12 files changed, 139 insertions, 37 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 421aee99b84a..6058b53dcb89 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -354,11 +354,26 @@ static int vma_has_reserves(struct vm_area_struct *vma)
         return 0;
 }
 
+static void clear_gigantic_page(struct page *page,
+                        unsigned long addr, unsigned long sz)
+{
+        int i;
+        struct page *p = page;
+
+        might_sleep();
+        for (i = 0; i < sz/PAGE_SIZE; i++, p = mem_map_next(p, page, i)) {
+                cond_resched();
+                clear_user_highpage(p, addr + i * PAGE_SIZE);
+        }
+}
 static void clear_huge_page(struct page *page,
                         unsigned long addr, unsigned long sz)
 {
         int i;
 
+        if (unlikely(sz > MAX_ORDER_NR_PAGES))
+                return clear_gigantic_page(page, addr, sz);
+
         might_sleep();
         for (i = 0; i < sz/PAGE_SIZE; i++) {
                 cond_resched();
@@ -366,12 +381,32 @@ static void clear_huge_page(struct page *page,
         }
 }
 
+static void copy_gigantic_page(struct page *dst, struct page *src,
+                           unsigned long addr, struct vm_area_struct *vma)
+{
+        int i;
+        struct hstate *h = hstate_vma(vma);
+        struct page *dst_base = dst;
+        struct page *src_base = src;
+        might_sleep();
+        for (i = 0; i < pages_per_huge_page(h); ) {
+                cond_resched();
+                copy_user_highpage(dst, src, addr + i*PAGE_SIZE, vma);
+
+                i++;
+                dst = mem_map_next(dst, dst_base, i);
+                src = mem_map_next(src, src_base, i);
+        }
+}
 static void copy_huge_page(struct page *dst, struct page *src,
                            unsigned long addr, struct vm_area_struct *vma)
 {
         int i;
         struct hstate *h = hstate_vma(vma);
 
+        if (unlikely(pages_per_huge_page(h) > MAX_ORDER_NR_PAGES))
+                return copy_gigantic_page(dst, src, addr, vma);
+
         might_sleep();
         for (i = 0; i < pages_per_huge_page(h); i++) {
                 cond_resched();
@@ -456,6 +491,8 @@ static void update_and_free_page(struct hstate *h, struct page *page)
 {
         int i;
 
+        VM_BUG_ON(h->order >= MAX_ORDER);
+
         h->nr_huge_pages--;
         h->nr_huge_pages_node[page_to_nid(page)]--;
         for (i = 0; i < pages_per_huge_page(h); i++) {
@@ -970,6 +1007,14 @@ found:
         return 1;
 }
 
+static void prep_compound_huge_page(struct page *page, int order)
+{
+        if (unlikely(order > (MAX_ORDER - 1)))
+                prep_compound_gigantic_page(page, order);
+        else
+                prep_compound_page(page, order);
+}
+
 /* Put bootmem huge pages into the standard lists after mem_map is up */
 static void __init gather_bootmem_prealloc(void)
 {
@@ -980,7 +1025,7 @@ static void __init gather_bootmem_prealloc(void)
                 struct hstate *h = m->hstate;
                 __ClearPageReserved(page);
                 WARN_ON(page_count(page) != 1);
-                prep_compound_page(page, h->order);
+                prep_compound_huge_page(page, h->order);
                 prep_new_huge_page(h, page, page_to_nid(page));
         }
 }
@@ -1751,6 +1796,7 @@ void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
 static int unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma,
                                 struct page *page, unsigned long address)
 {
+        struct hstate *h = hstate_vma(vma);
         struct vm_area_struct *iter_vma;
         struct address_space *mapping;
         struct prio_tree_iter iter;
@@ -1760,7 +1806,7 @@ static int unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma,
          * vm_pgoff is in PAGE_SIZE units, hence the different calculation
          * from page cache lookup which is in HPAGE_SIZE units.
          */
-        address = address & huge_page_mask(hstate_vma(vma));
+        address = address & huge_page_mask(h);
         pgoff = ((address - vma->vm_start) >> PAGE_SHIFT)
                 + (vma->vm_pgoff >> PAGE_SHIFT);
         mapping = (struct address_space *)page_private(page);
@@ -1779,7 +1825,7 @@ static int unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma,
                  */
                 if (!is_vma_resv_set(iter_vma, HPAGE_RESV_OWNER))
                         unmap_hugepage_range(iter_vma,
-                                address, address + HPAGE_SIZE,
+                                address, address + huge_page_size(h),
                                 page);
         }
 
