Merge branch 'linus' into core/printk

38 files changed, 609 insertions, 198 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index 170a9213c1b6..e4791b3ba55d 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -51,6 +51,7 @@ obj-$(CONFIG_UID16) += uid16.o
 obj-$(CONFIG_MODULES) += module.o
 obj-$(CONFIG_KALLSYMS) += kallsyms.o
 obj-$(CONFIG_PM) += power/
+obj-$(CONFIG_FREEZER) += power/
 obj-$(CONFIG_BSD_PROCESS_ACCT) += acct.o
 obj-$(CONFIG_KEXEC) += kexec.o
 obj-$(CONFIG_BACKTRACE_SELF_TEST) += backtracetest.o
diff --git a/kernel/async.c b/kernel/async.c
index 608b32b42812..f565891f2c9b 100644
--- a/kernel/async.c
+++ b/kernel/async.c
@@ -54,6 +54,7 @@ asynchronous and synchronous parts of the kernel.
 #include <linux/sched.h>
 #include <linux/init.h>
 #include <linux/kthread.h>
+#include <linux/delay.h>
 #include <asm/atomic.h>
 
 static async_cookie_t next_cookie = 1;
@@ -132,21 +133,23 @@ static void run_one_entry(void)
 	entry = list_first_entry(&async_pending, struct async_entry, list);
 
 	/* 2) move it to the running queue */
-	list_del(&entry->list);
-	list_add_tail(&entry->list, &async_running);
+	list_move_tail(&entry->list, entry->running);
 	spin_unlock_irqrestore(&async_lock, flags);
 
 	/* 3) run it (and print duration)*/
 	if (initcall_debug && system_state == SYSTEM_BOOTING) {
-		printk("calling  %lli_%pF @ %i\n", entry->cookie, entry->func, task_pid_nr(current));
+		printk("calling  %lli_%pF @ %i\n", (long long)entry->cookie,
+			entry->func, task_pid_nr(current));
 		calltime = ktime_get();
 	}
 	entry->func(entry->data, entry->cookie);
 	if (initcall_debug && system_state == SYSTEM_BOOTING) {
 		rettime = ktime_get();
 		delta = ktime_sub(rettime, calltime);
-		printk("initcall %lli_%pF returned 0 after %lld usecs\n", entry->cookie,
-			entry->func, ktime_to_ns(delta) >> 10);
+		printk("initcall %lli_%pF returned 0 after %lld usecs\n",
+			(long long)entry->cookie,
+			entry->func,
+			(long long)ktime_to_ns(delta) >> 10);
 	}
 
 	/* 4) remove it from the running queue */
@@ -205,18 +208,44 @@ static async_cookie_t __async_schedule(async_func_ptr *ptr, void *data, struct l
 	return newcookie;
 }
 
+/**
+ * async_schedule - schedule a function for asynchronous execution
+ * @ptr: function to execute asynchronously
+ * @data: data pointer to pass to the function
+ *
+ * Returns an async_cookie_t that may be used for checkpointing later.
+ * Note: This function may be called from atomic or non-atomic contexts.
+ */
 async_cookie_t async_schedule(async_func_ptr *ptr, void *data)
 {
-	return __async_schedule(ptr, data, &async_pending);
+	return __async_schedule(ptr, data, &async_running);
 }
 EXPORT_SYMBOL_GPL(async_schedule);
 
-async_cookie_t async_schedule_special(async_func_ptr *ptr, void *data, struct list_head *running)
+/**
+ * async_schedule_domain - schedule a function for asynchronous execution within a certain domain
+ * @ptr: function to execute asynchronously
+ * @data: data pointer to pass to the function
+ * @running: running list for the domain
+ *
+ * Returns an async_cookie_t that may be used for checkpointing later.
+ * @running may be used in the async_synchronize_*_domain() functions
+ * to wait within a certain synchronization domain rather than globally.
+ * A synchronization domain is specified via the running queue @running to use.
+ * Note: This function may be called from atomic or non-atomic contexts.
+ */
+async_cookie_t async_schedule_domain(async_func_ptr *ptr, void *data,
+				     struct list_head *running)
 {
 	return __async_schedule(ptr, data, running);
 }
-EXPORT_SYMBOL_GPL(async_schedule_special);
+EXPORT_SYMBOL_GPL(async_schedule_domain);
 
+/**
+ * async_synchronize_full - synchronize all asynchronous function calls
+ *
+ * This function waits until all asynchronous function calls have been done.
+ */
 void async_synchronize_full(void)
 {
 	do {
@@ -225,13 +254,30 @@ void async_synchronize_full(void)
 }
 EXPORT_SYMBOL_GPL(async_synchronize_full);
 
-void async_synchronize_full_special(struct list_head *list)
+/**
+ * async_synchronize_full_domain - synchronize all asynchronous function within a certain domain
+ * @list: running list to synchronize on
+ *
+ * This function waits until all asynchronous function calls for the
+ * synchronization domain specified by the running list @list have been done.
+ */
+void async_synchronize_full_domain(struct list_head *list)
 {
-	async_synchronize_cookie_special(next_cookie, list);
+	async_synchronize_cookie_domain(next_cookie, list);
 }
-EXPORT_SYMBOL_GPL(async_synchronize_full_special);
+EXPORT_SYMBOL_GPL(async_synchronize_full_domain);
 
-void async_synchronize_cookie_special(async_cookie_t cookie, struct list_head *running)
+/**
+ * async_synchronize_cookie_domain - synchronize asynchronous function calls within a certain domain with cookie checkpointing
+ * @cookie: async_cookie_t to use as checkpoint
+ * @running: running list to synchronize on
+ *
+ * This function waits until all asynchronous function calls for the
+ * synchronization domain specified by the running list @list submitted
+ * prior to @cookie have been done.
+ */
+void async_synchronize_cookie_domain(async_cookie_t cookie,
+				     struct list_head *running)
 {
 	ktime_t starttime, delta, endtime;
 
@@ -247,14 +293,22 @@ void async_synchronize_cookie_special(async_cookie_t cookie, struct list_head *r
 		delta = ktime_sub(endtime, starttime);
 
 		printk("async_continuing @ %i after %lli usec\n",
-			task_pid_nr(current), ktime_to_ns(delta) >> 10);
+			task_pid_nr(current),
+			(long long)ktime_to_ns(delta) >> 10);
 	}
 }
-EXPORT_SYMBOL_GPL(async_synchronize_cookie_special);
+EXPORT_SYMBOL_GPL(async_synchronize_cookie_domain);
 
+/**
+ * async_synchronize_cookie - synchronize asynchronous function calls with cookie checkpointing
+ * @cookie: async_cookie_t to use as checkpoint
+ *
+ * This function waits until all asynchronous function calls prior to @cookie
+ * have been done.
+ */
 void async_synchronize_cookie(async_cookie_t cookie)
 {
-	async_synchronize_cookie_special(cookie, &async_running);
+	async_synchronize_cookie_domain(cookie, &async_running);
 }
 EXPORT_SYMBOL_GPL(async_synchronize_cookie);
 
@@ -315,7 +369,11 @@ static int async_manager_thread(void *unused)
 		ec = atomic_read(&entry_count);
 
 		while (tc < ec && tc < MAX_THREADS) {
-			kthread_run(async_thread, NULL, "async/%i", tc);
+			if (IS_ERR(kthread_run(async_thread, NULL, "async/%i",
+					       tc))) {
+				msleep(100);
+				continue;
+			}
 			atomic_inc(&thread_count);
 			tc++;
 		}
@@ -330,7 +388,9 @@ static int async_manager_thread(void *unused)
 static int __init async_init(void)
 {
 	if (async_enabled)
-		kthread_run(async_manager_thread, NULL, "async/mgr");
+		if (IS_ERR(kthread_run(async_manager_thread, NULL,
+				       "async/mgr")))
+			async_enabled = 0;
 	return 0;
 }
 
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 5a54ff42874e..9edb5c4b79b4 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1122,8 +1122,8 @@ static void cgroup_kill_sb(struct super_block *sb) {
 
 	mutex_unlock(&cgroup_mutex);
 
-	kfree(root);
 	kill_litter_super(sb);
+	kfree(root);
 }
 
 static struct file_system_type cgroup_fs_type = {
@@ -2351,7 +2351,7 @@ static void cgroup_lock_hierarchy(struct cgroupfs_root *root)
 	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
 		struct cgroup_subsys *ss = subsys[i];
 		if (ss->root == root)
-			mutex_lock_nested(&ss->hierarchy_mutex, i);
+			mutex_lock(&ss->hierarchy_mutex);
 	}
 }
 
