Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/suspend-2.6

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/suspend-2.6:
  PM: PM QOS update fix
  Freezer / cgroup freezer: Update stale locking comments
  PM / platform_bus: Allow runtime PM by default
  i2c: Fix bus-level power management callbacks
  PM QOS update
  PM / Hibernate: Fix block_io.c printk warning
  PM / Hibernate: Group swap ops
  PM / Hibernate: Move the first_sector out of swsusp_write
  PM / Hibernate: Separate block_io
  PM / Hibernate: Snapshot cleanup
  FS / libfs: Implement simple_write_to_buffer
  PM / Hibernate: document open(/dev/snapshot) side effects
  PM / Runtime: Add sysfs debug files
  PM: Improve device power management document
  PM: Update device power management document
  PM: Allow runtime_suspend methods to call pm_schedule_suspend()
  PM: pm_wakeup - switch to using bool

8 files changed, 456 insertions, 431 deletions

diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c
index e5c0244962b0..ce71ed53e88f 100644
--- a/kernel/cgroup_freezer.c
+++ b/kernel/cgroup_freezer.c
@@ -89,10 +89,10 @@ struct cgroup_subsys freezer_subsys;
 
 /* Locks taken and their ordering
  * ------------------------------
- * css_set_lock
  * cgroup_mutex (AKA cgroup_lock)
- * task->alloc_lock (AKA task_lock)
  * freezer->lock
+ * css_set_lock
+ * task->alloc_lock (AKA task_lock)
  * task->sighand->siglock
  *
  * cgroup code forces css_set_lock to be taken before task->alloc_lock
@@ -100,33 +100,38 @@ struct cgroup_subsys freezer_subsys;
  * freezer_create(), freezer_destroy():
  * cgroup_mutex [ by cgroup core ]
  *
- * can_attach():
- * cgroup_mutex
+ * freezer_can_attach():
+ * cgroup_mutex (held by caller of can_attach)
  *
- * cgroup_frozen():
+ * cgroup_freezing_or_frozen():
  * task->alloc_lock (to get task's cgroup)
  *
  * freezer_fork() (preserving fork() performance means can't take cgroup_mutex):
- * task->alloc_lock (to get task's cgroup)
  * freezer->lock
  *  sighand->siglock (if the cgroup is freezing)
  *
  * freezer_read():
  * cgroup_mutex
  *  freezer->lock
+ *   write_lock css_set_lock (cgroup iterator start)
+ *    task->alloc_lock
  *   read_lock css_set_lock (cgroup iterator start)
  *
  * freezer_write() (freeze):
  * cgroup_mutex
  *  freezer->lock
+ *   write_lock css_set_lock (cgroup iterator start)
+ *    task->alloc_lock
  *   read_lock css_set_lock (cgroup iterator start)
- *    sighand->siglock
+ *    sighand->siglock (fake signal delivery inside freeze_task())
  *
  * freezer_write() (unfreeze):
  * cgroup_mutex
  *  freezer->lock
+ *   write_lock css_set_lock (cgroup iterator start)
+ *    task->alloc_lock
  *   read_lock css_set_lock (cgroup iterator start)
- *    task->alloc_lock (to prevent races with freeze_task())
+ *    task->alloc_lock (inside thaw_process(), prevents race with refrigerator())
  *     sighand->siglock
  */
 static struct cgroup_subsys_state *freezer_create(struct cgroup_subsys *ss,
diff --git a/kernel/pm_qos_params.c b/kernel/pm_qos_params.c
index 3db49b9ca374..f42d3f737a33 100644
--- a/kernel/pm_qos_params.c
+++ b/kernel/pm_qos_params.c
@@ -2,7 +2,7 @@
  * This module exposes the interface to kernel space for specifying
  * QoS dependencies.  It provides infrastructure for registration of:
  *
- * Dependents on a QoS value : register requirements
+ * Dependents on a QoS value : register requests
  * Watchers of QoS value : get notified when target QoS value changes
  *
  * This QoS design is best effort based.  Dependents register their QoS needs.
@@ -14,19 +14,21 @@
  * timeout: usec <-- currently not used.
  * throughput: kbs (kilo byte / sec)
  *
- * There are lists of pm_qos_objects each one wrapping requirements, notifiers
+ * There are lists of pm_qos_objects each one wrapping requests, notifiers
  *
- * User mode requirements on a QOS parameter register themselves to the
+ * User mode requests on a QOS parameter register themselves to the
  * subsystem by opening the device node /dev/... and writing there request to
  * the node.  As long as the process holds a file handle open to the node the
  * client continues to be accounted for.  Upon file release the usermode
- * requirement is removed and a new qos target is computed.  This way when the
- * requirement that the application has is cleaned up when closes the file
+ * request is removed and a new qos target is computed.  This way when the
+ * request that the application has is cleaned up when closes the file
  * pointer or exits the pm_qos_object will get an opportunity to clean up.
  *
  * Mark Gross <mgross@linux.intel.com>
  */
 
+/*#define DEBUG*/
+
 #include <linux/pm_qos_params.h>
 #include <linux/sched.h>
 #include <linux/spinlock.h>
@@ -42,25 +44,25 @@
 #include <linux/uaccess.h>
 
 /*
- * locking rule: all changes to requirements or notifiers lists
+ * locking rule: all changes to requests or notifiers lists
  * or pm_qos_object list and pm_qos_objects need to happen with pm_qos_lock
  * held, taken with _irqsave.  One lock to rule them all
  */
-struct requirement_list {
+struct pm_qos_request_list {
 	struct list_head list;
 	union {
 		s32 value;
 		s32 usec;
 		s32 kbps;
 	};
-	char *name;
+	int pm_qos_class;
 };
 
 static s32 max_compare(s32 v1, s32 v2);
 static s32 min_compare(s32 v1, s32 v2);
 
 struct pm_qos_object {
-	struct requirement_list requirements;
+	struct pm_qos_request_list requests;
 	struct blocking_notifier_head *notifiers;
 	struct miscdevice pm_qos_power_miscdev;
 	char *name;
@@ -72,7 +74,7 @@ struct pm_qos_object {
 static struct pm_qos_object null_pm_qos;
 static BLOCKING_NOTIFIER_HEAD(cpu_dma_lat_notifier);
 static struct pm_qos_object cpu_dma_pm_qos = {
-	.requirements = {LIST_HEAD_INIT(cpu_dma_pm_qos.requirements.list)},
+	.requests = {LIST_HEAD_INIT(cpu_dma_pm_qos.requests.list)},
 	.notifiers = &cpu_dma_lat_notifier,
 	.name = "cpu_dma_latency",
 	.default_value = 2000 * USEC_PER_SEC,
@@ -82,7 +84,7 @@ static struct pm_qos_object cpu_dma_pm_qos = {
 
 static BLOCKING_NOTIFIER_HEAD(network_lat_notifier);
 static struct pm_qos_object network_lat_pm_qos = {
-	.requirements = {LIST_HEAD_INIT(network_lat_pm_qos.requirements.list)},
+	.requests = {LIST_HEAD_INIT(network_lat_pm_qos.requests.list)},
 	.notifiers = &network_lat_notifier,
 	.name = "network_latency",
 	.default_value = 2000 * USEC_PER_SEC,
@@ -93,8 +95,7 @@ static struct pm_qos_object network_lat_pm_qos = {
 
 static BLOCKING_NOTIFIER_HEAD(network_throughput_notifier);
 static struct pm_qos_object network_throughput_pm_qos = {
-	.requirements =
-		{LIST_HEAD_INIT(network_throughput_pm_qos.requirements.list)},
+	.requests = {LIST_HEAD_INIT(network_throughput_pm_qos.requests.list)},
 	.notifiers = &network_throughput_notifier,
 	.name = "network_throughput",
 	.default_value = 0,
@@ -135,31 +136,34 @@ static s32 min_compare(s32 v1, s32 v2)
 }
 