@@ -2130,7 +2176,7 @@ same_page:
                         if (zeropage_ok)
                                 pages[i] = ZERO_PAGE(0);
                         else
-                                pages[i] = page + pfn_offset;
+                                pages[i] = mem_map_offset(page, pfn_offset);
                         get_page(pages[i]);
                 }
 
diff --git a/mm/internal.h b/mm/internal.h
index e4e728bdf324..13333bc2eb68 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -17,6 +17,7 @@ void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
                 unsigned long floor, unsigned long ceiling);
 
 extern void prep_compound_page(struct page *page, unsigned long order);
+extern void prep_compound_gigantic_page(struct page *page, unsigned long order);
 
 static inline void set_page_count(struct page *page, int v)
 {
@@ -176,6 +177,34 @@ static inline void free_page_mlock(struct page *page) { }
 #endif /* CONFIG_UNEVICTABLE_LRU */
 
 /*
+ * Return the mem_map entry representing the 'offset' subpage within
+ * the maximally aligned gigantic page 'base'.  Handle any discontiguity
+ * in the mem_map at MAX_ORDER_NR_PAGES boundaries.
+ */
+static inline struct page *mem_map_offset(struct page *base, int offset)
+{
+        if (unlikely(offset >= MAX_ORDER_NR_PAGES))
+                return pfn_to_page(page_to_pfn(base) + offset);
+        return base + offset;
+}
+
+/*
+ * Iterator over all subpages withing the maximally aligned gigantic
+ * page 'base'.  Handle any discontiguity in the mem_map.
+ */
+static inline struct page *mem_map_next(struct page *iter,
+                                                struct page *base, int offset)
+{
+        if (unlikely((offset & (MAX_ORDER_NR_PAGES - 1)) == 0)) {
+                unsigned long pfn = page_to_pfn(base) + offset;
+                if (!pfn_valid(pfn))
+                        return NULL;
+                return pfn_to_page(pfn);
+        }
+        return iter + 1;
+}
+
+/*
  * FLATMEM and DISCONTIGMEM configurations use alloc_bootmem_node,
  * so all functions starting at paging_init should be marked __init
  * in those cases. SPARSEMEM, however, allows for memory hotplug,
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 7555219c535b..e412ffa8e52e 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -489,12 +489,6 @@ check_range(struct mm_struct *mm, unsigned long start, unsigned long end,
         int err;
         struct vm_area_struct *first, *vma, *prev;
 
-        if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {
-
-                err = migrate_prep();
-                if (err)
-                        return ERR_PTR(err);
-        }
 
         first = find_vma(mm, start);
         if (!first)
@@ -809,9 +803,13 @@ int do_migrate_pages(struct mm_struct *mm,
         const nodemask_t *from_nodes, const nodemask_t *to_nodes, int flags)
 {
         int busy = 0;
-        int err = 0;
+        int err;
         nodemask_t tmp;
 
+        err = migrate_prep();
+        if (err)
+                return err;
+
         down_read(&mm->mmap_sem);
 
         err = migrate_vmas(mm, from_nodes, to_nodes, flags);
@@ -974,6 +972,12 @@ static long do_mbind(unsigned long start, unsigned long len,
                  start, start + len, mode, mode_flags,
                  nmask ? nodes_addr(*nmask)[0] : -1);
 
+        if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {
+
+                err = migrate_prep();
+                if (err)
+                        return err;
+        }
         down_write(&mm->mmap_sem);
         vma = check_range(mm, start, end, nmask,
                           flags | MPOL_MF_INVERT, &pagelist);
diff --git a/mm/migrate.c b/mm/migrate.c
index 142284229ce2..9dd10da1cc23 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -841,12 +841,12 @@ static int do_move_page_to_node_array(struct mm_struct *mm,
         struct page_to_node *pp;
         LIST_HEAD(pagelist);
 
+        migrate_prep();
         down_read(&mm->mmap_sem);
 
         /*
          * Build a list of pages to migrate
          */
-        migrate_prep();
         for (pp = pm; pp->node != MAX_NUMNODES; pp++) {
                 struct vm_area_struct *vma;
                 struct page *page;
diff --git a/mm/mlock.c b/mm/mlock.c
index 008ea70b7afa..a6da2aee940a 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -66,14 +66,10 @@ void __clear_page_mlock(struct page *page)
                 putback_lru_page(page);
         } else {
                 /*
-                 * Page not on the LRU yet.  Flush all pagevecs and retry.
+                 * We lost the race. the page already moved to evictable list.
                  */
-                lru_add_drain_all();
-                if (!isolate_lru_page(page))
-                        putback_lru_page(page);
-                else if (PageUnevictable(page))
+                if (PageUnevictable(page))
                         count_vm_event(UNEVICTABLE_PGSTRANDED);
-
         }
 }
 
