Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Minor overlapping changes in xfrm_device.c, between the double
ESP trailing bug fix setting the XFRM_INIT flag and the changes
in net-next preparing for bonding encryption support.

Signed-off-by: David S. Miller <davem@davemloft.net>

191 files changed, 2395 insertions, 1685 deletions

diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 69361ec43db5..b1cd4d97bc2a 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -42,7 +42,6 @@
 #include <linux/workqueue.h>
 #include <linux/scatterlist.h>
 #include <linux/io.h>
-#include <linux/async.h>
 #include <linux/log2.h>
 #include <linux/slab.h>
 #include <linux/glob.h>
@@ -5778,7 +5777,7 @@ int ata_host_register(struct ata_host *host, struct scsi_host_template *sht)
 	/* perform each probe asynchronously */
 	for (i = 0; i < host->n_ports; i++) {
 		struct ata_port *ap = host->ports[i];
-		async_schedule(async_port_probe, ap);
+		ap->cookie = async_schedule(async_port_probe, ap);
 	}
 
 	return 0;
@@ -5920,11 +5919,11 @@ void ata_host_detach(struct ata_host *host)
 {
 	int i;
 
-	/* Ensure ata_port probe has completed */
-	async_synchronize_full();
-
-	for (i = 0; i < host->n_ports; i++)
+	for (i = 0; i < host->n_ports; i++) {
+		/* Ensure ata_port probe has completed */
+		async_synchronize_cookie(host->ports[i]->cookie + 1);
 		ata_port_detach(host->ports[i]);
+	}
 
 	/* the host is dead now, dissociate ACPI */
 	ata_acpi_dissociate(host);
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 435781a16875..46336084b1a9 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -3684,12 +3684,13 @@ static unsigned int ata_scsi_mode_select_xlat(struct ata_queued_cmd *qc)
 {
 	struct scsi_cmnd *scmd = qc->scsicmd;
 	const u8 *cdb = scmd->cmnd;
-	const u8 *p;
 	u8 pg, spg;
 	unsigned six_byte, pg_len, hdr_len, bd_len;
 	int len;
 	u16 fp = (u16)-1;
 	u8 bp = 0xff;
+	u8 buffer[64];
+	const u8 *p = buffer;
 
 	VPRINTK("ENTER\n");
 
@@ -3723,12 +3724,14 @@ static unsigned int ata_scsi_mode_select_xlat(struct ata_queued_cmd *qc)
 	if (!scsi_sg_count(scmd) || scsi_sglist(scmd)->length < len)
 		goto invalid_param_len;
 
-	p = page_address(sg_page(scsi_sglist(scmd)));
-
 	/* Move past header and block descriptors.  */
 	if (len < hdr_len)
 		goto invalid_param_len;
 
+	if (!sg_copy_to_buffer(scsi_sglist(scmd), scsi_sg_count(scmd),
+			       buffer, sizeof(buffer)))
+		goto invalid_param_len;
+
 	if (six_byte)
 		bd_len = p[3];
 	else
diff --git a/drivers/ata/sata_rcar.c b/drivers/ata/sata_rcar.c
index 980aacdbcf3b..141ac600b64c 100644
--- a/drivers/ata/sata_rcar.c
+++ b/drivers/ata/sata_rcar.c
@@ -907,7 +907,7 @@ static int sata_rcar_probe(struct platform_device *pdev)
 	pm_runtime_enable(dev);
 	ret = pm_runtime_get_sync(dev);
 	if (ret < 0)
-		goto err_pm_disable;
+		goto err_pm_put;
 
 	host = ata_host_alloc(dev, 1);
 	if (!host) {
@@ -937,7 +937,6 @@ static int sata_rcar_probe(struct platform_device *pdev)
 
 err_pm_put:
 	pm_runtime_put(dev);
-err_pm_disable:
 	pm_runtime_disable(dev);
 	return ret;
 }
@@ -991,8 +990,10 @@ static int sata_rcar_resume(struct device *dev)
 	int ret;
 
 	ret = pm_runtime_get_sync(dev);
-	if (ret < 0)
+	if (ret < 0) {
+		pm_runtime_put(dev);
 		return ret;
+	}
 
 	if (priv->type == RCAR_GEN3_SATA) {
 		sata_rcar_init_module(priv);
@@ -1017,8 +1018,10 @@ static int sata_rcar_restore(struct device *dev)
 	int ret;
 
 	ret = pm_runtime_get_sync(dev);
-	if (ret < 0)
+	if (ret < 0) {
+		pm_runtime_put(dev);
 		return ret;
+	}
 
 	sata_rcar_setup_port(host);
 
diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index c472f624382d..06a796821e8b 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -17,6 +17,7 @@
 #include <linux/delay.h>
 #include <linux/log2.h>
 #include <linux/hwspinlock.h>
+#include <asm/unaligned.h>
 
 #define CREATE_TRACE_POINTS
 #include "trace.h"
@@ -249,22 +250,20 @@ static void regmap_format_8(void *buf, unsigned int val, unsigned int shift)
 
 static void regmap_format_16_be(void *buf, unsigned int val, unsigned int shift)
 {
-	__be16 *b = buf;
-
-	b[0] = cpu_to_be16(val << shift);
+	put_unaligned_be16(val << shift, buf);
 }
 
 static void regmap_format_16_le(void *buf, unsigned int val, unsigned int shift)
 {
-	__le16 *b = buf;
-
-	b[0] = cpu_to_le16(val << shift);
+	put_unaligned_le16(val << shift, buf);
 }
 
 static void regmap_format_16_native(void *buf, unsigned int val,
 				    unsigned int shift)
 {
-	*(u16 *)buf = val << shift;
+	u16 v = val << shift;
+
+	memcpy(buf, &v, sizeof(v));
 }
 
 static void regmap_format_24(void *buf, unsigned int val, unsigned int shift)
@@ -280,43 +279,39 @@ static void regmap_format_24(void *buf, unsigned int val, unsigned int shift)
 
 static void regmap_format_32_be(void *buf, unsigned int val, unsigned int shift)
 {
-	__be32 *b = buf;
-
-	b[0] = cpu_to_be32(val << shift);
+	put_unaligned_be32(val << shift, buf);
 }
 
 static void regmap_format_32_le(void *buf, unsigned int val, unsigned int shift)
 {
-	__le32 *b = buf;
-
-	b[0] = cpu_to_le32(val << shift);
+	put_unaligned_le32(val << shift, buf);
 }
 
 static void regmap_format_32_native(void *buf, unsigned int val,
 				    unsigned int shift)
 {
-	*(u32 *)buf = val << shift;
+	u32 v = val << shift;
+
+	memcpy(buf, &v, sizeof(v));
 }
 
 #ifdef CONFIG_64BIT
 static void regmap_format_64_be(void *buf, unsigned int val, unsigned int shift)
 {
-	__be64 *b = buf;
-
-	b[0] = cpu_to_be64((u64)val << shift);
+	put_unaligned_be64((u64) val << shift, buf);
 }
 
 static void regmap_format_64_le(void *buf, unsigned int val, unsigned int shift)
 {
-	__le64 *b = buf;
-
-	b[0] = cpu_to_le64((u64)val << shift);
+	put_unaligned_le64((u64) val << shift, buf);
 }
 
 static void regmap_format_64_native(void *buf, unsigned int val,
 				    unsigned int shift)
 {
-	*(u64 *)buf = (u64)val << shift;
+	u64 v = (u64) val << shift;
+
+	memcpy(buf, &v, sizeof(v));
 }
 #endif
 
@@ -333,35 +328,34 @@ static unsigned int regmap_parse_8(const void *buf)
 
 static unsigned int regmap_parse_16_be(const void *buf)
 {
-	const __be16 *b = buf;
-
-	return be16_to_cpu(b[0]);
+	return get_unaligned_be16(buf);
 }
 
 static unsigned int regmap_parse_16_le(const void *buf)
 {
-	const __le16 *b = buf;
-
-	return le16_to_cpu(b[0]);
+	return get_unaligned_le16(buf);
 }
 
 static void regmap_parse_16_be_inplace(void *buf)
 {
-	__be16 *b = buf;
+	u16 v = get_unaligned_be16(buf);
 
-	b[0] = be16_to_cpu(b[0]);
+	memcpy(buf, &v, sizeof(v));
 }
 
 static void regmap_parse_16_le_inplace(void *buf)
 {
-	__le16 *b = buf;
+	u16 v = get_unaligned_le16(buf);
 
-	b[0] = le16_to_cpu(b[0]);
+	memcpy(buf, &v, sizeof(v));
 }
 
 static unsigned int regmap_parse_16_native(const void *buf)
 {
-	return *(u16 *)buf;
+	u16 v;
+
+	memcpy(&v, buf, sizeof(v));
+	return v;
 }
 
 static unsigned int regmap_parse_24(const void *buf)
@@ -376,69 +370,67 @@ static unsigned int regmap_parse_24(const void *buf)
 
 static unsigned int regmap_parse_32_be(const void *buf)
 {
-	const __be32 *b = buf;
-
-	return be32_to_cpu(b[0]);
+	return get_unaligned_be32(buf);
 }
 
 static unsigned int regmap_parse_32_le(const void *buf)
 {
-	const __le32 *b = buf;
-
-	return le32_to_cpu(b[0]);
+	return get_unaligned_le32(buf);
 }
 
 static void regmap_parse_32_be_inplace(void *buf)
 {
-	__be32 *b = buf;
+	u32 v = get_unaligned_be32(buf);
 
-	b[0] = be32_to_cpu(b[0]);
+	memcpy(buf, &v, sizeof(v));
 }
 
 static void regmap_parse_32_le_inplace(void *buf)
 {
-	__le32 *b = buf;
+	u32 v = get_unaligned_le32(buf);
 
-	b[0] = le32_to_cpu(b[0]);
+	memcpy(buf, &v, sizeof(v));
 }
 
 static unsigned int regmap_parse_32_native(const void *buf)
 {
-	return *(u32 *)buf;
+	u32 v;
+
+	memcpy(&v, buf, sizeof(v));
+	return v;
 }
 
 #ifdef CONFIG_64BIT
 static unsigned int regmap_parse_64_be(const void *buf)
 {
-	const __be64 *b = buf;
-
-	return be64_to_cpu(b[0]);
+	return get_unaligned_be64(buf);
 }
 
 static unsigned int regmap_parse_64_le(const void *buf)
 {
-	const __le64 *b = buf;
-
-	return le64_to_cpu(b[0]);
+	return get_unaligned_le64(buf);
 }
 
 static void regmap_parse_64_be_inplace(void *buf)
 {
-	__be64 *b = buf;
+	u64 v =  get_unaligned_be64(buf);
 
-	b[0] = be64_to_cpu(b[0]);
+	memcpy(buf, &v, sizeof(v));
 }
 
 static void regmap_parse_64_le_inplace(void *buf)
 {
-	__le64 *b = buf;
+	u64 v = get_unaligned_le64(buf);
 
-	b[0] = le64_to_cpu(b[0]);
+	memcpy(buf, &v, sizeof(v));
 }
 
 static unsigned int regmap_parse_64_native(const void *buf)
 {
-	return *(u64 *)buf;
+	u64 v;
+
+	memcpy(&v, buf, sizeof(v));
+	return v;
 }
 #endif
 
@@ -1357,6 +1349,7 @@ void regmap_exit(struct regmap *map)
 	if (map->hwlock)
 		hwspin_lock_free(map->hwlock);
 	kfree_const(map->name);
+	kfree(map->patch);
 	kfree(map);
 }
 EXPORT_SYMBOL_GPL(regmap_exit);
@@ -2944,8 +2937,9 @@ EXPORT_SYMBOL_GPL(regmap_update_bits_base);
  * @reg: Register to read from
  * @bits: Bits to test
  *
- * Returns -1 if the underlying regmap_read() fails, 0 if at least one of the
- * tested bits is not set and 1 if all tested bits are set.
+ * Returns 0 if at least one of the tested bits is not set, 1 if all tested
+ * bits are set and a negative error number if the underlying regmap_read()
+ * fails.
  */
 int regmap_test_bits(struct regmap *map, unsigned int reg, unsigned int bits)
 {
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index c33bbbfd1bd9..475e1a738560 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -1368,14 +1368,14 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
 	    lo->lo_sizelimit != info->lo_sizelimit) {
 		size_changed = true;
 		sync_blockdev(lo->lo_device);
-		kill_bdev(lo->lo_device);
+		invalidate_bdev(lo->lo_device);
 	}
 
 	/* I/O need to be drained during transfer transition */
 	blk_mq_freeze_queue(lo->lo_queue);
 
 	if (size_changed && lo->lo_device->bd_inode->i_mapping->nrpages) {
-		/* If any pages were dirtied after kill_bdev(), try again */
+		/* If any pages were dirtied after invalidate_bdev(), try again */
 		err = -EAGAIN;
 		pr_warn("%s: loop%d (%s) has still dirty pages (nrpages=%lu)\n",
 			__func__, lo->lo_number, lo->lo_file_name,
@@ -1615,11 +1615,11 @@ static int loop_set_block_size(struct loop_device *lo, unsigned long arg)
 		return 0;
 
 	sync_blockdev(lo->lo_device);
-	kill_bdev(lo->lo_device);
+	invalidate_bdev(lo->lo_device);
 
 	blk_mq_freeze_queue(lo->lo_queue);
 
-	/* kill_bdev should have truncated all the pages */
+	/* invalidate_bdev should have truncated all the pages */
 	if (lo->lo_device->bd_inode->i_mapping->nrpages) {
 		err = -EAGAIN;
 		pr_warn("%s: loop%d (%s) has still dirty pages (nrpages=%lu)\n",
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 7420648a1de6..4f61e9209461 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -1451,8 +1451,10 @@ static void rbd_osd_req_callback(struct ceph_osd_request *osd_req)
 static void rbd_osd_format_read(struct ceph_osd_request *osd_req)
 {
 	struct rbd_obj_request *obj_request = osd_req->r_priv;
+	struct rbd_device *rbd_dev = obj_request->img_request->rbd_dev;
+	struct ceph_options *opt = rbd_dev->rbd_client->client->options;
 
-	osd_req->r_flags = CEPH_OSD_FLAG_READ;
+	osd_req->r_flags = CEPH_OSD_FLAG_READ | opt->read_from_replica;
 	osd_req->r_snapid = obj_request->img_request->snap_id;
 }
 
diff --git a/drivers/char/hw_random/ks-sa-rng.c b/drivers/char/hw_random/ks-sa-rng.c
index e2330e757f1f..001617033d6a 100644
--- a/drivers/char/hw_random/ks-sa-rng.c
+++ b/drivers/char/hw_random/ks-sa-rng.c
@@ -244,6 +244,7 @@ static int ks_sa_rng_probe(struct platform_device *pdev)
 	ret = pm_runtime_get_sync(dev);
 	if (ret < 0) {
 		dev_err(dev, "Failed to enable SA power-domain\n");
+		pm_runtime_put_noidle(dev);
 		pm_runtime_disable(dev);
 		return ret;
 	}
diff --git a/drivers/char/mem.c b/drivers/char/mem.c
index 31cae88a730b..934c92dcb9ab 100644
--- a/drivers/char/mem.c
+++ b/drivers/char/mem.c
@@ -171,7 +171,7 @@ static ssize_t read_mem(struct file *file, char __user *buf,
 			if (!ptr)
 				goto failed;
 
-			probe = probe_kernel_read(bounce, ptr, sz);
+			probe = copy_from_kernel_nofault(bounce, ptr, sz);
 			unxlate_dev_mem_ptr(p, ptr);
 			if (probe)
 				goto failed;
diff --git a/drivers/crypto/caam/Kconfig b/drivers/crypto/caam/Kconfig
index a62f228be6da..bc35aa0ec07a 100644
--- a/drivers/crypto/caam/Kconfig
+++ b/drivers/crypto/caam/Kconfig
@@ -147,7 +147,7 @@ config CRYPTO_DEV_FSL_CAAM_RNG_API
 	select HW_RANDOM
 	help
 	  Selecting this will register the SEC4 hardware rng to
-	  the hw_random API for suppying the kernel entropy pool.
+	  the hw_random API for supplying the kernel entropy pool.
 
 endif # CRYPTO_DEV_FSL_CAAM_JR
 
diff --git a/drivers/crypto/caam/ctrl.c b/drivers/crypto/caam/ctrl.c
index 4fcdd262e581..f3d20b7645e0 100644
--- a/drivers/crypto/caam/ctrl.c
+++ b/drivers/crypto/caam/ctrl.c
@@ -54,7 +54,7 @@ static void build_instantiation_desc(u32 *desc, int handle, int do_sk)
 
 		/*
 		 * load 1 to clear written reg:
-		 * resets the done interrrupt and returns the RNG to idle.
+		 * resets the done interrupt and returns the RNG to idle.
 		 */
 		append_load_imm_u32(desc, 1, LDST_SRCDST_WORD_CLRW);
 
@@ -156,7 +156,7 @@ static inline int run_descriptor_deco0(struct device *ctrldev, u32 *desc,
 				     DESC_DER_DECO_STAT_SHIFT;
 
 		/*
-		 * If an error occured in the descriptor, then
+		 * If an error occurred in the descriptor, then
 		 * the DECO status field will be set to 0x0D
 		 */
 		if (deco_state == DECO_STAT_HOST_ERR)
@@ -264,7 +264,7 @@ static void devm_deinstantiate_rng(void *data)
  *	   - -ENODEV if DECO0 couldn't be acquired
  *	   - -EAGAIN if an error occurred when executing the descriptor
  *	      f.i. there was a RNG hardware error due to not "good enough"
- *	      entropy being aquired.
+ *	      entropy being acquired.
  */
 static int instantiate_rng(struct device *ctrldev, int state_handle_mask,
 			   int gen_sk)
@@ -733,8 +733,8 @@ static int caam_probe(struct platform_device *pdev)
 	handle_imx6_err005766(&ctrl->mcr);
 
 	/*
-	 *  Read the Compile Time paramters and SCFGR to determine
-	 * if Virtualization is enabled for this platform
+	 *  Read the Compile Time parameters and SCFGR to determine
+	 * if virtualization is enabled for this platform
 	 */
 	scfgr = rd_reg32(&ctrl->scfgr);
 
@@ -863,9 +863,9 @@ static int caam_probe(struct platform_device *pdev)
 			}
 			/*
 			 * if instantiate_rng(...) fails, the loop will rerun
-			 * and the kick_trng(...) function will modfiy the
+			 * and the kick_trng(...) function will modify the
 			 * upper and lower limits of the entropy sampling
-			 * interval, leading to a sucessful initialization of
+			 * interval, leading to a successful initialization of
 			 * the RNG.
 			 */
 			ret = instantiate_rng(dev, inst_handles,
@@ -882,8 +882,8 @@ static int caam_probe(struct platform_device *pdev)
 			return ret;
 		}
 		/*
-		 * Set handles init'ed by this module as the complement of the
-		 * already initialized ones
+		 * Set handles initialized by this module as the complement of
+		 * the already initialized ones
 		 */
 		ctrlpriv->rng4_sh_init = ~ctrlpriv->rng4_sh_init & RDSTA_MASK;
 
diff --git a/drivers/crypto/caam/desc.h b/drivers/crypto/caam/desc.h
index e796d3cb9be8..e13470901586 100644
--- a/drivers/crypto/caam/desc.h
+++ b/drivers/crypto/caam/desc.h
@@ -18,7 +18,7 @@
  */
 
 #define SEC4_SG_LEN_EXT		0x80000000	/* Entry points to table */
-#define SEC4_SG_LEN_FIN		0x40000000	/* Last ent in table */
+#define SEC4_SG_LEN_FIN		0x40000000	/* Last entry in table */
 #define SEC4_SG_BPID_MASK	0x000000ff
 #define SEC4_SG_BPID_SHIFT	16
 #define SEC4_SG_LEN_MASK	0x3fffffff	/* Excludes EXT and FINAL */
@@ -113,7 +113,7 @@
  */
 #define HDR_REVERSE		0x00000800
 
-/* Propogate DNR property to SharedDesc */
+/* Propagate DNR property to SharedDesc */
 #define HDR_PROP_DNR		0x00000800
 
 /* JobDesc/SharedDesc share property */
diff --git a/drivers/crypto/caam/pdb.h b/drivers/crypto/caam/pdb.h
index 68c1fd5dee5d..8ccc22075043 100644
--- a/drivers/crypto/caam/pdb.h
+++ b/drivers/crypto/caam/pdb.h
@@ -453,7 +453,7 @@ struct srtp_decap_pdb {
 #define DSA_PDB_N_MASK		0x7f
 
 struct dsa_sign_pdb {
-	u32 sgf_ln; /* Use DSA_PDB_ defintions per above */
+	u32 sgf_ln; /* Use DSA_PDB_ definitions per above */
 	u8 *q;
 	u8 *r;
 	u8 *g;	/* or Gx,y */
diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c
index a2426334be61..476113e12489 100644
--- a/drivers/crypto/ccp/sev-dev.c
+++ b/drivers/crypto/ccp/sev-dev.c
@@ -376,6 +376,7 @@ static int sev_ioctl_do_pek_csr(struct sev_issue_cmd *argp, bool writable)
 	struct sev_device *sev = psp_master->sev_data;
 	struct sev_user_data_pek_csr input;
 	struct sev_data_pek_csr *data;
+	void __user *input_address;
 	void *blob = NULL;
 	int ret;
 
@@ -394,6 +395,7 @@ static int sev_ioctl_do_pek_csr(struct sev_issue_cmd *argp, bool writable)
 		goto cmd;
 
 	/* allocate a physically contiguous buffer to store the CSR blob */
+	input_address = (void __user *)input.address;
 	if (input.length > SEV_FW_BLOB_MAX_SIZE) {
 		ret = -EFAULT;
 		goto e_free;
@@ -426,7 +428,7 @@ cmd:
 	}
 
 	if (blob) {
-		if (copy_to_user((void __user *)input.address, blob, input.length))
+		if (copy_to_user(input_address, blob, input.length))
 			ret = -EFAULT;
 	}
 
@@ -437,7 +439,7 @@ e_free:
 	return ret;
 }
 
-void *psp_copy_user_blob(u64 __user uaddr, u32 len)
+void *psp_copy_user_blob(u64 uaddr, u32 len)
 {
 	if (!uaddr || !len)
 		return ERR_PTR(-EINVAL);
@@ -446,7 +448,7 @@ void *psp_copy_user_blob(u64 __user uaddr, u32 len)
 	if (len > SEV_FW_BLOB_MAX_SIZE)
 		return ERR_PTR(-EINVAL);
 
-	return memdup_user((void __user *)(uintptr_t)uaddr, len);
+	return memdup_user((void __user *)uaddr, len);
 }
 EXPORT_SYMBOL_GPL(psp_copy_user_blob);
 
@@ -621,6 +623,7 @@ static int sev_ioctl_do_get_id2(struct sev_issue_cmd *argp)
 {
 	struct sev_user_data_get_id2 input;
 	struct sev_data_get_id *data;
+	void __user *input_address;
 	void *id_blob = NULL;
 	int ret;
 
@@ -631,6 +634,8 @@ static int sev_ioctl_do_get_id2(struct sev_issue_cmd *argp)
 	if (copy_from_user(&input, (void __user *)argp->data, sizeof(input)))
 		return -EFAULT;
 
+	input_address = (void __user *)input.address;
+
 	data = kzalloc(sizeof(*data), GFP_KERNEL);
 	if (!data)
 		return -ENOMEM;
@@ -660,8 +665,7 @@ static int sev_ioctl_do_get_id2(struct sev_issue_cmd *argp)
 	}
 
 	if (id_blob) {
-		if (copy_to_user((void __user *)input.address,
-				 id_blob, data->len)) {
+		if (copy_to_user(input_address, id_blob, data->len)) {
 			ret = -EFAULT;
 			goto e_free;
 		}
@@ -720,6 +724,8 @@ static int sev_ioctl_do_pdh_export(struct sev_issue_cmd *argp, bool writable)
 	struct sev_user_data_pdh_cert_export input;
 	void *pdh_blob = NULL, *cert_blob = NULL;
 	struct sev_data_pdh_cert_export *data;
+	void __user *input_cert_chain_address;
+	void __user *input_pdh_cert_address;
 	int ret;
 
 	/* If platform is not in INIT state then transition it to INIT. */
@@ -745,6 +751,9 @@ static int sev_ioctl_do_pdh_export(struct sev_issue_cmd *argp, bool writable)
 	    !input.cert_chain_address)
 		goto cmd;
 
+	input_pdh_cert_address = (void __user *)input.pdh_cert_address;
+	input_cert_chain_address = (void __user *)input.cert_chain_address;
+
 	/* Allocate a physically contiguous buffer to store the PDH blob. */
 	if (input.pdh_cert_len > SEV_FW_BLOB_MAX_SIZE) {
 		ret = -EFAULT;
@@ -788,7 +797,7 @@ cmd:
 	}
 
 	if (pdh_blob) {
-		if (copy_to_user((void __user *)input.pdh_cert_address,
+		if (copy_to_user(input_pdh_cert_address,
 				 pdh_blob, input.pdh_cert_len)) {
 			ret = -EFAULT;
 			goto e_free_cert;
@@ -796,7 +805,7 @@ cmd:
 	}
 
 	if (cert_blob) {
-		if (copy_to_user((void __user *)input.cert_chain_address,
+		if (copy_to_user(input_cert_chain_address,
 				 cert_blob, input.cert_chain_len))
 			ret = -EFAULT;
 	}
diff --git a/drivers/crypto/hisilicon/sgl.c b/drivers/crypto/hisilicon/sgl.c
index 0e8c7e324fb4..725a739800b0 100644
--- a/drivers/crypto/hisilicon/sgl.c
+++ b/drivers/crypto/hisilicon/sgl.c
@@ -66,7 +66,8 @@ struct hisi_acc_sgl_pool *hisi_acc_create_sgl_pool(struct device *dev,
 
 	sgl_size = sizeof(struct acc_hw_sge) * sge_nr +
 		   sizeof(struct hisi_acc_hw_sgl);
-	block_size = PAGE_SIZE * (1 << (MAX_ORDER - 1));
+	block_size = 1 << (PAGE_SHIFT + MAX_ORDER <= 32 ?
+			   PAGE_SHIFT + MAX_ORDER - 1 : 31);
 	sgl_num_per_block = block_size / sgl_size;
 	block_num = count / sgl_num_per_block;
 	remain_sgl = count % sgl_num_per_block;
diff --git a/drivers/crypto/marvell/octeontx/otx_cptvf_algs.c b/drivers/crypto/marvell/octeontx/otx_cptvf_algs.c
index 60e744f680d3..1e0a1d70ebd3 100644
--- a/drivers/crypto/marvell/octeontx/otx_cptvf_algs.c
+++ b/drivers/crypto/marvell/octeontx/otx_cptvf_algs.c
@@ -118,6 +118,9 @@ static void otx_cpt_aead_callback(int status, void *arg1, void *arg2)
 	struct otx_cpt_req_info *cpt_req;
 	struct pci_dev *pdev;
 
+	if (!cpt_info)
+		goto complete;
+
 	cpt_req = cpt_info->req;
 	if (!status) {
 		/*
@@ -129,10 +132,10 @@ static void otx_cpt_aead_callback(int status, void *arg1, void *arg2)
 		    !cpt_req->is_enc)
 			status = validate_hmac_cipher_null(cpt_req);
 	}
-	if (cpt_info) {
-		pdev = cpt_info->pdev;
-		do_request_cleanup(pdev, cpt_info);
-	}
+	pdev = cpt_info->pdev;
+	do_request_cleanup(pdev, cpt_info);
+
+complete:
 	if (areq)
 		areq->complete(areq, status);
 }
diff --git a/drivers/dio/dio.c b/drivers/dio/dio.c
index c9aa15fb86a9..193b40e7aec0 100644
--- a/drivers/dio/dio.c
+++ b/drivers/dio/dio.c
@@ -135,7 +135,8 @@ int __init dio_find(int deviceid)
 		else
 			va = ioremap(pa, PAGE_SIZE);
 
-                if (probe_kernel_read(&i, (unsigned char *)va + DIO_IDOFF, 1)) {
+		if (copy_from_kernel_nofault(&i,
+				(unsigned char *)va + DIO_IDOFF, 1)) {
 			if (scode >= DIOII_SCBASE)
 				iounmap(va);
                         continue;             /* no board present at that select code */
@@ -208,7 +209,8 @@ static int __init dio_init(void)
 		else
 			va = ioremap(pa, PAGE_SIZE);
 
-                if (probe_kernel_read(&i, (unsigned char *)va + DIO_IDOFF, 1)) {
+		if (copy_from_kernel_nofault(&i,
+				(unsigned char *)va + DIO_IDOFF, 1)) {
 			if (scode >= DIOII_SCBASE)
 				iounmap(va);
                         continue;              /* no board present at that select code */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
index 775e389c9a13..16596a9ccabe 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
@@ -696,7 +696,7 @@ static ssize_t amdgpu_set_pp_table(struct device *dev,
  * default power levels, write "r" (reset) to the file to reset them.
  *
  *
- * < For Vega20 >
+ * < For Vega20 and newer ASICs >
  *
  * Reading the file will display:
  *
@@ -1668,7 +1668,7 @@ static ssize_t amdgpu_set_pp_power_profile_mode(struct device *dev,
 }
 
 /**
- * DOC: busy_percent
+ * DOC: gpu_busy_percent
  *
  * The amdgpu driver provides a sysfs API for reading how busy the GPU
  * is as a percentage.  The file gpu_busy_percent is used for this.
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index f0587d94294d..fee60921fccf 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -40,6 +40,7 @@
 #include <drm/drm_file.h>
 #include <drm/drm_drv.h>
 #include <drm/drm_device.h>
+#include <drm/drm_ioctl.h>
 #include <kgd_kfd_interface.h>
 #include <linux/swap.h>
 
@@ -1076,7 +1077,7 @@ static inline int kfd_devcgroup_check_permission(struct kfd_dev *kfd)
 #if defined(CONFIG_CGROUP_DEVICE) || defined(CONFIG_CGROUP_BPF)
 	struct drm_device *ddev = kfd->ddev;
 
-	return devcgroup_check_permission(DEVCG_DEV_CHAR, ddev->driver->major,
+	return devcgroup_check_permission(DEVCG_DEV_CHAR, DRM_MAJOR,
 					  ddev->render->index,
 					  DEVCG_ACC_WRITE | DEVCG_ACC_READ);
 #else
diff --git a/drivers/gpu/drm/amd/display/dc/dsc/Makefile b/drivers/gpu/drm/amd/display/dc/dsc/Makefile
index 3f66868df171..ea29cf95d470 100644
--- a/drivers/gpu/drm/amd/display/dc/dsc/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dsc/Makefile
@@ -28,8 +28,6 @@ endif
 endif
 
 CFLAGS_$(AMDDALPATH)/dc/dsc/rc_calc.o := $(dsc_ccflags)
-CFLAGS_$(AMDDALPATH)/dc/dsc/rc_calc_dpi.o := $(dsc_ccflags)
-CFLAGS_$(AMDDALPATH)/dc/dsc/dc_dsc.o := $(dsc_ccflags)
 
 DSC = dc_dsc.o rc_calc.o rc_calc_dpi.o
 
diff --git a/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c
index 0ea6662a1563..0c7f247bb7de 100644
--- a/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c
+++ b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c
@@ -22,10 +22,12 @@
  * Author: AMD
  */
 
+#include <drm/drm_dsc.h>
 #include "dc_hw_types.h"
 #include "dsc.h"
 #include <drm/drm_dp_helper.h>
 #include "dc.h"
+#include "rc_calc.h"
 
 /* This module's internal functions */
 
@@ -304,22 +306,6 @@ static inline uint32_t dsc_div_by_10_round_up(uint32_t value)
 	return (value + 9) / 10;
 }
 
-static inline uint32_t calc_dsc_bpp_x16(uint32_t stream_bandwidth_kbps, uint32_t pix_clk_100hz, uint32_t bpp_increment_div)
-{
-	uint32_t dsc_target_bpp_x16;
-	float f_dsc_target_bpp;
-	float f_stream_bandwidth_100bps = stream_bandwidth_kbps * 10.0f;
-	uint32_t precision = bpp_increment_div; // bpp_increment_div is actually precision
-
-	f_dsc_target_bpp = f_stream_bandwidth_100bps / pix_clk_100hz;
-
-	// Round down to the nearest precision stop to bring it into DSC spec range
-	dsc_target_bpp_x16 = (uint32_t)(f_dsc_target_bpp * precision);
-	dsc_target_bpp_x16 = (dsc_target_bpp_x16 * 16) / precision;
-
-	return dsc_target_bpp_x16;
-}
-
 /* Get DSC bandwidth range based on [min_bpp, max_bpp] target bitrate range, and timing's pixel clock
  * and uncompressed bandwidth.
  */
diff --git a/drivers/gpu/drm/amd/display/dc/dsc/rc_calc.c b/drivers/gpu/drm/amd/display/dc/dsc/rc_calc.c
index 03ae15946c6d..667afbc260f9 100644
--- a/drivers/gpu/drm/amd/display/dc/dsc/rc_calc.c
+++ b/drivers/gpu/drm/amd/display/dc/dsc/rc_calc.c
@@ -23,6 +23,7 @@
  * Authors: AMD
  *
  */
+#include <drm/drm_dsc.h>
 
 #include "os_types.h"
 #include "rc_calc.h"
@@ -40,7 +41,8 @@
 	break
 
 
-void get_qp_set(qp_set qps, enum colour_mode cm, enum bits_per_comp bpc, enum max_min max_min, float bpp)
+static void get_qp_set(qp_set qps, enum colour_mode cm, enum bits_per_comp bpc,
+		       enum max_min max_min, float bpp)
 {
 	int mode = MODE_SELECT(444, 422, 420);
 	int sel = table_hash(mode, bpc, max_min);
@@ -85,7 +87,7 @@ void get_qp_set(qp_set qps, enum colour_mode cm, enum bits_per_comp bpc, enum ma
 	memcpy(qps, table[index].qps, sizeof(qp_set));
 }
 
-double dsc_roundf(double num)
+static double dsc_roundf(double num)
 {
 	if (num < 0.0)
 		num = num - 0.5;
@@ -95,7 +97,7 @@ double dsc_roundf(double num)
 	return (int)(num);
 }
 
-double dsc_ceil(double num)
+static double dsc_ceil(double num)
 {
 	double retval = (int)num;
 
@@ -105,7 +107,7 @@ double dsc_ceil(double num)
 	return (int)retval;
 }
 
-void get_ofs_set(qp_set ofs, enum colour_mode mode, float bpp)
+static void get_ofs_set(qp_set ofs, enum colour_mode mode, float bpp)
 {
 	int   *p = ofs;
 
@@ -160,7 +162,7 @@ void get_ofs_set(qp_set ofs, enum colour_mode mode, float bpp)
 	}
 }
 
-int median3(int a, int b, int c)
+static int median3(int a, int b, int c)
 {
 	if (a > b)
 		swap(a, b);
@@ -172,13 +174,25 @@ int median3(int a, int b, int c)
 	return b;
 }
 
-void calc_rc_params(struct rc_params *rc, enum colour_mode cm, enum bits_per_comp bpc, float bpp, int slice_width, int slice_height, int minor_version)
+static void _do_calc_rc_params(struct rc_params *rc, enum colour_mode cm,
+			       enum bits_per_comp bpc, u8 drm_bpp,
+			       bool is_navite_422_or_420,
+			       int slice_width, int slice_height,
+			       int minor_version)
 {
+	float bpp;
 	float bpp_group;
 	float initial_xmit_delay_factor;
 	int padding_pixels;
 	int i;
 
+	bpp = ((float)drm_bpp / 16.0);
+	/* in native_422 or native_420 modes, the bits_per_pixel is double the
+	 * target bpp (the latter is what calc_rc_params expects)
+	 */
+	if (is_navite_422_or_420)
+		bpp /= 2.0;
+
 	rc->rc_quant_incr_limit0 = ((bpc == BPC_8) ? 11 : (bpc == BPC_10 ? 15 : 19)) - ((minor_version == 1 && cm == CM_444) ? 1 : 0);
 	rc->rc_quant_incr_limit1 = ((bpc == BPC_8) ? 11 : (bpc == BPC_10 ? 15 : 19)) - ((minor_version == 1 && cm == CM_444) ? 1 : 0);
 
@@ -251,3 +265,128 @@ void calc_rc_params(struct rc_params *rc, enum colour_mode cm, enum bits_per_com
 	rc->rc_buf_thresh[13] = 8064;
 }
 
+static u32 _do_bytes_per_pixel_calc(int slice_width, u8 drm_bpp,
+				    bool is_navite_422_or_420)
+{
+	float bpp;
+	u32 bytes_per_pixel;
+	double d_bytes_per_pixel;
+
+	bpp = ((float)drm_bpp / 16.0);
+	d_bytes_per_pixel = dsc_ceil(bpp * slice_width / 8.0) / slice_width;
+	// TODO: Make sure the formula for calculating this is precise (ceiling
+	// vs. floor, and at what point they should be applied)
+	if (is_navite_422_or_420)
+		d_bytes_per_pixel /= 2;
+
+	bytes_per_pixel = (u32)dsc_ceil(d_bytes_per_pixel * 0x10000000);
+
+	return bytes_per_pixel;
+}
+
+static u32 _do_calc_dsc_bpp_x16(u32 stream_bandwidth_kbps, u32 pix_clk_100hz,
+				u32 bpp_increment_div)
+{
+	u32 dsc_target_bpp_x16;
+	float f_dsc_target_bpp;
+	float f_stream_bandwidth_100bps;
+	// bpp_increment_div is actually precision
+	u32 precision = bpp_increment_div;
+
+	f_stream_bandwidth_100bps = stream_bandwidth_kbps * 10.0f;
+	f_dsc_target_bpp = f_stream_bandwidth_100bps / pix_clk_100hz;
+
+	// Round down to the nearest precision stop to bring it into DSC spec
+	// range
+	dsc_target_bpp_x16 = (u32)(f_dsc_target_bpp * precision);
+	dsc_target_bpp_x16 = (dsc_target_bpp_x16 * 16) / precision;
+
+	return dsc_target_bpp_x16;
+}
+
+/**
+ * calc_rc_params - reads the user's cmdline mode
+ * @rc: DC internal DSC parameters
+ * @pps: DRM struct with all required DSC values
+ *
+ * This function expects a drm_dsc_config data struct with all the required DSC
+ * values previously filled out by our driver and based on this information it
+ * computes some of the DSC values.
+ *
+ * @note This calculation requires float point operation, most of it executes
+ * under kernel_fpu_{begin,end}.
+ */
+void calc_rc_params(struct rc_params *rc, const struct drm_dsc_config *pps)
+{
+	enum colour_mode mode;
+	enum bits_per_comp bpc;
+	bool is_navite_422_or_420;
+	u8 drm_bpp = pps->bits_per_pixel;
+	int slice_width  = pps->slice_width;
+	int slice_height = pps->slice_height;
+
+	mode = pps->convert_rgb ? CM_RGB : (pps->simple_422  ? CM_444 :
+					   (pps->native_422  ? CM_422 :
+					    pps->native_420  ? CM_420 : CM_444));
+	bpc = (pps->bits_per_component == 8) ? BPC_8 : (pps->bits_per_component == 10)
+					     ? BPC_10 : BPC_12;
+
+	is_navite_422_or_420 = pps->native_422 || pps->native_420;
+
+	DC_FP_START();
+	_do_calc_rc_params(rc, mode, bpc, drm_bpp, is_navite_422_or_420,
+			   slice_width, slice_height,
+			   pps->dsc_version_minor);
+	DC_FP_END();
+}
+
+/**
+ * calc_dsc_bytes_per_pixel - calculate bytes per pixel
+ * @pps: DRM struct with all required DSC values
+ *
+ * Based on the information inside drm_dsc_config, this function calculates the
+ * total of bytes per pixel.
+ *
+ * @note This calculation requires float point operation, most of it executes
+ * under kernel_fpu_{begin,end}.
+ *
+ * Return:
+ * Return the number of bytes per pixel
+ */
+u32 calc_dsc_bytes_per_pixel(const struct drm_dsc_config *pps)
+
+{
+	u32 ret;
+	u8 drm_bpp = pps->bits_per_pixel;
+	int slice_width  = pps->slice_width;
+	bool is_navite_422_or_420 = pps->native_422 || pps->native_420;
+
+	DC_FP_START();
+	ret = _do_bytes_per_pixel_calc(slice_width, drm_bpp,
+				       is_navite_422_or_420);
+	DC_FP_END();
+	return ret;
+}
+
+/**
+ * calc_dsc_bpp_x16 - retrieve the dsc bits per pixel
+ * @stream_bandwidth_kbps:
+ * @pix_clk_100hz:
+ * @bpp_increment_div:
+ *
+ * Calculate the total of bits per pixel for DSC configuration.
+ *
+ * @note This calculation requires float point operation, most of it executes
+ * under kernel_fpu_{begin,end}.
+ */
+u32 calc_dsc_bpp_x16(u32 stream_bandwidth_kbps, u32 pix_clk_100hz,
+		     u32 bpp_increment_div)
+{
+	u32 dsc_bpp;
+
+	DC_FP_START();
+	dsc_bpp =  _do_calc_dsc_bpp_x16(stream_bandwidth_kbps, pix_clk_100hz,
+					bpp_increment_div);
+	DC_FP_END();
+	return dsc_bpp;
+}
diff --git a/drivers/gpu/drm/amd/display/dc/dsc/rc_calc.h b/drivers/gpu/drm/amd/display/dc/dsc/rc_calc.h
index b6b1f09c2009..21723fa6561e 100644
--- a/drivers/gpu/drm/amd/display/dc/dsc/rc_calc.h
+++ b/drivers/gpu/drm/amd/display/dc/dsc/rc_calc.h
@@ -77,7 +77,10 @@ struct qp_entry {
 
 typedef struct qp_entry qp_table[];
 
-void calc_rc_params(struct rc_params *rc, enum colour_mode cm, enum bits_per_comp bpc, float bpp, int slice_width, int slice_height, int minor_version);
+void calc_rc_params(struct rc_params *rc, const struct drm_dsc_config *pps);
+u32 calc_dsc_bytes_per_pixel(const struct drm_dsc_config *pps);
+u32 calc_dsc_bpp_x16(u32 stream_bandwidth_kbps, u32 pix_clk_100hz,
+		     u32 bpp_increment_div);
 
 #endif
 
diff --git a/drivers/gpu/drm/amd/display/dc/dsc/rc_calc_dpi.c b/drivers/gpu/drm/amd/display/dc/dsc/rc_calc_dpi.c
index 1f6e63b71456..ef830aded5b1 100644
--- a/drivers/gpu/drm/amd/display/dc/dsc/rc_calc_dpi.c
+++ b/drivers/gpu/drm/amd/display/dc/dsc/rc_calc_dpi.c
@@ -27,8 +27,6 @@
 #include "dscc_types.h"
 #include "rc_calc.h"
 
-double dsc_ceil(double num);
-
 static void copy_pps_fields(struct drm_dsc_config *to, const struct drm_dsc_config *from)
 {
 	to->line_buf_depth           = from->line_buf_depth;
@@ -100,34 +98,13 @@ static void copy_rc_to_cfg(struct drm_dsc_config *dsc_cfg, const struct rc_param
 
 int dscc_compute_dsc_parameters(const struct drm_dsc_config *pps, struct dsc_parameters *dsc_params)
 {
-	enum colour_mode  mode = pps->convert_rgb ? CM_RGB :
-							(pps->simple_422  ? CM_444 :
-							(pps->native_422  ? CM_422 :
-							pps->native_420  ? CM_420 : CM_444));
-	enum bits_per_comp bpc = (pps->bits_per_component == 8) ? BPC_8 :
-							(pps->bits_per_component == 10) ? BPC_10 : BPC_12;
-	float            bpp = ((float) pps->bits_per_pixel / 16.0);
-	int              slice_width  = pps->slice_width;
-	int              slice_height = pps->slice_height;
 	int              ret;
 	struct rc_params rc;
 	struct drm_dsc_config   dsc_cfg;
 
-	double d_bytes_per_pixel = dsc_ceil(bpp * slice_width / 8.0) / slice_width;
-
-	// TODO: Make sure the formula for calculating this is precise (ceiling vs. floor, and at what point they should be applied)
-	if (pps->native_422 || pps->native_420)
-		d_bytes_per_pixel /= 2;
-
-	dsc_params->bytes_per_pixel = (uint32_t)dsc_ceil(d_bytes_per_pixel * 0x10000000);
-
-	/* in native_422 or native_420 modes, the bits_per_pixel is double the target bpp
-	 * (the latter is what calc_rc_params expects)
-	 */
-	if (pps->native_422 || pps->native_420)
-		bpp /= 2.0;
+	dsc_params->bytes_per_pixel = calc_dsc_bytes_per_pixel(pps);
 
-	calc_rc_params(&rc, mode, bpc, bpp, slice_width, slice_height, pps->dsc_version_minor);
+	calc_rc_params(&rc, pps);
 	dsc_params->pps = *pps;
 	dsc_params->pps.initial_scale_value = 8 * rc.rc_model_size / (rc.rc_model_size - rc.initial_fullness_offset);
 
diff --git a/drivers/gpu/drm/amd/display/modules/color/color_gamma.c b/drivers/gpu/drm/amd/display/modules/color/color_gamma.c
index 9431b48aecb4..bcfe34ef8c28 100644
--- a/drivers/gpu/drm/amd/display/modules/color/color_gamma.c
+++ b/drivers/gpu/drm/amd/display/modules/color/color_gamma.c
@@ -843,7 +843,7 @@ static bool build_regamma(struct pwl_float_data_ex *rgb_regamma,
 	pow_buffer_ptr = -1; // reset back to no optimize
 	ret = true;
 release:
-	kfree(coeff);
+	kvfree(coeff);
 	return ret;
 }
 
@@ -1777,7 +1777,7 @@ bool calculate_user_regamma_ramp(struct dc_transfer_func *output_tf,
 
 	kfree(rgb_regamma);
 rgb_regamma_alloc_fail:
-	kvfree(rgb_user);
+	kfree(rgb_user);
 rgb_user_alloc_fail:
 	return ret;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c
index 85e5b1ed22c2..56923a96b450 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c
@@ -239,7 +239,7 @@ static void ci_initialize_power_tune_defaults(struct pp_hwmgr *hwmgr)
 
 	switch (dev_id) {
 	case 0x67BA:
-	case 0x66B1:
+	case 0x67B1:
 		smu_data->power_tune_defaults = &defaults_hawaii_pro;
 		break;
 	case 0x67B8:
diff --git a/drivers/gpu/drm/drm_encoder_slave.c b/drivers/gpu/drm/drm_encoder_slave.c
index cf804389f5ec..e464429d32df 100644
--- a/drivers/gpu/drm/drm_encoder_slave.c
+++ b/drivers/gpu/drm/drm_encoder_slave.c
@@ -61,13 +61,8 @@ int drm_i2c_encoder_init(struct drm_device *dev,
 
 	request_module("%s%s", I2C_MODULE_PREFIX, info->type);
 
-	client = i2c_new_device(adap, info);
-	if (!client) {
-		err = -ENOMEM;
-		goto fail;
-	}
-
-	if (!client->dev.driver) {
+	client = i2c_new_client_device(adap, info);
+	if (!i2c_client_has_driver(client)) {
 		err = -ENODEV;
 		goto fail_unregister;
 	}
@@ -84,7 +79,7 @@ int drm_i2c_encoder_init(struct drm_device *dev,
 
 	err = encoder_drv->encoder_init(client, dev, encoder);
 	if (err)
-		goto fail_unregister;
+		goto fail_module_put;
 
 	if (info->platform_data)
 		encoder->slave_funcs->set_config(&encoder->base,
@@ -92,10 +87,10 @@ int drm_i2c_encoder_init(struct drm_device *dev,
 
 	return 0;
 
+fail_module_put:
+	module_put(module);
 fail_unregister:
 	i2c_unregister_device(client);
-	module_put(module);
-fail:
 	return err;
 }
 EXPORT_SYMBOL(drm_i2c_encoder_init);
diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index aa22465bb56e..0575a1eea2a1 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -2579,14 +2579,14 @@ static void icl_ddi_vswing_sequence(struct intel_encoder *encoder,
 
 static void
 tgl_dkl_phy_ddi_vswing_sequence(struct intel_encoder *encoder, int link_clock,
-				u32 level)
+				u32 level, enum intel_output_type type)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	enum tc_port tc_port = intel_port_to_tc(dev_priv, encoder->port);
 	const struct tgl_dkl_phy_ddi_buf_trans *ddi_translations;
 	u32 n_entries, val, ln, dpcnt_mask, dpcnt_val;
 
-	if (encoder->type == INTEL_OUTPUT_HDMI) {
+	if (type == INTEL_OUTPUT_HDMI) {
 		n_entries = ARRAY_SIZE(tgl_dkl_phy_hdmi_ddi_trans);
 		ddi_translations = tgl_dkl_phy_hdmi_ddi_trans;
 	} else {
@@ -2638,7 +2638,7 @@ static void tgl_ddi_vswing_sequence(struct intel_encoder *encoder,
 	if (intel_phy_is_combo(dev_priv, phy))
 		icl_combo_phy_ddi_vswing_sequence(encoder, level, type);
 	else
-		tgl_dkl_phy_ddi_vswing_sequence(encoder, link_clock, level);
+		tgl_dkl_phy_ddi_vswing_sequence(encoder, link_clock, level, type);
 }
 
 static u32 translate_signal_level(struct intel_dp *intel_dp, int signal_levels)
@@ -2987,7 +2987,7 @@ icl_program_mg_dp_mode(struct intel_digital_port *intel_dig_port,
 		ln1 = intel_de_read(dev_priv, MG_DP_MODE(1, tc_port));
 	}
 
-	ln0 &= ~(MG_DP_MODE_CFG_DP_X1_MODE | MG_DP_MODE_CFG_DP_X1_MODE);
+	ln0 &= ~(MG_DP_MODE_CFG_DP_X1_MODE | MG_DP_MODE_CFG_DP_X2_MODE);
 	ln1 &= ~(MG_DP_MODE_CFG_DP_X1_MODE | MG_DP_MODE_CFG_DP_X2_MODE);
 
 	/* DPPATC */
@@ -3472,7 +3472,9 @@ static void intel_ddi_post_disable_dp(struct intel_atomic_state *state,
 					  INTEL_OUTPUT_DP_MST);
 	enum phy phy = intel_port_to_phy(dev_priv, encoder->port);
 
-	intel_dp_set_infoframes(encoder, false, old_crtc_state, old_conn_state);
+	if (!is_mst)
+		intel_dp_set_infoframes(encoder, false,
+					old_crtc_state, old_conn_state);
 
