Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6 into for-linus-1

* 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6: (9356 commits)
  [media] rc: update for bitop name changes
  fs: simplify iget & friends
  fs: pull inode->i_lock up out of writeback_single_inode
  fs: rename inode_lock to inode_hash_lock
  fs: move i_wb_list out from under inode_lock
  fs: move i_sb_list out from under inode_lock
  fs: remove inode_lock from iput_final and prune_icache
  fs: Lock the inode LRU list separately
  fs: factor inode disposal
  fs: protect inode->i_state with inode->i_lock
  lib, arch: add filter argument to show_mem and fix private implementations
  SLUB: Write to per cpu data when allocating it
  slub: Fix debugobjects with lockless fastpath
  autofs4: Do not potentially dereference NULL pointer returned by fget() in autofs_dev_ioctl_setpipefd()
  autofs4 - remove autofs4_lock
  autofs4 - fix d_manage() return on rcu-walk
  autofs4 - fix autofs4_expire_indirect() traversal
  autofs4 - fix dentry leak in autofs4_expire_direct()
  autofs4 - reinstate last used update on access
  vfs - check non-mountpoint dentry might block in __follow_mount_rcu()
  ...

NOTE!

This merge commit was created to fix compilation error. The block
tree was merged upstream and removed the 'elv_queue_empty()'
function which the new 'mtdswap' driver is using. So a simple
merge of the mtd tree with upstream does not compile. And the
mtd tree has already be published, so re-basing it is not an option.

To fix this unfortunate situation, I had to merge upstream into the
mtd-2.6.git tree without committing, put the fixup patch on top of
this, and then commit this. The result is that we do not have commits
which do not compile.

In other words, this merge commit "merges" 3 things: the MTD tree, the
upstream tree, and the fixup patch.

15 files changed, 617 insertions, 257 deletions

diff --git a/drivers/base/Makefile b/drivers/base/Makefile
index 5f51c3b4451e..4c5701c15f53 100644
--- a/drivers/base/Makefile
+++ b/drivers/base/Makefile
@@ -1,6 +1,6 @@
 # Makefile for the Linux device tree
 
-obj-y			:= core.o sys.o bus.o dd.o \
+obj-y			:= core.o sys.o bus.o dd.o syscore.o \
 			   driver.o class.o platform.o \
 			   cpu.o firmware.o init.o map.o devres.o \
 			   attribute_container.o transport_class.o
diff --git a/drivers/base/core.c b/drivers/base/core.c
index 080e9ca11017..81b78ede37c4 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -1320,7 +1320,10 @@ struct root_device
 	struct module *owner;
 };
 
-#define to_root_device(dev) container_of(dev, struct root_device, dev)
+inline struct root_device *to_root_device(struct device *d)
+{
+	return container_of(d, struct root_device, dev);
+}
 
 static void root_device_release(struct device *dev)
 {
@@ -1551,7 +1554,34 @@ EXPORT_SYMBOL_GPL(device_destroy);
  * on the same device to ensure that new_name is valid and
  * won't conflict with other devices.
  *
- * "Never use this function, bad things will happen" - gregkh
+ * Note: Don't call this function.  Currently, the networking layer calls this
+ * function, but that will change.  The following text from Kay Sievers offers
+ * some insight:
+ *
+ * Renaming devices is racy at many levels, symlinks and other stuff are not
+ * replaced atomically, and you get a "move" uevent, but it's not easy to
+ * connect the event to the old and new device. Device nodes are not renamed at
+ * all, there isn't even support for that in the kernel now.
+ *
+ * In the meantime, during renaming, your target name might be taken by another
+ * driver, creating conflicts. Or the old name is taken directly after you
+ * renamed it -- then you get events for the same DEVPATH, before you even see
+ * the "move" event. It's just a mess, and nothing new should ever rely on
+ * kernel device renaming. Besides that, it's not even implemented now for
+ * other things than (driver-core wise very simple) network devices.
+ *
+ * We are currently about to change network renaming in udev to completely
+ * disallow renaming of devices in the same namespace as the kernel uses,
+ * because we can't solve the problems properly, that arise with swapping names
+ * of multiple interfaces without races. Means, renaming of eth[0-9]* will only
+ * be allowed to some other name than eth[0-9]*, for the aforementioned
+ * reasons.
+ *
+ * Make up a "real" name in the driver before you register anything, or add
+ * some other attributes for userspace to find the device, or use udev to add
+ * symlinks -- but never rename kernel devices later, it's a complete mess. We
+ * don't even want to get into that and try to implement the missing pieces in
+ * the core. We really have other pieces to fix in the driver core mess. :)
  */
 int device_rename(struct device *dev, const char *new_name)
 {
diff --git a/drivers/base/firmware_class.c b/drivers/base/firmware_class.c
index 40af43ebd92d..8c798ef7f13f 100644
--- a/drivers/base/firmware_class.c
+++ b/drivers/base/firmware_class.c
@@ -593,8 +593,7 @@ int
 request_firmware(const struct firmware **firmware_p, const char *name,
                  struct device *device)
 {
-        int uevent = 1;
-        return _request_firmware(firmware_p, name, device, uevent, false);
+        return _request_firmware(firmware_p, name, device, true, false);
 }
 
 /**
@@ -618,7 +617,7 @@ struct firmware_work {
 	struct device *device;
 	void *context;
 	void (*cont)(const struct firmware *fw, void *context);
-	int uevent;
+	bool uevent;
 };
 
 static int request_firmware_work_func(void *arg)
@@ -661,7 +660,7 @@ static int request_firmware_work_func(void *arg)
  **/
 int
 request_firmware_nowait(
-	struct module *module, int uevent,
+	struct module *module, bool uevent,
 	const char *name, struct device *device, gfp_t gfp, void *context,
 	void (*cont)(const struct firmware *fw, void *context))
 {
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index cafeaaf0428f..3da6a43b7756 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -30,6 +30,14 @@
 static DEFINE_MUTEX(mem_sysfs_mutex);
 
 #define MEMORY_CLASS_NAME	"memory"
+#define MIN_MEMORY_BLOCK_SIZE	(1 << SECTION_SIZE_BITS)
+
+static int sections_per_block;
+
+static inline int base_memory_block_id(int section_nr)
+{
+	return section_nr / sections_per_block;
+}
 
 static struct sysdev_class memory_sysdev_class = {
 	.name = MEMORY_CLASS_NAME,
@@ -84,39 +92,72 @@ EXPORT_SYMBOL(unregister_memory_isolate_notifier);
  * register_memory - Setup a sysfs device for a memory block
  */
 static
-int register_memory(struct memory_block *memory, struct mem_section *section)
+int register_memory(struct memory_block *memory)
 {
 	int error;
 
 	memory->sysdev.cls = &memory_sysdev_class;
-	memory->sysdev.id = __section_nr(section);
+	memory->sysdev.id = memory->start_section_nr / sections_per_block;
 
 	error = sysdev_register(&memory->sysdev);
 	return error;
 }
 
 static void
-unregister_memory(struct memory_block *memory, struct mem_section *section)
+unregister_memory(struct memory_block *memory)
 {
 	BUG_ON(memory->sysdev.cls != &memory_sysdev_class);
-	BUG_ON(memory->sysdev.id != __section_nr(section));
 
 	/* drop the ref. we got in remove_memory_block() */
 	kobject_put(&memory->sysdev.kobj);
 	sysdev_unregister(&memory->sysdev);
 }
 
+unsigned long __weak memory_block_size_bytes(void)
+{
+	return MIN_MEMORY_BLOCK_SIZE;
+}
+
+static unsigned long get_memory_block_size(void)
+{
+	unsigned long block_sz;
+
+	block_sz = memory_block_size_bytes();
+
+	/* Validate blk_sz is a power of 2 and not less than section size */
+	if ((block_sz & (block_sz - 1)) || (block_sz < MIN_MEMORY_BLOCK_SIZE)) {
+		WARN_ON(1);
+		block_sz = MIN_MEMORY_BLOCK_SIZE;
+	}
+
+	return block_sz;
+}
+
 /*
  * use this as the physical section index that this memsection
  * uses.
  */
 
