Merge commit 'v2.6.28-rc2' into x86/pci-ioapic-boot-irq-quirks

9 files changed, 290 insertions, 204 deletions

diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index b45da40e8d25..dcd165f92a88 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -82,7 +82,7 @@ config PM_SLEEP_SMP
 
 config PM_SLEEP
 	bool
-	depends on SUSPEND || HIBERNATION
+	depends on SUSPEND || HIBERNATION || XEN_SAVE_RESTORE
 	default y
 
 config SUSPEND
@@ -94,6 +94,17 @@ config SUSPEND
 	  powered and thus its contents are preserved, such as the
 	  suspend-to-RAM state (e.g. the ACPI S3 state).
 
+config PM_TEST_SUSPEND
+	bool "Test suspend/resume and wakealarm during bootup"
+	depends on SUSPEND && PM_DEBUG && RTC_LIB=y
+	---help---
+	This option will let you suspend your machine during bootup, and
+	make it wake up a few seconds later using an RTC wakeup alarm.
+	Enable this with a kernel parameter like "test_suspend=mem".
+
+	You probably want to have your system's RTC driver statically
+	linked, ensuring that it's available when this test runs.
+
 config SUSPEND_FREEZER
 	bool "Enable freezer for suspend to RAM/standby" \
 		if ARCH_WANTS_FREEZER_CONTROL || BROKEN
diff --git a/kernel/power/disk.c b/kernel/power/disk.c
index f011e0870b52..c9d74083746f 100644
--- a/kernel/power/disk.c
+++ b/kernel/power/disk.c
@@ -14,6 +14,7 @@
 #include <linux/reboot.h>
 #include <linux/string.h>
 #include <linux/device.h>
+#include <linux/kmod.h>
 #include <linux/delay.h>
 #include <linux/fs.h>
 #include <linux/mount.h>
@@ -21,6 +22,7 @@
 #include <linux/console.h>
 #include <linux/cpu.h>
 #include <linux/freezer.h>
+#include <linux/ftrace.h>
 
 #include "power.h"
 
@@ -255,7 +257,7 @@ static int create_image(int platform_mode)
 
 int hibernation_snapshot(int platform_mode)
 {
-	int error;
+	int error, ftrace_save;
 
 	/* Free memory before shutting down devices. */
 	error = swsusp_shrink_memory();
@@ -267,6 +269,7 @@ int hibernation_snapshot(int platform_mode)
 		goto Close;
 
 	suspend_console();
+	ftrace_save = __ftrace_enabled_save();
 	error = device_suspend(PMSG_FREEZE);
 	if (error)
 		goto Recover_platform;
@@ -296,6 +299,7 @@ int hibernation_snapshot(int platform_mode)
  Resume_devices:
 	device_resume(in_suspend ?
 		(error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE);
+	__ftrace_enabled_restore(ftrace_save);
 	resume_console();
  Close:
 	platform_end(platform_mode);
@@ -366,10 +370,11 @@ static int resume_target_kernel(void)
 
 int hibernation_restore(int platform_mode)
 {
-	int error;
+	int error, ftrace_save;
 
 	pm_prepare_console();
 	suspend_console();
+	ftrace_save = __ftrace_enabled_save();
 	error = device_suspend(PMSG_QUIESCE);
 	if (error)
 		goto Finish;
@@ -384,6 +389,7 @@ int hibernation_restore(int platform_mode)
 	platform_restore_cleanup(platform_mode);
 	device_resume(PMSG_RECOVER);
  Finish:
+	__ftrace_enabled_restore(ftrace_save);
 	resume_console();
 	pm_restore_console();
 	return error;
@@ -396,7 +402,7 @@ int hibernation_restore(int platform_mode)
 
 int hibernation_platform_enter(void)
 {
-	int error;
+	int error, ftrace_save;
 
 	if (!hibernation_ops)
 		return -ENOSYS;
@@ -411,6 +417,7 @@ int hibernation_platform_enter(void)
 		goto Close;
 
 	suspend_console();
+	ftrace_save = __ftrace_enabled_save();
 	error = device_suspend(PMSG_HIBERNATE);
 	if (error) {
 		if (hibernation_ops->recover)
@@ -445,6 +452,7 @@ int hibernation_platform_enter(void)
 	hibernation_ops->finish();
  Resume_devices:
 	device_resume(PMSG_RESTORE);
+	__ftrace_enabled_restore(ftrace_save);
 	resume_console();
  Close:
 	hibernation_ops->end();
@@ -513,6 +521,10 @@ int hibernate(void)
 	if (error)
 		goto Exit;
 
