Re: Linux 4.9.32

[Greg KH]

diff --git a/Makefile b/Makefile
index 3601995f63f9..3d8781997968 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
 VERSION = 4
 PATCHLEVEL = 9
-SUBLEVEL = 31
+SUBLEVEL = 32
 EXTRAVERSION =
 NAME = Roaring Lionus
 
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 34e3f3c45634..f4e54503afa9 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -81,7 +81,7 @@ __setup("fpe=", fpe_setup);
 extern void init_default_cache_policy(unsigned long);
 extern void paging_init(const struct machine_desc *desc);
 extern void early_paging_init(const struct machine_desc *);
-extern void sanity_check_meminfo(void);
+extern void adjust_lowmem_bounds(void);
 extern enum reboot_mode reboot_mode;
 extern void setup_dma_zone(const struct machine_desc *desc);
 
@@ -1093,8 +1093,14 @@ void __init setup_arch(char **cmdline_p)
 	setup_dma_zone(mdesc);
 	xen_early_init();
 	efi_init();
-	sanity_check_meminfo();
+	/*
+	 * Make sure the calculation for lowmem/highmem is set appropriately
+	 * before reserving/allocating any mmeory
+	 */
+	adjust_lowmem_bounds();
 	arm_memblock_init(mdesc);
+	/* Memory may have been removed so recalculate the bounds. */
+	adjust_lowmem_bounds();
 
 	early_ioremap_reset();
 
diff --git a/arch/arm/kvm/init.S b/arch/arm/kvm/init.S
index bf89c919efc1..bd0ee7fc304c 100644
--- a/arch/arm/kvm/init.S
+++ b/arch/arm/kvm/init.S
@@ -95,7 +95,6 @@ __do_hyp_init:
 	@  - Write permission implies XN: disabled
 	@  - Instruction cache: enabled
 	@  - Data/Unified cache: enabled
-	@  - Memory alignment checks: enabled
 	@  - MMU: enabled (this code must be run from an identity mapping)
 	mrc	p15, 4, r0, c1, c0, 0	@ HSCR
 	ldr	r2, =HSCTLR_MASK
@@ -103,8 +102,8 @@ __do_hyp_init:
 	mrc	p15, 0, r1, c1, c0, 0	@ SCTLR
 	ldr	r2, =(HSCTLR_EE | HSCTLR_FI | HSCTLR_I | HSCTLR_C)
 	and	r1, r1, r2
- ARM(	ldr	r2, =(HSCTLR_M | HSCTLR_A)			)
- THUMB(	ldr	r2, =(HSCTLR_M | HSCTLR_A | HSCTLR_TE)		)
+ ARM(	ldr	r2, =(HSCTLR_M)					)
+ THUMB(	ldr	r2, =(HSCTLR_M | HSCTLR_TE)			)
 	orr	r1, r1, r2
 	orr	r0, r0, r1
 	mcr	p15, 4, r0, c1, c0, 0	@ HSCR
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index 2fd5c135e8a4..332ce3b5a34f 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -872,6 +872,9 @@ static pmd_t *stage2_get_pmd(struct kvm *kvm, struct kvm_mmu_memory_cache *cache
 	pmd_t *pmd;
 
 	pud = stage2_get_pud(kvm, cache, addr);
+	if (!pud)
+		return NULL;
+
 	if (stage2_pud_none(*pud)) {
 		if (!cache)
 			return NULL;
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 4001dd15818d..5cbfd9f86412 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -1152,13 +1152,12 @@ early_param("vmalloc", early_vmalloc);
 
 phys_addr_t arm_lowmem_limit __initdata = 0;
 
-void __init sanity_check_meminfo(void)
+void __init adjust_lowmem_bounds(void)
 {
 	phys_addr_t memblock_limit = 0;
-	int highmem = 0;
 	u64 vmalloc_limit;
 	struct memblock_region *reg;
-	bool should_use_highmem = false;
+	phys_addr_t lowmem_limit = 0;
 
 	/*
 	 * Let's use our own (unoptimized) equivalent of __pa() that is
@@ -1172,43 +1171,18 @@ void __init sanity_check_meminfo(void)
 	for_each_memblock(memory, reg) {
 		phys_addr_t block_start = reg->base;
 		phys_addr_t block_end = reg->base + reg->size;
-		phys_addr_t size_limit = reg->size;
 
-		if (reg->base >= vmalloc_limit)
-			highmem = 1;
-		else
-			size_limit = vmalloc_limit - reg->base;
-
-
-		if (!IS_ENABLED(CONFIG_HIGHMEM) || cache_is_vipt_aliasing()) {
-
-			if (highmem) {
-				pr_notice("Ignoring RAM at %pa-%pa (!CONFIG_HIGHMEM)\n",
-					  &block_start, &block_end);
-				memblock_remove(reg->base, reg->size);
-				should_use_highmem = true;
-				continue;
-			}
-
-			if (reg->size > size_limit) {
-				phys_addr_t overlap_size = reg->size - size_limit;
-
-				pr_notice("Truncating RAM at %pa-%pa",
-					  &block_start, &block_end);
-				block_end = vmalloc_limit;
-				pr_cont(" to -%pa", &block_end);
-				memblock_remove(vmalloc_limit, overlap_size);
-				should_use_highmem = true;
-			}
-		}
-
-		if (!highmem) {
-			if (block_end > arm_lowmem_limit) {
-				if (reg->size > size_limit)
-					arm_lowmem_limit = vmalloc_limit;
-				else
-					arm_lowmem_limit = block_end;
-			}
+		if (reg->base < vmalloc_limit) {
+			if (block_end > lowmem_limit)
+				/*
+				 * Compare as u64 to ensure vmalloc_limit does
+				 * not get truncated. block_end should always
+				 * fit in phys_addr_t so there should be no
+				 * issue with assignment.
+				 */
+				lowmem_limit = min_t(u64,
+							 vmalloc_limit,
+							 block_end);
 
 			/*
 			 * Find the first non-pmd-aligned page, and point
@@ -1227,14 +1201,13 @@ void __init sanity_check_meminfo(void)
 				if (!IS_ALIGNED(block_start, PMD_SIZE))
 					memblock_limit = block_start;
 				else if (!IS_ALIGNED(block_end, PMD_SIZE))
-					memblock_limit = arm_lowmem_limit;
+					memblock_limit = lowmem_limit;
 			}
 
 		}
 	}
 
-	if (should_use_highmem)
-		pr_notice("Consider using a HIGHMEM enabled kernel.\n");
+	arm_lowmem_limit = lowmem_limit;
 
 	high_memory = __va(arm_lowmem_limit - 1) + 1;
 
@@ -1248,6 +1221,18 @@ void __init sanity_check_meminfo(void)
 	if (!memblock_limit)
 		memblock_limit = arm_lowmem_limit;
 
+	if (!IS_ENABLED(CONFIG_HIGHMEM) || cache_is_vipt_aliasing()) {
+		if (memblock_end_of_DRAM() > arm_lowmem_limit) {
+			phys_addr_t end = memblock_end_of_DRAM();
+
+			pr_notice("Ignoring RAM at %pa-%pa\n",
+				  &memblock_limit, &end);
+			pr_notice("Consider using a HIGHMEM enabled kernel.\n");
+
+			memblock_remove(memblock_limit, end - memblock_limit);
+		}
+	}
+
 	memblock_set_current_limit(memblock_limit);
 }
 
diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c
index 2740967727e2..13a25d6282f8 100644
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@@ -85,7 +85,7 @@ static unsigned long irbar_read(void)
 }
 
 /* MPU initialisation functions */
-void __init sanity_check_meminfo_mpu(void)
+void __init adjust_lowmem_bounds_mpu(void)
 {
 	phys_addr_t phys_offset = PHYS_OFFSET;
 	phys_addr_t aligned_region_size, specified_mem_size, rounded_mem_size;
@@ -274,7 +274,7 @@ void __init mpu_setup(void)
 	}
 }
 #else
-static void sanity_check_meminfo_mpu(void) {}
+static void adjust_lowmem_bounds_mpu(void) {}
 static void __init mpu_setup(void) {}
 #endif /* CONFIG_ARM_MPU */
 
@@ -295,10 +295,10 @@ void __init arm_mm_memblock_reserve(void)
 #endif
 }
 
-void __init sanity_check_meminfo(void)
+void __init adjust_lowmem_bounds(void)
 {
 	phys_addr_t end;
-	sanity_check_meminfo_mpu();
+	adjust_lowmem_bounds_mpu();
 	end = memblock_end_of_DRAM();
 	high_memory = __va(end - 1) + 1;
 	memblock_set_current_limit(end);
diff --git a/arch/arm64/include/asm/asm-uaccess.h b/arch/arm64/include/asm/asm-uaccess.h
new file mode 100644
index 000000000000..be2d2347d995
--- /dev/null
+++ b/arch/arm64/include/asm/asm-uaccess.h
@@ -0,0 +1,13 @@
+#ifndef __ASM_ASM_UACCESS_H
+#define __ASM_ASM_UACCESS_H
+
+/*
+ * Remove the address tag from a virtual address, if present.
+ */
+	.macro	clear_address_tag, dst, addr
+	tst	\addr, #(1 << 55)
+	bic	\dst, \addr, #(0xff << 56)
+	csel	\dst, \dst, \addr, eq
+	.endm
+
+#endif
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 6c80b3699cb8..7393cc767edb 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -94,6 +94,10 @@
 #define SCTLR_ELx_A	(1 << 1)
 #define SCTLR_ELx_M	1
 
+#define SCTLR_EL2_RES1	((1 << 4)  | (1 << 5)  | (1 << 11) | (1 << 16) | \
+			 (1 << 16) | (1 << 18) | (1 << 22) | (1 << 23) | \
+			 (1 << 28) | (1 << 29))
+
 #define SCTLR_ELx_FLAGS	(SCTLR_ELx_M | SCTLR_ELx_A | SCTLR_ELx_C | \
 			 SCTLR_ELx_SA | SCTLR_ELx_I)
 
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index 14cca10aeb4e..811cf16a65f9 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -105,9 +105,9 @@ static inline void set_fs(mm_segment_t fs)
 })
 
 /*
- * When dealing with data aborts or instruction traps we may end up with
- * a tagged userland pointer. Clear the tag to get a sane pointer to pass
- * on to access_ok(), for instance.
+ * When dealing with data aborts, watchpoints, or instruction traps we may end
+ * up with a tagged userland pointer. Clear the tag to get a sane pointer to
+ * pass on to access_ok(), for instance.
  */
 #define untagged_addr(addr)		sign_extend64(addr, 55)
 
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 79b0fe24d5b7..b4c7db434654 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -30,6 +30,7 @@
 #include <asm/irq.h>
 #include <asm/memory.h>
 #include <asm/thread_info.h>
+#include <asm/asm-uaccess.h>
 #include <asm/unistd.h>
 
 /*
@@ -369,12 +370,13 @@ el1_da:
 	/*
 	 * Data abort handling
 	 */
-	mrs	x0, far_el1
+	mrs	x3, far_el1
 	enable_dbg
 	// re-enable interrupts if they were enabled in the aborted context
 	tbnz	x23, #7, 1f			// PSR_I_BIT
 	enable_irq
 1:
+	clear_address_tag x0, x3
 	mov	x2, sp				// struct pt_regs
 	bl	do_mem_abort
 
@@ -535,7 +537,7 @@ el0_da:
 	// enable interrupts before calling the main handler
 	enable_dbg_and_irq
 	ct_user_exit
-	bic	x0, x26, #(0xff << 56)
+	clear_address_tag x0, x26
 	mov	x1, x25
 	mov	x2, sp
 	bl	do_mem_abort
diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c
index 948b73148d56..0b9e5f6290f9 100644
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -36,6 +36,7 @@
 #include <asm/traps.h>
 #include <asm/cputype.h>
 #include <asm/system_misc.h>
+#include <asm/uaccess.h>
 
 /* Breakpoint currently in use for each BRP. */
 static DEFINE_PER_CPU(struct perf_event *, bp_on_reg[ARM_MAX_BRP]);
@@ -696,7 +697,7 @@ static int watchpoint_handler(unsigned long addr, unsigned int esr,
 
 		/* Check if the watchpoint value matches. */
 		val = read_wb_reg(AARCH64_DBG_REG_WVR, i);
-		if (val != (addr & ~alignment_mask))
+		if (val != (untagged_addr(addr) & ~alignment_mask))
 			goto unlock;
 
 		/* Possible match, check the byte address select to confirm. */
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 11e5eae088ab..f22826135c73 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -435,7 +435,7 @@ int cpu_enable_cache_maint_trap(void *__unused)
 }
 
 #define __user_cache_maint(insn, address, res)			\
-	if (untagged_addr(address) >= user_addr_max())		\
+	if (address >= user_addr_max())				\
 		res = -EFAULT;					\
 	else							\
 		asm volatile (					\
@@ -458,7 +458,7 @@ static void user_cache_maint_handler(unsigned int esr, struct pt_regs *regs)
 	int crm = (esr & ESR_ELx_SYS64_ISS_CRM_MASK) >> ESR_ELx_SYS64_ISS_CRM_SHIFT;
 	int ret = 0;
 
-	address = (rt == 31) ? 0 : regs->regs[rt];
+	address = (rt == 31) ? 0 : untagged_addr(regs->regs[rt]);
 
 	switch (crm) {
 	case ESR_ELx_SYS64_ISS_CRM_DC_CVAU:	/* DC CVAU, gets promoted */
diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp-init.S
index 6b29d3d9e1f2..4bbff904169d 100644
--- a/arch/arm64/kvm/hyp-init.S
+++ b/arch/arm64/kvm/hyp-init.S
@@ -102,10 +102,13 @@ __do_hyp_init:
 	tlbi	alle2
 	dsb	sy
 
-	mrs	x4, sctlr_el2
-	and	x4, x4, #SCTLR_ELx_EE	// preserve endianness of EL2
-	ldr	x5, =SCTLR_ELx_FLAGS
-	orr	x4, x4, x5
+	/*
+	 * Preserve all the RES1 bits while setting the default flags,
+	 * as well as the EE bit on BE. Drop the A flag since the compiler
+	 * is allowed to generate unaligned accesses.
+	 */
+	ldr	x4, =(SCTLR_EL2_RES1 | (SCTLR_ELx_FLAGS & ~SCTLR_ELx_A))
+CPU_BE(	orr	x4, x4, #SCTLR_ELx_EE)
 	msr	sctlr_el2, x4
 	isb
 
diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index 8b3b46b7b0f2..329771559cbb 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -44,8 +44,22 @@ extern void __init dump_numa_cpu_topology(void);
 extern int sysfs_add_device_to_node(struct device *dev, int nid);
 extern void sysfs_remove_device_from_node(struct device *dev, int nid);
 
+static inline int early_cpu_to_node(int cpu)
+{
+	int nid;
+
+	nid = numa_cpu_lookup_table[cpu];
+
+	/*
+	 * Fall back to node 0 if nid is unset (it should be, except bugs).
+	 * This allows callers to safely do NODE_DATA(early_cpu_to_node(cpu)).
+	 */
+	return (nid < 0) ? 0 : nid;
+}
 #else
 
+static inline int early_cpu_to_node(int cpu) { return 0; }
+
 static inline void dump_numa_cpu_topology(void) {}
 
 static inline int sysfs_add_device_to_node(struct device *dev, int nid)
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index c7164739dc75..b249c2fb99c8 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1659,6 +1659,7 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp)
 #ifdef CONFIG_VSX
 	current->thread.used_vsr = 0;
 #endif
+	current->thread.load_fp = 0;
 	memset(&current->thread.fp_state, 0, sizeof(current->thread.fp_state));
 	current->thread.fp_save_area = NULL;
 #ifdef CONFIG_ALTIVEC
@@ -1667,6 +1668,7 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp)
 	current->thread.vr_save_area = NULL;
 	current->thread.vrsave = 0;
 	current->thread.used_vr = 0;
+	current->thread.load_vec = 0;
 #endif /* CONFIG_ALTIVEC */
 #ifdef CONFIG_SPE
 	memset(current->thread.evr, 0, sizeof(current->thread.evr));
@@ -1678,6 +1680,7 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp)
 	current->thread.tm_tfhar = 0;
 	current->thread.tm_texasr = 0;
 	current->thread.tm_tfiar = 0;
+	current->thread.load_tm = 0;
 #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
 }
 EXPORT_SYMBOL(start_thread);
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index a12be60181bf..ada71bee176d 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -595,7 +595,7 @@ void __init emergency_stack_init(void)
 
 static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align)
 {
-	return __alloc_bootmem_node(NODE_DATA(cpu_to_node(cpu)), size, align,
+	return __alloc_bootmem_node(NODE_DATA(early_cpu_to_node(cpu)), size, align,
 				    __pa(MAX_DMA_ADDRESS));
 }
 
@@ -606,7 +606,7 @@ static void __init pcpu_fc_free(void *ptr, size_t size)
 
 static int pcpu_cpu_distance(unsigned int from, unsigned int to)
 {
-	if (cpu_to_node(from) == cpu_to_node(to))
+	if (early_cpu_to_node(from) == early_cpu_to_node(to))
 		return LOCAL_DISTANCE;
 	else
 		return REMOTE_DISTANCE;
diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index 76ec104e88be..c0a0947f43bb 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -124,6 +124,7 @@ static struct property *dlpar_clone_drconf_property(struct device_node *dn)
 	for (i = 0; i < num_lmbs; i++) {
 		lmbs[i].base_addr = be64_to_cpu(lmbs[i].base_addr);
 		lmbs[i].drc_index = be32_to_cpu(lmbs[i].drc_index);
+		lmbs[i].aa_index = be32_to_cpu(lmbs[i].aa_index);
 		lmbs[i].flags = be32_to_cpu(lmbs[i].flags);
 	}
 
@@ -147,6 +148,7 @@ static void dlpar_update_drconf_property(struct device_node *dn,
 	for (i = 0; i < num_lmbs; i++) {
 		lmbs[i].base_addr = cpu_to_be64(lmbs[i].base_addr);
 		lmbs[i].drc_index = cpu_to_be32(lmbs[i].drc_index);
+		lmbs[i].aa_index = cpu_to_be32(lmbs[i].aa_index);
 		lmbs[i].flags = cpu_to_be32(lmbs[i].flags);
 	}
 
diff --git a/arch/powerpc/sysdev/simple_gpio.c b/arch/powerpc/sysdev/simple_gpio.c
index ef470b470b04..6afddae2fb47 100644
--- a/arch/powerpc/sysdev/simple_gpio.c
+++ b/arch/powerpc/sysdev/simple_gpio.c
@@ -75,7 +75,8 @@ static int u8_gpio_dir_out(struct gpio_chip *gc, unsigned int gpio, int val)
 
 static void u8_gpio_save_regs(struct of_mm_gpio_chip *mm_gc)
 {
-	struct u8_gpio_chip *u8_gc = gpiochip_get_data(&mm_gc->gc);
+	struct u8_gpio_chip *u8_gc =
+		container_of(mm_gc, struct u8_gpio_chip, mm_gc);
 
 	u8_gc->data = in_8(mm_gc->regs);
 }
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 165ecdd24d22..b27e48e25841 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -187,9 +187,9 @@ config NR_CPUS
 	int "Maximum number of CPUs"
 	depends on SMP
 	range 2 32 if SPARC32
-	range 2 1024 if SPARC64
+	range 2 4096 if SPARC64
 	default 32 if SPARC32
-	default 64 if SPARC64
+	default 4096 if SPARC64
 
 source kernel/Kconfig.hz
 
diff --git a/arch/sparc/include/asm/mmu_64.h b/arch/sparc/include/asm/mmu_64.h
index f7de0dbc38af..83b36a5371ff 100644
--- a/arch/sparc/include/asm/mmu_64.h
+++ b/arch/sparc/include/asm/mmu_64.h
@@ -52,7 +52,7 @@
 #define CTX_NR_MASK		TAG_CONTEXT_BITS
 #define CTX_HW_MASK		(CTX_NR_MASK | CTX_PGSZ_MASK)
 
-#define CTX_FIRST_VERSION	((_AC(1,UL) << CTX_VERSION_SHIFT) + _AC(1,UL))
+#define CTX_FIRST_VERSION	BIT(CTX_VERSION_SHIFT)
 #define CTX_VALID(__ctx)	\
 	 (!(((__ctx.sparc64_ctx_val) ^ tlb_context_cache) & CTX_VERSION_MASK))
 #define CTX_HWBITS(__ctx)	((__ctx.sparc64_ctx_val) & CTX_HW_MASK)
diff --git a/arch/sparc/include/asm/mmu_context_64.h b/arch/sparc/include/asm/mmu_context_64.h
index b84be675e507..349dd23e2876 100644
--- a/arch/sparc/include/asm/mmu_context_64.h
+++ b/arch/sparc/include/asm/mmu_context_64.h
@@ -17,13 +17,8 @@ extern spinlock_t ctx_alloc_lock;
 extern unsigned long tlb_context_cache;
 extern unsigned long mmu_context_bmap[];
 
+DECLARE_PER_CPU(struct mm_struct *, per_cpu_secondary_mm);
 void get_new_mmu_context(struct mm_struct *mm);
-#ifdef CONFIG_SMP
-void smp_new_mmu_context_version(void);
-#else
-#define smp_new_mmu_context_version() do { } while (0)
-#endif
-
 int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
 void destroy_context(struct mm_struct *mm);
 
@@ -74,8 +69,9 @@ void __flush_tlb_mm(unsigned long, unsigned long);
 static inline void switch_mm(struct mm_struct *old_mm, struct mm_struct *mm, struct task_struct *tsk)
 {
 	unsigned long ctx_valid, flags;
-	int cpu;
+	int cpu = smp_processor_id();
 
+	per_cpu(per_cpu_secondary_mm, cpu) = mm;
 	if (unlikely(mm == &init_mm))
 		return;
 
@@ -121,7 +117,6 @@ static inline void switch_mm(struct mm_struct *old_mm, struct mm_struct *mm, str
 	 * for the first time, we must flush that context out of the
 	 * local TLB.
 	 */
-	cpu = smp_processor_id();
 	if (!ctx_valid || !cpumask_test_cpu(cpu, mm_cpumask(mm))) {
 		cpumask_set_cpu(cpu, mm_cpumask(mm));
 		__flush_tlb_mm(CTX_HWBITS(mm->context),
@@ -131,26 +126,7 @@ static inline void switch_mm(struct mm_struct *old_mm, struct mm_struct *mm, str
 }
 
 #define deactivate_mm(tsk,mm)	do { } while (0)
-
-/* Activate a new MM instance for the current task. */
-static inline void activate_mm(struct mm_struct *active_mm, struct mm_struct *mm)
-{
-	unsigned long flags;
-	int cpu;
-
-	spin_lock_irqsave(&mm->context.lock, flags);
-	if (!CTX_VALID(mm->context))
-		get_new_mmu_context(mm);
-	cpu = smp_processor_id();
-	if (!cpumask_test_cpu(cpu, mm_cpumask(mm)))
-		cpumask_set_cpu(cpu, mm_cpumask(mm));
-
-	load_secondary_context(mm);
-	__flush_tlb_mm(CTX_HWBITS(mm->context), SECONDARY_CONTEXT);
-	tsb_context_switch(mm);
-	spin_unlock_irqrestore(&mm->context.lock, flags);
-}
-
+#define activate_mm(active_mm, mm) switch_mm(active_mm, mm, NULL)
 #endif /* !(__ASSEMBLY__) */
 
