Merge tag 'dm-4.8-fixes-3' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm

Pull device mapper fixes from Mike Snitzer:

 - another stable fix for DM flakey (that tweaks the previous fix that
   didn't factor in expected 'drop_writes' behavior for read IO).

 - a dm-log bio operation flags fix for the broader block changes that
   were merged during the 4.8 merge window.

* tag 'dm-4.8-fixes-3' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm:
  dm log: fix unitialized bio operation flags
  dm flakey: fix reads to be issued if drop_writes configured
diff --git a/Documentation/PCI/MSI-HOWTO.txt b/Documentation/PCI/MSI-HOWTO.txt
index c55df29..cd9c9f6 100644
--- a/Documentation/PCI/MSI-HOWTO.txt
+++ b/Documentation/PCI/MSI-HOWTO.txt
@@ -94,14 +94,11 @@
 min_vecs argument set to this limit, and the PCI core will return -ENOSPC
 if it can't meet the minimum number of vectors.
 
-The flags argument should normally be set to 0, but can be used to pass the
-PCI_IRQ_NOMSI and PCI_IRQ_NOMSIX flag in case a device claims to support
-MSI or MSI-X, but the support is broken, or to pass PCI_IRQ_NOLEGACY in
-case the device does not support legacy interrupt lines.
-
-By default this function will spread the interrupts around the available
-CPUs, but this feature can be disabled by passing the PCI_IRQ_NOAFFINITY
-flag.
+The flags argument is used to specify which type of interrupt can be used
+by the device and the driver (PCI_IRQ_LEGACY, PCI_IRQ_MSI, PCI_IRQ_MSIX).
+A convenient short-hand (PCI_IRQ_ALL_TYPES) is also available to ask for
+any possible kind of interrupt.  If the PCI_IRQ_AFFINITY flag is set,
+pci_alloc_irq_vectors() will spread the interrupts around the available CPUs.
 
 To get the Linux IRQ numbers passed to request_irq() and free_irq() and the
 vectors, use the following function:
@@ -131,7 +128,7 @@
 capped to the supported limit, so there is no need to query the number of
 vectors supported beforehand:
 
-	nvec = pci_alloc_irq_vectors(pdev, 1, nvec, 0);
+	nvec = pci_alloc_irq_vectors(pdev, 1, nvec, PCI_IRQ_ALL_TYPES)
 	if (nvec < 0)
 		goto out_err;
 
@@ -140,7 +137,7 @@
 number to pci_alloc_irq_vectors() function as both 'min_vecs' and
 'max_vecs' parameters:
 
-	ret = pci_alloc_irq_vectors(pdev, nvec, nvec, 0);
+	ret = pci_alloc_irq_vectors(pdev, nvec, nvec, PCI_IRQ_ALL_TYPES);
 	if (ret < 0)
 		goto out_err;
 
@@ -148,15 +145,14 @@
 the single MSI mode for a device.  It could be done by passing two 1s as
 'min_vecs' and 'max_vecs':
 
-	ret = pci_alloc_irq_vectors(pdev, 1, 1, 0);
+	ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES);
 	if (ret < 0)
 		goto out_err;
 
 Some devices might not support using legacy line interrupts, in which case
-the PCI_IRQ_NOLEGACY flag can be used to fail the request if the platform
-can't provide MSI or MSI-X interrupts:
+the driver can specify that only MSI or MSI-X is acceptable:
 
-	nvec = pci_alloc_irq_vectors(pdev, 1, nvec, PCI_IRQ_NOLEGACY);
+	nvec = pci_alloc_irq_vectors(pdev, 1, nvec, PCI_IRQ_MSI | PCI_IRQ_MSIX);
 	if (nvec < 0)
 		goto out_err;
 
diff --git a/Documentation/devicetree/bindings/thermal/thermal.txt b/Documentation/devicetree/bindings/thermal/thermal.txt
index 41b817f..88b6ea1 100644
--- a/Documentation/devicetree/bindings/thermal/thermal.txt
+++ b/Documentation/devicetree/bindings/thermal/thermal.txt
@@ -62,7 +62,7 @@
 Required properties:
 - #cooling-cells:	Used to provide cooling device specific information
   Type: unsigned	while referring to it. Must be at least 2, in order
-  Size: one cell      	to specify minimum and maximum cooling state used
+  Size: one cell	to specify minimum and maximum cooling state used
 			in the reference. The first cell is the minimum
 			cooling state requested and the second cell is
 			the maximum cooling state requested in the reference.
@@ -119,7 +119,7 @@
 Optional property:
 - contribution:		The cooling contribution to the thermal zone of the
   Type: unsigned	referred cooling device at the referred trip point.
-  Size: one cell      	The contribution is a ratio of the sum
+  Size: one cell	The contribution is a ratio of the sum
 			of all cooling contributions within a thermal zone.
 
 Note: Using the THERMAL_NO_LIMIT (-1UL) constant in the cooling-device phandle
@@ -145,7 +145,7 @@
   Size: one cell
 
 - thermal-sensors:	A list of thermal sensor phandles and sensor specifier
-  Type: list of 	used while monitoring the thermal zone.
+  Type: list of		used while monitoring the thermal zone.
   phandles + sensor
   specifier
 
@@ -473,7 +473,7 @@
 				  <&adc>;	/* pcb north */
 
 		/* hotspot = 100 * bandgap - 120 * adc + 484 */
-		coefficients = 		<100	-120	484>;
+		coefficients =		<100	-120	484>;
 
 		trips {
 			...
@@ -502,7 +502,7 @@
         thermal-sensors =  <&adc>;
 
 		/* hotspot = 1 * adc + 6000 */
-	coefficients = 		<1	6000>;
+	coefficients =		<1	6000>;
 
 (d) - Board thermal
 
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 46c030a..a4f4d69 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -3032,6 +3032,10 @@
 				PAGE_SIZE is used as alignment.
 				PCI-PCI bridge can be specified, if resource
 				windows need to be expanded.
+				To specify the alignment for several
+				instances of a device, the PCI vendor,
+				device, subvendor, and subdevice may be
+				specified, e.g., 4096@pci:8086:9c22:103c:198f
 		ecrc=		Enable/disable PCIe ECRC (transaction layer
 				end-to-end CRC checking).
 				bios: Use BIOS/firmware settings. This is the
diff --git a/arch/arc/include/asm/entry.h b/arch/arc/include/asm/entry.h
index ad7860c..51597f3 100644
--- a/arch/arc/include/asm/entry.h
+++ b/arch/arc/include/asm/entry.h
@@ -142,7 +142,7 @@
 
 #ifdef CONFIG_ARC_CURR_IN_REG
 	; Retrieve orig r25 and save it with rest of callee_regs
-	ld.as   r12, [r12, PT_user_r25]
+	ld	r12, [r12, PT_user_r25]
 	PUSH	r12
 #else
 	PUSH	r25
@@ -198,7 +198,7 @@
 
 	; SP is back to start of pt_regs
 #ifdef CONFIG_ARC_CURR_IN_REG
-	st.as   r12, [sp, PT_user_r25]
+	st	r12, [sp, PT_user_r25]
 #endif
 .endm
 
diff --git a/arch/arc/include/asm/irqflags-compact.h b/arch/arc/include/asm/irqflags-compact.h
index c1d3645..4c6eed8 100644
--- a/arch/arc/include/asm/irqflags-compact.h
+++ b/arch/arc/include/asm/irqflags-compact.h
@@ -188,10 +188,10 @@
 .endm
 
 .macro IRQ_ENABLE  scratch
+	TRACE_ASM_IRQ_ENABLE
 	lr	\scratch, [status32]
 	or	\scratch, \scratch, (STATUS_E1_MASK | STATUS_E2_MASK)
 	flag	\scratch
-	TRACE_ASM_IRQ_ENABLE
 .endm
 
 #endif	/* __ASSEMBLY__ */
diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h
index 0f92d97..89eeb37 100644
--- a/arch/arc/include/asm/pgtable.h
+++ b/arch/arc/include/asm/pgtable.h
@@ -280,7 +280,7 @@
 
 #define pte_page(pte)		pfn_to_page(pte_pfn(pte))
 #define mk_pte(page, prot)	pfn_pte(page_to_pfn(page), prot)
-#define pfn_pte(pfn, prot)	(__pte(((pte_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot)))
+#define pfn_pte(pfn, prot)	__pte(((pfn) << PAGE_SHIFT) | pgprot_val(prot))
 
 /* Don't use virt_to_pfn for macros below: could cause truncations for PAE40*/
 #define pte_pfn(pte)		(pte_val(pte) >> PAGE_SHIFT)
diff --git a/arch/arc/include/uapi/asm/elf.h b/arch/arc/include/uapi/asm/elf.h
index 0f99ac8..0037a58 100644
--- a/arch/arc/include/uapi/asm/elf.h
+++ b/arch/arc/include/uapi/asm/elf.h
@@ -13,8 +13,15 @@
 
 /* Machine specific ELF Hdr flags */
 #define EF_ARC_OSABI_MSK	0x00000f00
-#define EF_ARC_OSABI_ORIG	0x00000000   /* MUST be zero for back-compat */
-#define EF_ARC_OSABI_CURRENT	0x00000300   /* v3 (no legacy syscalls) */
+
+#define EF_ARC_OSABI_V3		0x00000300   /* v3 (no legacy syscalls) */
+#define EF_ARC_OSABI_V4		0x00000400   /* v4 (64bit data any reg align) */
+
+#if __GNUC__ < 6
+#define EF_ARC_OSABI_CURRENT	EF_ARC_OSABI_V3
+#else
+#define EF_ARC_OSABI_CURRENT	EF_ARC_OSABI_V4
+#endif
 
 typedef unsigned long elf_greg_t;
 typedef unsigned long elf_fpregset_t;
diff --git a/arch/arc/kernel/arcksyms.c b/arch/arc/kernel/arcksyms.c
index 4d9e777..000dd04 100644
--- a/arch/arc/kernel/arcksyms.c
+++ b/arch/arc/kernel/arcksyms.c
@@ -28,6 +28,7 @@
 extern void __divdf3(void);
 extern void __floatunsidf(void);
 extern void __floatunsisf(void);
+extern void __udivdi3(void);
 
 EXPORT_SYMBOL(__ashldi3);
 EXPORT_SYMBOL(__ashrdi3);
@@ -45,6 +46,7 @@
 EXPORT_SYMBOL(__divdf3);
 EXPORT_SYMBOL(__floatunsidf);
 EXPORT_SYMBOL(__floatunsisf);
+EXPORT_SYMBOL(__udivdi3);
 
