Linux Virtualization - Nov 2018 - [PATCH net-next 0/3] basic in order support for vhost_net

Hi:

This series implement basic in order feature support for
vhost_net. This feature requires both driver and device to use
descriptors in order which can simplify the implementation and
optimizaton for both side. The series also implement a simple
optimization that avoid read available ring. Test shows 10%
performance improvement.

More optimizations could be done on top.

Jason Wang (3):
  virtio: introduce in order feature bit
  vhost_net: support in order feature
  vhost: don't touch avail ring if in_order is negotiated

 drivers/vhost/net.c                |  6 ++++--
 drivers/vhost/vhost.c              | 19 ++++++++++++-------
 include/uapi/linux/virtio_config.h |  6 ++++++
 3 files changed, 22 insertions(+), 9 deletions(-)

-- 
2.17.1

Signed-off-by: Jason Wang <jasowang at redhat.com>
---
 include/uapi/linux/virtio_config.h | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/include/uapi/linux/virtio_config.h
b/include/uapi/linux/virtio_config.h
index 449132c76b1c..64496afc016d 100644
--- a/include/uapi/linux/virtio_config.h
+++ b/include/uapi/linux/virtio_config.h
@@ -75,6 +75,12 @@
  */
 #define VIRTIO_F_IOMMU_PLATFORM		33
 
+/*
+ * Device uses buffers in the same order in which they have been
+ * available.
+ */
+#define VIRTIO_F_IN_ORDER		35
+
 /*
  * Does the device support Single Root I/O Virtualization?
  */
-- 
2.17.1

This makes vhost_net to support in order feature. This is as simple as
use datacopy path when it was negotiated. An alternative is not to
advertise in order when zerocopy is enabled which tends to be
suboptimal consider zerocopy may suffer from e.g HOL issues.

Signed-off-by: Jason Wang <jasowang at redhat.com>
---
 drivers/vhost/net.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index d919284f103b..bdf5de5a7eb2 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -74,7 +74,8 @@ enum {
 	VHOST_NET_FEATURES = VHOST_FEATURES |
 			 (1ULL << VHOST_NET_F_VIRTIO_NET_HDR) |
 			 (1ULL << VIRTIO_NET_F_MRG_RXBUF) |
-			 (1ULL << VIRTIO_F_IOMMU_PLATFORM)
+			 (1ULL << VIRTIO_F_IOMMU_PLATFORM) |
+	                 (1ULL << VIRTIO_F_IN_ORDER)
 };
 
 enum {
@@ -971,7 +972,8 @@ static void handle_tx(struct vhost_net *net)
 	vhost_disable_notify(&net->dev, vq);
 	vhost_net_disable_vq(net, vq);
 
-	if (vhost_sock_zcopy(sock))
+	if (vhost_sock_zcopy(sock) &&
+	    !vhost_has_feature(vq, VIRTIO_F_IN_ORDER))
 		handle_tx_zerocopy(net, sock);
 	else
 		handle_tx_copy(net, sock);
-- 
2.17.1

Device use descriptors table in order, so there's no need to read
index from available ring. This eliminate the cache contention on
avail ring completely.

Virito-user + vhost_kernel + XDP_DROP gives about ~10% improvement on
TX from 4.8Mpps to 5.3Mpps on Intel(R) Core(TM) i7-5600U CPU @
2.60GHz.

Signed-off-by: Jason Wang <jasowang at redhat.com>
---
 drivers/vhost/vhost.c | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 3a5f81a66d34..c8be151bc897 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -2002,6 +2002,7 @@ int vhost_get_vq_desc(struct vhost_virtqueue *vq,
 	__virtio16 avail_idx;
 	__virtio16 ring_head;
 	int ret, access;
+	bool in_order = vhost_has_feature(vq, VIRTIO_F_IN_ORDER);
 
 	/* Check it isn't doing very strange things with descriptor numbers. */
 	last_avail_idx = vq->last_avail_idx;
@@ -2034,15 +2035,19 @@ int vhost_get_vq_desc(struct vhost_virtqueue *vq,
 
 	/* Grab the next descriptor number they're advertising, and increment
 	 * the index we've seen. */
-	if (unlikely(vhost_get_avail(vq, ring_head,
-		     &vq->avail->ring[last_avail_idx & (vq->num - 1)]))) {
-		vq_err(vq, "Failed to read head: idx %d address %p\n",
-		       last_avail_idx,
-		       &vq->avail->ring[last_avail_idx % vq->num]);
-		return -EFAULT;
+	if (!in_order) {
+		if (unlikely(vhost_get_avail(vq, ring_head,
+		    &vq->avail->ring[last_avail_idx & (vq->num - 1)]))) {
+			vq_err(vq, "Failed to read head: idx %d address %p\n",
+				last_avail_idx,
+				&vq->avail->ring[last_avail_idx % vq->num]);
+			return -EFAULT;
+		}
+		head = vhost16_to_cpu(vq, ring_head);
+	} else {
+		head = last_avail_idx & (vq->num - 1);
 	}
 
-	head = vhost16_to_cpu(vq, ring_head);
 
 	/* If their number is silly, that's an error. */
 	if (unlikely(head >= vq->num)) {
-- 
2.17.1

On Fri, Nov 23, 2018 at 11:00:16AM +0800, Jason Wang
wrote:
> Device use descriptors table in order, so there's no need to read
> index from available ring. This eliminate the cache contention on
> avail ring completely.
Well this isn't what the in order feature says in the spec.