 
-static void update_target(int target)
+static void update_target(int pm_qos_class)
 {
 	s32 extreme_value;
-	struct requirement_list *node;
+	struct pm_qos_request_list *node;
 	unsigned long flags;
 	int call_notifier = 0;
 
 	spin_lock_irqsave(&pm_qos_lock, flags);
-	extreme_value = pm_qos_array[target]->default_value;
+	extreme_value = pm_qos_array[pm_qos_class]->default_value;
 	list_for_each_entry(node,
-			&pm_qos_array[target]->requirements.list, list) {
-		extreme_value = pm_qos_array[target]->comparitor(
+			&pm_qos_array[pm_qos_class]->requests.list, list) {
+		extreme_value = pm_qos_array[pm_qos_class]->comparitor(
 				extreme_value, node->value);
 	}
-	if (atomic_read(&pm_qos_array[target]->target_value) != extreme_value) {
+	if (atomic_read(&pm_qos_array[pm_qos_class]->target_value) !=
+			extreme_value) {
 		call_notifier = 1;
-		atomic_set(&pm_qos_array[target]->target_value, extreme_value);
-		pr_debug(KERN_ERR "new target for qos %d is %d\n", target,
-			atomic_read(&pm_qos_array[target]->target_value));
+		atomic_set(&pm_qos_array[pm_qos_class]->target_value,
+				extreme_value);
+		pr_debug(KERN_ERR "new target for qos %d is %d\n", pm_qos_class,
+			atomic_read(&pm_qos_array[pm_qos_class]->target_value));
 	}
 	spin_unlock_irqrestore(&pm_qos_lock, flags);
 
 	if (call_notifier)
-		blocking_notifier_call_chain(pm_qos_array[target]->notifiers,
-			(unsigned long) extreme_value, NULL);
+		blocking_notifier_call_chain(
+				pm_qos_array[pm_qos_class]->notifiers,
+					(unsigned long) extreme_value, NULL);
 }
 
 static int register_pm_qos_misc(struct pm_qos_object *qos)
@@ -185,125 +189,112 @@ static int find_pm_qos_object_by_minor(int minor)
 }
 
 /**
- * pm_qos_requirement - returns current system wide qos expectation
+ * pm_qos_request - returns current system wide qos expectation
  * @pm_qos_class: identification of which qos value is requested
  *
  * This function returns the current target value in an atomic manner.
  */
-int pm_qos_requirement(int pm_qos_class)
+int pm_qos_request(int pm_qos_class)
 {
 	return atomic_read(&pm_qos_array[pm_qos_class]->target_value);
 }
-EXPORT_SYMBOL_GPL(pm_qos_requirement);
+EXPORT_SYMBOL_GPL(pm_qos_request);
 
 /**
- * pm_qos_add_requirement - inserts new qos request into the list
+ * pm_qos_add_request - inserts new qos request into the list
  * @pm_qos_class: identifies which list of qos request to us
- * @name: identifies the request
  * @value: defines the qos request
  *
  * This function inserts a new entry in the pm_qos_class list of requested qos
  * performance characteristics.  It recomputes the aggregate QoS expectations
- * for the pm_qos_class of parameters.
+ * for the pm_qos_class of parameters, and returns the pm_qos_request list
+ * element as a handle for use in updating and removal.  Call needs to save
+ * this handle for later use.
  */
-int pm_qos_add_requirement(int pm_qos_class, char *name, s32 value)
+struct pm_qos_request_list *pm_qos_add_request(int pm_qos_class, s32 value)
 {
-	struct requirement_list *dep;
+	struct pm_qos_request_list *dep;
 	unsigned long flags;
 
-	dep = kzalloc(sizeof(struct requirement_list), GFP_KERNEL);
+	dep = kzalloc(sizeof(struct pm_qos_request_list), GFP_KERNEL);
 	if (dep) {
 		if (value == PM_QOS_DEFAULT_VALUE)
 			dep->value = pm_qos_array[pm_qos_class]->default_value;
 		else
 			dep->value = value;
-		dep->name = kstrdup(name, GFP_KERNEL);
-		if (!dep->name)
-			goto cleanup;
+		dep->pm_qos_class = pm_qos_class;
 
 		spin_lock_irqsave(&pm_qos_lock, flags);
 		list_add(&dep->list,
-			&pm_qos_array[pm_qos_class]->requirements.list);
+			&pm_qos_array[pm_qos_class]->requests.list);
 		spin_unlock_irqrestore(&pm_qos_lock, flags);
 		update_target(pm_qos_class);
-
-		return 0;
 	}
 
-cleanup:
-	kfree(dep);
-	return -ENOMEM;
+	return dep;
 }
-EXPORT_SYMBOL_GPL(pm_qos_add_requirement);
+EXPORT_SYMBOL_GPL(pm_qos_add_request);
 
 /**
- * pm_qos_update_requirement - modifies an existing qos request
- * @pm_qos_class: identifies which list of qos request to us
- * @name: identifies the request
+ * pm_qos_update_request - modifies an existing qos request
+ * @pm_qos_req : handle to list element holding a pm_qos request to use
  * @value: defines the qos request
  *
- * Updates an existing qos requirement for the pm_qos_class of parameters along
+ * Updates an existing qos request for the pm_qos_class of parameters along
  * with updating the target pm_qos_class value.
  *
- * If the named request isn't in the list then no change is made.
+ * Attempts are made to make this code callable on hot code paths.
  */
-int pm_qos_update_requirement(int pm_qos_class, char *name, s32 new_value)
+void pm_qos_update_request(struct pm_qos_request_list *pm_qos_req,
+		s32 new_value)
 {
 	unsigned long flags;
-	struct requirement_list *node;
 	int pending_update = 0;
+	s32 temp;
 
-	spin_lock_irqsave(&pm_qos_lock, flags);
-	list_for_each_entry(node,
-		&pm_qos_array[pm_qos_class]->requirements.list, list) {
-		if (strcmp(node->name, name) == 0) {
-			if (new_value == PM_QOS_DEFAULT_VALUE)
-				node->value =
-				pm_qos_array[pm_qos_class]->default_value;
-			else
-				node->value = new_value;
+	if (pm_qos_req) { /*guard against callers passing in null */
+		spin_lock_irqsave(&pm_qos_lock, flags);
+		if (new_value == PM_QOS_DEFAULT_VALUE)
+			temp = pm_qos_array[pm_qos_req->pm_qos_class]->default_value;
+		else
+			temp = new_value;
+
+		if (temp != pm_qos_req->value) {
 			pending_update = 1;
-			break;
+			pm_qos_req->value = temp;
 		}
+		spin_unlock_irqrestore(&pm_qos_lock, flags);
+		if (pending_update)
+			update_target(pm_qos_req->pm_qos_class);
 	}
-	spin_unlock_irqrestore(&pm_qos_lock, flags);
-	if (pending_update)
-		update_target(pm_qos_class);
-
-	return 0;
 }
-EXPORT_SYMBOL_GPL(pm_qos_update_requirement);
+EXPORT_SYMBOL_GPL(pm_qos_update_request);
 
