Merge branch 'master'

12 files changed, 409 insertions, 81 deletions

diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 88af42f5e04..c937d6e6550 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -126,8 +126,8 @@ BUFFER_FNS(Eopnotsupp, eopnotsupp)
 /* If we *know* page->private refers to buffer_heads */
 #define page_buffers(page)					\
 	({							\
-		BUG_ON(!PagePrivate(page));		\
-		((struct buffer_head *)(page)->private);	\
+		BUG_ON(!PagePrivate(page));			\
+		((struct buffer_head *)page_private(page));	\
 	})
 #define page_has_buffers(page)	PagePrivate(page)
 
@@ -219,7 +219,7 @@ static inline void attach_page_buffers(struct page *page,
 {
 	page_cache_get(page);
 	SetPagePrivate(page);
-	page->private = (unsigned long)head;
+	set_page_private(page, (unsigned long)head);
 }
 
 static inline void get_bh(struct buffer_head *bh)
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index d664330d900..0cea162b08c 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -16,7 +16,6 @@ static inline int is_vm_hugetlb_page(struct vm_area_struct *vma)
 int hugetlb_sysctl_handler(struct ctl_table *, int, struct file *, void __user *, size_t *, loff_t *);
 int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *);
 int follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *, struct page **, struct vm_area_struct **, unsigned long *, int *, int);
-void zap_hugepage_range(struct vm_area_struct *, unsigned long, unsigned long);
 void unmap_hugepage_range(struct vm_area_struct *, unsigned long, unsigned long);
 int hugetlb_prefault(struct address_space *, struct vm_area_struct *);
 int hugetlb_report_meminfo(char *);
@@ -87,7 +86,6 @@ static inline unsigned long hugetlb_total_pages(void)
 #define follow_huge_addr(mm, addr, write)	ERR_PTR(-EINVAL)
 #define copy_hugetlb_page_range(src, dst, vma)	({ BUG(); 0; })
 #define hugetlb_prefault(mapping, vma)		({ BUG(); 0; })
-#define zap_hugepage_range(vma, start, len)	BUG()
 #define unmap_hugepage_range(vma, start, end)	BUG()
 #define is_hugepage_mem_enough(size)		0
 #define hugetlb_report_meminfo(buf)		0
diff --git a/include/linux/memory.h b/include/linux/memory.h
new file mode 100644
index 00000000000..0def328ab5c
--- /dev/null
+++ b/include/linux/memory.h
@@ -0,0 +1,94 @@
+/*
+ * include/linux/memory.h - generic memory definition
+ *
+ * This is mainly for topological representation. We define the
+ * basic "struct memory_block" here, which can be embedded in per-arch
+ * definitions or NUMA information.
+ *
+ * Basic handling of the devices is done in drivers/base/memory.c
+ * and system devices are handled in drivers/base/sys.c.
+ *
+ * Memory block are exported via sysfs in the class/memory/devices/
+ * directory.
+ *
+ */
+#ifndef _LINUX_MEMORY_H_
+#define _LINUX_MEMORY_H_
+
+#include <linux/sysdev.h>
+#include <linux/node.h>
+#include <linux/compiler.h>
+
+#include <asm/semaphore.h>
+
+struct memory_block {
+	unsigned long phys_index;
+	unsigned long state;
+	/*
+	 * This serializes all state change requests.  It isn't
+	 * held during creation because the control files are
+	 * created long after the critical areas during
+	 * initialization.
+	 */
+	struct semaphore state_sem;
+	int phys_device;		/* to which fru does this belong? */
+	void *hw;			/* optional pointer to fw/hw data */
+	int (*phys_callback)(struct memory_block *);
+	struct sys_device sysdev;
+};
+
+/* These states are exposed to userspace as text strings in sysfs */
+#define	MEM_ONLINE		(1<<0) /* exposed to userspace */
+#define	MEM_GOING_OFFLINE	(1<<1) /* exposed to userspace */
+#define	MEM_OFFLINE		(1<<2) /* exposed to userspace */
+
+/*
+ * All of these states are currently kernel-internal for notifying
+ * kernel components and architectures.
+ *
+ * For MEM_MAPPING_INVALID, all notifier chains with priority >0
+ * are called before pfn_to_page() becomes invalid.  The priority=0
+ * entry is reserved for the function that actually makes
+ * pfn_to_page() stop working.  Any notifiers that want to be called
+ * after that should have priority <0.
+ */
+#define	MEM_MAPPING_INVALID	(1<<3)
+
+#ifndef CONFIG_MEMORY_HOTPLUG
+static inline int memory_dev_init(void)
+{
+	return 0;
+}
+static inline int register_memory_notifier(struct notifier_block *nb)
+{
+	return 0;
+}
+static inline void unregister_memory_notifier(struct notifier_block *nb)
+{
+}
+#else
+extern int register_memory(struct memory_block *, struct mem_section *section, struct node *);
