2020-10-01 21:05:15

by Si-Wei Liu

Subject: [PATCH] vdpa/mlx5: should keep avail_index despite device status

A VM with mlx5 vDPA has below warnings while being reset:

vhost VQ 0 ring restore failed: -1: Resource temporarily unavailable (11)
vhost VQ 1 ring restore failed: -1: Resource temporarily unavailable (11)

We should allow userspace emulating the virtio device be
able to get to vq's avail_index, regardless of vDPA device
status. Save the index that was last seen when virtq was
stopped, so that userspace doesn't complain.

Signed-off-by: Si-Wei Liu <[email protected]>
---
drivers/vdpa/mlx5/net/mlx5_vnet.c | 20 ++++++++++++++------
1 file changed, 14 insertions(+), 6 deletions(-)

diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index 70676a6..74264e59 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -1133,15 +1133,17 @@ static void suspend_vq(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *m
if (!mvq->initialized)
return;

- if (query_virtqueue(ndev, mvq, &attr)) {
- mlx5_vdpa_warn(&ndev->mvdev, "failed to query virtqueue\n");
- return;
- }
if (mvq->fw_state != MLX5_VIRTIO_NET_Q_OBJECT_STATE_RDY)
return;

if (modify_virtqueue(ndev, mvq, MLX5_VIRTIO_NET_Q_OBJECT_STATE_SUSPEND))
mlx5_vdpa_warn(&ndev->mvdev, "modify to suspend failed\n");
+
+ if (query_virtqueue(ndev, mvq, &attr)) {
+ mlx5_vdpa_warn(&ndev->mvdev, "failed to query virtqueue\n");
+ return;
+ }
+ mvq->avail_idx = attr.available_index;
}

static void suspend_vqs(struct mlx5_vdpa_net *ndev)
@@ -1411,8 +1413,14 @@ static int mlx5_vdpa_get_vq_state(struct vdpa_device *vdev, u16 idx, struct vdpa
struct mlx5_virtq_attr attr;
int err;

- if (!mvq->initialized)
- return -EAGAIN;
+ /* If the virtq object was destroyed, use the value saved at
+ * the last minute of suspend_vq. This caters for userspace
+ * that cares about emulating the index after vq is stopped.
+ */
+ if (!mvq->initialized) {
+ state->avail_index = mvq->avail_idx;
+ return 0;
+ }

err = query_virtqueue(ndev, mvq, &attr);
if (err) {
--
1.8.3.1

2020-10-02 20:18:40

by Si-Wei Liu

Subject: Re: [PATCH] vdpa/mlx5: should keep avail_index despite device status

+ Eli.

On Thu, Oct 1, 2020 at 2:02 PM Si-Wei Liu <[email protected]> wrote:
>
> A VM with mlx5 vDPA has below warnings while being reset:
>
> vhost VQ 0 ring restore failed: -1: Resource temporarily unavailable (11)
> vhost VQ 1 ring restore failed: -1: Resource temporarily unavailable (11)
>
> We should allow userspace emulating the virtio device be
> able to get to vq's avail_index, regardless of vDPA device
> status. Save the index that was last seen when virtq was
> stopped, so that userspace doesn't complain.
>
> Signed-off-by: Si-Wei Liu <[email protected]>
> ---
> drivers/vdpa/mlx5/net/mlx5_vnet.c | 20 ++++++++++++++------
> 1 file changed, 14 insertions(+), 6 deletions(-)
>
> diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
> index 70676a6..74264e59 100644
> --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
> +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
> @@ -1133,15 +1133,17 @@ static void suspend_vq(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *m
> if (!mvq->initialized)
> return;
>
> - if (query_virtqueue(ndev, mvq, &attr)) {
> - mlx5_vdpa_warn(&ndev->mvdev, "failed to query virtqueue\n");
> - return;
> - }
> if (mvq->fw_state != MLX5_VIRTIO_NET_Q_OBJECT_STATE_RDY)
> return;
>
> if (modify_virtqueue(ndev, mvq, MLX5_VIRTIO_NET_Q_OBJECT_STATE_SUSPEND))
> mlx5_vdpa_warn(&ndev->mvdev, "modify to suspend failed\n");
> +
> + if (query_virtqueue(ndev, mvq, &attr)) {
> + mlx5_vdpa_warn(&ndev->mvdev, "failed to query virtqueue\n");
> + return;
> + }
> + mvq->avail_idx = attr.available_index;
> }
>
> static void suspend_vqs(struct mlx5_vdpa_net *ndev)
> @@ -1411,8 +1413,14 @@ static int mlx5_vdpa_get_vq_state(struct vdpa_device *vdev, u16 idx, struct vdpa
> struct mlx5_virtq_attr attr;
> int err;
>
> - if (!mvq->initialized)
> - return -EAGAIN;
> + /* If the virtq object was destroyed, use the value saved at
> + * the last minute of suspend_vq. This caters for userspace
> + * that cares about emulating the index after vq is stopped.
> + */
> + if (!mvq->initialized) {
> + state->avail_index = mvq->avail_idx;
> + return 0;
> + }
>
> err = query_virtqueue(ndev, mvq, &attr);
> if (err) {
> --
> 1.8.3.1
>

