Merge branch 'master' into next

8 files changed, 40 insertions, 39 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index 379ff0bcbf6e..1b60f30cebfa 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -121,7 +121,6 @@ void __remove_from_page_cache(struct page *page)
         mapping->nrpages--;
         __dec_zone_page_state(page, NR_FILE_PAGES);
         BUG_ON(page_mapped(page));
-        mem_cgroup_uncharge_cache_page(page);
 
         /*
          * Some filesystems seem to re-dirty the page even after
@@ -145,6 +144,7 @@ void remove_from_page_cache(struct page *page)
         spin_lock_irq(&mapping->tree_lock);
         __remove_from_page_cache(page);
         spin_unlock_irq(&mapping->tree_lock);
+        mem_cgroup_uncharge_cache_page(page);
 }
 
 static int sync_page(void *word)
@@ -476,13 +476,13 @@ int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
                 if (likely(!error)) {
                         mapping->nrpages++;
                         __inc_zone_page_state(page, NR_FILE_PAGES);
+                        spin_unlock_irq(&mapping->tree_lock);
                 } else {
                         page->mapping = NULL;
+                        spin_unlock_irq(&mapping->tree_lock);
                         mem_cgroup_uncharge_cache_page(page);
                         page_cache_release(page);
                 }
-
-                spin_unlock_irq(&mapping->tree_lock);
                 radix_tree_preload_end();
         } else
                 mem_cgroup_uncharge_cache_page(page);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 28c655ba9353..e83ad2c9228c 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -316,7 +316,7 @@ static void resv_map_release(struct kref *ref)
 static struct resv_map *vma_resv_map(struct vm_area_struct *vma)
 {
         VM_BUG_ON(!is_vm_hugetlb_page(vma));
-        if (!(vma->vm_flags & VM_SHARED))
+        if (!(vma->vm_flags & VM_MAYSHARE))
                 return (struct resv_map *)(get_vma_private_data(vma) &
                                                         ~HPAGE_RESV_MASK);
         return NULL;
@@ -325,7 +325,7 @@ static struct resv_map *vma_resv_map(struct vm_area_struct *vma)
 static void set_vma_resv_map(struct vm_area_struct *vma, struct resv_map *map)
 {
         VM_BUG_ON(!is_vm_hugetlb_page(vma));
-        VM_BUG_ON(vma->vm_flags & VM_SHARED);
+        VM_BUG_ON(vma->vm_flags & VM_MAYSHARE);
 
         set_vma_private_data(vma, (get_vma_private_data(vma) &
                                 HPAGE_RESV_MASK) | (unsigned long)map);
@@ -334,7 +334,7 @@ static void set_vma_resv_map(struct vm_area_struct *vma, struct resv_map *map)
 static void set_vma_resv_flags(struct vm_area_struct *vma, unsigned long flags)
 {
         VM_BUG_ON(!is_vm_hugetlb_page(vma));
-        VM_BUG_ON(vma->vm_flags & VM_SHARED);
+        VM_BUG_ON(vma->vm_flags & VM_MAYSHARE);
 
         set_vma_private_data(vma, get_vma_private_data(vma) | flags);
 }
@@ -353,7 +353,7 @@ static void decrement_hugepage_resv_vma(struct hstate *h,
         if (vma->vm_flags & VM_NORESERVE)
                 return;
 
-        if (vma->vm_flags & VM_SHARED) {
+        if (vma->vm_flags & VM_MAYSHARE) {
                 /* Shared mappings always use reserves */
                 h->resv_huge_pages--;
         } else if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) {
@@ -369,14 +369,14 @@ static void decrement_hugepage_resv_vma(struct hstate *h,
 void reset_vma_resv_huge_pages(struct vm_area_struct *vma)
 {
         VM_BUG_ON(!is_vm_hugetlb_page(vma));
-        if (!(vma->vm_flags & VM_SHARED))
+        if (!(vma->vm_flags & VM_MAYSHARE))
                 vma->vm_private_data = (void *)0;
 }
 
 /* Returns true if the VMA has associated reserve pages */
 static int vma_has_reserves(struct vm_area_struct *vma)
 {
-        if (vma->vm_flags & VM_SHARED)
+        if (vma->vm_flags & VM_MAYSHARE)
                 return 1;
         if (is_vma_resv_set(vma, HPAGE_RESV_OWNER))
                 return 1;
@@ -924,7 +924,7 @@ static long vma_needs_reservation(struct hstate *h,
         struct address_space *mapping = vma->vm_file->f_mapping;
         struct inode *inode = mapping->host;
 