+	error = usermodehelper_disable();
+	if (error)
+		goto Exit;
+
 	/* Allocate memory management structures */
 	error = create_basic_memory_bitmaps();
 	if (error)
@@ -551,6 +563,7 @@ int hibernate(void)
 	thaw_processes();
  Finish:
 	free_basic_memory_bitmaps();
+	usermodehelper_enable();
  Exit:
 	pm_notifier_call_chain(PM_POST_HIBERNATION);
 	pm_restore_console();
@@ -627,6 +640,10 @@ static int software_resume(void)
 	if (error)
 		goto Finish;
 
+	error = usermodehelper_disable();
+	if (error)
+		goto Finish;
+
 	error = create_basic_memory_bitmaps();
 	if (error)
 		goto Finish;
@@ -634,7 +651,7 @@ static int software_resume(void)
 	pr_debug("PM: Preparing processes for restore.\n");
 	error = prepare_processes();
 	if (error) {
-		swsusp_close();
+		swsusp_close(FMODE_READ);
 		goto Done;
 	}
 
@@ -649,6 +666,7 @@ static int software_resume(void)
 	thaw_processes();
  Done:
 	free_basic_memory_bitmaps();
+	usermodehelper_enable();
  Finish:
 	pm_notifier_call_chain(PM_POST_RESTORE);
 	pm_restore_console();
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 3398f4651aa1..19122cf6d827 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -14,6 +14,7 @@
 #include <linux/string.h>
 #include <linux/delay.h>
 #include <linux/errno.h>
+#include <linux/kmod.h>
 #include <linux/init.h>
 #include <linux/console.h>
 #include <linux/cpu.h>
@@ -21,6 +22,7 @@
 #include <linux/freezer.h>
 #include <linux/vmstat.h>
 #include <linux/syscalls.h>
+#include <linux/ftrace.h>
 
 #include "power.h"
 
@@ -132,6 +134,61 @@ static inline int suspend_test(int level) { return 0; }
 
 #ifdef CONFIG_SUSPEND
 
+#ifdef CONFIG_PM_TEST_SUSPEND
+
+/*
+ * We test the system suspend code by setting an RTC wakealarm a short
+ * time in the future, then suspending.  Suspending the devices won't
+ * normally take long ... some systems only need a few milliseconds.
+ *
+ * The time it takes is system-specific though, so when we test this
+ * during system bootup we allow a LOT of time.
+ */
+#define TEST_SUSPEND_SECONDS	5
+
+static unsigned long suspend_test_start_time;
+
+static void suspend_test_start(void)
+{
+	/* FIXME Use better timebase than "jiffies", ideally a clocksource.
+	 * What we want is a hardware counter that will work correctly even
+	 * during the irqs-are-off stages of the suspend/resume cycle...
+	 */
+	suspend_test_start_time = jiffies;
+}
+
+static void suspend_test_finish(const char *label)
+{
+	long nj = jiffies - suspend_test_start_time;
+	unsigned msec;
+
+	msec = jiffies_to_msecs(abs(nj));
+	pr_info("PM: %s took %d.%03d seconds\n", label,
+			msec / 1000, msec % 1000);
+
+	/* Warning on suspend means the RTC alarm period needs to be
+	 * larger -- the system was sooo slooowwww to suspend that the
+	 * alarm (should have) fired before the system went to sleep!
+	 *
+	 * Warning on either suspend or resume also means the system
+	 * has some performance issues.  The stack dump of a WARN_ON
+	 * is more likely to get the right attention than a printk...
+	 */
+	WARN_ON(msec > (TEST_SUSPEND_SECONDS * 1000));
+}
+
+#else
+
+static void suspend_test_start(void)
+{
+}
+
+static void suspend_test_finish(const char *label)
+{
+}
+
+#endif
+
 /* This is just an arbitrary number */
 #define FREE_PAGE_NUMBER (100)
 
