24 files changed, 457 insertions, 197 deletions

diff --git a/kernel/.gitignore b/kernel/.gitignore
index ab4f1090f437..b3097bde4e9c 100644
--- a/kernel/.gitignore
+++ b/kernel/.gitignore
@@ -4,3 +4,4 @@
 config_data.h
 config_data.gz
 timeconst.h
+hz.bc
diff --git a/kernel/capability.c b/kernel/capability.c
index 493d97259484..f6c2ce5701e1 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -393,6 +393,30 @@ bool ns_capable(struct user_namespace *ns, int cap)
 EXPORT_SYMBOL(ns_capable);
 
 /**
+ * file_ns_capable - Determine if the file's opener had a capability in effect
+ * @file:  The file we want to check
+ * @ns:  The usernamespace we want the capability in
+ * @cap: The capability to be tested for
+ *
+ * Return true if task that opened the file had a capability in effect
+ * when the file was opened.
+ *
+ * This does not set PF_SUPERPRIV because the caller may not
+ * actually be privileged.
+ */
+bool file_ns_capable(const struct file *file, struct user_namespace *ns, int cap)
+{
+	if (WARN_ON_ONCE(!cap_valid(cap)))
+		return false;
+
+	if (security_capable(file->f_cred, ns, cap) == 0)
+		return true;
+
+	return false;
+}
+EXPORT_SYMBOL(file_ns_capable);
+
+/**
  * capable - Determine if the current task has a superior capability in effect
  * @cap: The capability to be tested for
  *
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 59412d037eed..9fcb0944f071 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4596,6 +4596,7 @@ void perf_event_comm(struct task_struct *task)
 	struct perf_event_context *ctx;
 	int ctxn;
 
+	rcu_read_lock();
 	for_each_task_context_nr(ctxn) {
 		ctx = task->perf_event_ctxp[ctxn];
 		if (!ctx)
@@ -4603,6 +4604,7 @@ void perf_event_comm(struct task_struct *task)
 
 		perf_event_enable_on_exec(ctx);
 	}
+	rcu_read_unlock();
 
 	if (!atomic_read(&nr_comm_events))
 		return;
@@ -4737,7 +4739,8 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
 	} else {
 		if (arch_vma_name(mmap_event->vma)) {
 			name = strncpy(tmp, arch_vma_name(mmap_event->vma),
-				       sizeof(tmp));
+				       sizeof(tmp) - 1);
+			tmp[sizeof(tmp) - 1] = '\0';
 			goto got_name;
 		}
 
@@ -5330,7 +5333,7 @@ static void sw_perf_event_destroy(struct perf_event *event)
 
 static int perf_swevent_init(struct perf_event *event)
 {
-	int event_id = event->attr.config;
+	u64 event_id = event->attr.config;
 
 	if (event->attr.type != PERF_TYPE_SOFTWARE)
 		return -ENOENT;
@@ -5986,6 +5989,7 @@ skip_type:
 	if (pmu->pmu_cpu_context)
 		goto got_cpu_context;
 
+	ret = -ENOMEM;
 	pmu->pmu_cpu_context = alloc_percpu(struct perf_cpu_context);
 	if (!pmu->pmu_cpu_context)
 		goto free_dev;
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index d56a64c99a8b..eb675c4d59df 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -16,7 +16,7 @@ struct ring_buffer {
 	int				page_order;	/* allocation order  */
 #endif
 	int				nr_pages;	/* nr of data pages  */
-	int				writable;	/* are we writable   */
+	int				overwrite;	/* can overwrite itself */
 
 	atomic_t			poll;		/* POLL_ for wakeups */
 
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 23cb34ff3973..97fddb09762b 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -18,12 +18,24 @@
 static bool perf_output_space(struct ring_buffer *rb, unsigned long tail,
 			      unsigned long offset, unsigned long head)
 {
-	unsigned long mask;
+	unsigned long sz = perf_data_size(rb);
+	unsigned long mask = sz - 1;
 
-	if (!rb->writable)
+	/*
+	 * check if user-writable
+	 * overwrite : over-write its own tail
+	 * !overwrite: buffer possibly drops events.
+	 */
+	if (rb->overwrite)
 		return true;
 
-	mask = perf_data_size(rb) - 1;
+	/*
+	 * verify that payload is not bigger than buffer
+	 * otherwise masking logic may fail to detect
+	 * the "not enough space" condition
+	 */
+	if ((head - offset) > sz)
+		return false;
 
 	offset = (offset - tail) & mask;
 	head   = (head   - tail) & mask;
@@ -212,7 +224,9 @@ ring_buffer_init(struct ring_buffer *rb, long watermark, int flags)
 		rb->watermark = max_size / 2;
 
 	if (flags & RING_BUFFER_WRITABLE)
-		rb->writable = 1;
+		rb->overwrite = 0;
+	else
+		rb->overwrite = 1;
 
 	atomic_set(&rb->refcount, 1);
 
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index cc47812d3feb..14be27feda49 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -63,6 +63,7 @@
 DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
 {
 
+	.lock = __RAW_SPIN_LOCK_UNLOCKED(hrtimer_bases.lock),
 	.clock_base =
 	{
 		{
@@ -1642,8 +1643,6 @@ static void __cpuinit init_hrtimers_cpu(int cpu)
 	struct hrtimer_cpu_base *cpu_base = &per_cpu(hrtimer_bases, cpu);
 	int i;
 
-	raw_spin_lock_init(&cpu_base->lock);
-
 	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
 		cpu_base->clock_base[i].cpu_base = cpu_base;
 		timerqueue_init_head(&cpu_base->clock_base[i].active);
diff --git a/kernel/kexec.c b/kernel/kexec.c
index bddd3d7a74b6..ffd4e111fd67 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -55,7 +55,7 @@ struct resource crashk_res = {
 	.flags = IORESOURCE_BUSY | IORESOURCE_MEM
 };
 struct resource crashk_low_res = {
-	.name  = "Crash kernel low",
+	.name  = "Crash kernel",
 	.start = 0,
 	.end   = 0,
 	.flags = IORESOURCE_BUSY | IORESOURCE_MEM
@@ -1368,35 +1368,114 @@ static int __init parse_crashkernel_simple(char 		*cmdline,
 	return 0;
 }
 
