Merge branch 'pm-sleep'

* pm-sleep:
  PM / Freezer: Remove references to TIF_FREEZE in comments
  PM / Sleep: Add more wakeup source initialization routines
  PM / Hibernate: Enable usermodehelpers in hibernate() error path
  PM / Sleep: Make __pm_stay_awake() delete wakeup source timers
  PM / Sleep: Fix race conditions related to wakeup source timer function
  PM / Sleep: Fix possible infinite loop during wakeup source destruction
  PM / Hibernate: print physical addresses consistently with other parts of kernel
  PM: Add comment describing relationships between PM callbacks to pm.h
  PM / Sleep: Drop suspend_stats_update()
  PM / Sleep: Make enter_state() in kernel/power/suspend.c static
  PM / Sleep: Unify kerneldoc comments in kernel/power/suspend.c
  PM / Sleep: Remove unnecessary label from suspend_freeze_processes()
  PM / Sleep: Do not check wakeup too often in try_to_freeze_tasks()
  PM / Sleep: Initialize wakeup source locks in wakeup_source_add()
  PM / Hibernate: Refactor and simplify freezer_test_done
  PM / Hibernate: Thaw kernel threads in hibernation_snapshot() in error/test path
  PM / Freezer / Docs: Document the beauty of freeze/thaw semantics
  PM / Suspend: Avoid code duplication in suspend statistics update
  PM / Sleep: Introduce generic callbacks for new device PM phases
  PM / Sleep: Introduce "late suspend" and "early resume" of devices

10 files changed, 104 insertions, 113 deletions

diff --git a/kernel/exit.c b/kernel/exit.c
index 4b4042f9bc6a..8e6b0e626b98 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -424,7 +424,7 @@ void daemonize(const char *name, ...)
 	 */
 	exit_mm(current);
 	/*
-	 * We don't want to have TIF_FREEZE set if the system-wide hibernation
+	 * We don't want to get frozen, in case system-wide hibernation
 	 * or suspend transition begins right now.
 	 */
 	current->flags |= (PF_NOFREEZE | PF_KTHREAD);
diff --git a/kernel/freezer.c b/kernel/freezer.c
index 9815b8d1eed5..11f82a4d4eae 100644
--- a/kernel/freezer.c
+++ b/kernel/freezer.c
@@ -99,9 +99,9 @@ static void fake_signal_wake_up(struct task_struct *p)
  * freeze_task - send a freeze request to given task
  * @p: task to send the request to
  *
- * If @p is freezing, the freeze request is sent by setting %TIF_FREEZE
- * flag and either sending a fake signal to it or waking it up, depending
- * on whether it has %PF_FREEZER_NOSIG set.
+ * If @p is freezing, the freeze request is sent either by sending a fake
+ * signal (if it's not a kernel thread) or waking it up (if it's a kernel
+ * thread).
  *
  * RETURNS:
  * %false, if @p is not freezing or already frozen; %true, otherwise
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 7b0886786701..a6a675cb9818 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -1546,13 +1546,13 @@ int kernel_kexec(void)
 		if (error)
 			goto Resume_console;
 		/* At this point, dpm_suspend_start() has been called,
-		 * but *not* dpm_suspend_noirq(). We *must* call
-		 * dpm_suspend_noirq() now.  Otherwise, drivers for
+		 * but *not* dpm_suspend_end(). We *must* call
+		 * dpm_suspend_end() now.  Otherwise, drivers for
 		 * some devices (e.g. interrupt controllers) become
 		 * desynchronized with the actual state of the
 		 * hardware at resume time, and evil weirdness ensues.
 		 */
-		error = dpm_suspend_noirq(PMSG_FREEZE);
+		error = dpm_suspend_end(PMSG_FREEZE);
 		if (error)
 			goto Resume_devices;
 		error = disable_nonboot_cpus();
@@ -1579,7 +1579,7 @@ int kernel_kexec(void)
 		local_irq_enable();
  Enable_cpus:
 		enable_nonboot_cpus();
-		dpm_resume_noirq(PMSG_RESTORE);
+		dpm_resume_start(PMSG_RESTORE);
  Resume_devices:
 		dpm_resume_end(PMSG_RESTORE);
  Resume_console:
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 6d6d28870335..0a186cfde788 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -245,8 +245,8 @@ void swsusp_show_speed(struct timeval *start, struct timeval *stop,
  * create_image - Create a hibernation image.
  * @platform_mode: Whether or not to use the platform driver.
  *
- * Execute device drivers' .freeze_noirq() callbacks, create a hibernation image
- * and execute the drivers' .thaw_noirq() callbacks.
+ * Execute device drivers' "late" and "noirq" freeze callbacks, create a
+ * hibernation image and run the drivers' "noirq" and "early" thaw callbacks.
  *
  * Control reappears in this routine after the subsequent restore.
  */
@@ -254,7 +254,7 @@ static int create_image(int platform_mode)
 {
 	int error;
 