2020-10-06 06:25:16

by Michael S. Tsirkin

Subject: Re: [PATCH] vdpa/mlx5: should keep avail_index despite device status

On Fri, Oct 02, 2020 at 01:17:00PM -0700, Si-Wei Liu wrote:
> + Eli.
>
> On Thu, Oct 1, 2020 at 2:02 PM Si-Wei Liu <[email protected]> wrote:
> >
> > A VM with mlx5 vDPA has below warnings while being reset:
> >
> > vhost VQ 0 ring restore failed: -1: Resource temporarily unavailable (11)
> > vhost VQ 1 ring restore failed: -1: Resource temporarily unavailable (11)
> >
> > We should allow userspace emulating the virtio device be
> > able to get to vq's avail_index, regardless of vDPA device
> > status. Save the index that was last seen when virtq was
> > stopped, so that userspace doesn't complain.
> >
> > Signed-off-by: Si-Wei Liu <[email protected]>

Eli can you review this pls? I need to send a pull request to Linux by
tomorrow - do we want to include this?

> > ---
> > drivers/vdpa/mlx5/net/mlx5_vnet.c | 20 ++++++++++++++------
> > 1 file changed, 14 insertions(+), 6 deletions(-)
> >
> > diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
> > index 70676a6..74264e59 100644
> > --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
> > +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
> > @@ -1133,15 +1133,17 @@ static void suspend_vq(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *m
> > if (!mvq->initialized)
> > return;
> >
> > - if (query_virtqueue(ndev, mvq, &attr)) {
> > - mlx5_vdpa_warn(&ndev->mvdev, "failed to query virtqueue\n");
> > - return;
> > - }
> > if (mvq->fw_state != MLX5_VIRTIO_NET_Q_OBJECT_STATE_RDY)
> > return;
> >
> > if (modify_virtqueue(ndev, mvq, MLX5_VIRTIO_NET_Q_OBJECT_STATE_SUSPEND))
> > mlx5_vdpa_warn(&ndev->mvdev, "modify to suspend failed\n");
> > +
> > + if (query_virtqueue(ndev, mvq, &attr)) {
> > + mlx5_vdpa_warn(&ndev->mvdev, "failed to query virtqueue\n");
> > + return;
> > + }
> > + mvq->avail_idx = attr.available_index;
> > }
> >
> > static void suspend_vqs(struct mlx5_vdpa_net *ndev)
> > @@ -1411,8 +1413,14 @@ static int mlx5_vdpa_get_vq_state(struct vdpa_device *vdev, u16 idx, struct vdpa
> > struct mlx5_virtq_attr attr;
> > int err;
> >
> > - if (!mvq->initialized)
> > - return -EAGAIN;
> > + /* If the virtq object was destroyed, use the value saved at
> > + * the last minute of suspend_vq. This caters for userspace
> > + * that cares about emulating the index after vq is stopped.
> > + */
> > + if (!mvq->initialized) {
> > + state->avail_index = mvq->avail_idx;
> > + return 0;
> > + }
> >
> > err = query_virtqueue(ndev, mvq, &attr);
> > if (err) {
> > --
> > 1.8.3.1
> >

2020-10-06 06:44:59

by Eli Cohen

Subject: Re: [PATCH] vdpa/mlx5: should keep avail_index despite device status

On Tue, Oct 06, 2020 at 02:22:15AM -0400, Michael S. Tsirkin wrote:

Acked-by: Eli Cohen <[email protected]>

> On Fri, Oct 02, 2020 at 01:17:00PM -0700, Si-Wei Liu wrote:
> > + Eli.
> >
> > On Thu, Oct 1, 2020 at 2:02 PM Si-Wei Liu <[email protected]> wrote:
> > >
> > > A VM with mlx5 vDPA has below warnings while being reset:
> > >
> > > vhost VQ 0 ring restore failed: -1: Resource temporarily unavailable (11)
> > > vhost VQ 1 ring restore failed: -1: Resource temporarily unavailable (11)
> > >
> > > We should allow userspace emulating the virtio device be
> > > able to get to vq's avail_index, regardless of vDPA device
> > > status. Save the index that was last seen when virtq was
> > > stopped, so that userspace doesn't complain.
> > >
> > > Signed-off-by: Si-Wei Liu <[email protected]>
>
> Eli can you review this pls? I need to send a pull request to Linux by
> tomorrow - do we want to include this?
>
> > > ---
> > > drivers/vdpa/mlx5/net/mlx5_vnet.c | 20 ++++++++++++++------
> > > 1 file changed, 14 insertions(+), 6 deletions(-)
> > >
> > > diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
> > > index 70676a6..74264e59 100644
> > > --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
> > > +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
> > > @@ -1133,15 +1133,17 @@ static void suspend_vq(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *m
> > > if (!mvq->initialized)
> > > return;
> > >
> > > - if (query_virtqueue(ndev, mvq, &attr)) {
> > > - mlx5_vdpa_warn(&ndev->mvdev, "failed to query virtqueue\n");
> > > - return;
> > > - }
> > > if (mvq->fw_state != MLX5_VIRTIO_NET_Q_OBJECT_STATE_RDY)
> > > return;
> > >
> > > if (modify_virtqueue(ndev, mvq, MLX5_VIRTIO_NET_Q_OBJECT_STATE_SUSPEND))
> > > mlx5_vdpa_warn(&ndev->mvdev, "modify to suspend failed\n");
> > > +
> > > + if (query_virtqueue(ndev, mvq, &attr)) {
> > > + mlx5_vdpa_warn(&ndev->mvdev, "failed to query virtqueue\n");
> > > + return;
> > > + }
> > > + mvq->avail_idx = attr.available_index;
> > > }
> > >
> > > static void suspend_vqs(struct mlx5_vdpa_net *ndev)
> > > @@ -1411,8 +1413,14 @@ static int mlx5_vdpa_get_vq_state(struct vdpa_device *vdev, u16 idx, struct vdpa
> > > struct mlx5_virtq_attr attr;
> > > int err;
> > >
> > > - if (!mvq->initialized)
> > > - return -EAGAIN;
> > > + /* If the virtq object was destroyed, use the value saved at
> > > + * the last minute of suspend_vq. This caters for userspace
> > > + * that cares about emulating the index after vq is stopped.
> > > + */
> > > + if (!mvq->initialized) {
> > > + state->avail_index = mvq->avail_idx;
> > > + return 0;
> > > + }
> > >
> > > err = query_virtqueue(ndev, mvq, &attr);
> > > if (err) {
> > > --
> > > 1.8.3.1
> > >
>

2020-10-10 09:24:12

by Jason Wang

Subject: Re: [PATCH] vdpa/mlx5: should keep avail_index despite device status

On 2020/10/2 上午4:18, Si-Wei Liu wrote:
> A VM with mlx5 vDPA has below warnings while being reset:
>
> vhost VQ 0 ring restore failed: -1: Resource temporarily unavailable (11)
> vhost VQ 1 ring restore failed: -1: Resource temporarily unavailable (11)
>
> We should allow userspace emulating the virtio device be
> able to get to vq's avail_index, regardless of vDPA device
> status. Save the index that was last seen when virtq was
> stopped, so that userspace doesn't complain.
>
> Signed-off-by: Si-Wei Liu <[email protected]>


Acked-by: Jason Wang <[email protected]>


> ---
> drivers/vdpa/mlx5/net/mlx5_vnet.c | 20 ++++++++++++++------
> 1 file changed, 14 insertions(+), 6 deletions(-)
>
> diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
> index 70676a6..74264e59 100644
> --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
> +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
> @@ -1133,15 +1133,17 @@ static void suspend_vq(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *m
> if (!mvq->initialized)
> return;
>
> - if (query_virtqueue(ndev, mvq, &attr)) {
> - mlx5_vdpa_warn(&ndev->mvdev, "failed to query virtqueue\n");
> - return;
> - }
> if (mvq->fw_state != MLX5_VIRTIO_NET_Q_OBJECT_STATE_RDY)
> return;
>
> if (modify_virtqueue(ndev, mvq, MLX5_VIRTIO_NET_Q_OBJECT_STATE_SUSPEND))
> mlx5_vdpa_warn(&ndev->mvdev, "modify to suspend failed\n");
> +
> + if (query_virtqueue(ndev, mvq, &attr)) {
> + mlx5_vdpa_warn(&ndev->mvdev, "failed to query virtqueue\n");
> + return;
> + }
> + mvq->avail_idx = attr.available_index;
> }
>
> static void suspend_vqs(struct mlx5_vdpa_net *ndev)
> @@ -1411,8 +1413,14 @@ static int mlx5_vdpa_get_vq_state(struct vdpa_device *vdev, u16 idx, struct vdpa
> struct mlx5_virtq_attr attr;
> int err;
>
> - if (!mvq->initialized)
> - return -EAGAIN;
> + /* If the virtq object was destroyed, use the value saved at
> + * the last minute of suspend_vq. This caters for userspace
> + * that cares about emulating the index after vq is stopped.
> + */
> + if (!mvq->initialized) {
> + state->avail_index = mvq->avail_idx;
> + return 0;
> + }
>
> err = query_virtqueue(ndev, mvq, &attr);
> if (err) {