Merge branch 'linus' into timers/core

Reason: Get upstream fixes before adding conflicting code.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

31 files changed, 539 insertions, 275 deletions

diff --git a/kernel/capability.c b/kernel/capability.c
index 493d9725948..f6c2ce5701e 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 b0cd86501c3..4d3124b3927 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4434,12 +4434,15 @@ static void perf_event_task_event(struct perf_task_event *task_event)
 			if (ctxn < 0)
 				goto next;
 			ctx = rcu_dereference(current->perf_event_ctxp[ctxn]);
+			if (ctx)
+				perf_event_task_ctx(ctx, task_event);
 		}
-		if (ctx)
-			perf_event_task_ctx(ctx, task_event);
 next:
 		put_cpu_ptr(pmu->pmu_cpu_context);
 	}
+	if (task_event->task_ctx)
+		perf_event_task_ctx(task_event->task_ctx, task_event);
+
 	rcu_read_unlock();
 }
 
@@ -4734,7 +4737,8 @@ 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;
 		}
 
@@ -5327,7 +5331,7 @@ 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;
@@ -5647,6 +5651,7 @@ static void perf_swevent_init_hrtimer(struct perf_event *event)
 		event->attr.sample_period = NSEC_PER_SEC / freq;
 		hwc->sample_period = event->attr.sample_period;
 		local64_set(&hwc->period_left, hwc->sample_period);
+		hwc->last_period = hwc->sample_period;
 		event->attr.freq = 0;
 	}
 }
@@ -5982,6 +5987,7 @@ 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 d56a64c99a8..eb675c4d59d 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 23cb34ff397..97fddb09762 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/exit.c b/kernel/exit.c
index 51e485ca993..60bc027c61c 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -835,7 +835,7 @@ void do_exit(long code)
 	/*
 	 * Make sure we are holding no locks:
 	 */
-	debug_check_no_locks_held();
+	debug_check_no_locks_held(tsk);
 	/*
 	 * We can do this unlocked here. The futex code uses this flag
 	 * just to verify whether the pi state cleanup has been done
diff --git a/kernel/fork.c b/kernel/fork.c
index 8d932b1c905..1766d324d5e 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1141,6 +1141,9 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS))
 		return ERR_PTR(-EINVAL);
 
