This is a note to let you know that I've just added the patch titled mm: memcg: make sure memory.events is uptodate when waking pollers to the 4.14-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary The filename of the patch is: mm-memcg-make-sure-memory.events-is-uptodate-when-waking-pollers.patch and it can be found in the queue-4.14 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable@xxxxxxxxxxxxxxx> know about it. >From foo@baz Sat Apr 3 10:50:40 AM CEST 2021 From: Frank van der Linden <fllinden@xxxxxxxxxx> Date: Tue, 30 Mar 2021 18:19:07 +0000 Subject: mm: memcg: make sure memory.events is uptodate when waking pollers To: <stable@xxxxxxxxxxxxxxx> Cc: <fllinden@xxxxxxxxxx> Message-ID: <20210330181910.15378-3-fllinden@xxxxxxxxxx> From: Frank van der Linden <fllinden@xxxxxxxxxx> From: Johannes Weiner <hannes@xxxxxxxxxxx> commit e27be240df53f1a20c659168e722b5d9f16cc7f4 upstream. Commit a983b5ebee57 ("mm: memcontrol: fix excessive complexity in memory.stat reporting") added per-cpu drift to all memory cgroup stats and events shown in memory.stat and memory.events. For memory.stat this is acceptable. But memory.events issues file notifications, and somebody polling the file for changes will be confused when the counters in it are unchanged after a wakeup. Luckily, the events in memory.events - MEMCG_LOW, MEMCG_HIGH, MEMCG_MAX, MEMCG_OOM - are sufficiently rare and high-level that we don't need per-cpu buffering for them: MEMCG_HIGH and MEMCG_MAX would be the most frequent, but they're counting invocations of reclaim, which is a complex operation that touches many shared cachelines. This splits memory.events from the generic VM events and tracks them in their own, unbuffered atomic counters. That's also cleaner, as it eliminates the ugly enum nesting of VM and cgroup events. [hannes@xxxxxxxxxxx: "array subscript is above array bounds"] Link: http://lkml.kernel.org/r/20180406155441.GA20806@xxxxxxxxxxx Link: http://lkml.kernel.org/r/20180405175507.GA24817@xxxxxxxxxxx Fixes: a983b5ebee57 ("mm: memcontrol: fix excessive complexity in memory.stat reporting") Signed-off-by: Johannes Weiner <hannes@xxxxxxxxxxx> Reported-by: Tejun Heo <tj@xxxxxxxxxx> Acked-by: Tejun Heo <tj@xxxxxxxxxx> Acked-by: Michal Hocko <mhocko@xxxxxxxx> Cc: Vladimir Davydov <vdavydov.dev@xxxxxxxxx> Cc: Roman Gushchin <guro@xxxxxx> Cc: Rik van Riel <riel@xxxxxxxxxxx> Cc: Stephen Rothwell <sfr@xxxxxxxxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx> Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx> --- include/linux/memcontrol.h | 35 ++++++++++++++++++----------------- mm/memcontrol.c | 28 ++++++++++++++++------------ mm/vmscan.c | 2 +- 3 files changed, 35 insertions(+), 30 deletions(-) --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -48,13 +48,12 @@ enum memcg_stat_item { MEMCG_NR_STAT, }; -/* Cgroup-specific events, on top of universal VM events */ -enum memcg_event_item { - MEMCG_LOW = NR_VM_EVENT_ITEMS, +enum memcg_memory_event { + MEMCG_LOW, MEMCG_HIGH, MEMCG_MAX, MEMCG_OOM, - MEMCG_NR_EVENTS, + MEMCG_NR_MEMORY_EVENTS, }; struct mem_cgroup_reclaim_cookie { @@ -88,7 +87,7 @@ enum mem_cgroup_events_target { struct mem_cgroup_stat_cpu { long count[MEMCG_NR_STAT]; - unsigned long events[MEMCG_NR_EVENTS]; + unsigned long events[NR_VM_EVENT_ITEMS]; unsigned long nr_page_events; unsigned long targets[MEM_CGROUP_NTARGETS]; }; @@ -202,7 +201,8 @@ struct mem_cgroup { /* OOM-Killer disable */ int oom_kill_disable; - /* handle for "memory.events" */ + /* memory.events */ + atomic_long_t memory_events[MEMCG_NR_MEMORY_EVENTS]; struct cgroup_file events_file; /* protect arrays of thresholds */ @@ -231,9 +231,10 @@ struct mem_cgroup { struct task_struct *move_lock_task; unsigned long move_lock_flags; + /* memory.stat */ struct mem_cgroup_stat_cpu __percpu *stat_cpu; atomic_long_t stat[MEMCG_NR_STAT]; - atomic_long_t events[MEMCG_NR_EVENTS]; + atomic_long_t events[NR_VM_EVENT_ITEMS]; unsigned long socket_pressure; @@ -645,9 +646,9 @@ unsigned long mem_cgroup_soft_limit_recl gfp_t gfp_mask, unsigned long *total_scanned); -/* idx can be of type enum memcg_event_item or vm_event_item */ static inline void __count_memcg_events(struct mem_cgroup *memcg, - int idx, unsigned long count) + enum vm_event_item idx, + unsigned long count) { unsigned long x; @@ -663,7 +664,8 @@ static inline void __count_memcg_events( } static inline void count_memcg_events(struct mem_cgroup *memcg, - int idx, unsigned long count) + enum vm_event_item idx, + unsigned