memcg: get/put parents at create/free

The lifetime of struct cgroup and struct mem_cgroup is different and
mem_cgroup has its own reference count for handling references from
swap_cgroup.

This causes strange problem that the parent mem_cgroup dies while child
mem_cgroup alive, and this problem causes a bug in case of
use_hierarchy==1 because res_counter_uncharge climbs up the tree.

This patch is for avoiding it by getting the parent at create, and putting
it at freeing.

Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Reviewed-by; KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Balbir Singh <balbir@linux.vnet.ibm.com>
Cc: Pavel Emelyanov <xemul@openvz.org>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Paul Menage <menage@google.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 4d0ea3c..76feccd 100644 (file)
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -202,6 +202,7 @@ pcg_default_flags[NR_CHARGE_TYPE] = {
 
 static void mem_cgroup_get(struct mem_cgroup *mem);
 static void mem_cgroup_put(struct mem_cgroup *mem);
+static struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *mem);
 
 static void mem_cgroup_charge_statistics(struct mem_cgroup *mem,
                                         struct page_cgroup *pc,
@@ -2193,10 +2194,23 @@ static void mem_cgroup_get(struct mem_cgroup *mem)
 
 static void mem_cgroup_put(struct mem_cgroup *mem)
 {
-       if (atomic_dec_and_test(&mem->refcnt))
+       if (atomic_dec_and_test(&mem->refcnt)) {
+               struct mem_cgroup *parent = parent_mem_cgroup(mem);
                __mem_cgroup_free(mem);
+               if (parent)
+                       mem_cgroup_put(parent);
+       }
 }
 
+/*
+ * Returns the parent mem_cgroup in memcgroup hierarchy with hierarchy enabled.
+ */
+static struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *mem)
+{
+       if (!mem->res.parent)
+               return NULL;
+       return mem_cgroup_from_res_counter(mem->res.parent, res);
+}
 
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
 static void __init enable_swap_cgroup(void)
@@ -2235,6 +2249,13 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
        if (parent && parent->use_hierarchy) {
                res_counter_init(&mem->res, &parent->res);
                res_counter_init(&mem->memsw, &parent->memsw);
+               /*
+                * We increment refcnt of the parent to ensure that we can
+                * safely access it on res_counter_charge/uncharge.
+                * This refcnt will be decremented when freeing this
+                * mem_cgroup(see mem_cgroup_put).
+                */
+               mem_cgroup_get(parent);
        } else {
                res_counter_init(&mem->res, NULL);
                res_counter_init(&mem->memsw, NULL);