+	if ((clone_flags & (CLONE_NEWUSER|CLONE_FS)) == (CLONE_NEWUSER|CLONE_FS))
+		return ERR_PTR(-EINVAL);
+
 	/*
 	 * Thread groups must share signals as well, and detached threads
 	 * can only be started up within the thread group.
@@ -1807,7 +1810,7 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags)
 	 * If unsharing a user namespace must also unshare the thread.
 	 */
 	if (unshare_flags & CLONE_NEWUSER)
-		unshare_flags |= CLONE_THREAD;
+		unshare_flags |= CLONE_THREAD | CLONE_FS;
 	/*
 	 * If unsharing a pid namespace must also unshare the thread.
 	 */
diff --git a/kernel/futex.c b/kernel/futex.c
index f0090a993da..b26dcfc02c9 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -223,7 +223,8 @@ static void drop_futex_key_refs(union futex_key *key)
  * @rw:		mapping needs to be read/write (values: VERIFY_READ,
  *              VERIFY_WRITE)
  *
- * Returns a negative error code or 0
+ * Return: a negative error code or 0
+ *
  * The key words are stored in *key on success.
  *
  * For shared mappings, it's (page->index, file_inode(vma->vm_file),
@@ -705,9 +706,9 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
  *			be "current" except in the case of requeue pi.
  * @set_waiters:	force setting the FUTEX_WAITERS bit (1) or not (0)
  *
- * Returns:
- *  0 - ready to wait
- *  1 - acquired the lock
+ * Return:
+ *  0 - ready to wait;
+ *  1 - acquired the lock;
  * <0 - error
  *
  * The hb->lock and futex_key refs shall be held by the caller.
@@ -1191,9 +1192,9 @@ void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key,
  * then direct futex_lock_pi_atomic() to force setting the FUTEX_WAITERS bit.
  * hb1 and hb2 must be held by the caller.
  *
- * Returns:
- *  0 - failed to acquire the lock atomicly
- *  1 - acquired the lock
+ * Return:
+ *  0 - failed to acquire the lock atomically;
+ *  1 - acquired the lock;
  * <0 - error
  */
 static int futex_proxy_trylock_atomic(u32 __user *pifutex,
@@ -1254,8 +1255,8 @@ static int futex_proxy_trylock_atomic(u32 __user *pifutex,
  * Requeue waiters on uaddr1 to uaddr2. In the requeue_pi case, try to acquire
  * uaddr2 atomically on behalf of the top waiter.
  *
- * Returns:
- * >=0 - on success, the number of tasks requeued or woken
+ * Return:
+ * >=0 - on success, the number of tasks requeued or woken;
  *  <0 - on error
  */
 static int futex_requeue(u32 __user *uaddr1, unsigned int flags,
@@ -1536,8 +1537,8 @@ static inline void queue_me(struct futex_q *q, struct futex_hash_bucket *hb)
  * The q->lock_ptr must not be held by the caller. A call to unqueue_me() must
  * be paired with exactly one earlier call to queue_me().
  *
- * Returns:
- *   1 - if the futex_q was still queued (and we removed unqueued it)
+ * Return:
+ *   1 - if the futex_q was still queued (and we removed unqueued it);
  *   0 - if the futex_q was already removed by the waking thread
  */
 static int unqueue_me(struct futex_q *q)
@@ -1707,9 +1708,9 @@ static long futex_wait_restart(struct restart_block *restart);
  * the pi_state owner as well as handle race conditions that may allow us to
  * acquire the lock. Must be called with the hb lock held.
  *
- * Returns:
- *  1 - success, lock taken
- *  0 - success, lock not taken
+ * Return:
+ *  1 - success, lock taken;
+ *  0 - success, lock not taken;
  * <0 - on error (-EFAULT)
  */
 static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked)
@@ -1824,8 +1825,8 @@ static void futex_wait_queue_me(struct futex_hash_bucket *hb, struct futex_q *q,
  * Return with the hb lock held and a q.key reference on success, and unlocked
  * with no q.key reference on failure.
  *
- * Returns:
- *  0 - uaddr contains val and hb has been locked
+ * Return:
+ *  0 - uaddr contains val and hb has been locked;
  * <1 - -EFAULT or -EWOULDBLOCK (uaddr does not contain val) and hb is unlocked
  */
 static int futex_wait_setup(u32 __user *uaddr, u32 val, unsigned int flags,
@@ -2203,9 +2204,9 @@ pi_faulted:
  * the wakeup and return the appropriate error code to the caller.  Must be
  * called with the hb lock held.
  *
- * Returns
- *  0 - no early wakeup detected
- * <0 - -ETIMEDOUT or -ERESTARTNOINTR
+ * Return:
+ *  0 = no early wakeup detected;
+ * <0 = -ETIMEDOUT or -ERESTARTNOINTR
  */
 static inline
 int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb,
@@ -2247,7 +2248,6 @@ int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb,
  * @val:	the expected value of uaddr
  * @abs_time:	absolute timeout
  * @bitset:	32 bit wakeup bitset set by userspace, defaults to all
- * @clockrt:	whether to use CLOCK_REALTIME (1) or CLOCK_MONOTONIC (0)
  * @uaddr2:	the pi futex we will take prior to returning to user-space
  *
  * The caller will wait on uaddr and will be requeued by futex_requeue() to
@@ -2258,7 +2258,7 @@ int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb,
  * there was a need to.
  *
  * We call schedule in futex_wait_queue_me() when we enqueue and return there
- * via the following:
+ * via the following--
  * 1) wakeup on uaddr2 after an atomic lock acquisition by futex_requeue()
  * 2) wakeup on uaddr2 after a requeue
  * 3) signal
@@ -2276,8 +2276,8 @@ int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb,
  *
  * If 4 or 7, we cleanup and return with -ETIMEDOUT.
  *
- * Returns:
- *  0 - On success
+ * Return:
+ *  0 - On success;
  * <0 - On error
  */
 static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index c0875ae0de1..609d8ff38b7 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 =
 	{
 		{
@@ -1662,8 +1663,6 @@ 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 bddd3d7a74b..ffd4e111fd6 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 e35be53f661..3fed7f0cbcd 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 691dc2ef9ba..9eb7fed0bba 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 259db207b5d..8a0efac4f99 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -4088,7 +4088,7 @@ void debug_check_no_locks_freed(const void *mem_from, unsigned long mem_len)
 }
 EXPORT_SYMBOL_GPL(debug_check_no_locks_freed);
 
-static void print_held_locks_bug(void)
+static void print_held_locks_bug(struct task_struct *curr)
 {
 	if (!debug_locks_off())
 		return;
@@ -4097,21 +4097,22 @@ static void print_held_locks_bug(void)
 
 	printk("\n");
 	printk("=====================================\n");
-	printk("[ BUG: %s/%d still has locks held! ]\n",
-	       current->comm, task_pid_nr(current));
+	printk("[ BUG: lock held at task exit time! ]\n");
 	print_kernel_ident();
 	printk("-------------------------------------\n");
-	lockdep_print_held_locks(current);
+	printk("%s/%d is exiting with locks still held!\n",
+		curr->comm, task_pid_nr(curr));
+	lockdep_print_held_locks(curr);
+
 	printk("\nstack backtrace:\n");
 	dump_stack();
 }
 