@@ -181,6 +238,10 @@ static int suspend_prepare(void)
 	if (error)
 		goto Finish;
 
+	error = usermodehelper_disable();
+	if (error)
+		goto Finish;
+
 	if (suspend_freeze_processes()) {
 		error = -EAGAIN;
 		goto Thaw;
@@ -200,6 +261,7 @@ static int suspend_prepare(void)
 
  Thaw:
 	suspend_thaw_processes();
+	usermodehelper_enable();
  Finish:
 	pm_notifier_call_chain(PM_POST_SUSPEND);
 	pm_restore_console();
@@ -255,7 +317,7 @@ static int suspend_enter(suspend_state_t state)
  */
 int suspend_devices_and_enter(suspend_state_t state)
 {
-	int error;
+	int error, ftrace_save;
 
 	if (!suspend_ops)
 		return -ENOSYS;
@@ -266,12 +328,14 @@ int suspend_devices_and_enter(suspend_state_t state)
 			goto Close;
 	}
 	suspend_console();
+	ftrace_save = __ftrace_enabled_save();
+	suspend_test_start();
 	error = device_suspend(PMSG_SUSPEND);
 	if (error) {
 		printk(KERN_ERR "PM: Some devices failed to suspend\n");
 		goto Recover_platform;
 	}
-
+	suspend_test_finish("suspend devices");
 	if (suspend_test(TEST_DEVICES))
 		goto Recover_platform;
 
@@ -293,7 +357,10 @@ int suspend_devices_and_enter(suspend_state_t state)
 	if (suspend_ops->finish)
 		suspend_ops->finish();
  Resume_devices:
+	suspend_test_start();
 	device_resume(PMSG_RESUME);
+	suspend_test_finish("resume devices");
+	__ftrace_enabled_restore(ftrace_save);
 	resume_console();
  Close:
 	if (suspend_ops->end)
@@ -315,6 +382,7 @@ int suspend_devices_and_enter(suspend_state_t state)
 static void suspend_finish(void)
 {
 	suspend_thaw_processes();
+	usermodehelper_enable();
 	pm_notifier_call_chain(PM_POST_SUSPEND);
 	pm_restore_console();
 }
@@ -521,3 +589,144 @@ static int __init pm_init(void)
 }
 
