Merge branch 'mpi-master' into wip-k-fmlpwip-k-fmlp

Conflicts:
	litmus/sched_cedf.c

1 files changed, 269 insertions, 115 deletions

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 74949fbef8c6..9670f71d7be9 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -14,6 +14,7 @@
 #include <linux/mm_types.h>
 #include <linux/range.h>
 #include <linux/pfn.h>
+#include <linux/bit_spinlock.h>
 
 struct mempolicy;
 struct anon_vma;
@@ -82,6 +83,7 @@ extern unsigned int kobjsize(const void *objp);
 #define VM_GROWSUP      0x00000200
 #else
 #define VM_GROWSUP      0x00000000
+#define VM_NOHUGEPAGE   0x00000200      /* MADV_NOHUGEPAGE marked this vma */
 #endif
 #define VM_PFNMAP       0x00000400      /* Page-ranges managed without "struct page", just pure PFN */
 #define VM_DENYWRITE    0x00000800      /* ETXTBSY on write attempts.. */
@@ -101,7 +103,11 @@ extern unsigned int kobjsize(const void *objp);
 #define VM_NORESERVE    0x00200000      /* should the VM suppress accounting */
 #define VM_HUGETLB      0x00400000      /* Huge TLB Page VM */
 #define VM_NONLINEAR    0x00800000      /* Is non-linear (remap_file_pages) */
+#ifndef CONFIG_TRANSPARENT_HUGEPAGE
 #define VM_MAPPED_COPY  0x01000000      /* T if mapped copy of data (nommu mmap) */
+#else
+#define VM_HUGEPAGE     0x01000000      /* MADV_HUGEPAGE marked this vma */
+#endif
 #define VM_INSERTPAGE   0x02000000      /* The vma has had "vm_insert_page()" done on it */
 #define VM_ALWAYSDUMP   0x04000000      /* Always include in core dumps */
 
@@ -131,7 +137,8 @@ extern unsigned int kobjsize(const void *objp);
 #define VM_RandomReadHint(v)            ((v)->vm_flags & VM_RAND_READ)
 
 /*
- * special vmas that are non-mergable, non-mlock()able
+ * Special vmas that are non-mergable, non-mlock()able.
+ * Note: mm/huge_memory.c VM_NO_THP depends on this definition.
  */
 #define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_RESERVED | VM_PFNMAP)
 
@@ -144,6 +151,9 @@ extern pgprot_t protection_map[16];
 #define FAULT_FLAG_WRITE        0x01    /* Fault was a write access */
 #define FAULT_FLAG_NONLINEAR    0x02    /* Fault was via a nonlinear mapping */
 #define FAULT_FLAG_MKWRITE      0x04    /* Fault was mkwrite of existing pte */
+#define FAULT_FLAG_ALLOW_RETRY  0x08    /* Retry fault if blocking */
+#define FAULT_FLAG_RETRY_NOWAIT 0x10    /* Don't drop mmap_sem and wait when retrying */
+#define FAULT_FLAG_KILLABLE     0x20    /* The fault task is in SIGKILL killable region */
 
 /*
  * This interface is used by x86 PAT code to identify a pfn mapping that is
@@ -155,12 +165,12 @@ extern pgprot_t protection_map[16];
  */
 static inline int is_linear_pfn_mapping(struct vm_area_struct *vma)
 {
-        return (vma->vm_flags & VM_PFN_AT_MMAP);
+        return !!(vma->vm_flags & VM_PFN_AT_MMAP);
 }
 
 static inline int is_pfn_mapping(struct vm_area_struct *vma)
 {
-        return (vma->vm_flags & VM_PFNMAP);
+        return !!(vma->vm_flags & VM_PFNMAP);
 }
 
 /*
@@ -241,6 +251,7 @@ struct inode;
  * files which need it (119 of them)
  */
 #include <linux/page-flags.h>
+#include <linux/huge_mm.h>
 
