diff options
author | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-07 18:49:45 +0000 |
---|---|---|
committer | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-07 18:49:45 +0000 |
commit | 2c3c1048746a4622d8c89a29670120dc8fab93c4 (patch) | |
tree | 848558de17fb3008cdf4d861b01ac7781903ce39 /drivers/net/ethernet/mellanox/mlx5/core/esw | |
parent | Initial commit. (diff) | |
download | linux-2c3c1048746a4622d8c89a29670120dc8fab93c4.tar.xz linux-2c3c1048746a4622d8c89a29670120dc8fab93c4.zip |
Adding upstream version 6.1.76.upstream/6.1.76
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'drivers/net/ethernet/mellanox/mlx5/core/esw')
23 files changed, 6143 insertions, 0 deletions
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/esw/Makefile new file mode 100644 index 000000000..c78512eed --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/Makefile @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +subdir-ccflags-y += -I$(src)/.. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_lgcy.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_lgcy.c new file mode 100644 index 000000000..6b4c9ffad --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_lgcy.c @@ -0,0 +1,178 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2020 Mellanox Technologies Inc. All rights reserved. */ + +#include "mlx5_core.h" +#include "eswitch.h" +#include "helper.h" +#include "lgcy.h" + +static void esw_acl_egress_lgcy_rules_destroy(struct mlx5_vport *vport) +{ + esw_acl_egress_vlan_destroy(vport); + if (!IS_ERR_OR_NULL(vport->egress.legacy.drop_rule)) { + mlx5_del_flow_rules(vport->egress.legacy.drop_rule); + vport->egress.legacy.drop_rule = NULL; + } +} + +static int esw_acl_egress_lgcy_groups_create(struct mlx5_eswitch *esw, + struct mlx5_vport *vport) +{ + int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + struct mlx5_core_dev *dev = esw->dev; + struct mlx5_flow_group *drop_grp; + u32 *flow_group_in; + int err = 0; + + err = esw_acl_egress_vlan_grp_create(esw, vport); + if (err) + return err; + + flow_group_in = kvzalloc(inlen, GFP_KERNEL); + if (!flow_group_in) { + err = -ENOMEM; + goto alloc_err; + } + + MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 1); + MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 1); + drop_grp = mlx5_create_flow_group(vport->egress.acl, flow_group_in); + if (IS_ERR(drop_grp)) { + err = PTR_ERR(drop_grp); + esw_warn(dev, "Failed to create E-Switch vport[%d] egress drop flow group, err(%d)\n", + vport->vport, err); + goto drop_grp_err; + } + + vport->egress.legacy.drop_grp = drop_grp; + kvfree(flow_group_in); + return 0; + +drop_grp_err: + kvfree(flow_group_in); +alloc_err: + esw_acl_egress_vlan_grp_destroy(vport); + return err; +} + +static void esw_acl_egress_lgcy_groups_destroy(struct mlx5_vport *vport) +{ + if (!IS_ERR_OR_NULL(vport->egress.legacy.drop_grp)) { + mlx5_destroy_flow_group(vport->egress.legacy.drop_grp); + vport->egress.legacy.drop_grp = NULL; + } + esw_acl_egress_vlan_grp_destroy(vport); +} + +int esw_acl_egress_lgcy_setup(struct mlx5_eswitch *esw, + struct mlx5_vport *vport) +{ + bool vst_mode_steering = esw_vst_mode_is_steering(esw); + struct mlx5_flow_destination drop_ctr_dst = {}; + struct mlx5_flow_destination *dst = NULL; + struct mlx5_fc *drop_counter = NULL; + struct mlx5_flow_act flow_act = {}; + /* The egress acl table contains 2 rules: + * 1)Allow traffic with vlan_tag=vst_vlan_id + * 2)Drop all other traffic. + */ + int table_size = 2; + int dest_num = 0; + int actions_flag; + int err = 0; + + if (vport->egress.legacy.drop_counter) { + drop_counter = vport->egress.legacy.drop_counter; + } else if (MLX5_CAP_ESW_EGRESS_ACL(esw->dev, flow_counter)) { + drop_counter = mlx5_fc_create(esw->dev, false); + if (IS_ERR(drop_counter)) { + esw_warn(esw->dev, + "vport[%d] configure egress drop rule counter err(%ld)\n", + vport->vport, PTR_ERR(drop_counter)); + drop_counter = NULL; + } + vport->egress.legacy.drop_counter = drop_counter; + } + + esw_acl_egress_lgcy_rules_destroy(vport); + + if (!vport->info.vlan && !vport->info.qos) { + esw_acl_egress_lgcy_cleanup(esw, vport); + return 0; + } + + if (!vport->egress.acl) { + vport->egress.acl = esw_acl_table_create(esw, vport, + MLX5_FLOW_NAMESPACE_ESW_EGRESS, + table_size); + if (IS_ERR(vport->egress.acl)) { + err = PTR_ERR(vport->egress.acl); + vport->egress.acl = NULL; + goto out; + } + + err = esw_acl_egress_lgcy_groups_create(esw, vport); + if (err) + goto out; + } + + esw_debug(esw->dev, + "vport[%d] configure egress rules, vlan(%d) qos(%d)\n", + vport->vport, vport->info.vlan, vport->info.qos); + + /* Allowed vlan rule */ + actions_flag = MLX5_FLOW_CONTEXT_ACTION_ALLOW; + if (vst_mode_steering) + actions_flag |= MLX5_FLOW_CONTEXT_ACTION_VLAN_POP; + err = esw_egress_acl_vlan_create(esw, vport, NULL, vport->info.vlan, + actions_flag); + if (err) + goto out; + + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP; + + /* Attach egress drop flow counter */ + if (drop_counter) { + flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_COUNT; + drop_ctr_dst.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; + drop_ctr_dst.counter_id = mlx5_fc_id(drop_counter); + dst = &drop_ctr_dst; + dest_num++; + } + vport->egress.legacy.drop_rule = + mlx5_add_flow_rules(vport->egress.acl, NULL, + &flow_act, dst, dest_num); + if (IS_ERR(vport->egress.legacy.drop_rule)) { + err = PTR_ERR(vport->egress.legacy.drop_rule); + esw_warn(esw->dev, + "vport[%d] configure egress drop rule failed, err(%d)\n", + vport->vport, err); + vport->egress.legacy.drop_rule = NULL; + goto out; + } + + return err; + +out: + esw_acl_egress_lgcy_cleanup(esw, vport); + return err; +} + +void esw_acl_egress_lgcy_cleanup(struct mlx5_eswitch *esw, + struct mlx5_vport *vport) +{ + if (IS_ERR_OR_NULL(vport->egress.acl)) + goto clean_drop_counter; + + esw_debug(esw->dev, "Destroy vport[%d] E-Switch egress ACL\n", vport->vport); + + esw_acl_egress_lgcy_rules_destroy(vport); + esw_acl_egress_lgcy_groups_destroy(vport); + esw_acl_egress_table_destroy(vport); + +clean_drop_counter: + if (vport->egress.legacy.drop_counter) { + mlx5_fc_destroy(esw->dev, vport->egress.legacy.drop_counter); + vport->egress.legacy.drop_counter = NULL; + } +} 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 new file mode 100644 index 000000000..2e504c746 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_ofld.c @@ -0,0 +1,259 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2020 Mellanox Technologies Inc. All rights reserved. */ + +#include "mlx5_core.h" +#include "eswitch.h" +#include "helper.h" +#include "ofld.h" + +static void esw_acl_egress_ofld_fwd2vport_destroy(struct mlx5_vport *vport) +{ + if (!vport->egress.offloads.fwd_rule) + return; + + mlx5_del_flow_rules(vport->egress.offloads.fwd_rule); + 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) +{ + struct mlx5_flow_act flow_act = {}; + int err = 0; + + esw_debug(esw->dev, "vport(%d) configure egress acl rule fwd2vport(%d)\n", + vport->vport, fwd_dest->vport.num); + + /* Delete the old egress forward-to-vport rule if any */ + esw_acl_egress_ofld_fwd2vport_destroy(vport); + + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; + + vport->egress.offloads.fwd_rule = + mlx5_add_flow_rules(vport->egress.acl, NULL, + &flow_act, fwd_dest, 1); + if (IS_ERR(vport->egress.offloads.fwd_rule)) { + err = PTR_ERR(vport->egress.offloads.fwd_rule); + esw_warn(esw->dev, + "vport(%d) failed to add fwd2vport acl rule err(%d)\n", + vport->vport, err); + vport->egress.offloads.fwd_rule = NULL; + } + + return err; +} + +static int esw_acl_egress_ofld_rules_create(struct mlx5_eswitch *esw, + struct mlx5_vport *vport, + struct mlx5_flow_destination *fwd_dest) +{ + int err = 0; + int action; + + if (MLX5_CAP_GEN(esw->dev, prio_tag_required)) { + /* For prio tag mode, there is only 1 FTEs: + * 1) prio tag packets - pop the prio tag VLAN, allow + * Unmatched traffic is allowed by default + */ + esw_debug(esw->dev, + "vport[%d] configure prio tag egress rules\n", vport->vport); + + action = MLX5_FLOW_CONTEXT_ACTION_VLAN_POP; + action |= fwd_dest ? MLX5_FLOW_CONTEXT_ACTION_FWD_DEST : + MLX5_FLOW_CONTEXT_ACTION_ALLOW; + + /* prio tag vlan rule - pop it so vport receives untagged packets */ + err = esw_egress_acl_vlan_create(esw, vport, fwd_dest, 0, action); + if (err) + goto prio_err; + } + + if (fwd_dest) { + err = esw_acl_egress_ofld_fwd2vport_create(esw, vport, fwd_dest); + if (err) + goto fwd_err; + } + + return 0; + +fwd_err: + esw_acl_egress_vlan_destroy(vport); +prio_err: + return err; +} + +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, + struct mlx5_vport *vport) +{ + int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + struct mlx5_flow_group *fwd_grp; + u32 *flow_group_in; + u32 flow_index = 0; + int ret = 0; + + if (MLX5_CAP_GEN(esw->dev, prio_tag_required)) { + ret = esw_acl_egress_vlan_grp_create(esw, vport); + if (ret) + return ret; + + flow_index++; + } + + if (!mlx5_esw_acl_egress_fwd2vport_supported(esw)) + goto out; + + flow_group_in = kvzalloc(inlen, GFP_KERNEL); + if (!flow_group_in) { + ret = -ENOMEM; + goto fwd_grp_err; + } + + /* This group holds 1 FTE to forward all packets to other vport + * when bond vports is supported. + */ + MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, flow_index); + MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, flow_index); + fwd_grp = mlx5_create_flow_group(vport->egress.acl, flow_group_in); + if (IS_ERR(fwd_grp)) { + ret = PTR_ERR(fwd_grp); + esw_warn(esw->dev, + "Failed to create vport[%d] egress fwd2vport flow group, err(%d)\n", + vport->vport, ret); + kvfree(flow_group_in); + goto fwd_grp_err; + } + vport->egress.offloads.fwd_grp = fwd_grp; + kvfree(flow_group_in); + return 0; + +fwd_grp_err: + esw_acl_egress_vlan_grp_destroy(vport); +out: + return ret; +} + +static void esw_acl_egress_ofld_groups_destroy(struct mlx5_vport *vport) +{ + if (!IS_ERR_OR_NULL(vport->egress.offloads.fwd_grp)) { + 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); +} + +static bool esw_acl_egress_needed(struct mlx5_eswitch *esw, u16 vport_num) +{ + return mlx5_eswitch_is_vf_vport(esw, vport_num) || mlx5_esw_is_sf_vport(esw, vport_num); +} + +int esw_acl_egress_ofld_setup(struct mlx5_eswitch *esw, struct mlx5_vport *vport) +{ + int table_size = 0; + int err; + + if (!mlx5_esw_acl_egress_fwd2vport_supported(esw) && + !MLX5_CAP_GEN(esw->dev, prio_tag_required)) + return 0; + + if (!esw_acl_egress_needed(esw, vport->vport)) + return 0; + + esw_acl_egress_ofld_rules_destroy(vport); + + if (mlx5_esw_acl_egress_fwd2vport_supported(esw)) + table_size++; + if (MLX5_CAP_GEN(esw->dev, prio_tag_required)) + table_size++; + vport->egress.acl = esw_acl_table_create(esw, vport, + MLX5_FLOW_NAMESPACE_ESW_EGRESS, table_size); + if (IS_ERR(vport->egress.acl)) { + err = PTR_ERR(vport->egress.acl); + vport->egress.acl = NULL; + return err; + } + + err = esw_acl_egress_ofld_groups_create(esw, vport); + if (err) + goto group_err; + + esw_debug(esw->dev, "vport[%d] configure egress rules\n", vport->vport); + + err = esw_acl_egress_ofld_rules_create(esw, vport, NULL); + if (err) + goto rules_err; + + return 0; + +rules_err: + esw_acl_egress_ofld_groups_destroy(vport); +group_err: + esw_acl_egress_table_destroy(vport); + return err; +} + +void esw_acl_egress_ofld_cleanup(struct mlx5_vport *vport) +{ + esw_acl_egress_ofld_rules_destroy(vport); + esw_acl_egress_ofld_groups_destroy(vport); + esw_acl_egress_table_destroy(vport); +} + +int mlx5_esw_acl_egress_vport_bond(struct mlx5_eswitch *esw, u16 active_vport_num, + u16 passive_vport_num) +{ + struct mlx5_vport *passive_vport = mlx5_eswitch_get_vport(esw, passive_vport_num); + struct mlx5_vport *active_vport = mlx5_eswitch_get_vport(esw, active_vport_num); + struct mlx5_flow_destination fwd_dest = {}; + + if (IS_ERR(active_vport)) + return PTR_ERR(active_vport); + if (IS_ERR(passive_vport)) + return PTR_ERR(passive_vport); + + /* Cleanup and recreate rules WITHOUT fwd2vport of active vport */ + esw_acl_egress_ofld_rules_destroy(active_vport); + esw_acl_egress_ofld_rules_create(esw, active_vport, NULL); + + /* Cleanup and recreate all rules + fwd2vport rule of passive vport to forward */ + esw_acl_egress_ofld_rules_destroy(passive_vport); + fwd_dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT; + fwd_dest.vport.num = active_vport_num; + fwd_dest.vport.vhca_id = MLX5_CAP_GEN(esw->dev, vhca_id); + fwd_dest.vport.flags = MLX5_FLOW_DEST_VPORT_VHCA_ID; + + return esw_acl_egress_ofld_rules_create(esw, passive_vport, &fwd_dest); +} + +int mlx5_esw_acl_egress_vport_unbond(struct mlx5_eswitch *esw, u16 vport_num) +{ + struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num); + + if (IS_ERR(vport)) + return PTR_ERR(vport); + + esw_acl_egress_ofld_rules_destroy(vport); + return esw_acl_egress_ofld_rules_create(esw, vport, NULL); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.c new file mode 100644 index 000000000..45b839116 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.c @@ -0,0 +1,163 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2020 Mellanox Technologies Inc. All rights reserved. */ + +#include "mlx5_core.h" +#include "eswitch.h" +#include "helper.h" + +struct mlx5_flow_table * +esw_acl_table_create(struct mlx5_eswitch *esw, struct mlx5_vport *vport, int ns, int size) +{ + struct mlx5_flow_table_attr ft_attr = {}; + struct mlx5_core_dev *dev = esw->dev; + struct mlx5_flow_namespace *root_ns; + struct mlx5_flow_table *acl; + int acl_supported; + u16 vport_num; + int err; + + acl_supported = (ns == MLX5_FLOW_NAMESPACE_ESW_INGRESS) ? + MLX5_CAP_ESW_INGRESS_ACL(dev, ft_support) : + MLX5_CAP_ESW_EGRESS_ACL(dev, ft_support); + + if (!acl_supported) + return ERR_PTR(-EOPNOTSUPP); + + vport_num = vport->vport; + esw_debug(dev, "Create vport[%d] %s ACL table\n", vport_num, + ns == MLX5_FLOW_NAMESPACE_ESW_INGRESS ? "ingress" : "egress"); + + root_ns = mlx5_get_flow_vport_acl_namespace(dev, ns, vport->index); + if (!root_ns) { + esw_warn(dev, "Failed to get E-Switch root namespace for vport (%d)\n", + vport_num); + return ERR_PTR(-EOPNOTSUPP); + } + + ft_attr.max_fte = size; + ft_attr.flags = MLX5_FLOW_TABLE_OTHER_VPORT; + acl = mlx5_create_vport_flow_table(root_ns, &ft_attr, vport_num); + if (IS_ERR(acl)) { + err = PTR_ERR(acl); + esw_warn(dev, "vport[%d] create %s ACL table, err(%d)\n", vport_num, + ns == MLX5_FLOW_NAMESPACE_ESW_INGRESS ? "ingress" : "egress", err); + } + return acl; +} + +int esw_egress_acl_vlan_create(struct mlx5_eswitch *esw, + struct mlx5_vport *vport, + struct mlx5_flow_destination *fwd_dest, + u16 vlan_id, u32 flow_action) +{ + struct mlx5_flow_act flow_act = {}; + struct mlx5_flow_spec *spec; + int err = 0; + + if (vport->egress.allowed_vlan) + return -EEXIST; + + spec = kvzalloc(sizeof(*spec), GFP_KERNEL); + if (!spec) + return -ENOMEM; + + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.cvlan_tag); + MLX5_SET_TO_ONES(fte_match_param, spec->match_value, outer_headers.cvlan_tag); + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.first_vid); + MLX5_SET(fte_match_param, spec->match_value, outer_headers.first_vid, vlan_id); + + spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; + flow_act.action = flow_action; + vport->egress.allowed_vlan = + mlx5_add_flow_rules(vport->egress.acl, spec, + &flow_act, fwd_dest, 0); + if (IS_ERR(vport->egress.allowed_vlan)) { + err = PTR_ERR(vport->egress.allowed_vlan); + esw_warn(esw->dev, + "vport[%d] configure egress vlan rule failed, err(%d)\n", + vport->vport, err); + vport->egress.allowed_vlan = NULL; + } + + kvfree(spec); + return err; +} + +void esw_acl_egress_vlan_destroy(struct mlx5_vport *vport) +{ + if (!IS_ERR_OR_NULL(vport->egress.allowed_vlan)) { + mlx5_del_flow_rules(vport->egress.allowed_vlan); + vport->egress.allowed_vlan = NULL; + } +} + +int esw_acl_egress_vlan_grp_create(struct mlx5_eswitch *esw, struct mlx5_vport *vport) +{ + int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + struct mlx5_flow_group *vlan_grp; + void *match_criteria; + u32 *flow_group_in; + int ret = 0; + + flow_group_in = kvzalloc(inlen, GFP_KERNEL); + if (!flow_group_in) + return -ENOMEM; + + MLX5_SET(create_flow_group_in, flow_group_in, + match_criteria_enable, MLX5_MATCH_OUTER_HEADERS); + match_criteria = MLX5_ADDR_OF(create_flow_group_in, + flow_group_in, match_criteria); + MLX5_SET_TO_ONES(fte_match_param, match_criteria, outer_headers.cvlan_tag); + MLX5_SET_TO_ONES(fte_match_param, match_criteria, outer_headers.first_vid); + 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); + + vlan_grp = mlx5_create_flow_group(vport->egress.acl, flow_group_in); + if (IS_ERR(vlan_grp)) { + ret = PTR_ERR(vlan_grp); + esw_warn(esw->dev, + "Failed to create E-Switch vport[%d] egress pop vlans flow group, err(%d)\n", + vport->vport, ret); + goto out; + } + vport->egress.vlan_grp = vlan_grp; + +out: + kvfree(flow_group_in); + return ret; +} + +void esw_acl_egress_vlan_grp_destroy(struct mlx5_vport *vport) +{ + if (!IS_ERR_OR_NULL(vport->egress.vlan_grp)) { + mlx5_destroy_flow_group(vport->egress.vlan_grp); + vport->egress.vlan_grp = NULL; + } +} + +void esw_acl_egress_table_destroy(struct mlx5_vport *vport) +{ + if (IS_ERR_OR_NULL(vport->egress.acl)) + return; + + mlx5_destroy_flow_table(vport->egress.acl); + vport->egress.acl = NULL; +} + +void esw_acl_ingress_table_destroy(struct mlx5_vport *vport) +{ + if (!vport->ingress.acl) + return; + + mlx5_destroy_flow_table(vport->ingress.acl); + vport->ingress.acl = NULL; +} + +void esw_acl_ingress_allow_rule_destroy(struct mlx5_vport *vport) +{ + if (!vport->ingress.allow_rule) + return; + + mlx5_del_flow_rules(vport->ingress.allow_rule); + vport->ingress.allow_rule = NULL; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.h new file mode 100644 index 000000000..a47063fab --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2020 Mellanox Technologies Inc. All rights reserved. */ + +#ifndef __MLX5_ESWITCH_ACL_HELPER_H__ +#define __MLX5_ESWITCH_ACL_HELPER_H__ + +#include "eswitch.h" + +/* General acl helper functions */ +struct mlx5_flow_table * +esw_acl_table_create(struct mlx5_eswitch *esw, struct mlx5_vport *vport, int ns, int size); + +/* Egress acl helper functions */ +void esw_acl_egress_table_destroy(struct mlx5_vport *vport); +int esw_egress_acl_vlan_create(struct mlx5_eswitch *esw, struct mlx5_vport *vport, + struct mlx5_flow_destination *fwd_dest, + u16 vlan_id, u32 flow_action); +void esw_acl_egress_vlan_destroy(struct mlx5_vport *vport); +int esw_acl_egress_vlan_grp_create(struct mlx5_eswitch *esw, struct mlx5_vport *vport); +void esw_acl_egress_vlan_grp_destroy(struct mlx5_vport *vport); + +/* Ingress acl helper functions */ +void esw_acl_ingress_table_destroy(struct mlx5_vport *vport); +void esw_acl_ingress_allow_rule_destroy(struct mlx5_vport *vport); + +#endif /* __MLX5_ESWITCH_ACL_HELPER_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_lgcy.