21 files changed, 425 insertions, 54 deletions

diff --git a/include/linux/balloon_compaction.h b/include/linux/balloon_compaction.h
new file mode 100644
index 00000000000..f7f1d7169b1
--- /dev/null
+++ b/include/linux/balloon_compaction.h
@@ -0,0 +1,272 @@
+/*
+ * include/linux/balloon_compaction.h
+ *
+ * Common interface definitions for making balloon pages movable by compaction.
+ *
+ * Despite being perfectly possible to perform ballooned pages migration, they
+ * make a special corner case to compaction scans because balloon pages are not
+ * enlisted at any LRU list like the other pages we do compact / migrate.
+ *
+ * As the page isolation scanning step a compaction thread does is a lockless
+ * procedure (from a page standpoint), it might bring some racy situations while
+ * performing balloon page compaction. In order to sort out these racy scenarios
+ * and safely perform balloon's page compaction and migration we must, always,
+ * ensure following these three simple rules:
+ *
+ *   i. when updating a balloon's page ->mapping element, strictly do it under
+ *      the following lock order, independently of the far superior
+ *      locking scheme (lru_lock, balloon_lock):
+ *	    +-page_lock(page);
+ *	      +--spin_lock_irq(&b_dev_info->pages_lock);
+ *	            ... page->mapping updates here ...
+ *
+ *  ii. before isolating or dequeueing a balloon page from the balloon device
+ *      pages list, the page reference counter must be raised by one and the
+ *      extra refcount must be dropped when the page is enqueued back into
+ *      the balloon device page list, thus a balloon page keeps its reference
+ *      counter raised only while it is under our special handling;
+ *
+ * iii. after the lockless scan step have selected a potential balloon page for
+ *      isolation, re-test the page->mapping flags and the page ref counter
+ *      under the proper page lock, to ensure isolating a valid balloon page
+ *      (not yet isolated, nor under release procedure)
+ *
+ * The functions provided by this interface are placed to help on coping with
+ * the aforementioned balloon page corner case, as well as to ensure the simple
+ * set of exposed rules are satisfied while we are dealing with balloon pages
+ * compaction / migration.
+ *
+ * Copyright (C) 2012, Red Hat, Inc.  Rafael Aquini <aquini@redhat.com>
+ */
+#ifndef _LINUX_BALLOON_COMPACTION_H
+#define _LINUX_BALLOON_COMPACTION_H
+#include <linux/pagemap.h>
+#include <linux/page-flags.h>
+#include <linux/migrate.h>
+#include <linux/gfp.h>
+#include <linux/err.h>
+
+/*
+ * Balloon device information descriptor.
+ * This struct is used to allow the common balloon compaction interface
+ * procedures to find the proper balloon device holding memory pages they'll
+ * have to cope for page compaction / migration, as well as it serves the
+ * balloon driver as a page book-keeper for its registered balloon devices.
+ */
+struct balloon_dev_info {
+	void *balloon_device;		/* balloon device descriptor */
+	struct address_space *mapping;	/* balloon special page->mapping */
+	unsigned long isolated_pages;	/* # of isolated pages for migration */
+	spinlock_t pages_lock;		/* Protection to pages list */
+	struct list_head pages;		/* Pages enqueued & handled to Host */
+};
+
+extern struct page *balloon_page_enqueue(struct balloon_dev_info *b_dev_info);
+extern struct page *balloon_page_dequeue(struct balloon_dev_info *b_dev_info);
+extern struct balloon_dev_info *balloon_devinfo_alloc(
+						void *balloon_dev_descriptor);
+
+static inline void balloon_devinfo_free(struct balloon_dev_info *b_dev_info)
+{
+	kfree(b_dev_info);
+}
+
+/*
+ * balloon_page_free - release a balloon page back to the page free lists
+ * @page: ballooned page to be set free
+ *
+ * This function must be used to properly set free an isolated/dequeued balloon
+ * page at the end of a sucessful page migration, or at the balloon driver's
+ * page release procedure.
+ */
+static inline void balloon_page_free(struct page *page)
+{
+	/*
+	 * Balloon pages always get an extra refcount before being isolated
+	 * and before being dequeued to help on sorting out fortuite colisions
+	 * between a thread attempting to isolate and another thread attempting
+	 * to release the very same balloon page.
+	 *
+	 * Before we handle the page back to Buddy, lets drop its extra refcnt.
+	 */
+	put_page(page);
+	__free_page(page);
+}
+
+#ifdef CONFIG_BALLOON_COMPACTION
+extern bool balloon_page_isolate(struct page *page);
+extern void balloon_page_putback(struct page *page);
+extern int balloon_page_migrate(struct page *newpage,
+				struct page *page, enum migrate_mode mode);
+extern struct address_space
+*balloon_mapping_alloc(struct balloon_dev_info *b_dev_info,
+			const struct address_space_operations *a_ops);
+
+static inline void balloon_mapping_free(struct address_space *balloon_mapping)
+{
+	kfree(balloon_mapping);
+}
+
+/*
+ * page_flags_cleared - helper to perform balloon @page ->flags tests.
+ *
+ * As balloon pages are obtained from buddy and we do not play with page->flags
+ * at driver level (exception made when we get the page lock for compaction),
