From 01b7768578a68abe597cfb36ebe0fc47c9305f88 Mon Sep 17 00:00:00 2001 From: Maher Sanalla Date: Wed, 25 Feb 2026 16:19:31 +0200 Subject: net/mlx5: Add TLP emulation device capabilities Introduce the hardware structures and definitions needed for the driver support of TLP emulation in mlx5_ifc. Signed-off-by: Maher Sanalla Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 23 ++++++++++++++++++++++- 1 file changed, 22 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 775cb0c56865..a3948b36820d 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1389,6 +1389,26 @@ struct mlx5_ifc_virtio_emulation_cap_bits { u8 reserved_at_1c0[0x640]; }; +struct mlx5_ifc_tlp_dev_emu_capabilities_bits { + u8 reserved_at_0[0x20]; + + u8 reserved_at_20[0x13]; + u8 log_tlp_rsp_gw_page_stride[0x5]; + u8 reserved_at_38[0x8]; + + u8 reserved_at_40[0xc0]; + + u8 reserved_at_100[0xc]; + u8 tlp_rsp_gw_num_pages[0x4]; + u8 reserved_at_110[0x10]; + + u8 reserved_at_120[0xa0]; + + u8 tlp_rsp_gw_pages_bar_offset[0x40]; + + u8 reserved_at_200[0x600]; +}; + enum { MLX5_ATOMIC_CAPS_ATOMIC_SIZE_QP_1_BYTE = 0x0, MLX5_ATOMIC_CAPS_ATOMIC_SIZE_QP_2_BYTES = 0x2, @@ -1961,7 +1981,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 log_max_rqt[0x5]; u8 reserved_at_390[0x3]; u8 log_max_rqt_size[0x5]; - u8 reserved_at_398[0x1]; + u8 tlp_device_emulation_manager[0x1]; u8 vnic_env_cnt_bar_uar_access[0x1]; u8 vnic_env_cnt_odp_page_fault[0x1]; u8 log_max_tis_per_sq[0x5]; @@ -3830,6 +3850,7 @@ union mlx5_ifc_hca_cap_union_bits { struct mlx5_ifc_tls_cap_bits tls_cap; struct mlx5_ifc_device_mem_cap_bits device_mem_cap; struct mlx5_ifc_virtio_emulation_cap_bits virtio_emulation_cap; + struct mlx5_ifc_tlp_dev_emu_capabilities_bits tlp_dev_emu_capabilities; struct mlx5_ifc_macsec_cap_bits macsec_cap; struct mlx5_ifc_crypto_cap_bits crypto_cap; struct mlx5_ifc_ipsec_cap_bits ipsec_cap; -- cgit v1.2.3 From 385a06f74ff7a03e3fb0b15fb87cfeb052d75073 Mon Sep 17 00:00:00 2001 From: Maher Sanalla Date: Wed, 25 Feb 2026 16:19:32 +0200 Subject: net/mlx5: Expose TLP emulation capabilities Expose and query TLP device emulation caps on driver load. Signed-off-by: Maher Sanalla Signed-off-by: Leon Romanovsky --- drivers/net/ethernet/mellanox/mlx5/core/fw.c | 6 ++++++ drivers/net/ethernet/mellanox/mlx5/core/main.c | 1 + include/linux/mlx5/device.h | 9 +++++++++ 3 files changed, 16 insertions(+) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c index eeb4437975f2..55249f405841 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c @@ -255,6 +255,12 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev) return err; } + if (MLX5_CAP_GEN(dev, tlp_device_emulation_manager)) { + err = mlx5_core_get_caps_mode(dev, MLX5_CAP_TLP_EMULATION, HCA_CAP_OPMOD_GET_CUR); + if (err) + return err; + } + if (MLX5_CAP_GEN(dev, ipsec_offload)) { err = mlx5_core_get_caps_mode(dev, MLX5_CAP_IPSEC, HCA_CAP_OPMOD_GET_CUR); if (err) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index fdc3ba20912e..b0bc4a7d4a93 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1772,6 +1772,7 @@ static const int types[] = { MLX5_CAP_CRYPTO, MLX5_CAP_SHAMPO, MLX5_CAP_ADV_RDMA, + MLX5_CAP_TLP_EMULATION, }; static void mlx5_hca_caps_free(struct mlx5_core_dev *dev) diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index b37fe39cef27..25c6b42140b2 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1259,6 +1259,7 @@ enum mlx5_cap_type { MLX5_CAP_PORT_SELECTION = 0x25, MLX5_CAP_ADV_VIRTUALIZATION = 0x26, MLX5_CAP_ADV_RDMA = 0x28, + MLX5_CAP_TLP_EMULATION = 0x2a, /* NUM OF CAP Types */ MLX5_CAP_NUM }; @@ -1481,6 +1482,14 @@ enum mlx5_qcam_feature_groups { MLX5_GET64(virtio_emulation_cap, \ (mdev)->caps.hca[MLX5_CAP_VDPA_EMULATION]->cur, cap) +#define MLX5_CAP_DEV_TLP_EMULATION(mdev, cap)\ + MLX5_GET(tlp_dev_emu_capabilities, \ + (mdev)->caps.hca[MLX5_CAP_TLP_EMULATION]->cur, cap) + +#define MLX5_CAP64_DEV_TLP_EMULATION(mdev, cap)\ + MLX5_GET64(tlp_dev_emu_capabilities, \ + (mdev)->caps.hca[MLX5_CAP_TLP_EMULATION]->cur, cap) + #define MLX5_CAP_IPSEC(mdev, cap)\ MLX5_GET(ipsec_cap, (mdev)->caps.hca[MLX5_CAP_IPSEC]->cur, cap) -- cgit v1.2.3 From f8e761655997cc0ee434fb5f35570d2e93d3a707 Mon Sep 17 00:00:00 2001 From: Alexei Lazar Date: Mon, 9 Mar 2026 11:34:27 +0200 Subject: net/mlx5: Add IFC bits for shared headroom pool PBMC support Add hardware interface definitions for shared headroom pool (SHP) in port buffer management: - shp_pbmc_pbsr_support: capability bit in PCAM enhanced features indicating device support for shared headroom pool in PBMC/PBSR. - shared_headroom_pool: buffer entry in PBMC register (pbmc_reg_bits) for the shared headroom pool configuration, reusing the bufferx layout; reduce trailing reserved region accordingly. Signed-off-by: Alexei Lazar Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20260309093435.1850724-2-tariqt@nvidia.com Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index a3948b36820d..a76c54bf1927 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -10845,7 +10845,9 @@ struct mlx5_ifc_pcam_enhanced_features_bits { u8 fec_200G_per_lane_in_pplm[0x1]; u8 reserved_at_1e[0x2a]; u8 fec_100G_per_lane_in_pplm[0x1]; - u8 reserved_at_49[0xa]; + u8 reserved_at_49[0x2]; + u8 shp_pbmc_pbsr_support[0x1]; + u8 reserved_at_4c[0x7]; u8 buffer_ownership[0x1]; u8 resereved_at_54[0x14]; u8 fec_50G_per_lane_in_pplm[0x1]; @@ -12090,8 +12092,9 @@ struct mlx5_ifc_pbmc_reg_bits { u8 port_buffer_size[0x10]; struct mlx5_ifc_bufferx_reg_bits buffer[10]; + struct mlx5_ifc_bufferx_reg_bits shared_headroom_pool; - u8 reserved_at_2e0[0x80]; + u8 reserved_at_320[0x40]; }; struct mlx5_ifc_sbpr_reg_bits { -- cgit v1.2.3 From 691dffc7255e740bc3df1c68b50b36786aadeb3a Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Mon, 9 Mar 2026 11:34:28 +0200 Subject: net/mlx5: Add silent mode set/query and VHCA RX IFC bits Update the mlx5 IFC headers with newly defined capability and command-layout bits: - Add silent_mode_query and rename silent_mode to silent_mode_set cap fields. - Add forward_vhca_rx and MLX5_IFC_FLOW_DESTINATION_TYPE_VHCA_RX. - Expose silent mode fields in the L2 table query command structures. Update the SD support check to use the new capability name (silent_mode_set) to match the updated IFC definition. Signed-off-by: Shay Drory Reviewed-by: Mark Bloch Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20260309093435.1850724-3-tariqt@nvidia.com Signed-off-by: Leon Romanovsky --- drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c | 2 +- include/linux/mlx5/mlx5_ifc.h | 19 ++++++++++++++----- 3 files changed, 16 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index c348ee62cd3a..16b28028609d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -1183,7 +1183,7 @@ int mlx5_fs_cmd_set_l2table_entry_silent(struct mlx5_core_dev *dev, u8 silent_mo { u32 in[MLX5_ST_SZ_DW(set_l2_table_entry_in)] = {}; - if (silent_mode && !MLX5_CAP_GEN(dev, silent_mode)) + if (silent_mode && !MLX5_CAP_GEN(dev, silent_mode_set)) return -EOPNOTSUPP; MLX5_SET(set_l2_table_entry_in, in, opcode, MLX5_CMD_OP_SET_L2_TABLE_ENTRY); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c index 954942ad93c5..762c783156b4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c @@ -107,7 +107,7 @@ static bool mlx5_sd_is_supported(struct mlx5_core_dev *dev, u8 host_buses) /* Disconnect secondaries from the network */ if (!MLX5_CAP_GEN(dev, eswitch_manager)) return false; - if (!MLX5_CAP_GEN(dev, silent_mode)) + if (!MLX5_CAP_GEN(dev, silent_mode_set)) return false; /* RX steering from primary to secondaries */ diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index a76c54bf1927..8fa4fb3d36cf 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -469,7 +469,8 @@ struct mlx5_ifc_flow_table_prop_layout_bits { u8 table_miss_action_domain[0x1]; u8 termination_table[0x1]; u8 reformat_and_fwd_to_table[0x1]; - u8 reserved_at_1a[0x2]; + u8 forward_vhca_rx[0x1]; + u8 reserved_at_1b[0x1]; u8 ipsec_encrypt[0x1]; u8 ipsec_decrypt[0x1]; u8 sw_owner_v2[0x1]; @@ -2012,12 +2013,14 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 disable_local_lb_mc[0x1]; u8 log_min_hairpin_wq_data_sz[0x5]; u8 reserved_at_3e8[0x1]; - u8 silent_mode[0x1]; + u8 silent_mode_set[0x1]; u8 vhca_state[0x1]; u8 log_max_vlan_list[0x5]; u8 reserved_at_3f0[0x3]; u8 log_max_current_mc_list[0x5]; - u8 reserved_at_3f8[0x3]; + u8 reserved_at_3f8[0x1]; + u8 silent_mode_query[0x1]; + u8 reserved_at_3fa[0x1]; u8 log_max_current_uc_list[0x5]; u8 general_obj_types[0x40]; @@ -2279,6 +2282,7 @@ enum mlx5_ifc_flow_destination_type { MLX5_IFC_FLOW_DESTINATION_TYPE_VPORT = 0x0, MLX5_IFC_FLOW_DESTINATION_TYPE_FLOW_TABLE = 0x1, MLX5_IFC_FLOW_DESTINATION_TYPE_TIR = 0x2, + MLX5_IFC_FLOW_DESTINATION_TYPE_VHCA_RX = 0x4, MLX5_IFC_FLOW_DESTINATION_TYPE_FLOW_SAMPLER = 0x6, MLX5_IFC_FLOW_DESTINATION_TYPE_UPLINK = 0x8, MLX5_IFC_FLOW_DESTINATION_TYPE_TABLE_TYPE = 0xA, @@ -6265,7 +6269,9 @@ struct mlx5_ifc_query_l2_table_entry_out_bits { u8 reserved_at_40[0xa0]; - u8 reserved_at_e0[0x13]; + u8 reserved_at_e0[0x11]; + u8 silent_mode[0x1]; + u8 reserved_at_f2[0x1]; u8 vlan_valid[0x1]; u8 vlan[0xc]; @@ -6281,7 +6287,10 @@ struct mlx5_ifc_query_l2_table_entry_in_bits { u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_at_40[0x60]; + u8 reserved_at_40[0x40]; + + u8 silent_mode_query[0x1]; + u8 reserved_at_81[0x1f]; u8 reserved_at_a0[0x8]; u8 table_index[0x18]; -- cgit v1.2.3 From 971b28accc09436fe6a6d5afd667dcbfb3ed7e03 Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Mon, 9 Mar 2026 11:34:32 +0200 Subject: net/mlx5: LAG, replace mlx5_get_dev_index with LAG sequence number Introduce mlx5_lag_get_dev_seq() which returns a device's sequence number within the LAG: master is always 0, remaining devices numbered sequentially. This provides a stable index for peer flow tracking and vport ordering without depending on native_port_num. Replace mlx5_get_dev_index() usage in en_tc.c (peer flow array indexing) and ib_rep.c (vport index ordering) with the new API. Signed-off-by: Shay Drory Reviewed-by: Mark Bloch Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20260309093435.1850724-7-tariqt@nvidia.com Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/mlx5/ib_rep.c | 4 ++- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 9 +++--- drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c | 34 +++++++++++++++++++++++ include/linux/mlx5/lag.h | 11 ++++++++ 4 files changed, 53 insertions(+), 5 deletions(-) create mode 100644 include/linux/mlx5/lag.h (limited to 'include') diff --git a/drivers/infiniband/hw/mlx5/ib_rep.c b/drivers/infiniband/hw/mlx5/ib_rep.c index 621834d75205..df8f049c5806 100644 --- a/drivers/infiniband/hw/mlx5/ib_rep.c +++ b/drivers/infiniband/hw/mlx5/ib_rep.c @@ -3,6 +3,7 @@ * Copyright (c) 2018 Mellanox Technologies. All rights reserved. */ +#include #include #include "ib_rep.h" #include "srq.h" @@ -134,7 +135,8 @@ mlx5_ib_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) /* Only 1 ib port is the representor for all uplinks */ peer_n_ports--; - if (mlx5_get_dev_index(peer_dev) < mlx5_get_dev_index(dev)) + if (mlx5_lag_get_dev_seq(peer_dev) < + mlx5_lag_get_dev_seq(dev)) vport_index += peer_n_ports; } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 1434b65d4746..397a93584fd6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -35,6 +35,7 @@ #include #include #include +#include #include #include #include @@ -2131,7 +2132,7 @@ static void mlx5e_tc_del_fdb_peer_flow(struct mlx5e_tc_flow *flow, mutex_unlock(&esw->offloads.peer_mutex); list_for_each_entry_safe(peer_flow, tmp, &flow->peer_flows, peer_flows) { - if (peer_index != mlx5_get_dev_index(peer_flow->priv->mdev)) + if (peer_index != mlx5_lag_get_dev_seq(peer_flow->priv->mdev)) continue; list_del(&peer_flow->peer_flows); @@ -2154,7 +2155,7 @@ static void mlx5e_tc_del_fdb_peers_flow(struct mlx5e_tc_flow *flow) devcom = flow->priv->mdev->priv.eswitch->devcom; mlx5_devcom_for_each_peer_entry(devcom, peer_esw, pos) { - i = mlx5_get_dev_index(peer_esw->dev); + i = mlx5_lag_get_dev_seq(peer_esw->dev); mlx5e_tc_del_fdb_peer_flow(flow, i); } } @@ -4584,7 +4585,7 @@ static int mlx5e_tc_add_fdb_peer_flow(struct flow_cls_offload *f, struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5_esw_flow_attr *attr = flow->attr->esw_attr; struct mlx5e_tc_flow_parse_attr *parse_attr; - int i = mlx5_get_dev_index(peer_esw->dev); + int i = mlx5_lag_get_dev_seq(peer_esw->dev); struct mlx5e_rep_priv *peer_urpriv; struct mlx5e_tc_flow *peer_flow; struct mlx5_core_dev *in_mdev; @@ -5525,7 +5526,7 @@ void mlx5e_tc_clean_fdb_peer_flows(struct mlx5_eswitch *esw) devcom = esw->devcom; mlx5_devcom_for_each_peer_entry(devcom, peer_esw, pos) { - i = mlx5_get_dev_index(peer_esw->dev); + i = mlx5_lag_get_dev_seq(peer_esw->dev); list_for_each_entry_safe(flow, tmp, &esw->offloads.peer_flows[i], peer[i]) mlx5e_tc_del_fdb_peers_flow(flow); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c index 4beee64c937a..51ec8f61ecbb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c @@ -35,6 +35,7 @@ #include #include #include +#include #include "lib/mlx5.h" #include "lib/devcom.h" #include "mlx5_core.h" @@ -369,6 +370,39 @@ int mlx5_lag_get_dev_index_by_seq(struct mlx5_lag *ldev, int seq) return -ENOENT; } +/* Reverse of mlx5_lag_get_dev_index_by_seq: given a device, return its + * sequence number in the LAG. Master is always 0, others numbered + * sequentially starting from 1. + */ +int mlx5_lag_get_dev_seq(struct mlx5_core_dev *dev) +{ + struct mlx5_lag *ldev = mlx5_lag_dev(dev); + int master_idx, i, num = 1; + struct lag_func *pf; + + if (!ldev) + return -ENOENT; + + master_idx = mlx5_lag_get_master_idx(ldev); + if (master_idx < 0) + return -ENOENT; + + pf = mlx5_lag_pf(ldev, master_idx); + if (pf && pf->dev == dev) + return 0; + + mlx5_ldev_for_each(i, 0, ldev) { + if (i == master_idx) + continue; + pf = mlx5_lag_pf(ldev, i); + if (pf->dev == dev) + return num; + num++; + } + return -ENOENT; +} +EXPORT_SYMBOL(mlx5_lag_get_dev_seq); + /* Devcom events for LAG master marking */ #define LAG_DEVCOM_PAIR (0) #define LAG_DEVCOM_UNPAIR (1) diff --git a/include/linux/mlx5/lag.h b/include/linux/mlx5/lag.h new file mode 100644 index 000000000000..d370dfd19055 --- /dev/null +++ b/include/linux/mlx5/lag.