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_lgcy.c new file mode 100644 index 000000000..093ed86a0 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_lgcy.c @@ -0,0 +1,305 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2020 Mellanox Technologies Inc. All rights reserved. */ + +#include "mlx5_core.h" +#include "eswitch.h" +#include "helper.h" +#include "lgcy.h" + +static void esw_acl_ingress_lgcy_rules_destroy(struct mlx5_vport *vport) +{ + if (vport->ingress.legacy.drop_rule) { + mlx5_del_flow_rules(vport->ingress.legacy.drop_rule); + vport->ingress.legacy.drop_rule = NULL; + } + esw_acl_ingress_allow_rule_destroy(vport); +} + +static int esw_acl_ingress_lgcy_groups_create(struct mlx5_eswitch *esw, + struct mlx5_vport *vport) +{ + int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + struct mlx5_core_dev *dev = esw->dev; + struct mlx5_flow_group *g; + void *match_criteria; + u32 *flow_group_in; + int err; + + flow_group_in = kvzalloc(inlen, GFP_KERNEL); + if (!flow_group_in) + return -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_OUTER_HEADERS); + MLX5_SET_TO_ONES(fte_match_param, match_criteria, outer_headers.cvlan_tag); + MLX5_SET_TO_ONES(fte_match_param, match_criteria, outer_headers.smac_47_16); + MLX5_SET_TO_ONES(fte_match_param, match_criteria, outer_headers.smac_15_0); + 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(vport->ingress.acl, flow_group_in); + if (IS_ERR(g)) { + err = PTR_ERR(g); + esw_warn(dev, "vport[%d] ingress create untagged spoofchk flow group, err(%d)\n", + vport->vport, err); + goto spoof_err; + } + vport->ingress.legacy.allow_untagged_spoofchk_grp = g; + + memset(flow_group_in, 0, inlen); + MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable, + MLX5_MATCH_OUTER_HEADERS); + MLX5_SET_TO_ONES(fte_match_param, match_criteria, outer_headers.cvlan_tag); + MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 1); + MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 1); + + g = mlx5_create_flow_group(vport->ingress.acl, flow_group_in); + if (IS_ERR(g)) { + err = PTR_ERR(g); + esw_warn(dev, "vport[%d] ingress create untagged flow group, err(%d)\n", + vport->vport, err); + goto untagged_err; + } + vport->ingress.legacy.allow_untagged_only_grp = g; + + memset(flow_group_in, 0, inlen); + MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable, + MLX5_MATCH_OUTER_HEADERS); + MLX5_SET_TO_ONES(fte_match_param, match_criteria, outer_headers.smac_47_16); + MLX5_SET_TO_ONES(fte_match_param, match_criteria, outer_headers.smac_15_0); + MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 2); + MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 2); + + g = mlx5_create_flow_group(vport->ingress.acl, flow_group_in); + if (IS_ERR(g)) { + err = PTR_ERR(g); + esw_warn(dev, "vport[%d] ingress create spoofchk flow group, err(%d)\n", + vport->vport, err); + goto allow_spoof_err; + } + vport->ingress.legacy.allow_spoofchk_only_grp = g; + + memset(flow_group_in, 0, inlen); + MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 3); + MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 3); + + g = mlx5_create_flow_group(vport->ingress.acl, flow_group_in); + if (IS_ERR(g)) { + err = PTR_ERR(g); + esw_warn(dev, "vport[%d] ingress create drop flow group, err(%d)\n", + vport->vport, err); + goto drop_err; + } + vport->ingress.legacy.drop_grp = g; + kvfree(flow_group_in); + return 0; + +drop_err: + if (!IS_ERR_OR_NULL(vport->ingress.legacy.allow_spoofchk_only_grp)) { + mlx5_destroy_flow_group(vport->ingress.legacy.allow_spoofchk_only_grp); + vport->ingress.legacy.allow_spoofchk_only_grp = NULL; + } +allow_spoof_err: + if (!IS_ERR_OR_NULL(vport->ingress.legacy.allow_untagged_only_grp)) { + mlx5_destroy_flow_group(vport->ingress.legacy.allow_untagged_only_grp); + vport->ingress.legacy.allow_untagged_only_grp = NULL; + } +untagged_err: + if (!IS_ERR_OR_NULL(vport->ingress.legacy.allow_untagged_spoofchk_grp)) { + mlx5_destroy_flow_group(vport->ingress.legacy.allow_untagged_spoofchk_grp); + vport->ingress.legacy.allow_untagged_spoofchk_grp = NULL; + } +spoof_err: + kvfree(flow_group_in); + return err; +} + +static void esw_acl_ingress_lgcy_groups_destroy(struct mlx5_vport *vport) +{ + if (vport->ingress.legacy.allow_spoofchk_only_grp) { + mlx5_destroy_flow_group(vport->ingress.legacy.allow_spoofchk_only_grp); + vport->ingress.legacy.allow_spoofchk_only_grp = NULL; + } + if (vport->ingress.legacy.allow_untagged_only_grp) { + mlx5_destroy_flow_group(vport->ingress.legacy.allow_untagged_only_grp); + vport->ingress.legacy.allow_untagged_only_grp = NULL; + } + if (vport->ingress.legacy.allow_untagged_spoofchk_grp) { + mlx5_destroy_flow_group(vport->ingress.legacy.allow_untagged_spoofchk_grp); + vport->ingress.legacy.allow_untagged_spoofchk_grp = NULL; + } + if (vport->ingress.legacy.drop_grp) { + mlx5_destroy_flow_group(vport->ingress.legacy.drop_grp); + vport->ingress.legacy.drop_grp = NULL; + } +} + +int esw_acl_ingress_lgcy_setup(struct mlx5_eswitch *esw, + struct mlx5_vport *vport) +{ + bool vst_mode_steering = esw_vst_mode_is_steering(esw); + struct mlx5_flow_destination drop_ctr_dst = {}; + struct mlx5_flow_destination *dst = NULL; + struct mlx5_flow_act flow_act = {}; + struct mlx5_flow_spec *spec = NULL; + struct mlx5_fc *counter = NULL; + bool vst_check_cvlan = false; + bool vst_push_cvlan = false; + /* The ingress acl table contains 4 groups + * (2 active rules at the same time - + * 1 allow rule from one of the first 3 groups. + * 1 drop rule from the last group): + * 1)Allow untagged traffic with smac=original mac. + * 2)Allow untagged traffic. + * 3)Allow traffic with smac=original mac. + * 4)Drop all other traffic. + */ + int table_size = 4; + int dest_num = 0; + int err = 0; + u8 *smac_v; + + esw_acl_ingress_lgcy_rules_destroy(vport); + + if (vport->ingress.legacy.drop_counter) { + counter = vport->ingress.legacy.drop_counter; + } else if (MLX5_CAP_ESW_INGRESS_ACL(esw->dev, flow_counter)) { + counter = mlx5_fc_create(esw->dev, false); + if (IS_ERR(counter)) { + esw_warn(esw->dev, + "vport[%d] configure ingress drop rule counter failed\n", + vport->vport); + counter = NULL; + } + vport->ingress.legacy.drop_counter = counter; + } + + if (!vport->info.vlan && !vport->info.qos && !vport->info.spoofchk) { + esw_acl_ingress_lgcy_cleanup(esw, vport); + return 0; + } + + if (!vport->ingress.acl) { + vport->ingress.acl = esw_acl_table_create(esw, vport, + MLX5_FLOW_NAMESPACE_ESW_INGRESS, + table_size); + if (IS_ERR(vport->ingress.acl)) { + err = PTR_ERR(vport->ingress.acl); + vport->ingress.acl = NULL; + return err; + } + + err = esw_acl_ingress_lgcy_groups_create(esw, vport); + if (err) + goto out; + } + + esw_debug(esw->dev, + "vport[%d] configure ingress rules, vlan(%d) qos(%d)\n", + vport->vport, vport->info.vlan, vport->info.qos); + + spec = kvzalloc(sizeof(*spec), GFP_KERNEL); + if (!spec) { + err = -ENOMEM; + goto out; + } + + if ((vport->info.vlan || vport->info.qos)) { + if (vst_mode_steering) + vst_push_cvlan = true; + else if (!MLX5_CAP_ESW(esw->dev, vport_cvlan_insert_always)) + vst_check_cvlan = true; + } + + if (vst_check_cvlan || vport->info.spoofchk) + spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; + + /* Create ingress allow rule */ + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_ALLOW; + if (vst_push_cvlan) { + flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH; + flow_act.vlan[0].prio = vport->info.qos; + flow_act.vlan[0].vid = vport->info.vlan; + flow_act.vlan[0].ethtype = ETH_P_8021Q; + } + + if (vst_check_cvlan) + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, + outer_headers.cvlan_tag); + + if (vport->info.spoofchk) { + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, + outer_headers.smac_47_16); + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, + outer_headers.smac_15_0); + smac_v = MLX5_ADDR_OF(fte_match_param, + spec->match_value, + outer_headers.smac_47_16); + ether_addr_copy(smac_v, vport->info.mac); + } + + vport->ingress.allow_rule = mlx5_add_flow_rules(vport->ingress.acl, spec, + &flow_act, NULL, 0); + if (IS_ERR(vport->ingress.allow_rule)) { + err = PTR_ERR(vport->ingress.allow_rule); + esw_warn(esw->dev, + "vport[%d] configure ingress allow rule, err(%d)\n", + vport->vport, err); + vport->ingress.allow_rule = NULL; + goto out; + } + + if (!vst_check_cvlan && !vport->info.spoofchk) + goto out; + + memset(&flow_act, 0, sizeof(flow_act)); + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP; + /* Attach drop flow counter */ + if (counter) { + flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_COUNT; + drop_ctr_dst.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; + drop_ctr_dst.counter_id = mlx5_fc_id(counter); + dst = &drop_ctr_dst; + dest_num++; + } + vport->ingress.legacy.drop_rule = + mlx5_add_flow_rules(vport->ingress.acl, NULL, + &flow_act, dst, dest_num); + if (IS_ERR(vport->ingress.legacy.drop_rule)) { + err = PTR_ERR(vport->ingress.legacy.drop_rule); + esw_warn(esw->dev, + "vport[%d] configure ingress drop rule, err(%d)\n", + vport->vport, err); + vport->ingress.legacy.drop_rule = NULL; + goto out; + } + kvfree(spec); + return 0; + +out: + if (err) + esw_acl_ingress_lgcy_cleanup(esw, vport); + kvfree(spec); + return err; +} + +void esw_acl_ingress_lgcy_cleanup(struct mlx5_eswitch *esw, + struct mlx5_vport *vport) +{ + if (IS_ERR_OR_NULL(vport->ingress.acl)) + goto clean_drop_counter; + + esw_debug(esw->dev, "Destroy vport[%d] E-Switch ingress ACL\n", vport->vport); + + esw_acl_ingress_lgcy_rules_destroy(vport); + esw_acl_ingress_lgcy_groups_destroy(vport); + esw_acl_ingress_table_destroy(vport); + +clean_drop_counter: + if (vport->ingress.legacy.drop_counter) { + mlx5_fc_destroy(esw->dev, vport->ingress.legacy.drop_counter); + vport->ingress.legacy.drop_counter = NULL; + } +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_ofld.