diff --git a/Makefile b/Makefile
index 82ae13348266..3ccf48b2714a 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 4
 PATCHLEVEL = 14
-SUBLEVEL = 138
+SUBLEVEL = 139
 EXTRAVERSION =
 NAME = Petit Gorille
 
diff --git a/arch/arm/mach-davinci/sleep.S b/arch/arm/mach-davinci/sleep.S
index cd350dee4df3..efcd400b2abb 100644
--- a/arch/arm/mach-davinci/sleep.S
+++ b/arch/arm/mach-davinci/sleep.S
@@ -37,6 +37,7 @@
 #define DEEPSLEEP_SLEEPENABLE_BIT	BIT(31)
 
 	.text
+	.arch	armv5te
 /*
  * Move DaVinci into deep sleep state
  *
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 47d45733a346..af1f065dc9f3 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -58,6 +58,11 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *v)
 	return !!(v->arch.pending_exceptions) || kvm_request_pending(v);
 }
 
+bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu)
+{
+	return kvm_arch_vcpu_runnable(vcpu);
+}
+
 bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu)
 {
 	return false;
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 9f3eb334c818..94af073476ce 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1077,6 +1077,7 @@ struct kvm_x86_ops {
 	int (*update_pi_irte)(struct kvm *kvm, unsigned int host_irq,
 			      uint32_t guest_irq, bool set);
 	void (*apicv_post_state_restore)(struct kvm_vcpu *vcpu);
+	bool (*dy_apicv_has_pending_interrupt)(struct kvm_vcpu *vcpu);
 
 	int (*set_hv_timer)(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc);
 	void (*cancel_hv_timer)(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 3a7e79f6cc77..093e7f567e69 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -4637,6 +4637,11 @@ static void svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec)
 		kvm_vcpu_wake_up(vcpu);
 }
 
+static bool svm_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu)
+{
+	return false;
+}
+
 static void svm_ir_list_del(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi)
 {
 	unsigned long flags;
@@ -5746,6 +5751,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
 
 	.pmu_ops = &amd_pmu_ops,
 	.deliver_posted_interrupt = svm_deliver_avic_intr,
+	.dy_apicv_has_pending_interrupt = svm_dy_apicv_has_pending_interrupt,
 	.update_pi_irte = svm_update_pi_irte,
 	.setup_mce = svm_setup_mce,
 };
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index ae484edcf7a3..f467d85b0352 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -9431,6 +9431,11 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu)
 	return max_irr;
 }
 
+static bool vmx_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu)
+{
+	return pi_test_on(vcpu_to_pi_desc(vcpu));
+}
+
 static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap)
 {
 	if (!kvm_vcpu_apicv_active(vcpu))
@@ -12756,6 +12761,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
 	.hwapic_isr_update = vmx_hwapic_isr_update,
 	.sync_pir_to_irr = vmx_sync_pir_to_irr,
 	.deliver_posted_interrupt = vmx_deliver_posted_interrupt,
+	.dy_apicv_has_pending_interrupt = vmx_dy_apicv_has_pending_interrupt,
 
 	.set_tss_addr = vmx_set_tss_addr,
 	.get_tdp_level = get_ept_level,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index a8526042d176..a620936d97cf 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -8711,6 +8711,22 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 	return kvm_vcpu_running(vcpu) || kvm_vcpu_has_events(vcpu);
 }
 
+bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu)
+{
+	if (READ_ONCE(vcpu->arch.pv.pv_unhalted))
+		return true;
+
+	if (kvm_test_request(KVM_REQ_NMI, vcpu) ||
+		kvm_test_request(KVM_REQ_SMI, vcpu) ||
+		 kvm_test_request(KVM_REQ_EVENT, vcpu))
+		return true;
+
+	if (vcpu->arch.apicv_active && kvm_x86_ops->dy_apicv_has_pending_interrupt(vcpu))
+		return true;
+
+	return false;
+}
+
 bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu)
 {
 	return vcpu->arch.preempted_in_kernel;
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index b162f92fd55c..27cab342a0b2 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -260,13 +260,14 @@ static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address)
 
 	pmd = pmd_offset(pud, address);
 	pmd_k = pmd_offset(pud_k, address);
-	if (!pmd_present(*pmd_k))
-		return NULL;
 
-	if (!pmd_present(*pmd))
+	if (pmd_present(*pmd) != pmd_present(*pmd_k))
 		set_pmd(pmd, *pmd_k);
+
+	if (!pmd_present(*pmd_k))
+		return NULL;
 	else
-		BUG_ON(pmd_page(*pmd) != pmd_page(*pmd_k));
+		BUG_ON(pmd_pfn(*pmd) != pmd_pfn(*pmd_k));
 
 	return pmd_k;
 }
@@ -286,17 +287,13 @@ void vmalloc_sync_all(void)
 		spin_lock(&pgd_lock);
 		list_for_each_entry(page, &pgd_list, lru) {
 			spinlock_t *pgt_lock;
-			pmd_t *ret;
 
 			/* the pgt_lock only for Xen */
 			pgt_lock = &pgd_page_get_mm(page)->page_table_lock;
 
 			spin_lock(pgt_lock);
-			ret = vmalloc_sync_one(page_address(page), address);
+			vmalloc_sync_one(page_address(page), address);
 			spin_unlock(pgt_lock);
-
-			if (!ret)
-				break;
 		}
 		spin_unlock(&pgd_lock);
 	}
diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c
index ca414910710e..b0a7afd4e7d3 100644
--- a/drivers/acpi/arm64/iort.c
+++ b/drivers/acpi/arm64/iort.c
@@ -506,8 +506,8 @@ static int iort_dev_find_its_id(struct device *dev, u32 req_id,
 
 	/* Move to ITS specific data */
 	its = (struct acpi_iort_its_group *)node->node_data;
-	if (idx > its->its_count) {
-		dev_err(dev, "requested ITS ID index [%d] is greater than available [%d]\n",
+	if (idx >= its->its_count) {
+		dev_err(dev, "requested ITS ID index [%d] overruns ITS entries [%d]\n",
 			idx, its->its_count);
 		return -ENXIO;
 	}
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index 1aad373da50e..8fbdfaacc222 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -5237,7 +5237,7 @@ static int drbd_do_auth(struct drbd_connection *connection)
 	unsigned int key_len;
 	char secret[SHARED_SECRET_MAX]; /* 64 byte */
 	unsigned int resp_size;
-	SHASH_DESC_ON_STACK(desc, connection->cram_hmac_tfm);
+	struct shash_desc *desc;
 	struct packet_info pi;
 	struct net_conf *nc;
 	int err, rv;
@@ -5250,6 +5250,13 @@ static int drbd_do_auth(struct drbd_connection *connection)
 	memcpy(secret, nc->shared_secret, key_len);
 	rcu_read_unlock();
 
+	desc = kmalloc(sizeof(struct shash_desc) +
+		       crypto_shash_descsize(connection->cram_hmac_tfm),
+		       GFP_KERNEL);
+	if (!desc) {
+		rv = -1;
+		goto fail;
+	}
 	desc->tfm = connection->cram_hmac_tfm;
 	desc->flags = 0;
 
@@ -5392,7 +5399,10 @@ static int drbd_do_auth(struct drbd_connection *connection)
 	kfree(peers_ch);
 	kfree(response);
 	kfree(right_response);
-	shash_desc_zero(desc);
+	if (desc) {
+		shash_desc_zero(desc);
+		kfree(desc);
+	}
 
 	return rv;
 }
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index bd447de4a5b8..87d7c42affbc 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -857,7 +857,7 @@ static void loop_unprepare_queue(struct loop_device *lo)
 
 static int loop_kthread_worker_fn(void *worker_ptr)
 {
-	current->flags |= PF_LESS_THROTTLE;
+	current->flags |= PF_LESS_THROTTLE | PF_MEMALLOC_NOIO;
 	return kthread_worker_fn(worker_ptr);
 }
 
diff --git a/drivers/cpufreq/pasemi-cpufreq.c b/drivers/cpufreq/pasemi-cpufreq.c
index 8456492124f0..d1bdd8f62247 100644
--- a/drivers/cpufreq/pasemi-cpufreq.c
+++ b/drivers/cpufreq/pasemi-cpufreq.c
@@ -145,10 +145,18 @@ static int pas_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	int err = -ENODEV;
 
 	cpu = of_get_cpu_node(policy->cpu, NULL);
+	if (!cpu)
+		goto out;
 
+	max_freqp = of_get_property(cpu, "clock-frequency", NULL);
 	of_node_put(cpu);
-	if (!cpu)
+	if (!max_freqp) {
+		err = -EINVAL;
 		goto out;
+	}
+
+	/* we need the freq in kHz */
+	max_freq = *max_freqp / 1000;
 
 	dn = of_find_compatible_node(NULL, NULL, "1682m-sdc");
 	if (!dn)
@@ -185,16 +193,6 @@ static int pas_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	}
 
 	pr_debug("init cpufreq on CPU %d\n", policy->cpu);
-
-	max_freqp = of_get_property(cpu, "clock-frequency", NULL);
-	if (!max_freqp) {
-		err = -EINVAL;
-		goto out_unmap_sdcpwr;
-	}
-
-	/* we need the freq in kHz */
-	max_freq = *max_freqp / 1000;
-
 	pr_debug("max clock-frequency is at %u kHz\n", max_freq);
 	pr_debug("initializing frequency table\n");
 
@@ -212,9 +210,6 @@ static int pas_cpufreq_cpu_init(struct cpufreq_policy *policy)
 
 	return cpufreq_generic_init(policy, pas_freqs, get_gizmo_latency());
 
-out_unmap_sdcpwr:
-	iounmap(sdcpwr_mapbase);
-
 out_unmap_sdcasr:
 	iounmap(sdcasr_mapbase);
 out:
diff --git a/drivers/crypto/ccp/ccp-crypto-aes-galois.c b/drivers/crypto/ccp/ccp-crypto-aes-galois.c
index 52313524a4dd..2ab97ecd9a08 100644
--- a/drivers/crypto/ccp/ccp-crypto-aes-galois.c
+++ b/drivers/crypto/ccp/ccp-crypto-aes-galois.c
@@ -63,6 +63,19 @@ static int ccp_aes_gcm_setkey(struct crypto_aead *tfm, const u8 *key,
 static int ccp_aes_gcm_setauthsize(struct crypto_aead *tfm,
 				   unsigned int authsize)
 {
+	switch (authsize) {
+	case 16:
+	case 15:
+	case 14:
+	case 13:
+	case 12:
+	case 8:
+	case 4:
+		break;
+	default:
+		return -EINVAL;
+	}
+
 	return 0;
 }
 
@@ -109,6 +122,7 @@ static int ccp_aes_gcm_crypt(struct aead_request *req, bool encrypt)
 	memset(&rctx->cmd, 0, sizeof(rctx->cmd));
 	INIT_LIST_HEAD(&rctx->cmd.entry);
 	rctx->cmd.engine = CCP_ENGINE_AES;
+	rctx->cmd.u.aes.authsize = crypto_aead_authsize(tfm);
 	rctx->cmd.u.aes.type = ctx->u.aes.type;
 	rctx->cmd.u.aes.mode = ctx->u.aes.mode;
 	rctx->cmd.u.aes.action = encrypt;
diff --git a/drivers/crypto/ccp/ccp-ops.c b/drivers/crypto/ccp/ccp-ops.c
index 73e49840305b..1e2e42106dee 100644
--- a/drivers/crypto/ccp/ccp-ops.c
+++ b/drivers/crypto/ccp/ccp-ops.c
@@ -178,14 +178,18 @@ static int ccp_init_dm_workarea(struct ccp_dm_workarea *wa,
 	return 0;
 }
 
-static void ccp_set_dm_area(struct ccp_dm_workarea *wa, unsigned int wa_offset,
-			    struct scatterlist *sg, unsigned int sg_offset,
-			    unsigned int len)
+static int ccp_set_dm_area(struct ccp_dm_workarea *wa, unsigned int wa_offset,
+			   struct scatterlist *sg, unsigned int sg_offset,
+			   unsigned int len)
 {
 	WARN_ON(!wa->address);
 