 	/*
 	 * Power down sink before disabling the port, otherwise we end
diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c
index d18b406f2a7d..f29e51ce489c 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c
@@ -397,6 +397,14 @@ static void intel_mst_post_disable_dp(struct intel_atomic_state *state,
 	 */
 	drm_dp_send_power_updown_phy(&intel_dp->mst_mgr, connector->port,
 				     false);
+
+	/*
+	 * BSpec 4287: disable DIP after the transcoder is disabled and before
+	 * the transcoder clock select is set to none.
+	 */
+	if (last_mst_stream)
+		intel_dp_set_infoframes(&intel_dig_port->base, false,
+					old_crtc_state, NULL);
 	/*
 	 * From TGL spec: "If multi-stream slave transcoder: Configure
 	 * Transcoder Clock Select to direct no clock to the transcoder"
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index da5b61085257..8691eb61e185 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -646,7 +646,7 @@ static int engine_setup_common(struct intel_engine_cs *engine)
 struct measure_breadcrumb {
 	struct i915_request rq;
 	struct intel_ring ring;
-	u32 cs[1024];
+	u32 cs[2048];
 };
 
 static int measure_breadcrumb_dw(struct intel_context *ce)
@@ -668,6 +668,8 @@ static int measure_breadcrumb_dw(struct intel_context *ce)
 
 	frame->ring.vaddr = frame->cs;
 	frame->ring.size = sizeof(frame->cs);
+	frame->ring.wrap =
+		BITS_PER_TYPE(frame->ring.size) - ilog2(frame->ring.size);
 	frame->ring.effective_size = frame->ring.size;
 	intel_ring_update_space(&frame->ring);
 	frame->rq.ring = &frame->ring;
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 87e6c5bdd2dc..7c3d8ef4a47c 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -1134,6 +1134,13 @@ __unwind_incomplete_requests(struct intel_engine_cs *engine)
 			list_move(&rq->sched.link, pl);
 			set_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
 
+			/* Check in case we rollback so far we wrap [size/2] */
+			if (intel_ring_direction(rq->ring,
+						 intel_ring_wrap(rq->ring,
+								 rq->tail),
+						 rq->ring->tail) > 0)
+				rq->context->lrc.desc |= CTX_DESC_FORCE_RESTORE;
+
 			active = rq;
 		} else {
 			struct intel_engine_cs *owner = rq->context->engine;
@@ -1498,8 +1505,9 @@ static u64 execlists_update_context(struct i915_request *rq)
 	 * HW has a tendency to ignore us rewinding the TAIL to the end of
 	 * an earlier request.
 	 */
+	GEM_BUG_ON(ce->lrc_reg_state[CTX_RING_TAIL] != rq->ring->tail);
+	prev = rq->ring->tail;
 	tail = intel_ring_set_tail(rq->ring, rq->tail);
-	prev = ce->lrc_reg_state[CTX_RING_TAIL];
 	if (unlikely(intel_ring_direction(rq->ring, tail, prev) <= 0))
 		desc |= CTX_DESC_FORCE_RESTORE;
 	ce->lrc_reg_state[CTX_RING_TAIL] = tail;
@@ -1895,7 +1903,8 @@ static void defer_active(struct intel_engine_cs *engine)
 
 static bool
 need_timeslice(const struct intel_engine_cs *engine,
-	       const struct i915_request *rq)
+	       const struct i915_request *rq,
+	       const struct rb_node *rb)
 {
 	int hint;
 
@@ -1903,9 +1912,28 @@ need_timeslice(const struct intel_engine_cs *engine,
 		return false;
 
 	hint = engine->execlists.queue_priority_hint;
+
+	if (rb) {
+		const struct virtual_engine *ve =
+			rb_entry(rb, typeof(*ve), nodes[engine->id].rb);
+		const struct intel_engine_cs *inflight =
+			intel_context_inflight(&ve->context);
+
+		if (!inflight || inflight == engine) {
+			struct i915_request *next;
+
+			rcu_read_lock();
+			next = READ_ONCE(ve->request);
+			if (next)
+				hint = max(hint, rq_prio(next));
+			rcu_read_unlock();
+		}
+	}
+
 	if (!list_is_last(&rq->sched.link, &engine->active.requests))
 		hint = max(hint, rq_prio(list_next_entry(rq, sched.link)));
 
+	GEM_BUG_ON(hint >= I915_PRIORITY_UNPREEMPTABLE);
 	return hint >= effective_prio(rq);
 }
 
@@ -1977,10 +2005,9 @@ static void set_timeslice(struct intel_engine_cs *engine)
 	set_timer_ms(&engine->execlists.timer, duration);
 }
 
-static void start_timeslice(struct intel_engine_cs *engine)
+static void start_timeslice(struct intel_engine_cs *engine, int prio)
 {
 	struct intel_engine_execlists *execlists = &engine->execlists;
-	const int prio = queue_prio(execlists);
 	unsigned long duration;
 
 	if (!intel_engine_has_timeslices(engine))
@@ -2140,7 +2167,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 			__unwind_incomplete_requests(engine);
 
 			last = NULL;
-		} else if (need_timeslice(engine, last) &&
+		} else if (need_timeslice(engine, last, rb) &&
 			   timeslice_expired(execlists, last)) {
 			if (i915_request_completed(last)) {
 				tasklet_hi_schedule(&execlists->tasklet);
@@ -2188,7 +2215,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 				 * Even if ELSP[1] is occupied and not worthy
 				 * of timeslices, our queue might be.
 				 */
-				start_timeslice(engine);
+				start_timeslice(engine, queue_prio(execlists));
 				return;
 			}
 		}
@@ -2223,7 +2250,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 
 			if (last && !can_merge_rq(last, rq)) {
 				spin_unlock(&ve->base.active.lock);
-				start_timeslice(engine);
+				start_timeslice(engine, rq_prio(rq));
 				return; /* leave this for another sibling */
 			}
 
@@ -4739,6 +4766,14 @@ static int gen12_emit_flush(struct i915_request *request, u32 mode)
 	return 0;
 }
 
+static void assert_request_valid(struct i915_request *rq)
+{
+	struct intel_ring *ring __maybe_unused = rq->ring;
+
+	/* Can we unwind this request without appearing to go forwards? */
+	GEM_BUG_ON(intel_ring_direction(ring, rq->wa_tail, rq->head) <= 0);
+}
+
 /*
  * Reserve space for 2 NOOPs at the end of each request to be
  * used as a workaround for not being allowed to do lite
@@ -4751,6 +4786,9 @@ static u32 *gen8_emit_wa_tail(struct i915_request *request, u32 *cs)
 	*cs++ = MI_NOOP;
 	request->wa_tail = intel_ring_offset(request, cs);
 
+	/* Check that entire request is less than half the ring */
+	assert_request_valid(request);
+
 	return cs;
 }
 
diff --git a/drivers/gpu/drm/i915/gt/intel_ring.c b/drivers/gpu/drm/i915/gt/intel_ring.c
index 8cda1b7e17ba..bdb324167ef3 100644
--- a/drivers/gpu/drm/i915/gt/intel_ring.c
+++ b/drivers/gpu/drm/i915/gt/intel_ring.c
@@ -315,3 +315,7 @@ int intel_ring_cacheline_align(struct i915_request *rq)
 	GEM_BUG_ON(rq->ring->emit & (CACHELINE_BYTES - 1));
 	return 0;
 }
+
+#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
+#include "selftest_ring.c"
+#endif
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 90a2b9e399b0..85d2bef51524 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -179,6 +179,12 @@ wa_write_or(struct i915_wa_list *wal, i915_reg_t reg, u32 set)
 }
 
 static void
+wa_write_clr(struct i915_wa_list *wal, i915_reg_t reg, u32 clr)
+{
+	wa_write_masked_or(wal, reg, clr, 0);
+}
+
+static void
 wa_masked_en(struct i915_wa_list *wal, i915_reg_t reg, u32 val)
 {
 	wa_add(wal, reg, 0, _MASKED_BIT_ENABLE(val), val);
@@ -687,6 +693,227 @@ int intel_engine_emit_ctx_wa(struct i915_request *rq)
 }
 
 static void
+gen4_gt_workarounds_init(struct drm_i915_private *i915,
+			 struct i915_wa_list *wal)
+{
+	/* WaDisable_RenderCache_OperationalFlush:gen4,ilk */
+	wa_masked_dis(wal, CACHE_MODE_0, RC_OP_FLUSH_ENABLE);
+}
+
+static void
+g4x_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
+{
+	gen4_gt_workarounds_init(i915, wal);
+
+	/* WaDisableRenderCachePipelinedFlush:g4x,ilk */
+	wa_masked_en(wal, CACHE_MODE_0, CM0_PIPELINED_RENDER_FLUSH_DISABLE);
+}
+
+static void
+ilk_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
+{
+	g4x_gt_workarounds_init(i915, wal);
+
+	wa_masked_en(wal, _3D_CHICKEN2, _3D_CHICKEN2_WM_READ_PIPELINED);
+}
+
+static void
+snb_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
+{
+	/* WaDisableHiZPlanesWhenMSAAEnabled:snb */
+	wa_masked_en(wal,
+		     _3D_CHICKEN,
+		     _3D_CHICKEN_HIZ_PLANE_DISABLE_MSAA_4X_SNB);
+
+	/* WaDisable_RenderCache_OperationalFlush:snb */
+	wa_masked_dis(wal, CACHE_MODE_0, RC_OP_FLUSH_ENABLE);
+
+	/*
+	 * BSpec recommends 8x4 when MSAA is used,
+	 * however in practice 16x4 seems fastest.
+	 *
+	 * Note that PS/WM thread counts depend on the WIZ hashing
+	 * disable bit, which we don't touch here, but it's good
+	 * to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
+	 */
+	wa_add(wal,
+	       GEN6_GT_MODE, 0,
+	       _MASKED_FIELD(GEN6_WIZ_HASHING_MASK, GEN6_WIZ_HASHING_16x4),
+	       GEN6_WIZ_HASHING_16x4);
+
+	wa_masked_dis(wal, CACHE_MODE_0, CM0_STC_EVICT_DISABLE_LRA_SNB);
+
+	wa_masked_en(wal,
+		     _3D_CHICKEN3,
+		     /* WaStripsFansDisableFastClipPerformanceFix:snb */
+		     _3D_CHICKEN3_SF_DISABLE_FASTCLIP_CULL |
+		     /*
+		      * Bspec says:
+		      * "This bit must be set if 3DSTATE_CLIP clip mode is set
+		      * to normal and 3DSTATE_SF number of SF output attributes
+		      * is more than 16."
+		      */
+		   _3D_CHICKEN3_SF_DISABLE_PIPELINED_ATTR_FETCH);
+}
+
+static void
+ivb_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
+{
+	/* WaDisableEarlyCull:ivb */
+	wa_masked_en(wal, _3D_CHICKEN3, _3D_CHICKEN_SF_DISABLE_OBJEND_CULL);
+
+	/* WaDisablePSDDualDispatchEnable:ivb */
+	if (IS_IVB_GT1(i915))
+		wa_masked_en(wal,
+			     GEN7_HALF_SLICE_CHICKEN1,
+			     GEN7_PSD_SINGLE_PORT_DISPATCH_ENABLE);
+
+	/* WaDisable_RenderCache_OperationalFlush:ivb */
+	wa_masked_dis(wal, CACHE_MODE_0_GEN7, RC_OP_FLUSH_ENABLE);
+
+	/* Apply the WaDisableRHWOOptimizationForRenderHang:ivb workaround. */
+	wa_masked_dis(wal,
+		      GEN7_COMMON_SLICE_CHICKEN1,
+		      GEN7_CSC1_RHWO_OPT_DISABLE_IN_RCC);
+
+	/* WaApplyL3ControlAndL3ChickenMode:ivb */
+	wa_write(wal, GEN7_L3CNTLREG1, GEN7_WA_FOR_GEN7_L3_CONTROL);
+	wa_write(wal, GEN7_L3_CHICKEN_MODE_REGISTER, GEN7_WA_L3_CHICKEN_MODE);
+
+	/* WaForceL3Serialization:ivb */
+	wa_write_clr(wal, GEN7_L3SQCREG4, L3SQ_URB_READ_CAM_MATCH_DISABLE);
+
+	/*
+	 * WaVSThreadDispatchOverride:ivb,vlv
+	 *
+	 * This actually overrides the dispatch
+	 * mode for all thread types.
+	 */
+	wa_write_masked_or(wal, GEN7_FF_THREAD_MODE,
+			   GEN7_FF_SCHED_MASK,
+			   GEN7_FF_TS_SCHED_HW |
+			   GEN7_FF_VS_SCHED_HW |
+			   GEN7_FF_DS_SCHED_HW);
+
+	if (0) { /* causes HiZ corruption on ivb:gt1 */
+		/* enable HiZ Raw Stall Optimization */
+		wa_masked_dis(wal, CACHE_MODE_0_GEN7, HIZ_RAW_STALL_OPT_DISABLE);
+	}
+
+	/* WaDisable4x2SubspanOptimization:ivb */
+	wa_masked_en(wal, CACHE_MODE_1, PIXEL_SUBSPAN_COLLECT_OPT_DISABLE);
+
+	/*
+	 * BSpec recommends 8x4 when MSAA is used,
+	 * however in practice 16x4 seems fastest.
+	 *
+	 * Note that PS/WM thread counts depend on the WIZ hashing
+	 * disable bit, which we don't touch here, but it's good
+	 * to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
+	 */
+	wa_add(wal, GEN7_GT_MODE, 0,
+	       _MASKED_FIELD(GEN6_WIZ_HASHING_MASK, GEN6_WIZ_HASHING_16x4),
+	       GEN6_WIZ_HASHING_16x4);
+}
+
+static void
+vlv_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
+{
+	/* WaDisableEarlyCull:vlv */
+	wa_masked_en(wal, _3D_CHICKEN3, _3D_CHICKEN_SF_DISABLE_OBJEND_CULL);
+
+	/* WaPsdDispatchEnable:vlv */
+	/* WaDisablePSDDualDispatchEnable:vlv */
+	wa_masked_en(wal,
+		     GEN7_HALF_SLICE_CHICKEN1,
+		     GEN7_MAX_PS_THREAD_DEP |
+		     GEN7_PSD_SINGLE_PORT_DISPATCH_ENABLE);
+
+	/* WaDisable_RenderCache_OperationalFlush:vlv */
+	wa_masked_dis(wal, CACHE_MODE_0_GEN7, RC_OP_FLUSH_ENABLE);
+
+	/* WaForceL3Serialization:vlv */
+	wa_write_clr(wal, GEN7_L3SQCREG4, L3SQ_URB_READ_CAM_MATCH_DISABLE);
+
+	/*
+	 * WaVSThreadDispatchOverride:ivb,vlv
+	 *
+	 * This actually overrides the dispatch
+	 * mode for all thread types.
+	 */
+	wa_write_masked_or(wal,
+			   GEN7_FF_THREAD_MODE,
+			   GEN7_FF_SCHED_MASK,
+			   GEN7_FF_TS_SCHED_HW |
+			   GEN7_FF_VS_SCHED_HW |
+			   GEN7_FF_DS_SCHED_HW);
+
+	/*
+	 * BSpec says this must be set, even though
+	 * WaDisable4x2SubspanOptimization isn't listed for VLV.
+	 */
+	wa_masked_en(wal, CACHE_MODE_1, PIXEL_SUBSPAN_COLLECT_OPT_DISABLE);
+
+	/*
+	 * BSpec recommends 8x4 when MSAA is used,
+	 * however in practice 16x4 seems fastest.
+	 *
+	 * Note that PS/WM thread counts depend on the WIZ hashing
+	 * disable bit, which we don't touch here, but it's good
+	 * to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
+	 */
+	wa_add(wal, GEN7_GT_MODE, 0,
+	       _MASKED_FIELD(GEN6_WIZ_HASHING_MASK, GEN6_WIZ_HASHING_16x4),
+	       GEN6_WIZ_HASHING_16x4);
+
+	/*
+	 * WaIncreaseL3CreditsForVLVB0:vlv
+	 * This is the hardware default actually.
+	 */
+	wa_write(wal, GEN7_L3SQCREG1, VLV_B0_WA_L3SQCREG1_VALUE);
+}
+
+static void
+hsw_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
+{
+	/* L3 caching of data atomics doesn't work -- disable it. */
+	wa_write(wal, HSW_SCRATCH1, HSW_SCRATCH1_L3_DATA_ATOMICS_DISABLE);
+
+	wa_add(wal,
+	       HSW_ROW_CHICKEN3, 0,
+	       _MASKED_BIT_ENABLE(HSW_ROW_CHICKEN3_L3_GLOBAL_ATOMICS_DISABLE),
+		0 /* XXX does this reg exist? */);
+
+	/* WaVSRefCountFullforceMissDisable:hsw */
+	wa_write_clr(wal, GEN7_FF_THREAD_MODE, GEN7_FF_VS_REF_CNT_FFME);
+
+	wa_masked_dis(wal,
+		      CACHE_MODE_0_GEN7,
+		      /* WaDisable_RenderCache_OperationalFlush:hsw */
+		      RC_OP_FLUSH_ENABLE |
+		      /* enable HiZ Raw Stall Optimization */
+		      HIZ_RAW_STALL_OPT_DISABLE);
+
+	/* WaDisable4x2SubspanOptimization:hsw */
+	wa_masked_en(wal, CACHE_MODE_1, PIXEL_SUBSPAN_COLLECT_OPT_DISABLE);
+
+	/*
+	 * BSpec recommends 8x4 when MSAA is used,
+	 * however in practice 16x4 seems fastest.
+	 *
+	 * Note that PS/WM thread counts depend on the WIZ hashing
+	 * disable bit, which we don't touch here, but it's good
+	 * to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
+	 */
+	wa_add(wal, GEN7_GT_MODE, 0,
+	       _MASKED_FIELD(GEN6_WIZ_HASHING_MASK, GEN6_WIZ_HASHING_16x4),
+	       GEN6_WIZ_HASHING_16x4);
+
+	/* WaSampleCChickenBitEnable:hsw */
+	wa_masked_en(wal, HALF_SLICE_CHICKEN3, HSW_SAMPLE_C_PERFORMANCE);
+}
+
+static void
 gen9_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
 {
 	/* WaDisableKillLogic:bxt,skl,kbl */
@@ -963,6 +1190,20 @@ gt_init_workarounds(struct drm_i915_private *i915, struct i915_wa_list *wal)
 		bxt_gt_workarounds_init(i915, wal);
 	else if (IS_SKYLAKE(i915))
 		skl_gt_workarounds_init(i915, wal);
+	else if (IS_HASWELL(i915))
+		hsw_gt_workarounds_init(i915, wal);
+	else if (IS_VALLEYVIEW(i915))
+		vlv_gt_workarounds_init(i915, wal);
+	else if (IS_IVYBRIDGE(i915))
+		ivb_gt_workarounds_init(i915, wal);
+	else if (IS_GEN(i915, 6))
+		snb_gt_workarounds_init(i915, wal);
+	else if (IS_GEN(i915, 5))
+		ilk_gt_workarounds_init(i915, wal);
+	else if (IS_G4X(i915))
+		g4x_gt_workarounds_init(i915, wal);
+	else if (IS_GEN(i915, 4))
+		gen4_gt_workarounds_init(i915, wal);
 	else if (INTEL_GEN(i915) <= 8)
 		return;
 	else
diff --git a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
index 2b2efff6e19d..4aa4cc917d8b 100644
--- a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
+++ b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
@@ -310,22 +310,20 @@ static bool wait_until_running(struct hang *h, struct i915_request *rq)
 			  1000));
 }
 
-static void engine_heartbeat_disable(struct intel_engine_cs *engine,
-				     unsigned long *saved)
+static void engine_heartbeat_disable(struct intel_engine_cs *engine)
 {
-	*saved = engine->props.heartbeat_interval_ms;
 	engine->props.heartbeat_interval_ms = 0;
 
 	intel_engine_pm_get(engine);
 	intel_engine_park_heartbeat(engine);
 }
 
-static void engine_heartbeat_enable(struct intel_engine_cs *engine,
-				    unsigned long saved)
+static void engine_heartbeat_enable(struct intel_engine_cs *engine)
 {
 	intel_engine_pm_put(engine);
 
-	engine->props.heartbeat_interval_ms = saved;
+	engine->props.heartbeat_interval_ms =
+		engine->defaults.heartbeat_interval_ms;
 }
 
 static int igt_hang_sanitycheck(void *arg)
@@ -473,7 +471,6 @@ static int igt_reset_nop_engine(void *arg)
 	for_each_engine(engine, gt, id) {
 		unsigned int reset_count, reset_engine_count, count;
 		struct intel_context *ce;
-		unsigned long heartbeat;
 		IGT_TIMEOUT(end_time);
 		int err;
 
@@ -485,7 +482,7 @@ static int igt_reset_nop_engine(void *arg)
 		reset_engine_count = i915_reset_engine_count(global, engine);
 		count = 0;
 
-		engine_heartbeat_disable(engine, &heartbeat);
+		engine_heartbeat_disable(engine);
 		set_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
 		do {
 			int i;
@@ -529,7 +526,7 @@ static int igt_reset_nop_engine(void *arg)
 			}
 		} while (time_before(jiffies, end_time));
 		clear_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
-		engine_heartbeat_enable(engine, heartbeat);
+		engine_heartbeat_enable(engine);
 
 		pr_info("%s(%s): %d resets\n", __func__, engine->name, count);
 
@@ -564,7 +561,6 @@ static int __igt_reset_engine(struct intel_gt *gt, bool active)
 
 	for_each_engine(engine, gt, id) {
 		unsigned int reset_count, reset_engine_count;
-		unsigned long heartbeat;
 		IGT_TIMEOUT(end_time);
 
 		if (active && !intel_engine_can_store_dword(engine))
@@ -580,7 +576,7 @@ static int __igt_reset_engine(struct intel_gt *gt, bool active)
 		reset_count = i915_reset_count(global);
 		reset_engine_count = i915_reset_engine_count(global, engine);
 
-		engine_heartbeat_disable(engine, &heartbeat);
+		engine_heartbeat_disable(engine);
 		set_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
 		do {
 			if (active) {
@@ -632,7 +628,7 @@ static int __igt_reset_engine(struct intel_gt *gt, bool active)
 			}
 		} while (time_before(jiffies, end_time));
 		clear_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
-		engine_heartbeat_enable(engine, heartbeat);
+		engine_heartbeat_enable(engine);
 
 		if (err)
 			break;
@@ -789,7 +785,6 @@ static int __igt_reset_engines(struct intel_gt *gt,
 		struct active_engine threads[I915_NUM_ENGINES] = {};
 		unsigned long device = i915_reset_count(global);
 		unsigned long count = 0, reported;
-		unsigned long heartbeat;
 		IGT_TIMEOUT(end_time);
 
 		if (flags & TEST_ACTIVE &&
@@ -832,7 +827,7 @@ static int __igt_reset_engines(struct intel_gt *gt,
 
 		yield(); /* start all threads before we begin */
 
-		engine_heartbeat_disable(engine, &heartbeat);
+		engine_heartbeat_disable(engine);
 		set_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
 		do {
 			struct i915_request *rq = NULL;
@@ -906,7 +901,7 @@ static int __igt_reset_engines(struct intel_gt *gt,
 			}
 		} while (time_before(jiffies, end_time));
 		clear_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
-		engine_heartbeat_enable(engine, heartbeat);
+		engine_heartbeat_enable(engine);
 
 		pr_info("i915_reset_engine(%s:%s): %lu resets\n",
 			engine->name, test_name, count);
diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c
index 824f99c4cc7c..924bc01ef526 100644
--- a/drivers/gpu/drm/i915/gt/selftest_lrc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c
@@ -51,22 +51,20 @@ static struct i915_vma *create_scratch(struct intel_gt *gt)
 	return vma;
 }
 
-static void engine_heartbeat_disable(struct intel_engine_cs *engine,
-				     unsigned long *saved)
+static void engine_heartbeat_disable(struct intel_engine_cs *engine)
 {
-	*saved = engine->props.heartbeat_interval_ms;
 	engine->props.heartbeat_interval_ms = 0;
 
 	intel_engine_pm_get(engine);
 	intel_engine_park_heartbeat(engine);
 }
 
-static void engine_heartbeat_enable(struct intel_engine_cs *engine,
-				    unsigned long saved)
+static void engine_heartbeat_enable(struct intel_engine_cs *engine)
 {
 	intel_engine_pm_put(engine);
 
-	engine->props.heartbeat_interval_ms = saved;
+	engine->props.heartbeat_interval_ms =
+		engine->defaults.heartbeat_interval_ms;
 }
 
 static bool is_active(struct i915_request *rq)
@@ -224,7 +222,6 @@ static int live_unlite_restore(struct intel_gt *gt, int prio)
 		struct intel_context *ce[2] = {};
 		struct i915_request *rq[2];
 		struct igt_live_test t;
-		unsigned long saved;
 		int n;
 
 		if (prio && !intel_engine_has_preemption(engine))
@@ -237,7 +234,7 @@ static int live_unlite_restore(struct intel_gt *gt, int prio)
 			err = -EIO;
 			break;
 		}
-		engine_heartbeat_disable(engine, &saved);
+		engine_heartbeat_disable(engine);
 
 		for (n = 0; n < ARRAY_SIZE(ce); n++) {
 			struct intel_context *tmp;
@@ -345,7 +342,7 @@ err_ce:
 			intel_context_put(ce[n]);
 		}
 
-		engine_heartbeat_enable(engine, saved);
+		engine_heartbeat_enable(engine);
 		if (igt_live_test_end(&t))
 			err = -EIO;
 		if (err)
@@ -466,7 +463,6 @@ static int live_hold_reset(void *arg)
 
 	for_each_engine(engine, gt, id) {
 		struct intel_context *ce;
-		unsigned long heartbeat;
 		struct i915_request *rq;
 
 		ce = intel_context_create(engine);
@@ -475,7 +471,7 @@ static int live_hold_reset(void *arg)
 			break;
 		}
 
-		engine_heartbeat_disable(engine, &heartbeat);
+		engine_heartbeat_disable(engine);
 
 		rq = igt_spinner_create_request(&spin, ce, MI_ARB_CHECK);
 		if (IS_ERR(rq)) {
@@ -535,7 +531,7 @@ static int live_hold_reset(void *arg)
 		i915_request_put(rq);
 
 out:
-		engine_heartbeat_enable(engine, heartbeat);
+		engine_heartbeat_enable(engine);
 		intel_context_put(ce);
 		if (err)
 			break;
@@ -580,10 +576,9 @@ static int live_error_interrupt(void *arg)
 
 	for_each_engine(engine, gt, id) {
 		const struct error_phase *p;
-		unsigned long heartbeat;
 		int err = 0;
 
-		engine_heartbeat_disable(engine, &heartbeat);
+		engine_heartbeat_disable(engine);
 
 		for (p = phases; p->error[0] != GOOD; p++) {
 			struct i915_request *client[ARRAY_SIZE(phases->error)];
@@ -682,7 +677,7 @@ out:
 			}
 		}
 
-		engine_heartbeat_enable(engine, heartbeat);
+		engine_heartbeat_enable(engine);
 		if (err) {
 			intel_gt_set_wedged(gt);
 			return err;
@@ -828,7 +823,7 @@ slice_semaphore_queue(struct intel_engine_cs *outer,
 		}
 	}
 
-	err = release_queue(outer, vma, n, INT_MAX);
+	err = release_queue(outer, vma, n, I915_PRIORITY_BARRIER);
 	if (err)
 		goto out;
 
@@ -895,16 +890,14 @@ static int live_timeslice_preempt(void *arg)
 		enum intel_engine_id id;
 
 		for_each_engine(engine, gt, id) {
-			unsigned long saved;
-
 			if (!intel_engine_has_preemption(engine))
 				continue;
 
 			memset(vaddr, 0, PAGE_SIZE);
 
-			engine_heartbeat_disable(engine, &saved);
+			engine_heartbeat_disable(engine);
 			err = slice_semaphore_queue(engine, vma, count);
-			engine_heartbeat_enable(engine, saved);
+			engine_heartbeat_enable(engine);
 			if (err)
 				goto err_pin;
 
@@ -1009,7 +1002,6 @@ static int live_timeslice_rewind(void *arg)
 		enum { X = 1, Z, Y };
 		struct i915_request *rq[3] = {};
 		struct intel_context *ce;
-		unsigned long heartbeat;
 		unsigned long timeslice;
 		int i, err = 0;
 		u32 *slot;
@@ -1028,7 +1020,7 @@ static int live_timeslice_rewind(void *arg)
 		 * Expect execution/evaluation order XZY
 		 */
 
-		engine_heartbeat_disable(engine, &heartbeat);
+		engine_heartbeat_disable(engine);
 		timeslice = xchg(&engine->props.timeslice_duration_ms, 1);
 
 		slot = memset32(engine->status_page.addr + 1000, 0, 4);
@@ -1122,7 +1114,7 @@ err:
 		wmb();
 
 		engine->props.timeslice_duration_ms = timeslice;
-		engine_heartbeat_enable(engine, heartbeat);
+		engine_heartbeat_enable(engine);
 		for (i = 0; i < 3; i++)
 			i915_request_put(rq[i]);
 		if (igt_flush_test(gt->i915))
@@ -1202,12 +1194,11 @@ static int live_timeslice_queue(void *arg)
 			.priority = I915_USER_PRIORITY(I915_PRIORITY_MAX),
 		};
 		struct i915_request *rq, *nop;
-		unsigned long saved;
 
 		if (!intel_engine_has_preemption(engine))
 			continue;
 
-		engine_heartbeat_disable(engine, &saved);
+		engine_heartbeat_disable(engine);
 		memset(vaddr, 0, PAGE_SIZE);
 
 		/* ELSP[0]: semaphore wait */
@@ -1284,7 +1275,7 @@ static int live_timeslice_queue(void *arg)
 err_rq:
 		i915_request_put(rq);
 err_heartbeat:
-		engine_heartbeat_enable(engine, saved);
+		engine_heartbeat_enable(engine);
 		if (err)
 			break;
 	}
@@ -1298,6 +1289,121 @@ err_obj:
 	return err;
 }
 
+static int live_timeslice_nopreempt(void *arg)
+{
+	struct intel_gt *gt = arg;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	struct igt_spinner spin;
+	int err = 0;
+
+	/*
+	 * We should not timeslice into a request that is marked with
+	 * I915_REQUEST_NOPREEMPT.
+	 */
+	if (!IS_ACTIVE(CONFIG_DRM_I915_TIMESLICE_DURATION))
+		return 0;
+
+	if (igt_spinner_init(&spin, gt))
+		return -ENOMEM;
+
+	for_each_engine(engine, gt, id) {
+		struct intel_context *ce;
+		struct i915_request *rq;
+		unsigned long timeslice;
+
+		if (!intel_engine_has_preemption(engine))
+			continue;
+
+		ce = intel_context_create(engine);
+		if (IS_ERR(ce)) {
+			err = PTR_ERR(ce);
+			break;
+		}
+
+		engine_heartbeat_disable(engine);
+		timeslice = xchg(&engine->props.timeslice_duration_ms, 1);
+
+		/* Create an unpreemptible spinner */
+
+		rq = igt_spinner_create_request(&spin, ce, MI_ARB_CHECK);
+		intel_context_put(ce);
+		if (IS_ERR(rq)) {
+			err = PTR_ERR(rq);
+			goto out_heartbeat;
+		}
+
+		i915_request_get(rq);
+		i915_request_add(rq);
+
+		if (!igt_wait_for_spinner(&spin, rq)) {
+			i915_request_put(rq);
+			err = -ETIME;
+			goto out_spin;
+		}
+
+		set_bit(I915_FENCE_FLAG_NOPREEMPT, &rq->fence.flags);
+		i915_request_put(rq);
+
+		/* Followed by a maximum priority barrier (heartbeat) */
+
+		ce = intel_context_create(engine);
+		if (IS_ERR(ce)) {
+			err = PTR_ERR(rq);
+			goto out_spin;
+		}
+
+		rq = intel_context_create_request(ce);
+		intel_context_put(ce);
+		if (IS_ERR(rq)) {
+			err = PTR_ERR(rq);
+			goto out_spin;
+		}
+
+		rq->sched.attr.priority = I915_PRIORITY_BARRIER;
+		i915_request_get(rq);
+		i915_request_add(rq);
+
+		/*
+		 * Wait until the barrier is in ELSP, and we know timeslicing
+		 * will have been activated.
+		 */
+		if (wait_for_submit(engine, rq, HZ / 2)) {
+			i915_request_put(rq);
+			err = -ETIME;
+			goto out_spin;
+		}
+
+		/*
+		 * Since the ELSP[0] request is unpreemptible, it should not
+		 * allow the maximum priority barrier through. Wait long
+		 * enough to see if it is timesliced in by mistake.
+		 */
+		if (i915_request_wait(rq, 0, timeslice_threshold(engine)) >= 0) {
+			pr_err("%s: I915_PRIORITY_BARRIER request completed, bypassing no-preempt request\n",
+			       engine->name);
+			err = -EINVAL;
+		}
+		i915_request_put(rq);
+
+out_spin:
+		igt_spinner_end(&spin);
+out_heartbeat:
+		xchg(&engine->props.timeslice_duration_ms, timeslice);
+		engine_heartbeat_enable(engine);
+		if (err)
+			break;
+
+		if (igt_flush_test(gt->i915)) {
+			err = -EIO;
+			break;
+		}
+	}
+
+	igt_spinner_fini(&spin);
+	return err;
+}
+
 static int live_busywait_preempt(void *arg)
 {
 	struct intel_gt *gt = arg;
@@ -4153,7 +4259,6 @@ static int reset_virtual_engine(struct intel_gt *gt,
 {
 	struct intel_engine_cs *engine;
 	struct intel_context *ve;
-	unsigned long *heartbeat;
 	struct igt_spinner spin;
 	struct i915_request *rq;
 	unsigned int n;
@@ -4165,15 +4270,9 @@ static int reset_virtual_engine(struct intel_gt *gt,
 	 * descendents are not executed while the capture is in progress.
 	 */
 
-	heartbeat = kmalloc_array(nsibling, sizeof(*heartbeat), GFP_KERNEL);
-	if (!heartbeat)
+	if (igt_spinner_init(&spin, gt))
 		return -ENOMEM;
 
-	if (igt_spinner_init(&spin, gt)) {
-		err = -ENOMEM;
-		goto out_free;
-	}
-
 	ve = intel_execlists_create_virtual(siblings, nsibling);
 	if (IS_ERR(ve)) {
 		err = PTR_ERR(ve);
@@ -4181,7 +4280,7 @@ static int reset_virtual_engine(struct intel_gt *gt,
 	}
 
 	for (n = 0; n < nsibling; n++)
-		engine_heartbeat_disable(siblings[n], &heartbeat[n]);
+		engine_heartbeat_disable(siblings[n]);
 
 	rq = igt_spinner_create_request(&spin, ve, MI_ARB_CHECK);
 	if (IS_ERR(rq)) {
@@ -4252,13 +4351,11 @@ out_rq:
 	i915_request_put(rq);
 out_heartbeat:
 	for (n = 0; n < nsibling; n++)
-		engine_heartbeat_enable(siblings[n], heartbeat[n]);
+		engine_heartbeat_enable(siblings[n]);
 
 	intel_context_put(ve);
 out_spin:
 	igt_spinner_fini(&spin);
-out_free:
-	kfree(heartbeat);
 	return err;
 }
 
@@ -4314,6 +4411,7 @@ int intel_execlists_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(live_timeslice_preempt),
 		SUBTEST(live_timeslice_rewind),
 		SUBTEST(live_timeslice_queue),
+		SUBTEST(live_timeslice_nopreempt),
 		SUBTEST(live_busywait_preempt),
 		SUBTEST(live_preempt),
 		SUBTEST(live_late_preempt),
@@ -4932,9 +5030,7 @@ static int live_lrc_gpr(void *arg)
 		return PTR_ERR(scratch);
 
 	for_each_engine(engine, gt, id) {
-		unsigned long heartbeat;
-
-		engine_heartbeat_disable(engine, &heartbeat);
+		engine_heartbeat_disable(engine);
 
 		err = __live_lrc_gpr(engine, scratch, false);
 		if (err)
@@ -4945,7 +5041,7 @@ static int live_lrc_gpr(void *arg)
 			goto err;
 
 err:
-		engine_heartbeat_enable(engine, heartbeat);
+		engine_heartbeat_enable(engine);
 		if (igt_flush_test(gt->i915))
 			err = -EIO;
 		if (err)
@@ -5092,10 +5188,9 @@ static int live_lrc_timestamp(void *arg)
 	 */
 
 	for_each_engine(data.engine, gt, id) {
-		unsigned long heartbeat;
 		int i, err = 0;
 
-		engine_heartbeat_disable(data.engine, &heartbeat);
+		engine_heartbeat_disable(data.engine);
 
 		for (i = 0; i < ARRAY_SIZE(data.ce); i++) {
 			struct intel_context *tmp;
@@ -5128,7 +5223,7 @@ static int live_lrc_timestamp(void *arg)
 		}
 
 err:
-		engine_heartbeat_enable(data.engine, heartbeat);
+		engine_heartbeat_enable(data.engine);
 		for (i = 0; i < ARRAY_SIZE(data.ce); i++) {
 			if (!data.ce[i])
 				break;
diff --git a/drivers/gpu/drm/i915/gt/selftest_mocs.c b/drivers/gpu/drm/i915/gt/selftest_mocs.c
index 8831ffee2061..63f87d8608c3 100644
--- a/drivers/gpu/drm/i915/gt/selftest_mocs.c
+++ b/drivers/gpu/drm/i915/gt/selftest_mocs.c
@@ -18,6 +18,20 @@ struct live_mocs {
 	void *vaddr;
 };
 
+static struct intel_context *mocs_context_create(struct intel_engine_cs *engine)
+{
+	struct intel_context *ce;
+
+	ce = intel_context_create(engine);
+	if (IS_ERR(ce))
+		return ce;
+
+	/* We build large requests to read the registers from the ring */
+	ce->ring = __intel_context_ring_size(SZ_16K);
+
+	return ce;
+}
+
 static int request_add_sync(struct i915_request *rq, int err)
 {
 	i915_request_get(rq);
@@ -301,7 +315,7 @@ static int live_mocs_clean(void *arg)
 	for_each_engine(engine, gt, id) {
 		struct intel_context *ce;
 
-		ce = intel_context_create(engine);
+		ce = mocs_context_create(engine);
 		if (IS_ERR(ce)) {
 			err = PTR_ERR(ce);
 			break;
@@ -395,7 +409,7 @@ static int live_mocs_reset(void *arg)
 	for_each_engine(engine, gt, id) {
 		struct intel_context *ce;
 
-		ce = intel_context_create(engine);
+		ce = mocs_context_create(engine);
 		if (IS_ERR(ce)) {
 			err = PTR_ERR(ce);
 			break;
diff --git a/drivers/gpu/drm/i915/gt/selftest_ring.c b/drivers/gpu/drm/i915/gt/selftest_ring.c
new file mode 100644
index 000000000000..2a8c534dc125
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/selftest_ring.c
@@ -0,0 +1,110 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+static struct intel_ring *mock_ring(unsigned long sz)
+{
+	struct intel_ring *ring;
+
+	ring = kzalloc(sizeof(*ring) + sz, GFP_KERNEL);
+	if (!ring)
+		return NULL;
+
+	kref_init(&ring->ref);
+	ring->size = sz;
+	ring->wrap = BITS_PER_TYPE(ring->size) - ilog2(sz);
+	ring->effective_size = sz;
+	ring->vaddr = (void *)(ring + 1);
+	atomic_set(&ring->pin_count, 1);
+
+	intel_ring_update_space(ring);
+
+	return ring;
+}
+
+static void mock_ring_free(struct intel_ring *ring)
+{
+	kfree(ring);
+}
+
+static int check_ring_direction(struct intel_ring *ring,
+				u32 next, u32 prev,
+				int expected)
+{
+	int result;
+
+	result = intel_ring_direction(ring, next, prev);
+	if (result < 0)
+		result = -1;
+	else if (result > 0)
+		result = 1;
+
+	if (result != expected) {
+		pr_err("intel_ring_direction(%u, %u):%d != %d\n",
+		       next, prev, result, expected);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int check_ring_step(struct intel_ring *ring, u32 x, u32 step)
+{
+	u32 prev = x, next = intel_ring_wrap(ring, x + step);
+	int err = 0;
+
+	err |= check_ring_direction(ring, next, next,  0);
+	err |= check_ring_direction(ring, prev, prev,  0);
+	err |= check_ring_direction(ring, next, prev,  1);
+	err |= check_ring_direction(ring, prev, next, -1);
+
+	return err;
+}
+
+static int check_ring_offset(struct intel_ring *ring, u32 x, u32 step)
+{
+	int err = 0;
+
+	err |= check_ring_step(ring, x, step);
+	err |= check_ring_step(ring, intel_ring_wrap(ring, x + 1), step);
+	err |= check_ring_step(ring, intel_ring_wrap(ring, x - 1), step);
+
+	return err;
+}
+
+static int igt_ring_direction(void *dummy)
+{
+	struct intel_ring *ring;
+	unsigned int half = 2048;
+	int step, err = 0;
+
+	ring = mock_ring(2 * half);
+	if (!ring)
+		return -ENOMEM;
+
+	GEM_BUG_ON(ring->size != 2 * half);
+
+	/* Precision of wrap detection is limited to ring->size / 2 */
+	for (step = 1; step < half; step <<= 1) {
+		err |= check_ring_offset(ring, 0, step);
+		err |= check_ring_offset(ring, half, step);
+	}
+	err |= check_ring_step(ring, 0, half - 64);
+
+	/* And check unwrapped handling for good measure */
+	err |= check_ring_offset(ring, 0, 2 * half + 64);
+	err |= check_ring_offset(ring, 3 * half, 1);
+
+	mock_ring_free(ring);
+	return err;
+}
+
+int intel_ring_mock_selftests(void)
+{
+	static const struct i915_subtest tests[] = {
+		SUBTEST(igt_ring_direction),
+	};
+
+	return i915_subtests(tests, NULL);
+}
diff --git a/drivers/gpu/drm/i915/gt/selftest_rps.c b/drivers/gpu/drm/i915/gt/selftest_rps.c
index 6275d69aa9cc..5049c3dd08a6 100644
--- a/drivers/gpu/drm/i915/gt/selftest_rps.c
+++ b/drivers/gpu/drm/i915/gt/selftest_rps.c
@@ -20,24 +20,20 @@
 /* Try to isolate the impact of cstates from determing frequency response */
 #define CPU_LATENCY 0 /* -1 to disable pm_qos, 0 to disable cstates */
 
-static unsigned long engine_heartbeat_disable(struct intel_engine_cs *engine)
+static void engine_heartbeat_disable(struct intel_engine_cs *engine)
 {
-	unsigned long old;
-
-	old = fetch_and_zero(&engine->props.heartbeat_interval_ms);
+	engine->props.heartbeat_interval_ms = 0;
 
 	intel_engine_pm_get(engine);
 	intel_engine_park_heartbeat(engine);
-
-	return old;
 }
 
-static void engine_heartbeat_enable(struct intel_engine_cs *engine,
-				    unsigned long saved)
+static void engine_heartbeat_enable(struct intel_engine_cs *engine)
 {
 	intel_engine_pm_put(engine);
 
-	engine->props.heartbeat_interval_ms = saved;
+	engine->props.heartbeat_interval_ms =
+		engine->defaults.heartbeat_interval_ms;
 }
 
 static void dummy_rps_work(struct work_struct *wrk)
@@ -246,7 +242,6 @@ int live_rps_clock_interval(void *arg)
 	intel_gt_check_clock_frequency(gt);
 
 	for_each_engine(engine, gt, id) {
-		unsigned long saved_heartbeat;
 		struct i915_request *rq;
 		u32 cycles;
 		u64 dt;
@@ -254,13 +249,13 @@ int live_rps_clock_interval(void *arg)
 		if (!intel_engine_can_store_dword(engine))
 			continue;
 
-		saved_heartbeat = engine_heartbeat_disable(engine);
+		engine_heartbeat_disable(engine);
 
 		rq = igt_spinner_create_request(&spin,
 						engine->kernel_context,
 						MI_NOOP);
 		if (IS_ERR(rq)) {
-			engine_heartbeat_enable(engine, saved_heartbeat);
+			engine_heartbeat_enable(engine);
 			err = PTR_ERR(rq);
 			break;
 		}
@@ -271,7 +266,7 @@ int live_rps_clock_interval(void *arg)
 			pr_err("%s: RPS spinner did not start\n",
 			       engine->name);
 			igt_spinner_end(&spin);
-			engine_heartbeat_enable(engine, saved_heartbeat);
+			engine_heartbeat_enable(engine);
 			intel_gt_set_wedged(engine->gt);
 			err = -EIO;
 			break;
@@ -327,7 +322,7 @@ int live_rps_clock_interval(void *arg)
 		intel_uncore_forcewake_put(gt->uncore, FORCEWAKE_ALL);
 
 		igt_spinner_end(&spin);
-		engine_heartbeat_enable(engine, saved_heartbeat);
+		engine_heartbeat_enable(engine);
 
 		if (err == 0) {
 			u64 time = intel_gt_pm_interval_to_ns(gt, cycles);
@@ -405,7 +400,6 @@ int live_rps_control(void *arg)
 
 	intel_gt_pm_get(gt);
 	for_each_engine(engine, gt, id) {
-		unsigned long saved_heartbeat;
 		struct i915_request *rq;
 		ktime_t min_dt, max_dt;
 		int f, limit;
@@ -414,7 +408,7 @@ int live_rps_control(void *arg)
 		if (!intel_engine_can_store_dword(engine))
 			continue;
 
-		saved_heartbeat = engine_heartbeat_disable(engine);
+		engine_heartbeat_disable(engine);
 
 		rq = igt_spinner_create_request(&spin,
 						engine->kernel_context,
@@ -430,7 +424,7 @@ int live_rps_control(void *arg)
 			pr_err("%s: RPS spinner did not start\n",
 			       engine->name);
 			igt_spinner_end(&spin);
-			engine_heartbeat_enable(engine, saved_heartbeat);
+			engine_heartbeat_enable(engine);
 			intel_gt_set_wedged(engine->gt);
 			err = -EIO;
 			break;
@@ -440,7 +434,7 @@ int live_rps_control(void *arg)
 			pr_err("%s: could not set minimum frequency [%x], only %x!\n",
 			       engine->name, rps->min_freq, read_cagf(rps));
 			igt_spinner_end(&spin);
-			engine_heartbeat_enable(engine, saved_heartbeat);
+			engine_heartbeat_enable(engine);
 			show_pstate_limits(rps);
 			err = -EINVAL;
 			break;
@@ -457,7 +451,7 @@ int live_rps_control(void *arg)
 			pr_err("%s: could not restore minimum frequency [%x], only %x!\n",
 			       engine->name, rps->min_freq, read_cagf(rps));
 			igt_spinner_end(&spin);
-			engine_heartbeat_enable(engine, saved_heartbeat);
+			engine_heartbeat_enable(engine);
 			show_pstate_limits(rps);
 			err = -EINVAL;
 			break;
@@ -472,7 +466,7 @@ int live_rps_control(void *arg)
 		min_dt = ktime_sub(ktime_get(), min_dt);
 
 		igt_spinner_end(&spin);
-		engine_heartbeat_enable(engine, saved_heartbeat);
+		engine_heartbeat_enable(engine);
 
 		pr_info("%s: range:[%x:%uMHz, %x:%uMHz] limit:[%x:%uMHz], %x:%x response %lluns:%lluns\n",
 			engine->name,
@@ -635,7 +629,6 @@ int live_rps_frequency_cs(void *arg)
 	rps->work.func = dummy_rps_work;
 
 	for_each_engine(engine, gt, id) {
-		unsigned long saved_heartbeat;
 		struct i915_request *rq;
 		struct i915_vma *vma;
 		u32 *cancel, *cntr;
@@ -644,14 +637,14 @@ int live_rps_frequency_cs(void *arg)
 			int freq;
 		} min, max;
 
-		saved_heartbeat = engine_heartbeat_disable(engine);
+		engine_heartbeat_disable(engine);
 
 		vma = create_spin_counter(engine,
 					  engine->kernel_context->vm, false,
 					  &cancel, &cntr);
 		if (IS_ERR(vma)) {
 			err = PTR_ERR(vma);
-			engine_heartbeat_enable(engine, saved_heartbeat);
+			engine_heartbeat_enable(engine);
 			break;
 		}
 
@@ -732,7 +725,7 @@ err_vma:
 		i915_vma_unpin(vma);
 		i915_vma_put(vma);
 
-		engine_heartbeat_enable(engine, saved_heartbeat);
+		engine_heartbeat_enable(engine);
 		if (igt_flush_test(gt->i915))
 			err = -EIO;
 		if (err)
@@ -778,7 +771,6 @@ int live_rps_frequency_srm(void *arg)
 	rps->work.func = dummy_rps_work;
 
 	for_each_engine(engine, gt, id) {
-		unsigned long saved_heartbeat;
 		struct i915_request *rq;
 		struct i915_vma *vma;
 		u32 *cancel, *cntr;
@@ -787,14 +779,14 @@ int live_rps_frequency_srm(void *arg)
 			int freq;
 		} min, max;
 
-		saved_heartbeat = engine_heartbeat_disable(engine);
+		engine_heartbeat_disable(engine);
 
 		vma = create_spin_counter(engine,
 					  engine->kernel_context->vm, true,
 					  &cancel, &cntr);
 		if (IS_ERR(vma)) {
 			err = PTR_ERR(vma);
-			engine_heartbeat_enable(engine, saved_heartbeat);
+			engine_heartbeat_enable(engine);
 			break;
 		}
 
@@ -874,7 +866,7 @@ err_vma:
 		i915_vma_unpin(vma);
 		i915_vma_put(vma);
 
-		engine_heartbeat_enable(engine, saved_heartbeat);
+		engine_heartbeat_enable(engine);
 		if (igt_flush_test(gt->i915))
 			err = -EIO;
 		if (err)
@@ -1066,16 +1058,14 @@ int live_rps_interrupt(void *arg)
 	for_each_engine(engine, gt, id) {
 		/* Keep the engine busy with a spinner; expect an UP! */
 		if (pm_events & GEN6_PM_RP_UP_THRESHOLD) {
-			unsigned long saved_heartbeat;
-
 			intel_gt_pm_wait_for_idle(engine->gt);
 			GEM_BUG_ON(intel_rps_is_active(rps));
 
-			saved_heartbeat = engine_heartbeat_disable(engine);
+			engine_heartbeat_disable(engine);
 
 			err = __rps_up_interrupt(rps, engine, &spin);
 
-			engine_heartbeat_enable(engine, saved_heartbeat);
+			engine_heartbeat_enable(engine);
 			if (err)
 				goto out;
 
@@ -1084,15 +1074,13 @@ int live_rps_interrupt(void *arg)
 
