[dpdk-dev] [PATCH v8 2/4] example/vhost: add support for vhost async data path

[Cheng Jiang <Cheng1.jiang@intel.com>]

This patch is to implement vhost DMA operation callbacks for CBDMA
PMD and add vhost async data-path in vhost sample. With providing
callback implementation for CBDMA, vswitch can leverage IOAT to
accelerate vhost async data-path.

Signed-off-by: Cheng Jiang <Cheng1.jiang@intel.com>
---
 examples/vhost/ioat.c | 100 ++++++++++++++++++++++++++++++++++++++++++
 examples/vhost/main.c |  57 +++++++++++++++++++++++-
 examples/vhost/main.h |  12 +++++
 3 files changed, 168 insertions(+), 1 deletion(-)

diff --git a/examples/vhost/ioat.c b/examples/vhost/ioat.c
index c3158d3c3..fa503c3db 100644
--- a/examples/vhost/ioat.c
+++ b/examples/vhost/ioat.c
@@ -6,11 +6,13 @@
 #include <rte_rawdev.h>
 #include <rte_ioat_rawdev.h>
 #include <rte_pci.h>
+#include <sys/uio.h>
 
 #include "main.h"
 
 #define MAX_VHOST_DEVICE 1024
 #define IOAT_RING_SIZE 4096
+#define MAX_ENQUEUED_SIZE 256
 
 struct dma_info {
 	struct rte_pci_addr addr;
@@ -25,6 +27,15 @@ struct dma_for_vhost {
 
 struct dma_for_vhost dma_bind[MAX_VHOST_DEVICE];
 
+struct packet_tracker {
+	unsigned short size_track[MAX_ENQUEUED_SIZE];
+	unsigned short next_read;
+	unsigned short next_write;
+	unsigned short last_remain;
+};
+
+struct packet_tracker cb_tracker[MAX_VHOST_DEVICE];
+
 int
 open_ioat(const char *value)
 {
@@ -115,3 +126,92 @@ open_ioat(const char *value)
 	free(input);
 	return ret;
 }
+
+uint32_t
+ioat_transfer_data_cb(int vid, uint16_t queue_id,
+		struct rte_vhost_async_desc *descs,
+		struct rte_vhost_async_status *opaque_data, uint16_t count)
+{
+	uint32_t i_desc;
+	int dev_id = dma_bind[vid].dmas[queue_id * 2 + VIRTIO_RXQ].dev_id;
+	struct rte_vhost_iov_iter *src = NULL;
+	struct rte_vhost_iov_iter *dst = NULL;
+	unsigned long i_seg;
+	unsigned short mask = MAX_ENQUEUED_SIZE - 1;
+	unsigned short write = cb_tracker[dev_id].next_write;
+
+	if (!opaque_data) {
+		for (i_desc = 0; i_desc < count; i_desc++) {
+			src = descs[i_desc].src;
+			dst = descs[i_desc].dst;
+			i_seg = 0;
+			while (i_seg < src->nr_segs) {
+				/*
+				 * TODO: Assuming that the ring space of the
+				 * IOAT device is large enough, so there is no
+				 * error here, and the actual error handling
+				 * will be added later.
+				 */
+				rte_ioat_enqueue_copy(dev_id,
+					(uintptr_t)(src->iov[i_seg].iov_base)
+						+ src->offset,
+					(uintptr_t)(dst->iov[i_seg].iov_base)
+						+ dst->offset,
+					src->iov[i_seg].iov_len,
+					0,
+					0);
+				i_seg++;
+			}
+			write &= mask;
+			cb_tracker[dev_id].size_track[write] = i_seg;
+			write++;
+		}
+	} else {
+		/* Opaque data is not supported */
+		return -1;
+	}
+	/* ring the doorbell */
+	rte_ioat_perform_ops(dev_id);
+	cb_tracker[dev_id].next_write = write;
+	return i_desc;
+}
+
+uint32_t
+ioat_check_completed_copies_cb(int vid, uint16_t queue_id,
+		struct rte_vhost_async_status *opaque_data,
+		uint16_t max_packets)
+{
+	if (!opaque_data) {
+		uintptr_t dump[255];
+		unsigned short n_seg;
+		unsigned short read, write;
+		unsigned short nb_packet = 0;
+		unsigned short mask = MAX_ENQUEUED_SIZE - 1;
+		unsigned short i;
+		int dev_id = dma_bind[vid].dmas[queue_id * 2
+				+ VIRTIO_RXQ].dev_id;
+		n_seg = rte_ioat_completed_ops(dev_id, 255, dump, dump);
+		n_seg += cb_tracker[dev_id].last_remain;
+		if (!n_seg)
+			return 0;
+		read = cb_tracker[dev_id].next_read;
+		write = cb_tracker[dev_id].next_write;
+		for (i = 0; i < max_packets; i++) {
+			read &= mask;
+			if (read == write)
+				break;
+			if (n_seg >= cb_tracker[dev_id].size_track[read]) {
+				n_seg -= cb_tracker[dev_id].size_track[read];
+				read++;
+				nb_packet++;
+			} else {
+				break;
+			}
+		}
+		cb_tracker[dev_id].next_read = read;
+		cb_tracker[dev_id].last_remain = n_seg;
+		return nb_packet;
+	}
+	/* Opaque data is not supported */
+	return -1;
+}
diff --git a/examples/vhost/main.c b/examples/vhost/main.c
index d759cae2c..896f5f781 100644
--- a/examples/vhost/main.c
+++ b/examples/vhost/main.c
@@ -804,9 +804,22 @@ virtio_xmit(struct vhost_dev *dst_vdev, struct vhost_dev *src_vdev,
 	    struct rte_mbuf *m)
 {
 	uint16_t ret;
+	struct rte_mbuf *m_cpl[1];
 
