memory-hotplug: hot-remove physical memory

Index: linux-3.5-rc6/arch/x86/kernel/e820.c
===================================================================
@@ -944,7 +944,7 @@ void __init e820_reserve_resources(void)
 	for (i = 0; i < e820_saved.nr_map; i++) {
 		struct e820entry *entry = &e820_saved.map[i];
 		firmware_map_add_early(entry->addr,
-			entry->addr + entry->size - 1,
+			entry->addr + entry->size,
 			e820_type_to_string(entry->type));
 	}
 }

Index: linux-3.5-rc6/drivers/firmware/memmap.c
===================================================================
@@ -98,7 +98,7 @@ 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.
- * @end:   End of the memory range (inclusive).
+ * @end:   End of the memory range.
  * @type:  Type of the memory range.
  * @entry: Pre-allocated (either kmalloc() or bootmem allocator), uninitialised
  *         entry.

@@ -113,7 +113,7 @@ static int firmware_map_add_entry(u64 st
 	BUG_ON(start > end);
 
 	entry->start = start;
-	entry->end = end;
+	entry->end = end - 1;
 	entry->type = type;
 	INIT_LIST_HEAD(&entry->list);
 	kobject_init(&entry->kobj, &memmap_ktype);

@@ -148,7 +148,7 @@ static int add_sysfs_fw_map_entry(struct
  * firmware_map_add_hotplug() - Adds a firmware mapping entry when we do
  * memory hotplug.
  * @start: Start of the memory range.
- * @end:   End of the memory range (inclusive).
+ * @end:   End of the memory range.
  * @type:  Type of the memory range.
  *
  * Adds a firmware mapping entry. This function is for memory hotplug, it is

@@ -175,7 +175,7 @@ int __meminit firmware_map_add_hotplug(u
 /**
  * firmware_map_add_early() - Adds a firmware mapping entry.
  * @start: Start of the memory range.
- * @end:   End of the memory range (inclusive).
+ * @end:   End of the memory range.
  * @type:  Type of the memory range.
  *
  * Adds a firmware mapping entry. This function uses the bootmem allocator

index 8fe0e02..5cafd6b 100644
@@ -323,6 +323,7 @@ static int acpi_memory_disable_device(struct acpi_memory_device *mem_device)
 			if (result)
 				return result;
 		}
+		list_del(&info->list);
 		kfree(info);
 	}
 

index 81a9def..8957ed9 100644
@@ -318,7 +318,7 @@ static int acpi_memory_disable_device(struct acpi_memory_device *mem_device)
 	 */
 	list_for_each_entry_safe(info, n, &mem_device->res_list, list) {
 		if (info->enabled) {
-			result = remove_memory(info->start_addr, info->length);
+			result = offline_memory(info->start_addr, info->length);
 			if (result)
 				return result;
 		}

index 7dda4f7..44e7de6 100644
@@ -248,26 +248,23 @@ static bool pages_correctly_reserved(unsigned long start_pfn,
 static int
 memory_block_action(unsigned long phys_index, unsigned long action)
 {
-	unsigned long start_pfn, start_paddr;
+	unsigned long start_pfn;
 	unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
 	struct page *first_page;
 	int ret;
 
 	first_page = pfn_to_page(phys_index << PFN_SECTION_SHIFT);
+	start_pfn = page_to_pfn(first_page);
 
 	switch (action) {
 		case MEM_ONLINE:
-			start_pfn = page_to_pfn(first_page);
-
 			if (!pages_correctly_reserved(start_pfn, nr_pages))
 				return -EBUSY;
 
 			ret = online_pages(start_pfn, nr_pages);
 			break;
 		case MEM_OFFLINE:
-			start_paddr = page_to_pfn(first_page) << PAGE_SHIFT;
-			ret = remove_memory(start_paddr,
-					    nr_pages << PAGE_SHIFT);
+			ret = offline_pages(start_pfn, nr_pages);
 			break;
 		default:
 			WARN(1, KERN_WARNING "%s(%ld, %ld) unknown action: "

index 910550f..c183f39 100644
@@ -233,7 +233,8 @@ static inline int is_mem_section_removable(unsigned long pfn,
 extern int mem_online_node(int nid);
 extern int add_memory(int nid, u64 start, u64 size);
 extern int arch_add_memory(int nid, u64 start, u64 size);
-extern int remove_memory(u64 start, u64 size);
+extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages);
+extern int offline_memory(u64 start, u64 size);
 extern int sparse_add_one_section(struct zone *zone, unsigned long start_pfn,
 								int nr_pages);
 extern void sparse_remove_one_section(struct zone *zone, struct mem_section *ms);

index 427bb29..7a6659f 100644
@@ -865,7 +865,7 @@ check_pages_isolated(unsigned long start_pfn, unsigned long end_pfn)
 	return offlined;
 }
 
-static int __ref offline_pages(unsigned long start_pfn,
+static int __ref __offline_pages(unsigned long start_pfn,
 		  unsigned long end_pfn, unsigned long timeout)
 {
 	unsigned long pfn, nr_pages, expire;

@@ -990,18 +990,24 @@ out:
 	return ret;
 }
 
-int remove_memory(u64 start, u64 size)
+int offline_pages(unsigned long start_pfn, unsigned long nr_pages)
 {
-	unsigned long start_pfn, end_pfn;
+	return __offline_pages(start_pfn, start_pfn + nr_pages, 120 * HZ);
+}
 
-	start_pfn = PFN_DOWN(start);
-	end_pfn = start_pfn + PFN_DOWN(size);
-	return offline_pages(start_pfn, end_pfn, 120 * HZ);
+int offline_memory(u64 start, u64 size)
+{
+	return -EINVAL;
 }
 #else
-int remove_memory(u64 start, u64 size)
+int offline_pages(u64 start, u64 size)
+{
+	return -EINVAL;
+}
+
+int offline_memory(u64 start, u64 size)
 {
 	return -EINVAL;
 }
 #endif /* CONFIG_MEMORY_HOTREMOVE */
-EXPORT_SYMBOL_GPL(remove_memory);
+EXPORT_SYMBOL_GPL(offline_memory);

index 44e7de6..86c8821 100644
@@ -275,13 +275,11 @@ memory_block_action(unsigned long phys_index, unsigned long action)
 	return ret;
 }
 
-static int memory_block_change_state(struct memory_block *mem,
+static int __memory_block_change_state(struct memory_block *mem,
 		unsigned long to_state, unsigned long from_state_req)
 {
 	int ret = 0;
 
-	mutex_lock(&mem->state_mutex);
-
 	if (mem->state != from_state_req) {
 		ret = -EINVAL;
 		goto out;

@@ -309,10 +307,20 @@ static int memory_block_change_state(struct memory_block *mem,
 		break;
 	}
 out:
-	mutex_unlock(&mem->state_mutex);
 	return ret;
 }
 
+static int memory_block_change_state(struct memory_block *mem,
+		unsigned long to_state, unsigned long from_state_req)
+{
+	int ret;
+
+	mutex_lock(&mem->state_mutex);
+	ret = __memory_block_change_state(mem, to_state, from_state_req);
+	mutex_unlock(&mem->state_mutex);
+
+	return ret;
+}
 static ssize_t
 store_mem_state(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t count)