+	if (len > (wa->length - wa_offset))
+		return -EINVAL;
+
 	scatterwalk_map_and_copy(wa->address + wa_offset, sg, sg_offset, len,
 				 0);
+	return 0;
 }
 
 static void ccp_get_dm_area(struct ccp_dm_workarea *wa, unsigned int wa_offset,
@@ -205,8 +209,11 @@ static int ccp_reverse_set_dm_area(struct ccp_dm_workarea *wa,
 				   unsigned int len)
 {
 	u8 *p, *q;
+	int	rc;
 
-	ccp_set_dm_area(wa, wa_offset, sg, sg_offset, len);
+	rc = ccp_set_dm_area(wa, wa_offset, sg, sg_offset, len);
+	if (rc)
+		return rc;
 
 	p = wa->address + wa_offset;
 	q = p + len - 1;
@@ -509,7 +516,9 @@ static int ccp_run_aes_cmac_cmd(struct ccp_cmd_queue *cmd_q,
 		return ret;
 
 	dm_offset = CCP_SB_BYTES - aes->key_len;
-	ccp_set_dm_area(&key, dm_offset, aes->key, 0, aes->key_len);
+	ret = ccp_set_dm_area(&key, dm_offset, aes->key, 0, aes->key_len);
+	if (ret)
+		goto e_key;
 	ret = ccp_copy_to_sb(cmd_q, &key, op.jobid, op.sb_key,
 			     CCP_PASSTHRU_BYTESWAP_256BIT);
 	if (ret) {
@@ -528,7 +537,9 @@ static int ccp_run_aes_cmac_cmd(struct ccp_cmd_queue *cmd_q,
 		goto e_key;
 
 	dm_offset = CCP_SB_BYTES - AES_BLOCK_SIZE;
-	ccp_set_dm_area(&ctx, dm_offset, aes->iv, 0, aes->iv_len);
+	ret = ccp_set_dm_area(&ctx, dm_offset, aes->iv, 0, aes->iv_len);
+	if (ret)
+		goto e_ctx;
 	ret = ccp_copy_to_sb(cmd_q, &ctx, op.jobid, op.sb_ctx,
 			     CCP_PASSTHRU_BYTESWAP_256BIT);
 	if (ret) {
@@ -556,8 +567,10 @@ static int ccp_run_aes_cmac_cmd(struct ccp_cmd_queue *cmd_q,
 				goto e_src;
 			}
 
-			ccp_set_dm_area(&ctx, 0, aes->cmac_key, 0,
-					aes->cmac_key_len);
+			ret = ccp_set_dm_area(&ctx, 0, aes->cmac_key, 0,
+					      aes->cmac_key_len);
+			if (ret)
+				goto e_src;
 			ret = ccp_copy_to_sb(cmd_q, &ctx, op.jobid, op.sb_ctx,
 					     CCP_PASSTHRU_BYTESWAP_256BIT);
 			if (ret) {
@@ -612,6 +625,7 @@ static int ccp_run_aes_gcm_cmd(struct ccp_cmd_queue *cmd_q,
 
 	unsigned long long *final;
 	unsigned int dm_offset;
+	unsigned int authsize;
 	unsigned int jobid;
 	unsigned int ilen;
 	bool in_place = true; /* Default value */
@@ -633,6 +647,21 @@ static int ccp_run_aes_gcm_cmd(struct ccp_cmd_queue *cmd_q,
 	if (!aes->key) /* Gotta have a key SGL */
 		return -EINVAL;
 
+	/* Zero defaults to 16 bytes, the maximum size */
+	authsize = aes->authsize ? aes->authsize : AES_BLOCK_SIZE;
+	switch (authsize) {
+	case 16:
+	case 15:
+	case 14:
+	case 13:
+	case 12:
+	case 8:
+	case 4:
+		break;
+	default:
+		return -EINVAL;
+	}
+
 	/* First, decompose the source buffer into AAD & PT,
 	 * and the destination buffer into AAD, CT & tag, or
 	 * the input into CT & tag.
@@ -647,7 +676,7 @@ static int ccp_run_aes_gcm_cmd(struct ccp_cmd_queue *cmd_q,
 		p_tag = scatterwalk_ffwd(sg_tag, p_outp, ilen);
 	} else {
 		/* Input length for decryption includes tag */
-		ilen = aes->src_len - AES_BLOCK_SIZE;
+		ilen = aes->src_len - authsize;
 		p_tag = scatterwalk_ffwd(sg_tag, p_inp, ilen);
 	}
 
@@ -669,7 +698,9 @@ static int ccp_run_aes_gcm_cmd(struct ccp_cmd_queue *cmd_q,
 		return ret;
 
 	dm_offset = CCP_SB_BYTES - aes->key_len;
-	ccp_set_dm_area(&key, dm_offset, aes->key, 0, aes->key_len);
+	ret = ccp_set_dm_area(&key, dm_offset, aes->key, 0, aes->key_len);
+	if (ret)
+		goto e_key;
 	ret = ccp_copy_to_sb(cmd_q, &key, op.jobid, op.sb_key,
 			     CCP_PASSTHRU_BYTESWAP_256BIT);
 	if (ret) {
@@ -688,7 +719,9 @@ static int ccp_run_aes_gcm_cmd(struct ccp_cmd_queue *cmd_q,
 		goto e_key;
 
 	dm_offset = CCP_AES_CTX_SB_COUNT * CCP_SB_BYTES - aes->iv_len;
-	ccp_set_dm_area(&ctx, dm_offset, aes->iv, 0, aes->iv_len);
+	ret = ccp_set_dm_area(&ctx, dm_offset, aes->iv, 0, aes->iv_len);
+	if (ret)
+		goto e_ctx;
 
 	ret = ccp_copy_to_sb(cmd_q, &ctx, op.jobid, op.sb_ctx,
 			     CCP_PASSTHRU_BYTESWAP_256BIT);
@@ -752,8 +785,7 @@ static int ccp_run_aes_gcm_cmd(struct ccp_cmd_queue *cmd_q,
 		while (src.sg_wa.bytes_left) {
 			ccp_prepare_data(&src, &dst, &op, AES_BLOCK_SIZE, true);
 			if (!src.sg_wa.bytes_left) {
-				unsigned int nbytes = aes->src_len
-						      % AES_BLOCK_SIZE;
+				unsigned int nbytes = ilen % AES_BLOCK_SIZE;
 
 				if (nbytes) {
 					op.eom = 1;
@@ -780,7 +812,9 @@ static int ccp_run_aes_gcm_cmd(struct ccp_cmd_queue *cmd_q,
 		goto e_dst;
 	}
 
-	ccp_set_dm_area(&ctx, dm_offset, aes->iv, 0, aes->iv_len);
+	ret = ccp_set_dm_area(&ctx, dm_offset, aes->iv, 0, aes->iv_len);
+	if (ret)
+		goto e_dst;
 
 	ret = ccp_copy_to_sb(cmd_q, &ctx, op.jobid, op.sb_ctx,
 			     CCP_PASSTHRU_BYTESWAP_256BIT);
@@ -823,17 +857,19 @@ static int ccp_run_aes_gcm_cmd(struct ccp_cmd_queue *cmd_q,
 
 	if (aes->action == CCP_AES_ACTION_ENCRYPT) {
 		/* Put the ciphered tag after the ciphertext. */
-		ccp_get_dm_area(&final_wa, 0, p_tag, 0, AES_BLOCK_SIZE);
+		ccp_get_dm_area(&final_wa, 0, p_tag, 0, authsize);
 	} else {
 		/* Does this ciphered tag match the input? */
-		ret = ccp_init_dm_workarea(&tag, cmd_q, AES_BLOCK_SIZE,
+		ret = ccp_init_dm_workarea(&tag, cmd_q, authsize,
 					   DMA_BIDIRECTIONAL);
 		if (ret)
 			goto e_tag;
-		ccp_set_dm_area(&tag, 0, p_tag, 0, AES_BLOCK_SIZE);
+		ret = ccp_set_dm_area(&tag, 0, p_tag, 0, authsize);
+		if (ret)
+			goto e_tag;
 
 		ret = crypto_memneq(tag.address, final_wa.address,
-				    AES_BLOCK_SIZE) ? -EBADMSG : 0;
+				    authsize) ? -EBADMSG : 0;
 		ccp_dm_free(&tag);
 	}
 
@@ -841,11 +877,11 @@ e_tag:
 	ccp_dm_free(&final_wa);
 
 e_dst:
-	if (aes->src_len && !in_place)
+	if (ilen > 0 && !in_place)
 		ccp_free_data(&dst, cmd_q);
 
 e_src:
-	if (aes->src_len)
+	if (ilen > 0)
 		ccp_free_data(&src, cmd_q);
 
 e_aad:
@@ -925,7 +961,9 @@ static int ccp_run_aes_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 		return ret;
 
 	dm_offset = CCP_SB_BYTES - aes->key_len;
-	ccp_set_dm_area(&key, dm_offset, aes->key, 0, aes->key_len);
+	ret = ccp_set_dm_area(&key, dm_offset, aes->key, 0, aes->key_len);
+	if (ret)
+		goto e_key;
 	ret = ccp_copy_to_sb(cmd_q, &key, op.jobid, op.sb_key,
 			     CCP_PASSTHRU_BYTESWAP_256BIT);
 	if (ret) {
@@ -946,7 +984,9 @@ static int ccp_run_aes_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 	if (aes->mode != CCP_AES_MODE_ECB) {
 		/* Load the AES context - convert to LE */
 		dm_offset = CCP_SB_BYTES - AES_BLOCK_SIZE;
-		ccp_set_dm_area(&ctx, dm_offset, aes->iv, 0, aes->iv_len);
+		ret = ccp_set_dm_area(&ctx, dm_offset, aes->iv, 0, aes->iv_len);
+		if (ret)
+			goto e_ctx;
 		ret = ccp_copy_to_sb(cmd_q, &ctx, op.jobid, op.sb_ctx,
 				     CCP_PASSTHRU_BYTESWAP_256BIT);
 		if (ret) {
@@ -1124,8 +1164,12 @@ static int ccp_run_xts_aes_cmd(struct ccp_cmd_queue *cmd_q,
 		 * big endian to little endian.
 		 */
 		dm_offset = CCP_SB_BYTES - AES_KEYSIZE_128;
-		ccp_set_dm_area(&key, dm_offset, xts->key, 0, xts->key_len);
-		ccp_set_dm_area(&key, 0, xts->key, xts->key_len, xts->key_len);
+		ret = ccp_set_dm_area(&key, dm_offset, xts->key, 0, xts->key_len);
+		if (ret)
+			goto e_key;
+		ret = ccp_set_dm_area(&key, 0, xts->key, xts->key_len, xts->key_len);
+		if (ret)
+			goto e_key;
 	} else {
 		/* Version 5 CCPs use a 512-bit space for the key: each portion
 		 * occupies 256 bits, or one entire slot, and is zero-padded.
@@ -1134,9 +1178,13 @@ static int ccp_run_xts_aes_cmd(struct ccp_cmd_queue *cmd_q,
 
 		dm_offset = CCP_SB_BYTES;
 		pad = dm_offset - xts->key_len;
-		ccp_set_dm_area(&key, pad, xts->key, 0, xts->key_len);
-		ccp_set_dm_area(&key, dm_offset + pad, xts->key, xts->key_len,
-				xts->key_len);
+		ret = ccp_set_dm_area(&key, pad, xts->key, 0, xts->key_len);
+		if (ret)
+			goto e_key;
+		ret = ccp_set_dm_area(&key, dm_offset + pad, xts->key,
+				      xts->key_len, xts->key_len);
+		if (ret)
+			goto e_key;
 	}
 	ret = ccp_copy_to_sb(cmd_q, &key, op.jobid, op.sb_key,
 			     CCP_PASSTHRU_BYTESWAP_256BIT);
@@ -1155,7 +1203,9 @@ static int ccp_run_xts_aes_cmd(struct ccp_cmd_queue *cmd_q,
 	if (ret)
 		goto e_key;
 
