Merge 4.3-rc3 into char-misc-next

We want those fixes in here as well.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

214 files changed, 2808 insertions, 1432 deletions

diff --git a/drivers/atm/he.c b/drivers/atm/he.c
index a8da3a50e374..0f5cb37636bc 100644
--- a/drivers/atm/he.c
+++ b/drivers/atm/he.c
@@ -1578,9 +1578,7 @@ he_stop(struct he_dev *he_dev)
 
 	kfree(he_dev->rbpl_virt);
 	kfree(he_dev->rbpl_table);
-
-	if (he_dev->rbpl_pool)
-		dma_pool_destroy(he_dev->rbpl_pool);
+	dma_pool_destroy(he_dev->rbpl_pool);
 
 	if (he_dev->rbrq_base)
 		dma_free_coherent(&he_dev->pci_dev->dev, CONFIG_RBRQ_SIZE * sizeof(struct he_rbrq),
@@ -1594,8 +1592,7 @@ he_stop(struct he_dev *he_dev)
 		dma_free_coherent(&he_dev->pci_dev->dev, CONFIG_TBRQ_SIZE * sizeof(struct he_tbrq),
 				  he_dev->tpdrq_base, he_dev->tpdrq_phys);
 
-	if (he_dev->tpd_pool)
-		dma_pool_destroy(he_dev->tpd_pool);
+	dma_pool_destroy(he_dev->tpd_pool);
 
 	if (he_dev->pci_dev) {
 		pci_read_config_word(he_dev->pci_dev, PCI_COMMAND, &command);
diff --git a/drivers/atm/solos-pci.c b/drivers/atm/solos-pci.c
index 74e18b0a6d89..3d7fb6516f74 100644
--- a/drivers/atm/solos-pci.c
+++ b/drivers/atm/solos-pci.c
@@ -805,7 +805,12 @@ static void solos_bh(unsigned long card_arg)
 					continue;
 				}
 
-				skb = alloc_skb(size + 1, GFP_ATOMIC);
+				/* Use netdev_alloc_skb() because it adds NET_SKB_PAD of
+				 * headroom, and ensures we can route packets back out an
+				 * Ethernet interface (for example) without having to
+				 * reallocate. Adding NET_IP_ALIGN also ensures that both
+				 * PPPoATM and PPPoEoBR2684 packets end up aligned. */
+				skb = netdev_alloc_skb_ip_align(NULL, size + 1);
 				if (!skb) {
 					if (net_ratelimit())
 						dev_warn(&card->dev->dev, "Failed to allocate sk_buff for RX\n");
@@ -869,7 +874,10 @@ static void solos_bh(unsigned long card_arg)
 		/* Allocate RX skbs for any ports which need them */
 		if (card->using_dma && card->atmdev[port] &&
 		    !card->rx_skb[port]) {
-			struct sk_buff *skb = alloc_skb(RX_DMA_SIZE, GFP_ATOMIC);
+			/* Unlike the MMIO case (qv) we can't add NET_IP_ALIGN
+			 * here; the FPGA can only DMA to addresses which are
+			 * aligned to 4 bytes. */
+			struct sk_buff *skb = dev_alloc_skb(RX_DMA_SIZE);
 			if (skb) {
 				SKB_CB(skb)->dma_addr =
 					dma_map_single(&card->dev->dev, skb->data,
diff --git a/drivers/base/cacheinfo.c b/drivers/base/cacheinfo.c
index 764280a91776..e9fd32e91668 100644
--- a/drivers/base/cacheinfo.c
+++ b/drivers/base/cacheinfo.c
@@ -148,7 +148,11 @@ static void cache_shared_cpu_map_remove(unsigned int cpu)
 
 			if (sibling == cpu) /* skip itself */
 				continue;
+
 			sib_cpu_ci = get_cpu_cacheinfo(sibling);
+			if (!sib_cpu_ci->info_list)
+				continue;
+
 			sib_leaf = sib_cpu_ci->info_list + index;
 			cpumask_clear_cpu(cpu, &sib_leaf->shared_cpu_map);
 			cpumask_clear_cpu(sibling, &this_leaf->shared_cpu_map);
@@ -159,6 +163,9 @@ static void cache_shared_cpu_map_remove(unsigned int cpu)
 
 static void free_cache_attributes(unsigned int cpu)
 {
+	if (!per_cpu_cacheinfo(cpu))
+		return;
+
 	cache_shared_cpu_map_remove(cpu);
 
 	kfree(per_cpu_cacheinfo(cpu));
@@ -514,8 +521,7 @@ static int cacheinfo_cpu_callback(struct notifier_block *nfb,
 		break;
 	case CPU_DEAD:
 		cache_remove_dev(cpu);
-		if (per_cpu_cacheinfo(cpu))
-			free_cache_attributes(cpu);
+		free_cache_attributes(cpu);
 		break;
 	}
 	return notifier_from_errno(rc);
diff --git a/drivers/char/hw_random/xgene-rng.c b/drivers/char/hw_random/xgene-rng.c
index c37cf754a985..3c77645405e5 100644
--- a/drivers/char/hw_random/xgene-rng.c
+++ b/drivers/char/hw_random/xgene-rng.c
@@ -344,11 +344,12 @@ static int xgene_rng_probe(struct platform_device *pdev)
 	if (IS_ERR(ctx->csr_base))
 		return PTR_ERR(ctx->csr_base);
 
-	ctx->irq = platform_get_irq(pdev, 0);
-	if (ctx->irq < 0) {
+	rc = platform_get_irq(pdev, 0);
+	if (rc < 0) {
 		dev_err(&pdev->dev, "No IRQ resource\n");
-		return ctx->irq;
+		return rc;
 	}
+	ctx->irq = rc;
 
 	dev_dbg(&pdev->dev, "APM X-Gene RNG BASE %p ALARM IRQ %d",
 		ctx->csr_base, ctx->irq);
diff --git a/drivers/crypto/marvell/cesa.h b/drivers/crypto/marvell/cesa.h
index b60698b30d30..bc2a55bc35e4 100644
--- a/drivers/crypto/marvell/cesa.h
+++ b/drivers/crypto/marvell/cesa.h
@@ -687,6 +687,33 @@ static inline u32 mv_cesa_get_int_mask(struct mv_cesa_engine *engine)
 
 int mv_cesa_queue_req(struct crypto_async_request *req);
 
+/*
+ * Helper function that indicates whether a crypto request needs to be
+ * cleaned up or not after being enqueued using mv_cesa_queue_req().
+ */
+static inline int mv_cesa_req_needs_cleanup(struct crypto_async_request *req,
+					    int ret)
+{
+	/*
+	 * The queue still had some space, the request was queued
+	 * normally, so there's no need to clean it up.
+	 */
+	if (ret == -EINPROGRESS)
+		return false;
+
+	/*
+	 * The queue had not space left, but since the request is
+	 * flagged with CRYPTO_TFM_REQ_MAY_BACKLOG, it was added to
+	 * the backlog and will be processed later. There's no need to
+	 * clean it up.
+	 */
+	if (ret == -EBUSY && req->flags & CRYPTO_TFM_REQ_MAY_BACKLOG)
+		return false;
+
+	/* Request wasn't queued, we need to clean it up */
+	return true;
+}
+
 /* TDMA functions */
 
 static inline void mv_cesa_req_dma_iter_init(struct mv_cesa_dma_iter *iter,
diff --git a/drivers/crypto/marvell/cipher.c b/drivers/crypto/marvell/cipher.c
index 0745cf3b9c0e..3df2f4e7adb2 100644
--- a/drivers/crypto/marvell/cipher.c
+++ b/drivers/crypto/marvell/cipher.c
@@ -189,7 +189,6 @@ static inline void mv_cesa_ablkcipher_prepare(struct crypto_async_request *req,
 {
 	struct ablkcipher_request *ablkreq = ablkcipher_request_cast(req);
 	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(ablkreq);
-
 	creq->req.base.engine = engine;
 
 	if (creq->req.base.type == CESA_DMA_REQ)
@@ -431,7 +430,7 @@ static int mv_cesa_des_op(struct ablkcipher_request *req,
 		return ret;
 
 	ret = mv_cesa_queue_req(&req->base);
-	if (ret && ret != -EINPROGRESS)
+	if (mv_cesa_req_needs_cleanup(&req->base, ret))
 		mv_cesa_ablkcipher_cleanup(req);
 
 	return ret;
@@ -551,7 +550,7 @@ static int mv_cesa_des3_op(struct ablkcipher_request *req,
 		return ret;
 
 	ret = mv_cesa_queue_req(&req->base);
-	if (ret && ret != -EINPROGRESS)
+	if (mv_cesa_req_needs_cleanup(&req->base, ret))
 		mv_cesa_ablkcipher_cleanup(req);
 
 	return ret;
@@ -693,7 +692,7 @@ static int mv_cesa_aes_op(struct ablkcipher_request *req,
 		return ret;
 
 	ret = mv_cesa_queue_req(&req->base);
-	if (ret && ret != -EINPROGRESS)
+	if (mv_cesa_req_needs_cleanup(&req->base, ret))
 		mv_cesa_ablkcipher_cleanup(req);
 
 	return ret;
diff --git a/drivers/crypto/marvell/hash.c b/drivers/crypto/marvell/hash.c
index ae9272eb9c1a..e8d0d7128137 100644
--- a/drivers/crypto/marvell/hash.c
+++ b/drivers/crypto/marvell/hash.c
@@ -739,10 +739,8 @@ static int mv_cesa_ahash_update(struct ahash_request *req)
 		return 0;
 
 	ret = mv_cesa_queue_req(&req->base);
-	if (ret && ret != -EINPROGRESS) {
+	if (mv_cesa_req_needs_cleanup(&req->base, ret))
 		mv_cesa_ahash_cleanup(req);
-		return ret;
-	}
 
 	return ret;
 }
@@ -766,7 +764,7 @@ static int mv_cesa_ahash_final(struct ahash_request *req)
 		return 0;
 
 	ret = mv_cesa_queue_req(&req->base);
-	if (ret && ret != -EINPROGRESS)
+	if (mv_cesa_req_needs_cleanup(&req->base, ret))
 		mv_cesa_ahash_cleanup(req);
 
 	return ret;
@@ -791,7 +789,7 @@ static int mv_cesa_ahash_finup(struct ahash_request *req)
 		return 0;
 
 	ret = mv_cesa_queue_req(&req->base);
-	if (ret && ret != -EINPROGRESS)
+	if (mv_cesa_req_needs_cleanup(&req->base, ret))
 		mv_cesa_ahash_cleanup(req);
 
 	return ret;
diff --git a/drivers/crypto/qat/qat_common/adf_aer.c b/drivers/crypto/qat/qat_common/adf_aer.c
index a57b4194de28..0a5ca0ba5d64 100644
--- a/drivers/crypto/qat/qat_common/adf_aer.c
+++ b/drivers/crypto/qat/qat_common/adf_aer.c
@@ -88,6 +88,9 @@ static void adf_dev_restore(struct adf_accel_dev *accel_dev)
 	struct pci_dev *parent = pdev->bus->self;
 	uint16_t bridge_ctl = 0;
 
+	if (accel_dev->is_vf)
+		return;
+
 	dev_info(&GET_DEV(accel_dev), "Resetting device qat_dev%d\n",
 		 accel_dev->accel_id);
 
diff --git a/drivers/extcon/extcon.c b/drivers/extcon/extcon.c
index a07addde297b..8dd0af1d50bc 100644
--- a/drivers/extcon/extcon.c
+++ b/drivers/extcon/extcon.c
@@ -159,7 +159,7 @@ static int find_cable_index_by_name(struct extcon_dev *edev, const char *name)
 static bool is_extcon_changed(u32 prev, u32 new, int idx, bool *attached)
 {
 	if (((prev >> idx) & 0x1) != ((new >> idx) & 0x1)) {
-		*attached = new ? true : false;
+		*attached = ((new >> idx) & 0x1) ? true : false;
 		return true;
 	}
 
diff --git a/drivers/firmware/Kconfig b/drivers/firmware/Kconfig
index d8de6a8dd4de..665efca59487 100644
--- a/drivers/firmware/Kconfig
+++ b/drivers/firmware/Kconfig
@@ -139,6 +139,14 @@ config QCOM_SCM
 	bool
 	depends on ARM || ARM64
 
+config QCOM_SCM_32
+	def_bool y
+	depends on QCOM_SCM && ARM
+
+config QCOM_SCM_64
+	def_bool y
+	depends on QCOM_SCM && ARM64
+
 source "drivers/firmware/broadcom/Kconfig"
 source "drivers/firmware/google/Kconfig"
 source "drivers/firmware/efi/Kconfig"
diff --git a/drivers/firmware/Makefile b/drivers/firmware/Makefile
index 000830fc6707..2ee83474a3c1 100644
--- a/drivers/firmware/Makefile
+++ b/drivers/firmware/Makefile
@@ -13,7 +13,8 @@ obj-$(CONFIG_ISCSI_IBFT_FIND)	+= iscsi_ibft_find.o
 obj-$(CONFIG_ISCSI_IBFT)	+= iscsi_ibft.o
 obj-$(CONFIG_FIRMWARE_MEMMAP)	+= memmap.o
 obj-$(CONFIG_QCOM_SCM)		+= qcom_scm.o
-obj-$(CONFIG_QCOM_SCM)		+= qcom_scm-32.o
+obj-$(CONFIG_QCOM_SCM_64)	+= qcom_scm-64.o
+obj-$(CONFIG_QCOM_SCM_32)	+= qcom_scm-32.o
 CFLAGS_qcom_scm-32.o :=$(call as-instr,.arch_extension sec,-DREQUIRES_SEC=1)
 
 obj-y				+= broadcom/
diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h
index e334a01cf92f..6b6548fda089 100644
--- a/drivers/firmware/efi/libstub/efistub.h
+++ b/drivers/firmware/efi/libstub/efistub.h
@@ -5,10 +5,6 @@
 /* error code which can't be mistaken for valid address */
 #define EFI_ERROR	(~0UL)
 
-#undef memcpy
-#undef memset
-#undef memmove
-
 void efi_char16_printk(efi_system_table_t *, efi_char16_t *);
 
 efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg, void *__image,
diff --git a/drivers/firmware/qcom_scm-64.c b/drivers/firmware/qcom_scm-64.c
new file mode 100644
index 000000000000..bb6555f6d63b
--- /dev/null
+++ b/drivers/firmware/qcom_scm-64.c
@@ -0,0 +1,63 @@
+/* Copyright (c) 2015, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/io.h>
+#include <linux/errno.h>
+#include <linux/qcom_scm.h>
+
+/**
+ * qcom_scm_set_cold_boot_addr() - Set the cold boot address for cpus
+ * @entry: Entry point function for the cpus
+ * @cpus: The cpumask of cpus that will use the entry point
+ *
+ * Set the cold boot address of the cpus. Any cpu outside the supported
+ * range would be removed from the cpu present mask.
+ */
+int __qcom_scm_set_cold_boot_addr(void *entry, const cpumask_t *cpus)
+{
+	return -ENOTSUPP;
+}
+
+/**
+ * qcom_scm_set_warm_boot_addr() - Set the warm boot address for cpus
+ * @entry: Entry point function for the cpus
+ * @cpus: The cpumask of cpus that will use the entry point
+ *
+ * Set the Linux entry point for the SCM to transfer control to when coming
+ * out of a power down. CPU power down may be executed on cpuidle or hotplug.
+ */
+int __qcom_scm_set_warm_boot_addr(void *entry, const cpumask_t *cpus)
+{
+	return -ENOTSUPP;
+}
+
+/**
+ * qcom_scm_cpu_power_down() - Power down the cpu
+ * @flags - Flags to flush cache
+ *
+ * This is an end point to power down cpu. If there was a pending interrupt,
+ * the control would return from this function, otherwise, the cpu jumps to the
+ * warm boot entry point set for this cpu upon reset.
+ */
+void __qcom_scm_cpu_power_down(u32 flags)
+{
+}
+
+int __qcom_scm_is_call_available(u32 svc_id, u32 cmd_id)
+{
+	return -ENOTSUPP;
+}
+
+int __qcom_scm_hdcp_req(struct qcom_scm_hdcp_req *req, u32 req_cnt, u32 *resp)
+{
+	return -ENOTSUPP;
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 668939a14206..6647fb26ef25 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -82,6 +82,7 @@ extern int amdgpu_vm_block_size;
 extern int amdgpu_enable_scheduler;
 extern int amdgpu_sched_jobs;
 extern int amdgpu_sched_hw_submission;
+extern int amdgpu_enable_semaphores;
 
 #define AMDGPU_WAIT_IDLE_TIMEOUT_IN_MS	        3000
 #define AMDGPU_MAX_USEC_TIMEOUT			100000	/* 100 ms */
@@ -432,7 +433,7 @@ int amdgpu_fence_driver_init(struct amdgpu_device *adev);
 void amdgpu_fence_driver_fini(struct amdgpu_device *adev);
 void amdgpu_fence_driver_force_completion(struct amdgpu_device *adev);
 
-void amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring);
+int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring);
 int amdgpu_fence_driver_start_ring(struct amdgpu_ring *ring,
 				   struct amdgpu_irq_src *irq_src,
 				   unsigned irq_type);
@@ -890,7 +891,7 @@ struct amdgpu_ring {
 	struct amdgpu_device		*adev;
 	const struct amdgpu_ring_funcs	*funcs;
 	struct amdgpu_fence_driver	fence_drv;
-	struct amd_gpu_scheduler 	*scheduler;
+	struct amd_gpu_scheduler 	sched;
 
 	spinlock_t              fence_lock;
 	struct mutex		*ring_lock;
@@ -1201,8 +1202,6 @@ struct amdgpu_gfx {
 	struct amdgpu_irq_src		priv_inst_irq;
 	/* gfx status */
 	uint32_t gfx_current_status;
-	/* sync signal for const engine */
-	unsigned ce_sync_offs;
 	/* ce ram size*/
 	unsigned ce_ram_size;
 };
@@ -1274,8 +1273,10 @@ struct amdgpu_job {
 	uint32_t		num_ibs;
 	struct mutex            job_lock;
 	struct amdgpu_user_fence uf;
-	int (*free_job)(struct amdgpu_job *sched_job);
+	int (*free_job)(struct amdgpu_job *job);
 };
+#define to_amdgpu_job(sched_job)		\
+		container_of((sched_job), struct amdgpu_job, base)
 
 static inline u32 amdgpu_get_ib_value(struct amdgpu_cs_parser *p, uint32_t ib_idx, int idx)
 {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index 496ed2192eba..84d68d658f8a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -183,7 +183,7 @@ int alloc_gtt_mem(struct kgd_dev *kgd, size_t size,
 		return -ENOMEM;
 
 	r = amdgpu_bo_create(rdev, size, PAGE_SIZE, true, AMDGPU_GEM_DOMAIN_GTT,
-			AMDGPU_GEM_CREATE_CPU_GTT_USWC, NULL, &(*mem)->bo);
+			     AMDGPU_GEM_CREATE_CPU_GTT_USWC, NULL, NULL, &(*mem)->bo);
 	if (r) {
 		dev_err(rdev->dev,
 			"failed to allocate BO for amdkfd (%d)\n", r);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
index 98d59ee640ce..cd639c362df3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
@@ -79,7 +79,8 @@ static void amdgpu_benchmark_move(struct amdgpu_device *adev, unsigned size,
 	int time;
 
 	n = AMDGPU_BENCHMARK_ITERATIONS;
-	r = amdgpu_bo_create(adev, size, PAGE_SIZE, true, sdomain, 0, NULL, &sobj);
+	r = amdgpu_bo_create(adev, size, PAGE_SIZE, true, sdomain, 0, NULL,
+			     NULL, &sobj);
 	if (r) {
 		goto out_cleanup;
 	}
@@ -91,7 +92,8 @@ static void amdgpu_benchmark_move(struct amdgpu_device *adev, unsigned size,
 	if (r) {
 		goto out_cleanup;
 	}
-	r = amdgpu_bo_create(adev, size, PAGE_SIZE, true, ddomain, 0, NULL, &dobj);
+	r = amdgpu_bo_create(adev, size, PAGE_SIZE, true, ddomain, 0, NULL,
+			     NULL, &dobj);
 	if (r) {
 		goto out_cleanup;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
index 6b1243f9f86d..1c3fc99c5465 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
@@ -86,7 +86,7 @@ static int amdgpu_cgs_gmap_kmem(void *cgs_device, void *kmem,
 
 	struct sg_table *sg = drm_prime_pages_to_sg(&kmem_page, npages);
 	ret = amdgpu_bo_create(adev, size, PAGE_SIZE, false,
-			       AMDGPU_GEM_DOMAIN_GTT, 0, sg, &bo);
+			       AMDGPU_GEM_DOMAIN_GTT, 0, sg, NULL, &bo);
 	if (ret)
 		return ret;
 	ret = amdgpu_bo_reserve(bo, false);
@@ -197,7 +197,8 @@ static int amdgpu_cgs_alloc_gpu_mem(void *cgs_device,
 
 	ret = amdgpu_bo_create_restricted(adev, size, PAGE_SIZE,
 					  true, domain, flags,
-					  NULL, &placement, &obj);
+					  NULL, &placement, NULL,
+					  &obj);
 	if (ret) {
 		DRM_ERROR("(%d) bo create failed\n", ret);
 		return ret;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 3b355aeb62fd..749420f1ea6f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -154,42 +154,41 @@ int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data)
 {
 	union drm_amdgpu_cs *cs = data;
 	uint64_t *chunk_array_user;
-	uint64_t *chunk_array = NULL;
+	uint64_t *chunk_array;
 	struct amdgpu_fpriv *fpriv = p->filp->driver_priv;
 	unsigned size, i;
-	int r = 0;
+	int ret;
 
-	if (!cs->in.num_chunks)
-		goto out;
+	if (cs->in.num_chunks == 0)
+		return 0;
+
+	chunk_array = kmalloc_array(cs->in.num_chunks, sizeof(uint64_t), GFP_KERNEL);
+	if (!chunk_array)
+		return -ENOMEM;
 
 	p->ctx = amdgpu_ctx_get(fpriv, cs->in.ctx_id);
 	if (!p->ctx) {
-		r = -EINVAL;
-		goto out;
+		ret = -EINVAL;
+		goto free_chunk;
 	}
+
 	p->bo_list = amdgpu_bo_list_get(fpriv, cs->in.bo_list_handle);
 
 	/* get chunks */
 	INIT_LIST_HEAD(&p->validated);
-	chunk_array = kmalloc_array(cs->in.num_chunks, sizeof(uint64_t), GFP_KERNEL);
-	if (chunk_array == NULL) {
-		r = -ENOMEM;
-		goto out;
-	}
-
 	chunk_array_user = (uint64_t __user *)(cs->in.chunks);
 	if (copy_from_user(chunk_array, chunk_array_user,
 			   sizeof(uint64_t)*cs->in.num_chunks)) {
-		r = -EFAULT;
-		goto out;
+		ret = -EFAULT;
+		goto put_bo_list;
 	}
 
 	p->nchunks = cs->in.num_chunks;
 	p->chunks = kmalloc_array(p->nchunks, sizeof(struct amdgpu_cs_chunk),
 			    GFP_KERNEL);
-	if (p->chunks == NULL) {
-		r = -ENOMEM;
-		goto out;
+	if (!p->chunks) {
+		ret = -ENOMEM;
+		goto put_bo_list;
 	}
 
 	for (i = 0; i < p->nchunks; i++) {
@@ -200,8 +199,9 @@ int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data)
 		chunk_ptr = (void __user *)chunk_array[i];
 		if (copy_from_user(&user_chunk, chunk_ptr,
 				       sizeof(struct drm_amdgpu_cs_chunk))) {
-			r = -EFAULT;
-			goto out;
+			ret = -EFAULT;
+			i--;
+			goto free_partial_kdata;
 		}
 		p->chunks[i].chunk_id = user_chunk.chunk_id;
 		p->chunks[i].length_dw = user_chunk.length_dw;
@@ -212,13 +212,14 @@ int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data)
 
 		p->chunks[i].kdata = drm_malloc_ab(size, sizeof(uint32_t));
 		if (p->chunks[i].kdata == NULL) {
-			r = -ENOMEM;
-			goto out;
+			ret = -ENOMEM;
+			i--;
+			goto free_partial_kdata;
 		}
 		size *= sizeof(uint32_t);
 		if (copy_from_user(p->chunks[i].kdata, cdata, size)) {
-			r = -EFAULT;
-			goto out;
+			ret = -EFAULT;
+			goto free_partial_kdata;
 		}
 
 		switch (p->chunks[i].chunk_id) {
@@ -238,15 +239,15 @@ int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data)
 				gobj = drm_gem_object_lookup(p->adev->ddev,
 							     p->filp, handle);
 				if (gobj == NULL) {
-					r = -EINVAL;
-					goto out;
+					ret = -EINVAL;
+					goto free_partial_kdata;
 				}
 
 				p->uf.bo = gem_to_amdgpu_bo(gobj);
 				p->uf.offset = fence_data->offset;
 			} else {
-				r = -EINVAL;
-				goto out;
+				ret = -EINVAL;
+				goto free_partial_kdata;
 			}
 			break;
 
@@ -254,19 +255,35 @@ int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data)
 			break;
 
 		default:
-			r = -EINVAL;
-			goto out;
+			ret = -EINVAL;
+			goto free_partial_kdata;
 		}
 	}
 
 
 	p->ibs = kcalloc(p->num_ibs, sizeof(struct amdgpu_ib), GFP_KERNEL);
-	if (!p->ibs)
-		r = -ENOMEM;
+	if (!p->ibs) {
+		ret = -ENOMEM;
+		goto free_all_kdata;
+	}
 
-out:
 	kfree(chunk_array);
-	return r;
+	return 0;
+
+free_all_kdata:
+	i = p->nchunks - 1;
+free_partial_kdata:
+	for (; i >= 0; i--)
+		drm_free_large(p->chunks[i].kdata);
+	kfree(p->chunks);
+put_bo_list:
+	if (p->bo_list)
+		amdgpu_bo_list_put(p->bo_list);
+	amdgpu_ctx_put(p->ctx);
+free_chunk:
+	kfree(chunk_array);
+
+	return ret;
 }
 
 /* Returns how many bytes TTM can move per IB.
@@ -321,25 +338,17 @@ static u64 amdgpu_cs_get_threshold_for_moves(struct amdgpu_device *adev)
 	return max(bytes_moved_threshold, 1024*1024ull);
 }
 
-int amdgpu_cs_list_validate(struct amdgpu_cs_parser *p)
+int amdgpu_cs_list_validate(struct amdgpu_device *adev,
+			    struct amdgpu_vm *vm,
+			    struct list_head *validated)
 {
-	struct amdgpu_fpriv *fpriv = p->filp->driver_priv;
-	struct amdgpu_vm *vm = &fpriv->vm;
-	struct amdgpu_device *adev = p->adev;
 	struct amdgpu_bo_list_entry *lobj;
-	struct list_head duplicates;
 	struct amdgpu_bo *bo;
 	u64 bytes_moved = 0, initial_bytes_moved;
 	u64 bytes_moved_threshold = amdgpu_cs_get_threshold_for_moves(adev);
 	int r;
 
-	INIT_LIST_HEAD(&duplicates);
-	r = ttm_eu_reserve_buffers(&p->ticket, &p->validated, true, &duplicates);
-	if (unlikely(r != 0)) {
-		return r;
-	}
-
-	list_for_each_entry(lobj, &p->validated, tv.head) {
+	list_for_each_entry(lobj, validated, tv.head) {
 		bo = lobj->robj;
 		if (!bo->pin_count) {
 			u32 domain = lobj->prefered_domains;
@@ -373,7 +382,6 @@ int amdgpu_cs_list_validate(struct amdgpu_cs_parser *p)
 					domain = lobj->allowed_domains;
 					goto retry;
 				}
-				ttm_eu_backoff_reservation(&p->ticket, &p->validated);
 				return r;
 			}
 		}
@@ -386,6 +394,7 @@ static int amdgpu_cs_parser_relocs(struct amdgpu_cs_parser *p)
 {
 	struct amdgpu_fpriv *fpriv = p->filp->driver_priv;
 	struct amdgpu_cs_buckets buckets;
+	struct list_head duplicates;
 	bool need_mmap_lock = false;
 	int i, r;
 
@@ -405,8 +414,22 @@ static int amdgpu_cs_parser_relocs(struct amdgpu_cs_parser *p)
 	if (need_mmap_lock)
 		down_read(&current->mm->mmap_sem);
 
-	r = amdgpu_cs_list_validate(p);
+	INIT_LIST_HEAD(&duplicates);
+	r = ttm_eu_reserve_buffers(&p->ticket, &p->validated, true, &duplicates);
+	if (unlikely(r != 0))
+		goto error_reserve;
+
+	r = amdgpu_cs_list_validate(p->adev, &fpriv->vm, &p->validated);
+	if (r)
+		goto error_validate;
+
+	r = amdgpu_cs_list_validate(p->adev, &fpriv->vm, &duplicates);
+
+error_validate:
+	if (r)
+		ttm_eu_backoff_reservation(&p->ticket, &p->validated);
 
+error_reserve:
 	if (need_mmap_lock)
 		up_read(&current->mm->mmap_sem);
 
@@ -772,15 +795,15 @@ static int amdgpu_cs_dependencies(struct amdgpu_device *adev,
 	return 0;
 }
 
-static int amdgpu_cs_free_job(struct amdgpu_job *sched_job)
+static int amdgpu_cs_free_job(struct amdgpu_job *job)
 {
 	int i;
-	if (sched_job->ibs)
-		for (i = 0; i < sched_job->num_ibs; i++)
-			amdgpu_ib_free(sched_job->adev, &sched_job->ibs[i]);
-	kfree(sched_job->ibs);
-	if (sched_job->uf.bo)
-		drm_gem_object_unreference_unlocked(&sched_job->uf.bo->gem_base);
+	if (job->ibs)
+		for (i = 0; i < job->num_ibs; i++)
+			amdgpu_ib_free(job->adev, &job->ibs[i]);
+	kfree(job->ibs);
+	if (job->uf.bo)
+		drm_gem_object_unreference_unlocked(&job->uf.bo->gem_base);
 	return 0;
 }
 
@@ -804,7 +827,7 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 	r = amdgpu_cs_parser_init(parser, data);
 	if (r) {
 		DRM_ERROR("Failed to initialize parser !\n");
-		amdgpu_cs_parser_fini(parser, r, false);
+		kfree(parser);
 		up_read(&adev->exclusive_lock);
 		r = amdgpu_cs_handle_lockup(adev, r);
 		return r;
@@ -842,7 +865,7 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 		job = kzalloc(sizeof(struct amdgpu_job), GFP_KERNEL);
 		if (!job)
 			return -ENOMEM;
-		job->base.sched = ring->scheduler;
+		job->base.sched = &ring->sched;
 		job->base.s_entity = &parser->ctx->rings[ring->idx].entity;
 		job->adev = parser->adev;
 		job->ibs = parser->ibs;
@@ -857,7 +880,7 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 
 		job->free_job = amdgpu_cs_free_job;
 		mutex_lock(&job->job_lock);
-		r = amd_sched_entity_push_job((struct amd_sched_job *)job);
+		r = amd_sched_entity_push_job(&job->base);
 		if (r) {
 			mutex_unlock(&job->job_lock);
 			amdgpu_cs_free_job(job);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
index 20cbc4eb5a6f..e0b80ccdfe8a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
@@ -43,10 +43,10 @@ int amdgpu_ctx_init(struct amdgpu_device *adev, bool kernel,
 		for (i = 0; i < adev->num_rings; i++) {
 			struct amd_sched_rq *rq;
 			if (kernel)
-				rq = &adev->rings[i]->scheduler->kernel_rq;
+				rq = &adev->rings[i]->sched.kernel_rq;
 			else
-				rq = &adev->rings[i]->scheduler->sched_rq;
-			r = amd_sched_entity_init(adev->rings[i]->scheduler,
+				rq = &adev->rings[i]->sched.sched_rq;
+			r = amd_sched_entity_init(&adev->rings[i]->sched,
 						  &ctx->rings[i].entity,
 						  rq, amdgpu_sched_jobs);
 			if (r)
@@ -55,7 +55,7 @@ int amdgpu_ctx_init(struct amdgpu_device *adev, bool kernel,
 
 		if (i < adev->num_rings) {
 			for (j = 0; j < i; j++)
-				amd_sched_entity_fini(adev->rings[j]->scheduler,
+				amd_sched_entity_fini(&adev->rings[j]->sched,
 						      &ctx->rings[j].entity);
 			kfree(ctx);
 			return r;
@@ -75,7 +75,7 @@ void amdgpu_ctx_fini(struct amdgpu_ctx *ctx)
 
 	if (amdgpu_enable_scheduler) {
 		for (i = 0; i < adev->num_rings; i++)
-			amd_sched_entity_fini(adev->rings[i]->scheduler,
+			amd_sched_entity_fini(&adev->rings[i]->sched,
 					      &ctx->rings[i].entity);
 	}
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 6ff6ae945794..6068d8207d10 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -246,7 +246,7 @@ static int amdgpu_vram_scratch_init(struct amdgpu_device *adev)
 		r = amdgpu_bo_create(adev, AMDGPU_GPU_PAGE_SIZE,
 				     PAGE_SIZE, true, AMDGPU_GEM_DOMAIN_VRAM,
 				     AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED,
-				     NULL, &adev->vram_scratch.robj);
+				     NULL, NULL, &adev->vram_scratch.robj);
 		if (r) {
 			return r;
 		}
@@ -449,7 +449,8 @@ static int amdgpu_wb_init(struct amdgpu_device *adev)
 
 	if (adev->wb.wb_obj == NULL) {
 		r = amdgpu_bo_create(adev, AMDGPU_MAX_WB * 4, PAGE_SIZE, true,
-				     AMDGPU_GEM_DOMAIN_GTT, 0,  NULL, &adev->wb.wb_obj);
+				     AMDGPU_GEM_DOMAIN_GTT, 0,  NULL, NULL,
+				     &adev->wb.wb_obj);
 		if (r) {
 			dev_warn(adev->dev, "(%d) create WB bo failed\n", r);
 			return r;
@@ -1650,9 +1651,11 @@ int amdgpu_suspend_kms(struct drm_device *dev, bool suspend, bool fbcon)
 	drm_kms_helper_poll_disable(dev);
 
 	/* turn off display hw */
+	drm_modeset_lock_all(dev);
 	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
 		drm_helper_connector_dpms(connector, DRM_MODE_DPMS_OFF);
 	}
+	drm_modeset_unlock_all(dev);
 
 	/* unpin the front buffers */
 	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
@@ -1747,9 +1750,11 @@ int amdgpu_resume_kms(struct drm_device *dev, bool resume, bool fbcon)
 	if (fbcon) {
 		drm_helper_resume_force_mode(dev);
 		/* turn on display hw */
+		drm_modeset_lock_all(dev);
 		list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
 			drm_helper_connector_dpms(connector, DRM_MODE_DPMS_ON);
 		}
+		drm_modeset_unlock_all(dev);
 	}
 
 	drm_kms_helper_poll_enable(dev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 0fcc0bd1622c..adb48353f2e1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -79,6 +79,7 @@ int amdgpu_exp_hw_support = 0;
 int amdgpu_enable_scheduler = 0;
 int amdgpu_sched_jobs = 16;
 int amdgpu_sched_hw_submission = 2;
+int amdgpu_enable_semaphores = 1;
 
 MODULE_PARM_DESC(vramlimit, "Restrict VRAM for testing, in megabytes");
 module_param_named(vramlimit, amdgpu_vram_limit, int, 0600);
@@ -152,6 +153,9 @@ module_param_named(sched_jobs, amdgpu_sched_jobs, int, 0444);
 MODULE_PARM_DESC(sched_hw_submission, "the max number of HW submissions (default 2)");
 module_param_named(sched_hw_submission, amdgpu_sched_hw_submission, int, 0444);
 
+MODULE_PARM_DESC(enable_semaphores, "Enable semaphores (1 = enable (default), 0 = disable)");
+module_param_named(enable_semaphores, amdgpu_enable_semaphores, int, 0644);
+
 static struct pci_device_id pciidlist[] = {
 #ifdef CONFIG_DRM_AMDGPU_CIK
 	/* Kaveri */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 1be2bd6d07ea..b3fc26c59787 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -609,9 +609,9 @@ int amdgpu_fence_driver_start_ring(struct amdgpu_ring *ring,
  * Init the fence driver for the requested ring (all asics).
  * Helper function for amdgpu_fence_driver_init().
  */
-void amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring)
+int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring)
 {
-	int i;
+	int i, r;
 
 	ring->fence_drv.cpu_addr = NULL;
 	ring->fence_drv.gpu_addr = 0;
@@ -625,15 +625,19 @@ void amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring)
 			amdgpu_fence_check_lockup);
 	ring->fence_drv.ring = ring;
 
+	init_waitqueue_head(&ring->fence_drv.fence_queue);
+
 	if (amdgpu_enable_scheduler) {
-		ring->scheduler = amd_sched_create(&amdgpu_sched_ops,
-						   ring->idx,
-						   amdgpu_sched_hw_submission,
-						   (void *)ring->adev);
-		if (!ring->scheduler)
-			DRM_ERROR("Failed to create scheduler on ring %d.\n",
-				  ring->idx);
+		r = amd_sched_init(&ring->sched, &amdgpu_sched_ops,
+				   amdgpu_sched_hw_submission, ring->name);
+		if (r) {
+			DRM_ERROR("Failed to create scheduler on ring %s.\n",
+				  ring->name);
+			return r;
+		}
 	}
+
+	return 0;
 }
 
 /**
@@ -681,8 +685,7 @@ void amdgpu_fence_driver_fini(struct amdgpu_device *adev)
 		wake_up_all(&ring->fence_drv.fence_queue);
 		amdgpu_irq_put(adev, ring->fence_drv.irq_src,
 			       ring->fence_drv.irq_type);
-		if (ring->scheduler)
-			amd_sched_destroy(ring->scheduler);
+		amd_sched_fini(&ring->sched);
 		ring->fence_drv.initialized = false;
 	}
 	mutex_unlock(&adev->ring_lock);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
index cbd3a486c5c2..7312d729d300 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
@@ -127,7 +127,7 @@ int amdgpu_gart_table_vram_alloc(struct amdgpu_device *adev)
 		r = amdgpu_bo_create(adev, adev->gart.table_size,
 				     PAGE_SIZE, true, AMDGPU_GEM_DOMAIN_VRAM,
 				     AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED,
-				     NULL, &adev->gart.robj);
+				     NULL, NULL, &adev->gart.robj);
 		if (r) {
 			return r;
 		}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index 5839fab374bf..7297ca3a0ba7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -69,7 +69,8 @@ int amdgpu_gem_object_create(struct amdgpu_device *adev, unsigned long size,
 		}
 	}
 retry:
-	r = amdgpu_bo_create(adev, size, alignment, kernel, initial_domain, flags, NULL, &robj);
+	r = amdgpu_bo_create(adev, size, alignment, kernel, initial_domain,
+			     flags, NULL, NULL, &robj);
 	if (r) {
 		if (r != -ERESTARTSYS) {
 			if (initial_domain == AMDGPU_GEM_DOMAIN_VRAM) {
@@ -426,6 +427,10 @@ int amdgpu_gem_metadata_ioctl(struct drm_device *dev, void *data,
 					   &args->data.data_size_bytes,
 					   &args->data.flags);
 	} else if (args->op == AMDGPU_GEM_METADATA_OP_SET_METADATA) {
+		if (args->data.data_size_bytes > sizeof(args->data.data)) {
+			r = -EINVAL;
+			goto unreserve;
+		}
 		r = amdgpu_bo_set_tiling_flags(robj, args->data.tiling_info);
 		if (!r)
 			r = amdgpu_bo_set_metadata(robj, args->data.data,
@@ -433,6 +438,7 @@ int amdgpu_gem_metadata_ioctl(struct drm_device *dev, void *data,
 						   args->data.flags);
 	}
 
+unreserve:
 	amdgpu_bo_unreserve(robj);
 out:
 	drm_gem_object_unreference_unlocked(gobj);
@@ -454,11 +460,12 @@ static void amdgpu_gem_va_update_vm(struct amdgpu_device *adev,
 	struct ttm_validate_buffer tv, *entry;
 	struct amdgpu_bo_list_entry *vm_bos;
 	struct ww_acquire_ctx ticket;
-	struct list_head list;
+	struct list_head list, duplicates;
 	unsigned domain;
 	int r;
 
 	INIT_LIST_HEAD(&list);
+	INIT_LIST_HEAD(&duplicates);
 
 	tv.bo = &bo_va->bo->tbo;
 	tv.shared = true;
@@ -468,7 +475,8 @@ static void amdgpu_gem_va_update_vm(struct amdgpu_device *adev,
 	if (!vm_bos)
 		return;
 
-	r = ttm_eu_reserve_buffers(&ticket, &list, true, NULL);
+	/* Provide duplicates to avoid -EALREADY */
+	r = ttm_eu_reserve_buffers(&ticket, &list, true, &duplicates);
 	if (r)
 		goto error_free;
 
@@ -651,7 +659,7 @@ int amdgpu_mode_dumb_create(struct drm_file *file_priv,
 	int r;
 
 	args->pitch = amdgpu_align_pitch(adev, args->width, args->bpp, 0) * ((args->bpp + 1) / 8);
-	args->size = args->pitch * args->height;
+	args->size = (u64)args->pitch * args->height;
 	args->size = ALIGN(args->size, PAGE_SIZE);
 
 	r = amdgpu_gem_object_create(adev, args->size, 0,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c
index 5c8a803acedc..534fc04e80fd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c
@@ -43,7 +43,7 @@ static int amdgpu_ih_ring_alloc(struct amdgpu_device *adev)
 		r = amdgpu_bo_create(adev, adev->irq.ih.ring_size,
 				     PAGE_SIZE, true,
 				     AMDGPU_GEM_DOMAIN_GTT, 0,
-				     NULL, &adev->irq.ih.ring_obj);
+				     NULL, NULL, &adev->irq.ih.ring_obj);
 		if (r) {
 			DRM_ERROR("amdgpu: failed to create ih ring buffer (%d).\n", r);
 			return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
index 0aba8e9bc8a0..7c42ff670080 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
@@ -140,7 +140,7 @@ void amdgpu_irq_preinstall(struct drm_device *dev)
  */
 int amdgpu_irq_postinstall(struct drm_device *dev)
 {
-	dev->max_vblank_count = 0x001fffff;
+	dev->max_vblank_count = 0x00ffffff;
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index 22367939ebf1..8c735f544b66 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -390,7 +390,7 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 				    min((size_t)size, sizeof(vram_gtt))) ? -EFAULT : 0;
 	}
 	case AMDGPU_INFO_READ_MMR_REG: {
-		unsigned n, alloc_size = info->read_mmr_reg.count * 4;
+		unsigned n, alloc_size;
 		uint32_t *regs;
 		unsigned se_num = (info->read_mmr_reg.instance >>
 				   AMDGPU_INFO_MMR_SE_INDEX_SHIFT) &
@@ -406,9 +406,10 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 		if (sh_num == AMDGPU_INFO_MMR_SH_INDEX_MASK)
 			sh_num = 0xffffffff;
 
-		regs = kmalloc(alloc_size, GFP_KERNEL);
+		regs = kmalloc_array(info->read_mmr_reg.count, sizeof(*regs), GFP_KERNEL);
 		if (!regs)
 			return -ENOMEM;
+		alloc_size = info->read_mmr_reg.count * sizeof(*regs);
 
 		for (i = 0; i < info->read_mmr_reg.count; i++)
 			if (amdgpu_asic_read_register(adev, se_num, sh_num,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 08b09d55b96f..1a7708f365f3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -215,6 +215,7 @@ int amdgpu_bo_create_restricted(struct amdgpu_device *adev,
 				bool kernel, u32 domain, u64 flags,
 				struct sg_table *sg,
 				struct ttm_placement *placement,
+				struct reservation_object *resv,
 				struct amdgpu_bo **bo_ptr)
 {
 	struct amdgpu_bo *bo;
@@ -261,7 +262,7 @@ int amdgpu_bo_create_restricted(struct amdgpu_device *adev,
 	/* Kernel allocation are uninterruptible */
 	r = ttm_bo_init(&adev->mman.bdev, &bo->tbo, size, type,
 			&bo->placement, page_align, !kernel, NULL,
-			acc_size, sg, NULL, &amdgpu_ttm_bo_destroy);
+			acc_size, sg, resv, &amdgpu_ttm_bo_destroy);
 	if (unlikely(r != 0)) {
 		return r;
 	}
@@ -275,7 +276,9 @@ int amdgpu_bo_create_restricted(struct amdgpu_device *adev,
 int amdgpu_bo_create(struct amdgpu_device *adev,
 		     unsigned long size, int byte_align,
 		     bool kernel, u32 domain, u64 flags,
-		     struct sg_table *sg, struct amdgpu_bo **bo_ptr)
+		     struct sg_table *sg,
+		     struct reservation_object *resv,
+		     struct amdgpu_bo **bo_ptr)
 {
 	struct ttm_placement placement = {0};
 	struct ttm_place placements[AMDGPU_GEM_DOMAIN_MAX + 1];
@@ -286,11 +289,9 @@ int amdgpu_bo_create(struct amdgpu_device *adev,
 	amdgpu_ttm_placement_init(adev, &placement,
 				  placements, domain, flags);
 
-	return amdgpu_bo_create_restricted(adev, size, byte_align,
-					   kernel, domain, flags,
-					   sg,
-					   &placement,
-					   bo_ptr);
+	return amdgpu_bo_create_restricted(adev, size, byte_align, kernel,
+					   domain, flags, sg, &placement,
+					   resv, bo_ptr);
 }
 
 int amdgpu_bo_kmap(struct amdgpu_bo *bo, void **ptr)
@@ -535,12 +536,10 @@ int amdgpu_bo_set_metadata (struct amdgpu_bo *bo, void *metadata,
 	if (metadata == NULL)
 		return -EINVAL;
 
-	buffer = kzalloc(metadata_size, GFP_KERNEL);
+	buffer = kmemdup(metadata, metadata_size, GFP_KERNEL);
 	if (buffer == NULL)
 		return -ENOMEM;
 
-	memcpy(buffer, metadata, metadata_size);
-
 	kfree(bo->metadata);
 	bo->metadata_flags = flags;
 	bo->metadata = buffer;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
index 6ea18dcec561..3c2ff4567798 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
@@ -129,12 +129,14 @@ int amdgpu_bo_create(struct amdgpu_device *adev,
 			    unsigned long size, int byte_align,
 			    bool kernel, u32 domain, u64 flags,
 			    struct sg_table *sg,
+			    struct reservation_object *resv,
 			    struct amdgpu_bo **bo_ptr);
 int amdgpu_bo_create_restricted(struct amdgpu_device *adev,
 				unsigned long size, int byte_align,
 				bool kernel, u32 domain, u64 flags,
 				struct sg_table *sg,
 				struct ttm_placement *placement,
+			        struct reservation_object *resv,
 				struct amdgpu_bo **bo_ptr);
 int amdgpu_bo_kmap(struct amdgpu_bo *bo, void **ptr);
 void amdgpu_bo_kunmap(struct amdgpu_bo *bo);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
index d9652fe32d6a..59f735a933a9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
@@ -61,12 +61,15 @@ struct drm_gem_object *amdgpu_gem_prime_import_sg_table(struct drm_device *dev,
 							struct dma_buf_attachment *attach,
 							struct sg_table *sg)
 {
+	struct reservation_object *resv = attach->dmabuf->resv;
 	struct amdgpu_device *adev = dev->dev_private;
 	struct amdgpu_bo *bo;
 	int ret;
 
+	ww_mutex_lock(&resv->lock, NULL);
 	ret = amdgpu_bo_create(adev, attach->dmabuf->size, PAGE_SIZE, false,
-			       AMDGPU_GEM_DOMAIN_GTT, 0, sg, &bo);
+			       AMDGPU_GEM_DOMAIN_GTT, 0, sg, resv, &bo);
+	ww_mutex_unlock(&resv->lock);
 	if (ret)
 		return ERR_PTR(ret);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
index 9bec91484c24..30dce235ddeb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
@@ -357,11 +357,11 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring,
 		ring->adev = adev;
 		ring->idx = adev->num_rings++;
 		adev->rings[ring->idx] = ring;
-		amdgpu_fence_driver_init_ring(ring);
+		r = amdgpu_fence_driver_init_ring(ring);
+		if (r)
+			return r;
 	}
 
-	init_waitqueue_head(&ring->fence_drv.fence_queue);
-
 	r = amdgpu_wb_get(adev, &ring->rptr_offs);
 	if (r) {
 		dev_err(adev->dev, "(%d) ring rptr_offs wb alloc failed\n", r);
@@ -407,7 +407,7 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring,
 	if (ring->ring_obj == NULL) {
 		r = amdgpu_bo_create(adev, ring->ring_size, PAGE_SIZE, true,
 				     AMDGPU_GEM_DOMAIN_GTT, 0,
-				     NULL, &ring->ring_obj);
+				     NULL, NULL, &ring->ring_obj);
 		if (r) {
 			dev_err(adev->dev, "(%d) ring create failed\n", r);
 			return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c
index 74dad270362c..e90712443fe9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c
@@ -64,8 +64,8 @@ int amdgpu_sa_bo_manager_init(struct amdgpu_device *adev,
 		INIT_LIST_HEAD(&sa_manager->flist[i]);
 	}
 
-	r = amdgpu_bo_create(adev, size, align, true,
-			     domain, 0, NULL, &sa_manager->bo);
+	r = amdgpu_bo_create(adev, size, align, true, domain,
+			     0, NULL, NULL, &sa_manager->bo);
 	if (r) {
 		dev_err(adev->dev, "(%d) failed to allocate bo for manager\n", r);
 		return r;
@@ -145,8 +145,13 @@ static uint32_t amdgpu_sa_get_ring_from_fence(struct fence *f)
 	struct amd_sched_fence *s_fence;
 
 	s_fence = to_amd_sched_fence(f);
-	if (s_fence)
-		return s_fence->scheduler->ring_id;
+	if (s_fence) {
+		struct amdgpu_ring *ring;
+
+		ring = container_of(s_fence->sched, struct amdgpu_ring, sched);
+		return ring->idx;
+	}
+
 	a_fence = to_amdgpu_fence(f);
 	if (a_fence)
 		return a_fence->ring->idx;
@@ -412,6 +417,26 @@ void amdgpu_sa_bo_free(struct amdgpu_device *adev, struct amdgpu_sa_bo **sa_bo,
 }
 
 #if defined(CONFIG_DEBUG_FS)
+
+static void amdgpu_sa_bo_dump_fence(struct fence *fence, struct seq_file *m)
+{
+	struct amdgpu_fence *a_fence = to_amdgpu_fence(fence);
+	struct amd_sched_fence *s_fence = to_amd_sched_fence(fence);
+
+	if (a_fence)
+		seq_printf(m, " protected by 0x%016llx on ring %d",
+			   a_fence->seq, a_fence->ring->idx);
+
+	if (s_fence) {
+		struct amdgpu_ring *ring;
+
+
+		ring = container_of(s_fence->sched, struct amdgpu_ring, sched);
+		seq_printf(m, " protected by 0x%016x on ring %d",
+			   s_fence->base.seqno, ring->idx);
+	}
+}
+
 void amdgpu_sa_bo_dump_debug_info(struct amdgpu_sa_manager *sa_manager,
 				  struct seq_file *m)
 {
@@ -428,18 +453,8 @@ void amdgpu_sa_bo_dump_debug_info(struct amdgpu_sa_manager *sa_manager,
 		}
 		seq_printf(m, "[0x%010llx 0x%010llx] size %8lld",
 			   soffset, eoffset, eoffset - soffset);
-		if (i->fence) {
-			struct amdgpu_fence *a_fence = to_amdgpu_fence(i->fence);
-			struct amd_sched_fence *s_fence = to_amd_sched_fence(i->fence);
-			if (a_fence)
-				seq_printf(m, " protected by 0x%016llx on ring %d",
-					   a_fence->seq, a_fence->ring->idx);
-			if (s_fence)
-				seq_printf(m, " protected by 0x%016x on ring %d",
-					   s_fence->base.seqno,
-					   s_fence->scheduler->ring_id);
-
-		}
+		if (i->fence)
+			amdgpu_sa_bo_dump_fence(i->fence, m);
 		seq_printf(m, "\n");
 	}
 	spin_unlock(&sa_manager->wq.lock);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c
index de98fbd2971e..2e946b2cad88 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c
@@ -27,63 +27,48 @@
 #include <drm/drmP.h>
 #include "amdgpu.h"
 