+ * we can safely identify a ballooned page by checking if the
+ * PAGE_FLAGS_CHECK_AT_PREP page->flags are all cleared.  This approach also
+ * helps us skip ballooned pages that are locked for compaction or release, thus
+ * mitigating their racy check at balloon_page_movable()
+ */
+static inline bool page_flags_cleared(struct page *page)
+{
+	return !(page->flags & PAGE_FLAGS_CHECK_AT_PREP);
+}
+
+/*
+ * __is_movable_balloon_page - helper to perform @page mapping->flags tests
+ */
+static inline bool __is_movable_balloon_page(struct page *page)
+{
+	struct address_space *mapping = page->mapping;
+	return mapping_balloon(mapping);
+}
+
+/*
+ * balloon_page_movable - test page->mapping->flags to identify balloon pages
+ *			  that can be moved by compaction/migration.
+ *
+ * This function is used at core compaction's page isolation scheme, therefore
+ * most pages exposed to it are not enlisted as balloon pages and so, to avoid
+ * undesired side effects like racing against __free_pages(), we cannot afford
+ * holding the page locked while testing page->mapping->flags here.
+ *
+ * As we might return false positives in the case of a balloon page being just
+ * released under us, the page->mapping->flags need to be re-tested later,
+ * under the proper page lock, at the functions that will be coping with the
+ * balloon page case.
+ */
+static inline bool balloon_page_movable(struct page *page)
+{
+	/*
+	 * Before dereferencing and testing mapping->flags, let's make sure
+	 * this is not a page that uses ->mapping in a different way
+	 */
+	if (page_flags_cleared(page) && !page_mapped(page) &&
+	    page_count(page) == 1)
+		return __is_movable_balloon_page(page);
+
+	return false;
+}
+
+/*
+ * balloon_page_insert - insert a page into the balloon's page list and make
+ *		         the page->mapping assignment accordingly.
+ * @page    : page to be assigned as a 'balloon page'
+ * @mapping : allocated special 'balloon_mapping'
+ * @head    : balloon's device page list head
+ *
+ * Caller must ensure the page is locked and the spin_lock protecting balloon
+ * pages list is held before inserting a page into the balloon device.
+ */
+static inline void balloon_page_insert(struct page *page,
+				       struct address_space *mapping,
+				       struct list_head *head)
+{
+	page->mapping = mapping;
+	list_add(&page->lru, head);
+}
+
+/*
+ * balloon_page_delete - delete a page from balloon's page list and clear
+ *			 the page->mapping assignement accordingly.
+ * @page    : page to be released from balloon's page list
+ *
+ * Caller must ensure the page is locked and the spin_lock protecting balloon
+ * pages list is held before deleting a page from the balloon device.
+ */
+static inline void balloon_page_delete(struct page *page)
+{
+	page->mapping = NULL;
+	list_del(&page->lru);
+}
+
+/*
+ * balloon_page_device - get the b_dev_info descriptor for the balloon device
+ *			 that enqueues the given page.
+ */
+static inline struct balloon_dev_info *balloon_page_device(struct page *page)
+{
+	struct address_space *mapping = page->mapping;
+	if (likely(mapping))
+		return mapping->private_data;
+
+	return NULL;
+}
+
+static inline gfp_t balloon_mapping_gfp_mask(void)
+{
+	return GFP_HIGHUSER_MOVABLE;
+}
+
+static inline bool balloon_compaction_check(void)
+{
+	return true;
+}
+
+#else /* !CONFIG_BALLOON_COMPACTION */
+
+static inline void *balloon_mapping_alloc(void *balloon_device,
+				const struct address_space_operations *a_ops)
+{
+	return ERR_PTR(-EOPNOTSUPP);
+}
+
+static inline void balloon_mapping_free(struct address_space *balloon_mapping)
+{
+	return;
+}
+
+static inline void balloon_page_insert(struct page *page,
+				       struct address_space *mapping,
+				       struct list_head *head)
+{
+	list_add(&page->lru, head);
+}
+
+static inline void balloon_page_delete(struct page *page)
+{
+	list_del(&page->lru);
+}
+
+static inline bool balloon_page_movable(struct page *page)
+{
+	return false;
+}
+
+static inline bool balloon_page_isolate(struct page *page)
+{
+	return false;
+}
+
+static inline void balloon_page_putback(struct page *page)
+{
+	return;
+}
+
+static inline int balloon_page_migrate(struct page *newpage,
+				struct page *page, enum migrate_mode mode)
+{
+	return 0;
+}
+
+static inline gfp_t balloon_mapping_gfp_mask(void)
+{
+	return GFP_HIGHUSER;
+}
+
+static inline bool balloon_compaction_check(void)
+{
+	return false;
+}
+#endif /* CONFIG_BALLOON_COMPACTION */
+#endif /* _LINUX_BALLOON_COMPACTION_H */
diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h
index 6d6795d46a7..7b74452c531 100644
--- a/include/linux/bootmem.h
+++ b/include/linux/bootmem.h
@@ -51,8 +51,8 @@ extern unsigned long free_all_bootmem(void);
 extern void free_bootmem_node(pg_data_t *pgdat,
 			      unsigned long addr,
 			      unsigned long size);
-extern void free_bootmem(unsigned long addr, unsigned long size);
-extern void free_bootmem_late(unsigned long addr, unsigned long size);
+extern void free_bootmem(unsigned long physaddr, unsigned long size);
+extern void free_bootmem_late(unsigned long physaddr, unsigned long size);
 