 #endif /* !(__SPARC64_MMU_CONTEXT_H) */
diff --git a/arch/sparc/include/asm/pil.h b/arch/sparc/include/asm/pil.h
index 266937030546..522b43db2ed3 100644
--- a/arch/sparc/include/asm/pil.h
+++ b/arch/sparc/include/asm/pil.h
@@ -20,7 +20,6 @@
 #define PIL_SMP_CALL_FUNC	1
 #define PIL_SMP_RECEIVE_SIGNAL	2
 #define PIL_SMP_CAPTURE		3
-#define PIL_SMP_CTX_NEW_VERSION	4
 #define PIL_DEVICE_IRQ		5
 #define PIL_SMP_CALL_FUNC_SNGL	6
 #define PIL_DEFERRED_PCR_WORK	7
diff --git a/arch/sparc/include/asm/vio.h b/arch/sparc/include/asm/vio.h
index 8174f6cdbbbb..9dca7a892978 100644
--- a/arch/sparc/include/asm/vio.h
+++ b/arch/sparc/include/asm/vio.h
@@ -327,6 +327,7 @@ struct vio_dev {
 	int			compat_len;
 
 	u64			dev_no;
+	u64			id;
 
 	unsigned long		channel_id;
 
diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c
index 34a7930b76ef..e1b1ce63a328 100644
--- a/arch/sparc/kernel/irq_64.c
+++ b/arch/sparc/kernel/irq_64.c
@@ -1034,17 +1034,26 @@ static void __init init_cpu_send_mondo_info(struct trap_per_cpu *tb)
 {
 #ifdef CONFIG_SMP
 	unsigned long page;
+	void *mondo, *p;
 
-	BUILD_BUG_ON((NR_CPUS * sizeof(u16)) > (PAGE_SIZE - 64));
+	BUILD_BUG_ON((NR_CPUS * sizeof(u16)) > PAGE_SIZE);
+
+	/* Make sure mondo block is 64byte aligned */
+	p = kzalloc(127, GFP_KERNEL);
+	if (!p) {
+		prom_printf("SUN4V: Error, cannot allocate mondo block.\n");
+		prom_halt();
+	}
+	mondo = (void *)(((unsigned long)p + 63) & ~0x3f);
+	tb->cpu_mondo_block_pa = __pa(mondo);
 
 	page = get_zeroed_page(GFP_KERNEL);
 	if (!page) {
-		prom_printf("SUN4V: Error, cannot allocate cpu mondo page.\n");
+		prom_printf("SUN4V: Error, cannot allocate cpu list page.\n");
 		prom_halt();
 	}
 
-	tb->cpu_mondo_block_pa = __pa(page);
-	tb->cpu_list_pa = __pa(page + 64);
+	tb->cpu_list_pa = __pa(page);
 #endif
 }
 
diff --git a/arch/sparc/kernel/kernel.h b/arch/sparc/kernel/kernel.h
index c9804551262c..6ae1e77be0bf 100644
--- a/arch/sparc/kernel/kernel.h
+++ b/arch/sparc/kernel/kernel.h
@@ -37,7 +37,6 @@ void handle_stdfmna(struct pt_regs *regs, unsigned long sfar, unsigned long sfsr
 /* smp_64.c */
 void __irq_entry smp_call_function_client(int irq, struct pt_regs *regs);
 void __irq_entry smp_call_function_single_client(int irq, struct pt_regs *regs);
-void __irq_entry smp_new_mmu_context_version_client(int irq, struct pt_regs *regs);
 void __irq_entry smp_penguin_jailcell(int irq, struct pt_regs *regs);
 void __irq_entry smp_receive_signal_client(int irq, struct pt_regs *regs);
 
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index 8182f7caf5b1..d5807d24b98f 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -963,37 +963,6 @@ void flush_dcache_page_all(struct mm_struct *mm, struct page *page)
 	preempt_enable();
 }
 
-void __irq_entry smp_new_mmu_context_version_client(int irq, struct pt_regs *regs)
-{
-	struct mm_struct *mm;
-	unsigned long flags;
-
-	clear_softint(1 << irq);
-
-	/* See if we need to allocate a new TLB context because
-	 * the version of the one we are using is now out of date.
-	 */
-	mm = current->active_mm;
-	if (unlikely(!mm || (mm == &init_mm)))
-		return;
-
-	spin_lock_irqsave(&mm->context.lock, flags);
-
-	if (unlikely(!CTX_VALID(mm->context)))
-		get_new_mmu_context(mm);
-
-	spin_unlock_irqrestore(&mm->context.lock, flags);
-
-	load_secondary_context(mm);
-	__flush_tlb_mm(CTX_HWBITS(mm->context),
-		       SECONDARY_CONTEXT);
-}
-
-void smp_new_mmu_context_version(void)
-{
-	smp_cross_call(&xcall_new_mmu_context_version, 0, 0, 0);
-}
-
 #ifdef CONFIG_KGDB
 void kgdb_roundup_cpus(unsigned long flags)
 {
diff --git a/arch/sparc/kernel/tsb.S b/arch/sparc/kernel/tsb.S
index d568c8207af7..395ec1800530 100644
--- a/arch/sparc/kernel/tsb.S
+++ b/arch/sparc/kernel/tsb.S
@@ -470,13 +470,16 @@ __tsb_context_switch:
 	.type	copy_tsb,#function
 copy_tsb:		/* %o0=old_tsb_base, %o1=old_tsb_size
 			 * %o2=new_tsb_base, %o3=new_tsb_size
+			 * %o4=page_size_shift
 			 */
 	sethi		%uhi(TSB_PASS_BITS), %g7
 	srlx		%o3, 4, %o3
-	add		%o0, %o1, %g1	/* end of old tsb */
+	add		%o0, %o1, %o1	/* end of old tsb */
 	sllx		%g7, 32, %g7
 	sub		%o3, 1, %o3	/* %o3 == new tsb hash mask */
 
+	mov		%o4, %g1	/* page_size_shift */
+
 661:	prefetcha	[%o0] ASI_N, #one_read
 	.section	.tsb_phys_patch, "ax"
 	.word		661b
@@ -501,9 +504,9 @@ copy_tsb:		/* %o0=old_tsb_base, %o1=old_tsb_size
 	/* This can definitely be computed faster... */
 	srlx		%o0, 4, %o5	/* Build index */
 	and		%o5, 511, %o5	/* Mask index */
-	sllx		%o5, PAGE_SHIFT, %o5 /* Put into vaddr position */
+	sllx		%o5, %g1, %o5	/* Put into vaddr position */
 	or		%o4, %o5, %o4	/* Full VADDR. */
-	srlx		%o4, PAGE_SHIFT, %o4 /* Shift down to create index */
+	srlx		%o4, %g1, %o4	/* Shift down to create index */
 	and		%o4, %o3, %o4	/* Mask with new_tsb_nents-1 */
 	sllx		%o4, 4, %o4	/* Shift back up into tsb ent offset */
 	TSB_STORE(%o2 + %o4, %g2)	/* Store TAG */
@@ -511,7 +514,7 @@ copy_tsb:		/* %o0=old_tsb_base, %o1=old_tsb_size
 	TSB_STORE(%o2 + %o4, %g3)	/* Store TTE */
 
 80:	add		%o0, 16, %o0
-	cmp		%o0, %g1
+	cmp		%o0, %o1
 	bne,pt		%xcc, 90b
 	 nop
 
diff --git a/arch/sparc/kernel/ttable_64.S b/arch/sparc/kernel/ttable_64.S
index c6dfdaa29e20..170ead662f2a 100644
--- a/arch/sparc/kernel/ttable_64.S
+++ b/arch/sparc/kernel/ttable_64.S
@@ -50,7 +50,7 @@ tl0_resv03e:	BTRAP(0x3e) BTRAP(0x3f) BTRAP(0x40)
 tl0_irq1:	TRAP_IRQ(smp_call_function_client, 1)
 tl0_irq2:	TRAP_IRQ(smp_receive_signal_client, 2)
 tl0_irq3:	TRAP_IRQ(smp_penguin_jailcell, 3)
-tl0_irq4:	TRAP_IRQ(smp_new_mmu_context_version_client, 4)
+tl0_irq4:       BTRAP(0x44)
 #else
 tl0_irq1:	BTRAP(0x41)
 tl0_irq2:	BTRAP(0x42)
diff --git a/arch/sparc/kernel/vio.c b/arch/sparc/kernel/vio.c
index f6bb857254fc..075d38980dee 100644
--- a/arch/sparc/kernel/vio.c
+++ b/arch/sparc/kernel/vio.c
@@ -302,13 +302,16 @@ static struct vio_dev *vio_create_one(struct mdesc_handle *hp, u64 mp,
 	if (!id) {
 		dev_set_name(&vdev->dev, "%s", bus_id_name);
 		vdev->dev_no = ~(u64)0;
+		vdev->id = ~(u64)0;
 	} else if (!cfg_handle) {
 		dev_set_name(&vdev->dev, "%s-%llu", bus_id_name, *id);
 		vdev->dev_no = *id;
+		vdev->id = ~(u64)0;
 	} else {
 		dev_set_name(&vdev->dev, "%s-%llu-%llu", bus_id_name,
 			     *cfg_handle, *id);
 		vdev->dev_no = *cfg_handle;
+		vdev->id = *id;
 	}
 
 	vdev->dev.parent = parent;
@@ -351,27 +354,84 @@ static void vio_add(struct mdesc_handle *hp, u64 node)
 	(void) vio_create_one(hp, node, &root_vdev->dev);
 }
 
+struct vio_md_node_query {
+	const char *type;
+	u64 dev_no;
+	u64 id;
+};
+
 static int vio_md_node_match(struct device *dev, void *arg)
 {
+	struct vio_md_node_query *query = (struct vio_md_node_query *) arg;
 	struct vio_dev *vdev = to_vio_dev(dev);
 
-	if (vdev->mp == (u64) arg)
-		return 1;
+	if (vdev->dev_no != query->dev_no)
+		return 0;
+	if (vdev->id != query->id)
+		return 0;
+	if (strcmp(vdev->type, query->type))
+		return 0;
 
-	return 0;
+	return 1;
 }
 
 static void vio_remove(struct mdesc_handle *hp, u64 node)
 {
+	const char *type;
+	const u64 *id, *cfg_handle;
+	u64 a;
+	struct vio_md_node_query query;
 	struct device *dev;
 
-	dev = device_find_child(&root_vdev->dev, (void *) node,
+	type = mdesc_get_property(hp, node, "device-type", NULL);
+	if (!type) {
+		type = mdesc_get_property(hp, node, "name", NULL);
+		if (!type)
+			type = mdesc_node_name(hp, node);
+	}
+
+	query.type = type;
+
+	id = mdesc_get_property(hp, node, "id", NULL);
+	cfg_handle = NULL;
+	mdesc_for_each_arc(a, hp, node, MDESC_ARC_TYPE_BACK) {
+		u64 target;
+
+		target = mdesc_arc_target(hp, a);
+		cfg_handle = mdesc_get_property(hp, target,
+						"cfg-handle", NULL);
+		if (cfg_handle)
+			break;
+	}
+
+	if (!id) {
+		query.dev_no = ~(u64)0;
+		query.id = ~(u64)0;
+	} else if (!cfg_handle) {
+		query.dev_no = *id;
+		query.id = ~(u64)0;
+	} else {
+		query.dev_no = *cfg_handle;
+		query.id = *id;
+	}
+
+	dev = device_find_child(&root_vdev->dev, &query,
 				vio_md_node_match);
 	if (dev) {
 		printk(KERN_INFO "VIO: Removing device %s\n", dev_name(dev));
 
 		device_unregister(dev);
 		put_device(dev);
+	} else {
+		if (!id)
+			printk(KERN_ERR "VIO: Removed unknown %s node.\n",
+			       type);
+		else if (!cfg_handle)
+			printk(KERN_ERR "VIO: Removed unknown %s node %llu.\n",
+			       type, *id);
+		else
+			printk(KERN_ERR "VIO: Removed unknown %s node %llu-%llu.\n",
+			       type, *cfg_handle, *id);
 	}
 }
 
diff --git a/arch/sparc/lib/Makefile b/arch/sparc/lib/Makefile
index 69912d2f8b54..07c03e72d812 100644
--- a/arch/sparc/lib/Makefile
+++ b/arch/sparc/lib/Makefile
@@ -15,6 +15,7 @@ lib-$(CONFIG_SPARC32) += copy_user.o locks.o
 lib-$(CONFIG_SPARC64) += atomic_64.o
 lib-$(CONFIG_SPARC32) += lshrdi3.o ashldi3.o
 lib-$(CONFIG_SPARC32) += muldi3.o bitext.o cmpdi2.o
+lib-$(CONFIG_SPARC64) += multi3.o
 
 lib-$(CONFIG_SPARC64) += copy_page.o clear_page.o bzero.o
 lib-$(CONFIG_SPARC64) += csum_copy.o csum_copy_from_user.o csum_copy_to_user.o
diff --git a/arch/sparc/lib/multi3.S b/arch/sparc/lib/multi3.S
new file mode 100644
index 000000000000..d6b6c97fe3c7
--- /dev/null
+++ b/arch/sparc/lib/multi3.S
@@ -0,0 +1,35 @@
+#include <linux/linkage.h>
+#include <asm/export.h>
+
+	.text
+	.align	4
+ENTRY(__multi3) /* %o0 = u, %o1 = v */
+	mov	%o1, %g1
+	srl	%o3, 0, %g4
+	mulx	%g4, %g1, %o1
+	srlx	%g1, 0x20, %g3
+	mulx	%g3, %g4, %g5
+	sllx	%g5, 0x20, %o5
+	srl	%g1, 0, %g4
+	sub	%o1, %o5, %o5
+	srlx	%o5, 0x20, %o5
+	addcc	%g5, %o5, %g5
+	srlx	%o3, 0x20, %o5
+	mulx	%g4, %o5, %g4
+	mulx	%g3, %o5, %o5
+	sethi	%hi(0x80000000), %g3
+	addcc	%g5, %g4, %g5
+	srlx	%g5, 0x20, %g5
+	add	%g3, %g3, %g3
+	movcc	%xcc, %g0, %g3
+	addcc	%o5, %g5, %o5
+	sllx	%g4, 0x20, %g4
+	add	%o1, %g4, %o1
+	add	%o5, %g3, %g2
+	mulx	%g1, %o2, %g1
+	add	%g1, %g2, %g1
+	mulx	%o0, %o3, %o0
+	retl
+	 add	%g1, %o0, %o0
+ENDPROC(__multi3)
+EXPORT_SYMBOL(__multi3)
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index bd7e2aa86c45..57154c638e71 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -658,10 +658,58 @@ EXPORT_SYMBOL(__flush_dcache_range);
 
 /* get_new_mmu_context() uses "cache + 1".  */
 DEFINE_SPINLOCK(ctx_alloc_lock);
-unsigned long tlb_context_cache = CTX_FIRST_VERSION - 1;
+unsigned long tlb_context_cache = CTX_FIRST_VERSION;
 #define MAX_CTX_NR	(1UL << CTX_NR_BITS)
 #define CTX_BMAP_SLOTS	BITS_TO_LONGS(MAX_CTX_NR)
 DECLARE_BITMAP(mmu_context_bmap, MAX_CTX_NR);
+DEFINE_PER_CPU(struct mm_struct *, per_cpu_secondary_mm) = {0};
+
+static void mmu_context_wrap(void)
+{
+	unsigned long old_ver = tlb_context_cache & CTX_VERSION_MASK;
+	unsigned long new_ver, new_ctx, old_ctx;
+	struct mm_struct *mm;
+	int cpu;
+
+	bitmap_zero(mmu_context_bmap, 1 << CTX_NR_BITS);
+
+	/* Reserve kernel context */
+	set_bit(0, mmu_context_bmap);
+
+	new_ver = (tlb_context_cache & CTX_VERSION_MASK) + CTX_FIRST_VERSION;
+	if (unlikely(new_ver == 0))
+		new_ver = CTX_FIRST_VERSION;
+	tlb_context_cache = new_ver;
+
+	/*
+	 * Make sure that any new mm that are added into per_cpu_secondary_mm,
+	 * are going to go through get_new_mmu_context() path.
+	 */
+	mb();
+
+	/*
+	 * Updated versions to current on those CPUs that had valid secondary
+	 * contexts
+	 */
+	for_each_online_cpu(cpu) {
+		/*
+		 * If a new mm is stored after we took this mm from the array,
+		 * it will go into get_new_mmu_context() path, because we
+		 * already bumped the version in tlb_context_cache.
+		 */
+		mm = per_cpu(per_cpu_secondary_mm, cpu);
+
+		if (unlikely(!mm || mm == &init_mm))
+			continue;
+
+		old_ctx = mm->context.sparc64_ctx_val;
+		if (likely((old_ctx & CTX_VERSION_MASK) == old_ver)) {
+			new_ctx = (old_ctx & ~CTX_VERSION_MASK) | new_ver;
+			set_bit(new_ctx & CTX_NR_MASK, mmu_context_bmap);
+			mm->context.sparc64_ctx_val = new_ctx;
+		}
+	}
+}
 
 /* Caller does TLB context flushing on local CPU if necessary.
  * The caller also ensures that CTX_VALID(mm->context) is false.
@@ -677,48 +725,30 @@ void get_new_mmu_context(struct mm_struct *mm)
 {
 	unsigned long ctx, new_ctx;
 	unsigned long orig_pgsz_bits;
-	int new_version;
 
 	spin_lock(&ctx_alloc_lock);
+retry:
+	/* wrap might have happened, test again if our context became valid */
+	if (unlikely(CTX_VALID(mm->context)))
+		goto out;
 	orig_pgsz_bits = (mm->context.sparc64_ctx_val & CTX_PGSZ_MASK);
 	ctx = (tlb_context_cache + 1) & CTX_NR_MASK;
 	new_ctx = find_next_zero_bit(mmu_context_bmap, 1 << CTX_NR_BITS, ctx);
-	new_version = 0;
 	if (new_ctx >= (1 << CTX_NR_BITS)) {
 		new_ctx = find_next_zero_bit(mmu_context_bmap, ctx, 1);
 		if (new_ctx >= ctx) {
-			int i;
-			new_ctx = (tlb_context_cache & CTX_VERSION_MASK) +
-				CTX_FIRST_VERSION;
-			if (new_ctx == 1)
-				new_ctx = CTX_FIRST_VERSION;
-
-			/* Don't call memset, for 16 entries that's just
-			 * plain silly...
-			 */
-			mmu_context_bmap[0] = 3;
-			mmu_context_bmap[1] = 0;
-			mmu_context_bmap[2] = 0;
-			mmu_context_bmap[3] = 0;
-			for (i = 4; i < CTX_BMAP_SLOTS; i += 4) {
-				mmu_context_bmap[i + 0] = 0;
-				mmu_context_bmap[i + 1] = 0;
-				mmu_context_bmap[i + 2] = 0;
-				mmu_context_bmap[i + 3] = 0;
-			}
-			new_version = 1;
-			goto out;
+			mmu_context_wrap();
+			goto retry;
 		}
 	}
+	if (mm->context.sparc64_ctx_val)
+		cpumask_clear(mm_cpumask(mm));
 	mmu_context_bmap[new_ctx>>6] |= (1UL << (new_ctx & 63));
 	new_ctx |= (tlb_context_cache & CTX_VERSION_MASK);
-out:
 	tlb_context_cache = new_ctx;
 	mm->context.sparc64_ctx_val = new_ctx | orig_pgsz_bits;
+out:
 	spin_unlock(&ctx_alloc_lock);
-
-	if (unlikely(new_version))
-		smp_new_mmu_context_version();
 }
 
 static int numa_enabled = 1;
diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c
index e20fbbafb0b0..84cd593117a6 100644
--- a/arch/sparc/mm/tsb.c
+++ b/arch/sparc/mm/tsb.c
@@ -451,7 +451,8 @@ void tsb_grow(struct mm_struct *mm, unsigned long tsb_index, unsigned long rss)
 		extern void copy_tsb(unsigned long old_tsb_base,
 				     unsigned long old_tsb_size,
 				     unsigned long new_tsb_base,
-				     unsigned long new_tsb_size);
+				     unsigned long new_tsb_size,
+				     unsigned long page_size_shift);
 		unsigned long old_tsb_base = (unsigned long) old_tsb;
 		unsigned long new_tsb_base = (unsigned long) new_tsb;
 
@@ -459,7 +460,9 @@ void tsb_grow(struct mm_struct *mm, unsigned long tsb_index, unsigned long rss)
 			old_tsb_base = __pa(old_tsb_base);
 			new_tsb_base = __pa(new_tsb_base);
 		}
-		copy_tsb(old_tsb_base, old_size, new_tsb_base, new_size);
+		copy_tsb(old_tsb_base, old_size, new_tsb_base, new_size,
+			tsb_index == MM_TSB_BASE ?
+			PAGE_SHIFT : REAL_HPAGE_SHIFT);
 	}
 
 	mm->context.tsb_block[tsb_index].tsb = new_tsb;
diff --git a/arch/sparc/mm/ultra.S b/arch/sparc/mm/ultra.S
index 5d2fd6cd3189..fcf4d27a38fb 100644
--- a/arch/sparc/mm/ultra.S
+++ b/arch/sparc/mm/ultra.S
@@ -971,11 +971,6 @@ xcall_capture:
 	wr		%g0, (1 << PIL_SMP_CAPTURE), %set_softint
 	retry
 
-	.globl		xcall_new_mmu_context_version
-xcall_new_mmu_context_version:
-	wr		%g0, (1 << PIL_SMP_CTX_NEW_VERSION), %set_softint
-	retry
-
 #ifdef CONFIG_KGDB
 	.globl		xcall_kgdb_capture
 xcall_kgdb_capture:
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index edbbfc854e39..9cf697ceedbf 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -162,8 +162,8 @@ void kvm_async_pf_task_wait(u32 token)
 			 */
 			rcu_irq_exit();
 			native_safe_halt();
-			rcu_irq_enter();
 			local_irq_disable();
+			rcu_irq_enter();
 		}
 	}
 	if (!n.halted)
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 967e459ff1e6..649d8f2c1e40 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -765,18 +765,20 @@ int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid,
 static int move_to_next_stateful_cpuid_entry(struct kvm_vcpu *vcpu, int i)
 {
 	struct kvm_cpuid_entry2 *e = &vcpu->arch.cpuid_entries[i];
-	int j, nent = vcpu->arch.cpuid_nent;
+	struct kvm_cpuid_entry2 *ej;
+	int j = i;
+	int nent = vcpu->arch.cpuid_nent;
 
 	e->flags &= ~KVM_CPUID_FLAG_STATE_READ_NEXT;
 	/* when no next entry is found, the current entry[i] is reselected */
-	for (j = i + 1; ; j = (j + 1) % nent) {
-		struct kvm_cpuid_entry2 *ej = &vcpu->arch.cpuid_entries[j];
-		if (ej->function == e->function) {
-			ej->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT;
-			return j;
-		}
-	}
-	return 0; /* silence gcc, even though control never reaches here */
+	do {
+		j = (j + 1) % nent;
+		ej = &vcpu->arch.cpuid_entries[j];
+	} while (ej->function != e->function);
+
+	ej->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT;
+
+	return j;
 }
 
 /* find an entry with matching function, matching index (if needed), and that
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index d9c7e986b4e4..5f2412704b81 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3489,12 +3489,15 @@ static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn)
 	return kvm_setup_async_pf(vcpu, gva, kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch);
 }
 
-static bool can_do_async_pf(struct kvm_vcpu *vcpu)
+bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu)
 {
 	if (unlikely(!lapic_in_kernel(vcpu) ||
 		     kvm_event_needs_reinjection(vcpu)))
 		return false;
 
+	if (is_guest_mode(vcpu))
+		return false;
+
 	return kvm_x86_ops->interrupt_allowed(vcpu);
 }
 
@@ -3510,7 +3513,7 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
 	if (!async)
 		return false; /* *pfn has correct page already */
 