 		/* Keep the engine awake but idle and check for DOWN */
 		if (pm_events & GEN6_PM_RP_DOWN_THRESHOLD) {
-			unsigned long saved_heartbeat;
-
-			saved_heartbeat = engine_heartbeat_disable(engine);
+			engine_heartbeat_disable(engine);
 			intel_rc6_disable(&gt->rc6);
 
 			err = __rps_down_interrupt(rps, engine);
 
 			intel_rc6_enable(&gt->rc6);
-			engine_heartbeat_enable(engine, saved_heartbeat);
+			engine_heartbeat_enable(engine);
 			if (err)
 				goto out;
 		}
@@ -1168,7 +1156,6 @@ int live_rps_power(void *arg)
 	rps->work.func = dummy_rps_work;
 
 	for_each_engine(engine, gt, id) {
-		unsigned long saved_heartbeat;
 		struct i915_request *rq;
 		struct {
 			u64 power;
@@ -1178,13 +1165,13 @@ int live_rps_power(void *arg)
 		if (!intel_engine_can_store_dword(engine))
 			continue;
 
-		saved_heartbeat = engine_heartbeat_disable(engine);
+		engine_heartbeat_disable(engine);
 
 		rq = igt_spinner_create_request(&spin,
 						engine->kernel_context,
 						MI_NOOP);
 		if (IS_ERR(rq)) {
-			engine_heartbeat_enable(engine, saved_heartbeat);
+			engine_heartbeat_enable(engine);
 			err = PTR_ERR(rq);
 			break;
 		}
@@ -1195,7 +1182,7 @@ int live_rps_power(void *arg)
 			pr_err("%s: RPS spinner did not start\n",
 			       engine->name);
 			igt_spinner_end(&spin);
-			engine_heartbeat_enable(engine, saved_heartbeat);
+			engine_heartbeat_enable(engine);
 			intel_gt_set_wedged(engine->gt);
 			err = -EIO;
 			break;
@@ -1208,7 +1195,7 @@ int live_rps_power(void *arg)
 		min.power = measure_power_at(rps, &min.freq);
 
 		igt_spinner_end(&spin);
-		engine_heartbeat_enable(engine, saved_heartbeat);
+		engine_heartbeat_enable(engine);
 
 		pr_info("%s: min:%llumW @ %uMHz, max:%llumW @ %uMHz\n",
 			engine->name,
diff --git a/drivers/gpu/drm/i915/gt/selftest_timeline.c b/drivers/gpu/drm/i915/gt/selftest_timeline.c
index c2578a0f2f14..ef1c35073dc0 100644
--- a/drivers/gpu/drm/i915/gt/selftest_timeline.c
+++ b/drivers/gpu/drm/i915/gt/selftest_timeline.c
@@ -751,22 +751,20 @@ out_free:
 	return err;
 }
 
-static void engine_heartbeat_disable(struct intel_engine_cs *engine,
-				     unsigned long *saved)
+static void engine_heartbeat_disable(struct intel_engine_cs *engine)
 {
-	*saved = engine->props.heartbeat_interval_ms;
 	engine->props.heartbeat_interval_ms = 0;
 
 	intel_engine_pm_get(engine);
 	intel_engine_park_heartbeat(engine);
 }
 
-static void engine_heartbeat_enable(struct intel_engine_cs *engine,
-				    unsigned long saved)
+static void engine_heartbeat_enable(struct intel_engine_cs *engine)
 {
 	intel_engine_pm_put(engine);
 
-	engine->props.heartbeat_interval_ms = saved;
+	engine->props.heartbeat_interval_ms =
+		engine->defaults.heartbeat_interval_ms;
 }
 
 static int live_hwsp_rollover_kernel(void *arg)
@@ -785,10 +783,9 @@ static int live_hwsp_rollover_kernel(void *arg)
 		struct intel_context *ce = engine->kernel_context;
 		struct intel_timeline *tl = ce->timeline;
 		struct i915_request *rq[3] = {};
-		unsigned long heartbeat;
 		int i;
 
-		engine_heartbeat_disable(engine, &heartbeat);
+		engine_heartbeat_disable(engine);
 		if (intel_gt_wait_for_idle(gt, HZ / 2)) {
 			err = -EIO;
 			goto out;
@@ -839,7 +836,7 @@ static int live_hwsp_rollover_kernel(void *arg)
 out:
 		for (i = 0; i < ARRAY_SIZE(rq); i++)
 			i915_request_put(rq[i]);
-		engine_heartbeat_enable(engine, heartbeat);
+		engine_heartbeat_enable(engine);
 		if (err)
 			break;
 	}
diff --git a/drivers/gpu/drm/i915/gt/selftest_workarounds.c b/drivers/gpu/drm/i915/gt/selftest_workarounds.c
index 5ed323254ee1..32785463ec9e 100644
--- a/drivers/gpu/drm/i915/gt/selftest_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/selftest_workarounds.c
@@ -623,6 +623,8 @@ err_request:
 				err = -EINVAL;
 				goto out_unpin;
 			}
+		} else {
+			rsvd = 0;
 		}
 
 		expect = results[0];
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 4dc601dffc08..284cf078135a 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -3125,6 +3125,7 @@ static void gen11_hpd_irq_setup(struct drm_i915_private *dev_priv)
 
 	val = I915_READ(GEN11_DE_HPD_IMR);
 	val &= ~hotplug_irqs;
+	val |= ~enabled_irqs & hotplug_irqs;
 	I915_WRITE(GEN11_DE_HPD_IMR, val);
 	POSTING_READ(GEN11_DE_HPD_IMR);
 
diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index e991a707bdb7..962ded9ce73f 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -269,12 +269,48 @@ static bool exclusive_mmio_access(const struct drm_i915_private *i915)
 	return IS_GEN(i915, 7);
 }
 
+static void engine_sample(struct intel_engine_cs *engine, unsigned int period_ns)
+{
+	struct intel_engine_pmu *pmu = &engine->pmu;
+	bool busy;
+	u32 val;
+
+	val = ENGINE_READ_FW(engine, RING_CTL);
+	if (val == 0) /* powerwell off => engine idle */
+		return;
+
+	if (val & RING_WAIT)
+		add_sample(&pmu->sample[I915_SAMPLE_WAIT], period_ns);
+	if (val & RING_WAIT_SEMAPHORE)
+		add_sample(&pmu->sample[I915_SAMPLE_SEMA], period_ns);
+
+	/* No need to sample when busy stats are supported. */
+	if (intel_engine_supports_stats(engine))
+		return;
+
+	/*
+	 * While waiting on a semaphore or event, MI_MODE reports the
+	 * ring as idle. However, previously using the seqno, and with
+	 * execlists sampling, we account for the ring waiting as the
+	 * engine being busy. Therefore, we record the sample as being
+	 * busy if either waiting or !idle.
+	 */
+	busy = val & (RING_WAIT_SEMAPHORE | RING_WAIT);
+	if (!busy) {
+		val = ENGINE_READ_FW(engine, RING_MI_MODE);
+		busy = !(val & MODE_IDLE);
+	}
+	if (busy)
+		add_sample(&pmu->sample[I915_SAMPLE_BUSY], period_ns);
+}
+
 static void
 engines_sample(struct intel_gt *gt, unsigned int period_ns)
 {
 	struct drm_i915_private *i915 = gt->i915;
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
+	unsigned long flags;
 
 	if ((i915->pmu.enable & ENGINE_SAMPLE_MASK) == 0)
 		return;
@@ -283,53 +319,17 @@ engines_sample(struct intel_gt *gt, unsigned int period_ns)
 		return;
 
 	for_each_engine(engine, gt, id) {
-		struct intel_engine_pmu *pmu = &engine->pmu;
-		spinlock_t *mmio_lock;
-		unsigned long flags;
-		bool busy;
-		u32 val;
-
 		if (!intel_engine_pm_get_if_awake(engine))
 			continue;
 
-		mmio_lock = NULL;
-		if (exclusive_mmio_access(i915))
-			mmio_lock = &engine->uncore->lock;
-
-		if (unlikely(mmio_lock))
-			spin_lock_irqsave(mmio_lock, flags);
-
-		val = ENGINE_READ_FW(engine, RING_CTL);
-		if (val == 0) /* powerwell off => engine idle */
-			goto skip;
-
-		if (val & RING_WAIT)
-			add_sample(&pmu->sample[I915_SAMPLE_WAIT], period_ns);
-		if (val & RING_WAIT_SEMAPHORE)
-			add_sample(&pmu->sample[I915_SAMPLE_SEMA], period_ns);
-
-		/* No need to sample when busy stats are supported. */
-		if (intel_engine_supports_stats(engine))
-			goto skip;
-
-		/*
-		 * While waiting on a semaphore or event, MI_MODE reports the
-		 * ring as idle. However, previously using the seqno, and with
-		 * execlists sampling, we account for the ring waiting as the
-		 * engine being busy. Therefore, we record the sample as being
-		 * busy if either waiting or !idle.
-		 */
-		busy = val & (RING_WAIT_SEMAPHORE | RING_WAIT);
-		if (!busy) {
-			val = ENGINE_READ_FW(engine, RING_MI_MODE);
-			busy = !(val & MODE_IDLE);
+		if (exclusive_mmio_access(i915)) {
+			spin_lock_irqsave(&engine->uncore->lock, flags);
+			engine_sample(engine, period_ns);
+			spin_unlock_irqrestore(&engine->uncore->lock, flags);
+		} else {
+			engine_sample(engine, period_ns);
 		}
-		if (busy)
-			add_sample(&pmu->sample[I915_SAMPLE_BUSY], period_ns);
 
-skip:
-		if (unlikely(mmio_lock))
-			spin_unlock_irqrestore(mmio_lock, flags);
 		intel_engine_pm_put_async(engine);
 	}
 }
diff --git a/drivers/gpu/drm/i915/i915_priolist_types.h b/drivers/gpu/drm/i915/i915_priolist_types.h
index 5003a71113cb..8aa7866ec6b6 100644
--- a/drivers/gpu/drm/i915/i915_priolist_types.h
+++ b/drivers/gpu/drm/i915/i915_priolist_types.h
@@ -42,7 +42,7 @@ enum {
  * active request.
  */
 #define I915_PRIORITY_UNPREEMPTABLE INT_MAX
-#define I915_PRIORITY_BARRIER INT_MAX
+#define I915_PRIORITY_BARRIER (I915_PRIORITY_UNPREEMPTABLE - 1)
 
 struct i915_priolist {
 	struct list_head requests[I915_PRIORITY_COUNT];
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 7717581350bd..06cd1d28a176 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -7896,7 +7896,7 @@ enum {
 
 /* GEN7 chicken */
 #define GEN7_COMMON_SLICE_CHICKEN1		_MMIO(0x7010)
-  #define GEN7_CSC1_RHWO_OPT_DISABLE_IN_RCC	((1 << 10) | (1 << 26))
+  #define GEN7_CSC1_RHWO_OPT_DISABLE_IN_RCC	(1 << 10)
   #define GEN9_RHWO_OPTIMIZATION_DISABLE	(1 << 14)
 
 #define COMMON_SLICE_CHICKEN2					_MMIO(0x7014)
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 696491d71a1d..07f663cd2d1c 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -6830,16 +6830,6 @@ static void ilk_init_clock_gating(struct drm_i915_private *dev_priv)
 	I915_WRITE(ILK_DISPLAY_CHICKEN2,
 		   I915_READ(ILK_DISPLAY_CHICKEN2) |
 		   ILK_ELPIN_409_SELECT);
-	I915_WRITE(_3D_CHICKEN2,
-		   _3D_CHICKEN2_WM_READ_PIPELINED << 16 |
-		   _3D_CHICKEN2_WM_READ_PIPELINED);
-
-	/* WaDisableRenderCachePipelinedFlush:ilk */
-	I915_WRITE(CACHE_MODE_0,
-		   _MASKED_BIT_ENABLE(CM0_PIPELINED_RENDER_FLUSH_DISABLE));
-
-	/* WaDisable_RenderCache_OperationalFlush:ilk */
-	I915_WRITE(CACHE_MODE_0, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE));
 
 	g4x_disable_trickle_feed(dev_priv);
 
@@ -6902,27 +6892,6 @@ static void gen6_init_clock_gating(struct drm_i915_private *dev_priv)
 		   I915_READ(ILK_DISPLAY_CHICKEN2) |
 		   ILK_ELPIN_409_SELECT);
 
-	/* WaDisableHiZPlanesWhenMSAAEnabled:snb */
-	I915_WRITE(_3D_CHICKEN,
-		   _MASKED_BIT_ENABLE(_3D_CHICKEN_HIZ_PLANE_DISABLE_MSAA_4X_SNB));
-
-	/* WaDisable_RenderCache_OperationalFlush:snb */
-	I915_WRITE(CACHE_MODE_0, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE));
-
-	/*
-	 * BSpec recoomends 8x4 when MSAA is used,
-	 * however in practice 16x4 seems fastest.
-	 *
-	 * Note that PS/WM thread counts depend on the WIZ hashing
-	 * disable bit, which we don't touch here, but it's good
-	 * to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
-	 */
-	I915_WRITE(GEN6_GT_MODE,
-		   _MASKED_FIELD(GEN6_WIZ_HASHING_MASK, GEN6_WIZ_HASHING_16x4));
-
-	I915_WRITE(CACHE_MODE_0,
-		   _MASKED_BIT_DISABLE(CM0_STC_EVICT_DISABLE_LRA_SNB));
-
 	I915_WRITE(GEN6_UCGCTL1,
 		   I915_READ(GEN6_UCGCTL1) |
 		   GEN6_BLBUNIT_CLOCK_GATE_DISABLE |
@@ -6945,18 +6914,6 @@ static void gen6_init_clock_gating(struct drm_i915_private *dev_priv)
 		   GEN6_RCPBUNIT_CLOCK_GATE_DISABLE |
 		   GEN6_RCCUNIT_CLOCK_GATE_DISABLE);
 
-	/* WaStripsFansDisableFastClipPerformanceFix:snb */
-	I915_WRITE(_3D_CHICKEN3,
-		   _MASKED_BIT_ENABLE(_3D_CHICKEN3_SF_DISABLE_FASTCLIP_CULL));
-
-	/*
-	 * Bspec says:
-	 * "This bit must be set if 3DSTATE_CLIP clip mode is set to normal and
-	 * 3DSTATE_SF number of SF output attributes is more than 16."
-	 */
-	I915_WRITE(_3D_CHICKEN3,
-		   _MASKED_BIT_ENABLE(_3D_CHICKEN3_SF_DISABLE_PIPELINED_ATTR_FETCH));
-
 	/*
 	 * According to the spec the following bits should be
 	 * set in order to enable memory self-refresh and fbc:
@@ -6986,24 +6943,6 @@ static void gen6_init_clock_gating(struct drm_i915_private *dev_priv)
 	gen6_check_mch_setup(dev_priv);
 }
 
-static void gen7_setup_fixed_func_scheduler(struct drm_i915_private *dev_priv)
-{
-	u32 reg = I915_READ(GEN7_FF_THREAD_MODE);
-
-	/*
-	 * WaVSThreadDispatchOverride:ivb,vlv
-	 *
-	 * This actually overrides the dispatch
-	 * mode for all thread types.
-	 */
-	reg &= ~GEN7_FF_SCHED_MASK;
-	reg |= GEN7_FF_TS_SCHED_HW;
-	reg |= GEN7_FF_VS_SCHED_HW;
-	reg |= GEN7_FF_DS_SCHED_HW;
-
-	I915_WRITE(GEN7_FF_THREAD_MODE, reg);
-}
-
 static void lpt_init_clock_gating(struct drm_i915_private *dev_priv)
 {
 	/*
@@ -7230,45 +7169,10 @@ static void bdw_init_clock_gating(struct drm_i915_private *dev_priv)
 
 static void hsw_init_clock_gating(struct drm_i915_private *dev_priv)
 {
-	/* L3 caching of data atomics doesn't work -- disable it. */
-	I915_WRITE(HSW_SCRATCH1, HSW_SCRATCH1_L3_DATA_ATOMICS_DISABLE);
-	I915_WRITE(HSW_ROW_CHICKEN3,
-		   _MASKED_BIT_ENABLE(HSW_ROW_CHICKEN3_L3_GLOBAL_ATOMICS_DISABLE));
-
 	/* This is required by WaCatErrorRejectionIssue:hsw */
 	I915_WRITE(GEN7_SQ_CHICKEN_MBCUNIT_CONFIG,
-			I915_READ(GEN7_SQ_CHICKEN_MBCUNIT_CONFIG) |
-			GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB);
-
-	/* WaVSRefCountFullforceMissDisable:hsw */
-	I915_WRITE(GEN7_FF_THREAD_MODE,
-		   I915_READ(GEN7_FF_THREAD_MODE) & ~GEN7_FF_VS_REF_CNT_FFME);
-
-	/* WaDisable_RenderCache_OperationalFlush:hsw */
-	I915_WRITE(CACHE_MODE_0_GEN7, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE));
-
-	/* enable HiZ Raw Stall Optimization */
-	I915_WRITE(CACHE_MODE_0_GEN7,
-		   _MASKED_BIT_DISABLE(HIZ_RAW_STALL_OPT_DISABLE));
-
-	/* WaDisable4x2SubspanOptimization:hsw */
-	I915_WRITE(CACHE_MODE_1,
-		   _MASKED_BIT_ENABLE(PIXEL_SUBSPAN_COLLECT_OPT_DISABLE));
-
-	/*
-	 * BSpec recommends 8x4 when MSAA is used,
-	 * however in practice 16x4 seems fastest.
-	 *
-	 * Note that PS/WM thread counts depend on the WIZ hashing
-	 * disable bit, which we don't touch here, but it's good
-	 * to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
-	 */
-	I915_WRITE(GEN7_GT_MODE,
-		   _MASKED_FIELD(GEN6_WIZ_HASHING_MASK, GEN6_WIZ_HASHING_16x4));
-
-	/* WaSampleCChickenBitEnable:hsw */
-	I915_WRITE(HALF_SLICE_CHICKEN3,
-		   _MASKED_BIT_ENABLE(HSW_SAMPLE_C_PERFORMANCE));
+		   I915_READ(GEN7_SQ_CHICKEN_MBCUNIT_CONFIG) |
+		   GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB);
 
 	/* WaSwitchSolVfFArbitrationPriority:hsw */
 	I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | HSW_ECOCHK_ARB_PRIO_SOL);
@@ -7282,32 +7186,11 @@ static void ivb_init_clock_gating(struct drm_i915_private *dev_priv)
 
 	I915_WRITE(ILK_DSPCLK_GATE_D, ILK_VRHUNIT_CLOCK_GATE_DISABLE);
 
-	/* WaDisableEarlyCull:ivb */
-	I915_WRITE(_3D_CHICKEN3,
-		   _MASKED_BIT_ENABLE(_3D_CHICKEN_SF_DISABLE_OBJEND_CULL));
-
 	/* WaDisableBackToBackFlipFix:ivb */
 	I915_WRITE(IVB_CHICKEN3,
 		   CHICKEN3_DGMG_REQ_OUT_FIX_DISABLE |
 		   CHICKEN3_DGMG_DONE_FIX_DISABLE);
 
-	/* WaDisablePSDDualDispatchEnable:ivb */
-	if (IS_IVB_GT1(dev_priv))
-		I915_WRITE(GEN7_HALF_SLICE_CHICKEN1,
-			   _MASKED_BIT_ENABLE(GEN7_PSD_SINGLE_PORT_DISPATCH_ENABLE));
-
-	/* WaDisable_RenderCache_OperationalFlush:ivb */
-	I915_WRITE(CACHE_MODE_0_GEN7, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE));
-
-	/* Apply the WaDisableRHWOOptimizationForRenderHang:ivb workaround. */
-	I915_WRITE(GEN7_COMMON_SLICE_CHICKEN1,
-		   GEN7_CSC1_RHWO_OPT_DISABLE_IN_RCC);
-
-	/* WaApplyL3ControlAndL3ChickenMode:ivb */
-	I915_WRITE(GEN7_L3CNTLREG1,
-			GEN7_WA_FOR_GEN7_L3_CONTROL);
-	I915_WRITE(GEN7_L3_CHICKEN_MODE_REGISTER,
-		   GEN7_WA_L3_CHICKEN_MODE);
 	if (IS_IVB_GT1(dev_priv))
 		I915_WRITE(GEN7_ROW_CHICKEN2,
 			   _MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE));
@@ -7319,10 +7202,6 @@ static void ivb_init_clock_gating(struct drm_i915_private *dev_priv)
 			   _MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE));
 	}
 
-	/* WaForceL3Serialization:ivb */
-	I915_WRITE(GEN7_L3SQCREG4, I915_READ(GEN7_L3SQCREG4) &
-		   ~L3SQ_URB_READ_CAM_MATCH_DISABLE);
-
 	/*
 	 * According to the spec, bit 13 (RCZUNIT) must be set on IVB.
 	 * This implements the WaDisableRCZUnitClockGating:ivb workaround.
@@ -7337,29 +7216,6 @@ static void ivb_init_clock_gating(struct drm_i915_private *dev_priv)
 
 	g4x_disable_trickle_feed(dev_priv);
 
-	gen7_setup_fixed_func_scheduler(dev_priv);
-
-	if (0) { /* causes HiZ corruption on ivb:gt1 */
-		/* enable HiZ Raw Stall Optimization */
-		I915_WRITE(CACHE_MODE_0_GEN7,
-			   _MASKED_BIT_DISABLE(HIZ_RAW_STALL_OPT_DISABLE));
-	}
-
-	/* WaDisable4x2SubspanOptimization:ivb */
-	I915_WRITE(CACHE_MODE_1,
-		   _MASKED_BIT_ENABLE(PIXEL_SUBSPAN_COLLECT_OPT_DISABLE));
-
-	/*
-	 * BSpec recommends 8x4 when MSAA is used,
-	 * however in practice 16x4 seems fastest.
-	 *
-	 * Note that PS/WM thread counts depend on the WIZ hashing
-	 * disable bit, which we don't touch here, but it's good
-	 * to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
-	 */
-	I915_WRITE(GEN7_GT_MODE,
-		   _MASKED_FIELD(GEN6_WIZ_HASHING_MASK, GEN6_WIZ_HASHING_16x4));
-
 	snpcr = I915_READ(GEN6_MBCUNIT_SNPCR);
 	snpcr &= ~GEN6_MBC_SNPCR_MASK;
 	snpcr |= GEN6_MBC_SNPCR_MED;
@@ -7373,28 +7229,11 @@ static void ivb_init_clock_gating(struct drm_i915_private *dev_priv)
 
 static void vlv_init_clock_gating(struct drm_i915_private *dev_priv)
 {
-	/* WaDisableEarlyCull:vlv */
-	I915_WRITE(_3D_CHICKEN3,
-		   _MASKED_BIT_ENABLE(_3D_CHICKEN_SF_DISABLE_OBJEND_CULL));
-
 	/* WaDisableBackToBackFlipFix:vlv */
 	I915_WRITE(IVB_CHICKEN3,
 		   CHICKEN3_DGMG_REQ_OUT_FIX_DISABLE |
 		   CHICKEN3_DGMG_DONE_FIX_DISABLE);
 
-	/* WaPsdDispatchEnable:vlv */
-	/* WaDisablePSDDualDispatchEnable:vlv */
-	I915_WRITE(GEN7_HALF_SLICE_CHICKEN1,
-		   _MASKED_BIT_ENABLE(GEN7_MAX_PS_THREAD_DEP |
-				      GEN7_PSD_SINGLE_PORT_DISPATCH_ENABLE));
-
-	/* WaDisable_RenderCache_OperationalFlush:vlv */
-	I915_WRITE(CACHE_MODE_0_GEN7, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE));
-
-	/* WaForceL3Serialization:vlv */
-	I915_WRITE(GEN7_L3SQCREG4, I915_READ(GEN7_L3SQCREG4) &
-		   ~L3SQ_URB_READ_CAM_MATCH_DISABLE);
-
 	/* WaDisableDopClockGating:vlv */
 	I915_WRITE(GEN7_ROW_CHICKEN2,
 		   _MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE));
@@ -7404,8 +7243,6 @@ static void vlv_init_clock_gating(struct drm_i915_private *dev_priv)
 		   I915_READ(GEN7_SQ_CHICKEN_MBCUNIT_CONFIG) |
 		   GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB);
 
-	gen7_setup_fixed_func_scheduler(dev_priv);
-
 	/*
 	 * According to the spec, bit 13 (RCZUNIT) must be set on IVB.
 	 * This implements the WaDisableRCZUnitClockGating:vlv workaround.
@@ -7420,30 +7257,6 @@ static void vlv_init_clock_gating(struct drm_i915_private *dev_priv)
 		   I915_READ(GEN7_UCGCTL4) | GEN7_L3BANK2X_CLOCK_GATE_DISABLE);
 
 	/*
-	 * BSpec says this must be set, even though
-	 * WaDisable4x2SubspanOptimization isn't listed for VLV.
-	 */
-	I915_WRITE(CACHE_MODE_1,
-		   _MASKED_BIT_ENABLE(PIXEL_SUBSPAN_COLLECT_OPT_DISABLE));
-
-	/*
-	 * BSpec recommends 8x4 when MSAA is used,
-	 * however in practice 16x4 seems fastest.
-	 *
-	 * Note that PS/WM thread counts depend on the WIZ hashing
-	 * disable bit, which we don't touch here, but it's good
-	 * to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
-	 */
-	I915_WRITE(GEN7_GT_MODE,
-		   _MASKED_FIELD(GEN6_WIZ_HASHING_MASK, GEN6_WIZ_HASHING_16x4));
-
-	/*
-	 * WaIncreaseL3CreditsForVLVB0:vlv
-	 * This is the hardware default actually.
-	 */
-	I915_WRITE(GEN7_L3SQCREG1, VLV_B0_WA_L3SQCREG1_VALUE);
-
-	/*
 	 * WaDisableVLVClockGating_VBIIssue:vlv
 	 * Disable clock gating on th GCFG unit to prevent a delay
 	 * in the reporting of vblank events.
@@ -7495,13 +7308,6 @@ static void g4x_init_clock_gating(struct drm_i915_private *dev_priv)
 		dspclk_gate |= DSSUNIT_CLOCK_GATE_DISABLE;
 	I915_WRITE(DSPCLK_GATE_D, dspclk_gate);
 
-	/* WaDisableRenderCachePipelinedFlush */
-	I915_WRITE(CACHE_MODE_0,
-		   _MASKED_BIT_ENABLE(CM0_PIPELINED_RENDER_FLUSH_DISABLE));
-
-	/* WaDisable_RenderCache_OperationalFlush:g4x */
-	I915_WRITE(CACHE_MODE_0, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE));
-
 	g4x_disable_trickle_feed(dev_priv);
 }
 
@@ -7517,11 +7323,6 @@ static void i965gm_init_clock_gating(struct drm_i915_private *dev_priv)
 	intel_uncore_write(uncore,
 			   MI_ARB_STATE,
 			   _MASKED_BIT_ENABLE(MI_ARB_DISPLAY_TRICKLE_FEED_DISABLE));
-
-	/* WaDisable_RenderCache_OperationalFlush:gen4 */
-	intel_uncore_write(uncore,
-			   CACHE_MODE_0,
-			   _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE));
 }
 
 static void i965g_init_clock_gating(struct drm_i915_private *dev_priv)
@@ -7534,9 +7335,6 @@ static void i965g_init_clock_gating(struct drm_i915_private *dev_priv)
 	I915_WRITE(RENCLK_GATE_D2, 0);
 	I915_WRITE(MI_ARB_STATE,
 		   _MASKED_BIT_ENABLE(MI_ARB_DISPLAY_TRICKLE_FEED_DISABLE));
-
-	/* WaDisable_RenderCache_OperationalFlush:gen4 */
-	I915_WRITE(CACHE_MODE_0, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE));
 }
 
 static void gen3_init_clock_gating(struct drm_i915_private *dev_priv)
diff --git a/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h b/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h
index 6a2be7d0dd95..6090ce35226b 100644
--- a/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h
+++ b/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h
@@ -21,6 +21,7 @@ selftest(fence, i915_sw_fence_mock_selftests)
 selftest(scatterlist, scatterlist_mock_selftests)
 selftest(syncmap, i915_syncmap_mock_selftests)
 selftest(uncore, intel_uncore_mock_selftests)
+selftest(ring, intel_ring_mock_selftests)
 selftest(engine, intel_engine_cs_mock_selftests)
 selftest(timelines, intel_timeline_mock_selftests)
 selftest(requests, i915_request_mock_selftests)
diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c
index d1f278f73011..26f03a14a478 100644
--- a/drivers/i2c/i2c-core-base.c
+++ b/drivers/i2c/i2c-core-base.c
@@ -816,31 +816,6 @@ out_err_silent:
 EXPORT_SYMBOL_GPL(i2c_new_client_device);
 
 /**
- * i2c_new_device - instantiate an i2c device
- * @adap: the adapter managing the device
- * @info: describes one I2C device; bus_num is ignored
- * Context: can sleep
- *
- * This deprecated function has the same functionality as
- * @i2c_new_client_device, it just returns NULL instead of an ERR_PTR in case of
- * an error for compatibility with current I2C API. It will be removed once all
- * users are converted.
- *
- * This returns the new i2c client, which may be saved for later use with
- * i2c_unregister_device(); or NULL to indicate an error.
- */
-struct i2c_client *
-i2c_new_device(struct i2c_adapter *adap, struct i2c_board_info const *info)
-{
-	struct i2c_client *ret;
-
-	ret = i2c_new_client_device(adap, info);
-	return IS_ERR(ret) ? NULL : ret;
-}
-EXPORT_SYMBOL_GPL(i2c_new_device);
-
-
-/**
  * i2c_unregister_device - reverse effect of i2c_new_*_device()
  * @client: value returned from i2c_new_*_device()
  * Context: can sleep
diff --git a/drivers/i2c/i2c-core-smbus.c b/drivers/i2c/i2c-core-smbus.c
index b34d2ff06931..56bb840142e3 100644
--- a/drivers/i2c/i2c-core-smbus.c
+++ b/drivers/i2c/i2c-core-smbus.c
@@ -4,7 +4,7 @@
  *
  * This file contains the SMBus functions which are always included in the I2C
  * core because they can be emulated via I2C. SMBus specific extensions
- * (e.g. smbalert) are handled in a seperate i2c-smbus module.
+ * (e.g. smbalert) are handled in a separate i2c-smbus module.
  *
  * All SMBus-related things are written by Frodo Looijaard <frodol@dds.nl>
  * SMBus 2.0 support by Mark Studebaker <mdsxyz123@yahoo.com> and
diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c
index 9ce787e37e22..0d1377232933 100644
--- a/drivers/infiniband/core/cm.c
+++ b/drivers/infiniband/core/cm.c
@@ -918,6 +918,7 @@ static void cm_free_work(struct cm_work *work)
 
 static void cm_queue_work_unlock(struct cm_id_private *cm_id_priv,
 				 struct cm_work *work)
+	__releases(&cm_id_priv->lock)
 {
 	bool immediate;
 
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 3d7cc9f0f3d4..c30cf5307ce3 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -1624,6 +1624,8 @@ static struct rdma_id_private *cma_find_listener(
 {
 	struct rdma_id_private *id_priv, *id_priv_dev;
 
+	lockdep_assert_held(&lock);
+
 	if (!bind_list)
 		return ERR_PTR(-EINVAL);
 
@@ -1670,6 +1672,7 @@ cma_ib_id_from_event(struct ib_cm_id *cm_id,
 		}
 	}
 
+	mutex_lock(&lock);
 	/*
 	 * Net namespace might be getting deleted while route lookup,
 	 * cm_id lookup is in progress. Therefore, perform netdevice
@@ -1711,6 +1714,7 @@ cma_ib_id_from_event(struct ib_cm_id *cm_id,
 	id_priv = cma_find_listener(bind_list, cm_id, ib_event, req, *net_dev);
 err:
 	rcu_read_unlock();
+	mutex_unlock(&lock);
 	if (IS_ERR(id_priv) && *net_dev) {
 		dev_put(*net_dev);
 		*net_dev = NULL;
@@ -2492,6 +2496,8 @@ static void cma_listen_on_dev(struct rdma_id_private *id_priv,
 	struct net *net = id_priv->id.route.addr.dev_addr.net;
 	int ret;
 
+	lockdep_assert_held(&lock);
+
 	if (cma_family(id_priv) == AF_IB && !rdma_cap_ib_cm(cma_dev->device, 1))
 		return;
 
@@ -3342,6 +3348,8 @@ static void cma_bind_port(struct rdma_bind_list *bind_list,
 	u64 sid, mask;
 	__be16 port;
 
+	lockdep_assert_held(&lock);
+
 	addr = cma_src_addr(id_priv);
 	port = htons(bind_list->port);
 
@@ -3370,6 +3378,8 @@ static int cma_alloc_port(enum rdma_ucm_port_space ps,
 	struct rdma_bind_list *bind_list;
 	int ret;
 
+	lockdep_assert_held(&lock);
+
 	bind_list = kzalloc(sizeof *bind_list, GFP_KERNEL);
 	if (!bind_list)
 		return -ENOMEM;
@@ -3396,6 +3406,8 @@ static int cma_port_is_unique(struct rdma_bind_list *bind_list,
 	struct sockaddr  *saddr = cma_src_addr(id_priv);
 	__be16 dport = cma_port(daddr);
 
+	lockdep_assert_held(&lock);
+
 	hlist_for_each_entry(cur_id, &bind_list->owners, node) {
 		struct sockaddr  *cur_daddr = cma_dst_addr(cur_id);
 		struct sockaddr  *cur_saddr = cma_src_addr(cur_id);
@@ -3435,6 +3447,8 @@ static int cma_alloc_any_port(enum rdma_ucm_port_space ps,
 	unsigned int rover;
 	struct net *net = id_priv->id.route.addr.dev_addr.net;
 
+	lockdep_assert_held(&lock);
+
 	inet_get_local_port_range(net, &low, &high);
 	remaining = (high - low) + 1;
 	rover = prandom_u32() % remaining + low;
@@ -3482,6 +3496,8 @@ static int cma_check_port(struct rdma_bind_list *bind_list,
 	struct rdma_id_private *cur_id;
 	struct sockaddr *addr, *cur_addr;
 
+	lockdep_assert_held(&lock);
+
 	addr = cma_src_addr(id_priv);
 	hlist_for_each_entry(cur_id, &bind_list->owners, node) {
 		if (id_priv == cur_id)
@@ -3512,6 +3528,8 @@ static int cma_use_port(enum rdma_ucm_port_space ps,
 	unsigned short snum;
 	int ret;
 
+	lockdep_assert_held(&lock);
+
 	snum = ntohs(cma_port(cma_src_addr(id_priv)));
 	if (snum < PROT_SOCK && !capable(CAP_NET_BIND_SERVICE))
 		return -EACCES;
diff --git a/drivers/infiniband/core/counters.c b/drivers/infiniband/core/counters.c
index 2257d7f7810f..738d1faf4bba 100644
--- a/drivers/infiniband/core/counters.c
+++ b/drivers/infiniband/core/counters.c
@@ -202,7 +202,7 @@ static int __rdma_counter_unbind_qp(struct ib_qp *qp)
 	return ret;
 }
 
-static void counter_history_stat_update(const struct rdma_counter *counter)
+static void counter_history_stat_update(struct rdma_counter *counter)
 {
 	struct ib_device *dev = counter->device;
 	struct rdma_port_counter *port_counter;
@@ -212,6 +212,8 @@ static void counter_history_stat_update(const struct rdma_counter *counter)
 	if (!port_counter->hstats)
 		return;
 
+	rdma_counter_query_stats(counter);
+
 	for (i = 0; i < counter->stats->num_counters; i++)
 		port_counter->hstats->value[i] += counter->stats->value[i];
 }
diff --git a/drivers/infiniband/core/mad.c b/drivers/infiniband/core/mad.c
index 186e0d652e8b..a09f8e3c7f3f 100644
--- a/drivers/infiniband/core/mad.c
+++ b/drivers/infiniband/core/mad.c
@@ -509,10 +509,10 @@ static void unregister_mad_agent(struct ib_mad_agent_private *mad_agent_priv)
 	xa_erase(&ib_mad_clients, mad_agent_priv->agent.hi_tid);
 
 	flush_workqueue(port_priv->wq);
-	ib_cancel_rmpp_recvs(mad_agent_priv);
 
 	deref_mad_agent(mad_agent_priv);
 	wait_for_completion(&mad_agent_priv->comp);
+	ib_cancel_rmpp_recvs(mad_agent_priv);
 
 	ib_mad_agent_security_cleanup(&mad_agent_priv->agent);
 
@@ -2718,6 +2718,7 @@ static int ib_mad_post_receive_mads(struct ib_mad_qp_info *qp_info,
 						 DMA_FROM_DEVICE);
 		if (unlikely(ib_dma_mapping_error(qp_info->port_priv->device,
 						  sg_list.addr))) {
+			kfree(mad_priv);
 			ret = -ENOMEM;
 			break;
 		}
diff --git a/drivers/infiniband/core/rdma_core.c b/drivers/infiniband/core/rdma_core.c
index 38de4942c682..3027cd2fb247 100644
--- a/drivers/infiniband/core/rdma_core.c
+++ b/drivers/infiniband/core/rdma_core.c
@@ -470,40 +470,46 @@ static struct ib_uobject *
 alloc_begin_fd_uobject(const struct uverbs_api_object *obj,
 		       struct uverbs_attr_bundle *attrs)
 {
-	const struct uverbs_obj_fd_type *fd_type =
-		container_of(obj->type_attrs, struct uverbs_obj_fd_type, type);
+	const struct uverbs_obj_fd_type *fd_type;
 	int new_fd;
-	struct ib_uobject *uobj;
+	struct ib_uobject *uobj, *ret;
 	struct file *filp;
 
+	uobj = alloc_uobj(attrs, obj);
+	if (IS_ERR(uobj))
+		return uobj;
+
+	fd_type =
+		container_of(obj->type_attrs, struct uverbs_obj_fd_type, type);
 	if (WARN_ON(fd_type->fops->release != &uverbs_uobject_fd_release &&
-		    fd_type->fops->release != &uverbs_async_event_release))
-		return ERR_PTR(-EINVAL);
+		    fd_type->fops->release != &uverbs_async_event_release)) {
+		ret = ERR_PTR(-EINVAL);
+		goto err_fd;
+	}
 
 	new_fd = get_unused_fd_flags(O_CLOEXEC);
-	if (new_fd < 0)
-		return ERR_PTR(new_fd);
-
-	uobj = alloc_uobj(attrs, obj);
-	if (IS_ERR(uobj))
+	if (new_fd < 0) {
+		ret = ERR_PTR(new_fd);
 		goto err_fd;
+	}
 
 	/* Note that uverbs_uobject_fd_release() is called during abort */
 	filp = anon_inode_getfile(fd_type->name, fd_type->fops, NULL,
 				  fd_type->flags);
 	if (IS_ERR(filp)) {
-		uverbs_uobject_put(uobj);
-		uobj = ERR_CAST(filp);
-		goto err_fd;
+		ret = ERR_CAST(filp);
+		goto err_getfile;
 	}
 	uobj->object = filp;
 
 	uobj->id = new_fd;
 	return uobj;
 
-err_fd:
+err_getfile:
 	put_unused_fd(new_fd);
-	return uobj;
+err_fd:
+	uverbs_uobject_put(uobj);
+	return ret;
 }
 
 struct ib_uobject *rdma_alloc_begin_uobject(const struct uverbs_api_object *obj,
diff --git a/drivers/infiniband/hw/efa/efa_verbs.c b/drivers/infiniband/hw/efa/efa_verbs.c
index 08313f7c73bc..7dd082441333 100644
--- a/drivers/infiniband/hw/efa/efa_verbs.c
+++ b/drivers/infiniband/hw/efa/efa_verbs.c
@@ -212,6 +212,7 @@ int efa_query_device(struct ib_device *ibdev,
 	props->max_send_sge = dev_attr->max_sq_sge;
 	props->max_recv_sge = dev_attr->max_rq_sge;
 	props->max_sge_rd = dev_attr->max_wr_rdma_sge;
+	props->max_pkeys = 1;
 
 	if (udata && udata->outlen) {
 		resp.max_sq_sge = dev_attr->max_sq_sge;
diff --git a/drivers/infiniband/hw/hfi1/debugfs.c b/drivers/infiniband/hw/hfi1/debugfs.c
index 4633a0ce1a8c..2ced236e1553 100644
--- a/drivers/infiniband/hw/hfi1/debugfs.c
+++ b/drivers/infiniband/hw/hfi1/debugfs.c
@@ -985,15 +985,10 @@ static ssize_t qsfp2_debugfs_read(struct file *file, char __user *buf,
 static int __i2c_debugfs_open(struct inode *in, struct file *fp, u32 target)
 {
 	struct hfi1_pportdata *ppd;
-	int ret;
 
 	ppd = private2ppd(fp);
 
-	ret = acquire_chip_resource(ppd->dd, i2c_target(target), 0);
-	if (ret) /* failed - release the module */
-		module_put(THIS_MODULE);
-
-	return ret;
+	return acquire_chip_resource(ppd->dd, i2c_target(target), 0);
 }
 
 static int i2c1_debugfs_open(struct inode *in, struct file *fp)
@@ -1013,7 +1008,6 @@ static int __i2c_debugfs_release(struct inode *in, struct file *fp, u32 target)
 	ppd = private2ppd(fp);
 
 	release_chip_resource(ppd->dd, i2c_target(target));
-	module_put(THIS_MODULE);
 
 	return 0;
 }
@@ -1031,18 +1025,10 @@ static int i2c2_debugfs_release(struct inode *in, struct file *fp)
 static int __qsfp_debugfs_open(struct inode *in, struct file *fp, u32 target)
 {
 	struct hfi1_pportdata *ppd;
-	int ret;
-
-	if (!try_module_get(THIS_MODULE))
-		return -ENODEV;
 
 	ppd = private2ppd(fp);
 
-	ret = acquire_chip_resource(ppd->dd, i2c_target(target), 0);
-	if (ret) /* failed - release the module */
-		module_put(THIS_MODULE);
-
-	return ret;
+	return acquire_chip_resource(ppd->dd, i2c_target(target), 0);
 }
 
 static int qsfp1_debugfs_open(struct inode *in, struct file *fp)
@@ -1062,7 +1048,6 @@ static int __qsfp_debugfs_release(struct inode *in, struct file *fp, u32 target)
 	ppd = private2ppd(fp);
 
 	release_chip_resource(ppd->dd, i2c_target(target));
-	module_put(THIS_MODULE);
 
 	return 0;
 }
diff --git a/drivers/infiniband/hw/hfi1/iowait.h b/drivers/infiniband/hw/hfi1/iowait.h
index 07847cb72169..d580aa17ae37 100644
--- a/drivers/infiniband/hw/hfi1/iowait.h
+++ b/drivers/infiniband/hw/hfi1/iowait.h
@@ -399,7 +399,7 @@ static inline void iowait_get_priority(struct iowait *w)
  * @wait_head: the wait queue
  *
  * This function is called to insert an iowait struct into a
- * wait queue after a resource (eg, sdma decriptor or pio
+ * wait queue after a resource (eg, sdma descriptor or pio
  * buffer) is run out.
  */
 static inline void iowait_queue(bool pkts_sent, struct iowait *w,
diff --git a/drivers/infiniband/hw/hfi1/ipoib.h b/drivers/infiniband/hw/hfi1/ipoib.h
index 185c9b02c974..b8c9d0a003fb 100644
--- a/drivers/infiniband/hw/hfi1/ipoib.h
+++ b/drivers/infiniband/hw/hfi1/ipoib.h
@@ -67,6 +67,9 @@ struct hfi1_ipoib_circ_buf {
  * @sde: sdma engine
  * @tx_list: tx request list
  * @sent_txreqs: count of txreqs posted to sdma
+ * @stops: count of stops of queue
+ * @ring_full: ring has been filled
+ * @no_desc: descriptor shortage seen
  * @flow: tracks when list needs to be flushed for a flow change
  * @q_idx: ipoib Tx queue index
  * @pkts_sent: indicator packets have been sent from this queue
@@ -80,6 +83,9 @@ struct hfi1_ipoib_txq {
 	struct sdma_engine *sde;
 	struct list_head tx_list;
 	u64 sent_txreqs;
+	atomic_t stops;
+	atomic_t ring_full;
+	atomic_t no_desc;
 	union hfi1_ipoib_flow flow;
 	u8 q_idx;
 	bool pkts_sent;
diff --git a/drivers/infiniband/hw/hfi1/ipoib_tx.c b/drivers/infiniband/hw/hfi1/ipoib_tx.c
index 883cb9d48022..9df292b51a05 100644
--- a/drivers/infiniband/hw/hfi1/ipoib_tx.c
+++ b/drivers/infiniband/hw/hfi1/ipoib_tx.c
@@ -55,23 +55,48 @@ static u64 hfi1_ipoib_txreqs(const u64 sent, const u64 completed)
 	return sent - completed;
 }
 
-static void hfi1_ipoib_check_queue_depth(struct hfi1_ipoib_txq *txq)
+static u64 hfi1_ipoib_used(struct hfi1_ipoib_txq *txq)
 {
-	if (unlikely(hfi1_ipoib_txreqs(++txq->sent_txreqs,
-				       atomic64_read(&txq->complete_txreqs)) >=
-	    min_t(unsigned int, txq->priv->netdev->tx_queue_len,
-		  txq->tx_ring.max_items - 1)))
+	return hfi1_ipoib_txreqs(txq->sent_txreqs,
+				 atomic64_read(&txq->complete_txreqs));
+}
+
+static void hfi1_ipoib_stop_txq(struct hfi1_ipoib_txq *txq)
+{
+	if (atomic_inc_return(&txq->stops) == 1)
 		netif_stop_subqueue(txq->priv->netdev, txq->q_idx);
 }
 
+static void hfi1_ipoib_wake_txq(struct hfi1_ipoib_txq *txq)
+{
+	if (atomic_dec_and_test(&txq->stops))
+		netif_wake_subqueue(txq->priv->netdev, txq->q_idx);
+}
+
+static uint hfi1_ipoib_ring_hwat(struct hfi1_ipoib_txq *txq)
+{
+	return min_t(uint, txq->priv->netdev->tx_queue_len,
+		     txq->tx_ring.max_items - 1);
+}
+
+static uint hfi1_ipoib_ring_lwat(struct hfi1_ipoib_txq *txq)
+{
+	return min_t(uint, txq->priv->netdev->tx_queue_len,
+		     txq->tx_ring.max_items) >> 1;
+}
+
+static void hfi1_ipoib_check_queue_depth(struct hfi1_ipoib_txq *txq)
+{
+	++txq->sent_txreqs;
+	if (hfi1_ipoib_used(txq) >= hfi1_ipoib_ring_hwat(txq) &&
+	    !atomic_xchg(&txq->ring_full, 1))
+		hfi1_ipoib_stop_txq(txq);
+}
+
 static void hfi1_ipoib_check_queue_stopped(struct hfi1_ipoib_txq *txq)
 {
 	struct net_device *dev = txq->priv->netdev;
 
-	/* If the queue is already running just return */
-	if (likely(!__netif_subqueue_stopped(dev, txq->q_idx)))
-		return;
-
 	/* If shutting down just return as queue state is irrelevant */
 	if (unlikely(dev->reg_state != NETREG_REGISTERED))
 		return;
@@ -86,11 +111,9 @@ static void hfi1_ipoib_check_queue_stopped(struct hfi1_ipoib_txq *txq)
 	 * Use the minimum of the current tx_queue_len or the rings max txreqs
 	 * to protect against ring overflow.
 	 */
-	if (hfi1_ipoib_txreqs(txq->sent_txreqs,
-			      atomic64_read(&txq->complete_txreqs))
-	    < min_t(unsigned int, dev->tx_queue_len,
-		    txq->tx_ring.max_items) >> 1)
-		netif_wake_subqueue(dev, txq->q_idx);
+	if (hfi1_ipoib_used(txq) < hfi1_ipoib_ring_lwat(txq) &&
+	    atomic_xchg(&txq->ring_full, 0))
+		hfi1_ipoib_wake_txq(txq);
 }
 
 static void hfi1_ipoib_free_tx(struct ipoib_txreq *tx, int budget)
@@ -364,11 +387,12 @@ static struct ipoib_txreq *hfi1_ipoib_send_dma_common(struct net_device *dev,
 	if (unlikely(!tx))
 		return ERR_PTR(-ENOMEM);
 
-	/* so that we can test if the sdma decriptors are there */
+	/* so that we can test if the sdma descriptors are there */
 	tx->txreq.num_desc = 0;
 	tx->priv = priv;
 	tx->txq = txp->txq;
 	tx->skb = skb;
+	INIT_LIST_HEAD(&tx->txreq.list);
 
 	hfi1_ipoib_build_ib_tx_headers(tx, txp);
 
@@ -469,6 +493,7 @@ static int hfi1_ipoib_send_dma_single(struct net_device *dev,
 
 	ret = hfi1_ipoib_submit_tx(txq, tx);
 	if (likely(!ret)) {
+tx_ok:
 		trace_sdma_output_ibhdr(tx->priv->dd,
 					&tx->sdma_hdr.hdr,
 					ib_is_sc5(txp->flow.sc5));
@@ -478,20 +503,8 @@ static int hfi1_ipoib_send_dma_single(struct net_device *dev,
 
 	txq->pkts_sent = false;
 
-	if (ret == -EBUSY) {
-		list_add_tail(&tx->txreq.list, &txq->tx_list);
-
-		trace_sdma_output_ibhdr(tx->priv->dd,
-					&tx->sdma_hdr.hdr,
-					ib_is_sc5(txp->flow.sc5));
-		hfi1_ipoib_check_queue_depth(txq);
-		return NETDEV_TX_OK;
-	}
-
-	if (ret == -ECOMM) {
-		hfi1_ipoib_check_queue_depth(txq);
-		return NETDEV_TX_OK;
-	}
+	if (ret == -EBUSY || ret == -ECOMM)
+		goto tx_ok;
 
 	sdma_txclean(priv->dd, &tx->txreq);
 	dev_kfree_skb_any(skb);
@@ -509,9 +522,17 @@ static int hfi1_ipoib_send_dma_list(struct net_device *dev,
 	struct ipoib_txreq *tx;
 
 	/* Has the flow change ? */
-	if (txq->flow.as_int != txp->flow.as_int)
-		(void)hfi1_ipoib_flush_tx_list(dev, txq);
-
+	if (txq->flow.as_int != txp->flow.as_int) {
+		int ret;
+
+		ret = hfi1_ipoib_flush_tx_list(dev, txq);
+		if (unlikely(ret)) {
+			if (ret == -EBUSY)
+				++dev->stats.tx_dropped;
+			dev_kfree_skb_any(skb);
+			return NETDEV_TX_OK;
+		}
+	}
 	tx = hfi1_ipoib_send_dma_common(dev, skb, txp);
 	if (IS_ERR(tx)) {
 		int ret = PTR_ERR(tx);
@@ -610,10 +631,14 @@ static int hfi1_ipoib_sdma_sleep(struct sdma_engine *sde,
 			return -EAGAIN;
 		}
 