 /*
  * Flags for reserve_bootmem (also if CONFIG_HAVE_ARCH_BOOTMEM_NODE,
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 75fe9a13480..408fb1e77a0 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -418,7 +418,7 @@ struct address_space {
 	struct backing_dev_info *backing_dev_info; /* device readahead, etc */
 	spinlock_t		private_lock;	/* for use by the address_space */
 	struct list_head	private_list;	/* ditto */
-	struct address_space	*assoc_mapping;	/* ditto */
+	void			*private_data;	/* ditto */
 } __attribute__((aligned(sizeof(long))));
 	/*
 	 * On most architectures that alignment is already the case; but
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index d0a79678f16..31e8041274f 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -266,7 +266,7 @@ static inline enum zone_type gfp_zone(gfp_t flags)
 
 static inline int gfp_zonelist(gfp_t flags)
 {
-	if (NUMA_BUILD && unlikely(flags & __GFP_THISNODE))
+	if (IS_ENABLED(CONFIG_NUMA) && unlikely(flags & __GFP_THISNODE))
 		return 1;
 
 	return 0;
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index b31cb7da034..1af47755245 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -8,6 +8,10 @@ extern int do_huge_pmd_anonymous_page(struct mm_struct *mm,
 extern int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 			 pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr,
 			 struct vm_area_struct *vma);
+extern void huge_pmd_set_accessed(struct mm_struct *mm,
+				  struct vm_area_struct *vma,
+				  unsigned long address, pmd_t *pmd,
+				  pmd_t orig_pmd, int dirty);
 extern int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			       unsigned long address, pmd_t *pmd,
 			       pmd_t orig_pmd);
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 225164842ab..3e7fa1acf09 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -183,7 +183,8 @@ extern const struct file_operations hugetlbfs_file_operations;
 extern const struct vm_operations_struct hugetlb_vm_ops;
 struct file *hugetlb_file_setup(const char *name, unsigned long addr,
 				size_t size, vm_flags_t acct,
-				struct user_struct **user, int creat_flags);
+				struct user_struct **user, int creat_flags,
+				int page_size_log);
 
 static inline int is_file_hugepages(struct file *file)
 {
@@ -195,12 +196,14 @@ static inline int is_file_hugepages(struct file *file)
 	return 0;
 }
 
