diff --git a/Makefile b/Makefile
index 8280953c8a45..a7c847f495b0 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
 VERSION = 4
 PATCHLEVEL = 13
-SUBLEVEL = 11
+SUBLEVEL = 12
 EXTRAVERSION =
 NAME = Fearless Coyote
 
diff --git a/arch/arm/boot/dts/armada-375.dtsi b/arch/arm/boot/dts/armada-375.dtsi
index 50c5e8417802..10b99530280a 100644
--- a/arch/arm/boot/dts/armada-375.dtsi
+++ b/arch/arm/boot/dts/armada-375.dtsi
@@ -178,9 +178,9 @@
 				reg = <0x8000 0x1000>;
 				cache-unified;
 				cache-level = <2>;
-				arm,double-linefill-incr = <1>;
+				arm,double-linefill-incr = <0>;
 				arm,double-linefill-wrap = <0>;
-				arm,double-linefill = <1>;
+				arm,double-linefill = <0>;
 				prefetch-data = <1>;
 			};
 
diff --git a/arch/arm/boot/dts/armada-38x.dtsi b/arch/arm/boot/dts/armada-38x.dtsi
index af31f5d6c0e5..c3448622e79e 100644
--- a/arch/arm/boot/dts/armada-38x.dtsi
+++ b/arch/arm/boot/dts/armada-38x.dtsi
@@ -143,9 +143,9 @@
 				reg = <0x8000 0x1000>;
 				cache-unified;
 				cache-level = <2>;
-				arm,double-linefill-incr = <1>;
+				arm,double-linefill-incr = <0>;
 				arm,double-linefill-wrap = <0>;
-				arm,double-linefill = <1>;
+				arm,double-linefill = <0>;
 				prefetch-data = <1>;
 			};
 
diff --git a/arch/arm/boot/dts/armada-39x.dtsi b/arch/arm/boot/dts/armada-39x.dtsi
index 60fbfd5907c7..55d02641d930 100644
--- a/arch/arm/boot/dts/armada-39x.dtsi
+++ b/arch/arm/boot/dts/armada-39x.dtsi
@@ -111,9 +111,9 @@
 				reg = <0x8000 0x1000>;
 				cache-unified;
 				cache-level = <2>;
-				arm,double-linefill-incr = <1>;
+				arm,double-linefill-incr = <0>;
 				arm,double-linefill-wrap = <0>;
-				arm,double-linefill = <1>;
+				arm,double-linefill = <0>;
 				prefetch-data = <1>;
 			};
 
diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild
index 721ab5ecfb9b..0f2c8a2a8131 100644
--- a/arch/arm/include/asm/Kbuild
+++ b/arch/arm/include/asm/Kbuild
@@ -20,7 +20,6 @@ generic-y += simd.h
 generic-y += sizes.h
 generic-y += timex.h
 generic-y += trace_clock.h
-generic-y += unaligned.h
 
 generated-y += mach-types.h
 generated-y += unistd-nr.h
diff --git a/arch/arm/include/asm/unaligned.h b/arch/arm/include/asm/unaligned.h
new file mode 100644
index 000000000000..ab905ffcf193
--- /dev/null
+++ b/arch/arm/include/asm/unaligned.h
@@ -0,0 +1,27 @@
+#ifndef __ASM_ARM_UNALIGNED_H
+#define __ASM_ARM_UNALIGNED_H
+
+/*
+ * We generally want to set CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS on ARMv6+,
+ * but we don't want to use linux/unaligned/access_ok.h since that can lead
+ * to traps on unaligned stm/ldm or strd/ldrd.
+ */
+#include <asm/byteorder.h>
+
+#if defined(__LITTLE_ENDIAN)
+# include <linux/unaligned/le_struct.h>
+# include <linux/unaligned/be_byteshift.h>
+# include <linux/unaligned/generic.h>
+# define get_unaligned	__get_unaligned_le
+# define put_unaligned	__put_unaligned_le
+#elif defined(__BIG_ENDIAN)
+# include <linux/unaligned/be_struct.h>
+# include <linux/unaligned/le_byteshift.h>
+# include <linux/unaligned/generic.h>
+# define get_unaligned	__get_unaligned_be
+# define put_unaligned	__put_unaligned_be
+#else
+# error need to define endianess
+#endif
+
+#endif /* __ASM_ARM_UNALIGNED_H */
diff --git a/arch/arm/kvm/emulate.c b/arch/arm/kvm/emulate.c
index 0064b86a2c87..30a13647c54c 100644
--- a/arch/arm/kvm/emulate.c
+++ b/arch/arm/kvm/emulate.c
@@ -227,7 +227,7 @@ void kvm_inject_undefined(struct kvm_vcpu *vcpu)
 	u32 return_offset = (is_thumb) ? 2 : 4;
 
 	kvm_update_psr(vcpu, UND_MODE);
-	*vcpu_reg(vcpu, 14) = *vcpu_pc(vcpu) - return_offset;
+	*vcpu_reg(vcpu, 14) = *vcpu_pc(vcpu) + return_offset;
 
 	/* Branch to exception vector */
 	*vcpu_pc(vcpu) = exc_vector_base(vcpu) + vect_offset;
@@ -239,10 +239,8 @@ void kvm_inject_undefined(struct kvm_vcpu *vcpu)
  */
 static void inject_abt(struct kvm_vcpu *vcpu, bool is_pabt, unsigned long addr)
 {
-	unsigned long cpsr = *vcpu_cpsr(vcpu);
-	bool is_thumb = (cpsr & PSR_T_BIT);
 	u32 vect_offset;
-	u32 return_offset = (is_thumb) ? 4 : 0;
+	u32 return_offset = (is_pabt) ? 4 : 8;
 	bool is_lpae;
 
 	kvm_update_psr(vcpu, ABT_MODE);
diff --git a/arch/arm/kvm/hyp/Makefile b/arch/arm/kvm/hyp/Makefile
index 8679405b0b2b..92eab1d51785 100644
--- a/arch/arm/kvm/hyp/Makefile
+++ b/arch/arm/kvm/hyp/Makefile
@@ -2,7 +2,7 @@
 # Makefile for Kernel-based Virtual Machine module, HYP part
 #
 
-ccflags-y += -fno-stack-protector
+ccflags-y += -fno-stack-protector -DDISABLE_BRANCH_PROFILING
 
 KVM=../../../../virt/kvm
 
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 8a62648848e5..c99ffd8dce27 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -116,7 +116,7 @@ static void __dump_instr(const char *lvl, struct pt_regs *regs)
 	for (i = -4; i < 1; i++) {
 		unsigned int val, bad;
 
-		bad = __get_user(val, &((u32 *)addr)[i]);
+		bad = get_user(val, &((u32 *)addr)[i]);
 
 		if (!bad)
 			p += sprintf(p, i == 0 ? "(%08x) " : "%08x ", val);
diff --git a/arch/arm64/kvm/hyp/Makefile b/arch/arm64/kvm/hyp/Makefile
index 14c4e3b14bcb..48b03547a969 100644
--- a/arch/arm64/kvm/hyp/Makefile
+++ b/arch/arm64/kvm/hyp/Makefile
@@ -2,7 +2,7 @@
 # Makefile for Kernel-based Virtual Machine module, HYP part
 #
 
-ccflags-y += -fno-stack-protector
+ccflags-y += -fno-stack-protector -DDISABLE_BRANCH_PROFILING
 