 /*
  * Methods to modify the page usage count.
@@ -304,6 +315,39 @@ static inline int is_vmalloc_or_module_addr(const void *x)
 }
 #endif
 
+static inline void compound_lock(struct page *page)
+{
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+        bit_spin_lock(PG_compound_lock, &page->flags);
+#endif
+}
+
+static inline void compound_unlock(struct page *page)
+{
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+        bit_spin_unlock(PG_compound_lock, &page->flags);
+#endif
+}
+
+static inline unsigned long compound_lock_irqsave(struct page *page)
+{
+        unsigned long uninitialized_var(flags);
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+        local_irq_save(flags);
+        compound_lock(page);
+#endif
+        return flags;
+}
+
+static inline void compound_unlock_irqrestore(struct page *page,
+                                              unsigned long flags)
+{
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+        compound_unlock(page);
+        local_irq_restore(flags);
+#endif
+}
+
 static inline struct page *compound_head(struct page *page)
 {
         if (unlikely(PageTail(page)))
@@ -318,9 +362,29 @@ static inline int page_count(struct page *page)
 
 static inline void get_page(struct page *page)
 {
-        page = compound_head(page);
-        VM_BUG_ON(atomic_read(&page->_count) == 0);
+        /*
+         * Getting a normal page or the head of a compound page
+         * requires to already have an elevated page->_count. Only if
+         * we're getting a tail page, the elevated page->_count is
+         * required only in the head page, so for tail pages the
+         * bugcheck only verifies that the page->_count isn't
+         * negative.
+         */
+        VM_BUG_ON(atomic_read(&page->_count) < !PageTail(page));
         atomic_inc(&page->_count);
+        /*
+         * Getting a tail page will elevate both the head and tail
+         * page->_count(s).
+         */
+        if (unlikely(PageTail(page))) {
+                /*
+                 * This is safe only because
+                 * __split_huge_page_refcount can't run under
+                 * get_page().
+                 */
+                VM_BUG_ON(atomic_read(&page->first_page->_count) <= 0);
+                atomic_inc(&page->first_page->_count);
+        }
 }
 
 static inline struct page *virt_to_head_page(const void *x)
@@ -338,6 +402,34 @@ static inline void init_page_count(struct page *page)
         atomic_set(&page->_count, 1);
 }
 
+/*
+ * PageBuddy() indicate that the page is free and in the buddy system
+ * (see mm/page_alloc.c).
+ *
+ * PAGE_BUDDY_MAPCOUNT_VALUE must be <= -2 but better not too close to
+ * -2 so that an underflow of the page_mapcount() won't be mistaken
+ * for a genuine PAGE_BUDDY_MAPCOUNT_VALUE. -128 can be created very
+ * efficiently by most CPU architectures.
+ */
+#define PAGE_BUDDY_MAPCOUNT_VALUE (-128)
+
+static inline int PageBuddy(struct page *page)
+{
+        return atomic_read(&page->_mapcount) == PAGE_BUDDY_MAPCOUNT_VALUE;
+}
+
+static inline void __SetPageBuddy(struct page *page)
+{
+        VM_BUG_ON(atomic_read(&page->_mapcount) != -1);
+        atomic_set(&page->_mapcount, PAGE_BUDDY_MAPCOUNT_VALUE);
+}
+
+static inline void __ClearPageBuddy(struct page *page)
+{
+        VM_BUG_ON(!PageBuddy(page));
+        atomic_set(&page->_mapcount, -1);
+}
+
 void put_page(struct page *page);
 void put_pages_list(struct list_head *pages);
 
@@ -369,11 +461,40 @@ static inline int compound_order(struct page *page)
         return (unsigned long)page[1].lru.prev;
 }
 
+static inline int compound_trans_order(struct page *page)
+{
+        int order;
+        unsigned long flags;
+
+        if (!PageHead(page))
+                return 0;
+
+        flags = compound_lock_irqsave(page);
+        order = compound_order(page);
+        compound_unlock_irqrestore(page, flags);
+        return order;
+}
+
 static inline void set_compound_order(struct page *page, unsigned long order)
 {
         page[1].lru.prev = (void *)order;
 }
 
