Calling napi_disable() on an already disabled napi can cause the
deadlock. Because the delayed refill work will call napi_disable(), we
must ensure that refill work is only enabled and scheduled after we have
enabled the rx queue's NAPI.
Signed-off-by: Bui Quang Minh <minhquangbui99@gmail.com>
---
drivers/net/virtio_net.c | 31 ++++++++++++++++++++++++-------
1 file changed, 24 insertions(+), 7 deletions(-)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 63126e490bda..8016d2b378cf 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -3208,16 +3208,31 @@ static int virtnet_open(struct net_device *dev)
int i, err;
for (i = 0; i < vi->max_queue_pairs; i++) {
+ bool schedule_refill = false;
+
+ /* - We must call try_fill_recv before enabling napi of the same
+ * receive queue so that it doesn't race with the call in
+ * virtnet_receive.
+ * - We must enable and schedule delayed refill work only when
+ * we have enabled all the receive queue's napi. Otherwise, in
+ * refill_work, we have a deadlock when calling napi_disable on
+ * an already disabled napi.
+ */
if (i < vi->curr_queue_pairs) {
- enable_delayed_refill(&vi->rq[i]);
/* Make sure we have some buffers: if oom use wq. */
if (!try_fill_recv(vi, &vi->rq[i], GFP_KERNEL))
- schedule_delayed_work(&vi->rq[i].refill, 0);
+ schedule_refill = true;
}
err = virtnet_enable_queue_pair(vi, i);
if (err < 0)
goto err_enable_qp;
+
+ if (i < vi->curr_queue_pairs) {
+ enable_delayed_refill(&vi->rq[i]);
+ if (schedule_refill)
+ schedule_delayed_work(&vi->rq[i].refill, 0);
+ }
}
if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_STATUS)) {
@@ -3456,11 +3471,16 @@ static void __virtnet_rx_resume(struct virtnet_info *vi,
bool running = netif_running(vi->dev);
bool schedule_refill = false;
+ /* See the comment in virtnet_open for the ordering rule
+ * of try_fill_recv, receive queue napi_enable and delayed
+ * refill enable/schedule.
+ */
if (refill && !try_fill_recv(vi, rq, GFP_KERNEL))
schedule_refill = true;
if (running)
virtnet_napi_enable(rq);
+ enable_delayed_refill(rq);
if (schedule_refill)
schedule_delayed_work(&rq->refill, 0);
}
@@ -3470,18 +3490,15 @@ static void virtnet_rx_resume_all(struct virtnet_info *vi)
int i;
for (i = 0; i < vi->max_queue_pairs; i++) {
- if (i < vi->curr_queue_pairs) {
- enable_delayed_refill(&vi->rq[i]);
+ if (i < vi->curr_queue_pairs)
__virtnet_rx_resume(vi, &vi->rq[i], true);
- } else {
+ 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(rq);
__virtnet_rx_resume(vi, rq, true);
}
--
2.43.0On Tue, Dec 23, 2025 at 10:25:32PM +0700, Bui Quang Minh wrote:
> Calling napi_disable() on an already disabled napi can cause the
> deadlock.
a deadlock?
> Because the delayed refill work will call napi_disable(), we
> must ensure that refill work is only enabled and scheduled after we have
> enabled the rx queue's NAPI.
a bugfix so needs a Fixes tag.
>
> Signed-off-by: Bui Quang Minh <minhquangbui99@gmail.com>
> ---
> drivers/net/virtio_net.c | 31 ++++++++++++++++++++++++-------
> 1 file changed, 24 insertions(+), 7 deletions(-)
>
> diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> index 63126e490bda..8016d2b378cf 100644
> --- a/drivers/net/virtio_net.c
> +++ b/drivers/net/virtio_net.c
> @@ -3208,16 +3208,31 @@ static int virtnet_open(struct net_device *dev)
> int i, err;
>
> for (i = 0; i < vi->max_queue_pairs; i++) {
> + bool schedule_refill = false;
> +
> + /* - We must call try_fill_recv before enabling napi of the same
> + * receive queue so that it doesn't race with the call in
> + * virtnet_receive.
> + * - We must enable and schedule delayed refill work only when
> + * we have enabled all the receive queue's napi. Otherwise, in
> + * refill_work, we have a deadlock when calling napi_disable on
> + * an already disabled napi.
