27 files changed, 298 insertions, 198 deletions

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index c29831076e7a..5a54ff42874e 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1115,8 +1115,10 @@ static void cgroup_kill_sb(struct super_block *sb) {
 	}
 	write_unlock(&css_set_lock);
 
-	list_del(&root->root_list);
-	root_count--;
+	if (!list_empty(&root->root_list)) {
+		list_del(&root->root_list);
+		root_count--;
+	}
 
 	mutex_unlock(&cgroup_mutex);
 
@@ -2434,7 +2436,9 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 
  err_remove:
 
+	cgroup_lock_hierarchy(root);
 	list_del(&cgrp->sibling);
+	cgroup_unlock_hierarchy(root);
 	root->number_of_cgroups--;
 
  err_destroy:
@@ -2507,7 +2511,7 @@ static int cgroup_clear_css_refs(struct cgroup *cgrp)
 	for_each_subsys(cgrp->root, ss) {
 		struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id];
 		int refcnt;
-		do {
+		while (1) {
 			/* We can only remove a CSS with a refcnt==1 */
 			refcnt = atomic_read(&css->refcnt);
 			if (refcnt > 1) {
@@ -2521,7 +2525,10 @@ static int cgroup_clear_css_refs(struct cgroup *cgrp)
 			 * css_tryget() to spin until we set the
 			 * CSS_REMOVED bits or abort
 			 */
-		} while (atomic_cmpxchg(&css->refcnt, refcnt, 0) != refcnt);
+			if (atomic_cmpxchg(&css->refcnt, refcnt, 0) == refcnt)
+				break;
+			cpu_relax();
+		}
 	}
  done:
 	for_each_subsys(cgrp->root, ss) {
@@ -2991,20 +2998,21 @@ int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys,
 		mutex_unlock(&cgroup_mutex);
 		return 0;
 	}
-	task_lock(tsk);
-	cg = tsk->cgroups;
-	parent = task_cgroup(tsk, subsys->subsys_id);
 
 	/* Pin the hierarchy */
-	if (!atomic_inc_not_zero(&parent->root->sb->s_active)) {
+	if (!atomic_inc_not_zero(&root->sb->s_active)) {
 		/* We race with the final deactivate_super() */
 		mutex_unlock(&cgroup_mutex);
 		return 0;
 	}
 
 	/* Keep the cgroup alive */
+	task_lock(tsk);
+	parent = task_cgroup(tsk, subsys->subsys_id);
+	cg = tsk->cgroups;
 	get_css_set(cg);
 	task_unlock(tsk);
+
 	mutex_unlock(&cgroup_mutex);
 
 	/* Now do the VFS work to create a cgroup */
@@ -3043,7 +3051,7 @@ int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys,
 		mutex_unlock(&inode->i_mutex);
 		put_css_set(cg);
 
-		deactivate_super(parent->root->sb);
+		deactivate_super(root->sb);
 		/* The cgroup is still accessible in the VFS, but
 		 * we're not going to try to rmdir() it at this
 		 * point. */
@@ -3069,7 +3077,7 @@ int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys,
 	mutex_lock(&cgroup_mutex);
 	put_css_set(cg);
 	mutex_unlock(&cgroup_mutex);
-	deactivate_super(parent->root->sb);
+	deactivate_super(root->sb);
 	return ret;
 }
 
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index a85678865c5e..f76db9dcaa05 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/dma-coherent.c b/kernel/dma-coherent.c
index 038707404b76..962a3b574f21 100644
--- a/kernel/dma-coherent.c
+++ b/kernel/dma-coherent.c
@@ -98,7 +98,7 @@ EXPORT_SYMBOL(dma_mark_declared_memory_occupied);
  * @size:	size of requested memory area
  * @dma_handle:	This will be filled with the correct dma handle
  * @ret:	This pointer will be filled with the virtual address
- * 		to allocated area.
+ *		to allocated area.
  *
  * This function should be only called from per-arch dma_alloc_coherent()
  * to support allocation from per-device coherent memory pools.
@@ -118,31 +118,32 @@ int dma_alloc_from_coherent(struct device *dev, ssize_t size,
 	mem = dev->dma_mem;
 	if (!mem)
 		return 0;
-	if (unlikely(size > mem->size))
- 		return 0;
+
+	*ret = NULL;
+
+	if (unlikely(size > (mem->size << PAGE_SHIFT)))
+		goto err;
 
