[dpdk-dev] [PATCH v1 04/14] vhost: add burst dequeue function

[Marvin Liu]

Add burst dequeue function like enqueue function for packed ring, burst
dequeue function will not support chained descritpors, single packet
dequeue function will handle it.

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

diff --git a/lib/librte_vhost/vhost.h b/lib/librte_vhost/vhost.h
index ed8b4aabf..b33f29ba0 100644
--- a/lib/librte_vhost/vhost.h
+++ b/lib/librte_vhost/vhost.h
@@ -41,6 +41,8 @@
 
 #define PACKED_DESCS_BURST 4
 #define PACKED_BURST_MASK (PACKED_DESCS_BURST - 1)
+#define DESC_SINGLE_DEQUEUE (VRING_DESC_F_NEXT | VRING_DESC_F_INDIRECT)
+
 /**
  * Structure contains buffer address, length and descriptor index
  * from vring to do scatter RX.
diff --git a/lib/librte_vhost/virtio_net.c b/lib/librte_vhost/virtio_net.c
index 454e8b33e..f34df3733 100644
--- a/lib/librte_vhost/virtio_net.c
+++ b/lib/librte_vhost/virtio_net.c
@@ -1603,6 +1603,150 @@ virtio_dev_tx_split(struct virtio_net *dev, struct vhost_virtqueue *vq,
 	return i;
 }
 