 /**
- * pm_qos_remove_requirement - modifies an existing qos request
- * @pm_qos_class: identifies which list of qos request to us
- * @name: identifies the request
+ * pm_qos_remove_request - modifies an existing qos request
+ * @pm_qos_req: handle to request list element
  *
- * Will remove named qos request from pm_qos_class list of parameters and
- * recompute the current target value for the pm_qos_class.
+ * Will remove pm qos request from the list of requests and
+ * recompute the current target value for the pm_qos_class.  Call this
+ * on slow code paths.
  */
-void pm_qos_remove_requirement(int pm_qos_class, char *name)
+void pm_qos_remove_request(struct pm_qos_request_list *pm_qos_req)
 {
 	unsigned long flags;
-	struct requirement_list *node;
-	int pending_update = 0;
+	int qos_class;
 
+	if (pm_qos_req == NULL)
+		return;
+		/* silent return to keep pcm code cleaner */
+
+	qos_class = pm_qos_req->pm_qos_class;
 	spin_lock_irqsave(&pm_qos_lock, flags);
-	list_for_each_entry(node,
-		&pm_qos_array[pm_qos_class]->requirements.list, list) {
-		if (strcmp(node->name, name) == 0) {
-			kfree(node->name);
-			list_del(&node->list);
-			kfree(node);
-			pending_update = 1;
-			break;
-		}
-	}
+	list_del(&pm_qos_req->list);
+	kfree(pm_qos_req);
 	spin_unlock_irqrestore(&pm_qos_lock, flags);
-	if (pending_update)
-		update_target(pm_qos_class);
+	update_target(qos_class);
 }
-EXPORT_SYMBOL_GPL(pm_qos_remove_requirement);
+EXPORT_SYMBOL_GPL(pm_qos_remove_request);
 
 /**
  * pm_qos_add_notifier - sets notification entry for changes to target value
@@ -313,7 +304,7 @@ EXPORT_SYMBOL_GPL(pm_qos_remove_requirement);
  * will register the notifier into a notification chain that gets called
  * upon changes to the pm_qos_class target value.
  */
- int pm_qos_add_notifier(int pm_qos_class, struct notifier_block *notifier)
+int pm_qos_add_notifier(int pm_qos_class, struct notifier_block *notifier)
 {
 	int retval;
 
@@ -343,21 +334,16 @@ int pm_qos_remove_notifier(int pm_qos_class, struct notifier_block *notifier)
 }
 EXPORT_SYMBOL_GPL(pm_qos_remove_notifier);
 
-#define PID_NAME_LEN 32
-
 static int pm_qos_power_open(struct inode *inode, struct file *filp)
 {
-	int ret;
 	long pm_qos_class;
-	char name[PID_NAME_LEN];
 
 	pm_qos_class = find_pm_qos_object_by_minor(iminor(inode));
 	if (pm_qos_class >= 0) {
-		filp->private_data = (void *)pm_qos_class;
-		snprintf(name, PID_NAME_LEN, "process_%d", current->pid);
-		ret = pm_qos_add_requirement(pm_qos_class, name,
-					PM_QOS_DEFAULT_VALUE);
-		if (ret >= 0)
+		filp->private_data = (void *) pm_qos_add_request(pm_qos_class,
+				PM_QOS_DEFAULT_VALUE);
+
+		if (filp->private_data)
 			return 0;
 	}
 	return -EPERM;
@@ -365,32 +351,40 @@ static int pm_qos_power_open(struct inode *inode, struct file *filp)
 
 static int pm_qos_power_release(struct inode *inode, struct file *filp)
 {
-	int pm_qos_class;
-	char name[PID_NAME_LEN];
+	struct pm_qos_request_list *req;
 
-	pm_qos_class = (long)filp->private_data;
-	snprintf(name, PID_NAME_LEN, "process_%d", current->pid);
-	pm_qos_remove_requirement(pm_qos_class, name);
+	req = (struct pm_qos_request_list *)filp->private_data;
+	pm_qos_remove_request(req);
 
 	return 0;
 }
 
+
 static ssize_t pm_qos_power_write(struct file *filp, const char __user *buf,
 		size_t count, loff_t *f_pos)
 {
 	s32 value;
-	int pm_qos_class;
-	char name[PID_NAME_LEN];
-
-	pm_qos_class = (long)filp->private_data;
-	if (count != sizeof(s32))
+	int x;
+	char ascii_value[11];
+	struct pm_qos_request_list *pm_qos_req;
+
+	if (count == sizeof(s32)) {
+		if (copy_from_user(&value, buf, sizeof(s32)))
+			return -EFAULT;
+	} else if (count == 11) { /* len('0x12345678/0') */
+		if (copy_from_user(ascii_value, buf, 11))
+			return -EFAULT;
+		x = sscanf(ascii_value, "%x", &value);
+		if (x != 1)
+			return -EINVAL;
+		pr_debug(KERN_ERR "%s, %d, 0x%x\n", ascii_value, x, value);
+	} else
 		return -EINVAL;
-	if (copy_from_user(&value, buf, sizeof(s32)))
-		return -EFAULT;
-	snprintf(name, PID_NAME_LEN, "process_%d", current->pid);
-	pm_qos_update_requirement(pm_qos_class, name, value);
 
-	return  sizeof(s32);
+	pm_qos_req = (struct pm_qos_request_list *)filp->private_data;
+	pm_qos_update_request(pm_qos_req, value);
+
+	return count;
 }
 
 
diff --git a/kernel/power/Makefile b/kernel/power/Makefile
index 43191815f874..524e058dcf06 100644
--- a/kernel/power/Makefile
+++ b/kernel/power/Makefile
@@ -8,7 +8,8 @@ obj-$(CONFIG_PM_SLEEP)		+= console.o
 obj-$(CONFIG_FREEZER)		+= process.o
 obj-$(CONFIG_SUSPEND)		+= suspend.o
 obj-$(CONFIG_PM_TEST_SUSPEND)	+= suspend_test.o
-obj-$(CONFIG_HIBERNATION)	+= hibernate.o snapshot.o swap.o user.o
+obj-$(CONFIG_HIBERNATION)	+= hibernate.o snapshot.o swap.o user.o \
+				   block_io.o
 obj-$(CONFIG_HIBERNATION_NVS)	+= hibernate_nvs.o
 
