From: Hui Zhu get_non_dying_memcg_start() redirects the stat updates of a dying memcg to its closest non-dying ancestor, but only on cgroup v1; on cgroup v2 the stats keep being accounted to the dying memcg itself. A later patch in this series restores lruvec_page_state_local() in count_shadow_nodes() to fix the broken workingset shadow node budget under MGLRU. count_shadow_nodes() is the only reader of those non-hierarchical state_locals on cgroup v2: when a memcg is offlined, its pages are reparented to the ancestor but their stat updates keep being accounted to the dying memcg, so count_shadow_nodes() computes a wrong shadow node budget and workingset thrashing protection is lost. This is user visible as premature reclaim of hot page cache and degraded performance under memory pressure. Apply the redirection to all hierarchies to fix this. Offlining is rare, so the added cost on the stat update fast path is limited to an rcu_read_lock() and a css_is_dying() check; the upward walk happens only while a memcg is dying. Fixes: 7404bd37cfbe ("mm: workingset: use lruvec_lru_size() to get the number of lru pages") Cc: stable@vger.kernel.org Signed-off-by: Hui Zhu Acked-by: Shakeel Butt --- mm/memcontrol.c | 30 +++++------------------------- 1 file changed, 5 insertions(+), 25 deletions(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 1271d390b617e..ace9fe2b46084 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -845,20 +845,14 @@ static long memcg_state_val_in_pages(int idx, long val) return val < 0 ? -res : res; } -#ifdef CONFIG_MEMCG_V1 /* - * Used in mod_memcg_state() and mod_memcg_lruvec_state() to avoid race with - * reparenting of non-hierarchical state_locals. + * Used in mod_memcg_state() and mod_memcg_lruvec_state() to avoid race + * with reparenting of non-hierarchical state_locals. Offlining a + * memcg is rare, so do the redirection for all cgroup hierarchies. */ -static inline struct mem_cgroup *get_non_dying_memcg_start(struct mem_cgroup *memcg, - bool *rcu_locked) +static inline struct mem_cgroup * +get_non_dying_memcg_start(struct mem_cgroup *memcg, bool *rcu_locked) { - /* Rebinding can cause this value to be changed at runtime */ - if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) { - *rcu_locked = false; - return memcg; - } - rcu_read_lock(); *rcu_locked = true; @@ -870,22 +864,8 @@ static inline struct mem_cgroup *get_non_dying_memcg_start(struct mem_cgroup *me static inline void get_non_dying_memcg_end(bool rcu_locked) { - if (!rcu_locked) - return; - rcu_read_unlock(); } -#else -static inline struct mem_cgroup *get_non_dying_memcg_start(struct mem_cgroup *memcg, - bool *rcu_locked) -{ - return memcg; -} - -static inline void get_non_dying_memcg_end(bool rcu_locked) -{ -} -#endif static void __mod_memcg_state(struct mem_cgroup *memcg, enum memcg_stat_item idx, long val) -- 2.43.0 From: Hui Zhu Commit 7404bd37cfbe ("mm: workingset: use lruvec_lru_size() to get the number of lru pages") switched count_shadow_nodes() to lruvec_lru_size(). With CONFIG_MEMCG enabled, lruvec_lru_size() reads mz->lru_zone_size, which only the classic LRU paths maintain. MGLRU accounts its pages through __update_lru_size(), which skips that array, so with MGLRU on the four evictable LRU lists are always seen as empty. The shadow node budget (pages >> 3) then collapses to slab plus unevictable pages, and the workingset shadow shrinker reclaims eviction tokens almost as fast as they are created, losing thrashing protection. lruvec_page_state_local() reads lruvec_stats->state_local instead, which both classic LRU and MGLRU maintain. Switch back to it. The reparenting race this re-exposes on cgroup v2 is closed by the preceding patch that redirects dying-memcg stat updates for all hierarchies. Fixes: 7404bd37cfbe ("mm: workingset: use lruvec_lru_size() to get the number of lru pages") Cc: stable@vger.kernel.org Signed-off-by: Hui Zhu Acked-by: Shakeel Butt --- mm/workingset.