diff --git a/Makefile b/Makefile
index cf9303a5d621..841675e63a38 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
 VERSION = 4
 PATCHLEVEL = 4
-SUBLEVEL = 56
+SUBLEVEL = 57
 EXTRAVERSION =
 NAME = Blurry Fish Butt
 
diff --git a/arch/powerpc/boot/zImage.lds.S b/arch/powerpc/boot/zImage.lds.S
index 861e72109df2..f080abfc2f83 100644
--- a/arch/powerpc/boot/zImage.lds.S
+++ b/arch/powerpc/boot/zImage.lds.S
@@ -68,6 +68,7 @@ SECTIONS
   }
 
 #ifdef CONFIG_PPC64_BOOT_WRAPPER
+  . = ALIGN(256);
   .got :
   {
     __toc_start = .;
diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c
index 5cc2e7af3a7b..b379146de55b 100644
--- a/arch/powerpc/kvm/emulate.c
+++ b/arch/powerpc/kvm/emulate.c
@@ -302,7 +302,6 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			advance = 0;
 			printk(KERN_ERR "Couldn't emulate instruction 0x%08x "
 			       "(op %d xop %d)\n", inst, get_op(inst), get_xop(inst));
-			kvmppc_core_queue_program(vcpu, 0);
 		}
 	}
 
diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c
index 3a40f718baef..4004e03267cd 100644
--- a/arch/s390/pci/pci_dma.c
+++ b/arch/s390/pci/pci_dma.c
@@ -455,7 +455,7 @@ int zpci_dma_init_device(struct zpci_dev *zdev)
 	zdev->dma_table = dma_alloc_cpu_table();
 	if (!zdev->dma_table) {
 		rc = -ENOMEM;
-		goto out_clean;
+		goto out;
 	}
 
 	/*
@@ -475,18 +475,22 @@ int zpci_dma_init_device(struct zpci_dev *zdev)
 	zdev->iommu_bitmap = vzalloc(zdev->iommu_pages / 8);
 	if (!zdev->iommu_bitmap) {
 		rc = -ENOMEM;
-		goto out_reg;
+		goto free_dma_table;
 	}
 
 	rc = zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma,
 				(u64) zdev->dma_table);
 	if (rc)
-		goto out_reg;
-	return 0;
+		goto free_bitmap;
 
-out_reg:
+	return 0;
+free_bitmap:
+	vfree(zdev->iommu_bitmap);
+	zdev->iommu_bitmap = NULL;
+free_dma_table:
 	dma_free_cpu_table(zdev->dma_table);
-out_clean:
+	zdev->dma_table = NULL;
+out:
 	return rc;
 }
 
diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c
index 440df0c7a2ee..a69321a77783 100644
--- a/arch/x86/crypto/ghash-clmulni-intel_glue.c
+++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c
@@ -219,6 +219,29 @@ static int ghash_async_final(struct ahash_request *req)
 	}
 }
 
+static int ghash_async_import(struct ahash_request *req, const void *in)
+{
+	struct ahash_request *cryptd_req = ahash_request_ctx(req);
+	struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
+	struct ghash_desc_ctx *dctx = shash_desc_ctx(desc);
+
+	ghash_async_init(req);
+	memcpy(dctx, in, sizeof(*dctx));
+	return 0;
+
+}
+
+static int ghash_async_export(struct ahash_request *req, void *out)
+{
+	struct ahash_request *cryptd_req = ahash_request_ctx(req);
+	struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
+	struct ghash_desc_ctx *dctx = shash_desc_ctx(desc);
+
+	memcpy(out, dctx, sizeof(*dctx));
+	return 0;
+
+}
+
 static int ghash_async_digest(struct ahash_request *req)
 {
 	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
@@ -288,8 +311,11 @@ static struct ahash_alg ghash_async_alg = {
 	.final		= ghash_async_final,
 	.setkey		= ghash_async_setkey,
 	.digest		= ghash_async_digest,
+	.export		= ghash_async_export,
+	.import		= ghash_async_import,
 	.halg = {
 		.digestsize	= GHASH_DIGEST_SIZE,
+		.statesize = sizeof(struct ghash_desc_ctx),
 		.base = {
 			.cra_name		= "ghash",
 			.cra_driver_name	= "ghash-clmulni",
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index 9e2ba5c6e1dd..f42e78de1e10 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -27,6 +27,12 @@ static bool xen_pvspin = true;
 
 static void xen_qlock_kick(int cpu)
 {
+	int irq = per_cpu(lock_kicker_irq, cpu);
+
+	/* Don't kick if the target's kicker interrupt is not initialized. */
+	if (irq == -1)
+		return;
+
 	xen_send_IPI_one(cpu, XEN_SPIN_UNLOCK_VECTOR);
 }
 
diff --git a/crypto/cryptd.c b/crypto/cryptd.c
index e7aa904cb20b..26a504db3f53 100644
--- a/crypto/cryptd.c
+++ b/crypto/cryptd.c
@@ -642,6 +642,7 @@ static int cryptd_create_hash(struct crypto_template *tmpl, struct rtattr **tb,
 	inst->alg.halg.base.cra_flags = type;
 
 	inst->alg.halg.digestsize = salg->digestsize;
+	inst->alg.halg.statesize = salg->statesize;
 	inst->alg.halg.base.cra_ctxsize = sizeof(struct cryptd_hash_ctx);
 
 	inst->alg.halg.base.cra_init = cryptd_hash_init_tfm;
diff --git a/crypto/mcryptd.c b/crypto/mcryptd.c
index a0ceb41d5ccc..b4f3930266b1 100644
--- a/crypto/mcryptd.c
+++ b/crypto/mcryptd.c
@@ -531,6 +531,7 @@ static int mcryptd_create_hash(struct crypto_template *tmpl, struct rtattr **tb,
 	inst->alg.halg.base.cra_flags = type;
 
 	inst->alg.halg.digestsize = salg->digestsize;
+	inst->alg.halg.statesize = salg->statesize;
 	inst->alg.halg.base.cra_ctxsize = sizeof(struct mcryptd_hash_ctx);
 
 	inst->alg.halg.base.cra_init = mcryptd_hash_init_tfm;
diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c
index 5fdac394207a..549cdbed7b0e 100644
--- a/drivers/acpi/acpi_video.c
+++ b/drivers/acpi/acpi_video.c
@@ -1211,6 +1211,9 @@ static int acpi_video_device_enumerate(struct acpi_video_bus *video)
 	union acpi_object *dod = NULL;
 	union acpi_object *obj;
 
