10 files changed, 320 insertions, 35 deletions

diff --git a/drivers/acpi/acpi_memhotplug.c b/drivers/acpi/acpi_memhotplug.c
index 034d3e72aa92..da1f82b445e0 100644
--- a/drivers/acpi/acpi_memhotplug.c
+++ b/drivers/acpi/acpi_memhotplug.c
@@ -280,9 +280,11 @@ static int acpi_memory_enable_device(struct acpi_memory_device *mem_device)
 
 static int acpi_memory_remove_memory(struct acpi_memory_device *mem_device)
 {
-	int result = 0;
+	int result = 0, nid;
 	struct acpi_memory_info *info, *n;
 
+	nid = acpi_get_node(mem_device->device->handle);
+
 	list_for_each_entry_safe(info, n, &mem_device->res_list, list) {
 		if (info->failed)
 			/* The kernel does not use this memory block */
@@ -295,7 +297,9 @@ static int acpi_memory_remove_memory(struct acpi_memory_device *mem_device)
 			 */
 			return -EBUSY;
 
-		result = remove_memory(info->start_addr, info->length);
+		if (nid < 0)
+			nid = memory_add_physaddr_to_nid(info->start_addr);
+		result = remove_memory(nid, info->start_addr, info->length);
 		if (result)
 			return result;
 
diff --git a/drivers/acpi/numa.c b/drivers/acpi/numa.c
index 33e609f63585..59844ee149be 100644
--- a/drivers/acpi/numa.c
+++ b/drivers/acpi/numa.c
@@ -282,10 +282,10 @@ acpi_table_parse_srat(enum acpi_srat_type id,
 					    handler, max_entries);
 }
 
-int __init acpi_numa_init(void)
-{
-	int cnt = 0;
+static int srat_mem_cnt;
 
+void __init early_parse_srat(void)
+{
 	/*
 	 * Should not limit number with cpu num that is from NR_CPUS or nr_cpus=
 	 * SRAT cpu entries could have different order with that in MADT.
@@ -295,21 +295,24 @@ int __init acpi_numa_init(void)
 	/* SRAT: Static Resource Affinity Table */
 	if (!acpi_table_parse(ACPI_SIG_SRAT, acpi_parse_srat)) {
 		acpi_table_parse_srat(ACPI_SRAT_TYPE_X2APIC_CPU_AFFINITY,
-				     acpi_parse_x2apic_affinity, 0);
+				      acpi_parse_x2apic_affinity, 0);
 		acpi_table_parse_srat(ACPI_SRAT_TYPE_CPU_AFFINITY,
-				     acpi_parse_processor_affinity, 0);
-		cnt = acpi_table_parse_srat(ACPI_SRAT_TYPE_MEMORY_AFFINITY,
-					    acpi_parse_memory_affinity,
-					    NR_NODE_MEMBLKS);
+				      acpi_parse_processor_affinity, 0);
+		srat_mem_cnt = acpi_table_parse_srat(ACPI_SRAT_TYPE_MEMORY_AFFINITY,
+						     acpi_parse_memory_affinity,
+						     NR_NODE_MEMBLKS);
 	}
+}
 
+int __init acpi_numa_init(void)
+{
 	/* SLIT: System Locality Information Table */
 	acpi_table_parse(ACPI_SIG_SLIT, acpi_parse_slit);
 
 	acpi_numa_arch_fixup();
 
-	if (cnt < 0)
-		return cnt;
+	if (srat_mem_cnt < 0)
+		return srat_mem_cnt;
 	else if (!parsed_numa_memblks)
 		return -ENOENT;
 	return 0;
diff --git a/drivers/acpi/processor_driver.c b/drivers/acpi/processor_driver.c
index cbf1f122666b..df34bd04ae62 100644
--- a/drivers/acpi/processor_driver.c
+++ b/drivers/acpi/processor_driver.c
@@ -45,6 +45,7 @@
 #include <linux/cpuidle.h>
 #include <linux/slab.h>
 #include <linux/acpi.h>
+#include <linux/memory_hotplug.h>
 