+#define SUFFIX_HIGH 0
+#define SUFFIX_LOW  1
+#define SUFFIX_NULL 2
+static __initdata char *suffix_tbl[] = {
+	[SUFFIX_HIGH] = ",high",
+	[SUFFIX_LOW]  = ",low",
+	[SUFFIX_NULL] = NULL,
+};
+
 /*
- * That function is the entry point for command line parsing and should be
- * called from the arch-specific code.
+ * That function parses "suffix"  crashkernel command lines like
+ *
+ *	crashkernel=size,[high|low]
+ *
+ * It returns 0 on success and -EINVAL on failure.
  */
+static int __init parse_crashkernel_suffix(char *cmdline,
+					   unsigned long long	*crash_size,
+					   unsigned long long	*crash_base,
+					   const char *suffix)
+{
+	char *cur = cmdline;
+
+	*crash_size = memparse(cmdline, &cur);
+	if (cmdline == cur) {
+		pr_warn("crashkernel: memory value expected\n");
+		return -EINVAL;
+	}
+
+	/* check with suffix */
+	if (strncmp(cur, suffix, strlen(suffix))) {
+		pr_warn("crashkernel: unrecognized char\n");
+		return -EINVAL;
+	}
+	cur += strlen(suffix);
+	if (*cur != ' ' && *cur != '\0') {
+		pr_warn("crashkernel: unrecognized char\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static __init char *get_last_crashkernel(char *cmdline,
+			     const char *name,
+			     const char *suffix)
+{
+	char *p = cmdline, *ck_cmdline = NULL;
+
+	/* find crashkernel and use the last one if there are more */
+	p = strstr(p, name);
+	while (p) {
+		char *end_p = strchr(p, ' ');
+		char *q;
+
+		if (!end_p)
+			end_p = p + strlen(p);
+
+		if (!suffix) {
+			int i;
+
+			/* skip the one with any known suffix */
+			for (i = 0; suffix_tbl[i]; i++) {
+				q = end_p - strlen(suffix_tbl[i]);
+				if (!strncmp(q, suffix_tbl[i],
+					     strlen(suffix_tbl[i])))
+					goto next;
+			}
+			ck_cmdline = p;
+		} else {
+			q = end_p - strlen(suffix);
+			if (!strncmp(q, suffix, strlen(suffix)))
+				ck_cmdline = p;
+		}
+next:
+		p = strstr(p+1, name);
+	}
+
+	if (!ck_cmdline)
+		return NULL;
+
+	return ck_cmdline;
+}
+
 static int __init __parse_crashkernel(char *cmdline,
 			     unsigned long long system_ram,
 			     unsigned long long *crash_size,
 			     unsigned long long *crash_base,
-				const char *name)
+			     const char *name,
+			     const char *suffix)
 {
-	char 	*p = cmdline, *ck_cmdline = NULL;
 	char	*first_colon, *first_space;
+	char	*ck_cmdline;
 
 	BUG_ON(!crash_size || !crash_base);
 	*crash_size = 0;
 	*crash_base = 0;
 
-	/* find crashkernel and use the last one if there are more */
-	p = strstr(p, name);
-	while (p) {
-		ck_cmdline = p;
-		p = strstr(p+1, name);
-	}
+	ck_cmdline = get_last_crashkernel(cmdline, name, suffix);
 
 	if (!ck_cmdline)
 		return -EINVAL;
 
 	ck_cmdline += strlen(name);
 
+	if (suffix)
+		return parse_crashkernel_suffix(ck_cmdline, crash_size,
+				crash_base, suffix);
 	/*
 	 * if the commandline contains a ':', then that's the extended
 	 * syntax -- if not, it must be the classic syntax
@@ -1413,13 +1492,26 @@ static int __init __parse_crashkernel(char *cmdline,
 	return 0;
 }
 
+/*
+ * That function is the entry point for command line parsing and should be
+ * called from the arch-specific code.
+ */
 int __init parse_crashkernel(char *cmdline,
 			     unsigned long long system_ram,
 			     unsigned long long *crash_size,
 			     unsigned long long *crash_base)
 {
 	return __parse_crashkernel(cmdline, system_ram, crash_size, crash_base,
-					"crashkernel=");
+					"crashkernel=", NULL);
+}
+
+int __init parse_crashkernel_high(char *cmdline,
+			     unsigned long long system_ram,
+			     unsigned long long *crash_size,
+			     unsigned long long *crash_base)
+{
+	return __parse_crashkernel(cmdline, system_ram, crash_size, crash_base,
+				"crashkernel=", suffix_tbl[SUFFIX_HIGH]);
 }
 
 int __init parse_crashkernel_low(char *cmdline,
@@ -1428,7 +1520,7 @@ int __init parse_crashkernel_low(char *cmdline,
 			     unsigned long long *crash_base)
 {
 	return __parse_crashkernel(cmdline, system_ram, crash_size, crash_base,
-					"crashkernel_low=");
+				"crashkernel=", suffix_tbl[SUFFIX_LOW]);
 }
 
 static void update_vmcoreinfo_note(void)
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index e35be53f6613..3fed7f0cbcdf 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -794,16 +794,16 @@ out:
 }
 
 #ifdef CONFIG_SYSCTL
-/* This should be called with kprobe_mutex locked */
 static void __kprobes optimize_all_kprobes(void)
 {
 	struct hlist_head *head;
 	struct kprobe *p;
 	unsigned int i;
 
+	mutex_lock(&kprobe_mutex);
 	/* If optimization is already allowed, just return */
 	if (kprobes_allow_optimization)
-		return;
+		goto out;
 
 	kprobes_allow_optimization = true;
 	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
@@ -813,18 +813,22 @@ static void __kprobes optimize_all_kprobes(void)
 				optimize_kprobe(p);
 	}
 	printk(KERN_INFO "Kprobes globally optimized\n");
+out:
+	mutex_unlock(&kprobe_mutex);
 }
 
-/* This should be called with kprobe_mutex locked */
 static void __kprobes unoptimize_all_kprobes(void)
 {
 	struct hlist_head *head;
 	struct kprobe *p;
 	unsigned int i;
 
