mm: memcg/slab: stop setting page->mem_cgroup pointer for slab pages

Every slab page charged to a non-root memory cgroup has a pointer to the
memory cgroup and holds a reference to it, which protects a non-empty
memory cgroup from being released.  At the same time the page has a
pointer to the corresponding kmem_cache, and also hold a reference to the
kmem_cache.  And kmem_cache by itself holds a reference to the cgroup.

So there is clearly some redundancy, which allows to stop setting the
page->mem_cgroup pointer and rely on getting memcg pointer indirectly via
kmem_cache.  Further it will allow to change this pointer easier, without
a need to go over all charged pages.

So let's stop setting page->mem_cgroup pointer for slab pages, and stop
using the css refcounter directly for protecting the memory cgroup from
going away.  Instead rely on kmem_cache as an intermediate object.

Make sure that vmstats and shrinker lists are working as previously, as
well as /proc/kpagecgroup interface.

Link: http://lkml.kernel.org/r/20190611231813.3148843-10-guro@fb.com
Signed-off-by: Roman Gushchin <guro@fb.com>
Acked-by: Vladimir Davydov <vdavydov.dev@gmail.com>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Waiman Long <longman@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Andrei Vagin <avagin@gmail.com>
Cc: Qian Cai <cai@lca.pw>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

mm/list_lru.c

@@ -12,6 +12,7 @@
 #include <linux/slab.h>
 #include <linux/mutex.h>
 #include <linux/memcontrol.h>
+#include "slab.h"
 
 #ifdef CONFIG_MEMCG_KMEM
 static LIST_HEAD(list_lrus);
@@ -63,7 +64,7 @@ static __always_inline struct mem_cgroup *mem_cgroup_from_kmem(void *ptr)
 	if (!memcg_kmem_enabled())
 		return NULL;
 	page = virt_to_head_page(ptr);
-	return page->mem_cgroup;
+	return memcg_from_slab_page(page);
 }
 
 static inline struct list_lru_one *

mm/memcontrol.c

@@ -486,6 +486,9 @@ ino_t page_cgroup_ino(struct page *page)
 	unsigned long ino = 0;
 
 	rcu_read_lock();
+	if (PageHead(page) && PageSlab(page))
+		memcg = memcg_from_slab_page(page);
+	else
 		memcg = READ_ONCE(page->mem_cgroup);
 	while (memcg && !(memcg->css.flags & CSS_ONLINE))
 		memcg = parent_mem_cgroup(memcg);
@@ -2802,9 +2805,6 @@ int __memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order,
 		cancel_charge(memcg, nr_pages);
 		return -ENOMEM;
 	}
-
-	page->mem_cgroup = memcg;
-
 	return 0;
 }
 
@@ -2827,9 +2827,11 @@ int __memcg_kmem_charge(struct page *page, gfp_t gfp, int order)
 	memcg = get_mem_cgroup_from_current();
 	if (!mem_cgroup_is_root(memcg)) {
 		ret = __memcg_kmem_charge_memcg(page, gfp, order, memcg);
-		if (!ret)
+		if (!ret) {
+			page->mem_cgroup = memcg;
 			__SetPageKmemcg(page);
 		}
+	}
 	css_put(&memcg->css);
 	return ret;
 }

mm/slab.h

@@ -255,30 +255,67 @@ static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s)
 	return s->memcg_params.root_cache;
 }
 
+/*
+ * Expects a pointer to a slab page. Please note, that PageSlab() check
+ * isn't sufficient, as it returns true also for tail compound slab pages,
+ * which do not have slab_cache pointer set.
+ * So this function assumes that the page can pass PageHead() and PageSlab()
+ * checks.
+ */
+static inline struct mem_cgroup *memcg_from_slab_page(struct page *page)
+{
+	struct kmem_cache *s;
+
+	s = READ_ONCE(page->slab_cache);
+	if (s && !is_root_cache(s))
+		return s->memcg_params.memcg;
+
+	return NULL;
+}
+
+/*
+ * Charge the slab page belonging to the non-root kmem_cache.
+ * Can be called for non-root kmem_caches only.
+ */
 static __always_inline int memcg_charge_slab(struct page *page,
 					     gfp_t gfp, int order,
 					     struct kmem_cache *s)
 {
+	struct mem_cgroup *memcg;
+	struct lruvec *lruvec;
 	int ret;
 
-	if (is_root_cache(s))
-		return 0;
-
-	ret = memcg_kmem_charge_memcg(page, gfp, order, s->memcg_params.memcg);
+	memcg = s->memcg_params.memcg;
+	ret = memcg_kmem_charge_memcg(page, gfp, order, memcg);
 	if (ret)
 		return ret;
 
+	lruvec = mem_cgroup_lruvec(page_pgdat(page), memcg);
+	mod_lruvec_state(lruvec, cache_vmstat_idx(s), 1 << order);
+
+	/* transer try_charge() page references to kmem_cache */
 	percpu_ref_get_many(&s->memcg_params.refcnt, 1 << order);
+	css_put_many(&memcg->css, 1 << order);
 
 	return 0;
 }
 
+/*
+ * Uncharge a slab page belonging to a non-root kmem_cache.
+ * Can be called for non-root kmem_caches only.
+ */
 static __always_inline void memcg_uncharge_slab(struct page *page, int order,
 						struct kmem_cache *s)
 {
-	if (!is_root_cache(s))
+	struct mem_cgroup *memcg;
+	struct lruvec *lruvec;
+
+	memcg = s->memcg_params.memcg;
+	lruvec = mem_cgroup_lruvec(page_pgdat(page), memcg);
+	mod_lruvec_state(lruvec, cache_vmstat_idx(s), -(1 << order));
+	memcg_kmem_uncharge_memcg(page, order, memcg);
+
 	percpu_ref_put_many(&s->memcg_params.refcnt, 1 << order);
-	memcg_kmem_uncharge(page, order);
 }
 
 extern void slab_init_memcg_params(struct kmem_cache *);
@@ -314,6 +351,11 @@ static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s)
 	return s;
 }
 
+static inline struct mem_cgroup *memcg_from_slab_page(struct page *page)
+{
+	return NULL;
+}
+
 static inline int memcg_charge_slab(struct page *page, gfp_t gfp, int order,
 				    struct kmem_cache *s)
 {
@@ -351,18 +393,24 @@ static __always_inline int charge_slab_page(struct page *page,
 					    gfp_t gfp, int order,
 					    struct kmem_cache *s)
 {
-	int ret = memcg_charge_slab(page, gfp, order, s);
+	if (is_root_cache(s)) {
+		mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s),
+				    1 << order);
+		return 0;
+	}
 
-	if (!ret)
-		mod_lruvec_page_state(page, cache_vmstat_idx(s), 1 << order);
-
-	return ret;
+	return memcg_charge_slab(page, gfp, order, s);
 }
 
 static __always_inline void uncharge_slab_page(struct page *page, int order,
 					       struct kmem_cache *s)
 {
-	mod_lruvec_page_state(page, cache_vmstat_idx(s), -(1 << order));
+	if (is_root_cache(s)) {
+		mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s),
+				    -(1 << order));
+		return;
+	}
+
 	memcg_uncharge_slab(page, order, s);
 }