From: Yang Shi yang.shi@linux.alibaba.com
mainline inclusion from mainline-v5.4-rc1 commit 0a432dcbeb32edcd211a5d8f7847d0da7642a8b4 category: bugfix bugzilla: 47240 CVE: NA
-------------------------------------------------
Currently shrinker is just allocated and can work when memcg kmem is enabled. But, THP deferred split shrinker is not slab shrinker, it doesn't make too much sense to have such shrinker depend on memcg kmem. It should be able to reclaim THP even though memcg kmem is disabled.
Introduce a new shrinker flag, SHRINKER_NONSLAB, for non-slab shrinker. When memcg kmem is disabled, just such shrinkers can be called in shrinking memcg slab.
[yang.shi@linux.alibaba.com: add comment] Link: http://lkml.kernel.org/r/1566496227-84952-4-git-send-email-yang.shi@linux.al... Link: http://lkml.kernel.org/r/1565144277-36240-4-git-send-email-yang.shi@linux.al... Signed-off-by: Yang Shi yang.shi@linux.alibaba.com Acked-by: Kirill A. Shutemov kirill.shutemov@linux.intel.com Reviewed-by: Kirill Tkhai ktkhai@virtuozzo.com Cc: Johannes Weiner hannes@cmpxchg.org Cc: Michal Hocko mhocko@suse.com Cc: "Kirill A . Shutemov" kirill.shutemov@linux.intel.com Cc: Hugh Dickins hughd@google.com Cc: Shakeel Butt shakeelb@google.com Cc: David Rientjes rientjes@google.com Cc: Qian Cai cai@lca.pw Cc: Vladimir Davydov vdavydov.dev@gmail.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Liu Shixin liushixin2@huawei.com Reviewed-by: Kefeng Wang wangkefeng.wang@huawei.com Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- include/linux/memcontrol.h | 19 +++++++++++-------- include/linux/shrinker.h | 7 ++++++- mm/memcontrol.c | 9 +-------- mm/vmscan.c | 36 +++++++++++++++++++----------------- 4 files changed, 37 insertions(+), 34 deletions(-)
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 029b4848ab6f3..7dc9ed226caf1 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -137,9 +137,8 @@ struct mem_cgroup_per_node {
struct mem_cgroup_reclaim_iter iter[DEF_PRIORITY + 1];
-#ifdef CONFIG_MEMCG_KMEM struct memcg_shrinker_map __rcu *shrinker_map; -#endif + struct rb_node tree_node; /* RB tree node */ unsigned long usage_in_excess;/* Set to the value by which */ /* the soft limit is exceeded*/ @@ -1282,6 +1281,11 @@ static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) } while ((memcg = parent_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); #else #define mem_cgroup_sockets_enabled 0 static inline void mem_cgroup_sk_alloc(struct sock *sk) { }; @@ -1290,6 +1294,11 @@ 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) +{ +} #endif
struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep); @@ -1361,10 +1370,6 @@ static inline int memcg_cache_id(struct mem_cgroup *memcg) return memcg ? memcg->kmemcg_id : -1; }
-extern int memcg_expand_shrinker_maps(int new_id); - -extern void memcg_set_shrinker_bit(struct mem_cgroup *memcg, - int nid, int shrinker_id); struct mem_cgroup *mem_cgroup_from_obj(void *p); #else
@@ -1407,8 +1412,6 @@ static inline void memcg_put_cache_ids(void) { }
-static inline void memcg_set_shrinker_bit(struct mem_cgroup *memcg, - int nid, int shrinker_id) { } static inline struct mem_cgroup *mem_cgroup_from_obj(void *p) { return NULL; diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h index 9443cafd19696..0f80123650e23 100644 --- a/include/linux/shrinker.h +++ b/include/linux/shrinker.h @@ -69,7 +69,7 @@ struct shrinker {
