diff --git a/Makefile b/Makefile
index 72ed8ff90329..8ec52cd19526 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
 VERSION = 4
 PATCHLEVEL = 9
-SUBLEVEL = 142
+SUBLEVEL = 143
 EXTRAVERSION =
 NAME = Roaring Lionus
 
@@ -509,6 +509,39 @@ ifneq ($(filter install,$(MAKECMDGOALS)),)
         endif
 endif
 
+ifeq ($(cc-name),clang)
+ifneq ($(CROSS_COMPILE),)
+CLANG_TARGET	:= -target $(notdir $(CROSS_COMPILE:%-=%))
+GCC_TOOLCHAIN	:= $(realpath $(dir $(shell which $(LD)))/..)
+endif
+ifneq ($(GCC_TOOLCHAIN),)
+CLANG_GCC_TC	:= -gcc-toolchain $(GCC_TOOLCHAIN)
+endif
+KBUILD_CFLAGS += $(CLANG_TARGET) $(CLANG_GCC_TC)
+KBUILD_AFLAGS += $(CLANG_TARGET) $(CLANG_GCC_TC)
+KBUILD_CPPFLAGS += $(call cc-option,-Qunused-arguments,)
+KBUILD_CFLAGS += $(call cc-disable-warning, unused-variable)
+KBUILD_CFLAGS += $(call cc-disable-warning, format-invalid-specifier)
+KBUILD_CFLAGS += $(call cc-disable-warning, gnu)
+KBUILD_CFLAGS += $(call cc-disable-warning, address-of-packed-member)
+# Quiet clang warning: comparison of unsigned expression < 0 is always false
+KBUILD_CFLAGS += $(call cc-disable-warning, tautological-compare)
+# CLANG uses a _MergedGlobals as optimization, but this breaks modpost, as the
+# source of a reference will be _MergedGlobals and not on of the whitelisted names.
+# See modpost pattern 2
+KBUILD_CFLAGS += $(call cc-option, -mno-global-merge,)
+KBUILD_CFLAGS += $(call cc-option, -fcatch-undefined-behavior)
+KBUILD_CFLAGS += $(call cc-option, -no-integrated-as)
+KBUILD_AFLAGS += $(call cc-option, -no-integrated-as)
+else
+
+# These warnings generated too much noise in a regular build.
+# Use make W=1 to enable them (see scripts/Makefile.build)
+KBUILD_CFLAGS += $(call cc-disable-warning, unused-but-set-variable)
+KBUILD_CFLAGS += $(call cc-disable-warning, unused-const-variable)
+endif
+
+
 ifeq ($(mixed-targets),1)
 # ===========================================================================
 # We're called with mixed targets (*config and build targets).
@@ -704,38 +737,6 @@ ifdef CONFIG_CC_STACKPROTECTOR
 endif
 KBUILD_CFLAGS += $(stackp-flag)
 
-ifeq ($(cc-name),clang)
-ifneq ($(CROSS_COMPILE),)
-CLANG_TARGET	:= -target $(notdir $(CROSS_COMPILE:%-=%))
-GCC_TOOLCHAIN	:= $(realpath $(dir $(shell which $(LD)))/..)
-endif
-ifneq ($(GCC_TOOLCHAIN),)
-CLANG_GCC_TC	:= -gcc-toolchain $(GCC_TOOLCHAIN)
-endif
-KBUILD_CFLAGS += $(CLANG_TARGET) $(CLANG_GCC_TC)
-KBUILD_AFLAGS += $(CLANG_TARGET) $(CLANG_GCC_TC)
-KBUILD_CPPFLAGS += $(call cc-option,-Qunused-arguments,)
-KBUILD_CFLAGS += $(call cc-disable-warning, unused-variable)
-KBUILD_CFLAGS += $(call cc-disable-warning, format-invalid-specifier)
-KBUILD_CFLAGS += $(call cc-disable-warning, gnu)
-KBUILD_CFLAGS += $(call cc-disable-warning, address-of-packed-member)
-# Quiet clang warning: comparison of unsigned expression < 0 is always false
-KBUILD_CFLAGS += $(call cc-disable-warning, tautological-compare)
-# CLANG uses a _MergedGlobals as optimization, but this breaks modpost, as the
-# source of a reference will be _MergedGlobals and not on of the whitelisted names.
-# See modpost pattern 2
-KBUILD_CFLAGS += $(call cc-option, -mno-global-merge,)
-KBUILD_CFLAGS += $(call cc-option, -fcatch-undefined-behavior)
-KBUILD_CFLAGS += $(call cc-option, -no-integrated-as)
-KBUILD_AFLAGS += $(call cc-option, -no-integrated-as)
-else
-
-# These warnings generated too much noise in a regular build.
-# Use make W=1 to enable them (see scripts/Makefile.build)
-KBUILD_CFLAGS += $(call cc-disable-warning, unused-but-set-variable)
-KBUILD_CFLAGS += $(call cc-disable-warning, unused-const-variable)
-endif
-
 ifdef CONFIG_FRAME_POINTER
 KBUILD_CFLAGS	+= -fno-omit-frame-pointer -fno-optimize-sibling-calls
 else
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index 6be9ee148b78..e14ddca59d02 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -104,7 +104,7 @@ tune-$(CONFIG_CPU_V6K)		=$(call cc-option,-mtune=arm1136j-s,-mtune=strongarm)
 tune-y := $(tune-y)
 
 ifeq ($(CONFIG_AEABI),y)
-CFLAGS_ABI	:=-mabi=aapcs-linux -mno-thumb-interwork -mfpu=vfp
+CFLAGS_ABI	:=-mabi=aapcs-linux -mfpu=vfp
 else
 CFLAGS_ABI	:=$(call cc-option,-mapcs-32,-mabi=apcs-gnu) $(call cc-option,-mno-thumb-interwork,)
 endif
diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile
index d50430c40045..552c7d7f84ce 100644
--- a/arch/arm/boot/compressed/Makefile
+++ b/arch/arm/boot/compressed/Makefile
@@ -112,7 +112,7 @@ CFLAGS_fdt_ro.o := $(nossp_flags)
 CFLAGS_fdt_rw.o := $(nossp_flags)
 CFLAGS_fdt_wip.o := $(nossp_flags)
 
-ccflags-y := -fpic -mno-single-pic-base -fno-builtin -I$(obj)
+ccflags-y := -fpic $(call cc-option,-mno-single-pic-base,) -fno-builtin -I$(obj)
 asflags-y := -DZIMAGE
 
 # Supply kernel BSS size to the decompressor via a linker symbol.
diff --git a/arch/arm/firmware/trusted_foundations.c b/arch/arm/firmware/trusted_foundations.c
index 3fb1b5a1dce9..689e6565abfc 100644
--- a/arch/arm/firmware/trusted_foundations.c
+++ b/arch/arm/firmware/trusted_foundations.c
@@ -31,21 +31,25 @@
 
 static unsigned long cpu_boot_addr;
 
-static void __naked tf_generic_smc(u32 type, u32 arg1, u32 arg2)
+static void tf_generic_smc(u32 type, u32 arg1, u32 arg2)
 {
+	register u32 r0 asm("r0") = type;
+	register u32 r1 asm("r1") = arg1;
+	register u32 r2 asm("r2") = arg2;
+
 	asm volatile(
 		".arch_extension	sec\n\t"
-		"stmfd	sp!, {r4 - r11, lr}\n\t"
+		"stmfd	sp!, {r4 - r11}\n\t"
 		__asmeq("%0", "r0")
 		__asmeq("%1", "r1")
 		__asmeq("%2", "r2")
 		"mov	r3, #0\n\t"
 		"mov	r4, #0\n\t"
 		"smc	#0\n\t"
-		"ldmfd	sp!, {r4 - r11, pc}"
+		"ldmfd	sp!, {r4 - r11}\n\t"
 		:
-		: "r" (type), "r" (arg1), "r" (arg2)
-		: "memory");
+		: "r" (r0), "r" (r1), "r" (r2)
+		: "memory", "r3", "r12", "lr");
 }
 
 static int tf_set_cpu_boot_addr(int cpu, unsigned long boot_addr)
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 655a65eaf105..cadf99923600 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -437,26 +437,6 @@ int x86_setup_perfctr(struct perf_event *event)
 	if (config == -1LL)
 		return -EINVAL;
 
-	/*
-	 * Branch tracing:
-	 */
-	if (attr->config == PERF_COUNT_HW_BRANCH_INSTRUCTIONS &&
-	    !attr->freq && hwc->sample_period == 1) {
-		/* BTS is not supported by this architecture. */
-		if (!x86_pmu.bts_active)
-			return -EOPNOTSUPP;
-
-		/* BTS is currently only allowed for user-mode. */
-		if (!attr->exclude_kernel)
-			return -EOPNOTSUPP;
-
-		/* disallow bts if conflicting events are present */
-		if (x86_add_exclusive(x86_lbr_exclusive_lbr))
-			return -EBUSY;
-
-		event->destroy = hw_perf_lbr_event_destroy;
-	}
-
 	hwc->config |= config;
 
 	return 0;
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 815039327932..4f8560774082 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2198,16 +2198,7 @@ done:
 static struct event_constraint *
 intel_bts_constraints(struct perf_event *event)
 {
-	struct hw_perf_event *hwc = &event->hw;
-	unsigned int hw_event, bts_event;
-
-	if (event->attr.freq)
-		return NULL;
-
-	hw_event = hwc->config & INTEL_ARCH_EVENT_MASK;
-	bts_event = x86_pmu.event_map(PERF_COUNT_HW_BRANCH_INSTRUCTIONS);
-
-	if (unlikely(hw_event == bts_event && hwc->sample_period == 1))
+	if (unlikely(intel_pmu_has_bts(event)))
 		return &bts_constraint;
 
 	return NULL;
@@ -2822,10 +2813,47 @@ static unsigned long intel_pmu_free_running_flags(struct perf_event *event)
 	return flags;
 }
 
