#include <rte_malloc.h>
#include <rte_log.h>
#include <rte_errno.h>
-#include <rte_pci.h>
#include <rte_string_fns.h>
+#include <rte_bus_pci.h>
#include <mlx5_glue.h>
#include <mlx5_common.h>
-#include <mlx5_common_pci.h>
+#include <mlx5_common_defs.h>
#include <mlx5_devx_cmds.h>
#include <mlx5_prm.h>
#include <mlx5_nl.h>
#include "mlx5_vdpa_utils.h"
#include "mlx5_vdpa.h"
+#define MLX5_VDPA_DRIVER_NAME vdpa_mlx5
#define MLX5_VDPA_DEFAULT_FEATURES ((1ULL << VHOST_USER_F_PROTOCOL_FEATURES) | \
(1ULL << VIRTIO_F_ANY_LAYOUT) | \
(1ULL << VHOST_USER_PROTOCOL_F_NET_MTU) | \
(1ULL << VHOST_USER_PROTOCOL_F_STATUS))
-#define MLX5_VDPA_MAX_RETRIES 20
-#define MLX5_VDPA_USEC 1000
#define MLX5_VDPA_DEFAULT_NO_TRAFFIC_MAX 16LLU
TAILQ_HEAD(mlx5_vdpa_privs, mlx5_vdpa_priv) priv_list =
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->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)
{
DRV_LOG(DEBUG, "Vhost MTU is 0.");
return ret;
}
- ret = mlx5_get_ifname_sysfs(priv->ctx->device->ibdev_path,
- request.ifr_name);
+ ret = mlx5_get_ifname_sysfs
+ (mlx5_os_get_ctx_device_name(priv->cdev->ctx),
+ request.ifr_name);
if (ret) {
DRV_LOG(DEBUG, "Cannot get kernel IF name - %d.", ret);
return ret;
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->configured)
+ ret |= mlx5_vdpa_lm_log(priv);
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;
priv->vid = 0;
/* The mutex may stay locked after event thread cancel - initiate it. */
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_err_event_setup(priv) ||
mlx5_vdpa_virtqs_prepare(priv) || mlx5_vdpa_steer_setup(priv) ||
mlx5_vdpa_cqe_event_setup(priv)) {
mlx5_vdpa_dev_close(vid);
DRV_LOG(ERR, "Invalid vDPA device: %s.", vdev->device->name);
return -EINVAL;
}
- return priv->ctx->cmd_fd;
+ return ((struct ibv_context *)priv->cdev->ctx)->cmd_fd;
}
static int
.reset_stats = mlx5_vdpa_reset_stats,
};
-/* Try to disable ROCE by Netlink\Devlink. */
-static int
-mlx5_vdpa_nl_roce_disable(const char *addr)
-{
- int nlsk_fd = mlx5_nl_init(NETLINK_GENERIC);
- int devlink_id;
- int enable;
- int ret;
-
- if (nlsk_fd < 0)
- return nlsk_fd;
- devlink_id = mlx5_nl_devlink_family_id_get(nlsk_fd);
- if (devlink_id < 0) {
- ret = devlink_id;
- DRV_LOG(DEBUG, "Failed to get devlink id for ROCE operations by"
- " Netlink.");
- goto close;
- }
- ret = mlx5_nl_enable_roce_get(nlsk_fd, devlink_id, addr, &enable);
- if (ret) {
- DRV_LOG(DEBUG, "Failed to get ROCE enable by Netlink: %d.",
- ret);
- goto close;
- } else if (!enable) {
- DRV_LOG(INFO, "ROCE has already disabled(Netlink).");
- goto close;
- }
- ret = mlx5_nl_enable_roce_set(nlsk_fd, devlink_id, addr, 0);
- if (ret)
- DRV_LOG(DEBUG, "Failed to disable ROCE by Netlink: %d.", ret);
- else
- DRV_LOG(INFO, "ROCE is disabled by Netlink successfully.");
-close:
- close(nlsk_fd);
- return ret;
-}
-
-/* Try to disable ROCE by sysfs. */
-static int
-mlx5_vdpa_sys_roce_disable(const char *addr)
-{
- FILE *file_o;
- int enable;
- int ret;
-
- MKSTR(file_p, "/sys/bus/pci/devices/%s/roce_enable", addr);
- file_o = fopen(file_p, "rb");
- if (!file_o) {
- rte_errno = ENOTSUP;
- return -ENOTSUP;
- }
- ret = fscanf(file_o, "%d", &enable);
- if (ret != 1) {
- rte_errno = EINVAL;
- ret = EINVAL;
- goto close;
- } else if (!enable) {
- ret = 0;
- DRV_LOG(INFO, "ROCE has already disabled(sysfs).");
- goto close;
- }
- fclose(file_o);
- file_o = fopen(file_p, "wb");
- if (!file_o) {
- rte_errno = ENOTSUP;
- return -ENOTSUP;
- }
- fprintf(file_o, "0\n");
- ret = 0;
-close:
- if (ret)
- DRV_LOG(DEBUG, "Failed to disable ROCE by sysfs: %d.", ret);
- else
- DRV_LOG(INFO, "ROCE is disabled by sysfs successfully.");
- fclose(file_o);
- return ret;
-}
-
-static int
-mlx5_vdpa_roce_disable(struct rte_pci_addr *addr, struct ibv_device **ibv)
-{
- char addr_name[64] = {0};
-
- rte_pci_device_name(addr, addr_name, sizeof(addr_name));
- /* Firstly try to disable ROCE by Netlink and fallback to sysfs. */
- if (mlx5_vdpa_nl_roce_disable(addr_name) == 0 ||
- mlx5_vdpa_sys_roce_disable(addr_name) == 0) {
- /*
- * Succeed to disable ROCE, wait for the IB device to appear
- * again after reload.