-void debug_check_no_locks_held(void)
+void debug_check_no_locks_held(struct task_struct *task)
 {
-	if (unlikely(current->lockdep_depth > 0))
-		print_held_locks_bug();
+	if (unlikely(task->lockdep_depth > 0))
+		print_held_locks_bug(task);
 }
-EXPORT_SYMBOL_GPL(debug_check_no_locks_held);
 
 void debug_show_all_locks(void)
 {
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index c1c3dc1c602..bea15bdf82b 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -181,6 +181,7 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
 	int nr;
 	int rc;
 	struct task_struct *task, *me = current;
+	int init_pids = thread_group_leader(me) ? 1 : 2;
 
 	/* Don't allow any more processes into the pid namespace */
 	disable_pid_allocation(pid_ns);
@@ -230,7 +231,7 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
 	 */
 	for (;;) {
 		set_current_state(TASK_UNINTERRUPTIBLE);
-		if (pid_ns->nr_hashed == 1)
+		if (pid_ns->nr_hashed == init_pids)
 			break;
 		schedule();
 	}
diff --git a/kernel/printk.c b/kernel/printk.c
index 0b31715f335..abbdd9e2ac8 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -63,8 +63,6 @@ void asmlinkage __attribute__((weak)) early_printk(const char *fmt, ...)
 #define MINIMUM_CONSOLE_LOGLEVEL 1 /* Minimum loglevel we let people use */
 #define DEFAULT_CONSOLE_LOGLEVEL 7 /* anything MORE serious than KERN_DEBUG */
 
-DECLARE_WAIT_QUEUE_HEAD(log_wait);
-
 int console_printk[4] = {
 	DEFAULT_CONSOLE_LOGLEVEL,	/* console_loglevel */
 	DEFAULT_MESSAGE_LOGLEVEL,	/* default_message_loglevel */
@@ -224,6 +222,7 @@ struct log {
 static DEFINE_RAW_SPINLOCK(logbuf_lock);
 
 #ifdef CONFIG_PRINTK
+DECLARE_WAIT_QUEUE_HEAD(log_wait);
 /* the next printk record to read by syslog(READ) or /proc/kmsg */
 static u64 syslog_seq;
 static u32 syslog_idx;
@@ -1957,45 +1956,6 @@ int is_console_locked(void)
 	return console_locked;
 }
 
-/*
- * Delayed printk version, for scheduler-internal messages:
- */
-#define PRINTK_BUF_SIZE		512
-
-#define PRINTK_PENDING_WAKEUP	0x01
-#define PRINTK_PENDING_SCHED	0x02
-
-static DEFINE_PER_CPU(int, printk_pending);
-static DEFINE_PER_CPU(char [PRINTK_BUF_SIZE], printk_sched_buf);
-
-static void wake_up_klogd_work_func(struct irq_work *irq_work)
-{
-	int pending = __this_cpu_xchg(printk_pending, 0);
-
-	if (pending & PRINTK_PENDING_SCHED) {
-		char *buf = __get_cpu_var(printk_sched_buf);
-		printk(KERN_WARNING "[sched_delayed] %s", buf);
-	}
-
-	if (pending & PRINTK_PENDING_WAKEUP)
-		wake_up_interruptible(&log_wait);
-}
-
-static DEFINE_PER_CPU(struct irq_work, wake_up_klogd_work) = {
-	.func = wake_up_klogd_work_func,
-	.flags = IRQ_WORK_LAZY,
-};
-
-void wake_up_klogd(void)
-{
-	preempt_disable();
-	if (waitqueue_active(&log_wait)) {
-		this_cpu_or(printk_pending, PRINTK_PENDING_WAKEUP);
-		irq_work_queue(&__get_cpu_var(wake_up_klogd_work));
-	}
-	preempt_enable();
-}
-
 static void console_cont_flush(char *text, size_t size)
 {
 	unsigned long flags;
@@ -2458,6 +2418,44 @@ static int __init printk_late_init(void)
 late_initcall(printk_late_init);
 