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */ + +#ifndef __MLX5_LAG_API_H__ +#define __MLX5_LAG_API_H__ + +struct mlx5_core_dev; + +int mlx5_lag_get_dev_seq(struct mlx5_core_dev *dev); + +#endif /* __MLX5_LAG_API_H__ */ -- cgit v1.2.3 From 0bc9059fab6365feaf95cc9a796a3d381915a70f Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Mon, 9 Mar 2026 11:34:33 +0200 Subject: net/mlx5: Add VHCA RX flow destination support for FW steering Introduce MLX5_FLOW_DESTINATION_TYPE_VHCA_RX as a new flow steering destination type. Wire the new destination through flow steering command setup by mapping it to MLX5_IFC_FLOW_DESTINATION_TYPE_VHCA_RX and passing the vhca id, extend forward-destination validation to accept it, and teach the flow steering tracepoint formatter to print rx_vhca_id. Signed-off-by: Shay Drory Reviewed-by: Mark Bloch Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20260309093435.1850724-8-tariqt@nvidia.com Signed-off-by: Leon Romanovsky --- drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c | 3 +++ drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c | 4 ++++ drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 7 +++++-- include/linux/mlx5/fs.h | 4 ++++ 4 files changed, 16 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c index 6d73127b7217..2cf1d3825def 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c @@ -282,6 +282,9 @@ const char *parse_fs_dst(struct trace_seq *p, case MLX5_FLOW_DESTINATION_TYPE_NONE: trace_seq_printf(p, "none\n"); break; + case MLX5_FLOW_DESTINATION_TYPE_VHCA_RX: + trace_seq_printf(p, "rx_vhca_id=%u\n", dst->vhca.id); + break; } trace_seq_putc(p, 0); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index 16b28028609d..1cd4cd898ec2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -716,6 +716,10 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev, id = dst->dest_attr.ft->id; ifc_type = MLX5_IFC_FLOW_DESTINATION_TYPE_TABLE_TYPE; break; + case MLX5_FLOW_DESTINATION_TYPE_VHCA_RX: + id = dst->dest_attr.vhca.id; + ifc_type = MLX5_IFC_FLOW_DESTINATION_TYPE_VHCA_RX; + break; default: id = dst->dest_attr.tir_num; ifc_type = MLX5_IFC_FLOW_DESTINATION_TYPE_TIR; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 2c3544880a30..003d211306a7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -503,7 +503,8 @@ static bool is_fwd_dest_type(enum mlx5_flow_destination_type type) type == MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER || type == MLX5_FLOW_DESTINATION_TYPE_TIR || type == MLX5_FLOW_DESTINATION_TYPE_RANGE || - type == MLX5_FLOW_DESTINATION_TYPE_TABLE_TYPE; + type == MLX5_FLOW_DESTINATION_TYPE_TABLE_TYPE || + type == MLX5_FLOW_DESTINATION_TYPE_VHCA_RX; } static bool check_valid_spec(const struct mlx5_flow_spec *spec) @@ -1890,7 +1891,9 @@ static bool mlx5_flow_dests_cmp(struct mlx5_flow_destination *d1, d1->range.hit_ft == d2->range.hit_ft && d1->range.miss_ft == d2->range.miss_ft && d1->range.min == d2->range.min && - d1->range.max == d2->range.max)) + d1->range.max == d2->range.max) || + (d1->type == MLX5_FLOW_DESTINATION_TYPE_VHCA_RX && + d1->vhca.id == d2->vhca.id)) return true; } diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 9cadb1d5e6df..02064424e868 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -55,6 +55,7 @@ enum mlx5_flow_destination_type { MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE_NUM, MLX5_FLOW_DESTINATION_TYPE_RANGE, MLX5_FLOW_DESTINATION_TYPE_TABLE_TYPE, + MLX5_FLOW_DESTINATION_TYPE_VHCA_RX, }; enum { @@ -189,6 +190,9 @@ struct mlx5_flow_destination { u32 ft_num; struct mlx5_flow_table *ft; struct mlx5_fc *counter; + struct { + u16 id; + } vhca; struct { u16 num; u16 vhca_id; -- cgit v1.2.3 From d6c9b4de8109a3b4ca9c6c6b7c5fbc42cfeff9ae Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Mon, 9 Mar 2026 11:34:34 +0200 Subject: {net/RDMA}/mlx5: Add LAG demux table API and vport demux rules Downstream patches will introduce SW-only LAG (e.g. shared_fdb without HW LAG). In this mode the firmware cannot