From d69b042f3d7406ddba560143b1796020df760800 Mon Sep 17 00:00:00 2001 From: Balbir Singh Date: Wed, 17 Jun 2009 16:26:34 -0700 Subject: memcg: add file-based RSS accounting Add file RSS tracking per memory cgroup We currently don't track file RSS, the RSS we report is actually anon RSS. All the file mapped pages, come in through the page cache and get accounted there. This patch adds support for accounting file RSS pages. It should 1. Help improve the metrics reported by the memory resource controller 2. Will form the basis for a future shared memory accounting heuristic that has been proposed by Kamezawa. Unfortunately, we cannot rename the existing "rss" keyword used in memory.stat to "anon_rss". We however, add "mapped_file" data and hope to educate the end user through documentation. [hugh.dickins@tiscali.co.uk: fix mem_cgroup_update_mapped_file_stat oops] Signed-off-by: Balbir Singh Acked-by: KAMEZAWA Hiroyuki Cc: Li Zefan Cc: Paul Menage Cc: Dhaval Giani Cc: Daisuke Nishimura Cc: YAMAMOTO Takashi Cc: KOSAKI Motohiro Cc: David Rientjes Signed-off-by: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 66 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 65 insertions(+), 1 deletion(-) (limited to 'mm/memcontrol.c') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 70db6e0a5eec..6f682901deb5 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -62,7 +62,8 @@ enum mem_cgroup_stat_index { * For MEM_CONTAINER_TYPE_ALL, usage = pagecache + rss. */ MEM_CGROUP_STAT_CACHE, /* # of pages charged as cache */ - MEM_CGROUP_STAT_RSS, /* # of pages charged as rss */ + MEM_CGROUP_STAT_RSS, /* # of pages charged as anon rss */ + MEM_CGROUP_STAT_MAPPED_FILE, /* # of pages charged as file rss */ MEM_CGROUP_STAT_PGPGIN_COUNT, /* # of pages paged in */ MEM_CGROUP_STAT_PGPGOUT_COUNT, /* # of pages paged out */ @@ -900,6 +901,44 @@ static void record_last_oom(struct mem_cgroup *mem) mem_cgroup_walk_tree(mem, NULL, record_last_oom_cb); } +/* + * Currently used to update mapped file statistics, but the routine can be + * generalized to update other statistics as well. + */ +void mem_cgroup_update_mapped_file_stat(struct page *page, int val) +{ + struct mem_cgroup *mem; + struct mem_cgroup_stat *stat; + struct mem_cgroup_stat_cpu *cpustat; + int cpu; + struct page_cgroup *pc; + + if (!page_is_file_cache(page)) + return; + + pc = lookup_page_cgroup(page); + if (unlikely(!pc)) + return; + + lock_page_cgroup(pc); + mem = pc->mem_cgroup; + if (!mem) + goto done; + + if (!PageCgroupUsed(pc)) + goto done; + + /* + * Preemption is already disabled, we don't need get_cpu() + */ + cpu = smp_processor_id(); + stat = &mem->stat; + cpustat = &stat->cpustat[cpu]; + + __mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_MAPPED_FILE, val); +done: + unlock_page_cgroup(pc); +} /* * Unlike exported interface, "oom" parameter is added. if oom==true, @@ -1098,6 +1137,10 @@ static int mem_cgroup_move_account(struct page_cgroup *pc, struct mem_cgroup_per_zone *from_mz, *to_mz; int nid, zid; int ret = -EBUSY; + struct page *page; + int cpu; + struct mem_cgroup_stat *stat; + struct mem_cgroup_stat_cpu *cpustat; VM_BUG_ON(from == to); VM_BUG_ON(PageLRU(pc->page)); @@ -1118,6 +1161,23 @@ static int mem_cgroup_move_account(struct page_cgroup *pc, res_counter_uncharge(&from->res, PAGE_SIZE); mem_cgroup_charge_statistics(from, pc, false); + + page = pc->page; + if (page_is_file_cache(page) && page_mapped(page)) { + cpu = smp_processor_id(); + /* Update mapped_file data for mem_cgroup "from" */ + stat = &from->stat; + cpustat = &stat->cpustat[cpu]; + __mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_MAPPED_FILE, + -1); + + /* Update mapped_file data for mem_cgroup "to" */ + stat = &to->stat; + cpustat = &stat->cpustat[cpu]; + __mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_MAPPED_FILE, + 1); + } + if (do_swap_account) res_counter_uncharge(&from->memsw, PAGE_SIZE); css_put(&from->css); @@ -2046,6 +2106,7 @@ static int mem_cgroup_reset(struct cgroup *cont, unsigned int event) enum { MCS_CACHE, MCS_RSS, + MCS_MAPPED_FILE, MCS_PGPGIN, MCS_PGPGOUT, MCS_INACTIVE_ANON, @@ -2066,6 +2127,7 @@ struct { } memcg_stat_strings[NR_MCS_STAT] = { {"cache", "total_cache"}, {"rss", "total_rss"}, + {"mapped_file", "total_mapped_file"}, {"pgpgin", "total_pgpgin"}, {"pgpgout", "total_pgpgout"}, {"inactive_anon", "total_inactive_anon"}, @@ -2086,6 +2148,8 @@ static int mem_cgroup_get_local_stat(struct mem_cgroup *mem, void *data) s->stat[MCS_CACHE] += val * PAGE_SIZE; val = mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_RSS); s->stat[MCS_RSS] += val * PAGE_SIZE; + val = mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_MAPPED_FILE); + s->stat[MCS_MAPPED_FILE] += val * PAGE_SIZE; val = mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_PGPGIN_COUNT); s->stat[MCS_PGPGIN] += val; val = mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_PGPGOUT_COUNT); -- cgit v1.2.3 From 338c843108bf5030d6765f4405126e70f8b77845 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Wed, 17 Jun 2009 16:27:15 -0700 Subject: memcg: remove some redundant checks We don't need to check do_swap_account in the case that the function which checks do_swap_account will never get called if do_swap_account == 0. Signed-off-by: Li Zefan Cc: Balbir Singh Acked-by: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 11 ++++------- mm/page_cgroup.c | 8 -------- 2 files changed, 4 insertions(+), 15 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 6f682901deb5..3468c38adde6 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -45,7 +45,7 @@ struct cgroup_subsys mem_cgroup_subsys __read_mostly; #define MEM_CGROUP_RECLAIM_RETRIES 5 #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP -/* Turned on only when memory cgroup is enabled && really_do_swap_account = 0 */ +/* Turned on only when memory cgroup is enabled && really_do_swap_account = 1 */ int do_swap_account __read_mostly; static int really_do_swap_account __initdata = 1; /* for remember boot option*/ #else @@ -1763,16 +1763,14 @@ static int mem_cgroup_resize_limit(struct mem_cgroup *memcg, return ret; } -int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg, - unsigned long long val) +static int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg, + unsigned long long val) { int retry_count; u64 memlimit, oldusage, curusage; int children = mem_cgroup_count_children(memcg); int ret = -EBUSY; - if (!do_swap_account) - return -EINVAL; /* see mem_cgroup_resize_res_limit */ retry_count = children * MEM_CGROUP_RECLAIM_RETRIES; oldusage = res_counter_read_u64(&memcg->memsw, RES_USAGE); @@ -2007,8 +2005,7 @@ static u64 mem_cgroup_read(struct cgroup *cont, struct cftype *cft) val = res_counter_read_u64(&mem->res, name); break; case _MEMSWAP: - if (do_swap_account) - val = res_counter_read_u64(&mem->memsw, name); + val = res_counter_read_u64(&mem->memsw, name); break; default: BUG(); diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c index 672089d5819f..f22b4ebbd8dc 100644 --- a/mm/page_cgroup.c +++ b/mm/page_cgroup.c @@ -311,8 +311,6 @@ static int swap_cgroup_prepare(int type) struct swap_cgroup_ctrl *ctrl; unsigned long idx, max; - if (!do_swap_account) - return 0; ctrl = &swap_cgroup_ctrl[type]; for (idx = 0; idx < ctrl->length; idx++) { @@ -349,9 +347,6 @@ unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id) struct swap_cgroup *sc; unsigned short old; - if (!do_swap_account) - return 0; - ctrl = &swap_cgroup_ctrl[type]; mappage = ctrl->map[idx]; @@ -380,9 +375,6 @@ unsigned short lookup_swap_cgroup(swp_entry_t ent) struct swap_cgroup *sc; unsigned short ret; - if (!do_swap_account) - return 0; - ctrl = &swap_cgroup_ctrl[type]; mappage = ctrl->map[idx]; sc = page_address(mappage); -- cgit v1.2.3 From 8a9478ca7f4bcb8945cec7f95d52dae2d5e50cbd Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Wed, 17 Jun 2009 16:27:17 -0700 Subject: memcg: fix swap accounting This patch fixes mis-accounting of swap usage in memcg. In the current implementation, memcg's swap account is uncharged only when swap is completely freed. But there are several cases where swap cannot be freed cleanly. For handling that, this patch changes that memcg uncharges swap account when swap has no references other than cache. By this, memcg's swap entry accounting can be fully synchronous with the application's behavior. This patch also changes memcg's hooks for swap-out. Signed-off-by: KAMEZAWA Hiroyuki Cc: Daisuke Nishimura Acked-by: Balbir Singh Cc: Hugh Dickins Cc: Johannes Weiner Cc: Li Zefan Cc: Dhaval Giani Cc: YAMAMOTO Takashi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 5 +++-- mm/memcontrol.c | 17 ++++++++++++----- mm/swapfile.c | 16 ++++++++++++---- 3 files changed, 27 insertions(+), 11 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/include/linux/swap.h b/include/linux/swap.h index dca9b9999aeb..c88b36665f79 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -319,10 +319,11 @@ static inline void disable_swap_token(void) } #ifdef CONFIG_CGROUP_MEM_RES_CTLR -extern void mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent); +extern void +mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout); #else static inline void -mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent) +mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout) { } #endif diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 3468c38adde6..a83e0395444b 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -189,6 +189,7 @@ enum charge_type { MEM_CGROUP_CHARGE_TYPE_SHMEM, /* used by page migration of shmem */ MEM_CGROUP_CHARGE_TYPE_FORCE, /* used