/* Allow L3 VXLAN flow creation. */
#define MLX5_L3_VXLAN_EN "l3_vxlan_en"
+/* Activate DV E-Switch flow steering. */
+#define MLX5_DV_ESW_EN "dv_esw_en"
+
/* Activate DV flow steering. */
#define MLX5_DV_FLOW_EN "dv_flow_en"
struct mlx5_switch_info info; /**< Switch information. */
struct ibv_device *ibv_dev; /**< Associated IB device. */
struct rte_eth_dev *eth_dev; /**< Associated Ethernet device. */
+ struct rte_pci_device *pci_dev; /**< Backend PCI device. */
};
static LIST_HEAD(, mlx5_ibv_shared) mlx5_ibv_list = LIST_HEAD_INITIALIZER();
* port dedicated IB device, the context will be used by only given
* port due to unification.
*
- * Routine first searches the context for the spesified IB device name,
+ * Routine first searches the context for the specified IB device name,
* if found the shared context assumed and reference counter is incremented.
* If no context found the new one is created and initialized with specified
* IB device context and parameters.
goto exit;
}
}
- /* No device found, we have to create new sharted context. */
+ /* No device found, we have to create new shared context. */
assert(spawn->max_port);
sh = rte_zmalloc("ethdev shared ib context",
sizeof(struct mlx5_ibv_shared) +
sizeof(sh->ibdev_name));
strncpy(sh->ibdev_path, sh->ctx->device->ibdev_path,
sizeof(sh->ibdev_path));
+ sh->pci_dev = spawn->pci_dev;
pthread_mutex_init(&sh->intr_mutex, NULL);
/*
* Setting port_id to max unallowed value means
err = ENOMEM;
goto error;
}
+ /*
+ * Once the device is added to the list of memory event
+ * callback, its global MR cache table cannot be expanded
+ * on the fly because of deadlock. If it overflows, lookup
+ * should be done by searching MR list linearly, which is slow.
+ *
+ * At this point the device is not added to the memory
+ * event list yet, context is just being created.
+ */
+ err = mlx5_mr_btree_init(&sh->mr.cache,
+ MLX5_MR_BTREE_CACHE_N * 2,
+ sh->pci_dev->device.numa_node);
+ if (err) {
+ err = rte_errno;
+ goto error;
+ }
LIST_INSERT_HEAD(&mlx5_ibv_list, sh, next);
exit:
pthread_mutex_unlock(&mlx5_ibv_list_mutex);
assert(rte_eal_process_type() == RTE_PROC_PRIMARY);
if (--sh->refcnt)
goto exit;
+ /* Release created Memory Regions. */
+ mlx5_mr_release(sh);
LIST_REMOVE(sh, next);
/*
* Ensure there is no async event handler installed.
/**
* Initialize DR related data within private structure.
* Routine checks the reference counter and does actual
- * resources creation/iniialization only if counter is zero.
+ * resources creation/initialization only if counter is zero.
*
* @param[in] priv
* Pointer to the private device data structure.