@@ -2637,6 +2637,7 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
 	BUG_ON(!list_empty(&init_task.tasks));
 
 	mutex_init(&ss->hierarchy_mutex);
+	lockdep_set_class(&ss->hierarchy_mutex, &ss->subsys_key);
 	ss->active = 1;
 }
 
diff --git a/kernel/exit.c b/kernel/exit.c
index f80dec3f1875..efd30ccf3858 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -118,6 +118,8 @@ static void __exit_signal(struct task_struct *tsk)
 		 * We won't ever get here for the group leader, since it
 		 * will have been the last reference on the signal_struct.
 		 */
+		sig->utime = cputime_add(sig->utime, task_utime(tsk));
+		sig->stime = cputime_add(sig->stime, task_stime(tsk));
 		sig->gtime = cputime_add(sig->gtime, task_gtime(tsk));
 		sig->min_flt += tsk->min_flt;
 		sig->maj_flt += tsk->maj_flt;
@@ -126,6 +128,7 @@ static void __exit_signal(struct task_struct *tsk)
 		sig->inblock += task_io_get_inblock(tsk);
 		sig->oublock += task_io_get_oublock(tsk);
 		task_io_accounting_add(&sig->ioac, &tsk->ioac);
+		sig->sum_sched_runtime += tsk->se.sum_exec_runtime;
 		sig = NULL; /* Marker for below. */
 	}
 
diff --git a/kernel/fork.c b/kernel/fork.c
index 242a706e7721..4854c2c4a82e 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -851,13 +851,14 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	sig->tty_old_pgrp = NULL;
 	sig->tty = NULL;
 
-	sig->cutime = sig->cstime = cputime_zero;
+	sig->utime = sig->stime = sig->cutime = sig->cstime = cputime_zero;
 	sig->gtime = cputime_zero;
 	sig->cgtime = cputime_zero;
 	sig->nvcsw = sig->nivcsw = sig->cnvcsw = sig->cnivcsw = 0;
 	sig->min_flt = sig->maj_flt = sig->cmin_flt = sig->cmaj_flt = 0;
 	sig->inblock = sig->oublock = sig->cinblock = sig->coublock = 0;
 	task_io_accounting_init(&sig->ioac);
+	sig->sum_sched_runtime = 0;
 	taskstats_tgid_init(sig);
 
 	task_lock(current->group_leader);
@@ -1005,6 +1006,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	 * triggers too late. This doesn't hurt, the check is only there
 	 * to stop root fork bombs.
 	 */
+	retval = -EAGAIN;
 	if (nr_threads >= max_threads)
 		goto bad_fork_cleanup_count;
 
@@ -1093,7 +1095,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 #ifdef CONFIG_DEBUG_MUTEXES
 	p->blocked_on = NULL; /* not blocked yet */
 #endif
-	if (unlikely(ptrace_reparented(current)))
+	if (unlikely(current->ptrace))
 		ptrace_fork(p, clone_flags);
 
 	/* Perform scheduler related setup. Assign this task to a CPU. */
@@ -1177,10 +1179,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 #endif
 	clear_all_latency_tracing(p);
 
-	/* Our parent execution domain becomes current domain
-	   These must match for thread signalling to apply */
-	p->parent_exec_id = p->self_exec_id;
-
 	/* ok, now we should be set up.. */
 	p->exit_signal = (clone_flags & CLONE_THREAD) ? -1 : (clone_flags & CSIGNAL);
 	p->pdeath_signal = 0;
@@ -1218,10 +1216,13 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		set_task_cpu(p, smp_processor_id());
 
 	/* CLONE_PARENT re-uses the old parent */
-	if (clone_flags & (CLONE_PARENT|CLONE_THREAD))
+	if (clone_flags & (CLONE_PARENT|CLONE_THREAD)) {
 		p->real_parent = current->real_parent;
-	else
+		p->parent_exec_id = current->parent_exec_id;
+	} else {
 		p->real_parent = current;
+		p->parent_exec_id = current->self_exec_id;
+	}
 
 	spin_lock(&current->sighand->siglock);
 
diff --git a/kernel/futex.c b/kernel/futex.c
index f89d373a9c6d..438701adce23 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1165,6 +1165,7 @@ static int futex_wait(u32 __user *uaddr, int fshared,
 		      u32 val, ktime_t *abs_time, u32 bitset, int clockrt)
 {
 	struct task_struct *curr = current;
+	struct restart_block *restart;
 	DECLARE_WAITQUEUE(wait, curr);
 	struct futex_hash_bucket *hb;
 	struct futex_q q;
@@ -1216,11 +1217,13 @@ retry:
 
 		if (!ret)
 			goto retry;
-		return ret;
+		goto out;
 	}
 	ret = -EWOULDBLOCK;
-	if (uval != val)
-		goto out_unlock_put_key;
+	if (unlikely(uval != val)) {
+		queue_unlock(&q, hb);
+		goto out_put_key;
+	}
 
 	/* Only actually queue if *uaddr contained val.  */
 	queue_me(&q, hb);
@@ -1284,38 +1287,38 @@ retry:
 	 */
 
 	/* If we were woken (and unqueued), we succeeded, whatever. */
+	ret = 0;
 	if (!unqueue_me(&q))
-		return 0;
+		goto out_put_key;
+	ret = -ETIMEDOUT;
 	if (rem)
-		return -ETIMEDOUT;
+		goto out_put_key;
 
 	/*
 	 * We expect signal_pending(current), but another thread may
 	 * have handled it for us already.
 	 */
+	ret = -ERESTARTSYS;
 	if (!abs_time)
-		return -ERESTARTSYS;
-	else {
-		struct restart_block *restart;
-		restart = &current_thread_info()->restart_block;
-		restart->fn = futex_wait_restart;
-		restart->futex.uaddr = (u32 *)uaddr;
-		restart->futex.val = val;
-		restart->futex.time = abs_time->tv64;
-		restart->futex.bitset = bitset;
-		restart->futex.flags = 0;
-
-		if (fshared)
-			restart->futex.flags |= FLAGS_SHARED;
-		if (clockrt)
-			restart->futex.flags |= FLAGS_CLOCKRT;
-		return -ERESTART_RESTARTBLOCK;
-	}
+		goto out_put_key;
 
-out_unlock_put_key:
-	queue_unlock(&q, hb);
-	put_futex_key(fshared, &q.key);
+	restart = &current_thread_info()->restart_block;
+	restart->fn = futex_wait_restart;
+	restart->futex.uaddr = (u32 *)uaddr;
+	restart->futex.val = val;
+	restart->futex.time = abs_time->tv64;
+	restart->futex.bitset = bitset;
+	restart->futex.flags = 0;
+
+	if (fshared)
+		restart->futex.flags |= FLAGS_SHARED;
+	if (clockrt)
+		restart->futex.flags |= FLAGS_CLOCKRT;
 
+	ret = -ERESTART_RESTARTBLOCK;
+
+out_put_key:
+	put_futex_key(fshared, &q.key);
 out:
 	return ret;
 }
diff --git a/kernel/irq/numa_migrate.c b/kernel/irq/numa_migrate.c
index ecf765c6a77a..acd88356ac76 100644
--- a/kernel/irq/numa_migrate.c
+++ b/kernel/irq/numa_migrate.c
@@ -71,7 +71,7 @@ static struct irq_desc *__real_move_irq_desc(struct irq_desc *old_desc,
 	desc = irq_desc_ptrs[irq];
 
 	if (desc && old_desc != desc)
-			goto out_unlock;
+		goto out_unlock;
 
 	node = cpu_to_node(cpu);
 	desc = kzalloc_node(sizeof(*desc), GFP_ATOMIC, node);
@@ -84,10 +84,15 @@ static struct irq_desc *__real_move_irq_desc(struct irq_desc *old_desc,
 	init_copy_one_irq_desc(irq, old_desc, desc, cpu);
 
 	irq_desc_ptrs[irq] = desc;
+	spin_unlock_irqrestore(&sparse_irq_lock, flags);
 
 	/* free the old one */
 	free_one_irq_desc(old_desc, desc);
+	spin_unlock(&old_desc->lock);
 	kfree(old_desc);
+	spin_lock(&desc->lock);
+
+	return desc;
 
 out_unlock:
 	spin_unlock_irqrestore(&sparse_irq_lock, flags);
diff --git a/kernel/itimer.c b/kernel/itimer.c
index 6a5fe93dd8bd..58762f7077ec 100644
--- a/kernel/itimer.c
+++ b/kernel/itimer.c
@@ -62,7 +62,7 @@ int do_getitimer(int which, struct itimerval *value)
 			struct task_cputime cputime;
 			cputime_t utime;
 
-			thread_group_cputime(tsk, &cputime);
+			thread_group_cputimer(tsk, &cputime);
 			utime = cputime.utime;
 			if (cputime_le(cval, utime)) { /* about to fire */
 				cval = jiffies_to_cputime(1);
@@ -82,7 +82,7 @@ int do_getitimer(int which, struct itimerval *value)
 			struct task_cputime times;
 			cputime_t ptime;
 
-			thread_group_cputime(tsk, &times);
+			thread_group_cputimer(tsk, &times);
 			ptime = cputime_add(times.utime, times.stime);
 			if (cputime_le(cval, ptime)) { /* about to fire */
 				cval = jiffies_to_cputime(1);
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 8a6d7b08864e..483899578259 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -1465,6 +1465,11 @@ int kernel_kexec(void)
 		error = device_power_down(PMSG_FREEZE);
 		if (error)
 			goto Enable_irqs;
+
+		/* Suspend system devices */
+		error = sysdev_suspend(PMSG_FREEZE);
+		if (error)
+			goto Power_up_devices;
 	} else
 #endif
 	{
@@ -1477,6 +1482,8 @@ int kernel_kexec(void)
 
