LKML Archive on lore.kernel.org
 help / color / Atom feed
From: Roman Gushchin <guro@fb.com>
To: Andrew Morton <akpm@linux-foundation.org>,
	Christoph Lameter <cl@linux.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>,
	Michal Hocko <mhocko@kernel.org>,
	Shakeel Butt <shakeelb@google.com>, <linux-mm@kvack.org>,
	Vlastimil Babka <vbabka@suse.cz>, <kernel-team@fb.com>,
	<linux-kernel@vger.kernel.org>, Roman Gushchin <guro@fb.com>
Subject: [PATCH v6 09/19] mm: memcg/slab: charge individual slab objects instead of pages
Date: Mon, 8 Jun 2020 16:06:44 -0700
Message-ID: <20200608230654.828134-10-guro@fb.com> (raw)
In-Reply-To: <20200608230654.828134-1-guro@fb.com>

Switch to per-object accounting of non-root slab objects.

Charging is performed using obj_cgroup API in the pre_alloc hook.
Obj_cgroup is charged with the size of the object and the size
of metadata: as now it's the size of an obj_cgroup pointer.
If the amount of memory has been charged successfully, the actual
allocation code is executed. Otherwise, -ENOMEM is returned.

In the post_alloc hook if the actual allocation succeeded,
corresponding vmstats are bumped and the obj_cgroup pointer is saved.
Otherwise, the charge is canceled.

On the free path obj_cgroup pointer is obtained and used to uncharge
the size of the releasing object.

Memcg and lruvec counters are now representing only memory used
by active slab objects and do not include the free space. The free
space is shared and doesn't belong to any specific cgroup.

Global per-node slab vmstats are still modified from (un)charge_slab_page()
functions. The idea is to keep all slab pages accounted as slab pages
on system level.

Signed-off-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
---
 mm/slab.h | 173 ++++++++++++++++++++++++------------------------------
 1 file changed, 77 insertions(+), 96 deletions(-)

diff --git a/mm/slab.h b/mm/slab.h
index 8bca0cb4b928..f219a29052d9 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -352,72 +352,6 @@ static inline struct mem_cgroup *memcg_from_slab_page(struct page *page)
 	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)
-{
-	unsigned int nr_pages = 1 << order;
-	struct mem_cgroup *memcg;
-	struct lruvec *lruvec;
-	int ret;
-
-	rcu_read_lock();
-	memcg = READ_ONCE(s->memcg_params.memcg);
-	while (memcg && !css_tryget_online(&memcg->css))
-		memcg = parent_mem_cgroup(memcg);
-	rcu_read_unlock();
-
-	if (unlikely(!memcg || mem_cgroup_is_root(memcg))) {
-		mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s),
-				    nr_pages << PAGE_SHIFT);
-		percpu_ref_get_many(&s->memcg_params.refcnt, nr_pages);
-		return 0;
-	}
-
-	ret = memcg_kmem_charge(memcg, gfp, nr_pages);
-	if (ret)
-		goto out;
-
-	lruvec = mem_cgroup_lruvec(memcg, page_pgdat(page));
-	mod_lruvec_state(lruvec, cache_vmstat_idx(s), nr_pages << PAGE_SHIFT);
-
-	percpu_ref_get_many(&s->memcg_params.refcnt, nr_pages);
-out:
-	css_put(&memcg->css);
-	return ret;
-}
-
-/*
- * 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)
-{
-	unsigned int nr_pages = 1 << order;
-	struct mem_cgroup *memcg;
-	struct lruvec *lruvec;
-
-	rcu_read_lock();
-	memcg = READ_ONCE(s->memcg_params.memcg);
-	if (likely(!mem_cgroup_is_root(memcg))) {
-		lruvec = mem_cgroup_lruvec(memcg, page_pgdat(page));
-		mod_lruvec_state(lruvec, cache_vmstat_idx(s),
-				 -(nr_pages << PAGE_SHIFT));
-		memcg_kmem_uncharge(memcg, nr_pages);
-	} else {
-		mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s),
-				    -(nr_pages << PAGE_SHIFT));
-	}
-	rcu_read_unlock();
-
-	percpu_ref_put_many(&s->memcg_params.refcnt, nr_pages);
-}
-
 static inline int memcg_alloc_page_obj_cgroups(struct page *page,
 					       struct kmem_cache *s, gfp_t gfp)
 {
@@ -438,6 +372,47 @@ static inline void memcg_free_page_obj_cgroups(struct page *page)
 	page->obj_cgroups = NULL;
 }
 