 /* ARC optimised assembler routines */
 EXPORT_SYMBOL(memset);
diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c
index b5db9e7..be1972b 100644
--- a/arch/arc/kernel/process.c
+++ b/arch/arc/kernel/process.c
@@ -199,7 +199,7 @@
 	}
 
 	eflags = x->e_flags;
-	if ((eflags & EF_ARC_OSABI_MSK) < EF_ARC_OSABI_CURRENT) {
+	if ((eflags & EF_ARC_OSABI_MSK) != EF_ARC_OSABI_CURRENT) {
 		pr_err("ABI mismatch - you need newer toolchain\n");
 		force_sigsegv(SIGSEGV, current);
 		return 0;
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index a946400..f52a0d0d 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -291,8 +291,10 @@
 			       cpu->dccm.base_addr, TO_KB(cpu->dccm.sz),
 			       cpu->iccm.base_addr, TO_KB(cpu->iccm.sz));
 
-	n += scnprintf(buf + n, len - n,
-		       "OS ABI [v3]\t: no-legacy-syscalls\n");
+	n += scnprintf(buf + n, len - n, "OS ABI [v%d]\t: %s\n",
+			EF_ARC_OSABI_CURRENT >> 8,
+			EF_ARC_OSABI_CURRENT == EF_ARC_OSABI_V3 ?
+			"no-legacy-syscalls" : "64-bit data any register aligned");
 
 	return buf;
 }
diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c
index 5a294b2..0b10efe 100644
--- a/arch/arc/mm/cache.c
+++ b/arch/arc/mm/cache.c
@@ -921,6 +921,15 @@
 
 	printk(arc_cache_mumbojumbo(0, str, sizeof(str)));
 
+	/*
+	 * Only master CPU needs to execute rest of function:
+	 *  - Assume SMP so all cores will have same cache config so
+	 *    any geomtry checks will be same for all
+	 *  - IOC setup / dma callbacks only need to be setup once
+	 */
+	if (cpu)
+		return;
+
 	if (IS_ENABLED(CONFIG_ARC_HAS_ICACHE)) {
 		struct cpuinfo_arc_cache *ic = &cpuinfo_arc700[cpu].icache;
 
diff --git a/arch/arc/mm/highmem.c b/arch/arc/mm/highmem.c
index 04f8332..77ff64a 100644
--- a/arch/arc/mm/highmem.c
+++ b/arch/arc/mm/highmem.c
@@ -61,6 +61,7 @@
 
 	return kmap_high(page);
 }
+EXPORT_SYMBOL(kmap);
 
 void *kmap_atomic(struct page *page)
 {
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index b0b82f5..3d2cef6 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -50,7 +50,7 @@
 static struct vcpu_info __percpu *xen_vcpu_info;
 
 /* Linux <-> Xen vCPU id mapping */
-DEFINE_PER_CPU(int, xen_vcpu_id) = -1;
+DEFINE_PER_CPU(uint32_t, xen_vcpu_id);
 EXPORT_PER_CPU_SYMBOL(xen_vcpu_id);
 
 /* These are unused until we support booting "pre-ballooned" */
diff --git a/arch/um/include/asm/common.lds.S b/arch/um/include/asm/common.lds.S
index 1dd5bd8..1330553 100644
--- a/arch/um/include/asm/common.lds.S
+++ b/arch/um/include/asm/common.lds.S
@@ -81,7 +81,7 @@
   .altinstr_replacement : { *(.altinstr_replacement) }
   /* .exit.text is discard at runtime, not link time, to deal with references
      from .altinstructions and .eh_frame */
-  .exit.text : { *(.exit.text) }
+  .exit.text : { EXIT_TEXT }
   .exit.data : { *(.exit.data) }
 
   .preinit_array : {
diff --git a/arch/x86/crypto/sha256-mb/sha256_mb.c b/arch/x86/crypto/sha256-mb/sha256_mb.c
index 89fa85e..6f97fb3 100644
--- a/arch/x86/crypto/sha256-mb/sha256_mb.c
+++ b/arch/x86/crypto/sha256-mb/sha256_mb.c
@@ -485,10 +485,10 @@
 
 			req = cast_mcryptd_ctx_to_req(req_ctx);
 			if (irqs_disabled())
-				rctx->complete(&req->base, ret);
+				req_ctx->complete(&req->base, ret);
 			else {
 				local_bh_disable();
-				rctx->complete(&req->base, ret);
+				req_ctx->complete(&req->base, ret);
 				local_bh_enable();
 			}
 		}
diff --git a/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S b/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S
index b691da9..a78a069 100644
--- a/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S
+++ b/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S
@@ -265,13 +265,14 @@
 	vpinsrd	$1, _args_digest+1*32(state, idx, 4), %xmm0, %xmm0
 	vpinsrd	$2, _args_digest+2*32(state, idx, 4), %xmm0, %xmm0
 	vpinsrd	$3, _args_digest+3*32(state, idx, 4), %xmm0, %xmm0
-	movl	_args_digest+4*32(state, idx, 4), tmp2_w
+	vmovd   _args_digest(state , idx, 4) , %xmm0
 	vpinsrd	$1, _args_digest+5*32(state, idx, 4), %xmm1, %xmm1
 	vpinsrd	$2, _args_digest+6*32(state, idx, 4), %xmm1, %xmm1
 	vpinsrd	$3, _args_digest+7*32(state, idx, 4), %xmm1, %xmm1
 
-	vmovdqu	%xmm0, _result_digest(job_rax)
-	movl	tmp2_w, _result_digest+1*16(job_rax)
+        vmovdqu %xmm0, _result_digest(job_rax)
+        offset =  (_result_digest + 1*16)
+        vmovdqu %xmm1, offset(job_rax)
 
 	pop	%rbx
 
diff --git a/arch/x86/crypto/sha512-mb/sha512_mb.c b/arch/x86/crypto/sha512-mb/sha512_mb.c
index f4cf5b7..d210174 100644
--- a/arch/x86/crypto/sha512-mb/sha512_mb.c
+++ b/arch/x86/crypto/sha512-mb/sha512_mb.c
@@ -497,10 +497,10 @@
 
 			req = cast_mcryptd_ctx_to_req(req_ctx);
 			if (irqs_disabled())
-				rctx->complete(&req->base, ret);
+				req_ctx->complete(&req->base, ret);
 			else {
 				local_bh_disable();
-				rctx->complete(&req->base, ret);
+				req_ctx->complete(&req->base, ret);
 				local_bh_enable();
 			}
 		}
diff --git a/arch/x86/pci/vmd.c b/arch/x86/pci/vmd.c
index b814ca6..7948be3 100644
--- a/arch/x86/pci/vmd.c
+++ b/arch/x86/pci/vmd.c
@@ -41,6 +41,7 @@
  * @node:	list item for parent traversal.
  * @rcu:	RCU callback item for freeing.
  * @irq:	back pointer to parent.
+ * @enabled:	true if driver enabled IRQ
  * @virq:	the virtual IRQ value provided to the requesting driver.
  *
  * Every MSI/MSI-X IRQ requested for a device in a VMD domain will be mapped to
@@ -50,6 +51,7 @@
 	struct list_head	node;
 	struct rcu_head		rcu;
 	struct vmd_irq_list	*irq;
+	bool			enabled;
 	unsigned int		virq;
 };
 
@@ -122,7 +124,9 @@
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&list_lock, flags);
+	WARN_ON(vmdirq->enabled);
 	list_add_tail_rcu(&vmdirq->node, &vmdirq->irq->irq_list);
+	vmdirq->enabled = true;
 	raw_spin_unlock_irqrestore(&list_lock, flags);
 
 	data->chip->irq_unmask(data);
@@ -136,8 +140,10 @@
 	data->chip->irq_mask(data);
 
 	raw_spin_lock_irqsave(&list_lock, flags);
-	list_del_rcu(&vmdirq->node);
-	INIT_LIST_HEAD_RCU(&vmdirq->node);
+	if (vmdirq->enabled) {
+		list_del_rcu(&vmdirq->node);
+		vmdirq->enabled = false;
+	}
 	raw_spin_unlock_irqrestore(&list_lock, flags);
 }
 
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 8ffb089..b86ebb1 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -118,7 +118,7 @@
 DEFINE_PER_CPU(struct vcpu_info, xen_vcpu_info);
 
 /* Linux <-> Xen vCPU id mapping */
-DEFINE_PER_CPU(int, xen_vcpu_id) = -1;
+DEFINE_PER_CPU(uint32_t, xen_vcpu_id);
 EXPORT_PER_CPU_SYMBOL(xen_vcpu_id);
 
 enum xen_domain_type xen_domain_type = XEN_NATIVE;
diff --git a/block/bio.c b/block/bio.c
index f394775..aa73540 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -667,18 +667,19 @@
 	bio->bi_iter.bi_sector	= bio_src->bi_iter.bi_sector;
 	bio->bi_iter.bi_size	= bio_src->bi_iter.bi_size;
 
-	if (bio_op(bio) == REQ_OP_DISCARD)
-		goto integrity_clone;
-
-	if (bio_op(bio) == REQ_OP_WRITE_SAME) {
+	switch (bio_op(bio)) {
+	case REQ_OP_DISCARD:
+	case REQ_OP_SECURE_ERASE:
+		break;
+	case REQ_OP_WRITE_SAME:
 		bio->bi_io_vec[bio->bi_vcnt++] = bio_src->bi_io_vec[0];
-		goto integrity_clone;
+		break;
+	default:
+		bio_for_each_segment(bv, bio_src, iter)
+			bio->bi_io_vec[bio->bi_vcnt++] = bv;
+		break;
 	}
 
-	bio_for_each_segment(bv, bio_src, iter)
-		bio->bi_io_vec[bio->bi_vcnt++] = bv;
-
-integrity_clone:
 	if (bio_integrity(bio_src)) {
 		int ret;
 
