linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Glauber Costa <glommer@parallels.com>
To: linux-kernel@vger.kernel.org
Cc: cgroups@vger.kernel.org, linux-mm@kvack.org,
	kamezawa.hiroyu@jp.fujitsu.com, Tejun Heo <tj@kernel.org>,
	Li Zefan <lizefan@huawei.com>, Greg Thelen <gthelen@google.com>,
	Suleiman Souhlal <suleiman@google.com>,
	Michal Hocko <mhocko@suse.cz>,
	Johannes Weiner <hannes@cmpxchg.org>,
	devel@openvz.org, Glauber Costa <glommer@parallels.com>,
	Christoph Lameter <cl@linux.com>,
	Pekka Enberg <penberg@cs.helsinki.fi>
Subject: [PATCH v2 19/29] skip memcg kmem allocations in specified code regions
Date: Fri, 11 May 2012 14:44:21 -0300	[thread overview]
Message-ID: <1336758272-24284-20-git-send-email-glommer@parallels.com> (raw)
In-Reply-To: <1336758272-24284-1-git-send-email-glommer@parallels.com>

This patch creates a mechanism that skip memcg allocations during
certain pieces of our core code. It basically works in the same way
as preempt_disable()/preempt_enable(): By marking a region under
which all allocations will be accounted to the root memcg.

We need this to prevent races in early cache creation, when we
allocate data using caches that are not necessarily created already.

Signed-off-by: Glauber Costa <glommer@parallels.com>
CC: Christoph Lameter <cl@linux.com>
CC: Pekka Enberg <penberg@cs.helsinki.fi>
CC: Michal Hocko <mhocko@suse.cz>
CC: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
CC: Johannes Weiner <hannes@cmpxchg.org>
CC: Suleiman Souhlal <suleiman@google.com>
---
 include/linux/sched.h |    1 +
 mm/memcontrol.c       |   25 +++++++++++++++++++++++++
 2 files changed, 26 insertions(+), 0 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 81a173c..0501114 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1613,6 +1613,7 @@ struct task_struct {
 		unsigned long nr_pages;	/* uncharged usage */
 		unsigned long memsw_nr_pages; /* uncharged mem+swap usage */
 	} memcg_batch;
+	atomic_t memcg_kmem_skip_account;
 #endif
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 	atomic_t ptrace_bp_refcnt;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 5a7416b..c4ecf9c 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -479,6 +479,21 @@ struct cg_proto *tcp_proto_cgroup(struct mem_cgroup *memcg)
 EXPORT_SYMBOL(tcp_proto_cgroup);
 #endif /* CONFIG_INET */
 
+static void memcg_stop_kmem_account(void)
+{
+	if (!current->mm)
+		return;
+
+	atomic_inc(&current->memcg_kmem_skip_account);
+}
+
+static void memcg_resume_kmem_account(void)
+{
+	if (!current->mm)
+		return;
+
+	atomic_dec(&current->memcg_kmem_skip_account);
+}
 char *mem_cgroup_cache_name(struct mem_cgroup *memcg, struct kmem_cache *cachep)
 {
 	char *name;
@@ -540,7 +555,9 @@ static struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *memcg,
 	if (new_cachep)
 		goto out;
 
+	memcg_stop_kmem_account();
 	new_cachep = kmem_cache_dup(memcg, cachep);
+	memcg_resume_kmem_account();
 
 	if (new_cachep == NULL) {
 		new_cachep = cachep;
@@ -631,7 +648,9 @@ static void memcg_create_cache_enqueue(struct mem_cgroup *memcg,
 	if (!css_tryget(&memcg->css))
 		return;
 
+	memcg_stop_kmem_account();
 	cw = kmalloc(sizeof(struct create_work), GFP_NOWAIT);
+	memcg_resume_kmem_account();
 	if (cw == NULL) {
 		css_put(&memcg->css);
 		return;
@@ -666,6 +685,9 @@ struct kmem_cache *__mem_cgroup_get_kmem_cache(struct kmem_cache *cachep,
 	int idx;
 	struct task_struct *p;
 
+	if (!current->mm || atomic_read(&current->memcg_kmem_skip_account))
+		return cachep;
+
 	gfp |=  cachep->allocflags;
 
 	if (cachep->memcg_params.memcg)
@@ -700,6 +722,9 @@ bool __mem_cgroup_new_kmem_page(struct page *page, gfp_t gfp)
 	if (!current->mm || in_interrupt())
 		return true;
 
+	if (!current->mm || atomic_read(&current->memcg_kmem_skip_account))
+		return true;
+
 	rcu_read_lock();
 	p = rcu_dereference(current->mm->owner);
 	memcg = mem_cgroup_from_task(p);
-- 
1.7.7.6

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

  parent reply	other threads:[~2012-05-11 17:50 UTC|newest]

