[RFC 13/15] vdpa/mlx5: add device close task

[Li Zhang <lizh@nvidia.com>]

Split the virtqs device close tasks after
stopping virt-queue between the configuration threads.
This accelerates the LM process and
reduces its time by 50%.

Signed-off-by: Li Zhang <lizh@nvidia.com>
---
 drivers/vdpa/mlx5/mlx5_vdpa.c         | 51 +++++++++++++++++++++++++--
 drivers/vdpa/mlx5/mlx5_vdpa.h         |  8 +++++
 drivers/vdpa/mlx5/mlx5_vdpa_cthread.c | 20 ++++++++++-
 drivers/vdpa/mlx5/mlx5_vdpa_virtq.c   | 14 ++++++++
 4 files changed, 90 insertions(+), 3 deletions(-)

diff --git a/drivers/vdpa/mlx5/mlx5_vdpa.c b/drivers/vdpa/mlx5/mlx5_vdpa.c
index 8dd8e6a2a0..d349682a83 100644
--- a/drivers/vdpa/mlx5/mlx5_vdpa.c
+++ b/drivers/vdpa/mlx5/mlx5_vdpa.c
@@ -245,7 +245,7 @@ mlx5_vdpa_mtu_set(struct mlx5_vdpa_priv *priv)
 	return kern_mtu == vhost_mtu ? 0 : -1;
 }
 
-static void
+void
 mlx5_vdpa_dev_cache_clean(struct mlx5_vdpa_priv *priv)
 {
 	/* Clean pre-created resource in dev removal only. */
@@ -254,6 +254,26 @@ mlx5_vdpa_dev_cache_clean(struct mlx5_vdpa_priv *priv)
 	mlx5_vdpa_mem_dereg(priv);
 }
 
+static bool
+mlx5_vdpa_wait_dev_close_tasks_done(struct mlx5_vdpa_priv *priv)
+{
+	uint32_t timeout = 0;
+
+	/* Check and wait all close tasks done. */
+	while (__atomic_load_n(&priv->dev_close_progress,
+		__ATOMIC_RELAXED) != 0 && timeout < 1000) {
+		rte_delay_us_sleep(10000);
+		timeout++;
+	}
+	if (priv->dev_close_progress) {
+		DRV_LOG(ERR,
+		"Failed to wait close device tasks done vid %d.",
+		priv->vid);
+		return true;
+	}
+	return false;
+}
+
 static int
 mlx5_vdpa_dev_close(int vid)
 {
@@ -271,6 +291,27 @@ mlx5_vdpa_dev_close(int vid)
 		ret |= mlx5_vdpa_lm_log(priv);
 		priv->state = MLX5_VDPA_STATE_IN_PROGRESS;
 	}
+	if (priv->use_c_thread) {
+		if (priv->last_c_thrd_idx >=
+			(conf_thread_mng.max_thrds - 1))
+			priv->last_c_thrd_idx = 0;
+		else
+			priv->last_c_thrd_idx++;
+		__atomic_store_n(&priv->dev_close_progress,
+			1, __ATOMIC_RELAXED);
+		if (mlx5_vdpa_task_add(priv,
+			priv->last_c_thrd_idx,
+			MLX5_VDPA_TASK_DEV_CLOSE_NOWAIT,
+			NULL, NULL, NULL, 1)) {
+			DRV_LOG(ERR,
+			"Fail to add dev close task. ");
+			goto single_thrd;
+		}
+		priv->state = MLX5_VDPA_STATE_PROBED;
+		DRV_LOG(INFO, "vDPA device %d was closed.", vid);
+		return ret;
+	}
+single_thrd:
 	pthread_mutex_lock(&priv->steer_update_lock);
 	mlx5_vdpa_steer_unset(priv);
 	pthread_mutex_unlock(&priv->steer_update_lock);
@@ -278,10 +319,12 @@ mlx5_vdpa_dev_close(int vid)
 	mlx5_vdpa_drain_cq(priv);
 	if (priv->lm_mr.addr)
 		mlx5_os_wrapped_mkey_destroy(&priv->lm_mr);
-	priv->state = MLX5_VDPA_STATE_PROBED;
 	if (!priv->connected)
 		mlx5_vdpa_dev_cache_clean(priv);
 	priv->vid = 0;
+	__atomic_store_n(&priv->dev_close_progress, 0,
+		__ATOMIC_RELAXED);
+	priv->state = MLX5_VDPA_STATE_PROBED;
 	DRV_LOG(INFO, "vDPA device %d was closed.", vid);
 	return ret;
 }
@@ -302,6 +345,8 @@ mlx5_vdpa_dev_config(int vid)
 		DRV_LOG(ERR, "Failed to reconfigure vid %d.", vid);
 		return -1;
 	}
+	if (mlx5_vdpa_wait_dev_close_tasks_done(priv))
+		return -1;
 	priv->vid = vid;
 	priv->connected = true;
 	if (mlx5_vdpa_mtu_set(priv))
@@ -839,6 +884,8 @@ mlx5_vdpa_dev_release(struct mlx5_vdpa_priv *priv)
 {
 	if (priv->state == MLX5_VDPA_STATE_CONFIGURED)
 		mlx5_vdpa_dev_close(priv->vid);
+	if (priv->use_c_thread)
+		mlx5_vdpa_wait_dev_close_tasks_done(priv);
 	mlx5_vdpa_release_dev_resources(priv);
 	if (priv->vdev)
 		rte_vdpa_unregister_device(priv->vdev);
diff --git a/drivers/vdpa/mlx5/mlx5_vdpa.h b/drivers/vdpa/mlx5/mlx5_vdpa.h
index e08931719f..b6392b9d66 100644
--- a/drivers/vdpa/mlx5/mlx5_vdpa.h
+++ b/drivers/vdpa/mlx5/mlx5_vdpa.h
@@ -84,6 +84,7 @@ enum mlx5_vdpa_task_type {
 	MLX5_VDPA_TASK_REG_MR = 1,
 	MLX5_VDPA_TASK_SETUP_VIRTQ,
 	MLX5_VDPA_TASK_STOP_VIRTQ,
+	MLX5_VDPA_TASK_DEV_CLOSE_NOWAIT,
 };
 