by force_empty */ MEM_CGROUP_CHARGE_TYPE_SWAPOUT, /* for accounting swapcache */ + MEM_CGROUP_CHARGE_TYPE_DROP, /* a page was unused swap cache */ NR_CHARGE_TYPE, }; @@ -1493,6 +1494,7 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) switch (ctype) { case MEM_CGROUP_CHARGE_TYPE_MAPPED: + case MEM_CGROUP_CHARGE_TYPE_DROP: if (page_mapped(page)) goto unlock_out; break; @@ -1556,18 +1558,23 @@ void mem_cgroup_uncharge_cache_page(struct page *page) * 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) +void +mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout) { struct mem_cgroup *memcg; + int ctype = MEM_CGROUP_CHARGE_TYPE_SWAPOUT; + + if (!swapout) /* this was a swap cache but the swap is unused ! */ + ctype = MEM_CGROUP_CHARGE_TYPE_DROP; + + memcg = __mem_cgroup_uncharge_common(page, ctype); - memcg = __mem_cgroup_uncharge_common(page, - MEM_CGROUP_CHARGE_TYPE_SWAPOUT); /* record memcg information */ - if (do_swap_account && memcg) { + if (do_swap_account && swapout && memcg) { swap_cgroup_record(ent, css_id(&memcg->css)); mem_cgroup_get(memcg); } - if (memcg) + if (swapout && memcg) css_put(&memcg->css); } #endif diff --git a/mm/swapfile.c b/mm/swapfile.c index 28faa01cf578..d1ade1a48ee7 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -583,8 +583,9 @@ static int swap_entry_free(struct swap_info_struct *p, swap_list.next = p - swap_info; nr_swap_pages++; p->inuse_pages--; - mem_cgroup_uncharge_swap(ent); } + if (!swap_count(count)) + mem_cgroup_uncharge_swap(ent); return count; } @@ -609,12 +610,19 @@ void swap_free(swp_entry_t entry) void swapcache_free(swp_entry_t entry, struct page *page) { struct swap_info_struct *p; + int ret; - if (page) - mem_cgroup_uncharge_swapcache(page, entry); p = swap_info_get(entry); if (p) { - swap_entry_free(p, entry, SWAP_CACHE); + ret = swap_entry_free(p, entry, SWAP_CACHE); + if (page) { + bool swapout; + if (ret) + swapout = true; /* the end of swap out */ + else + swapout = false; /* no more swap users! */ + mem_cgroup_uncharge_swapcache(page, entry, swapout); + } spin_unlock(&swap_lock); } return; -- cgit v1.2.3 From 22a668d7c3ef833e7d67e9cef587ecc78069d532 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Wed, 17 Jun 2009 16:27:19 -0700 Subject: memcg: fix behavior under memory.limit equals to memsw.limit A user can set memcg.limit_in_bytes == memcg.memsw.limit_in_bytes when the user just want to limit the total size of applications, in other words, not very interested in memory usage itself. In this case, swap-out will be done only by global-LRU. But, under current implementation, memory.limit_in_bytes is checked at first and try_to_free_page() may do swap-out. But, that swap-out is useless for memsw.limit_in_bytes and the thread may hit limit again. This patch tries to fix the current behavior at memory.limit == memsw.limit case. And documentation is updated to explain the behavior of this special case. Signed-off-by: KAMEZAWA Hiroyuki Cc: Daisuke Nishimura Cc: Balbir Singh Cc: Li Zefan Cc: Dhaval Giani Cc: YAMAMOTO Takashi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/cgroups/memory.txt | 17 +++++++++++------ mm/memcontrol.c | 19 +++++++++++++++++++ 2 files changed, 30 insertions(+), 6 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt index 1a608877b14e..af48135bd9b8 100644 --- a/Documentation/cgroups/memory.txt +++ b/Documentation/cgroups/memory.txt @@ -152,14 +152,19 @@ When swap is accounted, following files are added. usage of mem+swap is limited by memsw.limit_in_bytes. -Note: why 'mem+swap' rather than swap. +* why 'mem+swap' rather than swap. The global LRU(kswapd) can swap out arbitrary pages. Swap-out means to move account from memory to swap...there is no change in usage of -mem+swap. - -In other words, when we want to limit the usage of swap without affecting -global LRU, mem+swap limit is better than just limiting swap from OS point -of view. +mem+swap. In other words, when we want to limit the usage of swap without +affecting global LRU, mem+swap limit is better than just limiting swap from +OS point of view. + +* What happens when a cgroup hits memory.memsw.limit_in_bytes +When a cgroup his memory.memsw.limit_in_bytes, it's useless to do swap-out +in this cgroup. Then, swap-out will not be done by cgroup routine and file +caches are dropped. But as mentioned above, global LRU can do swapout memory +from it for sanity of the system's memory management state. You can't forbid +it by cgroup. 