-static ssize_t show_mem_phys_index(struct sys_device *dev,
+static ssize_t show_mem_start_phys_index(struct sys_device *dev,
 			struct sysdev_attribute *attr, char *buf)
 {
 	struct memory_block *mem =
 		container_of(dev, struct memory_block, sysdev);
-	return sprintf(buf, "%08lx\n", mem->phys_index);
+	unsigned long phys_index;
+
+	phys_index = mem->start_section_nr / sections_per_block;
+	return sprintf(buf, "%08lx\n", phys_index);
+}
+
+static ssize_t show_mem_end_phys_index(struct sys_device *dev,
+			struct sysdev_attribute *attr, char *buf)
+{
+	struct memory_block *mem =
+		container_of(dev, struct memory_block, sysdev);
+	unsigned long phys_index;
+
+	phys_index = mem->end_section_nr / sections_per_block;
+	return sprintf(buf, "%08lx\n", phys_index);
 }
 
 /*
@@ -125,13 +166,16 @@ static ssize_t show_mem_phys_index(struct sys_device *dev,
 static ssize_t show_mem_removable(struct sys_device *dev,
 			struct sysdev_attribute *attr, char *buf)
 {
-	unsigned long start_pfn;
-	int ret;
+	unsigned long i, pfn;
+	int ret = 1;
 	struct memory_block *mem =
 		container_of(dev, struct memory_block, sysdev);
 
-	start_pfn = section_nr_to_pfn(mem->phys_index);
-	ret = is_mem_section_removable(start_pfn, PAGES_PER_SECTION);
+	for (i = 0; i < sections_per_block; i++) {
+		pfn = section_nr_to_pfn(mem->start_section_nr + i);
+		ret &= is_mem_section_removable(pfn, PAGES_PER_SECTION);
+	}
+
 	return sprintf(buf, "%d\n", ret);
 }
 
@@ -184,17 +228,14 @@ int memory_isolate_notify(unsigned long val, void *v)
  * OK to have direct references to sparsemem variables in here.
  */
 static int
-memory_block_action(struct memory_block *mem, unsigned long action)
+memory_section_action(unsigned long phys_index, unsigned long action)
 {
 	int i;
-	unsigned long psection;
 	unsigned long start_pfn, start_paddr;
 	struct page *first_page;
 	int ret;
-	int old_state = mem->state;
 
-	psection = mem->phys_index;
-	first_page = pfn_to_page(psection << PFN_SECTION_SHIFT);
+	first_page = pfn_to_page(phys_index << PFN_SECTION_SHIFT);
 
 	/*
 	 * The probe routines leave the pages reserved, just
@@ -207,8 +248,8 @@ memory_block_action(struct memory_block *mem, unsigned long action)
 				continue;
 
 			printk(KERN_WARNING "section number %ld page number %d "
-				"not reserved, was it already online? \n",
-				psection, i);
+				"not reserved, was it already online?\n",
+				phys_index, i);
 			return -EBUSY;
 		}
 	}
@@ -219,18 +260,13 @@ memory_block_action(struct memory_block *mem, unsigned long action)
 			ret = online_pages(start_pfn, PAGES_PER_SECTION);
 			break;
 		case MEM_OFFLINE:
-			mem->state = MEM_GOING_OFFLINE;
 			start_paddr = page_to_pfn(first_page) << PAGE_SHIFT;
 			ret = remove_memory(start_paddr,
 					    PAGES_PER_SECTION << PAGE_SHIFT);
-			if (ret) {
-				mem->state = old_state;
-				break;
-			}
 			break;
 		default:
-			WARN(1, KERN_WARNING "%s(%p, %ld) unknown action: %ld\n",
-					__func__, mem, action, action);
+			WARN(1, KERN_WARNING "%s(%ld, %ld) unknown action: "
+			     "%ld\n", __func__, phys_index, action, action);
 			ret = -EINVAL;
 	}
 
@@ -240,7 +276,8 @@ memory_block_action(struct memory_block *mem, unsigned long action)
 static int memory_block_change_state(struct memory_block *mem,
 		unsigned long to_state, unsigned long from_state_req)
 {
-	int ret = 0;
+	int i, ret = 0;
+
 	mutex_lock(&mem->state_mutex);
 
 	if (mem->state != from_state_req) {
@@ -248,8 +285,23 @@ static int memory_block_change_state(struct memory_block *mem,
 		goto out;
 	}
 
-	ret = memory_block_action(mem, to_state);
-	if (!ret)
+	if (to_state == MEM_OFFLINE)
+		mem->state = MEM_GOING_OFFLINE;
+
+	for (i = 0; i < sections_per_block; i++) {
+		ret = memory_section_action(mem->start_section_nr + i,
+					    to_state);
+		if (ret)
+			break;
+	}
+
+	if (ret) {
+		for (i = 0; i < sections_per_block; i++)
+			memory_section_action(mem->start_section_nr + i,
+					      from_state_req);
+
+		mem->state = from_state_req;
+	} else
 		mem->state = to_state;
 
 out:
@@ -262,20 +314,15 @@ store_mem_state(struct sys_device *dev,
 		struct sysdev_attribute *attr, const char *buf, size_t count)
 {
 	struct memory_block *mem;
-	unsigned int phys_section_nr;
 	int ret = -EINVAL;
 
 	mem = container_of(dev, struct memory_block, sysdev);
-	phys_section_nr = mem->phys_index;
-
-	if (!present_section_nr(phys_section_nr))
-		goto out;
 
 	if (!strncmp(buf, "online", min((int)count, 6)))
 		ret = memory_block_change_state(mem, MEM_ONLINE, MEM_OFFLINE);
 	else if(!strncmp(buf, "offline", min((int)count, 7)))
 		ret = memory_block_change_state(mem, MEM_OFFLINE, MEM_ONLINE);
-out:
+
 	if (ret)
 		return ret;
 	return count;
@@ -298,7 +345,8 @@ static ssize_t show_phys_device(struct sys_device *dev,
 	return sprintf(buf, "%d\n", mem->phys_device);
 }
 
-static SYSDEV_ATTR(phys_index, 0444, show_mem_phys_index, NULL);
+static SYSDEV_ATTR(phys_index, 0444, show_mem_start_phys_index, NULL);
+static SYSDEV_ATTR(end_phys_index, 0444, show_mem_end_phys_index, NULL);
 static SYSDEV_ATTR(state, 0644, show_mem_state, store_mem_state);
 static SYSDEV_ATTR(phys_device, 0444, show_phys_device, NULL);
 static SYSDEV_ATTR(removable, 0444, show_mem_removable, NULL);
@@ -315,7 +363,7 @@ static ssize_t
 print_block_size(struct sysdev_class *class, struct sysdev_class_attribute *attr,
 		 char *buf)
 {
-	return sprintf(buf, "%lx\n", (unsigned long)PAGES_PER_SECTION * PAGE_SIZE);
+	return sprintf(buf, "%lx\n", get_memory_block_size());
 }
 
 static SYSDEV_CLASS_ATTR(block_size_bytes, 0444, print_block_size, NULL);
@@ -339,12 +387,19 @@ memory_probe_store(struct class *class, struct class_attribute *attr,
 {
 	u64 phys_addr;
 	int nid;
-	int ret;
+	int i, ret;
 
 	phys_addr = simple_strtoull(buf, NULL, 0);
 
-	nid = memory_add_physaddr_to_nid(phys_addr);
-	ret = add_memory(nid, phys_addr, PAGES_PER_SECTION << PAGE_SHIFT);
+	for (i = 0; i < sections_per_block; i++) {
+		nid = memory_add_physaddr_to_nid(phys_addr);
+		ret = add_memory(nid, phys_addr,
+				 PAGES_PER_SECTION << PAGE_SHIFT);
+		if (ret)
+			break;
+
+		phys_addr += MIN_MEMORY_BLOCK_SIZE;
+	}
 
 	if (ret)
 		count = ret;
@@ -444,6 +499,7 @@ struct memory_block *find_memory_block_hinted(struct mem_section *section,
 	struct sys_device *sysdev;
 	struct memory_block *mem;
 	char name[sizeof(MEMORY_CLASS_NAME) + 9 + 1];
+	int block_id = base_memory_block_id(__section_nr(section));
 
 	kobj = hint ? &hint->sysdev.kobj : NULL;
 