-	error = dpm_suspend_noirq(PMSG_FREEZE);
+	error = dpm_suspend_end(PMSG_FREEZE);
 	if (error) {
 		printk(KERN_ERR "PM: Some devices failed to power down, "
 			"aborting hibernation\n");
@@ -306,7 +306,7 @@ static int create_image(int platform_mode)
  Platform_finish:
 	platform_finish(platform_mode);
 
-	dpm_resume_noirq(in_suspend ?
+	dpm_resume_start(in_suspend ?
 		(error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE);
 
 	return error;
@@ -343,13 +343,13 @@ int hibernation_snapshot(int platform_mode)
 		 * successful freezer test.
 		 */
 		freezer_test_done = true;
-		goto Cleanup;
+		goto Thaw;
 	}
 
 	error = dpm_prepare(PMSG_FREEZE);
 	if (error) {
 		dpm_complete(PMSG_RECOVER);
-		goto Cleanup;
+		goto Thaw;
 	}
 
 	suspend_console();
@@ -385,6 +385,8 @@ int hibernation_snapshot(int platform_mode)
 	platform_end(platform_mode);
 	return error;
 
+ Thaw:
+	thaw_kernel_threads();
  Cleanup:
 	swsusp_free();
 	goto Close;
@@ -394,16 +396,16 @@ int hibernation_snapshot(int platform_mode)
  * resume_target_kernel - Restore system state from a hibernation image.
  * @platform_mode: Whether or not to use the platform driver.
  *
- * Execute device drivers' .freeze_noirq() callbacks, restore the contents of
- * highmem that have not been restored yet from the image and run the low-level
- * code that will restore the remaining contents of memory and switch to the
- * just restored target kernel.
+ * Execute device drivers' "noirq" and "late" freeze callbacks, restore the
+ * contents of highmem that have not been restored yet from the image and run
+ * the low-level code that will restore the remaining contents of memory and
+ * switch to the just restored target kernel.
  */
 static int resume_target_kernel(bool platform_mode)
 {
 	int error;
 
-	error = dpm_suspend_noirq(PMSG_QUIESCE);
+	error = dpm_suspend_end(PMSG_QUIESCE);
 	if (error) {
 		printk(KERN_ERR "PM: Some devices failed to power down, "
 			"aborting resume\n");
@@ -460,7 +462,7 @@ static int resume_target_kernel(bool platform_mode)
  Cleanup:
 	platform_restore_cleanup(platform_mode);
 
-	dpm_resume_noirq(PMSG_RECOVER);
+	dpm_resume_start(PMSG_RECOVER);
 
 	return error;
 }
@@ -518,7 +520,7 @@ int hibernation_platform_enter(void)
 		goto Resume_devices;
 	}
 
-	error = dpm_suspend_noirq(PMSG_HIBERNATE);
+	error = dpm_suspend_end(PMSG_HIBERNATE);
 	if (error)
 		goto Resume_devices;
 
@@ -549,7 +551,7 @@ int hibernation_platform_enter(void)
  Platform_finish:
 	hibernation_ops->finish();
 
-	dpm_resume_noirq(PMSG_RESTORE);
+	dpm_resume_start(PMSG_RESTORE);
 
  Resume_devices:
 	entering_platform_hibernation = false;
@@ -616,7 +618,7 @@ int hibernate(void)
 	/* Allocate memory management structures */
 	error = create_basic_memory_bitmaps();
 	if (error)
-		goto Exit;
+		goto Enable_umh;
 
 	printk(KERN_INFO "PM: Syncing filesystems ... ");
 	sys_sync();
@@ -624,15 +626,11 @@ int hibernate(void)
 
 	error = freeze_processes();
 	if (error)
-		goto Finish;
+		goto Free_bitmaps;
 
 	error = hibernation_snapshot(hibernation_mode == HIBERNATION_PLATFORM);
-	if (error)
-		goto Thaw;
-	if (freezer_test_done) {
-		freezer_test_done = false;
+	if (error || freezer_test_done)
 		goto Thaw;
-	}
 
 	if (in_suspend) {
 		unsigned int flags = 0;
@@ -657,8 +655,13 @@ int hibernate(void)
 
