* [PATCH v4] virtio_net: suppress cpu stall when free_unused_bufs
@ 2023-05-04 2:27 Wenliang Wang
2023-05-04 7:06 ` Michael S. Tsirkin
` (2 more replies)
0 siblings, 3 replies; 20+ messages in thread
From: Wenliang Wang @ 2023-05-04 2:27 UTC (permalink / raw)
To: mst, jasowang, davem, edumazet, kuba, pabeni, zhengqi.arch,
willemdebruijn.kernel
Cc: virtualization, netdev, linux-kernel, xuanzhuo, Wenliang Wang
For multi-queue and large ring-size use case, the following error
occurred when free_unused_bufs:
rcu: INFO: rcu_sched self-detected stall on CPU.
Fixes: 986a4f4d452d ("virtio_net: multiqueue support")
Signed-off-by: Wenliang Wang <wangwenliang.1995@bytedance.com>
---
v2:
-add need_resched check.
-apply same logic to sq.
v3:
-use cond_resched instead.
v4:
-add fixes tag
---
drivers/net/virtio_net.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 8d8038538fc4..a12ae26db0e2 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -3560,12 +3560,14 @@ static void free_unused_bufs(struct virtnet_info *vi)
struct virtqueue *vq = vi->sq[i].vq;
while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
virtnet_sq_free_unused_buf(vq, buf);
+ cond_resched();
}
for (i = 0; i < vi->max_queue_pairs; i++) {
struct virtqueue *vq = vi->rq[i].vq;
while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
virtnet_rq_free_unused_buf(vq, buf);
+ cond_resched();
}
}
--
2.20.1
^ permalink raw reply related [flat|nested] 20+ messages in thread
* Re: [PATCH v4] virtio_net: suppress cpu stall when free_unused_bufs
2023-05-04 2:27 [PATCH v4] virtio_net: suppress cpu stall when free_unused_bufs Wenliang Wang
@ 2023-05-04 7:06 ` Michael S. Tsirkin
2023-05-05 3:28 ` Jason Wang
2023-05-05 8:40 ` patchwork-bot+netdevbpf
2 siblings, 0 replies; 20+ messages in thread
From: Michael S. Tsirkin @ 2023-05-04 7:06 UTC (permalink / raw)
To: Wenliang Wang
Cc: jasowang, davem, edumazet, kuba, pabeni, zhengqi.arch,
willemdebruijn.kernel, virtualization, netdev, linux-kernel,
xuanzhuo
On Thu, May 04, 2023 at 10:27:06AM +0800, Wenliang Wang wrote:
> For multi-queue and large ring-size use case, the following error
> occurred when free_unused_bufs:
> rcu: INFO: rcu_sched self-detected stall on CPU.
>
> Fixes: 986a4f4d452d ("virtio_net: multiqueue support")
> Signed-off-by: Wenliang Wang <wangwenliang.1995@bytedance.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Probably a good idea for stable, too.
> ---
> v2:
> -add need_resched check.
> -apply same logic to sq.
> v3:
> -use cond_resched instead.
> v4:
> -add fixes tag
> ---
> drivers/net/virtio_net.c | 2 ++
> 1 file changed, 2 insertions(+)
>
> diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> index 8d8038538fc4..a12ae26db0e2 100644
> --- a/drivers/net/virtio_net.c
> +++ b/drivers/net/virtio_net.c
> @@ -3560,12 +3560,14 @@ static void free_unused_bufs(struct virtnet_info *vi)
> struct virtqueue *vq = vi->sq[i].vq;
> while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
> virtnet_sq_free_unused_buf(vq, buf);
> + cond_resched();
> }
>
> for (i = 0; i < vi->max_queue_pairs; i++) {
> struct virtqueue *vq = vi->rq[i].vq;
> while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
> virtnet_rq_free_unused_buf(vq, buf);
> + cond_resched();
> }
> }
>
> --
> 2.20.1
^ permalink raw reply [flat|nested] 20+ messages in thread
* Re: [PATCH v4] virtio_net: suppress cpu stall when free_unused_bufs
@ 2023-05-04 7:06 ` Michael S. Tsirkin
0 siblings, 0 replies; 20+ messages in thread
From: Michael S. Tsirkin @ 2023-05-04 7:06 UTC (permalink / raw)
To: Wenliang Wang
Cc: xuanzhuo, willemdebruijn.kernel, netdev, linux-kernel,
zhengqi.arch, virtualization, edumazet, kuba, pabeni, davem
On Thu, May 04, 2023 at 10:27:06AM +0800, Wenliang Wang wrote:
> For multi-queue and large ring-size use case, the following error
> occurred when free_unused_bufs:
> rcu: INFO: rcu_sched self-detected stall on CPU.
>
> Fixes: 986a4f4d452d ("virtio_net: multiqueue support")
> Signed-off-by: Wenliang Wang <wangwenliang.1995@bytedance.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Probably a good idea for stable, too.
> ---
> v2:
> -add need_resched check.
> -apply same logic to sq.
> v3:
> -use cond_resched instead.
> v4:
> -add fixes tag
> ---
> drivers/net/virtio_net.c | 2 ++
> 1 file changed, 2 insertions(+)
>
> diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> index 8d8038538fc4..a12ae26db0e2 100644
> --- a/drivers/net/virtio_net.c
> +++ b/drivers/net/virtio_net.c
> @@ -3560,12 +3560,14 @@ static void free_unused_bufs(struct virtnet_info *vi)
> struct virtqueue *vq = vi->sq[i].vq;
> while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
> virtnet_sq_free_unused_buf(vq, buf);
> + cond_resched();
> }
>
> for (i = 0; i < vi->max_queue_pairs; i++) {
> struct virtqueue *vq = vi->rq[i].vq;
> while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
> virtnet_rq_free_unused_buf(vq, buf);
> + cond_resched();
> }
> }
>
> --
> 2.20.1
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
^ permalink raw reply [flat|nested] 20+ messages in thread
* Re: [PATCH v4] virtio_net: suppress cpu stall when free_unused_bufs
2023-05-04 2:27 [PATCH v4] virtio_net: suppress cpu stall when free_unused_bufs Wenliang Wang
@ 2023-05-05 3:28 ` Jason Wang
2023-05-05 3:28 ` Jason Wang
2023-05-05 8:40 ` patchwork-bot+netdevbpf
2 siblings, 0 replies; 20+ messages in thread
From: Jason Wang @ 2023-05-05 3:28 UTC (permalink / raw)
To: Wenliang Wang
Cc: mst, davem, edumazet, kuba, pabeni, zhengqi.arch,
willemdebruijn.kernel, virtualization, netdev, linux-kernel,
xuanzhuo
On Thu, May 4, 2023 at 10:27 AM Wenliang Wang
<wangwenliang.1995@bytedance.com> wrote:
>
> For multi-queue and large ring-size use case, the following error
> occurred when free_unused_bufs:
> rcu: INFO: rcu_sched self-detected stall on CPU.