@@ -653,6 +661,21 @@ int unregister_memory_section(struct mem_section *section)
 }
 
 /*
+ * offline one memory block. If the memory block has been offlined, do nothing.
+ */
+int offline_memory_block(struct memory_block *mem)
+{
+	int ret = 0;
+
+	mutex_lock(&mem->state_mutex);
+	if (mem->state != MEM_OFFLINE)
+		ret = __memory_block_change_state(mem, MEM_OFFLINE, MEM_ONLINE);
+	mutex_unlock(&mem->state_mutex);
+
+	return ret;
+}
+
+/*
  * Initialize the sysfs support for memory devices...
  */
 int __init memory_dev_init(void)

index c183f39..0b040bb 100644
@@ -10,6 +10,7 @@ struct page;
 struct zone;
 struct pglist_data;
 struct mem_section;
+struct memory_block;
 
 #ifdef CONFIG_MEMORY_HOTPLUG
 

@@ -234,6 +235,7 @@ extern int mem_online_node(int nid);
 extern int add_memory(int nid, u64 start, u64 size);
 extern int arch_add_memory(int nid, u64 start, u64 size);
 extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages);
+extern int offline_memory_block(struct memory_block *mem);
 extern int offline_memory(u64 start, u64 size);
 extern int sparse_add_one_section(struct zone *zone, unsigned long start_pfn,
 								int nr_pages);

index 7a6659f..992454a 100644
@@ -997,7 +997,42 @@ int offline_pages(unsigned long start_pfn, unsigned long nr_pages)
 
 int offline_memory(u64 start, u64 size)
 {
-	return -EINVAL;
+	struct memory_block *mem = NULL;
+	struct mem_section *section;
+	unsigned long start_pfn, end_pfn;
+	unsigned long pfn, section_nr;
+	int ret;
+
+	start_pfn = PFN_DOWN(start);
+	end_pfn = start_pfn + PFN_DOWN(size);
+
+	for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
+		section_nr = pfn_to_section_nr(pfn);
+		if (!present_section_nr(section_nr))
+			continue;
+
+		section = __nr_to_section(section_nr);
+		/* same memblock? */
+		if (mem)
+			if ((section_nr >= mem->start_section_nr) &&
+			    (section_nr <= mem->end_section_nr))
+				continue;
+
+		mem = find_memory_block_hinted(section, mem);
+		if (!mem)
+			continue;
+
+		ret = offline_memory_block(mem);
+		if (ret) {
+			kobject_put(&mem->dev.kobj);
+			return ret;
+		}
+	}
+
+	if (mem)
+		kobject_put(&mem->dev.kobj);
+
+	return 0;
 }
 #else
 int offline_pages(u64 start, u64 size)

index 8957ed9..293d718 100644
@@ -83,6 +83,7 @@ struct acpi_memory_info {
 struct acpi_memory_device {
 	struct acpi_device * device;
 	unsigned int state;	/* State of the memory device */
+	int nid;
 	struct list_head res_list;
 };
 

@@ -256,6 +257,9 @@ static int acpi_memory_enable_device(struct acpi_memory_device *mem_device)
 		info->enabled = 1;
 		num_enabled++;
 	}
+
+	mem_device->nid = node;
+
 	if (!num_enabled) {
 		printk(KERN_ERR PREFIX "add_memory failed\n");
 		mem_device->state = MEMORY_INVALID_STATE;

index 293d718..ed37fc2 100644
@@ -29,6 +29,7 @@
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/types.h>
+#include <linux/memory.h>
 #include <linux/memory_hotplug.h>
 #include <linux/slab.h>
 #include <acpi/acpi_drivers.h>

@@ -310,26 +311,42 @@ static int acpi_memory_powerdown_device(struct acpi_memory_device *mem_device)
 	return 0;
 }
 
-static int acpi_memory_disable_device(struct acpi_memory_device *mem_device)
+static int
+acpi_memory_device_remove_memory(struct acpi_memory_device *mem_device)
 {
 	int result;
 	struct acpi_memory_info *info, *n;
+	int node = mem_device->nid;
 
-
-	/*
-	 * Ask the VM to offline this memory range.
-	 * Note: Assume that this function returns zero on success
-	 */
 	list_for_each_entry_safe(info, n, &mem_device->res_list, list) {
 		if (info->enabled) {
 			result = offline_memory(info->start_addr, info->length);
 			if (result)
 				return result;
+
+			result = remove_memory(node, info->start_addr,
+					       info->length);
+			if (result)
+				return result;
 		}
+
 		list_del(&info->list);
 		kfree(info);
 	}
 
+	return 0;
+}
+
+static int acpi_memory_disable_device(struct acpi_memory_device *mem_device)
+{
+	int result;
+
+	/*
+	 * Ask the VM to offline this memory range.
+	 * Note: Assume that this function returns zero on success
+	 */
+	result = acpi_memory_device_remove_memory(mem_device);
+
 	/* Power-off and eject the device */
 	result = acpi_memory_powerdown_device(mem_device);
 	if (result) {

@@ -478,12 +495,23 @@ static int acpi_memory_device_add(struct acpi_device *device)
 static int acpi_memory_device_remove(struct acpi_device *device, int type)
 {
 	struct acpi_memory_device *mem_device = NULL;
-
+	int result;
 
 	if (!device || !acpi_driver_data(device))
 		return -EINVAL;
 
 	mem_device = acpi_driver_data(device);
+
+	if (type == ACPI_BUS_REMOVAL_EJECT) {
+		/*
+		 * offline and remove memory only when the memory device is
+		 * ejected.
+		 */
+		result = acpi_memory_device_remove_memory(mem_device);
+		if (result)
+			return result;
+	}
+
 	kfree(mem_device);
 
 	return 0;

index 86c8821..038be73 100644
@@ -70,6 +70,45 @@ void unregister_memory_isolate_notifier(struct notifier_block *nb)
 }
 EXPORT_SYMBOL(unregister_memory_isolate_notifier);
 
+bool is_memblk_offline(unsigned long start, unsigned long size)
+{
+	struct memory_block *mem = NULL;
+	struct mem_section *section;
+	unsigned long start_pfn, end_pfn;
+	unsigned long pfn, section_nr;
+
+	start_pfn = PFN_DOWN(start);
+	end_pfn = PFN_UP(start + size);
+
+	for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
+		section_nr = pfn_to_section_nr(pfn);
+		if (!present_section_nr(section_nr))
+			continue;
+
+		section = __nr_to_section(section_nr);
+		/* same memblock? */
+		if (mem)
+			if ((section_nr >= mem->start_section_nr) &&
+			    (section_nr <= mem->end_section_nr))
+				continue;
+
+		mem = find_memory_block_hinted(section, mem);
+		if (!mem)
+			continue;
+		if (mem->state == MEM_OFFLINE)
+			continue;
+
+		kobject_put(&mem->dev.kobj);
+		return false;
+	}
+
+	if (mem)
+		kobject_put(&mem->dev.kobj);
+
+	return true;
+}
+EXPORT_SYMBOL(is_memblk_offline);
+
 /*
  * register_memory - Setup a sysfs device for a memory block
  */

index 1ac7f6e..7c66126 100644
@@ -106,6 +106,10 @@ static inline int memory_isolate_notify(unsigned long val, void *v)
 {
 	return 0;
 }
+static inline bool is_memblk_offline(unsigned long start, unsigned long size)
+{
+	return false;
+}
 #else
 extern int register_memory_notifier(struct notifier_block *nb);
 extern void unregister_memory_notifier(struct notifier_block *nb);