@@ -1788,7 +1789,7 @@
 	 * Discards need a mutable bio_vec to accommodate the payload
 	 * required by the DSM TRIM and UNMAP commands.
 	 */
-	if (bio_op(bio) == REQ_OP_DISCARD)
+	if (bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_SECURE_ERASE)
 		split = bio_clone_bioset(bio, gfp, bs);
 	else
 		split = bio_clone_fast(bio, gfp, bs);
diff --git a/block/blk-core.c b/block/blk-core.c
index 999442e..36c7ac3 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -515,7 +515,9 @@
 
 void blk_set_queue_dying(struct request_queue *q)
 {
-	queue_flag_set_unlocked(QUEUE_FLAG_DYING, q);
+	spin_lock_irq(q->queue_lock);
+	queue_flag_set(QUEUE_FLAG_DYING, q);
+	spin_unlock_irq(q->queue_lock);
 
 	if (q->mq_ops)
 		blk_mq_wake_waiters(q);
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 3eec75a..2642e5f 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -94,9 +94,31 @@
 	bool do_split = true;
 	struct bio *new = NULL;
 	const unsigned max_sectors = get_max_io_size(q, bio);
+	unsigned bvecs = 0;
 
 	bio_for_each_segment(bv, bio, iter) {
 		/*
+		 * With arbitrary bio size, the incoming bio may be very
+		 * big. We have to split the bio into small bios so that
+		 * each holds at most BIO_MAX_PAGES bvecs because
+		 * bio_clone() can fail to allocate big bvecs.
+		 *
+		 * It should have been better to apply the limit per
+		 * request queue in which bio_clone() is involved,
+		 * instead of globally. The biggest blocker is the
+		 * bio_clone() in bio bounce.
+		 *
+		 * If bio is splitted by this reason, we should have
+		 * allowed to continue bios merging, but don't do
+		 * that now for making the change simple.
+		 *
+		 * TODO: deal with bio bounce's bio_clone() gracefully
+		 * and convert the global limit into per-queue limit.
+		 */
+		if (bvecs++ >= BIO_MAX_PAGES)
+			goto split;
+
+		/*
 		 * If the queue doesn't support SG gaps and adding this
 		 * offset would create a gap, disallow it.
 		 */
@@ -172,12 +194,18 @@
 	struct bio *split, *res;
 	unsigned nsegs;
 
-	if (bio_op(*bio) == REQ_OP_DISCARD)
+	switch (bio_op(*bio)) {
+	case REQ_OP_DISCARD:
+	case REQ_OP_SECURE_ERASE:
 		split = blk_bio_discard_split(q, *bio, bs, &nsegs);
-	else if (bio_op(*bio) == REQ_OP_WRITE_SAME)
+		break;
+	case REQ_OP_WRITE_SAME:
 		split = blk_bio_write_same_split(q, *bio, bs, &nsegs);
-	else
+		break;
+	default:
 		split = blk_bio_segment_split(q, *bio, q->bio_split, &nsegs);
+		break;
+	}
 
 	/* physical segments can be figured out during splitting */
 	res = split ? split : *bio;
@@ -213,7 +241,7 @@
 	 * This should probably be returning 0, but blk_add_request_payload()
 	 * (Christoph!!!!)
 	 */
-	if (bio_op(bio) == REQ_OP_DISCARD)
+	if (bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_SECURE_ERASE)
 		return 1;
 
 	if (bio_op(bio) == REQ_OP_WRITE_SAME)
@@ -385,7 +413,9 @@
 	nsegs = 0;
 	cluster = blk_queue_cluster(q);
 
-	if (bio_op(bio) == REQ_OP_DISCARD) {
+	switch (bio_op(bio)) {
+	case REQ_OP_DISCARD:
+	case REQ_OP_SECURE_ERASE:
 		/*
 		 * This is a hack - drivers should be neither modifying the
 		 * biovec, nor relying on bi_vcnt - but because of
@@ -393,19 +423,16 @@
 		 * a payload we need to set up here (thank you Christoph) and
 		 * bi_vcnt is really the only way of telling if we need to.
 		 */
-
-		if (bio->bi_vcnt)
-			goto single_segment;
-
-		return 0;
-	}
-
-	if (bio_op(bio) == REQ_OP_WRITE_SAME) {
-single_segment:
+		if (!bio->bi_vcnt)
+			return 0;
+		/* Fall through */
+	case REQ_OP_WRITE_SAME:
 		*sg = sglist;
 		bvec = bio_iovec(bio);
 		sg_set_page(*sg, bvec.bv_page, bvec.bv_len, bvec.bv_offset);
 		return 1;
+	default:
+		break;
 	}
 
 	for_each_bio(bio)
diff --git a/block/blk-mq.c b/block/blk-mq.c
index e931a0e..13f5a6c 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -793,11 +793,12 @@
 	struct list_head *dptr;
 	int queued;
 
-	WARN_ON(!cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask));
-
 	if (unlikely(test_bit(BLK_MQ_S_STOPPED, &hctx->state)))
 		return;
 
+	WARN_ON(!cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask) &&
+		cpu_online(hctx->next_cpu));
+
 	hctx->run++;
 
 	/*
@@ -1036,10 +1037,11 @@
 EXPORT_SYMBOL(blk_mq_delay_queue);
 
 static inline void __blk_mq_insert_req_list(struct blk_mq_hw_ctx *hctx,
-					    struct blk_mq_ctx *ctx,
 					    struct request *rq,
 					    bool at_head)
 {
+	struct blk_mq_ctx *ctx = rq->mq_ctx;
+
 	trace_block_rq_insert(hctx->queue, rq);
 
 	if (at_head)
@@ -1053,20 +1055,16 @@
 {
 	struct blk_mq_ctx *ctx = rq->mq_ctx;
 
-	__blk_mq_insert_req_list(hctx, ctx, rq, at_head);
+	__blk_mq_insert_req_list(hctx, rq, at_head);
 	blk_mq_hctx_mark_pending(hctx, ctx);
 }
 
 void blk_mq_insert_request(struct request *rq, bool at_head, bool run_queue,
-		bool async)
+			   bool async)
 {
+	struct blk_mq_ctx *ctx = rq->mq_ctx;
 	struct request_queue *q = rq->q;
 	struct blk_mq_hw_ctx *hctx;
-	struct blk_mq_ctx *ctx = rq->mq_ctx, *current_ctx;
-
-	current_ctx = blk_mq_get_ctx(q);
-	if (!cpu_online(ctx->cpu))
-		rq->mq_ctx = ctx = current_ctx;
 
 	hctx = q->mq_ops->map_queue(q, ctx->cpu);
 
@@ -1076,8 +1074,6 @@
 
 	if (run_queue)
 		blk_mq_run_hw_queue(hctx, async);
-
-	blk_mq_put_ctx(current_ctx);
 }
 
 static void blk_mq_insert_requests(struct request_queue *q,
@@ -1088,14 +1084,9 @@
 
 {
 	struct blk_mq_hw_ctx *hctx;
-	struct blk_mq_ctx *current_ctx;
 
 	trace_block_unplug(q, depth, !from_schedule);
 
-	current_ctx = blk_mq_get_ctx(q);
-
-	if (!cpu_online(ctx->cpu))
-		ctx = current_ctx;
 	hctx = q->mq_ops->map_queue(q, ctx->cpu);
 
 	/*
@@ -1107,15 +1098,14 @@
 		struct request *rq;
 
 		rq = list_first_entry(list, struct request, queuelist);
+		BUG_ON(rq->mq_ctx != ctx);
 		list_del_init(&rq->queuelist);
-		rq->mq_ctx = ctx;
-		__blk_mq_insert_req_list(hctx, ctx, rq, false);
+		__blk_mq_insert_req_list(hctx, rq, false);
 	}
 	blk_mq_hctx_mark_pending(hctx, ctx);
 	spin_unlock(&ctx->lock);
 
 	blk_mq_run_hw_queue(hctx, from_schedule);
-	blk_mq_put_ctx(current_ctx);
 }
 
 static int plug_ctx_cmp(void *priv, struct list_head *a, struct list_head *b)
@@ -1630,16 +1620,17 @@
 	return 0;
 }
 
+/*
+ * 'cpu' is going away. splice any existing rq_list entries from this
+ * software queue to the hw queue dispatch list, and ensure that it
+ * gets run.
+ */
 static int blk_mq_hctx_cpu_offline(struct blk_mq_hw_ctx *hctx, int cpu)
 {
-	struct request_queue *q = hctx->queue;
 	struct blk_mq_ctx *ctx;
 	LIST_HEAD(tmp);
 
-	/*
-	 * Move ctx entries to new CPU, if this one is going away.
-	 */
-	ctx = __blk_mq_get_ctx(q, cpu);
+	ctx = __blk_mq_get_ctx(hctx->queue, cpu);
 
 	spin_lock(&ctx->lock);
 	if (!list_empty(&ctx->rq_list)) {
@@ -1651,24 +1642,11 @@
 	if (list_empty(&tmp))
 		return NOTIFY_OK;
 
-	ctx = blk_mq_get_ctx(q);
-	spin_lock(&ctx->lock);
-
-	while (!list_empty(&tmp)) {
-		struct request *rq;
-
-		rq = list_first_entry(&tmp, struct request, queuelist);
-		rq->mq_ctx = ctx;
-		list_move_tail(&rq->queuelist, &ctx->rq_list);
-	}
-
-	hctx = q->mq_ops->map_queue(q, ctx->cpu);
-	blk_mq_hctx_mark_pending(hctx, ctx);
-
-	spin_unlock(&ctx->lock);
+	spin_lock(&hctx->lock);
+	list_splice_tail_init(&tmp, &hctx->dispatch);
+	spin_unlock(&hctx->lock);
 
 	blk_mq_run_hw_queue(hctx, true);
-	blk_mq_put_ctx(ctx);
 	return NOTIFY_OK;
 }
 
diff --git a/block/elevator.c b/block/elevator.c
index 7096c22..f7d973a 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -366,7 +366,7 @@
 	list_for_each_prev(entry, &q->queue_head) {
 		struct request *pos = list_entry_rq(entry);
 
-		if ((req_op(rq) == REQ_OP_DISCARD) != (req_op(pos) == REQ_OP_DISCARD))
+		if (req_op(rq) != req_op(pos))
 			break;
 		if (rq_data_dir(rq) != rq_data_dir(pos))
 			break;
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index b71a9c7..e3d8e4c 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -3706,22 +3706,21 @@
 	if (UFDCS->rawcmd == 1)
 		UFDCS->rawcmd = 2;
 
-	if (mode & (FMODE_READ|FMODE_WRITE)) {
-		UDRS->last_checked = 0;
-		clear_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags);
-		check_disk_change(bdev);
-		if (test_bit(FD_DISK_CHANGED_BIT, &UDRS->flags))
-			goto out;
-		if (test_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags))
+	if (!(mode & FMODE_NDELAY)) {
+		if (mode & (FMODE_READ|FMODE_WRITE)) {
+			UDRS->last_checked = 0;
+			clear_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags);
+			check_disk_change(bdev);
+			if (test_bit(FD_DISK_CHANGED_BIT, &UDRS->flags))
+				goto out;
+			if (test_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags))
+				goto out;
+		}
+		res = -EROFS;
+		if ((mode & FMODE_WRITE) &&
+		    !test_bit(FD_DISK_WRITABLE_BIT, &UDRS->flags))
 			goto out;
 	}
-
-	res = -EROFS;
-
-	if ((mode & FMODE_WRITE) &&
-			!test_bit(FD_DISK_WRITABLE_BIT, &UDRS->flags))
-		goto out;
-
 	mutex_unlock(&open_lock);
 	mutex_unlock(&floppy_mutex);
 	return 0;
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index be4fea6..88ef6d4 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -189,6 +189,8 @@
 	struct mutex mutex;
 	struct xenbus_device *xbdev;
 	struct gendisk *gd;
+	u16 sector_size;
+	unsigned int physical_sector_size;
 	int vdevice;
 	blkif_vdev_t handle;
 	enum blkif_state connected;
@@ -910,9 +912,45 @@
 	.map_queue = blk_mq_map_queue,
 };
 