 	pageno = bitmap_find_free_region(mem->bitmap, mem->size, order);
-	if (pageno >= 0) {
-		/*
-		 * Memory was found in the per-device arena.
-		 */
-		*dma_handle = mem->device_base + (pageno << PAGE_SHIFT);
-		*ret = mem->virt_base + (pageno << PAGE_SHIFT);
-		memset(*ret, 0, size);
-	} else if (mem->flags & DMA_MEMORY_EXCLUSIVE) {
-		/*
-		 * The per-device arena is exhausted and we are not
-		 * permitted to fall back to generic memory.
-		 */
-		*ret = NULL;
-	} else {
-		/*
-		 * The per-device arena is exhausted and we are
-		 * permitted to fall back to generic memory.
-		 */
-		 return 0;
-	}
+	if (unlikely(pageno < 0))
+		goto err;
+
+	/*
+	 * Memory was found in the per-device area.
+	 */
+	*dma_handle = mem->device_base + (pageno << PAGE_SHIFT);
+	*ret = mem->virt_base + (pageno << PAGE_SHIFT);
+	memset(*ret, 0, size);
+
 	return 1;
+
+err:
+	/*
+	 * In the case where the allocation can not be satisfied from the
+	 * per-device area, try to fall back to generic memory if the
+	 * constraints allow it.
+	 */
+	return mem->flags & DMA_MEMORY_EXCLUSIVE;
 }
 EXPORT_SYMBOL(dma_alloc_from_coherent);
 
diff --git a/kernel/fork.c b/kernel/fork.c
index bf0cef8bbdf2..242a706e7721 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -817,17 +817,17 @@ static void posix_cpu_timers_init_group(struct signal_struct *sig)
 static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 {
 	struct signal_struct *sig;
-	int ret;
 
 	if (clone_flags & CLONE_THREAD) {
-		ret = thread_group_cputime_clone_thread(current);
-		if (likely(!ret)) {
-			atomic_inc(&current->signal->count);
-			atomic_inc(&current->signal->live);
-		}
-		return ret;
+		atomic_inc(&current->signal->count);
+		atomic_inc(&current->signal->live);
+		return 0;
 	}
 	sig = kmem_cache_alloc(signal_cachep, GFP_KERNEL);
+
+	if (sig)
+		posix_cpu_timers_init_group(sig);
+
 	tsk->signal = sig;
 	if (!sig)
 		return -ENOMEM;
@@ -864,8 +864,6 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	memcpy(sig->rlim, current->signal->rlim, sizeof sig->rlim);
 	task_unlock(current->group_leader);
 
-	posix_cpu_timers_init_group(sig);
-
 	acct_init_pacct(&sig->pacct);
 
 	tty_audit_fork(sig);
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 2dc30c59c5fd..f394d2a42ca3 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;
 	}
@@ -614,7 +621,9 @@ void clock_was_set(void)
  */
 void hres_timers_resume(void)
 {
-	/* Retrigger the CPU local events: */
+	WARN_ONCE(!irqs_disabled(),
+		  KERN_INFO "hres_timers_resume() called with IRQs enabled!");
+
 	retrigger_next_event(NULL);
 }
 
@@ -1156,6 +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
@@ -1165,6 +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);
@@ -1172,6 +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;
@@ -1224,7 +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;
 	}
 }
@@ -1578,6 +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 f63c706d25e1..7de11bd64dfe 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -383,6 +383,7 @@ 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
@@ -593,6 +594,7 @@ __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/handle.c b/kernel/irq/handle.c
index c20db0be9173..3aba8d12f328 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -39,6 +39,18 @@ void handle_bad_irq(unsigned int irq, struct irq_desc *desc)
 	ack_bad_irq(irq);
 }
 