- */
- int r;
- struct ibv_device *ibv_new;
-
- for (r = MLX5_VDPA_MAX_RETRIES; r; r--) {
- ibv_new = mlx5_os_get_ibv_device(addr);
- if (ibv_new) {
- *ibv = ibv_new;
- return 0;
- }
- usleep(MLX5_VDPA_USEC);
- }
- DRV_LOG(ERR, "Cannot much device %s after ROCE disable, "
- "retries exceed %d", addr_name, MLX5_VDPA_MAX_RETRIES);
- rte_errno = EAGAIN;
- }
- return -rte_errno;
-}
-
static int
mlx5_vdpa_args_check_handler(const char *key, const char *val, void *opaque)
{
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 {
- DRV_LOG(WARNING, "Invalid key %s.", key);
}
return 0;
}
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)
- return;
- kvlist = rte_kvargs_parse(devargs->args, NULL);
- if (kvlist == NULL)
+ if (mkvlist == 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;
DRV_LOG(DEBUG, "no traffic max is %u.", priv->no_traffic_max);
}
-/**
- * DPDK callback to register a mlx5 PCI device.
- *
- * This function spawns vdpa device out of a given PCI device.
- *
- * @param[in] pci_drv
- * PCI driver structure (mlx5_vpda_driver).
- * @param[in] pci_dev
- * PCI device information.
- *
- * @return
- * 0 on success, 1 to skip this driver, a negative errno value otherwise
- * and rte_errno is set.
- */
static int
-mlx5_vdpa_pci_probe(struct rte_pci_driver *pci_drv __rte_unused,
- struct rte_pci_device *pci_dev __rte_unused)
+mlx5_vdpa_dev_probe(struct mlx5_common_device *cdev,
+ struct mlx5_kvargs_ctrl *mkvlist)
{
- struct ibv_device *ibv;
struct mlx5_vdpa_priv *priv = NULL;
- struct ibv_context *ctx = NULL;
- struct mlx5_hca_attr attr;
- int ret;
+ struct mlx5_hca_attr *attr = &cdev->config.hca_attr;
+ int retry;
- ibv = mlx5_os_get_ibv_device(&pci_dev->addr);
- if (!ibv) {
- DRV_LOG(ERR, "No matching IB device for PCI slot "
- PCI_PRI_FMT ".", pci_dev->addr.domain,
- pci_dev->addr.bus, pci_dev->addr.devid,
- pci_dev->addr.function);
- return -rte_errno;
- } else {
- DRV_LOG(INFO, "PCI information matches for device \"%s\".",
- ibv->name);
- }
- if (mlx5_vdpa_roce_disable(&pci_dev->addr, &ibv) != 0) {
- DRV_LOG(WARNING, "Failed to disable ROCE for \"%s\".",
- ibv->name);
- return -rte_errno;
- }
- ctx = mlx5_glue->dv_open_device(ibv);
- if (!ctx) {
- DRV_LOG(ERR, "Failed to open IB device \"%s\".", ibv->name);
- rte_errno = ENODEV;
- return -rte_errno;
- }
- ret = mlx5_devx_cmd_query_hca_attr(ctx, &attr);
- if (ret) {
- DRV_LOG(ERR, "Unable to read HCA capabilities.");
- rte_errno = ENOTSUP;
- goto error;
- } else if (!attr.vdpa.valid || !attr.vdpa.max_num_virtio_queues) {
+ 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;
- goto error;
+ 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 * 2,
RTE_CACHE_LINE_SIZE);
if (!priv) {
DRV_LOG(ERR, "Failed to allocate private memory.");
rte_errno = ENOMEM;
- goto error;
+ 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;
- priv->ctx = ctx;
- priv->pci_dev = pci_dev;
- priv->var = mlx5_glue->dv_alloc_var(ctx, 0);