+static inline size_t obj_full_size(struct kmem_cache *s)
+{
+	/*
+	 * For each accounted object there is an extra space which is used
+	 * to store obj_cgroup membership. Charge it too.
+	 */
+	return s->size + sizeof(struct obj_cgroup *);
+}
+
+static inline struct kmem_cache *memcg_slab_pre_alloc_hook(struct kmem_cache *s,
+						struct obj_cgroup **objcgp,
+						size_t objects, gfp_t flags)
+{
+	struct kmem_cache *cachep;
+
+	cachep = memcg_kmem_get_cache(s, objcgp);
+	if (is_root_cache(cachep))
+		return s;
+
+	if (obj_cgroup_charge(*objcgp, flags, objects * obj_full_size(s))) {
+		memcg_kmem_put_cache(cachep);
+		cachep = NULL;
+	}
+
+	return cachep;
+}
+
+static inline void mod_objcg_state(struct obj_cgroup *objcg,
+				   struct pglist_data *pgdat,
+				   int idx, int nr)
+{
+	struct mem_cgroup *memcg;
+	struct lruvec *lruvec;
+
+	rcu_read_lock();
+	memcg = obj_cgroup_memcg(objcg);
+	lruvec = mem_cgroup_lruvec(memcg, pgdat);
+	mod_memcg_lruvec_state(lruvec, idx, nr);
+	rcu_read_unlock();
+}
+
 static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s,
 					      struct obj_cgroup *objcg,
 					      size_t size, void **p)
@@ -452,6 +427,10 @@ static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s,
 			off = obj_to_index(s, page, p[i]);
 			obj_cgroup_get(objcg);
 			page_obj_cgroups(page)[off] = objcg;
+			mod_objcg_state(objcg, page_pgdat(page),
+					cache_vmstat_idx(s), obj_full_size(s));
+		} else {
+			obj_cgroup_uncharge(objcg, obj_full_size(s));
 		}
 	}
 	obj_cgroup_put(objcg);
@@ -470,6 +449,11 @@ static inline void memcg_slab_free_hook(struct kmem_cache *s, struct page *page,
 	off = obj_to_index(s, page, p);
 	objcg = page_obj_cgroups(page)[off];
 	page_obj_cgroups(page)[off] = NULL;
+
+	obj_cgroup_uncharge(objcg, obj_full_size(s));
+	mod_objcg_state(objcg, page_pgdat(page), cache_vmstat_idx(s),
+			-obj_full_size(s));
+
 	obj_cgroup_put(objcg);
 }
 
@@ -511,17 +495,6 @@ 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)
-{
-	return 0;
-}
-
-static inline void memcg_uncharge_slab(struct page *page, int order,
-				       struct kmem_cache *s)
-{
-}
-
 static inline int memcg_alloc_page_obj_cgroups(struct page *page,
 					       struct kmem_cache *s, gfp_t gfp)
 {
@@ -532,6 +505,13 @@ static inline void memcg_free_page_obj_cgroups(struct page *page)
 {
 }
 
+static inline struct kmem_cache *memcg_slab_pre_alloc_hook(struct kmem_cache *s,
+						struct obj_cgroup **objcgp,
+						size_t objects, gfp_t flags)
+{
+	return NULL;
+}
+
 static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s,
 					      struct obj_cgroup *objcg,
 					      size_t size, void **p)
@@ -569,32 +549,33 @@ static __always_inline int charge_slab_page(struct page *page,
 					    gfp_t gfp, int order,
 					    struct kmem_cache *s)
 {
-	int ret;
-
-	if (is_root_cache(s)) {
-		mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s),
-				    PAGE_SIZE << order);
-		return 0;
-	}
+#ifdef CONFIG_MEMCG_KMEM
+	if (memcg_kmem_enabled() && !is_root_cache(s)) {
+		int ret;
 
-	ret = memcg_alloc_page_obj_cgroups(page, s, gfp);
-	if (ret)
-		return ret;
+		ret = memcg_alloc_page_obj_cgroups(page, s, gfp);
+		if (ret)
+			return ret;
 