@@ -451,7 +507,7 @@ struct memory_block *find_memory_block_hinted(struct mem_section *section,
 	 * This only works because we know that section == sysdev->id
 	 * slightly redundant with sysdev_register()
 	 */
-	sprintf(&name[0], "%s%d", MEMORY_CLASS_NAME, __section_nr(section));
+	sprintf(&name[0], "%s%d", MEMORY_CLASS_NAME, block_id);
 
 	kobj = kset_find_obj_hinted(&memory_sysdev_class.kset, name, kobj);
 	if (!kobj)
@@ -476,36 +532,62 @@ struct memory_block *find_memory_block(struct mem_section *section)
 	return find_memory_block_hinted(section, NULL);
 }
 
-static int add_memory_block(int nid, struct mem_section *section,
-			unsigned long state, enum mem_add_context context)
+static int init_memory_block(struct memory_block **memory,
+			     struct mem_section *section, unsigned long state)
 {
-	struct memory_block *mem = kzalloc(sizeof(*mem), GFP_KERNEL);
+	struct memory_block *mem;
 	unsigned long start_pfn;
+	int scn_nr;
 	int ret = 0;
 
+	mem = kzalloc(sizeof(*mem), GFP_KERNEL);
 	if (!mem)
 		return -ENOMEM;
 
-	mutex_lock(&mem_sysfs_mutex);
-
-	mem->phys_index = __section_nr(section);
+	scn_nr = __section_nr(section);
+	mem->start_section_nr =
+			base_memory_block_id(scn_nr) * sections_per_block;
+	mem->end_section_nr = mem->start_section_nr + sections_per_block - 1;
 	mem->state = state;
 	mem->section_count++;
 	mutex_init(&mem->state_mutex);
-	start_pfn = section_nr_to_pfn(mem->phys_index);
+	start_pfn = section_nr_to_pfn(mem->start_section_nr);
 	mem->phys_device = arch_get_memory_phys_device(start_pfn);
 
-	ret = register_memory(mem, section);
+	ret = register_memory(mem);
 	if (!ret)
 		ret = mem_create_simple_file(mem, phys_index);
 	if (!ret)
+		ret = mem_create_simple_file(mem, end_phys_index);
+	if (!ret)
 		ret = mem_create_simple_file(mem, state);
 	if (!ret)
 		ret = mem_create_simple_file(mem, phys_device);
 	if (!ret)
 		ret = mem_create_simple_file(mem, removable);
+
+	*memory = mem;
+	return ret;
+}
+
+static int add_memory_section(int nid, struct mem_section *section,
+			unsigned long state, enum mem_add_context context)
+{
+	struct memory_block *mem;
+	int ret = 0;
+
+	mutex_lock(&mem_sysfs_mutex);
+
+	mem = find_memory_block(section);
+	if (mem) {
+		mem->section_count++;
+		kobject_put(&mem->sysdev.kobj);
+	} else
+		ret = init_memory_block(&mem, section, state);
+
 	if (!ret) {
-		if (context == HOTPLUG)
+		if (context == HOTPLUG &&
+		    mem->section_count == sections_per_block)
 			ret = register_mem_sect_under_node(mem, nid);
 	}
 
@@ -520,16 +602,19 @@ int remove_memory_block(unsigned long node_id, struct mem_section *section,
 
 	mutex_lock(&mem_sysfs_mutex);
 	mem = find_memory_block(section);
+	unregister_mem_sect_under_nodes(mem, __section_nr(section));
 
 	mem->section_count--;
 	if (mem->section_count == 0) {
-		unregister_mem_sect_under_nodes(mem);
 		mem_remove_simple_file(mem, phys_index);
+		mem_remove_simple_file(mem, end_phys_index);
 		mem_remove_simple_file(mem, state);
 		mem_remove_simple_file(mem, phys_device);
 		mem_remove_simple_file(mem, removable);
-		unregister_memory(mem, section);
-	}
+		unregister_memory(mem);
+		kfree(mem);
+	} else
+		kobject_put(&mem->sysdev.kobj);
 
 	mutex_unlock(&mem_sysfs_mutex);
 	return 0;
@@ -541,7 +626,7 @@ int remove_memory_block(unsigned long node_id, struct mem_section *section,
  */
 int register_new_memory(int nid, struct mem_section *section)
 {
-	return add_memory_block(nid, section, MEM_OFFLINE, HOTPLUG);
+	return add_memory_section(nid, section, MEM_OFFLINE, HOTPLUG);
 }
 
 int unregister_memory_section(struct mem_section *section)
@@ -560,12 +645,16 @@ int __init memory_dev_init(void)
 	unsigned int i;
 	int ret;
 	int err;
+	unsigned long block_sz;
 
 	memory_sysdev_class.kset.uevent_ops = &memory_uevent_ops;
 	ret = sysdev_class_register(&memory_sysdev_class);
 	if (ret)
 		goto out;
 
+	block_sz = get_memory_block_size();
+	sections_per_block = block_sz / MIN_MEMORY_BLOCK_SIZE;
+
 	/*
 	 * Create entries for memory sections that were found
 	 * during boot and have been initialized
@@ -573,8 +662,8 @@ int __init memory_dev_init(void)
 	for (i = 0; i < NR_MEM_SECTIONS; i++) {
 		if (!present_section_nr(i))
 			continue;
-		err = add_memory_block(0, __nr_to_section(i), MEM_ONLINE,
-				       BOOT);
+		err = add_memory_section(0, __nr_to_section(i), MEM_ONLINE,
+					 BOOT);
 		if (!ret)
 			ret = err;
 	}
diff --git a/drivers/base/node.c b/drivers/base/node.c
index 36b43052001d..b3b72d64e805 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -375,8 +375,10 @@ int register_mem_sect_under_node(struct memory_block *mem_blk, int nid)
 		return -EFAULT;
 	if (!node_online(nid))
 		return 0;
-	sect_start_pfn = section_nr_to_pfn(mem_blk->phys_index);
-	sect_end_pfn = sect_start_pfn + PAGES_PER_SECTION - 1;
+
+	sect_start_pfn = section_nr_to_pfn(mem_blk->start_section_nr);
+	sect_end_pfn = section_nr_to_pfn(mem_blk->end_section_nr);
+	sect_end_pfn += PAGES_PER_SECTION - 1;
 	for (pfn = sect_start_pfn; pfn <= sect_end_pfn; pfn++) {
 		int page_nid;
 
@@ -400,7 +402,8 @@ int register_mem_sect_under_node(struct memory_block *mem_blk, int nid)
 }
 
 /* unregister memory section under all nodes that it spans */
-int unregister_mem_sect_under_nodes(struct memory_block *mem_blk)
+int unregister_mem_sect_under_nodes(struct memory_block *mem_blk,
+				    unsigned long phys_index)
 {
 	NODEMASK_ALLOC(nodemask_t, unlinked_nodes, GFP_KERNEL);
 	unsigned long pfn, sect_start_pfn, sect_end_pfn;
@@ -412,7 +415,8 @@ int unregister_mem_sect_under_nodes(struct memory_block *mem_blk)
 	if (!unlinked_nodes)
 		return -ENOMEM;
 	nodes_clear(*unlinked_nodes);
-	sect_start_pfn = section_nr_to_pfn(mem_blk->phys_index);
+
+	sect_start_pfn = section_nr_to_pfn(phys_index);
 	sect_end_pfn = sect_start_pfn + PAGES_PER_SECTION - 1;
 	for (pfn = sect_start_pfn; pfn <= sect_end_pfn; pfn++) {
 		int nid;
diff --git a/drivers/base/power/Makefile b/drivers/base/power/Makefile
index abe46edfe5b4..118c1b92a511 100644
--- a/drivers/base/power/Makefile
+++ b/drivers/base/power/Makefile
@@ -1,7 +1,6 @@
-obj-$(CONFIG_PM)	+= sysfs.o
+obj-$(CONFIG_PM)	+= sysfs.o generic_ops.o
 obj-$(CONFIG_PM_SLEEP)	+= main.o wakeup.o
 obj-$(CONFIG_PM_RUNTIME)	+= runtime.o
-obj-$(CONFIG_PM_OPS)	+= generic_ops.o
 obj-$(CONFIG_PM_TRACE_RTC)	+= trace.o
 obj-$(CONFIG_PM_OPP)	+= opp.o
 