> + */
> if (i < vi->curr_queue_pairs) {
> - enable_delayed_refill(&vi->rq[i]);
> /* Make sure we have some buffers: if oom use wq. */
> if (!try_fill_recv(vi, &vi->rq[i], GFP_KERNEL))
> - schedule_delayed_work(&vi->rq[i].refill, 0);
> + schedule_refill = true;
> }
>
> err = virtnet_enable_queue_pair(vi, i);
> if (err < 0)
> goto err_enable_qp;
> +
> + if (i < vi->curr_queue_pairs) {
> + enable_delayed_refill(&vi->rq[i]);
> + if (schedule_refill)
> + schedule_delayed_work(&vi->rq[i].refill, 0);
> + }
> }
>
> if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_STATUS)) {
> @@ -3456,11 +3471,16 @@ static void __virtnet_rx_resume(struct virtnet_info *vi,
> bool running = netif_running(vi->dev);
> bool schedule_refill = false;
>
> + /* See the comment in virtnet_open for the ordering rule
> + * of try_fill_recv, receive queue napi_enable and delayed
> + * refill enable/schedule.
> + */
> if (refill && !try_fill_recv(vi, rq, GFP_KERNEL))
> schedule_refill = true;
> if (running)
> virtnet_napi_enable(rq);
>
> + enable_delayed_refill(rq);
> if (schedule_refill)
> schedule_delayed_work(&rq->refill, 0);
> }
> @@ -3470,18 +3490,15 @@ static void virtnet_rx_resume_all(struct virtnet_info *vi)
> int i;
>
> for (i = 0; i < vi->max_queue_pairs; i++) {
> - if (i < vi->curr_queue_pairs) {
> - enable_delayed_refill(&vi->rq[i]);
> + if (i < vi->curr_queue_pairs)
> __virtnet_rx_resume(vi, &vi->rq[i], true);
> - } else {
> + 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(rq);
> __virtnet_rx_resume(vi, rq, true);
> }
>
> --
> 2.43.0
On Tue, Dec 23, 2025 at 10:25:32PM +0700, Bui Quang Minh wrote:
> Calling napi_disable() on an already disabled napi can cause the
> deadlock. Because the delayed refill work will call napi_disable(), we
> must ensure that refill work is only enabled and scheduled after we have
> enabled the rx queue's NAPI.
>
> Signed-off-by: Bui Quang Minh <minhquangbui99@gmail.com>
> ---
> drivers/net/virtio_net.c | 31 ++++++++++++++++++++++++-------
> 1 file changed, 24 insertions(+), 7 deletions(-)
>
> diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> index 63126e490bda..8016d2b378cf 100644
> --- a/drivers/net/virtio_net.c
> +++ b/drivers/net/virtio_net.c
> @@ -3208,16 +3208,31 @@ static int virtnet_open(struct net_device *dev)
> int i, err;
>
> for (i = 0; i < vi->max_queue_pairs; i++) {
> + bool schedule_refill = false;
> +
> + /* - We must call try_fill_recv before enabling napi of the same
> + * receive queue so that it doesn't race with the call in
> + * virtnet_receive.
> + * - We must enable and schedule delayed refill work only when
> + * we have enabled all the receive queue's napi. Otherwise, in
> + * refill_work, we have a deadlock when calling napi_disable on
> + * an already disabled napi.
> + */
I would do:
bool refill = i < vi->curr_queue_pairs;
in fact this is almost the same as resume with
one small difference. pass a flag so we do not duplicate code?
> if (i < vi->curr_queue_pairs) {
> - enable_delayed_refill(&vi->rq[i]);
> /* Make sure we have some buffers: if oom use wq. */
> if (!try_fill_recv(vi, &vi->rq[i], GFP_KERNEL))
> - schedule_delayed_work(&vi->rq[i].refill, 0);
> + schedule_refill = true;
> }
>
> err = virtnet_enable_queue_pair(vi, i);
> if (err < 0)
> goto err_enable_qp;
> +
> + if (i < vi->curr_queue_pairs) {
> + enable_delayed_refill(&vi->rq[i]);
> + if (schedule_refill)
> + schedule_delayed_work(&vi->rq[i].refill, 0);
hmm. should not schedule be under the lock?
> + }
> }
>
> if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_STATUS)) {
> @@ -3456,11 +3471,16 @@ static void __virtnet_rx_resume(struct virtnet_info *vi,
> bool running = netif_running(vi->dev);
> bool schedule_refill = false;
>
> + /* See the comment in virtnet_open for the ordering rule
> + * of try_fill_recv, receive queue napi_enable and delayed
> + * refill enable/schedule.
> + */
so maybe common code?
> if (refill && !try_fill_recv(vi, rq, GFP_KERNEL))
> schedule_refill = true;
> if (running)
> virtnet_napi_enable(rq);
>
> + enable_delayed_refill(rq);
> if (schedule_refill)
> schedule_delayed_work(&rq->refill, 0);
hmm. should not schedule be under the lock?
> }
> @@ -3470,18 +3490,15 @@ static void virtnet_rx_resume_all(struct virtnet_info *vi)
> int i;
>
> for (i = 0; i < vi->max_queue_pairs; i++) {
> - if (i < vi->curr_queue_pairs) {
> - enable_delayed_refill(&vi->rq[i]);
> + if (i < vi->curr_queue_pairs)
> __virtnet_rx_resume(vi, &vi->rq[i], true);
> - } else {
> + 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(rq);
> __virtnet_rx_resume(vi, rq, true);
> }
so I would add bool to virtnet_rx_resume and call it everywhere,
removing __virtnet_rx_resume. can be a patch on top.