-	ccp_set_dm_area(&ctx, 0, xts->iv, 0, xts->iv_len);
+	ret = ccp_set_dm_area(&ctx, 0, xts->iv, 0, xts->iv_len);
+	if (ret)
+		goto e_ctx;
 	ret = ccp_copy_to_sb(cmd_q, &ctx, op.jobid, op.sb_ctx,
 			     CCP_PASSTHRU_BYTESWAP_NOOP);
 	if (ret) {
@@ -1298,12 +1348,18 @@ static int ccp_run_des3_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 	dm_offset = CCP_SB_BYTES - des3->key_len; /* Basic offset */
 
 	len_singlekey = des3->key_len / 3;
-	ccp_set_dm_area(&key, dm_offset + 2 * len_singlekey,
-			des3->key, 0, len_singlekey);
-	ccp_set_dm_area(&key, dm_offset + len_singlekey,
-			des3->key, len_singlekey, len_singlekey);
-	ccp_set_dm_area(&key, dm_offset,
-			des3->key, 2 * len_singlekey, len_singlekey);
+	ret = ccp_set_dm_area(&key, dm_offset + 2 * len_singlekey,
+			      des3->key, 0, len_singlekey);
+	if (ret)
+		goto e_key;
+	ret = ccp_set_dm_area(&key, dm_offset + len_singlekey,
+			      des3->key, len_singlekey, len_singlekey);
+	if (ret)
+		goto e_key;
+	ret = ccp_set_dm_area(&key, dm_offset,
+			      des3->key, 2 * len_singlekey, len_singlekey);
+	if (ret)
+		goto e_key;
 
 	/* Copy the key to the SB */
 	ret = ccp_copy_to_sb(cmd_q, &key, op.jobid, op.sb_key,
@@ -1331,7 +1387,10 @@ static int ccp_run_des3_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 
 		/* Load the context into the LSB */
 		dm_offset = CCP_SB_BYTES - des3->iv_len;
-		ccp_set_dm_area(&ctx, dm_offset, des3->iv, 0, des3->iv_len);
+		ret = ccp_set_dm_area(&ctx, dm_offset, des3->iv, 0,
+				      des3->iv_len);
+		if (ret)
+			goto e_ctx;
 
 		if (cmd_q->ccp->vdata->version == CCP_VERSION(3, 0))
 			load_mode = CCP_PASSTHRU_BYTESWAP_NOOP;
@@ -1615,8 +1674,10 @@ static int ccp_run_sha_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 		}
 	} else {
 		/* Restore the context */
-		ccp_set_dm_area(&ctx, 0, sha->ctx, 0,
-				sb_count * CCP_SB_BYTES);
+		ret = ccp_set_dm_area(&ctx, 0, sha->ctx, 0,
+				      sb_count * CCP_SB_BYTES);
+		if (ret)
+			goto e_ctx;
 	}
 
 	ret = ccp_copy_to_sb(cmd_q, &ctx, op.jobid, op.sb_ctx,
@@ -1938,7 +1999,9 @@ static int ccp_run_passthru_cmd(struct ccp_cmd_queue *cmd_q,
 		if (ret)
 			return ret;
 
-		ccp_set_dm_area(&mask, 0, pt->mask, 0, pt->mask_len);
+		ret = ccp_set_dm_area(&mask, 0, pt->mask, 0, pt->mask_len);
+		if (ret)
+			goto e_mask;
 		ret = ccp_copy_to_sb(cmd_q, &mask, op.jobid, op.sb_key,
 				     CCP_PASSTHRU_BYTESWAP_NOOP);
 		if (ret) {
diff --git a/drivers/firmware/Kconfig b/drivers/firmware/Kconfig
index 6e4ed5a9c6fd..42c4ff75281b 100644
--- a/drivers/firmware/Kconfig
+++ b/drivers/firmware/Kconfig
@@ -156,7 +156,7 @@ config DMI_SCAN_MACHINE_NON_EFI_FALLBACK
 
 config ISCSI_IBFT_FIND
 	bool "iSCSI Boot Firmware Table Attributes"
-	depends on X86 && ACPI
+	depends on X86 && ISCSI_IBFT
 	default n
 	help
 	  This option enables the kernel to find the region of memory
@@ -167,7 +167,8 @@ config ISCSI_IBFT_FIND
 config ISCSI_IBFT
 	tristate "iSCSI Boot Firmware Table Attributes module"
 	select ISCSI_BOOT_SYSFS
-	depends on ISCSI_IBFT_FIND && SCSI && SCSI_LOWLEVEL
+	select ISCSI_IBFT_FIND if X86
+	depends on ACPI && SCSI && SCSI_LOWLEVEL
 	default	n
 	help
 	  This option enables support for detection and exposing of iSCSI
diff --git a/drivers/firmware/iscsi_ibft.c b/drivers/firmware/iscsi_ibft.c
index 132b9bae4b6a..220bbc91cebd 100644
--- a/drivers/firmware/iscsi_ibft.c
+++ b/drivers/firmware/iscsi_ibft.c
@@ -93,6 +93,10 @@ MODULE_DESCRIPTION("sysfs interface to BIOS iBFT information");
 MODULE_LICENSE("GPL");
 MODULE_VERSION(IBFT_ISCSI_VERSION);
 
+#ifndef CONFIG_ISCSI_IBFT_FIND
+struct acpi_table_ibft *ibft_addr;
+#endif
+
 struct ibft_hdr {
 	u8 id;
 	u8 version;
diff --git a/drivers/gpu/drm/drm_framebuffer.c b/drivers/gpu/drm/drm_framebuffer.c
index c21e10c780ac..af40189cdb60 100644
--- a/drivers/gpu/drm/drm_framebuffer.c
+++ b/drivers/gpu/drm/drm_framebuffer.c
@@ -773,7 +773,7 @@ static int atomic_remove_fb(struct drm_framebuffer *fb)
 	struct drm_device *dev = fb->dev;
 	struct drm_atomic_state *state;
 	struct drm_plane *plane;
-	struct drm_connector *conn;
+	struct drm_connector *conn __maybe_unused;
 	struct drm_connector_state *conn_state;
 	int i, ret = 0;
 	unsigned plane_mask;
diff --git a/drivers/gpu/drm/i915/intel_dsi_pll.c b/drivers/gpu/drm/i915/intel_dsi_pll.c
index 2ff2ee7f3b78..03c592753fc3 100644
--- a/drivers/gpu/drm/i915/intel_dsi_pll.c
+++ b/drivers/gpu/drm/i915/intel_dsi_pll.c
@@ -422,8 +422,8 @@ static void glk_dsi_program_esc_clock(struct drm_device *dev,
 	else
 		txesc2_div = 10;
 
-	I915_WRITE(MIPIO_TXESC_CLK_DIV1, txesc1_div & GLK_TX_ESC_CLK_DIV1_MASK);
-	I915_WRITE(MIPIO_TXESC_CLK_DIV2, txesc2_div & GLK_TX_ESC_CLK_DIV2_MASK);
+	I915_WRITE(MIPIO_TXESC_CLK_DIV1, (1 << (txesc1_div - 1)) & GLK_TX_ESC_CLK_DIV1_MASK);
+	I915_WRITE(MIPIO_TXESC_CLK_DIV2, (1 << (txesc2_div - 1)) & GLK_TX_ESC_CLK_DIV2_MASK);
 }
 
 /* Program BXT Mipi clocks and dividers */
diff --git a/drivers/hid/hid-sony.c b/drivers/hid/hid-sony.c
index d03203a82e8f..51f7bcd799fa 100644
--- a/drivers/hid/hid-sony.c
+++ b/drivers/hid/hid-sony.c
@@ -578,10 +578,14 @@ static void sony_set_leds(struct sony_sc *sc);
 static inline void sony_schedule_work(struct sony_sc *sc,
 				      enum sony_worker which)
 {
+	unsigned long flags;
+
 	switch (which) {
 	case SONY_WORKER_STATE:
-		if (!sc->defer_initialization)
+		spin_lock_irqsave(&sc->lock, flags);
+		if (!sc->defer_initialization && sc->state_worker_initialized)
 			schedule_work(&sc->state_worker);
+		spin_unlock_irqrestore(&sc->lock, flags);
 		break;
 	case SONY_WORKER_HOTPLUG:
 		if (sc->hotplug_worker_initialized)
@@ -2488,13 +2492,18 @@ static inline void sony_init_output_report(struct sony_sc *sc,
 
 static inline void sony_cancel_work_sync(struct sony_sc *sc)
 {
+	unsigned long flags;
+
 	if (sc->hotplug_worker_initialized)
 		cancel_work_sync(&sc->hotplug_worker);
-	if (sc->state_worker_initialized)
+	if (sc->state_worker_initialized) {
+		spin_lock_irqsave(&sc->lock, flags);
+		sc->state_worker_initialized = 0;
+		spin_unlock_irqrestore(&sc->lock, flags);
 		cancel_work_sync(&sc->state_worker);
+	}
 }
 
-
 static int sony_input_configured(struct hid_device *hdev,
 					struct hid_input *hidinput)
 {
diff --git a/drivers/hwmon/nct6775.c b/drivers/hwmon/nct6775.c
index ca9941fa741b..7e14143ed119 100644
--- a/drivers/hwmon/nct6775.c
+++ b/drivers/hwmon/nct6775.c
@@ -769,7 +769,7 @@ static const u16 NCT6106_REG_TARGET[] = { 0x111, 0x121, 0x131 };
 static const u16 NCT6106_REG_WEIGHT_TEMP_SEL[] = { 0x168, 0x178, 0x188 };
 static const u16 NCT6106_REG_WEIGHT_TEMP_STEP[] = { 0x169, 0x179, 0x189 };
 static const u16 NCT6106_REG_WEIGHT_TEMP_STEP_TOL[] = { 0x16a, 0x17a, 0x18a };
-static const u16 NCT6106_REG_WEIGHT_DUTY_STEP[] = { 0x16b, 0x17b, 0x17c };
+static const u16 NCT6106_REG_WEIGHT_DUTY_STEP[] = { 0x16b, 0x17b, 0x18b };
 static const u16 NCT6106_REG_WEIGHT_TEMP_BASE[] = { 0x16c, 0x17c, 0x18c };
 static const u16 NCT6106_REG_WEIGHT_DUTY_BASE[] = { 0x16d, 0x17d, 0x18d };
 
@@ -3592,6 +3592,7 @@ static int nct6775_probe(struct platform_device *pdev)
 		data->REG_FAN_TIME[0] = NCT6106_REG_FAN_STOP_TIME;
 		data->REG_FAN_TIME[1] = NCT6106_REG_FAN_STEP_UP_TIME;
 		data->REG_FAN_TIME[2] = NCT6106_REG_FAN_STEP_DOWN_TIME;
+		data->REG_TOLERANCE_H = NCT6106_REG_TOLERANCE_H;
 		data->REG_PWM[0] = NCT6106_REG_PWM;
 		data->REG_PWM[1] = NCT6106_REG_FAN_START_OUTPUT;
 		data->REG_PWM[2] = NCT6106_REG_FAN_STOP_OUTPUT;
diff --git a/drivers/hwmon/nct7802.c b/drivers/hwmon/nct7802.c
index 2876c18ed841..38ffbdb0a85f 100644
--- a/drivers/hwmon/nct7802.c
+++ b/drivers/hwmon/nct7802.c
@@ -768,7 +768,7 @@ static struct attribute *nct7802_in_attrs[] = {
 	&sensor_dev_attr_in3_alarm.dev_attr.attr,
 	&sensor_dev_attr_in3_beep.dev_attr.attr,
 