2.5 Reclaim diff --git a/mm/memcontrol.c b/mm/memcontrol.c index a83e0395444b..6ceb6f2dbac2 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -177,6 +177,9 @@ struct mem_cgroup { unsigned int swappiness; + /* set when res.limit == memsw.limit */ + bool memsw_is_minimum; + /* * statistics. This must be placed at the end of memcg. */ @@ -847,6 +850,10 @@ static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem, int ret, total = 0; int loop = 0; + /* If memsw_is_minimum==1, swap-out is of-no-use. */ + if (root_mem->memsw_is_minimum) + noswap = true; + while (loop < 2) { victim = mem_cgroup_select_victim(root_mem); if (victim == root_mem) @@ -1752,6 +1759,12 @@ static int mem_cgroup_resize_limit(struct mem_cgroup *memcg, break; } ret = res_counter_set_limit(&memcg->res, val); + if (!ret) { + if (memswlimit == val) + memcg->memsw_is_minimum = true; + else + memcg->memsw_is_minimum = false; + } mutex_unlock(&set_limit_mutex); if (!ret) @@ -1799,6 +1812,12 @@ static int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg, break; } ret = res_counter_set_limit(&memcg->memsw, val); + if (!ret) { + if (memlimit == val) + memcg->memsw_is_minimum = true; + else + memcg->memsw_is_minimum = false; + } mutex_unlock(&set_limit_mutex); if (!ret) -- cgit v1.2.3 From 2ffebca6aa7e1687905c842dd8c5c1e811e574e7 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Wed, 17 Jun 2009 16:27:21 -0700 Subject: memcg: fix lru rotation in isolate_pages Try to fix memcg's lru rotation sanity: make memcg use the same logic as the global LRU does. Now, at __isolate_lru_page() retruns -EBUSY, the page is rotated to the tail of LRU in global LRU's isolate LRU pages. But in memcg, it's not handled. This makes memcg do the same behavior as global LRU and rotate LRU in the page is busy. Signed-off-by: KAMEZAWA Hiroyuki Cc: KOSAKI Motohiro Acked-by: Daisuke Nishimura Cc: Balbir Singh Cc: Mel Gorman Cc: Minchan Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 13 ++++++++++++- mm/vmscan.c | 4 +++- 2 files changed, 15 insertions(+), 2 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 6ceb6f2dbac2..e2fa20dadf40 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -649,6 +649,7 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan, int zid = zone_idx(z); struct mem_cgroup_per_zone *mz; int lru = LRU_FILE * !!file + !!active; + int ret; BUG_ON(!mem_cont); mz = mem_cgroup_zoneinfo(mem_cont, nid, zid); @@ -666,9 +667,19 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan, continue; scan++; - if (__isolate_lru_page(page, mode, file) == 0) { + ret = __isolate_lru_page(page, mode, file); + switch (ret) { + case 0: list_move(&page->lru, dst); + mem_cgroup_del_lru(page); nr_taken++; + break; + case -EBUSY: + /* we don't affect global LRU but rotate in our LRU */ + mem_cgroup_rotate_lru_list(page, page_lru(page)); + break; + default: + break; } } diff --git a/mm/vmscan.c b/mm/vmscan.c index 4139aa52b941..e8fa2d9eb212 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -837,7 +837,6 @@ int __isolate_lru_page(struct page *page, int mode, int file) */ ClearPageLRU(page); ret = 0; - mem_cgroup_del_lru(page); } return ret; @@ -885,12 +884,14 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, switch (__isolate_lru_page(page, mode, file)) { case 0: list_move(&page->lru, dst); + mem_cgroup_del_lru(page); nr_taken++; break; case -EBUSY: /* else it is being freed elsewhere */ list_move(&page->lru, src); + mem_cgroup_rotate_lru_list(page, page_lru(page)); continue; default: @@ -931,6 +932,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, continue; if (__isolate_lru_page(cursor_page, mode, file) == 0) { list_move(&cursor_page->lru, dst); + mem_cgroup_del_lru(page); nr_taken++; scan++; } -- cgit v1.2.3 From 8aa7e847d834ed937a9ad37a0f2ad5b8584c1ab0 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 9 Jul 2009 14:52:32 +0200 Subject: Fix congestion_wait() sync/async vs read/write confusion Commit 1faa16d22877f4839bd433547d770c676d1d964c accidentally broke the bdi congestion wait queue logic, causing us to wait on congestion for WRITE (== 1) when we really wanted BLK_RW_ASYNC (== 0) instead. Signed-off-by: Jens Axboe --- arch/x86/lib/usercopy_32.c | 2 +- drivers/block/pktcdvd.c | 10 ++++++---- drivers/md/dm-crypt.c | 2 +- fs/fat/file.c | 2 +- fs/fuse/dev.c | 8 ++++---- fs/nfs/write.c | 8 +++++--- fs/reiserfs/journal.c | 2 +- fs/xfs/linux-2.6/kmem.c | 4 ++-- fs/xfs/linux-2.6/xfs_buf.c | 2 +- include/linux/backing-dev.h | 6 +++--- include/linux/blkdev.h | 8 ++++---- mm/backing-dev.c | 7 +++---- mm/memcontrol.c | 2 +- mm/page-writeback.c | 8 ++++---- mm/page_alloc.c | 4 ++-- mm/vmscan.c | 8 ++++---- 16 files changed, 43 insertions(+), 40 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c index 7c8ca91bb9ec..1f118d462acc 100644 --- a/arch/x86/lib/usercopy_32.c +++ b/arch/x86/lib/usercopy_32.c @@ -751,7 +751,7 @@ survive: if (retval == -ENOMEM && is_global_init(current)) { up_read(¤t->mm->mmap_sem); - congestion_wait(WRITE, HZ/50); + congestion_wait(BLK_RW_ASYNC, HZ/50); goto survive; } diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 83650e00632d..99a506f619b7 