long count) { unsigned long flags; @@ -672,9 +674,8 @@ static inline void count_memcg_events(st local_irq_restore(flags); } -/* idx can be of type enum memcg_event_item or vm_event_item */ static inline void count_memcg_page_event(struct page *page, - int idx) + enum vm_event_item idx) { if (page->mem_cgroup) count_memcg_events(page->mem_cgroup, idx, 1); @@ -698,10 +699,10 @@ static inline void count_memcg_event_mm( rcu_read_unlock(); } -static inline void mem_cgroup_event(struct mem_cgroup *memcg, - enum memcg_event_item event) +static inline void memcg_memory_event(struct mem_cgroup *memcg, + enum memcg_memory_event event) { - count_memcg_events(memcg, event, 1); + atomic_long_inc(&memcg->memory_events[event]); cgroup_file_notify(&memcg->events_file); } @@ -721,8 +722,8 @@ static inline bool mem_cgroup_disabled(v return true; } -static inline void mem_cgroup_event(struct mem_cgroup *memcg, - enum memcg_event_item event) +static inline void memcg_memory_event(struct mem_cgroup *memcg, + enum memcg_memory_event event) { } --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1872,7 +1872,7 @@ static int memcg_hotplug_cpu_dead(unsign } } - for (i = 0; i < MEMCG_NR_EVENTS; i++) { + for (i = 0; i < NR_VM_EVENT_ITEMS; i++) { long x; x = this_cpu_xchg(memcg->stat_cpu->events[i], 0); @@ -1891,7 +1891,7 @@ static void reclaim_high(struct mem_cgro do { if (page_counter_read(&memcg->memory) <= memcg->high) continue; - mem_cgroup_event(memcg, MEMCG_HIGH); + memcg_memory_event(memcg, MEMCG_HIGH); try_to_free_mem_cgroup_pages(memcg, nr_pages, gfp_mask, true); } while ((memcg = parent_mem_cgroup(memcg))); } @@ -1982,7 +1982,7 @@ retry: if (!gfpflags_allow_blocking(gfp_mask)) goto nomem; - mem_cgroup_event(mem_over_limit, MEMCG_MAX); + memcg_memory_event(mem_over_limit, MEMCG_MAX); nr_reclaimed = try_to_free_mem_cgroup_pages(mem_over_limit, nr_pages, gfp_mask, may_swap); @@ -2025,7 +2025,7 @@ retry: if (fatal_signal_pending(current)) goto force; - mem_cgroup_event(mem_over_limit, MEMCG_OOM); + memcg_memory_event(mem_over_limit, MEMCG_OOM); mem_cgroup_oom(mem_over_limit, gfp_mask, get_order(nr_pages * PAGE_SIZE)); @@ -2790,10 +2790,10 @@ static void tree_events(struct mem_cgrou struct mem_cgroup *iter; int i; - memset(events, 0, sizeof(*events) * MEMCG_NR_EVENTS); + memset(events, 0, sizeof(*events) * NR_VM_EVENT_ITEMS); for_each_mem_cgroup_tree(iter, memcg) { - for (i = 0; i < MEMCG_NR_EVENTS; i++) + for (i = 0; i < NR_VM_EVENT_ITEMS; i++) events[i] += memcg_sum_events(iter, i); } } @@ -5299,7 +5299,7 @@ static ssize_t memory_max_write(struct k continue; } - mem_cgroup_event(memcg, MEMCG_OOM); + memcg_memory_event(memcg, MEMCG_OOM); if (!mem_cgroup_out_of_memory(memcg, GFP_KERNEL, 0)) break; } @@ -5312,10 +5312,14 @@ static int memory_events_show(struct seq { struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); - seq_printf(m, "low %lu\n", memcg_sum_events(memcg, MEMCG_LOW)); - seq_printf(m, "high %lu\n", memcg_sum_events(memcg, MEMCG_HIGH)); - seq_printf(m, "max %lu\n", memcg_sum_events(memcg, MEMCG_MAX)); - seq_printf(m, "oom %lu\n", memcg_sum_events(memcg, MEMCG_OOM)); + seq_printf(m, "low %lu\n", + atomic_long_read(&memcg->memory_events[MEMCG_LOW])); + seq_printf(m, "high %lu\n", + atomic_long_read(&memcg->memory_events[MEMCG_HIGH])); + seq_printf(m, "max %lu\n", + atomic_long_read(&memcg->memory_events[MEMCG_MAX])); + seq_printf(m, "oom %lu\n", + atomic_long_read(&memcg->memory_events[MEMCG_OOM])); seq_printf(m, "oom_kill %lu\n", memcg_sum_events(memcg, OOM_KILL)); return 0; @@ -5325,7 +5329,7 @@ static int memory_stat_show(struct seq_f { struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); unsigned long stat[MEMCG_NR_STAT]; - unsigned long events[MEMCG_NR_EVENTS]; + unsigned long events[NR_VM_EVENT_ITEMS]; int i; /* --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2628,7 +2628,7 @@ static bool shrink_node(pg_data_t *pgdat sc->memcg_low_skipped = 1; continue; } - mem_cgroup_event(memcg, MEMCG_LOW); + memcg_memory_event(memcg, MEMCG_LOW); } reclaimed = sc->nr_reclaimed; Patches currently in stable-queue which might be from fllinden@xxxxxxxxxx are queue-4.14/mm-writeback-use-exact-memcg-dirty-counts.patch queue-4.14/mem_cgroup-make-sure-moving_account-move_lock_task-and-stat_cpu-in-the-same-cacheline.patch queue-4.14/mm-memcontrol-fix-nr_writeback-leak-in-memcg-and-system-stats.patch queue-4.14/mm-memcg-make-sure-memory.events-is-uptodate-when-waking-pollers.patch queue-4.14/mm-fix-oom_kill-event-handling.patch