#ifdef HAVE_MLX5DV_DR
struct mlx5_ibv_shared *sh = priv->sh;
int err = 0;
- void *ns;
+ void *domain;
assert(sh);
if (sh->dv_refcnt) {
return 0;
}
/* Reference counter is zero, we should initialize structures. */
- ns = mlx5dv_dr_create_ns(sh->ctx, MLX5DV_DR_NS_DOMAIN_INGRESS_BYPASS);
- if (!ns) {
- DRV_LOG(ERR, "ingress mlx5dv_dr_create_ns failed");
+ domain = mlx5_glue->dr_create_domain(sh->ctx,
+ MLX5DV_DR_DOMAIN_TYPE_NIC_RX);
+ if (!domain) {
+ DRV_LOG(ERR, "ingress mlx5dv_dr_create_domain failed");
err = errno;
goto error;
}
- priv->rx_ns = ns;
- ns = mlx5dv_dr_create_ns(sh->ctx, MLX5DV_DR_NS_DOMAIN_EGRESS_BYPASS);
- if (!ns) {
- DRV_LOG(ERR, "egress mlx5dv_dr_create_ns failed");
+ sh->rx_domain = domain;
+ domain = mlx5_glue->dr_create_domain(sh->ctx,
+ MLX5DV_DR_DOMAIN_TYPE_NIC_TX);
+ if (!domain) {
+ DRV_LOG(ERR, "egress mlx5dv_dr_create_domain failed");
err = errno;
goto error;
}
- priv->tx_ns = ns;
+ pthread_mutex_init(&sh->dv_mutex, NULL);
+ sh->tx_domain = domain;
+#ifdef HAVE_MLX5DV_DR_ESWITCH
+ if (priv->config.dv_esw_en) {
+ domain = mlx5_glue->dr_create_domain
+ (sh->ctx, MLX5DV_DR_DOMAIN_TYPE_FDB);
+ if (!domain) {
+ DRV_LOG(ERR, "FDB mlx5dv_dr_create_domain failed");
+ err = errno;
+ goto error;
+ }
+ sh->fdb_domain = domain;
+ sh->esw_drop_action = mlx5_glue->dr_create_flow_action_drop();
+ }
+#endif
sh->dv_refcnt++;
priv->dr_shared = 1;
return 0;
error:
/* Rollback the created objects. */
- if (priv->rx_ns) {
- mlx5dv_dr_destroy_ns(priv->rx_ns);
- priv->rx_ns = NULL;
+ if (sh->rx_domain) {
+ mlx5_glue->dr_destroy_domain(sh->rx_domain);
+ sh->rx_domain = NULL;
+ }
+ if (sh->tx_domain) {
+ mlx5_glue->dr_destroy_domain(sh->tx_domain);
+ sh->tx_domain = NULL;
+ }
+ if (sh->fdb_domain) {
+ mlx5_glue->dr_destroy_domain(sh->fdb_domain);
+ sh->fdb_domain = NULL;
}
- if (priv->tx_ns) {
- mlx5dv_dr_destroy_ns(priv->tx_ns);
- priv->tx_ns = NULL;
+ if (sh->esw_drop_action) {
+ mlx5_glue->destroy_flow_action(sh->esw_drop_action);
+ sh->esw_drop_action = NULL;
}
return err;
#else
assert(sh->dv_refcnt);
if (sh->dv_refcnt && --sh->dv_refcnt)
return;
- if (priv->rx_ns) {
- mlx5dv_dr_destroy_ns(priv->rx_ns);
- priv->rx_ns = NULL;
+ if (sh->rx_domain) {
+ mlx5_glue->dr_destroy_domain(sh->rx_domain);
+ sh->rx_domain = NULL;
}
- if (priv->tx_ns) {
- mlx5dv_dr_destroy_ns(priv->tx_ns);
- priv->tx_ns = NULL;
+ if (sh->tx_domain) {
+ mlx5_glue->dr_destroy_domain(sh->tx_domain);
+ sh->tx_domain = NULL;
}
+#ifdef HAVE_MLX5DV_DR_ESWITCH
+ if (sh->fdb_domain) {
+ mlx5_glue->dr_destroy_domain(sh->fdb_domain);
+ sh->fdb_domain = NULL;
+ }
+ if (sh->esw_drop_action) {
+ mlx5_glue->destroy_flow_action(sh->esw_drop_action);
+ sh->esw_drop_action = NULL;
+ }
+#endif
+ pthread_mutex_destroy(&sh->dv_mutex);
#else
(void)priv;
#endif
return ret;
}
-/**
- * Uninitialize shared data between primary and secondary process.
- *
- * The pointer of secondary process is dereferenced and primary process frees
- * the memzone.
- */
-static void
-mlx5_uninit_shared_data(void)
-{
- const struct rte_memzone *mz;
-
- rte_spinlock_lock(&mlx5_shared_data_lock);
- if (mlx5_shared_data) {
- if (rte_eal_process_type() == RTE_PROC_PRIMARY) {
- mz = rte_memzone_lookup(MZ_MLX5_PMD_SHARED_DATA);
- rte_memzone_free(mz);
- } else {
- memset(&mlx5_local_data, 0, sizeof(mlx5_local_data));
- }
- mlx5_shared_data = NULL;
- }
- rte_spinlock_unlock(&mlx5_shared_data_lock);
-}
-
/**
* Retrieve integer value from environment variable.