 #include <asm/io.h>
 #include <asm/cpu.h>
@@ -641,6 +642,7 @@ static int acpi_processor_remove(struct acpi_device *device)
 
 	per_cpu(processors, pr->id) = NULL;
 	per_cpu(processor_device_array, pr->id) = NULL;
+	try_offline_node(cpu_to_node(pr->id));
 
 free:
 	free_cpumask_var(pr->throttling.shared_cpu_map);
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index 83d0b17ba1c2..a51007b79032 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -693,6 +693,12 @@ int offline_memory_block(struct memory_block *mem)
 	return ret;
 }
 
+/* return true if the memory block is offlined, otherwise, return false */
+bool is_memblock_offlined(struct memory_block *mem)
+{
+	return mem->state == MEM_OFFLINE;
+}
+
 /*
  * Initialize the sysfs support for memory devices...
  */
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index 3148b10dc2e5..1244930e3d7a 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -124,6 +124,76 @@ unsigned long pm_runtime_autosuspend_expiration(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(pm_runtime_autosuspend_expiration);
 
+static int dev_memalloc_noio(struct device *dev, void *data)
+{
+	return dev->power.memalloc_noio;
+}
+
+/*
+ * pm_runtime_set_memalloc_noio - Set a device's memalloc_noio flag.
+ * @dev: Device to handle.
+ * @enable: True for setting the flag and False for clearing the flag.
+ *
+ * Set the flag for all devices in the path from the device to the
+ * root device in the device tree if @enable is true, otherwise clear
+ * the flag for devices in the path whose siblings don't set the flag.
+ *
+ * The function should only be called by block device, or network
+ * device driver for solving the deadlock problem during runtime
+ * resume/suspend:
+ *
+ *     If memory allocation with GFP_KERNEL is called inside runtime
+ *     resume/suspend callback of any one of its ancestors(or the
+ *     block device itself), the deadlock may be triggered inside the
+ *     memory allocation since it might not complete until the block
+ *     device becomes active and the involed page I/O finishes. The
+ *     situation is pointed out first by Alan Stern. Network device
+ *     are involved in iSCSI kind of situation.
+ *
+ * The lock of dev_hotplug_mutex is held in the function for handling
+ * hotplug race because pm_runtime_set_memalloc_noio() may be called
+ * in async probe().
+ *
+ * The function should be called between device_add() and device_del()
+ * on the affected device(block/network device).
+ */
+void pm_runtime_set_memalloc_noio(struct device *dev, bool enable)
+{
+	static DEFINE_MUTEX(dev_hotplug_mutex);
+
+	mutex_lock(&dev_hotplug_mutex);
+	for (;;) {
+		bool enabled;
+
+		/* hold power lock since bitfield is not SMP-safe. */
+		spin_lock_irq(&dev->power.lock);
+		enabled = dev->power.memalloc_noio;
+		dev->power.memalloc_noio = enable;
+		spin_unlock_irq(&dev->power.lock);
+
+		/*
+		 * not need to enable ancestors any more if the device
+		 * has been enabled.
+		 */
+		if (enabled && enable)
+			break;
+
+		dev = dev->parent;
+
+		/*
+		 * clear flag of the parent device only if all the
+		 * children don't set the flag because ancestor's
+		 * flag was set by any one of the descendants.
+		 */
+		if (!dev || (!enable &&
+			     device_for_each_child(dev, NULL,
+						   dev_memalloc_noio)))
+			break;
+	}
+	mutex_unlock(&dev_hotplug_mutex);
+}
+EXPORT_SYMBOL_GPL(pm_runtime_set_memalloc_noio);
+
 /**
  * rpm_check_suspend_allowed - Test whether a device may be suspended.
  * @dev: Device to test.
@@ -278,7 +348,24 @@ static int rpm_callback(int (*cb)(struct device *), struct device *dev)
 	if (!cb)
 		return -ENOSYS;
 
