vdpa/mlx5: support pre-creation of virtq resource

The motivation of this change is to reduce vDPA device queue creation
time by creating some queue resource in vDPA device probe stage.

In VM live migration scenario, this can reduce 0.8ms for each queue
creation, thus reduce LM network downtime.

To create queue resource(umem/counter) in advance, we need to know
virtio queue depth and max number of queue VM will use.

Introduce two new devargs: queues(max queue pair number) and queue_size
(queue depth). Two args must be both provided, if only one argument
provided, the argument will be ignored and no pre-creation.

The queues and queue_size must also be identical to vhost configuration
driver later receive. Otherwise either the pre-create resource is wasted
or missing or the resource need destroy and recreate(in case queue_size
mismatch).

Pre-create umem/counter will keep alive until vDPA device removal.

Signed-off-by: Yajun Wu <yajunw@nvidia.com>
Acked-by: Matan Azrad <matan@nvidia.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>

diff --git a/doc/guides/vdpadevs/mlx5.rst b/doc/guides/vdpadevs/mlx5.rst
index 3ded142311e0da6c0a75afabc1a7ebe0b59bfc88..e1c77776dddc3704dc8ff050b46a023348ef8aef 100644 (file)
--- a/doc/guides/vdpadevs/mlx5.rst
+++ b/doc/guides/vdpadevs/mlx5.rst
@@ -101,6 +101,20 @@ for an additional list of options shared with other mlx5 drivers.
 
   - 0, HW default.
 
+- ``queue_size`` parameter [int]
+
+  - 1 - 1024, Virtio queue depth for pre-creating queue resource to speed up
+    first time queue creation. Set it together with ``queues`` parameter.
+
+  - 0, default value, no pre-create virtq resource.
+
+- ``queues`` parameter [int]
+
+  - 1 - 128, Maximum number of virtio queue pair (including 1 Rx queue and 1 Tx queue)
+    for pre-creating queue resource to speed up first time queue creation.
+    Set it together with ``queue_size`` parameter.
+
+  - 0, default value, no pre-create virtq resource.
 
 Error handling
 ^^^^^^^^^^^^^^

diff --git a/drivers/vdpa/mlx5/mlx5_vdpa.c b/drivers/vdpa/mlx5/mlx5_vdpa.c
index fc17a4b0f2cbcf92dc93e76abb01a6c59f5ba49d..2550b084bf361554e48e3ea4e57ad0b613660614 100644 (file)
--- a/drivers/vdpa/mlx5/mlx5_vdpa.c
+++ b/drivers/vdpa/mlx5/mlx5_vdpa.c
@@ -245,7 +245,9 @@ mlx5_vdpa_mtu_set(struct mlx5_vdpa_priv *priv)
 static void
 mlx5_vdpa_dev_cache_clean(struct mlx5_vdpa_priv *priv)
 {
-       mlx5_vdpa_virtqs_cleanup(priv);
+       /* Clean pre-created resource in dev removal only. */
+       if (!priv->queues)
+               mlx5_vdpa_virtqs_cleanup(priv);
        mlx5_vdpa_mem_dereg(priv);
 }
 