+	mutex_lock(&kprobe_mutex);
 	/* If optimization is already prohibited, just return */
-	if (!kprobes_allow_optimization)
+	if (!kprobes_allow_optimization) {
+		mutex_unlock(&kprobe_mutex);
 		return;
+	}
 
 	kprobes_allow_optimization = false;
 	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
@@ -834,11 +838,14 @@ static void __kprobes unoptimize_all_kprobes(void)
 				unoptimize_kprobe(p, false);
 		}
 	}
+	mutex_unlock(&kprobe_mutex);
+
 	/* Wait for unoptimizing completion */
 	wait_for_kprobe_optimizer();
 	printk(KERN_INFO "Kprobes globally unoptimized\n");
 }
 
+static DEFINE_MUTEX(kprobe_sysctl_mutex);
 int sysctl_kprobes_optimization;
 int proc_kprobes_optimization_handler(struct ctl_table *table, int write,
 				      void __user *buffer, size_t *length,
@@ -846,7 +853,7 @@ int proc_kprobes_optimization_handler(struct ctl_table *table, int write,
 {
 	int ret;
 
-	mutex_lock(&kprobe_mutex);
+	mutex_lock(&kprobe_sysctl_mutex);
 	sysctl_kprobes_optimization = kprobes_allow_optimization ? 1 : 0;
 	ret = proc_dointvec_minmax(table, write, buffer, length, ppos);
 
@@ -854,7 +861,7 @@ int proc_kprobes_optimization_handler(struct ctl_table *table, int write,
 		optimize_all_kprobes();
 	else
 		unoptimize_all_kprobes();
-	mutex_unlock(&kprobe_mutex);
+	mutex_unlock(&kprobe_sysctl_mutex);
 
 	return ret;
 }
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 691dc2ef9baf..9eb7fed0bbaa 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -124,12 +124,12 @@ void *kthread_data(struct task_struct *task)
 
 static void __kthread_parkme(struct kthread *self)
 {
-	__set_current_state(TASK_INTERRUPTIBLE);
+	__set_current_state(TASK_PARKED);
 	while (test_bit(KTHREAD_SHOULD_PARK, &self->flags)) {
 		if (!test_and_set_bit(KTHREAD_IS_PARKED, &self->flags))
 			complete(&self->parked);
 		schedule();
-		__set_current_state(TASK_INTERRUPTIBLE);
+		__set_current_state(TASK_PARKED);
 	}
 	clear_bit(KTHREAD_IS_PARKED, &self->flags);
 	__set_current_state(TASK_RUNNING);
@@ -256,8 +256,13 @@ struct task_struct *kthread_create_on_node(int (*threadfn)(void *data),
 }
 EXPORT_SYMBOL(kthread_create_on_node);
 
-static void __kthread_bind(struct task_struct *p, unsigned int cpu)
+static void __kthread_bind(struct task_struct *p, unsigned int cpu, long state)
 {
+	/* Must have done schedule() in kthread() before we set_task_cpu */
+	if (!wait_task_inactive(p, state)) {
+		WARN_ON(1);
+		return;
+	}
 	/* It's safe because the task is inactive. */
 	do_set_cpus_allowed(p, cpumask_of(cpu));
 	p->flags |= PF_THREAD_BOUND;
@@ -274,12 +279,7 @@ static void __kthread_bind(struct task_struct *p, unsigned int cpu)
  */
 void kthread_bind(struct task_struct *p, unsigned int cpu)
 {
-	/* Must have done schedule() in kthread() before we set_task_cpu */
-	if (!wait_task_inactive(p, TASK_UNINTERRUPTIBLE)) {
-		WARN_ON(1);
-		return;
-	}
-	__kthread_bind(p, cpu);
+	__kthread_bind(p, cpu, TASK_UNINTERRUPTIBLE);
 }
 EXPORT_SYMBOL(kthread_bind);
 
@@ -324,6 +324,22 @@ static struct kthread *task_get_live_kthread(struct task_struct *k)
 	return NULL;
 }
 
+static void __kthread_unpark(struct task_struct *k, struct kthread *kthread)
+{
+	clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
+	/*
+	 * We clear the IS_PARKED bit here as we don't wait
+	 * until the task has left the park code. So if we'd
+	 * park before that happens we'd see the IS_PARKED bit
+	 * which might be about to be cleared.
+	 */
+	if (test_and_clear_bit(KTHREAD_IS_PARKED, &kthread->flags)) {
+		if (test_bit(KTHREAD_IS_PER_CPU, &kthread->flags))
+			__kthread_bind(k, kthread->cpu, TASK_PARKED);
+		wake_up_state(k, TASK_PARKED);
+	}
+}
+
 /**
  * kthread_unpark - unpark a thread created by kthread_create().
  * @k:		thread created by kthread_create().
@@ -336,20 +352,8 @@ void kthread_unpark(struct task_struct *k)
 {
 	struct kthread *kthread = task_get_live_kthread(k);
 
-	if (kthread) {
-		clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
-		/*
-		 * We clear the IS_PARKED bit here as we don't wait
-		 * until the task has left the park code. So if we'd
-		 * park before that happens we'd see the IS_PARKED bit
-		 * which might be about to be cleared.
-		 */
-		if (test_and_clear_bit(KTHREAD_IS_PARKED, &kthread->flags)) {
-			if (test_bit(KTHREAD_IS_PER_CPU, &kthread->flags))
-				__kthread_bind(k, kthread->cpu);
-			wake_up_process(k);
-		}
-	}
+	if (kthread)
+		__kthread_unpark(k, kthread);
 	put_task_struct(k);
 }
 
@@ -407,7 +411,7 @@ int kthread_stop(struct task_struct *k)
 	trace_sched_kthread_stop(k);
 	if (kthread) {
 		set_bit(KTHREAD_SHOULD_STOP, &kthread->flags);
-		clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
+		__kthread_unpark(k, kthread);
 		wake_up_process(k);
 		wait_for_completion(&kthread->exited);
 	}
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index 8a0efac4f99d..6a3bccba7e7d 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -380,6 +380,13 @@ static int verbose(struct lock_class *class)
 unsigned long nr_stack_trace_entries;
 static unsigned long stack_trace[MAX_STACK_TRACE_ENTRIES];
 