-	retval = __rpm_callback(cb, dev);
+	if (dev->power.memalloc_noio) {
+		unsigned int noio_flag;
+
+		/*
+		 * Deadlock might be caused if memory allocation with
+		 * GFP_KERNEL happens inside runtime_suspend and
+		 * runtime_resume callbacks of one block device's
+		 * ancestor or the block device itself. Network
+		 * device might be thought as part of iSCSI block
+		 * device, so network device and its ancestor should
+		 * be marked as memalloc_noio too.
+		 */
+		noio_flag = memalloc_noio_save();
+		retval = __rpm_callback(cb, dev);
+		memalloc_noio_restore(noio_flag);
+	} else {
+		retval = __rpm_callback(cb, dev);
+	}
 
 	dev->power.runtime_error = retval;
 	return retval != -EACCES ? retval : -EIO;
diff --git a/drivers/firmware/memmap.c b/drivers/firmware/memmap.c
index 90723e65b081..0b5b5f619c75 100644
--- a/drivers/firmware/memmap.c
+++ b/drivers/firmware/memmap.c
@@ -21,6 +21,7 @@
 #include <linux/types.h>
 #include <linux/bootmem.h>
 #include <linux/slab.h>
+#include <linux/mm.h>
 
 /*
  * Data types ------------------------------------------------------------------
@@ -52,6 +53,9 @@ static ssize_t start_show(struct firmware_map_entry *entry, char *buf);
 static ssize_t end_show(struct firmware_map_entry *entry, char *buf);
 static ssize_t type_show(struct firmware_map_entry *entry, char *buf);
 
+static struct firmware_map_entry * __meminit
+firmware_map_find_entry(u64 start, u64 end, const char *type);
+
 /*
  * Static data -----------------------------------------------------------------
  */
@@ -79,7 +83,52 @@ static const struct sysfs_ops memmap_attr_ops = {
 	.show = memmap_attr_show,
 };
 
-static struct kobj_type memmap_ktype = {
+/* Firmware memory map entries. */
+static LIST_HEAD(map_entries);
+static DEFINE_SPINLOCK(map_entries_lock);
+
+/*
+ * For memory hotplug, there is no way to free memory map entries allocated
+ * by boot mem after the system is up. So when we hot-remove memory whose
+ * map entry is allocated by bootmem, we need to remember the storage and
+ * reuse it when the memory is hot-added again.
+ */
+static LIST_HEAD(map_entries_bootmem);
+static DEFINE_SPINLOCK(map_entries_bootmem_lock);
+
+
+static inline struct firmware_map_entry *
+to_memmap_entry(struct kobject *kobj)
+{
+	return container_of(kobj, struct firmware_map_entry, kobj);
+}
+
+static void __meminit release_firmware_map_entry(struct kobject *kobj)
+{
+	struct firmware_map_entry *entry = to_memmap_entry(kobj);
+
+	if (PageReserved(virt_to_page(entry))) {
+		/*
+		 * Remember the storage allocated by bootmem, and reuse it when
+		 * the memory is hot-added again. The entry will be added to
+		 * map_entries_bootmem here, and deleted from &map_entries in
+		 * firmware_map_remove_entry().
+		 */
+		if (firmware_map_find_entry(entry->start, entry->end,
+		    entry->type)) {
+			spin_lock(&map_entries_bootmem_lock);
+			list_add(&entry->list, &map_entries_bootmem);
+			spin_unlock(&map_entries_bootmem_lock);
+		}
+
+		return;
+	}
+
+	kfree(entry);
+}
+
+static struct kobj_type __refdata memmap_ktype = {
+	.release	= release_firmware_map_entry,
 	.sysfs_ops	= &memmap_attr_ops,
 	.default_attrs	= def_attrs,
 };
@@ -88,13 +137,6 @@ static struct kobj_type memmap_ktype = {
  * Registration functions ------------------------------------------------------
  */
 