-		netif_stop_subqueue(txq->priv->netdev, txq->q_idx);
-
-		if (list_empty(&txq->wait.list))
+		if (list_empty(&txreq->list))
+			/* came from non-list submit */
+			list_add_tail(&txreq->list, &txq->tx_list);
+		if (list_empty(&txq->wait.list)) {
+			if (!atomic_xchg(&txq->no_desc, 1))
+				hfi1_ipoib_stop_txq(txq);
 			iowait_queue(pkts_sent, wait->iow, &sde->dmawait);
+		}
 
 		write_sequnlock(&sde->waitlock);
 		return -EBUSY;
@@ -648,9 +673,9 @@ static void hfi1_ipoib_flush_txq(struct work_struct *work)
 	struct net_device *dev = txq->priv->netdev;
 
 	if (likely(dev->reg_state == NETREG_REGISTERED) &&
-	    likely(__netif_subqueue_stopped(dev, txq->q_idx)) &&
 	    likely(!hfi1_ipoib_flush_tx_list(dev, txq)))
-		netif_wake_subqueue(dev, txq->q_idx);
+		if (atomic_xchg(&txq->no_desc, 0))
+			hfi1_ipoib_wake_txq(txq);
 }
 
 int hfi1_ipoib_txreq_init(struct hfi1_ipoib_dev_priv *priv)
@@ -704,6 +729,9 @@ int hfi1_ipoib_txreq_init(struct hfi1_ipoib_dev_priv *priv)
 		txq->sde = NULL;
 		INIT_LIST_HEAD(&txq->tx_list);
 		atomic64_set(&txq->complete_txreqs, 0);
+		atomic_set(&txq->stops, 0);
+		atomic_set(&txq->ring_full, 0);
+		atomic_set(&txq->no_desc, 0);
 		txq->q_idx = i;
 		txq->flow.tx_queue = 0xff;
 		txq->flow.sc5 = 0xff;
@@ -769,7 +797,7 @@ static void hfi1_ipoib_drain_tx_list(struct hfi1_ipoib_txq *txq)
 		atomic64_inc(complete_txreqs);
 	}
 
-	if (hfi1_ipoib_txreqs(txq->sent_txreqs, atomic64_read(complete_txreqs)))
+	if (hfi1_ipoib_used(txq))
 		dd_dev_warn(txq->priv->dd,
 			    "txq %d not empty found %llu requests\n",
 			    txq->q_idx,
diff --git a/drivers/infiniband/hw/hfi1/netdev_rx.c b/drivers/infiniband/hw/hfi1/netdev_rx.c
index 63688e85e8da..6d263c9749b3 100644
--- a/drivers/infiniband/hw/hfi1/netdev_rx.c
+++ b/drivers/infiniband/hw/hfi1/netdev_rx.c
@@ -373,7 +373,7 @@ void hfi1_netdev_free(struct hfi1_devdata *dd)
 {
 	if (dd->dummy_netdev) {
 		dd_dev_info(dd, "hfi1 netdev freed\n");
-		free_netdev(dd->dummy_netdev);
+		kfree(dd->dummy_netdev);
 		dd->dummy_netdev = NULL;
 	}
 }
diff --git a/drivers/infiniband/hw/hfi1/verbs_txreq.h b/drivers/infiniband/hw/hfi1/verbs_txreq.h
index bfa6e081cb56..d2d526c5a756 100644
--- a/drivers/infiniband/hw/hfi1/verbs_txreq.h
+++ b/drivers/infiniband/hw/hfi1/verbs_txreq.h
@@ -91,7 +91,7 @@ static inline struct verbs_txreq *get_txreq(struct hfi1_ibdev *dev,
 	tx->mr = NULL;
 	tx->sde = priv->s_sde;
 	tx->psc = priv->s_sendcontext;
-	/* so that we can test if the sdma decriptors are there */
+	/* so that we can test if the sdma descriptors are there */
 	tx->txreq.num_desc = 0;
 	/* Set the header type */
 	tx->phdr.hdr.hdr_type = priv->hdr_type;
diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h
index a77fa6730b2d..479fa557993e 100644
--- a/drivers/infiniband/hw/hns/hns_roce_device.h
+++ b/drivers/infiniband/hw/hns/hns_roce_device.h
@@ -898,13 +898,14 @@ struct hns_roce_hw {
 	int (*set_mac)(struct hns_roce_dev *hr_dev, u8 phy_port, u8 *addr);
 	void (*set_mtu)(struct hns_roce_dev *hr_dev, u8 phy_port,
 			enum ib_mtu mtu);
-	int (*write_mtpt)(void *mb_buf, struct hns_roce_mr *mr,
-			  unsigned long mtpt_idx);
+	int (*write_mtpt)(struct hns_roce_dev *hr_dev, void *mb_buf,
+			  struct hns_roce_mr *mr, unsigned long mtpt_idx);
 	int (*rereg_write_mtpt)(struct hns_roce_dev *hr_dev,
 				struct hns_roce_mr *mr, int flags, u32 pdn,
 				int mr_access_flags, u64 iova, u64 size,
 				void *mb_buf);
-	int (*frmr_write_mtpt)(void *mb_buf, struct hns_roce_mr *mr);
+	int (*frmr_write_mtpt)(struct hns_roce_dev *hr_dev, void *mb_buf,
+			       struct hns_roce_mr *mr);
 	int (*mw_write_mtpt)(void *mb_buf, struct hns_roce_mw *mw);
 	void (*write_cqc)(struct hns_roce_dev *hr_dev,
 			  struct hns_roce_cq *hr_cq, void *mb_buf, u64 *mtts,
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c
index d02207cd30df..cf39f560b800 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c
@@ -1756,10 +1756,10 @@ static void hns_roce_v1_set_mtu(struct hns_roce_dev *hr_dev, u8 phy_port,
 		   val);
 }
 
-static int hns_roce_v1_write_mtpt(void *mb_buf, struct hns_roce_mr *mr,
+static int hns_roce_v1_write_mtpt(struct hns_roce_dev *hr_dev, void *mb_buf,
+				  struct hns_roce_mr *mr,
 				  unsigned long mtpt_idx)
 {
-	struct hns_roce_dev *hr_dev = to_hr_dev(mr->ibmr.device);
 	u64 pages[HNS_ROCE_MAX_INNER_MTPT_NUM] = { 0 };
 	struct ib_device *ibdev = &hr_dev->ib_dev;
 	struct hns_roce_v1_mpt_entry *mpt_entry;
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
index c597d7281629..dd01a51816cc 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
@@ -910,7 +910,7 @@ static int hns_roce_v2_rst_process_cmd(struct hns_roce_dev *hr_dev)
 	instance_stage = handle->rinfo.instance_state;
 	reset_stage = handle->rinfo.reset_state;
 	reset_cnt = ops->ae_dev_reset_cnt(handle);
-	hw_resetting = ops->get_hw_reset_stat(handle);
+	hw_resetting = ops->get_cmdq_stat(handle);
 	sw_resetting = ops->ae_dev_resetting(handle);
 
 	if (reset_cnt != hr_dev->reset_cnt)
@@ -2529,10 +2529,10 @@ static int hns_roce_v2_set_mac(struct hns_roce_dev *hr_dev, u8 phy_port,
 	return hns_roce_cmq_send(hr_dev, &desc, 1);
 }
 
-static int set_mtpt_pbl(struct hns_roce_v2_mpt_entry *mpt_entry,
+static int set_mtpt_pbl(struct hns_roce_dev *hr_dev,
+			struct hns_roce_v2_mpt_entry *mpt_entry,
 			struct hns_roce_mr *mr)
 {
-	struct hns_roce_dev *hr_dev = to_hr_dev(mr->ibmr.device);
 	u64 pages[HNS_ROCE_V2_MAX_INNER_MTPT_NUM] = { 0 };
 	struct ib_device *ibdev = &hr_dev->ib_dev;
 	dma_addr_t pbl_ba;
@@ -2571,7 +2571,8 @@ static int set_mtpt_pbl(struct hns_roce_v2_mpt_entry *mpt_entry,
 	return 0;
 }
 
-static int hns_roce_v2_write_mtpt(void *mb_buf, struct hns_roce_mr *mr,
+static int hns_roce_v2_write_mtpt(struct hns_roce_dev *hr_dev,
+				  void *mb_buf, struct hns_roce_mr *mr,
 				  unsigned long mtpt_idx)
 {
 	struct hns_roce_v2_mpt_entry *mpt_entry;
@@ -2620,7 +2621,7 @@ static int hns_roce_v2_write_mtpt(void *mb_buf, struct hns_roce_mr *mr,
 	if (mr->type == MR_TYPE_DMA)
 		return 0;
 
-	ret = set_mtpt_pbl(mpt_entry, mr);
+	ret = set_mtpt_pbl(hr_dev, mpt_entry, mr);
 
 	return ret;
 }
@@ -2666,15 +2667,15 @@ static int hns_roce_v2_rereg_write_mtpt(struct hns_roce_dev *hr_dev,
 		mr->iova = iova;
 		mr->size = size;
 
-		ret = set_mtpt_pbl(mpt_entry, mr);
+		ret = set_mtpt_pbl(hr_dev, mpt_entry, mr);
 	}
 
 	return ret;
 }
 
-static int hns_roce_v2_frmr_write_mtpt(void *mb_buf, struct hns_roce_mr *mr)
+static int hns_roce_v2_frmr_write_mtpt(struct hns_roce_dev *hr_dev,
+				       void *mb_buf, struct hns_roce_mr *mr)
 {
-	struct hns_roce_dev *hr_dev = to_hr_dev(mr->ibmr.device);
 	struct ib_device *ibdev = &hr_dev->ib_dev;
 	struct hns_roce_v2_mpt_entry *mpt_entry;
 	dma_addr_t pbl_ba = 0;
diff --git a/drivers/infiniband/hw/hns/hns_roce_mr.c b/drivers/infiniband/hw/hns/hns_roce_mr.c
index 4c0bbb12770d..0e71ebee9e52 100644
--- a/drivers/infiniband/hw/hns/hns_roce_mr.c
+++ b/drivers/infiniband/hw/hns/hns_roce_mr.c
@@ -180,9 +180,10 @@ static int hns_roce_mr_enable(struct hns_roce_dev *hr_dev,
 	}
 
 	if (mr->type != MR_TYPE_FRMR)
-		ret = hr_dev->hw->write_mtpt(mailbox->buf, mr, mtpt_idx);
+		ret = hr_dev->hw->write_mtpt(hr_dev, mailbox->buf, mr,
+					     mtpt_idx);
 	else
-		ret = hr_dev->hw->frmr_write_mtpt(mailbox->buf, mr);
+		ret = hr_dev->hw->frmr_write_mtpt(hr_dev, mailbox->buf, mr);
 	if (ret) {
 		dev_err(dev, "Write mtpt fail!\n");
 		goto err_page;
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 81bf6b975e0e..f939c9b769f0 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -1862,7 +1862,7 @@ static int create_xrc_tgt_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 	if (!in)
 		return -ENOMEM;
 
-	if (MLX5_CAP_GEN(mdev, ece_support))
+	if (MLX5_CAP_GEN(mdev, ece_support) && ucmd)
 		MLX5_SET(create_qp_in, in, ece, ucmd->ece_options);
 	qpc = MLX5_ADDR_OF(create_qp_in, in, qpc);
 
@@ -2341,18 +2341,18 @@ static void destroy_qp_common(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 	unsigned long flags;
 	int err;
 
-	if (qp->ibqp.rwq_ind_tbl) {
+	if (qp->is_rss) {
 		destroy_rss_raw_qp_tir(dev, qp);
 		return;
 	}
 
-	base = (qp->ibqp.qp_type == IB_QPT_RAW_PACKET ||
+	base = (qp->type == IB_QPT_RAW_PACKET ||
 		qp->flags & IB_QP_CREATE_SOURCE_QPN) ?
-	       &qp->raw_packet_qp.rq.base :
-	       &qp->trans_qp.base;
+		       &qp->raw_packet_qp.rq.base :
+		       &qp->trans_qp.base;
 
 	if (qp->state != IB_QPS_RESET) {
-		if (qp->ibqp.qp_type != IB_QPT_RAW_PACKET &&
+		if (qp->type != IB_QPT_RAW_PACKET &&
 		    !(qp->flags & IB_QP_CREATE_SOURCE_QPN)) {
 			err = mlx5_core_qp_modify(dev, MLX5_CMD_OP_2RST_QP, 0,
 						  NULL, &base->mqp, NULL);
@@ -2368,8 +2368,8 @@ static void destroy_qp_common(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 				     base->mqp.qpn);
 	}
 
-	get_cqs(qp->ibqp.qp_type, qp->ibqp.send_cq, qp->ibqp.recv_cq,
-		&send_cq, &recv_cq);
+	get_cqs(qp->type, qp->ibqp.send_cq, qp->ibqp.recv_cq, &send_cq,
+		&recv_cq);
 
 	spin_lock_irqsave(&dev->reset_flow_resource_lock, flags);
 	mlx5_ib_lock_cqs(send_cq, recv_cq);
@@ -2391,7 +2391,7 @@ static void destroy_qp_common(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 	mlx5_ib_unlock_cqs(send_cq, recv_cq);
 	spin_unlock_irqrestore(&dev->reset_flow_resource_lock, flags);
 
-	if (qp->ibqp.qp_type == IB_QPT_RAW_PACKET ||
+	if (qp->type == IB_QPT_RAW_PACKET ||
 	    qp->flags & IB_QP_CREATE_SOURCE_QPN) {
 		destroy_raw_packet_qp(dev, qp);
 	} else {
@@ -2669,6 +2669,9 @@ static int process_create_flags(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 		return (create_flags) ? -EINVAL : 0;
 
 	process_create_flag(dev, &create_flags,
+			    IB_QP_CREATE_INTEGRITY_EN,
+			    MLX5_CAP_GEN(mdev, sho), qp);
+	process_create_flag(dev, &create_flags,
 			    IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK,
 			    MLX5_CAP_GEN(mdev, block_lb_mc), qp);
 	process_create_flag(dev, &create_flags, IB_QP_CREATE_CROSS_CHANNEL,
@@ -2873,7 +2876,6 @@ static int mlx5_ib_destroy_dct(struct mlx5_ib_qp *mqp)
 static int check_ucmd_data(struct mlx5_ib_dev *dev,
 			   struct mlx5_create_qp_params *params)
 {
-	struct ib_qp_init_attr *attr = params->attr;
 	struct ib_udata *udata = params->udata;
 	size_t size, last;
 	int ret;
@@ -2885,14 +2887,7 @@ static int check_ucmd_data(struct mlx5_ib_dev *dev,
 		 */
 		last = sizeof(struct mlx5_ib_create_qp_rss);
 	else
-		/* IB_QPT_RAW_PACKET doesn't have ECE data */
-		switch (attr->qp_type) {
-		case IB_QPT_RAW_PACKET:
-			last = offsetof(struct mlx5_ib_create_qp, ece_options);
-			break;
-		default:
-			last = offsetof(struct mlx5_ib_create_qp, reserved);
-		}
+		last = offsetof(struct mlx5_ib_create_qp, reserved);
 
 	if (udata->inlen <= last)
 		return 0;
@@ -2907,7 +2902,7 @@ static int check_ucmd_data(struct mlx5_ib_dev *dev,
 	if (!ret)
 		mlx5_ib_dbg(
 			dev,
-			"udata is not cleared, inlen = %lu, ucmd = %lu, last = %lu, size = %lu\n",
+			"udata is not cleared, inlen = %zu, ucmd = %zu, last = %zu, size = %zu\n",
 			udata->inlen, params->ucmd_size, last, size);
 	return ret ? 0 : -EINVAL;
 }
@@ -3002,10 +2997,18 @@ struct ib_qp *mlx5_ib_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *attr,
 	return &qp->ibqp;
 
 destroy_qp:
-	if (qp->type == MLX5_IB_QPT_DCT)
+	if (qp->type == MLX5_IB_QPT_DCT) {
 		mlx5_ib_destroy_dct(qp);
-	else
+	} else {
+		/*
+		 * The two lines below are temp solution till QP allocation
+		 * will be moved to be under IB/core responsiblity.
+		 */
+		qp->ibqp.send_cq = attr->send_cq;
+		qp->ibqp.recv_cq = attr->recv_cq;
 		destroy_qp_common(dev, qp, udata);
+	}
+
 	qp = NULL;
 free_qp:
 	kfree(qp);
@@ -4162,8 +4165,6 @@ static int mlx5_ib_modify_dct(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 
 		if (udata->outlen < min_resp_len)
 			return -EINVAL;
-		resp.response_length = min_resp_len;
-
 		/*
 		 * If we don't have enough space for the ECE options,
 		 * simply indicate it with resp.response_length.
@@ -4384,8 +4385,7 @@ static void to_rdma_ah_attr(struct mlx5_ib_dev *ibdev,
 				MLX5_GET(ads, path, src_addr_index),
 				MLX5_GET(ads, path, hop_limit),
 				MLX5_GET(ads, path, tclass));
-		memcpy(ah_attr, MLX5_ADDR_OF(ads, path, rgid_rip),
-		       MLX5_FLD_SZ_BYTES(ads, rgid_rip));
+		rdma_ah_set_dgid_raw(ah_attr, MLX5_ADDR_OF(ads, path, rgid_rip));
 	}
 }
 
diff --git a/drivers/infiniband/hw/mlx5/qpc.c b/drivers/infiniband/hw/mlx5/qpc.c
index c19d91d6dce8..7c3968ef9cd1 100644
--- a/drivers/infiniband/hw/mlx5/qpc.c
+++ b/drivers/infiniband/hw/mlx5/qpc.c
@@ -346,6 +346,9 @@ static int get_ece_from_mbox(void *out, u16 opcode)
 	int ece = 0;
 
 	switch (opcode) {
+	case MLX5_CMD_OP_INIT2INIT_QP:
+		ece = MLX5_GET(init2init_qp_out, out, ece);
+		break;
 	case MLX5_CMD_OP_INIT2RTR_QP:
 		ece = MLX5_GET(init2rtr_qp_out, out, ece);
 		break;
@@ -355,6 +358,9 @@ static int get_ece_from_mbox(void *out, u16 opcode)
 	case MLX5_CMD_OP_RTS2RTS_QP:
 		ece = MLX5_GET(rts2rts_qp_out, out, ece);
 		break;
+	case MLX5_CMD_OP_RST2INIT_QP:
+		ece = MLX5_GET(rst2init_qp_out, out, ece);
+		break;
 	default:
 		break;
 	}
@@ -406,6 +412,7 @@ static int modify_qp_mbox_alloc(struct mlx5_core_dev *dev, u16 opcode, int qpn,
 			return -ENOMEM;
 		MOD_QP_IN_SET_QPC(rst2init_qp, mbox->in, opcode, qpn,
 				  opt_param_mask, qpc, uid);
+		MLX5_SET(rst2init_qp_in, mbox->in, ece, ece);
 		break;
 	case MLX5_CMD_OP_INIT2RTR_QP:
 		if (MBOX_ALLOC(mbox, init2rtr_qp))
@@ -439,6 +446,7 @@ static int modify_qp_mbox_alloc(struct mlx5_core_dev *dev, u16 opcode, int qpn,
 			return -ENOMEM;
 		MOD_QP_IN_SET_QPC(init2init_qp, mbox->in, opcode, qpn,
 				  opt_param_mask, qpc, uid);
+		MLX5_SET(init2init_qp_in, mbox->in, ece, ece);
 		break;
 	default:
 		return -EINVAL;
diff --git a/drivers/infiniband/hw/qedr/qedr_iw_cm.c b/drivers/infiniband/hw/qedr/qedr_iw_cm.c
index 792eecd206b6..97fc7dd353b0 100644
--- a/drivers/infiniband/hw/qedr/qedr_iw_cm.c
+++ b/drivers/infiniband/hw/qedr/qedr_iw_cm.c
@@ -150,8 +150,17 @@ qedr_iw_issue_event(void *context,
 	if (params->cm_info) {
 		event.ird = params->cm_info->ird;
 		event.ord = params->cm_info->ord;
-		event.private_data_len = params->cm_info->private_data_len;
-		event.private_data = (void *)params->cm_info->private_data;
+		/* Only connect_request and reply have valid private data
+		 * the rest of the events this may be left overs from
+		 * connection establishment. CONNECT_REQUEST is issued via
+		 * qedr_iw_mpa_request
+		 */
+		if (event_type == IW_CM_EVENT_CONNECT_REPLY) {
+			event.private_data_len =
+				params->cm_info->private_data_len;
+			event.private_data =
+				(void *)params->cm_info->private_data;
+		}
 	}
 
 	if (ep->cm_id)
diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c
index 511b72809e14..7db35dd6ad74 100644
--- a/drivers/infiniband/sw/rdmavt/qp.c
+++ b/drivers/infiniband/sw/rdmavt/qp.c
@@ -1204,7 +1204,7 @@ struct ib_qp *rvt_create_qp(struct ib_pd *ibpd,
 		err = alloc_ud_wq_attr(qp, rdi->dparms.node);
 		if (err) {
 			ret = (ERR_PTR(err));
-			goto bail_driver_priv;
+			goto bail_rq_rvt;
 		}
 
 		if (init_attr->create_flags & IB_QP_CREATE_NETDEV_USE)
@@ -1314,9 +1314,11 @@ bail_qpn:
 	rvt_free_qpn(&rdi->qp_dev->qpn_table, qp->ibqp.qp_num);
 
 bail_rq_wq:
-	rvt_free_rq(&qp->r_rq);
 	free_ud_wq_attr(qp);
 
+bail_rq_rvt:
+	rvt_free_rq(&qp->r_rq);
+
 bail_driver_priv:
 	rdi->driver_f.qp_priv_free(rdi, qp);
 
diff --git a/drivers/infiniband/sw/siw/siw_qp_rx.c b/drivers/infiniband/sw/siw/siw_qp_rx.c
index 650520244ed0..7271d705f4b0 100644
--- a/drivers/infiniband/sw/siw/siw_qp_rx.c
+++ b/drivers/infiniband/sw/siw/siw_qp_rx.c
@@ -139,7 +139,8 @@ static int siw_rx_pbl(struct siw_rx_stream *srx, int *pbl_idx,
 			break;
 
 		bytes = min(bytes, len);
-		if (siw_rx_kva(srx, (void *)buf_addr, bytes) == bytes) {
+		if (siw_rx_kva(srx, (void *)(uintptr_t)buf_addr, bytes) ==
+		    bytes) {
 			copied += bytes;
 			offset += bytes;
 			len -= bytes;
diff --git a/drivers/input/serio/hp_sdc.c b/drivers/input/serio/hp_sdc.c
index 654252361653..13eacf6ab431 100644
--- a/drivers/input/serio/hp_sdc.c
+++ b/drivers/input/serio/hp_sdc.c
@@ -1021,7 +1021,7 @@ static int __init hp_sdc_register(void)
 	hp_sdc.base_io	 = (unsigned long) 0xf0428000;
 	hp_sdc.data_io	 = (unsigned long) hp_sdc.base_io + 1;
 	hp_sdc.status_io = (unsigned long) hp_sdc.base_io + 3;
-	if (!probe_kernel_read(&i, (unsigned char *)hp_sdc.data_io, 1))
+	if (!copy_from_kernel_nofault(&i, (unsigned char *)hp_sdc.data_io, 1))
 		hp_sdc.dev = (void *)1;
 	hp_sdc.dev_err   = hp_sdc_init();
 #endif
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 39de94edd73a..6548a601edf0 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -1389,7 +1389,7 @@ static int btree_gc_coalesce(struct btree *b, struct btree_op *op,
 			if (__set_blocks(n1, n1->keys + n2->keys,
 					 block_bytes(b->c)) >
 			    btree_blocks(new_nodes[i]))
-				goto out_nocoalesce;
+				goto out_unlock_nocoalesce;
 
 			keys = n2->keys;
 			/* Take the key of the node we're getting rid of */
@@ -1418,7 +1418,7 @@ static int btree_gc_coalesce(struct btree *b, struct btree_op *op,
 
 		if (__bch_keylist_realloc(&keylist,
 					  bkey_u64s(&new_nodes[i]->key)))
-			goto out_nocoalesce;
+			goto out_unlock_nocoalesce;
 
 		bch_btree_node_write(new_nodes[i], &cl);
 		bch_keylist_add(&keylist, &new_nodes[i]->key);
@@ -1464,6 +1464,10 @@ static int btree_gc_coalesce(struct btree *b, struct btree_op *op,
 	/* Invalidated our iterator */
 	return -EINTR;
 
+out_unlock_nocoalesce:
+	for (i = 0; i < nodes; i++)
+		mutex_unlock(&new_nodes[i]->write_lock);
+
 out_nocoalesce:
 	closure_sync(&cl);
 
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index f9975c22bf7e..2014016f9a60 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -19,6 +19,7 @@
 #include <linux/genhd.h>
 #include <linux/idr.h>
 #include <linux/kthread.h>
+#include <linux/workqueue.h>
 #include <linux/module.h>
 #include <linux/random.h>
 #include <linux/reboot.h>
@@ -819,7 +820,8 @@ static void bcache_device_free(struct bcache_device *d)
 }
 
 static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
-			      sector_t sectors, make_request_fn make_request_fn)
+			      sector_t sectors, make_request_fn make_request_fn,
+			      struct block_device *cached_bdev)
 {
 	struct request_queue *q;
 	const size_t max_stripes = min_t(size_t, INT_MAX,
@@ -885,6 +887,20 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
 	q->limits.io_min		= block_size;
 	q->limits.logical_block_size	= block_size;
 	q->limits.physical_block_size	= block_size;
+
+	if (q->limits.logical_block_size > PAGE_SIZE && cached_bdev) {
+		/*
+		 * This should only happen with BCACHE_SB_VERSION_BDEV.
+		 * Block/page size is checked for BCACHE_SB_VERSION_CDEV.
+		 */
+		pr_info("%s: sb/logical block size (%u) greater than page size (%lu) falling back to device logical block size (%u)\n",
+			d->disk->disk_name, q->limits.logical_block_size,
+			PAGE_SIZE, bdev_logical_block_size(cached_bdev));
+
+		/* This also adjusts physical block size/min io size if needed */
+		blk_queue_logical_block_size(q, bdev_logical_block_size(cached_bdev));
+	}
+
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, d->disk->queue);
 	blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, d->disk->queue);
 	blk_queue_flag_set(QUEUE_FLAG_DISCARD, d->disk->queue);
@@ -1340,7 +1356,7 @@ static int cached_dev_init(struct cached_dev *dc, unsigned int block_size)
 
 	ret = bcache_device_init(&dc->disk, block_size,
 			 dc->bdev->bd_part->nr_sects - dc->sb.data_offset,
-			 cached_dev_make_request);
+			 cached_dev_make_request, dc->bdev);
 	if (ret)
 		return ret;
 
@@ -1453,7 +1469,7 @@ static int flash_dev_run(struct cache_set *c, struct uuid_entry *u)
 	kobject_init(&d->kobj, &bch_flash_dev_ktype);
 
 	if (bcache_device_init(d, block_bytes(c), u->sectors,
-			flash_dev_make_request))
+			flash_dev_make_request, NULL))
 		goto err;
 
 	bcache_device_attach(d, c, u - c->uuids);
@@ -2364,7 +2380,7 @@ static bool bch_is_open(struct block_device *bdev)
 }
 
 struct async_reg_args {
-	struct work_struct reg_work;
+	struct delayed_work reg_work;
 	char *path;
 	struct cache_sb *sb;
 	struct cache_sb_disk *sb_disk;
@@ -2375,7 +2391,7 @@ static void register_bdev_worker(struct work_struct *work)
 {
 	int fail = false;
 	struct async_reg_args *args =
-		container_of(work, struct async_reg_args, reg_work);
+		container_of(work, struct async_reg_args, reg_work.work);
 	struct cached_dev *dc;
 
 	dc = kzalloc(sizeof(*dc), GFP_KERNEL);
@@ -2405,7 +2421,7 @@ static void register_cache_worker(struct work_struct *work)
 {
 	int fail = false;
 	struct async_reg_args *args =
-		container_of(work, struct async_reg_args, reg_work);
+		container_of(work, struct async_reg_args, reg_work.work);
 	struct cache *ca;
 
 	ca = kzalloc(sizeof(*ca), GFP_KERNEL);
@@ -2433,11 +2449,12 @@ out:
 static void register_device_aync(struct async_reg_args *args)
 {
 	if (SB_IS_BDEV(args->sb))
-		INIT_WORK(&args->reg_work, register_bdev_worker);
+		INIT_DELAYED_WORK(&args->reg_work, register_bdev_worker);
 	else
-		INIT_WORK(&args->reg_work, register_cache_worker);
+		INIT_DELAYED_WORK(&args->reg_work, register_cache_worker);
 
-	queue_work(system_wq, &args->reg_work);
+	/* 10 jiffies is enough for a delay */
+	queue_delayed_work(system_wq, &args->reg_work, 10);
 }
 
 static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
diff --git a/drivers/misc/kgdbts.c b/drivers/misc/kgdbts.c
index bccd341e9ae1..d5d2af4d10e6 100644
--- a/drivers/misc/kgdbts.c
+++ b/drivers/misc/kgdbts.c
@@ -828,7 +828,7 @@ static void run_plant_and_detach_test(int is_early)
 	char before[BREAK_INSTR_SIZE];
 	char after[BREAK_INSTR_SIZE];
 
-	probe_kernel_read(before, (char *)kgdbts_break_test,
+	copy_from_kernel_nofault(before, (char *)kgdbts_break_test,
 	  BREAK_INSTR_SIZE);
 	init_simple_test();
 	ts.tst = plant_and_detach_test;
@@ -836,8 +836,8 @@ static void run_plant_and_detach_test(int is_early)
 	/* Activate test with initial breakpoint */
 	if (!is_early)
 		kgdb_breakpoint();
-	probe_kernel_read(after, (char *)kgdbts_break_test,
-	  BREAK_INSTR_SIZE);
+	copy_from_kernel_nofault(after, (char *)kgdbts_break_test,
+			BREAK_INSTR_SIZE);
 	if (memcmp(before, after, BREAK_INSTR_SIZE)) {
 		printk(KERN_CRIT "kgdbts: ERROR kgdb corrupted memory\n");
 		panic("kgdb memory corruption");
diff --git a/drivers/net/bareudp.c b/drivers/net/bareudp.c
index 5d3c691a1c66..3dd46cd55114 100644
--- a/drivers/net/bareudp.c
+++ b/drivers/net/bareudp.c
@@ -572,6 +572,9 @@ static int bareudp2info(struct nlattr *data[], struct bareudp_conf *conf,
 	if (data[IFLA_BAREUDP_SRCPORT_MIN])
 		conf->sport_min =  nla_get_u16(data[IFLA_BAREUDP_SRCPORT_MIN]);
 
+	if (data[IFLA_BAREUDP_MULTIPROTO_MODE])
+		conf->multi_proto_mode = true;
+
 	return 0;
 }
 
diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index c7ac63f41918..946e41f020a5 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -1147,6 +1147,8 @@ static int bcm_sf2_sw_probe(struct platform_device *pdev)
 	set_bit(0, priv->cfp.used);
 	set_bit(0, priv->cfp.unique);
 
+	/* Balance of_node_put() done by of_find_node_by_name() */
+	of_node_get(dn);
 	ports = of_find_node_by_name(dn, "ports");
 	if (ports) {
 		bcm_sf2_identify_ports(priv, ports);
diff --git a/drivers/net/dsa/sja1105/sja1105_vl.c b/drivers/net/dsa/sja1105/sja1105_vl.c
index 9ddc49b7eb8f..ffc4042b4502 100644
--- a/drivers/net/dsa/sja1105/sja1105_vl.c
+++ b/drivers/net/dsa/sja1105/sja1105_vl.c
@@ -7,6 +7,165 @@
 
 #define SJA1105_SIZE_VL_STATUS			8
 
+/* Insert into the global gate list, sorted by gate action time. */
+static int sja1105_insert_gate_entry(struct sja1105_gating_config *gating_cfg,
+				     struct sja1105_rule *rule,
+				     u8 gate_state, s64 entry_time,
+				     struct netlink_ext_ack *extack)
+{
+	struct sja1105_gate_entry *e;
+	int rc;
+
+	e = kzalloc(sizeof(*e), GFP_KERNEL);
+	if (!e)
+		return -ENOMEM;
+
+	e->rule = rule;
+	e->gate_state = gate_state;
+	e->interval = entry_time;
+
+	if (list_empty(&gating_cfg->entries)) {
+		list_add(&e->list, &gating_cfg->entries);
+	} else {
+		struct sja1105_gate_entry *p;
+
+		list_for_each_entry(p, &gating_cfg->entries, list) {
+			if (p->interval == e->interval) {
+				NL_SET_ERR_MSG_MOD(extack,
+						   "Gate conflict");
+				rc = -EBUSY;
+				goto err;
+			}
+
+			if (e->interval < p->interval)
+				break;
+		}
+		list_add(&e->list, p->list.prev);
+	}
+
+	gating_cfg->num_entries++;
+
+	return 0;
+err:
+	kfree(e);
+	return rc;
+}
+
+/* The gate entries contain absolute times in their e->interval field. Convert
+ * that to proper intervals (i.e. "0, 5, 10, 15" to "5, 5, 5, 5").
+ */
+static void
+sja1105_gating_cfg_time_to_interval(struct sja1105_gating_config *gating_cfg,
+				    u64 cycle_time)
+{
+	struct sja1105_gate_entry *last_e;
+	struct sja1105_gate_entry *e;
+	struct list_head *prev;
+
+	list_for_each_entry(e, &gating_cfg->entries, list) {
+		struct sja1105_gate_entry *p;
+
+		prev = e->list.prev;
+
+		if (prev == &gating_cfg->entries)
+			continue;
+
+		p = list_entry(prev, struct sja1105_gate_entry, list);
+		p->interval = e->interval - p->interval;
+	}
+	last_e = list_last_entry(&gating_cfg->entries,
+				 struct sja1105_gate_entry, list);
+	last_e->interval = cycle_time - last_e->interval;
+}
+
+static void sja1105_free_gating_config(struct sja1105_gating_config *gating_cfg)
+{
+	struct sja1105_gate_entry *e, *n;
+
+	list_for_each_entry_safe(e, n, &gating_cfg->entries, list) {
+		list_del(&e->list);
+		kfree(e);
+	}
+}
+
+static int sja1105_compose_gating_subschedule(struct sja1105_private *priv,
+					      struct netlink_ext_ack *extack)
+{
+	struct sja1105_gating_config *gating_cfg = &priv->tas_data.gating_cfg;
+	struct sja1105_rule *rule;
+	s64 max_cycle_time = 0;
+	s64 its_base_time = 0;
+	int i, rc = 0;
+
+	sja1105_free_gating_config(gating_cfg);
+
+	list_for_each_entry(rule, &priv->flow_block.rules, list) {
+		if (rule->type != SJA1105_RULE_VL)
+			continue;
+		if (rule->vl.type != SJA1105_VL_TIME_TRIGGERED)
+			continue;
+
+		if (max_cycle_time < rule->vl.cycle_time) {
+			max_cycle_time = rule->vl.cycle_time;
+			its_base_time = rule->vl.base_time;
+		}
+	}
+
+	if (!max_cycle_time)
+		return 0;
+
+	dev_dbg(priv->ds->dev, "max_cycle_time %lld its_base_time %lld\n",
+		max_cycle_time, its_base_time);
+
+	gating_cfg->base_time = its_base_time;
+	gating_cfg->cycle_time = max_cycle_time;
+	gating_cfg->num_entries = 0;
+
+	list_for_each_entry(rule, &priv->flow_block.rules, list) {
+		s64 time;
+		s64 rbt;
+
+		if (rule->type != SJA1105_RULE_VL)
+			continue;
+		if (rule->vl.type != SJA1105_VL_TIME_TRIGGERED)
+			continue;
+
+		/* Calculate the difference between this gating schedule's
+		 * base time, and the base time of the gating schedule with the
+		 * longest cycle time. We call it the relative base time (rbt).
+		 */
+		rbt = future_base_time(rule->vl.base_time, rule->vl.cycle_time,
+				       its_base_time);
+		rbt -= its_base_time;
+
+		time = rbt;
+
+		for (i = 0; i < rule->vl.num_entries; i++) {
+			u8 gate_state = rule->vl.entries[i].gate_state;
+			s64 entry_time = time;
+
+			while (entry_time < max_cycle_time) {
+				rc = sja1105_insert_gate_entry(gating_cfg, rule,
+							       gate_state,
+							       entry_time,
+							       extack);
+				if (rc)
+					goto err;
+
+				entry_time += rule->vl.cycle_time;
+			}
+			time += rule->vl.entries[i].interval;
+		}
+	}
+
+	sja1105_gating_cfg_time_to_interval(gating_cfg, max_cycle_time);
+
+	return 0;
+err:
+	sja1105_free_gating_config(gating_cfg);
+	return rc;
+}
+
 /* The switch flow classification core implements TTEthernet, which 'thinks' in
  * terms of Virtual Links (VL), a concept borrowed from ARINC 664 part 7.
  * However it also has one other operating mode (VLLUPFORMAT=0) where it acts
@@ -342,7 +501,9 @@ int sja1105_vl_redirect(struct sja1105_private *priv, int port,
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Can only redirect based on DMAC");
 		return -EOPNOTSUPP;
-	} else if (key->type != SJA1105_KEY_VLAN_AWARE_VL) {
+	} else if ((priv->vlan_state == SJA1105_VLAN_BEST_EFFORT ||
+		    priv->vlan_state == SJA1105_VLAN_FILTERING_FULL) &&
+		   key->type != SJA1105_KEY_VLAN_AWARE_VL) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Can only redirect based on {DMAC, VID, PCP}");
 		return -EOPNOTSUPP;
@@ -388,171 +549,19 @@ int sja1105_vl_delete(struct sja1105_private *priv, int port,
 		kfree(rule);
 	}
 
-	rc = sja1105_init_virtual_links(priv, extack);
+	rc = sja1105_compose_gating_subschedule(priv, extack);
 	if (rc)
 		return rc;
 
-	return sja1105_static_config_reload(priv, SJA1105_VIRTUAL_LINKS);
-}
-
-/* Insert into the global gate list, sorted by gate action time. */
-static int sja1105_insert_gate_entry(struct sja1105_gating_config *gating_cfg,
-				     struct sja1105_rule *rule,
-				     u8 gate_state, s64 entry_time,
-				     struct netlink_ext_ack *extack)
-{
-	struct sja1105_gate_entry *e;
-	int rc;
-
-	e = kzalloc(sizeof(*e), GFP_KERNEL);
-	if (!e)
-		return -ENOMEM;
-
-	e->rule = rule;
-	e->gate_state = gate_state;
-	e->interval = entry_time;
-
-	if (list_empty(&gating_cfg->entries)) {
-		list_add(&e->list, &gating_cfg->entries);
-	} else {
-		struct sja1105_gate_entry *p;
-
-		list_for_each_entry(p, &gating_cfg->entries, list) {
-			if (p->interval == e->interval) {
-				NL_SET_ERR_MSG_MOD(extack,
-						   "Gate conflict");
-				rc = -EBUSY;
-				goto err;
-			}
-
-			if (e->interval < p->interval)
-				break;
-		}
-		list_add(&e->list, p->list.prev);
-	}
-
-	gating_cfg->num_entries++;
-
-	return 0;
-err:
-	kfree(e);
-	return rc;
-}
-
-/* The gate entries contain absolute times in their e->interval field. Convert
- * that to proper intervals (i.e. "0, 5, 10, 15" to "5, 5, 5, 5").
- */
-static void
-sja1105_gating_cfg_time_to_interval(struct sja1105_gating_config *gating_cfg,
-				    u64 cycle_time)
-{
-	struct sja1105_gate_entry *last_e;
-	struct sja1105_gate_entry *e;
-	struct list_head *prev;
-
-	list_for_each_entry(e, &gating_cfg->entries, list) {
-		struct sja1105_gate_entry *p;
-
-		prev = e->list.prev;
-
-		if (prev == &gating_cfg->entries)
-			continue;
-
-		p = list_entry(prev, struct sja1105_gate_entry, list);
-		p->interval = e->interval - p->interval;
-	}
-	last_e = list_last_entry(&gating_cfg->entries,
-				 struct sja1105_gate_entry, list);
-	if (last_e->list.prev != &gating_cfg->entries)
-		last_e->interval = cycle_time - last_e->interval;
-}
-
-static void sja1105_free_gating_config(struct sja1105_gating_config *gating_cfg)
-{
-	struct sja1105_gate_entry *e, *n;
-
-	list_for_each_entry_safe(e, n, &gating_cfg->entries, list) {
-		list_del(&e->list);
-		kfree(e);
-	}
-}
-
-static int sja1105_compose_gating_subschedule(struct sja1105_private *priv,
-					      struct netlink_ext_ack *extack)
-{
-	struct sja1105_gating_config *gating_cfg = &priv->tas_data.gating_cfg;
-	struct sja1105_rule *rule;
-	s64 max_cycle_time = 0;
-	s64 its_base_time = 0;
-	int i, rc = 0;
-
-	list_for_each_entry(rule, &priv->flow_block.rules, list) {
-		if (rule->type != SJA1105_RULE_VL)
-			continue;
-		if (rule->vl.type != SJA1105_VL_TIME_TRIGGERED)
-			continue;
-
-		if (max_cycle_time < rule->vl.cycle_time) {
-			max_cycle_time = rule->vl.cycle_time;
-			its_base_time = rule->vl.base_time;
-		}
-	}
-
-	if (!max_cycle_time)
-		return 0;
-
-	dev_dbg(priv->ds->dev, "max_cycle_time %lld its_base_time %lld\n",
-		max_cycle_time, its_base_time);
-
-	sja1105_free_gating_config(gating_cfg);
-
-	gating_cfg->base_time = its_base_time;
-	gating_cfg->cycle_time = max_cycle_time;
-	gating_cfg->num_entries = 0;
-
-	list_for_each_entry(rule, &priv->flow_block.rules, list) {
-		s64 time;
-		s64 rbt;
-
-		if (rule->type != SJA1105_RULE_VL)
-			continue;
-		if (rule->vl.type != SJA1105_VL_TIME_TRIGGERED)
-			continue;
-
-		/* Calculate the difference between this gating schedule's
-		 * base time, and the base time of the gating schedule with the
-		 * longest cycle time. We call it the relative base time (rbt).
-		 */
-		rbt = future_base_time(rule->vl.base_time, rule->vl.cycle_time,
-				       its_base_time);
-		rbt -= its_base_time;
-
-		time = rbt;
-
-		for (i = 0; i < rule->vl.num_entries; i++) {
-			u8 gate_state = rule->vl.entries[i].gate_state;
-			s64 entry_time = time;
-
-			while (entry_time < max_cycle_time) {
-				rc = sja1105_insert_gate_entry(gating_cfg, rule,
-							       gate_state,
-							       entry_time,
-							       extack);
-				if (rc)
-					goto err;
-
-				entry_time += rule->vl.cycle_time;
-			}
-			time += rule->vl.entries[i].interval;
-		}
-	}
+	rc = sja1105_init_virtual_links(priv, extack);
+	if (rc)
+		return rc;
 
-	sja1105_gating_cfg_time_to_interval(gating_cfg, max_cycle_time);
+	rc = sja1105_init_scheduling(priv);
+	if (rc < 0)
+		return rc;
 
-	return 0;
-err:
-	sja1105_free_gating_config(gating_cfg);
-	return rc;
+	return sja1105_static_config_reload(priv, SJA1105_VIRTUAL_LINKS);
 }
 
 int sja1105_vl_gate(struct sja1105_private *priv, int port,
@@ -588,14 +597,12 @@ int sja1105_vl_gate(struct sja1105_private *priv, int port,
 
 	if (priv->vlan_state == SJA1105_VLAN_UNAWARE &&
 	    key->type != SJA1105_KEY_VLAN_UNAWARE_VL) {
-		dev_err(priv->ds->dev, "1: vlan state %d key type %d\n",
-			priv->vlan_state, key->type);
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Can only gate based on DMAC");
 		return -EOPNOTSUPP;
-	} else if (key->type != SJA1105_KEY_VLAN_AWARE_VL) {
-		dev_err(priv->ds->dev, "2: vlan state %d key type %d\n",
-			priv->vlan_state, key->type);
+	} else if ((priv->vlan_state == SJA1105_VLAN_BEST_EFFORT ||
+		    priv->vlan_state == SJA1105_VLAN_FILTERING_FULL) &&
+		   key->type != SJA1105_KEY_VLAN_AWARE_VL) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Can only gate based on {DMAC, VID, PCP}");
 		return -EOPNOTSUPP;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index b93e05f91d77..6a884df44612 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -6292,6 +6292,7 @@ int bnxt_hwrm_set_coal(struct bnxt *bp)
 
 static void bnxt_hwrm_stat_ctx_free(struct bnxt *bp)
 {
+	struct hwrm_stat_ctx_clr_stats_input req0 = {0};
 	struct hwrm_stat_ctx_free_input req = {0};
 	int i;
 
@@ -6301,6 +6302,7 @@ static void bnxt_hwrm_stat_ctx_free(struct bnxt *bp)
 	if (BNXT_CHIP_TYPE_NITRO_A0(bp))
 		return;
 
+	bnxt_hwrm_cmd_hdr_init(bp, &req0, HWRM_STAT_CTX_CLR_STATS, -1, -1);
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_STAT_CTX_FREE, -1, -1);
 
 	mutex_lock(&bp->hwrm_cmd_lock);
@@ -6310,7 +6312,11 @@ static void bnxt_hwrm_stat_ctx_free(struct bnxt *bp)
 
 		if (cpr->hw_stats_ctx_id != INVALID_STATS_CTX_ID) {
 			req.stat_ctx_id = cpu_to_le32(cpr->hw_stats_ctx_id);
-
+			if (BNXT_FW_MAJ(bp) <= 20) {
+				req0.stat_ctx_id = req.stat_ctx_id;
+				_hwrm_send_message(bp, &req0, sizeof(req0),
+						   HWRM_CMD_TIMEOUT);
+			}
 			_hwrm_send_message(bp, &req, sizeof(req),
 					   HWRM_CMD_TIMEOUT);
 
@@ -6976,7 +6982,8 @@ static int __bnxt_hwrm_func_qcaps(struct bnxt *bp)
 		bp->fw_cap |= BNXT_FW_CAP_ERR_RECOVER_RELOAD;
 
 	bp->tx_push_thresh = 0;
-	if (flags & FUNC_QCAPS_RESP_FLAGS_PUSH_MODE_SUPPORTED)
+	if ((flags & FUNC_QCAPS_RESP_FLAGS_PUSH_MODE_SUPPORTED) &&
+	    BNXT_FW_MAJ(bp) > 217)
 		bp->tx_push_thresh = BNXT_TX_PUSH_THRESH;
 
 	hw_resc->max_rsscos_ctxs = le16_to_cpu(resp->max_rsscos_ctx);
@@ -7240,8 +7247,9 @@ static int __bnxt_hwrm_ver_get(struct bnxt *bp, bool silent)
 static int bnxt_hwrm_ver_get(struct bnxt *bp)
 {
 	struct hwrm_ver_get_output *resp = bp->hwrm_cmd_resp_addr;
+	u16 fw_maj, fw_min, fw_bld, fw_rsv;
 	u32 dev_caps_cfg, hwrm_ver;
-	int rc;
+	int rc, len;
 
 	bp->hwrm_max_req_len = HWRM_MAX_REQ_LEN;
 	mutex_lock(&bp->hwrm_cmd_lock);
@@ -7273,9 +7281,22 @@ static int bnxt_hwrm_ver_get(struct bnxt *bp)
 			 resp->hwrm_intf_maj_8b, resp->hwrm_intf_min_8b,
 			 resp->hwrm_intf_upd_8b);
 
-	snprintf(bp->fw_ver_str, BC_HWRM_STR_LEN, "%d.%d.%d.%d",
-		 resp->hwrm_fw_maj_8b, resp->hwrm_fw_min_8b,
-		 resp->hwrm_fw_bld_8b, resp->hwrm_fw_rsvd_8b);
+	fw_maj = le16_to_cpu(resp->hwrm_fw_major);
+	if (bp->hwrm_spec_code > 0x10803 && fw_maj) {
+		fw_min = le16_to_cpu(resp->hwrm_fw_minor);
+		fw_bld = le16_to_cpu(resp->hwrm_fw_build);
+		fw_rsv = le16_to_cpu(resp->hwrm_fw_patch);
+		len = FW_VER_STR_LEN;
+	} else {
+		fw_maj = resp->hwrm_fw_maj_8b;
+		fw_min = resp->hwrm_fw_min_8b;
+		fw_bld = resp->hwrm_fw_bld_8b;
+		fw_rsv = resp->hwrm_fw_rsvd_8b;
+		len = BC_HWRM_STR_LEN;
+	}
+	bp->fw_ver_code = BNXT_FW_VER_CODE(fw_maj, fw_min, fw_bld, fw_rsv);
+	snprintf(bp->fw_ver_str, len, "%d.%d.%d.%d", fw_maj, fw_min, fw_bld,
+		 fw_rsv);
 
 	if (strlen(resp->active_pkg_name)) {
 		int fw_ver_len = strlen(bp->fw_ver_str);
@@ -11892,7 +11913,8 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	dev->ethtool_ops = &bnxt_ethtool_ops;
 	pci_set_drvdata(pdev, dev);
 
-	bnxt_vpd_read_info(bp);
+	if (BNXT_PF(bp))
+		bnxt_vpd_read_info(bp);
 
 	rc = bnxt_alloc_hwrm_resources(bp);
 	if (rc)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 9e173d74b72a..78e2fd63ac3d 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1746,6 +1746,11 @@ struct bnxt {
 #define PHY_VER_STR_LEN         (FW_VER_STR_LEN - BC_HWRM_STR_LEN)
 	char			fw_ver_str[FW_VER_STR_LEN];
 	char			hwrm_ver_supp[FW_VER_STR_LEN];
+	u64			fw_ver_code;
+#define BNXT_FW_VER_CODE(maj, min, bld, rsv)			\
+	((u64)(maj) << 48 | (u64)(min) << 32 | (u64)(bld) << 16 | (rsv))
+#define BNXT_FW_MAJ(bp)		((bp)->fw_ver_code >> 48)
+
 	__be16			vxlan_port;
 	u8			vxlan_port_cnt;
 	__le16			vxlan_fw_dst_port_id;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
index 4d482d75a20b..0a9a4467d7c7 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
@@ -1889,7 +1889,8 @@ static void bnxt_tc_setup_indr_rel(void *cb_priv)
 }
 
 static int bnxt_tc_setup_indr_block(struct net_device *netdev, struct bnxt *bp,
-				    struct flow_block_offload *f)
+				    struct flow_block_offload *f, void *data,
+				    void (*cleanup)(struct flow_block_cb *block_cb))
 {
 	struct bnxt_flower_indr_block_cb_priv *cb_priv;
 	struct flow_block_cb *block_cb;
@@ -1907,9 +1908,10 @@ static int bnxt_tc_setup_indr_block(struct net_device *netdev, struct bnxt *bp,
 		cb_priv->bp = bp;
 		list_add(&cb_priv->list, &bp->tc_indr_block_list);
 
