From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1946063Ab2EKRve (ORCPT ); Fri, 11 May 2012 13:51:34 -0400 Received: from mailhub.sw.ru ([195.214.232.25]:4734 "EHLO relay.sw.ru" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1945946Ab2EKRv3 (ORCPT ); Fri, 11 May 2012 13:51:29 -0400 From: Glauber Costa To: Cc: , , , Tejun Heo , Li Zefan , Greg Thelen , Suleiman Souhlal , Michal Hocko , Johannes Weiner , , Glauber Costa , Christoph Lameter , Pekka Enberg Subject: [PATCH v2 19/29] skip memcg kmem allocations in specified code regions Date: Fri, 11 May 2012 14:44:21 -0300 Message-Id: <1336758272-24284-20-git-send-email-glommer@parallels.com> X-Mailer: git-send-email 1.7.7.6 In-Reply-To: <1336758272-24284-1-git-send-email-glommer@parallels.com> References: <1336758272-24284-1-git-send-email-glommer@parallels.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org 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 CC: Christoph Lameter CC: Pekka Enberg CC: Michal Hocko CC: Kamezawa Hiroyuki CC: Johannes Weiner CC: Suleiman Souhlal --- 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(¤t->memcg_kmem_skip_account); +} + +static void memcg_resume_kmem_account(void) +{ + if (!current->mm) + return; + + atomic_dec(¤t->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(¤t->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(¤t->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 From mboxrd@z Thu Jan 1 00:00:00 1970 From: Glauber Costa Subject: [PATCH v2 19/29] skip memcg kmem allocations in specified code regions Date: Fri, 11 May 2012 14:44:21 -0300 Message-ID: <1336758272-24284-20-git-send-email-glommer@parallels.com> References: <1336758272-24284-1-git-send-email-glommer@parallels.com> Return-path: In-Reply-To: <1336758272-24284-1-git-send-email-glommer@parallels.com> Sender: owner-linux-mm@kvack.org List-ID: MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit To: linux-kernel@vger.kernel.org Cc: cgroups@vger.kernel.org, linux-mm@kvack.org, kamezawa.hiroyu@jp.fujitsu.com, Tejun Heo , Li Zefan , Greg Thelen , Suleiman Souhlal , Michal Hocko , Johannes Weiner , devel@openvz.org, Glauber Costa , Christoph Lameter , Pekka Enberg 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 CC: Christoph Lameter CC: Pekka Enberg CC: Michal Hocko CC: Kamezawa Hiroyuki CC: Johannes Weiner CC: Suleiman Souhlal --- 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(¤t->memcg_kmem_skip_account); +} + +static void memcg_resume_kmem_account(void) +{ + if (!current->mm) + return; + + atomic_dec(¤t->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(¤t->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(¤t->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: email@kvack.org