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.
Signed-off-by: Glauber Costa <glommer@parallels.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
Acked-by: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Suleiman Souhlal <suleiman@google.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Frederic Weisbecker <fweisbec@redhat.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: JoonSoo Kim <js1304@gmail.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index b9afa06..9a62ac3 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -346,6 +346,7 @@
/* 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)
@@ -355,6 +356,23 @@
{
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. */
@@ -2722,10 +2740,16 @@
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);
}
/*
@@ -2764,13 +2788,9 @@
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);
@@ -2786,7 +2806,6 @@
/* The page allocation failed. Revert */
if (!page) {
memcg_uncharge_kmem(memcg, PAGE_SIZE << order);
- mem_cgroup_put(memcg);
return;
}
@@ -2827,7 +2846,6 @@
VM_BUG_ON(mem_cgroup_is_root(memcg));
memcg_uncharge_kmem(memcg, PAGE_SIZE << order);
- mem_cgroup_put(memcg);
}
#endif /* CONFIG_MEMCG_KMEM */
@@ -4217,6 +4235,13 @@
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:
@@ -4232,6 +4257,10 @@
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
}
/*
@@ -4920,6 +4949,20 @@
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)