+static void print_lockdep_off(const char *bug_msg)
+{
+	printk(KERN_DEBUG "%s\n", bug_msg);
+	printk(KERN_DEBUG "turning off the locking correctness validator.\n");
+	printk(KERN_DEBUG "Please attach the output of /proc/lock_stat to the bug report\n");
+}
+
 static int save_trace(struct stack_trace *trace)
 {
 	trace->nr_entries = 0;
@@ -409,8 +416,7 @@ static int save_trace(struct stack_trace *trace)
 		if (!debug_locks_off_graph_unlock())
 			return 0;
 
-		printk("BUG: MAX_STACK_TRACE_ENTRIES too low!\n");
-		printk("turning off the locking correctness validator.\n");
+		print_lockdep_off("BUG: MAX_STACK_TRACE_ENTRIES too low!");
 		dump_stack();
 
 		return 0;
@@ -763,8 +769,7 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
 		}
 		raw_local_irq_restore(flags);
 
-		printk("BUG: MAX_LOCKDEP_KEYS too low!\n");
-		printk("turning off the locking correctness validator.\n");
+		print_lockdep_off("BUG: MAX_LOCKDEP_KEYS too low!");
 		dump_stack();
 		return NULL;
 	}
@@ -834,8 +839,7 @@ static struct lock_list *alloc_list_entry(void)
 		if (!debug_locks_off_graph_unlock())
 			return NULL;
 
-		printk("BUG: MAX_LOCKDEP_ENTRIES too low!\n");
-		printk("turning off the locking correctness validator.\n");
+		print_lockdep_off("BUG: MAX_LOCKDEP_ENTRIES too low!");
 		dump_stack();
 		return NULL;
 	}
@@ -2000,7 +2004,7 @@ static inline int lookup_chain_cache(struct task_struct *curr,
 	struct lock_class *class = hlock_class(hlock);
 	struct list_head *hash_head = chainhashentry(chain_key);
 	struct lock_chain *chain;
-	struct held_lock *hlock_curr, *hlock_next;
+	struct held_lock *hlock_curr;
 	int i, j;
 
 	/*
@@ -2048,8 +2052,7 @@ cache_hit:
 		if (!debug_locks_off_graph_unlock())
 			return 0;
 
-		printk("BUG: MAX_LOCKDEP_CHAINS too low!\n");
-		printk("turning off the locking correctness validator.\n");
+		print_lockdep_off("BUG: MAX_LOCKDEP_CHAINS too low!");
 		dump_stack();
 		return 0;
 	}
@@ -2057,12 +2060,10 @@ cache_hit:
 	chain->chain_key = chain_key;
 	chain->irq_context = hlock->irq_context;
 	/* Find the first held_lock of current chain */
-	hlock_next = hlock;
 	for (i = curr->lockdep_depth - 1; i >= 0; i--) {
 		hlock_curr = curr->held_locks + i;
-		if (hlock_curr->irq_context != hlock_next->irq_context)
+		if (hlock_curr->irq_context != hlock->irq_context)
 			break;
-		hlock_next = hlock;
 	}
 	i++;
 	chain->depth = curr->lockdep_depth + 1 - i;
@@ -3190,9 +3191,9 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 #endif
 	if (unlikely(curr->lockdep_depth >= MAX_LOCK_DEPTH)) {
 		debug_locks_off();
-		printk("BUG: MAX_LOCK_DEPTH too low, depth: %i  max: %lu!\n",
+		print_lockdep_off("BUG: MAX_LOCK_DEPTH too low!");
+		printk(KERN_DEBUG "depth: %i  max: %lu!\n",
 		       curr->lockdep_depth, MAX_LOCK_DEPTH);
-		printk("turning off the locking correctness validator.\n");
 
 		lockdep_print_held_locks(current);
 		debug_show_all_locks();
diff --git a/kernel/mutex.c b/kernel/mutex.c
index 52f23011b6e0..ad53a664f113 100644
--- a/kernel/mutex.c
+++ b/kernel/mutex.c
@@ -37,6 +37,12 @@
 # include <asm/mutex.h>
 #endif
 
+/*
+ * A negative mutex count indicates that waiters are sleeping waiting for the
+ * mutex.
+ */
+#define	MUTEX_SHOW_NO_WAITER(mutex)	(atomic_read(&(mutex)->count) >= 0)
+
 void
 __mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key)
 {
@@ -44,6 +50,9 @@ __mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key)
 	spin_lock_init(&lock->wait_lock);
 	INIT_LIST_HEAD(&lock->wait_list);
 	mutex_clear_owner(lock);
+#ifdef CONFIG_MUTEX_SPIN_ON_OWNER
+	lock->spin_mlock = NULL;
+#endif
 
 	debug_mutex_init(lock, name, key);
 }
@@ -95,6 +104,124 @@ void __sched mutex_lock(struct mutex *lock)
 EXPORT_SYMBOL(mutex_lock);
 #endif
 