 core_initcall(pm_init);
+
+
+#ifdef CONFIG_PM_TEST_SUSPEND
+
+#include <linux/rtc.h>
+
+/*
+ * To test system suspend, we need a hands-off mechanism to resume the
+ * system.  RTCs wake alarms are a common self-contained mechanism.
+ */
+
+static void __init test_wakealarm(struct rtc_device *rtc, suspend_state_t state)
+{
+	static char err_readtime[] __initdata =
+		KERN_ERR "PM: can't read %s time, err %d\n";
+	static char err_wakealarm [] __initdata =
+		KERN_ERR "PM: can't set %s wakealarm, err %d\n";
+	static char err_suspend[] __initdata =
+		KERN_ERR "PM: suspend test failed, error %d\n";
+	static char info_test[] __initdata =
+		KERN_INFO "PM: test RTC wakeup from '%s' suspend\n";
+
+	unsigned long		now;
+	struct rtc_wkalrm	alm;
+	int			status;
+
+	/* this may fail if the RTC hasn't been initialized */
+	status = rtc_read_time(rtc, &alm.time);
+	if (status < 0) {
+		printk(err_readtime, rtc->dev.bus_id, status);
+		return;
+	}
+	rtc_tm_to_time(&alm.time, &now);
+
+	memset(&alm, 0, sizeof alm);
+	rtc_time_to_tm(now + TEST_SUSPEND_SECONDS, &alm.time);
+	alm.enabled = true;
+
+	status = rtc_set_alarm(rtc, &alm);
+	if (status < 0) {
+		printk(err_wakealarm, rtc->dev.bus_id, status);
+		return;
+	}
+
+	if (state == PM_SUSPEND_MEM) {
+		printk(info_test, pm_states[state]);
+		status = pm_suspend(state);
+		if (status == -ENODEV)
+			state = PM_SUSPEND_STANDBY;
+	}
+	if (state == PM_SUSPEND_STANDBY) {
+		printk(info_test, pm_states[state]);
+		status = pm_suspend(state);
+	}
+	if (status < 0)
+		printk(err_suspend, status);
+
+	/* Some platforms can't detect that the alarm triggered the
+	 * wakeup, or (accordingly) disable it after it afterwards.
+	 * It's supposed to give oneshot behavior; cope.
+	 */
+	alm.enabled = false;
+	rtc_set_alarm(rtc, &alm);
+}
+
+static int __init has_wakealarm(struct device *dev, void *name_ptr)
+{
+	struct rtc_device *candidate = to_rtc_device(dev);
+
+	if (!candidate->ops->set_alarm)
+		return 0;
+	if (!device_may_wakeup(candidate->dev.parent))
+		return 0;
+
+	*(char **)name_ptr = dev->bus_id;
+	return 1;
+}
+
+/*
+ * Kernel options like "test_suspend=mem" force suspend/resume sanity tests
+ * at startup time.  They're normally disabled, for faster boot and because
+ * we can't know which states really work on this particular system.
+ */
+static suspend_state_t test_state __initdata = PM_SUSPEND_ON;
+
+static char warn_bad_state[] __initdata =
+	KERN_WARNING "PM: can't test '%s' suspend state\n";
+
+static int __init setup_test_suspend(char *value)
+{
+	unsigned i;
+
+	/* "=mem" ==> "mem" */
+	value++;
+	for (i = 0; i < PM_SUSPEND_MAX; i++) {
+		if (!pm_states[i])
+			continue;
+		if (strcmp(pm_states[i], value) != 0)
+			continue;
+		test_state = (__force suspend_state_t) i;
+		return 0;
+	}
+	printk(warn_bad_state, value);
+	return 0;
+}
+__setup("test_suspend", setup_test_suspend);
+
+static int __init test_suspend(void)
+{
+	static char		warn_no_rtc[] __initdata =
+		KERN_WARNING "PM: no wakealarm-capable RTC driver is ready\n";
+
+	char			*pony = NULL;
+	struct rtc_device	*rtc = NULL;
+
+	/* PM is initialized by now; is that state testable? */
+	if (test_state == PM_SUSPEND_ON)
+		goto done;
+	if (!valid_state(test_state)) {
+		printk(warn_bad_state, pm_states[test_state]);
+		goto done;
+	}
+
+	/* RTCs have initialized by now too ... can we use one? */
+	class_find_device(rtc_class, NULL, &pony, has_wakealarm);
+	if (pony)
+		rtc = rtc_class_open(pony);
+	if (!rtc) {
+		printk(warn_no_rtc);
+		goto done;
+	}
+
+	/* go for it */
+	test_wakealarm(rtc, test_state);
+	rtc_class_close(rtc);
+done:
+	return 0;
+}
+late_initcall(test_suspend);
+
+#endif /* CONFIG_PM_TEST_SUSPEND */
diff --git a/kernel/power/power.h b/kernel/power/power.h
index 700f44ec8406..46b5ec7a3afb 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -53,8 +53,6 @@ extern int hibernation_platform_enter(void);
 
 extern int pfn_is_nosave(unsigned long);
 
