X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=drivers%2Fnet%2Fenic%2Fenic_ethdev.c;h=71e1b9c7d664a9a6b5cbb5dd0821d4a649e22af6;hb=6d13ea8e8e49ab957deae2bba5ecf4a4bfe747d1;hp=6ebad8d966473d46553e2ebd2c81bc778681516b;hpb=2a7e3d54659cd12d337ad816dcf202eec1af1367;p=dpdk.git diff --git a/drivers/net/enic/enic_ethdev.c b/drivers/net/enic/enic_ethdev.c index 6ebad8d966..71e1b9c7d6 100644 --- a/drivers/net/enic/enic_ethdev.c +++ b/drivers/net/enic/enic_ethdev.c @@ -24,10 +24,6 @@ int enicpmd_logtype_init; int enicpmd_logtype_flow; -#define PMD_INIT_LOG(level, fmt, args...) \ - rte_log(RTE_LOG_ ## level, enicpmd_logtype_init, \ - "%s" fmt "\n", __func__, ##args) - #define ENICPMD_FUNC_TRACE() PMD_INIT_LOG(DEBUG, " >>") /* @@ -41,10 +37,10 @@ static const struct rte_pci_id pci_id_enic_map[] = { }; #define ENIC_DEVARG_DISABLE_OVERLAY "disable-overlay" +#define ENIC_DEVARG_ENABLE_AVX2_RX "enable-avx2-rx" +#define ENIC_DEVARG_IG_VLAN_REWRITE "ig-vlan-rewrite" -RTE_INIT(enicpmd_init_log); -static void -enicpmd_init_log(void) +RTE_INIT(enicpmd_init_log) { enicpmd_logtype_init = rte_log_register("pmd.net.enic.init"); if (enicpmd_logtype_init >= 0) @@ -184,17 +180,21 @@ static int enicpmd_dev_tx_queue_setup(struct rte_eth_dev *eth_dev, uint16_t queue_idx, uint16_t nb_desc, unsigned int socket_id, - __rte_unused const struct rte_eth_txconf *tx_conf) + const struct rte_eth_txconf *tx_conf) { int ret; struct enic *enic = pmd_priv(eth_dev); + struct vnic_wq *wq; if (rte_eal_process_type() != RTE_PROC_PRIMARY) return -E_RTE_SECONDARY; ENICPMD_FUNC_TRACE(); RTE_ASSERT(queue_idx < enic->conf_wq_count); - eth_dev->data->tx_queues[queue_idx] = (void *)&enic->wq[queue_idx]; + wq = &enic->wq[queue_idx]; + wq->offloads = tx_conf->offloads | + eth_dev->data->dev_conf.txmode.offloads; + eth_dev->data->tx_queues[queue_idx] = (void *)wq; ret = enic_alloc_wq(enic, queue_idx, socket_id, nb_desc); if (ret) { @@ -367,6 +367,7 @@ static int enicpmd_dev_configure(struct rte_eth_dev *eth_dev) return ret; } + enic->mc_count = 0; enic->hw_ip_checksum = !!(eth_dev->data->dev_conf.rxmode.offloads & DEV_RX_OFFLOAD_CHECKSUM); /* All vlan offload masks to apply the current settings */ @@ -473,15 +474,40 @@ static void enicpmd_dev_info_get(struct rte_eth_dev *eth_dev, * ignoring vNIC mtu. */ device_info->max_rx_pktlen = enic_mtu_to_max_rx_pktlen(enic->max_mtu); - device_info->max_mac_addrs = ENIC_MAX_MAC_ADDR; + device_info->max_mac_addrs = ENIC_UNICAST_PERFECT_FILTERS; device_info->rx_offload_capa = enic->rx_offload_capa; device_info->tx_offload_capa = enic->tx_offload_capa; + device_info->tx_queue_offload_capa = enic->tx_queue_offload_capa; device_info->default_rxconf = (struct rte_eth_rxconf) { .rx_free_thresh = ENIC_DEFAULT_RX_FREE_THRESH }; device_info->reta_size = enic->reta_size; device_info->hash_key_size = enic->hash_key_size; device_info->flow_type_rss_offloads = enic->flow_type_rss_offloads; + device_info->rx_desc_lim = (struct rte_eth_desc_lim) { + .nb_max = enic->config.rq_desc_count, + .nb_min = ENIC_MIN_RQ_DESCS, + .nb_align = ENIC_ALIGN_DESCS, + }; + device_info->tx_desc_lim = (struct rte_eth_desc_lim) { + .nb_max = enic->config.wq_desc_count, + .nb_min = ENIC_MIN_WQ_DESCS, + .nb_align = ENIC_ALIGN_DESCS, + .nb_seg_max = ENIC_TX_XMIT_MAX, + .nb_mtu_seg_max = ENIC_NON_TSO_MAX_DESC, + }; + device_info->default_rxportconf = (struct rte_eth_dev_portconf) { + .burst_size = ENIC_DEFAULT_RX_BURST, + .ring_size = RTE_MIN(device_info->rx_desc_lim.nb_max, + ENIC_DEFAULT_RX_RING_SIZE), + .nb_queues = ENIC_DEFAULT_RX_RINGS, + }; + device_info->default_txportconf = (struct rte_eth_dev_portconf) { + .burst_size = ENIC_DEFAULT_TX_BURST, + .ring_size = RTE_MIN(device_info->tx_desc_lim.nb_max, + ENIC_DEFAULT_TX_RING_SIZE), + .nb_queues = ENIC_DEFAULT_TX_RINGS, + }; } static const uint32_t *enicpmd_dev_supported_ptypes_get(struct rte_eth_dev *dev) @@ -497,9 +523,34 @@ static const uint32_t *enicpmd_dev_supported_ptypes_get(struct rte_eth_dev *dev) RTE_PTYPE_L4_NONFRAG, RTE_PTYPE_UNKNOWN }; + static const uint32_t ptypes_overlay[] = { + RTE_PTYPE_L2_ETHER, + RTE_PTYPE_L2_ETHER_VLAN, + RTE_PTYPE_L3_IPV4_EXT_UNKNOWN, + RTE_PTYPE_L3_IPV6_EXT_UNKNOWN, + RTE_PTYPE_L4_TCP, + RTE_PTYPE_L4_UDP, + RTE_PTYPE_L4_FRAG, + RTE_PTYPE_L4_NONFRAG, + RTE_PTYPE_TUNNEL_GRENAT, + RTE_PTYPE_INNER_L2_ETHER, + RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN, + RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN, + RTE_PTYPE_INNER_L4_TCP, + RTE_PTYPE_INNER_L4_UDP, + RTE_PTYPE_INNER_L4_FRAG, + RTE_PTYPE_INNER_L4_NONFRAG, + RTE_PTYPE_UNKNOWN + }; - if (dev->rx_pkt_burst == enic_recv_pkts) - return ptypes; + if (dev->rx_pkt_burst != enic_dummy_recv_pkts && + dev->rx_pkt_burst != NULL) { + struct enic *enic = pmd_priv(dev); + if (enic->overlay_offload) + return ptypes_overlay; + else + return ptypes; + } return NULL; } @@ -553,7 +604,7 @@ static void enicpmd_dev_allmulticast_disable(struct rte_eth_dev *eth_dev) } static int enicpmd_add_mac_addr(struct rte_eth_dev *eth_dev, - struct ether_addr *mac_addr, + struct rte_ether_addr *mac_addr, __rte_unused uint32_t index, __rte_unused uint32_t pool) { struct enic *enic = pmd_priv(eth_dev); @@ -578,7 +629,7 @@ static void enicpmd_remove_mac_addr(struct rte_eth_dev *eth_dev, uint32_t index) } static int enicpmd_set_mac_addr(struct rte_eth_dev *eth_dev, - struct ether_addr *addr) + struct rte_ether_addr *addr) { struct enic *enic = pmd_priv(eth_dev); int ret; @@ -593,6 +644,97 @@ static int enicpmd_set_mac_addr(struct rte_eth_dev *eth_dev, return enic_set_mac_address(enic, addr->addr_bytes); } +static void debug_log_add_del_addr(struct rte_ether_addr *addr, bool add) +{ + char mac_str[ETHER_ADDR_FMT_SIZE]; + + ether_format_addr(mac_str, ETHER_ADDR_FMT_SIZE, addr); + PMD_INIT_LOG(DEBUG, " %s address %s\n", + add ? "add" : "remove", mac_str); +} + +static int enicpmd_set_mc_addr_list(struct rte_eth_dev *eth_dev, + struct rte_ether_addr *mc_addr_set, + uint32_t nb_mc_addr) +{ + struct enic *enic = pmd_priv(eth_dev); + char mac_str[ETHER_ADDR_FMT_SIZE]; + struct rte_ether_addr *addr; + uint32_t i, j; + int ret; + + ENICPMD_FUNC_TRACE(); + + /* Validate the given addresses first */ + for (i = 0; i < nb_mc_addr && mc_addr_set != NULL; i++) { + addr = &mc_addr_set[i]; + if (!is_multicast_ether_addr(addr) || + is_broadcast_ether_addr(addr)) { + ether_format_addr(mac_str, ETHER_ADDR_FMT_SIZE, addr); + PMD_INIT_LOG(ERR, " invalid multicast address %s\n", + mac_str); + return -EINVAL; + } + } + + /* Flush all if requested */ + if (nb_mc_addr == 0 || mc_addr_set == NULL) { + PMD_INIT_LOG(DEBUG, " flush multicast addresses\n"); + for (i = 0; i < enic->mc_count; i++) { + addr = &enic->mc_addrs[i]; + debug_log_add_del_addr(addr, false); + ret = vnic_dev_del_addr(enic->vdev, addr->addr_bytes); + if (ret) + return ret; + } + enic->mc_count = 0; + return 0; + } + + if (nb_mc_addr > ENIC_MULTICAST_PERFECT_FILTERS) { + PMD_INIT_LOG(ERR, " too many multicast addresses: max=%d\n", + ENIC_MULTICAST_PERFECT_FILTERS); + return -ENOSPC; + } + /* + * devcmd is slow, so apply the difference instead of flushing and + * adding everything. + * 1. Delete addresses on the NIC but not on the host + */ + for (i = 0; i < enic->mc_count; i++) { + addr = &enic->mc_addrs[i]; + for (j = 0; j < nb_mc_addr; j++) { + if (is_same_ether_addr(addr, &mc_addr_set[j])) + break; + } + if (j < nb_mc_addr) + continue; + debug_log_add_del_addr(addr, false); + ret = vnic_dev_del_addr(enic->vdev, addr->addr_bytes); + if (ret) + return ret; + } + /* 2. Add addresses on the host but not on the NIC */ + for (i = 0; i < nb_mc_addr; i++) { + addr = &mc_addr_set[i]; + for (j = 0; j < enic->mc_count; j++) { + if (is_same_ether_addr(addr, &enic->mc_addrs[j])) + break; + } + if (j < enic->mc_count) + continue; + debug_log_add_del_addr(addr, true); + ret = vnic_dev_add_addr(enic->vdev, addr->addr_bytes); + if (ret) + return ret; + } + /* Keep a copy so we can flush/apply later on.. */ + memcpy(enic->mc_addrs, mc_addr_set, + nb_mc_addr * sizeof(struct rte_ether_addr)); + enic->mc_count = nb_mc_addr; + return 0; +} + static int enicpmd_mtu_set(struct rte_eth_dev *eth_dev, uint16_t mtu) { struct enic *enic = pmd_priv(eth_dev); @@ -740,7 +882,7 @@ static void enicpmd_dev_txq_info_get(struct rte_eth_dev *dev, ENICPMD_FUNC_TRACE(); qinfo->nb_desc = wq->ring.desc_count; memset(&qinfo->conf, 0, sizeof(qinfo->conf)); - qinfo->conf.offloads = enic->tx_offload_capa; + qinfo->conf.offloads = wq->offloads; /* tx_thresh, and all the other fields are not applicable for enic */ } @@ -764,6 +906,99 @@ static int enicpmd_dev_rx_queue_intr_disable(struct rte_eth_dev *eth_dev, return 0; } +static int udp_tunnel_common_check(struct enic *enic, + struct rte_eth_udp_tunnel *tnl) +{ + if (tnl->prot_type != RTE_TUNNEL_TYPE_VXLAN) + return -ENOTSUP; + if (!enic->overlay_offload) { + PMD_INIT_LOG(DEBUG, " vxlan (overlay offload) is not " + "supported\n"); + return -ENOTSUP; + } + return 0; +} + +static int update_vxlan_port(struct enic *enic, uint16_t port) +{ + if (vnic_dev_overlay_offload_cfg(enic->vdev, + OVERLAY_CFG_VXLAN_PORT_UPDATE, + port)) { + PMD_INIT_LOG(DEBUG, " failed to update vxlan port\n"); + return -EINVAL; + } + PMD_INIT_LOG(DEBUG, " updated vxlan port to %u\n", port); + enic->vxlan_port = port; + return 0; +} + +static int enicpmd_dev_udp_tunnel_port_add(struct rte_eth_dev *eth_dev, + struct rte_eth_udp_tunnel *tnl) +{ + struct enic *enic = pmd_priv(eth_dev); + int ret; + + ENICPMD_FUNC_TRACE(); + ret = udp_tunnel_common_check(enic, tnl); + if (ret) + return ret; + /* + * The NIC has 1 configurable VXLAN port number. "Adding" a new port + * number replaces it. + */ + if (tnl->udp_port == enic->vxlan_port || tnl->udp_port == 0) { + PMD_INIT_LOG(DEBUG, " %u is already configured or invalid\n", + tnl->udp_port); + return -EINVAL; + } + return update_vxlan_port(enic, tnl->udp_port); +} + +static int enicpmd_dev_udp_tunnel_port_del(struct rte_eth_dev *eth_dev, + struct rte_eth_udp_tunnel *tnl) +{ + struct enic *enic = pmd_priv(eth_dev); + int ret; + + ENICPMD_FUNC_TRACE(); + ret = udp_tunnel_common_check(enic, tnl); + if (ret) + return ret; + /* + * Clear the previously set port number and restore the + * hardware default port number. Some drivers disable VXLAN + * offloads when there are no configured port numbers. But + * enic does not do that as VXLAN is part of overlay offload, + * which is tied to inner RSS and TSO. + */ + if (tnl->udp_port != enic->vxlan_port) { + PMD_INIT_LOG(DEBUG, " %u is not a configured vxlan port\n", + tnl->udp_port); + return -EINVAL; + } + return update_vxlan_port(enic, ENIC_DEFAULT_VXLAN_PORT); +} + +static int enicpmd_dev_fw_version_get(struct rte_eth_dev *eth_dev, + char *fw_version, size_t fw_size) +{ + struct vnic_devcmd_fw_info *info; + struct enic *enic; + int ret; + + ENICPMD_FUNC_TRACE(); + if (fw_version == NULL || fw_size <= 0) + return -EINVAL; + enic = pmd_priv(eth_dev); + ret = vnic_dev_fw_info(enic->vdev, &info); + if (ret) + return ret; + snprintf(fw_version, fw_size, "%s %s", + info->fw_version, info->fw_build); + fw_version[fw_size - 1] = '\0'; + return 0; +} + static const struct eth_dev_ops enicpmd_eth_dev_ops = { .dev_configure = enicpmd_dev_configure, .dev_start = enicpmd_dev_start, @@ -808,27 +1043,69 @@ static const struct eth_dev_ops enicpmd_eth_dev_ops = { .mac_addr_add = enicpmd_add_mac_addr, .mac_addr_remove = enicpmd_remove_mac_addr, .mac_addr_set = enicpmd_set_mac_addr, + .set_mc_addr_list = enicpmd_set_mc_addr_list, .filter_ctrl = enicpmd_dev_filter_ctrl, .reta_query = enicpmd_dev_rss_reta_query, .reta_update = enicpmd_dev_rss_reta_update, .rss_hash_conf_get = enicpmd_dev_rss_hash_conf_get, .rss_hash_update = enicpmd_dev_rss_hash_update, + .udp_tunnel_port_add = enicpmd_dev_udp_tunnel_port_add, + .udp_tunnel_port_del = enicpmd_dev_udp_tunnel_port_del, + .fw_version_get = enicpmd_dev_fw_version_get, }; -static int enic_parse_disable_overlay(__rte_unused const char *key, - const char *value, - void *opaque) +static int enic_parse_zero_one(const char *key, + const char *value, + void *opaque) { struct enic *enic; + bool b; enic = (struct enic *)opaque; if (strcmp(value, "0") == 0) { - enic->disable_overlay = false; + b = false; } else if (strcmp(value, "1") == 0) { - enic->disable_overlay = true; + b = true; + } else { + dev_err(enic, "Invalid value for %s" + ": expected=0|1 given=%s\n", key, value); + return -EINVAL; + } + if (strcmp(key, ENIC_DEVARG_DISABLE_OVERLAY) == 0) + enic->disable_overlay = b; + if (strcmp(key, ENIC_DEVARG_ENABLE_AVX2_RX) == 0) + enic->enable_avx2_rx = b; + return 0; +} + +static int enic_parse_ig_vlan_rewrite(__rte_unused const char *key, + const char *value, + void *opaque) +{ + struct enic *enic; + + enic = (struct enic *)opaque; + if (strcmp(value, "trunk") == 0) { + /* Trunk mode: always tag */ + enic->ig_vlan_rewrite_mode = IG_VLAN_REWRITE_MODE_DEFAULT_TRUNK; + } else if (strcmp(value, "untag") == 0) { + /* Untag default VLAN mode: untag if VLAN = default VLAN */ + enic->ig_vlan_rewrite_mode = + IG_VLAN_REWRITE_MODE_UNTAG_DEFAULT_VLAN; + } else if (strcmp(value, "priority") == 0) { + /* + * Priority-tag default VLAN mode: priority tag (VLAN header + * with ID=0) if VLAN = default + */ + enic->ig_vlan_rewrite_mode = + IG_VLAN_REWRITE_MODE_PRIORITY_TAG_DEFAULT_VLAN; + } else if (strcmp(value, "pass") == 0) { + /* Pass through mode: do not touch tags */ + enic->ig_vlan_rewrite_mode = IG_VLAN_REWRITE_MODE_PASS_THRU; } else { - dev_err(enic, "Invalid value for " ENIC_DEVARG_DISABLE_OVERLAY - ": expected=0|1 given=%s\n", value); + dev_err(enic, "Invalid value for " ENIC_DEVARG_IG_VLAN_REWRITE + ": expected=trunk|untag|priority|pass given=%s\n", + value); return -EINVAL; } return 0; @@ -837,20 +1114,29 @@ static int enic_parse_disable_overlay(__rte_unused const char *key, static int enic_check_devargs(struct rte_eth_dev *dev) { static const char *const valid_keys[] = { - ENIC_DEVARG_DISABLE_OVERLAY, NULL}; + ENIC_DEVARG_DISABLE_OVERLAY, + ENIC_DEVARG_ENABLE_AVX2_RX, + ENIC_DEVARG_IG_VLAN_REWRITE, + NULL}; struct enic *enic = pmd_priv(dev); struct rte_kvargs *kvlist; ENICPMD_FUNC_TRACE(); enic->disable_overlay = false; + enic->enable_avx2_rx = false; + enic->ig_vlan_rewrite_mode = IG_VLAN_REWRITE_MODE_PASS_THRU; if (!dev->device->devargs) return 0; kvlist = rte_kvargs_parse(dev->device->devargs->args, valid_keys); if (!kvlist) return -EINVAL; if (rte_kvargs_process(kvlist, ENIC_DEVARG_DISABLE_OVERLAY, - enic_parse_disable_overlay, enic) < 0) { + enic_parse_zero_one, enic) < 0 || + rte_kvargs_process(kvlist, ENIC_DEVARG_ENABLE_AVX2_RX, + enic_parse_zero_one, enic) < 0 || + rte_kvargs_process(kvlist, ENIC_DEVARG_IG_VLAN_REWRITE, + enic_parse_ig_vlan_rewrite, enic) < 0) { rte_kvargs_free(kvlist); return -EINVAL; } @@ -858,7 +1144,6 @@ static int enic_check_devargs(struct rte_eth_dev *dev) return 0; } -struct enic *enicpmd_list_head = NULL; /* Initialize the driver * It returns 0 on success. */ @@ -877,6 +1162,8 @@ static int eth_enicpmd_dev_init(struct rte_eth_dev *eth_dev) eth_dev->rx_pkt_burst = &enic_recv_pkts; eth_dev->tx_pkt_burst = &enic_xmit_pkts; eth_dev->tx_pkt_prepare = &enic_prep_pkts; + /* Let rte_eth_dev_close() release the port resources */ + eth_dev->data->dev_flags |= RTE_ETH_DEV_CLOSE_REMOVE; pdev = RTE_ETH_DEV_TO_PCI(eth_dev); rte_eth_copy_pci_info(eth_dev, pdev); @@ -906,7 +1193,8 @@ static int eth_enic_pci_remove(struct rte_pci_device *pci_dev) static struct rte_pci_driver rte_enic_pmd = { .id_table = pci_id_enic_map, - .drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC, + .drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC | + RTE_PCI_DRV_IOVA_AS_VA, .probe = eth_enic_pci_probe, .remove = eth_enic_pci_remove, }; @@ -915,4 +1203,6 @@ RTE_PMD_REGISTER_PCI(net_enic, rte_enic_pmd); RTE_PMD_REGISTER_PCI_TABLE(net_enic, pci_id_enic_map); RTE_PMD_REGISTER_KMOD_DEP(net_enic, "* igb_uio | uio_pci_generic | vfio-pci"); RTE_PMD_REGISTER_PARAM_STRING(net_enic, - ENIC_DEVARG_DISABLE_OVERLAY "=<0|1> "); + ENIC_DEVARG_DISABLE_OVERLAY "=0|1 " + ENIC_DEVARG_ENABLE_AVX2_RX "=0|1 " + ENIC_DEVARG_IG_VLAN_REWRITE "=trunk|untag|priority|pass");