-	if (!prefault && can_do_async_pf(vcpu)) {
+	if (!prefault && kvm_can_do_async_pf(vcpu)) {
 		trace_kvm_try_async_get_page(gva, gfn);
 		if (kvm_find_async_pf_gfn(vcpu, gfn)) {
 			trace_kvm_async_pf_doublefault(gva, gfn);
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index ddc56e91f2e4..c92834c55c59 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -75,6 +75,7 @@ enum {
 int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, bool direct);
 void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu);
 void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly);
+bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu);
 
 static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm)
 {
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 81bba3c2137d..62cde4f67c72 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -8444,8 +8444,7 @@ bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu)
 	if (!(vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED))
 		return true;
 	else
-		return !kvm_event_needs_reinjection(vcpu) &&
-			kvm_x86_ops->interrupt_allowed(vcpu);
+		return kvm_can_do_async_pf(vcpu);
 }
 
 void kvm_arch_start_assignment(struct kvm *kvm)
diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c
index cdfe8c628959..393a0c0288d1 100644
--- a/arch/x86/platform/efi/quirks.c
+++ b/arch/x86/platform/efi/quirks.c
@@ -358,6 +358,9 @@ void __init efi_free_boot_services(void)
 		free_bootmem_late(start, size);
 	}
 
+	if (!num_entries)
+		return;
+
 	new_size = efi.memmap.desc_size * num_entries;
 	new_phys = efi_memmap_alloc(num_entries);
 	if (!new_phys) {
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 3ab6807773ee..c7c3d4e6bc27 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -36,9 +36,13 @@ static const u64 cfq_target_latency = (u64)NSEC_PER_SEC * 3/10; /* 300 ms */
 static const int cfq_hist_divisor = 4;
 
 /*
- * offset from end of service tree
+ * offset from end of queue service tree for idle class
  */
 #define CFQ_IDLE_DELAY		(NSEC_PER_SEC / 5)
+/* offset from end of group service tree under time slice mode */
+#define CFQ_SLICE_MODE_GROUP_DELAY (NSEC_PER_SEC / 5)
+/* offset from end of group service under IOPS mode */
+#define CFQ_IOPS_MODE_GROUP_DELAY (HZ / 5)
 
 /*
  * below this threshold, we consider thinktime immediate
@@ -1370,6 +1374,14 @@ cfq_group_service_tree_add(struct cfq_rb_root *st, struct cfq_group *cfqg)
 	cfqg->vfraction = max_t(unsigned, vfr, 1);
 }
 
+static inline u64 cfq_get_cfqg_vdisktime_delay(struct cfq_data *cfqd)
+{
+	if (!iops_mode(cfqd))
+		return CFQ_SLICE_MODE_GROUP_DELAY;
+	else
+		return CFQ_IOPS_MODE_GROUP_DELAY;
+}
+
 static void
 cfq_group_notify_queue_add(struct cfq_data *cfqd, struct cfq_group *cfqg)
 {
@@ -1389,7 +1401,8 @@ cfq_group_notify_queue_add(struct cfq_data *cfqd, struct cfq_group *cfqg)
 	n = rb_last(&st->rb);
 	if (n) {
 		__cfqg = rb_entry_cfqg(n);
-		cfqg->vdisktime = __cfqg->vdisktime + CFQ_IDLE_DELAY;
+		cfqg->vdisktime = __cfqg->vdisktime +
+			cfq_get_cfqg_vdisktime_delay(cfqd);
 	} else
 		cfqg->vdisktime = st->min_vdisktime;
 	cfq_group_service_tree_add(st, cfqg);
diff --git a/crypto/asymmetric_keys/public_key.c b/crypto/asymmetric_keys/public_key.c
index fd76b5fc3b3a..4955eb66e361 100644
--- a/crypto/asymmetric_keys/public_key.c
+++ b/crypto/asymmetric_keys/public_key.c
@@ -140,7 +140,7 @@ int public_key_verify_signature(const struct public_key *pkey,
 	 * signature and returns that to us.
 	 */
 	ret = crypto_akcipher_verify(req);
-	if (ret == -EINPROGRESS) {
+	if ((ret == -EINPROGRESS) || (ret == -EBUSY)) {
 		wait_for_completion(&compl.completion);
 		ret = compl.err;
 	}
diff --git a/crypto/drbg.c b/crypto/drbg.c
index 053035b5c8f8..123d211efa12 100644
--- a/crypto/drbg.c
+++ b/crypto/drbg.c
@@ -1768,9 +1768,8 @@ static int drbg_kcapi_sym_ctr(struct drbg_state *drbg,
 			break;
 		case -EINPROGRESS:
 		case -EBUSY:
-			ret = wait_for_completion_interruptible(
-				&drbg->ctr_completion);
-			if (!ret && !drbg->ctr_async_err) {
+			wait_for_completion(&drbg->ctr_completion);
+			if (!drbg->ctr_async_err) {
 				reinit_completion(&drbg->ctr_completion);
 				break;
 			}
diff --git a/crypto/gcm.c b/crypto/gcm.c
index f624ac98c94e..dd33fbd2d868 100644
--- a/crypto/gcm.c
+++ b/crypto/gcm.c
@@ -152,10 +152,8 @@ static int crypto_gcm_setkey(struct crypto_aead *aead, const u8 *key,
 
 	err = crypto_skcipher_encrypt(&data->req);
 	if (err == -EINPROGRESS || err == -EBUSY) {
-		err = wait_for_completion_interruptible(
-			&data->result.completion);
-		if (!err)
-			err = data->result.err;
+		wait_for_completion(&data->result.completion);
+		err = data->result.err;
 	}
 
 	if (err)
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index 74f4c662f776..c94038206c3a 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -1362,6 +1362,40 @@ static inline void ahci_gtf_filter_workaround(struct ata_host *host)
 {}
 #endif
 
+/*
+ * On the Acer Aspire Switch Alpha 12, sometimes all SATA ports are detected
+ * as DUMMY, or detected but eventually get a "link down" and never get up
+ * again. When this happens, CAP.NP may hold a value of 0x00 or 0x01, and the
+ * port_map may hold a value of 0x00.
+ *
+ * Overriding CAP.NP to 0x02 and the port_map to 0x7 will reveal all 3 ports
+ * and can significantly reduce the occurrence of the problem.
+ *
+ * https://bugzilla.kernel.org/show_bug.cgi?id=189471
+ */
+static void acer_sa5_271_workaround(struct ahci_host_priv *hpriv,
+				    struct pci_dev *pdev)
+{
+	static const struct dmi_system_id sysids[] = {
+		{
+			.ident = "Acer Switch Alpha 12",
+			.matches = {
+				DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+				DMI_MATCH(DMI_PRODUCT_NAME, "Switch SA5-271")
+			},
+		},
+		{ }
+	};
+
+	if (dmi_check_system(sysids)) {
+		dev_info(&pdev->dev, "enabling Acer Switch Alpha 12 workaround\n");
+		if ((hpriv->saved_cap & 0xC734FF00) == 0xC734FF00) {
+			hpriv->port_map = 0x7;
+			hpriv->cap = 0xC734FF02;
+		}
+	}
+}
+
 #ifdef CONFIG_ARM64
 /*
  * Due to ERRATA#22536, ThunderX needs to handle HOST_IRQ_STAT differently.
@@ -1597,6 +1631,10 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 			 "online status unreliable, applying workaround\n");
 	}
 
+
+	/* Acer SA5-271 workaround modifies private_data */
+	acer_sa5_271_workaround(hpriv, pdev);
+
 	/* CAP.NP sometimes indicate the index of the last enabled
 	 * port, at other times, that of the last possible port, so
 	 * determining the maximum port number requires looking at
diff --git a/drivers/char/mem.c b/drivers/char/mem.c
index 6e0cbe092220..593a8818aca9 100644
--- a/drivers/char/mem.c
+++ b/drivers/char/mem.c
@@ -343,7 +343,7 @@ static int mmap_mem(struct file *file, struct vm_area_struct *vma)
 	phys_addr_t offset = (phys_addr_t)vma->vm_pgoff << PAGE_SHIFT;
 
 	/* It's illegal to wrap around the end of the physical address space. */
-	if (offset + (phys_addr_t)size < offset)
+	if (offset + (phys_addr_t)size - 1 < offset)
 		return -EINVAL;
 
 	if (!valid_mmap_phys_addr_range(vma->vm_pgoff, size))
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 6153b66139d5..286d4d61bd0b 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -2474,6 +2474,7 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data)
 	if (!(cpufreq_driver->flags & CPUFREQ_STICKY) &&
 	    list_empty(&cpufreq_policy_list)) {
 		/* if all ->init() calls failed, unregister */
+		ret = -ENODEV;
 		pr_debug("%s: No CPU initialized for driver %s\n", __func__,
 			 driver_data->name);
 		goto err_if_unreg;
diff --git a/drivers/dma/ep93xx_dma.c b/drivers/dma/ep93xx_dma.c
index d37e8dda8079..ec240592f5c8 100644
--- a/drivers/dma/ep93xx_dma.c
+++ b/drivers/dma/ep93xx_dma.c
@@ -201,6 +201,7 @@ struct ep93xx_dma_engine {
 	struct dma_device	dma_dev;
 	bool			m2m;
 	int			(*hw_setup)(struct ep93xx_dma_chan *);
+	void			(*hw_synchronize)(struct ep93xx_dma_chan *);
 	void			(*hw_shutdown)(struct ep93xx_dma_chan *);
 	void			(*hw_submit)(struct ep93xx_dma_chan *);
 	int			(*hw_interrupt)(struct ep93xx_dma_chan *);
@@ -323,6 +324,8 @@ static int m2p_hw_setup(struct ep93xx_dma_chan *edmac)
 		| M2P_CONTROL_ENABLE;
 	m2p_set_control(edmac, control);
 
+	edmac->buffer = 0;
+
 	return 0;
 }
 
@@ -331,21 +334,27 @@ static inline u32 m2p_channel_state(struct ep93xx_dma_chan *edmac)
 	return (readl(edmac->regs + M2P_STATUS) >> 4) & 0x3;
 }
 
-static void m2p_hw_shutdown(struct ep93xx_dma_chan *edmac)
+static void m2p_hw_synchronize(struct ep93xx_dma_chan *edmac)
 {
+	unsigned long flags;
 	u32 control;
 
+	spin_lock_irqsave(&edmac->lock, flags);
 	control = readl(edmac->regs + M2P_CONTROL);
 	control &= ~(M2P_CONTROL_STALLINT | M2P_CONTROL_NFBINT);
 	m2p_set_control(edmac, control);
+	spin_unlock_irqrestore(&edmac->lock, flags);
 
 	while (m2p_channel_state(edmac) >= M2P_STATE_ON)
-		cpu_relax();
+		schedule();
+}
 
+static void m2p_hw_shutdown(struct ep93xx_dma_chan *edmac)
+{
 	m2p_set_control(edmac, 0);
 
-	while (m2p_channel_state(edmac) == M2P_STATE_STALL)
-		cpu_relax();
+	while (m2p_channel_state(edmac) != M2P_STATE_IDLE)
+		dev_warn(chan2dev(edmac), "M2P: Not yet IDLE\n");
 }
 
 static void m2p_fill_desc(struct ep93xx_dma_chan *edmac)
@@ -1161,6 +1170,26 @@ ep93xx_dma_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t dma_addr,
 }
 
 /**
+ * ep93xx_dma_synchronize - Synchronizes the termination of transfers to the
+ * current context.
+ * @chan: channel
+ *
+ * Synchronizes the DMA channel termination to the current context. When this
+ * function returns it is guaranteed that all transfers for previously issued
+ * descriptors have stopped and and it is safe to free the memory associated
+ * with them. Furthermore it is guaranteed that all complete callback functions
+ * for a previously submitted descriptor have finished running and it is safe to
+ * free resources accessed from within the complete callbacks.
+ */
+static void ep93xx_dma_synchronize(struct dma_chan *chan)
+{
+	struct ep93xx_dma_chan *edmac = to_ep93xx_dma_chan(chan);
+
+	if (edmac->edma->hw_synchronize)
+		edmac->edma->hw_synchronize(edmac);
+}
+
+/**
  * ep93xx_dma_terminate_all - terminate all transactions
  * @chan: channel
  *
@@ -1323,6 +1352,7 @@ static int __init ep93xx_dma_probe(struct platform_device *pdev)
 	dma_dev->device_prep_slave_sg = ep93xx_dma_prep_slave_sg;
 	dma_dev->device_prep_dma_cyclic = ep93xx_dma_prep_dma_cyclic;
 	dma_dev->device_config = ep93xx_dma_slave_config;
+	dma_dev->device_synchronize = ep93xx_dma_synchronize;
 	dma_dev->device_terminate_all = ep93xx_dma_terminate_all;
 	dma_dev->device_issue_pending = ep93xx_dma_issue_pending;
 	dma_dev->device_tx_status = ep93xx_dma_tx_status;
@@ -1340,6 +1370,7 @@ static int __init ep93xx_dma_probe(struct platform_device *pdev)
 	} else {
 		dma_cap_set(DMA_PRIVATE, dma_dev->cap_mask);
 
+		edma->hw_synchronize = m2p_hw_synchronize;
 		edma->hw_setup = m2p_hw_setup;
 		edma->hw_shutdown = m2p_hw_shutdown;
 		edma->hw_submit = m2p_hw_submit;
diff --git a/drivers/dma/mv_xor_v2.c b/drivers/dma/mv_xor_v2.c
index a28a01fcba67..f3e211f8f6c5 100644
--- a/drivers/dma/mv_xor_v2.c
+++ b/drivers/dma/mv_xor_v2.c
@@ -161,6 +161,7 @@ struct mv_xor_v2_device {
 	struct mv_xor_v2_sw_desc *sw_desq;
 	int desc_size;
 	unsigned int npendings;
+	unsigned int hw_queue_idx;
 };
 
 /**
@@ -214,18 +215,6 @@ static void mv_xor_v2_set_data_buffers(struct mv_xor_v2_device *xor_dev,
 }
 
 /*
- * Return the next available index in the DESQ.
- */
-static int mv_xor_v2_get_desq_write_ptr(struct mv_xor_v2_device *xor_dev)
-{
-	/* read the index for the next available descriptor in the DESQ */
-	u32 reg = readl(xor_dev->dma_base + MV_XOR_V2_DMA_DESQ_ALLOC_OFF);
-
-	return ((reg >> MV_XOR_V2_DMA_DESQ_ALLOC_WRPTR_SHIFT)
-		& MV_XOR_V2_DMA_DESQ_ALLOC_WRPTR_MASK);
-}
-
-/*
  * notify the engine of new descriptors, and update the available index.
  */
 static void mv_xor_v2_add_desc_to_desq(struct mv_xor_v2_device *xor_dev,
@@ -257,22 +246,6 @@ static int mv_xor_v2_set_desc_size(struct mv_xor_v2_device *xor_dev)
 	return MV_XOR_V2_EXT_DESC_SIZE;
 }
 
-/*
- * Set the IMSG threshold
- */
-static inline
-void mv_xor_v2_set_imsg_thrd(struct mv_xor_v2_device *xor_dev, int thrd_val)
-{
-	u32 reg;
-
-	reg = readl(xor_dev->dma_base + MV_XOR_V2_DMA_IMSG_THRD_OFF);
-
-	reg &= (~MV_XOR_V2_DMA_IMSG_THRD_MASK << MV_XOR_V2_DMA_IMSG_THRD_SHIFT);
-	reg |= (thrd_val << MV_XOR_V2_DMA_IMSG_THRD_SHIFT);
-
-	writel(reg, xor_dev->dma_base + MV_XOR_V2_DMA_IMSG_THRD_OFF);
-}
-
 static irqreturn_t mv_xor_v2_interrupt_handler(int irq, void *data)
 {
 	struct mv_xor_v2_device *xor_dev = data;
@@ -288,12 +261,6 @@ static irqreturn_t mv_xor_v2_interrupt_handler(int irq, void *data)
 	if (!ndescs)
 		return IRQ_NONE;
 
-	/*
-	 * Update IMSG threshold, to disable new IMSG interrupts until
-	 * end of the tasklet
-	 */
-	mv_xor_v2_set_imsg_thrd(xor_dev, MV_XOR_V2_DESC_NUM);
-
 	/* schedule a tasklet to handle descriptors callbacks */
 	tasklet_schedule(&xor_dev->irq_tasklet);
 
@@ -306,7 +273,6 @@ static irqreturn_t mv_xor_v2_interrupt_handler(int irq, void *data)
 static dma_cookie_t
 mv_xor_v2_tx_submit(struct dma_async_tx_descriptor *tx)
 {
-	int desq_ptr;
 	void *dest_hw_desc;
 	dma_cookie_t cookie;
 	struct mv_xor_v2_sw_desc *sw_desc =
@@ -322,15 +288,15 @@ mv_xor_v2_tx_submit(struct dma_async_tx_descriptor *tx)
 	spin_lock_bh(&xor_dev->lock);
 	cookie = dma_cookie_assign(tx);
 
-	/* get the next available slot in the DESQ */
-	desq_ptr = mv_xor_v2_get_desq_write_ptr(xor_dev);
-
 	/* copy the HW descriptor from the SW descriptor to the DESQ */
-	dest_hw_desc = xor_dev->hw_desq_virt + desq_ptr;
+	dest_hw_desc = xor_dev->hw_desq_virt + xor_dev->hw_queue_idx;
 
 	memcpy(dest_hw_desc, &sw_desc->hw_desc, xor_dev->desc_size);
 
 	xor_dev->npendings++;
+	xor_dev->hw_queue_idx++;
+	if (xor_dev->hw_queue_idx >= MV_XOR_V2_DESC_NUM)
+		xor_dev->hw_queue_idx = 0;
 
 	spin_unlock_bh(&xor_dev->lock);
 
@@ -344,6 +310,7 @@ static struct mv_xor_v2_sw_desc	*
 mv_xor_v2_prep_sw_desc(struct mv_xor_v2_device *xor_dev)
 {
 	struct mv_xor_v2_sw_desc *sw_desc;
+	bool found = false;
 
 	/* Lock the channel */
 	spin_lock_bh(&xor_dev->lock);
@@ -355,19 +322,23 @@ mv_xor_v2_prep_sw_desc(struct mv_xor_v2_device *xor_dev)
 		return NULL;
 	}
 
-	/* get a free SW descriptor from the SW DESQ */
-	sw_desc = list_first_entry(&xor_dev->free_sw_desc,
-				   struct mv_xor_v2_sw_desc, free_list);
+	list_for_each_entry(sw_desc, &xor_dev->free_sw_desc, free_list) {
+		if (async_tx_test_ack(&sw_desc->async_tx)) {
+			found = true;
+			break;
+		}
+	}
+
+	if (!found) {
+		spin_unlock_bh(&xor_dev->lock);
+		return NULL;
+	}
+
 	list_del(&sw_desc->free_list);
 
 	/* Release the channel */
 	spin_unlock_bh(&xor_dev->lock);
 
-	/* set the async tx descriptor */
-	dma_async_tx_descriptor_init(&sw_desc->async_tx, &xor_dev->dmachan);
-	sw_desc->async_tx.tx_submit = mv_xor_v2_tx_submit;
-	async_tx_ack(&sw_desc->async_tx);
-
 	return sw_desc;
 }
 
@@ -389,6 +360,8 @@ mv_xor_v2_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest,
 		__func__, len, &src, &dest, flags);
 
 	sw_desc = mv_xor_v2_prep_sw_desc(xor_dev);
+	if (!sw_desc)
+		return NULL;
 
 	sw_desc->async_tx.flags = flags;
 
@@ -443,6 +416,8 @@ mv_xor_v2_prep_dma_xor(struct dma_chan *chan, dma_addr_t dest, dma_addr_t *src,
 		__func__, src_cnt, len, &dest, flags);
 
 	sw_desc = mv_xor_v2_prep_sw_desc(xor_dev);
+	if (!sw_desc)
+		return NULL;
 
 	sw_desc->async_tx.flags = flags;
 
@@ -491,6 +466,8 @@ mv_xor_v2_prep_dma_interrupt(struct dma_chan *chan, unsigned long flags)
 		container_of(chan, struct mv_xor_v2_device, dmachan);
 
 	sw_desc = mv_xor_v2_prep_sw_desc(xor_dev);
+	if (!sw_desc)
+		return NULL;
 
 	/* set the HW descriptor */
 	hw_descriptor = &sw_desc->hw_desc;
@@ -554,7 +531,6 @@ static void mv_xor_v2_tasklet(unsigned long data)
 {
 	struct mv_xor_v2_device *xor_dev = (struct mv_xor_v2_device *) data;
 	int pending_ptr, num_of_pending, i;
-	struct mv_xor_v2_descriptor *next_pending_hw_desc = NULL;
 	struct mv_xor_v2_sw_desc *next_pending_sw_desc = NULL;
 
 	dev_dbg(xor_dev->dmadev.dev, "%s %d\n", __func__, __LINE__);
@@ -562,17 +538,10 @@ static void mv_xor_v2_tasklet(unsigned long data)
 	/* get the pending descriptors parameters */
 	num_of_pending = mv_xor_v2_get_pending_params(xor_dev, &pending_ptr);
 
-	/* next HW descriptor */
-	next_pending_hw_desc = xor_dev->hw_desq_virt + pending_ptr;
-
 	/* loop over free descriptors */
 	for (i = 0; i < num_of_pending; i++) {
-
-		if (pending_ptr > MV_XOR_V2_DESC_NUM)
-			pending_ptr = 0;
-
-		if (next_pending_sw_desc != NULL)
-			next_pending_hw_desc++;
+		struct mv_xor_v2_descriptor *next_pending_hw_desc =
+			xor_dev->hw_desq_virt + pending_ptr;
 
 		/* get the SW descriptor related to the HW descriptor */
 		next_pending_sw_desc =
@@ -608,15 +577,14 @@ static void mv_xor_v2_tasklet(unsigned long data)
 
 		/* increment the next descriptor */
 		pending_ptr++;
+		if (pending_ptr >= MV_XOR_V2_DESC_NUM)
+			pending_ptr = 0;
 	}
 
 	if (num_of_pending != 0) {
 		/* free the descriptores */
 		mv_xor_v2_free_desc_from_desq(xor_dev, num_of_pending);
 	}
-
-	/* Update IMSG threshold, to enable new IMSG interrupts */
-	mv_xor_v2_set_imsg_thrd(xor_dev, 0);
 }
 
 /*
@@ -648,9 +616,6 @@ static int mv_xor_v2_descq_init(struct mv_xor_v2_device *xor_dev)
 	writel((xor_dev->hw_desq & 0xFFFF00000000) >> 32,
 	       xor_dev->dma_base + MV_XOR_V2_DMA_DESQ_BAHR_OFF);
 
-	/* enable the DMA engine */
-	writel(0, xor_dev->dma_base + MV_XOR_V2_DMA_DESQ_STOP_OFF);
-
 	/*
 	 * This is a temporary solution, until we activate the
 	 * SMMU. Set the attributes for reading & writing data buffers
@@ -694,6 +659,9 @@ static int mv_xor_v2_descq_init(struct mv_xor_v2_device *xor_dev)
 	reg |= MV_XOR_V2_GLOB_PAUSE_AXI_TIME_DIS_VAL;
 	writel(reg, xor_dev->glob_base + MV_XOR_V2_GLOB_PAUSE);
 
+	/* enable the DMA engine */
+	writel(0, xor_dev->dma_base + MV_XOR_V2_DMA_DESQ_STOP_OFF);
+
 	return 0;
 }
 
@@ -725,6 +693,10 @@ static int mv_xor_v2_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, xor_dev);
 
+	ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(40));
+	if (ret)
+		return ret;
+
 	xor_dev->clk = devm_clk_get(&pdev->dev, NULL);
 	if (IS_ERR(xor_dev->clk) && PTR_ERR(xor_dev->clk) == -EPROBE_DEFER)
 		return -EPROBE_DEFER;
@@ -785,8 +757,15 @@ static int mv_xor_v2_probe(struct platform_device *pdev)
 