 KVM=../../../../virt/kvm
 
diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c
index da6a8cfa54a0..3556715a774e 100644
--- a/arch/arm64/kvm/inject_fault.c
+++ b/arch/arm64/kvm/inject_fault.c
@@ -33,12 +33,26 @@
 #define LOWER_EL_AArch64_VECTOR		0x400
 #define LOWER_EL_AArch32_VECTOR		0x600
 
+/*
+ * Table taken from ARMv8 ARM DDI0487B-B, table G1-10.
+ */
+static const u8 return_offsets[8][2] = {
+	[0] = { 0, 0 },		/* Reset, unused */
+	[1] = { 4, 2 },		/* Undefined */
+	[2] = { 0, 0 },		/* SVC, unused */
+	[3] = { 4, 4 },		/* Prefetch abort */
+	[4] = { 8, 8 },		/* Data abort */
+	[5] = { 0, 0 },		/* HVC, unused */
+	[6] = { 4, 4 },		/* IRQ, unused */
+	[7] = { 4, 4 },		/* FIQ, unused */
+};
+
 static void prepare_fault32(struct kvm_vcpu *vcpu, u32 mode, u32 vect_offset)
 {
 	unsigned long cpsr;
 	unsigned long new_spsr_value = *vcpu_cpsr(vcpu);
 	bool is_thumb = (new_spsr_value & COMPAT_PSR_T_BIT);
-	u32 return_offset = (is_thumb) ? 4 : 0;
+	u32 return_offset = return_offsets[vect_offset >> 2][is_thumb];
 	u32 sctlr = vcpu_cp15(vcpu, c1_SCTLR);
 
 	cpsr = mode | COMPAT_PSR_I_BIT;
diff --git a/arch/mips/kernel/smp-cmp.c b/arch/mips/kernel/smp-cmp.c
index 76923349b4fe..797da807916f 100644
--- a/arch/mips/kernel/smp-cmp.c
+++ b/arch/mips/kernel/smp-cmp.c
@@ -19,7 +19,7 @@
 #undef DEBUG
 
 #include <linux/kernel.h>
-#include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/smp.h>
 #include <linux/cpumask.h>
 #include <linux/interrupt.h>
diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index 6bace7695788..20d7bc5f0eb5 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -66,6 +66,7 @@ EXPORT_SYMBOL(cpu_sibling_map);
 cpumask_t cpu_core_map[NR_CPUS] __read_mostly;
 EXPORT_SYMBOL(cpu_core_map);
 
+static DECLARE_COMPLETION(cpu_starting);
 static DECLARE_COMPLETION(cpu_running);
 
 /*
@@ -376,6 +377,12 @@ asmlinkage void start_secondary(void)
 	cpumask_set_cpu(cpu, &cpu_coherent_mask);
 	notify_cpu_starting(cpu);
 
+	/* Notify boot CPU that we're starting & ready to sync counters */
+	complete(&cpu_starting);
+
+	synchronise_count_slave(cpu);
+
+	/* The CPU is running and counters synchronised, now mark it online */
 	set_cpu_online(cpu, true);
 
 	set_cpu_sibling_map(cpu);
@@ -383,8 +390,11 @@ asmlinkage void start_secondary(void)
 
 	calculate_cpu_foreign_map();
 
+	/*
+	 * Notify boot CPU that we're up & online and it can safely return
+	 * from __cpu_up
+	 */
 	complete(&cpu_running);
-	synchronise_count_slave(cpu);
 
 	/*
 	 * irq will be enabled in ->smp_finish(), enabling it too early
@@ -443,17 +453,17 @@ int __cpu_up(unsigned int cpu, struct task_struct *tidle)
 {
 	mp_ops->boot_secondary(cpu, tidle);
 
-	/*
-	 * We must check for timeout here, as the CPU will not be marked
-	 * online until the counters are synchronised.
-	 */
-	if (!wait_for_completion_timeout(&cpu_running,
+	/* Wait for CPU to start and be ready to sync counters */
+	if (!wait_for_completion_timeout(&cpu_starting,
 					 msecs_to_jiffies(1000))) {
 		pr_crit("CPU%u: failed to start\n", cpu);
 		return -EIO;
 	}
 
 	synchronise_count_master(cpu);
+
+	/* Wait for CPU to finish startup & mark itself online before return */
+	wait_for_completion(&cpu_running);
 	return 0;
 }
 
diff --git a/arch/mips/mm/uasm-micromips.c b/arch/mips/mm/uasm-micromips.c
index c28ff53c8da0..cdb5a191b9d5 100644
--- a/arch/mips/mm/uasm-micromips.c
+++ b/arch/mips/mm/uasm-micromips.c
@@ -80,7 +80,7 @@ static const struct insn const insn_table_MM[insn_invalid] = {
 	[insn_jr]	= {M(mm_pool32a_op, 0, 0, 0, mm_jalr_op, mm_pool32axf_op), RS},
 	[insn_lb]	= {M(mm_lb32_op, 0, 0, 0, 0, 0), RT | RS | SIMM},
 	[insn_ld]	= {0, 0},
-	[insn_lh]	= {M(mm_lh32_op, 0, 0, 0, 0, 0), RS | RS | SIMM},
+	[insn_lh]	= {M(mm_lh32_op, 0, 0, 0, 0, 0), RT | RS | SIMM},
 	[insn_ll]	= {M(mm_pool32c_op, 0, 0, (mm_ll_func << 1), 0, 0), RS | RT | SIMM},
 	[insn_lld]	= {0, 0},
 	[insn_lui]	= {M(mm_pool32i_op, mm_lui_op, 0, 0, 0, 0), RS | SIMM},
diff --git a/arch/mips/net/ebpf_jit.c b/arch/mips/net/ebpf_jit.c
index 401776f92288..e45f05cc510d 100644
--- a/arch/mips/net/ebpf_jit.c
+++ b/arch/mips/net/ebpf_jit.c
@@ -1485,7 +1485,7 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 		}
 		src = ebpf_to_mips_reg(ctx, insn, src_reg_no_fp);
 		if (src < 0)
-			return dst;
+			return src;
 		if (BPF_MODE(insn->code) == BPF_XADD) {
 			switch (BPF_SIZE(insn->code)) {
 			case BPF_W:
diff --git a/arch/powerpc/include/asm/code-patching.h b/arch/powerpc/include/asm/code-patching.h
index 5482928eea1b..abef812de7f8 100644
--- a/arch/powerpc/include/asm/code-patching.h
+++ b/arch/powerpc/include/asm/code-patching.h
@@ -83,16 +83,8 @@ static inline unsigned long ppc_function_entry(void *func)
 	 * On PPC64 ABIv1 the function pointer actually points to the
 	 * function's descriptor. The first entry in the descriptor is the
 	 * address of the function text.
-	 *
-	 * However, we may also receive pointer to an assembly symbol. To
-	 * detect that, we first check if the function pointer we receive
-	 * already points to kernel/module text and we only dereference it
-	 * if it doesn't.
 	 */
-	if (kernel_text_address((unsigned long)func))
-		return (unsigned long)func;
-	else
-		return ((func_descr_t *)func)->entry;
+	return ((func_descr_t *)func)->entry;
 #else
 	return (unsigned long)func;
 #endif
diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
index 367494dc67d9..bebc3007a793 100644
--- a/arch/powerpc/kernel/kprobes.c
+++ b/arch/powerpc/kernel/kprobes.c
@@ -600,7 +600,12 @@ NOKPROBE_SYMBOL(kprobe_fault_handler);
 
 unsigned long arch_deref_entry_point(void *entry)
 {
-	return ppc_global_function_entry(entry);
+#ifdef PPC64_ELF_ABI_v1
+	if (!kernel_text_address((unsigned long)entry))
+		return ppc_global_function_entry(entry);
+	else
+#endif
+		return (unsigned long)entry;
 }
 NOKPROBE_SYMBOL(arch_deref_entry_point);
 
