Merge commit 'v2.6.29-rc4' into core/percpu

Conflicts:
	arch/x86/mach-voyager/voyager_smp.c
	arch/x86/mm/fault.c

20 files changed, 365 insertions, 93 deletions

diff --git a/kernel/async.c b/kernel/async.c
index 608b32b4281..f565891f2c9 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/cpuset.c b/kernel/cpuset.c
index a85678865c5..f76db9dcaa0 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -61,6 +61,14 @@
 #include <linux/cgroup.h>
 
 /*
+ * Workqueue for cpuset related tasks.
+ *
+ * Using kevent workqueue may cause deadlock when memory_migrate
+ * is set. So we create a separate workqueue thread for cpuset.
+ */
+static struct workqueue_struct *cpuset_wq;
+
+/*
  * Tracks how many cpusets are currently defined in system.
  * When there is only one cpuset (the root cpuset) we can
  * short circuit some hooks.
@@ -831,7 +839,7 @@ static DECLARE_WORK(rebuild_sched_domains_work, do_rebuild_sched_domains);
  */
 static void async_rebuild_sched_domains(void)
 {
-	schedule_work(&rebuild_sched_domains_work);
+	queue_work(cpuset_wq, &rebuild_sched_domains_work);
 }
 
 /*
@@ -2111,6 +2119,9 @@ void __init cpuset_init_smp(void)
 
 	hotcpu_notifier(cpuset_track_online_cpus, 0);
 	hotplug_memory_notifier(cpuset_track_online_nodes, 10);
+
+	cpuset_wq = create_singlethread_workqueue("cpuset");
+	BUG_ON(!cpuset_wq);
 }
 
 /**
diff --git a/kernel/fork.c b/kernel/fork.c
index 99309df985b..c078438ba6f 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1010,6 +1010,7 @@ 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;
 
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index f33afb0407b..f394d2a42ca 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -501,6 +501,13 @@ static void hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base)
 			continue;
 		timer = rb_entry(base->first, struct hrtimer, node);
 		expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
+		/*
+		 * clock_was_set() has changed base->offset so the
+		 * result might be negative. Fix it up to prevent a
+		 * false positive in clockevents_program_event()
+		 */
+		if (expires.tv64 < 0)
+			expires.tv64 = 0;
 		if (expires.tv64 < cpu_base->expires_next.tv64)
 			cpu_base->expires_next = expires;
 	}
@@ -1158,6 +1165,29 @@ static void __run_hrtimer(struct hrtimer *timer)
 
 #ifdef CONFIG_HIGH_RES_TIMERS
 
+static int force_clock_reprogram;
+
+/*
+ * After 5 iteration's attempts, we consider that hrtimer_interrupt()
+ * is hanging, which could happen with something that slows the interrupt
+ * such as the tracing. Then we force the clock reprogramming for each future
+ * hrtimer interrupts to avoid infinite loops and use the min_delta_ns
+ * threshold that we will overwrite.
+ * The next tick event will be scheduled to 3 times we currently spend on
+ * hrtimer_interrupt(). This gives a good compromise, the cpus will spend
+ * 1/4 of their time to process the hrtimer interrupts. This is enough to
+ * let it running without serious starvation.
+ */
+
+static inline void
+hrtimer_interrupt_hanging(struct clock_event_device *dev,
+			ktime_t try_time)
+{
+	force_clock_reprogram = 1;
+	dev->min_delta_ns = (unsigned long)try_time.tv64 * 3;
+	printk(KERN_WARNING "hrtimer: interrupt too slow, "
+		"forcing clock min delta to %lu ns\n", dev->min_delta_ns);
+}
 /*
  * High resolution timer interrupt
  * Called with interrupts disabled
@@ -1167,6 +1197,7 @@ void hrtimer_interrupt(struct clock_event_device *dev)
 	struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
 	struct hrtimer_clock_base *base;
 	ktime_t expires_next, now;
+	int nr_retries = 0;
 	int i;
 
 	BUG_ON(!cpu_base->hres_active);
@@ -1174,6 +1205,10 @@ void hrtimer_interrupt(struct clock_event_device *dev)
 	dev->next_event.tv64 = KTIME_MAX;
 
  retry:
+	/* 5 retries is enough to notice a hang */
+	if (!(++nr_retries % 5))
+		hrtimer_interrupt_hanging(dev, ktime_sub(ktime_get(), now));
+
 	now = ktime_get();
 
 	expires_next.tv64 = KTIME_MAX;
@@ -1226,7 +1261,7 @@ void hrtimer_interrupt(struct clock_event_device *dev)
 