>
> --
> 2.43.0
On 12/24/25 08:45, Michael S. Tsirkin wrote:
> On Tue, Dec 23, 2025 at 10:25:32PM +0700, Bui Quang Minh wrote:
>> Calling napi_disable() on an already disabled napi can cause the
>> deadlock. Because the delayed refill work will call napi_disable(), we
>> must ensure that refill work is only enabled and scheduled after we have
>> enabled the rx queue's NAPI.
>>
>> Signed-off-by: Bui Quang Minh <minhquangbui99@gmail.com>
>> ---
>> drivers/net/virtio_net.c | 31 ++++++++++++++++++++++++-------
>> 1 file changed, 24 insertions(+), 7 deletions(-)
>>
>> diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
>> index 63126e490bda..8016d2b378cf 100644
>> --- a/drivers/net/virtio_net.c
>> +++ b/drivers/net/virtio_net.c
>> @@ -3208,16 +3208,31 @@ static int virtnet_open(struct net_device *dev)
>> int i, err;
>>
>> for (i = 0; i < vi->max_queue_pairs; i++) {
>> + bool schedule_refill = false;
>
>
>> +
>> + /* - We must call try_fill_recv before enabling napi of the same
>> + * receive queue so that it doesn't race with the call in
>> + * virtnet_receive.
>> + * - We must enable and schedule delayed refill work only when
>> + * we have enabled all the receive queue's napi. Otherwise, in
>> + * refill_work, we have a deadlock when calling napi_disable on
>> + * an already disabled napi.
>> + */
>
> I would do:
>
> bool refill = i < vi->curr_queue_pairs;
>
> in fact this is almost the same as resume with
> one small difference. pass a flag so we do not duplicate code?
I'll fix it in next version.
>
>> if (i < vi->curr_queue_pairs) {
>> - enable_delayed_refill(&vi->rq[i]);
>> /* Make sure we have some buffers: if oom use wq. */
>> if (!try_fill_recv(vi, &vi->rq[i], GFP_KERNEL))
>> - schedule_delayed_work(&vi->rq[i].refill, 0);
>> + schedule_refill = true;
>> }
>>
>> err = virtnet_enable_queue_pair(vi, i);
>> if (err < 0)
>> goto err_enable_qp;
>> +
>> + if (i < vi->curr_queue_pairs) {
>> + enable_delayed_refill(&vi->rq[i]);
>> + if (schedule_refill)
>> + schedule_delayed_work(&vi->rq[i].refill, 0);
>
> hmm. should not schedule be under the lock?
I see that schedule is safe to be called concurrently.
struct work_struct {
atomic_long_t data;
struct list_head entry;
work_func_t func;
#ifdef CONFIG_LOCKDEP
struct lockdep_map lockdep_map;
#endif
};
The atomic_long_t field to set pending bit and worker pool's lock help
with the synchronization.
>
>> + }
>> }
>>
>> if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_STATUS)) {
>> @@ -3456,11 +3471,16 @@ static void __virtnet_rx_resume(struct virtnet_info *vi,
>> bool running = netif_running(vi->dev);
>> bool schedule_refill = false;
>>
>> + /* See the comment in virtnet_open for the ordering rule
>> + * of try_fill_recv, receive queue napi_enable and delayed
>> + * refill enable/schedule.
>> + */
> so maybe common code?
>
>> if (refill && !try_fill_recv(vi, rq, GFP_KERNEL))
>> schedule_refill = true;
>> if (running)
>> virtnet_napi_enable(rq);
>>
>> + enable_delayed_refill(rq);
>> if (schedule_refill)
>> schedule_delayed_work(&rq->refill, 0);
> hmm. should not schedule be under the lock?
>
>> }
>> @@ -3470,18 +3490,15 @@ static void virtnet_rx_resume_all(struct virtnet_info *vi)
>> int i;
>>
>> for (i = 0; i < vi->max_queue_pairs; i++) {
>> - if (i < vi->curr_queue_pairs) {
>> - enable_delayed_refill(&vi->rq[i]);
>> + if (i < vi->curr_queue_pairs)
>> __virtnet_rx_resume(vi, &vi->rq[i], true);
>> - } else {
>> + 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(rq);
>> __virtnet_rx_resume(vi, rq, true);
>> }
> so I would add bool to virtnet_rx_resume and call it everywhere,
> removing __virtnet_rx_resume. can be a patch on top.
I'll create another patch after this patch to clean up the
__virtnet_rx_resume in the next version.
Thanks,
Quang Minh.
>
>>
>> --
>> 2.43.0
© 2016 - 2026 Red Hat, Inc.