+static void blkif_set_queue_limits(struct blkfront_info *info)
+{
+	struct request_queue *rq = info->rq;
+	struct gendisk *gd = info->gd;
+	unsigned int segments = info->max_indirect_segments ? :
+				BLKIF_MAX_SEGMENTS_PER_REQUEST;
+
+	queue_flag_set_unlocked(QUEUE_FLAG_VIRT, rq);
+
+	if (info->feature_discard) {
+		queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, rq);
+		blk_queue_max_discard_sectors(rq, get_capacity(gd));
+		rq->limits.discard_granularity = info->discard_granularity;
+		rq->limits.discard_alignment = info->discard_alignment;
+		if (info->feature_secdiscard)
+			queue_flag_set_unlocked(QUEUE_FLAG_SECERASE, rq);
+	}
+
+	/* Hard sector size and max sectors impersonate the equiv. hardware. */
+	blk_queue_logical_block_size(rq, info->sector_size);
+	blk_queue_physical_block_size(rq, info->physical_sector_size);
+	blk_queue_max_hw_sectors(rq, (segments * XEN_PAGE_SIZE) / 512);
+
+	/* Each segment in a request is up to an aligned page in size. */
+	blk_queue_segment_boundary(rq, PAGE_SIZE - 1);
+	blk_queue_max_segment_size(rq, PAGE_SIZE);
+
+	/* Ensure a merged request will fit in a single I/O ring slot. */
+	blk_queue_max_segments(rq, segments / GRANTS_PER_PSEG);
+
+	/* Make sure buffer addresses are sector-aligned. */
+	blk_queue_dma_alignment(rq, 511);
+
+	/* Make sure we don't use bounce buffers. */
+	blk_queue_bounce_limit(rq, BLK_BOUNCE_ANY);
+}
+
 static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size,
-				unsigned int physical_sector_size,
-				unsigned int segments)
+				unsigned int physical_sector_size)
 {
 	struct request_queue *rq;
 	struct blkfront_info *info = gd->private_data;
@@ -944,36 +982,11 @@
 	}
 
 	rq->queuedata = info;
-	queue_flag_set_unlocked(QUEUE_FLAG_VIRT, rq);
-
-	if (info->feature_discard) {
-		queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, rq);
-		blk_queue_max_discard_sectors(rq, get_capacity(gd));
-		rq->limits.discard_granularity = info->discard_granularity;
-		rq->limits.discard_alignment = info->discard_alignment;
-		if (info->feature_secdiscard)
-			queue_flag_set_unlocked(QUEUE_FLAG_SECERASE, rq);
-	}
-
-	/* Hard sector size and max sectors impersonate the equiv. hardware. */
-	blk_queue_logical_block_size(rq, sector_size);
-	blk_queue_physical_block_size(rq, physical_sector_size);
-	blk_queue_max_hw_sectors(rq, (segments * XEN_PAGE_SIZE) / 512);
-
-	/* Each segment in a request is up to an aligned page in size. */
-	blk_queue_segment_boundary(rq, PAGE_SIZE - 1);
-	blk_queue_max_segment_size(rq, PAGE_SIZE);
-
-	/* Ensure a merged request will fit in a single I/O ring slot. */
-	blk_queue_max_segments(rq, segments / GRANTS_PER_PSEG);
-
-	/* Make sure buffer addresses are sector-aligned. */
-	blk_queue_dma_alignment(rq, 511);
-
-	/* Make sure we don't use bounce buffers. */
-	blk_queue_bounce_limit(rq, BLK_BOUNCE_ANY);
-
-	gd->queue = rq;
+	info->rq = gd->queue = rq;
+	info->gd = gd;
+	info->sector_size = sector_size;
+	info->physical_sector_size = physical_sector_size;
+	blkif_set_queue_limits(info);
 
 	return 0;
 }
@@ -1136,16 +1149,11 @@
 	gd->private_data = info;
 	set_capacity(gd, capacity);
 
-	if (xlvbd_init_blk_queue(gd, sector_size, physical_sector_size,
-				 info->max_indirect_segments ? :
-				 BLKIF_MAX_SEGMENTS_PER_REQUEST)) {
+	if (xlvbd_init_blk_queue(gd, sector_size, physical_sector_size)) {
 		del_gendisk(gd);
 		goto release;
 	}
 
-	info->rq = gd->queue;
-	info->gd = gd;
-
 	xlvbd_flush(info);
 
 	if (vdisk_info & VDISK_READONLY)
@@ -1315,7 +1323,7 @@
 			rinfo->ring_ref[i] = GRANT_INVALID_REF;
 		}
 	}
-	free_pages((unsigned long)rinfo->ring.sring, get_order(info->nr_ring_pages * PAGE_SIZE));
+	free_pages((unsigned long)rinfo->ring.sring, get_order(info->nr_ring_pages * XEN_PAGE_SIZE));
 	rinfo->ring.sring = NULL;
 
 	if (rinfo->irq)
@@ -2007,8 +2015,10 @@
 	struct split_bio *split_bio;
 
 	blkfront_gather_backend_features(info);
+	/* Reset limits changed by blk_mq_update_nr_hw_queues(). */
+	blkif_set_queue_limits(info);
 	segs = info->max_indirect_segments ? : BLKIF_MAX_SEGMENTS_PER_REQUEST;
-	blk_queue_max_segments(info->rq, segs);
+	blk_queue_max_segments(info->rq, segs / GRANTS_PER_PSEG);
 
 	for (r_index = 0; r_index < info->nr_rings; r_index++) {
 		struct blkfront_ring_info *rinfo = &info->rinfo[r_index];
@@ -2432,7 +2442,7 @@
 	if (err) {
 		xenbus_dev_fatal(info->xbdev, err, "xlvbd_add at %s",
 				 info->xbdev->otherend);
-		return;
+		goto fail;
 	}
 
 	xenbus_switch_state(info->xbdev, XenbusStateConnected);
@@ -2445,6 +2455,11 @@
 	device_add_disk(&info->xbdev->dev, info->gd);
 
 	info->is_ready = 1;
+	return;
+
+fail:
+	blkif_free(info, 0);
+	return;
 }
 
 /**
diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index 98dd47a..66a9410 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -50,6 +50,7 @@
 config OF_GPIO
 	def_bool y
 	depends on OF
+	depends on HAS_IOMEM
 
 config GPIO_ACPI
 	def_bool y
@@ -188,7 +189,7 @@
 config GPIO_ETRAXFS
 	bool "Axis ETRAX FS General I/O"
 	depends on CRIS || COMPILE_TEST
-	depends on OF
+	depends on OF_GPIO
 	select GPIO_GENERIC
 	select GPIOLIB_IRQCHIP
 	help
@@ -214,7 +215,7 @@
 
 config GPIO_GRGPIO
 	tristate "Aeroflex Gaisler GRGPIO support"
-	depends on OF
+	depends on OF_GPIO
 	select GPIO_GENERIC
 	select IRQ_DOMAIN
 	help
@@ -312,7 +313,7 @@
 config GPIO_MVEBU
 	def_bool y
 	depends on PLAT_ORION
-	depends on OF
+	depends on OF_GPIO
 	select GENERIC_IRQ_CHIP
 
 config GPIO_MXC
@@ -405,7 +406,7 @@
 	bool "NVIDIA Tegra GPIO support"
 	default ARCH_TEGRA
 	depends on ARCH_TEGRA || COMPILE_TEST
-	depends on OF
+	depends on OF_GPIO
 	help
 	  Say yes here to support GPIO pins on NVIDIA Tegra SoCs.
 
@@ -1099,7 +1100,7 @@
 
 config GPIO_74X164
 	tristate "74x164 serial-in/parallel-out 8-bits shift register"
-	depends on OF
+	depends on OF_GPIO
 	help
 	  Driver for 74x164 compatible serial-in/parallel-out 8-outputs
 	  shift registers. This driver can be used to provide access
diff --git a/drivers/gpio/gpio-max730x.c b/drivers/gpio/gpio-max730x.c
index 0880736..946d091 100644
--- a/drivers/gpio/gpio-max730x.c
+++ b/drivers/gpio/gpio-max730x.c
@@ -192,6 +192,10 @@
 	ts->chip.parent = dev;
 	ts->chip.owner = THIS_MODULE;
 
+	ret = gpiochip_add_data(&ts->chip, ts);
+	if (ret)
+		goto exit_destroy;
+
 	/*
 	 * initialize pullups according to platform data and cache the
 	 * register values for later use.
@@ -213,10 +217,6 @@
 		}
 	}
 
-	ret = gpiochip_add_data(&ts->chip, ts);
-	if (ret)
-		goto exit_destroy;
-
 	return ret;
 
 exit_destroy:
diff --git a/drivers/input/keyboard/tegra-kbc.c b/drivers/input/keyboard/tegra-kbc.c
index 7d61439..0c07e10 100644
--- a/drivers/input/keyboard/tegra-kbc.c
+++ b/drivers/input/keyboard/tegra-kbc.c
@@ -376,7 +376,7 @@
 	/* Reset the KBC controller to clear all previous status.*/
 	reset_control_assert(kbc->rst);
 	udelay(100);
-	reset_control_assert(kbc->rst);
+	reset_control_deassert(kbc->rst);
 	udelay(100);
 
 	tegra_kbc_config_pins(kbc);
diff --git a/drivers/input/rmi4/rmi_driver.c b/drivers/input/rmi4/rmi_driver.c
index faa295e..c83bce8 100644
--- a/drivers/input/rmi4/rmi_driver.c
+++ b/drivers/input/rmi4/rmi_driver.c
@@ -553,7 +553,6 @@
 		goto free_struct_buff;
 
 	reg = find_first_bit(rdesc->presense_map, RMI_REG_DESC_PRESENSE_BITS);
-	map_offset = 0;
 	for (i = 0; i < rdesc->num_registers; i++) {
 		struct rmi_register_desc_item *item = &rdesc->registers[i];
 		int reg_size = struct_buf[offset];
@@ -576,6 +575,8 @@
 		item->reg = reg;
 		item->reg_size = reg_size;
 
