From: Roman Gushchin <guro@fb.com>
To: <linux-mm@kvack.org>, Andrew Morton <akpm@linux-foundation.org>
Cc: Michal Hocko <mhocko@kernel.org>,
Johannes Weiner <hannes@cmpxchg.org>,
Shakeel Butt <shakeelb@google.com>,
Vladimir Davydov <vdavydov.dev@gmail.com>,
<linux-kernel@vger.kernel.org>, <kernel-team@fb.com>,
Bharata B Rao <bharata@linux.ibm.com>,
Yafang Shao <laoar.shao@gmail.com>, Roman Gushchin <guro@fb.com>
Subject: [PATCH v2 17/28] mm: memcg/slab: save obj_cgroup for non-root slab objects
Date: Mon, 27 Jan 2020 09:34:42 -0800 [thread overview]
Message-ID: <20200127173453.2089565-18-guro@fb.com> (raw)
In-Reply-To: <20200127173453.2089565-1-guro@fb.com>
Store the obj_cgroup pointer in the corresponding place of
page->obj_cgroups for each allocated non-root slab object.
Make sure that each allocated object holds a reference to obj_cgroup.
Objcg pointer is obtained from the memcg->objcg dereferencing
in memcg_kmem_get_cache() and passed from pre_alloc_hook to
post_alloc_hook. Then in case of successful allocation(s) it's
getting stored in the page->obj_cgroups vector.
The objcg obtaining part look a bit bulky now, but it will be simplified
by next commits in the series.
Signed-off-by: Roman Gushchin <guro@fb.com>
---
include/linux/memcontrol.h | 3 +-
mm/memcontrol.c | 14 +++++++--
mm/slab.c | 18 +++++++-----
mm/slab.h | 60 ++++++++++++++++++++++++++++++++++----
mm/slub.c | 14 +++++----
5 files changed, 88 insertions(+), 21 deletions(-)
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 30bbea3f85e2..54bfb26b5016 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -1431,7 +1431,8 @@ static inline void memcg_set_shrinker_bit(struct mem_cgroup *memcg,
}
#endif
-struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep);
+struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep,
+ struct obj_cgroup **objcgp);
void memcg_kmem_put_cache(struct kmem_cache *cachep);
#ifdef CONFIG_MEMCG_KMEM
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 94337ab1ebe9..0e9fe272e688 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2896,7 +2896,8 @@ static inline bool memcg_kmem_bypass(void)
* done with it, memcg_kmem_put_cache() must be called to release the
* reference.
*/
-struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep)
+struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep,
+ struct obj_cgroup **objcgp)
{
struct mem_cgroup *memcg;
struct kmem_cache *memcg_cachep;
@@ -2952,8 +2953,17 @@ struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep)
*/
if (unlikely(!memcg_cachep))
memcg_schedule_kmem_cache_create(memcg, cachep);
- else if (percpu_ref_tryget(&memcg_cachep->memcg_params.refcnt))
+ else if (percpu_ref_tryget(&memcg_cachep->memcg_params.refcnt)) {
+ struct obj_cgroup *objcg = rcu_dereference(memcg->objcg);
+
+ if (!objcg || !obj_cgroup_tryget(objcg)) {
+ percpu_ref_put(&memcg_cachep->memcg_params.refcnt);
+ goto out_unlock;
+ }
+
+ *objcgp = objcg;
cachep = memcg_cachep;
+ }
out_unlock:
rcu_read_unlock();