*
rte_free(ptr);
}
+/**
+ * Initialize process private data structure.
+ *
+ * @param dev
+ * Pointer to Ethernet device structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+int
+mlx5_proc_priv_init(struct rte_eth_dev *dev)
+{
+ struct mlx5_priv *priv = dev->data->dev_private;
+ struct mlx5_proc_priv *ppriv;
+ size_t ppriv_size;
+
+ /*
+ * UAR register table follows the process private structure. BlueFlame
+ * registers for Tx queues are stored in the table.
+ */
+ ppriv_size =
+ sizeof(struct mlx5_proc_priv) + priv->txqs_n * sizeof(void *);
+ ppriv = rte_malloc_socket("mlx5_proc_priv", ppriv_size,
+ RTE_CACHE_LINE_SIZE, dev->device->numa_node);
+ if (!ppriv) {
+ rte_errno = ENOMEM;
+ return -rte_errno;
+ }
+ ppriv->uar_table_sz = ppriv_size;
+ dev->process_private = ppriv;
+ return 0;
+}
+
+/**
+ * Un-initialize process private data structure.
+ *
+ * @param dev
+ * Pointer to Ethernet device structure.
+ */
+static void
+mlx5_proc_priv_uninit(struct rte_eth_dev *dev)
+{
+ if (!dev->process_private)
+ return;
+ rte_free(dev->process_private);
+ dev->process_private = NULL;
+}
+
/**
* DPDK callback to close the device.
*
priv->txqs_n = 0;
priv->txqs = NULL;
}
+ mlx5_proc_priv_uninit(dev);
mlx5_mprq_free_mp(dev);
- mlx5_mr_release(dev);
+ /* Remove from memory callback device list. */
+ rte_rwlock_write_lock(&mlx5_shared_data->mem_event_rwlock);
assert(priv->sh);
+ LIST_REMOVE(priv->sh, mem_event_cb);
+ rte_rwlock_write_unlock(&mlx5_shared_data->mem_event_rwlock);
mlx5_free_shared_dr(priv);
- if (priv->sh)
- mlx5_free_shared_ibctx(priv->sh);
- priv->sh = NULL;
if (priv->rss_conf.rss_key != NULL)
rte_free(priv->rss_conf.rss_key);
if (priv->reta_idx != NULL)
close(priv->nl_socket_rdma);
if (priv->tcf_context)
mlx5_flow_tcf_context_destroy(priv->tcf_context);
+ if (priv->sh) {
+ /*
+ * Free the shared context in last turn, because the cleanup
+ * routines above may use some shared fields, like
+ * mlx5_nl_mac_addr_flush() uses ibdev_path for retrieveing
+ * ifindex if Netlink fails.
+ */
+ mlx5_free_shared_ibctx(priv->sh);
+ priv->sh = NULL;
+ }
ret = mlx5_hrxq_ibv_verify(dev);
if (ret)
DRV_LOG(WARNING, "port %u some hash Rx queue still remain",
config->l3_vxlan_en = !!tmp;
} else if (strcmp(MLX5_VF_NL_EN, key) == 0) {
config->vf_nl_en = !!tmp;
+ } else if (strcmp(MLX5_DV_ESW_EN, key) == 0) {
+ config->dv_esw_en = !!tmp;
} else if (strcmp(MLX5_DV_FLOW_EN, key) == 0) {
config->dv_flow_en = !!tmp;
} else if (strcmp(MLX5_MR_EXT_MEMSEG_EN, key) == 0) {
MLX5_RX_VEC_EN,
MLX5_L3_VXLAN_EN,
MLX5_VF_NL_EN,
+ MLX5_DV_ESW_EN,
MLX5_DV_FLOW_EN,
MLX5_MR_EXT_MEMSEG_EN,
MLX5_REPRESENTOR,
static struct rte_pci_driver mlx5_driver;
-static int
-find_lower_va_bound(const struct rte_memseg_list *msl,
- const struct rte_memseg *ms, void *arg)
-{
- void **addr = arg;
-
- if (msl->external)
- return 0;
- if (*addr == NULL)
- *addr = ms->addr;
- else
- *addr = RTE_MIN(*addr, ms->addr);
-
- return 0;
-}
-
-/**
- * Reserve UAR address space for primary process.