 obj-$(CONFIG_MAGIC_SYSRQ)	+= poweroff.o
diff --git a/kernel/power/block_io.c b/kernel/power/block_io.c
new file mode 100644
index 000000000000..97024fd40cd5
--- /dev/null
+++ b/kernel/power/block_io.c
@@ -0,0 +1,103 @@
+/*
+ * This file provides functions for block I/O operations on swap/file.
+ *
+ * Copyright (C) 1998,2001-2005 Pavel Machek <pavel@ucw.cz>
+ * Copyright (C) 2006 Rafael J. Wysocki <rjw@sisk.pl>
+ *
+ * This file is released under the GPLv2.
+ */
+
+#include <linux/bio.h>
+#include <linux/kernel.h>
+#include <linux/pagemap.h>
+#include <linux/swap.h>
+
+#include "power.h"
+
+/**
+ *	submit - submit BIO request.
+ *	@rw:	READ or WRITE.
+ *	@off	physical offset of page.
+ *	@page:	page we're reading or writing.
+ *	@bio_chain: list of pending biod (for async reading)
+ *
+ *	Straight from the textbook - allocate and initialize the bio.
+ *	If we're reading, make sure the page is marked as dirty.
+ *	Then submit it and, if @bio_chain == NULL, wait.
+ */
+static int submit(int rw, struct block_device *bdev, sector_t sector,
+		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);
+	bio->bi_sector = sector;
+	bio->bi_bdev = bdev;
+	bio->bi_end_io = end_swap_bio_read;
+
+	if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) {
+		printk(KERN_ERR "PM: Adding page to bio failed at %llu\n",
+			(unsigned long long)sector);
+		bio_put(bio);
+		return -EFAULT;
+	}
+
+	lock_page(page);
+	bio_get(bio);
+
+	if (bio_chain == NULL) {
+		submit_bio(bio_rw, bio);
+		wait_on_page_locked(page);
+		if (rw == READ)
+			bio_set_pages_dirty(bio);
+		bio_put(bio);
+	} else {
+		if (rw == READ)
+			get_page(page);	/* These pages are freed later */
+		bio->bi_private = *bio_chain;
+		*bio_chain = bio;
+		submit_bio(bio_rw, bio);
+	}
+	return 0;
+}
+
+int hib_bio_read_page(pgoff_t page_off, void *addr, struct bio **bio_chain)
+{
+	return submit(READ, hib_resume_bdev, page_off * (PAGE_SIZE >> 9),
+			virt_to_page(addr), bio_chain);
+}
+
+int hib_bio_write_page(pgoff_t page_off, void *addr, struct bio **bio_chain)
+{
+	return submit(WRITE, hib_resume_bdev, page_off * (PAGE_SIZE >> 9),
+			virt_to_page(addr), bio_chain);
+}
+
+int hib_wait_on_bio_chain(struct bio **bio_chain)
+{
+	struct bio *bio;
+	struct bio *next_bio;
+	int ret = 0;
+
+	if (bio_chain == NULL)
+		return 0;
+
+	bio = *bio_chain;
+	if (bio == NULL)
+		return 0;
+	while (bio) {
+		struct page *page;
+
+		next_bio = bio->bi_private;
+		page = bio->bi_io_vec[0].bv_page;
+		wait_on_page_locked(page);
+		if (!PageUptodate(page) || PageError(page))
+			ret = -EIO;
+		put_page(page);
+		bio_put(bio);
+		bio = next_bio;
+	}
+	*bio_chain = NULL;
+	return ret;
+}
diff --git a/kernel/power/power.h b/kernel/power/power.h
index 46c5a26630a3..006270fe382d 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -97,24 +97,12 @@ extern int hibernate_preallocate_memory(void);
  */
 
 struct snapshot_handle {
-	loff_t		offset;	/* number of the last byte ready for reading
-				 * or writing in the sequence
-				 */
 	unsigned int	cur;	/* number of the block of PAGE_SIZE bytes the
 				 * next operation will refer to (ie. current)
 				 */
-	unsigned int	cur_offset;	/* offset with respect to the current
-					 * block (for the next operation)
-					 */
-	unsigned int	prev;	/* number of the block of PAGE_SIZE bytes that
-				 * was the current one previously
-				 */
 	void		*buffer;	/* address of the block to read from
 					 * or write to
 					 */
-	unsigned int	buf_offset;	/* location to read from or write to,
-					 * given as a displacement from 'buffer'
-					 */
 	int		sync_read;	/* Set to one to notify the caller of
 					 * snapshot_write_next() that it may
 					 * need to call wait_on_bio_chain()
@@ -125,12 +113,12 @@ struct snapshot_handle {
  * snapshot_read_next()/snapshot_write_next() is allowed to
  * read/write data after the function returns
  */
-#define data_of(handle)	((handle).buffer + (handle).buf_offset)
+#define data_of(handle)	((handle).buffer)
 
 extern unsigned int snapshot_additional_pages(struct zone *zone);
 extern unsigned long snapshot_get_image_size(void);
-extern int snapshot_read_next(struct snapshot_handle *handle, size_t count);
-extern int snapshot_write_next(struct snapshot_handle *handle, size_t count);
+extern int snapshot_read_next(struct snapshot_handle *handle);
+extern int snapshot_write_next(struct snapshot_handle *handle);
 extern void snapshot_write_finalize(struct snapshot_handle *handle);
 extern int snapshot_image_loaded(struct snapshot_handle *handle);
 
@@ -154,6 +142,15 @@ extern int swsusp_read(unsigned int *flags_p);
 extern int swsusp_write(unsigned int flags);
 extern void swsusp_close(fmode_t);
 
+/* kernel/power/block_io.c */
+extern struct block_device *hib_resume_bdev;
+
+extern int hib_bio_read_page(pgoff_t page_off, void *addr,
+		struct bio **bio_chain);
+extern int hib_bio_write_page(pgoff_t page_off, void *addr,
+		struct bio **bio_chain);
+extern int hib_wait_on_bio_chain(struct bio **bio_chain);
+
 struct timeval;
 /* kernel/power/swsusp.c */
 extern void swsusp_show_speed(struct timeval *, struct timeval *,
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index be861c26dda7..25ce010e9f8b 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -1604,14 +1604,9 @@ pack_pfns(unsigned long *buf, struct memory_bitmap *bm)
  *	snapshot_handle structure.  The structure gets updated and a pointer
  *	to it should be passed to this function every next time.
  *
- *	The @count parameter should contain the number of bytes the caller
- *	wants to read from the snapshot.  It must not be zero.
- *
  *	On success the function returns a positive number.  Then, the caller
  *	is allowed to read up to the returned number of bytes from the memory
- *	location computed by the data_of() macro.  The number returned
- *	may be smaller than @count, but this only happens if the read would
- *	cross a page boundary otherwise.
+ *	location computed by the data_of() macro.
  *
  *	The function returns 0 to indicate the end of data stream condition,
  *	and a negative number is returned on error.  In such cases the
@@ -1619,7 +1614,7 @@ pack_pfns(unsigned long *buf, struct memory_bitmap *bm)
  *	any more.
  */
 
-int snapshot_read_next(struct snapshot_handle *handle, size_t count)
+int snapshot_read_next(struct snapshot_handle *handle)
 {
 	if (handle->cur > nr_meta_pages + nr_copy_pages)
 		return 0;
@@ -1630,7 +1625,7 @@ int snapshot_read_next(struct snapshot_handle *handle, size_t count)
 		if (!buffer)
 			return -ENOMEM;
 	}
-	if (!handle->offset) {
+	if (!handle->cur) {
 		int error;
 
 		error = init_header((struct swsusp_info *)buffer);
@@ -1639,42 +1634,30 @@ int snapshot_read_next(struct snapshot_handle *handle, size_t count)
 		handle->buffer = buffer;
 		memory_bm_position_reset(&orig_bm);
 		memory_bm_position_reset(&copy_bm);
-	}
-	if (handle->prev < handle->cur) {
-		if (handle->cur <= nr_meta_pages) {
-			memset(buffer, 0, PAGE_SIZE);
-			pack_pfns(buffer, &orig_bm);
-		} else {
-			struct page *page;
+	} else if (handle->cur <= nr_meta_pages) {
+		memset(buffer, 0, PAGE_SIZE);
+		pack_pfns(buffer, &orig_bm);
+	} else {
+		struct page *page;
 
