| 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
| ||
|
Message-Id: <1351771665-11076-10-git-send-email-glommer@parallels.com>
Date: Thu, 1 Nov 2012 16:07:25 +0400
From: Glauber Costa <glommer@...allels.com>
To: <linux-mm@...ck.org>
Cc: <linux-kernel@...r.kernel.org>,
Andrew Morton <akpm@...ux-foundation.org>,
<kamezawa.hiroyu@...fujitsu.com>,
Johannes Weiner <hannes@...xchg.org>,
Tejun Heo <tj@...nel.org>, Michal Hocko <mhocko@...e.cz>,
Christoph Lameter <cl@...ux.com>,
Pekka Enberg <penberg@...nel.org>,
David Rientjes <rientjes@...gle.com>,
Glauber Costa <glommer@...allels.com>,
Pekka Enberg <penberg@...helsinki.fi>,
Suleiman Souhlal <suleiman@...gle.com>
Subject: [PATCH v6 09/29] memcg: kmem accounting lifecycle management
Because kmem charges can outlive the cgroup, we need to make sure that
we won't free the memcg structure while charges are still in flight.
For reviewing simplicity, the charge functions will issue
mem_cgroup_get() at every charge, and mem_cgroup_put() at every
uncharge.
This can get expensive, however, and we can do better. mem_cgroup_get()
only really needs to be issued once: when the first limit is set. In the
same spirit, we only need to issue mem_cgroup_put() when the last charge
is gone.
We'll need an extra bit in kmem_account_flags for that: KMEM_ACCOUNTED_DEAD.
it will be set when the cgroup dies, if there are charges in the group.
If there aren't, we can proceed right away.
Our uncharge function will have to test that bit every time the charges
drop to 0. Because that is not the likely output of
res_counter_uncharge, this should not impose a big hit on us: it is
certainly much better than a reference count decrease at every
operation.
[ v3: merged all lifecycle related patches in one ]
[ v5: changed memcg_kmem_dead's name ]
Signed-off-by: Glauber Costa <glommer@...allels.com>
Acked-by: Michal Hocko <mhocko@...e.cz>
Acked-by: Kamezawa Hiroyuki <kamezawa.hiroyu@...fujitsu.com>
CC: Christoph Lameter <cl@...ux.com>
CC: Pekka Enberg <penberg@...helsinki.fi>
CC: Johannes Weiner <hannes@...xchg.org>
CC: Suleiman Souhlal <suleiman@...gle.com>
CC: Tejun Heo <tj@...nel.org>
---
mm/memcontrol.c | 57 ++++++++++++++++++++++++++++++++++++++++++++++++++-------
1 file changed, 50 insertions(+), 7 deletions(-)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 1eefb64..91a021a 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -344,6 +344,7 @@ struct mem_cgroup {
/* internal only representation about the status of kmem accounting. */
enum {
KMEM_ACCOUNTED_ACTIVE = 0, /* accounted by this cgroup itself */
+ KMEM_ACCOUNTED_DEAD, /* dead memcg with pending kmem charges */
};
#define KMEM_ACCOUNTED_MASK (1 << KMEM_ACCOUNTED_ACTIVE)
@@ -353,6 +354,23 @@ static inline void memcg_kmem_set_active(struct mem_cgroup *memcg)
{
set_bit(KMEM_ACCOUNTED_ACTIVE, &memcg->kmem_account_flags);
}
+
+static bool memcg_kmem_is_active(struct mem_cgroup *memcg)
+{
+ return test_bit(KMEM_ACCOUNTED_ACTIVE, &memcg->kmem_account_flags);
+}
+
+static void memcg_kmem_mark_dead(struct mem_cgroup *memcg)
+{
+ if (test_bit(KMEM_ACCOUNTED_ACTIVE, &memcg->kmem_account_flags))
+ set_bit(KMEM_ACCOUNTED_DEAD, &memcg->kmem_account_flags);
+}
+
+static bool memcg_kmem_test_and_clear_dead(struct mem_cgroup *memcg)
+{
+ return test_and_clear_bit(KMEM_ACCOUNTED_DEAD,
+ &memcg->kmem_account_flags);
+}
#endif
/* Stuffs for move charges at task migration. */
@@ -2691,10 +2709,16 @@ static int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, u64 size)
static void memcg_uncharge_kmem(struct mem_cgroup *memcg, u64 size)
{
- res_counter_uncharge(&memcg->kmem, size);
res_counter_uncharge(&memcg->res, size);
if (do_swap_account)
res_counter_uncharge(&memcg->memsw, size);
+
+ /* Not down to 0 */
+ if (res_counter_uncharge(&memcg->kmem, size))
+ return;
+
+ if (memcg_kmem_test_and_clear_dead(memcg))
+ mem_cgroup_put(memcg);
}
/*
@@ -2733,13 +2757,9 @@ __memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **_memcg, int order)
return true;
}
- mem_cgroup_get(memcg);
-
ret = memcg_charge_kmem(memcg, gfp, PAGE_SIZE << order);
if (!ret)
*_memcg = memcg;
- else
- mem_cgroup_put(memcg);
css_put(&memcg->css);
return (ret == 0);
@@ -2755,7 +2775,6 @@ void __memcg_kmem_commit_charge(struct page *page, struct mem_cgroup *memcg,
/* The page allocation failed. Revert */
if (!page) {
memcg_uncharge_kmem(memcg, PAGE_SIZE << order);
- mem_cgroup_put(memcg);
return;
}
@@ -2796,7 +2815,6 @@ void __memcg_kmem_uncharge_pages(struct page *page, int order)
VM_BUG_ON(mem_cgroup_is_root(memcg));
memcg_uncharge_kmem(memcg, PAGE_SIZE << order);
- mem_cgroup_put(memcg);
}
#endif /* CONFIG_MEMCG_KMEM */
@@ -4180,6 +4198,13 @@ static int memcg_update_kmem_limit(struct cgroup *cont, u64 val)
VM_BUG_ON(ret);
memcg_kmem_set_active(memcg);
+ /*
+ * kmem charges can outlive the cgroup. In the case of slab
+ * pages, for instance, a page contain objects from various
+ * processes, so it is unfeasible to migrate them away. We
+ * need to reference count the memcg because of that.
+ */
+ mem_cgroup_get(memcg);
} else
ret = res_counter_set_limit(&memcg->kmem, val);
out:
@@ -4195,6 +4220,10 @@ static void memcg_propagate_kmem(struct mem_cgroup *memcg)
if (!parent)
return;
memcg->kmem_account_flags = parent->kmem_account_flags;
+#ifdef CONFIG_MEMCG_KMEM
+ if (memcg_kmem_is_active(memcg))
+ mem_cgroup_get(memcg);
+#endif
}
/*
@@ -4883,6 +4912,20 @@ static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
static void kmem_cgroup_destroy(struct mem_cgroup *memcg)
{
mem_cgroup_sockets_destroy(memcg);
+
+ memcg_kmem_mark_dead(memcg);
+
+ if (res_counter_read_u64(&memcg->kmem, RES_USAGE) != 0)
+ return;
+
+ /*
+ * Charges already down to 0, undo mem_cgroup_get() done in the charge
+ * path here, being careful not to race with memcg_uncharge_kmem: it is
+ * possible that the charges went down to 0 between mark_dead and the
+ * res_counter read, so in that case, we don't need the put
+ */
+ if (memcg_kmem_test_and_clear_dead(memcg))
+ mem_cgroup_put(memcg);
}
#else
static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
--
1.7.11.7
--
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/
Powered by blists - more mailing lists