6 files changed, 137 insertions, 108 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index ea8c3a4cd2ae..5f34bd8dda34 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2508,6 +2508,7 @@ static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
 {
         struct hstate *h = hstate_vma(vma);
         int ret = VM_FAULT_SIGBUS;
+        int anon_rmap = 0;
         pgoff_t idx;
         unsigned long size;
         struct page *page;
@@ -2562,14 +2563,13 @@ retry:
                         spin_lock(&inode->i_lock);
                         inode->i_blocks += blocks_per_huge_page(h);
                         spin_unlock(&inode->i_lock);
-                        page_dup_rmap(page);
                 } else {
                         lock_page(page);
                         if (unlikely(anon_vma_prepare(vma))) {
                                 ret = VM_FAULT_OOM;
                                 goto backout_unlocked;
                         }
-                        hugepage_add_new_anon_rmap(page, vma, address);
+                        anon_rmap = 1;
                 }
         } else {
                 /*
@@ -2582,7 +2582,6 @@ retry:
                               VM_FAULT_SET_HINDEX(h - hstates);
                         goto backout_unlocked;
                 }
-                page_dup_rmap(page);
         }
 
         /*
@@ -2606,6 +2605,10 @@ retry:
         if (!huge_pte_none(huge_ptep_get(ptep)))
                 goto backout;
 
+        if (anon_rmap)
+                hugepage_add_new_anon_rmap(page, vma, address);
+        else
+                page_dup_rmap(page);
         new_pte = make_huge_pte(vma, page, ((vma->vm_flags & VM_WRITE)
                                 && (vma->vm_flags & VM_SHARED)));
         set_huge_pte_at(mm, address, ptep, new_pte);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 3dbff4dcde35..4baddbae94cc 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3247,7 +3247,7 @@ int mem_cgroup_prepare_migration(struct page *page,
                 ctype = MEM_CGROUP_CHARGE_TYPE_CACHE;
         else
                 ctype = MEM_CGROUP_CHARGE_TYPE_SHMEM;
-        __mem_cgroup_commit_charge(memcg, page, 1, pc, ctype);
+        __mem_cgroup_commit_charge(memcg, newpage, 1, pc, ctype);
         return ret;
 }
 
diff --git a/mm/memory.c b/mm/memory.c
index 5e30583c2605..fa2f04e0337c 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -878,15 +878,24 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
                         }
                         if (likely(!non_swap_entry(entry)))
                                 rss[MM_SWAPENTS]++;
-                        else if (is_write_migration_entry(entry) &&
-                                        is_cow_mapping(vm_flags)) {
-                                /*
-                                 * COW mappings require pages in both parent
-                                 * and child to be set to read.
-                                 */
-                                make_migration_entry_read(&entry);
-                                pte = swp_entry_to_pte(entry);
-                                set_pte_at(src_mm, addr, src_pte, pte);
+                        else if (is_migration_entry(entry)) {
+                                page = migration_entry_to_page(entry);
+
+                                if (PageAnon(page))
+                                        rss[MM_ANONPAGES]++;
+                                else
+                                        rss[MM_FILEPAGES]++;
+
+                                if (is_write_migration_entry(entry) &&
+                                    is_cow_mapping(vm_flags)) {
+                                        /*
+                                         * COW mappings require pages in both
+                                         * parent and child to be set to read.
+                                         */
+                                        make_migration_entry_read(&entry);
+                                        pte = swp_entry_to_pte(entry);
+                                        set_pte_at(src_mm, addr, src_pte, pte);
+                                }
                         }
                 }
                 goto out_set_pte;
@@ -1191,6 +1200,16 @@ again:
 
                         if (!non_swap_entry(entry))
                                 rss[MM_SWAPENTS]--;
+                        else if (is_migration_entry(entry)) {
+                                struct page *page;
+
+                                page = migration_entry_to_page(entry);
+
+                                if (PageAnon(page))
+                                        rss[MM_ANONPAGES]--;
+                                else
+                                        rss[MM_FILEPAGES]--;
+                        }
                         if (unlikely(!free_swap_and_cache(entry)))
                                 print_bad_pte(vma, addr, ptent, NULL);
                 }
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 0027d8f4a1bb..d2186ecb36f7 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5413,7 +5413,25 @@ __count_immobile_pages(struct zone *zone, struct page *page, int count)
 
 bool is_pageblock_removable_nolock(struct page *page)
 {
-        struct zone *zone = page_zone(page);
+        struct zone *zone;
+        unsigned long pfn;
+
+        /*
+         * We have to be careful here because we are iterating over memory
+         * sections which are not zone aware so we might end up outside of
+         * the zone but still within the section.
+         * We have to take care about the node as well. If the node is offline
+         * its NODE_DATA will be NULL - see page_zone.
+         */
+        if (!node_online(page_to_nid(page)))
+                return false;
+
+        zone = page_zone(page);
+        pfn = page_to_pfn(page);
+        if (zone->zone_start_pfn > pfn ||
+                        zone->zone_start_pfn + zone->spanned_pages <= pfn)
+                return false;
+
         return __count_immobile_pages(zone, page, 0);
 }
 
diff --git a/mm/shmem.c b/mm/shmem.c
index feead1943d92..269d049294ab 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -379,7 +379,7 @@ static int shmem_free_swap(struct address_space *mapping,
 /*
  * Pagevec may contain swap entries, so shuffle up pages before releasing.
  */
-static void shmem_pagevec_release(struct pagevec *pvec)
+static void shmem_deswap_pagevec(struct pagevec *pvec)
 {
         int i, j;
 