 #ifdef CONFIG_KEXEC_JUMP
 	if (kexec_image->preserve_context) {
+		sysdev_resume();
+ Power_up_devices:
 		device_power_up(PMSG_RESTORE);
  Enable_irqs:
 		local_irq_enable();
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index fa07da94d7be..e976e505648d 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -230,6 +230,71 @@ static int cpu_clock_sample(const clockid_t which_clock, struct task_struct *p,
 	return 0;
 }
 
+void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times)
+{
+	struct sighand_struct *sighand;
+	struct signal_struct *sig;
+	struct task_struct *t;
+
+	*times = INIT_CPUTIME;
+
+	rcu_read_lock();
+	sighand = rcu_dereference(tsk->sighand);
+	if (!sighand)
+		goto out;
+
+	sig = tsk->signal;
+
+	t = tsk;
+	do {
+		times->utime = cputime_add(times->utime, t->utime);
+		times->stime = cputime_add(times->stime, t->stime);
+		times->sum_exec_runtime += t->se.sum_exec_runtime;
+
+		t = next_thread(t);
+	} while (t != tsk);
+
+	times->utime = cputime_add(times->utime, sig->utime);
+	times->stime = cputime_add(times->stime, sig->stime);
+	times->sum_exec_runtime += sig->sum_sched_runtime;
+out:
+	rcu_read_unlock();
+}
+
+static void update_gt_cputime(struct task_cputime *a, struct task_cputime *b)
+{
+	if (cputime_gt(b->utime, a->utime))
+		a->utime = b->utime;
+
+	if (cputime_gt(b->stime, a->stime))
+		a->stime = b->stime;
+
+	if (b->sum_exec_runtime > a->sum_exec_runtime)
+		a->sum_exec_runtime = b->sum_exec_runtime;
+}
+
+void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times)
+{
+	struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
+	struct task_cputime sum;
+	unsigned long flags;
+
+	spin_lock_irqsave(&cputimer->lock, flags);
+	if (!cputimer->running) {
+		cputimer->running = 1;
+		/*
+		 * The POSIX timer interface allows for absolute time expiry
+		 * values through the TIMER_ABSTIME flag, therefore we have
+		 * to synchronize the timer to the clock every time we start
+		 * it.
+		 */
+		thread_group_cputime(tsk, &sum);
+		update_gt_cputime(&cputimer->cputime, &sum);
+	}
+	*times = cputimer->cputime;
+	spin_unlock_irqrestore(&cputimer->lock, flags);
+}
+
 /*
  * Sample a process (thread group) clock for the given group_leader task.
  * Must be called with tasklist_lock held for reading.
@@ -457,7 +522,7 @@ void posix_cpu_timers_exit_group(struct task_struct *tsk)
 {
 	struct task_cputime cputime;
 
-	thread_group_cputime(tsk, &cputime);
+	thread_group_cputimer(tsk, &cputime);
 	cleanup_timers(tsk->signal->cpu_timers,
 		       cputime.utime, cputime.stime, cputime.sum_exec_runtime);
 }
@@ -616,6 +681,33 @@ static void cpu_timer_fire(struct k_itimer *timer)
 }
 
 /*
+ * Sample a process (thread group) timer for the given group_leader task.
+ * Must be called with tasklist_lock held for reading.
+ */
+static int cpu_timer_sample_group(const clockid_t which_clock,
+				  struct task_struct *p,
+				  union cpu_time_count *cpu)
+{
+	struct task_cputime cputime;
+
+	thread_group_cputimer(p, &cputime);
+	switch (CPUCLOCK_WHICH(which_clock)) {
+	default:
+		return -EINVAL;
+	case CPUCLOCK_PROF:
+		cpu->cpu = cputime_add(cputime.utime, cputime.stime);
+		break;
+	case CPUCLOCK_VIRT:
+		cpu->cpu = cputime.utime;
+		break;
+	case CPUCLOCK_SCHED:
+		cpu->sched = cputime.sum_exec_runtime + task_delta_exec(p);
+		break;
+	}
+	return 0;
+}
+
+/*
  * Guts of sys_timer_settime for CPU timers.
  * This is called with the timer locked and interrupts disabled.
  * If we return TIMER_RETRY, it's necessary to release the timer's lock
@@ -676,7 +768,7 @@ int posix_cpu_timer_set(struct k_itimer *timer, int flags,
 	if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
 		cpu_clock_sample(timer->it_clock, p, &val);
 	} else {
-		cpu_clock_sample_group(timer->it_clock, p, &val);
+		cpu_timer_sample_group(timer->it_clock, p, &val);
 	}
 
 	if (old) {
@@ -824,7 +916,7 @@ void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
 			read_unlock(&tasklist_lock);
 			goto dead;
 		} else {
-			cpu_clock_sample_group(timer->it_clock, p, &now);
+			cpu_timer_sample_group(timer->it_clock, p, &now);
 			clear_dead = (unlikely(p->exit_state) &&
 				      thread_group_empty(p));
 		}
@@ -964,6 +1056,19 @@ static void check_thread_timers(struct task_struct *tsk,
 	}
 }
 
+static void stop_process_timers(struct task_struct *tsk)
+{
+	struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
+	unsigned long flags;
+
+	if (!cputimer->running)
+		return;
+
+	spin_lock_irqsave(&cputimer->lock, flags);
+	cputimer->running = 0;
+	spin_unlock_irqrestore(&cputimer->lock, flags);
+}
+
 /*
  * Check for any per-thread CPU timers that have fired and move them
  * off the tsk->*_timers list onto the firing list.  Per-thread timers
@@ -987,13 +1092,15 @@ static void check_process_timers(struct task_struct *tsk,
 	    sig->rlim[RLIMIT_CPU].rlim_cur == RLIM_INFINITY &&
 	    list_empty(&timers[CPUCLOCK_VIRT]) &&
 	    cputime_eq(sig->it_virt_expires, cputime_zero) &&
-	    list_empty(&timers[CPUCLOCK_SCHED]))
+	    list_empty(&timers[CPUCLOCK_SCHED])) {
+		stop_process_timers(tsk);
 		return;
+	}
 
 	/*
 	 * Collect the current process totals.
 	 */
-	thread_group_cputime(tsk, &cputime);
+	thread_group_cputimer(tsk, &cputime);
 	utime = cputime.utime;
 	ptime = cputime_add(utime, cputime.stime);
 	sum_sched_runtime = cputime.sum_exec_runtime;
@@ -1164,7 +1271,7 @@ void posix_cpu_timer_schedule(struct k_itimer *timer)
 			clear_dead_task(timer, now);
 			goto out_unlock;
 		}
-		cpu_clock_sample_group(timer->it_clock, p, &now);
+		cpu_timer_sample_group(timer->it_clock, p, &now);
 		bump_cpu_timer(timer, now);
 		/* Leave the tasklist_lock locked for the call below.  */
 	}
@@ -1259,7 +1366,7 @@ static inline int fastpath_timer_check(struct task_struct *tsk)
 	if (!task_cputime_zero(&sig->cputime_expires)) {
 		struct task_cputime group_sample;
 
-		thread_group_cputime(tsk, &group_sample);
+		thread_group_cputimer(tsk, &group_sample);
 		if (task_cputime_expired(&group_sample, &sig->cputime_expires))
 			return 1;
 	}
@@ -1341,7 +1448,7 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx,
 	struct list_head *head;
 
 	BUG_ON(clock_idx == CPUCLOCK_SCHED);
-	cpu_clock_sample_group(clock_idx, tsk, &now);
+	cpu_timer_sample_group(clock_idx, tsk, &now);
 
 	if (oldval) {
 		if (!cputime_eq(*oldval, cputime_zero)) {
diff --git a/kernel/power/Makefile b/kernel/power/Makefile
index d7a10167a25b..720ea4f781bd 100644
--- a/kernel/power/Makefile
+++ b/kernel/power/Makefile
@@ -3,7 +3,7 @@ ifeq ($(CONFIG_PM_DEBUG),y)
 EXTRA_CFLAGS	+=	-DDEBUG
 endif
 
