Commit 4bc12818 authored by Bui Quang Minh's avatar Bui Quang Minh Committed by Jakub Kicinski
Browse files

virtio-net: disable delayed refill when pausing rx 



When pausing rx (e.g. set up xdp, xsk pool, rx resize), we call
napi_disable() on the receive queue's napi. In delayed refill_work, it
also calls napi_disable() on the receive queue's napi.  When
napi_disable() is called on an already disabled napi, it will sleep in
napi_disable_locked while still holding the netdev_lock. As a result,
later napi_enable gets stuck too as it cannot acquire the netdev_lock.
This leads to refill_work and the pause-then-resume tx are stuck
altogether.

This scenario can be reproducible by binding a XDP socket to virtio-net
interface without setting up the fill ring. As a result, try_fill_recv
will fail until the fill ring is set up and refill_work is scheduled.

This commit adds virtnet_rx_(pause/resume)_all helpers and fixes up the
virtnet_rx_resume to disable future and cancel all inflights delayed
refill_work before calling napi_disable() to pause the rx.

Fixes: 413f0271 ("net: protect NAPI enablement with netdev_lock()")
Acked-by: default avatarMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: default avatarBui Quang Minh <minhquangbui99@gmail.com>
Acked-by: default avatarJason Wang <jasowang@redhat.com>
Link: https://patch.msgid.link/20250417072806.18660-2-minhquangbui99@gmail.com


Signed-off-by: default avatarJakub Kicinski <kuba@kernel.org>
parent b7f0ee99

drivers/net/virtio_net.c

+57 −12
Original line number Diff line number Diff line
@@ -3342,7 +3342,8 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev) 
	return NETDEV_TX_OK;

}



static void virtnet_rx_pause(struct virtnet_info *vi, struct receive_queue *rq)

static void __virtnet_rx_pause(struct virtnet_info *vi,

			       struct receive_queue *rq)

{

	bool running = netif_running(vi->dev);
@@ -3352,17 +3353,63 @@ static void virtnet_rx_pause(struct virtnet_info *vi, struct receive_queue *rq) 
	}

}



static void virtnet_rx_resume(struct virtnet_info *vi, struct receive_queue *rq)

static void virtnet_rx_pause_all(struct virtnet_info *vi)

{

	int i;



	/*

	 * Make sure refill_work does not run concurrently to

	 * avoid napi_disable race which leads to deadlock.

	 */

	disable_delayed_refill(vi);

	cancel_delayed_work_sync(&vi->refill);

	for (i = 0; i < vi->max_queue_pairs; i++)

		__virtnet_rx_pause(vi, &vi->rq[i]);

}



static void virtnet_rx_pause(struct virtnet_info *vi, struct receive_queue *rq)

{

	/*

	 * Make sure refill_work does not run concurrently to

	 * avoid napi_disable race which leads to deadlock.

	 */

	disable_delayed_refill(vi);

	cancel_delayed_work_sync(&vi->refill);

	__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);



	if (!try_fill_recv(vi, rq, GFP_KERNEL))

	if (refill && !try_fill_recv(vi, rq, GFP_KERNEL))

		schedule_delayed_work(&vi->refill, 0);



	if (running)

		virtnet_napi_enable(rq);

}



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);

	}

}



static void virtnet_rx_resume(struct virtnet_info *vi, struct receive_queue *rq)

{

	enable_delayed_refill(vi);

	__virtnet_rx_resume(vi, rq, true);

}



static int virtnet_rx_resize(struct virtnet_info *vi,

			     struct receive_queue *rq, u32 ring_num)

{
@@ -5959,13 +6006,13 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog, 
	if (prog)

		bpf_prog_add(prog, vi->max_queue_pairs - 1);



	virtnet_rx_pause_all(vi);



	/* Make sure NAPI is not using any XDP TX queues for RX. */

	if (netif_running(dev)) {

		for (i = 0; i < vi->max_queue_pairs; i++) {

			virtnet_napi_disable(&vi->rq[i]);

		for (i = 0; i < vi->max_queue_pairs; i++)

			virtnet_napi_tx_disable(&vi->sq[i]);

	}

	}



	if (!prog) {

		for (i = 0; i < vi->max_queue_pairs; i++) {
@@ -5996,14 +6043,13 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog, 
		vi->xdp_enabled = false;

	}



	virtnet_rx_resume_all(vi);

	for (i = 0; i < vi->max_queue_pairs; i++) {

		if (old_prog)

			bpf_prog_put(old_prog);

		if (netif_running(dev)) {

			virtnet_napi_enable(&vi->rq[i]);

		if (netif_running(dev))

			virtnet_napi_tx_enable(&vi->sq[i]);

	}

	}



	return 0;
@@ -6014,12 +6060,11 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog, 
			rcu_assign_pointer(vi->rq[i].xdp_prog, old_prog);

	}



	virtnet_rx_resume_all(vi);

	if (netif_running(dev)) {

		for (i = 0; i < vi->max_queue_pairs; i++) {

			virtnet_napi_enable(&vi->rq[i]);

		for (i = 0; i < vi->max_queue_pairs; i++)

			virtnet_napi_tx_enable(&vi->sq[i]);

	}

	}

	if (prog)

		bpf_prog_sub(prog, vi->max_queue_pairs - 1);

	return err;