Q)mkdir -p $(PERF_O) .
+	$(Q)$(MAKE) --no-print-directory -C perf O=$(PERF_O) subdir=
 
 selftests: FORCE
 	$(call descend,testing/$@)
@@ -97,10 +107,10 @@ cgroup_clean hv_clean firewire_clean lguest_clean usb_clean virtio_clean vm_clea
 liblockdep_clean:
 	$(call descend,lib/lockdep,clean)
 
-libapikfs_clean:
+libapi_clean:
 	$(call descend,lib/api,clean)
 
-perf_clean: libapikfs_clean
+perf_clean:
 	$(call descend,$(@:_clean=),clean)
 
 selftests_clean:
diff --git a/tools/arch/alpha/include/asm/barrier.h b/tools/arch/alpha/include/asm/barrier.h
new file mode 100644
index 000000000000..95df19c95482
--- /dev/null
+++ b/tools/arch/alpha/include/asm/barrier.h
@@ -0,0 +1,8 @@
+#ifndef __TOOLS_LINUX_ASM_ALPHA_BARRIER_H
+#define __TOOLS_LINUX_ASM_ALPHA_BARRIER_H
+
+#define mb()	__asm__ __volatile__("mb": : :"memory")
+#define rmb()	__asm__ __volatile__("mb": : :"memory")
+#define wmb()	__asm__ __volatile__("wmb": : :"memory")
+
+#endif		/* __TOOLS_LINUX_ASM_ALPHA_BARRIER_H */
diff --git a/tools/arch/arm/include/asm/barrier.h b/tools/arch/arm/include/asm/barrier.h
new file mode 100644
index 000000000000..005c618a0ab0
--- /dev/null
+++ b/tools/arch/arm/include/asm/barrier.h
@@ -0,0 +1,12 @@
+#ifndef _TOOLS_LINUX_ASM_ARM_BARRIER_H
+#define _TOOLS_LINUX_ASM_ARM_BARRIER_H
+
+/*
+ * Use the __kuser_memory_barrier helper in the CPU helper page. See
+ * arch/arm/kernel/entry-armv.S in the kernel source for details.
+ */
+#define mb()		((void(*)(void))0xffff0fa0)()
+#define wmb()		((void(*)(void))0xffff0fa0)()
+#define rmb()		((void(*)(void))0xffff0fa0)()
+
+#endif /* _TOOLS_LINUX_ASM_ARM_BARRIER_H */
diff --git a/tools/arch/arm64/include/asm/barrier.h b/tools/arch/arm64/include/asm/barrier.h
new file mode 100644
index 000000000000..a0483c8e0142
--- /dev/null
+++ b/tools/arch/arm64/include/asm/barrier.h
@@ -0,0 +1,16 @@
+#ifndef _TOOLS_LINUX_ASM_AARCH64_BARRIER_H
+#define _TOOLS_LINUX_ASM_AARCH64_BARRIER_H
+
+/*
+ * From tools/perf/perf-sys.h, last modified in:
+ * f428ebd184c82a7914b2aa7e9f868918aaf7ea78 perf tools: Fix AAAAARGH64 memory barriers
+ *
+ * XXX: arch/arm64/include/asm/barrier.h in the kernel sources use dsb, is this
+ * a case like for arm32 where we do things differently in userspace?
+ */
+
+#define mb()		asm volatile("dmb ish" ::: "memory")
+#define wmb()		asm volatile("dmb ishst" ::: "memory")
+#define rmb()		asm volatile("dmb ishld" ::: "memory")
+
+#endif /* _TOOLS_LINUX_ASM_AARCH64_BARRIER_H */
diff --git a/tools/arch/ia64/include/asm/barrier.h b/tools/arch/ia64/include/asm/barrier.h
new file mode 100644
index 000000000000..e4422b4b634e
--- /dev/null
+++ b/tools/arch/ia64/include/asm/barrier.h
@@ -0,0 +1,48 @@
+/*
+ * Copied from the kernel sources to tools/:
+ *
+ * Memory barrier definitions.  This is based on information published
+ * in the Processor Abstraction Layer and the System Abstraction Layer
+ * manual.
+ *
+ * Copyright (C) 1998-2003 Hewlett-Packard Co
+ *	David Mosberger-Tang <davidm@hpl.hp.com>
+ * Copyright (C) 1999 Asit Mallick <asit.k.mallick@intel.com>
+ * Copyright (C) 1999 Don Dugger <don.dugger@intel.com>
+ */
+#ifndef _TOOLS_LINUX_ASM_IA64_BARRIER_H
+#define _TOOLS_LINUX_ASM_IA64_BARRIER_H
+
+#include <linux/compiler.h>
+
+/*
+ * Macros to force memory ordering.  In these descriptions, "previous"
+ * and "subsequent" refer to program order; "visible" means that all
+ * architecturally visible effects of a memory access have occurred
+ * (at a minimum, this means the memory has been read or written).
+ *
+ *   wmb():	Guarantees that all preceding stores to memory-
+ *		like regions are visible before any subsequent
+ *		stores and that all following stores will be
+ *		visible only after all previous stores.
+ *   rmb():	Like wmb(), but for reads.
+ *   mb():	wmb()/rmb() combo, i.e., all previous memory
+ *		accesses are visible before all subsequent
+ *		accesses and vice versa.  This is also known as
+ *		a "fence."
+ *
+ * Note: "mb()" and its variants cannot be used as a fence to order
+ * accesses to memory mapped I/O registers.  For that, mf.a needs to
+ * be used.  However, we don't want to always use mf.a because (a)
+ * it's (presumably) much slower than mf and (b) mf.a is supported for
+ * sequential memory pages only.
+ */
+
+/* XXX From arch/ia64/include/uapi/asm/gcc_intrin.h */
+#define ia64_mf()       asm volatile ("mf" ::: "memory")
+
+#define mb()		ia64_mf()
+#define rmb()		mb()
+#define wmb()		mb()
+
+#endif /* _TOOLS_LINUX_ASM_IA64_BARRIER_H */
diff --git a/tools/arch/mips/include/asm/barrier.h b/tools/arch/mips/include/asm/barrier.h
new file mode 100644
index 000000000000..80f96f7556e3
--- /dev/null
+++ b/tools/arch/mips/include/asm/barrier.h
@@ -0,0 +1,20 @@
+#ifndef _TOOLS_LINUX_ASM_MIPS_BARRIER_H
+#define _TOOLS_LINUX_ASM_MIPS_BARRIER_H
+/*
+ * FIXME: This came from tools/perf/perf-sys.h, where it was first introduced
+ * in c1e028ef40b8d6943b767028ba17d4f2ba020edb, more work needed to make it
+ * more closely follow the Linux kernel arch/mips/include/asm/barrier.h file.
+ * Probably when we continue work on tools/ Kconfig support to have all the
+ * CONFIG_ needed for properly doing that.
+ */
+#define mb()		asm volatile(					\
+				".set	mips2\n\t"			\
+				"sync\n\t"				\
+				".set	mips0"				\
+				: /* no output */			\
+				: /* no input */			\
+				: "memory")
+#define wmb()	mb()
+#define rmb()	mb()
+
+#endif /* _TOOLS_LINUX_ASM_MIPS_BARRIER_H */
diff --git a/tools/arch/powerpc/include/asm/barrier.h b/tools/arch/powerpc/include/asm/barrier.h
new file mode 100644
index 000000000000..b23aee8e6d90
--- /dev/null
+++ b/tools/arch/powerpc/include/asm/barrier.h
@@ -0,0 +1,29 @@
+/*
+ * Copied from the kernel sources:
+ *
+ * Copyright (C) 1999 Cort Dougan <cort@cs.nmt.edu>
+ */
+#ifndef _TOOLS_LINUX_ASM_POWERPC_BARRIER_H
+#define _TOOLS_LINUX_ASM_POWERPC_BARRIER_H
+
+/*
+ * Memory barrier.
+ * The sync instruction guarantees that all memory accesses initiated
+ * by this processor have been performed (with respect to all other
+ * mechanisms that access memory).  The eieio instruction is a barrier
+ * providing an ordering (separately) for (a) cacheable stores and (b)
+ * loads and stores to non-cacheable memory (e.g. I/O devices).
+ *
+ * mb() prevents loads and stores being reordered across this point.
+ * rmb() prevents loads being reordered across this point.
+ * wmb() prevents stores being reordered across this point.
+ *
+ * *mb() variants without smp_ prefix must order all types of memory
+ * operations with one another. sync is the only instruction sufficient
+ * to do this.
+ */
+#define mb()   __asm__ __volatile__ ("sync" : : : "memory")
+#define rmb()  __asm__ __volatile__ ("sync" : : : "memory")
+#define wmb()  __asm__ __volatile__ ("sync" : : : "memory")
+
+#endif /* _TOOLS_LINUX_ASM_POWERPC_BARRIER_H */
diff --git a/tools/arch/s390/include/asm/barrier.h b/tools/arch/s390/include/asm/barrier.h
new file mode 100644
index 000000000000..f85141266b92
--- /dev/null
+++ b/tools/arch/s390/include/asm/barrier.h
@@ -0,0 +1,30 @@
+/*
+ * Copied from the kernel sources:
+ *
+ * Copyright IBM Corp. 1999, 2009
+ *
+ * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
+ */
+
+#ifndef __TOOLS_LINUX_ASM_BARRIER_H
+#define __TOOLS_LINUX_ASM_BARRIER_H
+
+/*
+ * Force strict CPU ordering.
+ * And yes, this is required on UP too when we're talking
+ * to devices.
+ */
+
+#ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
+/* Fast-BCR without checkpoint synchronization */
+#define __ASM_BARRIER "bcr 14,0\n"
+#else
+#define __ASM_BARRIER "bcr 15,0\n"
+#endif
+
+#define mb() do {  asm volatile(__ASM_BARRIER : : : "memory"); } while (0)
+
+#define rmb()				mb()
+#define wmb()				mb()
+
+#endif /* __TOOLS_LIB_ASM_BARRIER_H */
diff --git a/tools/arch/sh/include/asm/barrier.h b/tools/arch/sh/include/asm/barrier.h
new file mode 100644
index 000000000000..c18fd7599b97
--- /dev/null
+++ b/tools/arch/sh/include/asm/barrier.h
@@ -0,0 +1,32 @@
+/*
+ * Copied from the kernel sources:
+ *
+ * Copyright (C) 1999, 2000  Niibe Yutaka  &  Kaz Kojima
+ * Copyright (C) 2002 Paul Mundt
+ */
+#ifndef __TOOLS_LINUX_ASM_SH_BARRIER_H
+#define __TOOLS_LINUX_ASM_SH_BARRIER_H
+
+/*
+ * A brief note on ctrl_barrier(), the control register write barrier.
+ *
+ * Legacy SH cores typically require a sequence of 8 nops after
+ * modification of a control register in order for the changes to take
+ * effect. On newer cores (like the sh4a and sh5) this is accomplished
+ * with icbi.
+ *
+ * Also note that on sh4a in the icbi case we can forego a synco for the
+ * write barrier, as it's not necessary for control registers.
+ *
+ * Historically we have only done this type of barrier for the MMUCR, but
+ * it's also necessary for the CCR, so we make it generic here instead.
+ */
+#if defined(__SH4A__) || defined(__SH5__)
+#define mb()		__asm__ __volatile__ ("synco": : :"memory")
+#define rmb()		mb()
+#define wmb()		mb()
+#endif
+
+#include <asm-generic/barrier.h>
+
+#endif /* __TOOLS_LINUX_ASM_SH_BARRIER_H */
diff --git a/tools/arch/sparc/include/asm/barrier.h b/tools/arch/sparc/include/asm/barrier.h
new file mode 100644
index 000000000000..8c017b3b1391
--- /dev/null
+++ b/tools/arch/sparc/include/asm/barrier.h
@@ -0,0 +1,8 @@
+#ifndef ___TOOLS_LINUX_ASM_SPARC_BARRIER_H
+#define ___TOOLS_LINUX_ASM_SPARC_BARRIER_H
+#if defined(__sparc__) && defined(__arch64__)
+#include "barrier_64.h"
+#else
+#include "barrier_32.h"
+#endif
+#endif
diff --git a/tools/arch/sparc/include/asm/barrier_32.h b/tools/arch/sparc/include/asm/barrier_32.h
new file mode 100644
index 000000000000..c5eadd0a7233
--- /dev/null
+++ b/tools/arch/sparc/include/asm/barrier_32.h
@@ -0,0 +1,6 @@
+#ifndef __TOOLS_PERF_SPARC_BARRIER_H
+#define __TOOLS_PERF_SPARC_BARRIER_H
+
+#include <asm-generic/barrier.h>
+
+#endif /* !(__TOOLS_PERF_SPARC_BARRIER_H) */
diff --git a/tools/arch/sparc/include/asm/barrier_64.h b/tools/arch/sparc/include/asm/barrier_64.h
new file mode 100644
index 000000000000..9a7d7322c3f7
--- /dev/null
+++ b/tools/arch/sparc/include/asm/barrier_64.h
@@ -0,0 +1,42 @@
+#ifndef __TOOLS_LINUX_SPARC64_BARRIER_H
+#define __TOOLS_LINUX_SPARC64_BARRIER_H
+
+/* Copied from the kernel sources to tools/:
+ *
+ * These are here in an effort to more fully work around Spitfire Errata
+ * #51.  Essentially, if a memory barrier occurs soon after a mispredicted
+ * branch, the chip can stop executing instructions until a trap occurs.
+ * Therefore, if interrupts are disabled, the chip can hang forever.
+ *
+ * It used to be believed that the memory barrier had to be right in the
+ * delay slot, but a case has been traced recently wherein the memory barrier
+ * was one instruction after the branch delay slot and the chip still hung.
+ * The offending sequence was the following in sym_wakeup_done() of the
+ * sym53c8xx_2 driver:
+ *
+ *	call	sym_ccb_from_dsa, 0
+ *	 movge	%icc, 0, %l0
+ *	brz,pn	%o0, .LL1303
+ *	 mov	%o0, %l2
+ *	membar	#LoadLoad
+ *
+ * The branch has to be mispredicted for the bug to occur.  Therefore, we put
+ * the memory barrier explicitly into a "branch always, predicted taken"
+ * delay slot to avoid the problem case.
+ */
+#define membar_safe(type) \
+do {	__asm__ __volatile__("ba,pt	%%xcc, 1f\n\t" \
+			     " membar	" type "\n" \
+			     "1:\n" \
+			     : : : "memory"); \
+} while (0)
+
+/* The kernel always executes in TSO memory model these days,
+ * and furthermore most sparc64 chips implement more stringent
+ * memory ordering than required by the specifications.
+ */
+#define mb()	membar_safe("#StoreLoad")
+#define rmb()	__asm__ __volatile__("":::"memory")
+#define wmb()	__asm__ __volatile__("":::"memory")
+
+#endif /* !(__TOOLS_LINUX_SPARC64_BARRIER_H) */
diff --git a/tools/arch/tile/include/asm/barrier.h b/tools/arch/tile/include/asm/barrier.h
new file mode 100644
index 000000000000..7d3692c3d4ac
--- /dev/null
+++ b/tools/arch/tile/include/asm/barrier.h
@@ -0,0 +1,15 @@
+#ifndef _TOOLS_LINUX_ASM_TILE_BARRIER_H
+#define _TOOLS_LINUX_ASM_TILE_BARRIER_H
+/*
+ * FIXME: This came from tools/perf/perf-sys.h, where it was first introduced
+ * in 620830b6954913647b7c7f68920cf48eddf6ad92, more work needed to make it
+ * more closely follow the Linux kernel arch/tile/include/asm/barrier.h file.
+ * Probably when we continue work on tools/ Kconfig support to have all the
+ * CONFIG_ needed for properly doing that.
+ */
+
+#define mb()		asm volatile ("mf" ::: "memory")
+#define wmb()		mb()
+#define rmb()		mb()
+
+#endif /* _TOOLS_LINUX_ASM_TILE_BARRIER_H */
diff --git a/tools/arch/x86/include/asm/atomic.h b/tools/arch/x86/include/asm/atomic.h
new file mode 100644
index 000000000000..059e33e94260
--- /dev/null
+++ b/tools/arch/x86/include/asm/atomic.h
@@ -0,0 +1,65 @@
+#ifndef _TOOLS_LINUX_ASM_X86_ATOMIC_H
+#define _TOOLS_LINUX_ASM_X86_ATOMIC_H
+
+#include <linux/compiler.h>
+#include <linux/types.h>
+#include "rmwcc.h"
+
+#define LOCK_PREFIX "\n\tlock; "
+
+/*
+ * Atomic operations that C can't guarantee us.  Useful for
+ * resource counting etc..
+ */
+
+#define ATOMIC_INIT(i)	{ (i) }
+
+/**
+ * atomic_read - read atomic variable
+ * @v: pointer of type atomic_t
+ *
+ * Atomically reads the value of @v.
+ */
+static inline int atomic_read(const atomic_t *v)
+{
+	return ACCESS_ONCE((v)->counter);
+}
+
+/**
+ * atomic_set - set atomic variable
+ * @v: pointer of type atomic_t
+ * @i: required value
+ *
+ * Atomically sets the value of @v to @i.
+ */
+static inline void atomic_set(atomic_t *v, int i)
+{
+	v->counter = i;
+}
+
+/**
+ * atomic_inc - increment atomic variable
+ * @v: pointer of type atomic_t
+ *
+ * Atomically increments @v by 1.
+ */
+static inline void atomic_inc(atomic_t *v)
+{
+	asm volatile(LOCK_PREFIX "incl %0"
+		     : "+m" (v->counter));
+}
+
+/**
+ * atomic_dec_and_test - decrement and test
+ * @v: pointer of type atomic_t
+ *
+ * Atomically decrements @v by 1 and
+ * returns true if the result is 0, or false for all other
+ * cases.
+ */
+static inline int atomic_dec_and_test(atomic_t *v)
+{
+	GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", "e");
+}
+
+#endif /* _TOOLS_LINUX_ASM_X86_ATOMIC_H */
diff --git a/tools/arch/x86/include/asm/barrier.h b/tools/arch/x86/include/asm/barrier.h
new file mode 100644
index 000000000000..f366d8e550e4
--- /dev/null
+++ b/tools/arch/x86/include/asm/barrier.h
@@ -0,0 +1,28 @@
+#ifndef _TOOLS_LINUX_ASM_X86_BARRIER_H
+#define _TOOLS_LINUX_ASM_X86_BARRIER_H
+
+/*
+ * Copied from the Linux kernel sources, and also moving code
+ * out from tools/perf/perf-sys.h so as to make it be located
+ * in a place similar as in the kernel sources.
+ *
+ * Force strict CPU ordering.
+ * And yes, this is required on UP too when we're talking
+ * to devices.
+ */
+
+#if defined(__i386__)
+/*
+ * Some non-Intel clones support out of order store. wmb() ceases to be a
+ * nop for these.
+ */
+#define mb()	asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
+#define rmb()	asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
+#define wmb()	asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
+#elif defined(__x86_64__)
+#define mb() 	asm volatile("mfence":::"memory")
+#define rmb()	asm volatile("lfence":::"memory")
+#define wmb()	asm volatile("sfence" ::: "memory")
+#endif
+
+#endif /* _TOOLS_LINUX_ASM_X86_BARRIER_H */
diff --git a/tools/arch/x86/include/asm/rmwcc.h b/tools/arch/x86/include/asm/rmwcc.h
new file mode 100644
index 000000000000..a6669bc06939
--- /dev/null
+++ b/tools/arch/x86/include/asm/rmwcc.h
@@ -0,0 +1,41 @@
+#ifndef _TOOLS_LINUX_ASM_X86_RMWcc
+#define _TOOLS_LINUX_ASM_X86_RMWcc
+
+#ifdef CC_HAVE_ASM_GOTO
+
+#define __GEN_RMWcc(fullop, var, cc, ...)				\
+do {									\
+	asm_volatile_goto (fullop "; j" cc " %l[cc_label]"		\
+			: : "m" (var), ## __VA_ARGS__ 			\
+			: "memory" : cc_label);				\
+	return 0;							\
+cc_label:								\
+	return 1;							\
+} while (0)
+
+#define GEN_UNARY_RMWcc(op, var, arg0, cc) 				\
+	__GEN_RMWcc(op " " arg0, var, cc)
+
+#define GEN_BINARY_RMWcc(op, var, vcon, val, arg0, cc)			\
+	__GEN_RMWcc(op " %1, " arg0, var, cc, vcon (val))
+
+#else /* !CC_HAVE_ASM_GOTO */
+
+#define __GEN_RMWcc(fullop, var, cc, ...)				\
+do {									\
+	char c;								\
+	asm volatile (fullop "; set" cc " %1"				\
+			: "+m" (var), "=qm" (c)				\
+			: __VA_ARGS__ : "memory");			\
+	return c != 0;							\
+} while (0)
+
+#define GEN_UNARY_RMWcc(op, var, arg0, cc)				\
+	__GEN_RMWcc(op " " arg0, var, cc)
+
+#define GEN_BINARY_RMWcc(op, var, vcon, val, arg0, cc)			\
+	__GEN_RMWcc(op " %2, " arg0, var, cc, vcon (val))
+
+#endif /* CC_HAVE_ASM_GOTO */
+
+#endif /* _TOOLS_LINUX_ASM_X86_RMWcc */
diff --git a/tools/arch/xtensa/include/asm/barrier.h b/tools/arch/xtensa/include/asm/barrier.h
new file mode 100644
index 000000000000..583800bd7259
--- /dev/null
+++ b/tools/arch/xtensa/include/asm/barrier.h
@@ -0,0 +1,18 @@
+/*
+ * Copied from the kernel sources to tools/:
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2001 - 2012 Tensilica Inc.
+ */
+
+#ifndef _TOOLS_LINUX_XTENSA_SYSTEM_H
+#define _TOOLS_LINUX_XTENSA_SYSTEM_H
+
+#define mb()  ({ __asm__ __volatile__("memw" : : : "memory"); })
+#define rmb() barrier()
+#define wmb() mb()
+
+#endif /* _TOOLS_LINUX_XTENSA_SYSTEM_H */
diff --git a/tools/build/Makefile.build b/tools/build/Makefile.build
index 10df57237a66..a51244a8022f 100644
--- a/tools/build/Makefile.build
+++ b/tools/build/Makefile.build
@@ -37,7 +37,7 @@ subdir-obj-y :=
 
 # Build definitions
 build-file := $(dir)/Build
-include $(build-file)
+-include $(build-file)
 
 quiet_cmd_flex  = FLEX     $@
 quiet_cmd_bison = BISON    $@
@@ -94,12 +94,12 @@ obj-y        := $(patsubst %/, %/$(obj)-in.o, $(obj-y))
 subdir-obj-y := $(filter %/$(obj)-in.o, $(obj-y))
 
 # '$(OUTPUT)/dir' prefix to all objects
-prefix       := $(subst ./,,$(OUTPUT)$(dir)/)
-obj-y        := $(addprefix $(prefix),$(obj-y))
-subdir-obj-y := $(addprefix $(prefix),$(subdir-obj-y))
+objprefix    := $(subst ./,,$(OUTPUT)$(dir)/)
+obj-y        := $(addprefix $(objprefix),$(obj-y))
+subdir-obj-y := $(addprefix $(objprefix),$(subdir-obj-y))
 
 # Final '$(obj)-in.o' object
-in-target := $(prefix)$(obj)-in.o
+in-target := $(objprefix)$(obj)-in.o
 
 PHONY += $(subdir-y)
 
diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index 3a0b0ca2a28c..2975632d51e2 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -27,7 +27,7 @@ endef
 #   the rule that uses them - an example for that is the 'bionic'
 #   feature check. ]
 #
-FEATURE_TESTS =			\
+FEATURE_TESTS ?=			\
 	backtrace			\
 	dwarf				\
 	fortify-source			\
@@ -53,7 +53,7 @@ FEATURE_TESTS =			\
 	zlib				\
 	lzma
 
-FEATURE_DISPLAY =			\
+FEATURE_DISPLAY ?=			\
 	dwarf				\
 	glibc				\
 	gtk2				\
diff --git a/tools/build/tests/ex/Build b/tools/build/tests/ex/Build
index 0e6c3e6767e6..70d876237c57 100644
--- a/tools/build/tests/ex/Build
+++ b/tools/build/tests/ex/Build
@@ -2,6 +2,7 @@ ex-y += ex.o
 ex-y += a.o
 ex-y += b.o
 ex-y += empty/
+ex-y += empty2/
 
 libex-y += c.o
 libex-y += d.o
diff --git a/tools/build/tests/ex/empty2/README b/tools/build/tests/ex/empty2/README
new file mode 100644
index 000000000000..2107cc5bf5a9
--- /dev/null
+++ b/tools/build/tests/ex/empty2/README
@@ -0,0 +1,2 @@
+This directory is left intentionally without Build file
+to test proper nesting into Build-less directories.
diff --git a/tools/include/asm-generic/atomic-gcc.h b/tools/include/asm-generic/atomic-gcc.h
new file mode 100644
index 000000000000..2ba78c9f5701
--- /dev/null
+++ b/tools/include/asm-generic/atomic-gcc.h
@@ -0,0 +1,63 @@
+#ifndef __TOOLS_ASM_GENERIC_ATOMIC_H
+#define __TOOLS_ASM_GENERIC_ATOMIC_H
+
+#include <linux/compiler.h>
+#include <linux/types.h>
+
+/*
+ * Atomic operations that C can't guarantee us.  Useful for
+ * resource counting etc..
+ *
+ * Excerpts obtained from the Linux kernel sources.
+ */
+
+#define ATOMIC_INIT(i)	{ (i) }
+
+/**
+ * atomic_read - read atomic variable
+ * @v: pointer of type atomic_t
+ *
+ * Atomically reads the value of @v.
+ */
+static inline int atomic_read(const atomic_t *v)
+{
+	return ACCESS_ONCE((v)->counter);
+}
+
+/**
+ * atomic_set - set atomic variable
+ * @v: pointer of type atomic_t
+ * @i: required value
+ *
+ * Atomically sets the value of @v to @i.
+ */
+static inline void atomic_set(atomic_t *v, int i)
+{
+        v->counter = i;
+}
+
+/**
+ * atomic_inc - increment atomic variable
+ * @v: pointer of type atomic_t
+ *
+ * Atomically increments @v by 1.
+ */
+static inline void atomic_inc(atomic_t *v)
+{
+	__sync_add_and_fetch(&v->counter, 1);
+}
+
+/**
+ * atomic_dec_and_test - decrement and test
+ * @v: pointer of type atomic_t
+ *
+ * Atomically decrements @v by 1 and
+ * returns true if the result is 0, or false for all other
+ * cases.
+ */
+static inline int atomic_dec_and_test(atomic_t *v)
+{
+	return __sync_sub_and_fetch(&v->counter, 1) == 0;
+}
+
+#endif /* __TOOLS_ASM_GENERIC_ATOMIC_H */
diff --git a/tools/include/asm-generic/barrier.h b/tools/include/asm-generic/barrier.h
new file mode 100644
index 000000000000..47b933903eaf
--- /dev/null
+++ b/tools/include/asm-generic/barrier.h
@@ -0,0 +1,44 @@
+/*
+ * Copied from the kernel sources to tools/perf/:
+ *
+ * Generic barrier definitions, originally based on MN10300 definitions.
+ *
+ * It should be possible to use these on really simple architectures,
+ * but it serves more as a starting point for new ports.
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+#ifndef __TOOLS_LINUX_ASM_GENERIC_BARRIER_H
+#define __TOOLS_LINUX_ASM_GENERIC_BARRIER_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/compiler.h>
+
+/*
+ * Force strict CPU ordering. And yes, this is required on UP too when we're
+ * talking to devices.
+ *
+ * Fall back to compiler barriers if nothing better is provided.
+ */
+
+#ifndef mb
+#define mb()	barrier()
+#endif
+
+#ifndef rmb
+#define rmb()	mb()
+#endif
+
+#ifndef wmb
+#define wmb()	mb()
+#endif
+
+#endif /* !__ASSEMBLY__ */
+#endif /* __TOOLS_LINUX_ASM_GENERIC_BARRIER_H */
diff --git a/tools/include/asm/atomic.h b/tools/include/asm/atomic.h
new file mode 100644
index 000000000000..70794f538a86
--- /dev/null
+++ b/tools/include/asm/atomic.h
@@ -0,0 +1,10 @@
+#ifndef __TOOLS_LINUX_ASM_ATOMIC_H
+#define __TOOLS_LINUX_ASM_ATOMIC_H
+
+#if defined(__i386__) || defined(__x86_64__)
+#include "../../arch/x86/include/asm/atomic.h"
+#else
+#include <asm-generic/atomic-gcc.h>
+#endif
+
+#endif /* __TOOLS_LINUX_ASM_ATOMIC_H */
diff --git a/tools/include/asm/barrier.h b/tools/include/asm/barrier.h
new file mode 100644
index 000000000000..ac66ac594685
--- /dev/null
+++ b/tools/include/asm/barrier.h
@@ -0,0 +1,27 @@
+#if defined(__i386__) || defined(__x86_64__)
+#include "../../arch/x86/include/asm/barrier.h"
+#elif defined(__arm__)
+#include "../../arch/arm/include/asm/barrier.h"
+#elif defined(__aarch64__)
+#include "../../arch/arm64/include/asm/barrier.h"
+#elif defined(__powerpc__)
+#include "../../arch/powerpc/include/asm/barrier.h"
+#elif defined(__s390__)
+#include "../../arch/s390/include/asm/barrier.h"
+#elif defined(__sh__)
+#include "../../arch/sh/include/asm/barrier.h"
+#elif defined(__sparc__)
+#include "../../arch/sparc/include/asm/barrier.h"
+#elif defined(__tile__)
+#include "../../arch/tile/include/asm/barrier.h"
+#elif defined(__alpha__)
+#include "../../arch/alpha/include/asm/barrier.h"
+#elif defined(__mips__)
+#include "../../arch/mips/include/asm/barrier.h"
+#elif defined(__ia64__)
+#include "../../arch/ia64/include/asm/barrier.h"
+#elif defined(__xtensa__)
+#include "../../arch/xtensa/include/asm/barrier.h"
+#else
+#include <asm-generic/barrier.h>
+#endif
diff --git a/tools/include/linux/atomic.h b/tools/include/linux/atomic.h
new file mode 100644
index 000000000000..4e3d3d18ebab
--- /dev/null
+++ b/tools/include/linux/atomic.h
@@ -0,0 +1,6 @@
+#ifndef __TOOLS_LINUX_ATOMIC_H
+#define __TOOLS_LINUX_ATOMIC_H
+
+#include <asm/atomic.h>
+
+#endif /* __TOOLS_LINUX_ATOMIC_H */
diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h
index 88461f09cc86..f0e72674c52d 100644
--- a/tools/include/linux/compiler.h
+++ b/tools/include/linux/compiler.h
@@ -1,6 +1,10 @@
 #ifndef _TOOLS_LINUX_COMPILER_H_
 #define _TOOLS_LINUX_COMPILER_H_
 
+/* Optimization barrier */
+/* The "volatile" is due to gcc bugs */
+#define barrier() __asm__ __volatile__("": : :"memory")
+
 #ifndef __always_inline
 # define __always_inline	inline __attribute__((always_inline))
 #endif
diff --git a/tools/perf/util/include/linux/kernel.h b/tools/include/linux/kernel.h
index 09e8e7aea7c6..76df53539c2a 100644
--- a/tools/perf/util/include/linux/kernel.h
+++ b/tools/include/linux/kernel.h
@@ -1,5 +1,5 @@
-#ifndef PERF_LINUX_KERNEL_H_
-#define PERF_LINUX_KERNEL_H_
+#ifndef __TOOLS_LINUX_KERNEL_H
+#define __TOOLS_LINUX_KERNEL_H
 
 #include <stdarg.h>
 #include <stdio.h>
diff --git a/tools/perf/util/include/linux/list.h b/tools/include/linux/list.h
index 76ddbc726343..76b014c96893 100644
--- a/tools/perf/util/include/linux/list.h
+++ b/tools/include/linux/list.h
@@ -1,10 +1,10 @@
 #include <linux/kernel.h>
 #include <linux/types.h>
 
-#include "../../../../include/linux/list.h"
+#include "../../../include/linux/list.h"
 
-#ifndef PERF_LIST_H
-#define PERF_LIST_H
+#ifndef TOOLS_LIST_H
+#define TOOLS_LIST_H
 /**
  * list_del_range - deletes range of entries from list.
  * @begin: first element in the range to delete from the list.
diff --git a/tools/include/linux/poison.h b/tools/include/linux/poison.h
new file mode 100644
index 000000000000..0c27bdf14233
--- /dev/null
+++ b/tools/include/linux/poison.h
@@ -0,0 +1 @@
+#include "../../../include/linux/poison.h"
diff --git a/tools/include/linux/types.h b/tools/include/linux/types.h
index b5cf25e05df2..8ebf6278b2ef 100644
--- a/tools/include/linux/types.h
+++ b/tools/include/linux/types.h
@@ -60,6 +60,14 @@ typedef __u32 __bitwise __be32;
 typedef __u64 __bitwise __le64;
 typedef __u64 __bitwise __be64;
 
+typedef struct {
+	int counter;
+} atomic_t;
+
+#ifndef __aligned_u64
+# define __aligned_u64 __u64 __attribute__((aligned(8)))
+#endif
+
 struct list_head {
 	struct list_head *next, *prev;
 };
diff --git a/tools/lib/traceevent/.gitignore b/tools/lib/traceevent/.gitignore
index 35f56be5a4cd..3c60335fe7be 100644
--- a/tools/lib/traceevent/.gitignore
+++ b/tools/lib/traceevent/.gitignore
@@ -1 +1,2 @@
 TRACEEVENT-CFLAGS
+libtraceevent-dynamic-list
diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index d410da335e3d..6daaff652aff 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -23,6 +23,7 @@ endef
 # Allow setting CC and AR, or setting CROSS_COMPILE as a prefix.
 $(call allow-override,CC,$(CROSS_COMPILE)gcc)
 $(call allow-override,AR,$(CROSS_COMPILE)ar)
+$(call allow-override,NM,$(CROSS_COMPILE)nm)
 
 EXT = -std=gnu99
 INSTALL = install
@@ -34,9 +35,15 @@ INSTALL = install
 DESTDIR ?=
 DESTDIR_SQ = '$(subst ','\'',$(DESTDIR))'
 
+LP64 := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1)
+ifeq ($(LP64), 1)
+  libdir_relative = lib64
+else
+  libdir_relative = lib
+endif
+
 prefix ?= /usr/local
-bindir_relative = bin
-bindir = $(prefix)/$(bindir_relative)
+libdir = $(prefix)/$(libdir_relative)
 man_dir = $(prefix)/share/man
 man_dir_SQ = '$(subst ','\'',$(man_dir))'
 
@@ -58,7 +65,7 @@ ifeq ($(prefix),$(HOME))
 override plugin_dir = $(HOME)/.traceevent/plugins
 set_plugin_dir := 0
 else
-override plugin_dir = $(prefix)/lib/traceevent/plugins
+override plugin_dir = $(libdir)/traceevent/plugins
 endif
 endif
 
@@ -85,11 +92,11 @@ srctree := $(patsubst %/,%,$(dir $(srctree)))
 #$(info Determined 'srctree' to be $(srctree))
 endif
 
-export prefix bindir src obj
+export prefix libdir src obj
 
 # Shell quotes
-bindir_SQ = $(subst ','\'',$(bindir))
-bindir_relative_SQ = $(subst ','\'',$(bindir_relative))
+libdir_SQ = $(subst ','\'',$(libdir))
+libdir_relative_SQ = $(subst ','\'',$(libdir_relative))
 plugin_dir_SQ = $(subst ','\'',$(plugin_dir))
 
 LIB_FILE = libtraceevent.a libtraceevent.so
@@ -151,8 +158,9 @@ PLUGINS_IN := $(PLUGINS:.so=-in.o)
 
 TE_IN    := $(OUTPUT)libtraceevent-in.o
 LIB_FILE := $(addprefix $(OUTPUT),$(LIB_FILE))
+DYNAMIC_LIST_FILE := $(OUTPUT)libtraceevent-dynamic-list
 
-CMD_TARGETS = $(LIB_FILE) $(PLUGINS)
+CMD_TARGETS = $(LIB_FILE) $(PLUGINS) $(DYNAMIC_LIST_FILE)
 
 TARGETS = $(CMD_TARGETS)
 
@@ -169,6 +177,9 @@ $(OUTPUT)libtraceevent.so: $(TE_IN)
 $(OUTPUT)libtraceevent.a: $(TE_IN)
 	$(QUIET_LINK)$(RM) $@; $(AR) rcs $@ $^
 
+$(OUTPUT)libtraceevent-dynamic-list: $(PLUGINS)
+	$(QUIET_GEN)$(call do_generate_dynamic_list_file, $(PLUGINS), $@)
+
 plugins: $(PLUGINS)
 
 __plugin_obj = $(notdir $@)
@@ -238,9 +249,16 @@ define do_install_plugins
 	done
 endef
 
+define do_generate_dynamic_list_file
+	(echo '{';							\
+	$(NM) -u -D $1 | awk 'NF>1 {print "\t"$$2";"}' | sort -u;	\
+	echo '};';							\
+	) > $2
+endef
+
 install_lib: all_cmd install_plugins
 	$(call QUIET_INSTALL, $(LIB_FILE)) \
-		$(call do_install,$(LIB_FILE),$(bindir_SQ))
+		$(call do_install,$(LIB_FILE),$(libdir_SQ))
 
 install_plugins: $(PLUGINS)
 	$(call QUIET_INSTALL, trace_plugins) \
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 29f94f6f0d9e..cc25f059ab3d 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -1387,7 +1387,7 @@ static int event_read_fields(struct event_format *event, struct format_field **f
 			do_warning_event(event, "%s: no type found", __func__);
 			goto fail;
 		}
-		field->name = last_token;
+		field->name = field->alias = last_token;
 
 		if (test_type(type, EVENT_OP))
 			goto fail;
@@ -1469,7 +1469,7 @@ static int event_read_fields(struct event_format *event, struct format_field **f
 				size_dynamic = type_size(field->name);
 				free_token(field->name);
 				strcat(field->type, brackets);
-				field->name = token;
+				field->name = field->alias = token;
 				type = read_token(&token);
 			} else {
 				char *new_type;
@@ -6444,6 +6444,8 @@ void pevent_ref(struct pevent *pevent)
 void pevent_free_format_field(struct format_field *field)
 {
 	free(field->type);
+	if (field->alias != field->name)
+		free(field->alias);
 	free(field->name);
 	free(field);
 }
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index 86a5839fb048..063b1971eb35 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -191,6 +191,7 @@ struct format_field {
 	struct event_format	*event;
 	char			*type;
 	char			*name;
+	char			*alias;
 	int			offset;
 	int			size;
 	unsigned int		arraylen;
diff --git a/tools/lib/traceevent/plugin_cfg80211.c b/tools/lib/traceevent/plugin_cfg80211.c
index 4592d8438318..ec57d0c1fbc2 100644
--- a/tools/lib/traceevent/plugin_cfg80211.c
+++ b/tools/lib/traceevent/plugin_cfg80211.c
@@ -4,6 +4,19 @@
 #include <endian.h>
 #include "event-parse.h"
 
+/*
+ * From glibc endian.h, for older systems where it is not present, e.g.: RHEL5,
+ * Fedora6.
+ */
+#ifndef le16toh
+# if __BYTE_ORDER == __LITTLE_ENDIAN
+#  define le16toh(x) (x)
+# else
+#  define le16toh(x) __bswap_16 (x)
+# endif
+#endif
+
+
 static unsigned long long
 process___le16_to_cpup(struct trace_seq *s, unsigned long long *args)
 {
diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore
index 812f904193e8..09db62ba5786 100644
--- a/tools/perf/.gitignore
+++ b/tools/perf/.gitignore
@@ -28,3 +28,4 @@ config.mak.autogen
 *-flex.*
 *.pyc
 *.pyo
+.config-detected
diff --git a/tools/perf/Documentation/callchain-overhead-calculation.txt b/tools/perf/Documentation/callchain-overhead-calculation.txt
new file mode 100644
index 000000000000..1a757927195e
--- /dev/null
+++ b/tools/perf/Documentation/callchain-overhead-calculation.txt
@@ -0,0 +1,108 @@
+Overhead calculation
+--------------------
+The overhead can be shown in two columns as 'Children' and 'Self' when
+perf collects callchains.  The 'self' overhead is simply calculated by
+adding all period values of the entry - usually a function (symbol).
+This is the value that perf shows traditionally and sum of all the
+'self' overhead values should be 100%.
+
+The 'children' overhead is calculated by adding all period values of
+the child functions so that it can show the total overhead of the
+higher level functions even if they don't directly execute much.
+'Children' here means functions that are called from another (parent)
+function.
+
+It might be confusing that the sum of all the 'children' overhead
+values exceeds 100% since each of them is already an accumulation of
+'self' overhead of its child functions.  But with this enabled, users
+can find which function has the most overhead even if samples are
+spread over the children.
+
+Consider the following example; there are three functions like below.
+
+-----------------------
+void foo(void) {
+    /* do something */
+}
+
+void bar(void) {
+    /* do something */
+    foo();
+}
+
+int main(void) {
+    bar()
+    return 0;
+}
+-----------------------
+
+In this case 'foo' is a child of 'bar', and 'bar' is an immediate
+child of 'main' so 'foo' also is a child of 'main'.  In other words,
+'main' is a parent of 'foo' and 'bar', and 'bar' is a parent of 'foo'.
+
+Suppose all samples are recorded in 'foo' and 'bar' only.  When it's
+recorded with callchains the output will show something like below
+in the usual (self-overhead-only) output of perf report:
+
+----------------------------------
+Overhead  Symbol
+........  .....................
+  60.00%  foo
+          |
+          --- foo
+              bar
+              main
+              __libc_start_main
+
+  40.00%  bar
+          |
+          --- bar
+              main
+              __libc_start_main
+----------------------------------
+
+When the --children option is enabled, the 'self' overhead values of
+child functions (i.e. 'foo' and 'bar') are added to the parents to
+calculate the 'children' overhead.  In this case the report could be
+displayed as:
+
+-------------------------------------------
+Children      Self  Symbol
+........  ........  ....................
+ 100.00%     0.00%  __libc_start_main
+          |
+          --- __libc_start_main
+
+ 100.00%     0.00%  main
+          |
+          --- main
+              __libc_start_main
+
+ 100.00%    40.00%  bar
+          |
+          --- bar
+              main
+              __libc_start_main
+
+  60.00%    60.00%  foo
+          |
+          --- foo
+              bar
+              main
+              __libc_start_main
+-------------------------------------------
+
+In the above output, the 'self' overhead of 'foo' (60%) was add to the
+'children' overhead of 'bar', 'main' and '\_\_libc_start_main'.
+Likewise, the 'self' overhead of 'bar' (40%) was added to the
+'children' overhead of 'main' and '\_\_libc_start_main'.
+
+So '\_\_libc_start_main' and 'main' are shown first since they have
+same (100%) 'children' overhead (even though they have zero 'self'
+overhead) and they are the parents of 'foo' and 'bar'.
+
+Since v3.16 the 'children' overhead is shown by default and the output
+is sorted by its values. The 'children' overhead is disabled by
+specifying --no-children option on the command line or by adding
+'report.children = false' or 'top.children = false' in the perf config
+file.
diff --git a/tools/perf/Documentation/perf-bench.txt b/tools/perf/Documentation/perf-bench.txt
index f6480cbf309b..bf3d0644bf10 100644
--- a/tools/perf/Documentation/perf-bench.txt
+++ b/tools/perf/Documentation/perf-bench.txt
@@ -210,6 +210,9 @@ Suite for evaluating hash tables.
 *wake*::
 Suite for evaluating wake calls.
 
+*wake-parallel*::
+Suite for evaluating parallel wake calls.
+
 *requeue*::
 Suite for evaluating requeue calls.
 
diff --git a/tools/perf/Documentation/perf-inject.txt b/tools/perf/Documentation/perf-inject.txt
index dc7442cf3d7f..b876ae312699 100644
--- a/tools/perf/Documentation/perf-inject.txt
+++ b/tools/perf/Documentation/perf-inject.txt
@@ -44,6 +44,33 @@ OPTIONS
 --kallsyms=<file>::
 	kallsyms pathname
 
+--itrace::
+	Decode Instruction Tracing data, replacing it with synthesized events.
+	Options are:
+
+		i	synthesize instructions events
+		b	synthesize branches events
+		c	synthesize branches events (calls only)
+		r	synthesize branches events (returns only)
+		x	synthesize transactions events
+		e	synthesize error events
+		d	create a debug log
+		g	synthesize a call chain (use with i or x)
+
+	The default is all events i.e. the same as --itrace=ibxe
+
+	In addition, the period (default 100000) for instructions events
+	can be specified in units of:
+
+		i	instructions
+		t	ticks
+		ms	milliseconds
+		us	microseconds
+		ns	nanoseconds (default)
+
+	Also the call chain size (default 16, max. 1024) for instructions or
+	transactions events can be specified.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-report[1], linkperf:perf-archive[1]
diff --git a/tools/perf/Documentation/perf-kmem.txt b/tools/perf/Documentation/perf-kmem.txt
index 23219c65c16f..ff0f433b3fce 100644
--- a/tools/perf/Documentation/perf-kmem.txt
+++ b/tools/perf/Documentation/perf-kmem.txt
@@ -37,7 +37,11 @@ OPTIONS
 
 -s <key[,key2...]>::
 --sort=<key[,key2...]>::
-	Sort the output (default: frag,hit,bytes)
+	Sort the output (default: 'frag,hit,bytes' for slab and 'bytes,hit'
+	for page).  Available sort keys are 'ptr, callsite, bytes, hit,
+	pingpong, frag' for slab and 'page, callsite, bytes, hit, order,
+	migtype, gfp' for page.  This option should be preceded by one of the
+	mode selection options - i.e. --slab, --page, --alloc and/or --caller.
 
 -l <num>::
 --line=<num>::
@@ -52,6 +56,11 @@ OPTIONS
 --page::
 	Analyze page allocator events
 
+--live::
+	Show live page stat.  The perf kmem shows total allocation stat by
+	default, but this option shows live (currently allocated) pages
+	instead.  (This option works with --page option only)
+
 SEE ALSO
 --------
 linkperf:perf-record[1]
diff --git a/tools/perf/Documentation/perf-kvm.txt b/tools/perf/Documentation/perf-kvm.txt
index 6252e776009c..6a5bb2b17039 100644
--- a/tools/perf/Documentation/perf-kvm.txt
+++ b/tools/perf/Documentation/perf-kvm.txt
@@ -151,6 +151,12 @@ STAT LIVE OPTIONS
        Show events other than HLT (x86 only) or Wait state (s390 only)
        that take longer than duration usecs.
 
+--proc-map-timeout::
+	When processing pre-existing threads /proc/XXX/mmap, it may take
+	a long time, because the file may be huge. A time out is needed
+	in such cases.
+	This option sets the time out limit. The default value is 500 ms.
+
 SEE ALSO
 --------
 linkperf:perf-top[1], linkperf:perf-record[1], linkperf:perf-report[1],
diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt
index 239609c09f83..3a8a9ba2b041 100644
--- a/tools/perf/Documentation/perf-probe.txt
+++ b/tools/perf/Documentation/perf-probe.txt
@@ -14,11 +14,13 @@ or
 or
 'perf probe' [options] --del='[GROUP:]EVENT' [...]
 or
-'perf probe' --list
+'perf probe' --list[=[GROUP:]EVENT]
 or
 'perf probe' [options] --line='LINE'
 or
 'perf probe' [options] --vars='PROBEPOINT'
+or
+'perf probe' [options] --funcs
 
 DESCRIPTION
 -----------
@@ -64,8 +66,8 @@ OPTIONS
 	classes(e.g. [a-z], [!A-Z]).
 
 -l::
---list::
-	List up current probe events.
+--list[=[GROUP:]EVENT]::
+	List up current probe events. This can also accept filtering patterns of event names.
 
 -L::
 --line=::
@@ -81,10 +83,15 @@ OPTIONS
 	(Only for --vars) Show external defined variables in addition to local
 	variables.
 
+--no-inlines::
+	(Only for --add) Search only for non-inlined functions. The functions
+	which do not have instances are ignored.
+
 -F::
---funcs::
+--funcs[=FILTER]::
 	Show available functions in given module or kernel. With -x/--exec,
 	can also list functions in a user space executable / shared library.
+	This also can accept a FILTER rule argument.
 
 --filter=FILTER::
 	(Only for --vars and --funcs) Set filter. FILTER is a combination of glob
@@ -148,7 +155,7 @@ Each probe argument follows below syntax.
  [NAME=]LOCALVAR|$retval|%REG|@SYMBOL[:TYPE]
 
 'NAME' specifies the name of this argument (optional). You can use the name of local variable, local data structure member (e.g. var->field, var.field2), local array with fixed index (e.g. array[1], var->array[0], var->pointer[2]), or kprobe-tracer argument format (e.g. $retval, %ax, etc). Note that the name of this argument will be set as the last member name if you specify a local data structure member (e.g. field2 for 'var->field1.field2'.)
-'$vars' special argument is also available for NAME, it is expanded to the local variables which can access at given probe point.
+'$vars' and '$params' special arguments are also available for NAME, '$vars' is expanded to the local variables (including function parameters) which can access at given probe point. '$params' is expanded to only the function parameters.
 'TYPE' casts the type of this argument (optional). If omitted, perf probe automatically set the type based on debuginfo. You can specify 'string' type only for the local variable or structure member which is an array of or a pointer to 'char' or 'unsigned char' type.
 
 On x86 systems %REG is always the short form of the register: for example %AX. %RAX or %EAX is not valid.
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 4847a793de65..9b9d9d086680 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -108,6 +108,8 @@ OPTIONS
 	Number of mmap data pages (must be a power of two) or size
 	specification with appended unit character - B/K/M/G. The
 	size is rounded up to have nearest pages power of two value.
+	Also, by adding a comma, the number of mmap pages for AUX
+	area tracing can be specified.
 
 --group::
 	Put all events in a single event group.  This precedes the --event
@@ -145,16 +147,21 @@ OPTIONS
 
 -s::
 --stat::
-	Per thread counts.
+	Record per-thread event counts.  Use it with 'perf report -T' to see
+	the values.
 
 -d::
 --data::
-	Sample addresses.
+	Record the sample addresses.
 
 -T::
 --timestamp::
-	Sample timestamps. Use it with 'perf report -D' to see the timestamps,
-	for instance.
+	Record the sample timestamps. Use it with 'perf report -D' to see the
+	timestamps, for instance.
+
+-P::
+--period::
+	Record the sample period.
 
 -n::
 --no-samples::
@@ -257,6 +264,18 @@ records. See clock_gettime(). In particular CLOCK_MONOTONIC and
 CLOCK_MONOTONIC_RAW are supported, some events might also allow
 CLOCK_BOOTTIME, CLOCK_REALTIME and CLOCK_TAI.
 
+-S::
+--snapshot::
+Select AUX area tracing Snapshot Mode. This option is valid only with an
+AUX area tracing event. Optionally the number of bytes to capture per
+snapshot can be specified. In Snapshot Mode, trace data is captured only when
+signal SIGUSR2 is received.
+
+--proc-map-timeout::
+When processing pre-existing threads /proc/XXX/mmap, it may take a long time,
+because the file may be huge. A time out is needed in such cases.
+This option sets the time out limit. The default value is 500 ms.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-list[1]
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 4879cf638824..c33b69f3374f 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -34,7 +34,8 @@ OPTIONS
 
 -T::
 --threads::
-	Show per-thread event counters
+	Show per-thread event counters.  The input data file should be recorded
+	with -s option.
 -c::
 --comms=::
 	Only consider symbols in these comms. CSV that understands
@@ -193,6 +194,7 @@ OPTIONS
 	Accumulate callchain of children to parent entry so that then can
 	show up in the output.  The output will have a new "Children" column
 	and will be sorted on the data.  It requires callchains are recorded.
+	See the `overhead calculation' section for more details.
 
 --max-stack::
 	Set the stack depth limit when parsing the callchain, anything
@@ -323,6 +325,37 @@ OPTIONS
 --header-only::
 	Show only perf.data header (forces --stdio).
 
+--itrace::
+	Options for decoding instruction tracing data. The options are:
+
+		i	synthesize instructions events
+		b	synthesize branches events
+		c	synthesize branches events (calls only)
+		r	synthesize branches events (returns only)
+		x	synthesize transactions events
+		e	synthesize error events
+		d	create a debug log
+		g	synthesize a call chain (use with i or x)
+
+	The default is all events i.e. the same as --itrace=ibxe
+
+	In addition, the period (default 100000) for instructions events
+	can be specified in units of:
+
+		i	instructions
+		t	ticks
+		ms	milliseconds
+		us	microseconds
+		ns	nanoseconds (default)
+
+	Also the call chain size (default 16, max. 1024) for instructions or
+	transactions events can be specified.
+
+	To disable decoding entirely, use --no-itrace.
+
+
+include::callchain-overhead-calculation.txt[]
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-annotate[1]
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 79445750fcb3..c82df572fac2 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -115,7 +115,8 @@ OPTIONS
 -f::
 --fields::
         Comma separated list of fields to print. Options are:
-        comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff, srcline, period.
+        comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff,
+	srcline, period, flags.
         Field list can be prepended with the type, trace, sw or hw,
         to indicate to which event type the field list applies.
         e.g., -f sw:comm,tid,time,ip,sym  and -f trace:time,cpu,trace
@@ -165,6 +166,12 @@ OPTIONS
 
 	At this point usage is displayed, and perf-script exits.
 
+	The flags field is synthesized and may have a value when Instruction
+	Trace decoding. The flags are "bcrosyiABEx" which stand for branch,
+	call, return, conditional, system, asynchronous, interrupt,
+	transaction abort, trace begin, trace end, and in transaction,
+	respectively.
+
 	Finally, a user may not set fields to none for all event types.
 	i.e., -f "" is not allowed.
 
@@ -221,6 +228,34 @@ OPTIONS
 --header-only
 	Show only perf.data header.
 
+--itrace::
+	Options for decoding instruction tracing data. The options are:
+
+		i	synthesize instructions events
+		b	synthesize branches events
+		c	synthesize branches events (calls only)
+		r	synthesize branches events (returns only)
+		x	synthesize transactions events
+		e	synthesize error events
+		d	create a debug log
+		g	synthesize a call chain (use with i or x)
+
+	The default is all events i.e. the same as --itrace=ibxe
+
+	In addition, the period (default 100000) for instructions events
+	can be specified in units of:
+
+		i	instructions
+		t	ticks
+		ms	milliseconds
+		us	microseconds
+		ns	nanoseconds (default)
+
+	Also the call chain size (default 16, max. 1024) for instructions or
+	transactions events can be specified.
+
+	To disable decoding entirely, use --no-itrace.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-script-perl[1],
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 3265b1070518..776aec4d0927 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -168,7 +168,7 @@ Default is to monitor all CPUS.
 	Accumulate callchain of children to parent entry so that then can
 	show up in the output.  The output will have a new "Children" column
 	and will be sorted on the data.  It requires -g/--call-graph option
-	enabled.
+	enabled.  See the `overhead calculation' section for more details.
 
 --max-stack::
 	Set the stack depth limit when parsing the callchain, anything
@@ -201,6 +201,12 @@ Default is to monitor all CPUS.
 	Force each column width to the provided list, for large terminal
 	readability.  0 means no limit (default behavior).
 
+--proc-map-timeout::
+	When processing pre-existing threads /proc/XXX/mmap, it may take
+	a long time, because the file may be huge. A time out is needed
+	in such cases.
+	This option sets the time out limit. The default value is 500 ms.
+
 
 INTERACTIVE PROMPTING KEYS
 --------------------------
@@ -234,6 +240,7 @@ INTERACTIVE PROMPTING KEYS
 
 Pressing any unmapped key displays a menu, and prompts for input.
 
+include::callchain-overhead-calculation.txt[]
 
 SEE ALSO
 --------
diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index ba03fd5d1a54..7ea078658a87 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -35,7 +35,7 @@ OPTIONS
 
 -e::
 --expr::
-	List of events to show, currently only syscall names.
+	List of syscalls to show, currently only syscall names.
 	Prefixing with ! shows all syscalls but the ones specified.  You may
 	need to escape it.
 
@@ -121,6 +121,11 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs.
 --event::
 	Trace other events, see 'perf list' for a complete list.
 
+--proc-map-timeout::
+	When processing pre-existing threads /proc/XXX/mmap, it may take a long time,
+	because the file may be huge. A time out is needed in such cases.
+	This option sets the time out limit. The default value is 500 ms.
+
 PAGEFAULTS
 ----------
 
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 11ccbb22ea2b..fe50a1b34aa0 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -1,12 +1,30 @@
 tools/perf
+tools/arch/alpha/include/asm/barrier.h
+tools/arch/arm/include/asm/barrier.h
+tools/arch/ia64/include/asm/barrier.h
+tools/arch/mips/include/asm/barrier.h
+tools/arch/powerpc/include/asm/barrier.h
+tools/arch/s390/include/asm/barrier.h
+tools/arch/sh/include/asm/barrier.h
+tools/arch/sparc/include/asm/barrier.h
+tools/arch/sparc/include/asm/barrier_32.h
+tools/arch/sparc/include/asm/barrier_64.h
+tools/arch/tile/include/asm/barrier.h
+tools/arch/x86/include/asm/barrier.h
+tools/arch/xtensa/include/asm/barrier.h
 tools/scripts
 tools/build
+tools/arch/x86/include/asm/atomic.h
+tools/arch/x86/include/asm/rmwcc.h
 tools/lib/traceevent
 tools/lib/api
 tools/lib/symbol/kallsyms.c
 tools/lib/symbol/kallsyms.h
 tools/lib/util/find_next_bit.c
+tools/include/asm/atomic.h
+tools/include/asm/barrier.h
 tools/include/asm/bug.h
+tools/include/asm-generic/barrier.h
 tools/include/asm-generic/bitops/arch_hweight.h
 tools/include/asm-generic/bitops/atomic.h
 tools/include/asm-generic/bitops/const_hweight.h
@@ -17,35 +35,35 @@ tools/include/asm-generic/bitops/fls64.h
 tools/include/asm-generic/bitops/fls.h
 tools/include/asm-generic/bitops/hweight.h
 tools/include/asm-generic/bitops.h
+tools/include/linux/atomic.h
 tools/include/linux/bitops.h
 tools/include/linux/compiler.h
 tools/include/linux/export.h
 tools/include/linux/hash.h
+tools/include/linux/kernel.h
+tools/include/linux/list.h
 tools/include/linux/log2.h
+tools/include/linux/poison.h
 tools/include/linux/types.h
 include/asm-generic/bitops/arch_hweight.h
 include/asm-generic/bitops/const_hweight.h
 include/asm-generic/bitops/fls64.h
 include/asm-generic/bitops/__fls.h
 include/asm-generic/bitops/fls.h
-include/linux/const.h
 include/linux/perf_event.h
 include/linux/rbtree.h
 include/linux/list.h
 include/linux/hash.h
 include/linux/stringify.h
-lib/find_next_bit.c
 lib/hweight.c
 lib/rbtree.c
 include/linux/swab.h
 arch/*/include/asm/unistd*.h
-arch/*/include/asm/perf_regs.h
 arch/*/include/uapi/asm/unistd*.h
 arch/*/include/uapi/asm/perf_regs.h
 arch/*/lib/memcpy*.S
 arch/*/lib/memset*.S
 include/linux/poison.h
-include/linux/magic.h
 include/linux/hw_breakpoint.h
 include/linux/rbtree_augmented.h
 include/uapi/linux/perf_event.h
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index c43a20517591..1af0cfeb7a57 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -73,6 +73,8 @@ include config/utilities.mak
 # for CTF data format.
 #
 # Define NO_LZMA if you do not want to support compressed (xz) kernel modules
+#
+# Define NO_AUXTRACE if you do not want AUX area tracing support
 
 ifeq ($(srctree),)
 srctree := $(patsubst %/,%,$(dir $(shell pwd)))
@@ -171,6 +173,9 @@ endif
 LIBTRACEEVENT = $(TE_PATH)libtraceevent.a
 export LIBTRACEEVENT
 
+LIBTRACEEVENT_DYNAMIC_LIST = $(TE_PATH)libtraceevent-dynamic-list
+LIBTRACEEVENT_DYNAMIC_LIST_LDFLAGS = -Xlinker --dynamic-list=$(LIBTRACEEVENT_DYNAMIC_LIST)
+
 LIBAPI = $(LIB_PATH)libapi.a
 export LIBAPI
 
@@ -185,8 +190,9 @@ python-clean := $(call QUIET_CLEAN, python) $(RM) -r $(PYTHON_EXTBUILD) $(OUTPUT
 PYTHON_EXT_SRCS := $(shell grep -v ^\# util/python-ext-sources)
 PYTHON_EXT_DEPS := util/python-ext-sources util/setup.py $(LIBTRACEEVENT) $(LIBAPI)
 
-$(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS)
-	$(QUIET_GEN)CFLAGS='$(CFLAGS)' $(PYTHON_WORD) util/setup.py \
+$(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS) $(LIBTRACEEVENT_DYNAMIC_LIST)
+	$(QUIET_GEN)CFLAGS='$(CFLAGS)' LDFLAGS='$(LDFLAGS) $(LIBTRACEEVENT_DYNAMIC_LIST_LDFLAGS)' \
+	  $(PYTHON_WORD) util/setup.py \
 	  --quiet build_ext; \
 	mkdir -p $(OUTPUT)python && \
 	cp $(PYTHON_EXTBUILD_LIB)perf.so $(OUTPUT)python/
@@ -276,8 +282,9 @@ build := -f $(srctree)/tools/build/Makefile.build dir=. obj
 $(PERF_IN): $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h FORCE
 	$(Q)$(MAKE) $(build)=perf
 
-$(OUTPUT)perf: $(PERFLIBS) $(PERF_IN)
-	$(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $(PERF_IN) $(LIBS) -o $@
+$(OUTPUT)perf: $(PERFLIBS) $(PERF_IN) $(LIBTRACEEVENT_DYNAMIC_LIST)
+	$(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $(LIBTRACEEVENT_DYNAMIC_LIST_LDFLAGS) \
+		$(PERF_IN) $(LIBS) -o $@
 
 $(GTK_IN): FORCE
 	$(Q)$(MAKE) $(build)=gtk
@@ -371,7 +378,13 @@ $(LIB_FILE): $(LIBPERF_IN)
 LIBTRACEEVENT_FLAGS += plugin_dir=$(plugindir_SQ)
 
 $(LIBTRACEEVENT): FORCE
-	$(Q)$(MAKE) -C $(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) O=$(OUTPUT) $(OUTPUT)libtraceevent.a plugins
+	$(Q)$(MAKE) -C $(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) O=$(OUTPUT) $(OUTPUT)libtraceevent.a
+
+libtraceevent_plugins: FORCE
+	$(Q)$(MAKE) -C $(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) O=$(OUTPUT) plugins
+
+$(LIBTRACEEVENT_DYNAMIC_LIST): libtraceevent_plugins
+	$(Q)$(MAKE) -C $(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) O=$(OUTPUT) $(OUTPUT)libtraceevent-dynamic-list
 
 $(LIBTRACEEVENT)-clean:
 	$(call QUIET_CLEAN, libtraceevent)
@@ -462,7 +475,7 @@ check: $(OUTPUT)common-cmds.h
 
 install-gtk:
 
-install-bin: all install-gtk
+install-tools: all install-gtk
 	$(call QUIET_INSTALL, binaries) \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(bindir_SQ)'; \
 		$(INSTALL) $(OUTPUT)perf '$(DESTDIR_SQ)$(bindir_SQ)'; \
@@ -500,12 +513,16 @@ endif
 	$(call QUIET_INSTALL, perf_completion-script) \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d'; \
 		$(INSTALL) perf-completion.sh '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d/perf'
+
+install-tests: all install-gtk
 	$(call QUIET_INSTALL, tests) \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \
 		$(INSTALL) tests/attr.py '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'; \
 		$(INSTALL) tests/attr/* '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'
 
+install-bin: install-tools install-tests
+
 install: install-bin try-install-man install-traceevent-plugins
 
 install-python_ext:
@@ -549,4 +566,5 @@ FORCE:
 .PHONY: all install clean config-clean strip install-gtk
 .PHONY: shell_compatibility_test please_set_SHELL_PATH_to_a_more_modern_shell
 .PHONY: $(GIT-HEAD-PHONY) TAGS tags cscope FORCE single_dep
+.PHONY: libtraceevent_plugins
 
diff --git a/tools/perf/arch/arm64/Build b/tools/perf/arch/arm64/Build
index 54afe4a467e7..41bf61da476a 100644
--- a/tools/perf/arch/arm64/Build
+++ b/tools/perf/arch/arm64/Build
@@ -1 +1,2 @@
 libperf-y += util/
+libperf-$(CONFIG_DWARF_UNWIND) += tests/
diff --git a/tools/perf/arch/arm64/include/perf_regs.h b/tools/perf/arch/arm64/include/perf_regs.h
index 1d3f39c3aa56..4e5af27e3fbf 100644
--- a/tools/perf/arch/arm64/include/perf_regs.h
+++ b/tools/perf/arch/arm64/include/perf_regs.h
@@ -5,8 +5,11 @@
 #include <linux/types.h>
 #include <asm/perf_regs.h>
 
+void perf_regs_load(u64 *regs);
+
 #define PERF_REGS_MASK	((1ULL << PERF_REG_ARM64_MAX) - 1)
 #define PERF_REGS_MAX	PERF_REG_ARM64_MAX
+#define PERF_SAMPLE_REGS_ABI	PERF_SAMPLE_REGS_ABI_64
 
 #define PERF_REG_IP	PERF_REG_ARM64_PC
 #define PERF_REG_SP	PERF_REG_ARM64_SP
diff --git a/tools/perf/arch/arm64/tests/Build b/tools/perf/arch/arm64/tests/Build
new file mode 100644
index 000000000000..b30eff9bcc83
--- /dev/null
+++ b/tools/perf/arch/arm64/tests/Build
@@ -0,0 +1,2 @@
+libperf-y += regs_load.o
+libperf-y += dwarf-unwind.o
diff --git a/tools/perf/arch/arm64/tests/dwarf-unwind.c b/tools/perf/arch/arm64/tests/dwarf-unwind.c
new file mode 100644
index 000000000000..cf04a4c91c59
--- /dev/null
+++ b/tools/perf/arch/arm64/tests/dwarf-unwind.c
@@ -0,0 +1,61 @@
+#include <string.h>
+#include "perf_regs.h"
+#include "thread.h"
+#include "map.h"
+#include "event.h"
+#include "debug.h"
+#include "tests/tests.h"
+
+#define STACK_SIZE 8192
+
+static int sample_ustack(struct perf_sample *sample,
+		struct thread *thread, u64 *regs)
+{
+	struct stack_dump *stack = &sample->user_stack;
+	struct map *map;
+	unsigned long sp;
+	u64 stack_size, *buf;
+
+	buf = malloc(STACK_SIZE);
+	if (!buf) {
+		pr_debug("failed to allocate sample uregs data\n");
+		return -1;
+	}
+
+	sp = (unsigned long) regs[PERF_REG_ARM64_SP];
+
+	map = map_groups__find(thread->mg, MAP__VARIABLE, (u64) sp);
+	if (!map) {
+		pr_debug("failed to get stack map\n");
+		free(buf);
+		return -1;
+	}
+
+	stack_size = map->end - sp;
+	stack_size = stack_size > STACK_SIZE ? STACK_SIZE : stack_size;
+
+	memcpy(buf, (void *) sp, stack_size);
+	stack->data = (char *) buf;
+	stack->size = stack_size;
+	return 0;
+}
+
+int test__arch_unwind_sample(struct perf_sample *sample,
+		struct thread *thread)
+{
+	struct regs_dump *regs = &sample->user_regs;
+	u64 *buf;
+
+	buf = calloc(1, sizeof(u64) * PERF_REGS_MAX);
+	if (!buf) {
+		pr_debug("failed to allocate sample uregs data\n");
+		return -1;
+	}
+
+	perf_regs_load(buf);
+	regs->abi  = PERF_SAMPLE_REGS_ABI;
+	regs->regs = buf;
+	regs->mask = PERF_REGS_MASK;
+
+	return sample_ustack(sample, thread, buf);
+}
diff --git a/tools/perf/arch/arm64/tests/regs_load.S b/tools/perf/arch/arm64/tests/regs_load.S
new file mode 100644
index 000000000000..025b46e579a6
--- /dev/null
+++ b/tools/perf/arch/arm64/tests/regs_load.S
@@ -0,0 +1,46 @@
+#include <linux/linkage.h>
+
+.text
+.type perf_regs_load,%function
+#define STR_REG(r)	str x##r, [x0, 8 * r]
+#define LDR_REG(r)	ldr x##r, [x0, 8 * r]
+#define SP	(8 * 31)
+#define PC	(8 * 32)
+ENTRY(perf_regs_load)
+	STR_REG(0)
+	STR_REG(1)
+	STR_REG(2)
+	STR_REG(3)
+	STR_REG(4)
+	STR_REG(5)
+	STR_REG(6)
+	STR_REG(7)
+	STR_REG(8)
+	STR_REG(9)
+	STR_REG(10)
+	STR_REG(11)
+	STR_REG(12)
+	STR_REG(13)
+	STR_REG(14)
+	STR_REG(15)
+	STR_REG(16)
+	STR_REG(17)
+	STR_REG(18)
+	STR_REG(19)
+	STR_REG(20)
+	STR_REG(21)
+	STR_REG(22)
+	STR_REG(23)
+	STR_REG(24)
+	STR_REG(25)
+	STR_REG(26)
+	STR_REG(27)
+	STR_REG(28)
+	STR_REG(29)
+	STR_REG(30)
+	mov x1, sp
+	str x1, [x0, #SP]
+	str x30, [x0, #PC]
+	LDR_REG(1)
+	ret
+ENDPROC(perf_regs_load)
diff --git a/tools/perf/arch/common.c b/tools/perf/arch/common.c
index 49776f190abf..b7bb42c44694 100644
--- a/tools/perf/arch/common.c
+++ b/tools/perf/arch/common.c
@@ -61,7 +61,7 @@ const char *const mips_triplets[] = {
 static bool lookup_path(char *name)
 {
 	bool found = false;
-	char *path, *tmp;
+	char *path, *tmp = NULL;
 	char buf[PATH_MAX];
 	char *env = getenv("PATH");
 
diff --git a/tools/perf/arch/powerpc/util/Build b/tools/perf/arch/powerpc/util/Build
index 0af6e9b3f728..7b8b0d1a1b62 100644
--- a/tools/perf/arch/powerpc/util/Build
+++ b/tools/perf/arch/powerpc/util/Build
@@ -1,4 +1,5 @@
 libperf-y += header.o
+libperf-y += sym-handling.o
 
 libperf-$(CONFIG_DWARF) += dwarf-regs.o
 libperf-$(CONFIG_DWARF) += skip-callchain-idx.o
diff --git a/tools/perf/arch/powerpc/util/sym-handling.c b/tools/perf/arch/powerpc/util/sym-handling.c
new file mode 100644
index 000000000000..bbc1a50768dd
--- /dev/null
+++ b/tools/perf/arch/powerpc/util/sym-handling.c
@@ -0,0 +1,82 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * Copyright (C) 2015 Naveen N. Rao, IBM Corporation
+ */
+
+#include "debug.h"
+#include "symbol.h"
+#include "map.h"
+#include "probe-event.h"
+
+#ifdef HAVE_LIBELF_SUPPORT
+bool elf__needs_adjust_symbols(GElf_Ehdr ehdr)
+{
+	return ehdr.e_type == ET_EXEC ||
+	       ehdr.e_type == ET_REL ||
+	       ehdr.e_type == ET_DYN;
+}
+
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+void arch__elf_sym_adjust(GElf_Sym *sym)
+{
+	sym->st_value += PPC64_LOCAL_ENTRY_OFFSET(sym->st_other);
+}
+#endif
+#endif
+
+#if !defined(_CALL_ELF) || _CALL_ELF != 2
+int arch__choose_best_symbol(struct symbol *syma,
+			     struct symbol *symb __maybe_unused)
+{
+	char *sym = syma->name;
+
+	/* Skip over any initial dot */
+	if (*sym == '.')
+		sym++;
+
+	/* Avoid "SyS" kernel syscall aliases */
+	if (strlen(sym) >= 3 && !strncmp(sym, "SyS", 3))
+		return SYMBOL_B;
+	if (strlen(sym) >= 10 && !strncmp(sym, "compat_SyS", 10))
+		return SYMBOL_B;
+
+	return SYMBOL_A;
+}
+
+/* Allow matching against dot variants */
+int arch__compare_symbol_names(const char *namea, const char *nameb)
+{
+	/* Skip over initial dot */
+	if (*namea == '.')
+		namea++;
+	if (*nameb == '.')
+		nameb++;
+
+	return strcmp(namea, nameb);
+}
+#endif
+
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+bool arch__prefers_symtab(void)
+{
+	return true;
+}
+
+#define PPC64LE_LEP_OFFSET	8
+
+void arch__fix_tev_from_maps(struct perf_probe_event *pev,
+			     struct probe_trace_event *tev, struct map *map)
+{
+	/*
+	 * ppc64 ABIv2 local entry point is currently always 2 instructions
+	 * (8 bytes) after the global entry point.
+	 */
+	if (!pev->uprobes && map->dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS) {
+		tev->point.address += PPC64LE_LEP_OFFSET;
+		tev->point.offset += PPC64LE_LEP_OFFSET;
+	}
+}
+#endif
diff --git a/tools/perf/bench/Build b/tools/perf/bench/Build
index 5ce98023d518..c3ab760e06b4 100644
--- a/tools/perf/bench/Build
+++ b/tools/perf/bench/Build
@@ -3,6 +3,7 @@ perf-y += sched-pipe.o
 perf-y += mem-memcpy.o
 perf-y += futex-hash.o
 perf-y += futex-wake.o
+perf-y += futex-wake-parallel.o
 perf-y += futex-requeue.o
 
 perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-asm.o
diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h
index 3c4dd44d45cb..70b2f718cc21 100644
--- a/tools/perf/bench/bench.h
+++ b/tools/perf/bench/bench.h
@@ -33,6 +33,8 @@ extern int bench_mem_memcpy(int argc, const char **argv,
 extern int bench_mem_memset(int argc, const char **argv, const char *prefix);
 extern int bench_futex_hash(int argc, const char **argv, const char *prefix);
 extern int bench_futex_wake(int argc, const char **argv, const char *prefix);
+extern int bench_futex_wake_parallel(int argc, const char **argv,
+				     const char *prefix);
 extern int bench_futex_requeue(int argc, const char **argv, const char *prefix);
 
 #define BENCH_FORMAT_DEFAULT_STR	"default"
diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c
new file mode 100644
index 000000000000..6d8c9fa2a16c
--- /dev/null
+++ b/tools/perf/bench/futex-wake-parallel.c
@@ -0,0 +1,294 @@
+/*
+ * Copyright (C) 2015 Davidlohr Bueso.
+ *
+ * Block a bunch of threads and let parallel waker threads wakeup an
+ * equal amount of them. The program output reflects the avg latency
+ * for each individual thread to service its share of work. Ultimately
+ * it can be used to measure futex_wake() changes.
+ */
+
+#include "../perf.h"
+#include "../util/util.h"
+#include "../util/stat.h"
+#include "../util/parse-options.h"
+#include "../util/header.h"
+#include "bench.h"
+#include "futex.h"
+
+#include <err.h>
+#include <stdlib.h>
+#include <sys/time.h>
+#include <pthread.h>
+
+struct thread_data {
+	pthread_t worker;
+	unsigned int nwoken;
+	struct timeval runtime;
+};
+
+static unsigned int nwakes = 1;
+
+/* all threads will block on the same futex -- hash bucket chaos ;) */
+static u_int32_t futex = 0;
+
+static pthread_t *blocked_worker;
+static bool done = false, silent = false, fshared = false;
+static unsigned int nblocked_threads = 0, nwaking_threads = 0;
+static pthread_mutex_t thread_lock;
+static pthread_cond_t thread_parent, thread_worker;
+static struct stats waketime_stats, wakeup_stats;
+static unsigned int ncpus, threads_starting;
+static int futex_flag = 0;
+
+static const struct option options[] = {
+	OPT_UINTEGER('t', "threads", &nblocked_threads, "Specify amount of threads"),
+	OPT_UINTEGER('w', "nwakers", &nwaking_threads, "Specify amount of waking threads"),
+	OPT_BOOLEAN( 's', "silent",  &silent,   "Silent mode: do not display data/details"),
+	OPT_BOOLEAN( 'S', "shared",  &fshared,  "Use shared futexes instead of private ones"),
+	OPT_END()
+};
+
+static const char * const bench_futex_wake_parallel_usage[] = {
+	"perf bench futex wake-parallel <options>",
+	NULL
+};
+
+static void *waking_workerfn(void *arg)
+{
+	struct thread_data *waker = (struct thread_data *) arg;
+	struct timeval start, end;
+
+	gettimeofday(&start, NULL);
+
+	waker->nwoken = futex_wake(&futex, nwakes, futex_flag);
+	if (waker->nwoken != nwakes)
+		warnx("couldn't wakeup all tasks (%d/%d)",
+		      waker->nwoken, nwakes);
+
+	gettimeofday(&end, NULL);
+	timersub(&end, &start, &waker->runtime);
+
+	pthread_exit(NULL);
+	return NULL;
+}
+
+static void wakeup_threads(struct thread_data *td, pthread_attr_t thread_attr)
+{
+	unsigned int i;
+
+	pthread_attr_setdetachstate(&thread_attr, PTHREAD_CREATE_JOINABLE);
+
+	/* create and block all threads */
+	for (i = 0; i < nwaking_threads; i++) {
+		/*
+		 * Thread creation order will impact per-thread latency
+		 * as it will affect the order to acquire the hb spinlock.
+		 * For now let the scheduler decide.
+		 */
+		if (pthread_create(&td[i].worker, &thread_attr,
+				   waking_workerfn, (void *)&td[i]))
+			err(EXIT_FAILURE, "pthread_create");
+	}
+
+	for (i = 0; i < nwaking_threads; i++)
+		if (pthread_join(td[i].worker, NULL))
+			err(EXIT_FAILURE, "pthread_join");
+}
+
+static void *blocked_workerfn(void *arg __maybe_unused)
+{
+	pthread_mutex_lock(&thread_lock);
+	threads_starting--;
+	if (!threads_starting)
+		pthread_cond_signal(&thread_parent);
+	pthread_cond_wait(&thread_worker, &thread_lock);
+	pthread_mutex_unlock(&thread_lock);
+
+	while (1) { /* handle spurious wakeups */
+		if (futex_wait(&futex, 0, NULL, futex_flag) != EINTR)
+			break;
+	}
+
+	pthread_exit(NULL);
+	return NULL;
+}
+
+static void block_threads(pthread_t *w, pthread_attr_t thread_attr)
+{
+	cpu_set_t cpu;
+	unsigned int i;
+
+	threads_starting = nblocked_threads;
+
+	/* create and block all threads */
+	for (i = 0; i < nblocked_threads; i++) {
+		CPU_ZERO(&cpu);
+		CPU_SET(i % ncpus, &cpu);
+
+		if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpu))
+			err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
+
+		if (pthread_create(&w[i], &thread_attr, blocked_workerfn, NULL))
+			err(EXIT_FAILURE, "pthread_create");
+	}
+}
+
+static void print_run(struct thread_data *waking_worker, unsigned int run_num)
+{
+	unsigned int i, wakeup_avg;
+	double waketime_avg, waketime_stddev;
+	struct stats __waketime_stats, __wakeup_stats;
+
+	init_stats(&__wakeup_stats);
+	init_stats(&__waketime_stats);
+
+	for (i = 0; i < nwaking_threads; i++) {
+		update_stats(&__waketime_stats, waking_worker[i].runtime.tv_usec);
+		update_stats(&__wakeup_stats, waking_worker[i].nwoken);
+	}
+
+	waketime_avg = avg_stats(&__waketime_stats);
+	waketime_stddev = stddev_stats(&__waketime_stats);
+	wakeup_avg = avg_stats(&__wakeup_stats);
+
+	printf("[Run %d]: Avg per-thread latency (waking %d/%d threads) "
+	       "in %.4f ms (+-%.2f%%)\n", run_num + 1, wakeup_avg,
+	       nblocked_threads, waketime_avg/1e3,
+	       rel_stddev_stats(waketime_stddev, waketime_avg));
+}
+
+static void print_summary(void)
+{
+	unsigned int wakeup_avg;
+	double waketime_avg, waketime_stddev;
+
+	waketime_avg = avg_stats(&waketime_stats);
+	waketime_stddev = stddev_stats(&waketime_stats);
+	wakeup_avg = avg_stats(&wakeup_stats);
+
+	printf("Avg per-thread latency (waking %d/%d threads) in %.4f ms (+-%.2f%%)\n",
+	       wakeup_avg,
+	       nblocked_threads,
+	       waketime_avg/1e3,
+	       rel_stddev_stats(waketime_stddev, waketime_avg));
+}
+
+
+static void do_run_stats(struct thread_data *waking_worker)
+{
+	unsigned int i;
+
+	for (i = 0; i < nwaking_threads; i++) {
+		update_stats(&waketime_stats, waking_worker[i].runtime.tv_usec);
+		update_stats(&wakeup_stats, waking_worker[i].nwoken);
+	}
+
+}
+
+static void toggle_done(int sig __maybe_unused,
+			siginfo_t *info __maybe_unused,
+			void *uc __maybe_unused)
+{
+	done = true;
+}
+
+int bench_futex_wake_parallel(int argc, const char **argv,
+			      const char *prefix __maybe_unused)
+{
+	int ret = 0;
+	unsigned int i, j;
+	struct sigaction act;
+	pthread_attr_t thread_attr;
+	struct thread_data *waking_worker;
+
+	argc = parse_options(argc, argv, options,
+			     bench_futex_wake_parallel_usage, 0);
+	if (argc) {
+		usage_with_options(bench_futex_wake_parallel_usage, options);
+		exit(EXIT_FAILURE);
+	}
+
+	sigfillset(&act.sa_mask);
+	act.sa_sigaction = toggle_done;
+	sigaction(SIGINT, &act, NULL);
+
+	ncpus = sysconf(_SC_NPROCESSORS_ONLN);
+	if (!nblocked_threads)
+		nblocked_threads = ncpus;
+
+	/* some sanity checks */
+	if (nwaking_threads > nblocked_threads || !nwaking_threads)
+		nwaking_threads = nblocked_threads;
+
+	if (nblocked_threads % nwaking_threads)
+		errx(EXIT_FAILURE, "Must be perfectly divisible");
+	/*
+	 * Each thread will wakeup nwakes tasks in
+	 * a single futex_wait call.
+	 */
+	nwakes = nblocked_threads/nwaking_threads;
+
+	blocked_worker = calloc(nblocked_threads, sizeof(*blocked_worker));
+	if (!blocked_worker)
+		err(EXIT_FAILURE, "calloc");
+
+	if (!fshared)
+		futex_flag = FUTEX_PRIVATE_FLAG;
+
+	printf("Run summary [PID %d]: blocking on %d threads (at [%s] "
+	       "futex %p), %d threads waking up %d at a time.\n\n",
+	       getpid(), nblocked_threads, fshared ? "shared":"private",
+	       &futex, nwaking_threads, nwakes);
+
+	init_stats(&wakeup_stats);
+	init_stats(&waketime_stats);
+
+	pthread_attr_init(&thread_attr);
+	pthread_mutex_init(&thread_lock, NULL);
+	pthread_cond_init(&thread_parent, NULL);
+	pthread_cond_init(&thread_worker, NULL);
+
+	for (j = 0; j < bench_repeat && !done; j++) {
+		waking_worker = calloc(nwaking_threads, sizeof(*waking_worker));
+		if (!waking_worker)
+			err(EXIT_FAILURE, "calloc");
+
+		/* create, launch & block all threads */
+		block_threads(blocked_worker, thread_attr);
+
+		/* make sure all threads are already blocked */
+		pthread_mutex_lock(&thread_lock);
+		while (threads_starting)
+			pthread_cond_wait(&thread_parent, &thread_lock);
+		pthread_cond_broadcast(&thread_worker);
+		pthread_mutex_unlock(&thread_lock);
+
+		usleep(100000);
+
+		/* Ok, all threads are patiently blocked, start waking folks up */
+		wakeup_threads(waking_worker, thread_attr);
+
+		for (i = 0; i < nblocked_threads; i++) {
+			ret = pthread_join(blocked_worker[i], NULL);
+			if (ret)
+				err(EXIT_FAILURE, "pthread_join");
+		}
+
+		do_run_stats(waking_worker);
+		if (!silent)
+			print_run(waking_worker, j);
+
+		free(waking_worker);
+	}
+
+	/* cleanup & report results */
+	pthread_cond_destroy(&thread_parent);
+	pthread_cond_destroy(&thread_worker);
+	pthread_mutex_destroy(&thread_lock);
+	pthread_attr_destroy(&thread_attr);
+
+	print_summary();
+
+	free(blocked_worker);
+	return ret;
+}
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
index 929f762be47e..e5e41d3bdce7 100644
--- a/tools/perf/bench/futex-wake.c
+++ b/tools/perf/bench/futex-wake.c
@@ -60,7 +60,12 @@ static void *workerfn(void *arg __maybe_unused)
 	pthread_cond_wait(&thread_worker, &thread_lock);
 	pthread_mutex_unlock(&thread_lock);
 
-	futex_wait(&futex1, 0, NULL, futex_flag);
+	while (1) {
+		if (futex_wait(&futex1, 0, NULL, futex_flag) != EINTR)
+			break;
+	}
+
+	pthread_exit(NULL);
 	return NULL;
 }
 
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index ba5efa4710b5..870b7e665a20 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -8,6 +8,7 @@
 #include "../builtin.h"
 #include "../util/util.h"
 #include "../util/parse-options.h"
+#include "../util/cloexec.h"
 
 #include "bench.h"
 
@@ -23,6 +24,7 @@
 #include <pthread.h>
 #include <sys/mman.h>
 #include <sys/time.h>
+#include <sys/resource.h>
 #include <sys/wait.h>
 #include <sys/prctl.h>
 #include <sys/types.h>
@@ -51,6 +53,9 @@ struct thread_data {
 	unsigned int		loops_done;
 	u64			val;
 	u64			runtime_ns;
+	u64			system_time_ns;
+	u64			user_time_ns;
+	double			speed_gbs;
 	pthread_mutex_t		*process_lock;
 };
 
@@ -1042,6 +1047,7 @@ static void *worker_thread(void *__tdata)
 	u64 bytes_done;
 	long work_done;
 	u32 l;
+	struct rusage rusage;
 
 	bind_to_cpumask(td->bind_cpumask);
 	bind_to_memnode(td->bind_node);
@@ -1194,6 +1200,13 @@ static void *worker_thread(void *__tdata)
 	timersub(&stop, &start0, &diff);
 	td->runtime_ns = diff.tv_sec * 1000000000ULL;
 	td->runtime_ns += diff.tv_usec * 1000ULL;
+	td->speed_gbs = bytes_done / (td->runtime_ns / 1e9) / 1e9;
+
+	getrusage(RUSAGE_THREAD, &rusage);
+	td->system_time_ns = rusage.ru_stime.tv_sec * 1000000000ULL;
+	td->system_time_ns += rusage.ru_stime.tv_usec * 1000ULL;
+	td->user_time_ns = rusage.ru_utime.tv_sec * 1000000000ULL;
+	td->user_time_ns += rusage.ru_utime.tv_usec * 1000ULL;
 
 	free_data(thread_data, g->p.bytes_thread);
 
@@ -1420,7 +1433,7 @@ static int __bench_numa(const char *name)
 	double runtime_sec_min;
 	int wait_stat;
 	double bytes;
-	int i, t;
+	int i, t, p;
 
 	if (init())
 		return -1;
@@ -1556,6 +1569,24 @@ static int __bench_numa(const char *name)
 	print_res(name, bytes / runtime_sec_max / 1e9,
 		"GB/sec,", "total-speed",	"GB/sec total speed");
 
+	if (g->p.show_details >= 2) {
+		char tname[32];
+		struct thread_data *td;
+		for (p = 0; p < g->p.nr_proc; p++) {
+			for (t = 0; t < g->p.nr_threads; t++) {
+				memset(tname, 0, 32);
+				td = g->threads + p*g->p.nr_threads + t;
+				snprintf(tname, 32, "process%d:thread%d", p, t);
+				print_res(tname, td->speed_gbs,
+					"GB/sec",	"thread-speed", "GB/sec/thread speed");
+				print_res(tname, td->system_time_ns / 1e9,
+					"secs",	"thread-system-time", "system CPU time/thread");
+				print_res(tname, td->user_time_ns / 1e9,
+					"secs",	"thread-user-time", "user CPU time/thread");
+			}
+		}
+	}
+
 	free(pids);
 
 	deinit();
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 71bf7451c0ca..2c1bec39c30e 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -59,6 +59,10 @@ static int perf_evsel__add_sample(struct perf_evsel *evsel,
 	    (al->sym == NULL ||
 	     strcmp(ann->sym_hist_filter, al->sym->name) != 0)) {
 		/* We're only interested in a symbol named sym_hist_filter */
+		/*
+		 * FIXME: why isn't this done in the symbol_filter when loading
+		 * the DSO?
+		 */
 		if (al->sym != NULL) {
 			rb_erase(&al->sym->rb_node,
 				 &al->map->dso->symbols[al->map->type]);
@@ -84,6 +88,7 @@ static int process_sample_event(struct perf_tool *tool,
 {
 	struct perf_annotate *ann = container_of(tool, struct perf_annotate, tool);
 	struct addr_location al;
+	int ret = 0;
 
 	if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
 		pr_warning("problem processing %d event, skipping it.\n",
@@ -92,15 +97,16 @@ static int process_sample_event(struct perf_tool *tool,
 	}
 
 	if (ann->cpu_list && !test_bit(sample->cpu, ann->cpu_bitmap))
-		return 0;
+		goto out_put;
 
 	if (!al.filtered && perf_evsel__add_sample(evsel, sample, &al, ann)) {
 		pr_warning("problem incrementing symbol count, "
 			   "skipping event\n");
-		return -1;
+		ret = -1;
 	}
-
-	return 0;
+out_put:
+	addr_location__put(&al);
+	return ret;
 }
 
 static int hist_entry__tty_annotate(struct hist_entry *he,
@@ -283,7 +289,6 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
 		},
 	};
 	struct perf_data_file file = {
-		.path  = input_name,
 		.mode  = PERF_DATA_MODE_READ,
 	};
 	const struct option options[] = {
@@ -324,6 +329,8 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
 		   "objdump binary to use for disassembly and annotations"),
 	OPT_BOOLEAN(0, "group", &symbol_conf.event_group,
 		    "Show event group information together"),
+	OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period,
+		    "Show a column with the sum of periods"),
 	OPT_END()
 	};
 	int ret = hists__init();
@@ -340,6 +347,8 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
 	else if (annotate.use_gtk)
 		use_browser = 2;
 
+	file.path  = input_name;
+
 	setup_browser(true);
 
 	annotate.session = perf_session__new(&file, false, &annotate.tool);
diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c
index b9a56fa83330..b5314e452ec7 100644
--- a/tools/perf/builtin-bench.c
+++ b/tools/perf/builtin-bench.c
@@ -58,6 +58,7 @@ static struct bench mem_benchmarks[] = {
 static struct bench futex_benchmarks[] = {
 	{ "hash",	"Benchmark for futex hash table",               bench_futex_hash	},
 	{ "wake",	"Benchmark for futex wake calls",               bench_futex_wake	},
+	{ "wake-parallel", "Benchmark for parallel futex wake calls",   bench_futex_wake_parallel },
 	{ "requeue",	"Benchmark for futex requeue calls",            bench_futex_requeue	},
 	{ "all",	"Test all futex benchmarks",			NULL			},
 	{ NULL,		NULL,						NULL			}
diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c
index feb420f74c2d..9fe93c8d4fcf 100644
--- a/tools/perf/builtin-buildid-list.c
+++ b/tools/perf/builtin-buildid-list.c
@@ -69,6 +69,15 @@ static int perf_session__list_build_ids(bool force, bool with_hits)
 	session = perf_session__new(&file, false, &build_id__mark_dso_hit_ops);
 	if (session == NULL)
 		return -1;
+
+	/*
+	 * We take all buildids when the file contains AUX area tracing data
+	 * because we do not decode the trace because it would take too long.
+	 */
+	if (!perf_data_file__is_pipe(&file) &&
+	    perf_header__has_feat(&session->header, HEADER_AUXTRACE))
+		with_hits = false;
+
 	/*
 	 * in pipe-mode, the only way to get the buildids is to parse
 	 * the record stream. Buildids are stored as RECORD_HEADER_BUILD_ID
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index df6307b4050a..daaa7dca9c3b 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -328,6 +328,7 @@ static int diff__process_sample_event(struct perf_tool *tool __maybe_unused,
 {
 	struct addr_location al;
 	struct hists *hists = evsel__hists(evsel);
+	int ret = -1;
 
 	if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
 		pr_warning("problem processing %d event, skipping it.\n",
@@ -338,7 +339,7 @@ static int diff__process_sample_event(struct perf_tool *tool __maybe_unused,
 	if (hists__add_entry(hists, &al, sample->period,
 			     sample->weight, sample->transaction)) {
 		pr_warning("problem incrementing symbol period, skipping event\n");
-		return -1;
+		goto out_put;
 	}
 
 	/*
@@ -350,8 +351,10 @@ static int diff__process_sample_event(struct perf_tool *tool __maybe_unused,
 	hists->stats.total_period += sample->period;
 	if (!al.filtered)
 		hists->stats.total_non_filtered_period += sample->period;
-
-	return 0;
+	ret = 0;
+out_put:
+	addr_location__put(&al);
+	return ret;
 }
 
 static struct perf_tool tool = {
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 40a33d7334cc..52ec66b23607 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -16,6 +16,7 @@
 #include "util/debug.h"
 #include "util/build-id.h"
 #include "util/data.h"
+#include "util/auxtrace.h"
 
 #include "util/parse-options.h"
 
@@ -26,10 +27,12 @@ struct perf_inject {
 	struct perf_session	*session;
 	bool			build_ids;
 	bool			sched_stat;
+	bool			have_auxtrace;
 	const char		*input_name;
 	struct perf_data_file	output;
 	u64			bytes_written;
 	struct list_head	samples;
+	struct itrace_synth_opts itrace_synth_opts;
 };
 
 struct event_entry {
@@ -38,14 +41,11 @@ struct event_entry {
 	union perf_event event[0];
 };
 
-static int perf_event__repipe_synth(struct perf_tool *tool,
-				    union perf_event *event)
+static int output_bytes(struct perf_inject *inject, void *buf, size_t sz)
 {
-	struct perf_inject *inject = container_of(tool, struct perf_inject, tool);
 	ssize_t size;
 
-	size = perf_data_file__write(&inject->output, event,
-				     event->header.size);
+	size = perf_data_file__write(&inject->output, buf, sz);
 	if (size < 0)
 		return -errno;
 
@@ -53,6 +53,15 @@ static int perf_event__repipe_synth(struct perf_tool *tool,
 	return 0;
 }
 
+static int perf_event__repipe_synth(struct perf_tool *tool,
+				    union perf_event *event)
+{
+	struct perf_inject *inject = container_of(tool, struct perf_inject,
+						  tool);
+
+	return output_bytes(inject, event, event->header.size);
+}
+
 static int perf_event__repipe_oe_synth(struct perf_tool *tool,
 				       union perf_event *event,
 				       struct ordered_events *oe __maybe_unused)
@@ -86,6 +95,79 @@ static int perf_event__repipe_attr(struct perf_tool *tool,
 	return perf_event__repipe_synth(tool, event);
 }
 
+#ifdef HAVE_AUXTRACE_SUPPORT
+
+static int copy_bytes(struct perf_inject *inject, int fd, off_t size)
+{
+	char buf[4096];
+	ssize_t ssz;
+	int ret;
+
+	while (size > 0) {
+		ssz = read(fd, buf, min(size, (off_t)sizeof(buf)));
+		if (ssz < 0)
+			return -errno;
+		ret = output_bytes(inject, buf, ssz);
+		if (ret)
+			return ret;
+		size -= ssz;
+	}
+
+	return 0;
+}
+
+static s64 perf_event__repipe_auxtrace(struct perf_tool *tool,
+				       union perf_event *event,
+				       struct perf_session *session
+				       __maybe_unused)
+{
+	struct perf_inject *inject = container_of(tool, struct perf_inject,
+						  tool);
+	int ret;
+
+	inject->have_auxtrace = true;
+
+	if (!inject->output.is_pipe) {
+		off_t offset;
+
+		offset = lseek(inject->output.fd, 0, SEEK_CUR);
+		if (offset == -1)
+			return -errno;
+		ret = auxtrace_index__auxtrace_event(&session->auxtrace_index,
+						     event, offset);
+		if (ret < 0)
+			return ret;
+	}
+
+	if (perf_data_file__is_pipe(session->file) || !session->one_mmap) {
+		ret = output_bytes(inject, event, event->header.size);
+		if (ret < 0)
+			return ret;
+		ret = copy_bytes(inject, perf_data_file__fd(session->file),
+				 event->auxtrace.size);
+	} else {
+		ret = output_bytes(inject, event,
+				   event->header.size + event->auxtrace.size);
+	}
+	if (ret < 0)
+		return ret;
+
+	return event->auxtrace.size;
+}
+
+#else
+
+static s64
+perf_event__repipe_auxtrace(struct perf_tool *tool __maybe_unused,
+			    union perf_event *event __maybe_unused,
+			    struct perf_session *session __maybe_unused)
+{
+	pr_err("AUX area tracing not supported\n");
+	return -EINVAL;
+}
+
+#endif
+
 static int perf_event__repipe(struct perf_tool *tool,
 			      union perf_event *event,
 			      struct perf_sample *sample __maybe_unused,
@@ -155,6 +237,32 @@ static int perf_event__repipe_fork(struct perf_tool *tool,
 	return err;
 }
 
+static int perf_event__repipe_comm(struct perf_tool *tool,
+				   union perf_event *event,
+				   struct perf_sample *sample,
+				   struct machine *machine)
+{
+	int err;
+
+	err = perf_event__process_comm(tool, event, sample, machine);
+	perf_event__repipe(tool, event, sample, machine);
+
+	return err;
+}
+
+static int perf_event__repipe_exit(struct perf_tool *tool,
+				   union perf_event *event,
+				   struct perf_sample *sample,
+				   struct machine *machine)
+{
+	int err;
+
+	err = perf_event__process_exit(tool, event, sample, machine);
+	perf_event__repipe(tool, event, sample, machine);
+
+	return err;
+}
+
 static int perf_event__repipe_tracing_data(struct perf_tool *tool,
 					   union perf_event *event,
 					   struct perf_session *session)
@@ -167,6 +275,18 @@ static int perf_event__repipe_tracing_data(struct perf_tool *tool,
 	return err;
 }
 
+static int perf_event__repipe_id_index(struct perf_tool *tool,
+				       union perf_event *event,
+				       struct perf_session *session)
+{
+	int err;
+
+	perf_event__repipe_synth(tool, event);
+	err = perf_event__process_id_index(tool, event, session);
+
+	return err;
+}
+
 static int dso__read_build_id(struct dso *dso)
 {
 	if (dso->has_build_id)
@@ -245,6 +365,7 @@ static int perf_event__inject_buildid(struct perf_tool *tool,
 		}
 	}
 
+	thread__put(thread);
 repipe:
 	perf_event__repipe(tool, event, sample, machine);
 	return 0;
@@ -351,16 +472,20 @@ static int __cmd_inject(struct perf_inject *inject)
 	struct perf_session *session = inject->session;
 	struct perf_data_file *file_out = &inject->output;
 	int fd = perf_data_file__fd(file_out);
+	u64 output_data_offset;
 
 	signal(SIGINT, sig_handler);
 
-	if (inject->build_ids || inject->sched_stat) {
+	if (inject->build_ids || inject->sched_stat ||
+	    inject->itrace_synth_opts.set) {
 		inject->tool.mmap	  = perf_event__repipe_mmap;
 		inject->tool.mmap2	  = perf_event__repipe_mmap2;
 		inject->tool.fork	  = perf_event__repipe_fork;
 		inject->tool.tracing_data = perf_event__repipe_tracing_data;
 	}
 