+		map_offset = 0;
+
 		do {
 			for (b = 0; b < 7; b++) {
 				if (struct_buf[offset] & (0x1 << b))
diff --git a/drivers/input/serio/i8042.c b/drivers/input/serio/i8042.c
index b4d3408..405252a 100644
--- a/drivers/input/serio/i8042.c
+++ b/drivers/input/serio/i8042.c
@@ -1305,6 +1305,7 @@
 	serio->write		= i8042_aux_write;
 	serio->start		= i8042_start;
 	serio->stop		= i8042_stop;
+	serio->ps2_cmd_mutex	= &i8042_mutex;
 	serio->port_data	= port;
 	serio->dev.parent	= &i8042_platform_device->dev;
 	if (idx < 0) {
diff --git a/drivers/input/touchscreen/ads7846.c b/drivers/input/touchscreen/ads7846.c
index a61b215..1ce3ecb 100644
--- a/drivers/input/touchscreen/ads7846.c
+++ b/drivers/input/touchscreen/ads7846.c
@@ -1473,7 +1473,6 @@
 
 	ads784x_hwmon_unregister(spi, ts);
 
-	regulator_disable(ts->reg);
 	regulator_put(ts->reg);
 
 	if (!ts->get_pendown_state) {
diff --git a/drivers/input/touchscreen/silead.c b/drivers/input/touchscreen/silead.c
index 7379fe1..b2744a6 100644
--- a/drivers/input/touchscreen/silead.c
+++ b/drivers/input/touchscreen/silead.c
@@ -464,7 +464,7 @@
 		return -ENODEV;
 
 	/* Power GPIO pin */
-	data->gpio_power = gpiod_get_optional(dev, "power", GPIOD_OUT_LOW);
+	data->gpio_power = devm_gpiod_get_optional(dev, "power", GPIOD_OUT_LOW);
 	if (IS_ERR(data->gpio_power)) {
 		if (PTR_ERR(data->gpio_power) != -EPROBE_DEFER)
 			dev_err(dev, "Shutdown GPIO request failed\n");
diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index ce80117..641e887 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -879,7 +879,7 @@
 	 * We may have concurrent producers, so we need to be careful
 	 * not to touch any of the shadow cmdq state.
 	 */
-	queue_read(cmd, Q_ENT(q, idx), q->ent_dwords);
+	queue_read(cmd, Q_ENT(q, cons), q->ent_dwords);
 	dev_err(smmu->dev, "skipping command in error state:\n");
 	for (i = 0; i < ARRAY_SIZE(cmd); ++i)
 		dev_err(smmu->dev, "\t0x%016llx\n", (unsigned long long)cmd[i]);
@@ -890,7 +890,7 @@
 		return;
 	}
 
-	queue_write(cmd, Q_ENT(q, idx), q->ent_dwords);
+	queue_write(Q_ENT(q, cons), cmd, q->ent_dwords);
 }
 
 static void arm_smmu_cmdq_issue_cmd(struct arm_smmu_device *smmu,
@@ -1034,6 +1034,9 @@
 		case STRTAB_STE_0_CFG_S2_TRANS:
 			ste_live = true;
 			break;
+		case STRTAB_STE_0_CFG_ABORT:
+			if (disable_bypass)
+				break;
 		default:
 			BUG(); /* STE corruption */
 		}
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 4f49fe2..2db74eb 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -686,8 +686,7 @@
 
 static irqreturn_t arm_smmu_context_fault(int irq, void *dev)
 {
-	int flags, ret;
-	u32 fsr, fsynr, resume;
+	u32 fsr, fsynr;
 	unsigned long iova;
 	struct iommu_domain *domain = dev;
 	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
@@ -701,34 +700,15 @@
 	if (!(fsr & FSR_FAULT))
 		return IRQ_NONE;
 
-	if (fsr & FSR_IGN)
-		dev_err_ratelimited(smmu->dev,
-				    "Unexpected context fault (fsr 0x%x)\n",
-				    fsr);
-
 	fsynr = readl_relaxed(cb_base + ARM_SMMU_CB_FSYNR0);
-	flags = fsynr & FSYNR0_WNR ? IOMMU_FAULT_WRITE : IOMMU_FAULT_READ;
-
 	iova = readq_relaxed(cb_base + ARM_SMMU_CB_FAR);
-	if (!report_iommu_fault(domain, smmu->dev, iova, flags)) {
-		ret = IRQ_HANDLED;
-		resume = RESUME_RETRY;
-	} else {
-		dev_err_ratelimited(smmu->dev,
-		    "Unhandled context fault: iova=0x%08lx, fsynr=0x%x, cb=%d\n",
-		    iova, fsynr, cfg->cbndx);
-		ret = IRQ_NONE;
-		resume = RESUME_TERMINATE;
-	}
 
-	/* Clear the faulting FSR */
+	dev_err_ratelimited(smmu->dev,
+	"Unhandled context fault: fsr=0x%x, iova=0x%08lx, fsynr=0x%x, cb=%d\n",
+			    fsr, iova, fsynr, cfg->cbndx);
+
 	writel(fsr, cb_base + ARM_SMMU_CB_FSR);
-
-	/* Retry or terminate any stalled transactions */
-	if (fsr & FSR_SS)
-		writel_relaxed(resume, cb_base + ARM_SMMU_CB_RESUME);
-
-	return ret;
+	return IRQ_HANDLED;
 }
 
 static irqreturn_t arm_smmu_global_fault(int irq, void *dev)
@@ -837,7 +817,7 @@
 	}
 
 	/* SCTLR */
-	reg = SCTLR_CFCFG | SCTLR_CFIE | SCTLR_CFRE | SCTLR_M | SCTLR_EAE_SBOP;
+	reg = SCTLR_CFIE | SCTLR_CFRE | SCTLR_M | SCTLR_EAE_SBOP;
 	if (stage1)
 		reg |= SCTLR_S1_ASIDPNE;
 #ifdef __BIG_ENDIAN
diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c
index 8c61399..def8ca1 100644
--- a/drivers/iommu/io-pgtable-arm-v7s.c
+++ b/drivers/iommu/io-pgtable-arm-v7s.c
@@ -286,12 +286,14 @@
 	int prot = IOMMU_READ;
 	arm_v7s_iopte attr = pte >> ARM_V7S_ATTR_SHIFT(lvl);
 
-	if (attr & ARM_V7S_PTE_AP_RDONLY)
+	if (!(attr & ARM_V7S_PTE_AP_RDONLY))
 		prot |= IOMMU_WRITE;
 	if ((attr & (ARM_V7S_TEX_MASK << ARM_V7S_TEX_SHIFT)) == 0)
 		prot |= IOMMU_MMIO;
 	else if (pte & ARM_V7S_ATTR_C)
 		prot |= IOMMU_CACHE;
+	if (pte & ARM_V7S_ATTR_XN(lvl))
+		prot |= IOMMU_NOEXEC;
 
 	return prot;
 }
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 95a4ca6..849ad44 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -760,7 +760,8 @@
 	if (!d->nr_stripes ||
 	    d->nr_stripes > INT_MAX ||
 	    d->nr_stripes > SIZE_MAX / sizeof(atomic_t)) {
-		pr_err("nr_stripes too large");
+		pr_err("nr_stripes too large or invalid: %u (start sector beyond end of disk?)",
+			(unsigned)d->nr_stripes);
 		return -ENOMEM;
 	}
 
@@ -1820,7 +1821,7 @@
 	free = roundup_pow_of_two(ca->sb.nbuckets) >> 10;
 
 	if (!init_fifo(&ca->free[RESERVE_BTREE], 8, GFP_KERNEL) ||
-	    !init_fifo(&ca->free[RESERVE_PRIO], prio_buckets(ca), GFP_KERNEL) ||
+	    !init_fifo_exact(&ca->free[RESERVE_PRIO], prio_buckets(ca), GFP_KERNEL) ||
 	    !init_fifo(&ca->free[RESERVE_MOVINGGC], free, GFP_KERNEL) ||
 	    !init_fifo(&ca->free[RESERVE_NONE], free, GFP_KERNEL) ||
 	    !init_fifo(&ca->free_inc,	free << 2, GFP_KERNEL) ||
@@ -1844,7 +1845,7 @@
 				struct block_device *bdev, struct cache *ca)
 {
 	char name[BDEVNAME_SIZE];
-	const char *err = NULL;
+	const char *err = NULL; /* must be set for any error case */
 	int ret = 0;
 
 	memcpy(&ca->sb, sb, sizeof(struct cache_sb));
@@ -1861,8 +1862,13 @@
 		ca->discard = CACHE_DISCARD(&ca->sb);
 
 	ret = cache_alloc(ca);
-	if (ret != 0)
+	if (ret != 0) {
+		if (ret == -ENOMEM)
+			err = "cache_alloc(): -ENOMEM";
+		else
+			err = "cache_alloc(): unknown error";
 		goto err;
+	}
 
 	if (kobject_add(&ca->kobj, &part_to_dev(bdev->bd_part)->kobj, "bcache")) {
 		err = "error calling kobject_add";
diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
index 48a5dd7..2206d44 100644
--- a/drivers/mmc/card/block.c
+++ b/drivers/mmc/card/block.c
@@ -1726,6 +1726,7 @@
 			break;
 
 		if (req_op(next) == REQ_OP_DISCARD ||
+		    req_op(next) == REQ_OP_SECURE_ERASE ||
 		    req_op(next) == REQ_OP_FLUSH)
 			break;
 