@@ -495,6 +497,12 @@ mlx5_vdpa_args_check_handler(const char *key, const char *val, void *opaque)
                priv->hw_max_latency_us = (uint32_t)tmp;
        } else if (strcmp(key, "hw_max_pending_comp") == 0) {
                priv->hw_max_pending_comp = (uint32_t)tmp;
+       } else if (strcmp(key, "queue_size") == 0) {
+               priv->queue_size = (uint16_t)tmp;
+       } else if (strcmp(key, "queues") == 0) {
+               priv->queues = (uint16_t)tmp;
+       } else {
+               DRV_LOG(WARNING, "Invalid key %s.", key);
        }
        return 0;
 }
@@ -525,9 +533,68 @@ mlx5_vdpa_config_get(struct mlx5_kvargs_ctrl *mkvlist,
        if (!priv->event_us &&
            priv->event_mode == MLX5_VDPA_EVENT_MODE_DYNAMIC_TIMER)
                priv->event_us = MLX5_VDPA_DEFAULT_TIMER_STEP_US;
+       if ((priv->queue_size && !priv->queues) ||
+               (!priv->queue_size && priv->queues)) {
+               priv->queue_size = 0;
+               priv->queues = 0;
+               DRV_LOG(WARNING, "Please provide both queue_size and queues.");
+       }
        DRV_LOG(DEBUG, "event mode is %d.", priv->event_mode);
        DRV_LOG(DEBUG, "event_us is %u us.", priv->event_us);
        DRV_LOG(DEBUG, "no traffic max is %u.", priv->no_traffic_max);
+       DRV_LOG(DEBUG, "queues is %u, queue_size is %u.", priv->queues,
+               priv->queue_size);
+}
+
+static int
+mlx5_vdpa_virtq_resource_prepare(struct mlx5_vdpa_priv *priv)
+{
+       uint32_t index;
+       uint32_t i;
+
+       if (!priv->queues)
+               return 0;
+       for (index = 0; index < (priv->queues * 2); ++index) {
+               struct mlx5_vdpa_virtq *virtq = &priv->virtqs[index];
+
+               if (priv->caps.queue_counters_valid) {
+                       if (!virtq->counters)
+                               virtq->counters =
+                                       mlx5_devx_cmd_create_virtio_q_counters
+                                               (priv->cdev->ctx);
+                       if (!virtq->counters) {
+                               DRV_LOG(ERR, "Failed to create virtq couners for virtq"
+                                       " %d.", index);
+                               return -1;
+                       }
+               }
+               for (i = 0; i < RTE_DIM(virtq->umems); ++i) {
+                       uint32_t size;
+                       void *buf;
+                       struct mlx5dv_devx_umem *obj;
+
+                       size = priv->caps.umems[i].a * priv->queue_size +
+                                       priv->caps.umems[i].b;
+                       buf = rte_zmalloc(__func__, size, 4096);
+                       if (buf == NULL) {
+                               DRV_LOG(ERR, "Cannot allocate umem %d memory for virtq"
+                                               " %u.", i, index);
+                               return -1;
+                       }
+                       obj = mlx5_glue->devx_umem_reg(priv->cdev->ctx, buf,
+                                       size, IBV_ACCESS_LOCAL_WRITE);
+                       if (obj == NULL) {
+                               rte_free(buf);
+                               DRV_LOG(ERR, "Failed to register umem %d for virtq %u.",
+                                               i, index);
+                               return -1;
+                       }
+                       virtq->umems[i].size = size;
+                       virtq->umems[i].buf = buf;
+                       virtq->umems[i].obj = obj;
+               }
+       }
+       return 0;
 }
 
 static int
@@ -608,6 +675,8 @@ mlx5_vdpa_create_dev_resources(struct mlx5_vdpa_priv *priv)
                return -rte_errno;
        if (mlx5_vdpa_event_qp_global_prepare(priv))
                return -rte_errno;
+       if (mlx5_vdpa_virtq_resource_prepare(priv))
+               return -rte_errno;
        return 0;
 }
 
@@ -642,6 +711,7 @@ mlx5_vdpa_dev_probe(struct mlx5_common_device *cdev,
                priv->num_lag_ports = 1;
        pthread_mutex_init(&priv->vq_config_lock, NULL);
        priv->cdev = cdev;
+       mlx5_vdpa_config_get(mkvlist, priv);
        if (mlx5_vdpa_create_dev_resources(priv))
                goto error;
        priv->vdev = rte_vdpa_register_device(cdev->dev, &mlx5_vdpa_ops);
@@ -650,7 +720,6 @@ mlx5_vdpa_dev_probe(struct mlx5_common_device *cdev,
                rte_errno = rte_errno ? rte_errno : EINVAL;
                goto error;
        }
-       mlx5_vdpa_config_get(mkvlist, priv);
        SLIST_INIT(&priv->mr_list);
        pthread_mutex_lock(&priv_list_lock);
        TAILQ_INSERT_TAIL(&priv_list, priv, next);
@@ -688,6 +757,8 @@ mlx5_vdpa_release_dev_resources(struct mlx5_vdpa_priv *priv)
 {
        uint32_t i;
 
+       if (priv->queues)
+               mlx5_vdpa_virtqs_cleanup(priv);
        mlx5_vdpa_dev_cache_clean(priv);
        for (i = 0; i < priv->caps.max_num_virtio_queues; i++) {
                if (!priv->virtqs[i].counters)

diff --git a/drivers/vdpa/mlx5/mlx5_vdpa.h b/drivers/vdpa/mlx5/mlx5_vdpa.h
index e7f3319f896a2ef442f90c6e0f2d01acc57ad094..f6719a3c606ae7046d3f0e375e5407a921b7d988 100644 (file)
--- a/drivers/vdpa/mlx5/mlx5_vdpa.h
+++ b/drivers/vdpa/mlx5/mlx5_vdpa.h
@@ -135,6 +135,8 @@ struct mlx5_vdpa_priv {
        uint8_t hw_latency_mode; /* Hardware CQ moderation mode. */
        uint16_t hw_max_latency_us; /* Hardware CQ moderation period in usec. */
        uint16_t hw_max_pending_comp; /* Hardware CQ moderation counter. */
+       uint16_t queue_size; /* virtq depth for pre-creating virtq resource */
+       uint16_t queues; /* Max virtq pair for pre-creating virtq resource */
        struct rte_vdpa_device *vdev; /* vDPA device. */
        struct mlx5_common_device *cdev; /* Backend mlx5 device. */
        int vid; /* vhost device id. */