>
> Fixes: 986a4f4d452d ("virtio_net: multiqueue support")
> Signed-off-by: Wenliang Wang <wangwenliang.1995@bytedance.com>
> ---
> v2:
> -add need_resched check.
> -apply same logic to sq.
> v3:
> -use cond_resched instead.
> v4:
> -add fixes tag
> ---
> drivers/net/virtio_net.c | 2 ++
> 1 file changed, 2 insertions(+)
>
> diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> index 8d8038538fc4..a12ae26db0e2 100644
> --- a/drivers/net/virtio_net.c
> +++ b/drivers/net/virtio_net.c
> @@ -3560,12 +3560,14 @@ static void free_unused_bufs(struct virtnet_info *vi)
> struct virtqueue *vq = vi->sq[i].vq;
> while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
> virtnet_sq_free_unused_buf(vq, buf);
> + cond_resched();
Does this really address the case when the virtqueue is very large?
Thanks
> }
>
> for (i = 0; i < vi->max_queue_pairs; i++) {
> struct virtqueue *vq = vi->rq[i].vq;
> while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
> virtnet_rq_free_unused_buf(vq, buf);
> + cond_resched();
> }
> }
>
> --
> 2.20.1
>
^ permalink raw reply [flat|nested] 20+ messages in thread
* Re: [PATCH v4] virtio_net: suppress cpu stall when free_unused_bufs
@ 2023-05-05 3:28 ` Jason Wang
0 siblings, 0 replies; 20+ messages in thread
From: Jason Wang @ 2023-05-05 3:28 UTC (permalink / raw)
To: Wenliang Wang
Cc: xuanzhuo, willemdebruijn.kernel, mst, netdev, linux-kernel,
zhengqi.arch, virtualization, edumazet, kuba, pabeni, davem
On Thu, May 4, 2023 at 10:27 AM Wenliang Wang
<wangwenliang.1995@bytedance.com> wrote:
>
> For multi-queue and large ring-size use case, the following error
> occurred when free_unused_bufs:
> rcu: INFO: rcu_sched self-detected stall on CPU.
>
> Fixes: 986a4f4d452d ("virtio_net: multiqueue support")
> Signed-off-by: Wenliang Wang <wangwenliang.1995@bytedance.com>
> ---
> v2:
> -add need_resched check.
> -apply same logic to sq.
> v3:
> -use cond_resched instead.
> v4:
> -add fixes tag
> ---
> drivers/net/virtio_net.c | 2 ++
> 1 file changed, 2 insertions(+)
>
> diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> index 8d8038538fc4..a12ae26db0e2 100644
> --- a/drivers/net/virtio_net.c
> +++ b/drivers/net/virtio_net.c
> @@ -3560,12 +3560,14 @@ static void free_unused_bufs(struct virtnet_info *vi)
> struct virtqueue *vq = vi->sq[i].vq;
> while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
> virtnet_sq_free_unused_buf(vq, buf);
> + cond_resched();
Does this really address the case when the virtqueue is very large?
Thanks
> }
>
> for (i = 0; i < vi->max_queue_pairs; i++) {
> struct virtqueue *vq = vi->rq[i].vq;
> while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
> virtnet_rq_free_unused_buf(vq, buf);
> + cond_resched();
> }
> }
>
> --
> 2.20.1
>
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
^ permalink raw reply [flat|nested] 20+ messages in thread
* Re: [PATCH v4] virtio_net: suppress cpu stall when free_unused_bufs
2023-05-04 2:27 [PATCH v4] virtio_net: suppress cpu stall when free_unused_bufs Wenliang Wang
2023-05-04 7:06 ` Michael S. Tsirkin
2023-05-05 3:28 ` Jason Wang
@ 2023-05-05 8:40 ` patchwork-bot+netdevbpf
2 siblings, 0 replies; 20+ messages in thread
From: patchwork-bot+netdevbpf @ 2023-05-05 8:40 UTC (permalink / raw)
To: Wenliang Wang
Cc: mst, jasowang, davem, edumazet, kuba, pabeni, zhengqi.arch,
willemdebruijn.kernel, virtualization, netdev, linux-kernel,
xuanzhuo
Hello:
This patch was applied to netdev/net.git (main)
by David S. Miller <davem@davemloft.net>:
On Thu, 4 May 2023 10:27:06 +0800 you wrote:
> For multi-queue and large ring-size use case, the following error
> occurred when free_unused_bufs:
> rcu: INFO: rcu_sched self-detected stall on CPU.
>
> Fixes: 986a4f4d452d ("virtio_net: multiqueue support")
> Signed-off-by: Wenliang Wang <wangwenliang.1995@bytedance.com>
>
> [...]
Here is the summary with links:
- [v4] virtio_net: suppress cpu stall when free_unused_bufs
https://git.kernel.org/netdev/net/c/f8bb51043945
You are awesome, thank you!
--
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html
^ permalink raw reply [flat|nested] 20+ messages in thread
* Re: [PATCH v4] virtio_net: suppress cpu stall when free_unused_bufs
2023-05-05 3:28 ` Jason Wang
@ 2023-05-06 2:04 ` Xuan Zhuo
-1 siblings, 0 replies; 20+ messages in thread
From: Xuan Zhuo @ 2023-05-06 2:04 UTC (permalink / raw)
To: Jason Wang
Cc: mst, davem, edumazet, kuba, pabeni, zhengqi.arch,
willemdebruijn.kernel, virtualization, netdev, linux-kernel,
Wenliang Wang
On Fri, 5 May 2023 11:28:25 +0800, Jason Wang <jasowang@redhat.com> wrote:
> On Thu, May 4, 2023 at 10:27 AM Wenliang Wang
> <wangwenliang.1995@bytedance.com> wrote:
> >
> > For multi-queue and large ring-size use case, the following error
> > occurred when free_unused_bufs:
> > rcu: INFO: rcu_sched self-detected stall on CPU.
> >
> > Fixes: 986a4f4d452d ("virtio_net: multiqueue support")
> > Signed-off-by: Wenliang Wang <wangwenliang.1995@bytedance.com>
> > ---
> > v2:
> > -add need_resched check.
> > -apply same logic to sq.
> > v3:
> > -use cond_resched instead.
> > v4:
> > -add fixes tag
> > ---
> > drivers/net/virtio_net.c | 2 ++
> > 1 file changed, 2 insertions(+)
> >
> > diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> > index 8d8038538fc4..a12ae26db0e2 100644
> > --- a/drivers/net/virtio_net.c
> > +++ b/drivers/net/virtio_net.c
> > @@ -3560,12 +3560,14 @@ static void free_unused_bufs(struct virtnet_info *vi)
> > struct virtqueue *vq = vi->sq[i].vq;
> > while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
> > virtnet_sq_free_unused_buf(vq, buf);
> > + cond_resched();
>
> Does this really address the case when the virtqueue is very large?
Yes, I also have this question. I think cond_resched() should be called every
time a certain number of buffers are processed.
Thanks.