+static __rte_always_inline int
+vhost_dequeue_burst_packed(struct virtio_net *dev, struct vhost_virtqueue *vq,
+	struct rte_mempool *mbuf_pool, struct rte_mbuf **pkts,
+	uint16_t avail_idx, uintptr_t *desc_addr, uint16_t *ids)
+{
+	bool wrap_counter = vq->avail_wrap_counter;
+	struct vring_packed_desc *descs = vq->desc_packed;
+	uint64_t len, len1, len2, len3;
+	uint64_t buf_len, buf_len1, buf_len2, buf_len3;
+	uint32_t buf_offset = dev->vhost_hlen;
+
+	// check whether desc is burst aligned
+	if (unlikely(avail_idx & PACKED_BURST_MASK))
+		return -1;
+
+	if (unlikely(!desc_is_avail(&descs[avail_idx], wrap_counter)) |
+		unlikely(!desc_is_avail(&descs[avail_idx + 1], wrap_counter)) |
+		unlikely(!desc_is_avail(&descs[avail_idx + 2], wrap_counter)) |
+		unlikely(!desc_is_avail(&descs[avail_idx + 3], wrap_counter)))
+		return 1;
+
+	if (unlikely((descs[avail_idx].flags & DESC_SINGLE_DEQUEUE) |
+		(descs[avail_idx + 1].flags & DESC_SINGLE_DEQUEUE) |
+		(descs[avail_idx + 2].flags & DESC_SINGLE_DEQUEUE) |
+		(descs[avail_idx + 3].flags & DESC_SINGLE_DEQUEUE)))
+		return -1;
+
+	rte_smp_rmb();
+
+	len = descs[avail_idx].len;
+	len1 = descs[avail_idx + 1].len;
+	len2 = descs[avail_idx + 2].len;
+	len3 = descs[avail_idx + 3].len;
+
+	desc_addr[0] = vhost_iova_to_vva(dev, vq, descs[avail_idx].addr, &len,
+					 VHOST_ACCESS_RW);
+
+	desc_addr[1] = vhost_iova_to_vva(dev, vq, descs[avail_idx + 1].addr,
+					 &len1, VHOST_ACCESS_RW);
+
+	desc_addr[2] = vhost_iova_to_vva(dev, vq, descs[avail_idx + 2].addr,
+					 &len2, VHOST_ACCESS_RW);
+
+	desc_addr[3] = vhost_iova_to_vva(dev, vq, descs[avail_idx + 3].addr,
+					 &len3, VHOST_ACCESS_RW);
+
+	if (unlikely((len != descs[avail_idx].len) |
+		(len1 != descs[avail_idx + 1].len) |
+		(len2 != descs[avail_idx + 2].len) |
+		(len3 != descs[avail_idx + 3].len))) {
+		return -1;
+	}
+
+	if (rte_pktmbuf_alloc_bulk(mbuf_pool, pkts, PACKED_DESCS_BURST))
+		return -1;
+
+	buf_len = pkts[0]->buf_len - pkts[0]->data_off;
+	buf_len1 = pkts[1]->buf_len - pkts[1]->data_off;
+	buf_len2 = pkts[2]->buf_len - pkts[2]->data_off;
+	buf_len3 = pkts[3]->buf_len - pkts[3]->data_off;
+
+	if (unlikely((buf_len < (len - buf_offset)) |
+		(buf_len1 < (len1 - buf_offset)) |
+		(buf_len2 < (len2 - buf_offset)) |
+		(buf_len3 < (len3 - buf_offset)))) {
+		rte_pktmbuf_free(pkts[0]);
+		rte_pktmbuf_free(pkts[1]);
+		rte_pktmbuf_free(pkts[2]);
+		rte_pktmbuf_free(pkts[3]);
+		return -1;
+	}
+
+	pkts[0]->pkt_len = descs[avail_idx].len - buf_offset;
+	pkts[1]->pkt_len = descs[avail_idx + 1].len - buf_offset;
+	pkts[2]->pkt_len = descs[avail_idx + 2].len - buf_offset;
+	pkts[3]->pkt_len = descs[avail_idx + 3].len - buf_offset;
+
+	pkts[0]->data_len = pkts[0]->pkt_len;
+	pkts[1]->data_len = pkts[1]->pkt_len;
+	pkts[2]->data_len = pkts[2]->pkt_len;
+	pkts[3]->data_len = pkts[3]->pkt_len;
+
+	ids[0] = descs[avail_idx].id;
+	ids[1] = descs[avail_idx + 1].id;
+	ids[2] = descs[avail_idx + 2].id;
+	ids[3] = descs[avail_idx + 3].id;
+
+	return 0;
+}
+
+static __rte_unused int
+virtio_dev_tx_burst_packed(struct virtio_net *dev, struct vhost_virtqueue *vq,
+	struct rte_mempool *mbuf_pool, struct rte_mbuf **pkts)
+{
+	uint16_t avail_idx = vq->last_avail_idx;
+	uint32_t buf_offset = dev->vhost_hlen;
+	uintptr_t desc_addr[4];
+	uint16_t ids[4];
+	int ret;
+	struct virtio_net_hdr *hdr, *hdr1, *hdr2, *hdr3;
+
+	ret = vhost_dequeue_burst_packed(dev, vq, mbuf_pool, pkts, avail_idx,
+					 desc_addr, ids);
+
+	if (ret)
+		return ret;
+
+	rte_prefetch0((void *)(uintptr_t)desc_addr[0]);
+	rte_prefetch0((void *)(uintptr_t)desc_addr[1]);
+	rte_prefetch0((void *)(uintptr_t)desc_addr[2]);
+	rte_prefetch0((void *)(uintptr_t)desc_addr[3]);
+
+	rte_memcpy(rte_pktmbuf_mtod_offset(pkts[0], void *, 0),
+		(void *)(uintptr_t)(desc_addr[0] + buf_offset),
+		pkts[0]->pkt_len);
+	rte_memcpy(rte_pktmbuf_mtod_offset(pkts[1], void *, 0),
+		(void *)(uintptr_t)(desc_addr[1] + buf_offset),
+		pkts[1]->pkt_len);
+	rte_memcpy(rte_pktmbuf_mtod_offset(pkts[2], void *, 0),
+		(void *)(uintptr_t)(desc_addr[2] + buf_offset),
+		pkts[2]->pkt_len);
+	rte_memcpy(rte_pktmbuf_mtod_offset(pkts[3], void *, 0),
+		(void *)(uintptr_t)(desc_addr[3] + buf_offset),
+		pkts[3]->pkt_len);
+
+	if (virtio_net_with_host_offload(dev)) {
+		hdr = (struct virtio_net_hdr *)((uintptr_t)desc_addr[0]);
+		hdr1 = (struct virtio_net_hdr *)((uintptr_t)desc_addr[1]);
+		hdr2 = (struct virtio_net_hdr *)((uintptr_t)desc_addr[2]);
+		hdr3 = (struct virtio_net_hdr *)((uintptr_t)desc_addr[3]);
+		vhost_dequeue_offload(hdr, pkts[0]);
+		vhost_dequeue_offload(hdr1, pkts[1]);
+		vhost_dequeue_offload(hdr2, pkts[2]);
+		vhost_dequeue_offload(hdr3, pkts[3]);
+	}
+
+	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_always_inline int
 vhost_dequeue_single_packed(struct virtio_net *dev, struct vhost_virtqueue *vq,
 	struct rte_mempool *mbuf_pool, struct rte_mbuf **pkts, uint16_t *buf_id,
-- 
2.17.1