 #if defined CONFIG_PRINTK
+/*
+ * Delayed printk version, for scheduler-internal messages:
+ */
+#define PRINTK_BUF_SIZE		512
+
+#define PRINTK_PENDING_WAKEUP	0x01
+#define PRINTK_PENDING_SCHED	0x02
+
+static DEFINE_PER_CPU(int, printk_pending);
+static DEFINE_PER_CPU(char [PRINTK_BUF_SIZE], printk_sched_buf);
+
+static void wake_up_klogd_work_func(struct irq_work *irq_work)
+{
+	int pending = __this_cpu_xchg(printk_pending, 0);
+
+	if (pending & PRINTK_PENDING_SCHED) {
+		char *buf = __get_cpu_var(printk_sched_buf);
+		printk(KERN_WARNING "[sched_delayed] %s", buf);
+	}
+
+	if (pending & PRINTK_PENDING_WAKEUP)
+		wake_up_interruptible(&log_wait);
+}
+
+static DEFINE_PER_CPU(struct irq_work, wake_up_klogd_work) = {
+	.func = wake_up_klogd_work_func,
+	.flags = IRQ_WORK_LAZY,
+};
+
+void wake_up_klogd(void)
+{
+	preempt_disable();
+	if (waitqueue_active(&log_wait)) {
+		this_cpu_or(printk_pending, PRINTK_PENDING_WAKEUP);
+		irq_work_queue(&__get_cpu_var(wake_up_klogd_work));
+	}
+	preempt_enable();
+}
 
 int printk_sched(const char *fmt, ...)
 {
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index c685e31492d..c3ae1446461 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 7f12624a393..67d04651f44 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)) {
@@ -4999,7 +5001,7 @@ 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 ed12cbb135f..e93cca92f38 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/signal.c b/kernel/signal.c
index 2ec870a4c3c..598dc06be42 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -485,6 +485,9 @@ flush_signal_handlers(struct task_struct *t, int force_default)
 		if (force_default || ka->sa.sa_handler != SIG_IGN)
 			ka->sa.sa_handler = SIG_DFL;
 		ka->sa.sa_flags = 0;
+#ifdef __ARCH_HAS_SA_RESTORER
+		ka->sa.sa_restorer = NULL;
+#endif
 		sigemptyset(&ka->sa.sa_mask);
 		ka++;
 	}
@@ -2682,7 +2685,7 @@ static int do_sigpending(void *set, unsigned long sigsetsize)
 /**
  *  sys_rt_sigpending - examine a pending signal that has been raised
  *			while blocked
- *  @set: stores pending signals
+ *  @uset: stores pending signals
  *  @sigsetsize: size of sigset_t type or larger
  */
 SYSCALL_DEFINE2(rt_sigpending, sigset_t __user *, uset, size_t, sigsetsize)
@@ -2945,7 +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 8eaed9aa9cf..02fc5c93367 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 81f56445fba..0da73cf73e6 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);
@@ -2185,9 +2186,8 @@ SYSCALL_DEFINE3(getcpu, unsigned __user *, cpup, unsigned __user *, nodep,
 
 char poweroff_cmd[POWEROFF_CMD_PATH_LEN] = "/sbin/poweroff";
 
-static int __orderly_poweroff(void)
+static int __orderly_poweroff(bool force)
 {
-	int argc;
 	char **argv;
 	static char *envp[] = {
 		"HOME=/",
@@ -2196,20 +2196,40 @@ static int __orderly_poweroff(void)
 	};
 	int ret;
 
-	argv = argv_split(GFP_ATOMIC, poweroff_cmd, &argc);
-	if (argv == NULL) {
+	argv = argv_split(GFP_KERNEL, poweroff_cmd, NULL);
+	if (argv) {
+		ret = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC);
+		argv_free(argv);
+	} else {
 		printk(KERN_WARNING "%s failed to allocate memory for \"%s\"\n",
-		       __func__, poweroff_cmd);
-		return -ENOMEM;
+					 __func__, poweroff_cmd);
+		ret = -ENOMEM;
 	}
 
-	ret = call_usermodehelper_fns(argv[0], argv, envp, UMH_WAIT_EXEC,
-				      NULL, NULL, NULL);
-	argv_free(argv);
+	if (ret && force) {
+		printk(KERN_WARNING "Failed to start orderly shutdown: "
+					"forcing the issue\n");
+		/*
+		 * I guess this should try to kick off some daemon to sync and
+		 * poweroff asap.  Or not even bother syncing if we're doing an
+		 * emergency shutdown?
+		 */
+		emergency_sync();
+		kernel_power_off();
+	}
 