+#ifdef CONFIG_MUTEX_SPIN_ON_OWNER
+/*
+ * In order to avoid a stampede of mutex spinners from acquiring the mutex
+ * more or less simultaneously, the spinners need to acquire a MCS lock
+ * first before spinning on the owner field.
+ *
+ * We don't inline mspin_lock() so that perf can correctly account for the
+ * time spent in this lock function.
+ */
+struct mspin_node {
+	struct mspin_node *next ;
+	int		  locked;	/* 1 if lock acquired */
+};
+#define	MLOCK(mutex)	((struct mspin_node **)&((mutex)->spin_mlock))
+
+static noinline
+void mspin_lock(struct mspin_node **lock, struct mspin_node *node)
+{
+	struct mspin_node *prev;
+
+	/* Init node */
+	node->locked = 0;
+	node->next   = NULL;
+
+	prev = xchg(lock, node);
+	if (likely(prev == NULL)) {
+		/* Lock acquired */
+		node->locked = 1;
+		return;
+	}
+	ACCESS_ONCE(prev->next) = node;
+	smp_wmb();
+	/* Wait until the lock holder passes the lock down */
+	while (!ACCESS_ONCE(node->locked))
+		arch_mutex_cpu_relax();
+}
+
+static void mspin_unlock(struct mspin_node **lock, struct mspin_node *node)
+{
+	struct mspin_node *next = ACCESS_ONCE(node->next);
+
+	if (likely(!next)) {
+		/*
+		 * Release the lock by setting it to NULL
+		 */
+		if (cmpxchg(lock, node, NULL) == node)
+			return;
+		/* Wait until the next pointer is set */
+		while (!(next = ACCESS_ONCE(node->next)))
+			arch_mutex_cpu_relax();
+	}
+	ACCESS_ONCE(next->locked) = 1;
+	smp_wmb();
+}
+
+/*
+ * Mutex spinning code migrated from kernel/sched/core.c
+ */
+
+static inline bool owner_running(struct mutex *lock, struct task_struct *owner)
+{
+	if (lock->owner != owner)
+		return false;
+
+	/*
+	 * Ensure we emit the owner->on_cpu, dereference _after_ checking
+	 * lock->owner still matches owner, if that fails, owner might
+	 * point to free()d memory, if it still matches, the rcu_read_lock()
+	 * ensures the memory stays valid.
+	 */
+	barrier();
+
+	return owner->on_cpu;
+}
+
+/*
+ * Look out! "owner" is an entirely speculative pointer
+ * access and not reliable.
+ */
+static noinline
+int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner)
+{
+	rcu_read_lock();
+	while (owner_running(lock, owner)) {
+		if (need_resched())
+			break;
+
+		arch_mutex_cpu_relax();
+	}
+	rcu_read_unlock();
+
+	/*
+	 * We break out the loop above on need_resched() and when the
+	 * owner changed, which is a sign for heavy contention. Return
+	 * success only when lock->owner is NULL.
+	 */
+	return lock->owner == NULL;
+}
+
+/*
+ * Initial check for entering the mutex spinning loop
+ */
+static inline int mutex_can_spin_on_owner(struct mutex *lock)
+{
+	int retval = 1;
+
+	rcu_read_lock();
+	if (lock->owner)
+		retval = lock->owner->on_cpu;
+	rcu_read_unlock();
+	/*
+	 * if lock->owner is not set, the mutex owner may have just acquired
+	 * it and not set the owner yet or the mutex has been released.
+	 */
+	return retval;
+}
+#endif
+
 static __used noinline void __sched __mutex_unlock_slowpath(atomic_t *lock_count);
 
 /**
@@ -158,25 +285,39 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 	 *
 	 * We can't do this for DEBUG_MUTEXES because that relies on wait_lock
 	 * to serialize everything.
+	 *
+	 * The mutex spinners are queued up using MCS lock so that only one
+	 * spinner can compete for the mutex. However, if mutex spinning isn't
+	 * going to happen, there is no point in going through the lock/unlock
+	 * overhead.
 	 */
+	if (!mutex_can_spin_on_owner(lock))
+		goto slowpath;
 
 	for (;;) {
 		struct task_struct *owner;
+		struct mspin_node  node;
 
 		/*
 		 * If there's an owner, wait for it to either
 		 * release the lock or go to sleep.
 		 */
+		mspin_lock(MLOCK(lock), &node);
 		owner = ACCESS_ONCE(lock->owner);
-		if (owner && !mutex_spin_on_owner(lock, owner))
+		if (owner && !mutex_spin_on_owner(lock, owner)) {
+			mspin_unlock(MLOCK(lock), &node);
 			break;
+		}
 
-		if (atomic_cmpxchg(&lock->count, 1, 0) == 1) {
+		if ((atomic_read(&lock->count) == 1) &&
+		    (atomic_cmpxchg(&lock->count, 1, 0) == 1)) {
 			lock_acquired(&lock->dep_map, ip);
 			mutex_set_owner(lock);
+			mspin_unlock(MLOCK(lock), &node);
 			preempt_enable();
 			return 0;
 		}
+		mspin_unlock(MLOCK(lock), &node);
 
 		/*
 		 * When there's no owner, we might have preempted between the
@@ -195,6 +336,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 		 */
 		arch_mutex_cpu_relax();
 	}
+slowpath:
 #endif
 	spin_lock_mutex(&lock->wait_lock, flags);
 
@@ -205,7 +347,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 	list_add_tail(&waiter.list, &lock->wait_list);
 	waiter.task = task;
 
-	if (atomic_xchg(&lock->count, -1) == 1)
+	if (MUTEX_SHOW_NO_WAITER(lock) && (atomic_xchg(&lock->count, -1) == 1))
 		goto done;
 
 	lock_contended(&lock->dep_map, ip);
@@ -220,7 +362,8 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 		 * that when we release the lock, we properly wake up the
 		 * other waiters:
 		 */
-		if (atomic_xchg(&lock->count, -1) == 1)
+		if (MUTEX_SHOW_NO_WAITER(lock) &&
+		   (atomic_xchg(&lock->count, -1) == 1))
 			break;
 
 		/*
diff --git a/kernel/rtmutex-tester.c b/kernel/rtmutex-tester.c
index 7890b10084a7..1d96dd0d93c1 100644
--- a/kernel/rtmutex-tester.c
+++ b/kernel/rtmutex-tester.c
@@ -14,6 +14,7 @@
 #include <linux/spinlock.h>
 #include <linux/timer.h>
 #include <linux/freezer.h>
+#include <linux/stat.h>
 
 #include "rtmutex.h"
 
@@ -366,8 +367,8 @@ static ssize_t sysfs_test_status(struct device *dev, struct device_attribute *at
 	return curr - buf;
 }
 
-static DEVICE_ATTR(status, 0600, sysfs_test_status, NULL);
-static DEVICE_ATTR(command, 0600, NULL, sysfs_test_command);
+static DEVICE_ATTR(status, S_IRUSR, sysfs_test_status, NULL);
+static DEVICE_ATTR(command, S_IWUSR, NULL, sysfs_test_command);
 
 static struct bus_type rttest_subsys = {
 	.name = "rttest",
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index c685e31492df..c3ae1446461c 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -176,10 +176,36 @@ static u64 sched_clock_remote(struct sched_clock_data *scd)
 	u64 this_clock, remote_clock;
 	u64 *ptr, old_val, val;
 