+extern int register_new_memory(struct mem_section *);
+extern int unregister_memory_section(struct mem_section *);
+extern int memory_dev_init(void);
+extern int register_memory_notifier(struct notifier_block *nb);
+extern void unregister_memory_notifier(struct notifier_block *nb);
+
+#define CONFIG_MEM_BLOCK_SIZE	(PAGES_PER_SECTION<<PAGE_SHIFT)
+
+extern int invalidate_phys_mapping(unsigned long, unsigned long);
+struct notifier_block;
+
+extern int register_memory_notifier(struct notifier_block *nb);
+extern void unregister_memory_notifier(struct notifier_block *nb);
+
+extern struct sysdev_class memory_sysdev_class;
+#endif /* CONFIG_MEMORY_HOTPLUG */
+
+#define hotplug_memory_notifier(fn, pri) {			\
+	static struct notifier_block fn##_mem_nb =		\
+		{ .notifier_call = fn, .priority = pri };	\
+	register_memory_notifier(&fn##_mem_nb);			\
+}
+
+#endif /* _LINUX_MEMORY_H_ */
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
new file mode 100644
index 00000000000..01f03bc06ef
--- /dev/null
+++ b/include/linux/memory_hotplug.h
@@ -0,0 +1,104 @@
+#ifndef __LINUX_MEMORY_HOTPLUG_H
+#define __LINUX_MEMORY_HOTPLUG_H
+
+#include <linux/mmzone.h>
+#include <linux/spinlock.h>
+#include <linux/mmzone.h>
+#include <linux/notifier.h>
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+/*
+ * pgdat resizing functions
+ */
+static inline
+void pgdat_resize_lock(struct pglist_data *pgdat, unsigned long *flags)
+{
+	spin_lock_irqsave(&pgdat->node_size_lock, *flags);
+}
+static inline
+void pgdat_resize_unlock(struct pglist_data *pgdat, unsigned long *flags)
+{
+	spin_unlock_irqrestore(&pgdat->node_size_lock, *flags);
+}
+static inline
+void pgdat_resize_init(struct pglist_data *pgdat)
+{
+	spin_lock_init(&pgdat->node_size_lock);
+}
+/*
+ * Zone resizing functions
+ */
+static inline unsigned zone_span_seqbegin(struct zone *zone)
+{
+	return read_seqbegin(&zone->span_seqlock);
+}
+static inline int zone_span_seqretry(struct zone *zone, unsigned iv)
+{
+	return read_seqretry(&zone->span_seqlock, iv);
+}
+static inline void zone_span_writelock(struct zone *zone)
+{
+	write_seqlock(&zone->span_seqlock);
+}
+static inline void zone_span_writeunlock(struct zone *zone)
+{
+	write_sequnlock(&zone->span_seqlock);
+}
+static inline void zone_seqlock_init(struct zone *zone)
+{
+	seqlock_init(&zone->span_seqlock);
+}
+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);
+/* need some defines for these for archs that don't support it */
+extern void online_page(struct page *page);
+/* VM interface that may be used by firmware interface */
+extern int add_memory(u64 start, u64 size);
+extern int remove_memory(u64 start, u64 size);
+extern int online_pages(unsigned long, unsigned long);
+
+/* reasonably generic interface to expand the physical pages in a zone  */
+extern int __add_pages(struct zone *zone, unsigned long start_pfn,
+	unsigned long nr_pages);
+#else /* ! CONFIG_MEMORY_HOTPLUG */
+/*
+ * Stub functions for when hotplug is off
+ */
+static inline void pgdat_resize_lock(struct pglist_data *p, unsigned long *f) {}
+static inline void pgdat_resize_unlock(struct pglist_data *p, unsigned long *f) {}
+static inline void pgdat_resize_init(struct pglist_data *pgdat) {}
+
+static inline unsigned zone_span_seqbegin(struct zone *zone)
+{
+	return 0;
+}
+static inline int zone_span_seqretry(struct zone *zone, unsigned iv)
+{
+	return 0;
+}
+static inline void zone_span_writelock(struct zone *zone) {}
+static inline void zone_span_writeunlock(struct zone *zone) {}
+static inline void zone_seqlock_init(struct zone *zone) {}
+
+static inline int mhp_notimplemented(const char *func)
+{
+	printk(KERN_WARNING "%s() called, with CONFIG_MEMORY_HOTPLUG disabled\n", func);
+	dump_stack();
+	return -ENOSYS;
+}
+
+static inline int __add_pages(struct zone *zone, unsigned long start_pfn,
+	unsigned long nr_pages)
+{
+	return mhp_notimplemented(__FUNCTION__);
+}
+#endif /* ! CONFIG_MEMORY_HOTPLUG */
+static inline int __remove_pages(struct zone *zone, unsigned long start_pfn,
+	unsigned long nr_pages)
+{
+	printk(KERN_WARNING "%s() called, not yet supported\n", __FUNCTION__);
+	dump_stack();
+	return -ENOSYS;
+}
+#endif /* __LINUX_MEMORY_HOTPLUG_H */
diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index 58385ee1c0a..7af8cb836e7 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -27,10 +27,10 @@
 