>
> Thanks
>
> > }
> >
> > for (i = 0; i < vi->max_queue_pairs; i++) {
> > struct virtqueue *vq = vi->rq[i].vq;
> > while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
> > virtnet_rq_free_unused_buf(vq, buf);
> > + cond_resched();
> > }
> > }
> >
> > --
> > 2.20.1
> >
>
^ permalink raw reply [flat|nested] 20+ messages in thread
* Re: [PATCH v4] virtio_net: suppress cpu stall when free_unused_bufs
@ 2023-05-06 2:04 ` Xuan Zhuo
0 siblings, 0 replies; 20+ messages in thread
From: Xuan Zhuo @ 2023-05-06 2:04 UTC (permalink / raw)
To: Jason Wang
Cc: willemdebruijn.kernel, Wenliang Wang, mst, netdev, linux-kernel,
zhengqi.arch, virtualization, edumazet, kuba, pabeni, davem
On Fri, 5 May 2023 11:28:25 +0800, Jason Wang <jasowang@redhat.com> wrote:
> On Thu, May 4, 2023 at 10:27 AM Wenliang Wang
> <wangwenliang.1995@bytedance.com> wrote:
> >
> > For multi-queue and large ring-size use case, the following error
> > occurred when free_unused_bufs:
> > rcu: INFO: rcu_sched self-detected stall on CPU.
> >
> > Fixes: 986a4f4d452d ("virtio_net: multiqueue support")
> > Signed-off-by: Wenliang Wang <wangwenliang.1995@bytedance.com>
> > ---
> > v2:
> > -add need_resched check.
> > -apply same logic to sq.
> > v3:
> > -use cond_resched instead.
> > v4:
> > -add fixes tag
> > ---
> > drivers/net/virtio_net.c | 2 ++
> > 1 file changed, 2 insertions(+)
> >
> > diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> > index 8d8038538fc4..a12ae26db0e2 100644
> > --- a/drivers/net/virtio_net.c
> > +++ b/drivers/net/virtio_net.c
> > @@ -3560,12 +3560,14 @@ static void free_unused_bufs(struct virtnet_info *vi)
> > struct virtqueue *vq = vi->sq[i].vq;
> > while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
> > virtnet_sq_free_unused_buf(vq, buf);
> > + cond_resched();
>
> Does this really address the case when the virtqueue is very large?
Yes, I also have this question. I think cond_resched() should be called every
time a certain number of buffers are processed.
Thanks.
>
> Thanks
>
> > }
> >
> > for (i = 0; i < vi->max_queue_pairs; i++) {
> > struct virtqueue *vq = vi->rq[i].vq;
> > while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
> > virtnet_rq_free_unused_buf(vq, buf);
> > + cond_resched();
> > }
> > }
> >
> > --
> > 2.20.1
> >
>
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
^ permalink raw reply [flat|nested] 20+ messages in thread
* Re: [PATCH v4] virtio_net: suppress cpu stall when free_unused_bufs
2023-05-05 3:28 ` Jason Wang
@ 2023-05-07 13:34 ` Michael S. Tsirkin
-1 siblings, 0 replies; 20+ messages in thread
From: Michael S. Tsirkin @ 2023-05-07 13:34 UTC (permalink / raw)
To: Jason Wang
Cc: xuanzhuo, willemdebruijn.kernel, Wenliang Wang, netdev,
linux-kernel, zhengqi.arch, virtualization, edumazet, kuba,
pabeni, davem
On Fri, May 05, 2023 at 11:28:25AM +0800, Jason Wang wrote:
> On Thu, May 4, 2023 at 10:27 AM Wenliang Wang
> <wangwenliang.1995@bytedance.com> wrote:
> >
> > For multi-queue and large ring-size use case, the following error
> > occurred when free_unused_bufs:
> > rcu: INFO: rcu_sched self-detected stall on CPU.
> >
> > Fixes: 986a4f4d452d ("virtio_net: multiqueue support")
> > Signed-off-by: Wenliang Wang <wangwenliang.1995@bytedance.com>
> > ---
> > v2:
> > -add need_resched check.
> > -apply same logic to sq.
> > v3:
> > -use cond_resched instead.
> > v4:
> > -add fixes tag
> > ---
> > drivers/net/virtio_net.c | 2 ++
> > 1 file changed, 2 insertions(+)
> >
> > diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> > index 8d8038538fc4..a12ae26db0e2 100644
> > --- a/drivers/net/virtio_net.c
> > +++ b/drivers/net/virtio_net.c
> > @@ -3560,12 +3560,14 @@ static void free_unused_bufs(struct virtnet_info *vi)
> > struct virtqueue *vq = vi->sq[i].vq;
> > while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
> > virtnet_sq_free_unused_buf(vq, buf);
> > + cond_resched();
>
> Does this really address the case when the virtqueue is very large?
>
> Thanks
it does in that a very large queue is still just 64k in size.
we might however have 64k of these queues.
> > }
> >
> > for (i = 0; i < vi->max_queue_pairs; i++) {
> > struct virtqueue *vq = vi->rq[i].vq;
> > while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
> > virtnet_rq_free_unused_buf(vq, buf);
> > + cond_resched();
> > }
> > }
> >
> > --
> > 2.20.1
> >
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
^ permalink raw reply [flat|nested] 20+ messages in thread
* Re: [PATCH v4] virtio_net: suppress cpu stall when free_unused_bufs
@ 2023-05-07 13:34 ` Michael S. Tsirkin
0 siblings, 0 replies; 20+ messages in thread
From: Michael S. Tsirkin @ 2023-05-07 13:34 UTC (permalink / raw)
To: Jason Wang
Cc: Wenliang Wang, davem, edumazet, kuba, pabeni, zhengqi.arch,
willemdebruijn.kernel, virtualization, netdev, linux-kernel,
xuanzhuo
On Fri, May 05, 2023 at 11:28:25AM +0800, Jason Wang wrote:
> On Thu, May 4, 2023 at 10:27 AM Wenliang Wang
> <wangwenliang.1995@bytedance.com> wrote:
> >
> > For multi-queue and large ring-size use case, the following error
> > occurred when free_unused_bufs:
> > rcu: INFO: rcu_sched self-detected stall on CPU.
> >
> > Fixes: 986a4f4d452d ("virtio_net: multiqueue support")
> > Signed-off-by: Wenliang Wang <wangwenliang.1995@bytedance.com>
> > ---
> > v2:
> > -add need_resched check.
> > -apply same logic to sq.
> > v3:
> > -use cond_resched instead.
> > v4:
> > -add fixes tag
> > ---
> > drivers/net/virtio_net.c | 2 ++
> > 1 file changed, 2 insertions(+)
> >
> > diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> > index 8d8038538fc4..a12ae26db0e2 100644
> > --- a/drivers/net/virtio_net.c
> > +++ b/drivers/net/virtio_net.c
> > @@ -3560,12 +3560,14 @@ static void free_unused_bufs(struct virtnet_info *vi)
> > struct virtqueue *vq = vi->sq[i].vq;
> > while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
> > virtnet_sq_free_unused_buf(vq, buf);
> > + cond_resched();
>
> Does this really address the case when the virtqueue is very large?