+static int intel_pmu_bts_config(struct perf_event *event)
+{
+	struct perf_event_attr *attr = &event->attr;
+
+	if (unlikely(intel_pmu_has_bts(event))) {
+		/* BTS is not supported by this architecture. */
+		if (!x86_pmu.bts_active)
+			return -EOPNOTSUPP;
+
+		/* BTS is currently only allowed for user-mode. */
+		if (!attr->exclude_kernel)
+			return -EOPNOTSUPP;
+
+		/* disallow bts if conflicting events are present */
+		if (x86_add_exclusive(x86_lbr_exclusive_lbr))
+			return -EBUSY;
+
+		event->destroy = hw_perf_lbr_event_destroy;
+	}
+
+	return 0;
+}
+
+static int core_pmu_hw_config(struct perf_event *event)
+{
+	int ret = x86_pmu_hw_config(event);
+
+	if (ret)
+		return ret;
+
+	return intel_pmu_bts_config(event);
+}
+
 static int intel_pmu_hw_config(struct perf_event *event)
 {
 	int ret = x86_pmu_hw_config(event);
 
+	if (ret)
+		return ret;
+
+	ret = intel_pmu_bts_config(event);
 	if (ret)
 		return ret;
 
@@ -2848,7 +2876,7 @@ static int intel_pmu_hw_config(struct perf_event *event)
 		/*
 		 * BTS is set up earlier in this path, so don't account twice
 		 */
-		if (!intel_pmu_has_bts(event)) {
+		if (!unlikely(intel_pmu_has_bts(event))) {
 			/* disallow lbr if conflicting events are present */
 			if (x86_add_exclusive(x86_lbr_exclusive_lbr))
 				return -EBUSY;
@@ -3265,7 +3293,7 @@ static __initconst const struct x86_pmu core_pmu = {
 	.enable_all		= core_pmu_enable_all,
 	.enable			= core_pmu_enable_event,
 	.disable		= x86_pmu_disable_event,
-	.hw_config		= x86_pmu_hw_config,
+	.hw_config		= core_pmu_hw_config,
 	.schedule_events	= x86_schedule_events,
 	.eventsel		= MSR_ARCH_PERFMON_EVENTSEL0,
 	.perfctr		= MSR_ARCH_PERFMON_PERFCTR0,
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 1bfebbc4d156..7ace39c51ff7 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -835,11 +835,16 @@ static inline int amd_pmu_init(void)
 
 static inline bool intel_pmu_has_bts(struct perf_event *event)
 {
-	if (event->attr.config == PERF_COUNT_HW_BRANCH_INSTRUCTIONS &&
-	    !event->attr.freq && event->hw.sample_period == 1)
-		return true;
+	struct hw_perf_event *hwc = &event->hw;
+	unsigned int hw_event, bts_event;
+
+	if (event->attr.freq)
+		return false;
+
+	hw_event = hwc->config & INTEL_ARCH_EVENT_MASK;
+	bts_event = x86_pmu.event_map(PERF_COUNT_HW_BRANCH_INSTRUCTIONS);
 
-	return false;
+	return hw_event == bts_event && hwc->sample_period == 1;
 }
 
 int intel_pmu_save_and_restart(struct perf_event *event);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 8a4d6bc8fed0..676edfc19a95 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -4297,9 +4297,9 @@ static bool need_remote_flush(u64 old, u64 new)
 }
 
 static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa,
-				    const u8 *new, int *bytes)
+				    int *bytes)
 {
-	u64 gentry;
+	u64 gentry = 0;
 	int r;
 
 	/*
@@ -4311,22 +4311,12 @@ static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa,
 		/* Handle a 32-bit guest writing two halves of a 64-bit gpte */
 		*gpa &= ~(gpa_t)7;
 		*bytes = 8;
-		r = kvm_vcpu_read_guest(vcpu, *gpa, &gentry, 8);
-		if (r)
-			gentry = 0;
-		new = (const u8 *)&gentry;
 	}
 
-	switch (*bytes) {
-	case 4:
-		gentry = *(const u32 *)new;
-		break;
-	case 8:
-		gentry = *(const u64 *)new;
-		break;
-	default:
-		gentry = 0;
-		break;
+	if (*bytes == 4 || *bytes == 8) {
+		r = kvm_vcpu_read_guest_atomic(vcpu, *gpa, &gentry, *bytes);
+		if (r)
+			gentry = 0;
 	}
 
 	return gentry;
@@ -4437,8 +4427,6 @@ static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 
 	pgprintk("%s: gpa %llx bytes %d\n", __func__, gpa, bytes);
 
-	gentry = mmu_pte_write_fetch_gpte(vcpu, &gpa, new, &bytes);
-
 	/*
 	 * No need to care whether allocation memory is successful
 	 * or not since pte prefetch is skiped if it does not have
@@ -4447,6 +4435,9 @@ static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 	mmu_topup_memory_caches(vcpu);
 
 	spin_lock(&vcpu->kvm->mmu_lock);
+
+	gentry = mmu_pte_write_fetch_gpte(vcpu, &gpa, &bytes);
+
 	++vcpu->kvm->stat.mmu_pte_write;
 	kvm_mmu_audit(vcpu, AUDIT_PRE_PTE_WRITE);
 
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 5f44d63a9d69..4bc35ac28d11 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1672,21 +1672,31 @@ out:
 	return ERR_PTR(err);
 }
 
+static void svm_clear_current_vmcb(struct vmcb *vmcb)
+{
+	int i;
+
+	for_each_online_cpu(i)
+		cmpxchg(&per_cpu(svm_data, i)->current_vmcb, vmcb, NULL);
+}
+
 static void svm_free_vcpu(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
+	/*
+	 * The vmcb page can be recycled, causing a false negative in
+	 * svm_vcpu_load(). So, ensure that no logical CPU has this
+	 * vmcb page recorded as its current vmcb.
+	 */
+	svm_clear_current_vmcb(svm->vmcb);
+
 	__free_page(pfn_to_page(svm->vmcb_pa >> PAGE_SHIFT));
 	__free_pages(virt_to_page(svm->msrpm), MSRPM_ALLOC_ORDER);
 	__free_page(virt_to_page(svm->nested.hsave));
 	__free_pages(virt_to_page(svm->nested.msrpm), MSRPM_ALLOC_ORDER);
 	kvm_vcpu_uninit(vcpu);
 	kmem_cache_free(kvm_vcpu_cache, svm);
-	/*
-	 * The vmcb page can be recycled, causing a false negative in
-	 * svm_vcpu_load(). So do a full IBPB now.
-	 */
-	indirect_branch_prediction_barrier();
 }
 
 static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 5013ef165f44..27d13b870e07 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6661,7 +6661,8 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu)
 	else {
 		if (vcpu->arch.apicv_active)
 			kvm_x86_ops->sync_pir_to_irr(vcpu);
-		kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors);
+		if (ioapic_in_kernel(vcpu->kvm))
+			kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors);
 	}
 	bitmap_or((ulong *)eoi_exit_bitmap, vcpu->arch.ioapic_handled_vectors,
 		  vcpu_to_synic(vcpu)->vec_bitmap, 256);
diff --git a/arch/xtensa/kernel/asm-offsets.c b/arch/xtensa/kernel/asm-offsets.c
index 8e10e357ee32..f1af06b8f3cd 100644
--- a/arch/xtensa/kernel/asm-offsets.c
+++ b/arch/xtensa/kernel/asm-offsets.c
@@ -91,14 +91,14 @@ int main(void)
 	DEFINE(THREAD_SP, offsetof (struct task_struct, thread.sp));
 	DEFINE(THREAD_CPENABLE, offsetof (struct thread_info, cpenable));
 #if XTENSA_HAVE_COPROCESSORS
-	DEFINE(THREAD_XTREGS_CP0, offsetof (struct thread_info, xtregs_cp));
-	DEFINE(THREAD_XTREGS_CP1, offsetof (struct thread_info, xtregs_cp));
-	DEFINE(THREAD_XTREGS_CP2, offsetof (struct thread_info, xtregs_cp));
-	DEFINE(THREAD_XTREGS_CP3, offsetof (struct thread_info, xtregs_cp));
-	DEFINE(THREAD_XTREGS_CP4, offsetof (struct thread_info, xtregs_cp));
-	DEFINE(THREAD_XTREGS_CP5, offsetof (struct thread_info, xtregs_cp));
-	DEFINE(THREAD_XTREGS_CP6, offsetof (struct thread_info, xtregs_cp));
-	DEFINE(THREAD_XTREGS_CP7, offsetof (struct thread_info, xtregs_cp));
+	DEFINE(THREAD_XTREGS_CP0, offsetof(struct thread_info, xtregs_cp.cp0));
+	DEFINE(THREAD_XTREGS_CP1, offsetof(struct thread_info, xtregs_cp.cp1));
+	DEFINE(THREAD_XTREGS_CP2, offsetof(struct thread_info, xtregs_cp.cp2));
+	DEFINE(THREAD_XTREGS_CP3, offsetof(struct thread_info, xtregs_cp.cp3));
+	DEFINE(THREAD_XTREGS_CP4, offsetof(struct thread_info, xtregs_cp.cp4));
+	DEFINE(THREAD_XTREGS_CP5, offsetof(struct thread_info, xtregs_cp.cp5));
+	DEFINE(THREAD_XTREGS_CP6, offsetof(struct thread_info, xtregs_cp.cp6));
+	DEFINE(THREAD_XTREGS_CP7, offsetof(struct thread_info, xtregs_cp.cp7));
 #endif
 	DEFINE(THREAD_XTREGS_USER, offsetof (struct thread_info, xtregs_user));
 	DEFINE(XTREGS_USER_SIZE, sizeof(xtregs_user_t));
diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c
index e0ded48561db..570307c91846 100644
--- a/arch/xtensa/kernel/process.c
+++ b/arch/xtensa/kernel/process.c
@@ -85,18 +85,21 @@ void coprocessor_release_all(struct thread_info *ti)
 
 void coprocessor_flush_all(struct thread_info *ti)
 {
-	unsigned long cpenable;
+	unsigned long cpenable, old_cpenable;
 	int i;
 
 	preempt_disable();
 