+#if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_HARDIRQS)
+static void __init init_irq_default_affinity(void)
+{
+	alloc_bootmem_cpumask_var(&irq_default_affinity);
+	cpumask_setall(irq_default_affinity);
+}
+#else
+static void __init init_irq_default_affinity(void)
+{
+}
+#endif
+
 /*
  * Linux has a controller-independent interrupt architecture.
  * Every controller has a 'controller-template', that is used
@@ -134,6 +146,8 @@ int __init early_irq_init(void)
 	int legacy_count;
 	int i;
 
+	init_irq_default_affinity();
+
 	desc = irq_desc_legacy;
 	legacy_count = ARRAY_SIZE(irq_desc_legacy);
 
@@ -219,6 +233,8 @@ int __init early_irq_init(void)
 	int count;
 	int i;
 
+	init_irq_default_affinity();
+
 	desc = irq_desc;
 	count = ARRAY_SIZE(irq_desc);
 
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index cd0cd8dcb345..291f03664552 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -15,17 +15,9 @@
 
 #include "internals.h"
 
-#ifdef CONFIG_SMP
+#if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_HARDIRQS)
 cpumask_var_t irq_default_affinity;
 
-static int init_irq_default_affinity(void)
-{
-	alloc_cpumask_var(&irq_default_affinity, GFP_KERNEL);
-	cpumask_setall(irq_default_affinity);
-	return 0;
-}
-core_initcall(init_irq_default_affinity);
-
 /**
  *	synchronize_irq - wait for pending IRQ handlers (on other CPUs)
  *	@irq: interrupt number to wait for
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index e694afa0eb8c..7b8b0f21a5b1 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -30,19 +30,20 @@
 #define all_var 0
 #endif
 
-extern const unsigned long kallsyms_addresses[];
-extern const u8 kallsyms_names[];
+/* These will be re-linked against their real values during the second link stage */
+extern const unsigned long kallsyms_addresses[] __attribute__((weak));
+extern const u8 kallsyms_names[] __attribute__((weak));
 
 /* tell the compiler that the count isn't in the small data section if the arch
  * has one (eg: FRV)
  */
 extern const unsigned long kallsyms_num_syms
-	__attribute__((__section__(".rodata")));
+__attribute__((weak, section(".rodata")));
 
-extern const u8 kallsyms_token_table[];
-extern const u16 kallsyms_token_index[];
+extern const u8 kallsyms_token_table[] __attribute__((weak));
+extern const u16 kallsyms_token_index[] __attribute__((weak));
 
-extern const unsigned long kallsyms_markers[];
+extern const unsigned long kallsyms_markers[] __attribute__((weak));
 
 static inline int is_kernel_inittext(unsigned long addr)
 {
@@ -167,6 +168,9 @@ static unsigned long get_symbol_pos(unsigned long addr,
 	unsigned long symbol_start = 0, symbol_end = 0;
 	unsigned long i, low, high, mid;
 
+	/* This kernel should never had been booted. */
+	BUG_ON(!kallsyms_addresses);
+
 	/* do a binary search on the sorted kallsyms_addresses array */
 	low = 0;
 	high = kallsyms_num_syms;
diff --git a/kernel/module.c b/kernel/module.c
index e8b51d41dd72..ba22484a987e 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/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index 157de3a47832..fa07da94d7be 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -10,76 +10,6 @@
 #include <linux/kernel_stat.h>
 