-		block_cb = flow_block_cb_alloc(bnxt_tc_setup_indr_block_cb,
-					       cb_priv, cb_priv,
-					       bnxt_tc_setup_indr_rel);
+		block_cb = flow_indr_block_cb_alloc(bnxt_tc_setup_indr_block_cb,
+						    cb_priv, cb_priv,
+						    bnxt_tc_setup_indr_rel, f,
+						    netdev, data, bp, cleanup);
 		if (IS_ERR(block_cb)) {
 			list_del(&cb_priv->list);
 			kfree(cb_priv);
@@ -1930,7 +1932,7 @@ static int bnxt_tc_setup_indr_block(struct net_device *netdev, struct bnxt *bp,
 		if (!block_cb)
 			return -ENOENT;
 
-		flow_block_cb_remove(block_cb, f);
+		flow_indr_block_cb_remove(block_cb, f);
 		list_del(&block_cb->driver_list);
 		break;
 	default:
@@ -1945,14 +1947,17 @@ static bool bnxt_is_netdev_indr_offload(struct net_device *netdev)
 }
 
 static int bnxt_tc_setup_indr_cb(struct net_device *netdev, void *cb_priv,
-				 enum tc_setup_type type, void *type_data)
+				 enum tc_setup_type type, void *type_data,
+				 void *data,
+				 void (*cleanup)(struct flow_block_cb *block_cb))
 {
 	if (!bnxt_is_netdev_indr_offload(netdev))
 		return -EOPNOTSUPP;
 
 	switch (type) {
 	case TC_SETUP_BLOCK:
-		return bnxt_tc_setup_indr_block(netdev, cb_priv, type_data);
+		return bnxt_tc_setup_indr_block(netdev, cb_priv, type_data, data,
+						cleanup);
 	default:
 		break;
 	}
@@ -2074,7 +2079,7 @@ void bnxt_shutdown_tc(struct bnxt *bp)
 		return;
 
 	flow_indr_dev_unregister(bnxt_tc_setup_indr_cb, bp,
-				 bnxt_tc_setup_indr_block_cb);
+				 bnxt_tc_setup_indr_rel);
 	rhashtable_destroy(&tc_info->flow_table);
 	rhashtable_destroy(&tc_info->l2_table);
 	rhashtable_destroy(&tc_info->decap_l2_table);
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index ff31da0ed846..af924a8b885f 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -459,17 +459,6 @@ static inline void bcmgenet_rdma_ring_writel(struct bcmgenet_priv *priv,
 			genet_dma_ring_regs[r]);
 }
 
-static bool bcmgenet_hfb_is_filter_enabled(struct bcmgenet_priv *priv,
-					   u32 f_index)
-{
-	u32 offset;
-	u32 reg;
-
-	offset = HFB_FLT_ENABLE_V3PLUS + (f_index < 32) * sizeof(u32);
-	reg = bcmgenet_hfb_reg_readl(priv, offset);
-	return !!(reg & (1 << (f_index % 32)));
-}
-
 static void bcmgenet_hfb_enable_filter(struct bcmgenet_priv *priv, u32 f_index)
 {
 	u32 offset;
@@ -533,19 +522,6 @@ static void bcmgenet_hfb_set_filter_length(struct bcmgenet_priv *priv,
 	bcmgenet_hfb_reg_writel(priv, reg, offset);
 }
 
-static int bcmgenet_hfb_find_unused_filter(struct bcmgenet_priv *priv)
-{
-	u32 f_index;
-
-	/* First MAX_NUM_OF_FS_RULES are reserved for Rx NFC filters */
-	for (f_index = MAX_NUM_OF_FS_RULES;
-	     f_index < priv->hw_params->hfb_filter_cnt; f_index++)
-		if (!bcmgenet_hfb_is_filter_enabled(priv, f_index))
-			return f_index;
-
-	return -ENOMEM;
-}
-
 static int bcmgenet_hfb_validate_mask(void *mask, size_t size)
 {
 	while (size) {
@@ -634,8 +610,9 @@ static int bcmgenet_hfb_create_rxnfc_filter(struct bcmgenet_priv *priv,
 {
 	struct ethtool_rx_flow_spec *fs = &rule->fs;
 	int err = 0, offset = 0, f_length = 0;
-	u16 val_16, mask_16;
 	u8 val_8, mask_8;
+	__be16 val_16;
+	u16 mask_16;
 	size_t size;
 	u32 *f_data;
 
@@ -744,59 +721,6 @@ static int bcmgenet_hfb_create_rxnfc_filter(struct bcmgenet_priv *priv,
 	return err;
 }
 
-/* bcmgenet_hfb_add_filter
- *
- * Add new filter to Hardware Filter Block to match and direct Rx traffic to
- * desired Rx queue.
- *
- * f_data is an array of unsigned 32-bit integers where each 32-bit integer
- * provides filter data for 2 bytes (4 nibbles) of Rx frame:
- *
- * bits 31:20 - unused
- * bit  19    - nibble 0 match enable
- * bit  18    - nibble 1 match enable
- * bit  17    - nibble 2 match enable
- * bit  16    - nibble 3 match enable
- * bits 15:12 - nibble 0 data
- * bits 11:8  - nibble 1 data
- * bits 7:4   - nibble 2 data
- * bits 3:0   - nibble 3 data
- *
- * Example:
- * In order to match:
- * - Ethernet frame type = 0x0800 (IP)
- * - IP version field = 4
- * - IP protocol field = 0x11 (UDP)
- *
- * The following filter is needed:
- * u32 hfb_filter_ipv4_udp[] = {
- *   Rx frame offset 0x00: 0x00000000, 0x00000000, 0x00000000, 0x00000000,
- *   Rx frame offset 0x08: 0x00000000, 0x00000000, 0x000F0800, 0x00084000,
- *   Rx frame offset 0x10: 0x00000000, 0x00000000, 0x00000000, 0x00030011,
- * };
- *
- * To add the filter to HFB and direct the traffic to Rx queue 0, call:
- * bcmgenet_hfb_add_filter(priv, hfb_filter_ipv4_udp,
- *                         ARRAY_SIZE(hfb_filter_ipv4_udp), 0);
- */
-int bcmgenet_hfb_add_filter(struct bcmgenet_priv *priv, u32 *f_data,
-			    u32 f_length, u32 rx_queue)
-{
-	int f_index;
-
-	f_index = bcmgenet_hfb_find_unused_filter(priv);
-	if (f_index < 0)
-		return -ENOMEM;
-
-	if (f_length > priv->hw_params->hfb_filter_size)
-		return -EINVAL;
-
-	bcmgenet_hfb_set_filter(priv, f_data, f_length, rx_queue, f_index);
-	bcmgenet_hfb_enable_filter(priv, f_index);
-
-	return 0;
-}
-
 /* bcmgenet_hfb_clear
  *
  * Clear Hardware Filter Block and disable all filtering.
@@ -2118,11 +2042,6 @@ static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev)
 		goto out;
 	}
 
-	if (skb_padto(skb, ETH_ZLEN)) {
-		ret = NETDEV_TX_OK;
-		goto out;
-	}
-
 	/* Retain how many bytes will be sent on the wire, without TSB inserted
 	 * by transmit checksum offload
 	 */
@@ -2169,6 +2088,9 @@ static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev)
 		len_stat = (size << DMA_BUFLENGTH_SHIFT) |
 			   (priv->hw_params->qtag_mask << DMA_TX_QTAG_SHIFT);
 
+		/* Note: if we ever change from DMA_TX_APPEND_CRC below we
+		 * will need to restore software padding of "runt" packets
+		 */
 		if (!i) {
 			len_stat |= DMA_TX_APPEND_CRC | DMA_SOP;
 			if (skb->ip_summed == CHECKSUM_PARTIAL)
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 7a3b22b35238..ebff1fc0d8ce 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -18168,8 +18168,8 @@ static pci_ers_result_t tg3_io_error_detected(struct pci_dev *pdev,
 
 	rtnl_lock();
 
-	/* We probably don't have netdev yet */
-	if (!netdev || !netif_running(netdev))
+	/* Could be second call or maybe we don't have netdev yet */
+	if (!netdev || tp->pcierr_recovery || !netif_running(netdev))
 		goto done;
 
 	/* We needn't recover from permanent error */
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 67933079aeea..52582e8ed90e 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -2558,7 +2558,7 @@ static int macb_open(struct net_device *dev)
 
 	err = macb_phylink_connect(bp);
 	if (err)
-		goto napi_exit;
+		goto reset_hw;
 
 	netif_tx_start_all_queues(dev);
 
@@ -2567,9 +2567,11 @@ static int macb_open(struct net_device *dev)
 
 	return 0;
 
-napi_exit:
+reset_hw:
+	macb_reset_hw(bp);
 	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue)
 		napi_disable(&queue->napi);
+	macb_free_consistent(bp);
 pm_exit:
 	pm_runtime_put_sync(&bp->pdev->dev);
 	return err;
@@ -3760,15 +3762,9 @@ static int macb_init(struct platform_device *pdev)
 
 static struct sifive_fu540_macb_mgmt *mgmt;
 
-/* Initialize and start the Receiver and Transmit subsystems */
-static int at91ether_start(struct net_device *dev)
+static int at91ether_alloc_coherent(struct macb *lp)
 {
-	struct macb *lp = netdev_priv(dev);
 	struct macb_queue *q = &lp->queues[0];
-	struct macb_dma_desc *desc;
-	dma_addr_t addr;
-	u32 ctl;
-	int i;
 
 	q->rx_ring = dma_alloc_coherent(&lp->pdev->dev,
 					 (AT91ETHER_MAX_RX_DESCR *
@@ -3790,6 +3786,43 @@ static int at91ether_start(struct net_device *dev)
 		return -ENOMEM;
 	}
 
+	return 0;
+}
+
+static void at91ether_free_coherent(struct macb *lp)
+{
+	struct macb_queue *q = &lp->queues[0];
+
+	if (q->rx_ring) {
+		dma_free_coherent(&lp->pdev->dev,
+				  AT91ETHER_MAX_RX_DESCR *
+				  macb_dma_desc_get_size(lp),
+				  q->rx_ring, q->rx_ring_dma);
+		q->rx_ring = NULL;
+	}
+
+	if (q->rx_buffers) {
+		dma_free_coherent(&lp->pdev->dev,
+				  AT91ETHER_MAX_RX_DESCR *
+				  AT91ETHER_MAX_RBUFF_SZ,
+				  q->rx_buffers, q->rx_buffers_dma);
+		q->rx_buffers = NULL;
+	}
+}
+
+/* Initialize and start the Receiver and Transmit subsystems */
+static int at91ether_start(struct macb *lp)
+{
+	struct macb_queue *q = &lp->queues[0];
+	struct macb_dma_desc *desc;
+	dma_addr_t addr;
+	u32 ctl;
+	int i, ret;
+
+	ret = at91ether_alloc_coherent(lp);
+	if (ret)
+		return ret;
+
 	addr = q->rx_buffers_dma;
 	for (i = 0; i < AT91ETHER_MAX_RX_DESCR; i++) {
 		desc = macb_rx_desc(q, i);
@@ -3811,9 +3844,39 @@ static int at91ether_start(struct net_device *dev)
 	ctl = macb_readl(lp, NCR);
 	macb_writel(lp, NCR, ctl | MACB_BIT(RE) | MACB_BIT(TE));
 
+	/* Enable MAC interrupts */
+	macb_writel(lp, IER, MACB_BIT(RCOMP)	|
+			     MACB_BIT(RXUBR)	|
+			     MACB_BIT(ISR_TUND)	|
+			     MACB_BIT(ISR_RLE)	|
+			     MACB_BIT(TCOMP)	|
+			     MACB_BIT(ISR_ROVR)	|
+			     MACB_BIT(HRESP));
+
 	return 0;
 }
 
+static void at91ether_stop(struct macb *lp)
+{
+	u32 ctl;
+
+	/* Disable MAC interrupts */
+	macb_writel(lp, IDR, MACB_BIT(RCOMP)	|
+			     MACB_BIT(RXUBR)	|
+			     MACB_BIT(ISR_TUND)	|
+			     MACB_BIT(ISR_RLE)	|
+			     MACB_BIT(TCOMP)	|
+			     MACB_BIT(ISR_ROVR) |
+			     MACB_BIT(HRESP));
+
+	/* Disable Receiver and Transmitter */
+	ctl = macb_readl(lp, NCR);
+	macb_writel(lp, NCR, ctl & ~(MACB_BIT(TE) | MACB_BIT(RE)));
+
+	/* Free resources. */
+	at91ether_free_coherent(lp);
+}
+
 /* Open the ethernet interface */
 static int at91ether_open(struct net_device *dev)
 {
@@ -3833,63 +3896,36 @@ static int at91ether_open(struct net_device *dev)
 
 	macb_set_hwaddr(lp);
 
-	ret = at91ether_start(dev);
+	ret = at91ether_start(lp);
 	if (ret)
-		return ret;
-
-	/* Enable MAC interrupts */
-	macb_writel(lp, IER, MACB_BIT(RCOMP)	|
-			     MACB_BIT(RXUBR)	|
-			     MACB_BIT(ISR_TUND)	|
-			     MACB_BIT(ISR_RLE)	|
-			     MACB_BIT(TCOMP)	|
-			     MACB_BIT(ISR_ROVR)	|
-			     MACB_BIT(HRESP));
+		goto pm_exit;
 
 	ret = macb_phylink_connect(lp);
 	if (ret)
-		return ret;
+		goto stop;
 
 	netif_start_queue(dev);
 
 	return 0;
+
+stop:
+	at91ether_stop(lp);
+pm_exit:
+	pm_runtime_put_sync(&lp->pdev->dev);
+	return ret;
 }
 
 /* Close the interface */
 static int at91ether_close(struct net_device *dev)
 {
 	struct macb *lp = netdev_priv(dev);
-	struct macb_queue *q = &lp->queues[0];
-	u32 ctl;
-
-	/* Disable Receiver and Transmitter */
-	ctl = macb_readl(lp, NCR);
-	macb_writel(lp, NCR, ctl & ~(MACB_BIT(TE) | MACB_BIT(RE)));
-
-	/* Disable MAC interrupts */
-	macb_writel(lp, IDR, MACB_BIT(RCOMP)	|
-			     MACB_BIT(RXUBR)	|
-			     MACB_BIT(ISR_TUND)	|
-			     MACB_BIT(ISR_RLE)	|
-			     MACB_BIT(TCOMP)	|
-			     MACB_BIT(ISR_ROVR) |
-			     MACB_BIT(HRESP));
 
 	netif_stop_queue(dev);
 
 	phylink_stop(lp->phylink);
 	phylink_disconnect_phy(lp->phylink);
 
-	dma_free_coherent(&lp->pdev->dev,
-			  AT91ETHER_MAX_RX_DESCR *
-			  macb_dma_desc_get_size(lp),
-			  q->rx_ring, q->rx_ring_dma);
-	q->rx_ring = NULL;
-
-	dma_free_coherent(&lp->pdev->dev,
-			  AT91ETHER_MAX_RX_DESCR * AT91ETHER_MAX_RBUFF_SZ,
-			  q->rx_buffers, q->rx_buffers_dma);
-	q->rx_buffers = NULL;
+	at91ether_stop(lp);
 
 	return pm_runtime_put(&lp->pdev->dev);
 }
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c
index 9960e9d206fc..75474f810249 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c
@@ -2381,7 +2381,6 @@ int cudbg_collect_dump_context(struct cudbg_init *pdbg_init,
 	u8 mem_type[CTXT_INGRESS + 1] = { 0 };
 	struct cudbg_buffer temp_buff = { 0 };
 	struct cudbg_ch_cntxt *buff;
-	u64 *dst_off, *src_off;
 	u8 *ctx_buf;
 	u8 i, k;
 	int rc;
@@ -2450,8 +2449,11 @@ int cudbg_collect_dump_context(struct cudbg_init *pdbg_init,
 		}
 
 		for (j = 0; j < max_ctx_qid; j++) {
+			__be64 *dst_off;
+			u64 *src_off;
+
 			src_off = (u64 *)(ctx_buf + j * SGE_CTXT_SIZE);
-			dst_off = (u64 *)buff->data;
+			dst_off = (__be64 *)buff->data;
 
 			/* The data is stored in 64-bit cpu order.  Convert it
 			 * to big endian before parsing.
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.h
index d3c654b9989b..80c6627fe981 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.h
@@ -136,6 +136,9 @@ static inline __u8 bitswap_1(unsigned char val)
 	       ((val & 0x02) << 5) |
 	       ((val & 0x01) << 7);
 }
+
+extern const char * const dcb_ver_array[];
+
 #define CXGB4_DCB_ENABLED true
 
 #else /* !CONFIG_CHELSIO_T4_DCB */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
index 828499256004..b477b8842905 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
@@ -2379,7 +2379,6 @@ static const struct file_operations rss_vf_config_debugfs_fops = {
 };
 
 #ifdef CONFIG_CHELSIO_T4_DCB
-extern char *dcb_ver_array[];
 
 /* Data Center Briging information for each port.
  */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
index 37d86af44074..b66a2e6cbbeb 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
@@ -598,7 +598,7 @@ static void fw_caps_to_lmm(enum fw_port_type port_type,
 /**
  *	lmm_to_fw_caps - translate ethtool Link Mode Mask to Firmware
  *	capabilities
- *	@et_lmm: ethtool Link Mode Mask
+ *	@link_mode_mask: ethtool Link Mode Mask
  *
  *	Translate ethtool Link Mode Mask into a Firmware Port capabilities
  *	value.
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
index a12df792d832..482b633f7679 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
@@ -165,6 +165,9 @@ static void set_nat_params(struct adapter *adap, struct filter_entry *f,
 			   unsigned int tid, bool dip, bool sip, bool dp,
 			   bool sp)
 {
+	u8 *nat_lp = (u8 *)&f->fs.nat_lport;
+	u8 *nat_fp = (u8 *)&f->fs.nat_fport;
+
 	if (dip) {
 		if (f->fs.type) {
 			set_tcb_field(adap, f, tid, TCB_SND_UNA_RAW_W,
@@ -236,8 +239,9 @@ static void set_nat_params(struct adapter *adap, struct filter_entry *f,
 	}
 
 	set_tcb_field(adap, f, tid, TCB_PDU_HDR_LEN_W, WORD_MASK,
-		      (dp ? f->fs.nat_lport : 0) |
-		      (sp ? f->fs.nat_fport << 16 : 0), 1);
+		      (dp ? (nat_lp[1] | nat_lp[0] << 8) : 0) |
+		      (sp ? (nat_fp[1] << 16 | nat_fp[0] << 24) : 0),
+		      1);
 }
 
 /* Validate filter spec against configuration done on the card. */
@@ -909,6 +913,9 @@ int set_filter_wr(struct adapter *adapter, int fidx)
 	fwr->fpm = htons(f->fs.mask.fport);
 
 	if (adapter->params.filter2_wr_support) {
+		u8 *nat_lp = (u8 *)&f->fs.nat_lport;
+		u8 *nat_fp = (u8 *)&f->fs.nat_fport;
+
 		fwr->natmode_to_ulp_type =
 			FW_FILTER2_WR_ULP_TYPE_V(f->fs.nat_mode ?
 						 ULP_MODE_TCPDDP :
@@ -916,8 +923,8 @@ int set_filter_wr(struct adapter *adapter, int fidx)
 			FW_FILTER2_WR_NATMODE_V(f->fs.nat_mode);
 		memcpy(fwr->newlip, f->fs.nat_lip, sizeof(fwr->newlip));
 		memcpy(fwr->newfip, f->fs.nat_fip, sizeof(fwr->newfip));
-		fwr->newlport = htons(f->fs.nat_lport);
-		fwr->newfport = htons(f->fs.nat_fport);
+		fwr->newlport = htons(nat_lp[1] | nat_lp[0] << 8);
+		fwr->newfport = htons(nat_fp[1] | nat_fp[0] << 8);
 	}
 
 	/* Mark the filter as "pending" and ship off the Filter Work Request.
@@ -1105,16 +1112,16 @@ static bool is_addr_all_mask(u8 *ipmask, int family)
 		struct in_addr *addr;
 
 		addr = (struct in_addr *)ipmask;
-		if (addr->s_addr == 0xffffffff)
+		if (ntohl(addr->s_addr) == 0xffffffff)
 			return true;
 	} else if (family == AF_INET6) {
 		struct in6_addr *addr6;
 
 		addr6 = (struct in6_addr *)ipmask;
-		if (addr6->s6_addr32[0] == 0xffffffff &&
-		    addr6->s6_addr32[1] == 0xffffffff &&
-		    addr6->s6_addr32[2] == 0xffffffff &&
-		    addr6->s6_addr32[3] == 0xffffffff)
+		if (ntohl(addr6->s6_addr32[0]) == 0xffffffff &&
+		    ntohl(addr6->s6_addr32[1]) == 0xffffffff &&
+		    ntohl(addr6->s6_addr32[2]) == 0xffffffff &&
+		    ntohl(addr6->s6_addr32[3]) == 0xffffffff)
 			return true;
 	}
 	return false;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 87505a0d906a..234f01389cb1 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -449,7 +449,7 @@ static int set_rxmode(struct net_device *dev, int mtu, bool sleep_ok)
  *		   or -1
  *	@addr: the new MAC address value
  *	@persist: whether a new MAC allocation should be persistent
- *	@add_smt: if true also add the address to the HW SMT
+ *	@smt_idx: the destination to store the new SMT index.
  *
  *	Modifies an MPS filter and sets it to the new MAC address if
  *	@tcam_idx >= 0, or adds the MAC address to a new filter if
@@ -1615,6 +1615,7 @@ static int tid_init(struct tid_info *t)
  *	@stid: the server TID
  *	@sip: local IP address to bind server to
  *	@sport: the server's TCP port
+ *	@vlan: the VLAN header information
  *	@queue: queue to direct messages from this server to
  *
  *	Create an IP server for the given port and address.
@@ -2609,7 +2610,7 @@ int cxgb4_create_server_filter(const struct net_device *dev, unsigned int stid,
 
 	/* Clear out filter specifications */
 	memset(&f->fs, 0, sizeof(struct ch_filter_specification));
-	f->fs.val.lport = cpu_to_be16(sport);
+	f->fs.val.lport = be16_to_cpu(sport);
 	f->fs.mask.lport  = ~0;
 	val = (u8 *)&sip;
 	if ((val[0] | val[1] | val[2] | val[3]) != 0) {
@@ -5378,10 +5379,10 @@ static inline bool is_x_10g_port(const struct link_config *lc)
 static int cfg_queues(struct adapter *adap)
 {
 	u32 avail_qsets, avail_eth_qsets, avail_uld_qsets;
-	u32 i, n10g = 0, qidx = 0, n1g = 0;
 	u32 ncpus = num_online_cpus();
 	u32 niqflint, neq, num_ulds;
 	struct sge *s = &adap->sge;
+	u32 i, n10g = 0, qidx = 0;
 	u32 q10g = 0, q1g;
 
 	/* Reduce memory usage in kdump environment, disable all offload. */
@@ -5427,7 +5428,6 @@ static int cfg_queues(struct adapter *adap)
 	if (n10g)
 		q10g = (avail_eth_qsets - (adap->params.nports - n10g)) / n10g;
 
-	n1g = adap->params.nports - n10g;
 #ifdef CONFIG_CHELSIO_T4_DCB
 	/* For Data Center Bridging support we need to be able to support up
 	 * to 8 Traffic Priorities; each of which will be assigned to its
@@ -5445,7 +5445,8 @@ static int cfg_queues(struct adapter *adap)
 	else
 		q10g = max(8U, q10g);
 
-	while ((q10g * n10g) > (avail_eth_qsets - n1g * q1g))
+	while ((q10g * n10g) >
+	       (avail_eth_qsets - (adap->params.nports - n10g) * q1g))
 		q10g--;
 
 #else /* !CONFIG_CHELSIO_T4_DCB */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c
index f5bc996ac77d..70dbee89118e 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c
@@ -194,6 +194,7 @@ int cxgb4_ptp_redirect_rx_packet(struct adapter *adapter, struct port_info *pi)
 }
 
 /**
+ * cxgb4_ptp_adjfreq - Adjust frequency of PHC cycle counter
  * @ptp: ptp clock structure
  * @ppb: Desired frequency change in parts per billion
  *
@@ -229,7 +230,7 @@ static int cxgb4_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb)
 
 /**
  * cxgb4_ptp_fineadjtime - Shift the time of the hardware clock
- * @ptp: ptp clock structure
+ * @adapter: board private structure
  * @delta: Desired change in nanoseconds
  *
  * Adjust the timer by resetting the timecounter structure.
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c
index ccc7aab9a8be..ae0e998d9338 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c
@@ -58,10 +58,6 @@ static struct ch_tc_pedit_fields pedits[] = {
 	PEDIT_FIELDS(IP6_, DST_63_32, 4, nat_lip, 4),
 	PEDIT_FIELDS(IP6_, DST_95_64, 4, nat_lip, 8),
 	PEDIT_FIELDS(IP6_, DST_127_96, 4, nat_lip, 12),
-	PEDIT_FIELDS(TCP_, SPORT, 2, nat_fport, 0),
-	PEDIT_FIELDS(TCP_, DPORT, 2, nat_lport, 0),
-	PEDIT_FIELDS(UDP_, SPORT, 2, nat_fport, 0),
-	PEDIT_FIELDS(UDP_, DPORT, 2, nat_lport, 0),
 };
 
 static struct ch_tc_flower_entry *allocate_flower_entry(void)
@@ -146,14 +142,14 @@ static void cxgb4_process_flow_match(struct net_device *dev,
 		struct flow_match_ports match;
 
 		flow_rule_match_ports(rule, &match);
-		fs->val.lport = cpu_to_be16(match.key->dst);
-		fs->mask.lport = cpu_to_be16(match.mask->dst);
-		fs->val.fport = cpu_to_be16(match.key->src);
-		fs->mask.fport = cpu_to_be16(match.mask->src);
+		fs->val.lport = be16_to_cpu(match.key->dst);
+		fs->mask.lport = be16_to_cpu(match.mask->dst);
+		fs->val.fport = be16_to_cpu(match.key->src);
+		fs->mask.fport = be16_to_cpu(match.mask->src);
 
 		/* also initialize nat_lport/fport to same values */
-		fs->nat_lport = cpu_to_be16(match.key->dst);
-		fs->nat_fport = cpu_to_be16(match.key->src);
+		fs->nat_lport = fs->val.lport;
+		fs->nat_fport = fs->val.fport;
 	}
 
 	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IP)) {
@@ -343,12 +339,9 @@ static void process_pedit_field(struct ch_filter_specification *fs, u32 val,
 		switch (offset) {
 		case PEDIT_TCP_SPORT_DPORT:
 			if (~mask & PEDIT_TCP_UDP_SPORT_MASK)
-				offload_pedit(fs, cpu_to_be32(val) >> 16,
-					      cpu_to_be32(mask) >> 16,
-					      TCP_SPORT);
+				fs->nat_fport = val;
 			else
-				offload_pedit(fs, cpu_to_be32(val),
-					      cpu_to_be32(mask), TCP_DPORT);
+				fs->nat_lport = val >> 16;
 		}
 		fs->nat_mode = NAT_MODE_ALL;
 		break;
@@ -356,12 +349,9 @@ static void process_pedit_field(struct ch_filter_specification *fs, u32 val,
 		switch (offset) {
 		case PEDIT_UDP_SPORT_DPORT:
 			if (~mask & PEDIT_TCP_UDP_SPORT_MASK)
-				offload_pedit(fs, cpu_to_be32(val) >> 16,
-					      cpu_to_be32(mask) >> 16,
-					      UDP_SPORT);
+				fs->nat_fport = val;
 			else
-				offload_pedit(fs, cpu_to_be32(val),
-					      cpu_to_be32(mask), UDP_DPORT);
+				fs->nat_lport = val >> 16;
 		}
 		fs->nat_mode = NAT_MODE_ALL;
 	}
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32.c
index 3f3c11e54d97..dede02505ceb 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32.c
@@ -48,7 +48,7 @@ static int fill_match_fields(struct adapter *adap,
 			     bool next_header)
 {
 	unsigned int i, j;
-	u32 val, mask;
+	__be32 val, mask;
 	int off, err;
 	bool found;
 
@@ -228,7 +228,7 @@ int cxgb4_config_knode(struct net_device *dev, struct tc_cls_u32_offload *cls)
 		const struct cxgb4_next_header *next;
 		bool found = false;
 		unsigned int i, j;
-		u32 val, mask;
+		__be32 val, mask;
 		int off;
 
 		if (t->table[link_uhtid - 1].link_handle) {
@@ -242,10 +242,10 @@ int cxgb4_config_knode(struct net_device *dev, struct tc_cls_u32_offload *cls)
 
 		/* Try to find matches that allow jumps to next header. */
 		for (i = 0; next[i].jump; i++) {
-			if (next[i].offoff != cls->knode.sel->offoff ||
-			    next[i].shift != cls->knode.sel->offshift ||
-			    next[i].mask != cls->knode.sel->offmask ||
-			    next[i].offset != cls->knode.sel->off)
+			if (next[i].sel.offoff != cls->knode.sel->offoff ||
+			    next[i].sel.offshift != cls->knode.sel->offshift ||
+			    next[i].sel.offmask != cls->knode.sel->offmask ||
+			    next[i].sel.off != cls->knode.sel->off)
 				continue;
 
 			/* Found a possible candidate.  Find a key that
@@ -257,9 +257,9 @@ int cxgb4_config_knode(struct net_device *dev, struct tc_cls_u32_offload *cls)
 				val = cls->knode.sel->keys[j].val;
 				mask = cls->knode.sel->keys[j].mask;
 
-				if (next[i].match_off == off &&
-				    next[i].match_val == val &&
-				    next[i].match_mask == mask) {
+				if (next[i].key.off == off &&
+				    next[i].key.val == val &&
+				    next[i].key.mask == mask) {
 					found = true;
 					break;
 				}
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32_parse.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32_parse.h
index 125868c6770a..f59dd4b2ae6f 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32_parse.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32_parse.h
@@ -38,12 +38,12 @@
 struct cxgb4_match_field {
 	int off; /* Offset from the beginning of the header to match */
 	/* Fill the value/mask pair in the spec if matched */
-	int (*val)(struct ch_filter_specification *f, u32 val, u32 mask);
+	int (*val)(struct ch_filter_specification *f, __be32 val, __be32 mask);
 };
 
 /* IPv4 match fields */
 static inline int cxgb4_fill_ipv4_tos(struct ch_filter_specification *f,
-				      u32 val, u32 mask)
+				      __be32 val, __be32 mask)
 {
 	f->val.tos  = (ntohl(val)  >> 16) & 0x000000FF;
 	f->mask.tos = (ntohl(mask) >> 16) & 0x000000FF;
@@ -52,7 +52,7 @@ static inline int cxgb4_fill_ipv4_tos(struct ch_filter_specification *f,
 }
 
 static inline int cxgb4_fill_ipv4_frag(struct ch_filter_specification *f,
-				       u32 val, u32 mask)
+				       __be32 val, __be32 mask)
 {
 	u32 mask_val;
 	u8 frag_val;
@@ -74,7 +74,7 @@ static inline int cxgb4_fill_ipv4_frag(struct ch_filter_specification *f,
 }
 
 static inline int cxgb4_fill_ipv4_proto(struct ch_filter_specification *f,
-					u32 val, u32 mask)
+					__be32 val, __be32 mask)
 {
 	f->val.proto  = (ntohl(val)  >> 16) & 0x000000FF;
 	f->mask.proto = (ntohl(mask) >> 16) & 0x000000FF;
@@ -83,7 +83,7 @@ static inline int cxgb4_fill_ipv4_proto(struct ch_filter_specification *f,
 }
 
 static inline int cxgb4_fill_ipv4_src_ip(struct ch_filter_specification *f,
-					 u32 val, u32 mask)
+					 __be32 val, __be32 mask)
 {
 	memcpy(&f->val.fip[0],  &val,  sizeof(u32));
 	memcpy(&f->mask.fip[0], &mask, sizeof(u32));
@@ -92,7 +92,7 @@ static inline int cxgb4_fill_ipv4_src_ip(struct ch_filter_specification *f,
 }
 
 static inline int cxgb4_fill_ipv4_dst_ip(struct ch_filter_specification *f,
-					 u32 val, u32 mask)
+					 __be32 val, __be32 mask)
 {
 	memcpy(&f->val.lip[0],  &val,  sizeof(u32));
 	memcpy(&f->mask.lip[0], &mask, sizeof(u32));
@@ -111,7 +111,7 @@ static const struct cxgb4_match_field cxgb4_ipv4_fields[] = {
 
 /* IPv6 match fields */
 static inline int cxgb4_fill_ipv6_tos(struct ch_filter_specification *f,
-				      u32 val, u32 mask)
+				      __be32 val, __be32 mask)
 {
 	f->val.tos  = (ntohl(val)  >> 20) & 0x000000FF;
 	f->mask.tos = (ntohl(mask) >> 20) & 0x000000FF;
@@ -120,7 +120,7 @@ static inline int cxgb4_fill_ipv6_tos(struct ch_filter_specification *f,
 }
 
 static inline int cxgb4_fill_ipv6_proto(struct ch_filter_specification *f,
-					u32 val, u32 mask)
+					__be32 val, __be32 mask)
 {
 	f->val.proto  = (ntohl(val)  >> 8) & 0x000000FF;
 	f->mask.proto = (ntohl(mask) >> 8) & 0x000000FF;
@@ -129,7 +129,7 @@ static inline int cxgb4_fill_ipv6_proto(struct ch_filter_specification *f,
 }
 
 static inline int cxgb4_fill_ipv6_src_ip0(struct ch_filter_specification *f,
-					  u32 val, u32 mask)
+					  __be32 val, __be32 mask)
 {
 	memcpy(&f->val.fip[0],  &val,  sizeof(u32));
 	memcpy(&f->mask.fip[0], &mask, sizeof(u32));
@@ -138,7 +138,7 @@ static inline int cxgb4_fill_ipv6_src_ip0(struct ch_filter_specification *f,
 }
 
 static inline int cxgb4_fill_ipv6_src_ip1(struct ch_filter_specification *f,
-					  u32 val, u32 mask)
+					  __be32 val, __be32 mask)
 {
 	memcpy(&f->val.fip[4],  &val,  sizeof(u32));
 	memcpy(&f->mask.fip[4], &mask, sizeof(u32));
@@ -147,7 +147,7 @@ static inline int cxgb4_fill_ipv6_src_ip1(struct ch_filter_specification *f,
 }
 
 static inline int cxgb4_fill_ipv6_src_ip2(struct ch_filter_specification *f,
-					  u32 val, u32 mask)
+					  __be32 val, __be32 mask)
 {
 	memcpy(&f->val.fip[8],  &val,  sizeof(u32));
 	memcpy(&f->mask.fip[8], &mask, sizeof(u32));
@@ -156,7 +156,7 @@ static inline int cxgb4_fill_ipv6_src_ip2(struct ch_filter_specification *f,
 }
 
 static inline int cxgb4_fill_ipv6_src_ip3(struct ch_filter_specification *f,
-					  u32 val, u32 mask)
+					  __be32 val, __be32 mask)
 {
 	memcpy(&f->val.fip[12],  &val,  sizeof(u32));
 	memcpy(&f->mask.fip[12], &mask, sizeof(u32));
@@ -165,7 +165,7 @@ static inline int cxgb4_fill_ipv6_src_ip3(struct ch_filter_specification *f,
 }
 
 static inline int cxgb4_fill_ipv6_dst_ip0(struct ch_filter_specification *f,
-					  u32 val, u32 mask)
+					  __be32 val, __be32 mask)
 {
 	memcpy(&f->val.lip[0],  &val,  sizeof(u32));
 	memcpy(&f->mask.lip[0], &mask, sizeof(u32));
@@ -174,7 +174,7 @@ static inline int cxgb4_fill_ipv6_dst_ip0(struct ch_filter_specification *f,
 }
 
 static inline int cxgb4_fill_ipv6_dst_ip1(struct ch_filter_specification *f,
-					  u32 val, u32 mask)
+					  __be32 val, __be32 mask)
 {
 	memcpy(&f->val.lip[4],  &val,  sizeof(u32));
 	memcpy(&f->mask.lip[4], &mask, sizeof(u32));
@@ -183,7 +183,7 @@ static inline int cxgb4_fill_ipv6_dst_ip1(struct ch_filter_specification *f,
 }
 
 static inline int cxgb4_fill_ipv6_dst_ip2(struct ch_filter_specification *f,
-					  u32 val, u32 mask)
+					  __be32 val, __be32 mask)
 {
 	memcpy(&f->val.lip[8],  &val,  sizeof(u32));
 	memcpy(&f->mask.lip[8], &mask, sizeof(u32));
@@ -192,7 +192,7 @@ static inline int cxgb4_fill_ipv6_dst_ip2(struct ch_filter_specification *f,
 }
 
 static inline int cxgb4_fill_ipv6_dst_ip3(struct ch_filter_specification *f,
-					  u32 val, u32 mask)
+					  __be32 val, __be32 mask)
 {
 	memcpy(&f->val.lip[12],  &val,  sizeof(u32));
 	memcpy(&f->mask.lip[12], &mask, sizeof(u32));
@@ -216,7 +216,7 @@ static const struct cxgb4_match_field cxgb4_ipv6_fields[] = {
 
 /* TCP/UDP match */
 static inline int cxgb4_fill_l4_ports(struct ch_filter_specification *f,
-				      u32 val, u32 mask)
+				      __be32 val, __be32 mask)
 {
 	f->val.fport  = ntohl(val)  >> 16;
 	f->mask.fport = ntohl(mask) >> 16;
@@ -237,19 +237,13 @@ static const struct cxgb4_match_field cxgb4_udp_fields[] = {
 };
 
 struct cxgb4_next_header {
-	unsigned int offset; /* Offset to next header */
-	/* offset, shift, and mask added to offset above
+	/* Offset, shift, and mask added to beginning of the header
 	 * to get to next header.  Useful when using a header
 	 * field's value to jump to next header such as IHL field
 	 * in IPv4 header.
 	 */
-	unsigned int offoff;
-	u32 shift;
-	u32 mask;
-	/* match criteria to make this jump */
-	unsigned int match_off;
-	u32 match_val;
-	u32 match_mask;
+	struct tc_u32_sel sel;
+	struct tc_u32_key key;
 	/* location of jump to make */
 	const struct cxgb4_match_field *jump;
 };
@@ -258,26 +252,74 @@ struct cxgb4_next_header {
  * IPv4 header.
  */
 static const struct cxgb4_next_header cxgb4_ipv4_jumps[] = {
-	{ .offset = 0, .offoff = 0, .shift = 6, .mask = 0xF,
-	  .match_off = 8, .match_val = 0x600, .match_mask = 0xFF00,
-	  .jump = cxgb4_tcp_fields },
-	{ .offset = 0, .offoff = 0, .shift = 6, .mask = 0xF,
-	  .match_off = 8, .match_val = 0x1100, .match_mask = 0xFF00,
-	  .jump = cxgb4_udp_fields },
-	{ .jump = NULL }
+	{
+		/* TCP Jump */
+		.sel = {
+			.off = 0,
+			.offoff = 0,
+			.offshift = 6,
+			.offmask = cpu_to_be16(0x0f00),
+		},
+		.key = {
+			.off = 8,
+			.val = cpu_to_be32(0x00060000),
+			.mask = cpu_to_be32(0x00ff0000),
+		},
+		.jump = cxgb4_tcp_fields,
+	},
+	{
+		/* UDP Jump */
+		.sel = {
+			.off = 0,
+			.offoff = 0,
+			.offshift = 6,
+			.offmask = cpu_to_be16(0x0f00),
+		},
+		.key = {
+			.off = 8,
+			.val = cpu_to_be32(0x00110000),
+			.mask = cpu_to_be32(0x00ff0000),
+		},
+		.jump = cxgb4_udp_fields,
+	},
+	{ .jump = NULL },
 };
 
 /* Accept a rule with a jump directly past the 40 Bytes of IPv6 fixed header
  * to get to transport layer header.
  */
 static const struct cxgb4_next_header cxgb4_ipv6_jumps[] = {
-	{ .offset = 0x28, .offoff = 0, .shift = 0, .mask = 0,
-	  .match_off = 4, .match_val = 0x60000, .match_mask = 0xFF0000,
-	  .jump = cxgb4_tcp_fields },
-	{ .offset = 0x28, .offoff = 0, .shift = 0, .mask = 0,
-	  .match_off = 4, .match_val = 0x110000, .match_mask = 0xFF0000,
-	  .jump = cxgb4_udp_fields },
-	{ .jump = NULL }
+	{
+		/* TCP Jump */
+		.sel = {
+			.off = 40,
+			.offoff = 0,
+			.offshift = 0,
+			.offmask = 0,
+		},
+		.key = {
+			.off = 4,
+			.val = cpu_to_be32(0x00000600),
+			.mask = cpu_to_be32(0x0000ff00),
+		},
+		.jump = cxgb4_tcp_fields,
+	},
+	{
+		/* UDP Jump */
+		.sel = {
+			.off = 40,
+			.offoff = 0,
+			.offshift = 0,
+			.offmask = 0,
+		},
+		.key = {
+			.off = 4,
+			.val = cpu_to_be32(0x00001100),
+			.mask = cpu_to_be32(0x0000ff00),
+		},
+		.jump = cxgb4_udp_fields,
+	},
+	{ .jump = NULL },
 };
 
 struct cxgb4_link {
diff --git a/drivers/net/ethernet/chelsio/cxgb4/l2t.c b/drivers/net/ethernet/chelsio/cxgb4/l2t.c
index 72b37a66c7d8..c4864125fe02 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/l2t.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/l2t.c
@@ -503,40 +503,19 @@ u64 cxgb4_select_ntuple(struct net_device *dev,
 EXPORT_SYMBOL(cxgb4_select_ntuple);
 
 /*
- * Called when address resolution fails for an L2T entry to handle packets
- * on the arpq head.  If a packet specifies a failure handler it is invoked,
- * otherwise the packet is sent to the device.
- */
-static void handle_failed_resolution(struct adapter *adap, struct l2t_entry *e)
-{
-	struct sk_buff *skb;
-
-	while ((skb = __skb_dequeue(&e->arpq)) != NULL) {
-		const struct l2t_skb_cb *cb = L2T_SKB_CB(skb);
-
-		spin_unlock(&e->lock);
-		if (cb->arp_err_handler)
-			cb->arp_err_handler(cb->handle, skb);
-		else
-			t4_ofld_send(adap, skb);
-		spin_lock(&e->lock);
-	}
-}
-
-/*
  * Called when the host's neighbor layer makes a change to some entry that is
  * loaded into the HW L2 table.
  */
 void t4_l2t_update(struct adapter *adap, struct neighbour *neigh)
 {
-	struct l2t_entry *e;
-	struct sk_buff_head *arpq = NULL;
-	struct l2t_data *d = adap->l2t;
 	unsigned int addr_len = neigh->tbl->key_len;
 	u32 *addr = (u32 *) neigh->primary_key;
-	int ifidx = neigh->dev->ifindex;
-	int hash = addr_hash(d, addr, addr_len, ifidx);
+	int hash, ifidx = neigh->dev->ifindex;
+	struct sk_buff_head *arpq = NULL;
+	struct l2t_data *d = adap->l2t;
+	struct l2t_entry *e;
 
+	hash = addr_hash(d, addr, addr_len, ifidx);
 	read_lock_bh(&d->lock);
 	for (e = d->l2tab[hash].first; e; e = e->next)
 		if (!addreq(e, addr) && e->ifindex == ifidx) {
@@ -569,8 +548,25 @@ void t4_l2t_update(struct adapter *adap, struct neighbour *neigh)
 			write_l2e(adap, e, 0);
 	}
 
-	if (arpq)
-		handle_failed_resolution(adap, e);
+	if (arpq) {
+		struct sk_buff *skb;
+
+		/* Called when address resolution fails for an L2T
+		 * entry to handle packets on the arpq head. If a
+		 * packet specifies a failure handler it is invoked,
+		 * otherwise the packet is sent to the device.
+		 */
+		while ((skb = __skb_dequeue(&e->arpq)) != NULL) {
+			const struct l2t_skb_cb *cb = L2T_SKB_CB(skb);
+
+			spin_unlock(&e->lock);
+			if (cb->arp_err_handler)
+				cb->arp_err_handler(cb->handle, skb);
+			else
+				t4_ofld_send(adap, skb);
+			spin_lock(&e->lock);
+		}
+	}
 	spin_unlock_bh(&e->lock);
 }
 
@@ -613,6 +609,7 @@ struct l2t_entry *t4_l2t_alloc_switching(struct adapter *adap, u16 vlan,
 }
 
 /**
+ * cxgb4_l2t_alloc_switching - Allocates an L2T entry for switch filters
  * @dev: net_device pointer
  * @vlan: VLAN Id
  * @port: Associated port
diff --git a/drivers/net/ethernet/chelsio/cxgb4/sched.c b/drivers/net/ethernet/chelsio/cxgb4/sched.c
index fde93c50cfec..a1b14468d1ff 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sched.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sched.c
@@ -598,7 +598,7 @@ struct sched_class *cxgb4_sched_class_alloc(struct net_device *dev,
 /**
  * cxgb4_sched_class_free - free a scheduling class
  * @dev: net_device pointer
- * @e: scheduling class
+ * @classid: scheduling class id to free
  *
  * Frees a scheduling class if there are no users.
  */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c
index b3da3d05aa2d..f9c6f13d7c99 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c
@@ -302,7 +302,7 @@ static void deferred_unmap_destructor(struct sk_buff *skb)
 
 /**
  *	free_tx_desc - reclaims Tx descriptors and their buffers
- *	@adapter: the adapter
+ *	@adap: the adapter
  *	@q: the Tx queue to reclaim descriptors from
  *	@n: the number of descriptors to reclaim
  *	@unmap: whether the buffers should be unmapped for DMA
@@ -722,6 +722,7 @@ static inline unsigned int flits_to_desc(unsigned int n)
 /**
  *	is_eth_imm - can an Ethernet packet be sent as immediate data?
  *	@skb: the packet
+ *	@chip_ver: chip version
  *
  *	Returns whether an Ethernet packet is small enough to fit as
  *	immediate data. Return value corresponds to headroom required.
@@ -749,6 +750,7 @@ static inline int is_eth_imm(const struct sk_buff *skb, unsigned int chip_ver)
 /**
  *	calc_tx_flits - calculate the number of flits for a packet Tx WR
  *	@skb: the packet
+ *	@chip_ver: chip version
  *
  *	Returns the number of flits needed for a Tx WR for the given Ethernet
  *	packet, including the needed WR and CPL headers.
@@ -804,6 +806,7 @@ static inline unsigned int calc_tx_flits(const struct sk_buff *skb,
 /**
  *	calc_tx_descs - calculate the number of Tx descriptors for a packet
  *	@skb: the packet
+ *	@chip_ver: chip version
  *
  *	Returns the number of Tx descriptors needed for the given Ethernet
  *	packet, including the needed WR and CPL headers.
@@ -1425,12 +1428,10 @@ static netdev_tx_t cxgb4_eth_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	qidx = skb_get_queue_mapping(skb);
 	if (ptp_enabled) {
-		spin_lock(&adap->ptp_lock);
 		if (!(adap->ptp_tx_skb)) {
 			skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
 			adap->ptp_tx_skb = skb_get(skb);
 		} else {
-			spin_unlock(&adap->ptp_lock);
 			goto out_free;
 		}
 		q = &adap->sge.ptptxq;
@@ -1444,11 +1445,8 @@ static netdev_tx_t cxgb4_eth_xmit(struct sk_buff *skb, struct net_device *dev)
 
 #ifdef CONFIG_CHELSIO_T4_FCOE
 	ret = cxgb_fcoe_offload(skb, adap, pi, &cntrl);
-	if (unlikely(ret == -ENOTSUPP)) {
-		if (ptp_enabled)
-			spin_unlock(&adap->ptp_lock);
+	if (unlikely(ret == -EOPNOTSUPP))
 		goto out_free;
-	}
 #endif /* CONFIG_CHELSIO_T4_FCOE */
 
 	chip_ver = CHELSIO_CHIP_VERSION(adap->params.chip);
@@ -1461,8 +1459,6 @@ static netdev_tx_t cxgb4_eth_xmit(struct sk_buff *skb, struct net_device *dev)
 		dev_err(adap->pdev_dev,
 			"%s: Tx ring %u full while queue awake!\n",
 			dev->name, qidx);
-		if (ptp_enabled)
-			spin_unlock(&adap->ptp_lock);
 		return NETDEV_TX_BUSY;
 	}
 
@@ -1481,8 +1477,6 @@ static netdev_tx_t cxgb4_eth_xmit(struct sk_buff *skb, struct net_device *dev)
 	    unlikely(cxgb4_map_skb(adap->pdev_dev, skb, sgl_sdesc->addr) < 0)) {
 		memset(sgl_sdesc->addr, 0, sizeof(sgl_sdesc->addr));
 		q->mapping_err++;
-		if (ptp_enabled)
-			spin_unlock(&adap->ptp_lock);
 		goto out_free;
 	}
 
@@ -1533,8 +1527,7 @@ static netdev_tx_t cxgb4_eth_xmit(struct sk_buff *skb, struct net_device *dev)
 			if (iph->version == 4) {
 				iph->check = 0;
 				iph->tot_len = 0;
-				iph->check = (u16)(~ip_fast_csum((u8 *)iph,
-								 iph->ihl));
+				iph->check = ~ip_fast_csum((u8 *)iph, iph->ihl);
 			}
 			if (skb->ip_summed == CHECKSUM_PARTIAL)
 				cntrl = hwcsum(adap->params.chip, skb);
@@ -1630,8 +1623,6 @@ static netdev_tx_t cxgb4_eth_xmit(struct sk_buff *skb, struct net_device *dev)
 	txq_advance(&q->q, ndesc);
 
 	cxgb4_ring_tx_db(adap, &q->q, ndesc);
-	if (ptp_enabled)
-		spin_unlock(&adap->ptp_lock);
 	return NETDEV_TX_OK;
 
 out_free:
@@ -2377,6 +2368,16 @@ netdev_tx_t t4_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (unlikely(qid >= pi->nqsets))
 		return cxgb4_ethofld_xmit(skb, dev);
 