@@ -2150,6 +2151,7 @@
 	struct mmc_card *card = md->queue.card;
 	struct mmc_host *host = card->host;
 	unsigned long flags;
+	bool req_is_special = mmc_req_is_special(req);
 
 	if (req && !mq->mqrq_prev->req)
 		/* claim host only for the first request */
@@ -2190,8 +2192,7 @@
 	}
 
 out:
-	if ((!req && !(mq->flags & MMC_QUEUE_NEW_REQUEST)) ||
-	    mmc_req_is_special(req))
+	if ((!req && !(mq->flags & MMC_QUEUE_NEW_REQUEST)) || req_is_special)
 		/*
 		 * Release host when there are no more requests
 		 * and after special request(discard, flush) is done.
diff --git a/drivers/mmc/card/queue.c b/drivers/mmc/card/queue.c
index bf14642..7080572 100644
--- a/drivers/mmc/card/queue.c
+++ b/drivers/mmc/card/queue.c
@@ -33,7 +33,8 @@
 	/*
 	 * We only like normal block requests and discards.
 	 */
-	if (req->cmd_type != REQ_TYPE_FS && req_op(req) != REQ_OP_DISCARD) {
+	if (req->cmd_type != REQ_TYPE_FS && req_op(req) != REQ_OP_DISCARD &&
+	    req_op(req) != REQ_OP_SECURE_ERASE) {
 		blk_dump_rq_flags(req, "MMC bad request");
 		return BLKPREP_KILL;
 	}
@@ -64,6 +65,8 @@
 		spin_unlock_irq(q->queue_lock);
 
 		if (req || mq->mqrq_prev->req) {
+			bool req_is_special = mmc_req_is_special(req);
+
 			set_current_state(TASK_RUNNING);
 			mq->issue_fn(mq, req);
 			cond_resched();
@@ -79,7 +82,7 @@
 			 * has been finished. Do not assign it to previous
 			 * request.
 			 */
-			if (mmc_req_is_special(req))
+			if (req_is_special)
 				mq->mqrq_cur->req = NULL;
 
 			mq->mqrq_prev->brq.mrq.data = NULL;
diff --git a/drivers/mmc/card/queue.h b/drivers/mmc/card/queue.h
index d625311..fee5e12 100644
--- a/drivers/mmc/card/queue.h
+++ b/drivers/mmc/card/queue.h
@@ -4,7 +4,9 @@
 static inline bool mmc_req_is_special(struct request *req)
 {
 	return req &&
-		(req_op(req) == REQ_OP_FLUSH || req_op(req) == REQ_OP_DISCARD);
+		(req_op(req) == REQ_OP_FLUSH ||
+		 req_op(req) == REQ_OP_DISCARD ||
+		 req_op(req) == REQ_OP_SECURE_ERASE);
 }
 
 struct request;
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 7ff2e82..2feacc7 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -81,10 +81,12 @@
 bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 		enum nvme_ctrl_state new_state)
 {
-	enum nvme_ctrl_state old_state = ctrl->state;
+	enum nvme_ctrl_state old_state;
 	bool changed = false;
 
 	spin_lock_irq(&ctrl->lock);
+
+	old_state = ctrl->state;
 	switch (new_state) {
 	case NVME_CTRL_LIVE:
 		switch (old_state) {
@@ -140,11 +142,12 @@
 	default:
 		break;
 	}
-	spin_unlock_irq(&ctrl->lock);
 
 	if (changed)
 		ctrl->state = new_state;
 
+	spin_unlock_irq(&ctrl->lock);
+
 	return changed;
 }
 EXPORT_SYMBOL_GPL(nvme_change_ctrl_state);
@@ -608,7 +611,7 @@
 
 	ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &cqe, NULL, 0, 0,
 			NVME_QID_ANY, 0, 0);
-	if (ret >= 0)
+	if (ret >= 0 && result)
 		*result = le32_to_cpu(cqe.result);
 	return ret;
 }
@@ -628,7 +631,7 @@
 
 	ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &cqe, NULL, 0, 0,
 			NVME_QID_ANY, 0, 0);
-	if (ret >= 0)
+	if (ret >= 0 && result)
 		*result = le32_to_cpu(cqe.result);
 	return ret;
 }
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index eafa613..98f1222 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -1069,7 +1069,7 @@
 		nvec = maxvec;
 
 	for (;;) {
-		if (!(flags & PCI_IRQ_NOAFFINITY)) {
+		if (flags & PCI_IRQ_AFFINITY) {
 			dev->irq_affinity = irq_create_affinity_mask(&nvec);
 			if (nvec < minvec)
 				return -ENOSPC;
@@ -1105,7 +1105,7 @@
  **/
 int pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec)
 {
-	return __pci_enable_msi_range(dev, minvec, maxvec, PCI_IRQ_NOAFFINITY);
+	return __pci_enable_msi_range(dev, minvec, maxvec, 0);
 }
 EXPORT_SYMBOL(pci_enable_msi_range);
 
@@ -1120,7 +1120,7 @@
 		return -ERANGE;
 
 	for (;;) {
-		if (!(flags & PCI_IRQ_NOAFFINITY)) {
+		if (flags & PCI_IRQ_AFFINITY) {
 			dev->irq_affinity = irq_create_affinity_mask(&nvec);
 			if (nvec < minvec)
 				return -ENOSPC;
@@ -1160,8 +1160,7 @@
 int pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries,
 		int minvec, int maxvec)
 {
-	return __pci_enable_msix_range(dev, entries, minvec, maxvec,
-			PCI_IRQ_NOAFFINITY);
+	return __pci_enable_msix_range(dev, entries, minvec, maxvec, 0);
 }
 EXPORT_SYMBOL(pci_enable_msix_range);
 
@@ -1187,22 +1186,25 @@
 {
 	int vecs = -ENOSPC;
 
-	if (!(flags & PCI_IRQ_NOMSIX)) {
+	if (flags & PCI_IRQ_MSIX) {
 		vecs = __pci_enable_msix_range(dev, NULL, min_vecs, max_vecs,
 				flags);
 		if (vecs > 0)
 			return vecs;
 	}
 
-	if (!(flags & PCI_IRQ_NOMSI)) {
+	if (flags & PCI_IRQ_MSI) {
 		vecs = __pci_enable_msi_range(dev, min_vecs, max_vecs, flags);
 		if (vecs > 0)
 			return vecs;
 	}
 
 	/* use legacy irq if allowed */
-	if (!(flags & PCI_IRQ_NOLEGACY) && min_vecs == 1)
+	if ((flags & PCI_IRQ_LEGACY) && min_vecs == 1) {
+		pci_intx(dev, 1);
 		return 1;
+	}
+
 	return vecs;
 }
 EXPORT_SYMBOL(pci_alloc_irq_vectors);
diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c
index 3788ed7..a32b417 100644
--- a/drivers/thermal/cpu_cooling.c
+++ b/drivers/thermal/cpu_cooling.c
@@ -740,12 +740,22 @@
 }
 
 /* Bind cpufreq callbacks to thermal cooling device ops */
+
 static struct thermal_cooling_device_ops cpufreq_cooling_ops = {
 	.get_max_state = cpufreq_get_max_state,
 	.get_cur_state = cpufreq_get_cur_state,
 	.set_cur_state = cpufreq_set_cur_state,
 };
 
+static struct thermal_cooling_device_ops cpufreq_power_cooling_ops = {
+	.get_max_state		= cpufreq_get_max_state,
+	.get_cur_state		= cpufreq_get_cur_state,
+	.set_cur_state		= cpufreq_set_cur_state,
+	.get_requested_power	= cpufreq_get_requested_power,
+	.state2power		= cpufreq_state2power,
+	.power2state		= cpufreq_power2state,
+};
+
 /* Notifier for cpufreq policy change */
 static struct notifier_block thermal_cpufreq_notifier_block = {
 	.notifier_call = cpufreq_thermal_notifier,
@@ -795,6 +805,7 @@
 	struct cpumask temp_mask;
 	unsigned int freq, i, num_cpus;
 	int ret;
+	struct thermal_cooling_device_ops *cooling_ops;
 
 	cpumask_and(&temp_mask, clip_cpus, cpu_online_mask);
 	policy = cpufreq_cpu_get(cpumask_first(&temp_mask));
@@ -850,10 +861,6 @@
 	cpumask_copy(&cpufreq_dev->allowed_cpus, clip_cpus);
 
 	if (capacitance) {
-		cpufreq_cooling_ops.get_requested_power =
-			cpufreq_get_requested_power;
-		cpufreq_cooling_ops.state2power = cpufreq_state2power;
-		cpufreq_cooling_ops.power2state = cpufreq_power2state;
 		cpufreq_dev->plat_get_static_power = plat_static_func;
 
 		ret = build_dyn_power_table(cpufreq_dev, capacitance);
@@ -861,6 +868,10 @@
 			cool_dev = ERR_PTR(ret);
 			goto free_table;
 		}
+
+		cooling_ops = &cpufreq_power_cooling_ops;
+	} else {
+		cooling_ops = &cpufreq_cooling_ops;
 	}
 
 	ret = get_idr(&cpufreq_idr, &cpufreq_dev->id);
@@ -885,7 +896,7 @@
 		 cpufreq_dev->id);
 
 	cool_dev = thermal_of_cooling_device_register(np, dev_name, cpufreq_dev,
-						      &cpufreq_cooling_ops);
+						      cooling_ops);
 	if (IS_ERR(cool_dev))
 		goto remove_idr;
 
diff --git a/drivers/thermal/imx_thermal.c b/drivers/thermal/imx_thermal.c
index c5547bd..e473548 100644
--- a/drivers/thermal/imx_thermal.c
+++ b/drivers/thermal/imx_thermal.c
@@ -471,8 +471,6 @@
 
 static int imx_thermal_probe(struct platform_device *pdev)
 {
-	const struct of_device_id *of_id =
-		of_match_device(of_imx_thermal_match, &pdev->dev);
 	struct imx_thermal_data *data;
 	struct regmap *map;
 	int measure_freq;
@@ -490,7 +488,7 @@
 	}
 	data->tempmon = map;
 
-	data->socdata = of_id->data;
+	data->socdata = of_device_get_match_data(&pdev->dev);
 
 	/* make sure the IRQ flag is clear before enabling irq on i.MX6SX */
 	if (data->socdata->version == TEMPMON_IMX6SX) {
diff --git a/drivers/thermal/int340x_thermal/int3406_thermal.c b/drivers/thermal/int340x_thermal/int3406_thermal.c
index a578cd2..1891f34 100644
--- a/drivers/thermal/int340x_thermal/int3406_thermal.c
+++ b/drivers/thermal/int340x_thermal/int3406_thermal.c
@@ -225,7 +225,6 @@
 	.remove = int3406_thermal_remove,
 	.driver = {
 		   .name = "int3406 thermal",
-		   .owner = THIS_MODULE,
 		   .acpi_match_table = int3406_thermal_match,
 		   },
 };
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index 9d6320e..6e29d05 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -88,7 +88,7 @@
 	struct scatterlist *tvc_prot_sgl;
 	struct page **tvc_upages;
 	/* Pointer to response header iovec */
-	struct iovec *tvc_resp_iov;
+	struct iovec tvc_resp_iov;
 	/* Pointer to vhost_scsi for our device */
 	struct vhost_scsi *tvc_vhost;
 	/* Pointer to vhost_virtqueue for the cmd */
@@ -547,7 +547,7 @@
 		memcpy(v_rsp.sense, cmd->tvc_sense_buf,
 		       se_cmd->scsi_sense_length);
 