+#ifdef CONFIG_MMU
+/*
+ * Do pte_mkwrite, but only if the vma says VM_WRITE.  We do this when
+ * servicing faults for write access.  In the normal case, do always want
+ * pte_mkwrite.  But get_user_pages can cause write faults for mappings
+ * that do not have writing enabled, when used by access_process_vm.
+ */
+static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
+{
+        if (likely(vma->vm_flags & VM_WRITE))
+                pte = pte_mkwrite(pte);
+        return pte;
+}
+#endif
+
 /*
  * Multiple processes may "see" the same page. E.g. for untouched
  * mappings of /dev/null, all processes see the same page full of
@@ -484,12 +605,8 @@ static inline void set_compound_order(struct page *page, unsigned long order)
 #define NODE_NOT_IN_PAGE_FLAGS
 #endif
 
-#ifndef PFN_SECTION_SHIFT
-#define PFN_SECTION_SHIFT 0
-#endif
-
 /*
- * Define the bit shifts to access each section.  For non-existant
+ * Define the bit shifts to access each section.  For non-existent
  * sections we define the shift as 0; that plus a 0 mask ensures
  * the compiler will optimise away reference to them.
  */
@@ -497,8 +614,8 @@ static inline void set_compound_order(struct page *page, unsigned long order)
 #define NODES_PGSHIFT           (NODES_PGOFF * (NODES_WIDTH != 0))
 #define ZONES_PGSHIFT           (ZONES_PGOFF * (ZONES_WIDTH != 0))
 
-/* NODE:ZONE or SECTION:ZONE is used to ID a zone for the buddy allcator */
-#ifdef NODE_NOT_IN_PAGEFLAGS
+/* NODE:ZONE or SECTION:ZONE is used to ID a zone for the buddy allocator */
+#ifdef NODE_NOT_IN_PAGE_FLAGS
 #define ZONEID_SHIFT            (SECTIONS_SHIFT + ZONES_SHIFT)
 #define ZONEID_PGOFF            ((SECTIONS_PGOFF < ZONES_PGOFF)? \
                                                 SECTIONS_PGOFF : ZONES_PGOFF)
@@ -561,6 +678,12 @@ static inline struct zone *page_zone(struct page *page)
 }
 
 #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
+static inline void set_page_section(struct page *page, unsigned long section)
+{
+        page->flags &= ~(SECTIONS_MASK << SECTIONS_PGSHIFT);
+        page->flags |= (section & SECTIONS_MASK) << SECTIONS_PGSHIFT;
+}
+
 static inline unsigned long page_to_section(struct page *page)
 {
         return (page->flags >> SECTIONS_PGSHIFT) & SECTIONS_MASK;
@@ -579,18 +702,14 @@ static inline void set_page_node(struct page *page, unsigned long node)
         page->flags |= (node & NODES_MASK) << NODES_PGSHIFT;
 }
 
-static inline void set_page_section(struct page *page, unsigned long section)
-{
-        page->flags &= ~(SECTIONS_MASK << SECTIONS_PGSHIFT);
-        page->flags |= (section & SECTIONS_MASK) << SECTIONS_PGSHIFT;
-}
-
 static inline void set_page_links(struct page *page, enum zone_type zone,
         unsigned long node, unsigned long pfn)
 {
         set_page_zone(page, zone);
         set_page_node(page, node);
+#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
         set_page_section(page, pfn_to_section_nr(pfn));
+#endif
 }
 