-obj-y				:= main.o
+obj-$(CONFIG_PM)		+= main.o
 obj-$(CONFIG_PM_SLEEP)		+= console.o
 obj-$(CONFIG_FREEZER)		+= process.o
 obj-$(CONFIG_HIBERNATION)	+= swsusp.o disk.o snapshot.o swap.o user.o
diff --git a/kernel/power/console.c b/kernel/power/console.c
index b8628be2a465..a3961b205de7 100644
--- a/kernel/power/console.c
+++ b/kernel/power/console.c
@@ -78,6 +78,12 @@ void pm_restore_console(void)
 	}
 	set_console(orig_fgconsole);
 	release_console_sem();
+
+	if (vt_waitactive(orig_fgconsole)) {
+		pr_debug("Resume: Can't switch VCs.");
+		return;
+	}
+
 	kmsg_redirect = orig_kmsg;
 }
 #endif
diff --git a/kernel/power/disk.c b/kernel/power/disk.c
index 432ee575c9ee..4a4a206b1979 100644
--- a/kernel/power/disk.c
+++ b/kernel/power/disk.c
@@ -227,6 +227,12 @@ static int create_image(int platform_mode)
 			"aborting hibernation\n");
 		goto Enable_irqs;
 	}
+	sysdev_suspend(PMSG_FREEZE);
+	if (error) {
+		printk(KERN_ERR "PM: Some devices failed to power down, "
+			"aborting hibernation\n");
+		goto Power_up_devices;
+	}
 
 	if (hibernation_test(TEST_CORE))
 		goto Power_up;
@@ -242,9 +248,11 @@ static int create_image(int platform_mode)
 	if (!in_suspend)
 		platform_leave(platform_mode);
  Power_up:
+	sysdev_resume();
 	/* NOTE:  device_power_up() is just a resume() for devices
 	 * that suspended with irqs off ... no overall powerup.
 	 */
+ Power_up_devices:
 	device_power_up(in_suspend ?
 		(error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE);
  Enable_irqs:
@@ -335,6 +343,7 @@ static int resume_target_kernel(void)
 			"aborting resume\n");
 		goto Enable_irqs;
 	}
+	sysdev_suspend(PMSG_QUIESCE);
 	/* We'll ignore saved state, but this gets preempt count (etc) right */
 	save_processor_state();
 	error = restore_highmem();
@@ -357,6 +366,7 @@ static int resume_target_kernel(void)
 	swsusp_free();
 	restore_processor_state();
 	touch_softlockup_watchdog();
+	sysdev_resume();
 	device_power_up(PMSG_RECOVER);
  Enable_irqs:
 	local_irq_enable();
@@ -440,6 +450,7 @@ int hibernation_platform_enter(void)
 	local_irq_disable();
 	error = device_power_down(PMSG_HIBERNATE);
 	if (!error) {
+		sysdev_suspend(PMSG_HIBERNATE);
 		hibernation_ops->enter();
 		/* We should never get here */
 		while (1);
@@ -595,6 +606,12 @@ static int software_resume(void)
 	unsigned int flags;
 
 	/*
+	 * If the user said "noresume".. bail out early.
+	 */
+	if (noresume)
+		return 0;
+
+	/*
 	 * name_to_dev_t() below takes a sysfs buffer mutex when sysfs
 	 * is configured into the kernel. Since the regular hibernate
 	 * trigger path is via sysfs which takes a buffer mutex before
@@ -610,6 +627,11 @@ static int software_resume(void)
 			mutex_unlock(&pm_mutex);
 			return -ENOENT;
 		}
+		/*
+		 * Some device discovery might still be in progress; we need
+		 * to wait for this to finish.
+		 */
+		wait_for_device_probe();
 		swsusp_resume_device = name_to_dev_t(resume_file);
 		pr_debug("PM: Resume from partition %s\n", resume_file);
 	} else {
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 239988873971..c9632f841f64 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -57,16 +57,6 @@ int pm_notifier_call_chain(unsigned long val)
 #ifdef CONFIG_PM_DEBUG
 int pm_test_level = TEST_NONE;
 
-static int suspend_test(int level)
-{
-	if (pm_test_level == level) {
-		printk(KERN_INFO "suspend debug: Waiting for 5 seconds.\n");
-		mdelay(5000);
-		return 1;
-	}
-	return 0;
-}
-
 static const char * const pm_tests[__TEST_AFTER_LAST] = {
 	[TEST_NONE] = "none",
 	[TEST_CORE] = "core",
@@ -125,14 +115,24 @@ static ssize_t pm_test_store(struct kobject *kobj, struct kobj_attribute *attr,
 }
 
 power_attr(pm_test);
-#else /* !CONFIG_PM_DEBUG */
-static inline int suspend_test(int level) { return 0; }
-#endif /* !CONFIG_PM_DEBUG */
+#endif /* CONFIG_PM_DEBUG */
 
 #endif /* CONFIG_PM_SLEEP */
 
 #ifdef CONFIG_SUSPEND
 
+static int suspend_test(int level)
+{
+#ifdef CONFIG_PM_DEBUG
+	if (pm_test_level == level) {
+		printk(KERN_INFO "suspend debug: Waiting for 5 seconds.\n");
+		mdelay(5000);
+		return 1;
+	}
+#endif /* !CONFIG_PM_DEBUG */
+	return 0;
+}
+
 #ifdef CONFIG_PM_TEST_SUSPEND
 
 /*
@@ -298,8 +298,12 @@ static int suspend_enter(suspend_state_t state)
 		goto Done;
 	}
 
-	if (!suspend_test(TEST_CORE))
-		error = suspend_ops->enter(state);
+	error = sysdev_suspend(PMSG_SUSPEND);
+	if (!error) {
+		if (!suspend_test(TEST_CORE))
+			error = suspend_ops->enter(state);
+		sysdev_resume();
+	}
 
 	device_power_up(PMSG_RESUME);
  Done:
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index 6da14358537c..505f319e489c 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -60,6 +60,7 @@ static struct block_device *resume_bdev;
 static int submit(int rw, pgoff_t page_off, struct page *page,
 			struct bio **bio_chain)
 {
+	const int bio_rw = rw | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_UNPLUG);
 	struct bio *bio;
 
 	bio = bio_alloc(__GFP_WAIT | __GFP_HIGH, 1);
@@ -80,7 +81,7 @@ static int submit(int rw, pgoff_t page_off, struct page *page,
 	bio_get(bio);
 
 	if (bio_chain == NULL) {
-		submit_bio(rw | (1 << BIO_RW_SYNC), bio);
+		submit_bio(bio_rw, bio);
 		wait_on_page_locked(page);
 		if (rw == READ)
 			bio_set_pages_dirty(bio);
@@ -90,7 +91,7 @@ static int submit(int rw, pgoff_t page_off, struct page *page,
 			get_page(page);	/* These pages are freed later */
 		bio->bi_private = *bio_chain;
 		*bio_chain = bio;
-		submit_bio(rw | (1 << BIO_RW_SYNC), bio);
+		submit_bio(bio_rw, bio);
 	}
 	return 0;
 }
diff --git a/kernel/power/user.c b/kernel/power/user.c
index 005b93d839ba..6c85359364f2 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -95,15 +95,15 @@ static int snapshot_open(struct inode *inode, struct file *filp)
 		data->swap = swsusp_resume_device ?
 			swap_type_of(swsusp_resume_device, 0, NULL) : -1;
 		data->mode = O_RDONLY;
-		error = pm_notifier_call_chain(PM_RESTORE_PREPARE);
+		error = pm_notifier_call_chain(PM_HIBERNATION_PREPARE);
 		if (error)
-			pm_notifier_call_chain(PM_POST_RESTORE);
+			pm_notifier_call_chain(PM_POST_HIBERNATION);
 	} else {
 		data->swap = -1;
 		data->mode = O_WRONLY;
-		error = pm_notifier_call_chain(PM_HIBERNATION_PREPARE);
+		error = pm_notifier_call_chain(PM_RESTORE_PREPARE);
 		if (error)
-			pm_notifier_call_chain(PM_POST_HIBERNATION);
+			pm_notifier_call_chain(PM_POST_RESTORE);
 	}
 	if (error)
 		atomic_inc(&snapshot_device_available);
diff --git a/kernel/printk.c b/kernel/printk.c
index 69188f226a93..e3602d0755b0 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -73,7 +73,6 @@ EXPORT_SYMBOL(oops_in_progress);
  * driver system.
  */
 static DECLARE_MUTEX(console_sem);
-static DECLARE_MUTEX(secondary_console_sem);
 struct console *console_drivers;
 EXPORT_SYMBOL_GPL(console_drivers);
 
@@ -891,12 +890,14 @@ void suspend_console(void)
 	printk("Suspending console(s) (use no_console_suspend to debug)\n");
 	acquire_console_sem();
 	console_suspended = 1;
+	up(&console_sem);
 }
 
 void resume_console(void)
 {
 	if (!console_suspend_enabled)
 		return;
+	down(&console_sem);
 	console_suspended = 0;
 	release_console_sem();
 }
@@ -912,11 +913,9 @@ void resume_console(void)
 void acquire_console_sem(void)
 {
 	BUG_ON(in_interrupt());
-	if (console_suspended) {
-		down(&secondary_console_sem);
-		return;
-	}
 	down(&console_sem);
+	if (console_suspended)
+		return;
 	console_locked = 1;
 	console_may_schedule = 1;
 }
@@ -926,6 +925,10 @@ int try_acquire_console_sem(void)
 {
 	if (down_trylock(&console_sem))
 		return -1;
+	if (console_suspended) {
+		up(&console_sem);
+		return -1;
+	}
 	console_locked = 1;
 	console_may_schedule = 0;
 	return 0;
@@ -979,7 +982,7 @@ void release_console_sem(void)
 	unsigned wake_klogd = 0;
 
 	if (console_suspended) {
-		up(&secondary_console_sem);
+		up(&console_sem);
 		return;
 	}
 
diff --git a/kernel/profile.c b/kernel/profile.c
index 784933acf5b8..7724e0409bae 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -114,12 +114,15 @@ int __ref profile_init(void)
 	if (!slab_is_available()) {
 		prof_buffer = alloc_bootmem(buffer_bytes);
 		alloc_bootmem_cpumask_var(&prof_cpu_mask);
+		cpumask_copy(prof_cpu_mask, cpu_possible_mask);
 		return 0;
 	}
 
 	if (!alloc_cpumask_var(&prof_cpu_mask, GFP_KERNEL))
 		return -ENOMEM;
 
