[PATCH v1 14/17] vdpa/mlx5: add virtq LM log task

[Li Zhang <lizh@nvidia.com>]

Split the virtqs LM log between the configuration threads.
This accelerates the LM process and reduces its time by 20%.

Signed-off-by: Li Zhang <lizh@nvidia.com>
---
 drivers/vdpa/mlx5/mlx5_vdpa.h         |  3 +
 drivers/vdpa/mlx5/mlx5_vdpa_cthread.c | 34 +++++++++++
 drivers/vdpa/mlx5/mlx5_vdpa_lm.c      | 85 +++++++++++++++++++++------
 3 files changed, 105 insertions(+), 17 deletions(-)

diff --git a/drivers/vdpa/mlx5/mlx5_vdpa.h b/drivers/vdpa/mlx5/mlx5_vdpa.h
index 35221f5ddc..e08931719f 100644
--- a/drivers/vdpa/mlx5/mlx5_vdpa.h
+++ b/drivers/vdpa/mlx5/mlx5_vdpa.h
@@ -72,6 +72,8 @@ enum {
 	MLX5_VDPA_NOTIFIER_STATE_ERR
 };
 
+#define MLX5_VDPA_USED_RING_LEN(size) \
+	((size) * sizeof(struct vring_used_elem) + sizeof(uint16_t) * 3)
 #define MLX5_VDPA_MAX_C_THRD 256
 #define MLX5_VDPA_MAX_TASKS_PER_THRD 4096
 #define MLX5_VDPA_TASKS_PER_DEV 64
@@ -81,6 +83,7 @@ enum {
 enum mlx5_vdpa_task_type {
 	MLX5_VDPA_TASK_REG_MR = 1,
 	MLX5_VDPA_TASK_SETUP_VIRTQ,
+	MLX5_VDPA_TASK_STOP_VIRTQ,
 };
 
 /* Generic task information and size must be multiple of 4B. */
diff --git a/drivers/vdpa/mlx5/mlx5_vdpa_cthread.c b/drivers/vdpa/mlx5/mlx5_vdpa_cthread.c
index 1389d369ae..98369f0887 100644
--- a/drivers/vdpa/mlx5/mlx5_vdpa_cthread.c
+++ b/drivers/vdpa/mlx5/mlx5_vdpa_cthread.c
@@ -104,6 +104,7 @@ mlx5_vdpa_c_thread_handle(void *arg)
 	struct mlx5_vdpa_priv *priv;
 	struct mlx5_vdpa_task task;
 	struct rte_ring *rng;
+	uint64_t features;
 	uint32_t thrd_idx;
 	uint32_t task_num;
 	int ret;
@@ -153,6 +154,39 @@ mlx5_vdpa_c_thread_handle(void *arg)
 			}
 			pthread_mutex_unlock(&virtq->virtq_lock);
 			break;
+		case MLX5_VDPA_TASK_STOP_VIRTQ:
+			virtq = &priv->virtqs[task.idx];
+			pthread_mutex_lock(&virtq->virtq_lock);
+			ret = mlx5_vdpa_virtq_stop(priv,
+					task.idx);
+			if (ret) {
+				DRV_LOG(ERR,
+				"Failed to stop virtq %d.",
+				task.idx);
+				__atomic_fetch_add(
+					task.err_cnt, 1,
+					__ATOMIC_RELAXED);
+				pthread_mutex_unlock(&virtq->virtq_lock);
+				break;
+			}
+			ret = rte_vhost_get_negotiated_features(
+				priv->vid, &features);
+			if (ret) {
+				DRV_LOG(ERR,
+		"Failed to get negotiated features virtq %d.",
+				task.idx);
+				__atomic_fetch_add(
+					task.err_cnt, 1,
+					__ATOMIC_RELAXED);
+				pthread_mutex_unlock(&virtq->virtq_lock);
+				break;
+			}
+			if (RTE_VHOST_NEED_LOG(features))
+				rte_vhost_log_used_vring(
+				priv->vid, task.idx, 0,
+			    MLX5_VDPA_USED_RING_LEN(virtq->vq_size));
+			pthread_mutex_unlock(&virtq->virtq_lock);
+			break;
 		default:
 			DRV_LOG(ERR, "Invalid vdpa task type %d.",
 			task.type);
diff --git a/drivers/vdpa/mlx5/mlx5_vdpa_lm.c b/drivers/vdpa/mlx5/mlx5_vdpa_lm.c
index efebf364d0..c2e78218ca 100644
--- a/drivers/vdpa/mlx5/mlx5_vdpa_lm.c
+++ b/drivers/vdpa/mlx5/mlx5_vdpa_lm.c
@@ -89,39 +89,90 @@ mlx5_vdpa_dirty_bitmap_set(struct mlx5_vdpa_priv *priv, uint64_t log_base,
 	return -1;
 }
 
