#include <net/if.h>
#include <sys/socket.h>
#include <sys/ioctl.h>
+#include <sys/mman.h>
#include <fcntl.h>
#include <netinet/in.h>
#include <rte_errno.h>
#include <rte_string_fns.h>
#include <rte_bus_pci.h>
+#include <rte_eal_paging.h>
#include <mlx5_glue.h>
#include <mlx5_common.h>
TAILQ_HEAD_INITIALIZER(priv_list);
static pthread_mutex_t priv_list_lock = PTHREAD_MUTEX_INITIALIZER;
+static void mlx5_vdpa_dev_release(struct mlx5_vdpa_priv *priv);
+
static struct mlx5_vdpa_priv *
mlx5_vdpa_find_priv_resource_by_vdev(struct rte_vdpa_device *vdev)
{
DRV_LOG(ERR, "Invalid vDPA device: %s.", vdev->device->name);
return -1;
}
- *queue_num = priv->caps.max_num_virtio_queues;
+ *queue_num = priv->caps.max_num_virtio_queues / 2;
return 0;
}
DRV_LOG(ERR, "Invalid vDPA device: %s.", vdev->device->name);
return -EINVAL;
}
- if (vring >= (int)priv->caps.max_num_virtio_queues * 2) {
+ if (vring >= (int)priv->caps.max_num_virtio_queues) {
DRV_LOG(ERR, "Too big vring id: %d.", vring);
return -E2BIG;
}
return 0;
}
-static int
-mlx5_vdpa_pd_create(struct mlx5_vdpa_priv *priv)
-{
-#ifdef HAVE_IBV_FLOW_DV_SUPPORT
- priv->pd = mlx5_glue->alloc_pd(priv->cdev->ctx);
- if (priv->pd == NULL) {
- DRV_LOG(ERR, "Failed to allocate PD.");
- return errno ? -errno : -ENOMEM;
- }
- struct mlx5dv_obj obj;
- struct mlx5dv_pd pd_info;
- int ret = 0;
-
- obj.pd.in = priv->pd;
- obj.pd.out = &pd_info;
- ret = mlx5_glue->dv_init_obj(&obj, MLX5DV_OBJ_PD);
- if (ret) {
- DRV_LOG(ERR, "Fail to get PD object info.");
- mlx5_glue->dealloc_pd(priv->pd);
- priv->pd = NULL;
- return -errno;
- }
- priv->pdn = pd_info.pdn;
- return 0;
-#else
- (void)priv;
- DRV_LOG(ERR, "Cannot get pdn - no DV support.");
- return -ENOTSUP;
-#endif /* HAVE_IBV_FLOW_DV_SUPPORT */
-}
-
static int
mlx5_vdpa_mtu_set(struct mlx5_vdpa_priv *priv)
{
return kern_mtu == vhost_mtu ? 0 : -1;
}
+static void
+mlx5_vdpa_dev_cache_clean(struct mlx5_vdpa_priv *priv)
+{
+ /* Clean pre-created resource in dev removal only. */
+ if (!priv->queues)
+ mlx5_vdpa_virtqs_cleanup(priv);
+ mlx5_vdpa_mem_dereg(priv);
+}
+
static int
mlx5_vdpa_dev_close(int vid)
{
DRV_LOG(ERR, "Invalid vDPA device: %s.", vdev->device->name);
return -1;
}
- if (priv->configured)
- ret |= mlx5_vdpa_lm_log(priv);
- mlx5_vdpa_err_event_unset(priv);
mlx5_vdpa_cqe_event_unset(priv);
+ if (priv->state == MLX5_VDPA_STATE_CONFIGURED) {
+ ret |= mlx5_vdpa_lm_log(priv);
+ priv->state = MLX5_VDPA_STATE_IN_PROGRESS;
+ }
mlx5_vdpa_steer_unset(priv);
mlx5_vdpa_virtqs_release(priv);
- mlx5_vdpa_event_qp_global_release(priv);
- mlx5_vdpa_mem_dereg(priv);
- if (priv->pd) {
- claim_zero(mlx5_glue->dealloc_pd(priv->pd));
- priv->pd = NULL;
- }
- priv->configured = 0;
+ 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;