 	/* add all SW descriptors to the free list */
 	for (i = 0; i < MV_XOR_V2_DESC_NUM; i++) {
-		xor_dev->sw_desq[i].idx = i;
-		list_add(&xor_dev->sw_desq[i].free_list,
+		struct mv_xor_v2_sw_desc *sw_desc =
+			xor_dev->sw_desq + i;
+		sw_desc->idx = i;
+		dma_async_tx_descriptor_init(&sw_desc->async_tx,
+					     &xor_dev->dmachan);
+		sw_desc->async_tx.tx_submit = mv_xor_v2_tx_submit;
+		async_tx_ack(&sw_desc->async_tx);
+
+		list_add(&sw_desc->free_list,
 			 &xor_dev->free_sw_desc);
 	}
 
diff --git a/drivers/dma/sh/usb-dmac.c b/drivers/dma/sh/usb-dmac.c
index 06ecdc38cee0..6682b3eec2b6 100644
--- a/drivers/dma/sh/usb-dmac.c
+++ b/drivers/dma/sh/usb-dmac.c
@@ -117,7 +117,7 @@ struct usb_dmac {
 #define USB_DMASWR			0x0008
 #define USB_DMASWR_SWR			(1 << 0)
 #define USB_DMAOR			0x0060
-#define USB_DMAOR_AE			(1 << 2)
+#define USB_DMAOR_AE			(1 << 1)
 #define USB_DMAOR_DME			(1 << 0)
 
 #define USB_DMASAR			0x0000
diff --git a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
index 5be788b269e2..1679727c22ef 100644
--- a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
@@ -900,6 +900,12 @@ static bool ci_dpm_vblank_too_short(struct amdgpu_device *adev)
 	u32 vblank_time = amdgpu_dpm_get_vblank_time(adev);
 	u32 switch_limit = adev->mc.vram_type == AMDGPU_VRAM_TYPE_GDDR5 ? 450 : 300;
 
+	/* disable mclk switching if the refresh is >120Hz, even if the
+	 * blanking period would allow it
+	 */
+	if (amdgpu_dpm_get_vrefresh(adev) > 120)
+		return true;
+
 	if (vblank_time < switch_limit)
 		return true;
 	else
diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index 6efdba4993fc..0f2fa9044668 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -379,7 +379,12 @@ EXPORT_SYMBOL(drm_put_dev);
 void drm_unplug_dev(struct drm_device *dev)
 {
 	/* for a USB device */
-	drm_dev_unregister(dev);
+	if (drm_core_check_feature(dev, DRIVER_MODESET))
+		drm_modeset_unregister_all(dev);
+
+	drm_minor_unregister(dev, DRM_MINOR_PRIMARY);
+	drm_minor_unregister(dev, DRM_MINOR_RENDER);
+	drm_minor_unregister(dev, DRM_MINOR_CONTROL);
 
 	mutex_lock(&drm_global_mutex);
 
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 923150de46cb..ca6efb69ef66 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -573,9 +573,7 @@ static int i915_load_modeset_init(struct drm_device *dev)
 	if (i915_inject_load_failure())
 		return -ENODEV;
 
-	ret = intel_bios_init(dev_priv);
-	if (ret)
-		DRM_INFO("failed to find VBIOS tables\n");
+	intel_bios_init(dev_priv);
 
 	/* If we have > 1 VGA cards, then we need to arbitrate access
 	 * to the common VGA resources.
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index e0d72457b23c..36a665f0e5c9 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -3584,7 +3584,7 @@ static inline bool intel_gmbus_is_forced_bit(struct i2c_adapter *adapter)
 extern void intel_i2c_reset(struct drm_device *dev);
 
 /* intel_bios.c */
-int intel_bios_init(struct drm_i915_private *dev_priv);
+void intel_bios_init(struct drm_i915_private *dev_priv);
 bool intel_bios_is_valid_vbt(const void *buf, size_t size);
 bool intel_bios_is_tv_present(struct drm_i915_private *dev_priv);
 bool intel_bios_is_lvds_present(struct drm_i915_private *dev_priv, u8 *i2c_pin);
diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c
index cf2560708e03..4ac36e3c341f 100644
--- a/drivers/gpu/drm/i915/intel_bios.c
+++ b/drivers/gpu/drm/i915/intel_bios.c
@@ -1332,6 +1332,7 @@ parse_device_mapping(struct drm_i915_private *dev_priv,
 	return;
 }
 
+/* Common defaults which may be overridden by VBT. */
 static void
 init_vbt_defaults(struct drm_i915_private *dev_priv)
 {
@@ -1368,6 +1369,18 @@ init_vbt_defaults(struct drm_i915_private *dev_priv)
 			&dev_priv->vbt.ddi_port_info[port];
 
 		info->hdmi_level_shift = HDMI_LEVEL_SHIFT_UNKNOWN;
+	}
+}
+
+/* Defaults to initialize only if there is no VBT. */
+static void
+init_vbt_missing_defaults(struct drm_i915_private *dev_priv)
+{
+	enum port port;
+
+	for (port = PORT_A; port < I915_MAX_PORTS; port++) {
+		struct ddi_vbt_port_info *info =
+			&dev_priv->vbt.ddi_port_info[port];
 
 		info->supports_dvi = (port != PORT_A && port != PORT_E);
 		info->supports_hdmi = info->supports_dvi;
@@ -1450,36 +1463,35 @@ static const struct vbt_header *find_vbt(void __iomem *bios, size_t size)
  * intel_bios_init - find VBT and initialize settings from the BIOS
  * @dev_priv: i915 device instance
  *
- * Loads the Video BIOS and checks that the VBT exists.  Sets scratch registers
- * to appropriate values.
- *
- * Returns 0 on success, nonzero on failure.
+ * Parse and initialize settings from the Video BIOS Tables (VBT). If the VBT
+ * was not found in ACPI OpRegion, try to find it in PCI ROM first. Also
+ * initialize some defaults if the VBT is not present at all.
  */
-int
-intel_bios_init(struct drm_i915_private *dev_priv)
+void intel_bios_init(struct drm_i915_private *dev_priv)
 {
 	struct pci_dev *pdev = dev_priv->drm.pdev;
 	const struct vbt_header *vbt = dev_priv->opregion.vbt;
 	const struct bdb_header *bdb;
 	u8 __iomem *bios = NULL;
 
-	if (HAS_PCH_NOP(dev_priv))
-		return -ENODEV;
+	if (HAS_PCH_NOP(dev_priv)) {
+		DRM_DEBUG_KMS("Skipping VBT init due to disabled display.\n");
+		return;
+	}
 
 	init_vbt_defaults(dev_priv);
 
+	/* If the OpRegion does not have VBT, look in PCI ROM. */
 	if (!vbt) {
 		size_t size;
 
 		bios = pci_map_rom(pdev, &size);
 		if (!bios)
-			return -1;
+			goto out;
 
 		vbt = find_vbt(bios, size);
-		if (!vbt) {
-			pci_unmap_rom(pdev, bios);
-			return -1;
-		}
+		if (!vbt)
+			goto out;
 
 		DRM_DEBUG_KMS("Found valid VBT in PCI ROM\n");
 	}
@@ -1504,10 +1516,14 @@ intel_bios_init(struct drm_i915_private *dev_priv)
 	parse_mipi_sequence(dev_priv, bdb);
 	parse_ddi_ports(dev_priv, bdb);
 
+out:
+	if (!vbt) {
+		DRM_INFO("Failed to find VBIOS tables (VBT)\n");
+		init_vbt_missing_defaults(dev_priv);
+	}
+
 	if (bios)
 		pci_unmap_rom(pdev, bios);
-
-	return 0;
 }
 
 /**
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index 46568fc80848..6abf315fd6da 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -801,6 +801,7 @@ static struct drm_driver msm_driver = {
 	.prime_fd_to_handle = drm_gem_prime_fd_to_handle,
 	.gem_prime_export   = drm_gem_prime_export,
 	.gem_prime_import   = drm_gem_prime_import,
+	.gem_prime_res_obj  = msm_gem_prime_res_obj,
 	.gem_prime_pin      = msm_gem_prime_pin,
 	.gem_prime_unpin    = msm_gem_prime_unpin,
 	.gem_prime_get_sg_table = msm_gem_prime_get_sg_table,
diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h
index d0da52f2a806..bc98d48c47f8 100644
--- a/drivers/gpu/drm/msm/msm_drv.h
+++ b/drivers/gpu/drm/msm/msm_drv.h
@@ -203,6 +203,7 @@ struct sg_table *msm_gem_prime_get_sg_table(struct drm_gem_object *obj);
 void *msm_gem_prime_vmap(struct drm_gem_object *obj);
 void msm_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr);
 int msm_gem_prime_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma);
+struct reservation_object *msm_gem_prime_res_obj(struct drm_gem_object *obj);
 struct drm_gem_object *msm_gem_prime_import_sg_table(struct drm_device *dev,
 		struct dma_buf_attachment *attach, struct sg_table *sg);
 int msm_gem_prime_pin(struct drm_gem_object *obj);
diff --git a/drivers/gpu/drm/msm/msm_gem_prime.c b/drivers/gpu/drm/msm/msm_gem_prime.c
index 60bb290700ce..13403c6da6c7 100644
--- a/drivers/gpu/drm/msm/msm_gem_prime.c
+++ b/drivers/gpu/drm/msm/msm_gem_prime.c
@@ -70,3 +70,10 @@ void msm_gem_prime_unpin(struct drm_gem_object *obj)
 	if (!obj->import_attach)
 		msm_gem_put_pages(obj);
 }
+
+struct reservation_object *msm_gem_prime_res_obj(struct drm_gem_object *obj)
+{
+	struct msm_gem_object *msm_obj = to_msm_bo(obj);
+
+	return msm_obj->resv;
+}
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/timer.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/timer.h
index 82d3e28918fd..7e4f24ae7de8 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/timer.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/timer.h
@@ -4,6 +4,7 @@
 
 struct nvkm_alarm {
 	struct list_head head;
+	struct list_head exec;
 	u64 timestamp;
 	void (*func)(struct nvkm_alarm *);
 };
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/timer/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/timer/base.c
index f2a86eae0a0d..2437f7d41ca2 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/timer/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/timer/base.c
@@ -50,7 +50,8 @@ nvkm_timer_alarm_trigger(struct nvkm_timer *tmr)
 		/* Move to completed list.  We'll drop the lock before
 		 * executing the callback so it can reschedule itself.
 		 */
-		list_move_tail(&alarm->head, &exec);
+		list_del_init(&alarm->head);
+		list_add(&alarm->exec, &exec);
 	}
 
 	/* Shut down interrupt if no more pending alarms. */
@@ -59,8 +60,8 @@ nvkm_timer_alarm_trigger(struct nvkm_timer *tmr)
 	spin_unlock_irqrestore(&tmr->lock, flags);
 
 	/* Execute completed callbacks. */
-	list_for_each_entry_safe(alarm, atemp, &exec, head) {
-		list_del_init(&alarm->head);
+	list_for_each_entry_safe(alarm, atemp, &exec, exec) {
+		list_del(&alarm->exec);
 		alarm->func(alarm);
 	}
 }
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c
index b6a0806b06bf..a1c68e6a689e 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c
@@ -368,6 +368,8 @@ static void *vmw_local_fifo_reserve(struct vmw_private *dev_priv,
 				return fifo_state->static_buffer;
 			else {
 				fifo_state->dynamic_buffer = vmalloc(bytes);
+				if (!fifo_state->dynamic_buffer)
+					goto out_err;
 				return fifo_state->dynamic_buffer;
 			}
 		}
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
index 05fa092c942b..56b803384ea2 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
@@ -1275,11 +1275,14 @@ int vmw_gb_surface_define_ioctl(struct drm_device *dev, void *data,
 	struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
 	int ret;
 	uint32_t size;
-	uint32_t backup_handle;
+	uint32_t backup_handle = 0;
 
 	if (req->multisample_count != 0)
 		return -EINVAL;
 
+	if (req->mip_levels > DRM_VMW_MAX_MIP_LEVELS)
+		return -EINVAL;
+
 	if (unlikely(vmw_user_surface_size == 0))
 		vmw_user_surface_size = ttm_round_pot(sizeof(*user_srf)) +
 			128;
@@ -1315,12 +1318,16 @@ int vmw_gb_surface_define_ioctl(struct drm_device *dev, void *data,
 		ret = vmw_user_dmabuf_lookup(tfile, req->buffer_handle,
 					     &res->backup,
 					     &user_srf->backup_base);
-		if (ret == 0 && res->backup->base.num_pages * PAGE_SIZE <
-		    res->backup_size) {
-			DRM_ERROR("Surface backup buffer is too small.\n");
-			vmw_dmabuf_unreference(&res->backup);
-			ret = -EINVAL;
-			goto out_unlock;
+		if (ret == 0) {
+			if (res->backup->base.num_pages * PAGE_SIZE <
+			    res->backup_size) {
+				DRM_ERROR("Surface backup buffer is too small.\n");
+				vmw_dmabuf_unreference(&res->backup);
+				ret = -EINVAL;
+				goto out_unlock;
+			} else {
+				backup_handle = req->buffer_handle;
+			}
 		}
 	} else if (req->drm_surface_flags & drm_vmw_surface_flag_create_buffer)
 		ret = vmw_user_dmabuf_alloc(dev_priv, tfile,
diff --git a/drivers/iio/adc/bcm_iproc_adc.c b/drivers/iio/adc/bcm_iproc_adc.c
index 21d38c8af21e..7f4f9c4150e3 100644
--- a/drivers/iio/adc/bcm_iproc_adc.c
+++ b/drivers/iio/adc/bcm_iproc_adc.c
@@ -143,7 +143,7 @@ static void iproc_adc_reg_dump(struct iio_dev *indio_dev)
 	iproc_adc_dbg_reg(dev, adc_priv, IPROC_SOFT_BYPASS_DATA);
 }
 
-static irqreturn_t iproc_adc_interrupt_handler(int irq, void *data)
+static irqreturn_t iproc_adc_interrupt_thread(int irq, void *data)
 {
 	u32 channel_intr_status;
 	u32 intr_status;
@@ -167,7 +167,7 @@ static irqreturn_t iproc_adc_interrupt_handler(int irq, void *data)
 	return IRQ_NONE;
 }
 
-static irqreturn_t iproc_adc_interrupt_thread(int irq, void *data)
+static irqreturn_t iproc_adc_interrupt_handler(int irq, void *data)
 {
 	irqreturn_t retval = IRQ_NONE;
 	struct iproc_adc_priv *adc_priv;
@@ -181,7 +181,7 @@ static irqreturn_t iproc_adc_interrupt_thread(int irq, void *data)
 	adc_priv = iio_priv(indio_dev);
 
 	regmap_read(adc_priv->regmap, IPROC_INTERRUPT_STATUS, &intr_status);
-	dev_dbg(&indio_dev->dev, "iproc_adc_interrupt_thread(),INTRPT_STS:%x\n",
+	dev_dbg(&indio_dev->dev, "iproc_adc_interrupt_handler(),INTRPT_STS:%x\n",
 			intr_status);
 
 	intr_channels = (intr_status & IPROC_ADC_INTR_MASK) >> IPROC_ADC_INTR;
@@ -566,8 +566,8 @@ static int iproc_adc_probe(struct platform_device *pdev)
 	}
 
 	ret = devm_request_threaded_irq(&pdev->dev, adc_priv->irqno,
-				iproc_adc_interrupt_thread,
 				iproc_adc_interrupt_handler,
+				iproc_adc_interrupt_thread,
 				IRQF_SHARED, "iproc-adc", indio_dev);
 	if (ret) {
 		dev_err(&pdev->dev, "request_irq error %d\n", ret);
diff --git a/drivers/iio/light/ltr501.c b/drivers/iio/light/ltr501.c
index 3afc53a3d0b6..c298fd86ed86 100644
--- a/drivers/iio/light/ltr501.c
+++ b/drivers/iio/light/ltr501.c
@@ -74,9 +74,9 @@ static const int int_time_mapping[] = {100000, 50000, 200000, 400000};
 static const struct reg_field reg_field_it =
 				REG_FIELD(LTR501_ALS_MEAS_RATE, 3, 4);
 static const struct reg_field reg_field_als_intr =
-				REG_FIELD(LTR501_INTR, 0, 0);
-static const struct reg_field reg_field_ps_intr =
 				REG_FIELD(LTR501_INTR, 1, 1);
+static const struct reg_field reg_field_ps_intr =
+				REG_FIELD(LTR501_INTR, 0, 0);
 static const struct reg_field reg_field_als_rate =
 				REG_FIELD(LTR501_ALS_MEAS_RATE, 0, 2);
 static const struct reg_field reg_field_ps_rate =
diff --git a/drivers/iio/proximity/as3935.c b/drivers/iio/proximity/as3935.c
index 020459513384..268210ea4990 100644
--- a/drivers/iio/proximity/as3935.c
+++ b/drivers/iio/proximity/as3935.c
@@ -40,9 +40,9 @@
 #define AS3935_AFE_PWR_BIT	BIT(0)
 
 #define AS3935_INT		0x03
-#define AS3935_INT_MASK		0x07
+#define AS3935_INT_MASK		0x0f
 #define AS3935_EVENT_INT	BIT(3)
-#define AS3935_NOISE_INT	BIT(1)
+#define AS3935_NOISE_INT	BIT(0)
 
 #define AS3935_DATA		0x07
 #define AS3935_DATA_MASK	0x3F
@@ -215,7 +215,7 @@ static irqreturn_t as3935_trigger_handler(int irq, void *private)
 
 	st->buffer[0] = val & AS3935_DATA_MASK;
 	iio_push_to_buffers_with_timestamp(indio_dev, &st->buffer,
-					   pf->timestamp);
+					   iio_get_time_ns(indio_dev));
 err_read:
 	iio_trigger_notify_done(indio_dev->trig);
 
@@ -244,7 +244,7 @@ static void as3935_event_work(struct work_struct *work)
 
 	switch (val) {
 	case AS3935_EVENT_INT:
-		iio_trigger_poll(st->trig);
+		iio_trigger_poll_chained(st->trig);
 		break;
 	case AS3935_NOISE_INT:
 		dev_warn(&st->spi->dev, "noise level is too high\n");
diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c
index 7826994c45bf..cd834da5934a 100644
--- a/drivers/input/mouse/elantech.c
+++ b/drivers/input/mouse/elantech.c
@@ -1118,8 +1118,10 @@ static int elantech_get_resolution_v4(struct psmouse *psmouse,
  * Asus UX32VD             0x361f02        00, 15, 0e      clickpad
  * Avatar AVIU-145A2       0x361f00        ?               clickpad
  * Fujitsu LIFEBOOK E544   0x470f00        d0, 12, 09      2 hw buttons
+ * Fujitsu LIFEBOOK E546   0x470f00        50, 12, 09      2 hw buttons
  * Fujitsu LIFEBOOK E547   0x470f00        50, 12, 09      2 hw buttons
  * Fujitsu LIFEBOOK E554   0x570f01        40, 14, 0c      2 hw buttons
+ * Fujitsu LIFEBOOK E557   0x570f01        40, 14, 0c      2 hw buttons
  * Fujitsu T725            0x470f01        05, 12, 09      2 hw buttons
  * Fujitsu H730            0x570f00        c0, 14, 0c      3 hw buttons (**)
  * Gigabyte U2442          0x450f01        58, 17, 0c      2 hw buttons
@@ -1525,6 +1527,13 @@ static const struct dmi_system_id elantech_dmi_force_crc_enabled[] = {
 		},
 	},
 	{
+		/* Fujitsu LIFEBOOK E546  does not work with crc_enabled == 0 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E546"),
+		},
+	},
+	{
 		/* Fujitsu LIFEBOOK E547 does not work with crc_enabled == 0 */
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
@@ -1546,6 +1555,13 @@ static const struct dmi_system_id elantech_dmi_force_crc_enabled[] = {
 		},
 	},
 	{
+		/* Fujitsu LIFEBOOK E557 does not work with crc_enabled == 0 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E557"),
+		},
+	},
+	{
 		/* Fujitsu LIFEBOOK U745 does not work with crc_enabled == 0 */
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
diff --git a/drivers/misc/cxl/file.c b/drivers/misc/cxl/file.c
index 77080cc5fa0a..afa211397048 100644
--- a/drivers/misc/cxl/file.c
+++ b/drivers/misc/cxl/file.c
@@ -155,11 +155,8 @@ static long afu_ioctl_start_work(struct cxl_context *ctx,
 
 	/* Do this outside the status_mutex to avoid a circular dependency with
 	 * the locking in cxl_mmap_fault() */
-	if (copy_from_user(&work, uwork,
-			   sizeof(struct cxl_ioctl_start_work))) {
-		rc = -EFAULT;
-		goto out;
-	}
+	if (copy_from_user(&work, uwork, sizeof(work)))
+		return -EFAULT;
 
 	mutex_lock(&ctx->status_mutex);
 	if (ctx->status != OPENED) {
diff --git a/drivers/misc/cxl/native.c b/drivers/misc/cxl/native.c
index a217a74ccc98..224c7103890c 100644
--- a/drivers/misc/cxl/native.c
+++ b/drivers/misc/cxl/native.c
@@ -1066,13 +1066,16 @@ int cxl_native_register_psl_err_irq(struct cxl *adapter)
 
 void cxl_native_release_psl_err_irq(struct cxl *adapter)
 {
-	if (adapter->native->err_virq != irq_find_mapping(NULL, adapter->native->err_hwirq))
+	if (adapter->native->err_virq == 0 ||
+	    adapter->native->err_virq !=
+	    irq_find_mapping(NULL, adapter->native->err_hwirq))
 		return;
 
 	cxl_p1_write(adapter, CXL_PSL_ErrIVTE, 0x0000000000000000);
 	cxl_unmap_irq(adapter->native->err_virq, adapter);
 	cxl_ops->release_one_irq(adapter, adapter->native->err_hwirq);
 	kfree(adapter->irq_name);
+	adapter->native->err_virq = 0;
 }
 
 int cxl_native_register_serr_irq(struct cxl_afu *afu)
@@ -1102,13 +1105,15 @@ int cxl_native_register_serr_irq(struct cxl_afu *afu)
 
 void cxl_native_release_serr_irq(struct cxl_afu *afu)
 {
-	if (afu->serr_virq != irq_find_mapping(NULL, afu->serr_hwirq))
+	if (afu->serr_virq == 0 ||
+	    afu->serr_virq != irq_find_mapping(NULL, afu->serr_hwirq))
 		return;
 
 	cxl_p1n_write(afu, CXL_PSL_SERR_An, 0x0000000000000000);
 	cxl_unmap_irq(afu->serr_virq, afu);
 	cxl_ops->release_one_irq(afu->adapter, afu->serr_hwirq);
 	kfree(afu->err_irq_name);
+	afu->serr_virq = 0;
 }
 
 int cxl_native_register_psl_irq(struct cxl_afu *afu)
@@ -1131,12 +1136,15 @@ int cxl_native_register_psl_irq(struct cxl_afu *afu)
 
 void cxl_native_release_psl_irq(struct cxl_afu *afu)
 {
-	if (afu->native->psl_virq != irq_find_mapping(NULL, afu->native->psl_hwirq))
+	if (afu->native->psl_virq == 0 ||
+	    afu->native->psl_virq !=
+	    irq_find_mapping(NULL, afu->native->psl_hwirq))
 		return;
 
 	cxl_unmap_irq(afu->native->psl_virq, afu);
 	cxl_ops->release_one_irq(afu->adapter, afu->native->psl_hwirq);
 	kfree(afu->psl_irq_name);
+	afu->native->psl_virq = 0;
 }
 
 static void recover_psl_err(struct cxl_afu *afu, u64 errstat)
diff --git a/drivers/misc/mei/bus.c b/drivers/misc/mei/bus.c
index dbe676de7a19..0c98ed44df05 100644
--- a/drivers/misc/mei/bus.c
+++ b/drivers/misc/mei/bus.c
@@ -678,8 +678,10 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *a,
 {
 	struct mei_cl_device *cldev = to_mei_cl_device(dev);
 	const uuid_le *uuid = mei_me_cl_uuid(cldev->me_cl);
+	u8 version = mei_me_cl_ver(cldev->me_cl);
 