+	output_data_offset = session->header.data_offset;
+
 	if (inject->build_ids) {
 		inject->tool.sample = perf_event__inject_buildid;
 	} else if (inject->sched_stat) {
@@ -379,17 +504,43 @@ static int __cmd_inject(struct perf_inject *inject)
 			else if (!strncmp(name, "sched:sched_stat_", 17))
 				evsel->handler = perf_inject__sched_stat;
 		}
+	} else if (inject->itrace_synth_opts.set) {
+		session->itrace_synth_opts = &inject->itrace_synth_opts;
+		inject->itrace_synth_opts.inject = true;
+		inject->tool.comm	    = perf_event__repipe_comm;
+		inject->tool.exit	    = perf_event__repipe_exit;
+		inject->tool.id_index	    = perf_event__repipe_id_index;
+		inject->tool.auxtrace_info  = perf_event__process_auxtrace_info;
+		inject->tool.auxtrace	    = perf_event__process_auxtrace;
+		inject->tool.ordered_events = true;
+		inject->tool.ordering_requires_timestamps = true;
+		/* Allow space in the header for new attributes */
+		output_data_offset = 4096;
 	}
 
+	if (!inject->itrace_synth_opts.set)
+		auxtrace_index__free(&session->auxtrace_index);
+
 	if (!file_out->is_pipe)
-		lseek(fd, session->header.data_offset, SEEK_SET);
+		lseek(fd, output_data_offset, SEEK_SET);
 
 	ret = perf_session__process_events(session);
 
 	if (!file_out->is_pipe) {
-		if (inject->build_ids)
+		if (inject->build_ids) {
 			perf_header__set_feat(&session->header,
 					      HEADER_BUILD_ID);
+			if (inject->have_auxtrace)
+				dsos__hit_all(session);
+		}
+		/*
+		 * The AUX areas have been removed and replaced with
+		 * synthesized hardware events, so clear the feature flag.
+		 */
+		if (inject->itrace_synth_opts.set)
+			perf_header__clear_feat(&session->header,
+						HEADER_AUXTRACE);
+		session->header.data_offset = output_data_offset;
 		session->header.data_size = inject->bytes_written;
 		perf_session__write_header(session, session->evlist, fd, true);
 	}
@@ -408,11 +559,16 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
 			.fork		= perf_event__repipe,
 			.exit		= perf_event__repipe,
 			.lost		= perf_event__repipe,
+			.aux		= perf_event__repipe,
+			.itrace_start	= perf_event__repipe,
 			.read		= perf_event__repipe_sample,
 			.throttle	= perf_event__repipe,
 			.unthrottle	= perf_event__repipe,
 			.attr		= perf_event__repipe_attr,
 			.tracing_data	= perf_event__repipe_op2_synth,
+			.auxtrace_info	= perf_event__repipe_op2_synth,
+			.auxtrace	= perf_event__repipe_auxtrace,
+			.auxtrace_error	= perf_event__repipe_op2_synth,
 			.finished_round	= perf_event__repipe_oe_synth,
 			.build_id	= perf_event__repipe_op2_synth,
 			.id_index	= perf_event__repipe_op2_synth,
@@ -444,6 +600,9 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
 		OPT_STRING(0, "kallsyms", &symbol_conf.kallsyms_name, "file",
 			   "kallsyms pathname"),
 		OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"),
+		OPT_CALLBACK_OPTARG(0, "itrace", &inject.itrace_synth_opts,
+				    NULL, "opts", "Instruction Tracing options",
+				    itrace_parse_synth_opts),
 		OPT_END()
 	};
 	const char * const inject_usage[] = {
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 1634186d537c..950f296dfcf7 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -10,6 +10,7 @@
 #include "util/header.h"
 #include "util/session.h"
 #include "util/tool.h"
+#include "util/callchain.h"
 
 #include "util/parse-options.h"
 #include "util/trace-event.h"
@@ -21,14 +22,19 @@
 #include <linux/rbtree.h>
 #include <linux/string.h>
 #include <locale.h>
+#include <regex.h>
 
 static int	kmem_slab;
 static int	kmem_page;
 
 static long	kmem_page_size;
+static enum {
+	KMEM_SLAB,
+	KMEM_PAGE,
+} kmem_default = KMEM_SLAB;  /* for backward compatibility */
 
 struct alloc_stat;
-typedef int (*sort_fn_t)(struct alloc_stat *, struct alloc_stat *);
+typedef int (*sort_fn_t)(void *, void *);
 
 static int			alloc_flag;
 static int			caller_flag;
@@ -179,8 +185,8 @@ static int perf_evsel__process_alloc_node_event(struct perf_evsel *evsel,
 	return ret;
 }
 
-static int ptr_cmp(struct alloc_stat *, struct alloc_stat *);
-static int callsite_cmp(struct alloc_stat *, struct alloc_stat *);
+static int ptr_cmp(void *, void *);
+static int slab_callsite_cmp(void *, void *);
 
 static struct alloc_stat *search_alloc_stat(unsigned long ptr,
 					    unsigned long call_site,
@@ -221,7 +227,8 @@ static int perf_evsel__process_free_event(struct perf_evsel *evsel,
 		s_alloc->pingpong++;
 
 		s_caller = search_alloc_stat(0, s_alloc->call_site,
-					     &root_caller_stat, callsite_cmp);
+					     &root_caller_stat,
+					     slab_callsite_cmp);
 		if (!s_caller)
 			return -1;
 		s_caller->pingpong++;
@@ -241,6 +248,8 @@ static unsigned long nr_page_fails;
 static unsigned long nr_page_nomatch;
 
 static bool use_pfn;
+static bool live_page;
+static struct perf_session *kmem_session;
 
 #define MAX_MIGRATE_TYPES  6
 #define MAX_PAGE_ORDER     11
@@ -250,6 +259,7 @@ static int order_stats[MAX_PAGE_ORDER][MAX_MIGRATE_TYPES];
 struct page_stat {
 	struct rb_node 	node;
 	u64 		page;
+	u64 		callsite;
 	int 		order;
 	unsigned 	gfp_flags;
 	unsigned 	migrate_type;
@@ -259,13 +269,158 @@ struct page_stat {
 	int 		nr_free;
 };
 
-static struct rb_root page_tree;
+static struct rb_root page_live_tree;
 static struct rb_root page_alloc_tree;
 static struct rb_root page_alloc_sorted;
+static struct rb_root page_caller_tree;
+static struct rb_root page_caller_sorted;
 
-static struct page_stat *search_page(unsigned long page, bool create)
+struct alloc_func {
+	u64 start;
+	u64 end;
+	char *name;
+};
+
+static int nr_alloc_funcs;
+static struct alloc_func *alloc_func_list;
+
+static int funcmp(const void *a, const void *b)
+{
+	const struct alloc_func *fa = a;
+	const struct alloc_func *fb = b;
+
+	if (fa->start > fb->start)
+		return 1;
+	else
+		return -1;
+}
+
+static int callcmp(const void *a, const void *b)
+{
+	const struct alloc_func *fa = a;
+	const struct alloc_func *fb = b;
+
+	if (fb->start <= fa->start && fa->end < fb->end)
+		return 0;
+
+	if (fa->start > fb->start)
+		return 1;
+	else
+		return -1;
+}
+
+static int build_alloc_func_list(void)
 {
-	struct rb_node **node = &page_tree.rb_node;
+	int ret;
+	struct map *kernel_map;
+	struct symbol *sym;
+	struct rb_node *node;
+	struct alloc_func *func;
+	struct machine *machine = &kmem_session->machines.host;
+	regex_t alloc_func_regex;
+	const char pattern[] = "^_?_?(alloc|get_free|get_zeroed)_pages?";
+
+	ret = regcomp(&alloc_func_regex, pattern, REG_EXTENDED);
+	if (ret) {
+		char err[BUFSIZ];
+
+		regerror(ret, &alloc_func_regex, err, sizeof(err));
+		pr_err("Invalid regex: %s\n%s", pattern, err);
+		return -EINVAL;
+	}
+
+	kernel_map = machine->vmlinux_maps[MAP__FUNCTION];
+	if (map__load(kernel_map, NULL) < 0) {
+		pr_err("cannot load kernel map\n");
+		return -ENOENT;
+	}
+
+	map__for_each_symbol(kernel_map, sym, node) {
+		if (regexec(&alloc_func_regex, sym->name, 0, NULL, 0))
+			continue;
+
+		func = realloc(alloc_func_list,
+			       (nr_alloc_funcs + 1) * sizeof(*func));
+		if (func == NULL)
+			return -ENOMEM;
+
+		pr_debug("alloc func: %s\n", sym->name);
+		func[nr_alloc_funcs].start = sym->start;
+		func[nr_alloc_funcs].end   = sym->end;
+		func[nr_alloc_funcs].name  = sym->name;
+
+		alloc_func_list = func;
+		nr_alloc_funcs++;
+	}
+
+	qsort(alloc_func_list, nr_alloc_funcs, sizeof(*func), funcmp);
+
+	regfree(&alloc_func_regex);
+	return 0;
+}
+
+/*
+ * Find first non-memory allocation function from callchain.
+ * The allocation functions are in the 'alloc_func_list'.
+ */
+static u64 find_callsite(struct perf_evsel *evsel, struct perf_sample *sample)
+{
+	struct addr_location al;
+	struct machine *machine = &kmem_session->machines.host;
+	struct callchain_cursor_node *node;
+
+	if (alloc_func_list == NULL) {
+		if (build_alloc_func_list() < 0)
+			goto out;
+	}
+
+	al.thread = machine__findnew_thread(machine, sample->pid, sample->tid);
+	sample__resolve_callchain(sample, NULL, evsel, &al, 16);
+
+	callchain_cursor_commit(&callchain_cursor);
+	while (true) {
+		struct alloc_func key, *caller;
+		u64 addr;
+
+		node = callchain_cursor_current(&callchain_cursor);
+		if (node == NULL)
+			break;
+
+		key.start = key.end = node->ip;
+		caller = bsearch(&key, alloc_func_list, nr_alloc_funcs,
+				 sizeof(key), callcmp);
+		if (!caller) {
+			/* found */
+			if (node->map)
+				addr = map__unmap_ip(node->map, node->ip);
+			else
+				addr = node->ip;
+
+			return addr;
+		} else
+			pr_debug3("skipping alloc function: %s\n", caller->name);
+
+		callchain_cursor_advance(&callchain_cursor);
+	}
+
+out:
+	pr_debug2("unknown callsite: %"PRIx64 "\n", sample->ip);
+	return sample->ip;
+}
+
+struct sort_dimension {
+	const char		name[20];
+	sort_fn_t		cmp;
+	struct list_head	list;
+};
+
+static LIST_HEAD(page_alloc_sort_input);
+static LIST_HEAD(page_caller_sort_input);
+
+static struct page_stat *
+__page_stat__findnew_page(struct page_stat *pstat, bool create)
+{
+	struct rb_node **node = &page_live_tree.rb_node;
 	struct rb_node *parent = NULL;
 	struct page_stat *data;
 
@@ -275,7 +430,7 @@ static struct page_stat *search_page(unsigned long page, bool create)
 		parent = *node;
 		data = rb_entry(*node, struct page_stat, node);
 
-		cmp = data->page - page;
+		cmp = data->page - pstat->page;
 		if (cmp < 0)
 			node = &parent->rb_left;
 		else if (cmp > 0)
@@ -289,49 +444,48 @@ static struct page_stat *search_page(unsigned long page, bool create)
 
 	data = zalloc(sizeof(*data));
 	if (data != NULL) {
-		data->page = page;
+		data->page = pstat->page;
+		data->order = pstat->order;
+		data->gfp_flags = pstat->gfp_flags;
+		data->migrate_type = pstat->migrate_type;
 
 		rb_link_node(&data->node, parent, node);
-		rb_insert_color(&data->node, &page_tree);
+		rb_insert_color(&data->node, &page_live_tree);
 	}
 
 	return data;
 }
 
-static int page_stat_cmp(struct page_stat *a, struct page_stat *b)
+static struct page_stat *page_stat__find_page(struct page_stat *pstat)
 {
-	if (a->page > b->page)
-		return -1;
-	if (a->page < b->page)
-		return 1;
-	if (a->order > b->order)
-		return -1;
-	if (a->order < b->order)
-		return 1;
-	if (a->migrate_type > b->migrate_type)
-		return -1;
-	if (a->migrate_type < b->migrate_type)
-		return 1;
-	if (a->gfp_flags > b->gfp_flags)
-		return -1;
-	if (a->gfp_flags < b->gfp_flags)
-		return 1;
-	return 0;
+	return __page_stat__findnew_page(pstat, false);
+}
+
+static struct page_stat *page_stat__findnew_page(struct page_stat *pstat)
+{
+	return __page_stat__findnew_page(pstat, true);
 }
 
-static struct page_stat *search_page_alloc_stat(struct page_stat *pstat, bool create)
+static struct page_stat *
+__page_stat__findnew_alloc(struct page_stat *pstat, bool create)
 {
 	struct rb_node **node = &page_alloc_tree.rb_node;
 	struct rb_node *parent = NULL;
 	struct page_stat *data;
+	struct sort_dimension *sort;
 
 	while (*node) {
-		s64 cmp;
+		int cmp = 0;
 
 		parent = *node;
 		data = rb_entry(*node, struct page_stat, node);
 
-		cmp = page_stat_cmp(data, pstat);
+		list_for_each_entry(sort, &page_alloc_sort_input, list) {
+			cmp = sort->cmp(pstat, data);
+			if (cmp)
+				break;
+		}
+
 		if (cmp < 0)
 			node = &parent->rb_left;
 		else if (cmp > 0)
@@ -357,6 +511,71 @@ static struct page_stat *search_page_alloc_stat(struct page_stat *pstat, bool cr
 	return data;
 }
 
+static struct page_stat *page_stat__find_alloc(struct page_stat *pstat)
+{
+	return __page_stat__findnew_alloc(pstat, false);
+}
+
+static struct page_stat *page_stat__findnew_alloc(struct page_stat *pstat)
+{
+	return __page_stat__findnew_alloc(pstat, true);
+}
+
+static struct page_stat *
+__page_stat__findnew_caller(struct page_stat *pstat, bool create)
+{
+	struct rb_node **node = &page_caller_tree.rb_node;
+	struct rb_node *parent = NULL;
+	struct page_stat *data;
+	struct sort_dimension *sort;
+
+	while (*node) {
+		int cmp = 0;
+
+		parent = *node;
+		data = rb_entry(*node, struct page_stat, node);
+
+		list_for_each_entry(sort, &page_caller_sort_input, list) {
+			cmp = sort->cmp(pstat, data);
+			if (cmp)
+				break;
+		}
+
+		if (cmp < 0)
+			node = &parent->rb_left;
+		else if (cmp > 0)
+			node = &parent->rb_right;
+		else
+			return data;
+	}
+
+	if (!create)
+		return NULL;
+
+	data = zalloc(sizeof(*data));
+	if (data != NULL) {
+		data->callsite = pstat->callsite;
+		data->order = pstat->order;
+		data->gfp_flags = pstat->gfp_flags;
+		data->migrate_type = pstat->migrate_type;
+
+		rb_link_node(&data->node, parent, node);
+		rb_insert_color(&data->node, &page_caller_tree);
+	}
+
+	return data;
+}
+
+static struct page_stat *page_stat__find_caller(struct page_stat *pstat)
+{
+	return __page_stat__findnew_caller(pstat, false);
+}
+
+static struct page_stat *page_stat__findnew_caller(struct page_stat *pstat)
+{
+	return __page_stat__findnew_caller(pstat, true);
+}
+
 static bool valid_page(u64 pfn_or_page)
 {
 	if (use_pfn && pfn_or_page == -1UL)
@@ -366,6 +585,176 @@ static bool valid_page(u64 pfn_or_page)
 	return true;
 }
 
+struct gfp_flag {
+	unsigned int flags;
+	char *compact_str;
+	char *human_readable;
+};
+
+static struct gfp_flag *gfps;
+static int nr_gfps;
+
+static int gfpcmp(const void *a, const void *b)
+{
+	const struct gfp_flag *fa = a;
+	const struct gfp_flag *fb = b;
+
+	return fa->flags - fb->flags;
+}
+
+/* see include/trace/events/gfpflags.h */
+static const struct {
+	const char *original;
+	const char *compact;
+} gfp_compact_table[] = {
+	{ "GFP_TRANSHUGE",		"THP" },
+	{ "GFP_HIGHUSER_MOVABLE",	"HUM" },
+	{ "GFP_HIGHUSER",		"HU" },
+	{ "GFP_USER",			"U" },
+	{ "GFP_TEMPORARY",		"TMP" },
+	{ "GFP_KERNEL",			"K" },
+	{ "GFP_NOFS",			"NF" },
+	{ "GFP_ATOMIC",			"A" },
+	{ "GFP_NOIO",			"NI" },
+	{ "GFP_HIGH",			"H" },
+	{ "GFP_WAIT",			"W" },
+	{ "GFP_IO",			"I" },
+	{ "GFP_COLD",			"CO" },
+	{ "GFP_NOWARN",			"NWR" },
+	{ "GFP_REPEAT",			"R" },
+	{ "GFP_NOFAIL",			"NF" },
+	{ "GFP_NORETRY",		"NR" },
+	{ "GFP_COMP",			"C" },
+	{ "GFP_ZERO",			"Z" },
+	{ "GFP_NOMEMALLOC",		"NMA" },
+	{ "GFP_MEMALLOC",		"MA" },
+	{ "GFP_HARDWALL",		"HW" },
+	{ "GFP_THISNODE",		"TN" },
+	{ "GFP_RECLAIMABLE",		"RC" },
+	{ "GFP_MOVABLE",		"M" },
+	{ "GFP_NOTRACK",		"NT" },
+	{ "GFP_NO_KSWAPD",		"NK" },
+	{ "GFP_OTHER_NODE",		"ON" },
+	{ "GFP_NOWAIT",			"NW" },
+};
+
+static size_t max_gfp_len;
+
+static char *compact_gfp_flags(char *gfp_flags)
+{
+	char *orig_flags = strdup(gfp_flags);
+	char *new_flags = NULL;
+	char *str, *pos = NULL;
+	size_t len = 0;
+
+	if (orig_flags == NULL)
+		return NULL;
+
+	str = strtok_r(orig_flags, "|", &pos);
+	while (str) {
+		size_t i;
+		char *new;
+		const char *cpt;
+
+		for (i = 0; i < ARRAY_SIZE(gfp_compact_table); i++) {
+			if (strcmp(gfp_compact_table[i].original, str))
+				continue;
+
+			cpt = gfp_compact_table[i].compact;
+			new = realloc(new_flags, len + strlen(cpt) + 2);
+			if (new == NULL) {
+				free(new_flags);
+				return NULL;
+			}
+
+			new_flags = new;
+
+			if (!len) {
+				strcpy(new_flags, cpt);
+			} else {
+				strcat(new_flags, "|");
+				strcat(new_flags, cpt);
+				len++;
+			}
+
+			len += strlen(cpt);
+		}
+
+		str = strtok_r(NULL, "|", &pos);
+	}
+
+	if (max_gfp_len < len)
+		max_gfp_len = len;
+
+	free(orig_flags);
+	return new_flags;
+}
+
+static char *compact_gfp_string(unsigned long gfp_flags)
+{
+	struct gfp_flag key = {
+		.flags = gfp_flags,
+	};
+	struct gfp_flag *gfp;
+
+	gfp = bsearch(&key, gfps, nr_gfps, sizeof(*gfps), gfpcmp);
+	if (gfp)
+		return gfp->compact_str;
+
+	return NULL;
+}
+
+static int parse_gfp_flags(struct perf_evsel *evsel, struct perf_sample *sample,
+			   unsigned int gfp_flags)
+{
+	struct pevent_record record = {
+		.cpu = sample->cpu,
+		.data = sample->raw_data,
+		.size = sample->raw_size,
+	};
+	struct trace_seq seq;
+	char *str, *pos = NULL;
+
+	if (nr_gfps) {
+		struct gfp_flag key = {
+			.flags = gfp_flags,
+		};
+
+		if (bsearch(&key, gfps, nr_gfps, sizeof(*gfps), gfpcmp))
+			return 0;
+	}
+
+	trace_seq_init(&seq);
+	pevent_event_info(&seq, evsel->tp_format, &record);
+
+	str = strtok_r(seq.buffer, " ", &pos);
+	while (str) {
+		if (!strncmp(str, "gfp_flags=", 10)) {
+			struct gfp_flag *new;
+
+			new = realloc(gfps, (nr_gfps + 1) * sizeof(*gfps));
+			if (new == NULL)
+				return -ENOMEM;
+
+			gfps = new;
+			new += nr_gfps++;
+
+			new->flags = gfp_flags;
+			new->human_readable = strdup(str + 10);
+			new->compact_str = compact_gfp_flags(str + 10);
+			if (!new->human_readable || !new->compact_str)
+				return -ENOMEM;
+
+			qsort(gfps, nr_gfps, sizeof(*gfps), gfpcmp);
+		}
+
+		str = strtok_r(NULL, " ", &pos);
+	}
+
+	trace_seq_destroy(&seq);
+	return 0;
+}
+
 static int perf_evsel__process_page_alloc_event(struct perf_evsel *evsel,
 						struct perf_sample *sample)
 {
@@ -375,6 +764,7 @@ static int perf_evsel__process_page_alloc_event(struct perf_evsel *evsel,
 	unsigned int migrate_type = perf_evsel__intval(evsel, sample,
 						       "migratetype");
 	u64 bytes = kmem_page_size << order;
+	u64 callsite;
 	struct page_stat *pstat;
 	struct page_stat this = {
 		.order = order,
@@ -397,20 +787,36 @@ static int perf_evsel__process_page_alloc_event(struct perf_evsel *evsel,
 		return 0;
 	}
 
+	if (parse_gfp_flags(evsel, sample, gfp_flags) < 0)
+		return -1;
+
+	callsite = find_callsite(evsel, sample);
+
 	/*
 	 * This is to find the current page (with correct gfp flags and
 	 * migrate type) at free event.
 	 */
-	pstat = search_page(page, true);
+	this.page = page;
+	pstat = page_stat__findnew_page(&this);
 	if (pstat == NULL)
 		return -ENOMEM;
 
-	pstat->order = order;
-	pstat->gfp_flags = gfp_flags;
-	pstat->migrate_type = migrate_type;
+	pstat->nr_alloc++;
+	pstat->alloc_bytes += bytes;
+	pstat->callsite = callsite;
+
+	if (!live_page) {
+		pstat = page_stat__findnew_alloc(&this);
+		if (pstat == NULL)
+			return -ENOMEM;
 
-	this.page = page;
-	pstat = search_page_alloc_stat(&this, true);
+		pstat->nr_alloc++;
+		pstat->alloc_bytes += bytes;
+		pstat->callsite = callsite;
+	}
+
+	this.callsite = callsite;
+	pstat = page_stat__findnew_caller(&this);
 	if (pstat == NULL)
 		return -ENOMEM;
 
@@ -441,7 +847,8 @@ static int perf_evsel__process_page_free_event(struct perf_evsel *evsel,
 	nr_page_frees++;
 	total_page_free_bytes += bytes;
 
-	pstat = search_page(page, false);
+	this.page = page;
+	pstat = page_stat__find_page(&this);
 	if (pstat == NULL) {
 		pr_debug2("missing free at page %"PRIx64" (order: %d)\n",
 			  page, order);
@@ -452,20 +859,41 @@ static int perf_evsel__process_page_free_event(struct perf_evsel *evsel,
 		return 0;
 	}
 
-	this.page = page;
 	this.gfp_flags = pstat->gfp_flags;
 	this.migrate_type = pstat->migrate_type;
+	this.callsite = pstat->callsite;
 
-	rb_erase(&pstat->node, &page_tree);
+	rb_erase(&pstat->node, &page_live_tree);
 	free(pstat);
 
-	pstat = search_page_alloc_stat(&this, false);
+	if (live_page) {
+		order_stats[this.order][this.migrate_type]--;
+	} else {
+		pstat = page_stat__find_alloc(&this);
+		if (pstat == NULL)
+			return -ENOMEM;
+
+		pstat->nr_free++;
+		pstat->free_bytes += bytes;
+	}
+
+	pstat = page_stat__find_caller(&this);
 	if (pstat == NULL)
 		return -ENOENT;
 
 	pstat->nr_free++;
 	pstat->free_bytes += bytes;
 
+	if (live_page) {
+		pstat->nr_alloc--;
+		pstat->alloc_bytes -= bytes;
+
+		if (pstat->nr_alloc == 0) {
+			rb_erase(&pstat->node, &page_caller_tree);
+			free(pstat);
+		}
+	}
+
 	return 0;
 }
 
@@ -478,6 +906,7 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 				struct perf_evsel *evsel,
 				struct machine *machine)
 {
+	int err = 0;
 	struct thread *thread = machine__findnew_thread(machine, sample->pid,
 							sample->tid);
 
@@ -491,10 +920,12 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 
 	if (evsel->handler != NULL) {
 		tracepoint_handler f = evsel->handler;
-		return f(evsel, sample);
+		err = f(evsel, sample);
 	}
 
-	return 0;
+	thread__put(thread);
+
+	return err;
 }
 
 static struct perf_tool perf_kmem = {
@@ -576,41 +1007,111 @@ static const char * const migrate_type_str[] = {
 	"UNKNOWN",
 };
 
-static void __print_page_result(struct rb_root *root,
-				struct perf_session *session __maybe_unused,
-				int n_lines)
+static void __print_page_alloc_result(struct perf_session *session, int n_lines)
 {
-	struct rb_node *next = rb_first(root);
+	struct rb_node *next = rb_first(&page_alloc_sorted);
+	struct machine *machine = &session->machines.host;
 	const char *format;
+	int gfp_len = max(strlen("GFP flags"), max_gfp_len);
 
-	printf("\n%.80s\n", graph_dotted_line);
-	printf(" %-16s | Total alloc (KB) | Hits      | Order | Mig.type | GFP flags\n",
-	       use_pfn ? "PFN" : "Page");
-	printf("%.80s\n", graph_dotted_line);
+	printf("\n%.105s\n", graph_dotted_line);
+	printf(" %-16s | %5s alloc (KB) | Hits      | Order | Mig.type | %-*s | Callsite\n",
+	       use_pfn ? "PFN" : "Page", live_page ? "Live" : "Total",
+	       gfp_len, "GFP flags");
+	printf("%.105s\n", graph_dotted_line);
 
 	if (use_pfn)
-		format = " %16llu | %'16llu | %'9d | %5d | %8s |  %08lx\n";
+		format = " %16llu | %'16llu | %'9d | %5d | %8s | %-*s | %s\n";
 	else
-		format = " %016llx | %'16llu | %'9d | %5d | %8s |  %08lx\n";
+		format = " %016llx | %'16llu | %'9d | %5d | %8s | %-*s | %s\n";
 
 	while (next && n_lines--) {
 		struct page_stat *data;
+		struct symbol *sym;
+		struct map *map;
+		char buf[32];
+		char *caller = buf;
 
 		data = rb_entry(next, struct page_stat, node);
+		sym = machine__find_kernel_function(machine, data->callsite,
+						    &map, NULL);
+		if (sym && sym->name)
+			caller = sym->name;
+		else
+			scnprintf(buf, sizeof(buf), "%"PRIx64, data->callsite);
 
 		printf(format, (unsigned long long)data->page,
 		       (unsigned long long)data->alloc_bytes / 1024,
 		       data->nr_alloc, data->order,
 		       migrate_type_str[data->migrate_type],
-		       (unsigned long)data->gfp_flags);
+		       gfp_len, compact_gfp_string(data->gfp_flags), caller);
 
 		next = rb_next(next);
 	}
 
-	if (n_lines == -1)
-		printf(" ...              | ...              | ...       | ...   | ...      | ...     \n");
+	if (n_lines == -1) {
+		printf(" ...              | ...              | ...       | ...   | ...      | %-*s | ...\n",
+		       gfp_len, "...");
+	}
+
+	printf("%.105s\n", graph_dotted_line);
+}
+
+static void __print_page_caller_result(struct perf_session *session, int n_lines)
+{
+	struct rb_node *next = rb_first(&page_caller_sorted);
+	struct machine *machine = &session->machines.host;
+	int gfp_len = max(strlen("GFP flags"), max_gfp_len);
+
+	printf("\n%.105s\n", graph_dotted_line);
+	printf(" %5s alloc (KB) | Hits      | Order | Mig.type | %-*s | Callsite\n",
+	       live_page ? "Live" : "Total", gfp_len, "GFP flags");
+	printf("%.105s\n", graph_dotted_line);
+
+	while (next && n_lines--) {
+		struct page_stat *data;
+		struct symbol *sym;
+		struct map *map;
+		char buf[32];
+		char *caller = buf;
+
+		data = rb_entry(next, struct page_stat, node);
+		sym = machine__find_kernel_function(machine, data->callsite,
+						    &map, NULL);
+		if (sym && sym->name)
+			caller = sym->name;
+		else
+			scnprintf(buf, sizeof(buf), "%"PRIx64, data->callsite);
+
+		printf(" %'16llu | %'9d | %5d | %8s | %-*s | %s\n",
+		       (unsigned long long)data->alloc_bytes / 1024,
+		       data->nr_alloc, data->order,
+		       migrate_type_str[data->migrate_type],
+		       gfp_len, compact_gfp_string(data->gfp_flags), caller);
+
+		next = rb_next(next);
+	}
+
+	if (n_lines == -1) {
+		printf(" ...              | ...       | ...   | ...      | %-*s | ...\n",
+		       gfp_len, "...");
+	}
 
-	printf("%.80s\n", graph_dotted_line);
+	printf("%.105s\n", graph_dotted_line);
+}
+
+static void print_gfp_flags(void)
+{
+	int i;
+
+	printf("#\n");
+	printf("# GFP flags\n");
+	printf("# ---------\n");
+	for (i = 0; i < nr_gfps; i++) {
+		printf("# %08x: %*s: %s\n", gfps[i].flags,
+		       (int) max_gfp_len, gfps[i].compact_str,
+		       gfps[i].human_readable);
+	}
 }
 
 static void print_slab_summary(void)
@@ -682,8 +1183,12 @@ static void print_slab_result(struct perf_session *session)
 
 static void print_page_result(struct perf_session *session)
 {
+	if (caller_flag || alloc_flag)
+		print_gfp_flags();
+	if (caller_flag)
+		__print_page_caller_result(session, caller_lines);
 	if (alloc_flag)
-		__print_page_result(&page_alloc_sorted, session, alloc_lines);
+		__print_page_alloc_result(session, alloc_lines);
 	print_page_summary();
 }
 
@@ -695,14 +1200,10 @@ static void print_result(struct perf_session *session)
 		print_page_result(session);
 }
 
-struct sort_dimension {
-	const char		name[20];
-	sort_fn_t		cmp;
-	struct list_head	list;
-};
-
-static LIST_HEAD(caller_sort);
-static LIST_HEAD(alloc_sort);
+static LIST_HEAD(slab_caller_sort);
+static LIST_HEAD(slab_alloc_sort);
+static LIST_HEAD(page_caller_sort);
+static LIST_HEAD(page_alloc_sort);
 
 static void sort_slab_insert(struct rb_root *root, struct alloc_stat *data,
 			     struct list_head *sort_list)
@@ -751,10 +1252,12 @@ static void __sort_slab_result(struct rb_root *root, struct rb_root *root_sorted
 	}
 }
 
-static void sort_page_insert(struct rb_root *root, struct page_stat *data)
+static void sort_page_insert(struct rb_root *root, struct page_stat *data,
+			     struct list_head *sort_list)
 {
 	struct rb_node **new = &root->rb_node;
 	struct rb_node *parent = NULL;
+	struct sort_dimension *sort;
 
 	while (*new) {
 		struct page_stat *this;
@@ -763,8 +1266,11 @@ static void sort_page_insert(struct rb_root *root, struct page_stat *data)
 		this = rb_entry(*new, struct page_stat, node);
 		parent = *new;
 
-		/* TODO: support more sort key */
-		cmp = data->alloc_bytes - this->alloc_bytes;
+		list_for_each_entry(sort, sort_list, list) {
+			cmp = sort->cmp(data, this);
+			if (cmp)
+				break;
+		}
 
 		if (cmp > 0)
 			new = &parent->rb_left;
@@ -776,7 +1282,8 @@ static void sort_page_insert(struct rb_root *root, struct page_stat *data)
 	rb_insert_color(&data->node, root);
 }
 
-static void __sort_page_result(struct rb_root *root, struct rb_root *root_sorted)
+static void __sort_page_result(struct rb_root *root, struct rb_root *root_sorted,
+			       struct list_head *sort_list)
 {
 	struct rb_node *node;
 	struct page_stat *data;
@@ -788,7 +1295,7 @@ static void __sort_page_result(struct rb_root *root, struct rb_root *root_sorted
 
 		rb_erase(node, root);
 		data = rb_entry(node, struct page_stat, node);
-		sort_page_insert(root_sorted, data);
+		sort_page_insert(root_sorted, data, sort_list);
 	}
 }
 
@@ -796,12 +1303,20 @@ static void sort_result(void)
 {
 	if (kmem_slab) {
 		__sort_slab_result(&root_alloc_stat, &root_alloc_sorted,
-				   &alloc_sort);
+				   &slab_alloc_sort);
 		__sort_slab_result(&root_caller_stat, &root_caller_sorted,
-				   &caller_sort);
+				   &slab_caller_sort);
 	}
 	if (kmem_page) {
-		__sort_page_result(&page_alloc_tree, &page_alloc_sorted);
+		if (live_page)
+			__sort_page_result(&page_live_tree, &page_alloc_sorted,
+					   &page_alloc_sort);
+		else
+			__sort_page_result(&page_alloc_tree, &page_alloc_sorted,
+					   &page_alloc_sort);
+
+		__sort_page_result(&page_caller_tree, &page_caller_sorted,
+				   &page_caller_sort);
 	}
 }
 
@@ -850,8 +1365,12 @@ out:
 	return err;
 }
 
-static int ptr_cmp(struct alloc_stat *l, struct alloc_stat *r)
+/* slab sort keys */
+static int ptr_cmp(void *a, void *b)
 {
+	struct alloc_stat *l = a;
+	struct alloc_stat *r = b;
+
 	if (l->ptr < r->ptr)
 		return -1;
 	else if (l->ptr > r->ptr)
@@ -864,8 +1383,11 @@ static struct sort_dimension ptr_sort_dimension = {
 	.cmp	= ptr_cmp,
 };
 
-static int callsite_cmp(struct alloc_stat *l, struct alloc_stat *r)
+static int slab_callsite_cmp(void *a, void *b)
 {
+	struct alloc_stat *l = a;
+	struct alloc_stat *r = b;
+
 	if (l->call_site < r->call_site)
 		return -1;
 	else if (l->call_site > r->call_site)
@@ -875,11 +1397,14 @@ static int callsite_cmp(struct alloc_stat *l, struct alloc_stat *r)
 
 static struct sort_dimension callsite_sort_dimension = {
 	.name	= "callsite",
-	.cmp	= callsite_cmp,
+	.cmp	= slab_callsite_cmp,
 };
 
-static int hit_cmp(struct alloc_stat *l, struct alloc_stat *r)
+static int hit_cmp(void *a, void *b)
 {
+	struct alloc_stat *l = a;
+	struct alloc_stat *r = b;
+
 	if (l->hit < r->hit)
 		return -1;
 	else if (l->hit > r->hit)
@@ -892,8 +1417,11 @@ static struct sort_dimension hit_sort_dimension = {
 	.cmp	= hit_cmp,
 };
 
-static int bytes_cmp(struct alloc_stat *l, struct alloc_stat *r)
+static int bytes_cmp(void *a, void *b)
 {
+	struct alloc_stat *l = a;
+	struct alloc_stat *r = b;
+
 	if (l->bytes_alloc < r->bytes_alloc)
 		return -1;
 	else if (l->bytes_alloc > r->bytes_alloc)
@@ -906,9 +1434,11 @@ static struct sort_dimension bytes_sort_dimension = {
 	.cmp	= bytes_cmp,
 };
 
-static int frag_cmp(struct alloc_stat *l, struct alloc_stat *r)
+static int frag_cmp(void *a, void *b)
 {
 	double x, y;
+	struct alloc_stat *l = a;
+	struct alloc_stat *r = b;
 
 	x = fragmentation(l->bytes_req, l->bytes_alloc);
 	y = fragmentation(r->bytes_req, r->bytes_alloc);
@@ -925,8 +1455,11 @@ static struct sort_dimension frag_sort_dimension = {
 	.cmp	= frag_cmp,
 };
 
-static int pingpong_cmp(struct alloc_stat *l, struct alloc_stat *r)
+static int pingpong_cmp(void *a, void *b)
 {
+	struct alloc_stat *l = a;
+	struct alloc_stat *r = b;
+
 	if (l->pingpong < r->pingpong)
 		return -1;
 	else if (l->pingpong > r->pingpong)
@@ -939,7 +1472,135 @@ static struct sort_dimension pingpong_sort_dimension = {
 	.cmp	= pingpong_cmp,
 };
 
-static struct sort_dimension *avail_sorts[] = {
+/* page sort keys */
+static int page_cmp(void *a, void *b)
+{
+	struct page_stat *l = a;
+	struct page_stat *r = b;
+
+	if (l->page < r->page)
+		return -1;
+	else if (l->page > r->page)
+		return 1;
+	return 0;
+}
+
+static struct sort_dimension page_sort_dimension = {
+	.name	= "page",
+	.cmp	= page_cmp,
+};
+
+static int page_callsite_cmp(void *a, void *b)
+{
+	struct page_stat *l = a;
+	struct page_stat *r = b;
+
+	if (l->callsite < r->callsite)
+		return -1;
+	else if (l->callsite > r->callsite)
+		return 1;
+	return 0;
+}
+
+static struct sort_dimension page_callsite_sort_dimension = {
+	.name	= "callsite",
+	.cmp	= page_callsite_cmp,
+};
+
+static int page_hit_cmp(void *a, void *b)
+{
+	struct page_stat *l = a;
+	struct page_stat *r = b;
+
+	if (l->nr_alloc < r->nr_alloc)
+		return -1;
+	else if (l->nr_alloc > r->nr_alloc)
+		return 1;
+	return 0;
+}
+
+static struct sort_dimension page_hit_sort_dimension = {
+	.name	= "hit",
+	.cmp	= page_hit_cmp,
+};
+
+static int page_bytes_cmp(void *a, void *b)
+{
+	struct page_stat *l = a;
+	struct page_stat *r = b;
+
+	if (l->alloc_bytes < r->alloc_bytes)
+		return -1;
+	else if (l->alloc_bytes > r->alloc_bytes)
+		return 1;
+	return 0;
+}
+
+static struct sort_dimension page_bytes_sort_dimension = {
+	.name	= "bytes",
+	.cmp	= page_bytes_cmp,
+};
+
+static int page_order_cmp(void *a, void *b)
+{
+	struct page_stat *l = a;
+	struct page_stat *r = b;
+
+	if (l->order < r->order)
+		return -1;
+	else if (l->order > r->order)
+		return 1;
+	return 0;
+}
+
+static struct sort_dimension page_order_sort_dimension = {
+	.name	= "order",
+	.cmp	= page_order_cmp,
+};
+
+static int migrate_type_cmp(void *a, void *b)
+{
+	struct page_stat *l = a;
+	struct page_stat *r = b;
+
+	/* for internal use to find free'd page */
+	if (l->migrate_type == -1U)
+		return 0;
+
+	if (l->migrate_type < r->migrate_type)
+		return -1;
+	else if (l->migrate_type > r->migrate_type)
+		return 1;
+	return 0;
+}
+
+static struct sort_dimension migrate_type_sort_dimension = {
+	.name	= "migtype",
+	.cmp	= migrate_type_cmp,
+};
+
+static int gfp_flags_cmp(void *a, void *b)
+{
+	struct page_stat *l = a;
+	struct page_stat *r = b;
+
+	/* for internal use to find free'd page */
+	if (l->gfp_flags == -1U)
+		return 0;
+
+	if (l->gfp_flags < r->gfp_flags)
+		return -1;
+	else if (l->gfp_flags > r->gfp_flags)
+		return 1;
+	return 0;
+}
+
+static struct sort_dimension gfp_flags_sort_dimension = {
+	.name	= "gfp",
+	.cmp	= gfp_flags_cmp,
+};
+
+static struct sort_dimension *slab_sorts[] = {
 	&ptr_sort_dimension,
 	&callsite_sort_dimension,
 	&hit_sort_dimension,
@@ -948,16 +1609,44 @@ static struct sort_dimension *avail_sorts[] = {
 	&pingpong_sort_dimension,
 };
 
-#define NUM_AVAIL_SORTS	((int)ARRAY_SIZE(avail_sorts))
+static struct sort_dimension *page_sorts[] = {
+	&page_sort_dimension,
+	&page_callsite_sort_dimension,
+	&page_hit_sort_dimension,
+	&page_bytes_sort_dimension,
+	&page_order_sort_dimension,
+	&migrate_type_sort_dimension,
+	&gfp_flags_sort_dimension,
+};
+
+static int slab_sort_dimension__add(const char *tok, struct list_head *list)
+{
+	struct sort_dimension *sort;
+	int i;
+
+	for (i = 0; i < (int)ARRAY_SIZE(slab_sorts); i++) {
+		if (!strcmp(slab_sorts[i]->name, tok)) {
+			sort = memdup(slab_sorts[i], sizeof(*slab_sorts[i]));
+			if (!sort) {
+				pr_err("%s: memdup failed\n", __func__);
+				return -1;
+			}
+			list_add_tail(&sort->list, list);
+			return 0;
+		}
+	}
+
+	return -1;
+}
 
-static int sort_dimension__add(const char *tok, struct list_head *list)
+static int page_sort_dimension__add(const char *tok, struct list_head *list)
 {
 	struct sort_dimension *sort;
 	int i;
 
-	for (i = 0; i < NUM_AVAIL_SORTS; i++) {
-		if (!strcmp(avail_sorts[i]->name, tok)) {
-			sort = memdup(avail_sorts[i], sizeof(*avail_sorts[i]));
+	for (i = 0; i < (int)ARRAY_SIZE(page_sorts); i++) {
+		if (!strcmp(page_sorts[i]->name, tok)) {
+			sort = memdup(page_sorts[i], sizeof(*page_sorts[i]));
 			if (!sort) {
 				pr_err("%s: memdup failed\n", __func__);
 				return -1;
@@ -970,7 +1659,33 @@ static int sort_dimension__add(const char *tok, struct list_head *list)
 	return -1;
 }
 
-static int setup_sorting(struct list_head *sort_list, const char *arg)
+static int setup_slab_sorting(struct list_head *sort_list, const char *arg)
+{
+	char *tok;
+	char *str = strdup(arg);
+	char *pos = str;
+
+	if (!str) {
+		pr_err("%s: strdup failed\n", __func__);
+		return -1;
+	}
+
+	while (true) {
+		tok = strsep(&pos, ",");
+		if (!tok)
+			break;
+		if (slab_sort_dimension__add(tok, sort_list) < 0) {
+			error("Unknown slab --sort key: '%s'", tok);
+			free(str);
+			return -1;
+		}
+	}
+
+	free(str);
+	return 0;
+}
+
+static int setup_page_sorting(struct list_head *sort_list, const char *arg)
 {
 	char *tok;
 	char *str = strdup(arg);
@@ -985,8 +1700,8 @@ static int setup_sorting(struct list_head *sort_list, const char *arg)
 		tok = strsep(&pos, ",");
 		if (!tok)
 			break;
-		if (sort_dimension__add(tok, sort_list) < 0) {
-			error("Unknown --sort key: '%s'", tok);
+		if (page_sort_dimension__add(tok, sort_list) < 0) {
+			error("Unknown page --sort key: '%s'", tok);
 			free(str);
 			return -1;
 		}
@@ -1002,10 +1717,18 @@ static int parse_sort_opt(const struct option *opt __maybe_unused,
 	if (!arg)
 		return -1;
 
-	if (caller_flag > alloc_flag)
-		return setup_sorting(&caller_sort, arg);
-	else
-		return setup_sorting(&alloc_sort, arg);
+	if (kmem_page > kmem_slab ||
+	    (kmem_page == 0 && kmem_slab == 0 && kmem_default == KMEM_PAGE)) {
+		if (caller_flag > alloc_flag)
+			return setup_page_sorting(&page_caller_sort, arg);
+		else
+			return setup_page_sorting(&page_alloc_sort, arg);
+	} else {
+		if (caller_flag > alloc_flag)
+			return setup_slab_sorting(&slab_caller_sort, arg);
+		else
+			return setup_slab_sorting(&slab_alloc_sort, arg);
+	}
 
 	return 0;
 }
@@ -1084,7 +1807,7 @@ static int __cmd_record(int argc, const char **argv)
 	if (kmem_slab)
 		rec_argc += ARRAY_SIZE(slab_events);
 	if (kmem_page)
-		rec_argc += ARRAY_SIZE(page_events);
+		rec_argc += ARRAY_SIZE(page_events) + 1; /* for -g */
 
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
 
@@ -1099,6 +1822,8 @@ static int __cmd_record(int argc, const char **argv)
 			rec_argv[i] = strdup(slab_events[j]);
 	}
 	if (kmem_page) {
+		rec_argv[i++] = strdup("-g");
+
 		for (j = 0; j < ARRAY_SIZE(page_events); j++, i++)
 			rec_argv[i] = strdup(page_events[j]);
 	}
@@ -1109,9 +1834,26 @@ static int __cmd_record(int argc, const char **argv)
 	return cmd_record(i, rec_argv, NULL);
 }
 
+static int kmem_config(const char *var, const char *value, void *cb)
+{
+	if (!strcmp(var, "kmem.default")) {
+		if (!strcmp(value, "slab"))
+			kmem_default = KMEM_SLAB;
+		else if (!strcmp(value, "page"))
+			kmem_default = KMEM_PAGE;
+		else
+			pr_err("invalid default value ('slab' or 'page' required): %s\n",
+			       value);
+		return 0;
+	}
+
+	return perf_default_config(var, value, cb);
+}
+
 int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
 {
-	const char * const default_sort_order = "frag,hit,bytes";
+	const char * const default_slab_sort = "frag,hit,bytes";
+	const char * const default_page_sort = "bytes,hit";
 	struct perf_data_file file = {
 		.mode = PERF_DATA_MODE_READ,
 	};
@@ -1124,8 +1866,8 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_CALLBACK_NOOPT(0, "alloc", NULL, NULL,
 			   "show per-allocation statistics", parse_alloc_opt),
 	OPT_CALLBACK('s', "sort", NULL, "key[,key2...]",
-		     "sort by keys: ptr, call_site, bytes, hit, pingpong, frag",
-		     parse_sort_opt),
+		     "sort by keys: ptr, callsite, bytes, hit, pingpong, frag, "
+		     "page, order, migtype, gfp", parse_sort_opt),
 	OPT_CALLBACK('l', "line", NULL, "num", "show n lines", parse_line_opt),
 	OPT_BOOLEAN(0, "raw-ip", &raw_ip, "show raw ip instead of symbol"),
 	OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"),
@@ -1133,6 +1875,7 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
 			   parse_slab_opt),
 	OPT_CALLBACK_NOOPT(0, "page", NULL, NULL, "Analyze page allocator",
 			   parse_page_opt),
+	OPT_BOOLEAN(0, "live", &live_page, "Show live page stat"),
 	OPT_END()
 	};
 	const char *const kmem_subcommands[] = { "record", "stat", NULL };
@@ -1142,15 +1885,21 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
 	};
 	struct perf_session *session;
 	int ret = -1;
+	const char errmsg[] = "No %s allocation events found.  Have you run 'perf kmem record --%s'?\n";
 
+	perf_config(kmem_config, NULL);
 	argc = parse_options_subcommand(argc, argv, kmem_options,
 					kmem_subcommands, kmem_usage, 0);
 
 	if (!argc)
 		usage_with_options(kmem_usage, kmem_options);
 
-	if (kmem_slab == 0 && kmem_page == 0)
-		kmem_slab = 1;  /* for backward compatibility */
+	if (kmem_slab == 0 && kmem_page == 0) {
+		if (kmem_default == KMEM_SLAB)
+			kmem_slab = 1;
+		else
+			kmem_page = 1;
+	}
 
 	if (!strncmp(argv[0], "rec", 3)) {
 		symbol__init(NULL);
@@ -1159,19 +1908,30 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	file.path = input_name;
 
-	session = perf_session__new(&file, false, &perf_kmem);
+	kmem_session = session = perf_session__new(&file, false, &perf_kmem);
 	if (session == NULL)
 		return -1;
 
+	if (kmem_slab) {
+		if (!perf_evlist__find_tracepoint_by_name(session->evlist,
+							  "kmem:kmalloc")) {
+			pr_err(errmsg, "slab", "slab");
+			return -1;
+		}
+	}
+
 	if (kmem_page) {
-		struct perf_evsel *evsel = perf_evlist__first(session->evlist);
+		struct perf_evsel *evsel;
 
-		if (evsel == NULL || evsel->tp_format == NULL) {
-			pr_err("invalid event found.. aborting\n");
+		evsel = perf_evlist__find_tracepoint_by_name(session->evlist,
+							     "kmem:mm_page_alloc");
+		if (evsel == NULL) {
+			pr_err(errmsg, "page", "page");
 			return -1;
 		}
 
 		kmem_page_size = pevent_get_page_size(evsel->tp_format->pevent);
+		symbol_conf.use_callchain = true;
 	}
 
 	symbol__init(&session->header.env);
@@ -1182,11 +1942,21 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
 		if (cpu__setup_cpunode_map())
 			goto out_delete;
 
-		if (list_empty(&caller_sort))
-			setup_sorting(&caller_sort, default_sort_order);
-		if (list_empty(&alloc_sort))
-			setup_sorting(&alloc_sort, default_sort_order);
-
+		if (list_empty(&slab_caller_sort))
+			setup_slab_sorting(&slab_caller_sort, default_slab_sort);
+		if (list_empty(&slab_alloc_sort))
+			setup_slab_sorting(&slab_alloc_sort, default_slab_sort);
+		if (list_empty(&page_caller_sort))
+			setup_page_sorting(&page_caller_sort, default_page_sort);
+		if (list_empty(&page_alloc_sort))
+			setup_page_sorting(&page_alloc_sort, default_page_sort);
+
+		if (kmem_page) {
+			setup_page_sorting(&page_alloc_sort_input,
+					   "page,order,migtype,gfp");
+			setup_page_sorting(&page_caller_sort_input,
+					   "callsite,order,migtype,gfp");
+		}
 		ret = __cmd_kmem(session);
 	} else
 		usage_with_options(kmem_usage, kmem_options);
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 1f9338f6109c..74878cd75078 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -651,6 +651,7 @@ static int process_sample_event(struct perf_tool *tool,
 				struct perf_evsel *evsel,
 				struct machine *machine)
 {
+	int err = 0;
 	struct thread *thread;
 	struct perf_kvm_stat *kvm = container_of(tool, struct perf_kvm_stat,
 						 tool);
@@ -666,9 +667,10 @@ static int process_sample_event(struct perf_tool *tool,
 	}
 
 	if (!handle_kvm_event(kvm, thread, evsel, sample))
-		return -1;
+		err = -1;
 
-	return 0;
+	thread__put(thread);
+	return err;
 }
 
 static int cpu_isa_config(struct perf_kvm_stat *kvm)
@@ -1309,6 +1311,8 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
 			"show events other than"
 			" HLT (x86 only) or Wait state (s390 only)"
 			" that take longer than duration usecs"),
+		OPT_UINTEGER(0, "proc-map-timeout", &kvm->opts.proc_map_timeout,
+				"per thread proc mmap processing timeout in ms"),
 		OPT_END()
 	};
 	const char * const live_usage[] = {
@@ -1336,6 +1340,7 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
 	kvm->opts.target.uses_mmap = false;
 	kvm->opts.target.uid_str = NULL;
 	kvm->opts.target.uid = UINT_MAX;
+	kvm->opts.proc_map_timeout = 500;
 
 	symbol__init(NULL);
 	disable_buildid_cache();
@@ -1391,7 +1396,7 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
 	perf_session__set_id_hdr_size(kvm->session);
 	ordered_events__set_copy_on_queue(&kvm->session->ordered_events, true);
 	machine__synthesize_threads(&kvm->session->machines.host, &kvm->opts.target,
-				    kvm->evlist->threads, false);
+				    kvm->evlist->threads, false, kvm->opts.proc_map_timeout);
 	err = kvm_live_open_events(kvm);
 	if (err)
 		goto out;
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index d49c2ab85fc2..de16aaed516e 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -769,6 +769,7 @@ static void dump_threads(void)
 		t = perf_session__findnew(session, st->tid);
 		pr_info("%10d: %s\n", st->tid, thread__comm_str(t));
 		node = rb_next(node);
+		thread__put(t);
 	};
 }
 
@@ -810,6 +811,7 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 				struct perf_evsel *evsel,
 				struct machine *machine)
 {
+	int err = 0;
 	struct thread *thread = machine__findnew_thread(machine, sample->pid,
 							sample->tid);
 
@@ -821,10 +823,12 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 
 	if (evsel->handler != NULL) {
 		tracepoint_handler f = evsel->handler;
-		return f(evsel, sample);
+		err = f(evsel, sample);
 	}
 
-	return 0;
+	thread__put(thread);
+
+	return err;
 }
 
 static void sort_result(void)
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index 675216e08bfc..da2ec06f0742 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -74,7 +74,7 @@ dump_raw_samples(struct perf_tool *tool,
 	}
 
 	if (al.filtered || (mem->hide_unresolved && al.sym == NULL))
-		return 0;
+		goto out_put;
 
 	if (al.map != NULL)
 		al.map->dso->hit = 1;
@@ -103,7 +103,8 @@ dump_raw_samples(struct perf_tool *tool,
 		symbol_conf.field_sep,
 		al.map ? (al.map->dso ? al.map->dso->long_name : "???") : "???",
 		al.sym ? al.sym->name : "???");
-
+out_put:
+	addr_location__put(&al);
 	return 0;
 }
 
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index f7b1af67e9f6..1272559fa22d 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -44,25 +44,19 @@
 
 #define DEFAULT_VAR_FILTER "!__k???tab_* & !__crc_*"
 #define DEFAULT_FUNC_FILTER "!_*"
+#define DEFAULT_LIST_FILTER "*:*"
 
 /* Session management structure */
 static struct {
+	int command;	/* Command short_name */
 	bool list_events;
-	bool force_add;
-	bool show_lines;
-	bool show_vars;
-	bool show_ext_vars;
-	bool show_funcs;
-	bool mod_events;
 	bool uprobes;
 	bool quiet;
 	bool target_used;
 	int nevents;
 	struct perf_probe_event events[MAX_PROBES];
-	struct strlist *dellist;
 	struct line_range line_range;
 	char *target;
-	int max_probe_points;
 	struct strfilter *filter;
 } params;
 
@@ -93,6 +87,28 @@ static int parse_probe_event(const char *str)
 	return ret;
 }
 
+static int params_add_filter(const char *str)
+{
+	const char *err = NULL;
+	int ret = 0;
+
+	pr_debug2("Add filter: %s\n", str);
+	if (!params.filter) {
+		params.filter = strfilter__new(str, &err);
+		if (!params.filter)
+			ret = err ? -EINVAL : -ENOMEM;
+	} else
+		ret = strfilter__or(params.filter, str, &err);
+
+	if (ret == -EINVAL) {
+		pr_err("Filter parse error at %td.\n", err - str + 1);
+		pr_err("Source: \"%s\"\n", str);
+		pr_err("         %*c\n", (int)(err - str + 1), '^');
+	}
+
+	return ret;
+}
+
 static int set_target(const char *ptr)
 {
 	int found = 0;
@@ -152,34 +168,11 @@ static int parse_probe_event_argv(int argc, const char **argv)
 
 		len += sprintf(&buf[len], "%s ", argv[i]);
 	}
-	params.mod_events = true;
 	ret = parse_probe_event(buf);
 	free(buf);
 	return ret;
 }
 
-static int opt_add_probe_event(const struct option *opt __maybe_unused,
-			      const char *str, int unset __maybe_unused)
-{
-	if (str) {
-		params.mod_events = true;
-		return parse_probe_event(str);
-	} else
-		return 0;
-}
-
-static int opt_del_probe_event(const struct option *opt __maybe_unused,
-			       const char *str, int unset __maybe_unused)
-{
-	if (str) {
-		params.mod_events = true;
-		if (!params.dellist)
-			params.dellist = strlist__new(true, NULL);
-		strlist__add(params.dellist, str);
-	}
-	return 0;
-}
-
 static int opt_set_target(const struct option *opt, const char *str,
 			int unset __maybe_unused)
 {
@@ -217,8 +210,10 @@ static int opt_set_target(const struct option *opt, const char *str,
 	return ret;
 }
 
+/* Command option callbacks */
+
 #ifdef HAVE_DWARF_SUPPORT
-static int opt_show_lines(const struct option *opt __maybe_unused,
+static int opt_show_lines(const struct option *opt,
 			  const char *str, int unset __maybe_unused)
 {
 	int ret = 0;
@@ -226,19 +221,19 @@ static int opt_show_lines(const struct option *opt __maybe_unused,
 	if (!str)
 		return 0;
 
-	if (params.show_lines) {
+	if (params.command == 'L') {
 		pr_warning("Warning: more than one --line options are"
 			   " detected. Only the first one is valid.\n");
 		return 0;
 	}
 
-	params.show_lines = true;
+	params.command = opt->short_name;
 	ret = parse_line_range_desc(str, &params.line_range);
 
 	return ret;
 }
 
-static int opt_show_vars(const struct option *opt __maybe_unused,
+static int opt_show_vars(const struct option *opt,
 			 const char *str, int unset __maybe_unused)
 {
 	struct perf_probe_event *pev = &params.events[params.nevents];
@@ -252,29 +247,39 @@ static int opt_show_vars(const struct option *opt __maybe_unused,
 		pr_err("  Error: '--vars' doesn't accept arguments.\n");
 		return -EINVAL;
 	}
-	params.show_vars = true;
+	params.command = opt->short_name;
 
 	return ret;
 }
 #endif
+static int opt_add_probe_event(const struct option *opt,
+			      const char *str, int unset __maybe_unused)
+{
+	if (str) {
+		params.command = opt->short_name;
+		return parse_probe_event(str);
+	}
+
+	return 0;
+}
+
+static int opt_set_filter_with_command(const struct option *opt,
+				       const char *str, int unset)
+{
+	if (!unset)
+		params.command = opt->short_name;
+
+	if (str)
+		return params_add_filter(str);
+
+	return 0;
+}
 
 static int opt_set_filter(const struct option *opt __maybe_unused,
 			  const char *str, int unset __maybe_unused)
 {
-	const char *err;
-
-	if (str) {
-		pr_debug2("Set filter: %s\n", str);
-		if (params.filter)
-			strfilter__delete(params.filter);
-		params.filter = strfilter__new(str, &err);
-		if (!params.filter) {
-			pr_err("Filter parse error at %td.\n", err - str + 1);
-			pr_err("Source: \"%s\"\n", str);
-			pr_err("         %*c\n", (int)(err - str + 1), '^');
-			return -EINVAL;
-		}
-	}
+	if (str)
+		return params_add_filter(str);
 
 	return 0;
 }
@@ -290,8 +295,6 @@ static void cleanup_params(void)
 
 	for (i = 0; i < params.nevents; i++)
 		clear_perf_probe_event(params.events + i);
-	if (params.dellist)
-		strlist__delete(params.dellist);
 	line_range__clear(&params.line_range);
 	free(params.target);
 	if (params.filter)
@@ -316,22 +319,24 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 		"perf probe [<options>] 'PROBEDEF' ['PROBEDEF' ...]",
 		"perf probe [<options>] --add 'PROBEDEF' [--add 'PROBEDEF' ...]",
 		"perf probe [<options>] --del '[GROUP:]EVENT' ...",
-		"perf probe --list",
+		"perf probe --list [GROUP:]EVENT ...",
 #ifdef HAVE_DWARF_SUPPORT
 		"perf probe [<options>] --line 'LINEDESC'",
 		"perf probe [<options>] --vars 'PROBEPOINT'",
 #endif
+		"perf probe [<options>] --funcs",
 		NULL
-};
+	};
 	struct option options[] = {
 	OPT_INCR('v', "verbose", &verbose,
 		    "be more verbose (show parsed arguments, etc)"),
 	OPT_BOOLEAN('q', "quiet", &params.quiet,
 		    "be quiet (do not show any mesages)"),
-	OPT_BOOLEAN('l', "list", &params.list_events,
-		    "list up current probe events"),
+	OPT_CALLBACK_DEFAULT('l', "list", NULL, "[GROUP:]EVENT",
+			     "list up probe events",
+			     opt_set_filter_with_command, DEFAULT_LIST_FILTER),
 	OPT_CALLBACK('d', "del", NULL, "[GROUP:]EVENT", "delete a probe event.",
-		opt_del_probe_event),
+		     opt_set_filter_with_command),
 	OPT_CALLBACK('a', "add", NULL,
 #ifdef HAVE_DWARF_SUPPORT
 		"[EVENT=]FUNC[@SRC][+OFF|%return|:RL|;PT]|SRC:AL|SRC;PT"
@@ -356,7 +361,7 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 		"\t\tARG:\tProbe argument (kprobe-tracer argument format.)\n",
 #endif
 		opt_add_probe_event),
-	OPT_BOOLEAN('f', "force", &params.force_add, "forcibly add events"
+	OPT_BOOLEAN('f', "force", &probe_conf.force_add, "forcibly add events"
 		    " with existing name"),
 #ifdef HAVE_DWARF_SUPPORT
 	OPT_CALLBACK('L', "line", NULL,
@@ -365,8 +370,10 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_CALLBACK('V', "vars", NULL,
 		     "FUNC[@SRC][+OFF|%return|:RL|;PT]|SRC:AL|SRC;PT",
 		     "Show accessible variables on PROBEDEF", opt_show_vars),
-	OPT_BOOLEAN('\0', "externs", &params.show_ext_vars,
+	OPT_BOOLEAN('\0', "externs", &probe_conf.show_ext_vars,
 		    "Show external variables too (with --vars only)"),
+	OPT_BOOLEAN('\0', "range", &probe_conf.show_location_range,
+		"Show variables location range in scope (with --vars only)"),
 	OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
 		   "file", "vmlinux pathname"),
 	OPT_STRING('s', "source", &symbol_conf.source_prefix,
@@ -374,12 +381,15 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_CALLBACK('m', "module", NULL, "modname|path",
 		"target module name (for online) or path (for offline)",
 		opt_set_target),
+	OPT_BOOLEAN('\0', "no-inlines", &probe_conf.no_inlines,
+		"Don't search inlined functions"),
 #endif
 	OPT__DRY_RUN(&probe_event_dry_run),
-	OPT_INTEGER('\0', "max-probes", &params.max_probe_points,
+	OPT_INTEGER('\0', "max-probes", &probe_conf.max_probes,
 		 "Set how many probe points can be found for a probe."),
-	OPT_BOOLEAN('F', "funcs", &params.show_funcs,
-		    "Show potential probe-able functions."),
+	OPT_CALLBACK_DEFAULT('F', "funcs", NULL, "[FILTER]",
+			     "Show potential probe-able functions.",
+			     opt_set_filter_with_command, DEFAULT_FUNC_FILTER),
 	OPT_CALLBACK('\0', "filter", NULL,
 		     "[!]FILTER", "Set a filter (with --vars/funcs only)\n"
 		     "\t\t\t(default: \"" DEFAULT_VAR_FILTER "\" for --vars,\n"
@@ -402,6 +412,7 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 	set_option_flag(options, 'L', "line", PARSE_OPT_EXCLUSIVE);
 	set_option_flag(options, 'V', "vars", PARSE_OPT_EXCLUSIVE);
 #endif
+	set_option_flag(options, 'F', "funcs", PARSE_OPT_EXCLUSIVE);
 
 	argc = parse_options(argc, argv, options, probe_usage,
 			     PARSE_OPT_STOP_AT_NON_OPTION);
@@ -410,11 +421,16 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 			pr_warning("  Error: '-' is not supported.\n");
 			usage_with_options(probe_usage, options);
 		}
+		if (params.command && params.command != 'a') {
+			pr_warning("  Error: another command except --add is set.\n");
+			usage_with_options(probe_usage, options);
+		}
 		ret = parse_probe_event_argv(argc, argv);
 		if (ret < 0) {
 			pr_err_with_code("  Error: Command Parse Error.", ret);
 			return ret;
 		}
+		params.command = 'a';
 	}
 
 	if (params.quiet) {
@@ -425,89 +441,70 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 		verbose = -1;
 	}
 
-	if (params.max_probe_points == 0)
-		params.max_probe_points = MAX_PROBES;
-
-	if ((!params.nevents && !params.dellist && !params.list_events &&
-	     !params.show_lines && !params.show_funcs))
-		usage_with_options(probe_usage, options);
+	if (probe_conf.max_probes == 0)
+		probe_conf.max_probes = MAX_PROBES;
 
 	/*
 	 * Only consider the user's kernel image path if given.
 	 */
 	symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);
 
-	if (params.list_events) {
+	switch (params.command) {
+	case 'l':
 		if (params.uprobes) {
 			pr_warning("  Error: Don't use --list with --exec.\n");
 			usage_with_options(probe_usage, options);
 		}
-		ret = show_perf_probe_events();
+		ret = show_perf_probe_events(params.filter);
 		if (ret < 0)
 			pr_err_with_code("  Error: Failed to show event list.", ret);
 		return ret;
-	}
-	if (params.show_funcs) {
-		if (!params.filter)
-			params.filter = strfilter__new(DEFAULT_FUNC_FILTER,
-						       NULL);
+	case 'F':
 		ret = show_available_funcs(params.target, params.filter,
 					params.uprobes);
-		strfilter__delete(params.filter);
-		params.filter = NULL;
 		if (ret < 0)
 			pr_err_with_code("  Error: Failed to show functions.", ret);
 		return ret;
-	}
-
 #ifdef HAVE_DWARF_SUPPORT
-	if (params.show_lines) {
+	case 'L':
 		ret = show_line_range(&params.line_range, params.target,
 				      params.uprobes);
 		if (ret < 0)
 			pr_err_with_code("  Error: Failed to show lines.", ret);
 		return ret;
-	}
-	if (params.show_vars) {
+	case 'V':
 		if (!params.filter)
 			params.filter = strfilter__new(DEFAULT_VAR_FILTER,
 						       NULL);
 
 		ret = show_available_vars(params.events, params.nevents,
-					  params.max_probe_points,
-					  params.target,
-					  params.filter,
-					  params.show_ext_vars);
-		strfilter__delete(params.filter);
-		params.filter = NULL;
+					  params.filter);
 		if (ret < 0)
 			pr_err_with_code("  Error: Failed to show vars.", ret);
 		return ret;
-	}
 #endif
-
-	if (params.dellist) {
-		ret = del_perf_probe_events(params.dellist);
+	case 'd':
+		ret = del_perf_probe_events(params.filter);
 		if (ret < 0) {
 			pr_err_with_code("  Error: Failed to delete events.", ret);
 			return ret;
 		}
-	}
-
-	if (params.nevents) {
+		break;
+	case 'a':
 		/* Ensure the last given target is used */
 		if (params.target && !params.target_used) {
 			pr_warning("  Error: -x/-m must follow the probe definitions.\n");
 			usage_with_options(probe_usage, options);
 		}
 
-		ret = add_perf_probe_events(params.events, params.nevents,
-					    params.max_probe_points,
-					    params.force_add);
+		ret = add_perf_probe_events(params.events, params.nevents);
 		if (ret < 0) {
 			pr_err_with_code("  Error: Failed to add events.", ret);
 			return ret;
 		}
+		break;
+	default:
+		usage_with_options(probe_usage, options);
 	}
 	return 0;
 }
@@ -522,5 +519,5 @@ int cmd_probe(int argc, const char **argv, const char *prefix)
 		cleanup_params();
 	}
 
-	return ret;
+	return ret < 0 ? ret : 0;
 }
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index c3efdfb630b5..de165a1b9240 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -27,6 +27,8 @@
 #include "util/cpumap.h"
 #include "util/thread_map.h"
 #include "util/data.h"
+#include "util/auxtrace.h"
+#include "util/parse-branch-options.h"
 
 #include <unistd.h>
 #include <sched.h>
@@ -38,6 +40,7 @@ struct record {
 	struct record_opts	opts;
 	u64			bytes_written;
 	struct perf_data_file	file;
+	struct auxtrace_record	*itr;
 	struct perf_evlist	*evlist;
 	struct perf_session	*session;
 	const char		*progname;
@@ -110,9 +113,12 @@ out:
 	return rc;
 }
 
-static volatile int done = 0;
+static volatile int done;
 static volatile int signr = -1;
-static volatile int child_finished = 0;
+static volatile int child_finished;
+static volatile int auxtrace_snapshot_enabled;
+static volatile int auxtrace_snapshot_err;
+static volatile int auxtrace_record__snapshot_started;
 
 static void sig_handler(int sig)
 {
@@ -133,6 +139,133 @@ static void record__sig_exit(void)
 	raise(signr);
 }
 
+#ifdef HAVE_AUXTRACE_SUPPORT
+
+static int record__process_auxtrace(struct perf_tool *tool,
+				    union perf_event *event, void *data1,
+				    size_t len1, void *data2, size_t len2)
+{
+	struct record *rec = container_of(tool, struct record, tool);
+	struct perf_data_file *file = &rec->file;
+	size_t padding;
+	u8 pad[8] = {0};
+
+	if (!perf_data_file__is_pipe(file)) {
+		off_t file_offset;
+		int fd = perf_data_file__fd(file);
+		int err;
+
+		file_offset = lseek(fd, 0, SEEK_CUR);
+		if (file_offset == -1)
+			return -1;
+		err = auxtrace_index__auxtrace_event(&rec->session->auxtrace_index,
+						     event, file_offset);
+		if (err)
+			return err;
+	}
+
+	/* event.auxtrace.size includes padding, see __auxtrace_mmap__read() */
+	padding = (len1 + len2) & 7;
+	if (padding)
+		padding = 8 - padding;
+
+	record__write(rec, event, event->header.size);
+	record__write(rec, data1, len1);
+	if (len2)
+		record__write(rec, data2, len2);
+	record__write(rec, &pad, padding);
+
+	return 0;
+}
+
+static int record__auxtrace_mmap_read(struct record *rec,
+				      struct auxtrace_mmap *mm)
+{
+	int ret;
+
+	ret = auxtrace_mmap__read(mm, rec->itr, &rec->tool,
+				  record__process_auxtrace);
+	if (ret < 0)
+		return ret;
+
+	if (ret)
+		rec->samples++;
+
+	return 0;
+}
+
+static int record__auxtrace_mmap_read_snapshot(struct record *rec,
+					       struct auxtrace_mmap *mm)
+{
+	int ret;
+
+	ret = auxtrace_mmap__read_snapshot(mm, rec->itr, &rec->tool,
+					   record__process_auxtrace,
+					   rec->opts.auxtrace_snapshot_size);
+	if (ret < 0)
+		return ret;
+
+	if (ret)
+		rec->samples++;
+
+	return 0;
+}
+
+static int record__auxtrace_read_snapshot_all(struct record *rec)
+{
+	int i;
+	int rc = 0;
+
+	for (i = 0; i < rec->evlist->nr_mmaps; i++) {
+		struct auxtrace_mmap *mm =
+				&rec->evlist->mmap[i].auxtrace_mmap;
+
+		if (!mm->base)
+			continue;
+
+		if (record__auxtrace_mmap_read_snapshot(rec, mm) != 0) {
+			rc = -1;
+			goto out;
+		}
+	}
+out:
+	return rc;
+}
+
+static void record__read_auxtrace_snapshot(struct record *rec)
+{
+	pr_debug("Recording AUX area tracing snapshot\n");
+	if (record__auxtrace_read_snapshot_all(rec) < 0) {
+		auxtrace_snapshot_err = -1;
+	} else {
+		auxtrace_snapshot_err = auxtrace_record__snapshot_finish(rec->itr);
+		if (!auxtrace_snapshot_err)
+			auxtrace_snapshot_enabled = 1;
+	}
+}
+
+#else
+
+static inline
+int record__auxtrace_mmap_read(struct record *rec __maybe_unused,
+			       struct auxtrace_mmap *mm __maybe_unused)
+{
+	return 0;
+}
+
+static inline
+void record__read_auxtrace_snapshot(struct record *rec __maybe_unused)
+{
+}
+
+static inline
+int auxtrace_record__snapshot_start(struct auxtrace_record *itr __maybe_unused)
+{
+	return 0;
+}
+
+#endif
+
 static int record__open(struct record *rec)
 {
 	char msg[512];
@@ -169,13 +302,16 @@ try_again:
 		goto out;
 	}
 
-	if (perf_evlist__mmap(evlist, opts->mmap_pages, false) < 0) {
+	if (perf_evlist__mmap_ex(evlist, opts->mmap_pages, false,
+				 opts->auxtrace_mmap_pages,
+				 opts->auxtrace_snapshot_mode) < 0) {
 		if (errno == EPERM) {
 			pr_err("Permission error mapping pages.\n"
 			       "Consider increasing "
 			       "/proc/sys/kernel/perf_event_mlock_kb,\n"
 			       "or try again with a smaller value of -m/--mmap_pages.\n"
-			       "(current value: %u)\n", opts->mmap_pages);
+			       "(current value: %u,%u)\n",
+			       opts->mmap_pages, opts->auxtrace_mmap_pages);
 			rc = -errno;
 		} else {
 			pr_err("failed to mmap with %d (%s)\n", errno,
@@ -209,12 +345,9 @@ static int process_buildids(struct record *rec)
 	struct perf_data_file *file  = &rec->file;
 	struct perf_session *session = rec->session;
 
-	u64 size = lseek(perf_data_file__fd(file), 0, SEEK_CUR);
-	if (size == 0)
+	if (file->size == 0)
 		return 0;
 
-	file->size = size;
-
 	/*
 	 * During this process, it'll load kernel map and replace the
 	 * dso->long_name to a real pathname it found.  In this case
@@ -270,12 +403,20 @@ static int record__mmap_read_all(struct record *rec)
 	int rc = 0;
 
 	for (i = 0; i < rec->evlist->nr_mmaps; i++) {
+		struct auxtrace_mmap *mm = &rec->evlist->mmap[i].auxtrace_mmap;
+
 		if (rec->evlist->mmap[i].base) {
 			if (record__mmap_read(rec, i) != 0) {
 				rc = -1;
 				goto out;
 			}
 		}
+
+		if (mm->base && !rec->opts.auxtrace_snapshot_mode &&
+		    record__auxtrace_mmap_read(rec, mm) != 0) {
+			rc = -1;
+			goto out;
+		}
 	}
 
 	/*
@@ -305,6 +446,9 @@ static void record__init_features(struct record *rec)
 
 	if (!rec->opts.branch_stack)
 		perf_header__clear_feat(&session->header, HEADER_BRANCH_STACK);
+
+	if (!rec->opts.full_auxtrace)
+		perf_header__clear_feat(&session->header, HEADER_AUXTRACE);
 }
 
 static volatile int workload_exec_errno;
@@ -323,6 +467,8 @@ static void workload_exec_failed_signal(int signo __maybe_unused,
 	child_finished = 1;
 }
 
+static void snapshot_sig_handler(int sig);
+
 static int __cmd_record(struct record *rec, int argc, const char **argv)
 {
 	int err;
@@ -343,6 +489,10 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	signal(SIGCHLD, sig_handler);
 	signal(SIGINT, sig_handler);
 	signal(SIGTERM, sig_handler);
+	if (rec->opts.auxtrace_snapshot_mode)
+		signal(SIGUSR2, snapshot_sig_handler);
+	else
+		signal(SIGUSR2, SIG_IGN);
 
 	session = perf_session__new(file, false, tool);
 	if (session == NULL) {
@@ -421,6 +571,13 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		}
 	}
 
+	if (rec->opts.full_auxtrace) {
+		err = perf_event__synthesize_auxtrace_info(rec->itr, tool,
+					session, process_synthesized_event);
+		if (err)
+			goto out_delete_session;
+	}
+
 	err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
 						 machine);
 	if (err < 0)
@@ -441,7 +598,8 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	}
 
 	err = __machine__synthesize_threads(machine, tool, &opts->target, rec->evlist->threads,
-					    process_synthesized_event, opts->sample_address);
+					    process_synthesized_event, opts->sample_address,
+					    opts->proc_map_timeout);
 	if (err != 0)
 		goto out_child;
 
@@ -475,14 +633,27 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		perf_evlist__enable(rec->evlist);
 	}
 
+	auxtrace_snapshot_enabled = 1;
 	for (;;) {
 		int hits = rec->samples;
 
 		if (record__mmap_read_all(rec) < 0) {
+			auxtrace_snapshot_enabled = 0;
 			err = -1;
 			goto out_child;
 		}
 
+		if (auxtrace_record__snapshot_started) {
+			auxtrace_record__snapshot_started = 0;
+			if (!auxtrace_snapshot_err)
+				record__read_auxtrace_snapshot(rec);
+			if (auxtrace_snapshot_err) {
+				pr_err("AUX area tracing snapshot failed\n");
+				err = -1;
+				goto out_child;
+			}
+		}
+
 		if (hits == rec->samples) {
 			if (done || draining)
 				break;
@@ -505,10 +676,12 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		 * disable events in this case.
 		 */
 		if (done && !disabled && !target__none(&opts->target)) {
+			auxtrace_snapshot_enabled = 0;
 			perf_evlist__disable(rec->evlist);
 			disabled = true;
 		}
 	}
+	auxtrace_snapshot_enabled = 0;
 
 	if (forks && workload_exec_errno) {
 		char msg[STRERR_BUFSIZE];
@@ -544,16 +717,25 @@ out_child:
 
 	if (!err && !file->is_pipe) {
 		rec->session->header.data_size += rec->bytes_written;
+		file->size = lseek(perf_data_file__fd(file), 0, SEEK_CUR);
 
-		if (!rec->no_buildid)
+		if (!rec->no_buildid) {
 			process_buildids(rec);
+			/*
+			 * We take all buildids when the file contains
+			 * AUX area tracing data because we do not decode the
+			 * trace because it would take too long.
+			 */
+			if (rec->opts.full_auxtrace)
+				dsos__hit_all(rec->session);
+		}
 		perf_session__write_header(rec->session, rec->evlist, fd, true);
 	}
 
 	if (!err && !quiet) {
 		char samples[128];
 
-		if (rec->samples)
+		if (rec->samples && !rec->opts.full_auxtrace)
 			scnprintf(samples, sizeof(samples),
 				  " (%" PRIu64 " samples)", rec->samples);
 		else
@@ -569,94 +751,6 @@ out_delete_session:
 	return status;
 }
 
-#define BRANCH_OPT(n, m) \
-	{ .name = n, .mode = (m) }
-
-#define BRANCH_END { .name = NULL }
-
-struct branch_mode {
-	const char *name;
-	int mode;
-};
-
-static const struct branch_mode branch_modes[] = {
-	BRANCH_OPT("u", PERF_SAMPLE_BRANCH_USER),
-	BRANCH_OPT("k", PERF_SAMPLE_BRANCH_KERNEL),
-	BRANCH_OPT("hv", PERF_SAMPLE_BRANCH_HV),
-	BRANCH_OPT("any", PERF_SAMPLE_BRANCH_ANY),
-	BRANCH_OPT("any_call", PERF_SAMPLE_BRANCH_ANY_CALL),
-	BRANCH_OPT("any_ret", PERF_SAMPLE_BRANCH_ANY_RETURN),
-	BRANCH_OPT("ind_call", PERF_SAMPLE_BRANCH_IND_CALL),
-	BRANCH_OPT("abort_tx", PERF_SAMPLE_BRANCH_ABORT_TX),
-	BRANCH_OPT("in_tx", PERF_SAMPLE_BRANCH_IN_TX),
-	BRANCH_OPT("no_tx", PERF_SAMPLE_BRANCH_NO_TX),
-	BRANCH_OPT("cond", PERF_SAMPLE_BRANCH_COND),
-	BRANCH_END
-};
-
-static int
-parse_branch_stack(const struct option *opt, const char *str, int unset)
-{
-#define ONLY_PLM \
-	(PERF_SAMPLE_BRANCH_USER	|\
-	 PERF_SAMPLE_BRANCH_KERNEL	|\
-	 PERF_SAMPLE_BRANCH_HV)
-
-	uint64_t *mode = (uint64_t *)opt->value;
-	const struct branch_mode *br;
-	char *s, *os = NULL, *p;
-	int ret = -1;
-
-	if (unset)
-		return 0;
-
-	/*
-	 * cannot set it twice, -b + --branch-filter for instance
-	 */
-	if (*mode)
-		return -1;
-
-	/* str may be NULL in case no arg is passed to -b */
-	if (str) {
-		/* because str is read-only */
-		s = os = strdup(str);
-		if (!s)
-			return -1;
-
-		for (;;) {
-			p = strchr(s, ',');
-			if (p)
-				*p = '\0';
-
-			for (br = branch_modes; br->name; br++) {
-				if (!strcasecmp(s, br->name))
-					break;
-			}
-			if (!br->name) {
-				ui__warning("unknown branch filter %s,"
-					    " check man page\n", s);
-				goto error;
-			}
-
-			*mode |= br->mode;
-
-			if (!p)
-				break;
-
-			s = p + 1;
-		}
-	}
-	ret = 0;
-
-	/* default to any branch */
-	if ((*mode & ~ONLY_PLM) == 0) {
-		*mode = PERF_SAMPLE_BRANCH_ANY;
-	}
-error:
-	free(os);
-	return ret;
-}
-
 static void callchain_debug(void)
 {
 	static const char *str[CALLCHAIN_MAX] = { "NONE", "FP", "DWARF", "LBR" };
@@ -795,6 +889,49 @@ static int parse_clockid(const struct option *opt, const char *str, int unset)
 	return -1;
 }
 
+static int record__parse_mmap_pages(const struct option *opt,
+				    const char *str,
+				    int unset __maybe_unused)
+{
+	struct record_opts *opts = opt->value;
+	char *s, *p;
+	unsigned int mmap_pages;
+	int ret;
+
+	if (!str)
+		return -EINVAL;
+
+	s = strdup(str);
+	if (!s)
+		return -ENOMEM;
+
+	p = strchr(s, ',');
+	if (p)
+		*p = '\0';
+
+	if (*s) {
+		ret = __perf_evlist__parse_mmap_pages(&mmap_pages, s);
+		if (ret)
+			goto out_free;
+		opts->mmap_pages = mmap_pages;
+	}
+
+	if (!p) {
+		ret = 0;
+		goto out_free;
+	}
+
+	ret = __perf_evlist__parse_mmap_pages(&mmap_pages, p + 1);
+	if (ret)
+		goto out_free;
+
+	opts->auxtrace_mmap_pages = mmap_pages;
+
+out_free:
+	free(s);
+	return ret;
+}
+
 static const char * const __record_usage[] = {
 	"perf record [<options>] [<command>]",
 	"perf record [<options>] -- <command> [<options>]",
@@ -823,6 +960,7 @@ static struct record record = {
 			.uses_mmap   = true,
 			.default_per_cpu = true,
 		},
+		.proc_map_timeout     = 500,
 	},
 	.tool = {
 		.sample		= process_sample_event,
@@ -875,9 +1013,9 @@ struct option __record_options[] = {
 			&record.opts.no_inherit_set,
 			"child tasks do not inherit counters"),
 	OPT_UINTEGER('F', "freq", &record.opts.user_freq, "profile at this frequency"),
-	OPT_CALLBACK('m', "mmap-pages", &record.opts.mmap_pages, "pages",
-		     "number of mmap data pages",
-		     perf_evlist__parse_mmap_pages),
+	OPT_CALLBACK('m', "mmap-pages", &record.opts, "pages[,pages]",
+		     "number of mmap data pages and AUX area tracing mmap pages",
+		     record__parse_mmap_pages),
 	OPT_BOOLEAN(0, "group", &record.opts.group,
 		    "put the counters into a counter group"),
 	OPT_CALLBACK_NOOPT('g', NULL, &record.opts,
@@ -891,10 +1029,9 @@ struct option __record_options[] = {
 	OPT_BOOLEAN('q', "quiet", &quiet, "don't print any message"),
 	OPT_BOOLEAN('s', "stat", &record.opts.inherit_stat,
 		    "per thread counts"),
-	OPT_BOOLEAN('d', "data", &record.opts.sample_address,
-		    "Sample addresses"),
-	OPT_BOOLEAN('T', "timestamp", &record.opts.sample_time, "Sample timestamps"),
-	OPT_BOOLEAN('P', "period", &record.opts.period, "Sample period"),
+	OPT_BOOLEAN('d', "data", &record.opts.sample_address, "Record the sample addresses"),
+	OPT_BOOLEAN('T', "timestamp", &record.opts.sample_time, "Record the sample timestamps"),
+	OPT_BOOLEAN('P', "period", &record.opts.period, "Record the sample period"),
 	OPT_BOOLEAN('n', "no-samples", &record.opts.no_samples,
 		    "don't sample"),
 	OPT_BOOLEAN('N', "no-buildid-cache", &record.no_buildid_cache,
@@ -929,6 +1066,10 @@ struct option __record_options[] = {
 	OPT_CALLBACK('k', "clockid", &record.opts,
 	"clockid", "clockid to use for events, see clock_gettime()",
 	parse_clockid),
+	OPT_STRING_OPTARG('S', "snapshot", &record.opts.auxtrace_snapshot_opts,
+			  "opts", "AUX area tracing Snapshot Mode", ""),
+	OPT_UINTEGER(0, "proc-map-timeout", &record.opts.proc_map_timeout,
+			"per thread proc mmap processing timeout in ms"),
 	OPT_END()
 };
 
@@ -936,7 +1077,7 @@ struct option *record_options = __record_options;
 
 int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 {
-	int err = -ENOMEM;
+	int err;
 	struct record *rec = &record;
 	char errbuf[BUFSIZ];
 
@@ -957,6 +1098,19 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 		usage_with_options(record_usage, record_options);
 	}
 
+	if (!rec->itr) {
+		rec->itr = auxtrace_record__init(rec->evlist, &err);
+		if (err)
+			return err;
+	}
+
+	err = auxtrace_parse_snapshot_options(rec->itr, &rec->opts,
+					      rec->opts.auxtrace_snapshot_opts);
+	if (err)
+		return err;
+
+	err = -ENOMEM;
+
 	symbol__init(NULL);
 
 	if (symbol_conf.kptr_restrict)
@@ -1002,6 +1156,10 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (perf_evlist__create_maps(rec->evlist, &rec->opts.target) < 0)
 		usage_with_options(record_usage, record_options);
 
+	err = auxtrace_record__options(rec->itr, rec->evlist, &rec->opts);
+	if (err)
+		goto out_symbol_exit;
+
 	if (record_opts__config(&rec->opts)) {
 		err = -EINVAL;
 		goto out_symbol_exit;
@@ -1011,5 +1169,15 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 out_symbol_exit:
 	perf_evlist__delete(rec->evlist);
 	symbol__exit();
+	auxtrace_record__free(rec->itr);
 	return err;
 }
+
+static void snapshot_sig_handler(int sig __maybe_unused)
+{
+	if (!auxtrace_snapshot_enabled)
+		return;
+	auxtrace_snapshot_enabled = 0;
+	auxtrace_snapshot_err = auxtrace_record__snapshot_start(record.itr);
+	auxtrace_record__snapshot_started = 1;
+}
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index b63aeda719be..32626ea3e227 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -36,6 +36,8 @@
 #include "util/data.h"
 #include "arch/common.h"
 
+#include "util/auxtrace.h"
+
 #include <dlfcn.h>
 #include <linux/bitmap.h>
 
@@ -137,10 +139,12 @@ static int process_sample_event(struct perf_tool *tool,
 	struct report *rep = container_of(tool, struct report, tool);
 	struct addr_location al;
 	struct hist_entry_iter iter = {
-		.hide_unresolved = rep->hide_unresolved,
-		.add_entry_cb = hist_iter__report_callback,
+		.evsel 			= evsel,
+		.sample 		= sample,
+		.hide_unresolved 	= rep->hide_unresolved,
+		.add_entry_cb 		= hist_iter__report_callback,
 	};
-	int ret;
+	int ret = 0;
 
 	if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
 		pr_debug("problem processing %d event, skipping it.\n",
@@ -149,10 +153,10 @@ static int process_sample_event(struct perf_tool *tool,
 	}
 
 	if (rep->hide_unresolved && al.sym == NULL)
-		return 0;
+		goto out_put;
 
 	if (rep->cpu_list && !test_bit(sample->cpu, rep->cpu_bitmap))
-		return 0;
+		goto out_put;
 
 	if (sort__mode == SORT_MODE__BRANCH)
 		iter.ops = &hist_iter_branch;
@@ -166,11 +170,11 @@ static int process_sample_event(struct perf_tool *tool,
 	if (al.map != NULL)
 		al.map->dso->hit = 1;
 
-	ret = hist_entry_iter__add(&iter, &al, evsel, sample, rep->max_stack,
-				   rep);
+	ret = hist_entry_iter__add(&iter, &al, rep->max_stack, rep);
 	if (ret < 0)
 		pr_debug("problem adding hist entry, skipping event\n");
-
+out_put:
+	addr_location__put(&al);
 	return ret;
 }
 
@@ -316,6 +320,7 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
 {
 	struct perf_evsel *pos;
 
+	fprintf(stdout, "#\n# Total Lost Samples: %" PRIu64 "\n#\n", evlist->stats.total_lost_samples);
 	evlist__for_each(evlist, pos) {
 		struct hists *hists = evsel__hists(pos);
 		const char *evname = perf_evsel__name(pos);
@@ -330,15 +335,14 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
 	}
 
 	if (sort_order == NULL &&
-	    parent_pattern == default_parent_pattern) {
+	    parent_pattern == default_parent_pattern)
 		fprintf(stdout, "#\n# (%s)\n#\n", help);
 
-		if (rep->show_threads) {
-			bool style = !strcmp(rep->pretty_printing_style, "raw");
-			perf_read_values_display(stdout, &rep->show_threads_values,
-						 style);
-			perf_read_values_destroy(&rep->show_threads_values);
-		}
+	if (rep->show_threads) {
+		bool style = !strcmp(rep->pretty_printing_style, "raw");
+		perf_read_values_display(stdout, &rep->show_threads_values,
+					 style);
+		perf_read_values_destroy(&rep->show_threads_values);
 	}
 
 	return 0;
@@ -585,6 +589,7 @@ parse_percent_limit(const struct option *opt, const char *str,
 int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	struct perf_session *session;
+	struct itrace_synth_opts itrace_synth_opts = { .set = 0, };
 	struct stat st;
 	bool has_br_stack = false;
 	int branch_mode = -1;
@@ -607,6 +612,9 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 			.attr		 = perf_event__process_attr,
 			.tracing_data	 = perf_event__process_tracing_data,
 			.build_id	 = perf_event__process_build_id,
+			.id_index	 = perf_event__process_id_index,
+			.auxtrace_info	 = perf_event__process_auxtrace_info,
+			.auxtrace	 = perf_event__process_auxtrace,
 			.ordered_events	 = true,
 			.ordering_requires_timestamps = true,
 		},
@@ -717,6 +725,9 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 		     "Don't show entries under that percent", parse_percent_limit),
 	OPT_CALLBACK(0, "percentage", NULL, "relative|absolute",
 		     "how to display percentage of filtered entries", parse_filter_percentage),
+	OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts",
+			    "Instruction Tracing options",
+			    itrace_parse_synth_opts),
 	OPT_END()
 	};
 	struct perf_data_file file = {
@@ -761,6 +772,8 @@ repeat:
 					       report.queue_size);
 	}
 
+	session->itrace_synth_opts = &itrace_synth_opts;
+
 	report.session = session;
 
 	has_br_stack = perf_header__has_feat(&session->header,
@@ -803,8 +816,8 @@ repeat:
 		goto error;
 	}
 
-	/* Force tty output for header output. */
-	if (report.header || report.header_only)
+	/* Force tty output for header output and per-thread stat. */
+	if (report.header || report.header_only || report.show_threads)
 		use_browser = 0;
 
 	if (strcmp(input_name, "-") != 0)
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 5275bab70313..33962612a5e9 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -95,6 +95,7 @@ struct work_atoms {
 	u64			total_lat;
 	u64			nb_atoms;
 	u64			total_runtime;
+	int			num_merged;
 };
 
 typedef int (*sort_fn_t)(struct work_atoms *, struct work_atoms *);
@@ -168,9 +169,10 @@ struct perf_sched {
 	u64		 all_runtime;
 	u64		 all_count;
 	u64		 cpu_last_switched[MAX_CPUS];
-	struct rb_root	 atom_root, sorted_atom_root;
+	struct rb_root	 atom_root, sorted_atom_root, merged_atom_root;
 	struct list_head sort_list, cmp_pid;
 	bool force;
+	bool skip_merge;
 };
 
 static u64 get_nsecs(void)
@@ -770,7 +772,7 @@ static int replay_fork_event(struct perf_sched *sched,
 	if (child == NULL || parent == NULL) {
 		pr_debug("thread does not exist on fork event: child %p, parent %p\n",
 				 child, parent);
-		return 0;
+		goto out_put;
 	}
 
 	if (verbose) {
@@ -781,6 +783,9 @@ static int replay_fork_event(struct perf_sched *sched,
 
 	register_pid(sched, parent->tid, thread__comm_str(parent));
 	register_pid(sched, child->tid, thread__comm_str(child));
+out_put:
+	thread__put(child);
+	thread__put(parent);
 	return 0;
 }
 
@@ -957,7 +962,7 @@ static int latency_switch_event(struct perf_sched *sched,
 	struct work_atoms *out_events, *in_events;
 	struct thread *sched_out, *sched_in;
 	u64 timestamp0, timestamp = sample->time;
-	int cpu = sample->cpu;
+	int cpu = sample->cpu, err = -1;
 	s64 delta;
 
 	BUG_ON(cpu >= MAX_CPUS || cpu < 0);
@@ -976,15 +981,17 @@ static int latency_switch_event(struct perf_sched *sched,
 
 	sched_out = machine__findnew_thread(machine, -1, prev_pid);
 	sched_in = machine__findnew_thread(machine, -1, next_pid);
+	if (sched_out == NULL || sched_in == NULL)
+		goto out_put;
 
 	out_events = thread_atoms_search(&sched->atom_root, sched_out, &sched->cmp_pid);
 	if (!out_events) {
 		if (thread_atoms_insert(sched, sched_out))
-			return -1;
+			goto out_put;
 		out_events = thread_atoms_search(&sched->atom_root, sched_out, &sched->cmp_pid);
 		if (!out_events) {
 			pr_err("out-event: Internal tree error");
-			return -1;
+			goto out_put;
 		}
 	}
 	if (add_sched_out_event(out_events, sched_out_state(prev_state), timestamp))
@@ -993,22 +1000,25 @@ static int latency_switch_event(struct perf_sched *sched,
 	in_events = thread_atoms_search(&sched->atom_root, sched_in, &sched->cmp_pid);
 	if (!in_events) {
 		if (thread_atoms_insert(sched, sched_in))
-			return -1;
+			goto out_put;
 		in_events = thread_atoms_search(&sched->atom_root, sched_in, &sched->cmp_pid);
 		if (!in_events) {
 			pr_err("in-event: Internal tree error");
-			return -1;
+			goto out_put;
 		}
 		/*
 		 * Take came in we have not heard about yet,
 		 * add in an initial atom in runnable state:
 		 */
 		if (add_sched_out_event(in_events, 'R', timestamp))
-			return -1;
+			goto out_put;
 	}
 	add_sched_in_event(in_events, timestamp);
-
-	return 0;
+	err = 0;
+out_put:
+	thread__put(sched_out);
+	thread__put(sched_in);
+	return err;
 }
 
 static int latency_runtime_event(struct perf_sched *sched,
@@ -1021,23 +1031,29 @@ static int latency_runtime_event(struct perf_sched *sched,
 	struct thread *thread = machine__findnew_thread(machine, -1, pid);
 	struct work_atoms *atoms = thread_atoms_search(&sched->atom_root, thread, &sched->cmp_pid);
 	u64 timestamp = sample->time;
-	int cpu = sample->cpu;
+	int cpu = sample->cpu, err = -1;
+
+	if (thread == NULL)
+		return -1;
 
 	BUG_ON(cpu >= MAX_CPUS || cpu < 0);
 	if (!atoms) {
 		if (thread_atoms_insert(sched, thread))
-			return -1;
+			goto out_put;
 		atoms = thread_atoms_search(&sched->atom_root, thread, &sched->cmp_pid);
 		if (!atoms) {
 			pr_err("in-event: Internal tree error");
-			return -1;
+			goto out_put;
 		}
 		if (add_sched_out_event(atoms, 'R', timestamp))
-			return -1;
+			goto out_put;
 	}
 
 	add_runtime_event(atoms, runtime, timestamp);
-	return 0;
+	err = 0;
+out_put:
+	thread__put(thread);
+	return err;
 }
 
 static int latency_wakeup_event(struct perf_sched *sched,
@@ -1050,19 +1066,22 @@ static int latency_wakeup_event(struct perf_sched *sched,
 	struct work_atom *atom;
 	struct thread *wakee;
 	u64 timestamp = sample->time;
+	int err = -1;
 
 	wakee = machine__findnew_thread(machine, -1, pid);
+	if (wakee == NULL)
+		return -1;
 	atoms = thread_atoms_search(&sched->atom_root, wakee, &sched->cmp_pid);
 	if (!atoms) {
 		if (thread_atoms_insert(sched, wakee))
-			return -1;
+			goto out_put;
 		atoms = thread_atoms_search(&sched->atom_root, wakee, &sched->cmp_pid);
 		if (!atoms) {
 			pr_err("wakeup-event: Internal tree error");
-			return -1;
+			goto out_put;
 		}
 		if (add_sched_out_event(atoms, 'S', timestamp))
-			return -1;
+			goto out_put;
 	}
 
 	BUG_ON(list_empty(&atoms->work_list));
@@ -1081,17 +1100,21 @@ static int latency_wakeup_event(struct perf_sched *sched,
 	 * skip in this case.
 	 */
 	if (sched->profile_cpu == -1 && atom->state != THREAD_SLEEPING)
-		return 0;
+		goto out_ok;
 
 	sched->nr_timestamps++;
 	if (atom->sched_out_time > timestamp) {
 		sched->nr_unordered_timestamps++;
-		return 0;
+		goto out_ok;
 	}
 
 	atom->state = THREAD_WAIT_CPU;
 	atom->wake_up_time = timestamp;
-	return 0;
+out_ok:
+	err = 0;
+out_put:
+	thread__put(wakee);
+	return err;
 }
 
 static int latency_migrate_task_event(struct perf_sched *sched,
@@ -1104,6 +1127,7 @@ static int latency_migrate_task_event(struct perf_sched *sched,
 	struct work_atoms *atoms;
 	struct work_atom *atom;
 	struct thread *migrant;
+	int err = -1;
 
 	/*
 	 * Only need to worry about migration when profiling one CPU.
@@ -1112,18 +1136,20 @@ static int latency_migrate_task_event(struct perf_sched *sched,
 		return 0;
 
 	migrant = machine__findnew_thread(machine, -1, pid);
+	if (migrant == NULL)
+		return -1;
 	atoms = thread_atoms_search(&sched->atom_root, migrant, &sched->cmp_pid);
 	if (!atoms) {
 		if (thread_atoms_insert(sched, migrant))
-			return -1;
+			goto out_put;
 		register_pid(sched, migrant->tid, thread__comm_str(migrant));
 		atoms = thread_atoms_search(&sched->atom_root, migrant, &sched->cmp_pid);
 		if (!atoms) {
 			pr_err("migration-event: Internal tree error");
-			return -1;
+			goto out_put;
 		}
 		if (add_sched_out_event(atoms, 'R', timestamp))
-			return -1;
+			goto out_put;
 	}
 
 	BUG_ON(list_empty(&atoms->work_list));
@@ -1135,8 +1161,10 @@ static int latency_migrate_task_event(struct perf_sched *sched,
 
 	if (atom->sched_out_time > timestamp)
 		sched->nr_unordered_timestamps++;
-
-	return 0;
+	err = 0;
+out_put:
+	thread__put(migrant);
+	return err;
 }
 
 static void output_lat_thread(struct perf_sched *sched, struct work_atoms *work_list)
@@ -1156,7 +1184,10 @@ static void output_lat_thread(struct perf_sched *sched, struct work_atoms *work_
 	sched->all_runtime += work_list->total_runtime;
 	sched->all_count   += work_list->nb_atoms;
 