-			page = pfn_to_page(memory_bm_next_pfn(&copy_bm));
-			if (PageHighMem(page)) {
-				/* Highmem pages are copied to the buffer,
-				 * because we can't return with a kmapped
-				 * highmem page (we may not be called again).
-				 */
-				void *kaddr;
+		page = pfn_to_page(memory_bm_next_pfn(&copy_bm));
+		if (PageHighMem(page)) {
+			/* Highmem pages are copied to the buffer,
+			 * because we can't return with a kmapped
+			 * highmem page (we may not be called again).
+			 */
+			void *kaddr;
 
-				kaddr = kmap_atomic(page, KM_USER0);
-				memcpy(buffer, kaddr, PAGE_SIZE);
-				kunmap_atomic(kaddr, KM_USER0);
-				handle->buffer = buffer;
-			} else {
-				handle->buffer = page_address(page);
-			}
+			kaddr = kmap_atomic(page, KM_USER0);
+			memcpy(buffer, kaddr, PAGE_SIZE);
+			kunmap_atomic(kaddr, KM_USER0);
+			handle->buffer = buffer;
+		} else {
+			handle->buffer = page_address(page);
 		}
-		handle->prev = handle->cur;
-	}
-	handle->buf_offset = handle->cur_offset;
-	if (handle->cur_offset + count >= PAGE_SIZE) {
-		count = PAGE_SIZE - handle->cur_offset;
-		handle->cur_offset = 0;
-		handle->cur++;
-	} else {
-		handle->cur_offset += count;
 	}
-	handle->offset += count;
-	return count;
+	handle->cur++;
+	return PAGE_SIZE;
 }
 
 /**
@@ -2133,14 +2116,9 @@ static void *get_buffer(struct memory_bitmap *bm, struct chain_allocator *ca)
  *	snapshot_handle structure.  The structure gets updated and a pointer
  *	to it should be passed to this function every next time.
  *
- *	The @count parameter should contain the number of bytes the caller
- *	wants to write to the image.  It must not be zero.
- *
  *	On success the function returns a positive number.  Then, the caller
  *	is allowed to write up to the returned number of bytes to the memory
- *	location computed by the data_of() macro.  The number returned
- *	may be smaller than @count, but this only happens if the write would
- *	cross a page boundary otherwise.
+ *	location computed by the data_of() macro.
  *
  *	The function returns 0 to indicate the "end of file" condition,
  *	and a negative number is returned on error.  In such cases the
@@ -2148,16 +2126,18 @@ static void *get_buffer(struct memory_bitmap *bm, struct chain_allocator *ca)
  *	any more.
  */
 
-int snapshot_write_next(struct snapshot_handle *handle, size_t count)
+int snapshot_write_next(struct snapshot_handle *handle)
 {
 	static struct chain_allocator ca;
 	int error = 0;
 
 	/* Check if we have already loaded the entire image */
-	if (handle->prev && handle->cur > nr_meta_pages + nr_copy_pages)
+	if (handle->cur > 1 && handle->cur > nr_meta_pages + nr_copy_pages)
 		return 0;
 
-	if (handle->offset == 0) {
+	handle->sync_read = 1;
+
+	if (!handle->cur) {
 		if (!buffer)
 			/* This makes the buffer be freed by swsusp_free() */
 			buffer = get_image_page(GFP_ATOMIC, PG_ANY);
@@ -2166,56 +2146,43 @@ int snapshot_write_next(struct snapshot_handle *handle, size_t count)
 			return -ENOMEM;
 
 		handle->buffer = buffer;
-	}
-	handle->sync_read = 1;
-	if (handle->prev < handle->cur) {
-		if (handle->prev == 0) {
-			error = load_header(buffer);
-			if (error)
-				return error;
+	} else if (handle->cur == 1) {
+		error = load_header(buffer);
+		if (error)
+			return error;
 
-			error = memory_bm_create(&copy_bm, GFP_ATOMIC, PG_ANY);
-			if (error)
-				return error;
+		error = memory_bm_create(&copy_bm, GFP_ATOMIC, PG_ANY);
+		if (error)
+			return error;
+
+	} else if (handle->cur <= nr_meta_pages + 1) {
+		error = unpack_orig_pfns(buffer, &copy_bm);
+		if (error)
+			return error;
 
-		} else if (handle->prev <= nr_meta_pages) {
-			error = unpack_orig_pfns(buffer, &copy_bm);
+		if (handle->cur == nr_meta_pages + 1) {
+			error = prepare_image(&orig_bm, &copy_bm);
 			if (error)
 				return error;
 
-			if (handle->prev == nr_meta_pages) {
-				error = prepare_image(&orig_bm, &copy_bm);
-				if (error)
-					return error;
-
-				chain_init(&ca, GFP_ATOMIC, PG_SAFE);
-				memory_bm_position_reset(&orig_bm);
-				restore_pblist = NULL;
-				handle->buffer = get_buffer(&orig_bm, &ca);
-				handle->sync_read = 0;
-				if (IS_ERR(handle->buffer))
-					return PTR_ERR(handle->buffer);
-			}
-		} else {
-			copy_last_highmem_page();
+			chain_init(&ca, GFP_ATOMIC, PG_SAFE);
+			memory_bm_position_reset(&orig_bm);
+			restore_pblist = NULL;
 			handle->buffer = get_buffer(&orig_bm, &ca);
+			handle->sync_read = 0;
 			if (IS_ERR(handle->buffer))
 				return PTR_ERR(handle->buffer);
-			if (handle->buffer != buffer)
-				handle->sync_read = 0;
 		}
-		handle->prev = handle->cur;
-	}
-	handle->buf_offset = handle->cur_offset;
-	if (handle->cur_offset + count >= PAGE_SIZE) {
-		count = PAGE_SIZE - handle->cur_offset;
-		handle->cur_offset = 0;
-		handle->cur++;
 	} else {
-		handle->cur_offset += count;
+		copy_last_highmem_page();
+		handle->buffer = get_buffer(&orig_bm, &ca);
+		if (IS_ERR(handle->buffer))
+			return PTR_ERR(handle->buffer);
+		if (handle->buffer != buffer)
+			handle->sync_read = 0;
 	}
-	handle->offset += count;
-	return count;
+	handle->cur++;
+	return PAGE_SIZE;
 }
 
 /**
@@ -2230,7 +2197,7 @@ void snapshot_write_finalize(struct snapshot_handle *handle)
 {
 	copy_last_highmem_page();
 	/* Free only if we have loaded the image entirely */
-	if (handle->prev && handle->cur > nr_meta_pages + nr_copy_pages) {
+	if (handle->cur > 1 && handle->cur > nr_meta_pages + nr_copy_pages) {
 		memory_bm_free(&orig_bm, PG_UNSAFE_CLEAR);
 		free_highmem_data();
 	}
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index 66824d71983a..b0bb21778391 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -29,6 +29,40 @@
 
