From 2bfd36374edd9ed7f2ebf66cacebedf7273901cb Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Tue, 4 May 2021 18:36:11 -0700 Subject: mm: vmscan: consolidate shrinker_maps handling code The shrinker map management is not purely memcg specific, it is at the intersection between memory cgroup and shrinkers. It's allocation and assignment of a structure, and the only memcg bit is the map is being stored in a memcg structure. So move the shrinker_maps handling code into vmscan.c for tighter integration with shrinker code, and remove the "memcg_" prefix. There is no functional change. Link: https://lkml.kernel.org/r/20210311190845.9708-3-shy828301@gmail.com Signed-off-by: Yang Shi Acked-by: Vlastimil Babka Acked-by: Kirill Tkhai Acked-by: Roman Gushchin Reviewed-by: Shakeel Butt Cc: Dave Chinner Cc: Johannes Weiner Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'include/linux/memcontrol.h') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 5904716f29ba..7dbd2c9bad32 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1610,10 +1610,9 @@ static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) return false; } -extern int memcg_expand_shrinker_maps(int new_id); - -extern void memcg_set_shrinker_bit(struct mem_cgroup *memcg, - int nid, int shrinker_id); +int alloc_shrinker_maps(struct mem_cgroup *memcg); +void free_shrinker_maps(struct mem_cgroup *memcg); +void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id); #else #define mem_cgroup_sockets_enabled 0 static inline void mem_cgroup_sk_alloc(struct sock *sk) { }; @@ -1623,8 +1622,8 @@ static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) return false; } -static inline void memcg_set_shrinker_bit(struct mem_cgroup *memcg, - int nid, int shrinker_id) +static inline void set_shrinker_bit(struct mem_cgroup *memcg, + int nid, int shrinker_id) { } #endif -- cgit v1.2.3 From e4262c4f51d6373447c9d89093f49ff6b1e607be Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Tue, 4 May 2021 18:36:23 -0700 Subject: mm: memcontrol: rename shrinker_map to shrinker_info The following patch is going to add nr_deferred into shrinker_map, the change will make shrinker_map not only include map anymore, so rename it to "memcg_shrinker_info". And this should make the patch adding nr_deferred cleaner and readable and make review easier. Also remove the "memcg_" prefix. Link: https://lkml.kernel.org/r/20210311190845.9708-7-shy828301@gmail.com Signed-off-by: Yang Shi Acked-by: Vlastimil Babka Acked-by: Kirill Tkhai Acked-by: Roman Gushchin Reviewed-by: Shakeel Butt Cc: Dave Chinner Cc: Johannes Weiner Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 8 +++---- mm/memcontrol.c | 6 ++--- mm/vmscan.c | 58 +++++++++++++++++++++++----------------------- 3 files changed, 36 insertions(+), 36 deletions(-) (limited to 'include/linux/memcontrol.h') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 7dbd2c9bad32..6cd800fe9a67 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -117,7 +117,7 @@ struct batched_lruvec_stat { * Bitmap of shrinker::id corresponding to memcg-aware shrinkers, * which have elements charged to this memcg. */ -struct memcg_shrinker_map { +struct shrinker_info { struct rcu_head rcu; unsigned long map[]; }; @@ -145,7 +145,7 @@ struct mem_cgroup_per_node { struct mem_cgroup_reclaim_iter iter; - struct memcg_shrinker_map __rcu *shrinker_map; + struct shrinker_info __rcu *shrinker_info; struct rb_node tree_node; /* RB tree node */ unsigned long usage_in_excess;/* Set to the value by which */ @@ -1610,8 +1610,8 @@ static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) return false; } -int alloc_shrinker_maps(struct mem_cgroup *memcg); -void free_shrinker_maps(struct mem_cgroup *memcg); +int alloc_shrinker_info(struct mem_cgroup *memcg); +void free_shrinker_info(struct mem_cgroup *memcg); void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id); #else #define mem_cgroup_sockets_enabled 0 diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 