-	ret = printf("  %s:%d ", thread__comm_str(work_list->thread), work_list->thread->tid);
+	if (work_list->num_merged > 1)
+		ret = printf("  %s:(%d) ", thread__comm_str(work_list->thread), work_list->num_merged);
+	else
+		ret = printf("  %s:%d ", thread__comm_str(work_list->thread), work_list->thread->tid);
 
 	for (i = 0; i < 24 - ret; i++)
 		printf(" ");
@@ -1276,17 +1307,22 @@ static int sort_dimension__add(const char *tok, struct list_head *list)
 static void perf_sched__sort_lat(struct perf_sched *sched)
 {
 	struct rb_node *node;
-
+	struct rb_root *root = &sched->atom_root;
+again:
 	for (;;) {
 		struct work_atoms *data;
-		node = rb_first(&sched->atom_root);
+		node = rb_first(root);
 		if (!node)
 			break;
 
-		rb_erase(node, &sched->atom_root);
+		rb_erase(node, root);
 		data = rb_entry(node, struct work_atoms, node);
 		__thread_latency_insert(&sched->sorted_atom_root, data, &sched->sort_list);
 	}
+	if (root == &sched->atom_root) {
+		root = &sched->merged_atom_root;
+		goto again;
+	}
 }
 
 static int process_sched_wakeup_event(struct perf_tool *tool,
@@ -1330,8 +1366,10 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
 	}
 
 	sched_in = machine__findnew_thread(machine, -1, next_pid);
+	if (sched_in == NULL)
+		return -1;
 
-	sched->curr_thread[this_cpu] = sched_in;
+	sched->curr_thread[this_cpu] = thread__get(sched_in);
 
 	printf("  ");
 
@@ -1381,6 +1419,8 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
 		printf("\n");
 	}
 
+	thread__put(sched_in);
+
 	return 0;
 }
 
@@ -1542,6 +1582,59 @@ static void print_bad_events(struct perf_sched *sched)
 	}
 }
 
+static void __merge_work_atoms(struct rb_root *root, struct work_atoms *data)
+{
+	struct rb_node **new = &(root->rb_node), *parent = NULL;
+	struct work_atoms *this;
+	const char *comm = thread__comm_str(data->thread), *this_comm;
+
+	while (*new) {
+		int cmp;
+
+		this = container_of(*new, struct work_atoms, node);
+		parent = *new;
+
+		this_comm = thread__comm_str(this->thread);
+		cmp = strcmp(comm, this_comm);
+		if (cmp > 0) {
+			new = &((*new)->rb_left);
+		} else if (cmp < 0) {
+			new = &((*new)->rb_right);
+		} else {
+			this->num_merged++;
+			this->total_runtime += data->total_runtime;
+			this->nb_atoms += data->nb_atoms;
+			this->total_lat += data->total_lat;
+			list_splice(&data->work_list, &this->work_list);
+			if (this->max_lat < data->max_lat) {
+				this->max_lat = data->max_lat;
+				this->max_lat_at = data->max_lat_at;
+			}
+			zfree(&data);
+			return;
+		}
+	}
+
+	data->num_merged++;
+	rb_link_node(&data->node, parent, new);
+	rb_insert_color(&data->node, root);
+}
+
+static void perf_sched__merge_lat(struct perf_sched *sched)
+{
+	struct work_atoms *data;
+	struct rb_node *node;
+
+	if (sched->skip_merge)
+		return;
+
+	while ((node = rb_first(&sched->atom_root))) {
+		rb_erase(node, &sched->atom_root);
+		data = rb_entry(node, struct work_atoms, node);
+		__merge_work_atoms(&sched->merged_atom_root, data);
+	}
+}
+
 static int perf_sched__lat(struct perf_sched *sched)
 {
 	struct rb_node *next;
@@ -1551,6 +1644,7 @@ static int perf_sched__lat(struct perf_sched *sched)
 	if (perf_sched__read_events(sched))
 		return -1;
 
+	perf_sched__merge_lat(sched);
 	perf_sched__sort_lat(sched);
 
 	printf("\n -----------------------------------------------------------------------------------------------------------------\n");
@@ -1702,6 +1796,7 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
 		.profile_cpu	      = -1,
 		.next_shortname1      = 'A',
 		.next_shortname2      = '0',
+		.skip_merge           = 0,
 	};
 	const struct option latency_options[] = {
 	OPT_STRING('s', "sort", &sched.sort_order, "key[,key2...]",
@@ -1712,6 +1807,8 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
 		    "CPU to profile on"),
 	OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
 		    "dump raw trace in ASCII"),
+	OPT_BOOLEAN('p', "pids", &sched.skip_merge,
+		    "latency stats per pid instead of per comm"),
 	OPT_END()
 	};
 	const struct option replay_options[] = {
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 58f10b8e6ff2..24809787369f 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -16,6 +16,7 @@
 #include "util/evsel.h"
 #include "util/sort.h"
 #include "util/data.h"
+#include "util/auxtrace.h"
 #include <linux/bitmap.h>
 
 static char const		*script_name;
@@ -26,6 +27,7 @@ static u64			nr_unordered;
 static bool			no_callchain;
 static bool			latency_format;
 static bool			system_wide;
+static bool			print_flags;
 static const char		*cpu_list;
 static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 
@@ -146,9 +148,10 @@ static const char *output_field2str(enum perf_output_field field)
 
 #define PRINT_FIELD(x)  (output[attr->type].fields & PERF_OUTPUT_##x)
 
-static int perf_evsel__check_stype(struct perf_evsel *evsel,
-				   u64 sample_type, const char *sample_msg,
-				   enum perf_output_field field)
+static int perf_evsel__do_check_stype(struct perf_evsel *evsel,
+				      u64 sample_type, const char *sample_msg,
+				      enum perf_output_field field,
+				      bool allow_user_set)
 {
 	struct perf_event_attr *attr = &evsel->attr;
 	int type = attr->type;
@@ -158,6 +161,8 @@ static int perf_evsel__check_stype(struct perf_evsel *evsel,
 		return 0;
 
 	if (output[type].user_set) {
+		if (allow_user_set)
+			return 0;
 		evname = perf_evsel__name(evsel);
 		pr_err("Samples for '%s' event do not have %s attribute set. "
 		       "Cannot print '%s' field.\n",
@@ -175,10 +180,22 @@ static int perf_evsel__check_stype(struct perf_evsel *evsel,
 	return 0;
 }
 
+static int perf_evsel__check_stype(struct perf_evsel *evsel,
+				   u64 sample_type, const char *sample_msg,
+				   enum perf_output_field field)
+{
+	return perf_evsel__do_check_stype(evsel, sample_type, sample_msg, field,
+					  false);
+}
+
 static int perf_evsel__check_attr(struct perf_evsel *evsel,
 				  struct perf_session *session)
 {
 	struct perf_event_attr *attr = &evsel->attr;
+	bool allow_user_set;
+
+	allow_user_set = perf_header__has_feat(&session->header,
+					       HEADER_AUXTRACE);
 
 	if (PRINT_FIELD(TRACE) &&
 		!perf_session__has_traces(session, "record -R"))
@@ -191,8 +208,8 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 	}
 
 	if (PRINT_FIELD(ADDR) &&
-		perf_evsel__check_stype(evsel, PERF_SAMPLE_ADDR, "ADDR",
-					PERF_OUTPUT_ADDR))
+		perf_evsel__do_check_stype(evsel, PERF_SAMPLE_ADDR, "ADDR",
+					   PERF_OUTPUT_ADDR, allow_user_set))
 		return -EINVAL;
 
 	if (PRINT_FIELD(SYM) && !PRINT_FIELD(IP) && !PRINT_FIELD(ADDR)) {
@@ -229,8 +246,8 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 		return -EINVAL;
 
 	if (PRINT_FIELD(CPU) &&
-		perf_evsel__check_stype(evsel, PERF_SAMPLE_CPU, "CPU",
-					PERF_OUTPUT_CPU))
+		perf_evsel__do_check_stype(evsel, PERF_SAMPLE_CPU, "CPU",
+					   PERF_OUTPUT_CPU, allow_user_set))
 		return -EINVAL;
 
 	if (PRINT_FIELD(PERIOD) &&
@@ -445,6 +462,25 @@ static void print_sample_bts(union perf_event *event,
 	printf("\n");
 }
 
+static void print_sample_flags(u32 flags)
+{
+	const char *chars = PERF_IP_FLAG_CHARS;
+	const int n = strlen(PERF_IP_FLAG_CHARS);
+	char str[33];
+	int i, pos = 0;
+
+	for (i = 0; i < n; i++, flags >>= 1) {
+		if (flags & 1)
+			str[pos++] = chars[i];
+	}
+	for (; i < 32; i++, flags >>= 1) {
+		if (flags & 1)
+			str[pos++] = '?';
+	}
+	str[pos] = 0;
+	printf("  %-4s ", str);
+}
+
 static void process_event(union perf_event *event, struct perf_sample *sample,
 			  struct perf_evsel *evsel, struct addr_location *al)
 {
@@ -464,6 +500,9 @@ static void process_event(union perf_event *event, struct perf_sample *sample,
 		printf("%s: ", evname ? evname : "[unknown]");
 	}
 
+	if (print_flags)
+		print_sample_flags(sample->flags);
+
 	if (is_bts_event(attr)) {
 		print_sample_bts(event, sample, evsel, thread, al);
 		return;
@@ -568,13 +607,14 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 	}
 
 	if (al.filtered)
-		return 0;
+		goto out_put;
 
 	if (cpu_list && !test_bit(sample->cpu, cpu_bitmap))
-		return 0;
+		goto out_put;
 
 	scripting_ops->process_event(event, sample, evsel, &al);
-
+out_put:
+	addr_location__put(&al);
 	return 0;
 }
 
@@ -642,8 +682,8 @@ static int process_comm_event(struct perf_tool *tool,
 	print_sample_start(sample, thread, evsel);
 	perf_event__fprintf(event, stdout);
 	ret = 0;
-
 out:
+	thread__put(thread);
 	return ret;
 }
 
@@ -674,6 +714,7 @@ static int process_fork_event(struct perf_tool *tool,
 	}
 	print_sample_start(sample, thread, evsel);
 	perf_event__fprintf(event, stdout);
+	thread__put(thread);
 
 	return 0;
 }
@@ -682,6 +723,7 @@ static int process_exit_event(struct perf_tool *tool,
 			      struct perf_sample *sample,
 			      struct machine *machine)
 {
+	int err = 0;
 	struct thread *thread;
 	struct perf_script *script = container_of(tool, struct perf_script, tool);
 	struct perf_session *session = script->session;
@@ -703,9 +745,10 @@ static int process_exit_event(struct perf_tool *tool,
 	perf_event__fprintf(event, stdout);
 
 	if (perf_event__process_exit(tool, event, sample, machine) < 0)
-		return -1;
+		err = -1;
 
-	return 0;
+	thread__put(thread);
+	return err;
 }
 
 static int process_mmap_event(struct perf_tool *tool,
@@ -735,7 +778,7 @@ static int process_mmap_event(struct perf_tool *tool,
 	}
 	print_sample_start(sample, thread, evsel);
 	perf_event__fprintf(event, stdout);
-
+	thread__put(thread);
 	return 0;
 }
 
@@ -766,7 +809,7 @@ static int process_mmap2_event(struct perf_tool *tool,
 	}
 	print_sample_start(sample, thread, evsel);
 	perf_event__fprintf(event, stdout);
-
+	thread__put(thread);
 	return 0;
 }
 
@@ -999,12 +1042,15 @@ static int parse_output_fields(const struct option *opt __maybe_unused,
 		}
 	}
 
-	tok = strtok(tok, ",");
-	while (tok) {
+	for (tok = strtok(tok, ","); tok; tok = strtok(NULL, ",")) {
 		for (i = 0; i < imax; ++i) {
 			if (strcmp(tok, all_output_options[i].str) == 0)
 				break;
 		}
+		if (i == imax && strcmp(tok, "flags") == 0) {
+			print_flags = true;
+			continue;
+		}
 		if (i == imax) {
 			fprintf(stderr, "Invalid field requested.\n");
 			rc = -EINVAL;
@@ -1032,8 +1078,6 @@ static int parse_output_fields(const struct option *opt __maybe_unused,
 			}
 			output[type].fields |= all_output_options[i].field;
 		}
-
-		tok = strtok(NULL, ",");
 	}
 
 	if (type >= 0) {
@@ -1497,6 +1541,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 	char *rec_script_path = NULL;
 	char *rep_script_path = NULL;
 	struct perf_session *session;
+	struct itrace_synth_opts itrace_synth_opts = { .set = false, };
 	char *script_path = NULL;
 	const char **__argv;
 	int i, j, err = 0;
@@ -1511,6 +1556,10 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 			.attr		 = process_attr,
 			.tracing_data	 = perf_event__process_tracing_data,
 			.build_id	 = perf_event__process_build_id,
+			.id_index	 = perf_event__process_id_index,
+			.auxtrace_info	 = perf_event__process_auxtrace_info,
+			.auxtrace	 = perf_event__process_auxtrace,
+			.auxtrace_error	 = perf_event__process_auxtrace_error,
 			.ordered_events	 = true,
 			.ordering_requires_timestamps = true,
 		},
@@ -1549,7 +1598,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 		     "comma separated output fields prepend with 'type:'. "
 		     "Valid types: hw,sw,trace,raw. "
 		     "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
-		     "addr,symoff,period", parse_output_fields),
+		     "addr,symoff,period,flags", parse_output_fields),
 	OPT_BOOLEAN('a', "all-cpus", &system_wide,
 		    "system-wide collection from all CPUs"),
 	OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]",
@@ -1570,6 +1619,9 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_BOOLEAN('\0', "show-mmap-events", &script.show_mmap_events,
 		    "Show the mmap events"),
 	OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"),
+	OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts",
+			    "Instruction Tracing options",
+			    itrace_parse_synth_opts),
 	OPT_END()
 	};
 	const char * const script_subcommands[] = { "record", "report", NULL };
@@ -1765,6 +1817,8 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	script.session = session;
 
+	session->itrace_synth_opts = &itrace_synth_opts;
+
 	if (cpu_list) {
 		err = perf_session__cpu_bitmap(session, cpu_list, cpu_bitmap);
 		if (err < 0)
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index f7b8218785f6..fcf99bdeb19e 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -73,8 +73,8 @@ static void print_counter(struct perf_evsel *counter, char *prefix);
 static void print_aggr(char *prefix);
 
 /* Default events used for perf stat -T */
-static const char * const transaction_attrs[] = {
-	"task-clock",
+static const char *transaction_attrs = {
+	"task-clock,"
 	"{"
 	"instructions,"
 	"cycles,"
@@ -86,8 +86,8 @@ static const char * const transaction_attrs[] = {
 };
 
 /* More limited version when the CPU does not have all events. */
-static const char * const transaction_limited_attrs[] = {
-	"task-clock",
+static const char * transaction_limited_attrs = {
+	"task-clock,"
 	"{"
 	"instructions,"
 	"cycles,"
@@ -96,30 +96,12 @@ static const char * const transaction_limited_attrs[] = {
 	"}"
 };
 
-/* must match transaction_attrs and the beginning limited_attrs */
-enum {
-	T_TASK_CLOCK,
-	T_INSTRUCTIONS,
-	T_CYCLES,
-	T_CYCLES_IN_TX,
-	T_TRANSACTION_START,
-	T_ELISION_START,
-	T_CYCLES_IN_TX_CP,
-};
-
 static struct perf_evlist	*evsel_list;
 
 static struct target target = {
 	.uid	= UINT_MAX,
 };
 
-enum aggr_mode {
-	AGGR_NONE,
-	AGGR_GLOBAL,
-	AGGR_SOCKET,
-	AGGR_CORE,
-};
-
 static int			run_count			=  1;
 static bool			no_inherit			= false;
 static bool			scale				=  true;
@@ -147,10 +129,6 @@ static int			(*aggr_get_id)(struct cpu_map *m, int cpu);
 
 static volatile int done = 0;
 
-struct perf_stat {
-	struct stats	  res_stats[3];
-};
-
 static inline void diff_timespec(struct timespec *r, struct timespec *a,
 				 struct timespec *b)
 {
@@ -180,6 +158,8 @@ static void perf_evsel__reset_stat_priv(struct perf_evsel *evsel)
 
 	for (i = 0; i < 3; i++)
 		init_stats(&ps->res_stats[i]);
+
+	perf_stat_evsel_id_init(evsel);
 }
 
 static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
@@ -198,24 +178,19 @@ static void perf_evsel__free_stat_priv(struct perf_evsel *evsel)
 
 static int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel)
 {
-	void *addr;
-	size_t sz;
+	struct perf_counts *counts;
 
-	sz = sizeof(*evsel->counts) +
-	     (perf_evsel__nr_cpus(evsel) * sizeof(struct perf_counts_values));
+	counts = perf_counts__new(perf_evsel__nr_cpus(evsel));
+	if (counts)
+		evsel->prev_raw_counts = counts;
 
-	addr = zalloc(sz);
-	if (!addr)
-		return -ENOMEM;
-
-	evsel->prev_raw_counts =  addr;
-
-	return 0;
+	return counts ? 0 : -ENOMEM;
 }
 
 static void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel)
 {
-	zfree(&evsel->prev_raw_counts);
+	perf_counts__delete(evsel->prev_raw_counts);
+	evsel->prev_raw_counts = NULL;
 }
 
 static void perf_evlist__free_stats(struct perf_evlist *evlist)
@@ -247,22 +222,6 @@ out_free:
 	return -1;
 }
 
-static struct stats runtime_nsecs_stats[MAX_NR_CPUS];
-static struct stats runtime_cycles_stats[MAX_NR_CPUS];
-static struct stats runtime_stalled_cycles_front_stats[MAX_NR_CPUS];
-static struct stats runtime_stalled_cycles_back_stats[MAX_NR_CPUS];
-static struct stats runtime_branches_stats[MAX_NR_CPUS];
-static struct stats runtime_cacherefs_stats[MAX_NR_CPUS];
-static struct stats runtime_l1_dcache_stats[MAX_NR_CPUS];
-static struct stats runtime_l1_icache_stats[MAX_NR_CPUS];
-static struct stats runtime_ll_cache_stats[MAX_NR_CPUS];
-static struct stats runtime_itlb_cache_stats[MAX_NR_CPUS];
-static struct stats runtime_dtlb_cache_stats[MAX_NR_CPUS];
-static struct stats runtime_cycles_in_tx_stats[MAX_NR_CPUS];
-static struct stats walltime_nsecs_stats;
-static struct stats runtime_transaction_stats[MAX_NR_CPUS];
-static struct stats runtime_elision_stats[MAX_NR_CPUS];
-
 static void perf_stat__reset_stats(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel;
@@ -272,23 +231,7 @@ static void perf_stat__reset_stats(struct perf_evlist *evlist)
 		perf_evsel__reset_counts(evsel, perf_evsel__nr_cpus(evsel));
 	}
 
-	memset(runtime_nsecs_stats, 0, sizeof(runtime_nsecs_stats));
-	memset(runtime_cycles_stats, 0, sizeof(runtime_cycles_stats));
-	memset(runtime_stalled_cycles_front_stats, 0, sizeof(runtime_stalled_cycles_front_stats));
-	memset(runtime_stalled_cycles_back_stats, 0, sizeof(runtime_stalled_cycles_back_stats));
-	memset(runtime_branches_stats, 0, sizeof(runtime_branches_stats));
-	memset(runtime_cacherefs_stats, 0, sizeof(runtime_cacherefs_stats));
-	memset(runtime_l1_dcache_stats, 0, sizeof(runtime_l1_dcache_stats));
-	memset(runtime_l1_icache_stats, 0, sizeof(runtime_l1_icache_stats));
-	memset(runtime_ll_cache_stats, 0, sizeof(runtime_ll_cache_stats));
-	memset(runtime_itlb_cache_stats, 0, sizeof(runtime_itlb_cache_stats));
-	memset(runtime_dtlb_cache_stats, 0, sizeof(runtime_dtlb_cache_stats));
-	memset(runtime_cycles_in_tx_stats, 0,
-			sizeof(runtime_cycles_in_tx_stats));
-	memset(runtime_transaction_stats, 0,
-		sizeof(runtime_transaction_stats));
-	memset(runtime_elision_stats, 0, sizeof(runtime_elision_stats));
-	memset(&walltime_nsecs_stats, 0, sizeof(walltime_nsecs_stats));
+	perf_stat__reset_shadow_stats();
 }
 
 static int create_perf_stat_counter(struct perf_evsel *evsel)
@@ -325,70 +268,6 @@ static inline int nsec_counter(struct perf_evsel *evsel)
 	return 0;
 }
 
-static struct perf_evsel *nth_evsel(int n)
-{
-	static struct perf_evsel **array;
-	static int array_len;
-	struct perf_evsel *ev;
-	int j;
-
-	/* Assumes this only called when evsel_list does not change anymore. */
-	if (!array) {
-		evlist__for_each(evsel_list, ev)
-			array_len++;
-		array = malloc(array_len * sizeof(void *));
-		if (!array)
-			exit(ENOMEM);
-		j = 0;
-		evlist__for_each(evsel_list, ev)
-			array[j++] = ev;
-	}
-	if (n < array_len)
-		return array[n];
-	return NULL;
-}
-
-/*
- * Update various tracking values we maintain to print
- * more semantic information such as miss/hit ratios,
- * instruction rates, etc:
- */
-static void update_shadow_stats(struct perf_evsel *counter, u64 *count,
-				int cpu)
-{
-	if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK))
-		update_stats(&runtime_nsecs_stats[cpu], count[0]);
-	else if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
-		update_stats(&runtime_cycles_stats[cpu], count[0]);
-	else if (transaction_run &&
-		 perf_evsel__cmp(counter, nth_evsel(T_CYCLES_IN_TX)))
-		update_stats(&runtime_cycles_in_tx_stats[cpu], count[0]);
-	else if (transaction_run &&
-		 perf_evsel__cmp(counter, nth_evsel(T_TRANSACTION_START)))
-		update_stats(&runtime_transaction_stats[cpu], count[0]);
-	else if (transaction_run &&
-		 perf_evsel__cmp(counter, nth_evsel(T_ELISION_START)))
-		update_stats(&runtime_elision_stats[cpu], count[0]);
-	else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND))
-		update_stats(&runtime_stalled_cycles_front_stats[cpu], count[0]);
-	else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND))
-		update_stats(&runtime_stalled_cycles_back_stats[cpu], count[0]);
-	else if (perf_evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS))
-		update_stats(&runtime_branches_stats[cpu], count[0]);
-	else if (perf_evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES))
-		update_stats(&runtime_cacherefs_stats[cpu], count[0]);
-	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1D))
-		update_stats(&runtime_l1_dcache_stats[cpu], count[0]);
-	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1I))
-		update_stats(&runtime_l1_icache_stats[cpu], count[0]);
-	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_LL))
-		update_stats(&runtime_ll_cache_stats[cpu], count[0]);
-	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_DTLB))
-		update_stats(&runtime_dtlb_cache_stats[cpu], count[0]);
-	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_ITLB))
-		update_stats(&runtime_itlb_cache_stats[cpu], count[0]);
-}
-
 static void zero_per_pkg(struct perf_evsel *counter)
 {
 	if (counter->per_pkg_mask)
@@ -449,7 +328,7 @@ static int read_cb(struct perf_evsel *evsel, int cpu, int thread __maybe_unused,
 		perf_counts_values__scale(count, scale, NULL);
 		evsel->counts->cpu[cpu] = *count;
 		if (aggr_mode == AGGR_NONE)
-			update_shadow_stats(evsel, count->values, cpu);
+			perf_stat__update_shadow_stats(evsel, count->values, cpu);
 		break;
 	case AGGR_GLOBAL:
 		aggr->val += count->val;
@@ -497,7 +376,7 @@ static int read_counter_aggr(struct perf_evsel *counter)
 	/*
 	 * Save the full runtime - to allow normalization during printout:
 	 */
-	update_shadow_stats(counter, count, 0);
+	perf_stat__update_shadow_stats(counter, count, 0);
 
 	return 0;
 }
@@ -665,7 +544,10 @@ static int __run_perf_stat(int argc, const char **argv)
 					ui__warning("%s event is not supported by the kernel.\n",
 						    perf_evsel__name(counter));
 				counter->supported = false;
-				continue;
+
+				if ((counter->leader != counter) ||
+				    !(counter->leader->nr_members > 1))
+					continue;
 			}
 
 			perf_evsel__open_strerror(counter, &target,
@@ -875,188 +757,8 @@ static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 		fprintf(output, "                                   ");
 }
 
-/* used for get_ratio_color() */
-enum grc_type {
-	GRC_STALLED_CYCLES_FE,
-	GRC_STALLED_CYCLES_BE,
-	GRC_CACHE_MISSES,
-	GRC_MAX_NR
-};
-
-static const char *get_ratio_color(enum grc_type type, double ratio)
-{
-	static const double grc_table[GRC_MAX_NR][3] = {
-		[GRC_STALLED_CYCLES_FE] = { 50.0, 30.0, 10.0 },
-		[GRC_STALLED_CYCLES_BE] = { 75.0, 50.0, 20.0 },
-		[GRC_CACHE_MISSES] 	= { 20.0, 10.0, 5.0 },
-	};
-	const char *color = PERF_COLOR_NORMAL;
-
-	if (ratio > grc_table[type][0])
-		color = PERF_COLOR_RED;
-	else if (ratio > grc_table[type][1])
-		color = PERF_COLOR_MAGENTA;
-	else if (ratio > grc_table[type][2])
-		color = PERF_COLOR_YELLOW;
-
-	return color;
-}
-
-static void print_stalled_cycles_frontend(int cpu,
-					  struct perf_evsel *evsel
-					  __maybe_unused, double avg)
-{
-	double total, ratio = 0.0;
-	const char *color;
-
-	total = avg_stats(&runtime_cycles_stats[cpu]);
-
-	if (total)
-		ratio = avg / total * 100.0;
-
-	color = get_ratio_color(GRC_STALLED_CYCLES_FE, ratio);
-
-	fprintf(output, " #  ");
-	color_fprintf(output, color, "%6.2f%%", ratio);
-	fprintf(output, " frontend cycles idle   ");
-}
-
-static void print_stalled_cycles_backend(int cpu,
-					 struct perf_evsel *evsel
-					 __maybe_unused, double avg)
-{
-	double total, ratio = 0.0;
-	const char *color;
-
-	total = avg_stats(&runtime_cycles_stats[cpu]);
-
-	if (total)
-		ratio = avg / total * 100.0;
-
-	color = get_ratio_color(GRC_STALLED_CYCLES_BE, ratio);
-
-	fprintf(output, " #  ");
-	color_fprintf(output, color, "%6.2f%%", ratio);
-	fprintf(output, " backend  cycles idle   ");
-}
-
-static void print_branch_misses(int cpu,
-				struct perf_evsel *evsel __maybe_unused,
-				double avg)
-{
-	double total, ratio = 0.0;
-	const char *color;
-
-	total = avg_stats(&runtime_branches_stats[cpu]);
-
-	if (total)
-		ratio = avg / total * 100.0;
-
-	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
-	fprintf(output, " #  ");
-	color_fprintf(output, color, "%6.2f%%", ratio);
-	fprintf(output, " of all branches        ");
-}
-
-static void print_l1_dcache_misses(int cpu,
-				   struct perf_evsel *evsel __maybe_unused,
-				   double avg)
-{
-	double total, ratio = 0.0;
-	const char *color;
-
-	total = avg_stats(&runtime_l1_dcache_stats[cpu]);
-
-	if (total)
-		ratio = avg / total * 100.0;
-
-	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
-	fprintf(output, " #  ");
-	color_fprintf(output, color, "%6.2f%%", ratio);
-	fprintf(output, " of all L1-dcache hits  ");
-}
-
-static void print_l1_icache_misses(int cpu,
-				   struct perf_evsel *evsel __maybe_unused,
-				   double avg)
-{
-	double total, ratio = 0.0;
-	const char *color;
-
-	total = avg_stats(&runtime_l1_icache_stats[cpu]);
-
-	if (total)
-		ratio = avg / total * 100.0;
-
-	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
-	fprintf(output, " #  ");
-	color_fprintf(output, color, "%6.2f%%", ratio);
-	fprintf(output, " of all L1-icache hits  ");
-}
-
-static void print_dtlb_cache_misses(int cpu,
-				    struct perf_evsel *evsel __maybe_unused,
-				    double avg)
-{
-	double total, ratio = 0.0;
-	const char *color;
-
-	total = avg_stats(&runtime_dtlb_cache_stats[cpu]);
-
-	if (total)
-		ratio = avg / total * 100.0;
-
-	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
-	fprintf(output, " #  ");
-	color_fprintf(output, color, "%6.2f%%", ratio);
-	fprintf(output, " of all dTLB cache hits ");
-}
-
-static void print_itlb_cache_misses(int cpu,
-				    struct perf_evsel *evsel __maybe_unused,
-				    double avg)
-{
-	double total, ratio = 0.0;
-	const char *color;
-
-	total = avg_stats(&runtime_itlb_cache_stats[cpu]);
-
-	if (total)
-		ratio = avg / total * 100.0;
-
-	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
-	fprintf(output, " #  ");
-	color_fprintf(output, color, "%6.2f%%", ratio);
-	fprintf(output, " of all iTLB cache hits ");
-}
-
-static void print_ll_cache_misses(int cpu,
-				  struct perf_evsel *evsel __maybe_unused,
-				  double avg)
-{
-	double total, ratio = 0.0;
-	const char *color;
-
-	total = avg_stats(&runtime_ll_cache_stats[cpu]);
-
-	if (total)
-		ratio = avg / total * 100.0;
-
-	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
-	fprintf(output, " #  ");
-	color_fprintf(output, color, "%6.2f%%", ratio);
-	fprintf(output, " of all LL-cache hits   ");
-}
-
 static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 {
-	double total, ratio = 0.0, total2;
 	double sc =  evsel->scale;
 	const char *fmt;
 	int cpu = cpu_map__id_to_cpu(id);
@@ -1090,138 +792,7 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 	if (csv_output || interval)
 		return;
 
-	if (perf_evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) {
-		total = avg_stats(&runtime_cycles_stats[cpu]);
-		if (total) {
-			ratio = avg / total;
-			fprintf(output, " #   %5.2f  insns per cycle        ", ratio);
-		} else {
-			fprintf(output, "                                   ");
-		}
-		total = avg_stats(&runtime_stalled_cycles_front_stats[cpu]);
-		total = max(total, avg_stats(&runtime_stalled_cycles_back_stats[cpu]));
-
-		if (total && avg) {
-			ratio = total / avg;
-			fprintf(output, "\n");
-			if (aggr_mode == AGGR_NONE)
-				fprintf(output, "        ");
-			fprintf(output, "                                                  #   %5.2f  stalled cycles per insn", ratio);
-		}
-
-	} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES) &&
-			runtime_branches_stats[cpu].n != 0) {
-		print_branch_misses(cpu, evsel, avg);
-	} else if (
-		evsel->attr.type == PERF_TYPE_HW_CACHE &&
-		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1D |
-					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
-					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
-			runtime_l1_dcache_stats[cpu].n != 0) {
-		print_l1_dcache_misses(cpu, evsel, avg);
-	} else if (
-		evsel->attr.type == PERF_TYPE_HW_CACHE &&
-		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1I |
-					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
-					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
-			runtime_l1_icache_stats[cpu].n != 0) {
-		print_l1_icache_misses(cpu, evsel, avg);
-	} else if (
-		evsel->attr.type == PERF_TYPE_HW_CACHE &&
-		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_DTLB |
-					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
-					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
-			runtime_dtlb_cache_stats[cpu].n != 0) {
-		print_dtlb_cache_misses(cpu, evsel, avg);
-	} else if (
-		evsel->attr.type == PERF_TYPE_HW_CACHE &&
-		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_ITLB |
-					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
-					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
-			runtime_itlb_cache_stats[cpu].n != 0) {
-		print_itlb_cache_misses(cpu, evsel, avg);
-	} else if (
-		evsel->attr.type == PERF_TYPE_HW_CACHE &&
-		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_LL |
-					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
-					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
-			runtime_ll_cache_stats[cpu].n != 0) {
-		print_ll_cache_misses(cpu, evsel, avg);
-	} else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES) &&
-			runtime_cacherefs_stats[cpu].n != 0) {
-		total = avg_stats(&runtime_cacherefs_stats[cpu]);
-
-		if (total)
-			ratio = avg * 100 / total;
-
-		fprintf(output, " # %8.3f %% of all cache refs    ", ratio);
-
-	} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) {
-		print_stalled_cycles_frontend(cpu, evsel, avg);
-	} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) {
-		print_stalled_cycles_backend(cpu, evsel, avg);
-	} else if (perf_evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) {
-		total = avg_stats(&runtime_nsecs_stats[cpu]);
-
-		if (total) {
-			ratio = avg / total;
-			fprintf(output, " # %8.3f GHz                    ", ratio);
-		} else {
-			fprintf(output, "                                   ");
-		}
-	} else if (transaction_run &&
-		   perf_evsel__cmp(evsel, nth_evsel(T_CYCLES_IN_TX))) {
-		total = avg_stats(&runtime_cycles_stats[cpu]);
-		if (total)
-			fprintf(output,
-				" #   %5.2f%% transactional cycles   ",
-				100.0 * (avg / total));
-	} else if (transaction_run &&
-		   perf_evsel__cmp(evsel, nth_evsel(T_CYCLES_IN_TX_CP))) {
-		total = avg_stats(&runtime_cycles_stats[cpu]);
-		total2 = avg_stats(&runtime_cycles_in_tx_stats[cpu]);
-		if (total2 < avg)
-			total2 = avg;
-		if (total)
-			fprintf(output,
-				" #   %5.2f%% aborted cycles         ",
-				100.0 * ((total2-avg) / total));
-	} else if (transaction_run &&
-		   perf_evsel__cmp(evsel, nth_evsel(T_TRANSACTION_START)) &&
-		   avg > 0 &&
-		   runtime_cycles_in_tx_stats[cpu].n != 0) {
-		total = avg_stats(&runtime_cycles_in_tx_stats[cpu]);
-
-		if (total)
-			ratio = total / avg;
-
-		fprintf(output, " # %8.0f cycles / transaction   ", ratio);
-	} else if (transaction_run &&
-		   perf_evsel__cmp(evsel, nth_evsel(T_ELISION_START)) &&
-		   avg > 0 &&
-		   runtime_cycles_in_tx_stats[cpu].n != 0) {
-		total = avg_stats(&runtime_cycles_in_tx_stats[cpu]);
-
-		if (total)
-			ratio = total / avg;
-
-		fprintf(output, " # %8.0f cycles / elision       ", ratio);
-	} else if (runtime_nsecs_stats[cpu].n != 0) {
-		char unit = 'M';
-
-		total = avg_stats(&runtime_nsecs_stats[cpu]);
-
-		if (total)
-			ratio = 1000.0 * avg / total;
-		if (ratio < 0.001) {
-			ratio *= 1000;
-			unit = 'K';
-		}
-
-		fprintf(output, " # %8.3f %c/sec                  ", ratio, unit);
-	} else {
-		fprintf(output, "                                   ");
-	}
+	perf_stat__print_shadow_stats(output, evsel, avg, cpu, aggr_mode);
 }
 
 static void print_aggr(char *prefix)
@@ -1536,17 +1107,6 @@ static int perf_stat_init_aggr_mode(void)
 	return 0;
 }
 
-static int setup_events(const char * const *attrs, unsigned len)
-{
-	unsigned i;
-
-	for (i = 0; i < len; i++) {
-		if (parse_events(evsel_list, attrs[i]))
-			return -1;
-	}
-	return 0;
-}
-
 /*
  * Add default attributes, if there were no attributes specified or
  * if -d/--detailed, -d -d or -d -d -d is used:
@@ -1668,12 +1228,10 @@ static int add_default_attributes(void)
 		int err;
 		if (pmu_have_event("cpu", "cycles-ct") &&
 		    pmu_have_event("cpu", "el-start"))
-			err = setup_events(transaction_attrs,
-					ARRAY_SIZE(transaction_attrs));
+			err = parse_events(evsel_list, transaction_attrs, NULL);
 		else
-			err = setup_events(transaction_limited_attrs,
-				 ARRAY_SIZE(transaction_limited_attrs));
-		if (err < 0) {
+			err = parse_events(evsel_list, transaction_limited_attrs, NULL);
+		if (err) {
 			fprintf(stderr, "Cannot set up transaction events\n");
 			return -1;
 		}
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index e50fe1187b0b..30e59620179d 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -61,13 +61,13 @@ struct timechart {
 				tasks_only,
 				with_backtrace,
 				topology;
+	bool			force;
 	/* IO related settings */
-	u64			io_events;
 	bool			io_only,
 				skip_eagain;
+	u64			io_events;
 	u64			min_time,
 				merge_dist;
-	bool			force;
 };
 
 struct per_pidcomm;
@@ -523,7 +523,7 @@ static const char *cat_backtrace(union perf_event *event,
 				 * Discard all.
 				 */
 				zfree(&p);
-				goto exit;
+				goto exit_put;
 			}
 			continue;
 		}
@@ -538,7 +538,8 @@ static const char *cat_backtrace(union perf_event *event,
 		else
 			fprintf(f, "..... %016" PRIx64 "\n", ip);
 	}
-
+exit_put:
+	addr_location__put(&al);
 exit:
 	fclose(f);
 
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 6a4d5d41c671..619a8696fda7 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -235,10 +235,13 @@ static void perf_top__show_details(struct perf_top *top)
 
 	more = symbol__annotate_printf(symbol, he->ms.map, top->sym_evsel,
 				       0, top->sym_pcnt_filter, top->print_entries, 4);
-	if (top->zero)
-		symbol__annotate_zero_histogram(symbol, top->sym_evsel->idx);
-	else
-		symbol__annotate_decay_histogram(symbol, top->sym_evsel->idx);
+
+	if (top->evlist->enabled) {
+		if (top->zero)
+			symbol__annotate_zero_histogram(symbol, top->sym_evsel->idx);
+		else
+			symbol__annotate_decay_histogram(symbol, top->sym_evsel->idx);
+	}
 	if (more != 0)
 		printf("%d lines not displayed, maybe increase display entries [e]\n", more);
 out_unlock:
@@ -276,11 +279,13 @@ static void perf_top__print_sym_table(struct perf_top *top)
 		return;
 	}
 
-	if (top->zero) {
-		hists__delete_entries(hists);
-	} else {
-		hists__decay_entries(hists, top->hide_user_symbols,
-				     top->hide_kernel_symbols);
+	if (top->evlist->enabled) {
+		if (top->zero) {
+			hists__delete_entries(hists);
+		} else {
+			hists__decay_entries(hists, top->hide_user_symbols,
+					     top->hide_kernel_symbols);
+		}
 	}
 
 	hists__collapse_resort(hists, NULL);
@@ -545,11 +550,13 @@ static void perf_top__sort_new_samples(void *arg)
 
 	hists = evsel__hists(t->sym_evsel);
 
-	if (t->zero) {
-		hists__delete_entries(hists);
-	} else {
-		hists__decay_entries(hists, t->hide_user_symbols,
-				     t->hide_kernel_symbols);
+	if (t->evlist->enabled) {
+		if (t->zero) {
+			hists__delete_entries(hists);
+		} else {
+			hists__decay_entries(hists, t->hide_user_symbols,
+					     t->hide_kernel_symbols);
+		}
 	}
 
 	hists__collapse_resort(hists, NULL);
@@ -579,8 +586,27 @@ static void *display_thread_tui(void *arg)
 		hists->uid_filter_str = top->record_opts.target.uid_str;
 	}
 
-	perf_evlist__tui_browse_hists(top->evlist, help, &hbt, top->min_percent,
-				      &top->session->header.env);
+	while (true)  {
+		int key = perf_evlist__tui_browse_hists(top->evlist, help, &hbt,
+							top->min_percent,
+							&top->session->header.env);
+
+		if (key != 'f')
+			break;
+
+		perf_evlist__toggle_enable(top->evlist);
+		/*
+		 * No need to refresh, resort/decay histogram entries
+		 * if we are not collecting samples:
+		 */
+		if (top->evlist->enabled) {
+			hbt.refresh = top->delay_secs;
+			help = "Press 'f' to disable the events or 'h' to see other hotkeys";
+		} else {
+			help = "Press 'f' again to re-enable the events";
+			hbt.refresh = 0;
+		}
+	}
 
 	done = 1;
 	return NULL;
@@ -775,7 +801,9 @@ static void perf_event__process_sample(struct perf_tool *tool,
 	if (al.sym == NULL || !al.sym->ignore) {
 		struct hists *hists = evsel__hists(evsel);
 		struct hist_entry_iter iter = {
-			.add_entry_cb = hist_iter__top_callback,
+			.evsel		= evsel,
+			.sample 	= sample,
+			.add_entry_cb 	= hist_iter__top_callback,
 		};
 
 		if (symbol_conf.cumulate_callchain)
@@ -785,15 +813,14 @@ static void perf_event__process_sample(struct perf_tool *tool,
 
 		pthread_mutex_lock(&hists->lock);
 
-		err = hist_entry_iter__add(&iter, &al, evsel, sample,
-					   top->max_stack, top);
+		err = hist_entry_iter__add(&iter, &al, top->max_stack, top);
 		if (err < 0)
 			pr_err("Problem incrementing symbol period, skipping event\n");
 
 		pthread_mutex_unlock(&hists->lock);
 	}
 
-	return;
+	addr_location__put(&al);
 }
 
 static void perf_top__mmap_read_idx(struct perf_top *top, int idx)
@@ -950,7 +977,7 @@ static int __cmd_top(struct perf_top *top)
 		goto out_delete;
 
 	machine__synthesize_threads(&top->session->machines.host, &opts->target,
-				    top->evlist->threads, false);
+				    top->evlist->threads, false, opts->proc_map_timeout);
 	ret = perf_top__start_counters(top);
 	if (ret)
 		goto out_delete;
@@ -1060,6 +1087,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 			.target		= {
 				.uses_mmap   = true,
 			},
+			.proc_map_timeout    = 500,
 		},
 		.max_stack	     = PERF_MAX_STACK_DEPTH,
 		.sym_pcnt_filter     = 5,
@@ -1159,6 +1187,8 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_STRING('w', "column-widths", &symbol_conf.col_width_list_str,
 		   "width[,width...]",
 		   "don't try to adjust column width, use these fixed values"),
+	OPT_UINTEGER(0, "proc-map-timeout", &opts->proc_map_timeout,
+			"per thread proc mmap processing timeout in ms"),
 	OPT_END()
 	};
 	const char * const top_usage[] = {
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index e122970361f2..de5d277d1ad7 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -16,7 +16,6 @@
 
 #include <libaudit.h>
 #include <stdlib.h>
-#include <sys/eventfd.h>
 #include <sys/mman.h>
 #include <linux/futex.h>
 
@@ -41,6 +40,51 @@
 # define EFD_SEMAPHORE		1
 #endif
 
+#ifndef EFD_NONBLOCK
+# define EFD_NONBLOCK		00004000
+#endif
+
+#ifndef EFD_CLOEXEC
+# define EFD_CLOEXEC		02000000
+#endif
+
+#ifndef O_CLOEXEC
+# define O_CLOEXEC		02000000
+#endif
+
+#ifndef SOCK_DCCP
+# define SOCK_DCCP		6
+#endif
+
+#ifndef SOCK_CLOEXEC
+# define SOCK_CLOEXEC		02000000
+#endif
+
+#ifndef SOCK_NONBLOCK
+# define SOCK_NONBLOCK		00004000
+#endif
+
+#ifndef MSG_CMSG_CLOEXEC
+# define MSG_CMSG_CLOEXEC	0x40000000
+#endif
+
+#ifndef PERF_FLAG_FD_NO_GROUP
+# define PERF_FLAG_FD_NO_GROUP		(1UL << 0)
+#endif
+
+#ifndef PERF_FLAG_FD_OUTPUT
+# define PERF_FLAG_FD_OUTPUT		(1UL << 1)
+#endif
+
+#ifndef PERF_FLAG_PID_CGROUP
+# define PERF_FLAG_PID_CGROUP		(1UL << 2) /* pid=cgroup id, per-cpu mode only */
+#endif
+
+#ifndef PERF_FLAG_FD_CLOEXEC
+# define PERF_FLAG_FD_CLOEXEC		(1UL << 3) /* O_CLOEXEC */
+#endif
+
+
 struct tp_field {
 	int offset;
 	union {
@@ -331,6 +375,14 @@ static size_t syscall_arg__scnprintf_hex(char *bf, size_t size,
 
 #define SCA_HEX syscall_arg__scnprintf_hex
 
+static size_t syscall_arg__scnprintf_int(char *bf, size_t size,
+					 struct syscall_arg *arg)
+{
+	return scnprintf(bf, size, "%d", arg->val);
+}
+
+#define SCA_INT syscall_arg__scnprintf_int
+
 static size_t syscall_arg__scnprintf_mmap_prot(char *bf, size_t size,
 					       struct syscall_arg *arg)
 {
@@ -783,6 +835,34 @@ static size_t syscall_arg__scnprintf_open_flags(char *bf, size_t size,
 
 #define SCA_OPEN_FLAGS syscall_arg__scnprintf_open_flags
 
+static size_t syscall_arg__scnprintf_perf_flags(char *bf, size_t size,
+						struct syscall_arg *arg)
+{
+	int printed = 0, flags = arg->val;
+
+	if (flags == 0)
+		return 0;
+
+#define	P_FLAG(n) \
+	if (flags & PERF_FLAG_##n) { \
+		printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
+		flags &= ~PERF_FLAG_##n; \
+	}
+
+	P_FLAG(FD_NO_GROUP);
+	P_FLAG(FD_OUTPUT);
+	P_FLAG(PID_CGROUP);
+	P_FLAG(FD_CLOEXEC);
+#undef P_FLAG
+
+	if (flags)
+		printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
+
+	return printed;
+}
+
+#define SCA_PERF_FLAGS syscall_arg__scnprintf_perf_flags
+
 static size_t syscall_arg__scnprintf_eventfd_flags(char *bf, size_t size,
 						   struct syscall_arg *arg)
 {
@@ -1050,6 +1130,11 @@ static struct syscall_fmt {
 	{ .name	    = "openat",	    .errmsg = true,
 	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */
 			     [2] = SCA_OPEN_FLAGS, /* flags */ }, },
+	{ .name	    = "perf_event_open", .errmsg = true,
+	  .arg_scnprintf = { [1] = SCA_INT, /* pid */
+			     [2] = SCA_INT, /* cpu */
+			     [3] = SCA_FD,  /* group_fd */
+			     [4] = SCA_PERF_FLAGS,  /* flags */ }, },
 	{ .name	    = "pipe2",	    .errmsg = true,
 	  .arg_scnprintf = { [1] = SCA_PIPE_FLAGS, /* flags */ }, },
 	{ .name	    = "poll",	    .errmsg = true, .timeout = true, },
@@ -1433,7 +1518,8 @@ static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist)
 		return -ENOMEM;
 
 	err = __machine__synthesize_threads(trace->host, &trace->tool, &trace->opts.target,
-					    evlist->threads, trace__tool_process, false);
+					    evlist->threads, trace__tool_process, false,
+					    trace->opts.proc_map_timeout);
 	if (err)
 		symbol__exit();
 
@@ -1712,7 +1798,7 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
 	void *args;
 	size_t printed = 0;
 	struct thread *thread;
-	int id = perf_evsel__sc_tp_uint(evsel, id, sample);
+	int id = perf_evsel__sc_tp_uint(evsel, id, sample), err = -1;
 	struct syscall *sc = trace__syscall_info(trace, evsel, id);
 	struct thread_trace *ttrace;
 
@@ -1725,14 +1811,14 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
 	thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
 	ttrace = thread__trace(thread, trace->output);
 	if (ttrace == NULL)
-		return -1;
+		goto out_put;
 
 	args = perf_evsel__sc_tp_ptr(evsel, args, sample);
 
 	if (ttrace->entry_str == NULL) {
 		ttrace->entry_str = malloc(1024);
 		if (!ttrace->entry_str)
-			return -1;
+			goto out_put;
 	}
 
 	if (!trace->summary_only)
@@ -1757,8 +1843,10 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
 		thread__put(trace->current);
 		trace->current = thread__get(thread);
 	}
-
-	return 0;
+	err = 0;
+out_put:
+	thread__put(thread);
+	return err;
 }
 
 static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
@@ -1768,7 +1856,7 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
 	long ret;
 	u64 duration = 0;
 	struct thread *thread;
-	int id = perf_evsel__sc_tp_uint(evsel, id, sample);
+	int id = perf_evsel__sc_tp_uint(evsel, id, sample), err = -1;
 	struct syscall *sc = trace__syscall_info(trace, evsel, id);
 	struct thread_trace *ttrace;
 
@@ -1781,7 +1869,7 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
 	thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
 	ttrace = thread__trace(thread, trace->output);
 	if (ttrace == NULL)
-		return -1;
+		goto out_put;
 
 	if (trace->summary)
 		thread__update_stats(ttrace, id, sample);
@@ -1835,8 +1923,10 @@ signed_print:
 	fputc('\n', trace->output);
 out:
 	ttrace->entry_pending = false;
-
-	return 0;
+	err = 0;
+out_put:
+	thread__put(thread);
+	return err;
 }
 
 static int trace__vfs_getname(struct trace *trace, struct perf_evsel *evsel,
@@ -1863,6 +1953,7 @@ static int trace__sched_stat_runtime(struct trace *trace, struct perf_evsel *evs
 
 	ttrace->runtime_ms += runtime_ms;
 	trace->runtime_ms += runtime_ms;
+	thread__put(thread);
 	return 0;
 
 out_dump:
@@ -1872,6 +1963,7 @@ out_dump:
 	       (pid_t)perf_evsel__intval(evsel, sample, "pid"),
 	       runtime,
 	       perf_evsel__intval(evsel, sample, "vruntime"));
+	thread__put(thread);
 	return 0;
 }
 
@@ -1924,11 +2016,12 @@ static int trace__pgfault(struct trace *trace,
 	struct addr_location al;
 	char map_type = 'd';
 	struct thread_trace *ttrace;
+	int err = -1;
 
 	thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
 	ttrace = thread__trace(thread, trace->output);
 	if (ttrace == NULL)
-		return -1;
+		goto out_put;
 
 	if (evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS_MAJ)
 		ttrace->pfmaj++;
@@ -1936,7 +2029,7 @@ static int trace__pgfault(struct trace *trace,
 		ttrace->pfmin++;
 
 	if (trace->summary_only)
-		return 0;
+		goto out;
 
 	thread__find_addr_location(thread, cpumode, MAP__FUNCTION,
 			      sample->ip, &al);
@@ -1967,8 +2060,11 @@ static int trace__pgfault(struct trace *trace,
 	print_location(trace->output, sample, &al, true, false);
 
 	fprintf(trace->output, " (%c%c)\n", map_type, al.level);
-
-	return 0;
+out:
+	err = 0;
+out_put:
+	thread__put(thread);
+	return err;
 }
 
 static bool skip_sample(struct trace *trace, struct perf_sample *sample)
@@ -2652,6 +2748,7 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 			.user_interval = ULLONG_MAX,
 			.no_buffering  = true,
 			.mmap_pages    = UINT_MAX,
+			.proc_map_timeout  = 500,
 		},
 		.output = stdout,
 		.show_comm = true,
@@ -2666,16 +2763,15 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_BOOLEAN(0, "comm", &trace.show_comm,
 		    "show the thread COMM next to its id"),
 	OPT_BOOLEAN(0, "tool_stats", &trace.show_tool_stats, "show tool stats"),
-	OPT_STRING('e', "expr", &ev_qualifier_str, "expr",
-		    "list of events to trace"),
+	OPT_STRING('e', "expr", &ev_qualifier_str, "expr", "list of syscalls to trace"),
 	OPT_STRING('o', "output", &output_name, "file", "output file name"),
 	OPT_STRING('i', "input", &input_name, "file", "Analyze events in file"),
 	OPT_STRING('p', "pid", &trace.opts.target.pid, "pid",
 		    "trace events on existing process id"),
 	OPT_STRING('t', "tid", &trace.opts.target.tid, "tid",
 		    "trace events on existing thread id"),
-	OPT_CALLBACK(0, "filter-pids", &trace, "float",
-		     "show only events with duration > N.M ms", trace__set_filter_pids),
+	OPT_CALLBACK(0, "filter-pids", &trace, "CSV list of pids",
+		     "pids to filter (by the kernel)", trace__set_filter_pids),
 	OPT_BOOLEAN('a', "all-cpus", &trace.opts.target.system_wide,
 		    "system-wide collection from all CPUs"),
 	OPT_STRING('C', "cpu", &trace.opts.target.cpu_list, "cpu",
@@ -2702,6 +2798,8 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 		     "Trace pagefaults", parse_pagefaults, "maj"),
 	OPT_BOOLEAN(0, "syscalls", &trace.trace_syscalls, "Trace syscalls"),
 	OPT_BOOLEAN('f', "force", &trace.force, "don't complain, do it"),
+	OPT_UINTEGER(0, "proc-map-timeout", &trace.opts.proc_map_timeout,
+			"per thread proc mmap processing timeout in ms"),
 	OPT_END()
 	};
 	const char * const trace_subcommands[] = { "record", NULL };
@@ -2712,11 +2810,10 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 	signal(SIGFPE, sighandler_dump_stack);
 
 	trace.evlist = perf_evlist__new();
-	if (trace.evlist == NULL)
-		return -ENOMEM;
 
 	if (trace.evlist == NULL) {
 		pr_err("Not enough memory to run!\n");
+		err = -ENOMEM;
 		goto out;
 	}
 
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 59a98c643240..317001c94660 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -32,7 +32,7 @@ ifeq ($(ARCH),x86)
     LIBUNWIND_LIBS = -lunwind -lunwind-x86_64
     $(call detected,CONFIG_X86_64)
   else
-    LIBUNWIND_LIBS = -lunwind -lunwind-x86
+    LIBUNWIND_LIBS = -lunwind-x86 -llzma -lunwind
   endif
   NO_PERF_REGS := 0
 endif
@@ -130,6 +130,8 @@ endif
 
 ifeq ($(DEBUG),0)
   CFLAGS += -O6
+else
+  CFLAGS += $(call cc-option,-Og,-O0)
 endif
 
 ifdef PARSER_DEBUG
@@ -268,6 +270,10 @@ else
   endif # libelf support
 endif # NO_LIBELF
 
+ifdef NO_DWARF
+  NO_LIBDW_DWARF_UNWIND := 1
+endif
+
 ifndef NO_LIBELF
   CFLAGS += -DHAVE_LIBELF_SUPPORT
   EXTLIBS += -lelf
@@ -610,6 +616,11 @@ ifdef LIBBABELTRACE
   endif
 endif
 
+ifndef NO_AUXTRACE
+  $(call detected,CONFIG_AUXTRACE)
+  CFLAGS += -DHAVE_AUXTRACE_SUPPORT
+endif
+
 # Among the variables below, these:
 #   perfexecdir
 #   template_dir
diff --git a/tools/perf/config/utilities.mak b/tools/perf/config/utilities.mak
index c16ce833079c..0ebef09c0842 100644
--- a/tools/perf/config/utilities.mak
+++ b/tools/perf/config/utilities.mak
@@ -177,3 +177,22 @@ $(if $($(1)),$(call _ge_attempt,$($(1)),$(1)),$(call _ge_attempt,$(2)))
 endef
 _ge_attempt = $(if $(get-executable),$(get-executable),$(call _gea_err,$(2)))
 _gea_err  = $(if $(1),$(error Please set '$(1)' appropriately))
+
+# try-run
+# Usage: option = $(call try-run, $(CC)...-o "$$TMP",option-ok,otherwise)
+# Exit code chooses option. "$$TMP" is can be used as temporary file and
+# is automatically cleaned up.
+try-run = $(shell set -e;		\
+	TMP="$(TMPOUT).$$$$.tmp";	\
+	TMPO="$(TMPOUT).$$$$.o";	\
+	if ($(1)) >/dev/null 2>&1;	\
+	then echo "$(2)";		\
+	else echo "$(3)";		\
+	fi;				\
+	rm -f "$$TMP" "$$TMPO")
+
+# cc-option
+# Usage: cflags-y += $(call cc-option,-march=winchip-c6,-march=i586)
+
+cc-option = $(call try-run,\
+	$(CC) $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS) $(1) -c -x c /dev/null -o "$$TMP",$(1),$(2))
diff --git a/tools/perf/perf-sys.h b/tools/perf/perf-sys.h
index 6ef68165c9db..83a25cef82fd 100644
--- a/tools/perf/perf-sys.h
+++ b/tools/perf/perf-sys.h
@@ -6,11 +6,9 @@
 #include <sys/syscall.h>
 #include <linux/types.h>
 #include <linux/perf_event.h>
+#include <asm/barrier.h>
 
 #if defined(__i386__)
-#define mb()		asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
-#define wmb()		asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
-#define rmb()		asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
 #define cpu_relax()	asm volatile("rep; nop" ::: "memory");
 #define CPUINFO_PROC	{"model name"}
 #ifndef __NR_perf_event_open
@@ -25,9 +23,6 @@
 #endif
 
 #if defined(__x86_64__)
-#define mb()		asm volatile("mfence" ::: "memory")
-#define wmb()		asm volatile("sfence" ::: "memory")
-#define rmb()		asm volatile("lfence" ::: "memory")
 #define cpu_relax()	asm volatile("rep; nop" ::: "memory");
 #define CPUINFO_PROC	{"model name"}
 #ifndef __NR_perf_event_open
@@ -43,129 +38,63 @@
 
 #ifdef __powerpc__
 #include "../../arch/powerpc/include/uapi/asm/unistd.h"
-#define mb()		asm volatile ("sync" ::: "memory")
-#define wmb()		asm volatile ("sync" ::: "memory")
-#define rmb()		asm volatile ("sync" ::: "memory")
 #define CPUINFO_PROC	{"cpu"}
 #endif
 
 #ifdef __s390__
-#define mb()		asm volatile("bcr 15,0" ::: "memory")
-#define wmb()		asm volatile("bcr 15,0" ::: "memory")
-#define rmb()		asm volatile("bcr 15,0" ::: "memory")
 #define CPUINFO_PROC	{"vendor_id"}
 #endif
 
 #ifdef __sh__
-#if defined(__SH4A__) || defined(__SH5__)
-# define mb()		asm volatile("synco" ::: "memory")
-# define wmb()		asm volatile("synco" ::: "memory")
-# define rmb()		asm volatile("synco" ::: "memory")
-#else
-# define mb()		asm volatile("" ::: "memory")
-# define wmb()		asm volatile("" ::: "memory")
-# define rmb()		asm volatile("" ::: "memory")
-#endif
 #define CPUINFO_PROC	{"cpu type"}
 #endif
 
 #ifdef __hppa__
-#define mb()		asm volatile("" ::: "memory")
-#define wmb()		asm volatile("" ::: "memory")
-#define rmb()		asm volatile("" ::: "memory")
 #define CPUINFO_PROC	{"cpu"}
 #endif
 
 #ifdef __sparc__
-#ifdef __LP64__
-#define mb()		asm volatile("ba,pt %%xcc, 1f\n"	\
-				     "membar #StoreLoad\n"	\
-				     "1:\n":::"memory")
-#else
-#define mb()		asm volatile("":::"memory")
-#endif
-#define wmb()		asm volatile("":::"memory")
-#define rmb()		asm volatile("":::"memory")
 #define CPUINFO_PROC	{"cpu"}
 #endif
 
 #ifdef __alpha__
-#define mb()		asm volatile("mb" ::: "memory")
-#define wmb()		asm volatile("wmb" ::: "memory")
-#define rmb()		asm volatile("mb" ::: "memory")
 #define CPUINFO_PROC	{"cpu model"}
 #endif
 
 #ifdef __ia64__
-#define mb()		asm volatile ("mf" ::: "memory")
-#define wmb()		asm volatile ("mf" ::: "memory")
-#define rmb()		asm volatile ("mf" ::: "memory")
 #define cpu_relax()	asm volatile ("hint @pause" ::: "memory")
 #define CPUINFO_PROC	{"model name"}
 #endif
 
 #ifdef __arm__
-/*
- * Use the __kuser_memory_barrier helper in the CPU helper page. See
- * arch/arm/kernel/entry-armv.S in the kernel source for details.
- */
-#define mb()		((void(*)(void))0xffff0fa0)()
-#define wmb()		((void(*)(void))0xffff0fa0)()
-#define rmb()		((void(*)(void))0xffff0fa0)()
 #define CPUINFO_PROC	{"model name", "Processor"}
 #endif
 
 #ifdef __aarch64__
-#define mb()		asm volatile("dmb ish" ::: "memory")
-#define wmb()		asm volatile("dmb ishst" ::: "memory")
-#define rmb()		asm volatile("dmb ishld" ::: "memory")
 #define cpu_relax()	asm volatile("yield" ::: "memory")
 #endif
 
 #ifdef __mips__
-#define mb()		asm volatile(					\
-				".set	mips2\n\t"			\
-				"sync\n\t"				\
-				".set	mips0"				\
-				: /* no output */			\
-				: /* no input */			\
-				: "memory")
-#define wmb()	mb()
-#define rmb()	mb()
 #define CPUINFO_PROC	{"cpu model"}
 #endif
 
 #ifdef __arc__
-#define mb()		asm volatile("" ::: "memory")
-#define wmb()		asm volatile("" ::: "memory")
-#define rmb()		asm volatile("" ::: "memory")
 #define CPUINFO_PROC	{"Processor"}
 #endif
 
 #ifdef __metag__
-#define mb()		asm volatile("" ::: "memory")
-#define wmb()		asm volatile("" ::: "memory")
-#define rmb()		asm volatile("" ::: "memory")
 #define CPUINFO_PROC	{"CPU"}
 #endif
 
 #ifdef __xtensa__
-#define mb()		asm volatile("memw" ::: "memory")
-#define wmb()		asm volatile("memw" ::: "memory")
-#define rmb()		asm volatile("" ::: "memory")
 #define CPUINFO_PROC	{"core ID"}
 #endif
 
 #ifdef __tile__
-#define mb()		asm volatile ("mf" ::: "memory")
-#define wmb()		asm volatile ("mf" ::: "memory")
-#define rmb()		asm volatile ("mf" ::: "memory")
 #define cpu_relax()	asm volatile ("mfspr zero, PASS" ::: "memory")
 #define CPUINFO_PROC    {"model name"}
 #endif
 
-#define barrier() asm volatile ("" ::: "memory")
-
 #ifndef cpu_relax
 #define cpu_relax() barrier()
 #endif
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index e14bb637255c..4a5827fff799 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -54,16 +54,22 @@ struct record_opts {
 	bool	     period;
 	bool	     sample_intr_regs;
 	bool	     running_time;
+	bool	     full_auxtrace;
+	bool	     auxtrace_snapshot_mode;
 	unsigned int freq;
 	unsigned int mmap_pages;
+	unsigned int auxtrace_mmap_pages;
 	unsigned int user_freq;
 	u64          branch_stack;
 	u64	     default_interval;
 	u64	     user_interval;
+	size_t	     auxtrace_snapshot_size;
+	const char   *auxtrace_snapshot_opts;
 	bool	     sample_transaction;
 	unsigned     initial_delay;
 	bool         use_clockid;
 	clockid_t    clockid;
+	unsigned int proc_map_timeout;
 };
 
 struct option;
diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index 6a8801b32017..ee41e705b2eb 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -3,9 +3,9 @@ perf-y += parse-events.o
 perf-y += dso-data.o
 perf-y += attr.o
 perf-y += vmlinux-kallsyms.o
-perf-y += open-syscall.o
-perf-y += open-syscall-all-cpus.o
-perf-y += open-syscall-tp-fields.o
+perf-y += openat-syscall.o
+perf-y += openat-syscall-all-cpus.o
+perf-y += openat-syscall-tp-fields.o
 perf-y += mmap-basic.o
 perf-y += perf-record.o
 perf-y += rdpmc.o
@@ -34,7 +34,7 @@ perf-y += kmod-path.o
 
 perf-$(CONFIG_X86) += perf-time-to-tsc.o
 
-ifeq ($(ARCH),$(filter $(ARCH),x86 arm))
+ifeq ($(ARCH),$(filter $(ARCH),x86 arm arm64))
 perf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o
 endif
 
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 4f4098167112..87b9961646e4 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -23,12 +23,12 @@ static struct test {
 		.func = test__vmlinux_matches_kallsyms,
 	},
 	{
-		.desc = "detect open syscall event",
-		.func = test__open_syscall_event,
+		.desc = "detect openat syscall event",
+		.func = test__openat_syscall_event,
 	},
 	{
-		.desc = "detect open syscall event on all cpus",
-		.func = test__open_syscall_event_on_all_cpus,
+		.desc = "detect openat syscall event on all cpus",
+		.func = test__openat_syscall_event_on_all_cpus,
 	},
 	{
 		.desc = "read samples using the mmap interface",
@@ -73,8 +73,8 @@ static struct test {
 		.func = test__perf_evsel__tp_sched_test,
 	},
 	{
-		.desc = "Generate and check syscalls:sys_enter_open event fields",
-		.func = test__syscall_open_tp_fields,
+		.desc = "Generate and check syscalls:sys_enter_openat event fields",
+		.func = test__syscall_openat_tp_fields,
 	},
 	{
 		.desc = "struct perf_event_attr setup",
@@ -126,7 +126,7 @@ static struct test {
 		.desc = "Test parsing with no sample_id_all bit set",
 		.func = test__parse_no_sample_id_all,
 	},
-#if defined(__x86_64__) || defined(__i386__) || defined(__arm__)
+#if defined(__x86_64__) || defined(__i386__) || defined(__arm__) || defined(__aarch64__)
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
 	{
 		.desc = "Test dwarf unwind",
@@ -219,7 +219,7 @@ static int run_test(struct test *test)
 	wait(&status);
 
 	if (WIFEXITED(status)) {
-		err = WEXITSTATUS(status);
+		err = (signed char)WEXITSTATUS(status);
 		pr_debug("test child finished with %d\n", err);
 	} else if (WIFSIGNALED(status)) {
 		err = -1;
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index f671ec37a7c4..22f8a00446e1 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -248,6 +248,7 @@ static int process_sample_event(struct machine *machine,
 	struct perf_sample sample;
 	struct thread *thread;
 	u8 cpumode;
+	int ret;
 
 	if (perf_evlist__parse_sample(evlist, event, &sample)) {
 		pr_debug("perf_evlist__parse_sample failed\n");
@@ -262,7 +263,9 @@ static int process_sample_event(struct machine *machine,
 
 	cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 
-	return read_object_code(sample.ip, READLEN, cpumode, thread, state);
+	ret = read_object_code(sample.ip, READLEN, cpumode, thread, state);
+	thread__put(thread);
+	return ret;
 }
 
 static int process_event(struct machine *machine, struct perf_evlist *evlist,
@@ -448,7 +451,7 @@ static int do_test_code_reading(bool try_kcore)
 	}
 
 	ret = perf_event__synthesize_thread_map(NULL, threads,
-						perf_event__process, machine, false);
+						perf_event__process, machine, false, 500);
 	if (ret < 0) {
 		pr_debug("perf_event__synthesize_thread_map failed\n");
 		goto out_err;
@@ -457,13 +460,13 @@ static int do_test_code_reading(bool try_kcore)
 	thread = machine__findnew_thread(machine, pid, pid);
 	if (!thread) {
 		pr_debug("machine__findnew_thread failed\n");
-		goto out_err;
+		goto out_put;
 	}
 
 	cpus = cpu_map__new(NULL);
 	if (!cpus) {
 		pr_debug("cpu_map__new failed\n");
-		goto out_err;
+		goto out_put;
 	}
 
 	while (1) {
@@ -472,7 +475,7 @@ static int do_test_code_reading(bool try_kcore)
 		evlist = perf_evlist__new();
 		if (!evlist) {
 			pr_debug("perf_evlist__new failed\n");
-			goto out_err;
+			goto out_put;
 		}
 
 		perf_evlist__set_maps(evlist, cpus, threads);
@@ -482,10 +485,10 @@ static int do_test_code_reading(bool try_kcore)
 		else
 			str = "cycles";
 		pr_debug("Parsing event '%s'\n", str);
-		ret = parse_events(evlist, str);
+		ret = parse_events(evlist, str, NULL);
 		if (ret < 0) {
 			pr_debug("parse_events failed\n");
-			goto out_err;
+			goto out_put;
 		}
 
 		perf_evlist__config(evlist, &opts);
@@ -506,7 +509,7 @@ static int do_test_code_reading(bool try_kcore)
 				continue;
 			}
 			pr_debug("perf_evlist__open failed\n");
-			goto out_err;
+			goto out_put;
 		}
 		break;
 	}
@@ -514,7 +517,7 @@ static int do_test_code_reading(bool try_kcore)
 	ret = perf_evlist__mmap(evlist, UINT_MAX, false);
 	if (ret < 0) {
 		pr_debug("perf_evlist__mmap failed\n");
-		goto out_err;
+		goto out_put;
 	}
 
 	perf_evlist__enable(evlist);
@@ -525,7 +528,7 @@ static int do_test_code_reading(bool try_kcore)
 
 	ret = process_events(machine, evlist, &state);
 	if (ret < 0)
-		goto out_err;
+		goto out_put;
 
 	if (!have_vmlinux && !have_kcore && !try_kcore)
 		err = TEST_CODE_READING_NO_KERNEL_OBJ;
@@ -535,7 +538,10 @@ static int do_test_code_reading(bool try_kcore)
 		err = TEST_CODE_READING_NO_ACCESS;
 	else
 		err = TEST_CODE_READING_OK;
+out_put:
+	thread__put(thread);
 out_err:
+
 	if (evlist) {
 		perf_evlist__delete(evlist);
 	} else {
diff --git a/tools/perf/tests/dso-data.c b/tools/perf/tests/dso-data.c
index 513e5febbe5a..a218aeaf56a0 100644
--- a/tools/perf/tests/dso-data.c
+++ b/tools/perf/tests/dso-data.c
@@ -99,6 +99,17 @@ struct test_data_offset offsets[] = {
 	},
 };
 
+/* move it from util/dso.c for compatibility */
+static int dso__data_fd(struct dso *dso, struct machine *machine)
+{
+	int fd = dso__data_get_fd(dso, machine);
+
+	if (fd >= 0)
+		dso__data_put_fd(dso);
+
+	return fd;
+}
+
 int test__dso_data(void)
 {
 	struct machine machine;
@@ -155,7 +166,7 @@ int test__dso_data(void)
 		free(buf);
 	}
 
-	dso__delete(dso);
+	dso__put(dso);
 	unlink(file);
 	return 0;
 }
@@ -215,7 +226,7 @@ static void dsos__delete(int cnt)
 		struct dso *dso = dsos[i];
 
 		unlink(dso->name);
-		dso__delete(dso);
+		dso__put(dso);
 	}
 
 	free(dsos);
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
index 0bf06bec68c7..40b36c462427 100644
--- a/tools/perf/tests/dwarf-unwind.c
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -28,7 +28,7 @@ static int init_live_machine(struct machine *machine)
 	pid_t pid = getpid();
 
 	return perf_event__synthesize_mmap_events(NULL, &event, pid, pid,
-						  mmap_handler, machine, true);
+						  mmap_handler, machine, true, 500);
 }
 
 #define MAX_STACK 8
@@ -170,6 +170,7 @@ int test__dwarf_unwind(void)
 	}
 
 	err = krava_1(thread);
+	thread__put(thread);
 
  out:
 	machine__delete_threads(machine);
diff --git a/tools/perf/tests/evsel-roundtrip-name.c b/tools/perf/tests/evsel-roundtrip-name.c
index b8d8341b383e..3fa715987a5e 100644
--- a/tools/perf/tests/evsel-roundtrip-name.c
+++ b/tools/perf/tests/evsel-roundtrip-name.c
@@ -23,7 +23,7 @@ static int perf_evsel__roundtrip_cache_name_test(void)
 			for (i = 0; i < PERF_COUNT_HW_CACHE_RESULT_MAX; i++) {
 				__perf_evsel__hw_cache_type_op_res_name(type, op, i,
 									name, sizeof(name));
-				err = parse_events(evlist, name);
+				err = parse_events(evlist, name, NULL);
 				if (err)
 					ret = err;
 			}
@@ -71,7 +71,7 @@ static int __perf_evsel__name_array_test(const char *names[], int nr_names)
                 return -ENOMEM;
 
 	for (i = 0; i < nr_names; ++i) {
-		err = parse_events(evlist, names[i]);
+		err = parse_events(evlist, names[i], NULL);
 		if (err) {
 			pr_debug("failed to parse event '%s', err %d\n",
 				 names[i], err);
diff --git a/tools/perf/tests/hists_common.c b/tools/perf/tests/hists_common.c
index a62c09134516..ce80b274b097 100644
--- a/tools/perf/tests/hists_common.c
+++ b/tools/perf/tests/hists_common.c
@@ -96,6 +96,7 @@ struct machine *setup_fake_machine(struct machines *machines)
 			goto out;
 
 		thread__set_comm(thread, fake_threads[i].comm, 0);
+		thread__put(thread);
 	}
 
 	for (i = 0; i < ARRAY_SIZE(fake_mmap_info); i++) {
@@ -120,8 +121,7 @@ struct machine *setup_fake_machine(struct machines *machines)
 		size_t k;
 		struct dso *dso;
 
-		dso = __dsos__findnew(&machine->user_dsos,
-				      fake_symbols[i].dso_name);
+		dso = machine__findnew_dso(machine, fake_symbols[i].dso_name);
 		if (dso == NULL)
 			goto out;
 
@@ -134,11 +134,15 @@ struct machine *setup_fake_machine(struct machines *machines)
 
 			sym = symbol__new(fsym->start, fsym->length,
 					  STB_GLOBAL, fsym->name);
-			if (sym == NULL)
+			if (sym == NULL) {
+				dso__put(dso);
 				goto out;
+			}
 
 			symbols__insert(&dso->symbols[MAP__FUNCTION], sym);
 		}
+
+		dso__put(dso);
 	}
 
 	return machine;
diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c
index 18619966454c..7d82c8be5e36 100644
--- a/tools/perf/tests/hists_cumulate.c
+++ b/tools/perf/tests/hists_cumulate.c
@@ -87,6 +87,8 @@ static int add_hist_entries(struct hists *hists, struct machine *machine)
 			},
 		};
 		struct hist_entry_iter iter = {
+			.evsel = evsel,
+			.sample	= &sample,
 			.hide_unresolved = false,
 		};
 
@@ -104,9 +106,11 @@ static int add_hist_entries(struct hists *hists, struct machine *machine)
 						  &sample) < 0)
 			goto out;
 
-		if (hist_entry_iter__add(&iter, &al, evsel, &sample,
-					 PERF_MAX_STACK_DEPTH, NULL) < 0)
+		if (hist_entry_iter__add(&iter, &al, PERF_MAX_STACK_DEPTH,
+					 NULL) < 0) {
+			addr_location__put(&al);
 			goto out;
+		}
 
 		fake_samples[i].thread = al.thread;
 		fake_samples[i].map = al.map;
@@ -695,7 +699,7 @@ int test__hists_cumulate(void)
 
 	TEST_ASSERT_VAL("No memory", evlist);
 
-	err = parse_events(evlist, "cpu-clock");
+	err = parse_events(evlist, "cpu-clock", NULL);
 	if (err)
 		goto out;
 
diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c
index 59e53db7914c..ce48775e6ada 100644
--- a/tools/perf/tests/hists_filter.c
+++ b/tools/perf/tests/hists_filter.c
@@ -63,6 +63,8 @@ static int add_hist_entries(struct perf_evlist *evlist,
 				},
 			};
 			struct hist_entry_iter iter = {
+				.evsel = evsel,
+				.sample = &sample,
 				.ops = &hist_iter_normal,
 				.hide_unresolved = false,
 			};
@@ -81,9 +83,11 @@ static int add_hist_entries(struct perf_evlist *evlist,
 							  &sample) < 0)
 				goto out;
 
-			if (hist_entry_iter__add(&iter, &al, evsel, &sample,
-						 PERF_MAX_STACK_DEPTH, NULL) < 0)
+			if (hist_entry_iter__add(&iter, &al,
+						 PERF_MAX_STACK_DEPTH, NULL) < 0) {
+				addr_location__put(&al);
 				goto out;
+			}
 
 			fake_samples[i].thread = al.thread;
 			fake_samples[i].map = al.map;
@@ -108,10 +112,10 @@ int test__hists_filter(void)
 
 	TEST_ASSERT_VAL("No memory", evlist);
 
-	err = parse_events(evlist, "cpu-clock");
+	err = parse_events(evlist, "cpu-clock", NULL);
 	if (err)
 		goto out;
-	err = parse_events(evlist, "task-clock");
+	err = parse_events(evlist, "task-clock", NULL);
 	if (err)
 		goto out;
 
diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c
index 278ba8344c23..8c102b011424 100644
--- a/tools/perf/tests/hists_link.c
+++ b/tools/perf/tests/hists_link.c
@@ -91,8 +91,10 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 
 			he = __hists__add_entry(hists, &al, NULL,
 						NULL, NULL, 1, 1, 0, true);
-			if (he == NULL)
+			if (he == NULL) {
+				addr_location__put(&al);
 				goto out;
+			}
 
 			fake_common_samples[k].thread = al.thread;
 			fake_common_samples[k].map = al.map;
@@ -115,8 +117,10 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 
 			he = __hists__add_entry(hists, &al, NULL,
 						NULL, NULL, 1, 1, 0, true);
-			if (he == NULL)
+			if (he == NULL) {
+				addr_location__put(&al);
 				goto out;
+			}
 
 			fake_samples[i][k].thread = al.thread;
 			fake_samples[i][k].map = al.map;
@@ -282,10 +286,10 @@ int test__hists_link(void)
 	if (evlist == NULL)
                 return -ENOMEM;
 
-	err = parse_events(evlist, "cpu-clock");
+	err = parse_events(evlist, "cpu-clock", NULL);
 	if (err)
 		goto out;
-	err = parse_events(evlist, "task-clock");
+	err = parse_events(evlist, "task-clock", NULL);
 	if (err)
 		goto out;
 
diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c
index b52c9faea224..adbebc852cc8 100644
--- a/tools/perf/tests/hists_output.c
+++ b/tools/perf/tests/hists_output.c
@@ -57,6 +57,8 @@ static int add_hist_entries(struct hists *hists, struct machine *machine)
 			},
 		};
 		struct hist_entry_iter iter = {
+			.evsel = evsel,
+			.sample = &sample,
 			.ops = &hist_iter_normal,
 			.hide_unresolved = false,
 		};
@@ -70,9 +72,11 @@ static int add_hist_entries(struct hists *hists, struct machine *machine)
 						  &sample) < 0)
 			goto out;
 
-		if (hist_entry_iter__add(&iter, &al, evsel, &sample,
-					 PERF_MAX_STACK_DEPTH, NULL) < 0)
+		if (hist_entry_iter__add(&iter, &al, PERF_MAX_STACK_DEPTH,
+					 NULL) < 0) {
+			addr_location__put(&al);
 			goto out;
+		}
 
 		fake_samples[i].thread = al.thread;
 		fake_samples[i].map = al.map;
@@ -590,7 +594,7 @@ int test__hists_output(void)
 
 	TEST_ASSERT_VAL("No memory", evlist);
 
-	err = parse_events(evlist, "cpu-clock");
+	err = parse_events(evlist, "cpu-clock", NULL);
 	if (err)
 		goto out;
 
diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c
index 7a5ab7b0b8f6..5b171d1e338b 100644
--- a/tools/perf/tests/keep-tracking.c
+++ b/tools/perf/tests/keep-tracking.c
@@ -78,8 +78,8 @@ int test__keep_tracking(void)
 
 	perf_evlist__set_maps(evlist, cpus, threads);
 
-	CHECK__(parse_events(evlist, "dummy:u"));
-	CHECK__(parse_events(evlist, "cycles:u"));
+	CHECK__(parse_events(evlist, "dummy:u", NULL));
+	CHECK__(parse_events(evlist, "cycles:u", NULL));
 
 	perf_evlist__config(evlist, &opts);
 
diff --git a/tools/perf/tests/kmod-path.c b/tools/perf/tests/kmod-path.c
index e8d7cbb9320c..08c433b4bf4f 100644
--- a/tools/perf/tests/kmod-path.c
+++ b/tools/perf/tests/kmod-path.c
@@ -34,9 +34,21 @@ static int test(const char *path, bool alloc_name, bool alloc_ext,
 	return 0;
 }
 
+static int test_is_kernel_module(const char *path, int cpumode, bool expect)
+{
+	TEST_ASSERT_VAL("is_kernel_module",
+			(!!is_kernel_module(path, cpumode)) == (!!expect));
+	pr_debug("%s (cpumode: %d) - is_kernel_module: %s\n",
+			path, cpumode, expect ? "true" : "false");
+	return 0;
+}
+
 #define T(path, an, ae, k, c, n, e) \
 	TEST_ASSERT_VAL("failed", !test(path, an, ae, k, c, n, e))
 
+#define M(path, c, e) \
+	TEST_ASSERT_VAL("failed", !test_is_kernel_module(path, c, e))
+
 int test__kmod_path__parse(void)
 {
 	/* path                alloc_name  alloc_ext   kmod  comp   name     ext */
@@ -44,30 +56,90 @@ int test__kmod_path__parse(void)
 	T("/xxxx/xxxx/x-x.ko", false     , true      , true, false, NULL   , NULL);
 	T("/xxxx/xxxx/x-x.ko", true      , false     , true, false, "[x_x]", NULL);
 	T("/xxxx/xxxx/x-x.ko", false     , false     , true, false, NULL   , NULL);
+	M("/xxxx/xxxx/x-x.ko", PERF_RECORD_MISC_CPUMODE_UNKNOWN, true);
+	M("/xxxx/xxxx/x-x.ko", PERF_RECORD_MISC_KERNEL, true);
+	M("/xxxx/xxxx/x-x.ko", PERF_RECORD_MISC_USER, false);
 
 	/* path                alloc_name  alloc_ext   kmod  comp  name   ext */
 	T("/xxxx/xxxx/x.ko.gz", true     , true      , true, true, "[x]", "gz");
 	T("/xxxx/xxxx/x.ko.gz", false    , true      , true, true, NULL , "gz");
 	T("/xxxx/xxxx/x.ko.gz", true     , false     , true, true, "[x]", NULL);
 	T("/xxxx/xxxx/x.ko.gz", false    , false     , true, true, NULL , NULL);
+	M("/xxxx/xxxx/x.ko.gz", PERF_RECORD_MISC_CPUMODE_UNKNOWN, true);
+	M("/xxxx/xxxx/x.ko.gz", PERF_RECORD_MISC_KERNEL, true);
+	M("/xxxx/xxxx/x.ko.gz", PERF_RECORD_MISC_USER, false);
 
 	/* path              alloc_name  alloc_ext  kmod   comp  name    ext */
 	T("/xxxx/xxxx/x.gz", true      , true     , false, true, "x.gz" ,"gz");
 	T("/xxxx/xxxx/x.gz", false     , true     , false, true, NULL   ,"gz");
 	T("/xxxx/xxxx/x.gz", true      , false    , false, true, "x.gz" , NULL);
 	T("/xxxx/xxxx/x.gz", false     , false    , false, true, NULL   , NULL);
+	M("/xxxx/xxxx/x.gz", PERF_RECORD_MISC_CPUMODE_UNKNOWN, false);
+	M("/xxxx/xxxx/x.gz", PERF_RECORD_MISC_KERNEL, false);
+	M("/xxxx/xxxx/x.gz", PERF_RECORD_MISC_USER, false);
 
 	/* path   alloc_name  alloc_ext  kmod   comp  name     ext */
 	T("x.gz", true      , true     , false, true, "x.gz", "gz");
 	T("x.gz", false     , true     , false, true, NULL  , "gz");
 	T("x.gz", true      , false    , false, true, "x.gz", NULL);
 	T("x.gz", false     , false    , false, true, NULL  , NULL);
+	M("x.gz", PERF_RECORD_MISC_CPUMODE_UNKNOWN, false);
+	M("x.gz", PERF_RECORD_MISC_KERNEL, false);
+	M("x.gz", PERF_RECORD_MISC_USER, false);
 
 	/* path      alloc_name  alloc_ext  kmod  comp  name  ext */
 	T("x.ko.gz", true      , true     , true, true, "[x]", "gz");
 	T("x.ko.gz", false     , true     , true, true, NULL , "gz");
 	T("x.ko.gz", true      , false    , true, true, "[x]", NULL);
 	T("x.ko.gz", false     , false    , true, true, NULL , NULL);
+	M("x.ko.gz", PERF_RECORD_MISC_CPUMODE_UNKNOWN, true);
+	M("x.ko.gz", PERF_RECORD_MISC_KERNEL, true);
+	M("x.ko.gz", PERF_RECORD_MISC_USER, false);
+
+	/* path            alloc_name  alloc_ext  kmod  comp   name             ext */
+	T("[test_module]", true      , true     , true, false, "[test_module]", NULL);
+	T("[test_module]", false     , true     , true, false, NULL           , NULL);
+	T("[test_module]", true      , false    , true, false, "[test_module]", NULL);
+	T("[test_module]", false     , false    , true, false, NULL           , NULL);
+	M("[test_module]", PERF_RECORD_MISC_CPUMODE_UNKNOWN, true);
+	M("[test_module]", PERF_RECORD_MISC_KERNEL, true);
+	M("[test_module]", PERF_RECORD_MISC_USER, false);
+
+	/* path            alloc_name  alloc_ext  kmod  comp   name             ext */
+	T("[test.module]", true      , true     , true, false, "[test.module]", NULL);
+	T("[test.module]", false     , true     , true, false, NULL           , NULL);
+	T("[test.module]", true      , false    , true, false, "[test.module]", NULL);
+	T("[test.module]", false     , false    , true, false, NULL           , NULL);
+	M("[test.module]", PERF_RECORD_MISC_CPUMODE_UNKNOWN, true);
+	M("[test.module]", PERF_RECORD_MISC_KERNEL, true);
+	M("[test.module]", PERF_RECORD_MISC_USER, false);
+
+	/* path     alloc_name  alloc_ext  kmod   comp   name      ext */
+	T("[vdso]", true      , true     , false, false, "[vdso]", NULL);
+	T("[vdso]", false     , true     , false, false, NULL    , NULL);
+	T("[vdso]", true      , false    , false, false, "[vdso]", NULL);
+	T("[vdso]", false     , false    , false, false, NULL    , NULL);
+	M("[vdso]", PERF_RECORD_MISC_CPUMODE_UNKNOWN, false);
+	M("[vdso]", PERF_RECORD_MISC_KERNEL, false);
+	M("[vdso]", PERF_RECORD_MISC_USER, false);
+
+	/* path         alloc_name  alloc_ext  kmod   comp   name          ext */
+	T("[vsyscall]", true      , true     , false, false, "[vsyscall]", NULL);
+	T("[vsyscall]", false     , true     , false, false, NULL        , NULL);
+	T("[vsyscall]", true      , false    , false, false, "[vsyscall]", NULL);
+	T("[vsyscall]", false     , false    , false, false, NULL        , NULL);
+	M("[vsyscall]", PERF_RECORD_MISC_CPUMODE_UNKNOWN, false);
+	M("[vsyscall]", PERF_RECORD_MISC_KERNEL, false);
+	M("[vsyscall]", PERF_RECORD_MISC_USER, false);
+
+	/* path                alloc_name  alloc_ext  kmod   comp   name      ext */
+	T("[kernel.kallsyms]", true      , true     , false, false, "[kernel.kallsyms]", NULL);
+	T("[kernel.kallsyms]", false     , true     , false, false, NULL               , NULL);
+	T("[kernel.kallsyms]", true      , false    , false, false, "[kernel.kallsyms]", NULL);
+	T("[kernel.kallsyms]", false     , false    , false, false, NULL               , NULL);
+	M("[kernel.kallsyms]", PERF_RECORD_MISC_CPUMODE_UNKNOWN, false);
+	M("[kernel.kallsyms]", PERF_RECORD_MISC_KERNEL, false);
+	M("[kernel.kallsyms]", PERF_RECORD_MISC_USER, false);
 
 	return 0;
 }
diff --git a/tools/perf/tests/make b/tools/perf/tests/make
index bff85324f799..65280d28662e 100644
--- a/tools/perf/tests/make
+++ b/tools/perf/tests/make
@@ -32,6 +32,7 @@ make_no_backtrace   := NO_BACKTRACE=1
 make_no_libnuma     := NO_LIBNUMA=1
 make_no_libaudit    := NO_LIBAUDIT=1
 make_no_libbionic   := NO_LIBBIONIC=1
+make_no_auxtrace    := NO_AUXTRACE=1
 make_tags           := tags
 make_cscope         := cscope
 make_help           := help
@@ -52,7 +53,7 @@ make_static         := LDFLAGS=-static
 make_minimal        := NO_LIBPERL=1 NO_LIBPYTHON=1 NO_NEWT=1 NO_GTK2=1
 make_minimal        += NO_DEMANGLE=1 NO_LIBELF=1 NO_LIBUNWIND=1 NO_BACKTRACE=1
 make_minimal        += NO_LIBNUMA=1 NO_LIBAUDIT=1 NO_LIBBIONIC=1
-make_minimal        += NO_LIBDW_DWARF_UNWIND=1
+make_minimal        += NO_LIBDW_DWARF_UNWIND=1 NO_AUXTRACE=1
 
 # $(run) contains all available tests
 run := make_pure
@@ -74,6 +75,7 @@ run += make_no_backtrace
 run += make_no_libnuma
 run += make_no_libaudit
 run += make_no_libbionic
+run += make_no_auxtrace
 run += make_help
 run += make_doc
 run += make_perf_o
@@ -223,7 +225,19 @@ tarpkg:
 	echo "- $@: $$cmd" && echo $$cmd > $@ && \
 	( eval $$cmd ) >> $@ 2>&1
 
-all: $(run) $(run_O) tarpkg
+make_kernelsrc:
+	@echo " - make -C <kernelsrc> tools/perf"
+	$(call clean); \
+	(make -C ../.. tools/perf) > $@ 2>&1 && \
+	test -x perf && rm -f $@ || (cat $@ ; false)
+
+make_kernelsrc_tools:
+	@echo " - make -C <kernelsrc>/tools perf"
+	$(call clean); \
+	(make -C ../../tools perf) > $@ 2>&1 && \
+	test -x perf && rm -f $@ || (cat $@ ; false)
+
+all: $(run) $(run_O) tarpkg make_kernelsrc make_kernelsrc_tools
 	@echo OK
 
 out: $(run_O)
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index 9b9622a33932..5855cf471210 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -23,10 +23,8 @@ int test__basic_mmap(void)
 	struct cpu_map *cpus;
 	struct perf_evlist *evlist;
 	cpu_set_t cpu_set;
-	const char *syscall_names[] = { "getsid", "getppid", "getpgrp",
-					"getpgid", };
-	pid_t (*syscalls[])(void) = { (void *)getsid, getppid, getpgrp,
-				      (void*)getpgid };
+	const char *syscall_names[] = { "getsid", "getppid", "getpgid", };
+	pid_t (*syscalls[])(void) = { (void *)getsid, getppid, (void*)getpgid };
 #define nsyscalls ARRAY_SIZE(syscall_names)
 	unsigned int nr_events[nsyscalls],
 		     expected_nr_events[nsyscalls], i, j;
diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c
index 2113f1c8611f..7f48efa7e295 100644
--- a/tools/perf/tests/mmap-thread-lookup.c
+++ b/tools/perf/tests/mmap-thread-lookup.c
@@ -129,7 +129,7 @@ static int synth_all(struct machine *machine)
 {
 	return perf_event__synthesize_threads(NULL,
 					      perf_event__process,
-					      machine, 0);
+					      machine, 0, 500);
 }
 
 static int synth_process(struct machine *machine)
@@ -141,7 +141,7 @@ static int synth_process(struct machine *machine)
 
 	err = perf_event__synthesize_thread_map(NULL, map,
 						perf_event__process,
-						machine, 0);
+						machine, 0, 500);
 
 	thread_map__delete(map);
 	return err;
@@ -191,6 +191,8 @@ static int mmap_events(synth_cb synth)
 				      PERF_RECORD_MISC_USER, MAP__FUNCTION,
 				      (unsigned long) (td->map + 1), &al);
 
+		thread__put(thread);
+
 		if (!al.map) {
 			pr_debug("failed, couldn't find map\n");
 			err = -1;
diff --git a/tools/perf/tests/open-syscall-all-cpus.c b/tools/perf/tests/openat-syscall-all-cpus.c
index 3ec885c48f8f..9a7a116e09b8 100644
--- a/tools/perf/tests/open-syscall-all-cpus.c
+++ b/tools/perf/tests/openat-syscall-all-cpus.c
@@ -3,13 +3,14 @@
 #include "thread_map.h"
 #include "cpumap.h"
 #include "debug.h"
+#include "stat.h"
 
-int test__open_syscall_event_on_all_cpus(void)
+int test__openat_syscall_event_on_all_cpus(void)
 {
 	int err = -1, fd, cpu;
 	struct cpu_map *cpus;
 	struct perf_evsel *evsel;
-	unsigned int nr_open_calls = 111, i;
+	unsigned int nr_openat_calls = 111, i;
 	cpu_set_t cpu_set;
 	struct thread_map *threads = thread_map__new(-1, getpid(), UINT_MAX);
 	char sbuf[STRERR_BUFSIZE];
@@ -27,7 +28,7 @@ int test__open_syscall_event_on_all_cpus(void)
 
 	CPU_ZERO(&cpu_set);
 
-	evsel = perf_evsel__newtp("syscalls", "sys_enter_open");
+	evsel = perf_evsel__newtp("syscalls", "sys_enter_openat");
 	if (evsel == NULL) {
 		if (tracefs_configured())
 			pr_debug("is tracefs mounted on /sys/kernel/tracing?\n");
@@ -46,7 +47,7 @@ int test__open_syscall_event_on_all_cpus(void)
 	}
 
 	for (cpu = 0; cpu < cpus->nr; ++cpu) {
-		unsigned int ncalls = nr_open_calls + cpu;
+		unsigned int ncalls = nr_openat_calls + cpu;
 		/*
 		 * XXX eventually lift this restriction in a way that
 		 * keeps perf building on older glibc installations
@@ -66,7 +67,7 @@ int test__open_syscall_event_on_all_cpus(void)
 			goto out_close_fd;
 		}
 		for (i = 0; i < ncalls; ++i) {
-			fd = open("/etc/passwd", O_RDONLY);
+			fd = openat(0, "/etc/passwd", O_RDONLY);
 			close(fd);
 		}
 		CPU_CLR(cpus->map[cpu], &cpu_set);
@@ -96,7 +97,7 @@ int test__open_syscall_event_on_all_cpus(void)
 			break;
 		}
 
-		expected = nr_open_calls + cpu;
+		expected = nr_openat_calls + cpu;
 		if (evsel->counts->cpu[cpu].val != expected) {
 			pr_debug("perf_evsel__read_on_cpu: expected to intercept %d calls on cpu %d, got %" PRIu64 "\n",
 				 expected, cpus->map[cpu], evsel->counts->cpu[cpu].val);
diff --git a/tools/perf/tests/open-syscall-tp-fields.c b/tools/perf/tests/openat-syscall-tp-fields.c
index 127dcae0b760..6245221479d7 100644
--- a/tools/perf/tests/open-syscall-tp-fields.c
+++ b/tools/perf/tests/openat-syscall-tp-fields.c
@@ -5,7 +5,7 @@
 #include "tests.h"
 #include "debug.h"
 
-int test__syscall_open_tp_fields(void)
+int test__syscall_openat_tp_fields(void)
 {
 	struct record_opts opts = {
 		.target = {
@@ -29,7 +29,7 @@ int test__syscall_open_tp_fields(void)
 		goto out;
 	}
 
-	evsel = perf_evsel__newtp("syscalls", "sys_enter_open");
+	evsel = perf_evsel__newtp("syscalls", "sys_enter_openat");
 	if (evsel == NULL) {
 		pr_debug("%s: perf_evsel__newtp\n", __func__);
 		goto out_delete_evlist;
@@ -66,7 +66,7 @@ int test__syscall_open_tp_fields(void)
 	/*
 	 * Generate the event:
 	 */
-	open(filename, flags);
+	openat(AT_FDCWD, filename, flags);
 
 	while (1) {
 		int before = nr_events;
diff --git a/tools/perf/tests/open-syscall.c b/tools/perf/tests/openat-syscall.c
index 07aa319bf334..9f9491bb8e48 100644
--- a/tools/perf/tests/open-syscall.c
+++ b/tools/perf/tests/openat-syscall.c
@@ -3,11 +3,11 @@
 #include "debug.h"
 #include "tests.h"
 
-int test__open_syscall_event(void)
+int test__openat_syscall_event(void)
 {
 	int err = -1, fd;
 	struct perf_evsel *evsel;
-	unsigned int nr_open_calls = 111, i;
+	unsigned int nr_openat_calls = 111, i;
 	struct thread_map *threads = thread_map__new(-1, getpid(), UINT_MAX);
 	char sbuf[STRERR_BUFSIZE];
 
@@ -16,7 +16,7 @@ int test__open_syscall_event(void)
 		return -1;
 	}
 
-	evsel = perf_evsel__newtp("syscalls", "sys_enter_open");
+	evsel = perf_evsel__newtp("syscalls", "sys_enter_openat");
 	if (evsel == NULL) {
 		if (tracefs_configured())
 			pr_debug("is tracefs mounted on /sys/kernel/tracing?\n");
@@ -34,8 +34,8 @@ int test__open_syscall_event(void)
 		goto out_evsel_delete;
 	}
 
-	for (i = 0; i < nr_open_calls; ++i) {
-		fd = open("/etc/passwd", O_RDONLY);
+	for (i = 0; i < nr_openat_calls; ++i) {
+		fd = openat(0, "/etc/passwd", O_RDONLY);
 		close(fd);
 	}
 
@@ -44,9 +44,9 @@ int test__open_syscall_event(void)
 		goto out_close_fd;
 	}
 
-	if (evsel->counts->cpu[0].val != nr_open_calls) {
+	if (evsel->counts->cpu[0].val != nr_openat_calls) {
 		pr_debug("perf_evsel__read_on_cpu: expected to intercept %d calls, got %" PRIu64 "\n",
-			 nr_open_calls, evsel->counts->cpu[0].val);
+			 nr_openat_calls, evsel->counts->cpu[0].val);
 		goto out_close_fd;
 	}
 
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 3de744961739..d76963f7ad3d 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -427,7 +427,7 @@ static int test__checkevent_list(struct perf_evlist *evlist)
 	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
 
-	/* syscalls:sys_enter_open:k */
+	/* syscalls:sys_enter_openat:k */
 	evsel = perf_evsel__next(evsel);
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_TRACEPOINT == evsel->attr.type);
 	TEST_ASSERT_VAL("wrong sample_type",
@@ -665,7 +665,7 @@ static int test__group3(struct perf_evlist *evlist __maybe_unused)
 	TEST_ASSERT_VAL("wrong number of entries", 5 == evlist->nr_entries);
 	TEST_ASSERT_VAL("wrong number of groups", 2 == evlist->nr_groups);
 
-	/* group1 syscalls:sys_enter_open:H */
+	/* group1 syscalls:sys_enter_openat:H */
 	evsel = leader = perf_evlist__first(evlist);
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_TRACEPOINT == evsel->attr.type);
 	TEST_ASSERT_VAL("wrong sample_type",
@@ -1293,7 +1293,7 @@ struct evlist_test {
 
 static struct evlist_test test__events[] = {
 	{
-		.name  = "syscalls:sys_enter_open",
+		.name  = "syscalls:sys_enter_openat",
 		.check = test__checkevent_tracepoint,
 		.id    = 0,
 	},
@@ -1353,7 +1353,7 @@ static struct evlist_test test__events[] = {
 		.id    = 11,
 	},
 	{
-		.name  = "syscalls:sys_enter_open:k",
+		.name  = "syscalls:sys_enter_openat:k",
 		.check = test__checkevent_tracepoint_modifier,
 		.id    = 12,
 	},
@@ -1408,7 +1408,7 @@ static struct evlist_test test__events[] = {
 		.id    = 22,
 	},
 	{
-		.name  = "r1,syscalls:sys_enter_open:k,1:1:hp",
+		.name  = "r1,syscalls:sys_enter_openat:k,1:1:hp",
 		.check = test__checkevent_list,
 		.id    = 23,
 	},
@@ -1443,7 +1443,7 @@ static struct evlist_test test__events[] = {
 		.id    = 29,
 	},
 	{
-		.name  = "group1{syscalls:sys_enter_open:H,cycles:kppp},group2{cycles,1:3}:G,instructions:u",
+		.name  = "group1{syscalls:sys_enter_openat:H,cycles:kppp},group2{cycles,1:3}:G,instructions:u",
 		.check = test__group3,
 		.id    = 30,
 	},
@@ -1571,7 +1571,7 @@ static int test_event(struct evlist_test *e)
 	if (evlist == NULL)
 		return -ENOMEM;
 