-	return scnprintf(buf, PAGE_SIZE, "mei:%s:%pUl:", cldev->name, uuid);
+	return scnprintf(buf, PAGE_SIZE, "mei:%s:%pUl:%02X:",
+			 cldev->name, uuid, version);
 }
 static DEVICE_ATTR_RO(modalias);
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index 0a9108cd4c45..0a5ee1d973ac 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -1931,7 +1931,7 @@ u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb,
 	}
 
 	/* select a non-FCoE queue */
-	return fallback(dev, skb) % BNX2X_NUM_ETH_QUEUES(bp);
+	return fallback(dev, skb) % (BNX2X_NUM_ETH_QUEUES(bp) * bp->max_cos);
 }
 
 void bnx2x_set_num_queues(struct bnx2x *bp)
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 19dc9e25aa72..f9c2feb4a4e7 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -2226,10 +2226,14 @@ static int cxgb_up(struct adapter *adap)
 		if (err)
 			goto irq_err;
 	}
+
+	mutex_lock(&uld_mutex);
 	enable_rx(adap);
 	t4_sge_start(adap);
 	t4_intr_enable(adap);
 	adap->flags |= FULL_INIT_DONE;
+	mutex_unlock(&uld_mutex);
+
 	notify_ulds(adap, CXGB4_STATE_UP);
 #if IS_ENABLED(CONFIG_IPV6)
 	update_clip(adap);
diff --git a/drivers/net/ethernet/ethoc.c b/drivers/net/ethernet/ethoc.c
index c044667a0a25..e31199f3048c 100644
--- a/drivers/net/ethernet/ethoc.c
+++ b/drivers/net/ethernet/ethoc.c
@@ -710,6 +710,8 @@ static int ethoc_open(struct net_device *dev)
 	if (ret)
 		return ret;
 
+	napi_enable(&priv->napi);
+
 	ethoc_init_ring(priv, dev->mem_start);
 	ethoc_reset(priv);
 
@@ -722,7 +724,6 @@ static int ethoc_open(struct net_device *dev)
 	}
 
 	phy_start(dev->phydev);
-	napi_enable(&priv->napi);
 
 	if (netif_msg_ifup(priv)) {
 		dev_info(&dev->dev, "I/O: %08lx Memory: %08lx-%08lx\n",
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index b2893fbe25e5..ef6bff820cf6 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1953,7 +1953,7 @@ static void stmmac_tso_allocator(struct stmmac_priv *priv, unsigned int des,
 
 		priv->hw->desc->prepare_tso_tx_desc(desc, 0, buff_size,
 			0, 1,
-			(last_segment) && (buff_size < TSO_MAX_BUFF_SIZE),
+			(last_segment) && (tmp_len <= TSO_MAX_BUFF_SIZE),
 			0, 0);
 
 		tmp_len -= TSO_MAX_BUFF_SIZE;
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 3c4c2cf6d444..55c4408892be 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -59,6 +59,8 @@ static const u8 all_zeros_mac[ETH_ALEN + 2];
 
 static int vxlan_sock_add(struct vxlan_dev *vxlan);
 
+static void vxlan_vs_del_dev(struct vxlan_dev *vxlan);
+
 /* per-network namespace private data for this module */
 struct vxlan_net {
 	struct list_head  vxlan_list;
@@ -717,6 +719,22 @@ static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f)
 	call_rcu(&f->rcu, vxlan_fdb_free);
 }
 
+static void vxlan_dst_free(struct rcu_head *head)
+{
+	struct vxlan_rdst *rd = container_of(head, struct vxlan_rdst, rcu);
+
+	dst_cache_destroy(&rd->dst_cache);
+	kfree(rd);
+}
+
+static void vxlan_fdb_dst_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f,
+				  struct vxlan_rdst *rd)
+{
+	list_del_rcu(&rd->list);
+	vxlan_fdb_notify(vxlan, f, rd, RTM_DELNEIGH);
+	call_rcu(&rd->rcu, vxlan_dst_free);
+}
+
 static int vxlan_fdb_parse(struct nlattr *tb[], struct vxlan_dev *vxlan,
 			   union vxlan_addr *ip, __be16 *port, __be32 *vni,
 			   u32 *ifindex)
@@ -847,9 +865,7 @@ static int vxlan_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[],
 	 * otherwise destroy the fdb entry
 	 */
 	if (rd && !list_is_singular(&f->remotes)) {
-		list_del_rcu(&rd->list);
-		vxlan_fdb_notify(vxlan, f, rd, RTM_DELNEIGH);
-		kfree_rcu(rd, rcu);
+		vxlan_fdb_dst_destroy(vxlan, f, rd);
 		goto out;
 	}
 
@@ -1026,6 +1042,8 @@ static void vxlan_sock_release(struct vxlan_dev *vxlan)
 	rcu_assign_pointer(vxlan->vn4_sock, NULL);
 	synchronize_net();
 
+	vxlan_vs_del_dev(vxlan);
+
 	if (__vxlan_sock_release_prep(sock4)) {
 		udp_tunnel_sock_release(sock4->sock);
 		kfree(sock4);
@@ -2286,6 +2304,15 @@ static void vxlan_cleanup(unsigned long arg)
 	mod_timer(&vxlan->age_timer, next_timer);
 }
 
+static void vxlan_vs_del_dev(struct vxlan_dev *vxlan)
+{
+	struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id);
+
+	spin_lock(&vn->sock_lock);
+	hlist_del_init_rcu(&vxlan->hlist);
+	spin_unlock(&vn->sock_lock);
+}
+
 static void vxlan_vs_add_dev(struct vxlan_sock *vs, struct vxlan_dev *vxlan)
 {
 	struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id);
@@ -3056,12 +3083,6 @@ static int vxlan_newlink(struct net *src_net, struct net_device *dev,
 static void vxlan_dellink(struct net_device *dev, struct list_head *head)
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
-	struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id);
-
-	spin_lock(&vn->sock_lock);
-	if (!hlist_unhashed(&vxlan->hlist))
-		hlist_del_rcu(&vxlan->hlist);
-	spin_unlock(&vn->sock_lock);
 
 	gro_cells_destroy(&vxlan->gro_cells);
 	list_del(&vxlan->next);
diff --git a/drivers/scsi/qla2xxx/qla_bsg.c b/drivers/scsi/qla2xxx/qla_bsg.c
index 643014f82f7d..4a6e086279f9 100644
--- a/drivers/scsi/qla2xxx/qla_bsg.c
+++ b/drivers/scsi/qla2xxx/qla_bsg.c
@@ -721,6 +721,8 @@ qla2x00_process_loopback(struct fc_bsg_job *bsg_job)
 		return -EIO;
 	}
 
+	memset(&elreq, 0, sizeof(elreq));
+
 	elreq.req_sg_cnt = dma_map_sg(&ha->pdev->dev,
 		bsg_job->request_payload.sg_list, bsg_job->request_payload.sg_cnt,
 		DMA_TO_DEVICE);
@@ -786,10 +788,9 @@ qla2x00_process_loopback(struct fc_bsg_job *bsg_job)
 
 	if (atomic_read(&vha->loop_state) == LOOP_READY &&
 	    (ha->current_topology == ISP_CFG_F ||
-	    ((IS_QLA81XX(ha) || IS_QLA8031(ha) || IS_QLA8044(ha)) &&
-	    le32_to_cpu(*(uint32_t *)req_data) == ELS_OPCODE_BYTE
-	    && req_data_len == MAX_ELS_FRAME_PAYLOAD)) &&
-		elreq.options == EXTERNAL_LOOPBACK) {
+	    (le32_to_cpu(*(uint32_t *)req_data) == ELS_OPCODE_BYTE &&
+	     req_data_len == MAX_ELS_FRAME_PAYLOAD)) &&
+	    elreq.options == EXTERNAL_LOOPBACK) {
 		type = "FC_BSG_HST_VENDOR_ECHO_DIAG";
 		ql_dbg(ql_dbg_user, vha, 0x701e,
 		    "BSG request type: %s.\n", type);
diff --git a/drivers/scsi/qla2xxx/qla_dbg.c b/drivers/scsi/qla2xxx/qla_dbg.c
index 45af34ddc432..658e4d15cb71 100644
--- a/drivers/scsi/qla2xxx/qla_dbg.c
+++ b/drivers/scsi/qla2xxx/qla_dbg.c
@@ -1131,7 +1131,7 @@ qla24xx_fw_dump(scsi_qla_host_t *vha, int hardware_locked)
 
 	/* Mailbox registers. */
 	mbx_reg = &reg->mailbox0;
-	for (cnt = 0; cnt < sizeof(fw->mailbox_reg) / 2; cnt++, dmp_reg++)
+	for (cnt = 0; cnt < sizeof(fw->mailbox_reg) / 2; cnt++, mbx_reg++)
 		fw->mailbox_reg[cnt] = htons(RD_REG_WORD(mbx_reg));
 
 	/* Transfer sequence registers. */
@@ -2090,7 +2090,7 @@ qla83xx_fw_dump(scsi_qla_host_t *vha, int hardware_locked)
 
 	/* Mailbox registers. */
 	mbx_reg = &reg->mailbox0;
-	for (cnt = 0; cnt < sizeof(fw->mailbox_reg) / 2; cnt++, dmp_reg++)
+	for (cnt = 0; cnt < sizeof(fw->mailbox_reg) / 2; cnt++, mbx_reg++)
 		fw->mailbox_reg[cnt] = htons(RD_REG_WORD(mbx_reg));
 
 	/* Transfer sequence registers. */
diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c
index 23698c998699..a1b01d66c9ab 100644
--- a/drivers/scsi/qla2xxx/qla_mbx.c
+++ b/drivers/scsi/qla2xxx/qla_mbx.c
@@ -4783,9 +4783,9 @@ qla2x00_echo_test(scsi_qla_host_t *vha, struct msg_echo_lb *mreq,
 
 	memset(mcp->mb, 0 , sizeof(mcp->mb));
 	mcp->mb[0] = MBC_DIAGNOSTIC_ECHO;
-	mcp->mb[1] = mreq->options | BIT_6;	/* BIT_6 specifies 64bit address */
+	/* BIT_6 specifies 64bit address */
+	mcp->mb[1] = mreq->options | BIT_15 | BIT_6;
 	if (IS_CNA_CAPABLE(ha)) {
-		mcp->mb[1] |= BIT_15;
 		mcp->mb[2] = vha->fcoe_fcf_idx;
 	}
 	mcp->mb[16] = LSW(mreq->rcv_dma);
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index f9b52a4b8c55..94630d4738e6 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -2420,10 +2420,10 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	if (mem_only) {
 		if (pci_enable_device_mem(pdev))
-			goto probe_out;
+			return ret;
 	} else {
 		if (pci_enable_device(pdev))
-			goto probe_out;
+			return ret;
 	}
 
 	/* This may fail but that's ok */
@@ -2433,7 +2433,7 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (!ha) {
 		ql_log_pci(ql_log_fatal, pdev, 0x0009,
 		    "Unable to allocate memory for ha.\n");
-		goto probe_out;
+		goto disable_device;
 	}
 	ql_dbg_pci(ql_dbg_init, pdev, 0x000a,
 	    "Memory allocated for ha=%p.\n", ha);
@@ -3039,7 +3039,7 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	kfree(ha);
 	ha = NULL;
 
-probe_out:
+disable_device:
 	pci_disable_device(pdev);
 	return ret;
 }
diff --git a/drivers/scsi/qla2xxx/qla_tmpl.c b/drivers/scsi/qla2xxx/qla_tmpl.c
index 36935c9ed669..9c2c7fe61280 100644
--- a/drivers/scsi/qla2xxx/qla_tmpl.c
+++ b/drivers/scsi/qla2xxx/qla_tmpl.c
@@ -371,7 +371,7 @@ qla27xx_fwdt_entry_t262(struct scsi_qla_host *vha,
 		goto done;
 	}
 
-	if (end <= start || start == 0 || end == 0) {
+	if (end < start || start == 0 || end == 0) {
 		ql_dbg(ql_dbg_misc, vha, 0xd023,
 		    "%s: unusable range (start=%x end=%x)\n", __func__,
 		    ent->t262.end_addr, ent->t262.start_addr);
diff --git a/drivers/staging/lustre/lustre/lov/lov_pack.c b/drivers/staging/lustre/lustre/lov/lov_pack.c
index be6e9857ce2a..a6d1cc804647 100644
--- a/drivers/staging/lustre/lustre/lov/lov_pack.c
+++ b/drivers/staging/lustre/lustre/lov/lov_pack.c
@@ -387,18 +387,10 @@ int lov_getstripe(struct lov_object *obj, struct lov_stripe_md *lsm,
 	struct lov_mds_md *lmmk = NULL;
 	int rc, lmmk_size, lmm_size;
 	int lum_size;
-	mm_segment_t seg;
 
 	if (!lsm)
 		return -ENODATA;
 
-	/*
-	 * "Switch to kernel segment" to allow copying from kernel space by
-	 * copy_{to,from}_user().
-	 */
-	seg = get_fs();
-	set_fs(KERNEL_DS);
-
 	/* we only need the header part from user space to get lmm_magic and
 	 * lmm_stripe_count, (the header part is common to v1 and v3)
 	 */
@@ -478,6 +470,5 @@ int lov_getstripe(struct lov_object *obj, struct lov_stripe_md *lsm,
 out_free:
 	kfree(lmmk);
 out:
-	set_fs(seg);
 	return rc;
 }
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index cae4dea6464e..077344cc819f 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -1182,15 +1182,28 @@ target_cmd_size_check(struct se_cmd *cmd, unsigned int size)
 	if (cmd->unknown_data_length) {
 		cmd->data_length = size;
 	} else if (size != cmd->data_length) {
-		pr_warn("TARGET_CORE[%s]: Expected Transfer Length:"
+		pr_warn_ratelimited("TARGET_CORE[%s]: Expected Transfer Length:"
 			" %u does not match SCSI CDB Length: %u for SAM Opcode:"
 			" 0x%02x\n", cmd->se_tfo->get_fabric_name(),
 				cmd->data_length, size, cmd->t_task_cdb[0]);
 
-		if (cmd->data_direction == DMA_TO_DEVICE &&
-		    cmd->se_cmd_flags & SCF_SCSI_DATA_CDB) {
-			pr_err("Rejecting underflow/overflow WRITE data\n");
-			return TCM_INVALID_CDB_FIELD;
+		if (cmd->data_direction == DMA_TO_DEVICE) {
+			if (cmd->se_cmd_flags & SCF_SCSI_DATA_CDB) {
+				pr_err_ratelimited("Rejecting underflow/overflow"
+						   " for WRITE data CDB\n");
+				return TCM_INVALID_CDB_FIELD;
+			}
+			/*
+			 * Some fabric drivers like iscsi-target still expect to
+			 * always reject overflow writes.  Reject this case until
+			 * full fabric driver level support for overflow writes
+			 * is introduced tree-wide.
+			 */
+			if (size > cmd->data_length) {
+				pr_err_ratelimited("Rejecting overflow for"
+						   " WRITE control CDB\n");
+				return TCM_INVALID_CDB_FIELD;
+			}
 		}
 		/*
 		 * Reject READ_* or WRITE_* with overflow/underflow for
diff --git a/drivers/tty/serial/ifx6x60.c b/drivers/tty/serial/ifx6x60.c
index d386346248de..91d2ddd6ef88 100644
--- a/drivers/tty/serial/ifx6x60.c
+++ b/drivers/tty/serial/ifx6x60.c
@@ -1381,9 +1381,9 @@ static struct spi_driver ifx_spi_driver = {
 static void __exit ifx_spi_exit(void)
 {
 	/* unregister */
+	spi_unregister_driver(&ifx_spi_driver);
 	tty_unregister_driver(tty_drv);
 	put_tty_driver(tty_drv);
-	spi_unregister_driver(&ifx_spi_driver);
 	unregister_reboot_notifier(&ifx_modem_reboot_notifier_block);
 }
 
diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c
index 4b26252c2885..ee84f89391ca 100644
--- a/drivers/tty/serial/sh-sci.c
+++ b/drivers/tty/serial/sh-sci.c
@@ -1976,11 +1976,13 @@ static int sci_startup(struct uart_port *port)
 
 	dev_dbg(port->dev, "%s(%d)\n", __func__, port->line);
 
+	sci_request_dma(port);
+
 	ret = sci_request_irq(s);
-	if (unlikely(ret < 0))
+	if (unlikely(ret < 0)) {
+		sci_free_dma(port);
 		return ret;
-
-	sci_request_dma(port);
+	}
 
 	return 0;
 }
@@ -2012,8 +2014,8 @@ static void sci_shutdown(struct uart_port *port)
 	}
 #endif
 
-	sci_free_dma(port);
 	sci_free_irq(s);
+	sci_free_dma(port);
 }
 
 static int sci_sck_calc(struct sci_port *s, unsigned int bps,
diff --git a/drivers/usb/chipidea/debug.c b/drivers/usb/chipidea/debug.c
index 6d23eede4d8c..1c31e8a08810 100644
--- a/drivers/usb/chipidea/debug.c
+++ b/drivers/usb/chipidea/debug.c
@@ -294,7 +294,8 @@ static int ci_role_show(struct seq_file *s, void *data)
 {
 	struct ci_hdrc *ci = s->private;
 
-	seq_printf(s, "%s\n", ci_role(ci)->name);
+	if (ci->role != CI_ROLE_END)
+		seq_printf(s, "%s\n", ci_role(ci)->name);
 
 	return 0;
 }
diff --git a/drivers/usb/chipidea/udc.c b/drivers/usb/chipidea/udc.c
index c9e80ad48fdc..6a15b7250e9c 100644
--- a/drivers/usb/chipidea/udc.c
+++ b/drivers/usb/chipidea/udc.c
@@ -1987,6 +1987,7 @@ static void udc_id_switch_for_host(struct ci_hdrc *ci)
 int ci_hdrc_gadget_init(struct ci_hdrc *ci)
 {
 	struct ci_role_driver *rdrv;
+	int ret;
 
 	if (!hw_read(ci, CAP_DCCPARAMS, DCCPARAMS_DC))
 		return -ENXIO;
@@ -1999,7 +2000,10 @@ int ci_hdrc_gadget_init(struct ci_hdrc *ci)
 	rdrv->stop	= udc_id_switch_for_host;
 	rdrv->irq	= udc_irq;
 	rdrv->name	= "gadget";
-	ci->roles[CI_ROLE_GADGET] = rdrv;
 
-	return udc_start(ci);
+	ret = udc_start(ci);
+	if (!ret)
+		ci->roles[CI_ROLE_GADGET] = rdrv;
+
+	return ret;
 }
diff --git a/drivers/usb/gadget/function/f_mass_storage.c b/drivers/usb/gadget/function/f_mass_storage.c
index 8f3659b65f53..ccd93c9e26ab 100644
--- a/drivers/usb/gadget/function/f_mass_storage.c
+++ b/drivers/usb/gadget/function/f_mass_storage.c
@@ -395,7 +395,11 @@ static int fsg_set_halt(struct fsg_dev *fsg, struct usb_ep *ep)
 /* Caller must hold fsg->lock */
 static void wakeup_thread(struct fsg_common *common)
 {
-	smp_wmb();	/* ensure the write of bh->state is complete */
+	/*
+	 * Ensure the reading of thread_wakeup_needed
+	 * and the writing of bh->state are completed
+	 */
+	smp_mb();
 	/* Tell the main thread that something has happened */
 	common->thread_wakeup_needed = 1;
 	if (common->thread_task)
@@ -626,7 +630,12 @@ static int sleep_thread(struct fsg_common *common, bool can_freeze)
 	}
 	__set_current_state(TASK_RUNNING);
 	common->thread_wakeup_needed = 0;
-	smp_rmb();	/* ensure the latest bh->state is visible */
+
+	/*
+	 * Ensure the writing of thread_wakeup_needed
+	 * and the reading of bh->state are completed
+	 */
+	smp_mb();
 	return rc;
 }
 
diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c
index 702040fe2001..0e6061496972 100644
--- a/drivers/xen/privcmd.c
+++ b/drivers/xen/privcmd.c
@@ -335,8 +335,8 @@ static int mmap_batch_fn(void *data, int nr, void *state)
 				st->global_error = 1;
 		}
 	}
-	st->va += PAGE_SIZE * nr;
-	st->index += nr;
+	st->va += XEN_PAGE_SIZE * nr;
+	st->index += nr / XEN_PFN_PER_PAGE;
 
 	return 0;
 }
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 2924bddb4a94..07e46b786500 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -713,7 +713,7 @@ struct block_device *bdget(dev_t dev)
 		bdev->bd_contains = NULL;
 		bdev->bd_super = NULL;
 		bdev->bd_inode = inode;
-		bdev->bd_block_size = (1 << inode->i_blkbits);
+		bdev->bd_block_size = i_blocksize(inode);
 		bdev->bd_part_count = 0;
 		bdev->bd_invalidated = 0;
 		inode->i_mode = S_IFBLK;
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 5909ae8c6731..e46e7fbe1b34 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3984,6 +3984,7 @@ static int update_space_info(struct btrfs_fs_info *info, u64 flags,
 				    info->space_info_kobj, "%s",
 				    alloc_name(found->flags));
 	if (ret) {
+		percpu_counter_destroy(&found->total_bytes_pinned);
 		kfree(found);
 		return ret;
 	}
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 3a14c87d9c92..3286a6e47ff0 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -2842,7 +2842,7 @@ static long btrfs_fallocate(struct file *file, int mode,
 		if (!ret)
 			ret = btrfs_prealloc_file_range(inode, mode,
 					range->start,
-					range->len, 1 << inode->i_blkbits,
+					range->len, i_blocksize(inode),
 					offset + len, &alloc_hint);
 		else
 			btrfs_free_reserved_data_space(inode, range->start,
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index be4da91d880f..bddbae796941 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -7435,8 +7435,8 @@ bool btrfs_page_exists_in_range(struct inode *inode, loff_t start, loff_t end)
 	int found = false;
 	void **pagep = NULL;
 	struct page *page = NULL;
-	int start_idx;
-	int end_idx;
+	unsigned long start_idx;
+	unsigned long end_idx;
 
 	start_idx = start >> PAGE_SHIFT;
 
diff --git a/fs/buffer.c b/fs/buffer.c
index b205a629001d..5d8f496d624e 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -2353,7 +2353,7 @@ static int cont_expand_zero(struct file *file, struct address_space *mapping,
 			    loff_t pos, loff_t *bytes)
 {
 	struct inode *inode = mapping->host;
-	unsigned blocksize = 1 << inode->i_blkbits;
+	unsigned int blocksize = i_blocksize(inode);
 	struct page *page;
 	void *fsdata;
 	pgoff_t index, curidx;
@@ -2433,8 +2433,8 @@ int cont_write_begin(struct file *file, struct address_space *mapping,
 			get_block_t *get_block, loff_t *bytes)
 {
 	struct inode *inode = mapping->host;
-	unsigned blocksize = 1 << inode->i_blkbits;
-	unsigned zerofrom;
+	unsigned int blocksize = i_blocksize(inode);
+	unsigned int zerofrom;
 	int err;
 
 	err = cont_expand_zero(file, mapping, pos, bytes);
@@ -2796,7 +2796,7 @@ int nobh_truncate_page(struct address_space *mapping,
 	struct buffer_head map_bh;
 	int err;
 