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index cdf82492b770..836877e2da22 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -21,7 +21,7 @@ obj-y			+= common.o
 obj-y			+= rdrand.o
 obj-y			+= match.o
 obj-y			+= bugs.o
-obj-$(CONFIG_CPU_FREQ)	+= aperfmperf.o
+obj-y			+= aperfmperf.o
 
 obj-$(CONFIG_PROC_FS)	+= proc.o
 obj-$(CONFIG_X86_FEATURE_NAMES) += capflags.o powerflags.o
diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c
index 0ee83321a313..957813e0180d 100644
--- a/arch/x86/kernel/cpu/aperfmperf.c
+++ b/arch/x86/kernel/cpu/aperfmperf.c
@@ -42,10 +42,6 @@ static void aperfmperf_snapshot_khz(void *dummy)
 	s64 time_delta = ktime_ms_delta(now, s->time);
 	unsigned long flags;
 
-	/* Don't bother re-computing within the cache threshold time. */
-	if (time_delta < APERFMPERF_CACHE_THRESHOLD_MS)
-		return;
-
 	local_irq_save(flags);
 	rdmsrl(MSR_IA32_APERF, aperf);
 	rdmsrl(MSR_IA32_MPERF, mperf);
@@ -74,6 +70,7 @@ static void aperfmperf_snapshot_khz(void *dummy)
 
 unsigned int arch_freq_get_on_cpu(int cpu)
 {
+	s64 time_delta;
 	unsigned int khz;
 
 	if (!cpu_khz)
@@ -82,6 +79,12 @@ unsigned int arch_freq_get_on_cpu(int cpu)
 	if (!static_cpu_has(X86_FEATURE_APERFMPERF))
 		return 0;
 
+	/* Don't bother re-computing within the cache threshold time. */
+	time_delta = ktime_ms_delta(ktime_get(), per_cpu(samples.time, cpu));
+	khz = per_cpu(samples.khz, cpu);
+	if (khz && time_delta < APERFMPERF_CACHE_THRESHOLD_MS)
+		return khz;
+
 	smp_call_function_single(cpu, aperfmperf_snapshot_khz, NULL, 1);
 	khz = per_cpu(samples.khz, cpu);
 	if (khz)
diff --git a/arch/x86/kernel/cpu/mcheck/dev-mcelog.c b/arch/x86/kernel/cpu/mcheck/dev-mcelog.c
index 10cec43aac38..7f85b76f43bc 100644
--- a/arch/x86/kernel/cpu/mcheck/dev-mcelog.c
+++ b/arch/x86/kernel/cpu/mcheck/dev-mcelog.c
@@ -24,14 +24,6 @@ static DEFINE_MUTEX(mce_chrdev_read_mutex);
 static char mce_helper[128];
 static char *mce_helper_argv[2] = { mce_helper, NULL };
 
-#define mce_log_get_idx_check(p) \
-({ \
-	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \
-			 !lockdep_is_held(&mce_chrdev_read_mutex), \
-			 "suspicious mce_log_get_idx_check() usage"); \
-	smp_load_acquire(&(p)); \
-})
-
 /*
  * Lockless MCE logging infrastructure.
  * This avoids deadlocks on printk locks without having to break locks. Also
@@ -53,43 +45,32 @@ static int dev_mce_log(struct notifier_block *nb, unsigned long val,
 				void *data)
 {
 	struct mce *mce = (struct mce *)data;
-	unsigned int next, entry;
-
-	wmb();
-	for (;;) {
-		entry = mce_log_get_idx_check(mcelog.next);
-		for (;;) {
-
-			/*
-			 * When the buffer fills up discard new entries.
-			 * Assume that the earlier errors are the more
-			 * interesting ones:
-			 */
-			if (entry >= MCE_LOG_LEN) {
-				set_bit(MCE_OVERFLOW,
-					(unsigned long *)&mcelog.flags);
-				return NOTIFY_OK;
-			}
-			/* Old left over entry. Skip: */
-			if (mcelog.entry[entry].finished) {
-				entry++;
-				continue;
-			}
-			break;
-		}
-		smp_rmb();
-		next = entry + 1;
-		if (cmpxchg(&mcelog.next, entry, next) == entry)
-			break;
+	unsigned int entry;
+
+	mutex_lock(&mce_chrdev_read_mutex);
+
+	entry = mcelog.next;
+
+	/*
+	 * When the buffer fills up discard new entries. Assume that the
+	 * earlier errors are the more interesting ones:
+	 */
+	if (entry >= MCE_LOG_LEN) {
+		set_bit(MCE_OVERFLOW, (unsigned long *)&mcelog.flags);
+		goto unlock;
 	}
+
+	mcelog.next = entry + 1;
+
 	memcpy(mcelog.entry + entry, mce, sizeof(struct mce));
-	wmb();
 	mcelog.entry[entry].finished = 1;
-	wmb();
 
 	/* wake processes polling /dev/mcelog */
 	wake_up_interruptible(&mce_chrdev_wait);
 
+unlock:
+	mutex_unlock(&mce_chrdev_read_mutex);
+
 	return NOTIFY_OK;
 }
 
@@ -177,13 +158,6 @@ static int mce_chrdev_release(struct inode *inode, struct file *file)
 	return 0;
 }
 
-static void collect_tscs(void *data)
-{
-	unsigned long *cpu_tsc = (unsigned long *)data;
-
-	cpu_tsc[smp_processor_id()] = rdtsc();
-}
-
 static int mce_apei_read_done;
 
 /* Collect MCE record of previous boot in persistent storage via APEI ERST. */
@@ -231,14 +205,9 @@ static ssize_t mce_chrdev_read(struct file *filp, char __user *ubuf,
 				size_t usize, loff_t *off)
 {
 	char __user *buf = ubuf;
-	unsigned long *cpu_tsc;
-	unsigned prev, next;
+	unsigned next;
 	int i, err;
 
-	cpu_tsc = kmalloc(nr_cpu_ids * sizeof(long), GFP_KERNEL);
-	if (!cpu_tsc)
-		return -ENOMEM;
-
 	mutex_lock(&mce_chrdev_read_mutex);
 
 	if (!mce_apei_read_done) {
@@ -247,65 +216,29 @@ static ssize_t mce_chrdev_read(struct file *filp, char __user *ubuf,
 			goto out;
 	}
 
-	next = mce_log_get_idx_check(mcelog.next);
-
 	/* Only supports full reads right now */
 	err = -EINVAL;
 	if (*off != 0 || usize < MCE_LOG_LEN*sizeof(struct mce))
 		goto out;
 
+	next = mcelog.next;
 	err = 0;
-	prev = 0;
-	do {
-		for (i = prev; i < next; i++) {
-			unsigned long start = jiffies;
-			struct mce *m = &mcelog.entry[i];
-
-			while (!m->finished) {
-				if (time_after_eq(jiffies, start + 2)) {
-					memset(m, 0, sizeof(*m));
-					goto timeout;
-				}
-				cpu_relax();
-			}
-			smp_rmb();
-			err |= copy_to_user(buf, m, sizeof(*m));
-			buf += sizeof(*m);
-timeout:
-			;
-		}
-
-		memset(mcelog.entry + prev, 0,
-		       (next - prev) * sizeof(struct mce));
-		prev = next;
-		next = cmpxchg(&mcelog.next, prev, 0);
-	} while (next != prev);
-
-	synchronize_sched();
 