09fd17ba6de2..36f31d611dea 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -5118,11 +5118,11 @@ static int mem_cgroup_css_online(struct cgroup_subsys_state *css) struct mem_cgroup *memcg = mem_cgroup_from_css(css); /* - * A memcg must be visible for expand_shrinker_maps() + * A memcg must be visible for expand_shrinker_info() * by the time the maps are allocated. So, we allocate maps * here, when for_each_mem_cgroup() can't skip it. */ - if (alloc_shrinker_maps(memcg)) { + if (alloc_shrinker_info(memcg)) { mem_cgroup_id_remove(memcg); return -ENOMEM; } @@ -5186,7 +5186,7 @@ static void mem_cgroup_css_free(struct cgroup_subsys_state *css) vmpressure_cleanup(&memcg->vmpressure); cancel_work_sync(&memcg->high_work); mem_cgroup_remove_from_trees(memcg); - free_shrinker_maps(memcg); + free_shrinker_info(memcg); memcg_free_kmem(memcg); mem_cgroup_free(memcg); } diff --git a/mm/vmscan.c b/mm/vmscan.c index aa99a835cf89..518084ce8757 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -192,16 +192,16 @@ static inline int shrinker_map_size(int nr_items) return (DIV_ROUND_UP(nr_items, BITS_PER_LONG) * sizeof(unsigned long)); } -static int expand_one_shrinker_map(struct mem_cgroup *memcg, - int size, int old_size) +static int expand_one_shrinker_info(struct mem_cgroup *memcg, + int size, int old_size) { - struct memcg_shrinker_map *new, *old; + struct shrinker_info *new, *old; struct mem_cgroup_per_node *pn; int nid; for_each_node(nid) { pn = memcg->nodeinfo[nid]; - old = rcu_dereference_protected(pn->shrinker_map, true); + old = rcu_dereference_protected(pn->shrinker_info, true); /* Not yet online memcg */ if (!old) return 0; @@ -214,17 +214,17 @@ static int expand_one_shrinker_map(struct mem_cgroup *memcg, memset(new->map, (int)0xff, old_size); memset((void *)new->map + old_size, 0, size - old_size); - rcu_assign_pointer(pn->shrinker_map, new); + rcu_assign_pointer(pn->shrinker_info, new); kvfree_rcu(old, rcu); } return 0; } -void free_shrinker_maps(struct mem_cgroup *memcg) +void free_shrinker_info(struct mem_cgroup *memcg) { struct mem_cgroup_per_node *pn; - struct memcg_shrinker_map *map; + struct shrinker_info *info; int nid; if (mem_cgroup_is_root(memcg)) @@ -232,15 +232,15 @@ void free_shrinker_maps(struct mem_cgroup *memcg) for_each_node(nid) { pn = memcg->nodeinfo[nid]; - map = rcu_dereference_protected(pn->shrinker_map, true); - kvfree(map); - rcu_assign_pointer(pn->shrinker_map, NULL); + info = rcu_dereference_protected(pn->shrinker_info, true); + kvfree(info); + rcu_assign_pointer(pn->shrinker_info, NULL); } } -int alloc_shrinker_maps(struct mem_cgroup *memcg) +int alloc_shrinker_info(struct mem_cgroup *memcg) { - struct memcg_shrinker_map *map; + struct shrinker_info *info; int nid, size, ret = 0; if (mem_cgroup_is_root(memcg)) @@ -249,20 +249,20 @@ int alloc_shrinker_maps(struct mem_cgroup *memcg) down_write(&shrinker_rwsem); size = shrinker_map_size(shrinker_nr_max); for_each_node(nid) { - map = kvzalloc_node(sizeof(*map) + size, GFP_KERNEL, nid); - if (!map) { - free_shrinker_maps(memcg); + info = kvzalloc_node(sizeof(*info) + size, GFP_KERNEL, nid); + if (!info) { + free_shrinker_info(memcg); ret = -ENOMEM; break; } - rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_map, map); + rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_info, info); } up_write(&shrinker_rwsem); return ret; } -static int expand_shrinker_maps(int new_id) +static int expand_shrinker_info(int new_id) { int size, old_size, ret = 0; int new_nr_max = new_id + 1; @@ -282,7 +282,7 @@ static int expand_shrinker_maps(int new_id) do { if (mem_cgroup_is_root(memcg)) continue; - ret = expand_one_shrinker_map(memcg, size, old_size); + ret = expand_one_shrinker_info(memcg, size, old_size); if (ret) { mem_cgroup_iter_break(NULL, memcg); goto out; @@ -298,13 +298,13 @@ out: void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id) { if (shrinker_id >= 0 && memcg && !mem_cgroup_is_root(memcg)) { - struct