-	ret = parse_events(evlist, e->name);
+	ret = parse_events(evlist, e->name, NULL);
 	if (ret) {
 		pr_debug("failed to parse event '%s', err %d\n",
 			 e->name, ret);
diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c
index f238442b238a..5f49484f1abc 100644
--- a/tools/perf/tests/perf-time-to-tsc.c
+++ b/tools/perf/tests/perf-time-to-tsc.c
@@ -68,7 +68,7 @@ int test__perf_time_to_tsc(void)
 
 	perf_evlist__set_maps(evlist, cpus, threads);
 
-	CHECK__(parse_events(evlist, "cycles:u"));
+	CHECK__(parse_events(evlist, "cycles:u", NULL));
 
 	perf_evlist__config(evlist, &opts);
 
diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c
index eeb68bb1972d..faa04e9d5d5f 100644
--- a/tools/perf/tests/pmu.c
+++ b/tools/perf/tests/pmu.c
@@ -152,7 +152,8 @@ int test__pmu(void)
 		if (ret)
 			break;
 
-		ret = perf_pmu__config_terms(&formats, &attr, terms, false);
+		ret = perf_pmu__config_terms(&formats, &attr, terms,
+					     false, NULL);
 		if (ret)
 			break;
 
diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c
index cc68648c7c55..0d31403ea593 100644
--- a/tools/perf/tests/switch-tracking.c
+++ b/tools/perf/tests/switch-tracking.c
@@ -347,7 +347,7 @@ int test__switch_tracking(void)
 	perf_evlist__set_maps(evlist, cpus, threads);
 
 	/* First event */
-	err = parse_events(evlist, "cpu-clock:u");
+	err = parse_events(evlist, "cpu-clock:u", NULL);
 	if (err) {
 		pr_debug("Failed to parse event dummy:u\n");
 		goto out_err;
@@ -356,7 +356,7 @@ int test__switch_tracking(void)
 	cpu_clocks_evsel = perf_evlist__last(evlist);
 
 	/* Second event */
-	err = parse_events(evlist, "cycles:u");
+	err = parse_events(evlist, "cycles:u", NULL);
 	if (err) {
 		pr_debug("Failed to parse event cycles:u\n");
 		goto out_err;
@@ -371,7 +371,7 @@ int test__switch_tracking(void)
 		goto out;
 	}
 
-	err = parse_events(evlist, sched_switch);
+	err = parse_events(evlist, sched_switch, NULL);
 	if (err) {
 		pr_debug("Failed to parse event %s\n", sched_switch);
 		goto out_err;
@@ -401,7 +401,7 @@ int test__switch_tracking(void)
 	perf_evsel__set_sample_bit(cycles_evsel, TIME);
 
 	/* Fourth event */
-	err = parse_events(evlist, "dummy:u");
+	err = parse_events(evlist, "dummy:u", NULL);
 	if (err) {
 		pr_debug("Failed to parse event dummy:u\n");
 		goto out_err;
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index 52758a33f64c..8e5038b48ba8 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -9,6 +9,15 @@ do {									 \
 	}								 \
 } while (0)
 
+#define TEST_ASSERT_EQUAL(text, val, expected)				 \
+do {									 \
+	if (val != expected) {						 \
+		pr_debug("FAILED %s:%d %s (%d != %d)\n",		 \
+			 __FILE__, __LINE__, text, val, expected);	 \
+		return -1;						 \
+	}								 \
+} while (0)
+
 enum {
 	TEST_OK   =  0,
 	TEST_FAIL = -1,
@@ -17,14 +26,14 @@ enum {
 
 /* Tests */
 int test__vmlinux_matches_kallsyms(void);
-int test__open_syscall_event(void);
-int test__open_syscall_event_on_all_cpus(void);
+int test__openat_syscall_event(void);
+int test__openat_syscall_event_on_all_cpus(void);
 int test__basic_mmap(void);
 int test__PERF_RECORD(void);
 int test__rdpmc(void);
 int test__perf_evsel__roundtrip_name_test(void);
 int test__perf_evsel__tp_sched_test(void);
-int test__syscall_open_tp_fields(void);
+int test__syscall_openat_tp_fields(void);
 int test__pmu(void);
 int test__attr(void);
 int test__dso_data(void);
@@ -53,7 +62,7 @@ int test__fdarray__filter(void);
 int test__fdarray__add(void);
 int test__kmod_path__parse(void);
 
-#if defined(__x86_64__) || defined(__i386__) || defined(__arm__)
+#if defined(__x86_64__) || defined(__i386__) || defined(__arm__) || defined(__aarch64__)
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
 struct thread;
 struct perf_sample;
diff --git a/tools/perf/tests/thread-mg-share.c b/tools/perf/tests/thread-mg-share.c
index b028499dd3cf..01fabb19d746 100644
--- a/tools/perf/tests/thread-mg-share.c
+++ b/tools/perf/tests/thread-mg-share.c
@@ -43,7 +43,7 @@ int test__thread_mg_share(void)
 			leader && t1 && t2 && t3 && other);
 
 	mg = leader->mg;
-	TEST_ASSERT_VAL("wrong refcnt", mg->refcnt == 4);
+	TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&mg->refcnt), 4);
 
 	/* test the map groups pointer is shared */
 	TEST_ASSERT_VAL("map groups don't match", mg == t1->mg);
@@ -58,33 +58,40 @@ int test__thread_mg_share(void)
 	other_leader = machine__find_thread(machine, 4, 4);
 	TEST_ASSERT_VAL("failed to find other leader", other_leader);
 
+	/*
+	 * Ok, now that all the rbtree related operations were done,
+	 * lets remove all of them from there so that we can do the
+	 * refcounting tests.
+	 */
+	machine__remove_thread(machine, leader);
+	machine__remove_thread(machine, t1);
+	machine__remove_thread(machine, t2);
+	machine__remove_thread(machine, t3);
+	machine__remove_thread(machine, other);
+	machine__remove_thread(machine, other_leader);
+
 	other_mg = other->mg;
-	TEST_ASSERT_VAL("wrong refcnt", other_mg->refcnt == 2);
+	TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&other_mg->refcnt), 2);
 
 	TEST_ASSERT_VAL("map groups don't match", other_mg == other_leader->mg);
 
 	/* release thread group */
-	thread__delete(leader);
-	TEST_ASSERT_VAL("wrong refcnt", mg->refcnt == 3);
+	thread__put(leader);
+	TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&mg->refcnt), 3);
 
-	thread__delete(t1);
-	TEST_ASSERT_VAL("wrong refcnt", mg->refcnt == 2);
+	thread__put(t1);
+	TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&mg->refcnt), 2);
 
-	thread__delete(t2);
-	TEST_ASSERT_VAL("wrong refcnt", mg->refcnt == 1);
+	thread__put(t2);
+	TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&mg->refcnt), 1);
 
-	thread__delete(t3);
+	thread__put(t3);
 
 	/* release other group  */
-	thread__delete(other_leader);
-	TEST_ASSERT_VAL("wrong refcnt", other_mg->refcnt == 1);
+	thread__put(other_leader);
+	TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&other_mg->refcnt), 1);
 
-	thread__delete(other);
-
-	/*
-	 * Cannot call machine__delete_threads(machine) now,
-	 * because we've already released all the threads.
-	 */
+	thread__put(other);
 
 	machines__exit(&machines);
 	return 0;
diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c
index 3d9088003a5b..b34c5fc829ae 100644
--- a/tools/perf/tests/vmlinux-kallsyms.c
+++ b/tools/perf/tests/vmlinux-kallsyms.c
@@ -23,9 +23,10 @@ int test__vmlinux_matches_kallsyms(void)
 	int err = -1;
 	struct rb_node *nd;
 	struct symbol *sym;
-	struct map *kallsyms_map, *vmlinux_map;
+	struct map *kallsyms_map, *vmlinux_map, *map;
 	struct machine kallsyms, vmlinux;
 	enum map_type type = MAP__FUNCTION;
+	struct maps *maps = &vmlinux.kmaps.maps[type];
 	u64 mem_start, mem_end;
 
 	/*
@@ -184,8 +185,8 @@ detour:
 
 	pr_info("Maps only in vmlinux:\n");
 
-	for (nd = rb_first(&vmlinux.kmaps.maps[type]); nd; nd = rb_next(nd)) {
-		struct map *pos = rb_entry(nd, struct map, rb_node), *pair;
+	for (map = maps__first(maps); map; map = map__next(map)) {
+		struct map *
 		/*
 		 * If it is the kernel, kallsyms is always "[kernel.kallsyms]", while
 		 * the kernel will have the path for the vmlinux file being used,
@@ -193,22 +194,22 @@ detour:
 		 * both cases.
 		 */
 		pair = map_groups__find_by_name(&kallsyms.kmaps, type,
-						(pos->dso->kernel ?
-							pos->dso->short_name :
-							pos->dso->name));
+						(map->dso->kernel ?
+							map->dso->short_name :
+							map->dso->name));
 		if (pair)
 			pair->priv = 1;
 		else
-			map__fprintf(pos, stderr);
+			map__fprintf(map, stderr);
 	}
 
 	pr_info("Maps in vmlinux with a different name in kallsyms:\n");
 
-	for (nd = rb_first(&vmlinux.kmaps.maps[type]); nd; nd = rb_next(nd)) {
-		struct map *pos = rb_entry(nd, struct map, rb_node), *pair;
+	for (map = maps__first(maps); map; map = map__next(map)) {
+		struct map *pair;
 
-		mem_start = vmlinux_map->unmap_ip(vmlinux_map, pos->start);
-		mem_end = vmlinux_map->unmap_ip(vmlinux_map, pos->end);
+		mem_start = vmlinux_map->unmap_ip(vmlinux_map, map->start);
+		mem_end = vmlinux_map->unmap_ip(vmlinux_map, map->end);
 
 		pair = map_groups__find(&kallsyms.kmaps, type, mem_start);
 		if (pair == NULL || pair->priv)
@@ -217,7 +218,7 @@ detour:
 		if (pair->start == mem_start) {
 			pair->priv = 1;
 			pr_info(" %" PRIx64 "-%" PRIx64 " %" PRIx64 " %s in kallsyms as",
-				pos->start, pos->end, pos->pgoff, pos->dso->name);
+				map->start, map->end, map->pgoff, map->dso->name);
 			if (mem_end != pair->end)
 				pr_info(":\n*%" PRIx64 "-%" PRIx64 " %" PRIx64,
 					pair->start, pair->end, pair->pgoff);
@@ -228,12 +229,11 @@ detour:
 
 	pr_info("Maps only in kallsyms:\n");
 
-	for (nd = rb_first(&kallsyms.kmaps.maps[type]);
-	     nd; nd = rb_next(nd)) {
-		struct map *pos = rb_entry(nd, struct map, rb_node);
+	maps = &kallsyms.kmaps.maps[type];
 
-		if (!pos->priv)
-			map__fprintf(pos, stderr);
+	for (map = maps__first(maps); map; map = map__next(map)) {
+		if (!map->priv)
+			map__fprintf(map, stderr);
 	}
 out:
 	machine__exit(&kallsyms);
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index e5250eb2dd57..5995a8bd7c69 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -11,16 +11,21 @@
 #include "../../util/evsel.h"
 #include <pthread.h>
 
+struct disasm_line_samples {
+	double		percent;
+	u64		nr;
+};
+
 struct browser_disasm_line {
-	struct rb_node	rb_node;
-	u32		idx;
-	int		idx_asm;
-	int		jump_sources;
+	struct rb_node			rb_node;
+	u32				idx;
+	int				idx_asm;
+	int				jump_sources;
 	/*
 	 * actual length of this array is saved on the nr_events field
 	 * of the struct annotate_browser
 	 */
-	double		percent[1];
+	struct disasm_line_samples	samples[1];
 };
 
 static struct annotate_browser_opt {
@@ -28,7 +33,8 @@ static struct annotate_browser_opt {
 	     use_offset,
 	     jump_arrows,
 	     show_linenr,
-	     show_nr_jumps;
+	     show_nr_jumps,
+	     show_total_period;
 } annotate_browser__opts = {
 	.use_offset	= true,
 	.jump_arrows	= true,
@@ -105,15 +111,20 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int
 	char bf[256];
 
 	for (i = 0; i < ab->nr_events; i++) {
-		if (bdl->percent[i] > percent_max)
-			percent_max = bdl->percent[i];
+		if (bdl->samples[i].percent > percent_max)
+			percent_max = bdl->samples[i].percent;
 	}
 
 	if (dl->offset != -1 && percent_max != 0.0) {
 		for (i = 0; i < ab->nr_events; i++) {
-			ui_browser__set_percent_color(browser, bdl->percent[i],
+			ui_browser__set_percent_color(browser,
+						      bdl->samples[i].percent,
 						      current_entry);
-			slsmg_printf("%6.2f ", bdl->percent[i]);
+			if (annotate_browser__opts.show_total_period)
+				slsmg_printf("%6" PRIu64 " ",
+					     bdl->samples[i].nr);
+			else
+				slsmg_printf("%6.2f ", bdl->samples[i].percent);
 		}
 	} else {
 		ui_browser__set_percent_color(browser, 0, current_entry);
@@ -273,9 +284,9 @@ static int disasm__cmp(struct browser_disasm_line *a,
 	int i;
 
 	for (i = 0; i < nr_pcnt; i++) {
-		if (a->percent[i] == b->percent[i])
+		if (a->samples[i].percent == b->samples[i].percent)
 			continue;
-		return a->percent[i] < b->percent[i];
+		return a->samples[i].percent < b->samples[i].percent;
 	}
 	return 0;
 }
@@ -366,14 +377,17 @@ static void annotate_browser__calc_percent(struct annotate_browser *browser,
 		next = disasm__get_next_ip_line(&notes->src->source, pos);
 
 		for (i = 0; i < browser->nr_events; i++) {
-			bpos->percent[i] = disasm__calc_percent(notes,
+			u64 nr_samples;
+
+			bpos->samples[i].percent = disasm__calc_percent(notes,
 						evsel->idx + i,
 						pos->offset,
 						next ? next->offset : len,
-					        &path);
+						&path, &nr_samples);
+			bpos->samples[i].nr = nr_samples;
 
-			if (max_percent < bpos->percent[i])
-				max_percent = bpos->percent[i];
+			if (max_percent < bpos->samples[i].percent)
+				max_percent = bpos->samples[i].percent;
 		}
 
 		if (max_percent < 0.01) {
@@ -737,6 +751,7 @@ static int annotate_browser__run(struct annotate_browser *browser,
 		"n             Search next string\n"
 		"o             Toggle disassembler output/simplified view\n"
 		"s             Toggle source code view\n"
+		"t             Toggle total period view\n"
 		"/             Search string\n"
 		"k             Toggle line numbers\n"
 		"r             Run available scripts\n"
@@ -812,6 +827,11 @@ show_sup_ins:
 				ui_helpline__puts("Actions are only available for 'callq', 'retq' & jump instructions.");
 			}
 			continue;
+		case 't':
+			annotate_browser__opts.show_total_period =
+			  !annotate_browser__opts.show_total_period;
+			annotate_browser__update_addr_width(browser);
+			continue;
 		case K_LEFT:
 		case K_ESC:
 		case 'q':
@@ -832,12 +852,20 @@ out:
 int map_symbol__tui_annotate(struct map_symbol *ms, struct perf_evsel *evsel,
 			     struct hist_browser_timer *hbt)
 {
+	/* Set default value for show_total_period.  */
+	annotate_browser__opts.show_total_period =
+	  symbol_conf.show_total_period;
+
 	return symbol__tui_annotate(ms->sym, ms->map, evsel, hbt);
 }
 
 int hist_entry__tui_annotate(struct hist_entry *he, struct perf_evsel *evsel,
 			     struct hist_browser_timer *hbt)
 {
+	/* reset abort key so that it can get Ctrl-C as a key */
+	SLang_reset_tty();
+	SLang_init_tty(0, 0, 0);
+
 	return map_symbol__tui_annotate(&he->ms, evsel, hbt);
 }
 
@@ -925,7 +953,8 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map,
 
 	if (perf_evsel__is_group_event(evsel)) {
 		nr_pcnt = evsel->nr_members;
-		sizeof_bdl += sizeof(double) * (nr_pcnt - 1);
+		sizeof_bdl += sizeof(struct disasm_line_samples) *
+		  (nr_pcnt - 1);
 	}
 
 	if (symbol__annotate(sym, map, sizeof_bdl) < 0) {
@@ -1002,6 +1031,7 @@ static struct annotate_config {
 	ANNOTATE_CFG(show_linenr),
 	ANNOTATE_CFG(show_nr_jumps),
 	ANNOTATE_CFG(use_offset),
+	ANNOTATE_CFG(show_total_period),
 };
 
 #undef ANNOTATE_CFG
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 995b7a8596b1..c42adb600091 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -25,6 +25,9 @@ struct hist_browser {
 	struct hists	    *hists;
 	struct hist_entry   *he_selection;
 	struct map_symbol   *selection;
+	struct hist_browser_timer *hbt;
+	struct pstack	    *pstack;
+	struct perf_session_env *env;
 	int		     print_seq;
 	bool		     show_dso;
 	bool		     show_headers;
@@ -60,7 +63,7 @@ static int hist_browser__get_folding(struct hist_browser *browser)
 		struct hist_entry *he =
 			rb_entry(nd, struct hist_entry, rb_node);
 
-		if (he->ms.unfolded)
+		if (he->unfolded)
 			unfolded_rows += he->nr_rows;
 	}
 	return unfolded_rows;
@@ -136,24 +139,19 @@ static char tree__folded_sign(bool unfolded)
 	return unfolded ? '-' : '+';
 }
 
-static char map_symbol__folded(const struct map_symbol *ms)
-{
-	return ms->has_children ? tree__folded_sign(ms->unfolded) : ' ';
-}
-
 static char hist_entry__folded(const struct hist_entry *he)
 {
-	return map_symbol__folded(&he->ms);
+	return he->has_children ? tree__folded_sign(he->unfolded) : ' ';
 }
 
 static char callchain_list__folded(const struct callchain_list *cl)
 {
-	return map_symbol__folded(&cl->ms);
+	return cl->has_children ? tree__folded_sign(cl->unfolded) : ' ';
 }
 
-static void map_symbol__set_folding(struct map_symbol *ms, bool unfold)
+static void callchain_list__set_folding(struct callchain_list *cl, bool unfold)
 {
-	ms->unfolded = unfold ? ms->has_children : false;
+	cl->unfolded = unfold ? cl->has_children : false;
 }
 
 static int callchain_node__count_rows_rb_tree(struct callchain_node *node)
@@ -189,7 +187,7 @@ static int callchain_node__count_rows(struct callchain_node *node)
 
 	list_for_each_entry(chain, &node->val, list) {
 		++n;
-		unfolded = chain->ms.unfolded;
+		unfolded = chain->unfolded;
 	}
 
 	if (unfolded)
@@ -211,15 +209,27 @@ static int callchain__count_rows(struct rb_root *chain)
 	return n;
 }
 
-static bool map_symbol__toggle_fold(struct map_symbol *ms)
+static bool hist_entry__toggle_fold(struct hist_entry *he)
 {
-	if (!ms)
+	if (!he)
 		return false;
 
-	if (!ms->has_children)
+	if (!he->has_children)
 		return false;
 
-	ms->unfolded = !ms->unfolded;
+	he->unfolded = !he->unfolded;
+	return true;
+}
+
+static bool callchain_list__toggle_fold(struct callchain_list *cl)
+{
+	if (!cl)
+		return false;
+
+	if (!cl->has_children)
+		return false;
+
+	cl->unfolded = !cl->unfolded;
 	return true;
 }
 
@@ -235,10 +245,10 @@ static void callchain_node__init_have_children_rb_tree(struct callchain_node *no
 		list_for_each_entry(chain, &child->val, list) {
 			if (first) {
 				first = false;
-				chain->ms.has_children = chain->list.next != &child->val ||
+				chain->has_children = chain->list.next != &child->val ||
 							 !RB_EMPTY_ROOT(&child->rb_root);
 			} else
-				chain->ms.has_children = chain->list.next == &child->val &&
+				chain->has_children = chain->list.next == &child->val &&
 							 !RB_EMPTY_ROOT(&child->rb_root);
 		}
 
@@ -252,11 +262,11 @@ static void callchain_node__init_have_children(struct callchain_node *node,
 	struct callchain_list *chain;
 
 	chain = list_entry(node->val.next, struct callchain_list, list);
-	chain->ms.has_children = has_sibling;
+	chain->has_children = has_sibling;
 
 	if (!list_empty(&node->val)) {
 		chain = list_entry(node->val.prev, struct callchain_list, list);
-		chain->ms.has_children = !RB_EMPTY_ROOT(&node->rb_root);
+		chain->has_children = !RB_EMPTY_ROOT(&node->rb_root);
 	}
 
 	callchain_node__init_have_children_rb_tree(node);
@@ -276,7 +286,7 @@ static void callchain__init_have_children(struct rb_root *root)
 static void hist_entry__init_have_children(struct hist_entry *he)
 {
 	if (!he->init_have_children) {
-		he->ms.has_children = !RB_EMPTY_ROOT(&he->sorted_chain);
+		he->has_children = !RB_EMPTY_ROOT(&he->sorted_chain);
 		callchain__init_have_children(&he->sorted_chain);
 		he->init_have_children = true;
 	}
@@ -284,14 +294,22 @@ static void hist_entry__init_have_children(struct hist_entry *he)
 
 static bool hist_browser__toggle_fold(struct hist_browser *browser)
 {
-	if (map_symbol__toggle_fold(browser->selection)) {
-		struct hist_entry *he = browser->he_selection;
+	struct hist_entry *he = browser->he_selection;
+	struct map_symbol *ms = browser->selection;
+	struct callchain_list *cl = container_of(ms, struct callchain_list, ms);
+	bool has_children;
 
+	if (ms == &he->ms)
+		has_children = hist_entry__toggle_fold(he);
+	else
+		has_children = callchain_list__toggle_fold(cl);
+
+	if (has_children) {
 		hist_entry__init_have_children(he);
 		browser->b.nr_entries -= he->nr_rows;
 		browser->nr_callchain_rows -= he->nr_rows;
 
-		if (he->ms.unfolded)
+		if (he->unfolded)
 			he->nr_rows = callchain__count_rows(&he->sorted_chain);
 		else
 			he->nr_rows = 0;
@@ -318,8 +336,8 @@ static int callchain_node__set_folding_rb_tree(struct callchain_node *node, bool
 
 		list_for_each_entry(chain, &child->val, list) {
 			++n;
-			map_symbol__set_folding(&chain->ms, unfold);
-			has_children = chain->ms.has_children;
+			callchain_list__set_folding(chain, unfold);
+			has_children = chain->has_children;
 		}
 
 		if (has_children)
@@ -337,8 +355,8 @@ static int callchain_node__set_folding(struct callchain_node *node, bool unfold)
 
 	list_for_each_entry(chain, &node->val, list) {
 		++n;
-		map_symbol__set_folding(&chain->ms, unfold);
-		has_children = chain->ms.has_children;
+		callchain_list__set_folding(chain, unfold);
+		has_children = chain->has_children;
 	}
 
 	if (has_children)
@@ -363,9 +381,9 @@ static int callchain__set_folding(struct rb_root *chain, bool unfold)
 static void hist_entry__set_folding(struct hist_entry *he, bool unfold)
 {
 	hist_entry__init_have_children(he);
-	map_symbol__set_folding(&he->ms, unfold);
+	he->unfolded = unfold ? he->has_children : false;
 
-	if (he->ms.has_children) {
+	if (he->has_children) {
 		int n = callchain__set_folding(&he->sorted_chain, unfold);
 		he->nr_rows = unfold ? n : 0;
 	} else
@@ -406,11 +424,11 @@ static void ui_browser__warn_lost_events(struct ui_browser *browser)
 		"Or reduce the sampling frequency.");
 }
 
-static int hist_browser__run(struct hist_browser *browser,
-			     struct hist_browser_timer *hbt)
+static int hist_browser__run(struct hist_browser *browser, const char *help)
 {
 	int key;
 	char title[160];
+	struct hist_browser_timer *hbt = browser->hbt;
 	int delay_secs = hbt ? hbt->refresh : 0;
 
 	browser->b.entries = &browser->hists->entries;
@@ -418,8 +436,7 @@ static int hist_browser__run(struct hist_browser *browser,
 
 	hists__browser_title(browser->hists, hbt, title, sizeof(title));
 
-	if (ui_browser__show(&browser->b, title,
-			     "Press '?' for help on key bindings") < 0)
+	if (ui_browser__show(&browser->b, title, help) < 0)
 		return -1;
 
 	while (1) {
@@ -1016,7 +1033,7 @@ do_offset:
 	if (offset > 0) {
 		do {
 			h = rb_entry(nd, struct hist_entry, rb_node);
-			if (h->ms.unfolded) {
+			if (h->unfolded) {
 				u16 remaining = h->nr_rows - h->row_offset;
 				if (offset > remaining) {
 					offset -= remaining;
@@ -1037,7 +1054,7 @@ do_offset:
 	} else if (offset < 0) {
 		while (1) {
 			h = rb_entry(nd, struct hist_entry, rb_node);
-			if (h->ms.unfolded) {
+			if (h->unfolded) {
 				if (first) {
 					if (-offset > h->row_offset) {
 						offset += h->row_offset;
@@ -1074,7 +1091,7 @@ do_offset:
 				 * row_offset at its last entry.
 				 */
 				h = rb_entry(nd, struct hist_entry, rb_node);
-				if (h->ms.unfolded)
+				if (h->unfolded)
 					h->row_offset = h->nr_rows;
 				break;
 			}
@@ -1195,7 +1212,9 @@ static int hist_browser__dump(struct hist_browser *browser)
 	return 0;
 }
 
-static struct hist_browser *hist_browser__new(struct hists *hists)
+static struct hist_browser *hist_browser__new(struct hists *hists,
+					      struct hist_browser_timer *hbt,
+					      struct perf_session_env *env)
 {
 	struct hist_browser *browser = zalloc(sizeof(*browser));
 
@@ -1206,6 +1225,8 @@ static struct hist_browser *hist_browser__new(struct hists *hists)
 		browser->b.seek = ui_browser__hists_seek;
 		browser->b.use_navkeypressed = true;
 		browser->show_headers = symbol_conf.show_hist_headers;
+		browser->hbt = hbt;
+		browser->env = env;
 	}
 
 	return browser;
@@ -1395,6 +1416,257 @@ close_file_and_continue:
 	return ret;
 }
 
+struct popup_action {
+	struct thread 		*thread;
+	struct dso		*dso;
+	struct map_symbol 	ms;
+
+	int (*fn)(struct hist_browser *browser, struct popup_action *act);
+};
+
+static int
+do_annotate(struct hist_browser *browser, struct popup_action *act)
+{
+	struct perf_evsel *evsel;
+	struct annotation *notes;
+	struct hist_entry *he;
+	int err;
+
+	if (!objdump_path && perf_session_env__lookup_objdump(browser->env))
+		return 0;
+
+	notes = symbol__annotation(act->ms.sym);
+	if (!notes->src)
+		return 0;
+
+	evsel = hists_to_evsel(browser->hists);
+	err = map_symbol__tui_annotate(&act->ms, evsel, browser->hbt);
+	he = hist_browser__selected_entry(browser);
+	/*
+	 * offer option to annotate the other branch source or target
+	 * (if they exists) when returning from annotate
+	 */
+	if ((err == 'q' || err == CTRL('c')) && he->branch_info)
+		return 1;
+
+	ui_browser__update_nr_entries(&browser->b, browser->hists->nr_entries);
+	if (err)
+		ui_browser__handle_resize(&browser->b);
+	return 0;
+}
+
+static int
+add_annotate_opt(struct hist_browser *browser __maybe_unused,
+		 struct popup_action *act, char **optstr,
+		 struct map *map, struct symbol *sym)
+{
+	if (sym == NULL || map->dso->annotate_warned)
+		return 0;
+
+	if (asprintf(optstr, "Annotate %s", sym->name) < 0)
+		return 0;
+
+	act->ms.map = map;
+	act->ms.sym = sym;
+	act->fn = do_annotate;
+	return 1;
+}
+
+static int
+do_zoom_thread(struct hist_browser *browser, struct popup_action *act)
+{
+	struct thread *thread = act->thread;
+
+	if (browser->hists->thread_filter) {
+		pstack__remove(browser->pstack, &browser->hists->thread_filter);
+		perf_hpp__set_elide(HISTC_THREAD, false);
+		thread__zput(browser->hists->thread_filter);
+		ui_helpline__pop();
+	} else {
+		ui_helpline__fpush("To zoom out press <- or -> + \"Zoom out of %s(%d) thread\"",
+				   thread->comm_set ? thread__comm_str(thread) : "",
+				   thread->tid);
+		browser->hists->thread_filter = thread__get(thread);
+		perf_hpp__set_elide(HISTC_THREAD, false);
+		pstack__push(browser->pstack, &browser->hists->thread_filter);
+	}
+
+	hists__filter_by_thread(browser->hists);
+	hist_browser__reset(browser);
+	return 0;
+}
+
+static int
+add_thread_opt(struct hist_browser *browser, struct popup_action *act,
+	       char **optstr, struct thread *thread)
+{
+	if (thread == NULL)
+		return 0;
+
+	if (asprintf(optstr, "Zoom %s %s(%d) thread",
+		     browser->hists->thread_filter ? "out of" : "into",
+		     thread->comm_set ? thread__comm_str(thread) : "",
+		     thread->tid) < 0)
+		return 0;
+
+	act->thread = thread;
+	act->fn = do_zoom_thread;
+	return 1;
+}
+
+static int
+do_zoom_dso(struct hist_browser *browser, struct popup_action *act)
+{
+	struct dso *dso = act->dso;
+
+	if (browser->hists->dso_filter) {
+		pstack__remove(browser->pstack, &browser->hists->dso_filter);
+		perf_hpp__set_elide(HISTC_DSO, false);
+		browser->hists->dso_filter = NULL;
+		ui_helpline__pop();
+	} else {
+		if (dso == NULL)
+			return 0;
+		ui_helpline__fpush("To zoom out press <- or -> + \"Zoom out of %s DSO\"",
+				   dso->kernel ? "the Kernel" : dso->short_name);
+		browser->hists->dso_filter = dso;
+		perf_hpp__set_elide(HISTC_DSO, true);
+		pstack__push(browser->pstack, &browser->hists->dso_filter);
+	}
+
+	hists__filter_by_dso(browser->hists);
+	hist_browser__reset(browser);
+	return 0;
+}
+
+static int
+add_dso_opt(struct hist_browser *browser, struct popup_action *act,
+	    char **optstr, struct dso *dso)
+{
+	if (dso == NULL)
+		return 0;
+
+	if (asprintf(optstr, "Zoom %s %s DSO",
+		     browser->hists->dso_filter ? "out of" : "into",
+		     dso->kernel ? "the Kernel" : dso->short_name) < 0)
+		return 0;
+
+	act->dso = dso;
+	act->fn = do_zoom_dso;
+	return 1;
+}
+
+static int
+do_browse_map(struct hist_browser *browser __maybe_unused,
+	      struct popup_action *act)
+{
+	map__browse(act->ms.map);
+	return 0;
+}
+
+static int
+add_map_opt(struct hist_browser *browser __maybe_unused,
+	    struct popup_action *act, char **optstr, struct map *map)
+{
+	if (map == NULL)
+		return 0;
+
+	if (asprintf(optstr, "Browse map details") < 0)
+		return 0;
+
+	act->ms.map = map;
+	act->fn = do_browse_map;
+	return 1;
+}
+
+static int
+do_run_script(struct hist_browser *browser __maybe_unused,
+	      struct popup_action *act)
+{
+	char script_opt[64];
+	memset(script_opt, 0, sizeof(script_opt));
+
+	if (act->thread) {
+		scnprintf(script_opt, sizeof(script_opt), " -c %s ",
+			  thread__comm_str(act->thread));
+	} else if (act->ms.sym) {
+		scnprintf(script_opt, sizeof(script_opt), " -S %s ",
+			  act->ms.sym->name);
+	}
+
+	script_browse(script_opt);
+	return 0;
+}
+
+static int
+add_script_opt(struct hist_browser *browser __maybe_unused,
+	       struct popup_action *act, char **optstr,
+	       struct thread *thread, struct symbol *sym)
+{
+	if (thread) {
+		if (asprintf(optstr, "Run scripts for samples of thread [%s]",
+			     thread__comm_str(thread)) < 0)
+			return 0;
+	} else if (sym) {
+		if (asprintf(optstr, "Run scripts for samples of symbol [%s]",
+			     sym->name) < 0)
+			return 0;
+	} else {
+		if (asprintf(optstr, "Run scripts for all samples") < 0)
+			return 0;
+	}
+
+	act->thread = thread;
+	act->ms.sym = sym;
+	act->fn = do_run_script;
+	return 1;
+}
+
+static int
+do_switch_data(struct hist_browser *browser __maybe_unused,
+	       struct popup_action *act __maybe_unused)
+{
+	if (switch_data_file()) {
+		ui__warning("Won't switch the data files due to\n"
+			    "no valid data file get selected!\n");
+		return 0;
+	}
+
+	return K_SWITCH_INPUT_DATA;
+}
+
+static int
+add_switch_opt(struct hist_browser *browser,
+	       struct popup_action *act, char **optstr)
+{
+	if (!is_report_browser(browser->hbt))
+		return 0;
+
+	if (asprintf(optstr, "Switch to another data file in PWD") < 0)
+		return 0;
+
+	act->fn = do_switch_data;
+	return 1;
+}
+
+static int
+do_exit_browser(struct hist_browser *browser __maybe_unused,
+		struct popup_action *act __maybe_unused)
+{
+	return 0;
+}
+
+static int
+add_exit_opt(struct hist_browser *browser __maybe_unused,
+	     struct popup_action *act, char **optstr)
+{
+	if (asprintf(optstr, "Exit") < 0)
+		return 0;
+
+	act->fn = do_exit_browser;
+	return 1;
+}
+
 static void hist_browser__update_nr_entries(struct hist_browser *hb)
 {
 	u64 nr_entries = 0;
@@ -1421,14 +1693,14 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 				    struct perf_session_env *env)
 {
 	struct hists *hists = evsel__hists(evsel);
-	struct hist_browser *browser = hist_browser__new(hists);
+	struct hist_browser *browser = hist_browser__new(hists, hbt, env);
 	struct branch_info *bi;
-	struct pstack *fstack;
-	char *options[16];
+#define MAX_OPTIONS  16
+	char *options[MAX_OPTIONS];
+	struct popup_action actions[MAX_OPTIONS];
 	int nr_options = 0;
 	int key = -1;
 	char buf[64];
-	char script_opt[64];
 	int delay_secs = hbt ? hbt->refresh : 0;
 	struct perf_hpp_fmt *fmt;
 
@@ -1463,23 +1735,29 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 	"t             Zoom into current Thread\n"
 	"V             Verbose (DSO names in callchains, etc)\n"
 	"z             Toggle zeroing of samples\n"
+	"f             Enable/Disable events\n"
 	"/             Filter symbol by name";
 
 	if (browser == NULL)
 		return -1;
 
+	/* reset abort key so that it can get Ctrl-C as a key */
+	SLang_reset_tty();
+	SLang_init_tty(0, 0, 0);
+
 	if (min_pcnt) {
 		browser->min_pcnt = min_pcnt;
 		hist_browser__update_nr_entries(browser);
 	}
 
-	fstack = pstack__new(2);
-	if (fstack == NULL)
+	browser->pstack = pstack__new(2);
+	if (browser->pstack == NULL)
 		goto out;
 
 	ui_helpline__push(helpline);
 
 	memset(options, 0, sizeof(options));
+	memset(actions, 0, sizeof(actions));
 
 	perf_hpp__for_each_format(fmt)
 		perf_hpp__reset_width(fmt, hists);
@@ -1489,16 +1767,12 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 
 	while (1) {
 		struct thread *thread = NULL;
-		const struct dso *dso = NULL;
-		int choice = 0,
-		    annotate = -2, zoom_dso = -2, zoom_thread = -2,
-		    annotate_f = -2, annotate_t = -2, browse_map = -2;
-		int scripts_comm = -2, scripts_symbol = -2,
-		    scripts_all = -2, switch_data = -2;
+		struct dso *dso = NULL;
+		int choice = 0;
 
 		nr_options = 0;
 
-		key = hist_browser__run(browser, hbt);
+		key = hist_browser__run(browser, helpline);
 
 		if (browser->he_selection != NULL) {
 			thread = hist_browser__selected_thread(browser);
@@ -1526,17 +1800,25 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 			    browser->selection->sym == NULL ||
 			    browser->selection->map->dso->annotate_warned)
 				continue;
-			goto do_annotate;
+
+			actions->ms.map = browser->selection->map;
+			actions->ms.sym = browser->selection->sym;
+			do_annotate(browser, actions);
+			continue;
 		case 'P':
 			hist_browser__dump(browser);
 			continue;
 		case 'd':
-			goto zoom_dso;
+			actions->dso = dso;
+			do_zoom_dso(browser, actions);
+			continue;
 		case 'V':
 			browser->show_dso = !browser->show_dso;
 			continue;
 		case 't':
-			goto zoom_thread;
+			actions->thread = thread;
+			do_zoom_thread(browser, actions);
+			continue;
 		case '/':
 			if (ui_browser__input_window("Symbol to show",
 					"Please enter the name of symbol you want to see",
@@ -1548,12 +1830,18 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 			}
 			continue;
 		case 'r':
-			if (is_report_browser(hbt))
-				goto do_scripts;
+			if (is_report_browser(hbt)) {
+				actions->thread = NULL;
+				actions->ms.sym = NULL;
+				do_run_script(browser, actions);
+			}
 			continue;
 		case 's':
-			if (is_report_browser(hbt))
-				goto do_data_switch;
+			if (is_report_browser(hbt)) {
+				key = do_switch_data(browser, actions);
+				if (key == K_SWITCH_INPUT_DATA)
+					goto out_free_stack;
+			}
 			continue;
 		case 'i':
 			/* env->arch is NULL for live-mode (i.e. perf top) */
@@ -1583,7 +1871,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 		case K_LEFT: {
 			const void *top;
 
-			if (pstack__empty(fstack)) {
+			if (pstack__empty(browser->pstack)) {
 				/*
 				 * Go back to the perf_evsel_menu__run or other user
 				 */
@@ -1591,11 +1879,17 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 					goto out_free_stack;
 				continue;
 			}
-			top = pstack__pop(fstack);
-			if (top == &browser->hists->dso_filter)
-				goto zoom_out_dso;
+			top = pstack__peek(browser->pstack);
+			if (top == &browser->hists->dso_filter) {
+				/*
+				 * No need to set actions->dso here since
+				 * it's just to remove the current filter.
+				 * Ditto for thread below.
+				 */
+				do_zoom_dso(browser, actions);
+			}
 			if (top == &browser->hists->thread_filter)
-				goto zoom_out_thread;
+				do_zoom_thread(browser, actions);
 			continue;
 		}
 		case K_ESC:
@@ -1607,7 +1901,12 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 		case 'q':
 		case CTRL('c'):
 			goto out_free_stack;
+		case 'f':
+			if (!is_report_browser(hbt))
+				goto out_free_stack;
+			/* Fall thru */
 		default:
+			helpline = "Press '?' for help on key bindings";
 			continue;
 		}
 
@@ -1623,196 +1922,71 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 			if (bi == NULL)
 				goto skip_annotation;
 
-			if (bi->from.sym != NULL &&
-			    !bi->from.map->dso->annotate_warned &&
-			    asprintf(&options[nr_options], "Annotate %s", bi->from.sym->name) > 0) {
-				annotate_f = nr_options++;
-			}
-
-			if (bi->to.sym != NULL &&
-			    !bi->to.map->dso->annotate_warned &&
-			    (bi->to.sym != bi->from.sym ||
-			     bi->to.map->dso != bi->from.map->dso) &&
-			    asprintf(&options[nr_options], "Annotate %s", bi->to.sym->name) > 0) {
-				annotate_t = nr_options++;
-			}
+			nr_options += add_annotate_opt(browser,
+						       &actions[nr_options],
+						       &options[nr_options],
+						       bi->from.map,
+						       bi->from.sym);
+			if (bi->to.sym != bi->from.sym)
+				nr_options += add_annotate_opt(browser,
+							&actions[nr_options],
+							&options[nr_options],
+							bi->to.map,
+							bi->to.sym);
 		} else {
-			if (browser->selection->sym != NULL &&
-			    !browser->selection->map->dso->annotate_warned) {
-				struct annotation *notes;
-
-				notes = symbol__annotation(browser->selection->sym);
-
-				if (notes->src &&
-				    asprintf(&options[nr_options], "Annotate %s",
-						 browser->selection->sym->name) > 0) {
-					annotate = nr_options++;
-				}
-			}
+			nr_options += add_annotate_opt(browser,
+						       &actions[nr_options],
+						       &options[nr_options],
+						       browser->selection->map,
+						       browser->selection->sym);
 		}
 skip_annotation:
-		if (thread != NULL &&
-		    asprintf(&options[nr_options], "Zoom %s %s(%d) thread",
-			     (browser->hists->thread_filter ? "out of" : "into"),
-			     (thread->comm_set ? thread__comm_str(thread) : ""),
-			     thread->tid) > 0)
-			zoom_thread = nr_options++;
-
-		if (dso != NULL &&
-		    asprintf(&options[nr_options], "Zoom %s %s DSO",
-			     (browser->hists->dso_filter ? "out of" : "into"),
-			     (dso->kernel ? "the Kernel" : dso->short_name)) > 0)
-			zoom_dso = nr_options++;
-
-		if (browser->selection != NULL &&
-		    browser->selection->map != NULL &&
-		    asprintf(&options[nr_options], "Browse map details") > 0)
-			browse_map = nr_options++;
+		nr_options += add_thread_opt(browser, &actions[nr_options],
+					     &options[nr_options], thread);
+		nr_options += add_dso_opt(browser, &actions[nr_options],
+					  &options[nr_options], dso);
+		nr_options += add_map_opt(browser, &actions[nr_options],
+					  &options[nr_options],
+					  browser->selection->map);
 
 		/* perf script support */
 		if (browser->he_selection) {
-			struct symbol *sym;
-
-			if (asprintf(&options[nr_options], "Run scripts for samples of thread [%s]",
-				     thread__comm_str(browser->he_selection->thread)) > 0)
-				scripts_comm = nr_options++;
-
-			sym = browser->he_selection->ms.sym;
-			if (sym && sym->namelen &&
-				asprintf(&options[nr_options], "Run scripts for samples of symbol [%s]",
-						sym->name) > 0)
-				scripts_symbol = nr_options++;
+			nr_options += add_script_opt(browser,
+						     &actions[nr_options],
+						     &options[nr_options],
+						     thread, NULL);
+			nr_options += add_script_opt(browser,
+						     &actions[nr_options],
+						     &options[nr_options],
+						     NULL, browser->selection->sym);
 		}
-
-		if (asprintf(&options[nr_options], "Run scripts for all samples") > 0)
-			scripts_all = nr_options++;
-
-		if (is_report_browser(hbt) && asprintf(&options[nr_options],
-				"Switch to another data file in PWD") > 0)
-			switch_data = nr_options++;
+		nr_options += add_script_opt(browser, &actions[nr_options],
+					     &options[nr_options], NULL, NULL);
+		nr_options += add_switch_opt(browser, &actions[nr_options],
+					     &options[nr_options]);
 add_exit_option:
-		options[nr_options++] = (char *)"Exit";
-retry_popup_menu:
-		choice = ui__popup_menu(nr_options, options);
-
-		if (choice == nr_options - 1)
-			break;
-
-		if (choice == -1) {
-			free_popup_options(options, nr_options - 1);
-			continue;
-		}
-
-		if (choice == annotate || choice == annotate_t || choice == annotate_f) {
-			struct hist_entry *he;
-			struct annotation *notes;
-			struct map_symbol ms;
-			int err;
-do_annotate:
-			if (!objdump_path && perf_session_env__lookup_objdump(env))
-				continue;
-
-			he = hist_browser__selected_entry(browser);
-			if (he == NULL)
-				continue;
-
-			if (choice == annotate_f) {
-				ms.map = he->branch_info->from.map;
-				ms.sym = he->branch_info->from.sym;
-			} else if (choice == annotate_t) {
-				ms.map = he->branch_info->to.map;
-				ms.sym = he->branch_info->to.sym;
-			} else {
-				ms = *browser->selection;
-			}
+		nr_options += add_exit_opt(browser, &actions[nr_options],
+					   &options[nr_options]);
 
-			notes = symbol__annotation(ms.sym);
-			if (!notes->src)
-				continue;
-
-			err = map_symbol__tui_annotate(&ms, evsel, hbt);
-			/*
-			 * offer option to annotate the other branch source or target
-			 * (if they exists) when returning from annotate
-			 */
-			if ((err == 'q' || err == CTRL('c'))
-			    && annotate_t != -2 && annotate_f != -2)
-				goto retry_popup_menu;
-
-			ui_browser__update_nr_entries(&browser->b, browser->hists->nr_entries);
-			if (err)
-				ui_browser__handle_resize(&browser->b);
-
-		} else if (choice == browse_map)
-			map__browse(browser->selection->map);
-		else if (choice == zoom_dso) {
-zoom_dso:
-			if (browser->hists->dso_filter) {
-				pstack__remove(fstack, &browser->hists->dso_filter);
-zoom_out_dso:
-				ui_helpline__pop();
-				browser->hists->dso_filter = NULL;
-				perf_hpp__set_elide(HISTC_DSO, false);
-			} else {
-				if (dso == NULL)
-					continue;
-				ui_helpline__fpush("To zoom out press <- or -> + \"Zoom out of %s DSO\"",
-						   dso->kernel ? "the Kernel" : dso->short_name);
-				browser->hists->dso_filter = dso;
-				perf_hpp__set_elide(HISTC_DSO, true);
-				pstack__push(fstack, &browser->hists->dso_filter);
-			}
-			hists__filter_by_dso(hists);
-			hist_browser__reset(browser);
-		} else if (choice == zoom_thread) {
-zoom_thread:
-			if (browser->hists->thread_filter) {
-				pstack__remove(fstack, &browser->hists->thread_filter);
-zoom_out_thread:
-				ui_helpline__pop();
-				thread__zput(browser->hists->thread_filter);
-				perf_hpp__set_elide(HISTC_THREAD, false);
-			} else {
-				ui_helpline__fpush("To zoom out press <- or -> + \"Zoom out of %s(%d) thread\"",
-						   thread->comm_set ? thread__comm_str(thread) : "",
-						   thread->tid);
-				browser->hists->thread_filter = thread__get(thread);
-				perf_hpp__set_elide(HISTC_THREAD, false);
-				pstack__push(fstack, &browser->hists->thread_filter);
-			}
-			hists__filter_by_thread(hists);
-			hist_browser__reset(browser);
-		}
-		/* perf scripts support */
-		else if (choice == scripts_all || choice == scripts_comm ||
-				choice == scripts_symbol) {
-do_scripts:
-			memset(script_opt, 0, 64);
+		do {
+			struct popup_action *act;
 
-			if (choice == scripts_comm)
-				sprintf(script_opt, " -c %s ", thread__comm_str(browser->he_selection->thread));
+			choice = ui__popup_menu(nr_options, options);
+			if (choice == -1 || choice >= nr_options)
+				break;
 
-			if (choice == scripts_symbol)
-				sprintf(script_opt, " -S %s ", browser->he_selection->ms.sym->name);
+			act = &actions[choice];
+			key = act->fn(browser, act);
+		} while (key == 1);
 
-			script_browse(script_opt);
-		}
-		/* Switch to another data file */
-		else if (choice == switch_data) {
-do_data_switch:
-			if (!switch_data_file()) {
-				key = K_SWITCH_INPUT_DATA;
-				break;
-			} else
-				ui__warning("Won't switch the data files due to\n"
-					"no valid data file get selected!\n");
-		}
+		if (key == K_SWITCH_INPUT_DATA)
+			break;
 	}
 out_free_stack:
-	pstack__delete(fstack);
+	pstack__delete(browser->pstack);
 out:
 	hist_browser__delete(browser);
-	free_popup_options(options, nr_options - 1);
+	free_popup_options(options, MAX_OPTIONS);
 	return key;
 }
 
diff --git a/tools/perf/ui/tui/setup.c b/tools/perf/ui/tui/setup.c
index b77e1d771363..60d1f29b4b50 100644
--- a/tools/perf/ui/tui/setup.c
+++ b/tools/perf/ui/tui/setup.c
@@ -129,7 +129,7 @@ int ui__init(void)
 	err = SLsmg_init_smg();
 	if (err < 0)
 		goto out;
-	err = SLang_init_tty(0, 0, 0);
+	err = SLang_init_tty(-1, 0, 0);
 	if (err < 0)
 		goto out;
 
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 797490a40075..586a59d46022 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -68,12 +68,15 @@ libperf-y += rblist.o
 libperf-y += intlist.o
 libperf-y += vdso.o
 libperf-y += stat.o
+libperf-y += stat-shadow.o
 libperf-y += record.o
 libperf-y += srcline.o
 libperf-y += data.o
 libperf-$(CONFIG_X86) += tsc.o
 libperf-y += cloexec.o
 libperf-y += thread-stack.o
+libperf-$(CONFIG_AUXTRACE) += auxtrace.o
+libperf-y += parse-branch-options.o
 
 libperf-$(CONFIG_LIBELF) += symbol-elf.o
 libperf-$(CONFIG_LIBELF) += probe-event.o
@@ -101,23 +104,23 @@ CFLAGS_exec_cmd.o += -DPERF_EXEC_PATH="BUILD_STR($(perfexecdir_SQ))" -DPREFIX="B
 
 $(OUTPUT)util/parse-events-flex.c: util/parse-events.l $(OUTPUT)util/parse-events-bison.c
 	$(call rule_mkdir)
-	@$(call echo-cmd,flex)$(FLEX) -o $@ --header-file=$(OUTPUT)util/parse-events-flex.h $(PARSER_DEBUG_FLEX) util/parse-events.l
+	$(Q)$(call echo-cmd,flex)$(FLEX) -o $@ --header-file=$(OUTPUT)util/parse-events-flex.h $(PARSER_DEBUG_FLEX) util/parse-events.l
 
 $(OUTPUT)util/parse-events-bison.c: util/parse-events.y
 	$(call rule_mkdir)
-	@$(call echo-cmd,bison)$(BISON) -v util/parse-events.y -d $(PARSER_DEBUG_BISON) -o $@ -p parse_events_
+	$(Q)$(call echo-cmd,bison)$(BISON) -v util/parse-events.y -d $(PARSER_DEBUG_BISON) -o $@ -p parse_events_
 
 $(OUTPUT)util/pmu-flex.c: util/pmu.l $(OUTPUT)util/pmu-bison.c
 	$(call rule_mkdir)
-	@$(call echo-cmd,flex)$(FLEX) -o $@ --header-file=$(OUTPUT)util/pmu-flex.h util/pmu.l
+	$(Q)$(call echo-cmd,flex)$(FLEX) -o $@ --header-file=$(OUTPUT)util/pmu-flex.h util/pmu.l
 
 $(OUTPUT)util/pmu-bison.c: util/pmu.y
 	$(call rule_mkdir)
-	@$(call echo-cmd,bison)$(BISON) -v util/pmu.y -d -o $@ -p perf_pmu_
+	$(Q)$(call echo-cmd,bison)$(BISON) -v util/pmu.y -d -o $@ -p perf_pmu_
 
 CFLAGS_parse-events-flex.o  += -w
 CFLAGS_pmu-flex.o           += -w
-CFLAGS_parse-events-bison.o += -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w
+CFLAGS_parse-events-bison.o += -DYYENABLE_NLS=0 -w
 CFLAGS_pmu-bison.o          += -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w
 
 $(OUTPUT)util/parse-events.o: $(OUTPUT)util/parse-events-flex.c $(OUTPUT)util/parse-events-bison.c
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 7f5bdfc9bc87..03b7bc70eb66 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -506,6 +506,17 @@ static int __symbol__inc_addr_samples(struct symbol *sym, struct map *map,
 	return 0;
 }
 
+static struct annotation *symbol__get_annotation(struct symbol *sym)
+{
+	struct annotation *notes = symbol__annotation(sym);
+
+	if (notes->src == NULL) {
+		if (symbol__alloc_hist(sym) < 0)
+			return NULL;
+	}
+	return notes;
+}
+
 static int symbol__inc_addr_samples(struct symbol *sym, struct map *map,
 				    int evidx, u64 addr)
 {
@@ -513,13 +524,9 @@ static int symbol__inc_addr_samples(struct symbol *sym, struct map *map,
 
 	if (sym == NULL)
 		return 0;
-
-	notes = symbol__annotation(sym);
-	if (notes->src == NULL) {
-		if (symbol__alloc_hist(sym) < 0)
-			return -ENOMEM;
-	}
-
+	notes = symbol__get_annotation(sym);
+	if (notes == NULL)
+		return -ENOMEM;
 	return __symbol__inc_addr_samples(sym, map, notes, evidx, addr);
 }
 
@@ -647,14 +654,15 @@ struct disasm_line *disasm__get_next_ip_line(struct list_head *head, struct disa
 }
 
 double disasm__calc_percent(struct annotation *notes, int evidx, s64 offset,
-			    s64 end, const char **path)
+			    s64 end, const char **path, u64 *nr_samples)
 {
 	struct source_line *src_line = notes->src->lines;
 	double percent = 0.0;
+	*nr_samples = 0;
 
 	if (src_line) {
 		size_t sizeof_src_line = sizeof(*src_line) +
-				sizeof(src_line->p) * (src_line->nr_pcnt - 1);
+				sizeof(src_line->samples) * (src_line->nr_pcnt - 1);
 
 		while (offset < end) {
 			src_line = (void *)notes->src->lines +
@@ -663,7 +671,8 @@ double disasm__calc_percent(struct annotation *notes, int evidx, s64 offset,
 			if (*path == NULL)
 				*path = src_line->path;
 
-			percent += src_line->p[evidx].percent;
+			percent += src_line->samples[evidx].percent;
+			*nr_samples += src_line->samples[evidx].nr;
 			offset++;
 		}
 	} else {
@@ -673,8 +682,10 @@ double disasm__calc_percent(struct annotation *notes, int evidx, s64 offset,
 		while (offset < end)
 			hits += h->addr[offset++];
 
-		if (h->sum)
+		if (h->sum) {
+			*nr_samples = hits;
 			percent = 100.0 * hits / h->sum;
+		}
 	}
 
 	return percent;
@@ -689,8 +700,10 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st
 
 	if (dl->offset != -1) {
 		const char *path = NULL;
+		u64 nr_samples;
 		double percent, max_percent = 0.0;
 		double *ppercents = &percent;
+		u64 *psamples = &nr_samples;
 		int i, nr_percent = 1;
 		const char *color;
 		struct annotation *notes = symbol__annotation(sym);
@@ -703,8 +716,10 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st
 		if (perf_evsel__is_group_event(evsel)) {
 			nr_percent = evsel->nr_members;
 			ppercents = calloc(nr_percent, sizeof(double));
-			if (ppercents == NULL)
+			psamples = calloc(nr_percent, sizeof(u64));
+			if (ppercents == NULL || psamples == NULL) {
 				return -1;
+			}
 		}
 
 		for (i = 0; i < nr_percent; i++) {
@@ -712,9 +727,10 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st
 					notes->src->lines ? i : evsel->idx + i,
 					offset,
 					next ? next->offset : (s64) len,
-					&path);
+					&path, &nr_samples);
 
 			ppercents[i] = percent;
+			psamples[i] = nr_samples;
 			if (percent > max_percent)
 				max_percent = percent;
 		}
@@ -752,8 +768,14 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st
 
 		for (i = 0; i < nr_percent; i++) {
 			percent = ppercents[i];
+			nr_samples = psamples[i];
 			color = get_percent_color(percent);
-			color_fprintf(stdout, color, " %7.2f", percent);
+
+			if (symbol_conf.show_total_period)
+				color_fprintf(stdout, color, " %7" PRIu64,
+					      nr_samples);
+			else
+				color_fprintf(stdout, color, " %7.2f", percent);
 		}
 
 		printf(" :	");
@@ -763,6 +785,9 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st
 		if (ppercents != &percent)
 			free(ppercents);
 
+		if (psamples != &nr_samples)
+			free(psamples);
+
 	} else if (max_lines && printed >= max_lines)
 		return 1;
 	else {
@@ -1096,7 +1121,7 @@ static void insert_source_line(struct rb_root *root, struct source_line *src_lin
 		ret = strcmp(iter->path, src_line->path);
 		if (ret == 0) {
 			for (i = 0; i < src_line->nr_pcnt; i++)
-				iter->p[i].percent_sum += src_line->p[i].percent;
+				iter->samples[i].percent_sum += src_line->samples[i].percent;
 			return;
 		}
 
@@ -1107,7 +1132,7 @@ static void insert_source_line(struct rb_root *root, struct source_line *src_lin
 	}
 
 	for (i = 0; i < src_line->nr_pcnt; i++)
-		src_line->p[i].percent_sum = src_line->p[i].percent;
+		src_line->samples[i].percent_sum = src_line->samples[i].percent;
 
 	rb_link_node(&src_line->node, parent, p);
 	rb_insert_color(&src_line->node, root);
@@ -1118,9 +1143,9 @@ static int cmp_source_line(struct source_line *a, struct source_line *b)
 	int i;
 
 	for (i = 0; i < a->nr_pcnt; i++) {
-		if (a->p[i].percent_sum == b->p[i].percent_sum)
+		if (a->samples[i].percent_sum == b->samples[i].percent_sum)
 			continue;
-		return a->p[i].percent_sum > b->p[i].percent_sum;
+		return a->samples[i].percent_sum > b->samples[i].percent_sum;
 	}
 
 	return 0;
@@ -1172,7 +1197,7 @@ static void symbol__free_source_line(struct symbol *sym, int len)
 	int i;
 
 	sizeof_src_line = sizeof(*src_line) +
-			  (sizeof(src_line->p) * (src_line->nr_pcnt - 1));
+			  (sizeof(src_line->samples) * (src_line->nr_pcnt - 1));
 
 	for (i = 0; i < len; i++) {
 		free_srcline(src_line->path);
@@ -1204,7 +1229,7 @@ static int symbol__get_source_line(struct symbol *sym, struct map *map,
 			h_sum += h->sum;
 		}
 		nr_pcnt = evsel->nr_members;
-		sizeof_src_line += (nr_pcnt - 1) * sizeof(src_line->p);
+		sizeof_src_line += (nr_pcnt - 1) * sizeof(src_line->samples);
 	}
 
 	if (!h_sum)
@@ -1224,10 +1249,10 @@ static int symbol__get_source_line(struct symbol *sym, struct map *map,
 
 		for (k = 0; k < nr_pcnt; k++) {
 			h = annotation__histogram(notes, evidx + k);
-			src_line->p[k].percent = 100.0 * h->addr[i] / h->sum;
+			src_line->samples[k].percent = 100.0 * h->addr[i] / h->sum;
 
-			if (src_line->p[k].percent > percent_max)
-				percent_max = src_line->p[k].percent;
+			if (src_line->samples[k].percent > percent_max)
+				percent_max = src_line->samples[k].percent;
 		}
 
 		if (percent_max <= 0.5)
@@ -1267,7 +1292,7 @@ static void print_summary(struct rb_root *root, const char *filename)
 
 		src_line = rb_entry(node, struct source_line, node);
 		for (i = 0; i < src_line->nr_pcnt; i++) {
-			percent = src_line->p[i].percent_sum;
+			percent = src_line->samples[i].percent_sum;
 			color = get_percent_color(percent);
 			color_fprintf(stdout, color, " %7.2f", percent);
 
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index cadbdc90a5cb..7e78e6c27078 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -72,23 +72,24 @@ struct disasm_line *disasm__get_next_ip_line(struct list_head *head, struct disa
 int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw);
 size_t disasm__fprintf(struct list_head *head, FILE *fp);
 double disasm__calc_percent(struct annotation *notes, int evidx, s64 offset,
-			    s64 end, const char **path);
+			    s64 end, const char **path, u64 *nr_samples);
 
 struct sym_hist {
 	u64		sum;
 	u64		addr[0];
 };
 
-struct source_line_percent {
+struct source_line_samples {
 	double		percent;
 	double		percent_sum;
+	double          nr;
 };
 
 struct source_line {
 	struct rb_node	node;
 	char		*path;
 	int		nr_pcnt;
-	struct source_line_percent p[1];
+	struct source_line_samples samples[1];
 };
 
 /** struct annotated_source - symbols with hits have this attached as in sannotation
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
new file mode 100644
index 000000000000..df66966cfde7
--- /dev/null
+++ b/tools/perf/util/auxtrace.c
@@ -0,0 +1,1352 @@
+/*
+ * auxtrace.c: AUX area trace support
+ * Copyright (c) 2013-2015, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#include <sys/types.h>
+#include <sys/mman.h>
+#include <stdbool.h>
+
+#include <linux/kernel.h>
+#include <linux/perf_event.h>
+#include <linux/types.h>
+#include <linux/bitops.h>
+#include <linux/log2.h>
+#include <linux/string.h>
+
+#include <sys/param.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <limits.h>
+#include <errno.h>
+#include <linux/list.h>
+
+#include "../perf.h"
+#include "util.h"
+#include "evlist.h"
+#include "cpumap.h"
+#include "thread_map.h"
+#include "asm/bug.h"
+#include "auxtrace.h"
+
+#include <linux/hash.h>
+
+#include "event.h"
+#include "session.h"
+#include "debug.h"
+#include "parse-options.h"
+
+int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
+			struct auxtrace_mmap_params *mp,
+			void *userpg, int fd)
+{
+	struct perf_event_mmap_page *pc = userpg;
+
+#if BITS_PER_LONG != 64 && !defined(HAVE_SYNC_COMPARE_AND_SWAP_SUPPORT)
+	pr_err("Cannot use AUX area tracing mmaps\n");
+	return -1;
+#endif
+
+	WARN_ONCE(mm->base, "Uninitialized auxtrace_mmap\n");
+
+	mm->userpg = userpg;
+	mm->mask = mp->mask;
+	mm->len = mp->len;
+	mm->prev = 0;
+	mm->idx = mp->idx;
+	mm->tid = mp->tid;
+	mm->cpu = mp->cpu;
+
+	if (!mp->len) {
+		mm->base = NULL;
+		return 0;
+	}
+
+	pc->aux_offset = mp->offset;
+	pc->aux_size = mp->len;
+
+	mm->base = mmap(NULL, mp->len, mp->prot, MAP_SHARED, fd, mp->offset);
+	if (mm->base == MAP_FAILED) {
+		pr_debug2("failed to mmap AUX area\n");
+		mm->base = NULL;
+		return -1;
+	}
+
+	return 0;
+}
+
+void auxtrace_mmap__munmap(struct auxtrace_mmap *mm)
+{
+	if (mm->base) {
+		munmap(mm->base, mm->len);
+		mm->base = NULL;
+	}
+}
+
+void auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp,
+				off_t auxtrace_offset,
+				unsigned int auxtrace_pages,
+				bool auxtrace_overwrite)
+{
+	if (auxtrace_pages) {
+		mp->offset = auxtrace_offset;
+		mp->len = auxtrace_pages * (size_t)page_size;
+		mp->mask = is_power_of_2(mp->len) ? mp->len - 1 : 0;
+		mp->prot = PROT_READ | (auxtrace_overwrite ? 0 : PROT_WRITE);
+		pr_debug2("AUX area mmap length %zu\n", mp->len);
+	} else {
+		mp->len = 0;
+	}
+}
+
+void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
+				   struct perf_evlist *evlist, int idx,
+				   bool per_cpu)
+{
+	mp->idx = idx;
+
+	if (per_cpu) {
+		mp->cpu = evlist->cpus->map[idx];
+		if (evlist->threads)
+			mp->tid = evlist->threads->map[0];
+		else
+			mp->tid = -1;
+	} else {
+		mp->cpu = -1;
+		mp->tid = evlist->threads->map[idx];
+	}
+}
+
+#define AUXTRACE_INIT_NR_QUEUES	32
+
+static struct auxtrace_queue *auxtrace_alloc_queue_array(unsigned int nr_queues)
+{
+	struct auxtrace_queue *queue_array;
+	unsigned int max_nr_queues, i;
+
+	max_nr_queues = UINT_MAX / sizeof(struct auxtrace_queue);
+	if (nr_queues > max_nr_queues)
+		return NULL;
+
+	queue_array = calloc(nr_queues, sizeof(struct auxtrace_queue));
+	if (!queue_array)
+		return NULL;
+
+	for (i = 0; i < nr_queues; i++) {
+		INIT_LIST_HEAD(&queue_array[i].head);
+		queue_array[i].priv = NULL;
+	}
+
+	return queue_array;
+}
+
+int auxtrace_queues__init(struct auxtrace_queues *queues)
+{
+	queues->nr_queues = AUXTRACE_INIT_NR_QUEUES;
+	queues->queue_array = auxtrace_alloc_queue_array(queues->nr_queues);
+	if (!queues->queue_array)
+		return -ENOMEM;
+	return 0;
+}
+
+static int auxtrace_queues__grow(struct auxtrace_queues *queues,
+				 unsigned int new_nr_queues)
+{
+	unsigned int nr_queues = queues->nr_queues;
+	struct auxtrace_queue *queue_array;
+	unsigned int i;
+
+	if (!nr_queues)
+		nr_queues = AUXTRACE_INIT_NR_QUEUES;
+
+	while (nr_queues && nr_queues < new_nr_queues)
+		nr_queues <<= 1;
+
+	if (nr_queues < queues->nr_queues || nr_queues < new_nr_queues)
+		return -EINVAL;
+
+	queue_array = auxtrace_alloc_queue_array(nr_queues);
+	if (!queue_array)
+		return -ENOMEM;
+
+	for (i = 0; i < queues->nr_queues; i++) {
+		list_splice_tail(&queues->queue_array[i].head,
+				 &queue_array[i].head);
+		queue_array[i].priv = queues->queue_array[i].priv;
+	}
+
+	queues->nr_queues = nr_queues;
+	queues->queue_array = queue_array;
+
+	return 0;
+}
+
+static void *auxtrace_copy_data(u64 size, struct perf_session *session)
+{
+	int fd = perf_data_file__fd(session->file);
+	void *p;
+	ssize_t ret;
+
+	if (size > SSIZE_MAX)
+		return NULL;
+
+	p = malloc(size);
+	if (!p)
+		return NULL;
+
+	ret = readn(fd, p, size);
+	if (ret != (ssize_t)size) {
+		free(p);
+		return NULL;
+	}
+
+	return p;
+}
+
+static int auxtrace_queues__add_buffer(struct auxtrace_queues *queues,
+				       unsigned int idx,
+				       struct auxtrace_buffer *buffer)
+{
+	struct auxtrace_queue *queue;
+	int err;
+
+	if (idx >= queues->nr_queues) {
+		err = auxtrace_queues__grow(queues, idx + 1);
+		if (err)
+			return err;
+	}
+
+	queue = &queues->queue_array[idx];
+
+	if (!queue->set) {
+		queue->set = true;
+		queue->tid = buffer->tid;
+		queue->cpu = buffer->cpu;
+	} else if (buffer->cpu != queue->cpu || buffer->tid != queue->tid) {
+		pr_err("auxtrace queue conflict: cpu %d, tid %d vs cpu %d, tid %d\n",
+		       queue->cpu, queue->tid, buffer->cpu, buffer->tid);
+		return -EINVAL;
+	}
+
+	buffer->buffer_nr = queues->next_buffer_nr++;
+
+	list_add_tail(&buffer->list, &queue->head);
+
+	queues->new_data = true;
+	queues->populated = true;
+
+	return 0;
+}
+
+/* Limit buffers to 32MiB on 32-bit */
+#define BUFFER_LIMIT_FOR_32_BIT (32 * 1024 * 1024)
+
+static int auxtrace_queues__split_buffer(struct auxtrace_queues *queues,
+					 unsigned int idx,
+					 struct auxtrace_buffer *buffer)
+{
+	u64 sz = buffer->size;
+	bool consecutive = false;
+	struct auxtrace_buffer *b;
+	int err;
+
+	while (sz > BUFFER_LIMIT_FOR_32_BIT) {
+		b = memdup(buffer, sizeof(struct auxtrace_buffer));
+		if (!b)
+			return -ENOMEM;
+		b->size = BUFFER_LIMIT_FOR_32_BIT;
+		b->consecutive = consecutive;
+		err = auxtrace_queues__add_buffer(queues, idx, b);
+		if (err) {
+			auxtrace_buffer__free(b);
+			return err;
+		}
+		buffer->data_offset += BUFFER_LIMIT_FOR_32_BIT;
+		sz -= BUFFER_LIMIT_FOR_32_BIT;
+		consecutive = true;
+	}
+
+	buffer->size = sz;
+	buffer->consecutive = consecutive;
+
+	return 0;
+}
+
+static int auxtrace_queues__add_event_buffer(struct auxtrace_queues *queues,
+					     struct perf_session *session,
+					     unsigned int idx,
+					     struct auxtrace_buffer *buffer)
+{
+	if (session->one_mmap) {
+		buffer->data = buffer->data_offset - session->one_mmap_offset +
+			       session->one_mmap_addr;
+	} else if (perf_data_file__is_pipe(session->file)) {
+		buffer->data = auxtrace_copy_data(buffer->size, session);
+		if (!buffer->data)
+			return -ENOMEM;
+		buffer->data_needs_freeing = true;
+	} else if (BITS_PER_LONG == 32 &&
+		   buffer->size > BUFFER_LIMIT_FOR_32_BIT) {
+		int err;
+
+		err = auxtrace_queues__split_buffer(queues, idx, buffer);
+		if (err)
+			return err;
+	}
+
+	return auxtrace_queues__add_buffer(queues, idx, buffer);
+}
+
+int auxtrace_queues__add_event(struct auxtrace_queues *queues,
+			       struct perf_session *session,
+			       union perf_event *event, off_t data_offset,
+			       struct auxtrace_buffer **buffer_ptr)
+{
+	struct auxtrace_buffer *buffer;
+	unsigned int idx;
+	int err;
+
+	buffer = zalloc(sizeof(struct auxtrace_buffer));
+	if (!buffer)
+		return -ENOMEM;
+
+	buffer->pid = -1;
+	buffer->tid = event->auxtrace.tid;
+	buffer->cpu = event->auxtrace.cpu;
+	buffer->data_offset = data_offset;
+	buffer->offset = event->auxtrace.offset;
+	buffer->reference = event->auxtrace.reference;
+	buffer->size = event->auxtrace.size;
+	idx = event->auxtrace.idx;
+
+	err = auxtrace_queues__add_event_buffer(queues, session, idx, buffer);
+	if (err)
+		goto out_err;
+
+	if (buffer_ptr)
+		*buffer_ptr = buffer;
+
+	return 0;
+
+out_err:
+	auxtrace_buffer__free(buffer);
+	return err;
+}
+
+static int auxtrace_queues__add_indexed_event(struct auxtrace_queues *queues,
+					      struct perf_session *session,
+					      off_t file_offset, size_t sz)
+{
+	union perf_event *event;
+	int err;
+	char buf[PERF_SAMPLE_MAX_SIZE];
+
+	err = perf_session__peek_event(session, file_offset, buf,
+				       PERF_SAMPLE_MAX_SIZE, &event, NULL);
+	if (err)
+		return err;
+
+	if (event->header.type == PERF_RECORD_AUXTRACE) {
+		if (event->header.size < sizeof(struct auxtrace_event) ||
+		    event->header.size != sz) {
+			err = -EINVAL;
+			goto out;
+		}
+		file_offset += event->header.size;
+		err = auxtrace_queues__add_event(queues, session, event,
+						 file_offset, NULL);
+	}
+out:
+	return err;
+}
+
+void auxtrace_queues__free(struct auxtrace_queues *queues)
+{
+	unsigned int i;
+
+	for (i = 0; i < queues->nr_queues; i++) {
+		while (!list_empty(&queues->queue_array[i].head)) {
+			struct auxtrace_buffer *buffer;
+
+			buffer = list_entry(queues->queue_array[i].head.next,
+					    struct auxtrace_buffer, list);
+			list_del(&buffer->list);
+			auxtrace_buffer__free(buffer);
+		}
+	}
+
+	zfree(&queues->queue_array);
+	queues->nr_queues = 0;
+}
+
+static void auxtrace_heapify(struct auxtrace_heap_item *heap_array,
+			     unsigned int pos, unsigned int queue_nr,
+			     u64 ordinal)
+{
+	unsigned int parent;
+
+	while (pos) {
+		parent = (pos - 1) >> 1;
+		if (heap_array[parent].ordinal <= ordinal)
+			break;
+		heap_array[pos] = heap_array[parent];
+		pos = parent;
+	}
+	heap_array[pos].queue_nr = queue_nr;
+	heap_array[pos].ordinal = ordinal;
+}
+
+int auxtrace_heap__add(struct auxtrace_heap *heap, unsigned int queue_nr,
+		       u64 ordinal)
+{
+	struct auxtrace_heap_item *heap_array;
+
+	if (queue_nr >= heap->heap_sz) {
+		unsigned int heap_sz = AUXTRACE_INIT_NR_QUEUES;
+
+		while (heap_sz <= queue_nr)
+			heap_sz <<= 1;
+		heap_array = realloc(heap->heap_array,
+				     heap_sz * sizeof(struct auxtrace_heap_item));
+		if (!heap_array)
+			return -ENOMEM;
+		heap->heap_array = heap_array;
+		heap->heap_sz = heap_sz;
+	}
+
+	auxtrace_heapify(heap->heap_array, heap->heap_cnt++, queue_nr, ordinal);
+
+	return 0;
+}
+
+void auxtrace_heap__free(struct auxtrace_heap *heap)
+{
+	zfree(&heap->heap_array);
+	heap->heap_cnt = 0;
+	heap->heap_sz = 0;
+}
+
+void auxtrace_heap__pop(struct auxtrace_heap *heap)
+{
+	unsigned int pos, last, heap_cnt = heap->heap_cnt;
+	struct auxtrace_heap_item *heap_array;
+
+	if (!heap_cnt)
+		return;
+
+	heap->heap_cnt -= 1;
+
+	heap_array = heap->heap_array;
+
+	pos = 0;
+	while (1) {
+		unsigned int left, right;
+
+		left = (pos << 1) + 1;
+		if (left >= heap_cnt)
+			break;
+		right = left + 1;
+		if (right >= heap_cnt) {
+			heap_array[pos] = heap_array[left];
+			return;
+		}
+		if (heap_array[left].ordinal < heap_array[right].ordinal) {
+			heap_array[pos] = heap_array[left];
+			pos = left;
+		} else {
+			heap_array[pos] = heap_array[right];
+			pos = right;
+		}
+	}
+
+	last = heap_cnt - 1;
+	auxtrace_heapify(heap_array, pos, heap_array[last].queue_nr,
+			 heap_array[last].ordinal);
+}
+
+size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr)
+{
+	if (itr)
+		return itr->info_priv_size(itr);
+	return 0;
+}
+
+static int auxtrace_not_supported(void)
+{
+	pr_err("AUX area tracing is not supported on this architecture\n");
+	return -EINVAL;
+}
+
+int auxtrace_record__info_fill(struct auxtrace_record *itr,
+			       struct perf_session *session,
+			       struct auxtrace_info_event *auxtrace_info,
+			       size_t priv_size)
+{
+	if (itr)
+		return itr->info_fill(itr, session, auxtrace_info, priv_size);
+	return auxtrace_not_supported();
+}
+
+void auxtrace_record__free(struct auxtrace_record *itr)
+{
+	if (itr)
+		itr->free(itr);
+}
+
+int auxtrace_record__snapshot_start(struct auxtrace_record *itr)
+{
+	if (itr && itr->snapshot_start)
+		return itr->snapshot_start(itr);
+	return 0;
+}
+
+int auxtrace_record__snapshot_finish(struct auxtrace_record *itr)
+{
+	if (itr && itr->snapshot_finish)
+		return itr->snapshot_finish(itr);
+	return 0;
+}
+
+int auxtrace_record__find_snapshot(struct auxtrace_record *itr, int idx,
+				   struct auxtrace_mmap *mm,
+				   unsigned char *data, u64 *head, u64 *old)
+{
+	if (itr && itr->find_snapshot)
+		return itr->find_snapshot(itr, idx, mm, data, head, old);
+	return 0;
+}
+
+int auxtrace_record__options(struct auxtrace_record *itr,
+			     struct perf_evlist *evlist,
+			     struct record_opts *opts)
+{
+	if (itr)
+		return itr->recording_options(itr, evlist, opts);
+	return 0;
+}
+
+u64 auxtrace_record__reference(struct auxtrace_record *itr)
+{
+	if (itr)
+		return itr->reference(itr);
+	return 0;
+}
+
+int auxtrace_parse_snapshot_options(struct auxtrace_record *itr,
+				    struct record_opts *opts, const char *str)
+{
+	if (!str)
+		return 0;
+
+	if (itr)
+		return itr->parse_snapshot_options(itr, opts, str);
+
+	pr_err("No AUX area tracing to snapshot\n");
+	return -EINVAL;
+}
+
+struct auxtrace_record *__weak
+auxtrace_record__init(struct perf_evlist *evlist __maybe_unused, int *err)
+{
+	*err = 0;
+	return NULL;
+}
+
+static int auxtrace_index__alloc(struct list_head *head)
+{
+	struct auxtrace_index *auxtrace_index;
+
+	auxtrace_index = malloc(sizeof(struct auxtrace_index));
+	if (!auxtrace_index)
+		return -ENOMEM;
+
+	auxtrace_index->nr = 0;
+	INIT_LIST_HEAD(&auxtrace_index->list);
+
+	list_add_tail(&auxtrace_index->list, head);
+
+	return 0;
+}
+
+void auxtrace_index__free(struct list_head *head)
+{
+	struct auxtrace_index *auxtrace_index, *n;
+
+	list_for_each_entry_safe(auxtrace_index, n, head, list) {
+		list_del(&auxtrace_index->list);
+		free(auxtrace_index);
+	}
+}
+
+static struct auxtrace_index *auxtrace_index__last(struct list_head *head)
+{
+	struct auxtrace_index *auxtrace_index;
+	int err;
+
+	if (list_empty(head)) {
+		err = auxtrace_index__alloc(head);
+		if (err)
+			return NULL;
+	}
+
+	auxtrace_index = list_entry(head->prev, struct auxtrace_index, list);
+
+	if (auxtrace_index->nr >= PERF_AUXTRACE_INDEX_ENTRY_COUNT) {
+		err = auxtrace_index__alloc(head);
+		if (err)
+			return NULL;
+		auxtrace_index = list_entry(head->prev, struct auxtrace_index,
+					    list);
+	}
+
+	return auxtrace_index;
+}
+
+int auxtrace_index__auxtrace_event(struct list_head *head,
+				   union perf_event *event, off_t file_offset)
+{
+	struct auxtrace_index *auxtrace_index;
+	size_t nr;
+
+	auxtrace_index = auxtrace_index__last(head);
+	if (!auxtrace_index)
+		return -ENOMEM;
+
+	nr = auxtrace_index->nr;
+	auxtrace_index->entries[nr].file_offset = file_offset;
+	auxtrace_index->entries[nr].sz = event->header.size;
+	auxtrace_index->nr += 1;
+
+	return 0;
+}
+
+static int auxtrace_index__do_write(int fd,
+				    struct auxtrace_index *auxtrace_index)
+{
+	struct auxtrace_index_entry ent;
+	size_t i;
+
+	for (i = 0; i < auxtrace_index->nr; i++) {
+		ent.file_offset = auxtrace_index->entries[i].file_offset;
+		ent.sz = auxtrace_index->entries[i].sz;
+		if (writen(fd, &ent, sizeof(ent)) != sizeof(ent))
+			return -errno;
+	}
+	return 0;
+}
+
+int auxtrace_index__write(int fd, struct list_head *head)
+{
+	struct auxtrace_index *auxtrace_index;
+	u64 total = 0;
+	int err;
+
+	list_for_each_entry(auxtrace_index, head, list)
+		total += auxtrace_index->nr;
+
+	if (writen(fd, &total, sizeof(total)) != sizeof(total))
+		return -errno;
+
+	list_for_each_entry(auxtrace_index, head, list) {
+		err = auxtrace_index__do_write(fd, auxtrace_index);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int auxtrace_index__process_entry(int fd, struct list_head *head,
+					 bool needs_swap)
+{
+	struct auxtrace_index *auxtrace_index;
+	struct auxtrace_index_entry ent;
+	size_t nr;
+
+	if (readn(fd, &ent, sizeof(ent)) != sizeof(ent))
+		return -1;
+
+	auxtrace_index = auxtrace_index__last(head);
+	if (!auxtrace_index)
+		return -1;
+
+	nr = auxtrace_index->nr;
+	if (needs_swap) {
+		auxtrace_index->entries[nr].file_offset =
+						bswap_64(ent.file_offset);
+		auxtrace_index->entries[nr].sz = bswap_64(ent.sz);
+	} else {
+		auxtrace_index->entries[nr].file_offset = ent.file_offset;
+		auxtrace_index->entries[nr].sz = ent.sz;
+	}
+
+	auxtrace_index->nr = nr + 1;
+
+	return 0;
+}
+
+int auxtrace_index__process(int fd, u64 size, struct perf_session *session,
+			    bool needs_swap)
+{
+	struct list_head *head = &session->auxtrace_index;
+	u64 nr;
+
+	if (readn(fd, &nr, sizeof(u64)) != sizeof(u64))
+		return -1;
+
+	if (needs_swap)
+		nr = bswap_64(nr);
+
+	if (sizeof(u64) + nr * sizeof(struct auxtrace_index_entry) > size)
+		return -1;
+
+	while (nr--) {
+		int err;
+
+		err = auxtrace_index__process_entry(fd, head, needs_swap);
+		if (err)
+			return -1;
+	}
+
+	return 0;
+}
+
+static int auxtrace_queues__process_index_entry(struct auxtrace_queues *queues,
+						struct perf_session *session,
+						struct auxtrace_index_entry *ent)
+{
+	return auxtrace_queues__add_indexed_event(queues, session,
+						  ent->file_offset, ent->sz);
+}
+
+int auxtrace_queues__process_index(struct auxtrace_queues *queues,
+				   struct perf_session *session)
+{
+	struct auxtrace_index *auxtrace_index;
+	struct auxtrace_index_entry *ent;
+	size_t i;
+	int err;
+
+	list_for_each_entry(auxtrace_index, &session->auxtrace_index, list) {
+		for (i = 0; i < auxtrace_index->nr; i++) {
+			ent = &auxtrace_index->entries[i];
+			err = auxtrace_queues__process_index_entry(queues,
+								   session,
+								   ent);
+			if (err)
+				return err;
+		}
+	}
+	return 0;
+}
+
+struct auxtrace_buffer *auxtrace_buffer__next(struct auxtrace_queue *queue,
+					      struct auxtrace_buffer *buffer)
+{
+	if (buffer) {
+		if (list_is_last(&buffer->list, &queue->head))
+			return NULL;
+		return list_entry(buffer->list.next, struct auxtrace_buffer,
+				  list);
+	} else {
+		if (list_empty(&queue->head))
+			return NULL;
+		return list_entry(queue->head.next, struct auxtrace_buffer,
+				  list);
+	}
+}
+
+void *auxtrace_buffer__get_data(struct auxtrace_buffer *buffer, int fd)
+{
+	size_t adj = buffer->data_offset & (page_size - 1);
+	size_t size = buffer->size + adj;
+	off_t file_offset = buffer->data_offset - adj;
+	void *addr;
+
+	if (buffer->data)
+		return buffer->data;
+
+	addr = mmap(NULL, size, PROT_READ, MAP_SHARED, fd, file_offset);
+	if (addr == MAP_FAILED)
+		return NULL;
+
+	buffer->mmap_addr = addr;
+	buffer->mmap_size = size;
+
+	buffer->data = addr + adj;
+
+	return buffer->data;
+}
+
+void auxtrace_buffer__put_data(struct auxtrace_buffer *buffer)
+{
+	if (!buffer->data || !buffer->mmap_addr)
+		return;
+	munmap(buffer->mmap_addr, buffer->mmap_size);
+	buffer->mmap_addr = NULL;
+	buffer->mmap_size = 0;
+	buffer->data = NULL;
+	buffer->use_data = NULL;
+}
+
+void auxtrace_buffer__drop_data(struct auxtrace_buffer *buffer)
+{
+	auxtrace_buffer__put_data(buffer);
+	if (buffer->data_needs_freeing) {
+		buffer->data_needs_freeing = false;
+		zfree(&buffer->data);
+		buffer->use_data = NULL;
+		buffer->size = 0;
+	}
+}
+
+void auxtrace_buffer__free(struct auxtrace_buffer *buffer)
+{
+	auxtrace_buffer__drop_data(buffer);
+	free(buffer);
+}
+
+void auxtrace_synth_error(struct auxtrace_error_event *auxtrace_error, int type,
+			  int code, int cpu, pid_t pid, pid_t tid, u64 ip,
+			  const char *msg)
+{
+	size_t size;
+
+	memset(auxtrace_error, 0, sizeof(struct auxtrace_error_event));
+
+	auxtrace_error->header.type = PERF_RECORD_AUXTRACE_ERROR;
+	auxtrace_error->type = type;
+	auxtrace_error->code = code;
+	auxtrace_error->cpu = cpu;
+	auxtrace_error->pid = pid;
+	auxtrace_error->tid = tid;
+	auxtrace_error->ip = ip;
+	strlcpy(auxtrace_error->msg, msg, MAX_AUXTRACE_ERROR_MSG);
+
+	size = (void *)auxtrace_error->msg - (void *)auxtrace_error +
+	       strlen(auxtrace_error->msg) + 1;
+	auxtrace_error->header.size = PERF_ALIGN(size, sizeof(u64));
+}
+
+int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr,
+					 struct perf_tool *tool,
+					 struct perf_session *session,
+					 perf_event__handler_t process)
+{
+	union perf_event *ev;
+	size_t priv_size;
+	int err;
+
+	pr_debug2("Synthesizing auxtrace information\n");
+	priv_size = auxtrace_record__info_priv_size(itr);
+	ev = zalloc(sizeof(struct auxtrace_info_event) + priv_size);
+	if (!ev)
+		return -ENOMEM;
+
+	ev->auxtrace_info.header.type = PERF_RECORD_AUXTRACE_INFO;
+	ev->auxtrace_info.header.size = sizeof(struct auxtrace_info_event) +
+					priv_size;
+	err = auxtrace_record__info_fill(itr, session, &ev->auxtrace_info,
+					 priv_size);
+	if (err)
+		goto out_free;
+
+	err = process(tool, ev, NULL, NULL);
+out_free:
+	free(ev);
+	return err;
+}
+
+static bool auxtrace__dont_decode(struct perf_session *session)
+{
+	return !session->itrace_synth_opts ||
+	       session->itrace_synth_opts->dont_decode;
+}
+
+int perf_event__process_auxtrace_info(struct perf_tool *tool __maybe_unused,
+				      union perf_event *event,
+				      struct perf_session *session __maybe_unused)
+{
+	enum auxtrace_type type = event->auxtrace_info.type;
+
+	if (dump_trace)
+		fprintf(stdout, " type: %u\n", type);
+
+	switch (type) {
+	case PERF_AUXTRACE_UNKNOWN:
+	default:
+		return -EINVAL;
+	}
+}
+
+s64 perf_event__process_auxtrace(struct perf_tool *tool,
+				 union perf_event *event,
+				 struct perf_session *session)
+{
+	s64 err;
+
+	if (dump_trace)
+		fprintf(stdout, " size: %#"PRIx64"  offset: %#"PRIx64"  ref: %#"PRIx64"  idx: %u  tid: %d  cpu: %d\n",
+			event->auxtrace.size, event->auxtrace.offset,
+			event->auxtrace.reference, event->auxtrace.idx,
+			event->auxtrace.tid, event->auxtrace.cpu);
+
+	if (auxtrace__dont_decode(session))
+		return event->auxtrace.size;
+
+	if (!session->auxtrace || event->header.type != PERF_RECORD_AUXTRACE)
+		return -EINVAL;
+
+	err = session->auxtrace->process_auxtrace_event(session, event, tool);
+	if (err < 0)
+		return err;
+
+	return event->auxtrace.size;
+}
+
+#define PERF_ITRACE_DEFAULT_PERIOD_TYPE		PERF_ITRACE_PERIOD_NANOSECS
+#define PERF_ITRACE_DEFAULT_PERIOD		100000
+#define PERF_ITRACE_DEFAULT_CALLCHAIN_SZ	16
+#define PERF_ITRACE_MAX_CALLCHAIN_SZ		1024
+
+void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts)
+{
+	synth_opts->instructions = true;
+	synth_opts->branches = true;
+	synth_opts->transactions = true;
+	synth_opts->errors = true;
+	synth_opts->period_type = PERF_ITRACE_DEFAULT_PERIOD_TYPE;
+	synth_opts->period = PERF_ITRACE_DEFAULT_PERIOD;
+	synth_opts->callchain_sz = PERF_ITRACE_DEFAULT_CALLCHAIN_SZ;
+}
+
+/*
+ * Please check tools/perf/Documentation/perf-script.txt for information
+ * about the options parsed here, which is introduced after this cset,
+ * when support in 'perf script' for these options is introduced.
+ */
+int itrace_parse_synth_opts(const struct option *opt, const char *str,
+			    int unset)
+{
+	struct itrace_synth_opts *synth_opts = opt->value;
+	const char *p;
+	char *endptr;
+
+	synth_opts->set = true;
+
+	if (unset) {
+		synth_opts->dont_decode = true;
+		return 0;
+	}
+
+	if (!str) {
+		itrace_synth_opts__set_default(synth_opts);
+		return 0;
+	}
+
+	for (p = str; *p;) {
+		switch (*p++) {
+		case 'i':
+			synth_opts->instructions = true;
+			while (*p == ' ' || *p == ',')
+				p += 1;
+			if (isdigit(*p)) {
+				synth_opts->period = strtoull(p, &endptr, 10);
+				p = endptr;
+				while (*p == ' ' || *p == ',')
+					p += 1;
+				switch (*p++) {
+				case 'i':
+					synth_opts->period_type =
+						PERF_ITRACE_PERIOD_INSTRUCTIONS;
+					break;
+				case 't':
+					synth_opts->period_type =
+						PERF_ITRACE_PERIOD_TICKS;
+					break;
+				case 'm':
+					synth_opts->period *= 1000;
+					/* Fall through */
+				case 'u':
+					synth_opts->period *= 1000;
+					/* Fall through */
+				case 'n':
+					if (*p++ != 's')
+						goto out_err;
+					synth_opts->period_type =
+						PERF_ITRACE_PERIOD_NANOSECS;
+					break;
+				case '\0':
+					goto out;
+				default:
+					goto out_err;
+				}
+			}
+			break;
+		case 'b':
+			synth_opts->branches = true;
+			break;
+		case 'x':
+			synth_opts->transactions = true;
+			break;
+		case 'e':
+			synth_opts->errors = true;
+			break;
+		case 'd':
+			synth_opts->log = true;
+			break;
+		case 'c':
+			synth_opts->branches = true;
+			synth_opts->calls = true;
+			break;
+		case 'r':
+			synth_opts->branches = true;
+			synth_opts->returns = true;
+			break;
+		case 'g':
+			synth_opts->callchain = true;
+			synth_opts->callchain_sz =
+					PERF_ITRACE_DEFAULT_CALLCHAIN_SZ;
+			while (*p == ' ' || *p == ',')
+				p += 1;
+			if (isdigit(*p)) {
+				unsigned int val;
+
+				val = strtoul(p, &endptr, 10);
+				p = endptr;
+				if (!val || val > PERF_ITRACE_MAX_CALLCHAIN_SZ)
+					goto out_err;
+				synth_opts->callchain_sz = val;
+			}
+			break;
+		case ' ':
+		case ',':
+			break;
+		default:
+			goto out_err;
+		}
+	}
+out:
+	if (synth_opts->instructions) {
+		if (!synth_opts->period_type)
+			synth_opts->period_type =
+					PERF_ITRACE_DEFAULT_PERIOD_TYPE;
+		if (!synth_opts->period)
+			synth_opts->period = PERF_ITRACE_DEFAULT_PERIOD;
+	}
+
+	return 0;
+
+out_err:
+	pr_err("Bad Instruction Tracing options '%s'\n", str);
+	return -EINVAL;
+}
+
+static const char * const auxtrace_error_type_name[] = {
+	[PERF_AUXTRACE_ERROR_ITRACE] = "instruction trace",
+};
+
+static const char *auxtrace_error_name(int type)
+{
+	const char *error_type_name = NULL;
+
+	if (type < PERF_AUXTRACE_ERROR_MAX)
+		error_type_name = auxtrace_error_type_name[type];
+	if (!error_type_name)
+		error_type_name = "unknown AUX";
+	return error_type_name;
+}
+
+size_t perf_event__fprintf_auxtrace_error(union perf_event *event, FILE *fp)
+{
+	struct auxtrace_error_event *e = &event->auxtrace_error;
+	int ret;
+
+	ret = fprintf(fp, " %s error type %u",
+		      auxtrace_error_name(e->type), e->type);
+	ret += fprintf(fp, " cpu %d pid %d tid %d ip %#"PRIx64" code %u: %s\n",
+		       e->cpu, e->pid, e->tid, e->ip, e->code, e->msg);
+	return ret;
+}
+
+void perf_session__auxtrace_error_inc(struct perf_session *session,
+				      union perf_event *event)
+{
+	struct auxtrace_error_event *e = &event->auxtrace_error;
+
+	if (e->type < PERF_AUXTRACE_ERROR_MAX)
+		session->evlist->stats.nr_auxtrace_errors[e->type] += 1;
+}
+
+void events_stats__auxtrace_error_warn(const struct events_stats *stats)
+{
+	int i;
+
+	for (i = 0; i < PERF_AUXTRACE_ERROR_MAX; i++) {
+		if (!stats->nr_auxtrace_errors[i])
+			continue;
+		ui__warning("%u %s errors\n",
+			    stats->nr_auxtrace_errors[i],
+			    auxtrace_error_name(i));
+	}
+}
+
+int perf_event__process_auxtrace_error(struct perf_tool *tool __maybe_unused,
+				       union perf_event *event,
+				       struct perf_session *session)
+{
+	if (auxtrace__dont_decode(session))
+		return 0;
+
+	perf_event__fprintf_auxtrace_error(event, stdout);
+	return 0;
+}
+
+static int __auxtrace_mmap__read(struct auxtrace_mmap *mm,
+				 struct auxtrace_record *itr,
+				 struct perf_tool *tool, process_auxtrace_t fn,
+				 bool snapshot, size_t snapshot_size)
+{
+	u64 head, old = mm->prev, offset, ref;
+	unsigned char *data = mm->base;
+	size_t size, head_off, old_off, len1, len2, padding;
+	union perf_event ev;
+	void *data1, *data2;
+
+	if (snapshot) {
+		head = auxtrace_mmap__read_snapshot_head(mm);
+		if (auxtrace_record__find_snapshot(itr, mm->idx, mm, data,
+						   &head, &old))
+			return -1;
+	} else {
+		head = auxtrace_mmap__read_head(mm);
+	}
+
+	if (old == head)
+		return 0;
+
+	pr_debug3("auxtrace idx %d old %#"PRIx64" head %#"PRIx64" diff %#"PRIx64"\n",
+		  mm->idx, old, head, head - old);
+
+	if (mm->mask) {
+		head_off = head & mm->mask;
+		old_off = old & mm->mask;
+	} else {
+		head_off = head % mm->len;
+		old_off = old % mm->len;
+	}
+
+	if (head_off > old_off)
+		size = head_off - old_off;
+	else
+		size = mm->len - (old_off - head_off);
+
+	if (snapshot && size > snapshot_size)
+		size = snapshot_size;
+
+	ref = auxtrace_record__reference(itr);
+
+	if (head > old || size <= head || mm->mask) {
+		offset = head - size;
+	} else {
+		/*
+		 * When the buffer size is not a power of 2, 'head' wraps at the
+		 * highest multiple of the buffer size, so we have to subtract
+		 * the remainder here.
+		 */
+		u64 rem = (0ULL - mm->len) % mm->len;
+
+		offset = head - size - rem;
+	}
+
+	if (size > head_off) {
+		len1 = size - head_off;
+		data1 = &data[mm->len - len1];
+		len2 = head_off;
+		data2 = &data[0];
+	} else {
+		len1 = size;
+		data1 = &data[head_off - len1];
+		len2 = 0;
+		data2 = NULL;
+	}
+
+	/* padding must be written by fn() e.g. record__process_auxtrace() */
+	padding = size & 7;
+	if (padding)
+		padding = 8 - padding;
+
+	memset(&ev, 0, sizeof(ev));
+	ev.auxtrace.header.type = PERF_RECORD_AUXTRACE;
+	ev.auxtrace.header.size = sizeof(ev.auxtrace);
+	ev.auxtrace.size = size + padding;
+	ev.auxtrace.offset = offset;
+	ev.auxtrace.reference = ref;
+	ev.auxtrace.idx = mm->idx;
+	ev.auxtrace.tid = mm->tid;
+	ev.auxtrace.cpu = mm->cpu;
+
+	if (fn(tool, &ev, data1, len1, data2, len2))
+		return -1;
+
+	mm->prev = head;
+
+	if (!snapshot) {
+		auxtrace_mmap__write_tail(mm, head);
+		if (itr->read_finish) {
+			int err;
+
+			err = itr->read_finish(itr, mm->idx);
+			if (err < 0)
+				return err;
+		}
+	}
+
+	return 1;
+}
+
+int auxtrace_mmap__read(struct auxtrace_mmap *mm, struct auxtrace_record *itr,
+			struct perf_tool *tool, process_auxtrace_t fn)
+{
+	return __auxtrace_mmap__read(mm, itr, tool, fn, false, 0);
+}
+
+int auxtrace_mmap__read_snapshot(struct auxtrace_mmap *mm,
+				 struct auxtrace_record *itr,
+				 struct perf_tool *tool, process_auxtrace_t fn,
+				 size_t snapshot_size)
+{
+	return __auxtrace_mmap__read(mm, itr, tool, fn, true, snapshot_size);
+}
+
+/**
+ * struct auxtrace_cache - hash table to implement a cache
+ * @hashtable: the hashtable
+ * @sz: hashtable size (number of hlists)
+ * @entry_size: size of an entry
+ * @limit: limit the number of entries to this maximum, when reached the cache
+ *         is dropped and caching begins again with an empty cache
+ * @cnt: current number of entries
+ * @bits: hashtable size (@sz = 2^@bits)
+ */
+struct auxtrace_cache {
+	struct hlist_head *hashtable;
+	size_t sz;
+	size_t entry_size;
+	size_t limit;
+	size_t cnt;
+	unsigned int bits;
+};
+
+struct auxtrace_cache *auxtrace_cache__new(unsigned int bits, size_t entry_size,
+					   unsigned int limit_percent)
+{
+	struct auxtrace_cache *c;
+	struct hlist_head *ht;
+	size_t sz, i;
+
+	c = zalloc(sizeof(struct auxtrace_cache));
+	if (!c)
+		return NULL;
+
+	sz = 1UL << bits;
+
+	ht = calloc(sz, sizeof(struct hlist_head));
+	if (!ht)
+		goto out_free;
+
+	for (i = 0; i < sz; i++)
+		INIT_HLIST_HEAD(&ht[i]);
+
+	c->hashtable = ht;
+	c->sz = sz;
+	c->entry_size = entry_size;
+	c->limit = (c->sz * limit_percent) / 100;
+	c->bits = bits;
+
+	return c;
+
+out_free:
+	free(c);
+	return NULL;
+}
+
+static void auxtrace_cache__drop(struct auxtrace_cache *c)
+{
+	struct auxtrace_cache_entry *entry;
+	struct hlist_node *tmp;
+	size_t i;
+
+	if (!c)
+		return;
+
+	for (i = 0; i < c->sz; i++) {
+		hlist_for_each_entry_safe(entry, tmp, &c->hashtable[i], hash) {
+			hlist_del(&entry->hash);
+			auxtrace_cache__free_entry(c, entry);
+		}
+	}
+
+	c->cnt = 0;
+}
+
+void auxtrace_cache__free(struct auxtrace_cache *c)
+{
+	if (!c)
+		return;
+
+	auxtrace_cache__drop(c);
+	free(c->hashtable);
+	free(c);
+}
+
+void *auxtrace_cache__alloc_entry(struct auxtrace_cache *c)
+{
+	return malloc(c->entry_size);
+}
+
+void auxtrace_cache__free_entry(struct auxtrace_cache *c __maybe_unused,
+				void *entry)
+{
+	free(entry);
+}
+
+int auxtrace_cache__add(struct auxtrace_cache *c, u32 key,
+			struct auxtrace_cache_entry *entry)
+{
+	if (c->limit && ++c->cnt > c->limit)
+		auxtrace_cache__drop(c);
+
+	entry->key = key;
+	hlist_add_head(&entry->hash, &c->hashtable[hash_32(key, c->bits)]);
+
+	return 0;
+}
+
+void *auxtrace_cache__lookup(struct auxtrace_cache *c, u32 key)
+{
+	struct auxtrace_cache_entry *entry;
+	struct hlist_head *hlist;
+
+	if (!c)
+		return NULL;
+
+	hlist = &c->hashtable[hash_32(key, c->bits)];
+	hlist_for_each_entry(entry, hlist, hash) {
+		if (entry->key == key)
+			return entry;
+	}
+
+	return NULL;
+}
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
new file mode 100644
index 000000000000..a171abbe7301
--- /dev/null
+++ b/tools/perf/util/auxtrace.h
@@ -0,0 +1,643 @@
+/*
+ * auxtrace.h: AUX area trace support
+ * Copyright (c) 2013-2015, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#ifndef __PERF_AUXTRACE_H
+#define __PERF_AUXTRACE_H
+
+#include <sys/types.h>
+#include <stdbool.h>
+#include <stddef.h>
+#include <linux/list.h>
+#include <linux/perf_event.h>
+#include <linux/types.h>
+
+#include "../perf.h"
+#include "event.h"
+#include "session.h"
+#include "debug.h"
+
+union perf_event;
+struct perf_session;
+struct perf_evlist;
+struct perf_tool;
+struct option;
+struct record_opts;
+struct auxtrace_info_event;
+struct events_stats;
+
+enum auxtrace_type {
+	PERF_AUXTRACE_UNKNOWN,
+};
+
+enum itrace_period_type {
+	PERF_ITRACE_PERIOD_INSTRUCTIONS,
+	PERF_ITRACE_PERIOD_TICKS,
+	PERF_ITRACE_PERIOD_NANOSECS,
+};
+
+/**
+ * struct itrace_synth_opts - AUX area tracing synthesis options.
+ * @set: indicates whether or not options have been set
+ * @inject: indicates the event (not just the sample) must be fully synthesized
+ *          because 'perf inject' will write it out
+ * @instructions: whether to synthesize 'instructions' events
+ * @branches: whether to synthesize 'branches' events
+ * @transactions: whether to synthesize events for transactions
+ * @errors: whether to synthesize decoder error events
+ * @dont_decode: whether to skip decoding entirely
+ * @log: write a decoding log
+ * @calls: limit branch samples to calls (can be combined with @returns)
+ * @returns: limit branch samples to returns (can be combined with @calls)
+ * @callchain: add callchain to 'instructions' events
+ * @callchain_sz: maximum callchain size
+ * @period: 'instructions' events period
+ * @period_type: 'instructions' events period type
+ */
+struct itrace_synth_opts {
+	bool			set;
+	bool			inject;
+	bool			instructions;
+	bool			branches;
+	bool			transactions;
+	bool			errors;
+	bool			dont_decode;
+	bool			log;
+	bool			calls;
+	bool			returns;
+	bool			callchain;
+	unsigned int		callchain_sz;
+	unsigned long long	period;
+	enum itrace_period_type	period_type;
+};
+
+/**
+ * struct auxtrace_index_entry - indexes a AUX area tracing event within a
+ *                               perf.data file.
+ * @file_offset: offset within the perf.data file
+ * @sz: size of the event
+ */
+struct auxtrace_index_entry {
+	u64			file_offset;
+	u64			sz;
+};
+
+#define PERF_AUXTRACE_INDEX_ENTRY_COUNT 256
+
+/**
+ * struct auxtrace_index - index of AUX area tracing events within a perf.data
+ *                         file.
+ * @list: linking a number of arrays of entries
+ * @nr: number of entries
+ * @entries: array of entries
+ */
+struct auxtrace_index {
+	struct list_head	list;
+	size_t			nr;
+	struct auxtrace_index_entry entries[PERF_AUXTRACE_INDEX_ENTRY_COUNT];
+};
+
+/**
+ * struct auxtrace - session callbacks to allow AUX area data decoding.
+ * @process_event: lets the decoder see all session events
+ * @flush_events: process any remaining data
+ * @free_events: free resources associated with event processing
+ * @free: free resources associated with the session
+ */
+struct auxtrace {
+	int (*process_event)(struct perf_session *session,
+			     union perf_event *event,
+			     struct perf_sample *sample,
+			     struct perf_tool *tool);
+	int (*process_auxtrace_event)(struct perf_session *session,
+				      union perf_event *event,
+				      struct perf_tool *tool);
+	int (*flush_events)(struct perf_session *session,
+			    struct perf_tool *tool);
+	void (*free_events)(struct perf_session *session);
+	void (*free)(struct perf_session *session);
+};
+
+/**
+ * struct auxtrace_buffer - a buffer containing AUX area tracing data.
+ * @list: buffers are queued in a list held by struct auxtrace_queue
+ * @size: size of the buffer in bytes
+ * @pid: in per-thread mode, the pid this buffer is associated with
+ * @tid: in per-thread mode, the tid this buffer is associated with
+ * @cpu: in per-cpu mode, the cpu this buffer is associated with
+ * @data: actual buffer data (can be null if the data has not been loaded)
+ * @data_offset: file offset at which the buffer can be read
+ * @mmap_addr: mmap address at which the buffer can be read
+ * @mmap_size: size of the mmap at @mmap_addr
+ * @data_needs_freeing: @data was malloc'd so free it when it is no longer
+ *                      needed
+ * @consecutive: the original data was split up and this buffer is consecutive
+ *               to the previous buffer
+ * @offset: offset as determined by aux_head / aux_tail members of struct
+ *          perf_event_mmap_page
+ * @reference: an implementation-specific reference determined when the data is
+ *             recorded
+ * @buffer_nr: used to number each buffer
+ * @use_size: implementation actually only uses this number of bytes
+ * @use_data: implementation actually only uses data starting at this address
+ */
+struct auxtrace_buffer {
+	struct list_head	list;
+	size_t			size;
+	pid_t			pid;
+	pid_t			tid;
+	int			cpu;
+	void			*data;
+	off_t			data_offset;
+	void			*mmap_addr;
+	size_t			mmap_size;
+	bool			data_needs_freeing;
+	bool			consecutive;
+	u64			offset;
+	u64			reference;
+	u64			buffer_nr;
+	size_t			use_size;
+	void			*use_data;
+};
+
+/**
+ * struct auxtrace_queue - a queue of AUX area tracing data buffers.
+ * @head: head of buffer list
+ * @tid: in per-thread mode, the tid this queue is associated with
+ * @cpu: in per-cpu mode, the cpu this queue is associated with
+ * @set: %true once this queue has been dedicated to a specific thread or cpu
+ * @priv: implementation-specific data
+ */
+struct auxtrace_queue {
+	struct list_head	head;
+	pid_t			tid;
+	int			cpu;
+	bool			set;
+	void			*priv;
+};
+
+/**
+ * struct auxtrace_queues - an array of AUX area tracing queues.
+ * @queue_array: array of queues
+ * @nr_queues: number of queues
+ * @new_data: set whenever new data is queued
+ * @populated: queues have been fully populated using the auxtrace_index
+ * @next_buffer_nr: used to number each buffer
+ */
+struct auxtrace_queues {
+	struct auxtrace_queue	*queue_array;
+	unsigned int		nr_queues;
+	bool			new_data;
+	bool			populated;
+	u64			next_buffer_nr;
+};
+
+/**
+ * struct auxtrace_heap_item - element of struct auxtrace_heap.
+ * @queue_nr: queue number
+ * @ordinal: value used for sorting (lowest ordinal is top of the heap) expected
+ *           to be a timestamp
+ */
+struct auxtrace_heap_item {
+	unsigned int		queue_nr;
+	u64			ordinal;
+};
+
+/**
+ * struct auxtrace_heap - a heap suitable for sorting AUX area tracing queues.
+ * @heap_array: the heap
+ * @heap_cnt: the number of elements in the heap
+ * @heap_sz: maximum number of elements (grows as needed)
+ */
+struct auxtrace_heap {
+	struct auxtrace_heap_item	*heap_array;
+	unsigned int		heap_cnt;
+	unsigned int		heap_sz;
+};
+
+/**
+ * struct auxtrace_mmap - records an mmap of the auxtrace buffer.
+ * @base: address of mapped area
+ * @userpg: pointer to buffer's perf_event_mmap_page
+ * @mask: %0 if @len is not a power of two, otherwise (@len - %1)
+ * @len: size of mapped area
+ * @prev: previous aux_head
+ * @idx: index of this mmap
+ * @tid: tid for a per-thread mmap (also set if there is only 1 tid on a per-cpu
+ *       mmap) otherwise %0
+ * @cpu: cpu number for a per-cpu mmap otherwise %-1
+ */
+struct auxtrace_mmap {
+	void		*base;
+	void		*userpg;
+	size_t		mask;
+	size_t		len;
+	u64		prev;
+	int		idx;
+	pid_t		tid;
+	int		cpu;
+};
+
+/**
+ * struct auxtrace_mmap_params - parameters to set up struct auxtrace_mmap.
+ * @mask: %0 if @len is not a power of two, otherwise (@len - %1)
+ * @offset: file offset of mapped area
+ * @len: size of mapped area
+ * @prot: mmap memory protection
+ * @idx: index of this mmap
+ * @tid: tid for a per-thread mmap (also set if there is only 1 tid on a per-cpu
+ *       mmap) otherwise %0
+ * @cpu: cpu number for a per-cpu mmap otherwise %-1
+ */
+struct auxtrace_mmap_params {
+	size_t		mask;
+	off_t		offset;
+	size_t		len;
+	int		prot;
+	int		idx;
+	pid_t		tid;
+	int		cpu;
+};
+
+/**
+ * struct auxtrace_record - callbacks for recording AUX area data.
+ * @recording_options: validate and process recording options
+ * @info_priv_size: return the size of the private data in auxtrace_info_event
+ * @info_fill: fill-in the private data in auxtrace_info_event
+ * @free: free this auxtrace record structure
+ * @snapshot_start: starting a snapshot
+ * @snapshot_finish: finishing a snapshot
+ * @find_snapshot: find data to snapshot within auxtrace mmap
+ * @parse_snapshot_options: parse snapshot options
+ * @reference: provide a 64-bit reference number for auxtrace_event
+ * @read_finish: called after reading from an auxtrace mmap
+ */
+struct auxtrace_record {
+	int (*recording_options)(struct auxtrace_record *itr,
+				 struct perf_evlist *evlist,
+				 struct record_opts *opts);
+	size_t (*info_priv_size)(struct auxtrace_record *itr);
+	int (*info_fill)(struct auxtrace_record *itr,
+			 struct perf_session *session,
+			 struct auxtrace_info_event *auxtrace_info,
+			 size_t priv_size);
+	void (*free)(struct auxtrace_record *itr);
+	int (*snapshot_start)(struct auxtrace_record *itr);
+	int (*snapshot_finish)(struct auxtrace_record *itr);
+	int (*find_snapshot)(struct auxtrace_record *itr, int idx,
+			     struct auxtrace_mmap *mm, unsigned char *data,
+			     u64 *head, u64 *old);
+	int (*parse_snapshot_options)(struct auxtrace_record *itr,
+				      struct record_opts *opts,
+				      const char *str);
+	u64 (*reference)(struct auxtrace_record *itr);
+	int (*read_finish)(struct auxtrace_record *itr, int idx);
+};
+
+#ifdef HAVE_AUXTRACE_SUPPORT
+
+/*
+ * In snapshot mode the mmapped page is read-only which makes using
+ * __sync_val_compare_and_swap() problematic.  However, snapshot mode expects
+ * the buffer is not updated while the snapshot is made (e.g. Intel PT disables
+ * the event) so there is not a race anyway.
+ */
+static inline u64 auxtrace_mmap__read_snapshot_head(struct auxtrace_mmap *mm)
+{
+	struct perf_event_mmap_page *pc = mm->userpg;
+	u64 head = ACCESS_ONCE(pc->aux_head);
+
+	/* Ensure all reads are done after we read the head */
+	rmb();
+	return head;
+}
+
+static inline u64 auxtrace_mmap__read_head(struct auxtrace_mmap *mm)
+{
+	struct perf_event_mmap_page *pc = mm->userpg;
+#if BITS_PER_LONG == 64 || !defined(HAVE_SYNC_COMPARE_AND_SWAP_SUPPORT)
+	u64 head = ACCESS_ONCE(pc->aux_head);
+#else
+	u64 head = __sync_val_compare_and_swap(&pc->aux_head, 0, 0);
+#endif
+
+	/* Ensure all reads are done after we read the head */
+	rmb();
+	return head;
+}
+
+static inline void auxtrace_mmap__write_tail(struct auxtrace_mmap *mm, u64 tail)
+{
+	struct perf_event_mmap_page *pc = mm->userpg;
+#if BITS_PER_LONG != 64 && defined(HAVE_SYNC_COMPARE_AND_SWAP_SUPPORT)
+	u64 old_tail;
+#endif
+
+	/* Ensure all reads are done before we write the tail out */
+	mb();
+#if BITS_PER_LONG == 64 || !defined(HAVE_SYNC_COMPARE_AND_SWAP_SUPPORT)
+	pc->aux_tail = tail;
+#else
+	do {
+		old_tail = __sync_val_compare_and_swap(&pc->aux_tail, 0, 0);
+	} while (!__sync_bool_compare_and_swap(&pc->aux_tail, old_tail, tail));
+#endif
+}
+
+int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
+			struct auxtrace_mmap_params *mp,
+			void *userpg, int fd);
+void auxtrace_mmap__munmap(struct auxtrace_mmap *mm);
+void auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp,
+				off_t auxtrace_offset,
+				unsigned int auxtrace_pages,
+				bool auxtrace_overwrite);
+void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
+				   struct perf_evlist *evlist, int idx,
+				   bool per_cpu);
+
+typedef int (*process_auxtrace_t)(struct perf_tool *tool,
+				  union perf_event *event, void *data1,
+				  size_t len1, void *data2, size_t len2);
+
+int auxtrace_mmap__read(struct auxtrace_mmap *mm, struct auxtrace_record *itr,
+			struct perf_tool *tool, process_auxtrace_t fn);
+
+int auxtrace_mmap__read_snapshot(struct auxtrace_mmap *mm,
+				 struct auxtrace_record *itr,
+				 struct perf_tool *tool, process_auxtrace_t fn,
+				 size_t snapshot_size);
+
+int auxtrace_queues__init(struct auxtrace_queues *queues);
+int auxtrace_queues__add_event(struct auxtrace_queues *queues,
+			       struct perf_session *session,
+			       union perf_event *event, off_t data_offset,
+			       struct auxtrace_buffer **buffer_ptr);
+void auxtrace_queues__free(struct auxtrace_queues *queues);
+int auxtrace_queues__process_index(struct auxtrace_queues *queues,
+				   struct perf_session *session);
+struct auxtrace_buffer *auxtrace_buffer__next(struct auxtrace_queue *queue,
+					      struct auxtrace_buffer *buffer);
+void *auxtrace_buffer__get_data(struct auxtrace_buffer *buffer, int fd);
+void auxtrace_buffer__put_data(struct auxtrace_buffer *buffer);
+void auxtrace_buffer__drop_data(struct auxtrace_buffer *buffer);
+void auxtrace_buffer__free(struct auxtrace_buffer *buffer);
+
+int auxtrace_heap__add(struct auxtrace_heap *heap, unsigned int queue_nr,
+		       u64 ordinal);
+void auxtrace_heap__pop(struct auxtrace_heap *heap);
+void auxtrace_heap__free(struct auxtrace_heap *heap);
+
+struct auxtrace_cache_entry {
+	struct hlist_node hash;
+	u32 key;
+};
+
+struct auxtrace_cache *auxtrace_cache__new(unsigned int bits, size_t entry_size,
+					   unsigned int limit_percent);
+void auxtrace_cache__free(struct auxtrace_cache *auxtrace_cache);
+void *auxtrace_cache__alloc_entry(struct auxtrace_cache *c);
+void auxtrace_cache__free_entry(struct auxtrace_cache *c, void *entry);
+int auxtrace_cache__add(struct auxtrace_cache *c, u32 key,
+			struct auxtrace_cache_entry *entry);
+void *auxtrace_cache__lookup(struct auxtrace_cache *c, u32 key);
+
+struct auxtrace_record *auxtrace_record__init(struct perf_evlist *evlist,
+					      int *err);
+
+int auxtrace_parse_snapshot_options(struct auxtrace_record *itr,
+				    struct record_opts *opts,
+				    const char *str);
+int auxtrace_record__options(struct auxtrace_record *itr,
+			     struct perf_evlist *evlist,
+			     struct record_opts *opts);
+size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr);
+int auxtrace_record__info_fill(struct auxtrace_record *itr,
+			       struct perf_session *session,
+			       struct auxtrace_info_event *auxtrace_info,
+			       size_t priv_size);
+void auxtrace_record__free(struct auxtrace_record *itr);
+int auxtrace_record__snapshot_start(struct auxtrace_record *itr);
+int auxtrace_record__snapshot_finish(struct auxtrace_record *itr);
+int auxtrace_record__find_snapshot(struct auxtrace_record *itr, int idx,
+				   struct auxtrace_mmap *mm,
+				   unsigned char *data, u64 *head, u64 *old);
+u64 auxtrace_record__reference(struct auxtrace_record *itr);
+
+int auxtrace_index__auxtrace_event(struct list_head *head, union perf_event *event,
+				   off_t file_offset);
+int auxtrace_index__write(int fd, struct list_head *head);
+int auxtrace_index__process(int fd, u64 size, struct perf_session *session,
+			    bool needs_swap);
+void auxtrace_index__free(struct list_head *head);
+
+void auxtrace_synth_error(struct auxtrace_error_event *auxtrace_error, int type,
+			  int code, int cpu, pid_t pid, pid_t tid, u64 ip,
+			  const char *msg);
+
+int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr,
+					 struct perf_tool *tool,
+					 struct perf_session *session,
+					 perf_event__handler_t process);
+int perf_event__process_auxtrace_info(struct perf_tool *tool,
+				      union perf_event *event,
+				      struct perf_session *session);
+s64 perf_event__process_auxtrace(struct perf_tool *tool,
+				 union perf_event *event,
+				 struct perf_session *session);
+int perf_event__process_auxtrace_error(struct perf_tool *tool,
+				       union perf_event *event,
+				       struct perf_session *session);
+int itrace_parse_synth_opts(const struct option *opt, const char *str,
+			    int unset);
+void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts);
+
+size_t perf_event__fprintf_auxtrace_error(union perf_event *event, FILE *fp);
+void perf_session__auxtrace_error_inc(struct perf_session *session,
+				      union perf_event *event);
+void events_stats__auxtrace_error_warn(const struct events_stats *stats);
+
+static inline int auxtrace__process_event(struct perf_session *session,
+					  union perf_event *event,
+					  struct perf_sample *sample,
+					  struct perf_tool *tool)
+{
+	if (!session->auxtrace)
+		return 0;
+
+	return session->auxtrace->process_event(session, event, sample, tool);
+}
+
+static inline int auxtrace__flush_events(struct perf_session *session,
+					 struct perf_tool *tool)
+{
+	if (!session->auxtrace)
+		return 0;
+
+	return session->auxtrace->flush_events(session, tool);
+}
+
+static inline void auxtrace__free_events(struct perf_session *session)
+{
+	if (!session->auxtrace)
+		return;
+
+	return session->auxtrace->free_events(session);
+}
+
+static inline void auxtrace__free(struct perf_session *session)
+{
+	if (!session->auxtrace)
+		return;
+
+	return session->auxtrace->free(session);
+}
+
+#else
+
+static inline struct auxtrace_record *
+auxtrace_record__init(struct perf_evlist *evlist __maybe_unused,
+		      int *err __maybe_unused)
+{
+	*err = 0;
+	return NULL;
+}
+
+static inline
+void auxtrace_record__free(struct auxtrace_record *itr __maybe_unused)
+{
+}
+
+static inline int
+perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr __maybe_unused,
+				     struct perf_tool *tool __maybe_unused,
+				     struct perf_session *session __maybe_unused,
+				     perf_event__handler_t process __maybe_unused)
+{
+	return -EINVAL;
+}
+
+static inline
+int auxtrace_record__options(struct auxtrace_record *itr __maybe_unused,
+			     struct perf_evlist *evlist __maybe_unused,
+			     struct record_opts *opts __maybe_unused)
+{
+	return 0;
+}
+
+#define perf_event__process_auxtrace_info		0
+#define perf_event__process_auxtrace			0
+#define perf_event__process_auxtrace_error		0
+
+static inline
+void perf_session__auxtrace_error_inc(struct perf_session *session
+				      __maybe_unused,
+				      union perf_event *event
+				      __maybe_unused)
+{
+}
+
+static inline
+void events_stats__auxtrace_error_warn(const struct events_stats *stats
+				       __maybe_unused)
+{
+}
+
+static inline
+int itrace_parse_synth_opts(const struct option *opt __maybe_unused,
+			    const char *str __maybe_unused,
+			    int unset __maybe_unused)
+{
+	pr_err("AUX area tracing not supported\n");
+	return -EINVAL;
+}
+
+static inline
+int auxtrace_parse_snapshot_options(struct auxtrace_record *itr __maybe_unused,
+				    struct record_opts *opts __maybe_unused,
+				    const char *str)
+{
+	if (!str)
+		return 0;
+	pr_err("AUX area tracing not supported\n");
+	return -EINVAL;
+}
+
+static inline
+int auxtrace__process_event(struct perf_session *session __maybe_unused,
+			    union perf_event *event __maybe_unused,
+			    struct perf_sample *sample __maybe_unused,
+			    struct perf_tool *tool __maybe_unused)
+{
+	return 0;
+}
+
+static inline
+int auxtrace__flush_events(struct perf_session *session __maybe_unused,
+			   struct perf_tool *tool __maybe_unused)
+{
+	return 0;
+}
+
+static inline
+void auxtrace__free_events(struct perf_session *session __maybe_unused)
+{
+}
+
+static inline
+void auxtrace_cache__free(struct auxtrace_cache *auxtrace_cache __maybe_unused)
+{
+}
+
+static inline
+void auxtrace__free(struct perf_session *session __maybe_unused)
+{
+}
+
+static inline
+int auxtrace_index__write(int fd __maybe_unused,
+			  struct list_head *head __maybe_unused)
+{
+	return -EINVAL;
+}
+
+static inline
+int auxtrace_index__process(int fd __maybe_unused,
+			    u64 size __maybe_unused,
+			    struct perf_session *session __maybe_unused,
+			    bool needs_swap __maybe_unused)
+{
+	return -EINVAL;
+}
+
+static inline
+void auxtrace_index__free(struct list_head *head __maybe_unused)
+{
+}
+
+int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
+			struct auxtrace_mmap_params *mp,
+			void *userpg, int fd);
+void auxtrace_mmap__munmap(struct auxtrace_mmap *mm);
+void auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp,
+				off_t auxtrace_offset,
+				unsigned int auxtrace_pages,
+				bool auxtrace_overwrite);
+void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
+				   struct perf_evlist *evlist, int idx,
+				   bool per_cpu);
+
+#endif
+
+#endif
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 61867dff5d5a..1f6fc2323ef9 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -43,6 +43,7 @@ int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused,
 	if (al.map != NULL)
 		al.map->dso->hit = 1;
 