@@ -120,6 +124,7 @@ extern int memory_isolate_notify(unsigned long val, void *v);
 extern struct memory_block *find_memory_block_hinted(struct mem_section *,
 							struct memory_block *);
 extern struct memory_block *find_memory_block(struct mem_section *);
+extern bool is_memblk_offline(unsigned long start, unsigned long size);
 #define CONFIG_MEM_BLOCK_SIZE	(PAGES_PER_SECTION<<PAGE_SHIFT)
 enum mem_add_context { BOOT, HOTPLUG };
 #endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */

index 0b040bb..fd84ea9 100644
@@ -222,6 +222,7 @@ static inline void unlock_memory_hotplug(void) {}
 #ifdef CONFIG_MEMORY_HOTREMOVE
 
 extern int is_mem_section_removable(unsigned long pfn, unsigned long nr_pages);
+extern int remove_memory(int nid, u64 start, u64 size);
 
 #else
 static inline int is_mem_section_removable(unsigned long pfn,

@@ -229,6 +230,10 @@ static inline int is_mem_section_removable(unsigned long pfn,
 {
 	return 0;
 }
+static inline int remove_memory(int nid, u64 start, u64 size)
+{
+	return -EBUSY;
+}
 #endif /* CONFIG_MEMORY_HOTREMOVE */
 
 extern int mem_online_node(int nid);

index 992454a..5af0a9f 100644
@@ -1034,6 +1034,28 @@ int offline_memory(u64 start, u64 size)
 
 	return 0;
 }
+
+int remove_memory(int nid, u64 start, u64 size)
+{
+	int ret = -EBUSY;
+	lock_memory_hotplug();
+	/*
+	 * The memory might become online by other task, even if you offine it.
+	 * So we check whether the cpu has been onlined or not.
+	 */
+	if (!is_memblk_offline(start, size)) {
+		pr_warn("memory removing [mem %#010llx-%#010llx] failed, "
+			"because the memmory range is online\n",
+			start, start + size);
+		ret = -EAGAIN;
+	}
+
+	unlock_memory_hotplug();
+	return ret;
+
+}
+EXPORT_SYMBOL_GPL(remove_memory);
+
 #else
 int offline_pages(u64 start, u64 size)
 {

index 458988b..822f705 100644
@@ -1168,6 +1168,25 @@ void sparse_init(void);
 #define sparse_index_init(_sec, _nid)  do {} while (0)
 #endif /* CONFIG_SPARSEMEM */
 
+#ifdef CONFIG_SPARSEMEM
+static inline int pfns_present(unsigned long pfn, unsigned long nr_pages)
+{
+	int i;
+	for (i = 0; i < nr_pages; i++) {
+		if (pfn_present(pfn + 1))
+			continue;
+		else
+			return -EINVAL;
+	}
+	return 0;
+}
+#else
+static inline int pfns_present(unsigned long pfn, unsigned long nr_pages)
+{
+	return 0;
+}
+#endif /* CONFIG_SPARSEMEM*/
+
 #ifdef CONFIG_NODES_SPAN_OTHER_NODES
 bool early_pfn_in_nid(unsigned long pfn, int nid);
 #else

index 5af0a9f..d510be0 100644
@@ -467,6 +467,19 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages)
 	struct memory_notify arg;
 
 	lock_memory_hotplug();
+	/*
+	 * If system supports memory hot-remove, the memory may have been
+	 * removed. So we check whether the memory has been removed or not.
+	 *
+	 * Note: When CONFIG_SPARSEMEM is defined, pfns_present() become
+	 *       effective. If CONFIG_SPARSEMEM is not defined, pfns_present()
+	 *       always returns 0.
+	 */
+	ret = pfns_present(pfn, nr_pages);
+	if (ret) {
+		unlock_memory_hotplug();
+		return ret;
+	}
 	arg.start_pfn = pfn;
 	arg.nr_pages = nr_pages;
 	arg.status_change_nid = -1;

index d1ecca2..1cefc34 100644
@@ -1224,7 +1224,7 @@ static int acpi_device_set_context(struct acpi_device *device)
 	return -ENODEV;
 }
 
-static int acpi_bus_remove(struct acpi_device *dev, int rmdevice)
+int acpi_bus_remove(struct acpi_device *dev, int rmdevice)
 {
 	if (!dev)
 		return -EINVAL;

@@ -1246,6 +1246,7 @@ static int acpi_bus_remove(struct acpi_device *dev, int rmdevice)
 
 	return 0;
 }
+EXPORT_SYMBOL(acpi_bus_remove);
 
 static int acpi_add_single_object(struct acpi_device **child,
 				  acpi_handle handle, int type,

index bde976e..2ccf109 100644
@@ -360,6 +360,7 @@ bool acpi_bus_power_manageable(acpi_handle handle);
 bool acpi_bus_can_wakeup(acpi_handle handle);
 int acpi_power_resource_register_device(struct device *dev, acpi_handle handle);
 void acpi_power_resource_unregister_device(struct device *dev, acpi_handle handle);
+int acpi_bus_remove(struct acpi_device *dev, int rmdevice);
 #ifdef CONFIG_ACPI_PROC_EVENT
 int acpi_bus_generate_proc_event(struct acpi_device *device, u8 type, int data);
 int acpi_bus_generate_proc_event4(const char *class, const char *bid, u8 type, int data);

index ed37fc2..755cc31 100644
@@ -423,8 +423,9 @@ static void acpi_memory_device_notify(acpi_handle handle, u32 event, void *data)
 		}
 
 		/*
-		 * TBD: Invoke acpi_bus_remove to cleanup data structures
+		 * Invoke acpi_bus_remove() to remove memory device
 		 */
+		acpi_bus_remove(device, 1);
 
 		/* _EJ0 succeeded; _OST is not necessary */
 		return;

index 1296605..e03e84f 100644
@@ -21,6 +21,7 @@
 #include <linux/types.h>
 #include <linux/bootmem.h>
 #include <linux/slab.h>
+#include <linux/mm.h>
 
 /*
  * Data types ------------------------------------------------------------------

@@ -79,7 +80,22 @@ static const struct sysfs_ops memmap_attr_ops = {
 	.show = memmap_attr_show,
 };
 
+#define to_memmap_entry(obj) container_of(obj, struct firmware_map_entry, kobj)
+
+static void release_firmware_map_entry(struct kobject *kobj)
+{
+	struct firmware_map_entry *entry = to_memmap_entry(kobj);
+	struct page *page;
+
+	page = virt_to_page(entry);
+	if (PageSlab(page) || PageCompound(page))
+		kfree(entry);
+
+	/* There is no way to free memory allocated from bootmem*/
+}
+
 static struct kobj_type memmap_ktype = {
+	.release	= release_firmware_map_entry,
 	.sysfs_ops	= &memmap_attr_ops,
 	.default_attrs	= def_attrs,
 };

