[dpdk-dev] [PATCH v8 2/4] vhost: add unsafe API to clear packets in async vhost

[Cheng Jiang <cheng1.jiang@intel.com>]

Applications need to stop DMA transfers and finish all the inflight
packets when in VM memory hot-plug case and async vhost is used. This
patch is to provide an unsafe API to clear inflight packets which
are submitted to DMA engine in vhost async data path. Update the
program guide and release notes for virtqueue inflight packets clear
API in vhost lib.

Signed-off-by: Cheng Jiang <cheng1.jiang@intel.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
---
 doc/guides/prog_guide/vhost_lib.rst    |  5 ++
 doc/guides/rel_notes/release_21_08.rst |  5 ++
 lib/vhost/rte_vhost_async.h            | 22 ++++++
 lib/vhost/version.map                  |  1 +
 lib/vhost/virtio_net.c                 | 93 +++++++++++++++++++-------
 5 files changed, 102 insertions(+), 24 deletions(-)

diff --git a/doc/guides/prog_guide/vhost_lib.rst b/doc/guides/prog_guide/vhost_lib.rst
index 70ce4974df..8874033165 100644
--- a/doc/guides/prog_guide/vhost_lib.rst
+++ b/doc/guides/prog_guide/vhost_lib.rst
@@ -305,6 +305,11 @@ The following is an overview of some key Vhost API functions:
   This function returns the amount of in-flight packets for the vhost
   queue using async acceleration.
 
+* ``rte_vhost_clear_queue_thread_unsafe(vid, queue_id, **pkts, count)``
+
+  Clear inflight packets which are submitted to DMA engine in vhost async data
+  path. Completed packets are returned to applications through ``pkts``.
+
 Vhost-user Implementations
 --------------------------
 
diff --git a/doc/guides/rel_notes/release_21_08.rst b/doc/guides/rel_notes/release_21_08.rst
index 543e93ff1d..d9c4cc5df0 100644
--- a/doc/guides/rel_notes/release_21_08.rst
+++ b/doc/guides/rel_notes/release_21_08.rst
@@ -155,6 +155,11 @@ New Features
   The experimental PMD power management API now supports managing
   multiple Ethernet Rx queues per lcore.
 
+* **Added inflight packets clear API in vhost library.**
+
+  Added an API which can clear the inflight packets submitted to DMA
+  engine in vhost async data path.
+
 
 Removed Items
 -------------
diff --git a/lib/vhost/rte_vhost_async.h b/lib/vhost/rte_vhost_async.h
index 02d012ae23..b25ff446f7 100644
--- a/lib/vhost/rte_vhost_async.h
+++ b/lib/vhost/rte_vhost_async.h
@@ -246,4 +246,26 @@ uint16_t rte_vhost_poll_enqueue_completed(int vid, uint16_t queue_id,
 __rte_experimental
 int rte_vhost_async_get_inflight(int vid, uint16_t queue_id);
 
+/**
+ * This function checks async completion status and clear packets for
+ * a specific vhost device queue. Packets which are inflight will be
+ * returned in an array.
+ *
+ * @note This function does not perform any locking
+ *
+ * @param vid
+ *  ID of vhost device to clear data
+ * @param queue_id
+ *  Queue id to clear data
+ * @param pkts
+ *  Blank array to get return packet pointer
+ * @param count
+ *  Size of the packet array
+ * @return
+ *  Number of packets returned
+ */
+__rte_experimental
+uint16_t rte_vhost_clear_queue_thread_unsafe(int vid, uint16_t queue_id,
+		struct rte_mbuf **pkts, uint16_t count);
+
 #endif /* _RTE_VHOST_ASYNC_H_ */
diff --git a/lib/vhost/version.map b/lib/vhost/version.map
index e0c89646e8..e2504ba657 100644
--- a/lib/vhost/version.map
+++ b/lib/vhost/version.map
@@ -84,4 +84,5 @@ EXPERIMENTAL {
 	rte_vhost_async_get_inflight;
 	rte_vhost_async_channel_register_thread_unsafe;
 	rte_vhost_async_channel_unregister_thread_unsafe;
+	rte_vhost_clear_queue_thread_unsafe;
 };
diff --git a/lib/vhost/virtio_net.c b/lib/vhost/virtio_net.c
index 3ab5229f76..8549afbbe1 100644
--- a/lib/vhost/virtio_net.c
+++ b/lib/vhost/virtio_net.c
@@ -2214,10 +2214,10 @@ write_back_completed_descs_packed(struct vhost_virtqueue *vq,
 	} while (nr_left > 0);
 }
 
-uint16_t rte_vhost_poll_enqueue_completed(int vid, uint16_t queue_id,
+static __rte_always_inline uint16_t
+vhost_poll_enqueue_completed(struct virtio_net *dev, uint16_t queue_id,
 		struct rte_mbuf **pkts, uint16_t count)
 {
-	struct virtio_net *dev = get_device(vid);
 	struct vhost_virtqueue *vq;
 	uint16_t n_pkts_cpl = 0, n_pkts_put = 0, n_descs = 0, n_buffers = 0;
 	uint16_t start_idx, pkts_idx, vq_size;
@@ -2225,26 +2225,8 @@ uint16_t rte_vhost_poll_enqueue_completed(int vid, uint16_t queue_id,
 	uint16_t from, i;
 	int32_t n_cpl;
 
