- if (ret) {
- rte_errno = EINVAL;
- rte_kvargs_free(kvlist);
- return -rte_errno;
- }
- }
- }
- rte_kvargs_free(kvlist);
- return 0;
-}
-
-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.
- *
- * Independent from individual device, this function initializes global
- * per-PMD data structures distinguishing primary and secondary processes.
- * Hence, each initialization is called once per a process.
- *
- * @return
- * 0 on success, a negative errno value otherwise and rte_errno is set.
- */
-static int
-mlx5_init_once(void)
-{
- struct mlx5_shared_data *sd;
- struct mlx5_local_data *ld = &mlx5_local_data;
- int ret;
-
- if (mlx5_init_shared_data())
- return -rte_errno;
- sd = mlx5_shared_data;
- assert(sd);
- rte_spinlock_lock(&sd->lock);
- switch (rte_eal_process_type()) {
- case RTE_PROC_PRIMARY:
- if (sd->init_done)
- break;
- LIST_INIT(&sd->mem_event_cb_list);
- rte_rwlock_init(&sd->mem_event_rwlock);
- 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;
- default:
- 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;
-}
-
-/**
- * Spawn an Ethernet device from Verbs information.
- *
- * @param dpdk_dev
- * Backing DPDK device.
- * @param spawn
- * Verbs device parameters (name, port, switch_info) to spawn.
- * @param config
- * Device configuration parameters.
- *
- * @return
- * A valid Ethernet device object on success, NULL otherwise and rte_errno
- * is set. The following errors are defined:
- *
- * EBUSY: device is not supposed to be spawned.
- * EEXIST: device is already spawned
- */
-static struct rte_eth_dev *
-mlx5_dev_spawn(struct rte_device *dpdk_dev,
- struct mlx5_dev_spawn_data *spawn,
- struct mlx5_dev_config config)
-{
- const struct mlx5_switch_info *switch_info = &spawn->info;
- struct mlx5_ibv_shared *sh = NULL;
- struct ibv_port_attr port_attr;
- struct mlx5dv_context dv_attr = { .comp_mask = 0 };
- struct rte_eth_dev *eth_dev = NULL;
- struct mlx5_priv *priv = NULL;
- int err = 0;
- unsigned int hw_padding = 0;
- unsigned int mps;
- unsigned int cqe_comp;
- unsigned int cqe_pad = 0;
- unsigned int tunnel_en = 0;
- unsigned int mpls_en = 0;
- unsigned int swp = 0;
- unsigned int mprq = 0;
- unsigned int mprq_min_stride_size_n = 0;
- 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;
- char name[RTE_ETH_NAME_MAX_LEN];
- int own_domain_id = 0;
- uint16_t port_id;
- unsigned int i;
-
- /* Determine if this port representor is supposed to be spawned. */
- if (switch_info->representor && dpdk_dev->devargs) {
- struct rte_eth_devargs eth_da;
-
- err = rte_eth_devargs_parse(dpdk_dev->devargs->args, ð_da);
- if (err) {
- rte_errno = -err;
- DRV_LOG(ERR, "failed to process device arguments: %s",
- strerror(rte_errno));
- return NULL;
- }
- for (i = 0; i < eth_da.nb_representor_ports; ++i)
- if (eth_da.representor_ports[i] ==
- (uint16_t)switch_info->port_name)
- break;
- if (i == eth_da.nb_representor_ports) {
- rte_errno = EBUSY;
- return NULL;
- }
- }
- /* Build device name. */
- if (!switch_info->representor)
- strlcpy(name, dpdk_dev->name, sizeof(name));
- else
- snprintf(name, sizeof(name), "%s_representor_%u",
- dpdk_dev->name, switch_info->port_name);
- /* check if the device is already spawned */
- if (rte_eth_dev_get_port_by_name(name, &port_id) == 0) {
- rte_errno = EEXIST;
- return NULL;
- }
- DRV_LOG(DEBUG, "naming Ethernet device \"%s\"", name);
- if (rte_eal_process_type() == RTE_PROC_SECONDARY) {
- eth_dev = rte_eth_dev_attach_secondary(name);
- if (eth_dev == NULL) {
- DRV_LOG(ERR, "can not attach rte ethdev");
- rte_errno = ENOMEM;
- return NULL;
- }
- eth_dev->device = dpdk_dev;
- eth_dev->dev_ops = &mlx5_dev_sec_ops;
- /* 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);
- if (err)
- return NULL;
- /*
- * Ethdev pointer is still required as input since
- * the primary device is not accessible from the
- * secondary process.
