1 files changed, 1250 insertions, 187 deletions

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 9260314a221..469bbf505f8 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -9,9 +9,8 @@
 #include <linux/swap.h>
 #include <linux/interrupt.h>
 #include <linux/pagemap.h>
-#include <linux/bootmem.h>
 #include <linux/compiler.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/pagevec.h>
 #include <linux/writeback.h>
 #include <linux/slab.h>
@@ -29,11 +28,103 @@
 #include <linux/suspend.h>
 #include <linux/mm_inline.h>
 #include <linux/firmware-map.h>
+#include <linux/stop_machine.h>
+#include <linux/hugetlb.h>
+#include <linux/memblock.h>
 
 #include <asm/tlbflush.h>
 
 #include "internal.h"
 
+/*
+ * online_page_callback contains pointer to current page onlining function.
+ * Initially it is generic_online_page(). If it is required it could be
+ * changed by calling set_online_page_callback() for callback registration
+ * and restore_online_page_callback() for generic callback restore.
+ */
+
+static void generic_online_page(struct page *page);
+
+static online_page_callback_t online_page_callback = generic_online_page;
+static DEFINE_MUTEX(online_page_callback_lock);
+
+/* The same as the cpu_hotplug lock, but for memory hotplug. */
+static struct {
+	struct task_struct *active_writer;
+	struct mutex lock; /* Synchronizes accesses to refcount, */
+	/*
+	 * Also blocks the new readers during
+	 * an ongoing mem hotplug operation.
+	 */
+	int refcount;
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	struct lockdep_map dep_map;
+#endif
+} mem_hotplug = {
+	.active_writer = NULL,
+	.lock = __MUTEX_INITIALIZER(mem_hotplug.lock),
+	.refcount = 0,
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	.dep_map = {.name = "mem_hotplug.lock" },
+#endif
+};
+
+/* Lockdep annotations for get/put_online_mems() and mem_hotplug_begin/end() */
+#define memhp_lock_acquire_read() lock_map_acquire_read(&mem_hotplug.dep_map)
+#define memhp_lock_acquire()      lock_map_acquire(&mem_hotplug.dep_map)
+#define memhp_lock_release()      lock_map_release(&mem_hotplug.dep_map)
+
+void get_online_mems(void)
+{
+	might_sleep();
+	if (mem_hotplug.active_writer == current)
+		return;
+	memhp_lock_acquire_read();
+	mutex_lock(&mem_hotplug.lock);
+	mem_hotplug.refcount++;
+	mutex_unlock(&mem_hotplug.lock);
+
+}
+
+void put_online_mems(void)
+{
+	if (mem_hotplug.active_writer == current)
+		return;
+	mutex_lock(&mem_hotplug.lock);
+
+	if (WARN_ON(!mem_hotplug.refcount))
+		mem_hotplug.refcount++; /* try to fix things up */
+
+	if (!--mem_hotplug.refcount && unlikely(mem_hotplug.active_writer))
+		wake_up_process(mem_hotplug.active_writer);
+	mutex_unlock(&mem_hotplug.lock);
+	memhp_lock_release();
+
+}
+
+static void mem_hotplug_begin(void)
+{
+	mem_hotplug.active_writer = current;
+
+	memhp_lock_acquire();
+	for (;;) {
+		mutex_lock(&mem_hotplug.lock);
+		if (likely(!mem_hotplug.refcount))
+			break;
+		__set_current_state(TASK_UNINTERRUPTIBLE);
+		mutex_unlock(&mem_hotplug.lock);
+		schedule();
+	}
+}
+
+static void mem_hotplug_done(void)
+{
+	mem_hotplug.active_writer = NULL;
+	mutex_unlock(&mem_hotplug.lock);
+	memhp_lock_release();
+}
+
 /* add this memory to iomem resource */
 static struct resource *register_memory_resource(u64 start, u64 size)
 {
@@ -46,8 +137,7 @@ static struct resource *register_memory_resource(u64 start, u64 size)
 	res->end = start + size - 1;
 	res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
 	if (request_resource(&iomem_resource, res) < 0) {
-		printk("System RAM resource %llx - %llx cannot be added\n",
-		(unsigned long long)res->start, (unsigned long long)res->end);
+		pr_debug("System RAM resource %pR cannot be added\n", res);
 		kfree(res);
 		res = NULL;
 	}
@@ -64,42 +154,39 @@ 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, int type)
+void get_page_bootmem(unsigned long info,  struct page *page,
+		      unsigned long type)
 {
-	atomic_set(&page->_mapcount, type);
+	page->lru.next = (struct list_head *) type;
 	SetPagePrivate(page);
 	set_page_private(page, info);
 	atomic_inc(&page->_count);
 }
 
-/* reference to __meminit __free_pages_bootmem is valid
- * so use __ref to tell modpost not to generate a warning */
-void __ref put_page_bootmem(struct page *page)
+void put_page_bootmem(struct page *page)
 {
-	int type;
+	unsigned long type;
 
-	type = atomic_read(&page->_mapcount);
-	BUG_ON(type >= -1);
+	type = (unsigned long) page->lru.next;
+	BUG_ON(type < MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE ||
+	       type > MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE);
 
 	if (atomic_dec_return(&page->_count) == 1) {
 		ClearPagePrivate(page);
 		set_page_private(page, 0);
-		reset_page_mapcount(page);
-		__free_pages_bootmem(page, 0);
+		INIT_LIST_HEAD(&page->lru);
+		free_reserved_page(page);
 	}
-
 }
 
+#ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE
+#ifndef CONFIG_SPARSEMEM_VMEMMAP
 static void register_page_bootmem_info_section(unsigned long start_pfn)
 {
 	unsigned long *usemap, mapsize, section_nr, i;
 	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);
 
@@ -127,6 +214,32 @@ static void register_page_bootmem_info_section(unsigned long start_pfn)
 		get_page_bootmem(section_nr, page, MIX_SECTION_INFO);
 
 }
+#else /* CONFIG_SPARSEMEM_VMEMMAP */
+static void register_page_bootmem_info_section(unsigned long start_pfn)
+{
+	unsigned long *usemap, mapsize, section_nr, i;
+	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);
+
+	register_page_bootmem_memmap(section_nr, memmap, PAGES_PER_SECTION);
+
+	usemap = __nr_to_section(section_nr)->pageblock_flags;
+	page = virt_to_page(usemap);
+
+	mapsize = PAGE_ALIGN(usemap_size()) >> PAGE_SHIFT;
+
+	for (i = 0; i < mapsize; i++, page++)
+		get_page_bootmem(section_nr, page, MIX_SECTION_INFO);
+}
+#endif /* !CONFIG_SPARSEMEM_VMEMMAP */
 
 void register_page_bootmem_info_node(struct pglist_data *pgdat)
 {
@@ -143,7 +256,7 @@ void register_page_bootmem_info_node(struct pglist_data *pgdat)
 
 	zone = &pgdat->node_zones[0];
 	for (; zone < pgdat->node_zones + MAX_NR_ZONES - 1; zone++) {
-		if (zone->wait_table) {
+		if (zone_is_initialized(zone)) {
 			nr_pages = zone->wait_table_hash_nr_entries
 				* sizeof(wait_queue_head_t);
 			nr_pages = PAGE_ALIGN(nr_pages) >> PAGE_SHIFT;
@@ -155,14 +268,21 @@ void register_page_bootmem_info_node(struct pglist_data *pgdat)
 	}
 
 	pfn = pgdat->node_start_pfn;
-	end_pfn = pfn + pgdat->node_spanned_pages;
-
-	/* register_section info */
-	for (; pfn < end_pfn; pfn += PAGES_PER_SECTION)
-		register_page_bootmem_info_section(pfn);
+	end_pfn = pgdat_end_pfn(pgdat);
 