  Thaw:
 	thaw_processes();
- Finish:
+
+	/* Don't bother checking whether freezer_test_done is true */
+	freezer_test_done = false;
+
+ Free_bitmaps:
 	free_basic_memory_bitmaps();
+ Enable_umh:
 	usermodehelper_enable();
  Exit:
 	pm_notifier_call_chain(PM_POST_HIBERNATION);
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 9824b41e5a18..1c12581f1c62 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -165,16 +165,20 @@ static int suspend_stats_show(struct seq_file *s, void *unused)
 	last_errno %= REC_FAILED_NUM;
 	last_step = suspend_stats.last_failed_step + REC_FAILED_NUM - 1;
 	last_step %= REC_FAILED_NUM;
-	seq_printf(s, "%s: %d\n%s: %d\n%s: %d\n%s: %d\n"
-			"%s: %d\n%s: %d\n%s: %d\n%s: %d\n",
+	seq_printf(s, "%s: %d\n%s: %d\n%s: %d\n%s: %d\n%s: %d\n"
+			"%s: %d\n%s: %d\n%s: %d\n%s: %d\n%s: %d\n",
 			"success", suspend_stats.success,
 			"fail", suspend_stats.fail,
 			"failed_freeze", suspend_stats.failed_freeze,
 			"failed_prepare", suspend_stats.failed_prepare,
 			"failed_suspend", suspend_stats.failed_suspend,
+			"failed_suspend_late",
+				suspend_stats.failed_suspend_late,
 			"failed_suspend_noirq",
 				suspend_stats.failed_suspend_noirq,
 			"failed_resume", suspend_stats.failed_resume,
+			"failed_resume_early",
+				suspend_stats.failed_resume_early,
 			"failed_resume_noirq",
 				suspend_stats.failed_resume_noirq);
 	seq_printf(s,	"failures:\n  last_failed_dev:\t%-s\n",
@@ -287,16 +291,10 @@ static ssize_t state_store(struct kobject *kobj, struct kobj_attribute *attr,
 
 #ifdef CONFIG_SUSPEND
 	for (s = &pm_states[state]; state < PM_SUSPEND_MAX; s++, state++) {
-		if (*s && len == strlen(*s) && !strncmp(buf, *s, len))
+		if (*s && len == strlen(*s) && !strncmp(buf, *s, len)) {
+			error = pm_suspend(state);
 			break;
-	}
-	if (state < PM_SUSPEND_MAX && *s) {
-		error = enter_state(state);
-		if (error) {
-			suspend_stats.fail++;
-			dpm_save_failed_errno(error);
-		} else
-			suspend_stats.success++;
+		}
 	}
 #endif
 
diff --git a/kernel/power/power.h b/kernel/power/power.h
index 21724eee5206..98f3622d7407 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -177,13 +177,11 @@ extern const char *const pm_states[];
 
 extern bool valid_state(suspend_state_t state);
 extern int suspend_devices_and_enter(suspend_state_t state);
-extern int enter_state(suspend_state_t state);
 #else /* !CONFIG_SUSPEND */
 static inline int suspend_devices_and_enter(suspend_state_t state)
 {
 	return -ENOSYS;
 }
-static inline int enter_state(suspend_state_t state) { return -ENOSYS; }
 static inline bool valid_state(suspend_state_t state) { return false; }
 #endif /* !CONFIG_SUSPEND */
 
@@ -234,16 +232,14 @@ static inline int suspend_freeze_processes(void)
 	int error;
 
 	error = freeze_processes();
-
 	/*
 	 * freeze_processes() automatically thaws every task if freezing
 	 * fails. So we need not do anything extra upon error.
 	 */
 	if (error)
-		goto Finish;
+		return error;
 
 	error = freeze_kernel_threads();
-
 	/*
 	 * freeze_kernel_threads() thaws only kernel threads upon freezing
 	 * failure. So we have to thaw the userspace tasks ourselves.
@@ -251,7 +247,6 @@ static inline int suspend_freeze_processes(void)
 	if (error)
 		thaw_processes();
 