/* These are for internal use */ struct list_head list; -#ifdef CONFIG_MEMCG_KMEM +#ifdef CONFIG_MEMCG /* ID in shrinker_idr */ int id; #endif @@ -81,6 +81,11 @@ struct shrinker { /* Flags */ #define SHRINKER_NUMA_AWARE (1 << 0) #define SHRINKER_MEMCG_AWARE (1 << 1) +/* + * It just makes sense when the shrinker is also MEMCG_AWARE for now, + * non-MEMCG_AWARE shrinker should not have this flag set. + */ +#define SHRINKER_NONSLAB (1 << 2)
extern int prealloc_shrinker(struct shrinker *shrinker); extern void register_shrinker_prepared(struct shrinker *shrinker); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index dfc09dcced679..4ce353c86687d 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -321,6 +321,7 @@ DEFINE_STATIC_KEY_FALSE(memcg_kmem_enabled_key); EXPORT_SYMBOL(memcg_kmem_enabled_key);
struct workqueue_struct *memcg_kmem_cache_wq; +#endif
static int memcg_shrinker_map_size; static DEFINE_MUTEX(memcg_shrinker_map_mutex); @@ -446,14 +447,6 @@ void memcg_set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id) } }
-#else /* CONFIG_MEMCG_KMEM */ -static int memcg_alloc_shrinker_maps(struct mem_cgroup *memcg) -{ - return 0; -} -static void memcg_free_shrinker_maps(struct mem_cgroup *memcg) { } -#endif /* CONFIG_MEMCG_KMEM */ - /** * mem_cgroup_css_from_page - css of the memcg associated with a page * @page: page of interest diff --git a/mm/vmscan.c b/mm/vmscan.c index 831d7bec3c80e..314b47e39e742 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -186,8 +186,7 @@ static DEFINE_PER_CPU(struct delayed_work, vmscan_work); static LIST_HEAD(shrinker_list); static DECLARE_RWSEM(shrinker_rwsem);
-#ifdef CONFIG_MEMCG_KMEM - +#ifdef CONFIG_MEMCG /* * We allow subsystems to populate their shrinker-related * LRU lists before register_shrinker_prepared() is called @@ -239,18 +238,7 @@ static void unregister_memcg_shrinker(struct shrinker *shrinker) idr_remove(&shrinker_idr, id); up_write(&shrinker_rwsem); } -#else /* CONFIG_MEMCG_KMEM */ -static int prealloc_memcg_shrinker(struct shrinker *shrinker) -{ - return 0; -}
-static void unregister_memcg_shrinker(struct shrinker *shrinker) -{ -} -#endif /* CONFIG_MEMCG_KMEM */ - -#ifdef CONFIG_MEMCG static bool global_reclaim(struct scan_control *sc) { return !sc->target_mem_cgroup; @@ -305,6 +293,15 @@ static bool memcg_congested(pg_data_t *pgdat,
} #else +static int prealloc_memcg_shrinker(struct shrinker *shrinker) +{ + return 0; +} + +static void unregister_memcg_shrinker(struct shrinker *shrinker) +{ +} + static bool global_reclaim(struct scan_control *sc) { return true; @@ -583,7 +580,7 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, return freed; }
-#ifdef CONFIG_MEMCG_KMEM +#ifdef CONFIG_MEMCG static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, int priority) { @@ -591,7 +588,7 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, unsigned long ret, freed = 0; int i;
- if (!memcg_kmem_enabled() || !mem_cgroup_online(memcg)) + if (!mem_cgroup_online(memcg)) return 0;
if (!down_read_trylock(&shrinker_rwsem)) @@ -617,6 +614,11 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, continue; }
+ /* Call non-slab shrinkers even though kmem is disabled */ + if (!memcg_kmem_enabled() && + !(shrinker->flags & SHRINKER_NONSLAB)) + continue; + ret = do_shrink_slab(&sc, shrinker, priority); if (ret == SHRINK_EMPTY) { clear_bit(i, map->map); @@ -653,13 +655,13 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, up_read(&shrinker_rwsem); return freed; } -#else /* CONFIG_MEMCG_KMEM */ +#else /* CONFIG_MEMCG */ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, int priority) { return 0; } -#endif /* CONFIG_MEMCG_KMEM */ +#endif /* CONFIG_MEMCG */
/** * shrink_slab - shrink slab caches