+	thread__put(thread);
 	return 0;
 }
 
@@ -59,8 +60,10 @@ static int perf_event__exit_del_thread(struct perf_tool *tool __maybe_unused,
 	dump_printf("(%d:%d):(%d:%d)\n", event->fork.pid, event->fork.tid,
 		    event->fork.ppid, event->fork.ptid);
 
-	if (thread)
+	if (thread) {
 		machine__remove_thread(machine, thread);
+		thread__put(thread);
+	}
 
 	return 0;
 }
@@ -159,15 +162,20 @@ static int write_buildid(const char *name, size_t name_len, u8 *build_id,
 	return write_padded(fd, name, name_len + 1, len);
 }
 
-static int __dsos__write_buildid_table(struct list_head *head,
-				       struct machine *machine,
-				       pid_t pid, u16 misc, int fd)
+static int machine__write_buildid_table(struct machine *machine, int fd)
 {
+	int err = 0;
 	char nm[PATH_MAX];
 	struct dso *pos;
+	u16 kmisc = PERF_RECORD_MISC_KERNEL,
+	    umisc = PERF_RECORD_MISC_USER;
 
-	dsos__for_each_with_build_id(pos, head) {
-		int err;
+	if (!machine__is_host(machine)) {
+		kmisc = PERF_RECORD_MISC_GUEST_KERNEL;
+		umisc = PERF_RECORD_MISC_GUEST_USER;
+	}
+
+	dsos__for_each_with_build_id(pos, &machine->dsos.head) {
 		const char *name;
 		size_t name_len;
 
@@ -186,32 +194,12 @@ static int __dsos__write_buildid_table(struct list_head *head,
 			name_len = pos->long_name_len + 1;
 		}
 
-		err = write_buildid(name, name_len, pos->build_id,
-				    pid, misc, fd);
+		err = write_buildid(name, name_len, pos->build_id, machine->pid,
+				    pos->kernel ? kmisc : umisc, fd);
 		if (err)
-			return err;
-	}
-
-	return 0;
-}
-
-static int machine__write_buildid_table(struct machine *machine, int fd)
-{
-	int err;
-	u16 kmisc = PERF_RECORD_MISC_KERNEL,
-	    umisc = PERF_RECORD_MISC_USER;
-
-	if (!machine__is_host(machine)) {
-		kmisc = PERF_RECORD_MISC_GUEST_KERNEL;
-		umisc = PERF_RECORD_MISC_GUEST_USER;
+			break;
 	}
 
-	err = __dsos__write_buildid_table(&machine->kernel_dsos.head, machine,
-					  machine->pid, kmisc, fd);
-	if (err == 0)
-		err = __dsos__write_buildid_table(&machine->user_dsos.head,
-						  machine, machine->pid, umisc,
-						  fd);
 	return err;
 }
 
@@ -244,13 +232,7 @@ static int __dsos__hit_all(struct list_head *head)
 
 static int machine__hit_all_dsos(struct machine *machine)
 {
-	int err;
-
-	err = __dsos__hit_all(&machine->kernel_dsos.head);
-	if (err)
-		return err;
-
-	return __dsos__hit_all(&machine->user_dsos.head);
+	return __dsos__hit_all(&machine->dsos.head);
 }
 
 int dsos__hit_all(struct perf_session *session)
@@ -490,9 +472,7 @@ static int __dsos__cache_build_ids(struct list_head *head,
 
 static int machine__cache_build_ids(struct machine *machine)
 {
-	int ret = __dsos__cache_build_ids(&machine->kernel_dsos.head, machine);
-	ret |= __dsos__cache_build_ids(&machine->user_dsos.head, machine);
-	return ret;
+	return __dsos__cache_build_ids(&machine->dsos.head, machine);
 }
 
 int perf_session__cache_build_ids(struct perf_session *session)
@@ -517,11 +497,7 @@ int perf_session__cache_build_ids(struct perf_session *session)
 
 static bool machine__read_build_ids(struct machine *machine, bool with_hits)
 {
-	bool ret;
-
-	ret  = __dsos__read_build_ids(&machine->kernel_dsos.head, with_hits);
-	ret |= __dsos__read_build_ids(&machine->user_dsos.head, with_hits);
-	return ret;
+	return __dsos__read_build_ids(&machine->dsos.head, with_hits);
 }
 
 bool perf_session__read_build_ids(struct perf_session *session, bool with_hits)
diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h
index fbcca21d66ab..c861373aaed3 100644
--- a/tools/perf/util/cache.h
+++ b/tools/perf/util/cache.h
@@ -30,7 +30,6 @@ extern const char *perf_config_dirname(const char *, const char *);
 
 /* pager.c */
 extern void setup_pager(void);
-extern const char *pager_program;
 extern int pager_in_use(void);
 extern int pager_use_color;
 
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 6033a0a212ca..679c2c6d8ade 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -72,6 +72,10 @@ extern struct callchain_param callchain_param;
 struct callchain_list {
 	u64			ip;
 	struct map_symbol	ms;
+	struct /* for TUI */ {
+		bool		unfolded;
+		bool		has_children;
+	};
 	char		       *srcline;
 	struct list_head	list;
 };
diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index 88f7be399432..32e12ecfe9c5 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -115,23 +115,19 @@ static int add_cgroup(struct perf_evlist *evlist, char *str)
 			goto found;
 		n++;
 	}
-	if (cgrp->refcnt == 0)
+	if (atomic_read(&cgrp->refcnt) == 0)
 		free(cgrp);
 
 	return -1;
 found:
-	cgrp->refcnt++;
+	atomic_inc(&cgrp->refcnt);
 	counter->cgrp = cgrp;
 	return 0;
 }
 
 void close_cgroup(struct cgroup_sel *cgrp)
 {
-	if (!cgrp)
-		return;
-
-	/* XXX: not reentrant */
-	if (--cgrp->refcnt == 0) {
+	if (cgrp && atomic_dec_and_test(&cgrp->refcnt)) {
 		close(cgrp->fd);
 		zfree(&cgrp->name);
 		free(cgrp);
diff --git a/tools/perf/util/cgroup.h b/tools/perf/util/cgroup.h
index 89acd6debdc5..b4b8cb42fe5e 100644
--- a/tools/perf/util/cgroup.h
+++ b/tools/perf/util/cgroup.h
@@ -1,12 +1,14 @@
 #ifndef __CGROUP_H__
 #define __CGROUP_H__
 
+#include <linux/atomic.h>
+
 struct option;
 
 struct cgroup_sel {
 	char *name;
 	int fd;
-	int refcnt;
+	atomic_t refcnt;
 };
 
 
diff --git a/tools/perf/util/comm.c b/tools/perf/util/comm.c
index b2bb59df65e1..21b7ff382c3f 100644
--- a/tools/perf/util/comm.c
+++ b/tools/perf/util/comm.c
@@ -2,24 +2,27 @@
 #include "util.h"
 #include <stdlib.h>
 #include <stdio.h>
+#include <linux/atomic.h>
 
 struct comm_str {
 	char *str;
 	struct rb_node rb_node;
-	int ref;
+	atomic_t refcnt;
 };
 
 /* Should perhaps be moved to struct machine */
 static struct rb_root comm_str_root;
 
-static void comm_str__get(struct comm_str *cs)
+static struct comm_str *comm_str__get(struct comm_str *cs)
 {
-	cs->ref++;
+	if (cs)
+		atomic_inc(&cs->refcnt);
+	return cs;
 }
 
 static void comm_str__put(struct comm_str *cs)
 {
-	if (!--cs->ref) {
+	if (cs && atomic_dec_and_test(&cs->refcnt)) {
 		rb_erase(&cs->rb_node, &comm_str_root);
 		zfree(&cs->str);
 		free(cs);
@@ -40,6 +43,8 @@ static struct comm_str *comm_str__alloc(const char *str)
 		return NULL;
 	}
 
+	atomic_set(&cs->refcnt, 0);
+
 	return cs;
 }
 
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index dd17c9a32fbc..5bfc1198ab46 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -14,6 +14,7 @@
 #include <babeltrace/ctf-writer/event.h>
 #include <babeltrace/ctf-writer/event-types.h>
 #include <babeltrace/ctf-writer/event-fields.h>
+#include <babeltrace/ctf-ir/utils.h>
 #include <babeltrace/ctf/events.h>
 #include <traceevent/event-parse.h>
 #include "asm/bug.h"
@@ -38,12 +39,21 @@ struct evsel_priv {
 	struct bt_ctf_event_class *event_class;
 };
 
+#define MAX_CPUS	4096
+
+struct ctf_stream {
+	struct bt_ctf_stream *stream;
+	int cpu;
+	u32 count;
+};
+
 struct ctf_writer {
 	/* writer primitives */
-	struct bt_ctf_writer		*writer;
-	struct bt_ctf_stream		*stream;
-	struct bt_ctf_stream_class	*stream_class;
-	struct bt_ctf_clock		*clock;
+	struct bt_ctf_writer		 *writer;
+	struct ctf_stream		**stream;
+	int				  stream_cnt;
+	struct bt_ctf_stream_class	 *stream_class;
+	struct bt_ctf_clock		 *clock;
 
 	/* data types */
 	union {
@@ -65,6 +75,9 @@ struct convert {
 
 	u64			events_size;
 	u64			events_count;
+
+	/* Ordered events configured queue size. */
+	u64			queue_size;
 };
 
 static int value_set(struct bt_ctf_field_type *type,
@@ -153,6 +166,43 @@ get_tracepoint_field_type(struct ctf_writer *cw, struct format_field *field)
 		return cw->data.u32;
 }
 
+static unsigned long long adjust_signedness(unsigned long long value_int, int size)
+{
+	unsigned long long value_mask;
+
+	/*
+	 * value_mask = (1 << (size * 8 - 1)) - 1.
+	 * Directly set value_mask for code readers.
+	 */
+	switch (size) {
+	case 1:
+		value_mask = 0x7fULL;
+		break;
+	case 2:
+		value_mask = 0x7fffULL;
+		break;
+	case 4:
+		value_mask = 0x7fffffffULL;
+		break;
+	case 8:
+		/*
+		 * For 64 bit value, return it self. There is no need
+		 * to fill high bit.
+		 */
+		/* Fall through */
+	default:
+		/* BUG! */
+		return value_int;
+	}
+
+	/* If it is a positive value, don't adjust. */
+	if ((value_int & (~0ULL - value_mask)) == 0)
+		return value_int;
+
+	/* Fill upper part of value_int with 1 to make it a negative long long. */
+	return (value_int & value_mask) | ~value_mask;
+}
+
 static int add_tracepoint_field_value(struct ctf_writer *cw,
 				      struct bt_ctf_event_class *event_class,
 				      struct bt_ctf_event *event,
@@ -164,7 +214,6 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 	struct bt_ctf_field *field;
 	const char *name = fmtf->name;
 	void *data = sample->raw_data;
-	unsigned long long value_int;
 	unsigned long flags = fmtf->flags;
 	unsigned int n_items;
 	unsigned int i;
@@ -172,6 +221,7 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 	unsigned int len;
 	int ret;
 
+	name = fmtf->alias;
 	offset = fmtf->offset;
 	len = fmtf->size;
 	if (flags & FIELD_IS_STRING)
@@ -208,11 +258,6 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 	type = get_tracepoint_field_type(cw, fmtf);
 
 	for (i = 0; i < n_items; i++) {
-		if (!(flags & FIELD_IS_STRING))
-			value_int = pevent_read_number(
-					fmtf->event->pevent,
-					data + offset + i * len, len);
-
 		if (flags & FIELD_IS_ARRAY)
 			field = bt_ctf_field_array_get_field(array_field, i);
 		else
@@ -226,12 +271,21 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 		if (flags & FIELD_IS_STRING)
 			ret = bt_ctf_field_string_set_value(field,
 					data + offset + i * len);
-		else if (!(flags & FIELD_IS_SIGNED))
-			ret = bt_ctf_field_unsigned_integer_set_value(
-					field, value_int);
-		else
-			ret = bt_ctf_field_signed_integer_set_value(
-					field, value_int);
+		else {
+			unsigned long long value_int;
+
+			value_int = pevent_read_number(
+					fmtf->event->pevent,
+					data + offset + i * len, len);
+
+			if (!(flags & FIELD_IS_SIGNED))
+				ret = bt_ctf_field_unsigned_integer_set_value(
+						field, value_int);
+			else
+				ret = bt_ctf_field_signed_integer_set_value(
+						field, adjust_signedness(value_int, len));
+		}
+
 		if (ret) {
 			pr_err("failed to set file value %s\n", name);
 			goto err_put_field;
@@ -346,12 +400,6 @@ static int add_generic_values(struct ctf_writer *cw,
 			return -1;
 	}
 
-	if (type & PERF_SAMPLE_CPU) {
-		ret = value_set_u32(cw, event, "perf_cpu", sample->cpu);
-		if (ret)
-			return -1;
-	}
-
 	if (type & PERF_SAMPLE_PERIOD) {
 		ret = value_set_u64(cw, event, "perf_period", sample->period);
 		if (ret)
@@ -381,6 +429,129 @@ static int add_generic_values(struct ctf_writer *cw,
 	return 0;
 }
 
+static int ctf_stream__flush(struct ctf_stream *cs)
+{
+	int err = 0;
+
+	if (cs) {
+		err = bt_ctf_stream_flush(cs->stream);
+		if (err)
+			pr_err("CTF stream %d flush failed\n", cs->cpu);
+
+		pr("Flush stream for cpu %d (%u samples)\n",
+		   cs->cpu, cs->count);
+
+		cs->count = 0;
+	}
+
+	return err;
+}
+
+static struct ctf_stream *ctf_stream__create(struct ctf_writer *cw, int cpu)
+{
+	struct ctf_stream *cs;
+	struct bt_ctf_field *pkt_ctx   = NULL;
+	struct bt_ctf_field *cpu_field = NULL;
+	struct bt_ctf_stream *stream   = NULL;
+	int ret;
+
+	cs = zalloc(sizeof(*cs));
+	if (!cs) {
+		pr_err("Failed to allocate ctf stream\n");
+		return NULL;
+	}
+
+	stream = bt_ctf_writer_create_stream(cw->writer, cw->stream_class);
+	if (!stream) {
+		pr_err("Failed to create CTF stream\n");
+		goto out;
+	}
+
+	pkt_ctx = bt_ctf_stream_get_packet_context(stream);
+	if (!pkt_ctx) {
+		pr_err("Failed to obtain packet context\n");
+		goto out;
+	}
+
+	cpu_field = bt_ctf_field_structure_get_field(pkt_ctx, "cpu_id");
+	bt_ctf_field_put(pkt_ctx);
+	if (!cpu_field) {
+		pr_err("Failed to obtain cpu field\n");
+		goto out;
+	}
+
+	ret = bt_ctf_field_unsigned_integer_set_value(cpu_field, (u32) cpu);
+	if (ret) {
+		pr_err("Failed to update CPU number\n");
+		goto out;
+	}
+
+	bt_ctf_field_put(cpu_field);
+
+	cs->cpu    = cpu;
+	cs->stream = stream;
+	return cs;
+
+out:
+	if (cpu_field)
+		bt_ctf_field_put(cpu_field);
+	if (stream)
+		bt_ctf_stream_put(stream);
+
+	free(cs);
+	return NULL;
+}
+
+static void ctf_stream__delete(struct ctf_stream *cs)
+{
+	if (cs) {
+		bt_ctf_stream_put(cs->stream);
+		free(cs);
+	}
+}
+
+static struct ctf_stream *ctf_stream(struct ctf_writer *cw, int cpu)
+{
+	struct ctf_stream *cs = cw->stream[cpu];
+
+	if (!cs) {
+		cs = ctf_stream__create(cw, cpu);
+		cw->stream[cpu] = cs;
+	}
+
+	return cs;
+}
+
+static int get_sample_cpu(struct ctf_writer *cw, struct perf_sample *sample,
+			  struct perf_evsel *evsel)
+{
+	int cpu = 0;
+
+	if (evsel->attr.sample_type & PERF_SAMPLE_CPU)
+		cpu = sample->cpu;
+
+	if (cpu > cw->stream_cnt) {
+		pr_err("Event was recorded for CPU %d, limit is at %d.\n",
+			cpu, cw->stream_cnt);
+		cpu = 0;
+	}
+
+	return cpu;
+}
+
+#define STREAM_FLUSH_COUNT 100000
+
+/*
+ * Currently we have no other way to determine the
+ * time for the stream flush other than keep track
+ * of the number of events and check it against
+ * threshold.
+ */
+static bool is_flush_needed(struct ctf_stream *cs)
+{
+	return cs->count >= STREAM_FLUSH_COUNT;
+}
+
 static int process_sample_event(struct perf_tool *tool,
 				union perf_event *_event __maybe_unused,
 				struct perf_sample *sample,
@@ -390,6 +561,7 @@ static int process_sample_event(struct perf_tool *tool,
 	struct convert *c = container_of(tool, struct convert, tool);
 	struct evsel_priv *priv = evsel->priv;
 	struct ctf_writer *cw = &c->writer;
+	struct ctf_stream *cs;
 	struct bt_ctf_event_class *event_class;
 	struct bt_ctf_event *event;
 	int ret;
@@ -424,9 +596,93 @@ static int process_sample_event(struct perf_tool *tool,
 			return -1;
 	}
 
-	bt_ctf_stream_append_event(cw->stream, event);
+	cs = ctf_stream(cw, get_sample_cpu(cw, sample, evsel));
+	if (cs) {
+		if (is_flush_needed(cs))
+			ctf_stream__flush(cs);
+
+		cs->count++;
+		bt_ctf_stream_append_event(cs->stream, event);
+	}
+
 	bt_ctf_event_put(event);
-	return 0;
+	return cs ? 0 : -1;
+}
+
+/* If dup < 0, add a prefix. Else, add _dupl_X suffix. */
+static char *change_name(char *name, char *orig_name, int dup)
+{
+	char *new_name = NULL;
+	size_t len;
+
+	if (!name)
+		name = orig_name;
+
+	if (dup >= 10)
+		goto out;
+	/*
+	 * Add '_' prefix to potential keywork.  According to
+	 * Mathieu Desnoyers (https://lkml.org/lkml/2015/1/23/652),
+	 * futher CTF spec updating may require us to use '$'.
+	 */
+	if (dup < 0)
+		len = strlen(name) + sizeof("_");
+	else
+		len = strlen(orig_name) + sizeof("_dupl_X");
+
+	new_name = malloc(len);
+	if (!new_name)
+		goto out;
+
+	if (dup < 0)
+		snprintf(new_name, len, "_%s", name);
+	else
+		snprintf(new_name, len, "%s_dupl_%d", orig_name, dup);
+
+out:
+	if (name != orig_name)
+		free(name);
+	return new_name;
+}
+
+static int event_class_add_field(struct bt_ctf_event_class *event_class,
+		struct bt_ctf_field_type *type,
+		struct format_field *field)
+{
+	struct bt_ctf_field_type *t = NULL;
+	char *name;
+	int dup = 1;
+	int ret;
+
+	/* alias was already assigned */
+	if (field->alias != field->name)
+		return bt_ctf_event_class_add_field(event_class, type,
+				(char *)field->alias);
+
+	name = field->name;
+
+	/* If 'name' is a keywork, add prefix. */
+	if (bt_ctf_validate_identifier(name))
+		name = change_name(name, field->name, -1);
+
+	if (!name) {
+		pr_err("Failed to fix invalid identifier.");
+		return -1;
+	}
+	while ((t = bt_ctf_event_class_get_field_by_name(event_class, name))) {
+		bt_ctf_field_type_put(t);
+		name = change_name(name, field->name, dup++);
+		if (!name) {
+			pr_err("Failed to create dup name for '%s'\n", field->name);
+			return -1;
+		}
+	}
+
+	ret = bt_ctf_event_class_add_field(event_class, type, name);
+	if (!ret)
+		field->alias = name;
+
+	return ret;
 }
 
 static int add_tracepoint_fields_types(struct ctf_writer *cw,
@@ -457,14 +713,14 @@ static int add_tracepoint_fields_types(struct ctf_writer *cw,
 		if (flags & FIELD_IS_ARRAY)
 			type = bt_ctf_field_type_array_create(type, field->arraylen);
 
-		ret = bt_ctf_event_class_add_field(event_class, type,
-				field->name);
+		ret = event_class_add_field(event_class, type, field);
 
 		if (flags & FIELD_IS_ARRAY)
 			bt_ctf_field_type_put(type);
 
 		if (ret) {
-			pr_err("Failed to add field '%s\n", field->name);
+			pr_err("Failed to add field '%s': %d\n",
+					field->name, ret);
 			return -1;
 		}
 	}
@@ -508,7 +764,7 @@ static int add_generic_types(struct ctf_writer *cw, struct perf_evsel *evsel,
 	do {								\
 		pr2("  field '%s'\n", n);				\
 		if (bt_ctf_event_class_add_field(cl, t, n)) {		\
-			pr_err("Failed to add field '%s;\n", n);	\
+			pr_err("Failed to add field '%s';\n", n);	\
 			return -1;					\
 		}							\
 	} while (0)
@@ -528,9 +784,6 @@ static int add_generic_types(struct ctf_writer *cw, struct perf_evsel *evsel,
 	if (type & PERF_SAMPLE_STREAM_ID)
 		ADD_FIELD(event_class, cw->data.u64, "perf_stream_id");
 
-	if (type & PERF_SAMPLE_CPU)
-		ADD_FIELD(event_class, cw->data.u32, "perf_cpu");
-
 	if (type & PERF_SAMPLE_PERIOD)
 		ADD_FIELD(event_class, cw->data.u64, "perf_period");
 
@@ -604,6 +857,39 @@ static int setup_events(struct ctf_writer *cw, struct perf_session *session)
 	return 0;
 }
 
+static int setup_streams(struct ctf_writer *cw, struct perf_session *session)
+{
+	struct ctf_stream **stream;
+	struct perf_header *ph = &session->header;
+	int ncpus;
+
+	/*
+	 * Try to get the number of cpus used in the data file,
+	 * if not present fallback to the MAX_CPUS.
+	 */
+	ncpus = ph->env.nr_cpus_avail ?: MAX_CPUS;
+
+	stream = zalloc(sizeof(*stream) * ncpus);
+	if (!stream) {
+		pr_err("Failed to allocate streams.\n");
+		return -ENOMEM;
+	}
+
+	cw->stream     = stream;
+	cw->stream_cnt = ncpus;
+	return 0;
+}
+
+static void free_streams(struct ctf_writer *cw)
+{
+	int cpu;
+
+	for (cpu = 0; cpu < cw->stream_cnt; cpu++)
+		ctf_stream__delete(cw->stream[cpu]);
+
+	free(cw->stream);
+}
+
 static int ctf_writer__setup_env(struct ctf_writer *cw,
 				 struct perf_session *session)
 {
@@ -713,7 +999,7 @@ static void ctf_writer__cleanup(struct ctf_writer *cw)
 	ctf_writer__cleanup_data(cw);
 
 	bt_ctf_clock_put(cw->clock);
-	bt_ctf_stream_put(cw->stream);
+	free_streams(cw);
 	bt_ctf_stream_class_put(cw->stream_class);
 	bt_ctf_writer_put(cw->writer);
 
@@ -725,8 +1011,9 @@ static int ctf_writer__init(struct ctf_writer *cw, const char *path)
 {
 	struct bt_ctf_writer		*writer;
 	struct bt_ctf_stream_class	*stream_class;
-	struct bt_ctf_stream		*stream;
 	struct bt_ctf_clock		*clock;
+	struct bt_ctf_field_type	*pkt_ctx_type;
+	int				ret;
 
 	/* CTF writer */
 	writer = bt_ctf_writer_create(path);
@@ -767,14 +1054,15 @@ static int ctf_writer__init(struct ctf_writer *cw, const char *path)
 	if (ctf_writer__init_data(cw))
 		goto err_cleanup;
 
-	/* CTF stream instance */
-	stream = bt_ctf_writer_create_stream(writer, stream_class);
-	if (!stream) {
-		pr("Failed to create CTF stream.\n");
+	/* Add cpu_id for packet context */
+	pkt_ctx_type = bt_ctf_stream_class_get_packet_context_type(stream_class);
+	if (!pkt_ctx_type)
 		goto err_cleanup;
-	}
 
-	cw->stream = stream;
+	ret = bt_ctf_field_type_structure_add_field(pkt_ctx_type, cw->data.u32, "cpu_id");
+	bt_ctf_field_type_put(pkt_ctx_type);
+	if (ret)
+		goto err_cleanup;
 
 	/* CTF clock writer setup */
 	if (bt_ctf_writer_add_clock(writer, clock)) {
@@ -791,6 +1079,28 @@ err:
 	return -1;
 }
 
+static int ctf_writer__flush_streams(struct ctf_writer *cw)
+{
+	int cpu, ret = 0;
+
+	for (cpu = 0; cpu < cw->stream_cnt && !ret; cpu++)
+		ret = ctf_stream__flush(cw->stream[cpu]);
+
+	return ret;
+}
+
+static int convert__config(const char *var, const char *value, void *cb)
+{
+	struct convert *c = cb;
+
+	if (!strcmp(var, "convert.queue-size")) {
+		c->queue_size = perf_config_u64(var, value);
+		return 0;
+	}
+
+	return perf_default_config(var, value, cb);
+}
+
 int bt_convert__perf2ctf(const char *input, const char *path, bool force)
 {
 	struct perf_session *session;
@@ -817,6 +1127,8 @@ int bt_convert__perf2ctf(const char *input, const char *path, bool force)
 	struct ctf_writer *cw = &c.writer;
 	int err = -1;
 
+	perf_config(convert__config, &c);
+
 	/* CTF writer */
 	if (ctf_writer__init(cw, path))
 		return -1;
@@ -826,6 +1138,11 @@ int bt_convert__perf2ctf(const char *input, const char *path, bool force)
 	if (!session)
 		goto free_writer;
 
+	if (c.queue_size) {
+		ordered_events__set_alloc_size(&session->ordered_events,
+					       c.queue_size);
+	}
+
 	/* CTF writer env/clock setup  */
 	if (ctf_writer__setup_env(cw, session))
 		goto free_session;
@@ -834,9 +1151,14 @@ int bt_convert__perf2ctf(const char *input, const char *path, bool force)
 	if (setup_events(cw, session))
 		goto free_session;
 
+	if (setup_streams(cw, session))
+		goto free_session;
+
 	err = perf_session__process_events(session);
 	if (!err)
-		err = bt_ctf_stream_flush(cw->stream);
+		err = ctf_writer__flush_streams(cw);
+	else
+		pr_err("Error during conversion.\n");
 
 	fprintf(stderr,
 		"[ perf data convert: Converted '%s' into CTF data '%s' ]\n",
@@ -847,11 +1169,15 @@ int bt_convert__perf2ctf(const char *input, const char *path, bool force)
 		(double) c.events_size / 1024.0 / 1024.0,
 		c.events_count);
 
-	/* its all good */
-free_session:
 	perf_session__delete(session);
+	ctf_writer__cleanup(cw);
+
+	return err;
 
+free_session:
+	perf_session__delete(session);
 free_writer:
 	ctf_writer__cleanup(cw);
+	pr_err("Error during conversion setup.\n");
 	return err;
 }
diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c
index bb39a3ffc70b..1c9689e4cc17 100644
--- a/tools/perf/util/db-export.c
+++ b/tools/perf/util/db-export.c
@@ -122,6 +122,7 @@ int db_export__machine(struct db_export *dbe, struct machine *machine)
 int db_export__thread(struct db_export *dbe, struct thread *thread,
 		      struct machine *machine, struct comm *comm)
 {
+	struct thread *main_thread;
 	u64 main_thread_db_id = 0;
 	int err;
 
@@ -131,8 +132,6 @@ int db_export__thread(struct db_export *dbe, struct thread *thread,
 	thread->db_id = ++dbe->thread_last_db_id;
 
 	if (thread->pid_ != -1) {
-		struct thread *main_thread;
-
 		if (thread->pid_ == thread->tid) {
 			main_thread = thread;
 		} else {
@@ -144,14 +143,16 @@ int db_export__thread(struct db_export *dbe, struct thread *thread,
 			err = db_export__thread(dbe, main_thread, machine,
 						comm);
 			if (err)
-				return err;
+				goto out_put;
 			if (comm) {
 				err = db_export__comm_thread(dbe, comm, thread);
 				if (err)
-					return err;
+					goto out_put;
 			}
 		}
 		main_thread_db_id = main_thread->db_id;
+		if (main_thread != thread)
+			thread__put(main_thread);
 	}
 
 	if (dbe->export_thread)
@@ -159,6 +160,10 @@ int db_export__thread(struct db_export *dbe, struct thread *thread,
 					  machine);
 
 	return 0;
+
+out_put:
+	thread__put(main_thread);
+	return err;
 }
 
 int db_export__comm(struct db_export *dbe, struct comm *comm,
@@ -229,7 +234,7 @@ int db_export__symbol(struct db_export *dbe, struct symbol *sym,
 static struct thread *get_main_thread(struct machine *machine, struct thread *thread)
 {
 	if (thread->pid_ == thread->tid)
-		return thread;
+		return thread__get(thread);
 
 	if (thread->pid_ == -1)
 		return NULL;
@@ -309,12 +314,12 @@ int db_export__sample(struct db_export *dbe, union perf_event *event,
 
 	err = db_export__thread(dbe, thread, al->machine, comm);
 	if (err)
-		return err;
+		goto out_put;
 
 	if (comm) {
 		err = db_export__comm(dbe, comm, main_thread);
 		if (err)
-			return err;
+			goto out_put;
 		es.comm_db_id = comm->db_id;
 	}
 
@@ -322,7 +327,7 @@ int db_export__sample(struct db_export *dbe, union perf_event *event,
 
 	err = db_ids_from_al(dbe, al, &es.dso_db_id, &es.sym_db_id, &es.offset);
 	if (err)
-		return err;
+		goto out_put;
 
 	if ((evsel->attr.sample_type & PERF_SAMPLE_ADDR) &&
 	    sample_addr_correlates_sym(&evsel->attr)) {
@@ -332,20 +337,22 @@ int db_export__sample(struct db_export *dbe, union perf_event *event,
 		err = db_ids_from_al(dbe, &addr_al, &es.addr_dso_db_id,
 				     &es.addr_sym_db_id, &es.addr_offset);
 		if (err)
-			return err;
+			goto out_put;
 		if (dbe->crp) {
 			err = thread_stack__process(thread, comm, sample, al,
 						    &addr_al, es.db_id,
 						    dbe->crp);
 			if (err)
-				return err;
+				goto out_put;
 		}
 	}
 
 	if (dbe->export_sample)
-		return dbe->export_sample(dbe, &es);
+		err = dbe->export_sample(dbe, &es);
 
-	return 0;
+out_put:
+	thread__put(main_thread);
+	return err;
 }
 
 static struct {
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index fc0ddd5792a9..7c0c08386a1d 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -4,6 +4,7 @@
 #include "symbol.h"
 #include "dso.h"
 #include "machine.h"
+#include "auxtrace.h"
 #include "util.h"
 #include "debug.h"
 
@@ -165,12 +166,28 @@ bool is_supported_compression(const char *ext)
 	return false;
 }
 
-bool is_kernel_module(const char *pathname)
+bool is_kernel_module(const char *pathname, int cpumode)
 {
 	struct kmod_path m;
-
-	if (kmod_path__parse(&m, pathname))
-		return NULL;
+	int mode = cpumode & PERF_RECORD_MISC_CPUMODE_MASK;
+
+	WARN_ONCE(mode != cpumode,
+		  "Internal error: passing unmasked cpumode (%x) to is_kernel_module",
+		  cpumode);
+
+	switch (mode) {
+	case PERF_RECORD_MISC_USER:
+	case PERF_RECORD_MISC_HYPERVISOR:
+	case PERF_RECORD_MISC_GUEST_USER:
+		return false;
+	/* Treat PERF_RECORD_MISC_CPUMODE_UNKNOWN as kernel */
+	default:
+		if (kmod_path__parse(&m, pathname)) {
+			pr_err("Failed to check whether %s is a kernel module or not. Assume it is.",
+					pathname);
+			return true;
+		}
+	}
 
 	return m.kmod;
 }
@@ -214,12 +231,33 @@ int __kmod_path__parse(struct kmod_path *m, const char *path,
 {
 	const char *name = strrchr(path, '/');
 	const char *ext  = strrchr(path, '.');
+	bool is_simple_name = false;
 
 	memset(m, 0x0, sizeof(*m));
 	name = name ? name + 1 : path;
 
+	/*
+	 * '.' is also a valid character for module name. For example:
+	 * [aaa.bbb] is a valid module name. '[' should have higher
+	 * priority than '.ko' suffix.
+	 *
+	 * The kernel names are from machine__mmap_name. Such
+	 * name should belong to kernel itself, not kernel module.
+	 */
+	if (name[0] == '[') {
+		is_simple_name = true;
+		if ((strncmp(name, "[kernel.kallsyms]", 17) == 0) ||
+		    (strncmp(name, "[guest.kernel.kallsyms", 22) == 0) ||
+		    (strncmp(name, "[vdso]", 6) == 0) ||
+		    (strncmp(name, "[vsyscall]", 10) == 0)) {
+			m->kmod = false;
+
+		} else
+			m->kmod = true;
+	}
+
 	/* No extension, just return name. */
-	if (ext == NULL) {
+	if ((ext == NULL) || is_simple_name) {
 		if (alloc_name) {
 			m->name = strdup(name);
 			return m->name ? 0 : -ENOMEM;
@@ -264,6 +302,7 @@ int __kmod_path__parse(struct kmod_path *m, const char *path,
  */
 static LIST_HEAD(dso__data_open);
 static long dso__data_open_cnt;
+static pthread_mutex_t dso__data_open_lock = PTHREAD_MUTEX_INITIALIZER;
 
 static void dso__list_add(struct dso *dso)
 {
@@ -433,18 +472,12 @@ static void check_data_close(void)
  */
 void dso__data_close(struct dso *dso)
 {
+	pthread_mutex_lock(&dso__data_open_lock);
 	close_dso(dso);
+	pthread_mutex_unlock(&dso__data_open_lock);
 }
 
-/**
- * dso__data_fd - Get dso's data file descriptor
- * @dso: dso object
- * @machine: machine object
- *
- * External interface to find dso's file, open it and
- * returns file descriptor.
- */
-int dso__data_fd(struct dso *dso, struct machine *machine)
+static void try_to_open_dso(struct dso *dso, struct machine *machine)
 {
 	enum dso_binary_type binary_type_data[] = {
 		DSO_BINARY_TYPE__BUILD_ID_CACHE,
@@ -453,11 +486,8 @@ int dso__data_fd(struct dso *dso, struct machine *machine)
 	};
 	int i = 0;
 
-	if (dso->data.status == DSO_DATA_STATUS_ERROR)
-		return -1;
-
 	if (dso->data.fd >= 0)
-		goto out;
+		return;
 
 	if (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND) {
 		dso->data.fd = open_dso(dso, machine);
@@ -477,10 +507,38 @@ out:
 		dso->data.status = DSO_DATA_STATUS_OK;
 	else
 		dso->data.status = DSO_DATA_STATUS_ERROR;
+}
+
+/**
+ * dso__data_get_fd - Get dso's data file descriptor
+ * @dso: dso object
+ * @machine: machine object
+ *
+ * External interface to find dso's file, open it and
+ * returns file descriptor.  It should be paired with
+ * dso__data_put_fd() if it returns non-negative value.
+ */
+int dso__data_get_fd(struct dso *dso, struct machine *machine)
+{
+	if (dso->data.status == DSO_DATA_STATUS_ERROR)
+		return -1;
+
+	if (pthread_mutex_lock(&dso__data_open_lock) < 0)
+		return -1;
+
+	try_to_open_dso(dso, machine);
+
+	if (dso->data.fd < 0)
+		pthread_mutex_unlock(&dso__data_open_lock);
 
 	return dso->data.fd;
 }
 
+void dso__data_put_fd(struct dso *dso __maybe_unused)
+{
+	pthread_mutex_unlock(&dso__data_open_lock);
+}
+
 bool dso__data_status_seen(struct dso *dso, enum dso_data_status_seen by)
 {
 	u32 flag = 1 << by;
@@ -494,10 +552,12 @@ bool dso__data_status_seen(struct dso *dso, enum dso_data_status_seen by)
 }
 
 static void
-dso_cache__free(struct rb_root *root)
+dso_cache__free(struct dso *dso)
 {
+	struct rb_root *root = &dso->data.cache;
 	struct rb_node *next = rb_first(root);
 
+	pthread_mutex_lock(&dso->lock);
 	while (next) {
 		struct dso_cache *cache;
 
@@ -506,10 +566,12 @@ dso_cache__free(struct rb_root *root)
 		rb_erase(&cache->rb_node, root);
 		free(cache);
 	}
+	pthread_mutex_unlock(&dso->lock);
 }
 
-static struct dso_cache *dso_cache__find(const struct rb_root *root, u64 offset)
+static struct dso_cache *dso_cache__find(struct dso *dso, u64 offset)
 {
+	const struct rb_root *root = &dso->data.cache;
 	struct rb_node * const *p = &root->rb_node;
 	const struct rb_node *parent = NULL;
 	struct dso_cache *cache;
@@ -528,17 +590,20 @@ static struct dso_cache *dso_cache__find(const struct rb_root *root, u64 offset)
 		else
 			return cache;
 	}
+
 	return NULL;
 }
 
-static void
-dso_cache__insert(struct rb_root *root, struct dso_cache *new)
+static struct dso_cache *
+dso_cache__insert(struct dso *dso, struct dso_cache *new)
 {
+	struct rb_root *root = &dso->data.cache;
 	struct rb_node **p = &root->rb_node;
 	struct rb_node *parent = NULL;
 	struct dso_cache *cache;
 	u64 offset = new->offset;
 
+	pthread_mutex_lock(&dso->lock);
 	while (*p != NULL) {
 		u64 end;
 
@@ -550,10 +615,17 @@ dso_cache__insert(struct rb_root *root, struct dso_cache *new)
 			p = &(*p)->rb_left;
 		else if (offset >= end)
 			p = &(*p)->rb_right;
+		else
+			goto out;
 	}
 
 	rb_link_node(&new->rb_node, parent, p);
 	rb_insert_color(&new->rb_node, root);
+
+	cache = NULL;
+out:
+	pthread_mutex_unlock(&dso->lock);
+	return cache;
 }
 
 static ssize_t
@@ -568,19 +640,33 @@ dso_cache__memcpy(struct dso_cache *cache, u64 offset,
 }
 
 static ssize_t
-dso_cache__read(struct dso *dso, u64 offset, u8 *data, ssize_t size)
+dso_cache__read(struct dso *dso, struct machine *machine,
+		u64 offset, u8 *data, ssize_t size)
 {
 	struct dso_cache *cache;
+	struct dso_cache *old;
 	ssize_t ret;
 
 	do {
 		u64 cache_offset;
 
-		ret = -ENOMEM;
-
 		cache = zalloc(sizeof(*cache) + DSO__DATA_CACHE_SIZE);
 		if (!cache)
+			return -ENOMEM;
+
+		pthread_mutex_lock(&dso__data_open_lock);
+
+		/*
+		 * dso->data.fd might be closed if other thread opened another
+		 * file (dso) due to open file limit (RLIMIT_NOFILE).
+		 */
+		try_to_open_dso(dso, machine);
+
+		if (dso->data.fd < 0) {
+			ret = -errno;
+			dso->data.status = DSO_DATA_STATUS_ERROR;
 			break;
+		}
 
 		cache_offset = offset & DSO__DATA_CACHE_MASK;
 
@@ -590,11 +676,20 @@ dso_cache__read(struct dso *dso, u64 offset, u8 *data, ssize_t size)
 
 		cache->offset = cache_offset;
 		cache->size   = ret;
-		dso_cache__insert(&dso->data.cache, cache);
+	} while (0);
 
-		ret = dso_cache__memcpy(cache, offset, data, size);
+	pthread_mutex_unlock(&dso__data_open_lock);
 
-	} while (0);
+	if (ret > 0) {
+		old = dso_cache__insert(dso, cache);
+		if (old) {
+			/* we lose the race */
+			free(cache);
+			cache = old;
+		}
+
+		ret = dso_cache__memcpy(cache, offset, data, size);
+	}
 
 	if (ret <= 0)
 		free(cache);
@@ -602,16 +697,16 @@ dso_cache__read(struct dso *dso, u64 offset, u8 *data, ssize_t size)
 	return ret;
 }
 
-static ssize_t dso_cache_read(struct dso *dso, u64 offset,
-			      u8 *data, ssize_t size)
+static ssize_t dso_cache_read(struct dso *dso, struct machine *machine,
+			      u64 offset, u8 *data, ssize_t size)
 {
 	struct dso_cache *cache;
 
-	cache = dso_cache__find(&dso->data.cache, offset);
+	cache = dso_cache__find(dso, offset);
 	if (cache)
 		return dso_cache__memcpy(cache, offset, data, size);
 	else
-		return dso_cache__read(dso, offset, data, size);
+		return dso_cache__read(dso, machine, offset, data, size);
 }
 
 /*
@@ -619,7 +714,8 @@ static ssize_t dso_cache_read(struct dso *dso, u64 offset,
  * in the rb_tree. Any read to already cached data is served
  * by cached data.
  */
-static ssize_t cached_read(struct dso *dso, u64 offset, u8 *data, ssize_t size)
+static ssize_t cached_read(struct dso *dso, struct machine *machine,
+			   u64 offset, u8 *data, ssize_t size)
 {
 	ssize_t r = 0;
 	u8 *p = data;
@@ -627,7 +723,7 @@ static ssize_t cached_read(struct dso *dso, u64 offset, u8 *data, ssize_t size)
 	do {
 		ssize_t ret;
 
-		ret = dso_cache_read(dso, offset, p, size);
+		ret = dso_cache_read(dso, machine, offset, p, size);
 		if (ret < 0)
 			return ret;
 
@@ -647,21 +743,44 @@ static ssize_t cached_read(struct dso *dso, u64 offset, u8 *data, ssize_t size)
 	return r;
 }
 
-static int data_file_size(struct dso *dso)
+static int data_file_size(struct dso *dso, struct machine *machine)
 {
+	int ret = 0;
 	struct stat st;
 	char sbuf[STRERR_BUFSIZE];
 
-	if (!dso->data.file_size) {
-		if (fstat(dso->data.fd, &st)) {
-			pr_err("dso mmap failed, fstat: %s\n",
-				strerror_r(errno, sbuf, sizeof(sbuf)));
-			return -1;
-		}
-		dso->data.file_size = st.st_size;
+	if (dso->data.file_size)
+		return 0;
+
+	if (dso->data.status == DSO_DATA_STATUS_ERROR)
+		return -1;
+
+	pthread_mutex_lock(&dso__data_open_lock);
+
+	/*
+	 * dso->data.fd might be closed if other thread opened another
+	 * file (dso) due to open file limit (RLIMIT_NOFILE).
+	 */
+	try_to_open_dso(dso, machine);
+
+	if (dso->data.fd < 0) {
+		ret = -errno;
+		dso->data.status = DSO_DATA_STATUS_ERROR;
+		goto out;
 	}
 
-	return 0;
+	if (fstat(dso->data.fd, &st) < 0) {
+		ret = -errno;
+		pr_err("dso cache fstat failed: %s\n",
+		       strerror_r(errno, sbuf, sizeof(sbuf)));
+		dso->data.status = DSO_DATA_STATUS_ERROR;
+		goto out;
+	}
+	dso->data.file_size = st.st_size;
+
+out:
+	pthread_mutex_unlock(&dso__data_open_lock);
+	return ret;
 }
 
 /**
@@ -673,23 +792,17 @@ static int data_file_size(struct dso *dso)
  */
 off_t dso__data_size(struct dso *dso, struct machine *machine)
 {
-	int fd;
-
-	fd = dso__data_fd(dso, machine);
-	if (fd < 0)
-		return fd;
-
-	if (data_file_size(dso))
+	if (data_file_size(dso, machine))
 		return -1;
 
 	/* For now just estimate dso data size is close to file size */
 	return dso->data.file_size;
 }
 
-static ssize_t data_read_offset(struct dso *dso, u64 offset,
-				u8 *data, ssize_t size)
+static ssize_t data_read_offset(struct dso *dso, struct machine *machine,
+				u64 offset, u8 *data, ssize_t size)
 {
-	if (data_file_size(dso))
+	if (data_file_size(dso, machine))
 		return -1;
 
 	/* Check the offset sanity. */
@@ -699,7 +812,7 @@ static ssize_t data_read_offset(struct dso *dso, u64 offset,
 	if (offset + size < offset)
 		return -1;
 
-	return cached_read(dso, offset, data, size);
+	return cached_read(dso, machine, offset, data, size);
 }
 
 /**
@@ -716,10 +829,10 @@ static ssize_t data_read_offset(struct dso *dso, u64 offset,
 ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
 			      u64 offset, u8 *data, ssize_t size)
 {
-	if (dso__data_fd(dso, machine) < 0)
+	if (dso->data.status == DSO_DATA_STATUS_ERROR)
 		return -1;
 
-	return data_read_offset(dso, offset, data, size);
+	return data_read_offset(dso, machine, offset, data, size);
 }
 
 /**
@@ -751,13 +864,13 @@ struct map *dso__new_map(const char *name)
 	return map;
 }
 
-struct dso *dso__kernel_findnew(struct machine *machine, const char *name,
-		    const char *short_name, int dso_type)
+struct dso *machine__findnew_kernel(struct machine *machine, const char *name,
+				    const char *short_name, int dso_type)
 {
 	/*
 	 * The kernel dso could be created by build_id processing.
 	 */
-	struct dso *dso = __dsos__findnew(&machine->kernel_dsos, name);
+	struct dso *dso = machine__findnew_dso(machine, name);
 
 	/*
 	 * We need to run this in all cases, since during the build_id
@@ -776,8 +889,8 @@ struct dso *dso__kernel_findnew(struct machine *machine, const char *name,
  * Either one of the dso or name parameter must be non-NULL or the
  * function will not work.
  */
-static struct dso *dso__findlink_by_longname(struct rb_root *root,
-					     struct dso *dso, const char *name)
+static struct dso *__dso__findlink_by_longname(struct rb_root *root,
+					       struct dso *dso, const char *name)
 {
 	struct rb_node **p = &root->rb_node;
 	struct rb_node  *parent = NULL;
@@ -824,10 +937,10 @@ static struct dso *dso__findlink_by_longname(struct rb_root *root,
 	return NULL;
 }
 
-static inline struct dso *
-dso__find_by_longname(const struct rb_root *root, const char *name)
+static inline struct dso *__dso__find_by_longname(struct rb_root *root,
+						  const char *name)
 {
-	return dso__findlink_by_longname((struct rb_root *)root, NULL, name);
+	return __dso__findlink_by_longname(root, NULL, name);
 }
 
 void dso__set_long_name(struct dso *dso, const char *name, bool name_allocated)
@@ -935,6 +1048,8 @@ struct dso *dso__new(const char *name)
 		RB_CLEAR_NODE(&dso->rb_node);
 		INIT_LIST_HEAD(&dso->node);
 		INIT_LIST_HEAD(&dso->data.open_entry);
+		pthread_mutex_init(&dso->lock, NULL);
+		atomic_set(&dso->refcnt, 1);
 	}
 
 	return dso;
@@ -961,12 +1076,27 @@ void dso__delete(struct dso *dso)
 	}
 
 	dso__data_close(dso);
-	dso_cache__free(&dso->data.cache);
+	auxtrace_cache__free(dso->auxtrace_cache);
+	dso_cache__free(dso);
 	dso__free_a2l(dso);
 	zfree(&dso->symsrc_filename);
+	pthread_mutex_destroy(&dso->lock);
 	free(dso);
 }
 
+struct dso *dso__get(struct dso *dso)
+{
+	if (dso)
+		atomic_inc(&dso->refcnt);
+	return dso;
+}
+
+void dso__put(struct dso *dso)
+{
+	if (dso && atomic_dec_and_test(&dso->refcnt))
+		dso__delete(dso);
+}
+
 void dso__set_build_id(struct dso *dso, void *build_id)
 {
 	memcpy(dso->build_id, build_id, sizeof(dso->build_id));
@@ -1033,14 +1163,41 @@ bool __dsos__read_build_ids(struct list_head *head, bool with_hits)
 	return have_build_id;
 }
 
-void dsos__add(struct dsos *dsos, struct dso *dso)
+void __dsos__add(struct dsos *dsos, struct dso *dso)
 {
 	list_add_tail(&dso->node, &dsos->head);
-	dso__findlink_by_longname(&dsos->root, dso, NULL);
+	__dso__findlink_by_longname(&dsos->root, dso, NULL);
+	/*
+	 * It is now in the linked list, grab a reference, then garbage collect
+	 * this when needing memory, by looking at LRU dso instances in the
+	 * list with atomic_read(&dso->refcnt) == 1, i.e. no references
+	 * anywhere besides the one for the list, do, under a lock for the
+	 * list: remove it from the list, then a dso__put(), that probably will
+	 * be the last and will then call dso__delete(), end of life.
+	 *
+	 * That, or at the end of the 'struct machine' lifetime, when all
+	 * 'struct dso' instances will be removed from the list, in
+	 * dsos__exit(), if they have no other reference from some other data
+	 * structure.
+	 *
+	 * E.g.: after processing a 'perf.data' file and storing references
+	 * to objects instantiated while processing events, we will have
+	 * references to the 'thread', 'map', 'dso' structs all from 'struct
+	 * hist_entry' instances, but we may not need anything not referenced,
+	 * so we might as well call machines__exit()/machines__delete() and
+	 * garbage collect it.
+	 */
+	dso__get(dso);
+}
+
+void dsos__add(struct dsos *dsos, struct dso *dso)
+{
+	pthread_rwlock_wrlock(&dsos->lock);
+	__dsos__add(dsos, dso);
+	pthread_rwlock_unlock(&dsos->lock);
 }
 
-struct dso *dsos__find(const struct dsos *dsos, const char *name,
-		       bool cmp_short)
+struct dso *__dsos__find(struct dsos *dsos, const char *name, bool cmp_short)
 {
 	struct dso *pos;
 
@@ -1050,15 +1207,24 @@ struct dso *dsos__find(const struct dsos *dsos, const char *name,
 				return pos;
 		return NULL;
 	}
-	return dso__find_by_longname(&dsos->root, name);
+	return __dso__find_by_longname(&dsos->root, name);
+}
+
+struct dso *dsos__find(struct dsos *dsos, const char *name, bool cmp_short)
+{
+	struct dso *dso;
+	pthread_rwlock_rdlock(&dsos->lock);
+	dso = __dsos__find(dsos, name, cmp_short);
+	pthread_rwlock_unlock(&dsos->lock);
+	return dso;
 }
 
-struct dso *dsos__addnew(struct dsos *dsos, const char *name)
+struct dso *__dsos__addnew(struct dsos *dsos, const char *name)
 {
 	struct dso *dso = dso__new(name);
 
 	if (dso != NULL) {
-		dsos__add(dsos, dso);
+		__dsos__add(dsos, dso);
 		dso__set_basename(dso);
 	}
 	return dso;
@@ -1066,9 +1232,18 @@ struct dso *dsos__addnew(struct dsos *dsos, const char *name)
 
 struct dso *__dsos__findnew(struct dsos *dsos, const char *name)
 {
-	struct dso *dso = dsos__find(dsos, name, false);
+	struct dso *dso = __dsos__find(dsos, name, false);
 
-	return dso ? dso : dsos__addnew(dsos, name);
+	return dso ? dso : __dsos__addnew(dsos, name);
+}
+
+struct dso *dsos__findnew(struct dsos *dsos, const char *name)
+{
+	struct dso *dso;
+	pthread_rwlock_wrlock(&dsos->lock);
+	dso = dso__get(__dsos__findnew(dsos, name));
+	pthread_rwlock_unlock(&dsos->lock);
+	return dso;
 }
 
 size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp,
@@ -1130,12 +1305,15 @@ size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp)
 enum dso_type dso__type(struct dso *dso, struct machine *machine)
 {
 	int fd;
+	enum dso_type type = DSO__TYPE_UNKNOWN;
 
-	fd = dso__data_fd(dso, machine);
-	if (fd < 0)
-		return DSO__TYPE_UNKNOWN;
+	fd = dso__data_get_fd(dso, machine);
+	if (fd >= 0) {
+		type = dso__type_fd(fd);
+		dso__data_put_fd(dso);
+	}
 
-	return dso__type_fd(fd);
+	return type;
 }
 
 int dso__strerror_load(struct dso *dso, char *buf, size_t buflen)
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index e0901b4ed8de..2fe98bb0e95b 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -1,9 +1,11 @@
 #ifndef __PERF_DSO
 #define __PERF_DSO
 
+#include <linux/atomic.h>
 #include <linux/types.h>
 #include <linux/rbtree.h>
 #include <stdbool.h>
+#include <pthread.h>
 #include <linux/types.h>
 #include <linux/bitops.h>
 #include "map.h"
@@ -124,9 +126,13 @@ struct dso_cache {
 struct dsos {
 	struct list_head head;
 	struct rb_root	 root;	/* rbtree root sorted by long name */
+	pthread_rwlock_t lock;
 };
 
+struct auxtrace_cache;
+
 struct dso {
+	pthread_mutex_t	 lock;
 	struct list_head node;
 	struct rb_node	 rb_node;	/* rbtree node sorted by long name */
 	struct rb_root	 symbols[MAP__NR_TYPES];
@@ -156,6 +162,7 @@ struct dso {
 	u16		 long_name_len;
 	u16		 short_name_len;
 	void		*dwfl;			/* DWARF debug info */
+	struct auxtrace_cache *auxtrace_cache;
 
 	/* dso data file */
 	struct {
@@ -173,7 +180,7 @@ struct dso {
 		void	 *priv;
 		u64	 db_id;
 	};
-
+	atomic_t	 refcnt;
 	char		 name[0];
 };
 
@@ -200,6 +207,17 @@ void dso__set_long_name(struct dso *dso, const char *name, bool name_allocated);
 
 int dso__name_len(const struct dso *dso);
 
+struct dso *dso__get(struct dso *dso);
+void dso__put(struct dso *dso);
+
+static inline void __dso__zput(struct dso **dso)
+{
+	dso__put(*dso);
+	*dso = NULL;
+}
+
+#define dso__zput(dso) __dso__zput(&dso)
+
 bool dso__loaded(const struct dso *dso, enum map_type type);
 
 bool dso__sorted_by_name(const struct dso *dso, enum map_type type);
@@ -216,7 +234,7 @@ char dso__symtab_origin(const struct dso *dso);
 int dso__read_binary_type_filename(const struct dso *dso, enum dso_binary_type type,
 				   char *root_dir, char *filename, size_t size);
 bool is_supported_compression(const char *ext);
-bool is_kernel_module(const char *pathname);
+bool is_kernel_module(const char *pathname, int cpumode);
 bool decompress_to_file(const char *ext, const char *filename, int output_fd);
 bool dso__needs_decompress(struct dso *dso);
 
@@ -236,7 +254,8 @@ int __kmod_path__parse(struct kmod_path *m, const char *path,
 
 /*
  * The dso__data_* external interface provides following functions:
- *   dso__data_fd
+ *   dso__data_get_fd
+ *   dso__data_put_fd
  *   dso__data_close
  *   dso__data_size
  *   dso__data_read_offset
@@ -253,8 +272,11 @@ int __kmod_path__parse(struct kmod_path *m, const char *path,
  * The current usage of the dso__data_* interface is as follows:
  *
  * Get DSO's fd:
- *   int fd = dso__data_fd(dso, machine);
- *   USE 'fd' SOMEHOW
+ *   int fd = dso__data_get_fd(dso, machine);
+ *   if (fd >= 0) {
+ *       USE 'fd' SOMEHOW
+ *       dso__data_put_fd(dso);
+ *   }
  *
  * Read DSO's data:
  *   n = dso__data_read_offset(dso_0, &machine, 0, buf, BUFSIZE);
@@ -273,7 +295,8 @@ int __kmod_path__parse(struct kmod_path *m, const char *path,
  *
  * TODO
 */
-int dso__data_fd(struct dso *dso, struct machine *machine);
+int dso__data_get_fd(struct dso *dso, struct machine *machine);
+void dso__data_put_fd(struct dso *dso __maybe_unused);
 void dso__data_close(struct dso *dso);
 
 off_t dso__data_size(struct dso *dso, struct machine *machine);
@@ -285,14 +308,16 @@ ssize_t dso__data_read_addr(struct dso *dso, struct map *map,
 bool dso__data_status_seen(struct dso *dso, enum dso_data_status_seen by);
 
 struct map *dso__new_map(const char *name);
-struct dso *dso__kernel_findnew(struct machine *machine, const char *name,
-				const char *short_name, int dso_type);
+struct dso *machine__findnew_kernel(struct machine *machine, const char *name,
+				    const char *short_name, int dso_type);
 
+void __dsos__add(struct dsos *dsos, struct dso *dso);
 void dsos__add(struct dsos *dsos, struct dso *dso);
-struct dso *dsos__addnew(struct dsos *dsos, const char *name);
-struct dso *dsos__find(const struct dsos *dsos, const char *name,
-		       bool cmp_short);
+struct dso *__dsos__addnew(struct dsos *dsos, const char *name);
+struct dso *__dsos__find(struct dsos *dsos, const char *name, bool cmp_short);
+struct dso *dsos__find(struct dsos *dsos, const char *name, bool cmp_short);
 struct dso *__dsos__findnew(struct dsos *dsos, const char *name);
+struct dso *dsos__findnew(struct dsos *dsos, const char *name);
 bool __dsos__read_build_ids(struct list_head *head, bool with_hits);
 
 size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp,
diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
index c34e024020c7..57f3ef41c2bc 100644
--- a/tools/perf/util/dwarf-aux.c
+++ b/tools/perf/util/dwarf-aux.c
@@ -139,11 +139,27 @@ int cu_walk_functions_at(Dwarf_Die *cu_die, Dwarf_Addr addr,
 bool die_compare_name(Dwarf_Die *dw_die, const char *tname)
 {
 	const char *name;
+
 	name = dwarf_diename(dw_die);
 	return name ? (strcmp(tname, name) == 0) : false;
 }
 
 /**
+ * die_match_name - Match diename and glob
+ * @dw_die: a DIE
+ * @glob: a string of target glob pattern
+ *
+ * Glob matching the name of @dw_die and @glob. Return false if matching fail.
+ */
+bool die_match_name(Dwarf_Die *dw_die, const char *glob)
+{
+	const char *name;
+
+	name = dwarf_diename(dw_die);
+	return name ? strglobmatch(name, glob) : false;
+}
+
+/**
  * die_get_call_lineno - Get callsite line number of inline-function instance
  * @in_die: a DIE of an inlined function instance
  *
@@ -417,6 +433,43 @@ struct __addr_die_search_param {
 	Dwarf_Die	*die_mem;
 };
 
+static int __die_search_func_tail_cb(Dwarf_Die *fn_die, void *data)
+{
+	struct __addr_die_search_param *ad = data;
+	Dwarf_Addr addr = 0;
+
+	if (dwarf_tag(fn_die) == DW_TAG_subprogram &&
+	    !dwarf_highpc(fn_die, &addr) &&
+	    addr == ad->addr) {
+		memcpy(ad->die_mem, fn_die, sizeof(Dwarf_Die));
+		return DWARF_CB_ABORT;
+	}
+	return DWARF_CB_OK;
+}
+
+/**
+ * die_find_tailfunc - Search for a non-inlined function with tail call at
+ * given address
+ * @cu_die: a CU DIE which including @addr
+ * @addr: target address
+ * @die_mem: a buffer for result DIE
+ *
+ * Search for a non-inlined function DIE with tail call at @addr. Stores the
+ * DIE to @die_mem and returns it if found. Returns NULL if failed.
+ */
+Dwarf_Die *die_find_tailfunc(Dwarf_Die *cu_die, Dwarf_Addr addr,
+				    Dwarf_Die *die_mem)
+{
+	struct __addr_die_search_param ad;
+	ad.addr = addr;
+	ad.die_mem = die_mem;
+	/* dwarf_getscopes can't find subprogram. */
+	if (!dwarf_getfuncs(cu_die, __die_search_func_tail_cb, &ad, 0))
+		return NULL;
+	else
+		return die_mem;
+}
+
 /* die_find callback for non-inlined function search */
 static int __die_search_func_cb(Dwarf_Die *fn_die, void *data)
 {
@@ -832,19 +885,17 @@ Dwarf_Die *die_find_member(Dwarf_Die *st_die, const char *name,
 /**
  * die_get_typename - Get the name of given variable DIE
  * @vr_die: a variable DIE
- * @buf: a buffer for result type name
- * @len: a max-length of @buf
+ * @buf: a strbuf for result type name
  *
- * Get the name of @vr_die and stores it to @buf. Return the actual length
- * of type name if succeeded. Return -E2BIG if @len is not enough long, and
- * Return -ENOENT if failed to find type name.
+ * Get the name of @vr_die and stores it to @buf. Return 0 if succeeded.
+ * and Return -ENOENT if failed to find type name.
  * Note that the result will stores typedef name if possible, and stores
  * "*(function_type)" if the type is a function pointer.
  */
-int die_get_typename(Dwarf_Die *vr_die, char *buf, int len)
+int die_get_typename(Dwarf_Die *vr_die, struct strbuf *buf)
 {
 	Dwarf_Die type;
-	int tag, ret, ret2;
+	int tag, ret;
 	const char *tmp = "";
 
 	if (__die_get_real_type(vr_die, &type) == NULL)
@@ -855,8 +906,8 @@ int die_get_typename(Dwarf_Die *vr_die, char *buf, int len)
 		tmp = "*";
 	else if (tag == DW_TAG_subroutine_type) {
 		/* Function pointer */
-		ret = snprintf(buf, len, "(function_type)");
-		return (ret >= len) ? -E2BIG : ret;
+		strbuf_addf(buf, "(function_type)");
+		return 0;
 	} else {
 		if (!dwarf_diename(&type))
 			return -ENOENT;
@@ -867,39 +918,156 @@ int die_get_typename(Dwarf_Die *vr_die, char *buf, int len)
 		else if (tag == DW_TAG_enumeration_type)
 			tmp = "enum ";
 		/* Write a base name */
-		ret = snprintf(buf, len, "%s%s", tmp, dwarf_diename(&type));
-		return (ret >= len) ? -E2BIG : ret;
-	}
-	ret = die_get_typename(&type, buf, len);
-	if (ret > 0) {
-		ret2 = snprintf(buf + ret, len - ret, "%s", tmp);
-		ret = (ret2 >= len - ret) ? -E2BIG : ret2 + ret;
+		strbuf_addf(buf, "%s%s", tmp, dwarf_diename(&type));
+		return 0;
 	}
+	ret = die_get_typename(&type, buf);
+	if (ret == 0)
+		strbuf_addf(buf, "%s", tmp);
+
 	return ret;
 }
 
 /**
  * die_get_varname - Get the name and type of given variable DIE
  * @vr_die: a variable DIE
- * @buf: a buffer for type and variable name
- * @len: the max-length of @buf
+ * @buf: a strbuf for type and variable name
  *
  * Get the name and type of @vr_die and stores it in @buf as "type\tname".
  */
-int die_get_varname(Dwarf_Die *vr_die, char *buf, int len)
+int die_get_varname(Dwarf_Die *vr_die, struct strbuf *buf)
 {
-	int ret, ret2;
+	int ret;
 
-	ret = die_get_typename(vr_die, buf, len);
+	ret = die_get_typename(vr_die, buf);
 	if (ret < 0) {
 		pr_debug("Failed to get type, make it unknown.\n");
-		ret = snprintf(buf, len, "(unknown_type)");
+		strbuf_addf(buf, "(unknown_type)");
 	}
-	if (ret > 0) {
-		ret2 = snprintf(buf + ret, len - ret, "\t%s",
-				dwarf_diename(vr_die));
-		ret = (ret2 >= len - ret) ? -E2BIG : ret2 + ret;
+
+	strbuf_addf(buf, "\t%s", dwarf_diename(vr_die));
+
+	return 0;
+}
+
+/**
+ * die_get_var_innermost_scope - Get innermost scope range of given variable DIE
+ * @sp_die: a subprogram DIE
+ * @vr_die: a variable DIE
+ * @buf: a strbuf for variable byte offset range
+ *
+ * Get the innermost scope range of @vr_die and stores it in @buf as
+ * "@<function_name+[NN-NN,NN-NN]>".
+ */
+static int die_get_var_innermost_scope(Dwarf_Die *sp_die, Dwarf_Die *vr_die,
+				struct strbuf *buf)
+{
+	Dwarf_Die *scopes;
+	int count;
+	size_t offset = 0;
+	Dwarf_Addr base;
+	Dwarf_Addr start, end;
+	Dwarf_Addr entry;
+	int ret;
+	bool first = true;
+	const char *name;
+
+	ret = dwarf_entrypc(sp_die, &entry);
+	if (ret)
+		return ret;
+
+	name = dwarf_diename(sp_die);
+	if (!name)
+		return -ENOENT;
+
+	count = dwarf_getscopes_die(vr_die, &scopes);
+
+	/* (*SCOPES)[1] is the DIE for the scope containing that scope */
+	if (count <= 1) {
+		ret = -EINVAL;
+		goto out;
 	}
+
+	while ((offset = dwarf_ranges(&scopes[1], offset, &base,
+				&start, &end)) > 0) {
+		start -= entry;
+		end -= entry;
+
+		if (first) {
+			strbuf_addf(buf, "@<%s+[%" PRIu64 "-%" PRIu64,
+				name, start, end);
+			first = false;
+		} else {
+			strbuf_addf(buf, ",%" PRIu64 "-%" PRIu64,
+				start, end);
+		}
+	}
+
+	if (!first)
+		strbuf_addf(buf, "]>");
+
+out:
+	free(scopes);
 	return ret;
 }
 
+/**
+ * die_get_var_range - Get byte offset range of given variable DIE
+ * @sp_die: a subprogram DIE
+ * @vr_die: a variable DIE
+ * @buf: a strbuf for type and variable name and byte offset range
+ *
+ * Get the byte offset range of @vr_die and stores it in @buf as
+ * "@<function_name+[NN-NN,NN-NN]>".
+ */
+int die_get_var_range(Dwarf_Die *sp_die, Dwarf_Die *vr_die, struct strbuf *buf)
+{
+	int ret = 0;
+	Dwarf_Addr base;
+	Dwarf_Addr start, end;
+	Dwarf_Addr entry;
+	Dwarf_Op *op;
+	size_t nops;
+	size_t offset = 0;
+	Dwarf_Attribute attr;
+	bool first = true;
+	const char *name;
+
+	ret = dwarf_entrypc(sp_die, &entry);
+	if (ret)
+		return ret;
+
+	name = dwarf_diename(sp_die);
+	if (!name)
+		return -ENOENT;
+
+	if (dwarf_attr(vr_die, DW_AT_location, &attr) == NULL)
+		return -EINVAL;
+
+	while ((offset = dwarf_getlocations(
+				&attr, offset, &base,
+				&start, &end, &op, &nops)) > 0) {
+		if (start == 0) {
+			/* Single Location Descriptions */
+			ret = die_get_var_innermost_scope(sp_die, vr_die, buf);
+			return ret;
+		}
+
+		/* Location Lists */
+		start -= entry;
+		end -= entry;
+		if (first) {
+			strbuf_addf(buf, "@<%s+[%" PRIu64 "-%" PRIu64,
+				name, start, end);
+			first = false;
+		} else {
+			strbuf_addf(buf, ",%" PRIu64 "-%" PRIu64,
+				start, end);
+		}
+	}
+
+	if (!first)
+		strbuf_addf(buf, "]>");
+
+	return ret;
+}
diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h
index af7dbcd5f929..c42ec366f2a7 100644
--- a/tools/perf/util/dwarf-aux.h
+++ b/tools/perf/util/dwarf-aux.h
@@ -47,6 +47,9 @@ extern bool die_is_func_instance(Dwarf_Die *dw_die);
 /* Compare diename and tname */
 extern bool die_compare_name(Dwarf_Die *dw_die, const char *tname);
 
+/* Matching diename with glob pattern */
+extern bool die_match_name(Dwarf_Die *dw_die, const char *glob);
+
 /* Get callsite line number of inline-function instance */
 extern int die_get_call_lineno(Dwarf_Die *in_die);
 
@@ -82,6 +85,10 @@ extern Dwarf_Die *die_find_child(Dwarf_Die *rt_die,
 extern Dwarf_Die *die_find_realfunc(Dwarf_Die *cu_die, Dwarf_Addr addr,
 				    Dwarf_Die *die_mem);
 
+/* Search a non-inlined function with tail call at given address */
+Dwarf_Die *die_find_tailfunc(Dwarf_Die *cu_die, Dwarf_Addr addr,
+				    Dwarf_Die *die_mem);
+
 /* Search the top inlined function including given address */
 extern Dwarf_Die *die_find_top_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
 					  Dwarf_Die *die_mem);
@@ -114,8 +121,10 @@ extern Dwarf_Die *die_find_member(Dwarf_Die *st_die, const char *name,
 				  Dwarf_Die *die_mem);
 
 /* Get the name of given variable DIE */
-extern int die_get_typename(Dwarf_Die *vr_die, char *buf, int len);
+extern int die_get_typename(Dwarf_Die *vr_die, struct strbuf *buf);
 
 /* Get the name and type of given variable DIE, stored as "type\tname" */
-extern int die_get_varname(Dwarf_Die *vr_die, char *buf, int len);
+extern int die_get_varname(Dwarf_Die *vr_die, struct strbuf *buf);
+extern int die_get_var_range(Dwarf_Die *sp_die, Dwarf_Die *vr_die,
+			struct strbuf *buf);
 #endif
diff --git a/tools/perf/util/environment.c b/tools/perf/util/environment.c
index 275b0ee345f5..7405123692f1 100644
--- a/tools/perf/util/environment.c
+++ b/tools/perf/util/environment.c
@@ -5,5 +5,4 @@
  */
 #include "cache.h"
 
-const char *pager_program;
 int pager_use_color = 1;
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index ff866c4d2e2f..d7d986d8f23e 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -23,12 +23,18 @@ static const char *perf_event__names[] = {
 	[PERF_RECORD_FORK]			= "FORK",
 	[PERF_RECORD_READ]			= "READ",
 	[PERF_RECORD_SAMPLE]			= "SAMPLE",
+	[PERF_RECORD_AUX]			= "AUX",
+	[PERF_RECORD_ITRACE_START]		= "ITRACE_START",
+	[PERF_RECORD_LOST_SAMPLES]		= "LOST_SAMPLES",
 	[PERF_RECORD_HEADER_ATTR]		= "ATTR",
 	[PERF_RECORD_HEADER_EVENT_TYPE]		= "EVENT_TYPE",
 	[PERF_RECORD_HEADER_TRACING_DATA]	= "TRACING_DATA",
 	[PERF_RECORD_HEADER_BUILD_ID]		= "BUILD_ID",
 	[PERF_RECORD_FINISHED_ROUND]		= "FINISHED_ROUND",
 	[PERF_RECORD_ID_INDEX]			= "ID_INDEX",
+	[PERF_RECORD_AUXTRACE_INFO]		= "AUXTRACE_INFO",
+	[PERF_RECORD_AUXTRACE]			= "AUXTRACE",
+	[PERF_RECORD_AUXTRACE_ERROR]		= "AUXTRACE_ERROR",
 };
 
 const char *perf_event__name(unsigned int id)
@@ -212,10 +218,14 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 				       pid_t pid, pid_t tgid,
 				       perf_event__handler_t process,
 				       struct machine *machine,
-				       bool mmap_data)
+				       bool mmap_data,
+				       unsigned int proc_map_timeout)
 {
 	char filename[PATH_MAX];
 	FILE *fp;
+	unsigned long long t;
+	bool truncation = false;
+	unsigned long long timeout = proc_map_timeout * 1000000ULL;
 	int rc = 0;
 
 	if (machine__is_default_guest(machine))
@@ -234,6 +244,7 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 	}
 
 	event->header.type = PERF_RECORD_MMAP2;
+	t = rdclock();
 
 	while (1) {
 		char bf[BUFSIZ];
@@ -247,6 +258,15 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 		if (fgets(bf, sizeof(bf), fp) == NULL)
 			break;
 
+		if ((rdclock() - t) > timeout) {
+			pr_warning("Reading %s time out. "
+				   "You may want to increase "
+				   "the time limit by --proc-map-timeout\n",
+				   filename);
+			truncation = true;
+			goto out;
+		}
+
 		/* ensure null termination since stack will be reused. */
 		strcpy(execname, "");
 
@@ -295,6 +315,10 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 			event->header.misc |= PERF_RECORD_MISC_MMAP_DATA;
 		}
 
+out:
+		if (truncation)
+			event->header.misc |= PERF_RECORD_MISC_PROC_MAP_PARSE_TIMEOUT;
+
 		if (!strcmp(execname, ""))
 			strcpy(execname, anonstr);
 
@@ -313,6 +337,9 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 			rc = -1;
 			break;
 		}
+
+		if (truncation)
+			break;
 	}
 
 	fclose(fp);
@@ -324,8 +351,9 @@ int perf_event__synthesize_modules(struct perf_tool *tool,
 				   struct machine *machine)
 {
 	int rc = 0;
-	struct rb_node *nd;
+	struct map *pos;
 	struct map_groups *kmaps = &machine->kmaps;
+	struct maps *maps = &kmaps->maps[MAP__FUNCTION];
 	union perf_event *event = zalloc((sizeof(event->mmap) +
 					  machine->id_hdr_size));
 	if (event == NULL) {
@@ -345,10 +373,8 @@ int perf_event__synthesize_modules(struct perf_tool *tool,
 	else
 		event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
 
-	for (nd = rb_first(&kmaps->maps[MAP__FUNCTION]);
-	     nd; nd = rb_next(nd)) {
+	for (pos = maps__first(maps); pos; pos = map__next(pos)) {
 		size_t size;
-		struct map *pos = rb_entry(nd, struct map, rb_node);
 
 		if (pos->dso->kernel)
 			continue;
@@ -381,7 +407,9 @@ static int __event__synthesize_thread(union perf_event *comm_event,
 				      pid_t pid, int full,
 					  perf_event__handler_t process,
 				      struct perf_tool *tool,
-				      struct machine *machine, bool mmap_data)
+				      struct machine *machine,
+				      bool mmap_data,
+				      unsigned int proc_map_timeout)
 {
 	char filename[PATH_MAX];
 	DIR *tasks;
@@ -398,7 +426,8 @@ static int __event__synthesize_thread(union perf_event *comm_event,
 			return -1;
 
 		return perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid,
-							  process, machine, mmap_data);
+							  process, machine, mmap_data,
+							  proc_map_timeout);
 	}
 
 	if (machine__is_default_guest(machine))
@@ -439,7 +468,7 @@ static int __event__synthesize_thread(union perf_event *comm_event,
 		if (_pid == pid) {
 			/* process the parent's maps too */
 			rc = perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid,
-						process, machine, mmap_data);
+						process, machine, mmap_data, proc_map_timeout);
 			if (rc)
 				break;
 		}
@@ -453,7 +482,8 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool,
 				      struct thread_map *threads,
 				      perf_event__handler_t process,
 				      struct machine *machine,
-				      bool mmap_data)
+				      bool mmap_data,
+				      unsigned int proc_map_timeout)
 {
 	union perf_event *comm_event, *mmap_event, *fork_event;
 	int err = -1, thread, j;
@@ -476,7 +506,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool,
 					       fork_event,
 					       threads->map[thread], 0,
 					       process, tool, machine,
-					       mmap_data)) {
+					       mmap_data, proc_map_timeout)) {
 			err = -1;
 			break;
 		}
@@ -502,7 +532,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool,
 						       fork_event,
 						       comm_event->comm.pid, 0,
 						       process, tool, machine,
-						       mmap_data)) {
+						       mmap_data, proc_map_timeout)) {
 				err = -1;
 				break;
 			}
@@ -519,7 +549,9 @@ out:
 
 int perf_event__synthesize_threads(struct perf_tool *tool,
 				   perf_event__handler_t process,
-				   struct machine *machine, bool mmap_data)
+				   struct machine *machine,
+				   bool mmap_data,
+				   unsigned int proc_map_timeout)
 {
 	DIR *proc;
 	char proc_path[PATH_MAX];
@@ -559,7 +591,8 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
  		 * one thread couldn't be synthesized.
  		 */
 		__event__synthesize_thread(comm_event, mmap_event, fork_event, pid,
-					   1, process, tool, machine, mmap_data);
+					   1, process, tool, machine, mmap_data,
+					   proc_map_timeout);
 	}
 
 	err = 0;
@@ -692,6 +725,30 @@ int perf_event__process_lost(struct perf_tool *tool __maybe_unused,
 	return machine__process_lost_event(machine, event, sample);
 }
 