+	if (!video->cap._DOD)
+		return AE_NOT_EXIST;
+
 	status = acpi_evaluate_object(video->device->handle, "_DOD", NULL, &buffer);
 	if (!ACPI_SUCCESS(status)) {
 		ACPI_EXCEPTION((AE_INFO, status, "Evaluating _DOD"));
diff --git a/drivers/char/tpm/tpm_tis.c b/drivers/char/tpm/tpm_tis.c
index 65f7eecc45b0..f10a107614b4 100644
--- a/drivers/char/tpm/tpm_tis.c
+++ b/drivers/char/tpm/tpm_tis.c
@@ -401,7 +401,7 @@ static void disable_interrupts(struct tpm_chip *chip)
 	iowrite32(intmask,
 		  chip->vendor.iobase +
 		  TPM_INT_ENABLE(chip->vendor.locality));
-	free_irq(chip->vendor.irq, chip);
+	devm_free_irq(chip->pdev, chip->vendor.irq, chip);
 	chip->vendor.irq = 0;
 }
 
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 8412ce5f93a7..86fa9fdc8323 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -626,9 +626,11 @@ static ssize_t show_cpuinfo_cur_freq(struct cpufreq_policy *policy,
 					char *buf)
 {
 	unsigned int cur_freq = __cpufreq_get(policy);
-	if (!cur_freq)
-		return sprintf(buf, "<unknown>");
-	return sprintf(buf, "%u\n", cur_freq);
+
+	if (cur_freq)
+		return sprintf(buf, "%u\n", cur_freq);
+
+	return sprintf(buf, "<unknown>\n");
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
index 7c42ff670080..a0924330d125 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
@@ -25,6 +25,7 @@
  *          Alex Deucher
  *          Jerome Glisse
  */
+#include <linux/irq.h>
 #include <drm/drmP.h>
 #include <drm/drm_crtc_helper.h>
 #include <drm/amdgpu_drm.h>
diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c
index 57c191798699..ddbf7e7e0d98 100644
--- a/drivers/hv/hv.c
+++ b/drivers/hv/hv.c
@@ -274,7 +274,7 @@ cleanup:
  *
  * This routine is called normally during driver unloading or exiting.
  */
-void hv_cleanup(void)
+void hv_cleanup(bool crash)
 {
 	union hv_x64_msr_hypercall_contents hypercall_msr;
 
@@ -284,7 +284,8 @@ void hv_cleanup(void)
 	if (hv_context.hypercall_page) {
 		hypercall_msr.as_uint64 = 0;
 		wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
-		vfree(hv_context.hypercall_page);
+		if (!crash)
+			vfree(hv_context.hypercall_page);
 		hv_context.hypercall_page = NULL;
 	}
 
@@ -304,7 +305,8 @@ void hv_cleanup(void)
 
 		hypercall_msr.as_uint64 = 0;
 		wrmsrl(HV_X64_MSR_REFERENCE_TSC, hypercall_msr.as_uint64);
-		vfree(hv_context.tsc_page);
+		if (!crash)
+			vfree(hv_context.tsc_page);
 		hv_context.tsc_page = NULL;
 	}
 #endif
diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c
index b853b4b083bd..43af91362be5 100644
--- a/drivers/hv/hv_balloon.c
+++ b/drivers/hv/hv_balloon.c
@@ -714,7 +714,7 @@ static bool pfn_covered(unsigned long start_pfn, unsigned long pfn_cnt)
 		 * If the pfn range we are dealing with is not in the current
 		 * "hot add block", move on.
 		 */
-		if ((start_pfn >= has->end_pfn))
+		if (start_pfn < has->start_pfn || start_pfn >= has->end_pfn)
 			continue;
 		/*
 		 * If the current hot add-request extends beyond
@@ -768,7 +768,7 @@ static unsigned long handle_pg_range(unsigned long pg_start,
 		 * If the pfn range we are dealing with is not in the current
 		 * "hot add block", move on.
 		 */
-		if ((start_pfn >= has->end_pfn))
+		if (start_pfn < has->start_pfn || start_pfn >= has->end_pfn)
 			continue;
 
 		old_covered_state = has->covered_end_pfn;
diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
index 12156db2e88e..75e383e6d03d 100644
--- a/drivers/hv/hyperv_vmbus.h
+++ b/drivers/hv/hyperv_vmbus.h
@@ -581,7 +581,7 @@ struct hv_ring_buffer_debug_info {
 
 extern int hv_init(void);
 
-extern void hv_cleanup(void);
+extern void hv_cleanup(bool crash);
 
 extern int hv_post_message(union hv_connection_id connection_id,
 			 enum hv_message_type message_type,
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 509ed9731630..802dcb409030 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -889,7 +889,7 @@ err_alloc:
 	bus_unregister(&hv_bus);
 
 err_cleanup:
-	hv_cleanup();
+	hv_cleanup(false);
 
 	return ret;
 }
@@ -1254,7 +1254,7 @@ static void hv_kexec_handler(void)
 	vmbus_initiate_unload();
 	for_each_online_cpu(cpu)
 		smp_call_function_single(cpu, hv_synic_cleanup, NULL, 1);
-	hv_cleanup();
+	hv_cleanup(false);
 };
 
 static void hv_crash_handler(struct pt_regs *regs)
@@ -1266,7 +1266,7 @@ static void hv_crash_handler(struct pt_regs *regs)
 	 * for kdump.
 	 */
 	hv_synic_cleanup(NULL);
-	hv_cleanup();
+	hv_cleanup(true);
 };
 
