Merge commit 'v2.6.29' into timers/core

34 files changed, 468 insertions, 202 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index 170a9213c1b..e4791b3ba55 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 67a2be71f51..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;
@@ -132,8 +133,7 @@ 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)*/
@@ -208,18 +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 {
@@ -228,13 +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;
 
@@ -254,11 +297,18 @@ void async_synchronize_cookie_special(async_cookie_t cookie, struct list_head *r
 			(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);
 
@@ -319,7 +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++;
 		}
@@ -334,7 +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 5a54ff42874..9edb5c4b79b 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/fork.c b/kernel/fork.c
index bb5fe56a7a9..4854c2c4a82 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1095,7 +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. */
@@ -1179,10 +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;
@@ -1220,10 +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 f89d373a9c6..438701adce2 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/kexec.c b/kernel/kexec.c
index 8a6d7b08864..48389957825 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/module.c b/kernel/module.c
index ba22484a987..1196f5d1170 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -2015,14 +2015,6 @@ 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,
@@ -2030,7 +2022,7 @@ static noinline struct module *load_module(void __user *umod,
 					 mod->name);
 		if (!percpu) {
 			err = -ENOMEM;
-			goto free_percpu;
+			goto free_mod;
 		}
 		sechdrs[pcpuindex].sh_flags &= ~(unsigned long)SHF_ALLOC;
 		mod->percpu = percpu;
@@ -2082,6 +2074,14 @@ static noinline struct module *load_module(void __user *umod,
 	/* Module has been moved. */
 	mod = (void *)sechdrs[modindex].sh_addr;
 
+#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_init;
+	}
+#endif
 	/* Now we've moved module, initialize linked lists, etc. */
 	module_unload_init(mod);
 
@@ -2288,15 +2288,17 @@ static noinline struct module *load_module(void __user *umod,
 	ftrace_release(mod->module_core, mod->core_size);
  free_unload:
 	module_unload_free(mod);
+ free_init:
+#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP)
+	percpu_modfree(mod->refptr);
+#endif
 	module_free(mod, mod->module_init);
  free_core:
 	module_free(mod, mod->module_core);
+	/* mod will be freed with core. Don't access it beyond this line! */
  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 db107c9bbc0..e976e505648 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -261,6 +261,40 @@ 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.
@@ -488,7 +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);
 }
@@ -507,29 +541,6 @@ static void clear_dead_task(struct k_itimer *timer, union cpu_time_count now)
 }
 
 /*
- * Enable the process wide cpu timer accounting.
- *
- * serialized using ->sighand->siglock
- */
-static void start_process_timers(struct task_struct *tsk)
-{
-	tsk->signal->cputimer.running = 1;
-	barrier();
-}
-
-/*
- * Release the process wide timer accounting -- timer stops ticking when
- * nobody cares about it.
- *
- * serialized using ->sighand->siglock
- */
-static void stop_process_timers(struct task_struct *tsk)
-{
-	tsk->signal->cputimer.running = 0;
-	barrier();
-}
-
-/*
  * Insert the timer on the appropriate list before any timers that
  * expire later.  This must be called with the tasklist_lock held
  * for reading, and interrupts disabled.
@@ -549,9 +560,6 @@ static void arm_timer(struct k_itimer *timer, union cpu_time_count now)
 	BUG_ON(!irqs_disabled());
 	spin_lock(&p->sighand->siglock);
 
-	if (!CPUCLOCK_PERTHREAD(timer->it_clock))
-		start_process_timers(p);
-
 	listpos = head;
 	if (CPUCLOCK_WHICH(timer->it_clock) == CPUCLOCK_SCHED) {
 		list_for_each_entry(next, head, entry) {
@@ -673,6 +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
@@ -733,7 +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) {
@@ -881,7 +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));
 		}
@@ -1021,6 +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
@@ -1223,7 +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.  */
 	}
@@ -1388,33 +1436,6 @@ void run_posix_cpu_timers(struct task_struct *tsk)
 }
 
 /*
- * 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;
-}
-
-/*
  * Set one of the process-wide special case CPU timers.
  * The tsk->sighand->siglock must be held by the caller.
  * The *newval argument is relative and we update it to be absolute, *oldval
@@ -1427,7 +1448,6 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx,
 	struct list_head *head;
 
 	BUG_ON(clock_idx == CPUCLOCK_SCHED);
-	start_process_timers(tsk);
 	cpu_timer_sample_group(clock_idx, tsk, &now);
 
 	if (oldval) {
diff --git a/kernel/power/Makefile b/kernel/power/Makefile
index d7a10167a25..720ea4f781b 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 b8628be2a46..a3961b205de 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 432ee575c9e..4a4a206b197 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 23998887397..c9632f841f6 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 6da14358537..505f319e489 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, b