-	/*
-	 * Collect entries that were still getting written before the
-	 * synchronize.
-	 */
-	on_each_cpu(collect_tscs, cpu_tsc, 1);
-
-	for (i = next; i < MCE_LOG_LEN; i++) {
+	for (i = 0; i < next; i++) {
 		struct mce *m = &mcelog.entry[i];
 
-		if (m->finished && m->tsc < cpu_tsc[m->cpu]) {
-			err |= copy_to_user(buf, m, sizeof(*m));
-			smp_rmb();
-			buf += sizeof(*m);
-			memset(m, 0, sizeof(*m));
-		}
+		err |= copy_to_user(buf, m, sizeof(*m));
+		buf += sizeof(*m);
 	}
 
+	memset(mcelog.entry, 0, next * sizeof(struct mce));
+	mcelog.next = 0;
+
 	if (err)
 		err = -EFAULT;
 
 out:
 	mutex_unlock(&mce_chrdev_read_mutex);
-	kfree(cpu_tsc);
 
 	return err ? err : buf - ubuf;
 }
diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c
index 218f79825b3c..510e69596278 100644
--- a/arch/x86/kernel/cpu/proc.c
+++ b/arch/x86/kernel/cpu/proc.c
@@ -2,6 +2,7 @@
 #include <linux/timex.h>
 #include <linux/string.h>
 #include <linux/seq_file.h>
+#include <linux/cpufreq.h>
 
 /*
  *	Get CPU information for use by the procfs.
@@ -75,9 +76,16 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 	if (c->microcode)
 		seq_printf(m, "microcode\t: 0x%x\n", c->microcode);
 
-	if (cpu_has(c, X86_FEATURE_TSC))
+	if (cpu_has(c, X86_FEATURE_TSC)) {
+		unsigned int freq = arch_freq_get_on_cpu(cpu);
+
+		if (!freq)
+			freq = cpufreq_quick_get(cpu);
+		if (!freq)
+			freq = cpu_khz;
 		seq_printf(m, "cpu MHz\t\t: %u.%03u\n",
-			   cpu_khz / 1000, (cpu_khz % 1000));
+			   freq / 1000, (freq % 1000));
+	}
 
 	/* Cache size */
 	if (c->x86_cache_size >= 0)
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index d3d5523862c2..b49952b5a189 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -593,10 +593,22 @@ static int virtblk_map_queues(struct blk_mq_tag_set *set)
 	return blk_mq_virtio_map_queues(set, vblk->vdev, 0);
 }
 
+#ifdef CONFIG_VIRTIO_BLK_SCSI
+static void virtblk_initialize_rq(struct request *req)
+{
+	struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);
+
+	scsi_req_init(&vbr->sreq);
+}
+#endif
+
 static const struct blk_mq_ops virtio_mq_ops = {
 	.queue_rq	= virtio_queue_rq,
 	.complete	= virtblk_request_done,
 	.init_request	= virtblk_init_request,
+#ifdef CONFIG_VIRTIO_BLK_SCSI
+	.initialize_rq_fn = virtblk_initialize_rq,
+#endif
 	.map_queues	= virtblk_map_queues,
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
index 31db356476f8..1086cf86354f 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
@@ -93,6 +93,10 @@ static int uvd_v6_0_early_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	if (!(adev->flags & AMD_IS_APU) &&
+	    (RREG32_SMC(ixCC_HARVEST_FUSES) & CC_HARVEST_FUSES__UVD_DISABLE_MASK))
+		return -ENOENT;
+
 	uvd_v6_0_set_ring_funcs(adev);
 	uvd_v6_0_set_irq_funcs(adev);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
index 90332f55cfba..cf81065e3c5a 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
@@ -365,15 +365,10 @@ static unsigned vce_v3_0_get_harvest_config(struct amdgpu_device *adev)
 {
 	u32 tmp;
 
-	/* Fiji, Stoney, Polaris10, Polaris11, Polaris12 are single pipe */
 	if ((adev->asic_type == CHIP_FIJI) ||
-	    (adev->asic_type == CHIP_STONEY) ||
-	    (adev->asic_type == CHIP_POLARIS10) ||
-	    (adev->asic_type == CHIP_POLARIS11) ||
-	    (adev->asic_type == CHIP_POLARIS12))
+	    (adev->asic_type == CHIP_STONEY))
 		return AMDGPU_VCE_HARVEST_VCE1;
 
-	/* Tonga and CZ are dual or single pipe */
 	if (adev->flags & AMD_IS_APU)
 		tmp = (RREG32_SMC(ixVCE_HARVEST_FUSE_MACRO__ADDRESS) &
 		       VCE_HARVEST_FUSE_MACRO__MASK) >>
@@ -391,6 +386,11 @@ static unsigned vce_v3_0_get_harvest_config(struct amdgpu_device *adev)
 	case 3:
 		return AMDGPU_VCE_HARVEST_VCE0 | AMDGPU_VCE_HARVEST_VCE1;
 	default:
+		if ((adev->asic_type == CHIP_POLARIS10) ||
+		    (adev->asic_type == CHIP_POLARIS11) ||
+		    (adev->asic_type == CHIP_POLARIS12))
+			return AMDGPU_VCE_HARVEST_VCE1;
+
 		return 0;
 	}
 }
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 61c313e21a91..169843de91cb 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -3687,9 +3687,16 @@ intel_edp_init_dpcd(struct intel_dp *intel_dp)
 
 	}
 
-	/* Read the eDP Display control capabilities registers */
-	if ((intel_dp->dpcd[DP_EDP_CONFIGURATION_CAP] & DP_DPCD_DISPLAY_CONTROL_CAPABLE) &&
-	    drm_dp_dpcd_read(&intel_dp->aux, DP_EDP_DPCD_REV,
+	/*
+	 * Read the eDP display control registers.
+	 *
+	 * Do this independent of DP_DPCD_DISPLAY_CONTROL_CAPABLE bit in
+	 * DP_EDP_CONFIGURATION_CAP, because some buggy displays do not have it
+	 * set, but require eDP 1.4+ detection (e.g. for supported link rates
+	 * method). The display control registers should read zero if they're
+	 * not supported anyway.
+	 */
+	if (drm_dp_dpcd_read(&intel_dp->aux, DP_EDP_DPCD_REV,
 			     intel_dp->edp_dpcd, sizeof(intel_dp->edp_dpcd)) ==
 			     sizeof(intel_dp->edp_dpcd))
 		DRM_DEBUG_KMS("EDP DPCD : %*ph\n", (int) sizeof(intel_dp->edp_dpcd),
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index d93efb49a2e2..954e9454625e 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -495,7 +495,6 @@ struct intel_crtc_scaler_state {
 