 /*
- * Allocate the thread_group_cputime structure appropriately and fill in the
- * current values of the fields.  Called from copy_signal() via
- * thread_group_cputime_clone_thread() when adding a second or subsequent
- * thread to a thread group.  Assumes interrupts are enabled when called.
- */
-int thread_group_cputime_alloc(struct task_struct *tsk)
-{
-	struct signal_struct *sig = tsk->signal;
-	struct task_cputime *cputime;
-
-	/*
-	 * If we have multiple threads and we don't already have a
-	 * per-CPU task_cputime struct (checked in the caller), allocate
-	 * one and fill it in with the times accumulated so far.  We may
-	 * race with another thread so recheck after we pick up the sighand
-	 * lock.
-	 */
-	cputime = alloc_percpu(struct task_cputime);
-	if (cputime == NULL)
-		return -ENOMEM;
-	spin_lock_irq(&tsk->sighand->siglock);
-	if (sig->cputime.totals) {
-		spin_unlock_irq(&tsk->sighand->siglock);
-		free_percpu(cputime);
-		return 0;
-	}
-	sig->cputime.totals = cputime;
-	cputime = per_cpu_ptr(sig->cputime.totals, smp_processor_id());
-	cputime->utime = tsk->utime;
-	cputime->stime = tsk->stime;
-	cputime->sum_exec_runtime = tsk->se.sum_exec_runtime;
-	spin_unlock_irq(&tsk->sighand->siglock);
-	return 0;
-}
-
-/**
- * thread_group_cputime - Sum the thread group time fields across all CPUs.
- *
- * @tsk:	The task we use to identify the thread group.
- * @times:	task_cputime structure in which we return the summed fields.
- *
- * Walk the list of CPUs to sum the per-CPU time fields in the thread group
- * time structure.
- */
-void thread_group_cputime(
-	struct task_struct *tsk,
-	struct task_cputime *times)
-{
-	struct task_cputime *totals, *tot;
-	int i;
-
-	totals = tsk->signal->cputime.totals;
-	if (!totals) {
-		times->utime = tsk->utime;
-		times->stime = tsk->stime;
-		times->sum_exec_runtime = tsk->se.sum_exec_runtime;
-		return;
-	}
-
-	times->stime = times->utime = cputime_zero;
-	times->sum_exec_runtime = 0;
-	for_each_possible_cpu(i) {
-		tot = per_cpu_ptr(totals, i);
-		times->utime = cputime_add(times->utime, tot->utime);
-		times->stime = cputime_add(times->stime, tot->stime);
-		times->sum_exec_runtime += tot->sum_exec_runtime;
-	}
-}
-
-/*
  * Called after updating RLIMIT_CPU to set timer expiration if necessary.
  */
 void update_rlimit_cpu(unsigned long rlim_new)
diff --git a/kernel/power/disk.c b/kernel/power/disk.c
index 45e8541ab7e3..432ee575c9ee 100644
--- a/kernel/power/disk.c
+++ b/kernel/power/disk.c
@@ -71,6 +71,14 @@ void hibernation_set_ops(struct platform_hibernation_ops *ops)
 	mutex_unlock(&pm_mutex);
 }
 
+static bool entering_platform_hibernation;
+
+bool system_entering_hibernation(void)
+{
+	return entering_platform_hibernation;
+}
+EXPORT_SYMBOL(system_entering_hibernation);
+
 #ifdef CONFIG_PM_DEBUG
 static void hibernation_debug_sleep(void)
 {
@@ -411,6 +419,7 @@ int hibernation_platform_enter(void)
 	if (error)
 		goto Close;
 
+	entering_platform_hibernation = true;
 	suspend_console();
 	error = device_suspend(PMSG_HIBERNATE);
 	if (error) {
@@ -445,6 +454,7 @@ int hibernation_platform_enter(void)
  Finish:
 	hibernation_ops->finish();
  Resume_devices:
+	entering_platform_hibernation = false;
 	device_resume(PMSG_RESTORE);
 	resume_console();
  Close:
diff --git a/kernel/rcuclassic.c b/kernel/rcuclassic.c
index 490934fc7ac3..bd5a9003497c 100644
--- a/kernel/rcuclassic.c
+++ b/kernel/rcuclassic.c
@@ -716,7 +716,7 @@ void rcu_check_callbacks(int cpu, int user)
 	raise_rcu_softirq();
 }
 
-static void rcu_init_percpu_data(int cpu, struct rcu_ctrlblk *rcp,
+static void __cpuinit rcu_init_percpu_data(int cpu, struct rcu_ctrlblk *rcp,
 						struct rcu_data *rdp)
 {
 	unsigned long flags;
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index f2d8638e6c60..b2fd602a6f6f 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -1314,7 +1314,7 @@ int rcu_needs_cpu(int cpu)
  * access due to the fact that this CPU cannot possibly have any RCU
  * callbacks in flight yet.
  */
-static void
+static void __cpuinit
 rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
 {
 	unsigned long flags;
diff --git a/kernel/relay.c b/kernel/relay.c
index d06450670c86..edc0ba6d8160 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -663,8 +663,10 @@ int relay_late_setup_files(struct rchan *chan,
 