 #include <linux/config.h>
 #include <linux/mmzone.h>
-#include <linux/bitmap.h>
 #include <linux/slab.h>
 #include <linux/rbtree.h>
 #include <linux/spinlock.h>
+#include <linux/nodemask.h>
 
 struct vm_area_struct;
 
@@ -47,8 +47,7 @@ struct vm_area_struct;
  * Locking policy for interlave:
  * In process context there is no locking because only the process accesses
  * its own state. All vma manipulation is somewhat protected by a down_read on
- * mmap_sem. For allocating in the interleave policy the page_table_lock
- * must be also aquired to protect il_next.
+ * mmap_sem.
  *
  * Freeing policy:
  * When policy is MPOL_BIND v.zonelist is kmalloc'ed and must be kfree'd.
@@ -63,7 +62,7 @@ struct mempolicy {
 	union {
 		struct zonelist  *zonelist;	/* bind */
 		short 		 preferred_node; /* preferred */
-		DECLARE_BITMAP(nodes, MAX_NUMNODES); /* interleave */
+		nodemask_t	 nodes;		/* interleave */
 		/* undefined for default */
 	} v;
 };
diff --git a/include/linux/mm.h b/include/linux/mm.h
index e1649578fb0..5c1fb0a2e80 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -157,7 +157,7 @@ extern unsigned int kobjsize(const void *objp);
 
 #define VM_DONTCOPY	0x00020000      /* Do not copy this vma on fork */
 #define VM_DONTEXPAND	0x00040000	/* Cannot expand with mremap() */
-#define VM_RESERVED	0x00080000	/* Don't unmap it from swap_out */
+#define VM_RESERVED	0x00080000	/* Pages managed in a special way */
 #define VM_ACCOUNT	0x00100000	/* Is a VM accounted object */
 #define VM_HUGETLB	0x00400000	/* Huge TLB Page VM */
 #define VM_NONLINEAR	0x00800000	/* Is non-linear (remap_file_pages) */
@@ -226,13 +226,18 @@ struct page {
 					 * to show when page is mapped
 					 * & limit reverse map searches.
 					 */
-	unsigned long private;		/* Mapping-private opaque data:
+	union {
+		unsigned long private;	/* Mapping-private opaque data:
 					 * usually used for buffer_heads
 					 * if PagePrivate set; used for
 					 * swp_entry_t if PageSwapCache
 					 * When page is free, this indicates
 					 * order in the buddy system.
 					 */
+#if NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS
+		spinlock_t ptl;
+#endif
+	} u;
 	struct address_space *mapping;	/* If low bit clear, points to
 					 * inode address_space, or NULL.
 					 * If page mapped as anonymous
@@ -260,6 +265,9 @@ struct page {
 #endif /* WANT_PAGE_VIRTUAL */
 };
 
+#define page_private(page)		((page)->u.private)
+#define set_page_private(page, v)	((page)->u.private = (v))
+
 /*
  * FIXME: take this include out, include page-flags.h in
  * files which need it (119 of them)
@@ -311,17 +319,17 @@ extern void FASTCALL(__page_cache_release(struct page *));
 
 #ifdef CONFIG_HUGETLB_PAGE
 
-static inline int page_count(struct page *p)
+static inline int page_count(struct page *page)
 {
-	if (PageCompound(p))
-		p = (struct page *)p->private;
-	return atomic_read(&(p)->_count) + 1;
+	if (PageCompound(page))
+		page = (struct page *)page_private(page);
+	return atomic_read(&page->_count) + 1;
 }
 
 static inline void get_page(struct page *page)
 {
 	if (unlikely(PageCompound(page)))
-		page = (struct page *)page->private;
+		page = (struct page *)page_private(page);
 	atomic_inc(&page->_count);
 }
 
