[PATCH 4.4 36/78] mm/memcontrol.c: fix use after free in mem_cgroup_iter()

From: Greg Kroah-Hartman
Date: Thu Aug 22 2019 - 13:45:32 EST


From: Miles Chen <miles.chen@xxxxxxxxxxxx>

commit 54a83d6bcbf8f4700013766b974bf9190d40b689 upstream.

This patch is sent to report an use after free in mem_cgroup_iter()
after merging commit be2657752e9e ("mm: memcg: fix use after free in
mem_cgroup_iter()").

I work with android kernel tree (4.9 & 4.14), and commit be2657752e9e
("mm: memcg: fix use after free in mem_cgroup_iter()") has been merged
to the trees. However, I can still observe use after free issues
addressed in the commit be2657752e9e. (on low-end devices, a few times
this month)

backtrace:
css_tryget <- crash here
mem_cgroup_iter
shrink_node
shrink_zones
do_try_to_free_pages
try_to_free_pages
__perform_reclaim
__alloc_pages_direct_reclaim
__alloc_pages_slowpath
__alloc_pages_nodemask

To debug, I poisoned mem_cgroup before freeing it:

static void __mem_cgroup_free(struct mem_cgroup *memcg)
for_each_node(node)
free_mem_cgroup_per_node_info(memcg, node);
free_percpu(memcg->stat);
+ /* poison memcg before freeing it */
+ memset(memcg, 0x78, sizeof(struct mem_cgroup));
kfree(memcg);
}

The coredump shows the position=0xdbbc2a00 is freed.

(gdb) p/x ((struct mem_cgroup_per_node *)0xe5009e00)->iter[8]
$13 = {position = 0xdbbc2a00, generation = 0x2efd}

0xdbbc2a00: 0xdbbc2e00 0x00000000 0xdbbc2800 0x00000100
0xdbbc2a10: 0x00000200 0x78787878 0x00026218 0x00000000
0xdbbc2a20: 0xdcad6000 0x00000001 0x78787800 0x00000000
0xdbbc2a30: 0x78780000 0x00000000 0x0068fb84 0x78787878
0xdbbc2a40: 0x78787878 0x78787878 0x78787878 0xe3fa5cc0
0xdbbc2a50: 0x78787878 0x78787878 0x00000000 0x00000000
0xdbbc2a60: 0x00000000 0x00000000 0x00000000 0x00000000
0xdbbc2a70: 0x00000000 0x00000000 0x00000000 0x00000000
0xdbbc2a80: 0x00000000 0x00000000 0x00000000 0x00000000
0xdbbc2a90: 0x00000001 0x00000000 0x00000000 0x00100000
0xdbbc2aa0: 0x00000001 0xdbbc2ac8 0x00000000 0x00000000
0xdbbc2ab0: 0x00000000 0x00000000 0x00000000 0x00000000
0xdbbc2ac0: 0x00000000 0x00000000 0xe5b02618 0x00001000
0xdbbc2ad0: 0x00000000 0x78787878 0x78787878 0x78787878
0xdbbc2ae0: 0x78787878 0x78787878 0x78787878 0x78787878
0xdbbc2af0: 0x78787878 0x78787878 0x78787878 0x78787878
0xdbbc2b00: 0x78787878 0x78787878 0x78787878 0x78787878
0xdbbc2b10: 0x78787878 0x78787878 0x78787878 0x78787878
0xdbbc2b20: 0x78787878 0x78787878 0x78787878 0x78787878
0xdbbc2b30: 0x78787878 0x78787878 0x78787878 0x78787878
0xdbbc2b40: 0x78787878 0x78787878 0x78787878 0x78787878
0xdbbc2b50: 0x78787878 0x78787878 0x78787878 0x78787878
0xdbbc2b60: 0x78787878 0x78787878 0x78787878 0x78787878
0xdbbc2b70: 0x78787878 0x78787878 0x78787878 0x78787878
0xdbbc2b80: 0x78787878 0x78787878 0x00000000 0x78787878
0xdbbc2b90: 0x78787878 0x78787878 0x78787878 0x78787878
0xdbbc2ba0: 0x78787878 0x78787878 0x78787878 0x78787878

In the reclaim path, try_to_free_pages() does not setup
sc.target_mem_cgroup and sc is passed to do_try_to_free_pages(), ...,
shrink_node().