+#if BITS_PER_LONG != 64
+again:
+	/*
+	 * Careful here: The local and the remote clock values need to
+	 * be read out atomic as we need to compare the values and
+	 * then update either the local or the remote side. So the
+	 * cmpxchg64 below only protects one readout.
+	 *
+	 * We must reread via sched_clock_local() in the retry case on
+	 * 32bit as an NMI could use sched_clock_local() via the
+	 * tracer and hit between the readout of
+	 * the low32bit and the high 32bit portion.
+	 */
+	this_clock = sched_clock_local(my_scd);
+	/*
+	 * We must enforce atomic readout on 32bit, otherwise the
+	 * update on the remote cpu can hit inbetween the readout of
+	 * the low32bit and the high 32bit portion.
+	 */
+	remote_clock = cmpxchg64(&scd->clock, 0, 0);
+#else
+	/*
+	 * On 64bit the read of [my]scd->clock is atomic versus the
+	 * update, so we can avoid the above 32bit dance.
+	 */
 	sched_clock_local(my_scd);
 again:
 	this_clock = my_scd->clock;
 	remote_clock = scd->clock;
+#endif
 
 	/*
 	 * Use the opportunity that we have both locks
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 7f12624a393c..42053547e0f5 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1498,8 +1498,10 @@ static void try_to_wake_up_local(struct task_struct *p)
 {
 	struct rq *rq = task_rq(p);
 
-	BUG_ON(rq != this_rq());
-	BUG_ON(p == current);
+	if (WARN_ON_ONCE(rq != this_rq()) ||
+	    WARN_ON_ONCE(p == current))
+		return;
+
 	lockdep_assert_held(&rq->lock);
 
 	if (!raw_spin_trylock(&p->pi_lock)) {
@@ -2997,51 +2999,6 @@ void __sched schedule_preempt_disabled(void)
 	preempt_disable();
 }
 
-#ifdef CONFIG_MUTEX_SPIN_ON_OWNER
-
-static inline bool owner_running(struct mutex *lock, struct task_struct *owner)
-{
-	if (lock->owner != owner)
-		return false;
-
-	/*
-	 * Ensure we emit the owner->on_cpu, dereference _after_ checking
-	 * lock->owner still matches owner, if that fails, owner might
-	 * point to free()d memory, if it still matches, the rcu_read_lock()
-	 * ensures the memory stays valid.
-	 */
-	barrier();
-
-	return owner->on_cpu;
-}
-
-/*
- * Look out! "owner" is an entirely speculative pointer
- * access and not reliable.
- */
-int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner)
-{
-	if (!sched_feat(OWNER_SPIN))
-		return 0;
-
-	rcu_read_lock();
-	while (owner_running(lock, owner)) {
-		if (need_resched())
-			break;
-
-		arch_mutex_cpu_relax();
-	}
-	rcu_read_unlock();
-
-	/*
-	 * We break out the loop above on need_resched() and when the
-	 * owner changed, which is a sign for heavy contention. Return
-	 * success only when lock->owner is NULL.
-	 */
-	return lock->owner == NULL;
-}
-#endif
-
 #ifdef CONFIG_PREEMPT
 /*
  * this is the entry point to schedule() from in-kernel preemption
@@ -4999,7 +4956,7 @@ static void sd_free_ctl_entry(struct ctl_table **tablep)
 }
 
 static int min_load_idx = 0;
-static int max_load_idx = CPU_LOAD_IDX_MAX;
+static int max_load_idx = CPU_LOAD_IDX_MAX-1;
 
 static void
 set_table_entry(struct ctl_table *entry,
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index ed12cbb135f4..e93cca92f38b 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -310,7 +310,7 @@ void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times)
 
 	t = tsk;
 	do {
-		task_cputime(tsk, &utime, &stime);
+		task_cputime(t, &utime, &stime);
 		times->utime += utime;
 		times->stime += stime;
 		times->sum_exec_runtime += task_sched_runtime(t);
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index 1ad1d2b5395f..99399f8e4799 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -46,13 +46,6 @@ SCHED_FEAT(DOUBLE_TICK, false)
 SCHED_FEAT(LB_BIAS, true)
 
 /*
- * Spin-wait on mutex acquisition when the mutex owner is running on
- * another cpu -- assumes that when the owner is running, it will soon
- * release the lock. Decreases scheduling overhead.
- */
-SCHED_FEAT(OWNER_SPIN, true)
-
-/*
  * Decrement CPU power based on time not spent running tasks
  */
 SCHED_FEAT(NONTASK_POWER, true)
diff --git a/kernel/signal.c b/kernel/signal.c
index dd72567767d9..598dc06be421 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2948,7 +2948,7 @@ do_send_specific(pid_t tgid, pid_t pid, int sig, struct siginfo *info)
 
 static int do_tkill(pid_t tgid, pid_t pid, int sig)
 {
-	struct siginfo info;
+	struct siginfo info = {};
 
 	info.si_signo = sig;
 	info.si_errno = 0;
diff --git a/kernel/smpboot.c b/kernel/smpboot.c
index 8eaed9aa9cf0..02fc5c933673 100644
--- a/kernel/smpboot.c
+++ b/kernel/smpboot.c
@@ -185,8 +185,18 @@ __smpboot_create_thread(struct smp_hotplug_thread *ht, unsigned int cpu)
 	}
 	get_task_struct(tsk);
 	*per_cpu_ptr(ht->store, cpu) = tsk;
-	if (ht->create)
-		ht->create(cpu);
+	if (ht->create) {
+		/*
+		 * Make sure that the task has actually scheduled out
+		 * into park position, before calling the create
+		 * callback. At least the migration thread callback
+		 * requires that the task is off the runqueue.
+		 */
+		if (!wait_task_inactive(tsk, TASK_PARKED))
+			WARN_ON(1);
+		else
+			ht->create(cpu);
+	}
 	return 0;
 }
 
diff --git a/kernel/sys.c b/kernel/sys.c
index 39c9c4a2949f..0da73cf73e60 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -324,7 +324,6 @@ void kernel_restart_prepare(char *cmd)
 	system_state = SYSTEM_RESTART;
 	usermodehelper_disable();
 	device_shutdown();
-	syscore_shutdown();
 }
 