-extern struct mutex pm_mutex;
-
 #define power_attr(_name) \
 static struct kobj_attribute _name##_attr = {	\
 	.attr	= {				\
@@ -155,7 +153,7 @@ extern int swsusp_shrink_memory(void);
 extern void swsusp_free(void);
 extern int swsusp_read(unsigned int *flags_p);
 extern int swsusp_write(unsigned int flags);
-extern void swsusp_close(void);
+extern void swsusp_close(fmode_t);
 
 struct timeval;
 /* kernel/power/swsusp.c */
diff --git a/kernel/power/poweroff.c b/kernel/power/poweroff.c
index 678ec736076b..72016f051477 100644
--- a/kernel/power/poweroff.c
+++ b/kernel/power/poweroff.c
@@ -10,6 +10,7 @@
 #include <linux/pm.h>
 #include <linux/workqueue.h>
 #include <linux/reboot.h>
+#include <linux/cpumask.h>
 
 /*
  * When the user hits Sys-Rq o to power down the machine this is the
@@ -25,7 +26,8 @@ static DECLARE_WORK(poweroff_work, do_poweroff);
 
 static void handle_poweroff(int key, struct tty_struct *tty)
 {
-	schedule_work(&poweroff_work);
+	/* run sysrq poweroff on boot cpu */
+	schedule_work_on(first_cpu(cpu_online_map), &poweroff_work);
 }
 
 static struct sysrq_key_op	sysrq_poweroff_op = {
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 5fb87652f214..ca634019497a 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -28,128 +28,13 @@ static inline int freezeable(struct task_struct * p)
 	return 1;
 }
 
-/*
- * freezing is complete, mark current process as frozen
- */
-static inline void frozen_process(void)
-{
-	if (!unlikely(current->flags & PF_NOFREEZE)) {
-		current->flags |= PF_FROZEN;
-		wmb();
-	}
-	clear_freeze_flag(current);
-}
-
-/* Refrigerator is place where frozen processes are stored :-). */
-void refrigerator(void)
-{
-	/* Hmm, should we be allowed to suspend when there are realtime
-	   processes around? */
-	long save;
-
-	task_lock(current);
-	if (freezing(current)) {
-		frozen_process();
-		task_unlock(current);
-	} else {
-		task_unlock(current);
-		return;
-	}
-	save = current->state;
-	pr_debug("%s entered refrigerator\n", current->comm);
-
-	spin_lock_irq(&current->sighand->siglock);
-	recalc_sigpending(); /* We sent fake signal, clean it up */
-	spin_unlock_irq(&current->sighand->siglock);
-
-	for (;;) {
-		set_current_state(TASK_UNINTERRUPTIBLE);
-		if (!frozen(current))
-			break;
-		schedule();
-	}
-	pr_debug("%s left refrigerator\n", current->comm);
-	__set_current_state(save);
-}
-
-static void fake_signal_wake_up(struct task_struct *p)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&p->sighand->siglock, flags);
-	signal_wake_up(p, 0);
-	spin_unlock_irqrestore(&p->sighand->siglock, flags);
-}
-
-static inline bool should_send_signal(struct task_struct *p)
-{
-	return !(p->flags & PF_FREEZER_NOSIG);
-}
-
-/**
- *	freeze_task - send a freeze request to given task
- *	@p: task to send the request to
- *	@sig_only: if set, the request will only be sent if the task has the
- *		PF_FREEZER_NOSIG flag unset
- *	Return value: 'false', if @sig_only is set and the task has
- *		PF_FREEZER_NOSIG set or the task is frozen, 'true', otherwise
- *
- *	The freeze request is sent by setting the tasks's TIF_FREEZE flag and
- *	either sending a fake signal to it or waking it up, depending on whether
- *	or not it has PF_FREEZER_NOSIG set.  If @sig_only is set and the task
- *	has PF_FREEZER_NOSIG set (ie. it is a typical kernel thread), its
- *	TIF_FREEZE flag will not be set.
- */
-static bool freeze_task(struct task_struct *p, bool sig_only)
-{
-	/*
-	 * We first check if the task is freezing and next if it has already
-	 * been frozen to avoid the race with frozen_process() which first marks
-	 * the task as frozen and next clears its TIF_FREEZE.
-	 */
-	if (!freezing(p)) {
-		rmb();
-		if (frozen(p))
-			return false;
-
-		if (!sig_only || should_send_signal(p))
-			set_freeze_flag(p);
-		else
-			return false;
-	}
-
-	if (should_send_signal(p)) {
-		if (!signal_pending(p))
-			fake_signal_wake_up(p);
-	} else if (sig_only) {
-		return false;
-	} else {
-		wake_up_state(p, TASK_INTERRUPTIBLE);
-	}
-
-	return true;
-}
-
-static void cancel_freezing(struct task_struct *p)
-{
-	unsigned long flags;
-
-	if (freezing(p)) {
-		pr_debug("  clean up: %s\n", p->comm);
-		clear_freeze_flag(p);
-		spin_lock_irqsave(&p->sighand->siglock, flags);
-		recalc_sigpending_and_wake(p);
-		spin_unlock_irqrestore(&p->sighand->siglock, flags);
-	}
-}
-
 static int try_to_freeze_tasks(bool sig_only)
 {
 	struct task_struct *g, *p;
 	unsigned long end_time;
 	unsigned int todo;
 	struct timeval start, end;
-	s64 elapsed_csecs64;
+	u64 elapsed_csecs64;
 	unsigned int elapsed_csecs;
 