-	&sensor_dev_attr_in4_input.dev_attr.attr,	/* 17 */
+	&sensor_dev_attr_in4_input.dev_attr.attr,	/* 16 */
 	&sensor_dev_attr_in4_min.dev_attr.attr,
 	&sensor_dev_attr_in4_max.dev_attr.attr,
 	&sensor_dev_attr_in4_alarm.dev_attr.attr,
@@ -794,9 +794,9 @@ static umode_t nct7802_in_is_visible(struct kobject *kobj,
 
 	if (index >= 6 && index < 11 && (reg & 0x03) != 0x03)	/* VSEN1 */
 		return 0;
-	if (index >= 11 && index < 17 && (reg & 0x0c) != 0x0c)	/* VSEN2 */
+	if (index >= 11 && index < 16 && (reg & 0x0c) != 0x0c)	/* VSEN2 */
 		return 0;
-	if (index >= 17 && (reg & 0x30) != 0x30)		/* VSEN3 */
+	if (index >= 16 && (reg & 0x30) != 0x30)		/* VSEN3 */
 		return 0;
 
 	return attr->mode;
diff --git a/drivers/iio/adc/max9611.c b/drivers/iio/adc/max9611.c
index b1dd17cbce58..f8f298c33b28 100644
--- a/drivers/iio/adc/max9611.c
+++ b/drivers/iio/adc/max9611.c
@@ -86,7 +86,7 @@
 #define MAX9611_TEMP_MAX_POS		0x7f80
 #define MAX9611_TEMP_MAX_NEG		0xff80
 #define MAX9611_TEMP_MIN_NEG		0xd980
-#define MAX9611_TEMP_MASK		GENMASK(7, 15)
+#define MAX9611_TEMP_MASK		GENMASK(15, 7)
 #define MAX9611_TEMP_SHIFT		0x07
 #define MAX9611_TEMP_RAW(_r)		((_r) >> MAX9611_TEMP_SHIFT)
 #define MAX9611_TEMP_SCALE_NUM		1000000
diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c
index 7c8d4baf647b..7db53eab7012 100644
--- a/drivers/input/mouse/synaptics.c
+++ b/drivers/input/mouse/synaptics.c
@@ -185,6 +185,7 @@ static const char * const smbus_pnp_ids[] = {
 	"LEN2055", /* E580 */
 	"SYN3052", /* HP EliteBook 840 G4 */
 	"SYN3221", /* HP 15-ay000 */
+	"SYN323d", /* HP Spectre X360 13-w013dx */
 	NULL
 };
 
diff --git a/drivers/misc/Makefile b/drivers/misc/Makefile
index ad0e64fdba34..76f6a4f628b3 100644
--- a/drivers/misc/Makefile
+++ b/drivers/misc/Makefile
@@ -69,8 +69,7 @@ KCOV_INSTRUMENT_lkdtm_rodata.o	:= n
 
 OBJCOPYFLAGS :=
 OBJCOPYFLAGS_lkdtm_rodata_objcopy.o := \
-			--set-section-flags .text=alloc,readonly \
-			--rename-section .text=.rodata
+	--rename-section .text=.rodata,alloc,readonly,load
 targets += lkdtm_rodata.o lkdtm_rodata_objcopy.o
 $(obj)/lkdtm_rodata_objcopy.o: $(obj)/lkdtm_rodata.o FORCE
 	$(call if_changed,objcopy)
diff --git a/drivers/mmc/host/cavium.c b/drivers/mmc/host/cavium.c
index fbd29f00fca0..d76fea1098e2 100644
--- a/drivers/mmc/host/cavium.c
+++ b/drivers/mmc/host/cavium.c
@@ -374,6 +374,7 @@ static int finish_dma_single(struct cvm_mmc_host *host, struct mmc_data *data)
 {
 	data->bytes_xfered = data->blocks * data->blksz;
 	data->error = 0;
+	dma_unmap_sg(host->dev, data->sg, data->sg_len, get_dma_dir(data));
 	return 1;
 }
 
@@ -1046,7 +1047,8 @@ int cvm_mmc_of_slot_probe(struct device *dev, struct cvm_mmc_host *host)
 		mmc->max_segs = 1;
 
 	/* DMA size field can address up to 8 MB */
-	mmc->max_seg_size = 8 * 1024 * 1024;
+	mmc->max_seg_size = min_t(unsigned int, 8 * 1024 * 1024,
+				  dma_get_max_seg_size(host->dev));
 	mmc->max_req_size = mmc->max_seg_size;
 	/* External DMA is in 512 byte blocks */
 	mmc->max_blk_size = 512;
diff --git a/drivers/net/can/rcar/rcar_canfd.c b/drivers/net/can/rcar/rcar_canfd.c
index 602c19e23f05..786d852a70d5 100644
--- a/drivers/net/can/rcar/rcar_canfd.c
+++ b/drivers/net/can/rcar/rcar_canfd.c
@@ -1512,10 +1512,11 @@ static int rcar_canfd_rx_poll(struct napi_struct *napi, int quota)
 
 	/* All packets processed */
 	if (num_pkts < quota) {
-		napi_complete_done(napi, num_pkts);
-		/* Enable Rx FIFO interrupts */
-		rcar_canfd_set_bit(priv->base, RCANFD_RFCC(ridx),
-				   RCANFD_RFCC_RFIE);
+		if (napi_complete_done(napi, num_pkts)) {
+			/* Enable Rx FIFO interrupts */
+			rcar_canfd_set_bit(priv->base, RCANFD_RFCC(ridx),
+					   RCANFD_RFCC_RFIE);
+		}
 	}
 	return num_pkts;
 }
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c
index 1ca76e03e965..d68c79f9a4b9 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c
@@ -594,16 +594,16 @@ static int peak_usb_ndo_stop(struct net_device *netdev)
 	dev->state &= ~PCAN_USB_STATE_STARTED;
 	netif_stop_queue(netdev);
 
+	close_candev(netdev);
+
+	dev->can.state = CAN_STATE_STOPPED;
+
 	/* unlink all pending urbs and free used memory */
 	peak_usb_unlink_all_urbs(dev);
 
 	if (dev->adapter->dev_stop)
 		dev->adapter->dev_stop(dev);
 
-	close_candev(netdev);
-
-	dev->can.state = CAN_STATE_STOPPED;
-
 	/* can set bus off now */
 	if (dev->adapter->dev_set_bus) {
 		int err = dev->adapter->dev_set_bus(dev, 0);
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
index 53d6bb045e9e..773fc15ac3ab 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
@@ -852,7 +852,7 @@ static int pcan_usb_fd_init(struct peak_usb_device *dev)
 			goto err_out;
 
 		/* allocate command buffer once for all for the interface */
-		pdev->cmd_buffer_addr = kmalloc(PCAN_UFD_CMD_BUFFER_SIZE,
+		pdev->cmd_buffer_addr = kzalloc(PCAN_UFD_CMD_BUFFER_SIZE,
 						GFP_KERNEL);
 		if (!pdev->cmd_buffer_addr)
 			goto err_out_1;
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c
index bbdd6058cd2f..d85fdc6949c6 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c
@@ -500,7 +500,7 @@ static int pcan_usb_pro_drv_loaded(struct peak_usb_device *dev, int loaded)
 	u8 *buffer;
 	int err;
 
-	buffer = kmalloc(PCAN_USBPRO_FCT_DRVLD_REQ_LEN, GFP_KERNEL);
+	buffer = kzalloc(PCAN_USBPRO_FCT_DRVLD_REQ_LEN, GFP_KERNEL);
 	if (!buffer)
 		return -ENOMEM;
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
index e9e466cae322..534c0ea7b232 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
@@ -778,7 +778,7 @@ static int iwl_mvm_sar_get_ewrd_table(struct iwl_mvm *mvm)
 
 	for (i = 0; i < n_profiles; i++) {
 		/* the tables start at element 3 */
-		static int pos = 3;
+		int pos = 3;
 
 		/* The EWRD profiles officially go from 2 to 4, but we
 		 * save them in sar_profiles[1-3] (because we don't
@@ -912,6 +912,22 @@ int iwl_mvm_sar_select_profile(struct iwl_mvm *mvm, int prof_a, int prof_b)
 	return iwl_mvm_send_cmd_pdu(mvm, REDUCE_TX_POWER_CMD, 0, len, &cmd);
 }
 
+static bool iwl_mvm_sar_geo_support(struct iwl_mvm *mvm)
+{
+	/*
+	 * The GEO_TX_POWER_LIMIT command is not supported on earlier
+	 * firmware versions.  Unfortunately, we don't have a TLV API
+	 * flag to rely on, so rely on the major version which is in
+	 * the first byte of ucode_ver.  This was implemented
+	 * initially on version 38 and then backported to 36, 29 and
+	 * 17.
+	 */
+	return IWL_UCODE_SERIAL(mvm->fw->ucode_ver) >= 38 ||
+	       IWL_UCODE_SERIAL(mvm->fw->ucode_ver) == 36 ||
+	       IWL_UCODE_SERIAL(mvm->fw->ucode_ver) == 29 ||
+	       IWL_UCODE_SERIAL(mvm->fw->ucode_ver) == 17;
+}
+
 int iwl_mvm_get_sar_geo_profile(struct iwl_mvm *mvm)
 {
 	struct iwl_geo_tx_power_profiles_resp *resp;
@@ -927,6 +943,9 @@ int iwl_mvm_get_sar_geo_profile(struct iwl_mvm *mvm)
 		.data = { &geo_cmd },
 	};
 
+	if (!iwl_mvm_sar_geo_support(mvm))
+		return -EOPNOTSUPP;
+
 	ret = iwl_mvm_send_cmd(mvm, &cmd);
 	if (ret) {
 		IWL_ERR(mvm, "Failed to get geographic profile info %d\n", ret);
@@ -952,13 +971,7 @@ static int iwl_mvm_sar_geo_init(struct iwl_mvm *mvm)
 	int ret, i, j;
 	u16 cmd_wide_id =  WIDE_ID(PHY_OPS_GROUP, GEO_TX_POWER_LIMIT);
 
-	/*
-	 * This command is not supported on earlier firmware versions.
-	 * Unfortunately, we don't have a TLV API flag to rely on, so
-	 * rely on the major version which is in the first byte of
-	 * ucode_ver.
-	 */
-	if (IWL_UCODE_SERIAL(mvm->fw->ucode_ver) < 41)
+	if (!iwl_mvm_sar_geo_support(mvm))
 		return 0;
 
 	ret = iwl_mvm_sar_get_wgds_table(mvm);
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
index 4704137a26e0..c3a2e6b6da65 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
@@ -401,6 +401,8 @@ static void iwl_pcie_tfd_unmap(struct iwl_trans *trans,
 					 DMA_TO_DEVICE);
 	}
 
+	meta->tbs = 0;
+
 	if (trans->cfg->use_tfh) {
 		struct iwl_tfh_tfd *tfd_fh = (void *)tfd;
 
diff --git a/drivers/net/wireless/marvell/mwifiex/main.h b/drivers/net/wireless/marvell/mwifiex/main.h
index a76bd797e454..597af4e66325 100644
--- a/drivers/net/wireless/marvell/mwifiex/main.h
+++ b/drivers/net/wireless/marvell/mwifiex/main.h
@@ -122,6 +122,7 @@ enum {
 
 #define MWIFIEX_MAX_TOTAL_SCAN_TIME	(MWIFIEX_TIMER_10S - MWIFIEX_TIMER_1S)
 