 /*
@@ -656,7 +775,7 @@ static inline struct address_space *page_mapping(struct page *page)
         VM_BUG_ON(PageSlab(page));
         if (unlikely(PageSwapCache(page)))
                 mapping = &swapper_space;
-        else if (unlikely((unsigned long)mapping & PAGE_MAPPING_ANON))
+        else if ((unsigned long)mapping & PAGE_MAPPING_ANON)
                 mapping = NULL;
         return mapping;
 }
@@ -718,12 +837,21 @@ static inline int page_mapped(struct page *page)
 #define VM_FAULT_SIGBUS 0x0002
 #define VM_FAULT_MAJOR  0x0004
 #define VM_FAULT_WRITE  0x0008  /* Special case for get_user_pages */
-#define VM_FAULT_HWPOISON 0x0010        /* Hit poisoned page */
+#define VM_FAULT_HWPOISON 0x0010        /* Hit poisoned small page */
+#define VM_FAULT_HWPOISON_LARGE 0x0020  /* Hit poisoned large page. Index encoded in upper bits */
 
 #define VM_FAULT_NOPAGE 0x0100  /* ->fault installed the pte, not return page */
 #define VM_FAULT_LOCKED 0x0200  /* ->fault locked the returned page */
+#define VM_FAULT_RETRY  0x0400  /* ->fault blocked, must retry */
+
+#define VM_FAULT_HWPOISON_LARGE_MASK 0xf000 /* encodes hpage index for large hwpoison */
 
-#define VM_FAULT_ERROR  (VM_FAULT_OOM | VM_FAULT_SIGBUS | VM_FAULT_HWPOISON)
+#define VM_FAULT_ERROR  (VM_FAULT_OOM | VM_FAULT_SIGBUS | VM_FAULT_HWPOISON | \
+                         VM_FAULT_HWPOISON_LARGE)
+
+/* Encode hstate index for a hwpoisoned large page */
+#define VM_FAULT_SET_HINDEX(x) ((x) << 12)
+#define VM_FAULT_GET_HINDEX(x) (((x) >> 12) & 0xf)
 
 /*
  * Can be called by the pagefault handler when it gets a VM_FAULT_OOM.
@@ -732,20 +860,19 @@ extern void pagefault_out_of_memory(void);
 
 #define offset_in_page(p)       ((unsigned long)(p) & ~PAGE_MASK)
 
-extern void show_free_areas(void);
+/*
+ * Flags passed to show_mem() and show_free_areas() to suppress output in
+ * various contexts.
+ */
+#define SHOW_MEM_FILTER_NODES   (0x0001u)       /* filter disallowed nodes */
+
+extern void show_free_areas(unsigned int flags);
+extern bool skip_free_areas_node(unsigned int flags, int nid);
 
 int shmem_lock(struct file *file, int lock, struct user_struct *user);
 struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags);
 int shmem_zero_setup(struct vm_area_struct *);
 
-#ifndef CONFIG_MMU
-extern unsigned long shmem_get_unmapped_area(struct file *file,
-                                             unsigned long addr,
-                                             unsigned long len,
-                                             unsigned long pgoff,
-                                             unsigned long flags);
-#endif
-
 extern int can_do_mlock(void);
 extern int user_shm_lock(size_t, struct user_struct *);
 extern void user_shm_unlock(size_t, struct user_struct *);
@@ -758,8 +885,6 @@ struct zap_details {
         struct address_space *check_mapping;    /* Check page->mapping if set */
         pgoff_t first_index;                    /* Lowest page->index to unmap */
         pgoff_t last_index;                     /* Highest page->index to unmap */
-        spinlock_t *i_mmap_lock;                /* For unmap_mapping_range: */
-        unsigned long truncate_count;           /* Compare vm_truncate_count */
 };
 
 struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
@@ -769,7 +894,7 @@ int zap_vma_ptes(struct vm_area_struct *vma, unsigned long address,
                 unsigned long size);
 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,
+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 *);
@@ -779,6 +904,9 @@ unsigned long unmap_vmas(struct mmu_gather **tlb,
  * @pgd_entry: if set, called for each non-empty PGD (top-level) entry
  * @pud_entry: if set, called for each non-empty PUD (2nd-level) entry
  * @pmd_entry: if set, called for each non-empty PMD (3rd-level) entry
+ *             this handler is required to be able to handle
+ *             pmd_trans_huge() pmds.  They may simply choose to
+ *             split_huge_page() instead of handling it explicitly.
  * @pte_entry: if set, called for each non-empty PTE (4th-level) entry
  * @pte_hole: if set, called for each hole at all levels
  * @hugetlb_entry: if set, called for each hugetlb entry
@@ -844,7 +972,13 @@ static inline int handle_mm_fault(struct mm_struct *mm,
 
