[dpdk-dev] [PATCH v4 2/8] net/virtio-user: add vectorized datapath parameter

[Marvin Liu <yong.liu@intel.com>]

Add new parameter "vectorized" which can enable vectorized datapath
explicitly. This parameter will work for both split ring and packed
ring. When "vectorized" option is on, driver will check both compiling
environment and running enviornment.

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

diff --git a/drivers/net/virtio/virtio_ethdev.c b/drivers/net/virtio/virtio_ethdev.c
index f9d0ea70d..19a36ad82 100644
--- a/drivers/net/virtio/virtio_ethdev.c
+++ b/drivers/net/virtio/virtio_ethdev.c
@@ -1547,7 +1547,7 @@ set_rxtx_funcs(struct rte_eth_dev *eth_dev)
 			eth_dev->rx_pkt_burst = &virtio_recv_pkts_packed;
 		}
 	} else {
-		if (hw->use_simple_rx) {
+		if (hw->use_vec_rx) {
 			PMD_INIT_LOG(INFO, "virtio: using simple Rx path on port %u",
 				eth_dev->data->port_id);
 			eth_dev->rx_pkt_burst = virtio_recv_pkts_vec;
@@ -2157,33 +2157,31 @@ virtio_dev_configure(struct rte_eth_dev *dev)
 			return -EBUSY;
 		}
 
-	hw->use_simple_rx = 1;
-
 	if (vtpci_with_feature(hw, VIRTIO_F_IN_ORDER)) {
 		hw->use_inorder_tx = 1;
 		hw->use_inorder_rx = 1;
-		hw->use_simple_rx = 0;
+		hw->use_vec_rx = 0;
 	}
 
 	if (vtpci_packed_queue(hw)) {
-		hw->use_simple_rx = 0;
+		hw->use_vec_rx = 0;
 		hw->use_inorder_rx = 0;
 	}
 
 #if defined RTE_ARCH_ARM64 || defined RTE_ARCH_ARM
 	if (!rte_cpu_get_flag_enabled(RTE_CPUFLAG_NEON)) {
-		hw->use_simple_rx = 0;
+		hw->use_vec_rx = 0;
 	}
 #endif
 	if (vtpci_with_feature(hw, VIRTIO_NET_F_MRG_RXBUF)) {
-		 hw->use_simple_rx = 0;
+		 hw->use_vec_rx = 0;
 	}
 
 	if (rx_offloads & (DEV_RX_OFFLOAD_UDP_CKSUM |
 			   DEV_RX_OFFLOAD_TCP_CKSUM |
 			   DEV_RX_OFFLOAD_TCP_LRO |
 			   DEV_RX_OFFLOAD_VLAN_STRIP))
-		hw->use_simple_rx = 0;
+		hw->use_vec_rx = 0;
 
 	return 0;
 }
diff --git a/drivers/net/virtio/virtio_pci.h b/drivers/net/virtio/virtio_pci.h
index 7433d2f08..36afed313 100644
--- a/drivers/net/virtio/virtio_pci.h
+++ b/drivers/net/virtio/virtio_pci.h
@@ -250,7 +250,8 @@ struct virtio_hw {
 	uint8_t	    vlan_strip;
 	uint8_t	    use_msix;
 	uint8_t     modern;
-	uint8_t     use_simple_rx;
+	uint8_t     use_vec_rx;
+	uint8_t     use_vec_tx;
 	uint8_t     use_inorder_rx;
 	uint8_t     use_inorder_tx;
 	uint8_t     weak_barriers;
diff --git a/drivers/net/virtio/virtio_rxtx.c b/drivers/net/virtio/virtio_rxtx.c
index 3a2dbc2e0..285af1d47 100644
--- a/drivers/net/virtio/virtio_rxtx.c
+++ b/drivers/net/virtio/virtio_rxtx.c
@@ -995,7 +995,7 @@ virtio_dev_rx_queue_setup_finish(struct rte_eth_dev *dev, uint16_t queue_idx)
 	/* Allocate blank mbufs for the each rx descriptor */
 	nbufs = 0;
 
-	if (hw->use_simple_rx) {
+	if (hw->use_vec_rx) {
 		for (desc_idx = 0; desc_idx < vq->vq_nentries;
 		     desc_idx++) {
 			vq->vq_split.ring.avail->ring[desc_idx] = desc_idx;
@@ -1013,7 +1013,7 @@ virtio_dev_rx_queue_setup_finish(struct rte_eth_dev *dev, uint16_t queue_idx)
 			&rxvq->fake_mbuf;
 	}
 
-	if (hw->use_simple_rx) {
+	if (hw->use_vec_rx) {
 		while (vq->vq_free_cnt >= RTE_VIRTIO_VPMD_RX_REARM_THRESH) {
 			virtio_rxq_rearm_vec(rxvq);
 			nbufs += RTE_VIRTIO_VPMD_RX_REARM_THRESH;
diff --git a/drivers/net/virtio/virtio_user_ethdev.c b/drivers/net/virtio/virtio_user_ethdev.c
index e61af4068..ca7797cfa 100644
--- a/drivers/net/virtio/virtio_user_ethdev.c
+++ b/drivers/net/virtio/virtio_user_ethdev.c
@@ -450,6 +450,8 @@ static const char *valid_args[] = {
 	VIRTIO_USER_ARG_IN_ORDER,
 #define VIRTIO_USER_ARG_PACKED_VQ      "packed_vq"
 	VIRTIO_USER_ARG_PACKED_VQ,
+#define VIRTIO_USER_ARG_VECTORIZED     "vectorized"
+	VIRTIO_USER_ARG_VECTORIZED,
 	NULL
 };
 