+	/* register section info */
+	for (; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
+		/*
+		 * Some platforms can assign the same pfn to multiple nodes - on
+		 * node0 as well as nodeN.  To avoid registering a pfn against
+		 * multiple nodes we check that this pfn does not already
+		 * reside in some other nodes.
+		 */
+		if (pfn_valid(pfn) && (pfn_to_nid(pfn) == node))
+			register_page_bootmem_info_section(pfn);
+	}
 }
-#endif /* !CONFIG_SPARSEMEM_VMEMMAP */
+#endif /* CONFIG_HAVE_BOOTMEM_INFO_NODE */
 
 static void grow_zone_span(struct zone *zone, unsigned long start_pfn,
 			   unsigned long end_pfn)
@@ -171,8 +291,8 @@ static void grow_zone_span(struct zone *zone, unsigned long start_pfn,
 
 	zone_span_writelock(zone);
 
-	old_zone_end_pfn = zone->zone_start_pfn + zone->spanned_pages;
-	if (start_pfn < zone->zone_start_pfn)
+	old_zone_end_pfn = zone_end_pfn(zone);
+	if (zone_is_empty(zone) || start_pfn < zone->zone_start_pfn)
 		zone->zone_start_pfn = start_pfn;
 
 	zone->spanned_pages = max(old_zone_end_pfn, end_pfn) -
@@ -181,13 +301,138 @@ static void grow_zone_span(struct zone *zone, unsigned long start_pfn,
 	zone_span_writeunlock(zone);
 }
 
+static void resize_zone(struct zone *zone, unsigned long start_pfn,
+		unsigned long end_pfn)
+{
+	zone_span_writelock(zone);
+
+	if (end_pfn - start_pfn) {
+		zone->zone_start_pfn = start_pfn;
+		zone->spanned_pages = end_pfn - start_pfn;
+	} else {
+		/*
+		 * make it consist as free_area_init_core(),
+		 * if spanned_pages = 0, then keep start_pfn = 0
+		 */
+		zone->zone_start_pfn = 0;
+		zone->spanned_pages = 0;
+	}
+
+	zone_span_writeunlock(zone);
+}
+
+static void fix_zone_id(struct zone *zone, unsigned long start_pfn,
+		unsigned long end_pfn)
+{
+	enum zone_type zid = zone_idx(zone);
+	int nid = zone->zone_pgdat->node_id;
+	unsigned long pfn;
+
+	for (pfn = start_pfn; pfn < end_pfn; pfn++)
+		set_page_links(pfn_to_page(pfn), zid, nid, pfn);
+}
+
+/* Can fail with -ENOMEM from allocating a wait table with vmalloc() or
+ * alloc_bootmem_node_nopanic()/memblock_virt_alloc_node_nopanic() */
+static int __ref ensure_zone_is_initialized(struct zone *zone,
+			unsigned long start_pfn, unsigned long num_pages)
+{
+	if (!zone_is_initialized(zone))
+		return init_currently_empty_zone(zone, start_pfn, num_pages,
+						 MEMMAP_HOTPLUG);
+	return 0;
+}
+
+static int __meminit move_pfn_range_left(struct zone *z1, struct zone *z2,
+		unsigned long start_pfn, unsigned long end_pfn)
+{
+	int ret;
+	unsigned long flags;
+	unsigned long z1_start_pfn;
+
+	ret = ensure_zone_is_initialized(z1, start_pfn, end_pfn - start_pfn);
+	if (ret)
+		return ret;
+
+	pgdat_resize_lock(z1->zone_pgdat, &flags);
+
+	/* can't move pfns which are higher than @z2 */
+	if (end_pfn > zone_end_pfn(z2))
+		goto out_fail;
+	/* the move out part must be at the left most of @z2 */
+	if (start_pfn > z2->zone_start_pfn)
+		goto out_fail;
+	/* must included/overlap */
+	if (end_pfn <= z2->zone_start_pfn)
+		goto out_fail;
+
+	/* use start_pfn for z1's start_pfn if z1 is empty */
+	if (!zone_is_empty(z1))
+		z1_start_pfn = z1->zone_start_pfn;
+	else
+		z1_start_pfn = start_pfn;
+
+	resize_zone(z1, z1_start_pfn, end_pfn);
+	resize_zone(z2, end_pfn, zone_end_pfn(z2));
+
+	pgdat_resize_unlock(z1->zone_pgdat, &flags);
+
+	fix_zone_id(z1, start_pfn, end_pfn);
+
+	return 0;
+out_fail:
+	pgdat_resize_unlock(z1->zone_pgdat, &flags);
+	return -1;
+}
+
+static int __meminit move_pfn_range_right(struct zone *z1, struct zone *z2,
+		unsigned long start_pfn, unsigned long end_pfn)
+{
+	int ret;
+	unsigned long flags;
+	unsigned long z2_end_pfn;
+
+	ret = ensure_zone_is_initialized(z2, start_pfn, end_pfn - start_pfn);
+	if (ret)
+		return ret;
+
+	pgdat_resize_lock(z1->zone_pgdat, &flags);
+
+	/* can't move pfns which are lower than @z1 */
+	if (z1->zone_start_pfn > start_pfn)
+		goto out_fail;
+	/* the move out part mast at the right most of @z1 */
+	if (zone_end_pfn(z1) >  end_pfn)
+		goto out_fail;
+	/* must included/overlap */
+	if (start_pfn >= zone_end_pfn(z1))
+		goto out_fail;
+
+	/* use end_pfn for z2's end_pfn if z2 is empty */
+	if (!zone_is_empty(z2))
+		z2_end_pfn = zone_end_pfn(z2);
+	else
+		z2_end_pfn = end_pfn;
+
+	resize_zone(z1, z1->zone_start_pfn, start_pfn);
+	resize_zone(z2, start_pfn, z2_end_pfn);
+
+	pgdat_resize_unlock(z1->zone_pgdat, &flags);
+
+	fix_zone_id(z2, start_pfn, end_pfn);
+
+	return 0;
+out_fail:
+	pgdat_resize_unlock(z1->zone_pgdat, &flags);
+	return -1;
+}
+
 static void grow_pgdat_span(struct pglist_data *pgdat, unsigned long start_pfn,
 			    unsigned long end_pfn)
 {
-	unsigned long old_pgdat_end_pfn =
-		pgdat->node_start_pfn + pgdat->node_spanned_pages;
+	unsigned long old_pgdat_end_pfn = pgdat_end_pfn(pgdat);
 
-	if (start_pfn < pgdat->node_start_pfn)
+	if (!pgdat->node_spanned_pages || start_pfn < pgdat->node_start_pfn)
 		pgdat->node_start_pfn = start_pfn;
 
 	pgdat->node_spanned_pages = max(old_pgdat_end_pfn, end_pfn) -
@@ -201,16 +446,13 @@ static int __meminit __add_zone(struct zone *zone, unsigned long phys_start_pfn)
 	int nid = pgdat->node_id;
 	int zone_type;
 	unsigned long flags;
+	int ret;
 
 	zone_type = zone - pgdat->node_zones;
-	if (!zone->wait_table) {
-		int ret;
+	ret = ensure_zone_is_initialized(zone, phys_start_pfn, nr_pages);
+	if (ret)
+		return ret;
 
