Web lists-archives.com

Re: [RFC v4 3/5] virtio_ring: add packed ring support

On 2018年05月16日 20:39, Tiwei Bie wrote:
On Wed, May 16, 2018 at 07:50:16PM +0800, Jason Wang wrote:
On 2018年05月16日 16:37, Tiwei Bie wrote:
   struct vring_virtqueue {
@@ -116,6 +117,9 @@ struct vring_virtqueue {
   			/* Last written value to driver->flags in
   			 * guest byte order. */
   			u16 event_flags_shadow;
+			/* ID allocation. */
+			struct idr buffer_id;
I'm not sure idr is fit for the performance critical case here. Need to
measure its performance impact, especially if we have few unused slots.
I'm also not sure.. But fortunately, it should be quite easy
to replace it with something else without changing other code.
If it will really hurt the performance, I'll change it.

We may want to do some benchmarking/profiling to see.

+static void detach_buf_packed(struct vring_virtqueue *vq, unsigned int head,
+			      unsigned int id, void **ctx)
+	struct vring_packed_desc *desc;
+	unsigned int i, j;
+	/* Clear data ptr. */
+	vq->desc_state[id].data = NULL;
+	i = head;
+	for (j = 0; j < vq->desc_state[id].num; j++) {
+		desc = &vq->vring_packed.desc[i];
+		vring_unmap_one_packed(vq, desc);
As mentioned in previous discussion, this probably won't work for the case
of out of order completion since it depends on the information in the
descriptor ring. We probably need to extend ctx to record such information.
Above code doesn't depend on the information in the descriptor
ring. The vq->desc_state[] is the extended ctx.

Best regards,
Tiwei Bie

Yes, but desc is a pointer to descriptor ring I think so vring_unmap_one_packed() still depends on the content of descriptor ring?