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_ofld.c new file mode 100644 index 000000000..db578a7e7 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_ofld.c @@ -0,0 +1,408 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2020 Mellanox Technologies Inc. All rights reserved. */ + +#include "mlx5_core.h" +#include "eswitch.h" +#include "helper.h" +#include "ofld.h" + +static bool +esw_acl_ingress_prio_tag_enabled(struct mlx5_eswitch *esw, + const struct mlx5_vport *vport) +{ + return (MLX5_CAP_GEN(esw->dev, prio_tag_required) && + mlx5_eswitch_is_vf_vport(esw, vport->vport)); +} + +static int esw_acl_ingress_prio_tag_create(struct mlx5_eswitch *esw, + struct mlx5_vport *vport) +{ + struct mlx5_flow_act flow_act = {}; + struct mlx5_flow_spec *spec; + int err = 0; + + /* For prio tag mode, there is only 1 FTEs: + * 1) Untagged packets - push prio tag VLAN and modify metadata if + * required, allow + * Unmatched traffic is allowed by default + */ + spec = kvzalloc(sizeof(*spec), GFP_KERNEL); + if (!spec) + return -ENOMEM; + + /* Untagged packets - push prio tag VLAN, allow */ + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.cvlan_tag); + MLX5_SET(fte_match_param, spec->match_value, outer_headers.cvlan_tag, 0); + spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH | + MLX5_FLOW_CONTEXT_ACTION_ALLOW; + flow_act.vlan[0].ethtype = ETH_P_8021Q; + flow_act.vlan[0].vid = 0; + flow_act.vlan[0].prio = 0; + + if (vport->ingress.offloads.modify_metadata_rule) { + flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR; + flow_act.modify_hdr = vport->ingress.offloads.modify_metadata; + } + + vport->ingress.allow_rule = mlx5_add_flow_rules(vport->ingress.acl, spec, + &flow_act, NULL, 0); + if (IS_ERR(vport->ingress.allow_rule)) { + err = PTR_ERR(vport->ingress.allow_rule); + esw_warn(esw->dev, + "vport[%d] configure ingress untagged allow rule, err(%d)\n", + vport->vport, err); + vport->ingress.allow_rule = NULL; + } + + kvfree(spec); + return err; +} + +static int esw_acl_ingress_mod_metadata_create(struct mlx5_eswitch *esw, + struct mlx5_vport *vport) +{ + u8 action[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {}; + struct mlx5_flow_act flow_act = {}; + int err = 0; + u32 key; + + key = mlx5_eswitch_get_vport_metadata_for_match(esw, vport->vport); + key >>= ESW_SOURCE_PORT_METADATA_OFFSET; + + MLX5_SET(set_action_in, action, action_type, MLX5_ACTION_TYPE_SET); + MLX5_SET(set_action_in, action, field, + MLX5_ACTION_IN_FIELD_METADATA_REG_C_0); + MLX5_SET(set_action_in, action, data, key); + MLX5_SET(set_action_in, action, offset, + ESW_SOURCE_PORT_METADATA_OFFSET); + MLX5_SET(set_action_in, action, length, + ESW_SOURCE_PORT_METADATA_BITS); + + vport->ingress.offloads.modify_metadata = + mlx5_modify_header_alloc(esw->dev, MLX5_FLOW_NAMESPACE_ESW_INGRESS, + 1, action); + if (IS_ERR(vport->ingress.offloads.modify_metadata)) { + err = PTR_ERR(vport->ingress.offloads.modify_metadata); + esw_warn(esw->dev, + "failed to alloc modify header for vport %d ingress acl (%d)\n", + vport->vport, err); + return err; + } + + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_MOD_HDR | MLX5_FLOW_CONTEXT_ACTION_ALLOW; + flow_act.modify_hdr = vport->ingress.offloads.modify_metadata; + flow_act.fg = vport->ingress.offloads.metadata_allmatch_grp; + vport->ingress.offloads.modify_metadata_rule = + mlx5_add_flow_rules(vport->ingress.acl, + NULL, &flow_act, NULL, 0); + if (IS_ERR(vport->ingress.offloads.modify_metadata_rule)) { + err = PTR_ERR(vport->ingress.offloads.modify_metadata_rule); + esw_warn(esw->dev, + "failed to add setting metadata rule for vport %d ingress acl, err(%d)\n", + vport->vport, err); + mlx5_modify_header_dealloc(esw->dev, vport->ingress.offloads.modify_metadata); + vport->ingress.offloads.modify_metadata_rule = NULL; + } + return err; +} + +static void esw_acl_ingress_mod_metadata_destroy(struct mlx5_eswitch *esw, + struct mlx5_vport *vport) +{ + if (!vport->ingress.offloads.modify_metadata_rule) + return; + + mlx5_del_flow_rules(vport->ingress.offloads.modify_metadata_rule); + mlx5_modify_header_dealloc(esw->dev, vport->ingress.offloads.modify_metadata); + vport->ingress.offloads.modify_metadata_rule = NULL; +} + +static int esw_acl_ingress_src_port_drop_create(struct mlx5_eswitch *esw, + struct mlx5_vport *vport) +{ + struct mlx5_flow_act flow_act = {}; + struct mlx5_flow_handle *flow_rule; + int err = 0; + + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP; + flow_act.fg = vport->ingress.offloads.drop_grp; + flow_rule = mlx5_add_flow_rules(vport->ingress.acl, NULL, &flow_act, NULL, 0); + if (IS_ERR(flow_rule)) { + err = PTR_ERR(flow_rule); + goto out; + } + + vport->ingress.offloads.drop_rule = flow_rule; +out: + return err; +} + +static void esw_acl_ingress_src_port_drop_destroy(struct mlx5_eswitch *esw, + struct mlx5_vport *vport) +{ + if (!vport->ingress.offloads.drop_rule) + return; + + mlx5_del_flow_rules(vport->ingress.offloads.drop_rule); + vport->ingress.offloads.drop_rule = NULL; +} + +static int esw_acl_ingress_ofld_rules_create(struct mlx5_eswitch *esw, + struct mlx5_vport *vport) +{ + int err; + + if (mlx5_eswitch_vport_match_metadata_enabled(esw)) { + err = esw_acl_ingress_mod_metadata_create(esw, vport); + if (err) { + esw_warn(esw->dev, + "vport(%d) create ingress modify metadata, err(%d)\n", + vport->vport, err); + return err; + } + } + + if (esw_acl_ingress_prio_tag_enabled(esw, vport)) { + err = esw_acl_ingress_prio_tag_create(esw, vport); + if (err) { + esw_warn(esw->dev, + "vport(%d) create ingress prio tag rule, err(%d)\n", + vport->vport, err); + goto prio_tag_err; + } + } + + return 0; + +prio_tag_err: + esw_acl_ingress_mod_metadata_destroy(esw, vport); + return err; +} + +static void esw_acl_ingress_ofld_rules_destroy(struct mlx5_eswitch *esw, + struct mlx5_vport *vport) +{ + esw_acl_ingress_allow_rule_destroy(vport); + esw_acl_ingress_mod_metadata_destroy(esw, vport); + esw_acl_ingress_src_port_drop_destroy(esw, vport); +} + +static int esw_acl_ingress_ofld_groups_create(struct mlx5_eswitch *esw, + struct mlx5_vport *vport) +{ + int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + struct mlx5_flow_group *g; + void *match_criteria; + u32 *flow_group_in; + u32 flow_index = 0; + int ret = 0; + + flow_group_in = kvzalloc(inlen, GFP_KERNEL); + if (!flow_group_in) + return -ENOMEM; + + if (vport->vport == MLX5_VPORT_UPLINK) { + /* This group can hold an FTE to drop all traffic. + * Need in case LAG is enabled. + */ + MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, flow_index); + MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, flow_index); + + g = mlx5_create_flow_group(vport->ingress.acl, flow_group_in); + if (IS_ERR(g)) { + ret = PTR_ERR(g); + esw_warn(esw->dev, "vport[%d] ingress create drop flow group, err(%d)\n", + vport->vport, ret); + goto drop_err; + } + vport->ingress.offloads.drop_grp = g; + flow_index++; + } + + if (esw_acl_ingress_prio_tag_enabled(esw, vport)) { + /* This group is to hold FTE to match untagged packets when prio_tag + * is enabled. + */ + memset(flow_group_in, 0, inlen); + 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_OUTER_HEADERS); + MLX5_SET_TO_ONES(fte_match_param, match_criteria, outer_headers.cvlan_tag); + MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, flow_index); + MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, flow_index); + + g = mlx5_create_flow_group(vport->ingress.acl, flow_group_in); + if (IS_ERR(g)) { + ret = PTR_ERR(g); + esw_warn(esw->dev, "vport[%d] ingress create untagged flow group, err(%d)\n", + vport->vport, ret); + goto prio_tag_err; + } + vport->ingress.offloads.metadata_prio_tag_grp = g; + flow_index++; + } + + if (mlx5_eswitch_vport_match_metadata_enabled(esw)) { + /* This group holds an FTE with no match to add metadata for + * tagged packets if prio-tag is enabled, or for all untagged + * traffic in case prio-tag is disabled. + */ + memset(flow_group_in, 0, inlen); + MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, flow_index); + MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, flow_index); + + g = mlx5_create_flow_group(vport->ingress.acl, flow_group_in); + if (IS_ERR(g)) { + ret = PTR_ERR(g); + esw_warn(esw->dev, "vport[%d] ingress create drop flow group, err(%d)\n", + vport->vport, ret); + goto metadata_err; + } + vport->ingress.offloads.metadata_allmatch_grp = g; + } + + kvfree(flow_group_in); + return 0; + +metadata_err: + if (!IS_ERR_OR_NULL(vport->ingress.offloads.metadata_prio_tag_grp)) { + mlx5_destroy_flow_group(vport->ingress.offloads.metadata_prio_tag_grp); + vport->ingress.offloads.metadata_prio_tag_grp = NULL; + } +prio_tag_err: + if (!IS_ERR_OR_NULL(vport->ingress.offloads.drop_grp)) { + mlx5_destroy_flow_group(vport->ingress.offloads.drop_grp); + vport->ingress.offloads.drop_grp = NULL; + } +drop_err: + kvfree(flow_group_in); + return ret; +} + +static void esw_acl_ingress_ofld_groups_destroy(struct mlx5_vport *vport) +{ + if (vport->ingress.offloads.metadata_allmatch_grp) { + mlx5_destroy_flow_group(vport->ingress.offloads.metadata_allmatch_grp); + vport->ingress.offloads.metadata_allmatch_grp = NULL; + } + + if (vport->ingress.offloads.metadata_prio_tag_grp) { + mlx5_destroy_flow_group(vport->ingress.offloads.metadata_prio_tag_grp); + vport->ingress.offloads.metadata_prio_tag_grp = NULL; + } + + if (vport->ingress.offloads.drop_grp) { + mlx5_destroy_flow_group(vport->ingress.offloads.drop_grp); + vport->ingress.offloads.drop_grp = NULL; + } +} + +int esw_acl_ingress_ofld_setup(struct mlx5_eswitch *esw, + struct mlx5_vport *vport) +{ + int num_ftes = 0; + int err; + + if (!mlx5_eswitch_vport_match_metadata_enabled(esw) && + !esw_acl_ingress_prio_tag_enabled(esw, vport)) + return 0; + + esw_acl_ingress_allow_rule_destroy(vport); + + if (mlx5_eswitch_vport_match_metadata_enabled(esw)) + num_ftes++; + if (vport->vport == MLX5_VPORT_UPLINK) + num_ftes++; + if (esw_acl_ingress_prio_tag_enabled(esw, vport)) + num_ftes++; + + vport->ingress.acl = esw_acl_table_create(esw, vport, + MLX5_FLOW_NAMESPACE_ESW_INGRESS, + num_ftes); + if (IS_ERR(vport->ingress.acl)) { + err = PTR_ERR(vport->ingress.acl); + vport->ingress.acl = NULL; + return err; + } + + err = esw_acl_ingress_ofld_groups_create(esw, vport); + if (err) + goto group_err; + + esw_debug(esw->dev, + "vport[%d] configure ingress rules\n", vport->vport); + + err = esw_acl_ingress_ofld_rules_create(esw, vport); + if (err) + goto rules_err; + + return 0; + +rules_err: + esw_acl_ingress_ofld_groups_destroy(vport); +group_err: + esw_acl_ingress_table_destroy(vport); + return err; +} + +void esw_acl_ingress_ofld_cleanup(struct mlx5_eswitch *esw, + struct mlx5_vport *vport) +{ + esw_acl_ingress_ofld_rules_destroy(esw, vport); + esw_acl_ingress_ofld_groups_destroy(vport); + esw_acl_ingress_table_destroy(vport); +} + +/* Caller must hold rtnl_lock */ +int mlx5_esw_acl_ingress_vport_bond_update(struct mlx5_eswitch *esw, u16 vport_num, + u32 metadata) +{ + struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num); + int err; + + if (WARN_ON_ONCE(IS_ERR(vport))) { + esw_warn(esw->dev, "vport(%d) invalid!