+#define WPA_GTK_OUI_OFFSET				2
 #define RSN_GTK_OUI_OFFSET				2
 
 #define MWIFIEX_OUI_NOT_PRESENT			0
diff --git a/drivers/net/wireless/marvell/mwifiex/scan.c b/drivers/net/wireless/marvell/mwifiex/scan.c
index 29284f9a0646..67c334221077 100644
--- a/drivers/net/wireless/marvell/mwifiex/scan.c
+++ b/drivers/net/wireless/marvell/mwifiex/scan.c
@@ -181,7 +181,8 @@ mwifiex_is_wpa_oui_present(struct mwifiex_bssdescriptor *bss_desc, u32 cipher)
 	u8 ret = MWIFIEX_OUI_NOT_PRESENT;
 
 	if (has_vendor_hdr(bss_desc->bcn_wpa_ie, WLAN_EID_VENDOR_SPECIFIC)) {
-		iebody = (struct ie_body *) bss_desc->bcn_wpa_ie->data;
+		iebody = (struct ie_body *)((u8 *)bss_desc->bcn_wpa_ie->data +
+					    WPA_GTK_OUI_OFFSET);
 		oui = &mwifiex_wpa_oui[cipher][0];
 		ret = mwifiex_search_oui_in_ie(iebody, oui);
 		if (ret)
diff --git a/drivers/s390/cio/qdio_main.c b/drivers/s390/cio/qdio_main.c
index ab8dd81fbc2b..1a40c73961b8 100644
--- a/drivers/s390/cio/qdio_main.c
+++ b/drivers/s390/cio/qdio_main.c
@@ -1577,13 +1577,13 @@ static int handle_outbound(struct qdio_q *q, unsigned int callflags,
 		rc = qdio_kick_outbound_q(q, phys_aob);
 	} else if (need_siga_sync(q)) {
 		rc = qdio_siga_sync_q(q);
+	} else if (count < QDIO_MAX_BUFFERS_PER_Q &&
+		   get_buf_state(q, prev_buf(bufnr), &state, 0) > 0 &&
+		   state == SLSB_CU_OUTPUT_PRIMED) {
+		/* The previous buffer is not processed yet, tack on. */
+		qperf_inc(q, fast_requeue);
 	} else {
-		/* try to fast requeue buffers */
-		get_buf_state(q, prev_buf(bufnr), &state, 0);
-		if (state != SLSB_CU_OUTPUT_PRIMED)
-			rc = qdio_kick_outbound_q(q, 0);
-		else
-			qperf_inc(q, fast_requeue);
+		rc = qdio_kick_outbound_q(q, 0);
 	}
 
 	/* in case of SIGA errors we must process the error immediately */
diff --git a/drivers/s390/cio/vfio_ccw_cp.c b/drivers/s390/cio/vfio_ccw_cp.c
index 1419eaea03d8..5a9e457caef3 100644
--- a/drivers/s390/cio/vfio_ccw_cp.c
+++ b/drivers/s390/cio/vfio_ccw_cp.c
@@ -119,8 +119,10 @@ static int pfn_array_alloc_pin(struct pfn_array *pa, struct device *mdev,
 				  sizeof(*pa->pa_iova_pfn) +
 				  sizeof(*pa->pa_pfn),
 				  GFP_KERNEL);
-	if (unlikely(!pa->pa_iova_pfn))
+	if (unlikely(!pa->pa_iova_pfn)) {
+		pa->pa_nr = 0;
 		return -ENOMEM;
+	}
 	pa->pa_pfn = pa->pa_iova_pfn + pa->pa_nr;
 
 	ret = pfn_array_pin(pa, mdev);
diff --git a/drivers/scsi/device_handler/scsi_dh_alua.c b/drivers/scsi/device_handler/scsi_dh_alua.c
index 09c6a16fab93..41f5f6410163 100644
--- a/drivers/scsi/device_handler/scsi_dh_alua.c
+++ b/drivers/scsi/device_handler/scsi_dh_alua.c
@@ -53,6 +53,7 @@
 #define ALUA_FAILOVER_TIMEOUT		60
 #define ALUA_FAILOVER_RETRIES		5
 #define ALUA_RTPG_DELAY_MSECS		5
+#define ALUA_RTPG_RETRY_DELAY		2
 
 /* device handler flags */
 #define ALUA_OPTIMIZE_STPG		0x01
@@ -677,7 +678,7 @@ static int alua_rtpg(struct scsi_device *sdev, struct alua_port_group *pg)
 	case SCSI_ACCESS_STATE_TRANSITIONING:
 		if (time_before(jiffies, pg->expiry)) {
 			/* State transition, retry */
-			pg->interval = 2;
+			pg->interval = ALUA_RTPG_RETRY_DELAY;
 			err = SCSI_DH_RETRY;
 		} else {
 			struct alua_dh_data *h;
@@ -802,6 +803,8 @@ static void alua_rtpg_work(struct work_struct *work)
 				spin_lock_irqsave(&pg->lock, flags);
 				pg->flags &= ~ALUA_PG_RUNNING;
 				pg->flags |= ALUA_PG_RUN_RTPG;
+				if (!pg->interval)
+					pg->interval = ALUA_RTPG_RETRY_DELAY;
 				spin_unlock_irqrestore(&pg->lock, flags);
 				queue_delayed_work(kaluad_wq, &pg->rtpg_work,
 						   pg->interval * HZ);
@@ -813,6 +816,8 @@ static void alua_rtpg_work(struct work_struct *work)
 		spin_lock_irqsave(&pg->lock, flags);
 		if (err == SCSI_DH_RETRY || pg->flags & ALUA_PG_RUN_RTPG) {
 			pg->flags &= ~ALUA_PG_RUNNING;
+			if (!pg->interval && !(pg->flags & ALUA_PG_RUN_RTPG))
+				pg->interval = ALUA_RTPG_RETRY_DELAY;
 			pg->flags |= ALUA_PG_RUN_RTPG;
 			spin_unlock_irqrestore(&pg->lock, flags);
 			queue_delayed_work(kaluad_wq, &pg->rtpg_work,
diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c
index a06b24a61622..34612add3829 100644
--- a/drivers/scsi/ibmvscsi/ibmvfc.c
+++ b/drivers/scsi/ibmvscsi/ibmvfc.c
@@ -4876,8 +4876,8 @@ static int ibmvfc_remove(struct vio_dev *vdev)
 
 	spin_lock_irqsave(vhost->host->host_lock, flags);
 	ibmvfc_purge_requests(vhost, DID_ERROR);
-	ibmvfc_free_event_pool(vhost);
 	spin_unlock_irqrestore(vhost->host->host_lock, flags);
+	ibmvfc_free_event_pool(vhost);
 
 	ibmvfc_free_mem(vhost);
 	spin_lock(&ibmvfc_driver_lock);
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index 73acd3e9ded7..8595d83229b7 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -2976,6 +2976,7 @@ megasas_fw_crash_buffer_show(struct device *cdev,
 	u32 size;
 	unsigned long buff_addr;
 	unsigned long dmachunk = CRASH_DMA_BUF_SIZE;
+	unsigned long chunk_left_bytes;
 	unsigned long src_addr;
 	unsigned long flags;
 	u32 buff_offset;
@@ -3001,6 +3002,8 @@ megasas_fw_crash_buffer_show(struct device *cdev,
 	}
 
 	size = (instance->fw_crash_buffer_size * dmachunk) - buff_offset;
+	chunk_left_bytes = dmachunk - (buff_offset % dmachunk);
+	size = (size > chunk_left_bytes) ? chunk_left_bytes : size;
 	size = (size >= PAGE_SIZE) ? (PAGE_SIZE - 1) : size;
 
 	src_addr = (unsigned long)instance->crash_buf[buff_offset / dmachunk] +
diff --git a/drivers/tty/tty_ldsem.c b/drivers/tty/tty_ldsem.c
index 5c2cec298816..c6ce34161281 100644
--- a/drivers/tty/tty_ldsem.c
+++ b/drivers/tty/tty_ldsem.c
@@ -139,8 +139,7 @@ static void __ldsem_wake_readers(struct ld_semaphore *sem)
 
 	list_for_each_entry_safe(waiter, next, &sem->read_wait, list) {
 		tsk = waiter->task;
-		smp_mb();
-		waiter->task = NULL;
+		smp_store_release(&waiter->task, NULL);
 		wake_up_process(tsk);
 		put_task_struct(tsk);
 	}
@@ -235,7 +234,7 @@ down_read_failed(struct ld_semaphore *sem, long count, long timeout)
 	for (;;) {
 		set_current_state(TASK_UNINTERRUPTIBLE);
 
-		if (!waiter.task)
+		if (!smp_load_acquire(&waiter.task))
 			break;
 		if (!timeout)
 			break;
diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c
index 492977f78fde..62b2a7105f02 100644
--- a/drivers/usb/core/devio.c
+++ b/drivers/usb/core/devio.c
@@ -1811,8 +1811,6 @@ static int proc_do_submiturb(struct usb_dev_state *ps, struct usbdevfs_urb *uurb
 	return 0;
 
  error:
-	if (as && as->usbm)
-		dec_usb_memory_use_count(as->usbm, &as->usbm->urb_use_count);
 	kfree(isopkt);
 	kfree(dr);
 	if (as)
diff --git a/drivers/usb/host/xhci-rcar.c b/drivers/usb/host/xhci-rcar.c
index 425c2edfd6ea..544e03452877 100644
--- a/drivers/usb/host/xhci-rcar.c
+++ b/drivers/usb/host/xhci-rcar.c
@@ -231,10 +231,15 @@ int xhci_rcar_init_quirk(struct usb_hcd *hcd)
 	 * pointers. So, this driver clears the AC64 bit of xhci->hcc_params
 	 * to call dma_set_coherent_mask(dev, DMA_BIT_MASK(32)) in
 	 * xhci_gen_setup().
+	 *
+	 * And, since the firmware/internal CPU control the USBSTS.STS_HALT
+	 * and the process speed is down when the roothub port enters U3,
+	 * long delay for the handshake of STS_HALT is neeed in xhci_suspend().
 	 */
 	if (xhci_rcar_is_gen2(hcd->self.controller) ||
-			xhci_rcar_is_gen3(hcd->self.controller))
-		xhci->quirks |= XHCI_NO_64BIT_SUPPORT;
+			xhci_rcar_is_gen3(hcd->self.controller)) {
+		xhci->quirks |= XHCI_NO_64BIT_SUPPORT | XHCI_SLOW_SUSPEND;
+	}
 
 	xhci->quirks |= XHCI_TRUST_TX_LENGTH;
 	return xhci_rcar_download_firmware(hcd);
diff --git a/drivers/usb/misc/iowarrior.c b/drivers/usb/misc/iowarrior.c
index be5881303681..43bee6dad5c9 100644
--- a/drivers/usb/misc/iowarrior.c
+++ b/drivers/usb/misc/iowarrior.c
@@ -870,19 +870,20 @@ static void iowarrior_disconnect(struct usb_interface *interface)
 	dev = usb_get_intfdata(interface);
 	mutex_lock(&iowarrior_open_disc_lock);
 	usb_set_intfdata(interface, NULL);
+	/* prevent device read, write and ioctl */
+	dev->present = 0;
 
 	minor = dev->minor;
+	mutex_unlock(&iowarrior_open_disc_lock);
+	/* give back our minor - this will call close() locks need to be dropped at this point*/
 
-	/* give back our minor */
 	usb_deregister_dev(interface, &iowarrior_class);
 
 	mutex_lock(&dev->mutex);
 
 	/* prevent device read, write and ioctl */
-	dev->present = 0;
 
 	mutex_unlock(&dev->mutex);
-	mutex_unlock(&iowarrior_open_disc_lock);
 
 	if (dev->opened) {
 		/* There is a process that holds a filedescriptor to the device ,
diff --git a/drivers/usb/misc/yurex.c b/drivers/usb/misc/yurex.c
index 8ee98bc6c468..081570677f24 100644
--- a/drivers/usb/misc/yurex.c
+++ b/drivers/usb/misc/yurex.c
@@ -96,7 +96,6 @@ static void yurex_delete(struct kref *kref)
 
 	dev_dbg(&dev->interface->dev, "%s\n", __func__);
 