 	/* Reprogramming necessary ? */
 	if (expires_next.tv64 != KTIME_MAX) {
-		if (tick_program_event(expires_next, 0))
+		if (tick_program_event(expires_next, force_clock_reprogram))
 			goto retry;
 	}
 }
@@ -1580,6 +1615,10 @@ static int __cpuinit hrtimer_cpu_notify(struct notifier_block *self,
 		break;
 
 #ifdef CONFIG_HOTPLUG_CPU
+	case CPU_DYING:
+	case CPU_DYING_FROZEN:
+		clockevents_notify(CLOCK_EVT_NOTIFY_CPU_DYING, &scpu);
+		break;
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
 	{
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index c248eba98b4..122fef4b0bd 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -386,6 +386,7 @@ handle_level_irq(unsigned int irq, struct irq_desc *desc)
 out_unlock:
 	spin_unlock(&desc->lock);
 }
+EXPORT_SYMBOL_GPL(handle_level_irq);
 
 /**
  *	handle_fasteoi_irq - irq handler for transparent controllers
@@ -596,6 +597,7 @@ __set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
 	}
 	spin_unlock_irqrestore(&desc->lock, flags);
 }
+EXPORT_SYMBOL_GPL(__set_irq_handler);
 
 void
 set_irq_chip_and_handler(unsigned int irq, struct irq_chip *chip,
diff --git a/kernel/irq/numa_migrate.c b/kernel/irq/numa_migrate.c
index 666260e4c06..7f9b80434e3 100644
--- a/kernel/irq/numa_migrate.c
+++ b/kernel/irq/numa_migrate.c
@@ -78,7 +78,7 @@ 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);
@@ -97,10 +97,15 @@ static struct irq_desc *__real_move_irq_desc(struct irq_desc *old_desc,
 	}
 
 	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/module.c b/kernel/module.c
index e8b51d41dd7..ba22484a987 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -573,13 +573,13 @@ static char last_unloaded_module[MODULE_NAME_LEN+1];
 /* Init the unload section of the module. */
 static void module_unload_init(struct module *mod)
 {
-	unsigned int i;
+	int cpu;
 
 	INIT_LIST_HEAD(&mod->modules_which_use_me);
-	for (i = 0; i < NR_CPUS; i++)
-		local_set(&mod->ref[i].count, 0);
+	for_each_possible_cpu(cpu)
+		local_set(__module_ref_addr(mod, cpu), 0);
 	/* Hold reference count during initialization. */
-	local_set(&mod->ref[raw_smp_processor_id()].count, 1);
+	local_set(__module_ref_addr(mod, raw_smp_processor_id()), 1);
 	/* Backwards compatibility macros put refcount during init. */
 	mod->waiter = current;
 }
@@ -717,10 +717,11 @@ static int try_stop_module(struct module *mod, int flags, int *forced)
 
 unsigned int module_refcount(struct module *mod)
 {
-	unsigned int i, total = 0;
+	unsigned int total = 0;
+	int cpu;
 
-	for (i = 0; i < NR_CPUS; i++)
-		total += local_read(&mod->ref[i].count);
+	for_each_possible_cpu(cpu)
+		total += local_read(__module_ref_addr(mod, cpu));
 	return total;
 }
 EXPORT_SYMBOL(module_refcount);
@@ -894,7 +895,7 @@ void module_put(struct module *module)
 {
 	if (module) {
 		unsigned int cpu = get_cpu();
-		local_dec(&module->ref[cpu].count);
+		local_dec(__module_ref_addr(module, cpu));
 		/* Maybe they're waiting for us to drop reference? */
 		if (unlikely(!module_is_live(module)))
 			wake_up_process(module->waiter);
@@ -1464,7 +1465,10 @@ static void free_module(struct module *mod)
 	kfree(mod->args);
 	if (mod->percpu)
 		percpu_modfree(mod->percpu);
-
+#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP)
+	if (mod->refptr)
+		percpu_modfree(mod->refptr);
+#endif
 	/* Free lock-classes: */
 	lockdep_free_key_range(mod->module_core, mod->core_size);
 
@@ -2011,6 +2015,14 @@ static noinline struct module *load_module(void __user *umod,
 	if (err < 0)
 		goto free_mod;
 