+	if (is_ptp_enabled(skb, dev)) {
+		struct adapter *adap = netdev2adap(dev);
+		netdev_tx_t ret;
+
+		spin_lock(&adap->ptp_lock);
+		ret = cxgb4_eth_xmit(skb, dev);
+		spin_unlock(&adap->ptp_lock);
+		return ret;
+	}
+
 	return cxgb4_eth_xmit(skb, dev);
 }
 
@@ -2410,9 +2411,9 @@ static void eosw_txq_flush_pending_skbs(struct sge_eosw_txq *eosw_txq)
 
 /**
  * cxgb4_ethofld_send_flowc - Send ETHOFLD flowc request to bind eotid to tc.
- * @dev - netdevice
- * @eotid - ETHOFLD tid to bind/unbind
- * @tc - traffic class. If set to FW_SCHED_CLS_NONE, then unbinds the @eotid
+ * @dev: netdevice
+ * @eotid: ETHOFLD tid to bind/unbind
+ * @tc: traffic class. If set to FW_SCHED_CLS_NONE, then unbinds the @eotid
  *
  * Send a FLOWC work request to bind an ETHOFLD TID to a traffic class.
  * If @tc is set to FW_SCHED_CLS_NONE, then the @eotid is unbound from
@@ -2691,7 +2692,6 @@ static inline unsigned int calc_tx_flits_ofld(const struct sk_buff *skb)
 
 /**
  *	txq_stop_maperr - stop a Tx queue due to I/O MMU exhaustion
- *	@adap: the adapter
  *	@q: the queue to stop
  *
  *	Mark a Tx queue stopped due to I/O MMU exhaustion and resulting
@@ -3286,7 +3286,7 @@ enum {
 
 /**
  *     t4_systim_to_hwstamp - read hardware time stamp
- *     @adap: the adapter
+ *     @adapter: the adapter
  *     @skb: the packet
  *
  *     Read Time Stamp from MPS packet and insert in skb which
@@ -3313,15 +3313,16 @@ static noinline int t4_systim_to_hwstamp(struct adapter *adapter,
 
 	hwtstamps = skb_hwtstamps(skb);
 	memset(hwtstamps, 0, sizeof(*hwtstamps));
-	hwtstamps->hwtstamp = ns_to_ktime(be64_to_cpu(*((u64 *)data)));
+	hwtstamps->hwtstamp = ns_to_ktime(get_unaligned_be64(data));
 
 	return RX_PTP_PKT_SUC;
 }
 
 /**
  *     t4_rx_hststamp - Recv PTP Event Message
- *     @adap: the adapter
+ *     @adapter: the adapter
  *     @rsp: the response queue descriptor holding the RX_PKT message
+ *     @rxq: the response queue holding the RX_PKT message
  *     @skb: the packet
  *
  *     PTP enabled and MPS packet, read HW timestamp
@@ -3345,7 +3346,7 @@ static int t4_rx_hststamp(struct adapter *adapter, const __be64 *rsp,
 
 /**
  *      t4_tx_hststamp - Loopback PTP Transmit Event Message
- *      @adap: the adapter
+ *      @adapter: the adapter
  *      @skb: the packet
  *      @dev: the ingress net device
  *
diff --git a/drivers/net/ethernet/chelsio/cxgb4/smt.c b/drivers/net/ethernet/chelsio/cxgb4/smt.c
index 01c65d13fc0e..cbe72ed27b1e 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/smt.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/smt.c
@@ -103,6 +103,7 @@ static void t4_smte_free(struct smt_entry *e)
 }
 
 /**
+ * cxgb4_smt_release - Release SMT entry
  * @e: smt entry to release
  *
  * Releases ref count and frees up an smt entry from SMT table
@@ -231,6 +232,7 @@ static struct smt_entry *t4_smt_alloc_switching(struct adapter *adap, u16 pfvf,
 }
 
 /**
+ * cxgb4_smt_alloc_switching - Allocates an SMT entry for switch filters.
  * @dev: net_device pointer
  * @smac: MAC address to add to SMT
  * Returns pointer to the SMT entry created
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
index 8f2b7c9aa384..70fe189202be 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
@@ -3163,7 +3163,7 @@ int t4_get_tp_version(struct adapter *adapter, u32 *vers)
 
 /**
  *	t4_get_exprom_version - return the Expansion ROM version (if any)
- *	@adapter: the adapter
+ *	@adap: the adapter
  *	@vers: where to place the version
  *
  *	Reads the Expansion ROM header from FLASH and returns the version
@@ -5302,7 +5302,7 @@ static unsigned int t4_use_ldst(struct adapter *adap)
  * @cmd: TP fw ldst address space type
  * @vals: where the indirect register values are stored/written
  * @nregs: how many indirect registers to read/write
- * @start_idx: index of first indirect register to read/write
+ * @start_index: index of first indirect register to read/write
  * @rw: Read (1) or Write (0)
  * @sleep_ok: if true we may sleep while awaiting command completion
  *
@@ -6107,7 +6107,7 @@ void t4_pmrx_get_stats(struct adapter *adap, u32 cnt[], u64 cycles[])
 
 /**
  *	compute_mps_bg_map - compute the MPS Buffer Group Map for a Port
- *	@adap: the adapter
+ *	@adapter: the adapter
  *	@pidx: the port index
  *
  *	Computes and returns a bitmap indicating which MPS buffer groups are
@@ -6244,7 +6244,7 @@ static unsigned int t4_get_tp_e2c_map(struct adapter *adapter, int pidx)
 
 /**
  *	t4_get_tp_ch_map - return TP ingress channels associated with a port
- *	@adapter: the adapter
+ *	@adap: the adapter
  *	@pidx: the port index
  *
  *	Returns a bitmap indicating which TP Ingress Channels are associated
@@ -6581,7 +6581,7 @@ int t4_mdio_rd(struct adapter *adap, unsigned int mbox, unsigned int phy_addr,
  *	@phy_addr: the PHY address
  *	@mmd: the PHY MMD to access (0 for clause 22 PHYs)
  *	@reg: the register to write
- *	@valp: value to write
+ *	@val: value to write
  *
  *	Issues a FW command through the given mailbox to write a PHY register.
  */
@@ -6607,7 +6607,7 @@ int t4_mdio_wr(struct adapter *adap, unsigned int mbox, unsigned int phy_addr,
 
 /**
  *	t4_sge_decode_idma_state - decode the idma state
- *	@adap: the adapter
+ *	@adapter: the adapter
  *	@state: the state idma is stuck in
  */
 void t4_sge_decode_idma_state(struct adapter *adapter, int state)
@@ -6774,7 +6774,7 @@ void t4_sge_decode_idma_state(struct adapter *adapter, int state)
  *      t4_sge_ctxt_flush - flush the SGE context cache
  *      @adap: the adapter
  *      @mbox: mailbox to use for the FW command
- *      @ctx_type: Egress or Ingress
+ *      @ctxt_type: Egress or Ingress
  *
  *      Issues a FW command through the given mailbox to flush the
  *      SGE context cache.
@@ -6801,7 +6801,7 @@ int t4_sge_ctxt_flush(struct adapter *adap, unsigned int mbox, int ctxt_type)
 
 /**
  *	t4_read_sge_dbqtimers - read SGE Doorbell Queue Timer values
- *	@adap - the adapter
+ *	@adap: the adapter
  *	@ndbqtimers: size of the provided SGE Doorbell Queue Timer table
  *	@dbqtimers: SGE Doorbell Queue Timer table
  *
@@ -7084,6 +7084,7 @@ static int t4_fw_halt(struct adapter *adap, unsigned int mbox, int force)
 /**
  *	t4_fw_restart - restart the firmware by taking the uP out of RESET
  *	@adap: the adapter
+ *	@mbox: mailbox to use for the FW command
  *	@reset: if we want to do a RESET to restart things
  *
  *	Restart firmware previously halted by t4_fw_halt().  On successful
@@ -7622,6 +7623,8 @@ int t4_cfg_pfvf(struct adapter *adap, unsigned int mbox, unsigned int pf,
  *	@nmac: number of MAC addresses needed (1 to 5)
  *	@mac: the MAC addresses of the VI
  *	@rss_size: size of RSS table slice associated with this VI
+ *	@vivld: the destination to store the VI Valid value.
+ *	@vin: the destination to store the VIN value.
  *
  *	Allocates a virtual interface for the given physical port.  If @mac is
  *	not %NULL it contains the MAC addresses of the VI as assigned by FW.
@@ -7840,7 +7843,7 @@ int t4_free_raw_mac_filt(struct adapter *adap, unsigned int viid,
  *      t4_alloc_encap_mac_filt - Adds a mac entry in mps tcam with VNI support
  *      @adap: the adapter
  *      @viid: the VI id
- *      @mac: the MAC address
+ *      @addr: the MAC address
  *      @mask: the mask
  *      @vni: the VNI id for the tunnel protocol
  *      @vni_mask: mask for the VNI id
@@ -7889,11 +7892,11 @@ int t4_alloc_encap_mac_filt(struct adapter *adap, unsigned int viid,
  *	t4_alloc_raw_mac_filt - Adds a mac entry in mps tcam
  *	@adap: the adapter
  *	@viid: the VI id
- *	@mac: the MAC address
+ *	@addr: the MAC address
  *	@mask: the mask
  *	@idx: index at which to add this entry
- *	@port_id: the port index
  *	@lookup_type: MAC address for inner (1) or outer (0) header
+ *	@port_id: the port index
  *	@sleep_ok: call is allowed to sleep
  *
  *	Adds the mac entry at the specified index using raw mac interface.
@@ -8118,7 +8121,7 @@ int t4_free_mac_filt(struct adapter *adap, unsigned int mbox,
  *	@idx: index of existing filter for old value of MAC address, or -1
  *	@addr: the new MAC address value
  *	@persist: whether a new MAC allocation should be persistent
- *	@add_smt: if true also add the address to the HW SMT
+ *	@smt_idx: the destination to store the new SMT index.
  *
  *	Modifies an exact-match filter and sets it to the new MAC address.
  *	Note that in general it is not possible to modify the value of a given
@@ -8440,7 +8443,6 @@ int t4_ofld_eq_free(struct adapter *adap, unsigned int mbox, unsigned int pf,
 
 /**
  *	t4_link_down_rc_str - return a string for a Link Down Reason Code
- *	@adap: the adapter
  *	@link_down_rc: Link Down Reason Code
  *
  *	Returns a string representation of the Link Down Reason Code.
@@ -8464,9 +8466,7 @@ static const char *t4_link_down_rc_str(unsigned char link_down_rc)
 	return reason[link_down_rc];
 }
 
-/**
- * Return the highest speed set in the port capabilities, in Mb/s.
- */
+/* Return the highest speed set in the port capabilities, in Mb/s. */
 static unsigned int fwcap_to_speed(fw_port_cap32_t caps)
 {
 	#define TEST_SPEED_RETURN(__caps_speed, __speed) \
@@ -9102,7 +9102,6 @@ found:
 /**
  *	t4_prep_adapter - prepare SW and HW for operation
  *	@adapter: the adapter
- *	@reset: if true perform a HW reset
  *
  *	Initialize adapter SW state for the various HW modules, set initial
  *	values for some adapter tunables, take PHYs out of reset, and
@@ -10387,6 +10386,7 @@ int t4_sched_params(struct adapter *adapter, u8 type, u8 level, u8 mode,
 /**
  *	t4_i2c_rd - read I2C data from adapter
  *	@adap: the adapter
+ *	@mbox: mailbox to use for the FW command
  *	@port: Port number if per-port device; <0 if not
  *	@devid: per-port device ID or absolute device ID
  *	@offset: byte offset into device I2C space
@@ -10442,7 +10442,7 @@ int t4_i2c_rd(struct adapter *adap, unsigned int mbox, int port,
 
 /**
  *      t4_set_vlan_acl - Set a VLAN id for the specified VF
- *      @adapter: the adapter
+ *      @adap: the adapter
  *      @mbox: mailbox to use for the FW command
  *      @vf: one of the VFs instantiated by the specified PF
  *      @vlan: The vlanid to be set
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
index cec865a97464..a7641be9094f 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
@@ -260,8 +260,7 @@ static int cxgb4vf_set_addr_hash(struct port_info *pi)
  *	@tcam_idx: TCAM index of existing filter for old value of MAC address,
  *		   or -1
  *	@addr: the new MAC address value
- *	@persist: whether a new MAC allocation should be persistent
- *	@add_smt: if true also add the address to the HW SMT
+ *	@persistent: whether a new MAC allocation should be persistent
  *
  *	Modifies an MPS filter and sets it to the new MAC address if
  *	@tcam_idx >= 0, or adds the MAC address to a new filter if
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c
index f71c973398ec..8c3d6e11a4bf 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c
@@ -1692,7 +1692,7 @@ static inline bool is_new_response(const struct rsp_ctrl *rc,
  *	restore_rx_bufs - put back a packet's RX buffers
  *	@gl: the packet gather list
  *	@fl: the SGE Free List
- *	@nfrags: how many fragments in @si
+ *	@frags: how many fragments in @si
  *
  *	Called when we find out that the current packet, @si, can't be
  *	processed right away for some reason.  This is a very rare event and
@@ -2054,7 +2054,7 @@ irq_handler_t t4vf_intr_handler(struct adapter *adapter)
 
 /**
  *	sge_rx_timer_cb - perform periodic maintenance of SGE RX queues
- *	@data: the adapter
+ *	@t: Rx timer
  *
  *	Runs periodically from a timer to perform maintenance of SGE RX queues.
  *
@@ -2113,7 +2113,7 @@ static void sge_rx_timer_cb(struct timer_list *t)
 
 /**
  *	sge_tx_timer_cb - perform periodic maintenance of SGE Tx queues
- *	@data: the adapter
+ *	@t: Tx timer
  *
  *	Runs periodically from a timer to perform maintenance of SGE TX queues.
  *
@@ -2405,6 +2405,7 @@ err:
  *	t4vf_sge_alloc_eth_txq - allocate an SGE Ethernet TX Queue
  *	@adapter: the adapter
  *	@txq: pointer to the new txq to be filled in
+ *	@dev: the network device
  *	@devq: the network TX queue associated with the new txq
  *	@iqid: the relative ingress queue ID to which events relating to
  *		the new txq should be directed
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c
index 9d49ff211cc1..a31b87390b50 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c
@@ -389,9 +389,7 @@ static inline enum cc_fec fwcap_to_cc_fec(fw_port_cap32_t fw_fec)
 	return cc_fec;
 }
 
-/**
- * Return the highest speed set in the port capabilities, in Mb/s.
- */
+/* Return the highest speed set in the port capabilities, in Mb/s. */
 static unsigned int fwcap_to_speed(fw_port_cap32_t caps)
 {
 	#define TEST_SPEED_RETURN(__caps_speed, __speed) \
@@ -1467,6 +1465,7 @@ int t4vf_identify_port(struct adapter *adapter, unsigned int viid,
  *	@bcast: 1 to enable broadcast Rx, 0 to disable it, -1 no change
  *	@vlanex: 1 to enable hardware VLAN Tag extraction, 0 to disable it,
  *		-1 no change
+ *	@sleep_ok: call is allowed to sleep
  *
  *	Sets Rx properties of a virtual interface.
  */
@@ -1906,7 +1905,7 @@ static const char *t4vf_link_down_rc_str(unsigned char link_down_rc)
 /**
  *	t4vf_handle_get_port_info - process a FW reply message
  *	@pi: the port info
- *	@rpl: start of the FW message
+ *	@cmd: start of the FW message
  *
  *	Processes a GET_PORT_INFO FW reply message.
  */
@@ -2137,8 +2136,6 @@ int t4vf_handle_fw_rpl(struct adapter *adapter, const __be64 *rpl)
 	return 0;
 }
 
-/**
- */
 int t4vf_prep_adapter(struct adapter *adapter)
 {
 	int err;
diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index 61dbf19075fb..ad261e67f5a8 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -1595,6 +1595,24 @@ static int enetc_set_psfp(struct net_device *ndev, int en)
 	return 0;
 }
 
+static void enetc_enable_rxvlan(struct net_device *ndev, bool en)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	int i;
+
+	for (i = 0; i < priv->num_rx_rings; i++)
+		enetc_bdr_enable_rxvlan(&priv->si->hw, i, en);
+}
+
+static void enetc_enable_txvlan(struct net_device *ndev, bool en)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	int i;
+
+	for (i = 0; i < priv->num_tx_rings; i++)
+		enetc_bdr_enable_txvlan(&priv->si->hw, i, en);
+}
+
 int enetc_set_features(struct net_device *ndev,
 		       netdev_features_t features)
 {
@@ -1604,6 +1622,14 @@ int enetc_set_features(struct net_device *ndev,
 	if (changed & NETIF_F_RXHASH)
 		enetc_set_rss(ndev, !!(features & NETIF_F_RXHASH));
 
+	if (changed & NETIF_F_HW_VLAN_CTAG_RX)
+		enetc_enable_rxvlan(ndev,
+				    !!(features & NETIF_F_HW_VLAN_CTAG_RX));
+
+	if (changed & NETIF_F_HW_VLAN_CTAG_TX)
+		enetc_enable_txvlan(ndev,
+				    !!(features & NETIF_F_HW_VLAN_CTAG_TX));
+
 	if (changed & NETIF_F_HW_TC)
 		err = enetc_set_psfp(ndev, !!(features & NETIF_F_HW_TC));
 
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_hw.h b/drivers/net/ethernet/freescale/enetc/enetc_hw.h
index f00c4382423e..fc357bc56835 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_hw.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h
@@ -531,22 +531,22 @@ struct enetc_msg_cmd_header {
 
 /* Common H/W utility functions */
 
-static inline void enetc_enable_rxvlan(struct enetc_hw *hw, int si_idx,
-				       bool en)
+static inline void enetc_bdr_enable_rxvlan(struct enetc_hw *hw, int idx,
+					   bool en)
 {
-	u32 val = enetc_rxbdr_rd(hw, si_idx, ENETC_RBMR);
+	u32 val = enetc_rxbdr_rd(hw, idx, ENETC_RBMR);
 
 	val = (val & ~ENETC_RBMR_VTE) | (en ? ENETC_RBMR_VTE : 0);
-	enetc_rxbdr_wr(hw, si_idx, ENETC_RBMR, val);
+	enetc_rxbdr_wr(hw, idx, ENETC_RBMR, val);
 }
 
-static inline void enetc_enable_txvlan(struct enetc_hw *hw, int si_idx,
-				       bool en)
+static inline void enetc_bdr_enable_txvlan(struct enetc_hw *hw, int idx,
+					   bool en)
 {
-	u32 val = enetc_txbdr_rd(hw, si_idx, ENETC_TBMR);
+	u32 val = enetc_txbdr_rd(hw, idx, ENETC_TBMR);
 
 	val = (val & ~ENETC_TBMR_VIH) | (en ? ENETC_TBMR_VIH : 0);
-	enetc_txbdr_wr(hw, si_idx, ENETC_TBMR, val);
+	enetc_txbdr_wr(hw, idx, ENETC_TBMR, val);
 }
 
 static inline void enetc_set_bdr_prio(struct enetc_hw *hw, int bdr_idx,
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
index 824d211ec00f..4fac57dbb3c8 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
@@ -649,14 +649,6 @@ static int enetc_pf_set_features(struct net_device *ndev,
 	netdev_features_t changed = ndev->features ^ features;
 	struct enetc_ndev_priv *priv = netdev_priv(ndev);
 
-	if (changed & NETIF_F_HW_VLAN_CTAG_RX)
-		enetc_enable_rxvlan(&priv->si->hw, 0,
-				    !!(features & NETIF_F_HW_VLAN_CTAG_RX));
-
-	if (changed & NETIF_F_HW_VLAN_CTAG_TX)
-		enetc_enable_txvlan(&priv->si->hw, 0,
-				    !!(features & NETIF_F_HW_VLAN_CTAG_TX));
-
 	if (changed & NETIF_F_HW_VLAN_CTAG_FILTER) {
 		struct enetc_pf *pf = enetc_si_priv(priv->si);
 
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index c117074c16e3..23f278e46975 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -699,7 +699,7 @@ static void hns_nic_rx_up_pro(struct hns_nic_ring_data *ring_data,
 	struct net_device *ndev = ring_data->napi.dev;
 
 	skb->protocol = eth_type_trans(skb, ndev);
-	(void)napi_gro_receive(&ring_data->napi, skb);
+	napi_gro_receive(&ring_data->napi, skb);
 }
 
 static int hns_desc_unused(struct hnae_ring *ring)
diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index 96d36ae5049e..c5c732601e35 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -1715,7 +1715,7 @@ static int ibmveth_probe(struct vio_dev *dev, const struct vio_device_id *id)
 	}
 
 	netdev->min_mtu = IBMVETH_MIN_MTU;
-	netdev->max_mtu = ETH_MAX_MTU;
+	netdev->max_mtu = ETH_MAX_MTU - IBMVETH_BUFF_OH;
 
 	memcpy(netdev->dev_addr, mac_addr_p, ETH_ALEN);
 
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 2baf7b3ff4cb..0fd7eae25fe9 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -1971,13 +1971,18 @@ static int do_reset(struct ibmvnic_adapter *adapter,
 			release_sub_crqs(adapter, 1);
 		} else {
 			rc = ibmvnic_reset_crq(adapter);
-			if (!rc)
+			if (rc == H_CLOSED || rc == H_SUCCESS) {
 				rc = vio_enable_interrupts(adapter->vdev);
+				if (rc)
+					netdev_err(adapter->netdev,
+						   "Reset failed to enable interrupts. rc=%d\n",
+						   rc);
+			}
 		}
 
 		if (rc) {
 			netdev_err(adapter->netdev,
-				   "Couldn't initialize crq. rc=%d\n", rc);
+				   "Reset couldn't initialize crq. rc=%d\n", rc);
 			goto out;
 		}
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index aa8026b1eb81..67806b7b2f49 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -2072,6 +2072,9 @@ static int i40e_set_ringparam(struct net_device *netdev,
 			err = i40e_setup_rx_descriptors(&rx_rings[i]);
 			if (err)
 				goto rx_unwind;
+			err = i40e_alloc_rx_bi(&rx_rings[i]);
+			if (err)
+				goto rx_unwind;
 
 			/* now allocate the Rx buffers to make sure the OS
 			 * has enough memory, any failure here means abort
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 5d807c8004f8..56ecd6c3f236 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -439,11 +439,15 @@ static void i40e_get_netdev_stats_struct(struct net_device *netdev,
 		i40e_get_netdev_stats_struct_tx(ring, stats);
 
 		if (i40e_enabled_xdp_vsi(vsi)) {
-			ring++;
+			ring = READ_ONCE(vsi->xdp_rings[i]);
+			if (!ring)
+				continue;
 			i40e_get_netdev_stats_struct_tx(ring, stats);
 		}
 
-		ring++;
+		ring = READ_ONCE(vsi->rx_rings[i]);
+		if (!ring)
+			continue;
 		do {
 			start   = u64_stats_fetch_begin_irq(&ring->syncp);
 			packets = ring->stats.packets;
@@ -787,6 +791,8 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi)
 	for (q = 0; q < vsi->num_queue_pairs; q++) {
 		/* locate Tx ring */
 		p = READ_ONCE(vsi->tx_rings[q]);
+		if (!p)
+			continue;
 
 		do {
 			start = u64_stats_fetch_begin_irq(&p->syncp);
@@ -800,8 +806,11 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi)
 		tx_linearize += p->tx_stats.tx_linearize;
 		tx_force_wb += p->tx_stats.tx_force_wb;
 
-		/* Rx queue is part of the same block as Tx queue */
-		p = &p[1];
+		/* locate Rx ring */
+		p = READ_ONCE(vsi->rx_rings[q]);
+		if (!p)
+			continue;
+
 		do {
 			start = u64_stats_fetch_begin_irq(&p->syncp);
 			packets = p->stats.packets;
@@ -10824,10 +10833,10 @@ static void i40e_vsi_clear_rings(struct i40e_vsi *vsi)
 	if (vsi->tx_rings && vsi->tx_rings[0]) {
 		for (i = 0; i < vsi->alloc_queue_pairs; i++) {
 			kfree_rcu(vsi->tx_rings[i], rcu);
-			vsi->tx_rings[i] = NULL;
-			vsi->rx_rings[i] = NULL;
+			WRITE_ONCE(vsi->tx_rings[i], NULL);
+			WRITE_ONCE(vsi->rx_rings[i], NULL);
 			if (vsi->xdp_rings)
-				vsi->xdp_rings[i] = NULL;
+				WRITE_ONCE(vsi->xdp_rings[i], NULL);
 		}
 	}
 }
@@ -10861,7 +10870,7 @@ static int i40e_alloc_rings(struct i40e_vsi *vsi)
 		if (vsi->back->hw_features & I40E_HW_WB_ON_ITR_CAPABLE)
 			ring->flags = I40E_TXR_FLAGS_WB_ON_ITR;
 		ring->itr_setting = pf->tx_itr_default;
-		vsi->tx_rings[i] = ring++;
+		WRITE_ONCE(vsi->tx_rings[i], ring++);
 
 		if (!i40e_enabled_xdp_vsi(vsi))
 			goto setup_rx;
@@ -10879,7 +10888,7 @@ static int i40e_alloc_rings(struct i40e_vsi *vsi)
 			ring->flags = I40E_TXR_FLAGS_WB_ON_ITR;
 		set_ring_xdp(ring);
 		ring->itr_setting = pf->tx_itr_default;
-		vsi->xdp_rings[i] = ring++;
+		WRITE_ONCE(vsi->xdp_rings[i], ring++);
 
 setup_rx:
 		ring->queue_index = i;
@@ -10892,7 +10901,7 @@ setup_rx:
 		ring->size = 0;
 		ring->dcb_tc = 0;
 		ring->itr_setting = pf->rx_itr_default;
-		vsi->rx_rings[i] = ring;
+		WRITE_ONCE(vsi->rx_rings[i], ring);
 	}
 
 	return 0;
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 28b46cc9f5cb..2e3a39cea2c0 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -1194,7 +1194,7 @@ static void ice_vsi_clear_rings(struct ice_vsi *vsi)
 		for (i = 0; i < vsi->alloc_txq; i++) {
 			if (vsi->tx_rings[i]) {
 				kfree_rcu(vsi->tx_rings[i], rcu);
-				vsi->tx_rings[i] = NULL;
+				WRITE_ONCE(vsi->tx_rings[i], NULL);
 			}
 		}
 	}
@@ -1202,7 +1202,7 @@ static void ice_vsi_clear_rings(struct ice_vsi *vsi)
 		for (i = 0; i < vsi->alloc_rxq; i++) {
 			if (vsi->rx_rings[i]) {
 				kfree_rcu(vsi->rx_rings[i], rcu);
-				vsi->rx_rings[i] = NULL;
+				WRITE_ONCE(vsi->rx_rings[i], NULL);
 			}
 		}
 	}
@@ -1235,7 +1235,7 @@ static int ice_vsi_alloc_rings(struct ice_vsi *vsi)
 		ring->vsi = vsi;
 		ring->dev = dev;
 		ring->count = vsi->num_tx_desc;
-		vsi->tx_rings[i] = ring;
+		WRITE_ONCE(vsi->tx_rings[i], ring);
 	}
 
 	/* Allocate Rx rings */
@@ -1254,7 +1254,7 @@ static int ice_vsi_alloc_rings(struct ice_vsi *vsi)
 		ring->netdev = vsi->netdev;
 		ring->dev = dev;
 		ring->count = vsi->num_rx_desc;
-		vsi->rx_rings[i] = ring;
+		WRITE_ONCE(vsi->rx_rings[i], ring);
 	}
 
 	return 0;
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 082825e3cb39..4cbd49c87568 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -1702,7 +1702,7 @@ static int ice_xdp_alloc_setup_rings(struct ice_vsi *vsi)
 		xdp_ring->netdev = NULL;
 		xdp_ring->dev = dev;
 		xdp_ring->count = vsi->num_tx_desc;
-		vsi->xdp_rings[i] = xdp_ring;
+		WRITE_ONCE(vsi->xdp_rings[i], xdp_ring);
 		if (ice_setup_tx_ring(xdp_ring))
 			goto free_xdp_rings;
 		ice_set_ring_xdp(xdp_ring);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
index fd9f5d41b594..2e35c5706cf1 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
@@ -921,7 +921,7 @@ static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter,
 		ring->queue_index = txr_idx;
 
 		/* assign ring to adapter */
-		adapter->tx_ring[txr_idx] = ring;
+		WRITE_ONCE(adapter->tx_ring[txr_idx], ring);
 
 		/* update count and index */
 		txr_count--;
@@ -948,7 +948,7 @@ static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter,
 		set_ring_xdp(ring);
 
 		/* assign ring to adapter */
-		adapter->xdp_ring[xdp_idx] = ring;
+		WRITE_ONCE(adapter->xdp_ring[xdp_idx], ring);
 
 		/* update count and index */
 		xdp_count--;
@@ -991,7 +991,7 @@ static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter,
 		ring->queue_index = rxr_idx;
 
 		/* assign ring to adapter */
-		adapter->rx_ring[rxr_idx] = ring;
+		WRITE_ONCE(adapter->rx_ring[rxr_idx], ring);
 
 		/* update count and index */
 		rxr_count--;
@@ -1020,13 +1020,13 @@ static void ixgbe_free_q_vector(struct ixgbe_adapter *adapter, int v_idx)
 
 	ixgbe_for_each_ring(ring, q_vector->tx) {
 		if (ring_is_xdp(ring))
-			adapter->xdp_ring[ring->queue_index] = NULL;
+			WRITE_ONCE(adapter->xdp_ring[ring->queue_index], NULL);
 		else
-			adapter->tx_ring[ring->queue_index] = NULL;
+			WRITE_ONCE(adapter->tx_ring[ring->queue_index], NULL);
 	}
 
 	ixgbe_for_each_ring(ring, q_vector->rx)
-		adapter->rx_ring[ring->queue_index] = NULL;
+		WRITE_ONCE(adapter->rx_ring[ring->queue_index], NULL);
 
 	adapter->q_vector[v_idx] = NULL;
 	napi_hash_del(&q_vector->napi);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index f162b8b8f345..97a423ecf808 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -7051,7 +7051,10 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter)
 	}
 
 	for (i = 0; i < adapter->num_rx_queues; i++) {
-		struct ixgbe_ring *rx_ring = adapter->rx_ring[i];
+		struct ixgbe_ring *rx_ring = READ_ONCE(adapter->rx_ring[i]);
+
+		if (!rx_ring)
+			continue;
 		non_eop_descs += rx_ring->rx_stats.non_eop_descs;
 		alloc_rx_page += rx_ring->rx_stats.alloc_rx_page;
 		alloc_rx_page_failed += rx_ring->rx_stats.alloc_rx_page_failed;
@@ -7072,15 +7075,20 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter)
 	packets = 0;
 	/* gather some stats to the adapter struct that are per queue */
 	for (i = 0; i < adapter->num_tx_queues; i++) {
-		struct ixgbe_ring *tx_ring = adapter->tx_ring[i];
+		struct ixgbe_ring *tx_ring = READ_ONCE(adapter->tx_ring[i]);
+
+		if (!tx_ring)
+			continue;
 		restart_queue += tx_ring->tx_stats.restart_queue;
 		tx_busy += tx_ring->tx_stats.tx_busy;
 		bytes += tx_ring->stats.bytes;
 		packets += tx_ring->stats.packets;
 	}
 	for (i = 0; i < adapter->num_xdp_queues; i++) {
-		struct ixgbe_ring *xdp_ring = adapter->xdp_ring[i];
+		struct ixgbe_ring *xdp_ring = READ_ONCE(adapter->xdp_ring[i]);
 
+		if (!xdp_ring)
+			continue;
 		restart_queue += xdp_ring->tx_stats.restart_queue;
 		tx_busy += xdp_ring->tx_stats.tx_busy;
 		bytes += xdp_ring->stats.bytes;
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 95b447c14411..197d8c6d189d 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -106,9 +106,11 @@
 #define      MVNETA_TX_IN_PRGRS                  BIT(1)
 #define      MVNETA_TX_FIFO_EMPTY                BIT(8)
 #define MVNETA_RX_MIN_FRAME_SIZE                 0x247c
+/* Only exists on Armada XP and Armada 370 */
 #define MVNETA_SERDES_CFG			 0x24A0
 #define      MVNETA_SGMII_SERDES_PROTO		 0x0cc7
 #define      MVNETA_QSGMII_SERDES_PROTO		 0x0667
+#define      MVNETA_HSGMII_SERDES_PROTO		 0x1107
 #define MVNETA_TYPE_PRIO                         0x24bc
 #define      MVNETA_FORCE_UNI                    BIT(21)
 #define MVNETA_TXQ_CMD_1                         0x24e4
@@ -3528,26 +3530,60 @@ static int mvneta_setup_txqs(struct mvneta_port *pp)
 	return 0;
 }
 
-static int mvneta_comphy_init(struct mvneta_port *pp)
+static int mvneta_comphy_init(struct mvneta_port *pp, phy_interface_t interface)
 {
 	int ret;
 
-	if (!pp->comphy)
-		return 0;
-
-	ret = phy_set_mode_ext(pp->comphy, PHY_MODE_ETHERNET,
-			       pp->phy_interface);
+	ret = phy_set_mode_ext(pp->comphy, PHY_MODE_ETHERNET, interface);
 	if (ret)
 		return ret;
 
 	return phy_power_on(pp->comphy);
 }
 
+static int mvneta_config_interface(struct mvneta_port *pp,
+				   phy_interface_t interface)
+{
+	int ret = 0;
+
+	if (pp->comphy) {
+		if (interface == PHY_INTERFACE_MODE_SGMII ||
+		    interface == PHY_INTERFACE_MODE_1000BASEX ||
+		    interface == PHY_INTERFACE_MODE_2500BASEX) {
+			ret = mvneta_comphy_init(pp, interface);
+		}
+	} else {
+		switch (interface) {
+		case PHY_INTERFACE_MODE_QSGMII:
+			mvreg_write(pp, MVNETA_SERDES_CFG,
+				    MVNETA_QSGMII_SERDES_PROTO);
+			break;
+
+		case PHY_INTERFACE_MODE_SGMII:
+		case PHY_INTERFACE_MODE_1000BASEX:
+			mvreg_write(pp, MVNETA_SERDES_CFG,
+				    MVNETA_SGMII_SERDES_PROTO);
+			break;
+
+		case PHY_INTERFACE_MODE_2500BASEX:
+			mvreg_write(pp, MVNETA_SERDES_CFG,
+				    MVNETA_HSGMII_SERDES_PROTO);
+			break;
+		default:
+			break;
+		}
+	}
+
+	pp->phy_interface = interface;
+
+	return ret;
+}
+
 static void mvneta_start_dev(struct mvneta_port *pp)
 {
 	int cpu;
 
-	WARN_ON(mvneta_comphy_init(pp));
+	WARN_ON(mvneta_config_interface(pp, pp->phy_interface));
 
 	mvneta_max_rx_size_set(pp, pp->pkt_size);
 	mvneta_txq_max_tx_size_set(pp, pp->pkt_size);
@@ -3925,14 +3961,10 @@ static void mvneta_mac_config(struct phylink_config *config, unsigned int mode,
 	if (state->speed == SPEED_2500)
 		new_ctrl4 |= MVNETA_GMAC4_SHORT_PREAMBLE_ENABLE;
 
-	if (pp->comphy && pp->phy_interface != state->interface &&
-	    (state->interface == PHY_INTERFACE_MODE_SGMII ||
-	     state->interface == PHY_INTERFACE_MODE_1000BASEX ||
-	     state->interface == PHY_INTERFACE_MODE_2500BASEX)) {
-		pp->phy_interface = state->interface;
-
-		WARN_ON(phy_power_off(pp->comphy));
-		WARN_ON(mvneta_comphy_init(pp));
+	if (pp->phy_interface != state->interface) {
+		if (pp->comphy)
+			WARN_ON(phy_power_off(pp->comphy));
+		WARN_ON(mvneta_config_interface(pp, state->interface));
 	}
 
 	if (new_ctrl0 != gmac_ctrl0)
@@ -4981,12 +5013,10 @@ static int mvneta_port_power_up(struct mvneta_port *pp, int phy_mode)
 	/* MAC Cause register should be cleared */
 	mvreg_write(pp, MVNETA_UNIT_INTR_CAUSE, 0);
 
-	if (phy_mode == PHY_INTERFACE_MODE_QSGMII)
-		mvreg_write(pp, MVNETA_SERDES_CFG, MVNETA_QSGMII_SERDES_PROTO);
-	else if (phy_mode == PHY_INTERFACE_MODE_SGMII ||
-		 phy_interface_mode_is_8023z(phy_mode))
-		mvreg_write(pp, MVNETA_SERDES_CFG, MVNETA_SGMII_SERDES_PROTO);
-	else if (!phy_interface_mode_is_rgmii(phy_mode))
+	if (phy_mode != PHY_INTERFACE_MODE_QSGMII &&
+	    phy_mode != PHY_INTERFACE_MODE_SGMII &&
+	    !phy_interface_mode_is_8023z(phy_mode) &&
+	    !phy_interface_mode_is_rgmii(phy_mode))
 		return -EINVAL;
 
 	return 0;
@@ -5175,10 +5205,10 @@ static int mvneta_probe(struct platform_device *pdev)
 	if (err < 0)
 		goto err_netdev;
 
-	err = mvneta_port_power_up(pp, phy_mode);
+	err = mvneta_port_power_up(pp, pp->phy_interface);
 	if (err < 0) {
 		dev_err(&pdev->dev, "can't power up port\n");
-		goto err_netdev;
+		return err;
 	}
 
 	/* Armada3700 network controller does not support per-cpu
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
index 80713123de5c..eefeb1cdc2ee 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
@@ -407,7 +407,9 @@ static int
 mlx5e_rep_indr_setup_block(struct net_device *netdev,
 			   struct mlx5e_rep_priv *rpriv,
 			   struct flow_block_offload *f,
-			   flow_setup_cb_t *setup_cb)
+			   flow_setup_cb_t *setup_cb,
+			   void *data,
+			   void (*cleanup)(struct flow_block_cb *block_cb))
 {
 	struct mlx5e_priv *priv = netdev_priv(rpriv->netdev);
 	struct mlx5e_rep_indr_block_priv *indr_priv;
@@ -438,8 +440,10 @@ mlx5e_rep_indr_setup_block(struct net_device *netdev,
 		list_add(&indr_priv->list,
 			 &rpriv->uplink_priv.tc_indr_block_priv_list);
 
-		block_cb = flow_block_cb_alloc(setup_cb, indr_priv, indr_priv,
-					       mlx5e_rep_indr_block_unbind);
+		block_cb = flow_indr_block_cb_alloc(setup_cb, indr_priv, indr_priv,
+						    mlx5e_rep_indr_block_unbind,
+						    f, netdev, data, rpriv,
+						    cleanup);
 		if (IS_ERR(block_cb)) {
 			list_del(&indr_priv->list);
 			kfree(indr_priv);
@@ -458,7 +462,7 @@ mlx5e_rep_indr_setup_block(struct net_device *netdev,
 		if (!block_cb)
 			return -ENOENT;
 
-		flow_block_cb_remove(block_cb, f);
+		flow_indr_block_cb_remove(block_cb, f);
 		list_del(&block_cb->driver_list);
 		return 0;
 	default:
@@ -469,15 +473,19 @@ mlx5e_rep_indr_setup_block(struct net_device *netdev,
 
 static
 int mlx5e_rep_indr_setup_cb(struct net_device *netdev, void *cb_priv,
-			    enum tc_setup_type type, void *type_data)
+			    enum tc_setup_type type, void *type_data,
+			    void *data,
+			    void (*cleanup)(struct flow_block_cb *block_cb))
 {
 	switch (type) {
 	case TC_SETUP_BLOCK:
 		return mlx5e_rep_indr_setup_block(netdev, cb_priv, type_data,
-						  mlx5e_rep_indr_setup_tc_cb);
+						  mlx5e_rep_indr_setup_tc_cb,
+						  data, cleanup);
 	case TC_SETUP_FT:
 		return mlx5e_rep_indr_setup_block(netdev, cb_priv, type_data,
-						  mlx5e_rep_indr_setup_ft_cb);
+						  mlx5e_rep_indr_setup_ft_cb,
+						  data, cleanup);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -496,7 +504,7 @@ int mlx5e_rep_tc_netdevice_event_register(struct mlx5e_rep_priv *rpriv)
 void mlx5e_rep_tc_netdevice_event_unregister(struct mlx5e_rep_priv *rpriv)
 {
 	flow_indr_dev_unregister(mlx5e_rep_indr_setup_cb, rpriv,
-				 mlx5e_rep_indr_setup_tc_cb);
+				 mlx5e_rep_indr_block_unbind);
 }
 
 #if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index f600e5c6b60d..a5c5363915dc 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -993,10 +993,10 @@ int __mlxsw_sp_port_headroom_set(struct mlxsw_sp_port *mlxsw_sp_port, int mtu,
 
 		lossy = !(pfc || pause_en);
 		thres_cells = mlxsw_sp_pg_buf_threshold_get(mlxsw_sp, mtu);
-		mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, &thres_cells);
+		thres_cells = mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, thres_cells);
 		delay_cells = mlxsw_sp_pg_buf_delay_get(mlxsw_sp, mtu, delay,
 							pfc, pause_en);
-		mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, &delay_cells);
+		delay_cells = mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, delay_cells);
 		total_cells = thres_cells + delay_cells;
 
 		taken_headroom_cells += total_cells;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 17dd16d82f87..3e794d58184b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -376,17 +376,15 @@ mlxsw_sp_port_vlan_find_by_vid(const struct mlxsw_sp_port *mlxsw_sp_port,
 	return NULL;
 }
 
-static inline void
+static inline u32
 mlxsw_sp_port_headroom_8x_adjust(const struct mlxsw_sp_port *mlxsw_sp_port,
-				 u16 *p_size)
+				 u32 size_cells)
 {
 	/* Ports with eight lanes use two headroom buffers between which the
 	 * configured headroom size is split. Therefore, multiply the calculated
 	 * headroom size by two.
 	 */
-	if (mlxsw_sp_port->mapping.width != 8)
-		return;
-	*p_size *= 2;
+	return mlxsw_sp_port->mapping.width == 8 ? 2 * size_cells : size_cells;
 }
 
 enum mlxsw_sp_flood_type {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
index f25a8b084b4b..6f84557a5a6f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
@@ -312,7 +312,7 @@ static int mlxsw_sp_port_pb_init(struct mlxsw_sp_port *mlxsw_sp_port)
 
 		if (i == MLXSW_SP_PB_UNUSED)
 			continue;
-		mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, &size);
+		size = mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, size);
 		mlxsw_reg_pbmc_lossy_buffer_pack(pbmc_pl, i, size);
 	}
 	mlxsw_reg_pbmc_lossy_buffer_pack(pbmc_pl,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
index f843545d3478..92351a79addc 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
@@ -782,7 +782,7 @@ mlxsw_sp_span_port_buffer_update(struct mlxsw_sp_port *mlxsw_sp_port, u16 mtu)
 		speed = 0;
 
 	buffsize = mlxsw_sp_span_buffsize_get(mlxsw_sp, speed, mtu);
-	mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, (u16 *) &buffsize);
+	buffsize = mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, buffsize);
 	mlxsw_reg_sbib_pack(sbib_pl, mlxsw_sp_port->local_port, buffsize);
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbib), sbib_pl);
 }
diff --git a/drivers/net/ethernet/neterion/vxge/vxge-config.h b/drivers/net/ethernet/neterion/vxge/vxge-config.h
index 628fa9b2f741..373165119850 100644
--- a/drivers/net/ethernet/neterion/vxge/vxge-config.h
+++ b/drivers/net/ethernet/neterion/vxge/vxge-config.h
@@ -297,7 +297,7 @@ struct vxge_hw_fifo_config {
  * @greedy_return: If Set it forces the device to return absolutely all RxD
  *             that are consumed and still on board when a timer interrupt
  *             triggers. If Clear, then if the device has already returned
- *             RxD before current timer interrupt trigerred and after the
+ *             RxD before current timer interrupt triggered and after the
  *             previous timer interrupt triggered, then the device is not
  *             forced to returned the rest of the consumed RxD that it has
  *             on board which account for a byte count less than the one
diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.c b/drivers/net/ethernet/netronome/nfp/flower/main.c
index c39327677a7d..bb448c82cdc2 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/main.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/main.c
@@ -861,7 +861,7 @@ static void nfp_flower_clean(struct nfp_app *app)
 	flush_work(&app_priv->cmsg_work);
 
 	flow_indr_dev_unregister(nfp_flower_indr_setup_tc_cb, app,
-				 nfp_flower_setup_indr_block_cb);
+				 nfp_flower_setup_indr_tc_release);
 
 	if (app_priv->flower_ext_feats & NFP_FL_FEATS_VF_RLIM)
 		nfp_flower_qos_cleanup(app);
diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h
index 6c3dc3baf387..7f54a620acad 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/main.h
+++ b/drivers/net/ethernet/netronome/nfp/flower/main.h
@@ -459,9 +459,10 @@ int nfp_flower_setup_qos_offload(struct nfp_app *app, struct net_device *netdev,
 				 struct tc_cls_matchall_offload *flow);
 void nfp_flower_stats_rlim_reply(struct nfp_app *app, struct sk_buff *skb);
 int nfp_flower_indr_setup_tc_cb(struct net_device *netdev, void *cb_priv,
-				enum tc_setup_type type, void *type_data);
-int nfp_flower_setup_indr_block_cb(enum tc_setup_type type, void *type_data,
-				   void *cb_priv);
+				enum tc_setup_type type, void *type_data,
+				void *data,
+				void (*cleanup)(struct flow_block_cb *block_cb));
+void nfp_flower_setup_indr_tc_release(void *cb_priv);
 
 void
 __nfp_flower_non_repr_priv_get(struct nfp_flower_non_repr_priv *non_repr_priv);
diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c
index 234c652700e1..3af27bb5f4b0 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c
@@ -1619,8 +1619,8 @@ nfp_flower_indr_block_cb_priv_lookup(struct nfp_app *app,
 	return NULL;
 }
 
-int nfp_flower_setup_indr_block_cb(enum tc_setup_type type,
-				   void *type_data, void *cb_priv)
+static int nfp_flower_setup_indr_block_cb(enum tc_setup_type type,
+					  void *type_data, void *cb_priv)
 {
 	struct nfp_flower_indr_block_cb_priv *priv = cb_priv;
 	struct flow_cls_offload *flower = type_data;
@@ -1637,7 +1637,7 @@ int nfp_flower_setup_indr_block_cb(enum tc_setup_type type,
 	}
 }
 
-static void nfp_flower_setup_indr_tc_release(void *cb_priv)
+void nfp_flower_setup_indr_tc_release(void *cb_priv)
 {
 	struct nfp_flower_indr_block_cb_priv *priv = cb_priv;
 
@@ -1647,7 +1647,8 @@ static void nfp_flower_setup_indr_tc_release(void *cb_priv)
 
 static int
 nfp_flower_setup_indr_tc_block(struct net_device *netdev, struct nfp_app *app,
-			       struct flow_block_offload *f)
+			       struct flow_block_offload *f, void *data,
+			       void (*cleanup)(struct flow_block_cb *block_cb))
 {
 	struct nfp_flower_indr_block_cb_priv *cb_priv;
 	struct nfp_flower_priv *priv = app->priv;
@@ -1676,9 +1677,10 @@ nfp_flower_setup_indr_tc_block(struct net_device *netdev, struct nfp_app *app,
 		cb_priv->app = app;
 		list_add(&cb_priv->list, &priv->indr_block_cb_priv);
 
-		block_cb = flow_block_cb_alloc(nfp_flower_setup_indr_block_cb,
-					       cb_priv, cb_priv,
-					       nfp_flower_setup_indr_tc_release);
+		block_cb = flow_indr_block_cb_alloc(nfp_flower_setup_indr_block_cb,
+						    cb_priv, cb_priv,
+						    nfp_flower_setup_indr_tc_release,
+						    f, netdev, data, app, cleanup);
 		if (IS_ERR(block_cb)) {
 			list_del(&cb_priv->list);
 			kfree(cb_priv);
@@ -1699,7 +1701,7 @@ nfp_flower_setup_indr_tc_block(struct net_device *netdev, struct nfp_app *app,
 		if (!block_cb)
 			return -ENOENT;
 
-		flow_block_cb_remove(block_cb, f);
+		flow_indr_block_cb_remove(block_cb, f);
 		list_del(&block_cb->driver_list);
 		return 0;
 	default:
@@ -1710,7 +1712,9 @@ nfp_flower_setup_indr_tc_block(struct net_device *netdev, struct nfp_app *app,
 
 int
 nfp_flower_indr_setup_tc_cb(struct net_device *netdev, void *cb_priv,
-			    enum tc_setup_type type, void *type_data)
+			    enum tc_setup_type type, void *type_data,
+			    void *data,
+			    void (*cleanup)(struct flow_block_cb *block_cb))
 {
 	if (!nfp_fl_is_netdev_to_offload(netdev))
 		return -EOPNOTSUPP;
@@ -1718,7 +1722,7 @@ nfp_flower_indr_setup_tc_cb(struct net_device *netdev, void *cb_priv,
 	switch (type) {
 	case TC_SETUP_BLOCK:
 		return nfp_flower_setup_indr_tc_block(netdev, cb_priv,
-						      type_data);
+						      type_data, data, cleanup);
 	default:
 		return -EOPNOTSUPP;
 	}
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h
index 32b9d7705404..55cef5b16aa5 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h
@@ -147,7 +147,7 @@ struct pch_gbe_regs {
 #define PCH_GBE_RH_ALM_FULL_8   0x00001000      /* 8 words */
 #define PCH_GBE_RH_ALM_FULL_16  0x00002000      /* 16 words */
 #define PCH_GBE_RH_ALM_FULL_32  0x00003000      /* 32 words */
-/* RX FIFO Read Triger Threshold */
+/* RX FIFO Read Trigger Threshold */
 #define PCH_GBE_RH_RD_TRG_4     0x00000000      /* 4 words */
 #define PCH_GBE_RH_RD_TRG_8     0x00000200      /* 8 words */
 #define PCH_GBE_RH_RD_TRG_16    0x00000400      /* 16 words */
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
index 9d8c969f21cb..aaa00edd9d5b 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@@ -96,7 +96,8 @@ static void ionic_link_status_check(struct ionic_lif *lif)
 	u16 link_status;
 	bool link_up;
 