>
> Thanks
it does in that a very large queue is still just 64k in size.
we might however have 64k of these queues.
> > }
> >
> > for (i = 0; i < vi->max_queue_pairs; i++) {
> > struct virtqueue *vq = vi->rq[i].vq;
> > while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
> > virtnet_rq_free_unused_buf(vq, buf);
> > + cond_resched();
> > }
> > }
> >
> > --
> > 2.20.1
> >
^ permalink raw reply [flat|nested] 20+ messages in thread
* Re: [PATCH v4] virtio_net: suppress cpu stall when free_unused_bufs
2023-05-07 13:34 ` Michael S. Tsirkin
@ 2023-05-08 3:12 ` Jason Wang
-1 siblings, 0 replies; 20+ messages in thread
From: Jason Wang @ 2023-05-08 3:12 UTC (permalink / raw)
To: Michael S. Tsirkin
Cc: Wenliang Wang, davem, edumazet, kuba, pabeni, zhengqi.arch,
willemdebruijn.kernel, virtualization, netdev, linux-kernel,
xuanzhuo
在 2023/5/7 21:34, Michael S. Tsirkin 写道:
> On Fri, May 05, 2023 at 11:28:25AM +0800, Jason Wang wrote:
>> On Thu, May 4, 2023 at 10:27 AM Wenliang Wang
>> <wangwenliang.1995@bytedance.com> wrote:
>>> For multi-queue and large ring-size use case, the following error
>>> occurred when free_unused_bufs:
>>> rcu: INFO: rcu_sched self-detected stall on CPU.
>>>
>>> Fixes: 986a4f4d452d ("virtio_net: multiqueue support")
>>> Signed-off-by: Wenliang Wang <wangwenliang.1995@bytedance.com>
>>> ---
>>> v2:
>>> -add need_resched check.
>>> -apply same logic to sq.
>>> v3:
>>> -use cond_resched instead.
>>> v4:
>>> -add fixes tag
>>> ---
>>> drivers/net/virtio_net.c | 2 ++
>>> 1 file changed, 2 insertions(+)
>>>
>>> diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
>>> index 8d8038538fc4..a12ae26db0e2 100644
>>> --- a/drivers/net/virtio_net.c
>>> +++ b/drivers/net/virtio_net.c
>>> @@ -3560,12 +3560,14 @@ static void free_unused_bufs(struct virtnet_info *vi)
>>> struct virtqueue *vq = vi->sq[i].vq;
>>> while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
>>> virtnet_sq_free_unused_buf(vq, buf);
>>> + cond_resched();
>> Does this really address the case when the virtqueue is very large?
>>
>> Thanks
>
> it does in that a very large queue is still just 64k in size.
> we might however have 64k of these queues.
Ok, but we have other similar loops especially the refill, I think we
may need cond_resched() there as well.
Thanks
>
>>> }
>>>
>>> for (i = 0; i < vi->max_queue_pairs; i++) {
>>> struct virtqueue *vq = vi->rq[i].vq;
>>> while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
>>> virtnet_rq_free_unused_buf(vq, buf);
>>> + cond_resched();
>>> }
>>> }
>>>
>>> --
>>> 2.20.1
>>>
^ permalink raw reply [flat|nested] 20+ messages in thread
* Re: [PATCH v4] virtio_net: suppress cpu stall when free_unused_bufs
@ 2023-05-08 3:12 ` Jason Wang
0 siblings, 0 replies; 20+ messages in thread
From: Jason Wang @ 2023-05-08 3:12 UTC (permalink / raw)
To: Michael S. Tsirkin
Cc: xuanzhuo, willemdebruijn.kernel, Wenliang Wang, netdev,
linux-kernel, zhengqi.arch, virtualization, edumazet, kuba,
pabeni, davem
在 2023/5/7 21:34, Michael S. Tsirkin 写道:
> On Fri, May 05, 2023 at 11:28:25AM +0800, Jason Wang wrote:
>> On Thu, May 4, 2023 at 10:27 AM Wenliang Wang
>> <wangwenliang.1995@bytedance.com> wrote:
>>> For multi-queue and large ring-size use case, the following error
>>> occurred when free_unused_bufs:
>>> rcu: INFO: rcu_sched self-detected stall on CPU.
>>>
>>> Fixes: 986a4f4d452d ("virtio_net: multiqueue support")
>>> Signed-off-by: Wenliang Wang <wangwenliang.1995@bytedance.com>
>>> ---
>>> v2:
>>> -add need_resched check.
>>> -apply same logic to sq.
>>> v3:
>>> -use cond_resched instead.
>>> v4:
>>> -add fixes tag
>>> ---
>>> drivers/net/virtio_net.c | 2 ++
>>> 1 file changed, 2 insertions(+)
>>>
>>> diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
>>> index 8d8038538fc4..a12ae26db0e2 100644
>>> --- a/drivers/net/virtio_net.c
>>> +++ b/drivers/net/virtio_net.c
>>> @@ -3560,12 +3560,14 @@ static void free_unused_bufs(struct virtnet_info *vi)
>>> struct virtqueue *vq = vi->sq[i].vq;
>>> while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
>>> virtnet_sq_free_unused_buf(vq, buf);
>>> + cond_resched();
>> Does this really address the case when the virtqueue is very large?
>>
>> Thanks
>
> it does in that a very large queue is still just 64k in size.
> we might however have 64k of these queues.
Ok, but we have other similar loops especially the refill, I think we
may need cond_resched() there as well.
Thanks
>
>>> }
>>>
>>> for (i = 0; i < vi->max_queue_pairs; i++) {
>>> struct virtqueue *vq = vi->rq[i].vq;
>>> while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
>>> virtnet_rq_free_unused_buf(vq, buf);
>>> + cond_resched();
>>> }
>>> }
>>>
>>> --
>>> 2.20.1
>>>
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
^ permalink raw reply [flat|nested] 20+ messages in thread
* Re: [PATCH v4] virtio_net: suppress cpu stall when free_unused_bufs
2023-05-08 3:12 ` Jason Wang
@ 2023-05-08 6:07 ` Michael S. Tsirkin
-1 siblings, 0 replies; 20+ messages in thread
From: Michael S. Tsirkin @ 2023-05-08 6:07 UTC (permalink / raw)
To: Jason Wang
Cc: Wenliang Wang, davem, edumazet, kuba, pabeni, zhengqi.arch,
willemdebruijn.kernel, virtualization, netdev, linux-kernel,
xuanzhuo
On Mon, May 08, 2023 at 11:12:03AM +0800, Jason Wang wrote:
>
> 在 2023/5/7 21:34, Michael S. Tsirkin 写道:
> > On Fri, May 05, 2023 at 11:28:25AM +0800, Jason Wang wrote:
> > > On Thu, May 4, 2023 at 10:27 AM Wenliang Wang
> > > <wangwenliang.1995@bytedance.com> wrote:
> > > > For multi-queue and large ring-size use case, the following error
> > > > occurred when free_unused_bufs:
> > > > rcu: INFO: rcu_sched self-detected stall on CPU.