- *
- * Process local resource is used by both primary and secondary to avoid
- * duplicate reservation. The space has to be available on both primary and
- * secondary process, TXQ UAR maps to this area using fixed mmap w/o double
- * check.
- *
- * @return
- * 0 on success, a negative errno value otherwise and rte_errno is set.
- */
-static int
-mlx5_uar_init_primary(void)
-{
- struct mlx5_shared_data *sd = mlx5_shared_data;
- void *addr = (void *)0;
-
- if (sd->uar_base)
- return 0;
- /* find out lower bound of hugepage segments */
- rte_memseg_walk(find_lower_va_bound, &addr);
- /* keep distance to hugepages to minimize potential conflicts. */
- addr = RTE_PTR_SUB(addr, (uintptr_t)(MLX5_UAR_OFFSET + MLX5_UAR_SIZE));
- /* anonymous mmap, no real memory consumption. */
- addr = mmap(addr, MLX5_UAR_SIZE,
- PROT_NONE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
- if (addr == MAP_FAILED) {
- DRV_LOG(ERR,
- "Failed to reserve UAR address space, please"
- " adjust MLX5_UAR_SIZE or try --base-virtaddr");
- rte_errno = ENOMEM;
- return -rte_errno;
- }
- /* Accept either same addr or a new addr returned from mmap if target
- * range occupied.
- */
- DRV_LOG(INFO, "Reserved UAR address space: %p", addr);
- sd->uar_base = addr; /* for primary and secondary UAR re-mmap. */
- return 0;
-}
-
-/**
- * Unmap UAR address space reserved for primary process.
- */
-static void
-mlx5_uar_uninit_primary(void)
-{
- struct mlx5_shared_data *sd = mlx5_shared_data;
-
- if (!sd->uar_base)
- return;
- munmap(sd->uar_base, MLX5_UAR_SIZE);
- sd->uar_base = NULL;
-}
-
-/**
- * Reserve UAR address space for secondary process, align with primary process.
- *
- * @return
- * 0 on success, a negative errno value otherwise and rte_errno is set.
- */
-static int
-mlx5_uar_init_secondary(void)
-{
- struct mlx5_shared_data *sd = mlx5_shared_data;
- struct mlx5_local_data *ld = &mlx5_local_data;
- void *addr;
-
- if (ld->uar_base) { /* Already reserved. */
- assert(sd->uar_base == ld->uar_base);
- return 0;
- }
- assert(sd->uar_base);
- /* anonymous mmap, no real memory consumption. */
- addr = mmap(sd->uar_base, MLX5_UAR_SIZE,
- PROT_NONE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
- if (addr == MAP_FAILED) {
- DRV_LOG(ERR, "UAR mmap failed: %p size: %llu",
- sd->uar_base, MLX5_UAR_SIZE);
- rte_errno = ENXIO;
- return -rte_errno;
- }
- if (sd->uar_base != addr) {
- DRV_LOG(ERR,
- "UAR address %p size %llu occupied, please"
- " adjust MLX5_UAR_OFFSET or try EAL parameter"
- " --base-virtaddr",
- sd->uar_base, MLX5_UAR_SIZE);
- rte_errno = ENXIO;
- return -rte_errno;
- }
- ld->uar_base = addr;
- DRV_LOG(INFO, "Reserved UAR address space: %p", addr);
- return 0;
-}
-
-/**
- * Unmap UAR address space reserved for secondary process.
- */
-static void
-mlx5_uar_uninit_secondary(void)
-{
- struct mlx5_local_data *ld = &mlx5_local_data;
-
- if (!ld->uar_base)
- return;
- munmap(ld->uar_base, MLX5_UAR_SIZE);
- ld->uar_base = NULL;
-}
-
/**
* PMD global initialization.
