Merge tag 'v3.9-rc5' into wq/for-3.10

Writeback conversion to workqueue will be based on top of wq/for-3.10
branch to take advantage of custom attrs and NUMA support for unbound
workqueues.  Mainline currently contains two commits which result in
non-trivial merge conflicts with wq/for-3.10 and because
block/for-3.10/core is based on v3.9-rc3 which contains one of the
conflicting commits, we need a pre-merge-window merge anyway.  Let's
pull v3.9-rc5 into wq/for-3.10 so that the block tree doesn't suffer
from workqueue merge conflicts.

The two conflicts and their resolutions:

* e68035fb65 ("workqueue: convert to idr_alloc()") in mainline changes
  worker_pool_assign_id() to use idr_alloc() instead of the old idr
  interface.  worker_pool_assign_id() goes through multiple locking
  changes in wq/for-3.10 causing the following conflict.

  static int worker_pool_assign_id(struct worker_pool *pool)
  {
	  int ret;

  <<<<<<< HEAD
	  lockdep_assert_held(&wq_pool_mutex);

	  do {
		  if (!idr_pre_get(&worker_pool_idr, GFP_KERNEL))
			  return -ENOMEM;
		  ret = idr_get_new(&worker_pool_idr, pool, &pool->id);
	  } while (ret == -EAGAIN);
  =======
	  mutex_lock(&worker_pool_idr_mutex);
	  ret = idr_alloc(&worker_pool_idr, pool, 0, 0, GFP_KERNEL);
	  if (ret >= 0)
		  pool->id = ret;
	  mutex_unlock(&worker_pool_idr_mutex);
  >>>>>>> c67bf5361e7e66a0ff1f4caf95f89347d55dfb89

	  return ret < 0 ? ret : 0;
  }

  We want locking from the former and idr_alloc() usage from the
  latter, which can be combined to the following.

  static int worker_pool_assign_id(struct worker_pool *pool)
  {
	  int ret;

	  lockdep_assert_held(&wq_pool_mutex);

	  ret = idr_alloc(&worker_pool_idr, pool, 0, 0, GFP_KERNEL);
	  if (ret >= 0) {
		  pool->id = ret;
		  return 0;
	  }
	  return ret;
   }

* eb2834285c ("workqueue: fix possible pool stall bug in
  wq_unbind_fn()") updated wq_unbind_fn() such that it has single
  larger for_each_std_worker_pool() loop instead of two separate loops
  with a schedule() call inbetween.  wq/for-3.10 renamed
  pool->assoc_mutex to pool->manager_mutex causing the following
  conflict (earlier function body and comments omitted for brevity).

  static void wq_unbind_fn(struct work_struct *work)
  {
  ...
		  spin_unlock_irq(&pool->lock);
  <<<<<<< HEAD
		  mutex_unlock(&pool->manager_mutex);
	  }
  =======
		  mutex_unlock(&pool->assoc_mutex);
  >>>>>>> c67bf5361e7e66a0ff1f4caf95f89347d55dfb89

		  schedule();

  <<<<<<< HEAD
	  for_each_cpu_worker_pool(pool, cpu)
  =======
  >>>>>>> c67bf5361e7e66a0ff1f4caf95f89347d55dfb89
		  atomic_set(&pool->nr_running, 0);

		  spin_lock_irq(&pool->lock);
		  wake_up_worker(pool);
		  spin_unlock_irq(&pool->lock);
	  }
  }

  The resolution is mostly trivial.  We want the control flow of the
  latter with the rename of the former.

  static void wq_unbind_fn(struct work_struct *work)
  {
  ...
		  spin_unlock_irq(&pool->lock);
		  mutex_unlock(&pool->manager_mutex);

		  schedule();

		  atomic_set(&pool->nr_running, 0);

		  spin_lock_irq(&pool->lock);
		  wake_up_worker(pool);
		  spin_unlock_irq(&pool->lock);
	  }
  }

Signed-off-by: Tejun Heo <tj@kernel.org>

22 files changed, 302 insertions, 180 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index b0cd865..59412d0 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();
 }
 
@@ -5647,6 +5650,7 @@ 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;
 	}
 }
diff --git a/kernel/exit.c b/kernel/exit.c
index 51e485c..60bc027 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 8d932b1..1766d32 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 f0090a9..b26dcfc 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/lockdep.c b/kernel/lockdep.c
index 259db20..8a0efac 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 c1c3dc1..bea15bd 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 0b31715..abbdd9e 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/signal.c b/kernel/signal.c
index 2ec870a..dd72567 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)
diff --git a/kernel/smpboot.c b/kernel/smpboot.c
index b9bde57..8eaed9a 100644
--- a/kernel/smpboot.c
+++ b/kernel/smpboot.c
@@ -131,7 +131,7 @@ static int smpboot_thread_fn(void *data)
 			continue;
 		}
 