 extern int make_pages_present(unsigned long addr, unsigned long end);
 extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, int write);
+extern int access_remote_vm(struct mm_struct *mm, unsigned long addr,
+                void *buf, int len, int write);
 
+int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
+                     unsigned long start, int len, unsigned int foll_flags,
+                     struct page **pages, struct vm_area_struct **vmas,
+                     int *nonblocking);
 int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
                         unsigned long start, int nr_pages, int write, int force,
                         struct page **pages, struct vm_area_struct **vmas);
@@ -860,16 +994,39 @@ int __set_page_dirty_no_writeback(struct page *page);
 int redirty_page_for_writepage(struct writeback_control *wbc,
                                 struct page *page);
 void account_page_dirtied(struct page *page, struct address_space *mapping);
+void account_page_writeback(struct page *page);
 int set_page_dirty(struct page *page);
 int set_page_dirty_lock(struct page *page);
 int clear_page_dirty_for_io(struct page *page);
 
 /* Is the vma a continuation of the stack vma above it? */
-static inline int vma_stack_continue(struct vm_area_struct *vma, unsigned long addr)
+static inline int vma_growsdown(struct vm_area_struct *vma, unsigned long addr)
 {
         return vma && (vma->vm_end == addr) && (vma->vm_flags & VM_GROWSDOWN);
 }
 
+static inline int stack_guard_page_start(struct vm_area_struct *vma,
+                                             unsigned long addr)
+{
+        return (vma->vm_flags & VM_GROWSDOWN) &&
+                (vma->vm_start == addr) &&
+                !vma_growsdown(vma->vm_prev, addr);
+}
+
+/* Is the vma a continuation of the stack vma below it? */
+static inline int vma_growsup(struct vm_area_struct *vma, unsigned long addr)
+{
+        return vma && (vma->vm_start == addr) && (vma->vm_flags & VM_GROWSUP);
+}
+
+static inline int stack_guard_page_end(struct vm_area_struct *vma,
+                                           unsigned long addr)
+{
+        return (vma->vm_flags & VM_GROWSUP) &&
+                (vma->vm_end == addr) &&
+                !vma_growsup(vma->vm_next, addr);
+}
+
 extern unsigned long move_page_tables(struct vm_area_struct *vma,
                 unsigned long old_addr, struct vm_area_struct *new_vma,
                 unsigned long new_addr, unsigned long len);
@@ -888,65 +1045,35 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
 /*
  * per-process(per-mm_struct) statistics.
  */
-#if defined(SPLIT_RSS_COUNTING)
-/*
- * The mm counters are not protected by its page_table_lock,
- * so must be incremented atomically.
- */
 static inline void set_mm_counter(struct mm_struct *mm, int member, long value)
 {
         atomic_long_set(&mm->rss_stat.count[member], value);
 }
 
+#if defined(SPLIT_RSS_COUNTING)
 unsigned long get_mm_counter(struct mm_struct *mm, int member);
-
-static inline void add_mm_counter(struct mm_struct *mm, int member, long value)
-{
-        atomic_long_add(value, &mm->rss_stat.count[member]);
-}
-
-static inline void inc_mm_counter(struct mm_struct *mm, int member)
-{
-        atomic_long_inc(&mm->rss_stat.count[member]);
-}
-
-static inline void dec_mm_counter(struct mm_struct *mm, int member)
-{
-        atomic_long_dec(&mm->rss_stat.count[member]);
-}
-
-#else  /* !USE_SPLIT_PTLOCKS */
-/*
- * The mm counters are protected by its page_table_lock,
- * so can be incremented directly.
- */
-static inline void set_mm_counter(struct mm_struct *mm, int member, long value)
-{
-        mm->rss_stat.count[member] = value;
-}
-
+#else
 static inline unsigned long get_mm_counter(struct mm_struct *mm, int member)
 {
-        return mm->rss_stat.count[member];
+        return atomic_long_read(&mm->rss_stat.count[member]);
 }
+#endif
 