/* The mutex may stay locked after event thread cancel - initiate it. */
pthread_mutex_init(&priv->vq_config_lock, NULL);
DRV_LOG(ERR, "Invalid vDPA device: %s.", vdev->device->name);
return -EINVAL;
}
- if (priv->configured && mlx5_vdpa_dev_close(vid)) {
+ if (priv->state == MLX5_VDPA_STATE_CONFIGURED &&
+ mlx5_vdpa_dev_close(vid)) {
DRV_LOG(ERR, "Failed to reconfigure vid %d.", vid);
return -1;
}
priv->vid = vid;
+ priv->connected = true;
if (mlx5_vdpa_mtu_set(priv))
DRV_LOG(WARNING, "MTU cannot be set on device %s.",
vdev->device->name);
- if (mlx5_vdpa_pd_create(priv) || mlx5_vdpa_mem_register(priv) ||
- mlx5_vdpa_err_event_setup(priv) ||
+ if (mlx5_vdpa_mem_register(priv) ||
mlx5_vdpa_virtqs_prepare(priv) || mlx5_vdpa_steer_setup(priv) ||
mlx5_vdpa_cqe_event_setup(priv)) {
mlx5_vdpa_dev_close(vid);
return -1;
}
- priv->configured = 1;
+ priv->state = MLX5_VDPA_STATE_CONFIGURED;
DRV_LOG(INFO, "vDPA device %d was configured.", vid);
return 0;
}
DRV_LOG(ERR, "Invalid device: %s.", vdev->device->name);
return -ENODEV;
}
- if (!priv->configured) {
- DRV_LOG(ERR, "Device %s was not configured.",
- vdev->device->name);
- return -ENODATA;
- }
- if (qid >= (int)priv->nr_virtqs) {
+ if (qid >= (int)priv->caps.max_num_virtio_queues) {
DRV_LOG(ERR, "Too big vring id: %d for device %s.", qid,
vdev->device->name);
return -E2BIG;
DRV_LOG(ERR, "Invalid device: %s.", vdev->device->name);
return -ENODEV;
}
- if (!priv->configured) {
- DRV_LOG(ERR, "Device %s was not configured.",
- vdev->device->name);
- return -ENODATA;
- }
- if (qid >= (int)priv->nr_virtqs) {
+ if (qid >= (int)priv->caps.max_num_virtio_queues) {
DRV_LOG(ERR, "Too big vring id: %d for device %s.", qid,
vdev->device->name);
return -E2BIG;
return mlx5_vdpa_virtq_stats_reset(priv, qid);
}
+static int
+mlx5_vdpa_dev_cleanup(int vid)
+{
+ struct rte_vdpa_device *vdev = rte_vhost_get_vdpa_device(vid);
+ struct mlx5_vdpa_priv *priv;
+
+ if (vdev == NULL)
+ return -1;
+ priv = mlx5_vdpa_find_priv_resource_by_vdev(vdev);
+ if (priv == NULL) {
+ DRV_LOG(ERR, "Invalid vDPA device: %s.", vdev->device->name);
+ return -1;
+ }
+ if (priv->state == MLX5_VDPA_STATE_PROBED)
+ mlx5_vdpa_dev_cache_clean(priv);
+ priv->connected = false;
+ return 0;
+}
+
static struct rte_vdpa_dev_ops mlx5_vdpa_ops = {
.get_queue_num = mlx5_vdpa_get_queue_num,
.get_features = mlx5_vdpa_get_vdpa_features,
.get_protocol_features = mlx5_vdpa_get_protocol_features,
.dev_conf = mlx5_vdpa_dev_config,
.dev_close = mlx5_vdpa_dev_close,
+ .dev_cleanup = mlx5_vdpa_dev_cleanup,
.set_vring_state = mlx5_vdpa_set_vring_state,
.set_features = mlx5_vdpa_features_set,
.migration_done = NULL,
unsigned long tmp;
int n_cores = sysconf(_SC_NPROCESSORS_ONLN);