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/mm/workingset.c b/mm/workingset.c index 7ac2b88c80ae5..8412f4840ae35 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -688,10 +688,9 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker, mem_cgroup_flush_stats_ratelimited(sc->memcg); lruvec = mem_cgroup_lruvec(sc->memcg, NODE_DATA(sc->nid)); - for (pages = 0, i = 0; i < NR_LRU_LISTS; i++) - pages += lruvec_lru_size(lruvec, i, MAX_NR_ZONES - 1); - + pages += lruvec_page_state_local(lruvec, + NR_LRU_BASE + i); pages += lruvec_page_state_local( lruvec, NR_SLAB_RECLAIMABLE_B) >> PAGE_SHIFT; pages += lruvec_page_state_local( -- 2.43.0 From: Hui Zhu get_non_dying_memcg_start() takes rcu_read_lock() on every stat update, but the lock only protects the upward walk to a non-dying ancestor, which happens solely while a memcg is being offlined. The dying check itself reads the CSS_DYING flag of a memcg the caller already holds a reference to, so it is safe without the lock. Check memcg_is_dying() first and return immediately when the memcg is alive, taking the RCU lock only on the rare dying path. On an anon fault/charge churn workload in a memcg this recovers the ~0.6% overhead added by the previous patch (4368077 vs 4343159 pages/s before, back to ~4377000 pages/s after). Fixes: 7404bd37cfbe ("mm: workingset: use lruvec_lru_size() to get the number of lru pages") Cc: stable@vger.kernel.org Signed-off-by: Hui Zhu Acked-by: Shakeel Butt --- mm/memcontrol.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index ace9fe2b46084..9995f3d2aae1b 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -853,6 +853,17 @@ static long memcg_state_val_in_pages(int idx, long val) static inline struct mem_cgroup * get_non_dying_memcg_start(struct mem_cgroup *memcg, bool *rcu_locked) { + /* + * Fast path: the caller holds a reference to @memcg, so reading + * its CSS_DYING flag without the RCU lock is safe. The RCU lock + * is only needed to walk up to a non-dying ancestor, which + * happens only while a memcg is actually being offlined. + */ + if (!memcg_is_dying(memcg)) { + *rcu_locked = false; + return memcg; + } + rcu_read_lock(); *rcu_locked = true; @@ -864,6 +875,9 @@ get_non_dying_memcg_start(struct mem_cgroup *memcg, bool *rcu_locked) static inline void get_non_dying_memcg_end(bool rcu_locked) { + if (!rcu_locked) + return; + rcu_read_unlock(); } -- 2.43.0 From: Hui Zhu On cgroup v2, reparent_state_local() returns early and never moves the dying memcg's non-hierarchical state_local base counts to its parent. Meanwhile memcg_reparent_objcgs() rewrites objcg->memcg to the parent, so when the reparented folios are freed later, the negative deltas land on the parent's lruvec. The parent therefore receives the uncharges without ever having received the matching charges, and its state_local (NR_LRU_BASE + lru, MEMCG_SOCK, NR_SLAB_RECLAIMABLE_B, NR_SLAB_UNRECLAIMABLE_B) permanently underflows. Since lruvec_page_state_local() clamps negative values to zero, the underflow masks the parent's own legitimate pages. count_shadow_nodes() is the only reader of these non-hierarchical state_locals on cgroup v2, so the underflow directly distorts the workingset shadow node budget. Fix this by reparenting the lruvec state_locals on cgroup v2 as well, mirroring what cgroup v1 already does. Only the lruvec stats consumed by count_shadow_nodes() are moved; the memcg-level stats are left alone because on v2 they are exposed through the rstat hierarchical tree and are not read from state_local. Fixes: 8285917d6f38 ("mm: memcontrol: prepare for reparenting non-hierarchical stats") Cc: stable@vger.kernel.org Signed-off-by: Hui Zhu --- mm/memcontrol-v1.h | 5 +++-- mm/memcontrol.c | 42 ++++++++++++++++++++++++++++-------------- 2 files changed, 31 insertions(+), 16 