create the LAG demux table, but vport demuxing is still required. Move LAG demux flow-table ownership to the LAG layer and introduce APIs to init/cleanup the demux table and add/delete per-vport rules. Adjust the RDMA driver to use the new APIs. In this mode, the LAG layer will create a flow group that matches vport metadata. Vports that are not native to the LAG master eswitch add the demux rule during IB representor load and remove it on unload. The demux rule forward traffic from said vports to their native eswitch manager via a new dest type - MLX5_FLOW_DESTINATION_TYPE_VHCA_RX. Signed-off-by: Shay Drory Reviewed-by: Mark Bloch Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20260309093435.1850724-9-tariqt@nvidia.com Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/mlx5/ib_rep.c | 20 ++- drivers/infiniband/hw/mlx5/main.c | 21 +-- drivers/infiniband/hw/mlx5/mlx5_ib.h | 1 - drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 12 ++ .../ethernet/mellanox/mlx5/core/eswitch_offloads.c | 83 ++++++++++- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 10 +- drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c | 152 +++++++++++++++++++++ drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h | 12 ++ include/linux/mlx5/fs.h | 6 +- include/linux/mlx5/lag.h | 10 ++ 10 files changed, 300 insertions(+), 27 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/hw/mlx5/ib_rep.c b/drivers/infiniband/hw/mlx5/ib_rep.c index df8f049c5806..1709b628702e 100644 --- a/drivers/infiniband/hw/mlx5/ib_rep.c +++ b/drivers/infiniband/hw/mlx5/ib_rep.c @@ -10,11 +10,13 @@ static int mlx5_ib_set_vport_rep(struct mlx5_core_dev *dev, + struct mlx5_core_dev *rep_dev, struct mlx5_eswitch_rep *rep, int vport_index) { struct mlx5_ib_dev *ibdev; struct net_device *ndev; + int ret; ibdev = mlx5_eswitch_uplink_get_proto_dev(dev->priv.eswitch, REP_IB); if (!ibdev) @@ -24,7 +26,17 @@ mlx5_ib_set_vport_rep(struct mlx5_core_dev *dev, rep->rep_data[REP_IB].priv = ibdev; ndev = mlx5_ib_get_rep_netdev(rep->esw, rep->vport); - return ib_device_set_netdev(&ibdev->ib_dev, ndev, vport_index + 1); + ret = ib_device_set_netdev(&ibdev->ib_dev, ndev, vport_index + 1); + if (ret) + return ret; + + /* Only Vports that are not native to the LAG master eswitch need to add + * demux rule. + */ + if (mlx5_eswitch_get_total_vports(dev) > vport_index) + return 0; + + return mlx5_lag_demux_rule_add(rep_dev, rep->vport, vport_index); } static void mlx5_ib_register_peer_vport_reps(struct mlx5_core_dev *mdev); @@ -131,7 +143,7 @@ mlx5_ib_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) if (mlx5_lag_is_master(peer_dev)) lag_master = peer_dev; - else if (!mlx5_lag_is_mpesw(dev)) + else if (!mlx5_lag_is_mpesw(peer_dev)) /* Only 1 ib port is the representor for all uplinks */ peer_n_ports--; @@ -145,7 +157,7 @@ mlx5_ib_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) if (rep->vport == MLX5_VPORT_UPLINK && !new_uplink) profile = &raw_eth_profile; else - return mlx5_ib_set_vport_rep(lag_master, rep, vport_index); + return mlx5_ib_set_vport_rep(lag_master, dev, rep, vport_index); if (mlx5_lag_is_shared_fdb(dev)) { ret = mlx5_ib_take_transport(lag_master); @@ -233,6 +245,8 @@ mlx5_ib_vport_rep_unload(struct mlx5_eswitch_rep *rep) vport_index = i; } + mlx5_lag_demux_rule_del(mdev, vport_index); + port = &dev->port[vport_index]; ib_device_set_netdev(&dev->ib_dev, NULL, vport_index + 1); diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 635002e684a5..9fb0629978bd 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -26,6 +26,7 @@ #include #include #include +#include #include #include #include @@ -3678,12 +3679,12 @@ static void mlx5e_lag_event_unregister(struct mlx5_ib_dev *dev) static int mlx5_eth_lag_init(struct mlx5_ib_dev *dev) { + struct mlx5_flow_table_attr ft_attr = {}; struct mlx5_core_dev *mdev = dev->mdev; - struct mlx5_flow_namespace *ns = mlx5_get_flow_namespace(mdev, - MLX5_FLOW_NAMESPACE_LAG); - struct mlx5_flow_table *ft; + struct mlx5_flow_namespace *ns; int err; + ns = mlx5_get_flow_namespace(mdev, MLX5_FLOW_NAMESPACE_LAG); if (!ns || !mlx5_lag_is_active(mdev)) return 0; @@ -3691,14 +3692,15 @@ static int mlx5_eth_lag_init(struct mlx5_ib_dev *dev) if (err) return err; - ft = mlx5_create_lag_demux_flow_table(ns, 0, 0); - if (IS_ERR(ft)) { - err = PTR_ERR(ft); + ft_attr.level = 0; + ft_attr.prio = 0; + ft_attr.max_fte = dev->num_ports; + + err = mlx5_lag_demux_init(mdev, &ft_attr); + if (err) goto err_destroy_vport_lag; - } mlx5e_lag_event_register(dev); - dev->flow_db->lag_demux_ft = ft; dev->lag_ports = mlx5_lag_get_num_ports(mdev); dev->lag_active = true; return 0; @@ -3716,8 +3718,7 @@ static void mlx5_eth_lag_cleanup(struct mlx5_ib_dev *dev) dev->lag_active = false; mlx5e_lag_event_unregister(dev); - mlx5_destroy_flow_table(dev->flow_db->lag_demux_ft); - dev->flow_db->lag_demux_ft = NULL; + mlx5_lag_demux_cleanup(mdev); mlx5_cmd_destroy_vport_lag(mdev); } diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index 4f4114d95130..3fc31415e107 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -306,7 +306,6 @@ struct mlx5_ib_flow_db { struct mlx5_ib_flow_prio rdma_rx[MLX5_IB_NUM_FLOW_FT]; struct mlx5_ib_flow_prio rdma_tx[MLX5_IB_NUM_FLOW_FT]; struct mlx5_ib_flow_prio opfcs[MLX5_IB_OPCOUNTER_MAX]; - struct mlx5_flow_table *lag_demux_ft; struct mlx5_ib_flow_prio *rdma_transport_rx[MLX5_RDMA_TRANSPORT_BYPASS_PRIO]; struct mlx5_ib_flow_prio *rdma_transport_tx[MLX5_RDMA_TRANSPORT_BYPASS_PRIO]; /* Protect flow steering bypass flow tables diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 96309a732d50..9b729789537f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -940,6 +940,12 @@ int mlx5_esw_ipsec_vf_packet_offload_supported(struct mlx5_core_dev *dev, u16 vport_num); bool mlx5_esw_host_functions_enabled(const struct mlx5_core_dev *dev); void mlx5_eswitch_safe_aux_devs_remove(struct mlx5_core_dev *dev); +struct mlx5_flow_group * +mlx5_esw_lag_demux_fg_create(struct mlx5_eswitch *esw, + struct mlx5_flow_table *ft); +struct mlx5_flow_handle * +mlx5_esw_lag_demux_rule_create(struct mlx5_eswitch *esw, u16 vport_num, + struct mlx5_flow_table *lag_ft); #else /* CONFIG_MLX5_ESWITCH */ /* eswitch API stubs */ static inline int mlx5_eswitch_init(struct mlx5_core_dev *dev) { return 0; } @@ -1025,6 +1031,12 @@ mlx5_esw_vport_vhca_id(struct mlx5_eswitch *esw, u16 vportn, u16 *vhca_id) static inline void mlx5_eswitch_safe_aux_devs_remove(struct mlx5_core_dev *dev) {} +static inline struct mlx5_flow_handle * +mlx5_esw_lag_demux_rule_create(struct mlx5_eswitch *esw, u16 vport_num, + struct mlx5_flow_table *lag_ft) +{ + return ERR_PTR(-EOPNOTSUPP); +} #endif /* CONFIG_MLX5_ESWITCH */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 90e6f97bdf4a..f98837470f39 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -1459,6 +1459,83 @@ esw_add_restore_rule(struct mlx5_eswitch *esw, u32 tag) return flow_rule; } +struct mlx5_flow_group * +mlx5_esw_lag_demux_fg_create(struct mlx5_eswitch *esw, + struct mlx5_flow_table *ft) +{ + int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + struct mlx5_flow_group *fg; + void *match_criteria; + void *flow_group_in; + + if (!mlx5_eswitch_vport_match_metadata_enabled(esw)) + return ERR_PTR(-EOPNOTSUPP); + + if (IS_ERR(ft)) + return ERR_CAST(ft); + + flow_group_in = kvzalloc(inlen, GFP_KERNEL); + if (!flow_group_in) + return ERR_PTR(-ENOMEM); + + match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in, + match_criteria); + MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable, + MLX5_MATCH_MISC_PARAMETERS_2); + 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, + ft->max_fte - 1); + + MLX5_SET(fte_match_param, match_criteria, + misc_parameters_2.metadata_reg_c_0, + mlx5_eswitch_get_vport_metadata_mask()); + + fg = mlx5_create_flow_group(ft, flow_group_in); + kvfree(flow_group_in); + if (IS_ERR(fg)) + esw_warn(esw->dev, "Can't create LAG demux flow group\n"); + + return fg; +} + +struct mlx5_flow_handle * +mlx5_esw_lag_demux_rule_create(struct mlx5_eswitch *esw, u16 vport_num, + struct mlx5_flow_table *lag_ft) +{ + struct mlx5_flow_spec *spec = kvzalloc(sizeof(*spec), GFP_KERNEL); + struct mlx5_flow_destination dest = {}; + struct mlx5_flow_act flow_act = {}; + struct mlx5_flow_handle *ret; + void *misc; + + if (!spec) + return ERR_PTR(-ENOMEM); + + if (!mlx5_eswitch_vport_match_metadata_enabled(esw)) { + kvfree(spec); + return ERR_PTR(-EOPNOTSUPP); + } + + misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, + misc_parameters_2); + MLX5_SET(fte_match_set_misc2, misc, metadata_reg_c_0, + mlx5_eswitch_get_vport_metadata_mask()); + spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2; + + misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, + misc_parameters_2); + MLX5_SET(fte_match_set_misc2, misc, metadata_reg_c_0, + mlx5_eswitch_get_vport_metadata_for_match(esw, vport_num)); + + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; + dest.type = MLX5_FLOW_DESTINATION_TYPE_VHCA_RX; + dest.vhca.id = MLX5_CAP_GEN(esw->dev, vhca_id); + + ret = mlx5_add_flow_rules(lag_ft, spec, &flow_act, &dest, 1); + kvfree(spec); + return ret; +} + #define MAX_PF_SQ 256 #define MAX_SQ_NVPORTS 32 @@ -2047,7 +2124,8 @@ static int esw_create_vport_rx_group(struct mlx5_eswitch *esw) if (IS_ERR(g)) { err = PTR_ERR(g); - mlx5_core_warn(esw->dev, "Failed to create vport rx group err %d\n", err); + esw_warn(esw->dev, "Failed to create vport rx group err %d\n", + err); goto out; } @@ -2092,7 +2170,8 @@ static int esw_create_vport_rx_drop_group(struct mlx5_eswitch *esw) if (IS_ERR(g)) { err = PTR_ERR(g); - mlx5_core_warn(esw->dev, "Failed to create vport rx drop group err %d\n", err); + esw_warn(esw->dev, + "Failed to create vport rx drop group err %d\n", err); goto out; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 003d211306a7..61a6ba1e49dd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -1438,15 +1438,9 @@ mlx5_create_vport_flow_table(struct mlx5_flow_namespace *ns, struct mlx5_flow_table* mlx5_create_lag_demux_flow_table(struct mlx5_flow_namespace *ns, - int prio, u32 level) + struct mlx5_flow_table_attr *ft_attr) { - struct mlx5_flow_table_attr ft_attr = {}; - - ft_attr.level = level; - ft_attr.prio = prio; - ft_attr.max_fte = 1; - - return __mlx5_create_flow_table(ns, &ft_attr, FS_FT_OP_MOD_LAG_DEMUX, 0); + return __mlx5_create_flow_table(ns, ft_attr, FS_FT_OP_MOD_LAG_DEMUX, 0); } EXPORT_SYMBOL(mlx5_create_lag_demux_flow_table); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c index 51ec8f61ecbb..449e4bd86c06 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c @@ -1471,6 +1471,158 @@ struct mlx5_devcom_comp_dev *mlx5_lag_get_devcom_comp(struct mlx5_lag *ldev) return devcom; } +static int mlx5_lag_demux_ft_fg_init(struct mlx5_core_dev *dev, + struct mlx5_flow_table_attr *ft_attr, + struct mlx5_lag *ldev) +{ +#ifdef CONFIG_MLX5_ESWITCH + struct mlx5_flow_namespace *ns; + struct mlx5_flow_group *fg; + int err; + + ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_LAG); + if (!ns) + return 0; + + ldev->lag_demux_ft = mlx5_create_flow_table(ns, ft_attr); + if (IS_ERR(ldev->lag_demux_ft)) + return PTR_ERR(ldev->lag_demux_ft); + + fg = mlx5_esw_lag_demux_fg_create(dev->priv.eswitch, + ldev->lag_demux_ft); + if (IS_ERR(fg)) { + err = PTR_ERR(fg); + mlx5_destroy_flow_table(ldev->lag_demux_ft); + ldev->lag_demux_ft = NULL; + return err; + } + + ldev->lag_demux_fg = fg; + return 0; +#else + return -EOPNOTSUPP; +#endif +} + +static int mlx5_lag_demux_fw_init(struct mlx5_core_dev *dev, + struct mlx5_flow_table_attr *ft_attr, + struct mlx5_lag *ldev) +{ + struct mlx5_flow_namespace *ns; + int err; + + ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_LAG); + if (!ns) + return 0; + + ldev->lag_demux_fg = NULL; + ft_attr->max_fte = 1; + ldev->lag_demux_ft = mlx5_create_lag_demux_flow_table(ns, ft_attr); + if (IS_ERR(ldev->lag_demux_ft)) { + err = PTR_ERR(ldev->lag_demux_ft); + ldev->lag_demux_ft = NULL; + return err; + } + + return 0; +} + +int mlx5_lag_demux_init(struct mlx5_core_dev *dev, + struct mlx5_flow_table_attr *ft_attr) +{ + struct mlx5_lag *ldev; + + if (!ft_attr) + return -EINVAL; + + ldev = mlx5_lag_dev(dev); + if (!ldev) + return -ENODEV; + + xa_init(&ldev->lag_demux_rules); + + if (mlx5_get_sd(dev)) + return mlx5_lag_demux_ft_fg_init(dev, ft_attr, ldev); + + return mlx5_lag_demux_fw_init(dev, ft_attr, ldev); +} +EXPORT_SYMBOL(mlx5_lag_demux_init); + +void mlx5_lag_demux_cleanup(struct mlx5_core_dev *dev) +{ + struct mlx5_flow_handle *rule; + struct mlx5_lag *ldev; + unsigned long vport_num; + + ldev = mlx5_lag_dev(dev); + if (!ldev) + return; + + xa_for_each(&ldev->lag_demux_rules, vport_num, rule) + mlx5_del_flow_rules(rule); + xa_destroy(&ldev->lag_demux_rules); + + if (ldev->lag_demux_fg) + mlx5_destroy_flow_group(ldev->lag_demux_fg); + if (ldev->lag_demux_ft) + mlx5_destroy_flow_table(ldev->lag_demux_ft); + ldev->lag_demux_fg = NULL; + ldev->lag_demux_ft = NULL; +} +EXPORT_SYMBOL(mlx5_lag_demux_cleanup); + +int mlx5_lag_demux_rule_add(struct mlx5_core_dev *vport_dev, u16 vport_num, + int index) +{ + struct mlx5_flow_handle *rule; + struct mlx5_lag *ldev; + int err; + + ldev = mlx5_lag_dev(vport_dev); + if (!ldev || !ldev->lag_demux_fg) + return 0; + + if (xa_load(&ldev->lag_demux_rules, index)) + return 0; + + rule = mlx5_esw_lag_demux_rule_create(vport_dev->priv.eswitch, + vport_num, ldev->lag_demux_ft); + if (IS_ERR(rule)) { + err = PTR_ERR(rule); + mlx5_core_warn(vport_dev, + "Failed to create LAG demux rule for vport %u, err %d\n", + vport_num, err); + return err; + } + + err = xa_err(xa_store(&ldev->lag_demux_rules, index, rule, + GFP_KERNEL)); + if (err) { + mlx5_del_flow_rules(rule); + mlx5_core_warn(vport_dev, + "Failed to store LAG demux rule for vport %u, err %d\n", + vport_num, err); + } + + return err; +} +EXPORT_SYMBOL(mlx5_lag_demux_rule_add); + +void mlx5_lag_demux_rule_del(struct mlx5_core_dev *dev, int index) +{ + struct mlx5_flow_handle *rule; + struct mlx5_lag *ldev; + + ldev = mlx5_lag_dev(dev); + if (!ldev || !ldev->lag_demux_fg) + return; + + rule = xa_erase(&ldev->lag_demux_rules, index); + if (rule) + mlx5_del_flow_rules(rule); +} +EXPORT_SYMBOL(mlx5_lag_demux_rule_del); + static void mlx5_queue_bond_work(struct mlx5_lag *ldev, unsigned long delay) { queue_delayed_work(ldev->wq, &ldev->bond_work, delay); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h index 30cbd61768f8..6c911374f409 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h @@ -5,6 +5,9 @@ #define __MLX5_LAG_H__ #include +#include +#include +#include #define MLX5_LAG_MAX_HASH_BUCKETS 16 /* XArray mark for the LAG master device @@ -83,6 +86,9 @@ struct mlx5_lag { /* Protect lag fields/state changes */ struct mutex lock; struct lag_mpesw lag_mpesw; + struct mlx5_flow_table *lag_demux_ft; + struct mlx5_flow_group *lag_demux_fg; + struct xarray lag_demux_rules; }; static inline struct mlx5_lag * @@ -133,6 +139,12 @@ mlx5_lag_is_ready(struct mlx5_lag *ldev) bool mlx5_lag_shared_fdb_supported(struct mlx5_lag *ldev); bool mlx5_lag_check_prereq(struct mlx5_lag *ldev); +int mlx5_lag_demux_init(struct mlx5_core_dev *dev, + struct mlx5_flow_table_attr *ft_attr); +void mlx5_lag_demux_cleanup(struct mlx5_core_dev *dev); +int mlx5_lag_demux_rule_add(struct mlx5_core_dev *dev, u16 vport_num, + int vport_index); +void mlx5_lag_demux_rule_del(struct mlx5_core_dev *dev, int vport_index); void mlx5_modify_lag(struct mlx5_lag *ldev, struct lag_tracker *tracker); int mlx5_activate_lag(struct mlx5_lag *ldev, diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 02064424e868..d8f3b7ef319e 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -252,9 +252,9 @@ mlx5_create_auto_grouped_flow_table(struct mlx5_flow_namespace *ns, struct mlx5_flow_table * mlx5_create_vport_flow_table(struct mlx5_flow_namespace *ns, struct mlx5_flow_table_attr *ft_attr, u16 vport); -struct mlx5_flow_table *mlx5_create_lag_demux_flow_table( - struct mlx5_flow_namespace *ns, - int prio, u32 level); +struct mlx5_flow_table * +mlx5_create_lag_demux_flow_table(struct mlx5_flow_namespace *ns, + struct mlx5_flow_table_attr *ft_attr); int mlx5_destroy_flow_table(struct mlx5_flow_table *ft); /* inbox should be set with the following values: diff --git a/include/linux/mlx5/lag.h b/include/linux/mlx5/lag.h index d370dfd19055..ab9f754664e5 100644 --- a/include/linux/mlx5/lag.h +++ b/include/linux/mlx5/lag.h @@ -4,8 +4,18 @@ #ifndef __MLX5_LAG_API_H__ #define __MLX5_LAG_API_H__ +#include + struct mlx5_core_dev; +struct mlx5_flow_table; +struct mlx5_flow_table_attr; +int mlx5_lag_demux_init(struct mlx5_core_dev *dev, + struct mlx5_flow_table_attr *ft_attr); +void mlx5_lag_demux_cleanup(struct mlx5_core_dev *dev); +int mlx5_lag_demux_rule_add(struct mlx5_core_dev *dev, u16 vport_num, + int vport_index); +void mlx5_lag_demux_rule_del(struct mlx5_core_dev *dev, int vport_index); int mlx5_lag_get_dev_seq(struct mlx5_core_dev *dev); #endif /* __MLX5_LAG_API_H__ */ -- cgit v1.2.3 From 4dd2115f43594da5271a1aa34fde6719b4259047 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Mon, 9 Mar 2026 11:34:35 +0200 Subject: net/mlx5: Expose MLX5_UMR_ALIGN definition Expose HW constant value in a shared header, to be used by core/EN drivers. Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20260309093435.1850724-10-tariqt@nvidia.com Reviewed-by: Dragos Tatulea Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/mlx5/mr.c | 1 - include/linux/mlx5/device.h | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 665323b90b64..ff56948597dd 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -51,7 +51,6 @@ enum { }; #define MLX5_MR_CACHE_PERSISTENT_ENTRY_MIN_DESCS 4 -#define MLX5_UMR_ALIGN 2048 static void create_mkey_callback(int status, struct mlx5_async_work *context); diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 25c6b42140b2..07a25f264292 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -293,6 +293,7 @@ enum { MLX5_UMR_INLINE = (1 << 7), }; +#define MLX5_UMR_ALIGN (2048) #define MLX5_UMR_FLEX_ALIGNMENT 0x40 #define MLX5_UMR_MTT_NUM_ENTRIES_ALIGNMENT (MLX5_UMR_FLEX_ALIGNMENT / sizeof(struct mlx5_mtt)) #define MLX5_UMR_KLM_NUM_ENTRIES_ALIGNMENT (MLX5_UMR_FLEX_ALIGNMENT / sizeof(struct mlx5_klm)) -- cgit v1.2.3