-	usb_put_dev(dev->udev);
 	if (dev->cntl_urb) {
 		usb_kill_urb(dev->cntl_urb);
 		kfree(dev->cntl_req);
@@ -112,6 +111,7 @@ static void yurex_delete(struct kref *kref)
 				dev->int_buffer, dev->urb->transfer_dma);
 		usb_free_urb(dev->urb);
 	}
+	usb_put_dev(dev->udev);
 	kfree(dev);
 }
 
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index fd2d199dd413..0e1c36c92f60 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -166,7 +166,7 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon)
 	if (tcon == NULL)
 		return 0;
 
-	if (smb2_command == SMB2_TREE_CONNECT)
+	if (smb2_command == SMB2_TREE_CONNECT || smb2_command == SMB2_IOCTL)
 		return 0;
 
 	if (tcon->tidStatus == CifsExiting) {
@@ -834,7 +834,12 @@ SMB2_sess_alloc_buffer(struct SMB2_sess_data *sess_data)
 	else
 		req->SecurityMode = 0;
 
+#ifdef CONFIG_CIFS_DFS_UPCALL
+	req->Capabilities = cpu_to_le32(SMB2_GLOBAL_CAP_DFS);
+#else
 	req->Capabilities = 0;
+#endif /* DFS_UPCALL */
+
 	req->Channel = 0; /* MBZ */
 
 	sess_data->iov[0].iov_base = (char *)req;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 27deee5c8fa8..6409ff4876cb 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2954,7 +2954,6 @@ static int _nfs4_do_setattr(struct inode *inode,
 	};
 	struct rpc_cred *delegation_cred = NULL;
 	unsigned long timestamp = jiffies;
-	fmode_t fmode;
 	bool truncate;
 	int status;
 
@@ -2962,11 +2961,12 @@ static int _nfs4_do_setattr(struct inode *inode,
 
 	/* Servers should only apply open mode checks for file size changes */
 	truncate = (arg->iap->ia_valid & ATTR_SIZE) ? true : false;
-	fmode = truncate ? FMODE_WRITE : FMODE_READ;
+	if (!truncate)
+		goto zero_stateid;
 
-	if (nfs4_copy_delegation_stateid(inode, fmode, &arg->stateid, &delegation_cred)) {
+	if (nfs4_copy_delegation_stateid(inode, FMODE_WRITE, &arg->stateid, &delegation_cred)) {
 		/* Use that stateid */
-	} else if (truncate && ctx != NULL) {
+	} else if (ctx != NULL && ctx->state) {
 		struct nfs_lock_context *l_ctx;
 		if (!nfs4_valid_open_stateid(ctx->state))
 			return -EBADF;
@@ -2978,8 +2978,10 @@ static int _nfs4_do_setattr(struct inode *inode,
 		nfs_put_lock_context(l_ctx);
 		if (status == -EIO)
 			return -EBADF;
-	} else
+	} else {
+zero_stateid:
 		nfs4_stateid_copy(&arg->stateid, &zero_stateid);
+	}
 	if (delegation_cred)
 		msg.rpc_cred = delegation_cred;
 
diff --git a/include/linux/ccp.h b/include/linux/ccp.h
index 7e9c991c95e0..43ed9e77cf81 100644
--- a/include/linux/ccp.h
+++ b/include/linux/ccp.h
@@ -173,6 +173,8 @@ struct ccp_aes_engine {
 	enum ccp_aes_mode mode;
 	enum ccp_aes_action action;
 
+	u32 authsize;
+
 	struct scatterlist *key;
 	u32 key_len;		/* In bytes */
 
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 026615e242d8..c8b9d3519c8e 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -808,6 +808,7 @@ void kvm_arch_check_processor_compat(void *rtn);
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu);
 bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu);
 int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu);
+bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu);
 
 #ifndef __KVM_HAVE_ARCH_VM_ALLOC
 static inline struct kvm *kvm_arch_alloc_vm(void)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 7994e569644e..9de2c8cdcc51 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1613,6 +1613,8 @@ static inline void tcp_init_send_head(struct sock *sk)
 	sk->sk_send_head = NULL;
 }
 
+static inline void tcp_init_send_head(struct sock *sk);
+
 /* write queue abstraction */
 static inline void tcp_write_queue_purge(struct sock *sk)
 {
@@ -1621,6 +1623,7 @@ static inline void tcp_write_queue_purge(struct sock *sk)
 	tcp_chrono_stop(sk, TCP_CHRONO_BUSY);
 	while ((skb = __skb_dequeue(&sk->sk_write_queue)) != NULL)
 		sk_wmem_free_skb(sk, skb);
+	tcp_init_send_head(sk);
 	sk_mem_reclaim(sk);
 	tcp_clear_all_retrans_hints(tcp_sk(sk));
 	tcp_init_send_head(sk);
diff --git a/include/sound/compress_driver.h b/include/sound/compress_driver.h
index 392bac18398b..33a07c3badf0 100644
--- a/include/sound/compress_driver.h
+++ b/include/sound/compress_driver.h
@@ -186,10 +186,7 @@ static inline void snd_compr_drain_notify(struct snd_compr_stream *stream)
 	if (snd_BUG_ON(!stream))
 		return;
 
-	if (stream->direction == SND_COMPRESS_PLAYBACK)
-		stream->runtime->state = SNDRV_PCM_STATE_SETUP;
-	else
-		stream->runtime->state = SNDRV_PCM_STATE_PREPARED;
+	stream->runtime->state = SNDRV_PCM_STATE_SETUP;
 
 	wake_up(&stream->runtime->sleep);
 }
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 3d4eb6f840eb..ea4f3f7a0c6f 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -10474,7 +10474,7 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
 		goto err_unlock;
 	}
 
-	perf_install_in_context(ctx, event, cpu);
+	perf_install_in_context(ctx, event, event->cpu);
 	perf_unpin_context(ctx);
 	mutex_unlock(&ctx->mutex);
 
diff --git a/lib/test_firmware.c b/lib/test_firmware.c
index f978aebe60c5..2e5e18bbfd28 100644
--- a/lib/test_firmware.c
+++ b/lib/test_firmware.c
@@ -895,8 +895,11 @@ static int __init test_firmware_init(void)
 		return -ENOMEM;
 
 	rc = __test_firmware_config_init();
-	if (rc)
+	if (rc) {
+		kfree(test_fw_config);
+		pr_err("could not init firmware test config: %d\n", rc);
 		return rc;
+	}
 
 	rc = misc_register(&test_fw_misc_device);
 	if (rc) {
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 6c906f6f16cc..0b8852d80f44 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1765,6 +1765,12 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align,
 	if (!addr)
 		return NULL;
 
+	/*
+	 * First make sure the mappings are removed from all page-tables
+	 * before they are freed.
+	 */
+	vmalloc_sync_all();
+
 	/*
 	 * In this function, newly allocated vm_struct has VM_UNINITIALIZED
 	 * flag. It means that vm_struct is not fully initialized.
@@ -2314,6 +2320,9 @@ EXPORT_SYMBOL(remap_vmalloc_range);
 /*
  * Implement a stub for vmalloc_sync_all() if the architecture chose not to
  * have one.
+ *
+ * The purpose of this function is to make sure the vmalloc area
+ * mappings are identical in all page-tables in the system.
  */
 void __weak vmalloc_sync_all(void)
 {
diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c
index 37fb9552e858..341d1bd637af 100644
--- a/net/ipv4/netfilter/ipt_rpfilter.c
+++ b/net/ipv4/netfilter/ipt_rpfilter.c
@@ -96,6 +96,7 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par)
 	flow.flowi4_mark = info->flags & XT_RPFILTER_VALID_MARK ? skb->mark : 0;
 	flow.flowi4_tos = RT_TOS(iph->tos);
 	flow.flowi4_scope = RT_SCOPE_UNIVERSE;
+	flow.flowi4_oif = l3mdev_master_ifindex_rcu(xt_in(par));
 
 	return rpfilter_lookup_reverse(xt_net(par), &flow, xt_in(par), info->flags) ^ invert;
 }
diff --git a/net/ipv6/netfilter/ip6t_rpfilter.c b/net/ipv6/netfilter/ip6t_rpfilter.c
index 40eb16bd9786..d535768bea0f 100644
--- a/net/ipv6/netfilter/ip6t_rpfilter.c
+++ b/net/ipv6/netfilter/ip6t_rpfilter.c
@@ -58,7 +58,9 @@ static bool rpfilter_lookup_reverse6(struct net *net, const struct sk_buff *skb,
 	if (rpfilter_addr_linklocal(&iph->saddr)) {
 		lookup_flags |= RT6_LOOKUP_F_IFACE;
 		fl6.flowi6_oif = dev->ifindex;
-	} else if ((flags & XT_RPFILTER_LOOSE) == 0)
+	/* Set flowi6_oif for vrf devices to lookup route in l3mdev domain. */
+	} else if (netif_is_l3_master(dev) || netif_is_l3_slave(dev) ||
+		  (flags & XT_RPFILTER_LOOSE) == 0)
 		fl6.flowi6_oif = dev->ifindex;
 
 	rt = (void *) ip6_route_lookup(net, &fl6, lookup_flags);
@@ -73,7 +75,9 @@ static bool rpfilter_lookup_reverse6(struct net *net, const struct sk_buff *skb,
 		goto out;
 	}
 
-	if (rt->rt6i_idev->dev == dev || (flags & XT_RPFILTER_LOOSE))
+	if (rt->rt6i_idev->dev == dev ||
+	    l3mdev_master_ifindex_rcu(rt->rt6i_idev->dev) == dev->ifindex ||
+	    (flags & XT_RPFILTER_LOOSE))
 		ret = true;
  out:
 	ip6_rt_put(rt);
diff --git a/net/mac80211/driver-ops.c b/net/mac80211/driver-ops.c
index bb886e7db47f..f783d1377d9a 100644
--- a/net/mac80211/driver-ops.c
+++ b/net/mac80211/driver-ops.c
@@ -169,11 +169,16 @@ int drv_conf_tx(struct ieee80211_local *local,
 	if (!check_sdata_in_driver(sdata))
 		return -EIO;
 
-	if (WARN_ONCE(params->cw_min == 0 ||
-		      params->cw_min > params->cw_max,
-		      "%s: invalid CW_min/CW_max: %d/%d\n",
-		      sdata->name, params->cw_min, params->cw_max))
+	if (params->cw_min == 0 || params->cw_min > params->cw_max) {
+		/*
+		 * If we can't configure hardware anyway, don't warn. We may
+		 * never have initialized the CW parameters.
+		 */
+		WARN_ONCE(local->ops->conf_tx,
+			  "%s: invalid CW_min/CW_max: %d/%d\n",
+			  sdata->name, params->cw_min, params->cw_max);
 		return -EINVAL;
+	}
 
 	trace_drv_conf_tx(local, sdata, ac, params);
 	if (local->ops->conf_tx)
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 960a57f7c983..d91db72b9e9e 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -1867,6 +1867,16 @@ static bool ieee80211_sta_wmm_params(struct ieee80211_local *local,
 		}
 	}
 