+	RSR_CPENABLE(old_cpenable);
 	cpenable = ti->cpenable;
+	WSR_CPENABLE(cpenable);
 
 	for (i = 0; i < XCHAL_CP_MAX; i++) {
 		if ((cpenable & 1) != 0 && coprocessor_owner[i] == ti)
 			coprocessor_flush(ti, i);
 		cpenable >>= 1;
 	}
+	WSR_CPENABLE(old_cpenable);
 
 	preempt_enable();
 }
diff --git a/drivers/bus/arm-cci.c b/drivers/bus/arm-cci.c
index 10f56133b281..8e08cb4fd7df 100644
--- a/drivers/bus/arm-cci.c
+++ b/drivers/bus/arm-cci.c
@@ -2103,8 +2103,6 @@ asmlinkage void __naked cci_enable_port_for_self(void)
 	[sizeof_struct_cpu_port] "i" (sizeof(struct cpu_port)),
 	[sizeof_struct_ace_port] "i" (sizeof(struct cci_ace_port)),
 	[offsetof_port_phys] "i" (offsetof(struct cci_ace_port, phys)) );
-
-	unreachable();
 }
 
 /**
diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c
index e2cec5b357fd..a32cd71f94bb 100644
--- a/drivers/dma/at_hdmac.c
+++ b/drivers/dma/at_hdmac.c
@@ -1774,6 +1774,12 @@ static void atc_free_chan_resources(struct dma_chan *chan)
 	atchan->descs_allocated = 0;
 	atchan->status = 0;
 
+	/*
+	 * Free atslave allocated in at_dma_xlate()
+	 */
+	kfree(chan->private);
+	chan->private = NULL;
+
 	dev_vdbg(chan2dev(chan), "free_chan_resources: done\n");
 }
 
@@ -1808,7 +1814,7 @@ static struct dma_chan *at_dma_xlate(struct of_phandle_args *dma_spec,
 	dma_cap_zero(mask);
 	dma_cap_set(DMA_SLAVE, mask);
 
-	atslave = devm_kzalloc(&dmac_pdev->dev, sizeof(*atslave), GFP_KERNEL);
+	atslave = kzalloc(sizeof(*atslave), GFP_KERNEL);
 	if (!atslave)
 		return NULL;
 
@@ -2139,6 +2145,8 @@ static int at_dma_remove(struct platform_device *pdev)
 	struct resource		*io;
 
 	at_dma_off(atdma);
+	if (pdev->dev.of_node)
+		of_dma_controller_free(pdev->dev.of_node);
 	dma_async_device_unregister(&atdma->dma_common);
 
 	dma_pool_destroy(atdma->memset_pool);
diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile
index 2cd9496eb696..310f8feb5174 100644
--- a/drivers/firmware/efi/libstub/Makefile
+++ b/drivers/firmware/efi/libstub/Makefile
@@ -12,7 +12,8 @@ cflags-$(CONFIG_X86)		+= -m$(BITS) -D__KERNEL__ $(LINUX_INCLUDE) -O2 \
 
 cflags-$(CONFIG_ARM64)		:= $(subst -pg,,$(KBUILD_CFLAGS)) -fpie
 cflags-$(CONFIG_ARM)		:= $(subst -pg,,$(KBUILD_CFLAGS)) \
-				   -fno-builtin -fpic -mno-single-pic-base
+				   -fno-builtin -fpic \
+				   $(call cc-option,-mno-single-pic-base)
 
 cflags-$(CONFIG_EFI_ARMSTUB)	+= -I$(srctree)/scripts/dtc/libfdt
 
diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c
index aded10662020..09d10dcf1fc6 100644
--- a/drivers/firmware/efi/libstub/efi-stub-helper.c
+++ b/drivers/firmware/efi/libstub/efi-stub-helper.c
@@ -355,6 +355,14 @@ efi_status_t efi_parse_options(char *cmdline)
 {
 	char *str;
 
+	/*
+	 * Currently, the only efi= option we look for is 'nochunk', which
+	 * is intended to work around known issues on certain x86 UEFI
+	 * versions. So ignore for now on other architectures.
+	 */
+	if (!IS_ENABLED(CONFIG_X86))
+		return EFI_SUCCESS;
+
 	/*
 	 * If no EFI parameters were specified on the cmdline we've got
 	 * nothing to do.
@@ -528,7 +536,8 @@ efi_status_t handle_cmdline_files(efi_system_table_t *sys_table_arg,
 			size = files[j].size;
 			while (size) {
 				unsigned long chunksize;
-				if (size > __chunk_size)
+
+				if (IS_ENABLED(CONFIG_X86) && size > __chunk_size)
 					chunksize = __chunk_size;
 				else
 					chunksize = size;
diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index 1606e7f08f4b..784c45484825 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -448,6 +448,14 @@ int vmbus_establish_gpadl(struct vmbus_channel *channel, void *kbuffer,
 	}
 	wait_for_completion(&msginfo->waitevent);
 
+	if (msginfo->response.gpadl_created.creation_status != 0) {
+		pr_err("Failed to establish GPADL: err = 0x%x\n",
+		       msginfo->response.gpadl_created.creation_status);
+
+		ret = -EDQUOT;
+		goto cleanup;
+	}
+
 	if (channel->rescind) {
 		ret = -ENODEV;
 		goto cleanup;
diff --git a/drivers/iio/magnetometer/st_magn_buffer.c b/drivers/iio/magnetometer/st_magn_buffer.c
index 0a9e8fadfa9d..37ab30566464 100644
--- a/drivers/iio/magnetometer/st_magn_buffer.c
+++ b/drivers/iio/magnetometer/st_magn_buffer.c
@@ -30,11 +30,6 @@ int st_magn_trig_set_state(struct iio_trigger *trig, bool state)
 	return st_sensors_set_dataready_irq(indio_dev, state);
 }
 
-static int st_magn_buffer_preenable(struct iio_dev *indio_dev)
-{
-	return st_sensors_set_enable(indio_dev, true);
-}
-
 static int st_magn_buffer_postenable(struct iio_dev *indio_dev)
 {
 	int err;
@@ -50,7 +45,7 @@ static int st_magn_buffer_postenable(struct iio_dev *indio_dev)
 	if (err < 0)
 		goto st_magn_buffer_postenable_error;
 
-	return err;
+	return st_sensors_set_enable(indio_dev, true);
 
 st_magn_buffer_postenable_error:
 	kfree(mdata->buffer_data);
@@ -63,11 +58,11 @@ static int st_magn_buffer_predisable(struct iio_dev *indio_dev)
 	int err;
 	struct st_sensor_data *mdata = iio_priv(indio_dev);
 
-	err = iio_triggered_buffer_predisable(indio_dev);
+	err = st_sensors_set_enable(indio_dev, false);
 	if (err < 0)
 		goto st_magn_buffer_predisable_error;
 
-	err = st_sensors_set_enable(indio_dev, false);
+	err = iio_triggered_buffer_predisable(indio_dev);
 
 st_magn_buffer_predisable_error:
 	kfree(mdata->buffer_data);
@@ -75,7 +70,6 @@ st_magn_buffer_predisable_error:
 }
 
 static const struct iio_buffer_setup_ops st_magn_buffer_setup_ops = {
-	.preenable = &st_magn_buffer_preenable,
 	.postenable = &st_magn_buffer_postenable,
 	.predisable = &st_magn_buffer_predisable,
 };
diff --git a/drivers/media/usb/em28xx/em28xx-dvb.c b/drivers/media/usb/em28xx/em28xx-dvb.c
index 8cedef0daae4..b0aea48907b7 100644
--- a/drivers/media/usb/em28xx/em28xx-dvb.c
+++ b/drivers/media/usb/em28xx/em28xx-dvb.c
@@ -2016,6 +2016,8 @@ static int em28xx_dvb_fini(struct em28xx *dev)
 		}
 	}
 
+	em28xx_unregister_dvb(dvb);
+
 	/* remove I2C SEC */
 	client = dvb->i2c_client_sec;
 	if (client) {
@@ -2037,7 +2039,6 @@ static int em28xx_dvb_fini(struct em28xx *dev)
 		i2c_unregister_device(client);
 	}
 