@@ -187,8 +183,6 @@ static long __mlock_vma_pages_range(struct vm_area_struct *vma,
         if (vma->vm_flags & VM_WRITE)
                 gup_flags |= GUP_FLAGS_WRITE;
 
-        lru_add_drain_all();    /* push cached pages to LRU */
-
         while (nr_pages > 0) {
                 int i;
 
@@ -251,8 +245,6 @@ static long __mlock_vma_pages_range(struct vm_area_struct *vma,
                 ret = 0;
         }
 
-        lru_add_drain_all();    /* to update stats */
-
         return ret;     /* count entire vma as locked_vm */
 }
 
@@ -546,6 +538,8 @@ asmlinkage long sys_mlock(unsigned long start, size_t len)
         if (!can_do_mlock())
                 return -EPERM;
 
+        lru_add_drain_all();    /* flush pagevec */
+
         down_write(&current->mm->mmap_sem);
         len = PAGE_ALIGN(len + (start & ~PAGE_MASK));
         start &= PAGE_MASK;
@@ -612,6 +606,8 @@ asmlinkage long sys_mlockall(int flags)
         if (!can_do_mlock())
                 goto out;
 
+        lru_add_drain_all();    /* flush pagevec */
+
         down_write(&current->mm->mmap_sem);
 
         lock_limit = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur;
diff --git a/mm/mmap.c b/mm/mmap.c
index de14ac21e5b5..d4855a682ab6 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1704,7 +1704,7 @@ find_extend_vma(struct mm_struct *mm, unsigned long addr)
         vma = find_vma_prev(mm, addr, &prev);
         if (vma && (vma->vm_start <= addr))
                 return vma;
-        if (expand_stack(prev, addr))
+        if (!prev || expand_stack(prev, addr))
                 return NULL;
         if (prev->vm_flags & VM_LOCKED) {
                 if (mlock_vma_pages_range(prev, addr, prev->vm_end) < 0)
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 0e0b282a2073..558f9afe6e4e 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -38,7 +38,6 @@ static DEFINE_SPINLOCK(zone_scan_mutex);
  * badness - calculate a numeric value for how bad this task has been
  * @p: task struct of which task we should calculate
  * @uptime: current uptime in seconds
- * @mem: target memory controller
  *
  * The formula used is relatively simple and documented inline in the
  * function. The main rationale is that we want to select a good task
@@ -295,6 +294,8 @@ static void dump_tasks(const struct mem_cgroup *mem)
                         continue;
                 if (mem && !task_in_mem_cgroup(p, mem))
                         continue;
+                if (!thread_group_leader(p))
+                        continue;
 
                 task_lock(p);
                 printk(KERN_INFO "[%5d] %5d %5d %8lu %8lu %3d     %3d %s\n",
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index d0a240fbb8bf..d8ac01474563 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -263,24 +263,39 @@ void prep_compound_page(struct page *page, unsigned long order)
 {
         int i;
         int nr_pages = 1 << order;
+
+        set_compound_page_dtor(page, free_compound_page);
+        set_compound_order(page, order);
+        __SetPageHead(page);
+        for (i = 1; i < nr_pages; i++) {
+                struct page *p = page + i;
+
+                __SetPageTail(p);
+                p->first_page = page;
+        }
+}
+
+#ifdef CONFIG_HUGETLBFS
+void prep_compound_gigantic_page(struct page *page, unsigned long order)
+{
+        int i;
+        int nr_pages = 1 << order;
         struct page *p = page + 1;
 
         set_compound_page_dtor(page, free_compound_page);
         set_compound_order(page, order);
         __SetPageHead(page);
-        for (i = 1; i < nr_pages; i++, p++) {
-                if (unlikely((i & (MAX_ORDER_NR_PAGES - 1)) == 0))
-                        p = pfn_to_page(page_to_pfn(page) + i);
+        for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) {
                 __SetPageTail(p);
                 p->first_page = page;
         }
 }
+#endif
 
 static void destroy_compound_page(struct page *page, unsigned long order)
 {
         int i;
         int nr_pages = 1 << order;
-        struct page *p = page + 1;
 
         if (unlikely(compound_order(page) != order))
                 bad_page(page);
@@ -288,9 +303,8 @@ static void destroy_compound_page(struct page *page, unsigned long order)
         if (unlikely(!PageHead(page)))
                         bad_page(page);
         __ClearPageHead(page);
-        for (i = 1; i < nr_pages; i++, p++) {
-                if (unlikely((i & (MAX_ORDER_NR_PAGES - 1)) == 0))
-                        p = pfn_to_page(page_to_pfn(page) + i);
+        for (i = 1; i < nr_pages; i++) {
+                struct page *p = page + i;
 
                 if (unlikely(!PageTail(p) |
                                 (p->first_page != page)))
@@ -1547,6 +1561,10 @@ nofail_alloc:
 