-static struct fence *amdgpu_sched_dependency(struct amd_sched_job *job)
+static struct fence *amdgpu_sched_dependency(struct amd_sched_job *sched_job)
 {
-	struct amdgpu_job *sched_job = (struct amdgpu_job *)job;
-	return amdgpu_sync_get_fence(&sched_job->ibs->sync);
+	struct amdgpu_job *job = to_amdgpu_job(sched_job);
+	return amdgpu_sync_get_fence(&job->ibs->sync);
 }
 
-static struct fence *amdgpu_sched_run_job(struct amd_sched_job *job)
+static struct fence *amdgpu_sched_run_job(struct amd_sched_job *sched_job)
 {
-	struct amdgpu_job *sched_job;
-	struct amdgpu_fence *fence;
+	struct amdgpu_fence *fence = NULL;
+	struct amdgpu_job *job;
 	int r;
 
-	if (!job) {
+	if (!sched_job) {
 		DRM_ERROR("job is null\n");
 		return NULL;
 	}
-	sched_job = (struct amdgpu_job *)job;
-	mutex_lock(&sched_job->job_lock);
-	r = amdgpu_ib_schedule(sched_job->adev,
-			       sched_job->num_ibs,
-			       sched_job->ibs,
-			       sched_job->base.owner);
-	if (r)
+	job = to_amdgpu_job(sched_job);
+	mutex_lock(&job->job_lock);
+	r = amdgpu_ib_schedule(job->adev,
+			       job->num_ibs,
+			       job->ibs,
+			       job->base.owner);
+	if (r) {
+		DRM_ERROR("Error scheduling IBs (%d)\n", r);
 		goto err;
-	fence = amdgpu_fence_ref(sched_job->ibs[sched_job->num_ibs - 1].fence);
-
-	if (sched_job->free_job)
-		sched_job->free_job(sched_job);
+	}
 
-	mutex_unlock(&sched_job->job_lock);
-	return &fence->base;
+	fence = amdgpu_fence_ref(job->ibs[job->num_ibs - 1].fence);
 
 err:
-	DRM_ERROR("Run job error\n");
-	mutex_unlock(&sched_job->job_lock);
-	job->sched->ops->process_job(job);
-	return NULL;
-}
+	if (job->free_job)
+		job->free_job(job);
 
-static void amdgpu_sched_process_job(struct amd_sched_job *job)
-{
-	struct amdgpu_job *sched_job;
-
-	if (!job) {
-		DRM_ERROR("job is null\n");
-		return;
-	}
-	sched_job = (struct amdgpu_job *)job;
-	/* after processing job, free memory */
-	fence_put(&sched_job->base.s_fence->base);
-	kfree(sched_job);
+	mutex_unlock(&job->job_lock);
+	fence_put(&job->base.s_fence->base);
+	kfree(job);
+	return fence ? &fence->base : NULL;
 }
 
 struct amd_sched_backend_ops amdgpu_sched_ops = {
 	.dependency = amdgpu_sched_dependency,
 	.run_job = amdgpu_sched_run_job,
-	.process_job = amdgpu_sched_process_job
 };
 
 int amdgpu_sched_ib_submit_kernel_helper(struct amdgpu_device *adev,
@@ -100,7 +85,7 @@ int amdgpu_sched_ib_submit_kernel_helper(struct amdgpu_device *adev,
 			kzalloc(sizeof(struct amdgpu_job), GFP_KERNEL);
 		if (!job)
 			return -ENOMEM;
-		job->base.sched = ring->scheduler;
+		job->base.sched = &ring->sched;
 		job->base.s_entity = &adev->kernel_ctx.rings[ring->idx].entity;
 		job->adev = adev;
 		job->ibs = ibs;
@@ -109,7 +94,7 @@ int amdgpu_sched_ib_submit_kernel_helper(struct amdgpu_device *adev,
 		mutex_init(&job->job_lock);
 		job->free_job = free_job;
 		mutex_lock(&job->job_lock);
-		r = amd_sched_entity_push_job((struct amd_sched_job *)job);
+		r = amd_sched_entity_push_job(&job->base);
 		if (r) {
 			mutex_unlock(&job->job_lock);
 			kfree(job);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
index 068aeaff7183..4921de15b451 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
@@ -65,8 +65,14 @@ static bool amdgpu_sync_same_dev(struct amdgpu_device *adev, struct fence *f)
 
 	if (a_fence)
 		return a_fence->ring->adev == adev;
-	if (s_fence)
-		return (struct amdgpu_device *)s_fence->scheduler->priv == adev;
+
+	if (s_fence) {
+		struct amdgpu_ring *ring;
+
+		ring = container_of(s_fence->sched, struct amdgpu_ring, sched);
+		return ring->adev == adev;
+	}
+
 	return false;
 }
 
@@ -251,6 +257,20 @@ int amdgpu_sync_wait(struct amdgpu_sync *sync)
 		fence_put(e->fence);
 		kfree(e);
 	}
+
+	if (amdgpu_enable_semaphores)
+		return 0;
+
+	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
+		struct amdgpu_fence *fence = sync->sync_to[i];
+		if (!fence)
+			continue;
+
+		r = fence_wait(&fence->base, false);
+		if (r)
+			return r;
+	}
+
 	return 0;
 }
 
@@ -285,7 +305,8 @@ int amdgpu_sync_rings(struct amdgpu_sync *sync,
 			return -EINVAL;
 		}
 
-		if (amdgpu_enable_scheduler || (count >= AMDGPU_NUM_SYNCS)) {
+		if (amdgpu_enable_scheduler || !amdgpu_enable_semaphores ||
+		    (count >= AMDGPU_NUM_SYNCS)) {
 			/* not enough room, wait manually */
 			r = fence_wait(&fence->base, false);
 			if (r)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c
index f80b1a43be8a..4865615e9c06 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c
@@ -59,8 +59,9 @@ static void amdgpu_do_test_moves(struct amdgpu_device *adev)
 		goto out_cleanup;
 	}
 
-	r = amdgpu_bo_create(adev, size, PAGE_SIZE, true, AMDGPU_GEM_DOMAIN_VRAM, 0,
-			     NULL, &vram_obj);
+	r = amdgpu_bo_create(adev, size, PAGE_SIZE, true,
+			     AMDGPU_GEM_DOMAIN_VRAM, 0,
+			     NULL, NULL, &vram_obj);
 	if (r) {
 		DRM_ERROR("Failed to create VRAM object\n");
 		goto out_cleanup;
@@ -80,7 +81,8 @@ static void amdgpu_do_test_moves(struct amdgpu_device *adev)
 		struct fence *fence = NULL;
 
 		r = amdgpu_bo_create(adev, size, PAGE_SIZE, true,
-				     AMDGPU_GEM_DOMAIN_GTT, 0, NULL, gtt_obj + i);
+				     AMDGPU_GEM_DOMAIN_GTT, 0, NULL,
+				     NULL, gtt_obj + i);
 		if (r) {
 			DRM_ERROR("Failed to create GTT object %d\n", i);
 			goto out_lclean;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index b5abd5cde413..364cbe975332 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -861,7 +861,7 @@ int amdgpu_ttm_init(struct amdgpu_device *adev)
 	r = amdgpu_bo_create(adev, 256 * 1024, PAGE_SIZE, true,
 			     AMDGPU_GEM_DOMAIN_VRAM,
 			     AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED,
-			     NULL, &adev->stollen_vga_memory);
+			     NULL, NULL, &adev->stollen_vga_memory);
 	if (r) {
 		return r;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
index 482e66797ae6..5cc95f1a7dab 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
@@ -247,7 +247,7 @@ int amdgpu_ucode_init_bo(struct amdgpu_device *adev)
 	const struct common_firmware_header *header = NULL;
 
 	err = amdgpu_bo_create(adev, adev->firmware.fw_size, PAGE_SIZE, true,
-			AMDGPU_GEM_DOMAIN_GTT, 0, NULL, bo);
+			AMDGPU_GEM_DOMAIN_GTT, 0, NULL, NULL, bo);
 	if (err) {
 		dev_err(adev->dev, "(%d) Firmware buffer allocate failed\n", err);
 		err = -ENOMEM;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
index 2cf6c6b06e3b..d0312364d950 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
@@ -156,7 +156,7 @@ int amdgpu_uvd_sw_init(struct amdgpu_device *adev)
 	r = amdgpu_bo_create(adev, bo_size, PAGE_SIZE, true,
 			     AMDGPU_GEM_DOMAIN_VRAM,
 			     AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED,
-			     NULL, &adev->uvd.vcpu_bo);
+			     NULL, NULL, &adev->uvd.vcpu_bo);
 	if (r) {
 		dev_err(adev->dev, "(%d) failed to allocate UVD bo\n", r);
 		return r;
@@ -543,46 +543,60 @@ static int amdgpu_uvd_cs_msg(struct amdgpu_uvd_cs_ctx *ctx,
 		return -EINVAL;
 	}
 
-	if (msg_type == 1) {
+	switch (msg_type) {
+	case 0:
+		/* it's a create msg, calc image size (width * height) */
+		amdgpu_bo_kunmap(bo);
+
+		/* try to alloc a new handle */
+		for (i = 0; i < AMDGPU_MAX_UVD_HANDLES; ++i) {
+			if (atomic_read(&adev->uvd.handles[i]) == handle) {
+				DRM_ERROR("Handle 0x%x already in use!\n", handle);
+				return -EINVAL;
+			}
+
+			if (!atomic_cmpxchg(&adev->uvd.handles[i], 0, handle)) {
+				adev->uvd.filp[i] = ctx->parser->filp;
+				return 0;
+			}
+		}
+
+		DRM_ERROR("No more free UVD handles!\n");
+		return -EINVAL;
+
+	case 1:
 		/* it's a decode msg, calc buffer sizes */
 		r = amdgpu_uvd_cs_msg_decode(msg, ctx->buf_sizes);
 		amdgpu_bo_kunmap(bo);
 		if (r)
 			return r;
 
-	} else if (msg_type == 2) {
+		/* validate the handle */
+		for (i = 0; i < AMDGPU_MAX_UVD_HANDLES; ++i) {
+			if (atomic_read(&adev->uvd.handles[i]) == handle) {
+				if (adev->uvd.filp[i] != ctx->parser->filp) {
+					DRM_ERROR("UVD handle collision detected!\n");
+					return -EINVAL;
+				}
+				return 0;
+			}
+		}
+
+		DRM_ERROR("Invalid UVD handle 0x%x!\n", handle);
+		return -ENOENT;
+
+	case 2:
 		/* it's a destroy msg, free the handle */
 		for (i = 0; i < AMDGPU_MAX_UVD_HANDLES; ++i)
 			atomic_cmpxchg(&adev->uvd.handles[i], handle, 0);
 		amdgpu_bo_kunmap(bo);
 		return 0;
-	} else {
-		/* it's a create msg */
-		amdgpu_bo_kunmap(bo);
-
-		if (msg_type != 0) {
-			DRM_ERROR("Illegal UVD message type (%d)!\n", msg_type);
-			return -EINVAL;
-		}
-
-		/* it's a create msg, no special handling needed */
-	}
-
-	/* create or decode, validate the handle */
-	for (i = 0; i < AMDGPU_MAX_UVD_HANDLES; ++i) {
-		if (atomic_read(&adev->uvd.handles[i]) == handle)
-			return 0;
-	}
 
-	/* handle not found try to alloc a new one */
-	for (i = 0; i < AMDGPU_MAX_UVD_HANDLES; ++i) {
-		if (!atomic_cmpxchg(&adev->uvd.handles[i], 0, handle)) {
-			adev->uvd.filp[i] = ctx->parser->filp;
-			return 0;
-		}
+	default:
+		DRM_ERROR("Illegal UVD message type (%d)!\n", msg_type);
+		return -EINVAL;
 	}
-
-	DRM_ERROR("No more free UVD handles!\n");
+	BUG();
 	return -EINVAL;
 }
 
@@ -805,10 +819,10 @@ int amdgpu_uvd_ring_parse_cs(struct amdgpu_cs_parser *parser, uint32_t ib_idx)
 }
 
 static int amdgpu_uvd_free_job(
-	struct amdgpu_job *sched_job)
+	struct amdgpu_job *job)
 {
-	amdgpu_ib_free(sched_job->adev, sched_job->ibs);
-	kfree(sched_job->ibs);
+	amdgpu_ib_free(job->adev, job->ibs);
+	kfree(job->ibs);
 	return 0;
 }
 
@@ -905,7 +919,7 @@ int amdgpu_uvd_get_create_msg(struct amdgpu_ring *ring, uint32_t handle,
 	r = amdgpu_bo_create(adev, 1024, PAGE_SIZE, true,
 			     AMDGPU_GEM_DOMAIN_VRAM,
 			     AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED,
-			     NULL, &bo);
+			     NULL, NULL, &bo);
 	if (r)
 		return r;
 
@@ -954,7 +968,7 @@ int amdgpu_uvd_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle,
 	r = amdgpu_bo_create(adev, 1024, PAGE_SIZE, true,
 			     AMDGPU_GEM_DOMAIN_VRAM,
 			     AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED,
-			     NULL, &bo);
+			     NULL, NULL, &bo);
 	if (r)
 		return r;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
index 3cab96c42aa8..74f2038ac747 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
@@ -143,7 +143,7 @@ int amdgpu_vce_sw_init(struct amdgpu_device *adev, unsigned long size)
 	r = amdgpu_bo_create(adev, size, PAGE_SIZE, true,
 			     AMDGPU_GEM_DOMAIN_VRAM,
 			     AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED,
-			     NULL, &adev->vce.vcpu_bo);
+			     NULL, NULL, &adev->vce.vcpu_bo);
 	if (r) {
 		dev_err(adev->dev, "(%d) failed to allocate VCE bo\n", r);
 		return r;
@@ -342,10 +342,10 @@ void amdgpu_vce_free_handles(struct amdgpu_device *adev, struct drm_file *filp)
 }
 
 static int amdgpu_vce_free_job(
-	struct amdgpu_job *sched_job)
+	struct amdgpu_job *job)
 {
-	amdgpu_ib_free(sched_job->adev, sched_job->ibs);
-	kfree(sched_job->ibs);
+	amdgpu_ib_free(job->adev, job->ibs);
+	kfree(job->ibs);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index f68b7cdc370a..1e14531353e0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -316,12 +316,12 @@ static void amdgpu_vm_update_pages(struct amdgpu_device *adev,
 	}
 }
 
-int amdgpu_vm_free_job(struct amdgpu_job *sched_job)
+int amdgpu_vm_free_job(struct amdgpu_job *job)
 {
 	int i;
-	for (i = 0; i < sched_job->num_ibs; i++)
-		amdgpu_ib_free(sched_job->adev, &sched_job->ibs[i]);
-	kfree(sched_job->ibs);
+	for (i = 0; i < job->num_ibs; i++)
+		amdgpu_ib_free(job->adev, &job->ibs[i]);
+	kfree(job->ibs);
 	return 0;
 }
 
@@ -686,31 +686,6 @@ static int amdgpu_vm_update_ptes(struct amdgpu_device *adev,
 }
 
 /**
- * amdgpu_vm_fence_pts - fence page tables after an update
- *
- * @vm: requested vm
- * @start: start of GPU address range
- * @end: end of GPU address range
- * @fence: fence to use
- *
- * Fence the page tables in the range @start - @end (cayman+).
- *
- * Global and local mutex must be locked!
- */
-static void amdgpu_vm_fence_pts(struct amdgpu_vm *vm,
-				uint64_t start, uint64_t end,
-				struct fence *fence)
-{
-	unsigned i;
-
-	start >>= amdgpu_vm_block_size;
-	end >>= amdgpu_vm_block_size;
-
-	for (i = start; i <= end; ++i)
-		amdgpu_bo_fence(vm->page_tables[i].bo, fence, true);
-}
-
-/**
  * amdgpu_vm_bo_update_mapping - update a mapping in the vm page table
  *
  * @adev: amdgpu_device pointer
@@ -813,8 +788,7 @@ static int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev,
 	if (r)
 		goto error_free;
 
-	amdgpu_vm_fence_pts(vm, mapping->it.start,
-			    mapping->it.last + 1, f);
+	amdgpu_bo_fence(vm->page_directory, f, true);
 	if (fence) {
 		fence_put(*fence);
 		*fence = fence_get(f);
@@ -855,7 +829,7 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev,
 	int r;
 
 	if (mem) {
-		addr = mem->start << PAGE_SHIFT;
+		addr = (u64)mem->start << PAGE_SHIFT;
 		if (mem->mem_type != TTM_PL_TT)
 			addr += adev->vm_manager.vram_base_offset;
 	} else {
@@ -1089,6 +1063,7 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev,
 
 	/* walk over the address space and allocate the page tables */
 	for (pt_idx = saddr; pt_idx <= eaddr; ++pt_idx) {
+		struct reservation_object *resv = vm->page_directory->tbo.resv;
 		struct amdgpu_bo *pt;
 
 		if (vm->page_tables[pt_idx].bo)
@@ -1097,11 +1072,13 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev,
 		/* drop mutex to allocate and clear page table */
 		mutex_unlock(&vm->mutex);
 
+		ww_mutex_lock(&resv->lock, NULL);
 		r = amdgpu_bo_create(adev, AMDGPU_VM_PTE_COUNT * 8,
 				     AMDGPU_GPU_PAGE_SIZE, true,
 				     AMDGPU_GEM_DOMAIN_VRAM,
 				     AMDGPU_GEM_CREATE_NO_CPU_ACCESS,
-				     NULL, &pt);
+				     NULL, resv, &pt);
+		ww_mutex_unlock(&resv->lock);
 		if (r)
 			goto error_free;
 
@@ -1303,7 +1280,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 	r = amdgpu_bo_create(adev, pd_size, align, true,
 			     AMDGPU_GEM_DOMAIN_VRAM,
 			     AMDGPU_GEM_CREATE_NO_CPU_ACCESS,
-			     NULL, &vm->page_directory);
+			     NULL, NULL, &vm->page_directory);
 	if (r)
 		return r;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/cz_smc.c b/drivers/gpu/drm/amd/amdgpu/cz_smc.c
index a72ffc7d6c26..e33180d3314a 100644
--- a/drivers/gpu/drm/amd/amdgpu/cz_smc.c
+++ b/drivers/gpu/drm/amd/amdgpu/cz_smc.c
@@ -814,7 +814,8 @@ int cz_smu_init(struct amdgpu_device *adev)
 	* 3. map kernel virtual address
 	*/
 	ret = amdgpu_bo_create(adev, priv->toc_buffer.data_size, PAGE_SIZE,
-				true, AMDGPU_GEM_DOMAIN_GTT, 0, NULL, toc_buf);
+			       true, AMDGPU_GEM_DOMAIN_GTT, 0, NULL, NULL,
+			       toc_buf);
 
 	if (ret) {
 		dev_err(adev->dev, "(%d) SMC TOC buffer allocation failed\n", ret);
@@ -822,7 +823,8 @@ int cz_smu_init(struct amdgpu_device *adev)
 	}
 
 	ret = amdgpu_bo_create(adev, priv->smu_buffer.data_size, PAGE_SIZE,
-				true, AMDGPU_GEM_DOMAIN_GTT, 0, NULL, smu_buf);
+			       true, AMDGPU_GEM_DOMAIN_GTT, 0, NULL, NULL,
+			       smu_buf);
 
 	if (ret) {
 		dev_err(adev->dev, "(%d) SMC Internal buffer allocation failed\n", ret);
diff --git a/drivers/gpu/drm/amd/amdgpu/fiji_smc.c b/drivers/gpu/drm/amd/amdgpu/fiji_smc.c
index 322edea65857..bda1249eb871 100644
--- a/drivers/gpu/drm/amd/amdgpu/fiji_smc.c
+++ b/drivers/gpu/drm/amd/amdgpu/fiji_smc.c
@@ -764,7 +764,7 @@ int fiji_smu_init(struct amdgpu_device *adev)
 	ret = amdgpu_bo_create(adev, image_size, PAGE_SIZE,
 			       true, AMDGPU_GEM_DOMAIN_VRAM,
 			       AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED,
-			       NULL, toc_buf);
+			       NULL, NULL, toc_buf);
 	if (ret) {
 		DRM_ERROR("Failed to allocate memory for TOC buffer\n");
 		return -ENOMEM;
@@ -774,7 +774,7 @@ int fiji_smu_init(struct amdgpu_device *adev)
 	ret = amdgpu_bo_create(adev, smu_internal_buffer_size, PAGE_SIZE,
 			       true, AMDGPU_GEM_DOMAIN_VRAM,
 			       AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED,
-			       NULL, smu_buf);
+			       NULL, NULL, smu_buf);
 	if (ret) {
 		DRM_ERROR("Failed to allocate memory for SMU internal buffer\n");
 		return -ENOMEM;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
index 4bd1e5cf65ca..e992bf2ff66c 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
@@ -3206,7 +3206,7 @@ static int gfx_v7_0_mec_init(struct amdgpu_device *adev)
 		r = amdgpu_bo_create(adev,
 				     adev->gfx.mec.num_mec *adev->gfx.mec.num_pipe * MEC_HPD_SIZE * 2,
 				     PAGE_SIZE, true,
-				     AMDGPU_GEM_DOMAIN_GTT, 0, NULL,
+				     AMDGPU_GEM_DOMAIN_GTT, 0, NULL, NULL,
 				     &adev->gfx.mec.hpd_eop_obj);
 		if (r) {
 			dev_warn(adev->dev, "(%d) create HDP EOP bo failed\n", r);
@@ -3373,7 +3373,7 @@ static int gfx_v7_0_cp_compute_resume(struct amdgpu_device *adev)
 			r = amdgpu_bo_create(adev,
 					     sizeof(struct bonaire_mqd),
 					     PAGE_SIZE, true,
-					     AMDGPU_GEM_DOMAIN_GTT, 0, NULL,
+					     AMDGPU_GEM_DOMAIN_GTT, 0, NULL, NULL,
 					     &ring->mqd_obj);
 			if (r) {
 				dev_warn(adev->dev, "(%d) create MQD bo failed\n", r);
@@ -3610,41 +3610,6 @@ static int gfx_v7_0_cp_resume(struct amdgpu_device *adev)
 	return 0;
 }
 
-static void gfx_v7_0_ce_sync_me(struct amdgpu_ring *ring)
-{
-	struct amdgpu_device *adev = ring->adev;
-	u64 gpu_addr = adev->wb.gpu_addr + adev->gfx.ce_sync_offs * 4;
-
-	/* instruct DE to set a magic number */
-	amdgpu_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
-	amdgpu_ring_write(ring, (WRITE_DATA_ENGINE_SEL(0) |
-							 WRITE_DATA_DST_SEL(5)));
-	amdgpu_ring_write(ring, gpu_addr & 0xfffffffc);
-	amdgpu_ring_write(ring, upper_32_bits(gpu_addr) & 0xffffffff);
-	amdgpu_ring_write(ring, 1);
-
-	/* let CE wait till condition satisfied */
-	amdgpu_ring_write(ring, PACKET3(PACKET3_WAIT_REG_MEM, 5));
-	amdgpu_ring_write(ring, (WAIT_REG_MEM_OPERATION(0) | /* wait */
-							 WAIT_REG_MEM_MEM_SPACE(1) | /* memory */
-							 WAIT_REG_MEM_FUNCTION(3) |  /* == */
-							 WAIT_REG_MEM_ENGINE(2)));   /* ce */
-	amdgpu_ring_write(ring, gpu_addr & 0xfffffffc);
-	amdgpu_ring_write(ring, upper_32_bits(gpu_addr) & 0xffffffff);
-	amdgpu_ring_write(ring, 1);
-	amdgpu_ring_write(ring, 0xffffffff);
-	amdgpu_ring_write(ring, 4); /* poll interval */
-
-	/* instruct CE to reset wb of ce_sync to zero */
-	amdgpu_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
-	amdgpu_ring_write(ring, (WRITE_DATA_ENGINE_SEL(2) |
-							 WRITE_DATA_DST_SEL(5) |
-							 WR_CONFIRM));
-	amdgpu_ring_write(ring, gpu_addr & 0xfffffffc);
-	amdgpu_ring_write(ring, upper_32_bits(gpu_addr) & 0xffffffff);
-	amdgpu_ring_write(ring, 0);
-}
-
 /*
  * vm
  * VMID 0 is the physical GPU addresses as used by the kernel.
@@ -3663,6 +3628,13 @@ static void gfx_v7_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
 					unsigned vm_id, uint64_t pd_addr)
 {
 	int usepfp = (ring->type == AMDGPU_RING_TYPE_GFX);
+	if (usepfp) {
+		/* synce CE with ME to prevent CE fetch CEIB before context switch done */
+		amdgpu_ring_write(ring, PACKET3(PACKET3_SWITCH_BUFFER, 0));
+		amdgpu_ring_write(ring, 0);
+		amdgpu_ring_write(ring, PACKET3(PACKET3_SWITCH_BUFFER, 0));
+		amdgpu_ring_write(ring, 0);
+	}
 
 	amdgpu_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
 	amdgpu_ring_write(ring, (WRITE_DATA_ENGINE_SEL(usepfp) |
@@ -3703,7 +3675,10 @@ static void gfx_v7_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
 		amdgpu_ring_write(ring, 0x0);
 
 		/* synce CE with ME to prevent CE fetch CEIB before context switch done */
-		gfx_v7_0_ce_sync_me(ring);
+		amdgpu_ring_write(ring, PACKET3(PACKET3_SWITCH_BUFFER, 0));
+		amdgpu_ring_write(ring, 0);
+		amdgpu_ring_write(ring, PACKET3(PACKET3_SWITCH_BUFFER, 0));
+		amdgpu_ring_write(ring, 0);
 	}
 }
 
@@ -3788,7 +3763,8 @@ static int gfx_v7_0_rlc_init(struct amdgpu_device *adev)
 			r = amdgpu_bo_create(adev, dws * 4, PAGE_SIZE, true,
 					     AMDGPU_GEM_DOMAIN_VRAM,
 					     AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED,
-					     NULL, &adev->gfx.rlc.save_restore_obj);
+					     NULL, NULL,
+					     &adev->gfx.rlc.save_restore_obj);
 			if (r) {
 				dev_warn(adev->dev, "(%d) create RLC sr bo failed\n", r);
 				return r;
@@ -3831,7 +3807,8 @@ static int gfx_v7_0_rlc_init(struct amdgpu_device *adev)
 			r = amdgpu_bo_create(adev, dws * 4, PAGE_SIZE, true,
 					     AMDGPU_GEM_DOMAIN_VRAM,
 					     AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED,
-					     NULL, &adev->gfx.rlc.clear_state_obj);
+					     NULL, NULL,
+					     &adev->gfx.rlc.clear_state_obj);
 			if (r) {
 				dev_warn(adev->dev, "(%d) create RLC c bo failed\n", r);
 				gfx_v7_0_rlc_fini(adev);
@@ -3870,7 +3847,8 @@ static int gfx_v7_0_rlc_init(struct amdgpu_device *adev)
 			r = amdgpu_bo_create(adev, adev->gfx.rlc.cp_table_size, PAGE_SIZE, true,
 					     AMDGPU_GEM_DOMAIN_VRAM,
 					     AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED,
-					     NULL, &adev->gfx.rlc.cp_table_obj);
+					     NULL, NULL,
+					     &adev->gfx.rlc.cp_table_obj);
 			if (r) {
 				dev_warn(adev->dev, "(%d) create RLC cp table bo failed\n", r);
 				gfx_v7_0_rlc_fini(adev);
@@ -4802,12 +4780,6 @@ static int gfx_v7_0_sw_init(void *handle)
 		return r;
 	}
 
-	r = amdgpu_wb_get(adev, &adev->gfx.ce_sync_offs);
-	if (r) {
-		DRM_ERROR("(%d) gfx.ce_sync_offs wb alloc failed\n", r);
-		return r;
-	}
-
 	for (i = 0; i < adev->gfx.num_gfx_rings; i++) {
 		ring = &adev->gfx.gfx_ring[i];
 		ring->ring_obj = NULL;
@@ -4851,21 +4823,21 @@ static int gfx_v7_0_sw_init(void *handle)
 	r = amdgpu_bo_create(adev, adev->gds.mem.gfx_partition_size,
 			PAGE_SIZE, true,
 			AMDGPU_GEM_DOMAIN_GDS, 0,
-			NULL, &adev->gds.gds_gfx_bo);
+			NULL, NULL, &adev->gds.gds_gfx_bo);
 	if (r)
 		return r;
 
 	r = amdgpu_bo_create(adev, adev->gds.gws.gfx_partition_size,
 		PAGE_SIZE, true,
 		AMDGPU_GEM_DOMAIN_GWS, 0,
-		NULL, &adev->gds.gws_gfx_bo);
+		NULL, NULL, &adev->gds.gws_gfx_bo);
 	if (r)
 		return r;
 
 	r = amdgpu_bo_create(adev, adev->gds.oa.gfx_partition_size,
 			PAGE_SIZE, true,
 			AMDGPU_GEM_DOMAIN_OA, 0,
-			NULL, &adev->gds.oa_gfx_bo);
+			NULL, NULL, &adev->gds.oa_gfx_bo);
 	if (r)
 		return r;
 
@@ -4886,8 +4858,6 @@ static int gfx_v7_0_sw_fini(void *handle)
 	for (i = 0; i < adev->gfx.num_compute_rings; i++)
 		amdgpu_ring_fini(&adev->gfx.compute_ring[i]);
 
-	amdgpu_wb_free(adev, adev->gfx.ce_sync_offs);
-
 	gfx_v7_0_cp_compute_fini(adev);
 	gfx_v7_0_rlc_fini(adev);
 	gfx_v7_0_mec_fini(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 53f07439a512..cb4f68f53f24 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -868,7 +868,7 @@ static int gfx_v8_0_mec_init(struct amdgpu_device *adev)
 		r = amdgpu_bo_create(adev,
 				     adev->gfx.mec.num_mec *adev->gfx.mec.num_pipe * MEC_HPD_SIZE * 2,
 				     PAGE_SIZE, true,
-				     AMDGPU_GEM_DOMAIN_GTT, 0, NULL,
+				     AMDGPU_GEM_DOMAIN_GTT, 0, NULL, NULL,
 				     &adev->gfx.mec.hpd_eop_obj);
 		if (r) {
 			dev_warn(adev->dev, "(%d) create HDP EOP bo failed\n", r);
@@ -940,12 +940,6 @@ static int gfx_v8_0_sw_init(void *handle)
 		return r;
 	}
 
-	r = amdgpu_wb_get(adev, &adev->gfx.ce_sync_offs);
-	if (r) {
-		DRM_ERROR("(%d) gfx.ce_sync_offs wb alloc failed\n", r);
-		return r;
-	}
-
 	/* set up the gfx ring */
 	for (i = 0; i < adev->gfx.num_gfx_rings; i++) {
 		ring = &adev->gfx.gfx_ring[i];
@@ -995,21 +989,21 @@ static int gfx_v8_0_sw_init(void *handle)
 	/* reserve GDS, GWS and OA resource for gfx */
 	r = amdgpu_bo_create(adev, adev->gds.mem.gfx_partition_size,
 			PAGE_SIZE, true,
-			AMDGPU_GEM_DOMAIN_GDS, 0,
+			AMDGPU_GEM_DOMAIN_GDS, 0, NULL,
 			NULL, &adev->gds.gds_gfx_bo);
 	if (r)
 		return r;
 
 	r = amdgpu_bo_create(adev, adev->gds.gws.gfx_partition_size,
 		PAGE_SIZE, true,
-		AMDGPU_GEM_DOMAIN_GWS, 0,
+		AMDGPU_GEM_DOMAIN_GWS, 0, NULL,
 		NULL, &adev->gds.gws_gfx_bo);
 	if (r)
 		return r;
 
 	r = amdgpu_bo_create(adev, adev->gds.oa.gfx_partition_size,
 			PAGE_SIZE, true,
-			AMDGPU_GEM_DOMAIN_OA, 0,
+			AMDGPU_GEM_DOMAIN_OA, 0, NULL,
 			NULL, &adev->gds.oa_gfx_bo);
 	if (r)
 		return r;
@@ -1033,8 +1027,6 @@ static int gfx_v8_0_sw_fini(void *handle)
 	for (i = 0; i < adev->gfx.num_compute_rings; i++)
 		amdgpu_ring_fini(&adev->gfx.compute_ring[i]);
 
-	amdgpu_wb_free(adev, adev->gfx.ce_sync_offs);
-
 	gfx_v8_0_mec_fini(adev);
 
 	return 0;
@@ -3106,7 +3098,7 @@ static int gfx_v8_0_cp_compute_resume(struct amdgpu_device *adev)
 					     sizeof(struct vi_mqd),
 					     PAGE_SIZE, true,
 					     AMDGPU_GEM_DOMAIN_GTT, 0, NULL,
-					     &ring->mqd_obj);
+					     NULL, &ring->mqd_obj);
 			if (r) {
 				dev_warn(adev->dev, "(%d) create MQD bo failed\n", r);
 				return r;
@@ -3965,6 +3957,7 @@ static void gfx_v8_0_ring_emit_fence_gfx(struct amdgpu_ring *ring, u64 addr,
 			  DATA_SEL(write64bit ? 2 : 1) | INT_SEL(int_sel ? 2 : 0));
 	amdgpu_ring_write(ring, lower_32_bits(seq));
 	amdgpu_ring_write(ring, upper_32_bits(seq));
+
 }
 
 /**
@@ -4005,49 +3998,34 @@ static bool gfx_v8_0_ring_emit_semaphore(struct amdgpu_ring *ring,
 	return true;
 }
 
-static void gfx_v8_0_ce_sync_me(struct amdgpu_ring *ring)
+static void gfx_v8_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
+					unsigned vm_id, uint64_t pd_addr)
 {
-	struct amdgpu_device *adev = ring->adev;
-	u64 gpu_addr = adev->wb.gpu_addr + adev->gfx.ce_sync_offs * 4;
-
-	/* instruct DE to set a magic number */
-	amdgpu_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
-	amdgpu_ring_write(ring, (WRITE_DATA_ENGINE_SEL(0) |
-							 WRITE_DATA_DST_SEL(5)));
-	amdgpu_ring_write(ring, gpu_addr & 0xfffffffc);
-	amdgpu_ring_write(ring, upper_32_bits(gpu_addr) & 0xffffffff);
-	amdgpu_ring_write(ring, 1);
+	int usepfp = (ring->type == AMDGPU_RING_TYPE_GFX);
+	uint32_t seq = ring->fence_drv.sync_seq[ring->idx];
+	uint64_t addr = ring->fence_drv.gpu_addr;
 
-	/* let CE wait till condition satisfied */
 	amdgpu_ring_write(ring, PACKET3(PACKET3_WAIT_REG_MEM, 5));
-	amdgpu_ring_write(ring, (WAIT_REG_MEM_OPERATION(0) | /* wait */
-							 WAIT_REG_MEM_MEM_SPACE(1) | /* memory */
-							 WAIT_REG_MEM_FUNCTION(3) |  /* == */
-							 WAIT_REG_MEM_ENGINE(2)));   /* ce */
-	amdgpu_ring_write(ring, gpu_addr & 0xfffffffc);
-	amdgpu_ring_write(ring, upper_32_bits(gpu_addr) & 0xffffffff);
-	amdgpu_ring_write(ring, 1);
+	amdgpu_ring_write(ring, (WAIT_REG_MEM_MEM_SPACE(1) | /* memory */
+		 WAIT_REG_MEM_FUNCTION(3))); /* equal */
+	amdgpu_ring_write(ring, addr & 0xfffffffc);
+	amdgpu_ring_write(ring, upper_32_bits(addr) & 0xffffffff);
+	amdgpu_ring_write(ring, seq);
 	amdgpu_ring_write(ring, 0xffffffff);
 	amdgpu_ring_write(ring, 4); /* poll interval */
 
-	/* instruct CE to reset wb of ce_sync to zero */
-	amdgpu_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
-	amdgpu_ring_write(ring, (WRITE_DATA_ENGINE_SEL(2) |
-							 WRITE_DATA_DST_SEL(5) |
-							 WR_CONFIRM));
-	amdgpu_ring_write(ring, gpu_addr & 0xfffffffc);
-	amdgpu_ring_write(ring, upper_32_bits(gpu_addr) & 0xffffffff);
-	amdgpu_ring_write(ring, 0);
-}
-
-static void gfx_v8_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
-					unsigned vm_id, uint64_t pd_addr)
-{
-	int usepfp = (ring->type == AMDGPU_RING_TYPE_GFX);
+	if (usepfp) {
+		/* synce CE with ME to prevent CE fetch CEIB before context switch done */
+		amdgpu_ring_write(ring, PACKET3(PACKET3_SWITCH_BUFFER, 0));
+		amdgpu_ring_write(ring, 0);
+		amdgpu_ring_write(ring, PACKET3(PACKET3_SWITCH_BUFFER, 0));
+		amdgpu_ring_write(ring, 0);
+	}
 
 	amdgpu_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
 	amdgpu_ring_write(ring, (WRITE_DATA_ENGINE_SEL(usepfp) |
-				 WRITE_DATA_DST_SEL(0)));
+				 WRITE_DATA_DST_SEL(0)) |
+				 WR_CONFIRM);
 	if (vm_id < 8) {
 		amdgpu_ring_write(ring,
 				  (mmVM_CONTEXT0_PAGE_TABLE_BASE_ADDR + vm_id));
@@ -4083,9 +4061,10 @@ static void gfx_v8_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
 		/* sync PFP to ME, otherwise we might get invalid PFP reads */
 		amdgpu_ring_write(ring, PACKET3(PACKET3_PFP_SYNC_ME, 0));
 		amdgpu_ring_write(ring, 0x0);
-
-		/* synce CE with ME to prevent CE fetch CEIB before context switch done */
-		gfx_v8_0_ce_sync_me(ring);
+		amdgpu_ring_write(ring, PACKET3(PACKET3_SWITCH_BUFFER, 0));
+		amdgpu_ring_write(ring, 0);
+		amdgpu_ring_write(ring, PACKET3(PACKET3_SWITCH_BUFFER, 0));
+		amdgpu_ring_write(ring, 0);
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/iceland_smc.c b/drivers/gpu/drm/amd/amdgpu/iceland_smc.c
index c900aa942ade..966d4b2ed9da 100644
--- a/drivers/gpu/drm/amd/amdgpu/iceland_smc.c
+++ b/drivers/gpu/drm/amd/amdgpu/iceland_smc.c
@@ -625,7 +625,7 @@ int iceland_smu_init(struct amdgpu_device *adev)
 	ret = amdgpu_bo_create(adev, image_size, PAGE_SIZE,
 			       true, AMDGPU_GEM_DOMAIN_VRAM,
 			       AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED,
-			       NULL, toc_buf);
+			       NULL, NULL, toc_buf);
 	if (ret) {
 		DRM_ERROR("Failed to allocate memory for TOC buffer\n");
 		return -ENOMEM;
diff --git a/drivers/gpu/drm/amd/amdgpu/tonga_smc.c b/drivers/gpu/drm/amd/amdgpu/tonga_smc.c
index 1f5ac941a610..5421309c1862 100644
--- a/drivers/gpu/drm/amd/amdgpu/tonga_smc.c
+++ b/drivers/gpu/drm/amd/amdgpu/tonga_smc.c
@@ -763,7 +763,7 @@ int tonga_smu_init(struct amdgpu_device *adev)
 	ret = amdgpu_bo_create(adev, image_size, PAGE_SIZE,
 			       true, AMDGPU_GEM_DOMAIN_VRAM,
 			       AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED,
-			       NULL, toc_buf);
+			       NULL, NULL, toc_buf);
 	if (ret) {
 		DRM_ERROR("Failed to allocate memory for TOC buffer\n");
 		return -ENOMEM;
@@ -773,7 +773,7 @@ int tonga_smu_init(struct amdgpu_device *adev)
 	ret = amdgpu_bo_create(adev, smu_internal_buffer_size, PAGE_SIZE,
 			       true, AMDGPU_GEM_DOMAIN_VRAM,
 			       AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED,
-			       NULL, smu_buf);
+			       NULL, NULL, smu_buf);
 	if (ret) {
 		DRM_ERROR("Failed to allocate memory for SMU internal buffer\n");
 		return -ENOMEM;
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
index 5fac5da694f0..ed50dd725788 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
@@ -224,11 +224,11 @@ static int uvd_v4_2_suspend(void *handle)
 	int r;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	r = uvd_v4_2_hw_fini(adev);
+	r = amdgpu_uvd_suspend(adev);
 	if (r)
 		return r;
 
-	r = amdgpu_uvd_suspend(adev);
+	r = uvd_v4_2_hw_fini(adev);
 	if (r)
 		return r;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
index 2d5c59c318af..9ad8b9906c0b 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
@@ -220,11 +220,11 @@ static int uvd_v5_0_suspend(void *handle)
 	int r;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	r = uvd_v5_0_hw_fini(adev);
+	r = amdgpu_uvd_suspend(adev);
 	if (r)
 		return r;
 
-	r = amdgpu_uvd_suspend(adev);
+	r = uvd_v5_0_hw_fini(adev);
 	if (r)
 		return r;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
index d9f553fce531..7e9934fa4193 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
@@ -214,14 +214,16 @@ static int uvd_v6_0_suspend(void *handle)
 	int r;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	/* Skip this for APU for now */
+	if (!(adev->flags & AMD_IS_APU)) {
+		r = amdgpu_uvd_suspend(adev);
+		if (r)
+			return r;
+	}
 	r = uvd_v6_0_hw_fini(adev);
 	if (r)
 		return r;
 
-	r = amdgpu_uvd_suspend(adev);
-	if (r)
-		return r;
-
 	return r;
 }
 
@@ -230,10 +232,12 @@ static int uvd_v6_0_resume(void *handle)
 	int r;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	r = amdgpu_uvd_resume(adev);
-	if (r)
-		return r;
-
+	/* Skip this for APU for now */
+	if (!(adev->flags & AMD_IS_APU)) {
+		r = amdgpu_uvd_resume(adev);
+		if (r)
+			return r;
+	}
 	r = uvd_v6_0_hw_init(adev);
 	if (r)
 		return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index 552d9e75ad1b..b55ceb14fdcd 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -1400,7 +1400,8 @@ static int vi_common_early_init(void *handle)
 	case CHIP_CARRIZO:
 		adev->has_uvd = true;
 		adev->cg_flags = 0;
-		adev->pg_flags = AMDGPU_PG_SUPPORT_UVD | AMDGPU_PG_SUPPORT_VCE;
+		/* Disable UVD pg */
+		adev->pg_flags = /* AMDGPU_PG_SUPPORT_UVD | */AMDGPU_PG_SUPPORT_VCE;
 		adev->external_rev_id = adev->rev_id + 0x1;
 		if (amdgpu_smc_load_fw && smc_enabled)
 			adev->firmware.smu_load = true;
diff --git a/drivers/gpu/drm/amd/scheduler/gpu_sched_trace.h b/drivers/gpu/drm/amd/scheduler/gpu_sched_trace.h
new file mode 100644
index 000000000000..144f50acc971
--- /dev/null
+++ b/drivers/gpu/drm/amd/scheduler/gpu_sched_trace.h
@@ -0,0 +1,41 @@
+#if !defined(_GPU_SCHED_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _GPU_SCHED_TRACE_H_
+
+#include <linux/stringify.h>
+#include <linux/types.h>
+#include <linux/tracepoint.h>
+
+#include <drm/drmP.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM gpu_sched
+#define TRACE_INCLUDE_FILE gpu_sched_trace
+
+TRACE_EVENT(amd_sched_job,
+	    TP_PROTO(struct amd_sched_job *sched_job),
+	    TP_ARGS(sched_job),
+	    TP_STRUCT__entry(
+			     __field(struct amd_sched_entity *, entity)
+			     __field(const char *, name)
+			     __field(u32, job_count)
+			     __field(int, hw_job_count)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->entity = sched_job->s_entity;
+			   __entry->name = sched_job->sched->name;
+			   __entry->job_count = kfifo_len(
+				   &sched_job->s_entity->job_queue) / sizeof(sched_job);
+			   __entry->hw_job_count = atomic_read(
+				   &sched_job->sched->hw_rq_count);
+			   ),
+	    TP_printk("entity=%p, ring=%s, job count:%u, hw job count:%d",
+		      __entry->entity, __entry->name, __entry->job_count,
+		      __entry->hw_job_count)
+);
+#endif
+
+/* This part must be outside protection */
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#include <trace/define_trace.h>
diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
index 9259f1b6664c..3697eeeecf82 100644
--- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
+++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
@@ -27,6 +27,9 @@
 #include <drm/drmP.h>
 #include "gpu_scheduler.h"
 
+#define CREATE_TRACE_POINTS
+#include "gpu_sched_trace.h"
+
 static struct amd_sched_job *
 amd_sched_entity_pop_job(struct amd_sched_entity *entity);
 static void amd_sched_wakeup(struct amd_gpu_scheduler *sched);
@@ -65,29 +68,29 @@ static struct amd_sched_job *
 amd_sched_rq_select_job(struct amd_sched_rq *rq)
 {
 	struct amd_sched_entity *entity;
-	struct amd_sched_job *job;
+	struct amd_sched_job *sched_job;
 
 	spin_lock(&rq->lock);
 
 	entity = rq->current_entity;
 	if (entity) {
 		list_for_each_entry_continue(entity, &rq->entities, list) {
-			job = amd_sched_entity_pop_job(entity);
-			if (job) {
+			sched_job = amd_sched_entity_pop_job(entity);
+			if (sched_job) {
 				rq->current_entity = entity;
 				spin_unlock(&rq->lock);
-				return job;
+				return sched_job;
 			}
 		}
 	}
 
 	list_for_each_entry(entity, &rq->entities, list) {
 
-		job = amd_sched_entity_pop_job(entity);
-		if (job) {
+		sched_job = amd_sched_entity_pop_job(entity);
+		if (sched_job) {
 			rq->current_entity = entity;
 			spin_unlock(&rq->lock);
-			return job;
+			return sched_job;
 		}
 
 		if (entity == rq->current_entity)
@@ -115,23 +118,27 @@ int amd_sched_entity_init(struct amd_gpu_scheduler *sched,
 			  struct amd_sched_rq *rq,
 			  uint32_t jobs)
 {
+	int r;
+
 	if (!(sched && entity && rq))
 		return -EINVAL;
 
 	memset(entity, 0, sizeof(struct amd_sched_entity));
-	entity->belongto_rq = rq;
-	entity->scheduler = sched;
-	entity->fence_context = fence_context_alloc(1);
-	if(kfifo_alloc(&entity->job_queue,
-		       jobs * sizeof(void *),
-		       GFP_KERNEL))
-		return -EINVAL;
+	INIT_LIST_HEAD(&entity->list);
+	entity->rq = rq;
+	entity->sched = sched;
 
 	spin_lock_init(&entity->queue_lock);
+	r = kfifo_alloc(&entity->job_queue, jobs * sizeof(void *), GFP_KERNEL);
+	if (r)
+		return r;
+
 	atomic_set(&entity->fence_seq, 0);
+	entity->fence_context = fence_context_alloc(1);
 
 	/* Add the entity to the run queue */
 	amd_sched_rq_add_entity(rq, entity);
+
 	return 0;
 }
 
@@ -146,8 +153,8 @@ int amd_sched_entity_init(struct amd_gpu_scheduler *sched,
 static bool amd_sched_entity_is_initialized(struct amd_gpu_scheduler *sched,
 					    struct amd_sched_entity *entity)
 {
-	return entity->scheduler == sched &&
-		entity->belongto_rq != NULL;
+	return entity->sched == sched &&
+		entity->rq != NULL;
 }
 
 /**
@@ -177,7 +184,7 @@ static bool amd_sched_entity_is_idle(struct amd_sched_entity *entity)
 void amd_sched_entity_fini(struct amd_gpu_scheduler *sched,
 			   struct amd_sched_entity *entity)
 {
-	struct amd_sched_rq *rq = entity->belongto_rq;
+	struct amd_sched_rq *rq = entity->rq;
 
 	if (!amd_sched_entity_is_initialized(sched, entity))
 		return;
@@ -198,22 +205,22 @@ static void amd_sched_entity_wakeup(struct fence *f, struct fence_cb *cb)
 		container_of(cb, struct amd_sched_entity, cb);
 	entity->dependency = NULL;
 	fence_put(f);
-	amd_sched_wakeup(entity->scheduler);
+	amd_sched_wakeup(entity->sched);
 }
 
 static struct amd_sched_job *
 amd_sched_entity_pop_job(struct amd_sched_entity *entity)
 {
-	struct amd_gpu_scheduler *sched = entity->scheduler;
-	struct amd_sched_job *job;
+	struct amd_gpu_scheduler *sched = entity->sched;
+	struct amd_sched_job *sched_job;
 
 	if (ACCESS_ONCE(entity->dependency))
 		return NULL;
 
-	if (!kfifo_out_peek(&entity->job_queue, &job, sizeof(job)))
+	if (!kfifo_out_peek(&entity->job_queue, &sched_job, sizeof(sched_job)))
 		return NULL;
 
-	while ((entity->dependency = sched->ops->dependency(job))) {
+	while ((entity->dependency = sched->ops->dependency(sched_job))) {
 
 		if (fence_add_callback(entity->dependency, &entity->cb,
 				       amd_sched_entity_wakeup))
@@ -222,32 +229,33 @@ amd_sched_entity_pop_job(struct amd_sched_entity *entity)
 			return NULL;
 	}
 
-	return job;
+	return sched_job;
 }
 
 /**
  * Helper to submit a job to the job queue
  *
- * @job		The pointer to job required to submit
+ * @sched_job		The pointer to job required to submit
  *
  * Returns true if we could submit the job.
  */
-static bool amd_sched_entity_in(struct amd_sched_job *job)
+static bool amd_sched_entity_in(struct amd_sched_job *sched_job)
 {
-	struct amd_sched_entity *entity = job->s_entity;
+	struct amd_sched_entity *entity = sched_job->s_entity;
 	bool added, first = false;
 
 	spin_lock(&entity->queue_lock);
-	added = kfifo_in(&entity->job_queue, &job, sizeof(job)) == sizeof(job);
+	added = kfifo_in(&entity->job_queue, &sched_job,
+			sizeof(sched_job)) == sizeof(sched_job);
 
-	if (added && kfifo_len(&entity->job_queue) == sizeof(job))
+	if (added && kfifo_len(&entity->job_queue) == sizeof(sched_job))
 		first = true;
 
 	spin_unlock(&entity->queue_lock);
 
 	/* first job wakes up scheduler */
 	if (first)
-		amd_sched_wakeup(job->sched);
+		amd_sched_wakeup(sched_job->sched);
 
 	return added;
 }
@@ -255,7 +263,7 @@ static bool amd_sched_entity_in(struct amd_sched_job *job)
 /**
  * Submit a job to the job queue
  *
- * @job		The pointer to job required to submit
+ * @sched_job		The pointer to job required to submit
  *
  * Returns 0 for success, negative error code otherwise.
  */
@@ -271,9 +279,9 @@ int amd_sched_entity_push_job(struct amd_sched_job *sched_job)
 	fence_get(&fence->base);
 	sched_job->s_fence = fence;
 
-	wait_event(entity->scheduler->job_scheduled,
+	wait_event(entity->sched->job_scheduled,
 		   amd_sched_entity_in(sched_job));
-
+	trace_amd_sched_job(sched_job);
 	return 0;
 }
 
@@ -301,30 +309,28 @@ static void amd_sched_wakeup(struct amd_gpu_scheduler *sched)
 static struct amd_sched_job *
 amd_sched_select_job(struct amd_gpu_scheduler *sched)
 {
-	struct amd_sched_job *job;
+	struct amd_sched_job *sched_job;
 
 	if (!amd_sched_ready(sched))
 		return NULL;
 
 	/* Kernel run queue has higher priority than normal run queue*/
-	job = amd_sched_rq_select_job(&sched->kernel_rq);
-	if (job == NULL)
-		job = amd_sched_rq_select_job(&sched->sched_rq);
+	sched_job = amd_sched_rq_select_job(&sched->kernel_rq);
+	if (sched_job == NULL)
+		sched_job = amd_sched_rq_select_job(&sched->sched_rq);
 
-	return job;
+	return sched_job;
 }
 
 static void amd_sched_process_job(struct fence *f, struct fence_cb *cb)
 {
-	struct amd_sched_job *sched_job =
-		container_of(cb, struct amd_sched_job, cb);
-	struct amd_gpu_scheduler *sched;
+	struct amd_sched_fence *s_fence =
+		container_of(cb, struct amd_sched_fence, cb);
+	struct amd_gpu_scheduler *sched = s_fence->sched;
 