@@ -123,6 +139,16 @@ static int firmware_map_add_entry(u64 start, u64 end,
 	return 0;
 }
 
+/**
+ * firmware_map_remove_entry() - Does the real work to remove a firmware
+ * memmap entry.
+ * @entry: removed entry.
+ **/
+static inline void firmware_map_remove_entry(struct firmware_map_entry *entry)
+{
+	list_del(&entry->list);
+}
+
 /*
  * Add memmap entry on sysfs
  */

@@ -144,6 +170,31 @@ 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);
+}
+
+/*
+ * Search memmap entry
+ */
+
+struct firmware_map_entry * __meminit
+find_firmware_map_entry(u64 start, u64 end, const char *type)
+{
+	struct firmware_map_entry *entry;
+
+	list_for_each_entry(entry, &map_entries, list)
+		if ((entry->start == start) && (entry->end == end) &&
+		    (!strcmp(entry->type, type)))
+			return entry;
+
+	return NULL;
+}
+
 /**
  * firmware_map_add_hotplug() - Adds a firmware mapping entry when we do
  * memory hotplug.

@@ -196,6 +247,32 @@ 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;
+
+	entry = find_firmware_map_entry(start, end - 1, type);
+	if (!entry)
+		return -EINVAL;
+
+	firmware_map_remove_entry(entry);
+
+	/* remove the memmap entry */
+	remove_sysfs_fw_map_entry(entry);
+
+	return 0;
+}
+
 /*
  * Sysfs functions -------------------------------------------------------------
  */

@@ -218,7 +295,6 @@ static ssize_t type_show(struct firmware_map_entry *entry, char *buf)
 }
 
 #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 ssize_t memmap_attr_show(struct kobject *kobj,
 				struct attribute *attr, char *buf)

index 43fe52f..71d4fa7 100644
@@ -25,6 +25,7 @@
 
 int firmware_map_add_early(u64 start, u64 end, const char *type);
 int firmware_map_add_hotplug(u64 start, u64 end, const char *type);
+int firmware_map_remove(u64 start, u64 end, const char *type);
 
 #else /* CONFIG_FIRMWARE_MEMMAP */
 

@@ -38,6 +39,11 @@ static inline int firmware_map_add_hotplug(u64 start, u64 end, const char *type)
 	return 0;
 }
 
+static inline int firmware_map_remove(u64 start, u64 end, const char *type)
+{
+	return 0;
+}
+
 #endif /* CONFIG_FIRMWARE_MEMMAP */
 
 #endif /* _LINUX_FIRMWARE_MAP_H */

index d510be0..5237d49 100644
@@ -1048,9 +1048,9 @@ int offline_memory(u64 start, u64 size)
 	return 0;
 }
 
-int remove_memory(int nid, u64 start, u64 size)
+int __ref remove_memory(int nid, u64 start, u64 size)
 {
-	int ret = -EBUSY;
+	int ret = 0;
 	lock_memory_hotplug();
 	/*
 	 * The memory might become online by other task, even if you offine it.

@@ -1061,8 +1061,13 @@ int remove_memory(int nid, u64 start, u64 size)
 			"because the memmory range is online\n",
 			start, start + size);
 		ret = -EAGAIN;
+		goto out;
 	}
 
+	/* remove memmap entry */
+	firmware_map_remove(start, start + size, "System RAM");
+
+out:
 	unlock_memory_hotplug();
 	return ret;
 

index 11d8e05..dc0a035 100644
@@ -77,7 +77,8 @@ static int pseries_remove_memblock(unsigned long base, unsigned int memblock_siz
 {
 	unsigned long start, start_pfn;
 	struct zone *zone;
-	int ret;
+	int i, ret;
+	int sections_to_remove;
 
 	start_pfn = base >> PAGE_SHIFT;
 

@@ -97,9 +98,13 @@ static int pseries_remove_memblock(unsigned long base, unsigned int memblock_siz
 	 * to sysfs "state" file and we can't remove sysfs entries
 	 * while writing to it. So we have to defer it to here.
 	 */
-	ret = __remove_pages(zone, start_pfn, memblock_size >> PAGE_SHIFT);
-	if (ret)
-		return ret;
+	sections_to_remove = (memblock_size >> PAGE_SHIFT) / PAGES_PER_SECTION;
+	for (i = 0; i < sections_to_remove; i++) {
+		unsigned long pfn = start_pfn + i * PAGES_PER_SECTION;
+		ret = __remove_pages(zone, start_pfn,  PAGES_PER_SECTION);
+		if (ret)
+			return ret;
+	}
 
 	/*
 	 * Update memory regions for memory remove

index 5237d49..d360c5c 100644
@@ -358,11 +358,11 @@ int __remove_pages(struct zone *zone, unsigned long phys_start_pfn,
 	BUG_ON(phys_start_pfn & ~PAGE_SECTION_MASK);
 	BUG_ON(nr_pages % PAGES_PER_SECTION);
 
+	release_mem_region(phys_start_pfn << PAGE_SHIFT,  nr_pages * PAGE_SIZE);
+
 	sections_to_remove = nr_pages / PAGES_PER_SECTION;
 	for (i = 0; i < sections_to_remove; i++) {
 		unsigned long pfn = phys_start_pfn + i*PAGES_PER_SECTION;
-		release_mem_region(pfn << PAGE_SHIFT,
-				   PAGES_PER_SECTION << PAGE_SHIFT);
 		ret = __remove_section(zone, __pfn_to_section(pfn));
 		if (ret)
 			break;

index 038be73..1cd3ef3 100644
@@ -109,6 +109,15 @@ bool is_memblk_offline(unsigned long start, unsigned long size)
 }
 EXPORT_SYMBOL(is_memblk_offline);
 
+#define to_memory_block(device) container_of(device, struct memory_block, dev)
+
+static void release_memory_block(struct device *dev)
+{
+	struct memory_block *mem = to_memory_block(dev);
+
+	kfree(mem);
+}
+
 /*
  * register_memory - Setup a sysfs device for a memory block
  */

@@ -119,6 +128,7 @@ int register_memory(struct memory_block *memory)
 
 	memory->dev.bus = &memory_subsys;
 	memory->dev.id = memory->start_section_nr / sections_per_block;
+	memory->dev.release = release_memory_block;
 
 	error = device_register(&memory->dev);
 	return error;

@@ -674,7 +684,6 @@ int remove_memory_block(unsigned long node_id, struct mem_section *section,
 		mem_remove_simple_file(mem, phys_device);
 		mem_remove_simple_file(mem, removable);
 		unregister_memory(mem);
-		kfree(mem);
 	} else
 		kobject_put(&mem->dev.kobj);
 

index dc0a035..cc14da4 100644
@@ -76,7 +76,6 @@ unsigned long memory_block_size_bytes(void)
 static int pseries_remove_memblock(unsigned long base, unsigned int memblock_size)
 {
 	unsigned long start, start_pfn;
-	struct zone *zone;
 	int i, ret;
 	int sections_to_remove;
 

@@ -87,8 +86,6 @@ static int pseries_remove_memblock(unsigned long base, unsigned int memblock_siz
 		return 0;
 	}
 
-	zone = page_zone(pfn_to_page(start_pfn));
-
 	/*
 	 * Remove section mappings and sysfs entries for the
 	 * section of the memory we are removing.

@@ -101,7 +98,7 @@ static int pseries_remove_memblock(unsigned long base, unsigned int memblock_siz
 	sections_to_remove = (memblock_size >> PAGE_SHIFT) / PAGES_PER_SECTION;
 	for (i = 0; i < sections_to_remove; i++) {
 		unsigned long pfn = start_pfn + i * PAGES_PER_SECTION;
-		ret = __remove_pages(zone, start_pfn,  PAGES_PER_SECTION);
+		ret = __remove_pages(start_pfn,  PAGES_PER_SECTION);
 		if (ret)
 			return ret;
 	}

index fd84ea9..8bf820d 100644
@@ -90,8 +90,7 @@ extern bool is_pageblock_removable_nolock(struct page *page);
 /* reasonably generic interface to expand the physical pages in a zone  */
 extern int __add_pages(int nid, struct zone *zone, unsigned long start_pfn,
 	unsigned long nr_pages);
-extern int __remove_pages(struct zone *zone, unsigned long start_pfn,
-	unsigned long nr_pages);
+extern int __remove_pages(unsigned long start_pfn, unsigned long nr_pages);
 
 #ifdef CONFIG_NUMA
 extern int memory_add_physaddr_to_nid(u64 start);

index d360c5c..a9e1579 100644
@@ -275,11 +275,14 @@ static int __meminit __add_section(int nid, struct zone *zone,
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
 static int __remove_section(struct zone *zone, struct mem_section *ms)
 {
-	/*
-	 * XXX: Freeing memmap with vmemmap is not implement yet.
-	 *      This should be removed later.
-	 */
-	return -EBUSY;
+	int ret = -EINVAL;
+
+	if (!valid_section(ms))
+		return ret;
+
+	ret = unregister_memory_section(ms);
+
+	return ret;
 }
 #else
 static int __remove_section(struct zone *zone, struct mem_section *ms)

@@ -346,11 +349,11 @@ EXPORT_SYMBOL_GPL(__add_pages);
  * sure that pages are marked reserved and zones are adjust properly by
  * calling offline_pages().
  */
-int __remove_pages(struct zone *zone, unsigned long phys_start_pfn,
-		 unsigned long nr_pages)
+int __remove_pages(unsigned long phys_start_pfn, unsigned long nr_pages)
 {
 	unsigned long i, ret = 0;
 	int sections_to_remove;
+	struct zone *zone;
 
 	/*
 	 * We can only remove entire sections

@@ -363,6 +366,7 @@ int __remove_pages(struct zone *zone, unsigned long phys_start_pfn,
 	sections_to_remove = nr_pages / PAGES_PER_SECTION;
 	for (i = 0; i < sections_to_remove; i++) {
 		unsigned long pfn = phys_start_pfn + i*PAGES_PER_SECTION;
+		zone = page_zone(pfn_to_page(pfn));
 		ret = __remove_section(zone, __pfn_to_section(pfn));
 		if (ret)
 			break;

index 0eab454..1e345ed 100644
@@ -688,6 +688,22 @@ int arch_add_memory(int nid, u64 start, u64 size)
 
 	return ret;
 }
+
+#ifdef CONFIG_MEMORY_HOTREMOVE
+int arch_remove_memory(u64 start, u64 size)
+{
+	unsigned long start_pfn = start >> PAGE_SHIFT;
+	unsigned long nr_pages = size >> PAGE_SHIFT;
+	int ret;
+
+	ret = __remove_pages(start_pfn, nr_pages);
+	if (ret)
+		pr_warn("%s: Problem encountered in __remove_pages() as"
+			" ret=%d\n", __func__,  ret);
+
+	return ret;
+}
+#endif
 #endif
 
 /*

index baaafde..249cef4 100644
@@ -133,6 +133,20 @@ int arch_add_memory(int nid, u64 start, u64 size)
 
 	return __add_pages(nid, zone, start_pfn, nr_pages);
 }
+
+#ifdef CONFIG_MEMORY_HOTREMOVE
+int arch_remove_memory(u64 start, u64 size)
+{
+	unsigned long start_pfn = start >> PAGE_SHIFT;
+	unsigned long nr_pages = size >> PAGE_SHIFT;
+
+	start = (unsigned long)__va(start);
+	if (remove_section_mapping(start, start + size))
+		return -EINVAL;
+
+	return __remove_pages(start_pfn, nr_pages);
+}
+#endif
 #endif /* CONFIG_MEMORY_HOTPLUG */
 
 /*

index 6adbc08..ca4bc46 100644
@@ -257,4 +257,12 @@ int arch_add_memory(int nid, u64 start, u64 size)
 		vmem_remove_mapping(start, size);
 	return rc;
 }
+
+#ifdef CONFIG_MEMORY_HOTREMOVE
+int arch_remove_memory(u64 start, u64 size)
+{
+	/* TODO */
+	return -EBUSY;
+}
+#endif
 #endif /* CONFIG_MEMORY_HOTPLUG */

index 82cc576..fc84491 100644
@@ -558,4 +558,19 @@ int memory_add_physaddr_to_nid(u64 addr)
 EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
 #endif
 
+#ifdef CONFIG_MEMORY_HOTREMOVE
+int arch_remove_memory(u64 start, u64 size)
+{
+	unsigned long start_pfn = start >> PAGE_SHIFT;
+	unsigned long nr_pages = size >> PAGE_SHIFT;
+	int ret;
+
+	ret = __remove_pages(start_pfn, nr_pages);
+	if (unlikely(ret))
+		pr_warn("%s: Failed, __remove_pages() == %d\n", __func__,
+			ret);
+
+	return ret;
+}
+#endif
 #endif /* CONFIG_MEMORY_HOTPLUG */

index ef29d6c..2749515 100644
@@ -935,6 +935,14 @@ int remove_memory(u64 start, u64 size)
 {
 	return -EINVAL;
 }
+
+#ifdef CONFIG_MEMORY_HOTREMOVE
+int arch_remove_memory(u64 start, u64 size)
+{
+	/* TODO */
+	return -EBUSY;
+}
+#endif
 #endif
 
 struct kmem_cache *pgd_cache;

index 013286a..b725af2 100644
@@ -334,6 +334,7 @@ static inline void update_page_count(int level, unsigned long pages) { }
  * as a pte too.
  */
 extern pte_t *lookup_address(unsigned long address, unsigned int *level);
+extern int __split_large_page(pte_t *kpte, unsigned long address, pte_t *pbase);
 
 #endif	/* !__ASSEMBLY__ */
 

index 575d86f..a690153 100644
@@ -842,6 +842,16 @@ int arch_add_memory(int nid, u64 start, u64 size)
 
 	return __add_pages(nid, zone, start_pfn, nr_pages);
 }
+
+#ifdef CONFIG_MEMORY_HOTREMOVE
+int arch_remove_memory(unsigned long start, unsigned long size)
+{
+	unsigned long start_pfn = start >> PAGE_SHIFT;
+	unsigned long nr_pages = size >> PAGE_SHIFT;
+
+	return __remove_pages(start_pfn, nr_pages);
+}
+#endif
 #endif
 
 /*

166 lines not on this page · raw message

73 lines not on this page · raw message

index 8bf820d..0d500be 100644
@@ -85,6 +85,7 @@ extern void __online_page_free(struct page *page);
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
 extern bool is_pageblock_removable_nolock(struct page *page);
+extern int arch_remove_memory(unsigned long start, unsigned long size);
 #endif /* CONFIG_MEMORY_HOTREMOVE */
 
 /* reasonably generic interface to expand the physical pages in a zone  */

index a9e1579..0c932e1 100644
@@ -1071,6 +1071,7 @@ int __ref remove_memory(int nid, u64 start, u64 size)
 	/* remove memmap entry */
 	firmware_map_remove(start, start + size, "System RAM");
 
+	arch_remove_memory(start, size);
 out:
 	unlock_memory_hotplug();
 	return ret;

index 0c932e1..eae946b 100644
@@ -95,10 +95,17 @@ static void release_memory_resource(struct resource *res)
 static void get_page_bootmem(unsigned long info,  struct page *page,
 			     unsigned long type)
 {
-	page->lru.next = (struct list_head *) type;
-	SetPagePrivate(page);
-	set_page_private(page, info);
-	atomic_inc(&page->_count);
+	unsigned long page_type;
+
+	page_type = (unsigned long) page->lru.next;
+	if (type < MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE ||
+	    type > MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE){
+		page->lru.next = (struct list_head *) type;
+		SetPagePrivate(page);
+		set_page_private(page, info);
+		atomic_inc(&page->_count);
+	} else
+		atomic_inc(&page->_count);
 }
 
 /* reference to __meminit __free_pages_bootmem is valid

index 0d500be..fe50a9b 100644
@@ -162,17 +162,8 @@ static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat)
 #endif /* CONFIG_NUMA */
 #endif /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */
 
-#ifdef CONFIG_SPARSEMEM_VMEMMAP
-static inline void register_page_bootmem_info_node(struct pglist_data *pgdat)
-{
-}
-static inline void put_page_bootmem(struct page *page)
-{
-}
-#else
 extern void register_page_bootmem_info_node(struct pglist_data *pgdat);
 extern void put_page_bootmem(struct page *page);
-#endif
 
 /*
  * Lock for memory hotplug guarantees 1) all callbacks for memory hotplug

index eae946b..180d555 100644
@@ -91,7 +91,6 @@ static void release_memory_resource(struct resource *res)
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
-#ifndef CONFIG_SPARSEMEM_VMEMMAP
 static void get_page_bootmem(unsigned long info,  struct page *page,
 			     unsigned long type)
 {

@@ -127,6 +126,7 @@ void __ref put_page_bootmem(struct page *page)
 
 }
 
+#ifndef CONFIG_SPARSEMEM_VMEMMAP
 static void register_page_bootmem_info_section(unsigned long start_pfn)
 {
 	unsigned long *usemap, mapsize, section_nr, i;

@@ -163,6 +163,11 @@ static void register_page_bootmem_info_section(unsigned long start_pfn)
 		get_page_bootmem(section_nr, page, MIX_SECTION_INFO);
 
 }
+#else
+static inline void register_page_bootmem_info_section(unsigned long start_pfn)
+{
+}
+#endif
 
 void register_page_bootmem_info_node(struct pglist_data *pgdat)
 {

@@ -198,7 +203,6 @@ void register_page_bootmem_info_node(struct pglist_data *pgdat)
 		register_page_bootmem_info_section(pfn);
 
 }
-#endif /* !CONFIG_SPARSEMEM_VMEMMAP */
 
 static void grow_zone_span(struct zone *zone, unsigned long start_pfn,
 			   unsigned long end_pfn)

index f1554a9..a151145 100644
@@ -1138,6 +1138,58 @@ vmemmap_populate(struct page *start_page, unsigned long size, int node)
 	return 0;
 }
 
+void register_page_bootmem_memmap(unsigned long section_nr,
+				  struct page *start_page, unsigned long size)
+{
+	unsigned long addr = (unsigned long)start_page;
+	unsigned long end = (unsigned long)(start_page + size);
+	unsigned long next;
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd;
+
+	for (; addr < end; addr = next) {
+		pte_t *pte = NULL;
+
+		pgd = pgd_offset_k(addr);
+		if (pgd_none(*pgd)) {
+			next = (addr + PAGE_SIZE) & PAGE_MASK;
+			continue;
+		}
+		get_page_bootmem(section_nr, pgd_page(*pgd), MIX_SECTION_INFO);
+
+		pud = pud_offset(pgd, addr);
+		if (pud_none(*pud)) {
+			next = (addr + PAGE_SIZE) & PAGE_MASK;
+			continue;
+		}
+		get_page_bootmem(section_nr, pud_page(*pud), MIX_SECTION_INFO);
+
+		if (!cpu_has_pse) {
+			next = (addr + PAGE_SIZE) & PAGE_MASK;
+			pmd = pmd_offset(pud, addr);
+			if (pmd_none(*pmd))
+				continue;
+			get_page_bootmem(section_nr, pmd_page(*pmd),
+					 MIX_SECTION_INFO);
+
+			pte = pte_offset_kernel(pmd, addr);
+			if (pte_none(*pte))
+				continue;
+			get_page_bootmem(section_nr, pte_page(*pte),
+					 SECTION_INFO);
+		} else {
+			next = pmd_addr_end(addr, end);
+
+			pmd = pmd_offset(pud, addr);
+			if (pmd_none(*pmd))
+				continue;
+			get_page_bootmem(section_nr, pmd_page(*pmd),
+					 SECTION_INFO);
+		}
+	}
+}
+
 void __meminit vmemmap_populate_print_last(void)
 {
 	if (p_start) {

index fe50a9b..e79d744 100644
@@ -164,6 +164,8 @@ static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat)
 
 extern void register_page_bootmem_info_node(struct pglist_data *pgdat);
 extern void put_page_bootmem(struct page *page);
+extern void get_page_bootmem(unsigned long ingo, struct page *page,
+			     unsigned long type);
 
 /*
  * Lock for memory hotplug guarantees 1) all callbacks for memory hotplug

index f9f279c..716f38b 100644
@@ -1586,7 +1586,8 @@ int vmemmap_populate_basepages(struct page *start_page,
 						unsigned long pages, int node);
 int vmemmap_populate(struct page *start_page, unsigned long pages, int node);
 void vmemmap_populate_print_last(void);
-
+void register_page_bootmem_memmap(unsigned long section_nr, struct page *map,
+				  unsigned long size);
 
 enum mf_flags {
 	MF_COUNT_INCREASED = 1 << 0,

index 180d555..adcc93d 100644
@@ -91,8 +91,8 @@ static void release_memory_resource(struct resource *res)
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
-static void get_page_bootmem(unsigned long info,  struct page *page,
-			     unsigned long type)
+void get_page_bootmem(unsigned long info,  struct page *page,
+		      unsigned long type)
 {
 	unsigned long page_type;
 