@@ -338,7 +346,7 @@ static inline void get_page(struct page *page)
 
 static inline void put_page(struct page *page)
 {
-	if (!PageReserved(page) && put_page_testzero(page))
+	if (put_page_testzero(page))
 		__page_cache_release(page);
 }
 
@@ -587,7 +595,7 @@ static inline int PageAnon(struct page *page)
 static inline pgoff_t page_index(struct page *page)
 {
 	if (unlikely(PageSwapCache(page)))
-		return page->private;
+		return page_private(page);
 	return page->index;
 }
 
@@ -682,7 +690,7 @@ struct zap_details {
 
 unsigned long zap_page_range(struct vm_area_struct *vma, unsigned long address,
 		unsigned long size, struct zap_details *);
-unsigned long unmap_vmas(struct mmu_gather **tlb, struct mm_struct *mm,
+unsigned long unmap_vmas(struct mmu_gather **tlb,
 		struct vm_area_struct *start_vma, unsigned long start_addr,
 		unsigned long end_addr, unsigned long *nr_accounted,
 		struct zap_details *);
@@ -704,10 +712,6 @@ static inline void unmap_shared_mapping_range(struct address_space *mapping,
 }
 
 extern int vmtruncate(struct inode * inode, loff_t offset);
-extern pud_t *FASTCALL(__pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address));
-extern pmd_t *FASTCALL(__pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address));
-extern pte_t *FASTCALL(pte_alloc_kernel(struct mm_struct *mm, pmd_t *pmd, unsigned long address));
-extern pte_t *FASTCALL(pte_alloc_map(struct mm_struct *mm, pmd_t *pmd, unsigned long address));
 extern int install_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, struct page *page, pgprot_t prot);
 extern int install_file_pte(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, unsigned long pgoff, pgprot_t prot);
 extern int __handle_mm_fault(struct mm_struct *mm,struct vm_area_struct *vma, unsigned long address, int write_access);
@@ -723,6 +727,7 @@ void install_arg_page(struct vm_area_struct *, struct page *, unsigned long);
 
 int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned long start,
 		int len, int write, int force, struct page **pages, struct vm_area_struct **vmas);
+void print_bad_pte(struct vm_area_struct *, pte_t, unsigned long);
 
 int __set_page_dirty_buffers(struct page *page);
 int __set_page_dirty_nobuffers(struct page *page);
@@ -759,38 +764,83 @@ struct shrinker;
 extern struct shrinker *set_shrinker(int, shrinker_t);
 extern void remove_shrinker(struct shrinker *shrinker);
 
-/*
- * On a two-level or three-level page table, this ends up being trivial. Thus
- * the inlining and the symmetry break with pte_alloc_map() that does all
- * of this out-of-line.
- */
+int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address);
+int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address);
+int __pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned long address);
+int __pte_alloc_kernel(pmd_t *pmd, unsigned long address);
+
 /*
  * The following ifdef needed to get the 4level-fixup.h header to work.
  * Remove it when 4level-fixup.h has been removed.
  */
-#ifdef CONFIG_MMU
-#ifndef __ARCH_HAS_4LEVEL_HACK 
+#if defined(CONFIG_MMU) && !defined(__ARCH_HAS_4LEVEL_HACK)
 static inline pud_t *pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
 {
-	if (pgd_none(*pgd))
-		return __pud_alloc(mm, pgd, address);
-	return pud_offset(pgd, address);
+	return (unlikely(pgd_none(*pgd)) && __pud_alloc(mm, pgd, address))?
+		NULL: pud_offset(pgd, address);
 }
 