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -1372,8 +1372,10 @@ try_next_bio: wakeup = (pd->write_congestion_on > 0 && pd->bio_queue_size <= pd->write_congestion_off); spin_unlock(&pd->lock); - if (wakeup) - clear_bdi_congested(&pd->disk->queue->backing_dev_info, WRITE); + if (wakeup) { + clear_bdi_congested(&pd->disk->queue->backing_dev_info, + BLK_RW_ASYNC); + } pkt->sleep_time = max(PACKET_WAIT_TIME, 1); pkt_set_state(pkt, PACKET_WAITING_STATE); @@ -2592,10 +2594,10 @@ static int pkt_make_request(struct request_queue *q, struct bio *bio) spin_lock(&pd->lock); if (pd->write_congestion_on > 0 && pd->bio_queue_size >= pd->write_congestion_on) { - set_bdi_congested(&q->backing_dev_info, WRITE); + set_bdi_congested(&q->backing_dev_info, BLK_RW_ASYNC); do { spin_unlock(&pd->lock); - congestion_wait(WRITE, HZ); + congestion_wait(BLK_RW_ASYNC, HZ); spin_lock(&pd->lock); } while(pd->bio_queue_size > pd->write_congestion_off); } diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 9933eb861c71..529e2ba505c3 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -776,7 +776,7 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io) * But don't wait if split was due to the io size restriction */ if (unlikely(out_of_pages)) - congestion_wait(WRITE, HZ/100); + congestion_wait(BLK_RW_ASYNC, HZ/100); /* * With async crypto it is unsafe to share the crypto context diff --git a/fs/fat/file.c b/fs/fat/file.c index b28ea646ff60..f042b965c95c 100644 --- a/fs/fat/file.c +++ b/fs/fat/file.c @@ -134,7 +134,7 @@ static int fat_file_release(struct inode *inode, struct file *filp) if ((filp->f_mode & FMODE_WRITE) && MSDOS_SB(inode->i_sb)->options.flush) { fat_flush_inodes(inode->i_sb, inode, NULL); - congestion_wait(WRITE, HZ/10); + congestion_wait(BLK_RW_ASYNC, HZ/10); } return 0; } diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index f58ecbc416c8..6484eb75acd6 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -286,8 +286,8 @@ __releases(&fc->lock) } if (fc->num_background == FUSE_CONGESTION_THRESHOLD && fc->connected && fc->bdi_initialized) { - clear_bdi_congested(&fc->bdi, READ); - clear_bdi_congested(&fc->bdi, WRITE); + clear_bdi_congested(&fc->bdi, BLK_RW_SYNC); + clear_bdi_congested(&fc->bdi, BLK_RW_ASYNC); } fc->num_background--; fc->active_background--; @@ -414,8 +414,8 @@ static void fuse_request_send_nowait_locked(struct fuse_conn *fc, fc->blocked = 1; if (fc->num_background == FUSE_CONGESTION_THRESHOLD && fc->bdi_initialized) { - set_bdi_congested(&fc->bdi, READ); - set_bdi_congested(&fc->bdi, WRITE); + set_bdi_congested(&fc->bdi, BLK_RW_SYNC); + set_bdi_congested(&fc->bdi, BLK_RW_ASYNC); } list_add_tail(&req->list, &fc->bg_queue); flush_bg_queue(fc); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index ce728829f79a..0a0a2ff767c3 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -202,8 +202,10 @@ static int nfs_set_page_writeback(struct page *page) struct nfs_server *nfss = NFS_SERVER(inode); if (atomic_long_inc_return(&nfss->writeback) > - NFS_CONGESTION_ON_THRESH) - set_bdi_congested(&nfss->backing_dev_info, WRITE); + NFS_CONGESTION_ON_THRESH) { + set_bdi_congested(&nfss->backing_dev_info, + BLK_RW_ASYNC); + } } return ret; } @@ -215,7 +217,7 @@ static void nfs_end_page_writeback(struct page *page) end_page_writeback(page); if (atomic_long_dec_return(&nfss->writeback) < NFS_CONGESTION_OFF_THRESH) - clear_bdi_congested(&nfss->backing_dev_info, WRITE); + clear_bdi_congested(&nfss->backing_dev_info, BLK_RW_ASYNC); } /* diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c index 77f5bb746bf0..90622200b39c 100644 --- a/fs/reiserfs/journal.c +++ b/fs/reiserfs/journal.c @@ -997,7 +997,7 @@ static int reiserfs_async_progress_wait(struct super_block *s) DEFINE_WAIT(wait); struct reiserfs_journal *j = SB_JOURNAL(s); if (atomic_read(&j->j_async_throttle)) - congestion_wait(WRITE, HZ / 10); + congestion_wait(BLK_RW_ASYNC, HZ / 10); return 0; } diff --git a/fs/xfs/linux-2.6/kmem.c b/fs/xfs/linux-2.6/kmem.c index 1cd3b55ee3d2..2d3f90afe5f1 100644 --- a/fs/xfs/linux-2.6/kmem.c +++ b/fs/xfs/linux-2.6/kmem.c @@ -53,7 +53,7 @@ kmem_alloc(size_t size, unsigned int __nocast flags) printk(KERN_ERR "XFS: possible memory allocation " "deadlock in %s (mode:0x%x)\n", __func__, lflags); - congestion_wait(WRITE, HZ/50); + congestion_wait(BLK_RW_ASYNC, HZ/50); } while (1); } @@ -130,7 +130,7 @@ kmem_zone_alloc(kmem_zone_t *zone, unsigned int __nocast flags) printk(KERN_ERR "XFS: possible memory allocation " "deadlock in %s (mode:0x%x)\n", __func__, lflags); - congestion_wait(WRITE, HZ/50); + congestion_wait(BLK_RW_ASYNC, HZ/50); } while (1); } diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c index 1418b916fc27..0c93c7ef3d18 100644 --- a/fs/xfs/linux-2.6/xfs_buf.c +++ b/fs/xfs/linux-2.6/xfs_buf.c @@ -412,7 +412,7 @@ _xfs_buf_lookup_pages( XFS_STATS_INC(xb_page_retries); xfsbufd_wakeup(0, gfp_mask); - congestion_wait(WRITE, HZ/50); + congestion_wait(BLK_RW_ASYNC, HZ/50); goto retry; } diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 0ec2c594868e..3a52a63c1351 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -229,9 +229,9 @@ static inline int bdi_rw_congested(struct backing_dev_info *bdi) (1 << BDI_async_congested)); } -void clear_bdi_congested(struct backing_dev_info *bdi, int rw); -void set_bdi_congested(struct backing_dev_info *bdi, int rw); -long congestion_wait(int rw, long timeout); +void clear_bdi_congested(struct backing_dev_info *bdi, int sync); +void set_bdi_congested(struct backing_dev_info *bdi, int sync); +long congestion_wait(int sync, long timeout); static inline bool bdi_cap_writeback_dirty(struct backing_dev_info *bdi) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 49ae07951d55..bb3d39978701 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -779,18 +779,18 @@ extern int sg_scsi_ioctl(struct request_queue *, struct gendisk *, fmode_t, * congested queues, and wake up anyone who was waiting for requests to be * put back. */ -static inline void blk_clear_queue_congested(struct request_queue *q, int rw) +static inline void blk_clear_queue_congested(struct request_queue *q, int sync) { - clear_bdi_congested(&q->backing_dev_info, rw); + clear_bdi_congested(&q->backing_dev_info, sync); } /* * A queue has just entered congestion. Flag that in the queue's VM-visible * state flags and increment the global gounter of congested queues. */ -static inline void blk_set_queue_congested(struct request_queue *q, int rw) +static inline void blk_set_queue_congested(struct request_queue *q, int sync) { - set_bdi_congested(&q->backing_dev_info, rw); + set_bdi_congested(&q->backing_dev_info, sync); } extern void blk_start_queue(struct request_queue *q); diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 493b468a5035..c86edd244294 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -283,7 +283,6 @@ static wait_queue_head_t congestion_wqh[2] = { __WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[1]) }; - void clear_bdi_congested(struct backing_dev_info *bdi, int sync) { enum bdi_state bit; @@ -308,18 +307,18 @@ EXPORT_SYMBOL(set_bdi_congested); /** * congestion_wait - wait for a backing_dev to become uncongested - * @rw: READ or WRITE + * @sync: SYNC or ASYNC IO * @timeout: timeout in jiffies * * Waits for up to @timeout jiffies for a backing_dev (any backing_dev) to exit * write congestion. If no backing_devs are congested then just wait for the * next write to be completed. */ -long congestion_wait(int rw, long timeout) +long congestion_wait(int sync, long timeout) { long ret; DEFINE_WAIT(wait); - wait_queue_head_t *wqh = &congestion_wqh[rw]; + wait_queue_head_t *wqh = &congestion_wqh[sync]; prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE); ret = io_schedule_timeout(timeout); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index e2fa20dadf40..e717964cb5a0 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1973,7 +1973,7 @@ try_to_free: if (!progress) { nr_retries--; /* maybe some writeback is necessary */ - congestion_wait(WRITE, HZ/10); + congestion_wait(BLK_RW_ASYNC, HZ/10); } } diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 7687879253b9..81627ebcd313 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -575,7 +575,7 @@ static void balance_dirty_pages(struct address_space *mapping) if (pages_written >= write_chunk) break; /* We've done our duty */ - congestion_wait(WRITE, HZ/10); + congestion_wait(BLK_RW_ASYNC, HZ/10); } if (bdi_nr_reclaimable + bdi_nr_writeback < bdi_thresh && @@ -669,7 +669,7 @@ void throttle_vm_writeout(gfp_t gfp_mask) if (global_page_state(NR_UNSTABLE_NFS) + global_page_state(NR_WRITEBACK) <= dirty_thresh) break; - congestion_wait(WRITE, HZ/10); + congestion_wait(BLK_RW_ASYNC, HZ/10); /* * The caller might hold locks which can prevent IO completion @@ -715,7 +715,7 @@ static void background_writeout(unsigned long _min_pages) if (wbc.nr_to_write > 0 || wbc.pages_skipped > 0) { /* Wrote less than expected */ if (wbc.encountered_congestion || wbc.more_io) - congestion_wait(WRITE, HZ/10); + congestion_wait(BLK_RW_ASYNC, HZ/10); else break; } @@ -787,7 +787,7 @@ static void wb_kupdate(unsigned long arg) writeback_inodes(&wbc); if (wbc.nr_to_write > 0) { if (wbc.encountered_congestion || wbc.more_io) - congestion_wait(WRITE, HZ/10); + congestion_wait(BLK_RW_ASYNC, HZ/10); else break; /* All the old data is written */ } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index ad7cd1c56b07..a35eeab2724c 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1666,7 +1666,7 @@ __alloc_pages_high_priority(gfp_t gfp_mask, unsigned int order, preferred_zone, migratetype); if (!page && gfp_mask & __GFP_NOFAIL) - congestion_wait(WRITE, HZ/50); + congestion_wait(BLK_RW_ASYNC, HZ/50); } while (!page && (gfp_mask & __GFP_NOFAIL)); return page; @@ -1831,7 +1831,7 @@ rebalance: pages_reclaimed += did_some_progress; if (should_alloc_retry(gfp_mask, order, pages_reclaimed)) { /* Wait for some write requests to complete then retry */ - congestion_wait(WRITE, HZ/50); + congestion_wait(BLK_RW_ASYNC, HZ/50); goto rebalance; } diff --git a/mm/vmscan.c b/mm/vmscan.c index 54155268dfca..dea7abd31098 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1104,7 +1104,7 @@ static unsigned long shrink_inactive_list(unsigned long max_scan, */ if (nr_freed < nr_taken && !current_is_kswapd() && lumpy_reclaim) { - congestion_wait(WRITE, HZ/10); + congestion_wait(BLK_RW_ASYNC, HZ/10); /* * The attempt at page out may have made some @@ -1721,7 +1721,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, /* Take a nap, wait for some writeback to complete */ if (sc->nr_scanned && priority < DEF_PRIORITY - 2) - congestion_wait(WRITE, HZ/10); + congestion_wait(BLK_RW_ASYNC, HZ/10); } /* top priority shrink_zones still had more to do? don't OOM, then */ if (!sc->all_unreclaimable && scanning_global_lru(sc)) @@ -1960,7 +1960,7 @@ loop_again: * another pass across the zones. */ if (total_scanned && priority < DEF_PRIORITY - 2) - congestion_wait(WRITE, HZ/10); + congestion_wait(BLK_RW_ASYNC, HZ/10); /* * We do this so kswapd doesn't build up large priorities for @@ -2233,7 +2233,7 @@ unsigned long shrink_all_memory(unsigned long nr_pages) goto out; if (sc.nr_scanned && prio < DEF_PRIORITY - 2) - congestion_wait(WRITE, HZ / 10); + congestion_wait(BLK_RW_ASYNC, HZ / 10); } } -- cgit v1.2.3 From 887032670d47366a8c8f25396ea7c14b7b2cc620 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Wed, 29 Jul 2009 15:04:06 -0700 Subject: cgroup avoid permanent sleep at rmdir After commit ec64f51545fffbc4cb968f0cea56341a4b07e85a ("cgroup: fix frequent -EBUSY at rmdir"), cgroup's rmdir (especially against memcg) doesn't return -EBUSY by temporary ref counts. That commit expects all refs after pre_destroy() is temporary but...it wasn't. Then, rmdir can wait permanently. This patch tries to fix that and change followings. - set CGRP_WAIT_ON_RMDIR flag before pre_destroy(). - clear CGRP_WAIT_ON_RMDIR flag when the subsys finds racy case. if there are sleeping ones, wakes them up. - rmdir() sleeps only when CGRP_WAIT_ON_RMDIR flag is set. Tested-by: Daisuke Nishimura Reported-by: Daisuke Nishimura Reviewed-by: Paul Menage Acked-by: Balbir Sigh Signed-off-by: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cgroup.h | 17 ++++++++++++++++ kernel/cgroup.c | 55 ++++++++++++++++++++++++++++++++++---------------- mm/memcontrol.c | 23 ++++++++++++++++++--- 3 files changed, 75 insertions(+), 20 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 20411d2876f8..90bba9e62286 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -362,6 +362,23 @@ int cgroup_task_count(const struct cgroup *cgrp); /* Return true if cgrp is a descendant of the task's cgroup */ int cgroup_is_descendant(const struct cgroup *cgrp, struct task_struct *task); +/* + * When the subsys has to access css and may add permanent refcnt to css, + * it should take care of racy conditions with rmdir(). Following set of + * functions, is for stop/restart rmdir if necessary. + * Because these will call css_get/put, "css" should be alive css. + * + * cgroup_exclude_rmdir(); + * ...do some jobs which may access arbitrary empty cgroup + * cgroup_release_and_wakeup_rmdir(); + * + * When someone removes a cgroup while cgroup_exclude_rmdir() holds it, + * it sleeps and cgroup_release_and_wakeup_rmdir() will wake him up. + */ + +void cgroup_exclude_rmdir(struct cgroup_subsys_state *css); +void cgroup_release_and_wakeup_rmdir(struct cgroup_subsys_state *css); + /* * Control Group subsystem type. * See Documentation/cgroups/cgroups.txt for details diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 250dac05680f..b6eadfe30e7b 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -735,16 +735,28 @@ static void cgroup_d_remove_dir(struct dentry *dentry) * reference to css->refcnt. In general, this refcnt is expected to goes down * to zero, soon. * - * CGRP_WAIT_ON_RMDIR flag is modified under cgroup's inode->i_mutex; + * CGRP_WAIT_ON_RMDIR flag is set under cgroup's inode->i_mutex; */ DECLARE_WAIT_QUEUE_HEAD(cgroup_rmdir_waitq); -static void cgroup_wakeup_rmdir_waiters(const struct cgroup *cgrp) +static void cgroup_wakeup_rmdir_waiter(struct cgroup *cgrp) { - if (unlikely(test_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags))) + if (unlikely(test_and_clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags))) wake_up_all(&cgroup_rmdir_waitq); } +void cgroup_exclude_rmdir(struct