-/*
- * Firmware memory map entries. No locking is needed because the
- * firmware_map_add() and firmware_map_add_early() functions are called
- * in firmware initialisation code in one single thread of execution.
- */
-static LIST_HEAD(map_entries);
-
 /**
  * firmware_map_add_entry() - Does the real work to add a firmware memmap entry.
  * @start: Start of the memory range.
@@ -118,11 +160,25 @@ static int firmware_map_add_entry(u64 start, u64 end,
 	INIT_LIST_HEAD(&entry->list);
 	kobject_init(&entry->kobj, &memmap_ktype);
 
+	spin_lock(&map_entries_lock);
 	list_add_tail(&entry->list, &map_entries);
+	spin_unlock(&map_entries_lock);
 
 	return 0;
 }
 
+/**
+ * firmware_map_remove_entry() - Does the real work to remove a firmware
+ * memmap entry.
+ * @entry: removed entry.
+ *
+ * The caller must hold map_entries_lock, and release it properly.
+ **/
+static inline void firmware_map_remove_entry(struct firmware_map_entry *entry)
+{
+	list_del(&entry->list);
+}
+
 /*
  * Add memmap entry on sysfs
  */
@@ -144,6 +200,78 @@ static int add_sysfs_fw_map_entry(struct firmware_map_entry *entry)
 	return 0;
 }
 
+/*
+ * Remove memmap entry on sysfs
+ */
+static inline void remove_sysfs_fw_map_entry(struct firmware_map_entry *entry)
+{
+	kobject_put(&entry->kobj);
+}
+
+/*
+ * firmware_map_find_entry_in_list() - Search memmap entry in a given list.
+ * @start: Start of the memory range.
+ * @end:   End of the memory range (exclusive).
+ * @type:  Type of the memory range.
+ * @list:  In which to find the entry.
+ *
+ * This function is to find the memmap entey of a given memory range in a
+ * given list. The caller must hold map_entries_lock, and must not release
+ * the lock until the processing of the returned entry has completed.
+ *
+ * Return: Pointer to the entry to be found on success, or NULL on failure.
+ */
+static struct firmware_map_entry * __meminit
+firmware_map_find_entry_in_list(u64 start, u64 end, const char *type,
+				struct list_head *list)
+{
+	struct firmware_map_entry *entry;
+
+	list_for_each_entry(entry, list, list)
+		if ((entry->start == start) && (entry->end == end) &&
+		    (!strcmp(entry->type, type))) {
+			return entry;
+		}
+
+	return NULL;
+}
+
+/*
+ * firmware_map_find_entry() - Search memmap entry in map_entries.
+ * @start: Start of the memory range.
+ * @end:   End of the memory range (exclusive).
+ * @type:  Type of the memory range.
+ *
+ * This function is to find the memmap entey of a given memory range.
+ * The caller must hold map_entries_lock, and must not release the lock
+ * until the processing of the returned entry has completed.
+ *
+ * Return: Pointer to the entry to be found on success, or NULL on failure.
+ */
+static struct firmware_map_entry * __meminit
+firmware_map_find_entry(u64 start, u64 end, const char *type)
+{
+	return firmware_map_find_entry_in_list(start, end, type, &map_entries);
+}
+
+/*
+ * firmware_map_find_entry_bootmem() - Search memmap entry in map_entries_bootmem.
+ * @start: Start of the memory range.
+ * @end:   End of the memory range (exclusive).
+ * @type:  Type of the memory range.
+ *
+ * This function is similar to firmware_map_find_entry except that it find the
+ * given entry in map_entries_bootmem.
+ *
+ * Return: Pointer to the entry to be found on success, or NULL on failure.
+ */
+static struct firmware_map_entry * __meminit
+firmware_map_find_entry_bootmem(u64 start, u64 end, const char *type)
+{
+	return firmware_map_find_entry_in_list(start, end, type,
+					       &map_entries_bootmem);
+}
+
 /**
  * firmware_map_add_hotplug() - Adds a firmware mapping entry when we do
  * memory hotplug.
@@ -161,9 +289,19 @@ int __meminit firmware_map_add_hotplug(u64 start, u64 end, const char *type)
 {
 	struct firmware_map_entry *entry;
 