-	sched = sched_job->sched;
-	amd_sched_fence_signal(sched_job->s_fence);
 	atomic_dec(&sched->hw_rq_count);
-	fence_put(&sched_job->s_fence->base);
-	sched->ops->process_job(sched_job);
+	amd_sched_fence_signal(s_fence);
+	fence_put(&s_fence->base);
 	wake_up_interruptible(&sched->wake_up_worker);
 }
 
@@ -338,87 +344,82 @@ static int amd_sched_main(void *param)
 
 	while (!kthread_should_stop()) {
 		struct amd_sched_entity *entity;
-		struct amd_sched_job *job;
+		struct amd_sched_fence *s_fence;
+		struct amd_sched_job *sched_job;
 		struct fence *fence;
 
 		wait_event_interruptible(sched->wake_up_worker,
 			kthread_should_stop() ||
-			(job = amd_sched_select_job(sched)));
+			(sched_job = amd_sched_select_job(sched)));
 
-		if (!job)
+		if (!sched_job)
 			continue;
 
-		entity = job->s_entity;
+		entity = sched_job->s_entity;
+		s_fence = sched_job->s_fence;
 		atomic_inc(&sched->hw_rq_count);
-		fence = sched->ops->run_job(job);
+		fence = sched->ops->run_job(sched_job);
 		if (fence) {
-			r = fence_add_callback(fence, &job->cb,
+			r = fence_add_callback(fence, &s_fence->cb,
 					       amd_sched_process_job);
 			if (r == -ENOENT)
-				amd_sched_process_job(fence, &job->cb);
+				amd_sched_process_job(fence, &s_fence->cb);
 			else if (r)
 				DRM_ERROR("fence add callback failed (%d)\n", r);
 			fence_put(fence);
+		} else {
+			DRM_ERROR("Failed to run job!\n");
+			amd_sched_process_job(NULL, &s_fence->cb);
 		}
 
-		count = kfifo_out(&entity->job_queue, &job, sizeof(job));
-		WARN_ON(count != sizeof(job));
+		count = kfifo_out(&entity->job_queue, &sched_job,
+				sizeof(sched_job));
+		WARN_ON(count != sizeof(sched_job));
 		wake_up(&sched->job_scheduled);
 	}
 	return 0;
 }
 
 /**
- * Create a gpu scheduler
+ * Init a gpu scheduler instance
  *
+ * @sched		The pointer to the scheduler
  * @ops			The backend operations for this scheduler.
- * @ring		The the ring id for the scheduler.
  * @hw_submissions	Number of hw submissions to do.
+ * @name		Name used for debugging
  *
- * Return the pointer to scheduler for success, otherwise return NULL
+ * Return 0 on success, otherwise error code.
 */
-struct amd_gpu_scheduler *amd_sched_create(struct amd_sched_backend_ops *ops,
-					   unsigned ring, unsigned hw_submission,
-					   void *priv)
+int amd_sched_init(struct amd_gpu_scheduler *sched,
+		   struct amd_sched_backend_ops *ops,
+		   unsigned hw_submission, const char *name)
 {
-	struct amd_gpu_scheduler *sched;
-
-	sched = kzalloc(sizeof(struct amd_gpu_scheduler), GFP_KERNEL);
-	if (!sched)
-		return NULL;
-
 	sched->ops = ops;
-	sched->ring_id = ring;
 	sched->hw_submission_limit = hw_submission;
-	sched->priv = priv;
-	snprintf(sched->name, sizeof(sched->name), "amdgpu[%d]", ring);
+	sched->name = name;
 	amd_sched_rq_init(&sched->sched_rq);
 	amd_sched_rq_init(&sched->kernel_rq);
 
 	init_waitqueue_head(&sched->wake_up_worker);
 	init_waitqueue_head(&sched->job_scheduled);
 	atomic_set(&sched->hw_rq_count, 0);
+
 	/* Each scheduler will run on a seperate kernel thread */
 	sched->thread = kthread_run(amd_sched_main, sched, sched->name);
 	if (IS_ERR(sched->thread)) {
-		DRM_ERROR("Failed to create scheduler for id %d.\n", ring);
-		kfree(sched);
-		return NULL;
+		DRM_ERROR("Failed to create scheduler for %s.\n", name);
+		return PTR_ERR(sched->thread);
 	}
 
-	return sched;
+	return 0;
 }
 
 /**
  * Destroy a gpu scheduler
  *
  * @sched	The pointer to the scheduler
- *
- * return 0 if succeed. -1 if failed.
  */
-int amd_sched_destroy(struct amd_gpu_scheduler *sched)
+void amd_sched_fini(struct amd_gpu_scheduler *sched)
 {
 	kthread_stop(sched->thread);
-	kfree(sched);
-	return  0;
 }
diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h
index 2af0e4d4d817..80b64dc22214 100644
--- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h
+++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h
@@ -38,13 +38,15 @@ struct amd_sched_rq;
 */
 struct amd_sched_entity {
 	struct list_head		list;
-	struct amd_sched_rq		*belongto_rq;
-	atomic_t			fence_seq;
-	/* the job_queue maintains the jobs submitted by clients */
-	struct kfifo                    job_queue;
+	struct amd_sched_rq		*rq;
+	struct amd_gpu_scheduler	*sched;
+
 	spinlock_t			queue_lock;
-	struct amd_gpu_scheduler	*scheduler;
+	struct kfifo                    job_queue;
+
+	atomic_t			fence_seq;
 	uint64_t                        fence_context;
+
 	struct fence			*dependency;
 	struct fence_cb			cb;
 };
@@ -62,13 +64,13 @@ struct amd_sched_rq {
 
 struct amd_sched_fence {
 	struct fence                    base;
-	struct amd_gpu_scheduler	*scheduler;
+	struct fence_cb                 cb;
+	struct amd_gpu_scheduler	*sched;
 	spinlock_t			lock;
 	void                            *owner;
 };
 
 struct amd_sched_job {
-	struct fence_cb                 cb;
 	struct amd_gpu_scheduler        *sched;
 	struct amd_sched_entity         *s_entity;
 	struct amd_sched_fence          *s_fence;
@@ -91,32 +93,29 @@ static inline struct amd_sched_fence *to_amd_sched_fence(struct fence *f)
  * these functions should be implemented in driver side
 */
 struct amd_sched_backend_ops {
-	struct fence *(*dependency)(struct amd_sched_job *job);
-	struct fence *(*run_job)(struct amd_sched_job *job);
-	void (*process_job)(struct amd_sched_job *job);
+	struct fence *(*dependency)(struct amd_sched_job *sched_job);
+	struct fence *(*run_job)(struct amd_sched_job *sched_job);
 };
 
 /**
  * One scheduler is implemented for each hardware ring
 */
 struct amd_gpu_scheduler {
-	struct task_struct		*thread;
+	struct amd_sched_backend_ops	*ops;
+	uint32_t			hw_submission_limit;
+	const char			*name;
 	struct amd_sched_rq		sched_rq;
 	struct amd_sched_rq		kernel_rq;
-	atomic_t			hw_rq_count;
-	struct amd_sched_backend_ops	*ops;
-	uint32_t			ring_id;
 	wait_queue_head_t		wake_up_worker;
 	wait_queue_head_t		job_scheduled;
-	uint32_t                        hw_submission_limit;
-	char                            name[20];
-	void                            *priv;
+	atomic_t			hw_rq_count;
+	struct task_struct		*thread;
 };
 
-struct amd_gpu_scheduler *
-amd_sched_create(struct amd_sched_backend_ops *ops,
-		 uint32_t ring, uint32_t hw_submission, void *priv);
-int amd_sched_destroy(struct amd_gpu_scheduler *sched);
+int amd_sched_init(struct amd_gpu_scheduler *sched,
+		   struct amd_sched_backend_ops *ops,
+		   uint32_t hw_submission, const char *name);
+void amd_sched_fini(struct amd_gpu_scheduler *sched);
 
 int amd_sched_entity_init(struct amd_gpu_scheduler *sched,
 			  struct amd_sched_entity *entity,
diff --git a/drivers/gpu/drm/amd/scheduler/sched_fence.c b/drivers/gpu/drm/amd/scheduler/sched_fence.c
index e62c37920e11..d802638094f4 100644
--- a/drivers/gpu/drm/amd/scheduler/sched_fence.c
+++ b/drivers/gpu/drm/amd/scheduler/sched_fence.c
@@ -36,7 +36,7 @@ struct amd_sched_fence *amd_sched_fence_create(struct amd_sched_entity *s_entity
 	if (fence == NULL)
 		return NULL;
 	fence->owner = owner;
-	fence->scheduler = s_entity->scheduler;
+	fence->sched = s_entity->sched;
 	spin_lock_init(&fence->lock);
 
 	seq = atomic_inc_return(&s_entity->fence_seq);
@@ -63,7 +63,7 @@ static const char *amd_sched_fence_get_driver_name(struct fence *fence)
 static const char *amd_sched_fence_get_timeline_name(struct fence *f)
 {
 	struct amd_sched_fence *fence = to_amd_sched_fence(f);
-	return (const char *)fence->scheduler->name;
+	return (const char *)fence->sched->name;
 }
 
 static bool amd_sched_fence_enable_signaling(struct fence *f)
diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c
index 9a860ca1e9d7..d93e7378c077 100644
--- a/drivers/gpu/drm/drm_ioctl.c
+++ b/drivers/gpu/drm/drm_ioctl.c
@@ -520,7 +520,8 @@ EXPORT_SYMBOL(drm_ioctl_permit);
 
 /** Ioctl table */
 static const struct drm_ioctl_desc drm_ioctls[] = {
-	DRM_IOCTL_DEF(DRM_IOCTL_VERSION, drm_version, DRM_UNLOCKED|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF(DRM_IOCTL_VERSION, drm_version,
+		      DRM_UNLOCKED|DRM_RENDER_ALLOW|DRM_CONTROL_ALLOW),
 	DRM_IOCTL_DEF(DRM_IOCTL_GET_UNIQUE, drm_getunique, 0),
 	DRM_IOCTL_DEF(DRM_IOCTL_GET_MAGIC, drm_getmagic, 0),
 	DRM_IOCTL_DEF(DRM_IOCTL_IRQ_BUSID, drm_irq_by_busid, DRM_MASTER|DRM_ROOT_ONLY),
diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.c b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.c
index 82be6b86a168..d1e300dcd544 100644
--- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.c
+++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.c
@@ -58,7 +58,8 @@ static void fsl_dcu_drm_plane_atomic_disable(struct drm_plane *plane,
 					     struct drm_plane_state *old_state)
 {
 	struct fsl_dcu_drm_device *fsl_dev = plane->dev->dev_private;
-	unsigned int index, value, ret;
+	unsigned int value;
+	int index, ret;
 
 	index = fsl_dcu_drm_plane_index(plane);
 	if (index < 0)
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 5a244ab9395b..39d73dbc1c47 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -640,6 +640,32 @@ static int __intel_get_crtc_scanline(struct intel_crtc *crtc)
 		position = __raw_i915_read32(dev_priv, PIPEDSL(pipe)) & DSL_LINEMASK_GEN3;
 
 	/*
+	 * On HSW, the DSL reg (0x70000) appears to return 0 if we
+	 * read it just before the start of vblank.  So try it again
+	 * so we don't accidentally end up spanning a vblank frame
+	 * increment, causing the pipe_update_end() code to squak at us.
+	 *
+	 * The nature of this problem means we can't simply check the ISR
+	 * bit and return the vblank start value; nor can we use the scanline
+	 * debug register in the transcoder as it appears to have the same
+	 * problem.  We may need to extend this to include other platforms,
+	 * but so far testing only shows the problem on HSW.
+	 */
+	if (IS_HASWELL(dev) && !position) {
+		int i, temp;
+
+		for (i = 0; i < 100; i++) {
+			udelay(1);
+			temp = __raw_i915_read32(dev_priv, PIPEDSL(pipe)) &
+				DSL_LINEMASK_GEN3;
+			if (temp != position) {
+				position = temp;
+				break;
+			}
+		}
+	}
+
+	/*
 	 * See update_scanline_offset() for the details on the
 	 * scanline_offset adjustment.
 	 */
diff --git a/drivers/gpu/drm/i915/intel_audio.c b/drivers/gpu/drm/i915/intel_audio.c
index 89c1a8ce1f98..2a5c76faf9f8 100644
--- a/drivers/gpu/drm/i915/intel_audio.c
+++ b/drivers/gpu/drm/i915/intel_audio.c
@@ -430,7 +430,7 @@ void intel_audio_codec_enable(struct intel_encoder *intel_encoder)
 
 /**
  * intel_audio_codec_disable - Disable the audio codec for HD audio
- * @encoder: encoder on which to disable audio
+ * @intel_encoder: encoder on which to disable audio
  *
  * The disable sequences must be performed before disabling the transcoder or
  * port.
diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c
index b3e437b3bb54..c19e669ffe50 100644
--- a/drivers/gpu/drm/i915/intel_bios.c
+++ b/drivers/gpu/drm/i915/intel_bios.c
@@ -42,7 +42,7 @@ find_section(const void *_bdb, int section_id)
 	const struct bdb_header *bdb = _bdb;
 	const u8 *base = _bdb;
 	int index = 0;
-	u16 total, current_size;
+	u32 total, current_size;
 	u8 current_id;
 
 	/* skip to first section */
@@ -57,6 +57,10 @@ find_section(const void *_bdb, int section_id)
 		current_size = *((const u16 *)(base + index));
 		index += 2;
 
+		/* The MIPI Sequence Block v3+ has a separate size field. */
+		if (current_id == BDB_MIPI_SEQUENCE && *(base + index) >= 3)
+			current_size = *((const u32 *)(base + index + 1));
+
 		if (index + current_size > total)
 			return NULL;
 
@@ -799,6 +803,12 @@ parse_mipi(struct drm_i915_private *dev_priv, const struct bdb_header *bdb)
 		return;
 	}
 
+	/* Fail gracefully for forward incompatible sequence block. */
+	if (sequence->version >= 3) {
+		DRM_ERROR("Unable to parse MIPI Sequence Block v3+\n");
+		return;
+	}
+
 	DRM_DEBUG_DRIVER("Found MIPI sequence block\n");
 
 	block_size = get_blocksize(sequence);
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 8cc9264f7809..cf418be7d30a 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -15087,9 +15087,12 @@ static void readout_plane_state(struct intel_crtc *crtc,
 
 		plane_state = to_intel_plane_state(p->base.state);
 
-		if (p->base.type == DRM_PLANE_TYPE_PRIMARY)
+		if (p->base.type == DRM_PLANE_TYPE_PRIMARY) {
 			plane_state->visible = primary_get_hw_state(crtc);
-		else {
+			if (plane_state->visible)
+				crtc->base.state->plane_mask |=
+					1 << drm_plane_index(&p->base);
+		} else {
 			if (active)
 				p->disable_plane(&p->base, &crtc->base);
 
diff --git a/drivers/gpu/drm/mgag200/mgag200_fb.c b/drivers/gpu/drm/mgag200/mgag200_fb.c
index 87de15ea1f93..b35b5b2db4ec 100644
--- a/drivers/gpu/drm/mgag200/mgag200_fb.c
+++ b/drivers/gpu/drm/mgag200/mgag200_fb.c
@@ -186,17 +186,19 @@ static int mgag200fb_create(struct drm_fb_helper *helper,
 
 	sysram = vmalloc(size);
 	if (!sysram)
-		return -ENOMEM;
+		goto err_sysram;
 
 	info = drm_fb_helper_alloc_fbi(helper);
-	if (IS_ERR(info))
-		return PTR_ERR(info);
+	if (IS_ERR(info)) {
+		ret = PTR_ERR(info);
+		goto err_alloc_fbi;
+	}
 
 	info->par = mfbdev;
 
 	ret = mgag200_framebuffer_init(dev, &mfbdev->mfb, &mode_cmd, gobj);
 	if (ret)
-		return ret;
+		goto err_framebuffer_init;
 
 	mfbdev->sysram = sysram;
 	mfbdev->size = size;
@@ -225,7 +227,17 @@ static int mgag200fb_create(struct drm_fb_helper *helper,
 
 	DRM_DEBUG_KMS("allocated %dx%d\n",
 		      fb->width, fb->height);
+
 	return 0;
+
+err_framebuffer_init:
+	drm_fb_helper_release_fbi(helper);
+err_alloc_fbi:
+	vfree(sysram);
+err_sysram:
+	drm_gem_object_unreference_unlocked(gobj);
+
+	return ret;
 }
 
 static int mga_fbdev_destroy(struct drm_device *dev,
@@ -276,23 +288,26 @@ int mgag200_fbdev_init(struct mga_device *mdev)
 	ret = drm_fb_helper_init(mdev->dev, &mfbdev->helper,
 				 mdev->num_crtc, MGAG200FB_CONN_LIMIT);
 	if (ret)
-		return ret;
+		goto err_fb_helper;
 
 	ret = drm_fb_helper_single_add_all_connectors(&mfbdev->helper);
 	if (ret)
-		goto fini;
+		goto err_fb_setup;
 
 	/* disable all the possible outputs/crtcs before entering KMS mode */
 	drm_helper_disable_unused_functions(mdev->dev);
 
 	ret = drm_fb_helper_initial_config(&mfbdev->helper, bpp_sel);
 	if (ret)
-		goto fini;
+		goto err_fb_setup;
 
 	return 0;
 
-fini:
+err_fb_setup:
 	drm_fb_helper_fini(&mfbdev->helper);
+err_fb_helper:
+	mdev->mfbdev = NULL;
+
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/mgag200/mgag200_main.c b/drivers/gpu/drm/mgag200/mgag200_main.c
index de06388069e7..b1a0f5656175 100644
--- a/drivers/gpu/drm/mgag200/mgag200_main.c
+++ b/drivers/gpu/drm/mgag200/mgag200_main.c
@@ -220,7 +220,7 @@ int mgag200_driver_load(struct drm_device *dev, unsigned long flags)
 	}
 	r = mgag200_mm_init(mdev);
 	if (r)
-		goto out;
+		goto err_mm;
 
 	drm_mode_config_init(dev);
 	dev->mode_config.funcs = (void *)&mga_mode_funcs;
@@ -233,7 +233,7 @@ int mgag200_driver_load(struct drm_device *dev, unsigned long flags)
 	r = mgag200_modeset_init(mdev);
 	if (r) {
 		dev_err(&dev->pdev->dev, "Fatal error during modeset init: %d\n", r);
-		goto out;
+		goto err_modeset;
 	}
 
 	/* Make small buffers to store a hardware cursor (double buffered icon updates) */
@@ -241,20 +241,24 @@ int mgag200_driver_load(struct drm_device *dev, unsigned long flags)
 					  &mdev->cursor.pixels_1);
 	mgag200_bo_create(dev, roundup(48*64, PAGE_SIZE), 0, 0,
 					  &mdev->cursor.pixels_2);
-	if (!mdev->cursor.pixels_2 || !mdev->cursor.pixels_1)
-		goto cursor_nospace;
-	mdev->cursor.pixels_current = mdev->cursor.pixels_1;
-	mdev->cursor.pixels_prev = mdev->cursor.pixels_2;
-	goto cursor_done;
- cursor_nospace:
-	mdev->cursor.pixels_1 = NULL;
-	mdev->cursor.pixels_2 = NULL;
-	dev_warn(&dev->pdev->dev, "Could not allocate space for cursors. Not doing hardware cursors.\n");
- cursor_done:
-
-out:
-	if (r)
-		mgag200_driver_unload(dev);
+	if (!mdev->cursor.pixels_2 || !mdev->cursor.pixels_1) {
+		mdev->cursor.pixels_1 = NULL;
+		mdev->cursor.pixels_2 = NULL;
+		dev_warn(&dev->pdev->dev,
+			"Could not allocate space for cursors. Not doing hardware cursors.\n");
+	} else {
+		mdev->cursor.pixels_current = mdev->cursor.pixels_1;
+		mdev->cursor.pixels_prev = mdev->cursor.pixels_2;
+	}
+
+	return 0;
+
+err_modeset:
+	drm_mode_config_cleanup(dev);
+	mgag200_mm_fini(mdev);
+err_mm:
+	dev->dev_private = NULL;
+
 	return r;
 }
 
diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c
index 7c6225c84ba6..dd845f82cc24 100644
--- a/drivers/gpu/drm/qxl/qxl_display.c
+++ b/drivers/gpu/drm/qxl/qxl_display.c
@@ -886,13 +886,15 @@ static enum drm_connector_status qxl_conn_detect(
 		drm_connector_to_qxl_output(connector);
 	struct drm_device *ddev = connector->dev;
 	struct qxl_device *qdev = ddev->dev_private;
-	int connected;
+	bool connected = false;
 
 	/* The first monitor is always connected */
-	connected = (output->index == 0) ||
-		    (qdev->client_monitors_config &&
-		     qdev->client_monitors_config->count > output->index &&
-		     qxl_head_enabled(&qdev->client_monitors_config->heads[output->index]));
+	if (!qdev->client_monitors_config) {
+		if (output->index == 0)
+			connected = true;
+	} else
+		connected = qdev->client_monitors_config->count > output->index &&
+		     qxl_head_enabled(&qdev->client_monitors_config->heads[output->index]);
 
 	DRM_DEBUG("#%d connected: %d\n", output->index, connected);
 	if (!connected)
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index d8319dae8358..f3f562f6d848 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -1573,10 +1573,12 @@ int radeon_suspend_kms(struct drm_device *dev, bool suspend, bool fbcon)
 
 	drm_kms_helper_poll_disable(dev);
 
+	drm_modeset_lock_all(dev);
 	/* turn off display hw */
 	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
 		drm_helper_connector_dpms(connector, DRM_MODE_DPMS_OFF);
 	}
+	drm_modeset_unlock_all(dev);
 
 	/* unpin the front buffers and cursors */
 	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
@@ -1734,9 +1736,11 @@ int radeon_resume_kms(struct drm_device *dev, bool resume, bool fbcon)
 	if (fbcon) {
 		drm_helper_resume_force_mode(dev);
 		/* turn on display hw */
+		drm_modeset_lock_all(dev);
 		list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
 			drm_helper_connector_dpms(connector, DRM_MODE_DPMS_ON);
 		}
+		drm_modeset_unlock_all(dev);
 	}
 
 	drm_kms_helper_poll_enable(dev);
diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c
index 787cd8fd897f..e9115d3f67b0 100644
--- a/drivers/gpu/drm/radeon/si_dpm.c
+++ b/drivers/gpu/drm/radeon/si_dpm.c
@@ -2927,6 +2927,7 @@ static struct si_dpm_quirk si_dpm_quirk_list[] = {
 	{ PCI_VENDOR_ID_ATI, 0x6810, 0x1462, 0x3036, 0, 120000 },
 	{ PCI_VENDOR_ID_ATI, 0x6811, 0x174b, 0xe271, 0, 120000 },
 	{ PCI_VENDOR_ID_ATI, 0x6810, 0x174b, 0xe271, 85000, 90000 },
+	{ PCI_VENDOR_ID_ATI, 0x6811, 0x1762, 0x2015, 0, 120000 },
 	{ 0, 0, 0, 0 },
 };
 
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 8d9b7de25613..745e996d2dbc 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -882,6 +882,8 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo,
 		if (ret)
 			return ret;
 		man = &bdev->man[mem_type];
+		if (!man->has_type || !man->use_type)
+			continue;
 
 		type_ok = ttm_bo_mt_compatible(man, mem_type, place,
 						&cur_flags);
@@ -889,6 +891,7 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo,
 		if (!type_ok)
 			continue;
 
+		type_found = true;
 		cur_flags = ttm_bo_select_caching(man, bo->mem.placement,
 						  cur_flags);
 		/*
@@ -901,12 +904,10 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo,
 		if (mem_type == TTM_PL_SYSTEM)
 			break;
 
-		if (man->has_type && man->use_type) {
-			type_found = true;
-			ret = (*man->func->get_node)(man, bo, place, mem);
-			if (unlikely(ret))
-				return ret;
-		}
+		ret = (*man->func->get_node)(man, bo, place, mem);
+		if (unlikely(ret))
+			return ret;
+		
 		if (mem->mm_node)
 			break;
 	}
@@ -917,9 +918,6 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo,
 		return 0;
 	}
 
-	if (!type_found)
-		return -EINVAL;
-
 	for (i = 0; i < placement->num_busy_placement; ++i) {
 		const struct ttm_place *place = &placement->busy_placement[i];
 
@@ -927,11 +925,12 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo,
 		if (ret)
 			return ret;
 		man = &bdev->man[mem_type];
-		if (!man->has_type)
+		if (!man->has_type || !man->use_type)
 			continue;
 		if (!ttm_bo_mt_compatible(man, mem_type, place, &cur_flags))
 			continue;
 
+		type_found = true;
 		cur_flags = ttm_bo_select_caching(man, bo->mem.placement,
 						  cur_flags);
 		/*
@@ -957,8 +956,13 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo,
 		if (ret == -ERESTARTSYS)
 			has_erestartsys = true;
 	}
-	ret = (has_erestartsys) ? -ERESTARTSYS : -ENOMEM;
-	return ret;
+
+	if (!type_found) {
+		printk(KERN_ERR TTM_PFX "No compatible memory type found.\n");
+		return -EINVAL;
+	}
+
+	return (has_erestartsys) ? -ERESTARTSYS : -ENOMEM;
 }
 EXPORT_SYMBOL(ttm_bo_mem_space);
 
diff --git a/drivers/gpu/drm/vmwgfx/Kconfig b/drivers/gpu/drm/vmwgfx/Kconfig
index 67720f70fe29..b49445df8a7e 100644
--- a/drivers/gpu/drm/vmwgfx/Kconfig
+++ b/drivers/gpu/drm/vmwgfx/Kconfig
@@ -1,6 +1,6 @@
 config DRM_VMWGFX
 	tristate "DRM driver for VMware Virtual GPU"
-	depends on DRM && PCI
+	depends on DRM && PCI && X86
 	select FB_DEFERRED_IO
 	select FB_CFB_FILLRECT
 	select FB_CFB_COPYAREA
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c
index ce659a125f2b..092ea81eeff7 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c
@@ -311,7 +311,6 @@ static int vmw_cotable_unbind(struct vmw_resource *res,
 	struct vmw_private *dev_priv = res->dev_priv;
 	struct ttm_buffer_object *bo = val_buf->bo;
 	struct vmw_fence_obj *fence;
-	int ret;
 
 	if (list_empty(&res->mob_head))
 		return 0;
@@ -328,7 +327,7 @@ static int vmw_cotable_unbind(struct vmw_resource *res,
 	if (likely(fence != NULL))
 		vmw_fence_obj_unreference(&fence);
 
-	return ret;
+	return 0;
 }
 
 /**
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index e13b20bd9908..2c7a25c71af2 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -752,12 +752,8 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset)
 	ttm_lock_set_kill(&dev_priv->fbdev_master.lock, false, SIGTERM);
 	dev_priv->active_master = &dev_priv->fbdev_master;
 
-
-	dev_priv->mmio_mtrr = arch_phys_wc_add(dev_priv->mmio_start,
-					       dev_priv->mmio_size);
-
-	dev_priv->mmio_virt = ioremap_wc(dev_priv->mmio_start,
-					 dev_priv->mmio_size);
+	dev_priv->mmio_virt = ioremap_cache(dev_priv->mmio_start,
+					    dev_priv->mmio_size);
 
 	if (unlikely(dev_priv->mmio_virt == NULL)) {
 		ret = -ENOMEM;
@@ -913,7 +909,6 @@ out_no_device:
 out_err4:
 	iounmap(dev_priv->mmio_virt);
 out_err3:
-	arch_phys_wc_del(dev_priv->mmio_mtrr);
 	vmw_ttm_global_release(dev_priv);
 out_err0:
 	for (i = vmw_res_context; i < vmw_res_max; ++i)
@@ -964,7 +959,6 @@ static int vmw_driver_unload(struct drm_device *dev)
 
 	ttm_object_device_release(&dev_priv->tdev);
 	iounmap(dev_priv->mmio_virt);
-	arch_phys_wc_del(dev_priv->mmio_mtrr);
 	if (dev_priv->ctx.staged_bindings)
 		vmw_binding_state_free(dev_priv->ctx.staged_bindings);
 	vmw_ttm_global_release(dev_priv);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index 6d02de6dc36c..f19fd39b43e1 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -376,7 +376,6 @@ struct vmw_private {
 	uint32_t initial_width;
 	uint32_t initial_height;
 	u32 __iomem *mmio_virt;
-	int mmio_mtrr;
 	uint32_t capabilities;
 	uint32_t max_gmr_ids;
 	uint32_t max_gmr_pages;
@@ -631,7 +630,8 @@ extern int vmw_user_dmabuf_alloc(struct vmw_private *dev_priv,
 				 uint32_t size,
 				 bool shareable,
 				 uint32_t *handle,
-				 struct vmw_dma_buffer **p_dma_buf);
+				 struct vmw_dma_buffer **p_dma_buf,
+				 struct ttm_base_object **p_base);
 extern int vmw_user_dmabuf_reference(struct ttm_object_file *tfile,
 				     struct vmw_dma_buffer *dma_buf,
 				     uint32_t *handle);
@@ -645,7 +645,8 @@ extern uint32_t vmw_dmabuf_validate_node(struct ttm_buffer_object *bo,
 					 uint32_t cur_validate_node);
 extern void vmw_dmabuf_validate_clear(struct ttm_buffer_object *bo);
 extern int vmw_user_dmabuf_lookup(struct ttm_object_file *tfile,
-				  uint32_t id, struct vmw_dma_buffer **out);
+				  uint32_t id, struct vmw_dma_buffer **out,
+				  struct ttm_base_object **base);
 extern int vmw_stream_claim_ioctl(struct drm_device *dev, void *data,
 				  struct drm_file *file_priv);
 extern int vmw_stream_unref_ioctl(struct drm_device *dev, void *data,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
index b56565457c96..5da5de0cb522 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
@@ -1236,7 +1236,8 @@ static int vmw_translate_mob_ptr(struct vmw_private *dev_priv,
 	struct vmw_relocation *reloc;
 	int ret;
 
-	ret = vmw_user_dmabuf_lookup(sw_context->fp->tfile, handle, &vmw_bo);
+	ret = vmw_user_dmabuf_lookup(sw_context->fp->tfile, handle, &vmw_bo,
+				     NULL);
 	if (unlikely(ret != 0)) {
 		DRM_ERROR("Could not find or use MOB buffer.\n");
 		ret = -EINVAL;
@@ -1296,7 +1297,8 @@ static int vmw_translate_guest_ptr(struct vmw_private *dev_priv,
 	struct vmw_relocation *reloc;
 	int ret;
 
-	ret = vmw_user_dmabuf_lookup(sw_context->fp->tfile, handle, &vmw_bo);
+	ret = vmw_user_dmabuf_lookup(sw_context->fp->tfile, handle, &vmw_bo,
+				     NULL);
 	if (unlikely(ret != 0)) {
 		DRM_ERROR("Could not find or use GMR region.\n");
 		ret = -EINVAL;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index 61fb7f3de311..15a6c01cd016 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -1685,7 +1685,6 @@ int vmw_kms_helper_dirty(struct vmw_private *dev_priv,
 	struct drm_crtc *crtc;
 	u32 num_units = 0;
 	u32 i, k;
-	int ret;
 
 	dirty->dev_priv = dev_priv;
 
@@ -1711,7 +1710,7 @@ int vmw_kms_helper_dirty(struct vmw_private *dev_priv,
 			if (!dirty->cmd) {
 				DRM_ERROR("Couldn't reserve fifo space "
 					  "for dirty blits.\n");
-				return ret;
+				return -ENOMEM;
 			}
 			memset(dirty->cmd, 0, dirty->fifo_reserve_size);
 		}
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c b/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c
index 76069f093ccf..222c9c2123a1 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c
@@ -484,7 +484,7 @@ int vmw_overlay_ioctl(struct drm_device *dev, void *data,
 		goto out_unlock;
 	}
 
-	ret = vmw_user_dmabuf_lookup(tfile, arg->handle, &buf);
+	ret = vmw_user_dmabuf_lookup(tfile, arg->handle, &buf, NULL);
 	if (ret)
 		goto out_unlock;
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
index c1912f852b42..e57667ca7557 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
@@ -354,7 +354,7 @@ int vmw_user_lookup_handle(struct vmw_private *dev_priv,
 	}
 
 	*out_surf = NULL;
-	ret = vmw_user_dmabuf_lookup(tfile, handle, out_buf);
+	ret = vmw_user_dmabuf_lookup(tfile, handle, out_buf, NULL);
 	return ret;
 }
 
@@ -481,7 +481,8 @@ int vmw_user_dmabuf_alloc(struct vmw_private *dev_priv,
 			  uint32_t size,
 			  bool shareable,
 			  uint32_t *handle,
-			  struct vmw_dma_buffer **p_dma_buf)
+			  struct vmw_dma_buffer **p_dma_buf,
+			  struct ttm_base_object **p_base)
 {
 	struct vmw_user_dma_buffer *user_bo;
 	struct ttm_buffer_object *tmp;
@@ -515,6 +516,10 @@ int vmw_user_dmabuf_alloc(struct vmw_private *dev_priv,
 	}
 
 	*p_dma_buf = &user_bo->dma;
+	if (p_base) {
+		*p_base = &user_bo->prime.base;
+		kref_get(&(*p_base)->refcount);
+	}
 	*handle = user_bo->prime.base.hash.key;
 
 out_no_base_object:
@@ -631,6 +636,7 @@ int vmw_user_dmabuf_synccpu_ioctl(struct drm_device *dev, void *data,
 	struct vmw_dma_buffer *dma_buf;
 	struct vmw_user_dma_buffer *user_bo;
 	struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
+	struct ttm_base_object *buffer_base;
 	int ret;
 
 	if ((arg->flags & (drm_vmw_synccpu_read | drm_vmw_synccpu_write)) == 0
@@ -643,7 +649,8 @@ int vmw_user_dmabuf_synccpu_ioctl(struct drm_device *dev, void *data,
 
 	switch (arg->op) {
 	case drm_vmw_synccpu_grab:
-		ret = vmw_user_dmabuf_lookup(tfile, arg->handle, &dma_buf);
+		ret = vmw_user_dmabuf_lookup(tfile, arg->handle, &dma_buf,
+					     &buffer_base);
 		if (unlikely(ret != 0))
 			return ret;
 
@@ -651,6 +658,7 @@ int vmw_user_dmabuf_synccpu_ioctl(struct drm_device *dev, void *data,
 				       dma);
 		ret = vmw_user_dmabuf_synccpu_grab(user_bo, tfile, arg->flags);
 		vmw_dmabuf_unreference(&dma_buf);
+		ttm_base_object_unref(&buffer_base);
 		if (unlikely(ret != 0 && ret != -ERESTARTSYS &&
 			     ret != -EBUSY)) {
 			DRM_ERROR("Failed synccpu grab on handle 0x%08x.\n",
@@ -692,7 +700,8 @@ int vmw_dmabuf_alloc_ioctl(struct drm_device *dev, void *data,
 		return ret;
 
 	ret = vmw_user_dmabuf_alloc(dev_priv, vmw_fpriv(file_priv)->tfile,
-				    req->size, false, &handle, &dma_buf);
+				    req->size, false, &handle, &dma_buf,
+				    NULL);
 	if (unlikely(ret != 0))
 		goto out_no_dmabuf;
 
@@ -721,7 +730,8 @@ int vmw_dmabuf_unref_ioctl(struct drm_device *dev, void *data,
 }
 
 int vmw_user_dmabuf_lookup(struct ttm_object_file *tfile,
-			   uint32_t handle, struct vmw_dma_buffer **out)
+			   uint32_t handle, struct vmw_dma_buffer **out,
+			   struct ttm_base_object **p_base)
 {
 	struct vmw_user_dma_buffer *vmw_user_bo;
 	struct ttm_base_object *base;
@@ -743,7 +753,10 @@ int vmw_user_dmabuf_lookup(struct ttm_object_file *tfile,
 	vmw_user_bo = container_of(base, struct vmw_user_dma_buffer,
 				   prime.base);
 	(void)ttm_bo_reference(&vmw_user_bo->dma.base);
-	ttm_base_object_unref(&base);
+	if (p_base)
+		*p_base = base;
+	else
+		ttm_base_object_unref(&base);
 	*out = &vmw_user_bo->dma;
 
 	return 0;
@@ -1004,7 +1017,7 @@ int vmw_dumb_create(struct drm_file *file_priv,
 
 	ret = vmw_user_dmabuf_alloc(dev_priv, vmw_fpriv(file_priv)->tfile,
 				    args->size, false, &args->handle,
-				    &dma_buf);
+				    &dma_buf, NULL);
 	if (unlikely(ret != 0))
 		goto out_no_dmabuf;
 
@@ -1032,7 +1045,7 @@ int vmw_dumb_map_offset(struct drm_file *file_priv,
 	struct vmw_dma_buffer *out_buf;
 	int ret;
 
-	ret = vmw_user_dmabuf_lookup(tfile, handle, &out_buf);
+	ret = vmw_user_dmabuf_lookup(tfile, handle, &out_buf, NULL);
 	if (ret != 0)
 		return -EINVAL;
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c
index bba1ee395478..fd47547b0234 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c
@@ -855,7 +855,7 @@ static int vmw_shader_define(struct drm_device *dev, struct drm_file *file_priv,
 
 	if (buffer_handle != SVGA3D_INVALID_ID) {
 		ret = vmw_user_dmabuf_lookup(tfile, buffer_handle,
-					     &buffer);
+					     &buffer, NULL);
 		if (unlikely(ret != 0)) {
 			DRM_ERROR("Could not find buffer for shader "
 				  "creation.\n");
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
index 3361769842f4..64b50409fa07 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
@@ -46,6 +46,7 @@ struct vmw_user_surface {
 	struct vmw_surface srf;
 	uint32_t size;
 	struct drm_master *master;
+	struct ttm_base_object *backup_base;
 };
 
 /**
@@ -656,6 +657,7 @@ static void vmw_user_surface_base_release(struct ttm_base_object **p_base)
 	struct vmw_resource *res = &user_srf->srf.res;
 
 	*p_base = NULL;
+	ttm_base_object_unref(&user_srf->backup_base);
 	vmw_resource_unreference(&res);
 }
 
@@ -851,7 +853,8 @@ int vmw_surface_define_ioctl(struct drm_device *dev, void *data,
 					    res->backup_size,
 					    true,
 					    &backup_handle,
-					    &res->backup);
+					    &res->backup,
+					    &user_srf->backup_base);
 		if (unlikely(ret != 0)) {
 			vmw_resource_unreference(&res);
 			goto out_unlock;
@@ -1321,7 +1324,8 @@ int vmw_gb_surface_define_ioctl(struct drm_device *dev, void *data,
 
 	if (req->buffer_handle != SVGA3D_INVALID_ID) {
 		ret = vmw_user_dmabuf_lookup(tfile, req->buffer_handle,
-					     &res->backup);
+					     &res->backup,
+					     &user_srf->backup_base);
 		if (ret == 0 && res->backup->base.num_pages * PAGE_SIZE <
 		    res->backup_size) {
 			DRM_ERROR("Surface backup buffer is too small.\n");
@@ -1335,7 +1339,8 @@ int vmw_gb_surface_define_ioctl(struct drm_device *dev, void *data,
 					    req->drm_surface_flags &
 					    drm_vmw_surface_flag_shareable,
 					    &backup_handle,
-					    &res->backup);
+					    &res->backup,
+					    &user_srf->backup_base);
 
 	if (unlikely(ret != 0)) {
 		vmw_resource_unreference(&res);
diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index 2f9aead4ecfc..652afd11a9ef 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -204,6 +204,8 @@ void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid)
 		spin_lock_irqsave(&vmbus_connection.channel_lock, flags);
 		list_del(&channel->listentry);
 		spin_unlock_irqrestore(&vmbus_connection.channel_lock, flags);
+
+		primary_channel = channel;
 	} else {
 		primary_channel = channel->primary_channel;
 		spin_lock_irqsave(&primary_channel->lock, flags);
@@ -211,6 +213,14 @@ void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid)
 		primary_channel->num_sc--;
 		spin_unlock_irqrestore(&primary_channel->lock, flags);
 	}
+
+	/*
+	 * We need to free the bit for init_vp_index() to work in the case
+	 * of sub-channel, when we reload drivers like hv_netvsc.
+	 */
+	cpumask_clear_cpu(channel->target_cpu,
+			  &primary_channel->alloced_cpus_in_node);
+
 	free_channel(channel);
 }
 
@@ -458,6 +468,13 @@ static void init_vp_index(struct vmbus_channel *channel, const uuid_le *type_gui
 			continue;
 		}
 
+		/*
+		 * NOTE: in the case of sub-channel, we clear the sub-channel
+		 * related bit(s) in primary->alloced_cpus_in_node in
+		 * hv_process_channel_removal(), so when we reload drivers
+		 * like hv_netvsc in SMP guest, here we're able to re-allocate
+		 * bit from primary->alloced_cpus_in_node.
+		 */
 		if (!cpumask_test_cpu(cur_cpu,
 				&primary->alloced_cpus_in_node)) {
 			cpumask_set_cpu(cur_cpu,
diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index 403bd29443b8..aa59037d7504 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -238,8 +238,6 @@ isert_alloc_rx_descriptors(struct isert_conn *isert_conn)
 		rx_sg->lkey = device->pd->local_dma_lkey;
 	}
 
-	isert_conn->rx_desc_head = 0;
-
 	return 0;
 
 dma_map_fail:
@@ -634,7 +632,7 @@ static void
 isert_init_conn(struct isert_conn *isert_conn)
 {
 	isert_conn->state = ISER_CONN_INIT;
-	INIT_LIST_HEAD(&isert_conn->accept_node);
+	INIT_LIST_HEAD(&isert_conn->node);
 	init_completion(&isert_conn->login_comp);
 	init_completion(&isert_conn->login_req_comp);
 	init_completion(&isert_conn->wait);
@@ -762,28 +760,15 @@ isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 	ret = isert_rdma_post_recvl(isert_conn);
 	if (ret)
 		goto out_conn_dev;
-	/*
-	 * Obtain the second reference now before isert_rdma_accept() to
-	 * ensure that any initiator generated REJECT CM event that occurs
-	 * asynchronously won't drop the last reference until the error path
-	 * in iscsi_target_login_sess_out() does it's ->iscsit_free_conn() ->
-	 * isert_free_conn() -> isert_put_conn() -> kref_put().
-	 */
-	if (!kref_get_unless_zero(&isert_conn->kref)) {
-		isert_warn("conn %p connect_release is running\n", isert_conn);
-		goto out_conn_dev;
-	}
 
 	ret = isert_rdma_accept(isert_conn);
 	if (ret)
 		goto out_conn_dev;
 
-	mutex_lock(&isert_np->np_accept_mutex);
-	list_add_tail(&isert_conn->accept_node, &isert_np->np_accept_list);
-	mutex_unlock(&isert_np->np_accept_mutex);
+	mutex_lock(&isert_np->mutex);
+	list_add_tail(&isert_conn->node, &isert_np->accepted);
+	mutex_unlock(&isert_np->mutex);
 
-	isert_info("np %p: Allow accept_np to continue\n", np);
-	up(&isert_np->np_sem);
 	return 0;
 
 out_conn_dev:
@@ -831,13 +816,21 @@ static void
 isert_connected_handler(struct rdma_cm_id *cma_id)
 {
 	struct isert_conn *isert_conn = cma_id->qp->qp_context;
+	struct isert_np *isert_np = cma_id->context;
 
 	isert_info("conn %p\n", isert_conn);
 
 	mutex_lock(&isert_conn->mutex);
-	if (isert_conn->state != ISER_CONN_FULL_FEATURE)
-		isert_conn->state = ISER_CONN_UP;
+	isert_conn->state = ISER_CONN_UP;
+	kref_get(&isert_conn->kref);
 	mutex_unlock(&isert_conn->mutex);
+
+	mutex_lock(&isert_np->mutex);
+	list_move_tail(&isert_conn->node, &isert_np->pending);
+	mutex_unlock(&isert_np->mutex);
+
+	isert_info("np %p: Allow accept_np to continue\n", isert_np);
+	up(&isert_np->sem);
 }
 
 static void
@@ -903,14 +896,14 @@ isert_np_cma_handler(struct isert_np *isert_np,
 
 	switch (event) {
 	case RDMA_CM_EVENT_DEVICE_REMOVAL:
-		isert_np->np_cm_id = NULL;
+		isert_np->cm_id = NULL;
 		break;
 	case RDMA_CM_EVENT_ADDR_CHANGE:
-		isert_np->np_cm_id = isert_setup_id(isert_np);
-		if (IS_ERR(isert_np->np_cm_id)) {
+		isert_np->cm_id = isert_setup_id(isert_np);
+		if (IS_ERR(isert_np->cm_id)) {
 			isert_err("isert np %p setup id failed: %ld\n",
-				  isert_np, PTR_ERR(isert_np->np_cm_id));
-			isert_np->np_cm_id = NULL;
+				  isert_np, PTR_ERR(isert_np->cm_id));
+			isert_np->cm_id = NULL;
 		}
 		break;
 	default:
@@ -929,7 +922,7 @@ isert_disconnected_handler(struct rdma_cm_id *cma_id,
 	struct isert_conn *isert_conn;
 	bool terminating = false;
 
-	if (isert_np->np_cm_id == cma_id)
+	if (isert_np->cm_id == cma_id)
 		return isert_np_cma_handler(cma_id->context, event);
 
 	isert_conn = cma_id->qp->qp_context;
@@ -945,13 +938,13 @@ isert_disconnected_handler(struct rdma_cm_id *cma_id,
 	if (terminating)
 		goto out;
 
-	mutex_lock(&isert_np->np_accept_mutex);
-	if (!list_empty(&isert_conn->accept_node)) {
-		list_del_init(&isert_conn->accept_node);
+	mutex_lock(&isert_np->mutex);
+	if (!list_empty(&isert_conn->node)) {
+		list_del_init(&isert_conn->node);
 		isert_put_conn(isert_conn);
 		queue_work(isert_release_wq, &isert_conn->release_work);
 	}
-	mutex_unlock(&isert_np->np_accept_mutex);
+	mutex_unlock(&isert_np->mutex);
 
 out:
 	return 0;
@@ -962,6 +955,7 @@ isert_connect_error(struct rdma_cm_id *cma_id)
 {
 	struct isert_conn *isert_conn = cma_id->qp->qp_context;
 
+	list_del_init(&isert_conn->node);
 	isert_conn->cm_id = NULL;
 	isert_put_conn(isert_conn);
 
@@ -1006,35 +1000,51 @@ isert_cma_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 }
 
 static int
-isert_post_recv(struct isert_conn *isert_conn, u32 count)
+isert_post_recvm(struct isert_conn *isert_conn, u32 count)
 {
 	struct ib_recv_wr *rx_wr, *rx_wr_failed;
 	int i, ret;
-	unsigned int rx_head = isert_conn->rx_desc_head;
 	struct iser_rx_desc *rx_desc;
 
 	for (rx_wr = isert_conn->rx_wr, i = 0; i < count; i++, rx_wr++) {
-		rx_desc		= &isert_conn->rx_descs[rx_head];
-		rx_wr->wr_id	= (uintptr_t)rx_desc;
-		rx_wr->sg_list	= &rx_desc->rx_sg;
-		rx_wr->num_sge	= 1;
-		rx_wr->next	= rx_wr + 1;
-		rx_head = (rx_head + 1) & (ISERT_QP_MAX_RECV_DTOS - 1);
+		rx_desc = &isert_conn->rx_descs[i];
+		rx_wr->wr_id = (uintptr_t)rx_desc;
+		rx_wr->sg_list = &rx_desc->rx_sg;
+		rx_wr->num_sge = 1;
+		rx_wr->next = rx_wr + 1;
 	}
-
 	rx_wr--;
 	rx_wr->next = NULL; /* mark end of work requests list */
 
 	isert_conn->post_recv_buf_count += count;
 	ret = ib_post_recv(isert_conn->qp, isert_conn->rx_wr,
-				&rx_wr_failed);
+			   &rx_wr_failed);
 	if (ret) {
 		isert_err("ib_post_recv() failed with ret: %d\n", ret);
 		isert_conn->post_recv_buf_count -= count;
-	} else {
-		isert_dbg("Posted %d RX buffers\n", count);
-		isert_conn->rx_desc_head = rx_head;
 	}
+
+	return ret;
+}
+
+static int
+isert_post_recv(struct isert_conn *isert_conn, struct iser_rx_desc *rx_desc)
+{
+	struct ib_recv_wr *rx_wr_failed, rx_wr;
+	int ret;
+
+	rx_wr.wr_id = (uintptr_t)rx_desc;
+	rx_wr.sg_list = &rx_desc->rx_sg;
+	rx_wr.num_sge = 1;
+	rx_wr.next = NULL;
+
+	isert_conn->post_recv_buf_count++;
+	ret = ib_post_recv(isert_conn->qp, &rx_wr, &rx_wr_failed);
+	if (ret) {
+		isert_err("ib_post_recv() failed with ret: %d\n", ret);
+		isert_conn->post_recv_buf_count--;
+	}
+
 	return ret;
 }
 
@@ -1205,7 +1215,8 @@ isert_put_login_tx(struct iscsi_conn *conn, struct iscsi_login *login,
 			if (ret)
 				return ret;
 
-			ret = isert_post_recv(isert_conn, ISERT_MIN_POSTED_RX);
+			ret = isert_post_recvm(isert_conn,
+					       ISERT_QP_MAX_RECV_DTOS);
 			if (ret)
 				return ret;
 
@@ -1278,7 +1289,7 @@ isert_rx_login_req(struct isert_conn *isert_conn)
 }
 
 static struct iscsi_cmd
-*isert_allocate_cmd(struct iscsi_conn *conn)
+*isert_allocate_cmd(struct iscsi_conn *conn, struct iser_rx_desc *rx_desc)
 {
 	struct isert_conn *isert_conn = conn->context;
 	struct isert_cmd *isert_cmd;
@@ -1292,6 +1303,7 @@ static struct iscsi_cmd
 	isert_cmd = iscsit_priv_cmd(cmd);
 	isert_cmd->conn = isert_conn;
 	isert_cmd->iscsi_cmd = cmd;
+	isert_cmd->rx_desc = rx_desc;
 
 	return cmd;
 }
@@ -1303,9 +1315,9 @@ isert_handle_scsi_cmd(struct isert_conn *isert_conn,
 {
 	struct iscsi_conn *conn = isert_conn->conn;
 	struct iscsi_scsi_req *hdr = (struct iscsi_scsi_req *)buf;
-	struct scatterlist *sg;
 	int imm_data, imm_data_len, unsol_data, sg_nents, rc;
 	bool dump_payload = false;
+	unsigned int data_len;
 
 	rc = iscsit_setup_scsi_cmd(conn, cmd, buf);
 	if (rc < 0)
@@ -1314,7 +1326,10 @@ isert_handle_scsi_cmd(struct isert_conn *isert_conn,
 	imm_data = cmd->immediate_data;
 	imm_data_len = cmd->first_burst_len;
 	unsol_data = cmd->unsolicited_data;
+	data_len = cmd->se_cmd.data_length;
 
+	if (imm_data && imm_data_len == data_len)
+		cmd->se_cmd.se_cmd_flags |= SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC;
 	rc = iscsit_process_scsi_cmd(conn, cmd, hdr);
 	if (rc < 0) {
 		return 0;
@@ -1326,13 +1341,20 @@ isert_handle_scsi_cmd(struct isert_conn *isert_conn,
 	if (!imm_data)
 		return 0;
 
-	sg = &cmd->se_cmd.t_data_sg[0];
-	sg_nents = max(1UL, DIV_ROUND_UP(imm_data_len, PAGE_SIZE));
-
-	isert_dbg("Copying Immediate SG: %p sg_nents: %u from %p imm_data_len: %d\n",
-		  sg, sg_nents, &rx_desc->data[0], imm_data_len);
-
-	sg_copy_from_buffer(sg, sg_nents, &rx_desc->data[0], imm_data_len);
+	if (imm_data_len != data_len) {
+		sg_nents = max(1UL, DIV_ROUND_UP(imm_data_len, PAGE_SIZE));
+		sg_copy_from_buffer(cmd->se_cmd.t_data_sg, sg_nents,
+				    &rx_desc->data[0], imm_data_len);
+		isert_dbg("Copy Immediate sg_nents: %u imm_data_len: %d\n",
+			  sg_nents, imm_data_len);
+	} else {
+		sg_init_table(&isert_cmd->sg, 1);
+		cmd->se_cmd.t_data_sg = &isert_cmd->sg;
+		cmd->se_cmd.t_data_nents = 1;
+		sg_set_buf(&isert_cmd->sg, &rx_desc->data[0], imm_data_len);
+		isert_dbg("Transfer Immediate imm_data_len: %d\n",
+			  imm_data_len);
+	}
 
 	cmd->write_data_done += imm_data_len;
 