-		iov_iter_init(&iov_iter, READ, cmd->tvc_resp_iov,
+		iov_iter_init(&iov_iter, READ, &cmd->tvc_resp_iov,
 			      cmd->tvc_in_iovs, sizeof(v_rsp));
 		ret = copy_to_iter(&v_rsp, sizeof(v_rsp), &iov_iter);
 		if (likely(ret == sizeof(v_rsp))) {
@@ -1044,7 +1044,7 @@
 		}
 		cmd->tvc_vhost = vs;
 		cmd->tvc_vq = vq;
-		cmd->tvc_resp_iov = &vq->iov[out];
+		cmd->tvc_resp_iov = vq->iov[out];
 		cmd->tvc_in_iovs = in;
 
 		pr_debug("vhost_scsi got command opcode: %#02x, lun: %d\n",
diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c
index 7487971..c1010f01 100644
--- a/drivers/xen/xenbus/xenbus_dev_frontend.c
+++ b/drivers/xen/xenbus/xenbus_dev_frontend.c
@@ -316,7 +316,7 @@
 			rc = -ENOMEM;
 			goto out;
 		}
-	} else {
+	} else if (msg_type == XS_TRANSACTION_END) {
 		list_for_each_entry(trans, &u->transactions, list)
 			if (trans->handle.id == u->u.msg.tx_id)
 				break;
diff --git a/fs/block_dev.c b/fs/block_dev.c
index c3cdde8..08ae993 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -249,7 +249,8 @@
 		 * thaw_bdev drops it.
 		 */
 		sb = get_super(bdev);
-		drop_super(sb);
+		if (sb)
+			drop_super(sb);
 		mutex_unlock(&bdev->bd_fsfreeze_mutex);
 		return sb;
 	}
@@ -646,7 +647,7 @@
 {
 	struct dentry *dent;
 	dent = mount_pseudo(fs_type, "bdev:", &bdev_sops, NULL, BDEVFS_MAGIC);
-	if (dent)
+	if (!IS_ERR(dent))
 		dent->d_sb->s_iflags |= SB_I_CGROUPWB;
 	return dent;
 }
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index d64d2a5..ccb401e 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -1699,11 +1699,11 @@
 	trace_f2fs_write_end(inode, pos, len, copied);
 
 	set_page_dirty(page);
-	f2fs_put_page(page, 1);
 
 	if (pos + copied > i_size_read(inode))
 		f2fs_i_size_write(inode, pos + copied);
 
+	f2fs_put_page(page, 1);
 	f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
 	return copied;
 }
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 675fa79..14f5fe2 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -538,7 +538,7 @@
 	/* NAT cache management */
 	struct radix_tree_root nat_root;/* root of the nat entry cache */
 	struct radix_tree_root nat_set_root;/* root of the nat set cache */
-	struct percpu_rw_semaphore nat_tree_lock;	/* protect nat_tree_lock */
+	struct rw_semaphore nat_tree_lock;	/* protect nat_tree_lock */
 	struct list_head nat_entries;	/* cached nat entry list (clean) */
 	unsigned int nat_cnt;		/* the # of cached nat entries */
 	unsigned int dirty_nat_cnt;	/* total num of nat entries in set */
@@ -787,7 +787,7 @@
 	struct f2fs_checkpoint *ckpt;		/* raw checkpoint pointer */
 	struct inode *meta_inode;		/* cache meta blocks */
 	struct mutex cp_mutex;			/* checkpoint procedure lock */
-	struct percpu_rw_semaphore cp_rwsem;		/* blocking FS operations */
+	struct rw_semaphore cp_rwsem;		/* blocking FS operations */
 	struct rw_semaphore node_write;		/* locking node writes */
 	wait_queue_head_t cp_wait;
 	unsigned long last_time[MAX_TIME];	/* to store time in jiffies */
@@ -1074,22 +1074,22 @@
 
 static inline void f2fs_lock_op(struct f2fs_sb_info *sbi)
 {
-	percpu_down_read(&sbi->cp_rwsem);
+	down_read(&sbi->cp_rwsem);
 }
 
 static inline void f2fs_unlock_op(struct f2fs_sb_info *sbi)
 {
-	percpu_up_read(&sbi->cp_rwsem);
+	up_read(&sbi->cp_rwsem);
 }
 
 static inline void f2fs_lock_all(struct f2fs_sb_info *sbi)
 {
-	percpu_down_write(&sbi->cp_rwsem);
+	down_write(&sbi->cp_rwsem);
 }
 
 static inline void f2fs_unlock_all(struct f2fs_sb_info *sbi)
 {
-	percpu_up_write(&sbi->cp_rwsem);
+	up_write(&sbi->cp_rwsem);
 }
 
 static inline int __get_cp_reason(struct f2fs_sb_info *sbi)
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 0e493f6..47abb96 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -2086,15 +2086,19 @@
 	if (unlikely(f2fs_readonly(src->i_sb)))
 		return -EROFS;
 
-	if (S_ISDIR(src->i_mode) || S_ISDIR(dst->i_mode))
-		return -EISDIR;
+	if (!S_ISREG(src->i_mode) || !S_ISREG(dst->i_mode))
+		return -EINVAL;
 
 	if (f2fs_encrypted_inode(src) || f2fs_encrypted_inode(dst))
 		return -EOPNOTSUPP;
 
 	inode_lock(src);
-	if (src != dst)
-		inode_lock(dst);
+	if (src != dst) {
+		if (!inode_trylock(dst)) {
+			ret = -EBUSY;
+			goto out;
+		}
+	}
 
 	ret = -EINVAL;
 	if (pos_in + len > src->i_size || pos_in + len < pos_in)
@@ -2152,6 +2156,7 @@
 out_unlock:
 	if (src != dst)
 		inode_unlock(dst);
+out:
 	inode_unlock(src);
 	return ret;
 }
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index b2fa4b6..f75d197 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -206,14 +206,14 @@
 	struct nat_entry *e;
 	bool need = false;
 
-	percpu_down_read(&nm_i->nat_tree_lock);
+	down_read(&nm_i->nat_tree_lock);
 	e = __lookup_nat_cache(nm_i, nid);
 	if (e) {
 		if (!get_nat_flag(e, IS_CHECKPOINTED) &&
 				!get_nat_flag(e, HAS_FSYNCED_INODE))
 			need = true;
 	}
-	percpu_up_read(&nm_i->nat_tree_lock);
+	up_read(&nm_i->nat_tree_lock);
 	return need;
 }
 
@@ -223,11 +223,11 @@
 	struct nat_entry *e;
 	bool is_cp = true;
 
-	percpu_down_read(&nm_i->nat_tree_lock);
+	down_read(&nm_i->nat_tree_lock);
 	e = __lookup_nat_cache(nm_i, nid);
 	if (e && !get_nat_flag(e, IS_CHECKPOINTED))
 		is_cp = false;
-	percpu_up_read(&nm_i->nat_tree_lock);
+	up_read(&nm_i->nat_tree_lock);
 	return is_cp;
 }
 
@@ -237,13 +237,13 @@
 	struct nat_entry *e;
 	bool need_update = true;
 
-	percpu_down_read(&nm_i->nat_tree_lock);
+	down_read(&nm_i->nat_tree_lock);
 	e = __lookup_nat_cache(nm_i, ino);
 	if (e && get_nat_flag(e, HAS_LAST_FSYNC) &&
 			(get_nat_flag(e, IS_CHECKPOINTED) ||
 			 get_nat_flag(e, HAS_FSYNCED_INODE)))
 		need_update = false;
-	percpu_up_read(&nm_i->nat_tree_lock);
+	up_read(&nm_i->nat_tree_lock);
 	return need_update;
 }
 
@@ -284,7 +284,7 @@
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	struct nat_entry *e;
 
-	percpu_down_write(&nm_i->nat_tree_lock);
+	down_write(&nm_i->nat_tree_lock);
 	e = __lookup_nat_cache(nm_i, ni->nid);
 	if (!e) {
 		e = grab_nat_entry(nm_i, ni->nid);
@@ -334,7 +334,7 @@
 			set_nat_flag(e, HAS_FSYNCED_INODE, true);
 		set_nat_flag(e, HAS_LAST_FSYNC, fsync_done);
 	}
-	percpu_up_write(&nm_i->nat_tree_lock);
+	up_write(&nm_i->nat_tree_lock);
 }
 
 int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink)
@@ -342,7 +342,8 @@
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	int nr = nr_shrink;
 
-	percpu_down_write(&nm_i->nat_tree_lock);
+	if (!down_write_trylock(&nm_i->nat_tree_lock))
+		return 0;
 
 	while (nr_shrink && !list_empty(&nm_i->nat_entries)) {
 		struct nat_entry *ne;
@@ -351,7 +352,7 @@
 		__del_from_nat_cache(nm_i, ne);
 		nr_shrink--;
 	}
-	percpu_up_write(&nm_i->nat_tree_lock);
+	up_write(&nm_i->nat_tree_lock);
 	return nr - nr_shrink;
 }
 
@@ -373,13 +374,13 @@
 	ni->nid = nid;
 
 	/* Check nat cache */
-	percpu_down_read(&nm_i->nat_tree_lock);
+	down_read(&nm_i->nat_tree_lock);
 	e = __lookup_nat_cache(nm_i, nid);
 	if (e) {
 		ni->ino = nat_get_ino(e);
 		ni->blk_addr = nat_get_blkaddr(e);
 		ni->version = nat_get_version(e);
-		percpu_up_read(&nm_i->nat_tree_lock);
+		up_read(&nm_i->nat_tree_lock);
 		return;
 	}
 
@@ -403,11 +404,11 @@
 	node_info_from_raw_nat(ni, &ne);
 	f2fs_put_page(page, 1);
 cache:
-	percpu_up_read(&nm_i->nat_tree_lock);
+	up_read(&nm_i->nat_tree_lock);
 	/* cache nat entry */
-	percpu_down_write(&nm_i->nat_tree_lock);
+	down_write(&nm_i->nat_tree_lock);
 	cache_nat_entry(sbi, nid, &ne);
-	percpu_up_write(&nm_i->nat_tree_lock);
+	up_write(&nm_i->nat_tree_lock);
 }
 
 /*
@@ -1788,7 +1789,7 @@
 	ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), FREE_NID_PAGES,
 							META_NAT, true);
 
-	percpu_down_read(&nm_i->nat_tree_lock);
+	down_read(&nm_i->nat_tree_lock);
 
 	while (1) {
 		struct page *page = get_current_nat_page(sbi, nid);
@@ -1820,7 +1821,7 @@
 			remove_free_nid(nm_i, nid);
 	}
 	up_read(&curseg->journal_rwsem);
-	percpu_up_read(&nm_i->nat_tree_lock);
+	up_read(&nm_i->nat_tree_lock);
 