 static inline void add_mm_counter(struct mm_struct *mm, int member, long value)
 {
-        mm->rss_stat.count[member] += value;
+        atomic_long_add(value, &mm->rss_stat.count[member]);
 }
 
 static inline void inc_mm_counter(struct mm_struct *mm, int member)
 {
-        mm->rss_stat.count[member]++;
+        atomic_long_inc(&mm->rss_stat.count[member]);
 }
 
 static inline void dec_mm_counter(struct mm_struct *mm, int member)
 {
-        mm->rss_stat.count[member]--;
+        atomic_long_dec(&mm->rss_stat.count[member]);
 }
 
-#endif /* !USE_SPLIT_PTLOCKS */
-
 static inline unsigned long get_mm_rss(struct mm_struct *mm)
 {
         return get_mm_counter(mm, MM_FILEPAGES) +
@@ -995,13 +1122,24 @@ static inline void sync_mm_rss(struct task_struct *task, struct mm_struct *mm)
 #endif
 
 /*
+ * This struct is used to pass information from page reclaim to the shrinkers.
+ * We consolidate the values for easier extention later.
+ */
+struct shrink_control {
+        gfp_t gfp_mask;
+
+        /* How many slab objects shrinker() should scan and try to reclaim */
+        unsigned long nr_to_scan;
+};
+
+/*
  * A callback you can register to apply pressure to ageable caches.
  *
- * 'shrink' is passed a count 'nr_to_scan' and a 'gfpmask'.  It should
- * look through the least-recently-used 'nr_to_scan' entries and
- * attempt to free them up.  It should return the number of objects
- * which remain in the cache.  If it returns -1, it means it cannot do
- * any scanning at this time (eg. there is a risk of deadlock).
+ * 'sc' is passed shrink_control which includes a count 'nr_to_scan'
+ * and a 'gfpmask'.  It should look through the least-recently-used
+ * 'nr_to_scan' entries and attempt to free them up.  It should return
+ * the number of objects which remain in the cache.  If it returns -1, it means
+ * it cannot do any scanning at this time (eg. there is a risk of deadlock).
  *
  * The 'gfpmask' refers to the allocation we are currently trying to
  * fulfil.
@@ -1010,7 +1148,7 @@ static inline void sync_mm_rss(struct task_struct *task, struct mm_struct *mm)
  * querying the cache size, so a fastpath for that case is appropriate.
  */
 struct shrinker {
-        int (*shrink)(struct shrinker *, int nr_to_scan, gfp_t gfp_mask);
+        int (*shrink)(struct shrinker *, struct shrink_control *sc);
         int seeks;      /* seeks to recreate an obj */
 
         /* These are for internal use */
@@ -1023,7 +1161,15 @@ extern void unregister_shrinker(struct shrinker *);
 
 int vma_wants_writenotify(struct vm_area_struct *vma);
 
-extern pte_t *get_locked_pte(struct mm_struct *mm, unsigned long addr, spinlock_t **ptl);
+extern pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr,
+                               spinlock_t **ptl);
+static inline pte_t *get_locked_pte(struct mm_struct *mm, unsigned long addr,
+                                    spinlock_t **ptl)
+{
+        pte_t *ptep;
+        __cond_lock(*ptl, ptep = __get_locked_pte(mm, addr, ptl));
+        return ptep;
+}
 
 #ifdef __PAGETABLE_PUD_FOLDED
 static inline int __pud_alloc(struct mm_struct *mm, pgd_t *pgd,
@@ -1045,7 +1191,8 @@ static inline int __pmd_alloc(struct mm_struct *mm, pud_t *pud,
 int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address);
 #endif
 