*
{
struct mlx5_shared_data *sd;
struct mlx5_local_data *ld = &mlx5_local_data;
- int ret;
if (mlx5_init_shared_data())
return -rte_errno;
rte_mem_event_callback_register("MLX5_MEM_EVENT_CB",
mlx5_mr_mem_event_cb, NULL);
mlx5_mp_init_primary();
- ret = mlx5_uar_init_primary();
- if (ret)
- goto error;
sd->init_done = true;
break;
case RTE_PROC_SECONDARY:
if (ld->init_done)
break;
mlx5_mp_init_secondary();
- ret = mlx5_uar_init_secondary();
- if (ret)
- goto error;
++sd->secondary_cnt;
ld->init_done = true;
break;
}
rte_spinlock_unlock(&sd->lock);
return 0;
-error:
- switch (rte_eal_process_type()) {
- case RTE_PROC_PRIMARY:
- mlx5_uar_uninit_primary();
- mlx5_mp_uninit_primary();
- rte_mem_event_callback_unregister("MLX5_MEM_EVENT_CB", NULL);
- break;
- case RTE_PROC_SECONDARY:
- mlx5_uar_uninit_secondary();
- mlx5_mp_uninit_secondary();
- break;
- default:
- break;
- }
- rte_spinlock_unlock(&sd->lock);
- mlx5_uninit_shared_data();
- return -rte_errno;
}
/**
unsigned int mprq_max_stride_size_n = 0;
unsigned int mprq_min_stride_num_n = 0;
unsigned int mprq_max_stride_num_n = 0;
- struct ether_addr mac;
+ struct rte_ether_addr mac;
char name[RTE_ETH_NAME_MAX_LEN];
int own_domain_id = 0;
uint16_t port_id;
}
eth_dev->device = dpdk_dev;
eth_dev->dev_ops = &mlx5_dev_sec_ops;
+ err = mlx5_proc_priv_init(eth_dev);
+ if (err)
+ return NULL;
/* Receive command fd from primary process */
err = mlx5_mp_req_verbs_cmd_fd(eth_dev);
if (err < 0)
return NULL;
/* Remap UAR for Tx queues. */
- err = mlx5_tx_uar_remap(eth_dev, err);
+ err = mlx5_tx_uar_init_secondary(eth_dev, err);
if (err)
return NULL;
/*
* Currently we support single E-Switch per PF configurations
* only and vport_id field contains the vport index for
* associated VF, which is deduced from representor port name.
- * For exapmple, let's have the IB device port 10, it has
+ * For example, let's have the IB device port 10, it has
* attached network device eth0, which has port name attribute
* pf0vf2, we can deduce the VF number as 2, and set vport index
* as 3 (2+1). This assigning schema should be changed if the
priv->tcf_context = NULL;
}
}
- if (config.dv_flow_en) {
- err = mlx5_alloc_shared_dr(priv);
- if (err)
- goto error;
- }
TAILQ_INIT(&priv->flows);
TAILQ_INIT(&priv->ctrl_flows);
/* Hint libmlx5 to use PMD allocator for data plane resources */
mlx5_set_link_up(eth_dev);
/*
* Even though the interrupt handler is not installed yet,
- * interrupts will still trigger on the asyn_fd from
+ * interrupts will still trigger on the async_fd from
* Verbs context returned by ibv_open_device().
*/
mlx5_link_update(eth_dev, 0);
+#ifdef HAVE_IBV_DEVX_OBJ
+ if (config.devx) {
+ err = mlx5_devx_cmd_query_hca_attr(sh->ctx, &config.hca_attr);
+ if (err) {
+ err = -err;
+ goto error;
+ }
+ }
+#endif
+#ifdef HAVE_MLX5DV_DR_ESWITCH
+ if (!(config.hca_attr.eswitch_manager && config.dv_flow_en &&
+ (switch_info->representor || switch_info->master)))
+ config.dv_esw_en = 0;
+#else
+ config.dv_esw_en = 0;
+#endif
/* Store device configuration on private structure. */
priv->config = config;
+ if (config.dv_flow_en) {
+ err = mlx5_alloc_shared_dr(priv);
+ if (err)
+ goto error;
+ }
/* Supported Verbs flow priority number detection. */
err = mlx5_flow_discover_priorities(eth_dev);
if (err < 0) {
goto error;
}
priv->config.flow_prio = err;
- /*
- * Once the device is added to the list of memory event
- * callback, its global MR cache table cannot be expanded
- * on the fly because of deadlock. If it overflows, lookup
- * should be done by searching MR list linearly, which is slow.
