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>

3 files changed, 29 insertions, 24 deletions

diff --git a/Documentation/controllers/memory.txt b/Documentation/controllers/memory.txt
index 9b53d58..1c07547 100644
--- a/Documentation/controllers/memory.txt
+++ b/Documentation/controllers/memory.txt
@@ -112,14 +112,22 @@ the per cgroup LRU.
 
 2.2.1 Accounting details
 
-All mapped pages (RSS) and unmapped user pages (Page Cache) are accounted.
-RSS pages are accounted at the time of page_add_*_rmap() unless they've already
-been accounted for earlier. A file page will be accounted for as Page Cache;
-it's mapped into the page tables of a process, duplicate accounting is carefully
-avoided. Page Cache pages are accounted at the time of add_to_page_cache().
-The corresponding routines that remove a page from the page tables or removes
-a page from Page Cache is used to decrement the accounting counters of the
-cgroup.
+All mapped anon pages (RSS) and cache pages (Page Cache) are accounted.
+(some pages which never be reclaimable and will not be on global LRU
+ are not accounted. we just accounts pages under usual vm management.)
+
+RSS pages are accounted at page_fault unless they've already been accounted
+for earlier. A file page will be accounted for as Page Cache when it's
+inserted into inode (radix-tree). While it's mapped into the page tables of
+processes, duplicate accounting is carefully avoided.
+
+A RSS page is unaccounted when it's fully unmapped. A PageCache page is
+unaccounted when it's removed from radix-tree.
+
+At page migration, accounting information is kept.
+
+Note: we just account pages-on-lru because our purpose is to control amount
+of used pages. not-on-lru pages are tend to be out-of-control from vm view.
 
 2.3 Shared Page Accounting
 
diff --git a/mm/memory.c b/mm/memory.c
index 54cf20e..3a6c4a6 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 7e90beb..8701d5f 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);
 		/*