- if (strcmp(key, RTE_DEVARGS_KEY_CLASS) == 0)
- return 0;
errno = 0;
tmp = strtoul(val, NULL, 0);
if (errno) {
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);
}
}
static void
-mlx5_vdpa_config_get(struct rte_devargs *devargs, struct mlx5_vdpa_priv *priv)
+mlx5_vdpa_config_get(struct mlx5_kvargs_ctrl *mkvlist,
+ struct mlx5_vdpa_priv *priv)
{
- struct rte_kvargs *kvlist;
+ const char **params = (const char *[]){
+ "event_core",
+ "event_mode",
+ "event_us",
+ "hw_latency_mode",
+ "hw_max_latency_us",
+ "hw_max_pending_comp",
+ "no_traffic_time",
+ NULL,
+ };
priv->event_mode = MLX5_VDPA_EVENT_MODE_FIXED_TIMER;
priv->event_us = 0;
priv->event_core = -1;
priv->no_traffic_max = MLX5_VDPA_DEFAULT_NO_TRAFFIC_MAX;
- if (devargs == NULL)
+ if (mkvlist == NULL)
return;
- kvlist = rte_kvargs_parse(devargs->args, NULL);
- if (kvlist == NULL)
- return;
- rte_kvargs_process(kvlist, NULL, mlx5_vdpa_args_check_handler, priv);
- rte_kvargs_free(kvlist);
+ mlx5_kvargs_process(mkvlist, params, mlx5_vdpa_args_check_handler,
+ priv);
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_dev_probe(struct mlx5_common_device *cdev)
+mlx5_vdpa_virtq_resource_prepare(struct mlx5_vdpa_priv *priv)
{
- struct mlx5_vdpa_priv *priv = NULL;
- struct mlx5_hca_attr attr;
- int ret;
+ uint32_t index;
+ uint32_t i;
- ret = mlx5_devx_cmd_query_hca_attr(cdev->ctx, &attr);
- if (ret) {
- DRV_LOG(ERR, "Unable to read HCA capabilities.");
- rte_errno = ENOTSUP;
+ if (!priv->queues)
+ return 0;
+ for (index = 0; index < (priv->queues * 2); ++index) {
+ struct mlx5_vdpa_virtq *virtq = &priv->virtqs[index];
+ int ret = mlx5_vdpa_event_qp_prepare(priv, priv->queue_size,
+ -1, &virtq->eqp);
+
+ if (ret) {
+ DRV_LOG(ERR, "Failed to create event QPs for virtq %d.",
+ index);
+ return -1;
+ }
+ 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
+mlx5_vdpa_create_dev_resources(struct mlx5_vdpa_priv *priv)
+{
+ struct mlx5_devx_tis_attr tis_attr = {0};
+ struct ibv_context *ctx = priv->cdev->ctx;
+ uint32_t i;
+ int retry;
+
+ for (retry = 0; retry < 7; retry++) {
+ priv->var = mlx5_glue->dv_alloc_var(ctx, 0);
+ if (priv->var != NULL)
+ break;
+ DRV_LOG(WARNING, "Failed to allocate VAR, retry %d.", retry);
+ /* Wait Qemu release VAR during vdpa restart, 0.1 sec based. */
+ usleep(100000U << retry);
+ }
+ if (!priv->var) {
+ DRV_LOG(ERR, "Failed to allocate VAR %u.", errno);
+ rte_errno = ENOMEM;
+ return -rte_errno;
+ }
+ /* Always map the entire page. */
+ priv->virtq_db_addr = mmap(NULL, priv->var->length, PROT_READ |
+ PROT_WRITE, MAP_SHARED, ctx->cmd_fd,
+ priv->var->mmap_off);
+ if (priv->virtq_db_addr == MAP_FAILED) {
+ DRV_LOG(ERR, "Failed to map doorbell page %u.", errno);
+ priv->virtq_db_addr = NULL;
+ rte_errno = errno;