It forces the used ring to be in the same order as
the available ring. So I don't think you can skip
checking the available ring. And in fact depending on
ring size and workload, using all of descriptor buffer might
cause a slowdown.
Rather you should be able to get
about the same speedup, but from skipping checking
the used ring in virtio.

> Virito-user + vhost_kernel + XDP_DROP gives about ~10% improvement on
> TX from 4.8Mpps to 5.3Mpps on Intel(R) Core(TM) i7-5600U CPU @
> 2.60GHz.
> 
> Signed-off-by: Jason Wang <jasowang at redhat.com>
> ---
>  drivers/vhost/vhost.c | 19 ++++++++++++-------
>  1 file changed, 12 insertions(+), 7 deletions(-)
> 
> diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
> index 3a5f81a66d34..c8be151bc897 100644
> --- a/drivers/vhost/vhost.c
> +++ b/drivers/vhost/vhost.c
> @@ -2002,6 +2002,7 @@ int vhost_get_vq_desc(struct vhost_virtqueue *vq,
>  	__virtio16 avail_idx;
>  	__virtio16 ring_head;
>  	int ret, access;
> +	bool in_order = vhost_has_feature(vq, VIRTIO_F_IN_ORDER);
>  
>  	/* Check it isn't doing very strange things with descriptor numbers.
*/
>  	last_avail_idx = vq->last_avail_idx;
> @@ -2034,15 +2035,19 @@ int vhost_get_vq_desc(struct vhost_virtqueue *vq,
>  
>  	/* Grab the next descriptor number they're advertising, and increment
>  	 * the index we've seen. */
> -	if (unlikely(vhost_get_avail(vq, ring_head,
> -		     &vq->avail->ring[last_avail_idx & (vq->num -
1)]))) {
> -		vq_err(vq, "Failed to read head: idx %d address %p\n",
> -		       last_avail_idx,
> -		       &vq->avail->ring[last_avail_idx % vq->num]);
> -		return -EFAULT;
> +	if (!in_order) {
> +		if (unlikely(vhost_get_avail(vq, ring_head,
> +		    &vq->avail->ring[last_avail_idx & (vq->num - 1)])))
{
> +			vq_err(vq, "Failed to read head: idx %d address %p\n",
> +				last_avail_idx,
> +				&vq->avail->ring[last_avail_idx % vq->num]);
> +			return -EFAULT;
> +		}
> +		head = vhost16_to_cpu(vq, ring_head);
> +	} else {
> +		head = last_avail_idx & (vq->num - 1);
>  	}
>  
> -	head = vhost16_to_cpu(vq, ring_head);
>  
>  	/* If their number is silly, that's an error. */
>  	if (unlikely(head >= vq->num)) {
> -- 
> 2.17.1

On Fri, Nov 23, 2018 at 11:00:15AM +0800, Jason Wang
wrote:
> This makes vhost_net to support in order feature. This is as simple as
> use datacopy path when it was negotiated. An alternative is not to
> advertise in order when zerocopy is enabled which tends to be
> suboptimal consider zerocopy may suffer from e.g HOL issues.
Well IIRC vhost_zerocopy_signal_used is used to
actually reorder used ring to match available ring.
So with a big comment explaining why it is so,
we could just enable IN_ORDER there too.
> 
> Signed-off-by: Jason Wang <jasowang at redhat.com>
> ---
>  drivers/vhost/net.c | 6 ++++--
>  1 file changed, 4 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
> index d919284f103b..bdf5de5a7eb2 100644
> --- a/drivers/vhost/net.c
> +++ b/drivers/vhost/net.c
> @@ -74,7 +74,8 @@ enum {
>  	VHOST_NET_FEATURES = VHOST_FEATURES |
>  			 (1ULL << VHOST_NET_F_VIRTIO_NET_HDR) |
>  			 (1ULL << VIRTIO_NET_F_MRG_RXBUF) |
> -			 (1ULL << VIRTIO_F_IOMMU_PLATFORM)
> +			 (1ULL << VIRTIO_F_IOMMU_PLATFORM) |
> +	                 (1ULL << VIRTIO_F_IN_ORDER)
>  };
>  
>  enum {
> @@ -971,7 +972,8 @@ static void handle_tx(struct vhost_net *net)
>  	vhost_disable_notify(&net->dev, vq);
>  	vhost_net_disable_vq(net, vq);
>  
> -	if (vhost_sock_zcopy(sock))
> +	if (vhost_sock_zcopy(sock) &&
> +	    !vhost_has_feature(vq, VIRTIO_F_IN_ORDER))
>  		handle_tx_zerocopy(net, sock);
>  	else
>  		handle_tx_copy(net, sock);
> -- 
> 2.17.1