+	cpumask_copy(prof_cpu_mask, cpu_possible_mask);
+
 	prof_buffer = kzalloc(buffer_bytes, GFP_KERNEL);
 	if (prof_buffer)
 		return 0;
diff --git a/kernel/rcuclassic.c b/kernel/rcuclassic.c
index bd5a9003497c..654c640a6b9c 100644
--- a/kernel/rcuclassic.c
+++ b/kernel/rcuclassic.c
@@ -679,8 +679,8 @@ int rcu_needs_cpu(int cpu)
 void rcu_check_callbacks(int cpu, int user)
 {
 	if (user ||
-	    (idle_cpu(cpu) && !in_softirq() &&
-				hardirq_count() <= (1 << HARDIRQ_SHIFT))) {
+	    (idle_cpu(cpu) && rcu_scheduler_active &&
+	     !in_softirq() && hardirq_count() <= (1 << HARDIRQ_SHIFT))) {
 
 		/*
 		 * Get here if this CPU took its interrupt from user
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index d92a76a881aa..cae8a059cf47 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -44,6 +44,7 @@
 #include <linux/cpu.h>
 #include <linux/mutex.h>
 #include <linux/module.h>
+#include <linux/kernel_stat.h>
 
 enum rcu_barrier {
 	RCU_BARRIER_STD,
@@ -55,6 +56,7 @@ static DEFINE_PER_CPU(struct rcu_head, rcu_barrier_head) = {NULL};
 static atomic_t rcu_barrier_cpu_count;
 static DEFINE_MUTEX(rcu_barrier_mutex);
 static struct completion rcu_barrier_completion;
+int rcu_scheduler_active __read_mostly;
 
 /*
  * Awaken the corresponding synchronize_rcu() instance now that a
@@ -80,6 +82,10 @@ void wakeme_after_rcu(struct rcu_head  *head)
 void synchronize_rcu(void)
 {
 	struct rcu_synchronize rcu;
+
+	if (rcu_blocking_is_gp())
+		return;
+
 	init_completion(&rcu.completion);
 	/* Will wake me after RCU finished. */
 	call_rcu(&rcu.head, wakeme_after_rcu);
@@ -175,3 +181,9 @@ void __init rcu_init(void)
 	__rcu_init();
 }
 
+void rcu_scheduler_starting(void)
+{
+	WARN_ON(num_online_cpus() != 1);
+	WARN_ON(nr_context_switches() > 0);
+	rcu_scheduler_active = 1;
+}
diff --git a/kernel/rcupreempt.c b/kernel/rcupreempt.c
index 33cfc50781f9..5d59e850fb71 100644
--- a/kernel/rcupreempt.c
+++ b/kernel/rcupreempt.c
@@ -1181,6 +1181,9 @@ void __synchronize_sched(void)
 {
 	struct rcu_synchronize rcu;
 
+	if (num_online_cpus() == 1)
+		return;  /* blocking is gp if only one CPU! */
+
 	init_completion(&rcu.completion);
 	/* Will wake me after RCU finished. */
 	call_rcu_sched(&rcu.head, wakeme_after_rcu);
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index b2fd602a6f6f..97ce31579ec0 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -948,8 +948,8 @@ static void rcu_do_batch(struct rcu_data *rdp)
 void rcu_check_callbacks(int cpu, int user)
 {
 	if (user ||
-	    (idle_cpu(cpu) && !in_softirq() &&
-				hardirq_count() <= (1 << HARDIRQ_SHIFT))) {
+	    (idle_cpu(cpu) && rcu_scheduler_active &&
+	     !in_softirq() && hardirq_count() <= (1 << HARDIRQ_SHIFT))) {
 
 		/*
 		 * Get here if this CPU took its interrupt from user
diff --git a/kernel/sched.c b/kernel/sched.c
index 242d0d47a70d..8e2558c2ba67 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -223,7 +223,7 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
 {
 	ktime_t now;
 
-	if (rt_bandwidth_enabled() && rt_b->rt_runtime == RUNTIME_INF)
+	if (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF)
 		return;
 
 	if (hrtimer_active(&rt_b->rt_period_timer))
@@ -2266,16 +2266,6 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync)
 	if (!sched_feat(SYNC_WAKEUPS))
 		sync = 0;
 
-	if (!sync) {
-		if (current->se.avg_overlap < sysctl_sched_migration_cost &&
-			  p->se.avg_overlap < sysctl_sched_migration_cost)
-			sync = 1;
-	} else {
-		if (current->se.avg_overlap >= sysctl_sched_migration_cost ||
-			  p->se.avg_overlap >= sysctl_sched_migration_cost)
-			sync = 0;
-	}
-
 #ifdef CONFIG_SMP
 	if (sched_feat(LB_WAKEUP_UPDATE)) {
 		struct sched_domain *sd;
@@ -3890,19 +3880,24 @@ int select_nohz_load_balancer(int stop_tick)
 	int cpu = smp_processor_id();
 
 	if (stop_tick) {
-		cpumask_set_cpu(cpu, nohz.cpu_mask);
 		cpu_rq(cpu)->in_nohz_recently = 1;
 
-		/*
-		 * If we are going offline and still the leader, give up!
-		 */
-		if (!cpu_active(cpu) &&
-		    atomic_read(&nohz.load_balancer) == cpu) {
+		if (!cpu_active(cpu)) {
+			if (atomic_read(&nohz.load_balancer) != cpu)
+				return 0;
+
+			/*
+			 * If we are going offline and still the leader,
+			 * give up!
+			 */
 			if (atomic_cmpxchg(&nohz.load_balancer, cpu, -1) != cpu)
 				BUG();
+
 			return 0;
 		}
 
+		cpumask_set_cpu(cpu, nohz.cpu_mask);
+
 		/* time for ilb owner also to sleep */
 		if (cpumask_weight(nohz.cpu_mask) == num_online_cpus()) {
 			if (atomic_read(&nohz.load_balancer) == cpu)
@@ -4697,8 +4692,8 @@ EXPORT_SYMBOL(default_wake_function);
  * started to run but is not in state TASK_RUNNING. try_to_wake_up() returns
  * zero in this (rare) case, and we handle it by continuing to scan the queue.
  */
-static void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
-			     int nr_exclusive, int sync, void *key)
+void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
+			int nr_exclusive, int sync, void *key)
 {
 	wait_queue_t *curr, *next;
 
@@ -6949,20 +6944,26 @@ static void free_rootdomain(struct root_domain *rd)
 
 static void rq_attach_root(struct rq *rq, struct root_domain *rd)
 {
+	struct root_domain *old_rd = NULL;
 	unsigned long flags;
 
 	spin_lock_irqsave(&rq->lock, flags);
 
 	if (rq->rd) {
-		struct root_domain *old_rd = rq->rd;
+		old_rd = rq->rd;
 
 		if (cpumask_test_cpu(rq->cpu, old_rd->online))
 			set_rq_offline(rq);
 
 		cpumask_clear_cpu(rq->cpu, old_rd->span);
 
-		if (atomic_dec_and_test(&old_rd->refcount))
-			free_rootdomain(old_rd);
+		/*
+		 * If we dont want to free the old_rt yet then
+		 * set old_rd to NULL to skip the freeing later
+		 * in this function:
+		 */
+		if (!atomic_dec_and_test(&old_rd->refcount))
+			old_rd = NULL;
 	}
 
 	atomic_inc(&rd->refcount);
@@ -6973,6 +6974,9 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd)
 		set_rq_online(rq);
 
 	spin_unlock_irqrestore(&rq->lock, flags);
+
+	if (old_rd)
+		free_rootdomain(old_rd);
 }
 
 static int __init_refok init_rootdomain(struct root_domain *rd, bool bootmem)
@@ -9220,6 +9224,16 @@ static int sched_rt_global_constraints(void)
 
 	return ret;
 }
+
+int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk)
+{
+	/* Don't accept realtime tasks when there is no way for them to run */
+	if (rt_task(tsk) && tg->rt_bandwidth.rt_runtime == 0)
+		return 0;
+
+	return 1;
+}
+
 #else /* !CONFIG_RT_GROUP_SCHED */
 static int sched_rt_global_constraints(void)
 {
@@ -9313,8 +9327,7 @@ cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
 		      struct task_struct *tsk)
 {
 #ifdef CONFIG_RT_GROUP_SCHED
-	/* Don't accept realtime tasks when there is no way for them to run */
-	if (rt_task(tsk) && cgroup_tg(cgrp)->rt_bandwidth.rt_runtime == 0)
+	if (!sched_rt_can_attach(cgroup_tg(cgrp), tsk))
 		return -EINVAL;
 #else
 	/* We don't support RT-tasks being in separate groups */
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index a7e50ba185ac..0566f2a03c42 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -1191,15 +1191,20 @@ wake_affine(struct sched_domain *this_sd, struct rq *this_rq,
 	    int idx, unsigned long load, unsigned long this_load,
 	    unsigned int imbalance)
 {
+	struct task_struct *curr = this_rq->curr;
+	struct task_group *tg;
 	unsigned long tl = this_load;
 	unsigned long tl_per_task;
-	struct task_group *tg;
 	unsigned long weight;
 	int balanced;
 
 	if (!(this_sd->flags & SD_WAKE_AFFINE) || !sched_feat(AFFINE_WAKEUPS))
 		return 0;
 