-	em28xx_unregister_dvb(dvb);
 	kfree(dvb);
 	dev->dvb = NULL;
 	kref_put(&dev->ref, em28xx_free_device);
diff --git a/drivers/misc/mic/scif/scif_rma.c b/drivers/misc/mic/scif/scif_rma.c
index f806a4471eb9..32ab0f43f506 100644
--- a/drivers/misc/mic/scif/scif_rma.c
+++ b/drivers/misc/mic/scif/scif_rma.c
@@ -414,7 +414,7 @@ static int scif_create_remote_lookup(struct scif_dev *remote_dev,
 		if (err)
 			goto error_window;
 		err = scif_map_page(&window->num_pages_lookup.lookup[j],
-				    vmalloc_dma_phys ?
+				    vmalloc_num_pages ?
 				    vmalloc_to_page(&window->num_pages[i]) :
 				    virt_to_page(&window->num_pages[i]),
 				    remote_dev);
diff --git a/drivers/net/rionet.c b/drivers/net/rionet.c
index a31f4610b493..2c2604e3f633 100644
--- a/drivers/net/rionet.c
+++ b/drivers/net/rionet.c
@@ -216,9 +216,9 @@ static int rionet_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 			 * it just report sending a packet to the target
 			 * (without actual packet transfer).
 			 */
-			dev_kfree_skb_any(skb);
 			ndev->stats.tx_packets++;
 			ndev->stats.tx_bytes += skb->len;
+			dev_kfree_skb_any(skb);
 		}
 	}
 
diff --git a/drivers/net/usb/ipheth.c b/drivers/net/usb/ipheth.c
index 76465b117b72..f1f8227e7342 100644
--- a/drivers/net/usb/ipheth.c
+++ b/drivers/net/usb/ipheth.c
@@ -140,7 +140,6 @@ struct ipheth_device {
 	struct usb_device *udev;
 	struct usb_interface *intf;
 	struct net_device *net;
-	struct sk_buff *tx_skb;
 	struct urb *tx_urb;
 	struct urb *rx_urb;
 	unsigned char *tx_buf;
@@ -229,6 +228,7 @@ static void ipheth_rcvbulk_callback(struct urb *urb)
 	case -ENOENT:
 	case -ECONNRESET:
 	case -ESHUTDOWN:
+	case -EPROTO:
 		return;
 	case 0:
 		break;
@@ -280,7 +280,6 @@ static void ipheth_sndbulk_callback(struct urb *urb)
 		dev_err(&dev->intf->dev, "%s: urb status: %d\n",
 		__func__, status);
 
-	dev_kfree_skb_irq(dev->tx_skb);
 	netif_wake_queue(dev->net);
 }
 
@@ -410,7 +409,7 @@ static int ipheth_tx(struct sk_buff *skb, struct net_device *net)
 	if (skb->len > IPHETH_BUF_SIZE) {
 		WARN(1, "%s: skb too large: %d bytes\n", __func__, skb->len);
 		dev->net->stats.tx_dropped++;
-		dev_kfree_skb_irq(skb);
+		dev_kfree_skb_any(skb);
 		return NETDEV_TX_OK;
 	}
 
@@ -430,12 +429,11 @@ static int ipheth_tx(struct sk_buff *skb, struct net_device *net)
 		dev_err(&dev->intf->dev, "%s: usb_submit_urb: %d\n",
 			__func__, retval);
 		dev->net->stats.tx_errors++;
-		dev_kfree_skb_irq(skb);
+		dev_kfree_skb_any(skb);
 	} else {
-		dev->tx_skb = skb;
-
 		dev->net->stats.tx_packets++;
 		dev->net->stats.tx_bytes += skb->len;
+		dev_consume_skb_any(skb);
 		netif_stop_queue(net);
 	}
 
diff --git a/drivers/net/wireless/ti/wlcore/cmd.c b/drivers/net/wireless/ti/wlcore/cmd.c
index 96f83f09b8c5..7f4da727bb7b 100644
--- a/drivers/net/wireless/ti/wlcore/cmd.c
+++ b/drivers/net/wireless/ti/wlcore/cmd.c
@@ -35,7 +35,6 @@
 #include "wl12xx_80211.h"
 #include "cmd.h"
 #include "event.h"
-#include "ps.h"
 #include "tx.h"
 #include "hw_ops.h"
 
@@ -192,10 +191,6 @@ int wlcore_cmd_wait_for_event_or_timeout(struct wl1271 *wl,
 
 	timeout_time = jiffies + msecs_to_jiffies(WL1271_EVENT_TIMEOUT);
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
-		return ret;
-
 	do {
 		if (time_after(jiffies, timeout_time)) {
 			wl1271_debug(DEBUG_CMD, "timeout waiting for event %d",
@@ -227,7 +222,6 @@ int wlcore_cmd_wait_for_event_or_timeout(struct wl1271 *wl,
 	} while (!event);
 
 out:
-	wl1271_ps_elp_sleep(wl);
 	kfree(events_vector);
 	return ret;
 }
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index a5e603062ee0..8f77fc0630ce 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -4540,8 +4540,8 @@ static int qeth_snmp_command_cb(struct qeth_card *card,
 {
 	struct qeth_ipa_cmd *cmd;
 	struct qeth_arp_query_info *qinfo;
-	struct qeth_snmp_cmd *snmp;
 	unsigned char *data;
+	void *snmp_data;
 	__u16 data_len;
 
 	QETH_CARD_TEXT(card, 3, "snpcmdcb");
@@ -4549,7 +4549,6 @@ static int qeth_snmp_command_cb(struct qeth_card *card,
 	cmd = (struct qeth_ipa_cmd *) sdata;
 	data = (unsigned char *)((char *)cmd - reply->offset);
 	qinfo = (struct qeth_arp_query_info *) reply->param;
-	snmp = &cmd->data.setadapterparms.data.snmp;
 
 	if (cmd->hdr.return_code) {
 		QETH_CARD_TEXT_(card, 4, "scer1%x", cmd->hdr.return_code);
@@ -4562,10 +4561,15 @@ static int qeth_snmp_command_cb(struct qeth_card *card,
 		return 0;
 	}
 	data_len = *((__u16 *)QETH_IPA_PDU_LEN_PDU1(data));
-	if (cmd->data.setadapterparms.hdr.seq_no == 1)
-		data_len -= (__u16)((char *)&snmp->data - (char *)cmd);
-	else
-		data_len -= (__u16)((char *)&snmp->request - (char *)cmd);
+	if (cmd->data.setadapterparms.hdr.seq_no == 1) {
+		snmp_data = &cmd->data.setadapterparms.data.snmp;
+		data_len -= offsetof(struct qeth_ipa_cmd,
+				     data.setadapterparms.data.snmp);
+	} else {
+		snmp_data = &cmd->data.setadapterparms.data.snmp.request;
+		data_len -= offsetof(struct qeth_ipa_cmd,
+				     data.setadapterparms.data.snmp.request);
+	}
 
 	/* check if there is enough room in userspace */
 	if ((qinfo->udata_len - qinfo->udata_offset) < data_len) {
@@ -4578,16 +4582,9 @@ static int qeth_snmp_command_cb(struct qeth_card *card,
 	QETH_CARD_TEXT_(card, 4, "sseqn%i",
 		cmd->data.setadapterparms.hdr.seq_no);
 	/*copy entries to user buffer*/
-	if (cmd->data.setadapterparms.hdr.seq_no == 1) {
-		memcpy(qinfo->udata + qinfo->udata_offset,
-		       (char *)snmp,
-		       data_len + offsetof(struct qeth_snmp_cmd, data));
-		qinfo->udata_offset += offsetof(struct qeth_snmp_cmd, data);
-	} else {
-		memcpy(qinfo->udata + qinfo->udata_offset,
-		       (char *)&snmp->request, data_len);
-	}
+	memcpy(qinfo->udata + qinfo->udata_offset, snmp_data, data_len);
 	qinfo->udata_offset += data_len;
+
 	/* check if all replies received ... */
 		QETH_CARD_TEXT_(card, 4, "srtot%i",
 			       cmd->data.setadapterparms.hdr.used_total);
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index 1e8f68960014..808437c5ec49 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -64,6 +64,9 @@ static const struct usb_device_id usb_quirk_list[] = {
 	/* Microsoft LifeCam-VX700 v2.0 */
 	{ USB_DEVICE(0x045e, 0x0770), .driver_info = USB_QUIRK_RESET_RESUME },
 
+	/* Cherry Stream G230 2.0 (G85-231) and 3.0 (G85-232) */
+	{ USB_DEVICE(0x046a, 0x0023), .driver_info = USB_QUIRK_RESET_RESUME },
+
 	/* Logitech HD Pro Webcams C920, C920-C, C925e and C930e */
 	{ USB_DEVICE(0x046d, 0x082d), .driver_info = USB_QUIRK_DELAY_INIT },
 	{ USB_DEVICE(0x046d, 0x0841), .driver_info = USB_QUIRK_DELAY_INIT },
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 26efe8c7535f..ed6b9bfe3759 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -1280,9 +1280,6 @@ int __dwc3_gadget_ep_set_halt(struct dwc3_ep *dep, int value, int protocol)
 		unsigned transfer_in_flight;
 		unsigned started;
 