+ return -rte_errno;
+ }
+ /* Add within page offset for 64K page system. */
+ priv->virtq_db_addr = (char *)priv->virtq_db_addr +
+ ((rte_mem_page_size() - 1) & priv->caps.doorbell_bar_offset);
+ DRV_LOG(DEBUG, "VAR address of doorbell mapping is %p.",
+ priv->virtq_db_addr);
+ priv->td = mlx5_devx_cmd_create_td(ctx);
+ if (!priv->td) {
+ DRV_LOG(ERR, "Failed to create transport domain.");
+ rte_errno = errno;
return -rte_errno;
- } else if (!attr.vdpa.valid || !attr.vdpa.max_num_virtio_queues) {
+ }
+ tis_attr.transport_domain = priv->td->id;
+ for (i = 0; i < priv->num_lag_ports; i++) {
+ /* 0 is auto affinity, non-zero value to propose port. */
+ tis_attr.lag_tx_port_affinity = i + 1;
+ priv->tiss[i] = mlx5_devx_cmd_create_tis(ctx, &tis_attr);
+ if (!priv->tiss[i]) {
+ DRV_LOG(ERR, "Failed to create TIS %u.", i);
+ return -rte_errno;
+ }
+ }
+ priv->null_mr = mlx5_glue->alloc_null_mr(priv->cdev->pd);
+ if (!priv->null_mr) {
+ DRV_LOG(ERR, "Failed to allocate null MR.");
+ rte_errno = errno;
+ return -rte_errno;
+ }
+ DRV_LOG(DEBUG, "Dump fill Mkey = %u.", priv->null_mr->lkey);
+#ifdef HAVE_MLX5DV_DR
+ priv->steer.domain = mlx5_glue->dr_create_domain(ctx,
+ MLX5DV_DR_DOMAIN_TYPE_NIC_RX);
+ if (!priv->steer.domain) {
+ DRV_LOG(ERR, "Failed to create Rx domain.");
+ rte_errno = errno;
+ return -rte_errno;
+ }
+#endif
+ priv->steer.tbl = mlx5_glue->dr_create_flow_tbl(priv->steer.domain, 0);
+ if (!priv->steer.tbl) {
+ DRV_LOG(ERR, "Failed to create table 0 with Rx domain.");
+ rte_errno = errno;
+ return -rte_errno;
+ }
+ if (mlx5_vdpa_err_event_setup(priv) != 0)
+ 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;
+}
+
+static int
+mlx5_vdpa_dev_probe(struct mlx5_common_device *cdev,
+ struct mlx5_kvargs_ctrl *mkvlist)
+{
+ struct mlx5_vdpa_priv *priv = NULL;
+ struct mlx5_hca_attr *attr = &cdev->config.hca_attr;
+
+ if (!attr->vdpa.valid || !attr->vdpa.max_num_virtio_queues) {
DRV_LOG(ERR, "Not enough capabilities to support vdpa, maybe "
"old FW/OFED version?");
rte_errno = ENOTSUP;
return -rte_errno;
}
- if (!attr.vdpa.queue_counters_valid)
+ if (!attr->vdpa.queue_counters_valid)
DRV_LOG(DEBUG, "No capability to support virtq statistics.");
priv = rte_zmalloc("mlx5 vDPA device private", sizeof(*priv) +
sizeof(struct mlx5_vdpa_virtq) *
- attr.vdpa.max_num_virtio_queues * 2,
+ attr->vdpa.max_num_virtio_queues,
RTE_CACHE_LINE_SIZE);
if (!priv) {
DRV_LOG(ERR, "Failed to allocate private memory.");
rte_errno = ENOMEM;
return -rte_errno;
}
- priv->caps = attr.vdpa;
- priv->log_max_rqt_size = attr.log_max_rqt_size;
- priv->num_lag_ports = attr.num_lag_ports;
- priv->qp_ts_format = attr.qp_ts_format;
- if (attr.num_lag_ports == 0)
+ priv->caps = attr->vdpa;
+ priv->log_max_rqt_size = attr->log_max_rqt_size;