+	if (sync && (curr->se.avg_overlap > sysctl_sched_migration_cost ||
+			p->se.avg_overlap > sysctl_sched_migration_cost))
+		sync = 0;
+
 	/*
 	 * If sync wakeup then subtract the (maximum possible)
 	 * effect of the currently running task from the load
@@ -1426,7 +1431,9 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int sync)
 	if (!sched_feat(WAKEUP_PREEMPT))
 		return;
 
-	if (sched_feat(WAKEUP_OVERLAP) && sync) {
+	if (sched_feat(WAKEUP_OVERLAP) && (sync ||
+			(se->avg_overlap < sysctl_sched_migration_cost &&
+			 pse->avg_overlap < sysctl_sched_migration_cost))) {
 		resched_task(curr);
 		return;
 	}
diff --git a/kernel/sched_stats.h b/kernel/sched_stats.h
index 8ab0cef8ecab..a8f93dd374e1 100644
--- a/kernel/sched_stats.h
+++ b/kernel/sched_stats.h
@@ -296,19 +296,21 @@ sched_info_switch(struct task_struct *prev, struct task_struct *next)
 static inline void account_group_user_time(struct task_struct *tsk,
 					   cputime_t cputime)
 {
-	struct task_cputime *times;
-	struct signal_struct *sig;
+	struct thread_group_cputimer *cputimer;
 
 	/* tsk == current, ensure it is safe to use ->signal */
 	if (unlikely(tsk->exit_state))
 		return;
 
-	sig = tsk->signal;
-	times = &sig->cputime.totals;
+	cputimer = &tsk->signal->cputimer;
 
-	spin_lock(&times->lock);
-	times->utime = cputime_add(times->utime, cputime);
-	spin_unlock(&times->lock);
+	if (!cputimer->running)
+		return;
+
+	spin_lock(&cputimer->lock);
+	cputimer->cputime.utime =
+		cputime_add(cputimer->cputime.utime, cputime);
+	spin_unlock(&cputimer->lock);
 }
 
 /**
@@ -324,19 +326,21 @@ static inline void account_group_user_time(struct task_struct *tsk,
 static inline void account_group_system_time(struct task_struct *tsk,
 					     cputime_t cputime)
 {
-	struct task_cputime *times;
-	struct signal_struct *sig;
+	struct thread_group_cputimer *cputimer;
 
 	/* tsk == current, ensure it is safe to use ->signal */
 	if (unlikely(tsk->exit_state))
 		return;
 
-	sig = tsk->signal;
-	times = &sig->cputime.totals;
+	cputimer = &tsk->signal->cputimer;
+
+	if (!cputimer->running)
+		return;
 
-	spin_lock(&times->lock);
-	times->stime = cputime_add(times->stime, cputime);
-	spin_unlock(&times->lock);
+	spin_lock(&cputimer->lock);
+	cputimer->cputime.stime =
+		cputime_add(cputimer->cputime.stime, cputime);
+	spin_unlock(&cputimer->lock);
 }
 
 /**
@@ -352,7 +356,7 @@ static inline void account_group_system_time(struct task_struct *tsk,
 static inline void account_group_exec_runtime(struct task_struct *tsk,
 					      unsigned long long ns)
 {
-	struct task_cputime *times;
+	struct thread_group_cputimer *cputimer;
 	struct signal_struct *sig;
 
 	sig = tsk->signal;
@@ -361,9 +365,12 @@ static inline void account_group_exec_runtime(struct task_struct *tsk,
 	if (unlikely(!sig))
 		return;
 
-	times = &sig->cputime.totals;
+	cputimer = &sig->cputimer;
+
+	if (!cputimer->running)
+		return;
 
-	spin_lock(&times->lock);
-	times->sum_exec_runtime += ns;
-	spin_unlock(&times->lock);
+	spin_lock(&cputimer->lock);
+	cputimer->cputime.sum_exec_runtime += ns;
+	spin_unlock(&cputimer->lock);
 }
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index ad64fcb731f2..57d4b13b631d 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -8,6 +8,7 @@
 
 #include <linux/seccomp.h>
 #include <linux/sched.h>
+#include <linux/compat.h>
 
 /* #define SECCOMP_DEBUG 1 */
 #define NR_SECCOMP_MODES 1
@@ -22,7 +23,7 @@ static int mode1_syscalls[] = {
 	0, /* null terminated */
 };
 
-#ifdef TIF_32BIT
+#ifdef CONFIG_COMPAT
 static int mode1_syscalls_32[] = {
 	__NR_seccomp_read_32, __NR_seccomp_write_32, __NR_seccomp_exit_32, __NR_seccomp_sigreturn_32,
 	0, /* null terminated */
@@ -37,8 +38,8 @@ void __secure_computing(int this_syscall)
 	switch (mode) {
 	case 1:
 		syscall = mode1_syscalls;
-#ifdef TIF_32BIT
-		if (test_thread_flag(TIF_32BIT))
+#ifdef CONFIG_COMPAT
+		if (is_compat_task())
 			syscall = mode1_syscalls_32;
 #endif
 		do {
diff --git a/kernel/signal.c b/kernel/signal.c
index b6b36768b758..2a74fe87c0dd 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1367,7 +1367,6 @@ int do_notify_parent(struct task_struct *tsk, int sig)
 	struct siginfo info;
 	unsigned long flags;
 	struct sighand_struct *psig;
-	struct task_cputime cputime;
 	int ret = sig;
 
 	BUG_ON(sig == -1);
@@ -1397,9 +1396,10 @@ int do_notify_parent(struct task_struct *tsk, int sig)
 	info.si_uid = __task_cred(tsk)->uid;
 	rcu_read_unlock();
 
-	thread_group_cputime(tsk, &cputime);
-	info.si_utime = cputime_to_jiffies(cputime.utime);
-	info.si_stime = cputime_to_jiffies(cputime.stime);
+	info.si_utime = cputime_to_clock_t(cputime_add(tsk->utime,
+				tsk->signal->utime));
+	info.si_stime = cputime_to_clock_t(cputime_add(tsk->stime,
+				tsk->signal->stime));
 
 	info.si_status = tsk->exit_code & 0x7f;
 	if (tsk->exit_code & 0x80)
diff --git a/kernel/softirq.c b/kernel/softirq.c
index bdbe9de9cd8d..9041ea7948fe 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -626,6 +626,7 @@ static int ksoftirqd(void * __bind_cpu)
 			preempt_enable_no_resched();
 			cond_resched();
 			preempt_disable();
+			rcu_qsctr_inc((long)__bind_cpu);
 		}
 		preempt_enable();
 		set_current_state(TASK_INTERRUPTIBLE);
diff --git a/kernel/sys.c b/kernel/sys.c
index e7dc0e10a485..37f458e6882a 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -559,7 +559,7 @@ error:
 	abort_creds(new);
 	return retval;
 }
-  
+
 /*
  * change the user struct in a credentials set to match the new UID
  */
@@ -571,6 +571,11 @@ static int set_user(struct cred *new)
 	if (!new_user)
 		return -EAGAIN;
 
+	if (!task_can_switch_user(new_user, current)) {
+		free_uid(new_user);
+		return -EINVAL;
+	}
+
 	if (atomic_read(&new_user->processes) >=
 				current->signal->rlim[RLIMIT_NPROC].rlim_cur &&
 			new_user != INIT_USER) {
@@ -631,10 +636,11 @@ SYSCALL_DEFINE2(setreuid, uid_t, ruid, uid_t, euid)
 			goto error;
 	}
 
-	retval = -EAGAIN;
-	if (new->uid != old->uid && set_user(new) < 0)
-		goto error;
-
+	if (new->uid != old->uid) {
+		retval = set_user(new);
+		if (retval < 0)
+			goto error;
+	}
 	if (ruid != (uid_t) -1 ||
 	    (euid != (uid_t) -1 && euid != old->uid))
 		new->suid = new->euid;
@@ -680,9 +686,10 @@ SYSCALL_DEFINE1(setuid, uid_t, uid)
 	retval = -EPERM;
 	if (capable(CAP_SETUID)) {
 		new->suid = new->uid = uid;
-		if (uid != old->uid && set_user(new) < 0) {
-			retval = -EAGAIN;
-			goto error;
+		if (uid != old->uid) {
+			retval = set_user(new);
+			if (retval < 0)
+				goto error;
 		}
 	} else if (uid != old->uid && uid != new->suid) {
 		goto error;
@@ -734,11 +741,13 @@ SYSCALL_DEFINE3(setresuid, uid_t, ruid, uid_t, euid, uid_t, suid)
 			goto error;
 	}
 
