[dpdk-stable] [PATCH 18.11 1/7] vhost: batch used descs chains write-back with packed ring

[Adrian Moreno <amorenoz@redhat.com>]

From: Maxime Coquelin <maxime.coquelin@redhat.com>

[ upstream commit b473ec1131ee44ee25e0536a04be65246b93f4f3 ]

Instead of writing back descriptors chains in order, let's
write the first chain flags last in order to improve batching.

Also, move the write barrier in logging cache sync, so that it
is done only when logging is enabled. It means there is now
one more barrier for split ring when logging is enabled.

With Kernel's pktgen benchmark, ~3% performance gain is measured.

Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Tiwei Bie <tiwei.bie@intel.com>
---
 lib/librte_vhost/vhost.h      |  7 ++-----
 lib/librte_vhost/virtio_net.c | 19 ++++++++++++++++---
 2 files changed, 18 insertions(+), 8 deletions(-)

diff --git a/lib/librte_vhost/vhost.h b/lib/librte_vhost/vhost.h
index daccf5c65..47d64bad3 100644
--- a/lib/librte_vhost/vhost.h
+++ b/lib/librte_vhost/vhost.h
@@ -456,12 +456,9 @@ vhost_log_cache_sync(struct virtio_net *dev, struct vhost_virtqueue *vq)
 		   !dev->log_base))
 		return;
 
-	log_base = (unsigned long *)(uintptr_t)dev->log_base;
+	rte_smp_wmb();
 
-	/*
-	 * It is expected a write memory barrier has been issued
-	 * before this function is called.
-	 */
+	log_base = (unsigned long *)(uintptr_t)dev->log_base;
 
 	for (i = 0; i < vq->log_cache_nb_elem; i++) {
 		struct log_cache_entry *elem = vq->log_cache + i;
diff --git a/lib/librte_vhost/virtio_net.c b/lib/librte_vhost/virtio_net.c
index 740db2ed7..6ae617698 100644
--- a/lib/librte_vhost/virtio_net.c
+++ b/lib/librte_vhost/virtio_net.c
@@ -136,6 +136,8 @@ flush_shadow_used_ring_packed(struct virtio_net *dev,
 {
 	int i;
 	uint16_t used_idx = vq->last_used_idx;
+	uint16_t head_idx = vq->last_used_idx;
+	uint16_t head_flags = 0;
 
 	/* Split loop in two to save memory barriers */
 	for (i = 0; i < vq->shadow_used_idx; i++) {
@@ -165,12 +167,17 @@ flush_shadow_used_ring_packed(struct virtio_net *dev,
 			flags &= ~VRING_DESC_F_AVAIL;
 		}
 
-		vq->desc_packed[vq->last_used_idx].flags = flags;
+		if (i > 0) {
+			vq->desc_packed[vq->last_used_idx].flags = flags;
 
-		vhost_log_cache_used_vring(dev, vq,
+			vhost_log_cache_used_vring(dev, vq,
 					vq->last_used_idx *
 					sizeof(struct vring_packed_desc),
 					sizeof(struct vring_packed_desc));
+		} else {
+			head_idx = vq->last_used_idx;
+			head_flags = flags;
+		}
 
 		vq->last_used_idx += vq->shadow_used_packed[i].count;
 		if (vq->last_used_idx >= vq->size) {
@@ -179,7 +186,13 @@ flush_shadow_used_ring_packed(struct virtio_net *dev,
 		}
 	}
 
-	rte_smp_wmb();
+	vq->desc_packed[head_idx].flags = head_flags;
+
+	vhost_log_cache_used_vring(dev, vq,
+				head_idx *
+				sizeof(struct vring_packed_desc),
+				sizeof(struct vring_packed_desc));
+
 	vq->shadow_used_idx = 0;
 	vhost_log_cache_sync(dev, vq);
 }
-- 
2.21.0