Indirect buffers are ring descriptors which point to more (even more)
descriptors.
This can be used to increase the effective ring capacity, which helps the
guest to batch large requests - very useful for blk devices.
This patch also enables indirect buffers for virtio-net and virtio-blk.
The patch is based on the lguest's code which does the same.
Signed-off-by: Sasha Levin <levinsasha...@gmail.com>
---
tools/kvm/virtio/blk.c | 3 ++-
tools/kvm/virtio/core.c | 47 ++++++++++++++++++++++++++++++++++++++---------
tools/kvm/virtio/net.c | 3 ++-
3 files changed, 42 insertions(+), 11 deletions(-)
diff --git a/tools/kvm/virtio/blk.c b/tools/kvm/virtio/blk.c
index 8c6f90b..d1a0197 100644
--- a/tools/kvm/virtio/blk.c
+++ b/tools/kvm/virtio/blk.c
@@ -148,7 +148,8 @@ static u32 get_host_features(struct kvm *kvm, void *dev)
{
return 1UL << VIRTIO_BLK_F_SEG_MAX
| 1UL << VIRTIO_BLK_F_FLUSH
- | 1UL << VIRTIO_RING_F_EVENT_IDX;
+ | 1UL << VIRTIO_RING_F_EVENT_IDX
+ | 1UL << VIRTIO_RING_F_INDIRECT_DESC;
}
static void set_guest_features(struct kvm *kvm, void *dev, u32 features)
diff --git a/tools/kvm/virtio/core.c b/tools/kvm/virtio/core.c
index a6f180e..fe9d588 100644
--- a/tools/kvm/virtio/core.c
+++ b/tools/kvm/virtio/core.c
@@ -33,27 +33,56 @@ struct vring_used_elem *virt_queue__set_used_elem(struct
virt_queue *queue, u32
return used_elem;
}
+/*
+ * Each buffer in the virtqueues is actually a chain of descriptors. This
+ * function returns the next descriptor in the chain, or vq->vring.num if we're
+ * at the end.
+ */
+static unsigned next_desc(struct vring_desc *desc,
+ unsigned int i, unsigned int max)
+{
+ unsigned int next;
+
+ /* If this descriptor says it doesn't chain, we're done. */
+ if (!(desc[i].flags & VRING_DESC_F_NEXT))
+ return max;
+
+ /* Check they're not leading us off end of descriptors. */
+ next = desc[i].next;
+ /* Make sure compiler knows to grab that: we don't want it changing! */
+ wmb();
+
+ return next;
+}
+
u16 virt_queue__get_head_iov(struct virt_queue *vq, struct iovec iov[], u16
*out, u16 *in, u16 head, struct kvm *kvm)
{
struct vring_desc *desc;
u16 idx;
+ u16 max;
idx = head;
*out = *in = 0;
+ max = vq->vring.num;
+ desc = vq->vring.desc;
+
+ if (desc[idx].flags & VRING_DESC_F_INDIRECT) {
+
+ max = desc[idx].len / sizeof(struct vring_desc);
+ desc = guest_flat_to_host(kvm, desc[idx].addr);
+ idx = 0;
+ }
do {
- desc = virt_queue__get_desc(vq, idx);
- iov[*out + *in].iov_base = guest_flat_to_host(kvm, desc->addr);
- iov[*out + *in].iov_len = desc->len;
- if (desc->flags & VRING_DESC_F_WRITE)
+ /* Grab the first descriptor, and check it's OK. */
+ iov[*out + *in].iov_len = desc[idx].len;
+ iov[*out + *in].iov_base = guest_flat_to_host(kvm,
desc[idx].addr);
+ /* If this is an input descriptor, increment that count. */
+ if (desc[idx].flags & VRING_DESC_F_WRITE)
(*in)++;
else
(*out)++;
- if (desc->flags & VRING_DESC_F_NEXT)
- idx = desc->next;
- else
- break;
- } while (1);
+ } while ((idx = next_desc(desc, idx, max)) != max);
return head;
}
diff --git a/tools/kvm/virtio/net.c b/tools/kvm/virtio/net.c
index ce34555..3fb5054 100644
--- a/tools/kvm/virtio/net.c
+++ b/tools/kvm/virtio/net.c
@@ -318,7 +318,8 @@ static u32 get_host_features(struct kvm *kvm, void *dev)
| 1UL << VIRTIO_NET_F_GUEST_UFO
| 1UL << VIRTIO_NET_F_GUEST_TSO4
| 1UL << VIRTIO_NET_F_GUEST_TSO6
- | 1UL << VIRTIO_RING_F_EVENT_IDX;
+ | 1UL << VIRTIO_RING_F_EVENT_IDX
+ | 1UL << VIRTIO_RING_F_INDIRECT_DESC;
}
static void set_guest_features(struct kvm *kvm, void *dev, u32 features)
--
1.7.8.rc3
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
