aboutsummaryrefslogtreecommitdiffstats
path: root/mm
diff options
context:
space:
mode:
authorKAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>2009-01-07 21:08:31 -0500
committerLinus Torvalds <torvalds@linux-foundation.org>2009-01-08 11:31:10 -0500
commit03f3c433648a97ae7c86be789edba67690f6ea60 (patch)
treed92a17f6fe9d90d3a6b46762742ef239bf5ecc44 /mm
parent42e9abb628def2c335a4ecf130bb6c88d916d885 (diff)
memcg: fix swap accounting leak
Fix swapin charge operation of memcg. Now, memcg has hooks to swap-out operation and checks SwapCache is really unused or not. That check depends on contents of struct page. I.e. If PageAnon(page) && page_mapped(page), the page is recoginized as still-in-use. Now, reuse_swap_page() calles delete_from_swap_cache() before establishment of any rmap. Then, in followinig sequence (Page fault with WRITE) try_charge() (charge += PAGESIZE) commit_charge() (Check page_cgroup is used or not..) reuse_swap_page() -> delete_from_swapcache() -> mem_cgroup_uncharge_swapcache() (charge -= PAGESIZE) ...... New charge is uncharged soon.... To avoid this, move commit_charge() after page_mapcount() goes up to 1. By this, try_charge() (usage += PAGESIZE) reuse_swap_page() (may usage -= PAGESIZE if PCG_USED is set) commit_charge() (If page_cgroup is not marked as PCG_USED, add new charge.) Accounting will be correct. Changelog (v2) -> (v3) - fixed invalid charge to swp_entry==0. - updated documentation. Changelog (v1) -> (v2) - fixed comment. [nishimura@mxp.nes.nec.co.jp: swap accounting leak doc fix] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Acked-by: Balbir Singh <balbir@linux.vnet.ibm.com> Tested-by: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Hugh Dickins <hugh@veritas.com> Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm')
-rw-r--r--mm/memcontrol.c7
-rw-r--r--mm/memory.c11
2 files changed, 10 insertions, 8 deletions
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index a7ecf23150c5..0ed61e27d526 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1169,10 +1169,11 @@ void mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr)
1169 /* 1169 /*
1170 * Now swap is on-memory. This means this page may be 1170 * Now swap is on-memory. This means this page may be
1171 * counted both as mem and swap....double count. 1171 * counted both as mem and swap....double count.
1172 * Fix it by uncharging from memsw. This SwapCache is stable 1172 * Fix it by uncharging from memsw. Basically, this SwapCache is stable
1173 * because we're still under lock_page(). 1173 * under lock_page(). But in do_swap_page()::memory.c, reuse_swap_page()
1174 * may call delete_from_swap_cache() before reach here.
1174 */ 1175 */
1175 if (do_swap_account) { 1176 if (do_swap_account && PageSwapCache(page)) {
1176 swp_entry_t ent = {.val = page_private(page)}; 1177 swp_entry_t ent = {.val = page_private(page)};
1177 struct mem_cgroup *memcg; 1178 struct mem_cgroup *memcg;
1178 memcg = swap_cgroup_record(ent, NULL); 1179 memcg = swap_cgroup_record(ent, NULL);
diff --git a/mm/memory.c b/mm/memory.c
index e5bfbe6b594c..e009ce870859 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2457,22 +2457,23 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
2457 * while the page is counted on swap but not yet in mapcount i.e. 2457 * while the page is counted on swap but not yet in mapcount i.e.
2458 * before page_add_anon_rmap() and swap_free(); try_to_free_swap() 2458 * before page_add_anon_rmap() and swap_free(); try_to_free_swap()
2459 * must be called after the swap_free(), or it will never succeed. 2459 * must be called after the swap_free(), or it will never succeed.
2460 * And mem_cgroup_commit_charge_swapin(), which uses the swp_entry 2460 * Because delete_from_swap_page() may be called by reuse_swap_page(),
2461 * in page->private, must be called before reuse_swap_page(), 2461 * mem_cgroup_commit_charge_swapin() may not be able to find swp_entry
2462 * which may delete_from_swap_cache(). 2462 * in page->private. In this case, a record in swap_cgroup is silently
2463 * discarded at swap_free().
2463 */ 2464 */
2464 2465
2465 mem_cgroup_commit_charge_swapin(page, ptr);
2466 inc_mm_counter(mm, anon_rss); 2466 inc_mm_counter(mm, anon_rss);
2467 pte = mk_pte(page, vma->vm_page_prot); 2467 pte = mk_pte(page, vma->vm_page_prot);
2468 if (write_access && reuse_swap_page(page)) { 2468 if (write_access && reuse_swap_page(page)) {
2469 pte = maybe_mkwrite(pte_mkdirty(pte), vma); 2469 pte = maybe_mkwrite(pte_mkdirty(pte), vma);
2470 write_access = 0; 2470 write_access = 0;
2471 } 2471 }
2472
2473 flush_icache_page(vma, page); 2472 flush_icache_page(vma, page);
2474 set_pte_at(mm, address, page_table, pte); 2473 set_pte_at(mm, address, page_table, pte);
2475 page_add_anon_rmap(page, vma, address); 2474 page_add_anon_rmap(page, vma, address);
2475 /* It's better to call commit-charge after rmap is established */
2476 mem_cgroup_commit_charge_swapin(page, ptr);
2476 2477
2477 swap_free(entry); 2478 swap_free(entry);
2478 if (vm_swap_full() || (vma->vm_flags & VM_LOCKED) || PageMlocked(page)) 2479 if (vm_swap_full() || (vma->vm_flags & VM_LOCKED) || PageMlocked(page))