 static int __init hv_acpi_init(void)
@@ -1330,7 +1330,7 @@ static void __exit vmbus_exit(void)
 						 &hyperv_panic_block);
 	}
 	bus_unregister(&hv_bus);
-	hv_cleanup();
+	hv_cleanup(false);
 	for_each_online_cpu(cpu) {
 		tasklet_kill(hv_context.event_dpc[cpu]);
 		smp_call_function_single(cpu, hv_synic_cleanup, NULL, 1);
diff --git a/drivers/isdn/gigaset/bas-gigaset.c b/drivers/isdn/gigaset/bas-gigaset.c
index aecec6d32463..7f1c625b08ec 100644
--- a/drivers/isdn/gigaset/bas-gigaset.c
+++ b/drivers/isdn/gigaset/bas-gigaset.c
@@ -2317,6 +2317,9 @@ static int gigaset_probe(struct usb_interface *interface,
 		return -ENODEV;
 	}
 
+	if (hostif->desc.bNumEndpoints < 1)
+		return -ENODEV;
+
 	dev_info(&udev->dev,
 		 "%s: Device matched (Vendor: 0x%x, Product: 0x%x)\n",
 		 __func__, le16_to_cpu(udev->descriptor.idVendor),
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index ebb0dd612ebd..122af340a531 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1477,7 +1477,25 @@ static void make_request(struct mddev *mddev, struct bio *bio)
 			split = bio;
 		}
 
+		/*
+		 * If a bio is splitted, the first part of bio will pass
+		 * barrier but the bio is queued in current->bio_list (see
+		 * generic_make_request). If there is a raise_barrier() called
+		 * here, the second part of bio can't pass barrier. But since
+		 * the first part bio isn't dispatched to underlaying disks
+		 * yet, the barrier is never released, hence raise_barrier will
+		 * alays wait. We have a deadlock.
+		 * Note, this only happens in read path. For write path, the
+		 * first part of bio is dispatched in a schedule() call
+		 * (because of blk plug) or offloaded to raid10d.
+		 * Quitting from the function immediately can change the bio
+		 * order queued in bio_list and avoid the deadlock.
+		 */
 		__make_request(mddev, split);
+		if (split != bio && bio_data_dir(bio) == READ) {
+			generic_make_request(bio);
+			break;
+		}
 	} while (split != bio);
 
 	/* In case raid10d snuck in to freeze_array */
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index e8a09ff9e724..c8a7802d2953 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -197,65 +197,6 @@ static void *init_ppi_data(struct rndis_message *msg, u32 ppi_size,
 	return ppi;
 }
 
-union sub_key {
-	u64 k;
-	struct {
-		u8 pad[3];
-		u8 kb;
-		u32 ka;
-	};
-};
-
-/* Toeplitz hash function
- * data: network byte order
- * return: host byte order
- */
-static u32 comp_hash(u8 *key, int klen, void *data, int dlen)
-{
-	union sub_key subk;
-	int k_next = 4;
-	u8 dt;
-	int i, j;
-	u32 ret = 0;
-
-	subk.k = 0;
-	subk.ka = ntohl(*(u32 *)key);
-
-	for (i = 0; i < dlen; i++) {
-		subk.kb = key[k_next];
-		k_next = (k_next + 1) % klen;
-		dt = ((u8 *)data)[i];
-		for (j = 0; j < 8; j++) {
-			if (dt & 0x80)
-				ret ^= subk.ka;
-			dt <<= 1;
-			subk.k <<= 1;
-		}
-	}
-
-	return ret;
-}
-
-static bool netvsc_set_hash(u32 *hash, struct sk_buff *skb)
-{
-	struct flow_keys flow;
-	int data_len;
-
-	if (!skb_flow_dissect_flow_keys(skb, &flow, 0) ||
-	    !(flow.basic.n_proto == htons(ETH_P_IP) ||
-	      flow.basic.n_proto == htons(ETH_P_IPV6)))
-		return false;
-
-	if (flow.basic.ip_proto == IPPROTO_TCP)
-		data_len = 12;
-	else
-		data_len = 8;
-
-	*hash = comp_hash(netvsc_hash_key, HASH_KEYLEN, &flow, data_len);
-
-	return true;
-}
-
 static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb,
 			void *accel_priv, select_queue_fallback_t fallback)
 {
@@ -268,11 +209,9 @@ static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb,
 	if (nvsc_dev == NULL || ndev->real_num_tx_queues <= 1)
 		return 0;
 
-	if (netvsc_set_hash(&hash, skb)) {
-		q_idx = nvsc_dev->send_table[hash % VRSS_SEND_TAB_SIZE] %
-			ndev->real_num_tx_queues;
-		skb_set_hash(skb, hash, PKT_HASH_TYPE_L3);
-	}
+	hash = skb_get_hash(skb);
+	q_idx = nvsc_dev->send_table[hash % VRSS_SEND_TAB_SIZE] %
+		ndev->real_num_tx_queues;
 
 	return q_idx;
 }
diff --git a/drivers/pinctrl/intel/pinctrl-cherryview.c b/drivers/pinctrl/intel/pinctrl-cherryview.c
index a009ae34c5ef..930f0f25c1ce 100644
--- a/drivers/pinctrl/intel/pinctrl-cherryview.c
+++ b/drivers/pinctrl/intel/pinctrl-cherryview.c
@@ -1466,12 +1466,11 @@ static int chv_gpio_probe(struct chv_pinctrl *pctrl, int irq)
 		offset += range->npins;
 	}
 
-	/* Mask and clear all interrupts */
-	chv_writel(0, pctrl->regs + CHV_INTMASK);
+	/* Clear all interrupts */
 	chv_writel(0xffff, pctrl->regs + CHV_INTSTAT);
 
 	ret = gpiochip_irqchip_add(chip, &chv_gpio_irqchip, 0,
-				   handle_simple_irq, IRQ_TYPE_NONE);
+				   handle_bad_irq, IRQ_TYPE_NONE);
 	if (ret) {
 		dev_err(pctrl->dev, "failed to add IRQ chip\n");
 		goto fail;
diff --git a/drivers/scsi/cxlflash/common.h b/drivers/scsi/cxlflash/common.h
index 5ada9268a450..a8ac4c0a1493 100644
--- a/drivers/scsi/cxlflash/common.h
+++ b/drivers/scsi/cxlflash/common.h
@@ -34,7 +34,6 @@ extern const struct file_operations cxlflash_cxl_fops;
 								   sectors
 								*/
 