 /* Generic task information and size must be multiple of 4B. */
@@ -206,6 +207,7 @@ struct mlx5_vdpa_priv {
 	uint64_t features; /* Negotiated features. */
 	uint16_t log_max_rqt_size;
 	uint16_t last_c_thrd_idx;
+	uint16_t dev_close_progress;
 	uint16_t num_mrs; /* Number of memory regions. */
 	struct mlx5_vdpa_steer steer;
 	struct mlx5dv_var *var;
@@ -578,4 +580,10 @@ mlx5_vdpa_c_thread_wait_bulk_tasks_done(uint32_t *remaining_cnt,
 		uint32_t *err_cnt, uint32_t sleep_time);
 int
 mlx5_vdpa_virtq_setup(struct mlx5_vdpa_priv *priv, int index, bool reg_kick);
+void
+mlx5_vdpa_vq_destroy(struct mlx5_vdpa_virtq *virtq);
+void
+mlx5_vdpa_dev_cache_clean(struct mlx5_vdpa_priv *priv);
+void
+mlx5_vdpa_virtq_unreg_intr_handle_all(struct mlx5_vdpa_priv *priv);
 #endif /* RTE_PMD_MLX5_VDPA_H_ */
diff --git a/drivers/vdpa/mlx5/mlx5_vdpa_cthread.c b/drivers/vdpa/mlx5/mlx5_vdpa_cthread.c
index 0e54226a90..07efa0cb16 100644
--- a/drivers/vdpa/mlx5/mlx5_vdpa_cthread.c
+++ b/drivers/vdpa/mlx5/mlx5_vdpa_cthread.c
@@ -63,7 +63,8 @@ mlx5_vdpa_task_add(struct mlx5_vdpa_priv *priv,
 		task[i].type = task_type;
 		task[i].remaining_cnt = remaining_cnt;
 		task[i].err_cnt = err_cnt;
-		task[i].idx = data[i];
+		if (data)
+			task[i].idx = data[i];
 	}
 	if (!mlx5_vdpa_c_thrd_ring_enqueue_bulk(rng, (void **)&task, num, NULL))
 		return -1;
@@ -190,6 +191,23 @@ mlx5_vdpa_c_thread_handle(void *arg)
 			    MLX5_VDPA_USED_RING_LEN(virtq->vq_size));
 			pthread_mutex_unlock(&virtq->virtq_lock);
 			break;
+		case MLX5_VDPA_TASK_DEV_CLOSE_NOWAIT:
+			mlx5_vdpa_virtq_unreg_intr_handle_all(priv);
+			pthread_mutex_lock(&priv->steer_update_lock);
+			mlx5_vdpa_steer_unset(priv);
+			pthread_mutex_unlock(&priv->steer_update_lock);
+			mlx5_vdpa_virtqs_release(priv);
+			mlx5_vdpa_drain_cq(priv);
+			if (priv->lm_mr.addr)
+				mlx5_os_wrapped_mkey_destroy(
+					&priv->lm_mr);
+			if (!priv->connected)
+				mlx5_vdpa_dev_cache_clean(priv);
+			priv->vid = 0;
+			__atomic_store_n(
+				&priv->dev_close_progress, 0,
+				__ATOMIC_RELAXED);
+			break;
 		default:
 			DRV_LOG(ERR, "Invalid vdpa task type %d.",
 			task.type);
diff --git a/drivers/vdpa/mlx5/mlx5_vdpa_virtq.c b/drivers/vdpa/mlx5/mlx5_vdpa_virtq.c
index 127b1cee7f..c1281be5f2 100644
--- a/drivers/vdpa/mlx5/mlx5_vdpa_virtq.c
+++ b/drivers/vdpa/mlx5/mlx5_vdpa_virtq.c
@@ -99,6 +99,20 @@ mlx5_vdpa_virtq_unregister_intr_handle(struct mlx5_vdpa_virtq *virtq)
 	rte_intr_instance_free(virtq->intr_handle);
 }
 
+void
+mlx5_vdpa_virtq_unreg_intr_handle_all(struct mlx5_vdpa_priv *priv)
+{
+	uint32_t i;
+	struct mlx5_vdpa_virtq *virtq;
+
+	for (i = 0; i < priv->nr_virtqs; i++) {
+		virtq = &priv->virtqs[i];
+		pthread_mutex_lock(&virtq->virtq_lock);
+		mlx5_vdpa_virtq_unregister_intr_handle(virtq);
+		pthread_mutex_unlock(&virtq->virtq_lock);
+	}
+}
+
 /* Release cached VQ resources. */
 void
 mlx5_vdpa_virtqs_cleanup(struct mlx5_vdpa_priv *priv)
-- 
2.27.0