 	return ret;
 }
 
+static bool poweroff_force;
+
+static void poweroff_work_func(struct work_struct *work)
+{
+	__orderly_poweroff(poweroff_force);
+}
+
+static DECLARE_WORK(poweroff_work, poweroff_work_func);
+
 /**
  * orderly_poweroff - Trigger an orderly system poweroff
  * @force: force poweroff if command execution fails
@@ -2219,21 +2239,9 @@ static int __orderly_poweroff(void)
  */
 int orderly_poweroff(bool force)
 {
-	int ret = __orderly_poweroff();
-
-	if (ret && force) {
-		printk(KERN_WARNING "Failed to start orderly shutdown: "
-		       "forcing the issue\n");
-
-		/*
-		 * I guess this should try to kick off some daemon to sync and
-		 * poweroff asap.  Or not even bother syncing if we're doing an
-		 * emergency shutdown?
-		 */
-		emergency_sync();
-		kernel_power_off();
-	}
-
-	return ret;
+	if (force) /* do not override the pending "true" */
+		poweroff_force = true;
+	schedule_work(&poweroff_work);
+	return 0;
 }
 EXPORT_SYMBOL_GPL(orderly_poweroff);
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index f8d2109ef0a..6e23fde83db 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -66,7 +66,8 @@ static void tick_broadcast_start_periodic(struct clock_event_device *bc)
  */
 int tick_check_broadcast_device(struct clock_event_device *dev)
 {
-	if ((tick_broadcast_device.evtdev &&
+	if ((dev->features & CLOCK_EVT_FEAT_DUMMY) ||
+	    (tick_broadcast_device.evtdev &&
 	     tick_broadcast_device.evtdev->rating >= dev->rating) ||
 	     (dev->features & CLOCK_EVT_FEAT_C3STOP))
 		return 0;
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 9e5b8c272ee..5a0f781cd72 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 ab25b88aae5..b3fde6d7b7f 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;
@@ -3104,8 +3103,8 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 					continue;
 			}
 
-			hlist_del(&entry->node);
-			call_rcu(&entry->rcu, ftrace_free_entry_rcu);
+			hlist_del_rcu(&entry->node);
+			call_rcu_sched(&entry->rcu, ftrace_free_entry_rcu);
 		}
 	}
 	__disable_ftrace_function_probe();
@@ -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 1f835a83cb2..66338c4f7f4 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;
 }
@@ -704,7 +704,7 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 void
 update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 {
-	struct ring_buffer *buf = tr->buffer;
+	struct ring_buffer *buf;
 
 	if (trace_stop_count)
 		return;
@@ -719,6 +719,7 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 
 	arch_spin_lock(&ftrace_max_lock);
 
+	buf = tr->buffer;
 	tr->buffer = max_tr.buffer;
 	max_tr.buffer = buf;
 
@@ -743,8 +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);
 
@@ -2880,11 +2884,25 @@ static int set_tracer_option(struct tracer *trace, char *cmp, int neg)
 	return -EINVAL;
 }
 
-static void set_tracer_flags(unsigned int mask, int enabled)
+/* Some tracers require overwrite to stay enabled */
+int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set)
+{
+	if (tracer->enabled && (mask & TRACE_ITER_OVERWRITE) && !set)
+		return -1;
+
+	return 0;
+}
+
+int set_tracer_flag(unsigned int mask, int enabled)
 {
 	/* do nothing if flag is already set */
 	if (!!(trace_flags & mask) == !!enabled)
-		return;
+		return 0;
+
+	/* Give the tracer a chance to approve the change */
+	if (current_trace->flag_changed)
+		if (current_trace->flag_changed(current_trace, mask, !!enabled))
+			return -EINVAL;
 
 	if (enabled)
 		trace_flags |= mask;
@@ -2894,18 +2912,24 @@ static void set_tracer_flags(unsigned int mask, int enabled)
 	if (mask == TRACE_ITER_RECORD_CMD)
 		trace_event_enable_cmd_record(enabled);
 
-	if (mask == TRACE_ITER_OVERWRITE)
+	if (mask == TRACE_ITER_OVERWRITE) {
 		ring_buffer_change_overwrite(global_trace.buffer, enabled);
+#ifdef CONFIG_TRACER_MAX_TRACE
+		ring_buffer_change_overwrite(max_tr.buffer, enabled);
+#endif
+	}
 
 	if (mask == TRACE_ITER_PRINTK)
 		trace_printk_start_stop_comm(enabled);
+
+	return 0;
 }
 
 static int trace_set_options(char *option)
 {
 	char *cmp;
 	int neg = 0;
-	int ret = 0;
+	int ret = -ENODEV;
 	int i;
 
 	cmp = strstrip(option);
@@ -2915,19 +2939,20 @@ static int trace_set_options(char *option)
 		cmp += 2;
 	}
 