+int perf_event__process_aux(struct perf_tool *tool __maybe_unused,
+			    union perf_event *event,
+			    struct perf_sample *sample __maybe_unused,
+			    struct machine *machine)
+{
+	return machine__process_aux_event(machine, event);
+}
+
+int perf_event__process_itrace_start(struct perf_tool *tool __maybe_unused,
+				     union perf_event *event,
+				     struct perf_sample *sample __maybe_unused,
+				     struct machine *machine)
+{
+	return machine__process_itrace_start_event(machine, event);
+}
+
+int perf_event__process_lost_samples(struct perf_tool *tool __maybe_unused,
+				     union perf_event *event,
+				     struct perf_sample *sample,
+				     struct machine *machine)
+{
+	return machine__process_lost_samples_event(machine, event, sample);
+}
+
 size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp)
 {
 	return fprintf(fp, " %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64 "]: %c %s\n",
@@ -755,6 +812,21 @@ int perf_event__process_exit(struct perf_tool *tool __maybe_unused,
 	return machine__process_exit_event(machine, event, sample);
 }
 
+size_t perf_event__fprintf_aux(union perf_event *event, FILE *fp)
+{
+	return fprintf(fp, " offset: %#"PRIx64" size: %#"PRIx64" flags: %#"PRIx64" [%s%s]\n",
+		       event->aux.aux_offset, event->aux.aux_size,
+		       event->aux.flags,
+		       event->aux.flags & PERF_AUX_FLAG_TRUNCATED ? "T" : "",
+		       event->aux.flags & PERF_AUX_FLAG_OVERWRITE ? "O" : "");
+}
+
+size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp)
+{
+	return fprintf(fp, " pid: %u tid: %u\n",
+		       event->itrace_start.pid, event->itrace_start.tid);
+}
+
 size_t perf_event__fprintf(union perf_event *event, FILE *fp)
 {
 	size_t ret = fprintf(fp, "PERF_RECORD_%s",
@@ -774,6 +846,12 @@ size_t perf_event__fprintf(union perf_event *event, FILE *fp)
 	case PERF_RECORD_MMAP2:
 		ret += perf_event__fprintf_mmap2(event, fp);
 		break;
+	case PERF_RECORD_AUX:
+		ret += perf_event__fprintf_aux(event, fp);
+		break;
+	case PERF_RECORD_ITRACE_START:
+		ret += perf_event__fprintf_itrace_start(event, fp);
+		break;
 	default:
 		ret += fprintf(fp, "\n");
 	}
@@ -877,6 +955,10 @@ void thread__find_addr_location(struct thread *thread,
 		al->sym = NULL;
 }
 
+/*
+ * Callers need to drop the reference to al->thread, obtained in
+ * machine__findnew_thread()
+ */
 int perf_event__preprocess_sample(const union perf_event *event,
 				  struct machine *machine,
 				  struct addr_location *al,
@@ -937,6 +1019,17 @@ int perf_event__preprocess_sample(const union perf_event *event,
 	return 0;
 }
 
+/*
+ * The preprocess_sample method will return with reference counts for the
+ * in it, when done using (and perhaps getting ref counts if needing to
+ * keep a pointer to one of those entries) it must be paired with
+ * addr_location__put(), so that the refcounts can be decremented.
+ */
+void addr_location__put(struct addr_location *al)
+{
+	thread__zput(al->thread);
+}
+
 bool is_bts_event(struct perf_event_attr *attr)
 {
 	return attr->type == PERF_TYPE_HARDWARE &&
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 09b9e8d3fcf7..c53f36384b64 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -52,6 +52,11 @@ struct lost_event {
 	u64 lost;
 };
 
+struct lost_samples_event {
+	struct perf_event_header header;
+	u64 lost;
+};
+
 /*
  * PERF_FORMAT_ENABLED | PERF_FORMAT_RUNNING | PERF_FORMAT_ID
  */
@@ -157,6 +162,8 @@ enum {
 	PERF_IP_FLAG_IN_TX		= 1ULL << 10,
 };
 
+#define PERF_IP_FLAG_CHARS "bcrosyiABEx"
+
 #define PERF_BRANCH_MASK		(\
 	PERF_IP_FLAG_BRANCH		|\
 	PERF_IP_FLAG_CALL		|\
@@ -215,9 +222,17 @@ enum perf_user_event_type { /* above any possible kernel type */
 	PERF_RECORD_HEADER_BUILD_ID		= 67,
 	PERF_RECORD_FINISHED_ROUND		= 68,
 	PERF_RECORD_ID_INDEX			= 69,
+	PERF_RECORD_AUXTRACE_INFO		= 70,
+	PERF_RECORD_AUXTRACE			= 71,
+	PERF_RECORD_AUXTRACE_ERROR		= 72,
 	PERF_RECORD_HEADER_MAX
 };
 
+enum auxtrace_error_type {
+	PERF_AUXTRACE_ERROR_ITRACE  = 1,
+	PERF_AUXTRACE_ERROR_MAX
+};
+
 /*
  * The kernel collects the number of events it couldn't send in a stretch and
  * when possible sends this number in a PERF_RECORD_LOST event. The number of
@@ -225,6 +240,12 @@ enum perf_user_event_type { /* above any possible kernel type */
  * total_lost tells exactly how many events the kernel in fact lost, i.e. it is
  * the sum of all struct lost_event.lost fields reported.
  *
+ * The kernel discards mixed up samples and sends the number in a
+ * PERF_RECORD_LOST_SAMPLES event. The number of lost-samples events is stored
+ * in .nr_events[PERF_RECORD_LOST_SAMPLES] while total_lost_samples tells
+ * exactly how many samples the kernel in fact dropped, i.e. it is the sum of
+ * all struct lost_samples_event.lost fields reported.
+ *
  * The total_period is needed because by default auto-freq is used, so
  * multipling nr_events[PERF_EVENT_SAMPLE] by a frequency isn't possible to get
  * the total number of low level events, it is necessary to to sum all struct
@@ -234,6 +255,7 @@ struct events_stats {
 	u64 total_period;
 	u64 total_non_filtered_period;
 	u64 total_lost;
+	u64 total_lost_samples;
 	u64 total_invalid_chains;
 	u32 nr_events[PERF_RECORD_HEADER_MAX];
 	u32 nr_non_filtered_samples;
@@ -242,6 +264,8 @@ struct events_stats {
 	u32 nr_invalid_chains;
 	u32 nr_unknown_id;
 	u32 nr_unprocessable_samples;
+	u32 nr_auxtrace_errors[PERF_AUXTRACE_ERROR_MAX];
+	u32 nr_proc_map_timeout;
 };
 
 struct attr_event {
@@ -280,6 +304,50 @@ struct id_index_event {
 	struct id_index_entry entries[0];
 };
 
+struct auxtrace_info_event {
+	struct perf_event_header header;
+	u32 type;
+	u32 reserved__; /* For alignment */
+	u64 priv[];
+};
+
+struct auxtrace_event {
+	struct perf_event_header header;
+	u64 size;
+	u64 offset;
+	u64 reference;
+	u32 idx;
+	u32 tid;
+	u32 cpu;
+	u32 reserved__; /* For alignment */
+};
+
+#define MAX_AUXTRACE_ERROR_MSG 64
+
+struct auxtrace_error_event {
+	struct perf_event_header header;
+	u32 type;
+	u32 code;
+	u32 cpu;
+	u32 pid;
+	u32 tid;
+	u32 reserved__; /* For alignment */
+	u64 ip;
+	char msg[MAX_AUXTRACE_ERROR_MSG];
+};
+
+struct aux_event {
+	struct perf_event_header header;
+	u64	aux_offset;
+	u64	aux_size;
+	u64	flags;
+};
+
+struct itrace_start_event {
+	struct perf_event_header header;
+	u32 pid, tid;
+};
+
 union perf_event {
 	struct perf_event_header	header;
 	struct mmap_event		mmap;
@@ -287,6 +355,7 @@ union perf_event {
 	struct comm_event		comm;
 	struct fork_event		fork;
 	struct lost_event		lost;
+	struct lost_samples_event	lost_samples;
 	struct read_event		read;
 	struct throttle_event		throttle;
 	struct sample_event		sample;
@@ -295,6 +364,11 @@ union perf_event {
 	struct tracing_data_event	tracing_data;
 	struct build_id_event		build_id;
 	struct id_index_event		id_index;
+	struct auxtrace_info_event	auxtrace_info;
+	struct auxtrace_event		auxtrace;
+	struct auxtrace_error_event	auxtrace_error;
+	struct aux_event		aux;
+	struct itrace_start_event	itrace_start;
 };
 
 void perf_event__print_totals(void);
@@ -310,10 +384,12 @@ typedef int (*perf_event__handler_t)(struct perf_tool *tool,
 int perf_event__synthesize_thread_map(struct perf_tool *tool,
 				      struct thread_map *threads,
 				      perf_event__handler_t process,
-				      struct machine *machine, bool mmap_data);
+				      struct machine *machine, bool mmap_data,
+				      unsigned int proc_map_timeout);
 int perf_event__synthesize_threads(struct perf_tool *tool,
 				   perf_event__handler_t process,
-				   struct machine *machine, bool mmap_data);
+				   struct machine *machine, bool mmap_data,
+				   unsigned int proc_map_timeout);
 int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
 				       perf_event__handler_t process,
 				       struct machine *machine);
@@ -330,6 +406,18 @@ int perf_event__process_lost(struct perf_tool *tool,
 			     union perf_event *event,
 			     struct perf_sample *sample,
 			     struct machine *machine);
+int perf_event__process_lost_samples(struct perf_tool *tool,
+				     union perf_event *event,
+				     struct perf_sample *sample,
+				     struct machine *machine);
+int perf_event__process_aux(struct perf_tool *tool,
+			    union perf_event *event,
+			    struct perf_sample *sample,
+			    struct machine *machine);
+int perf_event__process_itrace_start(struct perf_tool *tool,
+				     union perf_event *event,
+				     struct perf_sample *sample,
+				     struct machine *machine);
 int perf_event__process_mmap(struct perf_tool *tool,
 			     union perf_event *event,
 			     struct perf_sample *sample,
@@ -358,6 +446,8 @@ int perf_event__preprocess_sample(const union perf_event *event,
 				  struct addr_location *al,
 				  struct perf_sample *sample);
 
+void addr_location__put(struct addr_location *al);
+
 struct thread;
 
 bool is_bts_event(struct perf_event_attr *attr);
@@ -381,12 +471,15 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 				       pid_t pid, pid_t tgid,
 				       perf_event__handler_t process,
 				       struct machine *machine,
-				       bool mmap_data);
+				       bool mmap_data,
+				       unsigned int proc_map_timeout);
 
 size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_task(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_aux(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf(union perf_event *event, FILE *fp);
 
 u64 kallsyms__get_function_start(const char *kallsyms_filename,
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 080be93eea96..8366511b45f8 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -297,6 +297,8 @@ void perf_evlist__disable(struct perf_evlist *evlist)
 				      PERF_EVENT_IOC_DISABLE, 0);
 		}
 	}
+
+	evlist->enabled = false;
 }
 
 void perf_evlist__enable(struct perf_evlist *evlist)
@@ -316,6 +318,13 @@ void perf_evlist__enable(struct perf_evlist *evlist)
 				      PERF_EVENT_IOC_ENABLE, 0);
 		}
 	}
+
+	evlist->enabled = true;
+}
+
+void perf_evlist__toggle_enable(struct perf_evlist *evlist)
+{
+	(evlist->enabled ? perf_evlist__disable : perf_evlist__enable)(evlist);
 }
 
 int perf_evlist__disable_event(struct perf_evlist *evlist,
@@ -634,11 +643,18 @@ static struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist,
 union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
 {
 	struct perf_mmap *md = &evlist->mmap[idx];
-	u64 head = perf_mmap__read_head(md);
+	u64 head;
 	u64 old = md->prev;
 	unsigned char *data = md->base + page_size;
 	union perf_event *event = NULL;
 
+	/*
+	 * Check if event was unmapped due to a POLLHUP/POLLERR.
+	 */
+	if (!atomic_read(&md->refcnt))
+		return NULL;
+
+	head = perf_mmap__read_head(md);
 	if (evlist->overwrite) {
 		/*
 		 * If we're further behind than half the buffer, there's a chance
@@ -695,19 +711,19 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
 
 static bool perf_mmap__empty(struct perf_mmap *md)
 {
-	return perf_mmap__read_head(md) == md->prev;
+	return perf_mmap__read_head(md) == md->prev && !md->auxtrace_mmap.base;
 }
 
 static void perf_evlist__mmap_get(struct perf_evlist *evlist, int idx)
 {
-	++evlist->mmap[idx].refcnt;
+	atomic_inc(&evlist->mmap[idx].refcnt);
 }
 
 static void perf_evlist__mmap_put(struct perf_evlist *evlist, int idx)
 {
-	BUG_ON(evlist->mmap[idx].refcnt == 0);
+	BUG_ON(atomic_read(&evlist->mmap[idx].refcnt) == 0);
 
-	if (--evlist->mmap[idx].refcnt == 0)
+	if (atomic_dec_and_test(&evlist->mmap[idx].refcnt))
 		__perf_evlist__munmap(evlist, idx);
 }
 
@@ -721,17 +737,46 @@ void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx)
 		perf_mmap__write_tail(md, old);
 	}
 
-	if (md->refcnt == 1 && perf_mmap__empty(md))
+	if (atomic_read(&md->refcnt) == 1 && perf_mmap__empty(md))
 		perf_evlist__mmap_put(evlist, idx);
 }
 
+int __weak auxtrace_mmap__mmap(struct auxtrace_mmap *mm __maybe_unused,
+			       struct auxtrace_mmap_params *mp __maybe_unused,
+			       void *userpg __maybe_unused,
+			       int fd __maybe_unused)
+{
+	return 0;
+}
+
+void __weak auxtrace_mmap__munmap(struct auxtrace_mmap *mm __maybe_unused)
+{
+}
+
+void __weak auxtrace_mmap_params__init(
+			struct auxtrace_mmap_params *mp __maybe_unused,
+			off_t auxtrace_offset __maybe_unused,
+			unsigned int auxtrace_pages __maybe_unused,
+			bool auxtrace_overwrite __maybe_unused)
+{
+}
+
+void __weak auxtrace_mmap_params__set_idx(
+			struct auxtrace_mmap_params *mp __maybe_unused,
+			struct perf_evlist *evlist __maybe_unused,
+			int idx __maybe_unused,
+			bool per_cpu __maybe_unused)
+{
+}
+
 static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx)
 {
 	if (evlist->mmap[idx].base != NULL) {
 		munmap(evlist->mmap[idx].base, evlist->mmap_len);
 		evlist->mmap[idx].base = NULL;
-		evlist->mmap[idx].refcnt = 0;
+		atomic_set(&evlist->mmap[idx].refcnt, 0);
 	}
+	auxtrace_mmap__munmap(&evlist->mmap[idx].auxtrace_mmap);
 }
 
 void perf_evlist__munmap(struct perf_evlist *evlist)
@@ -759,6 +804,7 @@ static int perf_evlist__alloc_mmap(struct perf_evlist *evlist)
 struct mmap_params {
 	int prot;
 	int mask;
+	struct auxtrace_mmap_params auxtrace_mp;
 };
 
 static int __perf_evlist__mmap(struct perf_evlist *evlist, int idx,
@@ -777,7 +823,7 @@ static int __perf_evlist__mmap(struct perf_evlist *evlist, int idx,
 	 * evlist layer can't just drop it when filtering events in
 	 * perf_evlist__filter_pollfd().
 	 */
-	evlist->mmap[idx].refcnt = 2;
+	atomic_set(&evlist->mmap[idx].refcnt, 2);
 	evlist->mmap[idx].prev = 0;
 	evlist->mmap[idx].mask = mp->mask;
 	evlist->mmap[idx].base = mmap(NULL, evlist->mmap_len, mp->prot,
@@ -789,6 +835,10 @@ static int __perf_evlist__mmap(struct perf_evlist *evlist, int idx,
 		return -1;
 	}
 
+	if (auxtrace_mmap__mmap(&evlist->mmap[idx].auxtrace_mmap,
+				&mp->auxtrace_mp, evlist->mmap[idx].base, fd))
+		return -1;
+
 	return 0;
 }
 
@@ -853,6 +903,9 @@ static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist,
 	for (cpu = 0; cpu < nr_cpus; cpu++) {
 		int output = -1;
 
+		auxtrace_mmap_params__set_idx(&mp->auxtrace_mp, evlist, cpu,
+					      true);
+
 		for (thread = 0; thread < nr_threads; thread++) {
 			if (perf_evlist__mmap_per_evsel(evlist, cpu, mp, cpu,
 							thread, &output))
@@ -878,6 +931,9 @@ static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist,
 	for (thread = 0; thread < nr_threads; thread++) {
 		int output = -1;
 
+		auxtrace_mmap_params__set_idx(&mp->auxtrace_mp, evlist, thread,
+					      false);
+
 		if (perf_evlist__mmap_per_evsel(evlist, thread, mp, 0, thread,
 						&output))
 			goto out_unmap;
@@ -960,10 +1016,8 @@ static long parse_pages_arg(const char *str, unsigned long min,
 	return pages;
 }
 
-int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str,
-				  int unset __maybe_unused)
+int __perf_evlist__parse_mmap_pages(unsigned int *mmap_pages, const char *str)
 {
-	unsigned int *mmap_pages = opt->value;
 	unsigned long max = UINT_MAX;
 	long pages;
 
@@ -980,20 +1034,32 @@ int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str,
 	return 0;
 }
 
+int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str,
+				  int unset __maybe_unused)
+{
+	return __perf_evlist__parse_mmap_pages(opt->value, str);
+}
+
 /**
- * perf_evlist__mmap - Create mmaps to receive events.
+ * perf_evlist__mmap_ex - Create mmaps to receive events.
  * @evlist: list of events
  * @pages: map length in pages
  * @overwrite: overwrite older events?
+ * @auxtrace_pages - auxtrace map length in pages
+ * @auxtrace_overwrite - overwrite older auxtrace data?
  *
  * If @overwrite is %false the user needs to signal event consumption using
  * perf_mmap__write_tail().  Using perf_evlist__mmap_read() does this
  * automatically.
  *
+ * Similarly, if @auxtrace_overwrite is %false the user needs to signal data
+ * consumption using auxtrace_mmap__write_tail().
+ *
  * Return: %0 on success, negative error code otherwise.
  */
-int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
-		      bool overwrite)
+int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
+			 bool overwrite, unsigned int auxtrace_pages,
+			 bool auxtrace_overwrite)
 {
 	struct perf_evsel *evsel;
 	const struct cpu_map *cpus = evlist->cpus;
@@ -1013,6 +1079,9 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
 	pr_debug("mmap size %zuB\n", evlist->mmap_len);
 	mp.mask = evlist->mmap_len - page_size - 1;
 
+	auxtrace_mmap_params__init(&mp.auxtrace_mp, evlist->mmap_len,
+				   auxtrace_pages, auxtrace_overwrite);
+
 	evlist__for_each(evlist, evsel) {
 		if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
 		    evsel->sample_id == NULL &&
@@ -1026,6 +1095,12 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
 	return perf_evlist__mmap_per_cpu(evlist, &mp);
 }
 
+int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
+		      bool overwrite)
+{
+	return perf_evlist__mmap_ex(evlist, pages, overwrite, 0, false);
+}
+
 int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
 {
 	evlist->threads = thread_map__new_str(target->pid, target->tid,
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index b5cce95d644e..a8489b9d2812 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -1,6 +1,7 @@
 #ifndef __PERF_EVLIST_H
 #define __PERF_EVLIST_H 1
 
+#include <linux/atomic.h>
 #include <linux/list.h>
 #include <api/fd/array.h>
 #include <stdio.h>
@@ -8,6 +9,7 @@
 #include "event.h"
 #include "evsel.h"
 #include "util.h"
+#include "auxtrace.h"
 #include <unistd.h>
 
 struct pollfd;
@@ -26,8 +28,9 @@ struct record_opts;
 struct perf_mmap {
 	void		 *base;
 	int		 mask;
-	int		 refcnt;
+	atomic_t	 refcnt;
 	u64		 prev;
+	struct auxtrace_mmap auxtrace_mmap;
 	char		 event_copy[PERF_SAMPLE_MAX_SIZE] __attribute__((aligned(8)));
 };
 
@@ -37,6 +40,8 @@ struct perf_evlist {
 	int		 nr_entries;
 	int		 nr_groups;
 	int		 nr_mmaps;
+	bool		 overwrite;
+	bool		 enabled;
 	size_t		 mmap_len;
 	int		 id_pos;
 	int		 is_pos;
@@ -45,7 +50,6 @@ struct perf_evlist {
 		int	cork_fd;
 		pid_t	pid;
 	} workload;
-	bool		 overwrite;
 	struct fdarray	 pollfd;
 	struct perf_mmap *mmap;
 	struct thread_map *threads;
@@ -122,16 +126,21 @@ int perf_evlist__start_workload(struct perf_evlist *evlist);
 
 struct option;
 
+int __perf_evlist__parse_mmap_pages(unsigned int *mmap_pages, const char *str);
 int perf_evlist__parse_mmap_pages(const struct option *opt,
 				  const char *str,
 				  int unset);
 
+int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
+			 bool overwrite, unsigned int auxtrace_pages,
+			 bool auxtrace_overwrite);
 int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
 		      bool overwrite);
 void perf_evlist__munmap(struct perf_evlist *evlist);
 
 void perf_evlist__disable(struct perf_evlist *evlist);
 void perf_evlist__enable(struct perf_evlist *evlist);
+void perf_evlist__toggle_enable(struct perf_evlist *evlist);
 
 int perf_evlist__disable_event(struct perf_evlist *evlist,
 			       struct perf_evsel *evsel);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 33e3fd8c2e68..33449decf7bd 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -26,6 +26,7 @@
 #include "perf_regs.h"
 #include "debug.h"
 #include "trace-event.h"
+#include "stat.h"
 
 static struct {
 	bool sample_id_all;
@@ -851,19 +852,6 @@ int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads)
 	return 0;
 }
 
-void perf_evsel__reset_counts(struct perf_evsel *evsel, int ncpus)
-{
-	memset(evsel->counts, 0, (sizeof(*evsel->counts) +
-				 (ncpus * sizeof(struct perf_counts_values))));
-}
-
-int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus)
-{
-	evsel->counts = zalloc((sizeof(*evsel->counts) +
-				(ncpus * sizeof(struct perf_counts_values))));
-	return evsel->counts != NULL ? 0 : -ENOMEM;
-}
-
 static void perf_evsel__free_fd(struct perf_evsel *evsel)
 {
 	xyarray__delete(evsel->fd);
@@ -891,11 +879,6 @@ void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
 		}
 }
 
-void perf_evsel__free_counts(struct perf_evsel *evsel)
-{
-	zfree(&evsel->counts);
-}
-
 void perf_evsel__exit(struct perf_evsel *evsel)
 {
 	assert(list_empty(&evsel->node));
@@ -1058,7 +1041,7 @@ static void __p_read_format(char *buf, size_t size, u64 value)
 
 #define BUF_SIZE		1024
 
-#define p_hex(val)		snprintf(buf, BUF_SIZE, "%"PRIx64, (uint64_t)(val))
+#define p_hex(val)		snprintf(buf, BUF_SIZE, "%#"PRIx64, (uint64_t)(val))
 #define p_unsigned(val)		snprintf(buf, BUF_SIZE, "%"PRIu64, (uint64_t)(val))
 #define p_signed(val)		snprintf(buf, BUF_SIZE, "%"PRId64, (int64_t)(val))
 #define p_sample_type(val)	__p_sample_type(buf, BUF_SIZE, val)
@@ -1121,6 +1104,7 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
 	PRINT_ATTRf(sample_stack_user, p_unsigned);
 	PRINT_ATTRf(clockid, p_signed);
 	PRINT_ATTRf(sample_regs_intr, p_hex);
+	PRINT_ATTRf(aux_watermark, p_unsigned);
 
 	return ret;
 }
@@ -2148,7 +2132,9 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
 	case EMFILE:
 		return scnprintf(msg, size, "%s",
 			 "Too many events are opened.\n"
-			 "Try again after reducing the number of events.");
+			 "Probably the maximum number of open file descriptors has been reached.\n"
+			 "Hint: Try again after reducing the number of events.\n"
+			 "Hint: Try increasing the limit with 'ulimit -n <limit>'");
 	case ENODEV:
 		if (target->cpu_list)
 			return scnprintf(msg, size, "%s",
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index e486151b0308..bb0579e8a10a 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -73,7 +73,6 @@ struct perf_evsel {
 	char			*name;
 	double			scale;
 	const char		*unit;
-	bool			snapshot;
 	struct event_format	*tp_format;
 	union {
 		void		*priv;
@@ -86,6 +85,7 @@ struct perf_evsel {
 	unsigned int		sample_size;
 	int			id_pos;
 	int			is_pos;
+	bool			snapshot;
 	bool 			supported;
 	bool 			needs_swap;
 	bool			no_aux_samples;
@@ -93,11 +93,11 @@ struct perf_evsel {
 	bool			system_wide;
 	bool			tracking;
 	bool			per_pkg;
-	unsigned long		*per_pkg_mask;
 	/* parse modifier helper */
 	int			exclude_GH;
 	int			nr_members;
 	int			sample_read;
+	unsigned long		*per_pkg_mask;
 	struct perf_evsel	*leader;
 	char			*group_name;
 };
@@ -170,9 +170,6 @@ const char *perf_evsel__group_name(struct perf_evsel *evsel);
 int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size);
 
 int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads);
-int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus);
-void perf_evsel__reset_counts(struct perf_evsel *evsel, int ncpus);
-void perf_evsel__free_counts(struct perf_evsel *evsel);
 void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
 
 void __perf_evsel__set_sample_bit(struct perf_evsel *evsel,
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 918fd8ae2d80..21a77e7a171e 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -869,6 +869,20 @@ static int write_branch_stack(int fd __maybe_unused,
 	return 0;
 }
 
+static int write_auxtrace(int fd, struct perf_header *h,
+			  struct perf_evlist *evlist __maybe_unused)
+{
+	struct perf_session *session;
+	int err;
+
+	session = container_of(h, struct perf_session, header);
+
+	err = auxtrace_index__write(fd, &session->auxtrace_index);
+	if (err < 0)
+		pr_err("Failed to write auxtrace index\n");
+	return err;
+}
+
 static void print_hostname(struct perf_header *ph, int fd __maybe_unused,
 			   FILE *fp)
 {
@@ -1151,6 +1165,12 @@ static void print_branch_stack(struct perf_header *ph __maybe_unused,
 	fprintf(fp, "# contains samples with branch stack\n");
 }
 
+static void print_auxtrace(struct perf_header *ph __maybe_unused,
+			   int fd __maybe_unused, FILE *fp)
+{
+	fprintf(fp, "# contains AUX area data (e.g. instruction trace)\n");
+}
+
 static void print_pmu_mappings(struct perf_header *ph, int fd __maybe_unused,
 			       FILE *fp)
 {
@@ -1218,9 +1238,8 @@ static int __event_process_build_id(struct build_id_event *bev,
 				    struct perf_session *session)
 {
 	int err = -1;
-	struct dsos *dsos;
 	struct machine *machine;
-	u16 misc;
+	u16 cpumode;
 	struct dso *dso;
 	enum dso_kernel_type dso_type;
 
@@ -1228,39 +1247,37 @@ static int __event_process_build_id(struct build_id_event *bev,
 	if (!machine)
 		goto out;
 
-	misc = bev->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+	cpumode = bev->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 
-	switch (misc) {
+	switch (cpumode) {
 	case PERF_RECORD_MISC_KERNEL:
 		dso_type = DSO_TYPE_KERNEL;
-		dsos = &machine->kernel_dsos;
 		break;
 	case PERF_RECORD_MISC_GUEST_KERNEL:
 		dso_type = DSO_TYPE_GUEST_KERNEL;
-		dsos = &machine->kernel_dsos;
 		break;
 	case PERF_RECORD_MISC_USER:
 	case PERF_RECORD_MISC_GUEST_USER:
 		dso_type = DSO_TYPE_USER;
-		dsos = &machine->user_dsos;
 		break;
 	default:
 		goto out;
 	}
 
-	dso = __dsos__findnew(dsos, filename);
+	dso = machine__findnew_dso(machine, filename);
 	if (dso != NULL) {
 		char sbuild_id[BUILD_ID_SIZE * 2 + 1];
 
 		dso__set_build_id(dso, &bev->build_id);
 
-		if (!is_kernel_module(filename))
+		if (!is_kernel_module(filename, cpumode))
 			dso->kernel = dso_type;
 
 		build_id__sprintf(dso->build_id, sizeof(dso->build_id),
 				  sbuild_id);
 		pr_debug("build id event received for %s: %s\n",
 			 dso->long_name, sbuild_id);
+		dso__put(dso);
 	}
 
 	err = 0;
@@ -1821,6 +1838,22 @@ out_free:
 	return ret;
 }
 
+static int process_auxtrace(struct perf_file_section *section,
+			    struct perf_header *ph, int fd,
+			    void *data __maybe_unused)
+{
+	struct perf_session *session;
+	int err;
+
+	session = container_of(ph, struct perf_session, header);
+
+	err = auxtrace_index__process(fd, section->size, session,
+				      ph->needs_swap);
+	if (err < 0)
+		pr_err("Failed to process auxtrace index\n");
+	return err;
+}
+
 struct feature_ops {
 	int (*write)(int fd, struct perf_header *h, struct perf_evlist *evlist);
 	void (*print)(struct perf_header *h, int fd, FILE *fp);
@@ -1861,6 +1894,7 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
 	FEAT_OPA(HEADER_BRANCH_STACK,	branch_stack),
 	FEAT_OPP(HEADER_PMU_MAPPINGS,	pmu_mappings),
 	FEAT_OPP(HEADER_GROUP_DESC,	group_desc),
+	FEAT_OPP(HEADER_AUXTRACE,	auxtrace),
 };
 
 struct header_print_data {
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 3bb90ac172a1..d4d57962c591 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -30,6 +30,7 @@ enum {
 	HEADER_BRANCH_STACK,
 	HEADER_PMU_MAPPINGS,
 	HEADER_GROUP_DESC,
+	HEADER_AUXTRACE,
 	HEADER_LAST_FEATURE,
 	HEADER_FEAT_BITS	= 256,
 };
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index cc22b9158b93..6f28d53d4e46 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -313,8 +313,7 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template,
 				memset(&he->stat, 0, sizeof(he->stat));
 		}
 
-		if (he->ms.map)
-			he->ms.map->referenced = true;
+		map__get(he->ms.map);
 
 		if (he->branch_info) {
 			/*
@@ -324,6 +323,7 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template,
 			 */
 			he->branch_info = malloc(sizeof(*he->branch_info));
 			if (he->branch_info == NULL) {
+				map__zput(he->ms.map);
 				free(he->stat_acc);
 				free(he);
 				return NULL;
@@ -332,17 +332,13 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template,
 			memcpy(he->branch_info, template->branch_info,
 			       sizeof(*he->branch_info));
 
-			if (he->branch_info->from.map)
-				he->branch_info->from.map->referenced = true;
-			if (he->branch_info->to.map)
-				he->branch_info->to.map->referenced = true;
+			map__get(he->branch_info->from.map);
+			map__get(he->branch_info->to.map);
 		}
 
 		if (he->mem_info) {
-			if (he->mem_info->iaddr.map)
-				he->mem_info->iaddr.map->referenced = true;
-			if (he->mem_info->daddr.map)
-				he->mem_info->daddr.map->referenced = true;
+			map__get(he->mem_info->iaddr.map);
+			map__get(he->mem_info->daddr.map);
 		}
 
 		if (symbol_conf.use_callchain)
@@ -362,10 +358,10 @@ static u8 symbol__parent_filter(const struct symbol *parent)
 	return 0;
 }
 
-static struct hist_entry *add_hist_entry(struct hists *hists,
-					 struct hist_entry *entry,
-					 struct addr_location *al,
-					 bool sample_self)
+static struct hist_entry *hists__findnew_entry(struct hists *hists,
+					       struct hist_entry *entry,
+					       struct addr_location *al,
+					       bool sample_self)
 {
 	struct rb_node **p;
 	struct rb_node *parent = NULL;
@@ -407,9 +403,8 @@ static struct hist_entry *add_hist_entry(struct hists *hists,
 			 * the history counter to increment.
 			 */
 			if (he->ms.map != entry->ms.map) {
-				he->ms.map = entry->ms.map;
-				if (he->ms.map)
-					he->ms.map->referenced = true;
+				map__put(he->ms.map);
+				he->ms.map = map__get(entry->ms.map);
 			}
 			goto out;
 		}
@@ -468,7 +463,7 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
 		.transaction = transaction,
 	};
 
-	return add_hist_entry(hists, &entry, al, sample_self);
+	return hists__findnew_entry(hists, &entry, al, sample_self);
 }
 
 static int
@@ -548,9 +543,9 @@ iter_finish_mem_entry(struct hist_entry_iter *iter,
 
 out:
 	/*
-	 * We don't need to free iter->priv (mem_info) here since
-	 * the mem info was either already freed in add_hist_entry() or
-	 * passed to a new hist entry by hist_entry__new().
+	 * We don't need to free iter->priv (mem_info) here since the mem info
+	 * was either already freed in hists__findnew_entry() or passed to a
+	 * new hist entry by hist_entry__new().
 	 */
 	iter->priv = NULL;
 
@@ -851,19 +846,15 @@ const struct hist_iter_ops hist_iter_cumulative = {
 };
 
 int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
-			 struct perf_evsel *evsel, struct perf_sample *sample,
 			 int max_stack_depth, void *arg)
 {
 	int err, err2;
 
-	err = sample__resolve_callchain(sample, &iter->parent, evsel, al,
-					max_stack_depth);
+	err = sample__resolve_callchain(iter->sample, &iter->parent,
+					iter->evsel, al, max_stack_depth);
 	if (err)
 		return err;
 
-	iter->evsel = evsel;
-	iter->sample = sample;
-
 	err = iter->ops->prepare_entry(iter, al);
 	if (err)
 		goto out;
@@ -937,8 +928,20 @@ hist_entry__collapse(struct hist_entry *left, struct hist_entry *right)
 void hist_entry__delete(struct hist_entry *he)
 {
 	thread__zput(he->thread);
-	zfree(&he->branch_info);
-	zfree(&he->mem_info);
+	map__zput(he->ms.map);
+
+	if (he->branch_info) {
+		map__zput(he->branch_info->from.map);
+		map__zput(he->branch_info->to.map);
+		zfree(&he->branch_info);
+	}
+
+	if (he->mem_info) {
+		map__zput(he->mem_info->iaddr.map);
+		map__zput(he->mem_info->daddr.map);
+		zfree(&he->mem_info);
+	}
+
 	zfree(&he->stat_acc);
 	free_srcline(he->srcline);
 	free_callchain(he->callchain);
@@ -1163,7 +1166,7 @@ static void hists__remove_entry_filter(struct hists *hists, struct hist_entry *h
 		return;
 
 	/* force fold unfiltered entry for simplicity */
-	h->ms.unfolded = false;
+	h->unfolded = false;
 	h->row_offset = 0;
 	h->nr_rows = 0;
 
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 9f31b89a527a..5ed8d9c22981 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -111,7 +111,6 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
 				      u64 weight, u64 transaction,
 				      bool sample_self);
 int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
-			 struct perf_evsel *evsel, struct perf_sample *sample,
 			 int max_stack_depth, void *arg);
 
 int64_t hist_entry__cmp(struct hist_entry *left, struct hist_entry *right);
diff --git a/tools/perf/util/include/linux/poison.h b/tools/perf/util/include/linux/poison.h
deleted file mode 100644
index fef6dbc9ce13..000000000000
--- a/tools/perf/util/include/linux/poison.h
+++ /dev/null
@@ -1 +0,0 @@
-#include "../../../../include/linux/poison.h"
diff --git a/tools/perf/util/include/linux/rbtree.h b/tools/perf/util/include/linux/rbtree.h
index 2a030c5af3aa..f06d89f0b867 100644
--- a/tools/perf/util/include/linux/rbtree.h
+++ b/tools/perf/util/include/linux/rbtree.h
@@ -1,2 +1,16 @@
+#ifndef __TOOLS_LINUX_PERF_RBTREE_H
+#define __TOOLS_LINUX_PERF_RBTREE_H
 #include <stdbool.h>
 #include "../../../../include/linux/rbtree.h"
+
+/*
+ * Handy for checking that we are not deleting an entry that is
+ * already in a list, found in block/{blk-throttle,cfq-iosched}.c,
+ * probably should be moved to lib/rbtree.c...
+ */
+static inline void rb_erase_init(struct rb_node *n, struct rb_root *root)
+{
+	rb_erase(n, root);
+	RB_CLEAR_NODE(n);
+}
+#endif /* __TOOLS_LINUX_PERF_RBTREE_H */
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 527e032e24f6..4744673aff1b 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -14,20 +14,23 @@
 #include "unwind.h"
 #include "linux/hash.h"
 
+static void __machine__remove_thread(struct machine *machine, struct thread *th, bool lock);
+
 static void dsos__init(struct dsos *dsos)
 {
 	INIT_LIST_HEAD(&dsos->head);
 	dsos->root = RB_ROOT;
+	pthread_rwlock_init(&dsos->lock, NULL);
 }
 
 int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 {
 	map_groups__init(&machine->kmaps, machine);
 	RB_CLEAR_NODE(&machine->rb_node);
-	dsos__init(&machine->user_dsos);
-	dsos__init(&machine->kernel_dsos);
+	dsos__init(&machine->dsos);
 
 	machine->threads = RB_ROOT;
+	pthread_rwlock_init(&machine->threads_lock, NULL);
 	INIT_LIST_HEAD(&machine->dead_threads);
 	machine->last_match = NULL;
 
@@ -54,6 +57,7 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 
 		snprintf(comm, sizeof(comm), "[guest/%d]", pid);
 		thread__set_comm(thread, comm, 0);
+		thread__put(thread);
 	}
 
 	machine->current_tid = NULL;
@@ -78,37 +82,50 @@ out_delete:
 	return NULL;
 }
 
-static void dsos__delete(struct dsos *dsos)
+static void dsos__purge(struct dsos *dsos)
 {
 	struct dso *pos, *n;
 
+	pthread_rwlock_wrlock(&dsos->lock);
+
 	list_for_each_entry_safe(pos, n, &dsos->head, node) {
 		RB_CLEAR_NODE(&pos->rb_node);
-		list_del(&pos->node);
-		dso__delete(pos);
+		list_del_init(&pos->node);
+		dso__put(pos);
 	}
+
+	pthread_rwlock_unlock(&dsos->lock);
+}
+
+static void dsos__exit(struct dsos *dsos)
+{
+	dsos__purge(dsos);
+	pthread_rwlock_destroy(&dsos->lock);
 }
 
 void machine__delete_threads(struct machine *machine)
 {
-	struct rb_node *nd = rb_first(&machine->threads);
+	struct rb_node *nd;
 
+	pthread_rwlock_wrlock(&machine->threads_lock);
+	nd = rb_first(&machine->threads);
 	while (nd) {
 		struct thread *t = rb_entry(nd, struct thread, rb_node);
 
 		nd = rb_next(nd);
-		machine__remove_thread(machine, t);
+		__machine__remove_thread(machine, t, false);
 	}
+	pthread_rwlock_unlock(&machine->threads_lock);
 }
 
 void machine__exit(struct machine *machine)
 {
 	map_groups__exit(&machine->kmaps);
-	dsos__delete(&machine->user_dsos);
-	dsos__delete(&machine->kernel_dsos);
-	vdso__exit(machine);
+	dsos__exit(&machine->dsos);
+	machine__exit_vdso(machine);
 	zfree(&machine->root_dir);
 	zfree(&machine->current_tid);
+	pthread_rwlock_destroy(&machine->threads_lock);
 }
 
 void machine__delete(struct machine *machine)
@@ -303,7 +320,7 @@ static void machine__update_thread_pid(struct machine *machine,
 	if (th->pid_ == th->tid)
 		return;
 
-	leader = machine__findnew_thread(machine, th->pid_, th->pid_);
+	leader = __machine__findnew_thread(machine, th->pid_, th->pid_);
 	if (!leader)
 		goto out_err;
 
@@ -325,7 +342,7 @@ static void machine__update_thread_pid(struct machine *machine,
 		if (!map_groups__empty(th->mg))
 			pr_err("Discarding thread maps for %d:%d\n",
 			       th->pid_, th->tid);
-		map_groups__delete(th->mg);
+		map_groups__put(th->mg);
 	}
 
 	th->mg = map_groups__get(leader->mg);
@@ -336,9 +353,9 @@ out_err:
 	pr_err("Failed to join map groups for %d:%d\n", th->pid_, th->tid);
 }
 
-static struct thread *__machine__findnew_thread(struct machine *machine,
-						pid_t pid, pid_t tid,
-						bool create)
+static struct thread *____machine__findnew_thread(struct machine *machine,
+						  pid_t pid, pid_t tid,
+						  bool create)
 {
 	struct rb_node **p = &machine->threads.rb_node;
 	struct rb_node *parent = NULL;
@@ -356,7 +373,7 @@ static struct thread *__machine__findnew_thread(struct machine *machine,
 			return th;
 		}
 
-		thread__zput(machine->last_match);
+		machine->last_match = NULL;
 	}
 
 	while (*p != NULL) {
@@ -364,7 +381,7 @@ static struct thread *__machine__findnew_thread(struct machine *machine,
 		th = rb_entry(parent, struct thread, rb_node);
 
 		if (th->tid == tid) {
-			machine->last_match = thread__get(th);
+			machine->last_match = th;
 			machine__update_thread_pid(machine, th, pid);
 			return th;
 		}
@@ -392,7 +409,8 @@ static struct thread *__machine__findnew_thread(struct machine *machine,
 		 * leader and that would screwed the rb tree.
 		 */
 		if (thread__init_map_groups(th, machine)) {
-			rb_erase(&th->rb_node, &machine->threads);
+			rb_erase_init(&th->rb_node, &machine->threads);
+			RB_CLEAR_NODE(&th->rb_node);
 			thread__delete(th);
 			return NULL;
 		}
@@ -400,22 +418,36 @@ static struct thread *__machine__findnew_thread(struct machine *machine,
 		 * It is now in the rbtree, get a ref
 		 */
 		thread__get(th);
-		machine->last_match = thread__get(th);
+		machine->last_match = th;
 	}
 
 	return th;
 }
 
+struct thread *__machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid)
+{
+	return ____machine__findnew_thread(machine, pid, tid, true);
+}
+
 struct thread *machine__findnew_thread(struct machine *machine, pid_t pid,
 				       pid_t tid)
 {
-	return __machine__findnew_thread(machine, pid, tid, true);
+	struct thread *th;
+
+	pthread_rwlock_wrlock(&machine->threads_lock);
+	th = thread__get(__machine__findnew_thread(machine, pid, tid));
+	pthread_rwlock_unlock(&machine->threads_lock);
+	return th;
 }
 
 struct thread *machine__find_thread(struct machine *machine, pid_t pid,
 				    pid_t tid)
 {
-	return __machine__findnew_thread(machine, pid, tid, false);
+	struct thread *th;
+	pthread_rwlock_rdlock(&machine->threads_lock);
+	th =  thread__get(____machine__findnew_thread(machine, pid, tid, false));
+	pthread_rwlock_unlock(&machine->threads_lock);
+	return th;
 }
 
 struct comm *machine__thread_exec_comm(struct machine *machine,
@@ -434,6 +466,7 @@ int machine__process_comm_event(struct machine *machine, union perf_event *event
 							event->comm.pid,
 							event->comm.tid);
 	bool exec = event->header.misc & PERF_RECORD_MISC_COMM_EXEC;
+	int err = 0;
 
 	if (exec)
 		machine->comm_exec = true;
@@ -444,10 +477,12 @@ int machine__process_comm_event(struct machine *machine, union perf_event *event
 	if (thread == NULL ||
 	    __thread__set_comm(thread, event->comm.comm, sample->time, exec)) {
 		dump_printf("problem processing PERF_RECORD_COMM, skipping event.\n");
-		return -1;
+		err = -1;
 	}
 
-	return 0;
+	thread__put(thread);
+
+	return err;
 }
 
 int machine__process_lost_event(struct machine *machine __maybe_unused,
@@ -458,17 +493,27 @@ int machine__process_lost_event(struct machine *machine __maybe_unused,
 	return 0;
 }
 
-static struct dso*
-machine__module_dso(struct machine *machine, struct kmod_path *m,
-		    const char *filename)
+int machine__process_lost_samples_event(struct machine *machine __maybe_unused,
+					union perf_event *event, struct perf_sample *sample)
+{
+	dump_printf(": id:%" PRIu64 ": lost samples :%" PRIu64 "\n",
+		    sample->id, event->lost_samples.lost);
+	return 0;
+}
+
+static struct dso *machine__findnew_module_dso(struct machine *machine,
+					       struct kmod_path *m,
+					       const char *filename)
 {
 	struct dso *dso;
 
-	dso = dsos__find(&machine->kernel_dsos, m->name, true);
+	pthread_rwlock_wrlock(&machine->dsos.lock);
+
+	dso = __dsos__find(&machine->dsos, m->name, true);
 	if (!dso) {
-		dso = dsos__addnew(&machine->kernel_dsos, m->name);
+		dso = __dsos__addnew(&machine->dsos, m->name);
 		if (dso == NULL)
-			return NULL;
+			goto out_unlock;
 
 		if (machine__is_host(machine))
 			dso->symtab_type = DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE;
@@ -483,11 +528,30 @@ machine__module_dso(struct machine *machine, struct kmod_path *m,
 		dso__set_long_name(dso, strdup(filename), true);
 	}
 
+	dso__get(dso);
+out_unlock:
+	pthread_rwlock_unlock(&machine->dsos.lock);
 	return dso;
 }
 
-struct map *machine__new_module(struct machine *machine, u64 start,
-				const char *filename)
+int machine__process_aux_event(struct machine *machine __maybe_unused,
+			       union perf_event *event)
+{
+	if (dump_trace)
+		perf_event__fprintf_aux(event, stdout);
+	return 0;
+}
+
+int machine__process_itrace_start_event(struct machine *machine __maybe_unused,
+					union perf_event *event)
+{
+	if (dump_trace)
+		perf_event__fprintf_itrace_start(event, stdout);
+	return 0;
+}
+
+struct map *machine__findnew_module_map(struct machine *machine, u64 start,
+					const char *filename)
 {
 	struct map *map = NULL;
 	struct dso *dso;
@@ -501,7 +565,7 @@ struct map *machine__new_module(struct machine *machine, u64 start,
 	if (map)
 		goto out;
 
-	dso = machine__module_dso(machine, &m, filename);
+	dso = machine__findnew_module_dso(machine, &m, filename);
 	if (dso == NULL)
 		goto out;
 
@@ -519,13 +583,11 @@ out:
 size_t machines__fprintf_dsos(struct machines *machines, FILE *fp)
 {
 	struct rb_node *nd;
-	size_t ret = __dsos__fprintf(&machines->host.kernel_dsos.head, fp) +
-		     __dsos__fprintf(&machines->host.user_dsos.head, fp);
+	size_t ret = __dsos__fprintf(&machines->host.dsos.head, fp);
 
 	for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) {
 		struct machine *pos = rb_entry(nd, struct machine, rb_node);
-		ret += __dsos__fprintf(&pos->kernel_dsos.head, fp);
-		ret += __dsos__fprintf(&pos->user_dsos.head, fp);
+		ret += __dsos__fprintf(&pos->dsos.head, fp);
 	}
 
 	return ret;
@@ -534,8 +596,7 @@ size_t machines__fprintf_dsos(struct machines *machines, FILE *fp)
 size_t machine__fprintf_dsos_buildid(struct machine *m, FILE *fp,
 				     bool (skip)(struct dso *dso, int parm), int parm)
 {
-	return __dsos__fprintf_buildid(&m->kernel_dsos.head, fp, skip, parm) +
-	       __dsos__fprintf_buildid(&m->user_dsos.head, fp, skip, parm);
+	return __dsos__fprintf_buildid(&m->dsos.head, fp, skip, parm);
 }
 
 size_t machines__fprintf_dsos_buildid(struct machines *machines, FILE *fp,
@@ -575,12 +636,16 @@ size_t machine__fprintf(struct machine *machine, FILE *fp)
 	size_t ret = 0;
 	struct rb_node *nd;
 
+	pthread_rwlock_rdlock(&machine->threads_lock);
+
 	for (nd = rb_first(&machine->threads); nd; nd = rb_next(nd)) {
 		struct thread *pos = rb_entry(nd, struct thread, rb_node);
 
 		ret += thread__fprintf(pos, fp);
 	}
 
+	pthread_rwlock_unlock(&machine->threads_lock);
+
 	return ret;
 }
 
@@ -594,9 +659,8 @@ static struct dso *machine__get_kernel(struct machine *machine)
 		if (!vmlinux_name)
 			vmlinux_name = "[kernel.kallsyms]";
 
-		kernel = dso__kernel_findnew(machine, vmlinux_name,
-					     "[kernel]",
-					     DSO_TYPE_KERNEL);
+		kernel = machine__findnew_kernel(machine, vmlinux_name,
+						 "[kernel]", DSO_TYPE_KERNEL);
 	} else {
 		char bf[PATH_MAX];
 
@@ -606,9 +670,9 @@ static struct dso *machine__get_kernel(struct machine *machine)
 			vmlinux_name = machine__mmap_name(machine, bf,
 							  sizeof(bf));
 
-		kernel = dso__kernel_findnew(machine, vmlinux_name,
-					     "[guest.kernel]",
-					     DSO_TYPE_GUEST_KERNEL);
+		kernel = machine__findnew_kernel(machine, vmlinux_name,
+						 "[guest.kernel]",
+						 DSO_TYPE_GUEST_KERNEL);
 	}
 
 	if (kernel != NULL && (!kernel->has_build_id))
@@ -713,7 +777,6 @@ void machine__destroy_kernel_maps(struct machine *machine)
 				kmap->ref_reloc_sym = NULL;
 		}
 
-		map__delete(machine->vmlinux_maps[type]);
 		machine->vmlinux_maps[type] = NULL;
 	}
 }
@@ -970,7 +1033,7 @@ static int machine__create_module(void *arg, const char *name, u64 start)
 	struct machine *machine = arg;
 	struct map *map;
 
-	map = machine__new_module(machine, start, name);
+	map = machine__findnew_module_map(machine, start, name);
 	if (map == NULL)
 		return -1;
 
@@ -1062,7 +1125,7 @@ static bool machine__uses_kcore(struct machine *machine)
 {
 	struct dso *dso;
 
-	list_for_each_entry(dso, &machine->kernel_dsos.head, node) {
+	list_for_each_entry(dso, &machine->dsos.head, node) {
 		if (dso__is_kcore(dso))
 			return true;
 	}
@@ -1093,8 +1156,8 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 				strlen(kmmap_prefix) - 1) == 0;
 	if (event->mmap.filename[0] == '/' ||
 	    (!is_kernel_mmap && event->mmap.filename[0] == '[')) {
-		map = machine__new_module(machine, event->mmap.start,
-					  event->mmap.filename);
+		map = machine__findnew_module_map(machine, event->mmap.start,
+						  event->mmap.filename);
 		if (map == NULL)
 			goto out_problem;
 
@@ -1109,23 +1172,48 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 		struct dso *kernel = NULL;
 		struct dso *dso;
 
-		list_for_each_entry(dso, &machine->kernel_dsos.head, node) {
-			if (is_kernel_module(dso->long_name))
+		pthread_rwlock_rdlock(&machine->dsos.lock);
+
+		list_for_each_entry(dso, &machine->dsos.head, node) {
+
+			/*
+			 * The cpumode passed to is_kernel_module is not the
+			 * cpumode of *this* event. If we insist on passing
+			 * correct cpumode to is_kernel_module, we should
+			 * record the cpumode when we adding this dso to the
+			 * linked list.
+			 *
+			 * However we don't really need passing correct
+			 * cpumode.  We know the correct cpumode must be kernel
+			 * mode (if not, we should not link it onto kernel_dsos
+			 * list).
+			 *
+			 * Therefore, we pass PERF_RECORD_MISC_CPUMODE_UNKNOWN.
+			 * is_kernel_module() treats it as a kernel cpumode.
+			 */
+
+			if (!dso->kernel ||
+			    is_kernel_module(dso->long_name,
+					     PERF_RECORD_MISC_CPUMODE_UNKNOWN))
 				continue;
 
+
 			kernel = dso;
 			break;
 		}
 
+		pthread_rwlock_unlock(&machine->dsos.lock);
+
 		if (kernel == NULL)
-			kernel = __dsos__findnew(&machine->kernel_dsos,
-						 kmmap_prefix);
+			kernel = machine__findnew_dso(machine, kmmap_prefix);
 		if (kernel == NULL)
 			goto out_problem;
 
 		kernel->kernel = kernel_type;
-		if (__machine__create_kernel_maps(machine, kernel) < 0)
+		if (__machine__create_kernel_maps(machine, kernel) < 0) {
+			dso__put(kernel);
 			goto out_problem;
+		}
 
 		if (strstr(kernel->long_name, "vmlinux"))
 			dso__set_short_name(kernel, "[kernel.vmlinux]", false);
@@ -1197,11 +1285,15 @@ int machine__process_mmap2_event(struct machine *machine,
 			event->mmap2.filename, type, thread);
 
 	if (map == NULL)
-		goto out_problem;
+		goto out_problem_map;
 
 	thread__insert_map(thread, map);
+	thread__put(thread);
+	map__put(map);
 	return 0;
 
+out_problem_map:
+	thread__put(thread);
 out_problem:
 	dump_printf("problem processing PERF_RECORD_MMAP2, skipping event.\n");
 	return 0;
@@ -1244,31 +1336,46 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event
 			type, thread);
 
 	if (map == NULL)
-		goto out_problem;
+		goto out_problem_map;
 
 	thread__insert_map(thread, map);
+	thread__put(thread);
+	map__put(map);
 	return 0;
 
+out_problem_map:
+	thread__put(thread);
 out_problem:
 	dump_printf("problem processing PERF_RECORD_MMAP, skipping event.\n");
 	return 0;
 }
 
-void machine__remove_thread(struct machine *machine, struct thread *th)
+static void __machine__remove_thread(struct machine *machine, struct thread *th, bool lock)
 {
 	if (machine->last_match == th)
-		thread__zput(machine->last_match);
+		machine->last_match = NULL;
 
-	rb_erase(&th->rb_node, &machine->threads);
+	BUG_ON(atomic_read(&th->refcnt) == 0);
+	if (lock)
+		pthread_rwlock_wrlock(&machine->threads_lock);
+	rb_erase_init(&th->rb_node, &machine->threads);
+	RB_CLEAR_NODE(&th->rb_node);
 	/*
 	 * Move it first to the dead_threads list, then drop the reference,
 	 * if this is the last reference, then the thread__delete destructor
 	 * will be called and we will remove it from the dead_threads list.
 	 */
 	list_add_tail(&th->node, &machine->dead_threads);
+	if (lock)
+		pthread_rwlock_unlock(&machine->threads_lock);
 	thread__put(th);
 }
 
+void machine__remove_thread(struct machine *machine, struct thread *th)
+{
+	return __machine__remove_thread(machine, th, true);
+}
+
 int machine__process_fork_event(struct machine *machine, union perf_event *event,
 				struct perf_sample *sample)
 {
@@ -1278,10 +1385,13 @@ int machine__process_fork_event(struct machine *machine, union perf_event *event
 	struct thread *parent = machine__findnew_thread(machine,
 							event->fork.ppid,
 							event->fork.ptid);
+	int err = 0;
 
 	/* if a thread currently exists for the thread id remove it */
-	if (thread != NULL)
+	if (thread != NULL) {
 		machine__remove_thread(machine, thread);
+		thread__put(thread);
+	}
 
 	thread = machine__findnew_thread(machine, event->fork.pid,
 					 event->fork.tid);
@@ -1291,10 +1401,12 @@ int machine__process_fork_event(struct machine *machine, union perf_event *event
 	if (thread == NULL || parent == NULL ||
 	    thread__fork(thread, parent, sample->time) < 0) {
 		dump_printf("problem processing PERF_RECORD_FORK, skipping event.\n");
-		return -1;
+		err = -1;
 	}
+	thread__put(thread);
+	thread__put(parent);
 
-	return 0;
+	return err;
 }
 
 int machine__process_exit_event(struct machine *machine, union perf_event *event,
@@ -1307,8 +1419,10 @@ int machine__process_exit_event(struct machine *machine, union perf_event *event
 	if (dump_trace)
 		perf_event__fprintf_task(event, stdout);
 
-	if (thread != NULL)
+	if (thread != NULL) {
 		thread__exited(thread);
+		thread__put(thread);
+	}
 
 	return 0;
 }
@@ -1331,6 +1445,13 @@ int machine__process_event(struct machine *machine, union perf_event *event,
 		ret = machine__process_exit_event(machine, event, sample); break;
 	case PERF_RECORD_LOST:
 		ret = machine__process_lost_event(machine, event, sample); break;
+	case PERF_RECORD_AUX:
+		ret = machine__process_aux_event(machine, event); break;
+	case PERF_RECORD_ITRACE_START:
+		ret = machine__process_itrace_start_event(machine, event);
+	case PERF_RECORD_LOST_SAMPLES:
+		ret = machine__process_lost_samples_event(machine, event, sample); break;
+		break;
 	default:
 		ret = -1;
 		break;
@@ -1769,14 +1890,36 @@ int machine__for_each_thread(struct machine *machine,
 	return rc;
 }
 
+int machines__for_each_thread(struct machines *machines,
+			      int (*fn)(struct thread *thread, void *p),
+			      void *priv)
+{
+	struct rb_node *nd;
+	int rc = 0;
+
+	rc = machine__for_each_thread(&machines->host, fn, priv);
+	if (rc != 0)
+		return rc;
+
+	for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) {
+		struct machine *machine = rb_entry(nd, struct machine, rb_node);
+
+		rc = machine__for_each_thread(machine, fn, priv);
+		if (rc != 0)
+			return rc;
+	}
+	return rc;
+}
+
 int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool,
 				  struct target *target, struct thread_map *threads,
-				  perf_event__handler_t process, bool data_mmap)
+				  perf_event__handler_t process, bool data_mmap,
+				  unsigned int proc_map_timeout)
 {
 	if (target__has_task(target))
-		return perf_event__synthesize_thread_map(tool, threads, process, machine, data_mmap);
+		return perf_event__synthesize_thread_map(tool, threads, process, machine, data_mmap, proc_map_timeout);
 	else if (target__has_cpu(target))
-		return perf_event__synthesize_threads(tool, process, machine, data_mmap);
+		return perf_event__synthesize_threads(tool, process, machine, data_mmap, proc_map_timeout);
 	/* command specified */
 	return 0;
 }
@@ -1820,6 +1963,7 @@ int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid,
 		return -ENOMEM;
 
 	thread->cpu = cpu;
+	thread__put(thread);
 
 	return 0;
 }
@@ -1845,3 +1989,8 @@ int machine__get_kernel_start(struct machine *machine)
 	}
 	return err;
 }
+
+struct dso *machine__findnew_dso(struct machine *machine, const char *filename)
+{
+	return dsos__findnew(&machine->dsos, filename);
+}
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 6d64cedb9d1e..887798e511e9 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -30,11 +30,11 @@ struct machine {
 	bool		  comm_exec;
 	char		  *root_dir;
 	struct rb_root	  threads;
+	pthread_rwlock_t  threads_lock;
 	struct list_head  dead_threads;
 	struct thread	  *last_match;
 	struct vdso_info  *vdso_info;
-	struct dsos	  user_dsos;
-	struct dsos	  kernel_dsos;
+	struct dsos	  dsos;
 	struct map_groups kmaps;
 	struct map	  *vmlinux_maps[MAP__NR_TYPES];
 	u64		  kernel_start;
@@ -81,6 +81,12 @@ int machine__process_fork_event(struct machine *machine, union perf_event *event
 				struct perf_sample *sample);
 int machine__process_lost_event(struct machine *machine, union perf_event *event,
 				struct perf_sample *sample);
+int machine__process_lost_samples_event(struct machine *machine, union perf_event *event,
+					struct perf_sample *sample);
+int machine__process_aux_event(struct machine *machine,
+			       union perf_event *event);
+int machine__process_itrace_start_event(struct machine *machine,
+					union perf_event *event);
 int machine__process_mmap_event(struct machine *machine, union perf_event *event,
 				struct perf_sample *sample);
 int machine__process_mmap2_event(struct machine *machine, union perf_event *event,
@@ -147,8 +153,10 @@ static inline bool machine__is_host(struct machine *machine)
 	return machine ? machine->pid == HOST_KERNEL_ID : false;
 }
 
-struct thread *machine__findnew_thread(struct machine *machine, pid_t pid,
-				       pid_t tid);
+struct thread *__machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid);
+struct thread *machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid);
+
+struct dso *machine__findnew_dso(struct machine *machine, const char *filename);
 
 size_t machine__fprintf(struct machine *machine, FILE *fp);
 
@@ -181,8 +189,8 @@ struct symbol *machine__find_kernel_function_by_name(struct machine *machine,
 						 filter);
 }
 
-struct map *machine__new_module(struct machine *machine, u64 start,
-				const char *filename);
+struct map *machine__findnew_module_map(struct machine *machine, u64 start,
+					const char *filename);
 
 int machine__load_kallsyms(struct machine *machine, const char *filename,
 			   enum map_type type, symbol_filter_t filter);
@@ -208,16 +216,22 @@ size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp);
 int machine__for_each_thread(struct machine *machine,
 			     int (*fn)(struct thread *thread, void *p),
 			     void *priv);
+int machines__for_each_thread(struct machines *machines,
+			      int (*fn)(struct thread *thread, void *p),
+			      void *priv);
 
 int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool,
 				  struct target *target, struct thread_map *threads,
-				  perf_event__handler_t process, bool data_mmap);
+				  perf_event__handler_t process, bool data_mmap,
+				  unsigned int proc_map_timeout);
 static inline
 int machine__synthesize_threads(struct machine *machine, struct target *target,
-				struct thread_map *threads, bool data_mmap)
+				struct thread_map *threads, bool data_mmap,
+				unsigned int proc_map_timeout)
 {
 	return __machine__synthesize_threads(machine, NULL, target, threads,
-					     perf_event__process, data_mmap);
+					     perf_event__process, data_mmap,
+					     proc_map_timeout);
 }
 
 pid_t machine__get_current_tid(struct machine *machine, int cpu);
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index a14f08f41686..b5a5e9c02437 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -16,6 +16,8 @@
 #include "machine.h"
 #include <linux/string.h>
 
+static void __maps__insert(struct maps *maps, struct map *map);
+
 const char *map_type__name[MAP__NR_TYPES] = {
 	[MAP__FUNCTION] = "Functions",
 	[MAP__VARIABLE] = "Variables",
@@ -130,13 +132,13 @@ void map__init(struct map *map, enum map_type type,
 	map->end      = end;
 	map->pgoff    = pgoff;
 	map->reloc    = 0;
-	map->dso      = dso;
+	map->dso      = dso__get(dso);
 	map->map_ip   = map__map_ip;
 	map->unmap_ip = map__unmap_ip;
 	RB_CLEAR_NODE(&map->rb_node);
 	map->groups   = NULL;
-	map->referenced = false;
 	map->erange_warned = false;
+	atomic_set(&map->refcnt, 1);
 }
 
 struct map *map__new(struct machine *machine, u64 start, u64 len,
@@ -175,9 +177,9 @@ struct map *map__new(struct machine *machine, u64 start, u64 len,
 
 		if (vdso) {
 			pgoff = 0;
-			dso = vdso__dso_findnew(machine, thread);
+			dso = machine__findnew_vdso(machine, thread);
 		} else
-			dso = __dsos__findnew(&machine->user_dsos, filename);
+			dso = machine__findnew_dso(machine, filename);
 
 		if (dso == NULL)
 			goto out_delete;
@@ -195,6 +197,7 @@ struct map *map__new(struct machine *machine, u64 start, u64 len,
 			if (type != MAP__FUNCTION)
 				dso__set_loaded(dso, map->type);
 		}
+		dso__put(dso);
 	}
 	return map;
 out_delete:
@@ -221,11 +224,24 @@ struct map *map__new2(u64 start, struct dso *dso, enum map_type type)
 	return map;
 }
 
+static void map__exit(struct map *map)
+{
+	BUG_ON(!RB_EMPTY_NODE(&map->rb_node));
+	dso__zput(map->dso);
+}
+
 void map__delete(struct map *map)
 {
+	map__exit(map);
 	free(map);
 }
 
+void map__put(struct map *map)
+{
+	if (map && atomic_dec_and_test(&map->refcnt))
+		map__delete(map);
+}
+
 void map__fixup_start(struct map *map)
 {
 	struct rb_root *symbols = &map->dso->symbols[map->type];
@@ -292,6 +308,11 @@ int map__load(struct map *map, symbol_filter_t filter)
 	return 0;
 }
 
+int __weak arch__compare_symbol_names(const char *namea, const char *nameb)
+{
+	return strcmp(namea, nameb);
+}
+
 struct symbol *map__find_symbol(struct map *map, u64 addr,
 				symbol_filter_t filter)
 {
@@ -413,48 +434,49 @@ u64 map__objdump_2mem(struct map *map, u64 ip)
 	return ip + map->reloc;
 }
 
+static void maps__init(struct maps *maps)
+{
+	maps->entries = RB_ROOT;
+	pthread_rwlock_init(&maps->lock, NULL);
+}
+
 void map_groups__init(struct map_groups *mg, struct machine *machine)
 {
 	int i;
 	for (i = 0; i < MAP__NR_TYPES; ++i) {
-		mg->maps[i] = RB_ROOT;
-		INIT_LIST_HEAD(&mg->removed_maps[i]);
+		maps__init(&mg->maps[i]);
 	}
 	mg->machine = machine;
-	mg->refcnt = 1;
+	atomic_set(&mg->refcnt, 1);
 }
 
-static void maps__delete(struct rb_root *maps)
+static void __maps__purge(struct maps *maps)
 {
-	struct rb_node *next = rb_first(maps);
+	struct rb_root *root = &maps->entries;
+	struct rb_node *next = rb_first(root);
 
 	while (next) {
 		struct map *pos = rb_entry(next, struct map, rb_node);
 
 		next = rb_next(&pos->rb_node);
-		rb_erase(&pos->rb_node, maps);
-		map__delete(pos);
+		rb_erase_init(&pos->rb_node, root);
+		map__put(pos);
 	}
 }
 
-static void maps__delete_removed(struct list_head *maps)
+static void maps__exit(struct maps *maps)
 {
-	struct map *pos, *n;
-
-	list_for_each_entry_safe(pos, n, maps, node) {
-		list_del(&pos->node);
-		map__delete(pos);
-	}
+	pthread_rwlock_wrlock(&maps->lock);
+	__maps__purge(maps);
+	pthread_rwlock_unlock(&maps->lock);
 }
 
 void map_groups__exit(struct map_groups *mg)
 {
 	int i;
 
-	for (i = 0; i < MAP__NR_TYPES; ++i) {
-		maps__delete(&mg->maps[i]);
-		maps__delete_removed(&mg->removed_maps[i]);
-	}
+	for (i = 0; i < MAP__NR_TYPES; ++i)
+		maps__exit(&mg->maps[i]);
 }
 
 bool map_groups__empty(struct map_groups *mg)
@@ -464,8 +486,6 @@ bool map_groups__empty(struct map_groups *mg)
 	for (i = 0; i < MAP__NR_TYPES; ++i) {
 		if (maps__first(&mg->maps[i]))
 			return false;
-		if (!list_empty(&mg->removed_maps[i]))
-			return false;
 	}
 
 	return true;
@@ -489,32 +509,10 @@ void map_groups__delete(struct map_groups *mg)
 
 void map_groups__put(struct map_groups *mg)
 {
-	if (--mg->refcnt == 0)
+	if (mg && atomic_dec_and_test(&mg->refcnt))
 		map_groups__delete(mg);
 }
 
-void map_groups__flush(struct map_groups *mg)
-{
-	int type;
-
-	for (type = 0; type < MAP__NR_TYPES; type++) {
-		struct rb_root *root = &mg->maps[type];
-		struct rb_node *next = rb_first(root);
-
-		while (next) {
-			struct map *pos = rb_entry(next, struct map, rb_node);
-			next = rb_next(&pos->rb_node);
-			rb_erase(&pos->rb_node, root);
-			/*
-			 * We may have references to this map, for
-			 * instance in some hist_entry instances, so
-			 * just move them to a separate list.
-			 */
-			list_add_tail(&pos->node, &mg->removed_maps[pos->type]);
-		}
-	}
-}
-
 struct symbol *map_groups__find_symbol(struct map_groups *mg,
 				       enum map_type type, u64 addr,
 				       struct map **mapp,
@@ -538,20 +536,28 @@ struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg,
 					       struct map **mapp,
 					       symbol_filter_t filter)
 {
+	struct maps *maps = &mg->maps[type];
+	struct symbol *sym;
 	struct rb_node *nd;
 
-	for (nd = rb_first(&mg->maps[type]); nd; nd = rb_next(nd)) {
+	pthread_rwlock_rdlock(&maps->lock);
+
+	for (nd = rb_first(&maps->entries); nd; nd = rb_next(nd)) {
 		struct map *pos = rb_entry(nd, struct map, rb_node);
-		struct symbol *sym = map__find_symbol_by_name(pos, name, filter);
+
+		sym = map__find_symbol_by_name(pos, name, filter);
 
 		if (sym == NULL)
 			continue;
 		if (mapp != NULL)
 			*mapp = pos;
-		return sym;
+		goto out;
 	}
 
-	return NULL;
+	sym = NULL;
+out:
+	pthread_rwlock_unlock(&maps->lock);
+	return sym;
 }
 
 int map_groups__find_ams(struct addr_map_symbol *ams, symbol_filter_t filter)
@@ -571,73 +577,54 @@ int map_groups__find_ams(struct addr_map_symbol *ams, symbol_filter_t filter)
 	return ams->sym ? 0 : -1;
 }
 
-size_t __map_groups__fprintf_maps(struct map_groups *mg, enum map_type type,
-				  FILE *fp)
+static size_t maps__fprintf(struct maps *maps, FILE *fp)
 {
-	size_t printed = fprintf(fp, "%s:\n", map_type__name[type]);
+	size_t printed = 0;
 	struct rb_node *nd;
 
-	for (nd = rb_first(&mg->maps[type]); nd; nd = rb_next(nd)) {
+	pthread_rwlock_rdlock(&maps->lock);
+
+	for (nd = rb_first(&maps->entries); nd; nd = rb_next(nd)) {
 		struct map *pos = rb_entry(nd, struct map, rb_node);
 		printed += fprintf(fp, "Map:");
 		printed += map__fprintf(pos, fp);
 		if (verbose > 2) {
-			printed += dso__fprintf(pos->dso, type, fp);
+			printed += dso__fprintf(pos->dso, pos->type, fp);
 			printed += fprintf(fp, "--\n");
 		}
 	}
 
-	return printed;
-}
+	pthread_rwlock_unlock(&maps->lock);
 
-static size_t map_groups__fprintf_maps(struct map_groups *mg, FILE *fp)
-{
-	size_t printed = 0, i;
-	for (i = 0; i < MAP__NR_TYPES; ++i)
-		printed += __map_groups__fprintf_maps(mg, i, fp);
 	return printed;
 }
 
-static size_t __map_groups__fprintf_removed_maps(struct map_groups *mg,
-						 enum map_type type, FILE *fp)
+size_t __map_groups__fprintf_maps(struct map_groups *mg, enum map_type type,
+				  FILE *fp)
 {
-	struct map *pos;
-	size_t printed = 0;
-
-	list_for_each_entry(pos, &mg->removed_maps[type], node) {
-		printed += fprintf(fp, "Map:");
-		printed += map__fprintf(pos, fp);
-		if (verbose > 1) {
-			printed += dso__fprintf(pos->dso, type, fp);
-			printed += fprintf(fp, "--\n");
-		}
-	}
-	return printed;
+	size_t printed = fprintf(fp, "%s:\n", map_type__name[type]);
+	return printed += maps__fprintf(&mg->maps[type], fp);
 }
 
-static size_t map_groups__fprintf_removed_maps(struct map_groups *mg,
-					       FILE *fp)
+size_t map_groups__fprintf(struct map_groups *mg, FILE *fp)
 {
 	size_t printed = 0, i;
 	for (i = 0; i < MAP__NR_TYPES; ++i)
-		printed += __map_groups__fprintf_removed_maps(mg, i, fp);
+		printed += __map_groups__fprintf_maps(mg, i, fp);
 	return printed;
 }
 
-size_t map_groups__fprintf(struct map_groups *mg, FILE *fp)
+static int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp)
 {
-	size_t printed = map_groups__fprintf_maps(mg, fp);
-	printed += fprintf(fp, "Removed maps:\n");
-	return printed + map_groups__fprintf_removed_maps(mg, fp);
-}
-
-int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
-				   FILE *fp)
-{
-	struct rb_root *root = &mg->maps[map->type];
-	struct rb_node *next = rb_first(root);
+	struct rb_root *root;
+	struct rb_node *next;
 	int err = 0;
 
+	pthread_rwlock_wrlock(&maps->lock);
+
+	root = &maps->entries;
+	next = rb_first(root);
+
 	while (next) {
 		struct map *pos = rb_entry(next, struct map, rb_node);
 		next = rb_next(&pos->rb_node);
@@ -651,7 +638,7 @@ int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
 			map__fprintf(pos, fp);
 		}
 
-		rb_erase(&pos->rb_node, root);
+		rb_erase_init(&pos->rb_node, root);
 		/*
 		 * Now check if we need to create new maps for areas not
 		 * overlapped by the new map:
@@ -661,11 +648,11 @@ int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
 
 			if (before == NULL) {
 				err = -ENOMEM;
-				goto move_map;
+				goto put_map;
 			}
 
 			before->end = map->start;
-			map_groups__insert(mg, before);
+			__maps__insert(maps, before);
 			if (verbose >= 2)
 				map__fprintf(before, fp);
 		}
@@ -675,28 +662,31 @@ int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
 
 			if (after == NULL) {
 				err = -ENOMEM;
-				goto move_map;
+				goto put_map;
 			}
 
 			after->start = map->end;
-			map_groups__insert(mg, after);
+			__maps__insert(maps, after);
 			if (verbose >= 2)
 				map__fprintf(after, fp);
 		}
-move_map:
-		/*
-		 * If we have references, just move them to a separate list.
-		 */
-		if (pos->referenced)
-			list_add_tail(&pos->node, &mg->removed_maps[map->type]);
-		else
-			map__delete(pos);
+put_map:
+		map__put(pos);
 
 		if (err)
-			return err;
+			goto out;
 	}
 
-	return 0;
+	err = 0;
+out:
+	pthread_rwlock_unlock(&maps->lock);
+	return err;
+}
+
+int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
+				   FILE *fp)
+{
+	return maps__fixup_overlappings(&mg->maps[map->type], map, fp);
 }
 
 /*
@@ -705,20 +695,28 @@ move_map:
 int map_groups__clone(struct map_groups *mg,
 		      struct map_groups *parent, enum map_type type)
 {
-	struct rb_node *nd;
-	for (nd = rb_first(&parent->maps[type]); nd; nd = rb_next(nd)) {
-		struct map *map = rb_entry(nd, struct map, rb_node);
+	int err = -ENOMEM;
+	struct map *map;
+	struct maps *maps = &parent->maps[type];
+
+	pthread_rwlock_rdlock(&maps->lock);
+
+	for (map = maps__first(maps); map; map = map__next(map)) {
 		struct map *new = map__clone(map);
 		if (new == NULL)
-			return -ENOMEM;
+			goto out_unlock;
 		map_groups__insert(mg, new);
 	}
-	return 0;
+
+	err = 0;
+out_unlock:
+	pthread_rwlock_unlock(&maps->lock);
+	return err;
 }
 
-void maps__insert(struct rb_root *maps, struct map *map)
+static void __maps__insert(struct maps *maps, struct map *map)
 {
-	struct rb_node **p = &maps->rb_node;
+	struct rb_node **p = &maps->entries.rb_node;
 	struct rb_node *parent = NULL;
 	const u64 ip = map->start;
 	struct map *m;
@@ -733,20 +731,38 @@ void maps__insert(struct rb_root *maps, struct map *map)
 	}
 
 	rb_link_node(&map->rb_node, parent, p);
-	rb_insert_color(&map->rb_node, maps);
+	rb_insert_color(&map->rb_node, &maps->entries);
+	map__get(map);
 }
 
-void maps__remove(struct rb_root *maps, struct map *map)
+void maps__insert(struct maps *maps, struct map *map)
 {
-	rb_erase(&map->rb_node, maps);
+	pthread_rwlock_wrlock(&maps->lock);
+	__maps__insert(maps, map);
+	pthread_rwlock_unlock(&maps->lock);
 }
 
-struct map *maps__find(struct rb_root *maps, u64 ip)
+static void __maps__remove(struct maps *maps, struct map *map)
 {
-	struct rb_node **p = &maps->rb_node;
-	struct rb_node *parent = NULL;
+	rb_erase_init(&map->rb_node, &maps->entries);
+	map__put(map);
+}
+
+void maps__remove(struct maps *maps, struct map *map)
+{
+	pthread_rwlock_wrlock(&maps->lock);
+	__maps__remove(maps, map);
+	pthread_rwlock_unlock(&maps->lock);
+}
+
+struct map *maps__find(struct maps *maps, u64 ip)
+{
+	struct rb_node **p, *parent = NULL;
 	struct map *m;
 
+	pthread_rwlock_rdlock(&maps->lock);
+
+	p = &maps->entries.rb_node;
 	while (*p != NULL) {
 		parent = *p;
 		m = rb_entry(parent, struct map, rb_node);
@@ -755,22 +771,25 @@ struct map *maps__find(struct rb_root *maps, u64 ip)
 		else if (ip >= m->end)
 			p = &(*p)->rb_right;
 		else
-			return m;
+			goto out;
 	}
 
-	return NULL;
+	m = NULL;
+out:
+	pthread_rwlock_unlock(&maps->lock);
+	return m;
 }
 
-struct map *maps__first(struct rb_root *maps)
+struct map *maps__first(struct maps *maps)
 {
-	struct rb_node *first = rb_first(maps);
+	struct rb_node *first = rb_first(&maps->entries);
 
 	if (first)
 		return rb_entry(first, struct map, rb_node);
 	return NULL;
 }
 
-struct map *maps__next(struct map *map)
+struct map *map__next(struct map *map)
 {
 	struct rb_node *next = rb_next(&map->rb_node);
 
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index ec19c59ca38e..d73e687b224e 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -1,9 +1,11 @@
 #ifndef __PERF_MAP_H
 #define __PERF_MAP_H
 
+#include <linux/atomic.h>
 #include <linux/compiler.h>
 #include <linux/list.h>
 #include <linux/rbtree.h>
+#include <pthread.h>
 #include <stdio.h>
 #include <stdbool.h>
 #include <linux/types.h>
@@ -32,7 +34,6 @@ struct map {
 	u64			start;
 	u64			end;
 	u8 /* enum map_type */	type;
-	bool			referenced;
 	bool			erange_warned;
 	u32			priv;
 	u32			prot;
@@ -50,6 +51,7 @@ struct map {
 
 	struct dso		*dso;
 	struct map_groups	*groups;
+	atomic_t		refcnt;
 };
 
 struct kmap {
@@ -57,11 +59,15 @@ struct kmap {
 	struct map_groups	*kmaps;
 };
 
+struct maps {
+	struct rb_root	 entries;
+	pthread_rwlock_t lock;
+};
+
 struct map_groups {
-	struct rb_root	 maps[MAP__NR_TYPES];
-	struct list_head removed_maps[MAP__NR_TYPES];
+	struct maps	 maps[MAP__NR_TYPES];
 	struct machine	 *machine;
-	int		 refcnt;
+	atomic_t	 refcnt;
 };
 
 struct map_groups *map_groups__new(struct machine *machine);
@@ -70,7 +76,8 @@ bool map_groups__empty(struct map_groups *mg);
 
 static inline struct map_groups *map_groups__get(struct map_groups *mg)
 {
-	++mg->refcnt;
+	if (mg)
+		atomic_inc(&mg->refcnt);
 	return mg;
 }
 
@@ -124,7 +131,7 @@ struct thread;
  */
 #define __map__for_each_symbol_by_name(map, sym_name, pos, filter)	\
 	for (pos = map__find_symbol_by_name(map, sym_name, filter);	\
-	     pos && strcmp(pos->name, sym_name) == 0;		\
+	     pos && arch__compare_symbol_names(pos->name, sym_name) == 0;	\
 	     pos = symbol__next_by_name(pos))
 
 #define map__for_each_symbol_by_name(map, sym_name, pos)		\
@@ -132,6 +139,7 @@ struct thread;
 
 typedef int (*symbol_filter_t)(struct map *map, struct symbol *sym);
 
+int arch__compare_symbol_names(const char *namea, const char *nameb);
 void map__init(struct map *map, enum map_type type,
 	       u64 start, u64 end, u64 pgoff, struct dso *dso);
 struct map *map__new(struct machine *machine, u64 start, u64 len,
@@ -141,6 +149,24 @@ struct map *map__new(struct machine *machine, u64 start, u64 len,
 struct map *map__new2(u64 start, struct dso *dso, enum map_type type);
 void map__delete(struct map *map);
 struct map *map__clone(struct map *map);
+
+static inline struct map *map__get(struct map *map)
+{
+	if (map)
+		atomic_inc(&map->refcnt);
+	return map;
+}
+
+void map__put(struct map *map);
+
+static inline void __map__zput(struct map **map)
+{
+	map__put(*map);
+	*map = NULL;
+}
+
+#define map__zput(map) __map__zput(&map)
+
 int map__overlap(struct map *l, struct map *r);
 size_t map__fprintf(struct map *map, FILE *fp);
 size_t map__fprintf_dsoname(struct map *map, FILE *fp);
@@ -159,11 +185,11 @@ void map__reloc_vmlinux(struct map *map);
 
 size_t __map_groups__fprintf_maps(struct map_groups *mg, enum map_type type,
 				  FILE *fp);
-void maps__insert(struct rb_root *maps, struct map *map);
-void maps__remove(struct rb_root *maps, struct map *map);
-struct map *maps__find(struct rb_root *maps, u64 addr);
-struct map *maps__first(struct rb_root *maps);
-struct map *maps__next(struct map *map);
+void maps__insert(struct maps *maps, struct map *map);
+void maps__remove(struct maps *maps, struct map *map);
+struct map *maps__find(struct maps *maps, u64 addr);
+struct map *maps__first(struct maps *maps);
+struct map *map__next(struct map *map);
 void map_groups__init(struct map_groups *mg, struct machine *machine);
 void map_groups__exit(struct map_groups *mg);
 int map_groups__clone(struct map_groups *mg,
@@ -198,7 +224,7 @@ static inline struct map *map_groups__first(struct map_groups *mg,
 
 static inline struct map *map_groups__next(struct map *map)
 {
-	return maps__next(map);
+	return map__next(map);
 }
 
 struct symbol *map_groups__find_symbol(struct map_groups *mg,
@@ -230,6 +256,4 @@ int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
 struct map *map_groups__find_by_name(struct map_groups *mg,
 				     enum map_type type, const char *name);
 
-void map_groups__flush(struct map_groups *mg);
-
 #endif /* __PERF_MAP_H */
diff --git a/tools/perf/util/pager.c b/tools/perf/util/pager.c
index 31ee02d4e988..53ef006a951c 100644
--- a/tools/perf/util/pager.c
+++ b/tools/perf/util/pager.c
@@ -50,11 +50,6 @@ void setup_pager(void)
 
 	if (!isatty(1))
 		return;
-	if (!pager) {
-		if (!pager_program)
-			perf_config(perf_default_config, NULL);
-		pager = pager_program;
-	}
 	if (!pager)
 		pager = getenv("PAGER");
 	if (!(pager || access("/usr/bin/pager", X_OK)))
diff --git a/tools/perf/util/parse-branch-options.c b/tools/perf/util/parse-branch-options.c
new file mode 100644
index 000000000000..a3b1e13a05c0
--- /dev/null
+++ b/tools/perf/util/parse-branch-options.c
@@ -0,0 +1,94 @@
+#include "perf.h"
+#include "util/util.h"
+#include "util/debug.h"
+#include "util/parse-options.h"
+#include "util/parse-branch-options.h"
+
+#define BRANCH_OPT(n, m) \
+	{ .name = n, .mode = (m) }
+
+#define BRANCH_END { .name = NULL }
+
+struct branch_mode {
+	const char *name;
+	int mode;
+};
+
+static const struct branch_mode branch_modes[] = {
+	BRANCH_OPT("u", PERF_SAMPLE_BRANCH_USER),
+	BRANCH_OPT("k", PERF_SAMPLE_BRANCH_KERNEL),
+	BRANCH_OPT("hv", PERF_SAMPLE_BRANCH_HV),
+	BRANCH_OPT("any", PERF_SAMPLE_BRANCH_ANY),
+	BRANCH_OPT("any_call", PERF_SAMPLE_BRANCH_ANY_CALL),
+	BRANCH_OPT("any_ret", PERF_SAMPLE_BRANCH_ANY_RETURN),
+	BRANCH_OPT("ind_call", PERF_SAMPLE_BRANCH_IND_CALL),
+	BRANCH_OPT("abort_tx", PERF_SAMPLE_BRANCH_ABORT_TX),
+	BRANCH_OPT("in_tx", PERF_SAMPLE_BRANCH_IN_TX),
+	BRANCH_OPT("no_tx", PERF_SAMPLE_BRANCH_NO_TX),
+	BRANCH_OPT("cond", PERF_SAMPLE_BRANCH_COND),
+	BRANCH_OPT("ind_jmp", PERF_SAMPLE_BRANCH_IND_JUMP),
+	BRANCH_END
+};
+
+int
+parse_branch_stack(const struct option *opt, const char *str, int unset)
+{
+#define ONLY_PLM \
+	(PERF_SAMPLE_BRANCH_USER	|\
+	 PERF_SAMPLE_BRANCH_KERNEL	|\
+	 PERF_SAMPLE_BRANCH_HV)
+
+	uint64_t *mode = (uint64_t *)opt->value;
+	const struct branch_mode *br;
+	char *s, *os = NULL, *p;
+	int ret = -1;
+
+	if (unset)
+		return 0;
+
+	/*
+	 * cannot set it twice, -b + --branch-filter for instance
+	 */
+	if (*mode)
+		return -1;
+
+	/* str may be NULL in case no arg is passed to -b */
+	if (str) {
+		/* because str is read-only */
+		s = os = strdup(str);
+		if (!s)
+			return -1;
+
+		for (;;) {
+			p = strchr(s, ',');
+			if (p)
+				*p = '\0';
+
+			for (br = branch_modes; br->name; br++) {
+				if (!strcasecmp(s, br->name))
+					break;
+			}
+			if (!br->name) {
+				ui__warning("unknown branch filter %s,"
+					    " check man page\n", s);
+				goto error;
+			}
+
+			*mode |= br->mode;
+
+			if (!p)
+				break;
+
+			s = p + 1;
+		}
+	}
+	ret = 0;
+
+	/* default to any branch */
+	if ((*mode & ~ONLY_PLM) == 0) {
+		*mode = PERF_SAMPLE_BRANCH_ANY;
+	}
+error:
+	free(os);
+	return ret;
+}
diff --git a/tools/perf/util/parse-branch-options.h b/tools/perf/util/parse-branch-options.h
new file mode 100644
index 000000000000..b9d9470c2e82
--- /dev/null
+++ b/tools/perf/util/parse-branch-options.h
@@ -0,0 +1,5 @@
+#ifndef _PERF_PARSE_BRANCH_OPTIONS_H
+#define _PERF_PARSE_BRANCH_OPTIONS_H 1
+struct option;
+int parse_branch_stack(const struct option *opt, const char *str, int unset);
+#endif /* _PERF_PARSE_BRANCH_OPTIONS_H */
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index be0655388b38..2a4d1ec02846 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -17,6 +17,7 @@
 #include "parse-events-flex.h"
 #include "pmu.h"
 #include "thread_map.h"
+#include "asm/bug.h"
 
 #define MAX_NAME_LEN 100
 
@@ -538,16 +539,40 @@ int parse_events_add_breakpoint(struct list_head *list, int *idx,
 	return add_event(list, idx, &attr, NULL);
 }
 
+static int check_type_val(struct parse_events_term *term,
+			  struct parse_events_error *err,
+			  int type)
+{
+	if (type == term->type_val)
+		return 0;
+
+	if (err) {
+		err->idx = term->err_val;
+		if (type == PARSE_EVENTS__TERM_TYPE_NUM)
+			err->str = strdup("expected numeric value");
+		else
+			err->str = strdup("expected string value");
+	}
+	return -EINVAL;
+}
+
 static int config_term(struct perf_event_attr *attr,
-		       struct parse_events_term *term)
+		       struct parse_events_term *term,
+		       struct parse_events_error *err)
 {
-#define CHECK_TYPE_VAL(type)					\
-do {								\
-	if (PARSE_EVENTS__TERM_TYPE_ ## type != term->type_val)	\
-		return -EINVAL;					\
+#define CHECK_TYPE_VAL(type)						   \
+do {									   \
+	if (check_type_val(term, err, PARSE_EVENTS__TERM_TYPE_ ## type)) \
+		return -EINVAL;						   \
 } while (0)
 
 	switch (term->type_term) {
+	case PARSE_EVENTS__TERM_TYPE_USER:
+		/*
+		 * Always succeed for sysfs terms, as we dont know
+		 * at this point what type they need to have.
+		 */
+		return 0;
 	case PARSE_EVENTS__TERM_TYPE_CONFIG:
 		CHECK_TYPE_VAL(NUM);
 		attr->config = term->val.num;
@@ -582,18 +607,20 @@ do {								\
 }
 
 static int config_attr(struct perf_event_attr *attr,
-		       struct list_head *head, int fail)
+		       struct list_head *head,
+		       struct parse_events_error *err)
 {
 	struct parse_events_term *term;
 
 	list_for_each_entry(term, head, list)
-		if (config_term(attr, term) && fail)
+		if (config_term(attr, term, err))
 			return -EINVAL;
 
 	return 0;
 }
 
-int parse_events_add_numeric(struct list_head *list, int *idx,
+int parse_events_add_numeric(struct parse_events_evlist *data,
+			     struct list_head *list,
 			     u32 type, u64 config,
 			     struct list_head *head_config)
 {
@@ -604,10 +631,10 @@ int parse_events_add_numeric(struct list_head *list, int *idx,
 	attr.config = config;
 
 	if (head_config &&
-	    config_attr(&attr, head_config, 1))
+	    config_attr(&attr, head_config, data->error))
 		return -EINVAL;
 
-	return add_event(list, idx, &attr, NULL);
+	return add_event(list, &data->idx, &attr, NULL);
 }
 
 static int parse_events__is_name_term(struct parse_events_term *term)
@@ -626,8 +653,9 @@ static char *pmu_event_name(struct list_head *head_terms)
 	return NULL;
 }
 
-int parse_events_add_pmu(struct list_head *list, int *idx,
-			 char *name, struct list_head *head_config)
+int parse_events_add_pmu(struct parse_events_evlist *data,
+			 struct list_head *list, char *name,
+			 struct list_head *head_config)
 {
 	struct perf_event_attr attr;
 	struct perf_pmu_info info;
@@ -647,7 +675,7 @@ int parse_events_add_pmu(struct list_head *list, int *idx,
 
 	if (!head_config) {
 		attr.type = pmu->type;
-		evsel = __add_event(list, idx, &attr, NULL, pmu->cpus);
+		evsel = __add_event(list, &data->idx, &attr, NULL, pmu->cpus);
 		return evsel ? 0 : -ENOMEM;
 	}
 
@@ -658,13 +686,14 @@ int parse_events_add_pmu(struct list_head *list, int *idx,
 	 * Configure hardcoded terms first, no need to check
 	 * return value when called with fail == 0 ;)
 	 */
-	config_attr(&attr, head_config, 0);
+	if (config_attr(&attr, head_config, data->error))
+		return -EINVAL;
 
-	if (perf_pmu__config(pmu, &attr, head_config))
+	if (perf_pmu__config(pmu, &attr, head_config, data->error))
 		return -EINVAL;
 
-	evsel = __add_event(list, idx, &attr, pmu_event_name(head_config),
-			    pmu->cpus);
+	evsel = __add_event(list, &data->idx, &attr,
+			    pmu_event_name(head_config), pmu->cpus);
 	if (evsel) {
 		evsel->unit = info.unit;
 		evsel->scale = info.scale;
@@ -1019,11 +1048,13 @@ int parse_events_terms(struct list_head *terms, const char *str)
 	return ret;
 }
 
-int parse_events(struct perf_evlist *evlist, const char *str)
+int parse_events(struct perf_evlist *evlist, const char *str,
+		 struct parse_events_error *err)
 {
 	struct parse_events_evlist data = {
-		.list = LIST_HEAD_INIT(data.list),
-		.idx  = evlist->nr_entries,
+		.list  = LIST_HEAD_INIT(data.list),
+		.idx   = evlist->nr_entries,
+		.error = err,
 	};
 	int ret;
 
@@ -1044,16 +1075,87 @@ int parse_events(struct perf_evlist *evlist, const char *str)
 	return ret;
 }
 
+#define MAX_WIDTH 1000
+static int get_term_width(void)
+{
+	struct winsize ws;
+
+	get_term_dimensions(&ws);
+	return ws.ws_col > MAX_WIDTH ? MAX_WIDTH : ws.ws_col;
+}
+
+static void parse_events_print_error(struct parse_events_error *err,
+				     const char *event)
+{
+	const char *str = "invalid or unsupported event: ";
+	char _buf[MAX_WIDTH];
+	char *buf = (char *) event;
+	int idx = 0;
+
+	if (err->str) {
+		/* -2 for extra '' in the final fprintf */
+		int width       = get_term_width() - 2;
+		int len_event   = strlen(event);
+		int len_str, max_len, cut = 0;
+
+		/*
+		 * Maximum error index indent, we will cut
+		 * the event string if it's bigger.
+		 */
+		int max_err_idx = 10;
+
+		/*
+		 * Let's be specific with the message when
+		 * we have the precise error.
+		 */
+		str     = "event syntax error: ";
+		len_str = strlen(str);
+		max_len = width - len_str;
+
+		buf = _buf;
+
+		/* We're cutting from the beggining. */
+		if (err->idx > max_err_idx)
+			cut = err->idx - max_err_idx;
+
+		strncpy(buf, event + cut, max_len);
+
+		/* Mark cut parts with '..' on both sides. */
+		if (cut)
+			buf[0] = buf[1] = '.';
+
+		if ((len_event - cut) > max_len) {
+			buf[max_len - 1] = buf[max_len - 2] = '.';
+			buf[max_len] = 0;
+		}
+
+		idx = len_str + err->idx - cut;
+	}
+
+	fprintf(stderr, "%s'%s'\n", str, buf);
+	if (idx) {
+		fprintf(stderr, "%*s\\___ %s\n", idx + 1, "", err->str);
+		if (err->help)
+			fprintf(stderr, "\n%s\n", err->help);
+		free(err->str);
+		free(err->help);
+	}
+
+	fprintf(stderr, "Run 'perf list' for a list of valid events\n");
+}
+
+#undef MAX_WIDTH
+
 int parse_events_option(const struct option *opt, const char *str,
 			int unset __maybe_unused)
 {
 	struct perf_evlist *evlist = *(struct perf_evlist **)opt->value;
-	int ret = parse_events(evlist, str);
+	struct parse_events_error err = { .idx = 0, };
+	int ret = parse_events(evlist, str, &err);
+
+	if (ret)
+		parse_events_print_error(&err, str);
 
-	if (ret) {
-		fprintf(stderr, "invalid or unsupported event: '%s'\n", str);
-		fprintf(stderr, "Run 'perf list' for a list of valid events\n");
-	}
 	return ret;
 }
 
@@ -1460,7 +1562,7 @@ int parse_events__is_hardcoded_term(struct parse_events_term *term)
 
 static int new_term(struct parse_events_term **_term, int type_val,
 		    int type_term, char *config,
-		    char *str, u64 num)
+		    char *str, u64 num, int err_term, int err_val)
 {
 	struct parse_events_term *term;
 
@@ -1472,6 +1574,8 @@ static int new_term(struct parse_events_term **_term, int type_val,
 	term->type_val  = type_val;
 	term->type_term = type_term;
 	term->config = config;
+	term->err_term = err_term;
+	term->err_val  = err_val;
 
 	switch (type_val) {
 	case PARSE_EVENTS__TERM_TYPE_NUM:
@@ -1490,17 +1594,29 @@ static int new_term(struct parse_events_term **_term, int type_val,
 }
 
 int parse_events_term__num(struct parse_events_term **term,
-			   int type_term, char *config, u64 num)
+			   int type_term, char *config, u64 num,
+			   void *loc_term_, void *loc_val_)
 {
+	YYLTYPE *loc_term = loc_term_;
+	YYLTYPE *loc_val = loc_val_;
+
 	return new_term(term, PARSE_EVENTS__TERM_TYPE_NUM, type_term,
-			config, NULL, num);
+			config, NULL, num,
+			loc_term ? loc_term->first_column : 0,
+			loc_val ? loc_val->first_column : 0);
 }
 
 int parse_events_term__str(struct parse_events_term **term,
-			   int type_term, char *config, char *str)
+			   int type_term, char *config, char *str,
+			   void *loc_term_, void *loc_val_)
 {
+	YYLTYPE *loc_term = loc_term_;
+	YYLTYPE *loc_val = loc_val_;
+
 	return new_term(term, PARSE_EVENTS__TERM_TYPE_STR, type_term,
-			config, str, 0);
+			config, str, 0,
+			loc_term ? loc_term->first_column : 0,
+			loc_val ? loc_val->first_column : 0);
 }
 
 int parse_events_term__sym_hw(struct parse_events_term **term,
@@ -1514,18 +1630,20 @@ int parse_events_term__sym_hw(struct parse_events_term **term,
 	if (config)
 		return new_term(term, PARSE_EVENTS__TERM_TYPE_STR,
 				PARSE_EVENTS__TERM_TYPE_USER, config,
-				(char *) sym->symbol, 0);
+				(char *) sym->symbol, 0, 0, 0);
 	else
 		return new_term(term, PARSE_EVENTS__TERM_TYPE_STR,
 				PARSE_EVENTS__TERM_TYPE_USER,
-				(char *) "event", (char *) sym->symbol, 0);
+				(char *) "event", (char *) sym->symbol,
+				0, 0, 0);
 }
 
 int parse_events_term__clone(struct parse_events_term **new,
 			     struct parse_events_term *term)
 {
 	return new_term(new, term->type_val, term->type_term, term->config,
-			term->val.str, term->val.num);
+			term->val.str, term->val.num,
+			term->err_term, term->err_val);
 }
 
 void parse_events__free_terms(struct list_head *terms)
@@ -1535,3 +1653,15 @@ void parse_events__free_terms(struct list_head *terms)
 	list_for_each_entry_safe(term, h, terms, list)
 		free(term);
 }
+
+void parse_events_evlist_error(struct parse_events_evlist *data,
+			       int idx, const char *str)
+{
+	struct parse_events_error *err = data->error;
+
+	if (!err)
+		return;
+	err->idx = idx;
+	err->str = strdup(str);
+	WARN_ONCE(!err->str, "WARNING: failed to allocate error string");
+}
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 52a2dda4f954..131f29b2f132 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -12,6 +12,7 @@
 struct list_head;
 struct perf_evsel;
 struct perf_evlist;
+struct parse_events_error;
 
 struct option;
 