+
 #else /* !CONFIG_HUGETLBFS */
 
 #define is_file_hugepages(file)			0
 static inline struct file *
 hugetlb_file_setup(const char *name, unsigned long addr, size_t size,
-		vm_flags_t acctflag, struct user_struct **user, int creat_flags)
+		vm_flags_t acctflag, struct user_struct **user, int creat_flags,
+		int page_size_log)
 {
 	return ERR_PTR(-ENOSYS);
 }
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 7d8dfc7392f..dd9900cabf8 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -687,20 +687,6 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { }
 /* Trap pasters of __FUNCTION__ at compile-time */
 #define __FUNCTION__ (__func__)
 
-/* This helps us to avoid #ifdef CONFIG_NUMA */
-#ifdef CONFIG_NUMA
-#define NUMA_BUILD 1
-#else
-#define NUMA_BUILD 0
-#endif
-
-/* This helps us avoid #ifdef CONFIG_COMPACTION */
-#ifdef CONFIG_COMPACTION
-#define COMPACTION_BUILD 1
-#else
-#define COMPACTION_BUILD 0
-#endif
-
 /* This helps us to avoid #ifdef CONFIG_SYMBOL_PREFIX */
 #ifdef CONFIG_SYMBOL_PREFIX
 #define SYMBOL_PREFIX CONFIG_SYMBOL_PREFIX
diff --git a/include/linux/memory.h b/include/linux/memory.h
index ff9a9f8e0ed..a09216d0dcc 100644
--- a/include/linux/memory.h
+++ b/include/linux/memory.h
@@ -53,6 +53,7 @@ int arch_get_memory_phys_device(unsigned long start_pfn);
 struct memory_notify {
 	unsigned long start_pfn;
 	unsigned long nr_pages;
+	int status_change_nid_normal;
 	int status_change_nid;
 };
 
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 95573ec4ee6..4a45c4e5002 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -26,6 +26,13 @@ enum {
 	MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE = NODE_INFO,
 };
 
+/* Types for control the zone type of onlined memory */
+enum {
+	ONLINE_KEEP,
+	ONLINE_KERNEL,
+	ONLINE_MOVABLE,
+};
+
 /*
  * pgdat resizing functions
  */
@@ -46,6 +53,10 @@ void pgdat_resize_init(struct pglist_data *pgdat)
 }
 /*
  * Zone resizing functions
+ *
+ * Note: any attempt to resize a zone should has pgdat_resize_lock()
+ * zone_span_writelock() both held. This ensure the size of a zone
+ * can't be changed while pgdat_resize_lock() held.
  */
 static inline unsigned zone_span_seqbegin(struct zone *zone)
 {
@@ -71,7 +82,7 @@ extern int zone_grow_free_lists(struct zone *zone, unsigned long new_nr_pages);
 extern int zone_grow_waitqueues(struct zone *zone, unsigned long nr_pages);
 extern int add_one_highpage(struct page *page, int pfn, int bad_ppro);
 /* VM interface that may be used by firmware interface */
-extern int online_pages(unsigned long, unsigned long);
+extern int online_pages(unsigned long, unsigned long, int);
 extern void __offline_isolated_pages(unsigned long, unsigned long);
 
 typedef void (*online_page_callback_t)(struct page *page);
diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index ce7e6671968..0b5865c61ef 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -7,9 +7,27 @@
 
 typedef struct page *new_page_t(struct page *, unsigned long private, int **);
 
+/*
+ * Return values from addresss_space_operations.migratepage():
+ * - negative errno on page migration failure;
+ * - zero on page migration success;
+ *
+ * The balloon page migration introduces this special case where a 'distinct'
+ * return code is used to flag a successful page migration to unmap_and_move().
+ * This approach is necessary because page migration can race against balloon
+ * deflation procedure, and for such case we could introduce a nasty page leak
+ * if a successfully migrated balloon page gets released concurrently with
+ * migration's unmap_and_move() wrap-up steps.
+ */
+#define MIGRATEPAGE_SUCCESS		0
+#define MIGRATEPAGE_BALLOON_SUCCESS	1 /* special ret code for balloon page
+					   * sucessful migration case.
+					   */
+
 #ifdef CONFIG_MIGRATION
 
 extern void putback_lru_pages(struct list_head *l);
+extern void putback_movable_pages(struct list_head *l);
 extern int migrate_page(struct address_space *,
 			struct page *, struct page *, enum migrate_mode);
 extern int migrate_pages(struct list_head *l, new_page_t x,
@@ -33,6 +51,7 @@ extern int migrate_huge_page_move_mapping(struct address_space *mapping,
 #else
 
 static inline void putback_lru_pages(struct list_head *l) {}
+static inline void putback_movable_pages(struct list_head *l) {}
 static inline int migrate_pages(struct list_head *l, new_page_t x,
 		unsigned long private, bool offlining,
 		enum migrate_mode mode) { return -ENOSYS; }
diff --git a/include/linux/mm.h b/include/linux/mm.h
index bcaab4e6fe9..4af4f0b1be4 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1456,6 +1456,37 @@ extern unsigned long vm_mmap(struct file *, unsigned long,
         unsigned long, unsigned long,
         unsigned long, unsigned long);
 