- */
- err = mlx5_mr_btree_init(&priv->mr.cache,
- MLX5_MR_BTREE_CACHE_N * 2,
- eth_dev->device->numa_node);
- if (err) {
- err = rte_errno;
- goto error;
- }
/* Add device to memory callback list. */
rte_rwlock_write_lock(&mlx5_shared_data->mem_event_rwlock);
LIST_INSERT_HEAD(&mlx5_shared_data->mem_event_cb_list,
- priv, mem_event_cb);
+ sh, mem_event_cb);
rte_rwlock_write_unlock(&mlx5_shared_data->mem_event_rwlock);
return eth_dev;
error:
}
ibv_match[nd] = NULL;
if (!nd) {
- /* No device macthes, just complain and bail out. */
+ /* No device matches, just complain and bail out. */
mlx5_glue->free_device_list(ibv_list);
DRV_LOG(WARNING,
"no Verbs device matches PCI device " PCI_PRI_FMT ","
if (np > 1) {
/*
- * Signle IB device with multiple ports found,
+ * Single IB device with multiple ports found,
* it may be E-Switch master device and representors.
* We have to perform identification trough the ports.
*/
list[ns].ibv_port = i;
list[ns].ibv_dev = ibv_match[0];
list[ns].eth_dev = NULL;
+ list[ns].pci_dev = pci_dev;
list[ns].ifindex = mlx5_nl_ifindex
(nl_rdma, list[ns].ibv_dev->name, i);
if (!list[ns].ifindex) {
list[ns].ibv_port = 1;
list[ns].ibv_dev = ibv_match[i];
list[ns].eth_dev = NULL;
+ list[ns].pci_dev = pci_dev;
list[ns].ifindex = 0;
if (nl_rdma >= 0)
list[ns].ifindex = mlx5_nl_ifindex
(nl_rdma, list[ns].ibv_dev->name, 1);
if (!list[ns].ifindex) {
+ char ifname[IF_NAMESIZE];
+
/*
- * No network interface index found for the
- * specified device, it means there it is not
- * a representor/master.
+ * Netlink failed, it may happen with old
+ * ib_core kernel driver (before 4.16).
+ * We can assume there is old driver because
+ * here we are processing single ports IB
+ * devices. Let's try sysfs to retrieve
+ * the ifindex. The method works for
+ * master device only.
*/
- continue;
+ if (nd > 1) {
+ /*
+ * Multiple devices found, assume
+ * representors, can not distinguish
+ * master/representor and retrieve
+ * ifindex via sysfs.
+ */
+ continue;
+ }
+ ret = mlx5_get_master_ifname
+ (ibv_match[i]->ibdev_path, &ifname);
+ if (!ret)
+ list[ns].ifindex =
+ if_nametoindex(ifname);
+ if (!list[ns].ifindex) {
+ /*
+ * No network interface index found
+ * for the specified device, it means
+ * there it is neither representor
+ * nor master.
+ */
+ continue;
+ }
}
ret = -1;
if (nl_route >= 0)
.max_memcpy_len = MLX5_MPRQ_MEMCPY_DEFAULT_LEN,
.min_rxqs_num = MLX5_MPRQ_MIN_RXQS,
},
+ .dv_esw_en = 1,
};
/* Device specific configuration. */
switch (pci_dev->id.device_id) {
mlx5_pci_remove(struct rte_pci_device *pci_dev)
{
uint16_t port_id;
- struct rte_eth_dev *port;
- for (port_id = 0; port_id < RTE_MAX_ETHPORTS; port_id++) {
- port = &rte_eth_devices[port_id];
- if (port->state != RTE_ETH_DEV_UNUSED &&
- port->device == &pci_dev->device)
- rte_eth_dev_close(port_id);
- }
+ RTE_ETH_FOREACH_DEV_OF(port_id, &pci_dev->device)
+ rte_eth_dev_close(port_id);
return 0;
}
git.droids-corp.org / dpdk.git / blobdiff