 	mutex_lock(&relay_channels_mutex);
 	/* Is chan already set up? */
-	if (unlikely(chan->has_base_filename))
+	if (unlikely(chan->has_base_filename)) {
+		mutex_unlock(&relay_channels_mutex);
 		return -EEXIST;
+	}
 	chan->has_base_filename = 1;
 	chan->parent = parent;
 	curr_cpu = get_cpu();
diff --git a/kernel/sched.c b/kernel/sched.c
index c154825ae753..566c8c9e3a6d 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;
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 5cc1c162044f..a7e50ba185ac 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/sched_rt.c b/kernel/sched_rt.c
index 954e1a81b796..bac1061cea2f 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -968,8 +968,8 @@ static inline int pick_optimal_cpu(int this_cpu, cpumask_t *mask)
 	if ((this_cpu != -1) && cpu_isset(this_cpu, *mask))
 		return this_cpu;
 
-	first = first_cpu(*mask);
-	if (first != NR_CPUS)
+	first = cpumask_first(mask);
+	if (first < nr_cpu_ids)
 		return first;
 
 	return -1;
diff --git a/kernel/sched_stats.h b/kernel/sched_stats.h
index f2773b5d1226..8ab0cef8ecab 100644
--- a/kernel/sched_stats.h
+++ b/kernel/sched_stats.h
@@ -296,6 +296,7 @@ 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;
 
 	/* tsk == current, ensure it is safe to use ->signal */
@@ -303,13 +304,11 @@ static inline void account_group_user_time(struct task_struct *tsk,
 		return;
 
 	sig = tsk->signal;
-	if (sig->cputime.totals) {
-		struct task_cputime *times;
+	times = &sig->cputime.totals;
 
-		times = per_cpu_ptr(sig->cputime.totals, get_cpu());
-		times->utime = cputime_add(times->utime, cputime);
-		put_cpu_no_resched();
-	}
+	spin_lock(&times->lock);
+	times->utime = cputime_add(times->utime, cputime);
+	spin_unlock(&times->lock);
 }
 
 /**
@@ -325,6 +324,7 @@ 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;
 
 	/* tsk == current, ensure it is safe to use ->signal */
@@ -332,13 +332,11 @@ static inline void account_group_system_time(struct task_struct *tsk,
 		return;
 
 	sig = tsk->signal;
-	if (sig->cputime.totals) {
-		struct task_cputime *times;
+	times = &sig->cputime.totals;
 
-		times = per_cpu_ptr(sig->cputime.totals, get_cpu());
-		times->stime = cputime_add(times->stime, cputime);
-		put_cpu_no_resched();
-	}
+	spin_lock(&times->lock);
+	times->stime = cputime_add(times->stime, cputime);
+	spin_unlock(&times->lock);
 }
 
 /**
@@ -354,6 +352,7 @@ 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 signal_struct *sig;
 
 	sig = tsk->signal;
@@ -362,11 +361,9 @@ static inline void account_group_exec_runtime(struct task_struct *tsk,
 	if (unlikely(!sig))
 		return;
 
-	if (sig->cputime.totals) {
-		struct task_cputime *times;
+	times = &sig->cputime.totals;
 
-		times = per_cpu_ptr(sig->cputime.totals, get_cpu());
-		times->sum_exec_runtime += ns;
-		put_cpu_no_resched();
-	}
+	spin_lock(&times->lock);
+	times->sum_exec_runtime += ns;
+	spin_unlock(&times->lock);
 }
diff --git a/kernel/signal.c b/kernel/signal.c
index e73759783dc8..b6b36768b758 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 5cfa0e5e3e88..bbedbb7efe32 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/softlockup.c b/kernel/softlockup.c
index d9188c66278a..85d5a2455103 100644
--- a/kernel/softlockup.c
+++ b/kernel/softlockup.c
@@ -16,6 +16,7 @@
 #include <linux/lockdep.h>
 #include <linux/notifier.h>
 #include <linux/module.h>
+#include <linux/sysctl.h>
 
 #include <asm/irq_regs.h>
 
@@ -88,6 +89,14 @@ void touch_all_softlockup_watchdogs(void)
 }
 EXPORT_SYMBOL(touch_all_softlockup_watchdogs);
 
