linux-kernel - [PATCH v4 17/25] skip memcg kmem allocations in specified code regions

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <1340015298-14133-18-git-send-email-glommer@parallels.com>
Date:	Mon, 18 Jun 2012 14:28:10 +0400
From:	Glauber Costa <glommer@...allels.com>
To:	<linux-mm@...ck.org>
Cc:	Pekka Enberg <penberg@...nel.org>, Cristoph Lameter <cl@...ux.com>,
	David Rientjes <rientjes@...gle.com>,
	<cgroups@...r.kernel.org>, <devel@...nvz.org>,
	<kamezawa.hiroyu@...fujitsu.com>, <linux-kernel@...r.kernel.org>,
	Frederic Weisbecker <fweisbec@...il.com>,
	Suleiman Souhlal <suleiman@...gle.com>,
	Glauber Costa <glommer@...allels.com>,
	Pekka Enberg <penberg@...helsinki.fi>,
	Michal Hocko <mhocko@...e.cz>,
	Johannes Weiner <hannes@...xchg.org>
Subject: [PATCH v4 17/25] skip memcg kmem allocations in specified code regions

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@...allels.com>
CC: Christoph Lameter <cl@...ux.com>
CC: Pekka Enberg <penberg@...helsinki.fi>
CC: Michal Hocko <mhocko@...e.cz>
CC: Kamezawa Hiroyuki <kamezawa.hiroyu@...fujitsu.com>
CC: Johannes Weiner <hannes@...xchg.org>
CC: Suleiman Souhlal <suleiman@...gle.com>
---
 include/linux/sched.h |    1 +
 mm/memcontrol.c       |   26 ++++++++++++++++++++++++++
 2 files changed, 27 insertions(+)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 81a173c..0761dda 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;
+	unsigned int 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 324e550..233d3bc 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -479,6 +479,22 @@ 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;
+
+	current->memcg_kmem_skip_account++;
+}
+
+static void memcg_resume_kmem_account(void)
+{
+	if (!current->mm)
+		return;
+
+	current->memcg_kmem_skip_account--;
+}
+
 static char *mem_cgroup_cache_name(struct mem_cgroup *memcg, struct kmem_cache *cachep)
 {
 	char *name;
@@ -555,7 +571,9 @@ 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;
@@ -646,7 +664,9 @@ 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;
@@ -681,6 +701,9 @@ struct kmem_cache *__mem_cgroup_get_kmem_cache(struct kmem_cache *cachep,
 	int idx;
 	struct task_struct *p;
 
+	if (!current->mm || current->memcg_kmem_skip_account)
+		return cachep;
+
 	if (cachep->memcg_params.memcg)
 		return cachep;
 
@@ -713,6 +736,9 @@ bool __mem_cgroup_new_kmem_page(gfp_t gfp, void *_handle, int order)
 	struct task_struct *p;
 
 	handle = NULL;
+	if (current->memcg_kmem_skip_account)
+		return true;
+
 	rcu_read_lock();
 	p = rcu_dereference(current->mm->owner);
 	memcg = mem_cgroup_from_task(p);
-- 
1.7.10.2

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/