-		if (dep->flags & DWC3_EP_STALL)
-			return 0;
-
 		if (dep->number > 1)
 			trb = dwc3_ep_prev_trb(dep, dep->trb_enqueue);
 		else
@@ -1307,8 +1304,6 @@ int __dwc3_gadget_ep_set_halt(struct dwc3_ep *dep, int value, int protocol)
 		else
 			dep->flags |= DWC3_EP_STALL;
 	} else {
-		if (!(dep->flags & DWC3_EP_STALL))
-			return 0;
 
 		ret = dwc3_send_clear_stall_ep_cmd(dep);
 		if (ret)
diff --git a/drivers/usb/storage/unusual_realtek.h b/drivers/usb/storage/unusual_realtek.h
index 8fe624ad302a..7ca779493671 100644
--- a/drivers/usb/storage/unusual_realtek.h
+++ b/drivers/usb/storage/unusual_realtek.h
@@ -39,4 +39,14 @@ UNUSUAL_DEV(0x0bda, 0x0159, 0x0000, 0x9999,
 		"USB Card Reader",
 		USB_SC_DEVICE, USB_PR_DEVICE, init_realtek_cr, 0),
 
+UNUSUAL_DEV(0x0bda, 0x0177, 0x0000, 0x9999,
+		"Realtek",
+		"USB Card Reader",
+		USB_SC_DEVICE, USB_PR_DEVICE, init_realtek_cr, 0),
+
+UNUSUAL_DEV(0x0bda, 0x0184, 0x0000, 0x9999,
+		"Realtek",
+		"USB Card Reader",
+		USB_SC_DEVICE, USB_PR_DEVICE, init_realtek_cr, 0),
+
 #endif  /* defined(CONFIG_USB_STORAGE_REALTEK) || ... */
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index f6e111984ce2..a7b69deb6d70 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -2226,6 +2226,7 @@ static long btrfs_control_ioctl(struct file *file, unsigned int cmd,
 	vol = memdup_user((void __user *)arg, sizeof(*vol));
 	if (IS_ERR(vol))
 		return PTR_ERR(vol);
+	vol->name[BTRFS_PATH_NAME_MAX] = '\0';
 
 	switch (cmd) {
 	case BTRFS_IOC_SCAN_DEV:
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 9517de0e668c..fd6c74662e9a 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -1924,6 +1924,9 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 		return ret;
 	}
 
+	btrfs_trans_release_metadata(trans, root);
+	trans->block_rsv = NULL;
+
 	/* make a pass through all the delayed refs we have so far
 	 * any runnings procs may add more while we are here
 	 */
@@ -1933,9 +1936,6 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 		return ret;
 	}
 
-	btrfs_trans_release_metadata(trans, root);
-	trans->block_rsv = NULL;
-
 	cur_trans = trans->transaction;
 
 	/*
diff --git a/fs/direct-io.c b/fs/direct-io.c
index c6220a2daefd..07cc38ec66ca 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -278,8 +278,8 @@ static ssize_t dio_complete(struct dio *dio, ssize_t ret, bool is_async)
 		 */
 		dio->iocb->ki_pos += transferred;
 
-		if (dio->op == REQ_OP_WRITE)
-			ret = generic_write_sync(dio->iocb,  transferred);
+		if (ret > 0 && dio->op == REQ_OP_WRITE)
+			ret = generic_write_sync(dio->iocb, ret);
 		dio->iocb->ki_complete(dio->iocb, ret, 0);
 	}
 
diff --git a/fs/ext2/xattr.c b/fs/ext2/xattr.c
index fbdb8f171893..babef30d440b 100644
--- a/fs/ext2/xattr.c
+++ b/fs/ext2/xattr.c
@@ -609,9 +609,9 @@ skip_replace:
 	}
 
 cleanup:
-	brelse(bh);
 	if (!(bh && header == HDR(bh)))
 		kfree(header);
+	brelse(bh);
 	up_write(&EXT2_I(inode)->xattr_sem);
 
 	return error;
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 1def337b16d4..8e880f7f67b2 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -106,9 +106,9 @@ struct work_struct {
 #endif
 };
 
-#define WORK_DATA_INIT()	ATOMIC_LONG_INIT(WORK_STRUCT_NO_POOL)
+#define WORK_DATA_INIT()	ATOMIC_LONG_INIT((unsigned long)WORK_STRUCT_NO_POOL)
 #define WORK_DATA_STATIC_INIT()	\
-	ATOMIC_LONG_INIT(WORK_STRUCT_NO_POOL | WORK_STRUCT_STATIC)
+	ATOMIC_LONG_INIT((unsigned long)(WORK_STRUCT_NO_POOL | WORK_STRUCT_STATIC))
 
 struct delayed_work {
 	struct work_struct work;
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 9f7bba700e4e..7ea8da990b9d 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1839,7 +1839,7 @@ void vma_adjust_trans_huge(struct vm_area_struct *vma,
 	}
 }
 
-static void freeze_page(struct page *page)
+static void unmap_page(struct page *page)
 {
 	enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS |
 		TTU_RMAP_LOCKED;
@@ -1862,7 +1862,7 @@ static void freeze_page(struct page *page)
 	VM_BUG_ON_PAGE(ret, page + i - 1);
 }
 
-static void unfreeze_page(struct page *page)
+static void remap_page(struct page *page)
 {
 	int i;
 
@@ -1876,26 +1876,13 @@ static void __split_huge_page_tail(struct page *head, int tail,
 	struct page *page_tail = head + tail;
 
 	VM_BUG_ON_PAGE(atomic_read(&page_tail->_mapcount) != -1, page_tail);
-	VM_BUG_ON_PAGE(page_ref_count(page_tail) != 0, page_tail);
 
 	/*
-	 * tail_page->_refcount is zero and not changing from under us. But
-	 * get_page_unless_zero() may be running from under us on the
-	 * tail_page. If we used atomic_set() below instead of atomic_inc() or
-	 * atomic_add(), we would then run atomic_set() concurrently with
-	 * get_page_unless_zero(), and atomic_set() is implemented in C not
-	 * using locked ops. spin_unlock on x86 sometime uses locked ops
-	 * because of PPro errata 66, 92, so unless somebody can guarantee
-	 * atomic_set() here would be safe on all archs (and not only on x86),
-	 * it's safer to use atomic_inc()/atomic_add().
+	 * Clone page flags before unfreezing refcount.
+	 *
+	 * After successful get_page_unless_zero() might follow flags change,
+	 * for exmaple lock_page() which set PG_waiters.
 	 */
-	if (PageAnon(head)) {
-		page_ref_inc(page_tail);
-	} else {
-		/* Additional pin to radix tree */
-		page_ref_add(page_tail, 2);
-	}
-
 	page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP;
 	page_tail->flags |= (head->flags &
 			((1L << PG_referenced) |
@@ -1907,36 +1894,42 @@ static void __split_huge_page_tail(struct page *head, int tail,
 			 (1L << PG_unevictable) |
 			 (1L << PG_dirty)));
 
-	/*
-	 * After clearing PageTail the gup refcount can be released.
-	 * Page flags also must be visible before we make the page non-compound.
-	 */
+	/* ->mapping in first tail page is compound_mapcount */
+	VM_BUG_ON_PAGE(tail > 2 && page_tail->mapping != TAIL_MAPPING,
+			page_tail);
+	page_tail->mapping = head->mapping;
+	page_tail->index = head->index + tail;
+
+	/* Page flags must be visible before we make the page non-compound. */
 	smp_wmb();
 
+	/*
+	 * Clear PageTail before unfreezing page refcount.
+	 *
+	 * After successful get_page_unless_zero() might follow put_page()
+	 * which needs correct compound_head().
+	 */
 	clear_compound_head(page_tail);
 
+	/* Finally unfreeze refcount. Additional reference from page cache. */
+	page_ref_unfreeze(page_tail, 1 + (!PageAnon(head) ||
+					  PageSwapCache(head)));
+
 	if (page_is_young(head))
 		set_page_young(page_tail);
 	if (page_is_idle(head))
 		set_page_idle(page_tail);
 
-	/* ->mapping in first tail page is compound_mapcount */
-	VM_BUG_ON_PAGE(tail > 2 && page_tail->mapping != TAIL_MAPPING,
-			page_tail);
-	page_tail->mapping = head->mapping;
-
-	page_tail->index = head->index + tail;
 	page_cpupid_xchg_last(page_tail, page_cpupid_last(head));
 	lru_add_page_tail(head, page_tail, lruvec, list);
 }
 
 static void __split_huge_page(struct page *page, struct list_head *list,
-		unsigned long flags)
+		pgoff_t end, unsigned long flags)
 {
 	struct page *head = compound_head(page);
 	struct zone *zone = page_zone(head);
 	struct lruvec *lruvec;
-	pgoff_t end = -1;
 	int i;
 
 	lruvec = mem_cgroup_page_lruvec(head, zone->zone_pgdat);
@@ -1944,9 +1937,6 @@ static void __split_huge_page(struct page *page, struct list_head *list,
 	/* complete memcg works before add pages to LRU */
 	mem_cgroup_split_huge_fixup(head);
 
-	if (!PageAnon(page))
-		end = DIV_ROUND_UP(i_size_read(head->mapping->host), PAGE_SIZE);
-
 	for (i = HPAGE_PMD_NR - 1; i >= 1; i--) {
 		__split_huge_page_tail(head, i, lruvec, list);
 		/* Some pages can be beyond i_size: drop them from page cache */
@@ -1971,7 +1961,7 @@ static void __split_huge_page(struct page *page, struct list_head *list,
 
 	spin_unlock_irqrestore(zone_lru_lock(page_zone(head)), flags);
 
