[PATCH net] virtio_net: atomically disable rx mode work

[PATCH net] virtio_net: atomically disable rx mode work

[Weiming Shi]

virtio-net uses a boolean to gate rx_mode_work during device teardown.
The flag is changed under RTNL, but ndo_set_rx_mode checks it under the
address-list lock. A callback can therefore pass the check and enqueue work
after teardown has flushed it. The work is also enabled before late
probe operations that can fail, allowing probe unwind to free the netdev
with work still queued.

KASAN reports the worker using a virtqueue that probe unwind already freed:

  BUG: KASAN: slab-use-after-free in virtqueue_add_split
  Workqueue: events virtnet_rx_mode_work
  Call Trace:
   virtqueue_add_split (drivers/virtio/virtio_ring.c:706)
   virtqueue_add_sgs (drivers/virtio/virtio_ring.c:2839)
   virtnet_send_command_reply (drivers/net/virtio_net.c:3565)
   virtnet_rx_mode_work (drivers/net/virtio_net.c:3833)
   process_one_work (kernel/workqueue.c:3322)
   worker_thread (kernel/workqueue.c:3405)
  Freed by task 119:
   kfree (mm/slub.c:6625)
   vp_del_vq.isra.0 (drivers/virtio/virtio_pci_common.c:259)
   vp_del_vqs (drivers/virtio/virtio_pci_common.c:285)
   virtnet_probe (drivers/net/virtio_net.c:7129)

Use the workqueue disable mechanism to atomically reject new queue attempts
and drain running work. Keep work disabled until probe succeeds or restore
has reattached the netdev, then enable it and replay receive-mode state for
a running interface. Disable it before resource teardown in freeze and
remove.

Fixes: b9f7425239a0 ("virtio-net: convert rx mode setting to use workqueue")
Cc: stable@vger.kernel.org
Reported-by: <co+d17c2bc750a9cbbb@bugs.sh>
Assisted-by: LLM
Signed-off-by: Weiming Shi <bestswngs@gmail.com>
---
 drivers/net/virtio_net.c | 26 +++++++++-----------------
 1 file changed, 9 insertions(+), 17 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 7d2eeb9b122667..6fa4b7219aa5ac 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -441,9 +441,6 @@ struct virtnet_info {
 	/* Work struct for setting rx mode */
 	struct work_struct rx_mode_work;
 
-	/* OK to queue work setting RX mode? */
-	bool rx_mode_work_enabled;
-
 	/* Does the affinity hint is set for virtqueues? */
 	bool affinity_hint_set;
 
@@ -710,16 +707,13 @@ static void virtnet_rq_free_buf(struct virtnet_info *vi,
 
 static void enable_rx_mode_work(struct virtnet_info *vi)
 {
-	rtnl_lock();
-	vi->rx_mode_work_enabled = true;
-	rtnl_unlock();
+	if (enable_work(&vi->rx_mode_work) && netif_running(vi->dev))
+		schedule_work(&vi->rx_mode_work);
 }
 
 static void disable_rx_mode_work(struct virtnet_info *vi)
 {
-	rtnl_lock();
-	vi->rx_mode_work_enabled = false;
-	rtnl_unlock();
+	disable_work_sync(&vi->rx_mode_work);
 }
 
 static void virtqueue_napi_schedule(struct napi_struct *napi,
@@ -3894,8 +3888,7 @@ static void virtnet_set_rx_mode(struct net_device *dev)
 {
 	struct virtnet_info *vi = netdev_priv(dev);
 
-	if (vi->rx_mode_work_enabled)
-		schedule_work(&vi->rx_mode_work);
+	schedule_work(&vi->rx_mode_work);
 }
 
 static int virtnet_vlan_rx_add_vid(struct net_device *dev,
@@ -5711,7 +5704,6 @@ static void virtnet_freeze_down(struct virtio_device *vdev)
 	/* Make sure no work handler is accessing the device */
 	flush_work(&vi->config_work);
 	disable_rx_mode_work(vi);
-	flush_work(&vi->rx_mode_work);
 
 	if (netif_running(vi->dev)) {
 		rtnl_lock();
@@ -5741,8 +5733,6 @@ static int virtnet_restore_up(struct virtio_device *vdev)
 
 	virtio_device_ready(vdev);
 
-	enable_rx_mode_work(vi);
-
 	if (netif_running(vi->dev)) {
 		rtnl_lock();
 		err = virtnet_open(vi->dev);
@@ -5754,6 +5744,8 @@ static int virtnet_restore_up(struct virtio_device *vdev)
 	netif_tx_lock_bh(vi->dev);
 	netif_device_attach(vi->dev);
 	netif_tx_unlock_bh(vi->dev);
+
+	enable_rx_mode_work(vi);
 	return 0;
 
 err_destroy_pools:
@@ -6849,6 +6841,7 @@ static int virtnet_probe(struct virtio_device *vdev)
 
 	INIT_WORK(&vi->config_work, virtnet_config_changed_work);
 	INIT_WORK(&vi->rx_mode_work, virtnet_rx_mode_work);
+	disable_work(&vi->rx_mode_work);
 
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF)) {
 		vi->mergeable_rx_bufs = true;
@@ -7007,8 +7000,6 @@ static int virtnet_probe(struct virtio_device *vdev)
 	if (vi->has_rss || vi->has_rss_hash_report)
 		virtnet_init_default_rss(vi);
 
-	enable_rx_mode_work(vi);
-
 	for (i = 0; i < ARRAY_SIZE(guest_offloads); i++) {
 		unsigned int fbit;
 
@@ -7112,6 +7103,8 @@ static int virtnet_probe(struct virtio_device *vdev)
 		goto free_unregister_netdev;
 	}
 
+	enable_rx_mode_work(vi);
+
 	pr_debug("virtnet: registered device %s with %d RX and TX vq's\n",
 		 dev->name, max_queue_pairs);
 
@@ -7164,7 +7157,6 @@ static void virtnet_remove(struct virtio_device *vdev)
 	/* Make sure no work handler is accessing the device. */
 	flush_work(&vi->config_work);
 	disable_rx_mode_work(vi);
-	flush_work(&vi->rx_mode_work);
 
 	virtnet_free_irq_moder(vi);
 
-- 
2.55.0

Re: [PATCH net] virtio_net: atomically disable rx mode work

[sashiko-bot]

> virtio-net uses a boolean to gate rx_mode_work during device teardown.
> The flag is changed under RTNL, but ndo_set_rx_mode checks it under the
> address-list lock. A callback can therefore pass the check and enqueue work
> after teardown has flushed it. The work is also enabled before late
> probe operations that can fail, allowing probe unwind to free the netdev
> with work still queued.
> 
> KASAN reports the worker using a virtqueue that probe unwind already freed:
> 
>   BUG: KASAN: slab-use-after-free in virtqueue_add_split
>   Workqueue: events virtnet_rx_mode_work
>   Call Trace:
>    virtqueue_add_split (drivers/virtio/virtio_ring.c:706)
>    virtqueue_add_sgs (drivers/virtio/virtio_ring.c:2839)
>    virtnet_send_command_reply (drivers/net/virtio_net.c:3565)
> [ ... ]
> Fixes: b9f7425239a0 ("virtio-net: convert rx mode setting to use workqueue")
> Cc: stable@vger.kernel.org
> Reported-by: <co+d17c2bc750a9cbbb@bugs.sh>
> Assisted-by: LLM
> Signed-off-by: Weiming Shi <bestswngs@gmail.com>

Sashiko has reviewed this patch and found no issues.

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20261017114237.2786302-2-bestswngs@gmail.com?part=1