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 83404973f97a..052dc53eef38 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -423,26 +423,22 @@ static int device_resume_noirq(struct device *dev, pm_message_t state)
 	TRACE_DEVICE(dev);
 	TRACE_RESUME(0);
 
-	if (dev->bus && dev->bus->pm) {
-		pm_dev_dbg(dev, state, "EARLY ");
-		error = pm_noirq_op(dev, dev->bus->pm, state);
-		if (error)
-			goto End;
+	if (dev->pwr_domain) {
+		pm_dev_dbg(dev, state, "EARLY power domain ");
+		pm_noirq_op(dev, &dev->pwr_domain->ops, state);
 	}
 
 	if (dev->type && dev->type->pm) {
 		pm_dev_dbg(dev, state, "EARLY type ");
 		error = pm_noirq_op(dev, dev->type->pm, state);
-		if (error)
-			goto End;
-	}
-
-	if (dev->class && dev->class->pm) {
+	} else if (dev->class && dev->class->pm) {
 		pm_dev_dbg(dev, state, "EARLY class ");
 		error = pm_noirq_op(dev, dev->class->pm, state);
+	} else if (dev->bus && dev->bus->pm) {
+		pm_dev_dbg(dev, state, "EARLY ");
+		error = pm_noirq_op(dev, dev->bus->pm, state);
 	}
 
-End:
 	TRACE_RESUME(error);
 	return error;
 }
@@ -518,36 +514,39 @@ static int device_resume(struct device *dev, pm_message_t state, bool async)
 
 	dev->power.in_suspend = false;
 
-	if (dev->bus) {
-		if (dev->bus->pm) {
-			pm_dev_dbg(dev, state, "");
-			error = pm_op(dev, dev->bus->pm, state);
-		} else if (dev->bus->resume) {
-			pm_dev_dbg(dev, state, "legacy ");
-			error = legacy_resume(dev, dev->bus->resume);
-		}
-		if (error)
-			goto End;
+	if (dev->pwr_domain) {
+		pm_dev_dbg(dev, state, "power domain ");
+		pm_op(dev, &dev->pwr_domain->ops, state);
 	}
 
-	if (dev->type) {
-		if (dev->type->pm) {
-			pm_dev_dbg(dev, state, "type ");
-			error = pm_op(dev, dev->type->pm, state);
-		}
-		if (error)
-			goto End;
+	if (dev->type && dev->type->pm) {
+		pm_dev_dbg(dev, state, "type ");
+		error = pm_op(dev, dev->type->pm, state);
+		goto End;
 	}
 
 	if (dev->class) {
 		if (dev->class->pm) {
 			pm_dev_dbg(dev, state, "class ");
 			error = pm_op(dev, dev->class->pm, state);
+			goto End;
 		} else if (dev->class->resume) {
 			pm_dev_dbg(dev, state, "legacy class ");
 			error = legacy_resume(dev, dev->class->resume);
+			goto End;
 		}
 	}
+
+	if (dev->bus) {
+		if (dev->bus->pm) {
+			pm_dev_dbg(dev, state, "");
+			error = pm_op(dev, dev->bus->pm, state);
+		} else if (dev->bus->resume) {
+			pm_dev_dbg(dev, state, "legacy ");
+			error = legacy_resume(dev, dev->bus->resume);
+		}
+	}
+
  End:
 	device_unlock(dev);
 	complete_all(&dev->power.completion);
@@ -629,19 +628,23 @@ static void device_complete(struct device *dev, pm_message_t state)
 {
 	device_lock(dev);
 
-	if (dev->class && dev->class->pm && dev->class->pm->complete) {
-		pm_dev_dbg(dev, state, "completing class ");
-		dev->class->pm->complete(dev);
+	if (dev->pwr_domain && dev->pwr_domain->ops.complete) {
+		pm_dev_dbg(dev, state, "completing power domain ");
+		dev->pwr_domain->ops.complete(dev);
 	}
 
-	if (dev->type && dev->type->pm && dev->type->pm->complete) {
+	if (dev->type && dev->type->pm) {
 		pm_dev_dbg(dev, state, "completing type ");
-		dev->type->pm->complete(dev);
-	}
-
-	if (dev->bus && dev->bus->pm && dev->bus->pm->complete) {
+		if (dev->type->pm->complete)
+			dev->type->pm->complete(dev);
+	} else if (dev->class && dev->class->pm) {
+		pm_dev_dbg(dev, state, "completing class ");
+		if (dev->class->pm->complete)
+			dev->class->pm->complete(dev);
+	} else if (dev->bus && dev->bus->pm) {
 		pm_dev_dbg(dev, state, "completing ");
-		dev->bus->pm->complete(dev);
+		if (dev->bus->pm->complete)
+			dev->bus->pm->complete(dev);
 	}
 
 	device_unlock(dev);
@@ -669,7 +672,6 @@ static void dpm_complete(pm_message_t state)
 		mutex_unlock(&dpm_list_mtx);
 
 		device_complete(dev, state);
-		pm_runtime_put_sync(dev);
 
 		mutex_lock(&dpm_list_mtx);
 		put_device(dev);
@@ -727,29 +729,31 @@ static pm_message_t resume_event(pm_message_t sleep_state)
  */
 static int device_suspend_noirq(struct device *dev, pm_message_t state)
 {
-	int error = 0;
-
-	if (dev->class && dev->class->pm) {
-		pm_dev_dbg(dev, state, "LATE class ");
-		error = pm_noirq_op(dev, dev->class->pm, state);
-		if (error)
-			goto End;
-	}
+	int error;
 
 	if (dev->type && dev->type->pm) {
 		pm_dev_dbg(dev, state, "LATE type ");
 		error = pm_noirq_op(dev, dev->type->pm, state);
 		if (error)
-			goto End;
-	}
-
-	if (dev->bus && dev->bus->pm) {
+			return error;
+	} else if (dev->class && dev->class->pm) {
+		pm_dev_dbg(dev, state, "LATE class ");
+		error = pm_noirq_op(dev, dev->class->pm, state);
+		if (error)
+			return error;
+	} else if (dev->bus && dev->bus->pm) {
 		pm_dev_dbg(dev, state, "LATE ");
 		error = pm_noirq_op(dev, dev->bus->pm, state);
+		if (error)
+			return error;
 	}
 
-End:
-	return error;
+	if (dev->pwr_domain) {
+		pm_dev_dbg(dev, state, "LATE power domain ");
+		pm_noirq_op(dev, &dev->pwr_domain->ops, state);
+	}
+
+	return 0;
 }
 
 /**
@@ -836,25 +840,22 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async)
 		goto End;
 	}
 
+	if (dev->type && dev->type->pm) {
+		pm_dev_dbg(dev, state, "type ");
+		error = pm_op(dev, dev->type->pm, state);
+		goto Domain;
+	}
+
 	if (dev->class) {
 		if (dev->class->pm) {
 			pm_dev_dbg(dev, state, "class ");
 			error = pm_op(dev, dev->class->pm, state);
+			goto Domain;
 		} else if (dev->class->suspend) {
 			pm_dev_dbg(dev, state, "legacy class ");
 			error = legacy_suspend(dev, state, dev->class->suspend);
+			goto Domain;
 		}
-		if (error)
-			goto End;
-	}
-
-	if (dev->type) {
-		if (dev->type->pm) {
-			pm_dev_dbg(dev, state, "type ");
-			error = pm_op(dev, dev->type->pm, state);
-		}
-		if (error)
-			goto End;
 	}
 
 	if (dev->bus) {
@@ -867,6 +868,12 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async)
 		}
 	}
 
