[PATCH net V5] virtio-net: fix the race between refill work and close

[Jason Wang <jasowang@redhat.com>]

We try using cancel_delayed_work_sync() to prevent the work from
enabling NAPI. This is insufficient since we don't disable the source
of the refill work scheduling. This means an NAPI poll callback after
cancel_delayed_work_sync() can schedule the refill work then can
re-enable the NAPI that leads to use-after-free [1].

Since the work can enable NAPI, we can't simply disable NAPI before
calling cancel_delayed_work_sync(). So fix this by introducing a
dedicated boolean to control whether or not the work could be
scheduled from NAPI.

[1]
==================================================================
BUG: KASAN: use-after-free in refill_work+0x43/0xd4
Read of size 2 at addr ffff88810562c92e by task kworker/2:1/42

CPU: 2 PID: 42 Comm: kworker/2:1 Not tainted 5.19.0-rc1+ #480
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014
Workqueue: events refill_work
Call Trace:
 <TASK>
 dump_stack_lvl+0x34/0x44
 print_report.cold+0xbb/0x6ac
 ? _printk+0xad/0xde
 ? refill_work+0x43/0xd4
 kasan_report+0xa8/0x130
 ? refill_work+0x43/0xd4
 refill_work+0x43/0xd4
 process_one_work+0x43d/0x780
 worker_thread+0x2a0/0x6f0
 ? process_one_work+0x780/0x780
 kthread+0x167/0x1a0
 ? kthread_exit+0x50/0x50
 ret_from_fork+0x22/0x30
 </TASK>
...

Fixes: b2baed69e605c ("virtio_net: set/cancel work on ndo_open/ndo_stop")
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
Changes since V4:
- Tweak the variable name (using delayed_refill)
Changes since V3:
- rebase to -net
Changes since V2:
- use spin_unlock()/lock_bh() in open/stop to synchronize with bh
Changes since V1:
- Tweak the changelog
---
 drivers/net/virtio_net.c | 35 +++++++++++++++++++++++++++++++++--
 1 file changed, 33 insertions(+), 2 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 356cf8dd4164..b9ac4431becb 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -245,6 +245,12 @@ struct virtnet_info {
 	/* Work struct for refilling if we run low on memory. */
 	struct delayed_work refill;
 
+	/* Is delayed refill enabled? */
+	bool delayed_refill_enabled;
+
+	/* The lock to synchronize the access to delayed_refill_enabled */
+	spinlock_t refill_lock;
+
 	/* Work struct for config space updates */
 	struct work_struct config_work;
 
@@ -348,6 +354,20 @@ static struct page *get_a_page(struct receive_queue *rq, gfp_t gfp_mask)
 	return p;
 }
 
+static void enable_delayed_refill(struct virtnet_info *vi)
+{
+	spin_lock_bh(&vi->refill_lock);
+	vi->delayed_refill_enabled = true;
+	spin_unlock_bh(&vi->refill_lock);
+}
+
+static void disable_delayed_refill(struct virtnet_info *vi)
+{
+	spin_lock_bh(&vi->refill_lock);
+	vi->delayed_refill_enabled = false;
+	spin_unlock_bh(&vi->refill_lock);
+}
+
 static void virtqueue_napi_schedule(struct napi_struct *napi,
 				    struct virtqueue *vq)
 {
@@ -1527,8 +1547,12 @@ static int virtnet_receive(struct receive_queue *rq, int budget,
 	}
 
 	if (rq->vq->num_free > min((unsigned int)budget, virtqueue_get_vring_size(rq->vq)) / 2) {
-		if (!try_fill_recv(vi, rq, GFP_ATOMIC))
-			schedule_delayed_work(&vi->refill, 0);
+		if (!try_fill_recv(vi, rq, GFP_ATOMIC)) {
+			spin_lock(&vi->refill_lock);
+			if (vi->delayed_refill_enabled)
+				schedule_delayed_work(&vi->refill, 0);
+			spin_unlock(&vi->refill_lock);
+		}
 	}
 
 	u64_stats_update_begin(&rq->stats.syncp);
@@ -1651,6 +1675,8 @@ static int virtnet_open(struct net_device *dev)
 	struct virtnet_info *vi = netdev_priv(dev);
 	int i, err;
 
+	enable_delayed_refill(vi);
+
 	for (i = 0; i < vi->max_queue_pairs; i++) {
 		if (i < vi->curr_queue_pairs)
 			/* Make sure we have some buffers: if oom use wq. */
@@ -2033,6 +2059,8 @@ static int virtnet_close(struct net_device *dev)
 	struct virtnet_info *vi = netdev_priv(dev);
 	int i;
 
+	/* Make sure NAPI doesn't schedule refill work */
+	disable_delayed_refill(vi);
 	/* Make sure refill_work doesn't re-enable napi! */
 	cancel_delayed_work_sync(&vi->refill);
 
@@ -2792,6 +2820,8 @@ static int virtnet_restore_up(struct virtio_device *vdev)
 
 	virtio_device_ready(vdev);
 
+	enable_delayed_refill(vi);
+
 	if (netif_running(vi->dev)) {
 		err = virtnet_open(vi->dev);
 		if (err)
@@ -3535,6 +3565,7 @@ static int virtnet_probe(struct virtio_device *vdev)
 	vdev->priv = vi;
 
 	INIT_WORK(&vi->config_work, virtnet_config_changed_work);
+	spin_lock_init(&vi->refill_lock);
 
 	/* If we can receive ANY GSO packets, we must allocate large ones. */
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO4) ||
-- 
2.25.1