+int proc_dosoftlockup_thresh(struct ctl_table *table, int write,
+			     struct file *filp, void __user *buffer,
+			     size_t *lenp, loff_t *ppos)
+{
+	touch_all_softlockup_watchdogs();
+	return proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos);
+}
+
 /*
  * This callback runs from the timer interrupt, and checks
  * whether the watchdog thread has hung or not:
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 368d1638ee78..790f9d785663 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -809,7 +809,7 @@ static struct ctl_table kern_table[] = {
 		.data		= &softlockup_thresh,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= &proc_dointvec_minmax,
+		.proc_handler	= &proc_dosoftlockup_thresh,
 		.strategy	= &sysctl_intvec,
 		.extra1		= &neg_one,
 		.extra2		= &sixty,
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 63e05d423a09..21a5ca849514 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/time/tick-sched.c b/kernel/time/tick-sched.c
index 1b6c05bd0d0a..d3f1ef4d5cbe 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -134,7 +134,7 @@ __setup("nohz=", setup_tick_nohz);
  * value. We do this unconditionally on any cpu, as we don't know whether the
  * cpu, which has the update task assigned is in a long sleep.
  */
-void tick_nohz_update_jiffies(void)
+static void tick_nohz_update_jiffies(void)
 {
 	int cpu = smp_processor_id();
 	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
diff --git a/kernel/trace/kmemtrace.c b/kernel/trace/kmemtrace.c
index 72b326bba005..f04c0625f1cd 100644
--- a/kernel/trace/kmemtrace.c
+++ b/kernel/trace/kmemtrace.c
@@ -139,12 +139,12 @@ kmemtrace_print_alloc_compress(struct trace_iterator *iter,
 		return TRACE_TYPE_PARTIAL_LINE;
 
 	/* Requested */
-	ret = trace_seq_printf(s, "%4zd   ", entry->bytes_req);
+	ret = trace_seq_printf(s, "%4zu   ", entry->bytes_req);
 	if (!ret)
 		return TRACE_TYPE_PARTIAL_LINE;
 
 	/* Allocated */
-	ret = trace_seq_printf(s, "%4zd   ", entry->bytes_alloc);
+	ret = trace_seq_printf(s, "%4zu   ", entry->bytes_alloc);
 	if (!ret)
 		return TRACE_TYPE_PARTIAL_LINE;
 
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 1fc2bc20603f..e53ee18ef431 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -985,6 +985,8 @@ undo:
 }
 
 #ifdef CONFIG_SMP
+static struct workqueue_struct *work_on_cpu_wq __read_mostly;
+
 struct work_for_cpu {
 	struct work_struct work;
 	long (*fn)(void *);
@@ -1005,8 +1007,8 @@ static void do_work_for_cpu(struct work_struct *w)
  * @fn: the function to run
  * @arg: the function arg
  *
- * This will return -EINVAL in the cpu is not online, or the return value
- * of @fn otherwise.
+ * This will return the value @fn returns.
+ * It is up to the caller to ensure that the cpu doesn't go offline.
  */
 long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg)
 {
@@ -1015,14 +1017,8 @@ long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg)
 	INIT_WORK(&wfc.work, do_work_for_cpu);
 	wfc.fn = fn;
 	wfc.arg = arg;
-	get_online_cpus();
-	if (unlikely(!cpu_online(cpu)))
-		wfc.ret = -EINVAL;
-	else {
-		schedule_work_on(cpu, &wfc.work);
-		flush_work(&wfc.work);
-	}
-	put_online_cpus();
+	queue_work_on(cpu, work_on_cpu_wq, &wfc.work);
+	flush_work(&wfc.work);
 
 	return wfc.ret;
 }
@@ -1039,4 +1035,8 @@ void __init init_workqueues(void)
 	hotcpu_notifier(workqueue_cpu_callback, 0);
 	keventd_wq = create_workqueue("events");
 	BUG_ON(!keventd_wq);
+#ifdef CONFIG_SMP
+	work_on_cpu_wq = create_workqueue("work_on_cpu");
+	BUG_ON(!work_on_cpu_wq);
+#endif
 }