+	mutex_lock(&trace_types_lock);
+
 	for (i = 0; trace_options[i]; i++) {
 		if (strcmp(cmp, trace_options[i]) == 0) {
-			set_tracer_flags(1 << i, !neg);
+			ret = set_tracer_flag(1 << i, !neg);
 			break;
 		}
 	}
 
 	/* If no option could be set, test the specific tracer options */
-	if (!trace_options[i]) {
-		mutex_lock(&trace_types_lock);
+	if (!trace_options[i])
 		ret = set_tracer_option(current_trace, cmp, neg);
-		mutex_unlock(&trace_types_lock);
-	}
+
+	mutex_unlock(&trace_types_lock);
 
 	return ret;
 }
@@ -2937,6 +2962,7 @@ tracing_trace_options_write(struct file *filp, const char __user *ubuf,
 			size_t cnt, loff_t *ppos)
 {
 	char buf[64];
+	int ret;
 
 	if (cnt >= sizeof(buf))
 		return -EINVAL;
@@ -2946,7 +2972,9 @@ tracing_trace_options_write(struct file *filp, const char __user *ubuf,
 
 	buf[cnt] = 0;
 
-	trace_set_options(buf);
+	ret = trace_set_options(buf);
+	if (ret < 0)
+		return ret;
 
 	*ppos += cnt;
 
@@ -3250,6 +3278,9 @@ static int tracing_set_tracer(const char *buf)
 		goto out;
 
 	trace_branch_disable();
+
+	current_trace->enabled = false;
+
 	if (current_trace->reset)
 		current_trace->reset(tr);
 
@@ -3294,6 +3325,7 @@ static int tracing_set_tracer(const char *buf)
 	}
 
 	current_trace = t;
+	current_trace->enabled = true;
 	trace_branch_enable(tr);
  out:
 	mutex_unlock(&trace_types_lock);
@@ -4780,7 +4812,13 @@ trace_options_core_write(struct file *filp, const char __user *ubuf, size_t cnt,
 
 	if (val != 0 && val != 1)
 		return -EINVAL;
-	set_tracer_flags(1 << index, val);
+
+	mutex_lock(&trace_types_lock);
+	ret = set_tracer_flag(1 << index, val);
+	mutex_unlock(&trace_types_lock);
+
+	if (ret < 0)
+		return ret;
 
 	*ppos += cnt;
 
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 57d7e5397d5..2081971367e 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -283,11 +283,15 @@ struct tracer {
 	enum print_line_t	(*print_line)(struct trace_iterator *iter);
 	/* If you handled the flag setting, return 0 */
 	int			(*set_flag)(u32 old_flags, u32 bit, int set);
+	/* Return 0 if OK with change, else return non-zero */
+	int			(*flag_changed)(struct tracer *tracer,
+						u32 mask, int set);
 	struct tracer		*next;
 	struct tracer_flags	*flags;
 	bool			print_max;
 	bool			use_max_tr;
 	bool			allocated_snapshot;
+	bool			enabled;
 };
 
 
@@ -943,6 +947,8 @@ extern const char *__stop___trace_bprintk_fmt[];
 
 void trace_printk_init_buffers(void);
 void trace_printk_start_comm(void);
+int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set);
+int set_tracer_flag(unsigned int mask, int enabled);
 
 #undef FTRACE_ENTRY
 #define FTRACE_ENTRY(call, struct_name, id, tstruct, print, filter)	\
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index 713a2cac488..443b25b43b4 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -32,7 +32,7 @@ enum {
 
 static int trace_type __read_mostly;
 
-static int save_lat_flag;
+static int save_flags;
 
 static void stop_irqsoff_tracer(struct trace_array *tr, int graph);
 static int start_irqsoff_tracer(struct trace_array *tr, int graph);
@@ -558,8 +558,11 @@ static void stop_irqsoff_tracer(struct trace_array *tr, int graph)
 
 static void __irqsoff_tracer_init(struct trace_array *tr)
 {
-	save_lat_flag = trace_flags & TRACE_ITER_LATENCY_FMT;
-	trace_flags |= TRACE_ITER_LATENCY_FMT;
+	save_flags = trace_flags;
+
+	/* non overwrite screws up the latency tracers */
+	set_tracer_flag(TRACE_ITER_OVERWRITE, 1);
+	set_tracer_flag(TRACE_ITER_LATENCY_FMT, 1);
 
 	tracing_max_latency = 0;
 	irqsoff_trace = tr;
@@ -573,10 +576,13 @@ static void __irqsoff_tracer_init(struct trace_array *tr)
 
 static void irqsoff_tracer_reset(struct trace_array *tr)
 {
+	int lat_flag = save_flags & TRACE_ITER_LATENCY_FMT;
+	int overwrite_flag = save_flags & TRACE_ITER_OVERWRITE;
+
 	stop_irqsoff_tracer(tr, is_graph());
 