- Finish:
 	return error;
 }
 
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 7e426459e60a..0d2aeb226108 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -53,11 +53,9 @@ static int try_to_freeze_tasks(bool user_only)
 			 * It is "frozen enough".  If the task does wake
 			 * up, it will immediately call try_to_freeze.
 			 *
-			 * Because freeze_task() goes through p's
-			 * scheduler lock after setting TIF_FREEZE, it's
-			 * guaranteed that either we see TASK_RUNNING or
-			 * try_to_stop() after schedule() in ptrace/signal
-			 * stop sees TIF_FREEZE.
+			 * Because freeze_task() goes through p's scheduler lock, it's
+			 * guaranteed that TASK_STOPPED/TRACED -> TASK_RUNNING
+			 * transition can't race with task state testing here.
 			 */
 			if (!task_is_stopped_or_traced(p) &&
 			    !freezer_should_skip(p))
@@ -98,13 +96,15 @@ static int try_to_freeze_tasks(bool user_only)
 		       elapsed_csecs / 100, elapsed_csecs % 100,
 		       todo - wq_busy, wq_busy);
 
-		read_lock(&tasklist_lock);
-		do_each_thread(g, p) {
-			if (!wakeup && !freezer_should_skip(p) &&
-			    p != current && freezing(p) && !frozen(p))
-				sched_show_task(p);
-		} while_each_thread(g, p);
-		read_unlock(&tasklist_lock);
+		if (!wakeup) {
+			read_lock(&tasklist_lock);
+			do_each_thread(g, p) {
+				if (p != current && !freezer_should_skip(p)
+				    && freezing(p) && !frozen(p))
+					sched_show_task(p);
+			} while_each_thread(g, p);
+			read_unlock(&tasklist_lock);
+		}
 	} else {
 		printk("(elapsed %d.%02d seconds) ", elapsed_csecs / 100,
 			elapsed_csecs % 100);
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 6a768e537001..8e2e7461375f 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -711,9 +711,10 @@ static void mark_nosave_pages(struct memory_bitmap *bm)
 	list_for_each_entry(region, &nosave_regions, list) {
 		unsigned long pfn;
 
-		pr_debug("PM: Marking nosave pages: %016lx - %016lx\n",
-				region->start_pfn << PAGE_SHIFT,
-				region->end_pfn << PAGE_SHIFT);
+		pr_debug("PM: Marking nosave pages: [mem %#010llx-%#010llx]\n",
+			 (unsigned long long) region->start_pfn << PAGE_SHIFT,
+			 ((unsigned long long) region->end_pfn << PAGE_SHIFT)
+				- 1);
 
 		for (pfn = region->start_pfn; pfn < region->end_pfn; pfn++)
 			if (pfn_valid(pfn)) {
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 4fd51beed879..88e5c967370d 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -37,8 +37,8 @@ const char *const pm_states[PM_SUSPEND_MAX] = {
 static const struct platform_suspend_ops *suspend_ops;
 
 /**
- *	suspend_set_ops - Set the global suspend method table.
- *	@ops:	Pointer to ops structure.
+ * suspend_set_ops - Set the global suspend method table.
+ * @ops: Suspend operations to use.
  */
 void suspend_set_ops(const struct platform_suspend_ops *ops)
 {
@@ -58,11 +58,11 @@ bool valid_state(suspend_state_t state)
 }
 
 /**
- * suspend_valid_only_mem - generic memory-only valid callback
+ * suspend_valid_only_mem - Generic memory-only valid callback.
  *
- * Platform drivers that implement mem suspend only and only need
- * to check for that in their .valid callback can use this instead
- * of rolling their own .valid callback.
+ * Platform drivers that implement mem suspend only and only need to check for
+ * that in their .valid() callback can use this instead of rolling their own
+ * .valid() callback.
  */
 int suspend_valid_only_mem(suspend_state_t state)
 {
@@ -83,10 +83,11 @@ static int suspend_test(int level)
 }
 
 /**
- *	suspend_prepare - Do prep work before entering low-power state.
+ * suspend_prepare - Prepare for entering system sleep state.
  *
- *	This is common code that is called for each state that we're entering.
- *	Run suspend notifiers, allocate a console and stop all processes.
+ * Common code run for every system sleep state that can be entered (except for
+ * hibernation).  Run suspend notifiers, allocate the "suspend" console and
+ * freeze processes.
  */
 static int suspend_prepare(void)
 {
@@ -131,9 +132,9 @@ void __attribute__ ((weak)) arch_suspend_enable_irqs(void)
 }
 
 /**
- * suspend_enter - enter the desired system sleep state.
- * @state: State to enter
- * @wakeup: Returns information that suspend should not be entered again.
+ * suspend_enter - Make the system enter the given sleep state.
+ * @state: System sleep state to enter.
+ * @wakeup: Returns information that the sleep state should not be re-entered.
  *
  * This function should be called after devices have been suspended.
  */
@@ -147,7 +148,7 @@ static int suspend_enter(suspend_state_t state, bool *wakeup)
 			goto Platform_finish;
 	}
 