+ Domain:
+	if (!error && dev->pwr_domain) {
+		pm_dev_dbg(dev, state, "power domain ");
+		pm_op(dev, &dev->pwr_domain->ops, state);
+	}
+
  End:
 	device_unlock(dev);
 	complete_all(&dev->power.completion);
@@ -957,27 +964,34 @@ static int device_prepare(struct device *dev, pm_message_t state)
 
 	device_lock(dev);
 
-	if (dev->bus && dev->bus->pm && dev->bus->pm->prepare) {
+	if (dev->type && dev->type->pm) {
+		pm_dev_dbg(dev, state, "preparing type ");
+		if (dev->type->pm->prepare)
+			error = dev->type->pm->prepare(dev);
+		suspend_report_result(dev->type->pm->prepare, error);
+		if (error)
+			goto End;
+	} else if (dev->class && dev->class->pm) {
+		pm_dev_dbg(dev, state, "preparing class ");
+		if (dev->class->pm->prepare)
+			error = dev->class->pm->prepare(dev);
+		suspend_report_result(dev->class->pm->prepare, error);
+		if (error)
+			goto End;
+	} else if (dev->bus && dev->bus->pm) {
 		pm_dev_dbg(dev, state, "preparing ");
-		error = dev->bus->pm->prepare(dev);
+		if (dev->bus->pm->prepare)
+			error = dev->bus->pm->prepare(dev);
 		suspend_report_result(dev->bus->pm->prepare, error);
 		if (error)
 			goto End;
 	}
 
-	if (dev->type && dev->type->pm && dev->type->pm->prepare) {
-		pm_dev_dbg(dev, state, "preparing type ");
-		error = dev->type->pm->prepare(dev);
-		suspend_report_result(dev->type->pm->prepare, error);
-		if (error)
-			goto End;
+	if (dev->pwr_domain && dev->pwr_domain->ops.prepare) {
+		pm_dev_dbg(dev, state, "preparing power domain ");
+		dev->pwr_domain->ops.prepare(dev);
 	}
 
-	if (dev->class && dev->class->pm && dev->class->pm->prepare) {
-		pm_dev_dbg(dev, state, "preparing class ");
-		error = dev->class->pm->prepare(dev);
-		suspend_report_result(dev->class->pm->prepare, error);
-	}
  End:
 	device_unlock(dev);
 
@@ -1005,12 +1019,9 @@ static int dpm_prepare(pm_message_t state)
 		if (pm_runtime_barrier(dev) && device_may_wakeup(dev))
 			pm_wakeup_event(dev, 0);
 
-		if (pm_wakeup_pending()) {
-			pm_runtime_put_sync(dev);
-			error = -EBUSY;
-		} else {
-			error = device_prepare(dev, state);
-		}
+		pm_runtime_put_sync(dev);
+		error = pm_wakeup_pending() ?
+				-EBUSY : device_prepare(dev, state);
 
 		mutex_lock(&dpm_list_mtx);
 		if (error) {
diff --git a/drivers/base/power/opp.c b/drivers/base/power/opp.c
index 2bb9b4cf59d7..56a6899f5e9e 100644
--- a/drivers/base/power/opp.c
+++ b/drivers/base/power/opp.c
@@ -222,7 +222,7 @@ int opp_get_opp_count(struct device *dev)
  * opp_find_freq_exact() - search for an exact frequency
  * @dev:		device for which we do this operation
  * @freq:		frequency to search for
- * @is_available:	true/false - match for available opp
+ * @available:		true/false - match for available opp
  *
  * Searches for exact match in the opp list and returns pointer to the matching
  * opp if found, else returns ERR_PTR in case of error and should be handled
diff --git a/drivers/base/power/power.h b/drivers/base/power/power.h
index 698dde742587..f2a25f18fde7 100644
--- a/drivers/base/power/power.h
+++ b/drivers/base/power/power.h
@@ -58,19 +58,18 @@ static inline void device_pm_move_last(struct device *dev) {}
  * sysfs.c
  */
 
-extern int dpm_sysfs_add(struct device *);
-extern void dpm_sysfs_remove(struct device *);
-extern void rpm_sysfs_remove(struct device *);
+extern int dpm_sysfs_add(struct device *dev);
+extern void dpm_sysfs_remove(struct device *dev);
+extern void rpm_sysfs_remove(struct device *dev);
+extern int wakeup_sysfs_add(struct device *dev);
+extern void wakeup_sysfs_remove(struct device *dev);
 
 #else /* CONFIG_PM */
 
-static inline int dpm_sysfs_add(struct device *dev)
-{
-	return 0;
-}
-
-static inline void dpm_sysfs_remove(struct device *dev)
-{
-}
+static inline int dpm_sysfs_add(struct device *dev) { return 0; }
+static inline void dpm_sysfs_remove(struct device *dev) {}
+static inline void rpm_sysfs_remove(struct device *dev) {}
+static inline int wakeup_sysfs_add(struct device *dev) { return 0; }
+static inline void wakeup_sysfs_remove(struct device *dev) {}
 
 #endif
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index 656493a5e073..54597c859ecb 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -168,6 +168,7 @@ static int rpm_check_suspend_allowed(struct device *dev)
 static int rpm_idle(struct device *dev, int rpmflags)
 {
 	int (*callback)(struct device *);
+	int (*domain_callback)(struct device *);
 	int retval;
 
 	retval = rpm_check_suspend_allowed(dev);
@@ -213,19 +214,28 @@ static int rpm_idle(struct device *dev, int rpmflags)
 
 	dev->power.idle_notification = true;
 
-	if (dev->bus && dev->bus->pm && dev->bus->pm->runtime_idle)
-		callback = dev->bus->pm->runtime_idle;
-	else if (dev->type && dev->type->pm && dev->type->pm->runtime_idle)
+	if (dev->type && dev->type->pm)
 		callback = dev->type->pm->runtime_idle;
 	else if (dev->class && dev->class->pm)
 		callback = dev->class->pm->runtime_idle;
+	else if (dev->bus && dev->bus->pm)
+		callback = dev->bus->pm->runtime_idle;
 	else
 		callback = NULL;
 
-	if (callback) {
+	if (dev->pwr_domain)
+		domain_callback = dev->pwr_domain->ops.runtime_idle;
+	else
+		domain_callback = NULL;
+
+	if (callback || domain_callback) {
 		spin_unlock_irq(&dev->power.lock);
 
-		callback(dev);
+		if (domain_callback)
+			retval = domain_callback(dev);
+
+		if (!retval && callback)
+			callback(dev);
 
 		spin_lock_irq(&dev->power.lock);
 	}
@@ -372,12 +382,12 @@ static int rpm_suspend(struct device *dev, int rpmflags)
 
 	__update_runtime_status(dev, RPM_SUSPENDING);
 
-	if (dev->bus && dev->bus->pm && dev->bus->pm->runtime_suspend)
-		callback = dev->bus->pm->runtime_suspend;
-	else if (dev->type && dev->type->pm && dev->type->pm->runtime_suspend)
+	if (dev->type && dev->type->pm)
 		callback = dev->type->pm->runtime_suspend;
 	else if (dev->class && dev->class->pm)
 		callback = dev->class->pm->runtime_suspend;
+	else if (dev->bus && dev->bus->pm)
+		callback = dev->bus->pm->runtime_suspend;
 	else
 		callback = NULL;
 