> > > >
> > > > Fixes: 986a4f4d452d ("virtio_net: multiqueue support")
> > > > Signed-off-by: Wenliang Wang <wangwenliang.1995@bytedance.com>
> > > > ---
> > > > v2:
> > > > -add need_resched check.
> > > > -apply same logic to sq.
> > > > v3:
> > > > -use cond_resched instead.
> > > > v4:
> > > > -add fixes tag
> > > > ---
> > > > drivers/net/virtio_net.c | 2 ++
> > > > 1 file changed, 2 insertions(+)
> > > >
> > > > diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> > > > index 8d8038538fc4..a12ae26db0e2 100644
> > > > --- a/drivers/net/virtio_net.c
> > > > +++ b/drivers/net/virtio_net.c
> > > > @@ -3560,12 +3560,14 @@ static void free_unused_bufs(struct virtnet_info *vi)
> > > > struct virtqueue *vq = vi->sq[i].vq;
> > > > while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
> > > > virtnet_sq_free_unused_buf(vq, buf);
> > > > + cond_resched();
> > > Does this really address the case when the virtqueue is very large?
> > >
> > > Thanks
> >
> > it does in that a very large queue is still just 64k in size.
> > we might however have 64k of these queues.
>
>
> Ok, but we have other similar loops especially the refill, I think we may
> need cond_resched() there as well.
>
> Thanks
>
Refill is already per vq isn't it?
> >
> > > > }
> > > >
> > > > for (i = 0; i < vi->max_queue_pairs; i++) {
> > > > struct virtqueue *vq = vi->rq[i].vq;
> > > > while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
> > > > virtnet_rq_free_unused_buf(vq, buf);
> > > > + cond_resched();
> > > > }
> > > > }
> > > >
> > > > --
> > > > 2.20.1
> > > >
^ permalink raw reply [flat|nested] 20+ messages in thread
* Re: [PATCH v4] virtio_net: suppress cpu stall when free_unused_bufs
@ 2023-05-08 6:07 ` Michael S. Tsirkin
0 siblings, 0 replies; 20+ messages in thread
From: Michael S. Tsirkin @ 2023-05-08 6:07 UTC (permalink / raw)
To: Jason Wang
Cc: xuanzhuo, willemdebruijn.kernel, Wenliang Wang, netdev,
linux-kernel, zhengqi.arch, virtualization, edumazet, kuba,
pabeni, davem
On Mon, May 08, 2023 at 11:12:03AM +0800, Jason Wang wrote:
>
> 在 2023/5/7 21:34, Michael S. Tsirkin 写道:
> > On Fri, May 05, 2023 at 11:28:25AM +0800, Jason Wang wrote:
> > > On Thu, May 4, 2023 at 10:27 AM Wenliang Wang
> > > <wangwenliang.1995@bytedance.com> wrote:
> > > > For multi-queue and large ring-size use case, the following error
> > > > occurred when free_unused_bufs:
> > > > rcu: INFO: rcu_sched self-detected stall on CPU.
> > > >
> > > > Fixes: 986a4f4d452d ("virtio_net: multiqueue support")
> > > > Signed-off-by: Wenliang Wang <wangwenliang.1995@bytedance.com>
> > > > ---
> > > > v2:
> > > > -add need_resched check.
> > > > -apply same logic to sq.
> > > > v3:
> > > > -use cond_resched instead.
> > > > v4:
> > > > -add fixes tag
> > > > ---
> > > > drivers/net/virtio_net.c | 2 ++
> > > > 1 file changed, 2 insertions(+)
> > > >
> > > > diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> > > > index 8d8038538fc4..a12ae26db0e2 100644
> > > > --- a/drivers/net/virtio_net.c
> > > > +++ b/drivers/net/virtio_net.c
> > > > @@ -3560,12 +3560,14 @@ static void free_unused_bufs(struct virtnet_info *vi)
> > > > struct virtqueue *vq = vi->sq[i].vq;
> > > > while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
> > > > virtnet_sq_free_unused_buf(vq, buf);
> > > > + cond_resched();
> > > Does this really address the case when the virtqueue is very large?
> > >
> > > Thanks
> >
> > it does in that a very large queue is still just 64k in size.
> > we might however have 64k of these queues.
>
>
> Ok, but we have other similar loops especially the refill, I think we may
> need cond_resched() there as well.
>
> Thanks
>
Refill is already per vq isn't it?
> >
> > > > }
> > > >
> > > > for (i = 0; i < vi->max_queue_pairs; i++) {
> > > > struct virtqueue *vq = vi->rq[i].vq;
> > > > while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
> > > > virtnet_rq_free_unused_buf(vq, buf);
> > > > + cond_resched();
> > > > }
> > > > }
> > > >
> > > > --
> > > > 2.20.1
> > > >
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
^ permalink raw reply [flat|nested] 20+ messages in thread
* Re: [PATCH v4] virtio_net: suppress cpu stall when free_unused_bufs
2023-05-08 6:07 ` Michael S. Tsirkin
@ 2023-05-08 6:13 ` Jason Wang
-1 siblings, 0 replies; 20+ messages in thread
From: Jason Wang @ 2023-05-08 6:13 UTC (permalink / raw)
To: Michael S. Tsirkin
Cc: Wenliang Wang, davem, edumazet, kuba, pabeni, zhengqi.arch,
willemdebruijn.kernel, virtualization, netdev, linux-kernel,
xuanzhuo
On Mon, May 8, 2023 at 2:08 PM Michael S. Tsirkin <mst@redhat.com> wrote:
>
> On Mon, May 08, 2023 at 11:12:03AM +0800, Jason Wang wrote:
> >
> > 在 2023/5/7 21:34, Michael S. Tsirkin 写道:
> > > On Fri, May 05, 2023 at 11:28:25AM +0800, Jason Wang wrote:
> > > > On Thu, May 4, 2023 at 10:27 AM Wenliang Wang
> > > > <wangwenliang.1995@bytedance.com> wrote:
> > > > > For multi-queue and large ring-size use case, the following error
> > > > > occurred when free_unused_bufs:
> > > > > rcu: INFO: rcu_sched self-detected stall on CPU.
> > > > >
> > > > > Fixes: 986a4f4d452d ("virtio_net: multiqueue support")
> > > > > Signed-off-by: Wenliang Wang <wangwenliang.1995@bytedance.com>
> > > > > ---
> > > > > v2:
> > > > > -add need_resched check.
> > > > > -apply same logic to sq.
> > > > > v3:
> > > > > -use cond_resched instead.
> > > > > v4:
> > > > > -add fixes tag
> > > > > ---
> > > > > drivers/net/virtio_net.c | 2 ++
> > > > > 1 file changed, 2 insertions(+)
> > > > >
> > > > > diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> > > > > index 8d8038538fc4..a12ae26db0e2 100644
> > > > > --- a/drivers/net/virtio_net.c
> > > > > +++ b/drivers/net/virtio_net.c
> > > > > @@ -3560,12 +3560,14 @@ static void free_unused_bufs(struct virtnet_info *vi)
> > > > > struct virtqueue *vq = vi->sq[i].vq;
> > > > > while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
> > > > > virtnet_sq_free_unused_buf(vq, buf);
> > > > > + cond_resched();
> > > > Does this really address the case when the virtqueue is very large?
