mirrors/linux
1
0
Fork 1
mirror of https://github.com/torvalds/linux.git synced 2025-11-04 02:30:34 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

virtio-net: disable delayed refill when pausing rx

Browse source 
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: 413f0271f3 ("net: protect NAPI enablement with netdev_lock()")
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Bui Quang Minh <minhquangbui99@gmail.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Link: https://patch.msgid.link/20250417072806.18660-2-minhquangbui99@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This commit is contained in:
Bui Quang Minh 2025-04-17 14:28:03 +07:00 committed by Jakub Kicinski
parent b7f0ee992a
commit 4bc12818b3
1 changed files with 57 additions and 12 deletions
repo.diff.show_diff_stats Download patch file Download diff file Expand all files Collapse all files

69
drivers/net/virtio_net.c
View file

@ -3342,7 +3342,8 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
return NETDEV_TX_OK; 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); 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); 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); schedule_delayed_work(&vi->refill, 0);
if (running) if (running)
virtnet_napi_enable(rq); 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, static int virtnet_rx_resize(struct virtnet_info *vi,
struct receive_queue *rq, u32 ring_num) struct receive_queue *rq, u32 ring_num)
{ {
@ -5959,12 +6006,12 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
if (prog) if (prog)
bpf_prog_add(prog, vi->max_queue_pairs - 1); 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. */ /* Make sure NAPI is not using any XDP TX queues for RX. */
if (netif_running(dev)) { if (netif_running(dev)) {
for (i = 0; i < vi->max_queue_pairs; i++) { for (i = 0; i < vi->max_queue_pairs; i++)
virtnet_napi_disable(&vi->rq[i]);
virtnet_napi_tx_disable(&vi->sq[i]); virtnet_napi_tx_disable(&vi->sq[i]);
}
} }
if (!prog) { if (!prog) {
@ -5996,13 +6043,12 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
vi->xdp_enabled = false; vi->xdp_enabled = false;
} }
virtnet_rx_resume_all(vi);
for (i = 0; i < vi->max_queue_pairs; i++) { for (i = 0; i < vi->max_queue_pairs; i++) {
if (old_prog) if (old_prog)
bpf_prog_put(old_prog); bpf_prog_put(old_prog);
if (netif_running(dev)) { if (netif_running(dev))
virtnet_napi_enable(&vi->rq[i]);
virtnet_napi_tx_enable(&vi->sq[i]); virtnet_napi_tx_enable(&vi->sq[i]);
}
} }
return 0; return 0;
@ -6014,11 +6060,10 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
rcu_assign_pointer(vi->rq[i].xdp_prog, old_prog); rcu_assign_pointer(vi->rq[i].xdp_prog, old_prog);
} }
virtnet_rx_resume_all(vi);
if (netif_running(dev)) { if (netif_running(dev)) {
for (i = 0; i < vi->max_queue_pairs; i++) { for (i = 0; i < vi->max_queue_pairs; i++)
virtnet_napi_enable(&vi->rq[i]);
virtnet_napi_tx_enable(&vi->sq[i]); virtnet_napi_tx_enable(&vi->sq[i]);
}
} }
if (prog) if (prog)
bpf_prog_sub(prog, vi->max_queue_pairs - 1); bpf_prog_sub(prog, vi->max_queue_pairs - 1);