memcg_shrinker_map *map; + struct shrinker_info *info; rcu_read_lock(); - map = rcu_dereference(memcg->nodeinfo[nid]->shrinker_map); + info = rcu_dereference(memcg->nodeinfo[nid]->shrinker_info); /* Pairs with smp mb in shrink_slab() */ smp_mb__before_atomic(); - set_bit(shrinker_id, map->map); + set_bit(shrinker_id, info->map); rcu_read_unlock(); } } @@ -335,7 +335,7 @@ static int prealloc_memcg_shrinker(struct shrinker *shrinker) goto unlock; if (id >= shrinker_nr_max) { - if (expand_shrinker_maps(id)) { + if (expand_shrinker_info(id)) { idr_remove(&shrinker_idr, id); goto unlock; } @@ -665,7 +665,7 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, int priority) { - struct memcg_shrinker_map *map; + struct shrinker_info *info; unsigned long ret, freed = 0; int i; @@ -675,12 +675,12 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, if (!down_read_trylock(&shrinker_rwsem)) return 0; - map = rcu_dereference_protected(memcg->nodeinfo[nid]->shrinker_map, - true); - if (unlikely(!map)) + info = rcu_dereference_protected(memcg->nodeinfo[nid]->shrinker_info, + true); + if (unlikely(!info)) goto unlock; - for_each_set_bit(i, map->map, shrinker_nr_max) { + for_each_set_bit(i, info->map, shrinker_nr_max) { struct shrink_control sc = { .gfp_mask = gfp_mask, .nid = nid, @@ -691,7 +691,7 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, shrinker = idr_find(&shrinker_idr, i); if (unlikely(!shrinker || shrinker == SHRINKER_REGISTERING)) { if (!shrinker) - clear_bit(i, map->map); + clear_bit(i, info->map); continue; } @@ -702,7 +702,7 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, ret = do_shrink_slab(&sc, shrinker, priority); if (ret == SHRINK_EMPTY) { - clear_bit(i, map->map); + clear_bit(i, info->map); /* * After the shrinker reported that it had no objects to * free, but before we cleared the corresponding bit in -- cgit v1.2.3 From 3c6f17e6c5d048c8029578c475dd037dd5db58af Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Tue, 4 May 2021 18:36:33 -0700 Subject: mm: vmscan: add per memcg shrinker nr_deferred Currently the number of deferred objects are per shrinker, but some slabs, for example, vfs inode/dentry cache are per memcg, this would result in poor isolation among memcgs. The deferred objects typically are generated by __GFP_NOFS allocations, one memcg with excessive __GFP_NOFS allocations may blow up deferred objects, then other innocent memcgs may suffer from over shrink, excessive reclaim latency, etc. For example, two workloads run in memcgA and memcgB respectively, workload in B is vfs heavy workload. Workload in A generates excessive deferred objects, then B's vfs cache might be hit heavily (drop half of caches) by B's limit reclaim or global reclaim. We observed this hit in our production environment which was running vfs heavy workload shown as the below tracing log: <...>-409454 [016] .... 28286961.747146: mm_shrink_slab_start: super_cache_scan+0x0/0x1a0 ffff9a83046f3458: nid: 1 objects to shrink 3641681686040 gfp_flags GFP_HIGHUSER_MOVABLE|__GFP_ZERO pgs_scanned 1 lru_pgs 15721 cache items 246404277 delta 31345 total_scan 123202138 <...>-409454 [022] .... 28287105.928018: mm_shrink_slab_end: super_cache_scan+0x0/0x1a0 ffff9a83046f3458: nid: 1 unused scan count 3641681686040 new scan count 3641798379189 total_scan 602 last shrinker return val 123186855 The vfs cache and page cache ratio was 10:1 on this machine, and half of caches were dropped. This also resulted in significant amount of page caches were dropped due to inodes eviction. Make nr_deferred per memcg for memcg aware shrinkers would solve the unfairness and bring better isolation. The following patch will add nr_deferred to parent memcg when memcg offline. To preserve nr_deferred when reparenting memcgs to root, root memcg needs shrinker_info allocated too. When memcg is not enabled (!CONFIG_MEMCG or memcg disabled), the shrinker's nr_deferred would be used. And non memcg aware