-	retval = -EAGAIN;
 	if (ruid != (uid_t) -1) {
 		new->uid = ruid;
-		if (ruid != old->uid && set_user(new) < 0)
-			goto error;
+		if (ruid != old->uid) {
+			retval = set_user(new);
+			if (retval < 0)
+				goto error;
+		}
 	}
 	if (euid != (uid_t) -1)
 		new->euid = euid;
@@ -1525,22 +1534,14 @@ SYSCALL_DEFINE2(setrlimit, unsigned int, resource, struct rlimit __user *, rlim)
 		return -EINVAL;
 	if (copy_from_user(&new_rlim, rlim, sizeof(*rlim)))
 		return -EFAULT;
+	if (new_rlim.rlim_cur > new_rlim.rlim_max)
+		return -EINVAL;
 	old_rlim = current->signal->rlim + resource;
 	if ((new_rlim.rlim_max > old_rlim->rlim_max) &&
 	    !capable(CAP_SYS_RESOURCE))
 		return -EPERM;
-
-	if (resource == RLIMIT_NOFILE) {
-		if (new_rlim.rlim_max == RLIM_INFINITY)
-			new_rlim.rlim_max = sysctl_nr_open;
-		if (new_rlim.rlim_cur == RLIM_INFINITY)
-			new_rlim.rlim_cur = sysctl_nr_open;
-		if (new_rlim.rlim_max > sysctl_nr_open)
-			return -EPERM;
-	}
-
-	if (new_rlim.rlim_cur > new_rlim.rlim_max)
-		return -EINVAL;
+	if (resource == RLIMIT_NOFILE && new_rlim.rlim_max > sysctl_nr_open)
+		return -EPERM;
 
 	retval = security_task_setrlimit(resource, &new_rlim);
 	if (retval)
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 790f9d785663..c5ef44ff850f 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -101,6 +101,7 @@ static int two = 2;
 
 static int zero;
 static int one = 1;
+static unsigned long one_ul = 1;
 static int one_hundred = 100;
 
 /* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */
@@ -974,7 +975,7 @@ static struct ctl_table vm_table[] = {
 		.mode		= 0644,
 		.proc_handler	= &dirty_background_bytes_handler,
 		.strategy	= &sysctl_intvec,
-		.extra1		= &one,
+		.extra1		= &one_ul,
 	},
 	{
 		.ctl_name	= VM_DIRTY_RATIO,
@@ -995,7 +996,7 @@ static struct ctl_table vm_table[] = {
 		.mode		= 0644,
 		.proc_handler	= &dirty_bytes_handler,
 		.strategy	= &sysctl_intvec,
-		.extra1		= &one,
+		.extra1		= &one_ul,
 	},
 	{
 		.procname	= "dirty_writeback_centisecs",
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index e2a4ff6fc3a6..34e707e5ab87 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -52,6 +52,7 @@ config FUNCTION_TRACER
 	depends on HAVE_FUNCTION_TRACER
 	depends on DEBUG_KERNEL
 	select FRAME_POINTER
+	select KALLSYMS
 	select TRACING
 	select CONTEXT_SWITCH_TRACER
 	help
@@ -238,6 +239,7 @@ config STACK_TRACER
 	depends on DEBUG_KERNEL
 	select FUNCTION_TRACER
 	select STACKTRACE
+	select KALLSYMS
 	help
 	  This special tracer records the maximum stack footprint of the
 	  kernel and displays it in debugfs/tracing/stack_trace.
@@ -302,4 +304,27 @@ config FTRACE_STARTUP_TEST
 	  functioning properly. It will do tests on all the configured
 	  tracers of ftrace.
 
+config MMIOTRACE
+	bool "Memory mapped IO tracing"
+	depends on HAVE_MMIOTRACE_SUPPORT && DEBUG_KERNEL && PCI
+	select TRACING
+	help
+	  Mmiotrace traces Memory Mapped I/O access and is meant for
+	  debugging and reverse engineering. It is called from the ioremap
+	  implementation and works via page faults. Tracing is disabled by
+	  default and can be enabled at run-time.
+
+	  See Documentation/tracers/mmiotrace.txt.
+	  If you are not helping to develop drivers, say N.
+
+config MMIOTRACE_TEST
+	tristate "Test module for mmiotrace"
+	depends on MMIOTRACE && m
+	help
+	  This is a dumb module for testing mmiotrace. It is very dangerous
+	  as it will write garbage to IO memory starting at a given address.
+	  However, it should be safe to use on e.g. unused portion of VRAM.
+
+	  Say N, unless you absolutely know what you are doing.
+
 endmenu
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 7dcf6e9f2b04..fdf913dfc7e8 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1737,9 +1737,12 @@ static void clear_ftrace_pid(struct pid *pid)
 {
 	struct task_struct *p;
 
+	rcu_read_lock();
 	do_each_pid_task(pid, PIDTYPE_PID, p) {
 		clear_tsk_trace_trace(p);
 	} while_each_pid_task(pid, PIDTYPE_PID, p);
+	rcu_read_unlock();
+
 	put_pid(pid);
 }
 
@@ -1747,9 +1750,11 @@ static void set_ftrace_pid(struct pid *pid)
 {
 	struct task_struct *p;
 
+	rcu_read_lock();
 	do_each_pid_task(pid, PIDTYPE_PID, p) {
 		set_tsk_trace_trace(p);
 	} while_each_pid_task(pid, PIDTYPE_PID, p);
+	rcu_read_unlock();
 }
 
 static void clear_ftrace_pid_task(struct pid **pid)
@@ -2028,7 +2033,7 @@ free:
 static int start_graph_tracing(void)
 {
 	struct ftrace_ret_stack **ret_stack_list;
-	int ret;
+	int ret, cpu;
 
 	ret_stack_list = kmalloc(FTRACE_RETSTACK_ALLOC_SIZE *
 				sizeof(struct ftrace_ret_stack *),
@@ -2037,6 +2042,10 @@ static int start_graph_tracing(void)
 	if (!ret_stack_list)
 		return -ENOMEM;
 
+	/* The cpu_boot init_task->ret_stack will never be freed */
+	for_each_online_cpu(cpu)
+		ftrace_graph_init_task(idle_task(cpu));
+
 	do {
 		ret = alloc_retstack_tasklist(ret_stack_list);
 	} while (ret == -EAGAIN);
diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c
index fffcb069f1dc..80e503ef6136 100644
--- a/kernel/trace/trace_mmiotrace.c
+++ b/kernel/trace/trace_mmiotrace.c
@@ -9,6 +9,7 @@
 #include <linux/kernel.h>
 #include <linux/mmiotrace.h>
 #include <linux/pci.h>
+#include <asm/atomic.h>
 
 #include "trace.h"
 
@@ -19,6 +20,7 @@ struct header_iter {
 static struct trace_array *mmio_trace_array;
 static bool overrun_detected;
 static unsigned long prev_overruns;
+static atomic_t dropped_count;
 
 static void mmio_reset_data(struct trace_array *tr)
 {
@@ -121,11 +123,11 @@ static void mmio_close(struct trace_iterator *iter)
 
 static unsigned long count_overruns(struct trace_iterator *iter)
 {
-	unsigned long cnt = 0;
+	unsigned long cnt = atomic_xchg(&dropped_count, 0);
 	unsigned long over = ring_buffer_overruns(iter->tr->buffer);
 
 	if (over > prev_overruns)
-		cnt = over - prev_overruns;
+		cnt += over - prev_overruns;
 	prev_overruns = over;
 	return cnt;
 }
@@ -310,8 +312,10 @@ static void __trace_mmiotrace_rw(struct trace_array *tr,
 
 	event	= ring_buffer_lock_reserve(tr->buffer, sizeof(*entry),
 					   &irq_flags);
-	if (!event)
+	if (!event) {
+		atomic_inc(&dropped_count);
 		return;
+	}
 	entry	= ring_buffer_event_data(event);
 	tracing_generic_entry_update(&entry->ent, 0, preempt_count());
 	entry->ent.type			= TRACE_MMIO_RW;
@@ -338,8 +342,10 @@ static void __trace_mmiotrace_map(struct trace_array *tr,
 
 	event	= ring_buffer_lock_reserve(tr->buffer, sizeof(*entry),
 					   &irq_flags);
-	if (!event)
+	if (!event) {
+		atomic_inc(&dropped_count);
 		return;
+	}
 	entry	= ring_buffer_event_data(event);
 	tracing_generic_entry_update(&entry->ent, 0, preempt_count());
 	entry->ent.type			= TRACE_MMIO_MAP;
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 88c8eb70f54a..bc8e80a86bca 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -23,10 +23,20 @@ static int trace_test_buffer_cpu(struct trace_array *tr, int cpu)
 {
 	struct ring_buffer_event *event;
 	struct trace_entry *entry;
+	unsigned int loops = 0;
 
 	while ((event = ring_buffer_consume(tr->buffer, cpu, NULL))) {
 		entry = ring_buffer_event_data(event);
 
+		/*
+		 * The ring buffer is a size of trace_buf_size, if
+		 * we loop more than the size, there's something wrong
+		 * with the ring buffer.
+		 */
+		if (loops++ > trace_buf_size) {
+			printk(KERN_CONT ".. bad ring buffer ");
+			goto failed;
+		}
 		if (!trace_valid_entry(entry)) {
 			printk(KERN_CONT ".. invalid entry %d ",
 				entry->type);
@@ -57,11 +67,20 @@ static int trace_test_buffer(struct trace_array *tr, unsigned long *count)
 
 	cnt = ring_buffer_entries(tr->buffer);
 