-	error = dpm_suspend_noirq(PMSG_SUSPEND);
+	error = dpm_suspend_end(PMSG_SUSPEND);
 	if (error) {
 		printk(KERN_ERR "PM: Some devices failed to power down\n");
 		goto Platform_finish;
@@ -189,7 +190,7 @@ static int suspend_enter(suspend_state_t state, bool *wakeup)
 	if (suspend_ops->wake)
 		suspend_ops->wake();
 
-	dpm_resume_noirq(PMSG_RESUME);
+	dpm_resume_start(PMSG_RESUME);
 
  Platform_finish:
 	if (suspend_ops->finish)
@@ -199,9 +200,8 @@ static int suspend_enter(suspend_state_t state, bool *wakeup)
 }
 
 /**
- *	suspend_devices_and_enter - suspend devices and enter the desired system
- *				    sleep state.
- *	@state:		  state to enter
+ * suspend_devices_and_enter - Suspend devices and enter system sleep state.
+ * @state: System sleep state to enter.
  */
 int suspend_devices_and_enter(suspend_state_t state)
 {
@@ -251,10 +251,10 @@ int suspend_devices_and_enter(suspend_state_t state)
 }
 
 /**
- *	suspend_finish - Do final work before exiting suspend sequence.
+ * suspend_finish - Clean up before finishing the suspend sequence.
  *
- *	Call platform code to clean up, restart processes, and free the
- *	console that we've allocated. This is not called for suspend-to-disk.
+ * Call platform code to clean up, restart processes, and free the console that
+ * we've allocated. This routine is not called for hibernation.
  */
 static void suspend_finish(void)
 {
@@ -265,16 +265,14 @@ static void suspend_finish(void)
 }
 
 /**
- *	enter_state - Do common work of entering low-power state.
- *	@state:		pm_state structure for state we're entering.
+ * enter_state - Do common work needed to enter system sleep state.
+ * @state: System sleep state to enter.
  *
- *	Make sure we're the only ones trying to enter a sleep state. Fail
- *	if someone has beat us to it, since we don't want anything weird to
- *	happen when we wake up.
- *	Then, do the setup for suspend, enter the state, and cleaup (after
- *	we've woken up).
+ * Make sure that no one else is trying to put the system into a sleep state.
+ * Fail if that's not the case.  Otherwise, prepare for system suspend, make the
+ * system enter the given sleep state and clean up after wakeup.
  */
-int enter_state(suspend_state_t state)
+static int enter_state(suspend_state_t state)
 {
 	int error;
 
@@ -310,24 +308,26 @@ int enter_state(suspend_state_t state)
 }
 
 /**
- *	pm_suspend - Externally visible function for suspending system.
- *	@state:		Enumerated value of state to enter.
+ * pm_suspend - Externally visible function for suspending the system.
+ * @state: System sleep state to enter.
  *
- *	Determine whether or not value is within range, get state
- *	structure, and enter (above).
+ * Check if the value of @state represents one of the supported states,
+ * execute enter_state() and update system suspend statistics.
  */
 int pm_suspend(suspend_state_t state)
 {
-	int ret;
-	if (state > PM_SUSPEND_ON && state < PM_SUSPEND_MAX) {
-		ret = enter_state(state);
-		if (ret) {
-			suspend_stats.fail++;
-			dpm_save_failed_errno(ret);
-		} else
-			suspend_stats.success++;
-		return ret;
+	int error;
+
+	if (state <= PM_SUSPEND_ON || state >= PM_SUSPEND_MAX)
+		return -EINVAL;
+
+	error = enter_state(state);
+	if (error) {
+		suspend_stats.fail++;
+		dpm_save_failed_errno(error);
+	} else {
+		suspend_stats.success++;
 	}
-	return -EINVAL;
+	return error;
 }
 EXPORT_SYMBOL(pm_suspend);
diff --git a/kernel/power/user.c b/kernel/power/user.c
index 3e100075b13c..33c4329205af 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -249,16 +249,10 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
 		}
 		pm_restore_gfp_mask();
 		error = hibernation_snapshot(data->platform_support);
-		if (error) {
-			thaw_kernel_threads();
-		} else {
+		if (!error) {
 			error = put_user(in_suspend, (int __user *)arg);
-			if (!error && !freezer_test_done)
-				data->ready = 1;
-			if (freezer_test_done) {
-				freezer_test_done = false;
-				thaw_kernel_threads();
-			}
+			data->ready = !freezer_test_done && !error;
+			freezer_test_done = false;
 		}
 		break;