Thread overview: 63+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-05-11 17:44 [PATCH v2 00/29] kmem limitation for memcg Glauber Costa
2012-05-11 17:44 ` [PATCH v2 01/29] slab: dup name string Glauber Costa
2012-05-15 22:04   ` David Rientjes
2012-05-16  6:12     ` Glauber Costa
2012-05-11 17:44 ` [PATCH v2 02/29] slub: fix slab_state for slub Glauber Costa
2012-05-11 17:51   ` Christoph Lameter
2012-05-15 21:55   ` David Rientjes
2012-05-16  6:10     ` Glauber Costa
2012-05-17 10:14     ` Glauber Costa
2012-05-11 17:44 ` [PATCH v2 03/29] memcg: Always free struct memcg through schedule_work() Glauber Costa
2012-05-11 17:44 ` [PATCH v2 04/29] slub: always get the cache from its page in kfree Glauber Costa
2012-05-11 17:53   ` Christoph Lameter
2012-05-11 17:57     ` Glauber Costa
2012-05-11 18:06       ` Christoph Lameter
2012-05-11 18:11         ` Glauber Costa
2012-05-11 18:17           ` Christoph Lameter
2012-05-11 18:20             ` Glauber Costa
2012-05-11 18:32               ` Christoph Lameter
2012-05-11 18:42                 ` Glauber Costa
2012-05-11 18:56                   ` Christoph Lameter
2012-05-11 18:58                     ` Glauber Costa
2012-05-11 19:09                       ` Christoph Lameter
2012-05-11 19:11                         ` Glauber Costa
2012-05-11 19:20                           ` Christoph Lameter
2012-05-11 19:24                             ` Glauber Costa
2012-05-11 17:44 ` [PATCH v2 05/29] slab: rename gfpflags to allocflags Glauber Costa
2012-05-11 17:54   ` Christoph Lameter
2012-05-15 21:57   ` David Rientjes
2012-05-11 17:44 ` [PATCH v2 06/29] memcg: Make it possible to use the stock for more than one page Glauber Costa
2012-05-11 17:44 ` [PATCH v2 07/29] memcg: Reclaim when more than one page needed Glauber Costa
2012-05-11 17:44 ` [PATCH v2 08/29] slab: use obj_size field of struct kmem_cache when not debugging Glauber Costa
2012-05-11 17:44 ` [PATCH v2 09/29] memcg: change defines to an enum Glauber Costa
2012-05-11 17:44 ` [PATCH v2 10/29] res_counter: don't force return value checking in res_counter_charge_nofail Glauber Costa
2012-05-11 17:44 ` [PATCH v2 11/29] cgroups: ability to stop res charge propagation on bounded ancestor Glauber Costa
2012-05-15  2:59   ` KAMEZAWA Hiroyuki
2012-05-16  6:16     ` Glauber Costa
2012-05-11 17:44 ` [PATCH v2 12/29] kmem slab accounting basic infrastructure Glauber Costa
2012-05-11 17:44 ` [PATCH v2 13/29] slab/slub: struct memcg_params Glauber Costa
2012-05-11 17:44 ` [PATCH v2 14/29] slub: consider a memcg parameter in kmem_create_cache Glauber Costa
2012-05-11 17:44 ` [PATCH v2 15/29] slab: pass memcg parameter to kmem_cache_create Glauber Costa
2012-05-11 17:44 ` [PATCH v2 16/29] slub: create duplicate cache Glauber Costa
2012-05-11 17:44 ` [PATCH v2 17/29] slab: " Glauber Costa
2012-05-11 17:44 ` [PATCH v2 18/29] memcg: kmem controller charge/uncharge infrastructure Glauber Costa
2012-05-15  2:57   ` KAMEZAWA Hiroyuki
2012-05-16  6:42     ` Glauber Costa
2012-05-16  8:18       ` KAMEZAWA Hiroyuki
2012-05-16  8:25         ` Glauber Costa
2012-05-16  9:15           ` KAMEZAWA Hiroyuki
2012-05-11 17:44 ` Glauber Costa [this message]
2012-05-15  2:46   ` [PATCH v2 19/29] skip memcg kmem allocations in specified code regions KAMEZAWA Hiroyuki
2012-05-16  6:19     ` Glauber Costa
2012-05-16  7:55       ` KAMEZAWA Hiroyuki
2012-05-11 17:44 ` [PATCH v2 20/29] slub: charge allocation to a memcg Glauber Costa
2012-05-11 17:44 ` [PATCH v2 21/29] slab: per-memcg accounting of slab caches Glauber Costa
2012-05-11 17:44 ` [PATCH v2 22/29] memcg: disable kmem code when not in use Glauber Costa
2012-05-11 17:44 ` [PATCH v2 23/29] memcg: destroy memcg caches Glauber Costa
2012-05-11 17:44 ` [PATCH v2 24/29] memcg/slub: shrink dead caches Glauber Costa
2012-05-11 17:44 ` [PATCH v2 25/29] memcg: Track all the memcg children of a kmem_cache Glauber Costa
2012-05-11 17:44 ` [PATCH v2 26/29] memcg: Per-memcg memory.kmem.slabinfo file Glauber Costa
2012-05-11 17:44 ` [PATCH v2 27/29] slub: create slabinfo file for memcg Glauber Costa
2012-05-11 17:44 ` [PATCH v2 28/29] slub: track all children of a kmem cache Glauber Costa
2012-05-11 17:44 ` [PATCH v2 29/29] Documentation: add documentation for slab tracker for memcg Glauber Costa
2012-05-11 18:05 ` [PATCH v2 00/29] kmem limitation " Glauber Costa

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=1336758272-24284-20-git-send-email-glommer@parallels.com \
    --to=glommer@parallels.com \
    --cc=cgroups@vger.kernel.org \
    --cc=cl@linux.com \
    --cc=devel@openvz.org \
    --cc=gthelen@google.com \
    --cc=hannes@cmpxchg.org \
    --cc=kamezawa.hiroyu@jp.fujitsu.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=lizefan@huawei.com \
    --cc=mhocko@suse.cz \
    --cc=penberg@cs.helsinki.fi \
    --cc=suleiman@google.com \
    --cc=tj@kernel.org \
    /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