vhost: Get vring base from vq, not svq
cover vhost: Get vring base from vq, not svq
The SVQ vring used idx usually match with the guest visible one, as long as all the guest buffers (GPA) maps to exactly one buffer within qemu's VA. However, as we can see in virtqueue_map_desc, a single guest buffer could map to many buffers in SVQ vring.
The solution is to stop using the device's used idx and check for the last avail idx. Since we cannot report in-flight descriptors with vdpa, let's rewind all of them.
Also, move this rewind to the destination, so we keep migrating the in-flight ones in case the destnation backend support them (vhost-kernel, emulated virtio in qemu, etc.)
Eugenio Pérez (2):
vhost: Get vring base from vq, not svq
vhost: Move SVQ queue rewind to the destination
hw/virtio/vhost-vdpa.c | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-)
Signature · 1 line
2.31.1
PATCH 1/2 vhost: Get vring base from vq, not svq
The SVQ vring used idx usually match with the guest visible one, as long as all the guest buffers (GPA) maps to exactly one buffer within qemu's VA. However, as we can see in virtqueue_map_desc, a single guest buffer could map to many buffers in SVQ vring.
The solution is to stop using the device's used idx and check for the last avail idx. Since we cannot report in-flight descriptors with vdpa, let's rewind all of them.
--- hw/virtio/vhost-vdpa.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-)
hw/virtio/vhost-vdpa.c +5 -3
@@ -1194,11 +1194,10 @@ static int vhost_vdpa_get_vring_base(struct vhost_dev *dev, struct vhost_vring_state *ring) {struct vhost_vdpa *v = dev->opaque; -int vdpa_idx = ring->index - dev->vq_index;int ret;if (v->shadow_vqs_enabled) { -VhostShadowVirtqueue *svq =g_ptr_array_index (v->shadow_vqs, vdpa_idx); +VirtQueue *vq =virtio_get_queue (dev->vdev, ring->index);/* * Setting base as last used idx, so destination will see as available
@@ -1208,7 +1207,10 @@ static int vhost_vdpa_get_vring_base(struct vhost_dev *dev,* TODO: This is ok for networking, but other kinds of devices might * have problems with these retransmissions. */ - ring->num = svq->last_used_idx; +while (virtqueue_rewind (vq,1 )) { +continue ; + } + ring->num =virtio_queue_get_last_avail_idx (dev->vdev, ring->index);return 0 ; }
Signature · 1 line
2.31.1
PATCH 2/2 vhost: Move SVQ queue rewind to the destination
In reply to Eugenio PérezMigration with SVQ already migrate the inflight descriptors, so the destination can perform the work.
This makes easier to migrate between backends or to recover them in vhost devices that support set in flight descriptors.
--- hw/virtio/vhost-vdpa.c | 24 +++++++++++------------- 1 file changed, 11 insertions(+), 13 deletions(-)
hw/virtio/vhost-vdpa.c +11 -13
@@ -1178,7 +1178,18 @@ static int vhost_vdpa_set_vring_base(struct vhost_dev *dev, struct vhost_vring_state *ring) {struct vhost_vdpa *v = dev->opaque; +VirtQueue *vq =virtio_get_queue (dev->vdev, ring->index); +/* +* vhost-vdpa devices does not support in-flight requests. Set all of them +* as available. +* +* TODO: This is ok for networking, but other kinds of devices might +* have problems with these retransmissions. +*/ +while (virtqueue_rewind (vq,1 )) { +continue ; + }if (v->shadow_vqs_enabled) {/* * Device vring base was set at device start. SVQ base is handled by
@@ -1197,19 +1208,6 @@ static int vhost_vdpa_get_vring_base(struct vhost_dev *dev,int ret;if (v->shadow_vqs_enabled) { -VirtQueue *vq =virtio_get_queue (dev->vdev, ring->index); - -/* -* Setting base as last used idx, so destination will see as available -* all the entries that the device did not use, including the in-flight -* processing ones. -* -* TODO: This is ok for networking, but other kinds of devices might -* have problems with these retransmissions. -*/ -while (virtqueue_rewind (vq,1 )) { -continue ; - } ring->num =virtio_queue_get_last_avail_idx (dev->vdev, ring->index);return 0 ; }
Signature · 1 line
2.31.1