+#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP)
+	mod->refptr = percpu_modalloc(sizeof(local_t), __alignof__(local_t),
+				      mod->name);
+	if (!mod->refptr) {
+		err = -ENOMEM;
+		goto free_mod;
+	}
+#endif
 	if (pcpuindex) {
 		/* We have a special allocation for this section. */
 		percpu = percpu_modalloc(sechdrs[pcpuindex].sh_size,
@@ -2018,7 +2030,7 @@ static noinline struct module *load_module(void __user *umod,
 					 mod->name);
 		if (!percpu) {
 			err = -ENOMEM;
-			goto free_mod;
+			goto free_percpu;
 		}
 		sechdrs[pcpuindex].sh_flags &= ~(unsigned long)SHF_ALLOC;
 		mod->percpu = percpu;
@@ -2282,6 +2294,9 @@ static noinline struct module *load_module(void __user *umod,
  free_percpu:
 	if (percpu)
 		percpu_modfree(percpu);
+#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP)
+	percpu_modfree(mod->refptr);
+#endif
  free_mod:
 	kfree(args);
  free_hdr:
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 23998887397..b4d219016b6 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
 
 /*
diff --git a/kernel/sched.c b/kernel/sched.c
index c71d7d501ed..fc17fd91ab5 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -2266,6 +2266,16 @@ 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;
@@ -4687,8 +4697,8 @@ 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;
 
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 5cc1c162044..a7e50ba185a 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -719,7 +719,7 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int wakeup)
 		__enqueue_entity(cfs_rq, se);
 }
 
-static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
+static void __clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	if (cfs_rq->last == se)
 		cfs_rq->last = NULL;
@@ -728,6 +728,12 @@ static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		cfs_rq->next = NULL;
 }
 
+static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+	for_each_sched_entity(se)
+		__clear_buddies(cfs_rq_of(se), se);
+}
+
 static void
 dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep)
 {
@@ -768,8 +774,14 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
 
 	ideal_runtime = sched_slice(cfs_rq, curr);
 	delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime;
-	if (delta_exec > ideal_runtime)
+	if (delta_exec > ideal_runtime) {
 		resched_task(rq_of(cfs_rq)->curr);
+		/*
+		 * The current task ran long enough, ensure it doesn't get
+		 * re-elected due to buddy favours.
+		 */
+		clear_buddies(cfs_rq, curr);
+	}
 }
 
 static void
@@ -1179,20 +1191,15 @@ 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
@@ -1419,9 +1426,7 @@ 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 ||
-			(se->avg_overlap < sysctl_sched_migration_cost &&
-			 pse->avg_overlap < sysctl_sched_migration_cost))) {
+	if (sched_feat(WAKEUP_OVERLAP) && sync) {
 		resched_task(curr);
 		return;
 	}
@@ -1452,6 +1457,11 @@ static struct task_struct *pick_next_task_fair(struct rq *rq)
 
 	do {
 		se = pick_next_entity(cfs_rq);
+		/*
+		 * If se was a buddy, clear it so that it will have to earn
+		 * the favour again.
+		 */
+		__clear_buddies(cfs_rq, se);
 		set_next_entity(cfs_rq, se);
 		cfs_rq = group_cfs_rq(se);
 	} while (cfs_rq);
diff --git a/kernel/signal.c b/kernel/signal.c
index e73759783dc..b6b36768b75 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -909,7 +909,9 @@ static void print_fatal_signal(struct pt_regs *regs, int signr)
 	}
 #endif
 	printk("\n");
+	preempt_disable();
 	show_regs(regs);
+	preempt_enable();
 }
 
 static int __init setup_print_fatal_signals(char *str)
diff --git a/kernel/smp.c b/kernel/smp.c
index 5cfa0e5e3e8..bbedbb7efe3 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -18,6 +18,7 @@ __cacheline_aligned_in_smp DEFINE_SPINLOCK(call_function_lock);
 enum {
 	CSD_FLAG_WAIT		= 0x01,
 	CSD_FLAG_ALLOC		= 0x02,
+	CSD_FLAG_LOCK		= 0x04,
 };
 
 struct call_function_data {
@@ -186,6 +187,9 @@ void generic_smp_call_function_single_interrupt(void)
 			if (data_flags & CSD_FLAG_WAIT) {
 				smp_wmb();
 				data->flags &= ~CSD_FLAG_WAIT;
+			} else if (data_flags & CSD_FLAG_LOCK) {
+				smp_wmb();
+				data->flags &= ~CSD_FLAG_LOCK;
 			} else if (data_flags & CSD_FLAG_ALLOC)
 				kfree(data);
 		}
@@ -196,6 +200,8 @@ void generic_smp_call_function_single_interrupt(void)
 	}
 }
 