 #define SWSUSP_SIG	"S1SUSPEND"
 
+/*
+ *	The swap map is a data structure used for keeping track of each page
+ *	written to a swap partition.  It consists of many swap_map_page
+ *	structures that contain each an array of MAP_PAGE_SIZE swap entries.
+ *	These structures are stored on the swap and linked together with the
+ *	help of the .next_swap member.
+ *
+ *	The swap map is created during suspend.  The swap map pages are
+ *	allocated and populated one at a time, so we only need one memory
+ *	page to set up the entire structure.
+ *
+ *	During resume we also only need to use one swap_map_page structure
+ *	at a time.
+ */
+
+#define MAP_PAGE_ENTRIES	(PAGE_SIZE / sizeof(sector_t) - 1)
+
+struct swap_map_page {
+	sector_t entries[MAP_PAGE_ENTRIES];
+	sector_t next_swap;
+};
+
+/**
+ *	The swap_map_handle structure is used for handling swap in
+ *	a file-alike way
+ */
+
+struct swap_map_handle {
+	struct swap_map_page *cur;
+	sector_t cur_swap;
+	sector_t first_sector;
+	unsigned int k;
+};
+
 struct swsusp_header {
 	char reserved[PAGE_SIZE - 20 - sizeof(sector_t) - sizeof(int)];
 	sector_t image;
@@ -145,110 +179,24 @@ int swsusp_swap_in_use(void)
  */
 
 static unsigned short root_swap = 0xffff;
-static struct block_device *resume_bdev;
-
-/**
- *	submit - submit BIO request.
- *	@rw:	READ or WRITE.
- *	@off	physical offset of page.
- *	@page:	page we're reading or writing.
- *	@bio_chain: list of pending biod (for async reading)
- *
- *	Straight from the textbook - allocate and initialize the bio.
- *	If we're reading, make sure the page is marked as dirty.
- *	Then submit it and, if @bio_chain == NULL, wait.
- */
-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);
-	bio->bi_sector = page_off * (PAGE_SIZE >> 9);
-	bio->bi_bdev = resume_bdev;
-	bio->bi_end_io = end_swap_bio_read;
-
-	if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) {
-		printk(KERN_ERR "PM: Adding page to bio failed at %ld\n",
-			page_off);
-		bio_put(bio);
-		return -EFAULT;
-	}
-
-	lock_page(page);
-	bio_get(bio);
-
-	if (bio_chain == NULL) {
-		submit_bio(bio_rw, bio);
-		wait_on_page_locked(page);
-		if (rw == READ)
-			bio_set_pages_dirty(bio);
-		bio_put(bio);
-	} else {
-		if (rw == READ)
-			get_page(page);	/* These pages are freed later */
-		bio->bi_private = *bio_chain;
-		*bio_chain = bio;
-		submit_bio(bio_rw, bio);
-	}
-	return 0;
-}
-
-static int bio_read_page(pgoff_t page_off, void *addr, struct bio **bio_chain)
-{
-	return submit(READ, page_off, virt_to_page(addr), bio_chain);
-}
-
-static int bio_write_page(pgoff_t page_off, void *addr, struct bio **bio_chain)
-{
-	return submit(WRITE, page_off, virt_to_page(addr), bio_chain);
-}
-
-static int wait_on_bio_chain(struct bio **bio_chain)
-{
-	struct bio *bio;
-	struct bio *next_bio;
-	int ret = 0;
-
-	if (bio_chain == NULL)
-		return 0;
-
-	bio = *bio_chain;
-	if (bio == NULL)
-		return 0;
-	while (bio) {
-		struct page *page;
-
-		next_bio = bio->bi_private;
-		page = bio->bi_io_vec[0].bv_page;
-		wait_on_page_locked(page);
-		if (!PageUptodate(page) || PageError(page))
-			ret = -EIO;
-		put_page(page);
-		bio_put(bio);
-		bio = next_bio;
-	}
-	*bio_chain = NULL;
-	return ret;
-}
+struct block_device *hib_resume_bdev;
 
 /*
  * Saving part
  */
 
-static int mark_swapfiles(sector_t start, unsigned int flags)
+static int mark_swapfiles(struct swap_map_handle *handle, unsigned int flags)
 {
 	int error;
 
-	bio_read_page(swsusp_resume_block, swsusp_header, NULL);
+	hib_bio_read_page(swsusp_resume_block, swsusp_header, NULL);
 	if (!memcmp("SWAP-SPACE",swsusp_header->sig, 10) ||
 	    !memcmp("SWAPSPACE2",swsusp_header->sig, 10)) {
 		memcpy(swsusp_header->orig_sig,swsusp_header->sig, 10);
 		memcpy(swsusp_header->sig,SWSUSP_SIG, 10);
-		swsusp_header->image = start;
+		swsusp_header->image = handle->first_sector;
 		swsusp_header->flags = flags;
-		error = bio_write_page(swsusp_resume_block,
+		error = hib_bio_write_page(swsusp_resume_block,
 					swsusp_header, NULL);
 	} else {
 		printk(KERN_ERR "PM: Swap header not found!\n");
@@ -260,25 +208,26 @@ static int mark_swapfiles(sector_t start, unsigned int flags)
 /**
  *	swsusp_swap_check - check if the resume device is a swap device
  *	and get its index (if so)
+ *
+ *	This is called before saving image
  */
-
-static int swsusp_swap_check(void) /* This is called before saving image */
+static int swsusp_swap_check(void)
 {
 	int res;
 
 	res = swap_type_of(swsusp_resume_device, swsusp_resume_block,
-			&resume_bdev);
+			&hib_resume_bdev);
 	if (res < 0)
 		return res;
 
 	root_swap = res;
-	res = blkdev_get(resume_bdev, FMODE_WRITE);
+	res = blkdev_get(hib_resume_bdev, FMODE_WRITE);
 	if (res)
 		return res;
 
-	res = set_blocksize(resume_bdev, PAGE_SIZE);
+	res = set_blocksize(hib_resume_bdev, PAGE_SIZE);
 	if (res < 0)
-		blkdev_put(resume_bdev, FMODE_WRITE);
+		blkdev_put(hib_resume_bdev, FMODE_WRITE);
 
 	return res;
 }
@@ -309,42 +258,9 @@ static int write_page(void *buf, sector_t offset, struct bio **bio_chain)
 	} else {
 		src = buf;
 	}
-	return bio_write_page(offset, src, bio_chain);
+	return hib_bio_write_page(offset, src, bio_chain);
 }
 