 	ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nm_i->next_scan_nid),
 					nm_i->ra_nid_pages, META_NAT, false);
@@ -2209,7 +2210,7 @@
 	if (!nm_i->dirty_nat_cnt)
 		return;
 
-	percpu_down_write(&nm_i->nat_tree_lock);
+	down_write(&nm_i->nat_tree_lock);
 
 	/*
 	 * if there are no enough space in journal to store dirty nat
@@ -2232,7 +2233,7 @@
 	list_for_each_entry_safe(set, tmp, &sets, set_list)
 		__flush_nat_entry_set(sbi, set);
 
-	percpu_up_write(&nm_i->nat_tree_lock);
+	up_write(&nm_i->nat_tree_lock);
 
 	f2fs_bug_on(sbi, nm_i->dirty_nat_cnt);
 }
@@ -2268,8 +2269,7 @@
 
 	mutex_init(&nm_i->build_lock);
 	spin_lock_init(&nm_i->free_nid_list_lock);
-	if (percpu_init_rwsem(&nm_i->nat_tree_lock))
-		return -ENOMEM;
+	init_rwsem(&nm_i->nat_tree_lock);
 
 	nm_i->next_scan_nid = le32_to_cpu(sbi->ckpt->next_free_nid);
 	nm_i->bitmap_size = __bitmap_size(sbi, NAT_BITMAP);
@@ -2326,7 +2326,7 @@
 	spin_unlock(&nm_i->free_nid_list_lock);
 
 	/* destroy nat cache */
-	percpu_down_write(&nm_i->nat_tree_lock);
+	down_write(&nm_i->nat_tree_lock);
 	while ((found = __gang_lookup_nat_cache(nm_i,
 					nid, NATVEC_SIZE, natvec))) {
 		unsigned idx;
@@ -2351,9 +2351,8 @@
 			kmem_cache_free(nat_entry_set_slab, setvec[idx]);
 		}
 	}
-	percpu_up_write(&nm_i->nat_tree_lock);
+	up_write(&nm_i->nat_tree_lock);
 
-	percpu_free_rwsem(&nm_i->nat_tree_lock);
 	kfree(nm_i->nat_bitmap);
 	sbi->nm_info = NULL;
 	kfree(nm_i);
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 1b86d3f..7f863a6 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -706,8 +706,6 @@
 		percpu_counter_destroy(&sbi->nr_pages[i]);
 	percpu_counter_destroy(&sbi->alloc_valid_block_count);
 	percpu_counter_destroy(&sbi->total_valid_inode_count);
-
-	percpu_free_rwsem(&sbi->cp_rwsem);
 }
 
 static void f2fs_put_super(struct super_block *sb)
@@ -1483,9 +1481,6 @@
 {
 	int i, err;
 
-	if (percpu_init_rwsem(&sbi->cp_rwsem))
-		return -ENOMEM;
-
 	for (i = 0; i < NR_COUNT_TYPE; i++) {
 		err = percpu_counter_init(&sbi->nr_pages[i], 0, GFP_KERNEL);
 		if (err)
@@ -1686,6 +1681,7 @@
 		sbi->write_io[i].bio = NULL;
 	}
 
+	init_rwsem(&sbi->cp_rwsem);
 	init_waitqueue_head(&sbi->cp_wait);
 	init_sb_info(sbi);
 
diff --git a/fs/ubifs/tnc_commit.c b/fs/ubifs/tnc_commit.c
index b45345d..51157da 100644
--- a/fs/ubifs/tnc_commit.c
+++ b/fs/ubifs/tnc_commit.c
@@ -370,7 +370,7 @@
 
 	p = c->gap_lebs;
 	do {
-		ubifs_assert(p < c->gap_lebs + sizeof(int) * c->lst.idx_lebs);
+		ubifs_assert(p < c->gap_lebs + c->lst.idx_lebs);
 		written = layout_leb_in_gaps(c, p);
 		if (written < 0) {
 			err = written;
diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c
index e237811..11a0041 100644
--- a/fs/ubifs/xattr.c
+++ b/fs/ubifs/xattr.c
@@ -575,7 +575,8 @@
 	dbg_gen("xattr '%s', ino %lu ('%pd'), buf size %zd", name,
 		inode->i_ino, dentry, size);
 
-	return  __ubifs_getxattr(inode, name, buffer, size);
+	name = xattr_full_name(handler, name);
+	return __ubifs_getxattr(inode, name, buffer, size);
 }
 
 static int ubifs_xattr_set(const struct xattr_handler *handler,
@@ -586,6 +587,8 @@
 	dbg_gen("xattr '%s', host ino %lu ('%pd'), size %zd",
 		name, inode->i_ino, dentry, size);
 
+	name = xattr_full_name(handler, name);
+
 	if (value)
 		return __ubifs_setxattr(inode, name, value, size, flags);
 	else
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 59ffaa6..23ddf4b 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -71,7 +71,8 @@
 {
 	if (bio &&
 	    bio->bi_iter.bi_size &&
-	    bio_op(bio) != REQ_OP_DISCARD)
+	    bio_op(bio) != REQ_OP_DISCARD &&
+	    bio_op(bio) != REQ_OP_SECURE_ERASE)
 		return true;
 
 	return false;
@@ -79,7 +80,9 @@
 
 static inline bool bio_no_advance_iter(struct bio *bio)
 {
-	return bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_WRITE_SAME;
+	return bio_op(bio) == REQ_OP_DISCARD ||
+	       bio_op(bio) == REQ_OP_SECURE_ERASE ||
+	       bio_op(bio) == REQ_OP_WRITE_SAME;
 }
 
 static inline bool bio_is_rw(struct bio *bio)
@@ -199,6 +202,9 @@
 	if (bio_op(bio) == REQ_OP_DISCARD)
 		return 1;
 
+	if (bio_op(bio) == REQ_OP_SECURE_ERASE)
+		return 1;
+
 	if (bio_op(bio) == REQ_OP_WRITE_SAME)
 		return 1;
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 2c210b6..e79055c 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -882,7 +882,7 @@
 static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q,
 						     int op)
 {
-	if (unlikely(op == REQ_OP_DISCARD))
+	if (unlikely(op == REQ_OP_DISCARD || op == REQ_OP_SECURE_ERASE))
 		return min(q->limits.max_discard_sectors, UINT_MAX >> 9);
 
 	if (unlikely(op == REQ_OP_WRITE_SAME))
@@ -913,7 +913,9 @@
 	if (unlikely(rq->cmd_type != REQ_TYPE_FS))
 		return q->limits.max_hw_sectors;
 
-	if (!q->limits.chunk_sectors || (req_op(rq) == REQ_OP_DISCARD))
+	if (!q->limits.chunk_sectors ||
+	    req_op(rq) == REQ_OP_DISCARD ||
+	    req_op(rq) == REQ_OP_SECURE_ERASE)
 		return blk_queue_get_max_sectors(q, req_op(rq));
 
 	return min(blk_max_size_offset(q, offset),
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 2599a98..fbc1fa6 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1251,10 +1251,12 @@
 int pci_set_vga_state(struct pci_dev *pdev, bool decode,
 		      unsigned int command_bits, u32 flags);
 
-#define PCI_IRQ_NOLEGACY	(1 << 0) /* don't use legacy interrupts */
-#define PCI_IRQ_NOMSI		(1 << 1) /* don't use MSI interrupts */
-#define PCI_IRQ_NOMSIX		(1 << 2) /* don't use MSI-X interrupts */
-#define PCI_IRQ_NOAFFINITY	(1 << 3) /* don't auto-assign affinity */
+#define PCI_IRQ_LEGACY		(1 << 0) /* allow legacy interrupts */
+#define PCI_IRQ_MSI		(1 << 1) /* allow MSI interrupts */
+#define PCI_IRQ_MSIX		(1 << 2) /* allow MSI-X interrupts */
+#define PCI_IRQ_AFFINITY	(1 << 3) /* auto-assign affinity */
+#define PCI_IRQ_ALL_TYPES \
+	(PCI_IRQ_LEGACY | PCI_IRQ_MSI | PCI_IRQ_MSIX)
 
 /* kmem_cache style wrapper around pci_alloc_consistent() */
 
diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h
index 9a37c541..b5486e6 100644
--- a/include/xen/xen-ops.h
+++ b/include/xen/xen-ops.h
@@ -9,8 +9,8 @@
 
 DECLARE_PER_CPU(struct vcpu_info *, xen_vcpu);
 
-DECLARE_PER_CPU(int, xen_vcpu_id);
-static inline int xen_vcpu_nr(int cpu)
+DECLARE_PER_CPU(uint32_t, xen_vcpu_id);
+static inline uint32_t xen_vcpu_nr(int cpu)
 {
 	return per_cpu(xen_vcpu_id, cpu);
 }
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 7598e6c..dbafc5d 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -223,7 +223,7 @@
 	what |= MASK_TC_BIT(op_flags, META);
 	what |= MASK_TC_BIT(op_flags, PREFLUSH);
 	what |= MASK_TC_BIT(op_flags, FUA);
-	if (op == REQ_OP_DISCARD)
+	if (op == REQ_OP_DISCARD || op == REQ_OP_SECURE_ERASE)
 		what |= BLK_TC_ACT(BLK_TC_DISCARD);
 	if (op == REQ_OP_FLUSH)
 		what |= BLK_TC_ACT(BLK_TC_FLUSH);
diff --git a/mm/usercopy.c b/mm/usercopy.c
index 8ebae91..a3cc305 100644
--- a/mm/usercopy.c
+++ b/mm/usercopy.c
@@ -83,7 +83,7 @@
 	unsigned long check_high = check_low + n;
 
 	/* Does not overlap if entirely above or entirely below. */
-	if (check_low >= high || check_high < low)
+	if (check_low >= high || check_high <= low)
 		return false;
 
 	return true;
@@ -124,7 +124,7 @@
 static inline const char *check_bogus_address(const void *ptr, unsigned long n)
 {
 	/* Reject if object wraps past end of memory. */
-	if (ptr + n < ptr)
+	if ((unsigned long)ptr + n < (unsigned long)ptr)
 		return "<wrapped address>";
 
 	/* Reject if NULL or ZERO-allocation. */
diff --git a/tools/gpio/gpio-event-mon.c b/tools/gpio/gpio-event-mon.c
index 448ed96..1c14c25 100644
--- a/tools/gpio/gpio-event-mon.c
+++ b/tools/gpio/gpio-event-mon.c
@@ -1,5 +1,5 @@
 /*
- * gpio-hammer - example swiss army knife to shake GPIO lines on a system
+ * gpio-event-mon - monitor GPIO line events from userspace
  *
  * Copyright (C) 2016 Linus Walleij
  *