+static DEFINE_PER_CPU(struct call_single_data, csd_data);
+
 /*
  * smp_call_function_single - Run a function on a specific CPU
  * @func: The function to run. This must be fast and non-blocking.
@@ -224,14 +230,38 @@ int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
 		func(info);
 		local_irq_restore(flags);
 	} else if ((unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) {
-		struct call_single_data *data = NULL;
+		struct call_single_data *data;
 
 		if (!wait) {
+			/*
+			 * We are calling a function on a single CPU
+			 * and we are not going to wait for it to finish.
+			 * We first try to allocate the data, but if we
+			 * fail, we fall back to use a per cpu data to pass
+			 * the information to that CPU. Since all callers
+			 * of this code will use the same data, we must
+			 * synchronize the callers to prevent a new caller
+			 * from corrupting the data before the callee
+			 * can access it.
+			 *
+			 * The CSD_FLAG_LOCK is used to let us know when
+			 * the IPI handler is done with the data.
+			 * The first caller will set it, and the callee
+			 * will clear it. The next caller must wait for
+			 * it to clear before we set it again. This
+			 * will make sure the callee is done with the
+			 * data before a new caller will use it.
+			 */
 			data = kmalloc(sizeof(*data), GFP_ATOMIC);
 			if (data)
 				data->flags = CSD_FLAG_ALLOC;
-		}
-		if (!data) {
+			else {
+				data = &per_cpu(csd_data, me);
+				while (data->flags & CSD_FLAG_LOCK)
+					cpu_relax();
+				data->flags = CSD_FLAG_LOCK;
+			}
+		} else {
 			data = &d;
 			data->flags = CSD_FLAG_WAIT;
 		}
diff --git a/kernel/sys.c b/kernel/sys.c
index e7dc0e10a48..f145c415bc1 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1525,22 +1525,14 @@ 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/time/tick-common.c b/kernel/time/tick-common.c
index 63e05d423a0..21a5ca84951 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -274,6 +274,21 @@ out_bc:
 }
 
 /*
+ * Transfer the do_timer job away from a dying cpu.
+ *
+ * Called with interrupts disabled.
+ */
+static void tick_handover_do_timer(int *cpup)
+{
+	if (*cpup == tick_do_timer_cpu) {
+		int cpu = cpumask_first(cpu_online_mask);
+
+		tick_do_timer_cpu = (cpu < nr_cpu_ids) ? cpu :
+			TICK_DO_TIMER_NONE;
+	}
+}
+
+/*
  * Shutdown an event device on a given cpu:
  *
  * This is called on a life CPU, when a CPU is dead. So we cannot
@@ -297,13 +312,6 @@ static void tick_shutdown(unsigned int *cpup)
 		clockevents_exchange_device(dev, NULL);
 		td->evtdev = NULL;
 	}
-	/* Transfer the do_timer job away from this cpu */
-	if (*cpup == tick_do_timer_cpu) {
-		int cpu = cpumask_first(cpu_online_mask);
-
-		tick_do_timer_cpu = (cpu < nr_cpu_ids) ? cpu :
-			TICK_DO_TIMER_NONE;
-	}
 	spin_unlock_irqrestore(&tick_device_lock, flags);
 }
 
@@ -357,6 +365,10 @@ static int tick_notify(struct notifier_block *nb, unsigned long reason,
 		tick_broadcast_oneshot_control(reason);
 		break;
 
+	case CLOCK_EVT_NOTIFY_CPU_DYING:
+		tick_handover_do_timer(dev);
+		break;
+
 	case CLOCK_EVT_NOTIFY_CPU_DEAD:
 		tick_shutdown_broadcast_oneshot(dev);
 		tick_shutdown_broadcast(dev);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 2f32969c09d..9a236ffe2aa 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -17,6 +17,7 @@
 #include <linux/clocksource.h>
 #include <linux/kallsyms.h>
 #include <linux/seq_file.h>
+#include <linux/suspend.h>
 #include <linux/debugfs.h>
 #include <linux/hardirq.h>
 #include <linux/kthread.h>
@@ -1736,9 +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);
 }
 
@@ -1746,9 +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)
@@ -1965,6 +1971,7 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 
 static atomic_t ftrace_graph_active;
+static struct notifier_block ftrace_suspend_notifier;
 
 int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace)
 {
@@ -2043,6 +2050,27 @@ static int start_graph_tracing(void)
 	return ret;
 }
 