@@ -1407,6 +1429,15 @@ isert_handle_iscsi_dataout(struct isert_conn *isert_conn,
 	if (rc < 0)
 		return rc;
 
+	/*
+	 * multiple data-outs on the same command can arrive -
+	 * so post the buffer before hand
+	 */
+	rc = isert_post_recv(isert_conn, rx_desc);
+	if (rc) {
+		isert_err("ib_post_recv failed with %d\n", rc);
+		return rc;
+	}
 	return 0;
 }
 
@@ -1479,7 +1510,7 @@ isert_rx_opcode(struct isert_conn *isert_conn, struct iser_rx_desc *rx_desc,
 
 	switch (opcode) {
 	case ISCSI_OP_SCSI_CMD:
-		cmd = isert_allocate_cmd(conn);
+		cmd = isert_allocate_cmd(conn, rx_desc);
 		if (!cmd)
 			break;
 
@@ -1493,7 +1524,7 @@ isert_rx_opcode(struct isert_conn *isert_conn, struct iser_rx_desc *rx_desc,
 					rx_desc, (unsigned char *)hdr);
 		break;
 	case ISCSI_OP_NOOP_OUT:
-		cmd = isert_allocate_cmd(conn);
+		cmd = isert_allocate_cmd(conn, rx_desc);
 		if (!cmd)
 			break;
 
@@ -1506,7 +1537,7 @@ isert_rx_opcode(struct isert_conn *isert_conn, struct iser_rx_desc *rx_desc,
 						(unsigned char *)hdr);
 		break;
 	case ISCSI_OP_SCSI_TMFUNC:
-		cmd = isert_allocate_cmd(conn);
+		cmd = isert_allocate_cmd(conn, rx_desc);
 		if (!cmd)
 			break;
 
@@ -1514,22 +1545,20 @@ isert_rx_opcode(struct isert_conn *isert_conn, struct iser_rx_desc *rx_desc,
 						(unsigned char *)hdr);
 		break;
 	case ISCSI_OP_LOGOUT:
-		cmd = isert_allocate_cmd(conn);
+		cmd = isert_allocate_cmd(conn, rx_desc);
 		if (!cmd)
 			break;
 
 		ret = iscsit_handle_logout_cmd(conn, cmd, (unsigned char *)hdr);
 		break;
 	case ISCSI_OP_TEXT:
-		if (be32_to_cpu(hdr->ttt) != 0xFFFFFFFF) {
+		if (be32_to_cpu(hdr->ttt) != 0xFFFFFFFF)
 			cmd = iscsit_find_cmd_from_itt(conn, hdr->itt);
-			if (!cmd)
-				break;
-		} else {
-			cmd = isert_allocate_cmd(conn);
-			if (!cmd)
-				break;
-		}
+		else
+			cmd = isert_allocate_cmd(conn, rx_desc);
+
+		if (!cmd)
+			break;
 
 		isert_cmd = iscsit_priv_cmd(cmd);
 		ret = isert_handle_text_cmd(isert_conn, isert_cmd, cmd,
@@ -1589,7 +1618,7 @@ isert_rcv_completion(struct iser_rx_desc *desc,
 	struct ib_device *ib_dev = isert_conn->cm_id->device;
 	struct iscsi_hdr *hdr;
 	u64 rx_dma;
-	int rx_buflen, outstanding;
+	int rx_buflen;
 
 	if ((char *)desc == isert_conn->login_req_buf) {
 		rx_dma = isert_conn->login_req_dma;
@@ -1629,22 +1658,6 @@ isert_rcv_completion(struct iser_rx_desc *desc,
 				      DMA_FROM_DEVICE);
 
 	isert_conn->post_recv_buf_count--;
-	isert_dbg("Decremented post_recv_buf_count: %d\n",
-		  isert_conn->post_recv_buf_count);
-
-	if ((char *)desc == isert_conn->login_req_buf)
-		return;
-
-	outstanding = isert_conn->post_recv_buf_count;
-	if (outstanding + ISERT_MIN_POSTED_RX <= ISERT_QP_MAX_RECV_DTOS) {
-		int err, count = min(ISERT_QP_MAX_RECV_DTOS - outstanding,
-				ISERT_MIN_POSTED_RX);
-		err = isert_post_recv(isert_conn, count);
-		if (err) {
-			isert_err("isert_post_recv() count: %d failed, %d\n",
-			       count, err);
-		}
-	}
 }
 
 static int
@@ -2156,6 +2169,12 @@ isert_post_response(struct isert_conn *isert_conn, struct isert_cmd *isert_cmd)
 	struct ib_send_wr *wr_failed;
 	int ret;
 
+	ret = isert_post_recv(isert_conn, isert_cmd->rx_desc);
+	if (ret) {
+		isert_err("ib_post_recv failed with %d\n", ret);
+		return ret;
+	}
+
 	ret = ib_post_send(isert_conn->qp, &isert_cmd->tx_desc.send_wr,
 			   &wr_failed);
 	if (ret) {
@@ -2950,6 +2969,12 @@ isert_put_datain(struct iscsi_conn *conn, struct iscsi_cmd *cmd)
 				   &isert_cmd->tx_desc.send_wr);
 		isert_cmd->rdma_wr.s_send_wr.next = &isert_cmd->tx_desc.send_wr;
 		wr->send_wr_num += 1;
+
+		rc = isert_post_recv(isert_conn, isert_cmd->rx_desc);
+		if (rc) {
+			isert_err("ib_post_recv failed with %d\n", rc);
+			return rc;
+		}
 	}
 
 	rc = ib_post_send(isert_conn->qp, wr->send_wr, &wr_failed);
@@ -2999,9 +3024,16 @@ isert_get_dataout(struct iscsi_conn *conn, struct iscsi_cmd *cmd, bool recovery)
 static int
 isert_immediate_queue(struct iscsi_conn *conn, struct iscsi_cmd *cmd, int state)
 {
-	int ret;
+	struct isert_cmd *isert_cmd = iscsit_priv_cmd(cmd);
+	int ret = 0;
 
 	switch (state) {
+	case ISTATE_REMOVE:
+		spin_lock_bh(&conn->cmd_lock);
+		list_del_init(&cmd->i_conn_node);
+		spin_unlock_bh(&conn->cmd_lock);
+		isert_put_cmd(isert_cmd, true);
+		break;
 	case ISTATE_SEND_NOPIN_WANT_RESPONSE:
 		ret = isert_put_nopin(cmd, conn, false);
 		break;
@@ -3106,10 +3138,10 @@ isert_setup_np(struct iscsi_np *np,
 		isert_err("Unable to allocate struct isert_np\n");
 		return -ENOMEM;
 	}
-	sema_init(&isert_np->np_sem, 0);
-	mutex_init(&isert_np->np_accept_mutex);
-	INIT_LIST_HEAD(&isert_np->np_accept_list);
-	init_completion(&isert_np->np_login_comp);
+	sema_init(&isert_np->sem, 0);
+	mutex_init(&isert_np->mutex);
+	INIT_LIST_HEAD(&isert_np->accepted);
+	INIT_LIST_HEAD(&isert_np->pending);
 	isert_np->np = np;
 
 	/*
@@ -3125,7 +3157,7 @@ isert_setup_np(struct iscsi_np *np,
 		goto out;
 	}
 
-	isert_np->np_cm_id = isert_lid;
+	isert_np->cm_id = isert_lid;
 	np->np_context = isert_np;
 
 	return 0;
@@ -3214,7 +3246,7 @@ isert_accept_np(struct iscsi_np *np, struct iscsi_conn *conn)
 	int ret;
 
 accept_wait:
-	ret = down_interruptible(&isert_np->np_sem);
+	ret = down_interruptible(&isert_np->sem);
 	if (ret)
 		return -ENODEV;
 
@@ -3231,15 +3263,15 @@ accept_wait:
 	}
 	spin_unlock_bh(&np->np_thread_lock);
 
-	mutex_lock(&isert_np->np_accept_mutex);
-	if (list_empty(&isert_np->np_accept_list)) {
-		mutex_unlock(&isert_np->np_accept_mutex);
+	mutex_lock(&isert_np->mutex);
+	if (list_empty(&isert_np->pending)) {
+		mutex_unlock(&isert_np->mutex);
 		goto accept_wait;
 	}
-	isert_conn = list_first_entry(&isert_np->np_accept_list,
-			struct isert_conn, accept_node);
-	list_del_init(&isert_conn->accept_node);
-	mutex_unlock(&isert_np->np_accept_mutex);
+	isert_conn = list_first_entry(&isert_np->pending,
+			struct isert_conn, node);
+	list_del_init(&isert_conn->node);
+	mutex_unlock(&isert_np->mutex);
 
 	conn->context = isert_conn;
 	isert_conn->conn = conn;
@@ -3257,28 +3289,39 @@ isert_free_np(struct iscsi_np *np)
 	struct isert_np *isert_np = np->np_context;
 	struct isert_conn *isert_conn, *n;
 
-	if (isert_np->np_cm_id)
-		rdma_destroy_id(isert_np->np_cm_id);
+	if (isert_np->cm_id)
+		rdma_destroy_id(isert_np->cm_id);
 
 	/*
 	 * FIXME: At this point we don't have a good way to insure
 	 * that at this point we don't have hanging connections that
 	 * completed RDMA establishment but didn't start iscsi login
 	 * process. So work-around this by cleaning up what ever piled
-	 * up in np_accept_list.
+	 * up in accepted and pending lists.
 	 */
-	mutex_lock(&isert_np->np_accept_mutex);
-	if (!list_empty(&isert_np->np_accept_list)) {
-		isert_info("Still have isert connections, cleaning up...\n");
+	mutex_lock(&isert_np->mutex);
+	if (!list_empty(&isert_np->pending)) {
+		isert_info("Still have isert pending connections\n");
+		list_for_each_entry_safe(isert_conn, n,
+					 &isert_np->pending,
+					 node) {
+			isert_info("cleaning isert_conn %p state (%d)\n",
+				   isert_conn, isert_conn->state);
+			isert_connect_release(isert_conn);
+		}
+	}
+
+	if (!list_empty(&isert_np->accepted)) {
+		isert_info("Still have isert accepted connections\n");
 		list_for_each_entry_safe(isert_conn, n,
-					 &isert_np->np_accept_list,
-					 accept_node) {
+					 &isert_np->accepted,
+					 node) {
 			isert_info("cleaning isert_conn %p state (%d)\n",
 				   isert_conn, isert_conn->state);
 			isert_connect_release(isert_conn);
 		}
 	}
-	mutex_unlock(&isert_np->np_accept_mutex);
+	mutex_unlock(&isert_np->mutex);
 
 	np->np_context = NULL;
 	kfree(isert_np);
@@ -3345,6 +3388,41 @@ isert_wait4flush(struct isert_conn *isert_conn)
 	wait_for_completion(&isert_conn->wait_comp_err);
 }
 
+/**
+ * isert_put_unsol_pending_cmds() - Drop commands waiting for
+ *     unsolicitate dataout
+ * @conn:    iscsi connection
+ *
+ * We might still have commands that are waiting for unsolicited
+ * dataouts messages. We must put the extra reference on those
+ * before blocking on the target_wait_for_session_cmds
+ */
+static void
+isert_put_unsol_pending_cmds(struct iscsi_conn *conn)
+{
+	struct iscsi_cmd *cmd, *tmp;
+	static LIST_HEAD(drop_cmd_list);
+
+	spin_lock_bh(&conn->cmd_lock);
+	list_for_each_entry_safe(cmd, tmp, &conn->conn_cmd_list, i_conn_node) {
+		if ((cmd->cmd_flags & ICF_NON_IMMEDIATE_UNSOLICITED_DATA) &&
+		    (cmd->write_data_done < conn->sess->sess_ops->FirstBurstLength) &&
+		    (cmd->write_data_done < cmd->se_cmd.data_length))
+			list_move_tail(&cmd->i_conn_node, &drop_cmd_list);
+	}
+	spin_unlock_bh(&conn->cmd_lock);
+
+	list_for_each_entry_safe(cmd, tmp, &drop_cmd_list, i_conn_node) {
+		list_del_init(&cmd->i_conn_node);
+		if (cmd->i_state != ISTATE_REMOVE) {
+			struct isert_cmd *isert_cmd = iscsit_priv_cmd(cmd);
+
+			isert_info("conn %p dropping cmd %p\n", conn, cmd);
+			isert_put_cmd(isert_cmd, true);
+		}
+	}
+}
+
 static void isert_wait_conn(struct iscsi_conn *conn)
 {
 	struct isert_conn *isert_conn = conn->context;
@@ -3363,8 +3441,9 @@ static void isert_wait_conn(struct iscsi_conn *conn)
 	isert_conn_terminate(isert_conn);
 	mutex_unlock(&isert_conn->mutex);
 
-	isert_wait4cmds(conn);
 	isert_wait4flush(isert_conn);
+	isert_put_unsol_pending_cmds(conn);
+	isert_wait4cmds(conn);
 	isert_wait4logout(isert_conn);
 
 	queue_work(isert_release_wq, &isert_conn->release_work);
diff --git a/drivers/infiniband/ulp/isert/ib_isert.h b/drivers/infiniband/ulp/isert/ib_isert.h
index 6a04ba3c0f72..c5b99bcecbcf 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.h
+++ b/drivers/infiniband/ulp/isert/ib_isert.h
@@ -113,7 +113,6 @@ enum {
 };
 
 struct isert_rdma_wr {
-	struct list_head	wr_list;
 	struct isert_cmd	*isert_cmd;
 	enum iser_ib_op_code	iser_ib_op;
 	struct ib_sge		*ib_sge;
@@ -134,14 +133,13 @@ struct isert_cmd {
 	uint64_t		write_va;
 	u64			pdu_buf_dma;
 	u32			pdu_buf_len;
-	u32			read_va_off;
-	u32			write_va_off;
-	u32			rdma_wr_num;
 	struct isert_conn	*conn;
 	struct iscsi_cmd	*iscsi_cmd;
 	struct iser_tx_desc	tx_desc;
+	struct iser_rx_desc	*rx_desc;
 	struct isert_rdma_wr	rdma_wr;
 	struct work_struct	comp_work;
+	struct scatterlist	sg;
 };
 
 struct isert_device;
@@ -159,11 +157,10 @@ struct isert_conn {
 	u64			login_req_dma;
 	int			login_req_len;
 	u64			login_rsp_dma;
-	unsigned int		rx_desc_head;
 	struct iser_rx_desc	*rx_descs;
-	struct ib_recv_wr	rx_wr[ISERT_MIN_POSTED_RX];
+	struct ib_recv_wr	rx_wr[ISERT_QP_MAX_RECV_DTOS];
 	struct iscsi_conn	*conn;
-	struct list_head	accept_node;
+	struct list_head	node;
 	struct completion	login_comp;
 	struct completion	login_req_comp;
 	struct iser_tx_desc	login_tx_desc;
@@ -222,9 +219,9 @@ struct isert_device {
 
 struct isert_np {
 	struct iscsi_np         *np;
-	struct semaphore	np_sem;
-	struct rdma_cm_id	*np_cm_id;
-	struct mutex		np_accept_mutex;
-	struct list_head	np_accept_list;
-	struct completion	np_login_comp;
+	struct semaphore	sem;
+	struct rdma_cm_id	*cm_id;
+	struct mutex		mutex;
+	struct list_head	accepted;
+	struct list_head	pending;
 };
diff --git a/drivers/irqchip/irq-atmel-aic5.c b/drivers/irqchip/irq-atmel-aic5.c
index 9da9942ac83c..f6d680485bee 100644
--- a/drivers/irqchip/irq-atmel-aic5.c
+++ b/drivers/irqchip/irq-atmel-aic5.c
@@ -88,28 +88,36 @@ static void aic5_mask(struct irq_data *d)
 {
 	struct irq_domain *domain = d->domain;
 	struct irq_domain_chip_generic *dgc = domain->gc;
-	struct irq_chip_generic *gc = dgc->gc[0];
+	struct irq_chip_generic *bgc = dgc->gc[0];
+	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
 
-	/* Disable interrupt on AIC5 */
-	irq_gc_lock(gc);
+	/*
+	 * Disable interrupt on AIC5. We always take the lock of the
+	 * first irq chip as all chips share the same registers.
+	 */
+	irq_gc_lock(bgc);
 	irq_reg_writel(gc, d->hwirq, AT91_AIC5_SSR);
 	irq_reg_writel(gc, 1, AT91_AIC5_IDCR);
 	gc->mask_cache &= ~d->mask;
-	irq_gc_unlock(gc);
+	irq_gc_unlock(bgc);
 }
 
 static void aic5_unmask(struct irq_data *d)
 {
 	struct irq_domain *domain = d->domain;
 	struct irq_domain_chip_generic *dgc = domain->gc;
-	struct irq_chip_generic *gc = dgc->gc[0];
+	struct irq_chip_generic *bgc = dgc->gc[0];
+	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
 
-	/* Enable interrupt on AIC5 */
-	irq_gc_lock(gc);
+	/*
+	 * Enable interrupt on AIC5. We always take the lock of the
+	 * first irq chip as all chips share the same registers.
+	 */
+	irq_gc_lock(bgc);
 	irq_reg_writel(gc, d->hwirq, AT91_AIC5_SSR);
 	irq_reg_writel(gc, 1, AT91_AIC5_IECR);
 	gc->mask_cache |= d->mask;
-	irq_gc_unlock(gc);
+	irq_gc_unlock(bgc);
 }
 
 static int aic5_retrigger(struct irq_data *d)
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index d60c88df5234..4b3b6f8aff0c 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -968,7 +968,8 @@ static void crypt_free_buffer_pages(struct crypt_config *cc, struct bio *clone);
 
 /*
  * Generate a new unfragmented bio with the given size
- * This should never violate the device limitations
+ * This should never violate the device limitations (but only because
+ * max_segment_size is being constrained to PAGE_SIZE).
  *
  * This function may be called concurrently. If we allocate from the mempool
  * concurrently, there is a possibility of deadlock. For example, if we have
@@ -2045,9 +2046,20 @@ static int crypt_iterate_devices(struct dm_target *ti,
 	return fn(ti, cc->dev, cc->start, ti->len, data);
 }
 
+static void crypt_io_hints(struct dm_target *ti, struct queue_limits *limits)
+{
+	/*
+	 * Unfortunate constraint that is required to avoid the potential
+	 * for exceeding underlying device's max_segments limits -- due to
+	 * crypt_alloc_buffer() possibly allocating pages for the encryption
+	 * bio that are not as physically contiguous as the original bio.
+	 */
+	limits->max_segment_size = PAGE_SIZE;
+}
+
 static struct target_type crypt_target = {
 	.name   = "crypt",
-	.version = {1, 14, 0},
+	.version = {1, 14, 1},
 	.module = THIS_MODULE,
 	.ctr    = crypt_ctr,
 	.dtr    = crypt_dtr,
@@ -2058,6 +2070,7 @@ static struct target_type crypt_target = {
 	.resume = crypt_resume,
 	.message = crypt_message,
 	.iterate_devices = crypt_iterate_devices,
+	.io_hints = crypt_io_hints,
 };
 
 static int __init dm_crypt_init(void)
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index 6578b7bc1fbb..6fcbfb063366 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -4249,6 +4249,10 @@ static void thin_io_hints(struct dm_target *ti, struct queue_limits *limits)
 {
 	struct thin_c *tc = ti->private;
 	struct pool *pool = tc->pool;
+	struct queue_limits *pool_limits = dm_get_queue_limits(pool->pool_md);
+
+	if (!pool_limits->discard_granularity)
+		return; /* pool's discard support is disabled */
 
 	limits->discard_granularity = pool->sectors_per_block << SECTOR_SHIFT;
 	limits->max_discard_sectors = 2048 * 1024 * 16; /* 16G */
diff --git a/drivers/misc/cxl/sysfs.c b/drivers/misc/cxl/sysfs.c
index 25868c2ec03e..02006f7109a8 100644
--- a/drivers/misc/cxl/sysfs.c
+++ b/drivers/misc/cxl/sysfs.c
@@ -592,6 +592,8 @@ int cxl_sysfs_afu_add(struct cxl_afu *afu)
 
 	/* conditionally create the add the binary file for error info buffer */
 	if (afu->eb_len) {
+		sysfs_attr_init(&afu->attr_eb.attr);
+
 		afu->attr_eb.attr.name = "afu_err_buff";
 		afu->attr_eb.attr.mode = S_IRUGO;
 		afu->attr_eb.size = afu->eb_len;
diff --git a/drivers/misc/mei/debugfs.c b/drivers/misc/mei/debugfs.c
index 4b469cf9e60f..8504dbeacd3b 100644
--- a/drivers/misc/mei/debugfs.c
+++ b/drivers/misc/mei/debugfs.c
@@ -204,6 +204,8 @@ int mei_dbgfs_register(struct mei_device *dev, const char *name)
 	if (!dir)
 		return -ENOMEM;
 
+	dev->dbgfs_dir = dir;
+
 	f = debugfs_create_file("meclients", S_IRUSR, dir,
 				dev, &mei_dbgfs_fops_meclients);
 	if (!f) {
@@ -228,7 +230,6 @@ int mei_dbgfs_register(struct mei_device *dev, const char *name)
 		dev_err(dev->dev, "allow_fixed_address: registration failed\n");
 		goto err;
 	}
-	dev->dbgfs_dir = dir;
 	return 0;
 err:
 	mei_dbgfs_deregister(dev);
diff --git a/drivers/net/arcnet/arcnet.c b/drivers/net/arcnet/arcnet.c
index 10f71c732b59..816d0e94961c 100644
--- a/drivers/net/arcnet/arcnet.c
+++ b/drivers/net/arcnet/arcnet.c
@@ -326,7 +326,7 @@ static void arcdev_setup(struct net_device *dev)
 	dev->type = ARPHRD_ARCNET;
 	dev->netdev_ops = &arcnet_netdev_ops;
 	dev->header_ops = &arcnet_header_ops;
-	dev->hard_header_len = sizeof(struct archdr);
+	dev->hard_header_len = sizeof(struct arc_hardware);
 	dev->mtu = choose_mtu();
 
 	dev->addr_len = ARCNET_ALEN;
diff --git a/drivers/net/dsa/mv88e6xxx.c b/drivers/net/dsa/mv88e6xxx.c
index 6f13f7206762..f8baa897d1a0 100644
--- a/drivers/net/dsa/mv88e6xxx.c
+++ b/drivers/net/dsa/mv88e6xxx.c
@@ -2000,6 +2000,7 @@ static int mv88e6xxx_setup_port(struct dsa_switch *ds, int port)
 		 */
 		reg = _mv88e6xxx_reg_read(ds, REG_PORT(port), PORT_PCS_CTRL);
 		if (dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port)) {
+			reg &= ~PORT_PCS_CTRL_UNFORCED;
 			reg |= PORT_PCS_CTRL_FORCE_LINK |
 				PORT_PCS_CTRL_LINK_UP |
 				PORT_PCS_CTRL_DUPLEX_FULL |
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c
index cfa37041ab71..c4bb8027b3fb 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c
@@ -689,16 +689,24 @@ static int xgene_enet_phy_connect(struct net_device *ndev)
 			netdev_dbg(ndev, "No phy-handle found in DT\n");
 			return -ENODEV;
 		}
-		pdata->phy_dev = of_phy_find_device(phy_np);
-	}
 
-	phy_dev = pdata->phy_dev;
+		phy_dev = of_phy_connect(ndev, phy_np, &xgene_enet_adjust_link,
+					 0, pdata->phy_mode);
+		if (!phy_dev) {
+			netdev_err(ndev, "Could not connect to PHY\n");
+			return -ENODEV;
+		}
+
+		pdata->phy_dev = phy_dev;
+	} else {
+		phy_dev = pdata->phy_dev;
 
-	if (!phy_dev ||
-	    phy_connect_direct(ndev, phy_dev, &xgene_enet_adjust_link,
-			       pdata->phy_mode)) {
-		netdev_err(ndev, "Could not connect to PHY\n");
-		return  -ENODEV;
+		if (!phy_dev ||
+		    phy_connect_direct(ndev, phy_dev, &xgene_enet_adjust_link,
+				       pdata->phy_mode)) {
+			netdev_err(ndev, "Could not connect to PHY\n");
+			return  -ENODEV;
+		}
 	}
 
 	pdata->phy_speed = SPEED_UNKNOWN;
diff --git a/drivers/net/ethernet/arc/emac_arc.c b/drivers/net/ethernet/arc/emac_arc.c
index f9cb99bfb511..ffd180570920 100644
--- a/drivers/net/ethernet/arc/emac_arc.c
+++ b/drivers/net/ethernet/arc/emac_arc.c
@@ -78,6 +78,7 @@ static const struct of_device_id emac_arc_dt_ids[] = {
 	{ .compatible = "snps,arc-emac" },
 	{ /* Sentinel */ }
 };
+MODULE_DEVICE_TABLE(of, emac_arc_dt_ids);
 
 static struct platform_driver emac_arc_driver = {
 	.probe = emac_arc_probe,
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index b9a5a97ed4dd..f1b5364f3521 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -2079,6 +2079,7 @@ static const struct of_device_id bcm_sysport_of_match[] = {
 	{ .compatible = "brcm,systemport" },
 	{ /* sentinel */ }
 };
+MODULE_DEVICE_TABLE(of, bcm_sysport_of_match);
 
 static struct platform_driver bcm_sysport_driver = {
 	.probe	= bcm_sysport_probe,
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
index ba936635322a..b5e64b02200c 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
@@ -1946,6 +1946,7 @@ struct bnx2x {
 	u16 vlan_cnt;
 	u16 vlan_credit;
 	u16 vxlan_dst_port;
+	u8 vxlan_dst_port_count;
 	bool accept_any_vlan;
 };
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index e3da2bddf143..f1d62d5dbaff 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -3705,16 +3705,14 @@ out:
 
 void bnx2x_update_mfw_dump(struct bnx2x *bp)
 {
-	struct timeval epoc;
 	u32 drv_ver;
 	u32 valid_dump;
 
 	if (!SHMEM2_HAS(bp, drv_info))
 		return;
 
-	/* Update Driver load time */
-	do_gettimeofday(&epoc);
-	SHMEM2_WR(bp, drv_info.epoc, epoc.tv_sec);
+	/* Update Driver load time, possibly broken in y2038 */
+	SHMEM2_WR(bp, drv_info.epoc, (u32)ktime_get_real_seconds());
 
 	drv_ver = bnx2x_update_mng_version_utility(DRV_MODULE_VERSION, true);
 	SHMEM2_WR(bp, drv_info.drv_ver, drv_ver);
@@ -10110,12 +10108,18 @@ static void __bnx2x_add_vxlan_port(struct bnx2x *bp, u16 port)
 	if (!netif_running(bp->dev))
 		return;
 
-	if (bp->vxlan_dst_port || !IS_PF(bp)) {
+	if (bp->vxlan_dst_port_count && bp->vxlan_dst_port == port) {
+		bp->vxlan_dst_port_count++;
+		return;
+	}
+
+	if (bp->vxlan_dst_port_count || !IS_PF(bp)) {
 		DP(BNX2X_MSG_SP, "Vxlan destination port limit reached\n");
 		return;
 	}
 
 	bp->vxlan_dst_port = port;
+	bp->vxlan_dst_port_count = 1;
 	bnx2x_schedule_sp_rtnl(bp, BNX2X_SP_RTNL_ADD_VXLAN_PORT, 0);
 }
 
@@ -10130,10 +10134,14 @@ static void bnx2x_add_vxlan_port(struct net_device *netdev,
 
 static void __bnx2x_del_vxlan_port(struct bnx2x *bp, u16 port)
 {
-	if (!bp->vxlan_dst_port || bp->vxlan_dst_port != port || !IS_PF(bp)) {
+	if (!bp->vxlan_dst_port_count || bp->vxlan_dst_port != port ||
+	    !IS_PF(bp)) {
 		DP(BNX2X_MSG_SP, "Invalid vxlan port\n");
 		return;
 	}
+	bp->vxlan_dst_port--;
+	if (bp->vxlan_dst_port)
+		return;
 
 	if (netif_running(bp->dev)) {
 		bnx2x_schedule_sp_rtnl(bp, BNX2X_SP_RTNL_DEL_VXLAN_PORT, 0);
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
index c9bd7f16018e..ff702a707a91 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
@@ -4319,8 +4319,16 @@ static int bnx2x_setup_rss(struct bnx2x *bp,
 
 	/* RSS keys */
 	if (test_bit(BNX2X_RSS_SET_SRCH, &p->rss_flags)) {
-		memcpy(&data->rss_key[0], &p->rss_key[0],
-		       sizeof(data->rss_key));
+		u8 *dst = (u8 *)(data->rss_key) + sizeof(data->rss_key);
+		const u8 *src = (const u8 *)p->rss_key;
+		int i;
+
+		/* Apparently, bnx2x reads this array in reverse order
+		 * We need to byte swap rss_key to comply with Toeplitz specs.
+		 */
+		for (i = 0; i < sizeof(data->rss_key); i++)
+			*--dst = *src++;
+
 		caps |= ETH_RSS_UPDATE_RAMROD_DATA_UPDATE_RSS_KEY;
 	}
 
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index fadbd0088d3e..3bc701e4c59e 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -3155,6 +3155,7 @@ static const struct of_device_id bcmgenet_match[] = {
 	{ .compatible = "brcm,genet-v4", .data = (void *)GENET_V4 },
 	{ },
 };
+MODULE_DEVICE_TABLE(of, bcmgenet_match);
 
 static int bcmgenet_probe(struct platform_device *pdev)
 {
diff --git a/drivers/net/ethernet/brocade/bna/bna_tx_rx.c b/drivers/net/ethernet/brocade/bna/bna_tx_rx.c
index 5d0753cc7e73..04b0d16b210e 100644
--- a/drivers/net/ethernet/brocade/bna/bna_tx_rx.c
+++ b/drivers/net/ethernet/brocade/bna/bna_tx_rx.c
@@ -2400,6 +2400,7 @@ bna_rx_create(struct bna *bna, struct bnad *bnad,
 		q0->rcb->id = 0;
 		q0->rx_packets = q0->rx_bytes = 0;
 		q0->rx_packets_with_error = q0->rxbuf_alloc_failed = 0;
+		q0->rxbuf_map_failed = 0;
 
 		bna_rxq_qpt_setup(q0, rxp, dpage_count, PAGE_SIZE,
 			&dqpt_mem[i], &dsqpt_mem[i], &dpage_mem[i]);
@@ -2428,6 +2429,7 @@ bna_rx_create(struct bna *bna, struct bnad *bnad,
 					: rx_cfg->q1_buf_size;
 			q1->rx_packets = q1->rx_bytes = 0;
 			q1->rx_packets_with_error = q1->rxbuf_alloc_failed = 0;
+			q1->rxbuf_map_failed = 0;
 
 			bna_rxq_qpt_setup(q1, rxp, hpage_count, PAGE_SIZE,
 				&hqpt_mem[i], &hsqpt_mem[i],
diff --git a/drivers/net/ethernet/brocade/bna/bna_types.h b/drivers/net/ethernet/brocade/bna/bna_types.h
index e0e797f2ea14..c438d032e8bf 100644
--- a/drivers/net/ethernet/brocade/bna/bna_types.h
+++ b/drivers/net/ethernet/brocade/bna/bna_types.h
@@ -587,6 +587,7 @@ struct bna_rxq {
 	u64		rx_bytes;
 	u64		rx_packets_with_error;
 	u64		rxbuf_alloc_failed;
+	u64		rxbuf_map_failed;
 };
 
 /* RxQ pair */
diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c
index 506047c38607..21a0cfc3e7ec 100644
--- a/drivers/net/ethernet/brocade/bna/bnad.c
+++ b/drivers/net/ethernet/brocade/bna/bnad.c
@@ -399,7 +399,13 @@ bnad_rxq_refill_page(struct bnad *bnad, struct bna_rcb *rcb, u32 nalloc)
 		}
 
 		dma_addr = dma_map_page(&bnad->pcidev->dev, page, page_offset,
-				unmap_q->map_size, DMA_FROM_DEVICE);
+					unmap_q->map_size, DMA_FROM_DEVICE);
+		if (dma_mapping_error(&bnad->pcidev->dev, dma_addr)) {
+			put_page(page);
+			BNAD_UPDATE_CTR(bnad, rxbuf_map_failed);
+			rcb->rxq->rxbuf_map_failed++;
+			goto finishing;
+		}
 
 		unmap->page = page;
 		unmap->page_offset = page_offset;
@@ -454,8 +460,15 @@ bnad_rxq_refill_skb(struct bnad *bnad, struct bna_rcb *rcb, u32 nalloc)
 			rcb->rxq->rxbuf_alloc_failed++;
 			goto finishing;
 		}
+
 		dma_addr = dma_map_single(&bnad->pcidev->dev, skb->data,
 					  buff_sz, DMA_FROM_DEVICE);
+		if (dma_mapping_error(&bnad->pcidev->dev, dma_addr)) {
+			dev_kfree_skb_any(skb);
+			BNAD_UPDATE_CTR(bnad, rxbuf_map_failed);
+			rcb->rxq->rxbuf_map_failed++;
+			goto finishing;
+		}
 
 		unmap->skb = skb;
 		dma_unmap_addr_set(&unmap->vector, dma_addr, dma_addr);
@@ -3025,6 +3038,11 @@ bnad_start_xmit(struct sk_buff *skb, struct net_device *netdev)
 	unmap = head_unmap;
 	dma_addr = dma_map_single(&bnad->pcidev->dev, skb->data,
 				  len, DMA_TO_DEVICE);
+	if (dma_mapping_error(&bnad->pcidev->dev, dma_addr)) {
+		dev_kfree_skb_any(skb);
+		BNAD_UPDATE_CTR(bnad, tx_skb_map_failed);
+		return NETDEV_TX_OK;
+	}
 	BNA_SET_DMA_ADDR(dma_addr, &txqent->vector[0].host_addr);
 	txqent->vector[0].length = htons(len);
 	dma_unmap_addr_set(&unmap->vectors[0], dma_addr, dma_addr);
@@ -3056,6 +3074,15 @@ bnad_start_xmit(struct sk_buff *skb, struct net_device *netdev)
 
 		dma_addr = skb_frag_dma_map(&bnad->pcidev->dev, frag,
 					    0, size, DMA_TO_DEVICE);
+		if (dma_mapping_error(&bnad->pcidev->dev, dma_addr)) {
+			/* Undo the changes starting at tcb->producer_index */
+			bnad_tx_buff_unmap(bnad, unmap_q, q_depth,
+					   tcb->producer_index);
+			dev_kfree_skb_any(skb);
+			BNAD_UPDATE_CTR(bnad, tx_skb_map_failed);
+			return NETDEV_TX_OK;
+		}
+
 		dma_unmap_len_set(&unmap->vectors[vect_id], dma_len, size);
 		BNA_SET_DMA_ADDR(dma_addr, &txqent->vector[vect_id].host_addr);
 		txqent->vector[vect_id].length = htons(size);
diff --git a/drivers/net/ethernet/brocade/bna/bnad.h b/drivers/net/ethernet/brocade/bna/bnad.h
index faedbf24777e..f4ed816b93ee 100644
--- a/drivers/net/ethernet/brocade/bna/bnad.h
+++ b/drivers/net/ethernet/brocade/bna/bnad.h
@@ -175,6 +175,7 @@ struct bnad_drv_stats {
 	u64		tx_skb_headlen_zero;
 	u64		tx_skb_frag_zero;
 	u64		tx_skb_len_mismatch;
+	u64		tx_skb_map_failed;
 
 	u64		hw_stats_updates;
 	u64		netif_rx_dropped;
@@ -189,6 +190,7 @@ struct bnad_drv_stats {
 	u64		rx_unmap_q_alloc_failed;
 
 	u64		rxbuf_alloc_failed;
+	u64		rxbuf_map_failed;
 };
 
 /* Complete driver stats */
diff --git a/drivers/net/ethernet/brocade/bna/bnad_ethtool.c b/drivers/net/ethernet/brocade/bna/bnad_ethtool.c
index 2bdfc5dff4b1..0e4fdc3dd729 100644
--- a/drivers/net/ethernet/brocade/bna/bnad_ethtool.c
+++ b/drivers/net/ethernet/brocade/bna/bnad_ethtool.c
@@ -90,6 +90,7 @@ static const char *bnad_net_stats_strings[BNAD_ETHTOOL_STATS_NUM] = {
 	"tx_skb_headlen_zero",
 	"tx_skb_frag_zero",
 	"tx_skb_len_mismatch",
+	"tx_skb_map_failed",
 	"hw_stats_updates",
 	"netif_rx_dropped",
 
@@ -102,6 +103,7 @@ static const char *bnad_net_stats_strings[BNAD_ETHTOOL_STATS_NUM] = {
 	"tx_unmap_q_alloc_failed",
 	"rx_unmap_q_alloc_failed",
 	"rxbuf_alloc_failed",
+	"rxbuf_map_failed",
 
 	"mac_stats_clr_cnt",
 	"mac_frame_64",
@@ -807,6 +809,7 @@ bnad_per_q_stats_fill(struct bnad *bnad, u64 *buf, int bi)
 							rx_packets_with_error;
 					buf[bi++] = rcb->rxq->
 							rxbuf_alloc_failed;
+					buf[bi++] = rcb->rxq->rxbuf_map_failed;
 					buf[bi++] = rcb->producer_index;
 					buf[bi++] = rcb->consumer_index;
 				}
@@ -821,6 +824,7 @@ bnad_per_q_stats_fill(struct bnad *bnad, u64 *buf, int bi)
 							rx_packets_with_error;
 					buf[bi++] = rcb->rxq->
 							rxbuf_alloc_failed;
+					buf[bi++] = rcb->rxq->rxbuf_map_failed;
 					buf[bi++] = rcb->producer_index;
 					buf[bi++] = rcb->consumer_index;
 				}
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
index 8353a6cbfcc2..03ed00c49823 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
@@ -157,6 +157,11 @@ CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN
 	CH_PCI_ID_TABLE_FENTRY(0x5090),	/* Custom T540-CR */
 	CH_PCI_ID_TABLE_FENTRY(0x5091),	/* Custom T522-CR */
 	CH_PCI_ID_TABLE_FENTRY(0x5092),	/* Custom T520-CR */
+	CH_PCI_ID_TABLE_FENTRY(0x5093),	/* Custom T580-LP-CR */
+	CH_PCI_ID_TABLE_FENTRY(0x5094),	/* Custom T540-CR */
+	CH_PCI_ID_TABLE_FENTRY(0x5095),	/* Custom T540-CR-SO */
+	CH_PCI_ID_TABLE_FENTRY(0x5096),	/* Custom T580-CR */
+	CH_PCI_ID_TABLE_FENTRY(0x5097),	/* Custom T520-KR */
 
 	/* T6 adapters:
 	 */
diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h
index 0a27805cbbbd..821540913343 100644
--- a/drivers/net/ethernet/emulex/benet/be.h
+++ b/drivers/net/ethernet/emulex/benet/be.h
@@ -582,6 +582,7 @@ struct be_adapter {
 	u16 pvid;
 	__be16 vxlan_port;
 	int vxlan_port_count;
+	int vxlan_port_aliases;
 	struct phy_info phy;
 	u8 wol_cap;
 	bool wol_en;
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 12687bf52b95..7bf51a1a0a77 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -5176,6 +5176,11 @@ static void be_add_vxlan_port(struct net_device *netdev, sa_family_t sa_family,
 	if (lancer_chip(adapter) || BEx_chip(adapter) || be_is_mc(adapter))
 		return;
 
+	if (adapter->vxlan_port == port && adapter->vxlan_port_count) {
+		adapter->vxlan_port_aliases++;
+		return;
+	}
+
 	if (adapter->flags & BE_FLAGS_VXLAN_OFFLOADS) {
 		dev_info(dev,
 			 "Only one UDP port supported for VxLAN offloads\n");
@@ -5226,6 +5231,11 @@ static void be_del_vxlan_port(struct net_device *netdev, sa_family_t sa_family,
 	if (adapter->vxlan_port != port)
 		goto done;
 
+	if (adapter->vxlan_port_aliases) {
+		adapter->vxlan_port_aliases--;
+		return;
+	}
+
 	be_disable_vxlan_offloads(adapter);
 
 	dev_info(&adapter->pdev->dev,
diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index 4b69d061d90f..710715fcb23d 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -1710,8 +1710,10 @@ static void gfar_configure_serdes(struct net_device *dev)
 	 * everything for us?  Resetting it takes the link down and requires
 	 * several seconds for it to come back.
 	 */
-	if (phy_read(tbiphy, MII_BMSR) & BMSR_LSTATUS)
+	if (phy_read(tbiphy, MII_BMSR) & BMSR_LSTATUS) {
+		put_device(&tbiphy->dev);
 		return;
+	}
 
 	/* Single clk mode, mii mode off(for serdes communication) */
 	phy_write(tbiphy, MII_TBICON, TBICON_CLK_SELECT);
@@ -1723,6 +1725,8 @@ static void gfar_configure_serdes(struct net_device *dev)
 	phy_write(tbiphy, MII_BMCR,
 		  BMCR_ANENABLE | BMCR_ANRESTART | BMCR_FULLDPLX |
 		  BMCR_SPEED1000);
+
+	put_device(&tbiphy->dev);
 }
 
 static int __gfar_is_rx_idle(struct gfar_private *priv)
@@ -1970,8 +1974,7 @@ static int register_grp_irqs(struct gfar_priv_grp *grp)
 		/* Install our interrupt handlers for Error,
 		 * Transmit, and Receive
 		 */
-		err = request_irq(gfar_irq(grp, ER)->irq, gfar_error,
-				  IRQF_NO_SUSPEND,
+		err = request_irq(gfar_irq(grp, ER)->irq, gfar_error, 0,
 				  gfar_irq(grp, ER)->name, grp);
 		if (err < 0) {
 			netif_err(priv, intr, dev, "Can't get IRQ %d\n",
@@ -1979,6 +1982,8 @@ static int register_grp_irqs(struct gfar_priv_grp *grp)
 
 			goto err_irq_fail;
 		}
+		enable_irq_wake(gfar_irq(grp, ER)->irq);
+
 		err = request_irq(gfar_irq(grp, TX)->irq, gfar_transmit, 0,
 				  gfar_irq(grp, TX)->name, grp);
 		if (err < 0) {
@@ -1994,14 +1999,14 @@ static int register_grp_irqs(struct gfar_priv_grp *grp)
 			goto rx_irq_fail;
 		}
 	} else {
-		err = request_irq(gfar_irq(grp, TX)->irq, gfar_interrupt,
-				  IRQF_NO_SUSPEND,
+		err = request_irq(gfar_irq(grp, TX)->irq, gfar_interrupt, 0,
 				  gfar_irq(grp, TX)->name, grp);
 		if (err < 0) {
 			netif_err(priv, intr, dev, "Can't get IRQ %d\n",
 				  gfar_irq(grp, TX)->irq);
 			goto err_irq_fail;
 		}
+		enable_irq_wake(gfar_irq(grp, TX)->irq);
 	}
 
 	return 0;
diff --git a/drivers/net/ethernet/freescale/gianfar_ptp.c b/drivers/net/ethernet/freescale/gianfar_ptp.c
index 8e3cd77aa347..664d0c261269 100644
--- a/drivers/net/ethernet/freescale/gianfar_ptp.c
+++ b/drivers/net/ethernet/freescale/gianfar_ptp.c
@@ -557,6 +557,7 @@ static const struct of_device_id match_table[] = {
 	{ .compatible = "fsl,etsec-ptp" },
 	{},
 };
+MODULE_DEVICE_TABLE(of, match_table);
 
 static struct platform_driver gianfar_ptp_driver = {
 	.driver = {
diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c
index 4dd40e057f40..650f7888e32b 100644
--- a/drivers/net/ethernet/freescale/ucc_geth.c
+++ b/drivers/net/ethernet/freescale/ucc_geth.c
@@ -1384,6 +1384,8 @@ static int adjust_enet_interface(struct ucc_geth_private *ugeth)
 		value = phy_read(tbiphy, ENET_TBI_MII_CR);
 		value &= ~0x1000;	/* Turn off autonegotiation */
 		phy_write(tbiphy, ENET_TBI_MII_CR, value);
+
+		put_device(&tbiphy->dev);
 	}
 
 	init_check_frame_length_mode(ug_info->lengthCheckRx, &ug_regs->maccfg2);
@@ -1702,8 +1704,10 @@ static void uec_configure_serdes(struct net_device *dev)
 	 * everything for us?  Resetting it takes the link down and requires
 	 * several seconds for it to come back.
 	 */
-	if (phy_read(tbiphy, ENET_TBI_MII_SR) & TBISR_LSTATUS)
+	if (phy_read(tbiphy, ENET_TBI_MII_SR) & TBISR_LSTATUS) {
+		put_device(&tbiphy->dev);
 		return;
+	}
 
 	/* Single clk mode, mii mode off(for serdes communication) */
 	phy_write(tbiphy, ENET_TBI_MII_ANA, TBIANA_SETTINGS);
@@ -1711,6 +1715,8 @@ static void uec_configure_serdes(struct net_device *dev)
 	phy_write(tbiphy, ENET_TBI_MII_TBICON, TBICON_CLK_SELECT);
 
 	phy_write(tbiphy, ENET_TBI_MII_CR, TBICR_SETTINGS);
+
+	put_device(&tbiphy->dev);
 }
 
 /* Configure the PHY for dev.
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index fe2299ac4f5c..514df76fc70f 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -1479,6 +1479,7 @@ static int mvneta_rx(struct mvneta_port *pp, int rx_todo,
 		struct mvneta_rx_desc *rx_desc = mvneta_rxq_next_desc_get(rxq);
 		struct sk_buff *skb;
 		unsigned char *data;
+		dma_addr_t phys_addr;
 		u32 rx_status;
 		int rx_bytes, err;
 
@@ -1486,6 +1487,7 @@ static int mvneta_rx(struct mvneta_port *pp, int rx_todo,
 		rx_status = rx_desc->status;
 		rx_bytes = rx_desc->data_size - (ETH_FCS_LEN + MVNETA_MH_SIZE);
 		data = (unsigned char *)rx_desc->buf_cookie;
+		phys_addr = rx_desc->buf_phys_addr;
 
 		if (!mvneta_rxq_desc_is_first_last(rx_status) ||
 		    (rx_status & MVNETA_RXD_ERR_SUMMARY)) {
@@ -1534,7 +1536,7 @@ static int mvneta_rx(struct mvneta_port *pp, int rx_todo,
 		if (!skb)
 			goto err_drop_frame;
 
-		dma_unmap_single(dev->dev.parent, rx_desc->buf_phys_addr,
+		dma_unmap_single(dev->dev.parent, phys_addr,
 				 MVNETA_RX_BUF_SIZE(pp->pkt_size), DMA_FROM_DEVICE);
 
 		rcvd_pkts++;
@@ -3173,6 +3175,8 @@ static int mvneta_probe(struct platform_device *pdev)
 		struct phy_device *phy = of_phy_find_device(dn);
 
 		mvneta_fixed_link_update(pp, phy);
+
+		put_device(&phy->dev);
 	}
 
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 4c7de8c44659..e7a5000aa12c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -1270,8 +1270,6 @@ int mlx4_en_config_rss_steer(struct mlx4_en_priv *priv)
 		rss_context->hash_fn = MLX4_RSS_HASH_TOP;
 		memcpy(rss_context->rss_key, priv->rss_key,
 		       MLX4_EN_RSS_KEY_SIZE);
-		netdev_rss_key_fill(rss_context->rss_key,
-				    MLX4_EN_RSS_KEY_SIZE);
 	} else {
 		en_err(priv, "Unknown RSS hash function requested\n");
 		err = -EINVAL;
diff --git a/drivers/net/ethernet/micrel/ks8851.c b/drivers/net/ethernet/micrel/ks8851.c
index 66d4ab703f45..60f43ec22175 100644
--- a/drivers/net/ethernet/micrel/ks8851.c
+++ b/drivers/net/ethernet/micrel/ks8851.c
@@ -1601,6 +1601,7 @@ static const struct of_device_id ks8851_match_table[] = {
 	{ .compatible = "micrel,ks8851" },
 	{ }
 };
+MODULE_DEVICE_TABLE(of, ks8851_match_table);
 
 static struct spi_driver ks8851_driver = {
 	.driver = {
diff --git a/drivers/net/ethernet/moxa/moxart_ether.c b/drivers/net/ethernet/moxa/moxart_ether.c
index becbb5f1f5a7..a10c928bbd6b 100644
--- a/drivers/net/ethernet/moxa/moxart_ether.c
+++ b/drivers/net/ethernet/moxa/moxart_ether.c
@@ -552,6 +552,7 @@ static const struct of_device_id moxart_mac_match[] = {
 	{ .compatible = "moxa,moxart-mac" },
 	{ }
 };
+MODULE_DEVICE_TABLE(of, moxart_mac_match);
 
 static struct platform_driver moxart_mac_driver = {
 	.probe	= moxart_mac_probe,
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
index 06bcc734fe8d..d6696cfa11d2 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
@@ -536,6 +536,7 @@ struct qlcnic_hardware_context {
 	u8 extend_lb_time;
 	u8 phys_port_id[ETH_ALEN];
 	u8 lb_mode;
+	u8 vxlan_port_count;
 	u16 vxlan_port;
 	struct device *hwmon_dev;
 	u32 post_mode;
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
index 8b08b20e8b30..d4481454b5f8 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
@@ -483,11 +483,17 @@ static void qlcnic_add_vxlan_port(struct net_device *netdev,
 	/* Adapter supports only one VXLAN port. Use very first port
 	 * for enabling offload
 	 */
-	if (!qlcnic_encap_rx_offload(adapter) || ahw->vxlan_port)
+	if (!qlcnic_encap_rx_offload(adapter))
 		return;
+	if (!ahw->vxlan_port_count) {
+		ahw->vxlan_port_count = 1;
+		ahw->vxlan_port = ntohs(port);
+		adapter->flags |= QLCNIC_ADD_VXLAN_PORT;
+		return;
+	}
+	if (ahw->vxlan_port == ntohs(port))
+		ahw->vxlan_port_count++;
 
-	ahw->vxlan_port = ntohs(port);
-	adapter->flags |= QLCNIC_ADD_VXLAN_PORT;
 }
 
 static void qlcnic_del_vxlan_port(struct net_device *netdev,
@@ -496,11 +502,13 @@ static void qlcnic_del_vxlan_port(struct net_device *netdev,
 	struct qlcnic_adapter *adapter = netdev_priv(netdev);
 	struct qlcnic_hardware_context *ahw = adapter->ahw;
 
-	if (!qlcnic_encap_rx_offload(adapter) || !ahw->vxlan_port ||
+	if (!qlcnic_encap_rx_offload(adapter) || !ahw->vxlan_port_count ||
 	    (ahw->vxlan_port != ntohs(port)))
 		return;
 
