syszbot found an interesting use-after-free [1] happening
while IPv4 fragment rhashtable was destroyed at netns dismantle.
While no insertions can possibly happen at the time a dismantling
netns is destroying this rhashtable, timers can still fire and
attempt to remove elements from this rhashtable.
This is forbidden, since rhashtable_free_and_destroy() has
no synchronization against concurrent inserts and deletes.
It seems we need to clean the rhashtable before destroying it.
[1]
BUG: KASAN: use-after-free in __read_once_size include/linux/compiler.h:188
[inline]
BUG: KASAN: use-after-free in rhashtable_last_table+0x216/0x240
lib/rhashtable.c:217
Read of size 8 at addr ffff88019a4c8840 by task kworker/0:4/8279
CPU: 0 PID: 8279 Comm: kworker/0:4 Not tainted 4.19.0-rc5+ #61
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google
01/01/2011
Workqueue: events rht_deferred_worker
Call Trace:
__dump_stack lib/dump_stack.c:77 [inline]
dump_stack+0x1c4/0x2b4 lib/dump_stack.c:113
print_address_description.cold.8+0x9/0x1ff mm/kasan/report.c:256
kasan_report_error mm/kasan/report.c:354 [inline]
kasan_report.cold.9+0x242/0x309 mm/kasan/report.c:412
__asan_report_load8_noabort+0x14/0x20 mm/kasan/report.c:433
__read_once_size include/linux/compiler.h:188 [inline]
rhashtable_last_table+0x216/0x240 lib/rhashtable.c:217
rht_deferred_worker+0x157/0x1de0 lib/rhashtable.c:410
process_one_work+0xc90/0x1b90 kernel/workqueue.c:2153
worker_thread+0x17f/0x1390 kernel/workqueue.c:2296
kthread+0x35a/0x420 kernel/kthread.c:246
ret_from_fork+0x3a/0x50 arch/x86/entry/entry_64.S:413
Allocated by task 5:
save_stack+0x43/0xd0 mm/kasan/kasan.c:448
set_track mm/kasan/kasan.c:460 [inline]
kasan_kmalloc+0xc7/0xe0 mm/kasan/kasan.c:553
__do_kmalloc_node mm/slab.c:3682 [inline]
__kmalloc_node+0x47/0x70 mm/slab.c:3689
kmalloc_node include/linux/slab.h:555 [inline]
kvmalloc_node+0xb9/0xf0 mm/util.c:423
kvmalloc include/linux/mm.h:577 [inline]
kvzalloc include/linux/mm.h:585 [inline]
bucket_table_alloc+0x9a/0x4e0 lib/rhashtable.c:176
rhashtable_rehash_alloc+0x73/0x100 lib/rhashtable.c:353
rht_deferred_worker+0x278/0x1de0 lib/rhashtable.c:413
process_one_work+0xc90/0x1b90 kernel/workqueue.c:2153
worker_thread+0x17f/0x1390 kernel/workqueue.c:2296
kthread+0x35a/0x420 kernel/kthread.c:246
ret_from_fork+0x3a/0x50 arch/x86/entry/entry_64.S:413
Freed by task 8283:
save_stack+0x43/0xd0 mm/kasan/kasan.c:448
set_track mm/kasan/kasan.c:460 [inline]
__kasan_slab_free+0x102/0x150 mm/kasan/kasan.c:521
kasan_slab_free+0xe/0x10 mm/kasan/kasan.c:528
__cache_free mm/slab.c:3498 [inline]
kfree+0xcf/0x230 mm/slab.c:3813
kvfree+0x61/0x70 mm/util.c:452
bucket_table_free+0xda/0x250 lib/rhashtable.c:108
rhashtable_free_and_destroy+0x152/0x900 lib/rhashtable.c:1163
inet_frags_exit_net+0x3d/0x50 net/ipv4/inet_fragment.c:96
ipv4_frags_exit_net+0x73/0x90 net/ipv4/ip_fragment.c:914
ops_exit_list.isra.7+0xb0/0x160 net/core/net_namespace.c:153
cleanup_net+0x555/0xb10 net/core/net_namespace.c:551
process_one_work+0xc90/0x1b90 kernel/workqueue.c:2153
worker_thread+0x17f/0x1390 kernel/workqueue.c:2296
kthread+0x35a/0x420 kernel/kthread.c:246
ret_from_fork+0x3a/0x50 arch/x86/entry/entry_64.S:413
The buggy address belongs to the object at ffff88019a4c8800