return cachep;
diff --git a/mm/slab.c b/mm/slab.c
index 22e161b57367..f16e896d5a3d 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -3223,9 +3223,10 @@ slab_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid,
unsigned long save_flags;
void *ptr;
int slab_node = numa_mem_id();
+ struct obj_cgroup *objcg = NULL;
flags &= gfp_allowed_mask;
- cachep = slab_pre_alloc_hook(cachep, flags);
+ cachep = slab_pre_alloc_hook(cachep, &objcg, 1, flags);
if (unlikely(!cachep))
return NULL;
@@ -3261,7 +3262,7 @@ slab_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid,
if (unlikely(slab_want_init_on_alloc(flags, cachep)) && ptr)
memset(ptr, 0, cachep->object_size);
- slab_post_alloc_hook(cachep, flags, 1, &ptr);
+ slab_post_alloc_hook(cachep, objcg, flags, 1, &ptr);
return ptr;
}
@@ -3302,9 +3303,10 @@ slab_alloc(struct kmem_cache *cachep, gfp_t flags, unsigned long caller)
{
unsigned long save_flags;
void *objp;
+ struct obj_cgroup *objcg = NULL;
flags &= gfp_allowed_mask;
- cachep = slab_pre_alloc_hook(cachep, flags);
+ cachep = slab_pre_alloc_hook(cachep, &objcg, 1, flags);
if (unlikely(!cachep))
return NULL;
@@ -3318,7 +3320,7 @@ slab_alloc(struct kmem_cache *cachep, gfp_t flags, unsigned long caller)
if (unlikely(slab_want_init_on_alloc(flags, cachep)) && objp)
memset(objp, 0, cachep->object_size);
- slab_post_alloc_hook(cachep, flags, 1, &objp);
+ slab_post_alloc_hook(cachep, objcg, flags, 1, &objp);
return objp;
}
@@ -3440,6 +3442,7 @@ void ___cache_free(struct kmem_cache *cachep, void *objp,
memset(objp, 0, cachep->object_size);
kmemleak_free_recursive(objp, cachep->flags);
objp = cache_free_debugcheck(cachep, objp, caller);
+ memcg_slab_free_hook(cachep, virt_to_head_page(objp), objp);
/*
* Skip calling cache_free_alien() when the platform is not numa.
@@ -3505,8 +3508,9 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
void **p)
{
size_t i;
+ struct obj_cgroup *objcg = NULL;
- s = slab_pre_alloc_hook(s, flags);
+ s = slab_pre_alloc_hook(s, &objcg, size, flags);
if (!s)
return 0;
@@ -3529,13 +3533,13 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
for (i = 0; i < size; i++)
memset(p[i], 0, s->object_size);
- slab_post_alloc_hook(s, flags, size, p);
+ slab_post_alloc_hook(s, objcg, flags, size, p);
/* FIXME: Trace call missing. Christoph would like a bulk variant */
return size;
error:
local_irq_enable();
cache_alloc_debugcheck_after_bulk(s, flags, i, p, _RET_IP_);
- slab_post_alloc_hook(s, flags, i, p);
+ slab_post_alloc_hook(s, objcg, flags, i, p);
__kmem_cache_free_bulk(s, i, p);
return 0;
}
diff --git a/mm/slab.h b/mm/slab.h
index 8ee8c3a250ac..0fdbeaf4aa8c 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -437,6 +437,41 @@ static inline void memcg_free_page_obj_cgroups(struct page *page)
page->obj_cgroups = NULL;
}
+static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s,
+ struct obj_cgroup *objcg,
+ size_t size, void **p)
+{
+ struct page *page;
+ unsigned long off;
+ size_t i;
+
+ for (i = 0; i < size; i++) {
