memcg: avoid accounting special pages

There are not-on-LRU pages which can be mapped and they are not worth to
be accounted.  (becasue we can't shrink them and need dirty codes to
handle specical case) We'd like to make use of usual objrmap/radix-tree's
protcol and don't want to account out-of-vm's control pages.

When special_mapping_fault() is called, page->mapping is tend to be NULL
and it's charged as Anonymous page.  insert_page() also handles some
special pages from drivers.

This patch is for avoiding to account special pages.

Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Cc: Balbir Singh <balbir@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 13 insertions, 16 deletions

diff --git a/mm/memory.c b/mm/memory.c
index 54cf20ee0a83..3a6c4a658325 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1323,18 +1323,14 @@ static int insert_page(struct vm_area_struct *vma, unsigned long addr,
         pte_t *pte;
         spinlock_t *ptl;
 
-        retval = mem_cgroup_charge(page, mm, GFP_KERNEL);
-        if (retval)
-                goto out;
-
         retval = -EINVAL;
         if (PageAnon(page))
-                goto out_uncharge;
+                goto out;
         retval = -ENOMEM;
         flush_dcache_page(page);
         pte = get_locked_pte(mm, addr, &ptl);
         if (!pte)
-                goto out_uncharge;
+                goto out;
         retval = -EBUSY;
         if (!pte_none(*pte))
                 goto out_unlock;
@@ -1350,8 +1346,6 @@ static int insert_page(struct vm_area_struct *vma, unsigned long addr,
         return retval;
 out_unlock:
         pte_unmap_unlock(pte, ptl);
-out_uncharge:
-        mem_cgroup_uncharge_page(page);
 out:
         return retval;
 }
@@ -2463,6 +2457,7 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
         struct page *page;
         pte_t entry;
         int anon = 0;
+        int charged = 0;
         struct page *dirty_page = NULL;
         struct vm_fault vmf;
         int ret;
@@ -2503,6 +2498,12 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
                                 ret = VM_FAULT_OOM;
                                 goto out;
                         }
+                        if (mem_cgroup_charge(page, mm, GFP_KERNEL)) {
+                                ret = VM_FAULT_OOM;
+                                page_cache_release(page);
+                                goto out;
+                        }
+                        charged = 1;
                         /*
                          * Don't let another task, with possibly unlocked vma,
                          * keep the mlocked page.
@@ -2543,11 +2544,6 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 
         }
 
-        if (mem_cgroup_charge(page, mm, GFP_KERNEL)) {
-                ret = VM_FAULT_OOM;
-                goto out;
-        }
-
         page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
 
         /*
@@ -2585,7 +2581,8 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
                 /* no need to invalidate: a not-present page won't be cached */
                 update_mmu_cache(vma, address, entry);
         } else {
-                mem_cgroup_uncharge_page(page);
+                if (charged)
+                        mem_cgroup_uncharge_page(page);
                 if (anon)
                         page_cache_release(page);
                 else
diff --git a/mm/rmap.c b/mm/rmap.c
index 7e90bebbeb6c..8701d5fce732 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -727,8 +727,8 @@ void page_remove_rmap(struct page *page, struct vm_area_struct *vma)
                         page_clear_dirty(page);
                         set_page_dirty(page);
                 }
-
-                mem_cgroup_uncharge_page(page);
+                if (PageAnon(page))
+                        mem_cgroup_uncharge_page(page);
                 __dec_zone_page_state(page,
                         PageAnon(page) ? NR_ANON_PAGES : NR_FILE_MAPPED);
                 /*