[dpdk-dev] [PATCH v7 4/9] net/virtio-user: add vectorized path parameter

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

Add new parameter "vectorized" which can select vectorized path
explicitly. This parameter will work when RTE_LIBRTE_VIRTIO_INC_VECTOR
option is yes. When "vectorized" is set, driver will check both
compiling environment and running environment when selecting path.

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 37766cbb6..361c834a9 100644
--- a/drivers/net/virtio/virtio_ethdev.c
+++ b/drivers/net/virtio/virtio_ethdev.c
@@ -1551,8 +1551,8 @@ set_rxtx_funcs(struct rte_eth_dev *eth_dev)
 			eth_dev->rx_pkt_burst = &virtio_recv_pkts_packed;
 		}
 	} else {
-		if (hw->use_simple_rx) {
-			PMD_INIT_LOG(INFO, "virtio: using simple Rx path on port %u",
+		if (hw->use_vec_rx) {
+			PMD_INIT_LOG(INFO, "virtio: using vectorized Rx path on port %u",
 				eth_dev->data->port_id);
 			eth_dev->rx_pkt_burst = virtio_recv_pkts_vec;
 		} else if (hw->use_inorder_rx) {
@@ -2257,33 +2257,33 @@ virtio_dev_configure(struct rte_eth_dev *dev)
 			return -EBUSY;
 		}
 
-	hw->use_simple_rx = 1;
+	hw->use_vec_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 bd89357e4..668e688e1 100644
--- a/drivers/net/virtio/virtio_pci.h
+++ b/drivers/net/virtio/virtio_pci.h
@@ -253,7 +253,8 @@ 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 e450477e8..84f4cf946 100644
--- a/drivers/net/virtio/virtio_rxtx.c
+++ b/drivers/net/virtio/virtio_rxtx.c
@@ -996,7 +996,7 @@ 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 && !vtpci_packed_queue(hw)) {
 		for (desc_idx = 0; desc_idx < vq->vq_nentries;
 		     desc_idx++) {
 			vq->vq_split.ring.avail->ring[desc_idx] = desc_idx;
@@ -1014,7 +1014,7 @@ 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 && !vtpci_packed_queue(hw)) {
 		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 953f00d72..5c338cf44 100644
--- a/drivers/net/virtio/virtio_user_ethdev.c
+++ b/drivers/net/virtio/virtio_user_ethdev.c
@@ -452,6 +452,8 @@ static const char *valid_args[] = {
 	VIRTIO_USER_ARG_PACKED_VQ,
 #define VIRTIO_USER_ARG_SPEED          "speed"
 	VIRTIO_USER_ARG_SPEED,
+#define VIRTIO_USER_ARG_VECTORIZED     "vectorized"
+	VIRTIO_USER_ARG_VECTORIZED,
 	NULL
 };
 
@@ -525,7 +527,8 @@ 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;
@@ -559,6 +562,7 @@ 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;
@@ -675,6 +679,17 @@ 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;
@@ -727,6 +742,23 @@ 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;
+		}
+	} else {
+		hw->use_vec_rx = 0;
+		hw->use_vec_tx = 0;
+	}
+
 	rte_eth_dev_probing_finish(eth_dev);
 	ret = 0;
 
@@ -785,4 +817,5 @@ RTE_PMD_REGISTER_PARAM_STRING(net_virtio_user,
 	"mrg_rxbuf=<0|1> "
 	"in_order=<0|1> "
 	"packed_vq=<0|1> "
-	"speed=<int>");
+	"speed=<int> "
+	"vectorized=<0|1>");
diff --git a/drivers/net/virtio/virtqueue.c b/drivers/net/virtio/virtqueue.c
index 0b4e3bf3e..ca23180de 100644
--- a/drivers/net/virtio/virtqueue.c
+++ b/drivers/net/virtio/virtqueue.c
@@ -32,7 +32,8 @@ 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 && !vtpci_packed_queue(hw) &&
+		    type == VTNET_RQ) {
 			if (start <= end && idx >= start && idx < end)
 				continue;
 			if (start > end && (idx >= start || idx < end))
@@ -97,7 +98,7 @@ 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 +122,7 @@ 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