-		//BUG_ON(td->cpu != smp_processor_id());
+		BUG_ON(td->cpu != smp_processor_id());
 
 		/* Check for state change setup */
 		switch (td->status) {
@@ -209,6 +209,8 @@ static void smpboot_unpark_thread(struct smp_hotplug_thread *ht, unsigned int cp
 {
 	struct task_struct *tsk = *per_cpu_ptr(ht->store, cpu);
 
+	if (ht->pre_unpark)
+		ht->pre_unpark(cpu);
 	kthread_unpark(tsk);
 }
 
diff --git a/kernel/softirq.c b/kernel/softirq.c
index b4d252f..14d7758 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -323,18 +323,10 @@ void irq_enter(void)
 
 static inline void invoke_softirq(void)
 {
-	if (!force_irqthreads) {
-#ifdef __ARCH_IRQ_EXIT_IRQS_DISABLED
+	if (!force_irqthreads)
 		__do_softirq();
-#else
-		do_softirq();
-#endif
-	} else {
-		__local_bh_disable((unsigned long)__builtin_return_address(0),
-				SOFTIRQ_OFFSET);
+	else
 		wakeup_softirqd();
-		__local_bh_enable(SOFTIRQ_OFFSET);
-	}
 }
 
 /*
@@ -342,9 +334,15 @@ static inline void invoke_softirq(void)
  */
 void irq_exit(void)
 {
+#ifndef __ARCH_IRQ_EXIT_IRQS_DISABLED
+	local_irq_disable();
+#else
+	WARN_ON_ONCE(!irqs_disabled());
+#endif
+
 	account_irq_exit_time(current);
 	trace_hardirq_exit();
-	sub_preempt_count(IRQ_EXIT_OFFSET);
+	sub_preempt_count(HARDIRQ_OFFSET);
 	if (!in_interrupt() && local_softirq_pending())
 		invoke_softirq();
 
@@ -354,7 +352,6 @@ void irq_exit(void)
 		tick_nohz_irq_exit();
 #endif
 	rcu_irq_exit();
-	sched_preempt_enable_no_resched();
 }
 
 /*
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index 95d178c..c09f295 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -336,7 +336,7 @@ static struct smp_hotplug_thread cpu_stop_threads = {
 	.create			= cpu_stop_create,
 	.setup			= cpu_stop_unpark,
 	.park			= cpu_stop_park,
-	.unpark			= cpu_stop_unpark,
+	.pre_unpark		= cpu_stop_unpark,
 	.selfparking		= true,
 };
 
diff --git a/kernel/sys.c b/kernel/sys.c
index 81f5644..39c9c4a 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -2185,9 +2185,8 @@ 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 +2195,40 @@ 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 +2238,9 @@ 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 2fb8cb8..7f32fe0 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -67,7 +67,8 @@ 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/Kconfig b/kernel/trace/Kconfig
index 192473b..fc382d6 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -414,24 +414,28 @@ config PROBE_EVENTS
 	def_bool n
 
 config DYNAMIC_FTRACE
-	bool "enable/disable ftrace tracepoints dynamically"
+	bool "enable/disable function tracing dynamically"
 	depends on FUNCTION_TRACER
 	depends on HAVE_DYNAMIC_FTRACE
 	default y
 	help
-          This option will modify all the calls to ftrace dynamically
-	  (will patch them out of the binary image and replace them
-	  with a No-Op instruction) as they are called. A table is
-	  created to dynamically enable them again.
+	  This option will modify all the calls to function tracing
+	  dynamically (will patch them out of the binary image and
+	  replace them with a No-Op instruction) on boot up. During
+	  compile time, a table is made of all the locations that ftrace
+	  can function trace, and this table is linked into the kernel
+	  image. When this is enabled, functions can be individually
+	  enabled, and the functions not enabled will not affect
+	  performance of the system.
+
+	  See the files in /sys/kernel/debug/tracing:
+	    available_filter_functions
+	    set_ftrace_filter
+	    set_ftrace_notrace
 
 	  This way a CONFIG_FUNCTION_TRACER kernel is slightly larger, but
 	  otherwise has native performance as long as no tracing is active.
 