-#define NUM_RRQ_ENTRY    16     /* for master issued cmds */
 #define MAX_RHT_PER_CONTEXT (PAGE_SIZE / sizeof(struct sisl_rht_entry))
 
 /* AFU command retry limit */
@@ -48,9 +47,12 @@ extern const struct file_operations cxlflash_cxl_fops;
 							   index derivation
 							 */
 
-#define CXLFLASH_MAX_CMDS               16
+#define CXLFLASH_MAX_CMDS               256
 #define CXLFLASH_MAX_CMDS_PER_LUN       CXLFLASH_MAX_CMDS
 
+/* RRQ for master issued cmds */
+#define NUM_RRQ_ENTRY                   CXLFLASH_MAX_CMDS
+
 
 static inline void check_sizes(void)
 {
@@ -149,7 +151,7 @@ struct afu_cmd {
 struct afu {
 	/* Stuff requiring alignment go first. */
 
-	u64 rrq_entry[NUM_RRQ_ENTRY];	/* 128B RRQ */
+	u64 rrq_entry[NUM_RRQ_ENTRY];	/* 2K RRQ */
 	/*
 	 * Command & data for AFU commands.
 	 */
diff --git a/drivers/scsi/cxlflash/main.c b/drivers/scsi/cxlflash/main.c
index c86847c68448..2882bcac918a 100644
--- a/drivers/scsi/cxlflash/main.c
+++ b/drivers/scsi/cxlflash/main.c
@@ -2305,7 +2305,7 @@ static struct scsi_host_template driver_template = {
 	.eh_device_reset_handler = cxlflash_eh_device_reset_handler,
 	.eh_host_reset_handler = cxlflash_eh_host_reset_handler,
 	.change_queue_depth = cxlflash_change_queue_depth,
-	.cmd_per_lun = 16,
+	.cmd_per_lun = CXLFLASH_MAX_CMDS_PER_LUN,
 	.can_queue = CXLFLASH_MAX_CMDS,
 	.this_id = -1,
 	.sg_tablesize = SG_NONE,	/* No scatter gather support */
diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
index 6bffd91b973a..c1ccf1ee99ea 100644
--- a/drivers/scsi/libiscsi.c
+++ b/drivers/scsi/libiscsi.c
@@ -560,8 +560,12 @@ static void iscsi_complete_task(struct iscsi_task *task, int state)
 	WARN_ON_ONCE(task->state == ISCSI_TASK_FREE);
 	task->state = state;
 
-	if (!list_empty(&task->running))
+	spin_lock_bh(&conn->taskqueuelock);
+	if (!list_empty(&task->running)) {
+		pr_debug_once("%s while task on list", __func__);
 		list_del_init(&task->running);
+	}
+	spin_unlock_bh(&conn->taskqueuelock);
 
 	if (conn->task == task)
 		conn->task = NULL;
@@ -783,7 +787,9 @@ __iscsi_conn_send_pdu(struct iscsi_conn *conn, struct iscsi_hdr *hdr,
 		if (session->tt->xmit_task(task))
 			goto free_task;
 	} else {
+		spin_lock_bh(&conn->taskqueuelock);
 		list_add_tail(&task->running, &conn->mgmtqueue);
+		spin_unlock_bh(&conn->taskqueuelock);
 		iscsi_conn_queue_work(conn);
 	}
 
@@ -1474,8 +1480,10 @@ void iscsi_requeue_task(struct iscsi_task *task)
 	 * this may be on the requeue list already if the xmit_task callout
 	 * is handling the r2ts while we are adding new ones
 	 */
+	spin_lock_bh(&conn->taskqueuelock);
 	if (list_empty(&task->running))
 		list_add_tail(&task->running, &conn->requeue);
+	spin_unlock_bh(&conn->taskqueuelock);
 	iscsi_conn_queue_work(conn);
 }
 EXPORT_SYMBOL_GPL(iscsi_requeue_task);
@@ -1512,22 +1520,26 @@ static int iscsi_data_xmit(struct iscsi_conn *conn)
 	 * only have one nop-out as a ping from us and targets should not
 	 * overflow us with nop-ins
 	 */
+	spin_lock_bh(&conn->taskqueuelock);
 check_mgmt:
 	while (!list_empty(&conn->mgmtqueue)) {
 		conn->task = list_entry(conn->mgmtqueue.next,
 					 struct iscsi_task, running);
 		list_del_init(&conn->task->running);
+		spin_unlock_bh(&conn->taskqueuelock);
 		if (iscsi_prep_mgmt_task(conn, conn->task)) {
 			/* regular RX path uses back_lock */
 			spin_lock_bh(&conn->session->back_lock);
 			__iscsi_put_task(conn->task);
 			spin_unlock_bh(&conn->session->back_lock);
 			conn->task = NULL;
+			spin_lock_bh(&conn->taskqueuelock);
 			continue;
 		}
 		rc = iscsi_xmit_task(conn);
 		if (rc)
 			goto done;
+		spin_lock_bh(&conn->taskqueuelock);
 	}
 