-        if (vma->vm_flags & VM_SHARED) {
+        if (vma->vm_flags & VM_MAYSHARE) {
                 pgoff_t idx = vma_hugecache_offset(h, vma, addr);
                 return region_chg(&inode->i_mapping->private_list,
                                                         idx, idx + 1);
@@ -949,7 +949,7 @@ static void vma_commit_reservation(struct hstate *h,
         struct address_space *mapping = vma->vm_file->f_mapping;
         struct inode *inode = mapping->host;
 
-        if (vma->vm_flags & VM_SHARED) {
+        if (vma->vm_flags & VM_MAYSHARE) {
                 pgoff_t idx = vma_hugecache_offset(h, vma, addr);
                 region_add(&inode->i_mapping->private_list, idx, idx + 1);
 
@@ -1893,7 +1893,7 @@ retry_avoidcopy:
          * at the time of fork() could consume its reserves on COW instead
          * of the full address range.
          */
-        if (!(vma->vm_flags & VM_SHARED) &&
+        if (!(vma->vm_flags & VM_MAYSHARE) &&
                         is_vma_resv_set(vma, HPAGE_RESV_OWNER) &&
                         old_page != pagecache_page)
                 outside_reserve = 1;
@@ -2000,7 +2000,7 @@ retry:
                 clear_huge_page(page, address, huge_page_size(h));
                 __SetPageUptodate(page);
 
-                if (vma->vm_flags & VM_SHARED) {
+                if (vma->vm_flags & VM_MAYSHARE) {
                         int err;
                         struct inode *inode = mapping->host;
 
@@ -2104,7 +2104,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
                         goto out_mutex;
                 }
 
-                if (!(vma->vm_flags & VM_SHARED))
+                if (!(vma->vm_flags & VM_MAYSHARE))
                         pagecache_page = hugetlbfs_pagecache_page(h,
                                                                 vma, address);
         }
@@ -2289,7 +2289,7 @@ int hugetlb_reserve_pages(struct inode *inode,
          * to reserve the full area even if read-only as mprotect() may be
          * called to make the mapping read-write. Assume !vma is a shm mapping
          */
-        if (!vma || vma->vm_flags & VM_SHARED)
+        if (!vma || vma->vm_flags & VM_MAYSHARE)
                 chg = region_chg(&inode->i_mapping->private_list, from, to);
         else {
                 struct resv_map *resv_map = resv_map_alloc();
@@ -2330,7 +2330,7 @@ int hugetlb_reserve_pages(struct inode *inode,
          * consumed reservations are stored in the map. Hence, nothing
          * else has to be done for private mappings here
          */
-        if (!vma || vma->vm_flags & VM_SHARED)
+        if (!vma || vma->vm_flags & VM_MAYSHARE)
                 region_add(&inode->i_mapping->private_list, from, to);
         return 0;
 }
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 01c2d8f14685..78eb8552818b 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -314,14 +314,6 @@ static struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm)
         return mem;
 }
 
-static bool mem_cgroup_is_obsolete(struct mem_cgroup *mem)
-{
-        if (!mem)
-                return true;
-        return css_is_removed(&mem->css);
-}
-
-
 /*
  * Call callback function against all cgroup under hierarchy tree.
  */
@@ -932,7 +924,7 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm,
         if (unlikely(!mem))
                 return 0;
 
-        VM_BUG_ON(!mem || mem_cgroup_is_obsolete(mem));
+        VM_BUG_ON(css_is_removed(&mem->css));
 
         while (1) {
                 int ret;
@@ -1488,8 +1480,9 @@ void mem_cgroup_uncharge_cache_page(struct page *page)
         __mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_CACHE);
 }
 
+#ifdef CONFIG_SWAP
 /*
- * called from __delete_from_swap_cache() and drop "page" account.
+ * called after __delete_from_swap_cache() and drop "page" account.
  * memcg information is recorded to swap_cgroup of "ent"
  */
 void mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent)
@@ -1506,6 +1499,7 @@ void mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent)
         if (memcg)
                 css_put(&memcg->css);
 }
+#endif
 