 /**
@@ -370,6 +369,7 @@ void kernel_restart(char *cmd)
 {
 	kernel_restart_prepare(cmd);
 	disable_nonboot_cpus();
+	syscore_shutdown();
 	if (!cmd)
 		printk(KERN_EMERG "Restarting system.\n");
 	else
@@ -395,6 +395,7 @@ static void kernel_shutdown_prepare(enum system_states state)
 void kernel_halt(void)
 {
 	kernel_shutdown_prepare(SYSTEM_HALT);
+	disable_nonboot_cpus();
 	syscore_shutdown();
 	printk(KERN_EMERG "System halted.\n");
 	kmsg_dump(KMSG_DUMP_HALT);
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 9e5b8c272eec..5a0f781cd729 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -739,12 +739,6 @@ static void blk_add_trace_rq_complete(void *ignore,
 				      struct request_queue *q,
 				      struct request *rq)
 {
-	struct blk_trace *bt = q->blk_trace;
-
-	/* if control ever passes through here, it's a request based driver */
-	if (unlikely(bt && !bt->rq_based))
-		bt->rq_based = true;
-
 	blk_add_trace_rq(q, rq, BLK_TA_COMPLETE);
 }
 
@@ -780,24 +774,10 @@ static void blk_add_trace_bio_bounce(void *ignore,
 	blk_add_trace_bio(q, bio, BLK_TA_BOUNCE, 0);
 }
 
-static void blk_add_trace_bio_complete(void *ignore, struct bio *bio, int error)
+static void blk_add_trace_bio_complete(void *ignore,
+				       struct request_queue *q, struct bio *bio,
+				       int error)
 {
-	struct request_queue *q;
-	struct blk_trace *bt;
-
-	if (!bio->bi_bdev)
-		return;
-
-	q = bdev_get_queue(bio->bi_bdev);
-	bt = q->blk_trace;
-
-	/*
-	 * Request based drivers will generate both rq and bio completions.
-	 * Ignore bio ones.
-	 */
-	if (likely(!bt) || bt->rq_based)
-		return;
-
 	blk_add_trace_bio(q, bio, BLK_TA_COMPLETE, error);
 }
 
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 6893d5a2bf08..b3fde6d7b7fc 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -66,7 +66,7 @@
 
 static struct ftrace_ops ftrace_list_end __read_mostly = {
 	.func		= ftrace_stub,
-	.flags		= FTRACE_OPS_FL_RECURSION_SAFE,
+	.flags		= FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_STUB,
 };
 
 /* ftrace_enabled is a method to turn ftrace on or off */
@@ -694,7 +694,6 @@ int ftrace_profile_pages_init(struct ftrace_profile_stat *stat)
 		free_page(tmp);
 	}
 
-	free_page((unsigned long)stat->pages);
 	stat->pages = NULL;
 	stat->start = NULL;
 
@@ -1053,6 +1052,19 @@ static __init void ftrace_profile_debugfs(struct dentry *d_tracer)
 
 static struct pid * const ftrace_swapper_pid = &init_struct_pid;
 
+loff_t
+ftrace_filter_lseek(struct file *file, loff_t offset, int whence)
+{
+	loff_t ret;
+
+	if (file->f_mode & FMODE_READ)
+		ret = seq_lseek(file, offset, whence);
+	else
+		file->f_pos = ret = 1;
+
+	return ret;
+}
+
 #ifdef CONFIG_DYNAMIC_FTRACE
 
 #ifndef CONFIG_FTRACE_MCOUNT_RECORD
@@ -2613,7 +2625,7 @@ static void ftrace_filter_reset(struct ftrace_hash *hash)
  * routine, you can use ftrace_filter_write() for the write
  * routine if @flag has FTRACE_ITER_FILTER set, or
  * ftrace_notrace_write() if @flag has FTRACE_ITER_NOTRACE set.
- * ftrace_regex_lseek() should be used as the lseek routine, and
+ * ftrace_filter_lseek() should be used as the lseek routine, and
  * release must call ftrace_regex_release().
  */
 int
@@ -2697,19 +2709,6 @@ ftrace_notrace_open(struct inode *inode, struct file *file)
 				 inode, file);
 }
 
-loff_t
-ftrace_regex_lseek(struct file *file, loff_t offset, int whence)
-{
-	loff_t ret;
-
-	if (file->f_mode & FMODE_READ)
-		ret = seq_lseek(file, offset, whence);
-	else
-		file->f_pos = ret = 1;
-
-	return ret;
-}
-
 static int ftrace_match(char *str, char *regex, int len, int type)
 {
 	int matched = 0;
@@ -3441,14 +3440,14 @@ static char ftrace_filter_buf[FTRACE_FILTER_SIZE] __initdata;
 
 static int __init set_ftrace_notrace(char *str)
 {
-	strncpy(ftrace_notrace_buf, str, FTRACE_FILTER_SIZE);
+	strlcpy(ftrace_notrace_buf, str, FTRACE_FILTER_SIZE);
 	return 1;
 }
 __setup("ftrace_notrace=", set_ftrace_notrace);
 
 static int __init set_ftrace_filter(char *str)
 {
-	strncpy(ftrace_filter_buf, str, FTRACE_FILTER_SIZE);
+	strlcpy(ftrace_filter_buf, str, FTRACE_FILTER_SIZE);
 	return 1;
 }
 __setup("ftrace_filter=", set_ftrace_filter);
@@ -3571,7 +3570,7 @@ static const struct file_operations ftrace_filter_fops = {
 	.open = ftrace_filter_open,
 	.read = seq_read,
 	.write = ftrace_filter_write,
-	.llseek = ftrace_regex_lseek,
+	.llseek = ftrace_filter_lseek,
 	.release = ftrace_regex_release,
 };
 
@@ -3579,7 +3578,7 @@ static const struct file_operations ftrace_notrace_fops = {
 	.open = ftrace_notrace_open,
 	.read = seq_read,
 	.write = ftrace_notrace_write,
-	.llseek = ftrace_regex_lseek,
+	.llseek = ftrace_filter_lseek,
 	.release = ftrace_regex_release,
 };
 
@@ -3784,8 +3783,8 @@ static const struct file_operations ftrace_graph_fops = {
 	.open		= ftrace_graph_open,
 	.read		= seq_read,
 	.write		= ftrace_graph_write,
+	.llseek		= ftrace_filter_lseek,
 	.release	= ftrace_graph_release,
-	.llseek		= seq_lseek,
 };
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 
@@ -4131,7 +4130,8 @@ ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip,
 	preempt_disable_notrace();
 	trace_recursion_set(TRACE_CONTROL_BIT);
 	do_for_each_ftrace_op(op, ftrace_control_list) {
-		if (!ftrace_function_local_disabled(op) &&
+		if (!(op->flags & FTRACE_OPS_FL_STUB) &&
+		    !ftrace_function_local_disabled(op) &&
 		    ftrace_ops_test(op, ip))
 			op->func(ip, parent_ip, op, regs);
 	} while_for_each_ftrace_op(op);
@@ -4439,7 +4439,7 @@ static const struct file_operations ftrace_pid_fops = {
 	.open		= ftrace_pid_open,
 	.write		= ftrace_pid_write,
 	.read		= seq_read,
-	.llseek		= seq_lseek,
+	.llseek		= ftrace_filter_lseek,
 	.release	= ftrace_pid_release,
 };
 