 	if (builtin_net_driver) {
 		ret = vs_enqueue_pkts(dst_vdev, VIRTIO_RXQ, &m, 1);
+	} else if (async_vhost_driver) {
+		ret = rte_vhost_submit_enqueue_burst(dst_vdev->vid, VIRTIO_RXQ,
+						&m, 1);
+
+		if (likely(ret))
+			dst_vdev->nr_async_pkts++;
+
+		while (likely(dst_vdev->nr_async_pkts)) {
+			if (rte_vhost_poll_enqueue_completed(dst_vdev->vid,
+					VIRTIO_RXQ, m_cpl, 1))
+				dst_vdev->nr_async_pkts--;
+		}
 	} else {
 		ret = rte_vhost_enqueue_burst(dst_vdev->vid, VIRTIO_RXQ, &m, 1);
 	}
@@ -1055,6 +1068,19 @@ drain_mbuf_table(struct mbuf_table *tx_q)
 	}
 }
 
+static __rte_always_inline void
+complete_async_pkts(struct vhost_dev *vdev, uint16_t qid)
+{
+	struct rte_mbuf *p_cpl[MAX_PKT_BURST];
+	uint16_t complete_count;
+
+	complete_count = rte_vhost_poll_enqueue_completed(vdev->vid,
+						qid, p_cpl, MAX_PKT_BURST);
+	vdev->nr_async_pkts -= complete_count;
+	if (complete_count)
+		free_pkts(p_cpl, complete_count);
+}
+
 static __rte_always_inline void
 drain_eth_rx(struct vhost_dev *vdev)
 {
@@ -1063,6 +1089,10 @@ drain_eth_rx(struct vhost_dev *vdev)
 
 	rx_count = rte_eth_rx_burst(ports[0], vdev->vmdq_rx_q,
 				    pkts, MAX_PKT_BURST);
+
+	while (likely(vdev->nr_async_pkts))
+		complete_async_pkts(vdev, VIRTIO_RXQ);
+
 	if (!rx_count)
 		return;
 