- */
- eth_dev->rx_pkt_burst = mlx5_select_rx_function(eth_dev);
- eth_dev->tx_pkt_burst = mlx5_select_tx_function(eth_dev);
- return eth_dev;
- }
- sh = mlx5_alloc_shared_ibctx(spawn);
- if (!sh)
- return NULL;
- config.devx = sh->devx;
-#ifdef HAVE_IBV_MLX5_MOD_SWP
- dv_attr.comp_mask |= MLX5DV_CONTEXT_MASK_SWP;
-#endif
- /*
- * Multi-packet send is supported by ConnectX-4 Lx PF as well
- * as all ConnectX-5 devices.
- */
-#ifdef HAVE_IBV_DEVICE_TUNNEL_SUPPORT
- dv_attr.comp_mask |= MLX5DV_CONTEXT_MASK_TUNNEL_OFFLOADS;
-#endif
-#ifdef HAVE_IBV_DEVICE_STRIDING_RQ_SUPPORT
- dv_attr.comp_mask |= MLX5DV_CONTEXT_MASK_STRIDING_RQ;
-#endif
- mlx5_glue->dv_query_device(sh->ctx, &dv_attr);
- if (dv_attr.flags & MLX5DV_CONTEXT_FLAGS_MPW_ALLOWED) {
- if (dv_attr.flags & MLX5DV_CONTEXT_FLAGS_ENHANCED_MPW) {
- DRV_LOG(DEBUG, "enhanced MPW is supported");
- mps = MLX5_MPW_ENHANCED;
- } else {
- DRV_LOG(DEBUG, "MPW is supported");
- mps = MLX5_MPW;
- }
- } else {
- DRV_LOG(DEBUG, "MPW isn't supported");
- mps = MLX5_MPW_DISABLED;
- }
-#ifdef HAVE_IBV_MLX5_MOD_SWP
- if (dv_attr.comp_mask & MLX5DV_CONTEXT_MASK_SWP)
- swp = dv_attr.sw_parsing_caps.sw_parsing_offloads;
- DRV_LOG(DEBUG, "SWP support: %u", swp);
-#endif
- config.swp = !!swp;
-#ifdef HAVE_IBV_DEVICE_STRIDING_RQ_SUPPORT
- if (dv_attr.comp_mask & MLX5DV_CONTEXT_MASK_STRIDING_RQ) {
- struct mlx5dv_striding_rq_caps mprq_caps =
- dv_attr.striding_rq_caps;
-
- DRV_LOG(DEBUG, "\tmin_single_stride_log_num_of_bytes: %d",
- mprq_caps.min_single_stride_log_num_of_bytes);
- DRV_LOG(DEBUG, "\tmax_single_stride_log_num_of_bytes: %d",
- mprq_caps.max_single_stride_log_num_of_bytes);
- DRV_LOG(DEBUG, "\tmin_single_wqe_log_num_of_strides: %d",
- mprq_caps.min_single_wqe_log_num_of_strides);
- DRV_LOG(DEBUG, "\tmax_single_wqe_log_num_of_strides: %d",
- mprq_caps.max_single_wqe_log_num_of_strides);
- DRV_LOG(DEBUG, "\tsupported_qpts: %d",
- mprq_caps.supported_qpts);
- DRV_LOG(DEBUG, "device supports Multi-Packet RQ");
- mprq = 1;
- mprq_min_stride_size_n =
- mprq_caps.min_single_stride_log_num_of_bytes;
- mprq_max_stride_size_n =
- mprq_caps.max_single_stride_log_num_of_bytes;
- mprq_min_stride_num_n =
- mprq_caps.min_single_wqe_log_num_of_strides;
- mprq_max_stride_num_n =
- mprq_caps.max_single_wqe_log_num_of_strides;
- config.mprq.stride_num_n = RTE_MAX(MLX5_MPRQ_STRIDE_NUM_N,
- mprq_min_stride_num_n);
- }
-#endif
- if (RTE_CACHE_LINE_SIZE == 128 &&
- !(dv_attr.flags & MLX5DV_CONTEXT_FLAGS_CQE_128B_COMP))
- cqe_comp = 0;
- else
- cqe_comp = 1;
- config.cqe_comp = cqe_comp;
-#ifdef HAVE_IBV_MLX5_MOD_CQE_128B_PAD
- /* Whether device supports 128B Rx CQE padding. */
- cqe_pad = RTE_CACHE_LINE_SIZE == 128 &&
- (dv_attr.flags & MLX5DV_CONTEXT_FLAGS_CQE_128B_PAD);
-#endif
-#ifdef HAVE_IBV_DEVICE_TUNNEL_SUPPORT
- if (dv_attr.comp_mask & MLX5DV_CONTEXT_MASK_TUNNEL_OFFLOADS) {
