blob: 2142e5b0aa5debf3fefd3a4a67bd9e67a7e815c0 [file] [log] [blame]
From 453df2e095efbc34c76c3a5c01ba1decdcef1278 Mon Sep 17 00:00:00 2001
From: Chunguang Xu <brookxu@tencent.com>
Date: Sat, 21 Mar 2020 18:22:10 -0700
Subject: [PATCH] memcg: fix NULL pointer dereference in
__mem_cgroup_usage_unregister_event
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
commit 7d36665a5886c27ca4c4d0afd3ecc50b400f3587 upstream.
An eventfd monitors multiple memory thresholds of the cgroup, closes them,
the kernel deletes all events related to this eventfd. Before all events
are deleted, another eventfd monitors the memory threshold of this cgroup,
leading to a crash:
BUG: kernel NULL pointer dereference, address: 0000000000000004
#PF: supervisor write access in kernel mode
#PF: error_code(0x0002) - not-present page
PGD 800000033058e067 P4D 800000033058e067 PUD 3355ce067 PMD 0
Oops: 0002 [#1] SMP PTI
CPU: 2 PID: 14012 Comm: kworker/2:6 Kdump: loaded Not tainted 5.6.0-rc4 #3
Hardware name: LENOVO 20AWS01K00/20AWS01K00, BIOS GLET70WW (2.24 ) 05/21/2014
Workqueue: events memcg_event_remove
RIP: 0010:__mem_cgroup_usage_unregister_event+0xb3/0x190
RSP: 0018:ffffb47e01c4fe18 EFLAGS: 00010202
RAX: 0000000000000001 RBX: ffff8bb223a8a000 RCX: 0000000000000001
RDX: 0000000000000001 RSI: ffff8bb22fb83540 RDI: 0000000000000001
RBP: ffffb47e01c4fe48 R08: 0000000000000000 R09: 0000000000000010
R10: 000000000000000c R11: 071c71c71c71c71c R12: ffff8bb226aba880
R13: ffff8bb223a8a480 R14: 0000000000000000 R15: 0000000000000000
FS 0000000000000000(0000) GS:ffff8bb242680000(0000) knlGS:0000000000000000
CS 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000000000004 CR3: 000000032c29c003 CR4: 00000000001606e0
Call Trace:
memcg_event_remove+0x32/0x90
process_one_work+0x172/0x380
worker_thread+0x49/0x3f0
kthread+0xf8/0x130
ret_from_fork+0x35/0x40
CR2: 0000000000000004
We can reproduce this problem in the following ways:
1. We create a new cgroup subdirectory and a new eventfd, and then we
monitor multiple memory thresholds of the cgroup through this eventfd.
2. closing this eventfd, and __mem_cgroup_usage_unregister_event ()
will be called multiple times to delete all events related to this
eventfd.
The first time __mem_cgroup_usage_unregister_event() is called, the
kernel will clear all items related to this eventfd in thresholds->
primary.
Since there is currently only one eventfd, thresholds-> primary becomes
empty, so the kernel will set thresholds-> primary and hresholds-> spare
to NULL. If at this time, the user creates a new eventfd and monitor
the memory threshold of this cgroup, kernel will re-initialize
thresholds-> primary.
Then when __mem_cgroup_usage_unregister_event () is called for the
second time, because thresholds-> primary is not empty, the system will
access thresholds-> spare, but thresholds-> spare is NULL, which will
trigger a crash.
In general, the longer it takes to delete all events related to this
eventfd, the easier it is to trigger this problem.
The solution is to check whether the thresholds associated with the
eventfd has been cleared when deleting the event. If so, we do nothing.
[akpm@linux-foundation.org: fix comment, per Kirill]
Fixes: 907860ed381a ("cgroups: make cftype.unregister_event() void-returning")
Signed-off-by: Chunguang Xu <brookxu@tencent.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: <stable@vger.kernel.org>
Link: http://lkml.kernel.org/r/077a6f67-aefa-4591-efec-f2f3af2b0b02@gmail.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index b95391b7663a..6e5d87714853 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3890,7 +3890,7 @@ static void __mem_cgroup_usage_unregister_event(struct mem_cgroup *memcg,
struct mem_cgroup_thresholds *thresholds;
struct mem_cgroup_threshold_ary *new;
unsigned long usage;
- int i, j, size;
+ int i, j, size, entries;
mutex_lock(&memcg->thresholds_lock);
@@ -3910,14 +3910,20 @@ static void __mem_cgroup_usage_unregister_event(struct mem_cgroup *memcg,
__mem_cgroup_threshold(memcg, type == _MEMSWAP);
/* Calculate new number of threshold */
- size = 0;
+ size = entries = 0;
for (i = 0; i < thresholds->primary->size; i++) {
if (thresholds->primary->entries[i].eventfd != eventfd)
size++;
+ else
+ entries++;
}
new = thresholds->spare;
+ /* If no items related to eventfd have been cleared, nothing to do */
+ if (!entries)
+ goto unlock;
+
/* Set thresholds array to NULL if we don't have thresholds */
if (!size) {
kfree(new);
--
2.7.4