@@ -1087,16 +1117,22 @@ drain_eth_rx(struct vhost_dev *vdev)
 	if (builtin_net_driver) {
 		enqueue_count = vs_enqueue_pkts(vdev, VIRTIO_RXQ,
 						pkts, rx_count);
+	} else if (async_vhost_driver) {
+		enqueue_count = rte_vhost_submit_enqueue_burst(vdev->vid,
+					VIRTIO_RXQ, pkts, rx_count);
+		vdev->nr_async_pkts += enqueue_count;
 	} else {
 		enqueue_count = rte_vhost_enqueue_burst(vdev->vid, VIRTIO_RXQ,
 						pkts, rx_count);
 	}
+
 	if (enable_stats) {
 		rte_atomic64_add(&vdev->stats.rx_total_atomic, rx_count);
 		rte_atomic64_add(&vdev->stats.rx_atomic, enqueue_count);
 	}
 
-	free_pkts(pkts, rx_count);
+	if (!async_vhost_driver)
+		free_pkts(pkts, rx_count);
 }
 
 static __rte_always_inline void
@@ -1243,6 +1279,9 @@ destroy_device(int vid)
 		"(%d) device has been removed from data core\n",
 		vdev->vid);
 
+	if (async_vhost_driver)
+		rte_vhost_async_channel_unregister(vid, VIRTIO_RXQ);
+
 	rte_free(vdev);
 }
 
@@ -1257,6 +1296,12 @@ new_device(int vid)
 	uint32_t device_num_min = num_devices;
 	struct vhost_dev *vdev;
 
+	struct rte_vhost_async_channel_ops channel_ops = {
+		.transfer_data = ioat_transfer_data_cb,
+		.check_completed_copies = ioat_check_completed_copies_cb
+	};
+	struct rte_vhost_async_features f;
+
 	vdev = rte_zmalloc("vhost device", sizeof(*vdev), RTE_CACHE_LINE_SIZE);
 	if (vdev == NULL) {
 		RTE_LOG(INFO, VHOST_DATA,
@@ -1297,6 +1342,13 @@ new_device(int vid)
 		"(%d) device has been added to data core %d\n",
 		vid, vdev->coreid);
 
+	if (async_vhost_driver) {
+		f.async_inorder = 1;
+		f.async_threshold = 256;
+		return rte_vhost_async_channel_register(vid, VIRTIO_RXQ,
+			f.intval, &channel_ops);
+	}
+
 	return 0;
 }
 
@@ -1535,6 +1587,9 @@ main(int argc, char *argv[])
 	/* Register vhost user driver to handle vhost messages. */
 	for (i = 0; i < nb_sockets; i++) {
 		char *file = socket_files + i * PATH_MAX;
+		if (async_vhost_driver)
+			flags = flags | RTE_VHOST_USER_ASYNC_COPY;
+
 		ret = rte_vhost_driver_register(file, flags);
 		if (ret != 0) {
 			unregister_drivers(i);
diff --git a/examples/vhost/main.h b/examples/vhost/main.h
index fe83d255b..5a628473e 100644
--- a/examples/vhost/main.h
+++ b/examples/vhost/main.h
@@ -8,6 +8,7 @@
 #include <sys/queue.h>
 
 #include <rte_ether.h>
+#include <rte_vhost_async.h>
 
 /* Macros for printing using RTE_LOG */
 #define RTE_LOGTYPE_VHOST_CONFIG RTE_LOGTYPE_USER1
@@ -51,6 +52,7 @@ struct vhost_dev {
 	uint64_t features;
 	size_t hdr_len;
 	uint16_t nr_vrings;
+	uint16_t nr_async_pkts;
 	struct rte_vhost_memory *mem;
 	struct device_statistics stats;
 	TAILQ_ENTRY(vhost_dev) global_vdev_entry;
@@ -103,4 +105,14 @@ static int open_ioat(const char *value __rte_unused)
 
 #endif
 
+uint32_t
+ioat_transfer_data_cb(int vid, uint16_t queue_id,
+		struct rte_vhost_async_desc *descs,
+		struct rte_vhost_async_status *opaque_data, uint16_t count);
+
+uint32_t
+ioat_check_completed_copies_cb(int vid, uint16_t queue_id,
+		struct rte_vhost_async_status *opaque_data,
+		uint16_t max_packets);
+
 #endif /* _MAIN_H_ */
-- 
2.27.0