@@ -389,7 +389,36 @@ static void shmem_pagevec_release(struct pagevec *pvec)
                         pvec->pages[j++] = page;
         }
         pvec->nr = j;
-        pagevec_release(pvec);
+}
+
+/*
+ * SysV IPC SHM_UNLOCK restore Unevictable pages to their evictable lists.
+ */
+void shmem_unlock_mapping(struct address_space *mapping)
+{
+        struct pagevec pvec;
+        pgoff_t indices[PAGEVEC_SIZE];
+        pgoff_t index = 0;
+
+        pagevec_init(&pvec, 0);
+        /*
+         * Minor point, but we might as well stop if someone else SHM_LOCKs it.
+         */
+        while (!mapping_unevictable(mapping)) {
+                /*
+                 * Avoid pagevec_lookup(): find_get_pages() returns 0 as if it
+                 * has finished, if it hits a row of PAGEVEC_SIZE swap entries.
+                 */
+                pvec.nr = shmem_find_get_pages_and_swap(mapping, index,
+                                        PAGEVEC_SIZE, pvec.pages, indices);
+                if (!pvec.nr)
+                        break;
+                index = indices[pvec.nr - 1] + 1;
+                shmem_deswap_pagevec(&pvec);
+                check_move_unevictable_pages(pvec.pages, pvec.nr);
+                pagevec_release(&pvec);
+                cond_resched();
+        }
 }
 
 /*
@@ -440,7 +469,8 @@ void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend)
                         }
                         unlock_page(page);
                 }
-                shmem_pagevec_release(&pvec);
+                shmem_deswap_pagevec(&pvec);
+                pagevec_release(&pvec);
                 mem_cgroup_uncharge_end();
                 cond_resched();
                 index++;
@@ -470,7 +500,8 @@ void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend)
                         continue;
                 }
                 if (index == start && indices[0] > end) {
-                        shmem_pagevec_release(&pvec);
+                        shmem_deswap_pagevec(&pvec);
+                        pagevec_release(&pvec);
                         break;
                 }
                 mem_cgroup_uncharge_start();
@@ -494,7 +525,8 @@ void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend)
                         }
                         unlock_page(page);
                 }
-                shmem_pagevec_release(&pvec);
+                shmem_deswap_pagevec(&pvec);
+                pagevec_release(&pvec);
                 mem_cgroup_uncharge_end();
                 index++;
         }
@@ -1068,13 +1100,6 @@ int shmem_lock(struct file *file, int lock, struct user_struct *user)
                 user_shm_unlock(inode->i_size, user);
                 info->flags &= ~VM_LOCKED;
                 mapping_clear_unevictable(file->f_mapping);
-                /*
-                 * Ensure that a racing putback_lru_page() can see
-                 * the pages of this mapping are evictable when we
-                 * skip them due to !PageLRU during the scan.
-                 */
-                smp_mb__after_clear_bit();
-                scan_mapping_unevictable_pages(file->f_mapping);
         }
         retval = 0;
 
@@ -2445,6 +2470,10 @@ int shmem_lock(struct file *file, int lock, struct user_struct *user)
         return 0;
 }
 
+void shmem_unlock_mapping(struct address_space *mapping)
+{
+}
+
 void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend)
 {
         truncate_inode_pages_range(inode->i_mapping, lstart, lend);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 2880396f7953..c52b23552659 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -26,7 +26,6 @@
 #include <linux/buffer_head.h>  /* for try_to_release_page(),
                                         buffer_heads_over_limit */
 #include <linux/mm_inline.h>
-#include <linux/pagevec.h>
 #include <linux/backing-dev.h>
 #include <linux/rmap.h>
 #include <linux/topology.h>
@@ -661,7 +660,7 @@ redo:
                  * When racing with an mlock or AS_UNEVICTABLE clearing
                  * (page is unlocked) make sure that if the other thread
                  * does not observe our setting of PG_lru and fails
-                 * isolation/check_move_unevictable_page,
+                 * isolation/check_move_unevictable_pages,
                  * we see PG_mlocked/AS_UNEVICTABLE cleared below and move
                  * the page back to the evictable list.
                  *
@@ -3499,100 +3498,61 @@ int page_evictable(struct page *page, struct vm_area_struct *vma)
         return 1;
 }
 