@@ -390,6 +400,8 @@ static int rpm_suspend(struct device *dev, int rpmflags)
 		else
 			pm_runtime_cancel_pending(dev);
 	} else {
+		if (dev->pwr_domain)
+			rpm_callback(dev->pwr_domain->ops.runtime_suspend, dev);
  no_callback:
 		__update_runtime_status(dev, RPM_SUSPENDED);
 		pm_runtime_deactivate_timer(dev);
@@ -407,12 +419,15 @@ static int rpm_suspend(struct device *dev, int rpmflags)
 		goto out;
 	}
 
+	/* Maybe the parent is now able to suspend. */
 	if (parent && !parent->power.ignore_children && !dev->power.irq_safe) {
-		spin_unlock_irq(&dev->power.lock);
+		spin_unlock(&dev->power.lock);
 
-		pm_request_idle(parent);
+		spin_lock(&parent->power.lock);
+		rpm_idle(parent, RPM_ASYNC);
+		spin_unlock(&parent->power.lock);
 
-		spin_lock_irq(&dev->power.lock);
+		spin_lock(&dev->power.lock);
 	}
 
  out:
@@ -566,12 +581,15 @@ static int rpm_resume(struct device *dev, int rpmflags)
 
 	__update_runtime_status(dev, RPM_RESUMING);
 
-	if (dev->bus && dev->bus->pm && dev->bus->pm->runtime_resume)
-		callback = dev->bus->pm->runtime_resume;
-	else if (dev->type && dev->type->pm && dev->type->pm->runtime_resume)
+	if (dev->pwr_domain)
+		rpm_callback(dev->pwr_domain->ops.runtime_resume, dev);
+
+	if (dev->type && dev->type->pm)
 		callback = dev->type->pm->runtime_resume;
 	else if (dev->class && dev->class->pm)
 		callback = dev->class->pm->runtime_resume;
+	else if (dev->bus && dev->bus->pm)
+		callback = dev->bus->pm->runtime_resume;
 	else
 		callback = NULL;
 
diff --git a/drivers/base/power/sysfs.c b/drivers/base/power/sysfs.c
index 0b1e46bf3e56..fff49bee781d 100644
--- a/drivers/base/power/sysfs.c
+++ b/drivers/base/power/sysfs.c
@@ -431,26 +431,18 @@ static ssize_t async_store(struct device *dev, struct device_attribute *attr,
 static DEVICE_ATTR(async, 0644, async_show, async_store);
 #endif /* CONFIG_PM_ADVANCED_DEBUG */
 
-static struct attribute * power_attrs[] = {
-	&dev_attr_wakeup.attr,
-#ifdef CONFIG_PM_SLEEP
-	&dev_attr_wakeup_count.attr,
-	&dev_attr_wakeup_active_count.attr,
-	&dev_attr_wakeup_hit_count.attr,
-	&dev_attr_wakeup_active.attr,
-	&dev_attr_wakeup_total_time_ms.attr,
-	&dev_attr_wakeup_max_time_ms.attr,
-	&dev_attr_wakeup_last_time_ms.attr,
-#endif
+static struct attribute *power_attrs[] = {
 #ifdef CONFIG_PM_ADVANCED_DEBUG
+#ifdef CONFIG_PM_SLEEP
 	&dev_attr_async.attr,
+#endif
 #ifdef CONFIG_PM_RUNTIME
 	&dev_attr_runtime_status.attr,
 	&dev_attr_runtime_usage.attr,
 	&dev_attr_runtime_active_kids.attr,
 	&dev_attr_runtime_enabled.attr,
 #endif
-#endif
+#endif /* CONFIG_PM_ADVANCED_DEBUG */
 	NULL,
 };
 static struct attribute_group pm_attr_group = {
@@ -458,9 +450,26 @@ static struct attribute_group pm_attr_group = {
 	.attrs	= power_attrs,
 };
 
-#ifdef CONFIG_PM_RUNTIME
+static struct attribute *wakeup_attrs[] = {
+#ifdef CONFIG_PM_SLEEP
+	&dev_attr_wakeup.attr,
+	&dev_attr_wakeup_count.attr,
+	&dev_attr_wakeup_active_count.attr,
+	&dev_attr_wakeup_hit_count.attr,
+	&dev_attr_wakeup_active.attr,
+	&dev_attr_wakeup_total_time_ms.attr,
+	&dev_attr_wakeup_max_time_ms.attr,
+	&dev_attr_wakeup_last_time_ms.attr,
+#endif
+	NULL,
+};
+static struct attribute_group pm_wakeup_attr_group = {
+	.name	= power_group_name,
+	.attrs	= wakeup_attrs,
+};
 
 static struct attribute *runtime_attrs[] = {
+#ifdef CONFIG_PM_RUNTIME
 #ifndef CONFIG_PM_ADVANCED_DEBUG
 	&dev_attr_runtime_status.attr,
 #endif
@@ -468,6 +477,7 @@ static struct attribute *runtime_attrs[] = {
 	&dev_attr_runtime_suspended_time.attr,
 	&dev_attr_runtime_active_time.attr,
 	&dev_attr_autosuspend_delay_ms.attr,
+#endif /* CONFIG_PM_RUNTIME */
 	NULL,
 };
 static struct attribute_group pm_runtime_attr_group = {
@@ -480,35 +490,49 @@ int dpm_sysfs_add(struct device *dev)
 	int rc;
 
 	rc = sysfs_create_group(&dev->kobj, &pm_attr_group);
-	if (rc == 0 && !dev->power.no_callbacks) {
+	if (rc)
+		return rc;
+
+	if (pm_runtime_callbacks_present(dev)) {
 		rc = sysfs_merge_group(&dev->kobj, &pm_runtime_attr_group);
 		if (rc)
-			sysfs_remove_group(&dev->kobj, &pm_attr_group);
+			goto err_out;
+	}
+
+	if (device_can_wakeup(dev)) {
+		rc = sysfs_merge_group(&dev->kobj, &pm_wakeup_attr_group);
+		if (rc) {
+			if (pm_runtime_callbacks_present(dev))
+				sysfs_unmerge_group(&dev->kobj,
+						    &pm_runtime_attr_group);
+			goto err_out;
+		}
 	}
+	return 0;
+
+ err_out:
+	sysfs_remove_group(&dev->kobj, &pm_attr_group);
 	return rc;
 }
 
-void rpm_sysfs_remove(struct device *dev)
+int wakeup_sysfs_add(struct device *dev)
 {
-	sysfs_unmerge_group(&dev->kobj, &pm_runtime_attr_group);
+	return sysfs_merge_group(&dev->kobj, &pm_wakeup_attr_group);
 }
 
-void dpm_sysfs_remove(struct device *dev)
+void wakeup_sysfs_remove(struct device *dev)
 {
-	rpm_sysfs_remove(dev);
-	sysfs_remove_group(&dev->kobj, &pm_attr_group);
+	sysfs_unmerge_group(&dev->kobj, &pm_wakeup_attr_group);
 }
 
-#else /* CONFIG_PM_RUNTIME */
-
-int dpm_sysfs_add(struct device * dev)
+void rpm_sysfs_remove(struct device *dev)
 {
-	return sysfs_create_group(&dev->kobj, &pm_attr_group);
+	sysfs_unmerge_group(&dev->kobj, &pm_runtime_attr_group);
 }
 
-void dpm_sysfs_remove(struct device * dev)
+void dpm_sysfs_remove(struct device *dev)
 {
+	rpm_sysfs_remove(dev);
+	sysfs_unmerge_group(&dev->kobj, &pm_wakeup_attr_group);
 	sysfs_remove_group(&dev->kobj, &pm_attr_group);
 }
-
-#endif
diff --git a/drivers/base/power/trace.c b/drivers/base/power/trace.c
index 9f4258df4cfd..c80e138b62fe 100644
--- a/drivers/base/power/trace.c
+++ b/drivers/base/power/trace.c
@@ -112,7 +112,7 @@ static unsigned int read_magic_time(void)
 	unsigned int val;
 
 	get_rtc_time(&time);
-	printk("Time: %2d:%02d:%02d  Date: %02d/%02d/%02d\n",
+	pr_info("Time: %2d:%02d:%02d  Date: %02d/%02d/%02d\n",
 		time.tm_hour, time.tm_min, time.tm_sec,
 		time.tm_mon + 1, time.tm_mday, time.tm_year % 100);
 	val = time.tm_year;				/* 100 years */
@@ -179,7 +179,7 @@ static int show_file_hash(unsigned int value)
 		unsigned int hash = hash_string(lineno, file, FILEHASH);
 		if (hash != value)
 			continue;
-		printk("  hash matches %s:%u\n", file, lineno);
+		pr_info("  hash matches %s:%u\n", file, lineno);
 		match++;
 	}
 	return match;
@@ -255,7 +255,7 @@ static int late_resume_init(void)
 	val = val / FILEHASH;
 	dev = val /* % DEVHASH */;
 