In mem_cgroup_iter(), root is set to root_mem_cgroup because
sc->target_mem_cgroup is NULL. It is possible to assign a memcg to
root_mem_cgroup.nodeinfo.iter in mem_cgroup_iter().

try_to_free_pages
struct scan_control sc = {...}, target_mem_cgroup is 0x0;
do_try_to_free_pages
shrink_zones
shrink_node
mem_cgroup *root = sc->target_mem_cgroup;
memcg = mem_cgroup_iter(root, NULL, &reclaim);
mem_cgroup_iter()
if (!root)
root = root_mem_cgroup;
...

css = css_next_descendant_pre(css, &root->css);
memcg = mem_cgroup_from_css(css);
cmpxchg(&iter->position, pos, memcg);

My device uses memcg non-hierarchical mode. When we release a memcg:
invalidate_reclaim_iterators() reaches only dead_memcg and its parents.
If non-hierarchical mode is used, invalidate_reclaim_iterators() never
reaches root_mem_cgroup.

static void invalidate_reclaim_iterators(struct mem_cgroup *dead_memcg)
{
struct mem_cgroup *memcg = dead_memcg;

for (; memcg; memcg = parent_mem_cgroup(memcg)
...
}

So the use after free scenario looks like:

CPU1 CPU2

try_to_free_pages
do_try_to_free_pages
shrink_zones
shrink_node
mem_cgroup_iter()
if (!root)
root = root_mem_cgroup;
...
css = css_next_descendant_pre(css, &root->css);
memcg = mem_cgroup_from_css(css);
cmpxchg(&iter->position, pos, memcg);

invalidate_reclaim_iterators(memcg);
...
__mem_cgroup_free()
kfree(memcg);

try_to_free_pages
do_try_to_free_pages
shrink_zones
shrink_node
mem_cgroup_iter()
if (!root)
root = root_mem_cgroup;
...
mz = mem_cgroup_nodeinfo(root, reclaim->pgdat->node_id);
iter = &mz->iter[reclaim->priority];
pos = READ_ONCE(iter->position);
css_tryget(&pos->css) <- use after free

To avoid this, we should also invalidate root_mem_cgroup.nodeinfo.iter
in invalidate_reclaim_iterators().

[cai@xxxxxx: fix -Wparentheses compilation warning]
Link: http://lkml.kernel.org/r/1564580753-17531-1-git-send-email-cai@xxxxxx
Link: http://lkml.kernel.org/r/20190730015729.4406-1-miles.chen@xxxxxxxxxxxx
Fixes: 5ac8fb31ad2e ("mm: memcontrol: convert reclaim iterator to simple css refcounting")
Signed-off-by: Miles Chen <miles.chen@xxxxxxxxxxxx>
Signed-off-by: Qian Cai <cai@xxxxxx>
Acked-by: Michal Hocko <mhocko@xxxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Vladimir Davydov <vdavydov.dev@xxxxxxxxx>
Cc: <stable@xxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>


---
mm/memcontrol.c | 41 ++++++++++++++++++++++++++++++-----------
1 file changed, 30 insertions(+), 11 deletions(-)

--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -988,28 +988,47 @@ void mem_cgroup_iter_break(struct mem_cg
css_put(&prev->css);
}

-static void invalidate_reclaim_iterators(struct mem_cgroup *dead_memcg)
+static void __invalidate_reclaim_iterators(struct mem_cgroup *from,
+ struct mem_cgroup *dead_memcg)
{
- struct mem_cgroup *memcg = dead_memcg;
struct mem_cgroup_reclaim_iter *iter;
struct mem_cgroup_per_zone *mz;
int nid, zid;
int i;

- for (; memcg; memcg = parent_mem_cgroup(memcg)) {
- for_each_node(nid) {
- for (zid = 0; zid < MAX_NR_ZONES; zid++) {
- mz = &memcg->nodeinfo[nid]->zoneinfo[zid];
- for (i = 0; i <= DEF_PRIORITY; i++) {
- iter = &mz->iter[i];
- cmpxchg(&iter->position,
- dead_memcg, NULL);
- }
+ for_each_node(nid) {
+ for (zid = 0; zid < MAX_NR_ZONES; zid++) {
+ mz = &from->nodeinfo[nid]->zoneinfo[zid];
+ for (i = 0; i <= DEF_PRIORITY; i++) {
+ iter = &mz->iter[i];
+ cmpxchg(&iter->position,
+ dead_memcg, NULL);
}
}
}
}

+static void invalidate_reclaim_iterators(struct mem_cgroup *dead_memcg)
+{
+ struct mem_cgroup *memcg = dead_memcg;
+ struct mem_cgroup *last;
+
+ do {
+ __invalidate_reclaim_iterators(memcg, dead_memcg);
+ last = memcg;
+ } while ((memcg = parent_mem_cgroup(memcg)));
+
+ /*
+ * When cgruop1 non-hierarchy mode is used,
+ * parent_mem_cgroup() does not walk all the way up to the
+ * cgroup root (root_mem_cgroup). So we have to handle
+ * dead_memcg from cgroup root separately.
+ */
+ if (last != root_mem_cgroup)
+ __invalidate_reclaim_iterators(root_mem_cgroup,
+ dead_memcg);
+}
+
/*
* Iteration constructs for visiting all cgroups (under a tree). If
* loops are exited prematurely (break), mem_cgroup_iter_break() must