cgroup_subsys_state *css) +{ + css_get(css); +} + +void cgroup_release_and_wakeup_rmdir(struct cgroup_subsys_state *css) +{ + cgroup_wakeup_rmdir_waiter(css->cgroup); + css_put(css); +} + + static int rebind_subsystems(struct cgroupfs_root *root, unsigned long final_bits) { @@ -1359,7 +1371,7 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk) * wake up rmdir() waiter. the rmdir should fail since the cgroup * is no longer empty. */ - cgroup_wakeup_rmdir_waiters(cgrp); + cgroup_wakeup_rmdir_waiter(cgrp); return 0; } @@ -2743,34 +2755,43 @@ again: } mutex_unlock(&cgroup_mutex); + /* + * In general, subsystem has no css->refcnt after pre_destroy(). But + * in racy cases, subsystem may have to get css->refcnt after + * pre_destroy() and it makes rmdir return with -EBUSY. This sometimes + * make rmdir return -EBUSY too often. To avoid that, we use waitqueue + * for cgroup's rmdir. CGRP_WAIT_ON_RMDIR is for synchronizing rmdir + * and subsystem's reference count handling. Please see css_get/put + * and css_tryget() and cgroup_wakeup_rmdir_waiter() implementation. + */ + set_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags); + /* * Call pre_destroy handlers of subsys. Notify subsystems * that rmdir() request comes. */ ret = cgroup_call_pre_destroy(cgrp); - if (ret) + if (ret) { + clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags); return ret; + } mutex_lock(&cgroup_mutex); parent = cgrp->parent; if (atomic_read(&cgrp->count) || !list_empty(&cgrp->children)) { + clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags); mutex_unlock(&cgroup_mutex); return -EBUSY; } - /* - * css_put/get is provided for subsys to grab refcnt to css. In typical - * case, subsystem has no reference after pre_destroy(). But, under - * hierarchy management, some *temporal* refcnt can be hold. - * To avoid returning -EBUSY to a user, waitqueue is used. If subsys - * is really busy, it should return -EBUSY at pre_destroy(). wake_up - * is called when css_put() is called and refcnt goes down to 0. - */ - set_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags); prepare_to_wait(&cgroup_rmdir_waitq, &wait, TASK_INTERRUPTIBLE); - if (!cgroup_clear_css_refs(cgrp)) { mutex_unlock(&cgroup_mutex); - schedule(); + /* + * Because someone may call cgroup_wakeup_rmdir_waiter() before + * prepare_to_wait(), we need to check this flag. + */ + if (test_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags)) + schedule(); finish_wait(&cgroup_rmdir_waitq, &wait); clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags); if (signal_pending(current)) @@ -3342,7 +3363,7 @@ void __css_put(struct cgroup_subsys_state *css) set_bit(CGRP_RELEASABLE, &cgrp->flags); check_for_release(cgrp); } - cgroup_wakeup_rmdir_waiters(cgrp); + cgroup_wakeup_rmdir_waiter(cgrp); } rcu_read_unlock(); } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index e717964cb5a0..fd4529d86de5 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1207,6 +1207,12 @@ static int mem_cgroup_move_account(struct page_cgroup *pc, ret = 0; out: unlock_page_cgroup(pc); + /* + * We charges against "to" which may not have any tasks. Then, "to" + * can be under rmdir(). But in current implementation, caller of + * this function is just force_empty() and it's garanteed that + * "to" is never removed. So, we don't check rmdir status here. + */ return ret; } @@ -1428,6 +1434,7 @@ __mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr, return; if (!ptr) return; + cgroup_exclude_rmdir(&ptr->css); pc = lookup_page_cgroup(page); mem_cgroup_lru_del_before_commit_swapcache(page); __mem_cgroup_commit_charge(ptr, pc, ctype); @@ -1457,8 +1464,12 @@ __mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr, } rcu_read_unlock(); } - /* add this page(page_cgroup) to the LRU we want. */ - + /* + * At swapin, we may charge account against cgroup which has no tasks. + * So, rmdir()->pre_destroy() can be called while we do this charge. + * In that case, we need to call pre_destroy() again. check it here. + */ + cgroup_release_and_wakeup_rmdir(&ptr->css); } void mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr) @@ -1664,7 +1675,7 @@ void mem_cgroup_end_migration(struct mem_cgroup *mem, if (!mem) return; - + cgroup_exclude_rmdir(&mem->css); /* at migration success, oldpage->mapping is NULL. */ if (oldpage->mapping) { target = oldpage; @@ -1704,6 +1715,12 @@ void mem_cgroup_end_migration(struct mem_cgroup *mem, */ if (ctype == MEM_CGROUP_CHARGE_TYPE_MAPPED) mem_cgroup_uncharge_page(target); + /* + * At migration, we may charge account against cgroup which has no tasks + * So, rmdir()->pre_destroy() can be called while we do this charge. + * In that case, we need to call pre_destroy() again. check it here. + */ + cgroup_release_and_wakeup_rmdir(&mem->css); } /* -- cgit v1.2.3