-	adapter->flags |= QLCNIC_DEL_VXLAN_PORT;
+	ahw->vxlan_port_count--;
+	if (!ahw->vxlan_port_count)
+		adapter->flags |= QLCNIC_DEL_VXLAN_PORT;
 }
 
 static netdev_features_t qlcnic_features_check(struct sk_buff *skb,
diff --git a/drivers/net/ethernet/realtek/8139cp.c b/drivers/net/ethernet/realtek/8139cp.c
index d79e33b3c191..686334f4588d 100644
--- a/drivers/net/ethernet/realtek/8139cp.c
+++ b/drivers/net/ethernet/realtek/8139cp.c
@@ -157,6 +157,7 @@ enum {
 	NWayAdvert	= 0x66, /* MII ADVERTISE */
 	NWayLPAR	= 0x68, /* MII LPA */
 	NWayExpansion	= 0x6A, /* MII Expansion */
+	TxDmaOkLowDesc  = 0x82, /* Low 16 bit address of a Tx descriptor. */
 	Config5		= 0xD8,	/* Config5 */
 	TxPoll		= 0xD9,	/* Tell chip to check Tx descriptors for work */
 	RxMaxSize	= 0xDA, /* Max size of an Rx packet (8169 only) */
@@ -341,6 +342,7 @@ struct cp_private {
 	unsigned		tx_tail;
 	struct cp_desc		*tx_ring;
 	struct sk_buff		*tx_skb[CP_TX_RING_SIZE];
+	u32			tx_opts[CP_TX_RING_SIZE];
 
 	unsigned		rx_buf_sz;
 	unsigned		wol_enabled : 1; /* Is Wake-on-LAN enabled? */
@@ -665,7 +667,7 @@ static void cp_tx (struct cp_private *cp)
 		BUG_ON(!skb);
 
 		dma_unmap_single(&cp->pdev->dev, le64_to_cpu(txd->addr),
-				 le32_to_cpu(txd->opts1) & 0xffff,
+				 cp->tx_opts[tx_tail] & 0xffff,
 				 PCI_DMA_TODEVICE);
 
 		if (status & LastFrag) {
@@ -733,7 +735,7 @@ static netdev_tx_t cp_start_xmit (struct sk_buff *skb,
 {
 	struct cp_private *cp = netdev_priv(dev);
 	unsigned entry;
-	u32 eor, flags;
+	u32 eor, opts1;
 	unsigned long intr_flags;
 	__le32 opts2;
 	int mss = 0;
@@ -753,6 +755,21 @@ static netdev_tx_t cp_start_xmit (struct sk_buff *skb,
 	mss = skb_shinfo(skb)->gso_size;
 
 	opts2 = cpu_to_le32(cp_tx_vlan_tag(skb));
+	opts1 = DescOwn;
+	if (mss)
+		opts1 |= LargeSend | ((mss & MSSMask) << MSSShift);
+	else if (skb->ip_summed == CHECKSUM_PARTIAL) {
+		const struct iphdr *ip = ip_hdr(skb);
+		if (ip->protocol == IPPROTO_TCP)
+			opts1 |= IPCS | TCPCS;
+		else if (ip->protocol == IPPROTO_UDP)
+			opts1 |= IPCS | UDPCS;
+		else {
+			WARN_ONCE(1,
+				  "Net bug: asked to checksum invalid Legacy IP packet\n");
+			goto out_dma_error;
+		}
+	}
 
 	if (skb_shinfo(skb)->nr_frags == 0) {
 		struct cp_desc *txd = &cp->tx_ring[entry];
@@ -768,31 +785,20 @@ static netdev_tx_t cp_start_xmit (struct sk_buff *skb,
 		txd->addr = cpu_to_le64(mapping);
 		wmb();
 
-		flags = eor | len | DescOwn | FirstFrag | LastFrag;
-
-		if (mss)
-			flags |= LargeSend | ((mss & MSSMask) << MSSShift);
-		else if (skb->ip_summed == CHECKSUM_PARTIAL) {
-			const struct iphdr *ip = ip_hdr(skb);
-			if (ip->protocol == IPPROTO_TCP)
-				flags |= IPCS | TCPCS;
-			else if (ip->protocol == IPPROTO_UDP)
-				flags |= IPCS | UDPCS;
-			else
-				WARN_ON(1);	/* we need a WARN() */
-		}
+		opts1 |= eor | len | FirstFrag | LastFrag;
 
-		txd->opts1 = cpu_to_le32(flags);
+		txd->opts1 = cpu_to_le32(opts1);
 		wmb();
 
 		cp->tx_skb[entry] = skb;
-		entry = NEXT_TX(entry);
+		cp->tx_opts[entry] = opts1;
+		netif_dbg(cp, tx_queued, cp->dev, "tx queued, slot %d, skblen %d\n",
+			  entry, skb->len);
 	} else {
 		struct cp_desc *txd;
-		u32 first_len, first_eor;
+		u32 first_len, first_eor, ctrl;
 		dma_addr_t first_mapping;
 		int frag, first_entry = entry;
-		const struct iphdr *ip = ip_hdr(skb);
 
 		/* We must give this initial chunk to the device last.
 		 * Otherwise we could race with the device.
@@ -805,14 +811,14 @@ static netdev_tx_t cp_start_xmit (struct sk_buff *skb,
 			goto out_dma_error;
 
 		cp->tx_skb[entry] = skb;
-		entry = NEXT_TX(entry);
 
 		for (frag = 0; frag < skb_shinfo(skb)->nr_frags; frag++) {
 			const skb_frag_t *this_frag = &skb_shinfo(skb)->frags[frag];
 			u32 len;
-			u32 ctrl;
 			dma_addr_t mapping;
 
+			entry = NEXT_TX(entry);
+
 			len = skb_frag_size(this_frag);
 			mapping = dma_map_single(&cp->pdev->dev,
 						 skb_frag_address(this_frag),
@@ -824,19 +830,7 @@ static netdev_tx_t cp_start_xmit (struct sk_buff *skb,
 
 			eor = (entry == (CP_TX_RING_SIZE - 1)) ? RingEnd : 0;
 
-			ctrl = eor | len | DescOwn;
-
-			if (mss)
-				ctrl |= LargeSend |
-					((mss & MSSMask) << MSSShift);
-			else if (skb->ip_summed == CHECKSUM_PARTIAL) {
-				if (ip->protocol == IPPROTO_TCP)
-					ctrl |= IPCS | TCPCS;
-				else if (ip->protocol == IPPROTO_UDP)
-					ctrl |= IPCS | UDPCS;
-				else
-					BUG();
-			}
+			ctrl = opts1 | eor | len;
 
 			if (frag == skb_shinfo(skb)->nr_frags - 1)
 				ctrl |= LastFrag;
@@ -849,8 +843,8 @@ static netdev_tx_t cp_start_xmit (struct sk_buff *skb,
 			txd->opts1 = cpu_to_le32(ctrl);
 			wmb();
 
+			cp->tx_opts[entry] = ctrl;
 			cp->tx_skb[entry] = skb;
-			entry = NEXT_TX(entry);
 		}
 
 		txd = &cp->tx_ring[first_entry];
@@ -858,27 +852,17 @@ static netdev_tx_t cp_start_xmit (struct sk_buff *skb,
 		txd->addr = cpu_to_le64(first_mapping);
 		wmb();
 
-		if (skb->ip_summed == CHECKSUM_PARTIAL) {
-			if (ip->protocol == IPPROTO_TCP)
-				txd->opts1 = cpu_to_le32(first_eor | first_len |
-							 FirstFrag | DescOwn |
-							 IPCS | TCPCS);
-			else if (ip->protocol == IPPROTO_UDP)
-				txd->opts1 = cpu_to_le32(first_eor | first_len |
-							 FirstFrag | DescOwn |
-							 IPCS | UDPCS);
-			else
-				BUG();
-		} else
-			txd->opts1 = cpu_to_le32(first_eor | first_len |
-						 FirstFrag | DescOwn);
+		ctrl = opts1 | first_eor | first_len | FirstFrag;
+		txd->opts1 = cpu_to_le32(ctrl);
 		wmb();
+
+		cp->tx_opts[first_entry] = ctrl;
+		netif_dbg(cp, tx_queued, cp->dev, "tx queued, slots %d-%d, skblen %d\n",
+			  first_entry, entry, skb->len);
 	}
-	cp->tx_head = entry;
+	cp->tx_head = NEXT_TX(entry);
 
 	netdev_sent_queue(dev, skb->len);
-	netif_dbg(cp, tx_queued, cp->dev, "tx queued, slot %d, skblen %d\n",
-		  entry, skb->len);
 	if (TX_BUFFS_AVAIL(cp) <= (MAX_SKB_FRAGS + 1))
 		netif_stop_queue(dev);
 
@@ -1115,6 +1099,7 @@ static int cp_init_rings (struct cp_private *cp)
 {
 	memset(cp->tx_ring, 0, sizeof(struct cp_desc) * CP_TX_RING_SIZE);
 	cp->tx_ring[CP_TX_RING_SIZE - 1].opts1 = cpu_to_le32(RingEnd);
+	memset(cp->tx_opts, 0, sizeof(cp->tx_opts));
 
 	cp_init_rings_index(cp);
 
@@ -1151,7 +1136,7 @@ static void cp_clean_rings (struct cp_private *cp)
 			desc = cp->rx_ring + i;
 			dma_unmap_single(&cp->pdev->dev,le64_to_cpu(desc->addr),
 					 cp->rx_buf_sz, PCI_DMA_FROMDEVICE);
-			dev_kfree_skb(cp->rx_skb[i]);
+			dev_kfree_skb_any(cp->rx_skb[i]);
 		}
 	}
 
@@ -1164,7 +1149,7 @@ static void cp_clean_rings (struct cp_private *cp)
 					 le32_to_cpu(desc->opts1) & 0xffff,
 					 PCI_DMA_TODEVICE);
 			if (le32_to_cpu(desc->opts1) & LastFrag)
-				dev_kfree_skb(skb);
+				dev_kfree_skb_any(skb);
 			cp->dev->stats.tx_dropped++;
 		}
 	}
@@ -1172,6 +1157,7 @@ static void cp_clean_rings (struct cp_private *cp)
 
 	memset(cp->rx_ring, 0, sizeof(struct cp_desc) * CP_RX_RING_SIZE);
 	memset(cp->tx_ring, 0, sizeof(struct cp_desc) * CP_TX_RING_SIZE);
+	memset(cp->tx_opts, 0, sizeof(cp->tx_opts));
 
 	memset(cp->rx_skb, 0, sizeof(struct sk_buff *) * CP_RX_RING_SIZE);
 	memset(cp->tx_skb, 0, sizeof(struct sk_buff *) * CP_TX_RING_SIZE);
@@ -1249,7 +1235,7 @@ static void cp_tx_timeout(struct net_device *dev)
 {
 	struct cp_private *cp = netdev_priv(dev);
 	unsigned long flags;
-	int rc;
+	int rc, i;
 
 	netdev_warn(dev, "Transmit timeout, status %2x %4x %4x %4x\n",
 		    cpr8(Cmd), cpr16(CpCmd),
@@ -1257,13 +1243,26 @@ static void cp_tx_timeout(struct net_device *dev)
 
 	spin_lock_irqsave(&cp->lock, flags);
 
+	netif_dbg(cp, tx_err, cp->dev, "TX ring head %d tail %d desc %x\n",
+		  cp->tx_head, cp->tx_tail, cpr16(TxDmaOkLowDesc));
+	for (i = 0; i < CP_TX_RING_SIZE; i++) {
+		netif_dbg(cp, tx_err, cp->dev,
+			  "TX slot %d @%p: %08x (%08x) %08x %llx %p\n",
+			  i, &cp->tx_ring[i], le32_to_cpu(cp->tx_ring[i].opts1),
+			  cp->tx_opts[i], le32_to_cpu(cp->tx_ring[i].opts2),
+			  le64_to_cpu(cp->tx_ring[i].addr),
+			  cp->tx_skb[i]);
+	}
+
 	cp_stop_hw(cp);
 	cp_clean_rings(cp);
 	rc = cp_init_rings(cp);
 	cp_start_hw(cp);
-	cp_enable_irq(cp);
+	__cp_set_rx_mode(dev);
+	cpw16_f(IntrMask, cp_norx_intr_mask);
 
 	netif_wake_queue(dev);
+	napi_schedule_irqoff(&cp->napi);
 
 	spin_unlock_irqrestore(&cp->lock, flags);
 }
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
index b735fa22ac95..ebf6abc4853f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
@@ -161,11 +161,16 @@ int stmmac_mdio_reset(struct mii_bus *bus)
 
 		if (!gpio_request(reset_gpio, "mdio-reset")) {
 			gpio_direction_output(reset_gpio, active_low ? 1 : 0);
-			udelay(data->delays[0]);
+			if (data->delays[0])
+				msleep(DIV_ROUND_UP(data->delays[0], 1000));
+
 			gpio_set_value(reset_gpio, active_low ? 0 : 1);
-			udelay(data->delays[1]);
+			if (data->delays[1])
+				msleep(DIV_ROUND_UP(data->delays[1], 1000));
+
 			gpio_set_value(reset_gpio, active_low ? 1 : 0);
-			udelay(data->delays[2]);
+			if (data->delays[2])
+				msleep(DIV_ROUND_UP(data->delays[2], 1000));
 		}
 	}
 #endif
diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c
index 53fe200e0b79..cc106d892e29 100644
--- a/drivers/net/ethernet/sun/sunvnet.c
+++ b/drivers/net/ethernet/sun/sunvnet.c
@@ -1756,7 +1756,8 @@ static const struct net_device_ops vnet_ops = {
 #endif
 };
 
-static struct vnet *vnet_new(const u64 *local_mac)
+static struct vnet *vnet_new(const u64 *local_mac,
+			     struct vio_dev *vdev)
 {
 	struct net_device *dev;
 	struct vnet *vp;
@@ -1790,6 +1791,8 @@ static struct vnet *vnet_new(const u64 *local_mac)
 			   NETIF_F_HW_CSUM | NETIF_F_SG;
 	dev->features = dev->hw_features;
 
+	SET_NETDEV_DEV(dev, &vdev->dev);
+
 	err = register_netdev(dev);
 	if (err) {
 		pr_err("Cannot register net device, aborting\n");
@@ -1808,7 +1811,8 @@ err_out_free_dev:
 	return ERR_PTR(err);
 }
 
-static struct vnet *vnet_find_or_create(const u64 *local_mac)
+static struct vnet *vnet_find_or_create(const u64 *local_mac,
+					struct vio_dev *vdev)
 {
 	struct vnet *iter, *vp;
 
@@ -1821,7 +1825,7 @@ static struct vnet *vnet_find_or_create(const u64 *local_mac)
 		}
 	}
 	if (!vp)
-		vp = vnet_new(local_mac);
+		vp = vnet_new(local_mac, vdev);
 	mutex_unlock(&vnet_list_mutex);
 
 	return vp;
@@ -1848,7 +1852,8 @@ static void vnet_cleanup(void)
 static const char *local_mac_prop = "local-mac-address";
 
 static struct vnet *vnet_find_parent(struct mdesc_handle *hp,
-						u64 port_node)
+				     u64 port_node,
+				     struct vio_dev *vdev)
 {
 	const u64 *local_mac = NULL;
 	u64 a;
@@ -1869,7 +1874,7 @@ static struct vnet *vnet_find_parent(struct mdesc_handle *hp,
 	if (!local_mac)
 		return ERR_PTR(-ENODEV);
 
-	return vnet_find_or_create(local_mac);
+	return vnet_find_or_create(local_mac, vdev);
 }
 
 static struct ldc_channel_config vnet_ldc_cfg = {
@@ -1923,7 +1928,7 @@ static int vnet_port_probe(struct vio_dev *vdev, const struct vio_device_id *id)
 
 	hp = mdesc_grab();
 
-	vp = vnet_find_parent(hp, vdev->mp);
+	vp = vnet_find_parent(hp, vdev->mp, vdev);
 	if (IS_ERR(vp)) {
 		pr_err("Cannot find port parent vnet\n");
 		err = PTR_ERR(vp);
diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c
index 1a5aca55ea9f..9f9832f0dea9 100644
--- a/drivers/net/ethernet/ti/netcp_core.c
+++ b/drivers/net/ethernet/ti/netcp_core.c
@@ -291,13 +291,6 @@ static int netcp_module_probe(struct netcp_device *netcp_device,
 			    interface_list) {
 		struct netcp_intf_modpriv *intf_modpriv;
 
-		/* If interface not registered then register now */
-		if (!netcp_intf->netdev_registered)
-			ret = netcp_register_interface(netcp_intf);
-
-		if (ret)
-			return -ENODEV;
-
 		intf_modpriv = devm_kzalloc(dev, sizeof(*intf_modpriv),
 					    GFP_KERNEL);
 		if (!intf_modpriv)
@@ -306,6 +299,11 @@ static int netcp_module_probe(struct netcp_device *netcp_device,
 		interface = of_parse_phandle(netcp_intf->node_interface,
 					     module->name, 0);
 
+		if (!interface) {
+			devm_kfree(dev, intf_modpriv);
+			continue;
+		}
+
 		intf_modpriv->netcp_priv = netcp_intf;
 		intf_modpriv->netcp_module = module;
 		list_add_tail(&intf_modpriv->intf_list,
@@ -323,6 +321,18 @@ static int netcp_module_probe(struct netcp_device *netcp_device,
 			continue;
 		}
 	}
+
+	/* Now register the interface with netdev */
+	list_for_each_entry(netcp_intf,
+			    &netcp_device->interface_head,
+			    interface_list) {
+		/* If interface not registered then register now */
+		if (!netcp_intf->netdev_registered) {
+			ret = netcp_register_interface(netcp_intf);
+			if (ret)
+				return -ENODEV;
+		}
+	}
 	return 0;
 }
 
@@ -357,7 +367,6 @@ int netcp_register_module(struct netcp_module *module)
 		if (ret < 0)
 			goto fail;
 	}
-
 	mutex_unlock(&netcp_modules_lock);
 	return 0;
 
@@ -796,7 +805,7 @@ static void netcp_rxpool_free(struct netcp_intf *netcp)
 	netcp->rx_pool = NULL;
 }
 
-static void netcp_allocate_rx_buf(struct netcp_intf *netcp, int fdq)
+static int netcp_allocate_rx_buf(struct netcp_intf *netcp, int fdq)
 {
 	struct knav_dma_desc *hwdesc;
 	unsigned int buf_len, dma_sz;
@@ -810,7 +819,7 @@ static void netcp_allocate_rx_buf(struct netcp_intf *netcp, int fdq)
 	hwdesc = knav_pool_desc_get(netcp->rx_pool);
 	if (IS_ERR_OR_NULL(hwdesc)) {
 		dev_dbg(netcp->ndev_dev, "out of rx pool desc\n");
-		return;
+		return -ENOMEM;
 	}
 
 	if (likely(fdq == 0)) {
@@ -862,25 +871,26 @@ static void netcp_allocate_rx_buf(struct netcp_intf *netcp, int fdq)
 	knav_pool_desc_map(netcp->rx_pool, hwdesc, sizeof(*hwdesc), &dma,
 			   &dma_sz);
 	knav_queue_push(netcp->rx_fdq[fdq], dma, sizeof(*hwdesc), 0);
-	return;
+	return 0;
 
 fail:
 	knav_pool_desc_put(netcp->rx_pool, hwdesc);
+	return -ENOMEM;
 }
 
 /* Refill Rx FDQ with descriptors & attached buffers */
 static void netcp_rxpool_refill(struct netcp_intf *netcp)
 {
 	u32 fdq_deficit[KNAV_DMA_FDQ_PER_CHAN] = {0};
-	int i;
+	int i, ret = 0;
 
 	/* Calculate the FDQ deficit and refill */
 	for (i = 0; i < KNAV_DMA_FDQ_PER_CHAN && netcp->rx_fdq[i]; i++) {
 		fdq_deficit[i] = netcp->rx_queue_depths[i] -
 				 knav_queue_get_count(netcp->rx_fdq[i]);
 
-		while (fdq_deficit[i]--)
-			netcp_allocate_rx_buf(netcp, i);
+		while (fdq_deficit[i]-- && !ret)
+			ret = netcp_allocate_rx_buf(netcp, i);
 	} /* end for fdqs */
 }
 
@@ -893,12 +903,12 @@ static int netcp_rx_poll(struct napi_struct *napi, int budget)
 
 	packets = netcp_process_rx_packets(netcp, budget);
 
+	netcp_rxpool_refill(netcp);
 	if (packets < budget) {
 		napi_complete(&netcp->rx_napi);
 		knav_queue_enable_notify(netcp->rx_queue);
 	}
 
-	netcp_rxpool_refill(netcp);
 	return packets;
 }
 
@@ -1384,7 +1394,6 @@ static void netcp_addr_sweep_del(struct netcp_intf *netcp)
 			continue;
 		dev_dbg(netcp->ndev_dev, "deleting address %pM, type %x\n",
 			naddr->addr, naddr->type);
-		mutex_lock(&netcp_modules_lock);
 		for_each_module(netcp, priv) {
 			module = priv->netcp_module;
 			if (!module->del_addr)
@@ -1393,7 +1402,6 @@ static void netcp_addr_sweep_del(struct netcp_intf *netcp)
 						 naddr);
 			WARN_ON(error);
 		}
-		mutex_unlock(&netcp_modules_lock);
 		netcp_addr_del(netcp, naddr);
 	}
 }
@@ -1410,7 +1418,7 @@ static void netcp_addr_sweep_add(struct netcp_intf *netcp)
 			continue;
 		dev_dbg(netcp->ndev_dev, "adding address %pM, type %x\n",
 			naddr->addr, naddr->type);
-		mutex_lock(&netcp_modules_lock);
+
 		for_each_module(netcp, priv) {
 			module = priv->netcp_module;
 			if (!module->add_addr)
@@ -1418,7 +1426,6 @@ static void netcp_addr_sweep_add(struct netcp_intf *netcp)
 			error = module->add_addr(priv->module_priv, naddr);
 			WARN_ON(error);
 		}
-		mutex_unlock(&netcp_modules_lock);
 	}
 }
 
@@ -1432,6 +1439,7 @@ static void netcp_set_rx_mode(struct net_device *ndev)
 		   ndev->flags & IFF_ALLMULTI ||
 		   netdev_mc_count(ndev) > NETCP_MAX_MCAST_ADDR);
 
+	spin_lock(&netcp->lock);
 	/* first clear all marks */
 	netcp_addr_clear_mark(netcp);
 
@@ -1450,6 +1458,7 @@ static void netcp_set_rx_mode(struct net_device *ndev)
 	/* finally sweep and callout into modules */
 	netcp_addr_sweep_del(netcp);
 	netcp_addr_sweep_add(netcp);
+	spin_unlock(&netcp->lock);
 }
 
 static void netcp_free_navigator_resources(struct netcp_intf *netcp)
@@ -1614,7 +1623,6 @@ static int netcp_ndo_open(struct net_device *ndev)
 		goto fail;
 	}
 
-	mutex_lock(&netcp_modules_lock);
 	for_each_module(netcp, intf_modpriv) {
 		module = intf_modpriv->netcp_module;
 		if (module->open) {
@@ -1625,7 +1633,6 @@ static int netcp_ndo_open(struct net_device *ndev)
 			}
 		}
 	}
-	mutex_unlock(&netcp_modules_lock);
 
 	napi_enable(&netcp->rx_napi);
 	napi_enable(&netcp->tx_napi);
@@ -1642,7 +1649,6 @@ fail_open:
 		if (module->close)
 			module->close(intf_modpriv->module_priv, ndev);
 	}
-	mutex_unlock(&netcp_modules_lock);
 
 fail:
 	netcp_free_navigator_resources(netcp);
@@ -1666,7 +1672,6 @@ static int netcp_ndo_stop(struct net_device *ndev)
 	napi_disable(&netcp->rx_napi);
 	napi_disable(&netcp->tx_napi);
 
-	mutex_lock(&netcp_modules_lock);
 	for_each_module(netcp, intf_modpriv) {
 		module = intf_modpriv->netcp_module;
 		if (module->close) {
@@ -1675,7 +1680,6 @@ static int netcp_ndo_stop(struct net_device *ndev)
 				dev_err(netcp->ndev_dev, "Close failed\n");
 		}
 	}
-	mutex_unlock(&netcp_modules_lock);
 
 	/* Recycle Rx descriptors from completion queue */
 	netcp_empty_rx_queue(netcp);
@@ -1703,7 +1707,6 @@ static int netcp_ndo_ioctl(struct net_device *ndev,
 	if (!netif_running(ndev))
 		return -EINVAL;
 
-	mutex_lock(&netcp_modules_lock);
 	for_each_module(netcp, intf_modpriv) {
 		module = intf_modpriv->netcp_module;
 		if (!module->ioctl)
@@ -1719,7 +1722,6 @@ static int netcp_ndo_ioctl(struct net_device *ndev,
 	}
 
 out:
-	mutex_unlock(&netcp_modules_lock);
 	return (ret == 0) ? 0 : err;
 }
 
@@ -1754,11 +1756,12 @@ static int netcp_rx_add_vid(struct net_device *ndev, __be16 proto, u16 vid)
 	struct netcp_intf *netcp = netdev_priv(ndev);
 	struct netcp_intf_modpriv *intf_modpriv;
 	struct netcp_module *module;
+	unsigned long flags;
 	int err = 0;
 
 	dev_dbg(netcp->ndev_dev, "adding rx vlan id: %d\n", vid);
 
-	mutex_lock(&netcp_modules_lock);
+	spin_lock_irqsave(&netcp->lock, flags);
 	for_each_module(netcp, intf_modpriv) {
 		module = intf_modpriv->netcp_module;
 		if ((module->add_vid) && (vid != 0)) {
@@ -1770,7 +1773,8 @@ static int netcp_rx_add_vid(struct net_device *ndev, __be16 proto, u16 vid)
 			}
 		}
 	}
-	mutex_unlock(&netcp_modules_lock);
+	spin_unlock_irqrestore(&netcp->lock, flags);
+
 	return err;
 }
 
@@ -1779,11 +1783,12 @@ static int netcp_rx_kill_vid(struct net_device *ndev, __be16 proto, u16 vid)
 	struct netcp_intf *netcp = netdev_priv(ndev);
 	struct netcp_intf_modpriv *intf_modpriv;
 	struct netcp_module *module;
+	unsigned long flags;
 	int err = 0;
 
 	dev_dbg(netcp->ndev_dev, "removing rx vlan id: %d\n", vid);
 
-	mutex_lock(&netcp_modules_lock);
+	spin_lock_irqsave(&netcp->lock, flags);
 	for_each_module(netcp, intf_modpriv) {
 		module = intf_modpriv->netcp_module;
 		if (module->del_vid) {
@@ -1795,7 +1800,7 @@ static int netcp_rx_kill_vid(struct net_device *ndev, __be16 proto, u16 vid)
 			}
 		}
 	}
-	mutex_unlock(&netcp_modules_lock);
+	spin_unlock_irqrestore(&netcp->lock, flags);
 	return err;
 }
 
@@ -2040,7 +2045,6 @@ static int netcp_probe(struct platform_device *pdev)
 	struct device_node *child, *interfaces;
 	struct netcp_device *netcp_device;
 	struct device *dev = &pdev->dev;
-	struct netcp_module *module;
 	int ret;
 
 	if (!node) {
@@ -2087,14 +2091,6 @@ static int netcp_probe(struct platform_device *pdev)
 	/* Add the device instance to the list */
 	list_add_tail(&netcp_device->device_list, &netcp_devices);
 
-	/* Probe & attach any modules already registered */
-	mutex_lock(&netcp_modules_lock);
-	for_each_netcp_module(module) {
-		ret = netcp_module_probe(netcp_device, module);
-		if (ret < 0)
-			dev_err(dev, "module(%s) probe failed\n", module->name);
-	}
-	mutex_unlock(&netcp_modules_lock);
 	return 0;
 
 probe_quit_interface:
diff --git a/drivers/net/ethernet/ti/netcp_ethss.c b/drivers/net/ethernet/ti/netcp_ethss.c
index 6f16d6aaf7b7..6bff8d82ceab 100644
--- a/drivers/net/ethernet/ti/netcp_ethss.c
+++ b/drivers/net/ethernet/ti/netcp_ethss.c
@@ -77,6 +77,7 @@
 #define GBENU_ALE_OFFSET		0x1e000
 #define GBENU_HOST_PORT_NUM		0
 #define GBENU_NUM_ALE_ENTRIES		1024
+#define GBENU_SGMII_MODULE_SIZE		0x100
 
 /* 10G Ethernet SS defines */
 #define XGBE_MODULE_NAME		"netcp-xgbe"
@@ -149,8 +150,8 @@
 #define XGBE_STATS2_MODULE			2
 
 /* s: 0-based slave_port */
-#define SGMII_BASE(s) \
-	(((s) < 2) ? gbe_dev->sgmii_port_regs : gbe_dev->sgmii_port34_regs)
+#define SGMII_BASE(d, s) \
+	(((s) < 2) ? (d)->sgmii_port_regs : (d)->sgmii_port34_regs)
 
 #define GBE_TX_QUEUE				648
 #define	GBE_TXHOOK_ORDER			0
@@ -1997,13 +1998,8 @@ static void netcp_ethss_update_link_state(struct gbe_priv *gbe_dev,
 		return;
 
 	if (!SLAVE_LINK_IS_XGMII(slave)) {
-		if (gbe_dev->ss_version == GBE_SS_VERSION_14)
-			sgmii_link_state =
-				netcp_sgmii_get_port_link(SGMII_BASE(sp), sp);
-		else
-			sgmii_link_state =
-				netcp_sgmii_get_port_link(
-						gbe_dev->sgmii_port_regs, sp);
+		sgmii_link_state =
+			netcp_sgmii_get_port_link(SGMII_BASE(gbe_dev, sp), sp);
 	}
 
 	phy_link_state = gbe_phy_link_status(slave);
@@ -2100,17 +2096,11 @@ static void gbe_port_config(struct gbe_priv *gbe_dev, struct gbe_slave *slave,
 static void gbe_sgmii_rtreset(struct gbe_priv *priv,
 			      struct gbe_slave *slave, bool set)
 {
-	void __iomem *sgmii_port_regs;
-
 	if (SLAVE_LINK_IS_XGMII(slave))
 		return;
 
-	if ((priv->ss_version == GBE_SS_VERSION_14) && (slave->slave_num >= 2))
-		sgmii_port_regs = priv->sgmii_port34_regs;
-	else
-		sgmii_port_regs = priv->sgmii_port_regs;
-
-	netcp_sgmii_rtreset(sgmii_port_regs, slave->slave_num, set);
+	netcp_sgmii_rtreset(SGMII_BASE(priv, slave->slave_num),
+			    slave->slave_num, set);
 }
 
 static void gbe_slave_stop(struct gbe_intf *intf)
@@ -2136,17 +2126,12 @@ static void gbe_slave_stop(struct gbe_intf *intf)
 
 static void gbe_sgmii_config(struct gbe_priv *priv, struct gbe_slave *slave)
 {
-	void __iomem *sgmii_port_regs;
-
-	sgmii_port_regs = priv->sgmii_port_regs;
-	if ((priv->ss_version == GBE_SS_VERSION_14) && (slave->slave_num >= 2))
-		sgmii_port_regs = priv->sgmii_port34_regs;
+	if (SLAVE_LINK_IS_XGMII(slave))
+		return;
 
-	if (!SLAVE_LINK_IS_XGMII(slave)) {
-		netcp_sgmii_reset(sgmii_port_regs, slave->slave_num);
-		netcp_sgmii_config(sgmii_port_regs, slave->slave_num,
-				   slave->link_interface);
-	}
+	netcp_sgmii_reset(SGMII_BASE(priv, slave->slave_num), slave->slave_num);
+	netcp_sgmii_config(SGMII_BASE(priv, slave->slave_num), slave->slave_num,
+			   slave->link_interface);
 }
 
 static int gbe_slave_open(struct gbe_intf *gbe_intf)
@@ -2997,6 +2982,14 @@ static int set_gbenu_ethss_priv(struct gbe_priv *gbe_dev,
 	gbe_dev->switch_regs = regs;
 
 	gbe_dev->sgmii_port_regs = gbe_dev->ss_regs + GBENU_SGMII_MODULE_OFFSET;
+
+	/* Although sgmii modules are mem mapped to one contiguous
+	 * region on GBENU devices, setting sgmii_port34_regs allows
+	 * consistent code when accessing sgmii api
+	 */
+	gbe_dev->sgmii_port34_regs = gbe_dev->sgmii_port_regs +
+				     (2 * GBENU_SGMII_MODULE_SIZE);
+
 	gbe_dev->host_port_regs = gbe_dev->switch_regs + GBENU_HOST_PORT_OFFSET;
 
 	for (i = 0; i < (gbe_dev->max_num_ports); i++)
diff --git a/drivers/net/ethernet/via/Kconfig b/drivers/net/ethernet/via/Kconfig
index 2f1264b882b9..d3d094742a7e 100644
--- a/drivers/net/ethernet/via/Kconfig
+++ b/drivers/net/ethernet/via/Kconfig
@@ -17,7 +17,7 @@ if NET_VENDOR_VIA
 
 config VIA_RHINE
 	tristate "VIA Rhine support"
-	depends on (PCI || OF_IRQ)
+	depends on PCI || (OF_IRQ && GENERIC_PCI_IOMAP)
 	depends on HAS_DMA
 	select CRC32
 	select MII
diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
index 6008eee01a33..cf468c87ce57 100644
--- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c
+++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
@@ -828,6 +828,8 @@ static int xemaclite_mdio_setup(struct net_local *lp, struct device *dev)
 		if (!phydev)
 			dev_info(dev,
 				 "MDIO of the phy is not registered yet\n");
+		else
+			put_device(&phydev->dev);
 		return 0;
 	}
 
diff --git a/drivers/net/fjes/fjes_hw.c b/drivers/net/fjes/fjes_hw.c
index b5f4a78da828..2d3848c9dc35 100644
--- a/drivers/net/fjes/fjes_hw.c
+++ b/drivers/net/fjes/fjes_hw.c
@@ -1011,11 +1011,11 @@ static void fjes_hw_update_zone_task(struct work_struct *work)
 					set_bit(epidx, &irq_bit);
 				break;
 			}
-		}
-
-		hw->ep_shm_info[epidx].es_status = info[epidx].es_status;
-		hw->ep_shm_info[epidx].zone = info[epidx].zone;
 
+			hw->ep_shm_info[epidx].es_status =
+				info[epidx].es_status;
+			hw->ep_shm_info[epidx].zone = info[epidx].zone;
+		}
 		break;
 	}
 
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index da3259ce7c8d..8f5c02eed47d 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -126,6 +126,8 @@ static void geneve_rx(struct geneve_sock *gs, struct sk_buff *skb)
 	__be32 addr;
 	int err;
 
+	iph = ip_hdr(skb); /* outer IP header... */
+
 	if (gs->collect_md) {
 		static u8 zero_vni[3];
 
@@ -133,7 +135,6 @@ static void geneve_rx(struct geneve_sock *gs, struct sk_buff *skb)
 		addr = 0;
 	} else {
 		vni = gnvh->vni;
-		iph = ip_hdr(skb); /* Still outer IP header... */
 		addr = iph->saddr;
 	}
 
@@ -178,7 +179,6 @@ static void geneve_rx(struct geneve_sock *gs, struct sk_buff *skb)
 
 	skb_reset_network_header(skb);
 
-	iph = ip_hdr(skb); /* Now inner IP header... */
 	err = IP_ECN_decapsulate(iph, skb);
 
 	if (unlikely(err)) {
@@ -626,6 +626,7 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct geneve_sock *gs = geneve->sock;
 	struct ip_tunnel_info *info = NULL;
 	struct rtable *rt = NULL;
+	const struct iphdr *iip; /* interior IP header */
 	struct flowi4 fl4;
 	__u8 tos, ttl;
 	__be16 sport;
@@ -653,6 +654,8 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev)
 	sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true);
 	skb_reset_mac_header(skb);
 
+	iip = ip_hdr(skb);
+
 	if (info) {
 		const struct ip_tunnel_key *key = &info->key;
 		u8 *opts = NULL;
@@ -668,19 +671,16 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev)
 		if (unlikely(err))
 			goto err;
 
-		tos = key->tos;
+		tos = ip_tunnel_ecn_encap(key->tos, iip, skb);
 		ttl = key->ttl;
 		df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0;
 	} else {
-		const struct iphdr *iip; /* interior IP header */
-
 		udp_csum = false;
 		err = geneve_build_skb(rt, skb, 0, geneve->vni,
 				       0, NULL, udp_csum);
 		if (unlikely(err))
 			goto err;
 
-		iip = ip_hdr(skb);
 		tos = ip_tunnel_ecn_encap(fl4.flowi4_tos, iip, skb);
 		ttl = geneve->ttl;
 		if (!ttl && IN_MULTICAST(ntohl(fl4.daddr)))
@@ -748,12 +748,8 @@ static void geneve_setup(struct net_device *dev)
 	dev->features    |= NETIF_F_RXCSUM;
 	dev->features    |= NETIF_F_GSO_SOFTWARE;
 
-	dev->vlan_features = dev->features;
-	dev->features    |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX;
-
 	dev->hw_features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_RXCSUM;
 	dev->hw_features |= NETIF_F_GSO_SOFTWARE;
-	dev->hw_features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX;
 
 	netif_keep_dst(dev);
 	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_NO_QUEUE;
@@ -819,7 +815,7 @@ static struct geneve_dev *geneve_find_dev(struct geneve_net *gn,
 
 static int geneve_configure(struct net *net, struct net_device *dev,
 			    __be32 rem_addr, __u32 vni, __u8 ttl, __u8 tos,
-			    __u16 dst_port, bool metadata)
+			    __be16 dst_port, bool metadata)
 {
 	struct geneve_net *gn = net_generic(net, geneve_net_id);
 	struct geneve_dev *t, *geneve = netdev_priv(dev);
@@ -844,10 +840,10 @@ static int geneve_configure(struct net *net, struct net_device *dev,
 
 	geneve->ttl = ttl;
 	geneve->tos = tos;
-	geneve->dst_port = htons(dst_port);
+	geneve->dst_port = dst_port;
 	geneve->collect_md = metadata;
 
-	t = geneve_find_dev(gn, htons(dst_port), rem_addr, geneve->vni,
+	t = geneve_find_dev(gn, dst_port, rem_addr, geneve->vni,
 			    &tun_on_same_port, &tun_collect_md);
 	if (t)
 		return -EBUSY;
@@ -871,7 +867,7 @@ static int geneve_configure(struct net *net, struct net_device *dev,
 static int geneve_newlink(struct net *net, struct net_device *dev,
 			  struct nlattr *tb[], struct nlattr *data[])
 {
-	__u16 dst_port = GENEVE_UDP_PORT;
+	__be16 dst_port = htons(GENEVE_UDP_PORT);
 	__u8 ttl = 0, tos = 0;
 	bool metadata = false;
 	__be32 rem_addr;
@@ -890,7 +886,7 @@ static int geneve_newlink(struct net *net, struct net_device *dev,
 		tos = nla_get_u8(data[IFLA_GENEVE_TOS]);
 
 	if (data[IFLA_GENEVE_PORT])
-		dst_port = nla_get_u16(data[IFLA_GENEVE_PORT]);
+		dst_port = nla_get_be16(data[IFLA_GENEVE_PORT]);
 
 	if (data[IFLA_GENEVE_COLLECT_METADATA])
 		metadata = true;
@@ -913,7 +909,7 @@ static size_t geneve_get_size(const struct net_device *dev)
 		nla_total_size(sizeof(struct in_addr)) + /* IFLA_GENEVE_REMOTE */
 		nla_total_size(sizeof(__u8)) +  /* IFLA_GENEVE_TTL */
 		nla_total_size(sizeof(__u8)) +  /* IFLA_GENEVE_TOS */
-		nla_total_size(sizeof(__u16)) +  /* IFLA_GENEVE_PORT */
+		nla_total_size(sizeof(__be16)) +  /* IFLA_GENEVE_PORT */
 		nla_total_size(0) +	 /* IFLA_GENEVE_COLLECT_METADATA */
 		0;
 }
@@ -935,7 +931,7 @@ static int geneve_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	    nla_put_u8(skb, IFLA_GENEVE_TOS, geneve->tos))
 		goto nla_put_failure;
 
-	if (nla_put_u16(skb, IFLA_GENEVE_PORT, ntohs(geneve->dst_port)))
+	if (nla_put_be16(skb, IFLA_GENEVE_PORT, geneve->dst_port))
 		goto nla_put_failure;
 
 	if (geneve->collect_md) {
@@ -975,7 +971,7 @@ struct net_device *geneve_dev_create_fb(struct net *net, const char *name,
 	if (IS_ERR(dev))
 		return dev;
 
-	err = geneve_configure(net, dev, 0, 0, 0, 0, dst_port, true);
+	err = geneve_configure(net, dev, 0, 0, 0, 0, htons(dst_port), true);
 	if (err) {
 		free_netdev(dev);
 		return ERR_PTR(err);
diff --git a/drivers/net/irda/ali-ircc.c b/drivers/net/irda/ali-ircc.c
index 58ae11a14bb6..64bb44d5d867 100644
--- a/drivers/net/irda/ali-ircc.c
+++ b/drivers/net/irda/ali-ircc.c
@@ -1031,7 +1031,6 @@ static void ali_ircc_fir_change_speed(struct ali_ircc_cb *priv, __u32 baud)
 static void ali_ircc_sir_change_speed(struct ali_ircc_cb *priv, __u32 speed)
 {
 	struct ali_ircc_cb *self = priv;
-	unsigned long flags;
 	int iobase; 
 	int fcr;    /* FIFO control reg */
 	int lcr;    /* Line control reg */
@@ -1061,8 +1060,6 @@ static void ali_ircc_sir_change_speed(struct ali_ircc_cb *priv, __u32 speed)
 	/* Update accounting for new speed */
 	self->io.speed = speed;
 
-	spin_lock_irqsave(&self->lock, flags);
-
 	divisor = 115200/speed;
 	
 	fcr = UART_FCR_ENABLE_FIFO;
@@ -1089,9 +1086,6 @@ static void ali_ircc_sir_change_speed(struct ali_ircc_cb *priv, __u32 speed)
 	/* without this, the connection will be broken after come back from FIR speed,
 	   but with this, the SIR connection is harder to established */
 	outb((UART_MCR_DTR | UART_MCR_RTS | UART_MCR_OUT2), iobase+UART_MCR);
-	
-	spin_unlock_irqrestore(&self->lock, flags);
-	
 }
 
 static void ali_ircc_change_dongle_speed(struct ali_ircc_cb *priv, int speed)
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index edd77342773a..248478c6f6e4 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -1111,10 +1111,10 @@ static long macvtap_ioctl(struct file *file, unsigned int cmd,
 		return 0;
 
 	case TUNSETSNDBUF:
-		if (get_user(u, up))
+		if (get_user(s, sp))
 			return -EFAULT;
 
-		q->sk.sk_sndbuf = u;
+		q->sk.sk_sndbuf = s;
 		return 0;
 
 	case TUNGETVNETHDRSZ:
diff --git a/drivers/net/phy/fixed_phy.c b/drivers/net/phy/fixed_phy.c
index fb1299c6326e..e23bf5b90e17 100644
--- a/drivers/net/phy/fixed_phy.c
+++ b/drivers/net/phy/fixed_phy.c
@@ -220,7 +220,7 @@ int fixed_phy_update_state(struct phy_device *phydev,
 	struct fixed_mdio_bus *fmb = &platform_fmb;
 	struct fixed_phy *fp;
 
-	if (!phydev || !phydev->bus)
+	if (!phydev || phydev->bus != fmb->mii_bus)
 		return -EINVAL;
 
 	list_for_each_entry(fp, &fmb->phys, node) {
diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index e6897b6a8a53..5de8d5827536 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -785,6 +785,7 @@ static int marvell_read_status(struct phy_device *phydev)
 	int adv;
 	int err;
 	int lpa;
+	int lpagb;
 	int status = 0;
 
 	/* Update the link, but return if there
@@ -802,10 +803,17 @@ static int marvell_read_status(struct phy_device *phydev)
 		if (lpa < 0)
 			return lpa;
 
+		lpagb = phy_read(phydev, MII_STAT1000);
+		if (lpagb < 0)
+			return lpagb;
+
 		adv = phy_read(phydev, MII_ADVERTISE);
 		if (adv < 0)
 			return adv;
 
+		phydev->lp_advertising = mii_stat1000_to_ethtool_lpa_t(lpagb) |
+					 mii_lpa_to_ethtool_lpa_t(lpa);
+
 		lpa &= adv;
 
 		if (status & MII_M1011_PHY_STATUS_FULLDUPLEX)
@@ -853,6 +861,7 @@ static int marvell_read_status(struct phy_device *phydev)
 			phydev->speed = SPEED_10;
 
 		phydev->pause = phydev->asym_pause = 0;
+		phydev->lp_advertising = 0;
 	}
 
 	return 0;
diff --git a/drivers/net/phy/mdio-bcm-unimac.c b/drivers/net/phy/mdio-bcm-unimac.c
index 6a52a7f0fa0d..4bde5e728fe0 100644
--- a/drivers/net/phy/mdio-bcm-unimac.c
+++ b/drivers/net/phy/mdio-bcm-unimac.c
@@ -244,6 +244,7 @@ static const struct of_device_id unimac_mdio_ids[] = {
 	{ .compatible = "brcm,unimac-mdio", },
 	{ /* sentinel */ },
 };
+MODULE_DEVICE_TABLE(of, unimac_mdio_ids);
 
 static struct platform_driver unimac_mdio_driver = {
 	.driver = {
diff --git a/drivers/net/phy/mdio-gpio.c b/drivers/net/phy/mdio-gpio.c
index 7dc21e56a7aa..3bc9f03349f3 100644
--- a/drivers/net/phy/mdio-gpio.c
+++ b/drivers/net/phy/mdio-gpio.c
@@ -261,6 +261,7 @@ static const struct of_device_id mdio_gpio_of_match[] = {
 	{ .compatible = "virtual,mdio-gpio", },
 	{ /* sentinel */ }
 };
+MODULE_DEVICE_TABLE(of, mdio_gpio_of_match);
 
 static struct platform_driver mdio_gpio_driver = {
 	.probe = mdio_gpio_probe,
diff --git a/drivers/net/phy/mdio-mux.c b/drivers/net/phy/mdio-mux.c
index 4d4d25efc1e1..280c7c311f72 100644
--- a/drivers/net/phy/mdio-mux.c
+++ b/drivers/net/phy/mdio-mux.c
@@ -113,18 +113,18 @@ int mdio_mux_init(struct device *dev,
 	if (!parent_bus_node)
 		return -ENODEV;
 
-	parent_bus = of_mdio_find_bus(parent_bus_node);
-	if (parent_bus == NULL) {
-		ret_val = -EPROBE_DEFER;
-		goto err_parent_bus;
-	}
-
 	pb = devm_kzalloc(dev, sizeof(*pb), GFP_KERNEL);
 	if (pb == NULL) {
 		ret_val = -ENOMEM;
 		goto err_parent_bus;
 	}
 
+	parent_bus = of_mdio_find_bus(parent_bus_node);
+	if (parent_bus == NULL) {
+		ret_val = -EPROBE_DEFER;
+		goto err_parent_bus;
+	}
+
 	pb->switch_data = data;
 	pb->switch_fn = switch_fn;
 	pb->current_child = -1;
@@ -173,6 +173,10 @@ int mdio_mux_init(struct device *dev,
 		dev_info(dev, "Version " DRV_VERSION "\n");
 		return 0;
 	}
+
+	/* balance the reference of_mdio_find_bus() took */
+	put_device(&pb->mii_bus->dev);
+
 err_parent_bus:
 	of_node_put(parent_bus_node);
 	return ret_val;
@@ -189,6 +193,9 @@ void mdio_mux_uninit(void *mux_handle)
 		mdiobus_free(cb->mii_bus);
 		cb = cb->next;
 	}
+
+	/* balance the reference of_mdio_find_bus() in mdio_mux_init() took */
+	put_device(&pb->mii_bus->dev);
 }
 EXPORT_SYMBOL_GPL(mdio_mux_uninit);
 
diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c
index 02a4615b65f8..12f44c53cc8e 100644
--- a/drivers/net/phy/mdio_bus.c
+++ b/drivers/net/phy/mdio_bus.c
@@ -167,7 +167,9 @@ static int of_mdio_bus_match(struct device *dev, const void *mdio_bus_np)
  * of_mdio_find_bus - Given an mii_bus node, find the mii_bus.
  * @mdio_bus_np: Pointer to the mii_bus.
  *
- * Returns a pointer to the mii_bus, or NULL if none found.
+ * Returns a reference to the mii_bus, or NULL if none found.  The
+ * embedded struct device will have its reference count incremented,
+ * and this must be put once the bus is finished with.
  *
  * Because the association of a device_node and mii_bus is made via
  * of_mdiobus_register(), the mii_bus cannot be found before it is
@@ -234,15 +236,18 @@ static inline void of_mdiobus_link_phydev(struct mii_bus *mdio,
 #endif
 
 /**
- * mdiobus_register - bring up all the PHYs on a given bus and attach them to bus
+ * __mdiobus_register - bring up all the PHYs on a given bus and attach them to bus
  * @bus: target mii_bus
+ * @owner: module containing bus accessor functions
  *
  * Description: Called by a bus driver to bring up all the PHYs
- *   on a given bus, and attach them to the bus.
+ *   on a given bus, and attach them to the bus. Drivers should use
+ *   mdiobus_register() rather than __mdiobus_register() unless they
+ *   need to pass a specific owner module.
  *
  * Returns 0 on success or < 0 on error.
  */
-int mdiobus_register(struct mii_bus *bus)
+int __mdiobus_register(struct mii_bus *bus, struct module *owner)
 {
 	int i, err;
 
@@ -253,6 +258,7 @@ int mdiobus_register(struct mii_bus *bus)
 	BUG_ON(bus->state != MDIOBUS_ALLOCATED &&
 	       bus->state != MDIOBUS_UNREGISTERED);
 
+	bus->owner = owner;
 	bus->dev.parent = bus->parent;
 	bus->dev.class = &mdio_bus_class;
 	bus->dev.groups = NULL;
@@ -288,13 +294,16 @@ int mdiobus_register(struct mii_bus *bus)
 
 error:
 	while (--i >= 0) {
-		if (bus->phy_map[i])
-			device_unregister(&bus->phy_map[i]->dev);
+		struct phy_device *phydev = bus->phy_map[i];
+		if (phydev) {
+			phy_device_remove(phydev);
+			phy_device_free(phydev);
+		}
 	}
 	device_del(&bus->dev);
 	return err;
 }
-EXPORT_SYMBOL(mdiobus_register);
+EXPORT_SYMBOL(__mdiobus_register);
 
 void mdiobus_unregister(struct mii_bus *bus)
 {
@@ -304,9 +313,11 @@ void mdiobus_unregister(struct mii_bus *bus)
 	bus->state = MDIOBUS_UNREGISTERED;
 
 	for (i = 0; i < PHY_MAX_ADDR; i++) {
-		if (bus->phy_map[i])
-			device_unregister(&bus->phy_map[i]->dev);
-		bus->phy_map[i] = NULL;
+		struct phy_device *phydev = bus->phy_map[i];
+		if (phydev) {
+			phy_device_remove(phydev);
+			phy_device_free(phydev);
+		}
 	}
 	device_del(&bus->dev);
 }
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index c0f211127274..f761288abe66 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -384,6 +384,24 @@ int phy_device_register(struct phy_device *phydev)
 EXPORT_SYMBOL(phy_device_register);
 
 /**
+ * phy_device_remove - Remove a previously registered phy device from the MDIO bus
+ * @phydev: phy_device structure to remove
+ *
+ * This doesn't free the phy_device itself, it merely reverses the effects
+ * of phy_device_register(). Use phy_device_free() to free the device
+ * after calling this function.
+ */
+void phy_device_remove(struct phy_device *phydev)
+{
+	struct mii_bus *bus = phydev->bus;
+	int addr = phydev->addr;
+
+	device_del(&phydev->dev);
+	bus->phy_map[addr] = NULL;
+}
+EXPORT_SYMBOL(phy_device_remove);
+
+/**
  * phy_find_first - finds the first PHY device on the bus
  * @bus: the target MII bus
  */
@@ -578,14 +596,22 @@ EXPORT_SYMBOL(phy_init_hw);
  *     generic driver is used.  The phy_device is given a ptr to
  *     the attaching device, and given a callback for link status
  *     change.  The phy_device is returned to the attaching driver.
+ *     This function takes a reference on the phy device.
  */
 int phy_attach_direct(struct net_device *dev, struct phy_device *phydev,
 		      u32 flags, phy_interface_t interface)
 {
+	struct mii_bus *bus = phydev->bus;
 	struct device *d = &phydev->dev;
-	struct module *bus_module;
 	int err;
 
+	if (!try_module_get(bus->owner)) {
+		dev_err(&dev->dev, "failed to get the bus module\n");
+		return -EIO;
+	}
+
+	get_device(d);
+
 	/* Assume that if there is no driver, that it doesn't
 	 * exist, and we should use the genphy driver.
 	 */
@@ -600,20 +626,13 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev,
 			err = device_bind_driver(d);
 
 		if (err)
-			return err;
+			goto error;
 	}
 
 	if (phydev->attached_dev) {
 		dev_err(&dev->dev, "PHY already attached\n");
-		return -EBUSY;
-	}
-
-	/* Increment the bus module reference count */
-	bus_module = phydev->bus->dev.driver ?
-		     phydev->bus->dev.driver->owner : NULL;
-	if (!try_module_get(bus_module)) {
-		dev_err(&dev->dev, "failed to get the bus module\n");
-		return -EIO;
+		err = -EBUSY;
+		goto error;
 	}
 
 	phydev->attached_dev = dev;
@@ -636,6 +655,11 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev,
 		phy_resume(phydev);
 
 	return err;
+
+error:
+	put_device(d);
+	module_put(bus->owner);
+	return err;
 }
 EXPORT_SYMBOL(phy_attach_direct);
 
@@ -677,14 +701,15 @@ EXPORT_SYMBOL(phy_attach);
 /**
  * phy_detach - detach a PHY device from its network device
  * @phydev: target phy_device struct
+ *
+ * This detaches the phy device from its network device and the phy
+ * driver, and drops the reference count taken in phy_attach_direct().
  */
 void phy_detach(struct phy_device *phydev)
 {
+	struct mii_bus *bus;
 	int i;
 
