[v1,11/14] vhost: add burst and single zero dequeue functions

Message ID 20190905161421.55981-12-yong.liu@intel.com (mailing list archive)
State Superseded, archived
Delegated to: Maxime Coquelin
Headers
Series vhost packed ring performance optimization |

Checks

Context Check Description
ci/checkpatch success coding style OK
ci/Intel-compilation success Compilation OK

Commit Message

Marvin Liu Sept. 5, 2019, 4:14 p.m. UTC
  Optimize vhost zero copy dequeue path like normal dequeue path.

Signed-off-by: Marvin Liu <yong.liu@intel.com>
  

Patch

diff --git a/lib/librte_vhost/virtio_net.c b/lib/librte_vhost/virtio_net.c
index 269ec8a43..8032229a0 100644
--- a/lib/librte_vhost/virtio_net.c
+++ b/lib/librte_vhost/virtio_net.c
@@ -1979,6 +1979,108 @@  virtio_dev_tx_single_packed(struct virtio_net *dev, struct vhost_virtqueue *vq,
 	return 0;
 }
 
+static __rte_unused int
+virtio_dev_tx_burst_packed_zmbuf(struct virtio_net *dev,
+					struct vhost_virtqueue *vq,
+					struct rte_mempool *mbuf_pool,
+					struct rte_mbuf **pkts)
+{
+	struct zcopy_mbuf *zmbuf, *zmbuf1, *zmbuf2, *zmbuf3;
+	int ret;
+	uintptr_t desc_addr[4];
+	uint16_t ids[4];
+
+	uint16_t avail_idx = vq->last_avail_idx;
+
+	ret = vhost_dequeue_burst_packed(dev, vq, mbuf_pool, pkts, avail_idx,
+					desc_addr, ids);
+
+	if (ret)
+		return ret;
+
+	zmbuf = get_zmbuf(vq);
+	zmbuf1 = get_zmbuf(vq);
+	zmbuf2 = get_zmbuf(vq);
+	zmbuf3 = get_zmbuf(vq);
+
+	if (!zmbuf || !zmbuf1 || !zmbuf2 || !zmbuf3) {
+		rte_pktmbuf_free(pkts[0]);
+		rte_pktmbuf_free(pkts[1]);
+		rte_pktmbuf_free(pkts[2]);
+		rte_pktmbuf_free(pkts[3]);
+		return -1;
+	}
+
+	zmbuf->mbuf = pkts[0];
+	zmbuf->desc_idx = avail_idx;
+	zmbuf->desc_count = 1;
+
+	zmbuf1->mbuf = pkts[1];
+	zmbuf1->desc_idx = avail_idx + 1;
+	zmbuf1->desc_count = 1;
+
+	zmbuf2->mbuf = pkts[2];
+	zmbuf2->desc_idx = avail_idx + 2;
+	zmbuf2->desc_count = 1;
+
+	zmbuf3->mbuf = pkts[3];
+	zmbuf3->desc_idx = avail_idx + 3;
+	zmbuf3->desc_count = 1;
+
+	rte_mbuf_refcnt_update(pkts[0], 1);
+	rte_mbuf_refcnt_update(pkts[1], 1);
+	rte_mbuf_refcnt_update(pkts[2], 1);
+	rte_mbuf_refcnt_update(pkts[3], 1);
+
+	vq->nr_zmbuf += PACKED_DESCS_BURST;
+	TAILQ_INSERT_TAIL(&vq->zmbuf_list, zmbuf, next);
+	TAILQ_INSERT_TAIL(&vq->zmbuf_list, zmbuf1, next);
+	TAILQ_INSERT_TAIL(&vq->zmbuf_list, zmbuf2, next);
+	TAILQ_INSERT_TAIL(&vq->zmbuf_list, zmbuf3, next);
+
+	vq->last_avail_idx += PACKED_DESCS_BURST;
+	if (vq->last_avail_idx >= vq->size) {
+		vq->last_avail_idx -= vq->size;
+		vq->avail_wrap_counter ^= 1;
+	}
+
+	return 0;
+}
+
+static __rte_unused int
+virtio_dev_tx_single_packed_zmbuf(struct virtio_net *dev,
+	struct vhost_virtqueue *vq, struct rte_mempool *mbuf_pool,
+	struct rte_mbuf **pkts)
+{
+	uint16_t buf_id, desc_count;
+	struct zcopy_mbuf *zmbuf;
+
+	if (vhost_dequeue_single_packed(dev, vq, mbuf_pool, pkts, &buf_id,
+					&desc_count))
+		return -1;
+
+	zmbuf = get_zmbuf(vq);
+	if (!zmbuf) {
+		rte_pktmbuf_free(*pkts);
+		return -1;
+	}
+	zmbuf->mbuf = *pkts;
+	zmbuf->desc_idx = vq->last_avail_idx;
+	zmbuf->desc_count = desc_count;
+
+	rte_mbuf_refcnt_update(*pkts, 1);
+
+	vq->nr_zmbuf += 1;
+	TAILQ_INSERT_TAIL(&vq->zmbuf_list, zmbuf, next);
+
+	vq->last_avail_idx += desc_count;
+	if (vq->last_avail_idx >= vq->size) {
+		vq->last_avail_idx -= vq->size;
+		vq->avail_wrap_counter ^= 1;
+	}
+
+	return 0;
+}
 
 static __rte_noinline uint16_t
 virtio_dev_tx_packed(struct virtio_net *dev, struct vhost_virtqueue *vq,
@@ -2092,6 +2194,47 @@  virtio_dev_tx_packed(struct virtio_net *dev, struct vhost_virtqueue *vq,
 	return i;
 }
 
+static __rte_unused void
+free_zmbuf(struct vhost_virtqueue *vq)
+{
+	struct zcopy_mbuf *next = NULL;
+	struct zcopy_mbuf *zmbuf;
+
+	for (zmbuf = TAILQ_FIRST(&vq->zmbuf_list);
+	     zmbuf != NULL; zmbuf = next) {
+		next = TAILQ_NEXT(zmbuf, next);
+
+		uint16_t last_used_idx = vq->last_used_idx;
+
+		if (mbuf_is_consumed(zmbuf->mbuf)) {
+			uint16_t flags = 0;
+
+			if (vq->used_wrap_counter)
+				flags = VIRTIO_TX_USED_FLAG;
+			else
+				flags = VIRTIO_TX_USED_WRAP_FLAG;
+
+			vq->desc_packed[last_used_idx].id = zmbuf->desc_idx;
+			vq->desc_packed[last_used_idx].len = 0;
+
+			rte_smp_wmb();
+			vq->desc_packed[last_used_idx].flags = flags;
+
+			vq->last_used_idx += zmbuf->desc_count;
+			if (vq->last_used_idx >= vq->size) {
+				vq->used_wrap_counter ^= 1;
+				vq->last_used_idx -= vq->size;
+			}
+
+			TAILQ_REMOVE(&vq->zmbuf_list, zmbuf, next);
+			restore_mbuf(zmbuf->mbuf);
+			rte_pktmbuf_free(zmbuf->mbuf);
+			put_zmbuf(zmbuf);
+			vq->nr_zmbuf -= 1;
+		}
+	}
+}
+
 uint16_t
 rte_vhost_dequeue_burst(int vid, uint16_t queue_id,
 	struct rte_mempool *mbuf_pool, struct rte_mbuf **pkts, uint16_t count)