-/*
- *	The swap map is a data structure used for keeping track of each page
- *	written to a swap partition.  It consists of many swap_map_page
- *	structures that contain each an array of MAP_PAGE_SIZE swap entries.
- *	These structures are stored on the swap and linked together with the
- *	help of the .next_swap member.
- *
- *	The swap map is created during suspend.  The swap map pages are
- *	allocated and populated one at a time, so we only need one memory
- *	page to set up the entire structure.
- *
- *	During resume we also only need to use one swap_map_page structure
- *	at a time.
- */
-
-#define MAP_PAGE_ENTRIES	(PAGE_SIZE / sizeof(sector_t) - 1)
-
-struct swap_map_page {
-	sector_t entries[MAP_PAGE_ENTRIES];
-	sector_t next_swap;
-};
-
-/**
- *	The swap_map_handle structure is used for handling swap in
- *	a file-alike way
- */
-
-struct swap_map_handle {
-	struct swap_map_page *cur;
-	sector_t cur_swap;
-	unsigned int k;
-};
-
 static void release_swap_writer(struct swap_map_handle *handle)
 {
 	if (handle->cur)
@@ -354,16 +270,33 @@ static void release_swap_writer(struct swap_map_handle *handle)
 
 static int get_swap_writer(struct swap_map_handle *handle)
 {
+	int ret;
+
+	ret = swsusp_swap_check();
+	if (ret) {
+		if (ret != -ENOSPC)
+			printk(KERN_ERR "PM: Cannot find swap device, try "
+					"swapon -a.\n");
+		return ret;
+	}
 	handle->cur = (struct swap_map_page *)get_zeroed_page(GFP_KERNEL);
-	if (!handle->cur)
-		return -ENOMEM;
+	if (!handle->cur) {
+		ret = -ENOMEM;
+		goto err_close;
+	}
 	handle->cur_swap = alloc_swapdev_block(root_swap);
 	if (!handle->cur_swap) {
-		release_swap_writer(handle);
-		return -ENOSPC;
+		ret = -ENOSPC;
+		goto err_rel;
 	}
 	handle->k = 0;
+	handle->first_sector = handle->cur_swap;
 	return 0;
+err_rel:
+	release_swap_writer(handle);
+err_close:
+	swsusp_close(FMODE_WRITE);
+	return ret;
 }
 
 static int swap_write_page(struct swap_map_handle *handle, void *buf,
@@ -380,7 +313,7 @@ static int swap_write_page(struct swap_map_handle *handle, void *buf,
 		return error;
 	handle->cur->entries[handle->k++] = offset;
 	if (handle->k >= MAP_PAGE_ENTRIES) {
-		error = wait_on_bio_chain(bio_chain);
+		error = hib_wait_on_bio_chain(bio_chain);
 		if (error)
 			goto out;
 		offset = alloc_swapdev_block(root_swap);
@@ -406,6 +339,24 @@ static int flush_swap_writer(struct swap_map_handle *handle)
 		return -EINVAL;
 }
 
+static int swap_writer_finish(struct swap_map_handle *handle,
+		unsigned int flags, int error)
+{
+	if (!error) {
+		flush_swap_writer(handle);
+		printk(KERN_INFO "PM: S");
+		error = mark_swapfiles(handle, flags);
+		printk("|\n");
+	}
+
+	if (error)
+		free_all_swap_pages(root_swap);
+	release_swap_writer(handle);
+	swsusp_close(FMODE_WRITE);
+
+	return error;
+}
+
 /**
  *	save_image - save the suspend image data
  */
@@ -431,7 +382,7 @@ static int save_image(struct swap_map_handle *handle,
 	bio = NULL;
 	do_gettimeofday(&start);
 	while (1) {
-		ret = snapshot_read_next(snapshot, PAGE_SIZE);
+		ret = snapshot_read_next(snapshot);
 		if (ret <= 0)
 			break;
 		ret = swap_write_page(handle, data_of(*snapshot), &bio);
@@ -441,7 +392,7 @@ static int save_image(struct swap_map_handle *handle,
 			printk(KERN_CONT "\b\b\b\b%3d%%", nr_pages / m);
 		nr_pages++;
 	}
-	err2 = wait_on_bio_chain(&bio);
+	err2 = hib_wait_on_bio_chain(&bio);
 	do_gettimeofday(&stop);
 	if (!ret)
 		ret = err2;
@@ -483,50 +434,34 @@ int swsusp_write(unsigned int flags)
 	struct swap_map_handle handle;
 	struct snapshot_handle snapshot;
 	struct swsusp_info *header;
+	unsigned long pages;
 	int error;
 
-	error = swsusp_swap_check();
+	pages = snapshot_get_image_size();
+	error = get_swap_writer(&handle);
 	if (error) {
-		printk(KERN_ERR "PM: Cannot find swap device, try "
-				"swapon -a.\n");
+		printk(KERN_ERR "PM: Cannot get swap writer\n");
 		return error;
 	}
+	if (!enough_swap(pages)) {
+		printk(KERN_ERR "PM: Not enough free swap\n");
+		error = -ENOSPC;
+		goto out_finish;
+	}
 	memset(&snapshot, 0, sizeof(struct snapshot_handle));
-	error = snapshot_read_next(&snapshot, PAGE_SIZE);
+	error = snapshot_read_next(&snapshot);
 	if (error < PAGE_SIZE) {
 		if (error >= 0)
 			error = -EFAULT;
 
-		goto out;
+		goto out_finish;
 	}
 	header = (struct swsusp_info *)data_of(snapshot);
-	if (!enough_swap(header->pages)) {
-		printk(KERN_ERR "PM: Not enough free swap\n");
-		error = -ENOSPC;
-		goto out;
-	}
-	error = get_swap_writer(&handle);
-	if (!error) {
-		sector_t start = handle.cur_swap;
-
-		error = swap_write_page(&handle, header, NULL);
-		if (!error)
-			error = save_image(&handle, &snapshot,
-					header->pages - 1);
-
-		if (!error) {
-			flush_swap_writer(&handle);
-			printk(KERN_INFO "PM: S");
-			error = mark_swapfiles(start, flags);
-			printk("|\n");
-		}
-	}
-	if (error)
-		free_all_swap_pages(root_swap);
-
-	release_swap_writer(&handle);
- out:
-	swsusp_close(FMODE_WRITE);
+	error = swap_write_page(&handle, header, NULL);
+	if (!error)
+		error = save_image(&handle, &snapshot, pages - 1);
+out_finish:
+	error = swap_writer_finish(&handle, flags, error);
 	return error;
 }
 
@@ -542,18 +477,21 @@ static void release_swap_reader(struct swap_map_handle *handle)
 	handle->cur = NULL;
 }
 
-static int get_swap_reader(struct swap_map_handle *handle, sector_t start)
+static int get_swap_reader(struct swap_map_handle *handle,
+		unsigned int *flags_p)
 {
 	int error;
 
-	if (!start)
+	*flags_p = swsusp_header->flags;
+
+	if (!swsusp_header->image) /* how can this happen? */
 		return -EINVAL;
 
 	handle->cur = (struct swap_map_page *)get_zeroed_page(__GFP_WAIT | __GFP_HIGH);
 	if (!handle->cur)
 		return -ENOMEM;
 
-	error = bio_read_page(start, handle->cur, NULL);
+	error = hib_bio_read_page(swsusp_header->image, handle->cur, NULL);
 	if (error) {
 		release_swap_reader(handle);
 		return error;
@@ -573,21 +511,28 @@ static int swap_read_page(struct swap_map_handle *handle, void *buf,
 	offset = handle->cur->entries[handle->k];
 	if (!offset)
 		return -EFAULT;
-	error = bio_read_page(offset, buf, bio_chain);
+	error = hib_bio_read_page(offset, buf, bio_chain);
 	if (error)
 		return error;
 	if (++handle->k >= MAP_PAGE_ENTRIES) {
-		error = wait_on_bio_chain(bio_chain);
+		error = hib_wait_on_bio_chain(bio_chain);
 		handle->k = 0;
 		offset = handle->cur->next_swap;
 		if (!offset)
 			release_swap_reader(handle);
 		else if (!error)
-			error = bio_read_page(offset, handle->cur, NULL);
+			error = hib_bio_read_page(offset, handle->cur, NULL);
 	}
 	return error;
 }
 