> > > >
> > > > Thanks
> > >
> > > it does in that a very large queue is still just 64k in size.
> > > we might however have 64k of these queues.
> >
> >
> > Ok, but we have other similar loops especially the refill, I think we may
> > need cond_resched() there as well.
> >
> > Thanks
> >
>
> Refill is already per vq isn't it?
Not for the refill_work().
Thanks
>
>
> > >
> > > > > }
> > > > >
> > > > > for (i = 0; i < vi->max_queue_pairs; i++) {
> > > > > struct virtqueue *vq = vi->rq[i].vq;
> > > > > while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
> > > > > virtnet_rq_free_unused_buf(vq, buf);
> > > > > + cond_resched();
> > > > > }
> > > > > }
> > > > >
> > > > > --
> > > > > 2.20.1
> > > > >
>
^ permalink raw reply [flat|nested] 20+ messages in thread
* Re: [PATCH v4] virtio_net: suppress cpu stall when free_unused_bufs
@ 2023-05-08 6:13 ` Jason Wang
0 siblings, 0 replies; 20+ messages in thread
From: Jason Wang @ 2023-05-08 6:13 UTC (permalink / raw)
To: Michael S. Tsirkin
Cc: xuanzhuo, willemdebruijn.kernel, Wenliang Wang, netdev,
linux-kernel, zhengqi.arch, virtualization, edumazet, kuba,
pabeni, davem
On Mon, May 8, 2023 at 2:08 PM Michael S. Tsirkin <mst@redhat.com> wrote:
>
> On Mon, May 08, 2023 at 11:12:03AM +0800, Jason Wang wrote:
> >
> > 在 2023/5/7 21:34, Michael S. Tsirkin 写道:
> > > On Fri, May 05, 2023 at 11:28:25AM +0800, Jason Wang wrote:
> > > > On Thu, May 4, 2023 at 10:27 AM Wenliang Wang
> > > > <wangwenliang.1995@bytedance.com> wrote:
> > > > > For multi-queue and large ring-size use case, the following error
> > > > > occurred when free_unused_bufs:
> > > > > rcu: INFO: rcu_sched self-detected stall on CPU.
> > > > >
> > > > > Fixes: 986a4f4d452d ("virtio_net: multiqueue support")
> > > > > Signed-off-by: Wenliang Wang <wangwenliang.1995@bytedance.com>
> > > > > ---
> > > > > v2:
> > > > > -add need_resched check.
> > > > > -apply same logic to sq.
> > > > > v3:
> > > > > -use cond_resched instead.
> > > > > v4:
> > > > > -add fixes tag
> > > > > ---
> > > > > drivers/net/virtio_net.c | 2 ++
> > > > > 1 file changed, 2 insertions(+)
> > > > >
> > > > > diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> > > > > index 8d8038538fc4..a12ae26db0e2 100644
> > > > > --- a/drivers/net/virtio_net.c
> > > > > +++ b/drivers/net/virtio_net.c
> > > > > @@ -3560,12 +3560,14 @@ static void free_unused_bufs(struct virtnet_info *vi)
> > > > > struct virtqueue *vq = vi->sq[i].vq;
> > > > > while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
> > > > > virtnet_sq_free_unused_buf(vq, buf);
> > > > > + cond_resched();
> > > > Does this really address the case when the virtqueue is very large?
> > > >
> > > > Thanks
> > >
> > > it does in that a very large queue is still just 64k in size.
> > > we might however have 64k of these queues.
> >
> >
> > Ok, but we have other similar loops especially the refill, I think we may
> > need cond_resched() there as well.
> >
> > Thanks
> >
>
> Refill is already per vq isn't it?
Not for the refill_work().
Thanks
>
>
> > >
> > > > > }
> > > > >
> > > > > for (i = 0; i < vi->max_queue_pairs; i++) {
> > > > > struct virtqueue *vq = vi->rq[i].vq;
> > > > > while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
> > > > > virtnet_rq_free_unused_buf(vq, buf);
> > > > > + cond_resched();
> > > > > }
> > > > > }
> > > > >
> > > > > --
> > > > > 2.20.1
> > > > >
>
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
^ permalink raw reply [flat|nested] 20+ messages in thread
* Re: [PATCH v4] virtio_net: suppress cpu stall when free_unused_bufs
2023-05-08 6:13 ` Jason Wang
@ 2023-05-08 6:47 ` Michael S. Tsirkin
-1 siblings, 0 replies; 20+ messages in thread
From: Michael S. Tsirkin @ 2023-05-08 6:47 UTC (permalink / raw)
To: Jason Wang
Cc: xuanzhuo, willemdebruijn.kernel, Wenliang Wang, netdev,
linux-kernel, zhengqi.arch, virtualization, edumazet, kuba,
pabeni, davem
On Mon, May 08, 2023 at 02:13:42PM +0800, Jason Wang wrote:
> On Mon, May 8, 2023 at 2:08 PM Michael S. Tsirkin <mst@redhat.com> wrote:
> >
> > On Mon, May 08, 2023 at 11:12:03AM +0800, Jason Wang wrote:
> > >
> > > 在 2023/5/7 21:34, Michael S. Tsirkin 写道:
> > > > On Fri, May 05, 2023 at 11:28:25AM +0800, Jason Wang wrote:
> > > > > On Thu, May 4, 2023 at 10:27 AM Wenliang Wang
> > > > > <wangwenliang.1995@bytedance.com> wrote:
> > > > > > For multi-queue and large ring-size use case, the following error
> > > > > > occurred when free_unused_bufs:
> > > > > > rcu: INFO: rcu_sched self-detected stall on CPU.
> > > > > >
> > > > > > Fixes: 986a4f4d452d ("virtio_net: multiqueue support")
> > > > > > Signed-off-by: Wenliang Wang <wangwenliang.1995@bytedance.com>
> > > > > > ---
> > > > > > v2:
> > > > > > -add need_resched check.
> > > > > > -apply same logic to sq.
> > > > > > v3:
> > > > > > -use cond_resched instead.
> > > > > > v4:
> > > > > > -add fixes tag
> > > > > > ---
> > > > > > drivers/net/virtio_net.c | 2 ++
> > > > > > 1 file changed, 2 insertions(+)
> > > > > >
> > > > > > diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> > > > > > index 8d8038538fc4..a12ae26db0e2 100644
> > > > > > --- a/drivers/net/virtio_net.c
> > > > > > +++ b/drivers/net/virtio_net.c
> > > > > > @@ -3560,12 +3560,14 @@ static void free_unused_bufs(struct virtnet_info *vi)
> > > > > > struct virtqueue *vq = vi->sq[i].vq;
> > > > > > while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
> > > > > > virtnet_sq_free_unused_buf(vq, buf);
> > > > > > + cond_resched();
> > > > > Does this really address the case when the virtqueue is very large?