-		ret = init_currently_empty_zone(zone, phys_start_pfn,
-						nr_pages, MEMMAP_HOTPLUG);
-		if (ret)
-			return ret;
-	}
 	pgdat_resize_lock(zone->zone_pgdat, &flags);
 	grow_zone_span(zone, phys_start_pfn, phys_start_pfn + nr_pages);
 	grow_pgdat_span(zone->zone_pgdat, phys_start_pfn,
@@ -224,13 +466,12 @@ static int __meminit __add_zone(struct zone *zone, unsigned long phys_start_pfn)
 static int __meminit __add_section(int nid, struct zone *zone,
 					unsigned long phys_start_pfn)
 {
-	int nr_pages = PAGES_PER_SECTION;
 	int ret;
 
 	if (pfn_valid(phys_start_pfn))
 		return -EEXIST;
 
-	ret = sparse_add_one_section(zone, phys_start_pfn, nr_pages);
+	ret = sparse_add_one_section(zone, phys_start_pfn);
 
 	if (ret < 0)
 		return ret;
@@ -243,36 +484,6 @@ 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)
-{
-	/*
-	 * XXX: Freeing memmap with vmemmap is not implement yet.
-	 *      This should be removed later.
-	 */
-	return -EBUSY;
-}
-#else
-static int __remove_section(struct zone *zone, struct mem_section *ms)
-{
-	unsigned long flags;
-	struct pglist_data *pgdat = zone->zone_pgdat;
-	int ret = -EINVAL;
-
-	if (!valid_section(ms))
-		return ret;
-
-	ret = unregister_memory_section(ms);
-	if (ret)
-		return ret;
-
-	pgdat_resize_lock(pgdat, &flags);
-	sparse_remove_one_section(zone, ms);
-	pgdat_resize_unlock(pgdat, &flags);
-	return 0;
-}
-#endif
-
 /*
  * Reasonably generic function for adding memory.  It is
  * expected that archs that support memory hotplug will
@@ -306,6 +517,230 @@ int __ref __add_pages(int nid, struct zone *zone, unsigned long phys_start_pfn,
 }
 EXPORT_SYMBOL_GPL(__add_pages);
 
+#ifdef CONFIG_MEMORY_HOTREMOVE
+/* find the smallest valid pfn in the range [start_pfn, end_pfn) */
+static int find_smallest_section_pfn(int nid, struct zone *zone,
+				     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;
+
+		if (unlikely(pfn_to_nid(start_pfn) != nid))
+			continue;
+
+		if (zone && zone != page_zone(pfn_to_page(start_pfn)))
+			continue;
+
+		return start_pfn;
+	}
+
+	return 0;
+}
+
+/* find the biggest valid pfn in the range [start_pfn, end_pfn). */
+static int find_biggest_section_pfn(int nid, struct zone *zone,
+				    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;
+
+		if (unlikely(pfn_to_nid(pfn) != nid))
+			continue;
+
+		if (zone && zone != page_zone(pfn_to_page(pfn)))
+			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 z = zone_end_pfn(zone); /* zone_end_pfn namespace clash */
+	unsigned long zone_end_pfn = z;
+	unsigned long pfn;
+	struct mem_section *ms;
+	int nid = zone_to_nid(zone);
+
+	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(nid, zone, 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(nid, zone, 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 (page_zone(pfn_to_page(pfn)) != zone)
+			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 p = pgdat_end_pfn(pgdat); /* pgdat_end_pfn namespace clash */
+	unsigned long pgdat_end_pfn = p;
+	unsigned long pfn;
+	struct mem_section *ms;
+	int nid = pgdat->node_id;
+
+	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(nid, NULL, 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(nid, NULL, 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 (pfn_to_nid(pfn) != nid)
+			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 start_pfn;
+	int scn_nr;
+	int ret = -EINVAL;
+
+	if (!valid_section(ms))
+		return ret;
+
+	ret = unregister_memory_section(ms);
+	if (ret)
+		return ret;
+
+	scn_nr = __section_nr(ms);
+	start_pfn = section_nr_to_pfn(scn_nr);
+	__remove_zone(zone, start_pfn);
+
+	sparse_remove_one_section(zone, ms);
+	return 0;
+}
+
 /**
  * __remove_pages() - remove sections of pages from a zone
  * @zone: zone from which pages need to be removed
@@ -320,8 +755,10 @@ EXPORT_SYMBOL_GPL(__add_pages);
 int __remove_pages(struct zone *zone, unsigned long phys_start_pfn,
 		 unsigned long nr_pages)
 {
-	unsigned long i, ret = 0;
+	unsigned long i;
 	int sections_to_remove;
+	resource_size_t start, size;
+	int ret = 0;
 
 	/*
 	 * We can only remove entire sections
@@ -329,11 +766,19 @@ 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);
 
+	start = phys_start_pfn << PAGE_SHIFT;
+	size = nr_pages * PAGE_SIZE;
+	ret = release_mem_region_adjustable(&iomem_resource, start, size);
+	if (ret) {
+		resource_size_t endres = start + size - 1;
+
+		pr_warn("Unable to release resource <%pa-%pa> (%d)\n",
+				&start, &endres, ret);
+	}
+
 	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;
@@ -341,27 +786,68 @@ int __remove_pages(struct zone *zone, unsigned long phys_start_pfn,
 	return ret;
 }
 EXPORT_SYMBOL_GPL(__remove_pages);
+#endif /* CONFIG_MEMORY_HOTREMOVE */
 
-void online_page(struct page *page)
+int set_online_page_callback(online_page_callback_t callback)
 {
-	unsigned long pfn = page_to_pfn(page);
+	int rc = -EINVAL;
 
-	totalram_pages++;
-	if (pfn >= num_physpages)
-		num_physpages = pfn + 1;
+	get_online_mems();
+	mutex_lock(&online_page_callback_lock);
 
-#ifdef CONFIG_HIGHMEM
-	if (PageHighMem(page))
-		totalhigh_pages++;
-#endif
+	if (online_page_callback == generic_online_page) {
+		online_page_callback = callback;
+		rc = 0;
+	}
 
-#ifdef CONFIG_FLATMEM
-	max_mapnr = max(page_to_pfn(page), max_mapnr);
-#endif
+	mutex_unlock(&online_page_callback_lock);
+	put_online_mems();
+
+	return rc;
+}
+EXPORT_SYMBOL_GPL(set_online_page_callback);
 
-	ClearPageReserved(page);
-	init_page_count(page);
-	__free_page(page);
+int restore_online_page_callback(online_page_callback_t callback)
+{
+	int rc = -EINVAL;
+
+	get_online_mems();
+	mutex_lock(&online_page_callback_lock);
+
+	if (online_page_callback == callback) {
+		online_page_callback = generic_online_page;
+		rc = 0;
+	}
+
+	mutex_unlock(&online_page_callback_lock);
+	put_online_mems();
+
+	return rc;
+}
+EXPORT_SYMBOL_GPL(restore_online_page_callback);
+
+void __online_page_set_limits(struct page *page)
+{
+}
+EXPORT_SYMBOL_GPL(__online_page_set_limits);
+
+void __online_page_increment_counters(struct page *page)
+{
+	adjust_managed_page_count(page, 1);
+}
+EXPORT_SYMBOL_GPL(__online_page_increment_counters);
+
+void __online_page_free(struct page *page)
+{
+	__free_reserved_page(page);
+}
+EXPORT_SYMBOL_GPL(__online_page_free);
+
+static void generic_online_page(struct page *page)
+{
+	__online_page_set_limits(page);
+	__online_page_increment_counters(page);
+	__online_page_free(page);
 }
 
 static int online_pages_range(unsigned long start_pfn, unsigned long nr_pages,
@@ -373,16 +859,108 @@ static int online_pages_range(unsigned long start_pfn, unsigned long nr_pages,
 	if (PageReserved(pfn_to_page(start_pfn)))
 		for (i = 0; i < nr_pages; i++) {
 			page = pfn_to_page(start_pfn + i);
-			online_page(page);
+			(*online_page_callback)(page);
 			onlined_pages++;
 		}
 	*(unsigned long *)arg = onlined_pages;
 	return 0;
 }
 