+ if (likely(p[i])) {
+ page = virt_to_head_page(p[i]);
+ off = obj_to_index(s, page, p[i]);
+ obj_cgroup_get(objcg);
+ page_obj_cgroups(page)[off] = objcg;
+ }
+ }
+ obj_cgroup_put(objcg);
+ memcg_kmem_put_cache(s);
+}
+
+static inline void memcg_slab_free_hook(struct kmem_cache *s, struct page *page,
+ void *p)
+{
+ struct obj_cgroup *objcg;
+ unsigned int off;
+
+ if (!memcg_kmem_enabled() || is_root_cache(s))
+ return;
+
+ off = obj_to_index(s, page, p);
+ objcg = page_obj_cgroups(page)[off];
+ page_obj_cgroups(page)[off] = NULL;
+ obj_cgroup_put(objcg);
+}
+
extern void slab_init_memcg_params(struct kmem_cache *);
extern void memcg_link_cache(struct kmem_cache *s, struct mem_cgroup *memcg);
@@ -496,6 +531,17 @@ static inline void memcg_free_page_obj_cgroups(struct page *page)
{
}
+static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s,
+ struct obj_cgroup *objcg,
+ size_t size, void **p)
+{
+}
+
+static inline void memcg_slab_free_hook(struct kmem_cache *s, struct page *page,
+ void *p)
+{
+}
+
static inline void slab_init_memcg_params(struct kmem_cache *s)
{
}
@@ -605,7 +651,8 @@ static inline size_t slab_ksize(const struct kmem_cache *s)
}
static inline struct kmem_cache *slab_pre_alloc_hook(struct kmem_cache *s,
- gfp_t flags)
+ struct obj_cgroup **objcgp,
+ size_t size, gfp_t flags)
{
flags &= gfp_allowed_mask;
@@ -619,13 +666,14 @@ 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);
+ return memcg_kmem_get_cache(s, objcgp);
return s;
}
-static inline void slab_post_alloc_hook(struct kmem_cache *s, gfp_t flags,
- size_t size, void **p)
+static inline void slab_post_alloc_hook(struct kmem_cache *s,
+ struct obj_cgroup *objcg,
+ gfp_t flags, size_t size, void **p)
{
size_t i;
@@ -637,8 +685,8 @@ static inline void slab_post_alloc_hook(struct kmem_cache *s, gfp_t flags,
s->flags, flags);
}
- if (memcg_kmem_enabled())
- memcg_kmem_put_cache(s);
+ if (!is_root_cache(s))
+ memcg_slab_post_alloc_hook(s, objcg, size, p);
}
#ifndef CONFIG_SLOB
diff --git a/mm/slub.c b/mm/slub.c
index 165e43076c8b..6365e89cd503 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2698,8 +2698,9 @@ static __always_inline void *slab_alloc_node(struct kmem_cache *s,
struct kmem_cache_cpu *c;
struct page *page;
unsigned long tid;
+ struct obj_cgroup *objcg = NULL;
- s = slab_pre_alloc_hook(s, gfpflags);
+ s = slab_pre_alloc_hook(s, &objcg, 1, gfpflags);
if (!s)
return NULL;
redo:
@@ -2775,7 +2776,7 @@ static __always_inline void *slab_alloc_node(struct kmem_cache *s,
if (unlikely(slab_want_init_on_alloc(gfpflags, s)) && object)
memset(object, 0, s->object_size);
- slab_post_alloc_hook(s, gfpflags, 1, &object);
+ slab_post_alloc_hook(s, objcg, gfpflags, 1, &object);
return object;
}
@@ -2980,6 +2981,8 @@ static __always_inline void do_slab_free(struct kmem_cache *s,
void *tail_obj = tail ? : head;
struct kmem_cache_cpu *c;
unsigned long tid;
+
+ memcg_slab_free_hook(s, page, head);
redo:
/*
* Determine the currently cpus per cpu slab.