> > > > >
> > > > > Thanks
> > > >
> > > > it does in that a very large queue is still just 64k in size.
> > > > we might however have 64k of these queues.
> > >
> > >
> > > Ok, but we have other similar loops especially the refill, I think we may
> > > need cond_resched() there as well.
> > >
> > > Thanks
> > >
> >
> > Refill is already per vq isn't it?
>
> Not for the refill_work().
>
> Thanks
Good point, refill_work probably needs cond_resched, too.
And I guess virtnet_open?
> >
> >
> > > >
> > > > > > }
> > > > > >
> > > > > > for (i = 0; i < vi->max_queue_pairs; i++) {
> > > > > > struct virtqueue *vq = vi->rq[i].vq;
> > > > > > while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
> > > > > > virtnet_rq_free_unused_buf(vq, buf);
> > > > > > + cond_resched();
> > > > > > }
> > > > > > }
> > > > > >
> > > > > > --
> > > > > > 2.20.1
> > > > > >
> >
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
^ permalink raw reply [flat|nested] 20+ messages in thread
* Re: [PATCH v4] virtio_net: suppress cpu stall when free_unused_bufs
@ 2023-05-08 6:47 ` Michael S. Tsirkin
0 siblings, 0 replies; 20+ messages in thread
From: Michael S. Tsirkin @ 2023-05-08 6:47 UTC (permalink / raw)
To: Jason Wang
Cc: Wenliang Wang, davem, edumazet, kuba, pabeni, zhengqi.arch,
willemdebruijn.kernel, virtualization, netdev, linux-kernel,
xuanzhuo
On Mon, May 08, 2023 at 02:13:42PM +0800, Jason Wang wrote:
> On Mon, May 8, 2023 at 2:08 PM Michael S. Tsirkin <mst@redhat.com> wrote:
> >
> > On Mon, May 08, 2023 at 11:12:03AM +0800, Jason Wang wrote:
> > >
> > > 在 2023/5/7 21:34, Michael S. Tsirkin 写道:
> > > > On Fri, May 05, 2023 at 11:28:25AM +0800, Jason Wang wrote:
> > > > > On Thu, May 4, 2023 at 10:27 AM Wenliang Wang
> > > > > <wangwenliang.1995@bytedance.com> wrote:
> > > > > > For multi-queue and large ring-size use case, the following error
> > > > > > occurred when free_unused_bufs:
> > > > > > rcu: INFO: rcu_sched self-detected stall on CPU.
> > > > > >
> > > > > > Fixes: 986a4f4d452d ("virtio_net: multiqueue support")
> > > > > > Signed-off-by: Wenliang Wang <wangwenliang.1995@bytedance.com>
> > > > > > ---
> > > > > > v2:
> > > > > > -add need_resched check.
> > > > > > -apply same logic to sq.
> > > > > > v3:
> > > > > > -use cond_resched instead.
> > > > > > v4:
> > > > > > -add fixes tag
> > > > > > ---
> > > > > > drivers/net/virtio_net.c | 2 ++
> > > > > > 1 file changed, 2 insertions(+)
> > > > > >
> > > > > > diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> > > > > > index 8d8038538fc4..a12ae26db0e2 100644
> > > > > > --- a/drivers/net/virtio_net.c
> > > > > > +++ b/drivers/net/virtio_net.c
> > > > > > @@ -3560,12 +3560,14 @@ static void free_unused_bufs(struct virtnet_info *vi)
> > > > > > struct virtqueue *vq = vi->sq[i].vq;
> > > > > > while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
> > > > > > virtnet_sq_free_unused_buf(vq, buf);
> > > > > > + cond_resched();
> > > > > Does this really address the case when the virtqueue is very large?
> > > > >
> > > > > Thanks
> > > >
> > > > it does in that a very large queue is still just 64k in size.
> > > > we might however have 64k of these queues.
> > >
> > >
> > > Ok, but we have other similar loops especially the refill, I think we may
> > > need cond_resched() there as well.
> > >
> > > Thanks
> > >
> >
> > Refill is already per vq isn't it?
>
> Not for the refill_work().
>
> Thanks
Good point, refill_work probably needs cond_resched, too.
And I guess virtnet_open?
> >
> >
> > > >
> > > > > > }
> > > > > >
> > > > > > for (i = 0; i < vi->max_queue_pairs; i++) {
> > > > > > struct virtqueue *vq = vi->rq[i].vq;
> > > > > > while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
> > > > > > virtnet_rq_free_unused_buf(vq, buf);
> > > > > > + cond_resched();
> > > > > > }
> > > > > > }
> > > > > >
> > > > > > --
> > > > > > 2.20.1
> > > > > >
> >
^ permalink raw reply [flat|nested] 20+ messages in thread
* Re: [PATCH v4] virtio_net: suppress cpu stall when free_unused_bufs
2023-05-08 6:47 ` Michael S. Tsirkin
@ 2023-05-09 3:14 ` Jason Wang
-1 siblings, 0 replies; 20+ messages in thread
From: Jason Wang @ 2023-05-09 3:14 UTC (permalink / raw)
To: Michael S. Tsirkin
Cc: Wenliang Wang, davem, edumazet, kuba, pabeni, zhengqi.arch,
willemdebruijn.kernel, virtualization, netdev, linux-kernel,
xuanzhuo
On Mon, May 8, 2023 at 2:47 PM Michael S. Tsirkin <mst@redhat.com> wrote:
>
> On Mon, May 08, 2023 at 02:13:42PM +0800, Jason Wang wrote:
> > On Mon, May 8, 2023 at 2:08 PM Michael S. Tsirkin <mst@redhat.com> wrote:
> > >
> > > On Mon, May 08, 2023 at 11:12:03AM +0800, Jason Wang wrote:
> > > >
> > > > 在 2023/5/7 21:34, Michael S. Tsirkin 写道:
> > > > > On Fri, May 05, 2023 at 11:28:25AM +0800, Jason Wang wrote:
> > > > > > On Thu, May 4, 2023 at 10:27 AM Wenliang Wang
> > > > > > <wangwenliang.1995@bytedance.com> wrote:
> > > > > > > For multi-queue and large ring-size use case, the following error
> > > > > > > occurred when free_unused_bufs:
> > > > > > > rcu: INFO: rcu_sched self-detected stall on CPU.
> > > > > > >
> > > > > > > Fixes: 986a4f4d452d ("virtio_net: multiqueue support")
> > > > > > > Signed-off-by: Wenliang Wang <wangwenliang.1995@bytedance.com>
> > > > > > > ---
> > > > > > > v2:
> > > > > > > -add need_resched check.
> > > > > > > -apply same logic to sq.
> > > > > > > v3:
> > > > > > > -use cond_resched instead.