+struct vm_unmapped_area_info {
+#define VM_UNMAPPED_AREA_TOPDOWN 1
+	unsigned long flags;
+	unsigned long length;
+	unsigned long low_limit;
+	unsigned long high_limit;
+	unsigned long align_mask;
+	unsigned long align_offset;
+};
+
+extern unsigned long unmapped_area(struct vm_unmapped_area_info *info);
+extern unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info);
+
+/*
+ * Search for an unmapped address range.
+ *
+ * We are looking for a range that:
+ * - does not intersect with any VMA;
+ * - is contained within the [low_limit, high_limit) interval;
+ * - is at least the desired size.
+ * - satisfies (begin_addr & align_mask) == (align_offset & align_mask)
+ */
+static inline unsigned long
+vm_unmapped_area(struct vm_unmapped_area_info *info)
+{
+	if (!(info->flags & VM_UNMAPPED_AREA_TOPDOWN))
+		return unmapped_area(info);
+	else
+		return unmapped_area_topdown(info);
+}
+
 /* truncate.c */
 extern void truncate_inode_pages(struct address_space *, loff_t);
 extern void truncate_inode_pages_range(struct address_space *,
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 31f8a3af7d9..7ade2731b5d 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -224,7 +224,8 @@ struct vm_region {
  * library, the executable area etc).
  */
 struct vm_area_struct {
-	struct mm_struct * vm_mm;	/* The address space we belong to. */
+	/* The first cache line has the info for VMA tree walking. */
+
 	unsigned long vm_start;		/* Our start address within vm_mm. */
 	unsigned long vm_end;		/* The first byte after our end address
 					   within vm_mm. */
@@ -232,11 +233,22 @@ struct vm_area_struct {
 	/* linked list of VM areas per task, sorted by address */
 	struct vm_area_struct *vm_next, *vm_prev;
 
+	struct rb_node vm_rb;
+
+	/*
+	 * Largest free memory gap in bytes to the left of this VMA.
+	 * Either between this VMA and vma->vm_prev, or between one of the
+	 * VMAs below us in the VMA rbtree and its ->vm_prev. This helps
+	 * get_unmapped_area find a free area of the right size.
+	 */
+	unsigned long rb_subtree_gap;
+
+	/* Second cache line starts here. */
+
+	struct mm_struct *vm_mm;	/* The address space we belong to. */
 	pgprot_t vm_page_prot;		/* Access permissions of this VMA. */
 	unsigned long vm_flags;		/* Flags, see mm.h. */
 
-	struct rb_node vm_rb;
-
 	/*
 	 * For areas with an address space and backing store,
 	 * linkage into the address_space->i_mmap interval tree, or
@@ -322,6 +334,7 @@ struct mm_struct {
 	unsigned long task_size;		/* size of task vm space */
 	unsigned long cached_hole_size; 	/* if non-zero, the largest hole below free_area_cache */
 	unsigned long free_area_cache;		/* first hole of size cached_hole_size or larger */
+	unsigned long highest_vm_end;		/* highest vma end address */
 	pgd_t * pgd;
 	atomic_t mm_users;			/* How many users with user space? */
 	atomic_t mm_count;			/* How many references to "struct mm_struct" (users count as 1) */
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index a23923ba826..0c0b1d608a6 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -63,10 +63,8 @@ enum {
 
 #ifdef CONFIG_CMA
 #  define is_migrate_cma(migratetype) unlikely((migratetype) == MIGRATE_CMA)
-#  define cma_wmark_pages(zone)	zone->min_cma_pages
 #else
 #  define is_migrate_cma(migratetype) false
-#  define cma_wmark_pages(zone) 0
 #endif
 