+ priv->num_lag_ports = attr->num_lag_ports;
+ if (attr->num_lag_ports == 0)
priv->num_lag_ports = 1;
+ pthread_mutex_init(&priv->vq_config_lock, NULL);
priv->cdev = cdev;
- priv->var = mlx5_glue->dv_alloc_var(priv->cdev->ctx, 0);
- if (!priv->var) {
- DRV_LOG(ERR, "Failed to allocate VAR %u.", errno);
+ 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);
if (priv->vdev == NULL) {
DRV_LOG(ERR, "Failed to register vDPA device.");
rte_errno = rte_errno ? rte_errno : EINVAL;
goto error;
}
- mlx5_vdpa_config_get(cdev->dev->devargs, priv);
SLIST_INIT(&priv->mr_list);
- pthread_mutex_init(&priv->vq_config_lock, NULL);
pthread_mutex_lock(&priv_list_lock);
TAILQ_INSERT_TAIL(&priv_list, priv, next);
pthread_mutex_unlock(&priv_list_lock);
return 0;
-
error:
- if (priv) {
- if (priv->var)
- mlx5_glue->dv_free_var(priv->var);
- rte_free(priv);
- }
+ if (priv)
+ mlx5_vdpa_dev_release(priv);
return -rte_errno;
}
if (found)
TAILQ_REMOVE(&priv_list, priv, next);
pthread_mutex_unlock(&priv_list_lock);
- if (found) {
- if (priv->configured)
- mlx5_vdpa_dev_close(priv->vid);
- if (priv->var) {
- mlx5_glue->dv_free_var(priv->var);
- priv->var = NULL;
- }
- if (priv->vdev)
- rte_vdpa_unregister_device(priv->vdev);
- pthread_mutex_destroy(&priv->vq_config_lock);
- rte_free(priv);
- }
+ if (found)
+ mlx5_vdpa_dev_release(priv);
return 0;
}
+static void
+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)
+ continue;
+ claim_zero(mlx5_devx_cmd_destroy(priv->virtqs[i].counters));
+ }
+ mlx5_vdpa_event_qp_global_release(priv);
+ mlx5_vdpa_err_event_unset(priv);
+ if (priv->steer.tbl)
+ claim_zero(mlx5_glue->dr_destroy_flow_tbl(priv->steer.tbl));
+ if (priv->steer.domain)
+ claim_zero(mlx5_glue->dr_destroy_domain(priv->steer.domain));
+ if (priv->null_mr)
+ claim_zero(mlx5_glue->dereg_mr(priv->null_mr));
+ for (i = 0; i < priv->num_lag_ports; i++) {
+ if (priv->tiss[i])
+ claim_zero(mlx5_devx_cmd_destroy(priv->tiss[i]));
+ }
+ if (priv->td)
+ claim_zero(mlx5_devx_cmd_destroy(priv->td));
+ if (priv->virtq_db_addr)
+ /* Mask out the within page offset for munmap. */
+ claim_zero(munmap((void *)((uintptr_t)priv->virtq_db_addr &
+ ~(rte_mem_page_size() - 1)), priv->var->length));
+ if (priv->var)
+ mlx5_glue->dv_free_var(priv->var);
+}
+
+static void
+mlx5_vdpa_dev_release(struct mlx5_vdpa_priv *priv)
+{
+ if (priv->state == MLX5_VDPA_STATE_CONFIGURED)
+ mlx5_vdpa_dev_close(priv->vid);
+ mlx5_vdpa_release_dev_resources(priv);
+ if (priv->vdev)
+ rte_vdpa_unregister_device(priv->vdev);
+ pthread_mutex_destroy(&priv->vq_config_lock);
+ rte_free(priv);
+}
+
static const struct rte_pci_id mlx5_vdpa_pci_id_map[] = {
{
RTE_PCI_DEVICE(PCI_VENDOR_ID_MELLANOX,
git.droids-corp.org / dpdk.git / blobdiff