@@ -29,7 +30,8 @@ const char *event_type(int type);
 
 extern int parse_events_option(const struct option *opt, const char *str,
 			       int unset);
-extern int parse_events(struct perf_evlist *evlist, const char *str);
+extern int parse_events(struct perf_evlist *evlist, const char *str,
+			struct parse_events_error *error);
 extern int parse_events_terms(struct list_head *terms, const char *str);
 extern int parse_filter(const struct option *opt, const char *str, int unset);
 
@@ -72,12 +74,23 @@ struct parse_events_term {
 	int type_term;
 	struct list_head list;
 	bool used;
+
+	/* error string indexes for within parsed string */
+	int err_term;
+	int err_val;
+};
+
+struct parse_events_error {
+	int   idx;	/* index in the parsed string */
+	char *str;      /* string to display at the index */
+	char *help;	/* optional help string */
 };
 
 struct parse_events_evlist {
-	struct list_head list;
-	int idx;
-	int nr_groups;
+	struct list_head	   list;
+	int			   idx;
+	int			   nr_groups;
+	struct parse_events_error *error;
 };
 
 struct parse_events_terms {
@@ -85,10 +98,12 @@ struct parse_events_terms {
 };
 
 int parse_events__is_hardcoded_term(struct parse_events_term *term);
-int parse_events_term__num(struct parse_events_term **_term,
-			   int type_term, char *config, u64 num);
-int parse_events_term__str(struct parse_events_term **_term,
-			   int type_term, char *config, char *str);
+int parse_events_term__num(struct parse_events_term **term,
+			   int type_term, char *config, u64 num,
+			   void *loc_term, void *loc_val);
+int parse_events_term__str(struct parse_events_term **term,
+			   int type_term, char *config, char *str,
+			   void *loc_term, void *loc_val);
 int parse_events_term__sym_hw(struct parse_events_term **term,
 			      char *config, unsigned idx);
 int parse_events_term__clone(struct parse_events_term **new,
@@ -99,21 +114,24 @@ int parse_events__modifier_group(struct list_head *list, char *event_mod);
 int parse_events_name(struct list_head *list, char *name);
 int parse_events_add_tracepoint(struct list_head *list, int *idx,
 				char *sys, char *event);
-int parse_events_add_numeric(struct list_head *list, int *idx,
+int parse_events_add_numeric(struct parse_events_evlist *data,
+			     struct list_head *list,
 			     u32 type, u64 config,
 			     struct list_head *head_config);
 int parse_events_add_cache(struct list_head *list, int *idx,
 			   char *type, char *op_result1, char *op_result2);
 int parse_events_add_breakpoint(struct list_head *list, int *idx,
 				void *ptr, char *type, u64 len);
-int parse_events_add_pmu(struct list_head *list, int *idx,
-			 char *pmu , struct list_head *head_config);
+int parse_events_add_pmu(struct parse_events_evlist *data,
+			 struct list_head *list, char *name,
+			 struct list_head *head_config);
 enum perf_pmu_event_symbol_type
 perf_pmu__parse_check(const char *name);
 void parse_events__set_leader(char *name, struct list_head *list);
 void parse_events_update_lists(struct list_head *list_event,
 			       struct list_head *list_all);
-void parse_events_error(void *data, void *scanner, char const *msg);
+void parse_events_evlist_error(struct parse_events_evlist *data,
+			       int idx, const char *str);
 
 void print_events(const char *event_glob, bool name_only);
 
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 8895cf3132ab..09e738fe9ea2 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -3,6 +3,8 @@
 %option bison-bridge
 %option prefix="parse_events_"
 %option stack
+%option bison-locations
+%option yylineno
 
 %{
 #include <errno.h>
@@ -51,6 +53,18 @@ static int str(yyscan_t scanner, int token)
 	return token;
 }
 
+#define REWIND(__alloc)				\
+do {								\
+	YYSTYPE *__yylval = parse_events_get_lval(yyscanner);	\
+	char *text = parse_events_get_text(yyscanner);		\
+								\
+	if (__alloc)						\
+		__yylval->str = strdup(text);			\
+								\
+	yycolumn -= strlen(text);				\
+	yyless(0);						\
+} while (0)
+
 static int pmu_str_check(yyscan_t scanner)
 {
 	YYSTYPE *yylval = parse_events_get_lval(scanner);
@@ -85,6 +99,13 @@ static int term(yyscan_t scanner, int type)
 	return PE_TERM;
 }
 
+#define YY_USER_ACTION					\
+do {							\
+	yylloc->last_column  = yylloc->first_column;	\
+	yylloc->first_column = yycolumn;		\
+	yycolumn += yyleng;				\
+} while (0);
+
 %}
 
 %x mem
@@ -119,6 +140,12 @@ modifier_bp	[rwx]{1,3}
 
 		if (start_token) {
 			parse_events_set_extra(NULL, yyscanner);
+			/*
+			 * The flex parser does not init locations variable
+			 * via the scan_string interface, so we need do the
+			 * init in here.
+			 */
+			yycolumn = 0;
 			return start_token;
 		}
          }
@@ -127,24 +154,30 @@ modifier_bp	[rwx]{1,3}
 <event>{
 
 {group}		{
-			BEGIN(INITIAL); yyless(0);
+			BEGIN(INITIAL);
+			REWIND(0);
 		}
 
 {event_pmu}	|
 {event}		{
-			str(yyscanner, PE_EVENT_NAME);
-			BEGIN(INITIAL); yyless(0);
+			BEGIN(INITIAL);
+			REWIND(1);
 			return PE_EVENT_NAME;
 		}
 
 .		|
 <<EOF>>		{
-			BEGIN(INITIAL); yyless(0);
+			BEGIN(INITIAL);
+			REWIND(0);
 		}
 
 }
 
 <config>{
+	/*
+	 * Please update formats_error_string any time
+	 * new static term is added.
+	 */
 config			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG); }
 config1			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG1); }
 config2			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG2); }
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 72def077dbbf..591905a02b92 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -2,6 +2,7 @@
 %parse-param {void *_data}
 %parse-param {void *scanner}
 %lex-param {void* scanner}
+%locations
 
 %{
 
@@ -14,8 +15,6 @@
 #include "parse-events.h"
 #include "parse-events-bison.h"
 
-extern int parse_events_lex (YYSTYPE* lvalp, void* scanner);
-
 #define ABORT_ON(val) \
 do { \
 	if (val) \
@@ -208,7 +207,7 @@ PE_NAME '/' event_config '/'
 	struct list_head *list;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_pmu(list, &data->idx, $1, $3));
+	ABORT_ON(parse_events_add_pmu(data, list, $1, $3));
 	parse_events__free_terms($3);
 	$$ = list;
 }
@@ -219,7 +218,7 @@ PE_NAME '/' '/'
 	struct list_head *list;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_pmu(list, &data->idx, $1, NULL));
+	ABORT_ON(parse_events_add_pmu(data, list, $1, NULL));
 	$$ = list;
 }
 |
@@ -232,11 +231,11 @@ PE_KERNEL_PMU_EVENT sep_dc
 
 	ALLOC_LIST(head);
 	ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
-					$1, 1));
+					$1, 1, &@1, NULL));
 	list_add_tail(&term->list, head);
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_pmu(list, &data->idx, "cpu", head));
+	ABORT_ON(parse_events_add_pmu(data, list, "cpu", head));
 	parse_events__free_terms(head);
 	$$ = list;
 }
@@ -252,7 +251,7 @@ PE_PMU_EVENT_PRE '-' PE_PMU_EVENT_SUF sep_dc
 
 	ALLOC_LIST(head);
 	ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
-					&pmu_name, 1));
+					&pmu_name, 1, &@1, NULL));
 	list_add_tail(&term->list, head);
 
 	ALLOC_LIST(list);
@@ -275,8 +274,7 @@ value_sym '/' event_config '/'
 	int config = $1 & 255;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_numeric(list, &data->idx,
-					  type, config, $3));
+	ABORT_ON(parse_events_add_numeric(data, list, type, config, $3));
 	parse_events__free_terms($3);
 	$$ = list;
 }
@@ -289,8 +287,7 @@ value_sym sep_slash_dc
 	int config = $1 & 255;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_numeric(list, &data->idx,
-					  type, config, NULL));
+	ABORT_ON(parse_events_add_numeric(data, list, type, config, NULL));
 	$$ = list;
 }
 
@@ -389,7 +386,15 @@ PE_NAME ':' PE_NAME
 	struct list_head *list;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_tracepoint(list, &data->idx, $1, $3));
+	if (parse_events_add_tracepoint(list, &data->idx, $1, $3)) {
+		struct parse_events_error *error = data->error;
+
+		if (error) {
+			error->idx = @1.first_column;
+			error->str = strdup("unknown tracepoint");
+		}
+		return -1;
+	}
 	$$ = list;
 }
 
@@ -400,7 +405,7 @@ PE_VALUE ':' PE_VALUE
 	struct list_head *list;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_numeric(list, &data->idx, (u32)$1, $3, NULL));
+	ABORT_ON(parse_events_add_numeric(data, list, (u32)$1, $3, NULL));
 	$$ = list;
 }
 
@@ -411,8 +416,7 @@ PE_RAW
 	struct list_head *list;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_numeric(list, &data->idx,
-					  PERF_TYPE_RAW, $1, NULL));
+	ABORT_ON(parse_events_add_numeric(data, list, PERF_TYPE_RAW, $1, NULL));
 	$$ = list;
 }
 
@@ -450,7 +454,7 @@ PE_NAME '=' PE_NAME
 	struct parse_events_term *term;
 
 	ABORT_ON(parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER,
-					$1, $3));
+					$1, $3, &@1, &@3));
 	$$ = term;
 }
 |
@@ -459,7 +463,7 @@ PE_NAME '=' PE_VALUE
 	struct parse_events_term *term;
 
 	ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
-					$1, $3));
+					$1, $3, &@1, &@3));
 	$$ = term;
 }
 |
@@ -477,7 +481,7 @@ PE_NAME
 	struct parse_events_term *term;
 
 	ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
-					$1, 1));
+					$1, 1, &@1, NULL));
 	$$ = term;
 }
 |
@@ -494,7 +498,7 @@ PE_TERM '=' PE_NAME
 {
 	struct parse_events_term *term;
 
-	ABORT_ON(parse_events_term__str(&term, (int)$1, NULL, $3));
+	ABORT_ON(parse_events_term__str(&term, (int)$1, NULL, $3, &@1, &@3));
 	$$ = term;
 }
 |
@@ -502,7 +506,7 @@ PE_TERM '=' PE_VALUE
 {
 	struct parse_events_term *term;
 
-	ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, $3));
+	ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, $3, &@1, &@3));
 	$$ = term;
 }
 |
@@ -510,7 +514,7 @@ PE_TERM
 {
 	struct parse_events_term *term;
 
-	ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, 1));
+	ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, 1, &@1, NULL));
 	$$ = term;
 }
 
@@ -520,7 +524,9 @@ sep_slash_dc: '/' | ':' |
 
 %%
 
-void parse_events_error(void *data __maybe_unused, void *scanner __maybe_unused,
+void parse_events_error(YYLTYPE *loc, void *data,
+			void *scanner __maybe_unused,
 			char const *msg __maybe_unused)
 {
+	parse_events_evlist_error(data, loc->last_column, "parser error");
 }
diff --git a/tools/perf/util/parse-options.h b/tools/perf/util/parse-options.h
index 59561fd86278..367d8b816cc7 100644
--- a/tools/perf/util/parse-options.h
+++ b/tools/perf/util/parse-options.h
@@ -123,6 +123,10 @@ struct option {
 #define OPT_LONG(s, l, v, h)        { .type = OPTION_LONG, .short_name = (s), .long_name = (l), .value = check_vtype(v, long *), .help = (h) }
 #define OPT_U64(s, l, v, h)         { .type = OPTION_U64, .short_name = (s), .long_name = (l), .value = check_vtype(v, u64 *), .help = (h) }
 #define OPT_STRING(s, l, v, a, h)   { .type = OPTION_STRING,  .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), (a), .help = (h) }
+#define OPT_STRING_OPTARG(s, l, v, a, h, d) \
+	{ .type = OPTION_STRING,  .short_name = (s), .long_name = (l), \
+	  .value = check_vtype(v, const char **), (a), .help = (h), \
+	  .flags = PARSE_OPT_OPTARG, .defval = (intptr_t)(d) }
 #define OPT_STRING_NOEMPTY(s, l, v, a, h)   { .type = OPTION_STRING,  .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), (a), .help = (h), .flags = PARSE_OPT_NOEMPTY}
 #define OPT_DATE(s, l, v, h) \
 	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = "time", .help = (h), .callback = parse_opt_approxidate_cb }
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 48411674da0f..0fcc624eb767 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -112,7 +112,11 @@ static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char *
 	if (sret < 0)
 		goto error;
 
-	scale[sret] = '\0';
+	if (scale[sret - 1] == '\n')
+		scale[sret - 1] = '\0';
+	else
+		scale[sret] = '\0';
+
 	/*
 	 * save current locale
 	 */
@@ -154,7 +158,10 @@ static int perf_pmu__parse_unit(struct perf_pmu_alias *alias, char *dir, char *n
 
 	close(fd);
 
-	alias->unit[sret] = '\0';
+	if (alias->unit[sret - 1] == '\n')
+		alias->unit[sret - 1] = '\0';
+	else
+		alias->unit[sret] = '\0';
 
 	return 0;
 error:
@@ -442,6 +449,10 @@ static struct perf_pmu *pmu_lookup(const char *name)
 	LIST_HEAD(aliases);
 	__u32 type;
 
+	/* No support for intel_bts or intel_pt so disallow them */
+	if (!strcmp(name, "intel_bts") || !strcmp(name, "intel_pt"))
+		return NULL;
+
 	/*
 	 * The pmu data we store & need consists of the pmu
 	 * type value and format definitions. Load both right
@@ -579,6 +590,38 @@ static int pmu_resolve_param_term(struct parse_events_term *term,
 	return -1;
 }
 
+static char *formats_error_string(struct list_head *formats)
+{
+	struct perf_pmu_format *format;
+	char *err, *str;
+	static const char *static_terms = "config,config1,config2,name,period,branch_type\n";
+	unsigned i = 0;
+
+	if (!asprintf(&str, "valid terms:"))
+		return NULL;
+
+	/* sysfs exported terms */
+	list_for_each_entry(format, formats, list) {
+		char c = i++ ? ',' : ' ';
+
+		err = str;
+		if (!asprintf(&str, "%s%c%s", err, c, format->name))
+			goto fail;
+		free(err);
+	}
+
+	/* static terms */
+	err = str;
+	if (!asprintf(&str, "%s,%s", err, static_terms))
+		goto fail;
+
+	free(err);
+	return str;
+fail:
+	free(err);
+	return NULL;
+}
+
 /*
  * Setup one of config[12] attr members based on the
  * user input data - term parameter.
@@ -587,7 +630,7 @@ static int pmu_config_term(struct list_head *formats,
 			   struct perf_event_attr *attr,
 			   struct parse_events_term *term,
 			   struct list_head *head_terms,
-			   bool zero)
+			   bool zero, struct parse_events_error *err)
 {
 	struct perf_pmu_format *format;
 	__u64 *vp;
@@ -611,6 +654,11 @@ static int pmu_config_term(struct list_head *formats,
 	if (!format) {
 		if (verbose)
 			printf("Invalid event/parameter '%s'\n", term->config);
+		if (err) {
+			err->idx  = term->err_term;
+			err->str  = strdup("unknown term");
+			err->help = formats_error_string(formats);
+		}
 		return -EINVAL;
 	}
 
@@ -636,9 +684,14 @@ static int pmu_config_term(struct list_head *formats,
 		val = term->val.num;
 	else if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR) {
 		if (strcmp(term->val.str, "?")) {
-			if (verbose)
+			if (verbose) {
 				pr_info("Invalid sysfs entry %s=%s\n",
 						term->config, term->val.str);
+			}
+			if (err) {
+				err->idx = term->err_val;
+				err->str = strdup("expected numeric value");
+			}
 			return -EINVAL;
 		}
 
@@ -654,12 +707,13 @@ static int pmu_config_term(struct list_head *formats,
 int perf_pmu__config_terms(struct list_head *formats,
 			   struct perf_event_attr *attr,
 			   struct list_head *head_terms,
-			   bool zero)
+			   bool zero, struct parse_events_error *err)
 {
 	struct parse_events_term *term;
 
 	list_for_each_entry(term, head_terms, list) {
-		if (pmu_config_term(formats, attr, term, head_terms, zero))
+		if (pmu_config_term(formats, attr, term, head_terms,
+				    zero, err))
 			return -EINVAL;
 	}
 
@@ -672,12 +726,14 @@ int perf_pmu__config_terms(struct list_head *formats,
  * 2) pmu format definitions - specified by pmu parameter
  */
 int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
-		     struct list_head *head_terms)
+		     struct list_head *head_terms,
+		     struct parse_events_error *err)
 {
 	bool zero = !!pmu->default_config;
 
 	attr->type = pmu->type;
-	return perf_pmu__config_terms(&pmu->format, attr, head_terms, zero);
+	return perf_pmu__config_terms(&pmu->format, attr, head_terms,
+				      zero, err);
 }
 
 static struct perf_pmu_alias *pmu_find_alias(struct perf_pmu *pmu,
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 6b1249fbdb5f..7b9c8cf8ae3e 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -4,6 +4,7 @@
 #include <linux/bitmap.h>
 #include <linux/perf_event.h>
 #include <stdbool.h>
+#include "parse-events.h"
 
 enum {
 	PERF_PMU_FORMAT_VALUE_CONFIG,
@@ -47,11 +48,12 @@ struct perf_pmu_alias {
 
 struct perf_pmu *perf_pmu__find(const char *name);
 int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
-		     struct list_head *head_terms);
+		     struct list_head *head_terms,
+		     struct parse_events_error *error);
 int perf_pmu__config_terms(struct list_head *formats,
 			   struct perf_event_attr *attr,
 			   struct list_head *head_terms,
-			   bool zero);
+			   bool zero, struct parse_events_error *error);
 int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
 			  struct perf_pmu_info *info);
 struct list_head *perf_pmu__alias(struct perf_pmu *pmu,
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index d05b77cf35f7..076527b639bd 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -51,6 +51,7 @@
 #define PERFPROBE_GROUP "probe"
 
 bool probe_event_dry_run;	/* Dry run flag */
+struct probe_conf probe_conf;
 
 #define semantic_error(msg ...) pr_err("Semantic error :" msg)
 
@@ -161,18 +162,18 @@ static u64 kernel_get_symbol_address_by_name(const char *name, bool reloc)
 
 static struct map *kernel_get_module_map(const char *module)
 {
-	struct rb_node *nd;
 	struct map_groups *grp = &host_machine->kmaps;
+	struct maps *maps = &grp->maps[MAP__FUNCTION];
+	struct map *pos;
 
 	/* A file path -- this is an offline module */
 	if (module && strchr(module, '/'))
-		return machine__new_module(host_machine, 0, module);
+		return machine__findnew_module_map(host_machine, 0, module);
 
 	if (!module)
 		module = "kernel";
 
-	for (nd = rb_first(&grp->maps[MAP__FUNCTION]); nd; nd = rb_next(nd)) {
-		struct map *pos = rb_entry(nd, struct map, rb_node);
+	for (pos = maps__first(maps); pos; pos = map__next(pos)) {
 		if (strncmp(pos->dso->short_name + 1, module,
 			    pos->dso->short_name_len - 2) == 0) {
 			return pos;
@@ -194,52 +195,11 @@ static void put_target_map(struct map *map, bool user)
 {
 	if (map && user) {
 		/* Only the user map needs to be released */
-		dso__delete(map->dso);
-		map__delete(map);
+		map__put(map);
 	}
 }
 
 
-static struct dso *kernel_get_module_dso(const char *module)
-{
-	struct dso *dso;
-	struct map *map;
-	const char *vmlinux_name;
-
-	if (module) {
-		list_for_each_entry(dso, &host_machine->kernel_dsos.head,
-				    node) {
-			if (strncmp(dso->short_name + 1, module,
-				    dso->short_name_len - 2) == 0)
-				goto found;
-		}
-		pr_debug("Failed to find module %s.\n", module);
-		return NULL;
-	}
-
-	map = host_machine->vmlinux_maps[MAP__FUNCTION];
-	dso = map->dso;
-
-	vmlinux_name = symbol_conf.vmlinux_name;
-	if (vmlinux_name) {
-		if (dso__load_vmlinux(dso, map, vmlinux_name, false, NULL) <= 0)
-			return NULL;
-	} else {
-		if (dso__load_vmlinux_path(dso, map, NULL) <= 0) {
-			pr_debug("Failed to load kernel map.\n");
-			return NULL;
-		}
-	}
-found:
-	return dso;
-}
-
-const char *kernel_get_module_path(const char *module)
-{
-	struct dso *dso = kernel_get_module_dso(module);
-	return (dso) ? dso->long_name : NULL;
-}
-
 static int convert_exec_to_group(const char *exec, char **result)
 {
 	char *ptr1, *ptr2, *exec_copy;
@@ -286,7 +246,55 @@ static void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs)
 		clear_probe_trace_event(tevs + i);
 }
 
+static bool kprobe_blacklist__listed(unsigned long address);
+static bool kprobe_warn_out_range(const char *symbol, unsigned long address)
+{
+	/* Get the address of _etext for checking non-probable text symbol */
+	if (kernel_get_symbol_address_by_name("_etext", false) < address)
+		pr_warning("%s is out of .text, skip it.\n", symbol);
+	else if (kprobe_blacklist__listed(address))
+		pr_warning("%s is blacklisted function, skip it.\n", symbol);
+	else
+		return false;
+
+	return true;
+}
+
 #ifdef HAVE_DWARF_SUPPORT
+
+static int kernel_get_module_dso(const char *module, struct dso **pdso)
+{
+	struct dso *dso;
+	struct map *map;
+	const char *vmlinux_name;
+	int ret = 0;
+
+	if (module) {
+		list_for_each_entry(dso, &host_machine->dsos.head, node) {
+			if (!dso->kernel)
+				continue;
+			if (strncmp(dso->short_name + 1, module,
+				    dso->short_name_len - 2) == 0)
+				goto found;
+		}
+		pr_debug("Failed to find module %s.\n", module);
+		return -ENOENT;
+	}
+
+	map = host_machine->vmlinux_maps[MAP__FUNCTION];
+	dso = map->dso;
+
+	vmlinux_name = symbol_conf.vmlinux_name;
+	dso->load_errno = 0;
+	if (vmlinux_name)
+		ret = dso__load_vmlinux(dso, map, vmlinux_name, false, NULL);
+	else
+		ret = dso__load_vmlinux_path(dso, map, NULL);
+found:
+	*pdso = dso;
+	return ret;
+}
+
 /*
  * Some binaries like glibc have special symbols which are on the symbol
  * table, but not in the debuginfo. If we can find the address of the
@@ -344,15 +352,14 @@ out:
 
 static int get_alternative_probe_event(struct debuginfo *dinfo,
 				       struct perf_probe_event *pev,
-				       struct perf_probe_point *tmp,
-				       const char *target)
+				       struct perf_probe_point *tmp)
 {
 	int ret;
 
 	memcpy(tmp, &pev->point, sizeof(*tmp));
 	memset(&pev->point, 0, sizeof(pev->point));
 	ret = find_alternative_probe_point(dinfo, tmp, &pev->point,
-					   target, pev->uprobes);
+					   pev->target, pev->uprobes);
 	if (ret < 0)
 		memcpy(&pev->point, tmp, sizeof(*tmp));
 
@@ -390,16 +397,25 @@ static int get_alternative_line_range(struct debuginfo *dinfo,
 static struct debuginfo *open_debuginfo(const char *module, bool silent)
 {
 	const char *path = module;
-	struct debuginfo *ret;
+	char reason[STRERR_BUFSIZE];
+	struct debuginfo *ret = NULL;
+	struct dso *dso = NULL;
+	int err;
 
 	if (!module || !strchr(module, '/')) {
-		path = kernel_get_module_path(module);
-		if (!path) {
+		err = kernel_get_module_dso(module, &dso);
+		if (err < 0) {
+			if (!dso || dso->load_errno == 0) {
+				if (!strerror_r(-err, reason, STRERR_BUFSIZE))
+					strcpy(reason, "(unknown)");
+			} else
+				dso__strerror_load(dso, reason, STRERR_BUFSIZE);
 			if (!silent)
-				pr_err("Failed to find path of %s module.\n",
-				       module ?: "kernel");
+				pr_err("Failed to find the path for %s: %s\n",
+					module ?: "kernel", reason);
 			return NULL;
 		}
+		path = dso->long_name;
 	}
 	ret = debuginfo__new(path);
 	if (!ret && !silent) {
@@ -413,6 +429,41 @@ static struct debuginfo *open_debuginfo(const char *module, bool silent)
 	return ret;
 }
 
+/* For caching the last debuginfo */
+static struct debuginfo *debuginfo_cache;
+static char *debuginfo_cache_path;
+
+static struct debuginfo *debuginfo_cache__open(const char *module, bool silent)
+{
+	if ((debuginfo_cache_path && !strcmp(debuginfo_cache_path, module)) ||
+	    (!debuginfo_cache_path && !module && debuginfo_cache))
+		goto out;
+
+	/* Copy module path */
+	free(debuginfo_cache_path);
+	if (module) {
+		debuginfo_cache_path = strdup(module);
+		if (!debuginfo_cache_path) {
+			debuginfo__delete(debuginfo_cache);
+			debuginfo_cache = NULL;
+			goto out;
+		}
+	}
+
+	debuginfo_cache = open_debuginfo(module, silent);
+	if (!debuginfo_cache)
+		zfree(&debuginfo_cache_path);
+out:
+	return debuginfo_cache;
+}
+
+static void debuginfo_cache__exit(void)
+{
+	debuginfo__delete(debuginfo_cache);
+	debuginfo_cache = NULL;
+	zfree(&debuginfo_cache_path);
+}
+
 
 static int get_text_start_address(const char *exec, unsigned long *address)
 {
@@ -474,12 +525,11 @@ static int find_perf_probe_point_from_dwarf(struct probe_trace_point *tp,
 	pr_debug("try to find information at %" PRIx64 " in %s\n", addr,
 		 tp->module ? : "kernel");
 
-	dinfo = open_debuginfo(tp->module, verbose == 0);
-	if (dinfo) {
+	dinfo = debuginfo_cache__open(tp->module, verbose == 0);
+	if (dinfo)
 		ret = debuginfo__find_probe_point(dinfo,
 						 (unsigned long)addr, pp);
-		debuginfo__delete(dinfo);
-	} else
+	else
 		ret = -ENOENT;
 
 	if (ret > 0) {
@@ -558,7 +608,7 @@ static int post_process_probe_trace_events(struct probe_trace_event *tevs,
 {
 	struct ref_reloc_sym *reloc_sym;
 	char *tmp;
-	int i;
+	int i, skipped = 0;
 
 	if (uprobe)
 		return add_exec_to_probe_trace_events(tevs, ntevs, module);
@@ -574,31 +624,40 @@ static int post_process_probe_trace_events(struct probe_trace_event *tevs,
 	}
 
 	for (i = 0; i < ntevs; i++) {
-		if (tevs[i].point.address && !tevs[i].point.retprobe) {
+		if (!tevs[i].point.address || tevs[i].point.retprobe)
+			continue;
+		/* If we found a wrong one, mark it by NULL symbol */
+		if (kprobe_warn_out_range(tevs[i].point.symbol,
+					  tevs[i].point.address)) {
+			tmp = NULL;
+			skipped++;
+		} else {
 			tmp = strdup(reloc_sym->name);
 			if (!tmp)
 				return -ENOMEM;
-			free(tevs[i].point.symbol);
-			tevs[i].point.symbol = tmp;
-			tevs[i].point.offset = tevs[i].point.address -
-					       reloc_sym->unrelocated_addr;
 		}
+		/* If we have no realname, use symbol for it */
+		if (!tevs[i].point.realname)
+			tevs[i].point.realname = tevs[i].point.symbol;
+		else
+			free(tevs[i].point.symbol);
+		tevs[i].point.symbol = tmp;
+		tevs[i].point.offset = tevs[i].point.address -
+				       reloc_sym->unrelocated_addr;
 	}
-	return 0;
+	return skipped;
 }
 
 /* Try to find perf_probe_event with debuginfo */
 static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
-					  struct probe_trace_event **tevs,
-					  int max_tevs, const char *target)
+					  struct probe_trace_event **tevs)
 {
 	bool need_dwarf = perf_probe_event_need_dwarf(pev);
 	struct perf_probe_point tmp;
 	struct debuginfo *dinfo;
 	int ntevs, ret = 0;
 
-	dinfo = open_debuginfo(target, !need_dwarf);
-
+	dinfo = open_debuginfo(pev->target, !need_dwarf);
 	if (!dinfo) {
 		if (need_dwarf)
 			return -ENOENT;
@@ -608,13 +667,12 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
 
 	pr_debug("Try to find probe point from debuginfo.\n");
 	/* Searching trace events corresponding to a probe event */
-	ntevs = debuginfo__find_trace_events(dinfo, pev, tevs, max_tevs);
+	ntevs = debuginfo__find_trace_events(dinfo, pev, tevs);
 
 	if (ntevs == 0)	{  /* Not found, retry with an alternative */
-		ret = get_alternative_probe_event(dinfo, pev, &tmp, target);
+		ret = get_alternative_probe_event(dinfo, pev, &tmp);
 		if (!ret) {
-			ntevs = debuginfo__find_trace_events(dinfo, pev,
-							     tevs, max_tevs);
+			ntevs = debuginfo__find_trace_events(dinfo, pev, tevs);
 			/*
 			 * Write back to the original probe_event for
 			 * setting appropriate (user given) event name
@@ -629,12 +687,15 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
 	if (ntevs > 0) {	/* Succeeded to find trace events */
 		pr_debug("Found %d probe_trace_events.\n", ntevs);
 		ret = post_process_probe_trace_events(*tevs, ntevs,
-							target, pev->uprobes);
-		if (ret < 0) {
+						pev->target, pev->uprobes);
+		if (ret < 0 || ret == ntevs) {
 			clear_probe_trace_events(*tevs, ntevs);
 			zfree(tevs);
 		}
-		return ret < 0 ? ret : ntevs;
+		if (ret != ntevs)
+			return ret < 0 ? ret : ntevs;
+		ntevs = 0;
+		/* Fall through */
 	}
 
 	if (ntevs == 0)	{	/* No error but failed to find probe point. */
@@ -809,8 +870,7 @@ int show_line_range(struct line_range *lr, const char *module, bool user)
 
 static int show_available_vars_at(struct debuginfo *dinfo,
 				  struct perf_probe_event *pev,
-				  int max_vls, struct strfilter *_filter,
-				  bool externs, const char *target)
+				  struct strfilter *_filter)
 {
 	char *buf;
 	int ret, i, nvars;
@@ -824,13 +884,12 @@ static int show_available_vars_at(struct debuginfo *dinfo,
 		return -EINVAL;
 	pr_debug("Searching variables at %s\n", buf);
 
-	ret = debuginfo__find_available_vars_at(dinfo, pev, &vls,
-						max_vls, externs);
+	ret = debuginfo__find_available_vars_at(dinfo, pev, &vls);
 	if (!ret) {  /* Not found, retry with an alternative */
-		ret = get_alternative_probe_event(dinfo, pev, &tmp, target);
+		ret = get_alternative_probe_event(dinfo, pev, &tmp);
 		if (!ret) {
 			ret = debuginfo__find_available_vars_at(dinfo, pev,
-						&vls, max_vls, externs);
+								&vls);
 			/* Release the old probe_point */
 			clear_perf_probe_point(&tmp);
 		}
@@ -877,8 +936,7 @@ end:
 
 /* Show available variables on given probe point */
 int show_available_vars(struct perf_probe_event *pevs, int npevs,
-			int max_vls, const char *module,
-			struct strfilter *_filter, bool externs)
+			struct strfilter *_filter)
 {
 	int i, ret = 0;
 	struct debuginfo *dinfo;
@@ -887,7 +945,7 @@ int show_available_vars(struct perf_probe_event *pevs, int npevs,
 	if (ret < 0)
 		return ret;
 
-	dinfo = open_debuginfo(module, false);
+	dinfo = open_debuginfo(pevs->target, false);
 	if (!dinfo) {
 		ret = -ENOENT;
 		goto out;
@@ -896,8 +954,7 @@ int show_available_vars(struct perf_probe_event *pevs, int npevs,
 	setup_pager();
 
 	for (i = 0; i < npevs && ret >= 0; i++)
-		ret = show_available_vars_at(dinfo, &pevs[i], max_vls, _filter,
-					     externs, module);
+		ret = show_available_vars_at(dinfo, &pevs[i], _filter);
 
 	debuginfo__delete(dinfo);
 out:
@@ -907,6 +964,10 @@ out:
 
 #else	/* !HAVE_DWARF_SUPPORT */
 
+static void debuginfo_cache__exit(void)
+{
+}
+
 static int
 find_perf_probe_point_from_dwarf(struct probe_trace_point *tp __maybe_unused,
 				 struct perf_probe_point *pp __maybe_unused,
@@ -916,9 +977,7 @@ find_perf_probe_point_from_dwarf(struct probe_trace_point *tp __maybe_unused,
 }
 
 static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
-				struct probe_trace_event **tevs __maybe_unused,
-				int max_tevs __maybe_unused,
-				const char *target __maybe_unused)
+				struct probe_trace_event **tevs __maybe_unused)
 {
 	if (perf_probe_event_need_dwarf(pev)) {
 		pr_warning("Debuginfo-analysis is not supported.\n");
@@ -937,10 +996,8 @@ int show_line_range(struct line_range *lr __maybe_unused,
 }
 
 int show_available_vars(struct perf_probe_event *pevs __maybe_unused,
-			int npevs __maybe_unused, int max_vls __maybe_unused,
-			const char *module __maybe_unused,
-			struct strfilter *filter __maybe_unused,
-			bool externs __maybe_unused)
+			int npevs __maybe_unused,
+			struct strfilter *filter __maybe_unused)
 {
 	pr_warning("Debuginfo-analysis is not supported.\n");
 	return -ENOSYS;
@@ -980,6 +1037,18 @@ static int parse_line_num(char **ptr, int *val, const char *what)
 	return 0;
 }
 
+/* Check the name is good for event, group or function */
+static bool is_c_func_name(const char *name)
+{
+	if (!isalpha(*name) && *name != '_')
+		return false;
+	while (*++name != '\0') {
+		if (!isalpha(*name) && !isdigit(*name) && *name != '_')
+			return false;
+	}
+	return true;
+}
+
 /*
  * Stuff 'lr' according to the line range described by 'arg'.
  * The line range syntax is described by:
@@ -1048,10 +1117,15 @@ int parse_line_range_desc(const char *arg, struct line_range *lr)
 			goto err;
 		}
 		lr->function = name;
-	} else if (strchr(name, '.'))
+	} else if (strchr(name, '/') || strchr(name, '.'))
 		lr->file = name;
-	else
+	else if (is_c_func_name(name))/* We reuse it for checking funcname */
 		lr->function = name;
+	else {	/* Invalid name */
+		semantic_error("'%s' is not a valid function name.\n", name);
+		err = -EINVAL;
+		goto err;
+	}
 
 	return 0;
 err:
@@ -1059,24 +1133,13 @@ err:
 	return err;
 }
 
-/* Check the name is good for event/group */
-static bool check_event_name(const char *name)
-{
-	if (!isalpha(*name) && *name != '_')
-		return false;
-	while (*++name != '\0') {
-		if (!isalpha(*name) && !isdigit(*name) && *name != '_')
-			return false;
-	}
-	return true;
-}
-
 /* Parse probepoint definition. */
 static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
 {
 	struct perf_probe_point *pp = &pev->point;
 	char *ptr, *tmp;
 	char c, nc = 0;
+	bool file_spec = false;
 	/*
 	 * <Syntax>
 	 * perf probe [EVENT=]SRC[:LN|;PTN]
@@ -1095,7 +1158,7 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
 			semantic_error("Group name is not supported yet.\n");
 			return -ENOTSUP;
 		}
-		if (!check_event_name(arg)) {
+		if (!is_c_func_name(arg)) {
 			semantic_error("%s is bad for event name -it must "
 				       "follow C symbol-naming rule.\n", arg);
 			return -EINVAL;
@@ -1107,6 +1170,23 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
 		arg = tmp;
 	}
 
+	/*
+	 * Check arg is function or file name and copy it.
+	 *
+	 * We consider arg to be a file spec if and only if it satisfies
+	 * all of the below criteria::
+	 * - it does not include any of "+@%",
+	 * - it includes one of ":;", and
+	 * - it has a period '.' in the name.
+	 *
+	 * Otherwise, we consider arg to be a function specification.
+	 */
+	if (!strpbrk(arg, "+@%") && (ptr = strpbrk(arg, ";:")) != NULL) {
+		/* This is a file spec if it includes a '.' before ; or : */
+		if (memchr(arg, '.', ptr - arg))
+			file_spec = true;
+	}
+
 	ptr = strpbrk(arg, ";:+@%");
 	if (ptr) {
 		nc = *ptr;
@@ -1117,10 +1197,9 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
 	if (tmp == NULL)
 		return -ENOMEM;
 
-	/* Check arg is function or file and copy it */
-	if (strchr(tmp, '.'))	/* File */
+	if (file_spec)
 		pp->file = tmp;
-	else			/* Function */
+	else
 		pp->function = tmp;
 
 	/* Parse other options */
@@ -1762,8 +1841,7 @@ static int find_perf_probe_point_from_map(struct probe_trace_point *tp,
 
 out:
 	if (map && !is_kprobe) {
-		dso__delete(map->dso);
-		map__delete(map);
+		map__put(map);
 	}
 
 	return ret;
@@ -1877,6 +1955,7 @@ static void clear_probe_trace_event(struct probe_trace_event *tev)
 	free(tev->event);
 	free(tev->group);
 	free(tev->point.symbol);
+	free(tev->point.realname);
 	free(tev->point.module);
 	for (i = 0; i < tev->nargs; i++) {
 		free(tev->args[i].name);
@@ -1954,7 +2033,7 @@ static int open_probe_events(const char *trace_file, bool readwrite)
 	if (ret >= 0) {
 		pr_debug("Opening %s write=%d\n", buf, readwrite);
 		if (readwrite && !probe_event_dry_run)
-			ret = open(buf, O_RDWR, O_APPEND);
+			ret = open(buf, O_RDWR | O_APPEND, 0);
 		else
 			ret = open(buf, O_RDONLY, 0);
 
@@ -2095,9 +2174,31 @@ kprobe_blacklist__find_by_address(struct list_head *blacklist,
 	return NULL;
 }
 
-/* Show an event */
-static int show_perf_probe_event(struct perf_probe_event *pev,
-				 const char *module)
+static LIST_HEAD(kprobe_blacklist);
+
+static void kprobe_blacklist__init(void)
+{
+	if (!list_empty(&kprobe_blacklist))
+		return;
+
+	if (kprobe_blacklist__load(&kprobe_blacklist) < 0)
+		pr_debug("No kprobe blacklist support, ignored\n");
+}
+
+static void kprobe_blacklist__release(void)
+{
+	kprobe_blacklist__delete(&kprobe_blacklist);
+}
+
+static bool kprobe_blacklist__listed(unsigned long address)
+{
+	return !!kprobe_blacklist__find_by_address(&kprobe_blacklist, address);
+}
+
+static int perf_probe_event__sprintf(const char *group, const char *event,
+				     struct perf_probe_event *pev,
+				     const char *module,
+				     struct strbuf *result)
 {
 	int i, ret;
 	char buf[128];
@@ -2108,30 +2209,67 @@ static int show_perf_probe_event(struct perf_probe_event *pev,
 	if (!place)
 		return -EINVAL;
 
-	ret = e_snprintf(buf, 128, "%s:%s", pev->group, pev->event);
+	ret = e_snprintf(buf, 128, "%s:%s", group, event);
 	if (ret < 0)
-		return ret;
+		goto out;
 
-	pr_info("  %-20s (on %s", buf, place);
+	strbuf_addf(result, "  %-20s (on %s", buf, place);
 	if (module)
-		pr_info(" in %s", module);
+		strbuf_addf(result, " in %s", module);
 
 	if (pev->nargs > 0) {
-		pr_info(" with");
+		strbuf_addstr(result, " with");
 		for (i = 0; i < pev->nargs; i++) {
 			ret = synthesize_perf_probe_arg(&pev->args[i],
 							buf, 128);
 			if (ret < 0)
-				break;
-			pr_info(" %s", buf);
+				goto out;
+			strbuf_addf(result, " %s", buf);
 		}
 	}
-	pr_info(")\n");
+	strbuf_addch(result, ')');
+out:
 	free(place);
 	return ret;
 }
 
-static int __show_perf_probe_events(int fd, bool is_kprobe)
+/* Show an event */
+static int show_perf_probe_event(const char *group, const char *event,
+				 struct perf_probe_event *pev,
+				 const char *module, bool use_stdout)
+{
+	struct strbuf buf = STRBUF_INIT;
+	int ret;
+
+	ret = perf_probe_event__sprintf(group, event, pev, module, &buf);
+	if (ret >= 0) {
+		if (use_stdout)
+			printf("%s\n", buf.buf);
+		else
+			pr_info("%s\n", buf.buf);
+	}
+	strbuf_release(&buf);
+
+	return ret;
+}
+
+static bool filter_probe_trace_event(struct probe_trace_event *tev,
+				     struct strfilter *filter)
+{
+	char tmp[128];
+
+	/* At first, check the event name itself */
+	if (strfilter__compare(filter, tev->event))
+		return true;
+
+	/* Next, check the combination of name and group */
+	if (e_snprintf(tmp, 128, "%s:%s", tev->group, tev->event) < 0)
+		return false;
+	return strfilter__compare(filter, tmp);
+}
+
+static int __show_perf_probe_events(int fd, bool is_kprobe,
+				    struct strfilter *filter)
 {
 	int ret = 0;
 	struct probe_trace_event tev;
@@ -2149,24 +2287,31 @@ static int __show_perf_probe_events(int fd, bool is_kprobe)
 	strlist__for_each(ent, rawlist) {
 		ret = parse_probe_trace_command(ent->s, &tev);
 		if (ret >= 0) {
+			if (!filter_probe_trace_event(&tev, filter))
+				goto next;
 			ret = convert_to_perf_probe_event(&tev, &pev,
 								is_kprobe);
-			if (ret >= 0)
-				ret = show_perf_probe_event(&pev,
-							    tev.point.module);
+			if (ret < 0)
+				goto next;
+			ret = show_perf_probe_event(pev.group, pev.event,
+						    &pev, tev.point.module,
+						    true);
 		}
+next:
 		clear_perf_probe_event(&pev);
 		clear_probe_trace_event(&tev);
 		if (ret < 0)
 			break;
 	}
 	strlist__delete(rawlist);
+	/* Cleanup cached debuginfo if needed */
+	debuginfo_cache__exit();
 
 	return ret;
 }
 
 /* List up current perf-probe events */
-int show_perf_probe_events(void)
+int show_perf_probe_events(struct strfilter *filter)
 {
 	int kp_fd, up_fd, ret;
 
@@ -2178,7 +2323,7 @@ int show_perf_probe_events(void)
 
 	kp_fd = open_kprobe_events(false);
 	if (kp_fd >= 0) {
-		ret = __show_perf_probe_events(kp_fd, true);
+		ret = __show_perf_probe_events(kp_fd, true, filter);
 		close(kp_fd);
 		if (ret < 0)
 			goto out;
@@ -2192,7 +2337,7 @@ int show_perf_probe_events(void)
 	}
 
 	if (up_fd >= 0) {
-		ret = __show_perf_probe_events(up_fd, false);
+		ret = __show_perf_probe_events(up_fd, false, filter);
 		close(up_fd);
 	}
 out:
@@ -2266,6 +2411,10 @@ static int get_new_event_name(char *buf, size_t len, const char *base,
 			      struct strlist *namelist, bool allow_suffix)
 {
 	int i, ret;
+	char *p;
+
+	if (*base == '.')
+		base++;
 
 	/* Try no suffix */
 	ret = e_snprintf(buf, len, "%s", base);
@@ -2273,6 +2422,10 @@ static int get_new_event_name(char *buf, size_t len, const char *base,
 		pr_debug("snprintf() failed: %d\n", ret);
 		return ret;
 	}
+	/* Cut off the postfixes (e.g. .const, .isra)*/
+	p = strchr(buf, '.');
+	if (p && p != buf)
+		*p = '\0';
 	if (!strlist__has_entry(namelist, buf))
 		return 0;
 
@@ -2328,10 +2481,9 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
 	int i, fd, ret;
 	struct probe_trace_event *tev = NULL;
 	char buf[64];
-	const char *event, *group;
+	const char *event = NULL, *group = NULL;
 	struct strlist *namelist;
-	LIST_HEAD(blacklist);
-	struct kprobe_blacklist_node *node;
+	bool safename;
 
 	if (pev->uprobes)
 		fd = open_uprobe_events(true);
@@ -2347,34 +2499,26 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
 	namelist = get_probe_trace_event_names(fd, false);
 	if (!namelist) {
 		pr_debug("Failed to get current event list.\n");
-		return -EIO;
-	}
-	/* Get kprobe blacklist if exists */
-	if (!pev->uprobes) {
-		ret = kprobe_blacklist__load(&blacklist);
-		if (ret < 0)
-			pr_debug("No kprobe blacklist support, ignored\n");
+		ret = -ENOMEM;
+		goto close_out;
 	}
 
+	safename = (pev->point.function && !strisglob(pev->point.function));
 	ret = 0;
 	pr_info("Added new event%s\n", (ntevs > 1) ? "s:" : ":");
 	for (i = 0; i < ntevs; i++) {
 		tev = &tevs[i];
-		/* Ensure that the address is NOT blacklisted */
-		node = kprobe_blacklist__find_by_address(&blacklist,
-							 tev->point.address);
-		if (node) {
-			pr_warning("Warning: Skipped probing on blacklisted function: %s\n", node->symbol);
+		/* Skip if the symbol is out of .text or blacklisted */
+		if (!tev->point.symbol)
 			continue;
-		}
 
 		if (pev->event)
 			event = pev->event;
 		else
-			if (pev->point.function)
+			if (safename)
 				event = pev->point.function;
 			else
-				event = tev->point.symbol;
+				event = tev->point.realname;
 		if (pev->group)
 			group = pev->group;
 		else
@@ -2399,15 +2543,12 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
 		/* Add added event name to namelist */
 		strlist__add(namelist, event);
 
-		/* Trick here - save current event/group */
-		event = pev->event;
-		group = pev->group;
-		pev->event = tev->event;
-		pev->group = tev->group;
-		show_perf_probe_event(pev, tev->point.module);
-		/* Trick here - restore current event/group */
-		pev->event = (char *)event;
-		pev->group = (char *)group;
+		/* We use tev's name for showing new events */
+		show_perf_probe_event(tev->group, tev->event, pev,
+				      tev->point.module, false);
+		/* Save the last valid name */
+		event = tev->event;
+		group = tev->group;
 
 		/*
 		 * Probes after the first probe which comes from same
@@ -2421,26 +2562,34 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
 		warn_uprobe_event_compat(tev);
 
 	/* Note that it is possible to skip all events because of blacklist */
-	if (ret >= 0 && tev->event) {
+	if (ret >= 0 && event) {
 		/* Show how to use the event. */
 		pr_info("\nYou can now use it in all perf tools, such as:\n\n");
-		pr_info("\tperf record -e %s:%s -aR sleep 1\n\n", tev->group,
-			 tev->event);
+		pr_info("\tperf record -e %s:%s -aR sleep 1\n\n", group, event);
 	}
 
-	kprobe_blacklist__delete(&blacklist);
 	strlist__delete(namelist);
+close_out:
 	close(fd);
 	return ret;
 }
 
-static int find_probe_functions(struct map *map, char *name)
+static int find_probe_functions(struct map *map, char *name,
+				struct symbol **syms)
 {
 	int found = 0;
 	struct symbol *sym;
+	struct rb_node *tmp;
+
+	if (map__load(map, NULL) < 0)
+		return 0;
 
-	map__for_each_symbol_by_name(map, name, sym) {
-		found++;
+	map__for_each_symbol(map, sym, tmp) {
+		if (strglobmatch(sym->name, name)) {
+			found++;
+			if (syms && found < probe_conf.max_probes)
+				syms[found - 1] = sym;
+		}
 	}
 
 	return found;
@@ -2449,42 +2598,52 @@ static int find_probe_functions(struct map *map, char *name)
 #define strdup_or_goto(str, label)	\
 	({ char *__p = strdup(str); if (!__p) goto label; __p; })
 
+void __weak arch__fix_tev_from_maps(struct perf_probe_event *pev __maybe_unused,
+				struct probe_trace_event *tev __maybe_unused,
+				struct map *map __maybe_unused) { }
+
 /*
  * Find probe function addresses from map.
  * Return an error or the number of found probe_trace_event
  */
 static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
-					    struct probe_trace_event **tevs,
-					    int max_tevs, const char *target)
+					    struct probe_trace_event **tevs)
 {
 	struct map *map = NULL;
 	struct ref_reloc_sym *reloc_sym = NULL;
 	struct symbol *sym;
+	struct symbol **syms = NULL;
 	struct probe_trace_event *tev;
 	struct perf_probe_point *pp = &pev->point;
 	struct probe_trace_point *tp;
 	int num_matched_functions;
-	int ret, i;
+	int ret, i, j, skipped = 0;
 
-	map = get_target_map(target, pev->uprobes);
+	map = get_target_map(pev->target, pev->uprobes);
 	if (!map) {
 		ret = -EINVAL;
 		goto out;
 	}
 
+	syms = malloc(sizeof(struct symbol *) * probe_conf.max_probes);
+	if (!syms) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
 	/*
 	 * Load matched symbols: Since the different local symbols may have
 	 * same name but different addresses, this lists all the symbols.
 	 */
-	num_matched_functions = find_probe_functions(map, pp->function);
+	num_matched_functions = find_probe_functions(map, pp->function, syms);
 	if (num_matched_functions == 0) {
 		pr_err("Failed to find symbol %s in %s\n", pp->function,
-			target ? : "kernel");
+			pev->target ? : "kernel");
 		ret = -ENOENT;
 		goto out;
-	} else if (num_matched_functions > max_tevs) {
+	} else if (num_matched_functions > probe_conf.max_probes) {
 		pr_err("Too many functions matched in %s\n",
-			target ? : "kernel");
+			pev->target ? : "kernel");
 		ret = -E2BIG;
 		goto out;
 	}
@@ -2507,7 +2666,9 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
 
 	ret = 0;
 
-	map__for_each_symbol_by_name(map, pp->function, sym) {
+	for (j = 0; j < num_matched_functions; j++) {
+		sym = syms[j];
+
 		tev = (*tevs) + ret;
 		tp = &tev->point;
 		if (ret == num_matched_functions) {
@@ -2524,16 +2685,24 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
 		}
 		/* Add one probe point */
 		tp->address = map->unmap_ip(map, sym->start) + pp->offset;
-		if (reloc_sym) {
+		/* If we found a wrong one, mark it by NULL symbol */
+		if (!pev->uprobes &&
+		    kprobe_warn_out_range(sym->name, tp->address)) {
+			tp->symbol = NULL;	/* Skip it */
+			skipped++;
+		} else if (reloc_sym) {
 			tp->symbol = strdup_or_goto(reloc_sym->name, nomem_out);
 			tp->offset = tp->address - reloc_sym->addr;
 		} else {
 			tp->symbol = strdup_or_goto(sym->name, nomem_out);
 			tp->offset = pp->offset;
 		}
+		tp->realname = strdup_or_goto(sym->name, nomem_out);
+
 		tp->retprobe = pp->retprobe;
-		if (target)
-			tev->point.module = strdup_or_goto(target, nomem_out);
+		if (pev->target)
+			tev->point.module = strdup_or_goto(pev->target,
+							   nomem_out);
 		tev->uprobes = pev->uprobes;
 		tev->nargs = pev->nargs;
 		if (tev->nargs) {
@@ -2555,10 +2724,16 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
 					strdup_or_goto(pev->args[i].type,
 							nomem_out);
 		}
+		arch__fix_tev_from_maps(pev, tev, map);
+	}
+	if (ret == skipped) {
+		ret = -ENOENT;
+		goto err_out;
 	}
 
 out:
 	put_target_map(map, pev->uprobes);
+	free(syms);
 	return ret;
 
 nomem_out:
@@ -2569,27 +2744,34 @@ err_out:
 	goto out;
 }
 
+bool __weak arch__prefers_symtab(void) { return false; }
+
 static int convert_to_probe_trace_events(struct perf_probe_event *pev,
-					  struct probe_trace_event **tevs,
-					  int max_tevs, const char *target)
+					 struct probe_trace_event **tevs)
 {
 	int ret;
 
 	if (pev->uprobes && !pev->group) {
 		/* Replace group name if not given */
-		ret = convert_exec_to_group(target, &pev->group);
+		ret = convert_exec_to_group(pev->target, &pev->group);
 		if (ret != 0) {
 			pr_warning("Failed to make a group name.\n");
 			return ret;
 		}
 	}
 
+	if (arch__prefers_symtab() && !perf_probe_event_need_dwarf(pev)) {
+		ret = find_probe_trace_events_from_map(pev, tevs);
+		if (ret > 0)
+			return ret; /* Found in symbol table */
+	}
+
 	/* Convert perf_probe_event with debuginfo */
-	ret = try_to_find_probe_trace_events(pev, tevs, max_tevs, target);
+	ret = try_to_find_probe_trace_events(pev, tevs);
 	if (ret != 0)
 		return ret;	/* Found in debuginfo or got an error */
 
-	return find_probe_trace_events_from_map(pev, tevs, max_tevs, target);
+	return find_probe_trace_events_from_map(pev, tevs);
 }
 
 struct __event_package {
@@ -2598,8 +2780,7 @@ struct __event_package {
 	int				ntevs;
 };
 
-int add_perf_probe_events(struct perf_probe_event *pevs, int npevs,
-			  int max_tevs, bool force_add)
+int add_perf_probe_events(struct perf_probe_event *pevs, int npevs)
 {
 	int i, j, ret;
 	struct __event_package *pkgs;
@@ -2619,20 +2800,24 @@ int add_perf_probe_events(struct perf_probe_event *pevs, int npevs,
 	/* Loop 1: convert all events */
 	for (i = 0; i < npevs; i++) {
 		pkgs[i].pev = &pevs[i];
+		/* Init kprobe blacklist if needed */
+		if (!pkgs[i].pev->uprobes)
+			kprobe_blacklist__init();
 		/* Convert with or without debuginfo */
 		ret  = convert_to_probe_trace_events(pkgs[i].pev,
-						     &pkgs[i].tevs,
-						     max_tevs,
-						     pkgs[i].pev->target);
+						     &pkgs[i].tevs);
 		if (ret < 0)
 			goto end;
 		pkgs[i].ntevs = ret;
 	}
+	/* This just release blacklist only if allocated */
+	kprobe_blacklist__release();
 
 	/* Loop 2: add all events */
 	for (i = 0; i < npevs; i++) {
 		ret = __add_probe_trace_events(pkgs[i].pev, pkgs[i].tevs,
-						pkgs[i].ntevs, force_add);
+					       pkgs[i].ntevs,
+					       probe_conf.force_add);
 		if (ret < 0)
 			break;
 	}
@@ -2684,40 +2869,39 @@ error:
 	return ret;
 }
 
-static int del_trace_probe_event(int fd, const char *buf,
-						  struct strlist *namelist)
+static int del_trace_probe_events(int fd, struct strfilter *filter,
+				  struct strlist *namelist)
 {
-	struct str_node *ent, *n;
-	int ret = -1;
+	struct str_node *ent;
+	const char *p;
+	int ret = -ENOENT;
 
-	if (strpbrk(buf, "*?")) { /* Glob-exp */
-		strlist__for_each_safe(ent, n, namelist)
-			if (strglobmatch(ent->s, buf)) {
-				ret = __del_trace_probe_event(fd, ent);
-				if (ret < 0)
-					break;
-				strlist__remove(namelist, ent);
-			}
-	} else {
-		ent = strlist__find(namelist, buf);
-		if (ent) {
+	if (!namelist)
+		return -ENOENT;
+
+	strlist__for_each(ent, namelist) {
+		p = strchr(ent->s, ':');
+		if ((p && strfilter__compare(filter, p + 1)) ||
+		    strfilter__compare(filter, ent->s)) {
 			ret = __del_trace_probe_event(fd, ent);
-			if (ret >= 0)
-				strlist__remove(namelist, ent);
+			if (ret < 0)
+				break;
 		}
 	}
 
 	return ret;
 }
 
-int del_perf_probe_events(struct strlist *dellist)
+int del_perf_probe_events(struct strfilter *filter)
 {
-	int ret = -1, ufd = -1, kfd = -1;
-	char buf[128];
-	const char *group, *event;
-	char *p, *str;
-	struct str_node *ent;
+	int ret, ret2, ufd = -1, kfd = -1;
 	struct strlist *namelist = NULL, *unamelist = NULL;
+	char *str = strfilter__string(filter);
+
+	if (!str)
+		return -EINVAL;
+
+	pr_debug("Delete filter: \'%s\'\n", str);
 
 	/* Get current event names */
 	kfd = open_kprobe_events(true);
@@ -2730,49 +2914,23 @@ int del_perf_probe_events(struct strlist *dellist)
 
 	if (kfd < 0 && ufd < 0) {
 		print_both_open_warning(kfd, ufd);
+		ret = kfd;
 		goto error;
 	}
 
-	if (namelist == NULL && unamelist == NULL)
+	ret = del_trace_probe_events(kfd, filter, namelist);
+	if (ret < 0 && ret != -ENOENT)
 		goto error;
 
-	strlist__for_each(ent, dellist) {
-		str = strdup(ent->s);
-		if (str == NULL) {
-			ret = -ENOMEM;
-			goto error;
-		}
-		pr_debug("Parsing: %s\n", str);
-		p = strchr(str, ':');
-		if (p) {
-			group = str;
-			*p = '\0';
-			event = p + 1;
-		} else {
-			group = "*";
-			event = str;
-		}
-
-		ret = e_snprintf(buf, 128, "%s:%s", group, event);
-		if (ret < 0) {
-			pr_err("Failed to copy event.");
-			free(str);
-			goto error;
-		}
-
-		pr_debug("Group: %s, Event: %s\n", group, event);
-
-		if (namelist)
-			ret = del_trace_probe_event(kfd, buf, namelist);
-
-		if (unamelist && ret != 0)
-			ret = del_trace_probe_event(ufd, buf, unamelist);
-
-		if (ret != 0)
-			pr_info("Info: Event \"%s\" does not exist.\n", buf);
-
-		free(str);
+	ret2 = del_trace_probe_events(ufd, filter, unamelist);
+	if (ret2 < 0 && ret2 != -ENOENT) {
+		ret = ret2;
+		goto error;
 	}
+	if (ret == -ENOENT && ret2 == -ENOENT)
+		pr_debug("\"%s\" does not hit any event.\n", str);
+		/* Note that this is silently ignored */
+	ret = 0;
 
 error:
 	if (kfd >= 0) {
@@ -2784,6 +2942,7 @@ error:
 		strlist__delete(unamelist);
 		close(ufd);
 	}
+	free(str);
 
 	return ret;
 }
@@ -2837,8 +2996,7 @@ int show_available_funcs(const char *target, struct strfilter *_filter,
 	dso__fprintf_symbols_by_name(map->dso, map->type, stdout);
 end:
 	if (user) {
-		dso__delete(map->dso);
-		map__delete(map);
+		map__put(map);
 	}
 	exit_symbol_maps();
 
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index d6b783447be9..31db6ee7db54 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -6,10 +6,20 @@
 #include "strlist.h"
 #include "strfilter.h"
 
+/* Probe related configurations */
+struct probe_conf {
+	bool	show_ext_vars;
+	bool	show_location_range;
+	bool	force_add;
+	bool	no_inlines;
+	int	max_probes;
+};
+extern struct probe_conf probe_conf;
 extern bool probe_event_dry_run;
 
 /* kprobe-tracer and uprobe-tracer tracing point */
 struct probe_trace_point {
+	char		*realname;	/* function real name (if needed) */
 	char		*symbol;	/* Base symbol */
 	char		*module;	/* Module name */
 	unsigned long	offset;		/* Offset from symbol */
@@ -121,20 +131,18 @@ extern void line_range__clear(struct line_range *lr);
 /* Initialize line range */
 extern int line_range__init(struct line_range *lr);
 
-/* Internal use: Return kernel/module path */
-extern const char *kernel_get_module_path(const char *module);
-
-extern int add_perf_probe_events(struct perf_probe_event *pevs, int npevs,
-				 int max_probe_points, bool force_add);
-extern int del_perf_probe_events(struct strlist *dellist);
-extern int show_perf_probe_events(void);
+extern int add_perf_probe_events(struct perf_probe_event *pevs, int npevs);
+extern int del_perf_probe_events(struct strfilter *filter);
+extern int show_perf_probe_events(struct strfilter *filter);
 extern int show_line_range(struct line_range *lr, const char *module,
 			   bool user);
 extern int show_available_vars(struct perf_probe_event *pevs, int npevs,
-			       int max_probe_points, const char *module,
-			       struct strfilter *filter, bool externs);
+			       struct strfilter *filter);
 extern int show_available_funcs(const char *module, struct strfilter *filter,
 				bool user);
+bool arch__prefers_symtab(void);
+void arch__fix_tev_from_maps(struct perf_probe_event *pev,
+			     struct probe_trace_event *tev, struct map *map);
 
 /* Maximum index number of event-name postfix */
 #define MAX_EVENT_INDEX	1024
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 2a76e14db732..2da65a710893 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -130,7 +130,7 @@ struct debuginfo *debuginfo__new(const char *path)
 			continue;
 		dinfo = __debuginfo__new(buf);
 	}
-	dso__delete(dso);
+	dso__put(dso);
 
 out:
 	/* if failed to open all distro debuginfo, open given binary */
@@ -177,7 +177,7 @@ static int convert_variable_location(Dwarf_Die *vr_die, Dwarf_Addr addr,
 	Dwarf_Word offs = 0;
 	bool ref = false;
 	const char *regs;
-	int ret;
+	int ret, ret2 = 0;
 
 	if (dwarf_attr(vr_die, DW_AT_external, &attr) != NULL)
 		goto static_var;
@@ -187,9 +187,19 @@ static int convert_variable_location(Dwarf_Die *vr_die, Dwarf_Addr addr,
 		return -EINVAL;	/* Broken DIE ? */
 	if (dwarf_getlocation_addr(&attr, addr, &op, &nops, 1) <= 0) {
 		ret = dwarf_entrypc(sp_die, &tmp);
-		if (ret || addr != tmp ||
-		    dwarf_tag(vr_die) != DW_TAG_formal_parameter ||
-		    dwarf_highpc(sp_die, &tmp))
+		if (ret)
+			return -ENOENT;
+
+		if (probe_conf.show_location_range &&
+			(dwarf_tag(vr_die) == DW_TAG_variable)) {
+			ret2 = -ERANGE;
+		} else if (addr != tmp ||
+			dwarf_tag(vr_die) != DW_TAG_formal_parameter) {
+			return -ENOENT;
+		}
+
+		ret = dwarf_highpc(sp_die, &tmp);
+		if (ret)
 			return -ENOENT;
 		/*
 		 * This is fuzzed by fentry mcount. We try to find the
@@ -210,7 +220,7 @@ found:
 	if (op->atom == DW_OP_addr) {
 static_var:
 		if (!tvar)
-			return 0;
+			return ret2;
 		/* Static variables on memory (not stack), make @varname */
 		ret = strlen(dwarf_diename(vr_die));
 		tvar->value = zalloc(ret + 2);
@@ -220,7 +230,7 @@ static_var:
 		tvar->ref = alloc_trace_arg_ref((long)offs);
 		if (tvar->ref == NULL)
 			return -ENOMEM;
-		return 0;
+		return ret2;
 	}
 
 	/* If this is based on frame buffer, set the offset */
@@ -250,14 +260,14 @@ static_var:
 	}
 
 	if (!tvar)
-		return 0;
+		return ret2;
 
 	regs = get_arch_regstr(regn);
 	if (!regs) {
 		/* This should be a bug in DWARF or this tool */
 		pr_warning("Mapping for the register number %u "
 			   "missing on this architecture.\n", regn);
-		return -ERANGE;
+		return -ENOTSUP;
 	}
 
 	tvar->value = strdup(regs);
@@ -269,7 +279,7 @@ static_var:
 		if (tvar->ref == NULL)
 			return -ENOMEM;
 	}
-	return 0;
+	return ret2;
 }
 
 #define BYTES_TO_BITS(nb)	((nb) * BITS_PER_LONG / sizeof(long))
@@ -517,10 +527,12 @@ static int convert_variable(Dwarf_Die *vr_die, struct probe_finder *pf)
 
 	ret = convert_variable_location(vr_die, pf->addr, pf->fb_ops,
 					&pf->sp_die, pf->tvar);
-	if (ret == -ENOENT || ret == -EINVAL)
-		pr_err("Failed to find the location of %s at this address.\n"
-		       " Perhaps, it has been optimized out.\n", pf->pvar->var);
-	else if (ret == -ENOTSUP)
+	if (ret == -ENOENT || ret == -EINVAL) {
+		pr_err("Failed to find the location of the '%s' variable at this address.\n"
+		       " Perhaps it has been optimized out.\n"
+		       " Use -V with the --range option to show '%s' location range.\n",
+		       pf->pvar->var, pf->pvar->var);
+	} else if (ret == -ENOTSUP)
 		pr_err("Sorry, we don't support this variable location yet.\n");
 	else if (ret == 0 && pf->pvar->field) {
 		ret = convert_variable_fields(vr_die, pf->pvar->var,
@@ -662,9 +674,15 @@ static int call_probe_finder(Dwarf_Die *sc_die, struct probe_finder *pf)
 	/* If not a real subprogram, find a real one */
 	if (!die_is_func_def(sc_die)) {
 		if (!die_find_realfunc(&pf->cu_die, pf->addr, &pf->sp_die)) {
-			pr_warning("Failed to find probe point in any "
-				   "functions.\n");
-			return -ENOENT;
+			if (die_find_tailfunc(&pf->cu_die, pf->addr, &pf->sp_die)) {
+				pr_warning("Ignoring tail call from %s\n",
+						dwarf_diename(&pf->sp_die));
+				return 0;
+			} else {
+				pr_warning("Failed to find probe point in any "
+					   "functions.\n");
+				return -ENOENT;
+			}
 		}
 	} else
 		memcpy(&pf->sp_die, sc_die, sizeof(Dwarf_Die));
@@ -719,7 +737,7 @@ static int find_best_scope_cb(Dwarf_Die *fn_die, void *data)
 	}
 	/* If the function name is given, that's what user expects */
 	if (fsp->function) {
-		if (die_compare_name(fn_die, fsp->function)) {
+		if (die_match_name(fn_die, fsp->function)) {
 			memcpy(fsp->die_mem, fn_die, sizeof(Dwarf_Die));
 			fsp->found = true;
 			return 1;
@@ -922,13 +940,14 @@ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data)
 
 	/* Check tag and diename */
 	if (!die_is_func_def(sp_die) ||
-	    !die_compare_name(sp_die, pp->function))
+	    !die_match_name(sp_die, pp->function))
 		return DWARF_CB_OK;
 
 	/* Check declared file */
 	if (pp->file && strtailcmp(pp->file, dwarf_decl_file(sp_die)))
 		return DWARF_CB_OK;
 
+	pr_debug("Matched function: %s\n", dwarf_diename(sp_die));
 	pf->fname = dwarf_decl_file(sp_die);
 	if (pp->line) { /* Function relative line */
 		dwarf_decl_line(sp_die, &pf->lno);
@@ -945,10 +964,20 @@ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data)
 			/* TODO: Check the address in this function */
 			param->retval = call_probe_finder(sp_die, pf);
 		}
-	} else
+	} else if (!probe_conf.no_inlines) {
 		/* Inlined function: search instances */
 		param->retval = die_walk_instances(sp_die,
 					probe_point_inline_cb, (void *)pf);
+		/* This could be a non-existed inline definition */
+		if (param->retval == -ENOENT && strisglob(pp->function))
+			param->retval = 0;
+	}
+
+	/* We need to find other candidates */
+	if (strisglob(pp->function) && param->retval >= 0) {
+		param->retval = 0;	/* We have to clear the result */
+		return DWARF_CB_OK;
+	}
 
 	return DWARF_CB_ABORT; /* Exit; no same symbol in this CU. */
 }
@@ -977,7 +1006,7 @@ static int pubname_search_cb(Dwarf *dbg, Dwarf_Global *gl, void *data)
 		if (dwarf_tag(param->sp_die) != DW_TAG_subprogram)
 			return DWARF_CB_OK;
 
-		if (die_compare_name(param->sp_die, param->function)) {
+		if (die_match_name(param->sp_die, param->function)) {
 			if (!dwarf_offdie(dbg, gl->cu_offset, param->cu_die))
 				return DWARF_CB_OK;
 
@@ -1030,7 +1059,7 @@ static int debuginfo__find_probes(struct debuginfo *dbg,
 		return -ENOMEM;
 
 	/* Fastpath: lookup by function name from .debug_pubnames section */
-	if (pp->function) {
+	if (pp->function && !strisglob(pp->function)) {
 		struct pubname_callback_param pubname_param = {
 			.function = pp->function,
 			.file	  = pp->file,
@@ -1089,6 +1118,7 @@ found:
 struct local_vars_finder {
 	struct probe_finder *pf;
 	struct perf_probe_arg *args;
+	bool vars;
 	int max_args;
 	int nargs;
 	int ret;
@@ -1103,7 +1133,7 @@ static int copy_variables_cb(Dwarf_Die *die_mem, void *data)
 
 	tag = dwarf_tag(die_mem);
 	if (tag == DW_TAG_formal_parameter ||
-	    tag == DW_TAG_variable) {
+	    (tag == DW_TAG_variable && vf->vars)) {
 		if (convert_variable_location(die_mem, vf->pf->addr,
 					      vf->pf->fb_ops, &pf->sp_die,
 					      NULL) == 0) {
@@ -1129,26 +1159,28 @@ static int expand_probe_args(Dwarf_Die *sc_die, struct probe_finder *pf,
 	Dwarf_Die die_mem;
 	int i;
 	int n = 0;
-	struct local_vars_finder vf = {.pf = pf, .args = args,
+	struct local_vars_finder vf = {.pf = pf, .args = args, .vars = false,
 				.max_args = MAX_PROBE_ARGS, .ret = 0};
 
 	for (i = 0; i < pf->pev->nargs; i++) {
 		/* var never be NULL */
-		if (strcmp(pf->pev->args[i].var, "$vars") == 0) {
-			pr_debug("Expanding $vars into:");
-			vf.nargs = n;
-			/* Special local variables */
-			die_find_child(sc_die, copy_variables_cb, (void *)&vf,
-				       &die_mem);
-			pr_debug(" (%d)\n", vf.nargs - n);
-			if (vf.ret < 0)
-				return vf.ret;
-			n = vf.nargs;
-		} else {
+		if (strcmp(pf->pev->args[i].var, PROBE_ARG_VARS) == 0)
+			vf.vars = true;
+		else if (strcmp(pf->pev->args[i].var, PROBE_ARG_PARAMS) != 0) {
 			/* Copy normal argument */
 			args[n] = pf->pev->args[i];
 			n++;
+			continue;
 		}
+		pr_debug("Expanding %s into:", pf->pev->args[i].var);
+		vf.nargs = n;
+		/* Special local variables */
+		die_find_child(sc_die, copy_variables_cb, (void *)&vf,
+			       &die_mem);
+		pr_debug(" (%d)\n", vf.nargs - n);
+		if (vf.ret < 0)
+			return vf.ret;
+		n = vf.nargs;
 	}
 	return n;
 }
@@ -1176,6 +1208,10 @@ static int add_probe_trace_event(Dwarf_Die *sc_die, struct probe_finder *pf)
 	if (ret < 0)
 		return ret;
 
+	tev->point.realname = strdup(dwarf_diename(sc_die));
+	if (!tev->point.realname)
+		return -ENOMEM;
+
 	pr_debug("Probe point found: %s+%lu\n", tev->point.symbol,
 		 tev->point.offset);
 
@@ -1213,15 +1249,15 @@ end:
 /* Find probe_trace_events specified by perf_probe_event from debuginfo */
 int debuginfo__find_trace_events(struct debuginfo *dbg,
 				 struct perf_probe_event *pev,
-				 struct probe_trace_event **tevs, int max_tevs)
+				 struct probe_trace_event **tevs)
 {
 	struct trace_event_finder tf = {
 			.pf = {.pev = pev, .callback = add_probe_trace_event},
-			.mod = dbg->mod, .max_tevs = max_tevs};
+			.max_tevs = probe_conf.max_probes, .mod = dbg->mod};
 	int ret;
 
 	/* Allocate result tevs array */
-	*tevs = zalloc(sizeof(struct probe_trace_event) * max_tevs);
+	*tevs = zalloc(sizeof(struct probe_trace_event) * tf.max_tevs);
 	if (*tevs == NULL)
 		return -ENOMEM;
 
@@ -1237,14 +1273,11 @@ int debuginfo__find_trace_events(struct debuginfo *dbg,
 	return (ret < 0) ? ret : tf.ntevs;
 }
 
-#define MAX_VAR_LEN 64
-
 /* Collect available variables in this scope */
 static int collect_variables_cb(Dwarf_Die *die_mem, void *data)
 {
 	struct available_var_finder *af = data;
 	struct variable_list *vl;
-	char buf[MAX_VAR_LEN];
 	int tag, ret;
 
 	vl = &af->vls[af->nvls - 1];
@@ -1255,11 +1288,38 @@ static int collect_variables_cb(Dwarf_Die *die_mem, void *data)
 		ret = convert_variable_location(die_mem, af->pf.addr,
 						af->pf.fb_ops, &af->pf.sp_die,
 						NULL);
-		if (ret == 0) {
-			ret = die_get_varname(die_mem, buf, MAX_VAR_LEN);
-			pr_debug2("Add new var: %s\n", buf);
-			if (ret > 0)
-				strlist__add(vl->vars, buf);
+		if (ret == 0 || ret == -ERANGE) {
+			int ret2;
+			bool externs = !af->child;
+			struct strbuf buf;
+
+			strbuf_init(&buf, 64);
+
+			if (probe_conf.show_location_range) {
+				if (!externs) {
+					if (ret)
+						strbuf_addf(&buf, "[INV]\t");
+					else
+						strbuf_addf(&buf, "[VAL]\t");
+				} else
+					strbuf_addf(&buf, "[EXT]\t");
+			}
+
+			ret2 = die_get_varname(die_mem, &buf);
+
+			if (!ret2 && probe_conf.show_location_range &&
+				!externs) {
+				strbuf_addf(&buf, "\t");
+				ret2 = die_get_var_range(&af->pf.sp_die,
+							die_mem, &buf);
+			}
+
+			pr_debug("Add new var: %s\n", buf.buf);
+			if (ret2 == 0) {
+				strlist__add(vl->vars,
+					strbuf_detach(&buf, NULL));
+			}
+			strbuf_release(&buf);
 		}
 	}
 
@@ -1302,9 +1362,9 @@ static int add_available_vars(Dwarf_Die *sc_die, struct probe_finder *pf)
 	die_find_child(sc_die, collect_variables_cb, (void *)af, &die_mem);
 
 	/* Find external variables */
-	if (!af->externs)
+	if (!probe_conf.show_ext_vars)
 		goto out;
-	/* Don't need to search child DIE for externs. */
+	/* Don't need to search child DIE for external vars. */
 	af->child = false;
 	die_find_child(&pf->cu_die, collect_variables_cb, (void *)af, &die_mem);
 
@@ -1324,17 +1384,16 @@ out:
  */
 int debuginfo__find_available_vars_at(struct debuginfo *dbg,
 				      struct perf_probe_event *pev,
-				      struct variable_list **vls,
-				      int max_vls, bool externs)
+				      struct variable_list **vls)
 {
 	struct available_var_finder af = {
 			.pf = {.pev = pev, .callback = add_available_vars},
 			.mod = dbg->mod,
-			.max_vls = max_vls, .externs = externs};
+			.max_vls = probe_conf.max_probes};
 	int ret;
 
 	/* Allocate result vls array */
-	*vls = zalloc(sizeof(struct variable_list) * max_vls);
+	*vls = zalloc(sizeof(struct variable_list) * af.max_vls);
 	if (*vls == NULL)
 		return -ENOMEM;
 
@@ -1535,7 +1594,7 @@ static int line_range_search_cb(Dwarf_Die *sp_die, void *data)
 		return DWARF_CB_OK;
 
 	if (die_is_func_def(sp_die) &&
-	    die_compare_name(sp_die, lr->function)) {
+	    die_match_name(sp_die, lr->function)) {
 		lf->fname = dwarf_decl_file(sp_die);
 		dwarf_decl_line(sp_die, &lr->offset);
 		pr_debug("fname: %s, lineno:%d\n", lf->fname, lr->offset);
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index ebf8c8c81453..bed82716e1b4 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -10,6 +10,9 @@
 #define MAX_PROBES		 128
 #define MAX_PROBE_ARGS		 128
 
+#define PROBE_ARG_VARS		"$vars"
+#define PROBE_ARG_PARAMS	"$params"
+
 static inline int is_c_varname(const char *name)
 {
 	/* TODO */
@@ -37,8 +40,7 @@ extern void debuginfo__delete(struct debuginfo *dbg);
 /* Find probe_trace_events specified by perf_probe_event from debuginfo */
 extern int debuginfo__find_trace_events(struct debuginfo *dbg,
 					struct perf_probe_event *pev,
-					struct probe_trace_event **tevs,
-					int max_tevs);
+					struct probe_trace_event **tevs);
 
 /* Find a perf_probe_point from debuginfo */
 extern int debuginfo__find_probe_point(struct debuginfo *dbg,
@@ -52,8 +54,7 @@ extern int debuginfo__find_line_range(struct debuginfo *dbg,
 /* Find available variables */
 extern int debuginfo__find_available_vars_at(struct debuginfo *dbg,
 					     struct perf_probe_event *pev,
-					     struct variable_list **vls,
-					     int max_points, bool externs);
+					     struct variable_list **vls);
 
 /* Find a src file from a DWARF tag path */
 int get_real_path(const char *raw_path, const char *comp_dir,
@@ -96,7 +97,6 @@ struct available_var_finder {
 	struct variable_list	*vls;		/* Found variable lists */
 	int			nvls;		/* Number of variable lists */
 	int			max_vls;	/* Max no. of variable lists */
-	bool			externs;	/* Find external vars too */
 	bool			child;		/* Search child scopes */
 };
 
diff --git a/tools/perf/util/pstack.c b/tools/perf/util/pstack.c
index a126e6cc6e73..b234a6e3d0d4 100644
--- a/tools/perf/util/pstack.c
+++ b/tools/perf/util/pstack.c
@@ -74,3 +74,10 @@ void *pstack__pop(struct pstack *pstack)
 	pstack->entries[pstack->top] = NULL;
 	return ret;
 }
+
+void *pstack__peek(struct pstack *pstack)
+{
+	if (pstack->top == 0)
+		return NULL;
+	return pstack->entries[pstack->top - 1];
+}
diff --git a/tools/perf/util/pstack.h b/tools/perf/util/pstack.h
index c3cb6584d527..ded7f2e36624 100644
--- a/tools/perf/util/pstack.h
+++ b/tools/perf/util/pstack.h
@@ -10,5 +10,6 @@ bool pstack__empty(const struct pstack *pstack);
 void pstack__remove(struct pstack *pstack, void *key);
 void pstack__push(struct pstack *pstack, void *key);
 void *pstack__pop(struct pstack *pstack);
+void *pstack__peek(struct pstack *pstack);
 
 #endif /* _PERF_PSTACK_ */
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index 4d28624a1eca..5925fec90562 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -16,6 +16,7 @@ util/util.c
 util/xyarray.c
 util/cgroup.c
 util/rblist.c
+util/stat.c
 util/strlist.c
 util/trace-event.c
 ../../lib/rbtree.c
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index 8acd0df88b5c..d457c523a33d 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -20,7 +20,7 @@ static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str)
 	if (!evlist)
 		return -ENOMEM;
 
-	if (parse_events(evlist, str))
+	if (parse_events(evlist, str, NULL))
 		goto out_delete;
 
 	evsel = perf_evlist__first(evlist);
@@ -119,7 +119,16 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts)
 			evsel->attr.comm_exec = 1;
 	}
 
-	if (evlist->nr_entries > 1) {
+	if (opts->full_auxtrace) {
+		/*
+		 * Need to be able to synthesize and parse selected events with
+		 * arbitrary sample types, which requires always being able to
+		 * match the id.
+		 */
+		use_sample_identifier = perf_can_sample_identifier();
+		evlist__for_each(evlist, evsel)
+			perf_evsel__set_sample_id(evsel, use_sample_identifier);
+	} else if (evlist->nr_entries > 1) {
 		struct perf_evsel *first = perf_evlist__first(evlist);
 
 		evlist__for_each(evlist, evsel) {
@@ -207,7 +216,7 @@ bool perf_evlist__can_select_event(struct perf_evlist *evlist, const char *str)
 	if (!temp_evlist)
 		return false;
 
-	err = parse_events(temp_evlist, str);
+	err = parse_events(temp_evlist, str, NULL);
 	if (err)
 		goto out_delete;
 
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 0c74012575ac..aa482c10469d 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -15,12 +15,14 @@
 #include "cpumap.h"
 #include "perf_regs.h"
 #include "asm/bug.h"
+#include "auxtrace.h"
+#include "thread-stack.h"
 
-static int machines__deliver_event(struct machines *machines,
-				   struct perf_evlist *evlist,
-				   union perf_event *event,
-				   struct perf_sample *sample,
-				   struct perf_tool *tool, u64 file_offset);
+static int perf_session__deliver_event(struct perf_session *session,
+				       union perf_event *event,
+				       struct perf_sample *sample,
+				       struct perf_tool *tool,
+				       u64 file_offset);
 
 static int perf_session__open(struct perf_session *session)
 {
@@ -105,8 +107,8 @@ static int ordered_events__deliver_event(struct ordered_events *oe,
 		return ret;
 	}
 
-	return machines__deliver_event(&session->machines, session->evlist, event->event,
-				       &sample, session->tool, event->file_offset);
+	return perf_session__deliver_event(session, event->event, &sample,
+					   session->tool, event->file_offset);
 }
 
 struct perf_session *perf_session__new(struct perf_data_file *file,
@@ -119,6 +121,7 @@ struct perf_session *perf_session__new(struct perf_data_file *file,
 
 	session->repipe = repipe;
 	session->tool   = tool;
+	INIT_LIST_HEAD(&session->auxtrace_index);
 	machines__init(&session->machines);
 	ordered_events__init(&session->ordered_events, ordered_events__deliver_event);
 
@@ -185,6 +188,8 @@ static void perf_session_env__delete(struct perf_session_env *env)
 
 void perf_session__delete(struct perf_session *session)
 {
+	auxtrace__free(session);
+	auxtrace_index__free(&session->auxtrace_index);
 	perf_session__destroy_kernel_maps(session);
 	perf_session__delete_threads(session);
 	perf_session_env__delete(&session->header.env);
@@ -262,6 +267,49 @@ static int process_id_index_stub(struct perf_tool *tool __maybe_unused,
 	return 0;
 }
 
+static int process_event_auxtrace_info_stub(struct perf_tool *tool __maybe_unused,
+				union perf_event *event __maybe_unused,
+				struct perf_session *session __maybe_unused)
+{
+	dump_printf(": unhandled!\n");
+	return 0;
+}
+
+static int skipn(int fd, off_t n)
+{
+	char buf[4096];
+	ssize_t ret;
+
+	while (n > 0) {
+		ret = read(fd, buf, min(n, (off_t)sizeof(buf)));
+		if (ret <= 0)
+			return ret;
+		n -= ret;
+	}
+
+	return 0;
+}
+
+static s64 process_event_auxtrace_stub(struct perf_tool *tool __maybe_unused,
+				       union perf_event *event,
+				       struct perf_session *session
+				       __maybe_unused)
+{
+	dump_printf(": unhandled!\n");
+	if (perf_data_file__is_pipe(session->file))
+		skipn(perf_data_file__fd(session->file), event->auxtrace.size);
+	return event->auxtrace.size;
+}
+
+static
+int process_event_auxtrace_error_stub(struct perf_tool *tool __maybe_unused,
+				      union perf_event *event __maybe_unused,
+				      struct perf_session *session __maybe_unused)
+{
+	dump_printf(": unhandled!\n");
+	return 0;
+}
+
 void perf_tool__fill_defaults(struct perf_tool *tool)
 {
 	if (tool->sample == NULL)
@@ -278,6 +326,12 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
 		tool->exit = process_event_stub;
 	if (tool->lost == NULL)
 		tool->lost = perf_event__process_lost;
+	if (tool->lost_samples == NULL)
+		tool->lost_samples = perf_event__process_lost_samples;
+	if (tool->aux == NULL)
+		tool->aux = perf_event__process_aux;
+	if (tool->itrace_start == NULL)
+		tool->itrace_start = perf_event__process_itrace_start;
 	if (tool->read == NULL)
 		tool->read = process_event_sample_stub;
 	if (tool->throttle == NULL)
@@ -298,6 +352,12 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
 	}
 	if (tool->id_index == NULL)
 		tool->id_index = process_id_index_stub;
+	if (tool->auxtrace_info == NULL)
+		tool->auxtrace_info = process_event_auxtrace_info_stub;
+	if (tool->auxtrace == NULL)
+		tool->auxtrace = process_event_auxtrace_stub;
+	if (tool->auxtrace_error == NULL)
+		tool->auxtrace_error = process_event_auxtrace_error_stub;
 }
 
 static void swap_sample_id_all(union perf_event *event, void *data)
@@ -390,6 +450,26 @@ static void perf_event__read_swap(union perf_event *event, bool sample_id_all)
 		swap_sample_id_all(event, &event->read + 1);
 }
 
+static void perf_event__aux_swap(union perf_event *event, bool sample_id_all)
+{
+	event->aux.aux_offset = bswap_64(event->aux.aux_offset);
+	event->aux.aux_size   = bswap_64(event->aux.aux_size);
+	event->aux.flags      = bswap_64(event->aux.flags);
+
+	if (sample_id_all)
+		swap_sample_id_all(event, &event->aux + 1);
+}
+
+static void perf_event__itrace_start_swap(union perf_event *event,
+					  bool sample_id_all)
+{
+	event->itrace_start.pid	 = bswap_32(event->itrace_start.pid);
+	event->itrace_start.tid	 = bswap_32(event->itrace_start.tid);
+
+	if (sample_id_all)
+		swap_sample_id_all(event, &event->itrace_start + 1);
+}
+
 static void perf_event__throttle_swap(union perf_event *event,
 				      bool sample_id_all)
 {
@@ -438,19 +518,42 @@ void perf_event__attr_swap(struct perf_event_attr *attr)
 {
 	attr->type		= bswap_32(attr->type);
 	attr->size		= bswap_32(attr->size);
-	attr->config		= bswap_64(attr->config);
-	attr->sample_period	= bswap_64(attr->sample_period);
-	attr->sample_type	= bswap_64(attr->sample_type);
-	attr->read_format	= bswap_64(attr->read_format);
-	attr->wakeup_events	= bswap_32(attr->wakeup_events);
-	attr->bp_type		= bswap_32(attr->bp_type);
-	attr->bp_addr		= bswap_64(attr->bp_addr);
-	attr->bp_len		= bswap_64(attr->bp_len);
-	attr->branch_sample_type = bswap_64(attr->branch_sample_type);
-	attr->sample_regs_user	 = bswap_64(attr->sample_regs_user);
-	attr->sample_stack_user  = bswap_32(attr->sample_stack_user);
 
-	swap_bitfield((u8 *) (&attr->read_format + 1), sizeof(u64));
+#define bswap_safe(f, n) 					\
+	(attr->size > (offsetof(struct perf_event_attr, f) + 	\
+		       sizeof(attr->f) * (n)))
+#define bswap_field(f, sz) 			\
+do { 						\
+	if (bswap_safe(f, 0))			\
+		attr->f = bswap_##sz(attr->f);	\
+} while(0)
+#define bswap_field_32(f) bswap_field(f, 32)
+#define bswap_field_64(f) bswap_field(f, 64)
+
+	bswap_field_64(config);
+	bswap_field_64(sample_period);
+	bswap_field_64(sample_type);
+	bswap_field_64(read_format);
+	bswap_field_32(wakeup_events);
+	bswap_field_32(bp_type);
+	bswap_field_64(bp_addr);
+	bswap_field_64(bp_len);
+	bswap_field_64(branch_sample_type);
+	bswap_field_64(sample_regs_user);
+	bswap_field_32(sample_stack_user);
+	bswap_field_32(aux_watermark);
+
+	/*
+	 * After read_format are bitfields. Check read_format because
+	 * we are unable to use offsetof on bitfield.
+	 */
+	if (bswap_safe(read_format, 1))
+		swap_bitfield((u8 *) (&attr->read_format + 1),
+			      sizeof(u64));
+#undef bswap_field_64
+#undef bswap_field_32
+#undef bswap_field
+#undef bswap_safe
 }
 
 static void perf_event__hdr_attr_swap(union perf_event *event,
@@ -478,6 +581,40 @@ static void perf_event__tracing_data_swap(union perf_event *event,
 	event->tracing_data.size = bswap_32(event->tracing_data.size);
 }
 
+static void perf_event__auxtrace_info_swap(union perf_event *event,
+					   bool sample_id_all __maybe_unused)
+{
+	size_t size;
+
+	event->auxtrace_info.type = bswap_32(event->auxtrace_info.type);
+
+	size = event->header.size;
+	size -= (void *)&event->auxtrace_info.priv - (void *)event;
+	mem_bswap_64(event->auxtrace_info.priv, size);
+}
+
+static void perf_event__auxtrace_swap(union perf_event *event,
+				      bool sample_id_all __maybe_unused)
+{
+	event->auxtrace.size      = bswap_64(event->auxtrace.size);
+	event->auxtrace.offset    = bswap_64(event->auxtrace.offset);
+	event->auxtrace.reference = bswap_64(event->auxtrace.reference);
+	event->auxtrace.idx       = bswap_32(event->auxtrace.idx);
+	event->auxtrace.tid       = bswap_32(event->auxtrace.tid);
+	event->auxtrace.cpu       = bswap_32(event->auxtrace.cpu);
+}
+
+static void perf_event__auxtrace_error_swap(union perf_event *event,
+					    bool sample_id_all __maybe_unused)
+{
+	event->auxtrace_error.type = bswap_32(event->auxtrace_error.type);
+	event->auxtrace_error.code = bswap_32(event->auxtrace_error.code);
+	event->auxtrace_error.cpu  = bswap_32(event->auxtrace_error.cpu);
+	event->auxtrace_error.pid  = bswap_32(event->auxtrace_error.pid);
+	event->auxtrace_error.tid  = bswap_32(event->auxtrace_error.tid);
+	event->auxtrace_error.ip   = bswap_64(event->auxtrace_error.ip);
+}
+
 typedef void (*perf_event__swap_op)(union perf_event *event,
 				    bool sample_id_all);
 
@@ -492,11 +629,17 @@ static perf_event__swap_op perf_event__swap_ops[] = {
 	[PERF_RECORD_THROTTLE]		  = perf_event__throttle_swap,
 	[PERF_RECORD_UNTHROTTLE]	  = perf_event__throttle_swap,
 	[PERF_RECORD_SAMPLE]		  = perf_event__all64_swap,
+	[PERF_RECORD_AUX]		  = perf_event__aux_swap,
+	[PERF_RECORD_ITRACE_START]	  = perf_event__itrace_start_swap,
+	[PERF_RECORD_LOST_SAMPLES]	  = perf_event__all64_swap,
 	[PERF_RECORD_HEADER_ATTR]	  = perf_event__hdr_attr_swap,
 	[PERF_RECORD_HEADER_EVENT_TYPE]	  = perf_event__event_type_swap,
 	[PERF_RECORD_HEADER_TRACING_DATA] = perf_event__tracing_data_swap,
 	[PERF_RECORD_HEADER_BUILD_ID]	  = NULL,
 	[PERF_RECORD_ID_INDEX]		  = perf_event__all64_swap,
+	[PERF_RECORD_AUXTRACE_INFO]	  = perf_event__auxtrace_info_swap,
+	[PERF_RECORD_AUXTRACE]		  = perf_event__auxtrace_swap,
+	[PERF_RECORD_AUXTRACE_ERROR]	  = perf_event__auxtrace_error_swap,
 	[PERF_RECORD_HEADER_MAX]	  = NULL,
 };
 
@@ -921,6 +1064,8 @@ static int machines__deliver_event(struct machines *machines,
 	case PERF_RECORD_MMAP:
 		return tool->mmap(tool, event, sample, machine);
 	case PERF_RECORD_MMAP2:
+		if (event->header.misc & PERF_RECORD_MISC_PROC_MAP_PARSE_TIMEOUT)
+			++evlist->stats.nr_proc_map_timeout;
 		return tool->mmap2(tool, event, sample, machine);
 	case PERF_RECORD_COMM:
 		return tool->comm(tool, event, sample, machine);
@@ -932,18 +1077,44 @@ static int machines__deliver_event(struct machines *machines,
 		if (tool->lost == perf_event__process_lost)
 			evlist->stats.total_lost += event->lost.lost;
 		return tool->lost(tool, event, sample, machine);
+	case PERF_RECORD_LOST_SAMPLES:
+		if (tool->lost_samples == perf_event__process_lost_samples)
+			evlist->stats.total_lost_samples += event->lost_samples.lost;
+		return tool->lost_samples(tool, event, sample, machine);
 	case PERF_RECORD_READ:
 		return tool->read(tool, event, sample, evsel, machine);
 	case PERF_RECORD_THROTTLE:
 		return tool->throttle(tool, event, sample, machine);
 	case PERF_RECORD_UNTHROTTLE:
 		return tool->unthrottle(tool, event, sample, machine);
+	case PERF_RECORD_AUX:
+		return tool->aux(tool, event, sample, machine);
+	case PERF_RECORD_ITRACE_START:
+		return tool->itrace_start(tool, event, sample, machine);
 	default:
 		++evlist->stats.nr_unknown_events;
 		return -1;
 	}
 }
 
+static int perf_session__deliver_event(struct perf_session *session,
+				       union perf_event *event,
+				       struct perf_sample *sample,
+				       struct perf_tool *tool,
+				       u64 file_offset)
+{
+	int ret;
+
+	ret = auxtrace__process_event(session, event, sample, tool);
+	if (ret < 0)
+		return ret;
+	if (ret > 0)
+		return 0;
+
+	return machines__deliver_event(&session->machines, session->evlist,
+				       event, sample, tool, file_offset);
+}
+
 static s64 perf_session__process_user_event(struct perf_session *session,
 					    union perf_event *event,
 					    u64 file_offset)
@@ -980,6 +1151,15 @@ static s64 perf_session__process_user_event(struct perf_session *session,
 		return tool->finished_round(tool, event, oe);
 	case PERF_RECORD_ID_INDEX:
 		return tool->id_index(tool, event, session);
+	case PERF_RECORD_AUXTRACE_INFO:
+		return tool->auxtrace_info(tool, event, session);
+	case PERF_RECORD_AUXTRACE:
+		/* setup for reading amidst mmap */
+		lseek(fd, file_offset + event->header.size, SEEK_SET);
+		return tool->auxtrace(tool, event, session);
+	case PERF_RECORD_AUXTRACE_ERROR:
+		perf_session__auxtrace_error_inc(session, event);
+		return tool->auxtrace_error(tool, event, session);
 	default:
 		return -EINVAL;
 	}
@@ -1034,7 +1214,7 @@ int perf_session__peek_event(struct perf_session *session, off_t file_offset,
 		return -1;
 
 	if (lseek(fd, file_offset, SEEK_SET) == (off_t)-1 ||
-	    readn(fd, &buf, hdr_sz) != (ssize_t)hdr_sz)
+	    readn(fd, buf, hdr_sz) != (ssize_t)hdr_sz)
 		return -1;
 
 	event = (union perf_event *)buf;
@@ -1042,12 +1222,12 @@ int perf_session__peek_event(struct perf_session *session, off_t file_offset,
 	if (session->header.needs_swap)
 		perf_event_header__bswap(&event->header);
 
-	if (event->header.size < hdr_sz)
+	if (event->header.size < hdr_sz || event->header.size > buf_sz)
 		return -1;
 
 	rest = event->header.size - hdr_sz;
 
-	if (readn(fd, &buf, rest) != (ssize_t)rest)
+	if (readn(fd, buf, rest) != (ssize_t)rest)
 		return -1;
 
 	if (session->header.needs_swap)
@@ -1096,8 +1276,8 @@ static s64 perf_session__process_event(struct perf_session *session,
 			return ret;
 	}
 
-	return machines__deliver_event(&session->machines, evlist, event,
-				       &sample, tool, file_offset);
+	return perf_session__deliver_event(session, event, &sample, tool,
+					   file_offset);
 }
 
 void perf_event_header__bswap(struct perf_event_header *hdr)
@@ -1138,6 +1318,18 @@ static void perf_session__warn_about_errors(const struct perf_session *session)
 			    stats->nr_events[PERF_RECORD_LOST]);
 	}
 
+	if (session->tool->lost_samples == perf_event__process_lost_samples) {
+		double drop_rate;
+
+		drop_rate = (double)stats->total_lost_samples /
+			    (double) (stats->nr_events[PERF_RECORD_SAMPLE] + stats->total_lost_samples);
+		if (drop_rate > 0.05) {
+			ui__warning("Processed %" PRIu64 " samples and lost %3.2f%% samples!\n\n",
+				    stats->nr_events[PERF_RECORD_SAMPLE] + stats->total_lost_samples,
+				    drop_rate * 100.0);
+		}
+	}
+
 	if (stats->nr_unknown_events != 0) {
 		ui__warning("Found %u unknown events!\n\n"
 			    "Is this an older tool processing a perf.data "
@@ -1168,6 +1360,32 @@ static void perf_session__warn_about_errors(const struct perf_session *session)
 
 	if (oe->nr_unordered_events != 0)
 		ui__warning("%u out of order events recorded.\n", oe->nr_unordered_events);
+
+	events_stats__auxtrace_error_warn(stats);
+
+	if (stats->nr_proc_map_timeout != 0) {
+		ui__warning("%d map information files for pre-existing threads were\n"
+			    "not processed, if there are samples for addresses they\n"
+			    "will not be resolved, you may find out which are these\n"
+			    "threads by running with -v and redirecting the output\n"
+			    "to a file.\n"
+			    "The time limit to process proc map is too short?\n"
+			    "Increase it by --proc-map-timeout\n",
+			    stats->nr_proc_map_timeout);
+	}
+}
+
+static int perf_session__flush_thread_stack(struct thread *thread,
+					    void *p __maybe_unused)
+{
+	return thread_stack__flush(thread);
+}
+
+static int perf_session__flush_thread_stacks(struct perf_session *session)
+{
+	return machines__for_each_thread(&session->machines,
+					 perf_session__flush_thread_stack,
+					 NULL);
 }
 
 volatile int session_done;
@@ -1256,10 +1474,17 @@ more:
 done:
 	/* do the final flush for ordered samples */
 	err = ordered_events__flush(oe, OE_FLUSH__FINAL);
+	if (err)
+		goto out_err;
+	err = auxtrace__flush_events(session, tool);
+	if (err)
+		goto out_err;
+	err = perf_session__flush_thread_stacks(session);
 out_err:
 	free(buf);
 	perf_session__warn_about_errors(session);
 	ordered_events__free(&session->ordered_events);
+	auxtrace__free_events(session);
 	return err;
 }
 