shrinkers use shrinker's nr_deferred all the time. Link: https://lkml.kernel.org/r/20210311190845.9708-10-shy828301@gmail.com Signed-off-by: Yang Shi Acked-by: Roman Gushchin Acked-by: Kirill Tkhai Reviewed-by: Shakeel Butt Cc: Dave Chinner Cc: Johannes Weiner Cc: Michal Hocko Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 7 +++--- mm/vmscan.c | 60 ++++++++++++++++++++++++++++++++-------------- 2 files changed, 46 insertions(+), 21 deletions(-) (limited to 'include/linux/memcontrol.h') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 6cd800fe9a67..32bd62047238 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -114,12 +114,13 @@ struct batched_lruvec_stat { }; /* - * Bitmap of shrinker::id corresponding to memcg-aware shrinkers, - * which have elements charged to this memcg. + * Bitmap and deferred work of shrinker::id corresponding to memcg-aware + * shrinkers, which have elements charged to this memcg. */ struct shrinker_info { struct rcu_head rcu; - unsigned long map[]; + atomic_long_t *nr_deferred; + unsigned long *map; }; /* diff --git a/mm/vmscan.c b/mm/vmscan.c index d1601163d895..db668c4c78f4 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -187,11 +187,17 @@ static DECLARE_RWSEM(shrinker_rwsem); #ifdef CONFIG_MEMCG static int shrinker_nr_max; +/* The shrinker_info is expanded in a batch of BITS_PER_LONG */ static inline int shrinker_map_size(int nr_items) { return (DIV_ROUND_UP(nr_items, BITS_PER_LONG) * sizeof(unsigned long)); } +static inline int shrinker_defer_size(int nr_items) +{ + return (round_up(nr_items, BITS_PER_LONG) * sizeof(atomic_long_t)); +} + static struct shrinker_info *shrinker_info_protected(struct mem_cgroup *memcg, int nid) { @@ -200,11 +206,13 @@ static struct shrinker_info *shrinker_info_protected(struct mem_cgroup *memcg, } static int expand_one_shrinker_info(struct mem_cgroup *memcg, - int size, int old_size) + int map_size, int defer_size, + int old_map_size, int old_defer_size) { struct shrinker_info *new, *old; struct mem_cgroup_per_node *pn; int nid; + int size = map_size + defer_size; for_each_node(nid) { pn = memcg->nodeinfo[nid]; @@ -217,9 +225,16 @@ static int expand_one_shrinker_info(struct mem_cgroup *memcg, if (!new) return -ENOMEM; - /* Set all old bits, clear all new bits */ - memset(new->map, (int)0xff, old_size); - memset((void *)new->map + old_size, 0, size - old_size); + new->nr_deferred = (atomic_long_t *)(new + 1); + new->map = (void *)new->nr_deferred + defer_size; + + /* map: set all old bits, clear all new bits */ + memset(new->map, (int)0xff, old_map_size); + memset((void *)new->map + old_map_size, 0, map_size - old_map_size); + /* nr_deferred: copy old values, clear all new values */ + memcpy(new->nr_deferred, old->nr_deferred, old_defer_size); + memset((void *)new->nr_deferred + old_defer_size, 0, + defer_size - old_defer_size); rcu_assign_pointer(pn->shrinker_info, new); kvfree_rcu(old, rcu); @@ -234,9 +249,6 @@ void free_shrinker_info(struct mem_cgroup *memcg) struct shrinker_info *info; int nid; - if (mem_cgroup_is_root(memcg)) - return; - for_each_node(nid) { pn = memcg->nodeinfo[nid]; info = rcu_dereference_protected(pn->shrinker_info, true); @@ -249,12 +261,12 @@ int alloc_shrinker_info(struct mem_cgroup *memcg) { struct shrinker_info *info; int nid, size, ret = 0; - - if (mem_cgroup_is_root(memcg)) - return 0; + int map_size, defer_size = 0; down_write(&shrinker_rwsem); - size = shrinker_map_size(shrinker_nr_max); + map_size = shrinker_map_size(shrinker_nr_max); + defer_size = shrinker_defer_size(shrinker_nr_max); + size = map_size + defer_size; for_each_node(nid) { info = kvzalloc_node(sizeof(*info) + size, GFP_KERNEL, nid); if (!info) { @@ -262,6 +274,8 @@ int alloc_shrinker_info(struct mem_cgroup *memcg) ret = -ENOMEM; break; } + info->nr_deferred = (atomic_long_t *)(info + 1); + info->map = (void *)info->nr_deferred + defer_size; rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_info, info); } up_write(&shrinker_rwsem); @@ -269,15 +283,21 @@ int alloc_shrinker_info(struct mem_cgroup *memcg) return ret; } +static inline bool need_expand(int nr_max) +{ + return round_up(nr_max, BITS_PER_LONG) > + round_up(shrinker_nr_max, BITS_PER_LONG); +} + static int expand_shrinker_info(int new_id) { - int size, old_size, ret = 0; + int ret = 0; int new_nr_max = new_id + 1; + int map_size, defer_size = 0; + int old_map_size, old_defer_size = 0; struct mem_cgroup *memcg; - size = shrinker_map_size(new_nr_max); - old_size = shrinker_map_size(shrinker_nr_max); - if (size <= old_size) + if (!need_expand(new_nr_max)) goto out; if (!root_mem_cgroup) @@ -285,11 +305,15 @@ static int expand_shrinker_info(int new_id) lockdep_assert_held(&shrinker_rwsem); + map_size = shrinker_map_size(new_nr_max); + defer_size = shrinker_defer_size(new_nr_max); + old_map_size = shrinker_map_size(shrinker_nr_max); + old_defer_size = shrinker_defer_size(shrinker_nr_max); + memcg = mem_cgroup_iter(NULL, NULL, NULL); do { - if (mem_cgroup_is_root(memcg)) - continue; - ret = expand_one_shrinker_info(memcg, size, old_size); + ret = expand_one_shrinker_info(memcg, map_size, defer_size, + old_map_size, old_defer_size); if (ret) { mem_cgroup_iter_break(NULL, memcg); goto out; -- cgit v1.2.3 From a178015cde69981cdcd8f109c5abc98703fead62 Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Tue, 4 May 2021 18:36:42 -0700 Subject: mm: memcontrol: reparent nr_deferred when memcg offline Now shrinker's nr_deferred is per memcg for memcg aware shrinkers, add to parent's corresponding nr_deferred when memcg offline. Link: https://lkml.kernel.org/r/20210311190845.9708-13-shy828301@gmail.com Signed-off-by: Yang Shi Acked-by: Vlastimil Babka Acked-by: Kirill Tkhai Acked-by: Roman Gushchin Reviewed-by: Shakeel Butt Cc: Dave Chinner Cc: Johannes Weiner Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 1 + mm/memcontrol.c | 1 + mm/vmscan.c | 24 ++++++++++++++++++++++++ 3 files changed, 26 insertions(+) (limited to 'include/linux/memcontrol.h') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 32bd62047238..c193be760709 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1614,6 +1614,7 @@ static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) int alloc_shrinker_info(struct mem_cgroup *memcg); void free_shrinker_info(struct mem_cgroup *memcg); void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id); +void reparent_shrinker_deferred(struct mem_cgroup *memcg); #else #define mem_cgroup_sockets_enabled 0 static inline void mem_cgroup_sk_alloc(struct sock *sk) { }; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 36f31d611dea..3004afb6d090 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -5154,6 +5154,7 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css) page_counter_set_low(&memcg->memory, 0); memcg_offline_kmem(memcg); + reparent_shrinker_deferred(memcg); wb_memcg_offline(memcg); drain_all_stock(memcg); diff --git a/mm/vmscan.c b/mm/vmscan.c index 9617c5ff3e98..8c2d2003acbe 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -397,6 +397,30 @@ static long add_nr_deferred_memcg(long nr, int nid, struct shrinker *shrinker, return atomic_long_add_return(nr, &info->nr_deferred[shrinker->id]); } +void reparent_shrinker_deferred(struct mem_cgroup *memcg) +{ + int i, nid; + long nr; + struct mem_cgroup *parent; + struct shrinker_info *child_info, *parent_info; + + parent = parent_mem_cgroup(memcg); + if (!parent) + parent = root_mem_cgroup; + + /* Prevent from concurrent shrinker_info expand */ + down_read(&shrinker_rwsem); + for_each_node(nid) { + child_info = shrinker_info_protected(memcg, nid); + parent_info = shrinker_info_protected(parent, nid); + for (i = 0; i < shrinker_nr_max; i++) { + nr = atomic_long_read(&child_info->nr_deferred[i]); + atomic_long_add(nr, &parent_info->nr_deferred[i]); + } + } + up_read(&shrinker_rwsem); +} + static bool cgroup_reclaim(struct scan_control *sc) { return sc->target_mem_cgroup; -- cgit v1.2.3