-	if (!dev)
-		return 0;
-
-	VHOST_LOG_DATA(DEBUG, "(%d) %s\n", dev->vid, __func__);
-	if (unlikely(!is_valid_virt_queue_idx(queue_id, 0, dev->nr_vring))) {
-		VHOST_LOG_DATA(ERR, "(%d) %s: invalid virtqueue idx %d.\n",
-			dev->vid, __func__, queue_id);
-		return 0;
-	}
-
 	vq = dev->virtqueue[queue_id];
 
-	if (unlikely(!vq->async_registered)) {
-		VHOST_LOG_DATA(ERR, "(%d) %s: async not registered for queue id %d.\n",
-			dev->vid, __func__, queue_id);
-		return 0;
-	}
-
-	rte_spinlock_lock(&vq->access_lock);
-
 	pkts_idx = vq->async_pkts_idx % vq->size;
 	pkts_info = vq->async_pkts_info;
 	vq_size = vq->size;
@@ -2252,7 +2234,7 @@ uint16_t rte_vhost_poll_enqueue_completed(int vid, uint16_t queue_id,
 		vq_size, vq->async_pkts_inflight_n);
 
 	if (count > vq->async_last_pkts_n) {
-		n_cpl = vq->async_ops.check_completed_copies(vid,
+		n_cpl = vq->async_ops.check_completed_copies(dev->vid,
 			queue_id, 0, count - vq->async_last_pkts_n);
 		if (n_cpl >= 0) {
 			n_pkts_cpl = n_cpl;
@@ -2268,7 +2250,7 @@ uint16_t rte_vhost_poll_enqueue_completed(int vid, uint16_t queue_id,
 	n_pkts_put = RTE_MIN(count, n_pkts_cpl);
 	if (unlikely(n_pkts_put == 0)) {
 		vq->async_last_pkts_n = n_pkts_cpl;
-		goto done;
+		return 0;
 	}
 
 	if (vq_is_packed(dev)) {
@@ -2310,10 +2292,73 @@ uint16_t rte_vhost_poll_enqueue_completed(int vid, uint16_t queue_id,
 		}
 	}
 
-done:
+	return n_pkts_put;
+}
+
+uint16_t
+rte_vhost_poll_enqueue_completed(int vid, uint16_t queue_id,
+		struct rte_mbuf **pkts, uint16_t count)
+{
+	struct virtio_net *dev = get_device(vid);
+	struct vhost_virtqueue *vq;
+	uint16_t n_pkts_cpl = 0;
+
+	if (!dev)
+		return 0;
+
+	VHOST_LOG_DATA(DEBUG, "(%d) %s\n", dev->vid, __func__);
+	if (unlikely(!is_valid_virt_queue_idx(queue_id, 0, dev->nr_vring))) {
+		VHOST_LOG_DATA(ERR, "(%d) %s: invalid virtqueue idx %d.\n",
+			dev->vid, __func__, queue_id);
+		return 0;
+	}
+
+	vq = dev->virtqueue[queue_id];
+
+	if (unlikely(!vq->async_registered)) {
+		VHOST_LOG_DATA(ERR, "(%d) %s: async not registered for queue id %d.\n",
+			dev->vid, __func__, queue_id);
+		return 0;
+	}
+
+	rte_spinlock_lock(&vq->access_lock);
+
+	n_pkts_cpl = vhost_poll_enqueue_completed(dev, queue_id, pkts, count);
+
 	rte_spinlock_unlock(&vq->access_lock);
 
-	return n_pkts_put;
+	return n_pkts_cpl;
+}
+
+uint16_t
+rte_vhost_clear_queue_thread_unsafe(int vid, uint16_t queue_id,
+		struct rte_mbuf **pkts, uint16_t count)
+{
+	struct virtio_net *dev = get_device(vid);
+	struct vhost_virtqueue *vq;
+	uint16_t n_pkts_cpl = 0;
+
+	if (!dev)
+		return 0;
+
+	VHOST_LOG_DATA(DEBUG, "(%d) %s\n", dev->vid, __func__);
+	if (unlikely(!is_valid_virt_queue_idx(queue_id, 0, dev->nr_vring))) {
+		VHOST_LOG_DATA(ERR, "(%d) %s: invalid virtqueue idx %d.\n",
+			dev->vid, __func__, queue_id);
+		return 0;
+	}
+
+	vq = dev->virtqueue[queue_id];
+
+	if (unlikely(!vq->async_registered)) {
+		VHOST_LOG_DATA(ERR, "(%d) %s: async not registered for queue id %d.\n",
+			dev->vid, __func__, queue_id);
+		return 0;
+	}
+
+	n_pkts_cpl = vhost_poll_enqueue_completed(dev, queue_id, pkts, count);
+
+	return n_pkts_cpl;
 }
 
 static __rte_always_inline uint32_t
-- 
2.29.2