-int __pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned long address);
+int __pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
+                pmd_t *pmd, unsigned long address);
 int __pte_alloc_kernel(pmd_t *pmd, unsigned long address);
 
 /*
@@ -1114,16 +1261,18 @@ static inline void pgtable_page_dtor(struct page *page)
         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(mm, vma, pmd, address)                            \
+        ((unlikely(pmd_none(*(pmd))) && __pte_alloc(mm, vma,    \
+                                                        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))? \
+        ((unlikely(pmd_none(*(pmd))) && __pte_alloc(mm, NULL,   \
+                                                        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))? \
+        ((unlikely(pmd_none(*(pmd))) && __pte_alloc_kernel(pmd, address))? \
                 NULL: pte_offset_kernel(pmd, address))
 
 extern void free_area_init(unsigned long * zones_size);
@@ -1175,8 +1324,8 @@ extern void free_bootmem_with_active_regions(int nid,
                                                 unsigned long max_low_pfn);
 int add_from_early_node_map(struct range *range, int az,
                                    int nr_range, int nid);
-void *__alloc_memory_core_early(int nodeid, u64 size, u64 align,
-                                 u64 goal, u64 limit);
+u64 __init find_memory_core_early(int nid, u64 size, u64 align,
+                                        u64 goal, u64 limit);
 typedef int (*work_fn_t)(unsigned long, unsigned long, void *);
 extern void work_with_active_regions(int nid, work_fn_t work_fn, void *data);
 extern void sparse_memory_present_with_active_regions(int nid);
@@ -1201,14 +1350,16 @@ extern void set_dma_reserve(unsigned long new_dma_reserve);
 extern void memmap_init_zone(unsigned long, int, unsigned long,
                                 unsigned long, enum memmap_context);
 extern void setup_per_zone_wmarks(void);
-extern void calculate_zone_inactive_ratio(struct zone *zone);
+extern int __meminit init_per_zone_wmark_min(void);
 extern void mem_init(void);
 extern void __init mmap_init(void);
-extern void show_mem(void);
+extern void show_mem(unsigned int flags);
 extern void si_meminfo(struct sysinfo * val);
 extern void si_meminfo_node(struct sysinfo *val, int nid);
 extern int after_bootmem;
 
+extern void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...);
+
 extern void setup_per_cpu_pageset(void);
 
 extern void zone_pcp_update(struct zone *zone);
@@ -1257,17 +1408,11 @@ extern void exit_mmap(struct mm_struct *);
 extern int mm_take_all_locks(struct mm_struct *mm);
 extern void mm_drop_all_locks(struct mm_struct *mm);
 
-#ifdef CONFIG_PROC_FS
 /* From fs/proc/base.c. callers must _not_ hold the mm's exe_file_lock */
 extern void added_exe_file_vma(struct mm_struct *mm);
 extern void removed_exe_file_vma(struct mm_struct *mm);
-#else
-static inline void added_exe_file_vma(struct mm_struct *mm)
-{}
-
-static inline void removed_exe_file_vma(struct mm_struct *mm)
-{}
-#endif /* CONFIG_PROC_FS */
+extern void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file);
+extern struct file *get_mm_exe_file(struct mm_struct *mm);
 
 extern int may_expand_vm(struct mm_struct *mm, unsigned long npages);
 extern int install_special_mapping(struct mm_struct *mm,
@@ -1281,7 +1426,7 @@ extern unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
         unsigned long flag, unsigned long pgoff);
 extern unsigned long mmap_region(struct file *file, unsigned long addr,
         unsigned long len, unsigned long flags,
-        unsigned int vm_flags, unsigned long pgoff);
+        vm_flags_t vm_flags, unsigned long pgoff);
 
 static inline unsigned long do_mmap(struct file *file, unsigned long addr,
         unsigned long len, unsigned long prot,
@@ -1338,15 +1483,17 @@ unsigned long ra_submit(struct file_ra_state *ra,
                         struct address_space *mapping,
                         struct file *filp);
 