deletions(-) diff --git a/mm/memcontrol-v1.h b/mm/memcontrol-v1.h index 1e394269c613d..0578b7076764d 100644 --- a/mm/memcontrol-v1.h +++ b/mm/memcontrol-v1.h @@ -25,6 +25,9 @@ int memory_stat_show(struct seq_file *m, void *v); struct mem_cgroup *mem_cgroup_private_id_get_online(struct mem_cgroup *memcg, unsigned int n); +void reparent_memcg_lruvec_state_local(struct mem_cgroup *memcg, + struct mem_cgroup *parent, int idx); + /* Cgroup v1-specific declarations */ #ifdef CONFIG_MEMCG_V1 @@ -73,8 +76,6 @@ void reparent_memcg1_lruvec_state_local(struct mem_cgroup *memcg, struct mem_cgr void reparent_memcg_state_local(struct mem_cgroup *memcg, struct mem_cgroup *parent, int idx); -void reparent_memcg_lruvec_state_local(struct mem_cgroup *memcg, - struct mem_cgroup *parent, int idx); void memcg1_account_kmem(struct mem_cgroup *memcg, int nr_pages); static inline bool memcg1_tcpmem_active(struct mem_cgroup *memcg) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 9995f3d2aae1b..f13030f75fa54 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -232,14 +232,29 @@ static inline struct obj_cgroup *__memcg_reparent_objcgs(struct mem_cgroup *memc return objcg; } -#ifdef CONFIG_MEMCG_V1 static void __mem_cgroup_flush_stats(struct mem_cgroup *memcg, bool force); -static inline void reparent_state_local(struct mem_cgroup *memcg, struct mem_cgroup *parent) +/* + * Reparent the non-hierarchical lruvec stats that count_shadow_nodes() reads + * to approximate the shadow node budget. They are not exposed to userspace + * on cgroup v2, but they must follow the reparented folios; otherwise the + * ancestor would only receive the negative deltas when the folios are freed + * without ever having received the positive base, and its local stats would + * permanently underflow. + */ +static void reparent_v2_lruvec_state_local(struct mem_cgroup *memcg, struct mem_cgroup *parent) { - if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) - return; + int i; + + for (i = 0; i < NR_LRU_LISTS; i++) + reparent_memcg_lruvec_state_local(memcg, parent, NR_LRU_BASE + i); + + reparent_memcg_lruvec_state_local(memcg, parent, NR_SLAB_RECLAIMABLE_B); + reparent_memcg_lruvec_state_local(memcg, parent, NR_SLAB_UNRECLAIMABLE_B); +} +static inline void reparent_state_local(struct mem_cgroup *memcg, struct mem_cgroup *parent) +{ /* * Reparent stats exposed non-hierarchically. Flush @memcg's stats first * to read its stats accurately , and conservatively flush @parent's @@ -248,17 +263,18 @@ static inline void reparent_state_local(struct mem_cgroup *memcg, struct mem_cgr */ __mem_cgroup_flush_stats(memcg, true); - /* The following counts are all non-hierarchical and need to be reparented. */ - reparent_memcg1_state_local(memcg, parent); - reparent_memcg1_lruvec_state_local(memcg, parent); + if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) { + reparent_v2_lruvec_state_local(memcg, parent); + } else { +#ifdef CONFIG_MEMCG_V1 + /* The following counts are all non-hierarchical and need to be reparented. */ + reparent_memcg1_state_local(memcg, parent); + reparent_memcg1_lruvec_state_local(memcg, parent); +#endif + } __mem_cgroup_flush_stats(parent, true); } -#else -static inline void reparent_state_local(struct mem_cgroup *memcg, struct mem_cgroup *parent) -{ -} -#endif static inline void reparent_locks(struct mem_cgroup *memcg, struct mem_cgroup *parent, int nid) { @@ -570,7 +586,6 @@ unsigned long lruvec_page_state_local(struct lruvec *lruvec, return x; } -#ifdef CONFIG_MEMCG_V1 static void __mod_memcg_lruvec_state(struct mem_cgroup_per_node *pn, enum node_stat_item idx, long val); @@ -592,7 +607,6 @@ void reparent_memcg_lruvec_state_local(struct mem_cgroup *memcg, __mod_memcg_lruvec_state(parent_pn, idx, value); } } -#endif /* Subset of vm_event_item to report for memcg event stats */ static const unsigned int memcg_vm_event_stat[] = { -- 2.43.0