 #define for_each_migratetype_order(order, type) \
@@ -383,13 +381,6 @@ struct zone {
 	/* see spanned/present_pages for more description */
 	seqlock_t		span_seqlock;
 #endif
-#ifdef CONFIG_CMA
-	/*
-	 * CMA needs to increase watermark levels during the allocation
-	 * process to make sure that the system is not starved.
-	 */
-	unsigned long		min_cma_pages;
-#endif
 	struct free_area	free_area[MAX_ORDER];
 
 #ifndef CONFIG_SPARSEMEM
diff --git a/include/linux/node.h b/include/linux/node.h
index 624e53cecc0..2115ad5d6f1 100644
--- a/include/linux/node.h
+++ b/include/linux/node.h
@@ -27,10 +27,9 @@ struct node {
 };
 
 struct memory_block;
-extern struct node node_devices[];
+extern struct node *node_devices[];
 typedef  void (*node_registration_func_t)(struct node *);
 
-extern int register_node(struct node *, int, struct node *);
 extern void unregister_node(struct node *node);
 #ifdef CONFIG_NUMA
 extern int register_one_node(int nid);
diff --git a/include/linux/oom.h b/include/linux/oom.h
index fb9826847b8..da60007075b 100644
--- a/include/linux/oom.h
+++ b/include/linux/oom.h
@@ -29,8 +29,23 @@ enum oom_scan_t {
 	OOM_SCAN_SELECT,	/* always select this thread first */
 };
 
-extern void compare_swap_oom_score_adj(int old_val, int new_val);
-extern int test_set_oom_score_adj(int new_val);
+/* Thread is the potential origin of an oom condition; kill first on oom */
+#define OOM_FLAG_ORIGIN		((__force oom_flags_t)0x1)
+
+static inline void set_current_oom_origin(void)
+{
+	current->signal->oom_flags |= OOM_FLAG_ORIGIN;
+}
+
+static inline void clear_current_oom_origin(void)
+{
+	current->signal->oom_flags &= ~OOM_FLAG_ORIGIN;
+}
+
+static inline bool oom_task_origin(const struct task_struct *p)
+{
+	return !!(p->signal->oom_flags & OOM_FLAG_ORIGIN);
+}
 
 extern unsigned long oom_badness(struct task_struct *p,
 		struct mem_cgroup *memcg, const nodemask_t *nodemask,
@@ -49,8 +64,6 @@ extern void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask,
 extern enum oom_scan_t oom_scan_process_thread(struct task_struct *task,
 		unsigned long totalpages, const nodemask_t *nodemask,
 		bool force_kill);
-extern void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
-				     int order);
 
 extern void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
 		int order, nodemask_t *mask, bool force_kill);
diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h
index 76a9539cfd3..a92061e08d4 100644
--- a/include/linux/page-isolation.h
+++ b/include/linux/page-isolation.h
@@ -2,7 +2,8 @@
 #define __LINUX_PAGEISOLATION_H
 
 
-bool has_unmovable_pages(struct zone *zone, struct page *page, int count);
+bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
+			 bool skip_hwpoisoned_pages);
 void set_pageblock_migratetype(struct page *page, int migratetype);
 int move_freepages_block(struct zone *zone, struct page *page,
 				int migratetype);
@@ -21,7 +22,7 @@ int move_freepages(struct zone *zone,
  */
 int
 start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
-			 unsigned migratetype);
+			 unsigned migratetype, bool skip_hwpoisoned_pages);
 
 /*
  * Changes MIGRATE_ISOLATE to MIGRATE_MOVABLE.
@@ -34,12 +35,13 @@ undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
 /*
  * Test all pages in [start_pfn, end_pfn) are isolated or not.
  */
-int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn);
+int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn,
+			bool skip_hwpoisoned_pages);
 
 /*
  * Internal functions. Changes pageblock's migrate type.
  */
-int set_migratetype_isolate(struct page *page);
+int set_migratetype_isolate(struct page *page, bool skip_hwpoisoned_pages);
 void unset_migratetype_isolate(struct page *page, unsigned migratetype);
 struct page *alloc_migrate_target(struct page *page, unsigned long private,
 				int **resultp);
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index e42c762f0dc..6da609d14c1 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -24,6 +24,7 @@ enum mapping_flags {
 	AS_ENOSPC	= __GFP_BITS_SHIFT + 1,	/* ENOSPC on async write */
 	AS_MM_ALL_LOCKS	= __GFP_BITS_SHIFT + 2,	/* under mm_take_all_locks() */
 	AS_UNEVICTABLE	= __GFP_BITS_SHIFT + 3,	/* e.g., ramdisk, SHM_LOCK */
+	AS_BALLOON_MAP  = __GFP_BITS_SHIFT + 4, /* balloon page special map */
 };
 
 static inline void mapping_set_error(struct address_space *mapping, int error)
@@ -53,6 +54,21 @@ static inline int mapping_unevictable(struct address_space *mapping)
 	return !!mapping;
 }
 