@@ -3157,9 +3160,10 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
{
struct kmem_cache_cpu *c;
int i;
+ struct obj_cgroup *objcg = NULL;
/* memcg and kmem_cache debug support */
- s = slab_pre_alloc_hook(s, flags);
+ s = slab_pre_alloc_hook(s, &objcg, size, flags);
if (unlikely(!s))
return false;
/*
@@ -3204,11 +3208,11 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
}
/* memcg and kmem_cache debug support */
- slab_post_alloc_hook(s, flags, size, p);
+ slab_post_alloc_hook(s, objcg, flags, size, p);
return i;
error:
local_irq_enable();
- slab_post_alloc_hook(s, flags, i, p);
+ slab_post_alloc_hook(s, objcg, flags, i, p);
__kmem_cache_free_bulk(s, i, p);
return 0;
}
--
2.24.1
next prev parent reply other threads:[~2020-01-27 17:43 UTC|newest]
Thread overview: 84+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-01-27 17:34 [PATCH v2 00/28] The new cgroup slab memory controller Roman Gushchin
2020-01-27 17:34 ` [PATCH v2 01/28] mm: kmem: cleanup (__)memcg_kmem_charge_memcg() arguments Roman Gushchin
2020-01-27 17:34 ` [PATCH v2 02/28] mm: kmem: cleanup memcg_kmem_uncharge_memcg() arguments Roman Gushchin
2020-01-27 17:34 ` [PATCH v2 03/28] mm: kmem: rename memcg_kmem_(un)charge() into memcg_kmem_(un)charge_page() Roman Gushchin
2020-01-27 17:34 ` [PATCH v2 04/28] mm: kmem: switch to nr_pages in (__)memcg_kmem_charge_memcg() Roman Gushchin
2020-01-27 17:34 ` [PATCH v2 05/28] mm: memcg/slab: cache page number in memcg_(un)charge_slab() Roman Gushchin
2020-01-27 17:34 ` [PATCH v2 06/28] mm: kmem: rename (__)memcg_kmem_(un)charge_memcg() to __memcg_kmem_(un)charge() Roman Gushchin
2020-01-27 17:34 ` [PATCH v2 07/28] mm: memcg/slab: introduce mem_cgroup_from_obj() Roman Gushchin
2020-02-03 16:05 ` Johannes Weiner
2020-01-27 17:34 ` [PATCH v2 08/28] mm: fork: fix kernel_stack memcg stats for various stack implementations Roman Gushchin
2020-02-03 16:12 ` Johannes Weiner
2020-01-27 17:34 ` [PATCH v2 09/28] mm: memcg/slab: rename __mod_lruvec_slab_state() into __mod_lruvec_obj_state() Roman Gushchin
2020-02-03 16:13 ` Johannes Weiner
2020-01-27 17:34 ` [PATCH v2 10/28] mm: memcg: introduce mod_lruvec_memcg_state() Roman Gushchin
2020-02-03 17:39 ` Johannes Weiner
2020-01-27 17:34 ` [PATCH v2 11/28] mm: slub: implement SLUB version of obj_to_index() Roman Gushchin
2020-02-03 17:44 ` Johannes Weiner
2020-01-27 17:34 ` [PATCH v2 12/28] mm: vmstat: use s32 for vm_node_stat_diff in struct per_cpu_nodestat Roman Gushchin
2020-02-03 17:58 ` Johannes Weiner
2020-02-03 18:25 ` Roman Gushchin
2020-02-03 20:34 ` Johannes Weiner
2020-02-03 22:28 ` Roman Gushchin
2020-02-03 22:39 ` Johannes Weiner
2020-02-04 1:44 ` Roman Gushchin
2020-01-27 17:34 ` [PATCH v2 13/28] mm: vmstat: convert slab vmstat counter to bytes Roman Gushchin
2020-01-27 17:34 ` [PATCH v2 14/28] mm: memcontrol: decouple reference counting from page accounting Roman Gushchin
2020-01-27 17:34 ` [PATCH v2 15/28] mm: memcg/slab: obj_cgroup API Roman Gushchin
2020-02-03 19:31 ` Johannes Weiner
2020-01-27 17:34 ` [PATCH v2 16/28] mm: memcg/slab: allocate obj_cgroups for non-root slab pages Roman Gushchin
2020-02-03 18:27 ` Johannes Weiner
2020-02-03 18:34 ` Roman Gushchin