+#ifdef CONFIG_MOVABLE_NODE
+/*
+ * When CONFIG_MOVABLE_NODE, we permit onlining of a node which doesn't have
+ * normal memory.
+ */
+static bool can_online_high_movable(struct zone *zone)
+{
+	return true;
+}
+#else /* CONFIG_MOVABLE_NODE */
+/* ensure every online node has NORMAL memory */
+static bool can_online_high_movable(struct zone *zone)
+{
+	return node_state(zone_to_nid(zone), N_NORMAL_MEMORY);
+}
+#endif /* CONFIG_MOVABLE_NODE */
 
-int online_pages(unsigned long pfn, unsigned long nr_pages)
+/* check which state of node_states will be changed when online memory */
+static void node_states_check_changes_online(unsigned long nr_pages,
+	struct zone *zone, struct memory_notify *arg)
 {
+	int nid = zone_to_nid(zone);
+	enum zone_type zone_last = ZONE_NORMAL;
+
+	/*
+	 * If we have HIGHMEM or movable node, node_states[N_NORMAL_MEMORY]
+	 * contains nodes which have zones of 0...ZONE_NORMAL,
+	 * set zone_last to ZONE_NORMAL.
+	 *
+	 * If we don't have HIGHMEM nor movable node,
+	 * node_states[N_NORMAL_MEMORY] contains nodes which have zones of
+	 * 0...ZONE_MOVABLE, set zone_last to ZONE_MOVABLE.
+	 */
+	if (N_MEMORY == N_NORMAL_MEMORY)
+		zone_last = ZONE_MOVABLE;
+
+	/*
+	 * if the memory to be online is in a zone of 0...zone_last, and
+	 * the zones of 0...zone_last don't have memory before online, we will
+	 * need to set the node to node_states[N_NORMAL_MEMORY] after
+	 * the memory is online.
+	 */
+	if (zone_idx(zone) <= zone_last && !node_state(nid, N_NORMAL_MEMORY))
+		arg->status_change_nid_normal = nid;
+	else
+		arg->status_change_nid_normal = -1;
+
+#ifdef CONFIG_HIGHMEM
+	/*
+	 * If we have movable node, node_states[N_HIGH_MEMORY]
+	 * contains nodes which have zones of 0...ZONE_HIGHMEM,
+	 * set zone_last to ZONE_HIGHMEM.
+	 *
+	 * If we don't have movable node, node_states[N_NORMAL_MEMORY]
+	 * contains nodes which have zones of 0...ZONE_MOVABLE,
+	 * set zone_last to ZONE_MOVABLE.
+	 */
+	zone_last = ZONE_HIGHMEM;
+	if (N_MEMORY == N_HIGH_MEMORY)
+		zone_last = ZONE_MOVABLE;
+
+	if (zone_idx(zone) <= zone_last && !node_state(nid, N_HIGH_MEMORY))
+		arg->status_change_nid_high = nid;
+	else
+		arg->status_change_nid_high = -1;
+#else
+	arg->status_change_nid_high = arg->status_change_nid_normal;
+#endif
+
+	/*
+	 * if the node don't have memory befor online, we will need to
+	 * set the node to node_states[N_MEMORY] after the memory
+	 * is online.
+	 */
+	if (!node_state(nid, N_MEMORY))
+		arg->status_change_nid = nid;
+	else
+		arg->status_change_nid = -1;
+}
+
+static void node_states_set_node(int node, struct memory_notify *arg)
+{
+	if (arg->status_change_nid_normal >= 0)
+		node_set_state(node, N_NORMAL_MEMORY);
+
+	if (arg->status_change_nid_high >= 0)
+		node_set_state(node, N_HIGH_MEMORY);
+
+	node_set_state(node, N_MEMORY);
+}
+
+
+int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_type)
+{
+	unsigned long flags;
 	unsigned long onlined_pages = 0;
 	struct zone *zone;
 	int need_zonelists_rebuild = 0;
@@ -390,68 +968,98 @@ int online_pages(unsigned long pfn, unsigned long nr_pages)
 	int ret;
 	struct memory_notify arg;
 
+	mem_hotplug_begin();
+	/*
+	 * This doesn't need a lock to do pfn_to_page().
+	 * The section can't be removed here because of the
+	 * memory_block->state_mutex.
+	 */
+	zone = page_zone(pfn_to_page(pfn));
+
+	ret = -EINVAL;
+	if ((zone_idx(zone) > ZONE_NORMAL || online_type == ONLINE_MOVABLE) &&
+	    !can_online_high_movable(zone))
+		goto out;
+
+	if (online_type == ONLINE_KERNEL && zone_idx(zone) == ZONE_MOVABLE) {
+		if (move_pfn_range_left(zone - 1, zone, pfn, pfn + nr_pages))
+			goto out;
+	}
+	if (online_type == ONLINE_MOVABLE && zone_idx(zone) == ZONE_MOVABLE - 1) {
+		if (move_pfn_range_right(zone, zone + 1, pfn, pfn + nr_pages))
+			goto out;
+	}
+
+	/* Previous code may changed the zone of the pfn range */
+	zone = page_zone(pfn_to_page(pfn));
+
 	arg.start_pfn = pfn;
 	arg.nr_pages = nr_pages;
-	arg.status_change_nid = -1;
+	node_states_check_changes_online(nr_pages, zone, &arg);
 
-	nid = page_to_nid(pfn_to_page(pfn));
-	if (node_present_pages(nid) == 0)
-		arg.status_change_nid = nid;
+	nid = pfn_to_nid(pfn);
 
 	ret = memory_notify(MEM_GOING_ONLINE, &arg);
 	ret = notifier_to_errno(ret);
 	if (ret) {
 		memory_notify(MEM_CANCEL_ONLINE, &arg);
-		return ret;
+		goto out;
 	}
 	/*
-	 * This doesn't need a lock to do pfn_to_page().
-	 * The section can't be removed here because of the
-	 * memory_block->state_mutex.
-	 */
-	zone = page_zone(pfn_to_page(pfn));
-	/*
 	 * If this zone is not populated, then it is not in zonelist.
 	 * This means the page allocator ignores this zone.
 	 * So, zonelist must be updated after online.
 	 */
 	mutex_lock(&zonelists_mutex);
-	if (!populated_zone(zone))
+	if (!populated_zone(zone)) {
 		need_zonelists_rebuild = 1;
+		build_all_zonelists(NULL, zone);
+	}
 
 	ret = walk_system_ram_range(pfn, nr_pages, &onlined_pages,
 		online_pages_range);
 	if (ret) {
+		if (need_zonelists_rebuild)
+			zone_pcp_reset(zone);
 		mutex_unlock(&zonelists_mutex);
-		printk(KERN_DEBUG "online_pages %lx at %lx failed\n",
-			nr_pages, pfn);
+		printk(KERN_DEBUG "online_pages [mem %#010llx-%#010llx] failed\n",
+		       (unsigned long long) pfn << PAGE_SHIFT,
+		       (((unsigned long long) pfn + nr_pages)
+			    << PAGE_SHIFT) - 1);
 		memory_notify(MEM_CANCEL_ONLINE, &arg);
-		return ret;
+		goto out;
 	}
 
 	zone->present_pages += onlined_pages;
+
+	pgdat_resize_lock(zone->zone_pgdat, &flags);
 	zone->zone_pgdat->node_present_pages += onlined_pages;
-	if (need_zonelists_rebuild)
-		build_all_zonelists(zone);
-	else
-		zone_pcp_update(zone);
+	pgdat_resize_unlock(zone->zone_pgdat, &flags);
 