@@ -4555,12 +4555,8 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
 		ftrace_startup_sysctl();
 
 		/* we are starting ftrace again */
-		if (ftrace_ops_list != &ftrace_list_end) {
-			if (ftrace_ops_list->next == &ftrace_list_end)
-				ftrace_trace_function = ftrace_ops_list->func;
-			else
-				ftrace_trace_function = ftrace_ops_list_func;
-		}
+		if (ftrace_ops_list != &ftrace_list_end)
+			update_ftrace_function();
 
 	} else {
 		/* stopping ftrace calls (just send to ftrace_stub) */
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 4f1dade56981..66338c4f7f4b 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -132,7 +132,7 @@ static char *default_bootup_tracer;
 
 static int __init set_cmdline_ftrace(char *str)
 {
-	strncpy(bootup_tracer_buf, str, MAX_TRACER_SIZE);
+	strlcpy(bootup_tracer_buf, str, MAX_TRACER_SIZE);
 	default_bootup_tracer = bootup_tracer_buf;
 	/* We are using ftrace early, expand it */
 	ring_buffer_expanded = 1;
@@ -162,7 +162,7 @@ static char *trace_boot_options __initdata;
 
 static int __init set_trace_boot_options(char *str)
 {
-	strncpy(trace_boot_options_buf, str, MAX_TRACER_SIZE);
+	strlcpy(trace_boot_options_buf, str, MAX_TRACER_SIZE);
 	trace_boot_options = trace_boot_options_buf;
 	return 0;
 }
@@ -744,8 +744,11 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
 		return;
 
 	WARN_ON_ONCE(!irqs_disabled());
-	if (WARN_ON_ONCE(!current_trace->allocated_snapshot))
+	if (!current_trace->allocated_snapshot) {
+		/* Only the nop tracer should hit this when disabling */
+		WARN_ON_ONCE(current_trace != &nop_trace);
 		return;
+	}
 
 	arch_spin_lock(&ftrace_max_lock);
 
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 42ca822fc701..83a8b5b7bd35 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -322,7 +322,7 @@ static const struct file_operations stack_trace_filter_fops = {
 	.open = stack_trace_filter_open,
 	.read = seq_read,
 	.write = ftrace_filter_write,
-	.llseek = ftrace_regex_lseek,
+	.llseek = ftrace_filter_lseek,
 	.release = ftrace_regex_release,
 };
 
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index a54f26f82eb2..e134d8f365dd 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -25,7 +25,8 @@
 
 static struct kmem_cache *user_ns_cachep __read_mostly;
 
-static bool new_idmap_permitted(struct user_namespace *ns, int cap_setid,
+static bool new_idmap_permitted(const struct file *file,
+				struct user_namespace *ns, int cap_setid,
 				struct uid_gid_map *map);
 
 static void set_cred_user_ns(struct cred *cred, struct user_namespace *user_ns)
@@ -612,10 +613,10 @@ static ssize_t map_write(struct file *file, const char __user *buf,
 	if (map->nr_extents != 0)
 		goto out;
 
-	/* Require the appropriate privilege CAP_SETUID or CAP_SETGID
-	 * over the user namespace in order to set the id mapping.
+	/*
+	 * Adjusting namespace settings requires capabilities on the target.
 	 */
-	if (cap_valid(cap_setid) && !ns_capable(ns, cap_setid))
+	if (cap_valid(cap_setid) && !file_ns_capable(file, ns, CAP_SYS_ADMIN))
 		goto out;
 
 	/* Get a buffer */
@@ -700,7 +701,7 @@ static ssize_t map_write(struct file *file, const char __user *buf,
 
 	ret = -EPERM;
 	/* Validate the user is allowed to use user id's mapped to. */
-	if (!new_idmap_permitted(ns, cap_setid, &new_map))
+	if (!new_idmap_permitted(file, ns, cap_setid, &new_map))
 		goto out;
 
 	/* Map the lower ids from the parent user namespace to the
@@ -787,7 +788,8 @@ ssize_t proc_projid_map_write(struct file *file, const char __user *buf, size_t
 			 &ns->projid_map, &ns->parent->projid_map);
 }
 
-static bool new_idmap_permitted(struct user_namespace *ns, int cap_setid,
+static bool new_idmap_permitted(const struct file *file, 
+				struct user_namespace *ns, int cap_setid,
 				struct uid_gid_map *new_map)
 {
 	/* Allow mapping to your own filesystem ids */
@@ -795,12 +797,12 @@ static bool new_idmap_permitted(struct user_namespace *ns, int cap_setid,
 		u32 id = new_map->extent[0].lower_first;
 		if (cap_setid == CAP_SETUID) {
 			kuid_t uid = make_kuid(ns->parent, id);
-			if (uid_eq(uid, current_fsuid()))
+			if (uid_eq(uid, file->f_cred->fsuid))
 				return true;
 		}
 		else if (cap_setid == CAP_SETGID) {
 			kgid_t gid = make_kgid(ns->parent, id);
-			if (gid_eq(gid, current_fsgid()))
+			if (gid_eq(gid, file->f_cred->fsgid))
 				return true;
 		}
 	}
@@ -811,8 +813,10 @@ static bool new_idmap_permitted(struct user_namespace *ns, int cap_setid,
 
 	/* Allow the specified ids if we have the appropriate capability
 	 * (CAP_SETUID or CAP_SETGID) over the parent user namespace.
+	 * And the opener of the id file also had the approprpiate capability.
 	 */
-	if (ns_capable(ns->parent, cap_setid))
+	if (ns_capable(ns->parent, cap_setid) &&
+	    file_ns_capable(file, ns->parent, cap_setid))
 		return true;
 
 	return false;