 struct intel_pipe_wm {
 	struct intel_wm_level wm[5];
-	struct intel_wm_level raw_wm[5];
 	uint32_t linetime;
 	bool fbc_wm_enabled;
 	bool pipe_enabled;
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 40b224b44d1b..1427cec843b9 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2696,9 +2696,9 @@ static void ilk_compute_wm_level(const struct drm_i915_private *dev_priv,
 				 const struct intel_crtc *intel_crtc,
 				 int level,
 				 struct intel_crtc_state *cstate,
-				 struct intel_plane_state *pristate,
-				 struct intel_plane_state *sprstate,
-				 struct intel_plane_state *curstate,
+				 const struct intel_plane_state *pristate,
+				 const struct intel_plane_state *sprstate,
+				 const struct intel_plane_state *curstate,
 				 struct intel_wm_level *result)
 {
 	uint16_t pri_latency = dev_priv->wm.pri_latency[level];
@@ -3016,28 +3016,24 @@ static int ilk_compute_pipe_wm(struct intel_crtc_state *cstate)
 	struct intel_pipe_wm *pipe_wm;
 	struct drm_device *dev = state->dev;
 	const struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_plane *intel_plane;
-	struct intel_plane_state *pristate = NULL;
-	struct intel_plane_state *sprstate = NULL;
-	struct intel_plane_state *curstate = NULL;
+	struct drm_plane *plane;
+	const struct drm_plane_state *plane_state;
+	const struct intel_plane_state *pristate = NULL;
+	const struct intel_plane_state *sprstate = NULL;
+	const struct intel_plane_state *curstate = NULL;
 	int level, max_level = ilk_wm_max_level(dev_priv), usable_level;
 	struct ilk_wm_maximums max;
 
 	pipe_wm = &cstate->wm.ilk.optimal;
 
-	for_each_intel_plane_on_crtc(dev, intel_crtc, intel_plane) {
-		struct intel_plane_state *ps;
-
-		ps = intel_atomic_get_existing_plane_state(state,
-							   intel_plane);
-		if (!ps)
-			continue;
+	drm_atomic_crtc_state_for_each_plane_state(plane, plane_state, &cstate->base) {
+		const struct intel_plane_state *ps = to_intel_plane_state(plane_state);
 
-		if (intel_plane->base.type == DRM_PLANE_TYPE_PRIMARY)
+		if (plane->type == DRM_PLANE_TYPE_PRIMARY)
 			pristate = ps;
-		else if (intel_plane->base.type == DRM_PLANE_TYPE_OVERLAY)
+		else if (plane->type == DRM_PLANE_TYPE_OVERLAY)
 			sprstate = ps;
-		else if (intel_plane->base.type == DRM_PLANE_TYPE_CURSOR)
+		else if (plane->type == DRM_PLANE_TYPE_CURSOR)
 			curstate = ps;
 	}
 
@@ -3059,11 +3055,9 @@ static int ilk_compute_pipe_wm(struct intel_crtc_state *cstate)
 	if (pipe_wm->sprites_scaled)
 		usable_level = 0;
 
-	ilk_compute_wm_level(dev_priv, intel_crtc, 0, cstate,
-			     pristate, sprstate, curstate, &pipe_wm->raw_wm[0]);
-
 	memset(&pipe_wm->wm, 0, sizeof(pipe_wm->wm));
-	pipe_wm->wm[0] = pipe_wm->raw_wm[0];
+	ilk_compute_wm_level(dev_priv, intel_crtc, 0, cstate,
+			     pristate, sprstate, curstate, &pipe_wm->wm[0]);
 
 	if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))
 		pipe_wm->linetime = hsw_compute_linetime_wm(cstate);
@@ -3073,8 +3067,8 @@ static int ilk_compute_pipe_wm(struct intel_crtc_state *cstate)
 
 	ilk_compute_wm_reg_maximums(dev_priv, 1, &max);
 
-	for (level = 1; level <= max_level; level++) {
-		struct intel_wm_level *wm = &pipe_wm->raw_wm[level];
+	for (level = 1; level <= usable_level; level++) {
+		struct intel_wm_level *wm = &pipe_wm->wm[level];
 
 		ilk_compute_wm_level(dev_priv, intel_crtc, level, cstate,
 				     pristate, sprstate, curstate, wm);
@@ -3084,13 +3078,10 @@ static int ilk_compute_pipe_wm(struct intel_crtc_state *cstate)
 		 * register maximums since such watermarks are
 		 * always invalid.
 		 */
-		if (level > usable_level)
-			continue;
-
-		if (ilk_validate_wm_level(level, &max, wm))
-			pipe_wm->wm[level] = *wm;
-		else
-			usable_level = level;
+		if (!ilk_validate_wm_level(level, &max, wm)) {
+			memset(wm, 0, sizeof(*wm));
+			break;
+		}
 	}
 
 	return 0;
diff --git a/drivers/irqchip/irq-mvebu-gicp.c b/drivers/irqchip/irq-mvebu-gicp.c
index b283fc90be1e..17a4a7b6cdbb 100644
--- a/drivers/irqchip/irq-mvebu-gicp.c
+++ b/drivers/irqchip/irq-mvebu-gicp.c
@@ -194,6 +194,7 @@ static int mvebu_gicp_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	gicp->dev = &pdev->dev;
+	spin_lock_init(&gicp->spi_lock);
 
 	gicp->res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!gicp->res)
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index e702d48bd023..81ba6e0d88d8 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -204,7 +204,8 @@ check_name(struct dentry *direntry, struct cifs_tcon *tcon)
 	struct cifs_sb_info *cifs_sb = CIFS_SB(direntry->d_sb);
 	int i;
 
-	if (unlikely(direntry->d_name.len >
+	if (unlikely(tcon->fsAttrInfo.MaxPathNameComponentLength &&
+		     direntry->d_name.len >
 		     le32_to_cpu(tcon->fsAttrInfo.MaxPathNameComponentLength)))
 		return -ENAMETOOLONG;
 
@@ -520,7 +521,7 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry,
 
 	rc = check_name(direntry, tcon);
 	if (rc)
-		goto out_free_xid;
+		goto out;
 
 	server = tcon->ses->server;
 
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 28d2753be094..a9e3b26e1b72 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -855,9 +855,12 @@ static int hugetlbfs_error_remove_page(struct address_space *mapping,
 				struct page *page)
 {
 	struct inode *inode = mapping->host;
+	pgoff_t index = page->index;
 
 	remove_huge_page(page);
-	hugetlb_fix_reserve_counts(inode);
+	if (unlikely(hugetlb_unreserve_pages(inode, index, index + 1, 1)))
+		hugetlb_fix_reserve_counts(inode);
+
 	return 0;
 }
 
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index fb15a96df0b6..386aecce881d 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -7310,13 +7310,24 @@ int ocfs2_truncate_inline(struct inode *inode, struct buffer_head *di_bh,
 
 static int ocfs2_trim_extent(struct super_block *sb,
 			     struct ocfs2_group_desc *gd,
-			     u32 start, u32 count)
+			     u64 group, u32 start, u32 count)
 {
 	u64 discard, bcount;
+	struct ocfs2_super *osb = OCFS2_SB(sb);
 
 	bcount = ocfs2_clusters_to_blocks(sb, count);
-	discard = le64_to_cpu(gd->bg_blkno) +
-			ocfs2_clusters_to_blocks(sb, start);
+	discard = ocfs2_clusters_to_blocks(sb, start);
+
+	/*
+	 * For the first cluster group, the gd->bg_blkno is not at the start
+	 * of the group, but at an offset from the start. If we add it while
+	 * calculating discard for first group, we will wrongly start fstrim a
+	 * few blocks after the desried start block and the range can cross
+	 * over into the next cluster group. So, add it only if this is not
+	 * the first cluster group.
+	 */
+	if (group != osb->first_cluster_group_blkno)
+		discard += le64_to_cpu(gd->bg_blkno);
 
 	trace_ocfs2_trim_extent(sb, (unsigned long long)discard, bcount);
 