-	mutex_unlock(&zonelists_mutex);
-	setup_per_zone_wmarks();
-	calculate_zone_inactive_ratio(zone);
 	if (onlined_pages) {
-		kswapd_run(zone_to_nid(zone));
-		node_set_state(zone_to_nid(zone), N_HIGH_MEMORY);
+		node_states_set_node(zone_to_nid(zone), &arg);
+		if (need_zonelists_rebuild)
+			build_all_zonelists(NULL, NULL);
+		else
+			zone_pcp_update(zone);
 	}
 
+	mutex_unlock(&zonelists_mutex);
+
+	init_per_zone_wmark_min();
+
+	if (onlined_pages)
+		kswapd_run(zone_to_nid(zone));
+
 	vm_total_pages = nr_free_pagecache_pages();
 
 	writeback_set_ratelimit();
 
 	if (onlined_pages)
 		memory_notify(MEM_ONLINE, &arg);
-
-	return 0;
+out:
+	mem_hotplug_done();
+	return ret;
 }
 #endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */
 
@@ -461,19 +1069,30 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start)
 	struct pglist_data *pgdat;
 	unsigned long zones_size[MAX_NR_ZONES] = {0};
 	unsigned long zholes_size[MAX_NR_ZONES] = {0};
-	unsigned long start_pfn = start >> PAGE_SHIFT;
+	unsigned long start_pfn = PFN_DOWN(start);
 
-	pgdat = arch_alloc_nodedata(nid);
-	if (!pgdat)
-		return NULL;
+	pgdat = NODE_DATA(nid);
+	if (!pgdat) {
+		pgdat = arch_alloc_nodedata(nid);
+		if (!pgdat)
+			return NULL;
 
-	arch_refresh_nodedata(nid, pgdat);
+		arch_refresh_nodedata(nid, pgdat);
+	}
 
 	/* we can use NODE_DATA(nid) from here */
 
 	/* init node's zones as empty zones, we don't have any present pages.*/
 	free_area_init_node(nid, zones_size, start_pfn, zholes_size);
 
+	/*
+	 * The node we allocated has no zone fallback lists. For avoiding
+	 * to access not-initialized zonelist, build here.
+	 */
+	mutex_lock(&zonelists_mutex);
+	build_all_zonelists(pgdat, NULL);
+	mutex_unlock(&zonelists_mutex);
+
 	return pgdat;
 }
 
@@ -485,17 +1104,23 @@ static void rollback_node_hotadd(int nid, pg_data_t *pgdat)
 }
 
 
-/*
+/**
+ * try_online_node - online a node if offlined
+ *
  * called by cpu_up() to online a node without onlined memory.
  */
-int mem_online_node(int nid)
+int try_online_node(int nid)
 {
 	pg_data_t	*pgdat;
 	int	ret;
 
-	lock_system_sleep();
+	if (node_online(nid))
+		return 0;
+
+	mem_hotplug_begin();
 	pgdat = hotadd_new_pgdat(nid, 0);
-	if (pgdat) {
+	if (!pgdat) {
+		pr_err("Cannot online node %d due to NULL pgdat\n", nid);
 		ret = -ENOMEM;
 		goto out;
 	}
@@ -503,32 +1128,65 @@ int mem_online_node(int nid)
 	ret = register_one_node(nid);
 	BUG_ON(ret);
 
+	if (pgdat->node_zonelists->_zonerefs->zone == NULL) {
+		mutex_lock(&zonelists_mutex);
+		build_all_zonelists(NULL, NULL);
+		mutex_unlock(&zonelists_mutex);
+	}
+
 out:
-	unlock_system_sleep();
+	mem_hotplug_done();
 	return ret;
 }
 
+static int check_hotplug_memory_range(u64 start, u64 size)
+{
+	u64 start_pfn = PFN_DOWN(start);
+	u64 nr_pages = size >> PAGE_SHIFT;
+
+	/* Memory range must be aligned with section */
+	if ((start_pfn & ~PAGE_SECTION_MASK) ||
+	    (nr_pages % PAGES_PER_SECTION) || (!nr_pages)) {
+		pr_err("Section-unaligned hotplug range: start 0x%llx, size 0x%llx\n",
+				(unsigned long long)start,
+				(unsigned long long)size);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 /* we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG */
 int __ref add_memory(int nid, u64 start, u64 size)
 {
 	pg_data_t *pgdat = NULL;
-	int new_pgdat = 0;
+	bool new_pgdat;
+	bool new_node;
 	struct resource *res;
 	int ret;
 
-	lock_system_sleep();
+	ret = check_hotplug_memory_range(start, size);
+	if (ret)
+		return ret;
 
 	res = register_memory_resource(start, size);
 	ret = -EEXIST;
 	if (!res)
-		goto out;
+		return ret;
+
+	{	/* Stupid hack to suppress address-never-null warning */
+		void *p = NODE_DATA(nid);
+		new_pgdat = !p;
+	}
+
+	mem_hotplug_begin();
 
-	if (!node_online(nid)) {
+	new_node = !node_online(nid);
+	if (new_node) {
 		pgdat = hotadd_new_pgdat(nid, start);
 		ret = -ENOMEM;
 		if (!pgdat)
-			goto out;
-		new_pgdat = 1;
+			goto error;
 	}
 
 	/* call arch's memory hotadd */
@@ -540,7 +1198,7 @@ int __ref add_memory(int nid, u64 start, u64 size)
 	/* we online node here. we can't roll back from here. */
 	node_set_online(nid);
 
-	if (new_pgdat) {
+	if (new_node) {
 		ret = register_one_node(nid);
 		/*
 		 * If sysfs file of new node can't create, cpu on the node
@@ -559,11 +1217,10 @@ error:
 	/* rollback pgdat allocation and others */
 	if (new_pgdat)
 		rollback_node_hotadd(nid, pgdat);
-	if (res)
-		release_memory_resource(res);
+	release_memory_resource(res);
 
 out:
-	unlock_system_sleep();
+	mem_hotplug_done();
 	return ret;
 }
 EXPORT_SYMBOL_GPL(add_memory);
@@ -643,10 +1300,12 @@ static int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn)
 }
 
 /*
- * Scanning pfn is much easier than scanning lru list.
- * Scan pfn from start to end and Find LRU page.
+ * Scan pfn range [start,end) to find movable/migratable pages (LRU pages
+ * and hugepages). We scan pfn because it's much easier than scanning over
+ * linked list. This function returns the pfn of the first found movable
+ * page if it's found, otherwise 0.
  */
-static unsigned long scan_lru_pages(unsigned long start, unsigned long end)
+static unsigned long scan_movable_pages(unsigned long start, unsigned long end)
 {
 	unsigned long pfn;
 	struct page *page;
@@ -655,18 +1314,18 @@ static unsigned long scan_lru_pages(unsigned long start, unsigned long end)
 			page = pfn_to_page(pfn);
 			if (PageLRU(page))
 				return pfn;
+			if (PageHuge(page)) {
+				if (is_hugepage_active(page))
+					return pfn;
+				else
+					pfn = round_up(pfn + 1,
+						1 << compound_order(page)) - 1;
+			}
 		}
 	}
 	return 0;
 }
 