+	/*
+	 * The trace_test_buffer_cpu runs a while loop to consume all data.
+	 * If the calling tracer is broken, and is constantly filling
+	 * the buffer, this will run forever, and hard lock the box.
+	 * We disable the ring buffer while we do this test to prevent
+	 * a hard lock up.
+	 */
+	tracing_off();
 	for_each_possible_cpu(cpu) {
 		ret = trace_test_buffer_cpu(tr, cpu);
 		if (ret)
 			break;
 	}
+	tracing_on();
 	__raw_spin_unlock(&ftrace_max_lock);
 	local_irq_restore(flags);
 
diff --git a/kernel/tsacct.c b/kernel/tsacct.c
index 43f891b05a4b..00d59d048edf 100644
--- a/kernel/tsacct.c
+++ b/kernel/tsacct.c
@@ -122,8 +122,10 @@ void acct_update_integrals(struct task_struct *tsk)
 	if (likely(tsk->mm)) {
 		cputime_t time, dtime;
 		struct timeval value;
+		unsigned long flags;
 		u64 delta;
 
+		local_irq_save(flags);
 		time = tsk->stime + tsk->utime;
 		dtime = cputime_sub(time, tsk->acct_timexpd);
 		jiffies_to_timeval(cputime_to_jiffies(dtime), &value);
@@ -131,10 +133,12 @@ void acct_update_integrals(struct task_struct *tsk)
 		delta = delta * USEC_PER_SEC + value.tv_usec;
 
 		if (delta == 0)
-			return;
+			goto out;
 		tsk->acct_timexpd = time;
 		tsk->acct_rss_mem1 += delta * get_mm_rss(tsk->mm);
 		tsk->acct_vm_mem1 += delta * tsk->mm->total_vm;
+	out:
+		local_irq_restore(flags);
 	}
 }
 
diff --git a/kernel/user.c b/kernel/user.c
index 477b6660f447..fbb300e6191f 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -72,6 +72,7 @@ static void uid_hash_insert(struct user_struct *up, struct hlist_head *hashent)
 static void uid_hash_remove(struct user_struct *up)
 {
 	hlist_del_init(&up->uidhash_node);
+	put_user_ns(up->user_ns);
 }
 
 static struct user_struct *uid_hash_find(uid_t uid, struct hlist_head *hashent)
@@ -285,14 +286,12 @@ int __init uids_sysfs_init(void)
 /* work function to remove sysfs directory for a user and free up
  * corresponding structures.
  */
-static void remove_user_sysfs_dir(struct work_struct *w)
+static void cleanup_user_struct(struct work_struct *w)
 {
 	struct user_struct *up = container_of(w, struct user_struct, work);
 	unsigned long flags;
 	int remove_user = 0;
 
-	if (up->user_ns != &init_user_ns)
-		return;
 	/* Make uid_hash_remove() + sysfs_remove_file() + kobject_del()
 	 * atomic.
 	 */
@@ -311,9 +310,11 @@ static void remove_user_sysfs_dir(struct work_struct *w)
 	if (!remove_user)
 		goto done;
 
-	kobject_uevent(&up->kobj, KOBJ_REMOVE);
-	kobject_del(&up->kobj);
-	kobject_put(&up->kobj);
+	if (up->user_ns == &init_user_ns) {
+		kobject_uevent(&up->kobj, KOBJ_REMOVE);
+		kobject_del(&up->kobj);
+		kobject_put(&up->kobj);
+	}
 
 	sched_destroy_user(up);
 	key_put(up->uid_keyring);
@@ -334,8 +335,7 @@ static void free_user(struct user_struct *up, unsigned long flags)
 	atomic_inc(&up->__count);
 	spin_unlock_irqrestore(&uidhash_lock, flags);
 
-	put_user_ns(up->user_ns);
-	INIT_WORK(&up->work, remove_user_sysfs_dir);
+	INIT_WORK(&up->work, cleanup_user_struct);
 	schedule_work(&up->work);
 }
 
@@ -357,12 +357,29 @@ static void free_user(struct user_struct *up, unsigned long flags)
 	sched_destroy_user(up);
 	key_put(up->uid_keyring);
 	key_put(up->session_keyring);
-	put_user_ns(up->user_ns);
 	kmem_cache_free(uid_cachep, up);
 }
 
 #endif
 
+#if defined(CONFIG_RT_GROUP_SCHED) && defined(CONFIG_USER_SCHED)
+/*
+ * We need to check if a setuid can take place. This function should be called
+ * before successfully completing the setuid.
+ */
+int task_can_switch_user(struct user_struct *up, struct task_struct *tsk)
+{
+
+	return sched_rt_can_attach(up->tg, tsk);
+
+}
+#else
+int task_can_switch_user(struct user_struct *up, struct task_struct *tsk)
+{
+	return 1;
+}
+#endif
+
 /*
  * Locate the user_struct for the passed UID.  If found, take a ref on it.  The
  * caller must undo that ref with free_uid().
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 79084311ee57..076c7c8215b0 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -60,12 +60,25 @@ int create_user_ns(struct cred *new)
 	return 0;
 }
 
-void free_user_ns(struct kref *kref)
+/*
+ * Deferred destructor for a user namespace.  This is required because
+ * free_user_ns() may be called with uidhash_lock held, but we need to call
+ * back to free_uid() which will want to take the lock again.
+ */
+static void free_user_ns_work(struct work_struct *work)
 {
-	struct user_namespace *ns;
-
-	ns = container_of(kref, struct user_namespace, kref);
+	struct user_namespace *ns =
+		container_of(work, struct user_namespace, destroyer);
 	free_uid(ns->creator);
 	kfree(ns);
 }
+
+void free_user_ns(struct kref *kref)
+{
+	struct user_namespace *ns =
+		container_of(kref, struct user_namespace, kref);
+
+	INIT_WORK(&ns->destroyer, free_user_ns_work);
+	schedule_work(&ns->destroyer);
+}
 EXPORT_SYMBOL(free_user_ns);
diff --git a/kernel/wait.c b/kernel/wait.c
index cd87131f2fc2..42a2dbc181c8 100644
--- a/kernel/wait.c
+++ b/kernel/wait.c
@@ -91,6 +91,15 @@ prepare_to_wait_exclusive(wait_queue_head_t *q, wait_queue_t *wait, int state)
 }
 EXPORT_SYMBOL(prepare_to_wait_exclusive);
 
+/*
+ * finish_wait - clean up after waiting in a queue
+ * @q: waitqueue waited on
+ * @wait: wait descriptor
+ *
+ * Sets current thread back to running state and removes
+ * the wait descriptor from the given waitqueue if still
+ * queued.
+ */
 void finish_wait(wait_queue_head_t *q, wait_queue_t *wait)
 {
 	unsigned long flags;
@@ -117,6 +126,39 @@ void finish_wait(wait_queue_head_t *q, wait_queue_t *wait)
 }
 EXPORT_SYMBOL(finish_wait);
 
+/*
+ * abort_exclusive_wait - abort exclusive waiting in a queue
+ * @q: waitqueue waited on
+ * @wait: wait descriptor
+ * @state: runstate of the waiter to be woken
+ * @key: key to identify a wait bit queue or %NULL
+ *
+ * Sets current thread back to running state and removes
+ * the wait descriptor from the given waitqueue if still
+ * queued.
+ *
+ * Wakes up the next waiter if the caller is concurrently
+ * woken up through the queue.
+ *
+ * This prevents waiter starvation where an exclusive waiter
+ * aborts and is woken up concurrently and noone wakes up
+ * the next waiter.
+ */
+void abort_exclusive_wait(wait_queue_head_t *q, wait_queue_t *wait,
+			unsigned int mode, void *key)
+{
+	unsigned long flags;
+
+	__set_current_state(TASK_RUNNING);
+	spin_lock_irqsave(&q->lock, flags);
+	if (!list_empty(&wait->task_list))
+		list_del_init(&wait->task_list);
+	else if (waitqueue_active(q))
+		__wake_up_common(q, mode, 1, 0, key);
+	spin_unlock_irqrestore(&q->lock, flags);
+}
+EXPORT_SYMBOL(abort_exclusive_wait);
+
 int autoremove_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key)
 {
 	int ret = default_wake_function(wait, mode, sync, key);
@@ -177,17 +219,20 @@ int __sched
 __wait_on_bit_lock(wait_queue_head_t *wq, struct wait_bit_queue *q,
 			int (*action)(void *), unsigned mode)
 {
-	int ret = 0;
-
 	do {
+		int ret;
+
 		prepare_to_wait_exclusive(wq, &q->wait, mode);
-		if (test_bit(q->key.bit_nr, q->key.flags)) {
-			if ((ret = (*action)(q->key.flags)))
-				break;
-		}
+		if (!test_bit(q->key.bit_nr, q->key.flags))
+			continue;
+		ret = action(q->key.flags);
+		if (!ret)
+			continue;
+		abort_exclusive_wait(wq, &q->wait, mode, &q->key);
+		return ret;
 	} while (test_and_set_bit(q->key.bit_nr, q->key.flags));
 	finish_wait(wq, &q->wait);
-	return ret;
+	return 0;
 }
 EXPORT_SYMBOL(__wait_on_bit_lock);