 static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
 {
-	if (pud_none(*pud))
-		return __pmd_alloc(mm, pud, address);
-	return pmd_offset(pud, address);
+	return (unlikely(pud_none(*pud)) && __pmd_alloc(mm, pud, address))?
+		NULL: pmd_offset(pud, address);
 }
-#endif
-#endif /* CONFIG_MMU */
+#endif /* CONFIG_MMU && !__ARCH_HAS_4LEVEL_HACK */
+
+#if NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS
+/*
+ * We tuck a spinlock to guard each pagetable page into its struct page,
+ * at page->private, with BUILD_BUG_ON to make sure that this will not
+ * overflow into the next struct page (as it might with DEBUG_SPINLOCK).
+ * When freeing, reset page->mapping so free_pages_check won't complain.
+ */
+#define __pte_lockptr(page)	&((page)->u.ptl)
+#define pte_lock_init(_page)	do {					\
+	spin_lock_init(__pte_lockptr(_page));				\
+} while (0)
+#define pte_lock_deinit(page)	((page)->mapping = NULL)
+#define pte_lockptr(mm, pmd)	({(void)(mm); __pte_lockptr(pmd_page(*(pmd)));})
+#else
+/*
+ * We use mm->page_table_lock to guard all pagetable pages of the mm.
+ */
+#define pte_lock_init(page)	do {} while (0)
+#define pte_lock_deinit(page)	do {} while (0)
+#define pte_lockptr(mm, pmd)	({(void)(pmd); &(mm)->page_table_lock;})
+#endif /* NR_CPUS < CONFIG_SPLIT_PTLOCK_CPUS */
+
+#define pte_offset_map_lock(mm, pmd, address, ptlp)	\
+({							\
+	spinlock_t *__ptl = pte_lockptr(mm, pmd);	\
+	pte_t *__pte = pte_offset_map(pmd, address);	\
+	*(ptlp) = __ptl;				\
+	spin_lock(__ptl);				\
+	__pte;						\
+})
+
+#define pte_unmap_unlock(pte, ptl)	do {		\
+	spin_unlock(ptl);				\
+	pte_unmap(pte);					\
+} while (0)
+
+#define pte_alloc_map(mm, pmd, address)			\
+	((unlikely(!pmd_present(*(pmd))) && __pte_alloc(mm, pmd, address))? \
+		NULL: pte_offset_map(pmd, address))
+
+#define pte_alloc_map_lock(mm, pmd, address, ptlp)	\
+	((unlikely(!pmd_present(*(pmd))) && __pte_alloc(mm, pmd, address))? \
+		NULL: pte_offset_map_lock(mm, pmd, address, ptlp))
+
+#define pte_alloc_kernel(pmd, address)			\
+	((unlikely(!pmd_present(*(pmd))) && __pte_alloc_kernel(pmd, address))? \
+		NULL: pte_offset_kernel(pmd, address))
 
 extern void free_area_init(unsigned long * zones_size);
 extern void free_area_init_node(int nid, pg_data_t *pgdat,
 	unsigned long * zones_size, unsigned long zone_start_pfn, 
 	unsigned long *zholes_size);
 extern void memmap_init_zone(unsigned long, int, unsigned long, unsigned long);
+extern void setup_per_zone_pages_min(void);
 extern void mem_init(void);
 extern void show_mem(void);
 extern void si_meminfo(struct sysinfo * val);
@@ -834,6 +884,7 @@ extern int split_vma(struct mm_struct *,
 extern int insert_vm_struct(struct mm_struct *, struct vm_area_struct *);
 extern void __vma_link_rb(struct mm_struct *, struct vm_area_struct *,
 	struct rb_node **, struct rb_node *);
+extern void unlink_file_vma(struct vm_area_struct *);
 extern struct vm_area_struct *copy_vma(struct vm_area_struct **,
 	unsigned long addr, unsigned long len, pgoff_t pgoff);
 extern void exit_mmap(struct mm_struct *);
@@ -894,7 +945,8 @@ void handle_ra_miss(struct address_space *mapping,
 unsigned long max_sane_readahead(unsigned long nr);
 
 /* Do stack extension */
-extern int expand_stack(struct vm_area_struct * vma, unsigned long address);
+extern int expand_stack(struct vm_area_struct *vma, unsigned long address);
+extern int expand_upwards(struct vm_area_struct *vma, unsigned long address);
 
 /* Look up the first VMA which satisfies  addr < vm_end,  NULL if none. */
 extern struct vm_area_struct * find_vma(struct mm_struct * mm, unsigned long addr);
@@ -917,40 +969,28 @@ static inline unsigned long vma_pages(struct vm_area_struct *vma)
 	return (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
 }
 
-extern struct vm_area_struct *find_extend_vma(struct mm_struct *mm, unsigned long addr);
+struct vm_area_struct *find_extend_vma(struct mm_struct *, unsigned long addr);
+struct page *vmalloc_to_page(void *addr);
+unsigned long vmalloc_to_pfn(void *addr);
+int remap_pfn_range(struct vm_area_struct *, unsigned long addr,
+			unsigned long pfn, unsigned long size, pgprot_t);
 