2020-02-03 20:46 ` Johannes Weiner
2020-02-03 21:19 ` Roman Gushchin
2020-02-03 22:29 ` Johannes Weiner
2020-01-27 17:34 ` Roman Gushchin [this message]
2020-02-03 19:53 ` [PATCH v2 17/28] mm: memcg/slab: save obj_cgroup for non-root slab objects Johannes Weiner
2020-01-27 17:34 ` [PATCH v2 18/28] mm: memcg/slab: charge individual slab objects instead of pages Roman Gushchin
2020-01-27 17:34 ` [PATCH v2 19/28] mm: memcg/slab: deprecate memory.kmem.slabinfo Roman Gushchin
2020-01-27 17:34 ` [PATCH v2 20/28] mm: memcg/slab: move memcg_kmem_bypass() to memcontrol.h Roman Gushchin
2020-01-27 17:34 ` [PATCH v2 21/28] mm: memcg/slab: use a single set of kmem_caches for all memory cgroups Roman Gushchin
2020-02-03 19:50 ` Johannes Weiner
2020-02-03 20:58 ` Roman Gushchin
2020-02-03 22:17 ` Johannes Weiner
2020-02-03 22:38 ` Roman Gushchin
2020-02-04 1:15 ` Roman Gushchin
2020-02-04 2:47 ` Johannes Weiner
2020-02-04 4:35 ` Roman Gushchin
2020-02-04 18:41 ` Johannes Weiner
2020-02-05 15:58 ` Roman Gushchin
2020-01-27 17:34 ` [PATCH v2 22/28] mm: memcg/slab: simplify memcg cache creation Roman Gushchin
2020-01-27 17:34 ` [PATCH v2 23/28] mm: memcg/slab: deprecate memcg_kmem_get_cache() Roman Gushchin
2020-01-27 17:34 ` [PATCH v2 24/28] mm: memcg/slab: deprecate slab_root_caches Roman Gushchin
2020-01-27 17:34 ` [PATCH v2 25/28] mm: memcg/slab: remove redundant check in memcg_accumulate_slabinfo() Roman Gushchin
2020-01-27 17:34 ` [PATCH v2 26/28] tools/cgroup: add slabinfo.py tool Roman Gushchin
2020-01-27 17:34 ` [PATCH v2 27/28] tools/cgroup: make slabinfo.py compatible with new slab controller Roman Gushchin
2020-01-30 2:17 ` Bharata B Rao
2020-01-30 2:44 ` Roman Gushchin
2020-01-31 22:24 ` Roman Gushchin
2020-02-12 5:21 ` Bharata B Rao
2020-02-12 20:42 ` Roman Gushchin
2020-01-27 17:34 ` [PATCH v2 28/28] kselftests: cgroup: add kernel memory accounting tests Roman Gushchin
2020-01-30 2:06 ` [PATCH v2 00/28] The new cgroup slab memory controller Bharata B Rao
2020-01-30 2:41 ` Roman Gushchin
2020-08-12 23:16 ` Pavel Tatashin
2020-08-12 23:18 ` Pavel Tatashin
2020-08-13 0:04 ` Roman Gushchin
2020-08-13 0:31 ` Pavel Tatashin
2020-08-28 16:47 ` Pavel Tatashin
2020-09-01 5:28 ` Bharata B Rao
2020-09-01 12:52 ` Pavel Tatashin
2020-09-02 6:23 ` Bharata B Rao
2020-09-02 12:34 ` Pavel Tatashin
2020-09-02 9:53 ` Vlastimil Babka
2020-09-02 10:39 ` David Hildenbrand
2020-09-02 12:42 ` Pavel Tatashin
2020-09-02 13:50 ` Michal Hocko
2020-09-02 14:20 ` Pavel Tatashin
2020-09-03 18:09 ` David Hildenbrand
2020-09-02 11:26 ` Michal Hocko
2020-09-02 12:51 ` Pavel Tatashin
2020-09-02 13:51 ` Michal Hocko
2020-09-02 11:32 ` Michal Hocko
2020-09-02 12:53 ` Pavel Tatashin
2020-09-02 13:52 ` Michal Hocko
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=20200127173453.2089565-18-guro@fb.com \
--to=guro@fb.com \
--cc=akpm@linux-foundation.org \
--cc=bharata@linux.ibm.com \
--cc=hannes@cmpxchg.org \
--cc=kernel-team@fb.com \
--cc=laoar.shao@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mhocko@kernel.org \
--cc=shakeelb@google.com \
--cc=vdavydov.dev@gmail.com \
/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
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox