diff options
Diffstat (limited to 'drivers/net/ethernet/mellanox')
128 files changed, 7717 insertions, 3529 deletions
diff --git a/drivers/net/ethernet/mellanox/mlx4/Kconfig b/drivers/net/ethernet/mellanox/mlx4/Kconfig index 400e611ba041..1b4b1f642317 100644 --- a/drivers/net/ethernet/mellanox/mlx4/Kconfig +++ b/drivers/net/ethernet/mellanox/mlx4/Kconfig @@ -6,8 +6,8 @@ config MLX4_EN tristate "Mellanox Technologies 1/10/40Gbit Ethernet support" depends on PCI && NETDEVICES && ETHERNET && INET + depends on PTP_1588_CLOCK_OPTIONAL select MLX4_CORE - imply PTP_1588_CLOCK help This driver supports Mellanox Technologies ConnectX Ethernet devices. diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index 3616b77caa0a..ef518b1040f7 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -998,7 +998,9 @@ mlx4_en_set_link_ksettings(struct net_device *dev, } static int mlx4_en_get_coalesce(struct net_device *dev, - struct ethtool_coalesce *coal) + struct ethtool_coalesce *coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct mlx4_en_priv *priv = netdev_priv(dev); @@ -1020,7 +1022,9 @@ static int mlx4_en_get_coalesce(struct net_device *dev, } static int mlx4_en_set_coalesce(struct net_device *dev, - struct ethtool_coalesce *coal) + struct ethtool_coalesce *coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct mlx4_en_priv *priv = netdev_priv(dev); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 5d0c9c62382d..a2f61a87cef8 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -2828,7 +2828,7 @@ static const struct net_device_ops mlx4_netdev_ops = { .ndo_set_mac_address = mlx4_en_set_mac, .ndo_validate_addr = eth_validate_addr, .ndo_change_mtu = mlx4_en_change_mtu, - .ndo_do_ioctl = mlx4_en_ioctl, + .ndo_eth_ioctl = mlx4_en_ioctl, .ndo_tx_timeout = mlx4_en_tx_timeout, .ndo_vlan_rx_add_vid = mlx4_en_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = mlx4_en_vlan_rx_kill_vid, diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 442991d91c15..7f6d3b82c29b 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -991,7 +991,7 @@ void mlx4_en_calc_rx_buf(struct net_device *dev) * expense of more costly truesize accounting */ priv->frag_info[0].frag_stride = PAGE_SIZE; - priv->dma_dir = PCI_DMA_BIDIRECTIONAL; + priv->dma_dir = DMA_BIDIRECTIONAL; priv->rx_headroom = XDP_PACKET_HEADROOM; i = 1; } else { @@ -1021,7 +1021,7 @@ void mlx4_en_calc_rx_buf(struct net_device *dev) buf_size += frag_size; i++; } - priv->dma_dir = PCI_DMA_FROMDEVICE; + priv->dma_dir = DMA_FROM_DEVICE; priv->rx_headroom = 0; } diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 31b74bddb7cd..c56b9dba4c71 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -297,12 +297,12 @@ u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv, dma_unmap_single(priv->ddev, tx_info->map0_dma, tx_info->map0_byte_count, - PCI_DMA_TODEVICE); + DMA_TO_DEVICE); else dma_unmap_page(priv->ddev, tx_info->map0_dma, tx_info->map0_byte_count, - PCI_DMA_TODEVICE); + DMA_TO_DEVICE); /* Optimize the common case when there are no wraparounds */ if (likely((void *)tx_desc + (tx_info->nr_txbb << LOG_TXBB_SIZE) <= end)) { @@ -311,7 +311,7 @@ u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv, dma_unmap_page(priv->ddev, (dma_addr_t)be64_to_cpu(data->addr), be32_to_cpu(data->byte_count), - PCI_DMA_TODEVICE); + DMA_TO_DEVICE); } } else { if ((void *)data >= end) @@ -325,7 +325,7 @@ u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv, dma_unmap_page(priv->ddev, (dma_addr_t)be64_to_cpu(data->addr), be32_to_cpu(data->byte_count), - PCI_DMA_TODEVICE); + DMA_TO_DEVICE); } } } @@ -831,7 +831,7 @@ static bool mlx4_en_build_dma_wqe(struct mlx4_en_priv *priv, dma = dma_map_single(ddev, skb->data + lso_header_size, byte_count, - PCI_DMA_TODEVICE); + DMA_TO_DEVICE); if (dma_mapping_error(ddev, dma)) goto tx_drop_unmap; @@ -853,7 +853,7 @@ tx_drop_unmap: ++data; dma_unmap_page(ddev, (dma_addr_t)be64_to_cpu(data->addr), be32_to_cpu(data->byte_count), - PCI_DMA_TODEVICE); + DMA_TO_DEVICE); } return false; @@ -1170,7 +1170,7 @@ netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring, tx_info->nr_bytes = max_t(unsigned int, length, ETH_ZLEN); dma_sync_single_range_for_device(priv->ddev, dma, frame->page_offset, - length, PCI_DMA_TODEVICE); + length, DMA_TO_DEVICE); data->addr = cpu_to_be64(dma + frame->page_offset); dma_wmb(); diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 28ac4693da3c..5a6b0fcaf7f8 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -3806,24 +3806,15 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data, pci_set_master(pdev); - err = pci_set_dma_mask(pdev, DMA_BIT_MASK(64)); + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); if (err) { dev_warn(&pdev->dev, "Warning: couldn't set 64-bit PCI DMA mask\n"); - err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)); + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); if (err) { dev_err(&pdev->dev, "Can't set PCI DMA mask, aborting\n"); goto err_release_regions; } } - err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64)); - if (err) { - dev_warn(&pdev->dev, "Warning: couldn't set 64-bit consistent PCI DMA mask\n"); - err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32)); - if (err) { - dev_err(&pdev->dev, "Can't set consistent PCI DMA mask, aborting\n"); - goto err_release_regions; - } - } /* Allow large DMA segments, up to the firmware limit of 1 GB */ dma_set_max_seg_size(&pdev->dev, 1024 * 1024 * 1024); @@ -4005,7 +3996,7 @@ static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id) printk_once(KERN_INFO "%s", mlx4_version); - devlink = devlink_alloc(&mlx4_devlink_ops, sizeof(*priv)); + devlink = devlink_alloc(&mlx4_devlink_ops, sizeof(*priv), &pdev->dev); if (!devlink) return -ENOMEM; priv = devlink_priv(devlink); @@ -4024,7 +4015,7 @@ static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id) mutex_init(&dev->persist->interface_state_mutex); mutex_init(&dev->persist->pci_status_mutex); - ret = devlink_register(devlink, &pdev->dev); + ret = devlink_register(devlink); if (ret) goto err_persist_free; ret = devlink_params_register(devlink, mlx4_devlink_params, diff --git a/drivers/net/ethernet/mellanox/mlx4/qp.c b/drivers/net/ethernet/mellanox/mlx4/qp.c index 427e7a31862c..b149e601f673 100644 --- a/drivers/net/ethernet/mellanox/mlx4/qp.c +++ b/drivers/net/ethernet/mellanox/mlx4/qp.c @@ -739,7 +739,7 @@ static void mlx4_cleanup_qp_zones(struct mlx4_dev *dev) int i; for (i = 0; - i < sizeof(qp_table->zones_uids)/sizeof(qp_table->zones_uids[0]); + i < ARRAY_SIZE(qp_table->zones_uids); i++) { struct mlx4_bitmap *bitmap = mlx4_zone_get_bitmap(qp_table->zones, @@ -917,7 +917,7 @@ int mlx4_qp_to_ready(struct mlx4_dev *dev, struct mlx4_mtt *mtt, { int err; int i; - enum mlx4_qp_state states[] = { + static const enum mlx4_qp_state states[] = { MLX4_QP_STATE_RST, MLX4_QP_STATE_INIT, MLX4_QP_STATE_RTR, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig index e1a5a79e27c7..92056452a9e3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig +++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig @@ -10,7 +10,7 @@ config MLX5_CORE select NET_DEVLINK depends on VXLAN || !VXLAN depends on MLXFW || !MLXFW - depends on PTP_1588_CLOCK || !PTP_1588_CLOCK + depends on PTP_1588_CLOCK_OPTIONAL depends on PCI_HYPERV_INTERFACE || !PCI_HYPERV_INTERFACE help Core driver for low level functionality of the ConnectX-4 and diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index b5072a3a2585..63032cd6efb1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -15,14 +15,15 @@ mlx5_core-y := main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \ health.o mcg.o cq.o alloc.o port.o mr.o pd.o \ transobj.o vport.o sriov.o fs_cmd.o fs_core.o pci_irq.o \ fs_counters.o fs_ft_pool.o rl.o lag.o dev.o events.o wq.o lib/gid.o \ - lib/devcom.o lib/pci_vsc.o lib/dm.o diag/fs_tracepoint.o \ + lib/devcom.o lib/pci_vsc.o lib/dm.o lib/fs_ttc.o diag/fs_tracepoint.o \ diag/fw_tracer.o diag/crdump.o devlink.o diag/rsc_dump.o \ fw_reset.o qos.o # # Netdev basic # -mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \ +mlx5_core-$(CONFIG_MLX5_CORE_EN) += en/rqt.o en/tir.o en/rss.o en/rx_res.o \ + en/channels.o en_main.o en_common.o en_fs.o en_ethtool.o \ en_tx.o en_rx.o en_dim.o en_txrx.o en/xdp.o en_stats.o \ en_selftest.o en/port.o en/monitor_stats.o en/health.o \ en/reporter_tx.o en/reporter_rx.o en/params.o en/xsk/pool.o \ @@ -43,19 +44,22 @@ mlx5_core-$(CONFIG_MLX5_CLS_ACT) += en_tc.o en/rep/tc.o en/rep/neigh.o \ lib/fs_chains.o en/tc_tun.o \ esw/indir_table.o en/tc_tun_encap.o \ en/tc_tun_vxlan.o en/tc_tun_gre.o en/tc_tun_geneve.o \ - en/tc_tun_mplsoudp.o diag/en_tc_tracepoint.o + en/tc_tun_mplsoudp.o diag/en_tc_tracepoint.o \ + en/tc/post_act.o mlx5_core-$(CONFIG_MLX5_TC_CT) += en/tc_ct.o +mlx5_core-$(CONFIG_MLX5_TC_SAMPLE) += en/tc/sample.o # # Core extra # mlx5_core-$(CONFIG_MLX5_ESWITCH) += eswitch.o eswitch_offloads.o eswitch_offloads_termtbl.o \ - ecpf.o rdma.o esw/legacy.o + ecpf.o rdma.o esw/legacy.o \ + esw/devlink_port.o esw/vporttbl.o esw/qos.o + mlx5_core-$(CONFIG_MLX5_ESWITCH) += esw/acl/helper.o \ esw/acl/egress_lgcy.o esw/acl/egress_ofld.o \ - esw/acl/ingress_lgcy.o esw/acl/ingress_ofld.o \ - esw/devlink_port.o esw/vporttbl.o -mlx5_core-$(CONFIG_MLX5_TC_SAMPLE) += esw/sample.o + esw/acl/ingress_lgcy.o esw/acl/ingress_ofld.o + mlx5_core-$(CONFIG_MLX5_BRIDGE) += esw/bridge.o en/rep/bridge.o mlx5_core-$(CONFIG_MLX5_MPFS) += lib/mpfs.o diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 9d79c5ec31e9..db5dfff585c9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -877,7 +877,7 @@ static void cb_timeout_handler(struct work_struct *work) ent->ret = -ETIMEDOUT; mlx5_core_warn(dev, "cmd[%d]: %s(0x%x) Async, timeout. Will cause a leak of a command resource\n", ent->idx, mlx5_command_str(msg_to_opcode(ent->in)), msg_to_opcode(ent->in)); - mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true); + mlx5_cmd_comp_handler(dev, 1ULL << ent->idx, true); out: cmd_ent_put(ent); /* for the cmd_ent_get() took on schedule delayed work */ @@ -994,7 +994,7 @@ static void cmd_work_handler(struct work_struct *work) MLX5_SET(mbox_out, ent->out, status, status); MLX5_SET(mbox_out, ent->out, syndrome, drv_synd); - mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true); + mlx5_cmd_comp_handler(dev, 1ULL << ent->idx, true); return; } @@ -1008,7 +1008,7 @@ static void cmd_work_handler(struct work_struct *work) poll_timeout(ent); /* make sure we read the descriptor after ownership is SW */ rmb(); - mlx5_cmd_comp_handler(dev, 1UL << ent->idx, (ent->ret == -ETIMEDOUT)); + mlx5_cmd_comp_handler(dev, 1ULL << ent->idx, (ent->ret == -ETIMEDOUT)); } } @@ -1068,7 +1068,7 @@ static void wait_func_handle_exec_timeout(struct mlx5_core_dev *dev, mlx5_command_str(msg_to_opcode(ent->in)), msg_to_opcode(ent->in)); ent->ret = -ETIMEDOUT; - mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true); + mlx5_cmd_comp_handler(dev, 1ULL << ent->idx, true); } static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cq.c b/drivers/net/ethernet/mellanox/mlx5/core/cq.c index 360e093874d4..cf97985628ab 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cq.c @@ -89,7 +89,8 @@ static void mlx5_add_cq_to_tasklet(struct mlx5_core_cq *cq, int mlx5_core_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq, u32 *in, int inlen, u32 *out, int outlen) { - int eqn = MLX5_GET(cqc, MLX5_ADDR_OF(create_cq_in, in, cq_context), c_eqn); + int eqn = MLX5_GET(cqc, MLX5_ADDR_OF(create_cq_in, in, cq_context), + c_eqn_or_apu_element); u32 din[MLX5_ST_SZ_DW(destroy_cq_in)] = {}; struct mlx5_eq_comp *eq; int err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c index 20bb37266254..e8093c4e09d4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c @@ -53,7 +53,7 @@ static bool is_eth_rep_supported(struct mlx5_core_dev *dev) return true; } -static bool is_eth_supported(struct mlx5_core_dev *dev) +bool mlx5_eth_supported(struct mlx5_core_dev *dev) { if (!IS_ENABLED(CONFIG_MLX5_CORE_EN)) return false; @@ -105,7 +105,18 @@ static bool is_eth_supported(struct mlx5_core_dev *dev) return true; } -static bool is_vnet_supported(struct mlx5_core_dev *dev) +static bool is_eth_enabled(struct mlx5_core_dev *dev) +{ + union devlink_param_value val; + int err; + + err = devlink_param_driverinit_value_get(priv_to_devlink(dev), + DEVLINK_PARAM_GENERIC_ID_ENABLE_ETH, + &val); + return err ? false : val.vbool; +} + +bool mlx5_vnet_supported(struct mlx5_core_dev *dev) { if (!IS_ENABLED(CONFIG_MLX5_VDPA_NET)) return false; @@ -127,6 +138,17 @@ static bool is_vnet_supported(struct mlx5_core_dev *dev) return true; } +static bool is_vnet_enabled(struct mlx5_core_dev *dev) +{ + union devlink_param_value val; + int err; + + err = devlink_param_driverinit_value_get(priv_to_devlink(dev), + DEVLINK_PARAM_GENERIC_ID_ENABLE_VNET, + &val); + return err ? false : val.vbool; +} + static bool is_ib_rep_supported(struct mlx5_core_dev *dev) { if (!IS_ENABLED(CONFIG_MLX5_INFINIBAND)) @@ -170,7 +192,7 @@ static bool is_mp_supported(struct mlx5_core_dev *dev) return true; } -static bool is_ib_supported(struct mlx5_core_dev *dev) +bool mlx5_rdma_supported(struct mlx5_core_dev *dev) { if (!IS_ENABLED(CONFIG_MLX5_INFINIBAND)) return false; @@ -187,6 +209,17 @@ static bool is_ib_supported(struct mlx5_core_dev *dev) return true; } +static bool is_ib_enabled(struct mlx5_core_dev *dev) +{ + union devlink_param_value val; + int err; + + err = devlink_param_driverinit_value_get(priv_to_devlink(dev), + DEVLINK_PARAM_GENERIC_ID_ENABLE_RDMA, + &val); + return err ? false : val.vbool; +} + enum { MLX5_INTERFACE_PROTOCOL_ETH, MLX5_INTERFACE_PROTOCOL_ETH_REP, @@ -201,13 +234,17 @@ enum { static const struct mlx5_adev_device { const char *suffix; bool (*is_supported)(struct mlx5_core_dev *dev); + bool (*is_enabled)(struct mlx5_core_dev *dev); } mlx5_adev_devices[] = { [MLX5_INTERFACE_PROTOCOL_VNET] = { .suffix = "vnet", - .is_supported = &is_vnet_supported }, + .is_supported = &mlx5_vnet_supported, + .is_enabled = &is_vnet_enabled }, [MLX5_INTERFACE_PROTOCOL_IB] = { .suffix = "rdma", - .is_supported = &is_ib_supported }, + .is_supported = &mlx5_rdma_supported, + .is_enabled = &is_ib_enabled }, [MLX5_INTERFACE_PROTOCOL_ETH] = { .suffix = "eth", - .is_supported = &is_eth_supported }, + .is_supported = &mlx5_eth_supported, + .is_enabled = &is_eth_enabled }, [MLX5_INTERFACE_PROTOCOL_ETH_REP] = { .suffix = "eth-rep", .is_supported = &is_eth_rep_supported }, [MLX5_INTERFACE_PROTOCOL_IB_REP] = { .suffix = "rdma-rep", @@ -308,6 +345,14 @@ int mlx5_attach_device(struct mlx5_core_dev *dev) if (!priv->adev[i]) { bool is_supported = false; + if (mlx5_adev_devices[i].is_enabled) { + bool enabled; + + enabled = mlx5_adev_devices[i].is_enabled(dev); + if (!enabled) + continue; + } + if (mlx5_adev_devices[i].is_supported) is_supported = mlx5_adev_devices[i].is_supported(dev); @@ -360,6 +405,14 @@ void mlx5_detach_device(struct mlx5_core_dev *dev) if (!priv->adev[i]) continue; + if (mlx5_adev_devices[i].is_enabled) { + bool enabled; + + enabled = mlx5_adev_devices[i].is_enabled(dev); + if (!enabled) + goto skip_suspend; + } + adev = &priv->adev[i]->adev; /* Auxiliary driver was unbind manually through sysfs */ if (!adev->dev.driver) @@ -447,12 +500,21 @@ static void delete_drivers(struct mlx5_core_dev *dev) if (!priv->adev[i]) continue; + if (mlx5_adev_devices[i].is_enabled) { + bool enabled; + + enabled = mlx5_adev_devices[i].is_enabled(dev); + if (!enabled) + goto del_adev; + } + if (mlx5_adev_devices[i].is_supported && !delete_all) is_supported = mlx5_adev_devices[i].is_supported(dev); if (is_supported) continue; +del_adev: del_adev(&priv->adev[i]->adev); priv->adev[i] = NULL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c index d791d351b489..e84287ffc7ce 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c @@ -7,6 +7,7 @@ #include "fw_reset.h" #include "fs_core.h" #include "eswitch.h" +#include "esw/qos.h" #include "sf/dev/dev.h" #include "sf/sf.h" @@ -292,6 +293,13 @@ static const struct devlink_ops mlx5_devlink_ops = { .eswitch_encap_mode_get = mlx5_devlink_eswitch_encap_mode_get, .port_function_hw_addr_get = mlx5_devlink_port_function_hw_addr_get, .port_function_hw_addr_set = mlx5_devlink_port_function_hw_addr_set, + .rate_leaf_tx_share_set = mlx5_esw_devlink_rate_leaf_tx_share_set, + .rate_leaf_tx_max_set = mlx5_esw_devlink_rate_leaf_tx_max_set, + .rate_node_tx_share_set = mlx5_esw_devlink_rate_node_tx_share_set, + .rate_node_tx_max_set = mlx5_esw_devlink_rate_node_tx_max_set, + .rate_node_new = mlx5_esw_devlink_rate_node_new, + .rate_node_del = mlx5_esw_devlink_rate_node_del, + .rate_leaf_parent_set = mlx5_esw_devlink_rate_parent_set, #endif #ifdef CONFIG_MLX5_SF_MANAGER .port_new = mlx5_devlink_sf_port_new, @@ -359,9 +367,10 @@ int mlx5_devlink_traps_get_action(struct mlx5_core_dev *dev, int trap_id, return 0; } -struct devlink *mlx5_devlink_alloc(void) +struct devlink *mlx5_devlink_alloc(struct device *dev) { - return devlink_alloc(&mlx5_devlink_ops, sizeof(struct mlx5_core_dev)); + return devlink_alloc(&mlx5_devlink_ops, sizeof(struct mlx5_core_dev), + dev); } void mlx5_devlink_free(struct devlink *devlink) @@ -595,6 +604,157 @@ static void mlx5_devlink_set_params_init_values(struct devlink *devlink) #endif } +static const struct devlink_param enable_eth_param = + DEVLINK_PARAM_GENERIC(ENABLE_ETH, BIT(DEVLINK_PARAM_CMODE_DRIVERINIT), + NULL, NULL, NULL); + +static int mlx5_devlink_eth_param_register(struct devlink *devlink) +{ + struct mlx5_core_dev *dev = devlink_priv(devlink); + union devlink_param_value value; + int err; + + if (!mlx5_eth_supported(dev)) + return 0; + + err = devlink_param_register(devlink, &enable_eth_param); + if (err) + return err; + + value.vbool = true; + devlink_param_driverinit_value_set(devlink, + DEVLINK_PARAM_GENERIC_ID_ENABLE_ETH, + value); + devlink_param_publish(devlink, &enable_eth_param); + return 0; +} + +static void mlx5_devlink_eth_param_unregister(struct devlink *devlink) +{ + struct mlx5_core_dev *dev = devlink_priv(devlink); + + if (!mlx5_eth_supported(dev)) + return; + + devlink_param_unpublish(devlink, &enable_eth_param); + devlink_param_unregister(devlink, &enable_eth_param); +} + +static int mlx5_devlink_enable_rdma_validate(struct devlink *devlink, u32 id, + union devlink_param_value val, + struct netlink_ext_ack *extack) +{ + struct mlx5_core_dev *dev = devlink_priv(devlink); + bool new_state = val.vbool; + + if (new_state && !mlx5_rdma_supported(dev)) + return -EOPNOTSUPP; + return 0; +} + +static const struct devlink_param enable_rdma_param = + DEVLINK_PARAM_GENERIC(ENABLE_RDMA, BIT(DEVLINK_PARAM_CMODE_DRIVERINIT), + NULL, NULL, mlx5_devlink_enable_rdma_validate); + +static int mlx5_devlink_rdma_param_register(struct devlink *devlink) +{ + struct mlx5_core_dev *dev = devlink_priv(devlink); + union devlink_param_value value; + int err; + + if (!IS_ENABLED(CONFIG_MLX5_INFINIBAND) || MLX5_ESWITCH_MANAGER(dev)) + return 0; + + err = devlink_param_register(devlink, &enable_rdma_param); + if (err) + return err; + + value.vbool = true; + devlink_param_driverinit_value_set(devlink, + DEVLINK_PARAM_GENERIC_ID_ENABLE_RDMA, + value); + devlink_param_publish(devlink, &enable_rdma_param); + return 0; +} + +static void mlx5_devlink_rdma_param_unregister(struct devlink *devlink) +{ + struct mlx5_core_dev *dev = devlink_priv(devlink); + + if (!IS_ENABLED(CONFIG_MLX5_INFINIBAND) || MLX5_ESWITCH_MANAGER(dev)) + return; + + devlink_param_unpublish(devlink, &enable_rdma_param); + devlink_param_unregister(devlink, &enable_rdma_param); +} + +static const struct devlink_param enable_vnet_param = + DEVLINK_PARAM_GENERIC(ENABLE_VNET, BIT(DEVLINK_PARAM_CMODE_DRIVERINIT), + NULL, NULL, NULL); + +static int mlx5_devlink_vnet_param_register(struct devlink *devlink) +{ + struct mlx5_core_dev *dev = devlink_priv(devlink); + union devlink_param_value value; + int err; + + if (!mlx5_vnet_supported(dev)) + return 0; + + err = devlink_param_register(devlink, &enable_vnet_param); + if (err) + return err; + + value.vbool = true; + devlink_param_driverinit_value_set(devlink, + DEVLINK_PARAM_GENERIC_ID_ENABLE_VNET, + value); + devlink_param_publish(devlink, &enable_rdma_param); + return 0; +} + +static void mlx5_devlink_vnet_param_unregister(struct devlink *devlink) +{ + struct mlx5_core_dev *dev = devlink_priv(devlink); + + if (!mlx5_vnet_supported(dev)) + return; + + devlink_param_unpublish(devlink, &enable_vnet_param); + devlink_param_unregister(devlink, &enable_vnet_param); +} + +static int mlx5_devlink_auxdev_params_register(struct devlink *devlink) +{ + int err; + + err = mlx5_devlink_eth_param_register(devlink); + if (err) + return err; + + err = mlx5_devlink_rdma_param_register(devlink); + if (err) + goto rdma_err; + + err = mlx5_devlink_vnet_param_register(devlink); + if (err) + goto vnet_err; + return 0; + +vnet_err: + mlx5_devlink_rdma_param_unregister(devlink); +rdma_err: + mlx5_devlink_eth_param_unregister(devlink); + return err; +} + +static void mlx5_devlink_auxdev_params_unregister(struct devlink *devlink) +{ + mlx5_devlink_vnet_param_unregister(devlink); + mlx5_devlink_rdma_param_unregister(devlink); + mlx5_devlink_eth_param_unregister(devlink); +} + #define MLX5_TRAP_DROP(_id, _group_id) \ DEVLINK_TRAP_GENERIC(DROP, DROP, _id, \ DEVLINK_TRAP_GROUP_GENERIC_ID_##_group_id, \ @@ -638,11 +798,11 @@ static void mlx5_devlink_traps_unregister(struct devlink *devlink) ARRAY_SIZE(mlx5_trap_groups_arr)); } -int mlx5_devlink_register(struct devlink *devlink, struct device *dev) +int mlx5_devlink_register(struct devlink *devlink) { int err; - err = devlink_register(devlink, dev); + err = devlink_register(devlink); if (err) return err; @@ -653,6 +813,10 @@ int mlx5_devlink_register(struct devlink *devlink, struct device *dev) mlx5_devlink_set_params_init_values(devlink); devlink_params_publish(devlink); + err = mlx5_devlink_auxdev_params_register(devlink); + if (err) + goto auxdev_reg_err; + err = mlx5_devlink_traps_register(devlink); if (err) goto traps_reg_err; @@ -660,6 +824,8 @@ int mlx5_devlink_register(struct devlink *devlink, struct device *dev) return 0; traps_reg_err: + mlx5_devlink_auxdev_params_unregister(devlink); +auxdev_reg_err: devlink_params_unregister(devlink, mlx5_devlink_params, ARRAY_SIZE(mlx5_devlink_params)); params_reg_err: @@ -670,6 +836,8 @@ params_reg_err: void mlx5_devlink_unregister(struct devlink *devlink) { mlx5_devlink_traps_unregister(devlink); + mlx5_devlink_auxdev_params_unregister(devlink); + devlink_params_unpublish(devlink); devlink_params_unregister(devlink, mlx5_devlink_params, ARRAY_SIZE(mlx5_devlink_params)); devlink_unregister(devlink); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.h b/drivers/net/ethernet/mellanox/mlx5/core/devlink.h index 7318d44b774b..30bf4882779b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.h @@ -31,9 +31,9 @@ int mlx5_devlink_trap_get_num_active(struct mlx5_core_dev *dev); int mlx5_devlink_traps_get_action(struct mlx5_core_dev *dev, int trap_id, enum devlink_trap_action *action); -struct devlink *mlx5_devlink_alloc(void); +struct devlink *mlx5_devlink_alloc(struct device *dev); void mlx5_devlink_free(struct devlink *devlink); -int mlx5_devlink_register(struct devlink *devlink, struct device *dev); +int mlx5_devlink_register(struct devlink *devlink); void mlx5_devlink_unregister(struct devlink *devlink); #endif /* __MLX5_DEVLINK_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index b1b51bbba054..669a75f3537a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -58,6 +58,7 @@ #include "en/qos.h" #include "lib/hv_vhca.h" #include "lib/clock.h" +#include "en/rx_res.h" extern const struct net_device_ops mlx5e_netdev_ops; struct page_pool; @@ -65,14 +66,13 @@ struct page_pool; #define MLX5E_METADATA_ETHER_TYPE (0x8CE4) #define MLX5E_METADATA_ETHER_LEN 8 -#define MLX5_SET_CFG(p, f, v) MLX5_SET(create_flow_group_in, p, f, v) - #define MLX5E_ETH_HARD_MTU (ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN) #define MLX5E_HW2SW_MTU(params, hwmtu) ((hwmtu) - ((params)->hard_mtu)) #define MLX5E_SW2HW_MTU(params, swmtu) ((swmtu) + ((params)->hard_mtu)) #define MLX5E_MAX_NUM_TC 8 +#define MLX5E_MAX_NUM_MQPRIO_CH_TC TC_QOPT_MAX_QUEUE #define MLX5_RX_HEADROOM NET_SKB_PAD #define MLX5_SKB_FRAG_SZ(len) (SKB_DATA_ALIGN(len) + \ @@ -126,7 +126,6 @@ struct page_pool; #define MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE_MPW 0x2 -#define MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ (64 * 1024) #define MLX5E_DEFAULT_LRO_TIMEOUT 32 #define MLX5E_LRO_TIMEOUT_ARR_SIZE 4 @@ -139,8 +138,6 @@ struct page_pool; #define MLX5E_PARAMS_DEFAULT_MIN_RX_WQES 0x80 #define MLX5E_PARAMS_DEFAULT_MIN_RX_WQES_MPW 0x2 -#define MLX5E_LOG_INDIR_RQT_SIZE 0x8 -#define MLX5E_INDIR_RQT_SIZE BIT(MLX5E_LOG_INDIR_RQT_SIZE) #define MLX5E_MIN_NUM_CHANNELS 0x1 #define MLX5E_MAX_NUM_CHANNELS (MLX5E_INDIR_RQT_SIZE / 2) #define MLX5E_MAX_NUM_SQS (MLX5E_MAX_NUM_CHANNELS * MLX5E_MAX_NUM_TC) @@ -252,7 +249,10 @@ struct mlx5e_params { u8 rq_wq_type; u8 log_rq_mtu_frames; u16 num_channels; - u8 num_tc; + struct { + u16 mode; + u8 num_tc; + } mqprio; bool rx_cqe_compress_def; bool tunneled_offload_en; struct dim_cq_moder rx_cq_moderation; @@ -272,6 +272,12 @@ struct mlx5e_params { bool ptp_rx; }; +static inline u8 mlx5e_get_dcb_num_tc(struct mlx5e_params *params) +{ + return params->mqprio.mode == TC_MQPRIO_MODE_DCB ? + params->mqprio.num_tc : 1; +} + enum { MLX5E_RQ_STATE_ENABLED, MLX5E_RQ_STATE_RECOVERING, @@ -745,29 +751,11 @@ enum { MLX5E_STATE_XDP_ACTIVE, }; -struct mlx5e_rqt { - u32 rqtn; - bool enabled; -}; - -struct mlx5e_tir { - u32 tirn; - struct mlx5e_rqt rqt; - struct list_head list; -}; - enum { MLX5E_TC_PRIO = 0, MLX5E_NIC_PRIO }; -struct mlx5e_rss_params { - u32 indirection_rqt[MLX5E_INDIR_RQT_SIZE]; - u32 rx_hash_fields[MLX5E_NUM_INDIR_TIRS]; - u8 toeplitz_hash_key[40]; - u8 hfunc; -}; - struct mlx5e_modify_sq_param { int curr_state; int next_state; @@ -837,13 +825,7 @@ struct mlx5e_priv { struct mlx5e_channels channels; u32 tisn[MLX5_MAX_PORTS][MLX5E_MAX_NUM_TC]; - struct mlx5e_rqt indir_rqt; - struct mlx5e_tir indir_tir[MLX5E_NUM_INDIR_TIRS]; - struct mlx5e_tir inner_indir_tir[MLX5E_NUM_INDIR_TIRS]; - struct mlx5e_tir direct_tir[MLX5E_MAX_NUM_CHANNELS]; - struct mlx5e_tir xsk_tir[MLX5E_MAX_NUM_CHANNELS]; - struct mlx5e_tir ptp_tir; - struct mlx5e_rss_params rss_params; + struct mlx5e_rx_res *rx_res; u32 tx_rates[MLX5E_MAX_NUM_SQS]; struct mlx5e_flow_steering fs; @@ -948,25 +930,6 @@ int mlx5e_vlan_rx_kill_vid(struct net_device *dev, __always_unused __be16 proto, u16 vid); void mlx5e_timestamp_init(struct mlx5e_priv *priv); -struct mlx5e_redirect_rqt_param { - bool is_rss; - union { - u32 rqn; /* Direct RQN (Non-RSS) */ - struct { - u8 hfunc; - struct mlx5e_channels *channels; - } rss; /* RSS data */ - }; -}; - -int mlx5e_redirect_rqt(struct mlx5e_priv *priv, u32 rqtn, int sz, - struct mlx5e_redirect_rqt_param rrp); -void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_rss_params *rss_params, - const struct mlx5e_tirc_config *ttconfig, - void *tirc, bool inner); -void mlx5e_modify_tirs_hash(struct mlx5e_priv *priv, void *in); -struct mlx5e_tirc_config mlx5e_tirc_get_default_config(enum mlx5e_traffic_types tt); - struct mlx5e_xsk_param; struct mlx5e_rq_param; @@ -1028,9 +991,6 @@ void mlx5e_activate_priv_channels(struct mlx5e_priv *priv); void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv); int mlx5e_ptp_rx_manage_fs_ctx(struct mlx5e_priv *priv, void *ctx); -void mlx5e_build_default_indir_rqt(u32 *indirection_rqt, int len, - int num_channels); - int mlx5e_modify_rq_state(struct mlx5e_rq *rq, int curr_state, int next_state); void mlx5e_activate_rq(struct mlx5e_rq *rq); void mlx5e_deactivate_rq(struct mlx5e_rq *rq); @@ -1065,10 +1025,6 @@ static inline bool mlx5_tx_swp_supported(struct mlx5_core_dev *mdev) extern const struct ethtool_ops mlx5e_ethtool_ops; -int mlx5e_create_tir(struct mlx5_core_dev *mdev, struct mlx5e_tir *tir, - u32 *in); -void mlx5e_destroy_tir(struct mlx5_core_dev *mdev, - struct mlx5e_tir *tir); int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev); void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev); int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb, @@ -1084,17 +1040,6 @@ void mlx5e_close_drop_rq(struct mlx5e_rq *drop_rq); int mlx5e_init_di_list(struct mlx5e_rq *rq, int wq_sz, int node); void mlx5e_free_di_list(struct mlx5e_rq *rq); -int mlx5e_create_indirect_rqt(struct mlx5e_priv *priv); - -int mlx5e_create_indirect_tirs(struct mlx5e_priv *priv, bool inner_ttc); -void mlx5e_destroy_indirect_tirs(struct mlx5e_priv *priv); - -int mlx5e_create_direct_rqts(struct mlx5e_priv *priv, struct mlx5e_tir *tirs, int n); -void mlx5e_destroy_direct_rqts(struct mlx5e_priv *priv, struct mlx5e_tir *tirs, int n); -int mlx5e_create_direct_tirs(struct mlx5e_priv *priv, struct mlx5e_tir *tirs, int n); -void mlx5e_destroy_direct_tirs(struct mlx5e_priv *priv, struct mlx5e_tir *tirs, int n); -void mlx5e_destroy_rqt(struct mlx5e_priv *priv, struct mlx5e_rqt *rqt); - int mlx5e_create_tis(struct mlx5_core_dev *mdev, void *in, u32 *tisn); void mlx5e_destroy_tis(struct mlx5_core_dev *mdev, u32 tisn); @@ -1106,7 +1051,6 @@ int mlx5e_close(struct net_device *netdev); int mlx5e_open(struct net_device *netdev); void mlx5e_queue_update_stats(struct mlx5e_priv *priv); -int mlx5e_bits_invert(unsigned long a, int size); int mlx5e_set_dev_port_mtu(struct mlx5e_priv *priv); int mlx5e_set_dev_port_mtu_ctx(struct mlx5e_priv *priv, void *context); @@ -1183,8 +1127,6 @@ int mlx5e_netdev_change_profile(struct mlx5e_priv *priv, void mlx5e_netdev_attach_nic_profile(struct mlx5e_priv *priv); void mlx5e_set_netdev_mtu_boundaries(struct mlx5e_priv *priv); void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16 mtu); -void mlx5e_build_rss_params(struct mlx5e_rss_params *rss_params, - u16 num_channels); void mlx5e_rx_dim_work(struct work_struct *work); void mlx5e_tx_dim_work(struct work_struct *work); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/channels.c b/drivers/net/ethernet/mellanox/mlx5/core/en/channels.c new file mode 100644 index 000000000000..e7c14c0de0a7 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/channels.c @@ -0,0 +1,46 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2021, Mellanox Technologies inc. All rights reserved. */ + +#include "channels.h" +#include "en.h" +#include "en/ptp.h" + +unsigned int mlx5e_channels_get_num(struct mlx5e_channels *chs) +{ + return chs->num; +} + +void mlx5e_channels_get_regular_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn) +{ + struct mlx5e_channel *c; + + WARN_ON(ix >= mlx5e_channels_get_num(chs)); + c = chs->c[ix]; + + *rqn = c->rq.rqn; +} + +bool mlx5e_channels_get_xsk_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn) +{ + struct mlx5e_channel *c; + + WARN_ON(ix >= mlx5e_channels_get_num(chs)); + c = chs->c[ix]; + + if (!test_bit(MLX5E_CHANNEL_STATE_XSK, c->state)) + return false; + + *rqn = c->xskrq.rqn; + return true; +} + +bool mlx5e_channels_get_ptp_rqn(struct mlx5e_channels *chs, u32 *rqn) +{ + struct mlx5e_ptp *c = chs->ptp; + + if (!c || !test_bit(MLX5E_PTP_STATE_RX, c->state)) + return false; + + *rqn = c->rq.rqn; + return true; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/channels.h b/drivers/net/ethernet/mellanox/mlx5/core/en/channels.h new file mode 100644 index 000000000000..ca00cbc827cb --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/channels.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2021, Mellanox Technologies inc. All rights reserved. */ + +#ifndef __MLX5_EN_CHANNELS_H__ +#define __MLX5_EN_CHANNELS_H__ + +#include <linux/kernel.h> + +struct mlx5e_channels; + +unsigned int mlx5e_channels_get_num(struct mlx5e_channels *chs); +void mlx5e_channels_get_regular_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn); +bool mlx5e_channels_get_xsk_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn); +bool mlx5e_channels_get_ptp_rqn(struct mlx5e_channels *chs, u32 *rqn); + +#endif /* __MLX5_EN_CHANNELS_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c index bc33eaada3b9..86e079310ac3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c @@ -55,19 +55,15 @@ void mlx5e_devlink_port_unregister(struct mlx5e_priv *priv) { struct devlink_port *dl_port = mlx5e_devlink_get_dl_port(priv); - if (dl_port->registered) - devlink_port_unregister(dl_port); + devlink_port_unregister(dl_port); } struct devlink_port *mlx5e_get_devlink_port(struct net_device *dev) { struct mlx5e_priv *priv = netdev_priv(dev); - struct devlink_port *port; if (!netif_device_present(dev)) return NULL; - port = mlx5e_devlink_get_dl_port(priv); - if (port->registered) - return port; - return NULL; + + return mlx5e_devlink_get_dl_port(priv); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h index 1d5ce07b83f4..41684a6c44e9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h @@ -5,6 +5,9 @@ #define __MLX5E_FLOW_STEER_H__ #include "mod_hdr.h" +#include "lib/fs_ttc.h" + +struct mlx5e_post_act; enum { MLX5E_TC_FT_LEVEL = 0, @@ -18,6 +21,7 @@ struct mlx5e_tc_table { struct mutex t_lock; struct mlx5_flow_table *t; struct mlx5_fs_chains *chains; + struct mlx5e_post_act *post_act; struct rhashtable ht; @@ -67,27 +71,7 @@ struct mlx5e_l2_table { bool promisc_enabled; }; -enum mlx5e_traffic_types { - MLX5E_TT_IPV4_TCP, - MLX5E_TT_IPV6_TCP, - MLX5E_TT_IPV4_UDP, - MLX5E_TT_IPV6_UDP, - MLX5E_TT_IPV4_IPSEC_AH, - MLX5E_TT_IPV6_IPSEC_AH, - MLX5E_TT_IPV4_IPSEC_ESP, - MLX5E_TT_IPV6_IPSEC_ESP, - MLX5E_TT_IPV4, - MLX5E_TT_IPV6, - MLX5E_TT_ANY, - MLX5E_NUM_TT, - MLX5E_NUM_INDIR_TIRS = MLX5E_TT_ANY, -}; - -struct mlx5e_tirc_config { - u8 l3_prot_type; - u8 l4_prot_type; - u32 rx_hash_fields; -}; +#define MLX5E_NUM_INDIR_TIRS (MLX5_NUM_TT - 1) #define MLX5_HASH_IP (MLX5_HASH_FIELD_SEL_SRC_IP |\ MLX5_HASH_FIELD_SEL_DST_IP) @@ -99,30 +83,6 @@ struct mlx5e_tirc_config { MLX5_HASH_FIELD_SEL_DST_IP |\ MLX5_HASH_FIELD_SEL_IPSEC_SPI) -enum mlx5e_tunnel_types { - MLX5E_TT_IPV4_GRE, - MLX5E_TT_IPV6_GRE, - MLX5E_TT_IPV4_IPIP, - MLX5E_TT_IPV6_IPIP, - MLX5E_TT_IPV4_IPV6, - MLX5E_TT_IPV6_IPV6, - MLX5E_NUM_TUNNEL_TT, -}; - -bool mlx5e_tunnel_inner_ft_supported(struct mlx5_core_dev *mdev); - -struct mlx5e_ttc_rule { - struct mlx5_flow_handle *rule; - struct mlx5_flow_destination default_dest; -}; - -/* L3/L4 traffic type classifier */ -struct mlx5e_ttc_table { - struct mlx5e_flow_table ft; - struct mlx5e_ttc_rule rules[MLX5E_NUM_TT]; - struct mlx5_flow_handle *tunnel_rules[MLX5E_NUM_TUNNEL_TT]; -}; - /* NIC prio FTS */ enum { MLX5E_PROMISC_FT_LEVEL, @@ -144,21 +104,7 @@ enum { #endif }; -#define MLX5E_TTC_NUM_GROUPS 3 -#define MLX5E_TTC_GROUP1_SIZE (BIT(3) + MLX5E_NUM_TUNNEL_TT) -#define MLX5E_TTC_GROUP2_SIZE BIT(1) -#define MLX5E_TTC_GROUP3_SIZE BIT(0) -#define MLX5E_TTC_TABLE_SIZE (MLX5E_TTC_GROUP1_SIZE +\ - MLX5E_TTC_GROUP2_SIZE +\ - MLX5E_TTC_GROUP3_SIZE) - -#define MLX5E_INNER_TTC_NUM_GROUPS 3 -#define MLX5E_INNER_TTC_GROUP1_SIZE BIT(3) -#define MLX5E_INNER_TTC_GROUP2_SIZE BIT(1) -#define MLX5E_INNER_TTC_GROUP3_SIZE BIT(0) -#define MLX5E_INNER_TTC_TABLE_SIZE (MLX5E_INNER_TTC_GROUP1_SIZE +\ - MLX5E_INNER_TTC_GROUP2_SIZE +\ - MLX5E_INNER_TTC_GROUP3_SIZE) +struct mlx5e_priv; #ifdef CONFIG_MLX5_EN_RXNFC @@ -226,8 +172,8 @@ struct mlx5e_flow_steering { struct mlx5e_promisc_table promisc; struct mlx5e_vlan_table *vlan; struct mlx5e_l2_table l2; - struct mlx5e_ttc_table ttc; - struct mlx5e_ttc_table inner_ttc; + struct mlx5_ttc_table *ttc; + struct mlx5_ttc_table *inner_ttc; #ifdef CONFIG_MLX5_EN_ARFS struct mlx5e_arfs_tables *arfs; #endif @@ -239,33 +185,13 @@ struct mlx5e_flow_steering { struct mlx5e_ptp_fs *ptp_fs; }; -struct ttc_params { - struct mlx5_flow_table_attr ft_attr; - u32 any_tt_tirn; - u32 indir_tirn[MLX5E_NUM_INDIR_TIRS]; - struct mlx5e_ttc_table *inner_ttc; -}; - -void mlx5e_set_ttc_basic_params(struct mlx5e_priv *priv, struct ttc_params *ttc_params); -void mlx5e_set_ttc_ft_params(struct ttc_params *ttc_params); -void mlx5e_set_inner_ttc_ft_params(struct ttc_params *ttc_params); - -int mlx5e_create_ttc_table(struct mlx5e_priv *priv, struct ttc_params *params, - struct mlx5e_ttc_table *ttc); -void mlx5e_destroy_ttc_table(struct mlx5e_priv *priv, - struct mlx5e_ttc_table *ttc); +void mlx5e_set_ttc_params(struct mlx5e_priv *priv, + struct ttc_params *ttc_params, bool tunnel); -int mlx5e_create_inner_ttc_table(struct mlx5e_priv *priv, struct ttc_params *params, - struct mlx5e_ttc_table *ttc); -void mlx5e_destroy_inner_ttc_table(struct mlx5e_priv *priv, - struct mlx5e_ttc_table *ttc); +void mlx5e_destroy_ttc_table(struct mlx5e_priv *priv); +int mlx5e_create_ttc_table(struct mlx5e_priv *priv); void mlx5e_destroy_flow_table(struct mlx5e_flow_table *ft); -int mlx5e_ttc_fwd_dest(struct mlx5e_priv *priv, enum mlx5e_traffic_types type, - struct mlx5_flow_destination *new_dest); -struct mlx5_flow_destination -mlx5e_ttc_get_default_dest(struct mlx5e_priv *priv, enum mlx5e_traffic_types type); -int mlx5e_ttc_fwd_default_dest(struct mlx5e_priv *priv, enum mlx5e_traffic_types type); void mlx5e_enable_cvlan_filter(struct mlx5e_priv *priv); void mlx5e_disable_cvlan_filter(struct mlx5e_priv *priv); @@ -273,7 +199,6 @@ void mlx5e_disable_cvlan_filter(struct mlx5e_priv *priv); int mlx5e_create_flow_steering(struct mlx5e_priv *priv); void mlx5e_destroy_flow_steering(struct mlx5e_priv *priv); -u8 mlx5e_get_proto_by_tunnel_type(enum mlx5e_tunnel_types tt); int mlx5e_add_vlan_trap(struct mlx5e_priv *priv, int trap_id, int tir_num); void mlx5e_remove_vlan_trap(struct mlx5e_priv *priv); int mlx5e_add_mac_trap(struct mlx5e_priv *priv, int trap_id, int tir_num); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c b/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c index 909faa6c89d7..7aa25a5e29d7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c @@ -33,22 +33,22 @@ static char *fs_udp_type2str(enum fs_udp_type i) } } -static enum mlx5e_traffic_types fs_udp2tt(enum fs_udp_type i) +static enum mlx5_traffic_types fs_udp2tt(enum fs_udp_type i) { switch (i) { case FS_IPV4_UDP: - return MLX5E_TT_IPV4_UDP; + return MLX5_TT_IPV4_UDP; default: /* FS_IPV6_UDP */ - return MLX5E_TT_IPV6_UDP; + return MLX5_TT_IPV6_UDP; } } -static enum fs_udp_type tt2fs_udp(enum mlx5e_traffic_types i) +static enum fs_udp_type tt2fs_udp(enum mlx5_traffic_types i) { switch (i) { - case MLX5E_TT_IPV4_UDP: + case MLX5_TT_IPV4_UDP: return FS_IPV4_UDP; - case MLX5E_TT_IPV6_UDP: + case MLX5_TT_IPV6_UDP: return FS_IPV6_UDP; default: return FS_UDP_NUM_TYPES; @@ -75,7 +75,7 @@ static void fs_udp_set_dport_flow(struct mlx5_flow_spec *spec, enum fs_udp_type struct mlx5_flow_handle * mlx5e_fs_tt_redirect_udp_add_rule(struct mlx5e_priv *priv, - enum mlx5e_traffic_types ttc_type, + enum mlx5_traffic_types ttc_type, u32 tir_num, u16 d_port) { enum fs_udp_type type = tt2fs_udp(ttc_type); @@ -124,7 +124,7 @@ static int fs_udp_add_default_rule(struct mlx5e_priv *priv, enum fs_udp_type typ fs_udp = priv->fs.udp; fs_udp_t = &fs_udp->tables[type]; - dest = mlx5e_ttc_get_default_dest(priv, fs_udp2tt(type)); + dest = mlx5_ttc_get_default_dest(priv->fs.ttc, fs_udp2tt(type)); rule = mlx5_add_flow_rules(fs_udp_t->t, NULL, &flow_act, &dest, 1); if (IS_ERR(rule)) { err = PTR_ERR(rule); @@ -259,7 +259,7 @@ static int fs_udp_disable(struct mlx5e_priv *priv) for (i = 0; i < FS_UDP_NUM_TYPES; i++) { /* Modify ttc rules destination to point back to the indir TIRs */ - err = mlx5e_ttc_fwd_default_dest(priv, fs_udp2tt(i)); + err = mlx5_ttc_fwd_default_dest(priv->fs.ttc, fs_udp2tt(i)); if (err) { netdev_err(priv->netdev, "%s: modify ttc[%d] default destination failed, err(%d)\n", @@ -281,7 +281,7 @@ static int fs_udp_enable(struct mlx5e_priv *priv) dest.ft = priv->fs.udp->tables[i].t; /* Modify ttc rules destination to point on the accel_fs FTs */ - err = mlx5e_ttc_fwd_dest(priv, fs_udp2tt(i), &dest); + err = mlx5_ttc_fwd_dest(priv->fs.ttc, fs_udp2tt(i), &dest); if (err) { netdev_err(priv->netdev, "%s: modify ttc[%d] destination to accel failed, err(%d)\n", @@ -401,7 +401,7 @@ static int fs_any_add_default_rule(struct mlx5e_priv *priv) fs_any = priv->fs.any; fs_any_t = &fs_any->table; - dest = mlx5e_ttc_get_default_dest(priv, MLX5E_TT_ANY); + dest = mlx5_ttc_get_default_dest(priv->fs.ttc, MLX5_TT_ANY); rule = mlx5_add_flow_rules(fs_any_t->t, NULL, &flow_act, &dest, 1); if (IS_ERR(rule)) { err = PTR_ERR(rule); @@ -514,11 +514,11 @@ static int fs_any_disable(struct mlx5e_priv *priv) int err; /* Modify ttc rules destination to point back to the indir TIRs */ - err = mlx5e_ttc_fwd_default_dest(priv, MLX5E_TT_ANY); + err = mlx5_ttc_fwd_default_dest(priv->fs.ttc, MLX5_TT_ANY); if (err) { netdev_err(priv->netdev, "%s: modify ttc[%d] default destination failed, err(%d)\n", - __func__, MLX5E_TT_ANY, err); + __func__, MLX5_TT_ANY, err); return err; } return 0; @@ -533,11 +533,11 @@ static int fs_any_enable(struct mlx5e_priv *priv) dest.ft = priv->fs.any->table.t; /* Modify ttc rules destination to point on the accel_fs FTs */ - err = mlx5e_ttc_fwd_dest(priv, MLX5E_TT_ANY, &dest); + err = mlx5_ttc_fwd_dest(priv->fs.ttc, MLX5_TT_ANY, &dest); if (err) { netdev_err(priv->netdev, "%s: modify ttc[%d] destination to accel failed, err(%d)\n", - __func__, MLX5E_TT_ANY, err); + __func__, MLX5_TT_ANY, err); return err; } return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.h index 8385df24eb99..7a70c4f38fda 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.h @@ -12,7 +12,7 @@ void mlx5e_fs_tt_redirect_del_rule(struct mlx5_flow_handle *rule); /* UDP traffic type redirect */ struct mlx5_flow_handle * mlx5e_fs_tt_redirect_udp_add_rule(struct mlx5e_priv *priv, - enum mlx5e_traffic_types ttc_type, + enum mlx5_traffic_types ttc_type, u32 tir_num, u16 d_port); void mlx5e_fs_tt_redirect_udp_destroy(struct mlx5e_priv *priv); int mlx5e_fs_tt_redirect_udp_create(struct mlx5e_priv *priv); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/mapping.c b/drivers/net/ethernet/mellanox/mlx5/core/en/mapping.c index ea321e528749..4e72ca8070e2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/mapping.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/mapping.c @@ -5,11 +5,15 @@ #include <linux/slab.h> #include <linux/xarray.h> #include <linux/hashtable.h> +#include <linux/refcount.h> #include "mapping.h" #define MAPPING_GRACE_PERIOD 2000 +static LIST_HEAD(shared_ctx_list); +static DEFINE_MUTEX(shared_ctx_lock); + struct mapping_ctx { struct xarray xarray; DECLARE_HASHTABLE(ht, 8); @@ -20,6 +24,10 @@ struct mapping_ctx { struct delayed_work dwork; struct list_head pending_list; spinlock_t pending_list_lock; /* Guards pending list */ + u64 id; + u8 type; + struct list_head list; + refcount_t refcount; }; struct mapping_item { @@ -205,11 +213,48 @@ mapping_create(size_t data_size, u32 max_id, bool delayed_removal) mutex_init(&ctx->lock); xa_init_flags(&ctx->xarray, XA_FLAGS_ALLOC1); + refcount_set(&ctx->refcount, 1); + INIT_LIST_HEAD(&ctx->list); + + return ctx; +} + +struct mapping_ctx * +mapping_create_for_id(u64 id, u8 type, size_t data_size, u32 max_id, bool delayed_removal) +{ + struct mapping_ctx *ctx; + + mutex_lock(&shared_ctx_lock); + list_for_each_entry(ctx, &shared_ctx_list, list) { + if (ctx->id == id && ctx->type == type) { + if (refcount_inc_not_zero(&ctx->refcount)) + goto unlock; + break; + } + } + + ctx = mapping_create(data_size, max_id, delayed_removal); + if (IS_ERR(ctx)) + goto unlock; + + ctx->id = id; + ctx->type = type; + list_add(&ctx->list, &shared_ctx_list); + +unlock: + mutex_unlock(&shared_ctx_lock); return ctx; } void mapping_destroy(struct mapping_ctx *ctx) { + if (!refcount_dec_and_test(&ctx->refcount)) + return; + + mutex_lock(&shared_ctx_lock); + list_del(&ctx->list); + mutex_unlock(&shared_ctx_lock); + mapping_flush_work(ctx); xa_destroy(&ctx->xarray); mutex_destroy(&ctx->lock); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/mapping.h b/drivers/net/ethernet/mellanox/mlx5/core/en/mapping.h index 285525cc5470..4e2119f0f4c1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/mapping.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/mapping.h @@ -24,4 +24,9 @@ struct mapping_ctx *mapping_create(size_t data_size, u32 max_id, bool delayed_removal); void mapping_destroy(struct mapping_ctx *ctx); +/* adds mapping with an id or get an existing mapping with the same id + */ +struct mapping_ctx * +mapping_create_for_id(u64 id, u8 type, size_t data_size, u32 max_id, bool delayed_removal); + #endif /* __MLX5_MAPPING_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c index 2cbf18c967f7..3cbb596821e8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c @@ -167,6 +167,18 @@ u16 mlx5e_get_rq_headroom(struct mlx5_core_dev *mdev, return is_linear_skb ? mlx5e_get_linear_rq_headroom(params, xsk) : 0; } +struct mlx5e_lro_param mlx5e_get_lro_param(struct mlx5e_params *params) +{ + struct mlx5e_lro_param lro_param; + + lro_param = (struct mlx5e_lro_param) { + .enabled = params->lro_en, + .timeout = params->lro_timeout, + }; + + return lro_param; +} + u16 mlx5e_calc_sq_stop_room(struct mlx5_core_dev *mdev, struct mlx5e_params *params) { bool is_mpwqe = MLX5E_GET_PFLAG(params, MLX5E_PFLAG_SKB_TX_MPWQE); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h index e9593f5f0661..879ad46d754e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h @@ -11,6 +11,11 @@ struct mlx5e_xsk_param { u16 chunk_size; }; +struct mlx5e_lro_param { + bool enabled; + u32 timeout; +}; + struct mlx5e_cq_param { u32 cqc[MLX5_ST_SZ_DW(cqc)]; struct mlx5_wq_param wq; @@ -120,6 +125,7 @@ u8 mlx5e_mpwqe_get_log_num_strides(struct mlx5_core_dev *mdev, u16 mlx5e_get_rq_headroom(struct mlx5_core_dev *mdev, struct mlx5e_params *params, struct mlx5e_xsk_param *xsk); +struct mlx5e_lro_param mlx5e_get_lro_param(struct mlx5e_params *params); /* Build queue parameters */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c index efef4adce086..ee688dec67a9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c @@ -326,13 +326,14 @@ static int mlx5e_ptp_open_txqsqs(struct mlx5e_ptp *c, struct mlx5e_ptp_params *cparams) { struct mlx5e_params *params = &cparams->params; + u8 num_tc = mlx5e_get_dcb_num_tc(params); int ix_base; int err; int tc; - ix_base = params->num_tc * params->num_channels; + ix_base = num_tc * params->num_channels; - for (tc = 0; tc < params->num_tc; tc++) { + for (tc = 0; tc < num_tc; tc++) { int txq_ix = ix_base + tc; err = mlx5e_ptp_open_txqsq(c, c->priv->tisn[c->lag_port][tc], txq_ix, @@ -365,9 +366,12 @@ static int mlx5e_ptp_open_tx_cqs(struct mlx5e_ptp *c, struct mlx5e_create_cq_param ccp = {}; struct dim_cq_moder ptp_moder = {}; struct mlx5e_cq_param *cq_param; + u8 num_tc; int err; int tc; + num_tc = mlx5e_get_dcb_num_tc(params); + ccp.node = dev_to_node(mlx5_core_dma_dev(c->mdev)); ccp.ch_stats = c->stats; ccp.napi = &c->napi; @@ -375,7 +379,7 @@ static int mlx5e_ptp_open_tx_cqs(struct mlx5e_ptp *c, cq_param = &cparams->txq_sq_param.cqp; - for (tc = 0; tc < params->num_tc; tc++) { + for (tc = 0; tc < num_tc; tc++) { struct mlx5e_cq *cq = &c->ptpsq[tc].txqsq.cq; err = mlx5e_open_cq(c->priv, ptp_moder, cq_param, &ccp, cq); @@ -383,7 +387,7 @@ static int mlx5e_ptp_open_tx_cqs(struct mlx5e_ptp *c, goto out_err_txqsq_cq; } - for (tc = 0; tc < params->num_tc; tc++) { + for (tc = 0; tc < num_tc; tc++) { struct mlx5e_cq *cq = &c->ptpsq[tc].ts_cq; struct mlx5e_ptpsq *ptpsq = &c->ptpsq[tc]; @@ -399,7 +403,7 @@ static int mlx5e_ptp_open_tx_cqs(struct mlx5e_ptp *c, out_err_ts_cq: for (--tc; tc >= 0; tc--) mlx5e_close_cq(&c->ptpsq[tc].ts_cq); - tc = params->num_tc; + tc = num_tc; out_err_txqsq_cq: for (--tc; tc >= 0; tc--) mlx5e_close_cq(&c->ptpsq[tc].txqsq.cq); @@ -475,7 +479,7 @@ static void mlx5e_ptp_build_params(struct mlx5e_ptp *c, params->num_channels = orig->num_channels; params->hard_mtu = orig->hard_mtu; params->sw_mtu = orig->sw_mtu; - params->num_tc = orig->num_tc; + params->mqprio = orig->mqprio; /* SQ */ if (test_bit(MLX5E_PTP_STATE_TX, c->state)) { @@ -605,9 +609,9 @@ static void mlx5e_ptp_rx_unset_fs(struct mlx5e_priv *priv) static int mlx5e_ptp_rx_set_fs(struct mlx5e_priv *priv) { + u32 tirn = mlx5e_rx_res_get_tirn_ptp(priv->rx_res); struct mlx5e_ptp_fs *ptp_fs = priv->fs.ptp_fs; struct mlx5_flow_handle *rule; - u32 tirn = priv->ptp_tir.tirn; int err; if (ptp_fs->valid) @@ -617,7 +621,7 @@ static int mlx5e_ptp_rx_set_fs(struct mlx5e_priv *priv) if (err) goto out_free; - rule = mlx5e_fs_tt_redirect_udp_add_rule(priv, MLX5E_TT_IPV4_UDP, + rule = mlx5e_fs_tt_redirect_udp_add_rule(priv, MLX5_TT_IPV4_UDP, tirn, PTP_EV_PORT); if (IS_ERR(rule)) { err = PTR_ERR(rule); @@ -625,7 +629,7 @@ static int mlx5e_ptp_rx_set_fs(struct mlx5e_priv *priv) } ptp_fs->udp_v4_rule = rule; - rule = mlx5e_fs_tt_redirect_udp_add_rule(priv, MLX5E_TT_IPV6_UDP, + rule = mlx5e_fs_tt_redirect_udp_add_rule(priv, MLX5_TT_IPV6_UDP, tirn, PTP_EV_PORT); if (IS_ERR(rule)) { err = PTR_ERR(rule); @@ -680,7 +684,7 @@ int mlx5e_ptp_open(struct mlx5e_priv *priv, struct mlx5e_params *params, c->pdev = mlx5_core_dma_dev(priv->mdev); c->netdev = priv->netdev; c->mkey_be = cpu_to_be32(priv->mdev->mlx5e_res.hw_objs.mkey.key); - c->num_tc = params->num_tc; + c->num_tc = mlx5e_get_dcb_num_tc(params); c->stats = &priv->ptp_stats.ch; c->lag_port = lag_port; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c index 5efe3278b0f6..e8a8d78e3e4d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c @@ -132,7 +132,7 @@ static u16 mlx5e_qid_from_qos(struct mlx5e_channels *chs, u16 qid) */ bool is_ptp = MLX5E_GET_PFLAG(&chs->params, MLX5E_PFLAG_TX_PORT_TS); - return (chs->params.num_channels + is_ptp) * chs->params.num_tc + qid; + return (chs->params.num_channels + is_ptp) * mlx5e_get_dcb_num_tc(&chs->params) + qid; } int mlx5e_get_txq_by_classid(struct mlx5e_priv *priv, u16 classid) @@ -733,8 +733,8 @@ static void mlx5e_reset_qdisc(struct net_device *dev, u16 qid) spin_unlock_bh(qdisc_lock(qdisc)); } -int mlx5e_htb_leaf_del(struct mlx5e_priv *priv, u16 classid, u16 *old_qid, - u16 *new_qid, struct netlink_ext_ack *extack) +int mlx5e_htb_leaf_del(struct mlx5e_priv *priv, u16 *classid, + struct netlink_ext_ack *extack) { struct mlx5e_qos_node *node; struct netdev_queue *txq; @@ -742,11 +742,9 @@ int mlx5e_htb_leaf_del(struct mlx5e_priv *priv, u16 classid, u16 *old_qid, bool opened; int err; - qos_dbg(priv->mdev, "TC_HTB_LEAF_DEL classid %04x\n", classid); - - *old_qid = *new_qid = 0; + qos_dbg(priv->mdev, "TC_HTB_LEAF_DEL classid %04x\n", *classid); - node = mlx5e_sw_node_find(priv, classid); + node = mlx5e_sw_node_find(priv, *classid); if (!node) return -ENOENT; @@ -764,7 +762,7 @@ int mlx5e_htb_leaf_del(struct mlx5e_priv *priv, u16 classid, u16 *old_qid, err = mlx5_qos_destroy_node(priv->mdev, node->hw_id); if (err) /* Not fatal. */ qos_warn(priv->mdev, "Failed to destroy leaf node %u (class %04x), err = %d\n", - node->hw_id, classid, err); + node->hw_id, *classid, err); mlx5e_sw_node_delete(priv, node); @@ -826,8 +824,7 @@ int mlx5e_htb_leaf_del(struct mlx5e_priv *priv, u16 classid, u16 *old_qid, if (opened) mlx5e_reactivate_qos_sq(priv, moved_qid, txq); - *old_qid = mlx5e_qid_from_qos(&priv->channels, moved_qid); - *new_qid = mlx5e_qid_from_qos(&priv->channels, qid); + *classid = node->classid; return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.h b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.h index 5af7991fcd19..757682b7c0e0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.h @@ -34,8 +34,8 @@ int mlx5e_htb_leaf_alloc_queue(struct mlx5e_priv *priv, u16 classid, struct netlink_ext_ack *extack); int mlx5e_htb_leaf_to_inner(struct mlx5e_priv *priv, u16 classid, u16 child_classid, u64 rate, u64 ceil, struct netlink_ext_ack *extack); -int mlx5e_htb_leaf_del(struct mlx5e_priv *priv, u16 classid, u16 *old_qid, - u16 *new_qid, struct netlink_ext_ack *extack); +int mlx5e_htb_leaf_del(struct mlx5e_priv *priv, u16 *classid, + struct netlink_ext_ack *extack); int mlx5e_htb_leaf_del_last(struct mlx5e_priv *priv, u16 classid, bool force, struct netlink_ext_ack *extack); int mlx5e_htb_node_modify(struct mlx5e_priv *priv, u16 classid, u64 rate, u64 ceil, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c index 3c0032c9647c..0c38c2e319be 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c @@ -15,9 +15,116 @@ struct mlx5_bridge_switchdev_fdb_work { struct work_struct work; struct switchdev_notifier_fdb_info fdb_info; struct net_device *dev; + struct mlx5_esw_bridge_offloads *br_offloads; bool add; }; +static bool mlx5_esw_bridge_dev_same_esw(struct net_device *dev, struct mlx5_eswitch *esw) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + + return esw == priv->mdev->priv.eswitch; +} + +static bool mlx5_esw_bridge_dev_same_hw(struct net_device *dev, struct mlx5_eswitch *esw) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + struct mlx5_core_dev *mdev, *esw_mdev; + u64 system_guid, esw_system_guid; + + mdev = priv->mdev; + esw_mdev = esw->dev; + + system_guid = mlx5_query_nic_system_image_guid(mdev); + esw_system_guid = mlx5_query_nic_system_image_guid(esw_mdev); + + return system_guid == esw_system_guid; +} + +static struct net_device * +mlx5_esw_bridge_lag_rep_get(struct net_device *dev, struct mlx5_eswitch *esw) +{ + struct net_device *lower; + struct list_head *iter; + + netdev_for_each_lower_dev(dev, lower, iter) { + struct mlx5_core_dev *mdev; + struct mlx5e_priv *priv; + + if (!mlx5e_eswitch_rep(lower)) + continue; + + priv = netdev_priv(lower); + mdev = priv->mdev; + if (mlx5_lag_is_shared_fdb(mdev) && mlx5_esw_bridge_dev_same_esw(lower, esw)) + return lower; + } + + return NULL; +} + +static struct net_device * +mlx5_esw_bridge_rep_vport_num_vhca_id_get(struct net_device *dev, struct mlx5_eswitch *esw, + u16 *vport_num, u16 *esw_owner_vhca_id) +{ + struct mlx5e_rep_priv *rpriv; + struct mlx5e_priv *priv; + + if (netif_is_lag_master(dev)) + dev = mlx5_esw_bridge_lag_rep_get(dev, esw); + + if (!dev || !mlx5e_eswitch_rep(dev) || !mlx5_esw_bridge_dev_same_hw(dev, esw)) + return NULL; + + priv = netdev_priv(dev); + rpriv = priv->ppriv; + *vport_num = rpriv->rep->vport; + *esw_owner_vhca_id = MLX5_CAP_GEN(priv->mdev, vhca_id); + return dev; +} + +static struct net_device * +mlx5_esw_bridge_lower_rep_vport_num_vhca_id_get(struct net_device *dev, struct mlx5_eswitch *esw, + u16 *vport_num, u16 *esw_owner_vhca_id) +{ + struct net_device *lower_dev; + struct list_head *iter; + + if (netif_is_lag_master(dev) || mlx5e_eswitch_rep(dev)) + return mlx5_esw_bridge_rep_vport_num_vhca_id_get(dev, esw, vport_num, + esw_owner_vhca_id); + + netdev_for_each_lower_dev(dev, lower_dev, iter) { + struct net_device *rep; + + if (netif_is_bridge_master(lower_dev)) + continue; + + rep = mlx5_esw_bridge_lower_rep_vport_num_vhca_id_get(lower_dev, esw, vport_num, + esw_owner_vhca_id); + if (rep) + return rep; + } + + return NULL; +} + +static bool mlx5_esw_bridge_is_local(struct net_device *dev, struct net_device *rep, + struct mlx5_eswitch *esw) +{ + struct mlx5_core_dev *mdev; + struct mlx5e_priv *priv; + + if (!mlx5_esw_bridge_dev_same_esw(rep, esw)) + return false; + + priv = netdev_priv(rep); + mdev = priv->mdev; + if (netif_is_lag_master(dev)) + return mlx5_lag_is_shared_fdb(mdev) && mlx5_lag_is_master(mdev); + return true; +} + static int mlx5_esw_bridge_port_changeupper(struct notifier_block *nb, void *ptr) { struct mlx5_esw_bridge_offloads *br_offloads = container_of(nb, @@ -25,37 +132,36 @@ static int mlx5_esw_bridge_port_changeupper(struct notifier_block *nb, void *ptr netdev_nb); struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct netdev_notifier_changeupper_info *info = ptr; + struct net_device *upper = info->upper_dev, *rep; + struct mlx5_eswitch *esw = br_offloads->esw; + u16 vport_num, esw_owner_vhca_id; struct netlink_ext_ack *extack; - struct mlx5e_rep_priv *rpriv; - struct mlx5_eswitch *esw; - struct mlx5_vport *vport; - struct net_device *upper; - struct mlx5e_priv *priv; - u16 vport_num; - - if (!mlx5e_eswitch_rep(dev)) - return 0; + int ifindex = upper->ifindex; + int err; - upper = info->upper_dev; if (!netif_is_bridge_master(upper)) return 0; - esw = br_offloads->esw; - priv = netdev_priv(dev); - if (esw != priv->mdev->priv.eswitch) + rep = mlx5_esw_bridge_rep_vport_num_vhca_id_get(dev, esw, &vport_num, &esw_owner_vhca_id); + if (!rep) return 0; - rpriv = priv->ppriv; - vport_num = rpriv->rep->vport; - vport = mlx5_eswitch_get_vport(esw, vport_num); - if (IS_ERR(vport)) - return PTR_ERR(vport); - extack = netdev_notifier_info_to_extack(&info->info); - return info->linking ? - mlx5_esw_bridge_vport_link(upper->ifindex, br_offloads, vport, extack) : - mlx5_esw_bridge_vport_unlink(upper->ifindex, br_offloads, vport, extack); + if (mlx5_esw_bridge_is_local(dev, rep, esw)) + err = info->linking ? + mlx5_esw_bridge_vport_link(ifindex, vport_num, esw_owner_vhca_id, + br_offloads, extack) : + mlx5_esw_bridge_vport_unlink(ifindex, vport_num, esw_owner_vhca_id, + br_offloads, extack); + else if (mlx5_esw_bridge_dev_same_hw(rep, esw)) + err = info->linking ? + mlx5_esw_bridge_vport_peer_link(ifindex, vport_num, esw_owner_vhca_id, + br_offloads, extack) : + mlx5_esw_bridge_vport_peer_unlink(ifindex, vport_num, esw_owner_vhca_id, + br_offloads, extack); + + return err; } static int mlx5_esw_bridge_switchdev_port_event(struct notifier_block *nb, @@ -75,31 +181,28 @@ static int mlx5_esw_bridge_switchdev_port_event(struct notifier_block *nb, return notifier_from_errno(err); } -static int mlx5_esw_bridge_port_obj_add(struct net_device *dev, - const void *ctx, - const struct switchdev_obj *obj, - struct netlink_ext_ack *extack) +static int +mlx5_esw_bridge_port_obj_add(struct net_device *dev, + struct switchdev_notifier_port_obj_info *port_obj_info, + struct mlx5_esw_bridge_offloads *br_offloads) { + struct netlink_ext_ack *extack = switchdev_notifier_info_to_extack(&port_obj_info->info); + const struct switchdev_obj *obj = port_obj_info->obj; const struct switchdev_obj_port_vlan *vlan; - struct mlx5e_rep_priv *rpriv; - struct mlx5_eswitch *esw; - struct mlx5_vport *vport; - struct mlx5e_priv *priv; - u16 vport_num; - int err = 0; + u16 vport_num, esw_owner_vhca_id; + int err; - priv = netdev_priv(dev); - rpriv = priv->ppriv; - vport_num = rpriv->rep->vport; - esw = priv->mdev->priv.eswitch; - vport = mlx5_eswitch_get_vport(esw, vport_num); - if (IS_ERR(vport)) - return PTR_ERR(vport); + if (!mlx5_esw_bridge_rep_vport_num_vhca_id_get(dev, br_offloads->esw, &vport_num, + &esw_owner_vhca_id)) + return 0; + + port_obj_info->handled = true; switch (obj->id) { case SWITCHDEV_OBJ_ID_PORT_VLAN: vlan = SWITCHDEV_OBJ_PORT_VLAN(obj); - err = mlx5_esw_bridge_port_vlan_add(vlan->vid, vlan->flags, esw, vport, extack); + err = mlx5_esw_bridge_port_vlan_add(vport_num, esw_owner_vhca_id, vlan->vid, + vlan->flags, br_offloads, extack); break; default: return -EOPNOTSUPP; @@ -107,29 +210,25 @@ static int mlx5_esw_bridge_port_obj_add(struct net_device *dev, return err; } -static int mlx5_esw_bridge_port_obj_del(struct net_device *dev, - const void *ctx, - const struct switchdev_obj *obj) +static int +mlx5_esw_bridge_port_obj_del(struct net_device *dev, + struct switchdev_notifier_port_obj_info *port_obj_info, + struct mlx5_esw_bridge_offloads *br_offloads) { + const struct switchdev_obj *obj = port_obj_info->obj; const struct switchdev_obj_port_vlan *vlan; - struct mlx5e_rep_priv *rpriv; - struct mlx5_eswitch *esw; - struct mlx5_vport *vport; - struct mlx5e_priv *priv; - u16 vport_num; + u16 vport_num, esw_owner_vhca_id; - priv = netdev_priv(dev); - rpriv = priv->ppriv; - vport_num = rpriv->rep->vport; - esw = priv->mdev->priv.eswitch; - vport = mlx5_eswitch_get_vport(esw, vport_num); - if (IS_ERR(vport)) - return PTR_ERR(vport); + if (!mlx5_esw_bridge_rep_vport_num_vhca_id_get(dev, br_offloads->esw, &vport_num, + &esw_owner_vhca_id)) + return 0; + + port_obj_info->handled = true; switch (obj->id) { case SWITCHDEV_OBJ_ID_PORT_VLAN: vlan = SWITCHDEV_OBJ_PORT_VLAN(obj); - mlx5_esw_bridge_port_vlan_del(vlan->vid, esw, vport); + mlx5_esw_bridge_port_vlan_del(vport_num, esw_owner_vhca_id, vlan->vid, br_offloads); break; default: return -EOPNOTSUPP; @@ -137,25 +236,21 @@ static int mlx5_esw_bridge_port_obj_del(struct net_device *dev, return 0; } -static int mlx5_esw_bridge_port_obj_attr_set(struct net_device *dev, - const void *ctx, - const struct switchdev_attr *attr, - struct netlink_ext_ack *extack) +static int +mlx5_esw_bridge_port_obj_attr_set(struct net_device *dev, + struct switchdev_notifier_port_attr_info *port_attr_info, + struct mlx5_esw_bridge_offloads *br_offloads) { - struct mlx5e_rep_priv *rpriv; - struct mlx5_eswitch *esw; - struct mlx5_vport *vport; - struct mlx5e_priv *priv; - u16 vport_num; - int err = 0; + struct netlink_ext_ack *extack = switchdev_notifier_info_to_extack(&port_attr_info->info); + const struct switchdev_attr *attr = port_attr_info->attr; + u16 vport_num, esw_owner_vhca_id; + int err; - priv = netdev_priv(dev); - rpriv = priv->ppriv; - vport_num = rpriv->rep->vport; - esw = priv->mdev->priv.eswitch; - vport = mlx5_eswitch_get_vport(esw, vport_num); - if (IS_ERR(vport)) - return PTR_ERR(vport); + if (!mlx5_esw_bridge_lower_rep_vport_num_vhca_id_get(dev, br_offloads->esw, &vport_num, + &esw_owner_vhca_id)) + return 0; + + port_attr_info->handled = true; switch (attr->id) { case SWITCHDEV_ATTR_ID_PORT_PRE_BRIDGE_FLAGS: @@ -167,10 +262,12 @@ static int mlx5_esw_bridge_port_obj_attr_set(struct net_device *dev, case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS: break; case SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME: - err = mlx5_esw_bridge_ageing_time_set(attr->u.ageing_time, esw, vport); + err = mlx5_esw_bridge_ageing_time_set(vport_num, esw_owner_vhca_id, + attr->u.ageing_time, br_offloads); break; case SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING: - err = mlx5_esw_bridge_vlan_filtering_set(attr->u.vlan_filtering, esw, vport); + err = mlx5_esw_bridge_vlan_filtering_set(vport_num, esw_owner_vhca_id, + attr->u.vlan_filtering, br_offloads); break; default: err = -EOPNOTSUPP; @@ -179,27 +276,24 @@ static int mlx5_esw_bridge_port_obj_attr_set(struct net_device *dev, return err; } -static int mlx5_esw_bridge_event_blocking(struct notifier_block *unused, +static int mlx5_esw_bridge_event_blocking(struct notifier_block *nb, unsigned long event, void *ptr) { + struct mlx5_esw_bridge_offloads *br_offloads = container_of(nb, + struct mlx5_esw_bridge_offloads, + nb_blk); struct net_device *dev = switchdev_notifier_info_to_dev(ptr); int err; switch (event) { case SWITCHDEV_PORT_OBJ_ADD: - err = switchdev_handle_port_obj_add(dev, ptr, - mlx5e_eswitch_rep, - mlx5_esw_bridge_port_obj_add); + err = mlx5_esw_bridge_port_obj_add(dev, ptr, br_offloads); break; case SWITCHDEV_PORT_OBJ_DEL: - err = switchdev_handle_port_obj_del(dev, ptr, - mlx5e_eswitch_rep, - mlx5_esw_bridge_port_obj_del); + err = mlx5_esw_bridge_port_obj_del(dev, ptr, br_offloads); break; case SWITCHDEV_PORT_ATTR_SET: - err = switchdev_handle_port_attr_set(dev, ptr, - mlx5e_eswitch_rep, - mlx5_esw_bridge_port_obj_attr_set); + err = mlx5_esw_bridge_port_obj_attr_set(dev, ptr, br_offloads); break; default: err = 0; @@ -222,27 +316,23 @@ static void mlx5_esw_bridge_switchdev_fdb_event_work(struct work_struct *work) container_of(work, struct mlx5_bridge_switchdev_fdb_work, work); struct switchdev_notifier_fdb_info *fdb_info = &fdb_work->fdb_info; + struct mlx5_esw_bridge_offloads *br_offloads = + fdb_work->br_offloads; struct net_device *dev = fdb_work->dev; - struct mlx5e_rep_priv *rpriv; - struct mlx5_eswitch *esw; - struct mlx5_vport *vport; - struct mlx5e_priv *priv; - u16 vport_num; + u16 vport_num, esw_owner_vhca_id; rtnl_lock(); - priv = netdev_priv(dev); - rpriv = priv->ppriv; - vport_num = rpriv->rep->vport; - esw = priv->mdev->priv.eswitch; - vport = mlx5_eswitch_get_vport(esw, vport_num); - if (IS_ERR(vport)) + if (!mlx5_esw_bridge_rep_vport_num_vhca_id_get(dev, br_offloads->esw, &vport_num, + &esw_owner_vhca_id)) goto out; if (fdb_work->add) - mlx5_esw_bridge_fdb_create(dev, esw, vport, fdb_info); + mlx5_esw_bridge_fdb_create(dev, vport_num, esw_owner_vhca_id, br_offloads, + fdb_info); else - mlx5_esw_bridge_fdb_remove(dev, esw, vport, fdb_info); + mlx5_esw_bridge_fdb_remove(dev, vport_num, esw_owner_vhca_id, br_offloads, + fdb_info); out: rtnl_unlock(); @@ -251,7 +341,8 @@ out: static struct mlx5_bridge_switchdev_fdb_work * mlx5_esw_bridge_init_switchdev_fdb_work(struct net_device *dev, bool add, - struct switchdev_notifier_fdb_info *fdb_info) + struct switchdev_notifier_fdb_info *fdb_info, + struct mlx5_esw_bridge_offloads *br_offloads) { struct mlx5_bridge_switchdev_fdb_work *work; u8 *addr; @@ -273,6 +364,7 @@ mlx5_esw_bridge_init_switchdev_fdb_work(struct net_device *dev, bool add, dev_hold(dev); work->dev = dev; + work->br_offloads = br_offloads; work->add = add; return work; } @@ -286,20 +378,14 @@ static int mlx5_esw_bridge_switchdev_event(struct notifier_block *nb, struct net_device *dev = switchdev_notifier_info_to_dev(ptr); struct switchdev_notifier_fdb_info *fdb_info; struct mlx5_bridge_switchdev_fdb_work *work; + struct mlx5_eswitch *esw = br_offloads->esw; struct switchdev_notifier_info *info = ptr; - struct net_device *upper; - struct mlx5e_priv *priv; - - if (!mlx5e_eswitch_rep(dev)) - return NOTIFY_DONE; - priv = netdev_priv(dev); - if (priv->mdev->priv.eswitch != br_offloads->esw) - return NOTIFY_DONE; + u16 vport_num, esw_owner_vhca_id; + struct net_device *upper, *rep; if (event == SWITCHDEV_PORT_ATTR_SET) { - int err = switchdev_handle_port_attr_set(dev, ptr, - mlx5e_eswitch_rep, - mlx5_esw_bridge_port_obj_attr_set); + int err = mlx5_esw_bridge_port_obj_attr_set(dev, ptr, br_offloads); + return notifier_from_errno(err); } @@ -309,7 +395,27 @@ static int mlx5_esw_bridge_switchdev_event(struct notifier_block *nb, if (!netif_is_bridge_master(upper)) return NOTIFY_DONE; + rep = mlx5_esw_bridge_rep_vport_num_vhca_id_get(dev, esw, &vport_num, &esw_owner_vhca_id); + if (!rep) + return NOTIFY_DONE; + switch (event) { + case SWITCHDEV_FDB_ADD_TO_BRIDGE: + /* only handle the event on native eswtich of representor */ + if (!mlx5_esw_bridge_is_local(dev, rep, esw)) + break; + + fdb_info = container_of(info, + struct switchdev_notifier_fdb_info, + info); + mlx5_esw_bridge_fdb_update_used(dev, vport_num, esw_owner_vhca_id, br_offloads, + fdb_info); + break; + case SWITCHDEV_FDB_DEL_TO_BRIDGE: + /* only handle the event on peers */ + if (mlx5_esw_bridge_is_local(dev, rep, esw)) + break; + fallthrough; case SWITCHDEV_FDB_ADD_TO_DEVICE: case SWITCHDEV_FDB_DEL_TO_DEVICE: fdb_info = container_of(info, @@ -318,7 +424,8 @@ static int mlx5_esw_bridge_switchdev_event(struct notifier_block *nb, work = mlx5_esw_bridge_init_switchdev_fdb_work(dev, event == SWITCHDEV_FDB_ADD_TO_DEVICE, - fdb_info); + fdb_info, + br_offloads); if (IS_ERR(work)) { WARN_ONCE(1, "Failed to init switchdev work, err=%ld", PTR_ERR(work)); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c index 059799e4f483..51a4d80f7fa3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c @@ -17,7 +17,7 @@ #include "en/mapping.h" #include "en/tc_tun.h" #include "lib/port_tun.h" -#include "esw/sample.h" +#include "en/tc/sample.h" struct mlx5e_rep_indr_block_priv { struct net_device *netdev; @@ -516,7 +516,6 @@ void mlx5e_rep_tc_netdevice_event_unregister(struct mlx5e_rep_priv *rpriv) mlx5e_rep_indr_block_unbind); } -#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) static bool mlx5e_restore_tunnel(struct mlx5e_priv *priv, struct sk_buff *skb, struct mlx5e_tc_update_priv *tc_priv, u32 tunnel_id) @@ -609,12 +608,13 @@ static bool mlx5e_restore_tunnel(struct mlx5e_priv *priv, struct sk_buff *skb, return true; } -static bool mlx5e_restore_skb(struct sk_buff *skb, u32 chain, u32 reg_c1, - struct mlx5e_tc_update_priv *tc_priv) +static bool mlx5e_restore_skb_chain(struct sk_buff *skb, u32 chain, u32 reg_c1, + struct mlx5e_tc_update_priv *tc_priv) { struct mlx5e_priv *priv = netdev_priv(skb->dev); u32 tunnel_id = (reg_c1 >> ESW_TUN_OFFSET) & TUNNEL_ID_MASK; +#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) if (chain) { struct mlx5_rep_uplink_priv *uplink_priv; struct mlx5e_rep_priv *uplink_rpriv; @@ -636,9 +636,25 @@ static bool mlx5e_restore_skb(struct sk_buff *skb, u32 chain, u32 reg_c1, zone_restore_id)) return false; } +#endif /* CONFIG_NET_TC_SKB_EXT */ + return mlx5e_restore_tunnel(priv, skb, tc_priv, tunnel_id); } -#endif /* CONFIG_NET_TC_SKB_EXT */ + +static void mlx5e_restore_skb_sample(struct mlx5e_priv *priv, struct sk_buff *skb, + struct mlx5_mapped_obj *mapped_obj, + struct mlx5e_tc_update_priv *tc_priv) +{ + if (!mlx5e_restore_tunnel(priv, skb, tc_priv, mapped_obj->sample.tunnel_id)) { + netdev_dbg(priv->netdev, + "Failed to restore tunnel info for sampled packet\n"); + return; + } +#if IS_ENABLED(CONFIG_MLX5_TC_SAMPLE) + mlx5e_tc_sample_skb(skb, mapped_obj); +#endif /* CONFIG_MLX5_TC_SAMPLE */ + mlx5_rep_tc_post_napi_receive(tc_priv); +} bool mlx5e_rep_tc_update_skb(struct mlx5_cqe64 *cqe, struct sk_buff *skb, @@ -647,7 +663,7 @@ bool mlx5e_rep_tc_update_skb(struct mlx5_cqe64 *cqe, struct mlx5_mapped_obj mapped_obj; struct mlx5_eswitch *esw; struct mlx5e_priv *priv; - u32 reg_c0, reg_c1; + u32 reg_c0; int err; reg_c0 = (be32_to_cpu(cqe->sop_drop_qpn) & MLX5E_TC_FLOW_ID_MASK); @@ -659,8 +675,6 @@ bool mlx5e_rep_tc_update_skb(struct mlx5_cqe64 *cqe, */ skb->mark = 0; - reg_c1 = be32_to_cpu(cqe->ft_metadata); - priv = netdev_priv(skb->dev); esw = priv->mdev->priv.eswitch; err = mapping_find(esw->offloads.reg_c0_obj_pool, reg_c0, &mapped_obj); @@ -671,18 +685,14 @@ bool mlx5e_rep_tc_update_skb(struct mlx5_cqe64 *cqe, return false; } -#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) - if (mapped_obj.type == MLX5_MAPPED_OBJ_CHAIN) - return mlx5e_restore_skb(skb, mapped_obj.chain, reg_c1, tc_priv); -#endif /* CONFIG_NET_TC_SKB_EXT */ -#if IS_ENABLED(CONFIG_MLX5_TC_SAMPLE) - if (mapped_obj.type == MLX5_MAPPED_OBJ_SAMPLE) { - mlx5_esw_sample_skb(skb, &mapped_obj); + if (mapped_obj.type == MLX5_MAPPED_OBJ_CHAIN) { + u32 reg_c1 = be32_to_cpu(cqe->ft_metadata); + + return mlx5e_restore_skb_chain(skb, mapped_obj.chain, reg_c1, tc_priv); + } else if (mapped_obj.type == MLX5_MAPPED_OBJ_SAMPLE) { + mlx5e_restore_skb_sample(priv, skb, &mapped_obj, tc_priv); return false; - } -#endif /* CONFIG_MLX5_TC_SAMPLE */ - if (mapped_obj.type != MLX5_MAPPED_OBJ_SAMPLE && - mapped_obj.type != MLX5_MAPPED_OBJ_CHAIN) { + } else { netdev_dbg(priv->netdev, "Invalid mapped object type: %d\n", mapped_obj.type); return false; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c index 9d361efd5ff7..bb682fd751c9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c @@ -372,7 +372,7 @@ static int mlx5e_tx_reporter_diagnose(struct devlink_health_reporter *reporter, for (i = 0; i < priv->channels.num; i++) { struct mlx5e_channel *c = priv->channels.c[i]; - for (tc = 0; tc < priv->channels.params.num_tc; tc++) { + for (tc = 0; tc < mlx5e_get_dcb_num_tc(&priv->channels.params); tc++) { struct mlx5e_txqsq *sq = &c->sq[tc]; err = mlx5e_tx_reporter_build_diagnose_output(fmsg, sq, tc); @@ -384,7 +384,7 @@ static int mlx5e_tx_reporter_diagnose(struct devlink_health_reporter *reporter, if (!ptp_ch || !test_bit(MLX5E_PTP_STATE_TX, ptp_ch->state)) goto close_sqs_nest; - for (tc = 0; tc < priv->channels.params.num_tc; tc++) { + for (tc = 0; tc < mlx5e_get_dcb_num_tc(&priv->channels.params); tc++) { err = mlx5e_tx_reporter_build_diagnose_output_ptpsq(fmsg, &ptp_ch->ptpsq[tc], tc); @@ -494,7 +494,7 @@ static int mlx5e_tx_reporter_dump_all_sqs(struct mlx5e_priv *priv, for (i = 0; i < priv->channels.num; i++) { struct mlx5e_channel *c = priv->channels.c[i]; - for (tc = 0; tc < priv->channels.params.num_tc; tc++) { + for (tc = 0; tc < mlx5e_get_dcb_num_tc(&priv->channels.params); tc++) { struct mlx5e_txqsq *sq = &c->sq[tc]; err = mlx5e_health_queue_dump(priv, fmsg, sq->sqn, "SQ"); @@ -504,7 +504,7 @@ static int mlx5e_tx_reporter_dump_all_sqs(struct mlx5e_priv *priv, } if (ptp_ch && test_bit(MLX5E_PTP_STATE_TX, ptp_ch->state)) { - for (tc = 0; tc < priv->channels.params.num_tc; tc++) { + for (tc = 0; tc < mlx5e_get_dcb_num_tc(&priv->channels.params); tc++) { struct mlx5e_txqsq *sq = &ptp_ch->ptpsq[tc].txqsq; err = mlx5e_health_queue_dump(priv, fmsg, sq->sqn, "PTP SQ"); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.c new file mode 100644 index 000000000000..b915fb29dd2c --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.c @@ -0,0 +1,170 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2021, Mellanox Technologies inc. All rights reserved. */ + +#include "rqt.h" +#include <linux/mlx5/transobj.h> + +void mlx5e_rss_params_indir_init_uniform(struct mlx5e_rss_params_indir *indir, + unsigned int num_channels) +{ + unsigned int i; + + for (i = 0; i < MLX5E_INDIR_RQT_SIZE; i++) + indir->table[i] = i % num_channels; +} + +static int mlx5e_rqt_init(struct mlx5e_rqt *rqt, struct mlx5_core_dev *mdev, + u16 max_size, u32 *init_rqns, u16 init_size) +{ + void *rqtc; + int inlen; + int err; + u32 *in; + int i; + + rqt->mdev = mdev; + rqt->size = max_size; + + inlen = MLX5_ST_SZ_BYTES(create_rqt_in) + sizeof(u32) * init_size; + in = kvzalloc(inlen, GFP_KERNEL); + if (!in) + return -ENOMEM; + + rqtc = MLX5_ADDR_OF(create_rqt_in, in, rqt_context); + + MLX5_SET(rqtc, rqtc, rqt_max_size, rqt->size); + + MLX5_SET(rqtc, rqtc, rqt_actual_size, init_size); + for (i = 0; i < init_size; i++) + MLX5_SET(rqtc, rqtc, rq_num[i], init_rqns[i]); + + err = mlx5_core_create_rqt(rqt->mdev, in, inlen, &rqt->rqtn); + + kvfree(in); + return err; +} + +int mlx5e_rqt_init_direct(struct mlx5e_rqt *rqt, struct mlx5_core_dev *mdev, + bool indir_enabled, u32 init_rqn) +{ + u16 max_size = indir_enabled ? MLX5E_INDIR_RQT_SIZE : 1; + + return mlx5e_rqt_init(rqt, mdev, max_size, &init_rqn, 1); +} + +static int mlx5e_bits_invert(unsigned long a, int size) +{ + int inv = 0; + int i; + + for (i = 0; i < size; i++) + inv |= (test_bit(size - i - 1, &a) ? 1 : 0) << i; + + return inv; +} + +static int mlx5e_calc_indir_rqns(u32 *rss_rqns, u32 *rqns, unsigned int num_rqns, + u8 hfunc, struct mlx5e_rss_params_indir *indir) +{ + unsigned int i; + + for (i = 0; i < MLX5E_INDIR_RQT_SIZE; i++) { + unsigned int ix = i; + + if (hfunc == ETH_RSS_HASH_XOR) + ix = mlx5e_bits_invert(ix, ilog2(MLX5E_INDIR_RQT_SIZE)); + + ix = indir->table[ix]; + + if (WARN_ON(ix >= num_rqns)) + /* Could be a bug in the driver or in the kernel part of + * ethtool: indir table refers to non-existent RQs. + */ + return -EINVAL; + rss_rqns[i] = rqns[ix]; + } + + return 0; +} + +int mlx5e_rqt_init_indir(struct mlx5e_rqt *rqt, struct mlx5_core_dev *mdev, + u32 *rqns, unsigned int num_rqns, + u8 hfunc, struct mlx5e_rss_params_indir *indir) +{ + u32 *rss_rqns; + int err; + + rss_rqns = kvmalloc_array(MLX5E_INDIR_RQT_SIZE, sizeof(*rss_rqns), GFP_KERNEL); + if (!rss_rqns) + return -ENOMEM; + + err = mlx5e_calc_indir_rqns(rss_rqns, rqns, num_rqns, hfunc, indir); + if (err) + goto out; + + err = mlx5e_rqt_init(rqt, mdev, MLX5E_INDIR_RQT_SIZE, rss_rqns, MLX5E_INDIR_RQT_SIZE); + +out: + kvfree(rss_rqns); + return err; +} + +void mlx5e_rqt_destroy(struct mlx5e_rqt *rqt) +{ + mlx5_core_destroy_rqt(rqt->mdev, rqt->rqtn); +} + +static int mlx5e_rqt_redirect(struct mlx5e_rqt *rqt, u32 *rqns, unsigned int size) +{ + unsigned int i; + void *rqtc; + int inlen; + u32 *in; + int err; + + inlen = MLX5_ST_SZ_BYTES(modify_rqt_in) + sizeof(u32) * size; + in = kvzalloc(inlen, GFP_KERNEL); + if (!in) + return -ENOMEM; + + rqtc = MLX5_ADDR_OF(modify_rqt_in, in, ctx); + + MLX5_SET(modify_rqt_in, in, bitmask.rqn_list, 1); + MLX5_SET(rqtc, rqtc, rqt_actual_size, size); + for (i = 0; i < size; i++) + MLX5_SET(rqtc, rqtc, rq_num[i], rqns[i]); + + err = mlx5_core_modify_rqt(rqt->mdev, rqt->rqtn, in, inlen); + + kvfree(in); + return err; +} + +int mlx5e_rqt_redirect_direct(struct mlx5e_rqt *rqt, u32 rqn) +{ + return mlx5e_rqt_redirect(rqt, &rqn, 1); +} + +int mlx5e_rqt_redirect_indir(struct mlx5e_rqt *rqt, u32 *rqns, unsigned int num_rqns, + u8 hfunc, struct mlx5e_rss_params_indir *indir) +{ + u32 *rss_rqns; + int err; + + if (WARN_ON(rqt->size != MLX5E_INDIR_RQT_SIZE)) + return -EINVAL; + + rss_rqns = kvmalloc_array(MLX5E_INDIR_RQT_SIZE, sizeof(*rss_rqns), GFP_KERNEL); + if (!rss_rqns) + return -ENOMEM; + + err = mlx5e_calc_indir_rqns(rss_rqns, rqns, num_rqns, hfunc, indir); + if (err) + goto out; + + err = mlx5e_rqt_redirect(rqt, rss_rqns, MLX5E_INDIR_RQT_SIZE); + +out: + kvfree(rss_rqns); + return err; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.h new file mode 100644 index 000000000000..60c985a12f24 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.h @@ -0,0 +1,42 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2021, Mellanox Technologies inc. All rights reserved. */ + +#ifndef __MLX5_EN_RQT_H__ +#define __MLX5_EN_RQT_H__ + +#include <linux/kernel.h> + +#define MLX5E_INDIR_RQT_SIZE (1 << 8) + +struct mlx5_core_dev; + +struct mlx5e_rss_params_indir { + u32 table[MLX5E_INDIR_RQT_SIZE]; +}; + +void mlx5e_rss_params_indir_init_uniform(struct mlx5e_rss_params_indir *indir, + unsigned int num_channels); + +struct mlx5e_rqt { + struct mlx5_core_dev *mdev; + u32 rqtn; + u16 size; +}; + +int mlx5e_rqt_init_direct(struct mlx5e_rqt *rqt, struct mlx5_core_dev *mdev, + bool indir_enabled, u32 init_rqn); +int mlx5e_rqt_init_indir(struct mlx5e_rqt *rqt, struct mlx5_core_dev *mdev, + u32 *rqns, unsigned int num_rqns, + u8 hfunc, struct mlx5e_rss_params_indir *indir); +void mlx5e_rqt_destroy(struct mlx5e_rqt *rqt); + +static inline u32 mlx5e_rqt_get_rqtn(struct mlx5e_rqt *rqt) +{ + return rqt->rqtn; +} + +int mlx5e_rqt_redirect_direct(struct mlx5e_rqt *rqt, u32 rqn); +int mlx5e_rqt_redirect_indir(struct mlx5e_rqt *rqt, u32 *rqns, unsigned int num_rqns, + u8 hfunc, struct mlx5e_rss_params_indir *indir); + +#endif /* __MLX5_EN_RQT_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c new file mode 100644 index 000000000000..625cd49ef96c --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c @@ -0,0 +1,588 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +// Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. + +#include "rss.h" + +#define mlx5e_rss_warn(__dev, format, ...) \ + dev_warn((__dev)->device, "%s:%d:(pid %d): " format, \ + __func__, __LINE__, current->pid, \ + ##__VA_ARGS__) + +static const struct mlx5e_rss_params_traffic_type rss_default_config[MLX5E_NUM_INDIR_TIRS] = { + [MLX5_TT_IPV4_TCP] = { + .l3_prot_type = MLX5_L3_PROT_TYPE_IPV4, + .l4_prot_type = MLX5_L4_PROT_TYPE_TCP, + .rx_hash_fields = MLX5_HASH_IP_L4PORTS, + }, + [MLX5_TT_IPV6_TCP] = { + .l3_prot_type = MLX5_L3_PROT_TYPE_IPV6, + .l4_prot_type = MLX5_L4_PROT_TYPE_TCP, + .rx_hash_fields = MLX5_HASH_IP_L4PORTS, + }, + [MLX5_TT_IPV4_UDP] = { + .l3_prot_type = MLX5_L3_PROT_TYPE_IPV4, + .l4_prot_type = MLX5_L4_PROT_TYPE_UDP, + .rx_hash_fields = MLX5_HASH_IP_L4PORTS, + }, + [MLX5_TT_IPV6_UDP] = { + .l3_prot_type = MLX5_L3_PROT_TYPE_IPV6, + .l4_prot_type = MLX5_L4_PROT_TYPE_UDP, + .rx_hash_fields = MLX5_HASH_IP_L4PORTS, + }, + [MLX5_TT_IPV4_IPSEC_AH] = { + .l3_prot_type = MLX5_L3_PROT_TYPE_IPV4, + .l4_prot_type = 0, + .rx_hash_fields = MLX5_HASH_IP_IPSEC_SPI, + }, + [MLX5_TT_IPV6_IPSEC_AH] = { + .l3_prot_type = MLX5_L3_PROT_TYPE_IPV6, + .l4_prot_type = 0, + .rx_hash_fields = MLX5_HASH_IP_IPSEC_SPI, + }, + [MLX5_TT_IPV4_IPSEC_ESP] = { + .l3_prot_type = MLX5_L3_PROT_TYPE_IPV4, + .l4_prot_type = 0, + .rx_hash_fields = MLX5_HASH_IP_IPSEC_SPI, + }, + [MLX5_TT_IPV6_IPSEC_ESP] = { + .l3_prot_type = MLX5_L3_PROT_TYPE_IPV6, + .l4_prot_type = 0, + .rx_hash_fields = MLX5_HASH_IP_IPSEC_SPI, + }, + [MLX5_TT_IPV4] = { + .l3_prot_type = MLX5_L3_PROT_TYPE_IPV4, + .l4_prot_type = 0, + .rx_hash_fields = MLX5_HASH_IP, + }, + [MLX5_TT_IPV6] = { + .l3_prot_type = MLX5_L3_PROT_TYPE_IPV6, + .l4_prot_type = 0, + .rx_hash_fields = MLX5_HASH_IP, + }, +}; + +struct mlx5e_rss_params_traffic_type +mlx5e_rss_get_default_tt_config(enum mlx5_traffic_types tt) +{ + return rss_default_config[tt]; +} + +struct mlx5e_rss { + struct mlx5e_rss_params_hash hash; + struct mlx5e_rss_params_indir indir; + u32 rx_hash_fields[MLX5E_NUM_INDIR_TIRS]; + struct mlx5e_tir *tir[MLX5E_NUM_INDIR_TIRS]; + struct mlx5e_tir *inner_tir[MLX5E_NUM_INDIR_TIRS]; + struct mlx5e_rqt rqt; + struct mlx5_core_dev *mdev; + u32 drop_rqn; + bool inner_ft_support; + bool enabled; + refcount_t refcnt; +}; + +struct mlx5e_rss *mlx5e_rss_alloc(void) +{ + return kvzalloc(sizeof(struct mlx5e_rss), GFP_KERNEL); +} + +void mlx5e_rss_free(struct mlx5e_rss *rss) +{ + kvfree(rss); +} + +static void mlx5e_rss_params_init(struct mlx5e_rss *rss) +{ + enum mlx5_traffic_types tt; + + rss->hash.hfunc = ETH_RSS_HASH_TOP; + netdev_rss_key_fill(rss->hash.toeplitz_hash_key, + sizeof(rss->hash.toeplitz_hash_key)); + for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) + rss->rx_hash_fields[tt] = + mlx5e_rss_get_default_tt_config(tt).rx_hash_fields; +} + +static struct mlx5e_tir **rss_get_tirp(struct mlx5e_rss *rss, enum mlx5_traffic_types tt, + bool inner) +{ + return inner ? &rss->inner_tir[tt] : &rss->tir[tt]; +} + +static struct mlx5e_tir *rss_get_tir(struct mlx5e_rss *rss, enum mlx5_traffic_types tt, + bool inner) +{ + return *rss_get_tirp(rss, tt, inner); +} + +static struct mlx5e_rss_params_traffic_type +mlx5e_rss_get_tt_config(struct mlx5e_rss *rss, enum mlx5_traffic_types tt) +{ + struct mlx5e_rss_params_traffic_type rss_tt; + + rss_tt = mlx5e_rss_get_default_tt_config(tt); + rss_tt.rx_hash_fields = rss->rx_hash_fields[tt]; + return rss_tt; +} + +static int mlx5e_rss_create_tir(struct mlx5e_rss *rss, + enum mlx5_traffic_types tt, + const struct mlx5e_lro_param *init_lro_param, + bool inner) +{ + struct mlx5e_rss_params_traffic_type rss_tt; + struct mlx5e_tir_builder *builder; + struct mlx5e_tir **tir_p; + struct mlx5e_tir *tir; + u32 rqtn; + int err; + + if (inner && !rss->inner_ft_support) { + mlx5e_rss_warn(rss->mdev, + "Cannot create inner indirect TIR[%d], RSS inner FT is not supported.\n", + tt); + return -EINVAL; + } + + tir_p = rss_get_tirp(rss, tt, inner); + if (*tir_p) + return -EINVAL; + + tir = kvzalloc(sizeof(*tir), GFP_KERNEL); + if (!tir) + return -ENOMEM; + + builder = mlx5e_tir_builder_alloc(false); + if (!builder) { + err = -ENOMEM; + goto free_tir; + } + + rqtn = mlx5e_rqt_get_rqtn(&rss->rqt); + mlx5e_tir_builder_build_rqt(builder, rss->mdev->mlx5e_res.hw_objs.td.tdn, + rqtn, rss->inner_ft_support); + mlx5e_tir_builder_build_lro(builder, init_lro_param); + rss_tt = mlx5e_rss_get_tt_config(rss, tt); + mlx5e_tir_builder_build_rss(builder, &rss->hash, &rss_tt, inner); + + err = mlx5e_tir_init(tir, builder, rss->mdev, true); + mlx5e_tir_builder_free(builder); + if (err) { + mlx5e_rss_warn(rss->mdev, "Failed to create %sindirect TIR: err = %d, tt = %d\n", + inner ? "inner " : "", err, tt); + goto free_tir; + } + + *tir_p = tir; + return 0; + +free_tir: + kvfree(tir); + return err; +} + +static void mlx5e_rss_destroy_tir(struct mlx5e_rss *rss, enum mlx5_traffic_types tt, + bool inner) +{ + struct mlx5e_tir **tir_p; + struct mlx5e_tir *tir; + + tir_p = rss_get_tirp(rss, tt, inner); + if (!*tir_p) + return; + + tir = *tir_p; + mlx5e_tir_destroy(tir); + kvfree(tir); + *tir_p = NULL; +} + +static int mlx5e_rss_create_tirs(struct mlx5e_rss *rss, + const struct mlx5e_lro_param *init_lro_param, + bool inner) +{ + enum mlx5_traffic_types tt, max_tt; + int err; + + for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) { + err = mlx5e_rss_create_tir(rss, tt, init_lro_param, inner); + if (err) + goto err_destroy_tirs; + } + + return 0; + +err_destroy_tirs: + max_tt = tt; + for (tt = 0; tt < max_tt; tt++) + mlx5e_rss_destroy_tir(rss, tt, inner); + return err; +} + +static void mlx5e_rss_destroy_tirs(struct mlx5e_rss *rss, bool inner) +{ + enum mlx5_traffic_types tt; + + for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) + mlx5e_rss_destroy_tir(rss, tt, inner); +} + +static int mlx5e_rss_update_tir(struct mlx5e_rss *rss, enum mlx5_traffic_types tt, + bool inner) +{ + struct mlx5e_rss_params_traffic_type rss_tt; + struct mlx5e_tir_builder *builder; + struct mlx5e_tir *tir; + int err; + + tir = rss_get_tir(rss, tt, inner); + if (!tir) + return 0; + + builder = mlx5e_tir_builder_alloc(true); + if (!builder) + return -ENOMEM; + + rss_tt = mlx5e_rss_get_tt_config(rss, tt); + + mlx5e_tir_builder_build_rss(builder, &rss->hash, &rss_tt, inner); + err = mlx5e_tir_modify(tir, builder); + + mlx5e_tir_builder_free(builder); + return err; +} + +static int mlx5e_rss_update_tirs(struct mlx5e_rss *rss) +{ + enum mlx5_traffic_types tt; + int err, retval; + + retval = 0; + + for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) { + err = mlx5e_rss_update_tir(rss, tt, false); + if (err) { + retval = retval ? : err; + mlx5e_rss_warn(rss->mdev, + "Failed to update RSS hash of indirect TIR for traffic type %d: err = %d\n", + tt, err); + } + + if (!rss->inner_ft_support) + continue; + + err = mlx5e_rss_update_tir(rss, tt, true); + if (err) { + retval = retval ? : err; + mlx5e_rss_warn(rss->mdev, + "Failed to update RSS hash of inner indirect TIR for traffic type %d: err = %d\n", + tt, err); + } + } + return retval; +} + +int mlx5e_rss_init_no_tirs(struct mlx5e_rss *rss, struct mlx5_core_dev *mdev, + bool inner_ft_support, u32 drop_rqn) +{ + rss->mdev = mdev; + rss->inner_ft_support = inner_ft_support; + rss->drop_rqn = drop_rqn; + + mlx5e_rss_params_init(rss); + refcount_set(&rss->refcnt, 1); + + return mlx5e_rqt_init_direct(&rss->rqt, mdev, true, drop_rqn); +} + +int mlx5e_rss_init(struct mlx5e_rss *rss, struct mlx5_core_dev *mdev, + bool inner_ft_support, u32 drop_rqn, + const struct mlx5e_lro_param *init_lro_param) +{ + int err; + + err = mlx5e_rss_init_no_tirs(rss, mdev, inner_ft_support, drop_rqn); + if (err) + goto err_out; + + err = mlx5e_rss_create_tirs(rss, init_lro_param, false); + if (err) + goto err_destroy_rqt; + + if (inner_ft_support) { + err = mlx5e_rss_create_tirs(rss, init_lro_param, true); + if (err) + goto err_destroy_tirs; + } + + return 0; + +err_destroy_tirs: + mlx5e_rss_destroy_tirs(rss, false); +err_destroy_rqt: + mlx5e_rqt_destroy(&rss->rqt); +err_out: + return err; +} + +int mlx5e_rss_cleanup(struct mlx5e_rss *rss) +{ + if (!refcount_dec_if_one(&rss->refcnt)) + return -EBUSY; + + mlx5e_rss_destroy_tirs(rss, false); + + if (rss->inner_ft_support) + mlx5e_rss_destroy_tirs(rss, true); + + mlx5e_rqt_destroy(&rss->rqt); + + return 0; +} + +void mlx5e_rss_refcnt_inc(struct mlx5e_rss *rss) +{ + refcount_inc(&rss->refcnt); +} + +void mlx5e_rss_refcnt_dec(struct mlx5e_rss *rss) +{ + refcount_dec(&rss->refcnt); +} + +unsigned int mlx5e_rss_refcnt_read(struct mlx5e_rss *rss) +{ + return refcount_read(&rss->refcnt); +} + +u32 mlx5e_rss_get_tirn(struct mlx5e_rss *rss, enum mlx5_traffic_types tt, + bool inner) +{ + struct mlx5e_tir *tir; + + WARN_ON(inner && !rss->inner_ft_support); + tir = rss_get_tir(rss, tt, inner); + WARN_ON(!tir); + + return mlx5e_tir_get_tirn(tir); +} + +/* Fill the "tirn" output parameter. + * Create the requested TIR if it's its first usage. + */ +int mlx5e_rss_obtain_tirn(struct mlx5e_rss *rss, + enum mlx5_traffic_types tt, + const struct mlx5e_lro_param *init_lro_param, + bool inner, u32 *tirn) +{ + struct mlx5e_tir *tir; + + tir = rss_get_tir(rss, tt, inner); + if (!tir) { /* TIR doesn't exist, create one */ + int err; + + err = mlx5e_rss_create_tir(rss, tt, init_lro_param, inner); + if (err) + return err; + tir = rss_get_tir(rss, tt, inner); + } + + *tirn = mlx5e_tir_get_tirn(tir); + return 0; +} + +static void mlx5e_rss_apply(struct mlx5e_rss *rss, u32 *rqns, unsigned int num_rqns) +{ + int err; + + err = mlx5e_rqt_redirect_indir(&rss->rqt, rqns, num_rqns, rss->hash.hfunc, &rss->indir); + if (err) + mlx5e_rss_warn(rss->mdev, "Failed to redirect RQT %#x to channels: err = %d\n", + mlx5e_rqt_get_rqtn(&rss->rqt), err); +} + +void mlx5e_rss_enable(struct mlx5e_rss *rss, u32 *rqns, unsigned int num_rqns) +{ + rss->enabled = true; + mlx5e_rss_apply(rss, rqns, num_rqns); +} + +void mlx5e_rss_disable(struct mlx5e_rss *rss) +{ + int err; + + rss->enabled = false; + err = mlx5e_rqt_redirect_direct(&rss->rqt, rss->drop_rqn); + if (err) + mlx5e_rss_warn(rss->mdev, "Failed to redirect RQT %#x to drop RQ %#x: err = %d\n", + mlx5e_rqt_get_rqtn(&rss->rqt), rss->drop_rqn, err); +} + +int mlx5e_rss_lro_set_param(struct mlx5e_rss *rss, struct mlx5e_lro_param *lro_param) +{ + struct mlx5e_tir_builder *builder; + enum mlx5_traffic_types tt; + int err, final_err; + + builder = mlx5e_tir_builder_alloc(true); + if (!builder) + return -ENOMEM; + + mlx5e_tir_builder_build_lro(builder, lro_param); + + final_err = 0; + + for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) { + struct mlx5e_tir *tir; + + tir = rss_get_tir(rss, tt, false); + if (!tir) + goto inner_tir; + err = mlx5e_tir_modify(tir, builder); + if (err) { + mlx5e_rss_warn(rss->mdev, "Failed to update LRO state of indirect TIR %#x for traffic type %d: err = %d\n", + mlx5e_tir_get_tirn(tir), tt, err); + if (!final_err) + final_err = err; + } + +inner_tir: + if (!rss->inner_ft_support) + continue; + + tir = rss_get_tir(rss, tt, true); + if (!tir) + continue; + err = mlx5e_tir_modify(tir, builder); + if (err) { + mlx5e_rss_warn(rss->mdev, "Failed to update LRO state of inner indirect TIR %#x for traffic type %d: err = %d\n", + mlx5e_tir_get_tirn(tir), tt, err); + if (!final_err) + final_err = err; + } + } + + mlx5e_tir_builder_free(builder); + return final_err; +} + +int mlx5e_rss_get_rxfh(struct mlx5e_rss *rss, u32 *indir, u8 *key, u8 *hfunc) +{ + unsigned int i; + + if (indir) + for (i = 0; i < MLX5E_INDIR_RQT_SIZE; i++) + indir[i] = rss->indir.table[i]; + + if (key) + memcpy(key, rss->hash.toeplitz_hash_key, + sizeof(rss->hash.toeplitz_hash_key)); + + if (hfunc) + *hfunc = rss->hash.hfunc; + + return 0; +} + +int mlx5e_rss_set_rxfh(struct mlx5e_rss *rss, const u32 *indir, + const u8 *key, const u8 *hfunc, + u32 *rqns, unsigned int num_rqns) +{ + bool changed_indir = false; + bool changed_hash = false; + + if (hfunc && *hfunc != rss->hash.hfunc) { + switch (*hfunc) { + case ETH_RSS_HASH_XOR: + case ETH_RSS_HASH_TOP: + break; + default: + return -EINVAL; + } + changed_hash = true; + changed_indir = true; + rss->hash.hfunc = *hfunc; + } + + if (key) { + if (rss->hash.hfunc == ETH_RSS_HASH_TOP) + changed_hash = true; + memcpy(rss->hash.toeplitz_hash_key, key, + sizeof(rss->hash.toeplitz_hash_key)); + } + + if (indir) { + unsigned int i; + + changed_indir = true; + + for (i = 0; i < MLX5E_INDIR_RQT_SIZE; i++) + rss->indir.table[i] = indir[i]; + } + + if (changed_indir && rss->enabled) + mlx5e_rss_apply(rss, rqns, num_rqns); + + if (changed_hash) + mlx5e_rss_update_tirs(rss); + + return 0; +} + +struct mlx5e_rss_params_hash mlx5e_rss_get_hash(struct mlx5e_rss *rss) +{ + return rss->hash; +} + +u8 mlx5e_rss_get_hash_fields(struct mlx5e_rss *rss, enum mlx5_traffic_types tt) +{ + return rss->rx_hash_fields[tt]; +} + +int mlx5e_rss_set_hash_fields(struct mlx5e_rss *rss, enum mlx5_traffic_types tt, + u8 rx_hash_fields) +{ + u8 old_rx_hash_fields; + int err; + + old_rx_hash_fields = rss->rx_hash_fields[tt]; + + if (old_rx_hash_fields == rx_hash_fields) + return 0; + + rss->rx_hash_fields[tt] = rx_hash_fields; + + err = mlx5e_rss_update_tir(rss, tt, false); + if (err) { + rss->rx_hash_fields[tt] = old_rx_hash_fields; + mlx5e_rss_warn(rss->mdev, + "Failed to update RSS hash fields of indirect TIR for traffic type %d: err = %d\n", + tt, err); + return err; + } + + if (!(rss->inner_ft_support)) + return 0; + + err = mlx5e_rss_update_tir(rss, tt, true); + if (err) { + /* Partial update happened. Try to revert - it may fail too, but + * there is nothing more we can do. + */ + rss->rx_hash_fields[tt] = old_rx_hash_fields; + mlx5e_rss_warn(rss->mdev, + "Failed to update RSS hash fields of inner indirect TIR for traffic type %d: err = %d\n", + tt, err); + if (mlx5e_rss_update_tir(rss, tt, false)) + mlx5e_rss_warn(rss->mdev, + "Partial update of RSS hash fields happened: failed to revert indirect TIR for traffic type %d to the old values\n", + tt); + } + + return err; +} + +void mlx5e_rss_set_indir_uniform(struct mlx5e_rss *rss, unsigned int nch) +{ + mlx5e_rss_params_indir_init_uniform(&rss->indir, nch); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h new file mode 100644 index 000000000000..d522a10dadf3 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h @@ -0,0 +1,49 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. */ + +#ifndef __MLX5_EN_RSS_H__ +#define __MLX5_EN_RSS_H__ + +#include "rqt.h" +#include "tir.h" +#include "fs.h" + +struct mlx5e_rss_params_traffic_type +mlx5e_rss_get_default_tt_config(enum mlx5_traffic_types tt); + +struct mlx5e_rss; + +struct mlx5e_rss *mlx5e_rss_alloc(void); +void mlx5e_rss_free(struct mlx5e_rss *rss); +int mlx5e_rss_init(struct mlx5e_rss *rss, struct mlx5_core_dev *mdev, + bool inner_ft_support, u32 drop_rqn, + const struct mlx5e_lro_param *init_lro_param); +int mlx5e_rss_init_no_tirs(struct mlx5e_rss *rss, struct mlx5_core_dev *mdev, + bool inner_ft_support, u32 drop_rqn); +int mlx5e_rss_cleanup(struct mlx5e_rss *rss); + +void mlx5e_rss_refcnt_inc(struct mlx5e_rss *rss); +void mlx5e_rss_refcnt_dec(struct mlx5e_rss *rss); +unsigned int mlx5e_rss_refcnt_read(struct mlx5e_rss *rss); + +u32 mlx5e_rss_get_tirn(struct mlx5e_rss *rss, enum mlx5_traffic_types tt, + bool inner); +int mlx5e_rss_obtain_tirn(struct mlx5e_rss *rss, + enum mlx5_traffic_types tt, + const struct mlx5e_lro_param *init_lro_param, + bool inner, u32 *tirn); + +void mlx5e_rss_enable(struct mlx5e_rss *rss, u32 *rqns, unsigned int num_rqns); +void mlx5e_rss_disable(struct mlx5e_rss *rss); + +int mlx5e_rss_lro_set_param(struct mlx5e_rss *rss, struct mlx5e_lro_param *lro_param); +int mlx5e_rss_get_rxfh(struct mlx5e_rss *rss, u32 *indir, u8 *key, u8 *hfunc); +int mlx5e_rss_set_rxfh(struct mlx5e_rss *rss, const u32 *indir, + const u8 *key, const u8 *hfunc, + u32 *rqns, unsigned int num_rqns); +struct mlx5e_rss_params_hash mlx5e_rss_get_hash(struct mlx5e_rss *rss); +u8 mlx5e_rss_get_hash_fields(struct mlx5e_rss *rss, enum mlx5_traffic_types tt); +int mlx5e_rss_set_hash_fields(struct mlx5e_rss *rss, enum mlx5_traffic_types tt, + u8 rx_hash_fields); +void mlx5e_rss_set_indir_uniform(struct mlx5e_rss *rss, unsigned int nch); +#endif /* __MLX5_EN_RSS_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c new file mode 100644 index 000000000000..bf0313e2682b --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c @@ -0,0 +1,690 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2021, Mellanox Technologies inc. All rights reserved. */ + +#include "rx_res.h" +#include "channels.h" +#include "params.h" + +#define MLX5E_MAX_NUM_RSS 16 + +struct mlx5e_rx_res { + struct mlx5_core_dev *mdev; + enum mlx5e_rx_res_features features; + unsigned int max_nch; + u32 drop_rqn; + + struct mlx5e_rss *rss[MLX5E_MAX_NUM_RSS]; + bool rss_active; + u32 rss_rqns[MLX5E_INDIR_RQT_SIZE]; + unsigned int rss_nch; + + struct { + struct mlx5e_rqt direct_rqt; + struct mlx5e_tir direct_tir; + struct mlx5e_rqt xsk_rqt; + struct mlx5e_tir xsk_tir; + } *channels; + + struct { + struct mlx5e_rqt rqt; + struct mlx5e_tir tir; + } ptp; +}; + +/* API for rx_res_rss_* */ + +static int mlx5e_rx_res_rss_init_def(struct mlx5e_rx_res *res, + const struct mlx5e_lro_param *init_lro_param, + unsigned int init_nch) +{ + bool inner_ft_support = res->features & MLX5E_RX_RES_FEATURE_INNER_FT; + struct mlx5e_rss *rss; + int err; + + if (WARN_ON(res->rss[0])) + return -EINVAL; + + rss = mlx5e_rss_alloc(); + if (!rss) + return -ENOMEM; + + err = mlx5e_rss_init(rss, res->mdev, inner_ft_support, res->drop_rqn, + init_lro_param); + if (err) + goto err_rss_free; + + mlx5e_rss_set_indir_uniform(rss, init_nch); + + res->rss[0] = rss; + + return 0; + +err_rss_free: + mlx5e_rss_free(rss); + return err; +} + +int mlx5e_rx_res_rss_init(struct mlx5e_rx_res *res, u32 *rss_idx, unsigned int init_nch) +{ + bool inner_ft_support = res->features & MLX5E_RX_RES_FEATURE_INNER_FT; + struct mlx5e_rss *rss; + int err, i; + + for (i = 1; i < MLX5E_MAX_NUM_RSS; i++) + if (!res->rss[i]) + break; + + if (i == MLX5E_MAX_NUM_RSS) + return -ENOSPC; + + rss = mlx5e_rss_alloc(); + if (!rss) + return -ENOMEM; + + err = mlx5e_rss_init_no_tirs(rss, res->mdev, inner_ft_support, res->drop_rqn); + if (err) + goto err_rss_free; + + mlx5e_rss_set_indir_uniform(rss, init_nch); + if (res->rss_active) + mlx5e_rss_enable(rss, res->rss_rqns, res->rss_nch); + + res->rss[i] = rss; + *rss_idx = i; + + return 0; + +err_rss_free: + mlx5e_rss_free(rss); + return err; +} + +static int __mlx5e_rx_res_rss_destroy(struct mlx5e_rx_res *res, u32 rss_idx) +{ + struct mlx5e_rss *rss = res->rss[rss_idx]; + int err; + + err = mlx5e_rss_cleanup(rss); + if (err) + return err; + + mlx5e_rss_free(rss); + res->rss[rss_idx] = NULL; + + return 0; +} + +int mlx5e_rx_res_rss_destroy(struct mlx5e_rx_res *res, u32 rss_idx) +{ + struct mlx5e_rss *rss; + + if (rss_idx >= MLX5E_MAX_NUM_RSS) + return -EINVAL; + + rss = res->rss[rss_idx]; + if (!rss) + return -EINVAL; + + return __mlx5e_rx_res_rss_destroy(res, rss_idx); +} + +static void mlx5e_rx_res_rss_destroy_all(struct mlx5e_rx_res *res) +{ + int i; + + for (i = 0; i < MLX5E_MAX_NUM_RSS; i++) { + struct mlx5e_rss *rss = res->rss[i]; + int err; + + if (!rss) + continue; + + err = __mlx5e_rx_res_rss_destroy(res, i); + if (err) { + unsigned int refcount; + + refcount = mlx5e_rss_refcnt_read(rss); + mlx5_core_warn(res->mdev, + "Failed to destroy RSS context %d, refcount = %u, err = %d\n", + i, refcount, err); + } + } +} + +static void mlx5e_rx_res_rss_enable(struct mlx5e_rx_res *res) +{ + int i; + + res->rss_active = true; + + for (i = 0; i < MLX5E_MAX_NUM_RSS; i++) { + struct mlx5e_rss *rss = res->rss[i]; + + if (!rss) + continue; + mlx5e_rss_enable(rss, res->rss_rqns, res->rss_nch); + } +} + +static void mlx5e_rx_res_rss_disable(struct mlx5e_rx_res *res) +{ + int i; + + res->rss_active = false; + + for (i = 0; i < MLX5E_MAX_NUM_RSS; i++) { + struct mlx5e_rss *rss = res->rss[i]; + + if (!rss) + continue; + mlx5e_rss_disable(rss); + } +} + +/* Updates the indirection table SW shadow, does not update the HW resources yet */ +void mlx5e_rx_res_rss_set_indir_uniform(struct mlx5e_rx_res *res, unsigned int nch) +{ + WARN_ON_ONCE(res->rss_active); + mlx5e_rss_set_indir_uniform(res->rss[0], nch); +} + +int mlx5e_rx_res_rss_get_rxfh(struct mlx5e_rx_res *res, u32 rss_idx, + u32 *indir, u8 *key, u8 *hfunc) +{ + struct mlx5e_rss *rss; + + if (rss_idx >= MLX5E_MAX_NUM_RSS) + return -EINVAL; + + rss = res->rss[rss_idx]; + if (!rss) + return -ENOENT; + + return mlx5e_rss_get_rxfh(rss, indir, key, hfunc); +} + +int mlx5e_rx_res_rss_set_rxfh(struct mlx5e_rx_res *res, u32 rss_idx, + const u32 *indir, const u8 *key, const u8 *hfunc) +{ + struct mlx5e_rss *rss; + + if (rss_idx >= MLX5E_MAX_NUM_RSS) + return -EINVAL; + + rss = res->rss[rss_idx]; + if (!rss) + return -ENOENT; + + return mlx5e_rss_set_rxfh(rss, indir, key, hfunc, res->rss_rqns, res->rss_nch); +} + +u8 mlx5e_rx_res_rss_get_hash_fields(struct mlx5e_rx_res *res, enum mlx5_traffic_types tt) +{ + struct mlx5e_rss *rss = res->rss[0]; + + return mlx5e_rss_get_hash_fields(rss, tt); +} + +int mlx5e_rx_res_rss_set_hash_fields(struct mlx5e_rx_res *res, enum mlx5_traffic_types tt, + u8 rx_hash_fields) +{ + struct mlx5e_rss *rss = res->rss[0]; + + return mlx5e_rss_set_hash_fields(rss, tt, rx_hash_fields); +} + +int mlx5e_rx_res_rss_cnt(struct mlx5e_rx_res *res) +{ + int i, cnt; + + cnt = 0; + for (i = 0; i < MLX5E_MAX_NUM_RSS; i++) + if (res->rss[i]) + cnt++; + + return cnt; +} + +int mlx5e_rx_res_rss_index(struct mlx5e_rx_res *res, struct mlx5e_rss *rss) +{ + int i; + + if (!rss) + return -EINVAL; + + for (i = 0; i < MLX5E_MAX_NUM_RSS; i++) + if (rss == res->rss[i]) + return i; + + return -ENOENT; +} + +struct mlx5e_rss *mlx5e_rx_res_rss_get(struct mlx5e_rx_res *res, u32 rss_idx) +{ + if (rss_idx >= MLX5E_MAX_NUM_RSS) + return NULL; + + return res->rss[rss_idx]; +} + +/* End of API rx_res_rss_* */ + +struct mlx5e_rx_res *mlx5e_rx_res_alloc(void) +{ + return kvzalloc(sizeof(struct mlx5e_rx_res), GFP_KERNEL); +} + +static int mlx5e_rx_res_channels_init(struct mlx5e_rx_res *res, + const struct mlx5e_lro_param *init_lro_param) +{ + bool inner_ft_support = res->features & MLX5E_RX_RES_FEATURE_INNER_FT; + struct mlx5e_tir_builder *builder; + int err = 0; + int ix; + + builder = mlx5e_tir_builder_alloc(false); + if (!builder) + return -ENOMEM; + + res->channels = kvcalloc(res->max_nch, sizeof(*res->channels), GFP_KERNEL); + if (!res->channels) { + err = -ENOMEM; + goto out; + } + + for (ix = 0; ix < res->max_nch; ix++) { + err = mlx5e_rqt_init_direct(&res->channels[ix].direct_rqt, + res->mdev, false, res->drop_rqn); + if (err) { + mlx5_core_warn(res->mdev, "Failed to create a direct RQT: err = %d, ix = %u\n", + err, ix); + goto err_destroy_direct_rqts; + } + } + + for (ix = 0; ix < res->max_nch; ix++) { + mlx5e_tir_builder_build_rqt(builder, res->mdev->mlx5e_res.hw_objs.td.tdn, + mlx5e_rqt_get_rqtn(&res->channels[ix].direct_rqt), + inner_ft_support); + mlx5e_tir_builder_build_lro(builder, init_lro_param); + mlx5e_tir_builder_build_direct(builder); + + err = mlx5e_tir_init(&res->channels[ix].direct_tir, builder, res->mdev, true); + if (err) { + mlx5_core_warn(res->mdev, "Failed to create a direct TIR: err = %d, ix = %u\n", + err, ix); + goto err_destroy_direct_tirs; + } + + mlx5e_tir_builder_clear(builder); + } + + if (!(res->features & MLX5E_RX_RES_FEATURE_XSK)) + goto out; + + for (ix = 0; ix < res->max_nch; ix++) { + err = mlx5e_rqt_init_direct(&res->channels[ix].xsk_rqt, + res->mdev, false, res->drop_rqn); + if (err) { + mlx5_core_warn(res->mdev, "Failed to create an XSK RQT: err = %d, ix = %u\n", + err, ix); + goto err_destroy_xsk_rqts; + } + } + + for (ix = 0; ix < res->max_nch; ix++) { + mlx5e_tir_builder_build_rqt(builder, res->mdev->mlx5e_res.hw_objs.td.tdn, + mlx5e_rqt_get_rqtn(&res->channels[ix].xsk_rqt), + inner_ft_support); + mlx5e_tir_builder_build_lro(builder, init_lro_param); + mlx5e_tir_builder_build_direct(builder); + + err = mlx5e_tir_init(&res->channels[ix].xsk_tir, builder, res->mdev, true); + if (err) { + mlx5_core_warn(res->mdev, "Failed to create an XSK TIR: err = %d, ix = %u\n", + err, ix); + goto err_destroy_xsk_tirs; + } + + mlx5e_tir_builder_clear(builder); + } + + goto out; + +err_destroy_xsk_tirs: + while (--ix >= 0) + mlx5e_tir_destroy(&res->channels[ix].xsk_tir); + + ix = res->max_nch; +err_destroy_xsk_rqts: + while (--ix >= 0) + mlx5e_rqt_destroy(&res->channels[ix].xsk_rqt); + + ix = res->max_nch; +err_destroy_direct_tirs: + while (--ix >= 0) + mlx5e_tir_destroy(&res->channels[ix].direct_tir); + + ix = res->max_nch; +err_destroy_direct_rqts: + while (--ix >= 0) + mlx5e_rqt_destroy(&res->channels[ix].direct_rqt); + + kvfree(res->channels); + +out: + mlx5e_tir_builder_free(builder); + + return err; +} + +static int mlx5e_rx_res_ptp_init(struct mlx5e_rx_res *res) +{ + bool inner_ft_support = res->features & MLX5E_RX_RES_FEATURE_INNER_FT; + struct mlx5e_tir_builder *builder; + int err; + + builder = mlx5e_tir_builder_alloc(false); + if (!builder) + return -ENOMEM; + + err = mlx5e_rqt_init_direct(&res->ptp.rqt, res->mdev, false, res->drop_rqn); + if (err) + goto out; + + mlx5e_tir_builder_build_rqt(builder, res->mdev->mlx5e_res.hw_objs.td.tdn, + mlx5e_rqt_get_rqtn(&res->ptp.rqt), + inner_ft_support); + mlx5e_tir_builder_build_direct(builder); + + err = mlx5e_tir_init(&res->ptp.tir, builder, res->mdev, true); + if (err) + goto err_destroy_ptp_rqt; + + goto out; + +err_destroy_ptp_rqt: + mlx5e_rqt_destroy(&res->ptp.rqt); + +out: + mlx5e_tir_builder_free(builder); + return err; +} + +static void mlx5e_rx_res_channels_destroy(struct mlx5e_rx_res *res) +{ + unsigned int ix; + + for (ix = 0; ix < res->max_nch; ix++) { + mlx5e_tir_destroy(&res->channels[ix].direct_tir); + mlx5e_rqt_destroy(&res->channels[ix].direct_rqt); + + if (!(res->features & MLX5E_RX_RES_FEATURE_XSK)) + continue; + + mlx5e_tir_destroy(&res->channels[ix].xsk_tir); + mlx5e_rqt_destroy(&res->channels[ix].xsk_rqt); + } + + kvfree(res->channels); +} + +static void mlx5e_rx_res_ptp_destroy(struct mlx5e_rx_res *res) +{ + mlx5e_tir_destroy(&res->ptp.tir); + mlx5e_rqt_destroy(&res->ptp.rqt); +} + +int mlx5e_rx_res_init(struct mlx5e_rx_res *res, struct mlx5_core_dev *mdev, + enum mlx5e_rx_res_features features, unsigned int max_nch, + u32 drop_rqn, const struct mlx5e_lro_param *init_lro_param, + unsigned int init_nch) +{ + int err; + + res->mdev = mdev; + res->features = features; + res->max_nch = max_nch; + res->drop_rqn = drop_rqn; + + err = mlx5e_rx_res_rss_init_def(res, init_lro_param, init_nch); + if (err) + goto err_out; + + err = mlx5e_rx_res_channels_init(res, init_lro_param); + if (err) + goto err_rss_destroy; + + err = mlx5e_rx_res_ptp_init(res); + if (err) + goto err_channels_destroy; + + return 0; + +err_channels_destroy: + mlx5e_rx_res_channels_destroy(res); +err_rss_destroy: + __mlx5e_rx_res_rss_destroy(res, 0); +err_out: + return err; +} + +void mlx5e_rx_res_destroy(struct mlx5e_rx_res *res) +{ + mlx5e_rx_res_ptp_destroy(res); + mlx5e_rx_res_channels_destroy(res); + mlx5e_rx_res_rss_destroy_all(res); +} + +void mlx5e_rx_res_free(struct mlx5e_rx_res *res) +{ + kvfree(res); +} + +u32 mlx5e_rx_res_get_tirn_direct(struct mlx5e_rx_res *res, unsigned int ix) +{ + return mlx5e_tir_get_tirn(&res->channels[ix].direct_tir); +} + +u32 mlx5e_rx_res_get_tirn_xsk(struct mlx5e_rx_res *res, unsigned int ix) +{ + WARN_ON(!(res->features & MLX5E_RX_RES_FEATURE_XSK)); + + return mlx5e_tir_get_tirn(&res->channels[ix].xsk_tir); +} + +u32 mlx5e_rx_res_get_tirn_rss(struct mlx5e_rx_res *res, enum mlx5_traffic_types tt) +{ + struct mlx5e_rss *rss = res->rss[0]; + + return mlx5e_rss_get_tirn(rss, tt, false); +} + +u32 mlx5e_rx_res_get_tirn_rss_inner(struct mlx5e_rx_res *res, enum mlx5_traffic_types tt) +{ + struct mlx5e_rss *rss = res->rss[0]; + + return mlx5e_rss_get_tirn(rss, tt, true); +} + +u32 mlx5e_rx_res_get_tirn_ptp(struct mlx5e_rx_res *res) +{ + WARN_ON(!(res->features & MLX5E_RX_RES_FEATURE_PTP)); + return mlx5e_tir_get_tirn(&res->ptp.tir); +} + +u32 mlx5e_rx_res_get_rqtn_direct(struct mlx5e_rx_res *res, unsigned int ix) +{ + return mlx5e_rqt_get_rqtn(&res->channels[ix].direct_rqt); +} + +void mlx5e_rx_res_channels_activate(struct mlx5e_rx_res *res, struct mlx5e_channels *chs) +{ + unsigned int nch, ix; + int err; + + nch = mlx5e_channels_get_num(chs); + + for (ix = 0; ix < chs->num; ix++) + mlx5e_channels_get_regular_rqn(chs, ix, &res->rss_rqns[ix]); + res->rss_nch = chs->num; + + mlx5e_rx_res_rss_enable(res); + + for (ix = 0; ix < nch; ix++) { + u32 rqn; + + mlx5e_channels_get_regular_rqn(chs, ix, &rqn); + err = mlx5e_rqt_redirect_direct(&res->channels[ix].direct_rqt, rqn); + if (err) + mlx5_core_warn(res->mdev, "Failed to redirect direct RQT %#x to RQ %#x (channel %u): err = %d\n", + mlx5e_rqt_get_rqtn(&res->channels[ix].direct_rqt), + rqn, ix, err); + + if (!(res->features & MLX5E_RX_RES_FEATURE_XSK)) + continue; + + if (!mlx5e_channels_get_xsk_rqn(chs, ix, &rqn)) + rqn = res->drop_rqn; + err = mlx5e_rqt_redirect_direct(&res->channels[ix].xsk_rqt, rqn); + if (err) + mlx5_core_warn(res->mdev, "Failed to redirect XSK RQT %#x to RQ %#x (channel %u): err = %d\n", + mlx5e_rqt_get_rqtn(&res->channels[ix].xsk_rqt), + rqn, ix, err); + } + for (ix = nch; ix < res->max_nch; ix++) { + err = mlx5e_rqt_redirect_direct(&res->channels[ix].direct_rqt, res->drop_rqn); + if (err) + mlx5_core_warn(res->mdev, "Failed to redirect direct RQT %#x to drop RQ %#x (channel %u): err = %d\n", + mlx5e_rqt_get_rqtn(&res->channels[ix].direct_rqt), + res->drop_rqn, ix, err); + + if (!(res->features & MLX5E_RX_RES_FEATURE_XSK)) + continue; + + err = mlx5e_rqt_redirect_direct(&res->channels[ix].xsk_rqt, res->drop_rqn); + if (err) + mlx5_core_warn(res->mdev, "Failed to redirect XSK RQT %#x to drop RQ %#x (channel %u): err = %d\n", + mlx5e_rqt_get_rqtn(&res->channels[ix].xsk_rqt), + res->drop_rqn, ix, err); + } + + if (res->features & MLX5E_RX_RES_FEATURE_PTP) { + u32 rqn; + + if (mlx5e_channels_get_ptp_rqn(chs, &rqn)) + rqn = res->drop_rqn; + + err = mlx5e_rqt_redirect_direct(&res->ptp.rqt, rqn); + if (err) + mlx5_core_warn(res->mdev, "Failed to redirect direct RQT %#x to RQ %#x (PTP): err = %d\n", + mlx5e_rqt_get_rqtn(&res->ptp.rqt), + rqn, err); + } +} + +void mlx5e_rx_res_channels_deactivate(struct mlx5e_rx_res *res) +{ + unsigned int ix; + int err; + + mlx5e_rx_res_rss_disable(res); + + for (ix = 0; ix < res->max_nch; ix++) { + err = mlx5e_rqt_redirect_direct(&res->channels[ix].direct_rqt, res->drop_rqn); + if (err) + mlx5_core_warn(res->mdev, "Failed to redirect direct RQT %#x to drop RQ %#x (channel %u): err = %d\n", + mlx5e_rqt_get_rqtn(&res->channels[ix].direct_rqt), + res->drop_rqn, ix, err); + + if (!(res->features & MLX5E_RX_RES_FEATURE_XSK)) + continue; + + err = mlx5e_rqt_redirect_direct(&res->channels[ix].xsk_rqt, res->drop_rqn); + if (err) + mlx5_core_warn(res->mdev, "Failed to redirect XSK RQT %#x to drop RQ %#x (channel %u): err = %d\n", + mlx5e_rqt_get_rqtn(&res->channels[ix].xsk_rqt), + res->drop_rqn, ix, err); + } + + if (res->features & MLX5E_RX_RES_FEATURE_PTP) { + err = mlx5e_rqt_redirect_direct(&res->ptp.rqt, res->drop_rqn); + if (err) + mlx5_core_warn(res->mdev, "Failed to redirect direct RQT %#x to drop RQ %#x (PTP): err = %d\n", + mlx5e_rqt_get_rqtn(&res->ptp.rqt), + res->drop_rqn, err); + } +} + +int mlx5e_rx_res_xsk_activate(struct mlx5e_rx_res *res, struct mlx5e_channels *chs, + unsigned int ix) +{ + u32 rqn; + int err; + + if (!mlx5e_channels_get_xsk_rqn(chs, ix, &rqn)) + return -EINVAL; + + err = mlx5e_rqt_redirect_direct(&res->channels[ix].xsk_rqt, rqn); + if (err) + mlx5_core_warn(res->mdev, "Failed to redirect XSK RQT %#x to XSK RQ %#x (channel %u): err = %d\n", + mlx5e_rqt_get_rqtn(&res->channels[ix].xsk_rqt), + rqn, ix, err); + return err; +} + +int mlx5e_rx_res_xsk_deactivate(struct mlx5e_rx_res *res, unsigned int ix) +{ + int err; + + err = mlx5e_rqt_redirect_direct(&res->channels[ix].xsk_rqt, res->drop_rqn); + if (err) + mlx5_core_warn(res->mdev, "Failed to redirect XSK RQT %#x to drop RQ %#x (channel %u): err = %d\n", + mlx5e_rqt_get_rqtn(&res->channels[ix].xsk_rqt), + res->drop_rqn, ix, err); + return err; +} + +int mlx5e_rx_res_lro_set_param(struct mlx5e_rx_res *res, struct mlx5e_lro_param *lro_param) +{ + struct mlx5e_tir_builder *builder; + int err, final_err; + unsigned int ix; + + builder = mlx5e_tir_builder_alloc(true); + if (!builder) + return -ENOMEM; + + mlx5e_tir_builder_build_lro(builder, lro_param); + + final_err = 0; + + for (ix = 0; ix < MLX5E_MAX_NUM_RSS; ix++) { + struct mlx5e_rss *rss = res->rss[ix]; + + if (!rss) + continue; + + err = mlx5e_rss_lro_set_param(rss, lro_param); + if (err) + final_err = final_err ? : err; + } + + for (ix = 0; ix < res->max_nch; ix++) { + err = mlx5e_tir_modify(&res->channels[ix].direct_tir, builder); + if (err) { + mlx5_core_warn(res->mdev, "Failed to update LRO state of direct TIR %#x for channel %u: err = %d\n", + mlx5e_tir_get_tirn(&res->channels[ix].direct_tir), ix, err); + if (!final_err) + final_err = err; + } + } + + mlx5e_tir_builder_free(builder); + return final_err; +} + +struct mlx5e_rss_params_hash mlx5e_rx_res_get_current_hash(struct mlx5e_rx_res *res) +{ + return mlx5e_rss_get_hash(res->rss[0]); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h new file mode 100644 index 000000000000..4a15942d79f7 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h @@ -0,0 +1,71 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2021, Mellanox Technologies inc. All rights reserved. */ + +#ifndef __MLX5_EN_RX_RES_H__ +#define __MLX5_EN_RX_RES_H__ + +#include <linux/kernel.h> +#include "rqt.h" +#include "tir.h" +#include "fs.h" +#include "rss.h" + +struct mlx5e_rx_res; + +struct mlx5e_channels; +struct mlx5e_rss_params_hash; + +enum mlx5e_rx_res_features { + MLX5E_RX_RES_FEATURE_INNER_FT = BIT(0), + MLX5E_RX_RES_FEATURE_XSK = BIT(1), + MLX5E_RX_RES_FEATURE_PTP = BIT(2), +}; + +/* Setup */ +struct mlx5e_rx_res *mlx5e_rx_res_alloc(void); +int mlx5e_rx_res_init(struct mlx5e_rx_res *res, struct mlx5_core_dev *mdev, + enum mlx5e_rx_res_features features, unsigned int max_nch, + u32 drop_rqn, const struct mlx5e_lro_param *init_lro_param, + unsigned int init_nch); +void mlx5e_rx_res_destroy(struct mlx5e_rx_res *res); +void mlx5e_rx_res_free(struct mlx5e_rx_res *res); + +/* TIRN getters for flow steering */ +u32 mlx5e_rx_res_get_tirn_direct(struct mlx5e_rx_res *res, unsigned int ix); +u32 mlx5e_rx_res_get_tirn_xsk(struct mlx5e_rx_res *res, unsigned int ix); +u32 mlx5e_rx_res_get_tirn_rss(struct mlx5e_rx_res *res, enum mlx5_traffic_types tt); +u32 mlx5e_rx_res_get_tirn_rss_inner(struct mlx5e_rx_res *res, enum mlx5_traffic_types tt); +u32 mlx5e_rx_res_get_tirn_ptp(struct mlx5e_rx_res *res); + +/* RQTN getters for modules that create their own TIRs */ +u32 mlx5e_rx_res_get_rqtn_direct(struct mlx5e_rx_res *res, unsigned int ix); + +/* Activate/deactivate API */ +void mlx5e_rx_res_channels_activate(struct mlx5e_rx_res *res, struct mlx5e_channels *chs); +void mlx5e_rx_res_channels_deactivate(struct mlx5e_rx_res *res); +int mlx5e_rx_res_xsk_activate(struct mlx5e_rx_res *res, struct mlx5e_channels *chs, + unsigned int ix); +int mlx5e_rx_res_xsk_deactivate(struct mlx5e_rx_res *res, unsigned int ix); + +/* Configuration API */ +void mlx5e_rx_res_rss_set_indir_uniform(struct mlx5e_rx_res *res, unsigned int nch); +int mlx5e_rx_res_rss_get_rxfh(struct mlx5e_rx_res *res, u32 rss_idx, + u32 *indir, u8 *key, u8 *hfunc); +int mlx5e_rx_res_rss_set_rxfh(struct mlx5e_rx_res *res, u32 rss_idx, + const u32 *indir, const u8 *key, const u8 *hfunc); + +u8 mlx5e_rx_res_rss_get_hash_fields(struct mlx5e_rx_res *res, enum mlx5_traffic_types tt); +int mlx5e_rx_res_rss_set_hash_fields(struct mlx5e_rx_res *res, enum mlx5_traffic_types tt, + u8 rx_hash_fields); +int mlx5e_rx_res_lro_set_param(struct mlx5e_rx_res *res, struct mlx5e_lro_param *lro_param); + +int mlx5e_rx_res_rss_init(struct mlx5e_rx_res *res, u32 *rss_idx, unsigned int init_nch); +int mlx5e_rx_res_rss_destroy(struct mlx5e_rx_res *res, u32 rss_idx); +int mlx5e_rx_res_rss_cnt(struct mlx5e_rx_res *res); +int mlx5e_rx_res_rss_index(struct mlx5e_rx_res *res, struct mlx5e_rss *rss); +struct mlx5e_rss *mlx5e_rx_res_rss_get(struct mlx5e_rx_res *res, u32 rss_idx); + +/* Workaround for hairpin */ +struct mlx5e_rss_params_hash mlx5e_rx_res_get_current_hash(struct mlx5e_rx_res *res); + +#endif /* __MLX5_EN_RX_RES_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c new file mode 100644 index 000000000000..a3e43e898a56 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c @@ -0,0 +1,164 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +// Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. + +#include "en_tc.h" +#include "post_act.h" +#include "mlx5_core.h" + +struct mlx5e_post_act { + enum mlx5_flow_namespace_type ns_type; + struct mlx5_fs_chains *chains; + struct mlx5_flow_table *ft; + struct mlx5e_priv *priv; + struct xarray ids; +}; + +struct mlx5e_post_act_handle { + enum mlx5_flow_namespace_type ns_type; + struct mlx5_flow_attr *attr; + struct mlx5_flow_handle *rule; + u32 id; +}; + +#define MLX5_POST_ACTION_BITS (mlx5e_tc_attr_to_reg_mappings[FTEID_TO_REG].mlen) +#define MLX5_POST_ACTION_MAX GENMASK(MLX5_POST_ACTION_BITS - 1, 0) +#define MLX5_POST_ACTION_MASK MLX5_POST_ACTION_MAX + +struct mlx5e_post_act * +mlx5e_tc_post_act_init(struct mlx5e_priv *priv, struct mlx5_fs_chains *chains, + enum mlx5_flow_namespace_type ns_type) +{ + struct mlx5e_post_act *post_act; + int err; + + if (ns_type == MLX5_FLOW_NAMESPACE_FDB && + !MLX5_CAP_ESW_FLOWTABLE_FDB(priv->mdev, ignore_flow_level)) { + mlx5_core_warn(priv->mdev, "firmware level support is missing\n"); + err = -EOPNOTSUPP; + goto err_check; + } else if (!MLX5_CAP_FLOWTABLE_NIC_RX(priv->mdev, ignore_flow_level)) { + mlx5_core_warn(priv->mdev, "firmware level support is missing\n"); + err = -EOPNOTSUPP; + goto err_check; + } + + post_act = kzalloc(sizeof(*post_act), GFP_KERNEL); + if (!post_act) { + err = -ENOMEM; + goto err_check; + } + post_act->ft = mlx5_chains_create_global_table(chains); + if (IS_ERR(post_act->ft)) { + err = PTR_ERR(post_act->ft); + mlx5_core_warn(priv->mdev, "failed to create post action table, err: %d\n", err); + goto err_ft; + } + post_act->chains = chains; + post_act->ns_type = ns_type; + post_act->priv = priv; + xa_init_flags(&post_act->ids, XA_FLAGS_ALLOC1); + return post_act; + +err_ft: + kfree(post_act); +err_check: + return ERR_PTR(err); +} + +void +mlx5e_tc_post_act_destroy(struct mlx5e_post_act *post_act) +{ + if (IS_ERR_OR_NULL(post_act)) + return; + + xa_destroy(&post_act->ids); + mlx5_chains_destroy_global_table(post_act->chains, post_act->ft); + kfree(post_act); +} + +struct mlx5e_post_act_handle * +mlx5e_tc_post_act_add(struct mlx5e_post_act *post_act, struct mlx5_flow_attr *attr) +{ + u32 attr_sz = ns_to_attr_sz(post_act->ns_type); + struct mlx5e_post_act_handle *handle = NULL; + struct mlx5_flow_attr *post_attr = NULL; + struct mlx5_flow_spec *spec = NULL; + int err; + + handle = kzalloc(sizeof(*handle), GFP_KERNEL); + spec = kvzalloc(sizeof(*spec), GFP_KERNEL); + post_attr = mlx5_alloc_flow_attr(post_act->ns_type); + if (!handle || !spec || !post_attr) { + kfree(post_attr); + kvfree(spec); + kfree(handle); + return ERR_PTR(-ENOMEM); + } + + memcpy(post_attr, attr, attr_sz); + post_attr->chain = 0; + post_attr->prio = 0; + post_attr->ft = post_act->ft; + post_attr->inner_match_level = MLX5_MATCH_NONE; + post_attr->outer_match_level = MLX5_MATCH_NONE; + post_attr->action &= ~(MLX5_FLOW_CONTEXT_ACTION_DECAP); + + handle->ns_type = post_act->ns_type; + /* Splits were handled before post action */ + if (handle->ns_type == MLX5_FLOW_NAMESPACE_FDB) + post_attr->esw_attr->split_count = 0; + + err = xa_alloc(&post_act->ids, &handle->id, post_attr, + XA_LIMIT(1, MLX5_POST_ACTION_MAX), GFP_KERNEL); + if (err) + goto err_xarray; + + /* Post action rule matches on fte_id and executes original rule's + * tc rule action + */ + mlx5e_tc_match_to_reg_match(spec, FTEID_TO_REG, + handle->id, MLX5_POST_ACTION_MASK); + + handle->rule = mlx5_tc_rule_insert(post_act->priv, spec, post_attr); + if (IS_ERR(handle->rule)) { + err = PTR_ERR(handle->rule); + netdev_warn(post_act->priv->netdev, "Failed to add post action rule"); + goto err_rule; + } + handle->attr = post_attr; + + kvfree(spec); + return handle; + +err_rule: + xa_erase(&post_act->ids, handle->id); +err_xarray: + kfree(post_attr); + kvfree(spec); + kfree(handle); + return ERR_PTR(err); +} + +void +mlx5e_tc_post_act_del(struct mlx5e_post_act *post_act, struct mlx5e_post_act_handle *handle) +{ + mlx5_tc_rule_delete(post_act->priv, handle->rule, handle->attr); + xa_erase(&post_act->ids, handle->id); + kfree(handle->attr); + kfree(handle); +} + +struct mlx5_flow_table * +mlx5e_tc_post_act_get_ft(struct mlx5e_post_act *post_act) +{ + return post_act->ft; +} + +/* Allocate a header modify action to write the post action handle fte id to a register. */ +int +mlx5e_tc_post_act_set_handle(struct mlx5_core_dev *dev, + struct mlx5e_post_act_handle *handle, + struct mlx5e_tc_mod_hdr_acts *acts) +{ + return mlx5e_tc_match_to_reg_set(dev, acts, handle->ns_type, FTEID_TO_REG, handle->id); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.h new file mode 100644 index 000000000000..b530ec1981a5 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */ + +#ifndef __MLX5_POST_ACTION_H__ +#define __MLX5_POST_ACTION_H__ + +#include "en.h" +#include "lib/fs_chains.h" + +struct mlx5_flow_attr; +struct mlx5e_priv; +struct mlx5e_tc_mod_hdr_acts; + +struct mlx5e_post_act * +mlx5e_tc_post_act_init(struct mlx5e_priv *priv, struct mlx5_fs_chains *chains, + enum mlx5_flow_namespace_type ns_type); + +void +mlx5e_tc_post_act_destroy(struct mlx5e_post_act *post_act); + +struct mlx5e_post_act_handle * +mlx5e_tc_post_act_add(struct mlx5e_post_act *post_act, struct mlx5_flow_attr *attr); + +void +mlx5e_tc_post_act_del(struct mlx5e_post_act *post_act, struct mlx5e_post_act_handle *handle); + +struct mlx5_flow_table * +mlx5e_tc_post_act_get_ft(struct mlx5e_post_act *post_act); + +int +mlx5e_tc_post_act_set_handle(struct mlx5_core_dev *dev, + struct mlx5e_post_act_handle *handle, + struct mlx5e_tc_mod_hdr_acts *acts); + +#endif /* __MLX5_POST_ACTION_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/sample.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c index d3ad78aa9d45..6552ecee3f9b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/sample.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c @@ -4,7 +4,8 @@ #include <linux/skbuff.h> #include <net/psample.h> #include "en/mapping.h" -#include "esw/sample.h" +#include "en/tc/post_act.h" +#include "sample.h" #include "eswitch.h" #include "en_tc.h" #include "fs_core.h" @@ -17,17 +18,18 @@ static const struct esw_vport_tbl_namespace mlx5_esw_vport_tbl_sample_ns = { .flags = MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT | MLX5_FLOW_TABLE_TUNNEL_EN_DECAP, }; -struct mlx5_esw_psample { - struct mlx5e_priv *priv; +struct mlx5e_tc_psample { + struct mlx5_eswitch *esw; struct mlx5_flow_table *termtbl; struct mlx5_flow_handle *termtbl_rule; DECLARE_HASHTABLE(hashtbl, 8); struct mutex ht_lock; /* protect hashtbl */ DECLARE_HASHTABLE(restore_hashtbl, 8); struct mutex restore_lock; /* protect restore_hashtbl */ + struct mlx5e_post_act *post_act; }; -struct mlx5_sampler { +struct mlx5e_sampler { struct hlist_node hlist; u32 sampler_id; u32 sample_ratio; @@ -36,29 +38,32 @@ struct mlx5_sampler { int count; }; -struct mlx5_sample_flow { - struct mlx5_sampler *sampler; - struct mlx5_sample_restore *restore; +struct mlx5e_sample_flow { + struct mlx5e_sampler *sampler; + struct mlx5e_sample_restore *restore; struct mlx5_flow_attr *pre_attr; struct mlx5_flow_handle *pre_rule; - struct mlx5_flow_handle *rule; + struct mlx5_flow_attr *post_attr; + struct mlx5_flow_handle *post_rule; + struct mlx5e_post_act_handle *post_act_handle; }; -struct mlx5_sample_restore { +struct mlx5e_sample_restore { struct hlist_node hlist; struct mlx5_modify_hdr *modify_hdr; struct mlx5_flow_handle *rule; + struct mlx5e_post_act_handle *post_act_handle; u32 obj_id; int count; }; static int -sampler_termtbl_create(struct mlx5_esw_psample *esw_psample) +sampler_termtbl_create(struct mlx5e_tc_psample *tc_psample) { - struct mlx5_core_dev *dev = esw_psample->priv->mdev; - struct mlx5_eswitch *esw = dev->priv.eswitch; + struct mlx5_eswitch *esw = tc_psample->esw; struct mlx5_flow_table_attr ft_attr = {}; struct mlx5_flow_destination dest = {}; + struct mlx5_core_dev *dev = esw->dev; struct mlx5_flow_namespace *root_ns; struct mlx5_flow_act act = {}; int err; @@ -79,20 +84,20 @@ sampler_termtbl_create(struct mlx5_esw_psample *esw_psample) ft_attr.prio = FDB_SLOW_PATH; ft_attr.max_fte = 1; ft_attr.level = 1; - esw_psample->termtbl = mlx5_create_auto_grouped_flow_table(root_ns, &ft_attr); - if (IS_ERR(esw_psample->termtbl)) { - err = PTR_ERR(esw_psample->termtbl); + tc_psample->termtbl = mlx5_create_auto_grouped_flow_table(root_ns, &ft_attr); + if (IS_ERR(tc_psample->termtbl)) { + err = PTR_ERR(tc_psample->termtbl); mlx5_core_warn(dev, "failed to create termtbl, err: %d\n", err); return err; } act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; dest.vport.num = esw->manager_vport; - esw_psample->termtbl_rule = mlx5_add_flow_rules(esw_psample->termtbl, NULL, &act, &dest, 1); - if (IS_ERR(esw_psample->termtbl_rule)) { - err = PTR_ERR(esw_psample->termtbl_rule); + tc_psample->termtbl_rule = mlx5_add_flow_rules(tc_psample->termtbl, NULL, &act, &dest, 1); + if (IS_ERR(tc_psample->termtbl_rule)) { + err = PTR_ERR(tc_psample->termtbl_rule); mlx5_core_warn(dev, "failed to create termtbl rule, err: %d\n", err); - mlx5_destroy_flow_table(esw_psample->termtbl); + mlx5_destroy_flow_table(tc_psample->termtbl); return err; } @@ -100,14 +105,14 @@ sampler_termtbl_create(struct mlx5_esw_psample *esw_psample) } static void -sampler_termtbl_destroy(struct mlx5_esw_psample *esw_psample) +sampler_termtbl_destroy(struct mlx5e_tc_psample *tc_psample) { - mlx5_del_flow_rules(esw_psample->termtbl_rule); - mlx5_destroy_flow_table(esw_psample->termtbl); + mlx5_del_flow_rules(tc_psample->termtbl_rule); + mlx5_destroy_flow_table(tc_psample->termtbl); } static int -sampler_obj_create(struct mlx5_core_dev *mdev, struct mlx5_sampler *sampler) +sampler_obj_create(struct mlx5_core_dev *mdev, struct mlx5e_sampler *sampler) { u32 in[MLX5_ST_SZ_DW(create_sampler_obj_in)] = {}; u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)]; @@ -163,16 +168,16 @@ sampler_cmp(u32 sample_ratio1, u32 default_table_id1, u32 sample_ratio2, u32 def return sample_ratio1 != sample_ratio2 || default_table_id1 != default_table_id2; } -static struct mlx5_sampler * -sampler_get(struct mlx5_esw_psample *esw_psample, u32 sample_ratio, u32 default_table_id) +static struct mlx5e_sampler * +sampler_get(struct mlx5e_tc_psample *tc_psample, u32 sample_ratio, u32 default_table_id) { - struct mlx5_sampler *sampler; + struct mlx5e_sampler *sampler; u32 hash_key; int err; - mutex_lock(&esw_psample->ht_lock); + mutex_lock(&tc_psample->ht_lock); hash_key = sampler_hash(sample_ratio, default_table_id); - hash_for_each_possible(esw_psample->hashtbl, sampler, hlist, hash_key) + hash_for_each_possible(tc_psample->hashtbl, sampler, hlist, hash_key) if (!sampler_cmp(sampler->sample_ratio, sampler->default_table_id, sample_ratio, default_table_id)) goto add_ref; @@ -183,42 +188,49 @@ sampler_get(struct mlx5_esw_psample *esw_psample, u32 sample_ratio, u32 default_ goto err_alloc; } - sampler->sample_table_id = esw_psample->termtbl->id; + sampler->sample_table_id = tc_psample->termtbl->id; sampler->default_table_id = default_table_id; sampler->sample_ratio = sample_ratio; - err = sampler_obj_create(esw_psample->priv->mdev, sampler); + err = sampler_obj_create(tc_psample->esw->dev, sampler); if (err) goto err_create; - hash_add(esw_psample->hashtbl, &sampler->hlist, hash_key); + hash_add(tc_psample->hashtbl, &sampler->hlist, hash_key); add_ref: sampler->count++; - mutex_unlock(&esw_psample->ht_lock); + mutex_unlock(&tc_psample->ht_lock); return sampler; err_create: kfree(sampler); err_alloc: - mutex_unlock(&esw_psample->ht_lock); + mutex_unlock(&tc_psample->ht_lock); return ERR_PTR(err); } static void -sampler_put(struct mlx5_esw_psample *esw_psample, struct mlx5_sampler *sampler) +sampler_put(struct mlx5e_tc_psample *tc_psample, struct mlx5e_sampler *sampler) { - mutex_lock(&esw_psample->ht_lock); + mutex_lock(&tc_psample->ht_lock); if (--sampler->count == 0) { hash_del(&sampler->hlist); - sampler_obj_destroy(esw_psample->priv->mdev, sampler->sampler_id); + sampler_obj_destroy(tc_psample->esw->dev, sampler->sampler_id); kfree(sampler); } - mutex_unlock(&esw_psample->ht_lock); + mutex_unlock(&tc_psample->ht_lock); } +/* obj_id is used to restore the sample parameters. + * Set fte_id in original flow table, then match it in the default table. + * Only set it for NICs can preserve reg_c or decap action. For other cases, + * use the same match in the default table. + * Use one header rewrite for both obj_id and fte_id. + */ static struct mlx5_modify_hdr * -sample_metadata_rule_get(struct mlx5_core_dev *mdev, u32 obj_id) +sample_modify_hdr_get(struct mlx5_core_dev *mdev, u32 obj_id, + struct mlx5e_post_act_handle *handle) { struct mlx5e_tc_mod_hdr_acts mod_acts = {}; struct mlx5_modify_hdr *modify_hdr; @@ -229,6 +241,12 @@ sample_metadata_rule_get(struct mlx5_core_dev *mdev, u32 obj_id) if (err) goto err_set_regc0; + if (handle) { + err = mlx5e_tc_post_act_set_handle(mdev, handle, &mod_acts); + if (err) + goto err_post_act; + } + modify_hdr = mlx5_modify_header_alloc(mdev, MLX5_FLOW_NAMESPACE_FDB, mod_acts.num_actions, mod_acts.actions); @@ -241,23 +259,40 @@ sample_metadata_rule_get(struct mlx5_core_dev *mdev, u32 obj_id) return modify_hdr; err_modify_hdr: +err_post_act: dealloc_mod_hdr_actions(&mod_acts); err_set_regc0: return ERR_PTR(err); } -static struct mlx5_sample_restore * -sample_restore_get(struct mlx5_esw_psample *esw_psample, u32 obj_id) +static u32 +restore_hash(u32 obj_id, struct mlx5e_post_act_handle *post_act_handle) { - struct mlx5_core_dev *mdev = esw_psample->priv->mdev; - struct mlx5_eswitch *esw = mdev->priv.eswitch; - struct mlx5_sample_restore *restore; + return jhash_2words(obj_id, hash32_ptr(post_act_handle), 0); +} + +static bool +restore_equal(struct mlx5e_sample_restore *restore, u32 obj_id, + struct mlx5e_post_act_handle *post_act_handle) +{ + return restore->obj_id == obj_id && restore->post_act_handle == post_act_handle; +} + +static struct mlx5e_sample_restore * +sample_restore_get(struct mlx5e_tc_psample *tc_psample, u32 obj_id, + struct mlx5e_post_act_handle *post_act_handle) +{ + struct mlx5_eswitch *esw = tc_psample->esw; + struct mlx5_core_dev *mdev = esw->dev; + struct mlx5e_sample_restore *restore; struct mlx5_modify_hdr *modify_hdr; + u32 hash_key; int err; - mutex_lock(&esw_psample->restore_lock); - hash_for_each_possible(esw_psample->restore_hashtbl, restore, hlist, obj_id) - if (restore->obj_id == obj_id) + mutex_lock(&tc_psample->restore_lock); + hash_key = restore_hash(obj_id, post_act_handle); + hash_for_each_possible(tc_psample->restore_hashtbl, restore, hlist, hash_key) + if (restore_equal(restore, obj_id, post_act_handle)) goto add_ref; restore = kzalloc(sizeof(*restore), GFP_KERNEL); @@ -266,8 +301,9 @@ sample_restore_get(struct mlx5_esw_psample *esw_psample, u32 obj_id) goto err_alloc; } restore->obj_id = obj_id; + restore->post_act_handle = post_act_handle; - modify_hdr = sample_metadata_rule_get(mdev, obj_id); + modify_hdr = sample_modify_hdr_get(mdev, obj_id, post_act_handle); if (IS_ERR(modify_hdr)) { err = PTR_ERR(modify_hdr); goto err_modify_hdr; @@ -280,10 +316,10 @@ sample_restore_get(struct mlx5_esw_psample *esw_psample, u32 obj_id) goto err_restore; } - hash_add(esw_psample->restore_hashtbl, &restore->hlist, obj_id); + hash_add(tc_psample->restore_hashtbl, &restore->hlist, hash_key); add_ref: restore->count++; - mutex_unlock(&esw_psample->restore_lock); + mutex_unlock(&tc_psample->restore_lock); return restore; err_restore: @@ -291,26 +327,26 @@ err_restore: err_modify_hdr: kfree(restore); err_alloc: - mutex_unlock(&esw_psample->restore_lock); + mutex_unlock(&tc_psample->restore_lock); return ERR_PTR(err); } static void -sample_restore_put(struct mlx5_esw_psample *esw_psample, struct mlx5_sample_restore *restore) +sample_restore_put(struct mlx5e_tc_psample *tc_psample, struct mlx5e_sample_restore *restore) { - mutex_lock(&esw_psample->restore_lock); + mutex_lock(&tc_psample->restore_lock); if (--restore->count == 0) hash_del(&restore->hlist); - mutex_unlock(&esw_psample->restore_lock); + mutex_unlock(&tc_psample->restore_lock); if (!restore->count) { mlx5_del_flow_rules(restore->rule); - mlx5_modify_header_dealloc(esw_psample->priv->mdev, restore->modify_hdr); + mlx5_modify_header_dealloc(tc_psample->esw->dev, restore->modify_hdr); kfree(restore); } } -void mlx5_esw_sample_skb(struct sk_buff *skb, struct mlx5_mapped_obj *mapped_obj) +void mlx5e_tc_sample_skb(struct sk_buff *skb, struct mlx5_mapped_obj *mapped_obj) { u32 trunc_size = mapped_obj->sample.trunc_size; struct psample_group psample_group = {}; @@ -325,6 +361,87 @@ void mlx5_esw_sample_skb(struct sk_buff *skb, struct mlx5_mapped_obj *mapped_obj psample_sample_packet(&psample_group, skb, mapped_obj->sample.rate, &md); } +static int +add_post_rule(struct mlx5_eswitch *esw, struct mlx5e_sample_flow *sample_flow, + struct mlx5_flow_spec *spec, struct mlx5_flow_attr *attr, + u32 *default_tbl_id) +{ + struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr; + u32 attr_sz = ns_to_attr_sz(MLX5_FLOW_NAMESPACE_FDB); + struct mlx5_vport_tbl_attr per_vport_tbl_attr; + struct mlx5_flow_table *default_tbl; + struct mlx5_flow_attr *post_attr; + int err; + + /* Allocate default table per vport, chain and prio. Otherwise, there is + * only one default table for the same sampler object. Rules with different + * prio and chain may overlap. For CT sample action, per vport default + * table is needed to resotre the metadata. + */ + per_vport_tbl_attr.chain = attr->chain; + per_vport_tbl_attr.prio = attr->prio; + per_vport_tbl_attr.vport = esw_attr->in_rep->vport; + per_vport_tbl_attr.vport_ns = &mlx5_esw_vport_tbl_sample_ns; + default_tbl = mlx5_esw_vporttbl_get(esw, &per_vport_tbl_attr); + if (IS_ERR(default_tbl)) { + err = PTR_ERR(default_tbl); + goto err_default_tbl; + } + *default_tbl_id = default_tbl->id; + + post_attr = mlx5_alloc_flow_attr(MLX5_FLOW_NAMESPACE_FDB); + if (!post_attr) { + err = -ENOMEM; + goto err_attr; + } + sample_flow->post_attr = post_attr; + memcpy(post_attr, attr, attr_sz); + /* Perform the original matches on the default table. + * Offload all actions except the sample action. + */ + post_attr->chain = 0; + post_attr->prio = 0; + post_attr->ft = default_tbl; + post_attr->flags = MLX5_ESW_ATTR_FLAG_NO_IN_PORT; + + /* When offloading sample and encap action, if there is no valid + * neigh data struct, a slow path rule is offloaded first. Source + * port metadata match is set at that time. A per vport table is + * already allocated. No need to match it again. So clear the source + * port metadata match. + */ + mlx5_eswitch_clear_rule_source_port(esw, spec); + sample_flow->post_rule = mlx5_eswitch_add_offloaded_rule(esw, spec, post_attr); + if (IS_ERR(sample_flow->post_rule)) { + err = PTR_ERR(sample_flow->post_rule); + goto err_rule; + } + return 0; + +err_rule: + kfree(post_attr); +err_attr: + mlx5_esw_vporttbl_put(esw, &per_vport_tbl_attr); +err_default_tbl: + return err; +} + +static void +del_post_rule(struct mlx5_eswitch *esw, struct mlx5e_sample_flow *sample_flow, + struct mlx5_flow_attr *attr) +{ + struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr; + struct mlx5_vport_tbl_attr tbl_attr; + + mlx5_eswitch_del_offloaded_rule(esw, sample_flow->post_rule, sample_flow->post_attr); + kfree(sample_flow->post_attr); + tbl_attr.chain = attr->chain; + tbl_attr.prio = attr->prio; + tbl_attr.vport = esw_attr->in_rep->vport; + tbl_attr.vport_ns = &mlx5_esw_vport_tbl_sample_ns; + mlx5_esw_vporttbl_put(esw, &tbl_attr); +} + /* For the following typical flow table: * * +-------------------------------+ @@ -342,8 +459,9 @@ void mlx5_esw_sample_skb(struct sk_buff *skb, struct mlx5_mapped_obj *mapped_obj * +---------------------+ * + original match + * +---------------------+ - * | - * v + * | set fte_id (if reg_c preserve cap) + * | do decap (if required) + * v * +------------------------------------------------+ * + Flow Sampler Object + * +------------------------------------------------+ @@ -353,80 +471,82 @@ void mlx5_esw_sample_skb(struct sk_buff *skb, struct mlx5_mapped_obj *mapped_obj * +------------------------------------------------+ * | | * v v - * +-----------------------------+ +----------------------------------------+ - * + sample table + + default table per <vport, chain, prio> + - * +-----------------------------+ +----------------------------------------+ - * + forward to management vport + + original match + - * +-----------------------------+ +----------------------------------------+ - * + other actions + - * +----------------------------------------+ + * +-----------------------------+ +-------------------+ + * + sample table + + default table + + * +-----------------------------+ +-------------------+ + * + forward to management vport + | + * +-----------------------------+ | + * +-------+------+ + * | |reg_c preserve cap + * | |or decap action + * v v + * +-----------------+ +-------------+ + * + per vport table + + post action + + * +-----------------+ +-------------+ + * + original match + + * +-----------------+ + * + other actions + + * +-----------------+ */ struct mlx5_flow_handle * -mlx5_esw_sample_offload(struct mlx5_esw_psample *esw_psample, +mlx5e_tc_sample_offload(struct mlx5e_tc_psample *tc_psample, struct mlx5_flow_spec *spec, - struct mlx5_flow_attr *attr) + struct mlx5_flow_attr *attr, + u32 tunnel_id) { + struct mlx5e_post_act_handle *post_act_handle = NULL; struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr; - struct mlx5_vport_tbl_attr per_vport_tbl_attr; struct mlx5_esw_flow_attr *pre_esw_attr; struct mlx5_mapped_obj restore_obj = {}; - struct mlx5_sample_flow *sample_flow; - struct mlx5_sample_attr *sample_attr; - struct mlx5_flow_table *default_tbl; + struct mlx5e_sample_flow *sample_flow; + struct mlx5e_sample_attr *sample_attr; struct mlx5_flow_attr *pre_attr; struct mlx5_eswitch *esw; + u32 default_tbl_id; u32 obj_id; int err; - if (IS_ERR_OR_NULL(esw_psample)) + if (IS_ERR_OR_NULL(tc_psample)) return ERR_PTR(-EOPNOTSUPP); /* If slow path flag is set, eg. when the neigh is invalid for encap, * don't offload sample action. */ - esw = esw_psample->priv->mdev->priv.eswitch; + esw = tc_psample->esw; if (attr->flags & MLX5_ESW_ATTR_FLAG_SLOW_PATH) return mlx5_eswitch_add_offloaded_rule(esw, spec, attr); sample_flow = kzalloc(sizeof(*sample_flow), GFP_KERNEL); if (!sample_flow) return ERR_PTR(-ENOMEM); - esw_attr->sample->sample_flow = sample_flow; - - /* Allocate default table per vport, chain and prio. Otherwise, there is - * only one default table for the same sampler object. Rules with different - * prio and chain may overlap. For CT sample action, per vport default - * table is needed to resotre the metadata. - */ - per_vport_tbl_attr.chain = attr->chain; - per_vport_tbl_attr.prio = attr->prio; - per_vport_tbl_attr.vport = esw_attr->in_rep->vport; - per_vport_tbl_attr.vport_ns = &mlx5_esw_vport_tbl_sample_ns; - default_tbl = mlx5_esw_vporttbl_get(esw, &per_vport_tbl_attr); - if (IS_ERR(default_tbl)) { - err = PTR_ERR(default_tbl); - goto err_default_tbl; - } + sample_attr = attr->sample_attr; + sample_attr->sample_flow = sample_flow; - /* Perform the original matches on the default table. - * Offload all actions except the sample action. - */ - esw_attr->sample->sample_default_tbl = default_tbl; - /* When offloading sample and encap action, if there is no valid - * neigh data struct, a slow path rule is offloaded first. Source - * port metadata match is set at that time. A per vport table is - * already allocated. No need to match it again. So clear the source - * port metadata match. + /* For NICs with reg_c_preserve support or decap action, use + * post action instead of the per vport, chain and prio table. + * Only match the fte id instead of the same match in the + * original flow table. */ - mlx5_eswitch_clear_rule_source_port(esw, spec); - sample_flow->rule = mlx5_eswitch_add_offloaded_rule(esw, spec, attr); - if (IS_ERR(sample_flow->rule)) { - err = PTR_ERR(sample_flow->rule); - goto err_offload_rule; + if (MLX5_CAP_GEN(esw->dev, reg_c_preserve) || + attr->action & MLX5_FLOW_CONTEXT_ACTION_DECAP) { + struct mlx5_flow_table *ft; + + ft = mlx5e_tc_post_act_get_ft(tc_psample->post_act); + default_tbl_id = ft->id; + post_act_handle = mlx5e_tc_post_act_add(tc_psample->post_act, attr); + if (IS_ERR(post_act_handle)) { + err = PTR_ERR(post_act_handle); + goto err_post_act; + } + sample_flow->post_act_handle = post_act_handle; + } else { + err = add_post_rule(esw, sample_flow, spec, attr, &default_tbl_id); + if (err) + goto err_post_rule; } /* Create sampler object. */ - sample_flow->sampler = sampler_get(esw_psample, esw_attr->sample->rate, default_tbl->id); + sample_flow->sampler = sampler_get(tc_psample, sample_attr->rate, default_tbl_id); if (IS_ERR(sample_flow->sampler)) { err = PTR_ERR(sample_flow->sampler); goto err_sampler; @@ -434,16 +554,17 @@ mlx5_esw_sample_offload(struct mlx5_esw_psample *esw_psample, /* Create an id mapping reg_c0 value to sample object. */ restore_obj.type = MLX5_MAPPED_OBJ_SAMPLE; - restore_obj.sample.group_id = esw_attr->sample->group_num; - restore_obj.sample.rate = esw_attr->sample->rate; - restore_obj.sample.trunc_size = esw_attr->sample->trunc_size; + restore_obj.sample.group_id = sample_attr->group_num; + restore_obj.sample.rate = sample_attr->rate; + restore_obj.sample.trunc_size = sample_attr->trunc_size; + restore_obj.sample.tunnel_id = tunnel_id; err = mapping_add(esw->offloads.reg_c0_obj_pool, &restore_obj, &obj_id); if (err) goto err_obj_id; - esw_attr->sample->restore_obj_id = obj_id; + sample_attr->restore_obj_id = obj_id; /* Create sample restore context. */ - sample_flow->restore = sample_restore_get(esw_psample, obj_id); + sample_flow->restore = sample_restore_get(tc_psample, obj_id, post_act_handle); if (IS_ERR(sample_flow->restore)) { err = PTR_ERR(sample_flow->restore); goto err_sample_restore; @@ -455,21 +576,23 @@ mlx5_esw_sample_offload(struct mlx5_esw_psample *esw_psample, pre_attr = mlx5_alloc_flow_attr(MLX5_FLOW_NAMESPACE_FDB); if (!pre_attr) { err = -ENOMEM; - goto err_alloc_flow_attr; - } - sample_attr = kzalloc(sizeof(*sample_attr), GFP_KERNEL); - if (!sample_attr) { - err = -ENOMEM; - goto err_alloc_sample_attr; + goto err_alloc_pre_flow_attr; } - pre_esw_attr = pre_attr->esw_attr; pre_attr->action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_MOD_HDR; + /* For decap action, do decap in the original flow table instead of the + * default flow table. + */ + if (tunnel_id) + pre_attr->action |= MLX5_FLOW_CONTEXT_ACTION_DECAP; pre_attr->modify_hdr = sample_flow->restore->modify_hdr; pre_attr->flags = MLX5_ESW_ATTR_FLAG_SAMPLE; + pre_attr->inner_match_level = attr->inner_match_level; + pre_attr->outer_match_level = attr->outer_match_level; pre_attr->chain = attr->chain; pre_attr->prio = attr->prio; - pre_esw_attr->sample = sample_attr; - pre_esw_attr->sample->sampler_id = sample_flow->sampler->sampler_id; + pre_attr->sample_attr = attr->sample_attr; + sample_attr->sampler_id = sample_flow->sampler->sampler_id; + pre_esw_attr = pre_attr->esw_attr; pre_esw_attr->in_mdev = esw_attr->in_mdev; pre_esw_attr->in_rep = esw_attr->in_rep; sample_flow->pre_rule = mlx5_eswitch_add_offloaded_rule(esw, spec, pre_attr); @@ -479,108 +602,113 @@ mlx5_esw_sample_offload(struct mlx5_esw_psample *esw_psample, } sample_flow->pre_attr = pre_attr; - return sample_flow->rule; + return sample_flow->post_rule; err_pre_offload_rule: - kfree(sample_attr); -err_alloc_sample_attr: kfree(pre_attr); -err_alloc_flow_attr: - sample_restore_put(esw_psample, sample_flow->restore); +err_alloc_pre_flow_attr: + sample_restore_put(tc_psample, sample_flow->restore); err_sample_restore: mapping_remove(esw->offloads.reg_c0_obj_pool, obj_id); err_obj_id: - sampler_put(esw_psample, sample_flow->sampler); + sampler_put(tc_psample, sample_flow->sampler); err_sampler: - /* For sample offload, rule is added in default_tbl. No need to call - * mlx5_esw_chains_put_table() - */ - attr->prio = 0; - attr->chain = 0; - mlx5_eswitch_del_offloaded_rule(esw, sample_flow->rule, attr); -err_offload_rule: - mlx5_esw_vporttbl_put(esw, &per_vport_tbl_attr); -err_default_tbl: + if (!post_act_handle) + del_post_rule(esw, sample_flow, attr); +err_post_rule: + if (post_act_handle) + mlx5e_tc_post_act_del(tc_psample->post_act, post_act_handle); +err_post_act: kfree(sample_flow); return ERR_PTR(err); } void -mlx5_esw_sample_unoffload(struct mlx5_esw_psample *esw_psample, +mlx5e_tc_sample_unoffload(struct mlx5e_tc_psample *tc_psample, struct mlx5_flow_handle *rule, struct mlx5_flow_attr *attr) { struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr; - struct mlx5_sample_flow *sample_flow; + struct mlx5e_sample_flow *sample_flow; struct mlx5_vport_tbl_attr tbl_attr; - struct mlx5_flow_attr *pre_attr; struct mlx5_eswitch *esw; - if (IS_ERR_OR_NULL(esw_psample)) + if (IS_ERR_OR_NULL(tc_psample)) return; /* If slow path flag is set, sample action is not offloaded. * No need to delete sample rule. */ - esw = esw_psample->priv->mdev->priv.eswitch; + esw = tc_psample->esw; if (attr->flags & MLX5_ESW_ATTR_FLAG_SLOW_PATH) { mlx5_eswitch_del_offloaded_rule(esw, rule, attr); return; } - sample_flow = esw_attr->sample->sample_flow; - pre_attr = sample_flow->pre_attr; - memset(pre_attr, 0, sizeof(*pre_attr)); - esw = esw_psample->priv->mdev->priv.eswitch; - mlx5_eswitch_del_offloaded_rule(esw, sample_flow->pre_rule, pre_attr); - mlx5_eswitch_del_offloaded_rule(esw, sample_flow->rule, attr); - - sample_restore_put(esw_psample, sample_flow->restore); - mapping_remove(esw->offloads.reg_c0_obj_pool, esw_attr->sample->restore_obj_id); - sampler_put(esw_psample, sample_flow->sampler); - tbl_attr.chain = attr->chain; - tbl_attr.prio = attr->prio; - tbl_attr.vport = esw_attr->in_rep->vport; - tbl_attr.vport_ns = &mlx5_esw_vport_tbl_sample_ns; - mlx5_esw_vporttbl_put(esw, &tbl_attr); + /* The following delete order can't be changed, otherwise, + * will hit fw syndromes. + */ + sample_flow = attr->sample_attr->sample_flow; + mlx5_eswitch_del_offloaded_rule(esw, sample_flow->pre_rule, sample_flow->pre_attr); + if (!sample_flow->post_act_handle) + mlx5_eswitch_del_offloaded_rule(esw, sample_flow->post_rule, + sample_flow->post_attr); + + sample_restore_put(tc_psample, sample_flow->restore); + mapping_remove(esw->offloads.reg_c0_obj_pool, attr->sample_attr->restore_obj_id); + sampler_put(tc_psample, sample_flow->sampler); + if (sample_flow->post_act_handle) { + mlx5e_tc_post_act_del(tc_psample->post_act, sample_flow->post_act_handle); + } else { + tbl_attr.chain = attr->chain; + tbl_attr.prio = attr->prio; + tbl_attr.vport = esw_attr->in_rep->vport; + tbl_attr.vport_ns = &mlx5_esw_vport_tbl_sample_ns; + mlx5_esw_vporttbl_put(esw, &tbl_attr); + kfree(sample_flow->post_attr); + } - kfree(pre_attr->esw_attr->sample); - kfree(pre_attr); + kfree(sample_flow->pre_attr); kfree(sample_flow); } -struct mlx5_esw_psample * -mlx5_esw_sample_init(struct mlx5e_priv *priv) +struct mlx5e_tc_psample * +mlx5e_tc_sample_init(struct mlx5_eswitch *esw, struct mlx5e_post_act *post_act) { - struct mlx5_esw_psample *esw_psample; + struct mlx5e_tc_psample *tc_psample; int err; - esw_psample = kzalloc(sizeof(*esw_psample), GFP_KERNEL); - if (!esw_psample) + tc_psample = kzalloc(sizeof(*tc_psample), GFP_KERNEL); + if (!tc_psample) return ERR_PTR(-ENOMEM); - esw_psample->priv = priv; - err = sampler_termtbl_create(esw_psample); + if (IS_ERR_OR_NULL(post_act)) { + err = PTR_ERR(post_act); + goto err_post_act; + } + tc_psample->post_act = post_act; + tc_psample->esw = esw; + err = sampler_termtbl_create(tc_psample); if (err) - goto err_termtbl; + goto err_post_act; - mutex_init(&esw_psample->ht_lock); - mutex_init(&esw_psample->restore_lock); + mutex_init(&tc_psample->ht_lock); + mutex_init(&tc_psample->restore_lock); - return esw_psample; + return tc_psample; -err_termtbl: - kfree(esw_psample); +err_post_act: + kfree(tc_psample); return ERR_PTR(err); } void -mlx5_esw_sample_cleanup(struct mlx5_esw_psample *esw_psample) +mlx5e_tc_sample_cleanup(struct mlx5e_tc_psample *tc_psample) { - if (IS_ERR_OR_NULL(esw_psample)) + if (IS_ERR_OR_NULL(tc_psample)) return; - mutex_destroy(&esw_psample->restore_lock); - mutex_destroy(&esw_psample->ht_lock); - sampler_termtbl_destroy(esw_psample); - kfree(esw_psample); + mutex_destroy(&tc_psample->restore_lock); + mutex_destroy(&tc_psample->ht_lock); + sampler_termtbl_destroy(tc_psample); + kfree(tc_psample); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.h new file mode 100644 index 000000000000..db0146df9b30 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2021 Mellanox Technologies. */ + +#ifndef __MLX5_EN_TC_SAMPLE_H__ +#define __MLX5_EN_TC_SAMPLE_H__ + +#include "eswitch.h" + +struct mlx5_flow_attr; +struct mlx5e_tc_psample; +struct mlx5e_post_act; + +struct mlx5e_sample_attr { + u32 group_num; + u32 rate; + u32 trunc_size; + u32 restore_obj_id; + u32 sampler_id; + struct mlx5e_sample_flow *sample_flow; +}; + +void mlx5e_tc_sample_skb(struct sk_buff *skb, struct mlx5_mapped_obj *mapped_obj); + +struct mlx5_flow_handle * +mlx5e_tc_sample_offload(struct mlx5e_tc_psample *sample_priv, + struct mlx5_flow_spec *spec, + struct mlx5_flow_attr *attr, + u32 tunnel_id); + +void +mlx5e_tc_sample_unoffload(struct mlx5e_tc_psample *sample_priv, + struct mlx5_flow_handle *rule, + struct mlx5_flow_attr *attr); + +struct mlx5e_tc_psample * +mlx5e_tc_sample_init(struct mlx5_eswitch *esw, struct mlx5e_post_act *post_act); + +void +mlx5e_tc_sample_cleanup(struct mlx5e_tc_psample *tc_psample); + +#endif /* __MLX5_EN_TC_SAMPLE_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c index 91e7a01e32be..6c949abcd2e1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c @@ -19,6 +19,7 @@ #include "en/tc_ct.h" #include "en/mod_hdr.h" #include "en/mapping.h" +#include "en/tc/post_act.h" #include "en.h" #include "en_tc.h" #include "en_rep.h" @@ -32,10 +33,6 @@ #define MLX5_CT_STATE_RELATED_BIT BIT(5) #define MLX5_CT_STATE_INVALID_BIT BIT(6) -#define MLX5_FTE_ID_BITS (mlx5e_tc_attr_to_reg_mappings[FTEID_TO_REG].mlen) -#define MLX5_FTE_ID_MAX GENMASK(MLX5_FTE_ID_BITS - 1, 0) -#define MLX5_FTE_ID_MASK MLX5_FTE_ID_MAX - #define MLX5_CT_LABELS_BITS (mlx5e_tc_attr_to_reg_mappings[LABELS_TO_REG].mlen) #define MLX5_CT_LABELS_MASK GENMASK(MLX5_CT_LABELS_BITS - 1, 0) @@ -46,14 +43,13 @@ struct mlx5_tc_ct_priv { struct mlx5_core_dev *dev; const struct net_device *netdev; struct mod_hdr_tbl *mod_hdr_tbl; - struct idr fte_ids; struct xarray tuple_ids; struct rhashtable zone_ht; struct rhashtable ct_tuples_ht; struct rhashtable ct_tuples_nat_ht; struct mlx5_flow_table *ct; struct mlx5_flow_table *ct_nat; - struct mlx5_flow_table *post_ct; + struct mlx5e_post_act *post_act; struct mutex control_lock; /* guards parallel adds/dels */ struct mapping_ctx *zone_mapping; struct mapping_ctx *labels_mapping; @@ -64,11 +60,9 @@ struct mlx5_tc_ct_priv { struct mlx5_ct_flow { struct mlx5_flow_attr *pre_ct_attr; - struct mlx5_flow_attr *post_ct_attr; struct mlx5_flow_handle *pre_ct_rule; - struct mlx5_flow_handle *post_ct_rule; + struct mlx5e_post_act_handle *post_act_handle; struct mlx5_ct_ft *ft; - u32 fte_id; u32 chain_mapping; }; @@ -768,7 +762,7 @@ mlx5_tc_ct_entry_add_rule(struct mlx5_tc_ct_priv *ct_priv, MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_COUNT; attr->dest_chain = 0; - attr->dest_ft = ct_priv->post_ct; + attr->dest_ft = mlx5e_tc_post_act_get_ft(ct_priv->post_act); attr->ft = nat ? ct_priv->ct_nat : ct_priv->ct; attr->outer_match_level = MLX5_MATCH_L4; attr->counter = entry->counter->counter; @@ -1432,7 +1426,7 @@ static int tc_ct_pre_ct_add_rules(struct mlx5_ct_ft *ct_ft, ctstate |= MLX5_CT_STATE_NAT_BIT; mlx5e_tc_match_to_reg_match(spec, CTSTATE_TO_REG, ctstate, ctstate); - dest.ft = ct_priv->post_ct; + dest.ft = mlx5e_tc_post_act_get_ft(ct_priv->post_act); rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1); if (IS_ERR(rule)) { err = PTR_ERR(rule); @@ -1716,9 +1710,9 @@ mlx5_tc_ct_del_ft_cb(struct mlx5_tc_ct_priv *ct_priv, struct mlx5_ct_ft *ft) * | do decap * v * +---------------------+ - * + pre_ct/pre_ct_nat + if matches +---------------------+ - * + zone+nat match +---------------->+ post_ct (see below) + - * +---------------------+ set zone +---------------------+ + * + pre_ct/pre_ct_nat + if matches +-------------------------+ + * + zone+nat match +---------------->+ post_act (see below) + + * +---------------------+ set zone +-------------------------+ * | set zone * v * +--------------------+ @@ -1732,7 +1726,7 @@ mlx5_tc_ct_del_ft_cb(struct mlx5_tc_ct_priv *ct_priv, struct mlx5_ct_ft *ft) * | do nat (if needed) * v * +--------------+ - * + post_ct + original filter actions + * + post_act + original filter actions * + fte_id match +------------------------> * +--------------+ */ @@ -1746,19 +1740,15 @@ __mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *ct_priv, struct mlx5e_priv *priv = netdev_priv(ct_priv->netdev); struct mlx5e_tc_mod_hdr_acts pre_mod_acts = {}; u32 attr_sz = ns_to_attr_sz(ct_priv->ns_type); - struct mlx5_flow_spec *post_ct_spec = NULL; + struct mlx5e_post_act_handle *handle; struct mlx5_flow_attr *pre_ct_attr; struct mlx5_modify_hdr *mod_hdr; - struct mlx5_flow_handle *rule; struct mlx5_ct_flow *ct_flow; int chain_mapping = 0, err; struct mlx5_ct_ft *ft; - u32 fte_id = 1; - post_ct_spec = kvzalloc(sizeof(*post_ct_spec), GFP_KERNEL); ct_flow = kzalloc(sizeof(*ct_flow), GFP_KERNEL); - if (!post_ct_spec || !ct_flow) { - kvfree(post_ct_spec); + if (!ct_flow) { kfree(ct_flow); return ERR_PTR(-ENOMEM); } @@ -1773,14 +1763,13 @@ __mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *ct_priv, } ct_flow->ft = ft; - err = idr_alloc_u32(&ct_priv->fte_ids, ct_flow, &fte_id, - MLX5_FTE_ID_MAX, GFP_KERNEL); - if (err) { - netdev_warn(priv->netdev, - "Failed to allocate fte id, err: %d\n", err); - goto err_idr; + handle = mlx5e_tc_post_act_add(ct_priv->post_act, attr); + if (IS_ERR(handle)) { + err = PTR_ERR(handle); + ct_dbg("Failed to allocate post action handle"); + goto err_post_act_handle; } - ct_flow->fte_id = fte_id; + ct_flow->post_act_handle = handle; /* Base flow attributes of both rules on original rule attribute */ ct_flow->pre_ct_attr = mlx5_alloc_flow_attr(ct_priv->ns_type); @@ -1789,15 +1778,8 @@ __mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *ct_priv, goto err_alloc_pre; } - ct_flow->post_ct_attr = mlx5_alloc_flow_attr(ct_priv->ns_type); - if (!ct_flow->post_ct_attr) { - err = -ENOMEM; - goto err_alloc_post; - } - pre_ct_attr = ct_flow->pre_ct_attr; memcpy(pre_ct_attr, attr, attr_sz); - memcpy(ct_flow->post_ct_attr, attr, attr_sz); /* Modify the original rule's action to fwd and modify, leave decap */ pre_ct_attr->action = attr->action & MLX5_FLOW_CONTEXT_ACTION_DECAP; @@ -1823,10 +1805,9 @@ __mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *ct_priv, goto err_mapping; } - err = mlx5e_tc_match_to_reg_set(priv->mdev, &pre_mod_acts, ct_priv->ns_type, - FTEID_TO_REG, fte_id); + err = mlx5e_tc_post_act_set_handle(priv->mdev, handle, &pre_mod_acts); if (err) { - ct_dbg("Failed to set fte_id register mapping"); + ct_dbg("Failed to set post action handle"); goto err_mapping; } @@ -1857,33 +1838,6 @@ __mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *ct_priv, } pre_ct_attr->modify_hdr = mod_hdr; - /* Post ct rule matches on fte_id and executes original rule's - * tc rule action - */ - mlx5e_tc_match_to_reg_match(post_ct_spec, FTEID_TO_REG, - fte_id, MLX5_FTE_ID_MASK); - - /* Put post_ct rule on post_ct flow table */ - ct_flow->post_ct_attr->chain = 0; - ct_flow->post_ct_attr->prio = 0; - ct_flow->post_ct_attr->ft = ct_priv->post_ct; - - /* Splits were handled before CT */ - if (ct_priv->ns_type == MLX5_FLOW_NAMESPACE_FDB) - ct_flow->post_ct_attr->esw_attr->split_count = 0; - - ct_flow->post_ct_attr->inner_match_level = MLX5_MATCH_NONE; - ct_flow->post_ct_attr->outer_match_level = MLX5_MATCH_NONE; - ct_flow->post_ct_attr->action &= ~(MLX5_FLOW_CONTEXT_ACTION_DECAP); - rule = mlx5_tc_rule_insert(priv, post_ct_spec, - ct_flow->post_ct_attr); - ct_flow->post_ct_rule = rule; - if (IS_ERR(ct_flow->post_ct_rule)) { - err = PTR_ERR(ct_flow->post_ct_rule); - ct_dbg("Failed to add post ct rule"); - goto err_insert_post_ct; - } - /* Change original rule point to ct table */ pre_ct_attr->dest_chain = 0; pre_ct_attr->dest_ft = nat ? ft->pre_ct_nat.ft : ft->pre_ct.ft; @@ -1897,28 +1851,21 @@ __mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *ct_priv, attr->ct_attr.ct_flow = ct_flow; dealloc_mod_hdr_actions(&pre_mod_acts); - kvfree(post_ct_spec); - return rule; + return ct_flow->pre_ct_rule; err_insert_orig: - mlx5_tc_rule_delete(priv, ct_flow->post_ct_rule, - ct_flow->post_ct_attr); -err_insert_post_ct: mlx5_modify_header_dealloc(priv->mdev, pre_ct_attr->modify_hdr); err_mapping: dealloc_mod_hdr_actions(&pre_mod_acts); mlx5_chains_put_chain_mapping(ct_priv->chains, ct_flow->chain_mapping); err_get_chain: - kfree(ct_flow->post_ct_attr); -err_alloc_post: kfree(ct_flow->pre_ct_attr); err_alloc_pre: - idr_remove(&ct_priv->fte_ids, fte_id); -err_idr: + mlx5e_tc_post_act_del(ct_priv->post_act, handle); +err_post_act_handle: mlx5_tc_ct_del_ft_cb(ct_priv, ft); err_ft: - kvfree(post_ct_spec); kfree(ct_flow); netdev_warn(priv->netdev, "Failed to offload ct flow, err %d\n", err); return ERR_PTR(err); @@ -2029,16 +1976,13 @@ __mlx5_tc_ct_delete_flow(struct mlx5_tc_ct_priv *ct_priv, pre_ct_attr); mlx5_modify_header_dealloc(priv->mdev, pre_ct_attr->modify_hdr); - if (ct_flow->post_ct_rule) { - mlx5_tc_rule_delete(priv, ct_flow->post_ct_rule, - ct_flow->post_ct_attr); + if (ct_flow->post_act_handle) { mlx5_chains_put_chain_mapping(ct_priv->chains, ct_flow->chain_mapping); - idr_remove(&ct_priv->fte_ids, ct_flow->fte_id); + mlx5e_tc_post_act_del(ct_priv->post_act, ct_flow->post_act_handle); mlx5_tc_ct_del_ft_cb(ct_priv, ct_flow->ft); } kfree(ct_flow->pre_ct_attr); - kfree(ct_flow->post_ct_attr); kfree(ct_flow); } @@ -2064,11 +2008,6 @@ static int mlx5_tc_ct_init_check_esw_support(struct mlx5_eswitch *esw, const char **err_msg) { - if (!MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ignore_flow_level)) { - *err_msg = "firmware level support is missing"; - return -EOPNOTSUPP; - } - if (!mlx5_eswitch_vlan_actions_supported(esw->dev, 1)) { /* vlan workaround should be avoided for multi chain rules. * This is just a sanity check as pop vlan action should @@ -2098,20 +2037,9 @@ mlx5_tc_ct_init_check_esw_support(struct mlx5_eswitch *esw, } static int -mlx5_tc_ct_init_check_nic_support(struct mlx5e_priv *priv, - const char **err_msg) -{ - if (!MLX5_CAP_FLOWTABLE_NIC_RX(priv->mdev, ignore_flow_level)) { - *err_msg = "firmware level support is missing"; - return -EOPNOTSUPP; - } - - return 0; -} - -static int mlx5_tc_ct_init_check_support(struct mlx5e_priv *priv, enum mlx5_flow_namespace_type ns_type, + struct mlx5e_post_act *post_act, const char **err_msg) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; @@ -2122,10 +2050,14 @@ mlx5_tc_ct_init_check_support(struct mlx5e_priv *priv, *err_msg = "tc skb extension missing"; return -EOPNOTSUPP; #endif + if (IS_ERR_OR_NULL(post_act)) { + *err_msg = "tc ct offload not supported, post action is missing"; + return -EOPNOTSUPP; + } + if (ns_type == MLX5_FLOW_NAMESPACE_FDB) return mlx5_tc_ct_init_check_esw_support(esw, err_msg); - else - return mlx5_tc_ct_init_check_nic_support(priv, err_msg); + return 0; } #define INIT_ERR_PREFIX "tc ct offload init failed" @@ -2133,19 +2065,19 @@ mlx5_tc_ct_init_check_support(struct mlx5e_priv *priv, struct mlx5_tc_ct_priv * mlx5_tc_ct_init(struct mlx5e_priv *priv, struct mlx5_fs_chains *chains, struct mod_hdr_tbl *mod_hdr, - enum mlx5_flow_namespace_type ns_type) + enum mlx5_flow_namespace_type ns_type, + struct mlx5e_post_act *post_act) { struct mlx5_tc_ct_priv *ct_priv; struct mlx5_core_dev *dev; const char *msg; + u64 mapping_id; int err; dev = priv->mdev; - err = mlx5_tc_ct_init_check_support(priv, ns_type, &msg); + err = mlx5_tc_ct_init_check_support(priv, ns_type, post_act, &msg); if (err) { - mlx5_core_warn(dev, - "tc ct offload not supported, %s\n", - msg); + mlx5_core_warn(dev, "tc ct offload not supported, %s\n", msg); goto err_support; } @@ -2153,13 +2085,17 @@ mlx5_tc_ct_init(struct mlx5e_priv *priv, struct mlx5_fs_chains *chains, if (!ct_priv) goto err_alloc; - ct_priv->zone_mapping = mapping_create(sizeof(u16), 0, true); + mapping_id = mlx5_query_nic_system_image_guid(dev); + + ct_priv->zone_mapping = mapping_create_for_id(mapping_id, MAPPING_TYPE_ZONE, + sizeof(u16), 0, true); if (IS_ERR(ct_priv->zone_mapping)) { err = PTR_ERR(ct_priv->zone_mapping); goto err_mapping_zone; } - ct_priv->labels_mapping = mapping_create(sizeof(u32) * 4, 0, true); + ct_priv->labels_mapping = mapping_create_for_id(mapping_id, MAPPING_TYPE_LABELS, + sizeof(u32) * 4, 0, true); if (IS_ERR(ct_priv->labels_mapping)) { err = PTR_ERR(ct_priv->labels_mapping); goto err_mapping_labels; @@ -2189,16 +2125,7 @@ mlx5_tc_ct_init(struct mlx5e_priv *priv, struct mlx5_fs_chains *chains, goto err_ct_nat_tbl; } - ct_priv->post_ct = mlx5_chains_create_global_table(chains); - if (IS_ERR(ct_priv->post_ct)) { - err = PTR_ERR(ct_priv->post_ct); - mlx5_core_warn(dev, - "%s, failed to create post ct table err: %d\n", - INIT_ERR_PREFIX, err); - goto err_post_ct_tbl; - } - - idr_init(&ct_priv->fte_ids); + ct_priv->post_act = post_act; mutex_init(&ct_priv->control_lock); rhashtable_init(&ct_priv->zone_ht, &zone_params); rhashtable_init(&ct_priv->ct_tuples_ht, &tuples_ht_params); @@ -2206,8 +2133,6 @@ mlx5_tc_ct_init(struct mlx5e_priv *priv, struct mlx5_fs_chains *chains, return ct_priv; -err_post_ct_tbl: - mlx5_chains_destroy_global_table(chains, ct_priv->ct_nat); err_ct_nat_tbl: mlx5_chains_destroy_global_table(chains, ct_priv->ct); err_ct_tbl: @@ -2232,7 +2157,6 @@ mlx5_tc_ct_clean(struct mlx5_tc_ct_priv *ct_priv) chains = ct_priv->chains; - mlx5_chains_destroy_global_table(chains, ct_priv->post_ct); mlx5_chains_destroy_global_table(chains, ct_priv->ct_nat); mlx5_chains_destroy_global_table(chains, ct_priv->ct); mapping_destroy(ct_priv->zone_mapping); @@ -2242,7 +2166,6 @@ mlx5_tc_ct_clean(struct mlx5_tc_ct_priv *ct_priv) rhashtable_destroy(&ct_priv->ct_tuples_nat_ht); rhashtable_destroy(&ct_priv->zone_ht); mutex_destroy(&ct_priv->control_lock); - idr_destroy(&ct_priv->fte_ids); kfree(ct_priv); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h index 644cf1641cde..363329f4aac6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h @@ -92,7 +92,8 @@ struct mlx5_ct_attr { struct mlx5_tc_ct_priv * mlx5_tc_ct_init(struct mlx5e_priv *priv, struct mlx5_fs_chains *chains, struct mod_hdr_tbl *mod_hdr, - enum mlx5_flow_namespace_type ns_type); + enum mlx5_flow_namespace_type ns_type, + struct mlx5e_post_act *post_act); void mlx5_tc_ct_clean(struct mlx5_tc_ct_priv *ct_priv); @@ -132,7 +133,8 @@ mlx5e_tc_ct_restore_flow(struct mlx5_tc_ct_priv *ct_priv, static inline struct mlx5_tc_ct_priv * mlx5_tc_ct_init(struct mlx5e_priv *priv, struct mlx5_fs_chains *chains, struct mod_hdr_tbl *mod_hdr, - enum mlx5_flow_namespace_type ns_type) + enum mlx5_flow_namespace_type ns_type, + struct mlx5e_post_act *post_act) { return NULL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c index 1e2d117082d4..b4e986818794 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c @@ -525,7 +525,7 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv, e->out_dev = attr.out_dev; e->route_dev_ifindex = attr.route_dev->ifindex; - /* It's importent to add the neigh to the hash table before checking + /* It's important to add the neigh to the hash table before checking * the neigh validity state. So if we'll get a notification, in case the * neigh changes it's validity state, we would find the relevant neigh * in the hash. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c new file mode 100644 index 000000000000..de936dc4bc48 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c @@ -0,0 +1,200 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2021, Mellanox Technologies inc. All rights reserved. */ + +#include "tir.h" +#include "params.h" +#include <linux/mlx5/transobj.h> + +#define MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ (64 * 1024) + +/* max() doesn't work inside square brackets. */ +#define MLX5E_TIR_CMD_IN_SZ_DW ( \ + MLX5_ST_SZ_DW(create_tir_in) > MLX5_ST_SZ_DW(modify_tir_in) ? \ + MLX5_ST_SZ_DW(create_tir_in) : MLX5_ST_SZ_DW(modify_tir_in) \ +) + +struct mlx5e_tir_builder { + u32 in[MLX5E_TIR_CMD_IN_SZ_DW]; + bool modify; +}; + +struct mlx5e_tir_builder *mlx5e_tir_builder_alloc(bool modify) +{ + struct mlx5e_tir_builder *builder; + + builder = kvzalloc(sizeof(*builder), GFP_KERNEL); + builder->modify = modify; + + return builder; +} + +void mlx5e_tir_builder_free(struct mlx5e_tir_builder *builder) +{ + kvfree(builder); +} + +void mlx5e_tir_builder_clear(struct mlx5e_tir_builder *builder) +{ + memset(builder->in, 0, sizeof(builder->in)); +} + +static void *mlx5e_tir_builder_get_tirc(struct mlx5e_tir_builder *builder) +{ + if (builder->modify) + return MLX5_ADDR_OF(modify_tir_in, builder->in, ctx); + return MLX5_ADDR_OF(create_tir_in, builder->in, ctx); +} + +void mlx5e_tir_builder_build_inline(struct mlx5e_tir_builder *builder, u32 tdn, u32 rqn) +{ + void *tirc = mlx5e_tir_builder_get_tirc(builder); + + WARN_ON(builder->modify); + + MLX5_SET(tirc, tirc, transport_domain, tdn); + MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_DIRECT); + MLX5_SET(tirc, tirc, rx_hash_fn, MLX5_RX_HASH_FN_NONE); + MLX5_SET(tirc, tirc, inline_rqn, rqn); +} + +void mlx5e_tir_builder_build_rqt(struct mlx5e_tir_builder *builder, u32 tdn, + u32 rqtn, bool inner_ft_support) +{ + void *tirc = mlx5e_tir_builder_get_tirc(builder); + + WARN_ON(builder->modify); + + MLX5_SET(tirc, tirc, transport_domain, tdn); + MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_INDIRECT); + MLX5_SET(tirc, tirc, indirect_table, rqtn); + MLX5_SET(tirc, tirc, tunneled_offload_en, inner_ft_support); +} + +void mlx5e_tir_builder_build_lro(struct mlx5e_tir_builder *builder, + const struct mlx5e_lro_param *lro_param) +{ + void *tirc = mlx5e_tir_builder_get_tirc(builder); + const unsigned int rough_max_l2_l3_hdr_sz = 256; + + if (builder->modify) + MLX5_SET(modify_tir_in, builder->in, bitmask.lro, 1); + + if (!lro_param->enabled) + return; + + MLX5_SET(tirc, tirc, lro_enable_mask, + MLX5_TIRC_LRO_ENABLE_MASK_IPV4_LRO | + MLX5_TIRC_LRO_ENABLE_MASK_IPV6_LRO); + MLX5_SET(tirc, tirc, lro_max_ip_payload_size, + (MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ - rough_max_l2_l3_hdr_sz) >> 8); + MLX5_SET(tirc, tirc, lro_timeout_period_usecs, lro_param->timeout); +} + +static int mlx5e_hfunc_to_hw(u8 hfunc) +{ + switch (hfunc) { + case ETH_RSS_HASH_TOP: + return MLX5_RX_HASH_FN_TOEPLITZ; + case ETH_RSS_HASH_XOR: + return MLX5_RX_HASH_FN_INVERTED_XOR8; + default: + return MLX5_RX_HASH_FN_NONE; + } +} + +void mlx5e_tir_builder_build_rss(struct mlx5e_tir_builder *builder, + const struct mlx5e_rss_params_hash *rss_hash, + const struct mlx5e_rss_params_traffic_type *rss_tt, + bool inner) +{ + void *tirc = mlx5e_tir_builder_get_tirc(builder); + void *hfso; + + if (builder->modify) + MLX5_SET(modify_tir_in, builder->in, bitmask.hash, 1); + + MLX5_SET(tirc, tirc, rx_hash_fn, mlx5e_hfunc_to_hw(rss_hash->hfunc)); + if (rss_hash->hfunc == ETH_RSS_HASH_TOP) { + const size_t len = MLX5_FLD_SZ_BYTES(tirc, rx_hash_toeplitz_key); + void *rss_key = MLX5_ADDR_OF(tirc, tirc, rx_hash_toeplitz_key); + + MLX5_SET(tirc, tirc, rx_hash_symmetric, 1); + memcpy(rss_key, rss_hash->toeplitz_hash_key, len); + } + + if (inner) + hfso = MLX5_ADDR_OF(tirc, tirc, rx_hash_field_selector_inner); + else + hfso = MLX5_ADDR_OF(tirc, tirc, rx_hash_field_selector_outer); + MLX5_SET(rx_hash_field_select, hfso, l3_prot_type, rss_tt->l3_prot_type); + MLX5_SET(rx_hash_field_select, hfso, l4_prot_type, rss_tt->l4_prot_type); + MLX5_SET(rx_hash_field_select, hfso, selected_fields, rss_tt->rx_hash_fields); +} + +void mlx5e_tir_builder_build_direct(struct mlx5e_tir_builder *builder) +{ + void *tirc = mlx5e_tir_builder_get_tirc(builder); + + WARN_ON(builder->modify); + + MLX5_SET(tirc, tirc, rx_hash_fn, MLX5_RX_HASH_FN_INVERTED_XOR8); +} + +void mlx5e_tir_builder_build_tls(struct mlx5e_tir_builder *builder) +{ + void *tirc = mlx5e_tir_builder_get_tirc(builder); + + WARN_ON(builder->modify); + + MLX5_SET(tirc, tirc, tls_en, 1); + MLX5_SET(tirc, tirc, self_lb_block, + MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST | + MLX5_TIRC_SELF_LB_BLOCK_BLOCK_MULTICAST); +} + +int mlx5e_tir_init(struct mlx5e_tir *tir, struct mlx5e_tir_builder *builder, + struct mlx5_core_dev *mdev, bool reg) +{ + int err; + + tir->mdev = mdev; + + err = mlx5_core_create_tir(tir->mdev, builder->in, &tir->tirn); + if (err) + return err; + + if (reg) { + struct mlx5e_hw_objs *res = &tir->mdev->mlx5e_res.hw_objs; + + mutex_lock(&res->td.list_lock); + list_add(&tir->list, &res->td.tirs_list); + mutex_unlock(&res->td.list_lock); + } else { + INIT_LIST_HEAD(&tir->list); + } + + return 0; +} + +void mlx5e_tir_destroy(struct mlx5e_tir *tir) +{ + struct mlx5e_hw_objs *res = &tir->mdev->mlx5e_res.hw_objs; + + /* Skip mutex if list_del is no-op (the TIR wasn't registered in the + * list). list_empty will never return true for an item of tirs_list, + * and READ_ONCE/WRITE_ONCE in list_empty/list_del guarantee consistency + * of the list->next value. + */ + if (!list_empty(&tir->list)) { + mutex_lock(&res->td.list_lock); + list_del(&tir->list); + mutex_unlock(&res->td.list_lock); + } + + mlx5_core_destroy_tir(tir->mdev, tir->tirn); +} + +int mlx5e_tir_modify(struct mlx5e_tir *tir, struct mlx5e_tir_builder *builder) +{ + return mlx5_core_modify_tir(tir->mdev, tir->tirn, builder->in); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tir.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tir.h new file mode 100644 index 000000000000..e45149a78ed9 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tir.h @@ -0,0 +1,58 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2021, Mellanox Technologies inc. All rights reserved. */ + +#ifndef __MLX5_EN_TIR_H__ +#define __MLX5_EN_TIR_H__ + +#include <linux/kernel.h> + +struct mlx5e_rss_params_hash { + u8 hfunc; + u8 toeplitz_hash_key[40]; +}; + +struct mlx5e_rss_params_traffic_type { + u8 l3_prot_type; + u8 l4_prot_type; + u32 rx_hash_fields; +}; + +struct mlx5e_tir_builder; +struct mlx5e_lro_param; + +struct mlx5e_tir_builder *mlx5e_tir_builder_alloc(bool modify); +void mlx5e_tir_builder_free(struct mlx5e_tir_builder *builder); +void mlx5e_tir_builder_clear(struct mlx5e_tir_builder *builder); + +void mlx5e_tir_builder_build_inline(struct mlx5e_tir_builder *builder, u32 tdn, u32 rqn); +void mlx5e_tir_builder_build_rqt(struct mlx5e_tir_builder *builder, u32 tdn, + u32 rqtn, bool inner_ft_support); +void mlx5e_tir_builder_build_lro(struct mlx5e_tir_builder *builder, + const struct mlx5e_lro_param *lro_param); +void mlx5e_tir_builder_build_rss(struct mlx5e_tir_builder *builder, + const struct mlx5e_rss_params_hash *rss_hash, + const struct mlx5e_rss_params_traffic_type *rss_tt, + bool inner); +void mlx5e_tir_builder_build_direct(struct mlx5e_tir_builder *builder); +void mlx5e_tir_builder_build_tls(struct mlx5e_tir_builder *builder); + +struct mlx5_core_dev; + +struct mlx5e_tir { + struct mlx5_core_dev *mdev; + u32 tirn; + struct list_head list; +}; + +int mlx5e_tir_init(struct mlx5e_tir *tir, struct mlx5e_tir_builder *builder, + struct mlx5_core_dev *mdev, bool reg); +void mlx5e_tir_destroy(struct mlx5e_tir *tir); + +static inline u32 mlx5e_tir_get_tirn(struct mlx5e_tir *tir) +{ + return tir->tirn; +} + +int mlx5e_tir_modify(struct mlx5e_tir *tir, struct mlx5e_tir_builder *builder); + +#endif /* __MLX5_EN_TIR_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c index 7f94508594fb..d54607a42740 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c @@ -92,30 +92,19 @@ static void mlx5e_close_trap_rq(struct mlx5e_rq *rq) static int mlx5e_create_trap_direct_rq_tir(struct mlx5_core_dev *mdev, struct mlx5e_tir *tir, u32 rqn) { - void *tirc; - int inlen; - u32 *in; + struct mlx5e_tir_builder *builder; int err; - inlen = MLX5_ST_SZ_BYTES(create_tir_in); - in = kvzalloc(inlen, GFP_KERNEL); - if (!in) + builder = mlx5e_tir_builder_alloc(false); + if (!builder) return -ENOMEM; - tirc = MLX5_ADDR_OF(create_tir_in, in, ctx); - MLX5_SET(tirc, tirc, transport_domain, mdev->mlx5e_res.hw_objs.td.tdn); - MLX5_SET(tirc, tirc, rx_hash_fn, MLX5_RX_HASH_FN_NONE); - MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_DIRECT); - MLX5_SET(tirc, tirc, inline_rqn, rqn); - err = mlx5e_create_tir(mdev, tir, in); - kvfree(in); + mlx5e_tir_builder_build_inline(builder, mdev->mlx5e_res.hw_objs.td.tdn, rqn); + err = mlx5e_tir_init(tir, builder, mdev, true); - return err; -} + mlx5e_tir_builder_free(builder); -static void mlx5e_destroy_trap_direct_rq_tir(struct mlx5_core_dev *mdev, struct mlx5e_tir *tir) -{ - mlx5e_destroy_tir(mdev, tir); + return err; } static void mlx5e_build_trap_params(struct mlx5_core_dev *mdev, @@ -173,7 +162,7 @@ err_napi_del: void mlx5e_close_trap(struct mlx5e_trap *trap) { - mlx5e_destroy_trap_direct_rq_tir(trap->mdev, &trap->tir); + mlx5e_tir_destroy(&trap->tir); mlx5e_close_trap_rq(&trap->rq); netif_napi_del(&trap->napi); kvfree(trap); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c index 71e8d66fa150..7b562d2c8a19 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c @@ -122,7 +122,7 @@ static int mlx5e_xsk_enable_locked(struct mlx5e_priv *priv, * any Fill Ring entries at the setup stage. */ - err = mlx5e_xsk_redirect_rqt_to_channel(priv, priv->channels.c[ix]); + err = mlx5e_rx_res_xsk_activate(priv->rx_res, &priv->channels, ix); if (unlikely(err)) goto err_deactivate; @@ -169,7 +169,7 @@ static int mlx5e_xsk_disable_locked(struct mlx5e_priv *priv, u16 ix) goto remove_pool; c = priv->channels.c[ix]; - mlx5e_xsk_redirect_rqt_to_drop(priv, ix); + mlx5e_rx_res_xsk_deactivate(priv->rx_res, ix); mlx5e_deactivate_xsk(c); mlx5e_close_xsk(c); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c index a8315f166696..538bc2419bd8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c @@ -126,7 +126,7 @@ int mlx5e_open_xsk(struct mlx5e_priv *priv, struct mlx5e_params *params, /* Create a separate SQ, so that when the buff pool is disabled, we could * close this SQ safely and stop receiving CQEs. In other case, e.g., if * the XDPSQ was used instead, we might run into trouble when the buff pool - * is disabled and then reenabled, but the SQ continues receiving CQEs + * is disabled and then re-enabled, but the SQ continues receiving CQEs * from the old buff pool. */ err = mlx5e_open_xdpsq(c, params, &cparam->xdp_sq, pool, &c->xsksq, true); @@ -183,73 +183,3 @@ void mlx5e_deactivate_xsk(struct mlx5e_channel *c) mlx5e_deactivate_rq(&c->xskrq); /* TX queue is disabled on close. */ } - -static int mlx5e_redirect_xsk_rqt(struct mlx5e_priv *priv, u16 ix, u32 rqn) -{ - struct mlx5e_redirect_rqt_param direct_rrp = { - .is_rss = false, - { - .rqn = rqn, - }, - }; - - u32 rqtn = priv->xsk_tir[ix].rqt.rqtn; - - return mlx5e_redirect_rqt(priv, rqtn, 1, direct_rrp); -} - -int mlx5e_xsk_redirect_rqt_to_channel(struct mlx5e_priv *priv, struct mlx5e_channel *c) -{ - return mlx5e_redirect_xsk_rqt(priv, c->ix, c->xskrq.rqn); -} - -int mlx5e_xsk_redirect_rqt_to_drop(struct mlx5e_priv *priv, u16 ix) -{ - return mlx5e_redirect_xsk_rqt(priv, ix, priv->drop_rq.rqn); -} - -int mlx5e_xsk_redirect_rqts_to_channels(struct mlx5e_priv *priv, struct mlx5e_channels *chs) -{ - int err, i; - - if (!priv->xsk.refcnt) - return 0; - - for (i = 0; i < chs->num; i++) { - struct mlx5e_channel *c = chs->c[i]; - - if (!test_bit(MLX5E_CHANNEL_STATE_XSK, c->state)) - continue; - - err = mlx5e_xsk_redirect_rqt_to_channel(priv, c); - if (unlikely(err)) - goto err_stop; - } - - return 0; - -err_stop: - for (i--; i >= 0; i--) { - if (!test_bit(MLX5E_CHANNEL_STATE_XSK, chs->c[i]->state)) - continue; - - mlx5e_xsk_redirect_rqt_to_drop(priv, i); - } - - return err; -} - -void mlx5e_xsk_redirect_rqts_to_drop(struct mlx5e_priv *priv, struct mlx5e_channels *chs) -{ - int i; - - if (!priv->xsk.refcnt) - return; - - for (i = 0; i < chs->num; i++) { - if (!test_bit(MLX5E_CHANNEL_STATE_XSK, chs->c[i]->state)) - continue; - - mlx5e_xsk_redirect_rqt_to_drop(priv, i); - } -} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.h index ca20f1ff5e39..50e111b85efd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.h @@ -17,9 +17,5 @@ int mlx5e_open_xsk(struct mlx5e_priv *priv, struct mlx5e_params *params, void mlx5e_close_xsk(struct mlx5e_channel *c); void mlx5e_activate_xsk(struct mlx5e_channel *c); void mlx5e_deactivate_xsk(struct mlx5e_channel *c); -int mlx5e_xsk_redirect_rqt_to_channel(struct mlx5e_priv *priv, struct mlx5e_channel *c); -int mlx5e_xsk_redirect_rqt_to_drop(struct mlx5e_priv *priv, u16 ix); -int mlx5e_xsk_redirect_rqts_to_channels(struct mlx5e_priv *priv, struct mlx5e_channels *chs); -void mlx5e_xsk_redirect_rqts_to_drop(struct mlx5e_priv *priv, struct mlx5e_channels *chs); #endif /* __MLX5_EN_XSK_SETUP_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c index e51f60b55daa..4c4ee524176c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c @@ -16,13 +16,13 @@ struct mlx5e_accel_fs_tcp { struct mlx5_flow_handle *default_rules[ACCEL_FS_TCP_NUM_TYPES]; }; -static enum mlx5e_traffic_types fs_accel2tt(enum accel_fs_tcp_type i) +static enum mlx5_traffic_types fs_accel2tt(enum accel_fs_tcp_type i) { switch (i) { case ACCEL_FS_IPV4_TCP: - return MLX5E_TT_IPV4_TCP; + return MLX5_TT_IPV4_TCP; default: /* ACCEL_FS_IPV6_TCP */ - return MLX5E_TT_IPV6_TCP; + return MLX5_TT_IPV6_TCP; } } @@ -161,7 +161,7 @@ static int accel_fs_tcp_add_default_rule(struct mlx5e_priv *priv, fs_tcp = priv->fs.accel_tcp; accel_fs_t = &fs_tcp->tables[type]; - dest = mlx5e_ttc_get_default_dest(priv, fs_accel2tt(type)); + dest = mlx5_ttc_get_default_dest(priv->fs.ttc, fs_accel2tt(type)); rule = mlx5_add_flow_rules(accel_fs_t->t, NULL, &flow_act, &dest, 1); if (IS_ERR(rule)) { err = PTR_ERR(rule); @@ -307,7 +307,7 @@ static int accel_fs_tcp_disable(struct mlx5e_priv *priv) for (i = 0; i < ACCEL_FS_TCP_NUM_TYPES; i++) { /* Modify ttc rules destination to point back to the indir TIRs */ - err = mlx5e_ttc_fwd_default_dest(priv, fs_accel2tt(i)); + err = mlx5_ttc_fwd_default_dest(priv->fs.ttc, fs_accel2tt(i)); if (err) { netdev_err(priv->netdev, "%s: modify ttc[%d] default destination failed, err(%d)\n", @@ -329,7 +329,7 @@ static int accel_fs_tcp_enable(struct mlx5e_priv *priv) dest.ft = priv->fs.accel_tcp->tables[i].t; /* Modify ttc rules destination to point on the accel_fs FTs */ - err = mlx5e_ttc_fwd_dest(priv, fs_accel2tt(i), &dest); + err = mlx5_ttc_fwd_dest(priv->fs.ttc, fs_accel2tt(i), &dest); if (err) { netdev_err(priv->netdev, "%s: modify ttc[%d] destination to accel failed, err(%d)\n", diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c index 34119ce92031..17da23dff0ed 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c @@ -41,11 +41,11 @@ struct mlx5e_ipsec_tx { }; /* IPsec RX flow steering */ -static enum mlx5e_traffic_types fs_esp2tt(enum accel_fs_esp_type i) +static enum mlx5_traffic_types fs_esp2tt(enum accel_fs_esp_type i) { if (i == ACCEL_FS_ESP4) - return MLX5E_TT_IPV4_IPSEC_ESP; - return MLX5E_TT_IPV6_IPSEC_ESP; + return MLX5_TT_IPV4_IPSEC_ESP; + return MLX5_TT_IPV6_IPSEC_ESP; } static int rx_err_add_rule(struct mlx5e_priv *priv, @@ -265,7 +265,8 @@ static int rx_create(struct mlx5e_priv *priv, enum accel_fs_esp_type type) accel_esp = priv->ipsec->rx_fs; fs_prot = &accel_esp->fs_prot[type]; - fs_prot->default_dest = mlx5e_ttc_get_default_dest(priv, fs_esp2tt(type)); + fs_prot->default_dest = + mlx5_ttc_get_default_dest(priv->fs.ttc, fs_esp2tt(type)); err = rx_err_create_ft(priv, fs_prot, &fs_prot->rx_err); if (err) @@ -301,7 +302,7 @@ static int rx_ft_get(struct mlx5e_priv *priv, enum accel_fs_esp_type type) /* connect */ dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; dest.ft = fs_prot->ft; - mlx5e_ttc_fwd_dest(priv, fs_esp2tt(type), &dest); + mlx5_ttc_fwd_dest(priv->fs.ttc, fs_esp2tt(type), &dest); out: mutex_unlock(&fs_prot->prot_mutex); @@ -320,7 +321,7 @@ static void rx_ft_put(struct mlx5e_priv *priv, enum accel_fs_esp_type type) goto out; /* disconnect */ - mlx5e_ttc_fwd_default_dest(priv, fs_esp2tt(type)); + mlx5_ttc_fwd_default_dest(priv->fs.ttc, fs_esp2tt(type)); /* remove FT */ rx_destroy(priv, type); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c index 4e58fade7a60..62abce008c7b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c @@ -49,7 +49,7 @@ struct mlx5e_ktls_offload_context_rx { struct mlx5e_rq_stats *rq_stats; struct mlx5e_tls_sw_stats *sw_stats; struct completion add_ctx; - u32 tirn; + struct mlx5e_tir tir; u32 key_id; u32 rxq; DECLARE_BITMAP(flags, MLX5E_NUM_PRIV_RX_FLAGS); @@ -99,31 +99,22 @@ mlx5e_ktls_rx_resync_create_resp_list(void) return resp_list; } -static int mlx5e_ktls_create_tir(struct mlx5_core_dev *mdev, u32 *tirn, u32 rqtn) +static int mlx5e_ktls_create_tir(struct mlx5_core_dev *mdev, struct mlx5e_tir *tir, u32 rqtn) { - int err, inlen; - void *tirc; - u32 *in; + struct mlx5e_tir_builder *builder; + int err; - inlen = MLX5_ST_SZ_BYTES(create_tir_in); - in = kvzalloc(inlen, GFP_KERNEL); - if (!in) + builder = mlx5e_tir_builder_alloc(false); + if (!builder) return -ENOMEM; - tirc = MLX5_ADDR_OF(create_tir_in, in, ctx); - - MLX5_SET(tirc, tirc, transport_domain, mdev->mlx5e_res.hw_objs.td.tdn); - MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_INDIRECT); - MLX5_SET(tirc, tirc, rx_hash_fn, MLX5_RX_HASH_FN_INVERTED_XOR8); - MLX5_SET(tirc, tirc, indirect_table, rqtn); - MLX5_SET(tirc, tirc, tls_en, 1); - MLX5_SET(tirc, tirc, self_lb_block, - MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST | - MLX5_TIRC_SELF_LB_BLOCK_BLOCK_MULTICAST); + mlx5e_tir_builder_build_rqt(builder, mdev->mlx5e_res.hw_objs.td.tdn, rqtn, false); + mlx5e_tir_builder_build_direct(builder); + mlx5e_tir_builder_build_tls(builder); + err = mlx5e_tir_init(tir, builder, mdev, false); - err = mlx5_core_create_tir(mdev, in, tirn); + mlx5e_tir_builder_free(builder); - kvfree(in); return err; } @@ -139,7 +130,8 @@ static void accel_rule_handle_work(struct work_struct *work) goto out; rule = mlx5e_accel_fs_add_sk(accel_rule->priv, priv_rx->sk, - priv_rx->tirn, MLX5_FS_DEFAULT_FLOW_TAG); + mlx5e_tir_get_tirn(&priv_rx->tir), + MLX5_FS_DEFAULT_FLOW_TAG); if (!IS_ERR_OR_NULL(rule)) accel_rule->rule = rule; out: @@ -173,8 +165,8 @@ post_static_params(struct mlx5e_icosq *sq, pi = mlx5e_icosq_get_next_pi(sq, num_wqebbs); wqe = MLX5E_TLS_FETCH_SET_STATIC_PARAMS_WQE(sq, pi); mlx5e_ktls_build_static_params(wqe, sq->pc, sq->sqn, &priv_rx->crypto_info, - priv_rx->tirn, priv_rx->key_id, - priv_rx->resync.seq, false, + mlx5e_tir_get_tirn(&priv_rx->tir), + priv_rx->key_id, priv_rx->resync.seq, false, TLS_OFFLOAD_CTX_DIR_RX); wi = (struct mlx5e_icosq_wqe_info) { .wqe_type = MLX5E_ICOSQ_WQE_UMR_TLS, @@ -202,8 +194,9 @@ post_progress_params(struct mlx5e_icosq *sq, pi = mlx5e_icosq_get_next_pi(sq, num_wqebbs); wqe = MLX5E_TLS_FETCH_SET_PROGRESS_PARAMS_WQE(sq, pi); - mlx5e_ktls_build_progress_params(wqe, sq->pc, sq->sqn, priv_rx->tirn, false, - next_record_tcp_sn, + mlx5e_ktls_build_progress_params(wqe, sq->pc, sq->sqn, + mlx5e_tir_get_tirn(&priv_rx->tir), + false, next_record_tcp_sn, TLS_OFFLOAD_CTX_DIR_RX); wi = (struct mlx5e_icosq_wqe_info) { .wqe_type = MLX5E_ICOSQ_WQE_SET_PSV_TLS, @@ -325,7 +318,7 @@ resync_post_get_progress_params(struct mlx5e_icosq *sq, psv = &wqe->psv; psv->num_psv = 1 << 4; psv->l_key = sq->channel->mkey_be; - psv->psv_index[0] = cpu_to_be32(priv_rx->tirn); + psv->psv_index[0] = cpu_to_be32(mlx5e_tir_get_tirn(&priv_rx->tir)); psv->va = cpu_to_be64(buf->dma_addr); wi = (struct mlx5e_icosq_wqe_info) { @@ -635,9 +628,9 @@ int mlx5e_ktls_add_rx(struct net_device *netdev, struct sock *sk, priv_rx->sw_stats = &priv->tls->sw_stats; mlx5e_set_ktls_rx_priv_ctx(tls_ctx, priv_rx); - rqtn = priv->direct_tir[rxq].rqt.rqtn; + rqtn = mlx5e_rx_res_get_rqtn_direct(priv->rx_res, rxq); - err = mlx5e_ktls_create_tir(mdev, &priv_rx->tirn, rqtn); + err = mlx5e_ktls_create_tir(mdev, &priv_rx->tir, rqtn); if (err) goto err_create_tir; @@ -658,7 +651,7 @@ int mlx5e_ktls_add_rx(struct net_device *netdev, struct sock *sk, return 0; err_post_wqes: - mlx5_core_destroy_tir(mdev, priv_rx->tirn); + mlx5e_tir_destroy(&priv_rx->tir); err_create_tir: mlx5_ktls_destroy_key(mdev, priv_rx->key_id); err_create_key: @@ -693,7 +686,7 @@ void mlx5e_ktls_del_rx(struct net_device *netdev, struct tls_context *tls_ctx) if (priv_rx->rule.rule) mlx5e_accel_fs_del_sk(priv_rx->rule.rule); - mlx5_core_destroy_tir(mdev, priv_rx->tirn); + mlx5e_tir_destroy(&priv_rx->tir); mlx5_ktls_destroy_key(mdev, priv_rx->key_id); /* priv_rx should normally be freed here, but if there is an outstanding * GET_PSV, deallocation will be delayed until the CQE for GET_PSV is diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c index 25403af32859..fe5d82fa6e92 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c @@ -98,17 +98,17 @@ struct arfs_rule { for (j = 0; j < ARFS_HASH_SIZE; j++) \ hlist_for_each_entry_safe(hn, tmp, &hash[j], hlist) -static enum mlx5e_traffic_types arfs_get_tt(enum arfs_type type) +static enum mlx5_traffic_types arfs_get_tt(enum arfs_type type) { switch (type) { case ARFS_IPV4_TCP: - return MLX5E_TT_IPV4_TCP; + return MLX5_TT_IPV4_TCP; case ARFS_IPV4_UDP: - return MLX5E_TT_IPV4_UDP; + return MLX5_TT_IPV4_UDP; case ARFS_IPV6_TCP: - return MLX5E_TT_IPV6_TCP; + return MLX5_TT_IPV6_TCP; case ARFS_IPV6_UDP: - return MLX5E_TT_IPV6_UDP; + return MLX5_TT_IPV6_UDP; default: return -EINVAL; } @@ -120,7 +120,7 @@ static int arfs_disable(struct mlx5e_priv *priv) for (i = 0; i < ARFS_NUM_TYPES; i++) { /* Modify ttc rules destination back to their default */ - err = mlx5e_ttc_fwd_default_dest(priv, arfs_get_tt(i)); + err = mlx5_ttc_fwd_default_dest(priv->fs.ttc, arfs_get_tt(i)); if (err) { netdev_err(priv->netdev, "%s: modify ttc[%d] default destination failed, err(%d)\n", @@ -149,7 +149,7 @@ int mlx5e_arfs_enable(struct mlx5e_priv *priv) for (i = 0; i < ARFS_NUM_TYPES; i++) { dest.ft = priv->fs.arfs->arfs_tables[i].ft.t; /* Modify ttc rules destination to point on the aRFS FTs */ - err = mlx5e_ttc_fwd_dest(priv, arfs_get_tt(i), &dest); + err = mlx5_ttc_fwd_dest(priv->fs.ttc, arfs_get_tt(i), &dest); if (err) { netdev_err(priv->netdev, "%s: modify ttc[%d] dest to arfs, failed err(%d)\n", @@ -192,10 +192,9 @@ static int arfs_add_default_rule(struct mlx5e_priv *priv, enum arfs_type type) { struct arfs_table *arfs_t = &priv->fs.arfs->arfs_tables[type]; - struct mlx5e_tir *tir = priv->indir_tir; struct mlx5_flow_destination dest = {}; MLX5_DECLARE_FLOW_ACT(flow_act); - enum mlx5e_traffic_types tt; + enum mlx5_traffic_types tt; int err = 0; dest.type = MLX5_FLOW_DESTINATION_TYPE_TIR; @@ -206,10 +205,10 @@ static int arfs_add_default_rule(struct mlx5e_priv *priv, return -EINVAL; } - /* FIXME: Must use mlx5e_ttc_get_default_dest(), + /* FIXME: Must use mlx5_ttc_get_default_dest(), * but can't since TTC default is not setup yet ! */ - dest.tir_num = tir[tt].tirn; + dest.tir_num = mlx5e_rx_res_get_tirn_rss(priv->rx_res, tt); arfs_t->default_rule = mlx5_add_flow_rules(arfs_t->ft.t, NULL, &flow_act, &dest, 1); @@ -553,7 +552,7 @@ static struct mlx5_flow_handle *arfs_add_rule(struct mlx5e_priv *priv, 16); } dest.type = MLX5_FLOW_DESTINATION_TYPE_TIR; - dest.tir_num = priv->direct_tir[arfs_rule->rxq].tirn; + dest.tir_num = mlx5e_rx_res_get_tirn_direct(priv->rx_res, arfs_rule->rxq); rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1); if (IS_ERR(rule)) { err = PTR_ERR(rule); @@ -576,7 +575,7 @@ static void arfs_modify_rule_rq(struct mlx5e_priv *priv, int err = 0; dst.type = MLX5_FLOW_DESTINATION_TYPE_TIR; - dst.tir_num = priv->direct_tir[rxq].tirn; + dst.tir_num = mlx5e_rx_res_get_tirn_direct(priv->rx_res, rxq); err = mlx5_modify_rule_destination(rule, &dst, NULL); if (err) netdev_warn(priv->netdev, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c index 8c166ee56d8b..84eb7201c142 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c @@ -33,36 +33,9 @@ #include "en.h" /* mlx5e global resources should be placed in this file. - * Global resources are common to all the netdevices crated on the same nic. + * Global resources are common to all the netdevices created on the same nic. */ -int mlx5e_create_tir(struct mlx5_core_dev *mdev, struct mlx5e_tir *tir, u32 *in) -{ - struct mlx5e_hw_objs *res = &mdev->mlx5e_res.hw_objs; - int err; - - err = mlx5_core_create_tir(mdev, in, &tir->tirn); - if (err) - return err; - - mutex_lock(&res->td.list_lock); - list_add(&tir->list, &res->td.tirs_list); - mutex_unlock(&res->td.list_lock); - - return 0; -} - -void mlx5e_destroy_tir(struct mlx5_core_dev *mdev, - struct mlx5e_tir *tir) -{ - struct mlx5e_hw_objs *res = &mdev->mlx5e_res.hw_objs; - - mutex_lock(&res->td.list_lock); - mlx5_core_destroy_tir(mdev, tir->tirn); - list_del(&tir->list); - mutex_unlock(&res->td.list_lock); -} - void mlx5e_mkey_set_relaxed_ordering(struct mlx5_core_dev *mdev, void *mkc) { bool ro_pci_enable = pcie_relaxed_ordering_enabled(mdev->pdev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index bd72572e03d1..2cfd12953909 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -420,6 +420,7 @@ int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv, unsigned int count = ch->combined_count; struct mlx5e_params new_params; bool arfs_enabled; + int rss_cnt; bool opened; int err = 0; @@ -455,6 +456,27 @@ int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv, goto out; } + /* Don't allow changing the number of channels if non-default RSS contexts exist, + * the kernel doesn't protect against set_channels operations that break them. + */ + rss_cnt = mlx5e_rx_res_rss_cnt(priv->rx_res) - 1; + if (rss_cnt) { + err = -EINVAL; + netdev_err(priv->netdev, "%s: Non-default RSS contexts exist (%d), cannot change the number of channels\n", + __func__, rss_cnt); + goto out; + } + + /* Don't allow changing the number of channels if MQPRIO mode channel offload is active, + * because it defines a partition over the channels queues. + */ + if (cur_params->mqprio.mode == TC_MQPRIO_MODE_CHANNEL) { + err = -EINVAL; + netdev_err(priv->netdev, "%s: MQPRIO mode channel offload is active, cannot change the number of channels\n", + __func__); + goto out; + } + new_params = *cur_params; new_params.num_channels = count; @@ -512,7 +534,9 @@ int mlx5e_ethtool_get_coalesce(struct mlx5e_priv *priv, } static int mlx5e_get_coalesce(struct net_device *netdev, - struct ethtool_coalesce *coal) + struct ethtool_coalesce *coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct mlx5e_priv *priv = netdev_priv(netdev); @@ -630,7 +654,9 @@ int mlx5e_ethtool_set_coalesce(struct mlx5e_priv *priv, } static int mlx5e_set_coalesce(struct net_device *netdev, - struct ethtool_coalesce *coal) + struct ethtool_coalesce *coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct mlx5e_priv *priv = netdev_priv(netdev); @@ -1172,7 +1198,7 @@ static int mlx5e_set_link_ksettings(struct net_device *netdev, u32 mlx5e_ethtool_get_rxfh_key_size(struct mlx5e_priv *priv) { - return sizeof(priv->rss_params.toeplitz_hash_key); + return sizeof_field(struct mlx5e_rss_params_hash, toeplitz_hash_key); } static u32 mlx5e_get_rxfh_key_size(struct net_device *netdev) @@ -1194,88 +1220,64 @@ static u32 mlx5e_get_rxfh_indir_size(struct net_device *netdev) return mlx5e_ethtool_get_rxfh_indir_size(priv); } -int mlx5e_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, - u8 *hfunc) +static int mlx5e_get_rxfh_context(struct net_device *dev, u32 *indir, + u8 *key, u8 *hfunc, u32 rss_context) { - struct mlx5e_priv *priv = netdev_priv(netdev); - struct mlx5e_rss_params *rss = &priv->rss_params; - - if (indir) - memcpy(indir, rss->indirection_rqt, - sizeof(rss->indirection_rqt)); - - if (key) - memcpy(key, rss->toeplitz_hash_key, - sizeof(rss->toeplitz_hash_key)); - - if (hfunc) - *hfunc = rss->hfunc; + struct mlx5e_priv *priv = netdev_priv(dev); + int err; - return 0; + mutex_lock(&priv->state_lock); + err = mlx5e_rx_res_rss_get_rxfh(priv->rx_res, rss_context, indir, key, hfunc); + mutex_unlock(&priv->state_lock); + return err; } -int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir, - const u8 *key, const u8 hfunc) +static int mlx5e_set_rxfh_context(struct net_device *dev, const u32 *indir, + const u8 *key, const u8 hfunc, + u32 *rss_context, bool delete) { struct mlx5e_priv *priv = netdev_priv(dev); - struct mlx5e_rss_params *rss = &priv->rss_params; - int inlen = MLX5_ST_SZ_BYTES(modify_tir_in); - bool refresh_tirs = false; - bool refresh_rqt = false; - void *in; - - if ((hfunc != ETH_RSS_HASH_NO_CHANGE) && - (hfunc != ETH_RSS_HASH_XOR) && - (hfunc != ETH_RSS_HASH_TOP)) - return -EINVAL; - - in = kvzalloc(inlen, GFP_KERNEL); - if (!in) - return -ENOMEM; + int err; mutex_lock(&priv->state_lock); - - if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != rss->hfunc) { - rss->hfunc = hfunc; - refresh_rqt = true; - refresh_tirs = true; - } - - if (indir) { - memcpy(rss->indirection_rqt, indir, - sizeof(rss->indirection_rqt)); - refresh_rqt = true; + if (delete) { + err = mlx5e_rx_res_rss_destroy(priv->rx_res, *rss_context); + goto unlock; } - if (key) { - memcpy(rss->toeplitz_hash_key, key, - sizeof(rss->toeplitz_hash_key)); - refresh_tirs = refresh_tirs || rss->hfunc == ETH_RSS_HASH_TOP; - } + if (*rss_context == ETH_RXFH_CONTEXT_ALLOC) { + unsigned int count = priv->channels.params.num_channels; - if (refresh_rqt && test_bit(MLX5E_STATE_OPENED, &priv->state)) { - struct mlx5e_redirect_rqt_param rrp = { - .is_rss = true, - { - .rss = { - .hfunc = rss->hfunc, - .channels = &priv->channels, - }, - }, - }; - u32 rqtn = priv->indir_rqt.rqtn; - - mlx5e_redirect_rqt(priv, rqtn, MLX5E_INDIR_RQT_SIZE, rrp); + err = mlx5e_rx_res_rss_init(priv->rx_res, rss_context, count); + if (err) + goto unlock; } - if (refresh_tirs) - mlx5e_modify_tirs_hash(priv, in); + err = mlx5e_rx_res_rss_set_rxfh(priv->rx_res, *rss_context, indir, key, + hfunc == ETH_RSS_HASH_NO_CHANGE ? NULL : &hfunc); +unlock: mutex_unlock(&priv->state_lock); + return err; +} - kvfree(in); +int mlx5e_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, + u8 *hfunc) +{ + return mlx5e_get_rxfh_context(netdev, indir, key, hfunc, 0); +} - return 0; +int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir, + const u8 *key, const u8 hfunc) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + int err; + + mutex_lock(&priv->state_lock); + err = mlx5e_rx_res_rss_set_rxfh(priv->rx_res, 0, indir, key, + hfunc == ETH_RSS_HASH_NO_CHANGE ? NULL : &hfunc); + mutex_unlock(&priv->state_lock); + return err; } #define MLX5E_PFC_PREVEN_AUTO_TOUT_MSEC 100 @@ -2358,6 +2360,8 @@ const struct ethtool_ops mlx5e_ethtool_ops = { .get_rxfh_indir_size = mlx5e_get_rxfh_indir_size, .get_rxfh = mlx5e_get_rxfh, .set_rxfh = mlx5e_set_rxfh, + .get_rxfh_context = mlx5e_get_rxfh_context, + .set_rxfh_context = mlx5e_set_rxfh_context, .get_rxnfc = mlx5e_get_rxnfc, .set_rxnfc = mlx5e_set_rxnfc, .get_tunable = mlx5e_get_tunable, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c index 0b75fab41ae8..c06b4b938ae7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c @@ -718,7 +718,7 @@ static int mlx5e_add_promisc_rule(struct mlx5e_priv *priv) if (!spec) return -ENOMEM; dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; - dest.ft = priv->fs.ttc.ft.t; + dest.ft = mlx5_get_ttc_flow_table(priv->fs.ttc); rule_p = &priv->fs.promisc.rule; *rule_p = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1); @@ -854,593 +854,59 @@ void mlx5e_destroy_flow_table(struct mlx5e_flow_table *ft) ft->t = NULL; } -static void mlx5e_cleanup_ttc_rules(struct mlx5e_ttc_table *ttc) -{ - int i; - - for (i = 0; i < MLX5E_NUM_TT; i++) { - if (!IS_ERR_OR_NULL(ttc->rules[i].rule)) { - mlx5_del_flow_rules(ttc->rules[i].rule); - ttc->rules[i].rule = NULL; - } - } - - for (i = 0; i < MLX5E_NUM_TUNNEL_TT; i++) { - if (!IS_ERR_OR_NULL(ttc->tunnel_rules[i])) { - mlx5_del_flow_rules(ttc->tunnel_rules[i]); - ttc->tunnel_rules[i] = NULL; - } - } -} - -struct mlx5e_etype_proto { - u16 etype; - u8 proto; -}; - -static struct mlx5e_etype_proto ttc_rules[] = { - [MLX5E_TT_IPV4_TCP] = { - .etype = ETH_P_IP, - .proto = IPPROTO_TCP, - }, - [MLX5E_TT_IPV6_TCP] = { - .etype = ETH_P_IPV6, - .proto = IPPROTO_TCP, - }, - [MLX5E_TT_IPV4_UDP] = { - .etype = ETH_P_IP, - .proto = IPPROTO_UDP, - }, - [MLX5E_TT_IPV6_UDP] = { - .etype = ETH_P_IPV6, - .proto = IPPROTO_UDP, - }, - [MLX5E_TT_IPV4_IPSEC_AH] = { - .etype = ETH_P_IP, - .proto = IPPROTO_AH, - }, - [MLX5E_TT_IPV6_IPSEC_AH] = { - .etype = ETH_P_IPV6, - .proto = IPPROTO_AH, - }, - [MLX5E_TT_IPV4_IPSEC_ESP] = { - .etype = ETH_P_IP, - .proto = IPPROTO_ESP, - }, - [MLX5E_TT_IPV6_IPSEC_ESP] = { - .etype = ETH_P_IPV6, - .proto = IPPROTO_ESP, - }, - [MLX5E_TT_IPV4] = { - .etype = ETH_P_IP, - .proto = 0, - }, - [MLX5E_TT_IPV6] = { - .etype = ETH_P_IPV6, - .proto = 0, - }, - [MLX5E_TT_ANY] = { - .etype = 0, - .proto = 0, - }, -}; - -static struct mlx5e_etype_proto ttc_tunnel_rules[] = { - [MLX5E_TT_IPV4_GRE] = { - .etype = ETH_P_IP, - .proto = IPPROTO_GRE, - }, - [MLX5E_TT_IPV6_GRE] = { - .etype = ETH_P_IPV6, - .proto = IPPROTO_GRE, - }, - [MLX5E_TT_IPV4_IPIP] = { - .etype = ETH_P_IP, - .proto = IPPROTO_IPIP, - }, - [MLX5E_TT_IPV6_IPIP] = { - .etype = ETH_P_IPV6, - .proto = IPPROTO_IPIP, - }, - [MLX5E_TT_IPV4_IPV6] = { - .etype = ETH_P_IP, - .proto = IPPROTO_IPV6, - }, - [MLX5E_TT_IPV6_IPV6] = { - .etype = ETH_P_IPV6, - .proto = IPPROTO_IPV6, - }, - -}; - -u8 mlx5e_get_proto_by_tunnel_type(enum mlx5e_tunnel_types tt) -{ - return ttc_tunnel_rules[tt].proto; -} - -static bool mlx5e_tunnel_proto_supported_rx(struct mlx5_core_dev *mdev, u8 proto_type) -{ - switch (proto_type) { - case IPPROTO_GRE: - return MLX5_CAP_ETH(mdev, tunnel_stateless_gre); - case IPPROTO_IPIP: - case IPPROTO_IPV6: - return (MLX5_CAP_ETH(mdev, tunnel_stateless_ip_over_ip) || - MLX5_CAP_ETH(mdev, tunnel_stateless_ip_over_ip_rx)); - default: - return false; - } -} - -static bool mlx5e_tunnel_any_rx_proto_supported(struct mlx5_core_dev *mdev) -{ - int tt; - - for (tt = 0; tt < MLX5E_NUM_TUNNEL_TT; tt++) { - if (mlx5e_tunnel_proto_supported_rx(mdev, ttc_tunnel_rules[tt].proto)) - return true; - } - return false; -} - -bool mlx5e_tunnel_inner_ft_supported(struct mlx5_core_dev *mdev) -{ - return (mlx5e_tunnel_any_rx_proto_supported(mdev) && - MLX5_CAP_FLOWTABLE_NIC_RX(mdev, ft_field_support.inner_ip_version)); -} - -static u8 mlx5e_etype_to_ipv(u16 ethertype) -{ - if (ethertype == ETH_P_IP) - return 4; - - if (ethertype == ETH_P_IPV6) - return 6; - - return 0; -} - -static struct mlx5_flow_handle * -mlx5e_generate_ttc_rule(struct mlx5e_priv *priv, - struct mlx5_flow_table *ft, - struct mlx5_flow_destination *dest, - u16 etype, - u8 proto) -{ - int match_ipv_outer = MLX5_CAP_FLOWTABLE_NIC_RX(priv->mdev, ft_field_support.outer_ip_version); - MLX5_DECLARE_FLOW_ACT(flow_act); - struct mlx5_flow_handle *rule; - struct mlx5_flow_spec *spec; - int err = 0; - u8 ipv; - - spec = kvzalloc(sizeof(*spec), GFP_KERNEL); - if (!spec) - return ERR_PTR(-ENOMEM); - - if (proto) { - spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; - MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.ip_protocol); - MLX5_SET(fte_match_param, spec->match_value, outer_headers.ip_protocol, proto); - } - - ipv = mlx5e_etype_to_ipv(etype); - if (match_ipv_outer && ipv) { - spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; - MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.ip_version); - MLX5_SET(fte_match_param, spec->match_value, outer_headers.ip_version, ipv); - } else if (etype) { - spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; - MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.ethertype); - MLX5_SET(fte_match_param, spec->match_value, outer_headers.ethertype, etype); - } - - rule = mlx5_add_flow_rules(ft, spec, &flow_act, dest, 1); - if (IS_ERR(rule)) { - err = PTR_ERR(rule); - netdev_err(priv->netdev, "%s: add rule failed\n", __func__); - } - - kvfree(spec); - return err ? ERR_PTR(err) : rule; -} - -static int mlx5e_generate_ttc_table_rules(struct mlx5e_priv *priv, - struct ttc_params *params, - struct mlx5e_ttc_table *ttc) -{ - struct mlx5_flow_destination dest = {}; - struct mlx5_flow_handle **trules; - struct mlx5e_ttc_rule *rules; - struct mlx5_flow_table *ft; - int tt; - int err; - - ft = ttc->ft.t; - rules = ttc->rules; - - dest.type = MLX5_FLOW_DESTINATION_TYPE_TIR; - for (tt = 0; tt < MLX5E_NUM_TT; tt++) { - struct mlx5e_ttc_rule *rule = &rules[tt]; - - if (tt == MLX5E_TT_ANY) - dest.tir_num = params->any_tt_tirn; - else - dest.tir_num = params->indir_tirn[tt]; - - rule->rule = mlx5e_generate_ttc_rule(priv, ft, &dest, - ttc_rules[tt].etype, - ttc_rules[tt].proto); - if (IS_ERR(rule->rule)) { - err = PTR_ERR(rule->rule); - rule->rule = NULL; - goto del_rules; - } - rule->default_dest = dest; - } - - if (!params->inner_ttc || !mlx5e_tunnel_inner_ft_supported(priv->mdev)) - return 0; - - trules = ttc->tunnel_rules; - dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; - dest.ft = params->inner_ttc->ft.t; - for (tt = 0; tt < MLX5E_NUM_TUNNEL_TT; tt++) { - if (!mlx5e_tunnel_proto_supported_rx(priv->mdev, - ttc_tunnel_rules[tt].proto)) - continue; - trules[tt] = mlx5e_generate_ttc_rule(priv, ft, &dest, - ttc_tunnel_rules[tt].etype, - ttc_tunnel_rules[tt].proto); - if (IS_ERR(trules[tt])) { - err = PTR_ERR(trules[tt]); - trules[tt] = NULL; - goto del_rules; - } - } - - return 0; - -del_rules: - mlx5e_cleanup_ttc_rules(ttc); - return err; -} - -static int mlx5e_create_ttc_table_groups(struct mlx5e_ttc_table *ttc, - bool use_ipv) -{ - int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); - struct mlx5e_flow_table *ft = &ttc->ft; - int ix = 0; - u32 *in; - int err; - u8 *mc; - - ft->g = kcalloc(MLX5E_TTC_NUM_GROUPS, - sizeof(*ft->g), GFP_KERNEL); - if (!ft->g) - return -ENOMEM; - in = kvzalloc(inlen, GFP_KERNEL); - if (!in) { - kfree(ft->g); - ft->g = NULL; - return -ENOMEM; - } - - /* L4 Group */ - mc = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria); - MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.ip_protocol); - if (use_ipv) - MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.ip_version); - else - MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.ethertype); - MLX5_SET_CFG(in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS); - MLX5_SET_CFG(in, start_flow_index, ix); - ix += MLX5E_TTC_GROUP1_SIZE; - MLX5_SET_CFG(in, end_flow_index, ix - 1); - ft->g[ft->num_groups] = mlx5_create_flow_group(ft->t, in); - if (IS_ERR(ft->g[ft->num_groups])) - goto err; - ft->num_groups++; - - /* L3 Group */ - MLX5_SET(fte_match_param, mc, outer_headers.ip_protocol, 0); - MLX5_SET_CFG(in, start_flow_index, ix); - ix += MLX5E_TTC_GROUP2_SIZE; - MLX5_SET_CFG(in, end_flow_index, ix - 1); - ft->g[ft->num_groups] = mlx5_create_flow_group(ft->t, in); - if (IS_ERR(ft->g[ft->num_groups])) - goto err; - ft->num_groups++; - - /* Any Group */ - memset(in, 0, inlen); - MLX5_SET_CFG(in, start_flow_index, ix); - ix += MLX5E_TTC_GROUP3_SIZE; - MLX5_SET_CFG(in, end_flow_index, ix - 1); - ft->g[ft->num_groups] = mlx5_create_flow_group(ft->t, in); - if (IS_ERR(ft->g[ft->num_groups])) - goto err; - ft->num_groups++; - - kvfree(in); - return 0; - -err: - err = PTR_ERR(ft->g[ft->num_groups]); - ft->g[ft->num_groups] = NULL; - kvfree(in); - - return err; -} - -static struct mlx5_flow_handle * -mlx5e_generate_inner_ttc_rule(struct mlx5e_priv *priv, - struct mlx5_flow_table *ft, - struct mlx5_flow_destination *dest, - u16 etype, u8 proto) -{ - MLX5_DECLARE_FLOW_ACT(flow_act); - struct mlx5_flow_handle *rule; - struct mlx5_flow_spec *spec; - int err = 0; - u8 ipv; - - spec = kvzalloc(sizeof(*spec), GFP_KERNEL); - if (!spec) - return ERR_PTR(-ENOMEM); - - ipv = mlx5e_etype_to_ipv(etype); - if (etype && ipv) { - spec->match_criteria_enable = MLX5_MATCH_INNER_HEADERS; - MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, inner_headers.ip_version); - MLX5_SET(fte_match_param, spec->match_value, inner_headers.ip_version, ipv); - } - - if (proto) { - spec->match_criteria_enable = MLX5_MATCH_INNER_HEADERS; - MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, inner_headers.ip_protocol); - MLX5_SET(fte_match_param, spec->match_value, inner_headers.ip_protocol, proto); - } - - rule = mlx5_add_flow_rules(ft, spec, &flow_act, dest, 1); - if (IS_ERR(rule)) { - err = PTR_ERR(rule); - netdev_err(priv->netdev, "%s: add rule failed\n", __func__); - } - - kvfree(spec); - return err ? ERR_PTR(err) : rule; -} - -static int mlx5e_generate_inner_ttc_table_rules(struct mlx5e_priv *priv, - struct ttc_params *params, - struct mlx5e_ttc_table *ttc) -{ - struct mlx5_flow_destination dest = {}; - struct mlx5e_ttc_rule *rules; - struct mlx5_flow_table *ft; - int err; - int tt; - - ft = ttc->ft.t; - rules = ttc->rules; - dest.type = MLX5_FLOW_DESTINATION_TYPE_TIR; - - for (tt = 0; tt < MLX5E_NUM_TT; tt++) { - struct mlx5e_ttc_rule *rule = &rules[tt]; - - if (tt == MLX5E_TT_ANY) - dest.tir_num = params->any_tt_tirn; - else - dest.tir_num = params->indir_tirn[tt]; - - rule->rule = mlx5e_generate_inner_ttc_rule(priv, ft, &dest, - ttc_rules[tt].etype, - ttc_rules[tt].proto); - if (IS_ERR(rule->rule)) { - err = PTR_ERR(rule->rule); - rule->rule = NULL; - goto del_rules; - } - rule->default_dest = dest; - } - - return 0; - -del_rules: - - mlx5e_cleanup_ttc_rules(ttc); - return err; -} - -static int mlx5e_create_inner_ttc_table_groups(struct mlx5e_ttc_table *ttc) -{ - int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); - struct mlx5e_flow_table *ft = &ttc->ft; - int ix = 0; - u32 *in; - int err; - u8 *mc; - - ft->g = kcalloc(MLX5E_INNER_TTC_NUM_GROUPS, sizeof(*ft->g), GFP_KERNEL); - if (!ft->g) - return -ENOMEM; - in = kvzalloc(inlen, GFP_KERNEL); - if (!in) { - kfree(ft->g); - ft->g = NULL; - return -ENOMEM; - } - - /* L4 Group */ - mc = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria); - MLX5_SET_TO_ONES(fte_match_param, mc, inner_headers.ip_protocol); - MLX5_SET_TO_ONES(fte_match_param, mc, inner_headers.ip_version); - MLX5_SET_CFG(in, match_criteria_enable, MLX5_MATCH_INNER_HEADERS); - MLX5_SET_CFG(in, start_flow_index, ix); - ix += MLX5E_INNER_TTC_GROUP1_SIZE; - MLX5_SET_CFG(in, end_flow_index, ix - 1); - ft->g[ft->num_groups] = mlx5_create_flow_group(ft->t, in); - if (IS_ERR(ft->g[ft->num_groups])) - goto err; - ft->num_groups++; - - /* L3 Group */ - MLX5_SET(fte_match_param, mc, inner_headers.ip_protocol, 0); - MLX5_SET_CFG(in, start_flow_index, ix); - ix += MLX5E_INNER_TTC_GROUP2_SIZE; - MLX5_SET_CFG(in, end_flow_index, ix - 1); - ft->g[ft->num_groups] = mlx5_create_flow_group(ft->t, in); - if (IS_ERR(ft->g[ft->num_groups])) - goto err; - ft->num_groups++; - - /* Any Group */ - memset(in, 0, inlen); - MLX5_SET_CFG(in, start_flow_index, ix); - ix += MLX5E_INNER_TTC_GROUP3_SIZE; - MLX5_SET_CFG(in, end_flow_index, ix - 1); - ft->g[ft->num_groups] = mlx5_create_flow_group(ft->t, in); - if (IS_ERR(ft->g[ft->num_groups])) - goto err; - ft->num_groups++; - - kvfree(in); - return 0; - -err: - err = PTR_ERR(ft->g[ft->num_groups]); - ft->g[ft->num_groups] = NULL; - kvfree(in); - - return err; -} - -void mlx5e_set_ttc_basic_params(struct mlx5e_priv *priv, - struct ttc_params *ttc_params) -{ - ttc_params->any_tt_tirn = priv->direct_tir[0].tirn; - ttc_params->inner_ttc = &priv->fs.inner_ttc; -} - -void mlx5e_set_inner_ttc_ft_params(struct ttc_params *ttc_params) +static void mlx5e_set_inner_ttc_params(struct mlx5e_priv *priv, + struct ttc_params *ttc_params) { struct mlx5_flow_table_attr *ft_attr = &ttc_params->ft_attr; + int tt; - ft_attr->max_fte = MLX5E_INNER_TTC_TABLE_SIZE; + memset(ttc_params, 0, sizeof(*ttc_params)); + ttc_params->ns = mlx5_get_flow_namespace(priv->mdev, + MLX5_FLOW_NAMESPACE_KERNEL); ft_attr->level = MLX5E_INNER_TTC_FT_LEVEL; ft_attr->prio = MLX5E_NIC_PRIO; + + for (tt = 0; tt < MLX5_NUM_TT; tt++) { + ttc_params->dests[tt].type = MLX5_FLOW_DESTINATION_TYPE_TIR; + ttc_params->dests[tt].tir_num = + tt == MLX5_TT_ANY ? + mlx5e_rx_res_get_tirn_direct(priv->rx_res, 0) : + mlx5e_rx_res_get_tirn_rss_inner(priv->rx_res, + tt); + } } -void mlx5e_set_ttc_ft_params(struct ttc_params *ttc_params) +void mlx5e_set_ttc_params(struct mlx5e_priv *priv, + struct ttc_params *ttc_params, bool tunnel) { struct mlx5_flow_table_attr *ft_attr = &ttc_params->ft_attr; + int tt; - ft_attr->max_fte = MLX5E_TTC_TABLE_SIZE; + memset(ttc_params, 0, sizeof(*ttc_params)); + ttc_params->ns = mlx5_get_flow_namespace(priv->mdev, + MLX5_FLOW_NAMESPACE_KERNEL); ft_attr->level = MLX5E_TTC_FT_LEVEL; ft_attr->prio = MLX5E_NIC_PRIO; -} - -int mlx5e_create_inner_ttc_table(struct mlx5e_priv *priv, struct ttc_params *params, - struct mlx5e_ttc_table *ttc) -{ - struct mlx5e_flow_table *ft = &ttc->ft; - int err; - if (!mlx5e_tunnel_inner_ft_supported(priv->mdev)) - return 0; - - ft->t = mlx5_create_flow_table(priv->fs.ns, ¶ms->ft_attr); - if (IS_ERR(ft->t)) { - err = PTR_ERR(ft->t); - ft->t = NULL; - return err; + for (tt = 0; tt < MLX5_NUM_TT; tt++) { + ttc_params->dests[tt].type = MLX5_FLOW_DESTINATION_TYPE_TIR; + ttc_params->dests[tt].tir_num = + tt == MLX5_TT_ANY ? + mlx5e_rx_res_get_tirn_direct(priv->rx_res, 0) : + mlx5e_rx_res_get_tirn_rss(priv->rx_res, tt); } - err = mlx5e_create_inner_ttc_table_groups(ttc); - if (err) - goto err; - - err = mlx5e_generate_inner_ttc_table_rules(priv, params, ttc); - if (err) - goto err; - - return 0; - -err: - mlx5e_destroy_flow_table(ft); - return err; -} - -void mlx5e_destroy_inner_ttc_table(struct mlx5e_priv *priv, - struct mlx5e_ttc_table *ttc) -{ - if (!mlx5e_tunnel_inner_ft_supported(priv->mdev)) + ttc_params->inner_ttc = tunnel; + if (!tunnel || !mlx5_tunnel_inner_ft_supported(priv->mdev)) return; - mlx5e_cleanup_ttc_rules(ttc); - mlx5e_destroy_flow_table(&ttc->ft); -} - -void mlx5e_destroy_ttc_table(struct mlx5e_priv *priv, - struct mlx5e_ttc_table *ttc) -{ - mlx5e_cleanup_ttc_rules(ttc); - mlx5e_destroy_flow_table(&ttc->ft); -} - -int mlx5e_create_ttc_table(struct mlx5e_priv *priv, struct ttc_params *params, - struct mlx5e_ttc_table *ttc) -{ - bool match_ipv_outer = MLX5_CAP_FLOWTABLE_NIC_RX(priv->mdev, ft_field_support.outer_ip_version); - struct mlx5e_flow_table *ft = &ttc->ft; - int err; - - ft->t = mlx5_create_flow_table(priv->fs.ns, ¶ms->ft_attr); - if (IS_ERR(ft->t)) { - err = PTR_ERR(ft->t); - ft->t = NULL; - return err; + for (tt = 0; tt < MLX5_NUM_TUNNEL_TT; tt++) { + ttc_params->tunnel_dests[tt].type = + MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; + ttc_params->tunnel_dests[tt].ft = + mlx5_get_ttc_flow_table(priv->fs.inner_ttc); } - - err = mlx5e_create_ttc_table_groups(ttc, match_ipv_outer); - if (err) - goto err; - - err = mlx5e_generate_ttc_table_rules(priv, params, ttc); - if (err) - goto err; - - return 0; -err: - mlx5e_destroy_flow_table(ft); - return err; -} - -int mlx5e_ttc_fwd_dest(struct mlx5e_priv *priv, enum mlx5e_traffic_types type, - struct mlx5_flow_destination *new_dest) -{ - return mlx5_modify_rule_destination(priv->fs.ttc.rules[type].rule, new_dest, NULL); -} - -struct mlx5_flow_destination -mlx5e_ttc_get_default_dest(struct mlx5e_priv *priv, enum mlx5e_traffic_types type) -{ - struct mlx5_flow_destination *dest = &priv->fs.ttc.rules[type].default_dest; - - WARN_ONCE(dest->type != MLX5_FLOW_DESTINATION_TYPE_TIR, - "TTC[%d] default dest is not setup yet", type); - - return *dest; -} - -int mlx5e_ttc_fwd_default_dest(struct mlx5e_priv *priv, enum mlx5e_traffic_types type) -{ - struct mlx5_flow_destination dest = mlx5e_ttc_get_default_dest(priv, type); - - return mlx5e_ttc_fwd_dest(priv, type, &dest); } static void mlx5e_del_l2_flow_rule(struct mlx5e_priv *priv, @@ -1473,7 +939,7 @@ static int mlx5e_add_l2_flow_rule(struct mlx5e_priv *priv, outer_headers.dmac_47_16); dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; - dest.ft = priv->fs.ttc.ft.t; + dest.ft = mlx5_get_ttc_flow_table(priv->fs.ttc); switch (type) { case MLX5E_FULLMATCH: @@ -1769,10 +1235,47 @@ static void mlx5e_destroy_vlan_table(struct mlx5e_priv *priv) kvfree(priv->fs.vlan); } -int mlx5e_create_flow_steering(struct mlx5e_priv *priv) +static void mlx5e_destroy_inner_ttc_table(struct mlx5e_priv *priv) +{ + if (!mlx5_tunnel_inner_ft_supported(priv->mdev)) + return; + mlx5_destroy_ttc_table(priv->fs.inner_ttc); +} + +void mlx5e_destroy_ttc_table(struct mlx5e_priv *priv) +{ + mlx5_destroy_ttc_table(priv->fs.ttc); +} + +static int mlx5e_create_inner_ttc_table(struct mlx5e_priv *priv) { struct ttc_params ttc_params = {}; - int tt, err; + + if (!mlx5_tunnel_inner_ft_supported(priv->mdev)) + return 0; + + mlx5e_set_inner_ttc_params(priv, &ttc_params); + priv->fs.inner_ttc = mlx5_create_inner_ttc_table(priv->mdev, + &ttc_params); + if (IS_ERR(priv->fs.inner_ttc)) + return PTR_ERR(priv->fs.inner_ttc); + return 0; +} + +int mlx5e_create_ttc_table(struct mlx5e_priv *priv) +{ + struct ttc_params ttc_params = {}; + + mlx5e_set_ttc_params(priv, &ttc_params, true); + priv->fs.ttc = mlx5_create_ttc_table(priv->mdev, &ttc_params); + if (IS_ERR(priv->fs.ttc)) + return PTR_ERR(priv->fs.ttc); + return 0; +} + +int mlx5e_create_flow_steering(struct mlx5e_priv *priv) +{ + int err; priv->fs.ns = mlx5_get_flow_namespace(priv->mdev, MLX5_FLOW_NAMESPACE_KERNEL); @@ -1787,23 +1290,15 @@ int mlx5e_create_flow_steering(struct mlx5e_priv *priv) priv->netdev->hw_features &= ~NETIF_F_NTUPLE; } - mlx5e_set_ttc_basic_params(priv, &ttc_params); - mlx5e_set_inner_ttc_ft_params(&ttc_params); - for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) - ttc_params.indir_tirn[tt] = priv->inner_indir_tir[tt].tirn; - - err = mlx5e_create_inner_ttc_table(priv, &ttc_params, &priv->fs.inner_ttc); + err = mlx5e_create_inner_ttc_table(priv); if (err) { - netdev_err(priv->netdev, "Failed to create inner ttc table, err=%d\n", + netdev_err(priv->netdev, + "Failed to create inner ttc table, err=%d\n", err); goto err_destroy_arfs_tables; } - mlx5e_set_ttc_ft_params(&ttc_params); - for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) - ttc_params.indir_tirn[tt] = priv->indir_tir[tt].tirn; - - err = mlx5e_create_ttc_table(priv, &ttc_params, &priv->fs.ttc); + err = mlx5e_create_ttc_table(priv); if (err) { netdev_err(priv->netdev, "Failed to create ttc table, err=%d\n", err); @@ -1837,9 +1332,9 @@ err_destory_vlan_table: err_destroy_l2_table: mlx5e_destroy_l2_table(priv); err_destroy_ttc_table: - mlx5e_destroy_ttc_table(priv, &priv->fs.ttc); + mlx5e_destroy_ttc_table(priv); err_destroy_inner_ttc_table: - mlx5e_destroy_inner_ttc_table(priv, &priv->fs.inner_ttc); + mlx5e_destroy_inner_ttc_table(priv); err_destroy_arfs_tables: mlx5e_arfs_destroy_tables(priv); @@ -1851,8 +1346,8 @@ void mlx5e_destroy_flow_steering(struct mlx5e_priv *priv) mlx5e_ptp_free_rx_fs(priv); mlx5e_destroy_vlan_table(priv); mlx5e_destroy_l2_table(priv); - mlx5e_destroy_ttc_table(priv, &priv->fs.ttc); - mlx5e_destroy_inner_ttc_table(priv, &priv->fs.inner_ttc); + mlx5e_destroy_ttc_table(priv); + mlx5e_destroy_inner_ttc_table(priv); mlx5e_arfs_destroy_tables(priv); mlx5e_ethtool_cleanup_steering(priv); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c index b416a8ee2eed..03693fa74a70 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c @@ -35,11 +35,19 @@ #include "en/params.h" #include "en/xsk/pool.h" +static int flow_type_to_traffic_type(u32 flow_type); + +static u32 flow_type_mask(u32 flow_type) +{ + return flow_type & ~(FLOW_EXT | FLOW_MAC_EXT | FLOW_RSS); +} + struct mlx5e_ethtool_rule { struct list_head list; struct ethtool_rx_flow_spec flow_spec; struct mlx5_flow_handle *rule; struct mlx5e_ethtool_table *eth_ft; + struct mlx5e_rss *rss; }; static void put_flow_table(struct mlx5e_ethtool_table *eth_ft) @@ -66,7 +74,7 @@ static struct mlx5e_ethtool_table *get_flow_table(struct mlx5e_priv *priv, int table_size; int prio; - switch (fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT)) { + switch (flow_type_mask(fs->flow_type)) { case TCP_V4_FLOW: case UDP_V4_FLOW: case TCP_V6_FLOW: @@ -329,7 +337,7 @@ static int set_flow_attrs(u32 *match_c, u32 *match_v, outer_headers); void *outer_headers_v = MLX5_ADDR_OF(fte_match_param, match_v, outer_headers); - u32 flow_type = fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT); + u32 flow_type = flow_type_mask(fs->flow_type); switch (flow_type) { case TCP_V4_FLOW: @@ -397,10 +405,53 @@ static bool outer_header_zero(u32 *match_criteria) size - 1); } +static int flow_get_tirn(struct mlx5e_priv *priv, + struct mlx5e_ethtool_rule *eth_rule, + struct ethtool_rx_flow_spec *fs, + u32 rss_context, u32 *tirn) +{ + if (fs->flow_type & FLOW_RSS) { + struct mlx5e_lro_param lro_param; + struct mlx5e_rss *rss; + u32 flow_type; + int err; + int tt; + + rss = mlx5e_rx_res_rss_get(priv->rx_res, rss_context); + if (!rss) + return -ENOENT; + + flow_type = flow_type_mask(fs->flow_type); + tt = flow_type_to_traffic_type(flow_type); + if (tt < 0) + return -EINVAL; + + lro_param = mlx5e_get_lro_param(&priv->channels.params); + err = mlx5e_rss_obtain_tirn(rss, tt, &lro_param, false, tirn); + if (err) + return err; + eth_rule->rss = rss; + mlx5e_rss_refcnt_inc(eth_rule->rss); + } else { + struct mlx5e_params *params = &priv->channels.params; + enum mlx5e_rq_group group; + u16 ix; + + mlx5e_qid_get_ch_and_group(params, fs->ring_cookie, &ix, &group); + + *tirn = group == MLX5E_RQ_GROUP_XSK ? + mlx5e_rx_res_get_tirn_xsk(priv->rx_res, ix) : + mlx5e_rx_res_get_tirn_direct(priv->rx_res, ix); + } + + return 0; +} + static struct mlx5_flow_handle * add_ethtool_flow_rule(struct mlx5e_priv *priv, + struct mlx5e_ethtool_rule *eth_rule, struct mlx5_flow_table *ft, - struct ethtool_rx_flow_spec *fs) + struct ethtool_rx_flow_spec *fs, u32 rss_context) { struct mlx5_flow_act flow_act = { .flags = FLOW_ACT_NO_APPEND }; struct mlx5_flow_destination *dst = NULL; @@ -419,22 +470,17 @@ add_ethtool_flow_rule(struct mlx5e_priv *priv, if (fs->ring_cookie == RX_CLS_FLOW_DISC) { flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP; } else { - struct mlx5e_params *params = &priv->channels.params; - enum mlx5e_rq_group group; - struct mlx5e_tir *tir; - u16 ix; - - mlx5e_qid_get_ch_and_group(params, fs->ring_cookie, &ix, &group); - tir = group == MLX5E_RQ_GROUP_XSK ? priv->xsk_tir : priv->direct_tir; - dst = kzalloc(sizeof(*dst), GFP_KERNEL); if (!dst) { err = -ENOMEM; goto free; } + err = flow_get_tirn(priv, eth_rule, fs, rss_context, &dst->tir_num); + if (err) + goto free; + dst->type = MLX5_FLOW_DESTINATION_TYPE_TIR; - dst->tir_num = tir[ix].tirn; flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; } @@ -458,6 +504,8 @@ static void del_ethtool_rule(struct mlx5e_priv *priv, { if (eth_rule->rule) mlx5_del_flow_rules(eth_rule->rule); + if (eth_rule->rss) + mlx5e_rss_refcnt_dec(eth_rule->rss); list_del(ð_rule->list); priv->fs.ethtool.tot_num_rules--; put_flow_table(eth_rule->eth_ft); @@ -618,7 +666,7 @@ static int validate_flow(struct mlx5e_priv *priv, fs->ring_cookie)) return -EINVAL; - switch (fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT)) { + switch (flow_type_mask(fs->flow_type)) { case ETHER_FLOW: num_tuples += validate_ethter(fs); break; @@ -667,7 +715,7 @@ static int validate_flow(struct mlx5e_priv *priv, static int mlx5e_ethtool_flow_replace(struct mlx5e_priv *priv, - struct ethtool_rx_flow_spec *fs) + struct ethtool_rx_flow_spec *fs, u32 rss_context) { struct mlx5e_ethtool_table *eth_ft; struct mlx5e_ethtool_rule *eth_rule; @@ -698,7 +746,7 @@ mlx5e_ethtool_flow_replace(struct mlx5e_priv *priv, err = -EINVAL; goto del_ethtool_rule; } - rule = add_ethtool_flow_rule(priv, eth_ft->ft, fs); + rule = add_ethtool_flow_rule(priv, eth_rule, eth_ft->ft, fs, rss_context); if (IS_ERR(rule)) { err = PTR_ERR(rule); goto del_ethtool_rule; @@ -744,10 +792,20 @@ mlx5e_ethtool_get_flow(struct mlx5e_priv *priv, return -EINVAL; list_for_each_entry(eth_rule, &priv->fs.ethtool.rules, list) { - if (eth_rule->flow_spec.location == location) { - info->fs = eth_rule->flow_spec; + int index; + + if (eth_rule->flow_spec.location != location) + continue; + if (!info) return 0; - } + info->fs = eth_rule->flow_spec; + if (!eth_rule->rss) + return 0; + index = mlx5e_rx_res_rss_index(priv->rx_res, eth_rule->rss); + if (index < 0) + return index; + info->rss_context = index; + return 0; } return -ENOENT; @@ -763,7 +821,7 @@ mlx5e_ethtool_get_all_flows(struct mlx5e_priv *priv, info->data = MAX_NUM_OF_ETHTOOL_RULES; while ((!err || err == -ENOENT) && idx < info->rule_cnt) { - err = mlx5e_ethtool_get_flow(priv, info, location); + err = mlx5e_ethtool_get_flow(priv, NULL, location); if (!err) rule_locs[idx++] = location; location++; @@ -785,45 +843,44 @@ void mlx5e_ethtool_init_steering(struct mlx5e_priv *priv) INIT_LIST_HEAD(&priv->fs.ethtool.rules); } -static enum mlx5e_traffic_types flow_type_to_traffic_type(u32 flow_type) +static int flow_type_to_traffic_type(u32 flow_type) { switch (flow_type) { case TCP_V4_FLOW: - return MLX5E_TT_IPV4_TCP; + return MLX5_TT_IPV4_TCP; case TCP_V6_FLOW: - return MLX5E_TT_IPV6_TCP; + return MLX5_TT_IPV6_TCP; case UDP_V4_FLOW: - return MLX5E_TT_IPV4_UDP; + return MLX5_TT_IPV4_UDP; case UDP_V6_FLOW: - return MLX5E_TT_IPV6_UDP; + return MLX5_TT_IPV6_UDP; case AH_V4_FLOW: - return MLX5E_TT_IPV4_IPSEC_AH; + return MLX5_TT_IPV4_IPSEC_AH; case AH_V6_FLOW: - return MLX5E_TT_IPV6_IPSEC_AH; + return MLX5_TT_IPV6_IPSEC_AH; case ESP_V4_FLOW: - return MLX5E_TT_IPV4_IPSEC_ESP; + return MLX5_TT_IPV4_IPSEC_ESP; case ESP_V6_FLOW: - return MLX5E_TT_IPV6_IPSEC_ESP; + return MLX5_TT_IPV6_IPSEC_ESP; case IPV4_FLOW: - return MLX5E_TT_IPV4; + return MLX5_TT_IPV4; case IPV6_FLOW: - return MLX5E_TT_IPV6; + return MLX5_TT_IPV6; default: - return MLX5E_NUM_INDIR_TIRS; + return -EINVAL; } } static int mlx5e_set_rss_hash_opt(struct mlx5e_priv *priv, struct ethtool_rxnfc *nfc) { - int inlen = MLX5_ST_SZ_BYTES(modify_tir_in); - enum mlx5e_traffic_types tt; u8 rx_hash_field = 0; - void *in; + int err; + int tt; tt = flow_type_to_traffic_type(nfc->flow_type); - if (tt == MLX5E_NUM_INDIR_TIRS) - return -EINVAL; + if (tt < 0) + return tt; /* RSS does not support anything other than hashing to queues * on src IP, dest IP, TCP/UDP src port and TCP/UDP dest @@ -848,35 +905,24 @@ static int mlx5e_set_rss_hash_opt(struct mlx5e_priv *priv, if (nfc->data & RXH_L4_B_2_3) rx_hash_field |= MLX5_HASH_FIELD_SEL_L4_DPORT; - in = kvzalloc(inlen, GFP_KERNEL); - if (!in) - return -ENOMEM; - mutex_lock(&priv->state_lock); - - if (rx_hash_field == priv->rss_params.rx_hash_fields[tt]) - goto out; - - priv->rss_params.rx_hash_fields[tt] = rx_hash_field; - mlx5e_modify_tirs_hash(priv, in); - -out: + err = mlx5e_rx_res_rss_set_hash_fields(priv->rx_res, tt, rx_hash_field); mutex_unlock(&priv->state_lock); - kvfree(in); - return 0; + + return err; } static int mlx5e_get_rss_hash_opt(struct mlx5e_priv *priv, struct ethtool_rxnfc *nfc) { - enum mlx5e_traffic_types tt; u32 hash_field = 0; + int tt; tt = flow_type_to_traffic_type(nfc->flow_type); - if (tt == MLX5E_NUM_INDIR_TIRS) - return -EINVAL; + if (tt < 0) + return tt; - hash_field = priv->rss_params.rx_hash_fields[tt]; + hash_field = mlx5e_rx_res_rss_get_hash_fields(priv->rx_res, tt); nfc->data = 0; if (hash_field & MLX5_HASH_FIELD_SEL_SRC_IP) @@ -898,7 +944,7 @@ int mlx5e_ethtool_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) switch (cmd->cmd) { case ETHTOOL_SRXCLSRLINS: - err = mlx5e_ethtool_flow_replace(priv, &cmd->fs); + err = mlx5e_ethtool_flow_replace(priv, &cmd->fs, cmd->rss_context); break; case ETHTOOL_SRXCLSRLDEL: err = mlx5e_ethtool_flow_remove(priv, cmd->fs.location); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 24f919ef9b8e..47efd858964d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -1619,7 +1619,7 @@ static int mlx5e_create_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param) (__be64 *)MLX5_ADDR_OF(create_cq_in, in, pas)); MLX5_SET(cqc, cqc, cq_period_mode, param->cq_period_mode); - MLX5_SET(cqc, cqc, c_eqn, eqn); + MLX5_SET(cqc, cqc, c_eqn_or_apu_element, eqn); MLX5_SET(cqc, cqc, uar_page, mdev->priv.uar->index); MLX5_SET(cqc, cqc, log_page_size, cq->wq_ctrl.buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT); @@ -1711,7 +1711,7 @@ static int mlx5e_open_sqs(struct mlx5e_channel *c, { int err, tc; - for (tc = 0; tc < params->num_tc; tc++) { + for (tc = 0; tc < mlx5e_get_dcb_num_tc(params); tc++) { int txq_ix = c->ix + tc * params->num_channels; err = mlx5e_open_txqsq(c, c->priv->tisn[c->lag_port][tc], txq_ix, @@ -1992,7 +1992,7 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, c->pdev = mlx5_core_dma_dev(priv->mdev); c->netdev = priv->netdev; c->mkey_be = cpu_to_be32(priv->mdev->mlx5e_res.hw_objs.mkey.key); - c->num_tc = params->num_tc; + c->num_tc = mlx5e_get_dcb_num_tc(params); c->xdp = !!params->xdp_prog; c->stats = &priv->channel_stats[ix].ch; c->aff_mask = irq_get_effective_affinity_mask(irq); @@ -2185,400 +2185,14 @@ void mlx5e_close_channels(struct mlx5e_channels *chs) chs->num = 0; } -static int -mlx5e_create_rqt(struct mlx5e_priv *priv, int sz, struct mlx5e_rqt *rqt) -{ - struct mlx5_core_dev *mdev = priv->mdev; - void *rqtc; - int inlen; - int err; - u32 *in; - int i; - - inlen = MLX5_ST_SZ_BYTES(create_rqt_in) + sizeof(u32) * sz; - in = kvzalloc(inlen, GFP_KERNEL); - if (!in) - return -ENOMEM; - - rqtc = MLX5_ADDR_OF(create_rqt_in, in, rqt_context); - - MLX5_SET(rqtc, rqtc, rqt_actual_size, sz); - MLX5_SET(rqtc, rqtc, rqt_max_size, sz); - - for (i = 0; i < sz; i++) - MLX5_SET(rqtc, rqtc, rq_num[i], priv->drop_rq.rqn); - - err = mlx5_core_create_rqt(mdev, in, inlen, &rqt->rqtn); - if (!err) - rqt->enabled = true; - - kvfree(in); - return err; -} - -void mlx5e_destroy_rqt(struct mlx5e_priv *priv, struct mlx5e_rqt *rqt) -{ - rqt->enabled = false; - mlx5_core_destroy_rqt(priv->mdev, rqt->rqtn); -} - -int mlx5e_create_indirect_rqt(struct mlx5e_priv *priv) -{ - struct mlx5e_rqt *rqt = &priv->indir_rqt; - int err; - - err = mlx5e_create_rqt(priv, MLX5E_INDIR_RQT_SIZE, rqt); - if (err) - mlx5_core_warn(priv->mdev, "create indirect rqts failed, %d\n", err); - return err; -} - -int mlx5e_create_direct_rqts(struct mlx5e_priv *priv, struct mlx5e_tir *tirs, int n) -{ - int err; - int ix; - - for (ix = 0; ix < n; ix++) { - err = mlx5e_create_rqt(priv, 1 /*size */, &tirs[ix].rqt); - if (unlikely(err)) - goto err_destroy_rqts; - } - - return 0; - -err_destroy_rqts: - mlx5_core_warn(priv->mdev, "create rqts failed, %d\n", err); - for (ix--; ix >= 0; ix--) - mlx5e_destroy_rqt(priv, &tirs[ix].rqt); - - return err; -} - -void mlx5e_destroy_direct_rqts(struct mlx5e_priv *priv, struct mlx5e_tir *tirs, int n) -{ - int i; - - for (i = 0; i < n; i++) - mlx5e_destroy_rqt(priv, &tirs[i].rqt); -} - -static int mlx5e_rx_hash_fn(int hfunc) -{ - return (hfunc == ETH_RSS_HASH_TOP) ? - MLX5_RX_HASH_FN_TOEPLITZ : - MLX5_RX_HASH_FN_INVERTED_XOR8; -} - -int mlx5e_bits_invert(unsigned long a, int size) -{ - int inv = 0; - int i; - - for (i = 0; i < size; i++) - inv |= (test_bit(size - i - 1, &a) ? 1 : 0) << i; - - return inv; -} - -static void mlx5e_fill_rqt_rqns(struct mlx5e_priv *priv, int sz, - struct mlx5e_redirect_rqt_param rrp, void *rqtc) -{ - int i; - - for (i = 0; i < sz; i++) { - u32 rqn; - - if (rrp.is_rss) { - int ix = i; - - if (rrp.rss.hfunc == ETH_RSS_HASH_XOR) - ix = mlx5e_bits_invert(i, ilog2(sz)); - - ix = priv->rss_params.indirection_rqt[ix]; - rqn = rrp.rss.channels->c[ix]->rq.rqn; - } else { - rqn = rrp.rqn; - } - MLX5_SET(rqtc, rqtc, rq_num[i], rqn); - } -} - -int mlx5e_redirect_rqt(struct mlx5e_priv *priv, u32 rqtn, int sz, - struct mlx5e_redirect_rqt_param rrp) -{ - struct mlx5_core_dev *mdev = priv->mdev; - void *rqtc; - int inlen; - u32 *in; - int err; - - inlen = MLX5_ST_SZ_BYTES(modify_rqt_in) + sizeof(u32) * sz; - in = kvzalloc(inlen, GFP_KERNEL); - if (!in) - return -ENOMEM; - - rqtc = MLX5_ADDR_OF(modify_rqt_in, in, ctx); - - MLX5_SET(rqtc, rqtc, rqt_actual_size, sz); - MLX5_SET(modify_rqt_in, in, bitmask.rqn_list, 1); - mlx5e_fill_rqt_rqns(priv, sz, rrp, rqtc); - err = mlx5_core_modify_rqt(mdev, rqtn, in, inlen); - - kvfree(in); - return err; -} - -static u32 mlx5e_get_direct_rqn(struct mlx5e_priv *priv, int ix, - struct mlx5e_redirect_rqt_param rrp) -{ - if (!rrp.is_rss) - return rrp.rqn; - - if (ix >= rrp.rss.channels->num) - return priv->drop_rq.rqn; - - return rrp.rss.channels->c[ix]->rq.rqn; -} - -static void mlx5e_redirect_rqts(struct mlx5e_priv *priv, - struct mlx5e_redirect_rqt_param rrp, - struct mlx5e_redirect_rqt_param *ptp_rrp) -{ - u32 rqtn; - int ix; - - if (priv->indir_rqt.enabled) { - /* RSS RQ table */ - rqtn = priv->indir_rqt.rqtn; - mlx5e_redirect_rqt(priv, rqtn, MLX5E_INDIR_RQT_SIZE, rrp); - } - - for (ix = 0; ix < priv->max_nch; ix++) { - struct mlx5e_redirect_rqt_param direct_rrp = { - .is_rss = false, - { - .rqn = mlx5e_get_direct_rqn(priv, ix, rrp) - }, - }; - - /* Direct RQ Tables */ - if (!priv->direct_tir[ix].rqt.enabled) - continue; - - rqtn = priv->direct_tir[ix].rqt.rqtn; - mlx5e_redirect_rqt(priv, rqtn, 1, direct_rrp); - } - if (ptp_rrp) { - rqtn = priv->ptp_tir.rqt.rqtn; - mlx5e_redirect_rqt(priv, rqtn, 1, *ptp_rrp); - } -} - -static void mlx5e_redirect_rqts_to_channels(struct mlx5e_priv *priv, - struct mlx5e_channels *chs) -{ - bool rx_ptp_support = priv->profile->rx_ptp_support; - struct mlx5e_redirect_rqt_param *ptp_rrp_p = NULL; - struct mlx5e_redirect_rqt_param rrp = { - .is_rss = true, - { - .rss = { - .channels = chs, - .hfunc = priv->rss_params.hfunc, - } - }, - }; - struct mlx5e_redirect_rqt_param ptp_rrp; - - if (rx_ptp_support) { - u32 ptp_rqn; - - ptp_rrp.is_rss = false; - ptp_rrp.rqn = mlx5e_ptp_get_rqn(priv->channels.ptp, &ptp_rqn) ? - priv->drop_rq.rqn : ptp_rqn; - ptp_rrp_p = &ptp_rrp; - } - mlx5e_redirect_rqts(priv, rrp, ptp_rrp_p); -} - -static void mlx5e_redirect_rqts_to_drop(struct mlx5e_priv *priv) -{ - bool rx_ptp_support = priv->profile->rx_ptp_support; - struct mlx5e_redirect_rqt_param drop_rrp = { - .is_rss = false, - { - .rqn = priv->drop_rq.rqn, - }, - }; - - mlx5e_redirect_rqts(priv, drop_rrp, rx_ptp_support ? &drop_rrp : NULL); -} - -static const struct mlx5e_tirc_config tirc_default_config[MLX5E_NUM_INDIR_TIRS] = { - [MLX5E_TT_IPV4_TCP] = { .l3_prot_type = MLX5_L3_PROT_TYPE_IPV4, - .l4_prot_type = MLX5_L4_PROT_TYPE_TCP, - .rx_hash_fields = MLX5_HASH_IP_L4PORTS, - }, - [MLX5E_TT_IPV6_TCP] = { .l3_prot_type = MLX5_L3_PROT_TYPE_IPV6, - .l4_prot_type = MLX5_L4_PROT_TYPE_TCP, - .rx_hash_fields = MLX5_HASH_IP_L4PORTS, - }, - [MLX5E_TT_IPV4_UDP] = { .l3_prot_type = MLX5_L3_PROT_TYPE_IPV4, - .l4_prot_type = MLX5_L4_PROT_TYPE_UDP, - .rx_hash_fields = MLX5_HASH_IP_L4PORTS, - }, - [MLX5E_TT_IPV6_UDP] = { .l3_prot_type = MLX5_L3_PROT_TYPE_IPV6, - .l4_prot_type = MLX5_L4_PROT_TYPE_UDP, - .rx_hash_fields = MLX5_HASH_IP_L4PORTS, - }, - [MLX5E_TT_IPV4_IPSEC_AH] = { .l3_prot_type = MLX5_L3_PROT_TYPE_IPV4, - .l4_prot_type = 0, - .rx_hash_fields = MLX5_HASH_IP_IPSEC_SPI, - }, - [MLX5E_TT_IPV6_IPSEC_AH] = { .l3_prot_type = MLX5_L3_PROT_TYPE_IPV6, - .l4_prot_type = 0, - .rx_hash_fields = MLX5_HASH_IP_IPSEC_SPI, - }, - [MLX5E_TT_IPV4_IPSEC_ESP] = { .l3_prot_type = MLX5_L3_PROT_TYPE_IPV4, - .l4_prot_type = 0, - .rx_hash_fields = MLX5_HASH_IP_IPSEC_SPI, - }, - [MLX5E_TT_IPV6_IPSEC_ESP] = { .l3_prot_type = MLX5_L3_PROT_TYPE_IPV6, - .l4_prot_type = 0, - .rx_hash_fields = MLX5_HASH_IP_IPSEC_SPI, - }, - [MLX5E_TT_IPV4] = { .l3_prot_type = MLX5_L3_PROT_TYPE_IPV4, - .l4_prot_type = 0, - .rx_hash_fields = MLX5_HASH_IP, - }, - [MLX5E_TT_IPV6] = { .l3_prot_type = MLX5_L3_PROT_TYPE_IPV6, - .l4_prot_type = 0, - .rx_hash_fields = MLX5_HASH_IP, - }, -}; - -struct mlx5e_tirc_config mlx5e_tirc_get_default_config(enum mlx5e_traffic_types tt) -{ - return tirc_default_config[tt]; -} - -static void mlx5e_build_tir_ctx_lro(struct mlx5e_params *params, void *tirc) -{ - if (!params->lro_en) - return; - -#define ROUGH_MAX_L2_L3_HDR_SZ 256 - - MLX5_SET(tirc, tirc, lro_enable_mask, - MLX5_TIRC_LRO_ENABLE_MASK_IPV4_LRO | - MLX5_TIRC_LRO_ENABLE_MASK_IPV6_LRO); - MLX5_SET(tirc, tirc, lro_max_ip_payload_size, - (MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ - ROUGH_MAX_L2_L3_HDR_SZ) >> 8); - MLX5_SET(tirc, tirc, lro_timeout_period_usecs, params->lro_timeout); -} - -void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_rss_params *rss_params, - const struct mlx5e_tirc_config *ttconfig, - void *tirc, bool inner) -{ - void *hfso = inner ? MLX5_ADDR_OF(tirc, tirc, rx_hash_field_selector_inner) : - MLX5_ADDR_OF(tirc, tirc, rx_hash_field_selector_outer); - - MLX5_SET(tirc, tirc, rx_hash_fn, mlx5e_rx_hash_fn(rss_params->hfunc)); - if (rss_params->hfunc == ETH_RSS_HASH_TOP) { - void *rss_key = MLX5_ADDR_OF(tirc, tirc, - rx_hash_toeplitz_key); - size_t len = MLX5_FLD_SZ_BYTES(tirc, - rx_hash_toeplitz_key); - - MLX5_SET(tirc, tirc, rx_hash_symmetric, 1); - memcpy(rss_key, rss_params->toeplitz_hash_key, len); - } - MLX5_SET(rx_hash_field_select, hfso, l3_prot_type, - ttconfig->l3_prot_type); - MLX5_SET(rx_hash_field_select, hfso, l4_prot_type, - ttconfig->l4_prot_type); - MLX5_SET(rx_hash_field_select, hfso, selected_fields, - ttconfig->rx_hash_fields); -} - -static void mlx5e_update_rx_hash_fields(struct mlx5e_tirc_config *ttconfig, - enum mlx5e_traffic_types tt, - u32 rx_hash_fields) -{ - *ttconfig = tirc_default_config[tt]; - ttconfig->rx_hash_fields = rx_hash_fields; -} - -void mlx5e_modify_tirs_hash(struct mlx5e_priv *priv, void *in) -{ - void *tirc = MLX5_ADDR_OF(modify_tir_in, in, ctx); - struct mlx5e_rss_params *rss = &priv->rss_params; - struct mlx5_core_dev *mdev = priv->mdev; - int ctxlen = MLX5_ST_SZ_BYTES(tirc); - struct mlx5e_tirc_config ttconfig; - int tt; - - MLX5_SET(modify_tir_in, in, bitmask.hash, 1); - - for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) { - memset(tirc, 0, ctxlen); - mlx5e_update_rx_hash_fields(&ttconfig, tt, - rss->rx_hash_fields[tt]); - mlx5e_build_indir_tir_ctx_hash(rss, &ttconfig, tirc, false); - mlx5_core_modify_tir(mdev, priv->indir_tir[tt].tirn, in); - } - - /* Verify inner tirs resources allocated */ - if (!priv->inner_indir_tir[0].tirn) - return; - - for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) { - memset(tirc, 0, ctxlen); - mlx5e_update_rx_hash_fields(&ttconfig, tt, - rss->rx_hash_fields[tt]); - mlx5e_build_indir_tir_ctx_hash(rss, &ttconfig, tirc, true); - mlx5_core_modify_tir(mdev, priv->inner_indir_tir[tt].tirn, in); - } -} - static int mlx5e_modify_tirs_lro(struct mlx5e_priv *priv) { - struct mlx5_core_dev *mdev = priv->mdev; - - void *in; - void *tirc; - int inlen; - int err; - int tt; - int ix; - - inlen = MLX5_ST_SZ_BYTES(modify_tir_in); - in = kvzalloc(inlen, GFP_KERNEL); - if (!in) - return -ENOMEM; - - MLX5_SET(modify_tir_in, in, bitmask.lro, 1); - tirc = MLX5_ADDR_OF(modify_tir_in, in, ctx); + struct mlx5e_rx_res *res = priv->rx_res; + struct mlx5e_lro_param lro_param; - mlx5e_build_tir_ctx_lro(&priv->channels.params, tirc); + lro_param = mlx5e_get_lro_param(&priv->channels.params); - for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) { - err = mlx5_core_modify_tir(mdev, priv->indir_tir[tt].tirn, in); - if (err) - goto free_in; - } - - for (ix = 0; ix < priv->max_nch; ix++) { - err = mlx5_core_modify_tir(mdev, priv->direct_tir[ix].tirn, in); - if (err) - goto free_in; - } - -free_in: - kvfree(in); - - return err; + return mlx5e_rx_res_lro_set_param(res, &lro_param); } static MLX5E_DEFINE_PREACTIVATE_WRAPPER_CTX(mlx5e_modify_tirs_lro); @@ -2649,22 +2263,34 @@ void mlx5e_set_netdev_mtu_boundaries(struct mlx5e_priv *priv) ETH_MAX_MTU); } -static void mlx5e_netdev_set_tcs(struct net_device *netdev, u16 nch, u8 ntc) +static int mlx5e_netdev_set_tcs(struct net_device *netdev, u16 nch, u8 ntc, + struct tc_mqprio_qopt_offload *mqprio) { - int tc; + int tc, err; netdev_reset_tc(netdev); if (ntc == 1) - return; + return 0; - netdev_set_num_tc(netdev, ntc); + err = netdev_set_num_tc(netdev, ntc); + if (err) { + netdev_WARN(netdev, "netdev_set_num_tc failed (%d), ntc = %d\n", err, ntc); + return err; + } - /* Map netdev TCs to offset 0 - * We have our own UP to TXQ mapping for QoS - */ - for (tc = 0; tc < ntc; tc++) - netdev_set_tc_queue(netdev, tc, nch, 0); + for (tc = 0; tc < ntc; tc++) { + u16 count, offset; + + /* For DCB mode, map netdev TCs to offset 0 + * We have our own UP to TXQ mapping for QoS + */ + count = mqprio ? mqprio->qopt.count[tc] : nch; + offset = mqprio ? mqprio->qopt.offset[tc] : 0; + netdev_set_tc_queue(netdev, tc, count, offset); + } + + return 0; } int mlx5e_update_tx_netdev_queues(struct mlx5e_priv *priv) @@ -2674,7 +2300,7 @@ int mlx5e_update_tx_netdev_queues(struct mlx5e_priv *priv) qos_queues = mlx5e_qos_cur_leaf_nodes(priv); nch = priv->channels.params.num_channels; - ntc = priv->channels.params.num_tc; + ntc = mlx5e_get_dcb_num_tc(&priv->channels.params); num_txqs = nch * ntc + qos_queues; if (MLX5E_GET_PFLAG(&priv->channels.params, MLX5E_PFLAG_TX_PORT_TS)) num_txqs += ntc; @@ -2698,11 +2324,12 @@ static int mlx5e_update_netdev_queues(struct mlx5e_priv *priv) old_ntc = netdev->num_tc ? : 1; nch = priv->channels.params.num_channels; - ntc = priv->channels.params.num_tc; + ntc = mlx5e_get_dcb_num_tc(&priv->channels.params); num_rxqs = nch * priv->profile->rq_groups; - mlx5e_netdev_set_tcs(netdev, nch, ntc); - + err = mlx5e_netdev_set_tcs(netdev, nch, ntc, NULL); + if (err) + goto err_out; err = mlx5e_update_tx_netdev_queues(priv); if (err) goto err_tcs; @@ -2723,7 +2350,8 @@ err_txqs: WARN_ON_ONCE(netif_set_real_num_tx_queues(netdev, old_num_txqs)); err_tcs: - mlx5e_netdev_set_tcs(netdev, old_num_txqs / old_ntc, old_ntc); + mlx5e_netdev_set_tcs(netdev, old_num_txqs / old_ntc, old_ntc, NULL); +err_out: return err; } @@ -2759,9 +2387,9 @@ int mlx5e_num_channels_changed(struct mlx5e_priv *priv) mlx5e_set_default_xps_cpumasks(priv, &priv->channels.params); - if (!netif_is_rxfh_configured(priv->netdev)) - mlx5e_build_default_indir_rqt(priv->rss_params.indirection_rqt, - MLX5E_INDIR_RQT_SIZE, count); + /* This function may be called on attach, before priv->rx_res is created. */ + if (!netif_is_rxfh_configured(priv->netdev) && priv->rx_res) + mlx5e_rx_res_rss_set_indir_uniform(priv->rx_res, count); return 0; } @@ -2773,7 +2401,7 @@ static void mlx5e_build_txq_maps(struct mlx5e_priv *priv) int i, ch, tc, num_tc; ch = priv->channels.num; - num_tc = priv->channels.params.num_tc; + num_tc = mlx5e_get_dcb_num_tc(&priv->channels.params); for (i = 0; i < ch; i++) { for (tc = 0; tc < num_tc; tc++) { @@ -2804,7 +2432,7 @@ static void mlx5e_update_num_tc_x_num_ch(struct mlx5e_priv *priv) { /* Sync with mlx5e_select_queue. */ WRITE_ONCE(priv->num_tc_x_num_ch, - priv->channels.params.num_tc * priv->channels.num); + mlx5e_get_dcb_num_tc(&priv->channels.params) * priv->channels.num); } void mlx5e_activate_priv_channels(struct mlx5e_priv *priv) @@ -2820,16 +2448,15 @@ void mlx5e_activate_priv_channels(struct mlx5e_priv *priv) mlx5e_add_sqs_fwd_rules(priv); mlx5e_wait_channels_min_rx_wqes(&priv->channels); - mlx5e_redirect_rqts_to_channels(priv, &priv->channels); - mlx5e_xsk_redirect_rqts_to_channels(priv, &priv->channels); + if (priv->rx_res) + mlx5e_rx_res_channels_activate(priv->rx_res, &priv->channels); } void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv) { - mlx5e_xsk_redirect_rqts_to_drop(priv, &priv->channels); - - mlx5e_redirect_rqts_to_drop(priv); + if (priv->rx_res) + mlx5e_rx_res_channels_deactivate(priv->rx_res); if (mlx5e_is_vport_rep(priv)) mlx5e_remove_sqs_fwd_rules(priv); @@ -3204,224 +2831,152 @@ static void mlx5e_cleanup_nic_tx(struct mlx5e_priv *priv) mlx5e_destroy_tises(priv); } -static void mlx5e_build_indir_tir_ctx_common(struct mlx5e_priv *priv, - u32 rqtn, u32 *tirc) -{ - MLX5_SET(tirc, tirc, transport_domain, priv->mdev->mlx5e_res.hw_objs.td.tdn); - MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_INDIRECT); - MLX5_SET(tirc, tirc, indirect_table, rqtn); - MLX5_SET(tirc, tirc, tunneled_offload_en, - priv->channels.params.tunneled_offload_en); - - mlx5e_build_tir_ctx_lro(&priv->channels.params, tirc); -} - -static void mlx5e_build_indir_tir_ctx(struct mlx5e_priv *priv, - enum mlx5e_traffic_types tt, - u32 *tirc) +static int mlx5e_modify_channels_scatter_fcs(struct mlx5e_channels *chs, bool enable) { - mlx5e_build_indir_tir_ctx_common(priv, priv->indir_rqt.rqtn, tirc); - mlx5e_build_indir_tir_ctx_hash(&priv->rss_params, - &tirc_default_config[tt], tirc, false); -} + int err = 0; + int i; -static void mlx5e_build_direct_tir_ctx(struct mlx5e_priv *priv, u32 rqtn, u32 *tirc) -{ - mlx5e_build_indir_tir_ctx_common(priv, rqtn, tirc); - MLX5_SET(tirc, tirc, rx_hash_fn, MLX5_RX_HASH_FN_INVERTED_XOR8); -} + for (i = 0; i < chs->num; i++) { + err = mlx5e_modify_rq_scatter_fcs(&chs->c[i]->rq, enable); + if (err) + return err; + } -static void mlx5e_build_inner_indir_tir_ctx(struct mlx5e_priv *priv, - enum mlx5e_traffic_types tt, - u32 *tirc) -{ - mlx5e_build_indir_tir_ctx_common(priv, priv->indir_rqt.rqtn, tirc); - mlx5e_build_indir_tir_ctx_hash(&priv->rss_params, - &tirc_default_config[tt], tirc, true); + return 0; } -int mlx5e_create_indirect_tirs(struct mlx5e_priv *priv, bool inner_ttc) +static int mlx5e_modify_channels_vsd(struct mlx5e_channels *chs, bool vsd) { - struct mlx5e_tir *tir; - void *tirc; - int inlen; - int i = 0; int err; - u32 *in; - int tt; - - inlen = MLX5_ST_SZ_BYTES(create_tir_in); - in = kvzalloc(inlen, GFP_KERNEL); - if (!in) - return -ENOMEM; - - for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) { - memset(in, 0, inlen); - tir = &priv->indir_tir[tt]; - tirc = MLX5_ADDR_OF(create_tir_in, in, ctx); - mlx5e_build_indir_tir_ctx(priv, tt, tirc); - err = mlx5e_create_tir(priv->mdev, tir, in); - if (err) { - mlx5_core_warn(priv->mdev, "create indirect tirs failed, %d\n", err); - goto err_destroy_inner_tirs; - } - } - - if (!inner_ttc || !mlx5e_tunnel_inner_ft_supported(priv->mdev)) - goto out; + int i; - for (i = 0; i < MLX5E_NUM_INDIR_TIRS; i++) { - memset(in, 0, inlen); - tir = &priv->inner_indir_tir[i]; - tirc = MLX5_ADDR_OF(create_tir_in, in, ctx); - mlx5e_build_inner_indir_tir_ctx(priv, i, tirc); - err = mlx5e_create_tir(priv->mdev, tir, in); - if (err) { - mlx5_core_warn(priv->mdev, "create inner indirect tirs failed, %d\n", err); - goto err_destroy_inner_tirs; - } + for (i = 0; i < chs->num; i++) { + err = mlx5e_modify_rq_vsd(&chs->c[i]->rq, vsd); + if (err) + return err; } - -out: - kvfree(in); + if (chs->ptp && test_bit(MLX5E_PTP_STATE_RX, chs->ptp->state)) + return mlx5e_modify_rq_vsd(&chs->ptp->rq, vsd); return 0; - -err_destroy_inner_tirs: - for (i--; i >= 0; i--) - mlx5e_destroy_tir(priv->mdev, &priv->inner_indir_tir[i]); - - for (tt--; tt >= 0; tt--) - mlx5e_destroy_tir(priv->mdev, &priv->indir_tir[tt]); - - kvfree(in); - - return err; } -int mlx5e_create_direct_tirs(struct mlx5e_priv *priv, struct mlx5e_tir *tirs, int n) +static int mlx5e_setup_tc_mqprio_dcb(struct mlx5e_priv *priv, + struct tc_mqprio_qopt *mqprio) { - struct mlx5e_tir *tir; - void *tirc; - int inlen; - int err = 0; - u32 *in; - int ix; - - inlen = MLX5_ST_SZ_BYTES(create_tir_in); - in = kvzalloc(inlen, GFP_KERNEL); - if (!in) - return -ENOMEM; + struct mlx5e_params new_params; + u8 tc = mqprio->num_tc; + int err; - for (ix = 0; ix < n; ix++) { - memset(in, 0, inlen); - tir = &tirs[ix]; - tirc = MLX5_ADDR_OF(create_tir_in, in, ctx); - mlx5e_build_direct_tir_ctx(priv, tir->rqt.rqtn, tirc); - err = mlx5e_create_tir(priv->mdev, tir, in); - if (unlikely(err)) - goto err_destroy_ch_tirs; - } + mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; - goto out; + if (tc && tc != MLX5E_MAX_NUM_TC) + return -EINVAL; -err_destroy_ch_tirs: - mlx5_core_warn(priv->mdev, "create tirs failed, %d\n", err); - for (ix--; ix >= 0; ix--) - mlx5e_destroy_tir(priv->mdev, &tirs[ix]); + new_params = priv->channels.params; + new_params.mqprio.mode = TC_MQPRIO_MODE_DCB; + new_params.mqprio.num_tc = tc ? tc : 1; -out: - kvfree(in); + err = mlx5e_safe_switch_params(priv, &new_params, + mlx5e_num_channels_changed_ctx, NULL, true); + priv->max_opened_tc = max_t(u8, priv->max_opened_tc, + mlx5e_get_dcb_num_tc(&priv->channels.params)); return err; } -void mlx5e_destroy_indirect_tirs(struct mlx5e_priv *priv) +static int mlx5e_mqprio_channel_validate(struct mlx5e_priv *priv, + struct tc_mqprio_qopt_offload *mqprio) { + struct net_device *netdev = priv->netdev; + int agg_count = 0; int i; - for (i = 0; i < MLX5E_NUM_INDIR_TIRS; i++) - mlx5e_destroy_tir(priv->mdev, &priv->indir_tir[i]); - - /* Verify inner tirs resources allocated */ - if (!priv->inner_indir_tir[0].tirn) - return; - - for (i = 0; i < MLX5E_NUM_INDIR_TIRS; i++) - mlx5e_destroy_tir(priv->mdev, &priv->inner_indir_tir[i]); -} - -void mlx5e_destroy_direct_tirs(struct mlx5e_priv *priv, struct mlx5e_tir *tirs, int n) -{ - int i; + if (mqprio->qopt.offset[0] != 0 || mqprio->qopt.num_tc < 1 || + mqprio->qopt.num_tc > MLX5E_MAX_NUM_MQPRIO_CH_TC) + return -EINVAL; - for (i = 0; i < n; i++) - mlx5e_destroy_tir(priv->mdev, &tirs[i]); -} + for (i = 0; i < mqprio->qopt.num_tc; i++) { + if (!mqprio->qopt.count[i]) { + netdev_err(netdev, "Zero size for queue-group (%d) is not supported\n", i); + return -EINVAL; + } + if (mqprio->min_rate[i]) { + netdev_err(netdev, "Min tx rate is not supported\n"); + return -EINVAL; + } + if (mqprio->max_rate[i]) { + netdev_err(netdev, "Max tx rate is not supported\n"); + return -EINVAL; + } -static int mlx5e_modify_channels_scatter_fcs(struct mlx5e_channels *chs, bool enable) -{ - int err = 0; - int i; + if (mqprio->qopt.offset[i] != agg_count) { + netdev_err(netdev, "Discontinuous queues config is not supported\n"); + return -EINVAL; + } + agg_count += mqprio->qopt.count[i]; + } - for (i = 0; i < chs->num; i++) { - err = mlx5e_modify_rq_scatter_fcs(&chs->c[i]->rq, enable); - if (err) - return err; + if (priv->channels.params.num_channels < agg_count) { + netdev_err(netdev, "Num of queues (%d) exceeds available (%d)\n", + agg_count, priv->channels.params.num_channels); + return -EINVAL; } return 0; } -static int mlx5e_modify_channels_vsd(struct mlx5e_channels *chs, bool vsd) +static int mlx5e_mqprio_channel_set_tcs_ctx(struct mlx5e_priv *priv, void *ctx) { - int err; - int i; + struct tc_mqprio_qopt_offload *mqprio = (struct tc_mqprio_qopt_offload *)ctx; + struct net_device *netdev = priv->netdev; + u8 num_tc; - for (i = 0; i < chs->num; i++) { - err = mlx5e_modify_rq_vsd(&chs->c[i]->rq, vsd); - if (err) - return err; - } - if (chs->ptp && test_bit(MLX5E_PTP_STATE_RX, chs->ptp->state)) - return mlx5e_modify_rq_vsd(&chs->ptp->rq, vsd); + if (priv->channels.params.mqprio.mode != TC_MQPRIO_MODE_CHANNEL) + return -EINVAL; + + num_tc = priv->channels.params.mqprio.num_tc; + mlx5e_netdev_set_tcs(netdev, 0, num_tc, mqprio); return 0; } -static int mlx5e_setup_tc_mqprio(struct mlx5e_priv *priv, - struct tc_mqprio_qopt *mqprio) +static int mlx5e_setup_tc_mqprio_channel(struct mlx5e_priv *priv, + struct tc_mqprio_qopt_offload *mqprio) { struct mlx5e_params new_params; - u8 tc = mqprio->num_tc; - int err = 0; + int err; - mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; + err = mlx5e_mqprio_channel_validate(priv, mqprio); + if (err) + return err; - if (tc && tc != MLX5E_MAX_NUM_TC) - return -EINVAL; + new_params = priv->channels.params; + new_params.mqprio.mode = TC_MQPRIO_MODE_CHANNEL; + new_params.mqprio.num_tc = mqprio->qopt.num_tc; + err = mlx5e_safe_switch_params(priv, &new_params, + mlx5e_mqprio_channel_set_tcs_ctx, mqprio, true); - mutex_lock(&priv->state_lock); + return err; +} +static int mlx5e_setup_tc_mqprio(struct mlx5e_priv *priv, + struct tc_mqprio_qopt_offload *mqprio) +{ /* MQPRIO is another toplevel qdisc that can't be attached * simultaneously with the offloaded HTB. */ - if (WARN_ON(priv->htb.maj_id)) { - err = -EINVAL; - goto out; - } - - new_params = priv->channels.params; - new_params.num_tc = tc ? tc : 1; - - err = mlx5e_safe_switch_params(priv, &new_params, - mlx5e_num_channels_changed_ctx, NULL, true); + if (WARN_ON(priv->htb.maj_id)) + return -EINVAL; -out: - priv->max_opened_tc = max_t(u8, priv->max_opened_tc, - priv->channels.params.num_tc); - mutex_unlock(&priv->state_lock); - return err; + switch (mqprio->mode) { + case TC_MQPRIO_MODE_DCB: + return mlx5e_setup_tc_mqprio_dcb(priv, &mqprio->qopt); + case TC_MQPRIO_MODE_CHANNEL: + return mlx5e_setup_tc_mqprio_channel(priv, mqprio); + default: + return -EOPNOTSUPP; + } } static int mlx5e_setup_tc_htb(struct mlx5e_priv *priv, struct tc_htb_qopt_offload *htb) @@ -3445,8 +3000,7 @@ static int mlx5e_setup_tc_htb(struct mlx5e_priv *priv, struct tc_htb_qopt_offloa return mlx5e_htb_leaf_to_inner(priv, htb->parent_classid, htb->classid, htb->rate, htb->ceil, htb->extack); case TC_HTB_LEAF_DEL: - return mlx5e_htb_leaf_del(priv, htb->classid, &htb->moved_qid, &htb->qid, - htb->extack); + return mlx5e_htb_leaf_del(priv, &htb->classid, htb->extack); case TC_HTB_LEAF_DEL_LAST: case TC_HTB_LEAF_DEL_LAST_FORCE: return mlx5e_htb_leaf_del_last(priv, htb->classid, @@ -3493,7 +3047,10 @@ static int mlx5e_setup_tc(struct net_device *dev, enum tc_setup_type type, priv, priv, true); } case TC_SETUP_QDISC_MQPRIO: - return mlx5e_setup_tc_mqprio(priv, type_data); + mutex_lock(&priv->state_lock); + err = mlx5e_setup_tc_mqprio(priv, type_data); + mutex_unlock(&priv->state_lock); + return err; case TC_SETUP_QDISC_HTB: mutex_lock(&priv->state_lock); err = mlx5e_setup_tc_htb(priv, type_data); @@ -4582,7 +4139,7 @@ const struct net_device_ops mlx5e_netdev_ops = { .ndo_set_features = mlx5e_set_features, .ndo_fix_features = mlx5e_fix_features, .ndo_change_mtu = mlx5e_change_nic_mtu, - .ndo_do_ioctl = mlx5e_ioctl, + .ndo_eth_ioctl = mlx5e_ioctl, .ndo_set_tx_maxrate = mlx5e_set_tx_maxrate, .ndo_features_check = mlx5e_features_check, .ndo_tx_timeout = mlx5e_tx_timeout, @@ -4611,15 +4168,6 @@ const struct net_device_ops mlx5e_netdev_ops = { .ndo_get_devlink_port = mlx5e_get_devlink_port, }; -void mlx5e_build_default_indir_rqt(u32 *indirection_rqt, int len, - int num_channels) -{ - int i; - - for (i = 0; i < len; i++) - indirection_rqt[i] = i % num_channels; -} - static u32 mlx5e_choose_lro_timeout(struct mlx5_core_dev *mdev, u32 wanted_timeout) { int i; @@ -4632,24 +4180,8 @@ static u32 mlx5e_choose_lro_timeout(struct mlx5_core_dev *mdev, u32 wanted_timeo return MLX5_CAP_ETH(mdev, lro_timer_supported_periods[i]); } -void mlx5e_build_rss_params(struct mlx5e_rss_params *rss_params, - u16 num_channels) -{ - enum mlx5e_traffic_types tt; - - rss_params->hfunc = ETH_RSS_HASH_TOP; - netdev_rss_key_fill(rss_params->toeplitz_hash_key, - sizeof(rss_params->toeplitz_hash_key)); - mlx5e_build_default_indir_rqt(rss_params->indirection_rqt, - MLX5E_INDIR_RQT_SIZE, num_channels); - for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) - rss_params->rx_hash_fields[tt] = - tirc_default_config[tt].rx_hash_fields; -} - void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16 mtu) { - struct mlx5e_rss_params *rss_params = &priv->rss_params; struct mlx5e_params *params = &priv->channels.params; struct mlx5_core_dev *mdev = priv->mdev; u8 rx_cq_period_mode; @@ -4660,12 +4192,12 @@ void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16 params->hard_mtu = MLX5E_ETH_HARD_MTU; params->num_channels = min_t(unsigned int, MLX5E_MAX_NUM_CHANNELS / 2, priv->max_nch); - params->num_tc = 1; + params->mqprio.num_tc = 1; /* Set an initial non-zero value, so that mlx5e_select_queue won't * divide by zero if called before first activating channels. */ - priv->num_tc_x_num_ch = params->num_channels * params->num_tc; + priv->num_tc_x_num_ch = params->num_channels * params->mqprio.num_tc; /* SQ */ params->log_sq_size = is_kdump_kernel() ? @@ -4709,10 +4241,7 @@ void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16 /* TX inline */ mlx5_query_min_inline(mdev, ¶ms->tx_min_inline_mode); - /* RSS */ - mlx5e_build_rss_params(rss_params, params->num_channels); - params->tunneled_offload_en = - mlx5e_tunnel_inner_ft_supported(mdev); + params->tunneled_offload_en = mlx5_tunnel_inner_ft_supported(mdev); /* AF_XDP */ params->xsk = xsk; @@ -4772,8 +4301,8 @@ static bool mlx5e_tunnel_any_tx_proto_supported(struct mlx5_core_dev *mdev) { int tt; - for (tt = 0; tt < MLX5E_NUM_TUNNEL_TT; tt++) { - if (mlx5e_tunnel_proto_supported_tx(mdev, mlx5e_get_proto_by_tunnel_type(tt))) + for (tt = 0; tt < MLX5_NUM_TUNNEL_TT; tt++) { + if (mlx5e_tunnel_proto_supported_tx(mdev, mlx5_get_proto_by_tunnel_type(tt))) return true; } return (mlx5_vxlan_allowed(mdev->vxlan) || mlx5_geneve_tx_allowed(mdev)); @@ -4812,7 +4341,14 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) netdev->hw_enc_features |= NETIF_F_HW_VLAN_CTAG_TX; netdev->hw_enc_features |= NETIF_F_HW_VLAN_CTAG_RX; + /* Tunneled LRO is not supported in the driver, and the same RQs are + * shared between inner and outer TIRs, so the driver can't disable LRO + * for inner TIRs while having it enabled for outer TIRs. Due to this, + * block LRO altogether if the firmware declares tunneled LRO support. + */ if (!!MLX5_CAP_ETH(mdev, lro_cap) && + !MLX5_CAP_ETH(mdev, tunnel_lro_vxlan) && + !MLX5_CAP_ETH(mdev, tunnel_lro_gre) && mlx5e_check_fragmented_striding_rq_cap(mdev)) netdev->vlan_features |= NETIF_F_LRO; @@ -4939,7 +4475,6 @@ static int mlx5e_nic_init(struct mlx5_core_dev *mdev, struct net_device *netdev) { struct mlx5e_priv *priv = netdev_priv(netdev); - struct devlink_port *dl_port; int err; mlx5e_build_nic_params(priv, &priv->xsk, netdev->mtu); @@ -4955,19 +4490,13 @@ static int mlx5e_nic_init(struct mlx5_core_dev *mdev, if (err) mlx5_core_err(mdev, "TLS initialization failed, %d\n", err); - dl_port = mlx5e_devlink_get_dl_port(priv); - if (dl_port->registered) - mlx5e_health_create_reporters(priv); - + mlx5e_health_create_reporters(priv); return 0; } static void mlx5e_nic_cleanup(struct mlx5e_priv *priv) { - struct devlink_port *dl_port = mlx5e_devlink_get_dl_port(priv); - - if (dl_port->registered) - mlx5e_health_destroy_reporters(priv); + mlx5e_health_destroy_reporters(priv); mlx5e_tls_cleanup(priv); mlx5e_ipsec_cleanup(priv); } @@ -4975,9 +4504,14 @@ static void mlx5e_nic_cleanup(struct mlx5e_priv *priv) static int mlx5e_init_nic_rx(struct mlx5e_priv *priv) { struct mlx5_core_dev *mdev = priv->mdev; - u16 max_nch = priv->max_nch; + enum mlx5e_rx_res_features features; + struct mlx5e_lro_param lro_param; int err; + priv->rx_res = mlx5e_rx_res_alloc(); + if (!priv->rx_res) + return -ENOMEM; + mlx5e_create_q_counters(priv); err = mlx5e_open_drop_rq(priv, &priv->drop_rq); @@ -4986,42 +4520,20 @@ static int mlx5e_init_nic_rx(struct mlx5e_priv *priv) goto err_destroy_q_counters; } - err = mlx5e_create_indirect_rqt(priv); + features = MLX5E_RX_RES_FEATURE_XSK | MLX5E_RX_RES_FEATURE_PTP; + if (priv->channels.params.tunneled_offload_en) + features |= MLX5E_RX_RES_FEATURE_INNER_FT; + lro_param = mlx5e_get_lro_param(&priv->channels.params); + err = mlx5e_rx_res_init(priv->rx_res, priv->mdev, features, + priv->max_nch, priv->drop_rq.rqn, &lro_param, + priv->channels.params.num_channels); if (err) goto err_close_drop_rq; - err = mlx5e_create_direct_rqts(priv, priv->direct_tir, max_nch); - if (err) - goto err_destroy_indirect_rqts; - - err = mlx5e_create_indirect_tirs(priv, true); - if (err) - goto err_destroy_direct_rqts; - - err = mlx5e_create_direct_tirs(priv, priv->direct_tir, max_nch); - if (err) - goto err_destroy_indirect_tirs; - - err = mlx5e_create_direct_rqts(priv, priv->xsk_tir, max_nch); - if (unlikely(err)) - goto err_destroy_direct_tirs; - - err = mlx5e_create_direct_tirs(priv, priv->xsk_tir, max_nch); - if (unlikely(err)) - goto err_destroy_xsk_rqts; - - err = mlx5e_create_direct_rqts(priv, &priv->ptp_tir, 1); - if (err) - goto err_destroy_xsk_tirs; - - err = mlx5e_create_direct_tirs(priv, &priv->ptp_tir, 1); - if (err) - goto err_destroy_ptp_rqt; - err = mlx5e_create_flow_steering(priv); if (err) { mlx5_core_warn(mdev, "create flow steering failed, %d\n", err); - goto err_destroy_ptp_direct_tir; + goto err_destroy_rx_res; } err = mlx5e_tc_nic_init(priv); @@ -5042,46 +4554,27 @@ err_tc_nic_cleanup: mlx5e_tc_nic_cleanup(priv); err_destroy_flow_steering: mlx5e_destroy_flow_steering(priv); -err_destroy_ptp_direct_tir: - mlx5e_destroy_direct_tirs(priv, &priv->ptp_tir, 1); -err_destroy_ptp_rqt: - mlx5e_destroy_direct_rqts(priv, &priv->ptp_tir, 1); -err_destroy_xsk_tirs: - mlx5e_destroy_direct_tirs(priv, priv->xsk_tir, max_nch); -err_destroy_xsk_rqts: - mlx5e_destroy_direct_rqts(priv, priv->xsk_tir, max_nch); -err_destroy_direct_tirs: - mlx5e_destroy_direct_tirs(priv, priv->direct_tir, max_nch); -err_destroy_indirect_tirs: - mlx5e_destroy_indirect_tirs(priv); -err_destroy_direct_rqts: - mlx5e_destroy_direct_rqts(priv, priv->direct_tir, max_nch); -err_destroy_indirect_rqts: - mlx5e_destroy_rqt(priv, &priv->indir_rqt); +err_destroy_rx_res: + mlx5e_rx_res_destroy(priv->rx_res); err_close_drop_rq: mlx5e_close_drop_rq(&priv->drop_rq); err_destroy_q_counters: mlx5e_destroy_q_counters(priv); + mlx5e_rx_res_free(priv->rx_res); + priv->rx_res = NULL; return err; } static void mlx5e_cleanup_nic_rx(struct mlx5e_priv *priv) { - u16 max_nch = priv->max_nch; - mlx5e_accel_cleanup_rx(priv); mlx5e_tc_nic_cleanup(priv); mlx5e_destroy_flow_steering(priv); - mlx5e_destroy_direct_tirs(priv, &priv->ptp_tir, 1); - mlx5e_destroy_direct_rqts(priv, &priv->ptp_tir, 1); - mlx5e_destroy_direct_tirs(priv, priv->xsk_tir, max_nch); - mlx5e_destroy_direct_rqts(priv, priv->xsk_tir, max_nch); - mlx5e_destroy_direct_tirs(priv, priv->direct_tir, max_nch); - mlx5e_destroy_indirect_tirs(priv); - mlx5e_destroy_direct_rqts(priv, priv->direct_tir, max_nch); - mlx5e_destroy_rqt(priv, &priv->indir_rqt); + mlx5e_rx_res_destroy(priv->rx_res); mlx5e_close_drop_rq(&priv->drop_rq); mlx5e_destroy_q_counters(priv); + mlx5e_rx_res_free(priv->rx_res); + priv->rx_res = NULL; } static int mlx5e_init_nic_tx(struct mlx5e_priv *priv) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index bf94bcb6fa5d..ae71a17fdb27 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -49,6 +49,7 @@ #include "en/devlink.h" #include "fs_core.h" #include "lib/mlx5.h" +#include "lib/devcom.h" #define CREATE_TRACE_POINTS #include "diag/en_rep_tracepoint.h" #include "en_accel/ipsec.h" @@ -250,7 +251,9 @@ static int mlx5e_rep_set_channels(struct net_device *dev, } static int mlx5e_rep_get_coalesce(struct net_device *netdev, - struct ethtool_coalesce *coal) + struct ethtool_coalesce *coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct mlx5e_priv *priv = netdev_priv(netdev); @@ -258,7 +261,9 @@ static int mlx5e_rep_get_coalesce(struct net_device *netdev, } static int mlx5e_rep_set_coalesce(struct net_device *netdev, - struct ethtool_coalesce *coal) + struct ethtool_coalesce *coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct mlx5e_priv *priv = netdev_priv(netdev); @@ -310,6 +315,8 @@ static void mlx5e_sqs2vport_stop(struct mlx5_eswitch *esw, rpriv = mlx5e_rep_to_rep_priv(rep); list_for_each_entry_safe(rep_sq, tmp, &rpriv->vport_sqs_list, list) { mlx5_eswitch_del_send_to_vport_rule(rep_sq->send_to_vport_rule); + if (rep_sq->send_to_vport_rule_peer) + mlx5_eswitch_del_send_to_vport_rule(rep_sq->send_to_vport_rule_peer); list_del(&rep_sq->list); kfree(rep_sq); } @@ -319,6 +326,7 @@ static int mlx5e_sqs2vport_start(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep, u32 *sqns_array, int sqns_num) { + struct mlx5_eswitch *peer_esw = NULL; struct mlx5_flow_handle *flow_rule; struct mlx5e_rep_priv *rpriv; struct mlx5e_rep_sq *rep_sq; @@ -329,6 +337,10 @@ static int mlx5e_sqs2vport_start(struct mlx5_eswitch *esw, return 0; rpriv = mlx5e_rep_to_rep_priv(rep); + if (mlx5_devcom_is_paired(esw->dev->priv.devcom, MLX5_DEVCOM_ESW_OFFLOADS)) + peer_esw = mlx5_devcom_get_peer_data(esw->dev->priv.devcom, + MLX5_DEVCOM_ESW_OFFLOADS); + for (i = 0; i < sqns_num; i++) { rep_sq = kzalloc(sizeof(*rep_sq), GFP_KERNEL); if (!rep_sq) { @@ -337,7 +349,7 @@ static int mlx5e_sqs2vport_start(struct mlx5_eswitch *esw, } /* Add re-inject rule to the PF/representor sqs */ - flow_rule = mlx5_eswitch_add_send_to_vport_rule(esw, rep, + flow_rule = mlx5_eswitch_add_send_to_vport_rule(esw, esw, rep, sqns_array[i]); if (IS_ERR(flow_rule)) { err = PTR_ERR(flow_rule); @@ -345,12 +357,34 @@ static int mlx5e_sqs2vport_start(struct mlx5_eswitch *esw, goto out_err; } rep_sq->send_to_vport_rule = flow_rule; + rep_sq->sqn = sqns_array[i]; + + if (peer_esw) { + flow_rule = mlx5_eswitch_add_send_to_vport_rule(peer_esw, esw, + rep, sqns_array[i]); + if (IS_ERR(flow_rule)) { + err = PTR_ERR(flow_rule); + mlx5_eswitch_del_send_to_vport_rule(rep_sq->send_to_vport_rule); + kfree(rep_sq); + goto out_err; + } + rep_sq->send_to_vport_rule_peer = flow_rule; + } + list_add(&rep_sq->list, &rpriv->vport_sqs_list); } + + if (peer_esw) + mlx5_devcom_release_peer_data(esw->dev->priv.devcom, MLX5_DEVCOM_ESW_OFFLOADS); + return 0; out_err: mlx5e_sqs2vport_stop(esw, rep); + + if (peer_esw) + mlx5_devcom_release_peer_data(esw->dev->priv.devcom, MLX5_DEVCOM_ESW_OFFLOADS); + return err; } @@ -364,7 +398,8 @@ int mlx5e_add_sqs_fwd_rules(struct mlx5e_priv *priv) int err = -ENOMEM; u32 *sqs; - sqs = kcalloc(priv->channels.num * priv->channels.params.num_tc, sizeof(*sqs), GFP_KERNEL); + sqs = kcalloc(priv->channels.num * mlx5e_get_dcb_num_tc(&priv->channels.params), + sizeof(*sqs), GFP_KERNEL); if (!sqs) goto out; @@ -581,13 +616,10 @@ static void mlx5e_build_rep_params(struct net_device *netdev) params->rx_dim_enabled = MLX5_CAP_GEN(mdev, cq_moderation); mlx5e_set_rx_cq_mode_params(params, cq_period_mode); - params->num_tc = 1; + params->mqprio.num_tc = 1; params->tunneled_offload_en = false; mlx5_query_min_inline(mdev, ¶ms->tx_min_inline_mode); - - /* RSS */ - mlx5e_build_rss_params(&priv->rss_params, params->num_channels); } static void mlx5e_build_rep_netdev(struct net_device *netdev, @@ -651,25 +683,23 @@ static int mlx5e_create_rep_ttc_table(struct mlx5e_priv *priv) struct mlx5e_rep_priv *rpriv = priv->ppriv; struct mlx5_eswitch_rep *rep = rpriv->rep; struct ttc_params ttc_params = {}; - int tt, err; + int err; priv->fs.ns = mlx5_get_flow_namespace(priv->mdev, MLX5_FLOW_NAMESPACE_KERNEL); /* The inner_ttc in the ttc params is intentionally not set */ - ttc_params.any_tt_tirn = priv->direct_tir[0].tirn; - mlx5e_set_ttc_ft_params(&ttc_params); + mlx5e_set_ttc_params(priv, &ttc_params, false); if (rep->vport != MLX5_VPORT_UPLINK) /* To give uplik rep TTC a lower level for chaining from root ft */ ttc_params.ft_attr.level = MLX5E_TTC_FT_LEVEL + 1; - for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) - ttc_params.indir_tirn[tt] = priv->indir_tir[tt].tirn; - - err = mlx5e_create_ttc_table(priv, &ttc_params, &priv->fs.ttc); - if (err) { - netdev_err(priv->netdev, "Failed to create rep ttc table, err=%d\n", err); + priv->fs.ttc = mlx5_create_ttc_table(priv->mdev, &ttc_params); + if (IS_ERR(priv->fs.ttc)) { + err = PTR_ERR(priv->fs.ttc); + netdev_err(priv->netdev, "Failed to create rep ttc table, err=%d\n", + err); return err; } return 0; @@ -687,7 +717,7 @@ static int mlx5e_create_rep_root_ft(struct mlx5e_priv *priv) /* non uplik reps will skip any bypass tables and go directly to * their own ttc */ - rpriv->root_ft = priv->fs.ttc.ft.t; + rpriv->root_ft = mlx5_get_ttc_flow_table(priv->fs.ttc); return 0; } @@ -760,9 +790,13 @@ int mlx5e_rep_bond_update(struct mlx5e_priv *priv, bool cleanup) static int mlx5e_init_rep_rx(struct mlx5e_priv *priv) { struct mlx5_core_dev *mdev = priv->mdev; - u16 max_nch = priv->max_nch; + struct mlx5e_lro_param lro_param; int err; + priv->rx_res = mlx5e_rx_res_alloc(); + if (!priv->rx_res) + return -ENOMEM; + mlx5e_init_l2_addr(priv); err = mlx5e_open_drop_rq(priv, &priv->drop_rq); @@ -771,25 +805,16 @@ static int mlx5e_init_rep_rx(struct mlx5e_priv *priv) return err; } - err = mlx5e_create_indirect_rqt(priv); + lro_param = mlx5e_get_lro_param(&priv->channels.params); + err = mlx5e_rx_res_init(priv->rx_res, priv->mdev, 0, + priv->max_nch, priv->drop_rq.rqn, &lro_param, + priv->channels.params.num_channels); if (err) goto err_close_drop_rq; - err = mlx5e_create_direct_rqts(priv, priv->direct_tir, max_nch); - if (err) - goto err_destroy_indirect_rqts; - - err = mlx5e_create_indirect_tirs(priv, false); - if (err) - goto err_destroy_direct_rqts; - - err = mlx5e_create_direct_tirs(priv, priv->direct_tir, max_nch); - if (err) - goto err_destroy_indirect_tirs; - err = mlx5e_create_rep_ttc_table(priv); if (err) - goto err_destroy_direct_tirs; + goto err_destroy_rx_res; err = mlx5e_create_rep_root_ft(priv); if (err) @@ -806,33 +831,26 @@ static int mlx5e_init_rep_rx(struct mlx5e_priv *priv) err_destroy_root_ft: mlx5e_destroy_rep_root_ft(priv); err_destroy_ttc_table: - mlx5e_destroy_ttc_table(priv, &priv->fs.ttc); -err_destroy_direct_tirs: - mlx5e_destroy_direct_tirs(priv, priv->direct_tir, max_nch); -err_destroy_indirect_tirs: - mlx5e_destroy_indirect_tirs(priv); -err_destroy_direct_rqts: - mlx5e_destroy_direct_rqts(priv, priv->direct_tir, max_nch); -err_destroy_indirect_rqts: - mlx5e_destroy_rqt(priv, &priv->indir_rqt); + mlx5_destroy_ttc_table(priv->fs.ttc); +err_destroy_rx_res: + mlx5e_rx_res_destroy(priv->rx_res); err_close_drop_rq: mlx5e_close_drop_rq(&priv->drop_rq); + mlx5e_rx_res_free(priv->rx_res); + priv->rx_res = NULL; return err; } static void mlx5e_cleanup_rep_rx(struct mlx5e_priv *priv) { - u16 max_nch = priv->max_nch; - mlx5e_ethtool_cleanup_steering(priv); rep_vport_rx_rule_destroy(priv); mlx5e_destroy_rep_root_ft(priv); - mlx5e_destroy_ttc_table(priv, &priv->fs.ttc); - mlx5e_destroy_direct_tirs(priv, priv->direct_tir, max_nch); - mlx5e_destroy_indirect_tirs(priv); - mlx5e_destroy_direct_rqts(priv, priv->direct_tir, max_nch); - mlx5e_destroy_rqt(priv, &priv->indir_rqt); + mlx5_destroy_ttc_table(priv->fs.ttc); + mlx5e_rx_res_destroy(priv->rx_res); mlx5e_close_drop_rq(&priv->drop_rq); + mlx5e_rx_res_free(priv->rx_res); + priv->rx_res = NULL; } static int mlx5e_init_ul_rep_rx(struct mlx5e_priv *priv) @@ -1264,10 +1282,64 @@ static void *mlx5e_vport_rep_get_proto_dev(struct mlx5_eswitch_rep *rep) return rpriv->netdev; } +static void mlx5e_vport_rep_event_unpair(struct mlx5_eswitch_rep *rep) +{ + struct mlx5e_rep_priv *rpriv; + struct mlx5e_rep_sq *rep_sq; + + rpriv = mlx5e_rep_to_rep_priv(rep); + list_for_each_entry(rep_sq, &rpriv->vport_sqs_list, list) { + if (!rep_sq->send_to_vport_rule_peer) + continue; + mlx5_eswitch_del_send_to_vport_rule(rep_sq->send_to_vport_rule_peer); + rep_sq->send_to_vport_rule_peer = NULL; + } +} + +static int mlx5e_vport_rep_event_pair(struct mlx5_eswitch *esw, + struct mlx5_eswitch_rep *rep, + struct mlx5_eswitch *peer_esw) +{ + struct mlx5_flow_handle *flow_rule; + struct mlx5e_rep_priv *rpriv; + struct mlx5e_rep_sq *rep_sq; + + rpriv = mlx5e_rep_to_rep_priv(rep); + list_for_each_entry(rep_sq, &rpriv->vport_sqs_list, list) { + if (rep_sq->send_to_vport_rule_peer) + continue; + flow_rule = mlx5_eswitch_add_send_to_vport_rule(peer_esw, esw, rep, rep_sq->sqn); + if (IS_ERR(flow_rule)) + goto err_out; + rep_sq->send_to_vport_rule_peer = flow_rule; + } + + return 0; +err_out: + mlx5e_vport_rep_event_unpair(rep); + return PTR_ERR(flow_rule); +} + +static int mlx5e_vport_rep_event(struct mlx5_eswitch *esw, + struct mlx5_eswitch_rep *rep, + enum mlx5_switchdev_event event, + void *data) +{ + int err = 0; + + if (event == MLX5_SWITCHDEV_EVENT_PAIR) + err = mlx5e_vport_rep_event_pair(esw, rep, data); + else if (event == MLX5_SWITCHDEV_EVENT_UNPAIR) + mlx5e_vport_rep_event_unpair(rep); + + return err; +} + static const struct mlx5_eswitch_rep_ops rep_ops = { .load = mlx5e_vport_rep_load, .unload = mlx5e_vport_rep_unload, - .get_proto_dev = mlx5e_vport_rep_get_proto_dev + .get_proto_dev = mlx5e_vport_rep_get_proto_dev, + .event = mlx5e_vport_rep_event, }; static int mlx5e_rep_probe(struct auxiliary_device *adev, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h index 47a2dfb7792a..48a203a9e7d9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h @@ -60,6 +60,7 @@ struct mlx5e_neigh_update_table { struct mlx5_tc_ct_priv; struct mlx5e_rep_bond; struct mlx5e_tc_tun_encap; +struct mlx5e_post_act; struct mlx5_rep_uplink_priv { /* Filters DB - instantiated by the uplink representor and shared by @@ -88,8 +89,9 @@ struct mlx5_rep_uplink_priv { /* maps tun_enc_opts to a unique id*/ struct mapping_ctx *tunnel_enc_opts_mapping; + struct mlx5e_post_act *post_act; struct mlx5_tc_ct_priv *ct_priv; - struct mlx5_esw_psample *esw_psample; + struct mlx5e_tc_psample *tc_psample; /* support eswitch vports bonding */ struct mlx5e_rep_bond *bond; @@ -146,7 +148,7 @@ struct mlx5e_neigh_hash_entry { */ refcount_t refcnt; - /* Save the last reported time offloaded trafic pass over one of the + /* Save the last reported time offloaded traffic pass over one of the * neigh hash entry flows. Use it to periodically update the neigh * 'used' value and avoid neigh deleting by the kernel. */ @@ -207,6 +209,8 @@ struct mlx5e_encap_entry { struct mlx5e_rep_sq { struct mlx5_flow_handle *send_to_vport_rule; + struct mlx5_flow_handle *send_to_vport_rule_peer; + u32 sqn; struct list_head list; }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 6eba574c5a36..ba8164792016 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -34,25 +34,20 @@ #include <net/flow_offload.h> #include <net/sch_generic.h> #include <net/pkt_cls.h> -#include <net/tc_act/tc_gact.h> -#include <net/tc_act/tc_skbedit.h> #include <linux/mlx5/fs.h> #include <linux/mlx5/device.h> #include <linux/rhashtable.h> #include <linux/refcount.h> #include <linux/completion.h> -#include <net/tc_act/tc_mirred.h> -#include <net/tc_act/tc_vlan.h> -#include <net/tc_act/tc_tunnel_key.h> #include <net/tc_act/tc_pedit.h> #include <net/tc_act/tc_csum.h> -#include <net/tc_act/tc_mpls.h> #include <net/psample.h> #include <net/arp.h> #include <net/ipv6_stubs.h> #include <net/bareudp.h> #include <net/bonding.h> #include "en.h" +#include "en/tc/post_act.h" #include "en_rep.h" #include "en/rep/tc.h" #include "en/rep/neigh.h" @@ -66,7 +61,7 @@ #include "en/mod_hdr.h" #include "en/tc_priv.h" #include "en/tc_tun_encap.h" -#include "esw/sample.h" +#include "en/tc/sample.h" #include "lib/devcom.h" #include "lib/geneve.h" #include "lib/fs_chains.h" @@ -103,7 +98,7 @@ struct mlx5e_tc_attr_to_reg_mapping mlx5e_tc_attr_to_reg_mappings[] = { [MARK_TO_REG] = mark_to_reg_ct, [LABELS_TO_REG] = labels_to_reg_ct, [FTEID_TO_REG] = fteid_to_reg_ct, - /* For NIC rules we store the retore metadata directly + /* For NIC rules we store the restore metadata directly * into reg_b that is passed to SW since we don't * jump between steering domains. */ @@ -252,7 +247,7 @@ get_ct_priv(struct mlx5e_priv *priv) } #if IS_ENABLED(CONFIG_MLX5_TC_SAMPLE) -static struct mlx5_esw_psample * +static struct mlx5e_tc_psample * get_sample_priv(struct mlx5e_priv *priv) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; @@ -263,7 +258,7 @@ get_sample_priv(struct mlx5e_priv *priv) uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH); uplink_priv = &uplink_rpriv->uplink_priv; - return uplink_priv->esw_psample; + return uplink_priv->tc_psample; } return NULL; @@ -340,12 +335,12 @@ struct mlx5e_hairpin { struct mlx5_core_dev *func_mdev; struct mlx5e_priv *func_priv; u32 tdn; - u32 tirn; + struct mlx5e_tir direct_tir; int num_channels; struct mlx5e_rqt indir_rqt; - u32 indir_tirn[MLX5E_NUM_INDIR_TIRS]; - struct mlx5e_ttc_table ttc; + struct mlx5e_tir indir_tir[MLX5E_NUM_INDIR_TIRS]; + struct mlx5_ttc_table *ttc; }; struct mlx5e_hairpin_entry { @@ -482,126 +477,101 @@ struct mlx5_core_dev *mlx5e_hairpin_get_mdev(struct net *net, int ifindex) static int mlx5e_hairpin_create_transport(struct mlx5e_hairpin *hp) { - u32 in[MLX5_ST_SZ_DW(create_tir_in)] = {}; - void *tirc; + struct mlx5e_tir_builder *builder; int err; + builder = mlx5e_tir_builder_alloc(false); + if (!builder) + return -ENOMEM; + err = mlx5_core_alloc_transport_domain(hp->func_mdev, &hp->tdn); if (err) - goto alloc_tdn_err; - - tirc = MLX5_ADDR_OF(create_tir_in, in, ctx); - - MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_DIRECT); - MLX5_SET(tirc, tirc, inline_rqn, hp->pair->rqn[0]); - MLX5_SET(tirc, tirc, transport_domain, hp->tdn); + goto out; - err = mlx5_core_create_tir(hp->func_mdev, in, &hp->tirn); + mlx5e_tir_builder_build_inline(builder, hp->tdn, hp->pair->rqn[0]); + err = mlx5e_tir_init(&hp->direct_tir, builder, hp->func_mdev, false); if (err) goto create_tir_err; - return 0; +out: + mlx5e_tir_builder_free(builder); + return err; create_tir_err: mlx5_core_dealloc_transport_domain(hp->func_mdev, hp->tdn); -alloc_tdn_err: - return err; + + goto out; } static void mlx5e_hairpin_destroy_transport(struct mlx5e_hairpin *hp) { - mlx5_core_destroy_tir(hp->func_mdev, hp->tirn); + mlx5e_tir_destroy(&hp->direct_tir); mlx5_core_dealloc_transport_domain(hp->func_mdev, hp->tdn); } -static int mlx5e_hairpin_fill_rqt_rqns(struct mlx5e_hairpin *hp, void *rqtc) -{ - struct mlx5e_priv *priv = hp->func_priv; - int i, ix, sz = MLX5E_INDIR_RQT_SIZE; - u32 *indirection_rqt, rqn; - - indirection_rqt = kcalloc(sz, sizeof(*indirection_rqt), GFP_KERNEL); - if (!indirection_rqt) - return -ENOMEM; - - mlx5e_build_default_indir_rqt(indirection_rqt, sz, - hp->num_channels); - - for (i = 0; i < sz; i++) { - ix = i; - if (priv->rss_params.hfunc == ETH_RSS_HASH_XOR) - ix = mlx5e_bits_invert(i, ilog2(sz)); - ix = indirection_rqt[ix]; - rqn = hp->pair->rqn[ix]; - MLX5_SET(rqtc, rqtc, rq_num[i], rqn); - } - - kfree(indirection_rqt); - return 0; -} - static int mlx5e_hairpin_create_indirect_rqt(struct mlx5e_hairpin *hp) { - int inlen, err, sz = MLX5E_INDIR_RQT_SIZE; struct mlx5e_priv *priv = hp->func_priv; struct mlx5_core_dev *mdev = priv->mdev; - void *rqtc; - u32 *in; + struct mlx5e_rss_params_indir *indir; + int err; - inlen = MLX5_ST_SZ_BYTES(create_rqt_in) + sizeof(u32) * sz; - in = kvzalloc(inlen, GFP_KERNEL); - if (!in) + indir = kvmalloc(sizeof(*indir), GFP_KERNEL); + if (!indir) return -ENOMEM; - rqtc = MLX5_ADDR_OF(create_rqt_in, in, rqt_context); + mlx5e_rss_params_indir_init_uniform(indir, hp->num_channels); + err = mlx5e_rqt_init_indir(&hp->indir_rqt, mdev, hp->pair->rqn, hp->num_channels, + mlx5e_rx_res_get_current_hash(priv->rx_res).hfunc, + indir); - MLX5_SET(rqtc, rqtc, rqt_actual_size, sz); - MLX5_SET(rqtc, rqtc, rqt_max_size, sz); - - err = mlx5e_hairpin_fill_rqt_rqns(hp, rqtc); - if (err) - goto out; - - err = mlx5_core_create_rqt(mdev, in, inlen, &hp->indir_rqt.rqtn); - if (!err) - hp->indir_rqt.enabled = true; - -out: - kvfree(in); + kvfree(indir); return err; } static int mlx5e_hairpin_create_indirect_tirs(struct mlx5e_hairpin *hp) { struct mlx5e_priv *priv = hp->func_priv; - u32 in[MLX5_ST_SZ_DW(create_tir_in)]; - int tt, i, err; - void *tirc; + struct mlx5e_rss_params_hash rss_hash; + enum mlx5_traffic_types tt, max_tt; + struct mlx5e_tir_builder *builder; + int err = 0; + + builder = mlx5e_tir_builder_alloc(false); + if (!builder) + return -ENOMEM; + + rss_hash = mlx5e_rx_res_get_current_hash(priv->rx_res); for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) { - struct mlx5e_tirc_config ttconfig = mlx5e_tirc_get_default_config(tt); + struct mlx5e_rss_params_traffic_type rss_tt; - memset(in, 0, MLX5_ST_SZ_BYTES(create_tir_in)); - tirc = MLX5_ADDR_OF(create_tir_in, in, ctx); + rss_tt = mlx5e_rss_get_default_tt_config(tt); - MLX5_SET(tirc, tirc, transport_domain, hp->tdn); - MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_INDIRECT); - MLX5_SET(tirc, tirc, indirect_table, hp->indir_rqt.rqtn); - mlx5e_build_indir_tir_ctx_hash(&priv->rss_params, &ttconfig, tirc, false); + mlx5e_tir_builder_build_rqt(builder, hp->tdn, + mlx5e_rqt_get_rqtn(&hp->indir_rqt), + false); + mlx5e_tir_builder_build_rss(builder, &rss_hash, &rss_tt, false); - err = mlx5_core_create_tir(hp->func_mdev, in, - &hp->indir_tirn[tt]); + err = mlx5e_tir_init(&hp->indir_tir[tt], builder, hp->func_mdev, false); if (err) { mlx5_core_warn(hp->func_mdev, "create indirect tirs failed, %d\n", err); goto err_destroy_tirs; } + + mlx5e_tir_builder_clear(builder); } - return 0; -err_destroy_tirs: - for (i = 0; i < tt; i++) - mlx5_core_destroy_tir(hp->func_mdev, hp->indir_tirn[i]); +out: + mlx5e_tir_builder_free(builder); return err; + +err_destroy_tirs: + max_tt = tt; + for (tt = 0; tt < max_tt; tt++) + mlx5e_tir_destroy(&hp->indir_tir[tt]); + + goto out; } static void mlx5e_hairpin_destroy_indirect_tirs(struct mlx5e_hairpin *hp) @@ -609,7 +579,7 @@ static void mlx5e_hairpin_destroy_indirect_tirs(struct mlx5e_hairpin *hp) int tt; for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) - mlx5_core_destroy_tir(hp->func_mdev, hp->indir_tirn[tt]); + mlx5e_tir_destroy(&hp->indir_tir[tt]); } static void mlx5e_hairpin_set_ttc_params(struct mlx5e_hairpin *hp, @@ -620,12 +590,16 @@ static void mlx5e_hairpin_set_ttc_params(struct mlx5e_hairpin *hp, memset(ttc_params, 0, sizeof(*ttc_params)); - ttc_params->any_tt_tirn = hp->tirn; - - for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) - ttc_params->indir_tirn[tt] = hp->indir_tirn[tt]; + ttc_params->ns = mlx5_get_flow_namespace(hp->func_mdev, + MLX5_FLOW_NAMESPACE_KERNEL); + for (tt = 0; tt < MLX5_NUM_TT; tt++) { + ttc_params->dests[tt].type = MLX5_FLOW_DESTINATION_TYPE_TIR; + ttc_params->dests[tt].tir_num = + tt == MLX5_TT_ANY ? + mlx5e_tir_get_tirn(&hp->direct_tir) : + mlx5e_tir_get_tirn(&hp->indir_tir[tt]); + } - ft_attr->max_fte = MLX5E_TTC_TABLE_SIZE; ft_attr->level = MLX5E_TC_TTC_FT_LEVEL; ft_attr->prio = MLX5E_TC_PRIO; } @@ -645,30 +619,31 @@ static int mlx5e_hairpin_rss_init(struct mlx5e_hairpin *hp) goto err_create_indirect_tirs; mlx5e_hairpin_set_ttc_params(hp, &ttc_params); - err = mlx5e_create_ttc_table(priv, &ttc_params, &hp->ttc); - if (err) + hp->ttc = mlx5_create_ttc_table(priv->mdev, &ttc_params); + if (IS_ERR(hp->ttc)) { + err = PTR_ERR(hp->ttc); goto err_create_ttc_table; + } netdev_dbg(priv->netdev, "add hairpin: using %d channels rss ttc table id %x\n", - hp->num_channels, hp->ttc.ft.t->id); + hp->num_channels, + mlx5_get_ttc_flow_table(priv->fs.ttc)->id); return 0; err_create_ttc_table: mlx5e_hairpin_destroy_indirect_tirs(hp); err_create_indirect_tirs: - mlx5e_destroy_rqt(priv, &hp->indir_rqt); + mlx5e_rqt_destroy(&hp->indir_rqt); return err; } static void mlx5e_hairpin_rss_cleanup(struct mlx5e_hairpin *hp) { - struct mlx5e_priv *priv = hp->func_priv; - - mlx5e_destroy_ttc_table(priv, &hp->ttc); + mlx5_destroy_ttc_table(hp->ttc); mlx5e_hairpin_destroy_indirect_tirs(hp); - mlx5e_destroy_rqt(priv, &hp->indir_rqt); + mlx5e_rqt_destroy(&hp->indir_rqt); } static struct mlx5e_hairpin * @@ -903,16 +878,17 @@ static int mlx5e_hairpin_flow_add(struct mlx5e_priv *priv, } netdev_dbg(priv->netdev, "add hairpin: tirn %x rqn %x peer %s sqn %x prio %d (log) data %d packets %d\n", - hp->tirn, hp->pair->rqn[0], + mlx5e_tir_get_tirn(&hp->direct_tir), hp->pair->rqn[0], dev_name(hp->pair->peer_mdev->device), hp->pair->sqn[0], match_prio, params.log_data_size, params.log_num_packets); attach_flow: if (hpe->hp->num_channels > 1) { flow_flag_set(flow, HAIRPIN_RSS); - flow->attr->nic_attr->hairpin_ft = hpe->hp->ttc.ft.t; + flow->attr->nic_attr->hairpin_ft = + mlx5_get_ttc_flow_table(hpe->hp->ttc); } else { - flow->attr->nic_attr->hairpin_tirn = hpe->hp->tirn; + flow->attr->nic_attr->hairpin_tirn = mlx5e_tir_get_tirn(&hpe->hp->direct_tir); } flow->hpe = hpe; @@ -1056,15 +1032,17 @@ err_ft_get: static int mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv, - struct mlx5e_tc_flow_parse_attr *parse_attr, struct mlx5e_tc_flow *flow, struct netlink_ext_ack *extack) { + struct mlx5e_tc_flow_parse_attr *parse_attr; struct mlx5_flow_attr *attr = flow->attr; struct mlx5_core_dev *dev = priv->mdev; - struct mlx5_fc *counter = NULL; + struct mlx5_fc *counter; int err; + parse_attr = attr->parse_attr; + if (flow_flag_test(flow, HAIRPIN)) { err = mlx5e_hairpin_flow_add(priv, flow, parse_attr, extack); if (err) @@ -1170,7 +1148,8 @@ mlx5e_tc_offload_fdb_rules(struct mlx5_eswitch *esw, mod_hdr_acts); #if IS_ENABLED(CONFIG_MLX5_TC_SAMPLE) } else if (flow_flag_test(flow, SAMPLE)) { - rule = mlx5_esw_sample_offload(get_sample_priv(flow->priv), spec, attr); + rule = mlx5e_tc_sample_offload(get_sample_priv(flow->priv), spec, attr, + mlx5e_tc_get_flow_tun_id(flow)); #endif } else { rule = mlx5_eswitch_add_offloaded_rule(esw, spec, attr); @@ -1209,7 +1188,7 @@ void mlx5e_tc_unoffload_fdb_rules(struct mlx5_eswitch *esw, #if IS_ENABLED(CONFIG_MLX5_TC_SAMPLE) if (flow_flag_test(flow, SAMPLE)) { - mlx5_esw_sample_unoffload(get_sample_priv(flow->priv), flow->rule[0], attr); + mlx5e_tc_sample_unoffload(get_sample_priv(flow->priv), flow->rule[0], attr); return; } #endif @@ -1402,9 +1381,9 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, bool vf_tun = false, encap_valid = true; struct net_device *encap_dev = NULL; struct mlx5_esw_flow_attr *esw_attr; - struct mlx5_fc *counter = NULL; struct mlx5e_rep_priv *rpriv; struct mlx5e_priv *out_priv; + struct mlx5_fc *counter; u32 max_prio, max_chain; int err = 0; int out_index; @@ -1591,6 +1570,7 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, else mlx5e_detach_mod_hdr(priv, flow); } + kfree(attr->sample_attr); kvfree(attr->parse_attr); kvfree(attr->esw_attr->rx_tun_attr); @@ -1600,7 +1580,6 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, if (flow_flag_test(flow, L3_TO_L2_DECAP)) mlx5e_detach_decap(priv, flow); - kfree(flow->attr->esw_attr->sample); kfree(flow->attr); } @@ -1665,17 +1644,22 @@ static void mlx5e_tc_del_flow(struct mlx5e_priv *priv, } } -static int flow_has_tc_fwd_action(struct flow_cls_offload *f) +static bool flow_requires_tunnel_mapping(u32 chain, struct flow_cls_offload *f) { struct flow_rule *rule = flow_cls_offload_flow_rule(f); struct flow_action *flow_action = &rule->action; const struct flow_action_entry *act; int i; + if (chain) + return false; + flow_action_for_each(i, act, flow_action) { switch (act->id) { case FLOW_ACTION_GOTO: return true; + case FLOW_ACTION_SAMPLE: + return true; default: continue; } @@ -1916,7 +1900,7 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv, return -EOPNOTSUPP; needs_mapping = !!flow->attr->chain; - sets_mapping = !flow->attr->chain && flow_has_tc_fwd_action(f); + sets_mapping = flow_requires_tunnel_mapping(flow->attr->chain, f); *match_inner = !needs_mapping; if ((needs_mapping || sets_mapping) && @@ -2489,7 +2473,7 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_3; } } - /* Currenlty supported only for MPLS over UDP */ + /* Currently supported only for MPLS over UDP */ if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_MPLS) && !netif_is_bareudp(filter_dev)) { NL_SET_ERR_MSG_MOD(extack, @@ -2743,7 +2727,9 @@ static int offload_pedit_fields(struct mlx5e_priv *priv, if (s_mask && a_mask) { NL_SET_ERR_MSG_MOD(extack, "can't set and add to the same HW field"); - printk(KERN_WARNING "mlx5: can't set and add to the same HW field (%x)\n", f->field); + netdev_warn(priv->netdev, + "mlx5: can't set and add to the same HW field (%x)\n", + f->field); return -EOPNOTSUPP; } @@ -2782,8 +2768,9 @@ static int offload_pedit_fields(struct mlx5e_priv *priv, if (first < next_z && next_z < last) { NL_SET_ERR_MSG_MOD(extack, "rewrite of few sub-fields isn't supported"); - printk(KERN_WARNING "mlx5: rewrite of few sub-fields (mask %lx) isn't offloaded\n", - mask); + netdev_warn(priv->netdev, + "mlx5: rewrite of few sub-fields (mask %lx) isn't offloaded\n", + mask); return -EOPNOTSUPP; } @@ -3370,10 +3357,10 @@ static int validate_goto_chain(struct mlx5e_priv *priv, static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct flow_action *flow_action, - struct mlx5e_tc_flow_parse_attr *parse_attr, struct mlx5e_tc_flow *flow, struct netlink_ext_ack *extack) { + struct mlx5e_tc_flow_parse_attr *parse_attr; struct mlx5_flow_attr *attr = flow->attr; struct pedit_headers_action hdrs[2] = {}; const struct flow_action_entry *act; @@ -3389,8 +3376,8 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, return -EOPNOTSUPP; nic_attr = attr->nic_attr; - nic_attr->flow_tag = MLX5_FS_DEFAULT_FLOW_TAG; + parse_attr = attr->parse_attr; flow_action_for_each(i, act, flow_action) { switch (act->id) { @@ -3399,10 +3386,8 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, MLX5_FLOW_CONTEXT_ACTION_COUNT; break; case FLOW_ACTION_DROP: - action |= MLX5_FLOW_CONTEXT_ACTION_DROP; - if (MLX5_CAP_FLOWTABLE(priv->mdev, - flow_table_properties_nic_receive.flow_counter)) - action |= MLX5_FLOW_CONTEXT_ACTION_COUNT; + action |= MLX5_FLOW_CONTEXT_ACTION_DROP | + MLX5_FLOW_CONTEXT_ACTION_COUNT; break; case FLOW_ACTION_MANGLE: case FLOW_ACTION_ADD: @@ -3443,7 +3428,7 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, "device is not on same HW, can't offload"); netdev_warn(priv->netdev, "device %s not on same HW, can't offload\n", peer_dev->name); - return -EINVAL; + return -EOPNOTSUPP; } } break; @@ -3453,7 +3438,7 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, if (mark & ~MLX5E_TC_FLOW_ID_MASK) { NL_SET_ERR_MSG_MOD(extack, "Bad flow mark - only 16 bit is supported"); - return -EINVAL; + return -EOPNOTSUPP; } nic_attr->flow_tag = mark; @@ -3750,20 +3735,19 @@ static int verify_uplink_forwarding(struct mlx5e_priv *priv, static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct flow_action *flow_action, struct mlx5e_tc_flow *flow, - struct netlink_ext_ack *extack, - struct net_device *filter_dev) + struct netlink_ext_ack *extack) { struct pedit_headers_action hdrs[2] = {}; struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5e_tc_flow_parse_attr *parse_attr; struct mlx5e_rep_priv *rpriv = priv->ppriv; + struct mlx5e_sample_attr sample_attr = {}; const struct ip_tunnel_info *info = NULL; struct mlx5_flow_attr *attr = flow->attr; int ifindexes[MLX5_MAX_FLOW_FWD_VPORTS]; bool ft_flow = mlx5e_is_ft_flow(flow); const struct flow_action_entry *act; struct mlx5_esw_flow_attr *esw_attr; - struct mlx5_sample_attr sample = {}; bool encap = false, decap = false; u32 action = attr->action; int err, i, if_count = 0; @@ -3816,7 +3800,7 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, "mpls pop supported only as first action"); return -EOPNOTSUPP; } - if (!netif_is_bareudp(filter_dev)) { + if (!netif_is_bareudp(parse_attr->filter_dev)) { NL_SET_ERR_MSG_MOD(extack, "mpls pop supported only on bareudp devices"); return -EOPNOTSUPP; @@ -3965,7 +3949,7 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, "devices %s %s not on same switch HW, can't offload forwarding\n", priv->netdev->name, out_dev->name); - return -EINVAL; + return -EOPNOTSUPP; } } break; @@ -4034,10 +4018,10 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, NL_SET_ERR_MSG_MOD(extack, "Sample action with connection tracking is not supported"); return -EOPNOTSUPP; } - sample.rate = act->sample.rate; - sample.group_num = act->sample.psample_group->group_num; + sample_attr.rate = act->sample.rate; + sample_attr.group_num = act->sample.psample_group->group_num; if (act->sample.truncate) - sample.trunc_size = act->sample.trunc_size; + sample_attr.trunc_size = act->sample.trunc_size; flow_flag_set(flow, SAMPLE); break; default: @@ -4122,10 +4106,10 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, * no errors after parsing. */ if (flow_flag_test(flow, SAMPLE)) { - esw_attr->sample = kzalloc(sizeof(*esw_attr->sample), GFP_KERNEL); - if (!esw_attr->sample) + attr->sample_attr = kzalloc(sizeof(*attr->sample_attr), GFP_KERNEL); + if (!attr->sample_attr) return -ENOMEM; - *esw_attr->sample = sample; + *attr->sample_attr = sample_attr; } return 0; @@ -4318,7 +4302,7 @@ __mlx5e_add_fdb_flow(struct mlx5e_priv *priv, if (err) goto err_free; - err = parse_tc_fdb_actions(priv, &rule->action, flow, extack, filter_dev); + err = parse_tc_fdb_actions(priv, &rule->action, flow, extack); if (err) goto err_free; @@ -4464,11 +4448,11 @@ mlx5e_add_nic_flow(struct mlx5e_priv *priv, if (err) goto err_free; - err = parse_tc_nic_actions(priv, &rule->action, parse_attr, flow, extack); + err = parse_tc_nic_actions(priv, &rule->action, flow, extack); if (err) goto err_free; - err = mlx5e_tc_add_nic_flow(priv, parse_attr, flow, extack); + err = mlx5e_tc_add_nic_flow(priv, flow, extack); if (err) goto err_free; @@ -4723,7 +4707,7 @@ static int apply_police_params(struct mlx5e_priv *priv, u64 rate, rate_mbps = max_t(u32, rate, 1); } - err = mlx5_esw_modify_vport_rate(esw, vport_num, rate_mbps); + err = mlx5_esw_qos_modify_vport_rate(esw, vport_num, rate_mbps); if (err) NL_SET_ERR_MSG_MOD(extack, "failed applying action to hardware"); @@ -4895,6 +4879,7 @@ int mlx5e_tc_nic_init(struct mlx5e_priv *priv) struct mlx5_core_dev *dev = priv->mdev; struct mapping_ctx *chains_mapping; struct mlx5_chains_attr attr = {}; + u64 mapping_id; int err; mlx5e_mod_hdr_tbl_init(&tc->mod_hdr); @@ -4908,8 +4893,12 @@ int mlx5e_tc_nic_init(struct mlx5e_priv *priv) lockdep_set_class(&tc->ht.mutex, &tc_ht_lock_key); - chains_mapping = mapping_create(sizeof(struct mlx5_mapped_obj), - MLX5E_TC_TABLE_CHAIN_TAG_MASK, true); + mapping_id = mlx5_query_nic_system_image_guid(dev); + + chains_mapping = mapping_create_for_id(mapping_id, MAPPING_TYPE_CHAIN, + sizeof(struct mlx5_mapped_obj), + MLX5E_TC_TABLE_CHAIN_TAG_MASK, true); + if (IS_ERR(chains_mapping)) { err = PTR_ERR(chains_mapping); goto err_mapping; @@ -4931,8 +4920,9 @@ int mlx5e_tc_nic_init(struct mlx5e_priv *priv) goto err_chains; } + tc->post_act = mlx5e_tc_post_act_init(priv, tc->chains, MLX5_FLOW_NAMESPACE_KERNEL); tc->ct = mlx5_tc_ct_init(priv, tc->chains, &priv->fs.tc.mod_hdr, - MLX5_FLOW_NAMESPACE_KERNEL); + MLX5_FLOW_NAMESPACE_KERNEL, tc->post_act); tc->netdevice_nb.notifier_call = mlx5e_tc_netdev_event; err = register_netdevice_notifier_dev_net(priv->netdev, @@ -4948,6 +4938,7 @@ int mlx5e_tc_nic_init(struct mlx5e_priv *priv) err_reg: mlx5_tc_ct_clean(tc->ct); + mlx5e_tc_post_act_destroy(tc->post_act); mlx5_chains_destroy(tc->chains); err_chains: mapping_destroy(chains_mapping); @@ -4986,6 +4977,7 @@ void mlx5e_tc_nic_cleanup(struct mlx5e_priv *priv) mutex_destroy(&tc->t_lock); mlx5_tc_ct_clean(tc->ct); + mlx5e_tc_post_act_destroy(tc->post_act); mapping_destroy(tc->mapping); mlx5_chains_destroy(tc->chains); } @@ -4998,6 +4990,7 @@ int mlx5e_tc_esw_init(struct rhashtable *tc_ht) struct mapping_ctx *mapping; struct mlx5_eswitch *esw; struct mlx5e_priv *priv; + u64 mapping_id; int err = 0; uplink_priv = container_of(tc_ht, struct mlx5_rep_uplink_priv, tc_ht); @@ -5005,17 +4998,24 @@ int mlx5e_tc_esw_init(struct rhashtable *tc_ht) priv = netdev_priv(rpriv->netdev); esw = priv->mdev->priv.eswitch; + uplink_priv->post_act = mlx5e_tc_post_act_init(priv, esw_chains(esw), + MLX5_FLOW_NAMESPACE_FDB); uplink_priv->ct_priv = mlx5_tc_ct_init(netdev_priv(priv->netdev), esw_chains(esw), &esw->offloads.mod_hdr, - MLX5_FLOW_NAMESPACE_FDB); + MLX5_FLOW_NAMESPACE_FDB, + uplink_priv->post_act); #if IS_ENABLED(CONFIG_MLX5_TC_SAMPLE) - uplink_priv->esw_psample = mlx5_esw_sample_init(netdev_priv(priv->netdev)); + uplink_priv->tc_psample = mlx5e_tc_sample_init(esw, uplink_priv->post_act); #endif - mapping = mapping_create(sizeof(struct tunnel_match_key), - TUNNEL_INFO_BITS_MASK, true); + mapping_id = mlx5_query_nic_system_image_guid(esw->dev); + + mapping = mapping_create_for_id(mapping_id, MAPPING_TYPE_TUNNEL, + sizeof(struct tunnel_match_key), + TUNNEL_INFO_BITS_MASK, true); + if (IS_ERR(mapping)) { err = PTR_ERR(mapping); goto err_tun_mapping; @@ -5023,7 +5023,8 @@ int mlx5e_tc_esw_init(struct rhashtable *tc_ht) uplink_priv->tunnel_mapping = mapping; /* 0xFFF is reserved for stack devices slow path table mark */ - mapping = mapping_create(sz_enc_opts, ENC_OPTS_BITS_MASK - 1, true); + mapping = mapping_create_for_id(mapping_id, MAPPING_TYPE_TUNNEL_ENC_OPTS, + sz_enc_opts, ENC_OPTS_BITS_MASK - 1, true); if (IS_ERR(mapping)) { err = PTR_ERR(mapping); goto err_enc_opts_mapping; @@ -5052,11 +5053,12 @@ err_enc_opts_mapping: mapping_destroy(uplink_priv->tunnel_mapping); err_tun_mapping: #if IS_ENABLED(CONFIG_MLX5_TC_SAMPLE) - mlx5_esw_sample_cleanup(uplink_priv->esw_psample); + mlx5e_tc_sample_cleanup(uplink_priv->tc_psample); #endif mlx5_tc_ct_clean(uplink_priv->ct_priv); netdev_warn(priv->netdev, "Failed to initialize tc (eswitch), err: %d", err); + mlx5e_tc_post_act_destroy(uplink_priv->post_act); return err; } @@ -5073,9 +5075,10 @@ void mlx5e_tc_esw_cleanup(struct rhashtable *tc_ht) mapping_destroy(uplink_priv->tunnel_mapping); #if IS_ENABLED(CONFIG_MLX5_TC_SAMPLE) - mlx5_esw_sample_cleanup(uplink_priv->esw_psample); + mlx5e_tc_sample_cleanup(uplink_priv->tc_psample); #endif mlx5_tc_ct_clean(uplink_priv->ct_priv); + mlx5e_tc_post_act_destroy(uplink_priv->post_act); } int mlx5e_tc_num_filters(struct mlx5e_priv *priv, unsigned long flags) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h index f7cbeb0b66d2..1a4cd882f0fb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h @@ -70,6 +70,7 @@ struct mlx5_flow_attr { struct mlx5_fc *counter; struct mlx5_modify_hdr *modify_hdr; struct mlx5_ct_attr ct_attr; + struct mlx5e_sample_attr *sample_attr; struct mlx5e_tc_flow_parse_attr *parse_attr; u32 chain; u16 prio; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_ofld.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_ofld.c index 505bf811984a..2e504c7461c6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_ofld.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_ofld.c @@ -15,6 +15,15 @@ static void esw_acl_egress_ofld_fwd2vport_destroy(struct mlx5_vport *vport) vport->egress.offloads.fwd_rule = NULL; } +static void esw_acl_egress_ofld_bounce_rule_destroy(struct mlx5_vport *vport) +{ + if (!vport->egress.offloads.bounce_rule) + return; + + mlx5_del_flow_rules(vport->egress.offloads.bounce_rule); + vport->egress.offloads.bounce_rule = NULL; +} + static int esw_acl_egress_ofld_fwd2vport_create(struct mlx5_eswitch *esw, struct mlx5_vport *vport, struct mlx5_flow_destination *fwd_dest) @@ -87,6 +96,7 @@ static void esw_acl_egress_ofld_rules_destroy(struct mlx5_vport *vport) { esw_acl_egress_vlan_destroy(vport); esw_acl_egress_ofld_fwd2vport_destroy(vport); + esw_acl_egress_ofld_bounce_rule_destroy(vport); } static int esw_acl_egress_ofld_groups_create(struct mlx5_eswitch *esw, @@ -145,6 +155,12 @@ static void esw_acl_egress_ofld_groups_destroy(struct mlx5_vport *vport) mlx5_destroy_flow_group(vport->egress.offloads.fwd_grp); vport->egress.offloads.fwd_grp = NULL; } + + if (!IS_ERR_OR_NULL(vport->egress.offloads.bounce_grp)) { + mlx5_destroy_flow_group(vport->egress.offloads.bounce_grp); + vport->egress.offloads.bounce_grp = NULL; + } + esw_acl_egress_vlan_grp_destroy(vport); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c index 69a3630818d7..7e221038df8d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c @@ -5,6 +5,7 @@ #include <linux/notifier.h> #include <net/netevent.h> #include <net/switchdev.h> +#include "lib/devcom.h" #include "bridge.h" #include "eswitch.h" #include "bridge_priv.h" @@ -56,7 +57,6 @@ struct mlx5_esw_bridge { struct list_head fdb_list; struct rhashtable fdb_ht; - struct xarray vports; struct mlx5_flow_table *egress_ft; struct mlx5_flow_group *egress_vlan_fg; @@ -77,6 +77,15 @@ mlx5_esw_bridge_fdb_offload_notify(struct net_device *dev, const unsigned char * call_switchdev_notifiers(val, dev, &send_info.info, NULL); } +static void +mlx5_esw_bridge_fdb_del_notify(struct mlx5_esw_bridge_fdb_entry *entry) +{ + if (!(entry->flags & (MLX5_ESW_BRIDGE_FLAG_ADDED_BY_USER | MLX5_ESW_BRIDGE_FLAG_PEER))) + mlx5_esw_bridge_fdb_offload_notify(entry->dev, entry->key.addr, + entry->key.vid, + SWITCHDEV_FDB_DEL_TO_BRIDGE); +} + static struct mlx5_flow_table * mlx5_esw_bridge_table_create(int max_fte, u32 level, struct mlx5_eswitch *esw) { @@ -400,9 +409,10 @@ mlx5_esw_bridge_egress_table_cleanup(struct mlx5_esw_bridge *bridge) } static struct mlx5_flow_handle * -mlx5_esw_bridge_ingress_flow_create(u16 vport_num, const unsigned char *addr, - struct mlx5_esw_bridge_vlan *vlan, u32 counter_id, - struct mlx5_esw_bridge *bridge) +mlx5_esw_bridge_ingress_flow_with_esw_create(u16 vport_num, const unsigned char *addr, + struct mlx5_esw_bridge_vlan *vlan, u32 counter_id, + struct mlx5_esw_bridge *bridge, + struct mlx5_eswitch *esw) { struct mlx5_esw_bridge_offloads *br_offloads = bridge->br_offloads; struct mlx5_flow_act flow_act = { @@ -430,7 +440,7 @@ mlx5_esw_bridge_ingress_flow_create(u16 vport_num, const unsigned char *addr, MLX5_SET(fte_match_param, rule_spec->match_criteria, misc_parameters_2.metadata_reg_c_0, mlx5_eswitch_get_vport_metadata_mask()); MLX5_SET(fte_match_param, rule_spec->match_value, misc_parameters_2.metadata_reg_c_0, - mlx5_eswitch_get_vport_metadata_for_match(br_offloads->esw, vport_num)); + mlx5_eswitch_get_vport_metadata_for_match(esw, vport_num)); if (vlan && vlan->pkt_reformat_push) { flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT; @@ -459,6 +469,35 @@ mlx5_esw_bridge_ingress_flow_create(u16 vport_num, const unsigned char *addr, } static struct mlx5_flow_handle * +mlx5_esw_bridge_ingress_flow_create(u16 vport_num, const unsigned char *addr, + struct mlx5_esw_bridge_vlan *vlan, u32 counter_id, + struct mlx5_esw_bridge *bridge) +{ + return mlx5_esw_bridge_ingress_flow_with_esw_create(vport_num, addr, vlan, counter_id, + bridge, bridge->br_offloads->esw); +} + +static struct mlx5_flow_handle * +mlx5_esw_bridge_ingress_flow_peer_create(u16 vport_num, const unsigned char *addr, + struct mlx5_esw_bridge_vlan *vlan, u32 counter_id, + struct mlx5_esw_bridge *bridge) +{ + struct mlx5_devcom *devcom = bridge->br_offloads->esw->dev->priv.devcom; + static struct mlx5_flow_handle *handle; + struct mlx5_eswitch *peer_esw; + + peer_esw = mlx5_devcom_get_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS); + if (!peer_esw) + return ERR_PTR(-ENODEV); + + handle = mlx5_esw_bridge_ingress_flow_with_esw_create(vport_num, addr, vlan, counter_id, + bridge, peer_esw); + + mlx5_devcom_release_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS); + return handle; +} + +static struct mlx5_flow_handle * mlx5_esw_bridge_ingress_filter_flow_create(u16 vport_num, const unsigned char *addr, struct mlx5_esw_bridge *bridge) { @@ -505,7 +544,7 @@ mlx5_esw_bridge_ingress_filter_flow_create(u16 vport_num, const unsigned char *a } static struct mlx5_flow_handle * -mlx5_esw_bridge_egress_flow_create(u16 vport_num, const unsigned char *addr, +mlx5_esw_bridge_egress_flow_create(u16 vport_num, u16 esw_owner_vhca_id, const unsigned char *addr, struct mlx5_esw_bridge_vlan *vlan, struct mlx5_esw_bridge *bridge) { @@ -550,6 +589,10 @@ mlx5_esw_bridge_egress_flow_create(u16 vport_num, const unsigned char *addr, vlan->vid); } + if (MLX5_CAP_ESW(bridge->br_offloads->esw->dev, merged_eswitch)) { + dest.vport.flags = MLX5_FLOW_DEST_VPORT_VHCA_ID; + dest.vport.vhca_id = esw_owner_vhca_id; + } handle = mlx5_add_flow_rules(bridge->egress_ft, rule_spec, &flow_act, &dest, 1); kvfree(rule_spec); @@ -576,7 +619,6 @@ static struct mlx5_esw_bridge *mlx5_esw_bridge_create(int ifindex, goto err_fdb_ht; INIT_LIST_HEAD(&bridge->fdb_list); - xa_init(&bridge->vports); bridge->ifindex = ifindex; bridge->refcnt = 1; bridge->ageing_time = clock_t_to_jiffies(BR_DEFAULT_AGEING_TIME); @@ -603,7 +645,6 @@ static void mlx5_esw_bridge_put(struct mlx5_esw_bridge_offloads *br_offloads, return; mlx5_esw_bridge_egress_table_cleanup(bridge); - WARN_ON(!xa_empty(&bridge->vports)); list_del(&bridge->list); rhashtable_destroy(&bridge->fdb_ht); kvfree(bridge); @@ -639,30 +680,40 @@ mlx5_esw_bridge_lookup(int ifindex, struct mlx5_esw_bridge_offloads *br_offloads return bridge; } +static unsigned long mlx5_esw_bridge_port_key_from_data(u16 vport_num, u16 esw_owner_vhca_id) +{ + return vport_num | (unsigned long)esw_owner_vhca_id << sizeof(vport_num) * BITS_PER_BYTE; +} + +static unsigned long mlx5_esw_bridge_port_key(struct mlx5_esw_bridge_port *port) +{ + return mlx5_esw_bridge_port_key_from_data(port->vport_num, port->esw_owner_vhca_id); +} + static int mlx5_esw_bridge_port_insert(struct mlx5_esw_bridge_port *port, - struct mlx5_esw_bridge *bridge) + struct mlx5_esw_bridge_offloads *br_offloads) { - return xa_insert(&bridge->vports, port->vport_num, port, GFP_KERNEL); + return xa_insert(&br_offloads->ports, mlx5_esw_bridge_port_key(port), port, GFP_KERNEL); } static struct mlx5_esw_bridge_port * -mlx5_esw_bridge_port_lookup(u16 vport_num, struct mlx5_esw_bridge *bridge) +mlx5_esw_bridge_port_lookup(u16 vport_num, u16 esw_owner_vhca_id, + struct mlx5_esw_bridge_offloads *br_offloads) { - return xa_load(&bridge->vports, vport_num); + return xa_load(&br_offloads->ports, mlx5_esw_bridge_port_key_from_data(vport_num, + esw_owner_vhca_id)); } static void mlx5_esw_bridge_port_erase(struct mlx5_esw_bridge_port *port, - struct mlx5_esw_bridge *bridge) + struct mlx5_esw_bridge_offloads *br_offloads) { - xa_erase(&bridge->vports, port->vport_num); + xa_erase(&br_offloads->ports, mlx5_esw_bridge_port_key(port)); } -static void mlx5_esw_bridge_fdb_entry_refresh(unsigned long lastuse, - struct mlx5_esw_bridge_fdb_entry *entry) +static void mlx5_esw_bridge_fdb_entry_refresh(struct mlx5_esw_bridge_fdb_entry *entry) { trace_mlx5_esw_bridge_fdb_entry_refresh(entry); - entry->lastuse = lastuse; mlx5_esw_bridge_fdb_offload_notify(entry->dev, entry->key.addr, entry->key.vid, SWITCHDEV_FDB_ADD_TO_BRIDGE); @@ -690,10 +741,7 @@ static void mlx5_esw_bridge_fdb_flush(struct mlx5_esw_bridge *bridge) struct mlx5_esw_bridge_fdb_entry *entry, *tmp; list_for_each_entry_safe(entry, tmp, &bridge->fdb_list, list) { - if (!(entry->flags & MLX5_ESW_BRIDGE_FLAG_ADDED_BY_USER)) - mlx5_esw_bridge_fdb_offload_notify(entry->dev, entry->key.addr, - entry->key.vid, - SWITCHDEV_FDB_DEL_TO_BRIDGE); + mlx5_esw_bridge_fdb_del_notify(entry); mlx5_esw_bridge_fdb_entry_cleanup(entry, bridge); } } @@ -841,10 +889,7 @@ static void mlx5_esw_bridge_vlan_flush(struct mlx5_esw_bridge_vlan *vlan, struct mlx5_esw_bridge_fdb_entry *entry, *tmp; list_for_each_entry_safe(entry, tmp, &vlan->fdb_list, vlan_list) { - if (!(entry->flags & MLX5_ESW_BRIDGE_FLAG_ADDED_BY_USER)) - mlx5_esw_bridge_fdb_offload_notify(entry->dev, entry->key.addr, - entry->key.vid, - SWITCHDEV_FDB_DEL_TO_BRIDGE); + mlx5_esw_bridge_fdb_del_notify(entry); mlx5_esw_bridge_fdb_entry_cleanup(entry, bridge); } @@ -875,13 +920,13 @@ static void mlx5_esw_bridge_port_vlans_flush(struct mlx5_esw_bridge_port *port, } static struct mlx5_esw_bridge_vlan * -mlx5_esw_bridge_port_vlan_lookup(u16 vid, u16 vport_num, struct mlx5_esw_bridge *bridge, - struct mlx5_eswitch *esw) +mlx5_esw_bridge_port_vlan_lookup(u16 vid, u16 vport_num, u16 esw_owner_vhca_id, + struct mlx5_esw_bridge *bridge, struct mlx5_eswitch *esw) { struct mlx5_esw_bridge_port *port; struct mlx5_esw_bridge_vlan *vlan; - port = mlx5_esw_bridge_port_lookup(vport_num, bridge); + port = mlx5_esw_bridge_port_lookup(vport_num, esw_owner_vhca_id, bridge->br_offloads); if (!port) { /* FDB is added asynchronously on wq while port might have been deleted * concurrently. Report on 'info' logging level and skip the FDB offload. @@ -904,24 +949,23 @@ mlx5_esw_bridge_port_vlan_lookup(u16 vid, u16 vport_num, struct mlx5_esw_bridge } static struct mlx5_esw_bridge_fdb_entry * -mlx5_esw_bridge_fdb_entry_init(struct net_device *dev, u16 vport_num, const unsigned char *addr, - u16 vid, bool added_by_user, struct mlx5_eswitch *esw, - struct mlx5_esw_bridge *bridge) +mlx5_esw_bridge_fdb_entry_init(struct net_device *dev, u16 vport_num, u16 esw_owner_vhca_id, + const unsigned char *addr, u16 vid, bool added_by_user, bool peer, + struct mlx5_eswitch *esw, struct mlx5_esw_bridge *bridge) { struct mlx5_esw_bridge_vlan *vlan = NULL; struct mlx5_esw_bridge_fdb_entry *entry; struct mlx5_flow_handle *handle; struct mlx5_fc *counter; - struct mlx5e_priv *priv; int err; if (bridge->flags & MLX5_ESW_BRIDGE_VLAN_FILTERING_FLAG && vid) { - vlan = mlx5_esw_bridge_port_vlan_lookup(vid, vport_num, bridge, esw); + vlan = mlx5_esw_bridge_port_vlan_lookup(vid, vport_num, esw_owner_vhca_id, bridge, + esw); if (IS_ERR(vlan)) return ERR_CAST(vlan); } - priv = netdev_priv(dev); entry = kvzalloc(sizeof(*entry), GFP_KERNEL); if (!entry) return ERR_PTR(-ENOMEM); @@ -930,19 +974,25 @@ mlx5_esw_bridge_fdb_entry_init(struct net_device *dev, u16 vport_num, const unsi entry->key.vid = vid; entry->dev = dev; entry->vport_num = vport_num; + entry->esw_owner_vhca_id = esw_owner_vhca_id; entry->lastuse = jiffies; if (added_by_user) entry->flags |= MLX5_ESW_BRIDGE_FLAG_ADDED_BY_USER; + if (peer) + entry->flags |= MLX5_ESW_BRIDGE_FLAG_PEER; - counter = mlx5_fc_create(priv->mdev, true); + counter = mlx5_fc_create(esw->dev, true); if (IS_ERR(counter)) { err = PTR_ERR(counter); goto err_ingress_fc_create; } entry->ingress_counter = counter; - handle = mlx5_esw_bridge_ingress_flow_create(vport_num, addr, vlan, mlx5_fc_id(counter), - bridge); + handle = peer ? + mlx5_esw_bridge_ingress_flow_peer_create(vport_num, addr, vlan, + mlx5_fc_id(counter), bridge) : + mlx5_esw_bridge_ingress_flow_create(vport_num, addr, vlan, + mlx5_fc_id(counter), bridge); if (IS_ERR(handle)) { err = PTR_ERR(handle); esw_warn(esw->dev, "Failed to create ingress flow(vport=%u,err=%d)\n", @@ -962,7 +1012,8 @@ mlx5_esw_bridge_fdb_entry_init(struct net_device *dev, u16 vport_num, const unsi entry->filter_handle = handle; } - handle = mlx5_esw_bridge_egress_flow_create(vport_num, addr, vlan, bridge); + handle = mlx5_esw_bridge_egress_flow_create(vport_num, esw_owner_vhca_id, addr, vlan, + bridge); if (IS_ERR(handle)) { err = PTR_ERR(handle); esw_warn(esw->dev, "Failed to create egress flow(vport=%u,err=%d)\n", @@ -994,32 +1045,37 @@ err_egress_flow_create: err_ingress_filter_flow_create: mlx5_del_flow_rules(entry->ingress_handle); err_ingress_flow_create: - mlx5_fc_destroy(priv->mdev, entry->ingress_counter); + mlx5_fc_destroy(esw->dev, entry->ingress_counter); err_ingress_fc_create: kvfree(entry); return ERR_PTR(err); } -int mlx5_esw_bridge_ageing_time_set(unsigned long ageing_time, struct mlx5_eswitch *esw, - struct mlx5_vport *vport) +int mlx5_esw_bridge_ageing_time_set(u16 vport_num, u16 esw_owner_vhca_id, unsigned long ageing_time, + struct mlx5_esw_bridge_offloads *br_offloads) { - if (!vport->bridge) + struct mlx5_esw_bridge_port *port; + + port = mlx5_esw_bridge_port_lookup(vport_num, esw_owner_vhca_id, br_offloads); + if (!port) return -EINVAL; - vport->bridge->ageing_time = clock_t_to_jiffies(ageing_time); + port->bridge->ageing_time = clock_t_to_jiffies(ageing_time); return 0; } -int mlx5_esw_bridge_vlan_filtering_set(bool enable, struct mlx5_eswitch *esw, - struct mlx5_vport *vport) +int mlx5_esw_bridge_vlan_filtering_set(u16 vport_num, u16 esw_owner_vhca_id, bool enable, + struct mlx5_esw_bridge_offloads *br_offloads) { + struct mlx5_esw_bridge_port *port; struct mlx5_esw_bridge *bridge; bool filtering; - if (!vport->bridge) + port = mlx5_esw_bridge_port_lookup(vport_num, esw_owner_vhca_id, br_offloads); + if (!port) return -EINVAL; - bridge = vport->bridge; + bridge = port->bridge; filtering = bridge->flags & MLX5_ESW_BRIDGE_VLAN_FILTERING_FLAG; if (filtering == enable) return 0; @@ -1033,114 +1089,143 @@ int mlx5_esw_bridge_vlan_filtering_set(bool enable, struct mlx5_eswitch *esw, return 0; } -static int mlx5_esw_bridge_vport_init(struct mlx5_esw_bridge_offloads *br_offloads, - struct mlx5_esw_bridge *bridge, - struct mlx5_vport *vport) +static int mlx5_esw_bridge_vport_init(u16 vport_num, u16 esw_owner_vhca_id, u16 flags, + struct mlx5_esw_bridge_offloads *br_offloads, + struct mlx5_esw_bridge *bridge) { struct mlx5_eswitch *esw = br_offloads->esw; struct mlx5_esw_bridge_port *port; int err; port = kvzalloc(sizeof(*port), GFP_KERNEL); - if (!port) { - err = -ENOMEM; - goto err_port_alloc; - } + if (!port) + return -ENOMEM; - port->vport_num = vport->vport; + port->vport_num = vport_num; + port->esw_owner_vhca_id = esw_owner_vhca_id; + port->bridge = bridge; + port->flags |= flags; xa_init(&port->vlans); - err = mlx5_esw_bridge_port_insert(port, bridge); + err = mlx5_esw_bridge_port_insert(port, br_offloads); if (err) { - esw_warn(esw->dev, "Failed to insert port metadata (vport=%u,err=%d)\n", - vport->vport, err); + esw_warn(esw->dev, + "Failed to insert port metadata (vport=%u,esw_owner_vhca_id=%u,err=%d)\n", + port->vport_num, port->esw_owner_vhca_id, err); goto err_port_insert; } trace_mlx5_esw_bridge_vport_init(port); - vport->bridge = bridge; return 0; err_port_insert: kvfree(port); -err_port_alloc: - mlx5_esw_bridge_put(br_offloads, bridge); return err; } static int mlx5_esw_bridge_vport_cleanup(struct mlx5_esw_bridge_offloads *br_offloads, - struct mlx5_vport *vport) + struct mlx5_esw_bridge_port *port) { - struct mlx5_esw_bridge *bridge = vport->bridge; + u16 vport_num = port->vport_num, esw_owner_vhca_id = port->esw_owner_vhca_id; + struct mlx5_esw_bridge *bridge = port->bridge; struct mlx5_esw_bridge_fdb_entry *entry, *tmp; - struct mlx5_esw_bridge_port *port; list_for_each_entry_safe(entry, tmp, &bridge->fdb_list, list) - if (entry->vport_num == vport->vport) + if (entry->vport_num == vport_num && entry->esw_owner_vhca_id == esw_owner_vhca_id) mlx5_esw_bridge_fdb_entry_cleanup(entry, bridge); - port = mlx5_esw_bridge_port_lookup(vport->vport, bridge); - if (!port) { - WARN(1, "Vport %u metadata not found on bridge", vport->vport); - return -EINVAL; - } - trace_mlx5_esw_bridge_vport_cleanup(port); mlx5_esw_bridge_port_vlans_flush(port, bridge); - mlx5_esw_bridge_port_erase(port, bridge); + mlx5_esw_bridge_port_erase(port, br_offloads); kvfree(port); mlx5_esw_bridge_put(br_offloads, bridge); - vport->bridge = NULL; return 0; } -int mlx5_esw_bridge_vport_link(int ifindex, struct mlx5_esw_bridge_offloads *br_offloads, - struct mlx5_vport *vport, struct netlink_ext_ack *extack) +static int mlx5_esw_bridge_vport_link_with_flags(int ifindex, u16 vport_num, u16 esw_owner_vhca_id, + u16 flags, + struct mlx5_esw_bridge_offloads *br_offloads, + struct netlink_ext_ack *extack) { struct mlx5_esw_bridge *bridge; int err; - WARN_ON(vport->bridge); - bridge = mlx5_esw_bridge_lookup(ifindex, br_offloads); if (IS_ERR(bridge)) { NL_SET_ERR_MSG_MOD(extack, "Error checking for existing bridge with same ifindex"); return PTR_ERR(bridge); } - err = mlx5_esw_bridge_vport_init(br_offloads, bridge, vport); - if (err) + err = mlx5_esw_bridge_vport_init(vport_num, esw_owner_vhca_id, flags, br_offloads, bridge); + if (err) { NL_SET_ERR_MSG_MOD(extack, "Error initializing port"); + goto err_vport; + } + return 0; + +err_vport: + mlx5_esw_bridge_put(br_offloads, bridge); return err; } -int mlx5_esw_bridge_vport_unlink(int ifindex, struct mlx5_esw_bridge_offloads *br_offloads, - struct mlx5_vport *vport, struct netlink_ext_ack *extack) +int mlx5_esw_bridge_vport_link(int ifindex, u16 vport_num, u16 esw_owner_vhca_id, + struct mlx5_esw_bridge_offloads *br_offloads, + struct netlink_ext_ack *extack) { - struct mlx5_esw_bridge *bridge = vport->bridge; + return mlx5_esw_bridge_vport_link_with_flags(ifindex, vport_num, esw_owner_vhca_id, 0, + br_offloads, extack); +} + +int mlx5_esw_bridge_vport_unlink(int ifindex, u16 vport_num, u16 esw_owner_vhca_id, + struct mlx5_esw_bridge_offloads *br_offloads, + struct netlink_ext_ack *extack) +{ + struct mlx5_esw_bridge_port *port; int err; - if (!bridge) { + port = mlx5_esw_bridge_port_lookup(vport_num, esw_owner_vhca_id, br_offloads); + if (!port) { NL_SET_ERR_MSG_MOD(extack, "Port is not attached to any bridge"); return -EINVAL; } - if (bridge->ifindex != ifindex) { + if (port->bridge->ifindex != ifindex) { NL_SET_ERR_MSG_MOD(extack, "Port is attached to another bridge"); return -EINVAL; } - err = mlx5_esw_bridge_vport_cleanup(br_offloads, vport); + err = mlx5_esw_bridge_vport_cleanup(br_offloads, port); if (err) NL_SET_ERR_MSG_MOD(extack, "Port cleanup failed"); return err; } -int mlx5_esw_bridge_port_vlan_add(u16 vid, u16 flags, struct mlx5_eswitch *esw, - struct mlx5_vport *vport, struct netlink_ext_ack *extack) +int mlx5_esw_bridge_vport_peer_link(int ifindex, u16 vport_num, u16 esw_owner_vhca_id, + struct mlx5_esw_bridge_offloads *br_offloads, + struct netlink_ext_ack *extack) +{ + if (!MLX5_CAP_ESW(br_offloads->esw->dev, merged_eswitch)) + return 0; + + return mlx5_esw_bridge_vport_link_with_flags(ifindex, vport_num, esw_owner_vhca_id, + MLX5_ESW_BRIDGE_PORT_FLAG_PEER, + br_offloads, extack); +} + +int mlx5_esw_bridge_vport_peer_unlink(int ifindex, u16 vport_num, u16 esw_owner_vhca_id, + struct mlx5_esw_bridge_offloads *br_offloads, + struct netlink_ext_ack *extack) +{ + return mlx5_esw_bridge_vport_unlink(ifindex, vport_num, esw_owner_vhca_id, br_offloads, + extack); +} + +int mlx5_esw_bridge_port_vlan_add(u16 vport_num, u16 esw_owner_vhca_id, u16 vid, u16 flags, + struct mlx5_esw_bridge_offloads *br_offloads, + struct netlink_ext_ack *extack) { struct mlx5_esw_bridge_port *port; struct mlx5_esw_bridge_vlan *vlan; - port = mlx5_esw_bridge_port_lookup(vport->vport, vport->bridge); + port = mlx5_esw_bridge_port_lookup(vport_num, esw_owner_vhca_id, br_offloads); if (!port) return -EINVAL; @@ -1148,10 +1233,10 @@ int mlx5_esw_bridge_port_vlan_add(u16 vid, u16 flags, struct mlx5_eswitch *esw, if (vlan) { if (vlan->flags == flags) return 0; - mlx5_esw_bridge_vlan_cleanup(port, vlan, vport->bridge); + mlx5_esw_bridge_vlan_cleanup(port, vlan, port->bridge); } - vlan = mlx5_esw_bridge_vlan_create(vid, flags, port, esw); + vlan = mlx5_esw_bridge_vlan_create(vid, flags, port, br_offloads->esw); if (IS_ERR(vlan)) { NL_SET_ERR_MSG_MOD(extack, "Failed to create VLAN entry"); return PTR_ERR(vlan); @@ -1159,62 +1244,93 @@ int mlx5_esw_bridge_port_vlan_add(u16 vid, u16 flags, struct mlx5_eswitch *esw, return 0; } -void mlx5_esw_bridge_port_vlan_del(u16 vid, struct mlx5_eswitch *esw, struct mlx5_vport *vport) +void mlx5_esw_bridge_port_vlan_del(u16 vport_num, u16 esw_owner_vhca_id, u16 vid, + struct mlx5_esw_bridge_offloads *br_offloads) { struct mlx5_esw_bridge_port *port; struct mlx5_esw_bridge_vlan *vlan; - port = mlx5_esw_bridge_port_lookup(vport->vport, vport->bridge); + port = mlx5_esw_bridge_port_lookup(vport_num, esw_owner_vhca_id, br_offloads); if (!port) return; vlan = mlx5_esw_bridge_vlan_lookup(vid, port); if (!vlan) return; - mlx5_esw_bridge_vlan_cleanup(port, vlan, vport->bridge); + mlx5_esw_bridge_vlan_cleanup(port, vlan, port->bridge); } -void mlx5_esw_bridge_fdb_create(struct net_device *dev, struct mlx5_eswitch *esw, - struct mlx5_vport *vport, - struct switchdev_notifier_fdb_info *fdb_info) +void mlx5_esw_bridge_fdb_update_used(struct net_device *dev, u16 vport_num, u16 esw_owner_vhca_id, + struct mlx5_esw_bridge_offloads *br_offloads, + struct switchdev_notifier_fdb_info *fdb_info) { - struct mlx5_esw_bridge *bridge = vport->bridge; struct mlx5_esw_bridge_fdb_entry *entry; - u16 vport_num = vport->vport; + struct mlx5_esw_bridge_fdb_key key; + struct mlx5_esw_bridge_port *port; + struct mlx5_esw_bridge *bridge; - if (!bridge) { - esw_info(esw->dev, "Vport is not assigned to bridge (vport=%u)\n", vport_num); + port = mlx5_esw_bridge_port_lookup(vport_num, esw_owner_vhca_id, br_offloads); + if (!port || port->flags & MLX5_ESW_BRIDGE_PORT_FLAG_PEER) + return; + + bridge = port->bridge; + ether_addr_copy(key.addr, fdb_info->addr); + key.vid = fdb_info->vid; + entry = rhashtable_lookup_fast(&bridge->fdb_ht, &key, fdb_ht_params); + if (!entry) { + esw_debug(br_offloads->esw->dev, + "FDB entry with specified key not found (MAC=%pM,vid=%u,vport=%u)\n", + key.addr, key.vid, vport_num); return; } - entry = mlx5_esw_bridge_fdb_entry_init(dev, vport_num, fdb_info->addr, fdb_info->vid, - fdb_info->added_by_user, esw, bridge); + entry->lastuse = jiffies; +} + +void mlx5_esw_bridge_fdb_create(struct net_device *dev, u16 vport_num, u16 esw_owner_vhca_id, + struct mlx5_esw_bridge_offloads *br_offloads, + struct switchdev_notifier_fdb_info *fdb_info) +{ + struct mlx5_esw_bridge_fdb_entry *entry; + struct mlx5_esw_bridge_port *port; + struct mlx5_esw_bridge *bridge; + + port = mlx5_esw_bridge_port_lookup(vport_num, esw_owner_vhca_id, br_offloads); + if (!port) + return; + + bridge = port->bridge; + entry = mlx5_esw_bridge_fdb_entry_init(dev, vport_num, esw_owner_vhca_id, fdb_info->addr, + fdb_info->vid, fdb_info->added_by_user, + port->flags & MLX5_ESW_BRIDGE_PORT_FLAG_PEER, + br_offloads->esw, bridge); if (IS_ERR(entry)) return; if (entry->flags & MLX5_ESW_BRIDGE_FLAG_ADDED_BY_USER) mlx5_esw_bridge_fdb_offload_notify(dev, entry->key.addr, entry->key.vid, SWITCHDEV_FDB_OFFLOADED); - else + else if (!(entry->flags & MLX5_ESW_BRIDGE_FLAG_PEER)) /* Take over dynamic entries to prevent kernel bridge from aging them out. */ mlx5_esw_bridge_fdb_offload_notify(dev, entry->key.addr, entry->key.vid, SWITCHDEV_FDB_ADD_TO_BRIDGE); } -void mlx5_esw_bridge_fdb_remove(struct net_device *dev, struct mlx5_eswitch *esw, - struct mlx5_vport *vport, +void mlx5_esw_bridge_fdb_remove(struct net_device *dev, u16 vport_num, u16 esw_owner_vhca_id, + struct mlx5_esw_bridge_offloads *br_offloads, struct switchdev_notifier_fdb_info *fdb_info) { - struct mlx5_esw_bridge *bridge = vport->bridge; + struct mlx5_eswitch *esw = br_offloads->esw; struct mlx5_esw_bridge_fdb_entry *entry; struct mlx5_esw_bridge_fdb_key key; - u16 vport_num = vport->vport; + struct mlx5_esw_bridge_port *port; + struct mlx5_esw_bridge *bridge; - if (!bridge) { - esw_warn(esw->dev, "Vport is not assigned to bridge (vport=%u)\n", vport_num); + port = mlx5_esw_bridge_port_lookup(vport_num, esw_owner_vhca_id, br_offloads); + if (!port) return; - } + bridge = port->bridge; ether_addr_copy(key.addr, fdb_info->addr); key.vid = fdb_info->vid; entry = rhashtable_lookup_fast(&bridge->fdb_ht, &key, fdb_ht_params); @@ -1225,9 +1341,7 @@ void mlx5_esw_bridge_fdb_remove(struct net_device *dev, struct mlx5_eswitch *esw return; } - if (!(entry->flags & MLX5_ESW_BRIDGE_FLAG_ADDED_BY_USER)) - mlx5_esw_bridge_fdb_offload_notify(dev, entry->key.addr, entry->key.vid, - SWITCHDEV_FDB_DEL_TO_BRIDGE); + mlx5_esw_bridge_fdb_del_notify(entry); mlx5_esw_bridge_fdb_entry_cleanup(entry, bridge); } @@ -1245,11 +1359,10 @@ void mlx5_esw_bridge_update(struct mlx5_esw_bridge_offloads *br_offloads) continue; if (time_after(lastuse, entry->lastuse)) { - mlx5_esw_bridge_fdb_entry_refresh(lastuse, entry); - } else if (time_is_before_jiffies(entry->lastuse + bridge->ageing_time)) { - mlx5_esw_bridge_fdb_offload_notify(entry->dev, entry->key.addr, - entry->key.vid, - SWITCHDEV_FDB_DEL_TO_BRIDGE); + mlx5_esw_bridge_fdb_entry_refresh(entry); + } else if (!(entry->flags & MLX5_ESW_BRIDGE_FLAG_PEER) && + time_is_before_jiffies(entry->lastuse + bridge->ageing_time)) { + mlx5_esw_bridge_fdb_del_notify(entry); mlx5_esw_bridge_fdb_entry_cleanup(entry, bridge); } } @@ -1258,13 +1371,11 @@ void mlx5_esw_bridge_update(struct mlx5_esw_bridge_offloads *br_offloads) static void mlx5_esw_bridge_flush(struct mlx5_esw_bridge_offloads *br_offloads) { - struct mlx5_eswitch *esw = br_offloads->esw; - struct mlx5_vport *vport; + struct mlx5_esw_bridge_port *port; unsigned long i; - mlx5_esw_for_each_vport(esw, i, vport) - if (vport->bridge) - mlx5_esw_bridge_vport_cleanup(br_offloads, vport); + xa_for_each(&br_offloads->ports, i, port) + mlx5_esw_bridge_vport_cleanup(br_offloads, port); WARN_ONCE(!list_empty(&br_offloads->bridges), "Cleaning up bridge offloads while still having bridges attached\n"); @@ -1279,6 +1390,7 @@ struct mlx5_esw_bridge_offloads *mlx5_esw_bridge_init(struct mlx5_eswitch *esw) return ERR_PTR(-ENOMEM); INIT_LIST_HEAD(&br_offloads->bridges); + xa_init(&br_offloads->ports); br_offloads->esw = esw; esw->br_offloads = br_offloads; @@ -1293,6 +1405,7 @@ void mlx5_esw_bridge_cleanup(struct mlx5_eswitch *esw) return; mlx5_esw_bridge_flush(br_offloads); + WARN_ON(!xa_empty(&br_offloads->ports)); esw->br_offloads = NULL; kvfree(br_offloads); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.h index d826942b27fc..efc39975226e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.h @@ -7,6 +7,7 @@ #include <linux/notifier.h> #include <linux/list.h> #include <linux/workqueue.h> +#include <linux/xarray.h> #include "eswitch.h" struct mlx5_flow_table; @@ -15,6 +16,8 @@ struct mlx5_flow_group; struct mlx5_esw_bridge_offloads { struct mlx5_eswitch *esw; struct list_head bridges; + struct xarray ports; + struct notifier_block netdev_nb; struct notifier_block nb_blk; struct notifier_block nb; @@ -31,23 +34,36 @@ struct mlx5_esw_bridge_offloads { struct mlx5_esw_bridge_offloads *mlx5_esw_bridge_init(struct mlx5_eswitch *esw); void mlx5_esw_bridge_cleanup(struct mlx5_eswitch *esw); -int mlx5_esw_bridge_vport_link(int ifindex, struct mlx5_esw_bridge_offloads *br_offloads, - struct mlx5_vport *vport, struct netlink_ext_ack *extack); -int mlx5_esw_bridge_vport_unlink(int ifindex, struct mlx5_esw_bridge_offloads *br_offloads, - struct mlx5_vport *vport, struct netlink_ext_ack *extack); -void mlx5_esw_bridge_fdb_create(struct net_device *dev, struct mlx5_eswitch *esw, - struct mlx5_vport *vport, +int mlx5_esw_bridge_vport_link(int ifindex, u16 vport_num, u16 esw_owner_vhca_id, + struct mlx5_esw_bridge_offloads *br_offloads, + struct netlink_ext_ack *extack); +int mlx5_esw_bridge_vport_unlink(int ifindex, u16 vport_num, u16 esw_owner_vhca_id, + struct mlx5_esw_bridge_offloads *br_offloads, + struct netlink_ext_ack *extack); +int mlx5_esw_bridge_vport_peer_link(int ifindex, u16 vport_num, u16 esw_owner_vhca_id, + struct mlx5_esw_bridge_offloads *br_offloads, + struct netlink_ext_ack *extack); +int mlx5_esw_bridge_vport_peer_unlink(int ifindex, u16 vport_num, u16 esw_owner_vhca_id, + struct mlx5_esw_bridge_offloads *br_offloads, + struct netlink_ext_ack *extack); +void mlx5_esw_bridge_fdb_update_used(struct net_device *dev, u16 vport_num, u16 esw_owner_vhca_id, + struct mlx5_esw_bridge_offloads *br_offloads, + struct switchdev_notifier_fdb_info *fdb_info); +void mlx5_esw_bridge_fdb_create(struct net_device *dev, u16 vport_num, u16 esw_owner_vhca_id, + struct mlx5_esw_bridge_offloads *br_offloads, struct switchdev_notifier_fdb_info *fdb_info); -void mlx5_esw_bridge_fdb_remove(struct net_device *dev, struct mlx5_eswitch *esw, - struct mlx5_vport *vport, +void mlx5_esw_bridge_fdb_remove(struct net_device *dev, u16 vport_num, u16 esw_owner_vhca_id, + struct mlx5_esw_bridge_offloads *br_offloads, struct switchdev_notifier_fdb_info *fdb_info); void mlx5_esw_bridge_update(struct mlx5_esw_bridge_offloads *br_offloads); -int mlx5_esw_bridge_ageing_time_set(unsigned long ageing_time, struct mlx5_eswitch *esw, - struct mlx5_vport *vport); -int mlx5_esw_bridge_vlan_filtering_set(bool enable, struct mlx5_eswitch *esw, - struct mlx5_vport *vport); -int mlx5_esw_bridge_port_vlan_add(u16 vid, u16 flags, struct mlx5_eswitch *esw, - struct mlx5_vport *vport, struct netlink_ext_ack *extack); -void mlx5_esw_bridge_port_vlan_del(u16 vid, struct mlx5_eswitch *esw, struct mlx5_vport *vport); +int mlx5_esw_bridge_ageing_time_set(u16 vport_num, u16 esw_owner_vhca_id, unsigned long ageing_time, + struct mlx5_esw_bridge_offloads *br_offloads); +int mlx5_esw_bridge_vlan_filtering_set(u16 vport_num, u16 esw_owner_vhca_id, bool enable, + struct mlx5_esw_bridge_offloads *br_offloads); +int mlx5_esw_bridge_port_vlan_add(u16 vport_num, u16 esw_owner_vhca_id, u16 vid, u16 flags, + struct mlx5_esw_bridge_offloads *br_offloads, + struct netlink_ext_ack *extack); +void mlx5_esw_bridge_port_vlan_del(u16 vport_num, u16 esw_owner_vhca_id, u16 vid, + struct mlx5_esw_bridge_offloads *br_offloads); #endif /* __MLX5_ESW_BRIDGE_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_priv.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_priv.h index d9ab2e8bc2cb..52964a82d6a6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_priv.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_priv.h @@ -19,6 +19,11 @@ struct mlx5_esw_bridge_fdb_key { enum { MLX5_ESW_BRIDGE_FLAG_ADDED_BY_USER = BIT(0), + MLX5_ESW_BRIDGE_FLAG_PEER = BIT(1), +}; + +enum { + MLX5_ESW_BRIDGE_PORT_FLAG_PEER = BIT(0), }; struct mlx5_esw_bridge_fdb_entry { @@ -28,6 +33,7 @@ struct mlx5_esw_bridge_fdb_entry { struct list_head list; struct list_head vlan_list; u16 vport_num; + u16 esw_owner_vhca_id; u16 flags; struct mlx5_flow_handle *ingress_handle; @@ -47,6 +53,9 @@ struct mlx5_esw_bridge_vlan { struct mlx5_esw_bridge_port { u16 vport_num; + u16 esw_owner_vhca_id; + u16 flags; + struct mlx5_esw_bridge *bridge; struct xarray vlans; }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c index 1703384eca95..20af557ae30c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c @@ -91,9 +91,15 @@ int mlx5_esw_offloads_devlink_port_register(struct mlx5_eswitch *esw, u16 vport_ if (err) goto reg_err; + err = devlink_rate_leaf_create(dl_port, vport); + if (err) + goto rate_err; + vport->dl_port = dl_port; return 0; +rate_err: + devlink_port_unregister(dl_port); reg_err: mlx5_esw_dl_port_free(dl_port); return err; @@ -109,6 +115,12 @@ void mlx5_esw_offloads_devlink_port_unregister(struct mlx5_eswitch *esw, u16 vpo vport = mlx5_eswitch_get_vport(esw, vport_num); if (IS_ERR(vport)) return; + + if (vport->dl_port->devlink_rate) { + mlx5_esw_qos_vport_update_group(esw, vport, NULL, NULL); + devlink_rate_leaf_destroy(vport->dl_port); + } + devlink_port_unregister(vport->dl_port); mlx5_esw_dl_port_free(vport->dl_port); vport->dl_port = NULL; @@ -148,8 +160,16 @@ int mlx5_esw_devlink_sf_port_register(struct mlx5_eswitch *esw, struct devlink_p if (err) return err; + err = devlink_rate_leaf_create(dl_port, vport); + if (err) + goto rate_err; + vport->dl_port = dl_port; return 0; + +rate_err: + devlink_port_unregister(dl_port); + return err; } void mlx5_esw_devlink_sf_port_unregister(struct mlx5_eswitch *esw, u16 vport_num) @@ -159,6 +179,12 @@ void mlx5_esw_devlink_sf_port_unregister(struct mlx5_eswitch *esw, u16 vport_num vport = mlx5_eswitch_get_vport(esw, vport_num); if (IS_ERR(vport)) return; + + if (vport->dl_port->devlink_rate) { + mlx5_esw_qos_vport_update_group(esw, vport, NULL, NULL); + devlink_rate_leaf_destroy(vport->dl_port); + } + devlink_port_unregister(vport->dl_port); vport->dl_port = NULL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/diag/bridge_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/diag/bridge_tracepoint.h index 227964b7d3b9..3401188e0a60 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/diag/bridge_tracepoint.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/diag/bridge_tracepoint.h @@ -85,11 +85,18 @@ DECLARE_EVENT_CLASS(mlx5_esw_bridge_port_template, TP_ARGS(port), TP_STRUCT__entry( __field(u16, vport_num) + __field(u16, esw_owner_vhca_id) + __field(u16, flags) ), TP_fast_assign( __entry->vport_num = port->vport_num; + __entry->esw_owner_vhca_id = port->esw_owner_vhca_id; + __entry->flags = port->flags; ), - TP_printk("vport_num=%hu", __entry->vport_num) + TP_printk("vport_num=%hu esw_owner_vhca_id=%hu flags=%hx", + __entry->vport_num, + __entry->esw_owner_vhca_id, + __entry->flags) ); DEFINE_EVENT(mlx5_esw_bridge_port_template, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/diag/qos_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/diag/qos_tracepoint.h new file mode 100644 index 000000000000..458baf0c6415 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/diag/qos_tracepoint.h @@ -0,0 +1,123 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */ + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM mlx5 + +#if !defined(_MLX5_ESW_TP_) || defined(TRACE_HEADER_MULTI_READ) +#define _MLX5_ESW_TP_ + +#include <linux/tracepoint.h> +#include "eswitch.h" + +TRACE_EVENT(mlx5_esw_vport_qos_destroy, + TP_PROTO(const struct mlx5_vport *vport), + TP_ARGS(vport), + TP_STRUCT__entry(__string(devname, dev_name(vport->dev->device)) + __field(unsigned short, vport_id) + __field(unsigned int, tsar_ix) + ), + TP_fast_assign(__assign_str(devname, dev_name(vport->dev->device)); + __entry->vport_id = vport->vport; + __entry->tsar_ix = vport->qos.esw_tsar_ix; + ), + TP_printk("(%s) vport=%hu tsar_ix=%u\n", + __get_str(devname), __entry->vport_id, __entry->tsar_ix + ) +); + +DECLARE_EVENT_CLASS(mlx5_esw_vport_qos_template, + TP_PROTO(const struct mlx5_vport *vport, u32 bw_share, u32 max_rate), + TP_ARGS(vport, bw_share, max_rate), + TP_STRUCT__entry(__string(devname, dev_name(vport->dev->device)) + __field(unsigned short, vport_id) + __field(unsigned int, tsar_ix) + __field(unsigned int, bw_share) + __field(unsigned int, max_rate) + __field(void *, group) + ), + TP_fast_assign(__assign_str(devname, dev_name(vport->dev->device)); + __entry->vport_id = vport->vport; + __entry->tsar_ix = vport->qos.esw_tsar_ix; + __entry->bw_share = bw_share; + __entry->max_rate = max_rate; + __entry->group = vport->qos.group; + ), + TP_printk("(%s) vport=%hu tsar_ix=%u bw_share=%u, max_rate=%u group=%p\n", + __get_str(devname), __entry->vport_id, __entry->tsar_ix, + __entry->bw_share, __entry->max_rate, __entry->group + ) +); + +DEFINE_EVENT(mlx5_esw_vport_qos_template, mlx5_esw_vport_qos_create, + TP_PROTO(const struct mlx5_vport *vport, u32 bw_share, u32 max_rate), + TP_ARGS(vport, bw_share, max_rate) + ); + +DEFINE_EVENT(mlx5_esw_vport_qos_template, mlx5_esw_vport_qos_config, + TP_PROTO(const struct mlx5_vport *vport, u32 bw_share, u32 max_rate), + TP_ARGS(vport, bw_share, max_rate) + ); + +DECLARE_EVENT_CLASS(mlx5_esw_group_qos_template, + TP_PROTO(const struct mlx5_core_dev *dev, + const struct mlx5_esw_rate_group *group, + unsigned int tsar_ix), + TP_ARGS(dev, group, tsar_ix), + TP_STRUCT__entry(__string(devname, dev_name(dev->device)) + __field(const void *, group) + __field(unsigned int, tsar_ix) + ), + TP_fast_assign(__assign_str(devname, dev_name(dev->device)); + __entry->group = group; + __entry->tsar_ix = tsar_ix; + ), + TP_printk("(%s) group=%p tsar_ix=%u\n", + __get_str(devname), __entry->group, __entry->tsar_ix + ) +); + +DEFINE_EVENT(mlx5_esw_group_qos_template, mlx5_esw_group_qos_create, + TP_PROTO(const struct mlx5_core_dev *dev, + const struct mlx5_esw_rate_group *group, + unsigned int tsar_ix), + TP_ARGS(dev, group, tsar_ix) + ); + +DEFINE_EVENT(mlx5_esw_group_qos_template, mlx5_esw_group_qos_destroy, + TP_PROTO(const struct mlx5_core_dev *dev, + const struct mlx5_esw_rate_group *group, + unsigned int tsar_ix), + TP_ARGS(dev, group, tsar_ix) + ); + +TRACE_EVENT(mlx5_esw_group_qos_config, + TP_PROTO(const struct mlx5_core_dev *dev, + const struct mlx5_esw_rate_group *group, + unsigned int tsar_ix, u32 bw_share, u32 max_rate), + TP_ARGS(dev, group, tsar_ix, bw_share, max_rate), + TP_STRUCT__entry(__string(devname, dev_name(dev->device)) + __field(const void *, group) + __field(unsigned int, tsar_ix) + __field(unsigned int, bw_share) + __field(unsigned int, max_rate) + ), + TP_fast_assign(__assign_str(devname, dev_name(dev->device)); + __entry->group = group; + __entry->tsar_ix = tsar_ix; + __entry->bw_share = bw_share; + __entry->max_rate = max_rate; + ), + TP_printk("(%s) group=%p tsar_ix=%u bw_share=%u max_rate=%u\n", + __get_str(devname), __entry->group, __entry->tsar_ix, + __entry->bw_share, __entry->max_rate + ) +); +#endif /* _MLX5_ESW_TP_ */ + +/* This part must be outside protection */ +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH esw/diag +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE qos_tracepoint +#include <trace/define_trace.h> diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c index d9041b16611d..df277a6cddc0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c @@ -11,6 +11,7 @@ #include "mlx5_core.h" #include "eswitch.h" #include "fs_core.h" +#include "esw/qos.h" enum { LEGACY_VEPA_PRIO = 0, @@ -508,3 +509,22 @@ unlock: mutex_unlock(&esw->state_lock); return err; } + +int mlx5_eswitch_set_vport_rate(struct mlx5_eswitch *esw, u16 vport, + u32 max_rate, u32 min_rate) +{ + struct mlx5_vport *evport = mlx5_eswitch_get_vport(esw, vport); + int err; + + if (!mlx5_esw_allowed(esw)) + return -EPERM; + if (IS_ERR(evport)) + return PTR_ERR(evport); + + mutex_lock(&esw->state_lock); + err = mlx5_esw_qos_set_vport_min_rate(esw, evport, min_rate, NULL); + if (!err) + err = mlx5_esw_qos_set_vport_max_rate(esw, evport, max_rate, NULL); + mutex_unlock(&esw->state_lock); + return err; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c new file mode 100644 index 000000000000..985e305179d1 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c @@ -0,0 +1,869 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */ + +#include "eswitch.h" +#include "esw/qos.h" +#include "en/port.h" +#define CREATE_TRACE_POINTS +#include "diag/qos_tracepoint.h" + +/* Minimum supported BW share value by the HW is 1 Mbit/sec */ +#define MLX5_MIN_BW_SHARE 1 + +#define MLX5_RATE_TO_BW_SHARE(rate, divider, limit) \ + min_t(u32, max_t(u32, DIV_ROUND_UP(rate, divider), MLX5_MIN_BW_SHARE), limit) + +struct mlx5_esw_rate_group { + u32 tsar_ix; + u32 max_rate; + u32 min_rate; + u32 bw_share; + struct list_head list; +}; + +static int esw_qos_tsar_config(struct mlx5_core_dev *dev, u32 *sched_ctx, + u32 parent_ix, u32 tsar_ix, + u32 max_rate, u32 bw_share) +{ + u32 bitmask = 0; + + if (!MLX5_CAP_GEN(dev, qos) || !MLX5_CAP_QOS(dev, esw_scheduling)) + return -EOPNOTSUPP; + + MLX5_SET(scheduling_context, sched_ctx, parent_element_id, parent_ix); + MLX5_SET(scheduling_context, sched_ctx, max_average_bw, max_rate); + MLX5_SET(scheduling_context, sched_ctx, bw_share, bw_share); + bitmask |= MODIFY_SCHEDULING_ELEMENT_IN_MODIFY_BITMASK_MAX_AVERAGE_BW; + bitmask |= MODIFY_SCHEDULING_ELEMENT_IN_MODIFY_BITMASK_BW_SHARE; + + return mlx5_modify_scheduling_element_cmd(dev, + SCHEDULING_HIERARCHY_E_SWITCH, + sched_ctx, + tsar_ix, + bitmask); +} + +static int esw_qos_group_config(struct mlx5_eswitch *esw, struct mlx5_esw_rate_group *group, + u32 max_rate, u32 bw_share, struct netlink_ext_ack *extack) +{ + u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {}; + struct mlx5_core_dev *dev = esw->dev; + int err; + + err = esw_qos_tsar_config(dev, sched_ctx, + esw->qos.root_tsar_ix, group->tsar_ix, + max_rate, bw_share); + if (err) + NL_SET_ERR_MSG_MOD(extack, "E-Switch modify group TSAR element failed"); + + trace_mlx5_esw_group_qos_config(dev, group, group->tsar_ix, bw_share, max_rate); + + return err; +} + +static int esw_qos_vport_config(struct mlx5_eswitch *esw, + struct mlx5_vport *vport, + u32 max_rate, u32 bw_share, + struct netlink_ext_ack *extack) +{ + u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {}; + struct mlx5_esw_rate_group *group = vport->qos.group; + struct mlx5_core_dev *dev = esw->dev; + u32 parent_tsar_ix; + void *vport_elem; + int err; + + if (!vport->qos.enabled) + return -EIO; + + parent_tsar_ix = group ? group->tsar_ix : esw->qos.root_tsar_ix; + MLX5_SET(scheduling_context, sched_ctx, element_type, + SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT); + vport_elem = MLX5_ADDR_OF(scheduling_context, sched_ctx, + element_attributes); + MLX5_SET(vport_element, vport_elem, vport_number, vport->vport); + + err = esw_qos_tsar_config(dev, sched_ctx, parent_tsar_ix, vport->qos.esw_tsar_ix, + max_rate, bw_share); + if (err) { + esw_warn(esw->dev, + "E-Switch modify TSAR vport element failed (vport=%d,err=%d)\n", + vport->vport, err); + NL_SET_ERR_MSG_MOD(extack, "E-Switch modify TSAR vport element failed"); + return err; + } + + trace_mlx5_esw_vport_qos_config(vport, bw_share, max_rate); + + return 0; +} + +static u32 esw_qos_calculate_min_rate_divider(struct mlx5_eswitch *esw, + struct mlx5_esw_rate_group *group, + bool group_level) +{ + u32 fw_max_bw_share = MLX5_CAP_QOS(esw->dev, max_tsar_bw_share); + struct mlx5_vport *evport; + u32 max_guarantee = 0; + unsigned long i; + + if (group_level) { + struct mlx5_esw_rate_group *group; + + list_for_each_entry(group, &esw->qos.groups, list) { + if (group->min_rate < max_guarantee) + continue; + max_guarantee = group->min_rate; + } + } else { + mlx5_esw_for_each_vport(esw, i, evport) { + if (!evport->enabled || !evport->qos.enabled || + evport->qos.group != group || evport->qos.min_rate < max_guarantee) + continue; + max_guarantee = evport->qos.min_rate; + } + } + + if (max_guarantee) + return max_t(u32, max_guarantee / fw_max_bw_share, 1); + + /* If vports min rate divider is 0 but their group has bw_share configured, then + * need to set bw_share for vports to minimal value. + */ + if (!group_level && !max_guarantee && group->bw_share) + return 1; + return 0; +} + +static u32 esw_qos_calc_bw_share(u32 min_rate, u32 divider, u32 fw_max) +{ + if (divider) + return MLX5_RATE_TO_BW_SHARE(min_rate, divider, fw_max); + + return 0; +} + +static int esw_qos_normalize_vports_min_rate(struct mlx5_eswitch *esw, + struct mlx5_esw_rate_group *group, + struct netlink_ext_ack *extack) +{ + u32 fw_max_bw_share = MLX5_CAP_QOS(esw->dev, max_tsar_bw_share); + u32 divider = esw_qos_calculate_min_rate_divider(esw, group, false); + struct mlx5_vport *evport; + unsigned long i; + u32 bw_share; + int err; + + mlx5_esw_for_each_vport(esw, i, evport) { + if (!evport->enabled || !evport->qos.enabled || evport->qos.group != group) + continue; + bw_share = esw_qos_calc_bw_share(evport->qos.min_rate, divider, fw_max_bw_share); + + if (bw_share == evport->qos.bw_share) + continue; + + err = esw_qos_vport_config(esw, evport, evport->qos.max_rate, bw_share, extack); + if (err) + return err; + + evport->qos.bw_share = bw_share; + } + + return 0; +} + +static int esw_qos_normalize_groups_min_rate(struct mlx5_eswitch *esw, u32 divider, + struct netlink_ext_ack *extack) +{ + u32 fw_max_bw_share = MLX5_CAP_QOS(esw->dev, max_tsar_bw_share); + struct mlx5_esw_rate_group *group; + u32 bw_share; + int err; + + list_for_each_entry(group, &esw->qos.groups, list) { + bw_share = esw_qos_calc_bw_share(group->min_rate, divider, fw_max_bw_share); + + if (bw_share == group->bw_share) + continue; + + err = esw_qos_group_config(esw, group, group->max_rate, bw_share, extack); + if (err) + return err; + + group->bw_share = bw_share; + + /* All the group's vports need to be set with default bw_share + * to enable them with QOS + */ + err = esw_qos_normalize_vports_min_rate(esw, group, extack); + + if (err) + return err; + } + + return 0; +} + +int mlx5_esw_qos_set_vport_min_rate(struct mlx5_eswitch *esw, + struct mlx5_vport *evport, + u32 min_rate, + struct netlink_ext_ack *extack) +{ + u32 fw_max_bw_share, previous_min_rate; + bool min_rate_supported; + int err; + + lockdep_assert_held(&esw->state_lock); + fw_max_bw_share = MLX5_CAP_QOS(esw->dev, max_tsar_bw_share); + min_rate_supported = MLX5_CAP_QOS(esw->dev, esw_bw_share) && + fw_max_bw_share >= MLX5_MIN_BW_SHARE; + if (min_rate && !min_rate_supported) + return -EOPNOTSUPP; + if (min_rate == evport->qos.min_rate) + return 0; + + previous_min_rate = evport->qos.min_rate; + evport->qos.min_rate = min_rate; + err = esw_qos_normalize_vports_min_rate(esw, evport->qos.group, extack); + if (err) + evport->qos.min_rate = previous_min_rate; + + return err; +} + +int mlx5_esw_qos_set_vport_max_rate(struct mlx5_eswitch *esw, + struct mlx5_vport *evport, + u32 max_rate, + struct netlink_ext_ack *extack) +{ + u32 act_max_rate = max_rate; + bool max_rate_supported; + int err; + + lockdep_assert_held(&esw->state_lock); + max_rate_supported = MLX5_CAP_QOS(esw->dev, esw_rate_limit); + + if (max_rate && !max_rate_supported) + return -EOPNOTSUPP; + if (max_rate == evport->qos.max_rate) + return 0; + + /* If parent group has rate limit need to set to group + * value when new max rate is 0. + */ + if (evport->qos.group && !max_rate) + act_max_rate = evport->qos.group->max_rate; + + err = esw_qos_vport_config(esw, evport, act_max_rate, evport->qos.bw_share, extack); + + if (!err) + evport->qos.max_rate = max_rate; + + return err; +} + +static int esw_qos_set_group_min_rate(struct mlx5_eswitch *esw, struct mlx5_esw_rate_group *group, + u32 min_rate, struct netlink_ext_ack *extack) +{ + u32 fw_max_bw_share = MLX5_CAP_QOS(esw->dev, max_tsar_bw_share); + struct mlx5_core_dev *dev = esw->dev; + u32 previous_min_rate, divider; + int err; + + if (!(MLX5_CAP_QOS(dev, esw_bw_share) && fw_max_bw_share >= MLX5_MIN_BW_SHARE)) + return -EOPNOTSUPP; + + if (min_rate == group->min_rate) + return 0; + + previous_min_rate = group->min_rate; + group->min_rate = min_rate; + divider = esw_qos_calculate_min_rate_divider(esw, group, true); + err = esw_qos_normalize_groups_min_rate(esw, divider, extack); + if (err) { + group->min_rate = previous_min_rate; + NL_SET_ERR_MSG_MOD(extack, "E-Switch group min rate setting failed"); + + /* Attempt restoring previous configuration */ + divider = esw_qos_calculate_min_rate_divider(esw, group, true); + if (esw_qos_normalize_groups_min_rate(esw, divider, extack)) + NL_SET_ERR_MSG_MOD(extack, "E-Switch BW share restore failed"); + } + + return err; +} + +static int esw_qos_set_group_max_rate(struct mlx5_eswitch *esw, + struct mlx5_esw_rate_group *group, + u32 max_rate, struct netlink_ext_ack *extack) +{ + struct mlx5_vport *vport; + unsigned long i; + int err; + + if (group->max_rate == max_rate) + return 0; + + err = esw_qos_group_config(esw, group, max_rate, group->bw_share, extack); + if (err) + return err; + + group->max_rate = max_rate; + + /* Any unlimited vports in the group should be set + * with the value of the group. + */ + mlx5_esw_for_each_vport(esw, i, vport) { + if (!vport->enabled || !vport->qos.enabled || + vport->qos.group != group || vport->qos.max_rate) + continue; + + err = esw_qos_vport_config(esw, vport, max_rate, vport->qos.bw_share, extack); + if (err) + NL_SET_ERR_MSG_MOD(extack, + "E-Switch vport implicit rate limit setting failed"); + } + + return err; +} + +static int esw_qos_vport_create_sched_element(struct mlx5_eswitch *esw, + struct mlx5_vport *vport, + u32 max_rate, u32 bw_share) +{ + u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {}; + struct mlx5_esw_rate_group *group = vport->qos.group; + struct mlx5_core_dev *dev = esw->dev; + u32 parent_tsar_ix; + void *vport_elem; + int err; + + parent_tsar_ix = group ? group->tsar_ix : esw->qos.root_tsar_ix; + MLX5_SET(scheduling_context, sched_ctx, element_type, + SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT); + vport_elem = MLX5_ADDR_OF(scheduling_context, sched_ctx, element_attributes); + MLX5_SET(vport_element, vport_elem, vport_number, vport->vport); + MLX5_SET(scheduling_context, sched_ctx, parent_element_id, parent_tsar_ix); + MLX5_SET(scheduling_context, sched_ctx, max_average_bw, max_rate); + MLX5_SET(scheduling_context, sched_ctx, bw_share, bw_share); + + err = mlx5_create_scheduling_element_cmd(dev, + SCHEDULING_HIERARCHY_E_SWITCH, + sched_ctx, + &vport->qos.esw_tsar_ix); + if (err) { + esw_warn(esw->dev, "E-Switch create TSAR vport element failed (vport=%d,err=%d)\n", + vport->vport, err); + return err; + } + + return 0; +} + +static int esw_qos_update_group_scheduling_element(struct mlx5_eswitch *esw, + struct mlx5_vport *vport, + struct mlx5_esw_rate_group *curr_group, + struct mlx5_esw_rate_group *new_group, + struct netlink_ext_ack *extack) +{ + u32 max_rate; + int err; + + err = mlx5_destroy_scheduling_element_cmd(esw->dev, + SCHEDULING_HIERARCHY_E_SWITCH, + vport->qos.esw_tsar_ix); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "E-Switch destroy TSAR vport element failed"); + return err; + } + + vport->qos.group = new_group; + max_rate = vport->qos.max_rate ? vport->qos.max_rate : new_group->max_rate; + + /* If vport is unlimited, we set the group's value. + * Therefore, if the group is limited it will apply to + * the vport as well and if not, vport will remain unlimited. + */ + err = esw_qos_vport_create_sched_element(esw, vport, max_rate, vport->qos.bw_share); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "E-Switch vport group set failed."); + goto err_sched; + } + + return 0; + +err_sched: + vport->qos.group = curr_group; + max_rate = vport->qos.max_rate ? vport->qos.max_rate : curr_group->max_rate; + if (esw_qos_vport_create_sched_element(esw, vport, max_rate, vport->qos.bw_share)) + esw_warn(esw->dev, "E-Switch vport group restore failed (vport=%d)\n", + vport->vport); + + return err; +} + +static int esw_qos_vport_update_group(struct mlx5_eswitch *esw, + struct mlx5_vport *vport, + struct mlx5_esw_rate_group *group, + struct netlink_ext_ack *extack) +{ + struct mlx5_esw_rate_group *new_group, *curr_group; + int err; + + if (!vport->enabled) + return -EINVAL; + + curr_group = vport->qos.group; + new_group = group ?: esw->qos.group0; + if (curr_group == new_group) + return 0; + + err = esw_qos_update_group_scheduling_element(esw, vport, curr_group, new_group, extack); + if (err) + return err; + + /* Recalculate bw share weights of old and new groups */ + if (vport->qos.bw_share) { + esw_qos_normalize_vports_min_rate(esw, curr_group, extack); + esw_qos_normalize_vports_min_rate(esw, new_group, extack); + } + + return 0; +} + +static struct mlx5_esw_rate_group * +esw_qos_create_rate_group(struct mlx5_eswitch *esw, struct netlink_ext_ack *extack) +{ + u32 tsar_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {}; + struct mlx5_esw_rate_group *group; + u32 divider; + int err; + + if (!MLX5_CAP_QOS(esw->dev, log_esw_max_sched_depth)) + return ERR_PTR(-EOPNOTSUPP); + + group = kzalloc(sizeof(*group), GFP_KERNEL); + if (!group) + return ERR_PTR(-ENOMEM); + + MLX5_SET(scheduling_context, tsar_ctx, parent_element_id, + esw->qos.root_tsar_ix); + err = mlx5_create_scheduling_element_cmd(esw->dev, + SCHEDULING_HIERARCHY_E_SWITCH, + tsar_ctx, + &group->tsar_ix); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "E-Switch create TSAR for group failed"); + goto err_sched_elem; + } + + list_add_tail(&group->list, &esw->qos.groups); + + divider = esw_qos_calculate_min_rate_divider(esw, group, true); + if (divider) { + err = esw_qos_normalize_groups_min_rate(esw, divider, extack); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "E-Switch groups normalization failed"); + goto err_min_rate; + } + } + trace_mlx5_esw_group_qos_create(esw->dev, group, group->tsar_ix); + + return group; + +err_min_rate: + list_del(&group->list); + err = mlx5_destroy_scheduling_element_cmd(esw->dev, + SCHEDULING_HIERARCHY_E_SWITCH, + group->tsar_ix); + if (err) + NL_SET_ERR_MSG_MOD(extack, "E-Switch destroy TSAR for group failed"); +err_sched_elem: + kfree(group); + return ERR_PTR(err); +} + +static int esw_qos_destroy_rate_group(struct mlx5_eswitch *esw, + struct mlx5_esw_rate_group *group, + struct netlink_ext_ack *extack) +{ + u32 divider; + int err; + + list_del(&group->list); + + divider = esw_qos_calculate_min_rate_divider(esw, NULL, true); + err = esw_qos_normalize_groups_min_rate(esw, divider, extack); + if (err) + NL_SET_ERR_MSG_MOD(extack, "E-Switch groups' normalization failed"); + + err = mlx5_destroy_scheduling_element_cmd(esw->dev, + SCHEDULING_HIERARCHY_E_SWITCH, + group->tsar_ix); + if (err) + NL_SET_ERR_MSG_MOD(extack, "E-Switch destroy TSAR_ID failed"); + + trace_mlx5_esw_group_qos_destroy(esw->dev, group, group->tsar_ix); + kfree(group); + return err; +} + +static bool esw_qos_element_type_supported(struct mlx5_core_dev *dev, int type) +{ + switch (type) { + case SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR: + return MLX5_CAP_QOS(dev, esw_element_type) & + ELEMENT_TYPE_CAP_MASK_TASR; + case SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT: + return MLX5_CAP_QOS(dev, esw_element_type) & + ELEMENT_TYPE_CAP_MASK_VPORT; + case SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT_TC: + return MLX5_CAP_QOS(dev, esw_element_type) & + ELEMENT_TYPE_CAP_MASK_VPORT_TC; + case SCHEDULING_CONTEXT_ELEMENT_TYPE_PARA_VPORT_TC: + return MLX5_CAP_QOS(dev, esw_element_type) & + ELEMENT_TYPE_CAP_MASK_PARA_VPORT_TC; + } + return false; +} + +void mlx5_esw_qos_create(struct mlx5_eswitch *esw) +{ + u32 tsar_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {}; + struct mlx5_core_dev *dev = esw->dev; + __be32 *attr; + int err; + + if (!MLX5_CAP_GEN(dev, qos) || !MLX5_CAP_QOS(dev, esw_scheduling)) + return; + + if (!esw_qos_element_type_supported(dev, SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR)) + return; + + mutex_lock(&esw->state_lock); + if (esw->qos.enabled) + goto unlock; + + MLX5_SET(scheduling_context, tsar_ctx, element_type, + SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR); + + attr = MLX5_ADDR_OF(scheduling_context, tsar_ctx, element_attributes); + *attr = cpu_to_be32(TSAR_ELEMENT_TSAR_TYPE_DWRR << 16); + + err = mlx5_create_scheduling_element_cmd(dev, + SCHEDULING_HIERARCHY_E_SWITCH, + tsar_ctx, + &esw->qos.root_tsar_ix); + if (err) { + esw_warn(dev, "E-Switch create root TSAR failed (%d)\n", err); + goto unlock; + } + + INIT_LIST_HEAD(&esw->qos.groups); + if (MLX5_CAP_QOS(dev, log_esw_max_sched_depth)) { + esw->qos.group0 = esw_qos_create_rate_group(esw, NULL); + if (IS_ERR(esw->qos.group0)) { + esw_warn(dev, "E-Switch create rate group 0 failed (%ld)\n", + PTR_ERR(esw->qos.group0)); + goto err_group0; + } + } + esw->qos.enabled = true; +unlock: + mutex_unlock(&esw->state_lock); + return; + +err_group0: + err = mlx5_destroy_scheduling_element_cmd(esw->dev, + SCHEDULING_HIERARCHY_E_SWITCH, + esw->qos.root_tsar_ix); + if (err) + esw_warn(esw->dev, "E-Switch destroy root TSAR failed (%d)\n", err); + mutex_unlock(&esw->state_lock); +} + +void mlx5_esw_qos_destroy(struct mlx5_eswitch *esw) +{ + struct devlink *devlink = priv_to_devlink(esw->dev); + int err; + + devlink_rate_nodes_destroy(devlink); + mutex_lock(&esw->state_lock); + if (!esw->qos.enabled) + goto unlock; + + if (esw->qos.group0) + esw_qos_destroy_rate_group(esw, esw->qos.group0, NULL); + + err = mlx5_destroy_scheduling_element_cmd(esw->dev, + SCHEDULING_HIERARCHY_E_SWITCH, + esw->qos.root_tsar_ix); + if (err) + esw_warn(esw->dev, "E-Switch destroy root TSAR failed (%d)\n", err); + + esw->qos.enabled = false; +unlock: + mutex_unlock(&esw->state_lock); +} + +int mlx5_esw_qos_vport_enable(struct mlx5_eswitch *esw, struct mlx5_vport *vport, + u32 max_rate, u32 bw_share) +{ + int err; + + lockdep_assert_held(&esw->state_lock); + if (!esw->qos.enabled) + return 0; + + if (vport->qos.enabled) + return -EEXIST; + + vport->qos.group = esw->qos.group0; + + err = esw_qos_vport_create_sched_element(esw, vport, max_rate, bw_share); + if (!err) { + vport->qos.enabled = true; + trace_mlx5_esw_vport_qos_create(vport, bw_share, max_rate); + } + + return err; +} + +void mlx5_esw_qos_vport_disable(struct mlx5_eswitch *esw, struct mlx5_vport *vport) +{ + int err; + + lockdep_assert_held(&esw->state_lock); + if (!esw->qos.enabled || !vport->qos.enabled) + return; + WARN(vport->qos.group && vport->qos.group != esw->qos.group0, + "Disabling QoS on port before detaching it from group"); + + err = mlx5_destroy_scheduling_element_cmd(esw->dev, + SCHEDULING_HIERARCHY_E_SWITCH, + vport->qos.esw_tsar_ix); + if (err) + esw_warn(esw->dev, "E-Switch destroy TSAR vport element failed (vport=%d,err=%d)\n", + vport->vport, err); + + vport->qos.enabled = false; + trace_mlx5_esw_vport_qos_destroy(vport); +} + +int mlx5_esw_qos_modify_vport_rate(struct mlx5_eswitch *esw, u16 vport_num, u32 rate_mbps) +{ + u32 ctx[MLX5_ST_SZ_DW(scheduling_context)] = {}; + struct mlx5_vport *vport; + u32 bitmask; + + vport = mlx5_eswitch_get_vport(esw, vport_num); + if (IS_ERR(vport)) + return PTR_ERR(vport); + + if (!vport->qos.enabled) + return -EOPNOTSUPP; + + MLX5_SET(scheduling_context, ctx, max_average_bw, rate_mbps); + bitmask = MODIFY_SCHEDULING_ELEMENT_IN_MODIFY_BITMASK_MAX_AVERAGE_BW; + + return mlx5_modify_scheduling_element_cmd(esw->dev, + SCHEDULING_HIERARCHY_E_SWITCH, + ctx, + vport->qos.esw_tsar_ix, + bitmask); +} + +#define MLX5_LINKSPEED_UNIT 125000 /* 1Mbps in Bps */ + +/* Converts bytes per second value passed in a pointer into megabits per + * second, rewriting last. If converted rate exceed link speed or is not a + * fraction of Mbps - returns error. + */ +static int esw_qos_devlink_rate_to_mbps(struct mlx5_core_dev *mdev, const char *name, + u64 *rate, struct netlink_ext_ack *extack) +{ + u32 link_speed_max, reminder; + u64 value; + int err; + + err = mlx5e_port_max_linkspeed(mdev, &link_speed_max); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Failed to get link maximum speed"); + return err; + } + + value = div_u64_rem(*rate, MLX5_LINKSPEED_UNIT, &reminder); + if (reminder) { + pr_err("%s rate value %lluBps not in link speed units of 1Mbps.\n", + name, *rate); + NL_SET_ERR_MSG_MOD(extack, "TX rate value not in link speed units of 1Mbps"); + return -EINVAL; + } + + if (value > link_speed_max) { + pr_err("%s rate value %lluMbps exceed link maximum speed %u.\n", + name, value, link_speed_max); + NL_SET_ERR_MSG_MOD(extack, "TX rate value exceed link maximum speed"); + return -EINVAL; + } + + *rate = value; + return 0; +} + +/* Eswitch devlink rate API */ + +int mlx5_esw_devlink_rate_leaf_tx_share_set(struct devlink_rate *rate_leaf, void *priv, + u64 tx_share, struct netlink_ext_ack *extack) +{ + struct mlx5_vport *vport = priv; + struct mlx5_eswitch *esw; + int err; + + esw = vport->dev->priv.eswitch; + if (!mlx5_esw_allowed(esw)) + return -EPERM; + + err = esw_qos_devlink_rate_to_mbps(vport->dev, "tx_share", &tx_share, extack); + if (err) + return err; + + mutex_lock(&esw->state_lock); + err = mlx5_esw_qos_set_vport_min_rate(esw, vport, tx_share, extack); + mutex_unlock(&esw->state_lock); + return err; +} + +int mlx5_esw_devlink_rate_leaf_tx_max_set(struct devlink_rate *rate_leaf, void *priv, + u64 tx_max, struct netlink_ext_ack *extack) +{ + struct mlx5_vport *vport = priv; + struct mlx5_eswitch *esw; + int err; + + esw = vport->dev->priv.eswitch; + if (!mlx5_esw_allowed(esw)) + return -EPERM; + + err = esw_qos_devlink_rate_to_mbps(vport->dev, "tx_max", &tx_max, extack); + if (err) + return err; + + mutex_lock(&esw->state_lock); + err = mlx5_esw_qos_set_vport_max_rate(esw, vport, tx_max, extack); + mutex_unlock(&esw->state_lock); + return err; +} + +int mlx5_esw_devlink_rate_node_tx_share_set(struct devlink_rate *rate_node, void *priv, + u64 tx_share, struct netlink_ext_ack *extack) +{ + struct mlx5_core_dev *dev = devlink_priv(rate_node->devlink); + struct mlx5_eswitch *esw = dev->priv.eswitch; + struct mlx5_esw_rate_group *group = priv; + int err; + + err = esw_qos_devlink_rate_to_mbps(dev, "tx_share", &tx_share, extack); + if (err) + return err; + + mutex_lock(&esw->state_lock); + err = esw_qos_set_group_min_rate(esw, group, tx_share, extack); + mutex_unlock(&esw->state_lock); + return err; +} + +int mlx5_esw_devlink_rate_node_tx_max_set(struct devlink_rate *rate_node, void *priv, + u64 tx_max, struct netlink_ext_ack *extack) +{ + struct mlx5_core_dev *dev = devlink_priv(rate_node->devlink); + struct mlx5_eswitch *esw = dev->priv.eswitch; + struct mlx5_esw_rate_group *group = priv; + int err; + + err = esw_qos_devlink_rate_to_mbps(dev, "tx_max", &tx_max, extack); + if (err) + return err; + + mutex_lock(&esw->state_lock); + err = esw_qos_set_group_max_rate(esw, group, tx_max, extack); + mutex_unlock(&esw->state_lock); + return err; +} + +int mlx5_esw_devlink_rate_node_new(struct devlink_rate *rate_node, void **priv, + struct netlink_ext_ack *extack) +{ + struct mlx5_esw_rate_group *group; + struct mlx5_eswitch *esw; + int err = 0; + + esw = mlx5_devlink_eswitch_get(rate_node->devlink); + if (IS_ERR(esw)) + return PTR_ERR(esw); + + mutex_lock(&esw->state_lock); + if (esw->mode != MLX5_ESWITCH_OFFLOADS) { + NL_SET_ERR_MSG_MOD(extack, + "Rate node creation supported only in switchdev mode"); + err = -EOPNOTSUPP; + goto unlock; + } + + group = esw_qos_create_rate_group(esw, extack); + if (IS_ERR(group)) { + err = PTR_ERR(group); + goto unlock; + } + + *priv = group; +unlock: + mutex_unlock(&esw->state_lock); + return err; +} + +int mlx5_esw_devlink_rate_node_del(struct devlink_rate *rate_node, void *priv, + struct netlink_ext_ack *extack) +{ + struct mlx5_esw_rate_group *group = priv; + struct mlx5_eswitch *esw; + int err; + + esw = mlx5_devlink_eswitch_get(rate_node->devlink); + if (IS_ERR(esw)) + return PTR_ERR(esw); + + mutex_lock(&esw->state_lock); + err = esw_qos_destroy_rate_group(esw, group, extack); + mutex_unlock(&esw->state_lock); + return err; +} + +int mlx5_esw_qos_vport_update_group(struct mlx5_eswitch *esw, + struct mlx5_vport *vport, + struct mlx5_esw_rate_group *group, + struct netlink_ext_ack *extack) +{ + int err; + + mutex_lock(&esw->state_lock); + err = esw_qos_vport_update_group(esw, vport, group, extack); + mutex_unlock(&esw->state_lock); + return err; +} + +int mlx5_esw_devlink_rate_parent_set(struct devlink_rate *devlink_rate, + struct devlink_rate *parent, + void *priv, void *parent_priv, + struct netlink_ext_ack *extack) +{ + struct mlx5_esw_rate_group *group; + struct mlx5_vport *vport = priv; + + if (!parent) + return mlx5_esw_qos_vport_update_group(vport->dev->priv.eswitch, + vport, NULL, extack); + + group = parent_priv; + return mlx5_esw_qos_vport_update_group(vport->dev->priv.eswitch, vport, group, extack); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.h new file mode 100644 index 000000000000..28451abe2d2f --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */ + +#ifndef __MLX5_ESW_QOS_H__ +#define __MLX5_ESW_QOS_H__ + +#ifdef CONFIG_MLX5_ESWITCH + +int mlx5_esw_qos_set_vport_min_rate(struct mlx5_eswitch *esw, + struct mlx5_vport *evport, + u32 min_rate, + struct netlink_ext_ack *extack); +int mlx5_esw_qos_set_vport_max_rate(struct mlx5_eswitch *esw, + struct mlx5_vport *evport, + u32 max_rate, + struct netlink_ext_ack *extack); +void mlx5_esw_qos_create(struct mlx5_eswitch *esw); +void mlx5_esw_qos_destroy(struct mlx5_eswitch *esw); +int mlx5_esw_qos_vport_enable(struct mlx5_eswitch *esw, struct mlx5_vport *vport, + u32 max_rate, u32 bw_share); +void mlx5_esw_qos_vport_disable(struct mlx5_eswitch *esw, struct mlx5_vport *vport); + +int mlx5_esw_devlink_rate_leaf_tx_share_set(struct devlink_rate *rate_leaf, void *priv, + u64 tx_share, struct netlink_ext_ack *extack); +int mlx5_esw_devlink_rate_leaf_tx_max_set(struct devlink_rate *rate_leaf, void *priv, + u64 tx_max, struct netlink_ext_ack *extack); +int mlx5_esw_devlink_rate_node_tx_share_set(struct devlink_rate *rate_node, void *priv, + u64 tx_share, struct netlink_ext_ack *extack); +int mlx5_esw_devlink_rate_node_tx_max_set(struct devlink_rate *rate_node, void *priv, + u64 tx_max, struct netlink_ext_ack *extack); +int mlx5_esw_devlink_rate_node_new(struct devlink_rate *rate_node, void **priv, + struct netlink_ext_ack *extack); +int mlx5_esw_devlink_rate_node_del(struct devlink_rate *rate_node, void *priv, + struct netlink_ext_ack *extack); +int mlx5_esw_devlink_rate_parent_set(struct devlink_rate *devlink_rate, + struct devlink_rate *parent, + void *priv, void *parent_priv, + struct netlink_ext_ack *extack); +#endif + +#endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/sample.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/sample.h deleted file mode 100644 index 2a3f4be10030..000000000000 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/sample.h +++ /dev/null @@ -1,42 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ -/* Copyright (c) 2021 Mellanox Technologies. */ - -#ifndef __MLX5_EN_TC_SAMPLE_H__ -#define __MLX5_EN_TC_SAMPLE_H__ - -#include "en.h" -#include "eswitch.h" - -struct mlx5e_priv; -struct mlx5_flow_attr; -struct mlx5_esw_psample; - -struct mlx5_sample_attr { - u32 group_num; - u32 rate; - u32 trunc_size; - u32 restore_obj_id; - u32 sampler_id; - struct mlx5_flow_table *sample_default_tbl; - struct mlx5_sample_flow *sample_flow; -}; - -void mlx5_esw_sample_skb(struct sk_buff *skb, struct mlx5_mapped_obj *mapped_obj); - -struct mlx5_flow_handle * -mlx5_esw_sample_offload(struct mlx5_esw_psample *sample_priv, - struct mlx5_flow_spec *spec, - struct mlx5_flow_attr *attr); - -void -mlx5_esw_sample_unoffload(struct mlx5_esw_psample *sample_priv, - struct mlx5_flow_handle *rule, - struct mlx5_flow_attr *attr); - -struct mlx5_esw_psample * -mlx5_esw_sample_init(struct mlx5e_priv *priv); - -void -mlx5_esw_sample_cleanup(struct mlx5_esw_psample *esw_psample); - -#endif /* __MLX5_EN_TC_SAMPLE_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 97e6cb6f13c1..ec136b499204 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -38,6 +38,7 @@ #include <linux/mlx5/mpfs.h> #include "esw/acl/lgcy.h" #include "esw/legacy.h" +#include "esw/qos.h" #include "mlx5_core.h" #include "lib/eq.h" #include "eswitch.h" @@ -740,201 +741,6 @@ static void esw_vport_change_handler(struct work_struct *work) mutex_unlock(&esw->state_lock); } -static bool element_type_supported(struct mlx5_eswitch *esw, int type) -{ - const struct mlx5_core_dev *dev = esw->dev; - - switch (type) { - case SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR: - return MLX5_CAP_QOS(dev, esw_element_type) & - ELEMENT_TYPE_CAP_MASK_TASR; - case SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT: - return MLX5_CAP_QOS(dev, esw_element_type) & - ELEMENT_TYPE_CAP_MASK_VPORT; - case SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT_TC: - return MLX5_CAP_QOS(dev, esw_element_type) & - ELEMENT_TYPE_CAP_MASK_VPORT_TC; - case SCHEDULING_CONTEXT_ELEMENT_TYPE_PARA_VPORT_TC: - return MLX5_CAP_QOS(dev, esw_element_type) & - ELEMENT_TYPE_CAP_MASK_PARA_VPORT_TC; - } - return false; -} - -/* Vport QoS management */ -static void esw_create_tsar(struct mlx5_eswitch *esw) -{ - u32 tsar_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0}; - struct mlx5_core_dev *dev = esw->dev; - __be32 *attr; - int err; - - if (!MLX5_CAP_GEN(dev, qos) || !MLX5_CAP_QOS(dev, esw_scheduling)) - return; - - if (!element_type_supported(esw, SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR)) - return; - - if (esw->qos.enabled) - return; - - MLX5_SET(scheduling_context, tsar_ctx, element_type, - SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR); - - attr = MLX5_ADDR_OF(scheduling_context, tsar_ctx, element_attributes); - *attr = cpu_to_be32(TSAR_ELEMENT_TSAR_TYPE_DWRR << 16); - - err = mlx5_create_scheduling_element_cmd(dev, - SCHEDULING_HIERARCHY_E_SWITCH, - tsar_ctx, - &esw->qos.root_tsar_id); - if (err) { - esw_warn(esw->dev, "E-Switch create TSAR failed (%d)\n", err); - return; - } - - esw->qos.enabled = true; -} - -static void esw_destroy_tsar(struct mlx5_eswitch *esw) -{ - int err; - - if (!esw->qos.enabled) - return; - - err = mlx5_destroy_scheduling_element_cmd(esw->dev, - SCHEDULING_HIERARCHY_E_SWITCH, - esw->qos.root_tsar_id); - if (err) - esw_warn(esw->dev, "E-Switch destroy TSAR failed (%d)\n", err); - - esw->qos.enabled = false; -} - -static int esw_vport_enable_qos(struct mlx5_eswitch *esw, - struct mlx5_vport *vport, - u32 initial_max_rate, u32 initial_bw_share) -{ - u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0}; - struct mlx5_core_dev *dev = esw->dev; - void *vport_elem; - int err = 0; - - if (!esw->qos.enabled) - return 0; - - if (vport->qos.enabled) - return -EEXIST; - - MLX5_SET(scheduling_context, sched_ctx, element_type, - SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT); - vport_elem = MLX5_ADDR_OF(scheduling_context, sched_ctx, - element_attributes); - MLX5_SET(vport_element, vport_elem, vport_number, vport->vport); - MLX5_SET(scheduling_context, sched_ctx, parent_element_id, - esw->qos.root_tsar_id); - MLX5_SET(scheduling_context, sched_ctx, max_average_bw, - initial_max_rate); - MLX5_SET(scheduling_context, sched_ctx, bw_share, initial_bw_share); - - err = mlx5_create_scheduling_element_cmd(dev, - SCHEDULING_HIERARCHY_E_SWITCH, - sched_ctx, - &vport->qos.esw_tsar_ix); - if (err) { - esw_warn(esw->dev, "E-Switch create TSAR vport element failed (vport=%d,err=%d)\n", - vport->vport, err); - return err; - } - - vport->qos.enabled = true; - return 0; -} - -static void esw_vport_disable_qos(struct mlx5_eswitch *esw, - struct mlx5_vport *vport) -{ - int err; - - if (!vport->qos.enabled) - return; - - err = mlx5_destroy_scheduling_element_cmd(esw->dev, - SCHEDULING_HIERARCHY_E_SWITCH, - vport->qos.esw_tsar_ix); - if (err) - esw_warn(esw->dev, "E-Switch destroy TSAR vport element failed (vport=%d,err=%d)\n", - vport->vport, err); - - vport->qos.enabled = false; -} - -static int esw_vport_qos_config(struct mlx5_eswitch *esw, - struct mlx5_vport *vport, - u32 max_rate, u32 bw_share) -{ - u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0}; - struct mlx5_core_dev *dev = esw->dev; - void *vport_elem; - u32 bitmask = 0; - int err = 0; - - if (!MLX5_CAP_GEN(dev, qos) || !MLX5_CAP_QOS(dev, esw_scheduling)) - return -EOPNOTSUPP; - - if (!vport->qos.enabled) - return -EIO; - - MLX5_SET(scheduling_context, sched_ctx, element_type, - SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT); - vport_elem = MLX5_ADDR_OF(scheduling_context, sched_ctx, - element_attributes); - MLX5_SET(vport_element, vport_elem, vport_number, vport->vport); - MLX5_SET(scheduling_context, sched_ctx, parent_element_id, - esw->qos.root_tsar_id); - MLX5_SET(scheduling_context, sched_ctx, max_average_bw, - max_rate); - MLX5_SET(scheduling_context, sched_ctx, bw_share, bw_share); - bitmask |= MODIFY_SCHEDULING_ELEMENT_IN_MODIFY_BITMASK_MAX_AVERAGE_BW; - bitmask |= MODIFY_SCHEDULING_ELEMENT_IN_MODIFY_BITMASK_BW_SHARE; - - err = mlx5_modify_scheduling_element_cmd(dev, - SCHEDULING_HIERARCHY_E_SWITCH, - sched_ctx, - vport->qos.esw_tsar_ix, - bitmask); - if (err) { - esw_warn(esw->dev, "E-Switch modify TSAR vport element failed (vport=%d,err=%d)\n", - vport->vport, err); - return err; - } - - return 0; -} - -int mlx5_esw_modify_vport_rate(struct mlx5_eswitch *esw, u16 vport_num, - u32 rate_mbps) -{ - u32 ctx[MLX5_ST_SZ_DW(scheduling_context)] = {}; - struct mlx5_vport *vport; - - vport = mlx5_eswitch_get_vport(esw, vport_num); - if (IS_ERR(vport)) - return PTR_ERR(vport); - - if (!vport->qos.enabled) - return -EOPNOTSUPP; - - MLX5_SET(scheduling_context, ctx, max_average_bw, rate_mbps); - - return mlx5_modify_scheduling_element_cmd(esw->dev, - SCHEDULING_HIERARCHY_E_SWITCH, - ctx, - vport->qos.esw_tsar_ix, - MODIFY_SCHEDULING_ELEMENT_IN_MODIFY_BITMASK_MAX_AVERAGE_BW); -} - static void node_guid_gen_from_mac(u64 *node_guid, const u8 *mac) { ((u8 *)node_guid)[7] = mac[0]; @@ -976,7 +782,7 @@ static int esw_vport_setup(struct mlx5_eswitch *esw, struct mlx5_vport *vport) return err; /* Attach vport to the eswitch rate limiter */ - esw_vport_enable_qos(esw, vport, vport->qos.max_rate, vport->qos.bw_share); + mlx5_esw_qos_vport_enable(esw, vport, vport->qos.max_rate, vport->qos.bw_share); if (mlx5_esw_is_manager_vport(esw, vport_num)) return 0; @@ -1013,7 +819,7 @@ static void esw_vport_cleanup(struct mlx5_eswitch *esw, struct mlx5_vport *vport vport_num, 1, MLX5_VPORT_ADMIN_STATE_DOWN); - esw_vport_disable_qos(esw, vport); + mlx5_esw_qos_vport_disable(esw, vport); esw_vport_cleanup_acl(esw, vport); } @@ -1454,12 +1260,10 @@ int mlx5_eswitch_enable_locked(struct mlx5_eswitch *esw, int mode, int num_vfs) mlx5_eswitch_update_num_of_vfs(esw, num_vfs); - esw_create_tsar(esw); + mlx5_esw_qos_create(esw); esw->mode = mode; - mlx5_lag_update(esw->dev); - if (mode == MLX5_ESWITCH_LEGACY) { err = esw_legacy_enable(esw); } else { @@ -1486,7 +1290,7 @@ abort: if (mode == MLX5_ESWITCH_OFFLOADS) mlx5_rescan_drivers(esw->dev); - esw_destroy_tsar(esw); + mlx5_esw_qos_destroy(esw); mlx5_esw_acls_ns_cleanup(esw); return err; } @@ -1494,7 +1298,7 @@ abort: /** * mlx5_eswitch_enable - Enable eswitch * @esw: Pointer to eswitch - * @num_vfs: Enable eswitch swich for given number of VFs. + * @num_vfs: Enable eswitch switch for given number of VFs. * Caller must pass num_vfs > 0 when enabling eswitch for * vf vports. * mlx5_eswitch_enable() returns 0 on success or error code on failure. @@ -1506,6 +1310,7 @@ int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int num_vfs) if (!mlx5_esw_allowed(esw)) return 0; + mlx5_lag_disable_change(esw->dev); down_write(&esw->mode_lock); if (esw->mode == MLX5_ESWITCH_NONE) { ret = mlx5_eswitch_enable_locked(esw, MLX5_ESWITCH_LEGACY, num_vfs); @@ -1519,6 +1324,7 @@ int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int num_vfs) esw->esw_funcs.num_vfs = num_vfs; } up_write(&esw->mode_lock); + mlx5_lag_enable_change(esw->dev); return ret; } @@ -1550,12 +1356,10 @@ void mlx5_eswitch_disable_locked(struct mlx5_eswitch *esw, bool clear_vf) old_mode = esw->mode; esw->mode = MLX5_ESWITCH_NONE; - mlx5_lag_update(esw->dev); - if (old_mode == MLX5_ESWITCH_OFFLOADS) mlx5_rescan_drivers(esw->dev); - esw_destroy_tsar(esw); + mlx5_esw_qos_destroy(esw); mlx5_esw_acls_ns_cleanup(esw); if (clear_vf) @@ -1567,10 +1371,12 @@ void mlx5_eswitch_disable(struct mlx5_eswitch *esw, bool clear_vf) if (!mlx5_esw_allowed(esw)) return; + mlx5_lag_disable_change(esw->dev); down_write(&esw->mode_lock); mlx5_eswitch_disable_locked(esw, clear_vf); esw->esw_funcs.num_vfs = 0; up_write(&esw->mode_lock); + mlx5_lag_enable_change(esw->dev); } static int mlx5_query_hca_cap_host_pf(struct mlx5_core_dev *dev, void *out) @@ -1759,7 +1565,9 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev) ida_init(&esw->offloads.vport_metadata_ida); xa_init_flags(&esw->offloads.vhca_map, XA_FLAGS_ALLOC); mutex_init(&esw->state_lock); + lockdep_register_key(&esw->mode_lock_key); init_rwsem(&esw->mode_lock); + lockdep_set_class(&esw->mode_lock, &esw->mode_lock_key); esw->enabled_vports = 0; esw->mode = MLX5_ESWITCH_NONE; @@ -1793,6 +1601,7 @@ void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw) esw->dev->priv.eswitch = NULL; destroy_workqueue(esw->work_queue); + lockdep_unregister_key(&esw->mode_lock_key); mutex_destroy(&esw->state_lock); WARN_ON(!xa_empty(&esw->offloads.vhca_map)); xa_destroy(&esw->offloads.vhca_map); @@ -1889,8 +1698,7 @@ is_port_function_supported(struct mlx5_eswitch *esw, u16 vport_num) mlx5_esw_is_sf_vport(esw, vport_num); } -int mlx5_devlink_port_function_hw_addr_get(struct devlink *devlink, - struct devlink_port *port, +int mlx5_devlink_port_function_hw_addr_get(struct devlink_port *port, u8 *hw_addr, int *hw_addr_len, struct netlink_ext_ack *extack) { @@ -1899,7 +1707,7 @@ int mlx5_devlink_port_function_hw_addr_get(struct devlink *devlink, int err = -EOPNOTSUPP; u16 vport_num; - esw = mlx5_devlink_eswitch_get(devlink); + esw = mlx5_devlink_eswitch_get(port->devlink); if (IS_ERR(esw)) return PTR_ERR(esw); @@ -1923,8 +1731,7 @@ int mlx5_devlink_port_function_hw_addr_get(struct devlink *devlink, return err; } -int mlx5_devlink_port_function_hw_addr_set(struct devlink *devlink, - struct devlink_port *port, +int mlx5_devlink_port_function_hw_addr_set(struct devlink_port *port, const u8 *hw_addr, int hw_addr_len, struct netlink_ext_ack *extack) { @@ -1933,7 +1740,7 @@ int mlx5_devlink_port_function_hw_addr_set(struct devlink *devlink, int err = -EOPNOTSUPP; u16 vport_num; - esw = mlx5_devlink_eswitch_get(devlink); + esw = mlx5_devlink_eswitch_get(port->devlink); if (IS_ERR(esw)) { NL_SET_ERR_MSG_MOD(extack, "Eswitch doesn't support set hw_addr"); return PTR_ERR(esw); @@ -2049,110 +1856,6 @@ int __mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw, return err; } -static u32 calculate_vports_min_rate_divider(struct mlx5_eswitch *esw) -{ - u32 fw_max_bw_share = MLX5_CAP_QOS(esw->dev, max_tsar_bw_share); - struct mlx5_vport *evport; - u32 max_guarantee = 0; - unsigned long i; - - mlx5_esw_for_each_vport(esw, i, evport) { - if (!evport->enabled || evport->qos.min_rate < max_guarantee) - continue; - max_guarantee = evport->qos.min_rate; - } - - if (max_guarantee) - return max_t(u32, max_guarantee / fw_max_bw_share, 1); - return 0; -} - -static int normalize_vports_min_rate(struct mlx5_eswitch *esw) -{ - u32 fw_max_bw_share = MLX5_CAP_QOS(esw->dev, max_tsar_bw_share); - u32 divider = calculate_vports_min_rate_divider(esw); - struct mlx5_vport *evport; - u32 vport_max_rate; - u32 vport_min_rate; - unsigned long i; - u32 bw_share; - int err; - - mlx5_esw_for_each_vport(esw, i, evport) { - if (!evport->enabled) - continue; - vport_min_rate = evport->qos.min_rate; - vport_max_rate = evport->qos.max_rate; - bw_share = 0; - - if (divider) - bw_share = MLX5_RATE_TO_BW_SHARE(vport_min_rate, - divider, - fw_max_bw_share); - - if (bw_share == evport->qos.bw_share) - continue; - - err = esw_vport_qos_config(esw, evport, vport_max_rate, - bw_share); - if (!err) - evport->qos.bw_share = bw_share; - else - return err; - } - - return 0; -} - -int mlx5_eswitch_set_vport_rate(struct mlx5_eswitch *esw, u16 vport, - u32 max_rate, u32 min_rate) -{ - struct mlx5_vport *evport = mlx5_eswitch_get_vport(esw, vport); - u32 fw_max_bw_share; - u32 previous_min_rate; - bool min_rate_supported; - bool max_rate_supported; - int err = 0; - - if (!mlx5_esw_allowed(esw)) - return -EPERM; - if (IS_ERR(evport)) - return PTR_ERR(evport); - - fw_max_bw_share = MLX5_CAP_QOS(esw->dev, max_tsar_bw_share); - min_rate_supported = MLX5_CAP_QOS(esw->dev, esw_bw_share) && - fw_max_bw_share >= MLX5_MIN_BW_SHARE; - max_rate_supported = MLX5_CAP_QOS(esw->dev, esw_rate_limit); - - if ((min_rate && !min_rate_supported) || (max_rate && !max_rate_supported)) - return -EOPNOTSUPP; - - mutex_lock(&esw->state_lock); - - if (min_rate == evport->qos.min_rate) - goto set_max_rate; - - previous_min_rate = evport->qos.min_rate; - evport->qos.min_rate = min_rate; - err = normalize_vports_min_rate(esw); - if (err) { - evport->qos.min_rate = previous_min_rate; - goto unlock; - } - -set_max_rate: - if (max_rate == evport->qos.max_rate) - goto unlock; - - err = esw_vport_qos_config(esw, evport, max_rate, evport->qos.bw_share); - if (!err) - evport->qos.max_rate = max_rate; - -unlock: - mutex_unlock(&esw->state_lock); - return err; -} - int mlx5_eswitch_get_vport_stats(struct mlx5_eswitch *esw, u16 vport_num, struct ifla_vf_stats *vf_stats) @@ -2366,10 +2069,23 @@ int mlx5_esw_try_lock(struct mlx5_eswitch *esw) */ void mlx5_esw_unlock(struct mlx5_eswitch *esw) { + if (!mlx5_esw_allowed(esw)) + return; up_write(&esw->mode_lock); } /** + * mlx5_esw_lock() - Take write lock on esw mode lock + * @esw: eswitch device. + */ +void mlx5_esw_lock(struct mlx5_eswitch *esw) +{ + if (!mlx5_esw_allowed(esw)) + return; + down_write(&esw->mode_lock); +} + +/** * mlx5_eswitch_get_total_vports - Get total vports of the eswitch * * @dev: Pointer to core device @@ -2384,3 +2100,15 @@ u16 mlx5_eswitch_get_total_vports(const struct mlx5_core_dev *dev) return mlx5_esw_allowed(esw) ? esw->total_vports : 0; } EXPORT_SYMBOL_GPL(mlx5_eswitch_get_total_vports); + +/** + * mlx5_eswitch_get_core_dev - Get the mdev device + * @esw : eswitch device. + * + * Return the mellanox core device which manages the eswitch. + */ +struct mlx5_core_dev *mlx5_eswitch_get_core_dev(struct mlx5_eswitch *esw) +{ + return mlx5_esw_allowed(esw) ? esw->dev : NULL; +} +EXPORT_SYMBOL(mlx5_eswitch_get_core_dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index d562edf5b0bc..2c7444101bb9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -46,7 +46,7 @@ #include "lib/fs_chains.h" #include "sf/sf.h" #include "en/tc_ct.h" -#include "esw/sample.h" +#include "en/tc/sample.h" enum mlx5_mapped_obj_type { MLX5_MAPPED_OBJ_CHAIN, @@ -61,6 +61,7 @@ struct mlx5_mapped_obj { u32 group_id; u32 rate; u32 trunc_size; + u32 tunnel_id; } sample; }; }; @@ -75,17 +76,20 @@ struct mlx5_mapped_obj { #define MLX5_MAX_MC_PER_VPORT(dev) \ (1 << MLX5_CAP_GEN(dev, log_max_current_mc_list)) -#define MLX5_MIN_BW_SHARE 1 - -#define MLX5_RATE_TO_BW_SHARE(rate, divider, limit) \ - min_t(u32, max_t(u32, (rate) / (divider), MLX5_MIN_BW_SHARE), limit) - #define mlx5_esw_has_fwd_fdb(dev) \ MLX5_CAP_ESW_FLOWTABLE(dev, fdb_multi_path_to_table) #define esw_chains(esw) \ ((esw)->fdb_table.offloads.esw_chains_priv) +enum { + MAPPING_TYPE_CHAIN, + MAPPING_TYPE_TUNNEL, + MAPPING_TYPE_TUNNEL_ENC_OPTS, + MAPPING_TYPE_LABELS, + MAPPING_TYPE_ZONE, +}; + struct vport_ingress { struct mlx5_flow_table *acl; struct mlx5_flow_handle *allow_rule; @@ -124,6 +128,8 @@ struct vport_egress { struct { struct mlx5_flow_group *fwd_grp; struct mlx5_flow_handle *fwd_rule; + struct mlx5_flow_handle *bounce_rule; + struct mlx5_flow_group *bounce_grp; } offloads; }; }; @@ -150,8 +156,6 @@ enum mlx5_eswitch_vport_event { MLX5_VPORT_PROMISC_CHANGE = BIT(3), }; -struct mlx5_esw_bridge; - struct mlx5_vport { struct mlx5_core_dev *dev; struct hlist_head uc_list[MLX5_L2_ADDR_HASH_SIZE]; @@ -173,6 +177,7 @@ struct mlx5_vport { u32 bw_share; u32 min_rate; u32 max_rate; + struct mlx5_esw_rate_group *group; } qos; u16 vport; @@ -180,7 +185,6 @@ struct mlx5_vport { enum mlx5_eswitch_vport_event enabled_events; int index; struct devlink_port *dl_port; - struct mlx5_esw_bridge *bridge; }; struct mlx5_esw_indir_table; @@ -302,7 +306,9 @@ struct mlx5_eswitch { struct { bool enabled; - u32 root_tsar_id; + u32 root_tsar_ix; + struct mlx5_esw_rate_group *group0; + struct list_head groups; /* Protected by esw->state_lock */ } qos; struct mlx5_esw_bridge_offloads *br_offloads; @@ -315,6 +321,7 @@ struct mlx5_eswitch { u32 large_group_num; } params; struct blocking_notifier_head n_head; + struct lock_class_key mode_lock_key; }; void esw_offloads_disable(struct mlx5_eswitch *esw); @@ -327,8 +334,7 @@ int mlx5_esw_offloads_vport_metadata_set(struct mlx5_eswitch *esw, bool enable); u32 mlx5_esw_match_metadata_alloc(struct mlx5_eswitch *esw); void mlx5_esw_match_metadata_free(struct mlx5_eswitch *esw, u32 metadata); -int mlx5_esw_modify_vport_rate(struct mlx5_eswitch *esw, u16 vport_num, - u32 rate_mbps); +int mlx5_esw_qos_modify_vport_rate(struct mlx5_eswitch *esw, u16 vport_num, u32 rate_mbps); /* E-Switch API */ int mlx5_eswitch_init(struct mlx5_core_dev *dev); @@ -351,6 +357,10 @@ int mlx5_eswitch_set_vport_trust(struct mlx5_eswitch *esw, u16 vport_num, bool setting); int mlx5_eswitch_set_vport_rate(struct mlx5_eswitch *esw, u16 vport, u32 max_rate, u32 min_rate); +int mlx5_esw_qos_vport_update_group(struct mlx5_eswitch *esw, + struct mlx5_vport *vport, + struct mlx5_esw_rate_group *group, + struct netlink_ext_ack *extack); int mlx5_eswitch_set_vepa(struct mlx5_eswitch *esw, u8 setting); int mlx5_eswitch_get_vepa(struct mlx5_eswitch *esw, u8 *setting); int mlx5_eswitch_get_vport_config(struct mlx5_eswitch *esw, @@ -461,7 +471,6 @@ struct mlx5_esw_flow_attr { } dests[MLX5_MAX_FLOW_FWD_VPORTS]; struct mlx5_rx_tun_attr *rx_tun_attr; struct mlx5_pkt_reformat *decap_pkt_reformat; - struct mlx5_sample_attr *sample; }; int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode, @@ -475,12 +484,10 @@ int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink, struct netlink_ext_ack *extack); int mlx5_devlink_eswitch_encap_mode_get(struct devlink *devlink, enum devlink_eswitch_encap_mode *encap); -int mlx5_devlink_port_function_hw_addr_get(struct devlink *devlink, - struct devlink_port *port, +int mlx5_devlink_port_function_hw_addr_get(struct devlink_port *port, u8 *hw_addr, int *hw_addr_len, struct netlink_ext_ack *extack); -int mlx5_devlink_port_function_hw_addr_set(struct devlink *devlink, - struct devlink_port *port, +int mlx5_devlink_port_function_hw_addr_set(struct devlink_port *port, const u8 *hw_addr, int hw_addr_len, struct netlink_ext_ack *extack); @@ -699,11 +706,18 @@ void mlx5_esw_get(struct mlx5_core_dev *dev); void mlx5_esw_put(struct mlx5_core_dev *dev); int mlx5_esw_try_lock(struct mlx5_eswitch *esw); void mlx5_esw_unlock(struct mlx5_eswitch *esw); +void mlx5_esw_lock(struct mlx5_eswitch *esw); void esw_vport_change_handle_locked(struct mlx5_vport *vport); bool mlx5_esw_offloads_controller_valid(const struct mlx5_eswitch *esw, u32 controller); +int mlx5_eswitch_offloads_config_single_fdb(struct mlx5_eswitch *master_esw, + struct mlx5_eswitch *slave_esw); +void mlx5_eswitch_offloads_destroy_single_fdb(struct mlx5_eswitch *master_esw, + struct mlx5_eswitch *slave_esw); +int mlx5_eswitch_reload_reps(struct mlx5_eswitch *esw); + #else /* CONFIG_MLX5_ESWITCH */ /* eswitch API stubs */ static inline int mlx5_eswitch_init(struct mlx5_core_dev *dev) { return 0; } @@ -719,6 +733,9 @@ static inline const u32 *mlx5_esw_query_functions(struct mlx5_core_dev *dev) return ERR_PTR(-EOPNOTSUPP); } +static inline void mlx5_esw_unlock(struct mlx5_eswitch *esw) { return; } +static inline void mlx5_esw_lock(struct mlx5_eswitch *esw) { return; } + static inline struct mlx5_flow_handle * esw_add_restore_rule(struct mlx5_eswitch *esw, u32 tag) { @@ -731,6 +748,23 @@ mlx5_esw_vport_to_devlink_port_index(const struct mlx5_core_dev *dev, { return vport_num; } + +static inline int +mlx5_eswitch_offloads_config_single_fdb(struct mlx5_eswitch *master_esw, + struct mlx5_eswitch *slave_esw) +{ + return 0; +} + +static inline void +mlx5_eswitch_offloads_destroy_single_fdb(struct mlx5_eswitch *master_esw, + struct mlx5_eswitch *slave_esw) {} + +static inline int +mlx5_eswitch_reload_reps(struct mlx5_eswitch *esw) +{ + return 0; +} #endif /* CONFIG_MLX5_ESWITCH */ #endif /* __MLX5_ESWITCH_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 3bb71a186004..0d461e38add3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -187,12 +187,12 @@ esw_cleanup_decap_indir(struct mlx5_eswitch *esw, static int esw_setup_sampler_dest(struct mlx5_flow_destination *dest, struct mlx5_flow_act *flow_act, - struct mlx5_esw_flow_attr *esw_attr, + struct mlx5_flow_attr *attr, int i) { flow_act->flags |= FLOW_ACT_IGNORE_FLOW_LEVEL; dest[i].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER; - dest[i].sampler_id = esw_attr->sample->sampler_id; + dest[i].sampler_id = attr->sample_attr->sampler_id; return 0; } @@ -435,7 +435,7 @@ esw_setup_dests(struct mlx5_flow_destination *dest, attr->flags |= MLX5_ESW_ATTR_FLAG_SRC_REWRITE; if (attr->flags & MLX5_ESW_ATTR_FLAG_SAMPLE) { - esw_setup_sampler_dest(dest, flow_act, esw_attr, *i); + esw_setup_sampler_dest(dest, flow_act, attr, *i); (*i)++; } else if (attr->dest_ft) { esw_setup_ft_dest(dest, flow_act, esw, attr, spec, *i); @@ -540,10 +540,7 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) flow_act.modify_hdr = attr->modify_hdr; - /* esw_attr->sample is allocated only when there is a sample action */ - if (esw_attr->sample && esw_attr->sample->sample_default_tbl) { - fdb = esw_attr->sample->sample_default_tbl; - } else if (split) { + if (split) { fwd_attr.chain = attr->chain; fwd_attr.prio = attr->prio; fwd_attr.vport = esw_attr->in_rep->vport; @@ -927,6 +924,7 @@ out: struct mlx5_flow_handle * mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *on_esw, + struct mlx5_eswitch *from_esw, struct mlx5_eswitch_rep *rep, u32 sqn) { @@ -945,10 +943,10 @@ mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *on_esw, misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters); MLX5_SET(fte_match_set_misc, misc, source_sqn, sqn); /* source vport is the esw manager */ - MLX5_SET(fte_match_set_misc, misc, source_port, rep->esw->manager_vport); + MLX5_SET(fte_match_set_misc, misc, source_port, from_esw->manager_vport); if (MLX5_CAP_ESW(on_esw->dev, merged_eswitch)) MLX5_SET(fte_match_set_misc, misc, source_eswitch_owner_vhca_id, - MLX5_CAP_GEN(rep->esw->dev, vhca_id)); + MLX5_CAP_GEN(from_esw->dev, vhca_id)); misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters); MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_sqn); @@ -964,6 +962,9 @@ mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *on_esw, dest.vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID; flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; + if (rep->vport == MLX5_VPORT_UPLINK) + spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_LOCAL_VPORT; + flow_rule = mlx5_add_flow_rules(on_esw->fdb_table.offloads.slow_fdb, spec, &flow_act, &dest, 1); if (IS_ERR(flow_rule)) @@ -1614,7 +1615,18 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw) goto ns_err; } - table_size = esw->total_vports * MAX_SQ_NVPORTS + MAX_PF_SQ + + /* To be strictly correct: + * MLX5_MAX_PORTS * (esw->total_vports * MAX_SQ_NVPORTS + MAX_PF_SQ) + * should be: + * esw->total_vports * MAX_SQ_NVPORTS + MAX_PF_SQ + + * peer_esw->total_vports * MAX_SQ_NVPORTS + MAX_PF_SQ + * but as the peer device might not be in switchdev mode it's not + * possible. We use the fact that by default FW sets max vfs and max sfs + * to the same value on both devices. If it needs to be changed in the future note + * the peer miss group should also be created based on the number of + * total vports of the peer (currently is also uses esw->total_vports). + */ + table_size = MLX5_MAX_PORTS * (esw->total_vports * MAX_SQ_NVPORTS + MAX_PF_SQ) + MLX5_ESW_MISS_FLOWS + esw->total_vports + esw->esw_funcs.num_vfs; /* create the slow path fdb with encap set, so further table instances @@ -1671,7 +1683,8 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw) source_eswitch_owner_vhca_id_valid, 1); } - ix = esw->total_vports * MAX_SQ_NVPORTS + MAX_PF_SQ; + /* See comment above table_size calculation */ + ix = MLX5_MAX_PORTS * (esw->total_vports * MAX_SQ_NVPORTS + MAX_PF_SQ); MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 0); MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, ix - 1); @@ -2311,14 +2324,293 @@ void esw_offloads_unload_rep(struct mlx5_eswitch *esw, u16 vport_num) mlx5_esw_offloads_devlink_port_unregister(esw, vport_num); } +static int esw_set_uplink_slave_ingress_root(struct mlx5_core_dev *master, + struct mlx5_core_dev *slave) +{ + u32 in[MLX5_ST_SZ_DW(set_flow_table_root_in)] = {}; + u32 out[MLX5_ST_SZ_DW(set_flow_table_root_out)] = {}; + struct mlx5_eswitch *esw; + struct mlx5_flow_root_namespace *root; + struct mlx5_flow_namespace *ns; + struct mlx5_vport *vport; + int err; + + MLX5_SET(set_flow_table_root_in, in, opcode, + MLX5_CMD_OP_SET_FLOW_TABLE_ROOT); + MLX5_SET(set_flow_table_root_in, in, table_type, FS_FT_ESW_INGRESS_ACL); + MLX5_SET(set_flow_table_root_in, in, other_vport, 1); + MLX5_SET(set_flow_table_root_in, in, vport_number, MLX5_VPORT_UPLINK); + + if (master) { + esw = master->priv.eswitch; + vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_UPLINK); + MLX5_SET(set_flow_table_root_in, in, table_of_other_vport, 1); + MLX5_SET(set_flow_table_root_in, in, table_vport_number, + MLX5_VPORT_UPLINK); + + ns = mlx5_get_flow_vport_acl_namespace(master, + MLX5_FLOW_NAMESPACE_ESW_INGRESS, + vport->index); + root = find_root(&ns->node); + mutex_lock(&root->chain_lock); + + MLX5_SET(set_flow_table_root_in, in, + table_eswitch_owner_vhca_id_valid, 1); + MLX5_SET(set_flow_table_root_in, in, + table_eswitch_owner_vhca_id, + MLX5_CAP_GEN(master, vhca_id)); + MLX5_SET(set_flow_table_root_in, in, table_id, + root->root_ft->id); + } else { + esw = slave->priv.eswitch; + vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_UPLINK); + ns = mlx5_get_flow_vport_acl_namespace(slave, + MLX5_FLOW_NAMESPACE_ESW_INGRESS, + vport->index); + root = find_root(&ns->node); + mutex_lock(&root->chain_lock); + MLX5_SET(set_flow_table_root_in, in, table_id, root->root_ft->id); + } + + err = mlx5_cmd_exec(slave, in, sizeof(in), out, sizeof(out)); + mutex_unlock(&root->chain_lock); + + return err; +} + +static int esw_set_slave_root_fdb(struct mlx5_core_dev *master, + struct mlx5_core_dev *slave) +{ + u32 in[MLX5_ST_SZ_DW(set_flow_table_root_in)] = {}; + u32 out[MLX5_ST_SZ_DW(set_flow_table_root_out)] = {}; + struct mlx5_flow_root_namespace *root; + struct mlx5_flow_namespace *ns; + int err; + + MLX5_SET(set_flow_table_root_in, in, opcode, + MLX5_CMD_OP_SET_FLOW_TABLE_ROOT); + MLX5_SET(set_flow_table_root_in, in, table_type, + FS_FT_FDB); + + if (master) { + ns = mlx5_get_flow_namespace(master, + MLX5_FLOW_NAMESPACE_FDB); + root = find_root(&ns->node); + mutex_lock(&root->chain_lock); + MLX5_SET(set_flow_table_root_in, in, + table_eswitch_owner_vhca_id_valid, 1); + MLX5_SET(set_flow_table_root_in, in, + table_eswitch_owner_vhca_id, + MLX5_CAP_GEN(master, vhca_id)); + MLX5_SET(set_flow_table_root_in, in, table_id, + root->root_ft->id); + } else { + ns = mlx5_get_flow_namespace(slave, + MLX5_FLOW_NAMESPACE_FDB); + root = find_root(&ns->node); + mutex_lock(&root->chain_lock); + MLX5_SET(set_flow_table_root_in, in, table_id, + root->root_ft->id); + } + + err = mlx5_cmd_exec(slave, in, sizeof(in), out, sizeof(out)); + mutex_unlock(&root->chain_lock); + + return err; +} + +static int __esw_set_master_egress_rule(struct mlx5_core_dev *master, + struct mlx5_core_dev *slave, + struct mlx5_vport *vport, + struct mlx5_flow_table *acl) +{ + struct mlx5_flow_handle *flow_rule = NULL; + struct mlx5_flow_destination dest = {}; + struct mlx5_flow_act flow_act = {}; + struct mlx5_flow_spec *spec; + int err = 0; + void *misc; + + spec = kvzalloc(sizeof(*spec), GFP_KERNEL); + if (!spec) + return -ENOMEM; + + spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS; + misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, + misc_parameters); + MLX5_SET(fte_match_set_misc, misc, source_port, MLX5_VPORT_UPLINK); + MLX5_SET(fte_match_set_misc, misc, source_eswitch_owner_vhca_id, + MLX5_CAP_GEN(slave, vhca_id)); + + misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters); + MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port); + MLX5_SET_TO_ONES(fte_match_set_misc, misc, + source_eswitch_owner_vhca_id); + + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; + dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT; + dest.vport.num = slave->priv.eswitch->manager_vport; + dest.vport.vhca_id = MLX5_CAP_GEN(slave, vhca_id); + dest.vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID; + + flow_rule = mlx5_add_flow_rules(acl, spec, &flow_act, + &dest, 1); + if (IS_ERR(flow_rule)) + err = PTR_ERR(flow_rule); + else + vport->egress.offloads.bounce_rule = flow_rule; + + kvfree(spec); + return err; +} + +static int esw_set_master_egress_rule(struct mlx5_core_dev *master, + struct mlx5_core_dev *slave) +{ + int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + struct mlx5_eswitch *esw = master->priv.eswitch; + struct mlx5_flow_table_attr ft_attr = { + .max_fte = 1, .prio = 0, .level = 0, + }; + struct mlx5_flow_namespace *egress_ns; + struct mlx5_flow_table *acl; + struct mlx5_flow_group *g; + struct mlx5_vport *vport; + void *match_criteria; + u32 *flow_group_in; + int err; + + vport = mlx5_eswitch_get_vport(esw, esw->manager_vport); + if (IS_ERR(vport)) + return PTR_ERR(vport); + + egress_ns = mlx5_get_flow_vport_acl_namespace(master, + MLX5_FLOW_NAMESPACE_ESW_EGRESS, + vport->index); + if (!egress_ns) + return -EINVAL; + + if (vport->egress.acl) + return -EINVAL; + + flow_group_in = kvzalloc(inlen, GFP_KERNEL); + if (!flow_group_in) + return -ENOMEM; + + acl = mlx5_create_vport_flow_table(egress_ns, &ft_attr, vport->vport); + if (IS_ERR(acl)) { + err = PTR_ERR(acl); + goto out; + } + + match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in, + match_criteria); + MLX5_SET_TO_ONES(fte_match_param, match_criteria, + misc_parameters.source_port); + MLX5_SET_TO_ONES(fte_match_param, match_criteria, + misc_parameters.source_eswitch_owner_vhca_id); + MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable, + MLX5_MATCH_MISC_PARAMETERS); + + MLX5_SET(create_flow_group_in, flow_group_in, + source_eswitch_owner_vhca_id_valid, 1); + MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 0); + MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 0); + + g = mlx5_create_flow_group(acl, flow_group_in); + if (IS_ERR(g)) { + err = PTR_ERR(g); + goto err_group; + } + + err = __esw_set_master_egress_rule(master, slave, vport, acl); + if (err) + goto err_rule; + + vport->egress.acl = acl; + vport->egress.offloads.bounce_grp = g; + + kvfree(flow_group_in); + + return 0; + +err_rule: + mlx5_destroy_flow_group(g); +err_group: + mlx5_destroy_flow_table(acl); +out: + kvfree(flow_group_in); + return err; +} + +static void esw_unset_master_egress_rule(struct mlx5_core_dev *dev) +{ + struct mlx5_vport *vport; + + vport = mlx5_eswitch_get_vport(dev->priv.eswitch, + dev->priv.eswitch->manager_vport); + + esw_acl_egress_ofld_cleanup(vport); +} + +int mlx5_eswitch_offloads_config_single_fdb(struct mlx5_eswitch *master_esw, + struct mlx5_eswitch *slave_esw) +{ + int err; + + err = esw_set_uplink_slave_ingress_root(master_esw->dev, + slave_esw->dev); + if (err) + return -EINVAL; + + err = esw_set_slave_root_fdb(master_esw->dev, + slave_esw->dev); + if (err) + goto err_fdb; + + err = esw_set_master_egress_rule(master_esw->dev, + slave_esw->dev); + if (err) + goto err_acl; + + return err; + +err_acl: + esw_set_slave_root_fdb(NULL, slave_esw->dev); + +err_fdb: + esw_set_uplink_slave_ingress_root(NULL, slave_esw->dev); + + return err; +} + +void mlx5_eswitch_offloads_destroy_single_fdb(struct mlx5_eswitch *master_esw, + struct mlx5_eswitch *slave_esw) +{ + esw_unset_master_egress_rule(master_esw->dev); + esw_set_slave_root_fdb(NULL, slave_esw->dev); + esw_set_uplink_slave_ingress_root(NULL, slave_esw->dev); +} + #define ESW_OFFLOADS_DEVCOM_PAIR (0) #define ESW_OFFLOADS_DEVCOM_UNPAIR (1) -static int mlx5_esw_offloads_pair(struct mlx5_eswitch *esw, - struct mlx5_eswitch *peer_esw) +static void mlx5_esw_offloads_rep_event_unpair(struct mlx5_eswitch *esw) { + const struct mlx5_eswitch_rep_ops *ops; + struct mlx5_eswitch_rep *rep; + unsigned long i; + u8 rep_type; - return esw_add_fdb_peer_miss_rules(esw, peer_esw->dev); + mlx5_esw_for_each_rep(esw, i, rep) { + rep_type = NUM_REP_TYPES; + while (rep_type--) { + ops = esw->offloads.rep_ops[rep_type]; + if (atomic_read(&rep->rep_data[rep_type].state) == REP_LOADED && + ops->event) + ops->event(esw, rep, MLX5_SWITCHDEV_EVENT_UNPAIR, NULL); + } + } } static void mlx5_esw_offloads_unpair(struct mlx5_eswitch *esw) @@ -2326,9 +2618,42 @@ static void mlx5_esw_offloads_unpair(struct mlx5_eswitch *esw) #if IS_ENABLED(CONFIG_MLX5_CLS_ACT) mlx5e_tc_clean_fdb_peer_flows(esw); #endif + mlx5_esw_offloads_rep_event_unpair(esw); esw_del_fdb_peer_miss_rules(esw); } +static int mlx5_esw_offloads_pair(struct mlx5_eswitch *esw, + struct mlx5_eswitch *peer_esw) +{ + const struct mlx5_eswitch_rep_ops *ops; + struct mlx5_eswitch_rep *rep; + unsigned long i; + u8 rep_type; + int err; + + err = esw_add_fdb_peer_miss_rules(esw, peer_esw->dev); + if (err) + return err; + + mlx5_esw_for_each_rep(esw, i, rep) { + for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++) { + ops = esw->offloads.rep_ops[rep_type]; + if (atomic_read(&rep->rep_data[rep_type].state) == REP_LOADED && + ops->event) { + err = ops->event(esw, rep, MLX5_SWITCHDEV_EVENT_PAIR, peer_esw); + if (err) + goto err_out; + } + } + } + + return 0; + +err_out: + mlx5_esw_offloads_unpair(esw); + return err; +} + static int mlx5_esw_offloads_set_ns_peer(struct mlx5_eswitch *esw, struct mlx5_eswitch *peer_esw, bool pair) @@ -2619,6 +2944,31 @@ static void esw_destroy_uplink_offloads_acl_tables(struct mlx5_eswitch *esw) esw_vport_destroy_offloads_acl_tables(esw, vport); } +int mlx5_eswitch_reload_reps(struct mlx5_eswitch *esw) +{ + struct mlx5_eswitch_rep *rep; + unsigned long i; + int ret; + + if (!esw || esw->mode != MLX5_ESWITCH_OFFLOADS) + return 0; + + rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_UPLINK); + if (atomic_read(&rep->rep_data[REP_ETH].state) != REP_LOADED) + return 0; + + ret = mlx5_esw_offloads_rep_load(esw, MLX5_VPORT_UPLINK); + if (ret) + return ret; + + mlx5_esw_for_each_rep(esw, i, rep) { + if (atomic_read(&rep->rep_data[REP_ETH].state) == REP_LOADED) + mlx5_esw_offloads_rep_load(esw, rep->vport); + } + + return 0; +} + static int esw_offloads_steering_init(struct mlx5_eswitch *esw) { struct mlx5_esw_indir_table *indir; @@ -2788,6 +3138,7 @@ int esw_offloads_enable(struct mlx5_eswitch *esw) struct mapping_ctx *reg_c0_obj_pool; struct mlx5_vport *vport; unsigned long i; + u64 mapping_id; int err; if (MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, reformat) && @@ -2811,9 +3162,13 @@ int esw_offloads_enable(struct mlx5_eswitch *esw) if (err) goto err_vport_metadata; - reg_c0_obj_pool = mapping_create(sizeof(struct mlx5_mapped_obj), - ESW_REG_C0_USER_DATA_METADATA_MASK, - true); + mapping_id = mlx5_query_nic_system_image_guid(esw->dev); + + reg_c0_obj_pool = mapping_create_for_id(mapping_id, MAPPING_TYPE_CHAIN, + sizeof(struct mlx5_mapped_obj), + ESW_REG_C0_USER_DATA_METADATA_MASK, + true); + if (IS_ERR(reg_c0_obj_pool)) { err = PTR_ERR(reg_c0_obj_pool); goto err_pool; @@ -2991,10 +3346,11 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode, if (esw_mode_from_devlink(mode, &mlx5_mode)) return -EINVAL; + mlx5_lag_disable_change(esw->dev); err = mlx5_esw_try_lock(esw); if (err < 0) { NL_SET_ERR_MSG_MOD(extack, "Can't change mode, E-Switch is busy"); - return err; + goto enable_lag; } cur_mlx5_mode = err; err = 0; @@ -3018,6 +3374,8 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode, unlock: mlx5_esw_unlock(esw); +enable_lag: + mlx5_lag_enable_change(esw->dev); return err; } @@ -3091,8 +3449,11 @@ int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode, switch (MLX5_CAP_ETH(dev, wqe_inline_mode)) { case MLX5_CAP_INLINE_MODE_NOT_REQUIRED: - if (mode == DEVLINK_ESWITCH_INLINE_MODE_NONE) + if (mode == DEVLINK_ESWITCH_INLINE_MODE_NONE) { + err = 0; goto out; + } + fallthrough; case MLX5_CAP_INLINE_MODE_L2: NL_SET_ERR_MSG_MOD(extack, "Inline mode can't be set"); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/events.c b/drivers/net/ethernet/mellanox/mlx5/core/events.c index d713ae24d6b6..a1ac3a654962 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/events.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/events.c @@ -27,7 +27,7 @@ static int pcie_core(struct notifier_block *, unsigned long, void *); static int forward_event(struct notifier_block *, unsigned long, void *); static struct mlx5_nb events_nbs_ref[] = { - /* Events to be proccessed by mlx5_core */ + /* Events to be processed by mlx5_core */ {.nb.notifier_call = any_notifier, .event_type = MLX5_EVENT_TYPE_NOTIFY_ANY }, {.nb.notifier_call = temp_warn, .event_type = MLX5_EVENT_TYPE_TEMP_WARN_EVENT }, {.nb.notifier_call = port_module, .event_type = MLX5_EVENT_TYPE_PORT_MODULE_EVENT }, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c index d5da4ab65766..306279b7f9e7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c @@ -453,7 +453,7 @@ static int mlx5_fpga_conn_create_cq(struct mlx5_fpga_conn *conn, int cq_size) cqc = MLX5_ADDR_OF(create_cq_in, in, cq_context); MLX5_SET(cqc, cqc, log_cq_size, ilog2(cq_size)); - MLX5_SET(cqc, cqc, c_eqn, eqn); + MLX5_SET(cqc, cqc, c_eqn_or_apu_element, eqn); MLX5_SET(cqc, cqc, uar_page, fdev->conn_res.uar->index); MLX5_SET(cqc, cqc, log_page_size, conn->cq.wq_ctrl.buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c index 0bba92cf5dc0..8ec148010d62 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c @@ -1516,7 +1516,7 @@ static int mlx5_fpga_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm, mutex_lock(&fpga_xfrm->lock); if (!fpga_xfrm->sa_ctx) - /* Unbounded xfrm, chane only sw attrs */ + /* Unbounded xfrm, change only sw attrs */ goto change_sw_xfrm_attrs; /* copy original hw sa */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index 896a6c3dbdb7..7db8df64a60e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -152,17 +152,56 @@ static int mlx5_cmd_stub_destroy_ns(struct mlx5_flow_root_namespace *ns) return 0; } +static int mlx5_cmd_set_slave_root_fdb(struct mlx5_core_dev *master, + struct mlx5_core_dev *slave, + bool ft_id_valid, + u32 ft_id) +{ + u32 out[MLX5_ST_SZ_DW(set_flow_table_root_out)] = {}; + u32 in[MLX5_ST_SZ_DW(set_flow_table_root_in)] = {}; + struct mlx5_flow_root_namespace *root; + struct mlx5_flow_namespace *ns; + + MLX5_SET(set_flow_table_root_in, in, opcode, + MLX5_CMD_OP_SET_FLOW_TABLE_ROOT); + MLX5_SET(set_flow_table_root_in, in, table_type, + FS_FT_FDB); + if (ft_id_valid) { + MLX5_SET(set_flow_table_root_in, in, + table_eswitch_owner_vhca_id_valid, 1); + MLX5_SET(set_flow_table_root_in, in, + table_eswitch_owner_vhca_id, + MLX5_CAP_GEN(master, vhca_id)); + MLX5_SET(set_flow_table_root_in, in, table_id, + ft_id); + } else { + ns = mlx5_get_flow_namespace(slave, + MLX5_FLOW_NAMESPACE_FDB); + root = find_root(&ns->node); + MLX5_SET(set_flow_table_root_in, in, table_id, + root->root_ft->id); + } + + return mlx5_cmd_exec(slave, in, sizeof(in), out, sizeof(out)); +} + static int mlx5_cmd_update_root_ft(struct mlx5_flow_root_namespace *ns, struct mlx5_flow_table *ft, u32 underlay_qpn, bool disconnect) { u32 in[MLX5_ST_SZ_DW(set_flow_table_root_in)] = {}; struct mlx5_core_dev *dev = ns->dev; + int err; if ((MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_IB) && underlay_qpn == 0) return 0; + if (ft->type == FS_FT_FDB && + mlx5_lag_is_shared_fdb(dev) && + !mlx5_lag_is_master(dev)) + return 0; + MLX5_SET(set_flow_table_root_in, in, opcode, MLX5_CMD_OP_SET_FLOW_TABLE_ROOT); MLX5_SET(set_flow_table_root_in, in, table_type, ft->type); @@ -177,7 +216,24 @@ static int mlx5_cmd_update_root_ft(struct mlx5_flow_root_namespace *ns, MLX5_SET(set_flow_table_root_in, in, other_vport, !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT)); - return mlx5_cmd_exec_in(dev, set_flow_table_root, in); + err = mlx5_cmd_exec_in(dev, set_flow_table_root, in); + if (!err && + ft->type == FS_FT_FDB && + mlx5_lag_is_shared_fdb(dev) && + mlx5_lag_is_master(dev)) { + err = mlx5_cmd_set_slave_root_fdb(dev, + mlx5_lag_get_peer_mdev(dev), + !disconnect, (!disconnect) ? + ft->id : 0); + if (err && !disconnect) { + MLX5_SET(set_flow_table_root_in, in, op_mod, 0); + MLX5_SET(set_flow_table_root_in, in, table_id, + ns->root_ft->id); + mlx5_cmd_exec_in(dev, set_flow_table_root, in); + } + } + + return err; } static int mlx5_cmd_create_flow_table(struct mlx5_flow_root_namespace *ns, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index c0697e1b7118..9fe8e3c204d6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -413,7 +413,7 @@ static bool check_valid_spec(const struct mlx5_flow_spec *spec) return true; } -static struct mlx5_flow_root_namespace *find_root(struct fs_node *node) +struct mlx5_flow_root_namespace *find_root(struct fs_node *node) { struct fs_node *root; struct mlx5_flow_namespace *ns; @@ -2343,7 +2343,7 @@ static int create_leaf_prios(struct mlx5_flow_namespace *ns, int prio, #define FLOW_TABLE_BIT_SZ 1 #define GET_FLOW_TABLE_CAP(dev, offset) \ - ((be32_to_cpu(*((__be32 *)(dev->caps.hca_cur[MLX5_CAP_FLOW_TABLE]) + \ + ((be32_to_cpu(*((__be32 *)(dev->caps.hca[MLX5_CAP_FLOW_TABLE]->cur) + \ offset / 32)) >> \ (32 - FLOW_TABLE_BIT_SZ - (offset & 0x1f))) & FLOW_TABLE_BIT_SZ) static bool has_required_caps(struct mlx5_core_dev *dev, struct node_caps *caps) @@ -2493,7 +2493,7 @@ static void set_prio_attrs_in_prio(struct fs_prio *prio, int acc_level) acc_level_ns = set_prio_attrs_in_ns(ns, acc_level); /* If this a prio with chains, and we can jump from one chain - * (namepsace) to another, so we accumulate the levels + * (namespace) to another, so we accumulate the levels */ if (prio->node.type == FS_TYPE_PRIO_CHAINS) acc_level = acc_level_ns; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index 7317cdeab661..98240badc342 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -294,6 +294,8 @@ void mlx5_fs_egress_acls_cleanup(struct mlx5_core_dev *dev); int mlx5_fs_ingress_acls_init(struct mlx5_core_dev *dev, int total_vports); void mlx5_fs_ingress_acls_cleanup(struct mlx5_core_dev *dev); +struct mlx5_flow_root_namespace *find_root(struct fs_node *node); + #define fs_get_obj(v, _node) {v = container_of((_node), typeof(*v), node); } #define fs_list_for_each_entry(pos, root) \ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 9abeb80ffa31..037e18dd4be0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -170,7 +170,7 @@ static bool reset_fw_if_needed(struct mlx5_core_dev *dev) /* The reset only needs to be issued by one PF. The health buffer is * shared between all functions, and will be cleared during a reset. - * Check again to avoid a redundant 2nd reset. If the fatal erros was + * Check again to avoid a redundant 2nd reset. If the fatal errors was * PCI related a reset won't help. */ fatal_error = mlx5_health_check_fatal_sensors(dev); @@ -213,10 +213,6 @@ void mlx5_enter_error_state(struct mlx5_core_dev *dev, bool force) mutex_lock(&dev->intf_state_mutex); if (!err_detected && dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) goto unlock;/* a previous error is still being handled */ - if (dev->state == MLX5_DEVICE_STATE_UNINITIALIZED) { - dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR; - goto unlock; - } enter_error_state(dev, force); unlock: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c index 0e487ec57d5c..0c8594c7df21 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c @@ -99,7 +99,9 @@ static void mlx5i_get_channels(struct net_device *dev, } static int mlx5i_set_coalesce(struct net_device *netdev, - struct ethtool_coalesce *coal) + struct ethtool_coalesce *coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct mlx5e_priv *priv = mlx5i_epriv(netdev); @@ -107,7 +109,9 @@ static int mlx5i_set_coalesce(struct net_device *netdev, } static int mlx5i_get_coalesce(struct net_device *netdev, - struct ethtool_coalesce *coal) + struct ethtool_coalesce *coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct mlx5e_priv *priv = mlx5i_epriv(netdev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index 7d7ed025db0d..67571e5040d6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -50,7 +50,7 @@ static const struct net_device_ops mlx5i_netdev_ops = { .ndo_init = mlx5i_dev_init, .ndo_uninit = mlx5i_dev_cleanup, .ndo_change_mtu = mlx5i_change_mtu, - .ndo_do_ioctl = mlx5i_ioctl, + .ndo_eth_ioctl = mlx5i_ioctl, }; /* IPoIB mlx5 netdev profile */ @@ -314,8 +314,7 @@ static void mlx5i_cleanup_tx(struct mlx5e_priv *priv) static int mlx5i_create_flow_steering(struct mlx5e_priv *priv) { - struct ttc_params ttc_params = {}; - int tt, err; + int err; priv->fs.ns = mlx5_get_flow_namespace(priv->mdev, MLX5_FLOW_NAMESPACE_KERNEL); @@ -330,33 +329,15 @@ static int mlx5i_create_flow_steering(struct mlx5e_priv *priv) priv->netdev->hw_features &= ~NETIF_F_NTUPLE; } - mlx5e_set_ttc_basic_params(priv, &ttc_params); - mlx5e_set_inner_ttc_ft_params(&ttc_params); - for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) - ttc_params.indir_tirn[tt] = priv->inner_indir_tir[tt].tirn; - - err = mlx5e_create_inner_ttc_table(priv, &ttc_params, &priv->fs.inner_ttc); - if (err) { - netdev_err(priv->netdev, "Failed to create inner ttc table, err=%d\n", - err); - goto err_destroy_arfs_tables; - } - - mlx5e_set_ttc_ft_params(&ttc_params); - for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) - ttc_params.indir_tirn[tt] = priv->indir_tir[tt].tirn; - - err = mlx5e_create_ttc_table(priv, &ttc_params, &priv->fs.ttc); + err = mlx5e_create_ttc_table(priv); if (err) { netdev_err(priv->netdev, "Failed to create ttc table, err=%d\n", err); - goto err_destroy_inner_ttc_table; + goto err_destroy_arfs_tables; } return 0; -err_destroy_inner_ttc_table: - mlx5e_destroy_inner_ttc_table(priv, &priv->fs.inner_ttc); err_destroy_arfs_tables: mlx5e_arfs_destroy_tables(priv); @@ -365,17 +346,20 @@ err_destroy_arfs_tables: static void mlx5i_destroy_flow_steering(struct mlx5e_priv *priv) { - mlx5e_destroy_ttc_table(priv, &priv->fs.ttc); - mlx5e_destroy_inner_ttc_table(priv, &priv->fs.inner_ttc); + mlx5e_destroy_ttc_table(priv); mlx5e_arfs_destroy_tables(priv); } static int mlx5i_init_rx(struct mlx5e_priv *priv) { struct mlx5_core_dev *mdev = priv->mdev; - u16 max_nch = priv->max_nch; + struct mlx5e_lro_param lro_param; int err; + priv->rx_res = mlx5e_rx_res_alloc(); + if (!priv->rx_res) + return -ENOMEM; + mlx5e_create_q_counters(priv); err = mlx5e_open_drop_rq(priv, &priv->drop_rq); @@ -384,54 +368,38 @@ static int mlx5i_init_rx(struct mlx5e_priv *priv) goto err_destroy_q_counters; } - err = mlx5e_create_indirect_rqt(priv); + lro_param = mlx5e_get_lro_param(&priv->channels.params); + err = mlx5e_rx_res_init(priv->rx_res, priv->mdev, 0, + priv->max_nch, priv->drop_rq.rqn, &lro_param, + priv->channels.params.num_channels); if (err) goto err_close_drop_rq; - err = mlx5e_create_direct_rqts(priv, priv->direct_tir, max_nch); - if (err) - goto err_destroy_indirect_rqts; - - err = mlx5e_create_indirect_tirs(priv, true); - if (err) - goto err_destroy_direct_rqts; - - err = mlx5e_create_direct_tirs(priv, priv->direct_tir, max_nch); - if (err) - goto err_destroy_indirect_tirs; - err = mlx5i_create_flow_steering(priv); if (err) - goto err_destroy_direct_tirs; + goto err_destroy_rx_res; return 0; -err_destroy_direct_tirs: - mlx5e_destroy_direct_tirs(priv, priv->direct_tir, max_nch); -err_destroy_indirect_tirs: - mlx5e_destroy_indirect_tirs(priv); -err_destroy_direct_rqts: - mlx5e_destroy_direct_rqts(priv, priv->direct_tir, max_nch); -err_destroy_indirect_rqts: - mlx5e_destroy_rqt(priv, &priv->indir_rqt); +err_destroy_rx_res: + mlx5e_rx_res_destroy(priv->rx_res); err_close_drop_rq: mlx5e_close_drop_rq(&priv->drop_rq); err_destroy_q_counters: mlx5e_destroy_q_counters(priv); + mlx5e_rx_res_free(priv->rx_res); + priv->rx_res = NULL; return err; } static void mlx5i_cleanup_rx(struct mlx5e_priv *priv) { - u16 max_nch = priv->max_nch; - mlx5i_destroy_flow_steering(priv); - mlx5e_destroy_direct_tirs(priv, priv->direct_tir, max_nch); - mlx5e_destroy_indirect_tirs(priv); - mlx5e_destroy_direct_rqts(priv, priv->direct_tir, max_nch); - mlx5e_destroy_rqt(priv, &priv->indir_rqt); + mlx5e_rx_res_destroy(priv->rx_res); mlx5e_close_drop_rq(&priv->drop_rq); mlx5e_destroy_q_counters(priv); + mlx5e_rx_res_free(priv->rx_res); + priv->rx_res = NULL; } /* The stats groups order is opposite to the update_stats() order calls */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c index 18ee21b06a00..5308f23702bc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c @@ -149,7 +149,7 @@ static const struct net_device_ops mlx5i_pkey_netdev_ops = { .ndo_get_stats64 = mlx5i_get_stats, .ndo_uninit = mlx5i_pkey_dev_cleanup, .ndo_change_mtu = mlx5i_pkey_change_mtu, - .ndo_do_ioctl = mlx5i_pkey_ioctl, + .ndo_eth_ioctl = mlx5i_pkey_ioctl, }; /* Child NDOs */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c index 40ef60f562b4..49ca57c6d31d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c @@ -32,7 +32,9 @@ #include <linux/netdevice.h> #include <linux/mlx5/driver.h> +#include <linux/mlx5/eswitch.h> #include <linux/mlx5/vport.h> +#include "lib/devcom.h" #include "mlx5_core.h" #include "eswitch.h" #include "lag.h" @@ -45,7 +47,7 @@ static DEFINE_SPINLOCK(lag_lock); static int mlx5_cmd_create_lag(struct mlx5_core_dev *dev, u8 remap_port1, - u8 remap_port2) + u8 remap_port2, bool shared_fdb) { u32 in[MLX5_ST_SZ_DW(create_lag_in)] = {}; void *lag_ctx = MLX5_ADDR_OF(create_lag_in, in, ctx); @@ -54,6 +56,7 @@ static int mlx5_cmd_create_lag(struct mlx5_core_dev *dev, u8 remap_port1, MLX5_SET(lagc, lag_ctx, tx_remap_affinity_1, remap_port1); MLX5_SET(lagc, lag_ctx, tx_remap_affinity_2, remap_port2); + MLX5_SET(lagc, lag_ctx, fdb_selection_mode, shared_fdb); return mlx5_cmd_exec_in(dev, create_lag, in); } @@ -224,35 +227,59 @@ void mlx5_modify_lag(struct mlx5_lag *ldev, } static int mlx5_create_lag(struct mlx5_lag *ldev, - struct lag_tracker *tracker) + struct lag_tracker *tracker, + bool shared_fdb) { struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev; + struct mlx5_core_dev *dev1 = ldev->pf[MLX5_LAG_P2].dev; + u32 in[MLX5_ST_SZ_DW(destroy_lag_in)] = {}; int err; mlx5_infer_tx_affinity_mapping(tracker, &ldev->v2p_map[MLX5_LAG_P1], &ldev->v2p_map[MLX5_LAG_P2]); - mlx5_core_info(dev0, "lag map port 1:%d port 2:%d", - ldev->v2p_map[MLX5_LAG_P1], ldev->v2p_map[MLX5_LAG_P2]); + mlx5_core_info(dev0, "lag map port 1:%d port 2:%d shared_fdb:%d", + ldev->v2p_map[MLX5_LAG_P1], ldev->v2p_map[MLX5_LAG_P2], + shared_fdb); err = mlx5_cmd_create_lag(dev0, ldev->v2p_map[MLX5_LAG_P1], - ldev->v2p_map[MLX5_LAG_P2]); - if (err) + ldev->v2p_map[MLX5_LAG_P2], shared_fdb); + if (err) { mlx5_core_err(dev0, "Failed to create LAG (%d)\n", err); + return err; + } + + if (shared_fdb) { + err = mlx5_eswitch_offloads_config_single_fdb(dev0->priv.eswitch, + dev1->priv.eswitch); + if (err) + mlx5_core_err(dev0, "Can't enable single FDB mode\n"); + else + mlx5_core_info(dev0, "Operation mode is single FDB\n"); + } + + if (err) { + MLX5_SET(destroy_lag_in, in, opcode, MLX5_CMD_OP_DESTROY_LAG); + if (mlx5_cmd_exec_in(dev0, destroy_lag, in)) + mlx5_core_err(dev0, + "Failed to deactivate RoCE LAG; driver restart required\n"); + } + return err; } int mlx5_activate_lag(struct mlx5_lag *ldev, struct lag_tracker *tracker, - u8 flags) + u8 flags, + bool shared_fdb) { bool roce_lag = !!(flags & MLX5_LAG_FLAG_ROCE); struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev; int err; - err = mlx5_create_lag(ldev, tracker); + err = mlx5_create_lag(ldev, tracker, shared_fdb); if (err) { if (roce_lag) { mlx5_core_err(dev0, @@ -266,6 +293,7 @@ int mlx5_activate_lag(struct mlx5_lag *ldev, } ldev->flags |= flags; + ldev->shared_fdb = shared_fdb; return 0; } @@ -279,6 +307,12 @@ static int mlx5_deactivate_lag(struct mlx5_lag *ldev) ldev->flags &= ~MLX5_LAG_MODE_FLAGS; mlx5_lag_mp_reset(ldev); + if (ldev->shared_fdb) { + mlx5_eswitch_offloads_destroy_single_fdb(ldev->pf[MLX5_LAG_P1].dev->priv.eswitch, + ldev->pf[MLX5_LAG_P2].dev->priv.eswitch); + ldev->shared_fdb = false; + } + MLX5_SET(destroy_lag_in, in, opcode, MLX5_CMD_OP_DESTROY_LAG); err = mlx5_cmd_exec_in(dev0, destroy_lag, in); if (err) { @@ -334,6 +368,10 @@ static void mlx5_lag_remove_devices(struct mlx5_lag *ldev) if (!ldev->pf[i].dev) continue; + if (ldev->pf[i].dev->priv.flags & + MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV) + continue; + ldev->pf[i].dev->priv.flags |= MLX5_PRIV_FLAGS_DISABLE_IB_ADEV; mlx5_rescan_drivers_locked(ldev->pf[i].dev); } @@ -343,12 +381,15 @@ static void mlx5_disable_lag(struct mlx5_lag *ldev) { struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev; struct mlx5_core_dev *dev1 = ldev->pf[MLX5_LAG_P2].dev; + bool shared_fdb = ldev->shared_fdb; bool roce_lag; int err; roce_lag = __mlx5_lag_is_roce(ldev); - if (roce_lag) { + if (shared_fdb) { + mlx5_lag_remove_devices(ldev); + } else if (roce_lag) { if (!(dev0->priv.flags & MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV)) { dev0->priv.flags |= MLX5_PRIV_FLAGS_DISABLE_IB_ADEV; mlx5_rescan_drivers_locked(dev0); @@ -360,8 +401,34 @@ static void mlx5_disable_lag(struct mlx5_lag *ldev) if (err) return; - if (roce_lag) + if (shared_fdb || roce_lag) mlx5_lag_add_devices(ldev); + + if (shared_fdb) { + if (!(dev0->priv.flags & MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV)) + mlx5_eswitch_reload_reps(dev0->priv.eswitch); + if (!(dev1->priv.flags & MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV)) + mlx5_eswitch_reload_reps(dev1->priv.eswitch); + } +} + +static bool mlx5_shared_fdb_supported(struct mlx5_lag *ldev) +{ + struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev; + struct mlx5_core_dev *dev1 = ldev->pf[MLX5_LAG_P2].dev; + + if (is_mdev_switchdev_mode(dev0) && + is_mdev_switchdev_mode(dev1) && + mlx5_eswitch_vport_match_metadata_enabled(dev0->priv.eswitch) && + mlx5_eswitch_vport_match_metadata_enabled(dev1->priv.eswitch) && + mlx5_devcom_is_paired(dev0->priv.devcom, + MLX5_DEVCOM_ESW_OFFLOADS) && + MLX5_CAP_GEN(dev1, lag_native_fdb_selection) && + MLX5_CAP_ESW(dev1, root_ft_on_other_esw) && + MLX5_CAP_ESW(dev0, esw_shared_ingress_acl)) + return true; + + return false; } static void mlx5_do_bond(struct mlx5_lag *ldev) @@ -372,14 +439,17 @@ static void mlx5_do_bond(struct mlx5_lag *ldev) bool do_bond, roce_lag; int err; - if (!mlx5_lag_is_ready(ldev)) - return; - - tracker = ldev->tracker; + if (!mlx5_lag_is_ready(ldev)) { + do_bond = false; + } else { + tracker = ldev->tracker; - do_bond = tracker.is_bonded && mlx5_lag_check_prereq(ldev); + do_bond = tracker.is_bonded && mlx5_lag_check_prereq(ldev); + } if (do_bond && !__mlx5_lag_is_active(ldev)) { + bool shared_fdb = mlx5_shared_fdb_supported(ldev); + roce_lag = !mlx5_sriov_is_enabled(dev0) && !mlx5_sriov_is_enabled(dev1); @@ -389,23 +459,40 @@ static void mlx5_do_bond(struct mlx5_lag *ldev) dev1->priv.eswitch->mode == MLX5_ESWITCH_NONE; #endif - if (roce_lag) + if (shared_fdb || roce_lag) mlx5_lag_remove_devices(ldev); err = mlx5_activate_lag(ldev, &tracker, roce_lag ? MLX5_LAG_FLAG_ROCE : - MLX5_LAG_FLAG_SRIOV); + MLX5_LAG_FLAG_SRIOV, + shared_fdb); if (err) { - if (roce_lag) + if (shared_fdb || roce_lag) mlx5_lag_add_devices(ldev); return; - } - - if (roce_lag) { + } else if (roce_lag) { dev0->priv.flags &= ~MLX5_PRIV_FLAGS_DISABLE_IB_ADEV; mlx5_rescan_drivers_locked(dev0); mlx5_nic_vport_enable_roce(dev1); + } else if (shared_fdb) { + dev0->priv.flags &= ~MLX5_PRIV_FLAGS_DISABLE_IB_ADEV; + mlx5_rescan_drivers_locked(dev0); + + err = mlx5_eswitch_reload_reps(dev0->priv.eswitch); + if (!err) + err = mlx5_eswitch_reload_reps(dev1->priv.eswitch); + + if (err) { + dev0->priv.flags |= MLX5_PRIV_FLAGS_DISABLE_IB_ADEV; + mlx5_rescan_drivers_locked(dev0); + mlx5_deactivate_lag(ldev); + mlx5_lag_add_devices(ldev); + mlx5_eswitch_reload_reps(dev0->priv.eswitch); + mlx5_eswitch_reload_reps(dev1->priv.eswitch); + mlx5_core_err(dev0, "Failed to enable lag\n"); + return; + } } } else if (do_bond && __mlx5_lag_is_active(ldev)) { mlx5_modify_lag(ldev, &tracker); @@ -419,21 +506,48 @@ static void mlx5_queue_bond_work(struct mlx5_lag *ldev, unsigned long delay) queue_delayed_work(ldev->wq, &ldev->bond_work, delay); } +static void mlx5_lag_lock_eswitches(struct mlx5_core_dev *dev0, + struct mlx5_core_dev *dev1) +{ + if (dev0) + mlx5_esw_lock(dev0->priv.eswitch); + if (dev1) + mlx5_esw_lock(dev1->priv.eswitch); +} + +static void mlx5_lag_unlock_eswitches(struct mlx5_core_dev *dev0, + struct mlx5_core_dev *dev1) +{ + if (dev1) + mlx5_esw_unlock(dev1->priv.eswitch); + if (dev0) + mlx5_esw_unlock(dev0->priv.eswitch); +} + static void mlx5_do_bond_work(struct work_struct *work) { struct delayed_work *delayed_work = to_delayed_work(work); struct mlx5_lag *ldev = container_of(delayed_work, struct mlx5_lag, bond_work); + struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev; + struct mlx5_core_dev *dev1 = ldev->pf[MLX5_LAG_P2].dev; int status; status = mlx5_dev_list_trylock(); if (!status) { - /* 1 sec delay. */ mlx5_queue_bond_work(ldev, HZ); return; } + if (ldev->mode_changes_in_progress) { + mlx5_dev_list_unlock(); + mlx5_queue_bond_work(ldev, HZ); + return; + } + + mlx5_lag_lock_eswitches(dev0, dev1); mlx5_do_bond(ldev); + mlx5_lag_unlock_eswitches(dev0, dev1); mlx5_dev_list_unlock(); } @@ -631,7 +745,7 @@ static void mlx5_ldev_remove_mdev(struct mlx5_lag *ldev, } /* Must be called with intf_mutex held */ -static void __mlx5_lag_dev_add_mdev(struct mlx5_core_dev *dev) +static int __mlx5_lag_dev_add_mdev(struct mlx5_core_dev *dev) { struct mlx5_lag *ldev = NULL; struct mlx5_core_dev *tmp_dev; @@ -639,7 +753,7 @@ static void __mlx5_lag_dev_add_mdev(struct mlx5_core_dev *dev) if (!MLX5_CAP_GEN(dev, vport_group_manager) || !MLX5_CAP_GEN(dev, lag_master) || MLX5_CAP_GEN(dev, num_lag_ports) != MLX5_MAX_PORTS) - return; + return 0; tmp_dev = mlx5_get_next_phys_dev(dev); if (tmp_dev) @@ -649,15 +763,17 @@ static void __mlx5_lag_dev_add_mdev(struct mlx5_core_dev *dev) ldev = mlx5_lag_dev_alloc(dev); if (!ldev) { mlx5_core_err(dev, "Failed to alloc lag dev\n"); - return; + return 0; } } else { + if (ldev->mode_changes_in_progress) + return -EAGAIN; mlx5_ldev_get(ldev); } mlx5_ldev_add_mdev(ldev, dev); - return; + return 0; } void mlx5_lag_remove_mdev(struct mlx5_core_dev *dev) @@ -668,7 +784,13 @@ void mlx5_lag_remove_mdev(struct mlx5_core_dev *dev) if (!ldev) return; +recheck: mlx5_dev_list_lock(); + if (ldev->mode_changes_in_progress) { + mlx5_dev_list_unlock(); + msleep(100); + goto recheck; + } mlx5_ldev_remove_mdev(ldev, dev); mlx5_dev_list_unlock(); mlx5_ldev_put(ldev); @@ -676,8 +798,16 @@ void mlx5_lag_remove_mdev(struct mlx5_core_dev *dev) void mlx5_lag_add_mdev(struct mlx5_core_dev *dev) { + int err; + +recheck: mlx5_dev_list_lock(); - __mlx5_lag_dev_add_mdev(dev); + err = __mlx5_lag_dev_add_mdev(dev); + if (err) { + mlx5_dev_list_unlock(); + msleep(100); + goto recheck; + } mlx5_dev_list_unlock(); } @@ -691,11 +821,11 @@ void mlx5_lag_remove_netdev(struct mlx5_core_dev *dev, if (!ldev) return; - if (__mlx5_lag_is_active(ldev)) - mlx5_disable_lag(ldev); - mlx5_ldev_remove_netdev(ldev, netdev); ldev->flags &= ~MLX5_LAG_FLAG_READY; + + if (__mlx5_lag_is_active(ldev)) + mlx5_queue_bond_work(ldev, 0); } /* Must be called with intf_mutex held */ @@ -717,6 +847,7 @@ void mlx5_lag_add_netdev(struct mlx5_core_dev *dev, if (i >= MLX5_MAX_PORTS) ldev->flags |= MLX5_LAG_FLAG_READY; + mlx5_queue_bond_work(ldev, 0); } bool mlx5_lag_is_roce(struct mlx5_core_dev *dev) @@ -747,6 +878,21 @@ bool mlx5_lag_is_active(struct mlx5_core_dev *dev) } EXPORT_SYMBOL(mlx5_lag_is_active); +bool mlx5_lag_is_master(struct mlx5_core_dev *dev) +{ + struct mlx5_lag *ldev; + bool res; + + spin_lock(&lag_lock); + ldev = mlx5_lag_dev(dev); + res = ldev && __mlx5_lag_is_active(ldev) && + dev == ldev->pf[MLX5_LAG_P1].dev; + spin_unlock(&lag_lock); + + return res; +} +EXPORT_SYMBOL(mlx5_lag_is_master); + bool mlx5_lag_is_sriov(struct mlx5_core_dev *dev) { struct mlx5_lag *ldev; @@ -761,19 +907,50 @@ bool mlx5_lag_is_sriov(struct mlx5_core_dev *dev) } EXPORT_SYMBOL(mlx5_lag_is_sriov); -void mlx5_lag_update(struct mlx5_core_dev *dev) +bool mlx5_lag_is_shared_fdb(struct mlx5_core_dev *dev) +{ + struct mlx5_lag *ldev; + bool res; + + spin_lock(&lag_lock); + ldev = mlx5_lag_dev(dev); + res = ldev && __mlx5_lag_is_sriov(ldev) && ldev->shared_fdb; + spin_unlock(&lag_lock); + + return res; +} +EXPORT_SYMBOL(mlx5_lag_is_shared_fdb); + +void mlx5_lag_disable_change(struct mlx5_core_dev *dev) { + struct mlx5_core_dev *dev0; + struct mlx5_core_dev *dev1; struct mlx5_lag *ldev; mlx5_dev_list_lock(); + ldev = mlx5_lag_dev(dev); - if (!ldev) - goto unlock; + dev0 = ldev->pf[MLX5_LAG_P1].dev; + dev1 = ldev->pf[MLX5_LAG_P2].dev; - mlx5_do_bond(ldev); + ldev->mode_changes_in_progress++; + if (__mlx5_lag_is_active(ldev)) { + mlx5_lag_lock_eswitches(dev0, dev1); + mlx5_disable_lag(ldev); + mlx5_lag_unlock_eswitches(dev0, dev1); + } + mlx5_dev_list_unlock(); +} -unlock: +void mlx5_lag_enable_change(struct mlx5_core_dev *dev) +{ + struct mlx5_lag *ldev; + + mlx5_dev_list_lock(); + ldev = mlx5_lag_dev(dev); + ldev->mode_changes_in_progress--; mlx5_dev_list_unlock(); + mlx5_queue_bond_work(ldev, 0); } struct net_device *mlx5_lag_get_roce_netdev(struct mlx5_core_dev *dev) @@ -828,6 +1005,26 @@ unlock: } EXPORT_SYMBOL(mlx5_lag_get_slave_port); +struct mlx5_core_dev *mlx5_lag_get_peer_mdev(struct mlx5_core_dev *dev) +{ + struct mlx5_core_dev *peer_dev = NULL; + struct mlx5_lag *ldev; + + spin_lock(&lag_lock); + ldev = mlx5_lag_dev(dev); + if (!ldev) + goto unlock; + + peer_dev = ldev->pf[MLX5_LAG_P1].dev == dev ? + ldev->pf[MLX5_LAG_P2].dev : + ldev->pf[MLX5_LAG_P1].dev; + +unlock: + spin_unlock(&lag_lock); + return peer_dev; +} +EXPORT_SYMBOL(mlx5_lag_get_peer_mdev); + int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev, u64 *values, int num_counters, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.h b/drivers/net/ethernet/mellanox/mlx5/core/lag.h index 191392c37558..d4bae528954e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.h @@ -39,6 +39,8 @@ struct lag_tracker { */ struct mlx5_lag { u8 flags; + int mode_changes_in_progress; + bool shared_fdb; u8 v2p_map[MLX5_MAX_PORTS]; struct kref ref; struct lag_func pf[MLX5_MAX_PORTS]; @@ -71,7 +73,8 @@ void mlx5_modify_lag(struct mlx5_lag *ldev, struct lag_tracker *tracker); int mlx5_activate_lag(struct mlx5_lag *ldev, struct lag_tracker *tracker, - u8 flags); + u8 flags, + bool shared_fdb); int mlx5_lag_dev_get_netdev_idx(struct mlx5_lag *ldev, struct net_device *ndev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c index 516bfc2bd797..f239b352a58a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c @@ -161,7 +161,7 @@ static void mlx5_lag_fib_route_event(struct mlx5_lag *ldev, struct lag_tracker tracker; tracker = ldev->tracker; - mlx5_activate_lag(ldev, &tracker, MLX5_LAG_FLAG_MULTIPATH); + mlx5_activate_lag(ldev, &tracker, MLX5_LAG_FLAG_MULTIPATH, false); } mlx5_lag_set_port_affinity(ldev, MLX5_LAG_NORMAL_AFFINITY); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c index ce696d523493..ffac8a0e7a23 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c @@ -749,7 +749,7 @@ static int mlx5_pps_event(struct notifier_block *nb, } else { ptp_event.type = PTP_CLOCK_EXTTS; } - /* TODOL clock->ptp can be NULL if ptp_clock_register failes */ + /* TODOL clock->ptp can be NULL if ptp_clock_register fails */ ptp_clock_event(clock->ptp, &ptp_event); break; case PTP_PF_PEROUT: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c new file mode 100644 index 000000000000..749d17c0057d --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c @@ -0,0 +1,602 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +// Copyright (c) 2021 NVIDIA CORPORATION & AFFILIATES. + +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/tcp.h> +#include <linux/mlx5/fs.h> +#include <linux/mlx5/driver.h> +#include "mlx5_core.h" +#include "lib/fs_ttc.h" + +#define MLX5_TTC_NUM_GROUPS 3 +#define MLX5_TTC_GROUP1_SIZE (BIT(3) + MLX5_NUM_TUNNEL_TT) +#define MLX5_TTC_GROUP2_SIZE BIT(1) +#define MLX5_TTC_GROUP3_SIZE BIT(0) +#define MLX5_TTC_TABLE_SIZE (MLX5_TTC_GROUP1_SIZE +\ + MLX5_TTC_GROUP2_SIZE +\ + MLX5_TTC_GROUP3_SIZE) + +#define MLX5_INNER_TTC_NUM_GROUPS 3 +#define MLX5_INNER_TTC_GROUP1_SIZE BIT(3) +#define MLX5_INNER_TTC_GROUP2_SIZE BIT(1) +#define MLX5_INNER_TTC_GROUP3_SIZE BIT(0) +#define MLX5_INNER_TTC_TABLE_SIZE (MLX5_INNER_TTC_GROUP1_SIZE +\ + MLX5_INNER_TTC_GROUP2_SIZE +\ + MLX5_INNER_TTC_GROUP3_SIZE) + +/* L3/L4 traffic type classifier */ +struct mlx5_ttc_table { + int num_groups; + struct mlx5_flow_table *t; + struct mlx5_flow_group **g; + struct mlx5_ttc_rule rules[MLX5_NUM_TT]; + struct mlx5_flow_handle *tunnel_rules[MLX5_NUM_TUNNEL_TT]; +}; + +struct mlx5_flow_table *mlx5_get_ttc_flow_table(struct mlx5_ttc_table *ttc) +{ + return ttc->t; +} + +static void mlx5_cleanup_ttc_rules(struct mlx5_ttc_table *ttc) +{ + int i; + + for (i = 0; i < MLX5_NUM_TT; i++) { + if (!IS_ERR_OR_NULL(ttc->rules[i].rule)) { + mlx5_del_flow_rules(ttc->rules[i].rule); + ttc->rules[i].rule = NULL; + } + } + + for (i = 0; i < MLX5_NUM_TUNNEL_TT; i++) { + if (!IS_ERR_OR_NULL(ttc->tunnel_rules[i])) { + mlx5_del_flow_rules(ttc->tunnel_rules[i]); + ttc->tunnel_rules[i] = NULL; + } + } +} + +struct mlx5_etype_proto { + u16 etype; + u8 proto; +}; + +static struct mlx5_etype_proto ttc_rules[] = { + [MLX5_TT_IPV4_TCP] = { + .etype = ETH_P_IP, + .proto = IPPROTO_TCP, + }, + [MLX5_TT_IPV6_TCP] = { + .etype = ETH_P_IPV6, + .proto = IPPROTO_TCP, + }, + [MLX5_TT_IPV4_UDP] = { + .etype = ETH_P_IP, + .proto = IPPROTO_UDP, + }, + [MLX5_TT_IPV6_UDP] = { + .etype = ETH_P_IPV6, + .proto = IPPROTO_UDP, + }, + [MLX5_TT_IPV4_IPSEC_AH] = { + .etype = ETH_P_IP, + .proto = IPPROTO_AH, + }, + [MLX5_TT_IPV6_IPSEC_AH] = { + .etype = ETH_P_IPV6, + .proto = IPPROTO_AH, + }, + [MLX5_TT_IPV4_IPSEC_ESP] = { + .etype = ETH_P_IP, + .proto = IPPROTO_ESP, + }, + [MLX5_TT_IPV6_IPSEC_ESP] = { + .etype = ETH_P_IPV6, + .proto = IPPROTO_ESP, + }, + [MLX5_TT_IPV4] = { + .etype = ETH_P_IP, + .proto = 0, + }, + [MLX5_TT_IPV6] = { + .etype = ETH_P_IPV6, + .proto = 0, + }, + [MLX5_TT_ANY] = { + .etype = 0, + .proto = 0, + }, +}; + +static struct mlx5_etype_proto ttc_tunnel_rules[] = { + [MLX5_TT_IPV4_GRE] = { + .etype = ETH_P_IP, + .proto = IPPROTO_GRE, + }, + [MLX5_TT_IPV6_GRE] = { + .etype = ETH_P_IPV6, + .proto = IPPROTO_GRE, + }, + [MLX5_TT_IPV4_IPIP] = { + .etype = ETH_P_IP, + .proto = IPPROTO_IPIP, + }, + [MLX5_TT_IPV6_IPIP] = { + .etype = ETH_P_IPV6, + .proto = IPPROTO_IPIP, + }, + [MLX5_TT_IPV4_IPV6] = { + .etype = ETH_P_IP, + .proto = IPPROTO_IPV6, + }, + [MLX5_TT_IPV6_IPV6] = { + .etype = ETH_P_IPV6, + .proto = IPPROTO_IPV6, + }, + +}; + +u8 mlx5_get_proto_by_tunnel_type(enum mlx5_tunnel_types tt) +{ + return ttc_tunnel_rules[tt].proto; +} + +static bool mlx5_tunnel_proto_supported_rx(struct mlx5_core_dev *mdev, + u8 proto_type) +{ + switch (proto_type) { + case IPPROTO_GRE: + return MLX5_CAP_ETH(mdev, tunnel_stateless_gre); + case IPPROTO_IPIP: + case IPPROTO_IPV6: + return (MLX5_CAP_ETH(mdev, tunnel_stateless_ip_over_ip) || + MLX5_CAP_ETH(mdev, tunnel_stateless_ip_over_ip_rx)); + default: + return false; + } +} + +static bool mlx5_tunnel_any_rx_proto_supported(struct mlx5_core_dev *mdev) +{ + int tt; + + for (tt = 0; tt < MLX5_NUM_TUNNEL_TT; tt++) { + if (mlx5_tunnel_proto_supported_rx(mdev, + ttc_tunnel_rules[tt].proto)) + return true; + } + return false; +} + +bool mlx5_tunnel_inner_ft_supported(struct mlx5_core_dev *mdev) +{ + return (mlx5_tunnel_any_rx_proto_supported(mdev) && + MLX5_CAP_FLOWTABLE_NIC_RX(mdev, + ft_field_support.inner_ip_version)); +} + +static u8 mlx5_etype_to_ipv(u16 ethertype) +{ + if (ethertype == ETH_P_IP) + return 4; + + if (ethertype == ETH_P_IPV6) + return 6; + + return 0; +} + +static struct mlx5_flow_handle * +mlx5_generate_ttc_rule(struct mlx5_core_dev *dev, struct mlx5_flow_table *ft, + struct mlx5_flow_destination *dest, u16 etype, u8 proto) +{ + int match_ipv_outer = + MLX5_CAP_FLOWTABLE_NIC_RX(dev, + ft_field_support.outer_ip_version); + MLX5_DECLARE_FLOW_ACT(flow_act); + struct mlx5_flow_handle *rule; + struct mlx5_flow_spec *spec; + int err = 0; + u8 ipv; + + spec = kvzalloc(sizeof(*spec), GFP_KERNEL); + if (!spec) + return ERR_PTR(-ENOMEM); + + if (proto) { + spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.ip_protocol); + MLX5_SET(fte_match_param, spec->match_value, outer_headers.ip_protocol, proto); + } + + ipv = mlx5_etype_to_ipv(etype); + if (match_ipv_outer && ipv) { + spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.ip_version); + MLX5_SET(fte_match_param, spec->match_value, outer_headers.ip_version, ipv); + } else if (etype) { + spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.ethertype); + MLX5_SET(fte_match_param, spec->match_value, outer_headers.ethertype, etype); + } + + rule = mlx5_add_flow_rules(ft, spec, &flow_act, dest, 1); + if (IS_ERR(rule)) { + err = PTR_ERR(rule); + mlx5_core_err(dev, "%s: add rule failed\n", __func__); + } + + kvfree(spec); + return err ? ERR_PTR(err) : rule; +} + +static int mlx5_generate_ttc_table_rules(struct mlx5_core_dev *dev, + struct ttc_params *params, + struct mlx5_ttc_table *ttc) +{ + struct mlx5_flow_handle **trules; + struct mlx5_ttc_rule *rules; + struct mlx5_flow_table *ft; + int tt; + int err; + + ft = ttc->t; + rules = ttc->rules; + for (tt = 0; tt < MLX5_NUM_TT; tt++) { + struct mlx5_ttc_rule *rule = &rules[tt]; + + rule->rule = mlx5_generate_ttc_rule(dev, ft, ¶ms->dests[tt], + ttc_rules[tt].etype, + ttc_rules[tt].proto); + if (IS_ERR(rule->rule)) { + err = PTR_ERR(rule->rule); + rule->rule = NULL; + goto del_rules; + } + rule->default_dest = params->dests[tt]; + } + + if (!params->inner_ttc || !mlx5_tunnel_inner_ft_supported(dev)) + return 0; + + trules = ttc->tunnel_rules; + for (tt = 0; tt < MLX5_NUM_TUNNEL_TT; tt++) { + if (!mlx5_tunnel_proto_supported_rx(dev, + ttc_tunnel_rules[tt].proto)) + continue; + trules[tt] = mlx5_generate_ttc_rule(dev, ft, + ¶ms->tunnel_dests[tt], + ttc_tunnel_rules[tt].etype, + ttc_tunnel_rules[tt].proto); + if (IS_ERR(trules[tt])) { + err = PTR_ERR(trules[tt]); + trules[tt] = NULL; + goto del_rules; + } + } + + return 0; + +del_rules: + mlx5_cleanup_ttc_rules(ttc); + return err; +} + +static int mlx5_create_ttc_table_groups(struct mlx5_ttc_table *ttc, + bool use_ipv) +{ + int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + int ix = 0; + u32 *in; + int err; + u8 *mc; + + ttc->g = kcalloc(MLX5_TTC_NUM_GROUPS, sizeof(*ttc->g), GFP_KERNEL); + if (!ttc->g) + return -ENOMEM; + in = kvzalloc(inlen, GFP_KERNEL); + if (!in) { + kfree(ttc->g); + ttc->g = NULL; + return -ENOMEM; + } + + /* L4 Group */ + mc = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria); + MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.ip_protocol); + if (use_ipv) + MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.ip_version); + else + MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.ethertype); + MLX5_SET_CFG(in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS); + MLX5_SET_CFG(in, start_flow_index, ix); + ix += MLX5_TTC_GROUP1_SIZE; + MLX5_SET_CFG(in, end_flow_index, ix - 1); + ttc->g[ttc->num_groups] = mlx5_create_flow_group(ttc->t, in); + if (IS_ERR(ttc->g[ttc->num_groups])) + goto err; + ttc->num_groups++; + + /* L3 Group */ + MLX5_SET(fte_match_param, mc, outer_headers.ip_protocol, 0); + MLX5_SET_CFG(in, start_flow_index, ix); + ix += MLX5_TTC_GROUP2_SIZE; + MLX5_SET_CFG(in, end_flow_index, ix - 1); + ttc->g[ttc->num_groups] = mlx5_create_flow_group(ttc->t, in); + if (IS_ERR(ttc->g[ttc->num_groups])) + goto err; + ttc->num_groups++; + + /* Any Group */ + memset(in, 0, inlen); + MLX5_SET_CFG(in, start_flow_index, ix); + ix += MLX5_TTC_GROUP3_SIZE; + MLX5_SET_CFG(in, end_flow_index, ix - 1); + ttc->g[ttc->num_groups] = mlx5_create_flow_group(ttc->t, in); + if (IS_ERR(ttc->g[ttc->num_groups])) + goto err; + ttc->num_groups++; + + kvfree(in); + return 0; + +err: + err = PTR_ERR(ttc->g[ttc->num_groups]); + ttc->g[ttc->num_groups] = NULL; + kvfree(in); + + return err; +} + +static struct mlx5_flow_handle * +mlx5_generate_inner_ttc_rule(struct mlx5_core_dev *dev, + struct mlx5_flow_table *ft, + struct mlx5_flow_destination *dest, + u16 etype, u8 proto) +{ + MLX5_DECLARE_FLOW_ACT(flow_act); + struct mlx5_flow_handle *rule; + struct mlx5_flow_spec *spec; + int err = 0; + u8 ipv; + + spec = kvzalloc(sizeof(*spec), GFP_KERNEL); + if (!spec) + return ERR_PTR(-ENOMEM); + + ipv = mlx5_etype_to_ipv(etype); + if (etype && ipv) { + spec->match_criteria_enable = MLX5_MATCH_INNER_HEADERS; + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, inner_headers.ip_version); + MLX5_SET(fte_match_param, spec->match_value, inner_headers.ip_version, ipv); + } + + if (proto) { + spec->match_criteria_enable = MLX5_MATCH_INNER_HEADERS; + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, inner_headers.ip_protocol); + MLX5_SET(fte_match_param, spec->match_value, inner_headers.ip_protocol, proto); + } + + rule = mlx5_add_flow_rules(ft, spec, &flow_act, dest, 1); + if (IS_ERR(rule)) { + err = PTR_ERR(rule); + mlx5_core_err(dev, "%s: add inner TTC rule failed\n", __func__); + } + + kvfree(spec); + return err ? ERR_PTR(err) : rule; +} + +static int mlx5_generate_inner_ttc_table_rules(struct mlx5_core_dev *dev, + struct ttc_params *params, + struct mlx5_ttc_table *ttc) +{ + struct mlx5_ttc_rule *rules; + struct mlx5_flow_table *ft; + int err; + int tt; + + ft = ttc->t; + rules = ttc->rules; + + for (tt = 0; tt < MLX5_NUM_TT; tt++) { + struct mlx5_ttc_rule *rule = &rules[tt]; + + rule->rule = mlx5_generate_inner_ttc_rule(dev, ft, + ¶ms->dests[tt], + ttc_rules[tt].etype, + ttc_rules[tt].proto); + if (IS_ERR(rule->rule)) { + err = PTR_ERR(rule->rule); + rule->rule = NULL; + goto del_rules; + } + rule->default_dest = params->dests[tt]; + } + + return 0; + +del_rules: + + mlx5_cleanup_ttc_rules(ttc); + return err; +} + +static int mlx5_create_inner_ttc_table_groups(struct mlx5_ttc_table *ttc) +{ + int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + int ix = 0; + u32 *in; + int err; + u8 *mc; + + ttc->g = kcalloc(MLX5_INNER_TTC_NUM_GROUPS, sizeof(*ttc->g), + GFP_KERNEL); + if (!ttc->g) + return -ENOMEM; + in = kvzalloc(inlen, GFP_KERNEL); + if (!in) { + kfree(ttc->g); + ttc->g = NULL; + return -ENOMEM; + } + + /* L4 Group */ + mc = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria); + MLX5_SET_TO_ONES(fte_match_param, mc, inner_headers.ip_protocol); + MLX5_SET_TO_ONES(fte_match_param, mc, inner_headers.ip_version); + MLX5_SET_CFG(in, match_criteria_enable, MLX5_MATCH_INNER_HEADERS); + MLX5_SET_CFG(in, start_flow_index, ix); + ix += MLX5_INNER_TTC_GROUP1_SIZE; + MLX5_SET_CFG(in, end_flow_index, ix - 1); + ttc->g[ttc->num_groups] = mlx5_create_flow_group(ttc->t, in); + if (IS_ERR(ttc->g[ttc->num_groups])) + goto err; + ttc->num_groups++; + + /* L3 Group */ + MLX5_SET(fte_match_param, mc, inner_headers.ip_protocol, 0); + MLX5_SET_CFG(in, start_flow_index, ix); + ix += MLX5_INNER_TTC_GROUP2_SIZE; + MLX5_SET_CFG(in, end_flow_index, ix - 1); + ttc->g[ttc->num_groups] = mlx5_create_flow_group(ttc->t, in); + if (IS_ERR(ttc->g[ttc->num_groups])) + goto err; + ttc->num_groups++; + + /* Any Group */ + memset(in, 0, inlen); + MLX5_SET_CFG(in, start_flow_index, ix); + ix += MLX5_INNER_TTC_GROUP3_SIZE; + MLX5_SET_CFG(in, end_flow_index, ix - 1); + ttc->g[ttc->num_groups] = mlx5_create_flow_group(ttc->t, in); + if (IS_ERR(ttc->g[ttc->num_groups])) + goto err; + ttc->num_groups++; + + kvfree(in); + return 0; + +err: + err = PTR_ERR(ttc->g[ttc->num_groups]); + ttc->g[ttc->num_groups] = NULL; + kvfree(in); + + return err; +} + +struct mlx5_ttc_table *mlx5_create_inner_ttc_table(struct mlx5_core_dev *dev, + struct ttc_params *params) +{ + struct mlx5_ttc_table *ttc; + int err; + + ttc = kvzalloc(sizeof(*ttc), GFP_KERNEL); + if (!ttc) + return ERR_PTR(-ENOMEM); + + WARN_ON_ONCE(params->ft_attr.max_fte); + params->ft_attr.max_fte = MLX5_INNER_TTC_TABLE_SIZE; + ttc->t = mlx5_create_flow_table(params->ns, ¶ms->ft_attr); + if (IS_ERR(ttc->t)) { + err = PTR_ERR(ttc->t); + kvfree(ttc); + return ERR_PTR(err); + } + + err = mlx5_create_inner_ttc_table_groups(ttc); + if (err) + goto destroy_ft; + + err = mlx5_generate_inner_ttc_table_rules(dev, params, ttc); + if (err) + goto destroy_ft; + + return ttc; + +destroy_ft: + mlx5_destroy_ttc_table(ttc); + return ERR_PTR(err); +} + +void mlx5_destroy_ttc_table(struct mlx5_ttc_table *ttc) +{ + int i; + + mlx5_cleanup_ttc_rules(ttc); + for (i = ttc->num_groups - 1; i >= 0; i--) { + if (!IS_ERR_OR_NULL(ttc->g[i])) + mlx5_destroy_flow_group(ttc->g[i]); + ttc->g[i] = NULL; + } + + kfree(ttc->g); + mlx5_destroy_flow_table(ttc->t); + kvfree(ttc); +} + +struct mlx5_ttc_table *mlx5_create_ttc_table(struct mlx5_core_dev *dev, + struct ttc_params *params) +{ + bool match_ipv_outer = + MLX5_CAP_FLOWTABLE_NIC_RX(dev, + ft_field_support.outer_ip_version); + struct mlx5_ttc_table *ttc; + int err; + + ttc = kvzalloc(sizeof(*ttc), GFP_KERNEL); + if (!ttc) + return ERR_PTR(-ENOMEM); + + WARN_ON_ONCE(params->ft_attr.max_fte); + params->ft_attr.max_fte = MLX5_TTC_TABLE_SIZE; + ttc->t = mlx5_create_flow_table(params->ns, ¶ms->ft_attr); + if (IS_ERR(ttc->t)) { + err = PTR_ERR(ttc->t); + kvfree(ttc); + return ERR_PTR(err); + } + + err = mlx5_create_ttc_table_groups(ttc, match_ipv_outer); + if (err) + goto destroy_ft; + + err = mlx5_generate_ttc_table_rules(dev, params, ttc); + if (err) + goto destroy_ft; + + return ttc; + +destroy_ft: + mlx5_destroy_ttc_table(ttc); + return ERR_PTR(err); +} + +int mlx5_ttc_fwd_dest(struct mlx5_ttc_table *ttc, enum mlx5_traffic_types type, + struct mlx5_flow_destination *new_dest) +{ + return mlx5_modify_rule_destination(ttc->rules[type].rule, new_dest, + NULL); +} + +struct mlx5_flow_destination +mlx5_ttc_get_default_dest(struct mlx5_ttc_table *ttc, + enum mlx5_traffic_types type) +{ + struct mlx5_flow_destination *dest = &ttc->rules[type].default_dest; + + WARN_ONCE(dest->type != MLX5_FLOW_DESTINATION_TYPE_TIR, + "TTC[%d] default dest is not setup yet", type); + + return *dest; +} + +int mlx5_ttc_fwd_default_dest(struct mlx5_ttc_table *ttc, + enum mlx5_traffic_types type) +{ + struct mlx5_flow_destination dest = mlx5_ttc_get_default_dest(ttc, type); + + return mlx5_ttc_fwd_dest(ttc, type, &dest); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.h new file mode 100644 index 000000000000..ce95be8f8382 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.h @@ -0,0 +1,70 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2020 Mellanox Technologies. */ + +#ifndef __ML5_FS_TTC_H__ +#define __ML5_FS_TTC_H__ + +#include <linux/mlx5/fs.h> + +enum mlx5_traffic_types { + MLX5_TT_IPV4_TCP, + MLX5_TT_IPV6_TCP, + MLX5_TT_IPV4_UDP, + MLX5_TT_IPV6_UDP, + MLX5_TT_IPV4_IPSEC_AH, + MLX5_TT_IPV6_IPSEC_AH, + MLX5_TT_IPV4_IPSEC_ESP, + MLX5_TT_IPV6_IPSEC_ESP, + MLX5_TT_IPV4, + MLX5_TT_IPV6, + MLX5_TT_ANY, + MLX5_NUM_TT, + MLX5_NUM_INDIR_TIRS = MLX5_TT_ANY, +}; + +enum mlx5_tunnel_types { + MLX5_TT_IPV4_GRE, + MLX5_TT_IPV6_GRE, + MLX5_TT_IPV4_IPIP, + MLX5_TT_IPV6_IPIP, + MLX5_TT_IPV4_IPV6, + MLX5_TT_IPV6_IPV6, + MLX5_NUM_TUNNEL_TT, +}; + +struct mlx5_ttc_rule { + struct mlx5_flow_handle *rule; + struct mlx5_flow_destination default_dest; +}; + +struct mlx5_ttc_table; + +struct ttc_params { + struct mlx5_flow_namespace *ns; + struct mlx5_flow_table_attr ft_attr; + struct mlx5_flow_destination dests[MLX5_NUM_TT]; + bool inner_ttc; + struct mlx5_flow_destination tunnel_dests[MLX5_NUM_TUNNEL_TT]; +}; + +struct mlx5_flow_table *mlx5_get_ttc_flow_table(struct mlx5_ttc_table *ttc); + +struct mlx5_ttc_table *mlx5_create_ttc_table(struct mlx5_core_dev *dev, + struct ttc_params *params); +void mlx5_destroy_ttc_table(struct mlx5_ttc_table *ttc); + +struct mlx5_ttc_table *mlx5_create_inner_ttc_table(struct mlx5_core_dev *dev, + struct ttc_params *params); + +int mlx5_ttc_fwd_dest(struct mlx5_ttc_table *ttc, enum mlx5_traffic_types type, + struct mlx5_flow_destination *new_dest); +struct mlx5_flow_destination +mlx5_ttc_get_default_dest(struct mlx5_ttc_table *ttc, + enum mlx5_traffic_types type); +int mlx5_ttc_fwd_default_dest(struct mlx5_ttc_table *ttc, + enum mlx5_traffic_types type); + +bool mlx5_tunnel_inner_ft_supported(struct mlx5_core_dev *mdev); +u8 mlx5_get_proto_by_tunnel_type(enum mlx5_tunnel_types tt); + +#endif /* __MLX5_FS_TTC_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c index 38084400ee8f..e3b0a131c3e1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c @@ -40,7 +40,7 @@ struct mlx5_vxlan { struct mlx5_core_dev *mdev; - /* max_num_ports is usuallly 4, 16 buckets is more than enough */ + /* max_num_ports is usually 4, 16 buckets is more than enough */ DECLARE_HASHTABLE(htable, 4); struct mutex sync_lock; /* sync add/del port HW operations */ }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index c84ad87c99bb..79482824c64f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -252,28 +252,16 @@ static int set_dma_caps(struct pci_dev *pdev) { int err; - err = pci_set_dma_mask(pdev, DMA_BIT_MASK(64)); + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); if (err) { dev_warn(&pdev->dev, "Warning: couldn't set 64-bit PCI DMA mask\n"); - err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)); + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); if (err) { dev_err(&pdev->dev, "Can't set PCI DMA mask, aborting\n"); return err; } } - err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64)); - if (err) { - dev_warn(&pdev->dev, - "Warning: couldn't set 64-bit consistent PCI DMA mask\n"); - err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32)); - if (err) { - dev_err(&pdev->dev, - "Can't set consistent PCI DMA mask, aborting\n"); - return err; - } - } - dma_set_max_seg_size(&pdev->dev, 2u * 1024 * 1024 * 1024); return err; } @@ -389,11 +377,11 @@ static int mlx5_core_get_caps_mode(struct mlx5_core_dev *dev, switch (cap_mode) { case HCA_CAP_OPMOD_GET_MAX: - memcpy(dev->caps.hca_max[cap_type], hca_caps, + memcpy(dev->caps.hca[cap_type]->max, hca_caps, MLX5_UN_SZ_BYTES(hca_cap_union)); break; case HCA_CAP_OPMOD_GET_CUR: - memcpy(dev->caps.hca_cur[cap_type], hca_caps, + memcpy(dev->caps.hca[cap_type]->cur, hca_caps, MLX5_UN_SZ_BYTES(hca_cap_union)); break; default: @@ -469,7 +457,7 @@ static int handle_hca_cap_odp(struct mlx5_core_dev *dev, void *set_ctx) return err; set_hca_cap = MLX5_ADDR_OF(set_hca_cap_in, set_ctx, capability); - memcpy(set_hca_cap, dev->caps.hca_cur[MLX5_CAP_ODP], + memcpy(set_hca_cap, dev->caps.hca[MLX5_CAP_ODP]->cur, MLX5_ST_SZ_BYTES(odp_cap)); #define ODP_CAP_SET_MAX(dev, field) \ @@ -514,7 +502,7 @@ static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx) set_hca_cap = MLX5_ADDR_OF(set_hca_cap_in, set_ctx, capability); - memcpy(set_hca_cap, dev->caps.hca_cur[MLX5_CAP_GENERAL], + memcpy(set_hca_cap, dev->caps.hca[MLX5_CAP_GENERAL]->cur, MLX5_ST_SZ_BYTES(cmd_hca_cap)); mlx5_core_dbg(dev, "Current Pkey table size %d Setting new size %d\n", @@ -596,7 +584,7 @@ static int handle_hca_cap_roce(struct mlx5_core_dev *dev, void *set_ctx) return 0; set_hca_cap = MLX5_ADDR_OF(set_hca_cap_in, set_ctx, capability); - memcpy(set_hca_cap, dev->caps.hca_cur[MLX5_CAP_ROCE], + memcpy(set_hca_cap, dev->caps.hca[MLX5_CAP_ROCE]->cur, MLX5_ST_SZ_BYTES(roce_cap)); MLX5_SET(roce_cap, set_hca_cap, sw_r_roce_src_udp_port, 1); @@ -748,14 +736,12 @@ static int mlx5_core_set_issi(struct mlx5_core_dev *dev) static int mlx5_pci_init(struct mlx5_core_dev *dev, struct pci_dev *pdev, const struct pci_device_id *id) { - struct mlx5_priv *priv = &dev->priv; int err = 0; mutex_init(&dev->pci_status_mutex); pci_set_drvdata(dev->pdev, dev); dev->bar_addr = pci_resource_start(pdev, 0); - priv->numa_node = dev_to_node(mlx5_core_dma_dev(dev)); err = mlx5_pci_enable_device(dev); if (err) { @@ -1179,6 +1165,7 @@ static int mlx5_load(struct mlx5_core_dev *dev) goto err_ec; } + mlx5_lag_add_mdev(dev); err = mlx5_sriov_attach(dev); if (err) { mlx5_core_err(dev, "sriov init failed %d\n", err); @@ -1186,11 +1173,11 @@ static int mlx5_load(struct mlx5_core_dev *dev) } mlx5_sf_dev_table_create(dev); - mlx5_lag_add_mdev(dev); return 0; err_sriov: + mlx5_lag_remove_mdev(dev); mlx5_ec_cleanup(dev); err_ec: mlx5_sf_hw_table_destroy(dev); @@ -1222,9 +1209,9 @@ err_irq_table: static void mlx5_unload(struct mlx5_core_dev *dev) { - mlx5_lag_remove_mdev(dev); mlx5_sf_dev_table_destroy(dev); mlx5_sriov_detach(dev); + mlx5_lag_remove_mdev(dev); mlx5_ec_cleanup(dev); mlx5_sf_hw_table_destroy(dev); mlx5_vhca_event_stop(dev); @@ -1248,11 +1235,6 @@ int mlx5_init_one(struct mlx5_core_dev *dev) int err = 0; mutex_lock(&dev->intf_state_mutex); - if (test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state)) { - mlx5_core_warn(dev, "interface is up, NOP\n"); - goto out; - } - /* remove any previous indication of internal error */ dev->state = MLX5_DEVICE_STATE_UP; err = mlx5_function_setup(dev, true); @@ -1271,7 +1253,7 @@ int mlx5_init_one(struct mlx5_core_dev *dev) set_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state); - err = mlx5_devlink_register(priv_to_devlink(dev), dev->device); + err = mlx5_devlink_register(priv_to_devlink(dev)); if (err) goto err_devlink_reg; @@ -1293,7 +1275,6 @@ function_teardown: mlx5_function_teardown(dev, true); err_function: dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR; -out: mutex_unlock(&dev->intf_state_mutex); return err; } @@ -1380,6 +1361,60 @@ out: mutex_unlock(&dev->intf_state_mutex); } +static const int types[] = { + MLX5_CAP_GENERAL, + MLX5_CAP_GENERAL_2, + MLX5_CAP_ETHERNET_OFFLOADS, + MLX5_CAP_IPOIB_ENHANCED_OFFLOADS, + MLX5_CAP_ODP, + MLX5_CAP_ATOMIC, + MLX5_CAP_ROCE, + MLX5_CAP_IPOIB_OFFLOADS, + MLX5_CAP_FLOW_TABLE, + MLX5_CAP_ESWITCH_FLOW_TABLE, + MLX5_CAP_ESWITCH, + MLX5_CAP_VECTOR_CALC, + MLX5_CAP_QOS, + MLX5_CAP_DEBUG, + MLX5_CAP_DEV_MEM, + MLX5_CAP_DEV_EVENT, + MLX5_CAP_TLS, + MLX5_CAP_VDPA_EMULATION, + MLX5_CAP_IPSEC, +}; + +static void mlx5_hca_caps_free(struct mlx5_core_dev *dev) +{ + int type; + int i; + + for (i = 0; i < ARRAY_SIZE(types); i++) { + type = types[i]; + kfree(dev->caps.hca[type]); + } +} + +static int mlx5_hca_caps_alloc(struct mlx5_core_dev *dev) +{ + struct mlx5_hca_cap *cap; + int type; + int i; + + for (i = 0; i < ARRAY_SIZE(types); i++) { + cap = kzalloc(sizeof(*cap), GFP_KERNEL); + if (!cap) + goto err; + type = types[i]; + dev->caps.hca[type] = cap; + } + + return 0; + +err: + mlx5_hca_caps_free(dev); + return -ENOMEM; +} + int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx) { struct mlx5_priv *priv = &dev->priv; @@ -1399,6 +1434,7 @@ int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx) mutex_init(&priv->pgdir_mutex); INIT_LIST_HEAD(&priv->pgdir_list); + priv->numa_node = dev_to_node(mlx5_core_dma_dev(dev)); priv->dbg_root = debugfs_create_dir(dev_name(dev->device), mlx5_debugfs_root); INIT_LIST_HEAD(&priv->traps); @@ -1415,8 +1451,14 @@ int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx) if (err) goto err_adev_init; + err = mlx5_hca_caps_alloc(dev); + if (err) + goto err_hca_caps; + return 0; +err_hca_caps: + mlx5_adev_cleanup(dev); err_adev_init: mlx5_pagealloc_cleanup(dev); err_pagealloc_init: @@ -1435,6 +1477,7 @@ void mlx5_mdev_uninit(struct mlx5_core_dev *dev) { struct mlx5_priv *priv = &dev->priv; + mlx5_hca_caps_free(dev); mlx5_adev_cleanup(dev); mlx5_pagealloc_cleanup(dev); mlx5_health_cleanup(dev); @@ -1452,7 +1495,7 @@ static int probe_one(struct pci_dev *pdev, const struct pci_device_id *id) struct devlink *devlink; int err; - devlink = mlx5_devlink_alloc(); + devlink = mlx5_devlink_alloc(&pdev->dev); if (!devlink) { dev_err(&pdev->dev, "devlink alloc failed\n"); return -ENOMEM; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index da365b8f0141..230eab7e3bc9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -168,6 +168,8 @@ void mlx5_lag_add_netdev(struct mlx5_core_dev *dev, struct net_device *netdev); void mlx5_lag_remove_netdev(struct mlx5_core_dev *dev, struct net_device *netdev); void mlx5_lag_add_mdev(struct mlx5_core_dev *dev); void mlx5_lag_remove_mdev(struct mlx5_core_dev *dev); +void mlx5_lag_disable_change(struct mlx5_core_dev *dev); +void mlx5_lag_enable_change(struct mlx5_core_dev *dev); int mlx5_events_init(struct mlx5_core_dev *dev); void mlx5_events_cleanup(struct mlx5_core_dev *dev); @@ -275,4 +277,9 @@ static inline u32 mlx5_sriov_get_vf_total_msix(struct pci_dev *pdev) return MLX5_CAP_GEN_MAX(dev, num_total_dynamic_vf_msix); } + +bool mlx5_eth_supported(struct mlx5_core_dev *dev); +bool mlx5_rdma_supported(struct mlx5_core_dev *dev); +bool mlx5_vnet_supported(struct mlx5_core_dev *dev); + #endif /* __MLX5_CORE_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c index 3465b363fc2f..c79a10b3454d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c @@ -18,7 +18,7 @@ #define MLX5_SFS_PER_CTRL_IRQ 64 #define MLX5_IRQ_CTRL_SF_MAX 8 -/* min num of vectores for SFs to be enabled */ +/* min num of vectors for SFs to be enabled */ #define MLX5_IRQ_VEC_COMP_BASE_SF 2 #define MLX5_EQ_SHARE_IRQ_MAX_COMP (8) @@ -28,13 +28,13 @@ #define MLX5_EQ_REFS_PER_IRQ (2) struct mlx5_irq { - u32 index; struct atomic_notifier_head nh; cpumask_var_t mask; char name[MLX5_MAX_IRQ_NAME]; - struct kref kref; - int irqn; struct mlx5_irq_pool *pool; + int refcount; + u32 index; + int irqn; }; struct mlx5_irq_pool { @@ -138,9 +138,8 @@ out: return ret; } -static void irq_release(struct kref *kref) +static void irq_release(struct mlx5_irq *irq) { - struct mlx5_irq *irq = container_of(kref, struct mlx5_irq, kref); struct mlx5_irq_pool *pool = irq->pool; xa_erase(&pool->irqs, irq->index); @@ -159,10 +158,31 @@ static void irq_put(struct mlx5_irq *irq) struct mlx5_irq_pool *pool = irq->pool; mutex_lock(&pool->lock); - kref_put(&irq->kref, irq_release); + irq->refcount--; + if (!irq->refcount) + irq_release(irq); mutex_unlock(&pool->lock); } +static int irq_get_locked(struct mlx5_irq *irq) +{ + lockdep_assert_held(&irq->pool->lock); + if (WARN_ON_ONCE(!irq->refcount)) + return 0; + irq->refcount++; + return 1; +} + +static int irq_get(struct mlx5_irq *irq) +{ + int err; + + mutex_lock(&irq->pool->lock); + err = irq_get_locked(irq); + mutex_unlock(&irq->pool->lock); + return err; +} + static irqreturn_t irq_int_handler(int irq, void *nh) { atomic_notifier_call_chain(nh, 0, NULL); @@ -215,7 +235,7 @@ static struct mlx5_irq *irq_request(struct mlx5_irq_pool *pool, int i) goto err_cpumask; } irq->pool = pool; - kref_init(&irq->kref); + irq->refcount = 1; irq->index = i; err = xa_err(xa_store(&pool->irqs, irq->index, irq, GFP_KERNEL)); if (err) { @@ -235,18 +255,18 @@ err_req_irq: int mlx5_irq_attach_nb(struct mlx5_irq *irq, struct notifier_block *nb) { - int err; + int ret; - err = kref_get_unless_zero(&irq->kref); - if (WARN_ON_ONCE(!err)) + ret = irq_get(irq); + if (!ret) /* Something very bad happens here, we are enabling EQ * on non-existing IRQ. */ return -ENOENT; - err = atomic_notifier_chain_register(&irq->nh, nb); - if (err) + ret = atomic_notifier_chain_register(&irq->nh, nb); + if (ret) irq_put(irq); - return err; + return ret; } int mlx5_irq_detach_nb(struct mlx5_irq *irq, struct notifier_block *nb) @@ -304,10 +324,9 @@ static struct mlx5_irq *irq_pool_find_least_loaded(struct mlx5_irq_pool *pool, xa_for_each_range(&pool->irqs, index, iter, start, end) { if (!cpumask_equal(iter->mask, affinity)) continue; - if (kref_read(&iter->kref) < pool->min_threshold) + if (iter->refcount < pool->min_threshold) return iter; - if (!irq || kref_read(&iter->kref) < - kref_read(&irq->kref)) + if (!irq || iter->refcount < irq->refcount) irq = iter; } return irq; @@ -322,7 +341,7 @@ static struct mlx5_irq *irq_pool_request_affinity(struct mlx5_irq_pool *pool, mutex_lock(&pool->lock); least_loaded_irq = irq_pool_find_least_loaded(pool, affinity); if (least_loaded_irq && - kref_read(&least_loaded_irq->kref) < pool->min_threshold) + least_loaded_irq->refcount < pool->min_threshold) goto out; new_irq = irq_pool_create_irq(pool, affinity); if (IS_ERR(new_irq)) { @@ -340,11 +359,11 @@ static struct mlx5_irq *irq_pool_request_affinity(struct mlx5_irq_pool *pool, least_loaded_irq = new_irq; goto unlock; out: - kref_get(&least_loaded_irq->kref); - if (kref_read(&least_loaded_irq->kref) > pool->max_threshold) + irq_get_locked(least_loaded_irq); + if (least_loaded_irq->refcount > pool->max_threshold) mlx5_core_dbg(pool->dev, "IRQ %u overloaded, pool_name: %s, %u EQs on this irq\n", least_loaded_irq->irqn, pool->name, - kref_read(&least_loaded_irq->kref) / MLX5_EQ_REFS_PER_IRQ); + least_loaded_irq->refcount / MLX5_EQ_REFS_PER_IRQ); unlock: mutex_unlock(&pool->lock); return least_loaded_irq; @@ -360,7 +379,7 @@ irq_pool_request_vector(struct mlx5_irq_pool *pool, int vecidx, mutex_lock(&pool->lock); irq = xa_load(&pool->irqs, vecidx); if (irq) { - kref_get(&irq->kref); + irq_get_locked(irq); goto unlock; } irq = irq_request(pool, vecidx); @@ -427,7 +446,7 @@ out: return irq; mlx5_core_dbg(dev, "irq %u mapped to cpu %*pbl, %u EQs on this irq\n", irq->irqn, cpumask_pr_args(affinity), - kref_read(&irq->kref) / MLX5_EQ_REFS_PER_IRQ); + irq->refcount / MLX5_EQ_REFS_PER_IRQ); return irq; } @@ -459,8 +478,12 @@ static void irq_pool_free(struct mlx5_irq_pool *pool) struct mlx5_irq *irq; unsigned long index; + /* There are cases in which we are destrying the irq_table before + * freeing all the IRQs, fast teardown for example. Hence, free the irqs + * which might not have been freed. + */ xa_for_each(&pool->irqs, index, irq) - irq_release(&irq->kref); + irq_release(irq); xa_destroy(&pool->irqs); mutex_destroy(&pool->lock); kvfree(pool); @@ -483,7 +506,7 @@ static int irq_pools_init(struct mlx5_core_dev *dev, int sf_vec, int pf_vec) if (!mlx5_sf_max_functions(dev)) return 0; if (sf_vec < MLX5_IRQ_VEC_COMP_BASE_SF) { - mlx5_core_err(dev, "Not enough IRQs for SFs. SF may run at lower performance\n"); + mlx5_core_dbg(dev, "Not enught IRQs for SFs. SF may run at lower performance\n"); return 0; } @@ -601,7 +624,7 @@ void mlx5_irq_table_destroy(struct mlx5_core_dev *dev) return; /* There are cases where IRQs still will be in used when we reaching - * to here. Hence, making sure all the irqs are realeased. + * to here. Hence, making sure all the irqs are released. */ irq_pools_destroy(table); pci_free_irq_vectors(dev->pdev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c index fa0288afc0dd..871c2fbe18d3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c @@ -39,7 +39,7 @@ static ssize_t sfnum_show(struct device *dev, struct device_attribute *attr, cha struct auxiliary_device *adev = container_of(dev, struct auxiliary_device, dev); struct mlx5_sf_dev *sf_dev = container_of(adev, struct mlx5_sf_dev, adev); - return scnprintf(buf, PAGE_SIZE, "%u\n", sf_dev->sfnum); + return sysfs_emit(buf, "%u\n", sf_dev->sfnum); } static DEVICE_ATTR_RO(sfnum); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c index 42c8ee03fe3e..052f48068dc1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c @@ -14,7 +14,7 @@ static int mlx5_sf_dev_probe(struct auxiliary_device *adev, const struct auxilia struct devlink *devlink; int err; - devlink = mlx5_devlink_alloc(); + devlink = mlx5_devlink_alloc(&adev->dev); if (!devlink) return -ENOMEM; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c index 1be048769309..13891fdc607e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c @@ -164,12 +164,12 @@ static bool mlx5_sf_is_active(const struct mlx5_sf *sf) return sf->hw_state == MLX5_VHCA_STATE_ACTIVE || sf->hw_state == MLX5_VHCA_STATE_IN_USE; } -int mlx5_devlink_sf_port_fn_state_get(struct devlink *devlink, struct devlink_port *dl_port, +int mlx5_devlink_sf_port_fn_state_get(struct devlink_port *dl_port, enum devlink_port_fn_state *state, enum devlink_port_fn_opstate *opstate, struct netlink_ext_ack *extack) { - struct mlx5_core_dev *dev = devlink_priv(devlink); + struct mlx5_core_dev *dev = devlink_priv(dl_port->devlink); struct mlx5_sf_table *table; struct mlx5_sf *sf; int err = 0; @@ -248,11 +248,11 @@ out: return err; } -int mlx5_devlink_sf_port_fn_state_set(struct devlink *devlink, struct devlink_port *dl_port, +int mlx5_devlink_sf_port_fn_state_set(struct devlink_port *dl_port, enum devlink_port_fn_state state, struct netlink_ext_ack *extack) { - struct mlx5_core_dev *dev = devlink_priv(devlink); + struct mlx5_core_dev *dev = devlink_priv(dl_port->devlink); struct mlx5_sf_table *table; struct mlx5_sf *sf; int err; @@ -476,7 +476,7 @@ static void mlx5_sf_table_disable(struct mlx5_sf_table *table) return; /* Balances with refcount_set; drop the reference so that new user cmd cannot start - * and new vhca event handler cannnot run. + * and new vhca event handler cannot run. */ mlx5_sf_table_put(table); wait_for_completion(&table->disable_complete); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h index 81ce13b19ee8..3a480e06ecc0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h @@ -24,11 +24,11 @@ int mlx5_devlink_sf_port_new(struct devlink *devlink, unsigned int *new_port_index); int mlx5_devlink_sf_port_del(struct devlink *devlink, unsigned int port_index, struct netlink_ext_ack *extack); -int mlx5_devlink_sf_port_fn_state_get(struct devlink *devlink, struct devlink_port *dl_port, +int mlx5_devlink_sf_port_fn_state_get(struct devlink_port *dl_port, enum devlink_port_fn_state *state, enum devlink_port_fn_opstate *opstate, struct netlink_ext_ack *extack); -int mlx5_devlink_sf_port_fn_state_set(struct devlink *devlink, struct devlink_port *dl_port, +int mlx5_devlink_sf_port_fn_state_set(struct devlink_port *dl_port, enum devlink_port_fn_state state, struct netlink_ext_ack *extack); #else diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c index 6475ba35cf6b..a5b9f65db23c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c @@ -18,12 +18,39 @@ enum dr_action_valid_state { DR_ACTION_STATE_ENCAP, DR_ACTION_STATE_DECAP, DR_ACTION_STATE_MODIFY_HDR, - DR_ACTION_STATE_MODIFY_VLAN, + DR_ACTION_STATE_POP_VLAN, + DR_ACTION_STATE_PUSH_VLAN, DR_ACTION_STATE_NON_TERM, DR_ACTION_STATE_TERM, DR_ACTION_STATE_MAX, }; +static const char * const action_type_to_str[] = { + [DR_ACTION_TYP_TNL_L2_TO_L2] = "DR_ACTION_TYP_TNL_L2_TO_L2", + [DR_ACTION_TYP_L2_TO_TNL_L2] = "DR_ACTION_TYP_L2_TO_TNL_L2", + [DR_ACTION_TYP_TNL_L3_TO_L2] = "DR_ACTION_TYP_TNL_L3_TO_L2", + [DR_ACTION_TYP_L2_TO_TNL_L3] = "DR_ACTION_TYP_L2_TO_TNL_L3", + [DR_ACTION_TYP_DROP] = "DR_ACTION_TYP_DROP", + [DR_ACTION_TYP_QP] = "DR_ACTION_TYP_QP", + [DR_ACTION_TYP_FT] = "DR_ACTION_TYP_FT", + [DR_ACTION_TYP_CTR] = "DR_ACTION_TYP_CTR", + [DR_ACTION_TYP_TAG] = "DR_ACTION_TYP_TAG", + [DR_ACTION_TYP_MODIFY_HDR] = "DR_ACTION_TYP_MODIFY_HDR", + [DR_ACTION_TYP_VPORT] = "DR_ACTION_TYP_VPORT", + [DR_ACTION_TYP_POP_VLAN] = "DR_ACTION_TYP_POP_VLAN", + [DR_ACTION_TYP_PUSH_VLAN] = "DR_ACTION_TYP_PUSH_VLAN", + [DR_ACTION_TYP_INSERT_HDR] = "DR_ACTION_TYP_INSERT_HDR", + [DR_ACTION_TYP_REMOVE_HDR] = "DR_ACTION_TYP_REMOVE_HDR", + [DR_ACTION_TYP_MAX] = "DR_ACTION_UNKNOWN", +}; + +static const char *dr_action_id_to_str(enum mlx5dr_action_type action_id) +{ + if (action_id > DR_ACTION_TYP_MAX) + action_id = DR_ACTION_TYP_MAX; + return action_type_to_str[action_id]; +} + static const enum dr_action_valid_state next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] = { [DR_ACTION_DOMAIN_NIC_INGRESS] = { @@ -39,8 +66,10 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_INSERT_HDR] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_REMOVE_HDR] = DR_ACTION_STATE_DECAP, [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, - [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, + [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_POP_VLAN, + [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_PUSH_VLAN, }, [DR_ACTION_STATE_DECAP] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, @@ -53,7 +82,8 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_INSERT_HDR] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, - [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, + [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_POP_VLAN, + [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_PUSH_VLAN, }, [DR_ACTION_STATE_ENCAP] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, @@ -73,20 +103,31 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_INSERT_HDR] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_PUSH_VLAN, }, - [DR_ACTION_STATE_MODIFY_VLAN] = { + [DR_ACTION_STATE_POP_VLAN] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_QP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, - [DR_ACTION_TYP_TAG] = DR_ACTION_STATE_MODIFY_VLAN, - [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_MODIFY_VLAN, - [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, + [DR_ACTION_TYP_TAG] = DR_ACTION_STATE_POP_VLAN, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_POP_VLAN, + [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_POP_VLAN, [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_INSERT_HDR] = DR_ACTION_STATE_ENCAP, }, + [DR_ACTION_STATE_PUSH_VLAN] = { + [DR_ACTION_TYP_QP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_TAG] = DR_ACTION_STATE_PUSH_VLAN, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_PUSH_VLAN, + [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_PUSH_VLAN, + [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_ENCAP, + }, [DR_ACTION_STATE_NON_TERM] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_QP] = DR_ACTION_STATE_TERM, @@ -99,8 +140,10 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_INSERT_HDR] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_REMOVE_HDR] = DR_ACTION_STATE_DECAP, [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, - [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, + [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_POP_VLAN, + [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_PUSH_VLAN, }, [DR_ACTION_STATE_TERM] = { [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_TERM, @@ -115,8 +158,16 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_INSERT_HDR] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_REMOVE_HDR] = DR_ACTION_STATE_DECAP, [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, - [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, + [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_PUSH_VLAN, + [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_POP_VLAN, + }, + [DR_ACTION_STATE_DECAP] = { + [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_DECAP, }, [DR_ACTION_STATE_ENCAP] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, @@ -132,14 +183,25 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_INSERT_HDR] = DR_ACTION_STATE_ENCAP, - [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, + [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_PUSH_VLAN, + }, + [DR_ACTION_STATE_POP_VLAN] = { + [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_POP_VLAN, + [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_POP_VLAN, + [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_PUSH_VLAN, + [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, + [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_INSERT_HDR] = DR_ACTION_STATE_ENCAP, }, - [DR_ACTION_STATE_MODIFY_VLAN] = { + [DR_ACTION_STATE_PUSH_VLAN] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, - [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_MODIFY_VLAN, - [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_PUSH_VLAN, + [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_PUSH_VLAN, [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_INSERT_HDR] = DR_ACTION_STATE_ENCAP, @@ -152,8 +214,10 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_INSERT_HDR] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_REMOVE_HDR] = DR_ACTION_STATE_DECAP, [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, - [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, + [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_PUSH_VLAN, + [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_POP_VLAN, }, [DR_ACTION_STATE_TERM] = { [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_TERM, @@ -170,8 +234,10 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_INSERT_HDR] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_REMOVE_HDR] = DR_ACTION_STATE_DECAP, [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, - [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, + [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_PUSH_VLAN, + [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_POP_VLAN, [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, }, [DR_ACTION_STATE_DECAP] = { @@ -180,11 +246,12 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_DECAP, [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, - [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_INSERT_HDR] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_POP_VLAN, + [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_PUSH_VLAN, }, [DR_ACTION_STATE_ENCAP] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, @@ -203,13 +270,26 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_INSERT_HDR] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_PUSH_VLAN, }, - [DR_ACTION_STATE_MODIFY_VLAN] = { + [DR_ACTION_STATE_POP_VLAN] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, - [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, - [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_MODIFY_VLAN, + [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_POP_VLAN, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_POP_VLAN, + [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, + [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_INSERT_HDR] = DR_ACTION_STATE_ENCAP, + }, + [DR_ACTION_STATE_PUSH_VLAN] = { + [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_PUSH_VLAN, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_PUSH_VLAN, [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, @@ -226,8 +306,10 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_INSERT_HDR] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_REMOVE_HDR] = DR_ACTION_STATE_DECAP, [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, - [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, + [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_POP_VLAN, + [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_PUSH_VLAN, [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, }, [DR_ACTION_STATE_TERM] = { @@ -244,8 +326,17 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_INSERT_HDR] = DR_ACTION_STATE_ENCAP, - [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, + [DR_ACTION_TYP_REMOVE_HDR] = DR_ACTION_STATE_DECAP, + [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_PUSH_VLAN, + [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_POP_VLAN, + [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, + }, + [DR_ACTION_STATE_DECAP] = { + [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_DECAP, [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, }, [DR_ACTION_STATE_ENCAP] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, @@ -262,15 +353,27 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_INSERT_HDR] = DR_ACTION_STATE_ENCAP, - [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, + [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_PUSH_VLAN, + [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, + }, + [DR_ACTION_STATE_POP_VLAN] = { + [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_POP_VLAN, + [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_POP_VLAN, + [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_PUSH_VLAN, + [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, + [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_INSERT_HDR] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, }, - [DR_ACTION_STATE_MODIFY_VLAN] = { + [DR_ACTION_STATE_PUSH_VLAN] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, - [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, - [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_MODIFY_VLAN, + [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_PUSH_VLAN, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_PUSH_VLAN, [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_INSERT_HDR] = DR_ACTION_STATE_ENCAP, @@ -285,7 +388,9 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_INSERT_HDR] = DR_ACTION_STATE_ENCAP, - [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, + [DR_ACTION_TYP_REMOVE_HDR] = DR_ACTION_STATE_DECAP, + [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_PUSH_VLAN, + [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_POP_VLAN, [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, }, [DR_ACTION_STATE_TERM] = { @@ -314,6 +419,9 @@ dr_action_reformat_to_action_type(enum mlx5dr_action_reformat_type reformat_type case DR_ACTION_REFORMAT_TYP_INSERT_HDR: *action_type = DR_ACTION_TYP_INSERT_HDR; break; + case DR_ACTION_REFORMAT_TYP_REMOVE_HDR: + *action_type = DR_ACTION_TYP_REMOVE_HDR; + break; default: return -EINVAL; } @@ -326,7 +434,7 @@ dr_action_reformat_to_action_type(enum mlx5dr_action_reformat_type reformat_type * the new size of the STEs array, rule with actions. */ static void dr_actions_apply(struct mlx5dr_domain *dmn, - enum mlx5dr_ste_entry_type ste_type, + enum mlx5dr_domain_nic_type nic_type, u8 *action_type_set, u8 *last_ste, struct mlx5dr_ste_actions_attr *attr, @@ -335,7 +443,7 @@ static void dr_actions_apply(struct mlx5dr_domain *dmn, struct mlx5dr_ste_ctx *ste_ctx = dmn->ste_ctx; u32 added_stes = 0; - if (ste_type == MLX5DR_STE_TYPE_RX) + if (nic_type == DR_DOMAIN_NIC_TYPE_RX) mlx5dr_ste_set_actions_rx(ste_ctx, dmn, action_type_set, last_ste, attr, &added_stes); else @@ -347,7 +455,7 @@ static void dr_actions_apply(struct mlx5dr_domain *dmn, static enum dr_action_domain dr_action_get_action_domain(enum mlx5dr_domain_type domain, - enum mlx5dr_ste_entry_type ste_type) + enum mlx5dr_domain_nic_type nic_type) { switch (domain) { case MLX5DR_DOMAIN_TYPE_NIC_RX: @@ -355,7 +463,7 @@ dr_action_get_action_domain(enum mlx5dr_domain_type domain, case MLX5DR_DOMAIN_TYPE_NIC_TX: return DR_ACTION_DOMAIN_NIC_EGRESS; case MLX5DR_DOMAIN_TYPE_FDB: - if (ste_type == MLX5DR_STE_TYPE_RX) + if (nic_type == DR_DOMAIN_NIC_TYPE_RX) return DR_ACTION_DOMAIN_FDB_INGRESS; return DR_ACTION_DOMAIN_FDB_EGRESS; default: @@ -421,6 +529,18 @@ static int dr_action_handle_cs_recalc(struct mlx5dr_domain *dmn, return 0; } +static void dr_action_print_sequence(struct mlx5dr_domain *dmn, + struct mlx5dr_action *actions[], + int last_idx) +{ + int i; + + for (i = 0; i <= last_idx; i++) + mlx5dr_err(dmn, "< %s (%d) > ", + dr_action_id_to_str(actions[i]->action_type), + actions[i]->action_type); +} + #define WITH_VLAN_NUM_HW_ACTIONS 6 int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher, @@ -431,7 +551,7 @@ int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher, u32 *new_hw_ste_arr_sz) { struct mlx5dr_domain_rx_tx *nic_dmn = nic_matcher->nic_tbl->nic_dmn; - bool rx_rule = nic_dmn->ste_type == MLX5DR_STE_TYPE_RX; + bool rx_rule = nic_dmn->type == DR_DOMAIN_NIC_TYPE_RX; struct mlx5dr_domain *dmn = matcher->tbl->dmn; u8 action_type_set[DR_ACTION_TYP_MAX] = {}; struct mlx5dr_ste_actions_attr attr = {}; @@ -445,7 +565,7 @@ int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher, attr.gvmi = dmn->info.caps.gvmi; attr.hit_gvmi = dmn->info.caps.gvmi; attr.final_icm_addr = nic_dmn->default_icm_addr; - action_domain = dr_action_get_action_domain(dmn->type, nic_dmn->ste_type); + action_domain = dr_action_get_action_domain(dmn->type, nic_dmn->type); for (i = 0; i < num_actions; i++) { struct mlx5dr_action_dest_tbl *dest_tbl; @@ -467,11 +587,11 @@ int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher, if (dest_tbl->tbl->dmn != dmn) { mlx5dr_err(dmn, "Destination table belongs to a different domain\n"); - goto out_invalid_arg; + return -EINVAL; } if (dest_tbl->tbl->level <= matcher->tbl->level) { - mlx5_core_warn_once(dmn->mdev, - "Connecting table to a lower/same level destination table\n"); + mlx5_core_dbg_once(dmn->mdev, + "Connecting table to a lower/same level destination table\n"); mlx5dr_dbg(dmn, "Connecting table at level %d to a destination table at level %d\n", matcher->tbl->level, @@ -509,7 +629,7 @@ int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher, break; case DR_ACTION_TYP_QP: mlx5dr_info(dmn, "Domain doesn't support QP\n"); - goto out_invalid_arg; + return -EOPNOTSUPP; case DR_ACTION_TYP_CTR: attr.ctr_id = action->ctr->ctr_id + action->ctr->offeset; @@ -536,7 +656,7 @@ int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher, if (rx_rule && !(dmn->ste_ctx->actions_caps & DR_STE_CTX_ACTION_CAP_RX_ENCAP)) { mlx5dr_info(dmn, "Device doesn't support Encap on RX\n"); - goto out_invalid_arg; + return -EOPNOTSUPP; } attr.reformat.size = action->reformat->size; attr.reformat.id = action->reformat->id; @@ -549,48 +669,66 @@ int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher, attr.hit_gvmi = action->vport->caps->vhca_gvmi; dest_action = action; if (rx_rule) { - /* Loopback on WIRE vport is not supported */ - if (action->vport->caps->num == WIRE_PORT) - goto out_invalid_arg; - + if (action->vport->caps->num == WIRE_PORT) { + mlx5dr_dbg(dmn, "Device doesn't support Loopback on WIRE vport\n"); + return -EOPNOTSUPP; + } attr.final_icm_addr = action->vport->caps->icm_address_rx; } else { attr.final_icm_addr = action->vport->caps->icm_address_tx; } break; case DR_ACTION_TYP_POP_VLAN: + if (!rx_rule && !(dmn->ste_ctx->actions_caps & + DR_STE_CTX_ACTION_CAP_TX_POP)) { + mlx5dr_dbg(dmn, "Device doesn't support POP VLAN action on TX\n"); + return -EOPNOTSUPP; + } + max_actions_type = MLX5DR_MAX_VLANS; attr.vlans.count++; break; case DR_ACTION_TYP_PUSH_VLAN: + if (rx_rule && !(dmn->ste_ctx->actions_caps & + DR_STE_CTX_ACTION_CAP_RX_PUSH)) { + mlx5dr_dbg(dmn, "Device doesn't support PUSH VLAN action on RX\n"); + return -EOPNOTSUPP; + } + max_actions_type = MLX5DR_MAX_VLANS; - if (attr.vlans.count == MLX5DR_MAX_VLANS) + if (attr.vlans.count == MLX5DR_MAX_VLANS) { + mlx5dr_dbg(dmn, "Max VLAN push/pop count exceeded\n"); return -EINVAL; + } attr.vlans.headers[attr.vlans.count++] = action->push_vlan->vlan_hdr; break; case DR_ACTION_TYP_INSERT_HDR: + case DR_ACTION_TYP_REMOVE_HDR: attr.reformat.size = action->reformat->size; attr.reformat.id = action->reformat->id; attr.reformat.param_0 = action->reformat->param_0; attr.reformat.param_1 = action->reformat->param_1; break; default: - goto out_invalid_arg; + mlx5dr_err(dmn, "Unsupported action type %d\n", action_type); + return -EINVAL; } /* Check action duplication */ if (++action_type_set[action_type] > max_actions_type) { mlx5dr_err(dmn, "Action type %d supports only max %d time(s)\n", action_type, max_actions_type); - goto out_invalid_arg; + return -EINVAL; } /* Check action state machine is valid */ if (dr_action_validate_and_get_next_state(action_domain, action_type, &state)) { - mlx5dr_err(dmn, "Invalid action sequence provided\n"); + mlx5dr_err(dmn, "Invalid action (gvmi: %d, is_rx: %d) sequence provided:", + attr.gvmi, rx_rule); + dr_action_print_sequence(dmn, actions, i); return -EOPNOTSUPP; } } @@ -614,16 +752,13 @@ int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher, } dr_actions_apply(dmn, - nic_dmn->ste_type, + nic_dmn->type, action_type_set, last_ste, &attr, new_hw_ste_arr_sz); return 0; - -out_invalid_arg: - return -EINVAL; } static unsigned int action_size[DR_ACTION_TYP_MAX] = { @@ -638,6 +773,7 @@ static unsigned int action_size[DR_ACTION_TYP_MAX] = { [DR_ACTION_TYP_VPORT] = sizeof(struct mlx5dr_action_vport), [DR_ACTION_TYP_PUSH_VLAN] = sizeof(struct mlx5dr_action_push_vlan), [DR_ACTION_TYP_INSERT_HDR] = sizeof(struct mlx5dr_action_reformat), + [DR_ACTION_TYP_REMOVE_HDR] = sizeof(struct mlx5dr_action_reformat), [DR_ACTION_TYP_SAMPLER] = sizeof(struct mlx5dr_action_sampler), }; @@ -709,7 +845,8 @@ dec_ref: struct mlx5dr_action * mlx5dr_action_create_mult_dest_tbl(struct mlx5dr_domain *dmn, struct mlx5dr_action_dest *dests, - u32 num_of_dests) + u32 num_of_dests, + bool ignore_flow_level) { struct mlx5dr_cmd_flow_destination_hw_info *hw_dests; struct mlx5dr_action **ref_actions; @@ -776,7 +913,8 @@ mlx5dr_action_create_mult_dest_tbl(struct mlx5dr_domain *dmn, num_of_dests, reformat_req, &action->dest_tbl->fw_tbl.id, - &action->dest_tbl->fw_tbl.group_id); + &action->dest_tbl->fw_tbl.group_id, + ignore_flow_level); if (ret) goto free_action; @@ -884,11 +1022,23 @@ dr_action_verify_reformat_params(enum mlx5dr_action_type reformat_type, size_t data_sz, void *data) { - if ((!data && data_sz) || (data && !data_sz) || - ((reformat_param_0 || reformat_param_1) && - reformat_type != DR_ACTION_TYP_INSERT_HDR) || - reformat_type > DR_ACTION_TYP_INSERT_HDR) { - mlx5dr_dbg(dmn, "Invalid reformat parameter!\n"); + if (reformat_type == DR_ACTION_TYP_INSERT_HDR) { + if ((!data && data_sz) || (data && !data_sz) || + MLX5_CAP_GEN_2(dmn->mdev, max_reformat_insert_size) < data_sz || + MLX5_CAP_GEN_2(dmn->mdev, max_reformat_insert_offset) < reformat_param_1) { + mlx5dr_dbg(dmn, "Invalid reformat parameters for INSERT_HDR\n"); + goto out_err; + } + } else if (reformat_type == DR_ACTION_TYP_REMOVE_HDR) { + if (data || + MLX5_CAP_GEN_2(dmn->mdev, max_reformat_remove_size) < data_sz || + MLX5_CAP_GEN_2(dmn->mdev, max_reformat_remove_offset) < reformat_param_1) { + mlx5dr_dbg(dmn, "Invalid reformat parameters for REMOVE_HDR\n"); + goto out_err; + } + } else if (reformat_param_0 || reformat_param_1 || + reformat_type > DR_ACTION_TYP_REMOVE_HDR) { + mlx5dr_dbg(dmn, "Invalid reformat parameters\n"); goto out_err; } @@ -987,7 +1137,6 @@ dr_action_create_reformat_action(struct mlx5dr_domain *dmn, return 0; } case DR_ACTION_TYP_INSERT_HDR: - { ret = mlx5dr_cmd_create_reformat_ctx(dmn->mdev, MLX5_REFORMAT_TYPE_INSERT_HDR, reformat_param_0, @@ -1002,7 +1151,12 @@ dr_action_create_reformat_action(struct mlx5dr_domain *dmn, action->reformat->param_0 = reformat_param_0; action->reformat->param_1 = reformat_param_1; return 0; - } + case DR_ACTION_TYP_REMOVE_HDR: + action->reformat->id = 0; + action->reformat->size = data_sz; + action->reformat->param_0 = reformat_param_0; + action->reformat->param_1 = reformat_param_1; + return 0; default: mlx5dr_info(dmn, "Reformat type is not supported %d\n", action->action_type); return -EINVAL; @@ -1658,6 +1812,7 @@ int mlx5dr_action_destroy(struct mlx5dr_action *action) } break; case DR_ACTION_TYP_TNL_L2_TO_L2: + case DR_ACTION_TYP_REMOVE_HDR: refcount_dec(&action->reformat->dmn->refcount); break; case DR_ACTION_TYP_TNL_L3_TO_L2: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c index 54e1f5438bbe..56307283bf9b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c @@ -655,6 +655,7 @@ int mlx5dr_cmd_set_fte(struct mlx5_core_dev *dev, MLX5_SET(set_fte_in, in, table_type, ft->type); MLX5_SET(set_fte_in, in, table_id, ft->id); MLX5_SET(set_fte_in, in, flow_index, fte->index); + MLX5_SET(set_fte_in, in, ignore_flow_level, fte->ignore_flow_level); if (ft->vport) { MLX5_SET(set_fte_in, in, vport_number, ft->vport); MLX5_SET(set_fte_in, in, other_vport, 1); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c index 7091b1be84ef..0fe159809ba1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c @@ -245,7 +245,7 @@ static int dr_domain_caps_init(struct mlx5_core_dev *mdev, return -ENOTSUPP; dmn->info.supp_sw_steering = true; - dmn->info.rx.ste_type = MLX5DR_STE_TYPE_RX; + dmn->info.rx.type = DR_DOMAIN_NIC_TYPE_RX; dmn->info.rx.default_icm_addr = dmn->info.caps.nic_rx_drop_address; dmn->info.rx.drop_icm_addr = dmn->info.caps.nic_rx_drop_address; break; @@ -254,7 +254,7 @@ static int dr_domain_caps_init(struct mlx5_core_dev *mdev, return -ENOTSUPP; dmn->info.supp_sw_steering = true; - dmn->info.tx.ste_type = MLX5DR_STE_TYPE_TX; + dmn->info.tx.type = DR_DOMAIN_NIC_TYPE_TX; dmn->info.tx.default_icm_addr = dmn->info.caps.nic_tx_allow_address; dmn->info.tx.drop_icm_addr = dmn->info.caps.nic_tx_drop_address; break; @@ -265,8 +265,8 @@ static int dr_domain_caps_init(struct mlx5_core_dev *mdev, if (!DR_DOMAIN_SW_STEERING_SUPPORTED(dmn, fdb)) return -ENOTSUPP; - dmn->info.rx.ste_type = MLX5DR_STE_TYPE_RX; - dmn->info.tx.ste_type = MLX5DR_STE_TYPE_TX; + dmn->info.rx.type = DR_DOMAIN_NIC_TYPE_RX; + dmn->info.tx.type = DR_DOMAIN_NIC_TYPE_TX; vport_cap = mlx5dr_get_vport_cap(&dmn->info.caps, 0); if (!vport_cap) { mlx5dr_err(dmn, "Failed to get esw manager vport\n"); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c index 7ccfd40586ce..0d6f86eb248b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c @@ -103,7 +103,8 @@ int mlx5dr_fw_create_md_tbl(struct mlx5dr_domain *dmn, int num_dest, bool reformat_req, u32 *tbl_id, - u32 *group_id) + u32 *group_id, + bool ignore_flow_level) { struct mlx5dr_cmd_create_flow_table_attr ft_attr = {}; struct mlx5dr_cmd_fte_info fte_info = {}; @@ -137,6 +138,7 @@ int mlx5dr_fw_create_md_tbl(struct mlx5dr_domain *dmn, fte_info.dests_size = num_dest; fte_info.val = val; fte_info.dest_arr = dest; + fte_info.ignore_flow_level = ignore_flow_level; ret = mlx5dr_cmd_set_fte(dmn->mdev, 0, 0, &ft_info, *group_id, &fte_info); if (ret) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c index 6f6191d1d5a6..b5409cc021d3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c @@ -396,13 +396,14 @@ static int dr_matcher_set_ste_builders(struct mlx5dr_matcher *matcher, struct mlx5dr_domain *dmn = matcher->tbl->dmn; struct mlx5dr_ste_ctx *ste_ctx = dmn->ste_ctx; struct mlx5dr_match_param mask = {}; + bool allow_empty_match = false; struct mlx5dr_ste_build *sb; bool inner, rx; int idx = 0; int ret, i; sb = nic_matcher->ste_builder_arr[outer_ipv][inner_ipv]; - rx = nic_dmn->ste_type == MLX5DR_STE_TYPE_RX; + rx = nic_dmn->type == DR_DOMAIN_NIC_TYPE_RX; /* Create a temporary mask to track and clear used mask fields */ if (matcher->match_criteria & DR_MATCHER_CRITERIA_OUTER) @@ -428,6 +429,16 @@ static int dr_matcher_set_ste_builders(struct mlx5dr_matcher *matcher, if (ret) return ret; + /* Optimize RX pipe by reducing source port match, since + * the FDB RX part is connected only to the wire. + */ + if (dmn->type == MLX5DR_DOMAIN_TYPE_FDB && + rx && mask.misc.source_port) { + mask.misc.source_port = 0; + mask.misc.source_eswitch_owner_vhca_id = 0; + allow_empty_match = true; + } + /* Outer */ if (matcher->match_criteria & (DR_MATCHER_CRITERIA_OUTER | DR_MATCHER_CRITERIA_MISC | @@ -619,7 +630,8 @@ static int dr_matcher_set_ste_builders(struct mlx5dr_matcher *matcher, } /* Empty matcher, takes all */ - if (matcher->match_criteria == DR_MATCHER_CRITERIA_EMPTY) + if ((!idx && allow_empty_match) || + matcher->match_criteria == DR_MATCHER_CRITERIA_EMPTY) mlx5dr_ste_build_empty_always_hit(&sb[idx++], rx); if (idx == 0) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c index ffdfb5a94b14..aca80efc28fa 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c @@ -81,6 +81,7 @@ dr_rule_create_collision_entry(struct mlx5dr_matcher *matcher, } ste->ste_chain_location = orig_ste->ste_chain_location; + ste->htbl->pointing_ste = orig_ste->htbl->pointing_ste; /* In collision entry, all members share the same miss_list_head */ ste->htbl->miss_list = mlx5dr_ste_get_miss_list(orig_ste); @@ -185,6 +186,9 @@ dr_rule_rehash_handle_collision(struct mlx5dr_matcher *matcher, if (!new_ste) return NULL; + /* Update collision pointing STE */ + new_ste->htbl->pointing_ste = col_ste->htbl->pointing_ste; + /* In collision entry, all members share the same miss_list_head */ new_ste->htbl->miss_list = mlx5dr_ste_get_miss_list(col_ste); @@ -212,7 +216,7 @@ static void dr_rule_rehash_copy_ste_ctrl(struct mlx5dr_matcher *matcher, new_ste->next_htbl = cur_ste->next_htbl; new_ste->ste_chain_location = cur_ste->ste_chain_location; - if (!mlx5dr_ste_is_last_in_rule(nic_matcher, new_ste->ste_chain_location)) + if (new_ste->next_htbl) new_ste->next_htbl->pointing_ste = new_ste; /* We need to copy the refcount since this ste @@ -220,10 +224,8 @@ static void dr_rule_rehash_copy_ste_ctrl(struct mlx5dr_matcher *matcher, */ new_ste->refcount = cur_ste->refcount; - /* Link old STEs rule_mem list to the new ste */ - mlx5dr_rule_update_rule_member(cur_ste, new_ste); - INIT_LIST_HEAD(&new_ste->rule_list); - list_splice_tail_init(&cur_ste->rule_list, &new_ste->rule_list); + /* Link old STEs rule to the new ste */ + mlx5dr_rule_set_last_member(cur_ste->rule_rx_tx, new_ste, false); } static struct mlx5dr_ste * @@ -404,7 +406,7 @@ dr_rule_rehash_htbl(struct mlx5dr_rule *rule, info.miss_icm_addr = nic_matcher->e_anchor->chunk->icm_addr; mlx5dr_ste_set_formatted_ste(dmn->ste_ctx, dmn->info.caps.gvmi, - nic_dmn, + nic_dmn->type, new_htbl, formatted_ste, &info); @@ -581,34 +583,66 @@ free_action_members: return -ENOMEM; } -/* While the pointer of ste is no longer valid, like while moving ste to be - * the first in the miss_list, and to be in the origin table, - * all rule-members that are attached to this ste should update their ste member - * to the new pointer - */ -void mlx5dr_rule_update_rule_member(struct mlx5dr_ste *ste, - struct mlx5dr_ste *new_ste) +void mlx5dr_rule_set_last_member(struct mlx5dr_rule_rx_tx *nic_rule, + struct mlx5dr_ste *ste, + bool force) +{ + /* Update rule member is usually done for the last STE or during rule + * creation to recover from mid-creation failure (for this peruse the + * force flag is used) + */ + if (ste->next_htbl && !force) + return; + + /* Update is required since each rule keeps track of its last STE */ + ste->rule_rx_tx = nic_rule; + nic_rule->last_rule_ste = ste; +} + +static struct mlx5dr_ste *dr_rule_get_pointed_ste(struct mlx5dr_ste *curr_ste) +{ + struct mlx5dr_ste *first_ste; + + first_ste = list_first_entry(mlx5dr_ste_get_miss_list(curr_ste), + struct mlx5dr_ste, miss_list_node); + + return first_ste->htbl->pointing_ste; +} + +int mlx5dr_rule_get_reverse_rule_members(struct mlx5dr_ste **ste_arr, + struct mlx5dr_ste *curr_ste, + int *num_of_stes) { - struct mlx5dr_rule_member *rule_mem; + bool first = false; + + *num_of_stes = 0; + + if (!curr_ste) + return -ENOENT; + + /* Iterate from last to first */ + while (!first) { + first = curr_ste->ste_chain_location == 1; + ste_arr[*num_of_stes] = curr_ste; + *num_of_stes += 1; + curr_ste = dr_rule_get_pointed_ste(curr_ste); + } - list_for_each_entry(rule_mem, &ste->rule_list, use_ste_list) - rule_mem->ste = new_ste; + return 0; } static void dr_rule_clean_rule_members(struct mlx5dr_rule *rule, struct mlx5dr_rule_rx_tx *nic_rule) { - struct mlx5dr_rule_member *rule_mem; - struct mlx5dr_rule_member *tmp_mem; + struct mlx5dr_ste *ste_arr[DR_RULE_MAX_STES + DR_ACTION_MAX_STES]; + struct mlx5dr_ste *curr_ste = nic_rule->last_rule_ste; + int i; - if (list_empty(&nic_rule->rule_members_list)) + if (mlx5dr_rule_get_reverse_rule_members(ste_arr, curr_ste, &i)) return; - list_for_each_entry_safe(rule_mem, tmp_mem, &nic_rule->rule_members_list, list) { - list_del(&rule_mem->list); - list_del(&rule_mem->use_ste_list); - mlx5dr_ste_put(rule_mem->ste, rule->matcher, nic_rule->nic_matcher); - kvfree(rule_mem); - } + + while (i--) + mlx5dr_ste_put(ste_arr[i], rule->matcher, nic_rule->nic_matcher); } static u16 dr_get_bits_per_mask(u16 byte_mask) @@ -628,43 +662,25 @@ static bool dr_rule_need_enlarge_hash(struct mlx5dr_ste_htbl *htbl, struct mlx5dr_domain_rx_tx *nic_dmn) { struct mlx5dr_ste_htbl_ctrl *ctrl = &htbl->ctrl; + int threshold; if (dmn->info.max_log_sw_icm_sz <= htbl->chunk_size) return false; - if (!ctrl->may_grow) + if (!mlx5dr_ste_htbl_may_grow(htbl)) return false; if (dr_get_bits_per_mask(htbl->byte_mask) * BITS_PER_BYTE <= htbl->chunk_size) return false; - if (ctrl->num_of_collisions >= ctrl->increase_threshold && - (ctrl->num_of_valid_entries - ctrl->num_of_collisions) >= ctrl->increase_threshold) + threshold = mlx5dr_ste_htbl_increase_threshold(htbl); + if (ctrl->num_of_collisions >= threshold && + (ctrl->num_of_valid_entries - ctrl->num_of_collisions) >= threshold) return true; return false; } -static int dr_rule_add_member(struct mlx5dr_rule_rx_tx *nic_rule, - struct mlx5dr_ste *ste) -{ - struct mlx5dr_rule_member *rule_mem; - - rule_mem = kvzalloc(sizeof(*rule_mem), GFP_KERNEL); - if (!rule_mem) - return -ENOMEM; - - INIT_LIST_HEAD(&rule_mem->list); - INIT_LIST_HEAD(&rule_mem->use_ste_list); - - rule_mem->ste = ste; - list_add_tail(&rule_mem->list, &nic_rule->rule_members_list); - - list_add_tail(&rule_mem->use_ste_list, &ste->rule_list); - - return 0; -} - static int dr_rule_handle_action_stes(struct mlx5dr_rule *rule, struct mlx5dr_rule_rx_tx *nic_rule, struct list_head *send_ste_list, @@ -679,15 +695,13 @@ static int dr_rule_handle_action_stes(struct mlx5dr_rule *rule, struct mlx5dr_domain *dmn = matcher->tbl->dmn; u8 *curr_hw_ste, *prev_hw_ste; struct mlx5dr_ste *action_ste; - int i, k, ret; + int i, k; /* Two cases: * 1. num_of_builders is equal to new_hw_ste_arr_sz, the action in the ste * 2. num_of_builders is less then new_hw_ste_arr_sz, new ste was added * to support the action. */ - if (num_of_builders == new_hw_ste_arr_sz) - return 0; for (i = num_of_builders, k = 0; i < new_hw_ste_arr_sz; i++, k++) { curr_hw_ste = hw_ste_arr + i * DR_STE_SIZE; @@ -700,6 +714,10 @@ static int dr_rule_handle_action_stes(struct mlx5dr_rule *rule, mlx5dr_ste_get(action_ste); + action_ste->htbl->pointing_ste = last_ste; + last_ste->next_htbl = action_ste->htbl; + last_ste = action_ste; + /* While free ste we go over the miss list, so add this ste to the list */ list_add_tail(&action_ste->miss_list_node, mlx5dr_ste_get_miss_list(action_ste)); @@ -713,21 +731,19 @@ static int dr_rule_handle_action_stes(struct mlx5dr_rule *rule, mlx5dr_ste_set_hit_addr_by_next_htbl(dmn->ste_ctx, prev_hw_ste, action_ste->htbl); - ret = dr_rule_add_member(nic_rule, action_ste); - if (ret) { - mlx5dr_dbg(dmn, "Failed adding rule member\n"); - goto free_ste_info; - } + + mlx5dr_rule_set_last_member(nic_rule, action_ste, true); + mlx5dr_send_fill_and_append_ste_send_info(action_ste, DR_STE_SIZE, 0, curr_hw_ste, ste_info_arr[k], send_ste_list, false); } + last_ste->next_htbl = NULL; + return 0; -free_ste_info: - kfree(ste_info_arr[k]); err_exit: mlx5dr_ste_put(action_ste, matcher, nic_matcher); return -ENOMEM; @@ -1015,12 +1031,12 @@ static enum mlx5dr_ipv dr_rule_get_ipv(struct mlx5dr_match_spec *spec) } static bool dr_rule_skip(enum mlx5dr_domain_type domain, - enum mlx5dr_ste_entry_type ste_type, + enum mlx5dr_domain_nic_type nic_type, struct mlx5dr_match_param *mask, struct mlx5dr_match_param *value, u32 flow_source) { - bool rx = ste_type == MLX5DR_STE_TYPE_RX; + bool rx = nic_type == DR_DOMAIN_NIC_TYPE_RX; if (domain != MLX5DR_DOMAIN_TYPE_FDB) return false; @@ -1065,9 +1081,7 @@ dr_rule_create_rule_nic(struct mlx5dr_rule *rule, nic_matcher = nic_rule->nic_matcher; nic_dmn = nic_matcher->nic_tbl->nic_dmn; - INIT_LIST_HEAD(&nic_rule->rule_members_list); - - if (dr_rule_skip(dmn->type, nic_dmn->ste_type, &matcher->mask, param, + if (dr_rule_skip(dmn->type, nic_dmn->type, &matcher->mask, param, rule->flow_source)) return 0; @@ -1121,14 +1135,8 @@ dr_rule_create_rule_nic(struct mlx5dr_rule *rule, cur_htbl = ste->next_htbl; - /* Keep all STEs in the rule struct */ - ret = dr_rule_add_member(nic_rule, ste); - if (ret) { - mlx5dr_dbg(dmn, "Failed adding rule member index %d\n", i); - goto free_ste; - } - mlx5dr_ste_get(ste); + mlx5dr_rule_set_last_member(nic_rule, ste, true); } /* Connect actions */ @@ -1153,8 +1161,6 @@ dr_rule_create_rule_nic(struct mlx5dr_rule *rule, return 0; -free_ste: - mlx5dr_ste_put(ste, matcher, nic_matcher); free_rule: dr_rule_clean_rule_members(rule, nic_rule); /* Clean all ste_info's */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c index 9df0e73d1c35..bfb14b4b1906 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c @@ -325,10 +325,14 @@ static int dr_handle_pending_wc(struct mlx5dr_domain *dmn, do { ne = dr_poll_cq(send_ring->cq, 1); - if (ne < 0) + if (unlikely(ne < 0)) { + mlx5_core_warn_once(dmn->mdev, "SMFS QPN 0x%x is disabled/limited", + send_ring->qp->qpn); + send_ring->err_state = true; return ne; - else if (ne == 1) + } else if (ne == 1) { send_ring->pending_wqe -= send_ring->signal_th; + } } while (is_drain && send_ring->pending_wqe); return 0; @@ -361,6 +365,14 @@ static int dr_postsend_icm_data(struct mlx5dr_domain *dmn, u32 buff_offset; int ret; + if (unlikely(dmn->mdev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR || + send_ring->err_state)) { + mlx5_core_dbg_once(dmn->mdev, + "Skipping post send: QP err state: %d, device state: %d\n", + send_ring->err_state, dmn->mdev->state); + return 0; + } + spin_lock(&send_ring->lock); ret = dr_handle_pending_wc(dmn, send_ring); @@ -620,6 +632,7 @@ static int dr_cmd_modify_qp_rtr2rts(struct mlx5_core_dev *mdev, MLX5_SET(qpc, qpc, retry_count, attr->retry_cnt); MLX5_SET(qpc, qpc, rnr_retry, attr->rnr_retry); + MLX5_SET(qpc, qpc, primary_address_path.ack_timeout, 0x8); /* ~1ms */ MLX5_SET(rtr2rts_qp_in, in, opcode, MLX5_CMD_OP_RTR2RTS_QP); MLX5_SET(rtr2rts_qp_in, in, qpn, dr_qp->qpn); @@ -789,7 +802,7 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev, cqc = MLX5_ADDR_OF(create_cq_in, in, cq_context); MLX5_SET(cqc, cqc, log_cq_size, ilog2(ncqe)); - MLX5_SET(cqc, cqc, c_eqn, eqn); + MLX5_SET(cqc, cqc, c_eqn_or_apu_element, eqn); MLX5_SET(cqc, cqc, uar_page, uar->index); MLX5_SET(cqc, cqc, log_page_size, cq->wq_ctrl.buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c index 9b1529137cba..1cdfe4fccc7a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c @@ -172,9 +172,6 @@ static void dr_ste_replace(struct mlx5dr_ste *dst, struct mlx5dr_ste *src) dst->next_htbl->pointing_ste = dst; dst->refcount = src->refcount; - - INIT_LIST_HEAD(&dst->rule_list); - list_splice_tail_init(&src->rule_list, &dst->rule_list); } /* Free ste which is the head and the only one in miss_list */ @@ -233,12 +230,12 @@ dr_ste_replace_head_ste(struct mlx5dr_matcher_rx_tx *nic_matcher, /* Remove from the miss_list the next_ste before copy */ list_del_init(&next_ste->miss_list_node); - /* All rule-members that use next_ste should know about that */ - mlx5dr_rule_update_rule_member(next_ste, ste); - /* Move data from next into ste */ dr_ste_replace(ste, next_ste); + /* Update the rule on STE change */ + mlx5dr_rule_set_last_member(next_ste->rule_rx_tx, ste, false); + /* Copy all 64 hw_ste bytes */ memcpy(hw_ste, ste->hw_ste, DR_STE_SIZE_REDUCED); sb_idx = ste->ste_chain_location - 1; @@ -382,14 +379,15 @@ void mlx5dr_ste_prepare_for_postsend(struct mlx5dr_ste_ctx *ste_ctx, /* Init one ste as a pattern for ste data array */ void mlx5dr_ste_set_formatted_ste(struct mlx5dr_ste_ctx *ste_ctx, u16 gvmi, - struct mlx5dr_domain_rx_tx *nic_dmn, + enum mlx5dr_domain_nic_type nic_type, struct mlx5dr_ste_htbl *htbl, u8 *formatted_ste, struct mlx5dr_htbl_connect_info *connect_info) { + bool is_rx = nic_type == DR_DOMAIN_NIC_TYPE_RX; struct mlx5dr_ste ste = {}; - ste_ctx->ste_init(formatted_ste, htbl->lu_type, nic_dmn->ste_type, gvmi); + ste_ctx->ste_init(formatted_ste, htbl->lu_type, is_rx, gvmi); ste.hw_ste = formatted_ste; if (connect_info->type == CONNECT_HIT) @@ -408,7 +406,7 @@ int mlx5dr_ste_htbl_init_and_postsend(struct mlx5dr_domain *dmn, mlx5dr_ste_set_formatted_ste(dmn->ste_ctx, dmn->info.caps.gvmi, - nic_dmn, + nic_dmn->type, htbl, formatted_ste, connect_info); @@ -466,21 +464,6 @@ free_table: return -ENOENT; } -static void dr_ste_set_ctrl(struct mlx5dr_ste_htbl *htbl) -{ - struct mlx5dr_ste_htbl_ctrl *ctrl = &htbl->ctrl; - int num_of_entries; - - htbl->ctrl.may_grow = true; - - if (htbl->chunk_size == DR_CHUNK_SIZE_MAX - 1 || !htbl->byte_mask) - htbl->ctrl.may_grow = false; - - /* Threshold is 50%, one is added to table of size 1 */ - num_of_entries = mlx5dr_icm_pool_chunk_size_to_entries(htbl->chunk_size); - ctrl->increase_threshold = (num_of_entries + 1) / 2; -} - struct mlx5dr_ste_htbl *mlx5dr_ste_htbl_alloc(struct mlx5dr_icm_pool *pool, enum mlx5dr_icm_chunk_size chunk_size, u16 lu_type, u16 byte_mask) @@ -513,11 +496,9 @@ struct mlx5dr_ste_htbl *mlx5dr_ste_htbl_alloc(struct mlx5dr_icm_pool *pool, ste->refcount = 0; INIT_LIST_HEAD(&ste->miss_list_node); INIT_LIST_HEAD(&htbl->miss_list[i]); - INIT_LIST_HEAD(&ste->rule_list); } htbl->chunk_size = chunk_size; - dr_ste_set_ctrl(htbl); return htbl; out_free_htbl: @@ -649,6 +630,7 @@ int mlx5dr_ste_build_ste_arr(struct mlx5dr_matcher *matcher, u8 *ste_arr) { struct mlx5dr_domain_rx_tx *nic_dmn = nic_matcher->nic_tbl->nic_dmn; + bool is_rx = nic_dmn->type == DR_DOMAIN_NIC_TYPE_RX; struct mlx5dr_domain *dmn = matcher->tbl->dmn; struct mlx5dr_ste_ctx *ste_ctx = dmn->ste_ctx; struct mlx5dr_ste_build *sb; @@ -663,7 +645,7 @@ int mlx5dr_ste_build_ste_arr(struct mlx5dr_matcher *matcher, for (i = 0; i < nic_matcher->num_of_builders; i++) { ste_ctx->ste_init(ste_arr, sb->lu_type, - nic_dmn->ste_type, + is_rx, dmn->info.caps.gvmi); mlx5dr_ste_set_bit_mask(ste_arr, sb->bit_mask); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.h index 12a8bbbf944b..2d52d065dc8b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.h @@ -146,7 +146,7 @@ struct mlx5dr_ste_ctx { /* Getters and Setters */ void (*ste_init)(u8 *hw_ste_p, u16 lu_type, - u8 entry_type, u16 gvmi); + bool is_rx, u16 gvmi); void (*set_next_lu_type)(u8 *hw_ste_p, u16 lu_type); u16 (*get_next_lu_type)(u8 *hw_ste_p); void (*set_miss_addr)(u8 *hw_ste_p, u64 miss_addr); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c index e4dd4eed5aee..9c704bce3c12 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c @@ -8,6 +8,12 @@ #define SVLAN_ETHERTYPE 0x88a8 #define DR_STE_ENABLE_FLOW_TAG BIT(31) +enum dr_ste_v0_entry_type { + DR_STE_TYPE_TX = 1, + DR_STE_TYPE_RX = 2, + DR_STE_TYPE_MODIFY_PKT = 6, +}; + enum dr_ste_v0_action_tunl { DR_STE_TUNL_ACTION_NONE = 0, DR_STE_TUNL_ACTION_ENABLE = 1, @@ -292,8 +298,8 @@ static void dr_ste_v0_set_hit_addr(u8 *hw_ste_p, u64 icm_addr, u32 ht_size) MLX5_SET(ste_general, hw_ste_p, next_table_base_31_5_size, index); } -static void dr_ste_v0_init(u8 *hw_ste_p, u16 lu_type, - u8 entry_type, u16 gvmi) +static void dr_ste_v0_init_full(u8 *hw_ste_p, u16 lu_type, + enum dr_ste_v0_entry_type entry_type, u16 gvmi) { dr_ste_v0_set_entry_type(hw_ste_p, entry_type); dr_ste_v0_set_lu_type(hw_ste_p, lu_type); @@ -307,6 +313,15 @@ static void dr_ste_v0_init(u8 *hw_ste_p, u16 lu_type, MLX5_SET(ste_rx_steering_mult, hw_ste_p, miss_address_63_48, gvmi); } +static void dr_ste_v0_init(u8 *hw_ste_p, u16 lu_type, + bool is_rx, u16 gvmi) +{ + enum dr_ste_v0_entry_type entry_type; + + entry_type = is_rx ? DR_STE_TYPE_RX : DR_STE_TYPE_TX; + dr_ste_v0_init_full(hw_ste_p, lu_type, entry_type, gvmi); +} + static void dr_ste_v0_rx_set_flow_tag(u8 *hw_ste_p, u32 flow_tag) { MLX5_SET(ste_rx_steering_mult, hw_ste_p, qp_list_pointer, @@ -380,13 +395,13 @@ static void dr_ste_v0_set_rewrite_actions(u8 *hw_ste_p, u16 num_of_actions, static void dr_ste_v0_arr_init_next(u8 **last_ste, u32 *added_stes, - enum mlx5dr_ste_entry_type entry_type, + enum dr_ste_v0_entry_type entry_type, u16 gvmi) { (*added_stes)++; *last_ste += DR_STE_SIZE; - dr_ste_v0_init(*last_ste, MLX5DR_STE_LU_TYPE_DONT_CARE, - entry_type, gvmi); + dr_ste_v0_init_full(*last_ste, MLX5DR_STE_LU_TYPE_DONT_CARE, + entry_type, gvmi); } static void @@ -404,7 +419,7 @@ dr_ste_v0_set_actions_tx(struct mlx5dr_domain *dmn, * modify headers for outer headers only */ if (action_type_set[DR_ACTION_TYP_MODIFY_HDR]) { - dr_ste_v0_set_entry_type(last_ste, MLX5DR_STE_TYPE_MODIFY_PKT); + dr_ste_v0_set_entry_type(last_ste, DR_STE_TYPE_MODIFY_PKT); dr_ste_v0_set_rewrite_actions(last_ste, attr->modify_actions, attr->modify_index); @@ -417,7 +432,7 @@ dr_ste_v0_set_actions_tx(struct mlx5dr_domain *dmn, if (i || action_type_set[DR_ACTION_TYP_MODIFY_HDR]) dr_ste_v0_arr_init_next(&last_ste, added_stes, - MLX5DR_STE_TYPE_TX, + DR_STE_TYPE_TX, attr->gvmi); dr_ste_v0_set_tx_push_vlan(last_ste, @@ -435,7 +450,7 @@ dr_ste_v0_set_actions_tx(struct mlx5dr_domain *dmn, action_type_set[DR_ACTION_TYP_PUSH_VLAN]) dr_ste_v0_arr_init_next(&last_ste, added_stes, - MLX5DR_STE_TYPE_TX, + DR_STE_TYPE_TX, attr->gvmi); dr_ste_v0_set_tx_encap(last_ste, @@ -469,7 +484,7 @@ dr_ste_v0_set_actions_rx(struct mlx5dr_domain *dmn, dr_ste_v0_set_counter_id(last_ste, attr->ctr_id); if (action_type_set[DR_ACTION_TYP_TNL_L3_TO_L2]) { - dr_ste_v0_set_entry_type(last_ste, MLX5DR_STE_TYPE_MODIFY_PKT); + dr_ste_v0_set_entry_type(last_ste, DR_STE_TYPE_MODIFY_PKT); dr_ste_v0_set_rx_decap_l3(last_ste, attr->decap_with_vlan); dr_ste_v0_set_rewrite_actions(last_ste, attr->decap_actions, @@ -488,7 +503,7 @@ dr_ste_v0_set_actions_rx(struct mlx5dr_domain *dmn, action_type_set[DR_ACTION_TYP_TNL_L3_TO_L2]) dr_ste_v0_arr_init_next(&last_ste, added_stes, - MLX5DR_STE_TYPE_RX, + DR_STE_TYPE_RX, attr->gvmi); dr_ste_v0_set_rx_pop_vlan(last_ste); @@ -496,13 +511,13 @@ dr_ste_v0_set_actions_rx(struct mlx5dr_domain *dmn, } if (action_type_set[DR_ACTION_TYP_MODIFY_HDR]) { - if (dr_ste_v0_get_entry_type(last_ste) == MLX5DR_STE_TYPE_MODIFY_PKT) + if (dr_ste_v0_get_entry_type(last_ste) == DR_STE_TYPE_MODIFY_PKT) dr_ste_v0_arr_init_next(&last_ste, added_stes, - MLX5DR_STE_TYPE_MODIFY_PKT, + DR_STE_TYPE_MODIFY_PKT, attr->gvmi); else - dr_ste_v0_set_entry_type(last_ste, MLX5DR_STE_TYPE_MODIFY_PKT); + dr_ste_v0_set_entry_type(last_ste, DR_STE_TYPE_MODIFY_PKT); dr_ste_v0_set_rewrite_actions(last_ste, attr->modify_actions, @@ -510,10 +525,10 @@ dr_ste_v0_set_actions_rx(struct mlx5dr_domain *dmn, } if (action_type_set[DR_ACTION_TYP_TAG]) { - if (dr_ste_v0_get_entry_type(last_ste) == MLX5DR_STE_TYPE_MODIFY_PKT) + if (dr_ste_v0_get_entry_type(last_ste) == DR_STE_TYPE_MODIFY_PKT) dr_ste_v0_arr_init_next(&last_ste, added_stes, - MLX5DR_STE_TYPE_RX, + DR_STE_TYPE_RX, attr->gvmi); dr_ste_v0_rx_set_flow_tag(last_ste, attr->flow_tag); @@ -1157,6 +1172,7 @@ dr_ste_v0_build_eth_ipv6_l3_l4_tag(struct mlx5dr_match_param *value, u8 *tag) { struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer; + struct mlx5dr_match_misc *misc = &value->misc; DR_STE_SET_TAG(eth_l4, tag, dst_port, spec, tcp_dport); DR_STE_SET_TAG(eth_l4, tag, src_port, spec, tcp_sport); @@ -1168,6 +1184,11 @@ dr_ste_v0_build_eth_ipv6_l3_l4_tag(struct mlx5dr_match_param *value, DR_STE_SET_TAG(eth_l4, tag, ecn, spec, ip_ecn); DR_STE_SET_TAG(eth_l4, tag, ipv6_hop_limit, spec, ttl_hoplimit); + if (sb->inner) + DR_STE_SET_TAG(eth_l4, tag, flow_label, misc, inner_ipv6_flow_label); + else + DR_STE_SET_TAG(eth_l4, tag, flow_label, misc, outer_ipv6_flow_label); + if (spec->tcp_flags) { DR_STE_SET_TCP_FLAGS(eth_l4, tag, spec); spec->tcp_flags = 0; @@ -1772,7 +1793,7 @@ dr_ste_v0_build_flex_parser_tnl_geneve_tlv_opt_init(struct mlx5dr_ste_build *sb, static int dr_ste_v0_build_flex_parser_tnl_gtpu_tag(struct mlx5dr_match_param *value, struct mlx5dr_ste_build *sb, - uint8_t *tag) + u8 *tag) { struct mlx5dr_match_misc3 *misc3 = &value->misc3; @@ -1802,7 +1823,7 @@ static void dr_ste_v0_build_flex_parser_tnl_gtpu_init(struct mlx5dr_ste_build *s static int dr_ste_v0_build_tnl_gtpu_flex_parser_0_tag(struct mlx5dr_match_param *value, struct mlx5dr_ste_build *sb, - uint8_t *tag) + u8 *tag) { if (dr_is_flex_parser_0_id(sb->caps->flex_parser_id_gtpu_dw_0)) DR_STE_SET_FLEX_PARSER_FIELD(tag, gtpu_dw_0, sb->caps, &value->misc3); @@ -1829,7 +1850,7 @@ dr_ste_v0_build_tnl_gtpu_flex_parser_0_init(struct mlx5dr_ste_build *sb, static int dr_ste_v0_build_tnl_gtpu_flex_parser_1_tag(struct mlx5dr_match_param *value, struct mlx5dr_ste_build *sb, - uint8_t *tag) + u8 *tag) { if (dr_is_flex_parser_1_id(sb->caps->flex_parser_id_gtpu_dw_0)) DR_STE_SET_FLEX_PARSER_FIELD(tag, gtpu_dw_0, sb->caps, &value->misc3); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c index 4aaca8eb7597..b2481c99da79 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c @@ -322,7 +322,7 @@ static void dr_ste_v1_set_hit_addr(u8 *hw_ste_p, u64 icm_addr, u32 ht_size) } static void dr_ste_v1_init(u8 *hw_ste_p, u16 lu_type, - u8 entry_type, u16 gvmi) + bool is_rx, u16 gvmi) { dr_ste_v1_set_lu_type(hw_ste_p, lu_type); dr_ste_v1_set_next_lu_type(hw_ste_p, MLX5DR_STE_LU_TYPE_DONT_CARE); @@ -402,8 +402,23 @@ static void dr_ste_v1_set_insert_hdr(u8 *hw_ste_p, u8 *d_action, dr_ste_v1_set_reparse(hw_ste_p); } -static void dr_ste_v1_set_tx_push_vlan(u8 *hw_ste_p, u8 *d_action, - u32 vlan_hdr) +static void dr_ste_v1_set_remove_hdr(u8 *hw_ste_p, u8 *s_action, + u8 anchor, u8 offset, + int size) +{ + MLX5_SET(ste_single_action_remove_header_size_v1, s_action, + action_id, DR_STE_V1_ACTION_ID_REMOVE_BY_SIZE); + MLX5_SET(ste_single_action_remove_header_size_v1, s_action, start_anchor, anchor); + + /* The hardware expects here size and offset in words (2 byte) */ + MLX5_SET(ste_single_action_remove_header_size_v1, s_action, remove_size, size / 2); + MLX5_SET(ste_single_action_remove_header_size_v1, s_action, start_offset, offset / 2); + + dr_ste_v1_set_reparse(hw_ste_p); +} + +static void dr_ste_v1_set_push_vlan(u8 *hw_ste_p, u8 *d_action, + u32 vlan_hdr) { MLX5_SET(ste_double_action_insert_with_inline_v1, d_action, action_id, DR_STE_V1_ACTION_ID_INSERT_INLINE); @@ -416,7 +431,7 @@ static void dr_ste_v1_set_tx_push_vlan(u8 *hw_ste_p, u8 *d_action, dr_ste_v1_set_reparse(hw_ste_p); } -static void dr_ste_v1_set_rx_pop_vlan(u8 *hw_ste_p, u8 *s_action, u8 vlans_num) +static void dr_ste_v1_set_pop_vlan(u8 *hw_ste_p, u8 *s_action, u8 vlans_num) { MLX5_SET(ste_single_action_remove_header_size_v1, s_action, action_id, DR_STE_V1_ACTION_ID_REMOVE_BY_SIZE); @@ -503,13 +518,28 @@ static void dr_ste_v1_set_actions_tx(struct mlx5dr_domain *dmn, { u8 *action = MLX5_ADDR_OF(ste_match_bwc_v1, last_ste, action); u8 action_sz = DR_STE_ACTION_DOUBLE_SZ; + bool allow_modify_hdr = true; bool allow_encap = true; + if (action_type_set[DR_ACTION_TYP_POP_VLAN]) { + if (action_sz < DR_STE_ACTION_SINGLE_SZ) { + dr_ste_v1_arr_init_next_match(&last_ste, added_stes, + attr->gvmi); + action = MLX5_ADDR_OF(ste_mask_and_match_v1, + last_ste, action); + action_sz = DR_STE_ACTION_TRIPLE_SZ; + } + dr_ste_v1_set_pop_vlan(last_ste, action, attr->vlans.count); + action_sz -= DR_STE_ACTION_SINGLE_SZ; + action += DR_STE_ACTION_SINGLE_SZ; + allow_modify_hdr = false; + } + if (action_type_set[DR_ACTION_TYP_CTR]) dr_ste_v1_set_counter_id(last_ste, attr->ctr_id); if (action_type_set[DR_ACTION_TYP_MODIFY_HDR]) { - if (action_sz < DR_STE_ACTION_DOUBLE_SZ) { + if (!allow_modify_hdr || action_sz < DR_STE_ACTION_DOUBLE_SZ) { dr_ste_v1_arr_init_next_match(&last_ste, added_stes, attr->gvmi); action = MLX5_ADDR_OF(ste_mask_and_match_v1, @@ -534,7 +564,8 @@ static void dr_ste_v1_set_actions_tx(struct mlx5dr_domain *dmn, action_sz = DR_STE_ACTION_TRIPLE_SZ; allow_encap = true; } - dr_ste_v1_set_tx_push_vlan(last_ste, action, attr->vlans.headers[i]); + dr_ste_v1_set_push_vlan(last_ste, action, + attr->vlans.headers[i]); action_sz -= DR_STE_ACTION_DOUBLE_SZ; action += DR_STE_ACTION_DOUBLE_SZ; } @@ -579,6 +610,18 @@ static void dr_ste_v1_set_actions_tx(struct mlx5dr_domain *dmn, attr->reformat.size); action_sz -= DR_STE_ACTION_DOUBLE_SZ; action += DR_STE_ACTION_DOUBLE_SZ; + } else if (action_type_set[DR_ACTION_TYP_REMOVE_HDR]) { + if (action_sz < DR_STE_ACTION_SINGLE_SZ) { + dr_ste_v1_arr_init_next_match(&last_ste, added_stes, attr->gvmi); + action = MLX5_ADDR_OF(ste_mask_and_match_v1, last_ste, action); + action_sz = DR_STE_ACTION_TRIPLE_SZ; + } + dr_ste_v1_set_remove_hdr(last_ste, action, + attr->reformat.param_0, + attr->reformat.param_1, + attr->reformat.size); + action_sz -= DR_STE_ACTION_SINGLE_SZ; + action += DR_STE_ACTION_SINGLE_SZ; } dr_ste_v1_set_hit_gvmi(last_ste, attr->hit_gvmi); @@ -635,7 +678,7 @@ static void dr_ste_v1_set_actions_rx(struct mlx5dr_domain *dmn, allow_ctr = false; } - dr_ste_v1_set_rx_pop_vlan(last_ste, action, attr->vlans.count); + dr_ste_v1_set_pop_vlan(last_ste, action, attr->vlans.count); action_sz -= DR_STE_ACTION_SINGLE_SZ; action += DR_STE_ACTION_SINGLE_SZ; } @@ -656,6 +699,26 @@ static void dr_ste_v1_set_actions_rx(struct mlx5dr_domain *dmn, action += DR_STE_ACTION_DOUBLE_SZ; } + if (action_type_set[DR_ACTION_TYP_PUSH_VLAN]) { + int i; + + for (i = 0; i < attr->vlans.count; i++) { + if (action_sz < DR_STE_ACTION_DOUBLE_SZ || + !allow_modify_hdr) { + dr_ste_v1_arr_init_next_match(&last_ste, + added_stes, + attr->gvmi); + action = MLX5_ADDR_OF(ste_mask_and_match_v1, + last_ste, action); + action_sz = DR_STE_ACTION_TRIPLE_SZ; + } + dr_ste_v1_set_push_vlan(last_ste, action, + attr->vlans.headers[i]); + action_sz -= DR_STE_ACTION_DOUBLE_SZ; + action += DR_STE_ACTION_DOUBLE_SZ; + } + } + if (action_type_set[DR_ACTION_TYP_CTR]) { /* Counter action set after decap and before insert_hdr * to exclude decaped / encaped header respectively. @@ -714,6 +777,20 @@ static void dr_ste_v1_set_actions_rx(struct mlx5dr_domain *dmn, action_sz -= DR_STE_ACTION_DOUBLE_SZ; action += DR_STE_ACTION_DOUBLE_SZ; allow_modify_hdr = false; + } else if (action_type_set[DR_ACTION_TYP_REMOVE_HDR]) { + if (action_sz < DR_STE_ACTION_SINGLE_SZ) { + dr_ste_v1_arr_init_next_match(&last_ste, added_stes, attr->gvmi); + action = MLX5_ADDR_OF(ste_mask_and_match_v1, last_ste, action); + action_sz = DR_STE_ACTION_TRIPLE_SZ; + allow_modify_hdr = true; + allow_ctr = true; + } + dr_ste_v1_set_remove_hdr(last_ste, action, + attr->reformat.param_0, + attr->reformat.param_1, + attr->reformat.size); + action_sz -= DR_STE_ACTION_SINGLE_SZ; + action += DR_STE_ACTION_SINGLE_SZ; } dr_ste_v1_set_hit_gvmi(last_ste, attr->hit_gvmi); @@ -1844,7 +1921,7 @@ dr_ste_v1_build_flex_parser_tnl_geneve_tlv_opt_init(struct mlx5dr_ste_build *sb, static int dr_ste_v1_build_flex_parser_tnl_gtpu_tag(struct mlx5dr_match_param *value, struct mlx5dr_ste_build *sb, - uint8_t *tag) + u8 *tag) { struct mlx5dr_match_misc3 *misc3 = &value->misc3; @@ -1868,7 +1945,7 @@ static void dr_ste_v1_build_flex_parser_tnl_gtpu_init(struct mlx5dr_ste_build *s static int dr_ste_v1_build_tnl_gtpu_flex_parser_0_tag(struct mlx5dr_match_param *value, struct mlx5dr_ste_build *sb, - uint8_t *tag) + u8 *tag) { if (dr_is_flex_parser_0_id(sb->caps->flex_parser_id_gtpu_dw_0)) DR_STE_SET_FLEX_PARSER_FIELD(tag, gtpu_dw_0, sb->caps, &value->misc3); @@ -1895,7 +1972,7 @@ dr_ste_v1_build_tnl_gtpu_flex_parser_0_init(struct mlx5dr_ste_build *sb, static int dr_ste_v1_build_tnl_gtpu_flex_parser_1_tag(struct mlx5dr_match_param *value, struct mlx5dr_ste_build *sb, - uint8_t *tag) + u8 *tag) { if (dr_is_flex_parser_1_id(sb->caps->flex_parser_id_gtpu_dw_0)) DR_STE_SET_FLEX_PARSER_FIELD(tag, gtpu_dw_0, sb->caps, &value->misc3); @@ -1960,7 +2037,9 @@ struct mlx5dr_ste_ctx ste_ctx_v1 = { .set_byte_mask = &dr_ste_v1_set_byte_mask, .get_byte_mask = &dr_ste_v1_get_byte_mask, /* Actions */ - .actions_caps = DR_STE_CTX_ACTION_CAP_RX_ENCAP, + .actions_caps = DR_STE_CTX_ACTION_CAP_TX_POP | + DR_STE_CTX_ACTION_CAP_RX_PUSH | + DR_STE_CTX_ACTION_CAP_RX_ENCAP, .set_actions_rx = &dr_ste_v1_set_actions_rx, .set_actions_tx = &dr_ste_v1_set_actions_tx, .modify_field_arr_sz = ARRAY_SIZE(dr_ste_v1_action_modify_field_arr), diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h index f5e93fa87aff..b20e8aabb861 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h @@ -83,15 +83,14 @@ enum { DR_STE_SIZE_CTRL = 32, DR_STE_SIZE_TAG = 16, DR_STE_SIZE_MASK = 16, -}; - -enum { DR_STE_SIZE_REDUCED = DR_STE_SIZE - DR_STE_SIZE_MASK, }; enum mlx5dr_ste_ctx_action_cap { DR_STE_CTX_ACTION_CAP_NONE = 0, - DR_STE_CTX_ACTION_CAP_RX_ENCAP = 1 << 0, + DR_STE_CTX_ACTION_CAP_TX_POP = 1 << 0, + DR_STE_CTX_ACTION_CAP_RX_PUSH = 1 << 1, + DR_STE_CTX_ACTION_CAP_RX_ENCAP = 1 << 2, }; enum { @@ -124,6 +123,7 @@ enum mlx5dr_action_type { DR_ACTION_TYP_POP_VLAN, DR_ACTION_TYP_PUSH_VLAN, DR_ACTION_TYP_INSERT_HDR, + DR_ACTION_TYP_REMOVE_HDR, DR_ACTION_TYP_SAMPLER, DR_ACTION_TYP_MAX, }; @@ -140,6 +140,7 @@ struct mlx5dr_icm_buddy_mem; struct mlx5dr_ste_htbl; struct mlx5dr_match_param; struct mlx5dr_cmd_caps; +struct mlx5dr_rule_rx_tx; struct mlx5dr_matcher_rx_tx; struct mlx5dr_ste_ctx; @@ -151,14 +152,14 @@ struct mlx5dr_ste { /* attached to the miss_list head at each htbl entry */ struct list_head miss_list_node; - /* each rule member that uses this ste attached here */ - struct list_head rule_list; - /* this ste is member of htbl */ struct mlx5dr_ste_htbl *htbl; struct mlx5dr_ste_htbl *next_htbl; + /* The rule this STE belongs to */ + struct mlx5dr_rule_rx_tx *rule_rx_tx; + /* this ste is part of a rule, located in ste's chain */ u8 ste_chain_location; }; @@ -171,8 +172,6 @@ struct mlx5dr_ste_htbl_ctrl { /* total number of collisions entries attached to this table */ unsigned int num_of_collisions; - unsigned int increase_threshold; - u8 may_grow:1; }; struct mlx5dr_ste_htbl { @@ -804,10 +803,15 @@ struct mlx5dr_cmd_caps { u8 isolate_vl_tc:1; }; +enum mlx5dr_domain_nic_type { + DR_DOMAIN_NIC_TYPE_RX, + DR_DOMAIN_NIC_TYPE_TX, +}; + struct mlx5dr_domain_rx_tx { u64 drop_icm_addr; u64 default_icm_addr; - enum mlx5dr_ste_entry_type ste_type; + enum mlx5dr_domain_nic_type type; struct mutex mutex; /* protect rx/tx domain */ }; @@ -885,14 +889,6 @@ struct mlx5dr_matcher { struct mlx5dv_flow_matcher *dv_matcher; }; -struct mlx5dr_rule_member { - struct mlx5dr_ste *ste; - /* attached to mlx5dr_rule via this */ - struct list_head list; - /* attached to mlx5dr_ste via this */ - struct list_head use_ste_list; -}; - struct mlx5dr_ste_action_modify_field { u16 hw_field; u8 start; @@ -993,8 +989,8 @@ struct mlx5dr_htbl_connect_info { }; struct mlx5dr_rule_rx_tx { - struct list_head rule_members_list; struct mlx5dr_matcher_rx_tx *nic_matcher; + struct mlx5dr_ste *last_rule_ste; }; struct mlx5dr_rule { @@ -1005,8 +1001,12 @@ struct mlx5dr_rule { u32 flow_source; }; -void mlx5dr_rule_update_rule_member(struct mlx5dr_ste *new_ste, - struct mlx5dr_ste *ste); +void mlx5dr_rule_set_last_member(struct mlx5dr_rule_rx_tx *nic_rule, + struct mlx5dr_ste *ste, + bool force); +int mlx5dr_rule_get_reverse_rule_members(struct mlx5dr_ste **ste_arr, + struct mlx5dr_ste *curr_ste, + int *num_of_stes); struct mlx5dr_icm_chunk { struct mlx5dr_icm_buddy_mem *buddy_mem; @@ -1083,6 +1083,25 @@ mlx5dr_icm_pool_chunk_size_to_byte(enum mlx5dr_icm_chunk_size chunk_size, return entry_size * num_of_entries; } +static inline int +mlx5dr_ste_htbl_increase_threshold(struct mlx5dr_ste_htbl *htbl) +{ + int num_of_entries = + mlx5dr_icm_pool_chunk_size_to_entries(htbl->chunk_size); + + /* Threshold is 50%, one is added to table of size 1 */ + return (num_of_entries + 1) / 2; +} + +static inline bool +mlx5dr_ste_htbl_may_grow(struct mlx5dr_ste_htbl *htbl) +{ + if (htbl->chunk_size == DR_CHUNK_SIZE_MAX - 1 || !htbl->byte_mask) + return false; + + return true; +} + static inline struct mlx5dr_cmd_vport_cap * mlx5dr_get_vport_cap(struct mlx5dr_cmd_caps *caps, u32 vport) { @@ -1216,7 +1235,7 @@ int mlx5dr_ste_htbl_init_and_postsend(struct mlx5dr_domain *dmn, bool update_hw_ste); void mlx5dr_ste_set_formatted_ste(struct mlx5dr_ste_ctx *ste_ctx, u16 gvmi, - struct mlx5dr_domain_rx_tx *nic_dmn, + enum mlx5dr_domain_nic_type nic_type, struct mlx5dr_ste_htbl *htbl, u8 *formatted_ste, struct mlx5dr_htbl_connect_info *connect_info); @@ -1282,6 +1301,7 @@ struct mlx5dr_send_ring { u8 sync_buff[MIN_READ_SYNC]; struct mlx5dr_mr *sync_mr; spinlock_t lock; /* Protect the data path of the send ring */ + bool err_state; /* send_ring is not usable in err state */ }; int mlx5dr_send_ring_alloc(struct mlx5dr_domain *dmn); @@ -1333,6 +1353,7 @@ struct mlx5dr_cmd_fte_info { u32 *val; struct mlx5_flow_act action; struct mlx5dr_cmd_flow_destination_hw_info *dest_arr; + bool ignore_flow_level; }; int mlx5dr_cmd_set_fte(struct mlx5_core_dev *dev, @@ -1362,7 +1383,8 @@ int mlx5dr_fw_create_md_tbl(struct mlx5dr_domain *dmn, int num_dest, bool reformat_req, u32 *tbl_id, - u32 *group_id); + u32 *group_id, + bool ignore_flow_level); void mlx5dr_fw_destroy_md_tbl(struct mlx5dr_domain *dmn, u32 tbl_id, u32 group_id); #endif /* _DR_TYPES_H_ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c index d5926dd7e972..7e58f4e594b7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c @@ -133,6 +133,9 @@ static int mlx5_cmd_dr_modify_flow_table(struct mlx5_flow_root_namespace *ns, struct mlx5_flow_table *ft, struct mlx5_flow_table *next_ft) { + if (mlx5_dr_is_fw_table(ft->flags)) + return mlx5_fs_cmd_get_fw_cmds()->modify_flow_table(ns, ft, next_ft); + return set_miss_action(ns, ft, next_ft); } @@ -487,9 +490,13 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns, actions[num_actions++] = term_actions->dest; } else if (num_term_actions > 1) { + bool ignore_flow_level = + !!(fte->action.flags & FLOW_ACT_IGNORE_FLOW_LEVEL); + tmp_action = mlx5dr_action_create_mult_dest_tbl(domain, term_actions, - num_term_actions); + num_term_actions, + ignore_flow_level); if (!tmp_action) { err = -EOPNOTSUPP; goto free_actions; @@ -557,6 +564,9 @@ static int mlx5_cmd_dr_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns case MLX5_REFORMAT_TYPE_INSERT_HDR: dr_reformat = DR_ACTION_REFORMAT_TYP_INSERT_HDR; break; + case MLX5_REFORMAT_TYPE_REMOVE_HDR: + dr_reformat = DR_ACTION_REFORMAT_TYP_REMOVE_HDR; + break; default: mlx5_core_err(ns->dev, "Packet-reformat not supported(%d)\n", params->type); @@ -615,15 +625,6 @@ static void mlx5_cmd_dr_modify_header_dealloc(struct mlx5_flow_root_namespace *n mlx5dr_action_destroy(modify_hdr->action.dr_action); } -static int mlx5_cmd_dr_update_fte(struct mlx5_flow_root_namespace *ns, - struct mlx5_flow_table *ft, - struct mlx5_flow_group *group, - int modify_mask, - struct fs_fte *fte) -{ - return -EOPNOTSUPP; -} - static int mlx5_cmd_dr_delete_fte(struct mlx5_flow_root_namespace *ns, struct mlx5_flow_table *ft, struct fs_fte *fte) @@ -648,6 +649,36 @@ static int mlx5_cmd_dr_delete_fte(struct mlx5_flow_root_namespace *ns, return 0; } +static int mlx5_cmd_dr_update_fte(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_table *ft, + struct mlx5_flow_group *group, + int modify_mask, + struct fs_fte *fte) +{ + struct fs_fte fte_tmp = {}; + int ret; + + if (mlx5_dr_is_fw_table(ft->flags)) + return mlx5_fs_cmd_get_fw_cmds()->update_fte(ns, ft, group, modify_mask, fte); + + /* Backup current dr rule details */ + fte_tmp.fs_dr_rule = fte->fs_dr_rule; + memset(&fte->fs_dr_rule, 0, sizeof(struct mlx5_fs_dr_rule)); + + /* First add the new updated rule, then delete the old rule */ + ret = mlx5_cmd_dr_create_fte(ns, ft, group, fte); + if (ret) + goto restore_fte; + + ret = mlx5_cmd_dr_delete_fte(ns, ft, &fte_tmp); + WARN_ONCE(ret, "dr update fte duplicate rule deletion failed\n"); + return ret; + +restore_fte: + fte->fs_dr_rule = fte_tmp.fs_dr_rule; + return ret; +} + static int mlx5_cmd_dr_set_peer(struct mlx5_flow_root_namespace *ns, struct mlx5_flow_root_namespace *peer_ns) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr.h index 9643ee647f57..d2a937f69784 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr.h @@ -8,12 +8,6 @@ enum { MLX5DR_STE_LU_TYPE_DONT_CARE = 0x0f, }; -enum mlx5dr_ste_entry_type { - MLX5DR_STE_TYPE_TX = 1, - MLX5DR_STE_TYPE_RX = 2, - MLX5DR_STE_TYPE_MODIFY_PKT = 6, -}; - struct mlx5_ifc_ste_general_bits { u8 entry_type[0x4]; u8 reserved_at_4[0x4]; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h index bbfe101d4e57..c5a8b1601999 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h @@ -27,6 +27,7 @@ enum mlx5dr_action_reformat_type { DR_ACTION_REFORMAT_TYP_TNL_L3_TO_L2, DR_ACTION_REFORMAT_TYP_L2_TO_TNL_L3, DR_ACTION_REFORMAT_TYP_INSERT_HDR, + DR_ACTION_REFORMAT_TYP_REMOVE_HDR, }; struct mlx5dr_match_parameters { @@ -94,7 +95,8 @@ mlx5dr_action_create_dest_vport(struct mlx5dr_domain *domain, struct mlx5dr_action * mlx5dr_action_create_mult_dest_tbl(struct mlx5dr_domain *dmn, struct mlx5dr_action_dest *dests, - u32 num_of_dests); + u32 num_of_dests, + bool ignore_flow_level); struct mlx5dr_action *mlx5dr_action_create_drop(void); diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c index a0a059e0154f..3e85b17f5857 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c @@ -199,7 +199,7 @@ static int mlxbf_gige_stop(struct net_device *netdev) return 0; } -static int mlxbf_gige_do_ioctl(struct net_device *netdev, +static int mlxbf_gige_eth_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) { if (!(netif_running(netdev))) @@ -253,7 +253,7 @@ static const struct net_device_ops mlxbf_gige_netdev_ops = { .ndo_start_xmit = mlxbf_gige_start_xmit, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, - .ndo_do_ioctl = mlxbf_gige_do_ioctl, + .ndo_eth_ioctl = mlxbf_gige_eth_ioctl, .ndo_set_rx_mode = mlxbf_gige_set_rx_mode, .ndo_get_stats64 = mlxbf_gige_get_stats64, }; @@ -269,9 +269,6 @@ static int mlxbf_gige_probe(struct platform_device *pdev) { struct phy_device *phydev; struct net_device *netdev; - struct resource *mac_res; - struct resource *llu_res; - struct resource *plu_res; struct mlxbf_gige *priv; void __iomem *llu_base; void __iomem *plu_base; @@ -280,27 +277,15 @@ static int mlxbf_gige_probe(struct platform_device *pdev) int addr; int err; - mac_res = platform_get_resource(pdev, IORESOURCE_MEM, MLXBF_GIGE_RES_MAC); - if (!mac_res) - return -ENXIO; - - base = devm_ioremap_resource(&pdev->dev, mac_res); + base = devm_platform_ioremap_resource(pdev, MLXBF_GIGE_RES_MAC); if (IS_ERR(base)) return PTR_ERR(base); - llu_res = platform_get_resource(pdev, IORESOURCE_MEM, MLXBF_GIGE_RES_LLU); - if (!llu_res) - return -ENXIO; - - llu_base = devm_ioremap_resource(&pdev->dev, llu_res); + llu_base = devm_platform_ioremap_resource(pdev, MLXBF_GIGE_RES_LLU); if (IS_ERR(llu_base)) return PTR_ERR(llu_base); - plu_res = platform_get_resource(pdev, IORESOURCE_MEM, MLXBF_GIGE_RES_PLU); - if (!plu_res) - return -ENXIO; - - plu_base = devm_ioremap_resource(&pdev->dev, plu_res); + plu_base = devm_platform_ioremap_resource(pdev, MLXBF_GIGE_RES_PLU); if (IS_ERR(plu_base)) return PTR_ERR(plu_base); diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_mdio.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_mdio.c index e32dd34fdcc0..7905179a9575 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_mdio.c +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_mdio.c @@ -145,14 +145,9 @@ static int mlxbf_gige_mdio_write(struct mii_bus *bus, int phy_add, int mlxbf_gige_mdio_probe(struct platform_device *pdev, struct mlxbf_gige *priv) { struct device *dev = &pdev->dev; - struct resource *res; int ret; - res = platform_get_resource(pdev, IORESOURCE_MEM, MLXBF_GIGE_RES_MDIO9); - if (!res) - return -ENODEV; - - priv->mdio_io = devm_ioremap_resource(dev, res); + priv->mdio_io = devm_platform_ioremap_resource(pdev, MLXBF_GIGE_RES_MDIO9); if (IS_ERR(priv->mdio_io)) return PTR_ERR(priv->mdio_io); diff --git a/drivers/net/ethernet/mellanox/mlxsw/Kconfig b/drivers/net/ethernet/mellanox/mlxsw/Kconfig index 12871c8dc7c1..d1ae248e125c 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/Kconfig +++ b/drivers/net/ethernet/mellanox/mlxsw/Kconfig @@ -58,10 +58,10 @@ config MLXSW_SPECTRUM depends on NET_IPGRE || NET_IPGRE=n depends on IPV6_GRE || IPV6_GRE=n depends on VXLAN || VXLAN=n + depends on PTP_1588_CLOCK_OPTIONAL select GENERIC_ALLOCATOR select PARMAN select OBJAGG - imply PTP_1588_CLOCK select NET_PTP_CLASSIFY if PTP_1588_CLOCK default m help diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index e775f08fb464..f080fab3de2b 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -1927,7 +1927,8 @@ __mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info, if (!reload) { alloc_size = sizeof(*mlxsw_core) + mlxsw_driver->priv_size; - devlink = devlink_alloc(&mlxsw_devlink_ops, alloc_size); + devlink = devlink_alloc(&mlxsw_devlink_ops, alloc_size, + mlxsw_bus_info->dev); if (!devlink) { err = -ENOMEM; goto err_devlink_alloc; @@ -1974,7 +1975,7 @@ __mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info, goto err_emad_init; if (!reload) { - err = devlink_register(devlink, mlxsw_bus_info->dev); + err = devlink_register(devlink); if (err) goto err_devlink_register; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 88699e678544..250c5a24264d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -1207,7 +1207,7 @@ static const struct net_device_ops mlxsw_sp_port_netdev_ops = { .ndo_vlan_rx_kill_vid = mlxsw_sp_port_kill_vid, .ndo_set_features = mlxsw_sp_set_features, .ndo_get_devlink_port = mlxsw_sp_port_get_devlink_port, - .ndo_do_ioctl = mlxsw_sp_port_ioctl, + .ndo_eth_ioctl = mlxsw_sp_port_ioctl, }; static int @@ -2717,6 +2717,22 @@ mlxsw_sp_sample_trigger_params_unset(struct mlxsw_sp *mlxsw_sp, static int mlxsw_sp_netdevice_event(struct notifier_block *unused, unsigned long event, void *ptr); +#define MLXSW_SP_DEFAULT_PARSING_DEPTH 96 +#define MLXSW_SP_INCREASED_PARSING_DEPTH 128 +#define MLXSW_SP_DEFAULT_VXLAN_UDP_DPORT 4789 + +static void mlxsw_sp_parsing_init(struct mlxsw_sp *mlxsw_sp) +{ + mlxsw_sp->parsing.parsing_depth = MLXSW_SP_DEFAULT_PARSING_DEPTH; + mlxsw_sp->parsing.vxlan_udp_dport = MLXSW_SP_DEFAULT_VXLAN_UDP_DPORT; + mutex_init(&mlxsw_sp->parsing.lock); +} + +static void mlxsw_sp_parsing_fini(struct mlxsw_sp *mlxsw_sp) +{ + mutex_destroy(&mlxsw_sp->parsing.lock); +} + static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core, const struct mlxsw_bus_info *mlxsw_bus_info, struct netlink_ext_ack *extack) @@ -2727,6 +2743,7 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core, mlxsw_sp->core = mlxsw_core; mlxsw_sp->bus_info = mlxsw_bus_info; + mlxsw_sp_parsing_init(mlxsw_sp); mlxsw_core_emad_string_tlv_enable(mlxsw_core); err = mlxsw_sp_base_mac_get(mlxsw_sp); @@ -2926,6 +2943,7 @@ err_policers_init: mlxsw_sp_fids_fini(mlxsw_sp); err_fids_init: mlxsw_sp_kvdl_fini(mlxsw_sp); + mlxsw_sp_parsing_fini(mlxsw_sp); return err; } @@ -3046,6 +3064,7 @@ static void mlxsw_sp_fini(struct mlxsw_core *mlxsw_core) mlxsw_sp_policers_fini(mlxsw_sp); mlxsw_sp_fids_fini(mlxsw_sp); mlxsw_sp_kvdl_fini(mlxsw_sp); + mlxsw_sp_parsing_fini(mlxsw_sp); } /* Per-FID flood tables are used for both "true" 802.1D FIDs and emulated @@ -3611,6 +3630,69 @@ void mlxsw_sp_port_dev_put(struct mlxsw_sp_port *mlxsw_sp_port) dev_put(mlxsw_sp_port->dev); } +int mlxsw_sp_parsing_depth_inc(struct mlxsw_sp *mlxsw_sp) +{ + char mprs_pl[MLXSW_REG_MPRS_LEN]; + int err = 0; + + mutex_lock(&mlxsw_sp->parsing.lock); + + if (refcount_inc_not_zero(&mlxsw_sp->parsing.parsing_depth_ref)) + goto out_unlock; + + mlxsw_reg_mprs_pack(mprs_pl, MLXSW_SP_INCREASED_PARSING_DEPTH, + mlxsw_sp->parsing.vxlan_udp_dport); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mprs), mprs_pl); + if (err) + goto out_unlock; + + mlxsw_sp->parsing.parsing_depth = MLXSW_SP_INCREASED_PARSING_DEPTH; + refcount_set(&mlxsw_sp->parsing.parsing_depth_ref, 1); + +out_unlock: + mutex_unlock(&mlxsw_sp->parsing.lock); + return err; +} + +void mlxsw_sp_parsing_depth_dec(struct mlxsw_sp *mlxsw_sp) +{ + char mprs_pl[MLXSW_REG_MPRS_LEN]; + + mutex_lock(&mlxsw_sp->parsing.lock); + + if (!refcount_dec_and_test(&mlxsw_sp->parsing.parsing_depth_ref)) + goto out_unlock; + + mlxsw_reg_mprs_pack(mprs_pl, MLXSW_SP_DEFAULT_PARSING_DEPTH, + mlxsw_sp->parsing.vxlan_udp_dport); + mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mprs), mprs_pl); + mlxsw_sp->parsing.parsing_depth = MLXSW_SP_DEFAULT_PARSING_DEPTH; + +out_unlock: + mutex_unlock(&mlxsw_sp->parsing.lock); +} + +int mlxsw_sp_parsing_vxlan_udp_dport_set(struct mlxsw_sp *mlxsw_sp, + __be16 udp_dport) +{ + char mprs_pl[MLXSW_REG_MPRS_LEN]; + int err; + + mutex_lock(&mlxsw_sp->parsing.lock); + + mlxsw_reg_mprs_pack(mprs_pl, mlxsw_sp->parsing.parsing_depth, + be16_to_cpu(udp_dport)); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mprs), mprs_pl); + if (err) + goto out_unlock; + + mlxsw_sp->parsing.vxlan_udp_dport = be16_to_cpu(udp_dport); + +out_unlock: + mutex_unlock(&mlxsw_sp->parsing.lock); + return err; +} + static void mlxsw_sp_port_lag_uppers_cleanup(struct mlxsw_sp_port *mlxsw_sp_port, struct net_device *lag_dev) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index f99db88ee884..3a43cba6d23c 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -148,6 +148,13 @@ struct mlxsw_sp_port_mapping { u8 lane; }; +struct mlxsw_sp_parsing { + refcount_t parsing_depth_ref; + u16 parsing_depth; + u16 vxlan_udp_dport; + struct mutex lock; /* Protects parsing configuration */ +}; + struct mlxsw_sp { struct mlxsw_sp_port **ports; struct mlxsw_core *core; @@ -173,6 +180,7 @@ struct mlxsw_sp { struct mlxsw_sp_counter_pool *counter_pool; struct mlxsw_sp_span *span; struct mlxsw_sp_trap *trap; + struct mlxsw_sp_parsing parsing; const struct mlxsw_sp_switchdev_ops *switchdev_ops; const struct mlxsw_sp_kvdl_ops *kvdl_ops; const struct mlxsw_afa_ops *afa_ops; @@ -652,6 +660,10 @@ struct mlxsw_sp_port *mlxsw_sp_port_dev_lower_find(struct net_device *dev); struct mlxsw_sp_port *mlxsw_sp_port_lower_dev_hold(struct net_device *dev); void mlxsw_sp_port_dev_put(struct mlxsw_sp_port *mlxsw_sp_port); struct mlxsw_sp_port *mlxsw_sp_port_dev_lower_find_rcu(struct net_device *dev); +int mlxsw_sp_parsing_depth_inc(struct mlxsw_sp *mlxsw_sp); +void mlxsw_sp_parsing_depth_dec(struct mlxsw_sp *mlxsw_sp); +int mlxsw_sp_parsing_vxlan_udp_dport_set(struct mlxsw_sp *mlxsw_sp, + __be16 udp_dport); /* spectrum_dcb.c */ #ifdef CONFIG_MLXSW_SPECTRUM_DCB diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.h index d8104fc6c900..98d1fdc25eac 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.h @@ -29,7 +29,6 @@ struct mlxsw_sp_nve { unsigned int num_max_mc_entries[MLXSW_SP_L3_PROTO_MAX]; u32 tunnel_index; u16 ul_rif_index; /* Reserved for Spectrum */ - unsigned int inc_parsing_depth_refs; }; struct mlxsw_sp_nve_ops { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c index b84bb4b65098..d018d2da5949 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c @@ -10,14 +10,6 @@ #include "spectrum.h" #include "spectrum_nve.h" -/* Eth (18B) | IPv6 (40B) | UDP (8B) | VxLAN (8B) | Eth (14B) | IPv6 (40B) - * - * In the worst case - where we have a VLAN tag on the outer Ethernet - * header and IPv6 in overlay and underlay - we need to parse 128 bytes - */ -#define MLXSW_SP_NVE_VXLAN_PARSING_DEPTH 128 -#define MLXSW_SP_NVE_DEFAULT_PARSING_DEPTH 96 - #define MLXSW_SP_NVE_VXLAN_SUPPORTED_FLAGS (VXLAN_F_UDP_ZERO_CSUM_TX | \ VXLAN_F_LEARN) @@ -115,66 +107,6 @@ static void mlxsw_sp_nve_vxlan_config(const struct mlxsw_sp_nve *nve, config->udp_dport = cfg->dst_port; } -static int __mlxsw_sp_nve_parsing_set(struct mlxsw_sp *mlxsw_sp, - unsigned int parsing_depth, - __be16 udp_dport) -{ - char mprs_pl[MLXSW_REG_MPRS_LEN]; - - mlxsw_reg_mprs_pack(mprs_pl, parsing_depth, be16_to_cpu(udp_dport)); - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mprs), mprs_pl); -} - -static int mlxsw_sp_nve_parsing_set(struct mlxsw_sp *mlxsw_sp, - __be16 udp_dport) -{ - int parsing_depth = mlxsw_sp->nve->inc_parsing_depth_refs ? - MLXSW_SP_NVE_VXLAN_PARSING_DEPTH : - MLXSW_SP_NVE_DEFAULT_PARSING_DEPTH; - - return __mlxsw_sp_nve_parsing_set(mlxsw_sp, parsing_depth, udp_dport); -} - -static int -__mlxsw_sp_nve_inc_parsing_depth_get(struct mlxsw_sp *mlxsw_sp, - __be16 udp_dport) -{ - int err; - - mlxsw_sp->nve->inc_parsing_depth_refs++; - - err = mlxsw_sp_nve_parsing_set(mlxsw_sp, udp_dport); - if (err) - goto err_nve_parsing_set; - return 0; - -err_nve_parsing_set: - mlxsw_sp->nve->inc_parsing_depth_refs--; - return err; -} - -static void -__mlxsw_sp_nve_inc_parsing_depth_put(struct mlxsw_sp *mlxsw_sp, - __be16 udp_dport) -{ - mlxsw_sp->nve->inc_parsing_depth_refs--; - mlxsw_sp_nve_parsing_set(mlxsw_sp, udp_dport); -} - -int mlxsw_sp_nve_inc_parsing_depth_get(struct mlxsw_sp *mlxsw_sp) -{ - __be16 udp_dport = mlxsw_sp->nve->config.udp_dport; - - return __mlxsw_sp_nve_inc_parsing_depth_get(mlxsw_sp, udp_dport); -} - -void mlxsw_sp_nve_inc_parsing_depth_put(struct mlxsw_sp *mlxsw_sp) -{ - __be16 udp_dport = mlxsw_sp->nve->config.udp_dport; - - __mlxsw_sp_nve_inc_parsing_depth_put(mlxsw_sp, udp_dport); -} - static void mlxsw_sp_nve_vxlan_config_prepare(char *tngcr_pl, const struct mlxsw_sp_nve_config *config) @@ -238,10 +170,14 @@ static int mlxsw_sp1_nve_vxlan_init(struct mlxsw_sp_nve *nve, struct mlxsw_sp *mlxsw_sp = nve->mlxsw_sp; int err; - err = __mlxsw_sp_nve_inc_parsing_depth_get(mlxsw_sp, config->udp_dport); + err = mlxsw_sp_parsing_vxlan_udp_dport_set(mlxsw_sp, config->udp_dport); if (err) return err; + err = mlxsw_sp_parsing_depth_inc(mlxsw_sp); + if (err) + goto err_parsing_depth_inc; + err = mlxsw_sp1_nve_vxlan_config_set(mlxsw_sp, config); if (err) goto err_config_set; @@ -263,7 +199,9 @@ err_promote_decap: err_rtdp_set: mlxsw_sp1_nve_vxlan_config_clear(mlxsw_sp); err_config_set: - __mlxsw_sp_nve_inc_parsing_depth_put(mlxsw_sp, 0); + mlxsw_sp_parsing_depth_dec(mlxsw_sp); +err_parsing_depth_inc: + mlxsw_sp_parsing_vxlan_udp_dport_set(mlxsw_sp, 0); return err; } @@ -275,7 +213,8 @@ static void mlxsw_sp1_nve_vxlan_fini(struct mlxsw_sp_nve *nve) mlxsw_sp_router_nve_demote_decap(mlxsw_sp, config->ul_tb_id, config->ul_proto, &config->ul_sip); mlxsw_sp1_nve_vxlan_config_clear(mlxsw_sp); - __mlxsw_sp_nve_inc_parsing_depth_put(mlxsw_sp, 0); + mlxsw_sp_parsing_depth_dec(mlxsw_sp); + mlxsw_sp_parsing_vxlan_udp_dport_set(mlxsw_sp, 0); } static int @@ -412,10 +351,14 @@ static int mlxsw_sp2_nve_vxlan_init(struct mlxsw_sp_nve *nve, struct mlxsw_sp *mlxsw_sp = nve->mlxsw_sp; int err; - err = __mlxsw_sp_nve_inc_parsing_depth_get(mlxsw_sp, config->udp_dport); + err = mlxsw_sp_parsing_vxlan_udp_dport_set(mlxsw_sp, config->udp_dport); if (err) return err; + err = mlxsw_sp_parsing_depth_inc(mlxsw_sp); + if (err) + goto err_parsing_depth_inc; + err = mlxsw_sp2_nve_vxlan_config_set(mlxsw_sp, config); if (err) goto err_config_set; @@ -438,7 +381,9 @@ err_promote_decap: err_rtdp_set: mlxsw_sp2_nve_vxlan_config_clear(mlxsw_sp); err_config_set: - __mlxsw_sp_nve_inc_parsing_depth_put(mlxsw_sp, 0); + mlxsw_sp_parsing_depth_dec(mlxsw_sp); +err_parsing_depth_inc: + mlxsw_sp_parsing_vxlan_udp_dport_set(mlxsw_sp, 0); return err; } @@ -450,7 +395,8 @@ static void mlxsw_sp2_nve_vxlan_fini(struct mlxsw_sp_nve *nve) mlxsw_sp_router_nve_demote_decap(mlxsw_sp, config->ul_tb_id, config->ul_proto, &config->ul_sip); mlxsw_sp2_nve_vxlan_config_clear(mlxsw_sp); - __mlxsw_sp_nve_inc_parsing_depth_put(mlxsw_sp, 0); + mlxsw_sp_parsing_depth_dec(mlxsw_sp); + mlxsw_sp_parsing_vxlan_udp_dport_set(mlxsw_sp, 0); } const struct mlxsw_sp_nve_ops mlxsw_sp2_nve_vxlan_ops = { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c index bfef65d1587c..1a180384e7e8 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c @@ -975,14 +975,14 @@ static int mlxsw_sp1_ptp_mtpppc_update(struct mlxsw_sp_port *mlxsw_sp_port, } if ((ing_types || egr_types) && !(orig_ing_types || orig_egr_types)) { - err = mlxsw_sp_nve_inc_parsing_depth_get(mlxsw_sp); + err = mlxsw_sp_parsing_depth_inc(mlxsw_sp); if (err) { netdev_err(mlxsw_sp_port->dev, "Failed to increase parsing depth"); return err; } } if (!(ing_types || egr_types) && (orig_ing_types || orig_egr_types)) - mlxsw_sp_nve_inc_parsing_depth_put(mlxsw_sp); + mlxsw_sp_parsing_depth_dec(mlxsw_sp); return mlxsw_sp1_ptp_mtpppc_set(mlxsw_sp_port->mlxsw_sp, ing_types, egr_types); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index f69cbb3852d5..19bb3ca0515e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -9484,6 +9484,7 @@ struct mlxsw_sp_mp_hash_config { DECLARE_BITMAP(fields, __MLXSW_REG_RECR2_FIELD_CNT); DECLARE_BITMAP(inner_headers, __MLXSW_REG_RECR2_HEADER_CNT); DECLARE_BITMAP(inner_fields, __MLXSW_REG_RECR2_INNER_FIELD_CNT); + bool inc_parsing_depth; }; #define MLXSW_SP_MP_HASH_HEADER_SET(_headers, _header) \ @@ -9654,6 +9655,7 @@ static void mlxsw_sp_mp6_hash_init(struct mlxsw_sp *mlxsw_sp, MLXSW_SP_MP_HASH_FIELD_SET(fields, IPV6_FLOW_LABEL); /* Inner */ mlxsw_sp_mp_hash_inner_l3(config); + config->inc_parsing_depth = true; break; case 3: /* Outer */ @@ -9678,22 +9680,53 @@ static void mlxsw_sp_mp6_hash_init(struct mlxsw_sp *mlxsw_sp, MLXSW_SP_MP_HASH_FIELD_SET(fields, TCP_UDP_DPORT); /* Inner */ mlxsw_sp_mp_hash_inner_custom(config, hash_fields); + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_MASK) + config->inc_parsing_depth = true; break; } } +static int mlxsw_sp_mp_hash_parsing_depth_adjust(struct mlxsw_sp *mlxsw_sp, + bool old_inc_parsing_depth, + bool new_inc_parsing_depth) +{ + int err; + + if (!old_inc_parsing_depth && new_inc_parsing_depth) { + err = mlxsw_sp_parsing_depth_inc(mlxsw_sp); + if (err) + return err; + mlxsw_sp->router->inc_parsing_depth = true; + } else if (old_inc_parsing_depth && !new_inc_parsing_depth) { + mlxsw_sp_parsing_depth_dec(mlxsw_sp); + mlxsw_sp->router->inc_parsing_depth = false; + } + + return 0; +} + static int mlxsw_sp_mp_hash_init(struct mlxsw_sp *mlxsw_sp) { + bool old_inc_parsing_depth, new_inc_parsing_depth; struct mlxsw_sp_mp_hash_config config = {}; char recr2_pl[MLXSW_REG_RECR2_LEN]; unsigned long bit; u32 seed; + int err; seed = jhash(mlxsw_sp->base_mac, sizeof(mlxsw_sp->base_mac), 0); mlxsw_reg_recr2_pack(recr2_pl, seed); mlxsw_sp_mp4_hash_init(mlxsw_sp, &config); mlxsw_sp_mp6_hash_init(mlxsw_sp, &config); + old_inc_parsing_depth = mlxsw_sp->router->inc_parsing_depth; + new_inc_parsing_depth = config.inc_parsing_depth; + err = mlxsw_sp_mp_hash_parsing_depth_adjust(mlxsw_sp, + old_inc_parsing_depth, + new_inc_parsing_depth); + if (err) + return err; + for_each_set_bit(bit, config.headers, __MLXSW_REG_RECR2_HEADER_CNT) mlxsw_reg_recr2_outer_header_enables_set(recr2_pl, bit, 1); for_each_set_bit(bit, config.fields, __MLXSW_REG_RECR2_FIELD_CNT) @@ -9703,7 +9736,16 @@ static int mlxsw_sp_mp_hash_init(struct mlxsw_sp *mlxsw_sp) for_each_set_bit(bit, config.inner_fields, __MLXSW_REG_RECR2_INNER_FIELD_CNT) mlxsw_reg_recr2_inner_header_fields_enable_set(recr2_pl, bit, 1); - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(recr2), recr2_pl); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(recr2), recr2_pl); + if (err) + goto err_reg_write; + + return 0; + +err_reg_write: + mlxsw_sp_mp_hash_parsing_depth_adjust(mlxsw_sp, new_inc_parsing_depth, + old_inc_parsing_depth); + return err; } #else static int mlxsw_sp_mp_hash_init(struct mlxsw_sp *mlxsw_sp) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h index c5d7007f9173..25d3eae63501 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h @@ -81,6 +81,7 @@ struct mlxsw_sp_router { size_t adj_grp_size_ranges_count; struct delayed_work nh_grp_activity_dw; struct list_head nh_res_grp_list; + bool inc_parsing_depth; }; struct mlxsw_sp_fib_entry_priv { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index 8f90cd323d5f..22fede5cb32c 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -335,14 +335,16 @@ mlxsw_sp_bridge_port_find(struct mlxsw_sp_bridge *bridge, static struct mlxsw_sp_bridge_port * mlxsw_sp_bridge_port_create(struct mlxsw_sp_bridge_device *bridge_device, - struct net_device *brport_dev) + struct net_device *brport_dev, + struct netlink_ext_ack *extack) { struct mlxsw_sp_bridge_port *bridge_port; struct mlxsw_sp_port *mlxsw_sp_port; + int err; bridge_port = kzalloc(sizeof(*bridge_port), GFP_KERNEL); if (!bridge_port) - return NULL; + return ERR_PTR(-ENOMEM); mlxsw_sp_port = mlxsw_sp_port_dev_lower_find(brport_dev); bridge_port->lagged = mlxsw_sp_port->lagged; @@ -359,12 +361,23 @@ mlxsw_sp_bridge_port_create(struct mlxsw_sp_bridge_device *bridge_device, list_add(&bridge_port->list, &bridge_device->ports_list); bridge_port->ref_count = 1; + err = switchdev_bridge_port_offload(brport_dev, mlxsw_sp_port->dev, + NULL, NULL, NULL, false, extack); + if (err) + goto err_switchdev_offload; + return bridge_port; + +err_switchdev_offload: + list_del(&bridge_port->list); + kfree(bridge_port); + return ERR_PTR(err); } static void mlxsw_sp_bridge_port_destroy(struct mlxsw_sp_bridge_port *bridge_port) { + switchdev_bridge_port_unoffload(bridge_port->dev, NULL, NULL, NULL); list_del(&bridge_port->list); WARN_ON(!list_empty(&bridge_port->vlans_list)); kfree(bridge_port); @@ -390,9 +403,10 @@ mlxsw_sp_bridge_port_get(struct mlxsw_sp_bridge *bridge, if (IS_ERR(bridge_device)) return ERR_CAST(bridge_device); - bridge_port = mlxsw_sp_bridge_port_create(bridge_device, brport_dev); - if (!bridge_port) { - err = -ENOMEM; + bridge_port = mlxsw_sp_bridge_port_create(bridge_device, brport_dev, + extack); + if (IS_ERR(bridge_port)) { + err = PTR_ERR(bridge_port); goto err_bridge_port_create; } @@ -1569,7 +1583,6 @@ mlxsw_sp_mc_write_mdb_entry(struct mlxsw_sp *mlxsw_sp, { long *flood_bitmap; int num_of_ports; - int alloc_size; u16 mid_idx; int err; @@ -1579,18 +1592,17 @@ mlxsw_sp_mc_write_mdb_entry(struct mlxsw_sp *mlxsw_sp, return false; num_of_ports = mlxsw_core_max_ports(mlxsw_sp->core); - alloc_size = sizeof(long) * BITS_TO_LONGS(num_of_ports); - flood_bitmap = kzalloc(alloc_size, GFP_KERNEL); + flood_bitmap = bitmap_alloc(num_of_ports, GFP_KERNEL); if (!flood_bitmap) return false; - bitmap_copy(flood_bitmap, mid->ports_in_mid, num_of_ports); + bitmap_copy(flood_bitmap, mid->ports_in_mid, num_of_ports); mlxsw_sp_mc_get_mrouters_bitmap(flood_bitmap, bridge_device, mlxsw_sp); mid->mid = mid_idx; err = mlxsw_sp_port_smid_full_entry(mlxsw_sp, mid_idx, flood_bitmap, bridge_device->mrouter); - kfree(flood_bitmap); + bitmap_free(flood_bitmap); if (err) return false; |