-extern struct page * vmalloc_to_page(void *addr);
-extern unsigned long vmalloc_to_pfn(void *addr);
-extern struct page * follow_page(struct mm_struct *mm, unsigned long address,
-		int write);
-extern int check_user_page_readable(struct mm_struct *mm, unsigned long address);
-int remap_pfn_range(struct vm_area_struct *, unsigned long,
-		unsigned long, unsigned long, pgprot_t);
+struct page *follow_page(struct mm_struct *, unsigned long address,
+			unsigned int foll_flags);
+#define FOLL_WRITE	0x01	/* check pte is writable */
+#define FOLL_TOUCH	0x02	/* mark page accessed */
+#define FOLL_GET	0x04	/* do get_page on page */
+#define FOLL_ANON	0x08	/* give ZERO_PAGE if no pgtable */
 
 #ifdef CONFIG_PROC_FS
-void __vm_stat_account(struct mm_struct *, unsigned long, struct file *, long);
+void vm_stat_account(struct mm_struct *, unsigned long, struct file *, long);
 #else
-static inline void __vm_stat_account(struct mm_struct *mm,
+static inline void vm_stat_account(struct mm_struct *mm,
 			unsigned long flags, struct file *file, long pages)
 {
 }
 #endif /* CONFIG_PROC_FS */
 
-static inline void vm_stat_account(struct vm_area_struct *vma)
-{
-	__vm_stat_account(vma->vm_mm, vma->vm_flags, vma->vm_file,
-							vma_pages(vma));
-}
-
-static inline void vm_stat_unaccount(struct vm_area_struct *vma)
-{
-	__vm_stat_account(vma->vm_mm, vma->vm_flags, vma->vm_file,
-							-vma_pages(vma));
-}
-
-/* update per process rss and vm hiwater data */
-extern void update_mem_hiwater(struct task_struct *tsk);
-
 #ifndef CONFIG_DEBUG_PAGEALLOC
 static inline void
 kernel_map_pages(struct page *page, int numpages, int enable)
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 7519eb4191e..f5fa3082fd6 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -12,6 +12,7 @@
 #include <linux/threads.h>
 #include <linux/numa.h>
 #include <linux/init.h>
+#include <linux/seqlock.h>
 #include <asm/atomic.h>
 
 /* Free memory management - zoned buddy allocator.  */
@@ -137,6 +138,10 @@ struct zone {
 	 * free areas of different sizes
 	 */
 	spinlock_t		lock;
+#ifdef CONFIG_MEMORY_HOTPLUG
+	/* see spanned/present_pages for more description */
+	seqlock_t		span_seqlock;
+#endif
 	struct free_area	free_area[MAX_ORDER];
 
 
@@ -220,6 +225,16 @@ struct zone {
 	/* zone_start_pfn == zone_start_paddr >> PAGE_SHIFT */
 	unsigned long		zone_start_pfn;
 
+	/*
+	 * zone_start_pfn, spanned_pages and present_pages are all
+	 * protected by span_seqlock.  It is a seqlock because it has
+	 * to be read outside of zone->lock, and it is done in the main
+	 * allocator path.  But, it is written quite infrequently.
+	 *
+	 * The lock is declared along with zone->lock because it is
+	 * frequently read in proximity to zone->lock.  It's good to
+	 * give them a chance of being in the same cacheline.
+	 */
 	unsigned long		spanned_pages;	/* total size, including holes */
 	unsigned long		present_pages;	/* amount of memory (excluding holes) */
 
@@ -273,6 +288,16 @@ typedef struct pglist_data {
 	struct page *node_mem_map;
 #endif
 	struct bootmem_data *bdata;
+#ifdef CONFIG_MEMORY_HOTPLUG
+	/*
+	 * Must be held any time you expect node_start_pfn, node_present_pages
+	 * or node_spanned_pages stay constant.  Holding this will also
+	 * guarantee that any pfn_valid() stays that way.
+	 *
+	 * Nests above zone->lock and zone->size_seqlock.
+	 */
+	spinlock_t node_size_lock;
+#endif
 	unsigned long node_start_pfn;
 	unsigned long node_present_pages; /* total number of physical pages */
 	unsigned long node_spanned_pages; /* total size of physical page
@@ -293,6 +318,8 @@ typedef struct pglist_data {
 #endif
 #define nid_page_nr(nid, pagenr) 	pgdat_page_nr(NODE_DATA(nid),(pagenr))
 