-	if (!save_lat_flag)
-		trace_flags &= ~TRACE_ITER_LATENCY_FMT;
+	set_tracer_flag(TRACE_ITER_LATENCY_FMT, lat_flag);
+	set_tracer_flag(TRACE_ITER_OVERWRITE, overwrite_flag);
 }
 
 static void irqsoff_tracer_start(struct trace_array *tr)
@@ -609,6 +615,7 @@ static struct tracer irqsoff_tracer __read_mostly =
 	.print_line     = irqsoff_print_line,
 	.flags		= &tracer_flags,
 	.set_flag	= irqsoff_set_flag,
+	.flag_changed	= trace_keep_overwrite,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest    = trace_selftest_startup_irqsoff,
 #endif
@@ -642,6 +649,7 @@ static struct tracer preemptoff_tracer __read_mostly =
 	.print_line     = irqsoff_print_line,
 	.flags		= &tracer_flags,
 	.set_flag	= irqsoff_set_flag,
+	.flag_changed	= trace_keep_overwrite,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest    = trace_selftest_startup_preemptoff,
 #endif
@@ -677,6 +685,7 @@ static struct tracer preemptirqsoff_tracer __read_mostly =
 	.print_line     = irqsoff_print_line,
 	.flags		= &tracer_flags,
 	.set_flag	= irqsoff_set_flag,
+	.flag_changed	= trace_keep_overwrite,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest    = trace_selftest_startup_preemptirqsoff,
 #endif
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 75aa97fbe1a..fde652c9a51 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -36,7 +36,7 @@ static void __wakeup_reset(struct trace_array *tr);
 static int wakeup_graph_entry(struct ftrace_graph_ent *trace);
 static void wakeup_graph_return(struct ftrace_graph_ret *trace);
 
-static int save_lat_flag;
+static int save_flags;
 
 #define TRACE_DISPLAY_GRAPH     1
 
@@ -540,8 +540,11 @@ static void stop_wakeup_tracer(struct trace_array *tr)
 
 static int __wakeup_tracer_init(struct trace_array *tr)
 {
-	save_lat_flag = trace_flags & TRACE_ITER_LATENCY_FMT;
-	trace_flags |= TRACE_ITER_LATENCY_FMT;
+	save_flags = trace_flags;
+
+	/* non overwrite screws up the latency tracers */
+	set_tracer_flag(TRACE_ITER_OVERWRITE, 1);
+	set_tracer_flag(TRACE_ITER_LATENCY_FMT, 1);
 
 	tracing_max_latency = 0;
 	wakeup_trace = tr;
@@ -563,12 +566,15 @@ static int wakeup_rt_tracer_init(struct trace_array *tr)
 
 static void wakeup_tracer_reset(struct trace_array *tr)
 {
+	int lat_flag = save_flags & TRACE_ITER_LATENCY_FMT;
+	int overwrite_flag = save_flags & TRACE_ITER_OVERWRITE;
+
 	stop_wakeup_tracer(tr);
 	/* make sure we put back any tasks we are tracing */
 	wakeup_reset(tr);
 
-	if (!save_lat_flag)
-		trace_flags &= ~TRACE_ITER_LATENCY_FMT;
+	set_tracer_flag(TRACE_ITER_LATENCY_FMT, lat_flag);
+	set_tracer_flag(TRACE_ITER_OVERWRITE, overwrite_flag);
 }
 
 static void wakeup_tracer_start(struct trace_array *tr)
@@ -594,6 +600,7 @@ static struct tracer wakeup_tracer __read_mostly =
 	.print_line	= wakeup_print_line,
 	.flags		= &tracer_flags,
 	.set_flag	= wakeup_set_flag,
+	.flag_changed	= trace_keep_overwrite,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest    = trace_selftest_startup_wakeup,
 #endif
@@ -615,6 +622,7 @@ static struct tracer wakeup_rt_tracer __read_mostly =
 	.print_line	= wakeup_print_line,
 	.flags		= &tracer_flags,
 	.set_flag	= wakeup_set_flag,
+	.flag_changed	= trace_keep_overwrite,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest    = trace_selftest_startup_wakeup,
 #endif
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 42ca822fc70..83a8b5b7bd3 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.c b/kernel/user.c
index e81978e8c03..8e635a18ab5 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -51,6 +51,8 @@ struct user_namespace init_user_ns = {
 	.owner = GLOBAL_ROOT_UID,
 	.group = GLOBAL_ROOT_GID,
 	.proc_inum = PROC_USER_INIT_INO,
+	.may_mount_sysfs = true,
+	.may_mount_proc = true,
 };
 EXPORT_SYMBOL_GPL(init_user_ns);
 
