Commit d0fcc38f5fa4 ("vhost: improve device readiness notifications") makes the assumption that every Virtio devices are considered ready for preocessing as soon as first queue pair is configured and enabled. While this is true for Virtio-net, it isn't for Virtio-scsi and Virtio-blk. This patch fixes this by only making this assumption for the builtin Virtio-net backend, and restores back to previous behaviour for other backends. Fixes: d0fcc38f5fa4 ("vhost: improve device readiness notifications") Reported-by: Changpeng Liu <changpeng.liu@intel.com> Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com> Signed-off-by: Changpeng Liu <changpeng.liu@intel.com> --- lib/librte_vhost/vhost_user.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/lib/librte_vhost/vhost_user.c b/lib/librte_vhost/vhost_user.c index 501218e192..b00e1f91dc 100644 --- a/lib/librte_vhost/vhost_user.c +++ b/lib/librte_vhost/vhost_user.c @@ -1343,21 +1343,28 @@ vq_is_ready(struct virtio_net *dev, struct vhost_virtqueue *vq) vq->enabled; } -#define VIRTIO_DEV_NUM_VQS_TO_BE_READY 2u +#define VIRTIO_BUILTIN_NUM_VQS_TO_BE_READY 2u static int virtio_is_ready(struct virtio_net *dev) { struct vhost_virtqueue *vq; - uint32_t i; + uint32_t i, nr_vring = dev->nr_vring; if (dev->flags & VIRTIO_DEV_READY) return 1; - if (dev->nr_vring < VIRTIO_DEV_NUM_VQS_TO_BE_READY) + if (!dev->nr_vring) return 0; - for (i = 0; i < VIRTIO_DEV_NUM_VQS_TO_BE_READY; i++) { + if (dev->flags & VIRTIO_DEV_BUILTIN_VIRTIO_NET) { + nr_vring = VIRTIO_BUILTIN_NUM_VQS_TO_BE_READY; + + if (dev->nr_vring < nr_vring) + return 0; + } + + for (i = 0; i < nr_vring; i++) { vq = dev->virtqueue[i]; if (!vq_is_ready(dev, vq)) -- 2.26.2
> -----Original Message-----
> From: Maxime Coquelin <maxime.coquelin@redhat.com>
> Sent: Wednesday, September 23, 2020 5:49 PM
> To: dev@dpdk.org; Xia, Chenbo <chenbo.xia@intel.com>; matan@mellanox.com;
> Zawadzki, Tomasz <tomasz.zawadzki@intel.com>; Liu, Changpeng
> <changpeng.liu@intel.com>
> Cc: Maxime Coquelin <maxime.coquelin@redhat.com>
> Subject: [PATCH] vhost: fix external backends readiness
>
> Commit d0fcc38f5fa4 ("vhost: improve device readiness notifications")
> makes the assumption that every Virtio devices are considered
> ready for preocessing as soon as first queue pair is configured
> and enabled.
>
> While this is true for Virtio-net, it isn't for Virtio-scsi
> and Virtio-blk.
>
> This patch fixes this by only making this assumption for
> the builtin Virtio-net backend, and restores back to previous
> behaviour for other backends.
>
> Fixes: d0fcc38f5fa4 ("vhost: improve device readiness notifications")
>
> Reported-by: Changpeng Liu <changpeng.liu@intel.com>
> Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
> Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
> ---
> lib/librte_vhost/vhost_user.c | 15 +++++++++++----
> 1 file changed, 11 insertions(+), 4 deletions(-)
>
> diff --git a/lib/librte_vhost/vhost_user.c b/lib/librte_vhost/vhost_user.c
> index 501218e192..b00e1f91dc 100644
> --- a/lib/librte_vhost/vhost_user.c
> +++ b/lib/librte_vhost/vhost_user.c
> @@ -1343,21 +1343,28 @@ vq_is_ready(struct virtio_net *dev, struct
> vhost_virtqueue *vq)
> vq->enabled;
> }
>
> -#define VIRTIO_DEV_NUM_VQS_TO_BE_READY 2u
> +#define VIRTIO_BUILTIN_NUM_VQS_TO_BE_READY 2u
>
> static int
> virtio_is_ready(struct virtio_net *dev)
> {
> struct vhost_virtqueue *vq;
> - uint32_t i;
> + uint32_t i, nr_vring = dev->nr_vring;
>
> if (dev->flags & VIRTIO_DEV_READY)
> return 1;
>
> - if (dev->nr_vring < VIRTIO_DEV_NUM_VQS_TO_BE_READY)
> + if (!dev->nr_vring)
> return 0;
>
> - for (i = 0; i < VIRTIO_DEV_NUM_VQS_TO_BE_READY; i++) {
> + if (dev->flags & VIRTIO_DEV_BUILTIN_VIRTIO_NET) {
> + nr_vring = VIRTIO_BUILTIN_NUM_VQS_TO_BE_READY;
> +
> + if (dev->nr_vring < nr_vring)
> + return 0;
> + }
> +
> + for (i = 0; i < nr_vring; i++) {
> vq = dev->virtqueue[i];
>
> if (!vq_is_ready(dev, vq))
> --
> 2.26.2
Reviewed-by: Chenbo Xia <chenbo.xia@intel.com>
28/09/2020 12:55, Xia, Chenbo:
> >
> > Commit d0fcc38f5fa4 ("vhost: improve device readiness notifications")
> > makes the assumption that every Virtio devices are considered
> > ready for preocessing as soon as first queue pair is configured
> > and enabled.
> >
> > While this is true for Virtio-net, it isn't for Virtio-scsi
> > and Virtio-blk.
> >
> > This patch fixes this by only making this assumption for
> > the builtin Virtio-net backend, and restores back to previous
> > behaviour for other backends.
> >
> > Fixes: d0fcc38f5fa4 ("vhost: improve device readiness notifications")
> >
> > Reported-by: Changpeng Liu <changpeng.liu@intel.com>
> > Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
> > Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
>
> Reviewed-by: Chenbo Xia <chenbo.xia@intel.com>
Applied in the main repository, thanks.