-	entry = kzalloc(sizeof(struct firmware_map_entry), GFP_ATOMIC);
-	if (!entry)
-		return -ENOMEM;
+	entry = firmware_map_find_entry_bootmem(start, end, type);
+	if (!entry) {
+		entry = kzalloc(sizeof(struct firmware_map_entry), GFP_ATOMIC);
+		if (!entry)
+			return -ENOMEM;
+	} else {
+		/* Reuse storage allocated by bootmem. */
+		spin_lock(&map_entries_bootmem_lock);
+		list_del(&entry->list);
+		spin_unlock(&map_entries_bootmem_lock);
+
+		memset(entry, 0, sizeof(*entry));
+	}
 
 	firmware_map_add_entry(start, end, type, entry);
 	/* create the memmap entry */
@@ -196,6 +334,36 @@ int __init firmware_map_add_early(u64 start, u64 end, const char *type)
 	return firmware_map_add_entry(start, end, type, entry);
 }
 
+/**
+ * firmware_map_remove() - remove a firmware mapping entry
+ * @start: Start of the memory range.
+ * @end:   End of the memory range.
+ * @type:  Type of the memory range.
+ *
+ * removes a firmware mapping entry.
+ *
+ * Returns 0 on success, or -EINVAL if no entry.
+ **/
+int __meminit firmware_map_remove(u64 start, u64 end, const char *type)
+{
+	struct firmware_map_entry *entry;
+
+	spin_lock(&map_entries_lock);
+	entry = firmware_map_find_entry(start, end - 1, type);
+	if (!entry) {
+		spin_unlock(&map_entries_lock);
+		return -EINVAL;
+	}
+
+	firmware_map_remove_entry(entry);
+	spin_unlock(&map_entries_lock);
+
+	/* remove the memmap entry */
+	remove_sysfs_fw_map_entry(entry);
+
+	return 0;
+}
+
 /*
  * Sysfs functions -------------------------------------------------------------
  */
@@ -217,8 +385,10 @@ static ssize_t type_show(struct firmware_map_entry *entry, char *buf)
 	return snprintf(buf, PAGE_SIZE, "%s\n", entry->type);
 }
 
-#define to_memmap_attr(_attr) container_of(_attr, struct memmap_attribute, attr)
-#define to_memmap_entry(obj) container_of(obj, struct firmware_map_entry, kobj)
+static inline struct memmap_attribute *to_memmap_attr(struct attribute *attr)
+{
+	return container_of(attr, struct memmap_attribute, attr);
+}
 
 static ssize_t memmap_attr_show(struct kobject *kobj,
 				struct attribute *attr, char *buf)
diff --git a/drivers/md/persistent-data/dm-transaction-manager.c b/drivers/md/persistent-data/dm-transaction-manager.c
index d247a35da3c6..7b17a1fdeaf9 100644
--- a/drivers/md/persistent-data/dm-transaction-manager.c
+++ b/drivers/md/persistent-data/dm-transaction-manager.c
@@ -25,8 +25,8 @@ struct shadow_info {
 /*
  * It would be nice if we scaled with the size of transaction.
  */
-#define HASH_SIZE 256
-#define HASH_MASK (HASH_SIZE - 1)
+#define DM_HASH_SIZE 256
+#define DM_HASH_MASK (DM_HASH_SIZE - 1)
 
 struct dm_transaction_manager {
 	int is_clone;
@@ -36,7 +36,7 @@ struct dm_transaction_manager {
 	struct dm_space_map *sm;
 
 	spinlock_t lock;
-	struct hlist_head buckets[HASH_SIZE];
+	struct hlist_head buckets[DM_HASH_SIZE];
 };
 
 /*----------------------------------------------------------------*/
@@ -44,7 +44,7 @@ struct dm_transaction_manager {
 static int is_shadow(struct dm_transaction_manager *tm, dm_block_t b)
 {
 	int r = 0;
-	unsigned bucket = dm_hash_block(b, HASH_MASK);
+	unsigned bucket = dm_hash_block(b, DM_HASH_MASK);
 	struct shadow_info *si;
 	struct hlist_node *n;
 