+	/* WMM specification requires all 4 ACIs. */
+	for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) {
+		if (params[ac].cw_min == 0) {
+			sdata_info(sdata,
+				   "AP has invalid WMM params (missing AC %d), using defaults\n",
+				   ac);
+			return false;
+		}
+	}
+
 	for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) {
 		mlme_dbg(sdata,
 			 "WMM AC=%d acm=%d aifs=%d cWmin=%d cWmax=%d txop=%d uapsd=%d, downgraded=%d\n",
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index 733d3e4a30d8..2cee032af46d 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -530,7 +530,7 @@ static int nfnetlink_bind(struct net *net, int group)
 	ss = nfnetlink_get_subsys(type << 8);
 	rcu_read_unlock();
 	if (!ss)
-		request_module("nfnetlink-subsys-%d", type);
+		request_module_nowait("nfnetlink-subsys-%d", type);
 	return 0;
 }
 #endif
diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c
index 24f2f7567ddb..010a565b4000 100644
--- a/net/netfilter/nft_hash.c
+++ b/net/netfilter/nft_hash.c
@@ -131,7 +131,7 @@ static int nft_symhash_init(const struct nft_ctx *ctx,
 	priv->dreg = nft_parse_register(tb[NFTA_HASH_DREG]);
 
 	priv->modulus = ntohl(nla_get_be32(tb[NFTA_HASH_MODULUS]));
-	if (priv->modulus <= 1)
+	if (priv->modulus < 1)
 		return -ERANGE;
 
 	if (priv->offset + priv->modulus - 1 < priv->offset)
diff --git a/scripts/sphinx-pre-install b/scripts/sphinx-pre-install
index 067459760a7b..3524dbc31316 100755
--- a/scripts/sphinx-pre-install
+++ b/scripts/sphinx-pre-install
@@ -301,7 +301,7 @@ sub give_redhat_hints()
 	#
 	# Checks valid for RHEL/CentOS version 7.x.
 	#
-	if (! $system_release =~ /Fedora/) {
+	if (!($system_release =~ /Fedora/)) {
 		$map{"virtualenv"} = "python-virtualenv";
 	}
 
diff --git a/sound/core/compress_offload.c b/sound/core/compress_offload.c
index 555df64d46ff..2e2d18468491 100644
--- a/sound/core/compress_offload.c
+++ b/sound/core/compress_offload.c
@@ -575,10 +575,7 @@ snd_compr_set_params(struct snd_compr_stream *stream, unsigned long arg)
 		stream->metadata_set = false;
 		stream->next_track = false;
 
-		if (stream->direction == SND_COMPRESS_PLAYBACK)
-			stream->runtime->state = SNDRV_PCM_STATE_SETUP;
-		else
-			stream->runtime->state = SNDRV_PCM_STATE_PREPARED;
+		stream->runtime->state = SNDRV_PCM_STATE_SETUP;
 	} else {
 		return -EPERM;
 	}
@@ -694,8 +691,17 @@ static int snd_compr_start(struct snd_compr_stream *stream)
 {
 	int retval;
 
-	if (stream->runtime->state != SNDRV_PCM_STATE_PREPARED)
+	switch (stream->runtime->state) {
+	case SNDRV_PCM_STATE_SETUP:
+		if (stream->direction != SND_COMPRESS_CAPTURE)
+			return -EPERM;
+		break;
+	case SNDRV_PCM_STATE_PREPARED:
+		break;
+	default:
 		return -EPERM;
+	}
+
 	retval = stream->ops->trigger(stream, SNDRV_PCM_TRIGGER_START);
 	if (!retval)
 		stream->runtime->state = SNDRV_PCM_STATE_RUNNING;
@@ -706,9 +712,15 @@ static int snd_compr_stop(struct snd_compr_stream *stream)
 {
 	int retval;
 
-	if (stream->runtime->state == SNDRV_PCM_STATE_PREPARED ||
-			stream->runtime->state == SNDRV_PCM_STATE_SETUP)
+	switch (stream->runtime->state) {
+	case SNDRV_PCM_STATE_OPEN:
+	case SNDRV_PCM_STATE_SETUP:
+	case SNDRV_PCM_STATE_PREPARED:
 		return -EPERM;
+	default:
+		break;
+	}
+
 	retval = stream->ops->trigger(stream, SNDRV_PCM_TRIGGER_STOP);
 	if (!retval) {
 		snd_compr_drain_notify(stream);
@@ -796,9 +808,17 @@ static int snd_compr_drain(struct snd_compr_stream *stream)
 {
 	int retval;
 
-	if (stream->runtime->state == SNDRV_PCM_STATE_PREPARED ||
-			stream->runtime->state == SNDRV_PCM_STATE_SETUP)
+	switch (stream->runtime->state) {
+	case SNDRV_PCM_STATE_OPEN:
+	case SNDRV_PCM_STATE_SETUP:
+	case SNDRV_PCM_STATE_PREPARED:
+	case SNDRV_PCM_STATE_PAUSED:
 		return -EPERM;
+	case SNDRV_PCM_STATE_XRUN:
+		return -EPIPE;
+	default:
+		break;
+	}
 
 	retval = stream->ops->trigger(stream, SND_COMPR_TRIGGER_DRAIN);
 	if (retval) {
@@ -818,6 +838,10 @@ static int snd_compr_next_track(struct snd_compr_stream *stream)
 	if (stream->runtime->state != SNDRV_PCM_STATE_RUNNING)
 		return -EPERM;
 
+	/* next track doesn't have any meaning for capture streams */
+	if (stream->direction == SND_COMPRESS_CAPTURE)
+		return -EPERM;
+
 	/* you can signal next track if this is intended to be a gapless stream
 	 * and current track metadata is set
 	 */
@@ -835,9 +859,23 @@ static int snd_compr_next_track(struct snd_compr_stream *stream)
 static int snd_compr_partial_drain(struct snd_compr_stream *stream)
 {
 	int retval;
-	if (stream->runtime->state == SNDRV_PCM_STATE_PREPARED ||
-			stream->runtime->state == SNDRV_PCM_STATE_SETUP)
+
+	switch (stream->runtime->state) {
+	case SNDRV_PCM_STATE_OPEN:
+	case SNDRV_PCM_STATE_SETUP:
+	case SNDRV_PCM_STATE_PREPARED:
+	case SNDRV_PCM_STATE_PAUSED:
+		return -EPERM;
+	case SNDRV_PCM_STATE_XRUN:
+		return -EPIPE;
+	default:
+		break;
+	}
+
+	/* partial drain doesn't have any meaning for capture streams */
+	if (stream->direction == SND_COMPRESS_CAPTURE)
 		return -EPERM;
+
 	/* stream can be drained only when next track has been signalled */
 	if (stream->next_track == false)
 		return -EPERM;
diff --git a/sound/firewire/packets-buffer.c b/sound/firewire/packets-buffer.c
index ea1506679c66..3b09b8ef3a09 100644
--- a/sound/firewire/packets-buffer.c
+++ b/sound/firewire/packets-buffer.c
@@ -37,7 +37,7 @@ int iso_packets_buffer_init(struct iso_packets_buffer *b, struct fw_unit *unit,
 	packets_per_page = PAGE_SIZE / packet_size;
 	if (WARN_ON(!packets_per_page)) {
 		err = -EINVAL;
-		goto error;
+		goto err_packets;
 	}
 	pages = DIV_ROUND_UP(count, packets_per_page);
 
diff --git a/sound/pci/hda/hda_controller.c b/sound/pci/hda/hda_controller.c
index a12e594d4e3b..a41c1bec7c88 100644
--- a/sound/pci/hda/hda_controller.c
+++ b/sound/pci/hda/hda_controller.c
@@ -609,11 +609,9 @@ static int azx_pcm_open(struct snd_pcm_substream *substream)
 	}
 	runtime->private_data = azx_dev;
 
-	if (chip->gts_present)
-		azx_pcm_hw.info = azx_pcm_hw.info |
-			SNDRV_PCM_INFO_HAS_LINK_SYNCHRONIZED_ATIME;
-
 	runtime->hw = azx_pcm_hw;
+	if (chip->gts_present)
+		runtime->hw.info |= SNDRV_PCM_INFO_HAS_LINK_SYNCHRONIZED_ATIME;
 	runtime->hw.channels_min = hinfo->channels_min;
 	runtime->hw.channels_max = hinfo->channels_max;
 	runtime->hw.formats = hinfo->formats;
@@ -626,6 +624,13 @@ static int azx_pcm_open(struct snd_pcm_substream *substream)
 				     20,
 				     178000000);
 
+	/* by some reason, the playback stream stalls on PulseAudio with
+	 * tsched=1 when a capture stream triggers.  Until we figure out the
+	 * real cause, disable tsched mode by telling the PCM info flag.
+	 */
+	if (chip->driver_caps & AZX_DCAPS_AMD_WORKAROUND)
+		runtime->hw.info |= SNDRV_PCM_INFO_BATCH;
+
 	if (chip->align_buffer_size)
 		/* constrain buffer sizes to be multiple of 128
 		   bytes. This is more efficient in terms of memory
diff --git a/sound/pci/hda/hda_controller.h b/sound/pci/hda/hda_controller.h
index 53c3cd28bc99..8a9dd4767b1e 100644
--- a/sound/pci/hda/hda_controller.h
+++ b/sound/pci/hda/hda_controller.h
@@ -40,7 +40,7 @@
 /* 14 unused */
 #define AZX_DCAPS_CTX_WORKAROUND (1 << 15)	/* X-Fi workaround */
 #define AZX_DCAPS_POSFIX_LPIB	(1 << 16)	/* Use LPIB as default */
-/* 17 unused */
+#define AZX_DCAPS_AMD_WORKAROUND (1 << 17)	/* AMD-specific workaround */
 #define AZX_DCAPS_NO_64BIT	(1 << 18)	/* No 64bit address */
 #define AZX_DCAPS_SYNC_WRITE	(1 << 19)	/* sync each cmd write */
 #define AZX_DCAPS_OLD_SSYNC	(1 << 20)	/* Old SSYNC reg for ICH */
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index d349f69ef03c..4631579e1e18 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -78,6 +78,7 @@ enum {
 	POS_FIX_VIACOMBO,
 	POS_FIX_COMBO,
 	POS_FIX_SKL,
+	POS_FIX_FIFO,
 };
 
 /* Defines for ATI HD Audio support in SB450 south bridge */
@@ -149,7 +150,7 @@ module_param_array(model, charp, NULL, 0444);
 MODULE_PARM_DESC(model, "Use the given board model.");
 module_param_array(position_fix, int, NULL, 0444);
 MODULE_PARM_DESC(position_fix, "DMA pointer read method."
-		 "(-1 = system default, 0 = auto, 1 = LPIB, 2 = POSBUF, 3 = VIACOMBO, 4 = COMBO, 5 = SKL+).");
+		 "(-1 = system default, 0 = auto, 1 = LPIB, 2 = POSBUF, 3 = VIACOMBO, 4 = COMBO, 5 = SKL+, 6 = FIFO).");
 module_param_array(bdl_pos_adj, int, NULL, 0644);
 MODULE_PARM_DESC(bdl_pos_adj, "BDL position adjustment offset.");
 module_param_array(probe_mask, int, NULL, 0444);
@@ -350,6 +351,11 @@ enum {
 #define AZX_DCAPS_PRESET_ATI_HDMI_NS \
 	(AZX_DCAPS_PRESET_ATI_HDMI | AZX_DCAPS_SNOOP_OFF)
 
+/* quirks for AMD SB */
+#define AZX_DCAPS_PRESET_AMD_SB \
+	(AZX_DCAPS_NO_TCSEL | AZX_DCAPS_SYNC_WRITE | AZX_DCAPS_AMD_WORKAROUND |\
+	 AZX_DCAPS_SNOOP_TYPE(ATI) | AZX_DCAPS_PM_RUNTIME)
+
 /* quirks for Nvidia */
 #define AZX_DCAPS_PRESET_NVIDIA \
 	(AZX_DCAPS_NO_MSI | AZX_DCAPS_CORBRP_SELF_CLEAR |\
@@ -917,6 +923,49 @@ static unsigned int azx_via_get_position(struct azx *chip,
 	return bound_pos + mod_dma_pos;
 }
 