- tunnel_en = ((dv_attr.tunnel_offloads_caps &
- MLX5DV_RAW_PACKET_CAP_TUNNELED_OFFLOAD_VXLAN) &&
- (dv_attr.tunnel_offloads_caps &
- MLX5DV_RAW_PACKET_CAP_TUNNELED_OFFLOAD_GRE));
- }
- DRV_LOG(DEBUG, "tunnel offloading is %ssupported",
- tunnel_en ? "" : "not ");
-#else
- DRV_LOG(WARNING,
- "tunnel offloading disabled due to old OFED/rdma-core version");
-#endif
- config.tunnel_en = tunnel_en;
-#ifdef HAVE_IBV_DEVICE_MPLS_SUPPORT
- mpls_en = ((dv_attr.tunnel_offloads_caps &
- MLX5DV_RAW_PACKET_CAP_TUNNELED_OFFLOAD_CW_MPLS_OVER_GRE) &&
- (dv_attr.tunnel_offloads_caps &
- MLX5DV_RAW_PACKET_CAP_TUNNELED_OFFLOAD_CW_MPLS_OVER_UDP));
- DRV_LOG(DEBUG, "MPLS over GRE/UDP tunnel offloading is %ssupported",
- mpls_en ? "" : "not ");
-#else
- DRV_LOG(WARNING, "MPLS over GRE/UDP tunnel offloading disabled due to"
- " old OFED/rdma-core version or firmware configuration");
-#endif
- config.mpls_en = mpls_en;
- /* Check port status. */
- err = mlx5_glue->query_port(sh->ctx, spawn->ibv_port, &port_attr);
- if (err) {
- DRV_LOG(ERR, "port query failed: %s", strerror(err));
- goto error;
- }
- if (port_attr.link_layer != IBV_LINK_LAYER_ETHERNET) {
- DRV_LOG(ERR, "port is not configured in Ethernet mode");
- err = EINVAL;
- goto error;
- }
- if (port_attr.state != IBV_PORT_ACTIVE)
- DRV_LOG(DEBUG, "port is not active: \"%s\" (%d)",
- mlx5_glue->port_state_str(port_attr.state),
- port_attr.state);
- /* Allocate private eth device data. */
- priv = rte_zmalloc("ethdev private structure",
- sizeof(*priv),
- RTE_CACHE_LINE_SIZE);
- if (priv == NULL) {
- DRV_LOG(ERR, "priv allocation failure");
- err = ENOMEM;
- goto error;
- }
- priv->sh = sh;
- priv->ibv_port = spawn->ibv_port;
- priv->mtu = ETHER_MTU;
-#ifndef RTE_ARCH_64
- /* Initialize UAR access locks for 32bit implementations. */
- rte_spinlock_init(&priv->uar_lock_cq);
- for (i = 0; i < MLX5_UAR_PAGE_NUM_MAX; i++)
- rte_spinlock_init(&priv->uar_lock[i]);
-#endif
- /* Some internal functions rely on Netlink sockets, open them now. */
- priv->nl_socket_rdma = mlx5_nl_init(NETLINK_RDMA);
- priv->nl_socket_route = mlx5_nl_init(NETLINK_ROUTE);
- priv->nl_sn = 0;
- priv->representor = !!switch_info->representor;
- priv->master = !!switch_info->master;
- priv->domain_id = RTE_ETH_DEV_SWITCH_DOMAIN_ID_INVALID;
- /*
- * 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 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
- * multiple E-Switch instances per PF configurations or/and PCI
- * subfunctions are added.
- */
- priv->vport_id = switch_info->representor ?
- switch_info->port_name + 1 : -1;
- /* representor_id field keeps the unmodified port/VF index. */
- priv->representor_id = switch_info->representor ?
- switch_info->port_name : -1;
- /*
- * Look for sibling devices in order to reuse their switch domain
- * if any, otherwise allocate one.