which belongs to the cache kmalloc-16384 of size 16384
The buggy address is located 64 bytes inside of
16384-byte region [ffff88019a4c8800, ffff88019a4cc800)
The buggy address belongs to the page:
page:ffffea0006693200 count:1 mapcount:0 mapping:ffff8801da802200 index:0x0
compound_mapcount: 0
flags: 0x2fffc0000008100(slab|head)
raw: 02fffc0000008100 ffffea0006685608 ffffea0006617c08 ffff8801da802200
raw: 0000000000000000 ffff88019a4c8800 0000000100000001 0000000000000000
page dumped because: kasan: bad access detected
Memory state around the buggy address:
ffff88019a4c8700: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
ffff88019a4c8780: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
>ffff88019a4c8800: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
^
ffff88019a4c8880: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
ffff88019a4c8900: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
Fixes: 648700f76b03 ("inet: frags: use rhashtables for reassembly units")
Signed-off-by: Eric Dumazet <eduma...@google.com>
Reported-by: syzbot <syzkal...@googlegroups.com>
Cc: Thomas Graf <tg...@suug.ch>
Cc: Herbert Xu <herb...@gondor.apana.org.au>
---
net/ipv4/inet_fragment.c | 55 ++++++++++++++++++++++++----------------
1 file changed, 33 insertions(+), 22 deletions(-)
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index
bcb11f3a27c0c34115af05034a5a20f57842eb0a..50d74a191ff14078bcb87c86640fe7dd342f9956
100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -68,32 +68,43 @@ void inet_frags_fini(struct inet_frags *f)
}
EXPORT_SYMBOL(inet_frags_fini);
-static void inet_frags_free_cb(void *ptr, void *arg)
-{
- struct inet_frag_queue *fq = ptr;
-
- /* If we can not cancel the timer, it means this frag_queue
- * is already disappearing, we have nothing to do.
- * Otherwise, we own a refcount until the end of this function.
- */
- if (!del_timer(&fq->timer))
- return;
-
- spin_lock_bh(&fq->lock);
- if (!(fq->flags & INET_FRAG_COMPLETE)) {
- fq->flags |= INET_FRAG_COMPLETE;
- refcount_dec(&fq->refcnt);
- }
- spin_unlock_bh(&fq->lock);
-
- inet_frag_put(fq);
-}
-
void inet_frags_exit_net(struct netns_frags *nf)
{
+ struct rhashtable_iter hti;
+ struct inet_frag_queue *fq;
+
+ /* Since we want to cleanup the hashtable, make sure that
+ * we wont trigger an automatic shrinking while in our
+ * rhashtable_walk_next() loop.
+ * Also make sure that no resize is in progress.
+ */
nf->high_thresh = 0; /* prevent creation of new frags */
+ nf->rhashtable.p.automatic_shrinking = false;
+ cancel_work_sync(&nf->rhashtable.run_work);
- rhashtable_free_and_destroy(&nf->rhashtable, inet_frags_free_cb, NULL);
+ rhashtable_walk_enter(&nf->rhashtable, &hti);
+ rhashtable_walk_start(&hti);
+ while ((fq = rhashtable_walk_next(&hti)) != NULL) {
+ if (IS_ERR(fq)) /* should not happen */
+ break;
+ if (!del_timer_sync(&fq->timer))
+ continue;
+
+ spin_lock_bh(&fq->lock);
+ inet_frag_kill(fq);
+ spin_unlock_bh(&fq->lock);
+
+ inet_frag_put(fq);
+ if (need_resched()) {
+ rhashtable_walk_stop(&hti);
+ cond_resched();
+ rhashtable_walk_start(&hti);
+ }
+ }
+ rhashtable_walk_stop(&hti);
+ rhashtable_walk_exit(&hti);
+
+ rhashtable_destroy(&nf->rhashtable);
}
EXPORT_SYMBOL(inet_frags_exit_net);
--
2.19.0.605.g01d371f741-goog