-#define MLX5_VDPA_USED_RING_LEN(size) \
-	((size) * sizeof(struct vring_used_elem) + sizeof(uint16_t) * 3)
-
 int
 mlx5_vdpa_lm_log(struct mlx5_vdpa_priv *priv)
 {
+	uint32_t remaining_cnt = 0, err_cnt = 0, task_num = 0;
+	uint32_t i, thrd_idx, data[1];
 	struct mlx5_vdpa_virtq *virtq;
 	uint64_t features;
-	int ret = rte_vhost_get_negotiated_features(priv->vid, &features);
-	int i;
+	int ret;
 
+	ret = rte_vhost_get_negotiated_features(priv->vid, &features);
 	if (ret) {
 		DRV_LOG(ERR, "Failed to get negotiated features.");
 		return -1;
 	}
-	if (!RTE_VHOST_NEED_LOG(features))
-		return 0;
-	for (i = 0; i < priv->nr_virtqs; ++i) {
-		virtq = &priv->virtqs[i];
-		if (!priv->virtqs[i].virtq) {
-			DRV_LOG(DEBUG, "virtq %d is invalid for LM log.", i);
-		} else {
+	if (priv->use_c_thread && priv->nr_virtqs) {
+		uint32_t main_task_idx[priv->nr_virtqs];
+
+		for (i = 0; i < priv->nr_virtqs; i++) {
+			virtq = &priv->virtqs[i];
+			if (!virtq->configured)
+				continue;
+			thrd_idx = i % (conf_thread_mng.max_thrds + 1);
+			if (!thrd_idx) {
+				main_task_idx[task_num] = i;
+				task_num++;
+				continue;
+			}
+			thrd_idx = priv->last_c_thrd_idx + 1;
+			if (thrd_idx >= conf_thread_mng.max_thrds)
+				thrd_idx = 0;
+			priv->last_c_thrd_idx = thrd_idx;
+			data[0] = i;
+			if (mlx5_vdpa_task_add(priv, thrd_idx,
+				MLX5_VDPA_TASK_STOP_VIRTQ,
+				&remaining_cnt, &err_cnt,
+				(void **)&data, 1)) {
+				DRV_LOG(ERR, "Fail to add "
+					"task stop virtq (%d).", i);
+				main_task_idx[task_num] = i;
+				task_num++;
+			}
+		}
+		for (i = 0; i < task_num; i++) {
+			virtq = &priv->virtqs[main_task_idx[i]];
 			pthread_mutex_lock(&virtq->virtq_lock);
-			ret = mlx5_vdpa_virtq_stop(priv, i);
+			ret = mlx5_vdpa_virtq_stop(priv,
+					main_task_idx[i]);
+			if (ret) {
+				pthread_mutex_unlock(&virtq->virtq_lock);
+				DRV_LOG(ERR,
+				"Failed to stop virtq %d.", i);
+				return -1;
+			}
+			if (RTE_VHOST_NEED_LOG(features))
+				rte_vhost_log_used_vring(priv->vid, i, 0,
+				MLX5_VDPA_USED_RING_LEN(virtq->vq_size));
 			pthread_mutex_unlock(&virtq->virtq_lock);
+		}
+		if (mlx5_vdpa_c_thread_wait_bulk_tasks_done(&remaining_cnt,
+			&err_cnt, 2000)) {
+			DRV_LOG(ERR,
+			"Failed to wait virt-queue setup tasks ready.");
+			return -1;
+		}
+	} else {
+		for (i = 0; i < priv->nr_virtqs; i++) {
+			virtq = &priv->virtqs[i];
+			pthread_mutex_lock(&virtq->virtq_lock);
+			if (!virtq->configured) {
+				pthread_mutex_unlock(&virtq->virtq_lock);
+				continue;
+			}
+			ret = mlx5_vdpa_virtq_stop(priv, i);
 			if (ret) {
-				DRV_LOG(ERR, "Failed to stop virtq %d for LM "
-					"log.", i);
+				pthread_mutex_unlock(&virtq->virtq_lock);
+				DRV_LOG(ERR,
+				"Failed to stop virtq %d for LM log.", i);
 				return -1;
 			}
+			if (RTE_VHOST_NEED_LOG(features))
+				rte_vhost_log_used_vring(priv->vid, i, 0,
+				MLX5_VDPA_USED_RING_LEN(virtq->vq_size));
+			pthread_mutex_unlock(&virtq->virtq_lock);
 		}
-		rte_vhost_log_used_vring(priv->vid, i, 0,
-			      MLX5_VDPA_USED_RING_LEN(priv->virtqs[i].vq_size));
 	}
 	return 0;
 }
-- 
2.31.1