+#ifdef CONFIG_SHMEM
 /**
- * check_move_unevictable_page - check page for evictability and move to appropriate zone lru list
- * @page: page to check evictability and move to appropriate lru list
- * @zone: zone page is in
+ * check_move_unevictable_pages - check pages for evictability and move to appropriate zone lru list
+ * @pages:      array of pages to check
+ * @nr_pages:   number of pages to check
  *
- * Checks a page for evictability and moves the page to the appropriate
- * zone lru list.
+ * Checks pages for evictability and moves them to the appropriate lru list.
  *
- * Restrictions: zone->lru_lock must be held, page must be on LRU and must
- * have PageUnevictable set.
+ * This function is only used for SysV IPC SHM_UNLOCK.
  */
-static void check_move_unevictable_page(struct page *page, struct zone *zone)
+void check_move_unevictable_pages(struct page **pages, int nr_pages)
 {
         struct lruvec *lruvec;
+        struct zone *zone = NULL;
+        int pgscanned = 0;
+        int pgrescued = 0;
+        int i;
 
-        VM_BUG_ON(PageActive(page));
-retry:
-        ClearPageUnevictable(page);
-        if (page_evictable(page, NULL)) {
-                enum lru_list l = page_lru_base_type(page);
-
-                __dec_zone_state(zone, NR_UNEVICTABLE);
-                lruvec = mem_cgroup_lru_move_lists(zone, page,
-                                                   LRU_UNEVICTABLE, l);
-                list_move(&page->lru, &lruvec->lists[l]);
-                __inc_zone_state(zone, NR_INACTIVE_ANON + l);
-                __count_vm_event(UNEVICTABLE_PGRESCUED);
-        } else {
-                /*
-                 * rotate unevictable list
-                 */
-                SetPageUnevictable(page);
-                lruvec = mem_cgroup_lru_move_lists(zone, page, LRU_UNEVICTABLE,
-                                                   LRU_UNEVICTABLE);
-                list_move(&page->lru, &lruvec->lists[LRU_UNEVICTABLE]);
-                if (page_evictable(page, NULL))
-                        goto retry;
-        }
-}
-
-/**
- * scan_mapping_unevictable_pages - scan an address space for evictable pages
- * @mapping: struct address_space to scan for evictable pages
- *
- * Scan all pages in mapping.  Check unevictable pages for
- * evictability and move them to the appropriate zone lru list.
- */
-void scan_mapping_unevictable_pages(struct address_space *mapping)
-{
-        pgoff_t next = 0;
-        pgoff_t end   = (i_size_read(mapping->host) + PAGE_CACHE_SIZE - 1) >>
-                         PAGE_CACHE_SHIFT;
-        struct zone *zone;
-        struct pagevec pvec;
-
-        if (mapping->nrpages == 0)
-                return;
-
-        pagevec_init(&pvec, 0);
-        while (next < end &&
-                pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) {
-                int i;
-                int pg_scanned = 0;
-
-                zone = NULL;
-
-                for (i = 0; i < pagevec_count(&pvec); i++) {
-                        struct page *page = pvec.pages[i];
-                        pgoff_t page_index = page->index;
-                        struct zone *pagezone = page_zone(page);
+        for (i = 0; i < nr_pages; i++) {
+                struct page *page = pages[i];
+                struct zone *pagezone;
 
-                        pg_scanned++;
-                        if (page_index > next)
-                                next = page_index;
-                        next++;
+                pgscanned++;
+                pagezone = page_zone(page);
+                if (pagezone != zone) {
+                        if (zone)
+                                spin_unlock_irq(&zone->lru_lock);
+                        zone = pagezone;
+                        spin_lock_irq(&zone->lru_lock);
+                }
 
-                        if (pagezone != zone) {
-                                if (zone)
-                                        spin_unlock_irq(&zone->lru_lock);
-                                zone = pagezone;
-                                spin_lock_irq(&zone->lru_lock);
-                        }
+                if (!PageLRU(page) || !PageUnevictable(page))
+                        continue;
 
-                        if (PageLRU(page) && PageUnevictable(page))
-                                check_move_unevictable_page(page, zone);
+                if (page_evictable(page, NULL)) {
+                        enum lru_list lru = page_lru_base_type(page);
+
+                        VM_BUG_ON(PageActive(page));
+                        ClearPageUnevictable(page);
+                        __dec_zone_state(zone, NR_UNEVICTABLE);
+                        lruvec = mem_cgroup_lru_move_lists(zone, page,
+                                                LRU_UNEVICTABLE, lru);
+                        list_move(&page->lru, &lruvec->lists[lru]);
+                        __inc_zone_state(zone, NR_INACTIVE_ANON + lru);
+                        pgrescued++;
                 }
-                if (zone)
-                        spin_unlock_irq(&zone->lru_lock);
-                pagevec_release(&pvec);
-
-                count_vm_events(UNEVICTABLE_PGSCANNED, pg_scanned);
         }
 
+        if (zone) {
+                __count_vm_events(UNEVICTABLE_PGRESCUED, pgrescued);
+                __count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned);
+                spin_unlock_irq(&zone->lru_lock);
+        }
 }
+#endif /* CONFIG_SHMEM */
 
 static void warn_scan_unevictable_pages(void)
 {