@@ -1402,10 +1627,17 @@ more:
 out:
 	/* do the final flush for ordered samples */
 	err = ordered_events__flush(oe, OE_FLUSH__FINAL);
+	if (err)
+		goto out_err;
+	err = auxtrace__flush_events(session, tool);
+	if (err)
+		goto out_err;
+	err = perf_session__flush_thread_stacks(session);
 out_err:
 	ui_progress__finish();
 	perf_session__warn_about_errors(session);
 	ordered_events__free(&session->ordered_events);
+	auxtrace__free_events(session);
 	session->one_mmap = false;
 	return err;
 }
@@ -1488,7 +1720,13 @@ size_t perf_session__fprintf_dsos_buildid(struct perf_session *session, FILE *fp
 
 size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp)
 {
-	size_t ret = fprintf(fp, "Aggregated stats:\n");
+	size_t ret;
+	const char *msg = "";
+
+	if (perf_header__has_feat(&session->header, HEADER_AUXTRACE))
+		msg = " (excludes AUX area (e.g. instruction trace) decoded / synthesized events)";
+
+	ret = fprintf(fp, "Aggregated stats:%s\n", msg);
 
 	ret += events_stats__fprintf(&session->evlist->stats, fp);
 	return ret;
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index d5fa7b7916ef..b44afc75d1cc 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -15,10 +15,16 @@
 struct ip_callchain;
 struct thread;
 
+struct auxtrace;
+struct itrace_synth_opts;
+
 struct perf_session {
 	struct perf_header	header;
 	struct machines		machines;
 	struct perf_evlist	*evlist;
+	struct auxtrace		*auxtrace;
+	struct itrace_synth_opts *itrace_synth_opts;
+	struct list_head	auxtrace_index;
 	struct trace_event	tevent;
 	bool			repipe;
 	bool			one_mmap;
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 4593f36ecc4c..4c65a143a34c 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -89,14 +89,14 @@ static int64_t
 sort__comm_cmp(struct hist_entry *left, struct hist_entry *right)
 {
 	/* Compare the addr that should be unique among comm */
-	return comm__str(right->comm) - comm__str(left->comm);
+	return strcmp(comm__str(right->comm), comm__str(left->comm));
 }
 
 static int64_t
 sort__comm_collapse(struct hist_entry *left, struct hist_entry *right)
 {
 	/* Compare the addr that should be unique among comm */
-	return comm__str(right->comm) - comm__str(left->comm);
+	return strcmp(comm__str(right->comm), comm__str(left->comm));
 }
 
 static int64_t
@@ -182,18 +182,16 @@ static int64_t _sort__addr_cmp(u64 left_ip, u64 right_ip)
 
 static int64_t _sort__sym_cmp(struct symbol *sym_l, struct symbol *sym_r)
 {
-	u64 ip_l, ip_r;
-
 	if (!sym_l || !sym_r)
 		return cmp_null(sym_l, sym_r);
 
 	if (sym_l == sym_r)
 		return 0;
 
-	ip_l = sym_l->start;
-	ip_r = sym_r->start;
+	if (sym_l->start != sym_r->start)
+		return (int64_t)(sym_r->start - sym_l->start);
 
-	return (int64_t)(ip_r - ip_l);
+	return (int64_t)(sym_r->end - sym_l->end);
 }
 
 static int64_t
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 846036a921dc..e97cd476d336 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -58,15 +58,16 @@ struct he_stat {
 
 struct hist_entry_diff {
 	bool	computed;
+	union {
+		/* PERF_HPP__DELTA */
+		double	period_ratio_delta;
 
-	/* PERF_HPP__DELTA */
-	double	period_ratio_delta;
-
-	/* PERF_HPP__RATIO */
-	double	period_ratio;
+		/* PERF_HPP__RATIO */
+		double	period_ratio;
 
-	/* HISTC_WEIGHTED_DIFF */
-	s64	wdiff;
+		/* HISTC_WEIGHTED_DIFF */
+		s64	wdiff;
+	};
 };
 
 /**
@@ -92,21 +93,28 @@ struct hist_entry {
 	s32			cpu;
 	u8			cpumode;
 
-	struct hist_entry_diff	diff;
-
 	/* We are added by hists__add_dummy_entry. */
 	bool			dummy;
 
-	/* XXX These two should move to some tree widget lib */
-	u16			row_offset;
-	u16			nr_rows;
-
-	bool			init_have_children;
 	char			level;
 	u8			filtered;
+	union {
+		/*
+		 * Since perf diff only supports the stdio output, TUI
+		 * fields are only accessed from perf report (or perf
+		 * top).  So make it an union to reduce memory usage.
+		 */
+		struct hist_entry_diff	diff;
+		struct /* for TUI */ {
+			u16	row_offset;
+			u16	nr_rows;
+			bool	init_have_children;
+			bool	unfolded;
+			bool	has_children;
+		};
+	};
 	char			*srcline;
 	struct symbol		*parent;
-	unsigned long		position;
 	struct rb_root		sorted_chain;
 	struct branch_info	*branch_info;
 	struct hists		*hists;
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
new file mode 100644
index 000000000000..53e8bb7bc852
--- /dev/null
+++ b/tools/perf/util/stat-shadow.c
@@ -0,0 +1,434 @@
+#include <stdio.h>
+#include "evsel.h"
+#include "stat.h"
+#include "color.h"
+
+enum {
+	CTX_BIT_USER	= 1 << 0,
+	CTX_BIT_KERNEL	= 1 << 1,
+	CTX_BIT_HV	= 1 << 2,
+	CTX_BIT_HOST	= 1 << 3,
+	CTX_BIT_IDLE	= 1 << 4,
+	CTX_BIT_MAX	= 1 << 5,
+};
+
+#define NUM_CTX CTX_BIT_MAX
+
+static struct stats runtime_nsecs_stats[MAX_NR_CPUS];
+static struct stats runtime_cycles_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_stalled_cycles_front_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_stalled_cycles_back_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_branches_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_cacherefs_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_l1_dcache_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_l1_icache_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_ll_cache_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_itlb_cache_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_dtlb_cache_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_cycles_in_tx_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_transaction_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_elision_stats[NUM_CTX][MAX_NR_CPUS];
+
+struct stats walltime_nsecs_stats;
+
+static int evsel_context(struct perf_evsel *evsel)
+{
+	int ctx = 0;
+
+	if (evsel->attr.exclude_kernel)
+		ctx |= CTX_BIT_KERNEL;
+	if (evsel->attr.exclude_user)
+		ctx |= CTX_BIT_USER;
+	if (evsel->attr.exclude_hv)
+		ctx |= CTX_BIT_HV;
+	if (evsel->attr.exclude_host)
+		ctx |= CTX_BIT_HOST;
+	if (evsel->attr.exclude_idle)
+		ctx |= CTX_BIT_IDLE;
+
+	return ctx;
+}
+
+void perf_stat__reset_shadow_stats(void)
+{
+	memset(runtime_nsecs_stats, 0, sizeof(runtime_nsecs_stats));
+	memset(runtime_cycles_stats, 0, sizeof(runtime_cycles_stats));
+	memset(runtime_stalled_cycles_front_stats, 0, sizeof(runtime_stalled_cycles_front_stats));
+	memset(runtime_stalled_cycles_back_stats, 0, sizeof(runtime_stalled_cycles_back_stats));
+	memset(runtime_branches_stats, 0, sizeof(runtime_branches_stats));
+	memset(runtime_cacherefs_stats, 0, sizeof(runtime_cacherefs_stats));
+	memset(runtime_l1_dcache_stats, 0, sizeof(runtime_l1_dcache_stats));
+	memset(runtime_l1_icache_stats, 0, sizeof(runtime_l1_icache_stats));
+	memset(runtime_ll_cache_stats, 0, sizeof(runtime_ll_cache_stats));
+	memset(runtime_itlb_cache_stats, 0, sizeof(runtime_itlb_cache_stats));
+	memset(runtime_dtlb_cache_stats, 0, sizeof(runtime_dtlb_cache_stats));
+	memset(runtime_cycles_in_tx_stats, 0,
+			sizeof(runtime_cycles_in_tx_stats));
+	memset(runtime_transaction_stats, 0,
+		sizeof(runtime_transaction_stats));
+	memset(runtime_elision_stats, 0, sizeof(runtime_elision_stats));
+	memset(&walltime_nsecs_stats, 0, sizeof(walltime_nsecs_stats));
+}
+
+/*
+ * Update various tracking values we maintain to print
+ * more semantic information such as miss/hit ratios,
+ * instruction rates, etc:
+ */
+void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
+				    int cpu)
+{
+	int ctx = evsel_context(counter);
+
+	if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK))
+		update_stats(&runtime_nsecs_stats[cpu], count[0]);
+	else if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
+		update_stats(&runtime_cycles_stats[ctx][cpu], count[0]);
+	else if (perf_stat_evsel__is(counter, CYCLES_IN_TX))
+		update_stats(&runtime_transaction_stats[ctx][cpu], count[0]);
+	else if (perf_stat_evsel__is(counter, TRANSACTION_START))
+		update_stats(&runtime_transaction_stats[ctx][cpu], count[0]);
+	else if (perf_stat_evsel__is(counter, ELISION_START))
+		update_stats(&runtime_elision_stats[ctx][cpu], count[0]);
+	else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND))
+		update_stats(&runtime_stalled_cycles_front_stats[ctx][cpu], count[0]);
+	else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND))
+		update_stats(&runtime_stalled_cycles_back_stats[ctx][cpu], count[0]);
+	else if (perf_evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS))
+		update_stats(&runtime_branches_stats[ctx][cpu], count[0]);
+	else if (perf_evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES))
+		update_stats(&runtime_cacherefs_stats[ctx][cpu], count[0]);
+	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1D))
+		update_stats(&runtime_l1_dcache_stats[ctx][cpu], count[0]);
+	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1I))
+		update_stats(&runtime_ll_cache_stats[ctx][cpu], count[0]);
+	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_LL))
+		update_stats(&runtime_ll_cache_stats[ctx][cpu], count[0]);
+	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_DTLB))
+		update_stats(&runtime_dtlb_cache_stats[ctx][cpu], count[0]);
+	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_ITLB))
+		update_stats(&runtime_itlb_cache_stats[ctx][cpu], count[0]);
+}
+
+/* used for get_ratio_color() */
+enum grc_type {
+	GRC_STALLED_CYCLES_FE,
+	GRC_STALLED_CYCLES_BE,
+	GRC_CACHE_MISSES,
+	GRC_MAX_NR
+};
+
+static const char *get_ratio_color(enum grc_type type, double ratio)
+{
+	static const double grc_table[GRC_MAX_NR][3] = {
+		[GRC_STALLED_CYCLES_FE] = { 50.0, 30.0, 10.0 },
+		[GRC_STALLED_CYCLES_BE] = { 75.0, 50.0, 20.0 },
+		[GRC_CACHE_MISSES] 	= { 20.0, 10.0, 5.0 },
+	};
+	const char *color = PERF_COLOR_NORMAL;
+
+	if (ratio > grc_table[type][0])
+		color = PERF_COLOR_RED;
+	else if (ratio > grc_table[type][1])
+		color = PERF_COLOR_MAGENTA;
+	else if (ratio > grc_table[type][2])
+		color = PERF_COLOR_YELLOW;
+
+	return color;
+}
+
+static void print_stalled_cycles_frontend(FILE *out, int cpu,
+					  struct perf_evsel *evsel
+					  __maybe_unused, double avg)
+{
+	double total, ratio = 0.0;
+	const char *color;
+	int ctx = evsel_context(evsel);
+
+	total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
+
+	if (total)
+		ratio = avg / total * 100.0;
+
+	color = get_ratio_color(GRC_STALLED_CYCLES_FE, ratio);
+
+	fprintf(out, " #  ");
+	color_fprintf(out, color, "%6.2f%%", ratio);
+	fprintf(out, " frontend cycles idle   ");
+}
+
+static void print_stalled_cycles_backend(FILE *out, int cpu,
+					 struct perf_evsel *evsel
+					 __maybe_unused, double avg)
+{
+	double total, ratio = 0.0;
+	const char *color;
+	int ctx = evsel_context(evsel);
+
+	total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
+
+	if (total)
+		ratio = avg / total * 100.0;
+
+	color = get_ratio_color(GRC_STALLED_CYCLES_BE, ratio);
+
+	fprintf(out, " #  ");
+	color_fprintf(out, color, "%6.2f%%", ratio);
+	fprintf(out, " backend  cycles idle   ");
+}
+
+static void print_branch_misses(FILE *out, int cpu,
+				struct perf_evsel *evsel __maybe_unused,
+				double avg)
+{
+	double total, ratio = 0.0;
+	const char *color;
+	int ctx = evsel_context(evsel);
+
+	total = avg_stats(&runtime_branches_stats[ctx][cpu]);
+
+	if (total)
+		ratio = avg / total * 100.0;
+
+	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
+
+	fprintf(out, " #  ");
+	color_fprintf(out, color, "%6.2f%%", ratio);
+	fprintf(out, " of all branches        ");
+}
+
+static void print_l1_dcache_misses(FILE *out, int cpu,
+				   struct perf_evsel *evsel __maybe_unused,
+				   double avg)
+{
+	double total, ratio = 0.0;
+	const char *color;
+	int ctx = evsel_context(evsel);
+
+	total = avg_stats(&runtime_l1_dcache_stats[ctx][cpu]);
+
+	if (total)
+		ratio = avg / total * 100.0;
+
+	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
+
+	fprintf(out, " #  ");
+	color_fprintf(out, color, "%6.2f%%", ratio);
+	fprintf(out, " of all L1-dcache hits  ");
+}
+
+static void print_l1_icache_misses(FILE *out, int cpu,
+				   struct perf_evsel *evsel __maybe_unused,
+				   double avg)
+{
+	double total, ratio = 0.0;
+	const char *color;
+	int ctx = evsel_context(evsel);
+
+	total = avg_stats(&runtime_l1_icache_stats[ctx][cpu]);
+
+	if (total)
+		ratio = avg / total * 100.0;
+
+	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
+
+	fprintf(out, " #  ");
+	color_fprintf(out, color, "%6.2f%%", ratio);
+	fprintf(out, " of all L1-icache hits  ");
+}
+
+static void print_dtlb_cache_misses(FILE *out, int cpu,
+				    struct perf_evsel *evsel __maybe_unused,
+				    double avg)
+{
+	double total, ratio = 0.0;
+	const char *color;
+	int ctx = evsel_context(evsel);
+
+	total = avg_stats(&runtime_dtlb_cache_stats[ctx][cpu]);
+
+	if (total)
+		ratio = avg / total * 100.0;
+
+	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
+
+	fprintf(out, " #  ");
+	color_fprintf(out, color, "%6.2f%%", ratio);
+	fprintf(out, " of all dTLB cache hits ");
+}
+
+static void print_itlb_cache_misses(FILE *out, int cpu,
+				    struct perf_evsel *evsel __maybe_unused,
+				    double avg)
+{
+	double total, ratio = 0.0;
+	const char *color;
+	int ctx = evsel_context(evsel);
+
+	total = avg_stats(&runtime_itlb_cache_stats[ctx][cpu]);
+
+	if (total)
+		ratio = avg / total * 100.0;
+
+	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
+
+	fprintf(out, " #  ");
+	color_fprintf(out, color, "%6.2f%%", ratio);
+	fprintf(out, " of all iTLB cache hits ");
+}
+
+static void print_ll_cache_misses(FILE *out, int cpu,
+				  struct perf_evsel *evsel __maybe_unused,
+				  double avg)
+{
+	double total, ratio = 0.0;
+	const char *color;
+	int ctx = evsel_context(evsel);
+
+	total = avg_stats(&runtime_ll_cache_stats[ctx][cpu]);
+
+	if (total)
+		ratio = avg / total * 100.0;
+
+	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
+
+	fprintf(out, " #  ");
+	color_fprintf(out, color, "%6.2f%%", ratio);
+	fprintf(out, " of all LL-cache hits   ");
+}
+
+void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
+				   double avg, int cpu, enum aggr_mode aggr)
+{
+	double total, ratio = 0.0, total2;
+	int ctx = evsel_context(evsel);
+
+	if (perf_evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) {
+		total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
+		if (total) {
+			ratio = avg / total;
+			fprintf(out, " #   %5.2f  insns per cycle        ", ratio);
+		} else {
+			fprintf(out, "                                   ");
+		}
+		total = avg_stats(&runtime_stalled_cycles_front_stats[ctx][cpu]);
+		total = max(total, avg_stats(&runtime_stalled_cycles_back_stats[ctx][cpu]));
+
+		if (total && avg) {
+			ratio = total / avg;
+			fprintf(out, "\n");
+			if (aggr == AGGR_NONE)
+				fprintf(out, "        ");
+			fprintf(out, "                                                  #   %5.2f  stalled cycles per insn", ratio);
+		}
+
+	} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES) &&
+			runtime_branches_stats[ctx][cpu].n != 0) {
+		print_branch_misses(out, cpu, evsel, avg);
+	} else if (
+		evsel->attr.type == PERF_TYPE_HW_CACHE &&
+		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1D |
+					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
+					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
+			runtime_l1_dcache_stats[ctx][cpu].n != 0) {
+		print_l1_dcache_misses(out, cpu, evsel, avg);
+	} else if (
+		evsel->attr.type == PERF_TYPE_HW_CACHE &&
+		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1I |
+					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
+					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
+			runtime_l1_icache_stats[ctx][cpu].n != 0) {
+		print_l1_icache_misses(out, cpu, evsel, avg);
+	} else if (
+		evsel->attr.type == PERF_TYPE_HW_CACHE &&
+		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_DTLB |
+					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
+					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
+			runtime_dtlb_cache_stats[ctx][cpu].n != 0) {
+		print_dtlb_cache_misses(out, cpu, evsel, avg);
+	} else if (
+		evsel->attr.type == PERF_TYPE_HW_CACHE &&
+		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_ITLB |
+					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
+					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
+			runtime_itlb_cache_stats[ctx][cpu].n != 0) {
+		print_itlb_cache_misses(out, cpu, evsel, avg);
+	} else if (
+		evsel->attr.type == PERF_TYPE_HW_CACHE &&
+		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_LL |
+					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
+					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
+			runtime_ll_cache_stats[ctx][cpu].n != 0) {
+		print_ll_cache_misses(out, cpu, evsel, avg);
+	} else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES) &&
+			runtime_cacherefs_stats[ctx][cpu].n != 0) {
+		total = avg_stats(&runtime_cacherefs_stats[ctx][cpu]);
+
+		if (total)
+			ratio = avg * 100 / total;
+
+		fprintf(out, " # %8.3f %% of all cache refs    ", ratio);
+
+	} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) {
+		print_stalled_cycles_frontend(out, cpu, evsel, avg);
+	} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) {
+		print_stalled_cycles_backend(out, cpu, evsel, avg);
+	} else if (perf_evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) {
+		total = avg_stats(&runtime_nsecs_stats[cpu]);
+
+		if (total) {
+			ratio = avg / total;
+			fprintf(out, " # %8.3f GHz                    ", ratio);
+		} else {
+			fprintf(out, "                                   ");
+		}
+	} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX)) {
+		total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
+		if (total)
+			fprintf(out,
+				" #   %5.2f%% transactional cycles   ",
+				100.0 * (avg / total));
+	} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX_CP)) {
+		total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
+		total2 = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
+		if (total2 < avg)
+			total2 = avg;
+		if (total)
+			fprintf(out,
+				" #   %5.2f%% aborted cycles         ",
+				100.0 * ((total2-avg) / total));
+	} else if (perf_stat_evsel__is(evsel, TRANSACTION_START) &&
+		   avg > 0 &&
+		   runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
+		total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
+
+		if (total)
+			ratio = total / avg;
+
+		fprintf(out, " # %8.0f cycles / transaction   ", ratio);
+	} else if (perf_stat_evsel__is(evsel, ELISION_START) &&
+		   avg > 0 &&
+		   runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
+		total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
+
+		if (total)
+			ratio = total / avg;
+
+		fprintf(out, " # %8.0f cycles / elision       ", ratio);
+	} else if (runtime_nsecs_stats[cpu].n != 0) {
+		char unit = 'M';
+
+		total = avg_stats(&runtime_nsecs_stats[cpu]);
+
+		if (total)
+			ratio = 1000.0 * avg / total;
+		if (ratio < 0.001) {
+			ratio *= 1000;
+			unit = 'K';
+		}
+
+		fprintf(out, " # %8.3f %c/sec                  ", ratio, unit);
+	} else {
+		fprintf(out, "                                   ");
+	}
+}
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 6506b3dfb605..4014b709f956 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -1,6 +1,6 @@
 #include <math.h>
-
 #include "stat.h"
+#include "evsel.h"
 
 void update_stats(struct stats *stats, u64 val)
 {
@@ -61,3 +61,72 @@ double rel_stddev_stats(double stddev, double avg)
 
 	return pct;
 }
+
+bool __perf_evsel_stat__is(struct perf_evsel *evsel,
+			   enum perf_stat_evsel_id id)
+{
+	struct perf_stat *ps = evsel->priv;
+
+	return ps->id == id;
+}
+
+#define ID(id, name) [PERF_STAT_EVSEL_ID__##id] = #name
+static const char *id_str[PERF_STAT_EVSEL_ID__MAX] = {
+	ID(NONE,		x),
+	ID(CYCLES_IN_TX,	cpu/cycles-t/),
+	ID(TRANSACTION_START,	cpu/tx-start/),
+	ID(ELISION_START,	cpu/el-start/),
+	ID(CYCLES_IN_TX_CP,	cpu/cycles-ct/),
+};
+#undef ID
+
+void perf_stat_evsel_id_init(struct perf_evsel *evsel)
+{
+	struct perf_stat *ps = evsel->priv;
+	int i;
+
+	/* ps->id is 0 hence PERF_STAT_EVSEL_ID__NONE by default */
+
+	for (i = 0; i < PERF_STAT_EVSEL_ID__MAX; i++) {
+		if (!strcmp(perf_evsel__name(evsel), id_str[i])) {
+			ps->id = i;
+			break;
+		}
+	}
+}
+
+struct perf_counts *perf_counts__new(int ncpus)
+{
+	int size = sizeof(struct perf_counts) +
+		   ncpus * sizeof(struct perf_counts_values);
+
+	return zalloc(size);
+}
+
+void perf_counts__delete(struct perf_counts *counts)
+{
+	free(counts);
+}
+
+static void perf_counts__reset(struct perf_counts *counts, int ncpus)
+{
+	memset(counts, 0, (sizeof(*counts) +
+	       (ncpus * sizeof(struct perf_counts_values))));
+}
+
+void perf_evsel__reset_counts(struct perf_evsel *evsel, int ncpus)
+{
+	perf_counts__reset(evsel->counts, ncpus);
+}
+
+int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus)
+{
+	evsel->counts = perf_counts__new(ncpus);
+	return evsel->counts != NULL ? 0 : -ENOMEM;
+}
+
+void perf_evsel__free_counts(struct perf_evsel *evsel)
+{
+	perf_counts__delete(evsel->counts);
+	evsel->counts = NULL;
+}
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 5667fc3e39cf..093dc3cb28dd 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -2,6 +2,7 @@
 #define __PERF_STATS_H
 
 #include <linux/types.h>
+#include <stdio.h>
 
 struct stats
 {
@@ -9,6 +10,27 @@ struct stats
 	u64 max, min;
 };
 
+enum perf_stat_evsel_id {
+	PERF_STAT_EVSEL_ID__NONE = 0,
+	PERF_STAT_EVSEL_ID__CYCLES_IN_TX,
+	PERF_STAT_EVSEL_ID__TRANSACTION_START,
+	PERF_STAT_EVSEL_ID__ELISION_START,
+	PERF_STAT_EVSEL_ID__CYCLES_IN_TX_CP,
+	PERF_STAT_EVSEL_ID__MAX,
+};
+
+struct perf_stat {
+	struct stats		res_stats[3];
+	enum perf_stat_evsel_id	id;
+};
+
+enum aggr_mode {
+	AGGR_NONE,
+	AGGR_GLOBAL,
+	AGGR_SOCKET,
+	AGGR_CORE,
+};
+
 void update_stats(struct stats *stats, u64 val);
 double avg_stats(struct stats *stats);
 double stddev_stats(struct stats *stats);
@@ -22,4 +44,28 @@ static inline void init_stats(struct stats *stats)
 	stats->min  = (u64) -1;
 	stats->max  = 0;
 }
+
+struct perf_evsel;
+bool __perf_evsel_stat__is(struct perf_evsel *evsel,
+			   enum perf_stat_evsel_id id);
+
+#define perf_stat_evsel__is(evsel, id) \
+	__perf_evsel_stat__is(evsel, PERF_STAT_EVSEL_ID__ ## id)
+
+void perf_stat_evsel_id_init(struct perf_evsel *evsel);
+
+extern struct stats walltime_nsecs_stats;
+
+void perf_stat__reset_shadow_stats(void);
+void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
+				    int cpu);
+void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
+				   double avg, int cpu, enum aggr_mode aggr);
+
+struct perf_counts *perf_counts__new(int ncpus);
+void perf_counts__delete(struct perf_counts *counts);
+
+void perf_evsel__reset_counts(struct perf_evsel *evsel, int ncpus);
+int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus);
+void perf_evsel__free_counts(struct perf_evsel *evsel);
 #endif
diff --git a/tools/perf/util/strfilter.c b/tools/perf/util/strfilter.c
index 79a757a2a15c..bcae659b6546 100644
--- a/tools/perf/util/strfilter.c
+++ b/tools/perf/util/strfilter.c
@@ -170,6 +170,46 @@ struct strfilter *strfilter__new(const char *rules, const char **err)
 	return filter;
 }
 
+static int strfilter__append(struct strfilter *filter, bool _or,
+			     const char *rules, const char **err)
+{
+	struct strfilter_node *right, *root;
+	const char *ep = NULL;
+
+	if (!filter || !rules)
+		return -EINVAL;
+
+	right = strfilter_node__new(rules, &ep);
+	if (!right || *ep != '\0') {
+		if (err)
+			*err = ep;
+		goto error;
+	}
+	root = strfilter_node__alloc(_or ? OP_or : OP_and, filter->root, right);
+	if (!root) {
+		ep = NULL;
+		goto error;
+	}
+
+	filter->root = root;
+	return 0;
+
+error:
+	strfilter_node__delete(right);
+	return ep ? -EINVAL : -ENOMEM;
+}
+
+int strfilter__or(struct strfilter *filter, const char *rules, const char **err)
+{
+	return strfilter__append(filter, true, rules, err);
+}
+
+int strfilter__and(struct strfilter *filter, const char *rules,
+		   const char **err)
+{
+	return strfilter__append(filter, false, rules, err);
+}
+
 static bool strfilter_node__compare(struct strfilter_node *node,
 				    const char *str)
 {
@@ -197,3 +237,70 @@ bool strfilter__compare(struct strfilter *filter, const char *str)
 		return false;
 	return strfilter_node__compare(filter->root, str);
 }
+
+static int strfilter_node__sprint(struct strfilter_node *node, char *buf);
+
+/* sprint node in parenthesis if needed */
+static int strfilter_node__sprint_pt(struct strfilter_node *node, char *buf)
+{
+	int len;
+	int pt = node->r ? 2 : 0;	/* don't need to check node->l */
+
+	if (buf && pt)
+		*buf++ = '(';
+	len = strfilter_node__sprint(node, buf);
+	if (len < 0)
+		return len;
+	if (buf && pt)
+		*(buf + len) = ')';
+	return len + pt;
+}
+
+static int strfilter_node__sprint(struct strfilter_node *node, char *buf)
+{
+	int len = 0, rlen;
+
+	if (!node || !node->p)
+		return -EINVAL;
+
+	switch (*node->p) {
+	case '|':
+	case '&':
+		len = strfilter_node__sprint_pt(node->l, buf);
+		if (len < 0)
+			return len;
+	case '!':
+		if (buf) {
+			*(buf + len++) = *node->p;
+			buf += len;
+		} else
+			len++;
+		rlen = strfilter_node__sprint_pt(node->r, buf);
+		if (rlen < 0)
+			return rlen;
+		len += rlen;
+		break;
+	default:
+		len = strlen(node->p);
+		if (buf)
+			strcpy(buf, node->p);
+	}
+
+	return len;
+}
+
+char *strfilter__string(struct strfilter *filter)
+{
+	int len;
+	char *ret = NULL;
+
+	len = strfilter_node__sprint(filter->root, NULL);
+	if (len < 0)
+		return NULL;
+
+	ret = malloc(len + 1);
+	if (ret)
+		strfilter_node__sprint(filter->root, ret);
+
+	return ret;
+}
diff --git a/tools/perf/util/strfilter.h b/tools/perf/util/strfilter.h
index fe611f3c9e39..cff5eda88728 100644
--- a/tools/perf/util/strfilter.h
+++ b/tools/perf/util/strfilter.h
@@ -29,6 +29,32 @@ struct strfilter {
 struct strfilter *strfilter__new(const char *rules, const char **err);
 
 /**
+ * strfilter__or - Append an additional rule by logical-or
+ * @filter: Original string filter
+ * @rules: Filter rule to be appended at left of the root of
+ *         @filter by using logical-or.
+ * @err: Pointer which points an error detected on @rules
+ *
+ * Parse @rules and join it to the @filter by using logical-or.
+ * Return 0 if success, or return the error code.
+ */
+int strfilter__or(struct strfilter *filter,
+		  const char *rules, const char **err);
+
+/**
+ * strfilter__add - Append an additional rule by logical-and
+ * @filter: Original string filter
+ * @rules: Filter rule to be appended at left of the root of
+ *         @filter by using logical-and.
+ * @err: Pointer which points an error detected on @rules
+ *
+ * Parse @rules and join it to the @filter by using logical-and.
+ * Return 0 if success, or return the error code.
+ */
+int strfilter__and(struct strfilter *filter,
+		   const char *rules, const char **err);
+
+/**
  * strfilter__compare - compare given string and a string filter
  * @filter: String filter
  * @str: target string
@@ -45,4 +71,13 @@ bool strfilter__compare(struct strfilter *filter, const char *str);
  */
 void strfilter__delete(struct strfilter *filter);
 
+/**
+ * strfilter__string - Reconstruct a rule string from filter
+ * @filter: String filter to reconstruct
+ *
+ * Reconstruct a rule string from @filter. This will be good for
+ * debug messages. Note that returning string must be freed afterward.
+ */
+char *strfilter__string(struct strfilter *filter);
+
 #endif
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index a7ab6063e038..65f7e389ae09 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -630,6 +630,11 @@ void symsrc__destroy(struct symsrc *ss)
 	close(ss->fd);
 }
 
+bool __weak elf__needs_adjust_symbols(GElf_Ehdr ehdr)
+{
+	return ehdr.e_type == ET_EXEC || ehdr.e_type == ET_REL;
+}
+
 int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
 		 enum dso_binary_type type)
 {
@@ -678,6 +683,7 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
 		}
 
 		if (!dso__build_id_equal(dso, build_id)) {
+			pr_debug("%s: build id mismatch for %s.\n", __func__, name);
 			dso->load_errno = DSO_LOAD_ERRNO__MISMATCHING_BUILDID;
 			goto out_elf_end;
 		}
@@ -711,8 +717,7 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
 						     ".gnu.prelink_undo",
 						     NULL) != NULL);
 	} else {
-		ss->adjust_symbols = ehdr.e_type == ET_EXEC ||
-				     ehdr.e_type == ET_REL;
+		ss->adjust_symbols = elf__needs_adjust_symbols(ehdr);
 	}
 
 	ss->name   = strdup(name);
@@ -771,6 +776,8 @@ static bool want_demangle(bool is_kernel_sym)
 	return is_kernel_sym ? symbol_conf.demangle_kernel : symbol_conf.demangle;
 }
 
+void __weak arch__elf_sym_adjust(GElf_Sym *sym __maybe_unused) { }
+
 int dso__load_sym(struct dso *dso, struct map *map,
 		  struct symsrc *syms_ss, struct symsrc *runtime_ss,
 		  symbol_filter_t filter, int kmodule)
@@ -935,6 +942,8 @@ int dso__load_sym(struct dso *dso, struct map *map,
 		    (sym.st_value & 1))
 			--sym.st_value;
 
+		arch__elf_sym_adjust(&sym);
+
 		if (dso->kernel || kmodule) {
 			char dso_name[PATH_MAX];
 
@@ -963,8 +972,10 @@ int dso__load_sym(struct dso *dso, struct map *map,
 					map->unmap_ip = map__unmap_ip;
 					/* Ensure maps are correctly ordered */
 					if (kmaps) {
+						map__get(map);
 						map_groups__remove(kmaps, map);
 						map_groups__insert(kmaps, map);
+						map__put(map);
 					}
 				}
 
@@ -1005,7 +1016,7 @@ int dso__load_sym(struct dso *dso, struct map *map,
 				curr_map = map__new2(start, curr_dso,
 						     map->type);
 				if (curr_map == NULL) {
-					dso__delete(curr_dso);
+					dso__put(curr_dso);
 					goto out_elf_end;
 				}
 				if (adjust_kernel_syms) {
@@ -1020,11 +1031,7 @@ int dso__load_sym(struct dso *dso, struct map *map,
 				}
 				curr_dso->symtab_type = dso->symtab_type;
 				map_groups__insert(kmaps, curr_map);
-				/*
-				 * The new DSO should go to the kernel DSOS
-				 */
-				dsos__add(&map->groups->machine->kernel_dsos,
-					  curr_dso);
+				dsos__add(&map->groups->machine->dsos, curr_dso);
 				dso__set_loaded(curr_dso, map->type);
 			} else
 				curr_dso = curr_map->dso;
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 201f6c4ca738..504f2d73b7ee 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -85,8 +85,17 @@ static int prefix_underscores_count(const char *str)
 	return tail - str;
 }
 
-#define SYMBOL_A 0
-#define SYMBOL_B 1
+int __weak arch__choose_best_symbol(struct symbol *syma,
+				    struct symbol *symb __maybe_unused)
+{
+	/* Avoid "SyS" kernel syscall aliases */
+	if (strlen(syma->name) >= 3 && !strncmp(syma->name, "SyS", 3))
+		return SYMBOL_B;
+	if (strlen(syma->name) >= 10 && !strncmp(syma->name, "compat_SyS", 10))
+		return SYMBOL_B;
+
+	return SYMBOL_A;
+}
 
 static int choose_best_symbol(struct symbol *syma, struct symbol *symb)
 {
@@ -134,13 +143,7 @@ static int choose_best_symbol(struct symbol *syma, struct symbol *symb)
 	else if (na < nb)
 		return SYMBOL_B;
 
-	/* Avoid "SyS" kernel syscall aliases */
-	if (na >= 3 && !strncmp(syma->name, "SyS", 3))
-		return SYMBOL_B;
-	if (na >= 10 && !strncmp(syma->name, "compat_SyS", 10))
-		return SYMBOL_B;
-
-	return SYMBOL_A;
+	return arch__choose_best_symbol(syma, symb);
 }
 
 void symbols__fixup_duplicate(struct rb_root *symbols)
@@ -199,18 +202,18 @@ void symbols__fixup_end(struct rb_root *symbols)
 
 void __map_groups__fixup_end(struct map_groups *mg, enum map_type type)
 {
-	struct map *prev, *curr;
-	struct rb_node *nd, *prevnd = rb_first(&mg->maps[type]);
+	struct maps *maps = &mg->maps[type];
+	struct map *next, *curr;
 
-	if (prevnd == NULL)
-		return;
+	pthread_rwlock_wrlock(&maps->lock);
 
-	curr = rb_entry(prevnd, struct map, rb_node);
+	curr = maps__first(maps);
+	if (curr == NULL)
+		goto out_unlock;
 
-	for (nd = rb_next(prevnd); nd; nd = rb_next(nd)) {
-		prev = curr;
-		curr = rb_entry(nd, struct map, rb_node);
-		prev->end = curr->start;
+	for (next = map__next(curr); next; next = map__next(curr)) {
+		curr->end = next->start;
+		curr = next;
 	}
 
 	/*
@@ -218,6 +221,9 @@ void __map_groups__fixup_end(struct map_groups *mg, enum map_type type)
 	 * last map final address.
 	 */
 	curr->end = ~0ULL;
+
+out_unlock:
+	pthread_rwlock_unlock(&maps->lock);
 }
 
 struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name)
@@ -397,7 +403,7 @@ static struct symbol *symbols__find_by_name(struct rb_root *symbols,
 					    const char *name)
 {
 	struct rb_node *n;
-	struct symbol_name_rb_node *s;
+	struct symbol_name_rb_node *s = NULL;
 
 	if (symbols == NULL)
 		return NULL;
@@ -408,7 +414,7 @@ static struct symbol *symbols__find_by_name(struct rb_root *symbols,
 		int cmp;
 
 		s = rb_entry(n, struct symbol_name_rb_node, rb_node);
-		cmp = strcmp(name, s->sym.name);
+		cmp = arch__compare_symbol_names(name, s->sym.name);
 
 		if (cmp < 0)
 			n = n->rb_left;
@@ -426,7 +432,7 @@ static struct symbol *symbols__find_by_name(struct rb_root *symbols,
 		struct symbol_name_rb_node *tmp;
 
 		tmp = rb_entry(n, struct symbol_name_rb_node, rb_node);
-		if (strcmp(tmp->sym.name, s->sym.name))
+		if (arch__compare_symbol_names(tmp->sym.name, s->sym.name))
 			break;
 
 		s = tmp;
@@ -653,14 +659,14 @@ static int dso__split_kallsyms_for_kcore(struct dso *dso, struct map *map,
 		curr_map = map_groups__find(kmaps, map->type, pos->start);
 
 		if (!curr_map || (filter && filter(curr_map, pos))) {
-			rb_erase(&pos->rb_node, root);
+			rb_erase_init(&pos->rb_node, root);
 			symbol__delete(pos);
 		} else {
 			pos->start -= curr_map->start - curr_map->pgoff;
 			if (pos->end)
 				pos->end -= curr_map->start - curr_map->pgoff;
 			if (curr_map != map) {
-				rb_erase(&pos->rb_node, root);
+				rb_erase_init(&pos->rb_node, root);
 				symbols__insert(
 					&curr_map->dso->symbols[curr_map->type],
 					pos);
@@ -780,7 +786,7 @@ static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta,
 
 			curr_map = map__new2(pos->start, ndso, map->type);
 			if (curr_map == NULL) {
-				dso__delete(ndso);
+				dso__put(ndso);
 				return -1;
 			}
 
@@ -1167,20 +1173,23 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 	/* Add new maps */
 	while (!list_empty(&md.maps)) {
 		new_map = list_entry(md.maps.next, struct map, node);
-		list_del(&new_map->node);
+		list_del_init(&new_map->node);
 		if (new_map == replacement_map) {
 			map->start	= new_map->start;
 			map->end	= new_map->end;
 			map->pgoff	= new_map->pgoff;
 			map->map_ip	= new_map->map_ip;
 			map->unmap_ip	= new_map->unmap_ip;
-			map__delete(new_map);
 			/* Ensure maps are correctly ordered */
+			map__get(map);
 			map_groups__remove(kmaps, map);
 			map_groups__insert(kmaps, map);
+			map__put(map);
 		} else {
 			map_groups__insert(kmaps, new_map);
 		}
+
+		map__put(new_map);
 	}
 
 	/*
@@ -1205,8 +1214,8 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 out_err:
 	while (!list_empty(&md.maps)) {
 		map = list_entry(md.maps.next, struct map, node);
-		list_del(&map->node);
-		map__delete(map);
+		list_del_init(&map->node);
+		map__put(map);
 	}
 	close(fd);
 	return -EINVAL;
@@ -1355,7 +1364,7 @@ static bool dso__is_compatible_symtab_type(struct dso *dso, bool kmod,
 	case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP:
 		/*
 		 * kernel modules know their symtab type - it's set when
-		 * creating a module dso in machine__new_module().
+		 * creating a module dso in machine__findnew_module_map().
 		 */
 		return kmod && dso->symtab_type == type;
 
@@ -1380,12 +1389,22 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 	struct symsrc *syms_ss = NULL, *runtime_ss = NULL;
 	bool kmod;
 
-	dso__set_loaded(dso, map->type);
+	pthread_mutex_lock(&dso->lock);
+
+	/* check again under the dso->lock */
+	if (dso__loaded(dso, map->type)) {
+		ret = 1;
+		goto out;
+	}
 
-	if (dso->kernel == DSO_TYPE_KERNEL)
-		return dso__load_kernel_sym(dso, map, filter);
-	else if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
-		return dso__load_guest_kernel_sym(dso, map, filter);
+	if (dso->kernel) {
+		if (dso->kernel == DSO_TYPE_KERNEL)
+			ret = dso__load_kernel_sym(dso, map, filter);
+		else if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
+			ret = dso__load_guest_kernel_sym(dso, map, filter);
+
+		goto out;
+	}
 
 	if (map->groups && map->groups->machine)
 		machine = map->groups->machine;
@@ -1398,18 +1417,18 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 		struct stat st;
 
 		if (lstat(dso->name, &st) < 0)
-			return -1;
+			goto out;
 
 		if (st.st_uid && (st.st_uid != geteuid())) {
 			pr_warning("File %s not owned by current user or root, "
 				"ignoring it.\n", dso->name);
-			return -1;
+			goto out;
 		}
 
 		ret = dso__load_perf_map(dso, map, filter);
 		dso->symtab_type = ret > 0 ? DSO_BINARY_TYPE__JAVA_JIT :
 					     DSO_BINARY_TYPE__NOT_FOUND;
-		return ret;
+		goto out;
 	}
 
 	if (machine)
@@ -1417,7 +1436,7 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 
 	name = malloc(PATH_MAX);
 	if (!name)
-		return -1;
+		goto out;
 
 	kmod = dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE ||
 		dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP ||
@@ -1498,23 +1517,32 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 out_free:
 	free(name);
 	if (ret < 0 && strstr(dso->name, " (deleted)") != NULL)
-		return 0;
+		ret = 0;
+out:
+	dso__set_loaded(dso, map->type);
+	pthread_mutex_unlock(&dso->lock);
+
 	return ret;
 }
 
 struct map *map_groups__find_by_name(struct map_groups *mg,
 				     enum map_type type, const char *name)
 {
-	struct rb_node *nd;
+	struct maps *maps = &mg->maps[type];
+	struct map *map;
 
-	for (nd = rb_first(&mg->maps[type]); nd; nd = rb_next(nd)) {
-		struct map *map = rb_entry(nd, struct map, rb_node);
+	pthread_rwlock_rdlock(&maps->lock);
 
+	for (map = maps__first(maps); map; map = map__next(map)) {
 		if (map->dso && strcmp(map->dso->short_name, name) == 0)
-			return map;
+			goto out_unlock;
 	}
 
-	return NULL;
+	map = NULL;
+
+out_unlock:
+	pthread_rwlock_unlock(&maps->lock);
+	return map;
 }
 
 int dso__load_vmlinux(struct dso *dso, struct map *map,
@@ -1802,6 +1830,7 @@ static void vmlinux_path__exit(void)
 {
 	while (--vmlinux_path__nr_entries >= 0)
 		zfree(&vmlinux_path[vmlinux_path__nr_entries]);
+	vmlinux_path__nr_entries = 0;
 
 	zfree(&vmlinux_path);
 }
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 09561500164a..bef47ead1d9b 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -158,8 +158,6 @@ struct ref_reloc_sym {
 struct map_symbol {
 	struct map    *map;
 	struct symbol *sym;
-	bool	      unfolded;
-	bool	      has_children;
 };
 
 struct addr_map_symbol {
@@ -303,4 +301,14 @@ int setup_list(struct strlist **list, const char *list_str,
 int setup_intlist(struct intlist **list, const char *list_str,
 		  const char *list_name);
 
+#ifdef HAVE_LIBELF_SUPPORT
+bool elf__needs_adjust_symbols(GElf_Ehdr ehdr);
+void arch__elf_sym_adjust(GElf_Sym *sym);
+#endif
+
+#define SYMBOL_A 0
+#define SYMBOL_B 1
+
+int arch__choose_best_symbol(struct symbol *syma, struct symbol *symb);
+
 #endif /* __PERF_SYMBOL */
diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c
index 9ed59a452d1f..679688e70ae7 100644
--- a/tools/perf/util/thread-stack.c
+++ b/tools/perf/util/thread-stack.c
@@ -219,7 +219,7 @@ static int thread_stack__call_return(struct thread *thread,
 	return crp->process(&cr, crp->data);
 }
 
-static int thread_stack__flush(struct thread *thread, struct thread_stack *ts)
+static int __thread_stack__flush(struct thread *thread, struct thread_stack *ts)
 {
 	struct call_return_processor *crp = ts->crp;
 	int err;
@@ -242,6 +242,14 @@ static int thread_stack__flush(struct thread *thread, struct thread_stack *ts)
 	return 0;
 }
 
+int thread_stack__flush(struct thread *thread)
+{
+	if (thread->ts)
+		return __thread_stack__flush(thread, thread->ts);
+
+	return 0;
+}
+
 int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
 			u64 to_ip, u16 insn_len, u64 trace_nr)
 {
@@ -264,7 +272,7 @@ int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
 	 */
 	if (trace_nr != thread->ts->trace_nr) {
 		if (thread->ts->trace_nr)
-			thread_stack__flush(thread, thread->ts);
+			__thread_stack__flush(thread, thread->ts);
 		thread->ts->trace_nr = trace_nr;
 	}
 
@@ -297,7 +305,7 @@ void thread_stack__set_trace_nr(struct thread *thread, u64 trace_nr)
 
 	if (trace_nr != thread->ts->trace_nr) {
 		if (thread->ts->trace_nr)
-			thread_stack__flush(thread, thread->ts);
+			__thread_stack__flush(thread, thread->ts);
 		thread->ts->trace_nr = trace_nr;
 	}
 }
@@ -305,7 +313,7 @@ void thread_stack__set_trace_nr(struct thread *thread, u64 trace_nr)
 void thread_stack__free(struct thread *thread)
 {
 	if (thread->ts) {
-		thread_stack__flush(thread, thread->ts);
+		__thread_stack__flush(thread, thread->ts);
 		zfree(&thread->ts->stack);
 		zfree(&thread->ts);
 	}
@@ -689,7 +697,7 @@ int thread_stack__process(struct thread *thread, struct comm *comm,
 
 	/* Flush stack on exec */
 	if (ts->comm != comm && thread->pid_ == thread->tid) {
-		err = thread_stack__flush(thread, ts);
+		err = __thread_stack__flush(thread, ts);
 		if (err)
 			return err;
 		ts->comm = comm;
diff --git a/tools/perf/util/thread-stack.h b/tools/perf/util/thread-stack.h
index b843bbef8ba2..e1528f1374c3 100644
--- a/tools/perf/util/thread-stack.h
+++ b/tools/perf/util/thread-stack.h
@@ -96,6 +96,7 @@ int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
 void thread_stack__set_trace_nr(struct thread *thread, u64 trace_nr);
 void thread_stack__sample(struct thread *thread, struct ip_callchain *chain,
 			  size_t sz, u64 ip);
+int thread_stack__flush(struct thread *thread);
 void thread_stack__free(struct thread *thread);
 
 struct call_return_processor *
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 1c8fbc9588c5..28c4b746baa1 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -18,7 +18,7 @@ int thread__init_map_groups(struct thread *thread, struct machine *machine)
 	if (pid == thread->tid || pid == -1) {
 		thread->mg = map_groups__new(machine);
 	} else {
-		leader = machine__findnew_thread(machine, pid, pid);
+		leader = __machine__findnew_thread(machine, pid, pid);
 		if (leader)
 			thread->mg = map_groups__get(leader->mg);
 	}
@@ -53,7 +53,8 @@ struct thread *thread__new(pid_t pid, pid_t tid)
 			goto err_thread;
 
 		list_add(&comm->list, &thread->comm_list);
-
+		atomic_set(&thread->refcnt, 0);
+		RB_CLEAR_NODE(&thread->rb_node);
 	}
 
 	return thread;
@@ -67,6 +68,8 @@ void thread__delete(struct thread *thread)
 {
 	struct comm *comm, *tmp;
 
+	BUG_ON(!RB_EMPTY_NODE(&thread->rb_node));
+
 	thread_stack__free(thread);
 
 	if (thread->mg) {
@@ -84,13 +87,14 @@ void thread__delete(struct thread *thread)
 
 struct thread *thread__get(struct thread *thread)
 {
-	++thread->refcnt;
+	if (thread)
+		atomic_inc(&thread->refcnt);
 	return thread;
 }
 
 void thread__put(struct thread *thread)
 {
-	if (thread && --thread->refcnt == 0) {
+	if (thread && atomic_dec_and_test(&thread->refcnt)) {
 		list_del_init(&thread->node);
 		thread__delete(thread);
 	}
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 9b8a54dc34a8..a0ac0317affb 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -1,6 +1,7 @@
 #ifndef __PERF_THREAD_H
 #define __PERF_THREAD_H
 
+#include <linux/atomic.h>
 #include <linux/rbtree.h>
 #include <linux/list.h>
 #include <unistd.h>
@@ -21,12 +22,12 @@ struct thread {
 	pid_t			tid;
 	pid_t			ppid;
 	int			cpu;
-	int			refcnt;
+	atomic_t		refcnt;
 	char			shortname[3];
 	bool			comm_set;
+	int			comm_len;
 	bool			dead; /* if set thread has exited */
 	struct list_head	comm_list;
-	int			comm_len;
 	u64			db_id;
 
 	void			*priv;
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index f93b9734735b..f4822bd03709 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -20,6 +20,15 @@ static int filter(const struct dirent *dir)
 		return 1;
 }
 
+static struct thread_map *thread_map__realloc(struct thread_map *map, int nr)
+{
+	size_t size = sizeof(*map) + sizeof(pid_t) * nr;
+
+	return realloc(map, size);
+}
+
+#define thread_map__alloc(__nr) thread_map__realloc(NULL, __nr)
+
 struct thread_map *thread_map__new_by_pid(pid_t pid)
 {
 	struct thread_map *threads;
@@ -33,7 +42,7 @@ struct thread_map *thread_map__new_by_pid(pid_t pid)
 	if (items <= 0)
 		return NULL;
 
-	threads = malloc(sizeof(*threads) + sizeof(pid_t) * items);
+	threads = thread_map__alloc(items);
 	if (threads != NULL) {
 		for (i = 0; i < items; i++)
 			threads->map[i] = atoi(namelist[i]->d_name);
@@ -49,7 +58,7 @@ struct thread_map *thread_map__new_by_pid(pid_t pid)
 
 struct thread_map *thread_map__new_by_tid(pid_t tid)
 {
-	struct thread_map *threads = malloc(sizeof(*threads) + sizeof(pid_t));
+	struct thread_map *threads = thread_map__alloc(1);
 
 	if (threads != NULL) {
 		threads->map[0] = tid;
@@ -65,8 +74,8 @@ struct thread_map *thread_map__new_by_uid(uid_t uid)
 	int max_threads = 32, items, i;
 	char path[256];
 	struct dirent dirent, *next, **namelist = NULL;
-	struct thread_map *threads = malloc(sizeof(*threads) +
-					    max_threads * sizeof(pid_t));
+	struct thread_map *threads = thread_map__alloc(max_threads);
+
 	if (threads == NULL)
 		goto out;
 
@@ -185,8 +194,7 @@ static struct thread_map *thread_map__new_by_pid_str(const char *pid_str)
 			goto out_free_threads;
 
 		total_tasks += items;
-		nt = realloc(threads, (sizeof(*threads) +
-				       sizeof(pid_t) * total_tasks));
+		nt = thread_map__realloc(threads, total_tasks);
 		if (nt == NULL)
 			goto out_free_namelist;
 
@@ -216,7 +224,7 @@ out_free_threads:
 
 struct thread_map *thread_map__new_dummy(void)
 {
-	struct thread_map *threads = malloc(sizeof(*threads) + sizeof(pid_t));
+	struct thread_map *threads = thread_map__alloc(1);
 
 	if (threads != NULL) {
 		threads->map[0]	= -1;
@@ -253,7 +261,7 @@ static struct thread_map *thread_map__new_by_tid_str(const char *tid_str)
 			continue;
 
 		ntasks++;
-		nt = realloc(threads, sizeof(*threads) + sizeof(pid_t) * ntasks);
+		nt = thread_map__realloc(threads, ntasks);
 
 		if (nt == NULL)
 			goto out_free_threads;
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index 51d9e56c0f84..c307dd438286 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -3,6 +3,8 @@
 
 #include <stdbool.h>
 
+#include <linux/types.h>
+
 struct perf_session;
 union perf_event;
 struct perf_evlist;
@@ -29,6 +31,9 @@ typedef int (*event_op2)(struct perf_tool *tool, union perf_event *event,
 typedef int (*event_oe)(struct perf_tool *tool, union perf_event *event,
 			struct ordered_events *oe);
 
+typedef s64 (*event_op3)(struct perf_tool *tool, union perf_event *event,
+			 struct perf_session *session);
+
 struct perf_tool {
 	event_sample	sample,
 			read;
@@ -38,13 +43,19 @@ struct perf_tool {
 			fork,
 			exit,
 			lost,
+			lost_samples,
+			aux,
+			itrace_start,
 			throttle,
 			unthrottle;
 	event_attr_op	attr;
 	event_op2	tracing_data;
 	event_oe	finished_round;
 	event_op2	build_id,
-			id_index;
+			id_index,
+			auxtrace_info,
+			auxtrace_error;
+	event_op3	auxtrace;
 	bool		ordered_events;
 	bool		ordering_requires_timestamps;
 };
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index 25d6c737be3e..d4957418657e 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -173,7 +173,7 @@ void parse_ftrace_printk(struct pevent *pevent,
 	char *line;
 	char *next = NULL;
 	char *addr_str;
-	char *fmt;
+	char *fmt = NULL;
 
 	line = strtok_r(file, "\n", &next);
 	while (line) {
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index 7b09a443a280..4c00507ee3fd 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -269,13 +269,14 @@ static int read_unwind_spec_eh_frame(struct dso *dso, struct machine *machine,
 	u64 offset = dso->data.eh_frame_hdr_offset;
 
 	if (offset == 0) {
-		fd = dso__data_fd(dso, machine);
+		fd = dso__data_get_fd(dso, machine);
 		if (fd < 0)
 			return -EINVAL;
 
 		/* Check the .eh_frame section for unwinding info */
 		offset = elf_section_offset(fd, ".eh_frame_hdr");
 		dso->data.eh_frame_hdr_offset = offset;
+		dso__data_put_fd(dso);
 	}
 
 	if (offset)
@@ -294,13 +295,14 @@ static int read_unwind_spec_debug_frame(struct dso *dso,
 	u64 ofs = dso->data.debug_frame_offset;
 
 	if (ofs == 0) {
-		fd = dso__data_fd(dso, machine);
+		fd = dso__data_get_fd(dso, machine);
 		if (fd < 0)
 			return -EINVAL;
 
 		/* Check the .debug_frame section for unwinding info */
 		ofs = elf_section_offset(fd, ".debug_frame");
 		dso->data.debug_frame_offset = ofs;
+		dso__data_put_fd(dso);
 	}
 
 	*offset = ofs;
@@ -353,10 +355,13 @@ find_proc_info(unw_addr_space_t as, unw_word_t ip, unw_proc_info_t *pi,
 #ifndef NO_LIBUNWIND_DEBUG_FRAME
 	/* Check the .debug_frame section for unwinding info */
 	if (!read_unwind_spec_debug_frame(map->dso, ui->machine, &segbase)) {
-		int fd = dso__data_fd(map->dso, ui->machine);
+		int fd = dso__data_get_fd(map->dso, ui->machine);
 		int is_exec = elf_is_exec(fd, map->dso->name);
 		unw_word_t base = is_exec ? 0 : map->start;
 
+		if (fd >= 0)
+			dso__data_put_fd(map->dso);
+
 		memset(&di, 0, sizeof(di));
 		if (dwarf_find_debug_frame(0, &di, ip, base, map->dso->name,
 					   map->start, map->end))
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 4ee6d0d4c993..edc2d633b332 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -72,20 +72,60 @@ int mkdir_p(char *path, mode_t mode)
 	return (stat(path, &st) && mkdir(path, mode)) ? -1 : 0;
 }
 
-static int slow_copyfile(const char *from, const char *to, mode_t mode)
+int rm_rf(char *path)
+{
+	DIR *dir;
+	int ret = 0;
+	struct dirent *d;
+	char namebuf[PATH_MAX];
+
+	dir = opendir(path);
+	if (dir == NULL)
+		return 0;
+
+	while ((d = readdir(dir)) != NULL && !ret) {
+		struct stat statbuf;
+
+		if (!strcmp(d->d_name, ".") || !strcmp(d->d_name, ".."))
+			continue;
+
+		scnprintf(namebuf, sizeof(namebuf), "%s/%s",
+			  path, d->d_name);
+
+		ret = stat(namebuf, &statbuf);
+		if (ret < 0) {
+			pr_debug("stat failed: %s\n", namebuf);
+			break;
+		}
+
+		if (S_ISREG(statbuf.st_mode))
+			ret = unlink(namebuf);
+		else if (S_ISDIR(statbuf.st_mode))
+			ret = rm_rf(namebuf);
+		else {
+			pr_debug("unknown file: %s\n", namebuf);
+			ret = -1;
+		}
+	}
+	closedir(dir);
+
+	if (ret < 0)
+		return ret;
+
+	return rmdir(path);
+}
+
+static int slow_copyfile(const char *from, const char *to)
 {
 	int err = -1;
 	char *line = NULL;
 	size_t n;
 	FILE *from_fp = fopen(from, "r"), *to_fp;
-	mode_t old_umask;
 
 	if (from_fp == NULL)
 		goto out;
 
-	old_umask = umask(mode ^ 0777);
 	to_fp = fopen(to, "w");
-	umask(old_umask);
 	if (to_fp == NULL)
 		goto out_fclose_from;
 
@@ -102,42 +142,81 @@ out:
 	return err;
 }
 
+int copyfile_offset(int ifd, loff_t off_in, int ofd, loff_t off_out, u64 size)
+{
+	void *ptr;
+	loff_t pgoff;
+
+	pgoff = off_in & ~(page_size - 1);
+	off_in -= pgoff;
+
+	ptr = mmap(NULL, off_in + size, PROT_READ, MAP_PRIVATE, ifd, pgoff);
+	if (ptr == MAP_FAILED)
+		return -1;
+
+	while (size) {
+		ssize_t ret = pwrite(ofd, ptr + off_in, size, off_out);
+		if (ret < 0 && errno == EINTR)
+			continue;
+		if (ret <= 0)
+			break;
+
+		size -= ret;
+		off_in += ret;
+		off_out -= ret;
+	}
+	munmap(ptr, off_in + size);
+
+	return size ? -1 : 0;
+}
+
 int copyfile_mode(const char *from, const char *to, mode_t mode)
 {
 	int fromfd, tofd;
 	struct stat st;
-	void *addr;
 	int err = -1;
+	char *tmp = NULL, *ptr = NULL;
 
 	if (stat(from, &st))
 		goto out;
 
-	if (st.st_size == 0) /* /proc? do it slowly... */
-		return slow_copyfile(from, to, mode);
-
-	fromfd = open(from, O_RDONLY);
-	if (fromfd < 0)
+	/* extra 'x' at the end is to reserve space for '.' */
+	if (asprintf(&tmp, "%s.XXXXXXx", to) < 0) {
+		tmp = NULL;
 		goto out;
+	}
+	ptr = strrchr(tmp, '/');
+	if (!ptr)
+		goto out;
+	ptr = memmove(ptr + 1, ptr, strlen(ptr) - 1);
+	*ptr = '.';
 
-	tofd = creat(to, mode);
+	tofd = mkstemp(tmp);
 	if (tofd < 0)
-		goto out_close_from;
+		goto out;
+
+	if (fchmod(tofd, mode))
+		goto out_close_to;
+
+	if (st.st_size == 0) { /* /proc? do it slowly... */
+		err = slow_copyfile(from, tmp);
+		goto out_close_to;
+	}
 
-	addr = mmap(NULL, st.st_size, PROT_READ, MAP_PRIVATE, fromfd, 0);
-	if (addr == MAP_FAILED)
+	fromfd = open(from, O_RDONLY);
+	if (fromfd < 0)
 		goto out_close_to;
 
-	if (write(tofd, addr, st.st_size) == st.st_size)
-		err = 0;
+	err = copyfile_offset(fromfd, 0, tofd, 0, st.st_size);
 
-	munmap(addr, st.st_size);
+	close(fromfd);
 out_close_to:
 	close(tofd);
-	if (err)
-		unlink(to);
-out_close_from:
-	close(fromfd);
+	if (!err)
+		err = link(tmp, to);
+	unlink(tmp);
 out:
+	free(tmp);
 	return err;
 }
 
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 1ff23e04ad27..8bce58b47a82 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -249,14 +249,20 @@ static inline int sane_case(int x, int high)
 }
 
 int mkdir_p(char *path, mode_t mode);
+int rm_rf(char *path);
 int copyfile(const char *from, const char *to);
 int copyfile_mode(const char *from, const char *to, mode_t mode);
+int copyfile_offset(int fromfd, loff_t from_ofs, int tofd, loff_t to_ofs, u64 size);
 
 s64 perf_atoll(const char *str);
 char **argv_split(const char *str, int *argcp);
 void argv_free(char **argv);
 bool strglobmatch(const char *str, const char *pat);
 bool strlazymatch(const char *str, const char *pat);
+static inline bool strisglob(const char *str)
+{
+	return strpbrk(str, "*?[") != NULL;
+}
 int strtailcmp(const char *s1, const char *s2);
 char *strxfrchar(char *s, char from, char to);
 unsigned long convert_unit(unsigned long value, char *unit);
diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
index 5c7dd796979d..4b89118f158d 100644
--- a/tools/perf/util/vdso.c
+++ b/tools/perf/util/vdso.c
@@ -101,7 +101,7 @@ static char *get_file(struct vdso_file *vdso_file)
 	return vdso;
 }
 
-void vdso__exit(struct machine *machine)
+void machine__exit_vdso(struct machine *machine)
 {
 	struct vdso_info *vdso_info = machine->vdso_info;
 
@@ -120,14 +120,14 @@ void vdso__exit(struct machine *machine)
 	zfree(&machine->vdso_info);
 }
 
-static struct dso *vdso__new(struct machine *machine, const char *short_name,
-			     const char *long_name)
+static struct dso *__machine__addnew_vdso(struct machine *machine, const char *short_name,
+					  const char *long_name)
 {
 	struct dso *dso;
 
 	dso = dso__new(short_name);
 	if (dso != NULL) {
-		dsos__add(&machine->user_dsos, dso);
+		__dsos__add(&machine->dsos, dso);
 		dso__set_long_name(dso, long_name, false);
 	}
 
@@ -230,27 +230,31 @@ static const char *vdso__get_compat_file(struct vdso_file *vdso_file)
 	return vdso_file->temp_file_name;
 }
 
-static struct dso *vdso__findnew_compat(struct machine *machine,
-					struct vdso_file *vdso_file)
+static struct dso *__machine__findnew_compat(struct machine *machine,
+					     struct vdso_file *vdso_file)
 {
 	const char *file_name;
 	struct dso *dso;
 
-	dso = dsos__find(&machine->user_dsos, vdso_file->dso_name, true);
+	pthread_rwlock_wrlock(&machine->dsos.lock);
+	dso = __dsos__find(&machine->dsos, vdso_file->dso_name, true);
 	if (dso)
-		return dso;
+		goto out_unlock;
 
 	file_name = vdso__get_compat_file(vdso_file);
 	if (!file_name)
-		return NULL;
+		goto out_unlock;
 
-	return vdso__new(machine, vdso_file->dso_name, file_name);
+	dso = __machine__addnew_vdso(machine, vdso_file->dso_name, file_name);
+out_unlock:
+	pthread_rwlock_unlock(&machine->dsos.lock);
+	return dso;
 }
 
-static int vdso__dso_findnew_compat(struct machine *machine,
-				    struct thread *thread,
-				    struct vdso_info *vdso_info,
-				    struct dso **dso)
+static int __machine__findnew_vdso_compat(struct machine *machine,
+					  struct thread *thread,
+					  struct vdso_info *vdso_info,
+					  struct dso **dso)
 {
 	enum dso_type dso_type;
 
@@ -267,10 +271,10 @@ static int vdso__dso_findnew_compat(struct machine *machine,
 
 	switch (dso_type) {
 	case DSO__TYPE_32BIT:
-		*dso = vdso__findnew_compat(machine, &vdso_info->vdso32);
+		*dso = __machine__findnew_compat(machine, &vdso_info->vdso32);
 		return 1;
 	case DSO__TYPE_X32BIT:
-		*dso = vdso__findnew_compat(machine, &vdso_info->vdsox32);
+		*dso = __machine__findnew_compat(machine, &vdso_info->vdsox32);
 		return 1;
 	case DSO__TYPE_UNKNOWN:
 	case DSO__TYPE_64BIT:
@@ -281,35 +285,37 @@ static int vdso__dso_findnew_compat(struct machine *machine,
 
 #endif
 
-struct dso *vdso__dso_findnew(struct machine *machine,
-			      struct thread *thread __maybe_unused)
+struct dso *machine__findnew_vdso(struct machine *machine,
+				  struct thread *thread __maybe_unused)
 {
 	struct vdso_info *vdso_info;
-	struct dso *dso;
+	struct dso *dso = NULL;
 
+	pthread_rwlock_wrlock(&machine->dsos.lock);
 	if (!machine->vdso_info)
 		machine->vdso_info = vdso_info__new();
 
 	vdso_info = machine->vdso_info;
 	if (!vdso_info)
-		return NULL;
+		goto out_unlock;
 
 #if BITS_PER_LONG == 64
-	if (vdso__dso_findnew_compat(machine, thread, vdso_info, &dso))
-		return dso;
+	if (__machine__findnew_vdso_compat(machine, thread, vdso_info, &dso))
+		goto out_unlock;
 #endif
 
-	dso = dsos__find(&machine->user_dsos, DSO__NAME_VDSO, true);
+	dso = __dsos__find(&machine->dsos, DSO__NAME_VDSO, true);
 	if (!dso) {
 		char *file;
 
 		file = get_file(&vdso_info->vdso);
-		if (!file)
-			return NULL;
-
-		dso = vdso__new(machine, DSO__NAME_VDSO, file);
+		if (file)
+			dso = __machine__addnew_vdso(machine, DSO__NAME_VDSO, file);
 	}
 
+out_unlock:
+	dso__get(dso);
+	pthread_rwlock_unlock(&machine->dsos.lock);
 	return dso;
 }
 
diff --git a/tools/perf/util/vdso.h b/tools/perf/util/vdso.h
index d97da1616f0c..cdc4fabfc212 100644
--- a/tools/perf/util/vdso.h
+++ b/tools/perf/util/vdso.h
@@ -23,7 +23,7 @@ bool dso__is_vdso(struct dso *dso);
 struct machine;
 struct thread;
 
-struct dso *vdso__dso_findnew(struct machine *machine, struct thread *thread);
-void vdso__exit(struct machine *machine);
+struct dso *machine__findnew_vdso(struct machine *machine, struct thread *thread);
+void machine__exit_vdso(struct machine *machine);
 
 #endif /* __PERF_VDSO__ */
diff --git a/tools/perf/util/xyarray.c b/tools/perf/util/xyarray.c
index 22afbf6c536a..c10ba41ef3f6 100644
--- a/tools/perf/util/xyarray.c
+++ b/tools/perf/util/xyarray.c
@@ -9,11 +9,19 @@ struct xyarray *xyarray__new(int xlen, int ylen, size_t entry_size)
 	if (xy != NULL) {
 		xy->entry_size = entry_size;
 		xy->row_size   = row_size;
+		xy->entries    = xlen * ylen;
 	}
 
 	return xy;
 }
 
+void xyarray__reset(struct xyarray *xy)
+{
+	size_t n = xy->entries * xy->entry_size;
+
+	memset(xy->contents, 0, n);
+}
+
 void xyarray__delete(struct xyarray *xy)
 {
 	free(xy);
diff --git a/tools/perf/util/xyarray.h b/tools/perf/util/xyarray.h
index c488a07275dd..7f30af371b7e 100644
--- a/tools/perf/util/xyarray.h
+++ b/tools/perf/util/xyarray.h
@@ -6,11 +6,13 @@
 struct xyarray {
 	size_t row_size;
 	size_t entry_size;
+	size_t entries;
 	char contents[];
 };
 
 struct xyarray *xyarray__new(int xlen, int ylen, size_t entry_size);
 void xyarray__delete(struct xyarray *xy);
+void xyarray__reset(struct xyarray *xy);
 
 static inline void *xyarray__entry(struct xyarray *xy, int x, int y)
 {
diff --git a/tools/power/x86/turbostat/Makefile b/tools/power/x86/turbostat/Makefile
index 4039854560d0..e367b1a85d70 100644
--- a/tools/power/x86/turbostat/Makefile
+++ b/tools/power/x86/turbostat/Makefile
@@ -9,7 +9,7 @@ endif
 
 turbostat : turbostat.c
 CFLAGS +=	-Wall
-CFLAGS +=	-DMSRHEADER='"../../../../arch/x86/include/uapi/asm/msr-index.h"'
+CFLAGS +=	-DMSRHEADER='"../../../../arch/x86/include/asm/msr-index.h"'
 
 %: %.c
 	@mkdir -p $(BUILD_OUTPUT)
diff --git a/tools/testing/selftests/rcutorture/bin/configinit.sh b/tools/testing/selftests/rcutorture/bin/configinit.sh
index 15f1a17ca96e..3f81a1095206 100755
--- a/tools/testing/selftests/rcutorture/bin/configinit.sh
+++ b/tools/testing/selftests/rcutorture/bin/configinit.sh
@@ -66,7 +66,7 @@ make $buildloc $TORTURE_DEFCONFIG > $builddir/Make.defconfig.out 2>&1
 mv $builddir/.config $builddir/.config.sav
 sh $T/upd.sh < $builddir/.config.sav > $builddir/.config
 cp $builddir/.config $builddir/.config.new
-yes '' | make $buildloc oldconfig > $builddir/Make.modconfig.out 2>&1
+yes '' | make $buildloc oldconfig > $builddir/Make.oldconfig.out 2> $builddir/Make.oldconfig.err
 
 # verify new config matches specification.
 configcheck.sh $builddir/.config $c
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
index 4f5b20f367a9..d86bdd6b6cc2 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
@@ -43,6 +43,10 @@ do
 		if test -f "$i/console.log"
 		then
 			configcheck.sh $i/.config $i/ConfigFragment
+			if test -r $i/Make.oldconfig.err
+			then
+				cat $i/Make.oldconfig.err
+			fi
 			parse-build.sh $i/Make.out $configfile
 			parse-torture.sh $i/console.log $configfile
 			parse-console.sh $i/console.log $configfile
diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
index dd2812ceb0ba..fbe2dbff1e21 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm.sh
@@ -55,7 +55,7 @@ usage () {
 	echo "       --bootargs kernel-boot-arguments"
 	echo "       --bootimage relative-path-to-kernel-boot-image"
 	echo "       --buildonly"
-	echo "       --configs \"config-file list\""
+	echo "       --configs \"config-file list w/ repeat factor (3*TINY01)\""
 	echo "       --cpus N"
 	echo "       --datestamp string"
 	echo "       --defconfig string"
@@ -178,13 +178,26 @@ fi
 touch $T/cfgcpu
 for CF in $configs
 do
-	if test -f "$CONFIGFRAG/$CF"
+	case $CF in
+	[0-9]\**|[0-9][0-9]\**|[0-9][0-9][0-9]\**)
+		config_reps=`echo $CF | sed -e 's/\*.*$//'`
+		CF1=`echo $CF | sed -e 's/^[^*]*\*//'`
+		;;
+	*)
+		config_reps=1
+		CF1=$CF
+		;;
+	esac
+	if test -f "$CONFIGFRAG/$CF1"
 	then
-		cpu_count=`configNR_CPUS.sh $CONFIGFRAG/$CF`
-		cpu_count=`configfrag_boot_cpus "$TORTURE_BOOTARGS" "$CONFIGFRAG/$CF" "$cpu_count"`
-		echo $CF $cpu_count >> $T/cfgcpu
+		cpu_count=`configNR_CPUS.sh $CONFIGFRAG/$CF1`
+		cpu_count=`configfrag_boot_cpus "$TORTURE_BOOTARGS" "$CONFIGFRAG/$CF1" "$cpu_count"`
+		for ((cur_rep=0;cur_rep<$config_reps;cur_rep++))
+		do
+			echo $CF1 $cpu_count >> $T/cfgcpu
+		done
 	else
-		echo "The --configs file $CF does not exist, terminating."
+		echo "The --configs file $CF1 does not exist, terminating."
 		exit 1
 	fi
 done
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/CFcommon b/tools/testing/selftests/rcutorture/configs/rcu/CFcommon
index 49701218dc62..f824b4c9d9d9 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/CFcommon
+++ b/tools/testing/selftests/rcutorture/configs/rcu/CFcommon
@@ -1,3 +1,5 @@
 CONFIG_RCU_TORTURE_TEST=y
 CONFIG_PRINTK_TIME=y
+CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP=y
 CONFIG_RCU_TORTURE_TEST_SLOW_INIT=y
+CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N
index 9fbb41b9b314..1a087c3c8bb8 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N
+++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N
@@ -5,3 +5,4 @@ CONFIG_HOTPLUG_CPU=y
 CONFIG_PREEMPT_NONE=y
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=n
+CONFIG_RCU_EXPERT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P
index 4b6f272dba27..4837430a71c0 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P
+++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P
@@ -5,3 +5,4 @@ CONFIG_HOTPLUG_CPU=y
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
+#CHECK#CONFIG_RCU_EXPERT=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P.boot b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P.boot
index 238bfe3bd0cc..84a7d51b7481 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P.boot
+++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P.boot
@@ -1 +1 @@
-rcutorture.torture_type=srcu
+rcutorture.torture_type=srcud
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS01 b/tools/testing/selftests/rcutorture/configs/rcu/TASKS01
index 97f0a0b27ef7..2cc0e60eba6e 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TASKS01
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS01
@@ -5,5 +5,6 @@ CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
 CONFIG_DEBUG_LOCK_ALLOC=y
-CONFIG_PROVE_RCU=y
-CONFIG_TASKS_RCU=y
+CONFIG_PROVE_LOCKING=n
+#CHECK#CONFIG_PROVE_RCU=n
+CONFIG_RCU_EXPERT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS02 b/tools/testing/selftests/rcutorture/configs/rcu/TASKS02
index 696d2ea74d13..ad2be91e5ee7 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TASKS02
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS02
@@ -2,4 +2,3 @@ CONFIG_SMP=n
 CONFIG_PREEMPT_NONE=y
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=n
-CONFIG_TASKS_RCU=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS03 b/tools/testing/selftests/rcutorture/configs/rcu/TASKS03
index 9c60da5b5d1d..c70c51d5ded1 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TASKS03
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS03
@@ -6,8 +6,8 @@ CONFIG_HIBERNATION=n
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
-CONFIG_TASKS_RCU=y
 CONFIG_HZ_PERIODIC=n
 CONFIG_NO_HZ_IDLE=n
 CONFIG_NO_HZ_FULL=y
 CONFIG_NO_HZ_FULL_ALL=y
+#CHECK#CONFIG_RCU_EXPERT=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TINY02 b/tools/testing/selftests/rcutorture/configs/rcu/TINY02
index 36e41df3d27a..f1892e0371c9 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TINY02
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TINY02
@@ -8,7 +8,7 @@ CONFIG_NO_HZ_IDLE=n
 CONFIG_NO_HZ_FULL=n
 CONFIG_RCU_TRACE=y
 CONFIG_PROVE_LOCKING=y
-CONFIG_PROVE_RCU=y
+#CHECK#CONFIG_PROVE_RCU=y
 CONFIG_DEBUG_LOCK_ALLOC=y
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
 CONFIG_PREEMPT_COUNT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TINY02.boot b/tools/testing/selftests/rcutorture/configs/rcu/TINY02.boot
index 0f0802730014..6c1a292a65fb 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TINY02.boot
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TINY02.boot
@@ -1,2 +1,3 @@
 rcupdate.rcu_self_test=1
 rcupdate.rcu_self_test_bh=1
+rcutorture.torture_type=rcu_bh
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE01 b/tools/testing/selftests/rcutorture/configs/rcu/TREE01
index f8a10a7500c6..8e9137f66831 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE01
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE01
@@ -16,3 +16,4 @@ CONFIG_DEBUG_LOCK_ALLOC=n
 CONFIG_RCU_CPU_STALL_INFO=n
 CONFIG_RCU_BOOST=n
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+CONFIG_RCU_EXPERT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE02 b/tools/testing/selftests/rcutorture/configs/rcu/TREE02
index 629122fb8b4a..aeea6a204d14 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE02
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE02
@@ -14,10 +14,10 @@ CONFIG_SUSPEND=n
 CONFIG_HIBERNATION=n
 CONFIG_RCU_FANOUT=3
 CONFIG_RCU_FANOUT_LEAF=3
-CONFIG_RCU_FANOUT_EXACT=n
 CONFIG_RCU_NOCB_CPU=n
 CONFIG_DEBUG_LOCK_ALLOC=y
 CONFIG_PROVE_LOCKING=n
 CONFIG_RCU_CPU_STALL_INFO=n
 CONFIG_RCU_BOOST=n
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+CONFIG_RCU_EXPERT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE02-T b/tools/testing/selftests/rcutorture/configs/rcu/TREE02-T
index a25de47888a4..2ac9e68ea3d1 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE02-T
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE02-T
@@ -14,7 +14,6 @@ CONFIG_SUSPEND=n
 CONFIG_HIBERNATION=n
 CONFIG_RCU_FANOUT=3
 CONFIG_RCU_FANOUT_LEAF=3
-CONFIG_RCU_FANOUT_EXACT=n
 CONFIG_RCU_NOCB_CPU=n
 CONFIG_DEBUG_LOCK_ALLOC=y
 CONFIG_PROVE_LOCKING=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE03 b/tools/testing/selftests/rcutorture/configs/rcu/TREE03
index 53f24e0a0ab6..72aa7d87ea99 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE03
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE03
@@ -1,5 +1,5 @@
 CONFIG_SMP=y
-CONFIG_NR_CPUS=8
+CONFIG_NR_CPUS=16
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
@@ -9,12 +9,12 @@ CONFIG_NO_HZ_IDLE=n
 CONFIG_NO_HZ_FULL=n
 CONFIG_RCU_TRACE=y
 CONFIG_HOTPLUG_CPU=y
-CONFIG_RCU_FANOUT=4
-CONFIG_RCU_FANOUT_LEAF=4
-CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_RCU_FANOUT=2
+CONFIG_RCU_FANOUT_LEAF=2
 CONFIG_RCU_NOCB_CPU=n
 CONFIG_DEBUG_LOCK_ALLOC=n
 CONFIG_RCU_CPU_STALL_INFO=n
 CONFIG_RCU_BOOST=y
 CONFIG_RCU_KTHREAD_PRIO=2
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+CONFIG_RCU_EXPERT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot
new file mode 100644
index 000000000000..120c0c88d100
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot
@@ -0,0 +1 @@
+rcutorture.onoff_interval=1 rcutorture.onoff_holdoff=30
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE04 b/tools/testing/selftests/rcutorture/configs/rcu/TREE04
index 0f84db35b36d..3f5112751cda 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE04
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE04
@@ -13,10 +13,10 @@ CONFIG_RCU_TRACE=y
 CONFIG_HOTPLUG_CPU=n
 CONFIG_SUSPEND=n
 CONFIG_HIBERNATION=n
-CONFIG_RCU_FANOUT=2
-CONFIG_RCU_FANOUT_LEAF=2
-CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_RCU_FANOUT=4
+CONFIG_RCU_FANOUT_LEAF=4
 CONFIG_RCU_NOCB_CPU=n
 CONFIG_DEBUG_LOCK_ALLOC=n
-CONFIG_RCU_CPU_STALL_INFO=y
+CONFIG_RCU_CPU_STALL_INFO=n
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+CONFIG_RCU_EXPERT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE05 b/tools/testing/selftests/rcutorture/configs/rcu/TREE05
index 212e3bfd2b2a..c04dfea6fd21 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE05
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE05
@@ -12,11 +12,11 @@ CONFIG_RCU_TRACE=n
 CONFIG_HOTPLUG_CPU=y
 CONFIG_RCU_FANOUT=6
 CONFIG_RCU_FANOUT_LEAF=6
-CONFIG_RCU_FANOUT_EXACT=n
 CONFIG_RCU_NOCB_CPU=y
 CONFIG_RCU_NOCB_CPU_NONE=y
 CONFIG_DEBUG_LOCK_ALLOC=y
 CONFIG_PROVE_LOCKING=y
-CONFIG_PROVE_RCU=y
+#CHECK#CONFIG_PROVE_RCU=y
 CONFIG_RCU_CPU_STALL_INFO=n
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+CONFIG_RCU_EXPERT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE06 b/tools/testing/selftests/rcutorture/configs/rcu/TREE06
index 7eee63b44218..f51d2c73a68e 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE06
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE06
@@ -14,10 +14,10 @@ CONFIG_SUSPEND=n
 CONFIG_HIBERNATION=n
 CONFIG_RCU_FANOUT=6
 CONFIG_RCU_FANOUT_LEAF=6
-CONFIG_RCU_FANOUT_EXACT=y
 CONFIG_RCU_NOCB_CPU=n
 CONFIG_DEBUG_LOCK_ALLOC=y
 CONFIG_PROVE_LOCKING=y
-CONFIG_PROVE_RCU=y
+#CHECK#CONFIG_PROVE_RCU=y
 CONFIG_RCU_CPU_STALL_INFO=n
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
+CONFIG_RCU_EXPERT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE06.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE06.boot
index da9a03a398db..dd90f28ed700 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE06.boot
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE06.boot
@@ -1,3 +1,4 @@
 rcupdate.rcu_self_test=1
 rcupdate.rcu_self_test_bh=1
 rcupdate.rcu_self_test_sched=1
+rcutree.rcu_fanout_exact=1
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE07 b/tools/testing/selftests/rcutorture/configs/rcu/TREE07
index 92a97fa97dec..f422af4ff5a3 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE07
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE07
@@ -15,8 +15,8 @@ CONFIG_RCU_TRACE=y
 CONFIG_HOTPLUG_CPU=y
 CONFIG_RCU_FANOUT=2
 CONFIG_RCU_FANOUT_LEAF=2
-CONFIG_RCU_FANOUT_EXACT=n
 CONFIG_RCU_NOCB_CPU=n
 CONFIG_DEBUG_LOCK_ALLOC=n
-CONFIG_RCU_CPU_STALL_INFO=y
+CONFIG_RCU_CPU_STALL_INFO=n
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+CONFIG_RCU_EXPERT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE08 b/tools/testing/selftests/rcutorture/configs/rcu/TREE08
index 5812027d6f9f..a24d2ca30646 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE08
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE08
@@ -1,5 +1,5 @@
 CONFIG_SMP=y
-CONFIG_NR_CPUS=16
+CONFIG_NR_CPUS=8
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
@@ -13,13 +13,13 @@ CONFIG_HOTPLUG_CPU=n
 CONFIG_SUSPEND=n
 CONFIG_HIBERNATION=n
 CONFIG_RCU_FANOUT=3
-CONFIG_RCU_FANOUT_EXACT=y
 CONFIG_RCU_FANOUT_LEAF=2
 CONFIG_RCU_NOCB_CPU=y
 CONFIG_RCU_NOCB_CPU_ALL=y
 CONFIG_DEBUG_LOCK_ALLOC=n
 CONFIG_PROVE_LOCKING=y
-CONFIG_PROVE_RCU=y
+#CHECK#CONFIG_PROVE_RCU=y
 CONFIG_RCU_CPU_STALL_INFO=n
 CONFIG_RCU_BOOST=n
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+CONFIG_RCU_EXPERT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T b/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T
index 3eaeccacb083..b2b8cea69dc9 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T
@@ -13,7 +13,6 @@ CONFIG_HOTPLUG_CPU=n
 CONFIG_SUSPEND=n
 CONFIG_HIBERNATION=n
 CONFIG_RCU_FANOUT=3
-CONFIG_RCU_FANOUT_EXACT=y
 CONFIG_RCU_FANOUT_LEAF=2
 CONFIG_RCU_NOCB_CPU=y
 CONFIG_RCU_NOCB_CPU_ALL=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T.boot
new file mode 100644
index 000000000000..883149b5f2d1
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T.boot
@@ -0,0 +1 @@
+rcutree.rcu_fanout_exact=1
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE08.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE08.boot
index 2561daf605ad..fb066dc82769 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE08.boot
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE08.boot
@@ -1,3 +1,4 @@
 rcutorture.torture_type=sched
 rcupdate.rcu_self_test=1
 rcupdate.rcu_self_test_sched=1
+rcutree.rcu_fanout_exact=1
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE09 b/tools/testing/selftests/rcutorture/configs/rcu/TREE09
index 6076b36f6c0b..aa4ed08d999d 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE09
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE09
@@ -16,3 +16,4 @@ CONFIG_DEBUG_LOCK_ALLOC=n
 CONFIG_RCU_CPU_STALL_INFO=n
 CONFIG_RCU_BOOST=n
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+#CHECK#CONFIG_RCU_EXPERT=n
diff --git a/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt b/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt
index ec03c883db00..b24c0004fc49 100644
--- a/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt
+++ b/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt
@@ -12,13 +12,12 @@ CONFIG_NO_HZ_IDLE -- Do those not otherwise specified. (Groups of two.)
 CONFIG_NO_HZ_FULL -- Do two, one with CONFIG_NO_HZ_FULL_SYSIDLE.
 CONFIG_NO_HZ_FULL_SYSIDLE -- Do one.
 CONFIG_PREEMPT -- Do half.  (First three and #8.)
-CONFIG_PROVE_LOCKING -- Do all but two, covering CONFIG_PROVE_RCU and not.
-CONFIG_PROVE_RCU -- Do all but one under CONFIG_PROVE_LOCKING.
+CONFIG_PROVE_LOCKING -- Do several, covering CONFIG_DEBUG_LOCK_ALLOC=y and not.
+CONFIG_PROVE_RCU -- Hardwired to CONFIG_PROVE_LOCKING.
 CONFIG_RCU_BOOST -- one of PREEMPT_RCU.
 CONFIG_RCU_KTHREAD_PRIO -- set to 2 for _BOOST testing.
-CONFIG_RCU_CPU_STALL_INFO -- Do one.
-CONFIG_RCU_FANOUT -- Cover hierarchy as currently, but overlap with others.
-CONFIG_RCU_FANOUT_EXACT -- Do one.
+CONFIG_RCU_CPU_STALL_INFO -- Now default, avoid at least twice.
+CONFIG_RCU_FANOUT -- Cover hierarchy, but overlap with others.
 CONFIG_RCU_FANOUT_LEAF -- Do one non-default.
 CONFIG_RCU_FAST_NO_HZ -- Do one, but not with CONFIG_RCU_NOCB_CPU_ALL.
 CONFIG_RCU_NOCB_CPU -- Do three, see below.
@@ -27,28 +26,19 @@ CONFIG_RCU_NOCB_CPU_NONE -- Do one.
 CONFIG_RCU_NOCB_CPU_ZERO -- Do one.
 CONFIG_RCU_TRACE -- Do half.
 CONFIG_SMP -- Need one !SMP for PREEMPT_RCU.
+!RCU_EXPERT -- Do a few, but these have to be vanilla configurations.
 RCU-bh: Do one with PREEMPT and one with !PREEMPT.
 RCU-sched: Do one with PREEMPT but not BOOST.
 
 
-Hierarchy:
-
-TREE01.	CONFIG_NR_CPUS=8, CONFIG_RCU_FANOUT=8, CONFIG_RCU_FANOUT_EXACT=n.
-TREE02.	CONFIG_NR_CPUS=8, CONFIG_RCU_FANOUT=3, CONFIG_RCU_FANOUT_EXACT=n,
-	CONFIG_RCU_FANOUT_LEAF=3.
-TREE03.	CONFIG_NR_CPUS=8, CONFIG_RCU_FANOUT=4, CONFIG_RCU_FANOUT_EXACT=n,
-	CONFIG_RCU_FANOUT_LEAF=4.
-TREE04.	CONFIG_NR_CPUS=8, CONFIG_RCU_FANOUT=2, CONFIG_RCU_FANOUT_EXACT=n,
-	CONFIG_RCU_FANOUT_LEAF=2.
-TREE05.	CONFIG_NR_CPUS=8, CONFIG_RCU_FANOUT=6, CONFIG_RCU_FANOUT_EXACT=n
-	CONFIG_RCU_FANOUT_LEAF=6.
-TREE06.	CONFIG_NR_CPUS=8, CONFIG_RCU_FANOUT=6, CONFIG_RCU_FANOUT_EXACT=y
-	CONFIG_RCU_FANOUT_LEAF=6.
-TREE07.	CONFIG_NR_CPUS=16, CONFIG_RCU_FANOUT=2, CONFIG_RCU_FANOUT_EXACT=n,
-	CONFIG_RCU_FANOUT_LEAF=2.
-TREE08.	CONFIG_NR_CPUS=16, CONFIG_RCU_FANOUT=3, CONFIG_RCU_FANOUT_EXACT=y,
-	CONFIG_RCU_FANOUT_LEAF=2.
-TREE09.	CONFIG_NR_CPUS=1.
+Boot parameters:
+
+nohz_full - do at least one.
+maxcpu -- do at least one.
+rcupdate.rcu_self_test_bh -- Do at least one each, offloaded and not.
+rcupdate.rcu_self_test_sched -- Do at least one each, offloaded and not.
+rcupdate.rcu_self_test -- Do at least one each, offloaded and not.
+rcutree.rcu_fanout_exact -- Do at least one.
 
 
 Kconfig Parameters Ignored:
diff --git a/tools/testing/selftests/timers/leap-a-day.c b/tools/testing/selftests/timers/leap-a-day.c
index b8272e6c4b3b..fb46ad6ac92c 100644
--- a/tools/testing/selftests/timers/leap-a-day.c
+++ b/tools/testing/selftests/timers/leap-a-day.c
@@ -44,6 +44,7 @@
 #include <time.h>
 #include <sys/time.h>
 #include <sys/timex.h>
+#include <sys/errno.h>
 #include <string.h>
 #include <signal.h>
 #include <unistd.h>
@@ -63,6 +64,9 @@ static inline int ksft_exit_fail(void)
 #define NSEC_PER_SEC 1000000000ULL
 #define CLOCK_TAI 11
 
+time_t next_leap;
+int error_found;
+
 /* returns 1 if a <= b, 0 otherwise */
 static inline int in_order(struct timespec a, struct timespec b)
 {
@@ -134,6 +138,35 @@ void handler(int unused)
 	exit(0);
 }
 
+void sigalarm(int signo)
+{
+	struct timex tx;
+	int ret;
+
+	tx.modes = 0;
+	ret = adjtimex(&tx);
+
+	if (tx.time.tv_sec < next_leap) {
+		printf("Error: Early timer expiration! (Should be %ld)\n", next_leap);
+		error_found = 1;
+		printf("adjtimex: %10ld sec + %6ld us (%i)\t%s\n",
+					tx.time.tv_sec,
+					tx.time.tv_usec,
+					tx.tai,
+					time_state_str(ret));
+	}
+	if (ret != TIME_WAIT) {
+		printf("Error: Timer seeing incorrect NTP state? (Should be TIME_WAIT)\n");
+		error_found = 1;
+		printf("adjtimex: %10ld sec + %6ld us (%i)\t%s\n",
+					tx.time.tv_sec,
+					tx.time.tv_usec,
+					tx.tai,
+					time_state_str(ret));
+	}
+}
+
+
 /* Test for known hrtimer failure */
 void test_hrtimer_failure(void)
 {
@@ -144,12 +177,19 @@ void test_hrtimer_failure(void)
 	clock_nanosleep(CLOCK_REALTIME, TIMER_ABSTIME, &target, NULL);
 	clock_gettime(CLOCK_REALTIME, &now);
 
-	if (!in_order(target, now))
+	if (!in_order(target, now)) {
 		printf("ERROR: hrtimer early expiration failure observed.\n");
+		error_found = 1;
+	}
 }
 
 int main(int argc, char **argv)
 {
+	timer_t tm1;
+	struct itimerspec its1;
+	struct sigevent se;
+	struct sigaction act;
+	int signum = SIGRTMAX;
 	int settime = 0;
 	int tai_time = 0;
 	int insert = 1;
@@ -191,6 +231,12 @@ int main(int argc, char **argv)
 	signal(SIGINT, handler);
 	signal(SIGKILL, handler);
 
+	/* Set up timer signal handler: */
+	sigfillset(&act.sa_mask);
+	act.sa_flags = 0;
+	act.sa_handler = sigalarm;
+	sigaction(signum, &act, NULL);
+
 	if (iterations < 0)
 		printf("This runs continuously. Press ctrl-c to stop\n");
 	else
@@ -201,7 +247,7 @@ int main(int argc, char **argv)
 		int ret;
 		struct timespec ts;
 		struct timex tx;
-		time_t now, next_leap;
+		time_t now;
 
 		/* Get the current time */
 		clock_gettime(CLOCK_REALTIME, &ts);
@@ -251,10 +297,27 @@ int main(int argc, char **argv)
 
 		printf("Scheduling leap second for %s", ctime(&next_leap));
 
+		/* Set up timer */
+		printf("Setting timer for %ld -  %s", next_leap, ctime(&next_leap));
+		memset(&se, 0, sizeof(se));
+		se.sigev_notify = SIGEV_SIGNAL;
+		se.sigev_signo = signum;
+		se.sigev_value.sival_int = 0;
+		if (timer_create(CLOCK_REALTIME, &se, &tm1) == -1) {
+			printf("Error: timer_create failed\n");
+			return ksft_exit_fail();
+		}
+		its1.it_value.tv_sec = next_leap;
+		its1.it_value.tv_nsec = 0;
+		its1.it_interval.tv_sec = 0;
+		its1.it_interval.tv_nsec = 0;
+		timer_settime(tm1, TIMER_ABSTIME, &its1, NULL);
+
 		/* Wake up 3 seconds before leap */
 		ts.tv_sec = next_leap - 3;
 		ts.tv_nsec = 0;
 
+
 		while (clock_nanosleep(CLOCK_REALTIME, TIMER_ABSTIME, &ts, NULL))
 			printf("Something woke us up, returning to sleep\n");
 
@@ -276,6 +339,7 @@ int main(int argc, char **argv)
 		while (now < next_leap + 2) {
 			char buf[26];
 			struct timespec tai;
+			int ret;
 
 			tx.modes = 0;
 			ret = adjtimex(&tx);
@@ -308,8 +372,13 @@ int main(int argc, char **argv)
 		/* Note if kernel has known hrtimer failure */
 		test_hrtimer_failure();
 
-		printf("Leap complete\n\n");
-
+		printf("Leap complete\n");
+		if (error_found) {
+			printf("Errors observed\n");
+			clear_time_state();
+			return ksft_exit_fail();
+		}
+		printf("\n");
 		if ((iterations != -1) && !(--iterations))
 			break;
 	}
diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile
index 9b0d8baf2934..caa60d56d7d1 100644
--- a/tools/testing/selftests/x86/Makefile
+++ b/tools/testing/selftests/x86/Makefile
@@ -4,7 +4,7 @@ include ../lib.mk
 
 .PHONY: all all_32 all_64 warn_32bit_failure clean
 
-TARGETS_C_BOTHBITS := sigreturn single_step_syscall
+TARGETS_C_BOTHBITS := sigreturn single_step_syscall sysret_ss_attrs
 TARGETS_C_32BIT_ONLY := entry_from_vm86
 
 TARGETS_C_32BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_32BIT_ONLY)
@@ -57,3 +57,6 @@ warn_32bit_failure:
 	echo "  yum install glibc-devel.*i686";				\
 	exit 0;
 endif
+
+# Some tests have additional dependencies.
+sysret_ss_attrs_64: thunks.S
diff --git a/tools/testing/selftests/x86/sysret_ss_attrs.c b/tools/testing/selftests/x86/sysret_ss_attrs.c
new file mode 100644
index 000000000000..ce42d5a64009
--- /dev/null
+++ b/tools/testing/selftests/x86/sysret_ss_attrs.c
@@ -0,0 +1,112 @@
+/*
+ * sysret_ss_attrs.c - test that syscalls return valid hidden SS attributes
+ * Copyright (c) 2015 Andrew Lutomirski
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * On AMD CPUs, SYSRET can return with a valid SS descriptor with with
+ * the hidden attributes set to an unusable state.  Make sure the kernel
+ * doesn't let this happen.
+ */
+
+#define _GNU_SOURCE
+
+#include <stdlib.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <string.h>
+#include <sys/mman.h>
+#include <err.h>
+#include <stddef.h>
+#include <stdbool.h>
+#include <pthread.h>
+
+static void *threadproc(void *ctx)
+{
+	/*
+	 * Do our best to cause sleeps on this CPU to exit the kernel and
+	 * re-enter with SS = 0.
+	 */
+	while (true)
+		;
+
+	return NULL;
+}
+
+#ifdef __x86_64__
+extern unsigned long call32_from_64(void *stack, void (*function)(void));
+
+asm (".pushsection .text\n\t"
+     ".code32\n\t"
+     "test_ss:\n\t"
+     "pushl $0\n\t"
+     "popl %eax\n\t"
+     "ret\n\t"
+     ".code64");
+extern void test_ss(void);
+#endif
+
+int main()
+{
+	/*
+	 * Start a busy-looping thread on the same CPU we're on.
+	 * For simplicity, just stick everything to CPU 0.  This will
+	 * fail in some containers, but that's probably okay.
+	 */
+	cpu_set_t cpuset;
+	CPU_ZERO(&cpuset);
+	CPU_SET(0, &cpuset);
+	if (sched_setaffinity(0, sizeof(cpuset), &cpuset) != 0)
+		printf("[WARN]\tsched_setaffinity failed\n");
+
+	pthread_t thread;
+	if (pthread_create(&thread, 0, threadproc, 0) != 0)
+		err(1, "pthread_create");
+
+#ifdef __x86_64__
+	unsigned char *stack32 = mmap(NULL, 4096, PROT_READ | PROT_WRITE,
+				      MAP_32BIT | MAP_ANONYMOUS | MAP_PRIVATE,
+				      -1, 0);
+	if (stack32 == MAP_FAILED)
+		err(1, "mmap");
+#endif
+
+	printf("[RUN]\tSyscalls followed by SS validation\n");
+
+	for (int i = 0; i < 1000; i++) {
+		/*
+		 * Go to sleep and return using sysret (if we're 64-bit
+		 * or we're 32-bit on AMD on a 64-bit kernel).  On AMD CPUs,
+		 * SYSRET doesn't fix up the cached SS descriptor, so the
+		 * kernel needs some kind of workaround to make sure that we
+		 * end the system call with a valid stack segment.  This
+		 * can be a confusing failure because the SS *selector*
+		 * is the same regardless.
+		 */
+		usleep(2);
+
+#ifdef __x86_64__
+		/*
+		 * On 32-bit, just doing a syscall through glibc is enough
+		 * to cause a crash if our cached SS descriptor is invalid.
+		 * On 64-bit, it's not, so try extra hard.
+		 */
+		call32_from_64(stack32 + 4088, test_ss);
+#endif
+	}
+
+	printf("[OK]\tWe survived\n");
+
+#ifdef __x86_64__
+	munmap(stack32, 4096);
+#endif
+
+	return 0;
+}
diff --git a/tools/testing/selftests/x86/thunks.S b/tools/testing/selftests/x86/thunks.S
new file mode 100644
index 000000000000..ce8a995bbb17
--- /dev/null
+++ b/tools/testing/selftests/x86/thunks.S
@@ -0,0 +1,67 @@
+/*
+ * thunks.S - assembly helpers for mixed-bitness code
+ * Copyright (c) 2015 Andrew Lutomirski
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * These are little helpers that make it easier to switch bitness on
+ * the fly.
+ */
+
+	.text
+
+	.global call32_from_64
+	.type call32_from_64, @function
+call32_from_64:
+	// rdi: stack to use
+	// esi: function to call
+
+	// Save registers
+	pushq %rbx
+	pushq %rbp
+	pushq %r12
+	pushq %r13
+	pushq %r14
+	pushq %r15
+	pushfq
+
+	// Switch stacks
+	mov %rsp,(%rdi)
+	mov %rdi,%rsp
+
+	// Switch to compatibility mode
+	pushq $0x23  /* USER32_CS */
+	pushq $1f
+	lretq
+
+1:
+	.code32
+	// Call the function
+	call *%esi
+	// Switch back to long mode
+	jmp $0x33,$1f
+	.code64
+
+1:
+	// Restore the stack
+	mov (%rsp),%rsp
+
+	// Restore registers
+	popfq
+	popq %r15
+	popq %r14
+	popq %r13
+	popq %r12
+	popq %rbp
+	popq %rbx
+
+	ret
+
+.size call32_from_64, .-call32_from_64