 	/* process pending command queue */
@@ -1535,19 +1547,24 @@ check_mgmt:
 		conn->task = list_entry(conn->cmdqueue.next, struct iscsi_task,
 					running);
 		list_del_init(&conn->task->running);
+		spin_unlock_bh(&conn->taskqueuelock);
 		if (conn->session->state == ISCSI_STATE_LOGGING_OUT) {
 			fail_scsi_task(conn->task, DID_IMM_RETRY);
+			spin_lock_bh(&conn->taskqueuelock);
 			continue;
 		}
 		rc = iscsi_prep_scsi_cmd_pdu(conn->task);
 		if (rc) {
 			if (rc == -ENOMEM || rc == -EACCES) {
+				spin_lock_bh(&conn->taskqueuelock);
 				list_add_tail(&conn->task->running,
 					      &conn->cmdqueue);
 				conn->task = NULL;
+				spin_unlock_bh(&conn->taskqueuelock);
 				goto done;
 			} else
 				fail_scsi_task(conn->task, DID_ABORT);
+			spin_lock_bh(&conn->taskqueuelock);
 			continue;
 		}
 		rc = iscsi_xmit_task(conn);
@@ -1558,6 +1575,7 @@ check_mgmt:
 		 * we need to check the mgmt queue for nops that need to
 		 * be sent to aviod starvation
 		 */
+		spin_lock_bh(&conn->taskqueuelock);
 		if (!list_empty(&conn->mgmtqueue))
 			goto check_mgmt;
 	}
@@ -1577,12 +1595,15 @@ check_mgmt:
 		conn->task = task;
 		list_del_init(&conn->task->running);
 		conn->task->state = ISCSI_TASK_RUNNING;
+		spin_unlock_bh(&conn->taskqueuelock);
 		rc = iscsi_xmit_task(conn);
 		if (rc)
 			goto done;
+		spin_lock_bh(&conn->taskqueuelock);
 		if (!list_empty(&conn->mgmtqueue))
 			goto check_mgmt;
 	}
+	spin_unlock_bh(&conn->taskqueuelock);
 	spin_unlock_bh(&conn->session->frwd_lock);
 	return -ENODATA;
 
@@ -1738,7 +1759,9 @@ int iscsi_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *sc)
 			goto prepd_reject;
 		}
 	} else {
+		spin_lock_bh(&conn->taskqueuelock);
 		list_add_tail(&task->running, &conn->cmdqueue);
+		spin_unlock_bh(&conn->taskqueuelock);
 		iscsi_conn_queue_work(conn);
 	}
 
@@ -2900,6 +2923,7 @@ iscsi_conn_setup(struct iscsi_cls_session *cls_session, int dd_size,
 	INIT_LIST_HEAD(&conn->mgmtqueue);
 	INIT_LIST_HEAD(&conn->cmdqueue);
 	INIT_LIST_HEAD(&conn->requeue);
+	spin_lock_init(&conn->taskqueuelock);
 	INIT_WORK(&conn->xmitwork, iscsi_xmitworker);
 
 	/* allocate login_task used for the login/text sequences */
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index c14ab6c3ae40..60c21093f865 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -11387,6 +11387,7 @@ static struct pci_driver lpfc_driver = {
 	.id_table	= lpfc_id_table,
 	.probe		= lpfc_pci_probe_one,
 	.remove		= lpfc_pci_remove_one,
+	.shutdown	= lpfc_pci_remove_one,
 	.suspend        = lpfc_pci_suspend_one,
 	.resume		= lpfc_pci_resume_one,
 	.err_handler    = &lpfc_err_handler,
diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c
index de18790eb21c..d72a4058fd08 100644
--- a/drivers/target/target_core_pscsi.c
+++ b/drivers/target/target_core_pscsi.c
@@ -154,7 +154,7 @@ static void pscsi_tape_read_blocksize(struct se_device *dev,
 
 	buf = kzalloc(12, GFP_KERNEL);
 	if (!buf)
-		return;
+		goto out_free;
 
 	memset(cdb, 0, MAX_COMMAND_SIZE);
 	cdb[0] = MODE_SENSE;
@@ -169,9 +169,10 @@ static void pscsi_tape_read_blocksize(struct se_device *dev,
 	 * If MODE_SENSE still returns zero, set the default value to 1024.
 	 */
 	sdev->sector_size = (buf[9] << 16) | (buf[10] << 8) | (buf[11]);
+out_free:
 	if (!sdev->sector_size)
 		sdev->sector_size = 1024;
-out_free:
+
 	kfree(buf);
 }
 
@@ -314,9 +315,10 @@ static int pscsi_add_device_to_list(struct se_device *dev,
 				sd->lun, sd->queue_depth);
 	}
 
-	dev->dev_attrib.hw_block_size = sd->sector_size;
+	dev->dev_attrib.hw_block_size =
+		min_not_zero((int)sd->sector_size, 512);
 	dev->dev_attrib.hw_max_sectors =
-		min_t(int, sd->host->max_sectors, queue_max_hw_sectors(q));
+		min_not_zero(sd->host->max_sectors, queue_max_hw_sectors(q));
 	dev->dev_attrib.hw_queue_depth = sd->queue_depth;
 
 	/*
@@ -339,8 +341,10 @@ static int pscsi_add_device_to_list(struct se_device *dev,
 	/*
 	 * For TYPE_TAPE, attempt to determine blocksize with MODE_SENSE.
 	 */
-	if (sd->type == TYPE_TAPE)
+	if (sd->type == TYPE_TAPE) {
 		pscsi_tape_read_blocksize(dev, sd);
+		dev->dev_attrib.hw_block_size = sd->sector_size;
+	}
 	return 0;
 }
 
@@ -406,7 +410,7 @@ static int pscsi_create_type_disk(struct se_device *dev, struct scsi_device *sd)
 /*
  * Called with struct Scsi_Host->host_lock called.
  */
-static int pscsi_create_type_rom(struct se_device *dev, struct scsi_device *sd)
+static int pscsi_create_type_nondisk(struct se_device *dev, struct scsi_device *sd)
 	__releases(sh->host_lock)
 {
 	struct pscsi_hba_virt *phv = dev->se_hba->hba_ptr;
@@ -433,28 +437,6 @@ static int pscsi_create_type_rom(struct se_device *dev, struct scsi_device *sd)
 	return 0;
 }
 