-	if (!test_bit(IONIC_LIF_F_LINK_CHECK_REQUESTED, lif->state))
+	if (!test_bit(IONIC_LIF_F_LINK_CHECK_REQUESTED, lif->state) ||
+	    test_bit(IONIC_LIF_F_QUEUE_RESET, lif->state))
 		return;
 
 	link_status = le16_to_cpu(lif->info->status.link_status);
@@ -1245,6 +1246,7 @@ static int ionic_init_nic_features(struct ionic_lif *lif)
 
 	netdev->hw_features |= netdev->hw_enc_features;
 	netdev->features |= netdev->hw_features;
+	netdev->vlan_features |= netdev->features & ~NETIF_F_VLAN_FEATURES;
 
 	netdev->priv_flags |= IFF_UNICAST_FLT |
 			      IFF_LIVE_ADDR_CHANGE;
@@ -1692,15 +1694,15 @@ static void ionic_stop_queues(struct ionic_lif *lif)
 	if (!test_and_clear_bit(IONIC_LIF_F_UP, lif->state))
 		return;
 
-	ionic_txrx_disable(lif);
 	netif_tx_disable(lif->netdev);
+	ionic_txrx_disable(lif);
 }
 
 int ionic_stop(struct net_device *netdev)
 {
 	struct ionic_lif *lif = netdev_priv(netdev);
 
-	if (!netif_device_present(netdev))
+	if (test_bit(IONIC_LIF_F_FW_RESET, lif->state))
 		return 0;
 
 	ionic_stop_queues(lif);
@@ -1983,18 +1985,19 @@ int ionic_reset_queues(struct ionic_lif *lif)
 	bool running;
 	int err = 0;
 
-	/* Put off the next watchdog timeout */
-	netif_trans_update(lif->netdev);
-
 	err = ionic_wait_for_bit(lif, IONIC_LIF_F_QUEUE_RESET);
 	if (err)
 		return err;
 
 	running = netif_running(lif->netdev);
-	if (running)
+	if (running) {
+		netif_device_detach(lif->netdev);
 		err = ionic_stop(lif->netdev);
-	if (!err && running)
+	}
+	if (!err && running) {
 		ionic_open(lif->netdev);
+		netif_device_attach(lif->netdev);
+	}
 
 	clear_bit(IONIC_LIF_F_QUEUE_RESET, lif->state);
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
index 7b76667acaba..08ba9d54ab63 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
@@ -271,7 +271,7 @@ static void qed_cxt_qm_iids(struct qed_hwfn *p_hwfn,
 		vf_tids += segs[NUM_TASK_PF_SEGMENTS].count;
 	}
 
-	iids->vf_cids += vf_cids * p_mngr->vf_count;
+	iids->vf_cids = vf_cids;
 	iids->tids += vf_tids * p_mngr->vf_count;
 
 	DP_VERBOSE(p_hwfn, QED_MSG_ILT,
@@ -465,6 +465,20 @@ static struct qed_ilt_cli_blk *qed_cxt_set_blk(struct qed_ilt_cli_blk *p_blk)
 	return p_blk;
 }
 
+static void qed_cxt_ilt_blk_reset(struct qed_hwfn *p_hwfn)
+{
+	struct qed_ilt_client_cfg *clients = p_hwfn->p_cxt_mngr->clients;
+	u32 cli_idx, blk_idx;
+
+	for (cli_idx = 0; cli_idx < MAX_ILT_CLIENTS; cli_idx++) {
+		for (blk_idx = 0; blk_idx < ILT_CLI_PF_BLOCKS; blk_idx++)
+			clients[cli_idx].pf_blks[blk_idx].total_size = 0;
+
+		for (blk_idx = 0; blk_idx < ILT_CLI_VF_BLOCKS; blk_idx++)
+			clients[cli_idx].vf_blks[blk_idx].total_size = 0;
+	}
+}
+
 int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn, u32 *line_count)
 {
 	struct qed_cxt_mngr *p_mngr = p_hwfn->p_cxt_mngr;
@@ -484,6 +498,11 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn, u32 *line_count)
 
 	p_mngr->pf_start_line = RESC_START(p_hwfn, QED_ILT);
 
+	/* Reset all ILT blocks at the beginning of ILT computing in order
+	 * to prevent memory allocation for irrelevant blocks afterwards.
+	 */
+	qed_cxt_ilt_blk_reset(p_hwfn);
+
 	DP_VERBOSE(p_hwfn, QED_MSG_ILT,
 		   "hwfn [%d] - Set context manager starting line to be 0x%08x\n",
 		   p_hwfn->my_id, p_hwfn->p_cxt_mngr->pf_start_line);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c
index 57a0dab88431..81e8fbe4a05b 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_debug.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c
@@ -5568,7 +5568,8 @@ static const char * const s_status_str[] = {
 
 	/* DBG_STATUS_INVALID_FILTER_TRIGGER_DWORDS */
 	"The filter/trigger constraint dword offsets are not enabled for recording",
-
+	/* DBG_STATUS_NO_MATCHING_FRAMING_MODE */
+	"No matching framing mode",
 
 	/* DBG_STATUS_VFC_READ_ERROR */
 	"Error reading from VFC",
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c
index 1eebf30fa798..3aa51374e727 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c
@@ -980,7 +980,7 @@ int qed_llh_add_mac_filter(struct qed_dev *cdev,
 	struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev);
 	struct qed_ptt *p_ptt = qed_ptt_acquire(p_hwfn);
 	union qed_llh_filter filter = {};
-	u8 filter_idx, abs_ppfid;
+	u8 filter_idx, abs_ppfid = 0;
 	u32 high, low, ref_cnt;
 	int rc = 0;
 
@@ -1368,6 +1368,8 @@ static void qed_dbg_user_data_free(struct qed_hwfn *p_hwfn)
 
 void qed_resc_free(struct qed_dev *cdev)
 {
+	struct qed_rdma_info *rdma_info;
+	struct qed_hwfn *p_hwfn;
 	int i;
 
 	if (IS_VF(cdev)) {
@@ -1385,7 +1387,8 @@ void qed_resc_free(struct qed_dev *cdev)
 	qed_llh_free(cdev);
 
 	for_each_hwfn(cdev, i) {
-		struct qed_hwfn *p_hwfn = &cdev->hwfns[i];
+		p_hwfn = cdev->hwfns + i;
+		rdma_info = p_hwfn->p_rdma_info;
 
 		qed_cxt_mngr_free(p_hwfn);
 		qed_qm_info_free(p_hwfn);
@@ -1404,8 +1407,10 @@ void qed_resc_free(struct qed_dev *cdev)
 			qed_ooo_free(p_hwfn);
 		}
 
-		if (QED_IS_RDMA_PERSONALITY(p_hwfn))
+		if (QED_IS_RDMA_PERSONALITY(p_hwfn) && rdma_info) {
+			qed_spq_unregister_async_cb(p_hwfn, rdma_info->proto);
 			qed_rdma_info_free(p_hwfn);
+		}
 
 		qed_iov_free(p_hwfn);
 		qed_l2_free(p_hwfn);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
index d2fe61a5cf56..5409a2da6106 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
@@ -2836,8 +2836,6 @@ int qed_iwarp_stop(struct qed_hwfn *p_hwfn)
 	if (rc)
 		return rc;
 
-	qed_spq_unregister_async_cb(p_hwfn, PROTOCOLID_IWARP);
-
 	return qed_iwarp_ll2_stop(p_hwfn);
 }
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_roce.c b/drivers/net/ethernet/qlogic/qed/qed_roce.c
index 4566815f7b87..7271dd7166e5 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_roce.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_roce.c
@@ -113,7 +113,6 @@ void qed_roce_stop(struct qed_hwfn *p_hwfn)
 			break;
 		}
 	}
-	qed_spq_unregister_async_cb(p_hwfn, PROTOCOLID_ROCE);
 }
 
 static void qed_rdma_copy_gids(struct qed_rdma_qp *qp, __le32 *src_gid,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.c b/drivers/net/ethernet/qlogic/qed/qed_vf.c
index 856051f50eb7..adc2c8f3d48e 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_vf.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_vf.c
@@ -81,12 +81,17 @@ static void qed_vf_pf_req_end(struct qed_hwfn *p_hwfn, int req_status)
 	mutex_unlock(&(p_hwfn->vf_iov_info->mutex));
 }
 
+#define QED_VF_CHANNEL_USLEEP_ITERATIONS	90
+#define QED_VF_CHANNEL_USLEEP_DELAY		100
+#define QED_VF_CHANNEL_MSLEEP_ITERATIONS	10
+#define QED_VF_CHANNEL_MSLEEP_DELAY		25
+
 static int qed_send_msg2pf(struct qed_hwfn *p_hwfn, u8 *done, u32 resp_size)
 {
 	union vfpf_tlvs *p_req = p_hwfn->vf_iov_info->vf2pf_request;
 	struct ustorm_trigger_vf_zone trigger;
 	struct ustorm_vf_zone *zone_data;
-	int rc = 0, time = 100;
+	int iter, rc = 0;
 
 	zone_data = (struct ustorm_vf_zone *)PXP_VF_BAR0_START_USDM_ZONE_B;
 
@@ -126,11 +131,19 @@ static int qed_send_msg2pf(struct qed_hwfn *p_hwfn, u8 *done, u32 resp_size)
 	REG_WR(p_hwfn, (uintptr_t)&zone_data->trigger, *((u32 *)&trigger));
 
 	/* When PF would be done with the response, it would write back to the
-	 * `done' address. Poll until then.
+	 * `done' address from a coherent DMA zone. Poll until then.
 	 */
-	while ((!*done) && time) {
-		msleep(25);
-		time--;
+
+	iter = QED_VF_CHANNEL_USLEEP_ITERATIONS;
+	while (!*done && iter--) {
+		udelay(QED_VF_CHANNEL_USLEEP_DELAY);
+		dma_rmb();
+	}
+
+	iter = QED_VF_CHANNEL_MSLEEP_ITERATIONS;
+	while (!*done && iter--) {
+		msleep(QED_VF_CHANNEL_MSLEEP_DELAY);
+		dma_rmb();
 	}
 
 	if (!*done) {
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index 756c05eb96f3..29e285430f99 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -1229,7 +1229,7 @@ static int __qede_probe(struct pci_dev *pdev, u32 dp_module, u8 dp_level,
 
 	/* PTP not supported on VFs */
 	if (!is_vf)
-		qede_ptp_enable(edev, (mode == QEDE_PROBE_NORMAL));
+		qede_ptp_enable(edev);
 
 	edev->ops->register_ops(cdev, &qede_ll_ops, edev);
 
@@ -1318,6 +1318,7 @@ static void __qede_remove(struct pci_dev *pdev, enum qede_remove_mode mode)
 	if (system_state == SYSTEM_POWER_OFF)
 		return;
 	qed_ops->common->remove(cdev);
+	edev->cdev = NULL;
 
 	/* Since this can happen out-of-sync with other flows,
 	 * don't release the netdevice until after slowpath stop
diff --git a/drivers/net/ethernet/qlogic/qede/qede_ptp.c b/drivers/net/ethernet/qlogic/qede/qede_ptp.c
index 4c7f7a7fc151..cd5841a9415e 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_ptp.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_ptp.c
@@ -412,6 +412,7 @@ void qede_ptp_disable(struct qede_dev *edev)
 	if (ptp->tx_skb) {
 		dev_kfree_skb_any(ptp->tx_skb);
 		ptp->tx_skb = NULL;
+		clear_bit_unlock(QEDE_FLAGS_PTP_TX_IN_PRORGESS, &edev->flags);
 	}
 
 	/* Disable PTP in HW */
@@ -423,7 +424,7 @@ void qede_ptp_disable(struct qede_dev *edev)
 	edev->ptp = NULL;
 }
 
-static int qede_ptp_init(struct qede_dev *edev, bool init_tc)
+static int qede_ptp_init(struct qede_dev *edev)
 {
 	struct qede_ptp *ptp;
 	int rc;
@@ -444,25 +445,19 @@ static int qede_ptp_init(struct qede_dev *edev, bool init_tc)
 	/* Init work queue for Tx timestamping */
 	INIT_WORK(&ptp->work, qede_ptp_task);
 
-	/* Init cyclecounter and timecounter. This is done only in the first
-	 * load. If done in every load, PTP application will fail when doing
-	 * unload / load (e.g. MTU change) while it is running.
-	 */
-	if (init_tc) {
-		memset(&ptp->cc, 0, sizeof(ptp->cc));
-		ptp->cc.read = qede_ptp_read_cc;
-		ptp->cc.mask = CYCLECOUNTER_MASK(64);
-		ptp->cc.shift = 0;
-		ptp->cc.mult = 1;
-
-		timecounter_init(&ptp->tc, &ptp->cc,
-				 ktime_to_ns(ktime_get_real()));
-	}
+	/* Init cyclecounter and timecounter */
+	memset(&ptp->cc, 0, sizeof(ptp->cc));
+	ptp->cc.read = qede_ptp_read_cc;
+	ptp->cc.mask = CYCLECOUNTER_MASK(64);
+	ptp->cc.shift = 0;
+	ptp->cc.mult = 1;
 
-	return rc;
+	timecounter_init(&ptp->tc, &ptp->cc, ktime_to_ns(ktime_get_real()));
+
+	return 0;
 }
 
-int qede_ptp_enable(struct qede_dev *edev, bool init_tc)
+int qede_ptp_enable(struct qede_dev *edev)
 {
 	struct qede_ptp *ptp;
 	int rc;
@@ -483,7 +478,7 @@ int qede_ptp_enable(struct qede_dev *edev, bool init_tc)
 
 	edev->ptp = ptp;
 
-	rc = qede_ptp_init(edev, init_tc);
+	rc = qede_ptp_init(edev);
 	if (rc)
 		goto err1;
 
diff --git a/drivers/net/ethernet/qlogic/qede/qede_ptp.h b/drivers/net/ethernet/qlogic/qede/qede_ptp.h
index 691a14c4b2c5..89c7f3cf3ee2 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_ptp.h
+++ b/drivers/net/ethernet/qlogic/qede/qede_ptp.h
@@ -41,7 +41,7 @@ void qede_ptp_rx_ts(struct qede_dev *edev, struct sk_buff *skb);
 void qede_ptp_tx_ts(struct qede_dev *edev, struct sk_buff *skb);
 int qede_ptp_hw_ts(struct qede_dev *edev, struct ifreq *req);
 void qede_ptp_disable(struct qede_dev *edev);
-int qede_ptp_enable(struct qede_dev *edev, bool init_tc);
+int qede_ptp_enable(struct qede_dev *edev);
 int qede_ptp_get_ts_info(struct qede_dev *edev, struct ethtool_ts_info *ts);
 
 static inline void qede_ptp_record_rx_ts(struct qede_dev *edev,
diff --git a/drivers/net/ethernet/qlogic/qede/qede_rdma.c b/drivers/net/ethernet/qlogic/qede/qede_rdma.c
index 2d873ae8a234..668ccc9d49f8 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_rdma.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_rdma.c
@@ -105,6 +105,7 @@ static void qede_rdma_destroy_wq(struct qede_dev *edev)
 
 	qede_rdma_cleanup_event(edev);
 	destroy_workqueue(edev->rdma_info.rdma_wq);
+	edev->rdma_info.rdma_wq = NULL;
 }
 
 int qede_rdma_dev_add(struct qede_dev *edev, bool recovery)
@@ -325,7 +326,7 @@ static void qede_rdma_add_event(struct qede_dev *edev,
 	if (edev->rdma_info.exp_recovery)
 		return;
 
-	if (!edev->rdma_info.qedr_dev)
+	if (!edev->rdma_info.qedr_dev || !edev->rdma_info.rdma_wq)
 		return;
 
 	/* We don't want the cleanup flow to start while we're allocating and
diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index c4136740db44..226205099253 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -2053,8 +2053,11 @@ static void rtl_release_firmware(struct rtl8169_private *tp)
 void r8169_apply_firmware(struct rtl8169_private *tp)
 {
 	/* TODO: release firmware if rtl_fw_write_firmware signals failure. */
-	if (tp->rtl_fw)
+	if (tp->rtl_fw) {
 		rtl_fw_write_firmware(tp, tp->rtl_fw);
+		/* At least one firmware doesn't reset tp->ocp_base. */
+		tp->ocp_base = OCP_STD_PHY_BASE;
+	}
 }
 
 static void rtl8168_config_eee_mac(struct rtl8169_private *tp)
diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c
index 328bc38848bb..0f366cc50b74 100644
--- a/drivers/net/ethernet/socionext/netsec.c
+++ b/drivers/net/ethernet/socionext/netsec.c
@@ -1044,8 +1044,9 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget)
 			skb->ip_summed = CHECKSUM_UNNECESSARY;
 
 next:
-		if ((skb && napi_gro_receive(&priv->napi, skb) != GRO_DROP) ||
-		    xdp_result) {
+		if (skb)
+			napi_gro_receive(&priv->napi, skb);
+		if (skb || xdp_result) {
 			ndev->stats.rx_packets++;
 			ndev->stats.rx_bytes += xdp.data_end - xdp.data;
 		}
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 75266580b586..4661ef865807 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -1649,6 +1649,7 @@ static int geneve_changelink(struct net_device *dev, struct nlattr *tb[],
 	geneve->collect_md = metadata;
 	geneve->use_udp6_rx_checksums = use_udp6_rx_checksums;
 	geneve->ttl_inherit = ttl_inherit;
+	geneve->df = df;
 	geneve_unquiesce(geneve, gs4, gs6);
 
 	return 0;
diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig
index f25702386d83..e351d65533aa 100644
--- a/drivers/net/phy/Kconfig
+++ b/drivers/net/phy/Kconfig
@@ -480,8 +480,7 @@ config MICROCHIP_T1_PHY
 config MICROSEMI_PHY
 	tristate "Microsemi PHYs"
 	depends on MACSEC || MACSEC=n
-	select CRYPTO_AES
-	select CRYPTO_ECB
+	select CRYPTO_LIB_AES if MACSEC
 	help
 	  Currently supports VSC8514, VSC8530, VSC8531, VSC8540 and VSC8541 PHYs
 
diff --git a/drivers/net/phy/mscc/mscc_macsec.c b/drivers/net/phy/mscc/mscc_macsec.c
index 77c8c2fb28de..1d4c012194e9 100644
--- a/drivers/net/phy/mscc/mscc_macsec.c
+++ b/drivers/net/phy/mscc/mscc_macsec.c
@@ -10,7 +10,7 @@
 #include <linux/phy.h>
 #include <dt-bindings/net/mscc-phy-vsc8531.h>
 
-#include <crypto/skcipher.h>
+#include <crypto/aes.h>
 
 #include <net/macsec.h>
 
@@ -504,39 +504,17 @@ static u32 vsc8584_macsec_flow_context_id(struct macsec_flow *flow)
 static int vsc8584_macsec_derive_key(const u8 key[MACSEC_KEYID_LEN],
 				     u16 key_len, u8 hkey[16])
 {
-	struct crypto_skcipher *tfm = crypto_alloc_skcipher("ecb(aes)", 0, 0);
-	struct skcipher_request *req = NULL;
-	struct scatterlist src, dst;
-	DECLARE_CRYPTO_WAIT(wait);
-	u32 input[4] = {0};
+	const u8 input[AES_BLOCK_SIZE] = {0};
+	struct crypto_aes_ctx ctx;
 	int ret;
 
-	if (IS_ERR(tfm))
-		return PTR_ERR(tfm);
-
-	req = skcipher_request_alloc(tfm, GFP_KERNEL);
-	if (!req) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG |
-				      CRYPTO_TFM_REQ_MAY_SLEEP, crypto_req_done,
-				      &wait);
-	ret = crypto_skcipher_setkey(tfm, key, key_len);
-	if (ret < 0)
-		goto out;
-
-	sg_init_one(&src, input, 16);
-	sg_init_one(&dst, hkey, 16);
-	skcipher_request_set_crypt(req, &src, &dst, 16, NULL);
-
-	ret = crypto_wait_req(crypto_skcipher_encrypt(req), &wait);
+	ret = aes_expandkey(&ctx, key, key_len);
+	if (ret)
+		return ret;
 
-out:
-	skcipher_request_free(req);
-	crypto_free_skcipher(tfm);
-	return ret;
+	aes_encrypt(&ctx, hkey, input);
+	memzero_explicit(&ctx, sizeof(ctx));
+	return 0;
 }
 
 static int vsc8584_macsec_transformation(struct phy_device *phydev,
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 1de3938628f4..56cfae950472 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -840,7 +840,7 @@ static void phy_error(struct phy_device *phydev)
  * phy_disable_interrupts - Disable the PHY interrupts from the PHY side
  * @phydev: target phy_device struct
  */
-static int phy_disable_interrupts(struct phy_device *phydev)
+int phy_disable_interrupts(struct phy_device *phydev)
 {
 	int err;
 
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 6d47485e68f9..5998fb505b21 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -832,8 +832,10 @@ static int get_phy_c22_id(struct mii_bus *bus, int addr, u32 *phy_id)
 
 	/* Grab the bits from PHYIR2, and put them in the lower half */
 	phy_reg = mdiobus_read(bus, addr, MII_PHYSID2);
-	if (phy_reg < 0)
-		return -EIO;
+	if (phy_reg < 0) {
+		/* returning -ENODEV doesn't stop bus scanning */
+		return (phy_reg == -EIO || phy_reg == -ENODEV) ? -ENODEV : -EIO;
+	}
 
 	*phy_id |= phy_reg;
 
@@ -1142,6 +1144,10 @@ int phy_init_hw(struct phy_device *phydev)
 	if (ret < 0)
 		return ret;
 
+	ret = phy_disable_interrupts(phydev);
+	if (ret)
+		return ret;
+
 	if (phydev->drv->config_init)
 		ret = phydev->drv->config_init(phydev);
 
diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 494af91535ba..dae6c8b51d7f 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -1464,6 +1464,8 @@ int phylink_ethtool_set_pauseparam(struct phylink *pl,
 				   struct ethtool_pauseparam *pause)
 {
 	struct phylink_link_state *config = &pl->link_config;
+	bool manual_changed;
+	int pause_state;
 
 	ASSERT_RTNL();
 
@@ -1478,15 +1480,15 @@ int phylink_ethtool_set_pauseparam(struct phylink *pl,
 	    !pause->autoneg && pause->rx_pause != pause->tx_pause)
 		return -EINVAL;
 
-	mutex_lock(&pl->state_mutex);
-	config->pause = 0;
+	pause_state = 0;
 	if (pause->autoneg)
-		config->pause |= MLO_PAUSE_AN;
+		pause_state |= MLO_PAUSE_AN;
 	if (pause->rx_pause)
-		config->pause |= MLO_PAUSE_RX;
+		pause_state |= MLO_PAUSE_RX;
 	if (pause->tx_pause)
-		config->pause |= MLO_PAUSE_TX;
+		pause_state |= MLO_PAUSE_TX;
 
+	mutex_lock(&pl->state_mutex);
 	/*
 	 * See the comments for linkmode_set_pause(), wrt the deficiencies
 	 * with the current implementation.  A solution to this issue would
@@ -1503,18 +1505,35 @@ int phylink_ethtool_set_pauseparam(struct phylink *pl,
 	linkmode_set_pause(config->advertising, pause->tx_pause,
 			   pause->rx_pause);
 
-	/* If we have a PHY, phylib will call our link state function if the
-	 * mode has changed, which will trigger a resolve and update the MAC
-	 * configuration.
+	manual_changed = (config->pause ^ pause_state) & MLO_PAUSE_AN ||
+			 (!(pause_state & MLO_PAUSE_AN) &&
+			   (config->pause ^ pause_state) & MLO_PAUSE_TXRX_MASK);
+
+	config->pause = pause_state;
+
+	if (!pl->phydev && !test_bit(PHYLINK_DISABLE_STOPPED,
+				     &pl->phylink_disable_state))
+		phylink_pcs_config(pl, true, &pl->link_config);
+
+	mutex_unlock(&pl->state_mutex);
+
+	/* If we have a PHY, a change of the pause frame advertisement will
+	 * cause phylib to renegotiate (if AN is enabled) which will in turn
+	 * call our phylink_phy_change() and trigger a resolve.  Note that
+	 * we can't hold our state mutex while calling phy_set_asym_pause().
 	 */
-	if (pl->phydev) {
+	if (pl->phydev)
 		phy_set_asym_pause(pl->phydev, pause->rx_pause,
 				   pause->tx_pause);
-	} else if (!test_bit(PHYLINK_DISABLE_STOPPED,
-			     &pl->phylink_disable_state)) {
-		phylink_pcs_config(pl, true, &pl->link_config);
+
+	/* If the manual pause settings changed, make sure we trigger a
+	 * resolve to update their state; we can not guarantee that the
+	 * link will cycle.
+	 */
+	if (manual_changed) {
+		pl->mac_link_dropped = true;
+		phylink_run_resolve(pl);
 	}
-	mutex_unlock(&pl->state_mutex);
 
 	return 0;
 }
diff --git a/drivers/net/phy/smsc.c b/drivers/net/phy/smsc.c
index 93da7d3d0954..74568ae16125 100644
--- a/drivers/net/phy/smsc.c
+++ b/drivers/net/phy/smsc.c
@@ -122,10 +122,13 @@ static int lan87xx_read_status(struct phy_device *phydev)
 		if (rc < 0)
 			return rc;
 
-		/* Wait max 640 ms to detect energy */
-		phy_read_poll_timeout(phydev, MII_LAN83C185_CTRL_STATUS, rc,
-				      rc & MII_LAN83C185_ENERGYON, 10000,
-				      640000, true);
+		/* Wait max 640 ms to detect energy and the timeout is not
+		 * an actual error.
+		 */
+		read_poll_timeout(phy_read, rc,
+				  rc & MII_LAN83C185_ENERGYON || rc < 0,
+				  10000, 640000, true, phydev,
+				  MII_LAN83C185_CTRL_STATUS);
 		if (rc < 0)
 			return rc;
 
diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c
index 950711448f39..a38e868e44d4 100644
--- a/drivers/net/usb/ax88179_178a.c
+++ b/drivers/net/usb/ax88179_178a.c
@@ -1491,10 +1491,10 @@ static int ax88179_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 		}
 
 		if (pkt_cnt == 0) {
-			/* Skip IP alignment psudo header */
-			skb_pull(skb, 2);
 			skb->len = pkt_len;
-			skb_set_tail_pointer(skb, pkt_len);
+			/* Skip IP alignment pseudo header */
+			skb_pull(skb, 2);
+			skb_set_tail_pointer(skb, skb->len);
 			skb->truesize = pkt_len + sizeof(struct sk_buff);
 			ax88179_rx_checksum(skb, pkt_hdr);
 			return 1;
@@ -1503,8 +1503,9 @@ static int ax88179_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 		ax_skb = skb_clone(skb, GFP_ATOMIC);
 		if (ax_skb) {
 			ax_skb->len = pkt_len;
-			ax_skb->data = skb->data + 2;
-			skb_set_tail_pointer(ax_skb, pkt_len);
+			/* Skip IP alignment pseudo header */
+			skb_pull(ax_skb, 2);
+			skb_set_tail_pointer(ax_skb, ax_skb->len);
 			ax_skb->truesize = pkt_len + sizeof(struct sk_buff);
 			ax88179_rx_checksum(ax_skb, pkt_hdr);
 			usbnet_skb_return(dev, ax_skb);
diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c
index 355be77f4241..3cf4dc3433f9 100644
--- a/drivers/net/usb/smsc95xx.c
+++ b/drivers/net/usb/smsc95xx.c
@@ -1324,7 +1324,7 @@ static void smsc95xx_unbind(struct usbnet *dev, struct usb_interface *intf)
 	struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]);
 
 	if (pdata) {
-		cancel_delayed_work(&pdata->carrier_check);
+		cancel_delayed_work_sync(&pdata->carrier_check);
 		netif_dbg(dev, ifdown, dev->net, "free pdata\n");
 		kfree(pdata);
 		pdata = NULL;
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index e8085ab6d484..89d85dcb200e 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -1380,6 +1380,8 @@ static int vxlan_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb,
 			struct vxlan_rdst *rd;
 
 			if (rcu_access_pointer(f->nh)) {
+				if (*idx < cb->args[2])
+					goto skip_nh;
 				err = vxlan_fdb_info(skb, vxlan, f,
 						     NETLINK_CB(cb->skb).portid,
 						     cb->nlh->nlmsg_seq,
@@ -1387,6 +1389,8 @@ static int vxlan_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb,
 						     NLM_F_MULTI, NULL);
 				if (err < 0)
 					goto out;
+skip_nh:
+				*idx += 1;
 				continue;
 			}
 
diff --git a/drivers/net/wireguard/device.c b/drivers/net/wireguard/device.c
index 3ac3f8570ca1..a8f151b1b5fa 100644
--- a/drivers/net/wireguard/device.c
+++ b/drivers/net/wireguard/device.c
@@ -45,17 +45,18 @@ static int wg_open(struct net_device *dev)
 	if (dev_v6)
 		dev_v6->cnf.addr_gen_mode = IN6_ADDR_GEN_MODE_NONE;
 
+	mutex_lock(&wg->device_update_lock);
 	ret = wg_socket_init(wg, wg->incoming_port);
 	if (ret < 0)
-		return ret;
-	mutex_lock(&wg->device_update_lock);
+		goto out;
 	list_for_each_entry(peer, &wg->peer_list, peer_list) {
 		wg_packet_send_staged_packets(peer);
 		if (peer->persistent_keepalive_interval)
 			wg_packet_send_keepalive(peer);
 	}
+out:
 	mutex_unlock(&wg->device_update_lock);
-	return 0;
+	return ret;
 }
 
 #ifdef CONFIG_PM_SLEEP
@@ -225,6 +226,7 @@ static void wg_destruct(struct net_device *dev)
 	list_del(&wg->device_list);
 	rtnl_unlock();
 	mutex_lock(&wg->device_update_lock);
+	rcu_assign_pointer(wg->creating_net, NULL);
 	wg->incoming_port = 0;
 	wg_socket_reinit(wg, NULL, NULL);
 	/* The final references are cleared in the below calls to destroy_workqueue. */
@@ -240,13 +242,11 @@ static void wg_destruct(struct net_device *dev)
 	skb_queue_purge(&wg->incoming_handshakes);
 	free_percpu(dev->tstats);
 	free_percpu(wg->incoming_handshakes_worker);
-	if (wg->have_creating_net_ref)
-		put_net(wg->creating_net);
 	kvfree(wg->index_hashtable);
 	kvfree(wg->peer_hashtable);
 	mutex_unlock(&wg->device_update_lock);
 
-	pr_debug("%s: Interface deleted\n", dev->name);
+	pr_debug("%s: Interface destroyed\n", dev->name);
 	free_netdev(dev);
 }
 
@@ -292,7 +292,7 @@ static int wg_newlink(struct net *src_net, struct net_device *dev,
 	struct wg_device *wg = netdev_priv(dev);
 	int ret = -ENOMEM;
 
-	wg->creating_net = src_net;
+	rcu_assign_pointer(wg->creating_net, src_net);
 	init_rwsem(&wg->static_identity.lock);
 	mutex_init(&wg->socket_update_lock);
 	mutex_init(&wg->device_update_lock);
@@ -393,30 +393,26 @@ static struct rtnl_link_ops link_ops __read_mostly = {
 	.newlink		= wg_newlink,
 };
 
-static int wg_netdevice_notification(struct notifier_block *nb,
-				     unsigned long action, void *data)
+static void wg_netns_pre_exit(struct net *net)
 {
-	struct net_device *dev = ((struct netdev_notifier_info *)data)->dev;
-	struct wg_device *wg = netdev_priv(dev);
-
-	ASSERT_RTNL();
-
-	if (action != NETDEV_REGISTER || dev->netdev_ops != &netdev_ops)
-		return 0;
+	struct wg_device *wg;
 
-	if (dev_net(dev) == wg->creating_net && wg->have_creating_net_ref) {
-		put_net(wg->creating_net);
-		wg->have_creating_net_ref = false;
-	} else if (dev_net(dev) != wg->creating_net &&
-		   !wg->have_creating_net_ref) {
-		wg->have_creating_net_ref = true;
-		get_net(wg->creating_net);
+	rtnl_lock();
+	list_for_each_entry(wg, &device_list, device_list) {
+		if (rcu_access_pointer(wg->creating_net) == net) {
+			pr_debug("%s: Creating namespace exiting\n", wg->dev->name);
+			netif_carrier_off(wg->dev);
+			mutex_lock(&wg->device_update_lock);
+			rcu_assign_pointer(wg->creating_net, NULL);
+			wg_socket_reinit(wg, NULL, NULL);
+			mutex_unlock(&wg->device_update_lock);
+		}
 	}
-	return 0;
+	rtnl_unlock();
 }
 
-static struct notifier_block netdevice_notifier = {
-	.notifier_call = wg_netdevice_notification
+static struct pernet_operations pernet_ops = {
+	.pre_exit = wg_netns_pre_exit
 };
 
 int __init wg_device_init(void)
@@ -429,18 +425,18 @@ int __init wg_device_init(void)
 		return ret;
 #endif
 
-	ret = register_netdevice_notifier(&netdevice_notifier);
+	ret = register_pernet_device(&pernet_ops);
 	if (ret)
 		goto error_pm;
 
 	ret = rtnl_link_register(&link_ops);
 	if (ret)
-		goto error_netdevice;
+		goto error_pernet;
 
 	return 0;
 
-error_netdevice:
-	unregister_netdevice_notifier(&netdevice_notifier);
+error_pernet:
+	unregister_pernet_device(&pernet_ops);
 error_pm:
 #ifdef CONFIG_PM_SLEEP
 	unregister_pm_notifier(&pm_notifier);
@@ -451,7 +447,7 @@ error_pm:
 void wg_device_uninit(void)
 {
 	rtnl_link_unregister(&link_ops);
-	unregister_netdevice_notifier(&netdevice_notifier);
+	unregister_pernet_device(&pernet_ops);
 #ifdef CONFIG_PM_SLEEP
 	unregister_pm_notifier(&pm_notifier);
 #endif
diff --git a/drivers/net/wireguard/device.h b/drivers/net/wireguard/device.h
index b15a8be9d816..4d0144e16947 100644
--- a/drivers/net/wireguard/device.h
+++ b/drivers/net/wireguard/device.h
@@ -40,7 +40,7 @@ struct wg_device {
 	struct net_device *dev;
 	struct crypt_queue encrypt_queue, decrypt_queue;
 	struct sock __rcu *sock4, *sock6;
-	struct net *creating_net;
+	struct net __rcu *creating_net;
 	struct noise_static_identity static_identity;
 	struct workqueue_struct *handshake_receive_wq, *handshake_send_wq;
 	struct workqueue_struct *packet_crypt_wq;
@@ -56,7 +56,6 @@ struct wg_device {
 	unsigned int num_peers, device_update_gen;
 	u32 fwmark;
 	u16 incoming_port;
-	bool have_creating_net_ref;
 };
 
 int wg_device_init(void);
diff --git a/drivers/net/wireguard/netlink.c b/drivers/net/wireguard/netlink.c
index 802099c8828a..20a4f3c0a0a1 100644
--- a/drivers/net/wireguard/netlink.c
+++ b/drivers/net/wireguard/netlink.c
@@ -511,11 +511,15 @@ static int wg_set_device(struct sk_buff *skb, struct genl_info *info)
 	if (flags & ~__WGDEVICE_F_ALL)
 		goto out;
 
-	ret = -EPERM;
-	if ((info->attrs[WGDEVICE_A_LISTEN_PORT] ||
-	     info->attrs[WGDEVICE_A_FWMARK]) &&
-	    !ns_capable(wg->creating_net->user_ns, CAP_NET_ADMIN))
-		goto out;
+	if (info->attrs[WGDEVICE_A_LISTEN_PORT] || info->attrs[WGDEVICE_A_FWMARK]) {
+		struct net *net;
+		rcu_read_lock();
+		net = rcu_dereference(wg->creating_net);
+		ret = !net || !ns_capable(net->user_ns, CAP_NET_ADMIN) ? -EPERM : 0;
+		rcu_read_unlock();
+		if (ret)
+			goto out;
+	}
 
 	++wg->device_update_gen;
 
diff --git a/drivers/net/wireguard/noise.c b/drivers/net/wireguard/noise.c
index 626433690abb..201a22681945 100644
--- a/drivers/net/wireguard/noise.c
+++ b/drivers/net/wireguard/noise.c
@@ -617,8 +617,8 @@ wg_noise_handshake_consume_initiation(struct message_handshake_initiation *src,
 	memcpy(handshake->hash, hash, NOISE_HASH_LEN);
 	memcpy(handshake->chaining_key, chaining_key, NOISE_HASH_LEN);
 	handshake->remote_index = src->sender_index;
-	if ((s64)(handshake->last_initiation_consumption -
-	    (initiation_consumption = ktime_get_coarse_boottime_ns())) < 0)
+	initiation_consumption = ktime_get_coarse_boottime_ns();
+	if ((s64)(handshake->last_initiation_consumption - initiation_consumption) < 0)
 		handshake->last_initiation_consumption = initiation_consumption;
 	handshake->state = HANDSHAKE_CONSUMED_INITIATION;
 	up_write(&handshake->lock);
diff --git a/drivers/net/wireguard/receive.c b/drivers/net/wireguard/receive.c
index 91438144e4f7..9b2ab6fc91cd 100644
--- a/drivers/net/wireguard/receive.c
+++ b/drivers/net/wireguard/receive.c
@@ -414,14 +414,8 @@ static void wg_packet_consume_data_done(struct wg_peer *peer,
 	if (unlikely(routed_peer != peer))
 		goto dishonest_packet_peer;
 
-	if (unlikely(napi_gro_receive(&peer->napi, skb) == GRO_DROP)) {
-		++dev->stats.rx_dropped;
-		net_dbg_ratelimited("%s: Failed to give packet to userspace from peer %llu (%pISpfsc)\n",
-				    dev->name, peer->internal_id,
-				    &peer->endpoint.addr);
-	} else {
-		update_rx_stats(peer, message_data_len(len_before_trim));
-	}
+	napi_gro_receive(&peer->napi, skb);
+	update_rx_stats(peer, message_data_len(len_before_trim));
 	return;
 
 dishonest_packet_peer:
diff --git a/drivers/net/wireguard/socket.c b/drivers/net/wireguard/socket.c
index f9018027fc13..c33e2c81635f 100644
--- a/drivers/net/wireguard/socket.c
+++ b/drivers/net/wireguard/socket.c
@@ -347,6 +347,7 @@ static void set_sock_opts(struct socket *sock)
 
 int wg_socket_init(struct wg_device *wg, u16 port)
 {
+	struct net *net;
 	int ret;
 	struct udp_tunnel_sock_cfg cfg = {
 		.sk_user_data = wg,
@@ -371,37 +372,47 @@ int wg_socket_init(struct wg_device *wg, u16 port)
 	};
 #endif
 
+	rcu_read_lock();
+	net = rcu_dereference(wg->creating_net);
+	net = net ? maybe_get_net(net) : NULL;
+	rcu_read_unlock();
+	if (unlikely(!net))
+		return -ENONET;
+
 #if IS_ENABLED(CONFIG_IPV6)
 retry:
 #endif
 
-	ret = udp_sock_create(wg->creating_net, &port4, &new4);
+	ret = udp_sock_create(net, &port4, &new4);
 	if (ret < 0) {
 		pr_err("%s: Could not create IPv4 socket\n", wg->dev->name);
-		return ret;
+		goto out;
 	}
 	set_sock_opts(new4);
-	setup_udp_tunnel_sock(wg->creating_net, new4, &cfg);
+	setup_udp_tunnel_sock(net, new4, &cfg);
 
 #if IS_ENABLED(CONFIG_IPV6)
 	if (ipv6_mod_enabled()) {
 		port6.local_udp_port = inet_sk(new4->sk)->inet_sport;
-		ret = udp_sock_create(wg->creating_net, &port6, &new6);
+		ret = udp_sock_create(net, &port6, &new6);
 		if (ret < 0) {
 			udp_tunnel_sock_release(new4);
 			if (ret == -EADDRINUSE && !port && retries++ < 100)
 				goto retry;
 			pr_err("%s: Could not create IPv6 socket\n",
 			       wg->dev->name);
-			return ret;
+			goto out;
 		}
 		set_sock_opts(new6);
-		setup_udp_tunnel_sock(wg->creating_net, new6, &cfg);
+		setup_udp_tunnel_sock(net, new6, &cfg);
 	}
 #endif
 
 	wg_socket_reinit(wg, new4->sk, new6 ? new6->sk : NULL);
-	return 0;
+	ret = 0;
+out:
+	put_net(net);
+	return ret;
 }
 
 void wg_socket_reinit(struct wg_device *wg, struct sock *new4,
diff --git a/drivers/net/wireless/ath/wil6210/txrx.c b/drivers/net/wireless/ath/wil6210/txrx.c
index bc8c15fb609d..080e5aa60bea 100644
--- a/drivers/net/wireless/ath/wil6210/txrx.c
+++ b/drivers/net/wireless/ath/wil6210/txrx.c
@@ -897,7 +897,6 @@ static void wil_rx_handle_eapol(struct wil6210_vif *vif, struct sk_buff *skb)
 void wil_netif_rx(struct sk_buff *skb, struct net_device *ndev, int cid,
 		  struct wil_net_stats *stats, bool gro)
 {
-	gro_result_t rc = GRO_NORMAL;
 	struct wil6210_vif *vif = ndev_to_vif(ndev);
 	struct wil6210_priv *wil = ndev_to_wil(ndev);
 	struct wireless_dev *wdev = vif_to_wdev(vif);
@@ -908,22 +907,16 @@ void wil_netif_rx(struct sk_buff *skb, struct net_device *ndev, int cid,
 	 */
 	int mcast = is_multicast_ether_addr(da);
 	struct sk_buff *xmit_skb = NULL;
-	static const char * const gro_res_str[] = {
-		[GRO_MERGED]		= "GRO_MERGED",
-		[GRO_MERGED_FREE]	= "GRO_MERGED_FREE",
-		[GRO_HELD]		= "GRO_HELD",
-		[GRO_NORMAL]		= "GRO_NORMAL",
-		[GRO_DROP]		= "GRO_DROP",
-		[GRO_CONSUMED]		= "GRO_CONSUMED",
-	};
 
 	if (wdev->iftype == NL80211_IFTYPE_STATION) {
 		sa = wil_skb_get_sa(skb);
 		if (mcast && ether_addr_equal(sa, ndev->dev_addr)) {
 			/* mcast packet looped back to us */
-			rc = GRO_DROP;
 			dev_kfree_skb(skb);
-			goto stats;
+			ndev->stats.rx_dropped++;
+			stats->rx_dropped++;
+			wil_dbg_txrx(wil, "Rx drop %d bytes\n", len);
+			return;
 		}
 	} else if (wdev->iftype == NL80211_IFTYPE_AP && !vif->ap_isolate) {
 		if (mcast) {
@@ -967,26 +960,16 @@ void wil_netif_rx(struct sk_buff *skb, struct net_device *ndev, int cid,
 			wil_rx_handle_eapol(vif, skb);
 
 		if (gro)
-			rc = napi_gro_receive(&wil->napi_rx, skb);
+			napi_gro_receive(&wil->napi_rx, skb);
 		else
 			netif_rx_ni(skb);
-		wil_dbg_txrx(wil, "Rx complete %d bytes => %s\n",
-			     len, gro_res_str[rc]);
-	}
-stats:
-	/* statistics. rc set to GRO_NORMAL for AP bridging */
-	if (unlikely(rc == GRO_DROP)) {
-		ndev->stats.rx_dropped++;
-		stats->rx_dropped++;
-		wil_dbg_txrx(wil, "Rx drop %d bytes\n", len);
-	} else {
-		ndev->stats.rx_packets++;
-		stats->rx_packets++;
-		ndev->stats.rx_bytes += len;
-		stats->rx_bytes += len;
-		if (mcast)
-			ndev->stats.multicast++;
 	}
+	ndev->stats.rx_packets++;
+	stats->rx_packets++;
+	ndev->stats.rx_bytes += len;
+	stats->rx_bytes += len;
+	if (mcast)
+		ndev->stats.multicast++;
 }
 
 void wil_netif_rx_any(struct sk_buff *skb, struct net_device *ndev)
diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c
index ccbb5b43b8b2..4502f9c4708d 100644
--- a/drivers/nvdimm/region_devs.c
+++ b/drivers/nvdimm/region_devs.c
@@ -679,18 +679,8 @@ static umode_t region_visible(struct kobject *kobj, struct attribute *a, int n)
 		return a->mode;
 	}
 
-	if (a == &dev_attr_align.attr) {
-		int i;
-
-		for (i = 0; i < nd_region->ndr_mappings; i++) {
-			struct nd_mapping *nd_mapping = &nd_region->mapping[i];
-			struct nvdimm *nvdimm = nd_mapping->nvdimm;
-
-			if (test_bit(NDD_LABELING, &nvdimm->flags))
-				return a->mode;
-		}
-		return 0;
-	}
+	if (a == &dev_attr_align.attr)
+		return a->mode;
 
 	if (a != &dev_attr_set_cookie.attr
 			&& a != &dev_attr_available_size.attr)
diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c
index f5c46c72f4d3..eb84507de28a 100644
--- a/drivers/of/of_mdio.c
+++ b/drivers/of/of_mdio.c
@@ -314,10 +314,15 @@ int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np)
 				 child, addr);
 
 			if (of_mdiobus_child_is_phy(child)) {
+				/* -ENODEV is the return code that PHYLIB has
+				 * standardized on to indicate that bus
+				 * scanning should continue.
+				 */
 				rc = of_mdiobus_register_phy(mdio, child, addr);
-				if (rc && rc != -ENODEV)
+				if (!rc)
+					break;
+				if (rc != -ENODEV)
 					goto unregister;
-				break;
 			}
 		}
 	}
diff --git a/drivers/pinctrl/freescale/pinctrl-imx.c b/drivers/pinctrl/freescale/pinctrl-imx.c
index cb7e0f08d2cf..1f81569c7ae3 100644
--- a/drivers/pinctrl/freescale/pinctrl-imx.c
+++ b/drivers/pinctrl/freescale/pinctrl-imx.c
@@ -824,13 +824,12 @@ int imx_pinctrl_probe(struct platform_device *pdev,
 				return -EINVAL;
 			}
 
-			ipctl->input_sel_base = devm_of_iomap(&pdev->dev, np,
-							      0, NULL);
+			ipctl->input_sel_base = of_iomap(np, 0);
 			of_node_put(np);
-			if (IS_ERR(ipctl->input_sel_base)) {
+			if (!ipctl->input_sel_base) {
 				dev_err(&pdev->dev,
 					"iomuxc input select base address not found\n");
-				return PTR_ERR(ipctl->input_sel_base);
+				return -ENOMEM;
 			}
 		}
 	}
diff --git a/drivers/pinctrl/pinctrl-mcp23s08_spi.c b/drivers/pinctrl/pinctrl-mcp23s08_spi.c
index e06fb885fd2b..1f47a661b0a7 100644
--- a/drivers/pinctrl/pinctrl-mcp23s08_spi.c
+++ b/drivers/pinctrl/pinctrl-mcp23s08_spi.c
@@ -126,10 +126,7 @@ static int mcp23s08_spi_regmap_init(struct mcp23s08 *mcp, struct device *dev,
 	copy->name = name;
 
 	mcp->regmap = devm_regmap_init(dev, &mcp23sxx_spi_regmap, mcp, copy);
-	if (IS_ERR(mcp->regmap))
-		return PTR_ERR(mcp->regmap);
-
-	return 0;
+	return PTR_ERR_OR_ZERO(mcp->regmap);
 }
 
 static int mcp23s08_probe(struct spi_device *spi)
diff --git a/drivers/pinctrl/pinctrl-single.c b/drivers/pinctrl/pinctrl-single.c
index 1e0614daee9b..f3a8a465d27e 100644
--- a/drivers/pinctrl/pinctrl-single.c
+++ b/drivers/pinctrl/pinctrl-single.c
@@ -958,7 +958,7 @@ static int pcs_parse_pinconf(struct pcs_device *pcs, struct device_node *np,
 }
 
 /**
- * smux_parse_one_pinctrl_entry() - parses a device tree mux entry
+ * pcs_parse_one_pinctrl_entry() - parses a device tree mux entry
  * @pctldev: pin controller device
  * @pcs: pinctrl driver instance
  * @np: device node of the mux entry
diff --git a/drivers/pinctrl/qcom/pinctrl-ipq6018.c b/drivers/pinctrl/qcom/pinctrl-ipq6018.c
index 38c33a778cb8..ec50a3b4bd16 100644
--- a/drivers/pinctrl/qcom/pinctrl-ipq6018.c
+++ b/drivers/pinctrl/qcom/pinctrl-ipq6018.c
@@ -367,7 +367,8 @@ static const char * const wci20_groups[] = {
 
 static const char * const qpic_pad_groups[] = {
 	"gpio0", "gpio1", "gpio2", "gpio3", "gpio4", "gpio9", "gpio10",
-	"gpio11", "gpio17",
+	"gpio11", "gpio17", "gpio15", "gpio12", "gpio13", "gpio14", "gpio5",
+	"gpio6", "gpio7", "gpio8",
 };
 
 static const char * const burn0_groups[] = {
diff --git a/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c b/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c
index fe0be8a6ebb7..092a48e4dff5 100644
--- a/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c
+++ b/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c
@@ -170,6 +170,7 @@ struct pmic_gpio_state {
 	struct regmap	*map;
 	struct pinctrl_dev *ctrl;
 	struct gpio_chip chip;
+	struct irq_chip irq;
 };
 
 static const struct pinconf_generic_params pmic_gpio_bindings[] = {
@@ -917,16 +918,6 @@ static int pmic_gpio_populate(struct pmic_gpio_state *state,
 	return 0;
 }
 
-static struct irq_chip pmic_gpio_irq_chip = {
-	.name = "spmi-gpio",
-	.irq_ack = irq_chip_ack_parent,
-	.irq_mask = irq_chip_mask_parent,
-	.irq_unmask = irq_chip_unmask_parent,
-	.irq_set_type = irq_chip_set_type_parent,
-	.irq_set_wake = irq_chip_set_wake_parent,
-	.flags = IRQCHIP_MASK_ON_SUSPEND,
-};
-
 static int pmic_gpio_domain_translate(struct irq_domain *domain,
 				      struct irq_fwspec *fwspec,
 				      unsigned long *hwirq,
@@ -1053,8 +1044,16 @@ static int pmic_gpio_probe(struct platform_device *pdev)
 	if (!parent_domain)
 		return -ENXIO;
 