> > > > > > > v4:
> > > > > > > -add fixes tag
> > > > > > > ---
> > > > > > > drivers/net/virtio_net.c | 2 ++
> > > > > > > 1 file changed, 2 insertions(+)
> > > > > > >
> > > > > > > diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> > > > > > > index 8d8038538fc4..a12ae26db0e2 100644
> > > > > > > --- a/drivers/net/virtio_net.c
> > > > > > > +++ b/drivers/net/virtio_net.c
> > > > > > > @@ -3560,12 +3560,14 @@ static void free_unused_bufs(struct virtnet_info *vi)
> > > > > > > struct virtqueue *vq = vi->sq[i].vq;
> > > > > > > while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
> > > > > > > virtnet_sq_free_unused_buf(vq, buf);
> > > > > > > + cond_resched();
> > > > > > Does this really address the case when the virtqueue is very large?
> > > > > >
> > > > > > Thanks
> > > > >
> > > > > it does in that a very large queue is still just 64k in size.
> > > > > we might however have 64k of these queues.
> > > >
> > > >
> > > > Ok, but we have other similar loops especially the refill, I think we may
> > > > need cond_resched() there as well.
> > > >
> > > > Thanks
> > > >
> > >
> > > Refill is already per vq isn't it?
> >
> > Not for the refill_work().
> >
> > Thanks
>
> Good point, refill_work probably needs cond_resched, too.
> And I guess virtnet_open?
Yes, let me draft a patch.
Thanks
>
>
> > >
> > >
> > > > >
> > > > > > > }
> > > > > > >
> > > > > > > for (i = 0; i < vi->max_queue_pairs; i++) {
> > > > > > > struct virtqueue *vq = vi->rq[i].vq;
> > > > > > > while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
> > > > > > > virtnet_rq_free_unused_buf(vq, buf);
> > > > > > > + cond_resched();
> > > > > > > }
> > > > > > > }
> > > > > > >
> > > > > > > --
> > > > > > > 2.20.1
> > > > > > >
> > >
>
^ permalink raw reply [flat|nested] 20+ messages in thread
* Re: [PATCH v4] virtio_net: suppress cpu stall when free_unused_bufs
@ 2023-05-09 3:14 ` Jason Wang
0 siblings, 0 replies; 20+ messages in thread
From: Jason Wang @ 2023-05-09 3:14 UTC (permalink / raw)
To: Michael S. Tsirkin
Cc: xuanzhuo, willemdebruijn.kernel, Wenliang Wang, netdev,
linux-kernel, zhengqi.arch, virtualization, edumazet, kuba,
pabeni, davem
On Mon, May 8, 2023 at 2:47 PM Michael S. Tsirkin <mst@redhat.com> wrote:
>
> On Mon, May 08, 2023 at 02:13:42PM +0800, Jason Wang wrote:
> > On Mon, May 8, 2023 at 2:08 PM Michael S. Tsirkin <mst@redhat.com> wrote:
> > >
> > > On Mon, May 08, 2023 at 11:12:03AM +0800, Jason Wang wrote:
> > > >
> > > > 在 2023/5/7 21:34, Michael S. Tsirkin 写道:
> > > > > On Fri, May 05, 2023 at 11:28:25AM +0800, Jason Wang wrote:
> > > > > > On Thu, May 4, 2023 at 10:27 AM Wenliang Wang
> > > > > > <wangwenliang.1995@bytedance.com> wrote:
> > > > > > > For multi-queue and large ring-size use case, the following error
> > > > > > > occurred when free_unused_bufs:
> > > > > > > rcu: INFO: rcu_sched self-detected stall on CPU.
> > > > > > >
> > > > > > > Fixes: 986a4f4d452d ("virtio_net: multiqueue support")
> > > > > > > Signed-off-by: Wenliang Wang <wangwenliang.1995@bytedance.com>
> > > > > > > ---
> > > > > > > v2:
> > > > > > > -add need_resched check.
> > > > > > > -apply same logic to sq.
> > > > > > > v3:
> > > > > > > -use cond_resched instead.
> > > > > > > v4:
> > > > > > > -add fixes tag
> > > > > > > ---
> > > > > > > drivers/net/virtio_net.c | 2 ++
> > > > > > > 1 file changed, 2 insertions(+)
> > > > > > >
> > > > > > > diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> > > > > > > index 8d8038538fc4..a12ae26db0e2 100644
> > > > > > > --- a/drivers/net/virtio_net.c
> > > > > > > +++ b/drivers/net/virtio_net.c
> > > > > > > @@ -3560,12 +3560,14 @@ static void free_unused_bufs(struct virtnet_info *vi)
> > > > > > > struct virtqueue *vq = vi->sq[i].vq;
> > > > > > > while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
> > > > > > > virtnet_sq_free_unused_buf(vq, buf);
> > > > > > > + cond_resched();
> > > > > > Does this really address the case when the virtqueue is very large?
> > > > > >
> > > > > > Thanks
> > > > >
> > > > > it does in that a very large queue is still just 64k in size.
> > > > > we might however have 64k of these queues.
> > > >
> > > >
> > > > Ok, but we have other similar loops especially the refill, I think we may
> > > > need cond_resched() there as well.
> > > >
> > > > Thanks
> > > >
> > >
> > > Refill is already per vq isn't it?
> >
> > Not for the refill_work().
> >
> > Thanks
>
> Good point, refill_work probably needs cond_resched, too.
> And I guess virtnet_open?
Yes, let me draft a patch.
Thanks
>
>
> > >
> > >
> > > > >
> > > > > > > }
> > > > > > >
> > > > > > > for (i = 0; i < vi->max_queue_pairs; i++) {
> > > > > > > struct virtqueue *vq = vi->rq[i].vq;
> > > > > > > while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
> > > > > > > virtnet_rq_free_unused_buf(vq, buf);
> > > > > > > + cond_resched();
> > > > > > > }
> > > > > > > }
> > > > > > >
> > > > > > > --
> > > > > > > 2.20.1
> > > > > > >
> > >
>
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
^ permalink raw reply [flat|nested] 20+ messages in thread
end of thread, other threads:[~2023-05-09 3:15 UTC | newest]
Thread overview: 20+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2023-05-04 2:27 [PATCH v4] virtio_net: suppress cpu stall when free_unused_bufs Wenliang Wang
2023-05-04 7:06 ` Michael S. Tsirkin
2023-05-04 7:06 ` Michael S. Tsirkin
2023-05-05 3:28 ` Jason Wang
2023-05-05 3:28 ` Jason Wang
2023-05-06 2:04 ` Xuan Zhuo
2023-05-06 2:04 ` Xuan Zhuo
2023-05-07 13:34 ` Michael S. Tsirkin
2023-05-07 13:34 ` Michael S. Tsirkin
2023-05-08 3:12 ` Jason Wang
2023-05-08 3:12 ` Jason Wang
2023-05-08 6:07 ` Michael S. Tsirkin
2023-05-08 6:07 ` Michael S. Tsirkin
2023-05-08 6:13 ` Jason Wang
2023-05-08 6:13 ` Jason Wang
2023-05-08 6:47 ` Michael S. Tsirkin
2023-05-08 6:47 ` Michael S. Tsirkin
2023-05-09 3:14 ` Jason Wang
2023-05-09 3:14 ` Jason Wang
2023-05-05 8:40 ` patchwork-bot+netdevbpf
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.