-	blocksize = 1 << inode->i_blkbits;
+	blocksize = i_blocksize(inode);
 	length = offset & (blocksize - 1);
 
 	/* Block boundary? Nothing to do */
@@ -2874,7 +2874,7 @@ int block_truncate_page(struct address_space *mapping,
 	struct buffer_head *bh;
 	int err;
 
-	blocksize = 1 << inode->i_blkbits;
+	blocksize = i_blocksize(inode);
 	length = offset & (blocksize - 1);
 
 	/* Block boundary? Nothing to do */
@@ -2986,7 +2986,7 @@ sector_t generic_block_bmap(struct address_space *mapping, sector_t block,
 	struct inode *inode = mapping->host;
 	tmp.b_state = 0;
 	tmp.b_blocknr = 0;
-	tmp.b_size = 1 << inode->i_blkbits;
+	tmp.b_size = i_blocksize(inode);
 	get_block(inode, block, &tmp, 0);
 	return tmp.b_blocknr;
 }
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 18dc18f8af2c..900ffafb85ca 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -745,7 +745,7 @@ static int ceph_writepages_start(struct address_space *mapping,
 	struct pagevec pvec;
 	int done = 0;
 	int rc = 0;
-	unsigned wsize = 1 << inode->i_blkbits;
+	unsigned int wsize = i_blocksize(inode);
 	struct ceph_osd_request *req = NULL;
 	int do_sync = 0;
 	loff_t snap_size, i_size;
diff --git a/fs/direct-io.c b/fs/direct-io.c
index fb9aa16a7727..c60756e89833 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -587,7 +587,7 @@ static int dio_set_defer_completion(struct dio *dio)
 /*
  * Call into the fs to map some more disk blocks.  We record the current number
  * of available blocks at sdio->blocks_available.  These are in units of the
- * fs blocksize, (1 << inode->i_blkbits).
+ * fs blocksize, i_blocksize(inode).
  *
  * The fs is allowed to map lots of blocks at once.  If it wants to do that,
  * it uses the passed inode-relative block number as the file offset, as usual.
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 9fbf92ca358c..a3e0b3b7441d 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -3413,13 +3413,13 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 	struct ext4_sb_info *sbi;
 	struct ext4_extent_header *eh;
 	struct ext4_map_blocks split_map;
-	struct ext4_extent zero_ex;
+	struct ext4_extent zero_ex1, zero_ex2;
 	struct ext4_extent *ex, *abut_ex;
 	ext4_lblk_t ee_block, eof_block;
 	unsigned int ee_len, depth, map_len = map->m_len;
 	int allocated = 0, max_zeroout = 0;
 	int err = 0;
-	int split_flag = 0;
+	int split_flag = EXT4_EXT_DATA_VALID2;
 
 	ext_debug("ext4_ext_convert_to_initialized: inode %lu, logical"
 		"block %llu, max_blocks %u\n", inode->i_ino,
@@ -3436,7 +3436,8 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 	ex = path[depth].p_ext;
 	ee_block = le32_to_cpu(ex->ee_block);
 	ee_len = ext4_ext_get_actual_len(ex);
-	zero_ex.ee_len = 0;
+	zero_ex1.ee_len = 0;
+	zero_ex2.ee_len = 0;
 
 	trace_ext4_ext_convert_to_initialized_enter(inode, map, ex);
 
@@ -3576,62 +3577,52 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 	if (ext4_encrypted_inode(inode))
 		max_zeroout = 0;
 
-	/* If extent is less than s_max_zeroout_kb, zeroout directly */
-	if (max_zeroout && (ee_len <= max_zeroout)) {
-		err = ext4_ext_zeroout(inode, ex);
-		if (err)
-			goto out;
-		zero_ex.ee_block = ex->ee_block;
-		zero_ex.ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex));
-		ext4_ext_store_pblock(&zero_ex, ext4_ext_pblock(ex));
-
-		err = ext4_ext_get_access(handle, inode, path + depth);
-		if (err)
-			goto out;
-		ext4_ext_mark_initialized(ex);
-		ext4_ext_try_to_merge(handle, inode, path, ex);
-		err = ext4_ext_dirty(handle, inode, path + path->p_depth);
-		goto out;
-	}
-
 	/*
-	 * four cases:
+	 * five cases:
 	 * 1. split the extent into three extents.
-	 * 2. split the extent into two extents, zeroout the first half.
-	 * 3. split the extent into two extents, zeroout the second half.
+	 * 2. split the extent into two extents, zeroout the head of the first
+	 *    extent.
+	 * 3. split the extent into two extents, zeroout the tail of the second
+	 *    extent.
 	 * 4. split the extent into two extents with out zeroout.
+	 * 5. no splitting needed, just possibly zeroout the head and / or the
+	 *    tail of the extent.
 	 */
 	split_map.m_lblk = map->m_lblk;
 	split_map.m_len = map->m_len;
 
-	if (max_zeroout && (allocated > map->m_len)) {
+	if (max_zeroout && (allocated > split_map.m_len)) {
 		if (allocated <= max_zeroout) {
-			/* case 3 */
-			zero_ex.ee_block =
-					 cpu_to_le32(map->m_lblk);
-			zero_ex.ee_len = cpu_to_le16(allocated);
-			ext4_ext_store_pblock(&zero_ex,
-				ext4_ext_pblock(ex) + map->m_lblk - ee_block);
-			err = ext4_ext_zeroout(inode, &zero_ex);
+			/* case 3 or 5 */
+			zero_ex1.ee_block =
+				 cpu_to_le32(split_map.m_lblk +
+					     split_map.m_len);
+			zero_ex1.ee_len =
+				cpu_to_le16(allocated - split_map.m_len);
+			ext4_ext_store_pblock(&zero_ex1,
+				ext4_ext_pblock(ex) + split_map.m_lblk +
+				split_map.m_len - ee_block);
+			err = ext4_ext_zeroout(inode, &zero_ex1);
 			if (err)
 				goto out;
-			split_map.m_lblk = map->m_lblk;
 			split_map.m_len = allocated;
-		} else if (map->m_lblk - ee_block + map->m_len < max_zeroout) {
-			/* case 2 */
-			if (map->m_lblk != ee_block) {
-				zero_ex.ee_block = ex->ee_block;
-				zero_ex.ee_len = cpu_to_le16(map->m_lblk -
+		}
+		if (split_map.m_lblk - ee_block + split_map.m_len <
+								max_zeroout) {
+			/* case 2 or 5 */
+			if (split_map.m_lblk != ee_block) {
+				zero_ex2.ee_block = ex->ee_block;
+				zero_ex2.ee_len = cpu_to_le16(split_map.m_lblk -
 							ee_block);
-				ext4_ext_store_pblock(&zero_ex,
+				ext4_ext_store_pblock(&zero_ex2,
 						      ext4_ext_pblock(ex));
-				err = ext4_ext_zeroout(inode, &zero_ex);
+				err = ext4_ext_zeroout(inode, &zero_ex2);
 				if (err)
 					goto out;
 			}
 
+			split_map.m_len += split_map.m_lblk - ee_block;
 			split_map.m_lblk = ee_block;
-			split_map.m_len = map->m_lblk - ee_block + map->m_len;
 			allocated = map->m_len;
 		}
 	}
@@ -3642,8 +3633,11 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 		err = 0;
 out:
 	/* If we have gotten a failure, don't zero out status tree */
-	if (!err)
-		err = ext4_zeroout_es(inode, &zero_ex);
+	if (!err) {
+		err = ext4_zeroout_es(inode, &zero_ex1);
+		if (!err)
+			err = ext4_zeroout_es(inode, &zero_ex2);
+	}
 	return err ? err : allocated;
 }
 
@@ -4893,6 +4887,8 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 
 	/* Zero out partial block at the edges of the range */
 	ret = ext4_zero_partial_blocks(handle, inode, offset, len);
+	if (ret >= 0)
+		ext4_update_inode_fsync_trans(handle, inode, 1);
 
 	if (file->f_flags & O_SYNC)
 		ext4_handle_sync(handle);
@@ -5579,6 +5575,7 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 		ext4_handle_sync(handle);
 	inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
 	ext4_mark_inode_dirty(handle, inode);
+	ext4_update_inode_fsync_trans(handle, inode, 1);
 
 out_stop:
 	ext4_journal_stop(handle);
@@ -5752,6 +5749,8 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
 	up_write(&EXT4_I(inode)->i_data_sem);
 	if (IS_SYNC(inode))
 		ext4_handle_sync(handle);
+	if (ret >= 0)
+		ext4_update_inode_fsync_trans(handle, inode, 1);
 
 out_stop:
 	ext4_journal_stop(handle);
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 2a822d30e73f..9e77c089e8cb 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -432,47 +432,27 @@ static int ext4_find_unwritten_pgoff(struct inode *inode,
 		num = min_t(pgoff_t, end - index, PAGEVEC_SIZE);
 		nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index,
 					  (pgoff_t)num);
-		if (nr_pages == 0) {
-			if (whence == SEEK_DATA)
-				break;
-
-			BUG_ON(whence != SEEK_HOLE);
-			/*
-			 * If this is the first time to go into the loop and
-			 * offset is not beyond the end offset, it will be a
-			 * hole at this offset
-			 */
-			if (lastoff == startoff || lastoff < endoff)
-				found = 1;
-			break;
-		}
-
-		/*
-		 * If this is the first time to go into the loop and
-		 * offset is smaller than the first page offset, it will be a
-		 * hole at this offset.
-		 */
-		if (lastoff == startoff && whence == SEEK_HOLE &&
-		    lastoff < page_offset(pvec.pages[0])) {
-			found = 1;
+		if (nr_pages == 0)
 			break;
-		}
 
 		for (i = 0; i < nr_pages; i++) {
 			struct page *page = pvec.pages[i];
 			struct buffer_head *bh, *head;
 
 			/*
-			 * If the current offset is not beyond the end of given
-			 * range, it will be a hole.
+			 * If current offset is smaller than the page offset,
+			 * there is a hole at this offset.
 			 */
-			if (lastoff < endoff && whence == SEEK_HOLE &&
-			    page->index > end) {
+			if (whence == SEEK_HOLE && lastoff < endoff &&
+			    lastoff < page_offset(pvec.pages[i])) {
 				found = 1;
 				*offset = lastoff;
 				goto out;
 			}
 
+			if (page->index > end)
+				goto out;
+
 			lock_page(page);
 
 			if (unlikely(page->mapping != inode->i_mapping)) {
@@ -512,20 +492,18 @@ static int ext4_find_unwritten_pgoff(struct inode *inode,
 			unlock_page(page);
 		}
 
-		/*
-		 * The no. of pages is less than our desired, that would be a
-		 * hole in there.
-		 */
-		if (nr_pages < num && whence == SEEK_HOLE) {
-			found = 1;
-			*offset = lastoff;
+		/* The no. of pages is less than our desired, we are done. */
+		if (nr_pages < num)
 			break;
-		}
 
 		index = pvec.pages[i - 1]->index + 1;
 		pagevec_release(&pvec);
 	} while (index <= end);
 
+	if (whence == SEEK_HOLE && lastoff < endoff) {
+		found = 1;
+		*offset = lastoff;
+	}
 out:
 	pagevec_release(&pvec);
 	return found;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 01329688fb9e..1b29efcab3dc 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -2205,7 +2205,7 @@ static int mpage_process_page_bufs(struct mpage_da_data *mpd,
 {
 	struct inode *inode = mpd->inode;
 	int err;
-	ext4_lblk_t blocks = (i_size_read(inode) + (1 << inode->i_blkbits) - 1)
+	ext4_lblk_t blocks = (i_size_read(inode) + i_blocksize(inode) - 1)
 							>> inode->i_blkbits;
 
 	do {
@@ -3454,14 +3454,14 @@ static ssize_t ext4_direct_IO_write(struct kiocb *iocb, struct iov_iter *iter)
 		 * writes need zeroing either because they can race with page
 		 * faults or because they use partial blocks.
 		 */
-		if (round_down(offset, 1<<inode->i_blkbits) >= inode->i_size &&
+		if (round_down(offset, i_blocksize(inode)) >= inode->i_size &&
 		    ext4_aligned_io(inode, offset, count))
 			get_block_func = ext4_dio_get_block;
 		else
 			get_block_func = ext4_dax_get_block;
 		dio_flags = DIO_LOCKING;
 	} else if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) ||
-		   round_down(offset, 1 << inode->i_blkbits) >= inode->i_size) {
+		   round_down(offset, i_blocksize(inode)) >= inode->i_size) {
 		get_block_func = ext4_dio_get_block;
 		dio_flags = DIO_LOCKING | DIO_SKIP_HOLES;
 	} else if (is_sync_kiocb(iocb)) {
@@ -4044,6 +4044,8 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
 
 	inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
 	ext4_mark_inode_dirty(handle, inode);
+	if (ret >= 0)
+		ext4_update_inode_fsync_trans(handle, inode, 1);
 out_stop:
 	ext4_journal_stop(handle);
 out_dio:
@@ -5046,7 +5048,7 @@ static void ext4_wait_for_tail_page_commit(struct inode *inode)
 	 * do. We do the check mainly to optimize the common PAGE_SIZE ==
 	 * blocksize case
 	 */
-	if (offset > PAGE_SIZE - (1 << inode->i_blkbits))
+	if (offset > PAGE_SIZE - i_blocksize(inode))
 		return;
 	while (1) {
 		page = find_lock_page(inode->i_mapping,
@@ -5441,8 +5443,9 @@ static int ext4_expand_extra_isize(struct inode *inode,
 	/* No extended attributes present */
 	if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR) ||
 	    header->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC)) {
-		memset((void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE, 0,
-			new_extra_isize);
+		memset((void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE +
+		       EXT4_I(inode)->i_extra_isize, 0,
+		       new_extra_isize - EXT4_I(inode)->i_extra_isize);
 		EXT4_I(inode)->i_extra_isize = new_extra_isize;
 		return 0;
 	}
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 2e9fc7a61048..846b57ff58de 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -838,7 +838,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp)
 	inode = page->mapping->host;
 	sb = inode->i_sb;
 	ngroups = ext4_get_groups_count(sb);
-	blocksize = 1 << inode->i_blkbits;
+	blocksize = i_blocksize(inode);
 	blocks_per_page = PAGE_SIZE / blocksize;
 
 	groups_per_page = blocks_per_page >> 1;
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index 6fc14def0c70..578f8c33fb44 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -187,7 +187,7 @@ mext_page_mkuptodate(struct page *page, unsigned from, unsigned to)
 	if (PageUptodate(page))
 		return 0;
 
-	blocksize = 1 << inode->i_blkbits;
+	blocksize = i_blocksize(inode);
 	if (!page_has_buffers(page))
 		create_empty_buffers(page, blocksize, 0);
 
diff --git a/fs/iomap.c b/fs/iomap.c
index 814ae8f9587d..798c291cbc75 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -419,8 +419,8 @@ int
 iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
 		struct iomap_ops *ops)
 {
-	unsigned blocksize = (1 << inode->i_blkbits);
-	unsigned off = pos & (blocksize - 1);
+	unsigned int blocksize = i_blocksize(inode);
+	unsigned int off = pos & (blocksize - 1);
 
 	/* Block boundary? Nothing to do */
 	if (!off)
diff --git a/fs/jfs/super.c b/fs/jfs/super.c
index 85671f7f8518..14be95bc0bcd 100644
--- a/fs/jfs/super.c
+++ b/fs/jfs/super.c
@@ -758,7 +758,7 @@ static ssize_t jfs_quota_read(struct super_block *sb, int type, char *data,
 				sb->s_blocksize - offset : toread;
 
 		tmp_bh.b_state = 0;
-		tmp_bh.b_size = 1 << inode->i_blkbits;
+		tmp_bh.b_size = i_blocksize(inode);
 		err = jfs_get_block(inode, blk, &tmp_bh, 0);
 		if (err)
 			return err;
@@ -798,7 +798,7 @@ static ssize_t jfs_quota_write(struct super_block *sb, int type,
 				sb->s_blocksize - offset : towrite;
 
 		tmp_bh.b_state = 0;
-		tmp_bh.b_size = 1 << inode->i_blkbits;
+		tmp_bh.b_size = i_blocksize(inode);
 		err = jfs_get_block(inode, blk, &tmp_bh, 1);
 		if (err)
 			goto out;
diff --git a/fs/mpage.c b/fs/mpage.c
index d2413af0823a..d2fcb149720d 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -115,7 +115,7 @@ map_buffer_to_page(struct page *page, struct buffer_head *bh, int page_block)
 			SetPageUptodate(page);    
 			return;
 		}
-		create_empty_buffers(page, 1 << inode->i_blkbits, 0);
+		create_empty_buffers(page, i_blocksize(inode), 0);
 	}
 	head = page_buffers(page);
 	page_bh = head;
diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c
index 0780ff864539..3e396dbb1eb9 100644
--- a/fs/nfsd/blocklayout.c
+++ b/fs/nfsd/blocklayout.c
@@ -23,7 +23,7 @@ nfsd4_block_proc_layoutget(struct inode *inode, const struct svc_fh *fhp,
 {
 	struct nfsd4_layout_seg *seg = &args->lg_seg;
 	struct super_block *sb = inode->i_sb;
-	u32 block_size = (1 << inode->i_blkbits);
+	u32 block_size = i_blocksize(inode);
 	struct pnfs_block_extent *bex;
 	struct iomap iomap;
 	u32 device_generation = 0;
@@ -180,7 +180,7 @@ nfsd4_block_proc_layoutcommit(struct inode *inode,
 	int nr_iomaps;
 
 	nr_iomaps = nfsd4_block_decode_layoutupdate(lcp->lc_up_layout,
-			lcp->lc_up_len, &iomaps, 1 << inode->i_blkbits);
+			lcp->lc_up_len, &iomaps, i_blocksize(inode));
 	if (nr_iomaps < 0)
 		return nfserrno(nr_iomaps);
 
@@ -372,7 +372,7 @@ nfsd4_scsi_proc_layoutcommit(struct inode *inode,
 	int nr_iomaps;
 
 	nr_iomaps = nfsd4_scsi_decode_layoutupdate(lcp->lc_up_layout,
-			lcp->lc_up_len, &iomaps, 1 << inode->i_blkbits);
+			lcp->lc_up_len, &iomaps, i_blocksize(inode));
 	if (nr_iomaps < 0)
 		return nfserrno(nr_iomaps);
 
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 650226f33298..022d95886d66 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -1783,6 +1783,12 @@ nfsd4_proc_compound(struct svc_rqst *rqstp,
 			opdesc->op_get_currentstateid(cstate, &op->u);
 		op->status = opdesc->op_func(rqstp, cstate, &op->u);
 
+		/* Only from SEQUENCE */
+		if (cstate->status == nfserr_replay_cache) {
+			dprintk("%s NFS4.1 replay from cache\n", __func__);
+			status = op->status;
+			goto out;
+		}
 		if (!op->status) {
 			if (opdesc->op_set_currentstateid)
 				opdesc->op_set_currentstateid(cstate, &op->u);
@@ -1793,14 +1799,7 @@ nfsd4_proc_compound(struct svc_rqst *rqstp,
 			if (need_wrongsec_check(rqstp))
 				op->status = check_nfsd_access(current_fh->fh_export, rqstp);
 		}
-
 encode_op:
-		/* Only from SEQUENCE */
-		if (cstate->status == nfserr_replay_cache) {
-			dprintk("%s NFS4.1 replay from cache\n", __func__);
-			status = op->status;
-			goto out;
-		}
 		if (op->status == nfserr_replay_me) {
 			op->replay = &cstate->replay_owner->so_replay;
 			nfsd4_encode_replay(&resp->xdr, op);
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 2ee80e1f5230..4e7a56a0a9b6 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -2793,9 +2793,16 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp,
 	}
 #endif /* CONFIG_NFSD_PNFS */
 	if (bmval2 & FATTR4_WORD2_SUPPATTR_EXCLCREAT) {
-		status = nfsd4_encode_bitmap(xdr, NFSD_SUPPATTR_EXCLCREAT_WORD0,
-						  NFSD_SUPPATTR_EXCLCREAT_WORD1,
-						  NFSD_SUPPATTR_EXCLCREAT_WORD2);
+		u32 supp[3];
+
+		supp[0] = nfsd_suppattrs0(minorversion);
+		supp[1] = nfsd_suppattrs1(minorversion);
+		supp[2] = nfsd_suppattrs2(minorversion);
+		supp[0] &= NFSD_SUPPATTR_EXCLCREAT_WORD0;
+		supp[1] &= NFSD_SUPPATTR_EXCLCREAT_WORD1;
+		supp[2] &= NFSD_SUPPATTR_EXCLCREAT_WORD2;
+
+		status = nfsd4_encode_bitmap(xdr, supp[0], supp[1], supp[2]);
 		if (status)
 			goto out;
 	}
diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c
index d5c23da43513..c21e0b4454a6 100644
--- a/fs/nilfs2/btnode.c
+++ b/fs/nilfs2/btnode.c
@@ -50,7 +50,7 @@ nilfs_btnode_create_block(struct address_space *btnc, __u64 blocknr)
 		brelse(bh);
 		BUG();
 	}
-	memset(bh->b_data, 0, 1 << inode->i_blkbits);
+	memset(bh->b_data, 0, i_blocksize(inode));
 	bh->b_bdev = inode->i_sb->s_bdev;
 	bh->b_blocknr = blocknr;
 	set_buffer_mapped(bh);
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index c7f4fef9ebf5..7ffe71a8dfb9 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -51,7 +51,7 @@ void nilfs_inode_add_blocks(struct inode *inode, int n)
 {
 	struct nilfs_root *root = NILFS_I(inode)->i_root;
 
-	inode_add_bytes(inode, (1 << inode->i_blkbits) * n);
+	inode_add_bytes(inode, i_blocksize(inode) * n);
 	if (root)
 		atomic64_add(n, &root->blocks_count);
 }
@@ -60,7 +60,7 @@ void nilfs_inode_sub_blocks(struct inode *inode, int n)
 {
 	struct nilfs_root *root = NILFS_I(inode)->i_root;
 
-	inode_sub_bytes(inode, (1 << inode->i_blkbits) * n);
+	inode_sub_bytes(inode, i_blocksize(inode) * n);
 	if (root)
 		atomic64_sub(n, &root->blocks_count);
 }
diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c
index d56d3a5bea88..98835ed6bef4 100644
--- a/fs/nilfs2/mdt.c
+++ b/fs/nilfs2/mdt.c
@@ -57,7 +57,7 @@ nilfs_mdt_insert_new_block(struct inode *inode, unsigned long block,
 	set_buffer_mapped(bh);
 
 	kaddr = kmap_atomic(bh->b_page);
-	memset(kaddr + bh_offset(bh), 0, 1 << inode->i_blkbits);
+	memset(kaddr + bh_offset(bh), 0, i_blocksize(inode));
 	if (init_block)
 		init_block(inode, bh, kaddr);
 	flush_dcache_page(bh->b_page);
@@ -501,7 +501,7 @@ void nilfs_mdt_set_entry_size(struct inode *inode, unsigned int entry_size,
 	struct nilfs_mdt_info *mi = NILFS_MDT(inode);
 
 	mi->mi_entry_size = entry_size;
-	mi->mi_entries_per_block = (1 << inode->i_blkbits) / entry_size;
+	mi->mi_entries_per_block = i_blocksize(inode) / entry_size;
 	mi->mi_first_entry_offset = DIV_ROUND_UP(header_size, entry_size);
 }
 