-	return memcg_charge_slab(page, gfp, order, s);
+		percpu_ref_get_many(&s->memcg_params.refcnt, 1 << order);
+	}
+#endif
+	mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s),
+			    PAGE_SIZE << order);
+	return 0;
 }
 
 static __always_inline void uncharge_slab_page(struct page *page, int order,
 					       struct kmem_cache *s)
 {
-	if (is_root_cache(s)) {
-		mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s),
-				    -(PAGE_SIZE << order));
-		return;
+#ifdef CONFIG_MEMCG_KMEM
+	if (memcg_kmem_enabled() && !is_root_cache(s)) {
+		memcg_free_page_obj_cgroups(page);
+		percpu_ref_put_many(&s->memcg_params.refcnt, 1 << order);
 	}
-
-	memcg_free_page_obj_cgroups(page);
-	memcg_uncharge_slab(page, order, s);
+#endif
+	mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s),
+			    -(PAGE_SIZE << order));
 }
 
 static inline struct kmem_cache *cache_from_obj(struct kmem_cache *s, void *x)
@@ -666,7 +647,7 @@ static inline struct kmem_cache *slab_pre_alloc_hook(struct kmem_cache *s,
 
 	if (memcg_kmem_enabled() &&
 	    ((flags & __GFP_ACCOUNT) || (s->flags & SLAB_ACCOUNT)))
-		return memcg_kmem_get_cache(s, objcgp);
+		return memcg_slab_pre_alloc_hook(s, objcgp, size, flags);
 
 	return s;
 }
-- 
2.25.4


  parent reply index

Thread overview: 92+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-06-08 23:06 [PATCH v6 00/19] The new cgroup slab memory controller Roman Gushchin
2020-06-08 23:06 ` [PATCH v6 01/19] mm: memcg: factor out memcg- and lruvec-level changes out of __mod_lruvec_state() Roman Gushchin
2020-06-17  1:52   ` Shakeel Butt
2020-06-17  2:50     ` Roman Gushchin
2020-06-17  2:59       ` Shakeel Butt
2020-06-17  3:19         ` Roman Gushchin
2020-06-08 23:06 ` [PATCH v6 02/19] mm: memcg: prepare for byte-sized vmstat items Roman Gushchin
2020-06-17  2:57   ` Shakeel Butt
2020-06-17  3:19     ` Roman Gushchin
2020-06-17 15:55   ` Shakeel Butt
2020-06-08 23:06 ` [PATCH v6 03/19] mm: memcg: convert vmstat slab counters to bytes Roman Gushchin
2020-06-17  3:03   ` Shakeel Butt
2020-06-08 23:06 ` [PATCH v6 04/19] mm: slub: implement SLUB version of obj_to_index() Roman Gushchin
2020-06-17  3:08   ` Shakeel Butt
2020-06-08 23:06 ` [PATCH v6 05/19] mm: memcontrol: decouple reference counting from page accounting Roman Gushchin
2020-06-18  0:47   ` Shakeel Butt
2020-06-18 14:55   ` Shakeel Butt
2020-06-18 19:51     ` Roman Gushchin
2020-06-19  1:08     ` Roman Gushchin
2020-06-19  1:18       ` Shakeel Butt
2020-06-19  1:31   ` Shakeel Butt
2020-06-08 23:06 ` [PATCH v6 06/19] mm: memcg/slab: obj_cgroup API Roman Gushchin
2020-06-19 15:42   ` Shakeel Butt
2020-06-19 21:38     ` Roman Gushchin
2020-06-19 22:16       ` Shakeel Butt
2020-06-19 22:52         ` Roman Gushchin
2020-06-20 22:50       ` Andrew Morton
2020-06-08 23:06 ` [PATCH v6 07/19] mm: memcg/slab: allocate obj_cgroups for non-root slab pages Roman Gushchin
2020-06-19 16:36   ` Shakeel Butt
2020-06-20  0:25     ` Roman Gushchin
2020-06-20  0:31       ` Shakeel Butt
2020-06-08 23:06 ` [PATCH v6 08/19] mm: memcg/slab: save obj_cgroup for non-root slab objects Roman Gushchin
2020-06-20  0:16   ` Shakeel Butt
2020-06-20  1:19     ` Roman Gushchin
2020-06-08 23:06 ` Roman Gushchin [this message]
2020-06-20  0:54   ` [PATCH v6 09/19] mm: memcg/slab: charge individual slab objects instead of pages Shakeel Butt
2020-06-20  1:29     ` Roman Gushchin
2020-06-08 23:06 ` [PATCH v6 10/19] mm: memcg/slab: deprecate memory.kmem.slabinfo Roman Gushchin
2020-06-22 17:12   ` Shakeel Butt
2020-06-22 18:01     ` Roman Gushchin
2020-06-22 18:09       ` Shakeel Butt
2020-06-22 18:25         ` Roman Gushchin
2020-06-22 18:38           ` Shakeel Butt
2020-06-08 23:06 ` [PATCH v6 11/19] mm: memcg/slab: move memcg_kmem_bypass() to memcontrol.h Roman Gushchin
2020-06-20  1:19   ` Shakeel Butt
2020-06-08 23:06 ` [PATCH v6 12/19] mm: memcg/slab: use a single set of kmem_caches for all accounted allocations Roman Gushchin
2020-06-22 16:56   ` Shakeel Butt
2020-06-08 23:06 ` [PATCH v6 13/19] mm: memcg/slab: simplify memcg cache creation Roman Gushchin
2020-06-22 17:29   ` Shakeel Butt
2020-06-22 17:40     ` Roman Gushchin
2020-06-22 18:03       ` Shakeel Butt
2020-06-08 23:06 ` [PATCH v6 14/19] mm: memcg/slab: remove memcg_kmem_get_cache() Roman Gushchin
2020-06-22 18:42   ` Shakeel Butt
2020-06-08 23:06 ` [PATCH v6 15/19] mm: memcg/slab: deprecate slab_root_caches Roman Gushchin
2020-06-22 17:36   ` Shakeel Butt
2020-06-08 23:06 ` [PATCH v6 16/19] mm: memcg/slab: remove redundant check in memcg_accumulate_slabinfo() Roman Gushchin
2020-06-22 17:32   ` Shakeel Butt
2020-06-08 23:06 ` [PATCH v6 17/19] mm: memcg/slab: use a single set of kmem_caches for all allocations Roman Gushchin
2020-06-17 23:35   ` Andrew Morton
2020-06-18  0:35     ` Roman Gushchin
2020-06-18  7:33       ` Vlastimil Babka
2020-06-18 19:54         ` Roman Gushchin
2020-06-22 19:21   ` Shakeel Butt
2020-06-22 20:37     ` Roman Gushchin
2020-06-22 21:04       ` Shakeel Butt
2020-06-22 21:13         ` Roman Gushchin
2020-06-22 21:28           ` Shakeel Butt
2020-06-22 21:58             ` Roman Gushchin
2020-06-22 22:05               ` Shakeel Butt
2020-06-08 23:06 ` [PATCH v6 18/19] kselftests: cgroup: add kernel memory accounting tests Roman Gushchin
2020-06-17  1:46 ` [PATCH v6 00/19] The new cgroup slab memory controller Shakeel Butt
2020-06-17  2:41   ` Roman Gushchin
2020-06-17  3:05     ` Shakeel Butt
2020-06-17  3:32       ` Roman Gushchin
2020-06-17 11:24         ` Vlastimil Babka
2020-06-17 14:31           ` Mel Gorman
2020-06-20  0:57             ` Roman Gushchin
2020-06-18  1:29           ` Roman Gushchin
2020-06-18  8:43             ` Jesper Dangaard Brouer
2020-06-18  9:31               ` Jesper Dangaard Brouer
2020-06-19  1:30                 ` Roman Gushchin
2020-06-19  8:32                   ` Jesper Dangaard Brouer
2020-06-19  1:27               ` Roman Gushchin
2020-06-19  9:39                 ` Jesper Dangaard Brouer
2020-06-19 18:47                   ` Roman Gushchin
2020-06-18  1:18   ` Roman Gushchin
2020-06-18  9:27 ` Mike Rapoport
2020-06-18 20:43   ` Roman Gushchin
2020-06-21 22:57 ` Qian Cai
2020-06-21 23:34   ` Roman Gushchin
2020-06-21 23:53     ` Qian Cai
2020-06-22  3:07       ` Roman Gushchin