-static struct page *
-hotremove_migrate_alloc(struct page *page, unsigned long private, int **x)
-{
-	/* This should be improooooved!! */
-	return alloc_page(GFP_HIGHUSER_MOVABLE);
-}
-
 #define NR_OFFLINE_AT_ONCE_PAGES	(256)
 static int
 do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
@@ -682,7 +1341,20 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
 		if (!pfn_valid(pfn))
 			continue;
 		page = pfn_to_page(pfn);
-		if (!page_count(page))
+
+		if (PageHuge(page)) {
+			struct page *head = compound_head(page);
+			pfn = page_to_pfn(head) + (1<<compound_order(head)) - 1;
+			if (compound_order(head) > PFN_SECTION_SHIFT) {
+				ret = -EBUSY;
+				break;
+			}
+			if (isolate_huge_page(page, &source))
+				move_pages -= 1 << compound_order(head);
+			continue;
+		}
+
+		if (!get_page_unless_zero(page))
 			continue;
 		/*
 		 * We can skip free pages. And we can only deal with pages on
@@ -690,6 +1362,7 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
 		 */
 		ret = isolate_lru_page(page);
 		if (!ret) { /* Success */
+			put_page(page);
 			list_add_tail(&page->lru, &source);
 			move_pages--;
 			inc_zone_page_state(page, NR_ISOLATED_ANON +
@@ -699,9 +1372,10 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
 #ifdef CONFIG_DEBUG_VM
 			printk(KERN_ALERT "removing pfn %lx from LRU failed\n",
 			       pfn);
-			dump_page(page);
+			dump_page(page, "failed to remove from LRU");
 #endif
-			/* Becasue we don't have big zone->lock. we should
+			put_page(page);
+			/* Because we don't have big zone->lock. we should
 			   check this again here. */
 			if (page_count(page)) {
 				not_managed++;
@@ -712,13 +1386,18 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
 	}
 	if (!list_empty(&source)) {
 		if (not_managed) {
-			putback_lru_pages(&source);
+			putback_movable_pages(&source);
 			goto out;
 		}
-		/* this function returns # of failed pages */
-		ret = migrate_pages(&source, hotremove_migrate_alloc, 0, 1);
+
+		/*
+		 * alloc_migrate_target should be improooooved!!
+		 * migrate_pages returns # of failed pages.
+		 */
+		ret = migrate_pages(&source, alloc_migrate_target, NULL, 0,
+					MIGRATE_SYNC, MR_MEMORY_HOTPLUG);
 		if (ret)
-			putback_lru_pages(&source);
+			putback_movable_pages(&source);
 	}
 out:
 	return ret;
@@ -751,7 +1430,7 @@ check_pages_isolated_cb(unsigned long start_pfn, unsigned long nr_pages,
 {
 	int ret;
 	long offlined = *(long *)data;
-	ret = test_pages_isolated(start_pfn, start_pfn + nr_pages);
+	ret = test_pages_isolated(start_pfn, start_pfn + nr_pages, true);
 	offlined = nr_pages;
 	if (!ret)
 		*(long *)data += offlined;
@@ -771,16 +1450,173 @@ check_pages_isolated(unsigned long start_pfn, unsigned long end_pfn)
 	return offlined;
 }
 
-static int offline_pages(unsigned long start_pfn,
+#ifdef CONFIG_MOVABLE_NODE
+/*
+ * When CONFIG_MOVABLE_NODE, we permit offlining of a node which doesn't have
+ * normal memory.
+ */
+static bool can_offline_normal(struct zone *zone, unsigned long nr_pages)
+{
+	return true;
+}
+#else /* CONFIG_MOVABLE_NODE */
+/* ensure the node has NORMAL memory if it is still online */
+static bool can_offline_normal(struct zone *zone, unsigned long nr_pages)
+{
+	struct pglist_data *pgdat = zone->zone_pgdat;
+	unsigned long present_pages = 0;
+	enum zone_type zt;
+
+	for (zt = 0; zt <= ZONE_NORMAL; zt++)
+		present_pages += pgdat->node_zones[zt].present_pages;
+
+	if (present_pages > nr_pages)
+		return true;
+
+	present_pages = 0;
+	for (; zt <= ZONE_MOVABLE; zt++)
+		present_pages += pgdat->node_zones[zt].present_pages;
+
+	/*
+	 * we can't offline the last normal memory until all
+	 * higher memory is offlined.
+	 */
+	return present_pages == 0;
+}
+#endif /* CONFIG_MOVABLE_NODE */
+
+static int __init cmdline_parse_movable_node(char *p)
+{
+#ifdef CONFIG_MOVABLE_NODE
+	/*
+	 * Memory used by the kernel cannot be hot-removed because Linux
+	 * cannot migrate the kernel pages. When memory hotplug is
+	 * enabled, we should prevent memblock from allocating memory
+	 * for the kernel.
+	 *
+	 * ACPI SRAT records all hotpluggable memory ranges. But before
+	 * SRAT is parsed, we don't know about it.
+	 *
+	 * The kernel image is loaded into memory at very early time. We
+	 * cannot prevent this anyway. So on NUMA system, we set any
+	 * node the kernel resides in as un-hotpluggable.
+	 *
+	 * Since on modern servers, one node could have double-digit
+	 * gigabytes memory, we can assume the memory around the kernel
+	 * image is also un-hotpluggable. So before SRAT is parsed, just
+	 * allocate memory near the kernel image to try the best to keep
+	 * the kernel away from hotpluggable memory.
+	 */
+	memblock_set_bottom_up(true);
+	movable_node_enabled = true;
+#else
+	pr_warn("movable_node option not supported\n");
+#endif
+	return 0;
+}
+early_param("movable_node", cmdline_parse_movable_node);
+
+/* check which state of node_states will be changed when offline memory */
+static void node_states_check_changes_offline(unsigned long nr_pages,
+		struct zone *zone, struct memory_notify *arg)
+{
+	struct pglist_data *pgdat = zone->zone_pgdat;
+	unsigned long present_pages = 0;
+	enum zone_type zt, zone_last = ZONE_NORMAL;
+
+	/*
+	 * If we have HIGHMEM or movable node, node_states[N_NORMAL_MEMORY]
+	 * contains nodes which have zones of 0...ZONE_NORMAL,
+	 * set zone_last to ZONE_NORMAL.
+	 *
+	 * If we don't have HIGHMEM nor movable node,
+	 * node_states[N_NORMAL_MEMORY] contains nodes which have zones of
+	 * 0...ZONE_MOVABLE, set zone_last to ZONE_MOVABLE.
+	 */
+	if (N_MEMORY == N_NORMAL_MEMORY)
+		zone_last = ZONE_MOVABLE;
+
+	/*
+	 * check whether node_states[N_NORMAL_MEMORY] will be changed.
+	 * If the memory to be offline is in a zone of 0...zone_last,
+	 * and it is the last present memory, 0...zone_last will
+	 * become empty after offline , thus we can determind we will
+	 * need to clear the node from node_states[N_NORMAL_MEMORY].
+	 */
+	for (zt = 0; zt <= zone_last; zt++)
+		present_pages += pgdat->node_zones[zt].present_pages;
+	if (zone_idx(zone) <= zone_last && nr_pages >= present_pages)
+		arg->status_change_nid_normal = zone_to_nid(zone);
+	else
+		arg->status_change_nid_normal = -1;
+
+#ifdef CONFIG_HIGHMEM
+	/*
+	 * If we have movable node, node_states[N_HIGH_MEMORY]
+	 * contains nodes which have zones of 0...ZONE_HIGHMEM,
+	 * set zone_last to ZONE_HIGHMEM.
+	 *
+	 * If we don't have movable node, node_states[N_NORMAL_MEMORY]
+	 * contains nodes which have zones of 0...ZONE_MOVABLE,
+	 * set zone_last to ZONE_MOVABLE.
+	 */
+	zone_last = ZONE_HIGHMEM;
+	if (N_MEMORY == N_HIGH_MEMORY)
+		zone_last = ZONE_MOVABLE;
+
+	for (; zt <= zone_last; zt++)
+		present_pages += pgdat->node_zones[zt].present_pages;
+	if (zone_idx(zone) <= zone_last && nr_pages >= present_pages)
+		arg->status_change_nid_high = zone_to_nid(zone);
+	else
+		arg->status_change_nid_high = -1;
+#else
+	arg->status_change_nid_high = arg->status_change_nid_normal;
+#endif
+
+	/*
+	 * node_states[N_HIGH_MEMORY] contains nodes which have 0...ZONE_MOVABLE
+	 */
+	zone_last = ZONE_MOVABLE;
+
+	/*
+	 * check whether node_states[N_HIGH_MEMORY] will be changed
+	 * If we try to offline the last present @nr_pages from the node,
+	 * we can determind we will need to clear the node from
+	 * node_states[N_HIGH_MEMORY].
+	 */
+	for (; zt <= zone_last; zt++)
+		present_pages += pgdat->node_zones[zt].present_pages;
+	if (nr_pages >= present_pages)
+		arg->status_change_nid = zone_to_nid(zone);
+	else
+		arg->status_change_nid = -1;
+}
+
+static void node_states_clear_node(int node, struct memory_notify *arg)
+{
+	if (arg->status_change_nid_normal >= 0)
+		node_clear_state(node, N_NORMAL_MEMORY);
+
+	if ((N_MEMORY != N_NORMAL_MEMORY) &&
+	    (arg->status_change_nid_high >= 0))
+		node_clear_state(node, N_HIGH_MEMORY);
+
+	if ((N_MEMORY != N_HIGH_MEMORY) &&
+	    (arg->status_change_nid >= 0))
+		node_clear_state(node, N_MEMORY);
+}
+
+static int __ref __offline_pages(unsigned long start_pfn,
 		  unsigned long end_pfn, unsigned long timeout)
 {
 	unsigned long pfn, nr_pages, expire;
 	long offlined_pages;
 	int ret, drain, retry_max, node;
+	unsigned long flags;
 	struct zone *zone;
 	struct memory_notify arg;
 