@@ -164,8 +164,25 @@ static void register_page_bootmem_info_section(unsigned long start_pfn)
 
 }
 #else
-static inline void register_page_bootmem_info_section(unsigned long start_pfn)
+static void register_page_bootmem_info_section(unsigned long start_pfn)
 {
+	unsigned long mapsize, section_nr;
+	struct mem_section *ms;
+	struct page *page, *memmap;
+
+	if (!pfn_valid(start_pfn))
+		return;
+
+	section_nr = pfn_to_section_nr(start_pfn);
+	ms = __nr_to_section(section_nr);
+
+	memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr);
+
+	page = virt_to_page(memmap);
+	mapsize = sizeof(struct page) * PAGES_PER_SECTION;
+	mapsize = PAGE_ALIGN(mapsize) >> PAGE_SHIFT;
+
+	register_page_bootmem_memmap(section_nr, memmap, PAGES_PER_SECTION);
 }
 #endif
 

index a151145..ef83955 100644
@@ -1138,6 +1138,127 @@ vmemmap_populate(struct page *start_page, unsigned long size, int node)
 	return 0;
 }
 
+#define PAGE_INUSE 0xFD
+
+unsigned long find_and_clear_pte_page(unsigned long addr, unsigned long end,
+			    struct page **pp, int *page_size)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte;
+	void *page_addr;
+	unsigned long next;
+
+	*pp = NULL;
+
+	pgd = pgd_offset_k(addr);
+	if (pgd_none(*pgd))
+		return pgd_addr_end(addr, end);
+
+	pud = pud_offset(pgd, addr);
+	if (pud_none(*pud))
+		return pud_addr_end(addr, end);
+
+	if (!cpu_has_pse) {
+		next = (addr + PAGE_SIZE) & PAGE_MASK;
+		pmd = pmd_offset(pud, addr);
+		if (pmd_none(*pmd))
+			return next;
+
+		pte = pte_offset_kernel(pmd, addr);
+		if (pte_none(*pte))
+			return next;
+
+		*page_size = PAGE_SIZE;
+		*pp = pte_page(*pte);
+	} else {
+		next = pmd_addr_end(addr, end);
+
+		pmd = pmd_offset(pud, addr);
+		if (pmd_none(*pmd))
+			return next;
+
+		*page_size = PMD_SIZE;
+		*pp = pmd_page(*pmd);
+	}
+
+	/*
+	 * Removed page structs are filled with 0xFD.
+	 */
+	memset((void *)addr, PAGE_INUSE, next - addr);
+
+	page_addr = page_address(*pp);
+
+	/*
+	 * Check the page is filled with 0xFD or not.
+	 * memchr_inv() returns the address. In this case, we cannot
+	 * clear PTE/PUD entry, since the page is used by other.
+	 * So we cannot also free the page.
+	 *
+	 * memchr_inv() returns NULL. In this case, we can clear
+	 * PTE/PUD entry, since the page is not used by other.
+	 * So we can also free the page.
+	 */
+	if (memchr_inv(page_addr, PAGE_INUSE, *page_size)) {
+		*pp = NULL;
+		return next;
+	}
+
+	if (!cpu_has_pse)
+		pte_clear(&init_mm, addr, pte);
+	else
+		pmd_clear(pmd);
+
+	return next;
+}
+
+void vmemmap_kfree(struct page *memmap, unsigned long nr_pages)
+{
+	unsigned long addr = (unsigned long)memmap;
+	unsigned long end = (unsigned long)(memmap + nr_pages);
+	unsigned long next;
+	struct page *page;
+	int page_size;
+
+	for (; addr < end; addr = next) {
+		page = NULL;
+		page_size = 0;
+		next = find_and_clear_pte_page(addr, end, &page, &page_size);
+		if (!page)
+			continue;
+
+		free_pages((unsigned long)page_address(page),
+			    get_order(page_size));
+		__flush_tlb_one(addr);
+	}
+
+}
+
+void vmemmap_free_bootmem(struct page *memmap, unsigned long nr_pages)
+{
+	unsigned long addr = (unsigned long)memmap;
+	unsigned long end = (unsigned long)(memmap + nr_pages);
+	unsigned long next;
+	struct page *page;
+	int page_size;
+	unsigned long magic;
+
+	for (; addr < end; addr = next) {
+		page = NULL;
+		page_size = 0;
+		next = find_and_clear_pte_page(addr, end, &page, &page_size);
+		if (!page)
+			continue;
+
+		magic = (unsigned long) page->lru.next;
+		if (magic == SECTION_INFO)
+			put_page_bootmem(page);
+		flush_tlb_kernel_range(addr, end);
+	}
+
+}
+
 void register_page_bootmem_memmap(unsigned long section_nr,
 				  struct page *start_page, unsigned long size)
 {

index 716f38b..a5f23a9 100644
@@ -1588,6 +1588,8 @@ int vmemmap_populate(struct page *start_page, unsigned long pages, int node);
 void vmemmap_populate_print_last(void);
 void register_page_bootmem_memmap(unsigned long section_nr, struct page *map,
 				  unsigned long size);
+void vmemmap_kfree(struct page *memmpa, unsigned long nr_pages);
+void vmemmap_free_bootmem(struct page *memmpa, unsigned long nr_pages);
 
 enum mf_flags {
 	MF_COUNT_INCREASED = 1 << 0,

index adcc93d..859425c 100644
@@ -300,19 +300,6 @@ static int __meminit __add_section(int nid, struct zone *zone,
 	return register_new_memory(nid, __pfn_to_section(phys_start_pfn));
 }
 
-#ifdef CONFIG_SPARSEMEM_VMEMMAP
-static int __remove_section(struct zone *zone, struct mem_section *ms)
-{
-	int ret = -EINVAL;
-
-	if (!valid_section(ms))
-		return ret;
-
-	ret = unregister_memory_section(ms);
-
-	return ret;
-}
-#else
 static int __remove_section(struct zone *zone, struct mem_section *ms)
 {
 	unsigned long flags;

@@ -329,9 +316,9 @@ static int __remove_section(struct zone *zone, struct mem_section *ms)
 	pgdat_resize_lock(pgdat, &flags);
 	sparse_remove_one_section(zone, ms);
 	pgdat_resize_unlock(pgdat, &flags);
-	return 0;
+
+	return ret;
 }
-#endif
 
 /*
  * Reasonably generic function for adding memory.  It is

index c7bb952..3b212a1 100644
@@ -622,12 +622,13 @@ static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid,
 	/* This will make the necessary allocations eventually. */
 	return sparse_mem_map_populate(pnum, nid);
 }
-static void __kfree_section_memmap(struct page *memmap, unsigned long nr_pages)
+static void __kfree_section_memmap(struct page *page, unsigned long nr_pages)
 {
-	return; /* XXX: Not implemented yet */
+	vmemmap_kfree(page, nr_pages);
 }
 static void free_map_bootmem(struct page *page, unsigned long nr_pages)
 {
+	vmemmap_free_bootmem(page, nr_pages);
 }
 #else
 static struct page *__kmalloc_section_memmap(unsigned long nr_pages)

index 859425c..5ac035f 100644
@@ -300,10 +300,187 @@ static int __meminit __add_section(int nid, struct zone *zone,
 	return register_new_memory(nid, __pfn_to_section(phys_start_pfn));
 }
 