+#define AMD_FIFO_SIZE	32
+
+/* get the current DMA position with FIFO size correction */
+static unsigned int azx_get_pos_fifo(struct azx *chip, struct azx_dev *azx_dev)
+{
+	struct snd_pcm_substream *substream = azx_dev->core.substream;
+	struct snd_pcm_runtime *runtime = substream->runtime;
+	unsigned int pos, delay;
+
+	pos = snd_hdac_stream_get_pos_lpib(azx_stream(azx_dev));
+	if (!runtime)
+		return pos;
+
+	runtime->delay = AMD_FIFO_SIZE;
+	delay = frames_to_bytes(runtime, AMD_FIFO_SIZE);
+	if (azx_dev->insufficient) {
+		if (pos < delay) {
+			delay = pos;
+			runtime->delay = bytes_to_frames(runtime, pos);
+		} else {
+			azx_dev->insufficient = 0;
+		}
+	}
+
+	/* correct the DMA position for capture stream */
+	if (substream->stream == SNDRV_PCM_STREAM_CAPTURE) {
+		if (pos < delay)
+			pos += azx_dev->core.bufsize;
+		pos -= delay;
+	}
+
+	return pos;
+}
+
+static int azx_get_delay_from_fifo(struct azx *chip, struct azx_dev *azx_dev,
+				   unsigned int pos)
+{
+	struct snd_pcm_substream *substream = azx_dev->core.substream;
+
+	/* just read back the calculated value in the above */
+	return substream->runtime->delay;
+}
+
 static unsigned int azx_skl_get_dpib_pos(struct azx *chip,
 					 struct azx_dev *azx_dev)
 {
@@ -1484,6 +1533,7 @@ static int check_position_fix(struct azx *chip, int fix)
 	case POS_FIX_VIACOMBO:
 	case POS_FIX_COMBO:
 	case POS_FIX_SKL:
+	case POS_FIX_FIFO:
 		return fix;
 	}
 
@@ -1500,6 +1550,10 @@ static int check_position_fix(struct azx *chip, int fix)
 		dev_dbg(chip->card->dev, "Using VIACOMBO position fix\n");
 		return POS_FIX_VIACOMBO;
 	}
+	if (chip->driver_caps & AZX_DCAPS_AMD_WORKAROUND) {
+		dev_dbg(chip->card->dev, "Using FIFO position fix\n");
+		return POS_FIX_FIFO;
+	}
 	if (chip->driver_caps & AZX_DCAPS_POSFIX_LPIB) {
 		dev_dbg(chip->card->dev, "Using LPIB position fix\n");
 		return POS_FIX_LPIB;
@@ -1520,6 +1574,7 @@ static void assign_position_fix(struct azx *chip, int fix)
 		[POS_FIX_VIACOMBO] = azx_via_get_position,
 		[POS_FIX_COMBO] = azx_get_pos_lpib,
 		[POS_FIX_SKL] = azx_get_pos_skl,
+		[POS_FIX_FIFO] = azx_get_pos_fifo,
 	};
 
 	chip->get_position[0] = chip->get_position[1] = callbacks[fix];
@@ -1534,6 +1589,9 @@ static void assign_position_fix(struct azx *chip, int fix)
 			azx_get_delay_from_lpib;
 	}
 
+	if (fix == POS_FIX_FIFO)
+		chip->get_delay[0] = chip->get_delay[1] =
+			azx_get_delay_from_fifo;
 }
 
 /*
@@ -2516,6 +2574,9 @@ static const struct pci_device_id azx_ids[] = {
 	/* AMD Hudson */
 	{ PCI_DEVICE(0x1022, 0x780d),
 	  .driver_data = AZX_DRIVER_GENERIC | AZX_DCAPS_PRESET_ATI_SB },
+	/* AMD, X370 & co */
+	{ PCI_DEVICE(0x1022, 0x1457),
+	  .driver_data = AZX_DRIVER_GENERIC | AZX_DCAPS_PRESET_AMD_SB },
 	/* AMD Stoney */
 	{ PCI_DEVICE(0x1022, 0x157a),
 	  .driver_data = AZX_DRIVER_GENERIC | AZX_DCAPS_PRESET_ATI_SB |
diff --git a/sound/sound_core.c b/sound/sound_core.c
index 99b73c675743..20d4e2e1bacf 100644
--- a/sound/sound_core.c
+++ b/sound/sound_core.c
@@ -287,7 +287,8 @@ retry:
 				goto retry;
 			}
 			spin_unlock(&sound_loader_lock);
-			return -EBUSY;
+			r = -EBUSY;
+			goto fail;
 		}
 	}
 
diff --git a/tools/perf/arch/s390/util/machine.c b/tools/perf/arch/s390/util/machine.c
index a19690a17291..c8c86a0c9b79 100644
--- a/tools/perf/arch/s390/util/machine.c
+++ b/tools/perf/arch/s390/util/machine.c
@@ -6,8 +6,9 @@
 #include "machine.h"
 #include "api/fs/fs.h"
 #include "debug.h"
+#include "symbol.h"
 
-int arch__fix_module_text_start(u64 *start, const char *name)
+int arch__fix_module_text_start(u64 *start, u64 *size, const char *name)
 {
 	u64 m_start = *start;
 	char path[PATH_MAX];
@@ -17,7 +18,35 @@ int arch__fix_module_text_start(u64 *start, const char *name)
 	if (sysfs__read_ull(path, (unsigned long long *)start) < 0) {
 		pr_debug2("Using module %s start:%#lx\n", path, m_start);
 		*start = m_start;
+	} else {
+		/* Successful read of the modules segment text start address.
+		 * Calculate difference between module start address
+		 * in memory and module text segment start address.
+		 * For example module load address is 0x3ff8011b000
+		 * (from /proc/modules) and module text segment start
+		 * address is 0x3ff8011b870 (from file above).
+		 *
+		 * Adjust the module size and subtract the GOT table
+		 * size located at the beginning of the module.
+		 */
+		*size -= (*start - m_start);
 	}
 
 	return 0;
 }
+
+/* On s390 kernel text segment start is located at very low memory addresses,
+ * for example 0x10000. Modules are located at very high memory addresses,
+ * for example 0x3ff xxxx xxxx. The gap between end of kernel text segment
+ * and beginning of first module's text segment is very big.
+ * Therefore do not fill this gap and do not assign it to the kernel dso map.
+ */
+void arch__symbols__fixup_end(struct symbol *p, struct symbol *c)
+{
+	if (strchr(p->name, '[') == NULL && strchr(c->name, '['))
+		/* Last kernel symbol mapped to end of page */
+		p->end = roundup(p->end, page_size);
+	else
+		p->end = c->start;
+	pr_debug4("%s sym:%s end:%#lx\n", __func__, p->name, p->end);
+}
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index c0065923a525..e1ac51aaedcf 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -712,6 +712,16 @@ __cmd_probe(int argc, const char **argv)
 
 		ret = perf_add_probe_events(params.events, params.nevents);
 		if (ret < 0) {
+
+			/*
+			 * When perf_add_probe_events() fails it calls
+			 * cleanup_perf_probe_events(pevs, npevs), i.e.
+			 * cleanup_perf_probe_events(params.events, params.nevents), which
+			 * will call clear_perf_probe_event(), so set nevents to zero
+			 * to avoid cleanup_params() to call clear_perf_probe_event() again
+			 * on the same pevs.
+			 */
+			params.nevents = 0;
 			pr_err_with_code("  Error: Failed to add events.", ret);
 			return ret;
 		}
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 26437143c940..c892a28e7b04 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -3081,7 +3081,7 @@ int perf_event__process_feature(struct perf_tool *tool,
 		return 0;
 
 	ff.buf  = (void *)fe->data;
-	ff.size = event->header.size - sizeof(event->header);
+	ff.size = event->header.size - sizeof(*fe);
 	ff.ph = &session->header;
 
 	if (feat_ops[feat].process(&ff, NULL))
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index d246080cd85e..5145c6a84c47 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1233,6 +1233,7 @@ static int machine__set_modules_path(struct machine *machine)
 	return map_groups__set_modules_path_dir(&machine->kmaps, modules_path, 0);
 }
 int __weak arch__fix_module_text_start(u64 *start __maybe_unused,
+				u64 *size __maybe_unused,
 				const char *name __maybe_unused)
 {
 	return 0;
@@ -1244,7 +1245,7 @@ static int machine__create_module(void *arg, const char *name, u64 start,
 	struct machine *machine = arg;
 	struct map *map;
 
-	if (arch__fix_module_text_start(&start, name) < 0)
+	if (arch__fix_module_text_start(&start, &size, name) < 0)
 		return -1;
 
 	map = machine__findnew_module_map(machine, start, name);
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 13041b036a5b..ec339cdf854c 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -213,7 +213,7 @@ struct symbol *machine__find_kernel_function_by_name(struct machine *machine,
 
 struct map *machine__findnew_module_map(struct machine *machine, u64 start,
 					const char *filename);
-int arch__fix_module_text_start(u64 *start, const char *name);
+int arch__fix_module_text_start(u64 *start, u64 *size, const char *name);
 
 int __machine__load_kallsyms(struct machine *machine, const char *filename,
 			     enum map_type type, bool no_kcore);
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 3936f69f385c..27bffcb213eb 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -93,6 +93,11 @@ static int prefix_underscores_count(const char *str)
 	return tail - str;
 }
 
+void __weak arch__symbols__fixup_end(struct symbol *p, struct symbol *c)
+{
+	p->end = c->start;
+}
+
 const char * __weak arch__normalize_symbol_name(const char *name)
 {
 	return name;
@@ -219,7 +224,7 @@ void symbols__fixup_end(struct rb_root *symbols)
 		curr = rb_entry(nd, struct symbol, rb_node);
 
 		if (prev->end == prev->start && prev->end != curr->start)
-			prev->end = curr->start;
+			arch__symbols__fixup_end(prev, curr);
 	}
 
 	/* Last entry */
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 698c65e603a8..95ac21be8481 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -351,6 +351,7 @@ const char *arch__normalize_symbol_name(const char *name);
 #define SYMBOL_A 0
 #define SYMBOL_B 1
 
+void arch__symbols__fixup_end(struct symbol *p, struct symbol *c);
 int arch__compare_symbol_names(const char *namea, const char *nameb);
 int arch__compare_symbol_names_n(const char *namea, const char *nameb,
 				 unsigned int n);
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 1dbcd3c8dee0..177436c8e026 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -160,14 +160,24 @@ struct comm *thread__comm(const struct thread *thread)
 
 struct comm *thread__exec_comm(const struct thread *thread)
 {
-	struct comm *comm, *last = NULL;
+	struct comm *comm, *last = NULL, *second_last = NULL;
 
 	list_for_each_entry(comm, &thread->comm_list, list) {
 		if (comm->exec)
 			return comm;
+		second_last = last;
 		last = comm;
 	}
 
+	/*
+	 * 'last' with no start time might be the parent's comm of a synthesized
+	 * thread (created by processing a synthesized fork event). For a main
+	 * thread, that is very probably wrong. Prefer a later comm to avoid
+	 * that case.
+	 */
+	if (second_last && !last->start && thread->pid_ == thread->tid)
+		return second_last;
+
 	return last;
 }
 
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index dbbfcd082513..89fd40e57cae 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2314,6 +2314,29 @@ static bool kvm_vcpu_eligible_for_directed_yield(struct kvm_vcpu *vcpu)
 #endif
 }
 
+/*
+ * Unlike kvm_arch_vcpu_runnable, this function is called outside
+ * a vcpu_load/vcpu_put pair.  However, for most architectures
+ * kvm_arch_vcpu_runnable does not require vcpu_load.
+ */
+bool __weak kvm_arch_dy_runnable(struct kvm_vcpu *vcpu)
+{
+	return kvm_arch_vcpu_runnable(vcpu);
+}
+
+static bool vcpu_dy_runnable(struct kvm_vcpu *vcpu)
+{
+	if (kvm_arch_dy_runnable(vcpu))
+		return true;
+
+#ifdef CONFIG_KVM_ASYNC_PF
+	if (!list_empty_careful(&vcpu->async_pf.done))
+		return true;
+#endif
+
+	return false;
+}
+
 void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode)
 {
 	struct kvm *kvm = me->kvm;
@@ -2343,7 +2366,7 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode)
 				continue;
 			if (vcpu == me)
 				continue;
-			if (swait_active(&vcpu->wq) && !kvm_arch_vcpu_runnable(vcpu))
+			if (swait_active(&vcpu->wq) && !vcpu_dy_runnable(vcpu))
 				continue;
 			if (yield_to_kernel_mode && !kvm_arch_vcpu_in_kernel(vcpu))
 				continue;