This is a note to let you know that I've just added the patch titled
bpf: Check map->usercnt after timer->timer is assigned
to the 6.5-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
bpf-check-map-usercnt-after-timer-timer-is-assigned.patch
and it can be found in the queue-6.5 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
commit f1becaca84f65514e04d48b74a3e206495b1db3f
Author: Hou Tao <houtao1@xxxxxxxxxx>
Date: Mon Oct 30 14:36:16 2023 +0800
bpf: Check map->usercnt after timer->timer is assigned
[ Upstream commit fd381ce60a2d79cc967506208085336d3d268ae0 ]
When there are concurrent uref release and bpf timer init operations,
the following sequence diagram is possible. It will break the guarantee
provided by bpf_timer: bpf_timer will still be alive after userspace
application releases or unpins the map. It also will lead to kmemleak
for old kernel version which doesn't release bpf_timer when map is
released.
bpf program X:
bpf_timer_init()
lock timer->lock
read timer->timer as NULL
read map->usercnt != 0
process Y:
close(map_fd)
// put last uref
bpf_map_put_uref()
atomic_dec_and_test(map->usercnt)
array_map_free_timers()
bpf_timer_cancel_and_free()
// just return
read timer->timer is NULL
t = bpf_map_kmalloc_node()
timer->timer = t
unlock timer->lock
Fix the problem by checking map->usercnt after timer->timer is assigned,
so when there are concurrent uref release and bpf timer init, either
bpf_timer_cancel_and_free() from uref release reads a no-NULL timer
or the newly-added atomic64_read() returns a zero usercnt.
Because atomic_dec_and_test(map->usercnt) and READ_ONCE(timer->timer)
in bpf_timer_cancel_and_free() are not protected by a lock, so add
a memory barrier to guarantee the order between map->usercnt and
timer->timer. Also use WRITE_ONCE(timer->timer, x) to match the lockless
read of timer->timer in bpf_timer_cancel_and_free().
Reported-by: Hsin-Wei Hung <hsinweih@xxxxxxx>
Closes: https://lore.kernel.org/bpf/CABcoxUaT2k9hWsS1tNgXyoU3E-=PuOgMn737qK984fbFmfYixQ@xxxxxxxxxxxxxx
Fixes: b00628b1c7d5 ("bpf: Introduce bpf timers.")
Signed-off-by: Hou Tao <houtao1@xxxxxxxxxx>
Link: https://lore.kernel.org/r/20231030063616.1653024-1-houtao@xxxxxxxxxxxxxxx
Signed-off-by: Alexei Starovoitov <ast@xxxxxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 3779300002327..add185dfa5c65 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -1174,13 +1174,6 @@ BPF_CALL_3(bpf_timer_init, struct bpf_timer_kern *, timer, struct bpf_map *, map
ret = -EBUSY;
goto out;
}
- if (!atomic64_read(&map->usercnt)) {
- /* maps with timers must be either held by user space
- * or pinned in bpffs.
- */
- ret = -EPERM;
- goto out;
- }
/* allocate hrtimer via map_kmalloc to use memcg accounting */
t = bpf_map_kmalloc_node(map, sizeof(*t), GFP_ATOMIC, map->numa_node);
if (!t) {
@@ -1193,7 +1186,21 @@ BPF_CALL_3(bpf_timer_init, struct bpf_timer_kern *, timer, struct bpf_map *, map
rcu_assign_pointer(t->callback_fn, NULL);
hrtimer_init(&t->timer, clockid, HRTIMER_MODE_REL_SOFT);
t->timer.function = bpf_timer_cb;
- timer->timer = t;
+ WRITE_ONCE(timer->timer, t);
+ /* Guarantee the order between timer->timer and map->usercnt. So
+ * when there are concurrent uref release and bpf timer init, either
+ * bpf_timer_cancel_and_free() called by uref release reads a no-NULL
+ * timer or atomic64_read() below returns a zero usercnt.
+ */
+ smp_mb();
+ if (!atomic64_read(&map->usercnt)) {
+ /* maps with timers must be either held by user space
+ * or pinned in bpffs.
+ */
+ WRITE_ONCE(timer->timer, NULL);
+ kfree(t);
+ ret = -EPERM;
+ }
out:
__bpf_spin_unlock_irqrestore(&timer->lock);
return ret;
@@ -1368,7 +1375,7 @@ void bpf_timer_cancel_and_free(void *val)
/* The subsequent bpf_timer_start/cancel() helpers won't be able to use
* this timer, since it won't be initialized.
*/
- timer->timer = NULL;
+ WRITE_ONCE(timer->timer, NULL);
out:
__bpf_spin_unlock_irqrestore(&timer->lock);
if (!t)