-	if (phydev->bus->dev.driver)
-		module_put(phydev->bus->dev.driver->owner);
-
 	phydev->attached_dev->phydev = NULL;
 	phydev->attached_dev = NULL;
 	phy_suspend(phydev);
@@ -700,6 +725,15 @@ void phy_detach(struct phy_device *phydev)
 			break;
 		}
 	}
+
+	/*
+	 * The phydev might go away on the put_device() below, so avoid
+	 * a use-after-free bug by reading the underlying bus first.
+	 */
+	bus = phydev->bus;
+
+	put_device(&phydev->dev);
+	module_put(bus->owner);
 }
 EXPORT_SYMBOL(phy_detach);
 
diff --git a/drivers/net/phy/vitesse.c b/drivers/net/phy/vitesse.c
index 17cad185169d..76cad712ddb2 100644
--- a/drivers/net/phy/vitesse.c
+++ b/drivers/net/phy/vitesse.c
@@ -66,7 +66,6 @@
 #define PHY_ID_VSC8244			0x000fc6c0
 #define PHY_ID_VSC8514			0x00070670
 #define PHY_ID_VSC8574			0x000704a0
-#define PHY_ID_VSC8641			0x00070431
 #define PHY_ID_VSC8662			0x00070660
 #define PHY_ID_VSC8221			0x000fc550
 #define PHY_ID_VSC8211			0x000fc4b0
@@ -273,18 +272,6 @@ static struct phy_driver vsc82xx_driver[] = {
 	.config_intr    = &vsc82xx_config_intr,
 	.driver         = { .owner = THIS_MODULE,},
 }, {
-	.phy_id         = PHY_ID_VSC8641,
-	.name           = "Vitesse VSC8641",
-	.phy_id_mask    = 0x000ffff0,
-	.features       = PHY_GBIT_FEATURES,
-	.flags          = PHY_HAS_INTERRUPT,
-	.config_init    = &vsc824x_config_init,
-	.config_aneg    = &vsc82x4_config_aneg,
-	.read_status    = &genphy_read_status,
-	.ack_interrupt  = &vsc824x_ack_interrupt,
-	.config_intr    = &vsc82xx_config_intr,
-	.driver         = { .owner = THIS_MODULE,},
-}, {
 	.phy_id         = PHY_ID_VSC8662,
 	.name           = "Vitesse VSC8662",
 	.phy_id_mask    = 0x000ffff0,
@@ -331,7 +318,6 @@ static struct mdio_device_id __maybe_unused vitesse_tbl[] = {
 	{ PHY_ID_VSC8244, 0x000fffc0 },
 	{ PHY_ID_VSC8514, 0x000ffff0 },
 	{ PHY_ID_VSC8574, 0x000ffff0 },
-	{ PHY_ID_VSC8641, 0x000ffff0 },
 	{ PHY_ID_VSC8662, 0x000ffff0 },
 	{ PHY_ID_VSC8221, 0x000ffff0 },
 	{ PHY_ID_VSC8211, 0x000ffff0 },
diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index 0481daf9201a..ed00446759b2 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -2755,6 +2755,7 @@ static struct ppp *ppp_create_interface(struct net *net, int unit,
 	 */
 	dev_net_set(dev, net);
 
+	rtnl_lock();
 	mutex_lock(&pn->all_ppp_mutex);
 
 	if (unit < 0) {
@@ -2785,7 +2786,7 @@ static struct ppp *ppp_create_interface(struct net *net, int unit,
 	ppp->file.index = unit;
 	sprintf(dev->name, "ppp%d", unit);
 
-	ret = register_netdev(dev);
+	ret = register_netdevice(dev);
 	if (ret != 0) {
 		unit_put(&pn->units_idr, unit);
 		netdev_err(ppp->dev, "PPP: couldn't register device %s (%d)\n",
@@ -2797,6 +2798,7 @@ static struct ppp *ppp_create_interface(struct net *net, int unit,
 
 	atomic_inc(&ppp_unit_count);
 	mutex_unlock(&pn->all_ppp_mutex);
+	rtnl_unlock();
 
 	*retp = 0;
 	return ppp;
diff --git a/drivers/net/usb/Kconfig b/drivers/net/usb/Kconfig
index 1610b79ae386..fbb9325d1f6e 100644
--- a/drivers/net/usb/Kconfig
+++ b/drivers/net/usb/Kconfig
@@ -583,4 +583,15 @@ config USB_VL600
 
 	  http://ubuntuforums.org/showpost.php?p=10589647&postcount=17
 
+config USB_NET_CH9200
+	tristate "QingHeng CH9200 USB ethernet support"
+	depends on USB_USBNET
+	select MII
+	help
+	  Choose this option if you have a USB ethernet adapter with a QinHeng
+	  CH9200 chipset.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called ch9200.
+
 endif # USB_NET_DRIVERS
diff --git a/drivers/net/usb/Makefile b/drivers/net/usb/Makefile
index cf6a0e610a7f..b5f04068dbe4 100644
--- a/drivers/net/usb/Makefile
+++ b/drivers/net/usb/Makefile
@@ -38,4 +38,4 @@ obj-$(CONFIG_USB_NET_HUAWEI_CDC_NCM)	+= huawei_cdc_ncm.o
 obj-$(CONFIG_USB_VL600)		+= lg-vl600.o
 obj-$(CONFIG_USB_NET_QMI_WWAN)	+= qmi_wwan.o
 obj-$(CONFIG_USB_NET_CDC_MBIM)	+= cdc_mbim.o
-
+obj-$(CONFIG_USB_NET_CH9200)	+= ch9200.o
diff --git a/drivers/net/usb/ch9200.c b/drivers/net/usb/ch9200.c
new file mode 100644
index 000000000000..5e151e6a3e09
--- /dev/null
+++ b/drivers/net/usb/ch9200.c
@@ -0,0 +1,432 @@
+/*
+ * USB 10M/100M ethernet adapter
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2. This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/stddef.h>
+#include <linux/init.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/ethtool.h>
+#include <linux/mii.h>
+#include <linux/usb.h>
+#include <linux/crc32.h>
+#include <linux/usb/usbnet.h>
+#include <linux/slab.h>
+
+#define CH9200_VID		0x1A86
+#define CH9200_PID_E092		0xE092
+
+#define CTRL_TIMEOUT_MS		1000
+
+#define CONTROL_TIMEOUT_MS 1000
+
+#define REQUEST_READ	0x0E
+#define REQUEST_WRITE	0x0F
+
+/* Address space:
+ * 00-63 : MII
+ * 64-128: MAC
+ *
+ * Note: all accesses must be 16-bit
+ */
+
+#define MAC_REG_CTRL 64
+#define MAC_REG_STATUS 66
+#define MAC_REG_INTERRUPT_MASK 68
+#define MAC_REG_PHY_COMMAND 70
+#define MAC_REG_PHY_DATA 72
+#define MAC_REG_STATION_L 74
+#define MAC_REG_STATION_M 76
+#define MAC_REG_STATION_H 78
+#define MAC_REG_HASH_L 80
+#define MAC_REG_HASH_M1 82
+#define MAC_REG_HASH_M2 84
+#define MAC_REG_HASH_H 86
+#define MAC_REG_THRESHOLD 88
+#define MAC_REG_FIFO_DEPTH 90
+#define MAC_REG_PAUSE 92
+#define MAC_REG_FLOW_CONTROL 94
+
+/* Control register bits
+ *
+ * Note: bits 13 and 15 are reserved
+ */
+#define LOOPBACK		(0x01 << 14)
+#define BASE100X		(0x01 << 12)
+#define MBPS_10			(0x01 << 11)
+#define DUPLEX_MODE		(0x01 << 10)
+#define PAUSE_FRAME		(0x01 << 9)
+#define PROMISCUOUS		(0x01 << 8)
+#define MULTICAST		(0x01 << 7)
+#define BROADCAST		(0x01 << 6)
+#define HASH			(0x01 << 5)
+#define APPEND_PAD		(0x01 << 4)
+#define APPEND_CRC		(0x01 << 3)
+#define TRANSMITTER_ACTION	(0x01 << 2)
+#define RECEIVER_ACTION		(0x01 << 1)
+#define DMA_ACTION		(0x01 << 0)
+
+/* Status register bits
+ *
+ * Note: bits 7-15 are reserved
+ */
+#define ALIGNMENT		(0x01 << 6)
+#define FIFO_OVER_RUN		(0x01 << 5)
+#define FIFO_UNDER_RUN		(0x01 << 4)
+#define RX_ERROR		(0x01 << 3)
+#define RX_COMPLETE		(0x01 << 2)
+#define TX_ERROR		(0x01 << 1)
+#define TX_COMPLETE		(0x01 << 0)
+
+/* FIFO depth register bits
+ *
+ * Note: bits 6 and 14 are reserved
+ */
+
+#define ETH_TXBD		(0x01 << 15)
+#define ETN_TX_FIFO_DEPTH	(0x01 << 8)
+#define ETH_RXBD		(0x01 << 7)
+#define ETH_RX_FIFO_DEPTH	(0x01 << 0)
+
+static int control_read(struct usbnet *dev,
+			unsigned char request, unsigned short value,
+			unsigned short index, void *data, unsigned short size,
+			int timeout)
+{
+	unsigned char *buf = NULL;
+	unsigned char request_type;
+	int err = 0;
+
+	if (request == REQUEST_READ)
+		request_type = (USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_OTHER);
+	else
+		request_type = (USB_DIR_IN | USB_TYPE_VENDOR |
+				USB_RECIP_DEVICE);
+
+	netdev_dbg(dev->net, "Control_read() index=0x%02x size=%d\n",
+		   index, size);
+
+	buf = kmalloc(size, GFP_KERNEL);
+	if (!buf) {
+		err = -ENOMEM;
+		goto err_out;
+	}
+
+	err = usb_control_msg(dev->udev,
+			      usb_rcvctrlpipe(dev->udev, 0),
+			      request, request_type, value, index, buf, size,
+			      timeout);
+	if (err == size)
+		memcpy(data, buf, size);
+	else if (err >= 0)
+		err = -EINVAL;
+	kfree(buf);
+
+	return err;
+
+err_out:
+	return err;
+}
+
+static int control_write(struct usbnet *dev, unsigned char request,
+			 unsigned short value, unsigned short index,
+			 void *data, unsigned short size, int timeout)
+{
+	unsigned char *buf = NULL;
+	unsigned char request_type;
+	int err = 0;
+
+	if (request == REQUEST_WRITE)
+		request_type = (USB_DIR_OUT | USB_TYPE_VENDOR |
+				USB_RECIP_OTHER);
+	else
+		request_type = (USB_DIR_OUT | USB_TYPE_VENDOR |
+				USB_RECIP_DEVICE);
+
+	netdev_dbg(dev->net, "Control_write() index=0x%02x size=%d\n",
+		   index, size);
+
+	if (data) {
+		buf = kmalloc(size, GFP_KERNEL);
+		if (!buf) {
+			err = -ENOMEM;
+			goto err_out;
+		}
+		memcpy(buf, data, size);
+	}
+
+	err = usb_control_msg(dev->udev,
+			      usb_sndctrlpipe(dev->udev, 0),
+			      request, request_type, value, index, buf, size,
+			      timeout);
+	if (err >= 0 && err < size)
+		err = -EINVAL;
+	kfree(buf);
+
+	return 0;
+
+err_out:
+	return err;
+}
+
+static int ch9200_mdio_read(struct net_device *netdev, int phy_id, int loc)
+{
+	struct usbnet *dev = netdev_priv(netdev);
+	unsigned char buff[2];
+
+	netdev_dbg(netdev, "ch9200_mdio_read phy_id:%02x loc:%02x\n",
+		   phy_id, loc);
+
+	if (phy_id != 0)
+		return -ENODEV;
+
+	control_read(dev, REQUEST_READ, 0, loc * 2, buff, 0x02,
+		     CONTROL_TIMEOUT_MS);
+
+	return (buff[0] | buff[1] << 8);
+}
+
+static void ch9200_mdio_write(struct net_device *netdev,
+			      int phy_id, int loc, int val)
+{
+	struct usbnet *dev = netdev_priv(netdev);
+	unsigned char buff[2];
+
+	netdev_dbg(netdev, "ch9200_mdio_write() phy_id=%02x loc:%02x\n",
+		   phy_id, loc);
+
+	if (phy_id != 0)
+		return;
+
+	buff[0] = (unsigned char)val;
+	buff[1] = (unsigned char)(val >> 8);
+
+	control_write(dev, REQUEST_WRITE, 0, loc * 2, buff, 0x02,
+		      CONTROL_TIMEOUT_MS);
+}
+
+static int ch9200_link_reset(struct usbnet *dev)
+{
+	struct ethtool_cmd ecmd;
+
+	mii_check_media(&dev->mii, 1, 1);
+	mii_ethtool_gset(&dev->mii, &ecmd);
+
+	netdev_dbg(dev->net, "link_reset() speed:%d duplex:%d\n",
+		   ecmd.speed, ecmd.duplex);
+
+	return 0;
+}
+
+static void ch9200_status(struct usbnet *dev, struct urb *urb)
+{
+	int link;
+	unsigned char *buf;
+
+	if (urb->actual_length < 16)
+		return;
+
+	buf = urb->transfer_buffer;
+	link = !!(buf[0] & 0x01);
+
+	if (link) {
+		netif_carrier_on(dev->net);
+		usbnet_defer_kevent(dev, EVENT_LINK_RESET);
+	} else {
+		netif_carrier_off(dev->net);
+	}
+}
+
+static struct sk_buff *ch9200_tx_fixup(struct usbnet *dev, struct sk_buff *skb,
+				       gfp_t flags)
+{
+	int i = 0;
+	int len = 0;
+	int tx_overhead = 0;
+
+	tx_overhead = 0x40;
+
+	len = skb->len;
+	if (skb_headroom(skb) < tx_overhead) {
+		struct sk_buff *skb2;
+
+		skb2 = skb_copy_expand(skb, tx_overhead, 0, flags);
+		dev_kfree_skb_any(skb);
+		skb = skb2;
+		if (!skb)
+			return NULL;
+	}
+
+	__skb_push(skb, tx_overhead);
+	/* usbnet adds padding if length is a multiple of packet size
+	 * if so, adjust length value in header
+	 */
+	if ((skb->len % dev->maxpacket) == 0)
+		len++;
+
+	skb->data[0] = len;
+	skb->data[1] = len >> 8;
+	skb->data[2] = 0x00;
+	skb->data[3] = 0x80;
+
+	for (i = 4; i < 48; i++)
+		skb->data[i] = 0x00;
+
+	skb->data[48] = len;
+	skb->data[49] = len >> 8;
+	skb->data[50] = 0x00;
+	skb->data[51] = 0x80;
+
+	for (i = 52; i < 64; i++)
+		skb->data[i] = 0x00;
+
+	return skb;
+}
+
+static int ch9200_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
+{
+	int len = 0;
+	int rx_overhead = 0;
+
+	rx_overhead = 64;
+
+	if (unlikely(skb->len < rx_overhead)) {
+		dev_err(&dev->udev->dev, "unexpected tiny rx frame\n");
+		return 0;
+	}
+
+	len = (skb->data[skb->len - 16] | skb->data[skb->len - 15] << 8);
+	skb_trim(skb, len);
+
+	return 1;
+}
+
+static int get_mac_address(struct usbnet *dev, unsigned char *data)
+{
+	int err = 0;
+	unsigned char mac_addr[0x06];
+	int rd_mac_len = 0;
+
+	netdev_dbg(dev->net, "get_mac_address:\n\tusbnet VID:%0x PID:%0x\n",
+		   dev->udev->descriptor.idVendor,
+		   dev->udev->descriptor.idProduct);
+
+	memset(mac_addr, 0, sizeof(mac_addr));
+	rd_mac_len = control_read(dev, REQUEST_READ, 0,
+				  MAC_REG_STATION_L, mac_addr, 0x02,
+				  CONTROL_TIMEOUT_MS);
+	rd_mac_len += control_read(dev, REQUEST_READ, 0, MAC_REG_STATION_M,
+				   mac_addr + 2, 0x02, CONTROL_TIMEOUT_MS);
+	rd_mac_len += control_read(dev, REQUEST_READ, 0, MAC_REG_STATION_H,
+				   mac_addr + 4, 0x02, CONTROL_TIMEOUT_MS);
+	if (rd_mac_len != ETH_ALEN)
+		err = -EINVAL;
+
+	data[0] = mac_addr[5];
+	data[1] = mac_addr[4];
+	data[2] = mac_addr[3];
+	data[3] = mac_addr[2];
+	data[4] = mac_addr[1];
+	data[5] = mac_addr[0];
+
+	return err;
+}
+
+static int ch9200_bind(struct usbnet *dev, struct usb_interface *intf)
+{
+	int retval = 0;
+	unsigned char data[2];
+
+	retval = usbnet_get_endpoints(dev, intf);
+	if (retval)
+		return retval;
+
+	dev->mii.dev = dev->net;
+	dev->mii.mdio_read = ch9200_mdio_read;
+	dev->mii.mdio_write = ch9200_mdio_write;
+	dev->mii.reg_num_mask = 0x1f;
+
+	dev->mii.phy_id_mask = 0x1f;
+
+	dev->hard_mtu = dev->net->mtu + dev->net->hard_header_len;
+	dev->rx_urb_size = 24 * 64 + 16;
+	mii_nway_restart(&dev->mii);
+
+	data[0] = 0x01;
+	data[1] = 0x0F;
+	retval = control_write(dev, REQUEST_WRITE, 0, MAC_REG_THRESHOLD, data,
+			       0x02, CONTROL_TIMEOUT_MS);
+
+	data[0] = 0xA0;
+	data[1] = 0x90;
+	retval = control_write(dev, REQUEST_WRITE, 0, MAC_REG_FIFO_DEPTH, data,
+			       0x02, CONTROL_TIMEOUT_MS);
+
+	data[0] = 0x30;
+	data[1] = 0x00;
+	retval = control_write(dev, REQUEST_WRITE, 0, MAC_REG_PAUSE, data,
+			       0x02, CONTROL_TIMEOUT_MS);
+
+	data[0] = 0x17;
+	data[1] = 0xD8;
+	retval = control_write(dev, REQUEST_WRITE, 0, MAC_REG_FLOW_CONTROL,
+			       data, 0x02, CONTROL_TIMEOUT_MS);
+
+	/* Undocumented register */
+	data[0] = 0x01;
+	data[1] = 0x00;
+	retval = control_write(dev, REQUEST_WRITE, 0, 254, data, 0x02,
+			       CONTROL_TIMEOUT_MS);
+
+	data[0] = 0x5F;
+	data[1] = 0x0D;
+	retval = control_write(dev, REQUEST_WRITE, 0, MAC_REG_CTRL, data, 0x02,
+			       CONTROL_TIMEOUT_MS);
+
+	retval = get_mac_address(dev, dev->net->dev_addr);
+
+	return retval;
+}
+
+static const struct driver_info ch9200_info = {
+	.description = "CH9200 USB to Network Adaptor",
+	.flags = FLAG_ETHER,
+	.bind = ch9200_bind,
+	.rx_fixup = ch9200_rx_fixup,
+	.tx_fixup = ch9200_tx_fixup,
+	.status = ch9200_status,
+	.link_reset = ch9200_link_reset,
+	.reset = ch9200_link_reset,
+};
+
+static const struct usb_device_id ch9200_products[] = {
+	{
+	 USB_DEVICE(0x1A86, 0xE092),
+	 .driver_info = (unsigned long)&ch9200_info,
+	 },
+	{},
+};
+
+MODULE_DEVICE_TABLE(usb, ch9200_products);
+
+static struct usb_driver ch9200_driver = {
+	.name = "ch9200",
+	.id_table = ch9200_products,
+	.probe = usbnet_probe,
+	.disconnect = usbnet_disconnect,
+	.suspend = usbnet_suspend,
+	.resume = usbnet_resume,
+};
+
+module_usb_driver(ch9200_driver);
+
+MODULE_DESCRIPTION("QinHeng CH9200 USB Network device");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index e7094fbd7568..488c6f50df73 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -193,7 +193,8 @@ static netdev_tx_t vrf_process_v4_outbound(struct sk_buff *skb,
 		.flowi4_oif = vrf_dev->ifindex,
 		.flowi4_iif = LOOPBACK_IFINDEX,
 		.flowi4_tos = RT_TOS(ip4h->tos),
-		.flowi4_flags = FLOWI_FLAG_ANYSRC | FLOWI_FLAG_VRFSRC,
+		.flowi4_flags = FLOWI_FLAG_ANYSRC | FLOWI_FLAG_VRFSRC |
+				FLOWI_FLAG_SKIP_NH_OIF,
 		.daddr = ip4h->daddr,
 	};
 
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index cf8b7f0473b3..bbac1d35ed4e 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2392,10 +2392,6 @@ static void vxlan_setup(struct net_device *dev)
 
 	eth_hw_addr_random(dev);
 	ether_setup(dev);
-	if (vxlan->default_dst.remote_ip.sa.sa_family == AF_INET6)
-		dev->needed_headroom = ETH_HLEN + VXLAN6_HEADROOM;
-	else
-		dev->needed_headroom = ETH_HLEN + VXLAN_HEADROOM;
 
 	dev->netdev_ops = &vxlan_netdev_ops;
 	dev->destructor = free_netdev;
@@ -2640,8 +2636,11 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev,
 		dst->remote_ip.sa.sa_family = AF_INET;
 
 	if (dst->remote_ip.sa.sa_family == AF_INET6 ||
-	    vxlan->cfg.saddr.sa.sa_family == AF_INET6)
+	    vxlan->cfg.saddr.sa.sa_family == AF_INET6) {
+		if (!IS_ENABLED(CONFIG_IPV6))
+			return -EPFNOSUPPORT;
 		use_ipv6 = true;
+	}
 
 	if (conf->remote_ifindex) {
 		struct net_device *lowerdev
@@ -2670,8 +2669,12 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev,
 
 		dev->needed_headroom = lowerdev->hard_header_len +
 				       (use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM);
-	} else if (use_ipv6)
+	} else if (use_ipv6) {
 		vxlan->flags |= VXLAN_F_IPV6;
+		dev->needed_headroom = ETH_HLEN + VXLAN6_HEADROOM;
+	} else {
+		dev->needed_headroom = ETH_HLEN + VXLAN_HEADROOM;
+	}
 
 	memcpy(&vxlan->cfg, conf, sizeof(*conf));
 	if (!vxlan->cfg.dst_port)
diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c
index 1350fa25cdb0..a87a868fed64 100644
--- a/drivers/of/of_mdio.c
+++ b/drivers/of/of_mdio.c
@@ -197,7 +197,8 @@ static int of_phy_match(struct device *dev, void *phy_np)
  * of_phy_find_device - Give a PHY node, find the phy_device
  * @phy_np: Pointer to the phy's device tree node
  *
- * Returns a pointer to the phy_device.
+ * If successful, returns a pointer to the phy_device with the embedded
+ * struct device refcount incremented by one, or NULL on failure.
  */
 struct phy_device *of_phy_find_device(struct device_node *phy_np)
 {
@@ -217,7 +218,9 @@ EXPORT_SYMBOL(of_phy_find_device);
  * @hndlr: Link state callback for the network device
  * @iface: PHY data interface type
  *
- * Returns a pointer to the phy_device if successful.  NULL otherwise
+ * If successful, returns a pointer to the phy_device with the embedded
+ * struct device refcount incremented by one, or NULL on failure. The
+ * refcount must be dropped by calling phy_disconnect() or phy_detach().
  */
 struct phy_device *of_phy_connect(struct net_device *dev,
 				  struct device_node *phy_np,
@@ -225,13 +228,19 @@ struct phy_device *of_phy_connect(struct net_device *dev,
 				  phy_interface_t iface)
 {
 	struct phy_device *phy = of_phy_find_device(phy_np);
+	int ret;
 
 	if (!phy)
 		return NULL;
 
 	phy->dev_flags = flags;
 
-	return phy_connect_direct(dev, phy, hndlr, iface) ? NULL : phy;
+	ret = phy_connect_direct(dev, phy, hndlr, iface);
+
+	/* refcount is held by phy_connect_direct() on success */
+	put_device(&phy->dev);
+
+	return ret ? NULL : phy;
 }
 EXPORT_SYMBOL(of_phy_connect);
 
@@ -241,17 +250,27 @@ EXPORT_SYMBOL(of_phy_connect);
  * @phy_np: Node pointer for the PHY
  * @flags: flags to pass to the PHY
  * @iface: PHY data interface type
+ *
+ * If successful, returns a pointer to the phy_device with the embedded
+ * struct device refcount incremented by one, or NULL on failure. The
+ * refcount must be dropped by calling phy_disconnect() or phy_detach().
  */
 struct phy_device *of_phy_attach(struct net_device *dev,
 				 struct device_node *phy_np, u32 flags,
 				 phy_interface_t iface)
 {
 	struct phy_device *phy = of_phy_find_device(phy_np);
+	int ret;
 
 	if (!phy)
 		return NULL;
 
-	return phy_attach_direct(dev, phy, flags, iface) ? NULL : phy;
+	ret = phy_attach_direct(dev, phy, flags, iface);
+
+	/* refcount is held by phy_attach_direct() on success */
+	put_device(&phy->dev);
+
+	return ret ? NULL : phy;
 }
 EXPORT_SYMBOL(of_phy_attach);
 
diff --git a/drivers/of/of_pci_irq.c b/drivers/of/of_pci_irq.c
index 1710d9dc7fc2..2306313c0029 100644
--- a/drivers/of/of_pci_irq.c
+++ b/drivers/of/of_pci_irq.c
@@ -38,8 +38,8 @@ int of_irq_parse_pci(const struct pci_dev *pdev, struct of_phandle_args *out_irq
 	 */
 	rc = pci_read_config_byte(pdev, PCI_INTERRUPT_PIN, &pin);
 	if (rc != 0)
-		return rc;
-	/* No pin, exit */
+		goto err;
+	/* No pin, exit with no error message. */
 	if (pin == 0)
 		return -ENODEV;
 
@@ -53,8 +53,10 @@ int of_irq_parse_pci(const struct pci_dev *pdev, struct of_phandle_args *out_irq
 			ppnode = pci_bus_to_OF_node(pdev->bus);
 
 			/* No node for host bridge ? give up */
-			if (ppnode == NULL)
-				return -EINVAL;
+			if (ppnode == NULL) {
+				rc = -EINVAL;
+				goto err;
+			}
 		} else {
 			/* We found a P2P bridge, check if it has a node */
 			ppnode = pci_device_to_OF_node(ppdev);
@@ -86,7 +88,13 @@ int of_irq_parse_pci(const struct pci_dev *pdev, struct of_phandle_args *out_irq
 	out_irq->args[0] = pin;
 	laddr[0] = cpu_to_be32((pdev->bus->number << 16) | (pdev->devfn << 8));
 	laddr[1] = laddr[2] = cpu_to_be32(0);
-	return of_irq_parse_raw(laddr, out_irq);
+	rc = of_irq_parse_raw(laddr, out_irq);
+	if (rc)
+		goto err;
+	return 0;
+err:
+	dev_err(&pdev->dev, "of_irq_parse_pci() failed with rc=%d\n", rc);
+	return rc;
 }
 EXPORT_SYMBOL_GPL(of_irq_parse_pci);
 
@@ -105,10 +113,8 @@ int of_irq_parse_and_map_pci(const struct pci_dev *dev, u8 slot, u8 pin)
 	int ret;
 
 	ret = of_irq_parse_pci(dev, &oirq);
-	if (ret) {
-		dev_err(&dev->dev, "of_irq_parse_pci() failed with rc=%d\n", ret);
+	if (ret)
 		return 0; /* Proper return code 0 == NO_IRQ */
-	}
 
 	return irq_create_of_mapping(&oirq);
 }
diff --git a/drivers/parisc/dino.c b/drivers/parisc/dino.c
index baec33c4e698..a0580afe1713 100644
--- a/drivers/parisc/dino.c
+++ b/drivers/parisc/dino.c
@@ -560,6 +560,9 @@ dino_fixup_bus(struct pci_bus *bus)
 	} else if (bus->parent) {
 		int i;
 
+		pci_read_bridge_bases(bus);
+
+
 		for(i = PCI_BRIDGE_RESOURCES; i < PCI_NUM_RESOURCES; i++) {
 			if((bus->self->resource[i].flags & 
 			    (IORESOURCE_IO | IORESOURCE_MEM)) == 0)
diff --git a/drivers/parisc/lba_pci.c b/drivers/parisc/lba_pci.c
index 7b9e89ba0465..a32c1f6c252c 100644
--- a/drivers/parisc/lba_pci.c
+++ b/drivers/parisc/lba_pci.c
@@ -693,6 +693,7 @@ lba_fixup_bus(struct pci_bus *bus)
 	if (bus->parent) {
 		int i;
 		/* PCI-PCI Bridge */
+		pci_read_bridge_bases(bus);
 		for (i = PCI_BRIDGE_RESOURCES; i < PCI_NUM_RESOURCES; i++)
 			pci_claim_bridge_resource(bus->self, i);
 	} else {
diff --git a/drivers/pci/access.c b/drivers/pci/access.c
index 769f7e35f1a2..59ac36fe7c42 100644
--- a/drivers/pci/access.c
+++ b/drivers/pci/access.c
@@ -442,7 +442,8 @@ static const struct pci_vpd_ops pci_vpd_pci22_ops = {
 static ssize_t pci_vpd_f0_read(struct pci_dev *dev, loff_t pos, size_t count,
 			       void *arg)
 {
-	struct pci_dev *tdev = pci_get_slot(dev->bus, PCI_SLOT(dev->devfn));
+	struct pci_dev *tdev = pci_get_slot(dev->bus,
+					    PCI_DEVFN(PCI_SLOT(dev->devfn), 0));
 	ssize_t ret;
 
 	if (!tdev)
@@ -456,7 +457,8 @@ static ssize_t pci_vpd_f0_read(struct pci_dev *dev, loff_t pos, size_t count,
 static ssize_t pci_vpd_f0_write(struct pci_dev *dev, loff_t pos, size_t count,
 				const void *arg)
 {
-	struct pci_dev *tdev = pci_get_slot(dev->bus, PCI_SLOT(dev->devfn));
+	struct pci_dev *tdev = pci_get_slot(dev->bus,
+					    PCI_DEVFN(PCI_SLOT(dev->devfn), 0));
 	ssize_t ret;
 
 	if (!tdev)
@@ -473,22 +475,6 @@ static const struct pci_vpd_ops pci_vpd_f0_ops = {
 	.release = pci_vpd_pci22_release,
 };
 
-static int pci_vpd_f0_dev_check(struct pci_dev *dev)
-{
-	struct pci_dev *tdev = pci_get_slot(dev->bus, PCI_SLOT(dev->devfn));
-	int ret = 0;
-
-	if (!tdev)
-		return -ENODEV;
-	if (!tdev->vpd || !tdev->multifunction ||
-	    dev->class != tdev->class || dev->vendor != tdev->vendor ||
-	    dev->device != tdev->device)
-		ret = -ENODEV;
-
-	pci_dev_put(tdev);
-	return ret;
-}
-
 int pci_vpd_pci22_init(struct pci_dev *dev)
 {
 	struct pci_vpd_pci22 *vpd;
@@ -497,12 +483,7 @@ int pci_vpd_pci22_init(struct pci_dev *dev)
 	cap = pci_find_capability(dev, PCI_CAP_ID_VPD);
 	if (!cap)
 		return -ENODEV;
-	if (dev->dev_flags & PCI_DEV_FLAGS_VPD_REF_F0) {
-		int ret = pci_vpd_f0_dev_check(dev);
 
-		if (ret)
-			return ret;
-	}
 	vpd = kzalloc(sizeof(*vpd), GFP_ATOMIC);
 	if (!vpd)
 		return -ENOMEM;
diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c
index 6fbd3f2b5992..d3346d23963b 100644
--- a/drivers/pci/bus.c
+++ b/drivers/pci/bus.c
@@ -256,6 +256,8 @@ bool pci_bus_clip_resource(struct pci_dev *dev, int idx)
 
 		res->start = start;
 		res->end = end;
+		res->flags &= ~IORESOURCE_UNSET;
+		orig_res.flags &= ~IORESOURCE_UNSET;
 		dev_printk(KERN_DEBUG, &dev->dev, "%pR clipped to %pR\n",
 				 &orig_res, res);
 
diff --git a/drivers/pci/host/pci-rcar-gen2.c b/drivers/pci/host/pci-rcar-gen2.c
index 367e28fa7564..c4f64bfee551 100644
--- a/drivers/pci/host/pci-rcar-gen2.c
+++ b/drivers/pci/host/pci-rcar-gen2.c
@@ -362,6 +362,7 @@ static int rcar_pci_probe(struct platform_device *pdev)
 static struct of_device_id rcar_pci_of_match[] = {
 	{ .compatible = "renesas,pci-r8a7790", },
 	{ .compatible = "renesas,pci-r8a7791", },
+	{ .compatible = "renesas,pci-r8a7794", },
 	{ },
 };
 
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 0b2be174d981..8361d27e5eca 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -676,15 +676,20 @@ static struct irq_domain *pci_host_bridge_msi_domain(struct pci_bus *bus)
 static void pci_set_bus_msi_domain(struct pci_bus *bus)
 {
 	struct irq_domain *d;
+	struct pci_bus *b;
 
 	/*
-	 * Either bus is the root, and we must obtain it from the
-	 * firmware, or we inherit it from the bridge device.
+	 * The bus can be a root bus, a subordinate bus, or a virtual bus
+	 * created by an SR-IOV device.  Walk up to the first bridge device
+	 * found or derive the domain from the host bridge.
 	 */
-	if (pci_is_root_bus(bus))
-		d = pci_host_bridge_msi_domain(bus);
-	else
-		d = dev_get_msi_domain(&bus->self->dev);
+	for (b = bus, d = NULL; !d && !pci_is_root_bus(b); b = b->parent) {
+		if (b->self)
+			d = dev_get_msi_domain(&b->self->dev);
+	}
+
+	if (!d)
+		d = pci_host_bridge_msi_domain(b);
 
 	dev_set_msi_domain(&bus->dev, d);
 }
@@ -855,9 +860,6 @@ int pci_scan_bridge(struct pci_bus *bus, struct pci_dev *dev, int max, int pass)
 			child->bridge_ctl = bctl;
 		}
 
-		/* Read and initialize bridge resources */
-		pci_read_bridge_bases(child);
-
 		cmax = pci_scan_child_bus(child);
 		if (cmax > subordinate)
 			dev_warn(&dev->dev, "bridge has subordinate %02x but max busn %02x\n",
@@ -918,9 +920,6 @@ int pci_scan_bridge(struct pci_bus *bus, struct pci_dev *dev, int max, int pass)
 
 		if (!is_cardbus) {
 			child->bridge_ctl = bctl;
-
-			/* Read and initialize bridge resources */
-			pci_read_bridge_bases(child);
 			max = pci_scan_child_bus(child);
 		} else {
 			/*
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 6a30252cd79f..b03373fd05ca 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -1907,11 +1907,27 @@ static void quirk_netmos(struct pci_dev *dev)
 DECLARE_PCI_FIXUP_CLASS_HEADER(PCI_VENDOR_ID_NETMOS, PCI_ANY_ID,
 			 PCI_CLASS_COMMUNICATION_SERIAL, 8, quirk_netmos);
 
+/*
+ * Quirk non-zero PCI functions to route VPD access through function 0 for
+ * devices that share VPD resources between functions.  The functions are
+ * expected to be identical devices.
+ */
 static void quirk_f0_vpd_link(struct pci_dev *dev)
 {
-	if (!dev->multifunction || !PCI_FUNC(dev->devfn))
+	struct pci_dev *f0;
+
+	if (!PCI_FUNC(dev->devfn))
 		return;
-	dev->dev_flags |= PCI_DEV_FLAGS_VPD_REF_F0;
+
+	f0 = pci_get_slot(dev->bus, PCI_DEVFN(PCI_SLOT(dev->devfn), 0));
+	if (!f0)
+		return;
+
+	if (f0->vpd && dev->class == f0->class &&
+	    dev->vendor == f0->vendor && dev->device == f0->device)
+		dev->dev_flags |= PCI_DEV_FLAGS_VPD_REF_F0;
+
+	pci_dev_put(f0);
 }
 DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, PCI_ANY_ID,
 			      PCI_CLASS_NETWORK_ETHERNET, 8, quirk_f0_vpd_link);
diff --git a/drivers/regulator/anatop-regulator.c b/drivers/regulator/anatop-regulator.c
index 738adfa5332b..52ea605f8130 100644
--- a/drivers/regulator/anatop-regulator.c
+++ b/drivers/regulator/anatop-regulator.c
@@ -318,6 +318,7 @@ static const struct of_device_id of_anatop_regulator_match_tbl[] = {
 	{ .compatible = "fsl,anatop-regulator", },
 	{ /* end */ }
 };
+MODULE_DEVICE_TABLE(of, of_anatop_regulator_match_tbl);
 
 static struct platform_driver anatop_regulator_driver = {
 	.driver = {
diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index 7a85ac9e32c5..7849187d91ae 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -1394,15 +1394,15 @@ static int regulator_resolve_supply(struct regulator_dev *rdev)
 		return 0;
 
 	r = regulator_dev_lookup(dev, rdev->supply_name, &ret);
-	if (ret == -ENODEV) {
-		/*
-		 * No supply was specified for this regulator and
-		 * there will never be one.
-		 */
-		return 0;
-	}
-
 	if (!r) {
+		if (ret == -ENODEV) {
+			/*
+			 * No supply was specified for this regulator and
+			 * there will never be one.
+			 */
+			return 0;
+		}
+
 		if (have_full_constraints()) {
 			r = dummy_regulator_rdev;
 		} else {
@@ -1422,11 +1422,10 @@ static int regulator_resolve_supply(struct regulator_dev *rdev)
 		return ret;
 
 	/* Cascade always-on state to supply */
-	if (_regulator_is_enabled(rdev)) {
+	if (_regulator_is_enabled(rdev) && rdev->supply) {
 		ret = regulator_enable(rdev->supply);
 		if (ret < 0) {
-			if (rdev->supply)
-				_regulator_put(rdev->supply);
+			_regulator_put(rdev->supply);
 			return ret;
 		}
 	}
diff --git a/drivers/regulator/gpio-regulator.c b/drivers/regulator/gpio-regulator.c
index 464018de7e97..7bba8b747f30 100644
--- a/drivers/regulator/gpio-regulator.c
+++ b/drivers/regulator/gpio-regulator.c
@@ -394,6 +394,7 @@ static const struct of_device_id regulator_gpio_of_match[] = {
 	{ .compatible = "regulator-gpio", },
 	{},
 };
+MODULE_DEVICE_TABLE(of, regulator_gpio_of_match);
 #endif
 
 static struct platform_driver gpio_regulator_driver = {
diff --git a/drivers/regulator/pbias-regulator.c b/drivers/regulator/pbias-regulator.c
index 4fa7bcaf454e..f9d74d63be7c 100644
--- a/drivers/regulator/pbias-regulator.c
+++ b/drivers/regulator/pbias-regulator.c
@@ -45,6 +45,10 @@ struct pbias_regulator_data {
 	int voltage;
 };
 
+struct pbias_of_data {
+	unsigned int offset;
+};
+
 static const unsigned int pbias_volt_table[] = {
 	1800000,
 	3000000
@@ -102,8 +106,35 @@ static struct of_regulator_match pbias_matches[] = {
 };
 #define PBIAS_NUM_REGS	ARRAY_SIZE(pbias_matches)
 
+/* Offset from SCM general area (and syscon) base */
+
+static const struct pbias_of_data pbias_of_data_omap2 = {
+	.offset = 0x230,
+};
+
+static const struct pbias_of_data pbias_of_data_omap3 = {
+	.offset = 0x2b0,
+};
+
+static const struct pbias_of_data pbias_of_data_omap4 = {
+	.offset = 0x60,
+};
+
+static const struct pbias_of_data pbias_of_data_omap5 = {
+	.offset = 0x60,
+};
+
+static const struct pbias_of_data pbias_of_data_dra7 = {
+	.offset = 0xe00,
+};
+
 static const struct of_device_id pbias_of_match[] = {
 	{ .compatible = "ti,pbias-omap", },
+	{ .compatible = "ti,pbias-omap2", .data = &pbias_of_data_omap2, },
+	{ .compatible = "ti,pbias-omap3", .data = &pbias_of_data_omap3, },
+	{ .compatible = "ti,pbias-omap4", .data = &pbias_of_data_omap4, },
+	{ .compatible = "ti,pbias-omap5", .data = &pbias_of_data_omap5, },
+	{ .compatible = "ti,pbias-dra7", .data = &pbias_of_data_dra7, },
 	{},
 };
 MODULE_DEVICE_TABLE(of, pbias_of_match);
@@ -118,6 +149,9 @@ static int pbias_regulator_probe(struct platform_device *pdev)
 	const struct pbias_reg_info *info;
 	int ret = 0;
 	int count, idx, data_idx = 0;
+	const struct of_device_id *match;
+	const struct pbias_of_data *data;
+	unsigned int offset;
 
 	count = of_regulator_match(&pdev->dev, np, pbias_matches,
 						PBIAS_NUM_REGS);
@@ -133,6 +167,20 @@ static int pbias_regulator_probe(struct platform_device *pdev)
 	if (IS_ERR(syscon))
 		return PTR_ERR(syscon);
 
+	match = of_match_device(of_match_ptr(pbias_of_match), &pdev->dev);
+	if (match && match->data) {
+		data = match->data;
+		offset = data->offset;
+	} else {
+		res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+		if (!res)
+			return -EINVAL;
+
+		offset = res->start;
+		dev_WARN(&pdev->dev,
+			 "using legacy dt data for pbias offset\n");
+	}
+
 	cfg.regmap = syscon;
 	cfg.dev = &pdev->dev;
 
@@ -145,10 +193,6 @@ static int pbias_regulator_probe(struct platform_device *pdev)
 		if (!info)
 			return -ENODEV;
 
-		res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-		if (!res)
-			return -EINVAL;
-
 		drvdata[data_idx].syscon = syscon;
 		drvdata[data_idx].info = info;
 		drvdata[data_idx].desc.name = info->name;
@@ -158,9 +202,9 @@ static int pbias_regulator_probe(struct platform_device *pdev)
 		drvdata[data_idx].desc.volt_table = pbias_volt_table;
 		drvdata[data_idx].desc.n_voltages = 2;
 		drvdata[data_idx].desc.enable_time = info->enable_time;
-		drvdata[data_idx].desc.vsel_reg = res->start;
+		drvdata[data_idx].desc.vsel_reg = offset;
 		drvdata[data_idx].desc.vsel_mask = info->vmode;
-		drvdata[data_idx].desc.enable_reg = res->start;
+		drvdata[data_idx].desc.enable_reg = offset;
 		drvdata[data_idx].desc.enable_mask = info->enable_mask;
 		drvdata[data_idx].desc.enable_val = info->enable;
 		drvdata[data_idx].desc.disable_val = info->disable_val;
diff --git a/drivers/regulator/tps65218-regulator.c b/drivers/regulator/tps65218-regulator.c
index 7f97223f95c5..a02c1b961039 100644
--- a/drivers/regulator/tps65218-regulator.c
+++ b/drivers/regulator/tps65218-regulator.c
@@ -73,7 +73,7 @@ static const struct regulator_linear_range dcdc4_ranges[] = {
 };
 
 static struct tps_info tps65218_pmic_regs[] = {
-	TPS65218_INFO(DCDC1, "DCDC1", 850000, 167500),
+	TPS65218_INFO(DCDC1, "DCDC1", 850000, 1675000),
 	TPS65218_INFO(DCDC2, "DCDC2", 850000, 1675000),
 	TPS65218_INFO(DCDC3, "DCDC3", 900000, 3400000),
 	TPS65218_INFO(DCDC4, "DCDC4", 1175000, 3400000),
diff --git a/drivers/regulator/vexpress.c b/drivers/regulator/vexpress.c
index bed9d3ee4198..c810cbbd463f 100644
--- a/drivers/regulator/vexpress.c
+++ b/drivers/regulator/vexpress.c
@@ -103,6 +103,7 @@ static const struct of_device_id vexpress_regulator_of_match[] = {
 	{ .compatible = "arm,vexpress-volt", },
 	{ }
 };
+MODULE_DEVICE_TABLE(of, vexpress_regulator_of_match);
 
 static struct platform_driver vexpress_regulator_driver = {
 	.probe = vexpress_regulator_probe,
diff --git a/drivers/sh/pm_runtime.c b/drivers/sh/pm_runtime.c
index d3d1891cda3c..25abd4eb7d10 100644
--- a/drivers/sh/pm_runtime.c
+++ b/drivers/sh/pm_runtime.c
@@ -35,20 +35,11 @@ static struct pm_clk_notifier_block platform_bus_notifier = {
 static int __init sh_pm_runtime_init(void)
 {
 	if (IS_ENABLED(CONFIG_ARCH_SHMOBILE_MULTI)) {
-		if (!of_machine_is_compatible("renesas,emev2") &&
-		    !of_machine_is_compatible("renesas,r7s72100") &&
-#ifndef CONFIG_PM_GENERIC_DOMAINS_OF
-		    !of_machine_is_compatible("renesas,r8a73a4") &&
-		    !of_machine_is_compatible("renesas,r8a7740") &&
-		    !of_machine_is_compatible("renesas,sh73a0") &&
-#endif
-		    !of_machine_is_compatible("renesas,r8a7778") &&
-		    !of_machine_is_compatible("renesas,r8a7779") &&
-		    !of_machine_is_compatible("renesas,r8a7790") &&
-		    !of_machine_is_compatible("renesas,r8a7791") &&
-		    !of_machine_is_compatible("renesas,r8a7792") &&
-		    !of_machine_is_compatible("renesas,r8a7793") &&
-		    !of_machine_is_compatible("renesas,r8a7794"))
+		if (!of_find_compatible_node(NULL, NULL,
+					     "renesas,cpg-mstp-clocks"))
+			return 0;
+		if (IS_ENABLED(CONFIG_PM_GENERIC_DOMAINS_OF) &&
+		    of_find_node_with_property(NULL, "#power-domain-cells"))
 			return 0;
 	}
 
diff --git a/drivers/spi/spi-atmel.c b/drivers/spi/spi-atmel.c
index bf9ed380bb1c..63318e2afba1 100644
--- a/drivers/spi/spi-atmel.c
+++ b/drivers/spi/spi-atmel.c
@@ -1720,6 +1720,7 @@ static int atmel_spi_runtime_resume(struct device *dev)
 	return clk_prepare_enable(as->clk);
 }
 
+#ifdef CONFIG_PM_SLEEP
 static int atmel_spi_suspend(struct device *dev)
 {
 	struct spi_master *master = dev_get_drvdata(dev);
@@ -1756,6 +1757,7 @@ static int atmel_spi_resume(struct device *dev)
 
 	return ret;
 }
+#endif
 
 static const struct dev_pm_ops atmel_spi_pm_ops = {
 	SET_SYSTEM_SLEEP_PM_OPS(atmel_spi_suspend, atmel_spi_resume)
diff --git a/drivers/spi/spi-bcm2835.c b/drivers/spi/spi-bcm2835.c
index e7874a6171ec..3e8eeb23d4e9 100644
--- a/drivers/spi/spi-bcm2835.c
+++ b/drivers/spi/spi-bcm2835.c
@@ -386,14 +386,14 @@ static bool bcm2835_spi_can_dma(struct spi_master *master,
 	/* otherwise we only allow transfers within the same page
 	 * to avoid wasting time on dma_mapping when it is not practical
 	 */
-	if (((size_t)tfr->tx_buf & PAGE_MASK) + tfr->len > PAGE_SIZE) {
+	if (((size_t)tfr->tx_buf & (PAGE_SIZE - 1)) + tfr->len > PAGE_SIZE) {
 		dev_warn_once(&spi->dev,
 			      "Unaligned spi tx-transfer bridging page\n");
 		return false;
 	}
-	if (((size_t)tfr->rx_buf & PAGE_MASK) + tfr->len > PAGE_SIZE) {
+	if (((size_t)tfr->rx_buf & (PAGE_SIZE - 1)) + tfr->len > PAGE_SIZE) {
 		dev_warn_once(&spi->dev,
-			      "Unaligned spi tx-transfer bridging page\n");
+			      "Unaligned spi rx-transfer bridging page\n");
 		return false;
 	}
 
diff --git a/drivers/spi/spi-meson-spifc.c b/drivers/spi/spi-meson-spifc.c
index 5468fc70dbf8..2465259f6241 100644
--- a/drivers/spi/spi-meson-spifc.c
+++ b/drivers/spi/spi-meson-spifc.c
@@ -444,6 +444,7 @@ static const struct of_device_id meson_spifc_dt_match[] = {
 	{ .compatible = "amlogic,meson6-spifc", },
 	{ },
 };
+MODULE_DEVICE_TABLE(of, meson_spifc_dt_match);
 
 static struct platform_driver meson_spifc_driver = {
 	.probe	= meson_spifc_probe,
diff --git a/drivers/spi/spi-mt65xx.c b/drivers/spi/spi-mt65xx.c
index 5f6315c47920..ecb6c58238c4 100644
--- a/drivers/spi/spi-mt65xx.c
+++ b/drivers/spi/spi-mt65xx.c
@@ -85,7 +85,7 @@ struct mtk_spi {
 	void __iomem *base;
 	u32 state;
 	u32 pad_sel;
-	struct clk *spi_clk, *parent_clk;
+	struct clk *parent_clk, *sel_clk, *spi_clk;
 	struct spi_transfer *cur_transfer;
 	u32 xfer_len;
 	struct scatterlist *tx_sgl, *rx_sgl;
@@ -173,22 +173,6 @@ static void mtk_spi_config(struct mtk_spi *mdata,
 		writel(mdata->pad_sel, mdata->base + SPI_PAD_SEL_REG);
 }
 
-static int mtk_spi_prepare_hardware(struct spi_master *master)
-{
-	struct spi_transfer *trans;
-	struct mtk_spi *mdata = spi_master_get_devdata(master);
-	struct spi_message *msg = master->cur_msg;
-
-	trans = list_first_entry(&msg->transfers, struct spi_transfer,
-				 transfer_list);
-	if (!trans->cs_change) {
-		mdata->state = MTK_SPI_IDLE;
-		mtk_spi_reset(mdata);
-	}
-
-	return 0;
-}
-
 static int mtk_spi_prepare_message(struct spi_master *master,
 				   struct spi_message *msg)
 {
@@ -228,11 +212,15 @@ static void mtk_spi_set_cs(struct spi_device *spi, bool enable)
 	struct mtk_spi *mdata = spi_master_get_devdata(spi->master);
 
 	reg_val = readl(mdata->base + SPI_CMD_REG);
-	if (!enable)
+	if (!enable) {
 		reg_val |= SPI_CMD_PAUSE_EN;
-	else
+		writel(reg_val, mdata->base + SPI_CMD_REG);
+	} else {
 		reg_val &= ~SPI_CMD_PAUSE_EN;
-	writel(reg_val, mdata->base + SPI_CMD_REG);
+		writel(reg_val, mdata->base + SPI_CMD_REG);
+		mdata->state = MTK_SPI_IDLE;
+		mtk_spi_reset(mdata);
+	}
 }
 
 static void mtk_spi_prepare_transfer(struct spi_master *master,
@@ -509,7 +497,6 @@ static int mtk_spi_probe(struct platform_device *pdev)
 	master->mode_bits = SPI_CPOL | SPI_CPHA;
 
 	master->set_cs = mtk_spi_set_cs;
-	master->prepare_transfer_hardware = mtk_spi_prepare_hardware;
 	master->prepare_message = mtk_spi_prepare_message;
 	master->transfer_one = mtk_spi_transfer_one;
 	master->can_dma = mtk_spi_can_dma;
@@ -576,13 +563,6 @@ static int mtk_spi_probe(struct platform_device *pdev)
 		goto err_put_master;
 	}
 
-	mdata->spi_clk = devm_clk_get(&pdev->dev, "spi-clk");
-	if (IS_ERR(mdata->spi_clk)) {
-		ret = PTR_ERR(mdata->spi_clk);
-		dev_err(&pdev->dev, "failed to get spi-clk: %d\n", ret);
-		goto err_put_master;
-	}
-
 	mdata->parent_clk = devm_clk_get(&pdev->dev, "parent-clk");
 	if (IS_ERR(mdata->parent_clk)) {
 		ret = PTR_ERR(mdata->parent_clk);
@@ -590,13 +570,27 @@ static int mtk_spi_probe(struct platform_device *pdev)
 		goto err_put_master;
 	}
 