-/*
- * Called with struct Scsi_Host->host_lock called.
- */
-static int pscsi_create_type_other(struct se_device *dev,
-		struct scsi_device *sd)
-	__releases(sh->host_lock)
-{
-	struct pscsi_hba_virt *phv = dev->se_hba->hba_ptr;
-	struct Scsi_Host *sh = sd->host;
-	int ret;
-
-	spin_unlock_irq(sh->host_lock);
-	ret = pscsi_add_device_to_list(dev, sd);
-	if (ret)
-		return ret;
-
-	pr_debug("CORE_PSCSI[%d] - Added Type: %s for %d:%d:%d:%llu\n",
-		phv->phv_host_id, scsi_device_type(sd->type), sh->host_no,
-		sd->channel, sd->id, sd->lun);
-	return 0;
-}
-
 static int pscsi_configure_device(struct se_device *dev)
 {
 	struct se_hba *hba = dev->se_hba;
@@ -542,11 +524,8 @@ static int pscsi_configure_device(struct se_device *dev)
 		case TYPE_DISK:
 			ret = pscsi_create_type_disk(dev, sd);
 			break;
-		case TYPE_ROM:
-			ret = pscsi_create_type_rom(dev, sd);
-			break;
 		default:
-			ret = pscsi_create_type_other(dev, sd);
+			ret = pscsi_create_type_nondisk(dev, sd);
 			break;
 		}
 
@@ -611,8 +590,7 @@ static void pscsi_free_device(struct se_device *dev)
 		else if (pdv->pdv_lld_host)
 			scsi_host_put(pdv->pdv_lld_host);
 
-		if ((sd->type == TYPE_DISK) || (sd->type == TYPE_ROM))
-			scsi_device_put(sd);
+		scsi_device_put(sd);
 
 		pdv->pdv_sd = NULL;
 	}
@@ -1088,7 +1066,6 @@ static sector_t pscsi_get_blocks(struct se_device *dev)
 	if (pdv->pdv_bd && pdv->pdv_bd->bd_part)
 		return pdv->pdv_bd->bd_part->nr_sects;
 
-	dump_stack();
 	return 0;
 }
 
diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c
index 2e27b1034ede..90c5dffc9fa4 100644
--- a/drivers/target/target_core_sbc.c
+++ b/drivers/target/target_core_sbc.c
@@ -1096,9 +1096,15 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops)
 			return ret;
 		break;
 	case VERIFY:
+	case VERIFY_16:
 		size = 0;
-		sectors = transport_get_sectors_10(cdb);
-		cmd->t_task_lba = transport_lba_32(cdb);
+		if (cdb[0] == VERIFY) {
+			sectors = transport_get_sectors_10(cdb);
+			cmd->t_task_lba = transport_lba_32(cdb);
+		} else {
+			sectors = transport_get_sectors_16(cdb);
+			cmd->t_task_lba = transport_lba_64(cdb);
+		}
 		cmd->execute_cmd = sbc_emulate_noop;
 		goto check_lba;
 	case REZERO_UNIT:
diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index f44ce09367bc..5724d7c41e29 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -966,7 +966,7 @@ static void usb_bus_init (struct usb_bus *bus)
 	bus->bandwidth_allocated = 0;
 	bus->bandwidth_int_reqs  = 0;
 	bus->bandwidth_isoc_reqs = 0;
-	mutex_init(&bus->usb_address0_mutex);
+	mutex_init(&bus->devnum_next_mutex);
 
 	INIT_LIST_HEAD (&bus->bus_list);
 }
@@ -2497,6 +2497,14 @@ struct usb_hcd *usb_create_shared_hcd(const struct hc_driver *driver,
 		return NULL;
 	}
 	if (primary_hcd == NULL) {
+		hcd->address0_mutex = kmalloc(sizeof(*hcd->address0_mutex),
+				GFP_KERNEL);
+		if (!hcd->address0_mutex) {
+			kfree(hcd);
+			dev_dbg(dev, "hcd address0 mutex alloc failed\n");
+			return NULL;
+		}
+		mutex_init(hcd->address0_mutex);
 		hcd->bandwidth_mutex = kmalloc(sizeof(*hcd->bandwidth_mutex),
 				GFP_KERNEL);
 		if (!hcd->bandwidth_mutex) {
@@ -2508,6 +2516,7 @@ struct usb_hcd *usb_create_shared_hcd(const struct hc_driver *driver,
 		dev_set_drvdata(dev, hcd);
 	} else {
 		mutex_lock(&usb_port_peer_mutex);
+		hcd->address0_mutex = primary_hcd->address0_mutex;
 		hcd->bandwidth_mutex = primary_hcd->bandwidth_mutex;
 		hcd->primary_hcd = primary_hcd;
 		primary_hcd->primary_hcd = primary_hcd;
@@ -2564,24 +2573,23 @@ EXPORT_SYMBOL_GPL(usb_create_hcd);
  * Don't deallocate the bandwidth_mutex until the last shared usb_hcd is
  * deallocated.
  *
- * Make sure to only deallocate the bandwidth_mutex when the primary HCD is
- * freed.  When hcd_release() is called for either hcd in a peer set
- * invalidate the peer's ->shared_hcd and ->primary_hcd pointers to
- * block new peering attempts
+ * Make sure to deallocate the bandwidth_mutex only when the last HCD is
+ * freed.  When hcd_release() is called for either hcd in a peer set,
+ * invalidate the peer's ->shared_hcd and ->primary_hcd pointers.
  */
 static void hcd_release(struct kref *kref)
 {
 	struct usb_hcd *hcd = container_of (kref, struct usb_hcd, kref);
 
 	mutex_lock(&usb_port_peer_mutex);
-	if (usb_hcd_is_primary_hcd(hcd))
-		kfree(hcd->bandwidth_mutex);
 	if (hcd->shared_hcd) {
 		struct usb_hcd *peer = hcd->shared_hcd;
 
 		peer->shared_hcd = NULL;
-		if (peer->primary_hcd == hcd)
-			peer->primary_hcd = NULL;
+		peer->primary_hcd = NULL;
+	} else {
+		kfree(hcd->address0_mutex);
+		kfree(hcd->bandwidth_mutex);
 	}
 	mutex_unlock(&usb_port_peer_mutex);
 	kfree(hcd);
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 780db8bb2262..f52d8abf6979 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -1980,7 +1980,7 @@ static void choose_devnum(struct usb_device *udev)
 	struct usb_bus	*bus = udev->bus;
 