-	BUG_ON(start_pfn >= end_pfn);
 	/* at least, alignment against pageblock is necessary */
 	if (!IS_ALIGNED(start_pfn, pageblock_nr_pages))
 		return -EINVAL;
@@ -791,22 +1627,25 @@ static int offline_pages(unsigned long start_pfn,
 	if (!test_pages_in_a_zone(start_pfn, end_pfn))
 		return -EINVAL;
 
-	lock_system_sleep();
+	mem_hotplug_begin();
 
 	zone = page_zone(pfn_to_page(start_pfn));
 	node = zone_to_nid(zone);
 	nr_pages = end_pfn - start_pfn;
 
+	ret = -EINVAL;
+	if (zone_idx(zone) <= ZONE_NORMAL && !can_offline_normal(zone, nr_pages))
+		goto out;
+
 	/* set above range as isolated */
-	ret = start_isolate_page_range(start_pfn, end_pfn);
+	ret = start_isolate_page_range(start_pfn, end_pfn,
+				       MIGRATE_MOVABLE, true);
 	if (ret)
 		goto out;
 
 	arg.start_pfn = start_pfn;
 	arg.nr_pages = nr_pages;
-	arg.status_change_nid = -1;
-	if (nr_pages >= node_present_pages(node))
-		arg.status_change_nid = node;
+	node_states_check_changes_offline(nr_pages, zone, &arg);
 
 	ret = memory_notify(MEM_GOING_OFFLINE, &arg);
 	ret = notifier_to_errno(ret);
@@ -832,8 +1671,8 @@ repeat:
 		drain_all_pages();
 	}
 
-	pfn = scan_lru_pages(start_pfn, end_pfn);
-	if (pfn) { /* We have page on LRU */
+	pfn = scan_movable_pages(start_pfn, end_pfn);
+	if (pfn) { /* We have movable pages */
 		ret = do_migrate_range(pfn, end_pfn);
 		if (!ret) {
 			drain = 1;
@@ -847,11 +1686,16 @@ repeat:
 			goto repeat;
 		}
 	}
-	/* drain all zone's lru pagevec, this is asyncronous... */
+	/* drain all zone's lru pagevec, this is asynchronous... */
 	lru_add_drain_all();
 	yield();
-	/* drain pcp pages , this is synchrouns. */
+	/* drain pcp pages, this is synchronous. */
 	drain_all_pages();
+	/*
+	 * dissolve free hugepages in the memory block before doing offlining
+	 * actually in order to make hugetlbfs's object counting consistent.
+	 */
+	dissolve_free_huge_pages(start_pfn, end_pfn);
 	/* check again */
 	offlined_pages = check_pages_isolated(start_pfn, end_pfn);
 	if (offlined_pages < 0) {
@@ -859,54 +1703,273 @@ repeat:
 		goto failed_removal;
 	}
 	printk(KERN_INFO "Offlined Pages %ld\n", offlined_pages);
-	/* Ok, all of our target is islaoted.
+	/* Ok, all of our target is isolated.
 	   We cannot do rollback at this point. */
 	offline_isolated_pages(start_pfn, end_pfn);
 	/* reset pagetype flags and makes migrate type to be MOVABLE */
-	undo_isolate_page_range(start_pfn, end_pfn);
+	undo_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE);
 	/* removal success */
+	adjust_managed_page_count(pfn_to_page(start_pfn), -offlined_pages);
 	zone->present_pages -= offlined_pages;
+
+	pgdat_resize_lock(zone->zone_pgdat, &flags);
 	zone->zone_pgdat->node_present_pages -= offlined_pages;
-	totalram_pages -= offlined_pages;
+	pgdat_resize_unlock(zone->zone_pgdat, &flags);
 