+/* find the smallest valid pfn in the range [start_pfn, end_pfn) */
+static int find_smallest_section_pfn(unsigned long start_pfn,
+				     unsigned long end_pfn)
+{
+	struct mem_section *ms;
+
+	for (; start_pfn < end_pfn; start_pfn += PAGES_PER_SECTION) {
+		ms = __pfn_to_section(start_pfn);
+
+		if (unlikely(!valid_section(ms)))
+			continue;
+
+		return start_pfn;
+	}
+
+	return 0;
+}
+
+/* find the biggest valid pfn in the range [start_pfn, end_pfn). */
+static int find_biggest_section_pfn(unsigned long start_pfn,
+				    unsigned long end_pfn)
+{
+	struct mem_section *ms;
+	unsigned long pfn;
+
+	/* pfn is the end pfn of a memory section. */
+	pfn = end_pfn - 1;
+	for (; pfn >= start_pfn; pfn -= PAGES_PER_SECTION) {
+		ms = __pfn_to_section(pfn);
+
+		if (unlikely(!valid_section(ms)))
+			continue;
+
+		return pfn;
+	}
+
+	return 0;
+}
+
+static void shrink_zone_span(struct zone *zone, unsigned long start_pfn,
+			     unsigned long end_pfn)
+{
+	unsigned long zone_start_pfn =  zone->zone_start_pfn;
+	unsigned long zone_end_pfn = zone->zone_start_pfn + zone->spanned_pages;
+	unsigned long pfn;
+	struct mem_section *ms;
+
+	zone_span_writelock(zone);
+	if (zone_start_pfn == start_pfn) {
+		/*
+		 * If the section is smallest section in the zone, it need
+		 * shrink zone->zone_start_pfn and zone->zone_spanned_pages.
+		 * In this case, we find second smallest valid mem_section
+		 * for shrinking zone.
+		 */
+		pfn = find_smallest_section_pfn(end_pfn, zone_end_pfn);
+		if (pfn) {
+			zone->zone_start_pfn = pfn;
+			zone->spanned_pages = zone_end_pfn - pfn;
+		}
+	} else if (zone_end_pfn == end_pfn) {
+		/*
+		 * If the section is biggest section in the zone, it need
+		 * shrink zone->spanned_pages.
+		 * In this case, we find second biggest valid mem_section for
+		 * shrinking zone.
+		 */
+		pfn = find_biggest_section_pfn(zone_start_pfn, start_pfn);
+		if (pfn)
+			zone->spanned_pages = pfn - zone_start_pfn + 1;
+	}
+
+	/*
+	 * The section is not biggest or smallest mem_section in the zone, it
+	 * only creates a hole in the zone. So in this case, we need not
+	 * change the zone. But perhaps, the zone has only hole data. Thus
+	 * it check the zone has only hole or not.
+	 */
+	pfn = zone_start_pfn;
+	for (; pfn < zone_end_pfn; pfn += PAGES_PER_SECTION) {
+		ms = __pfn_to_section(pfn);
+
+		if (unlikely(!valid_section(ms)))
+			continue;
+
+		 /* If the section is current section, it continues the loop */
+		if (start_pfn == pfn)
+			continue;
+
+		/* If we find valid section, we have nothing to do */
+		zone_span_writeunlock(zone);
+		return;
+	}
+
+	/* The zone has no valid section */
+	zone->zone_start_pfn = 0;
+	zone->spanned_pages = 0;
+	zone_span_writeunlock(zone);
+}
+
+static void shrink_pgdat_span(struct pglist_data *pgdat,
+			      unsigned long start_pfn, unsigned long end_pfn)
+{
+	unsigned long pgdat_start_pfn =  pgdat->node_start_pfn;
+	unsigned long pgdat_end_pfn =
+		pgdat->node_start_pfn + pgdat->node_spanned_pages;
+	unsigned long pfn;
+	struct mem_section *ms;
+
+	if (pgdat_start_pfn == start_pfn) {
+		/*
+		 * If the section is smallest section in the pgdat, it need
+		 * shrink pgdat->node_start_pfn and pgdat->node_spanned_pages.
+		 * In this case, we find second smallest valid mem_section
+		 * for shrinking zone.
+		 */
+		pfn = find_smallest_section_pfn(end_pfn, pgdat_end_pfn);
+		if (pfn) {
+			pgdat->node_start_pfn = pfn;
+			pgdat->node_spanned_pages = pgdat_end_pfn - pfn;
+		}
+	} else if (pgdat_end_pfn == end_pfn) {
+		/*
+		 * If the section is biggest section in the pgdat, it need
+		 * shrink pgdat->node_spanned_pages.
+		 * In this case, we find second biggest valid mem_section for
+		 * shrinking zone.
+		 */
+		pfn = find_biggest_section_pfn(pgdat_start_pfn, start_pfn);
+		if (pfn)
+			pgdat->node_spanned_pages = pfn - pgdat_start_pfn + 1;
+	}
+
+	/*
+	 * If the section is not biggest or smallest mem_section in the pgdat,
+	 * it only creates a hole in the pgdat. So in this case, we need not
+	 * change the pgdat.
+	 * But perhaps, the pgdat has only hole data. Thus it check the pgdat
+	 * has only hole or not.
+	 */
+	pfn = pgdat_start_pfn;
+	for (; pfn < pgdat_end_pfn; pfn += PAGES_PER_SECTION) {
+		ms = __pfn_to_section(pfn);
+
+		if (unlikely(!valid_section(ms)))
+			continue;
+
+		 /* If the section is current section, it continues the loop */
+		if (start_pfn == pfn)
+			continue;
+
+		/* If we find valid section, we have nothing to do */
+		return;
+	}
+
+	/* The pgdat has no valid section */
+	pgdat->node_start_pfn = 0;
+	pgdat->node_spanned_pages = 0;
+}
+
+static void __remove_zone(struct zone *zone, unsigned long start_pfn)
+{
+	struct pglist_data *pgdat = zone->zone_pgdat;
+	int nr_pages = PAGES_PER_SECTION;
+	int zone_type;
+	unsigned long flags;
+
+	zone_type = zone - pgdat->node_zones;
+
+	pgdat_resize_lock(zone->zone_pgdat, &flags);
+	shrink_zone_span(zone, start_pfn, start_pfn + nr_pages);
+	shrink_pgdat_span(pgdat, start_pfn, start_pfn + nr_pages);
+	pgdat_resize_unlock(zone->zone_pgdat, &flags);
+}
+
 static int __remove_section(struct zone *zone, struct mem_section *ms)
 {
 	unsigned long flags;
 	struct pglist_data *pgdat = zone->zone_pgdat;
+	unsigned long start_pfn;
+	int scn_nr;
 	int ret = -EINVAL;
 
 	if (!valid_section(ms))