\n", vport_num); + return PTR_ERR(vport); + } + + esw_acl_ingress_ofld_rules_destroy(esw, vport); + + vport->metadata = metadata ? metadata : vport->default_metadata; + + /* Recreate ingress acl rules with vport->metadata */ + err = esw_acl_ingress_ofld_rules_create(esw, vport); + if (err) + goto out; + + return 0; + +out: + vport->metadata = vport->default_metadata; + return err; +} + +int mlx5_esw_acl_ingress_vport_drop_rule_create(struct mlx5_eswitch *esw, u16 vport_num) +{ + struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num); + + if (IS_ERR(vport)) { + esw_warn(esw->dev, "vport(%d) invalid!\n", vport_num); + return PTR_ERR(vport); + } + + return esw_acl_ingress_src_port_drop_create(esw, vport); +} + +void mlx5_esw_acl_ingress_vport_drop_rule_destroy(struct mlx5_eswitch *esw, u16 vport_num) +{ + struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num); + + if (WARN_ON_ONCE(IS_ERR(vport))) { + esw_warn(esw->dev, "vport(%d) invalid!\n", vport_num); + return; + } + + esw_acl_ingress_src_port_drop_destroy(esw, vport); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/lgcy.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/lgcy.h new file mode 100644 index 000000000..44c152da3 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/lgcy.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2020 Mellanox Technologies Inc. All rights reserved. */ + +#ifndef __MLX5_ESWITCH_ACL_LGCY_H__ +#define __MLX5_ESWITCH_ACL_LGCY_H__ + +#include "eswitch.h" + +/* Eswitch acl egress external APIs */ +int esw_acl_egress_lgcy_setup(struct mlx5_eswitch *esw, struct mlx5_vport *vport); +void esw_acl_egress_lgcy_cleanup(struct mlx5_eswitch *esw, struct mlx5_vport *vport); + +/* Eswitch acl ingress external APIs */ +int esw_acl_ingress_lgcy_setup(struct mlx5_eswitch *esw, struct mlx5_vport *vport); +void esw_acl_ingress_lgcy_cleanup(struct mlx5_eswitch *esw, struct mlx5_vport *vport); + +#endif /* __MLX5_ESWITCH_ACL_LGCY_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ofld.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ofld.h new file mode 100644 index 000000000..11d3d3978 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ofld.h @@ -0,0 +1,44 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2020 Mellanox Technologies Inc. All rights reserved. */ + +#ifndef __MLX5_ESWITCH_ACL_OFLD_H__ +#define __MLX5_ESWITCH_ACL_OFLD_H__ + +#include "eswitch.h" + +#ifdef CONFIG_MLX5_ESWITCH +/* Eswitch acl egress external APIs */ +int esw_acl_egress_ofld_setup(struct mlx5_eswitch *esw, struct mlx5_vport *vport); +void esw_acl_egress_ofld_cleanup(struct mlx5_vport *vport); +int mlx5_esw_acl_egress_vport_bond(struct mlx5_eswitch *esw, u16 active_vport_num, + u16 passive_vport_num); +int mlx5_esw_acl_egress_vport_unbond(struct mlx5_eswitch *esw, u16 vport_num); + +static inline bool mlx5_esw_acl_egress_fwd2vport_supported(struct mlx5_eswitch *esw) +{ + return esw && esw->mode == MLX5_ESWITCH_OFFLOADS && + mlx5_eswitch_vport_match_metadata_enabled(esw) && + MLX5_CAP_ESW_FLOWTABLE(esw->dev, egress_acl_forward_to_vport); +} + +/* Eswitch acl ingress external APIs */ +int esw_acl_ingress_ofld_setup(struct mlx5_eswitch *esw, struct mlx5_vport *vport); +void esw_acl_ingress_ofld_cleanup(struct mlx5_eswitch *esw, struct mlx5_vport *vport); +int mlx5_esw_acl_ingress_vport_bond_update(struct mlx5_eswitch *esw, u16 vport_num, + u32 metadata); +void mlx5_esw_acl_ingress_vport_drop_rule_destroy(struct mlx5_eswitch *esw, u16 vport_num); +int mlx5_esw_acl_ingress_vport_drop_rule_create(struct mlx5_eswitch *esw, u16 vport_num); + +#else /* CONFIG_MLX5_ESWITCH */ +static void +mlx5_esw_acl_ingress_vport_drop_rule_destroy(struct mlx5_eswitch *esw, + u16 vport_num) +{} + +static int mlx5_esw_acl_ingress_vport_drop_rule_create(struct mlx5_eswitch *esw, + u16 vport_num) +{ + return 0; +} +#endif /* CONFIG_MLX5_ESWITCH */ +#endif /* __MLX5_ESWITCH_ACL_OFLD_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c new file mode 100644 index 000000000..d0b2676c3 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c @@ -0,0 +1,1853 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2021 Mellanox Technologies. */ + +#include <linux/build_bug.h> +#include <linux/list.h> +#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" +#define CREATE_TRACE_POINTS +#include "diag/bridge_tracepoint.h" + +#define MLX5_ESW_BRIDGE_INGRESS_TABLE_VLAN_GRP_SIZE 12000 +#define MLX5_ESW_BRIDGE_INGRESS_TABLE_UNTAGGED_GRP_SIZE 16000 +#define MLX5_ESW_BRIDGE_INGRESS_TABLE_VLAN_GRP_IDX_FROM 0 +#define MLX5_ESW_BRIDGE_INGRESS_TABLE_VLAN_GRP_IDX_TO \ + (MLX5_ESW_BRIDGE_INGRESS_TABLE_VLAN_GRP_SIZE - 1) +#define MLX5_ESW_BRIDGE_INGRESS_TABLE_VLAN_FILTER_GRP_IDX_FROM \ + (MLX5_ESW_BRIDGE_INGRESS_TABLE_VLAN_GRP_IDX_TO + 1) +#define MLX5_ESW_BRIDGE_INGRESS_TABLE_VLAN_FILTER_GRP_IDX_TO \ + (MLX5_ESW_BRIDGE_INGRESS_TABLE_VLAN_FILTER_GRP_IDX_FROM + \ + MLX5_ESW_BRIDGE_INGRESS_TABLE_VLAN_GRP_SIZE - 1) +#define MLX5_ESW_BRIDGE_INGRESS_TABLE_QINQ_GRP_IDX_FROM \ + (MLX5_ESW_BRIDGE_INGRESS_TABLE_VLAN_FILTER_GRP_IDX_TO + 1) +#define MLX5_ESW_BRIDGE_INGRESS_TABLE_QINQ_GRP_IDX_TO \ + (MLX5_ESW_BRIDGE_INGRESS_TABLE_QINQ_GRP_IDX_FROM + \ + MLX5_ESW_BRIDGE_INGRESS_TABLE_VLAN_GRP_SIZE - 1) +#define MLX5_ESW_BRIDGE_INGRESS_TABLE_QINQ_FILTER_GRP_IDX_FROM \ + (MLX5_ESW_BRIDGE_INGRESS_TABLE_QINQ_GRP_IDX_TO + 1) +#define MLX5_ESW_BRIDGE_INGRESS_TABLE_QINQ_FILTER_GRP_IDX_TO \ + (MLX5_ESW_BRIDGE_INGRESS_TABLE_QINQ_FILTER_GRP_IDX_FROM + \ + MLX5_ESW_BRIDGE_INGRESS_TABLE_VLAN_GRP_SIZE - 1) +#define MLX5_ESW_BRIDGE_INGRESS_TABLE_MAC_GRP_IDX_FROM \ + (MLX5_ESW_BRIDGE_INGRESS_TABLE_QINQ_FILTER_GRP_IDX_TO + 1) +#define MLX5_ESW_BRIDGE_INGRESS_TABLE_MAC_GRP_IDX_TO \ + (MLX5_ESW_BRIDGE_INGRESS_TABLE_MAC_GRP_IDX_FROM + \ + MLX5_ESW_BRIDGE_INGRESS_TABLE_UNTAGGED_GRP_SIZE - 1) +#define MLX5_ESW_BRIDGE_INGRESS_TABLE_SIZE \ + (MLX5_ESW_BRIDGE_INGRESS_TABLE_MAC_GRP_IDX_TO + 1) +static_assert(MLX5_ESW_BRIDGE_INGRESS_TABLE_SIZE == 64000); + +#define MLX5_ESW_BRIDGE_EGRESS_TABLE_VLAN_GRP_SIZE 16000 +#define MLX5_ESW_BRIDGE_EGRESS_TABLE_MAC_GRP_SIZE (32000 - 1) +#define MLX5_ESW_BRIDGE_EGRESS_TABLE_VLAN_GRP_IDX_FROM 0 +#define MLX5_ESW_BRIDGE_EGRESS_TABLE_VLAN_GRP_IDX_TO \ + (MLX5_ESW_BRIDGE_EGRESS_TABLE_VLAN_GRP_SIZE - 1) +#define MLX5_ESW_BRIDGE_EGRESS_TABLE_QINQ_GRP_IDX_FROM \ + (MLX5_ESW_BRIDGE_EGRESS_TABLE_VLAN_GRP_IDX_TO + 1) +#define MLX5_ESW_BRIDGE_EGRESS_TABLE_QINQ_GRP_IDX_TO \ + (MLX5_ESW_BRIDGE_EGRESS_TABLE_QINQ_GRP_IDX_FROM + \ + MLX5_ESW_BRIDGE_EGRESS_TABLE_VLAN_GRP_SIZE - 1) +#define MLX5_ESW_BRIDGE_EGRESS_TABLE_MAC_GRP_IDX_FROM \ + (MLX5_ESW_BRIDGE_EGRESS_TABLE_QINQ_GRP_IDX_TO + 1) +#define MLX5_ESW_BRIDGE_EGRESS_TABLE_MAC_GRP_IDX_TO \ + (MLX5_ESW_BRIDGE_EGRESS_TABLE_MAC_GRP_IDX_FROM + \ + MLX5_ESW_BRIDGE_EGRESS_TABLE_MAC_GRP_SIZE - 1) +#define MLX5_ESW_BRIDGE_EGRESS_TABLE_MISS_GRP_IDX_FROM \ + (MLX5_ESW_BRIDGE_EGRESS_TABLE_MAC_GRP_IDX_TO + 1) +#define MLX5_ESW_BRIDGE_EGRESS_TABLE_MISS_GRP_IDX_TO \ + MLX5_ESW_BRIDGE_EGRESS_TABLE_MISS_GRP_IDX_FROM +#define MLX5_ESW_BRIDGE_EGRESS_TABLE_SIZE \ + (MLX5_ESW_BRIDGE_EGRESS_TABLE_MISS_GRP_IDX_TO + 1) +static_assert(MLX5_ESW_BRIDGE_EGRESS_TABLE_SIZE == 64000); + +#define MLX5_ESW_BRIDGE_SKIP_TABLE_SIZE 0 + +enum { + MLX5_ESW_BRIDGE_LEVEL_INGRESS_TABLE, + MLX5_ESW_BRIDGE_LEVEL_EGRESS_TABLE, + MLX5_ESW_BRIDGE_LEVEL_SKIP_TABLE, +}; + +static const struct rhashtable_params fdb_ht_params = { + .key_offset = offsetof(struct mlx5_esw_bridge_fdb_entry, key), + .key_len = sizeof(struct mlx5_esw_bridge_fdb_key), + .head_offset = offsetof(struct mlx5_esw_bridge_fdb_entry, ht_node), + .automatic_shrinking = true, +}; + +enum { + MLX5_ESW_BRIDGE_VLAN_FILTERING_FLAG = BIT(0), +}; + +struct mlx5_esw_bridge { + int ifindex; + int refcnt; + struct list_head list; + struct mlx5_esw_bridge_offloads *br_offloads; + + struct list_head fdb_list; + struct rhashtable fdb_ht; + + struct mlx5_flow_table *egress_ft; + struct mlx5_flow_group *egress_vlan_fg; + struct mlx5_flow_group *egress_qinq_fg; + struct mlx5_flow_group *egress_mac_fg; + struct mlx5_flow_group *egress_miss_fg; + struct mlx5_pkt_reformat *egress_miss_pkt_reformat; + struct mlx5_flow_handle *egress_miss_handle; + unsigned long ageing_time; + u32 flags; + u16 vlan_proto; +}; + +static void +mlx5_esw_bridge_fdb_offload_notify(struct net_device *dev, const unsigned char *addr, u16 vid, + unsigned long val) +{ + struct switchdev_notifier_fdb_info send_info = {}; + + send_info.addr = addr; + send_info.vid = vid; + send_info.offloaded = true; + 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 bool mlx5_esw_bridge_pkt_reformat_vlan_pop_supported(struct mlx5_eswitch *esw) +{ + return BIT(MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, reformat_remove)) && + MLX5_CAP_GEN_2(esw->dev, max_reformat_remove_size) >= sizeof(struct vlan_hdr) && + MLX5_CAP_GEN_2(esw->dev, max_reformat_remove_offset) >= + offsetof(struct vlan_ethhdr, h_vlan_proto); +} + +static struct mlx5_pkt_reformat * +mlx5_esw_bridge_pkt_reformat_vlan_pop_create(struct mlx5_eswitch *esw) +{ + struct mlx5_pkt_reformat_params reformat_params = {}; + + reformat_params.type = MLX5_REFORMAT_TYPE_REMOVE_HDR; + reformat_params.param_0 = MLX5_REFORMAT_CONTEXT_ANCHOR_MAC_START; + reformat_params.param_1 = offsetof(struct vlan_ethhdr, h_vlan_proto); + reformat_params.size = sizeof(struct vlan_hdr); + return mlx5_packet_reformat_alloc(esw->dev, &reformat_params, MLX5_FLOW_NAMESPACE_FDB); +} + +static struct mlx5_flow_table * +mlx5_esw_bridge_table_create(int max_fte, u32 level, struct mlx5_eswitch *esw) +{ + struct mlx5_flow_table_attr ft_attr = {}; + struct mlx5_core_dev *dev = esw->dev; + struct mlx5_flow_namespace *ns; + struct mlx5_flow_table *fdb; + + ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_FDB); + if (!ns) { + esw_warn(dev, "Failed to get FDB namespace\n"); + return ERR_PTR(-ENOENT); + } + + ft_attr.flags = MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT; + ft_attr.max_fte = max_fte; + ft_attr.level = level; + ft_attr.prio = FDB_BR_OFFLOAD; + fdb = mlx5_create_flow_table(ns, &ft_attr); + if (IS_ERR(fdb)) + esw_warn(dev, "Failed to create bridge FDB Table (err=%ld)\n", PTR_ERR(fdb)); + + return fdb; +} + +static struct mlx5_flow_group * +mlx5_esw_bridge_ingress_vlan_proto_fg_create(unsigned int from, unsigned int to, u16 vlan_proto, + struct mlx5_eswitch *esw, + struct mlx5_flow_table *ingress_ft) +{ + int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + struct mlx5_flow_group *fg; + u32 *in, *match; + + in = kvzalloc(inlen, GFP_KERNEL); + if (!in) + return ERR_PTR(-ENOMEM); + + MLX5_SET(create_flow_group_in, in, match_criteria_enable, + MLX5_MATCH_OUTER_HEADERS | MLX5_MATCH_MISC_PARAMETERS_2); + match = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria); + + MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.smac_47_16); + MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.smac_15_0); + if (vlan_proto == ETH_P_8021Q) + MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.cvlan_tag); + else if (vlan_proto == ETH_P_8021AD) + MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.svlan_tag); + MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.first_vid); + + MLX5_SET(fte_match_param, match, misc_parameters_2.metadata_reg_c_0, + mlx5_eswitch_get_vport_metadata_mask()); + + MLX5_SET(create_flow_group_in, in, start_flow_index, from); + MLX5_SET(create_flow_group_in, in, end_flow_index, to); + + fg = mlx5_create_flow_group(ingress_ft, in); + kvfree(in); + if (IS_ERR(fg)) + esw_warn(esw->dev, + "Failed to create VLAN(proto=%x) flow group for bridge ingress table (err=%ld)\n", + vlan_proto, PTR_ERR(fg)); + + return fg; +} + +static struct mlx5_flow_group * +mlx5_esw_bridge_ingress_vlan_fg_create(struct mlx5_eswitch *esw, + struct mlx5_flow_table *ingress_ft) +{ + unsigned int from = MLX5_ESW_BRIDGE_INGRESS_TABLE_VLAN_GRP_IDX_FROM; + unsigned int to = MLX5_ESW_BRIDGE_INGRESS_TABLE_VLAN_GRP_IDX_TO; + + return mlx5_esw_bridge_ingress_vlan_proto_fg_create(from, to, ETH_P_8021Q, esw, ingress_ft); +} + +static struct mlx5_flow_group * +mlx5_esw_bridge_ingress_qinq_fg_create(struct mlx5_eswitch *esw, + struct mlx5_flow_table *ingress_ft) +{ + unsigned int from = MLX5_ESW_BRIDGE_INGRESS_TABLE_QINQ_GRP_IDX_FROM; + unsigned int to = MLX5_ESW_BRIDGE_INGRESS_TABLE_QINQ_GRP_IDX_TO; + + return mlx5_esw_bridge_ingress_vlan_proto_fg_create(from, to, ETH_P_8021AD, esw, + ingress_ft); +} + +static struct mlx5_flow_group * +mlx5_esw_bridge_ingress_vlan_proto_filter_fg_create(unsigned int from, unsigned int to, + u16 vlan_proto, struct mlx5_eswitch *esw, + struct mlx5_flow_table *ingress_ft) +{ + int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + struct mlx5_flow_group *fg; + u32 *in, *match; + + in = kvzalloc(inlen, GFP_KERNEL); + if (!in) + return ERR_PTR(-ENOMEM); + + MLX5_SET(create_flow_group_in, in, match_criteria_enable, + MLX5_MATCH_OUTER_HEADERS | MLX5_MATCH_MISC_PARAMETERS_2); + match = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria); + + MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.smac_47_16); + MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.smac_15_0); + if (vlan_proto == ETH_P_8021Q) + MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.cvlan_tag); + else if (vlan_proto == ETH_P_8021AD) + MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.svlan_tag); + MLX5_SET(fte_match_param, match, misc_parameters_2.metadata_reg_c_0, + mlx5_eswitch_get_vport_metadata_mask()); + + MLX5_SET(create_flow_group_in, in, start_flow_index, from); + MLX5_SET(create_flow_group_in, in, end_flow_index, to); + + fg = mlx5_create_flow_group(ingress_ft, in); + if (IS_ERR(fg)) + esw_warn(esw->dev, + "Failed to create bridge ingress table VLAN filter flow group (err=%ld)\n", + PTR_ERR(fg)); + kvfree(in); + return fg; +} + +static struct mlx5_flow_group * +mlx5_esw_bridge_ingress_vlan_filter_fg_create(struct mlx5_eswitch *esw, + struct mlx5_flow_table *ingress_ft) +{ + unsigned int from = MLX5_ESW_BRIDGE_INGRESS_TABLE_VLAN_FILTER_GRP_IDX_FROM; + unsigned int to = MLX5_ESW_BRIDGE_INGRESS_TABLE_VLAN_FILTER_GRP_IDX_TO; + + return mlx5_esw_bridge_ingress_vlan_proto_filter_fg_create(from, to, ETH_P_8021Q, esw, + ingress_ft); +} + +static struct mlx5_flow_group * +mlx5_esw_bridge_ingress_qinq_filter_fg_create(struct mlx5_eswitch *esw, + struct mlx5_flow_table *ingress_ft) +{ + unsigned int from = MLX5_ESW_BRIDGE_INGRESS_TABLE_QINQ_FILTER_GRP_IDX_FROM; + unsigned int to = MLX5_ESW_BRIDGE_INGRESS_TABLE_QINQ_FILTER_GRP_IDX_TO; + + return mlx5_esw_bridge_ingress_vlan_proto_filter_fg_create(from, to, ETH_P_8021AD, esw, + ingress_ft); +} + +static struct mlx5_flow_group * +mlx5_esw_bridge_ingress_mac_fg_create(struct mlx5_eswitch *esw, struct mlx5_flow_table *ingress_ft) +{ + int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + struct mlx5_flow_group *fg; + u32 *in, *match; + + in = kvzalloc(inlen, GFP_KERNEL); + if (!in) + return ERR_PTR(-ENOMEM); + + MLX5_SET(create_flow_group_in, in, match_criteria_enable, + MLX5_MATCH_OUTER_HEADERS | MLX5_MATCH_MISC_PARAMETERS_2); + match = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria); + + MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.smac_47_16); + MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.smac_15_0); + + MLX5_SET(fte_match_param, match, misc_parameters_2.metadata_reg_c_0, + mlx5_eswitch_get_vport_metadata_mask()); + + MLX5_SET(create_flow_group_in, in, start_flow_index, + MLX5_ESW_BRIDGE_INGRESS_TABLE_MAC_GRP_IDX_FROM); + MLX5_SET(create_flow_group_in, in, end_flow_index, + MLX5_ESW_BRIDGE_INGRESS_TABLE_MAC_GRP_IDX_TO); + + fg = mlx5_create_flow_group(ingress_ft, in); + if (IS_ERR(fg)) + esw_warn(esw->dev, + "Failed to create MAC flow group for bridge ingress table (err=%ld)\n", + PTR_ERR(fg)); + + kvfree(in); + return fg; +} + +static struct mlx5_flow_group * +mlx5_esw_bridge_egress_vlan_proto_fg_create(unsigned int from, unsigned int to, u16 vlan_proto, + struct mlx5_eswitch *esw, + struct mlx5_flow_table *egress_ft) +{ + int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + struct mlx5_flow_group *fg; + u32 *in, *match; + + in = kvzalloc(inlen, GFP_KERNEL); + if (!in) + return ERR_PTR(-ENOMEM); + + MLX5_SET(create_flow_group_in, in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS); + match = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria); + + MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.dmac_47_16); + MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.dmac_15_0); + if (vlan_proto == ETH_P_8021Q) + MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.cvlan_tag); + else if (vlan_proto == ETH_P_8021AD) + MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.svlan_tag); + MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.first_vid); + + MLX5_SET(create_flow_group_in, in, start_flow_index, from); + MLX5_SET(create_flow_group_in, in, end_flow_index, to); + + fg = mlx5_create_flow_group(egress_ft, in); + if (IS_ERR(fg)) + esw_warn(esw->dev, + "Failed to create VLAN flow group for bridge egress table (err=%ld)\n", + PTR_ERR(fg)); + kvfree(in); + return fg; +} + +static struct mlx5_flow_group * +mlx5_esw_bridge_egress_vlan_fg_create(struct mlx5_eswitch *esw, struct mlx5_flow_table *egress_ft) +{ + unsigned int from = MLX5_ESW_BRIDGE_EGRESS_TABLE_VLAN_GRP_IDX_FROM; + unsigned int to = MLX5_ESW_BRIDGE_EGRESS_TABLE_VLAN_GRP_IDX_TO; + + return mlx5_esw_bridge_egress_vlan_proto_fg_create(from, to, ETH_P_8021Q, esw, egress_ft); +} + +static struct mlx5_flow_group * +mlx5_esw_bridge_egress_qinq_fg_create(struct mlx5_eswitch *esw, + struct mlx5_flow_table *egress_ft) +{ + unsigned int from = MLX5_ESW_BRIDGE_EGRESS_TABLE_QINQ_GRP_IDX_FROM; + unsigned int to = MLX5_ESW_BRIDGE_EGRESS_TABLE_QINQ_GRP_IDX_TO; + + return mlx5_esw_bridge_egress_vlan_proto_fg_create(from, to, ETH_P_8021AD, esw, egress_ft); +} + +static struct mlx5_flow_group * +mlx5_esw_bridge_egress_mac_fg_create(struct mlx5_eswitch *esw, struct mlx5_flow_table *egress_ft) +{ + int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + struct mlx5_flow_group *fg; + u32 *in, *match; + + in = kvzalloc(inlen, GFP_KERNEL); + if (!in) + return ERR_PTR(-ENOMEM); + + MLX5_SET(create_flow_group_in, in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS); + match = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria); + + MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.dmac_47_16); + MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.dmac_15_0); + + MLX5_SET(create_flow_group_in, in, start_flow_index, + MLX5_ESW_BRIDGE_EGRESS_TABLE_MAC_GRP_IDX_FROM); + MLX5_SET(create_flow_group_in, in, end_flow_index, + MLX5_ESW_BRIDGE_EGRESS_TABLE_MAC_GRP_IDX_TO); + + fg = mlx5_create_flow_group(egress_ft, in); + if (IS_ERR(fg)) + esw_warn(esw->dev, + "Failed to create bridge egress table MAC flow group (err=%ld)\n", + PTR_ERR(fg)); + kvfree(in); + return fg; +} + +static struct mlx5_flow_group * +mlx5_esw_bridge_egress_miss_fg_create(struct mlx5_eswitch *esw, struct mlx5_flow_table *egress_ft) +{ + int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + struct mlx5_flow_group *fg; + u32 *in, *match; + + in = kvzalloc(inlen, GFP_KERNEL); + if (!in) + return ERR_PTR(-ENOMEM); + + MLX5_SET(create_flow_group_in, in, match_criteria_enable, MLX5_MATCH_MISC_PARAMETERS_2); + match = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria); + + MLX5_SET(fte_match_param, match, misc_parameters_2.metadata_reg_c_1, ESW_TUN_MASK); + + MLX5_SET(create_flow_group_in, in, start_flow_index, + MLX5_ESW_BRIDGE_EGRESS_TABLE_MISS_GRP_IDX_FROM); + MLX5_SET(create_flow_group_in, in, end_flow_index, + MLX5_ESW_BRIDGE_EGRESS_TABLE_MISS_GRP_IDX_TO); + + fg = mlx5_create_flow_group(egress_ft, in); + if (IS_ERR(fg)) + esw_warn(esw->dev, + "Failed to create bridge egress table miss flow group (err=%ld)\n", + PTR_ERR(fg)); + kvfree(in); + return fg; +} + +static int +mlx5_esw_bridge_ingress_table_init(struct mlx5_esw_bridge_offloads *br_offloads) +{ + struct mlx5_flow_group *mac_fg, *qinq_filter_fg, *qinq_fg, *vlan_filter_fg, *vlan_fg; + struct mlx5_flow_table *ingress_ft, *skip_ft; + struct mlx5_eswitch *esw = br_offloads->esw; + int err; + + if (!mlx5_eswitch_vport_match_metadata_enabled(esw)) + return -EOPNOTSUPP; + + ingress_ft = mlx5_esw_bridge_table_create(MLX5_ESW_BRIDGE_INGRESS_TABLE_SIZE, + MLX5_ESW_BRIDGE_LEVEL_INGRESS_TABLE, + esw); + if (IS_ERR(ingress_ft)) + return PTR_ERR(ingress_ft); + + skip_ft = mlx5_esw_bridge_table_create(MLX5_ESW_BRIDGE_SKIP_TABLE_SIZE, + MLX5_ESW_BRIDGE_LEVEL_SKIP_TABLE, + esw); + if (IS_ERR(skip_ft)) { + err = PTR_ERR(skip_ft); + goto err_skip_tbl; + } + + vlan_fg = mlx5_esw_bridge_ingress_vlan_fg_create(esw, ingress_ft); + if (IS_ERR(vlan_fg)) { + err = PTR_ERR(vlan_fg); + goto err_vlan_fg; + } + + vlan_filter_fg = mlx5_esw_bridge_ingress_vlan_filter_fg_create(esw, ingress_ft); + if (IS_ERR(vlan_filter_fg)) { + err = PTR_ERR(vlan_filter_fg); + goto err_vlan_filter_fg; + } + + qinq_fg = mlx5_esw_bridge_ingress_qinq_fg_create(esw, ingress_ft); + if (IS_ERR(qinq_fg)) { + err = PTR_ERR(qinq_fg); + goto err_qinq_fg; + } + + qinq_filter_fg = mlx5_esw_bridge_ingress_qinq_filter_fg_create(esw, ingress_ft); + if (IS_ERR(qinq_filter_fg)) { + err = PTR_ERR(qinq_filter_fg); + goto err_qinq_filter_fg; + } + + mac_fg = mlx5_esw_bridge_ingress_mac_fg_create(esw, ingress_ft); + if (IS_ERR(mac_fg)) { + err = PTR_ERR(mac_fg); + goto err_mac_fg; + } + + br_offloads->ingress_ft = ingress_ft; + br_offloads->skip_ft = skip_ft; + br_offloads->ingress_vlan_fg = vlan_fg; + br_offloads->ingress_vlan_filter_fg = vlan_filter_fg; + br_offloads->ingress_qinq_fg = qinq_fg; + br_offloads->ingress_qinq_filter_fg = qinq_filter_fg; + br_offloads->ingress_mac_fg = mac_fg; + return 0; + +err_mac_fg: + mlx5_destroy_flow_group(qinq_filter_fg); +err_qinq_filter_fg: + mlx5_destroy_flow_group(qinq_fg); +err_qinq_fg: + mlx5_destroy_flow_group(vlan_filter_fg); +err_vlan_filter_fg: + mlx5_destroy_flow_group(vlan_fg); +err_vlan_fg: + mlx5_destroy_flow_table(skip_ft); +err_skip_tbl: + mlx5_destroy_flow_table(ingress_ft); + return err; +} + +static void +mlx5_esw_bridge_ingress_table_cleanup(struct mlx5_esw_bridge_offloads *br_offloads) +{ + mlx5_destroy_flow_group(br_offloads->ingress_mac_fg); + br_offloads->ingress_mac_fg = NULL; + mlx5_destroy_flow_group(br_offloads->ingress_qinq_filter_fg); + br_offloads->ingress_qinq_filter_fg = NULL; + mlx5_destroy_flow_group(br_offloads->ingress_qinq_fg); + br_offloads->ingress_qinq_fg = NULL; + mlx5_destroy_flow_group(br_offloads->ingress_vlan_filter_fg); + br_offloads->ingress_vlan_filter_fg = NULL; + mlx5_destroy_flow_group(br_offloads->ingress_vlan_fg); + br_offloads->ingress_vlan_fg = NULL; + mlx5_destroy_flow_table(br_offloads->skip_ft); + br_offloads->skip_ft = NULL; + mlx5_destroy_flow_table(br_offloads->ingress_ft); + br_offloads->ingress_ft = NULL; +} + +static struct mlx5_flow_handle * +mlx5_esw_bridge_egress_miss_flow_create(struct mlx5_flow_table *egress_ft, + struct mlx5_flow_table *skip_ft, + struct mlx5_pkt_reformat *pkt_reformat); + +static int +mlx5_esw_bridge_egress_table_init(struct mlx5_esw_bridge_offloads *br_offloads, + struct mlx5_esw_bridge *bridge) +{ + struct mlx5_flow_group *miss_fg = NULL, *mac_fg, *vlan_fg, *qinq_fg; + struct mlx5_pkt_reformat *miss_pkt_reformat = NULL; + struct mlx5_flow_handle *miss_handle = NULL; + struct mlx5_eswitch *esw = br_offloads->esw; + struct mlx5_flow_table *egress_ft; + int err; + + egress_ft = mlx5_esw_bridge_table_create(MLX5_ESW_BRIDGE_EGRESS_TABLE_SIZE, + MLX5_ESW_BRIDGE_LEVEL_EGRESS_TABLE, + esw); + if (IS_ERR(egress_ft)) + return PTR_ERR(egress_ft); + + vlan_fg = mlx5_esw_bridge_egress_vlan_fg_create(esw, egress_ft); + if (IS_ERR(vlan_fg)) { + err = PTR_ERR(vlan_fg); + goto err_vlan_fg; + } + + qinq_fg = mlx5_esw_bridge_egress_qinq_fg_create(esw, egress_ft); + if (IS_ERR(qinq_fg)) { + err = PTR_ERR(qinq_fg); + goto err_qinq_fg; + } + + mac_fg = mlx5_esw_bridge_egress_mac_fg_create(esw, egress_ft); + if (IS_ERR(mac_fg)) { + err = PTR_ERR(mac_fg); + goto err_mac_fg; + } + + if (mlx5_esw_bridge_pkt_reformat_vlan_pop_supported(esw)) { + miss_fg = mlx5_esw_bridge_egress_miss_fg_create(esw, egress_ft); + if (IS_ERR(miss_fg)) { + esw_warn(esw->dev, "Failed to create miss flow group (err=%ld)\n", + PTR_ERR(miss_fg)); + miss_fg = NULL; + goto skip_miss_flow; + } + + miss_pkt_reformat = mlx5_esw_bridge_pkt_reformat_vlan_pop_create(esw); + if (IS_ERR(miss_pkt_reformat)) { + esw_warn(esw->dev, + "Failed to alloc packet reformat REMOVE_HEADER (err=%ld)\n", + PTR_ERR(miss_pkt_reformat)); + miss_pkt_reformat = NULL; + mlx5_destroy_flow_group(miss_fg); + miss_fg = NULL; + goto skip_miss_flow; + } + + miss_handle = mlx5_esw_bridge_egress_miss_flow_create(egress_ft, + br_offloads->skip_ft, + miss_pkt_reformat); + if (IS_ERR(miss_handle)) { + esw_warn(esw->dev, "Failed to create miss flow (err=%ld)\n", + PTR_ERR(miss_handle)); + miss_handle = NULL; + mlx5_packet_reformat_dealloc(esw->dev, miss_pkt_reformat); + miss_pkt_reformat = NULL; + mlx5_destroy_flow_group(miss_fg); + miss_fg = NULL; + goto skip_miss_flow; + } + } +skip_miss_flow: + + bridge->egress_ft = egress_ft; + bridge->egress_vlan_fg = vlan_fg; + bridge->egress_qinq_fg = qinq_fg; + bridge->egress_mac_fg = mac_fg; + bridge->egress_miss_fg = miss_fg; + bridge->egress_miss_pkt_reformat = miss_pkt_reformat; + bridge->egress_miss_handle = miss_handle; + return 0; + +err_mac_fg: + mlx5_destroy_flow_group(qinq_fg); +err_qinq_fg: + mlx5_destroy_flow_group(vlan_fg); +err_vlan_fg: + mlx5_destroy_flow_table(egress_ft); + return err; +} + +static void +mlx5_esw_bridge_egress_table_cleanup(struct mlx5_esw_bridge *bridge) +{ + if (bridge->egress_miss_handle) + mlx5_del_flow_rules(bridge->egress_miss_handle); + if (bridge->egress_miss_pkt_reformat) + mlx5_packet_reformat_dealloc(bridge->br_offloads->esw->dev, + bridge->egress_miss_pkt_reformat); + if (bridge->egress_miss_fg) + mlx5_destroy_flow_group(bridge->egress_miss_fg); + mlx5_destroy_flow_group(bridge->egress_mac_fg); + mlx5_destroy_flow_group(bridge->egress_qinq_fg); + mlx5_destroy_flow_group(bridge->egress_vlan_fg); + mlx5_destroy_flow_table(bridge->egress_ft); +} + +static struct mlx5_flow_handle * +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 = { + .action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_COUNT, + .flags = FLOW_ACT_NO_APPEND, + }; + struct mlx5_flow_destination dests[2] = {}; + struct mlx5_flow_spec *rule_spec; + struct mlx5_flow_handle *handle; + u8 *smac_v, *smac_c; + + rule_spec = kvzalloc(sizeof(*rule_spec), GFP_KERNEL); + if (!rule_spec) + return ERR_PTR(-ENOMEM); + + rule_spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS | MLX5_MATCH_MISC_PARAMETERS_2; + + smac_v = MLX5_ADDR_OF(fte_match_param, rule_spec->match_value, + outer_headers.smac_47_16); + ether_addr_copy(smac_v, addr); + smac_c = MLX5_ADDR_OF(fte_match_param, rule_spec->match_criteria, + outer_headers.smac_47_16); + eth_broadcast_addr(smac_c); + + 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(esw, vport_num)); + + if (vlan && vlan->pkt_reformat_push) { + flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT | + MLX5_FLOW_CONTEXT_ACTION_MOD_HDR; + flow_act.pkt_reformat = vlan->pkt_reformat_push; + flow_act.modify_hdr = vlan->pkt_mod_hdr_push_mark; + } else if (vlan) { + if (bridge->vlan_proto == ETH_P_8021Q) { + MLX5_SET_TO_ONES(fte_match_param, rule_spec->match_criteria, + outer_headers.cvlan_tag); + MLX5_SET_TO_ONES(fte_match_param, rule_spec->match_value, + outer_headers.cvlan_tag); + } else if (bridge->vlan_proto == ETH_P_8021AD) { + MLX5_SET_TO_ONES(fte_match_param, rule_spec->match_criteria, + outer_headers.svlan_tag); + MLX5_SET_TO_ONES(fte_match_param, rule_spec->match_value, + outer_headers.svlan_tag); + } + MLX5_SET_TO_ONES(fte_match_param, rule_spec->match_criteria, + outer_headers.first_vid); + MLX5_SET(fte_match_param, rule_spec->match_value, outer_headers.first_vid, + vlan->vid); + } + + dests[0].