-	  The changes to the code are done by a kernel thread that
-	  wakes up once a second and checks to see if any ftrace calls
-	  were made. If so, it runs stop_machine (stops all CPUS)
-	  and modifies the code to jump over the call to ftrace.
-
 config DYNAMIC_FTRACE_WITH_REGS
 	def_bool y
 	depends on DYNAMIC_FTRACE
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index ab25b88..6893d5a 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -3104,8 +3104,8 @@ __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();
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index c2e2c23..4f1dade 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -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;
 
@@ -2400,6 +2401,27 @@ static void test_ftrace_alive(struct seq_file *m)
 	seq_printf(m, "#          MAY BE MISSING FUNCTION EVENTS\n");
 }
 
+#ifdef CONFIG_TRACER_MAX_TRACE
+static void print_snapshot_help(struct seq_file *m, struct trace_iterator *iter)
+{
+	if (iter->trace->allocated_snapshot)
+		seq_printf(m, "#\n# * Snapshot is allocated *\n#\n");
+	else
+		seq_printf(m, "#\n# * Snapshot is freed *\n#\n");
+
+	seq_printf(m, "# Snapshot commands:\n");
+	seq_printf(m, "# echo 0 > snapshot : Clears and frees snapshot buffer\n");
+	seq_printf(m, "# echo 1 > snapshot : Allocates snapshot buffer, if not already allocated.\n");
+	seq_printf(m, "#                      Takes a snapshot of the main buffer.\n");
+	seq_printf(m, "# echo 2 > snapshot : Clears snapshot buffer (but does not allocate)\n");
+	seq_printf(m, "#                      (Doesn't have to be '2' works with any number that\n");
+	seq_printf(m, "#                       is not a '0' or '1')\n");
+}
+#else
+/* Should never be called */
+static inline void print_snapshot_help(struct seq_file *m, struct trace_iterator *iter) { }
+#endif
+
 static int s_show(struct seq_file *m, void *v)
 {
 	struct trace_iterator *iter = v;
@@ -2411,7 +2433,9 @@ static int s_show(struct seq_file *m, void *v)
 			seq_puts(m, "#\n");
 			test_ftrace_alive(m);
 		}
-		if (iter->trace && iter->trace->print_header)
+		if (iter->snapshot && trace_empty(iter))
+			print_snapshot_help(m, iter);
+		else if (iter->trace && iter->trace->print_header)
 			iter->trace->print_header(m);
 		else
 			trace_default_header(m);
@@ -2857,11 +2881,25 @@ 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;
@@ -2871,18 +2909,24 @@ 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);
@@ -2892,19 +2936,20 @@ 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;
 }
@@ -2914,6 +2959,7 @@ 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;
@@ -2923,7 +2969,9 @@ 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;
 
@@ -3227,6 +3275,9 @@ 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);
 
@@ -3271,6 +3322,7 @@ 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);
@@ -4144,8 +4196,6 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt,
 	default:
 		if (current_trace->allocated_snapshot)
 			tracing_reset_online_cpus(&max_tr);
-		else
-			ret = -EINVAL;
 		break;
 	}
 
@@ -4759,7 +4809,13 @@ 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 57d7e53..2081971 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 713a2ca..443b25b 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 75aa97f..fde652c 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/user.c b/kernel/user.c
index e81978e..8e635a1 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 8b65083..a54f26f 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -21,6 +21,7 @@
 #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;
 
@@ -60,6 +61,15 @@ 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 +96,8 @@ int create_user_ns(struct cred *new)
 
 	set_cred_user_ns(new, ns);
 
+	update_mnt_policy(ns);
+
 	return 0;
 }
 
@@ -837,6 +849,9 @@ 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 729ac6a..dd2a4c4 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -510,12 +510,11 @@ static int worker_pool_assign_id(struct worker_pool *pool)
 
 	lockdep_assert_held(&wq_pool_mutex);
 
-	do {
-		if (!idr_pre_get(&worker_pool_idr, GFP_KERNEL))
-			return -ENOMEM;
-		ret = idr_get_new(&worker_pool_idr, pool, &pool->id);
-	} while (ret == -EAGAIN);
-
+	ret = idr_alloc(&worker_pool_idr, pool, 0, 0, GFP_KERNEL);
+	if (ret >= 0) {
+		pool->id = ret;
+		return 0;
+	}
 	return ret;
 }
 
@@ -4408,28 +4407,34 @@ static void wq_unbind_fn(struct work_struct *work)
 
 		spin_unlock_irq(&pool->lock);
 		mutex_unlock(&pool->manager_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_cpu_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);
+	}
 }
 
 /**