@@ -7324,7 +7335,7 @@ static int ocfs2_trim_extent(struct super_block *sb,
 }
 
 static int ocfs2_trim_group(struct super_block *sb,
-			    struct ocfs2_group_desc *gd,
+			    struct ocfs2_group_desc *gd, u64 group,
 			    u32 start, u32 max, u32 minbits)
 {
 	int ret = 0, count = 0, next;
@@ -7343,7 +7354,7 @@ static int ocfs2_trim_group(struct super_block *sb,
 		next = ocfs2_find_next_bit(bitmap, max, start);
 
 		if ((next - start) >= minbits) {
-			ret = ocfs2_trim_extent(sb, gd,
+			ret = ocfs2_trim_extent(sb, gd, group,
 						start, next - start);
 			if (ret < 0) {
 				mlog_errno(ret);
@@ -7441,7 +7452,8 @@ int ocfs2_trim_fs(struct super_block *sb, struct fstrim_range *range)
 		}
 
 		gd = (struct ocfs2_group_desc *)gd_bh->b_data;
-		cnt = ocfs2_trim_group(sb, gd, first_bit, last_bit, minlen);
+		cnt = ocfs2_trim_group(sb, gd, group,
+				       first_bit, last_bit, minlen);
 		brelse(gd_bh);
 		gd_bh = NULL;
 		if (cnt < 0) {
diff --git a/include/linux/swap.h b/include/linux/swap.h
index d83d28e53e62..a615eda102ae 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -246,6 +246,10 @@ struct swap_info_struct {
 					 * both locks need hold, hold swap_lock
 					 * first.
 					 */
+	spinlock_t cont_lock;		/*
+					 * protect swap count continuation page
+					 * list.
+					 */
 	struct work_struct discard_work; /* discard worker */
 	struct swap_cluster_list discard_clusters; /* discard clusters list */
 };
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 7242a6e1ec76..95bbe99e4e6c 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -901,9 +901,11 @@ list_update_cgroup_event(struct perf_event *event,
 	cpuctx_entry = &cpuctx->cgrp_cpuctx_entry;
 	/* cpuctx->cgrp is NULL unless a cgroup event is active in this CPU .*/
 	if (add) {
+		struct perf_cgroup *cgrp = perf_cgroup_from_task(current, ctx);
+
 		list_add(cpuctx_entry, this_cpu_ptr(&cgrp_cpuctx_list));
-		if (perf_cgroup_from_task(current, ctx) == event->cgrp)
-			cpuctx->cgrp = event->cgrp;
+		if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup))
+			cpuctx->cgrp = cgrp;
 	} else {
 		list_del(cpuctx_entry);
 		cpuctx->cgrp = NULL;
diff --git a/kernel/futex.c b/kernel/futex.c
index bf57ab12ffe8..a6639b346373 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -901,11 +901,27 @@ void exit_pi_state_list(struct task_struct *curr)
 	 */
 	raw_spin_lock_irq(&curr->pi_lock);
 	while (!list_empty(head)) {
-
 		next = head->next;
 		pi_state = list_entry(next, struct futex_pi_state, list);
 		key = pi_state->key;
 		hb = hash_futex(&key);
+
+		/*
+		 * We can race against put_pi_state() removing itself from the
+		 * list (a waiter going away). put_pi_state() will first
+		 * decrement the reference count and then modify the list, so
+		 * its possible to see the list entry but fail this reference
+		 * acquire.
+		 *
+		 * In that case; drop the locks to let put_pi_state() make
+		 * progress and retry the loop.
+		 */
+		if (!atomic_inc_not_zero(&pi_state->refcount)) {
+			raw_spin_unlock_irq(&curr->pi_lock);
+			cpu_relax();
+			raw_spin_lock_irq(&curr->pi_lock);
+			continue;
+		}
 		raw_spin_unlock_irq(&curr->pi_lock);
 
 		spin_lock(&hb->lock);
@@ -916,8 +932,10 @@ void exit_pi_state_list(struct task_struct *curr)
 		 * task still owns the PI-state:
 		 */
 		if (head->next != next) {
+			/* retain curr->pi_lock for the loop invariant */
 			raw_spin_unlock(&pi_state->pi_mutex.wait_lock);
 			spin_unlock(&hb->lock);
+			put_pi_state(pi_state);
 			continue;
 		}
 
@@ -925,9 +943,8 @@ void exit_pi_state_list(struct task_struct *curr)
 		WARN_ON(list_empty(&pi_state->list));
 		list_del_init(&pi_state->list);
 		pi_state->owner = NULL;
-		raw_spin_unlock(&curr->pi_lock);
 
-		get_pi_state(pi_state);
+		raw_spin_unlock(&curr->pi_lock);
 		raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
 		spin_unlock(&hb->lock);
 
diff --git a/lib/asn1_decoder.c b/lib/asn1_decoder.c
index 0bd8a611eb83..fef5d2e114be 100644
--- a/lib/asn1_decoder.c
+++ b/lib/asn1_decoder.c
@@ -284,6 +284,9 @@ int asn1_ber_decoder(const struct asn1_decoder *decoder,
 				if (unlikely(len > datalen - dp))
 					goto data_overrun_error;
 			}
+		} else {
+			if (unlikely(len > datalen - dp))
+				goto data_overrun_error;
 		}
 
 		if (flags & FLAG_CONS) {
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 31e207cb399b..011725849f52 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3977,6 +3977,9 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
 			    unsigned long src_addr,
 			    struct page **pagep)
 {
+	struct address_space *mapping;
+	pgoff_t idx;
+	unsigned long size;
 	int vm_shared = dst_vma->vm_flags & VM_SHARED;
 	struct hstate *h = hstate_vma(dst_vma);
 	pte_t _dst_pte;
@@ -4014,13 +4017,24 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
 	__SetPageUptodate(page);
 	set_page_huge_active(page);
 
+	mapping = dst_vma->vm_file->f_mapping;
+	idx = vma_hugecache_offset(h, dst_vma, dst_addr);
+
 	/*
 	 * If shared, add to page cache
 	 */
 	if (vm_shared) {
-		struct address_space *mapping = dst_vma->vm_file->f_mapping;
-		pgoff_t idx = vma_hugecache_offset(h, dst_vma, dst_addr);
+		size = i_size_read(mapping->host) >> huge_page_shift(h);
+		ret = -EFAULT;
+		if (idx >= size)
+			goto out_release_nounlock;
 
+		/*
+		 * Serialization between remove_inode_hugepages() and
+		 * huge_add_to_page_cache() below happens through the
+		 * hugetlb_fault_mutex_table that here must be hold by
+		 * the caller.
+		 */
 		ret = huge_add_to_page_cache(page, mapping, idx);
 		if (ret)
 			goto out_release_nounlock;
@@ -4029,6 +4043,20 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
 	ptl = huge_pte_lockptr(h, dst_mm, dst_pte);
 	spin_lock(ptl);
 