 	do_gettimeofday(&start);
@@ -250,6 +135,9 @@ static void thaw_tasks(bool nosig_only)
 		if (nosig_only && should_send_signal(p))
 			continue;
 
+		if (cgroup_frozen(p))
+			continue;
+
 		thaw_process(p);
 	} while_each_thread(g, p);
 	read_unlock(&tasklist_lock);
@@ -264,4 +152,3 @@ void thaw_processes(void)
 	printk("done.\n");
 }
 
-EXPORT_SYMBOL(refrigerator);
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 5f91a07c4eac..5d2ab836e998 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -205,8 +205,7 @@ static void chain_free(struct chain_allocator *ca, int clear_page_nosave)
  *	objects.  The main list's elements are of type struct zone_bitmap
  *	and each of them corresonds to one zone.  For each zone bitmap
  *	object there is a list of objects of type struct bm_block that
- *	represent each blocks of bit chunks in which information is
- *	stored.
+ *	represent each blocks of bitmap in which information is stored.
  *
  *	struct memory_bitmap contains a pointer to the main list of zone
  *	bitmap objects, a struct bm_position used for browsing the bitmap,
@@ -224,26 +223,27 @@ static void chain_free(struct chain_allocator *ca, int clear_page_nosave)
  *	pfns that correspond to the start and end of the represented zone.
  *
  *	struct bm_block contains a pointer to the memory page in which
- *	information is stored (in the form of a block of bit chunks
- *	of type unsigned long each).  It also contains the pfns that
- *	correspond to the start and end of the represented memory area and
- *	the number of bit chunks in the block.
+ *	information is stored (in the form of a block of bitmap)
+ *	It also contains the pfns that correspond to the start and end of
+ *	the represented memory area.
  */
 
 #define BM_END_OF_MAP	(~0UL)
 
-#define BM_CHUNKS_PER_BLOCK	(PAGE_SIZE / sizeof(long))
-#define BM_BITS_PER_CHUNK	(sizeof(long) << 3)
 #define BM_BITS_PER_BLOCK	(PAGE_SIZE << 3)
 
 struct bm_block {
 	struct bm_block *next;		/* next element of the list */
 	unsigned long start_pfn;	/* pfn represented by the first bit */
 	unsigned long end_pfn;	/* pfn represented by the last bit plus 1 */
-	unsigned int size;	/* number of bit chunks */
-	unsigned long *data;	/* chunks of bits representing pages */
+	unsigned long *data;	/* bitmap representing pages */
 };
 
+static inline unsigned long bm_block_bits(struct bm_block *bb)
+{
+	return bb->end_pfn - bb->start_pfn;
+}
+
 struct zone_bitmap {
 	struct zone_bitmap *next;	/* next element of the list */
 	unsigned long start_pfn;	/* minimal pfn in this zone */
@@ -257,7 +257,6 @@ struct zone_bitmap {
 struct bm_position {
 	struct zone_bitmap *zone_bm;
 	struct bm_block *block;
-	int chunk;
 	int bit;
 };
 