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 8b650837083..e134d8f365d 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -21,10 +21,12 @@
 #include <linux/uaccess.h>
 #include <linux/ctype.h>
 #include <linux/projid.h>
+#include <linux/fs_struct.h>
 
 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)
@@ -60,6 +62,15 @@ int create_user_ns(struct cred *new)
 	kgid_t group = new->egid;
 	int ret;
 
+	/*
+	 * Verify that we can not violate the policy of which files
+	 * may be accessed that is specified by the root directory,
+	 * by verifing that the root directory is at the root of the
+	 * mount namespace which allows all files to be accessed.
+	 */
+	if (current_chrooted())
+		return -EPERM;
+
 	/* The creator needs a mapping in the parent user namespace
 	 * or else we won't be able to reasonably tell userspace who
 	 * created a user_namespace.
@@ -86,6 +97,8 @@ int create_user_ns(struct cred *new)
 
 	set_cred_user_ns(new, ns);
 
+	update_mnt_policy(ns);
+
 	return 0;
 }
 
@@ -600,10 +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 */
@@ -688,7 +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
@@ -775,7 +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 */
@@ -783,12 +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;
 		}
 	}
@@ -799,8 +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;
@@ -837,6 +853,9 @@ static int userns_install(struct nsproxy *nsproxy, void *ns)
 	if (atomic_read(&current->mm->mm_users) > 1)
 		return -EINVAL;
 
+	if (current->fs->users != 1)
+		return -EINVAL;
+
 	if (!ns_capable(user_ns, CAP_SYS_ADMIN))
 		return -EPERM;
 
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 81f2457811e..b48cd597145 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -457,11 +457,12 @@ static int worker_pool_assign_id(struct worker_pool *pool)
 	int ret;
 
 	mutex_lock(&worker_pool_idr_mutex);
-	idr_pre_get(&worker_pool_idr, GFP_KERNEL);
-	ret = idr_get_new(&worker_pool_idr, pool, &pool->id);
+	ret = idr_alloc(&worker_pool_idr, pool, 0, 0, GFP_KERNEL);
+	if (ret >= 0)
+		pool->id = ret;
 	mutex_unlock(&worker_pool_idr_mutex);
 
-	return ret;
+	return ret < 0 ? ret : 0;
 }
 
 /*
@@ -3446,28 +3447,34 @@ static void wq_unbind_fn(struct work_struct *work)
 
 		spin_unlock_irq(&pool->lock);
 		mutex_unlock(&pool->assoc_mutex);
-	}
 
-	/*
-	 * Call schedule() so that we cross rq->lock and thus can guarantee
-	 * sched callbacks see the %WORKER_UNBOUND flag.  This is necessary
-	 * as scheduler callbacks may be invoked from other cpus.
-	 */
-	schedule();
+		/*
+		 * Call schedule() so that we cross rq->lock and thus can
+		 * guarantee sched callbacks see the %WORKER_UNBOUND flag.
+		 * This is necessary as scheduler callbacks may be invoked
+		 * from other cpus.
+		 */
+		schedule();
 
-	/*
-	 * Sched callbacks are disabled now.  Zap nr_running.  After this,
-	 * nr_running stays zero and need_more_worker() and keep_working()
-	 * are always true as long as the worklist is not empty.  Pools on
-	 * @cpu now behave as unbound (in terms of concurrency management)
-	 * pools which are served by workers tied to the CPU.
-	 *
-	 * On return from this function, the current worker would trigger
-	 * unbound chain execution of pending work items if other workers
-	 * didn't already.
-	 */
-	for_each_std_worker_pool(pool, cpu)
+		/*
+		 * Sched callbacks are disabled now.  Zap nr_running.
+		 * After this, nr_running stays zero and need_more_worker()
+		 * and keep_working() are always true as long as the
+		 * worklist is not empty.  This pool now behaves as an
+		 * unbound (in terms of concurrency management) pool which
+		 * are served by workers tied to the pool.
+		 */
 		atomic_set(&pool->nr_running, 0);
+
+		/*
+		 * With concurrency management just turned off, a busy
+		 * worker blocking could lead to lengthy stalls.  Kick off
+		 * unbound chain execution of currently pending work items.
+		 */
+		spin_lock_irq(&pool->lock);
+		wake_up_worker(pool);
+		spin_unlock_irq(&pool->lock);
+	}
 }
 
 /*