+	/*
+	 * Recheck the i_size after holding PT lock to make sure not
+	 * to leave any page mapped (as page_mapped()) beyond the end
+	 * of the i_size (remove_inode_hugepages() is strict about
+	 * enforcing that). If we bail out here, we'll also leave a
+	 * page in the radix tree in the vm_shared case beyond the end
+	 * of the i_size, but remove_inode_hugepages() will take care
+	 * of it as soon as we drop the hugetlb_fault_mutex_table.
+	 */
+	size = i_size_read(mapping->host) >> huge_page_shift(h);
+	ret = -EFAULT;
+	if (idx >= size)
+		goto out_release_unlock;
+
 	ret = -EEXIST;
 	if (!huge_pte_none(huge_ptep_get(dst_pte)))
 		goto out_release_unlock;
diff --git a/mm/swapfile.c b/mm/swapfile.c
index a8952b6563c6..3191465b0ccf 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -2635,6 +2635,7 @@ static struct swap_info_struct *alloc_swap_info(void)
 	p->flags = SWP_USED;
 	spin_unlock(&swap_lock);
 	spin_lock_init(&p->lock);
+	spin_lock_init(&p->cont_lock);
 
 	return p;
 }
@@ -3307,6 +3308,7 @@ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask)
 	head = vmalloc_to_page(si->swap_map + offset);
 	offset &= ~PAGE_MASK;
 
+	spin_lock(&si->cont_lock);
 	/*
 	 * Page allocation does not initialize the page's lru field,
 	 * but it does always reset its private field.
@@ -3326,7 +3328,7 @@ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask)
 		 * a continuation page, free our allocation and use this one.
 		 */
 		if (!(count & COUNT_CONTINUED))
-			goto out;
+			goto out_unlock_cont;
 
 		map = kmap_atomic(list_page) + offset;
 		count = *map;
@@ -3337,11 +3339,13 @@ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask)
 		 * free our allocation and use this one.
 		 */
 		if ((count & ~COUNT_CONTINUED) != SWAP_CONT_MAX)
-			goto out;
+			goto out_unlock_cont;
 	}
 
 	list_add_tail(&page->lru, &head->lru);
 	page = NULL;			/* now it's attached, don't free it */
+out_unlock_cont:
+	spin_unlock(&si->cont_lock);
 out:
 	unlock_cluster(ci);
 	spin_unlock(&si->lock);
@@ -3366,6 +3370,7 @@ static bool swap_count_continued(struct swap_info_struct *si,
 	struct page *head;
 	struct page *page;
 	unsigned char *map;
+	bool ret;
 
 	head = vmalloc_to_page(si->swap_map + offset);
 	if (page_private(head) != SWP_CONTINUED) {
@@ -3373,6 +3378,7 @@ static bool swap_count_continued(struct swap_info_struct *si,
 		return false;		/* need to add count continuation */
 	}
 
+	spin_lock(&si->cont_lock);
 	offset &= ~PAGE_MASK;
 	page = list_entry(head->lru.next, struct page, lru);
 	map = kmap_atomic(page) + offset;
@@ -3393,8 +3399,10 @@ static bool swap_count_continued(struct swap_info_struct *si,
 		if (*map == SWAP_CONT_MAX) {
 			kunmap_atomic(map);
 			page = list_entry(page->lru.next, struct page, lru);
-			if (page == head)
-				return false;	/* add count continuation */
+			if (page == head) {
+				ret = false;	/* add count continuation */
+				goto out;
+			}
 			map = kmap_atomic(page) + offset;
 init_map:		*map = 0;		/* we didn't zero the page */
 		}
@@ -3407,7 +3415,7 @@ init_map:		*map = 0;		/* we didn't zero the page */
 			kunmap_atomic(map);
 			page = list_entry(page->lru.prev, struct page, lru);
 		}
-		return true;			/* incremented */
+		ret = true;			/* incremented */
 
 	} else {				/* decrementing */
 		/*
@@ -3433,8 +3441,11 @@ init_map:		*map = 0;		/* we didn't zero the page */
 			kunmap_atomic(map);
 			page = list_entry(page->lru.prev, struct page, lru);
 		}
-		return count == COUNT_CONTINUED;
+		ret = count == COUNT_CONTINUED;
 	}
+out:
+	spin_unlock(&si->cont_lock);
+	return ret;
 }
 
 /*
diff --git a/security/keys/keyring.c b/security/keys/keyring.c
index 06173b091a74..c04032302a25 100644
--- a/security/keys/keyring.c
+++ b/security/keys/keyring.c
@@ -459,34 +459,33 @@ static long keyring_read(const struct key *keyring,
 			 char __user *buffer, size_t buflen)
 {
 	struct keyring_read_iterator_context ctx;
-	unsigned long nr_keys;
-	int ret;
+	long ret;
 
 	kenter("{%d},,%zu", key_serial(keyring), buflen);
 
 	if (buflen & (sizeof(key_serial_t) - 1))
 		return -EINVAL;
 
-	nr_keys = keyring->keys.nr_leaves_on_tree;
-	if (nr_keys == 0)
-		return 0;
-
-	/* Calculate how much data we could return */
-	if (!buffer || !buflen)
-		return nr_keys * sizeof(key_serial_t);
-
-	/* Copy the IDs of the subscribed keys into the buffer */
-	ctx.buffer = (key_serial_t __user *)buffer;
-	ctx.buflen = buflen;
-	ctx.count = 0;
-	ret = assoc_array_iterate(&keyring->keys, keyring_read_iterator, &ctx);
-	if (ret < 0) {
-		kleave(" = %d [iterate]", ret);
-		return ret;
+	/* Copy as many key IDs as fit into the buffer */
+	if (buffer && buflen) {
+		ctx.buffer = (key_serial_t __user *)buffer;
+		ctx.buflen = buflen;
+		ctx.count = 0;
+		ret = assoc_array_iterate(&keyring->keys,
+					  keyring_read_iterator, &ctx);
+		if (ret < 0) {
+			kleave(" = %ld [iterate]", ret);
+			return ret;
+		}
 	}
 
-	kleave(" = %zu [ok]", ctx.count);
-	return ctx.count;
+	/* Return the size of the buffer needed */
+	ret = keyring->keys.nr_leaves_on_tree * sizeof(key_serial_t);
+	if (ret <= buflen)
+		kleave("= %ld [ok]", ret);
+	else
+		kleave("= %ld [buffer too small]", ret);
+	return ret;
 }
 
 /*
diff --git a/security/keys/trusted.c b/security/keys/trusted.c
index bd85315cbfeb..98aa89ff7bfd 100644
--- a/security/keys/trusted.c
+++ b/security/keys/trusted.c
@@ -1147,20 +1147,21 @@ static long trusted_read(const struct key *key, char __user *buffer,
 	p = dereference_key_locked(key);
 	if (!p)
 		return -EINVAL;
-	if (!buffer || buflen <= 0)
-		return 2 * p->blob_len;
-	ascii_buf = kmalloc(2 * p->blob_len, GFP_KERNEL);
-	if (!ascii_buf)
-		return -ENOMEM;
 