-	unfreeze_page(head);
+	remap_page(head);
 
 	for (i = 0; i < HPAGE_PMD_NR; i++) {
 		struct page *subpage = head + i;
@@ -2099,6 +2089,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 	int count, mapcount, extra_pins, ret;
 	bool mlocked;
 	unsigned long flags;
+	pgoff_t end;
 
 	VM_BUG_ON_PAGE(is_huge_zero_page(page), page);
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
@@ -2120,6 +2111,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 			goto out;
 		}
 		extra_pins = 0;
+		end = -1;
 		mapping = NULL;
 		anon_vma_lock_write(anon_vma);
 	} else {
@@ -2135,10 +2127,19 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 		extra_pins = HPAGE_PMD_NR;
 		anon_vma = NULL;
 		i_mmap_lock_read(mapping);
+
+		/*
+		 *__split_huge_page() may need to trim off pages beyond EOF:
+		 * but on 32-bit, i_size_read() takes an irq-unsafe seqlock,
+		 * which cannot be nested inside the page tree lock. So note
+		 * end now: i_size itself may be changed at any moment, but
+		 * head page lock is good enough to serialize the trimming.
+		 */
+		end = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE);
 	}
 
 	/*
-	 * Racy check if we can split the page, before freeze_page() will
+	 * Racy check if we can split the page, before unmap_page() will
 	 * split PMDs
 	 */
 	if (total_mapcount(head) != page_count(head) - extra_pins - 1) {
@@ -2147,7 +2148,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 	}
 
 	mlocked = PageMlocked(page);
-	freeze_page(head);
+	unmap_page(head);
 	VM_BUG_ON_PAGE(compound_mapcount(head), head);
 
 	/* Make sure the page is not on per-CPU pagevec as it takes pin */
@@ -2184,7 +2185,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 		if (mapping)
 			__dec_node_page_state(page, NR_SHMEM_THPS);
 		spin_unlock(&pgdata->split_queue_lock);
-		__split_huge_page(page, list, flags);
+		__split_huge_page(page, list, end, flags);
 		ret = 0;
 	} else {
 		if (IS_ENABLED(CONFIG_DEBUG_VM) && mapcount) {
@@ -2199,7 +2200,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 fail:		if (mapping)
 			spin_unlock(&mapping->tree_lock);
 		spin_unlock_irqrestore(zone_lru_lock(page_zone(head)), flags);
-		unfreeze_page(head);
+		remap_page(head);
 		ret = -EBUSY;
 	}
 
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 1df37ee996d5..e0cfc3a54b6a 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1286,7 +1286,7 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
  * collapse_shmem - collapse small tmpfs/shmem pages into huge one.
  *
  * Basic scheme is simple, details are more complex:
- *  - allocate and freeze a new huge page;
+ *  - allocate and lock a new huge page;
  *  - scan over radix tree replacing old pages the new one
  *    + swap in pages if necessary;
  *    + fill in gaps;
@@ -1294,11 +1294,11 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
  *  - if replacing succeed:
  *    + copy data over;
  *    + free old pages;
- *    + unfreeze huge page;
+ *    + unlock huge page;
  *  - if replacing failed;
  *    + put all pages back and unfreeze them;
  *    + restore gaps in the radix-tree;
- *    + free huge page;
+ *    + unlock and free huge page;
  */
 static void collapse_shmem(struct mm_struct *mm,
 		struct address_space *mapping, pgoff_t start,
@@ -1332,18 +1332,15 @@ static void collapse_shmem(struct mm_struct *mm,
 		goto out;
 	}
 
+	__SetPageLocked(new_page);
+	__SetPageSwapBacked(new_page);
 	new_page->index = start;
 	new_page->mapping = mapping;
-	__SetPageSwapBacked(new_page);
-	__SetPageLocked(new_page);
-	BUG_ON(!page_ref_freeze(new_page, 1));
-
 
 	/*
-	 * At this point the new_page is 'frozen' (page_count() is zero), locked
-	 * and not up-to-date. It's safe to insert it into radix tree, because
-	 * nobody would be able to map it or use it in other way until we
-	 * unfreeze it.
+	 * At this point the new_page is locked and not up-to-date.
+	 * It's safe to insert it into the page cache, because nobody would
+	 * be able to map it or use it in another way until we unlock it.
 	 */
 
 	index = start;
@@ -1351,19 +1348,29 @@ static void collapse_shmem(struct mm_struct *mm,
 	radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) {
 		int n = min(iter.index, end) - index;
 
+		/*
+		 * Stop if extent has been hole-punched, and is now completely
+		 * empty (the more obvious i_size_read() check would take an
+		 * irq-unsafe seqlock on 32-bit).
+		 */
+		if (n >= HPAGE_PMD_NR) {
+			result = SCAN_TRUNCATED;
+			goto tree_locked;
+		}
+
 		/*
 		 * Handle holes in the radix tree: charge it from shmem and
 		 * insert relevant subpage of new_page into the radix-tree.
 		 */
 		if (n && !shmem_charge(mapping->host, n)) {
 			result = SCAN_FAIL;
-			break;
+			goto tree_locked;
 		}
-		nr_none += n;
 		for (; index < min(iter.index, end); index++) {
 			radix_tree_insert(&mapping->page_tree, index,
 					new_page + (index % HPAGE_PMD_NR));
 		}
+		nr_none += n;
 
 		/* We are done. */
 		if (index >= end)
@@ -1379,12 +1386,12 @@ static void collapse_shmem(struct mm_struct *mm,
 				result = SCAN_FAIL;
 				goto tree_unlocked;
 			}
-			spin_lock_irq(&mapping->tree_lock);
 		} else if (trylock_page(page)) {
 			get_page(page);
+			spin_unlock_irq(&mapping->tree_lock);
 		} else {
 			result = SCAN_PAGE_LOCK;
-			break;
+			goto tree_locked;
 		}
 
 		/*
@@ -1393,17 +1400,24 @@ static void collapse_shmem(struct mm_struct *mm,
 		 */
 		VM_BUG_ON_PAGE(!PageLocked(page), page);
 		VM_BUG_ON_PAGE(!PageUptodate(page), page);
-		VM_BUG_ON_PAGE(PageTransCompound(page), page);
+
+		/*
+		 * If file was truncated then extended, or hole-punched, before
+		 * we locked the first page, then a THP might be there already.
+		 */
+		if (PageTransCompound(page)) {
+			result = SCAN_PAGE_COMPOUND;
+			goto out_unlock;
+		}
 
 		if (page_mapping(page) != mapping) {
 			result = SCAN_TRUNCATED;
 			goto out_unlock;
 		}
-		spin_unlock_irq(&mapping->tree_lock);
 
 		if (isolate_lru_page(page)) {
 			result = SCAN_DEL_PAGE_LRU;
-			goto out_isolate_failed;
+			goto out_unlock;
 		}
 
 		if (page_mapped(page))
@@ -1425,7 +1439,9 @@ static void collapse_shmem(struct mm_struct *mm,
 		 */
 		if (!page_ref_freeze(page, 3)) {
 			result = SCAN_PAGE_COUNT;
-			goto out_lru;
+			spin_unlock_irq(&mapping->tree_lock);
+			putback_lru_page(page);
+			goto out_unlock;
 		}
 
 		/*
@@ -1441,17 +1457,10 @@ static void collapse_shmem(struct mm_struct *mm,
 		slot = radix_tree_iter_next(&iter);
 		index++;
 		continue;
-out_lru:
-		spin_unlock_irq(&mapping->tree_lock);
-		putback_lru_page(page);
-out_isolate_failed:
-		unlock_page(page);
-		put_page(page);
-		goto tree_unlocked;
 out_unlock:
 		unlock_page(page);
 		put_page(page);
-		break;
+		goto tree_unlocked;
 	}
 
 	/*
@@ -1459,14 +1468,18 @@ out_unlock:
 	 * This code only triggers if there's nothing in radix tree
 	 * beyond 'end'.
 	 */
-	if (result == SCAN_SUCCEED && index < end) {
+	if (index < end) {
 		int n = end - index;
 
+		/* Stop if extent has been truncated, and is now empty */
+		if (n >= HPAGE_PMD_NR) {
+			result = SCAN_TRUNCATED;
+			goto tree_locked;
+		}
 		if (!shmem_charge(mapping->host, n)) {
 			result = SCAN_FAIL;
 			goto tree_locked;
 		}
-
 		for (; index < end; index++) {
 			radix_tree_insert(&mapping->page_tree, index,
 					new_page + (index % HPAGE_PMD_NR));
@@ -1474,57 +1487,62 @@ out_unlock:
 		nr_none += n;
 	}
 