+static inline void mapping_set_balloon(struct address_space *mapping)
+{
+	set_bit(AS_BALLOON_MAP, &mapping->flags);
+}
+
+static inline void mapping_clear_balloon(struct address_space *mapping)
+{
+	clear_bit(AS_BALLOON_MAP, &mapping->flags);
+}
+
+static inline int mapping_balloon(struct address_space *mapping)
+{
+	return mapping && test_bit(AS_BALLOON_MAP, &mapping->flags);
+}
+
 static inline gfp_t mapping_gfp_mask(struct address_space * mapping)
 {
 	return (__force gfp_t)mapping->flags & __GFP_BITS_MASK;
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 0dd42a02df2..3e387df065f 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -631,9 +631,10 @@ struct signal_struct {
 	struct rw_semaphore group_rwsem;
 #endif
 
-	int oom_score_adj;	/* OOM kill score adjustment */
-	int oom_score_adj_min;	/* OOM kill score adjustment minimum value.
-				 * Only settable by CAP_SYS_RESOURCE. */
+	oom_flags_t oom_flags;
+	short oom_score_adj;		/* OOM kill score adjustment */
+	short oom_score_adj_min;	/* OOM kill score adjustment min value.
+					 * Only settable by CAP_SYS_RESOURCE. */
 
 	struct mutex cred_guard_mutex;	/* guard against foreign influences on
 					 * credential calculations
diff --git a/include/linux/shm.h b/include/linux/shm.h
index bcf8a6a3ec0..429c1995d75 100644
--- a/include/linux/shm.h
+++ b/include/linux/shm.h
@@ -29,6 +29,21 @@ struct shmid_kernel /* private to the kernel */
 #define SHM_HUGETLB     04000   /* segment will use huge TLB pages */
 #define SHM_NORESERVE   010000  /* don't check for reservations */
 
+/* Bits [26:31] are reserved */
+
+/*
+ * When SHM_HUGETLB is set bits [26:31] encode the log2 of the huge page size.
+ * This gives us 6 bits, which is enough until someone invents 128 bit address
+ * spaces.
+ *
+ * Assume these are all power of twos.
+ * When 0 use the default page size.
+ */
+#define SHM_HUGE_SHIFT  26
+#define SHM_HUGE_MASK   0x3f
+#define SHM_HUGE_2MB    (21 << SHM_HUGE_SHIFT)
+#define SHM_HUGE_1GB    (30 << SHM_HUGE_SHIFT)
+
 #ifdef CONFIG_SYSVIPC
 long do_shmat(int shmid, char __user *shmaddr, int shmflg, unsigned long *addr,
 	      unsigned long shmlba);
diff --git a/include/linux/types.h b/include/linux/types.h
index 1cc0e4b9a04..4d118ba1134 100644
--- a/include/linux/types.h
+++ b/include/linux/types.h
@@ -156,6 +156,7 @@ typedef u32 dma_addr_t;
 #endif
 typedef unsigned __bitwise__ gfp_t;
 typedef unsigned __bitwise__ fmode_t;
+typedef unsigned __bitwise__ oom_flags_t;
 
 #ifdef CONFIG_PHYS_ADDR_T_64BIT
 typedef u64 phys_addr_t;
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 50c3e8fa06a..b82a83aba31 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -161,14 +161,7 @@ void __bdi_update_bandwidth(struct backing_dev_info *bdi,
 			    unsigned long start_time);
 
 void page_writeback_init(void);
-void balance_dirty_pages_ratelimited_nr(struct address_space *mapping,
-					unsigned long nr_pages_dirtied);
-
-static inline void
-balance_dirty_pages_ratelimited(struct address_space *mapping)
-{
-	balance_dirty_pages_ratelimited_nr(mapping, 1);
-}
+void balance_dirty_pages_ratelimited(struct address_space *mapping);
 
 typedef int (*writepage_t)(struct page *page, struct writeback_control *wbc,
 				void *data);