+#include <linux/memory_hotplug.h>
+
 extern struct pglist_data *pgdat_list;
 
 void __get_zone_counts(unsigned long *active, unsigned long *inactive,
@@ -509,6 +536,7 @@ static inline struct mem_section *__nr_to_section(unsigned long nr)
 		return NULL;
 	return &mem_section[SECTION_NR_TO_ROOT(nr)][nr & SECTION_ROOT_MASK];
 }
+extern int __section_nr(struct mem_section* ms);
 
 /*
  * We use the lower bits of the mem_map pointer to store
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index e80fb7ee6ef..35b30e6c8cf 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -95,8 +95,8 @@ int try_to_unmap(struct page *);
 /*
  * Called from mm/filemap_xip.c to unmap empty zero page
  */
-pte_t *page_check_address(struct page *, struct mm_struct *, unsigned long);
-
+pte_t *page_check_address(struct page *, struct mm_struct *,
+				unsigned long, spinlock_t **);
 
 /*
  * Used by swapoff to help locate where page is expected in vma.
diff --git a/include/linux/rwsem-spinlock.h b/include/linux/rwsem-spinlock.h
index b52a2af25f1..f30f805080a 100644
--- a/include/linux/rwsem-spinlock.h
+++ b/include/linux/rwsem-spinlock.h
@@ -61,5 +61,10 @@ extern void FASTCALL(__up_read(struct rw_semaphore *sem));
 extern void FASTCALL(__up_write(struct rw_semaphore *sem));
 extern void FASTCALL(__downgrade_write(struct rw_semaphore *sem));
 
+static inline int rwsem_is_locked(struct rw_semaphore *sem)
+{
+	return (sem->activity != 0);
+}
+
 #endif /* __KERNEL__ */
 #endif /* _LINUX_RWSEM_SPINLOCK_H */
diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h
index 7f717e95ae3..66ff545552f 100644
--- a/include/linux/scatterlist.h
+++ b/include/linux/scatterlist.h
@@ -1,14 +1,23 @@
 #ifndef _LINUX_SCATTERLIST_H
 #define _LINUX_SCATTERLIST_H
 
-static inline void sg_init_one(struct scatterlist *sg,
-			       u8 *buf, unsigned int buflen)
-{
-	memset(sg, 0, sizeof(*sg));
+#include <asm/scatterlist.h>
+#include <linux/mm.h>
+#include <linux/string.h>
 
+static inline void sg_set_buf(struct scatterlist *sg, void *buf,
+			      unsigned int buflen)
+{
 	sg->page = virt_to_page(buf);
 	sg->offset = offset_in_page(buf);
 	sg->length = buflen;
 }
 
+static inline void sg_init_one(struct scatterlist *sg, void *buf,
+			       unsigned int buflen)
+{
+	memset(sg, 0, sizeof(*sg));
+	sg_set_buf(sg, buf, buflen);
+}
+
 #endif /* _LINUX_SCATTERLIST_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 27519df0f98..1c30bc308ef 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -249,6 +249,36 @@ arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr,
 extern void arch_unmap_area(struct mm_struct *, unsigned long);
 extern void arch_unmap_area_topdown(struct mm_struct *, unsigned long);
 
+#if NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS
+/*
+ * The mm counters are not protected by its page_table_lock,
+ * so must be incremented atomically.
+ */
+#ifdef ATOMIC64_INIT
+#define set_mm_counter(mm, member, value) atomic64_set(&(mm)->_##member, value)
+#define get_mm_counter(mm, member) ((unsigned long)atomic64_read(&(mm)->_##member))
+#define add_mm_counter(mm, member, value) atomic64_add(value, &(mm)->_##member)
+#define inc_mm_counter(mm, member) atomic64_inc(&(mm)->_##member)
+#define dec_mm_counter(mm, member) atomic64_dec(&(mm)->_##member)
+typedef atomic64_t mm_counter_t;
+#else /* !ATOMIC64_INIT */
+/*
+ * The counters wrap back to 0 at 2^32 * PAGE_SIZE,
+ * that is, at 16TB if using 4kB page size.
+ */
+#define set_mm_counter(mm, member, value) atomic_set(&(mm)->_##member, value)
+#define get_mm_counter(mm, member) ((unsigned long)atomic_read(&(mm)->_##member))
+#define add_mm_counter(mm, member, value) atomic_add(value, &(mm)->_##member)
+#define inc_mm_counter(mm, member) atomic_inc(&(mm)->_##member)
+#define dec_mm_counter(mm, member) atomic_dec(&(mm)->_##member)
+typedef atomic_t mm_counter_t;
+#endif /* !ATOMIC64_INIT */
+
+#else  /* NR_CPUS < CONFIG_SPLIT_PTLOCK_CPUS */
+/*
+ * The mm counters are protected by its page_table_lock,
+ * so can be incremented directly.
+ */
 #define set_mm_counter(mm, member, value) (mm)->_##member = (value)
 #define get_mm_counter(mm, member) ((mm)->_##member)
 #define add_mm_counter(mm, member, value) (mm)->_##member += (value)
@@ -256,6 +286,20 @@ extern void arch_unmap_area_topdown(struct mm_struct *, unsigned long);
 #define dec_mm_counter(mm, member) (mm)->_##member--
 typedef unsigned long mm_counter_t;
 