@@ -272,12 +271,6 @@ struct memory_bitmap {
 
 /* Functions that operate on memory bitmaps */
 
-static inline void memory_bm_reset_chunk(struct memory_bitmap *bm)
-{
-	bm->cur.chunk = 0;
-	bm->cur.bit = -1;
-}
-
 static void memory_bm_position_reset(struct memory_bitmap *bm)
 {
 	struct zone_bitmap *zone_bm;
@@ -285,7 +278,7 @@ static void memory_bm_position_reset(struct memory_bitmap *bm)
 	zone_bm = bm->zone_bm_list;
 	bm->cur.zone_bm = zone_bm;
 	bm->cur.block = zone_bm->bm_blocks;
-	memory_bm_reset_chunk(bm);
+	bm->cur.bit = 0;
 }
 
 static void memory_bm_free(struct memory_bitmap *bm, int clear_nosave_free);
@@ -394,12 +387,10 @@ memory_bm_create(struct memory_bitmap *bm, gfp_t gfp_mask, int safe_needed)
 			bb->start_pfn = pfn;
 			if (nr >= BM_BITS_PER_BLOCK) {
 				pfn += BM_BITS_PER_BLOCK;
-				bb->size = BM_CHUNKS_PER_BLOCK;
 				nr -= BM_BITS_PER_BLOCK;
 			} else {
 				/* This is executed only once in the loop */
 				pfn += nr;
-				bb->size = DIV_ROUND_UP(nr, BM_BITS_PER_CHUNK);
 			}
 			bb->end_pfn = pfn;
 			bb = bb->next;
@@ -478,8 +469,8 @@ static int memory_bm_find_bit(struct memory_bitmap *bm, unsigned long pfn,
 	}
 	zone_bm->cur_block = bb;
 	pfn -= bb->start_pfn;
-	*bit_nr = pfn % BM_BITS_PER_CHUNK;
-	*addr = bb->data + pfn / BM_BITS_PER_CHUNK;
+	*bit_nr = pfn;
+	*addr = bb->data;
 	return 0;
 }
 
@@ -528,36 +519,6 @@ static int memory_bm_test_bit(struct memory_bitmap *bm, unsigned long pfn)
 	return test_bit(bit, addr);
 }
 
-/* Two auxiliary functions for memory_bm_next_pfn */
-
-/* Find the first set bit in the given chunk, if there is one */
-
-static inline int next_bit_in_chunk(int bit, unsigned long *chunk_p)
-{
-	bit++;
-	while (bit < BM_BITS_PER_CHUNK) {
-		if (test_bit(bit, chunk_p))
-			return bit;
-
-		bit++;
-	}
-	return -1;
-}
-
-/* Find a chunk containing some bits set in given block of bits */
-
-static inline int next_chunk_in_block(int n, struct bm_block *bb)
-{
-	n++;
-	while (n < bb->size) {
-		if (bb->data[n])
-			return n;
-
-		n++;
-	}
-	return -1;
-}
-
 /**
  *	memory_bm_next_pfn - find the pfn that corresponds to the next set bit
  *	in the bitmap @bm.  If the pfn cannot be found, BM_END_OF_MAP is
@@ -571,40 +532,33 @@ static unsigned long memory_bm_next_pfn(struct memory_bitmap *bm)
 {
 	struct zone_bitmap *zone_bm;
 	struct bm_block *bb;
-	int chunk;
 	int bit;
 
 	do {
 		bb = bm->cur.block;
 		do {
-			chunk = bm->cur.chunk;
 			bit = bm->cur.bit;
-			do {
-				bit = next_bit_in_chunk(bit, bb->data + chunk);
-				if (bit >= 0)
-					goto Return_pfn;
-
-				chunk = next_chunk_in_block(chunk, bb);
-				bit = -1;
-			} while (chunk >= 0);
+			bit = find_next_bit(bb->data, bm_block_bits(bb), bit);
+			if (bit < bm_block_bits(bb))
+				goto Return_pfn;
+
 			bb = bb->next;
 			bm->cur.block = bb;
-			memory_bm_reset_chunk(bm);
+			bm->cur.bit = 0;
 		} while (bb);
 		zone_bm = bm->cur.zone_bm->next;
 		if (zone_bm) {
 			bm->cur.zone_bm = zone_bm;
 			bm->cur.block = zone_bm->bm_blocks;
-			memory_bm_reset_chunk(bm);
+			bm->cur.bit = 0;
 		}
 	} while (zone_bm);
 	memory_bm_position_reset(bm);
 	return BM_END_OF_MAP;
 