+	mdata->sel_clk = devm_clk_get(&pdev->dev, "sel-clk");
+	if (IS_ERR(mdata->sel_clk)) {
+		ret = PTR_ERR(mdata->sel_clk);
+		dev_err(&pdev->dev, "failed to get sel-clk: %d\n", ret);
+		goto err_put_master;
+	}
+
+	mdata->spi_clk = devm_clk_get(&pdev->dev, "spi-clk");
+	if (IS_ERR(mdata->spi_clk)) {
+		ret = PTR_ERR(mdata->spi_clk);
+		dev_err(&pdev->dev, "failed to get spi-clk: %d\n", ret);
+		goto err_put_master;
+	}
+
 	ret = clk_prepare_enable(mdata->spi_clk);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "failed to enable spi_clk (%d)\n", ret);
 		goto err_put_master;
 	}
 
-	ret = clk_set_parent(mdata->spi_clk, mdata->parent_clk);
+	ret = clk_set_parent(mdata->sel_clk, mdata->parent_clk);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "failed to clk_set_parent (%d)\n", ret);
 		goto err_disable_clk;
@@ -630,7 +624,6 @@ static int mtk_spi_remove(struct platform_device *pdev)
 	pm_runtime_disable(&pdev->dev);
 
 	mtk_spi_reset(mdata);
-	clk_disable_unprepare(mdata->spi_clk);
 	spi_master_put(master);
 
 	return 0;
diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c
index fdd791977041..a8ef38ebb9c9 100644
--- a/drivers/spi/spi-pxa2xx.c
+++ b/drivers/spi/spi-pxa2xx.c
@@ -654,6 +654,10 @@ static irqreturn_t ssp_int(int irq, void *dev_id)
 	if (!(sccr1_reg & SSCR1_TIE))
 		mask &= ~SSSR_TFS;
 
+	/* Ignore RX timeout interrupt if it is disabled */
+	if (!(sccr1_reg & SSCR1_TINTE))
+		mask &= ~SSSR_TINT;
+
 	if (!(status & mask))
 		return IRQ_NONE;
 
diff --git a/drivers/spi/spi-xtensa-xtfpga.c b/drivers/spi/spi-xtensa-xtfpga.c
index 2e32ea2f194f..be6155cba9de 100644
--- a/drivers/spi/spi-xtensa-xtfpga.c
+++ b/drivers/spi/spi-xtensa-xtfpga.c
@@ -34,13 +34,13 @@ struct xtfpga_spi {
 static inline void xtfpga_spi_write32(const struct xtfpga_spi *spi,
 				      unsigned addr, u32 val)
 {
-	iowrite32(val, spi->regs + addr);
+	__raw_writel(val, spi->regs + addr);
 }
 
 static inline unsigned int xtfpga_spi_read32(const struct xtfpga_spi *spi,
 					     unsigned addr)
 {
-	return ioread32(spi->regs + addr);
+	return __raw_readl(spi->regs + addr);
 }
 
 static inline void xtfpga_spi_wait_busy(struct xtfpga_spi *xspi)
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 3abb3903f2ad..a5f53de813d3 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -1610,8 +1610,7 @@ static struct class spi_master_class = {
  *
  * The caller is responsible for assigning the bus number and initializing
  * the master's methods before calling spi_register_master(); and (after errors
- * adding the device) calling spi_master_put() and kfree() to prevent a memory
- * leak.
+ * adding the device) calling spi_master_put() to prevent a memory leak.
  */
 struct spi_master *spi_alloc_master(struct device *dev, unsigned size)
 {
diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c
index fba92a526531..ef008e52f953 100644
--- a/drivers/spi/spidev.c
+++ b/drivers/spi/spidev.c
@@ -651,7 +651,8 @@ static int spidev_release(struct inode *inode, struct file *filp)
 		kfree(spidev->rx_buffer);
 		spidev->rx_buffer = NULL;
 
-		spidev->speed_hz = spidev->spi->max_speed_hz;
+		if (spidev->spi)
+			spidev->speed_hz = spidev->spi->max_speed_hz;
 
 		/* ... after we unbound from the underlying device? */
 		spin_lock_irq(&spidev->spi_lock);
diff --git a/drivers/staging/android/TODO b/drivers/staging/android/TODO
index 20288fc53946..8f3ac37bfe12 100644
--- a/drivers/staging/android/TODO
+++ b/drivers/staging/android/TODO
@@ -5,5 +5,25 @@ TODO:
 	- add proper arch dependencies as needed
 	- audit userspace interfaces to make sure they are sane
 
+
+ion/
+ - Remove ION_IOC_SYNC: Flushing for devices should be purely a kernel internal
+   interface on top of dma-buf. flush_for_device needs to be added to dma-buf
+   first.
+ - Remove ION_IOC_CUSTOM: Atm used for cache flushing for cpu access in some
+   vendor trees. Should be replaced with an ioctl on the dma-buf to expose the
+   begin/end_cpu_access hooks to userspace.
+ - Clarify the tricks ion plays with explicitly managing coherency behind the
+   dma api's back (this is absolutely needed for high-perf gpu drivers): Add an
+   explicit coherency management mode to flush_for_device to be used by drivers
+   which want to manage caches themselves and which indicates whether cpu caches
+   need flushing.
+ - With those removed there's probably no use for ION_IOC_IMPORT anymore either
+   since ion would just be the central allocator for shared buffers.
+ - Add dt-binding to expose cma regions as ion heaps, with the rule that any
+   such cma regions must already be used by some device for dma. I.e. ion only
+   exposes existing cma regions and doesn't reserve unecessarily memory when
+   booting a system which doesn't use ion.
+
 Please send patches to Greg Kroah-Hartman <greg@kroah.com> and Cc:
 Arve Hjønnevåg <arve@android.com> and Riley Andrews <riandrews@android.com>
diff --git a/drivers/staging/android/ion/ion.c b/drivers/staging/android/ion/ion.c
index 217aa537c4eb..6e8d8392ca38 100644
--- a/drivers/staging/android/ion/ion.c
+++ b/drivers/staging/android/ion/ion.c
@@ -1179,13 +1179,13 @@ struct ion_handle *ion_import_dma_buf(struct ion_client *client, int fd)
 		mutex_unlock(&client->lock);
 		goto end;
 	}
-	mutex_unlock(&client->lock);
 
 	handle = ion_handle_create(client, buffer);
-	if (IS_ERR(handle))
+	if (IS_ERR(handle)) {
+		mutex_unlock(&client->lock);
 		goto end;
+	}
 
-	mutex_lock(&client->lock);
 	ret = ion_handle_add(client, handle);
 	mutex_unlock(&client->lock);
 	if (ret) {
diff --git a/drivers/staging/fbtft/fb_uc1611.c b/drivers/staging/fbtft/fb_uc1611.c
index 32f3a9d921d6..5cafa50d1fac 100644
--- a/drivers/staging/fbtft/fb_uc1611.c
+++ b/drivers/staging/fbtft/fb_uc1611.c
@@ -76,7 +76,7 @@ static int init_display(struct fbtft_par *par)
 
 	/* Set CS active high */
 	par->spi->mode |= SPI_CS_HIGH;
-	ret = par->spi->master->setup(par->spi);
+	ret = spi_setup(par->spi);
 	if (ret) {
 		dev_err(par->info->device, "Could not set SPI_CS_HIGH\n");
 		return ret;
diff --git a/drivers/staging/fbtft/fb_watterott.c b/drivers/staging/fbtft/fb_watterott.c
index 88fb2c0132d5..8eae6ef25846 100644
--- a/drivers/staging/fbtft/fb_watterott.c
+++ b/drivers/staging/fbtft/fb_watterott.c
@@ -169,7 +169,7 @@ static int init_display(struct fbtft_par *par)
 	/* enable SPI interface by having CS and MOSI low during reset */
 	save_mode = par->spi->mode;
 	par->spi->mode |= SPI_CS_HIGH;
-	ret = par->spi->master->setup(par->spi); /* set CS inactive low */
+	ret = spi_setup(par->spi); /* set CS inactive low */
 	if (ret) {
 		dev_err(par->info->device, "Could not set SPI_CS_HIGH\n");
 		return ret;
@@ -180,7 +180,7 @@ static int init_display(struct fbtft_par *par)
 	par->fbtftops.reset(par);
 	mdelay(1000);
 	par->spi->mode = save_mode;
-	ret = par->spi->master->setup(par->spi);
+	ret = spi_setup(par->spi);
 	if (ret) {
 		dev_err(par->info->device, "Could not restore SPI mode\n");
 		return ret;
diff --git a/drivers/staging/fbtft/fbtft-core.c b/drivers/staging/fbtft/fbtft-core.c
index 23392eb6799e..7f5fa3d1cab0 100644
--- a/drivers/staging/fbtft/fbtft-core.c
+++ b/drivers/staging/fbtft/fbtft-core.c
@@ -1436,15 +1436,11 @@ int fbtft_probe_common(struct fbtft_display *display,
 
 	/* 9-bit SPI setup */
 	if (par->spi && display->buswidth == 9) {
-		par->spi->bits_per_word = 9;
-		ret = par->spi->master->setup(par->spi);
-		if (ret) {
+		if (par->spi->master->bits_per_word_mask & SPI_BPW_MASK(9)) {
+			par->spi->bits_per_word = 9;
+		} else {
 			dev_warn(&par->spi->dev,
 				"9-bit SPI not available, emulating using 8-bit.\n");
-			par->spi->bits_per_word = 8;
-			ret = par->spi->master->setup(par->spi);
-			if (ret)
-				goto out_release;
 			/* allocate buffer with room for dc bits */
 			par->extra = devm_kzalloc(par->info->device,
 				par->txbuf.len + (par->txbuf.len / 8) + 8,
diff --git a/drivers/staging/fbtft/flexfb.c b/drivers/staging/fbtft/flexfb.c
index c763efc5de7d..3f380a0086c3 100644
--- a/drivers/staging/fbtft/flexfb.c
+++ b/drivers/staging/fbtft/flexfb.c
@@ -463,15 +463,12 @@ static int flexfb_probe_common(struct spi_device *sdev,
 			}
 			par->fbtftops.write_register = fbtft_write_reg8_bus9;
 			par->fbtftops.write_vmem = fbtft_write_vmem16_bus9;
-			sdev->bits_per_word = 9;
-			ret = sdev->master->setup(sdev);
-			if (ret) {
+			if (par->spi->master->bits_per_word_mask
+			    & SPI_BPW_MASK(9)) {
+				par->spi->bits_per_word = 9;
+			} else {
 				dev_warn(dev,
 					"9-bit SPI not available, emulating using 8-bit.\n");
-				sdev->bits_per_word = 8;
-				ret = sdev->master->setup(sdev);
-				if (ret)
-					goto out_release;
 				/* allocate buffer with room for dc bits */
 				par->extra = devm_kzalloc(par->info->device,
 						par->txbuf.len + (par->txbuf.len / 8) + 8,
diff --git a/drivers/staging/lustre/README.txt b/drivers/staging/lustre/README.txt
index cf0ca50ff83b..0676243eea9e 100644
--- a/drivers/staging/lustre/README.txt
+++ b/drivers/staging/lustre/README.txt
@@ -14,10 +14,8 @@ Unlike shared disk storage cluster filesystems (e.g. OCFS2, GFS, GPFS),
 Lustre has independent Metadata and Data servers that clients can access
 in parallel to maximize performance.
 
-In order to use Lustre client you will need to download lustre client
-tools from
-https://downloads.hpdd.intel.com/public/lustre/latest-feature-release/
-the package name is lustre-client.
+In order to use Lustre client you will need to download the "lustre-client"
+package that contains the userspace tools from http://lustre.org/download/
 
 You will need to install and configure your Lustre servers separately.
 
@@ -76,12 +74,10 @@ Mount Options
 
 More Information
 ================
-You can get more information at
-OpenSFS website: http://lustre.opensfs.org/about/
-Intel HPDD wiki: https://wiki.hpdd.intel.com
+You can get more information at the Lustre website: http://wiki.lustre.org/
 
-Out of tree Lustre client and server code is available at:
-http://git.whamcloud.com/fs/lustre-release.git
+Source for the userspace tools and out-of-tree client and server code
+is available at: http://git.hpdd.intel.com/fs/lustre-release.git
 
 Latest binary packages:
-http://lustre.opensfs.org/download-lustre/
+http://lustre.org/download/
diff --git a/drivers/staging/most/Kconfig b/drivers/staging/most/Kconfig
index d50de03de7b9..0b9b9b539f70 100644
--- a/drivers/staging/most/Kconfig
+++ b/drivers/staging/most/Kconfig
@@ -1,5 +1,6 @@
 menuconfig MOST
         tristate "MOST driver"
+	depends on HAS_DMA
         select MOSTCORE
         default n
         ---help---
diff --git a/drivers/staging/most/hdm-dim2/Kconfig b/drivers/staging/most/hdm-dim2/Kconfig
index 1d4ad1d67758..fc548769479b 100644
--- a/drivers/staging/most/hdm-dim2/Kconfig
+++ b/drivers/staging/most/hdm-dim2/Kconfig
@@ -5,6 +5,7 @@
 config HDM_DIM2
 	tristate "DIM2 HDM"
 	depends on AIM_NETWORK
+	depends on HAS_IOMEM
 
 	---help---
 	  Say Y here if you want to connect via MediaLB to network transceiver.
diff --git a/drivers/staging/most/hdm-usb/Kconfig b/drivers/staging/most/hdm-usb/Kconfig
index a482c3fdf34b..ec1546312ee6 100644
--- a/drivers/staging/most/hdm-usb/Kconfig
+++ b/drivers/staging/most/hdm-usb/Kconfig
@@ -4,7 +4,7 @@
 
 config HDM_USB
 	tristate "USB HDM"
-	depends on USB
+	depends on USB && NET
 	select AIM_NETWORK
 	---help---
 	  Say Y here if you want to connect via USB to network tranceiver.
diff --git a/drivers/staging/most/mostcore/Kconfig b/drivers/staging/most/mostcore/Kconfig
index 38abf1b21b66..47172546d728 100644
--- a/drivers/staging/most/mostcore/Kconfig
+++ b/drivers/staging/most/mostcore/Kconfig
@@ -4,6 +4,7 @@
 
 config MOSTCORE
 	tristate "MOST Core"
+	depends on HAS_DMA
 
 	---help---
 	  Say Y here if you want to enable MOST support.
diff --git a/drivers/staging/unisys/visorbus/Makefile b/drivers/staging/unisys/visorbus/Makefile
index fa27ee5f336c..fc790e7592fc 100644
--- a/drivers/staging/unisys/visorbus/Makefile
+++ b/drivers/staging/unisys/visorbus/Makefile
@@ -10,4 +10,3 @@ visorbus-y += visorchipset.o
 visorbus-y += periodic_work.o
 
 ccflags-y += -Idrivers/staging/unisys/include
-ccflags-y += -Idrivers/staging/unisys/visorutil
diff --git a/drivers/staging/unisys/visorbus/visorbus_main.c b/drivers/staging/unisys/visorbus/visorbus_main.c
index 2309f5f2b238..a272b48bab28 100644
--- a/drivers/staging/unisys/visorbus/visorbus_main.c
+++ b/drivers/staging/unisys/visorbus/visorbus_main.c
@@ -37,6 +37,8 @@ static int visorbus_debugref;
 #define POLLJIFFIES_TESTWORK         100
 #define POLLJIFFIES_NORMALCHANNEL     10
 
+static int busreg_rc = -ENODEV; /* stores the result from bus registration */
+
 static int visorbus_uevent(struct device *xdev, struct kobj_uevent_env *env);
 static int visorbus_match(struct device *xdev, struct device_driver *xdrv);
 static void fix_vbus_dev_info(struct visor_device *visordev);
@@ -863,6 +865,9 @@ int visorbus_register_visor_driver(struct visor_driver *drv)
 {
 	int rc = 0;
 
+	if (busreg_rc < 0)
+		return -ENODEV; /*can't register on a nonexistent bus*/
+
 	drv->driver.name = drv->name;
 	drv->driver.bus = &visorbus_type;
 	drv->driver.probe = visordriver_probe_device;
@@ -885,6 +890,8 @@ int visorbus_register_visor_driver(struct visor_driver *drv)
 	if (rc < 0)
 		return rc;
 	rc = register_driver_attributes(drv);
+	if (rc < 0)
+		driver_unregister(&drv->driver);
 	return rc;
 }
 EXPORT_SYMBOL_GPL(visorbus_register_visor_driver);
@@ -1260,10 +1267,8 @@ remove_bus_instance(struct visor_device *dev)
 static int
 create_bus_type(void)
 {
-	int rc = 0;
-
-	rc = bus_register(&visorbus_type);
-	return rc;
+	busreg_rc = bus_register(&visorbus_type);
+	return busreg_rc;
 }
 
 /** Remove the one-and-only one instance of the visor bus type (visorbus_type).
diff --git a/drivers/staging/unisys/visornic/visornic_main.c b/drivers/staging/unisys/visornic/visornic_main.c
index 8c9da7ea7845..9d3c1e282062 100644
--- a/drivers/staging/unisys/visornic/visornic_main.c
+++ b/drivers/staging/unisys/visornic/visornic_main.c
@@ -1189,16 +1189,16 @@ visornic_rx(struct uiscmdrsp *cmdrsp)
 	spin_lock_irqsave(&devdata->priv_lock, flags);
 	atomic_dec(&devdata->num_rcvbuf_in_iovm);
 
-	/* update rcv stats - call it with priv_lock held */
-	devdata->net_stats.rx_packets++;
-	devdata->net_stats.rx_bytes = skb->len;
-
 	/* set length to how much was ACTUALLY received -
 	 * NOTE: rcv_done_len includes actual length of data rcvd
 	 * including ethhdr
 	 */
 	skb->len = cmdrsp->net.rcv.rcv_done_len;
 
+	/* update rcv stats - call it with priv_lock held */
+	devdata->net_stats.rx_packets++;
+	devdata->net_stats.rx_bytes += skb->len;
+
 	/* test enabled while holding lock */
 	if (!(devdata->enabled && devdata->enab_dis_acked)) {
 		/* don't process it unless we're in enable mode and until
@@ -1924,13 +1924,16 @@ static int visornic_probe(struct visor_device *dev)
 			"%s debugfs_create_dir %s failed\n",
 			__func__, netdev->name);
 		err = -ENOMEM;
-		goto cleanup_xmit_cmdrsp;
+		goto cleanup_register_netdev;
 	}
 
 	dev_info(&dev->device, "%s success netdev=%s\n",
 		 __func__, netdev->name);
 	return 0;
 
+cleanup_register_netdev:
+	unregister_netdev(netdev);
+
 cleanup_napi_add:
 	del_timer_sync(&devdata->irq_poll_timer);
 	netif_napi_del(&devdata->napi);
@@ -2128,8 +2131,9 @@ static int visornic_init(void)
 	if (!dev_num_pool)
 		goto cleanup_workqueue;
 
-	visorbus_register_visor_driver(&visornic_driver);
-	return 0;
+	err = visorbus_register_visor_driver(&visornic_driver);
+	if (!err)
+		return 0;
 
 cleanup_workqueue:
 	if (visornic_timeout_reset_workqueue) {
diff --git a/drivers/target/iscsi/iscsi_target_parameters.c b/drivers/target/iscsi/iscsi_target_parameters.c
index e8a52f7d6204..51d1734d5390 100644
--- a/drivers/target/iscsi/iscsi_target_parameters.c
+++ b/drivers/target/iscsi/iscsi_target_parameters.c
@@ -407,6 +407,7 @@ int iscsi_create_default_params(struct iscsi_param_list **param_list_ptr)
 			TYPERANGE_UTF8, USE_INITIAL_ONLY);
 	if (!param)
 		goto out;
+
 	/*
 	 * Extra parameters for ISER from RFC-5046
 	 */
@@ -496,9 +497,9 @@ int iscsi_set_keys_to_negotiate(
 		} else if (!strcmp(param->name, SESSIONTYPE)) {
 			SET_PSTATE_NEGOTIATE(param);
 		} else if (!strcmp(param->name, IFMARKER)) {
-			SET_PSTATE_NEGOTIATE(param);
+			SET_PSTATE_REJECT(param);
 		} else if (!strcmp(param->name, OFMARKER)) {
-			SET_PSTATE_NEGOTIATE(param);
+			SET_PSTATE_REJECT(param);
 		} else if (!strcmp(param->name, IFMARKINT)) {
 			SET_PSTATE_REJECT(param);
 		} else if (!strcmp(param->name, OFMARKINT)) {
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index dcc424ac35d4..88ea4e4f124b 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -62,22 +62,13 @@ transport_lookup_cmd_lun(struct se_cmd *se_cmd, u64 unpacked_lun)
 	struct se_session *se_sess = se_cmd->se_sess;
 	struct se_node_acl *nacl = se_sess->se_node_acl;
 	struct se_dev_entry *deve;
+	sense_reason_t ret = TCM_NO_SENSE;
 
 	rcu_read_lock();
 	deve = target_nacl_find_deve(nacl, unpacked_lun);
 	if (deve) {
 		atomic_long_inc(&deve->total_cmds);
 
-		if ((se_cmd->data_direction == DMA_TO_DEVICE) &&
-		    (deve->lun_flags & TRANSPORT_LUNFLAGS_READ_ONLY)) {
-			pr_err("TARGET_CORE[%s]: Detected WRITE_PROTECTED LUN"
-				" Access for 0x%08llx\n",
-				se_cmd->se_tfo->get_fabric_name(),
-				unpacked_lun);
-			rcu_read_unlock();
-			return TCM_WRITE_PROTECTED;
-		}
-
 		if (se_cmd->data_direction == DMA_TO_DEVICE)
 			atomic_long_add(se_cmd->data_length,
 					&deve->write_bytes);
@@ -93,6 +84,17 @@ transport_lookup_cmd_lun(struct se_cmd *se_cmd, u64 unpacked_lun)
 
 		percpu_ref_get(&se_lun->lun_ref);
 		se_cmd->lun_ref_active = true;
+
+		if ((se_cmd->data_direction == DMA_TO_DEVICE) &&
+		    (deve->lun_flags & TRANSPORT_LUNFLAGS_READ_ONLY)) {
+			pr_err("TARGET_CORE[%s]: Detected WRITE_PROTECTED LUN"
+				" Access for 0x%08llx\n",
+				se_cmd->se_tfo->get_fabric_name(),
+				unpacked_lun);
+			rcu_read_unlock();
+			ret = TCM_WRITE_PROTECTED;
+			goto ref_dev;
+		}
 	}
 	rcu_read_unlock();
 
@@ -109,12 +111,6 @@ transport_lookup_cmd_lun(struct se_cmd *se_cmd, u64 unpacked_lun)
 				unpacked_lun);
 			return TCM_NON_EXISTENT_LUN;
 		}
-		/*
-		 * Force WRITE PROTECT for virtual LUN 0
-		 */
-		if ((se_cmd->data_direction != DMA_FROM_DEVICE) &&
-		    (se_cmd->data_direction != DMA_NONE))
-			return TCM_WRITE_PROTECTED;
 
 		se_lun = se_sess->se_tpg->tpg_virt_lun0;
 		se_cmd->se_lun = se_sess->se_tpg->tpg_virt_lun0;
@@ -123,6 +119,15 @@ transport_lookup_cmd_lun(struct se_cmd *se_cmd, u64 unpacked_lun)
 
 		percpu_ref_get(&se_lun->lun_ref);
 		se_cmd->lun_ref_active = true;
+
+		/*
+		 * Force WRITE PROTECT for virtual LUN 0
+		 */
+		if ((se_cmd->data_direction != DMA_FROM_DEVICE) &&
+		    (se_cmd->data_direction != DMA_NONE)) {
+			ret = TCM_WRITE_PROTECTED;
+			goto ref_dev;
+		}
 	}
 	/*
 	 * RCU reference protected by percpu se_lun->lun_ref taken above that
@@ -130,6 +135,7 @@ transport_lookup_cmd_lun(struct se_cmd *se_cmd, u64 unpacked_lun)
 	 * pointer can be kfree_rcu() by the final se_lun->lun_group put via
 	 * target_core_fabric_configfs.c:target_fabric_port_release
 	 */
+ref_dev:
 	se_cmd->se_dev = rcu_dereference_raw(se_lun->lun_se_dev);
 	atomic_long_inc(&se_cmd->se_dev->num_cmds);
 
@@ -140,7 +146,7 @@ transport_lookup_cmd_lun(struct se_cmd *se_cmd, u64 unpacked_lun)
 		atomic_long_add(se_cmd->data_length,
 				&se_cmd->se_dev->read_bytes);
 
-	return 0;
+	return ret;
 }
 EXPORT_SYMBOL(transport_lookup_cmd_lun);
 
@@ -427,8 +433,6 @@ void core_disable_device_list_for_node(
 
 	hlist_del_rcu(&orig->link);
 	clear_bit(DEF_PR_REG_ACTIVE, &orig->deve_flags);
-	rcu_assign_pointer(orig->se_lun, NULL);
-	rcu_assign_pointer(orig->se_lun_acl, NULL);
 	orig->lun_flags = 0;
 	orig->creation_time = 0;
 	orig->attach_count--;
@@ -439,6 +443,9 @@ void core_disable_device_list_for_node(
 	kref_put(&orig->pr_kref, target_pr_kref_release);
 	wait_for_completion(&orig->pr_comp);
 
+	rcu_assign_pointer(orig->se_lun, NULL);
+	rcu_assign_pointer(orig->se_lun_acl, NULL);
+
 	kfree_rcu(orig, rcu_head);
 
 	core_scsi3_free_pr_reg_from_nacl(dev, nacl);
diff --git a/drivers/target/target_core_hba.c b/drivers/target/target_core_hba.c
index 9522960c7fdd..22390e0e046c 100644
--- a/drivers/target/target_core_hba.c
+++ b/drivers/target/target_core_hba.c
@@ -187,5 +187,5 @@ core_delete_hba(struct se_hba *hba)
 
 bool target_sense_desc_format(struct se_device *dev)
 {
-	return dev->transport->get_blocks(dev) > U32_MAX;
+	return (dev) ? dev->transport->get_blocks(dev) > U32_MAX : false;
 }
diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c
index 5a9982f5d5d6..0f19e11acac2 100644
--- a/drivers/target/target_core_iblock.c
+++ b/drivers/target/target_core_iblock.c
@@ -105,6 +105,8 @@ static int iblock_configure_device(struct se_device *dev)
 	mode = FMODE_READ|FMODE_EXCL;
 	if (!ib_dev->ibd_readonly)
 		mode |= FMODE_WRITE;
+	else
+		dev->dev_flags |= DF_READ_ONLY;
 
 	bd = blkdev_get_by_path(ib_dev->ibd_udev_path, mode, ib_dev);
 	if (IS_ERR(bd)) {
diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c
index 5ab7100de17e..e7933115087a 100644
--- a/drivers/target/target_core_pr.c
+++ b/drivers/target/target_core_pr.c
@@ -618,7 +618,7 @@ static struct t10_pr_registration *__core_scsi3_do_alloc_registration(
 	struct se_device *dev,
 	struct se_node_acl *nacl,
 	struct se_lun *lun,
-	struct se_dev_entry *deve,
+	struct se_dev_entry *dest_deve,
 	u64 mapped_lun,
 	unsigned char *isid,
 	u64 sa_res_key,
@@ -640,7 +640,29 @@ static struct t10_pr_registration *__core_scsi3_do_alloc_registration(
 	INIT_LIST_HEAD(&pr_reg->pr_reg_atp_mem_list);
 	atomic_set(&pr_reg->pr_res_holders, 0);
 	pr_reg->pr_reg_nacl = nacl;
-	pr_reg->pr_reg_deve = deve;
+	/*
+	 * For destination registrations for ALL_TG_PT=1 and SPEC_I_PT=1,
+	 * the se_dev_entry->pr_ref will have been already obtained by
+	 * core_get_se_deve_from_rtpi() or __core_scsi3_alloc_registration().
+	 *
+	 * Otherwise, locate se_dev_entry now and obtain a reference until
+	 * registration completes in __core_scsi3_add_registration().
+	 */
+	if (dest_deve) {
+		pr_reg->pr_reg_deve = dest_deve;
+	} else {
+		rcu_read_lock();
+		pr_reg->pr_reg_deve = target_nacl_find_deve(nacl, mapped_lun);
+		if (!pr_reg->pr_reg_deve) {
+			rcu_read_unlock();
+			pr_err("Unable to locate PR deve %s mapped_lun: %llu\n",
+				nacl->initiatorname, mapped_lun);
+			kmem_cache_free(t10_pr_reg_cache, pr_reg);
+			return NULL;
+		}
+		kref_get(&pr_reg->pr_reg_deve->pr_kref);
+		rcu_read_unlock();
+	}
 	pr_reg->pr_res_mapped_lun = mapped_lun;
 	pr_reg->pr_aptpl_target_lun = lun->unpacked_lun;
 	pr_reg->tg_pt_sep_rtpi = lun->lun_rtpi;
@@ -936,17 +958,29 @@ static int __core_scsi3_check_aptpl_registration(
 		    !(strcmp(pr_reg->pr_tport, t_port)) &&
 		     (pr_reg->pr_reg_tpgt == tpgt) &&
 		     (pr_reg->pr_aptpl_target_lun == target_lun)) {
+			/*
+			 * Obtain the ->pr_reg_deve pointer + reference, that
+			 * is released by __core_scsi3_add_registration() below.
+			 */
+			rcu_read_lock();
+			pr_reg->pr_reg_deve = target_nacl_find_deve(nacl, mapped_lun);
+			if (!pr_reg->pr_reg_deve) {
+				pr_err("Unable to locate PR APTPL %s mapped_lun:"
+					" %llu\n", nacl->initiatorname, mapped_lun);
+				rcu_read_unlock();
+				continue;
+			}
+			kref_get(&pr_reg->pr_reg_deve->pr_kref);
+			rcu_read_unlock();
 
 			pr_reg->pr_reg_nacl = nacl;
 			pr_reg->tg_pt_sep_rtpi = lun->lun_rtpi;
-
 			list_del(&pr_reg->pr_reg_aptpl_list);
 			spin_unlock(&pr_tmpl->aptpl_reg_lock);
 			/*
 			 * At this point all of the pointers in *pr_reg will
 			 * be setup, so go ahead and add the registration.
 			 */
-
 			__core_scsi3_add_registration(dev, nacl, pr_reg, 0, 0);
 			/*
 			 * If this registration is the reservation holder,
@@ -1044,18 +1078,11 @@ static void __core_scsi3_add_registration(
 
 	__core_scsi3_dump_registration(tfo, dev, nacl, pr_reg, register_type);
 	spin_unlock(&pr_tmpl->registration_lock);
-
-	rcu_read_lock();
-	deve = pr_reg->pr_reg_deve;
-	if (deve)
-		set_bit(DEF_PR_REG_ACTIVE, &deve->deve_flags);
-	rcu_read_unlock();
-
 	/*
 	 * Skip extra processing for ALL_TG_PT=0 or REGISTER_AND_MOVE.
 	 */
 	if (!pr_reg->pr_reg_all_tg_pt || register_move)
-		return;
+		goto out;
 	/*
 	 * Walk pr_reg->pr_reg_atp_list and add registrations for ALL_TG_PT=1
 	 * allocated in __core_scsi3_alloc_registration()
@@ -1075,19 +1102,31 @@ static void __core_scsi3_add_registration(
 		__core_scsi3_dump_registration(tfo, dev, nacl_tmp, pr_reg_tmp,
 					       register_type);
 		spin_unlock(&pr_tmpl->registration_lock);
-
+		/*
+		 * Drop configfs group dependency reference and deve->pr_kref
+		 * obtained from  __core_scsi3_alloc_registration() code.
+		 */
 		rcu_read_lock();
 		deve = pr_reg_tmp->pr_reg_deve;
-		if (deve)
+		if (deve) {
 			set_bit(DEF_PR_REG_ACTIVE, &deve->deve_flags);
+			core_scsi3_lunacl_undepend_item(deve);
+			pr_reg_tmp->pr_reg_deve = NULL;
+		}
 		rcu_read_unlock();
-
-		/*
-		 * Drop configfs group dependency reference from
-		 * __core_scsi3_alloc_registration()
-		 */
-		core_scsi3_lunacl_undepend_item(pr_reg_tmp->pr_reg_deve);
 	}
+out:
+	/*
+	 * Drop deve->pr_kref obtained in __core_scsi3_do_alloc_registration()
+	 */
+	rcu_read_lock();
+	deve = pr_reg->pr_reg_deve;
+	if (deve) {
+		set_bit(DEF_PR_REG_ACTIVE, &deve->deve_flags);
+		kref_put(&deve->pr_kref, target_pr_kref_release);
+		pr_reg->pr_reg_deve = NULL;
+	}
+	rcu_read_unlock();
 }
 
 static int core_scsi3_alloc_registration(
@@ -1785,9 +1824,11 @@ core_scsi3_decode_spec_i_port(
 			dest_node_acl->initiatorname, i_buf, (dest_se_deve) ?
 			dest_se_deve->mapped_lun : 0);
 
-		if (!dest_se_deve)
+		if (!dest_se_deve) {
+			kref_put(&local_pr_reg->pr_reg_deve->pr_kref,
+				 target_pr_kref_release);
 			continue;
-
+		}
 		core_scsi3_lunacl_undepend_item(dest_se_deve);
 		core_scsi3_nodeacl_undepend_item(dest_node_acl);
 		core_scsi3_tpg_undepend_item(dest_tpg);
@@ -1823,9 +1864,11 @@ out:
 
 		kmem_cache_free(t10_pr_reg_cache, dest_pr_reg);
 
-		if (!dest_se_deve)
+		if (!dest_se_deve) {
+			kref_put(&local_pr_reg->pr_reg_deve->pr_kref,
+				 target_pr_kref_release);
 			continue;
-
+		}
 		core_scsi3_lunacl_undepend_item(dest_se_deve);
 		core_scsi3_nodeacl_undepend_item(dest_node_acl);
 		core_scsi3_tpg_undepend_item(dest_tpg);
diff --git a/drivers/target/target_core_tpg.c b/drivers/target/target_core_tpg.c
index 2d0381dd105c..5fb9dd7f08bb 100644
--- a/drivers/target/target_core_tpg.c
+++ b/drivers/target/target_core_tpg.c
@@ -668,7 +668,10 @@ int core_tpg_add_lun(
 	list_add_tail(&lun->lun_dev_link, &dev->dev_sep_list);
 	spin_unlock(&dev->se_port_lock);
 
-	lun->lun_access = lun_access;
+	if (dev->dev_flags & DF_READ_ONLY)
+		lun->lun_access = TRANSPORT_LUNFLAGS_READ_ONLY;
+	else
+		lun->lun_access = lun_access;
 	if (!(dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE))
 		hlist_add_head_rcu(&lun->link, &tpg->tpg_lun_hlist);
 	mutex_unlock(&tpg->tpg_lun_mutex);
diff --git a/drivers/thermal/Kconfig b/drivers/thermal/Kconfig
index 039004400987..5aabc4bc0d75 100644
--- a/drivers/thermal/Kconfig
+++ b/drivers/thermal/Kconfig
@@ -163,7 +163,7 @@ config THERMAL_EMULATION
 
 config HISI_THERMAL
 	tristate "Hisilicon thermal driver"
-	depends on ARCH_HISI && CPU_THERMAL && OF
+	depends on (ARCH_HISI && CPU_THERMAL && OF) || COMPILE_TEST
 	help
 	  Enable this to plug hisilicon's thermal sensor driver into the Linux
 	  thermal framework. cpufreq is used as the cooling device to throttle
@@ -182,7 +182,7 @@ config IMX_THERMAL
 
 config SPEAR_THERMAL
 	bool "SPEAr thermal sensor driver"
-	depends on PLAT_SPEAR
+	depends on PLAT_SPEAR || COMPILE_TEST
 	depends on OF
 	help
 	  Enable this to plug the SPEAr thermal sensor driver into the Linux
@@ -190,7 +190,7 @@ config SPEAR_THERMAL
 
 config ROCKCHIP_THERMAL
 	tristate "Rockchip thermal driver"
-	depends on ARCH_ROCKCHIP
+	depends on ARCH_ROCKCHIP || COMPILE_TEST
 	depends on RESET_CONTROLLER
 	help
 	  Rockchip thermal driver provides support for Temperature sensor
@@ -208,7 +208,7 @@ config RCAR_THERMAL
 
 config KIRKWOOD_THERMAL
 	tristate "Temperature sensor on Marvell Kirkwood SoCs"
-	depends on MACH_KIRKWOOD
+	depends on MACH_KIRKWOOD || COMPILE_TEST
 	depends on OF
 	help
 	  Support for the Kirkwood thermal sensor driver into the Linux thermal
@@ -216,7 +216,7 @@ config KIRKWOOD_THERMAL
 
 config DOVE_THERMAL
 	tristate "Temperature sensor on Marvell Dove SoCs"
-	depends on ARCH_DOVE || MACH_DOVE
+	depends on ARCH_DOVE || MACH_DOVE || COMPILE_TEST
 	depends on OF
 	help
 	  Support for the Dove thermal sensor driver in the Linux thermal
@@ -234,7 +234,7 @@ config DB8500_THERMAL
 
 config ARMADA_THERMAL
 	tristate "Armada 370/XP thermal management"
-	depends on ARCH_MVEBU
+	depends on ARCH_MVEBU || COMPILE_TEST
 	depends on OF
 	help
 	  Enable this option if you want to have support for thermal management
@@ -349,11 +349,12 @@ config INTEL_PCH_THERMAL
 	  programmable trip points and other information.
 
 menu "Texas Instruments thermal drivers"
+depends on ARCH_HAS_BANDGAP || COMPILE_TEST
 source "drivers/thermal/ti-soc-thermal/Kconfig"
 endmenu
 
 menu "Samsung thermal drivers"
-depends on ARCH_EXYNOS
+depends on ARCH_EXYNOS || COMPILE_TEST
 source "drivers/thermal/samsung/Kconfig"
 endmenu
 
@@ -364,7 +365,7 @@ endmenu
 
 config QCOM_SPMI_TEMP_ALARM
 	tristate "Qualcomm SPMI PMIC Temperature Alarm"
-	depends on OF && SPMI && IIO
+	depends on OF && (SPMI || COMPILE_TEST) && IIO
 	select REGMAP_SPMI
 	help
 	  This enables a thermal sysfs driver for Qualcomm plug-and-play (QPNP)
diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c
index 620dcd405ff6..42c6f71bdcc1 100644
--- a/drivers/thermal/cpu_cooling.c
+++ b/drivers/thermal/cpu_cooling.c
@@ -262,7 +262,9 @@ static int cpufreq_thermal_notifier(struct notifier_block *nb,
  * efficiently.  Power is stored in mW, frequency in KHz.  The
  * resulting table is in ascending order.
  *
- * Return: 0 on success, -E* on error.
+ * Return: 0 on success, -EINVAL if there are no OPPs for any CPUs,
+ * -ENOMEM if we run out of memory or -EAGAIN if an OPP was
+ * added/enabled while the function was executing.
  */
 static int build_dyn_power_table(struct cpufreq_cooling_device *cpufreq_device,
 				 u32 capacitance)
@@ -273,8 +275,6 @@ static int build_dyn_power_table(struct cpufreq_cooling_device *cpufreq_device,
 	int num_opps = 0, cpu, i, ret = 0;
 	unsigned long freq;
 
-	rcu_read_lock();
-
 	for_each_cpu(cpu, &cpufreq_device->allowed_cpus) {
 		dev = get_cpu_device(cpu);
 		if (!dev) {
@@ -284,24 +284,20 @@ static int build_dyn_power_table(struct cpufreq_cooling_device *cpufreq_device,
 		}
 
 		num_opps = dev_pm_opp_get_opp_count(dev);
-		if (num_opps > 0) {
+		if (num_opps > 0)
 			break;
-		} else if (num_opps < 0) {
-			ret = num_opps;
-			goto unlock;
-		}
+		else if (num_opps < 0)
+			return num_opps;
 	}
 
-	if (num_opps == 0) {
-		ret = -EINVAL;
-		goto unlock;
-	}
+	if (num_opps == 0)
+		return -EINVAL;
 
 	power_table = kcalloc(num_opps, sizeof(*power_table), GFP_KERNEL);
-	if (!power_table) {
-		ret = -ENOMEM;
-		goto unlock;
-	}
+	if (!power_table)
+		return -ENOMEM;
+
+	rcu_read_lock();
 
 	for (freq = 0, i = 0;
 	     opp = dev_pm_opp_find_freq_ceil(dev, &freq), !IS_ERR(opp);
@@ -309,6 +305,12 @@ static int build_dyn_power_table(struct cpufreq_cooling_device *cpufreq_device,
 		u32 freq_mhz, voltage_mv;
 		u64 power;
 
+		if (i >= num_opps) {
+			rcu_read_unlock();
+			ret = -EAGAIN;
+			goto free_power_table;
+		}
+
 		freq_mhz = freq / 1000000;
 		voltage_mv = dev_pm_opp_get_voltage(opp) / 1000;
 
@@ -326,17 +328,22 @@ static int build_dyn_power_table(struct cpufreq_cooling_device *cpufreq_device,
 		power_table[i].power = power;
 	}
 
-	if (i == 0) {
+	rcu_read_unlock();
+
+	if (i != num_opps) {
 		ret = PTR_ERR(opp);
-		goto unlock;
+		goto free_power_table;
 	}
 
 	cpufreq_device->cpu_dev = dev;
 	cpufreq_device->dyn_power_table = power_table;
 	cpufreq_device->dyn_power_table_entries = i;
 
-unlock:
-	rcu_read_unlock();
+	return 0;
+
+free_power_table:
+	kfree(power_table);
+
 	return ret;
 }
 
@@ -847,7 +854,7 @@ __cpufreq_cooling_register(struct device_node *np,
 	ret = get_idr(&cpufreq_idr, &cpufreq_dev->id);
 	if (ret) {
 		cool_dev = ERR_PTR(ret);
-		goto free_table;
+		goto free_power_table;
 	}
 
 	snprintf(dev_name, sizeof(dev_name), "thermal-cpufreq-%d",
@@ -889,6 +896,8 @@ __cpufreq_cooling_register(struct device_node *np,
 
 remove_idr:
 	release_idr(&cpufreq_idr, cpufreq_dev->id);
+free_power_table:
+	kfree(cpufreq_dev->dyn_power_table);
 free_table:
 	kfree(cpufreq_dev->freq_table);
 free_time_in_idle_timestamp:
@@ -1039,6 +1048,7 @@ void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev)
 
 	thermal_cooling_device_unregister(cpufreq_dev->cool_dev);
 	release_idr(&cpufreq_idr, cpufreq_dev->id);
+	kfree(cpufreq_dev->dyn_power_table);
 	kfree(cpufreq_dev->time_in_idle_timestamp);
 	kfree(cpufreq_dev->time_in_idle);
 	kfree(cpufreq_dev->freq_table);
diff --git a/drivers/thermal/db8500_cpufreq_cooling.c b/drivers/thermal/db8500_cpufreq_cooling.c
index 607b62c7e611..e58bd0b658b5 100644
--- a/drivers/thermal/db8500_cpufreq_cooling.c
+++ b/drivers/thermal/db8500_cpufreq_cooling.c
@@ -72,6 +72,7 @@ static const struct of_device_id db8500_cpufreq_cooling_match[] = {
 	{ .compatible = "stericsson,db8500-cpufreq-cooling" },
 	{},
 };
+MODULE_DEVICE_TABLE(of, db8500_cpufreq_cooling_match);
 #endif
 
 static struct platform_driver db8500_cpufreq_cooling_driver = {
diff --git a/drivers/thermal/power_allocator.c b/drivers/thermal/power_allocator.c
index 9c8a7aad0252..7ff96270c933 100644
--- a/drivers/thermal/power_allocator.c
+++ b/drivers/thermal/power_allocator.c
@@ -24,6 +24,8 @@
 
 #include "thermal_core.h"
 
+#define INVALID_TRIP -1
+
 #define FRAC_BITS 10
 #define int_to_frac(x) ((x) << FRAC_BITS)
 #define frac_to_int(x) ((x) >> FRAC_BITS)
@@ -56,16 +58,21 @@ static inline s64 div_frac(s64 x, s64 y)
 
 /**
  * struct power_allocator_params - parameters for the power allocator governor
+ * @allocated_tzp:	whether we have allocated tzp for this thermal zone and
+ *			it needs to be freed on unbind
  * @err_integral:	accumulated error in the PID controller.
  * @prev_err:	error in the previous iteration of the PID controller.
  *		Used to calculate the derivative term.
  * @trip_switch_on:	first passive trip point of the thermal zone.  The
  *			governor switches on when this trip point is crossed.
+ *			If the thermal zone only has one passive trip point,
+ *			@trip_switch_on should be INVALID_TRIP.
  * @trip_max_desired_temperature:	last passive trip point of the thermal
  *					zone.  The temperature we are
  *					controlling for.
  */
 struct power_allocator_params {
+	bool allocated_tzp;
 	s64 err_integral;
 	s32 prev_err;
 	int trip_switch_on;
@@ -73,6 +80,88 @@ struct power_allocator_params {
 };
 
 /**
+ * estimate_sustainable_power() - Estimate the sustainable power of a thermal zone
+ * @tz: thermal zone we are operating in
+ *
+ * For thermal zones that don't provide a sustainable_power in their
+ * thermal_zone_params, estimate one.  Calculate it using the minimum
+ * power of all the cooling devices as that gives a valid value that
+ * can give some degree of functionality.  For optimal performance of
+ * this governor, provide a sustainable_power in the thermal zone's
+ * thermal_zone_params.
+ */
+static u32 estimate_sustainable_power(struct thermal_zone_device *tz)
+{
+	u32 sustainable_power = 0;
+	struct thermal_instance *instance;
+	struct power_allocator_params *params = tz->governor_data;
+
+	list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
+		struct thermal_cooling_device *cdev = instance->cdev;
+		u32 min_power;
+
+		if (instance->trip != params->trip_max_desired_temperature)
+			continue;
+
+		if (power_actor_get_min_power(cdev, tz, &min_power))
+			continue;
+
+		sustainable_power += min_power;
+	}
+
+	return sustainable_power;
+}
+
+/**
+ * estimate_pid_constants() - Estimate the constants for the PID controller
+ * @tz:		thermal zone for which to estimate the constants
+ * @sustainable_power:	sustainable power for the thermal zone
+ * @trip_switch_on:	trip point number for the switch on temperature
+ * @control_temp:	target temperature for the power allocator governor
+ * @force:	whether to force the update of the constants
+ *
+ * This function is used to update the estimation of the PID
+ * controller constants in struct thermal_zone_parameters.
+ * Sustainable power is provided in case it was estimated.  The
+ * estimated sustainable_power should not be stored in the
+ * thermal_zone_parameters so it has to be passed explicitly to this
+ * function.
+ *
+ * If @force is not set, the values in the thermal zone's parameters
+ * are preserved if they are not zero.  If @force is set, the values
+ * in thermal zone's parameters are overwritten.
+ */
+static void estimate_pid_constants(struct thermal_zone_device *tz,
+				   u32 sustainable_power, int trip_switch_on,
+				   int control_temp, bool force)
+{
+	int ret;
+	int switch_on_temp;
+	u32 temperature_threshold;
+
+	ret = tz->ops->get_trip_temp(tz, trip_switch_on, &switch_on_temp);
+	if (ret)
+		switch_on_temp = 0;
+
+	temperature_threshold = control_temp - switch_on_temp;
+
+	if (!tz->tzp->k_po || force)
+		tz->tzp->k_po = int_to_frac(sustainable_power) /
+			temperature_threshold;
+
+	if (!tz->tzp->k_pu || force)
+		tz->tzp->k_pu = int_to_frac(2 * sustainable_power) /
+			temperature_threshold;
+
+	if (!tz->tzp->k_i || force)
+		tz->tzp->k_i = int_to_frac(10) / 1000;
+	/*
+	 * The default for k_d and integral_cutoff is 0, so we can
+	 * leave them as they are.
+	 */
+}
+
+/**
  * pid_controller() - PID controller
  * @tz:	thermal zone we are operating in
  * @current_temp:	the current temperature in millicelsius
@@ -98,10 +187,20 @@ static u32 pid_controller(struct thermal_zone_device *tz,
 {
 	s64 p, i, d, power_range;
 	s32 err, max_power_frac;
+	u32 sustainable_power;
 	struct power_allocator_params *params = tz->governor_data;
 
 	max_power_frac = int_to_frac(max_allocatable_power);
 
+	if (tz->tzp->sustainable_power) {
+		sustainable_power = tz->tzp->sustainable_power;
+	} else {
+		sustainable_power = estimate_sustainable_power(tz);
+		estimate_pid_constants(tz, sustainable_power,
+				       params->trip_switch_on, control_temp,
+				       true);
+	}
+
 	err = control_temp - current_temp;
 	err = int_to_frac(err);
 
@@ -139,7 +238,7 @@ static u32 pid_controller(struct thermal_zone_device *tz,
 	power_range = p + i + d;
 
 	/* feed-forward the known sustainable dissipatable power */
-	power_range = tz->tzp->sustainable_power + frac_to_int(power_range);
+	power_range = sustainable_power + frac_to_int(power_range);
 
 	power_range = clamp(power_range, (s64)0, (s64)max_allocatable_power);
 
@@ -247,6 +346,11 @@ static int allocate_power(struct thermal_zone_device *tz,
 		}
 	}
 
+	if (!num_actors) {
+		ret = -ENODEV;
+		goto unlock;
+	}
+
 	/*
 	 * We need to allocate five arrays of the same size:
 	 * req_power, max_power, granted_power, extra_actor_power and
@@ -340,43 +444,66 @@ unlock:
 	return ret;
 }
 
-static int get_governor_trips(struct thermal_zone_device *tz,
-			      struct power_allocator_params *params)
+/**
+ * get_governor_trips() - get the number of the two trip points that are key for this governor
+ * @tz:	thermal zone to operate on
+ * @params:	pointer to private data for this governor
+ *
+ * The power allocator governor works optimally with two trips points:
+ * a "switch on" trip point and a "maximum desired temperature".  These
+ * are defined as the first and last passive trip points.
+ *
+ * If there is only one trip point, then that's considered to be the
+ * "maximum desired temperature" trip point and the governor is always
+ * on.  If there are no passive or active trip points, then the
+ * governor won't do anything.  In fact, its throttle function
+ * won't be called at all.
+ */
+static void get_governor_trips(struct thermal_zone_device *tz,
+			       struct power_allocator_params *params)
 {
-	int i, ret, last_passive;
+	int i, last_active, last_passive;
 	bool found_first_passive;
 
 	found_first_passive = false;
-	last_passive = -1;
-	ret = -EINVAL;
+	last_active = INVALID_TRIP;
+	last_passive = INVALID_TRIP;
 
 	for (i = 0; i < tz->trips; i++) {
 		enum thermal_trip_type type;
+		int ret;
 
 		ret = tz->ops->get_trip_type(tz, i, &type);
-		if (ret)
-			return ret;
+		if (ret) {
+			dev_warn(&tz->device,
+				 "Failed to get trip point %d type: %d\n", i,
+				 ret);
+			continue;
+		}
 
-		if (!found_first_passive) {
-			if (type == THERMAL_TRIP_PASSIVE) {
+		if (type == THERMAL_TRIP_PASSIVE) {
+			if (!found_first_passive) {
 				params->trip_switch_on = i;
 				found_first_passive = true;
+			} else  {
+				last_passive = i;
 			}
-		} else if (type == THERMAL_TRIP_PASSIVE) {
-			last_passive = i;
+		} else if (type == THERMAL_TRIP_ACTIVE) {
+			last_active = i;
 		} else {
 			break;
 		}
 	}
 
-	if (last_passive != -1) {
+	if (last_passive != INVALID_TRIP) {
 		params->trip_max_desired_temperature = last_passive;
-		ret = 0;
+	} else if (found_first_passive) {
+		params->trip_max_desired_temperature = params->trip_switch_on;
+		params->trip_switch_on = INVALID_TRIP;
 	} else {
-		ret = -EINVAL;
+		params->trip_switch_on = INVALID_TRIP;
+		params->trip_max_desired_temperature = last_active;
 	}
-
-	return ret;
 }
 
 static void reset_pid_controller(struct power_allocator_params *params)
@@ -405,60 +532,45 @@ static void allow_maximum_power(struct thermal_zone_device *tz)
  * power_allocator_bind() - bind the power_allocator governor to a thermal zone
  * @tz:	thermal zone to bind it to
  *
- * Check that the thermal zone is valid for this governor, that is, it
- * has two thermal trips.  If so, initialize the PID controller
- * parameters and bind it to the thermal zone.
+ * Initialize the PID controller parameters and bind it to the thermal
+ * zone.
  *
- * Return: 0 on success, -EINVAL if the trips were invalid or -ENOMEM
- * if we ran out of memory.
+ * Return: 0 on success, or -ENOMEM if we ran out of memory.
  */
 static int power_allocator_bind(struct thermal_zone_device *tz)
 {
 	int ret;
 	struct power_allocator_params *params;
-	int switch_on_temp, control_temp;
-	u32 temperature_threshold;
-
-	if (!tz->tzp || !tz->tzp->sustainable_power) {
-		dev_err(&tz->device,
-			"power_allocator: missing sustainable_power\n");
-		return -EINVAL;
-	}
+	int control_temp;
 
 	params = kzalloc(sizeof(*params), GFP_KERNEL);
 	if (!params)
 		return -ENOMEM;
 