- */
- RTE_ETH_FOREACH_DEV_OF(port_id, dpdk_dev) {
- const struct mlx5_priv *opriv =
- rte_eth_devices[port_id].data->dev_private;
-
- if (!opriv ||
- opriv->domain_id ==
- RTE_ETH_DEV_SWITCH_DOMAIN_ID_INVALID)
- continue;
- priv->domain_id = opriv->domain_id;
- break;
- }
- if (priv->domain_id == RTE_ETH_DEV_SWITCH_DOMAIN_ID_INVALID) {
- err = rte_eth_switch_domain_alloc(&priv->domain_id);
- if (err) {
- err = rte_errno;
- DRV_LOG(ERR, "unable to allocate switch domain: %s",
- strerror(rte_errno));
- goto error;
- }
- own_domain_id = 1;
- }
- err = mlx5_args(&config, dpdk_dev->devargs);
- if (err) {
- err = rte_errno;
- DRV_LOG(ERR, "failed to process device arguments: %s",
- strerror(rte_errno));
- goto error;
- }
- config.hw_csum = !!(sh->device_attr.device_cap_flags_ex &
- IBV_DEVICE_RAW_IP_CSUM);
- DRV_LOG(DEBUG, "checksum offloading is %ssupported",
- (config.hw_csum ? "" : "not "));
-#if !defined(HAVE_IBV_DEVICE_COUNTERS_SET_V42) && \
- !defined(HAVE_IBV_DEVICE_COUNTERS_SET_V45)
- DRV_LOG(DEBUG, "counters are not supported");
-#endif
-#ifndef HAVE_IBV_FLOW_DV_SUPPORT
- if (config.dv_flow_en) {
- DRV_LOG(WARNING, "DV flow is not supported");
- config.dv_flow_en = 0;
- }
-#endif
- config.ind_table_max_size =
- sh->device_attr.rss_caps.max_rwq_indirection_table_size;
- /*
- * Remove this check once DPDK supports larger/variable
- * indirection tables.
- */
- if (config.ind_table_max_size > (unsigned int)ETH_RSS_RETA_SIZE_512)
- config.ind_table_max_size = ETH_RSS_RETA_SIZE_512;
- DRV_LOG(DEBUG, "maximum Rx indirection table size is %u",
- config.ind_table_max_size);
- config.hw_vlan_strip = !!(sh->device_attr.raw_packet_caps &
- IBV_RAW_PACKET_CAP_CVLAN_STRIPPING);
- DRV_LOG(DEBUG, "VLAN stripping is %ssupported",
- (config.hw_vlan_strip ? "" : "not "));
- config.hw_fcs_strip = !!(sh->device_attr.raw_packet_caps &
- IBV_RAW_PACKET_CAP_SCATTER_FCS);
- DRV_LOG(DEBUG, "FCS stripping configuration is %ssupported",
- (config.hw_fcs_strip ? "" : "not "));
-#if defined(HAVE_IBV_WQ_FLAG_RX_END_PADDING)
- hw_padding = !!sh->device_attr.rx_pad_end_addr_align;
-#elif defined(HAVE_IBV_WQ_FLAGS_PCI_WRITE_END_PADDING)
- hw_padding = !!(sh->device_attr.device_cap_flags_ex &
- IBV_DEVICE_PCI_WRITE_END_PADDING);
-#endif
- if (config.hw_padding && !hw_padding) {
- DRV_LOG(DEBUG, "Rx end alignment padding isn't supported");
- config.hw_padding = 0;
- } else if (config.hw_padding) {
- DRV_LOG(DEBUG, "Rx end alignment padding is enabled");
- }
- config.tso = (sh->device_attr.tso_caps.max_tso > 0 &&
- (sh->device_attr.tso_caps.supported_qpts &
- (1 << IBV_QPT_RAW_PACKET)));
- if (config.tso)
- config.tso_max_payload_sz = sh->device_attr.tso_caps.max_tso;
- /*
- * MPW is disabled by default, while the Enhanced MPW is enabled
- * by default.
- */
- if (config.mps == MLX5_ARG_UNSET)
- config.mps = (mps == MLX5_MPW_ENHANCED) ? MLX5_MPW_ENHANCED :
- MLX5_MPW_DISABLED;
- else
- config.mps = config.mps ? mps : MLX5_MPW_DISABLED;
- DRV_LOG(INFO, "%sMPS is %s",
- config.mps == MLX5_MPW_ENHANCED ? "enhanced " : "",
- config.mps != MLX5_MPW_DISABLED ? "enabled" : "disabled");
- if (config.cqe_comp && !cqe_comp) {
- DRV_LOG(WARNING, "Rx CQE compression isn't supported");
- config.cqe_comp = 0;
- }
- if (config.cqe_pad && !cqe_pad) {
- DRV_LOG(WARNING, "Rx CQE padding isn't supported");
- config.cqe_pad = 0;
- } else if (config.cqe_pad) {
- DRV_LOG(INFO, "Rx CQE padding is enabled");
- }
- if (config.mprq.enabled && mprq) {
- if (config.mprq.stride_num_n > mprq_max_stride_num_n ||
- config.mprq.stride_num_n < mprq_min_stride_num_n) {
- config.mprq.stride_num_n =
- RTE_MAX(MLX5_MPRQ_STRIDE_NUM_N,
- mprq_min_stride_num_n);
- DRV_LOG(WARNING,
- "the number of strides"
- " for Multi-Packet RQ is out of range,"
- " setting default value (%u)",
- 1 << config.mprq.stride_num_n);