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index bedcae2c28e6..7d18d62e8e07 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -723,7 +723,7 @@ static size_t nilfs_lookup_dirty_data_buffers(struct inode *inode,
 
 		lock_page(page);
 		if (!page_has_buffers(page))
-			create_empty_buffers(page, 1 << inode->i_blkbits, 0);
+			create_empty_buffers(page, i_blocksize(inode), 0);
 		unlock_page(page);
 
 		bh = head = page_buffers(page);
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index c5c5b9748ea3..f2961b13e8c5 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -599,7 +599,7 @@ int ocfs2_map_page_blocks(struct page *page, u64 *p_blkno,
 	int ret = 0;
 	struct buffer_head *head, *bh, *wait[2], **wait_bh = wait;
 	unsigned int block_end, block_start;
-	unsigned int bsize = 1 << inode->i_blkbits;
+	unsigned int bsize = i_blocksize(inode);
 
 	if (!page_has_buffers(page))
 		create_empty_buffers(page, bsize, 0);
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 000c234d7bbd..0db6f83fdea1 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -808,7 +808,7 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from,
 	/* We know that zero_from is block aligned */
 	for (block_start = zero_from; block_start < zero_to;
 	     block_start = block_end) {
-		block_end = block_start + (1 << inode->i_blkbits);
+		block_end = block_start + i_blocksize(inode);
 
 		/*
 		 * block_start is block-aligned.  Bump it by one to force
diff --git a/fs/orangefs/orangefs-utils.c b/fs/orangefs/orangefs-utils.c
index 06af81f71e10..9b96b99539d6 100644
--- a/fs/orangefs/orangefs-utils.c
+++ b/fs/orangefs/orangefs-utils.c
@@ -306,7 +306,7 @@ int orangefs_inode_getattr(struct inode *inode, int new, int bypass)
 		break;
 	case S_IFDIR:
 		inode->i_size = PAGE_SIZE;
-		orangefs_inode->blksize = (1 << inode->i_blkbits);
+		orangefs_inode->blksize = i_blocksize(inode);
 		spin_lock(&inode->i_lock);
 		inode_set_bytes(inode, inode->i_size);
 		spin_unlock(&inode->i_lock);
@@ -316,7 +316,7 @@ int orangefs_inode_getattr(struct inode *inode, int new, int bypass)
 		if (new) {
 			inode->i_size = (loff_t)strlen(new_op->
 			    downcall.resp.getattr.link_target);
-			orangefs_inode->blksize = (1 << inode->i_blkbits);
+			orangefs_inode->blksize = i_blocksize(inode);
 			ret = strscpy(orangefs_inode->link_target,
 			    new_op->downcall.resp.getattr.link_target,
 			    ORANGEFS_NAME_MAX);
diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c
index 2f8c5c9bdaf6..b396eb09f288 100644
--- a/fs/reiserfs/file.c
+++ b/fs/reiserfs/file.c
@@ -189,7 +189,7 @@ int reiserfs_commit_page(struct inode *inode, struct page *page,
 	int ret = 0;
 
 	th.t_trans_id = 0;
-	blocksize = 1 << inode->i_blkbits;
+	blocksize = i_blocksize(inode);
 
 	if (logit) {
 		reiserfs_write_lock(s);
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index 58b2dedb2a3a..bd4c727f4610 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -524,7 +524,7 @@ static int reiserfs_get_blocks_direct_io(struct inode *inode,
 	 * referenced in convert_tail_for_hole() that may be called from
 	 * reiserfs_get_block()
 	 */
-	bh_result->b_size = (1 << inode->i_blkbits);
+	bh_result->b_size = i_blocksize(inode);
 
 	ret = reiserfs_get_block(inode, iblock, bh_result,
 				 create | GET_BLOCK_NO_DANGLE);
diff --git a/fs/stat.c b/fs/stat.c
index bc045c7994e1..068fdbcc9e26 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -31,7 +31,7 @@ void generic_fillattr(struct inode *inode, struct kstat *stat)
 	stat->atime = inode->i_atime;
 	stat->mtime = inode->i_mtime;
 	stat->ctime = inode->i_ctime;
-	stat->blksize = (1 << inode->i_blkbits);
+	stat->blksize = i_blocksize(inode);
 	stat->blocks = inode->i_blocks;
 }
 
@@ -454,6 +454,7 @@ void __inode_add_bytes(struct inode *inode, loff_t bytes)
 		inode->i_bytes -= 512;
 	}
 }
+EXPORT_SYMBOL(__inode_add_bytes);
 
 void inode_add_bytes(struct inode *inode, loff_t bytes)
 {
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index aad46401ede5..129b18a29c8f 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -1214,7 +1214,7 @@ int udf_setsize(struct inode *inode, loff_t newsize)
 {
 	int err;
 	struct udf_inode_info *iinfo;
-	int bsize = 1 << inode->i_blkbits;
+	int bsize = i_blocksize(inode);
 
 	if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
 	      S_ISLNK(inode->i_mode)))
diff --git a/fs/ufs/balloc.c b/fs/ufs/balloc.c
index 67e085d591d8..a81b97013021 100644
--- a/fs/ufs/balloc.c
+++ b/fs/ufs/balloc.c
@@ -81,7 +81,8 @@ void ufs_free_fragments(struct inode *inode, u64 fragment, unsigned count)
 			ufs_error (sb, "ufs_free_fragments",
 				   "bit already cleared for fragment %u", i);
 	}
-	
+
+	inode_sub_bytes(inode, count << uspi->s_fshift);
 	fs32_add(sb, &ucg->cg_cs.cs_nffree, count);
 	uspi->cs_total.cs_nffree += count;
 	fs32_add(sb, &UFS_SB(sb)->fs_cs(cgno).cs_nffree, count);
@@ -183,6 +184,7 @@ void ufs_free_blocks(struct inode *inode, u64 fragment, unsigned count)
 			ufs_error(sb, "ufs_free_blocks", "freeing free fragment");
 		}
 		ubh_setblock(UCPI_UBH(ucpi), ucpi->c_freeoff, blkno);
+		inode_sub_bytes(inode, uspi->s_fpb << uspi->s_fshift);
 		if ((UFS_SB(sb)->s_flags & UFS_CG_MASK) == UFS_CG_44BSD)
 			ufs_clusteracct (sb, ucpi, blkno, 1);
 
@@ -494,6 +496,20 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment,
 	return 0;
 }		
 
+static bool try_add_frags(struct inode *inode, unsigned frags)
+{
+	unsigned size = frags * i_blocksize(inode);
+	spin_lock(&inode->i_lock);
+	__inode_add_bytes(inode, size);
+	if (unlikely((u32)inode->i_blocks != inode->i_blocks)) {
+		__inode_sub_bytes(inode, size);
+		spin_unlock(&inode->i_lock);
+		return false;
+	}
+	spin_unlock(&inode->i_lock);
+	return true;
+}
+
 static u64 ufs_add_fragments(struct inode *inode, u64 fragment,
 			     unsigned oldcount, unsigned newcount)
 {
@@ -530,6 +546,9 @@ static u64 ufs_add_fragments(struct inode *inode, u64 fragment,
 	for (i = oldcount; i < newcount; i++)
 		if (ubh_isclr (UCPI_UBH(ucpi), ucpi->c_freeoff, fragno + i))
 			return 0;
+
+	if (!try_add_frags(inode, count))
+		return 0;
 	/*
 	 * Block can be extended
 	 */
@@ -647,6 +666,7 @@ static u64 ufs_alloc_fragments(struct inode *inode, unsigned cgno,
 			ubh_setbit (UCPI_UBH(ucpi), ucpi->c_freeoff, goal + i);
 		i = uspi->s_fpb - count;
 
+		inode_sub_bytes(inode, i << uspi->s_fshift);
 		fs32_add(sb, &ucg->cg_cs.cs_nffree, i);
 		uspi->cs_total.cs_nffree += i;
 		fs32_add(sb, &UFS_SB(sb)->fs_cs(cgno).cs_nffree, i);
@@ -657,6 +677,8 @@ static u64 ufs_alloc_fragments(struct inode *inode, unsigned cgno,
 	result = ufs_bitmap_search (sb, ucpi, goal, allocsize);
 	if (result == INVBLOCK)
 		return 0;
+	if (!try_add_frags(inode, count))
+		return 0;
 	for (i = 0; i < count; i++)
 		ubh_clrbit (UCPI_UBH(ucpi), ucpi->c_freeoff, result + i);
 	
@@ -716,6 +738,8 @@ static u64 ufs_alloccg_block(struct inode *inode,
 		return INVBLOCK;
 	ucpi->c_rotor = result;
 gotit:
+	if (!try_add_frags(inode, uspi->s_fpb))
+		return 0;
 	blkno = ufs_fragstoblks(result);
 	ubh_clrblock (UCPI_UBH(ucpi), ucpi->c_freeoff, blkno);
 	if ((UFS_SB(sb)->s_flags & UFS_CG_MASK) == UFS_CG_44BSD)
diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c
index 190d64be22ed..a2760a2869f4 100644
--- a/fs/ufs/inode.c
+++ b/fs/ufs/inode.c
@@ -235,7 +235,8 @@ ufs_extend_tail(struct inode *inode, u64 writes_to,
 
 	p = ufs_get_direct_data_ptr(uspi, ufsi, block);
 	tmp = ufs_new_fragments(inode, p, lastfrag, ufs_data_ptr_to_cpu(sb, p),
-				new_size, err, locked_page);
+				new_size - (lastfrag & uspi->s_fpbmask), err,
+				locked_page);
 	return tmp != 0;
 }
 
@@ -284,7 +285,7 @@ ufs_inode_getfrag(struct inode *inode, unsigned index,
 			goal += uspi->s_fpb;
 	}
 	tmp = ufs_new_fragments(inode, p, ufs_blknum(new_fragment),
-				goal, uspi->s_fpb, err, locked_page);
+				goal, nfrags, err, locked_page);
 
 	if (!tmp) {
 		*err = -ENOSPC;
@@ -402,7 +403,9 @@ static int ufs_getfrag_block(struct inode *inode, sector_t fragment, struct buff
 
 	if (!create) {
 		phys64 = ufs_frag_map(inode, offsets, depth);
-		goto out;
+		if (phys64)
+			map_bh(bh_result, sb, phys64 + frag);
+		return 0;
 	}
 
         /* This code entered only while writing ....? */
diff --git a/fs/ufs/super.c b/fs/ufs/super.c
index f3469ad0fef2..351162ff1bfd 100644
--- a/fs/ufs/super.c
+++ b/fs/ufs/super.c
@@ -746,6 +746,23 @@ static void ufs_put_super(struct super_block *sb)
 	return;
 }
 
+static u64 ufs_max_bytes(struct super_block *sb)
+{
+	struct ufs_sb_private_info *uspi = UFS_SB(sb)->s_uspi;
+	int bits = uspi->s_apbshift;
+	u64 res;
+
+	if (bits > 21)
+		res = ~0ULL;
+	else
+		res = UFS_NDADDR + (1LL << bits) + (1LL << (2*bits)) +
+			(1LL << (3*bits));
+
+	if (res >= (MAX_LFS_FILESIZE >> uspi->s_bshift))
+		return MAX_LFS_FILESIZE;
+	return res << uspi->s_bshift;
+}
+
 static int ufs_fill_super(struct super_block *sb, void *data, int silent)
 {
 	struct ufs_sb_info * sbi;
@@ -1211,6 +1228,7 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent)
 			    "fast symlink size (%u)\n", uspi->s_maxsymlinklen);
 		uspi->s_maxsymlinklen = maxsymlen;
 	}
+	sb->s_maxbytes = ufs_max_bytes(sb);
 	sb->s_max_links = UFS_LINK_MAX;
 
 	inode = ufs_iget(sb, UFS_ROOTINO);
diff --git a/fs/ufs/util.h b/fs/ufs/util.h
index b7fbf53dbc81..398019fb1448 100644
--- a/fs/ufs/util.h
+++ b/fs/ufs/util.h
@@ -473,15 +473,19 @@ static inline unsigned _ubh_find_last_zero_bit_(
 static inline int _ubh_isblockset_(struct ufs_sb_private_info * uspi,
 	struct ufs_buffer_head * ubh, unsigned begin, unsigned block)
 {
+	u8 mask;
 	switch (uspi->s_fpb) {
 	case 8:
 	    	return (*ubh_get_addr (ubh, begin + block) == 0xff);
 	case 4:
-		return (*ubh_get_addr (ubh, begin + (block >> 1)) == (0x0f << ((block & 0x01) << 2)));
+		mask = 0x0f << ((block & 0x01) << 2);
+		return (*ubh_get_addr (ubh, begin + (block >> 1)) & mask) == mask;
 	case 2:
-		return (*ubh_get_addr (ubh, begin + (block >> 2)) == (0x03 << ((block & 0x03) << 1)));
+		mask = 0x03 << ((block & 0x03) << 1);
+		return (*ubh_get_addr (ubh, begin + (block >> 2)) & mask) == mask;
 	case 1:
-		return (*ubh_get_addr (ubh, begin + (block >> 3)) == (0x01 << (block & 0x07)));
+		mask = 0x01 << (block & 0x07);
+		return (*ubh_get_addr (ubh, begin + (block >> 3)) & mask) == mask;
 	}
 	return 0;	
 }
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 6df0a7ce3e8a..578981412615 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -108,9 +108,9 @@ xfs_finish_page_writeback(
 	unsigned int		bsize;
 
 	ASSERT(bvec->bv_offset < PAGE_SIZE);
-	ASSERT((bvec->bv_offset & ((1 << inode->i_blkbits) - 1)) == 0);
+	ASSERT((bvec->bv_offset & (i_blocksize(inode) - 1)) == 0);
 	ASSERT(end < PAGE_SIZE);
-	ASSERT((bvec->bv_len & ((1 << inode->i_blkbits) - 1)) == 0);
+	ASSERT((bvec->bv_len & (i_blocksize(inode) - 1)) == 0);
 
 	bh = head = page_buffers(bvec->bv_page);
 
@@ -349,7 +349,7 @@ xfs_map_blocks(
 {
 	struct xfs_inode	*ip = XFS_I(inode);
 	struct xfs_mount	*mp = ip->i_mount;
-	ssize_t			count = 1 << inode->i_blkbits;
+	ssize_t			count = i_blocksize(inode);
 	xfs_fileoff_t		offset_fsb, end_fsb;
 	int			error = 0;
 	int			bmapi_flags = XFS_BMAPI_ENTIRE;
@@ -759,7 +759,7 @@ xfs_aops_discard_page(
 			break;
 		}
 next_buffer:
-		offset += 1 << inode->i_blkbits;
+		offset += i_blocksize(inode);
 
 	} while ((bh = bh->b_this_page) != head);
 
@@ -847,7 +847,7 @@ xfs_writepage_map(
 	LIST_HEAD(submit_list);
 	struct xfs_ioend	*ioend, *next;
 	struct buffer_head	*bh, *head;
-	ssize_t			len = 1 << inode->i_blkbits;
+	ssize_t			len = i_blocksize(inode);
 	int			error = 0;
 	int			count = 0;
 	int			uptodate = 1;
@@ -1250,7 +1250,7 @@ xfs_map_trim_size(
 	    offset + mapping_size >= i_size_read(inode)) {
 		/* limit mapping to block that spans EOF */
 		mapping_size = roundup_64(i_size_read(inode) - offset,
-					  1 << inode->i_blkbits);
+					  i_blocksize(inode));
 	}
 	if (mapping_size > LONG_MAX)
 		mapping_size = LONG_MAX;
@@ -1286,7 +1286,7 @@ __xfs_get_blocks(
 		return -EIO;
 
 	offset = (xfs_off_t)iblock << inode->i_blkbits;
-	ASSERT(bh_result->b_size >= (1 << inode->i_blkbits));
+	ASSERT(bh_result->b_size >= i_blocksize(inode));
 	size = bh_result->b_size;
 
 	if (!create && offset >= i_size_read(inode))
@@ -1634,7 +1634,7 @@ xfs_vm_set_page_dirty(
 			if (offset < end_offset)
 				set_buffer_dirty(bh);
 			bh = bh->b_this_page;
-			offset += 1 << inode->i_blkbits;
+			offset += i_blocksize(inode);
 		} while (bh != head);
 	}
 	/*
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index a90ec3fad69f..df206cfc21f7 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -823,7 +823,7 @@ xfs_file_fallocate(
 		if (error)
 			goto out_unlock;
 	} else if (mode & FALLOC_FL_COLLAPSE_RANGE) {
-		unsigned blksize_mask = (1 << inode->i_blkbits) - 1;
+		unsigned int blksize_mask = i_blocksize(inode) - 1;
 
 		if (offset & blksize_mask || len & blksize_mask) {
 			error = -EINVAL;
@@ -845,7 +845,7 @@ xfs_file_fallocate(
 		if (error)
 			goto out_unlock;
 	} else if (mode & FALLOC_FL_INSERT_RANGE) {
-		unsigned blksize_mask = (1 << inode->i_blkbits) - 1;
+		unsigned int blksize_mask = i_blocksize(inode) - 1;
 
 		new_size = i_size_read(inode) + len;
 		if (offset & blksize_mask || len & blksize_mask) {
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 5b17de62c962..6fb1c34cf805 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -46,6 +46,7 @@ enum {
 	CSS_ONLINE	= (1 << 1), /* between ->css_online() and ->css_offline() */
 	CSS_RELEASED	= (1 << 2), /* refcnt reached zero, released */
 	CSS_VISIBLE	= (1 << 3), /* css is visible to userland */
+	CSS_DYING	= (1 << 4), /* css is dying */
 };
 
 /* bits in struct cgroup flags field */
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 307ae63ef262..7620a8bc0493 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -344,6 +344,26 @@ static inline bool css_tryget_online(struct cgroup_subsys_state *css)
 }
 
 /**
+ * css_is_dying - test whether the specified css is dying
+ * @css: target css
+ *
+ * Test whether @css is in the process of offlining or already offline.  In
+ * most cases, ->css_online() and ->css_offline() callbacks should be
+ * enough; however, the actual offline operations are RCU delayed and this
+ * test returns %true also when @css is scheduled to be offlined.
+ *
+ * This is useful, for example, when the use case requires synchronous
+ * behavior with respect to cgroup removal.  cgroup removal schedules css
+ * offlining but the css can seem alive while the operation is being
+ * delayed.  If the delay affects user visible semantics, this test can be
+ * used to resolve the situation.
+ */
+static inline bool css_is_dying(struct cgroup_subsys_state *css)
+{
+	return !(css->flags & CSS_NO_REF) && percpu_ref_is_dying(&css->refcnt);
+}
+
+/**
  * css_put - put a css reference
  * @css: target css
  *
diff --git a/include/linux/fs.h b/include/linux/fs.h
index dc0478c07b2a..2f63d44368bd 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -705,6 +705,11 @@ struct inode {
 	void			*i_private; /* fs or device private pointer */
 };
 
+static inline unsigned int i_blocksize(const struct inode *node)
+{
+	return (1 << node->i_blkbits);
+}
+
 static inline int inode_unhashed(struct inode *inode)
 {
 	return hlist_unhashed(&inode->i_hash);
diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index e0e539321ab9..d53a23100401 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -53,7 +53,8 @@ extern int ptrace_request(struct task_struct *child, long request,
 			  unsigned long addr, unsigned long data);
 extern void ptrace_notify(int exit_code);
 extern void __ptrace_link(struct task_struct *child,
-			  struct task_struct *new_parent);
+			  struct task_struct *new_parent,
+			  const struct cred *ptracer_cred);
 extern void __ptrace_unlink(struct task_struct *child);
 extern void exit_ptrace(struct task_struct *tracer, struct list_head *dead);
 #define PTRACE_MODE_READ	0x01
@@ -205,7 +206,7 @@ static inline void ptrace_init_task(struct task_struct *child, bool ptrace)
 
 	if (unlikely(ptrace) && current->ptrace) {
 		child->ptrace = current->ptrace;
-		__ptrace_link(child, current->parent);
+		__ptrace_link(child, current->parent, current->ptracer_cred);
 
 		if (child->ptrace & PT_SEIZED)
 			task_set_jobctl_pending(child, JOBCTL_TRAP_STOP);
@@ -214,6 +215,8 @@ static inline void ptrace_init_task(struct task_struct *child, bool ptrace)
 
 		set_tsk_thread_flag(child, TIF_SIGPENDING);
 	}
+	else
+		child->ptracer_cred = NULL;
 }
 
 /**
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 7f15f95625e7..91afb4aadaa6 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -1001,6 +1001,7 @@ int inet6_hash_connect(struct inet_timewait_death_row *death_row,
  */
 extern const struct proto_ops inet6_stream_ops;
 extern const struct proto_ops inet6_dgram_ops;
+extern const struct proto_ops inet6_sockraw_ops;
 
 struct group_source_req;
 struct group_filter;
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index a3d2aad2443f..1fde8eec9529 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -5407,6 +5407,11 @@ static void kill_css(struct cgroup_subsys_state *css)
 {
 	lockdep_assert_held(&cgroup_mutex);
 
+	if (css->flags & CSS_DYING)
+		return;
+
+	css->flags |= CSS_DYING;
+
 	/*
 	 * This must happen before css is disassociated with its cgroup.
 	 * See seq_css() for details.
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 99c6c568bc55..8f52977aad59 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -1765,13 +1765,13 @@ static ssize_t write_cpuhp_target(struct device *dev,
 	ret = !sp->name || sp->cant_stop ? -EINVAL : 0;
 	mutex_unlock(&cpuhp_state_mutex);
 	if (ret)
-		return ret;
+		goto out;
 
 	if (st->state < target)
 		ret = do_cpu_up(dev->id, target);
 	else
 		ret = do_cpu_down(dev->id, target);
-
+out:
 	unlock_device_hotplug();
 	return ret ? ret : count;
 }
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 29f815d2ef7e..24d175d2b62d 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -174,9 +174,9 @@ typedef enum {
 } cpuset_flagbits_t;
 
 /* convenient tests for these bits */
-static inline bool is_cpuset_online(const struct cpuset *cs)
+static inline bool is_cpuset_online(struct cpuset *cs)
 {
-	return test_bit(CS_ONLINE, &cs->flags);
+	return test_bit(CS_ONLINE, &cs->flags) && !css_is_dying(&cs->css);
 }
 
 static inline int is_cpu_exclusive(const struct cpuset *cs)
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 07c0dc806dfc..11cc1d83c770 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7062,6 +7062,21 @@ static void perf_log_itrace_start(struct perf_event *event)
 	perf_output_end(&handle);
 }
 
+static bool sample_is_allowed(struct perf_event *event, struct pt_regs *regs)
+{
+	/*
+	 * Due to interrupt latency (AKA "skid"), we may enter the
+	 * kernel before taking an overflow, even if the PMU is only
+	 * counting user events.
+	 * To avoid leaking information to userspace, we must always
+	 * reject kernel samples when exclude_kernel is set.
+	 */
+	if (event->attr.exclude_kernel && !user_mode(regs))
+		return false;
+
+	return true;
+}
+
 /*
  * Generic event overflow handling, sampling.
  */
@@ -7109,6 +7124,12 @@ static int __perf_event_overflow(struct perf_event *event,
 	}
 
 	/*
+	 * For security, drop the skid kernel samples if necessary.
+	 */
+	if (!sample_is_allowed(event, regs))
+		return ret;
+
+	/*
 	 * XXX event_limit might not quite work as expected on inherited
 	 * events
 	 */
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index a5caecef88be..f39a7be98fc1 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -57,19 +57,25 @@ int ptrace_access_vm(struct task_struct *tsk, unsigned long addr,
 }
 