-	printk("  Magic number: %d:%d:%d\n", user, file, dev);
+	pr_info("  Magic number: %d:%d:%d\n", user, file, dev);
 	show_file_hash(file);
 	show_dev_hash(dev);
 	return 0;
diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c
index 8ec406d8f548..4573c83df6dd 100644
--- a/drivers/base/power/wakeup.c
+++ b/drivers/base/power/wakeup.c
@@ -24,12 +24,26 @@
  */
 bool events_check_enabled;
 
-/* The counter of registered wakeup events. */
-static atomic_t event_count = ATOMIC_INIT(0);
-/* A preserved old value of event_count. */
+/*
+ * Combined counters of registered wakeup events and wakeup events in progress.
+ * They need to be modified together atomically, so it's better to use one
+ * atomic variable to hold them both.
+ */
+static atomic_t combined_event_count = ATOMIC_INIT(0);
+
+#define IN_PROGRESS_BITS	(sizeof(int) * 4)
+#define MAX_IN_PROGRESS		((1 << IN_PROGRESS_BITS) - 1)
+
+static void split_counters(unsigned int *cnt, unsigned int *inpr)
+{
+	unsigned int comb = atomic_read(&combined_event_count);
+
+	*cnt = (comb >> IN_PROGRESS_BITS);
+	*inpr = comb & MAX_IN_PROGRESS;
+}
+
+/* A preserved old value of the events counter. */
 static unsigned int saved_count;
-/* The counter of wakeup events being processed. */
-static atomic_t events_in_progress = ATOMIC_INIT(0);
 
 static DEFINE_SPINLOCK(events_lock);
 
@@ -228,6 +242,35 @@ int device_wakeup_disable(struct device *dev)
 EXPORT_SYMBOL_GPL(device_wakeup_disable);
 
 /**
+ * device_set_wakeup_capable - Set/reset device wakeup capability flag.
+ * @dev: Device to handle.
+ * @capable: Whether or not @dev is capable of waking up the system from sleep.
+ *
+ * If @capable is set, set the @dev's power.can_wakeup flag and add its
+ * wakeup-related attributes to sysfs.  Otherwise, unset the @dev's
+ * power.can_wakeup flag and remove its wakeup-related attributes from sysfs.
+ *
+ * This function may sleep and it can't be called from any context where
+ * sleeping is not allowed.
+ */
+void device_set_wakeup_capable(struct device *dev, bool capable)
+{
+	if (!!dev->power.can_wakeup == !!capable)
+		return;
+
+	if (device_is_registered(dev)) {
+		if (capable) {
+			if (wakeup_sysfs_add(dev))
+				return;
+		} else {
+			wakeup_sysfs_remove(dev);
+		}
+	}
+	dev->power.can_wakeup = capable;
+}
+EXPORT_SYMBOL_GPL(device_set_wakeup_capable);
+
+/**
  * device_init_wakeup - Device wakeup initialization.
  * @dev: Device to handle.
  * @enable: Whether or not to enable @dev as a wakeup device.
@@ -307,7 +350,8 @@ static void wakeup_source_activate(struct wakeup_source *ws)
 	ws->timer_expires = jiffies;
 	ws->last_time = ktime_get();
 
-	atomic_inc(&events_in_progress);
+	/* Increment the counter of events in progress. */
+	atomic_inc(&combined_event_count);
 }
 
 /**
@@ -394,14 +438,10 @@ static void wakeup_source_deactivate(struct wakeup_source *ws)
 	del_timer(&ws->timer);
 
 	/*
-	 * event_count has to be incremented before events_in_progress is
-	 * modified, so that the callers of pm_check_wakeup_events() and
-	 * pm_save_wakeup_count() don't see the old value of event_count and
-	 * events_in_progress equal to zero at the same time.
+	 * Increment the counter of registered wakeup events and decrement the
+	 * couter of wakeup events in progress simultaneously.
 	 */
-	atomic_inc(&event_count);
-	smp_mb__before_atomic_dec();
-	atomic_dec(&events_in_progress);
+	atomic_add(MAX_IN_PROGRESS, &combined_event_count);
 }
 
 /**
@@ -556,8 +596,10 @@ bool pm_wakeup_pending(void)
 
 	spin_lock_irqsave(&events_lock, flags);
 	if (events_check_enabled) {
-		ret = ((unsigned int)atomic_read(&event_count) != saved_count)
-			|| atomic_read(&events_in_progress);
+		unsigned int cnt, inpr;
+
+		split_counters(&cnt, &inpr);
+		ret = (cnt != saved_count || inpr > 0);
 		events_check_enabled = !ret;
 	}
 	spin_unlock_irqrestore(&events_lock, flags);
@@ -573,25 +615,25 @@ bool pm_wakeup_pending(void)
  * Store the number of registered wakeup events at the address in @count.  Block
  * if the current number of wakeup events being processed is nonzero.
  *
- * Return false if the wait for the number of wakeup events being processed to
+ * Return 'false' if the wait for the number of wakeup events being processed to
  * drop down to zero has been interrupted by a signal (and the current number
- * of wakeup events being processed is still nonzero).  Otherwise return true.
+ * of wakeup events being processed is still nonzero).  Otherwise return 'true'.
  */
 bool pm_get_wakeup_count(unsigned int *count)
 {
-	bool ret;
-
-	if (capable(CAP_SYS_ADMIN))
-		events_check_enabled = false;
+	unsigned int cnt, inpr;
 
-	while (atomic_read(&events_in_progress) && !signal_pending(current)) {
+	for (;;) {
+		split_counters(&cnt, &inpr);
+		if (inpr == 0 || signal_pending(current))
+			break;
 		pm_wakeup_update_hit_counts();
 		schedule_timeout_interruptible(msecs_to_jiffies(TIMEOUT));
 	}
 
-	ret = !atomic_read(&events_in_progress);
-	*count = atomic_read(&event_count);
-	return ret;
+	split_counters(&cnt, &inpr);
+	*count = cnt;
+	return !inpr;
 }
 
 /**
@@ -600,24 +642,25 @@ bool pm_get_wakeup_count(unsigned int *count)
  *
  * If @count is equal to the current number of registered wakeup events and the
  * current number of wakeup events being processed is zero, store @count as the
- * old number of registered wakeup events to be used by pm_check_wakeup_events()
- * and return true.  Otherwise return false.
+ * old number of registered wakeup events for pm_check_wakeup_events(), enable
+ * wakeup events detection and return 'true'.  Otherwise disable wakeup events
+ * detection and return 'false'.
  */
 bool pm_save_wakeup_count(unsigned int count)
 {
-	bool ret = false;
+	unsigned int cnt, inpr;
 
+	events_check_enabled = false;
 	spin_lock_irq(&events_lock);
-	if (count == (unsigned int)atomic_read(&event_count)
-	    && !atomic_read(&events_in_progress)) {
+	split_counters(&cnt, &inpr);
+	if (cnt == count && inpr == 0) {
 		saved_count = count;
 		events_check_enabled = true;
-		ret = true;
 	}
 	spin_unlock_irq(&events_lock);
-	if (!ret)
+	if (!events_check_enabled)
 		pm_wakeup_update_hit_counts();
-	return ret;
+	return events_check_enabled;
 }
 
 static struct dentry *wakeup_sources_stats_dentry;
diff --git a/drivers/base/sys.c b/drivers/base/sys.c
index 1667aaf4fde6..f6fb54741602 100644
--- a/drivers/base/sys.c
+++ b/drivers/base/sys.c
@@ -166,6 +166,36 @@ EXPORT_SYMBOL_GPL(sysdev_class_unregister);
 
 static DEFINE_MUTEX(sysdev_drivers_lock);
 