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200608230654.828134-10-guro@fb.com \
    --to=guro@fb.com \
    --cc=akpm@linux-foundation.org \
    --cc=cl@linux.com \
    --cc=hannes@cmpxchg.org \
    --cc=kernel-team@fb.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mhocko@kernel.org \
    --cc=shakeelb@google.com \
    --cc=vbabka@suse.cz \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

LKML Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/lkml/0 lkml/git/0.git
	git clone --mirror https://lore.kernel.org/lkml/1 lkml/git/1.git
	git clone --mirror https://lore.kernel.org/lkml/2 lkml/git/2.git
	git clone --mirror https://lore.kernel.org/lkml/3 lkml/git/3.git
	git clone --mirror https://lore.kernel.org/lkml/4 lkml/git/4.git
	git clone --mirror https://lore.kernel.org/lkml/5 lkml/git/5.git
	git clone --mirror https://lore.kernel.org/lkml/6 lkml/git/6.git
	git clone --mirror https://lore.kernel.org/lkml/7 lkml/git/7.git
	git clone --mirror https://lore.kernel.org/lkml/8 lkml/git/8.git
	git clone --mirror https://lore.kernel.org/lkml/9 lkml/git/9.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 lkml lkml/ https://lore.kernel.org/lkml \
		linux-kernel@vger.kernel.org
	public-inbox-index lkml

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-kernel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git