+static int swap_reader_finish(struct swap_map_handle *handle)
+{
+	release_swap_reader(handle);
+
+	return 0;
+}
+
 /**
  *	load_image - load the image using the swap map handle
  *	@handle and the snapshot handle @snapshot
@@ -615,21 +560,21 @@ static int load_image(struct swap_map_handle *handle,
 	bio = NULL;
 	do_gettimeofday(&start);
 	for ( ; ; ) {
-		error = snapshot_write_next(snapshot, PAGE_SIZE);
+		error = snapshot_write_next(snapshot);
 		if (error <= 0)
 			break;
 		error = swap_read_page(handle, data_of(*snapshot), &bio);
 		if (error)
 			break;
 		if (snapshot->sync_read)
-			error = wait_on_bio_chain(&bio);
+			error = hib_wait_on_bio_chain(&bio);
 		if (error)
 			break;
 		if (!(nr_pages % m))
 			printk("\b\b\b\b%3d%%", nr_pages / m);
 		nr_pages++;
 	}
-	err2 = wait_on_bio_chain(&bio);
+	err2 = hib_wait_on_bio_chain(&bio);
 	do_gettimeofday(&stop);
 	if (!error)
 		error = err2;
@@ -657,20 +602,20 @@ int swsusp_read(unsigned int *flags_p)
 	struct snapshot_handle snapshot;
 	struct swsusp_info *header;
 
-	*flags_p = swsusp_header->flags;
-
 	memset(&snapshot, 0, sizeof(struct snapshot_handle));
-	error = snapshot_write_next(&snapshot, PAGE_SIZE);
+	error = snapshot_write_next(&snapshot);
 	if (error < PAGE_SIZE)
 		return error < 0 ? error : -EFAULT;
 	header = (struct swsusp_info *)data_of(snapshot);
-	error = get_swap_reader(&handle, swsusp_header->image);
+	error = get_swap_reader(&handle, flags_p);
+	if (error)
+		goto end;
 	if (!error)
 		error = swap_read_page(&handle, header, NULL);
 	if (!error)
 		error = load_image(&handle, &snapshot, header->pages - 1);
-	release_swap_reader(&handle);
-
+	swap_reader_finish(&handle);
+end:
 	if (!error)
 		pr_debug("PM: Image successfully loaded\n");
 	else
@@ -686,11 +631,11 @@ int swsusp_check(void)
 {
 	int error;
 
-	resume_bdev = open_by_devnum(swsusp_resume_device, FMODE_READ);
-	if (!IS_ERR(resume_bdev)) {
-		set_blocksize(resume_bdev, PAGE_SIZE);
+	hib_resume_bdev = open_by_devnum(swsusp_resume_device, FMODE_READ);
+	if (!IS_ERR(hib_resume_bdev)) {
+		set_blocksize(hib_resume_bdev, PAGE_SIZE);
 		memset(swsusp_header, 0, PAGE_SIZE);
-		error = bio_read_page(swsusp_resume_block,
+		error = hib_bio_read_page(swsusp_resume_block,
 					swsusp_header, NULL);
 		if (error)
 			goto put;
@@ -698,7 +643,7 @@ int swsusp_check(void)
 		if (!memcmp(SWSUSP_SIG, swsusp_header->sig, 10)) {
 			memcpy(swsusp_header->sig, swsusp_header->orig_sig, 10);
 			/* Reset swap signature now */
-			error = bio_write_page(swsusp_resume_block,
+			error = hib_bio_write_page(swsusp_resume_block,
 						swsusp_header, NULL);
 		} else {
 			error = -EINVAL;
@@ -706,11 +651,11 @@ int swsusp_check(void)
 
 put:
 		if (error)
-			blkdev_put(resume_bdev, FMODE_READ);
+			blkdev_put(hib_resume_bdev, FMODE_READ);
 		else
 			pr_debug("PM: Signature found, resuming\n");
 	} else {
-		error = PTR_ERR(resume_bdev);
+		error = PTR_ERR(hib_resume_bdev);
 	}
 
 	if (error)
@@ -725,12 +670,12 @@ put:
 
 void swsusp_close(fmode_t mode)
 {
-	if (IS_ERR(resume_bdev)) {
+	if (IS_ERR(hib_resume_bdev)) {
 		pr_debug("PM: Image device not initialised\n");
 		return;
 	}
 
-	blkdev_put(resume_bdev, mode);
+	blkdev_put(hib_resume_bdev, mode);
 }
 
 static int swsusp_header_init(void)
diff --git a/kernel/power/user.c b/kernel/power/user.c
index a8c96212bc1b..e819e17877ca 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -151,6 +151,7 @@ static ssize_t snapshot_read(struct file *filp, char __user *buf,
 {
 	struct snapshot_data *data;
 	ssize_t res;
+	loff_t pg_offp = *offp & ~PAGE_MASK;
 
 	mutex_lock(&pm_mutex);
 
@@ -159,14 +160,19 @@ static ssize_t snapshot_read(struct file *filp, char __user *buf,
 		res = -ENODATA;
 		goto Unlock;
 	}
-	res = snapshot_read_next(&data->handle, count);
-	if (res > 0) {
-		if (copy_to_user(buf, data_of(data->handle), res))
-			res = -EFAULT;
-		else
-			*offp = data->handle.offset;
+	if (!pg_offp) { /* on page boundary? */
+		res = snapshot_read_next(&data->handle);
+		if (res <= 0)
+			goto Unlock;
+	} else {
+		res = PAGE_SIZE - pg_offp;
 	}
 
+	res = simple_read_from_buffer(buf, count, &pg_offp,
+			data_of(data->handle), res);
+	if (res > 0)
+		*offp += res;
+
  Unlock:
 	mutex_unlock(&pm_mutex);
 
@@ -178,18 +184,25 @@ static ssize_t snapshot_write(struct file *filp, const char __user *buf,
 {
 	struct snapshot_data *data;
 	ssize_t res;
+	loff_t pg_offp = *offp & ~PAGE_MASK;
 
 	mutex_lock(&pm_mutex);
 
 	data = filp->private_data;
-	res = snapshot_write_next(&data->handle, count);
-	if (res > 0) {
-		if (copy_from_user(data_of(data->handle), buf, res))
-			res = -EFAULT;
-		else
-			*offp = data->handle.offset;
+
+	if (!pg_offp) {
+		res = snapshot_write_next(&data->handle);
+		if (res <= 0)
+			goto unlock;
+	} else {
+		res = PAGE_SIZE - pg_offp;
 	}
 
+	res = simple_write_to_buffer(data_of(data->handle), res, &pg_offp,
+			buf, count);
+	if (res > 0)
+		*offp += res;
+unlock:
 	mutex_unlock(&pm_mutex);
 
 	return res;