@@ -71,7 +71,7 @@ static void insert_shadow(struct dm_transaction_manager *tm, dm_block_t b)
 	si = kmalloc(sizeof(*si), GFP_NOIO);
 	if (si) {
 		si->where = b;
-		bucket = dm_hash_block(b, HASH_MASK);
+		bucket = dm_hash_block(b, DM_HASH_MASK);
 		spin_lock(&tm->lock);
 		hlist_add_head(&si->hlist, tm->buckets + bucket);
 		spin_unlock(&tm->lock);
@@ -86,7 +86,7 @@ static void wipe_shadow_table(struct dm_transaction_manager *tm)
 	int i;
 
 	spin_lock(&tm->lock);
-	for (i = 0; i < HASH_SIZE; i++) {
+	for (i = 0; i < DM_HASH_SIZE; i++) {
 		bucket = tm->buckets + i;
 		hlist_for_each_entry_safe(si, n, tmp, bucket, hlist)
 			kfree(si);
@@ -115,7 +115,7 @@ static struct dm_transaction_manager *dm_tm_create(struct dm_block_manager *bm,
 	tm->sm = sm;
 
 	spin_lock_init(&tm->lock);
-	for (i = 0; i < HASH_SIZE; i++)
+	for (i = 0; i < DM_HASH_SIZE; i++)
 		INIT_HLIST_HEAD(tm->buckets + i);
 
 	return tm;
diff --git a/drivers/staging/zcache/zbud.c b/drivers/staging/zcache/zbud.c
index 328c397ea5dc..fdff5c6a0239 100644
--- a/drivers/staging/zcache/zbud.c
+++ b/drivers/staging/zcache/zbud.c
@@ -404,7 +404,7 @@ static inline struct page *zbud_unuse_zbudpage(struct zbudpage *zbudpage,
 	else
 		zbud_pers_pageframes--;
 	zbudpage_spin_unlock(zbudpage);
-	reset_page_mapcount(page);
+	page_mapcount_reset(page);
 	init_page_count(page);
 	page->index = 0;
 	return page;
diff --git a/drivers/staging/zsmalloc/zsmalloc-main.c b/drivers/staging/zsmalloc/zsmalloc-main.c
index 06f73a93a44d..e78d262c5249 100644
--- a/drivers/staging/zsmalloc/zsmalloc-main.c
+++ b/drivers/staging/zsmalloc/zsmalloc-main.c
@@ -472,7 +472,7 @@ static void reset_page(struct page *page)
 	set_page_private(page, 0);
 	page->mapping = NULL;
 	page->freelist = NULL;
-	reset_page_mapcount(page);
+	page_mapcount_reset(page);
 }
 
 static void free_zspage(struct page *first_page)
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 1775ad471edd..5480352f984d 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -5177,6 +5177,7 @@ int usb_reset_device(struct usb_device *udev)
 {
 	int ret;
 	int i;
+	unsigned int noio_flag;
 	struct usb_host_config *config = udev->actconfig;
 
 	if (udev->state == USB_STATE_NOTATTACHED ||
@@ -5186,6 +5187,17 @@ int usb_reset_device(struct usb_device *udev)
 		return -EINVAL;
 	}
 
+	/*
+	 * Don't allocate memory with GFP_KERNEL in current
+	 * context to avoid possible deadlock if usb mass
+	 * storage interface or usbnet interface(iSCSI case)
+	 * is included in current configuration. The easist
+	 * approach is to do it for every device reset,
+	 * because the device 'memalloc_noio' flag may have
+	 * not been set before reseting the usb device.
+	 */
+	noio_flag = memalloc_noio_save();
+
 	/* Prevent autosuspend during the reset */
 	usb_autoresume_device(udev);
 
@@ -5230,6 +5242,7 @@ int usb_reset_device(struct usb_device *udev)
 	}
 
 	usb_autosuspend_device(udev);
+	memalloc_noio_restore(noio_flag);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(usb_reset_device);