+#endif /* NR_CPUS < CONFIG_SPLIT_PTLOCK_CPUS */
+
+#define get_mm_rss(mm)					\
+	(get_mm_counter(mm, file_rss) + get_mm_counter(mm, anon_rss))
+#define update_hiwater_rss(mm)	do {			\
+	unsigned long _rss = get_mm_rss(mm);		\
+	if ((mm)->hiwater_rss < _rss)			\
+		(mm)->hiwater_rss = _rss;		\
+} while (0)
+#define update_hiwater_vm(mm)	do {			\
+	if ((mm)->hiwater_vm < (mm)->total_vm)		\
+		(mm)->hiwater_vm = (mm)->total_vm;	\
+} while (0)
+
 struct mm_struct {
 	struct vm_area_struct * mmap;		/* list of VMAs */
 	struct rb_root mm_rb;
@@ -279,15 +323,20 @@ struct mm_struct {
 						 * by mmlist_lock
 						 */
 
+	/* Special counters, in some configurations protected by the
+	 * page_table_lock, in other configurations by being atomic.
+	 */
+	mm_counter_t _file_rss;
+	mm_counter_t _anon_rss;
+
+	unsigned long hiwater_rss;	/* High-watermark of RSS usage */
+	unsigned long hiwater_vm;	/* High-water virtual memory usage */
+
+	unsigned long total_vm, locked_vm, shared_vm, exec_vm;
+	unsigned long stack_vm, reserved_vm, def_flags, nr_ptes;
 	unsigned long start_code, end_code, start_data, end_data;
 	unsigned long start_brk, brk, start_stack;
 	unsigned long arg_start, arg_end, env_start, env_end;
-	unsigned long total_vm, locked_vm, shared_vm;
-	unsigned long exec_vm, stack_vm, reserved_vm, def_flags, nr_ptes;
-
-	/* Special counters protected by the page_table_lock */
-	mm_counter_t _rss;
-	mm_counter_t _anon_rss;
 
 	unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */
 
@@ -308,11 +357,7 @@ struct mm_struct {
 	/* aio bits */
 	rwlock_t		ioctx_list_lock;
 	struct kioctx		*ioctx_list;
-
 	struct kioctx		default_kioctx;
-
-	unsigned long hiwater_rss;	/* High-water RSS usage */
-	unsigned long hiwater_vm;	/* High-water virtual memory usage */
 };
 
 struct sighand_struct {
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 3701a0673d2..1d5577b2b75 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -32,10 +32,14 @@ struct vm_struct {
  *	Highlevel APIs for driver use
  */
 extern void *vmalloc(unsigned long size);
+extern void *vmalloc_node(unsigned long size, int node);
 extern void *vmalloc_exec(unsigned long size);
 extern void *vmalloc_32(unsigned long size);
 extern void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot);
-extern void *__vmalloc_area(struct vm_struct *area, gfp_t gfp_mask, pgprot_t prot);
+extern void *__vmalloc_area(struct vm_struct *area, gfp_t gfp_mask,
+				pgprot_t prot);
+extern void *__vmalloc_node(unsigned long size, gfp_t gfp_mask,
+				pgprot_t prot, int node);
 extern void vfree(void *addr);
 
 extern void *vmap(struct page **pages, unsigned int count,
@@ -48,6 +52,8 @@ extern void vunmap(void *addr);
 extern struct vm_struct *get_vm_area(unsigned long size, unsigned long flags);
 extern struct vm_struct *__get_vm_area(unsigned long size, unsigned long flags,
 					unsigned long start, unsigned long end);
+extern struct vm_struct *get_vm_area_node(unsigned long size,
+					unsigned long flags, int node);
 extern struct vm_struct *remove_vm_area(void *addr);
 extern struct vm_struct *__remove_vm_area(void *addr);
 extern int map_vm_area(struct vm_struct *area, pgprot_t prot,