+	__inc_node_page_state(new_page, NR_SHMEM_THPS);
+	if (nr_none) {
+		struct zone *zone = page_zone(new_page);
+
+		__mod_node_page_state(zone->zone_pgdat, NR_FILE_PAGES, nr_none);
+		__mod_node_page_state(zone->zone_pgdat, NR_SHMEM, nr_none);
+	}
+
 tree_locked:
 	spin_unlock_irq(&mapping->tree_lock);
 tree_unlocked:
 
 	if (result == SCAN_SUCCEED) {
-		unsigned long flags;
-		struct zone *zone = page_zone(new_page);
-
 		/*
 		 * Replacing old pages with new one has succeed, now we need to
 		 * copy the content and free old pages.
 		 */
+		index = start;
 		list_for_each_entry_safe(page, tmp, &pagelist, lru) {
+			while (index < page->index) {
+				clear_highpage(new_page + (index % HPAGE_PMD_NR));
+				index++;
+			}
 			copy_highpage(new_page + (page->index % HPAGE_PMD_NR),
 					page);
 			list_del(&page->lru);
-			unlock_page(page);
-			page_ref_unfreeze(page, 1);
 			page->mapping = NULL;
+			page_ref_unfreeze(page, 1);
 			ClearPageActive(page);
 			ClearPageUnevictable(page);
+			unlock_page(page);
 			put_page(page);
+			index++;
 		}
-
-		local_irq_save(flags);
-		__inc_node_page_state(new_page, NR_SHMEM_THPS);
-		if (nr_none) {
-			__mod_node_page_state(zone->zone_pgdat, NR_FILE_PAGES, nr_none);
-			__mod_node_page_state(zone->zone_pgdat, NR_SHMEM, nr_none);
+		while (index < end) {
+			clear_highpage(new_page + (index % HPAGE_PMD_NR));
+			index++;
 		}
-		local_irq_restore(flags);
 
-		/*
-		 * Remove pte page tables, so we can re-faulti
-		 * the page as huge.
-		 */
-		retract_page_tables(mapping, start);
-
-		/* Everything is ready, let's unfreeze the new_page */
-		set_page_dirty(new_page);
 		SetPageUptodate(new_page);
-		page_ref_unfreeze(new_page, HPAGE_PMD_NR);
+		page_ref_add(new_page, HPAGE_PMD_NR - 1);
+		set_page_dirty(new_page);
 		mem_cgroup_commit_charge(new_page, memcg, false, true);
 		lru_cache_add_anon(new_page);
-		unlock_page(new_page);
 
+		/*
+		 * Remove pte page tables, so we can re-fault the page as huge.
+		 */
+		retract_page_tables(mapping, start);
 		*hpage = NULL;
 	} else {
 		/* Something went wrong: rollback changes to the radix-tree */
-		shmem_uncharge(mapping->host, nr_none);
 		spin_lock_irq(&mapping->tree_lock);
+		mapping->nrpages -= nr_none;
+		shmem_uncharge(mapping->host, nr_none);
+
 		radix_tree_for_each_slot(slot, &mapping->page_tree, &iter,
 				start) {
 			if (iter.index >= end)
@@ -1549,20 +1567,19 @@ tree_unlocked:
 			page_ref_unfreeze(page, 2);
 			radix_tree_replace_slot(slot, page);
 			spin_unlock_irq(&mapping->tree_lock);
-			putback_lru_page(page);
 			unlock_page(page);
+			putback_lru_page(page);
 			spin_lock_irq(&mapping->tree_lock);
 			slot = radix_tree_iter_next(&iter);
 		}
 		VM_BUG_ON(nr_none);
 		spin_unlock_irq(&mapping->tree_lock);
 
-		/* Unfreeze new_page, caller would take care about freeing it */
-		page_ref_unfreeze(new_page, 1);
 		mem_cgroup_cancel_charge(new_page, memcg, true);
-		unlock_page(new_page);
 		new_page->mapping = NULL;
 	}
+
+	unlock_page(new_page);
 out:
 	VM_BUG_ON(!list_empty(&pagelist));
 	/* TODO: tracepoints */
diff --git a/mm/shmem.c b/mm/shmem.c
index 358a92be43eb..9b17bd4cbc5e 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -181,6 +181,38 @@ static inline void shmem_unacct_blocks(unsigned long flags, long pages)
 		vm_unacct_memory(pages * VM_ACCT(PAGE_SIZE));
 }
 
+static inline bool shmem_inode_acct_block(struct inode *inode, long pages)
+{
+	struct shmem_inode_info *info = SHMEM_I(inode);
+	struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
+
+	if (shmem_acct_block(info->flags, pages))
+		return false;
+
+	if (sbinfo->max_blocks) {
+		if (percpu_counter_compare(&sbinfo->used_blocks,
+					   sbinfo->max_blocks - pages) > 0)
+			goto unacct;
+		percpu_counter_add(&sbinfo->used_blocks, pages);
+	}
+
+	return true;
+
+unacct:
+	shmem_unacct_blocks(info->flags, pages);
+	return false;
+}
+
+static inline void shmem_inode_unacct_blocks(struct inode *inode, long pages)
+{
+	struct shmem_inode_info *info = SHMEM_I(inode);
+	struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
+
+	if (sbinfo->max_blocks)
+		percpu_counter_sub(&sbinfo->used_blocks, pages);
+	shmem_unacct_blocks(info->flags, pages);
+}
+
 static const struct super_operations shmem_ops;
 static const struct address_space_operations shmem_aops;
 static const struct file_operations shmem_file_operations;
@@ -237,61 +269,46 @@ static void shmem_recalc_inode(struct inode *inode)
 
 	freed = info->alloced - info->swapped - inode->i_mapping->nrpages;
 	if (freed > 0) {
-		struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
-		if (sbinfo->max_blocks)
-			percpu_counter_add(&sbinfo->used_blocks, -freed);
 		info->alloced -= freed;
 		inode->i_blocks -= freed * BLOCKS_PER_PAGE;
-		shmem_unacct_blocks(info->flags, freed);
+		shmem_inode_unacct_blocks(inode, freed);
 	}
 }
 
 bool shmem_charge(struct inode *inode, long pages)
 {
 	struct shmem_inode_info *info = SHMEM_I(inode);
-	struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
 	unsigned long flags;
 
-	if (shmem_acct_block(info->flags, pages))
+	if (!shmem_inode_acct_block(inode, pages))
 		return false;
+
+	/* nrpages adjustment first, then shmem_recalc_inode() when balanced */
+	inode->i_mapping->nrpages += pages;
+
 	spin_lock_irqsave(&info->lock, flags);
 	info->alloced += pages;
 	inode->i_blocks += pages * BLOCKS_PER_PAGE;
 	shmem_recalc_inode(inode);
 	spin_unlock_irqrestore(&info->lock, flags);
-	inode->i_mapping->nrpages += pages;
 
-	if (!sbinfo->max_blocks)
-		return true;
-	if (percpu_counter_compare(&sbinfo->used_blocks,
-				sbinfo->max_blocks - pages) > 0) {
-		inode->i_mapping->nrpages -= pages;
-		spin_lock_irqsave(&info->lock, flags);
-		info->alloced -= pages;
-		shmem_recalc_inode(inode);
-		spin_unlock_irqrestore(&info->lock, flags);
-		shmem_unacct_blocks(info->flags, pages);
-		return false;
-	}
-	percpu_counter_add(&sbinfo->used_blocks, pages);
 	return true;
 }
 
 void shmem_uncharge(struct inode *inode, long pages)
 {
 	struct shmem_inode_info *info = SHMEM_I(inode);
-	struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
 	unsigned long flags;
 
+	/* nrpages adjustment done by __delete_from_page_cache() or caller */
+
 	spin_lock_irqsave(&info->lock, flags);
 	info->alloced -= pages;
 	inode->i_blocks -= pages * BLOCKS_PER_PAGE;
 	shmem_recalc_inode(inode);
 	spin_unlock_irqrestore(&info->lock, flags);
 
-	if (sbinfo->max_blocks)
-		percpu_counter_sub(&sbinfo->used_blocks, pages);
-	shmem_unacct_blocks(info->flags, pages);
+	shmem_inode_unacct_blocks(inode, pages);
 }
 
 /*
@@ -1424,9 +1441,10 @@ static struct page *shmem_alloc_page(gfp_t gfp,
 }
 
 static struct page *shmem_alloc_and_acct_page(gfp_t gfp,
-		struct shmem_inode_info *info, struct shmem_sb_info *sbinfo,
+		struct inode *inode,
 		pgoff_t index, bool huge)
 {
+	struct shmem_inode_info *info = SHMEM_I(inode);
 	struct page *page;
 	int nr;
 	int err = -ENOSPC;
@@ -1435,14 +1453,8 @@ static struct page *shmem_alloc_and_acct_page(gfp_t gfp,
 		huge = false;
 	nr = huge ? HPAGE_PMD_NR : 1;
 
-	if (shmem_acct_block(info->flags, nr))
+	if (!shmem_inode_acct_block(inode, nr))
 		goto failed;
-	if (sbinfo->max_blocks) {
-		if (percpu_counter_compare(&sbinfo->used_blocks,
-					sbinfo->max_blocks - nr) > 0)
-			goto unacct;
-		percpu_counter_add(&sbinfo->used_blocks, nr);
-	}
 
 	if (huge)
 		page = shmem_alloc_hugepage(gfp, info, index);
@@ -1455,10 +1467,7 @@ static struct page *shmem_alloc_and_acct_page(gfp_t gfp,
 	}
 
 	err = -ENOMEM;
-	if (sbinfo->max_blocks)
-		percpu_counter_add(&sbinfo->used_blocks, -nr);
-unacct:
-	shmem_unacct_blocks(info->flags, nr);
+	shmem_inode_unacct_blocks(inode, nr);
 failed:
 	return ERR_PTR(err);
 }
@@ -1485,11 +1494,13 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp,
 {
 	struct page *oldpage, *newpage;
 	struct address_space *swap_mapping;
+	swp_entry_t entry;
 	pgoff_t swap_index;
 	int error;
 
 	oldpage = *pagep;
-	swap_index = page_private(oldpage);
+	entry.val = page_private(oldpage);
+	swap_index = swp_offset(entry);
 	swap_mapping = page_mapping(oldpage);
 