-/* Do stack extension */
+/* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */
 extern int expand_stack(struct vm_area_struct *vma, unsigned long address);
+
+/* CONFIG_STACK_GROWSUP still needs to to grow downwards at some places */
+extern int expand_downwards(struct vm_area_struct *vma,
+                unsigned long address);
 #if VM_GROWSUP
 extern int expand_upwards(struct vm_area_struct *vma, unsigned long address);
 #else
   #define expand_upwards(vma, address) do { } while (0)
 #endif
-extern int expand_stack_downwards(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);
@@ -1394,6 +1541,11 @@ struct page *follow_page(struct vm_area_struct *, unsigned long address,
 #define FOLL_GET        0x04    /* do get_page on page */
 #define FOLL_DUMP       0x08    /* give error on hole if it would be zero */
 #define FOLL_FORCE      0x10    /* get_user_pages read/write w/o permission */
+#define FOLL_NOWAIT     0x20    /* if a disk transfer is needed, start the IO
+                                 * and return without waiting upon it */
+#define FOLL_MLOCK      0x40    /* mark page as mlocked */
+#define FOLL_SPLIT      0x80    /* don't return transhuge pages, split them */
+#define FOLL_HWPOISON   0x100   /* check page is hwpoisoned */
 
 typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr,
                         void *data);
@@ -1432,19 +1584,20 @@ static inline bool kernel_page_present(struct page *page) { return true; }
 #endif /* CONFIG_HIBERNATION */
 #endif
 
-extern struct vm_area_struct *get_gate_vma(struct task_struct *tsk);
+extern struct vm_area_struct *get_gate_vma(struct mm_struct *mm);
 #ifdef  __HAVE_ARCH_GATE_AREA
-int in_gate_area_no_task(unsigned long addr);
-int in_gate_area(struct task_struct *task, unsigned long addr);
+int in_gate_area_no_mm(unsigned long addr);
+int in_gate_area(struct mm_struct *mm, unsigned long addr);
 #else
-int in_gate_area_no_task(unsigned long addr);
-#define in_gate_area(task, addr) ({(void)task; in_gate_area_no_task(addr);})
+int in_gate_area_no_mm(unsigned long addr);
+#define in_gate_area(mm, addr) ({(void)mm; in_gate_area_no_mm(addr);})
 #endif  /* __HAVE_ARCH_GATE_AREA */
 
 int drop_caches_sysctl_handler(struct ctl_table *, int,
                                         void __user *, size_t *, loff_t *);
-unsigned long shrink_slab(unsigned long scanned, gfp_t gfp_mask,
-                        unsigned long lru_pages);
+unsigned long shrink_slab(struct shrink_control *shrink,
+                          unsigned long nr_pages_scanned,
+                          unsigned long lru_pages);
 
 #ifndef CONFIG_MMU
 #define randomize_va_space 0
@@ -1486,16 +1639,17 @@ extern int sysctl_memory_failure_recovery;
 extern void shake_page(struct page *p, int access);
 extern atomic_long_t mce_bad_pages;
 extern int soft_offline_page(struct page *page, int flags);
-#ifdef CONFIG_MEMORY_FAILURE
-int is_hwpoison_address(unsigned long addr);
-#else
-static inline int is_hwpoison_address(unsigned long addr)
-{
-        return 0;
-}
-#endif
 
 extern void dump_page(struct page *page);
 
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS)
+extern void clear_huge_page(struct page *page,
+                            unsigned long addr,
+                            unsigned int pages_per_huge_page);
+extern void copy_user_huge_page(struct page *dst, struct page *src,
+                                unsigned long addr, struct vm_area_struct *vma,
+                                unsigned int pages_per_huge_page);
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */
+
 #endif /* __KERNEL__ */
 #endif /* _LINUX_MM_H */