+/*
+ * @dev != NULL means that we're unwinding because some drv->add()
+ * failed for some reason. You need to grab sysdev_drivers_lock before
+ * calling this.
+ */
+static void __sysdev_driver_remove(struct sysdev_class *cls,
+				   struct sysdev_driver *drv,
+				   struct sys_device *from_dev)
+{
+	struct sys_device *dev = from_dev;
+
+	list_del_init(&drv->entry);
+	if (!cls)
+		return;
+
+	if (!drv->remove)
+		goto kset_put;
+
+	if (dev)
+		list_for_each_entry_continue_reverse(dev, &cls->kset.list,
+						     kobj.entry)
+			drv->remove(dev);
+	else
+		list_for_each_entry(dev, &cls->kset.list, kobj.entry)
+			drv->remove(dev);
+
+kset_put:
+	kset_put(&cls->kset);
+}
+
 /**
  *	sysdev_driver_register - Register auxillary driver
  *	@cls:	Device class driver belongs to.
@@ -175,14 +205,14 @@ static DEFINE_MUTEX(sysdev_drivers_lock);
  *	called on each operation on devices of that class. The refcount
  *	of @cls is incremented.
  */
-
 int sysdev_driver_register(struct sysdev_class *cls, struct sysdev_driver *drv)
 {
+	struct sys_device *dev = NULL;
 	int err = 0;
 
 	if (!cls) {
-		WARN(1, KERN_WARNING "sysdev: invalid class passed to "
-			"sysdev_driver_register!\n");
+		WARN(1, KERN_WARNING "sysdev: invalid class passed to %s!\n",
+			__func__);
 		return -EINVAL;
 	}
 
@@ -198,19 +228,27 @@ int sysdev_driver_register(struct sysdev_class *cls, struct sysdev_driver *drv)
 
 		/* If devices of this class already exist, tell the driver */
 		if (drv->add) {
-			struct sys_device *dev;
-			list_for_each_entry(dev, &cls->kset.list, kobj.entry)
-				drv->add(dev);
+			list_for_each_entry(dev, &cls->kset.list, kobj.entry) {
+				err = drv->add(dev);
+				if (err)
+					goto unwind;
+			}
 		}
 	} else {
 		err = -EINVAL;
 		WARN(1, KERN_ERR "%s: invalid device class\n", __func__);
 	}
+
+	goto unlock;
+
+unwind:
+	__sysdev_driver_remove(cls, drv, dev);
+
+unlock:
 	mutex_unlock(&sysdev_drivers_lock);
 	return err;
 }
 
-
 /**
  *	sysdev_driver_unregister - Remove an auxillary driver.
  *	@cls:	Class driver belongs to.
@@ -220,23 +258,12 @@ void sysdev_driver_unregister(struct sysdev_class *cls,
 			      struct sysdev_driver *drv)
 {
 	mutex_lock(&sysdev_drivers_lock);
-	list_del_init(&drv->entry);
-	if (cls) {
-		if (drv->remove) {
-			struct sys_device *dev;
-			list_for_each_entry(dev, &cls->kset.list, kobj.entry)
-				drv->remove(dev);
-		}
-		kset_put(&cls->kset);
-	}
+	__sysdev_driver_remove(cls, drv, NULL);
 	mutex_unlock(&sysdev_drivers_lock);
 }
-
 EXPORT_SYMBOL_GPL(sysdev_driver_register);
 EXPORT_SYMBOL_GPL(sysdev_driver_unregister);
 
-
-
 /**
  *	sysdev_register - add a system device to the tree
  *	@sysdev:	device in question
diff --git a/drivers/base/syscore.c b/drivers/base/syscore.c
new file mode 100644
index 000000000000..90af2943f9e4
--- /dev/null
+++ b/drivers/base/syscore.c
@@ -0,0 +1,117 @@
+/*
+ *  syscore.c - Execution of system core operations.
+ *
+ *  Copyright (C) 2011 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc.
+ *
+ *  This file is released under the GPLv2.
+ */
+
+#include <linux/syscore_ops.h>
+#include <linux/mutex.h>
+#include <linux/module.h>
+
+static LIST_HEAD(syscore_ops_list);
+static DEFINE_MUTEX(syscore_ops_lock);
+
+/**
+ * register_syscore_ops - Register a set of system core operations.
+ * @ops: System core operations to register.
+ */
+void register_syscore_ops(struct syscore_ops *ops)
+{
+	mutex_lock(&syscore_ops_lock);
+	list_add_tail(&ops->node, &syscore_ops_list);
+	mutex_unlock(&syscore_ops_lock);
+}
+EXPORT_SYMBOL_GPL(register_syscore_ops);
+
+/**
+ * unregister_syscore_ops - Unregister a set of system core operations.
+ * @ops: System core operations to unregister.
+ */
+void unregister_syscore_ops(struct syscore_ops *ops)
+{
+	mutex_lock(&syscore_ops_lock);
+	list_del(&ops->node);
+	mutex_unlock(&syscore_ops_lock);
+}
+EXPORT_SYMBOL_GPL(unregister_syscore_ops);
+
+#ifdef CONFIG_PM_SLEEP
+/**
+ * syscore_suspend - Execute all the registered system core suspend callbacks.
+ *
+ * This function is executed with one CPU on-line and disabled interrupts.
+ */
+int syscore_suspend(void)
+{
+	struct syscore_ops *ops;
+	int ret = 0;
+
+	WARN_ONCE(!irqs_disabled(),
+		"Interrupts enabled before system core suspend.\n");
+
+	list_for_each_entry_reverse(ops, &syscore_ops_list, node)
+		if (ops->suspend) {
+			if (initcall_debug)
+				pr_info("PM: Calling %pF\n", ops->suspend);
+			ret = ops->suspend();
+			if (ret)
+				goto err_out;
+			WARN_ONCE(!irqs_disabled(),
+				"Interrupts enabled after %pF\n", ops->suspend);
+		}
+
+	return 0;
+
+ err_out:
+	pr_err("PM: System core suspend callback %pF failed.\n", ops->suspend);
+
+	list_for_each_entry_continue(ops, &syscore_ops_list, node)
+		if (ops->resume)
+			ops->resume();
+
+	return ret;
+}
+
+/**
+ * syscore_resume - Execute all the registered system core resume callbacks.
+ *
+ * This function is executed with one CPU on-line and disabled interrupts.
+ */
+void syscore_resume(void)
+{
+	struct syscore_ops *ops;
+
+	WARN_ONCE(!irqs_disabled(),
+		"Interrupts enabled before system core resume.\n");
+
+	list_for_each_entry(ops, &syscore_ops_list, node)
+		if (ops->resume) {
+			if (initcall_debug)
+				pr_info("PM: Calling %pF\n", ops->resume);
+			ops->resume();
+			WARN_ONCE(!irqs_disabled(),
+				"Interrupts enabled after %pF\n", ops->resume);
+		}
+}
+#endif /* CONFIG_PM_SLEEP */
+
+/**
+ * syscore_shutdown - Execute all the registered system core shutdown callbacks.
+ */
+void syscore_shutdown(void)
+{
+	struct syscore_ops *ops;
+
+	mutex_lock(&syscore_ops_lock);
+
+	list_for_each_entry_reverse(ops, &syscore_ops_list, node)
+		if (ops->shutdown) {
+			if (initcall_debug)
+				pr_info("PM: Calling %pF\n", ops->shutdown);
+			ops->shutdown();
+		}
+
+	mutex_unlock(&syscore_ops_lock);
+}