  Return_pfn:
-	bm->cur.chunk = chunk;
-	bm->cur.bit = bit;
-	return bb->start_pfn + chunk * BM_BITS_PER_CHUNK + bit;
+	bm->cur.bit = bit + 1;
+	return bb->start_pfn + bit;
 }
 
 /**
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index a0abf9a463f9..b7713b53d07a 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -14,7 +14,6 @@
 #include <linux/module.h>
 #include <linux/file.h>
 #include <linux/utsname.h>
-#include <linux/version.h>
 #include <linux/delay.h>
 #include <linux/bitops.h>
 #include <linux/genhd.h>
@@ -173,13 +172,13 @@ static int swsusp_swap_check(void) /* This is called before saving image */
 		return res;
 
 	root_swap = res;
-	res = blkdev_get(resume_bdev, FMODE_WRITE, O_RDWR);
+	res = blkdev_get(resume_bdev, FMODE_WRITE);
 	if (res)
 		return res;
 
 	res = set_blocksize(resume_bdev, PAGE_SIZE);
 	if (res < 0)
-		blkdev_put(resume_bdev);
+		blkdev_put(resume_bdev, FMODE_WRITE);
 
 	return res;
 }
@@ -427,7 +426,7 @@ int swsusp_write(unsigned int flags)
 
 	release_swap_writer(&handle);
  out:
-	swsusp_close();
+	swsusp_close(FMODE_WRITE);
 	return error;
 }
 
@@ -575,7 +574,7 @@ int swsusp_read(unsigned int *flags_p)
 		error = load_image(&handle, &snapshot, header->pages - 1);
 	release_swap_reader(&handle);
 
-	blkdev_put(resume_bdev);
+	blkdev_put(resume_bdev, FMODE_READ);
 
 	if (!error)
 		pr_debug("PM: Image successfully loaded\n");
@@ -610,7 +609,7 @@ int swsusp_check(void)
 			return -EINVAL;
 		}
 		if (error)
-			blkdev_put(resume_bdev);
+			blkdev_put(resume_bdev, FMODE_READ);
 		else
 			pr_debug("PM: Signature found, resuming\n");
 	} else {
@@ -627,14 +626,14 @@ int swsusp_check(void)
  *	swsusp_close - close swap device.
  */
 
-void swsusp_close(void)
+void swsusp_close(fmode_t mode)
 {
 	if (IS_ERR(resume_bdev)) {
 		pr_debug("PM: Image device not initialised\n");
 		return;
 	}
 
-	blkdev_put(resume_bdev);
+	blkdev_put(resume_bdev, mode); /* move up */
 }
 
 static int swsusp_header_init(void)
diff --git a/kernel/power/user.c b/kernel/power/user.c
index a6332a313262..005b93d839ba 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -212,13 +212,20 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
 	case SNAPSHOT_FREEZE:
 		if (data->frozen)
 			break;
+
 		printk("Syncing filesystems ... ");
 		sys_sync();
 		printk("done.\n");
 
-		error = freeze_processes();
+		error = usermodehelper_disable();
 		if (error)
+			break;
+
+		error = freeze_processes();
+		if (error) {
 			thaw_processes();
+			usermodehelper_enable();
+		}
 		if (!error)
 			data->frozen = 1;
 		break;
@@ -227,6 +234,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
 		if (!data->frozen || data->ready)
 			break;
 		thaw_processes();
+		usermodehelper_enable();
 		data->frozen = 0;
 		break;