 	/*
@@ -1508,7 +1519,7 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp,
 	__SetPageLocked(newpage);
 	__SetPageSwapBacked(newpage);
 	SetPageUptodate(newpage);
-	set_page_private(newpage, swap_index);
+	set_page_private(newpage, entry.val);
 	SetPageSwapCache(newpage);
 
 	/*
@@ -1718,10 +1729,9 @@ repeat:
 		}
 
 alloc_huge:
-		page = shmem_alloc_and_acct_page(gfp, info, sbinfo,
-				index, true);
+		page = shmem_alloc_and_acct_page(gfp, inode, index, true);
 		if (IS_ERR(page)) {
-alloc_nohuge:		page = shmem_alloc_and_acct_page(gfp, info, sbinfo,
+alloc_nohuge:		page = shmem_alloc_and_acct_page(gfp, inode,
 					index, false);
 		}
 		if (IS_ERR(page)) {
@@ -1843,10 +1853,7 @@ clear:
 	 * Error recovery.
 	 */
 unacct:
-	if (sbinfo->max_blocks)
-		percpu_counter_sub(&sbinfo->used_blocks,
-				1 << compound_order(page));
-	shmem_unacct_blocks(info->flags, 1 << compound_order(page));
+	shmem_inode_unacct_blocks(inode, 1 << compound_order(page));
 
 	if (PageTransHuge(page)) {
 		unlock_page(page);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 68ecb7d71c2b..dca1fed0d7da 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4421,6 +4421,10 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet)
 	nf_reset(skb);
 	nf_reset_trace(skb);
 
+#ifdef CONFIG_NET_SWITCHDEV
+	skb->offload_fwd_mark = 0;
+#endif
+
 	if (!xnet)
 		return;
 
diff --git a/sound/core/control.c b/sound/core/control.c
index 995cde48c1be..511368fe974e 100644
--- a/sound/core/control.c
+++ b/sound/core/control.c
@@ -346,6 +346,40 @@ static int snd_ctl_find_hole(struct snd_card *card, unsigned int count)
 	return 0;
 }
 
+/* add a new kcontrol object; call with card->controls_rwsem locked */
+static int __snd_ctl_add(struct snd_card *card, struct snd_kcontrol *kcontrol)
+{
+	struct snd_ctl_elem_id id;
+	unsigned int idx;
+	unsigned int count;
+
+	id = kcontrol->id;
+	if (id.index > UINT_MAX - kcontrol->count)
+		return -EINVAL;
+
+	if (snd_ctl_find_id(card, &id)) {
+		dev_err(card->dev,
+			"control %i:%i:%i:%s:%i is already present\n",
+			id.iface, id.device, id.subdevice, id.name, id.index);
+		return -EBUSY;
+	}
+
+	if (snd_ctl_find_hole(card, kcontrol->count) < 0)
+		return -ENOMEM;
+
+	list_add_tail(&kcontrol->list, &card->controls);
+	card->controls_count += kcontrol->count;
+	kcontrol->id.numid = card->last_numid + 1;
+	card->last_numid += kcontrol->count;
+
+	id = kcontrol->id;
+	count = kcontrol->count;
+	for (idx = 0; idx < count; idx++, id.index++, id.numid++)
+		snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_ADD, &id);
+
+	return 0;
+}
+
 /**
  * snd_ctl_add - add the control instance to the card
  * @card: the card instance
@@ -362,45 +396,18 @@ static int snd_ctl_find_hole(struct snd_card *card, unsigned int count)
  */
 int snd_ctl_add(struct snd_card *card, struct snd_kcontrol *kcontrol)
 {
-	struct snd_ctl_elem_id id;
-	unsigned int idx;
-	unsigned int count;
 	int err = -EINVAL;
 
 	if (! kcontrol)
 		return err;
 	if (snd_BUG_ON(!card || !kcontrol->info))
 		goto error;
-	id = kcontrol->id;
-	if (id.index > UINT_MAX - kcontrol->count)
-		goto error;
 
 	down_write(&card->controls_rwsem);
-	if (snd_ctl_find_id(card, &id)) {
-		up_write(&card->controls_rwsem);
-		dev_err(card->dev, "control %i:%i:%i:%s:%i is already present\n",
-					id.iface,
-					id.device,
-					id.subdevice,
-					id.name,
-					id.index);
-		err = -EBUSY;
-		goto error;
-	}
-	if (snd_ctl_find_hole(card, kcontrol->count) < 0) {
-		up_write(&card->controls_rwsem);
-		err = -ENOMEM;
-		goto error;
-	}
-	list_add_tail(&kcontrol->list, &card->controls);
-	card->controls_count += kcontrol->count;
-	kcontrol->id.numid = card->last_numid + 1;
-	card->last_numid += kcontrol->count;
-	id = kcontrol->id;
-	count = kcontrol->count;
+	err = __snd_ctl_add(card, kcontrol);
 	up_write(&card->controls_rwsem);
-	for (idx = 0; idx < count; idx++, id.index++, id.numid++)
-		snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_ADD, &id);
+	if (err < 0)
+		goto error;
 	return 0;
 
  error:
@@ -1354,9 +1361,12 @@ static int snd_ctl_elem_add(struct snd_ctl_file *file,
 		kctl->tlv.c = snd_ctl_elem_user_tlv;
 
 	/* This function manage to free the instance on failure. */
-	err = snd_ctl_add(card, kctl);
-	if (err < 0)
-		return err;
+	down_write(&card->controls_rwsem);
+	err = __snd_ctl_add(card, kctl);
+	if (err < 0) {
+		snd_ctl_free_one(kctl);
+		goto unlock;
+	}
 	offset = snd_ctl_get_ioff(kctl, &info->id);
 	snd_ctl_build_ioff(&info->id, kctl, offset);
 	/*
@@ -1367,10 +1377,10 @@ static int snd_ctl_elem_add(struct snd_ctl_file *file,
 	 * which locks the element.
 	 */
 
-	down_write(&card->controls_rwsem);
 	card->user_ctl_count++;
-	up_write(&card->controls_rwsem);
 
+ unlock:
+	up_write(&card->controls_rwsem);
 	return 0;
 }
 
diff --git a/sound/isa/wss/wss_lib.c b/sound/isa/wss/wss_lib.c
index 913b731d2236..f40330ddb9b2 100644
--- a/sound/isa/wss/wss_lib.c
+++ b/sound/isa/wss/wss_lib.c
@@ -1531,7 +1531,6 @@ static int snd_wss_playback_open(struct snd_pcm_substream *substream)
 	if (err < 0) {
 		if (chip->release_dma)
 			chip->release_dma(chip, chip->dma_private_data, chip->dma1);
-		snd_free_pages(runtime->dma_area, runtime->dma_bytes);
 		return err;
 	}
 	chip->playback_substream = substream;
@@ -1572,7 +1571,6 @@ static int snd_wss_capture_open(struct snd_pcm_substream *substream)
 	if (err < 0) {
 		if (chip->release_dma)
 			chip->release_dma(chip, chip->dma_private_data, chip->dma2);
-		snd_free_pages(runtime->dma_area, runtime->dma_bytes);
 		return err;
 	}
 	chip->capture_substream = substream;
diff --git a/sound/pci/ac97/ac97_codec.c b/sound/pci/ac97/ac97_codec.c
index 82259ca61e64..c4840fda44b4 100644
--- a/sound/pci/ac97/ac97_codec.c
+++ b/sound/pci/ac97/ac97_codec.c
@@ -824,7 +824,7 @@ static int snd_ac97_put_spsa(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_
 {
 	struct snd_ac97 *ac97 = snd_kcontrol_chip(kcontrol);
 	int reg = kcontrol->private_value & 0xff;
-	int shift = (kcontrol->private_value >> 8) & 0xff;
+	int shift = (kcontrol->private_value >> 8) & 0x0f;
 	int mask = (kcontrol->private_value >> 16) & 0xff;
 	// int invert = (kcontrol->private_value >> 24) & 0xff;
 	unsigned short value, old, new;
diff --git a/sound/sparc/cs4231.c b/sound/sparc/cs4231.c
index 30bdc971883b..017e241b0ec9 100644
--- a/sound/sparc/cs4231.c
+++ b/sound/sparc/cs4231.c
@@ -1146,10 +1146,8 @@ static int snd_cs4231_playback_open(struct snd_pcm_substream *substream)
 	runtime->hw = snd_cs4231_playback;
 
 	err = snd_cs4231_open(chip, CS4231_MODE_PLAY);
-	if (err < 0) {
-		snd_free_pages(runtime->dma_area, runtime->dma_bytes);
+	if (err < 0)
 		return err;
-	}
 	chip->playback_substream = substream;
 	chip->p_periods_sent = 0;
 	snd_pcm_set_sync(substream);
@@ -1167,10 +1165,8 @@ static int snd_cs4231_capture_open(struct snd_pcm_substream *substream)
 	runtime->hw = snd_cs4231_capture;
 
 	err = snd_cs4231_open(chip, CS4231_MODE_RECORD);
-	if (err < 0) {
-		snd_free_pages(runtime->dma_area, runtime->dma_bytes);
+	if (err < 0)
 		return err;
-	}
 	chip->capture_substream = substream;
 	chip->c_periods_sent = 0;
 	snd_pcm_set_sync(substream);