+ priv->cdev = cdev;
+ for (retry = 0; retry < 7; retry++) {
+ priv->var = mlx5_glue->dv_alloc_var(priv->cdev->ctx, 0);
+ if (priv->var != NULL)
+ break;
+ DRV_LOG(WARNING, "Failed to allocate VAR, retry %d.\n", 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);
goto error;
}
- priv->vdev = rte_vdpa_register_device(&pci_dev->device,
- &mlx5_vdpa_ops);
+ priv->err_intr_handle =
+ rte_intr_instance_alloc(RTE_INTR_INSTANCE_F_SHARED);
+ if (priv->err_intr_handle == NULL) {
+ DRV_LOG(ERR, "Fail to allocate intr_handle");
+ 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(pci_dev->device.devargs, priv);
+ mlx5_vdpa_config_get(mkvlist, priv);
SLIST_INIT(&priv->mr_list);
pthread_mutex_init(&priv->vq_config_lock, NULL);
pthread_mutex_lock(&priv_list_lock);
if (priv) {
if (priv->var)
mlx5_glue->dv_free_var(priv->var);
+ rte_intr_instance_free(priv->err_intr_handle);
rte_free(priv);
}
- if (ctx)
- mlx5_glue->close_device(ctx);
return -rte_errno;
}
-/**
- * DPDK callback to remove a PCI device.
- *
- * This function removes all vDPA devices belong to a given PCI device.
- *
- * @param[in] pci_dev
- * Pointer to the PCI device.
- *
- * @return
- * 0 on success, the function cannot fail.
- */
static int
-mlx5_vdpa_pci_remove(struct rte_pci_device *pci_dev)
+mlx5_vdpa_dev_remove(struct mlx5_common_device *cdev)
{
struct mlx5_vdpa_priv *priv = NULL;
int found = 0;
pthread_mutex_lock(&priv_list_lock);
TAILQ_FOREACH(priv, &priv_list, next) {
- if (!rte_pci_addr_cmp(&priv->pci_dev->addr, &pci_dev->addr)) {
+ if (priv->vdev->device == cdev->dev) {
found = 1;
break;
}
}
if (priv->vdev)
rte_vdpa_unregister_device(priv->vdev);
- mlx5_glue->close_device(priv->ctx);
pthread_mutex_destroy(&priv->vq_config_lock);
+ rte_intr_instance_free(priv->err_intr_handle);
rte_free(priv);
}
return 0;
}
};
-static struct mlx5_pci_driver mlx5_vdpa_driver = {
- .driver_class = MLX5_CLASS_VDPA,
- .pci_driver = {
- .driver = {
- .name = "mlx5_vdpa",
- },
- .id_table = mlx5_vdpa_pci_id_map,
- .probe = mlx5_vdpa_pci_probe,
- .remove = mlx5_vdpa_pci_remove,
- .drv_flags = 0,
- },
+static struct mlx5_class_driver mlx5_vdpa_driver = {
+ .drv_class = MLX5_CLASS_VDPA,
+ .name = RTE_STR(MLX5_VDPA_DRIVER_NAME),
+ .id_table = mlx5_vdpa_pci_id_map,
+ .probe = mlx5_vdpa_dev_probe,
+ .remove = mlx5_vdpa_dev_remove,
};
RTE_LOG_REGISTER_DEFAULT(mlx5_vdpa_logtype, NOTICE)
{
mlx5_common_init();
if (mlx5_glue)
- mlx5_pci_driver_register(&mlx5_vdpa_driver);
+ mlx5_class_driver_register(&mlx5_vdpa_driver);
}
-RTE_PMD_EXPORT_NAME(net_mlx5_vdpa, __COUNTER__);
-RTE_PMD_REGISTER_PCI_TABLE(net_mlx5_vdpa, mlx5_vdpa_pci_id_map);
-RTE_PMD_REGISTER_KMOD_DEP(net_mlx5_vdpa, "* ib_uverbs & mlx5_core & mlx5_ib");
+RTE_PMD_EXPORT_NAME(MLX5_VDPA_DRIVER_NAME, __COUNTER__);
+RTE_PMD_REGISTER_PCI_TABLE(MLX5_VDPA_DRIVER_NAME, mlx5_vdpa_pci_id_map);
+RTE_PMD_REGISTER_KMOD_DEP(MLX5_VDPA_DRIVER_NAME, "* ib_uverbs & mlx5_core & mlx5_ib");