-	setup_per_zone_wmarks();
-	calculate_zone_inactive_ratio(zone);
-	if (!node_present_pages(node)) {
-		node_clear_state(node, N_HIGH_MEMORY);
+	init_per_zone_wmark_min();
+
+	if (!populated_zone(zone)) {
+		zone_pcp_reset(zone);
+		mutex_lock(&zonelists_mutex);
+		build_all_zonelists(NULL, NULL);
+		mutex_unlock(&zonelists_mutex);
+	} else
+		zone_pcp_update(zone);
+
+	node_states_clear_node(node, &arg);
+	if (arg.status_change_nid >= 0)
 		kswapd_stop(node);
-	}
 
 	vm_total_pages = nr_free_pagecache_pages();
 	writeback_set_ratelimit();
 
 	memory_notify(MEM_OFFLINE, &arg);
-	unlock_system_sleep();
+	mem_hotplug_done();
 	return 0;
 
 failed_removal:
-	printk(KERN_INFO "memory offlining %lx to %lx failed\n",
-		start_pfn, end_pfn);
+	printk(KERN_INFO "memory offlining [mem %#010llx-%#010llx] failed\n",
+	       (unsigned long long) start_pfn << PAGE_SHIFT,
+	       ((unsigned long long) end_pfn << PAGE_SHIFT) - 1);
 	memory_notify(MEM_CANCEL_OFFLINE, &arg);
 	/* pushback to free area */
-	undo_isolate_page_range(start_pfn, end_pfn);
+	undo_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE);
 
 out:
-	unlock_system_sleep();
+	mem_hotplug_done();
 	return ret;
 }
 
-int remove_memory(u64 start, u64 size)
+int offline_pages(unsigned long start_pfn, unsigned long nr_pages)
+{
+	return __offline_pages(start_pfn, start_pfn + nr_pages, 120 * HZ);
+}
+#endif /* CONFIG_MEMORY_HOTREMOVE */
+
+/**
+ * walk_memory_range - walks through all mem sections in [start_pfn, end_pfn)
+ * @start_pfn: start pfn of the memory range
+ * @end_pfn: end pfn of the memory range
+ * @arg: argument passed to func
+ * @func: callback for each memory section walked
+ *
+ * This function walks through all present mem sections in range
+ * [start_pfn, end_pfn) and call func on each mem section.
+ *
+ * Returns the return value of func.
+ */
+int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn,
+		void *arg, int (*func)(struct memory_block *, void *))
 {
-	unsigned long start_pfn, end_pfn;
+	struct memory_block *mem = NULL;
+	struct mem_section *section;
+	unsigned long pfn, section_nr;
+	int ret;
+
+	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 = func(mem, arg);
+		if (ret) {
+			kobject_put(&mem->dev.kobj);
+			return ret;
+		}
+	}
 
-	start_pfn = PFN_DOWN(start);
-	end_pfn = start_pfn + PFN_DOWN(size);
-	return offline_pages(start_pfn, end_pfn, 120 * HZ);
+	if (mem)
+		kobject_put(&mem->dev.kobj);
+
+	return 0;
 }
-#else
-int remove_memory(u64 start, u64 size)
+
+#ifdef CONFIG_MEMORY_HOTREMOVE
+static int check_memblock_offlined_cb(struct memory_block *mem, void *arg)
 {
-	return -EINVAL;
+	int ret = !is_memblock_offlined(mem);
+
+	if (unlikely(ret)) {
+		phys_addr_t beginpa, endpa;
+
+		beginpa = PFN_PHYS(section_nr_to_pfn(mem->start_section_nr));
+		endpa = PFN_PHYS(section_nr_to_pfn(mem->end_section_nr + 1))-1;
+		pr_warn("removing memory fails, because memory "
+			"[%pa-%pa] is onlined\n",
+			&beginpa, &endpa);
+	}
+
+	return ret;
+}
+
+static int check_cpu_on_node(pg_data_t *pgdat)
+{
+	int cpu;
+
+	for_each_present_cpu(cpu) {
+		if (cpu_to_node(cpu) == pgdat->node_id)
+			/*
+			 * the cpu on this node isn't removed, and we can't
+			 * offline this node.
+			 */
+			return -EBUSY;
+	}
+
+	return 0;
+}
+
+static void unmap_cpu_on_node(pg_data_t *pgdat)
+{
+#ifdef CONFIG_ACPI_NUMA
+	int cpu;
+
+	for_each_possible_cpu(cpu)
+		if (cpu_to_node(cpu) == pgdat->node_id)
+			numa_clear_node(cpu);
+#endif
+}
+
+static int check_and_unmap_cpu_on_node(pg_data_t *pgdat)
+{
+	int ret;
+
+	ret = check_cpu_on_node(pgdat);
+	if (ret)
+		return ret;
+
+	/*
+	 * the node will be offlined when we come here, so we can clear
+	 * the cpu_to_node() now.
+	 */
+
+	unmap_cpu_on_node(pgdat);
+	return 0;
+}
+
+/**
+ * try_offline_node
+ *
+ * Offline a node if all memory sections and cpus of the node are removed.
+ *
+ * NOTE: The caller must call lock_device_hotplug() to serialize hotplug
+ * and online/offline operations before this call.
+ */
+void try_offline_node(int nid)
+{
+	pg_data_t *pgdat = NODE_DATA(nid);
+	unsigned long start_pfn = pgdat->node_start_pfn;
+	unsigned long end_pfn = start_pfn + pgdat->node_spanned_pages;
+	unsigned long pfn;
+	struct page *pgdat_page = virt_to_page(pgdat);
+	int i;
+
+	for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
+		unsigned long section_nr = pfn_to_section_nr(pfn);
+
+		if (!present_section_nr(section_nr))
+			continue;
+
+		if (pfn_to_nid(pfn) != nid)
+			continue;
+
+		/*
+		 * some memory sections of this node are not removed, and we
+		 * can't offline node now.
+		 */
+		return;
+	}
+
+	if (check_and_unmap_cpu_on_node(pgdat))
+		return;
+
+	/*
+	 * all memory/cpu of this node are removed, we can offline this
+	 * node now.
+	 */
+	node_set_offline(nid);
+	unregister_one_node(nid);
+
+	if (!PageSlab(pgdat_page) && !PageCompound(pgdat_page))
+		/* node data is allocated from boot memory */
+		return;
+
+	/* free waittable in each zone */
+	for (i = 0; i < MAX_NR_ZONES; i++) {
+		struct zone *zone = pgdat->node_zones + i;
+
+		/*
+		 * wait_table may be allocated from boot memory,
+		 * here only free if it's allocated by vmalloc.
+		 */
+		if (is_vmalloc_addr(zone->wait_table))
+			vfree(zone->wait_table);
+	}
+
+	/*
+	 * Since there is no way to guarentee the address of pgdat/zone is not
+	 * on stack of any kernel threads or used by other kernel objects
+	 * without reference counting or other symchronizing method, do not
+	 * reset node_data and free pgdat here. Just reset it to 0 and reuse
+	 * the memory when the node is online again.
+	 */
+	memset(pgdat, 0, sizeof(*pgdat));
+}
+EXPORT_SYMBOL(try_offline_node);
+
+/**
+ * remove_memory
+ *
+ * NOTE: The caller must call lock_device_hotplug() to serialize hotplug
+ * and online/offline operations before this call, as required by
+ * try_offline_node().
+ */
+void __ref remove_memory(int nid, u64 start, u64 size)
+{
+	int ret;
+
+	BUG_ON(check_hotplug_memory_range(start, size));
+
+	mem_hotplug_begin();
+
+	/*
+	 * All memory blocks must be offlined before removing memory.  Check
+	 * whether all memory blocks in question are offline and trigger a BUG()
+	 * if this is not the case.
+	 */
+	ret = walk_memory_range(PFN_DOWN(start), PFN_UP(start + size - 1), NULL,
+				check_memblock_offlined_cb);
+	if (ret)
+		BUG();
+
+	/* remove memmap entry */
+	firmware_map_remove(start, start + size, "System RAM");
+
+	arch_remove_memory(start, size);
+
+	try_offline_node(nid);
+
+	mem_hotplug_done();
 }
-#endif /* CONFIG_MEMORY_HOTREMOVE */
 EXPORT_SYMBOL_GPL(remove_memory);
+#endif /* CONFIG_MEMORY_HOTREMOVE */