         /* We now go into synchronous reclaim */
         cpuset_memory_pressure_bump();
+        /*
+         * The task's cpuset might have expanded its set of allowable nodes
+         */
+        cpuset_update_task_memory_state();
         p->flags |= PF_MEMALLOC;
         reclaim_state.reclaimed_slab = 0;
         p->reclaim_state = &reclaim_state;
diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c
index f59d797dc5a9..1223d927904d 100644
--- a/mm/page_cgroup.c
+++ b/mm/page_cgroup.c
@@ -165,7 +165,7 @@ int online_page_cgroup(unsigned long start_pfn,
         unsigned long start, end, pfn;
         int fail = 0;
 
-        start = start_pfn & (PAGES_PER_SECTION - 1);
+        start = start_pfn & ~(PAGES_PER_SECTION - 1);
         end = ALIGN(start_pfn + nr_pages, PAGES_PER_SECTION);
 
         for (pfn = start; !fail && pfn < end; pfn += PAGES_PER_SECTION) {
@@ -188,7 +188,7 @@ int offline_page_cgroup(unsigned long start_pfn,
 {
         unsigned long start, end, pfn;
 
-        start = start_pfn & (PAGES_PER_SECTION - 1);
+        start = start_pfn & ~(PAGES_PER_SECTION - 1);
         end = ALIGN(start_pfn + nr_pages, PAGES_PER_SECTION);
 
         for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION)
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index b70a7fec1ff6..5e0ffd967452 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -130,10 +130,11 @@ int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn)
                 if (page && get_pageblock_migratetype(page) != MIGRATE_ISOLATE)
                         break;
         }
-        if (pfn < end_pfn)
+        page = __first_valid_page(start_pfn, end_pfn - start_pfn);
+        if ((pfn < end_pfn) || !page)
                 return -EBUSY;
         /* Check all pages are free or Marked as ISOLATED */
-        zone = page_zone(pfn_to_page(pfn));
+        zone = page_zone(page);
         spin_lock_irqsave(&zone->lock, flags);
         ret = __test_page_isolated_in_pageblock(start_pfn, end_pfn);
         spin_unlock_irqrestore(&zone->lock, flags);
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index a91b5f8fcaf6..a13ea6401ae7 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -64,7 +64,7 @@ void __meminit vmemmap_verify(pte_t *pte, int node,
         unsigned long pfn = pte_pfn(*pte);
         int actual_node = early_pfn_to_nid(pfn);
 
-        if (actual_node != node)
+        if (node_distance(actual_node, node) > LOCAL_DISTANCE)
                 printk(KERN_WARNING "[%lx-%lx] potential offnode "
                         "page_structs\n", start, end - 1);
 }
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index f1cc03bbf6ac..ba6b0f5f7fac 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -178,7 +178,7 @@ static int vmap_page_range(unsigned long addr, unsigned long end,
 static inline int is_vmalloc_or_module_addr(const void *x)
 {
         /*
-         * x86-64 and sparc64 put modules in a special place,
+         * ARM, x86-64 and sparc64 put modules in a special place,
          * and fall back on vmalloc() if that fails. Others
          * just put it in the vmalloc space.
          */
@@ -592,6 +592,8 @@ static void free_unmap_vmap_area_addr(unsigned long addr)
 
 #define VMAP_BLOCK_SIZE         (VMAP_BBMAP_BITS * PAGE_SIZE)
 
+static bool vmap_initialized __read_mostly = false;
+
 struct vmap_block_queue {
         spinlock_t lock;
         struct list_head free;
@@ -828,6 +830,9 @@ void vm_unmap_aliases(void)
         int cpu;
         int flush = 0;
 
+        if (unlikely(!vmap_initialized))
+                return;
+
         for_each_possible_cpu(cpu) {
                 struct vmap_block_queue *vbq = &per_cpu(vmap_block_queue, cpu);
                 struct vmap_block *vb;
@@ -942,6 +947,8 @@ void __init vmalloc_init(void)
                 INIT_LIST_HEAD(&vbq->dirty);
                 vbq->nr_dirty = 0;
         }
+
+        vmap_initialized = true;
 }
 
 void unmap_kernel_range(unsigned long addr, unsigned long size)