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
 /*
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 92bcf1db16b2..a7b2460e922b 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -284,22 +284,28 @@ static void dump_tasks(const struct mem_cgroup *mem)
         printk(KERN_INFO "[ pid ]   uid  tgid total_vm      rss cpu oom_adj "
                "name\n");
         do_each_thread(g, p) {
-                /*
-                 * total_vm and rss sizes do not exist for tasks with a
-                 * detached mm so there's no need to report them.
-                 */
-                if (!p->mm)
-                        continue;
+                struct mm_struct *mm;
+
                 if (mem && !task_in_mem_cgroup(p, mem))
                         continue;
                 if (!thread_group_leader(p))
                         continue;
 
                 task_lock(p);
+                mm = p->mm;
+                if (!mm) {
+                        /*
+                         * total_vm and rss sizes do not exist for tasks with no
+                         * mm so there's no need to report them; they can't be
+                         * oom killed anyway.
+                         */
+                        task_unlock(p);
+                        continue;
+                }
                 printk(KERN_INFO "[%5d] %5d %5d %8lu %8lu %3d     %3d %s\n",
-                       p->pid, __task_cred(p)->uid, p->tgid,
-                       p->mm->total_vm, get_mm_rss(p->mm), (int)task_cpu(p),
-                       p->oomkilladj, p->comm);
+                       p->pid, __task_cred(p)->uid, p->tgid, mm->total_vm,
+                       get_mm_rss(mm), (int)task_cpu(p), p->oomkilladj,
+                       p->comm);
                 task_unlock(p);
         } while_each_thread(g, p);
 }
diff --git a/mm/rmap.c b/mm/rmap.c
index 16521664010d..23122af32611 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -14,7 +14,7 @@
  * Original design by Rik van Riel <riel@conectiva.com.br> 2001
  * File methods by Dave McCracken <dmccr@us.ibm.com> 2003, 2004
  * Anonymous methods by Andrea Arcangeli <andrea@suse.de> 2004
- * Contributions by Hugh Dickins <hugh@veritas.com> 2003, 2004
+ * Contributions by Hugh Dickins 2003, 2004
  */
 
 /*
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 3ecea98ecb45..1416e7e9e02d 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -109,8 +109,6 @@ int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp_mask)
  */
 void __delete_from_swap_cache(struct page *page)
 {
-        swp_entry_t ent = {.val = page_private(page)};
-
         VM_BUG_ON(!PageLocked(page));
         VM_BUG_ON(!PageSwapCache(page));
         VM_BUG_ON(PageWriteback(page));
@@ -121,7 +119,6 @@ void __delete_from_swap_cache(struct page *page)
         total_swapcache_pages--;
         __dec_zone_page_state(page, NR_FILE_PAGES);
         INC_CACHE_INFO(del_total);
-        mem_cgroup_uncharge_swapcache(page, ent);
 }
 
 /**
@@ -191,6 +188,7 @@ void delete_from_swap_cache(struct page *page)
         __delete_from_swap_cache(page);
         spin_unlock_irq(&swapper_space.tree_lock);
 
+        mem_cgroup_uncharge_swapcache(page, entry);
         swap_free(entry);
         page_cache_release(page);
 }
diff --git a/mm/truncate.c b/mm/truncate.c
index 55206fab7b99..12e1579f9165 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -359,6 +359,7 @@ invalidate_complete_page2(struct address_space *mapping, struct page *page)
         BUG_ON(page_has_private(page));
         __remove_from_page_cache(page);
         spin_unlock_irq(&mapping->tree_lock);
+        mem_cgroup_uncharge_cache_page(page);
         page_cache_release(page);       /* pagecache ref */
         return 1;
 failed:
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 5fa3eda1f03f..d254306562cd 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -470,10 +470,12 @@ static int __remove_mapping(struct address_space *mapping, struct page *page)
                 swp_entry_t swap = { .val = page_private(page) };
                 __delete_from_swap_cache(page);
                 spin_unlock_irq(&mapping->tree_lock);
+                mem_cgroup_uncharge_swapcache(page, swap);
                 swap_free(swap);
         } else {
                 __remove_from_page_cache(page);
                 spin_unlock_irq(&mapping->tree_lock);
+                mem_cgroup_uncharge_cache_page(page);
         }
 
         return 1;