 
+void __ptrace_link(struct task_struct *child, struct task_struct *new_parent,
+		   const struct cred *ptracer_cred)
+{
+	BUG_ON(!list_empty(&child->ptrace_entry));
+	list_add(&child->ptrace_entry, &new_parent->ptraced);
+	child->parent = new_parent;
+	child->ptracer_cred = get_cred(ptracer_cred);
+}
+
 /*
  * ptrace a task: make the debugger its new parent and
  * move it to the ptrace list.
  *
  * Must be called with the tasklist lock write-held.
  */
-void __ptrace_link(struct task_struct *child, struct task_struct *new_parent)
+static void ptrace_link(struct task_struct *child, struct task_struct *new_parent)
 {
-	BUG_ON(!list_empty(&child->ptrace_entry));
-	list_add(&child->ptrace_entry, &new_parent->ptraced);
-	child->parent = new_parent;
 	rcu_read_lock();
-	child->ptracer_cred = get_cred(__task_cred(new_parent));
+	__ptrace_link(child, new_parent, __task_cred(new_parent));
 	rcu_read_unlock();
 }
 
@@ -383,7 +389,7 @@ static int ptrace_attach(struct task_struct *task, long request,
 		flags |= PT_SEIZED;
 	task->ptrace = flags;
 
-	__ptrace_link(task, current);
+	ptrace_link(task, current);
 
 	/* SEIZE doesn't trap tracee on attach */
 	if (!seize)
@@ -456,7 +462,7 @@ static int ptrace_traceme(void)
 		 */
 		if (!ret && !(current->real_parent->flags & PF_EXITING)) {
 			current->ptrace = PT_PTRACED;
-			__ptrace_link(current, current->real_parent);
+			ptrace_link(current, current->real_parent);
 		}
 	}
 	write_unlock_irq(&tasklist_lock);
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 69e06898997d..cb771c76682e 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -32,6 +32,7 @@ struct sugov_policy {
 	u64 last_freq_update_time;
 	s64 freq_update_delay_ns;
 	unsigned int next_freq;
+	unsigned int cached_raw_freq;
 
 	/* The next fields are only needed if fast switch cannot be used. */
 	struct irq_work irq_work;
@@ -46,7 +47,6 @@ struct sugov_cpu {
 	struct update_util_data update_util;
 	struct sugov_policy *sg_policy;
 
-	unsigned int cached_raw_freq;
 	unsigned long iowait_boost;
 	unsigned long iowait_boost_max;
 	u64 last_update;
@@ -140,9 +140,9 @@ static unsigned int get_next_freq(struct sugov_cpu *sg_cpu, unsigned long util,
 
 	freq = (freq + (freq >> 2)) * util / max;
 
-	if (freq == sg_cpu->cached_raw_freq && sg_policy->next_freq != UINT_MAX)
+	if (freq == sg_policy->cached_raw_freq && sg_policy->next_freq != UINT_MAX)
 		return sg_policy->next_freq;
-	sg_cpu->cached_raw_freq = freq;
+	sg_policy->cached_raw_freq = freq;
 	return cpufreq_driver_resolve_freq(policy, freq);
 }
 
@@ -502,25 +502,19 @@ static int sugov_start(struct cpufreq_policy *policy)
 	sg_policy->next_freq = UINT_MAX;
 	sg_policy->work_in_progress = false;
 	sg_policy->need_freq_update = false;
+	sg_policy->cached_raw_freq = 0;
 
 	for_each_cpu(cpu, policy->cpus) {
 		struct sugov_cpu *sg_cpu = &per_cpu(sugov_cpu, cpu);
 
+		memset(sg_cpu, 0, sizeof(*sg_cpu));
 		sg_cpu->sg_policy = sg_policy;
-		if (policy_is_shared(policy)) {
-			sg_cpu->util = 0;
-			sg_cpu->max = 0;
-			sg_cpu->flags = SCHED_CPUFREQ_RT;
-			sg_cpu->last_update = 0;
-			sg_cpu->cached_raw_freq = 0;
-			sg_cpu->iowait_boost = 0;
-			sg_cpu->iowait_boost_max = policy->cpuinfo.max_freq;
-			cpufreq_add_update_util_hook(cpu, &sg_cpu->update_util,
-						     sugov_update_shared);
-		} else {
-			cpufreq_add_update_util_hook(cpu, &sg_cpu->update_util,
-						     sugov_update_single);
-		}
+		sg_cpu->flags = SCHED_CPUFREQ_RT;
+		sg_cpu->iowait_boost_max = policy->cpuinfo.max_freq;
+		cpufreq_add_update_util_hook(cpu, &sg_cpu->update_util,
+					     policy_is_shared(policy) ?
+							sugov_update_shared :
+							sugov_update_single);
 	}
 	return 0;
 }
diff --git a/lib/test_user_copy.c b/lib/test_user_copy.c
index 0ecef3e4690e..5e6db6b1e3bd 100644
--- a/lib/test_user_copy.c
+++ b/lib/test_user_copy.c
@@ -58,7 +58,9 @@ static int __init test_user_copy_init(void)
 	usermem = (char __user *)user_addr;
 	bad_usermem = (char *)user_addr;
 
-	/* Legitimate usage: none of these should fail. */
+	/*
+	 * Legitimate usage: none of these copies should fail.
+	 */
 	ret |= test(copy_from_user(kmem, usermem, PAGE_SIZE),
 		    "legitimate copy_from_user failed");
 	ret |= test(copy_to_user(usermem, kmem, PAGE_SIZE),
@@ -68,19 +70,33 @@ static int __init test_user_copy_init(void)
 	ret |= test(put_user(value, (unsigned long __user *)usermem),
 		    "legitimate put_user failed");
 
-	/* Invalid usage: none of these should succeed. */
+	/*
+	 * Invalid usage: none of these copies should succeed.
+	 */
+
+	/* Reject kernel-to-kernel copies through copy_from_user(). */
 	ret |= test(!copy_from_user(kmem, (char __user *)(kmem + PAGE_SIZE),
 				    PAGE_SIZE),
 		    "illegal all-kernel copy_from_user passed");
+
+#if 0
+	/*
+	 * When running with SMAP/PAN/etc, this will Oops the kernel
+	 * due to the zeroing of userspace memory on failure. This needs
+	 * to be tested in LKDTM instead, since this test module does not
+	 * expect to explode.
+	 */
 	ret |= test(!copy_from_user(bad_usermem, (char __user *)kmem,
 				    PAGE_SIZE),
 		    "illegal reversed copy_from_user passed");
+#endif
 	ret |= test(!copy_to_user((char __user *)kmem, kmem + PAGE_SIZE,
 				  PAGE_SIZE),
 		    "illegal all-kernel copy_to_user passed");
 	ret |= test(!copy_to_user((char __user *)kmem, bad_usermem,
 				  PAGE_SIZE),
 		    "illegal reversed copy_to_user passed");
+
 	ret |= test(!get_user(value, (unsigned long __user *)kmem),
 		    "illegal get_user passed");
 	ret |= test(!put_user(value, (unsigned long __user *)kmem),
diff --git a/mm/truncate.c b/mm/truncate.c
index 8d8c62d89e6d..9c809e7d73c3 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -753,7 +753,7 @@ EXPORT_SYMBOL(truncate_setsize);
  */
 void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to)
 {
-	int bsize = 1 << inode->i_blkbits;
+	int bsize = i_blocksize(inode);
 	loff_t rounded_from;
 	struct page *page;
 	pgoff_t index;
diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c
index 5a782f543aff..16b5aa9a91f1 100644
--- a/net/bridge/br_stp_if.c
+++ b/net/bridge/br_stp_if.c
@@ -185,7 +185,8 @@ static void br_stp_start(struct net_bridge *br)
 		br_debug(br, "using kernel STP\n");
 
 		/* To start timers on any ports left in blocking */
-		mod_timer(&br->hello_timer, jiffies + br->hello_time);
+		if (br->dev->flags & IFF_UP)
+			mod_timer(&br->hello_timer, jiffies + br->hello_time);
 		br_port_state_selection(br);
 	}
 
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 971b9471d427..f60fe82c2c1e 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1015,7 +1015,7 @@ static struct inet_protosw inetsw_array[] =
 		.type =       SOCK_DGRAM,
 		.protocol =   IPPROTO_ICMP,
 		.prot =       &ping_prot,
-		.ops =        &inet_dgram_ops,
+		.ops =        &inet_sockraw_ops,
 		.flags =      INET_PROTOSW_REUSE,
        },
 
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index baea5df43598..0cdbea9b9288 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -179,6 +179,7 @@ void tcp_init_congestion_control(struct sock *sk)
 {
 	const struct inet_connection_sock *icsk = inet_csk(sk);
 
+	tcp_sk(sk)->prior_ssthresh = 0;
 	if (icsk->icsk_ca_ops->init)
 		icsk->icsk_ca_ops->init(sk);
 	if (tcp_ca_needs_ecn(sk))
diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c
index 37ac9de713c6..8d772fea1dde 100644
--- a/net/ipv6/calipso.c
+++ b/net/ipv6/calipso.c
@@ -1319,7 +1319,7 @@ static int calipso_skbuff_setattr(struct sk_buff *skb,
 	struct ipv6hdr *ip6_hdr;
 	struct ipv6_opt_hdr *hop;
 	unsigned char buf[CALIPSO_MAX_BUFFER];
-	int len_delta, new_end, pad;
+	int len_delta, new_end, pad, payload;
 	unsigned int start, end;
 
 	ip6_hdr = ipv6_hdr(skb);
@@ -1346,6 +1346,8 @@ static int calipso_skbuff_setattr(struct sk_buff *skb,
 	if (ret_val < 0)
 		return ret_val;
 
+	ip6_hdr = ipv6_hdr(skb); /* Reset as skb_cow() may have moved it */
+
 	if (len_delta) {
 		if (len_delta > 0)
 			skb_push(skb, len_delta);
@@ -1355,6 +1357,8 @@ static int calipso_skbuff_setattr(struct sk_buff *skb,
 			sizeof(*ip6_hdr) + start);
 		skb_reset_network_header(skb);
 		ip6_hdr = ipv6_hdr(skb);
+		payload = ntohs(ip6_hdr->payload_len);
+		ip6_hdr->payload_len = htons(payload + len_delta);
 	}
 
 	hop = (struct ipv6_opt_hdr *)(ip6_hdr + 1);
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 013086b248e2..424fbe1f8978 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -116,8 +116,10 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 
 		if (udpfrag) {
 			int err = ip6_find_1stfragopt(skb, &prevhdr);
-			if (err < 0)
+			if (err < 0) {
+				kfree_skb_list(segs);
 				return ERR_PTR(err);
+			}
 			fptr = (struct frag_hdr *)((u8 *)ipv6h + err);
 			fptr->frag_off = htons(offset);
 			if (skb->next)
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index 66e2d9dfc43a..982868193dbb 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -198,7 +198,7 @@ static struct inet_protosw pingv6_protosw = {
 	.type =      SOCK_DGRAM,
 	.protocol =  IPPROTO_ICMPV6,
 	.prot =      &pingv6_prot,
-	.ops =       &inet6_dgram_ops,
+	.ops =       &inet6_sockraw_ops,
 	.flags =     INET_PROTOSW_REUSE,
 };
 
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 1a2fe5c3a366..71ffa526cb23 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -1330,7 +1330,7 @@ void raw6_proc_exit(void)
 #endif	/* CONFIG_PROC_FS */
 
 /* Same as inet6_dgram_ops, sans udp_poll.  */
-static const struct proto_ops inet6_sockraw_ops = {
+const struct proto_ops inet6_sockraw_ops = {
 	.family		   = PF_INET6,
 	.owner		   = THIS_MODULE,
 	.release	   = inet6_release,
diff --git a/net/ipv6/xfrm6_mode_ro.c b/net/ipv6/xfrm6_mode_ro.c
index 0e015906f9ca..07d36573f50b 100644
--- a/net/ipv6/xfrm6_mode_ro.c
+++ b/net/ipv6/xfrm6_mode_ro.c
@@ -47,6 +47,8 @@ static int xfrm6_ro_output(struct xfrm_state *x, struct sk_buff *skb)
 	iph = ipv6_hdr(skb);
 
 	hdr_len = x->type->hdr_offset(x, skb, &prevhdr);
+	if (hdr_len < 0)
+		return hdr_len;
 	skb_set_mac_header(skb, (prevhdr - x->props.header_len) - skb->data);
 	skb_set_network_header(skb, -x->props.header_len);
 	skb->transport_header = skb->network_header + hdr_len;
diff --git a/net/ipv6/xfrm6_mode_transport.c b/net/ipv6/xfrm6_mode_transport.c
index 4e344105b3fd..1d3bbe6e1183 100644
--- a/net/ipv6/xfrm6_mode_transport.c
+++ b/net/ipv6/xfrm6_mode_transport.c
@@ -28,6 +28,8 @@ static int xfrm6_transport_output(struct xfrm_state *x, struct sk_buff *skb)
 	iph = ipv6_hdr(skb);
 
 	hdr_len = x->type->hdr_offset(x, skb, &prevhdr);
+	if (hdr_len < 0)
+		return hdr_len;
 	skb_set_mac_header(skb, (prevhdr - x->props.header_len) - skb->data);
 	skb_set_network_header(skb, -x->props.header_len);
 	skb->transport_header = skb->network_header + hdr_len;
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index 36493a7cae88..93820e0d8814 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -118,17 +118,17 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set,
 		else if (d > 0)
 			p = &parent->rb_right;
 		else {
-			if (nft_set_elem_active(&rbe->ext, genmask)) {
-				if (nft_rbtree_interval_end(rbe) &&
-				    !nft_rbtree_interval_end(new))
-					p = &parent->rb_left;
-				else if (!nft_rbtree_interval_end(rbe) &&
-					 nft_rbtree_interval_end(new))
-					p = &parent->rb_right;
-				else {
-					*ext = &rbe->ext;
-					return -EEXIST;
-				}
+			if (nft_rbtree_interval_end(rbe) &&
+			    !nft_rbtree_interval_end(new)) {
+				p = &parent->rb_left;
+			} else if (!nft_rbtree_interval_end(rbe) &&
+				   nft_rbtree_interval_end(new)) {
+				p = &parent->rb_right;
+			} else if (nft_set_elem_active(&rbe->ext, genmask)) {
+				*ext = &rbe->ext;
+				return -EEXIST;
+			} else {
+				p = &parent->rb_left;
 			}
 		}
 	}
diff --git a/security/keys/encrypted-keys/encrypted.c b/security/keys/encrypted-keys/encrypted.c
index 17a06105ccb6..56c458dd16a2 100644
--- a/security/keys/encrypted-keys/encrypted.c
+++ b/security/keys/encrypted-keys/encrypted.c
@@ -480,12 +480,9 @@ static int derived_key_encrypt(struct encrypted_key_payload *epayload,
 	struct skcipher_request *req;
 	unsigned int encrypted_datalen;
 	u8 iv[AES_BLOCK_SIZE];
-	unsigned int padlen;
-	char pad[16];
 	int ret;
 
 	encrypted_datalen = roundup(epayload->decrypted_datalen, blksize);
-	padlen = encrypted_datalen - epayload->decrypted_datalen;
 
 	req = init_skcipher_req(derived_key, derived_keylen);
 	ret = PTR_ERR(req);
@@ -493,11 +490,10 @@ static int derived_key_encrypt(struct encrypted_key_payload *epayload,
 		goto out;
 	dump_decrypted_data(epayload);
 
-	memset(pad, 0, sizeof pad);
 	sg_init_table(sg_in, 2);
 	sg_set_buf(&sg_in[0], epayload->decrypted_data,
 		   epayload->decrypted_datalen);
-	sg_set_buf(&sg_in[1], pad, padlen);
+	sg_set_page(&sg_in[1], ZERO_PAGE(0), AES_BLOCK_SIZE, 0);
 
 	sg_init_table(sg_out, 1);
 	sg_set_buf(sg_out, epayload->encrypted_data, encrypted_datalen);
@@ -584,9 +580,14 @@ static int derived_key_decrypt(struct encrypted_key_payload *epayload,
 	struct skcipher_request *req;
 	unsigned int encrypted_datalen;
 	u8 iv[AES_BLOCK_SIZE];
-	char pad[16];
+	u8 *pad;
 	int ret;
 
+	/* Throwaway buffer to hold the unused zero padding at the end */
+	pad = kmalloc(AES_BLOCK_SIZE, GFP_KERNEL);
+	if (!pad)
+		return -ENOMEM;
+
 	encrypted_datalen = roundup(epayload->decrypted_datalen, blksize);
 	req = init_skcipher_req(derived_key, derived_keylen);
 	ret = PTR_ERR(req);
@@ -594,13 +595,12 @@ static int derived_key_decrypt(struct encrypted_key_payload *epayload,
 		goto out;
 	dump_encrypted_data(epayload, encrypted_datalen);
 
-	memset(pad, 0, sizeof pad);
 	sg_init_table(sg_in, 1);
 	sg_init_table(sg_out, 2);
 	sg_set_buf(sg_in, epayload->encrypted_data, encrypted_datalen);
 	sg_set_buf(&sg_out[0], epayload->decrypted_data,
 		   epayload->decrypted_datalen);
-	sg_set_buf(&sg_out[1], pad, sizeof pad);
+	sg_set_buf(&sg_out[1], pad, AES_BLOCK_SIZE);
 
 	memcpy(iv, epayload->iv, sizeof(iv));
 	skcipher_request_set_crypt(req, sg_in, sg_out, encrypted_datalen, iv);
@@ -612,6 +612,7 @@ static int derived_key_decrypt(struct encrypted_key_payload *epayload,
 		goto out;
 	dump_decrypted_data(epayload);
 out:
+	kfree(pad);
 	return ret;
 }
 
diff --git a/security/keys/key.c b/security/keys/key.c
index 346fbf201c22..2f4ce35ae2aa 100644
--- a/security/keys/key.c
+++ b/security/keys/key.c
@@ -962,12 +962,11 @@ int key_update(key_ref_t key_ref, const void *payload, size_t plen)
 	/* the key must be writable */
 	ret = key_permission(key_ref, KEY_NEED_WRITE);
 	if (ret < 0)
-		goto error;
+		return ret;
 
 	/* attempt to update it if supported */
-	ret = -EOPNOTSUPP;
 	if (!key->type->update)
-		goto error;
+		return -EOPNOTSUPP;
 
 	memset(&prep, 0, sizeof(prep));
 	prep.data = payload;
diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c
index dbbfd7735ce5..ada12c3e3ac4 100644
--- a/security/keys/keyctl.c
+++ b/security/keys/keyctl.c
@@ -97,7 +97,7 @@ SYSCALL_DEFINE5(add_key, const char __user *, _type,
 	/* pull the payload in if one was supplied */
 	payload = NULL;
 
-	if (_payload) {
+	if (plen) {
 		ret = -ENOMEM;
 		payload = kmalloc(plen, GFP_KERNEL | __GFP_NOWARN);
 		if (!payload) {
@@ -327,7 +327,7 @@ long keyctl_update_key(key_serial_t id,
 
 	/* pull the payload in if one was supplied */
 	payload = NULL;
-	if (_payload) {
+	if (plen) {
 		ret = -ENOMEM;
 		payload = kmalloc(plen, GFP_KERNEL);
 		if (!payload)
diff --git a/sound/core/timer.c b/sound/core/timer.c
index ad153149b231..e5ddc475dca4 100644
--- a/sound/core/timer.c
+++ b/sound/core/timer.c
@@ -1622,6 +1622,7 @@ static int snd_timer_user_tselect(struct file *file,
 	if (err < 0)
 		goto __err;
 
+	tu->qhead = tu->qtail = tu->qused = 0;
 	kfree(tu->queue);
 	tu->queue = NULL;
 	kfree(tu->tqueue);
@@ -1963,6 +1964,7 @@ static ssize_t snd_timer_user_read(struct file *file, char __user *buffer,
 
 	tu = file->private_data;
 	unit = tu->tread ? sizeof(struct snd_timer_tread) : sizeof(struct snd_timer_read);
+	mutex_lock(&tu->ioctl_lock);
 	spin_lock_irq(&tu->qlock);
 	while ((long)count - result >= unit) {
 		while (!tu->qused) {
@@ -1978,7 +1980,9 @@ static ssize_t snd_timer_user_read(struct file *file, char __user *buffer,
 			add_wait_queue(&tu->qchange_sleep, &wait);
 
 			spin_unlock_irq(&tu->qlock);
+			mutex_unlock(&tu->ioctl_lock);
 			schedule();
+			mutex_lock(&tu->ioctl_lock);
 			spin_lock_irq(&tu->qlock);
 
 			remove_wait_queue(&tu->qchange_sleep, &wait);
@@ -1998,7 +2002,6 @@ static ssize_t snd_timer_user_read(struct file *file, char __user *buffer,
 		tu->qused--;
 		spin_unlock_irq(&tu->qlock);
 
-		mutex_lock(&tu->ioctl_lock);
 		if (tu->tread) {
 			if (copy_to_user(buffer, &tu->tqueue[qhead],
 					 sizeof(struct snd_timer_tread)))
@@ -2008,7 +2011,6 @@ static ssize_t snd_timer_user_read(struct file *file, char __user *buffer,
 					 sizeof(struct snd_timer_read)))
 				err = -EFAULT;
 		}
-		mutex_unlock(&tu->ioctl_lock);
 
 		spin_lock_irq(&tu->qlock);
 		if (err < 0)
@@ -2018,6 +2020,7 @@ static ssize_t snd_timer_user_read(struct file *file, char __user *buffer,
 	}
  _error:
 	spin_unlock_irq(&tu->qlock);
+	mutex_unlock(&tu->ioctl_lock);
 	return result > 0 ? result : err;
 }
 
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index c0bbcd903261..4e3de566809c 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -2076,6 +2076,9 @@ static int soc_cleanup_card_resources(struct snd_soc_card *card)
 	list_for_each_entry(rtd, &card->rtd_list, list)
 		flush_delayed_work(&rtd->delayed_work);
 
+	/* free the ALSA card at first; this syncs with pending operations */
+	snd_card_free(card->snd_card);
+
 	/* remove and free each DAI */
 	soc_remove_dai_links(card);
 	soc_remove_pcm_runtimes(card);
@@ -2090,9 +2093,7 @@ static int soc_cleanup_card_resources(struct snd_soc_card *card)
 	if (card->remove)
 		card->remove(card);
 
-	snd_card_free(card->snd_card);
 	return 0;
-
 }
 
 /* removes a socdev */
diff --git a/virt/kvm/arm/vgic/vgic-v2.c b/virt/kvm/arm/vgic/vgic-v2.c
index 834137e7b83f..1ab58f7b5d74 100644
--- a/virt/kvm/arm/vgic/vgic-v2.c
+++ b/virt/kvm/arm/vgic/vgic-v2.c
@@ -168,6 +168,13 @@ void vgic_v2_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr)
 	if (irq->hw) {
 		val |= GICH_LR_HW;
 		val |= irq->hwintid << GICH_LR_PHYSID_CPUID_SHIFT;
+		/*
+		 * Never set pending+active on a HW interrupt, as the
+		 * pending state is kept at the physical distributor
+		 * level.
+		 */
+		if (irq->active && irq->pending)
+			val &= ~GICH_LR_PENDING_BIT;
 	} else {
 		if (irq->config == VGIC_CONFIG_LEVEL)
 			val |= GICH_LR_EOI;
diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c
index e6b03fd8c374..f1320063db28 100644
--- a/virt/kvm/arm/vgic/vgic-v3.c
+++ b/virt/kvm/arm/vgic/vgic-v3.c
@@ -151,6 +151,13 @@ void vgic_v3_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr)
 	if (irq->hw) {
 		val |= ICH_LR_HW;
 		val |= ((u64)irq->hwintid) << ICH_LR_PHYS_ID_SHIFT;
+		/*
+		 * Never set pending+active on a HW interrupt, as the
+		 * pending state is kept at the physical distributor
+		 * level.
+		 */
+		if (irq->active && irq->pending)
+			val &= ~ICH_LR_PENDING_BIT;
 	} else {
 		if (irq->config == VGIC_CONFIG_LEVEL)
 			val |= ICH_LR_EOI;