+	state->irq.name = "spmi-gpio",
+	state->irq.irq_ack = irq_chip_ack_parent,
+	state->irq.irq_mask = irq_chip_mask_parent,
+	state->irq.irq_unmask = irq_chip_unmask_parent,
+	state->irq.irq_set_type = irq_chip_set_type_parent,
+	state->irq.irq_set_wake = irq_chip_set_wake_parent,
+	state->irq.flags = IRQCHIP_MASK_ON_SUSPEND,
+
 	girq = &state->chip.irq;
-	girq->chip = &pmic_gpio_irq_chip;
+	girq->chip = &state->irq;
 	girq->default_type = IRQ_TYPE_NONE;
 	girq->handler = handle_level_irq;
 	girq->fwnode = of_node_to_fwnode(state->dev->of_node);
diff --git a/drivers/pinctrl/tegra/pinctrl-tegra.c b/drivers/pinctrl/tegra/pinctrl-tegra.c
index 21661f6490d6..195cfe557511 100644
--- a/drivers/pinctrl/tegra/pinctrl-tegra.c
+++ b/drivers/pinctrl/tegra/pinctrl-tegra.c
@@ -731,8 +731,8 @@ static int tegra_pinctrl_resume(struct device *dev)
 }
 
 const struct dev_pm_ops tegra_pinctrl_pm = {
-	.suspend = &tegra_pinctrl_suspend,
-	.resume = &tegra_pinctrl_resume
+	.suspend_noirq = &tegra_pinctrl_suspend,
+	.resume_noirq = &tegra_pinctrl_resume
 };
 
 static bool tegra_pinctrl_gpio_node_has_range(struct tegra_pmx *pmx)
diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig
index 8f677f5d79b4..edb1c4f8b496 100644
--- a/drivers/regulator/Kconfig
+++ b/drivers/regulator/Kconfig
@@ -684,7 +684,7 @@ config REGULATOR_MT6323
 
 config REGULATOR_MT6358
 	tristate "MediaTek MT6358 PMIC"
-	depends on MFD_MT6397 && BROKEN
+	depends on MFD_MT6397
 	help
 	  Say y here to select this option to enable the power regulator of
 	  MediaTek MT6358 PMIC.
diff --git a/drivers/regulator/da9063-regulator.c b/drivers/regulator/da9063-regulator.c
index e1d6c8f6d40b..fe65b5acaf28 100644
--- a/drivers/regulator/da9063-regulator.c
+++ b/drivers/regulator/da9063-regulator.c
@@ -512,7 +512,6 @@ static const struct da9063_regulator_info da9063_regulator_info[] = {
 	},
 	{
 		DA9063_LDO(DA9063, LDO9, 950, 50, 3600),
-		.suspend = BFIELD(DA9063_REG_LDO9_CONT, DA9063_VLDO9_SEL),
 	},
 	{
 		DA9063_LDO(DA9063, LDO11, 900, 50, 3600),
diff --git a/drivers/regulator/helpers.c b/drivers/regulator/helpers.c
index e970e9d2f8be..e4bb09bbd3fa 100644
--- a/drivers/regulator/helpers.c
+++ b/drivers/regulator/helpers.c
@@ -486,7 +486,7 @@ int regulator_map_voltage_pickable_linear_range(struct regulator_dev *rdev,
 			continue;
 		}
 
-		ret = selector + sel;
+		ret = selector + sel - range->min_sel;
 
 		voltage = rdev->desc->ops->list_voltage(rdev, ret);
 
diff --git a/drivers/regulator/pfuze100-regulator.c b/drivers/regulator/pfuze100-regulator.c
index 689537927f6f..4c8e8b472287 100644
--- a/drivers/regulator/pfuze100-regulator.c
+++ b/drivers/regulator/pfuze100-regulator.c
@@ -209,6 +209,19 @@ static const struct regulator_ops pfuze100_swb_regulator_ops = {
 
 };
 
+static const struct regulator_ops pfuze3000_sw_regulator_ops = {
+	.enable = regulator_enable_regmap,
+	.disable = regulator_disable_regmap,
+	.is_enabled = regulator_is_enabled_regmap,
+	.list_voltage = regulator_list_voltage_table,
+	.map_voltage = regulator_map_voltage_ascend,
+	.set_voltage_sel = regulator_set_voltage_sel_regmap,
+	.get_voltage_sel = regulator_get_voltage_sel_regmap,
+	.set_voltage_time_sel = regulator_set_voltage_time_sel,
+	.set_ramp_delay = pfuze100_set_ramp_delay,
+
+};
+
 #define PFUZE100_FIXED_REG(_chip, _name, base, voltage)	\
 	[_chip ## _ ## _name] = {	\
 		.desc = {	\
@@ -318,23 +331,28 @@ static const struct regulator_ops pfuze100_swb_regulator_ops = {
 	.stby_mask = 0x20,	\
 }
 
-
-#define PFUZE3000_SW2_REG(_chip, _name, base, min, max, step)	{	\
-	.desc = {	\
-		.name = #_name,\
-		.n_voltages = ((max) - (min)) / (step) + 1,	\
-		.ops = &pfuze100_sw_regulator_ops,	\
-		.type = REGULATOR_VOLTAGE,	\
-		.id = _chip ## _ ## _name,	\
-		.owner = THIS_MODULE,	\
-		.min_uV = (min),	\
-		.uV_step = (step),	\
-		.vsel_reg = (base) + PFUZE100_VOL_OFFSET,	\
-		.vsel_mask = 0x7,	\
-	},	\
-	.stby_reg = (base) + PFUZE100_STANDBY_OFFSET,	\
-	.stby_mask = 0x7,	\
-}
+/* No linar case for the some switches of PFUZE3000 */
+#define PFUZE3000_SW_REG(_chip, _name, base, mask, voltages)	\
+	[_chip ## _ ##  _name] = {	\
+		.desc = {	\
+			.name = #_name,	\
+			.n_voltages = ARRAY_SIZE(voltages),	\
+			.ops = &pfuze3000_sw_regulator_ops,	\
+			.type = REGULATOR_VOLTAGE,	\
+			.id = _chip ## _ ## _name,	\
+			.owner = THIS_MODULE,	\
+			.volt_table = voltages,	\
+			.vsel_reg = (base) + PFUZE100_VOL_OFFSET,	\
+			.vsel_mask = (mask),	\
+			.enable_reg = (base) + PFUZE100_MODE_OFFSET,	\
+			.enable_mask = 0xf,	\
+			.enable_val = 0x8,	\
+			.enable_time = 500,	\
+		},	\
+		.stby_reg = (base) + PFUZE100_STANDBY_OFFSET,	\
+		.stby_mask = (mask),	\
+		.sw_reg = true,		\
+	}
 
 #define PFUZE3000_SW3_REG(_chip, _name, base, min, max, step)	{	\
 	.desc = {	\
@@ -391,9 +409,9 @@ static struct pfuze_regulator pfuze200_regulators[] = {
 };
 
 static struct pfuze_regulator pfuze3000_regulators[] = {
-	PFUZE100_SWB_REG(PFUZE3000, SW1A, PFUZE100_SW1ABVOL, 0x1f, pfuze3000_sw1a),
+	PFUZE3000_SW_REG(PFUZE3000, SW1A, PFUZE100_SW1ABVOL, 0x1f, pfuze3000_sw1a),
 	PFUZE100_SW_REG(PFUZE3000, SW1B, PFUZE100_SW1CVOL, 700000, 1475000, 25000),
-	PFUZE100_SWB_REG(PFUZE3000, SW2, PFUZE100_SW2VOL, 0x7, pfuze3000_sw2lo),
+	PFUZE3000_SW_REG(PFUZE3000, SW2, PFUZE100_SW2VOL, 0x7, pfuze3000_sw2lo),
 	PFUZE3000_SW3_REG(PFUZE3000, SW3, PFUZE100_SW3AVOL, 900000, 1650000, 50000),
 	PFUZE100_SWB_REG(PFUZE3000, SWBST, PFUZE100_SWBSTCON1, 0x3, pfuze100_swbst),
 	PFUZE100_SWB_REG(PFUZE3000, VSNVS, PFUZE100_VSNVSVOL, 0x7, pfuze100_vsnvs),
@@ -407,8 +425,8 @@ static struct pfuze_regulator pfuze3000_regulators[] = {
 };
 
 static struct pfuze_regulator pfuze3001_regulators[] = {
-	PFUZE100_SWB_REG(PFUZE3001, SW1, PFUZE100_SW1ABVOL, 0x1f, pfuze3000_sw1a),
-	PFUZE100_SWB_REG(PFUZE3001, SW2, PFUZE100_SW2VOL, 0x7, pfuze3000_sw2lo),
+	PFUZE3000_SW_REG(PFUZE3001, SW1, PFUZE100_SW1ABVOL, 0x1f, pfuze3000_sw1a),
+	PFUZE3000_SW_REG(PFUZE3001, SW2, PFUZE100_SW2VOL, 0x7, pfuze3000_sw2lo),
 	PFUZE3000_SW3_REG(PFUZE3001, SW3, PFUZE100_SW3AVOL, 900000, 1650000, 50000),
 	PFUZE100_SWB_REG(PFUZE3001, VSNVS, PFUZE100_VSNVSVOL, 0x7, pfuze100_vsnvs),
 	PFUZE100_VGEN_REG(PFUZE3001, VLDO1, PFUZE100_VGEN1VOL, 1800000, 3300000, 100000),
diff --git a/drivers/s390/cio/qdio.h b/drivers/s390/cio/qdio.h
index eb13c479e11d..bb1c8402c67d 100644
--- a/drivers/s390/cio/qdio.h
+++ b/drivers/s390/cio/qdio.h
@@ -182,10 +182,9 @@ enum qdio_irq_poll_states {
 };
 
 struct qdio_input_q {
-	/* first ACK'ed buffer */
-	int ack_start;
-	/* how many SBALs are acknowledged */
-	int ack_count;
+	/* Batch of SBALs that we processed while polling the queue: */
+	unsigned int batch_start;
+	unsigned int batch_count;
 	/* last time of noticing incoming data */
 	u64 timestamp;
 };
diff --git a/drivers/s390/cio/qdio_debug.c b/drivers/s390/cio/qdio_debug.c
index 286b044fb027..da95c923d81a 100644
--- a/drivers/s390/cio/qdio_debug.c
+++ b/drivers/s390/cio/qdio_debug.c
@@ -110,8 +110,8 @@ static int qstat_show(struct seq_file *m, void *v)
 	seq_printf(m, "nr_used: %d  ftc: %d\n",
 		   atomic_read(&q->nr_buf_used), q->first_to_check);
 	if (q->is_input_q) {
-		seq_printf(m, "ack start: %d  ack count: %d\n",
-			   q->u.in.ack_start, q->u.in.ack_count);
+		seq_printf(m, "batch start: %u  batch count: %u\n",
+			   q->u.in.batch_start, q->u.in.batch_count);
 		seq_printf(m, "DSCI: %x   IRQs disabled: %u\n",
 			   *(u8 *)q->irq_ptr->dsci,
 			   test_bit(QDIO_IRQ_DISABLED,
diff --git a/drivers/s390/cio/qdio_main.c b/drivers/s390/cio/qdio_main.c
index 610c05f59589..0c919a11a46e 100644
--- a/drivers/s390/cio/qdio_main.c
+++ b/drivers/s390/cio/qdio_main.c
@@ -254,10 +254,17 @@ static inline int set_buf_states(struct qdio_q *q, int bufnr,
 	if (is_qebsm(q))
 		return qdio_do_sqbs(q, state, bufnr, count);
 
+	/* Ensure that all preceding changes to the SBALs are visible: */
+	mb();
+
 	for (i = 0; i < count; i++) {
-		xchg(&q->slsb.val[bufnr], state);
+		WRITE_ONCE(q->slsb.val[bufnr], state);
 		bufnr = next_buf(bufnr);
 	}
+
+	/* Make our SLSB changes visible: */
+	mb();
+
 	return count;
 }
 
@@ -393,15 +400,15 @@ int debug_get_buf_state(struct qdio_q *q, unsigned int bufnr,
 
 static inline void qdio_stop_polling(struct qdio_q *q)
 {
-	if (!q->u.in.ack_count)
+	if (!q->u.in.batch_count)
 		return;
 
 	qperf_inc(q, stop_polling);
 
 	/* show the card that we are not polling anymore */
-	set_buf_states(q, q->u.in.ack_start, SLSB_P_INPUT_NOT_INIT,
-		       q->u.in.ack_count);
-	q->u.in.ack_count = 0;
+	set_buf_states(q, q->u.in.batch_start, SLSB_P_INPUT_NOT_INIT,
+		       q->u.in.batch_count);
+	q->u.in.batch_count = 0;
 }
 
 static inline void account_sbals(struct qdio_q *q, unsigned int count)
@@ -441,42 +448,13 @@ static void process_buffer_error(struct qdio_q *q, unsigned int start,
 static inline void inbound_handle_work(struct qdio_q *q, unsigned int start,
 				       int count, bool auto_ack)
 {
-	int new;
-
-	if (auto_ack) {
-		if (!q->u.in.ack_count) {
-			q->u.in.ack_count = count;
-			q->u.in.ack_start = start;
-			return;
-		}
-
-		/* delete the previous ACK's */
-		set_buf_states(q, q->u.in.ack_start, SLSB_P_INPUT_NOT_INIT,
-			       q->u.in.ack_count);
-		q->u.in.ack_count = count;
-		q->u.in.ack_start = start;
-		return;
-	}
-
-	/*
-	 * ACK the newest buffer. The ACK will be removed in qdio_stop_polling
-	 * or by the next inbound run.
-	 */
-	new = add_buf(start, count - 1);
-	set_buf_state(q, new, SLSB_P_INPUT_ACK);
-
-	/* delete the previous ACKs */
-	if (q->u.in.ack_count)
-		set_buf_states(q, q->u.in.ack_start, SLSB_P_INPUT_NOT_INIT,
-			       q->u.in.ack_count);
+	/* ACK the newest SBAL: */
+	if (!auto_ack)
+		set_buf_state(q, add_buf(start, count - 1), SLSB_P_INPUT_ACK);
 
-	q->u.in.ack_count = 1;
-	q->u.in.ack_start = new;
-	count--;
-	if (!count)
-		return;
-	/* need to change ALL buffers to get more interrupts */
-	set_buf_states(q, start, SLSB_P_INPUT_NOT_INIT, count);
+	if (!q->u.in.batch_count)
+		q->u.in.batch_start = start;
+	q->u.in.batch_count += count;
 }
 
 static int get_inbound_buffer_frontier(struct qdio_q *q, unsigned int start)
@@ -525,15 +503,18 @@ static int get_inbound_buffer_frontier(struct qdio_q *q, unsigned int start)
 			account_sbals_error(q, count);
 		return count;
 	case SLSB_CU_INPUT_EMPTY:
-	case SLSB_P_INPUT_NOT_INIT:
-	case SLSB_P_INPUT_ACK:
 		if (q->irq_ptr->perf_stat_enabled)
 			q->q_stats.nr_sbal_nop++;
 		DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "in nop:%1d %#02x",
 			      q->nr, start);
 		return 0;
+	case SLSB_P_INPUT_NOT_INIT:
+	case SLSB_P_INPUT_ACK:
+		/* We should never see this state, throw a WARN: */
 	default:
-		WARN_ON_ONCE(1);
+		dev_WARN_ONCE(&q->irq_ptr->cdev->dev, 1,
+			      "found state %#x at index %u on queue %u\n",
+			      state, start, q->nr);
 		return 0;
 	}
 }
@@ -738,11 +719,14 @@ static int get_outbound_buffer_frontier(struct qdio_q *q, unsigned int start)
 		DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "out primed:%1d",
 			      q->nr);
 		return 0;
-	case SLSB_P_OUTPUT_NOT_INIT:
 	case SLSB_P_OUTPUT_HALTED:
 		return 0;
+	case SLSB_P_OUTPUT_NOT_INIT:
+		/* We should never see this state, throw a WARN: */
 	default:
-		WARN_ON_ONCE(1);
+		dev_WARN_ONCE(&q->irq_ptr->cdev->dev, 1,
+			      "found state %#x at index %u on queue %u\n",
+			      state, start, q->nr);
 		return 0;
 	}
 }
@@ -938,10 +922,10 @@ static void qdio_int_handler_pci(struct qdio_irq *irq_ptr)
 	}
 }
 
-static void qdio_handle_activate_check(struct ccw_device *cdev,
-				unsigned long intparm, int cstat, int dstat)
+static void qdio_handle_activate_check(struct qdio_irq *irq_ptr,
+				       unsigned long intparm, int cstat,
+				       int dstat)
 {
-	struct qdio_irq *irq_ptr = cdev->private->qdio_data;
 	struct qdio_q *q;
 
 	DBF_ERROR("%4x ACT CHECK", irq_ptr->schid.sch_no);
@@ -968,11 +952,9 @@ no_handler:
 	lgr_info_log();
 }
 
-static void qdio_establish_handle_irq(struct ccw_device *cdev, int cstat,
+static void qdio_establish_handle_irq(struct qdio_irq *irq_ptr, int cstat,
 				      int dstat)
 {
-	struct qdio_irq *irq_ptr = cdev->private->qdio_data;
-
 	DBF_DEV_EVENT(DBF_INFO, irq_ptr, "qest irq");
 
 	if (cstat)
@@ -1019,7 +1001,7 @@ void qdio_int_handler(struct ccw_device *cdev, unsigned long intparm,
 
 	switch (irq_ptr->state) {
 	case QDIO_IRQ_STATE_INACTIVE:
-		qdio_establish_handle_irq(cdev, cstat, dstat);
+		qdio_establish_handle_irq(irq_ptr, cstat, dstat);
 		break;
 	case QDIO_IRQ_STATE_CLEANUP:
 		qdio_set_state(irq_ptr, QDIO_IRQ_STATE_INACTIVE);
@@ -1031,7 +1013,7 @@ void qdio_int_handler(struct ccw_device *cdev, unsigned long intparm,
 			return;
 		}
 		if (cstat || dstat)
-			qdio_handle_activate_check(cdev, intparm, cstat,
+			qdio_handle_activate_check(irq_ptr, intparm, cstat,
 						   dstat);
 		break;
 	case QDIO_IRQ_STATE_STOPPED:
@@ -1446,12 +1428,12 @@ static int handle_inbound(struct qdio_q *q, unsigned int callflags,
 
 	qperf_inc(q, inbound_call);
 
-	/* If any ACKed SBALs are returned to HW, adjust ACK tracking: */
-	overlap = min(count - sub_buf(q->u.in.ack_start, bufnr),
-		      q->u.in.ack_count);
+	/* If any processed SBALs are returned to HW, adjust our tracking: */
+	overlap = min_t(int, count - sub_buf(q->u.in.batch_start, bufnr),
+			     q->u.in.batch_count);
 	if (overlap > 0) {
-		q->u.in.ack_start = add_buf(q->u.in.ack_start, overlap);
-		q->u.in.ack_count -= overlap;
+		q->u.in.batch_start = add_buf(q->u.in.batch_start, overlap);
+		q->u.in.batch_count -= overlap;
 	}
 
 	count = set_buf_states(q, bufnr, SLSB_CU_INPUT_EMPTY, count);
@@ -1535,12 +1517,11 @@ static int handle_outbound(struct qdio_q *q, unsigned int callflags,
 int do_QDIO(struct ccw_device *cdev, unsigned int callflags,
 	    int q_nr, unsigned int bufnr, unsigned int count)
 {
-	struct qdio_irq *irq_ptr;
+	struct qdio_irq *irq_ptr = cdev->private->qdio_data;
 
 	if (bufnr >= QDIO_MAX_BUFFERS_PER_Q || count > QDIO_MAX_BUFFERS_PER_Q)
 		return -EINVAL;
 
-	irq_ptr = cdev->private->qdio_data;
 	if (!irq_ptr)
 		return -ENODEV;
 
diff --git a/drivers/s390/crypto/zcrypt_ep11misc.c b/drivers/s390/crypto/zcrypt_ep11misc.c
index 004ce022fc78..3c3d403abe92 100644
--- a/drivers/s390/crypto/zcrypt_ep11misc.c
+++ b/drivers/s390/crypto/zcrypt_ep11misc.c
@@ -195,11 +195,10 @@ static inline struct ep11_cprb *alloc_cprb(size_t payload_len)
 	size_t len = sizeof(struct ep11_cprb) + payload_len;
 	struct ep11_cprb *cprb;
 
-	cprb = kmalloc(len, GFP_KERNEL);
+	cprb = kzalloc(len, GFP_KERNEL);
 	if (!cprb)
 		return NULL;
 
-	memset(cprb, 0, len);
 	cprb->cprb_len = sizeof(struct ep11_cprb);
 	cprb->cprb_ver_id = 0x04;
 	memcpy(cprb->func_id, "T4", 2);
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 18a0fb75a710..88e998de2d03 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -4544,9 +4544,6 @@ static int qeth_setadpparms_set_access_ctrl_cb(struct qeth_card *card,
 	int fallback = *(int *)reply->param;
 
 	QETH_CARD_TEXT(card, 4, "setaccb");
-	if (cmd->hdr.return_code)
-		return -EIO;
-	qeth_setadpparms_inspect_rc(cmd);
 
 	access_ctrl_req = &cmd->data.setadapterparms.data.set_access_ctrl;
 	QETH_CARD_TEXT_(card, 2, "rc=%d",
@@ -4556,7 +4553,7 @@ static int qeth_setadpparms_set_access_ctrl_cb(struct qeth_card *card,
 		QETH_DBF_MESSAGE(3, "ERR:SET_ACCESS_CTRL(%#x) on device %x: %#x\n",
 				 access_ctrl_req->subcmd_code, CARD_DEVID(card),
 				 cmd->data.setadapterparms.hdr.return_code);
-	switch (cmd->data.setadapterparms.hdr.return_code) {
+	switch (qeth_setadpparms_inspect_rc(cmd)) {
 	case SET_ACCESS_CTRL_RC_SUCCESS:
 		if (card->options.isolation == ISOLATION_MODE_NONE) {
 			dev_info(&card->gdev->dev,
@@ -6840,9 +6837,11 @@ netdev_features_t qeth_features_check(struct sk_buff *skb,
 				      struct net_device *dev,
 				      netdev_features_t features)
 {
+	struct qeth_card *card = dev->ml_priv;
+
 	/* Traffic with local next-hop is not eligible for some offloads: */
-	if (skb->ip_summed == CHECKSUM_PARTIAL) {
-		struct qeth_card *card = dev->ml_priv;
+	if (skb->ip_summed == CHECKSUM_PARTIAL &&
+	    card->options.isolation != ISOLATION_MODE_FWD) {
 		netdev_features_t restricted = 0;
 
 		if (skb_is_gso(skb) && !netif_needs_gso(skb, features))
diff --git a/drivers/s390/virtio/virtio_ccw.c b/drivers/s390/virtio/virtio_ccw.c
index 957889a42d2e..5730572b52cd 100644
--- a/drivers/s390/virtio/virtio_ccw.c
+++ b/drivers/s390/virtio/virtio_ccw.c
@@ -1372,27 +1372,6 @@ static struct ccw_device_id virtio_ids[] = {
 	{},
 };
 
-#ifdef CONFIG_PM_SLEEP
-static int virtio_ccw_freeze(struct ccw_device *cdev)
-{
-	struct virtio_ccw_device *vcdev = dev_get_drvdata(&cdev->dev);
-
-	return virtio_device_freeze(&vcdev->vdev);
-}
-
-static int virtio_ccw_restore(struct ccw_device *cdev)
-{
-	struct virtio_ccw_device *vcdev = dev_get_drvdata(&cdev->dev);
-	int ret;
-
-	ret = virtio_ccw_set_transport_rev(vcdev);
-	if (ret)
-		return ret;
-
-	return virtio_device_restore(&vcdev->vdev);
-}
-#endif
-
 static struct ccw_driver virtio_ccw_driver = {
 	.driver = {
 		.owner = THIS_MODULE,
@@ -1405,11 +1384,6 @@ static struct ccw_driver virtio_ccw_driver = {
 	.set_online = virtio_ccw_online,
 	.notify = virtio_ccw_cio_notify,
 	.int_class = IRQIO_VIR,
-#ifdef CONFIG_PM_SLEEP
-	.freeze = virtio_ccw_freeze,
-	.thaw = virtio_ccw_restore,
-	.restore = virtio_ccw_restore,
-#endif
 };
 
 static int __init pure_hex(char **cp, unsigned int *val, int min_digit,
diff --git a/drivers/scsi/aic94xx/aic94xx_init.c b/drivers/scsi/aic94xx/aic94xx_init.c
index d022407e5645..bef47f38dd0d 100644
--- a/drivers/scsi/aic94xx/aic94xx_init.c
+++ b/drivers/scsi/aic94xx/aic94xx_init.c
@@ -40,6 +40,7 @@ static struct scsi_host_template aic94xx_sht = {
 	/* .name is initialized */
 	.name			= "aic94xx",
 	.queuecommand		= sas_queuecommand,
+	.dma_need_drain		= ata_scsi_dma_need_drain,
 	.target_alloc		= sas_target_alloc,
 	.slave_configure	= sas_slave_configure,
 	.scan_finished		= asd_scan_finished,
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
index 2e1718f9ade2..09a7669dad4c 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
@@ -1756,6 +1756,7 @@ static struct scsi_host_template sht_v1_hw = {
 	.proc_name		= DRV_NAME,
 	.module			= THIS_MODULE,
 	.queuecommand		= sas_queuecommand,
+	.dma_need_drain		= ata_scsi_dma_need_drain,
 	.target_alloc		= sas_target_alloc,
 	.slave_configure	= hisi_sas_slave_configure,
 	.scan_finished		= hisi_sas_scan_finished,
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
index e7e7849a4c14..968d38702353 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
@@ -3532,6 +3532,7 @@ static struct scsi_host_template sht_v2_hw = {
 	.proc_name		= DRV_NAME,
 	.module			= THIS_MODULE,
 	.queuecommand		= sas_queuecommand,
+	.dma_need_drain		= ata_scsi_dma_need_drain,
 	.target_alloc		= sas_target_alloc,
 	.slave_configure	= hisi_sas_slave_configure,
 	.scan_finished		= hisi_sas_scan_finished,
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index 3e6b78a1f993..55e2321a65bc 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -3075,6 +3075,7 @@ static struct scsi_host_template sht_v3_hw = {
 	.proc_name		= DRV_NAME,
 	.module			= THIS_MODULE,
 	.queuecommand		= sas_queuecommand,
+	.dma_need_drain		= ata_scsi_dma_need_drain,
 	.target_alloc		= sas_target_alloc,
 	.slave_configure	= hisi_sas_slave_configure,
 	.scan_finished		= hisi_sas_scan_finished,
diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c
index 7d77997d26d4..7d86f4ca266c 100644
--- a/drivers/scsi/ipr.c
+++ b/drivers/scsi/ipr.c
@@ -6731,6 +6731,7 @@ static struct scsi_host_template driver_template = {
 	.compat_ioctl = ipr_ioctl,
 #endif
 	.queuecommand = ipr_queuecommand,
+	.dma_need_drain = ata_scsi_dma_need_drain,
 	.eh_abort_handler = ipr_eh_abort,
 	.eh_device_reset_handler = ipr_eh_dev_reset,
 	.eh_host_reset_handler = ipr_eh_host_reset,
diff --git a/drivers/scsi/isci/init.c b/drivers/scsi/isci/init.c
index 974c3b9116d5..085e285f427d 100644
--- a/drivers/scsi/isci/init.c
+++ b/drivers/scsi/isci/init.c
@@ -153,6 +153,7 @@ static struct scsi_host_template isci_sht = {
 	.name				= DRV_NAME,
 	.proc_name			= DRV_NAME,
 	.queuecommand			= sas_queuecommand,
+	.dma_need_drain			= ata_scsi_dma_need_drain,
 	.target_alloc			= sas_target_alloc,
 	.slave_configure		= sas_slave_configure,
 	.scan_finished			= isci_host_scan_finished,
diff --git a/drivers/scsi/mvsas/mv_init.c b/drivers/scsi/mvsas/mv_init.c
index 5973eed94938..b0de3bdb01db 100644
--- a/drivers/scsi/mvsas/mv_init.c
+++ b/drivers/scsi/mvsas/mv_init.c
@@ -33,6 +33,7 @@ static struct scsi_host_template mvs_sht = {
 	.module			= THIS_MODULE,
 	.name			= DRV_NAME,
 	.queuecommand		= sas_queuecommand,
+	.dma_need_drain		= ata_scsi_dma_need_drain,
 	.target_alloc		= sas_target_alloc,
 	.slave_configure	= sas_slave_configure,
 	.scan_finished		= mvs_scan_finished,
diff --git a/drivers/scsi/pm8001/pm8001_init.c b/drivers/scsi/pm8001/pm8001_init.c
index a8f5344fdfda..9e99262a2b9d 100644
--- a/drivers/scsi/pm8001/pm8001_init.c
+++ b/drivers/scsi/pm8001/pm8001_init.c
@@ -87,6 +87,7 @@ static struct scsi_host_template pm8001_sht = {
 	.module			= THIS_MODULE,
 	.name			= DRV_NAME,
 	.queuecommand		= sas_queuecommand,
+	.dma_need_drain		= ata_scsi_dma_need_drain,
 	.target_alloc		= sas_target_alloc,
 	.slave_configure	= sas_slave_configure,
 	.scan_finished		= pm8001_scan_finished,
diff --git a/drivers/scsi/ufs/ufs_bsg.c b/drivers/scsi/ufs/ufs_bsg.c
index 53dd87628cbe..516a7f573942 100644
--- a/drivers/scsi/ufs/ufs_bsg.c
+++ b/drivers/scsi/ufs/ufs_bsg.c
@@ -106,8 +106,10 @@ static int ufs_bsg_request(struct bsg_job *job)
 		desc_op = bsg_request->upiu_req.qr.opcode;
 		ret = ufs_bsg_alloc_desc_buffer(hba, job, &desc_buff,
 						&desc_len, desc_op);
-		if (ret)
+		if (ret) {
+			pm_runtime_put_sync(hba->dev);
 			goto out;
+		}
 
 		/* fall through */
 	case UPIU_TRANSACTION_NOP_OUT:
diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c
index a35faced0456..58190c94561f 100644
--- a/drivers/spi/spi-fsl-dspi.c
+++ b/drivers/spi/spi-fsl-dspi.c
@@ -588,14 +588,14 @@ static void dspi_release_dma(struct fsl_dspi *dspi)
 		return;
 
 	if (dma->chan_tx) {
-		dma_unmap_single(dma->chan_tx->device->dev, dma->tx_dma_phys,
-				 dma_bufsize, DMA_TO_DEVICE);
+		dma_free_coherent(dma->chan_tx->device->dev, dma_bufsize,
+				  dma->tx_dma_buf, dma->tx_dma_phys);
 		dma_release_channel(dma->chan_tx);
 	}
 
 	if (dma->chan_rx) {
-		dma_unmap_single(dma->chan_rx->device->dev, dma->rx_dma_phys,
-				 dma_bufsize, DMA_FROM_DEVICE);
+		dma_free_coherent(dma->chan_rx->device->dev, dma_bufsize,
+				  dma->rx_dma_buf, dma->rx_dma_phys);
 		dma_release_channel(dma->chan_rx);
 	}
 }
diff --git a/drivers/spi/spi-rspi.c b/drivers/spi/spi-rspi.c
index 06192c9ea813..cbc2387d450c 100644
--- a/drivers/spi/spi-rspi.c
+++ b/drivers/spi/spi-rspi.c
@@ -179,7 +179,7 @@
 
 struct rspi_data {
 	void __iomem *addr;
-	u32 max_speed_hz;
+	u32 speed_hz;
 	struct spi_controller *ctlr;
 	struct platform_device *pdev;
 	wait_queue_head_t wait;
@@ -258,8 +258,7 @@ static int rspi_set_config_register(struct rspi_data *rspi, int access_size)
 	rspi_write8(rspi, rspi->sppcr, RSPI_SPPCR);
 
 	/* Sets transfer bit rate */
-	spbr = DIV_ROUND_UP(clk_get_rate(rspi->clk),
-			    2 * rspi->max_speed_hz) - 1;
+	spbr = DIV_ROUND_UP(clk_get_rate(rspi->clk), 2 * rspi->speed_hz) - 1;
 	rspi_write8(rspi, clamp(spbr, 0, 255), RSPI_SPBR);
 
 	/* Disable dummy transmission, set 16-bit word access, 1 frame */
@@ -299,14 +298,14 @@ static int rspi_rz_set_config_register(struct rspi_data *rspi, int access_size)
 
 	clksrc = clk_get_rate(rspi->clk);
 	while (div < 3) {
-		if (rspi->max_speed_hz >= clksrc/4) /* 4=(CLK/2)/2 */
+		if (rspi->speed_hz >= clksrc/4) /* 4=(CLK/2)/2 */
 			break;
 		div++;
 		clksrc /= 2;
 	}
 
 	/* Sets transfer bit rate */
-	spbr = DIV_ROUND_UP(clksrc, 2 * rspi->max_speed_hz) - 1;
+	spbr = DIV_ROUND_UP(clksrc, 2 * rspi->speed_hz) - 1;
 	rspi_write8(rspi, clamp(spbr, 0, 255), RSPI_SPBR);
 	rspi->spcmd |= div << 2;
 
@@ -341,7 +340,7 @@ static int qspi_set_config_register(struct rspi_data *rspi, int access_size)
 	rspi_write8(rspi, rspi->sppcr, RSPI_SPPCR);
 
 	/* Sets transfer bit rate */
-	spbr = DIV_ROUND_UP(clk_get_rate(rspi->clk), 2 * rspi->max_speed_hz);
+	spbr = DIV_ROUND_UP(clk_get_rate(rspi->clk), 2 * rspi->speed_hz);
 	rspi_write8(rspi, clamp(spbr, 0, 255), RSPI_SPBR);
 
 	/* Disable dummy transmission, set byte access */
@@ -949,9 +948,24 @@ static int rspi_prepare_message(struct spi_controller *ctlr,
 {
 	struct rspi_data *rspi = spi_controller_get_devdata(ctlr);
 	struct spi_device *spi = msg->spi;
+	const struct spi_transfer *xfer;
 	int ret;
 
-	rspi->max_speed_hz = spi->max_speed_hz;
+	/*
+	 * As the Bit Rate Register must not be changed while the device is
+	 * active, all transfers in a message must use the same bit rate.
+	 * In theory, the sequencer could be enabled, and each Command Register
+	 * could divide the base bit rate by a different value.
+	 * However, most RSPI variants do not have Transfer Data Length
+	 * Multiplier Setting Registers, so each sequence step would be limited
+	 * to a single word, making this feature unsuitable for large
+	 * transfers, which would gain most from it.
+	 */
+	rspi->speed_hz = spi->max_speed_hz;
+	list_for_each_entry(xfer, &msg->transfers, transfer_list) {
+		if (xfer->speed_hz < rspi->speed_hz)
+			rspi->speed_hz = xfer->speed_hz;
+	}
 
 	rspi->spcmd = SPCMD_SSLKP;
 	if (spi->mode & SPI_CPOL)
diff --git a/drivers/spi/spi-sprd-adi.c b/drivers/spi/spi-sprd-adi.c
index 88e6543648cb..bd23c4689b46 100644
--- a/drivers/spi/spi-sprd-adi.c
+++ b/drivers/spi/spi-sprd-adi.c
@@ -389,9 +389,9 @@ static int sprd_adi_restart_handler(struct notifier_block *this,
 	sprd_adi_write(sadi, sadi->slave_pbase + REG_WDG_CTRL, val);
 
 	/* Load the watchdog timeout value, 50ms is always enough. */
+	sprd_adi_write(sadi, sadi->slave_pbase + REG_WDG_LOAD_HIGH, 0);
 	sprd_adi_write(sadi, sadi->slave_pbase + REG_WDG_LOAD_LOW,
 		       WDG_LOAD_VAL & WDG_LOAD_MASK);
-	sprd_adi_write(sadi, sadi->slave_pbase + REG_WDG_LOAD_HIGH, 0);
 
 	/* Start the watchdog to reset system */
 	sprd_adi_read(sadi, sadi->slave_pbase + REG_WDG_CTRL, &val);
diff --git a/drivers/spi/spi-stm32-qspi.c b/drivers/spi/spi-stm32-qspi.c
index 3c44bb2fd9b1..a900962b4336 100644
--- a/drivers/spi/spi-stm32-qspi.c
+++ b/drivers/spi/spi-stm32-qspi.c
@@ -553,20 +553,6 @@ static const struct spi_controller_mem_ops stm32_qspi_mem_ops = {
 	.exec_op = stm32_qspi_exec_op,
 };
 
-static void stm32_qspi_release(struct stm32_qspi *qspi)
-{
-	pm_runtime_get_sync(qspi->dev);
-	/* disable qspi */
-	writel_relaxed(0, qspi->io_base + QSPI_CR);
-	stm32_qspi_dma_free(qspi);
-	mutex_destroy(&qspi->lock);
-	pm_runtime_put_noidle(qspi->dev);
-	pm_runtime_disable(qspi->dev);
-	pm_runtime_set_suspended(qspi->dev);
-	pm_runtime_dont_use_autosuspend(qspi->dev);
-	clk_disable_unprepare(qspi->clk);
-}
-
 static int stm32_qspi_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -642,7 +628,7 @@ static int stm32_qspi_probe(struct platform_device *pdev)
 	if (IS_ERR(rstc)) {
 		ret = PTR_ERR(rstc);
 		if (ret == -EPROBE_DEFER)
-			goto err_qspi_release;
+			goto err_clk_disable;
 	} else {
 		reset_control_assert(rstc);
 		udelay(2);
@@ -653,7 +639,7 @@ static int stm32_qspi_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, qspi);
 	ret = stm32_qspi_dma_setup(qspi);
 	if (ret)
-		goto err_qspi_release;
+		goto err_dma_free;
 
 	mutex_init(&qspi->lock);
 
@@ -673,15 +659,26 @@ static int stm32_qspi_probe(struct platform_device *pdev)
 
 	ret = devm_spi_register_master(dev, ctrl);
 	if (ret)
-		goto err_qspi_release;
+		goto err_pm_runtime_free;
 
 	pm_runtime_mark_last_busy(dev);
 	pm_runtime_put_autosuspend(dev);
 
 	return 0;
 
-err_qspi_release:
-	stm32_qspi_release(qspi);
+err_pm_runtime_free:
+	pm_runtime_get_sync(qspi->dev);
+	/* disable qspi */
+	writel_relaxed(0, qspi->io_base + QSPI_CR);
+	mutex_destroy(&qspi->lock);
+	pm_runtime_put_noidle(qspi->dev);
+	pm_runtime_disable(qspi->dev);
+	pm_runtime_set_suspended(qspi->dev);
+	pm_runtime_dont_use_autosuspend(qspi->dev);
+err_dma_free:
+	stm32_qspi_dma_free(qspi);
+err_clk_disable:
+	clk_disable_unprepare(qspi->clk);
 err_master_put:
 	spi_master_put(qspi->ctrl);
 
@@ -692,7 +689,16 @@ static int stm32_qspi_remove(struct platform_device *pdev)
 {
 	struct stm32_qspi *qspi = platform_get_drvdata(pdev);
 
-	stm32_qspi_release(qspi);
+	pm_runtime_get_sync(qspi->dev);
+	/* disable qspi */
+	writel_relaxed(0, qspi->io_base + QSPI_CR);
+	stm32_qspi_dma_free(qspi);
+	mutex_destroy(&qspi->lock);
+	pm_runtime_put_noidle(qspi->dev);
+	pm_runtime_disable(qspi->dev);
+	pm_runtime_set_suspended(qspi->dev);
+	pm_runtime_dont_use_autosuspend(qspi->dev);
+	clk_disable_unprepare(qspi->clk);
 
 	return 0;
 }
diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c
index d753df700e9e..59e07675ef86 100644
--- a/drivers/spi/spidev.c
+++ b/drivers/spi/spidev.c
@@ -609,15 +609,20 @@ err_find_dev:
 static int spidev_release(struct inode *inode, struct file *filp)
 {
 	struct spidev_data	*spidev;
+	int			dofree;
 
 	mutex_lock(&device_list_lock);
 	spidev = filp->private_data;
 	filp->private_data = NULL;
 
+	spin_lock_irq(&spidev->spi_lock);
+	/* ... after we unbound from the underlying device? */
+	dofree = (spidev->spi == NULL);
+	spin_unlock_irq(&spidev->spi_lock);
+
 	/* last close? */
 	spidev->users--;
 	if (!spidev->users) {
-		int		dofree;
 
 		kfree(spidev->tx_buffer);
 		spidev->tx_buffer = NULL;
@@ -625,19 +630,14 @@ static int spidev_release(struct inode *inode, struct file *filp)
 		kfree(spidev->rx_buffer);
 		spidev->rx_buffer = NULL;
 
-		spin_lock_irq(&spidev->spi_lock);
-		if (spidev->spi)
-			spidev->speed_hz = spidev->spi->max_speed_hz;
-
-		/* ... after we unbound from the underlying device? */
-		dofree = (spidev->spi == NULL);
-		spin_unlock_irq(&spidev->spi_lock);
-
 		if (dofree)
 			kfree(spidev);
+		else
+			spidev->speed_hz = spidev->spi->max_speed_hz;
 	}
 #ifdef CONFIG_SPI_SLAVE
-	spi_slave_abort(spidev->spi);
+	if (!dofree)
+		spi_slave_abort(spidev->spi);
 #endif
 	mutex_unlock(&device_list_lock);
 
@@ -787,13 +787,13 @@ static int spidev_remove(struct spi_device *spi)
 {
 	struct spidev_data	*spidev = spi_get_drvdata(spi);
 
+	/* prevent new opens */
+	mutex_lock(&device_list_lock);
 	/* make sure ops on existing fds can abort cleanly */
 	spin_lock_irq(&spidev->spi_lock);
 	spidev->spi = NULL;
 	spin_unlock_irq(&spidev->spi_lock);
 
-	/* prevent new opens */
-	mutex_lock(&device_list_lock);
 	list_del(&spidev->device_entry);
 	device_destroy(spidev_class, spidev->devt);
 	clear_bit(MINOR(spidev->devt), minors);
diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c
index ff6562f602e0..de211ef3738c 100644
--- a/drivers/vdpa/vdpa.c
+++ b/drivers/vdpa/vdpa.c
@@ -63,7 +63,7 @@ static void vdpa_release_dev(struct device *d)
  * @config: the bus operations that is supported by this device
  * @size: size of the parent structure that contains private data
  *
- * Drvier should use vdap_alloc_device() wrapper macro instead of
+ * Driver should use vdpa_alloc_device() wrapper macro instead of
  * using this directly.
  *
  * Returns an error when parent/config/dma_dev is not set or fail to get
diff --git a/drivers/vhost/test.c b/drivers/vhost/test.c
index 0466921f4772..a09dedc79f68 100644
--- a/drivers/vhost/test.c
+++ b/drivers/vhost/test.c
@@ -263,9 +263,62 @@ static int vhost_test_set_features(struct vhost_test *n, u64 features)
 	return 0;
 }
 
+static long vhost_test_set_backend(struct vhost_test *n, unsigned index, int fd)
+{
+	static void *backend;
+
+	const bool enable = fd != -1;
+	struct vhost_virtqueue *vq;
+	int r;
+
+	mutex_lock(&n->dev.mutex);
+	r = vhost_dev_check_owner(&n->dev);
+	if (r)
+		goto err;
+
+	if (index >= VHOST_TEST_VQ_MAX) {
+		r = -ENOBUFS;
+		goto err;
+	}
+	vq = &n->vqs[index];
+	mutex_lock(&vq->mutex);
+
+	/* Verify that ring has been setup correctly. */
+	if (!vhost_vq_access_ok(vq)) {
+		r = -EFAULT;
+		goto err_vq;
+	}
+	if (!enable) {
+		vhost_poll_stop(&vq->poll);
+		backend = vhost_vq_get_backend(vq);
+		vhost_vq_set_backend(vq, NULL);
+	} else {
+		vhost_vq_set_backend(vq, backend);
+		r = vhost_vq_init_access(vq);
+		if (r == 0)
+			r = vhost_poll_start(&vq->poll, vq->kick);
+	}
+
+	mutex_unlock(&vq->mutex);
+
+	if (enable) {
+		vhost_test_flush_vq(n, index);
+	}
+
+	mutex_unlock(&n->dev.mutex);
+	return 0;
+
+err_vq:
+	mutex_unlock(&vq->mutex);
+err:
+	mutex_unlock(&n->dev.mutex);
+	return r;
+}
+
 static long vhost_test_ioctl(struct file *f, unsigned int ioctl,
 			     unsigned long arg)
 {
+	struct vhost_vring_file backend;
 	struct vhost_test *n = f->private_data;
 	void __user *argp = (void __user *)arg;
 	u64 __user *featurep = argp;
@@ -277,6 +330,10 @@ static long vhost_test_ioctl(struct file *f, unsigned int ioctl,
 		if (copy_from_user(&test, argp, sizeof test))
 			return -EFAULT;
 		return vhost_test_run(n, test);
+	case VHOST_TEST_SET_BACKEND:
+		if (copy_from_user(&backend, argp, sizeof backend))
+			return -EFAULT;
+		return vhost_test_set_backend(n, backend.index, backend.fd);
 	case VHOST_GET_FEATURES:
 		features = VHOST_FEATURES;
 		if (copy_to_user(featurep, &features, sizeof features))
diff --git a/drivers/vhost/test.h b/drivers/vhost/test.h
index 7dd265bfdf81..822bc4bee03a 100644
--- a/drivers/vhost/test.h
+++ b/drivers/vhost/test.h
@@ -4,5 +4,6 @@
 
 /* Start a given test on the virtio null device. 0 stops all tests. */
 #define VHOST_TEST_RUN _IOW(VHOST_VIRTIO, 0x31, int)
+#define VHOST_TEST_SET_BACKEND _IOW(VHOST_VIRTIO, 0x32, int)
 
 #endif
diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
index 7580e34f76c1..a54b60d6623f 100644
--- a/drivers/vhost/vdpa.c
+++ b/drivers/vhost/vdpa.c
@@ -818,7 +818,7 @@ static int vhost_vdpa_mmap(struct file *file, struct vm_area_struct *vma)
 	struct vdpa_device *vdpa = v->vdpa;
 	const struct vdpa_config_ops *ops = vdpa->config;
 	struct vdpa_notification_area notify;
-	int index = vma->vm_pgoff;
+	unsigned long index = vma->vm_pgoff;
 
 	if (vma->vm_end - vma->vm_start != PAGE_SIZE)
 		return -EINVAL;
diff --git a/drivers/video/backlight/tosa_lcd.c b/drivers/video/backlight/tosa_lcd.c
index e8ab583e5098..113116d3585c 100644
--- a/drivers/video/backlight/tosa_lcd.c
+++ b/drivers/video/backlight/tosa_lcd.c
@@ -107,7 +107,7 @@ static void tosa_lcd_tg_on(struct tosa_lcd_data *data)
 	/* TG LCD GVSS */
 	tosa_tg_send(spi, TG_PINICTL, 0x0);
 
-	if (!data->i2c) {
+	if (IS_ERR_OR_NULL(data->i2c)) {
 		/*
 		 * after the pannel is powered up the first time,
 		 * we can access the i2c bus so probe for the DAC
@@ -119,7 +119,7 @@ static void tosa_lcd_tg_on(struct tosa_lcd_data *data)
 			.addr	= DAC_BASE,
 			.platform_data = data->spi,
 		};
-		data->i2c = i2c_new_device(adap, &info);
+		data->i2c = i2c_new_client_device(adap, &info);
 	}
 }
 
diff --git a/drivers/video/fbdev/hpfb.c b/drivers/video/fbdev/hpfb.c
index f02be0db335e..8d418abdd767 100644
--- a/drivers/video/fbdev/hpfb.c
+++ b/drivers/video/fbdev/hpfb.c
@@ -402,7 +402,7 @@ int __init hpfb_init(void)
 	if (err)
 		return err;
 
-	err = probe_kernel_read(&i, (unsigned char *)INTFBVADDR + DIO_IDOFF, 1);
+	err = copy_from_kernel_nofault(&i, (unsigned char *)INTFBVADDR + DIO_IDOFF, 1);
 
 	if (!err && (i == DIO_ID_FBUFFER) && topcat_sid_ok(sid = DIO_SECID(INTFBVADDR))) {
 		if (!request_mem_region(INTFBPADDR, DIO_DEVSIZE, "Internal Topcat"))
diff --git a/drivers/virtio/virtio_mem.c b/drivers/virtio/virtio_mem.c
index 50c689f25045..f26f5f64ae82 100644
--- a/drivers/virtio/virtio_mem.c
+++ b/drivers/virtio/virtio_mem.c
@@ -101,6 +101,11 @@ struct virtio_mem {
 
 	/* The parent resource for all memory added via this device. */
 	struct resource *parent_resource;
+	/*
+	 * Copy of "System RAM (virtio_mem)" to be used for
+	 * add_memory_driver_managed().
+	 */
+	const char *resource_name;
 
 	/* Summary of all memory block states. */
 	unsigned long nb_mb_state[VIRTIO_MEM_MB_STATE_COUNT];
@@ -414,8 +419,20 @@ static int virtio_mem_mb_add(struct virtio_mem *vm, unsigned long mb_id)
 	if (nid == NUMA_NO_NODE)
 		nid = memory_add_physaddr_to_nid(addr);
 
+	/*
+	 * When force-unloading the driver and we still have memory added to
+	 * Linux, the resource name has to stay.
+	 */
+	if (!vm->resource_name) {
+		vm->resource_name = kstrdup_const("System RAM (virtio_mem)",
+						  GFP_KERNEL);
+		if (!vm->resource_name)
+			return -ENOMEM;
+	}
+
 	dev_dbg(&vm->vdev->dev, "adding memory block: %lu\n", mb_id);
-	return add_memory(nid, addr, memory_block_size_bytes());
+	return add_memory_driver_managed(nid, addr, memory_block_size_bytes(),
+					 vm->resource_name);
 }
 
 /*
@@ -1192,7 +1209,7 @@ static int virtio_mem_mb_plug_any_sb(struct virtio_mem *vm, unsigned long mb_id,
 						VIRTIO_MEM_MB_STATE_OFFLINE);
 	}
 
-	return rc;
+	return 0;
 }
 
 /*
@@ -1890,10 +1907,12 @@ static void virtio_mem_remove(struct virtio_device *vdev)
 	    vm->nb_mb_state[VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL] ||
 	    vm->nb_mb_state[VIRTIO_MEM_MB_STATE_ONLINE] ||
 	    vm->nb_mb_state[VIRTIO_MEM_MB_STATE_ONLINE_PARTIAL] ||
-	    vm->nb_mb_state[VIRTIO_MEM_MB_STATE_ONLINE_MOVABLE])
+	    vm->nb_mb_state[VIRTIO_MEM_MB_STATE_ONLINE_MOVABLE]) {
 		dev_warn(&vdev->dev, "device still has system memory added\n");
-	else
+	} else {
 		virtio_mem_delete_resource(vm);
+		kfree_const(vm->resource_name);
+	}
 
 	/* remove all tracking data - no locking needed */
 	vfree(vm->mb_state);