 	/* be safe when more hub events are proceed in parallel */
-	mutex_lock(&bus->usb_address0_mutex);
+	mutex_lock(&bus->devnum_next_mutex);
 	if (udev->wusb) {
 		devnum = udev->portnum + 1;
 		BUG_ON(test_bit(devnum, bus->devmap.devicemap));
@@ -1998,7 +1998,7 @@ static void choose_devnum(struct usb_device *udev)
 		set_bit(devnum, bus->devmap.devicemap);
 		udev->devnum = devnum;
 	}
-	mutex_unlock(&bus->usb_address0_mutex);
+	mutex_unlock(&bus->devnum_next_mutex);
 }
 
 static void release_devnum(struct usb_device *udev)
@@ -4262,7 +4262,7 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1,
 	if (oldspeed == USB_SPEED_LOW)
 		delay = HUB_LONG_RESET_TIME;
 
-	mutex_lock(&hdev->bus->usb_address0_mutex);
+	mutex_lock(hcd->address0_mutex);
 
 	/* Reset the device; full speed may morph to high speed */
 	/* FIXME a USB 2.0 device may morph into SuperSpeed on reset. */
@@ -4548,7 +4548,7 @@ fail:
 		hub_port_disable(hub, port1, 0);
 		update_devnum(udev, devnum);	/* for disconnect processing */
 	}
-	mutex_unlock(&hdev->bus->usb_address0_mutex);
+	mutex_unlock(hcd->address0_mutex);
 	return retval;
 }
 
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 6fe8e30eeb99..68345a9e59b8 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -3666,7 +3666,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	db_count = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) - 1) /
 		   EXT4_DESC_PER_BLOCK(sb);
 	if (ext4_has_feature_meta_bg(sb)) {
-		if (le32_to_cpu(es->s_first_meta_bg) >= db_count) {
+		if (le32_to_cpu(es->s_first_meta_bg) > db_count) {
 			ext4_msg(sb, KERN_WARNING,
 				 "first meta block group too large: %u "
 				 "(group descriptor block count %u)",
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index de7b4f97ac75..be519416c112 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -207,7 +207,7 @@ struct lm_lockname {
 	struct gfs2_sbd *ln_sbd;
 	u64 ln_number;
 	unsigned int ln_type;
-};
+} __packed __aligned(sizeof(int));
 
 #define lm_name_equal(name1, name2) \
         (((name1)->ln_number == (name2)->ln_number) &&	\
diff --git a/include/linux/log2.h b/include/linux/log2.h
index fd7ff3d91e6a..f38fae23bdac 100644
--- a/include/linux/log2.h
+++ b/include/linux/log2.h
@@ -16,12 +16,6 @@
 #include <linux/bitops.h>
 
 /*
- * deal with unrepresentable constant logarithms
- */
-extern __attribute__((const, noreturn))
-int ____ilog2_NaN(void);
-
-/*
  * non-constant log of base 2 calculators
  * - the arch may override these in asm/bitops.h if they can be implemented
  *   more efficiently than using fls() and fls64()
@@ -85,7 +79,7 @@ unsigned long __rounddown_pow_of_two(unsigned long n)
 #define ilog2(n)				\
 (						\
 	__builtin_constant_p(n) ? (		\
-		(n) < 1 ? ____ilog2_NaN() :	\
+		(n) < 2 ? 0 :			\
 		(n) & (1ULL << 63) ? 63 :	\
 		(n) & (1ULL << 62) ? 62 :	\
 		(n) & (1ULL << 61) ? 61 :	\
@@ -148,10 +142,7 @@ unsigned long __rounddown_pow_of_two(unsigned long n)
 		(n) & (1ULL <<  4) ?  4 :	\
 		(n) & (1ULL <<  3) ?  3 :	\
 		(n) & (1ULL <<  2) ?  2 :	\
-		(n) & (1ULL <<  1) ?  1 :	\
-		(n) & (1ULL <<  0) ?  0 :	\
-		____ilog2_NaN()			\
-				   ) :		\
+		1 ) :				\
 	(sizeof(n) <= 4) ?			\
 	__ilog2_u32(n) :			\
 	__ilog2_u64(n)				\
diff --git a/include/linux/usb.h b/include/linux/usb.h
index 12891ffd4bf0..8c75af6b7d5b 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -371,14 +371,13 @@ struct usb_bus {
 
 	int devnum_next;		/* Next open device number in
 					 * round-robin allocation */
+	struct mutex devnum_next_mutex; /* devnum_next mutex */
 
 	struct usb_devmap devmap;	/* device address allocation map */
 	struct usb_device *root_hub;	/* Root hub */
 	struct usb_bus *hs_companion;	/* Companion EHCI bus, if any */
 	struct list_head bus_list;	/* list of busses */
 
-	struct mutex usb_address0_mutex; /* unaddressed device mutex */
-
 	int bandwidth_allocated;	/* on this bus: how much of the time
 					 * reserved for periodic (intr/iso)
 					 * requests is used, on average?
diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h
index f89c24bd53a4..3993b21f3d11 100644
--- a/include/linux/usb/hcd.h
+++ b/include/linux/usb/hcd.h
@@ -180,6 +180,7 @@ struct usb_hcd {
 	 * bandwidth_mutex should be dropped after a successful control message
 	 * to the device, or resetting the bandwidth after a failed attempt.
 	 */
+	struct mutex		*address0_mutex;
 	struct mutex		*bandwidth_mutex;
 	struct usb_hcd		*shared_hcd;
 	struct usb_hcd		*primary_hcd;
diff --git a/include/scsi/libiscsi.h b/include/scsi/libiscsi.h
index 4d1c46aac331..c7b1dc713cdd 100644
--- a/include/scsi/libiscsi.h
+++ b/include/scsi/libiscsi.h
@@ -196,6 +196,7 @@ struct iscsi_conn {
 	struct iscsi_task	*task;		/* xmit task in progress */
 