-	bufp = ascii_buf;
-	for (i = 0; i < p->blob_len; i++)
-		bufp = hex_byte_pack(bufp, p->blob[i]);
-	if ((copy_to_user(buffer, ascii_buf, 2 * p->blob_len)) != 0) {
+	if (buffer && buflen >= 2 * p->blob_len) {
+		ascii_buf = kmalloc(2 * p->blob_len, GFP_KERNEL);
+		if (!ascii_buf)
+			return -ENOMEM;
+
+		bufp = ascii_buf;
+		for (i = 0; i < p->blob_len; i++)
+			bufp = hex_byte_pack(bufp, p->blob[i]);
+		if (copy_to_user(buffer, ascii_buf, 2 * p->blob_len) != 0) {
+			kzfree(ascii_buf);
+			return -EFAULT;
+		}
 		kzfree(ascii_buf);
-		return -EFAULT;
 	}
-	kzfree(ascii_buf);
 	return 2 * p->blob_len;
 }
 
diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c
index 6c9cba2166d9..d10c780dfd54 100644
--- a/sound/core/seq/seq_clientmgr.c
+++ b/sound/core/seq/seq_clientmgr.c
@@ -663,7 +663,7 @@ static int deliver_to_subscribers(struct snd_seq_client *client,
 	if (atomic)
 		read_lock(&grp->list_lock);
 	else
-		down_read(&grp->list_mutex);
+		down_read_nested(&grp->list_mutex, hop);
 	list_for_each_entry(subs, &grp->list_head, src_list) {
 		/* both ports ready? */
 		if (atomic_read(&subs->ref_count) != 2)
diff --git a/sound/core/timer_compat.c b/sound/core/timer_compat.c
index 6a437eb66115..59127b6ef39e 100644
--- a/sound/core/timer_compat.c
+++ b/sound/core/timer_compat.c
@@ -133,7 +133,8 @@ enum {
 #endif /* CONFIG_X86_X32 */
 };
 
-static long snd_timer_user_ioctl_compat(struct file *file, unsigned int cmd, unsigned long arg)
+static long __snd_timer_user_ioctl_compat(struct file *file, unsigned int cmd,
+					  unsigned long arg)
 {
 	void __user *argp = compat_ptr(arg);
 
@@ -153,7 +154,7 @@ static long snd_timer_user_ioctl_compat(struct file *file, unsigned int cmd, uns
 	case SNDRV_TIMER_IOCTL_PAUSE:
 	case SNDRV_TIMER_IOCTL_PAUSE_OLD:
 	case SNDRV_TIMER_IOCTL_NEXT_DEVICE:
-		return snd_timer_user_ioctl(file, cmd, (unsigned long)argp);
+		return __snd_timer_user_ioctl(file, cmd, (unsigned long)argp);
 	case SNDRV_TIMER_IOCTL_GPARAMS32:
 		return snd_timer_user_gparams_compat(file, argp);
 	case SNDRV_TIMER_IOCTL_INFO32:
@@ -167,3 +168,15 @@ static long snd_timer_user_ioctl_compat(struct file *file, unsigned int cmd, uns
 	}
 	return -ENOIOCTLCMD;
 }
+
+static long snd_timer_user_ioctl_compat(struct file *file, unsigned int cmd,
+					unsigned long arg)
+{
+	struct snd_timer_user *tu = file->private_data;
+	long ret;
+
+	mutex_lock(&tu->ioctl_lock);
+	ret = __snd_timer_user_ioctl_compat(file, cmd, arg);
+	mutex_unlock(&tu->ioctl_lock);
+	return ret;
+}
diff --git a/sound/soc/codecs/adau17x1.c b/sound/soc/codecs/adau17x1.c
index 2c1bd2763864..6758f789b712 100644
--- a/sound/soc/codecs/adau17x1.c
+++ b/sound/soc/codecs/adau17x1.c
@@ -90,6 +90,27 @@ static int adau17x1_pll_event(struct snd_soc_dapm_widget *w,
 	return 0;
 }
 
+static int adau17x1_adc_fixup(struct snd_soc_dapm_widget *w,
+	struct snd_kcontrol *kcontrol, int event)
+{
+	struct snd_soc_codec *codec = snd_soc_dapm_to_codec(w->dapm);
+	struct adau *adau = snd_soc_codec_get_drvdata(codec);
+
+	/*
+	 * If we are capturing, toggle the ADOSR bit in Converter Control 0 to
+	 * avoid losing SNR (workaround from ADI). This must be done after
+	 * the ADC(s) have been enabled. According to the data sheet, it is
+	 * normally illegal to set this bit when the sampling rate is 96 kHz,
+	 * but according to ADI it is acceptable for this workaround.
+	 */
+	regmap_update_bits(adau->regmap, ADAU17X1_CONVERTER0,
+		ADAU17X1_CONVERTER0_ADOSR, ADAU17X1_CONVERTER0_ADOSR);
+	regmap_update_bits(adau->regmap, ADAU17X1_CONVERTER0,
+		ADAU17X1_CONVERTER0_ADOSR, 0);
+
+	return 0;
+}
+
 static const char * const adau17x1_mono_stereo_text[] = {
 	"Stereo",
 	"Mono Left Channel (L+R)",
@@ -121,7 +142,8 @@ static const struct snd_soc_dapm_widget adau17x1_dapm_widgets[] = {
 	SND_SOC_DAPM_MUX("Right DAC Mode Mux", SND_SOC_NOPM, 0, 0,
 		&adau17x1_dac_mode_mux),
 
-	SND_SOC_DAPM_ADC("Left Decimator", NULL, ADAU17X1_ADC_CONTROL, 0, 0),
+	SND_SOC_DAPM_ADC_E("Left Decimator", NULL, ADAU17X1_ADC_CONTROL, 0, 0,
+			   adau17x1_adc_fixup, SND_SOC_DAPM_POST_PMU),
 	SND_SOC_DAPM_ADC("Right Decimator", NULL, ADAU17X1_ADC_CONTROL, 1, 0),
 	SND_SOC_DAPM_DAC("Left DAC", NULL, ADAU17X1_DAC_CONTROL0, 0, 0),
 	SND_SOC_DAPM_DAC("Right DAC", NULL, ADAU17X1_DAC_CONTROL0, 1, 0),
diff --git a/sound/soc/codecs/adau17x1.h b/sound/soc/codecs/adau17x1.h
index bf04b7efee40..db350035fad7 100644
--- a/sound/soc/codecs/adau17x1.h
+++ b/sound/soc/codecs/adau17x1.h
@@ -129,5 +129,7 @@ bool adau17x1_has_dsp(struct adau *adau);
 
 #define ADAU17X1_CONVERTER0_CONVSR_MASK		0x7
 
+#define ADAU17X1_CONVERTER0_ADOSR		BIT(3)
+
 
 #endif
diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c
index aa6b68db80b4..b606f1643fe5 100644
--- a/virt/kvm/arm/vgic/vgic-its.c
+++ b/virt/kvm/arm/vgic/vgic-its.c
@@ -1803,37 +1803,33 @@ typedef int (*entry_fn_t)(struct vgic_its *its, u32 id, void *entry,
 static int scan_its_table(struct vgic_its *its, gpa_t base, int size, int esz,
 			  int start_id, entry_fn_t fn, void *opaque)
 {
-	void *entry = kzalloc(esz, GFP_KERNEL);
 	struct kvm *kvm = its->dev->kvm;
 	unsigned long len = size;
 	int id = start_id;
 	gpa_t gpa = base;
+	char entry[esz];
 	int ret;
 
+	memset(entry, 0, esz);
+
 	while (len > 0) {
 		int next_offset;
 		size_t byte_offset;
 
 		ret = kvm_read_guest(kvm, gpa, entry, esz);
 		if (ret)
-			goto out;
+			return ret;
 
 		next_offset = fn(its, id, entry, opaque);
-		if (next_offset <= 0) {
-			ret = next_offset;
-			goto out;
-		}
+		if (next_offset <= 0)
+			return next_offset;
 
 		byte_offset = next_offset * esz;
 		id += next_offset;
 		gpa += byte_offset;
 		len -= byte_offset;
 	}
-	ret =  1;
-
-out:
-	kfree(entry);
-	return ret;
+	return 1;
 }
 
 /**