@@ -518,7 +520,8 @@ virtio_user_eth_dev_alloc(struct rte_vdev_device *vdev)
 	 */
 	hw->use_msix = 1;
 	hw->modern   = 0;
-	hw->use_simple_rx = 0;
+	hw->use_vec_rx = 0;
+	hw->use_vec_tx = 0;
 	hw->use_inorder_rx = 0;
 	hw->use_inorder_tx = 0;
 	hw->virtio_user_dev = dev;
@@ -552,6 +555,8 @@ virtio_user_pmd_probe(struct rte_vdev_device *dev)
 	uint64_t mrg_rxbuf = 1;
 	uint64_t in_order = 1;
 	uint64_t packed_vq = 0;
+	uint64_t vectorized = 0;
+
 	char *path = NULL;
 	char *ifname = NULL;
 	char *mac_addr = NULL;
@@ -668,6 +673,17 @@ virtio_user_pmd_probe(struct rte_vdev_device *dev)
 		}
 	}
 
+#ifdef RTE_LIBRTE_VIRTIO_INC_VECTOR
+	if (rte_kvargs_count(kvlist, VIRTIO_USER_ARG_VECTORIZED) == 1) {
+		if (rte_kvargs_process(kvlist, VIRTIO_USER_ARG_VECTORIZED,
+				       &get_integer_arg, &vectorized) < 0) {
+			PMD_INIT_LOG(ERR, "error to parse %s",
+				     VIRTIO_USER_ARG_VECTORIZED);
+			goto end;
+		}
+	}
+#endif
+
 	if (queues > 1 && cq == 0) {
 		PMD_INIT_LOG(ERR, "multi-q requires ctrl-q");
 		goto end;
@@ -705,6 +721,7 @@ virtio_user_pmd_probe(struct rte_vdev_device *dev)
 	}
 
 	hw = eth_dev->data->dev_private;
+
 	if (virtio_user_dev_init(hw->virtio_user_dev, path, queues, cq,
 			 queue_size, mac_addr, &ifname, server_mode,
 			 mrg_rxbuf, in_order, packed_vq) < 0) {
@@ -720,6 +737,20 @@ virtio_user_pmd_probe(struct rte_vdev_device *dev)
 		goto end;
 	}
 
+	if (vectorized) {
+		if (packed_vq) {
+#if defined(CC_AVX512_SUPPORT)
+			hw->use_vec_rx = 1;
+			hw->use_vec_tx = 1;
+#else
+			PMD_INIT_LOG(INFO,
+				"building environment do not match packed ring vectorized requirement");
+#endif
+		} else {
+			hw->use_vec_rx = 1;
+		}
+	}
+
 	rte_eth_dev_probing_finish(eth_dev);
 	ret = 0;
 
@@ -777,4 +808,5 @@ RTE_PMD_REGISTER_PARAM_STRING(net_virtio_user,
 	"server=<0|1> "
 	"mrg_rxbuf=<0|1> "
 	"in_order=<0|1> "
-	"packed_vq=<0|1>");
+	"packed_vq=<0|1>"
+	"vectorized=<0|1>");
diff --git a/drivers/net/virtio/virtqueue.c b/drivers/net/virtio/virtqueue.c
index 0b4e3bf3e..349ff0c9d 100644
--- a/drivers/net/virtio/virtqueue.c
+++ b/drivers/net/virtio/virtqueue.c
@@ -32,7 +32,7 @@ virtqueue_detach_unused(struct virtqueue *vq)
 	end = (vq->vq_avail_idx + vq->vq_free_cnt) & (vq->vq_nentries - 1);
 
 	for (idx = 0; idx < vq->vq_nentries; idx++) {
-		if (hw->use_simple_rx && type == VTNET_RQ) {
+		if (hw->use_vec_rx && type == VTNET_RQ) {
 			if (start <= end && idx >= start && idx < end)
 				continue;
 			if (start > end && (idx >= start || idx < end))
@@ -97,7 +97,7 @@ virtqueue_rxvq_flush_split(struct virtqueue *vq)
 	for (i = 0; i < nb_used; i++) {
 		used_idx = vq->vq_used_cons_idx & (vq->vq_nentries - 1);
 		uep = &vq->vq_split.ring.used->ring[used_idx];
-		if (hw->use_simple_rx) {
+		if (hw->use_vec_rx) {
 			desc_idx = used_idx;
 			rte_pktmbuf_free(vq->sw_ring[desc_idx]);
 			vq->vq_free_cnt++;
@@ -121,7 +121,7 @@ virtqueue_rxvq_flush_split(struct virtqueue *vq)
 		vq->vq_used_cons_idx++;
 	}
 
-	if (hw->use_simple_rx) {
+	if (hw->use_vec_rx) {
 		while (vq->vq_free_cnt >= RTE_VIRTIO_VPMD_RX_REARM_THRESH) {
 			virtio_rxq_rearm_vec(rxq);
 			if (virtqueue_kick_prepare(vq))
-- 
2.17.1