net: fix skb use after free in netpoll_send_skb_on_dev
diff mbox series

Message ID 1566577920-20956-1-git-send-email-loyou85@gmail.com
State Changes Requested
Delegated to: David Miller
Headers show
Series
  • net: fix skb use after free in netpoll_send_skb_on_dev
Related show

Commit Message

Feng Sun Aug. 23, 2019, 4:32 p.m. UTC
After commit baeababb5b85d5c4e6c917efe2a1504179438d3b
("tun: return NET_XMIT_DROP for dropped packets"),
when tun_net_xmit drop packets, it will free skb and return NET_XMIT_DROP,
netpoll_send_skb_on_dev will run into two use after free cases:
1. retry netpoll_start_xmit with freed skb;
2. queue freed skb in npinfo->txq.

hit the first case with following kernel log:

[  117.864773] kernel BUG at mm/slub.c:306!
[  117.864773] invalid opcode: 0000 [#1] SMP PTI
[  117.864774] CPU: 3 PID: 2627 Comm: loop_printmsg Kdump: loaded Tainted: P           OE     5.3.0-050300rc5-generic #201908182231
[  117.864775] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014
[  117.864775] RIP: 0010:kmem_cache_free+0x28d/0x2b0
[  117.864781] Call Trace:
[  117.864781]  ? tun_net_xmit+0x21c/0x460
[  117.864781]  kfree_skbmem+0x4e/0x60
[  117.864782]  kfree_skb+0x3a/0xa0
[  117.864782]  tun_net_xmit+0x21c/0x460
[  117.864782]  netpoll_start_xmit+0x11d/0x1b0
[  117.864788]  netpoll_send_skb_on_dev+0x1b8/0x200
[  117.864789]  __br_forward+0x1b9/0x1e0 [bridge]
[  117.864789]  ? skb_clone+0x53/0xd0
[  117.864790]  ? __skb_clone+0x2e/0x120
[  117.864790]  deliver_clone+0x37/0x50 [bridge]
[  117.864790]  maybe_deliver+0x89/0xc0 [bridge]
[  117.864791]  br_flood+0x6c/0x130 [bridge]
[  117.864791]  br_dev_xmit+0x315/0x3c0 [bridge]
[  117.864792]  netpoll_start_xmit+0x11d/0x1b0
[  117.864792]  netpoll_send_skb_on_dev+0x1b8/0x200
[  117.864792]  netpoll_send_udp+0x2c6/0x3e8
[  117.864793]  write_msg+0xd9/0xf0 [netconsole]
[  117.864793]  console_unlock+0x386/0x4e0
[  117.864793]  vprintk_emit+0x17e/0x280
[  117.864794]  vprintk_default+0x29/0x50
[  117.864794]  vprintk_func+0x4c/0xbc
[  117.864794]  printk+0x58/0x6f
[  117.864795]  loop_fun+0x24/0x41 [printmsg_loop]
[  117.864795]  kthread+0x104/0x140
[  117.864795]  ? 0xffffffffc05b1000
[  117.864796]  ? kthread_park+0x80/0x80
[  117.864796]  ret_from_fork+0x35/0x40

Signed-off-by: Feng Sun <loyou85@gmail.com>
Signed-off-by: Xiaojun Zhao <xiaojunzhao141@gmail.com>
---
 net/core/netpoll.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

Comments

David Miller Aug. 26, 2019, 2:48 a.m. UTC | #1
From: Feng Sun <loyou85@gmail.com>
Date: Sat, 24 Aug 2019 00:32:00 +0800

> After commit baeababb5b85d5c4e6c917efe2a1504179438d3b
> ("tun: return NET_XMIT_DROP for dropped packets"),
> when tun_net_xmit drop packets, it will free skb and return NET_XMIT_DROP,
> netpoll_send_skb_on_dev will run into two use after free cases:

I don't know what to do here.

Really, the intention of the design is that the only valid
->ndo_start_xmit() values are those with macro names fitting the
pattern NETDEV_TX_*, which means only NETDEV_TX_OK and NETDEV_TX_BUSY
are valid.

NET_XMIT_* values are for qdisc ->enqueue() methods.

Note, particularly, that when ->ndo_start_xmit() values are propagated
through ->enqueue() calls they get masked out with NET_XMIT_MASK.

However, I see that most of the code doing enqueueing and invocation
of ->ndo_start_xmit() use the dev_xmit_complete() helper to check this
condition.

So probably that is what netpoll should be using as well.

Patch
diff mbox series

diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 2cf27da..b4bffe6 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -335,7 +335,7 @@  void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
 
 				HARD_TX_UNLOCK(dev, txq);
 
-				if (status == NETDEV_TX_OK)
+				if (status == NETDEV_TX_OK || status == NET_XMIT_DROP)
 					break;
 
 			}
@@ -352,7 +352,7 @@  void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
 
 	}
 
-	if (status != NETDEV_TX_OK) {
+	if (status != NETDEV_TX_OK && status != NET_XMIT_DROP) {
 		skb_queue_tail(&npinfo->txq, skb);
 		schedule_delayed_work(&npinfo->tx_work,0);
 	}