-	ret = get_governor_trips(tz, params);
-	if (ret) {
-		dev_err(&tz->device,
-			"thermal zone %s has wrong trip setup for power allocator\n",
-			tz->type);
-		goto free;
-	}
+	if (!tz->tzp) {
+		tz->tzp = kzalloc(sizeof(*tz->tzp), GFP_KERNEL);
+		if (!tz->tzp) {
+			ret = -ENOMEM;
+			goto free_params;
+		}
 
-	ret = tz->ops->get_trip_temp(tz, params->trip_switch_on,
-				     &switch_on_temp);
-	if (ret)
-		goto free;
+		params->allocated_tzp = true;
+	}
 
-	ret = tz->ops->get_trip_temp(tz, params->trip_max_desired_temperature,
-				     &control_temp);
-	if (ret)
-		goto free;
+	if (!tz->tzp->sustainable_power)
+		dev_warn(&tz->device, "power_allocator: sustainable_power will be estimated\n");
 
-	temperature_threshold = control_temp - switch_on_temp;
+	get_governor_trips(tz, params);
 
-	tz->tzp->k_po = tz->tzp->k_po ?:
-		int_to_frac(tz->tzp->sustainable_power) / temperature_threshold;
-	tz->tzp->k_pu = tz->tzp->k_pu ?:
-		int_to_frac(2 * tz->tzp->sustainable_power) /
-		temperature_threshold;
-	tz->tzp->k_i = tz->tzp->k_i ?: int_to_frac(10) / 1000;
-	/*
-	 * The default for k_d and integral_cutoff is 0, so we can
-	 * leave them as they are.
-	 */
+	if (tz->trips > 0) {
+		ret = tz->ops->get_trip_temp(tz,
+					params->trip_max_desired_temperature,
+					&control_temp);
+		if (!ret)
+			estimate_pid_constants(tz, tz->tzp->sustainable_power,
+					       params->trip_switch_on,
+					       control_temp, false);
+	}
 
 	reset_pid_controller(params);
 
@@ -466,14 +578,23 @@ static int power_allocator_bind(struct thermal_zone_device *tz)
 
 	return 0;
 
-free:
+free_params:
 	kfree(params);
+
 	return ret;
 }
 
 static void power_allocator_unbind(struct thermal_zone_device *tz)
 {
+	struct power_allocator_params *params = tz->governor_data;
+
 	dev_dbg(&tz->device, "Unbinding from thermal zone %d\n", tz->id);
+
+	if (params->allocated_tzp) {
+		kfree(tz->tzp);
+		tz->tzp = NULL;
+	}
+
 	kfree(tz->governor_data);
 	tz->governor_data = NULL;
 }
@@ -499,13 +620,7 @@ static int power_allocator_throttle(struct thermal_zone_device *tz, int trip)
 
 	ret = tz->ops->get_trip_temp(tz, params->trip_switch_on,
 				     &switch_on_temp);
-	if (ret) {
-		dev_warn(&tz->device,
-			 "Failed to get switch on temperature: %d\n", ret);
-		return ret;
-	}
-
-	if (current_temp < switch_on_temp) {
+	if (!ret && (current_temp < switch_on_temp)) {
 		tz->passive = 0;
 		reset_pid_controller(params);
 		allow_maximum_power(tz);
diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 5e5fc7015c7f..d9e525cc9c1c 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -1013,6 +1013,34 @@ int power_actor_get_max_power(struct thermal_cooling_device *cdev,
 }
 
 /**
+ * power_actor_get_min_power() - get the mainimum power that a cdev can consume
+ * @cdev:	pointer to &thermal_cooling_device
+ * @tz:		a valid thermal zone device pointer
+ * @min_power:	pointer in which to store the minimum power
+ *
+ * Calculate the minimum power consumption in milliwatts that the
+ * cooling device can currently consume and store it in @min_power.
+ *
+ * Return: 0 on success, -EINVAL if @cdev doesn't support the
+ * power_actor API or -E* on other error.
+ */
+int power_actor_get_min_power(struct thermal_cooling_device *cdev,
+			      struct thermal_zone_device *tz, u32 *min_power)
+{
+	unsigned long max_state;
+	int ret;
+
+	if (!cdev_is_power_actor(cdev))
+		return -EINVAL;
+
+	ret = cdev->ops->get_max_state(cdev, &max_state);
+	if (ret)
+		return ret;
+
+	return cdev->ops->state2power(cdev, tz, max_state, min_power);
+}
+
+/**
  * power_actor_set_power() - limit the maximum power that a cooling device can consume
  * @cdev:	pointer to &thermal_cooling_device
  * @instance:	thermal instance to update
diff --git a/drivers/thermal/ti-soc-thermal/Kconfig b/drivers/thermal/ti-soc-thermal/Kconfig
index bd4c7beba679..cb6686ff09ae 100644
--- a/drivers/thermal/ti-soc-thermal/Kconfig
+++ b/drivers/thermal/ti-soc-thermal/Kconfig
@@ -1,7 +1,5 @@
 config TI_SOC_THERMAL
 	tristate "Texas Instruments SoCs temperature sensor driver"
-	depends on THERMAL
-	depends on ARCH_HAS_BANDGAP
 	help
 	  If you say yes here you get support for the Texas Instruments
 	  OMAP4460+ on die bandgap temperature sensor support. The register
@@ -24,7 +22,7 @@ config TI_THERMAL
 config OMAP4_THERMAL
 	bool "Texas Instruments OMAP4 thermal support"
 	depends on TI_SOC_THERMAL
-	depends on ARCH_OMAP4
+	depends on ARCH_OMAP4 || COMPILE_TEST
 	help
 	  If you say yes here you get thermal support for the Texas Instruments
 	  OMAP4 SoC family. The current chip supported are:
@@ -38,7 +36,7 @@ config OMAP4_THERMAL
 config OMAP5_THERMAL
 	bool "Texas Instruments OMAP5 thermal support"
 	depends on TI_SOC_THERMAL
-	depends on SOC_OMAP5
+	depends on SOC_OMAP5 || COMPILE_TEST
 	help
 	  If you say yes here you get thermal support for the Texas Instruments
 	  OMAP5 SoC family. The current chip supported are:
@@ -50,7 +48,7 @@ config OMAP5_THERMAL
 config DRA752_THERMAL
 	bool "Texas Instruments DRA752 thermal support"
 	depends on TI_SOC_THERMAL
-	depends on SOC_DRA7XX
+	depends on SOC_DRA7XX || COMPILE_TEST
 	help
 	  If you say yes here you get thermal support for the Texas Instruments
 	  DRA752 SoC family. The current chip supported are:
diff --git a/drivers/thunderbolt/nhi.c b/drivers/thunderbolt/nhi.c
index c68fe1222c16..20a41f7de76f 100644
--- a/drivers/thunderbolt/nhi.c
+++ b/drivers/thunderbolt/nhi.c
@@ -643,7 +643,7 @@ static struct pci_device_id nhi_ids[] = {
 	{
 		.class = PCI_CLASS_SYSTEM_OTHER << 8, .class_mask = ~0,
 		.vendor = PCI_VENDOR_ID_INTEL, .device = 0x156c,
-		.subvendor = 0x2222, .subdevice = 0x1111,
+		.subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID,
 	},
 	{ 0,}
 };
diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c
index 54e6c8ddef5d..b1e0ba3e525b 100644
--- a/drivers/tty/serial/8250/8250_port.c
+++ b/drivers/tty/serial/8250/8250_port.c
@@ -2910,3 +2910,5 @@ int serial8250_console_setup(struct uart_port *port, char *options, bool probe)
 }
 
 #endif /* CONFIG_SERIAL_8250_CONSOLE */
+
+MODULE_LICENSE("GPL");
diff --git a/drivers/usb/chipidea/ci_hdrc_imx.c b/drivers/usb/chipidea/ci_hdrc_imx.c
index 867e9f3f3859..dcc50c878159 100644
--- a/drivers/usb/chipidea/ci_hdrc_imx.c
+++ b/drivers/usb/chipidea/ci_hdrc_imx.c
@@ -61,7 +61,7 @@ static const struct of_device_id ci_hdrc_imx_dt_ids[] = {
 	{ .compatible = "fsl,imx27-usb", .data = &imx27_usb_data},
 	{ .compatible = "fsl,imx6q-usb", .data = &imx6q_usb_data},
 	{ .compatible = "fsl,imx6sl-usb", .data = &imx6sl_usb_data},
-	{ .compatible = "fsl,imx6sx-usb", .data = &imx6sl_usb_data},
+	{ .compatible = "fsl,imx6sx-usb", .data = &imx6sx_usb_data},
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, ci_hdrc_imx_dt_ids);
diff --git a/drivers/usb/chipidea/ci_hdrc_usb2.c b/drivers/usb/chipidea/ci_hdrc_usb2.c
index 9eae1a16cef9..4456d2cf80ff 100644
--- a/drivers/usb/chipidea/ci_hdrc_usb2.c
+++ b/drivers/usb/chipidea/ci_hdrc_usb2.c
@@ -12,6 +12,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/module.h>
 #include <linux/of.h>
+#include <linux/of_platform.h>
 #include <linux/phy/phy.h>
 #include <linux/platform_device.h>
 #include <linux/usb/chipidea.h>
@@ -30,18 +31,36 @@ static const struct ci_hdrc_platform_data ci_default_pdata = {
 	.flags		= CI_HDRC_DISABLE_STREAMING,
 };
 
+static struct ci_hdrc_platform_data ci_zynq_pdata = {
+	.capoffset	= DEF_CAPOFFSET,
+};
+
+static const struct of_device_id ci_hdrc_usb2_of_match[] = {
+	{ .compatible = "chipidea,usb2"},
+	{ .compatible = "xlnx,zynq-usb-2.20a", .data = &ci_zynq_pdata},
+	{ }
+};
+MODULE_DEVICE_TABLE(of, ci_hdrc_usb2_of_match);
+
 static int ci_hdrc_usb2_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct ci_hdrc_usb2_priv *priv;
 	struct ci_hdrc_platform_data *ci_pdata = dev_get_platdata(dev);
 	int ret;
+	const struct of_device_id *match;
 
 	if (!ci_pdata) {
 		ci_pdata = devm_kmalloc(dev, sizeof(*ci_pdata), GFP_KERNEL);
 		*ci_pdata = ci_default_pdata;	/* struct copy */
 	}
 
+	match = of_match_device(ci_hdrc_usb2_of_match, &pdev->dev);
+	if (match && match->data) {
+		/* struct copy */
+		*ci_pdata = *(struct ci_hdrc_platform_data *)match->data;
+	}
+
 	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
 		return -ENOMEM;
@@ -96,12 +115,6 @@ static int ci_hdrc_usb2_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static const struct of_device_id ci_hdrc_usb2_of_match[] = {
-	{ .compatible = "chipidea,usb2" },
-	{ }
-};
-MODULE_DEVICE_TABLE(of, ci_hdrc_usb2_of_match);
-
 static struct platform_driver ci_hdrc_usb2_driver = {
 	.probe	= ci_hdrc_usb2_probe,
 	.remove	= ci_hdrc_usb2_remove,
diff --git a/drivers/usb/chipidea/udc.c b/drivers/usb/chipidea/udc.c
index a637da25dda0..8223fe73ea85 100644
--- a/drivers/usb/chipidea/udc.c
+++ b/drivers/usb/chipidea/udc.c
@@ -656,6 +656,44 @@ __acquires(hwep->lock)
 	return 0;
 }
 
+static int _ep_set_halt(struct usb_ep *ep, int value, bool check_transfer)
+{
+	struct ci_hw_ep *hwep = container_of(ep, struct ci_hw_ep, ep);
+	int direction, retval = 0;
+	unsigned long flags;
+
+	if (ep == NULL || hwep->ep.desc == NULL)
+		return -EINVAL;
+
+	if (usb_endpoint_xfer_isoc(hwep->ep.desc))
+		return -EOPNOTSUPP;
+
+	spin_lock_irqsave(hwep->lock, flags);
+
+	if (value && hwep->dir == TX && check_transfer &&
+		!list_empty(&hwep->qh.queue) &&
+			!usb_endpoint_xfer_control(hwep->ep.desc)) {
+		spin_unlock_irqrestore(hwep->lock, flags);
+		return -EAGAIN;
+	}
+
+	direction = hwep->dir;
+	do {
+		retval |= hw_ep_set_halt(hwep->ci, hwep->num, hwep->dir, value);
+
+		if (!value)
+			hwep->wedge = 0;
+
+		if (hwep->type == USB_ENDPOINT_XFER_CONTROL)
+			hwep->dir = (hwep->dir == TX) ? RX : TX;
+
+	} while (hwep->dir != direction);
+
+	spin_unlock_irqrestore(hwep->lock, flags);
+	return retval;
+}
+
+
 /**
  * _gadget_stop_activity: stops all USB activity, flushes & disables all endpts
  * @gadget: gadget
@@ -1051,7 +1089,7 @@ __acquires(ci->lock)
 				num += ci->hw_ep_max / 2;
 
 			spin_unlock(&ci->lock);
-			err = usb_ep_set_halt(&ci->ci_hw_ep[num].ep);
+			err = _ep_set_halt(&ci->ci_hw_ep[num].ep, 1, false);
 			spin_lock(&ci->lock);
 			if (!err)
 				isr_setup_status_phase(ci);
@@ -1117,8 +1155,8 @@ delegate:
 
 	if (err < 0) {
 		spin_unlock(&ci->lock);
-		if (usb_ep_set_halt(&hwep->ep))
-			dev_err(ci->dev, "error: ep_set_halt\n");
+		if (_ep_set_halt(&hwep->ep, 1, false))
+			dev_err(ci->dev, "error: _ep_set_halt\n");
 		spin_lock(&ci->lock);
 	}
 }
@@ -1149,9 +1187,9 @@ __acquires(ci->lock)
 					err = isr_setup_status_phase(ci);
 				if (err < 0) {
 					spin_unlock(&ci->lock);
-					if (usb_ep_set_halt(&hwep->ep))
+					if (_ep_set_halt(&hwep->ep, 1, false))
 						dev_err(ci->dev,
-							"error: ep_set_halt\n");
+						"error: _ep_set_halt\n");
 					spin_lock(&ci->lock);
 				}
 			}
@@ -1397,41 +1435,7 @@ static int ep_dequeue(struct usb_ep *ep, struct usb_request *req)
  */
 static int ep_set_halt(struct usb_ep *ep, int value)
 {
-	struct ci_hw_ep *hwep = container_of(ep, struct ci_hw_ep, ep);
-	int direction, retval = 0;
-	unsigned long flags;
-
-	if (ep == NULL || hwep->ep.desc == NULL)
-		return -EINVAL;
-
-	if (usb_endpoint_xfer_isoc(hwep->ep.desc))
-		return -EOPNOTSUPP;
-
-	spin_lock_irqsave(hwep->lock, flags);
-
-#ifndef STALL_IN
-	/* g_file_storage MS compliant but g_zero fails chapter 9 compliance */
-	if (value && hwep->type == USB_ENDPOINT_XFER_BULK && hwep->dir == TX &&
-	    !list_empty(&hwep->qh.queue)) {
-		spin_unlock_irqrestore(hwep->lock, flags);
-		return -EAGAIN;
-	}
-#endif
-
-	direction = hwep->dir;
-	do {
-		retval |= hw_ep_set_halt(hwep->ci, hwep->num, hwep->dir, value);
-
-		if (!value)
-			hwep->wedge = 0;
-
-		if (hwep->type == USB_ENDPOINT_XFER_CONTROL)
-			hwep->dir = (hwep->dir == TX) ? RX : TX;
-
-	} while (hwep->dir != direction);
-
-	spin_unlock_irqrestore(hwep->lock, flags);
-	return retval;
+	return _ep_set_halt(ep, value, true);
 }
 
 /**
diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c
index b2a540b43f97..b9ddf0c1ffe5 100644
--- a/drivers/usb/core/config.c
+++ b/drivers/usb/core/config.c
@@ -112,7 +112,7 @@ static void usb_parse_ss_endpoint_companion(struct device *ddev, int cfgno,
 				cfgno, inum, asnum, ep->desc.bEndpointAddress);
 		ep->ss_ep_comp.bmAttributes = 16;
 	} else if (usb_endpoint_xfer_isoc(&ep->desc) &&
-			desc->bmAttributes > 2) {
+		   USB_SS_MULT(desc->bmAttributes) > 3) {
 		dev_warn(ddev, "Isoc endpoint has Mult of %d in "
 				"config %d interface %d altsetting %d ep %d: "
 				"setting to 3\n", desc->bmAttributes + 1,
@@ -121,7 +121,8 @@ static void usb_parse_ss_endpoint_companion(struct device *ddev, int cfgno,
 	}
 
 	if (usb_endpoint_xfer_isoc(&ep->desc))
-		max_tx = (desc->bMaxBurst + 1) * (desc->bmAttributes + 1) *
+		max_tx = (desc->bMaxBurst + 1) *
+			(USB_SS_MULT(desc->bmAttributes)) *
 			usb_endpoint_maxp(&ep->desc);
 	else if (usb_endpoint_xfer_int(&ep->desc))
 		max_tx = usb_endpoint_maxp(&ep->desc) *
diff --git a/drivers/usb/dwc3/dwc3-omap.c b/drivers/usb/dwc3/dwc3-omap.c
index a5a1b7c45743..22e9606d8e08 100644
--- a/drivers/usb/dwc3/dwc3-omap.c
+++ b/drivers/usb/dwc3/dwc3-omap.c
@@ -514,8 +514,6 @@ static int dwc3_omap_probe(struct platform_device *pdev)
 		goto err1;
 	}
 
-	dwc3_omap_enable_irqs(omap);
-
 	ret = dwc3_omap_extcon_register(omap);
 	if (ret < 0)
 		goto err2;
@@ -526,6 +524,8 @@ static int dwc3_omap_probe(struct platform_device *pdev)
 		goto err3;
 	}
 
+	dwc3_omap_enable_irqs(omap);
+
 	return 0;
 
 err3:
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 0c25704dcb6b..1e8bdf817811 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -2665,8 +2665,6 @@ static irqreturn_t dwc3_interrupt(int irq, void *_dwc)
 	int				i;
 	irqreturn_t			ret = IRQ_NONE;
 
-	spin_lock(&dwc->lock);
-
 	for (i = 0; i < dwc->num_event_buffers; i++) {
 		irqreturn_t status;
 
@@ -2675,8 +2673,6 @@ static irqreturn_t dwc3_interrupt(int irq, void *_dwc)
 			ret = status;
 	}
 
-	spin_unlock(&dwc->lock);
-
 	return ret;
 }
 
diff --git a/drivers/usb/gadget/epautoconf.c b/drivers/usb/gadget/epautoconf.c
index 978435a51038..6399c106a3a5 100644
--- a/drivers/usb/gadget/epautoconf.c
+++ b/drivers/usb/gadget/epautoconf.c
@@ -186,6 +186,7 @@ void usb_ep_autoconfig_reset (struct usb_gadget *gadget)
 
 	list_for_each_entry (ep, &gadget->ep_list, ep_list) {
 		ep->claimed = false;
+		ep->driver_data = NULL;
 	}
 	gadget->in_epnum = 0;
 	gadget->out_epnum = 0;
diff --git a/drivers/usb/gadget/udc/amd5536udc.c b/drivers/usb/gadget/udc/amd5536udc.c
index fdacddb18c00..175ca93fe5e2 100644
--- a/drivers/usb/gadget/udc/amd5536udc.c
+++ b/drivers/usb/gadget/udc/amd5536udc.c
@@ -3138,8 +3138,8 @@ static void udc_pci_remove(struct pci_dev *pdev)
 	writel(AMD_BIT(UDC_DEVCFG_SOFTRESET), &dev->regs->cfg);
 	if (dev->irq_registered)
 		free_irq(pdev->irq, dev);
-	if (dev->regs)
-		iounmap(dev->regs);
+	if (dev->virt_addr)
+		iounmap(dev->virt_addr);
 	if (dev->mem_region)
 		release_mem_region(pci_resource_start(pdev, 0),
 				pci_resource_len(pdev, 0));
@@ -3226,17 +3226,13 @@ static int udc_pci_probe(
 
 	/* init */
 	dev = kzalloc(sizeof(struct udc), GFP_KERNEL);
-	if (!dev) {
-		retval = -ENOMEM;
-		goto finished;
-	}
+	if (!dev)
+		return -ENOMEM;
 
 	/* pci setup */
 	if (pci_enable_device(pdev) < 0) {
-		kfree(dev);
-		dev = NULL;
 		retval = -ENODEV;
-		goto finished;
+		goto err_pcidev;
 	}
 	dev->active = 1;
 
@@ -3246,28 +3242,22 @@ static int udc_pci_probe(
 
 	if (!request_mem_region(resource, len, name)) {
 		dev_dbg(&pdev->dev, "pci device used already\n");
-		kfree(dev);
-		dev = NULL;
 		retval = -EBUSY;
-		goto finished;
+		goto err_memreg;
 	}
 	dev->mem_region = 1;
 
 	dev->virt_addr = ioremap_nocache(resource, len);
 	if (dev->virt_addr == NULL) {
 		dev_dbg(&pdev->dev, "start address cannot be mapped\n");
-		kfree(dev);
-		dev = NULL;
 		retval = -EFAULT;
-		goto finished;
+		goto err_ioremap;
 	}
 
 	if (!pdev->irq) {
 		dev_err(&pdev->dev, "irq not set\n");
-		kfree(dev);
-		dev = NULL;
 		retval = -ENODEV;
-		goto finished;
+		goto err_irq;
 	}
 
 	spin_lock_init(&dev->lock);
@@ -3283,10 +3273,8 @@ static int udc_pci_probe(
 
 	if (request_irq(pdev->irq, udc_irq, IRQF_SHARED, name, dev) != 0) {
 		dev_dbg(&pdev->dev, "request_irq(%d) fail\n", pdev->irq);
-		kfree(dev);
-		dev = NULL;
 		retval = -EBUSY;
-		goto finished;
+		goto err_irq;
 	}
 	dev->irq_registered = 1;
 
@@ -3314,8 +3302,17 @@ static int udc_pci_probe(
 		return 0;
 
 finished:
-	if (dev)
-		udc_pci_remove(pdev);
+	udc_pci_remove(pdev);
+	return retval;
+
+err_irq:
+	iounmap(dev->virt_addr);
+err_ioremap:
+	release_mem_region(resource, len);
+err_memreg:
+	pci_disable_device(pdev);
+err_pcidev:
+	kfree(dev);
 	return retval;
 }
 
diff --git a/drivers/usb/gadget/udc/atmel_usba_udc.c b/drivers/usb/gadget/udc/atmel_usba_udc.c
index 3dfada8d6061..f0f2b066ac08 100644
--- a/drivers/usb/gadget/udc/atmel_usba_udc.c
+++ b/drivers/usb/gadget/udc/atmel_usba_udc.c
@@ -2002,6 +2002,17 @@ static struct usba_ep * atmel_udc_of_init(struct platform_device *pdev,
 		ep->udc = udc;
 		INIT_LIST_HEAD(&ep->queue);
 
+		if (ep->index == 0) {
+			ep->ep.caps.type_control = true;
+		} else {
+			ep->ep.caps.type_iso = ep->can_isoc;
+			ep->ep.caps.type_bulk = true;
+			ep->ep.caps.type_int = true;
+		}
+
+		ep->ep.caps.dir_in = true;
+		ep->ep.caps.dir_out = true;
+
 		if (i)
 			list_add_tail(&ep->ep.ep_list, &udc->gadget.ep_list);
 
diff --git a/drivers/usb/gadget/udc/bdc/bdc_core.c b/drivers/usb/gadget/udc/bdc/bdc_core.c
index 5c8f4effb62a..ccb9c213cc9f 100644
--- a/drivers/usb/gadget/udc/bdc/bdc_core.c
+++ b/drivers/usb/gadget/udc/bdc/bdc_core.c
@@ -324,8 +324,7 @@ static void bdc_mem_free(struct bdc *bdc)
 				bdc->scratchpad.buff, bdc->scratchpad.sp_dma);
 
 	/* Destroy the dma pools */
-	if (bdc->bd_table_pool)
-		dma_pool_destroy(bdc->bd_table_pool);
+	dma_pool_destroy(bdc->bd_table_pool);
 
 	/* Free the bdc_ep array */
 	kfree(bdc->bdc_ep_array);
diff --git a/drivers/usb/gadget/udc/dummy_hcd.c b/drivers/usb/gadget/udc/dummy_hcd.c
index 1379ad40d864..27af0f008b57 100644
--- a/drivers/usb/gadget/udc/dummy_hcd.c
+++ b/drivers/usb/gadget/udc/dummy_hcd.c
@@ -1348,6 +1348,7 @@ static int transfer(struct dummy_hcd *dum_hcd, struct urb *urb,
 {
 	struct dummy		*dum = dum_hcd->dum;
 	struct dummy_request	*req;
+	int			sent = 0;
 
 top:
 	/* if there's no request queued, the device is NAKing; return */
@@ -1385,12 +1386,15 @@ top:
 			if (len == 0)
 				break;
 
-			/* use an extra pass for the final short packet */
-			if (len > ep->ep.maxpacket) {
-				rescan = 1;
-				len -= (len % ep->ep.maxpacket);
+			/* send multiple of maxpacket first, then remainder */
+			if (len >= ep->ep.maxpacket) {
+				is_short = 0;
+				if (len % ep->ep.maxpacket)
+					rescan = 1;
+				len -= len % ep->ep.maxpacket;
+			} else {
+				is_short = 1;
 			}
-			is_short = (len % ep->ep.maxpacket) != 0;
 
 			len = dummy_perform_transfer(urb, req, len);
 
@@ -1399,6 +1403,7 @@ top:
 				req->req.status = len;
 			} else {
 				limit -= len;
+				sent += len;
 				urb->actual_length += len;
 				req->req.actual += len;
 			}
@@ -1421,7 +1426,7 @@ top:
 					*status = -EOVERFLOW;
 				else
 					*status = 0;
-			} else if (!to_host) {
+			} else {
 				*status = 0;
 				if (host_len > dev_len)
 					req->req.status = -EOVERFLOW;
@@ -1429,15 +1434,24 @@ top:
 					req->req.status = 0;
 			}
 
-		/* many requests terminate without a short packet */
+		/*
+		 * many requests terminate without a short packet.
+		 * send a zlp if demanded by flags.
+		 */
 		} else {
-			if (req->req.length == req->req.actual
-					&& !req->req.zero)
-				req->req.status = 0;
-			if (urb->transfer_buffer_length == urb->actual_length
-					&& !(urb->transfer_flags
-						& URB_ZERO_PACKET))
-				*status = 0;
+			if (req->req.length == req->req.actual) {
+				if (req->req.zero && to_host)
+					rescan = 1;
+				else
+					req->req.status = 0;
+			}
+			if (urb->transfer_buffer_length == urb->actual_length) {
+				if (urb->transfer_flags & URB_ZERO_PACKET &&
+				    !to_host)
+					rescan = 1;
+				else
+					*status = 0;
+			}
 		}
 
 		/* device side completion --> continuable */
@@ -1460,7 +1474,7 @@ top:
 		if (rescan)
 			goto top;
 	}
-	return limit;
+	return sent;
 }
 
 static int periodic_bytes(struct dummy *dum, struct dummy_ep *ep)
@@ -1890,7 +1904,7 @@ restart:
 		default:
 treat_control_like_bulk:
 			ep->last_io = jiffies;
-			total = transfer(dum_hcd, urb, ep, limit, &status);
+			total -= transfer(dum_hcd, urb, ep, limit, &status);
 			break;
 		}
 
diff --git a/drivers/usb/gadget/udc/gr_udc.c b/drivers/usb/gadget/udc/gr_udc.c
index 8aa2593c2c36..b9429bc42511 100644
--- a/drivers/usb/gadget/udc/gr_udc.c
+++ b/drivers/usb/gadget/udc/gr_udc.c
@@ -2117,8 +2117,7 @@ static int gr_remove(struct platform_device *pdev)
 		return -EBUSY;
 
 	gr_dfs_delete(dev);
-	if (dev->desc_pool)
-		dma_pool_destroy(dev->desc_pool);
+	dma_pool_destroy(dev->desc_pool);
 	platform_set_drvdata(pdev, NULL);
 
 	gr_free_request(&dev->epi[0].ep, &dev->ep0reqi->req);
diff --git a/drivers/usb/gadget/udc/mv_u3d_core.c b/drivers/usb/gadget/udc/mv_u3d_core.c
index 4c489692745e..dafe74eb9ade 100644
--- a/drivers/usb/gadget/udc/mv_u3d_core.c
+++ b/drivers/usb/gadget/udc/mv_u3d_core.c
@@ -1767,8 +1767,7 @@ static int mv_u3d_remove(struct platform_device *dev)
 	usb_del_gadget_udc(&u3d->gadget);
 
 	/* free memory allocated in probe */
-	if (u3d->trb_pool)
-		dma_pool_destroy(u3d->trb_pool);
+	dma_pool_destroy(u3d->trb_pool);
 
 	if (u3d->ep_context)
 		dma_free_coherent(&dev->dev, u3d->ep_context_size,
diff --git a/drivers/usb/gadget/udc/mv_udc_core.c b/drivers/usb/gadget/udc/mv_udc_core.c
index 339af51df57d..81b6229c7805 100644
--- a/drivers/usb/gadget/udc/mv_udc_core.c
+++ b/drivers/usb/gadget/udc/mv_udc_core.c
@@ -2100,8 +2100,7 @@ static int mv_udc_remove(struct platform_device *pdev)
 	}
 
 	/* free memory allocated in probe */
-	if (udc->dtd_pool)
-		dma_pool_destroy(udc->dtd_pool);
+	dma_pool_destroy(udc->dtd_pool);
 
 	if (udc->ep_dqh)
 		dma_free_coherent(&pdev->dev, udc->ep_dqh_size,
diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c
index 9a8c936cd42c..41f841fa6c4d 100644
--- a/drivers/usb/host/xhci-mem.c
+++ b/drivers/usb/host/xhci-mem.c
@@ -1498,10 +1498,10 @@ int xhci_endpoint_init(struct xhci_hcd *xhci,
 	 * use Event Data TRBs, and we don't chain in a link TRB on short
 	 * transfers, we're basically dividing by 1.
 	 *
-	 * xHCI 1.0 specification indicates that the Average TRB Length should
-	 * be set to 8 for control endpoints.
+	 * xHCI 1.0 and 1.1 specification indicates that the Average TRB Length
+	 * should be set to 8 for control endpoints.
 	 */
-	if (usb_endpoint_xfer_control(&ep->desc) && xhci->hci_version == 0x100)
+	if (usb_endpoint_xfer_control(&ep->desc) && xhci->hci_version >= 0x100)
 		ep_ctx->tx_info |= cpu_to_le32(AVG_TRB_LENGTH_FOR_EP(8));
 	else
 		ep_ctx->tx_info |=
@@ -1792,8 +1792,7 @@ void xhci_mem_cleanup(struct xhci_hcd *xhci)
 	int size;
 	int i, j, num_ports;
 
-	if (timer_pending(&xhci->cmd_timer))
-		del_timer_sync(&xhci->cmd_timer);
+	del_timer_sync(&xhci->cmd_timer);
 
 	/* Free the Event Ring Segment Table and the actual Event Ring */
 	size = sizeof(struct xhci_erst_entry)*(xhci->erst.num_entries);
@@ -2321,6 +2320,10 @@ int xhci_mem_init(struct xhci_hcd *xhci, gfp_t flags)
 
 	INIT_LIST_HEAD(&xhci->cmd_list);
 
+	/* init command timeout timer */
+	setup_timer(&xhci->cmd_timer, xhci_handle_command_timeout,
+		    (unsigned long)xhci);
+
 	page_size = readl(&xhci->op_regs->page_size);
 	xhci_dbg_trace(xhci, trace_xhci_dbg_init,
 			"Supported page size register = 0x%x", page_size);
@@ -2505,10 +2508,6 @@ int xhci_mem_init(struct xhci_hcd *xhci, gfp_t flags)
 			"Wrote ERST address to ir_set 0.");
 	xhci_print_ir_set(xhci, 0);
 
-	/* init command timeout timer */
-	setup_timer(&xhci->cmd_timer, xhci_handle_command_timeout,
-		    (unsigned long)xhci);
-
 	/*
 	 * XXX: Might need to set the Interrupter Moderation Register to
 	 * something other than the default (~1ms minimum between interrupts).
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index 5590eac2b22d..c79d33676672 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -180,51 +180,6 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
 				"QUIRK: Resetting on resume");
 }
 
-/*
- * In some Intel xHCI controllers, in order to get D3 working,
- * through a vendor specific SSIC CONFIG register at offset 0x883c,
- * SSIC PORT need to be marked as "unused" before putting xHCI
- * into D3. After D3 exit, the SSIC port need to be marked as "used".
- * Without this change, xHCI might not enter D3 state.
- * Make sure PME works on some Intel xHCI controllers by writing 1 to clear
- * the Internal PME flag bit in vendor specific PMCTRL register at offset 0x80a4
- */
-static void xhci_pme_quirk(struct usb_hcd *hcd, bool suspend)
-{
-	struct xhci_hcd	*xhci = hcd_to_xhci(hcd);
-	struct pci_dev		*pdev = to_pci_dev(hcd->self.controller);
-	u32 val;
-	void __iomem *reg;
-
-	if (pdev->vendor == PCI_VENDOR_ID_INTEL &&
-		 pdev->device == PCI_DEVICE_ID_INTEL_CHERRYVIEW_XHCI) {
-
-		reg = (void __iomem *) xhci->cap_regs + PORT2_SSIC_CONFIG_REG2;
-
-		/* Notify SSIC that SSIC profile programming is not done */
-		val = readl(reg) & ~PROG_DONE;
-		writel(val, reg);
-
-		/* Mark SSIC port as unused(suspend) or used(resume) */
-		val = readl(reg);
-		if (suspend)
-			val |= SSIC_PORT_UNUSED;
-		else
-			val &= ~SSIC_PORT_UNUSED;
-		writel(val, reg);
-
-		/* Notify SSIC that SSIC profile programming is done */
-		val = readl(reg) | PROG_DONE;
-		writel(val, reg);
-		readl(reg);
-	}
-
-	reg = (void __iomem *) xhci->cap_regs + 0x80a4;
-	val = readl(reg);
-	writel(val | BIT(28), reg);
-	readl(reg);
-}
-
 #ifdef CONFIG_ACPI
 static void xhci_pme_acpi_rtd3_enable(struct pci_dev *dev)
 {
@@ -345,6 +300,51 @@ static void xhci_pci_remove(struct pci_dev *dev)
 }
 
 #ifdef CONFIG_PM
+/*
+ * In some Intel xHCI controllers, in order to get D3 working,
+ * through a vendor specific SSIC CONFIG register at offset 0x883c,
+ * SSIC PORT need to be marked as "unused" before putting xHCI
+ * into D3. After D3 exit, the SSIC port need to be marked as "used".
+ * Without this change, xHCI might not enter D3 state.
+ * Make sure PME works on some Intel xHCI controllers by writing 1 to clear
+ * the Internal PME flag bit in vendor specific PMCTRL register at offset 0x80a4
+ */
+static void xhci_pme_quirk(struct usb_hcd *hcd, bool suspend)
+{
+	struct xhci_hcd	*xhci = hcd_to_xhci(hcd);
+	struct pci_dev		*pdev = to_pci_dev(hcd->self.controller);
+	u32 val;
+	void __iomem *reg;
+
+	if (pdev->vendor == PCI_VENDOR_ID_INTEL &&
+		 pdev->device == PCI_DEVICE_ID_INTEL_CHERRYVIEW_XHCI) {
+
+		reg = (void __iomem *) xhci->cap_regs + PORT2_SSIC_CONFIG_REG2;
+
+		/* Notify SSIC that SSIC profile programming is not done */
+		val = readl(reg) & ~PROG_DONE;
+		writel(val, reg);
+
+		/* Mark SSIC port as unused(suspend) or used(resume) */
+		val = readl(reg);
+		if (suspend)
+			val |= SSIC_PORT_UNUSED;
+		else
+			val &= ~SSIC_PORT_UNUSED;
+		writel(val, reg);
+
+		/* Notify SSIC that SSIC profile programming is done */
+		val = readl(reg) | PROG_DONE;
+		writel(val, reg);
+		readl(reg);
+	}
+
+	reg = (void __iomem *) xhci->cap_regs + 0x80a4;
+	val = readl(reg);
+	writel(val | BIT(28), reg);
+	readl(reg);
+}
+
 static int xhci_pci_suspend(struct usb_hcd *hcd, bool do_wakeup)
 {
 	struct xhci_hcd	*xhci = hcd_to_xhci(hcd);
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index a47a1e897086..43291f93afeb 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -302,6 +302,15 @@ static int xhci_abort_cmd_ring(struct xhci_hcd *xhci)
 	ret = xhci_handshake(&xhci->op_regs->cmd_ring,
 			CMD_RING_RUNNING, 0, 5 * 1000 * 1000);
 	if (ret < 0) {
+		/* we are about to kill xhci, give it one more chance */
+		xhci_write_64(xhci, temp_64 | CMD_RING_ABORT,
+			      &xhci->op_regs->cmd_ring);
+		udelay(1000);
+		ret = xhci_handshake(&xhci->op_regs->cmd_ring,
+				     CMD_RING_RUNNING, 0, 3 * 1000 * 1000);
+		if (ret == 0)
+			return 0;
+
 		xhci_err(xhci, "Stopped the command ring failed, "
 				"maybe the host is dead\n");
 		xhci->xhc_state |= XHCI_STATE_DYING;
@@ -3461,8 +3470,8 @@ int xhci_queue_ctrl_tx(struct xhci_hcd *xhci, gfp_t mem_flags,
 	if (start_cycle == 0)
 		field |= 0x1;
 
-	/* xHCI 1.0 6.4.1.2.1: Transfer Type field */
-	if (xhci->hci_version == 0x100) {
+	/* xHCI 1.0/1.1 6.4.1.2.1: Transfer Type field */
+	if (xhci->hci_version >= 0x100) {
 		if (urb->transfer_buffer_length > 0) {
 			if (setup->bRequestType & USB_DIR_IN)
 				field |= TRB_TX_TYPE(TRB_DATA_IN);
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 6b0f4a47e402..9957bd96d4bc 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -146,7 +146,8 @@ static int xhci_start(struct xhci_hcd *xhci)
 				"waited %u microseconds.\n",
 				XHCI_MAX_HALT_USEC);
 	if (!ret)
-		xhci->xhc_state &= ~XHCI_STATE_HALTED;
+		xhci->xhc_state &= ~(XHCI_STATE_HALTED | XHCI_STATE_DYING);
+
 	return ret;
 }
 
@@ -654,15 +655,6 @@ int xhci_run(struct usb_hcd *hcd)
 }
 EXPORT_SYMBOL_GPL(xhci_run);
 
-static void xhci_only_stop_hcd(struct usb_hcd *hcd)
-{
-	struct xhci_hcd *xhci = hcd_to_xhci(hcd);
-
-	spin_lock_irq(&xhci->lock);
-	xhci_halt(xhci);
-	spin_unlock_irq(&xhci->lock);
-}
-
 /*
  * Stop xHCI driver.
  *
@@ -677,12 +669,14 @@ void xhci_stop(struct usb_hcd *hcd)
 	u32 temp;
 	struct xhci_hcd *xhci = hcd_to_xhci(hcd);
 
-	if (!usb_hcd_is_primary_hcd(hcd)) {
-		xhci_only_stop_hcd(xhci->shared_hcd);
+	if (xhci->xhc_state & XHCI_STATE_HALTED)
 		return;
-	}
 
+	mutex_lock(&xhci->mutex);
 	spin_lock_irq(&xhci->lock);
+	xhci->xhc_state |= XHCI_STATE_HALTED;
+	xhci->cmd_ring_state = CMD_RING_STATE_STOPPED;
+
 	/* Make sure the xHC is halted for a USB3 roothub
 	 * (xhci_stop() could be called as part of failed init).
 	 */
@@ -717,6 +711,7 @@ void xhci_stop(struct usb_hcd *hcd)
 	xhci_dbg_trace(xhci, trace_xhci_dbg_init,
 			"xhci_stop completed - status = %x",
 			readl(&xhci->op_regs->status));
+	mutex_unlock(&xhci->mutex);
 }
 
 /*
@@ -3793,6 +3788,9 @@ static int xhci_setup_device(struct usb_hcd *hcd, struct usb_device *udev,
 
 	mutex_lock(&xhci->mutex);
 
+	if (xhci->xhc_state)	/* dying or halted */
+		goto out;
+
 	if (!udev->slot_id) {
 		xhci_dbg_trace(xhci, trace_xhci_dbg_address,
 				"Bad Slot ID %d", udev->slot_id);
diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c
index 514a6cdaeff6..4a518ff12310 100644
--- a/drivers/usb/musb/musb_core.c
+++ b/drivers/usb/musb/musb_core.c
@@ -1051,6 +1051,7 @@ void musb_start(struct musb *musb)
 	 * (c) peripheral initiates, using SRP
 	 */
 	if (musb->port_mode != MUSB_PORT_MODE_HOST &&
+			musb->xceiv->otg->state != OTG_STATE_A_WAIT_BCON &&
 			(devctl & MUSB_DEVCTL_VBUS) == MUSB_DEVCTL_VBUS) {
 		musb->is_active = 1;
 	} else {
@@ -2448,6 +2449,9 @@ static int musb_suspend(struct device *dev)
 	struct musb	*musb = dev_to_musb(dev);
 	unsigned long	flags;
 
+	musb_platform_disable(musb);
+	musb_generic_disable(musb);
+
 	spin_lock_irqsave(&musb->lock, flags);
 
 	if (is_peripheral_active(musb)) {
@@ -2501,6 +2505,9 @@ static int musb_resume(struct device *dev)
 	pm_runtime_disable(dev);
 	pm_runtime_set_active(dev);
 	pm_runtime_enable(dev);
+
+	musb_start(musb);
+
 	return 0;
 }
 
diff --git a/drivers/usb/musb/musb_cppi41.c b/drivers/usb/musb/musb_cppi41.c
index d07cafb7d5f5..e499b862a946 100644
--- a/drivers/usb/musb/musb_cppi41.c
+++ b/drivers/usb/musb/musb_cppi41.c
@@ -551,6 +551,9 @@ static int cppi41_dma_channel_abort(struct dma_channel *channel)
 	} else {
 		cppi41_set_autoreq_mode(cppi41_channel, EP_MODE_AUTOREQ_NONE);
 
+		/* delay to drain to cppi dma pipeline for isoch */
+		udelay(250);
+
 		csr = musb_readw(epio, MUSB_RXCSR);
 		csr &= ~(MUSB_RXCSR_H_REQPKT | MUSB_RXCSR_DMAENAB);
 		musb_writew(epio, MUSB_RXCSR, csr);
diff --git a/drivers/usb/musb/musb_dsps.c b/drivers/usb/musb/musb_dsps.c
index a0cfead6150f..84512d1d5eee 100644
--- a/drivers/usb/musb/musb_dsps.c
+++ b/drivers/usb/musb/musb_dsps.c
@@ -225,8 +225,11 @@ static void dsps_musb_enable(struct musb *musb)
 
 	dsps_writel(reg_base, wrp->epintr_set, epmask);
 	dsps_writel(reg_base, wrp->coreintr_set, coremask);
-	/* start polling for ID change. */
-	mod_timer(&glue->timer, jiffies + msecs_to_jiffies(wrp->poll_timeout));
+	/* start polling for ID change in dual-role idle mode */
+	if (musb->xceiv->otg->state == OTG_STATE_B_IDLE &&
+			musb->port_mode == MUSB_PORT_MODE_DUAL_ROLE)
+		mod_timer(&glue->timer, jiffies +
+				msecs_to_jiffies(wrp->poll_timeout));
 	dsps_musb_try_idle(musb, 0);
 }
 
diff --git a/drivers/usb/musb/ux500.c b/drivers/usb/musb/ux500.c
index 39168fe9b406..b2685e75a683 100644
--- a/drivers/usb/musb/ux500.c
+++ b/drivers/usb/musb/ux500.c
@@ -379,6 +379,8 @@ static const struct of_device_id ux500_match[] = {
         {}
 };
 
+MODULE_DEVICE_TABLE(of, ux500_match);
+
 static struct platform_driver ux500_driver = {
 	.probe		= ux500_probe,
 	.remove		= ux500_remove,
diff --git a/drivers/usb/phy/Kconfig b/drivers/usb/phy/Kconfig
index 7d3beee2a587..173132416170 100644
--- a/drivers/usb/phy/Kconfig
+++ b/drivers/usb/phy/Kconfig
@@ -155,7 +155,7 @@ config USB_MSM_OTG
 config USB_QCOM_8X16_PHY
 	tristate "Qualcomm APQ8016/MSM8916 on-chip USB PHY controller support"
 	depends on ARCH_QCOM || COMPILE_TEST
-	depends on RESET_CONTROLLER
+	depends on RESET_CONTROLLER && EXTCON
 	select USB_PHY
 	select USB_ULPI_VIEWPORT
 	help
diff --git a/drivers/usb/phy/phy-generic.c b/drivers/usb/phy/phy-generic.c
index ec6ecd03269c..5320cb8642cb 100644
--- a/drivers/usb/phy/phy-generic.c
+++ b/drivers/usb/phy/phy-generic.c
@@ -232,7 +232,8 @@ int usb_phy_gen_create_phy(struct device *dev, struct usb_phy_generic *nop,
 		clk_rate = pdata->clk_rate;
 		needs_vcc = pdata->needs_vcc;
 		if (gpio_is_valid(pdata->gpio_reset)) {
-			err = devm_gpio_request_one(dev, pdata->gpio_reset, 0,
+			err = devm_gpio_request_one(dev, pdata->gpio_reset,
+						    GPIOF_ACTIVE_LOW,
 						    dev_name(dev));
 			if (!err)
 				nop->gpiod_reset =
diff --git a/drivers/usb/phy/phy-isp1301.c b/drivers/usb/phy/phy-isp1301.c
index 8a55b37d1a02..db68156568e6 100644
--- a/drivers/usb/phy/phy-isp1301.c
+++ b/drivers/usb/phy/phy-isp1301.c
@@ -31,6 +31,7 @@ static const struct i2c_device_id isp1301_id[] = {
 	{ "isp1301", 0 },
 	{ }
 };
+MODULE_DEVICE_TABLE(i2c, isp1301_id);
 
 static struct i2c_client *isp1301_i2c_client;
 
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 6d1941a2396a..6956c4f62216 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -278,6 +278,10 @@ static void option_instat_callback(struct urb *urb);
 #define ZTE_PRODUCT_MF622			0x0001
 #define ZTE_PRODUCT_MF628			0x0015
 #define ZTE_PRODUCT_MF626			0x0031
+#define ZTE_PRODUCT_ZM8620_X			0x0396
+#define ZTE_PRODUCT_ME3620_MBIM			0x0426
+#define ZTE_PRODUCT_ME3620_X			0x1432
+#define ZTE_PRODUCT_ME3620_L			0x1433
 #define ZTE_PRODUCT_AC2726			0xfff1
 #define ZTE_PRODUCT_MG880			0xfffd
 #define ZTE_PRODUCT_CDMA_TECH			0xfffe
@@ -544,6 +548,18 @@ static const struct option_blacklist_info zte_mc2716_z_blacklist = {
 	.sendsetup = BIT(1) | BIT(2) | BIT(3),
 };
 
+static const struct option_blacklist_info zte_me3620_mbim_blacklist = {
+	.reserved = BIT(2) | BIT(3) | BIT(4),
+};
+
+static const struct option_blacklist_info zte_me3620_xl_blacklist = {
+	.reserved = BIT(3) | BIT(4) | BIT(5),
+};
+
+static const struct option_blacklist_info zte_zm8620_x_blacklist = {
+	.reserved = BIT(3) | BIT(4) | BIT(5),
+};
+
 static const struct option_blacklist_info huawei_cdc12_blacklist = {
 	.reserved = BIT(1) | BIT(2),
 };
@@ -1591,6 +1607,14 @@ static const struct usb_device_id option_ids[] = {
 	 .driver_info = (kernel_ulong_t)&zte_ad3812_z_blacklist },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_MC2716, 0xff, 0xff, 0xff),
 	 .driver_info = (kernel_ulong_t)&zte_mc2716_z_blacklist },
+	{ USB_DEVICE(ZTE_VENDOR_ID, ZTE_PRODUCT_ME3620_L),
+	 .driver_info = (kernel_ulong_t)&zte_me3620_xl_blacklist },
+	{ USB_DEVICE(ZTE_VENDOR_ID, ZTE_PRODUCT_ME3620_MBIM),
+	 .driver_info = (kernel_ulong_t)&zte_me3620_mbim_blacklist },
+	{ USB_DEVICE(ZTE_VENDOR_ID, ZTE_PRODUCT_ME3620_X),
+	 .driver_info = (kernel_ulong_t)&zte_me3620_xl_blacklist },
+	{ USB_DEVICE(ZTE_VENDOR_ID, ZTE_PRODUCT_ZM8620_X),
+	 .driver_info = (kernel_ulong_t)&zte_zm8620_x_blacklist },
 	{ USB_VENDOR_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff, 0x02, 0x01) },
 	{ USB_VENDOR_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff, 0x02, 0x05) },
 	{ USB_VENDOR_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff, 0x86, 0x10) },
diff --git a/drivers/usb/serial/whiteheat.c b/drivers/usb/serial/whiteheat.c
index 6c3734d2b45a..d3ea90bef84d 100644
--- a/drivers/usb/serial/whiteheat.c
+++ b/drivers/usb/serial/whiteheat.c
@@ -80,6 +80,8 @@ static int  whiteheat_firmware_download(struct usb_serial *serial,
 static int  whiteheat_firmware_attach(struct usb_serial *serial);
 
 /* function prototypes for the Connect Tech WhiteHEAT serial converter */
+static int whiteheat_probe(struct usb_serial *serial,
+				const struct usb_device_id *id);
 static int  whiteheat_attach(struct usb_serial *serial);
 static void whiteheat_release(struct usb_serial *serial);
 static int  whiteheat_port_probe(struct usb_serial_port *port);
@@ -116,6 +118,7 @@ static struct usb_serial_driver whiteheat_device = {
 	.description =		"Connect Tech - WhiteHEAT",
 	.id_table =		id_table_std,
 	.num_ports =		4,
+	.probe =		whiteheat_probe,
 	.attach =		whiteheat_attach,
 	.release =		whiteheat_release,
 	.port_probe =		whiteheat_port_probe,
@@ -217,6 +220,34 @@ static int whiteheat_firmware_attach(struct usb_serial *serial)
 /*****************************************************************************
  * Connect Tech's White Heat serial driver functions
  *****************************************************************************/
+
+static int whiteheat_probe(struct usb_serial *serial,
+				const struct usb_device_id *id)
+{
+	struct usb_host_interface *iface_desc;
+	struct usb_endpoint_descriptor *endpoint;
+	size_t num_bulk_in = 0;
+	size_t num_bulk_out = 0;
+	size_t min_num_bulk;
+	unsigned int i;
+
+	iface_desc = serial->interface->cur_altsetting;
+
+	for (i = 0; i < iface_desc->desc.bNumEndpoints; i++) {
+		endpoint = &iface_desc->endpoint[i].desc;
+		if (usb_endpoint_is_bulk_in(endpoint))
+			++num_bulk_in;
+		if (usb_endpoint_is_bulk_out(endpoint))
+			++num_bulk_out;
+	}
+
+	min_num_bulk = COMMAND_PORT + 1;
+	if (num_bulk_in < min_num_bulk || num_bulk_out < min_num_bulk)
+		return -ENODEV;
+
+	return 0;
+}
+
 static int whiteheat_attach(struct usb_serial *serial)
 {
 	struct usb_serial_port *command_port;