+/*
+ * Hibernation protection.
+ * The state of the current task is too much unstable during
+ * suspend/restore to disk. We want to protect against that.
+ */
+static int
+ftrace_suspend_notifier_call(struct notifier_block *bl, unsigned long state,
+							void *unused)
+{
+	switch (state) {
+	case PM_HIBERNATION_PREPARE:
+		pause_graph_tracing();
+		break;
+
+	case PM_POST_HIBERNATION:
+		unpause_graph_tracing();
+		break;
+	}
+	return NOTIFY_DONE;
+}
+
 int register_ftrace_graph(trace_func_graph_ret_t retfunc,
 			trace_func_graph_ent_t entryfunc)
 {
@@ -2050,6 +2078,9 @@ int register_ftrace_graph(trace_func_graph_ret_t retfunc,
 
 	mutex_lock(&ftrace_sysctl_lock);
 
+	ftrace_suspend_notifier.notifier_call = ftrace_suspend_notifier_call;
+	register_pm_notifier(&ftrace_suspend_notifier);
+
 	atomic_inc(&ftrace_graph_active);
 	ret = start_graph_tracing();
 	if (ret) {
@@ -2075,6 +2106,7 @@ void unregister_ftrace_graph(void)
 	ftrace_graph_return = (trace_func_graph_ret_t)ftrace_stub;
 	ftrace_graph_entry = ftrace_graph_entry_stub;
 	ftrace_shutdown(FTRACE_STOP_FUNC_RET);
+	unregister_pm_notifier(&ftrace_suspend_notifier);
 
 	mutex_unlock(&ftrace_sysctl_lock);
 }
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 8b0daf0662e..bd38c5cfd8a 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -246,7 +246,7 @@ static inline int test_time_stamp(u64 delta)
 	return 0;
 }
 
-#define BUF_PAGE_SIZE (PAGE_SIZE - sizeof(struct buffer_data_page))
+#define BUF_PAGE_SIZE (PAGE_SIZE - offsetof(struct buffer_data_page, data))
 
 /*
  * head_page == tail_page && head == tail then buffer is empty.
@@ -1025,12 +1025,8 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 		}
 
 		if (next_page == head_page) {
-			if (!(buffer->flags & RB_FL_OVERWRITE)) {
-				/* reset write */
-				if (tail <= BUF_PAGE_SIZE)
-					local_set(&tail_page->write, tail);
+			if (!(buffer->flags & RB_FL_OVERWRITE))
 				goto out_unlock;
-			}
 
 			/* tail_page has not moved yet? */
 			if (tail_page == cpu_buffer->tail_page) {
@@ -1105,6 +1101,10 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 	return event;
 
  out_unlock:
+	/* reset write */
+	if (tail <= BUF_PAGE_SIZE)
+		local_set(&tail_page->write, tail);
+
 	__raw_spin_unlock(&cpu_buffer->lock);
 	local_irq_restore(flags);
 	return NULL;
@@ -2174,6 +2174,9 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
 
 	cpu_buffer->overrun = 0;
 	cpu_buffer->entries = 0;
+
+	cpu_buffer->write_stamp = 0;
+	cpu_buffer->read_stamp = 0;
 }
 
 /**
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index c580233add9..17bb88d86ac 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -40,7 +40,7 @@
 
 #define TRACE_BUFFER_FLAGS	(RB_FL_OVERWRITE)
 
-unsigned long __read_mostly	tracing_max_latency = (cycle_t)ULONG_MAX;
+unsigned long __read_mostly	tracing_max_latency;
 unsigned long __read_mostly	tracing_thresh;
 
 /*
@@ -3736,7 +3736,7 @@ static struct notifier_block trace_die_notifier = {
  * it if we decide to change what log level the ftrace dump
  * should be at.
  */
-#define KERN_TRACE		KERN_INFO
+#define KERN_TRACE		KERN_EMERG
 
 static void
 trace_printk_seq(struct trace_seq *s)
@@ -3770,6 +3770,7 @@ void ftrace_dump(void)
 	dump_ran = 1;
 
 	/* No turning back! */
+	tracing_off();
 	ftrace_kill();
 
 	for_each_tracing_cpu(cpu) {
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index 7c2e326bbc8..62a78d94353 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -380,6 +380,7 @@ static void stop_irqsoff_tracer(struct trace_array *tr)
 
 static void __irqsoff_tracer_init(struct trace_array *tr)
 {
+	tracing_max_latency = 0;
 	irqsoff_trace = tr;
 	/* make sure that the tracer is visible */
 	smp_wmb();
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 43586b689e3..42ae1e77b6b 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -333,6 +333,7 @@ static void stop_wakeup_tracer(struct trace_array *tr)
 
 static int wakeup_tracer_init(struct trace_array *tr)
 {
+	tracing_max_latency = 0;
 	wakeup_trace = tr;
 	start_wakeup_tracer(tr);
 	return 0;
diff --git a/kernel/wait.c b/kernel/wait.c
index cd87131f2fc..42a2dbc181c 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);