 	/* xmit */
+	spinlock_t		taskqueuelock;  /* protects the next three lists */
 	struct list_head	mgmtqueue;	/* mgmt (control) xmit queue */
 	struct list_head	cmdqueue;	/* data-path cmd queue */
 	struct list_head	requeue;	/* tasks needing another run */
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 9bbe9ac23cf2..e4b5494f05f8 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -9230,7 +9230,7 @@ static int perf_event_init_context(struct task_struct *child, int ctxn)
 		ret = inherit_task_group(event, parent, parent_ctx,
 					 child, ctxn, &inherited_all);
 		if (ret)
-			break;
+			goto out_unlock;
 	}
 
 	/*
@@ -9246,7 +9246,7 @@ static int perf_event_init_context(struct task_struct *child, int ctxn)
 		ret = inherit_task_group(event, parent, parent_ctx,
 					 child, ctxn, &inherited_all);
 		if (ret)
-			break;
+			goto out_unlock;
 	}
 
 	raw_spin_lock_irqsave(&parent_ctx->lock, flags);
@@ -9274,6 +9274,7 @@ static int perf_event_init_context(struct task_struct *child, int ctxn)
 	}
 
 	raw_spin_unlock_irqrestore(&parent_ctx->lock, flags);
+out_unlock:
 	mutex_unlock(&parent_ctx->mutex);
 
 	perf_unpin_context(parent_ctx);
diff --git a/kernel/fork.c b/kernel/fork.c
index 2e55b53399de..278a2ddad351 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -331,13 +331,14 @@ void set_task_stack_end_magic(struct task_struct *tsk)
 	*stackend = STACK_END_MAGIC;	/* for overflow detection */
 }
 
-static struct task_struct *dup_task_struct(struct task_struct *orig)
+static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 {
 	struct task_struct *tsk;
 	struct thread_info *ti;
-	int node = tsk_fork_get_node(orig);
 	int err;
 
+	if (node == NUMA_NO_NODE)
+		node = tsk_fork_get_node(orig);
 	tsk = alloc_task_struct_node(node);
 	if (!tsk)
 		return NULL;
@@ -1270,7 +1271,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 					int __user *child_tidptr,
 					struct pid *pid,
 					int trace,
-					unsigned long tls)
+					unsigned long tls,
+					int node)
 {
 	int retval;
 	struct task_struct *p;
@@ -1323,7 +1325,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		goto fork_out;
 
 	retval = -ENOMEM;
-	p = dup_task_struct(current);
+	p = dup_task_struct(current, node);
 	if (!p)
 		goto fork_out;
 
@@ -1699,7 +1701,8 @@ static inline void init_idle_pids(struct pid_link *links)
 struct task_struct *fork_idle(int cpu)
 {
 	struct task_struct *task;
-	task = copy_process(CLONE_VM, 0, 0, NULL, &init_struct_pid, 0, 0);
+	task = copy_process(CLONE_VM, 0, 0, NULL, &init_struct_pid, 0, 0,
+			    cpu_to_node(cpu));
 	if (!IS_ERR(task)) {
 		init_idle_pids(task->pids);
 		init_idle(task, cpu);
@@ -1744,7 +1747,7 @@ long _do_fork(unsigned long clone_flags,
 	}
 
 	p = copy_process(clone_flags, stack_start, stack_size,
-			 child_tidptr, NULL, trace, tls);
+			 child_tidptr, NULL, trace, tls, NUMA_NO_NODE);
 	/*
 	 * Do this prior waking up the new thread - the thread pointer
 	 * might get invalid after that point, if the thread exits quickly.
diff --git a/mm/percpu.c b/mm/percpu.c
index 1f376bce413c..ef6353f0adbd 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1012,8 +1012,11 @@ area_found:
 		mutex_unlock(&pcpu_alloc_mutex);
 	}
 
-	if (chunk != pcpu_reserved_chunk)
+	if (chunk != pcpu_reserved_chunk) {
+		spin_lock_irqsave(&pcpu_lock, flags);
 		pcpu_nr_empty_pop_pages -= occ_pages;
+		spin_unlock_irqrestore(&pcpu_lock, flags);
+	}
 
 	if (pcpu_nr_empty_pop_pages < PCPU_EMPTY_POP_PAGES_LOW)
 		pcpu_schedule_balance_work();
diff --git a/tools/include/linux/log2.h b/tools/include/linux/log2.h
index 41446668ccce..d5677d39c1e4 100644
--- a/tools/include/linux/log2.h
+++ b/tools/include/linux/log2.h
@@ -13,12 +13,6 @@
 #define _TOOLS_LINUX_LOG2_H
 
 /*
- * deal with unrepresentable constant logarithms
- */
-extern __attribute__((const, noreturn))
-int ____ilog2_NaN(void);
-
-/*
  * non-constant log of base 2 calculators
  * - the arch may override these in asm/bitops.h if they can be implemented
  *   more efficiently than using fls() and fls64()
@@ -78,7 +72,7 @@ unsigned long __rounddown_pow_of_two(unsigned long n)
 #define ilog2(n)				\
 (						\
 	__builtin_constant_p(n) ? (		\
-		(n) < 1 ? ____ilog2_NaN() :	\
+		(n) < 2 ? 0 :			\
 		(n) & (1ULL << 63) ? 63 :	\
 		(n) & (1ULL << 62) ? 62 :	\
 		(n) & (1ULL << 61) ? 61 :	\
@@ -141,10 +135,7 @@ unsigned long __rounddown_pow_of_two(unsigned long n)
 		(n) & (1ULL <<  4) ?  4 :	\
 		(n) & (1ULL <<  3) ?  3 :	\
 		(n) & (1ULL <<  2) ?  2 :	\
-		(n) & (1ULL <<  1) ?  1 :	\
-		(n) & (1ULL <<  0) ?  0 :	\
-		____ilog2_NaN()			\
-				   ) :		\
+		1 ) :				\
 	(sizeof(n) <= 4) ?			\
 	__ilog2_u32(n) :			\
 	__ilog2_u64(n)				\