Message-ID: <20251208153419.18196-1-minhquangbui99@gmail.com>
Date: Mon,  8 Dec 2025 22:34:19 +0700
From: Bui Quang Minh <minhquangbui99@...il.com>
To: netdev@...r.kernel.org
Cc: "Michael S. Tsirkin" <mst@...hat.com>,
	Jason Wang <jasowang@...hat.com>,
	Xuan Zhuo <xuanzhuo@...ux.alibaba.com>,
	Eugenio Pérez <eperezma@...hat.com>,
	Andrew Lunn <andrew+netdev@...n.ch>,
	"David S. Miller" <davem@...emloft.net>,
	Eric Dumazet <edumazet@...gle.com>,
	Jakub Kicinski <kuba@...nel.org>,
	Paolo Abeni <pabeni@...hat.com>,
	Alexei Starovoitov <ast@...nel.org>,
	Daniel Borkmann <daniel@...earbox.net>,
	Jesper Dangaard Brouer <hawk@...nel.org>,
	John Fastabend <john.fastabend@...il.com>,
	Stanislav Fomichev <sdf@...ichev.me>,
	virtualization@...ts.linux.dev,
	linux-kernel@...r.kernel.org,
	bpf@...r.kernel.org,
	Bui Quang Minh <minhquangbui99@...il.com>
Subject: [PATCH net] virtio-net: enable all napis before scheduling refill work

Calling napi_disable() on an already disabled napi can cause the
deadlock. In commit 4bc12818b363 ("virtio-net: disable delayed refill
when pausing rx"), to avoid the deadlock, when pausing the RX in
virtnet_rx_pause[_all](), we disable and cancel the delayed refill work.
However, in the virtnet_rx_resume_all(), we enable the delayed refill
work too early before enabling all the receive queue napis.

The deadlock can be reproduced by running
selftests/drivers/net/hw/xsk_reconfig.py with multiqueue virtio-net
device and inserting a cond_resched() inside the for loop in
virtnet_rx_resume_all() to increase the success rate. Because the worker
processing the delayed refilled work runs on the same CPU as
virtnet_rx_resume_all(), a reschedule is needed to cause the deadlock.
In real scenario, the contention on netdev_lock can cause the
reschedule.

This fixes the deadlock by ensuring all receive queue's napis are
enabled before we enable the delayed refill work in
virtnet_rx_resume_all() and virtnet_open().

Fixes: 4bc12818b363 ("virtio-net: disable delayed refill when pausing rx")
Reported-by: Paolo Abeni <pabeni@...hat.com>
Closes: https://netdev-ctrl.bots.linux.dev/logs/vmksft/drv-hw-dbg/results/400961/3-xdp-py/stderr
Signed-off-by: Bui Quang Minh <minhquangbui99@...il.com>
---
 drivers/net/virtio_net.c | 59 +++++++++++++++++++---------------------
 1 file changed, 28 insertions(+), 31 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 8e04adb57f52..f2b1ea65767d 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -2858,6 +2858,20 @@ static bool try_fill_recv(struct virtnet_info *vi, struct receive_queue *rq,
 	return err != -ENOMEM;
 }
 
+static void virtnet_rx_refill_all(struct virtnet_info *vi)
+{
+	bool schedule_refill = false;
+	int i;
+
+	enable_delayed_refill(vi);
+	for (i = 0; i < vi->curr_queue_pairs; i++)
+		if (!try_fill_recv(vi, &vi->rq[i], GFP_KERNEL))
+			schedule_refill = true;
+
+	if (schedule_refill)
+		schedule_delayed_work(&vi->refill, 0);
+}
+
 static void skb_recv_done(struct virtqueue *rvq)
 {
 	struct virtnet_info *vi = rvq->vdev->priv;
@@ -3216,19 +3230,14 @@ 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. */
-			if (!try_fill_recv(vi, &vi->rq[i], GFP_KERNEL))
-				schedule_delayed_work(&vi->refill, 0);
-
 		err = virtnet_enable_queue_pair(vi, i);
 		if (err < 0)
 			goto err_enable_qp;
 	}
 
+	virtnet_rx_refill_all(vi);
+
 	if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_STATUS)) {
 		if (vi->status & VIRTIO_NET_S_LINK_UP)
 			netif_carrier_on(vi->dev);
@@ -3463,39 +3472,27 @@ static void virtnet_rx_pause(struct virtnet_info *vi, struct receive_queue *rq)
 	__virtnet_rx_pause(vi, rq);
 }
 
-static void __virtnet_rx_resume(struct virtnet_info *vi,
-				struct receive_queue *rq,
-				bool refill)
-{
-	bool running = netif_running(vi->dev);
-	bool schedule_refill = false;
-
-	if (refill && !try_fill_recv(vi, rq, GFP_KERNEL))
-		schedule_refill = true;
-	if (running)
-		virtnet_napi_enable(rq);
-
-	if (schedule_refill)
-		schedule_delayed_work(&vi->refill, 0);
-}
-
 static void virtnet_rx_resume_all(struct virtnet_info *vi)
 {
 	int i;
 
-	enable_delayed_refill(vi);
-	for (i = 0; i < vi->max_queue_pairs; i++) {
-		if (i < vi->curr_queue_pairs)
-			__virtnet_rx_resume(vi, &vi->rq[i], true);
-		else
-			__virtnet_rx_resume(vi, &vi->rq[i], false);
+	if (netif_running(vi->dev)) {
+		for (i = 0; i < vi->max_queue_pairs; i++)
+			virtnet_napi_enable(&vi->rq[i]);
+
+		virtnet_rx_refill_all(vi);
 	}
 }
 
 static void virtnet_rx_resume(struct virtnet_info *vi, struct receive_queue *rq)
 {
-	enable_delayed_refill(vi);
-	__virtnet_rx_resume(vi, rq, true);
+	if (netif_running(vi->dev)) {
+		virtnet_napi_enable(rq);
+
+		enable_delayed_refill(vi);
+		if (!try_fill_recv(vi, rq, GFP_KERNEL))
+			schedule_delayed_work(&vi->refill, 0);
+	}
 }
 
 static int virtnet_rx_resize(struct virtnet_info *vi,
-- 
2.43.0

Powered by blists - more mailing lists