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; + dests[0].ft = bridge->egress_ft; + dests[1].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; + dests[1].counter_id = counter_id; + + handle = mlx5_add_flow_rules(br_offloads->ingress_ft, rule_spec, &flow_act, dests, + ARRAY_SIZE(dests)); + + kvfree(rule_spec); + return handle; +} + +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) +{ + struct mlx5_esw_bridge_offloads *br_offloads = bridge->br_offloads; + struct mlx5_flow_destination dest = { + .type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE, + .ft = br_offloads->skip_ft, + }; + struct mlx5_flow_act flow_act = { + .action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST, + .flags = FLOW_ACT_NO_APPEND, + }; + struct mlx5_flow_spec *rule_spec; + struct mlx5_flow_handle *handle; + u8 *smac_v, *smac_c; + + rule_spec = kvzalloc(sizeof(*rule_spec), GFP_KERNEL); + if (!rule_spec) + return ERR_PTR(-ENOMEM); + + rule_spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS | MLX5_MATCH_MISC_PARAMETERS_2; + + smac_v = MLX5_ADDR_OF(fte_match_param, rule_spec->match_value, + outer_headers.smac_47_16); + ether_addr_copy(smac_v, addr); + smac_c = MLX5_ADDR_OF(fte_match_param, rule_spec->match_criteria, + outer_headers.smac_47_16); + eth_broadcast_addr(smac_c); + + 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)); + + if (bridge->vlan_proto == ETH_P_8021Q) { + MLX5_SET_TO_ONES(fte_match_param, rule_spec->match_criteria, + outer_headers.cvlan_tag); + MLX5_SET_TO_ONES(fte_match_param, rule_spec->match_value, + outer_headers.cvlan_tag); + } else if (bridge->vlan_proto == ETH_P_8021AD) { + MLX5_SET_TO_ONES(fte_match_param, rule_spec->match_criteria, + outer_headers.svlan_tag); + MLX5_SET_TO_ONES(fte_match_param, rule_spec->match_value, + outer_headers.svlan_tag); + } + + handle = mlx5_add_flow_rules(br_offloads->ingress_ft, rule_spec, &flow_act, &dest, 1); + + kvfree(rule_spec); + return handle; +} + +static struct mlx5_flow_handle * +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) +{ + struct mlx5_flow_destination dest = { + .type = MLX5_FLOW_DESTINATION_TYPE_VPORT, + .vport.num = vport_num, + }; + struct mlx5_flow_act flow_act = { + .action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST, + .flags = FLOW_ACT_NO_APPEND, + }; + struct mlx5_flow_spec *rule_spec; + struct mlx5_flow_handle *handle; + u8 *dmac_v, *dmac_c; + + rule_spec = kvzalloc(sizeof(*rule_spec), GFP_KERNEL); + if (!rule_spec) + return ERR_PTR(-ENOMEM); + + if (MLX5_CAP_ESW_FLOWTABLE(bridge->br_offloads->esw->dev, flow_source) && + vport_num == MLX5_VPORT_UPLINK) + rule_spec->flow_context.flow_source = + MLX5_FLOW_CONTEXT_FLOW_SOURCE_LOCAL_VPORT; + rule_spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; + + dmac_v = MLX5_ADDR_OF(fte_match_param, rule_spec->match_value, + outer_headers.dmac_47_16); + ether_addr_copy(dmac_v, addr); + dmac_c = MLX5_ADDR_OF(fte_match_param, rule_spec->match_criteria, + outer_headers.dmac_47_16); + eth_broadcast_addr(dmac_c); + + if (vlan) { + if (vlan->pkt_reformat_pop) { + flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT; + flow_act.pkt_reformat = vlan->pkt_reformat_pop; + } + + if (bridge->vlan_proto == ETH_P_8021Q) { + MLX5_SET_TO_ONES(fte_match_param, rule_spec->match_criteria, + outer_headers.cvlan_tag); + MLX5_SET_TO_ONES(fte_match_param, rule_spec->match_value, + outer_headers.cvlan_tag); + } else if (bridge->vlan_proto == ETH_P_8021AD) { + MLX5_SET_TO_ONES(fte_match_param, rule_spec->match_criteria, + outer_headers.svlan_tag); + MLX5_SET_TO_ONES(fte_match_param, rule_spec->match_value, + outer_headers.svlan_tag); + } + MLX5_SET_TO_ONES(fte_match_param, rule_spec->match_criteria, + outer_headers.first_vid); + MLX5_SET(fte_match_param, rule_spec->match_value, outer_headers.first_vid, + 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); + return handle; +} + +static struct mlx5_flow_handle * +mlx5_esw_bridge_egress_miss_flow_create(struct mlx5_flow_table *egress_ft, + struct mlx5_flow_table *skip_ft, + struct mlx5_pkt_reformat *pkt_reformat) +{ + struct mlx5_flow_destination dest = { + .type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE, + .ft = skip_ft, + }; + struct mlx5_flow_act flow_act = { + .action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | + MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT, + .flags = FLOW_ACT_NO_APPEND, + .pkt_reformat = pkt_reformat, + }; + struct mlx5_flow_spec *rule_spec; + struct mlx5_flow_handle *handle; + + rule_spec = kvzalloc(sizeof(*rule_spec), GFP_KERNEL); + if (!rule_spec) + return ERR_PTR(-ENOMEM); + + rule_spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2; + + MLX5_SET(fte_match_param, rule_spec->match_criteria, + misc_parameters_2.metadata_reg_c_1, ESW_TUN_MASK); + MLX5_SET(fte_match_param, rule_spec->match_value, misc_parameters_2.metadata_reg_c_1, + ESW_TUN_BRIDGE_INGRESS_PUSH_VLAN_MARK); + + handle = mlx5_add_flow_rules(egress_ft, rule_spec, &flow_act, &dest, 1); + + kvfree(rule_spec); + return handle; +} + +static struct mlx5_esw_bridge *mlx5_esw_bridge_create(int ifindex, + struct mlx5_esw_bridge_offloads *br_offloads) +{ + struct mlx5_esw_bridge *bridge; + int err; + + bridge = kvzalloc(sizeof(*bridge), GFP_KERNEL); + if (!bridge) + return ERR_PTR(-ENOMEM); + + bridge->br_offloads = br_offloads; + err = mlx5_esw_bridge_egress_table_init(br_offloads, bridge); + if (err) + goto err_egress_tbl; + + err = rhashtable_init(&bridge->fdb_ht, &fdb_ht_params); + if (err) + goto err_fdb_ht; + + INIT_LIST_HEAD(&bridge->fdb_list); + bridge->ifindex = ifindex; + bridge->refcnt = 1; + bridge->ageing_time = clock_t_to_jiffies(BR_DEFAULT_AGEING_TIME); + bridge->vlan_proto = ETH_P_8021Q; + list_add(&bridge->list, &br_offloads->bridges); + + return bridge; + +err_fdb_ht: + mlx5_esw_bridge_egress_table_cleanup(bridge); +err_egress_tbl: + kvfree(bridge); + return ERR_PTR(err); +} + +static void mlx5_esw_bridge_get(struct mlx5_esw_bridge *bridge) +{ + bridge->refcnt++; +} + +static void mlx5_esw_bridge_put(struct mlx5_esw_bridge_offloads *br_offloads, + struct mlx5_esw_bridge *bridge) +{ + if (--bridge->refcnt) + return; + + mlx5_esw_bridge_egress_table_cleanup(bridge); + list_del(&bridge->list); + rhashtable_destroy(&bridge->fdb_ht); + kvfree(bridge); + + if (list_empty(&br_offloads->bridges)) + mlx5_esw_bridge_ingress_table_cleanup(br_offloads); +} + +static struct mlx5_esw_bridge * +mlx5_esw_bridge_lookup(int ifindex, struct mlx5_esw_bridge_offloads *br_offloads) +{ + struct mlx5_esw_bridge *bridge; + + ASSERT_RTNL(); + + list_for_each_entry(bridge, &br_offloads->bridges, list) { + if (bridge->ifindex == ifindex) { + mlx5_esw_bridge_get(bridge); + return bridge; + } + } + + if (!br_offloads->ingress_ft) { + int err = mlx5_esw_bridge_ingress_table_init(br_offloads); + + if (err) + return ERR_PTR(err); + } + + bridge = mlx5_esw_bridge_create(ifindex, br_offloads); + if (IS_ERR(bridge) && list_empty(&br_offloads->bridges)) + mlx5_esw_bridge_ingress_table_cleanup(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_offloads *br_offloads) +{ + 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, u16 esw_owner_vhca_id, + struct mlx5_esw_bridge_offloads *br_offloads) +{ + 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_offloads *br_offloads) +{ + xa_erase(&br_offloads->ports, mlx5_esw_bridge_port_key(port)); +} + +static void mlx5_esw_bridge_fdb_entry_refresh(struct mlx5_esw_bridge_fdb_entry *entry) +{ + trace_mlx5_esw_bridge_fdb_entry_refresh(entry); + + mlx5_esw_bridge_fdb_offload_notify(entry->dev, entry->key.addr, + entry->key.vid, + SWITCHDEV_FDB_ADD_TO_BRIDGE); +} + +static void +mlx5_esw_bridge_fdb_entry_cleanup(struct mlx5_esw_bridge_fdb_entry *entry, + struct mlx5_esw_bridge *bridge) +{ + trace_mlx5_esw_bridge_fdb_entry_cleanup(entry); + + rhashtable_remove_fast(&bridge->fdb_ht, &entry->ht_node, fdb_ht_params); + mlx5_del_flow_rules(entry->egress_handle); + if (entry->filter_handle) + mlx5_del_flow_rules(entry->filter_handle); + mlx5_del_flow_rules(entry->ingress_handle); + mlx5_fc_destroy(bridge->br_offloads->esw->dev, entry->ingress_counter); + list_del(&entry->vlan_list); + list_del(&entry->list); + kvfree(entry); +} + +static void +mlx5_esw_bridge_fdb_entry_notify_and_cleanup(struct mlx5_esw_bridge_fdb_entry *entry, + struct mlx5_esw_bridge *bridge) +{ + mlx5_esw_bridge_fdb_del_notify(entry); + mlx5_esw_bridge_fdb_entry_cleanup(entry, bridge); +} + +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) + mlx5_esw_bridge_fdb_entry_notify_and_cleanup(entry, bridge); +} + +static struct mlx5_esw_bridge_vlan * +mlx5_esw_bridge_vlan_lookup(u16 vid, struct mlx5_esw_bridge_port *port) +{ + return xa_load(&port->vlans, vid); +} + +static int +mlx5_esw_bridge_vlan_push_create(u16 vlan_proto, struct mlx5_esw_bridge_vlan *vlan, + struct mlx5_eswitch *esw) +{ + struct { + __be16 h_vlan_proto; + __be16 h_vlan_TCI; + } vlan_hdr = { htons(vlan_proto), htons(vlan->vid) }; + struct mlx5_pkt_reformat_params reformat_params = {}; + struct mlx5_pkt_reformat *pkt_reformat; + + if (!BIT(MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, reformat_insert)) || + MLX5_CAP_GEN_2(esw->dev, max_reformat_insert_size) < sizeof(vlan_hdr) || + MLX5_CAP_GEN_2(esw->dev, max_reformat_insert_offset) < + offsetof(struct vlan_ethhdr, h_vlan_proto)) { + esw_warn(esw->dev, "Packet reformat INSERT_HEADER is not supported\n"); + return -EOPNOTSUPP; + } + + reformat_params.type = MLX5_REFORMAT_TYPE_INSERT_HDR; + reformat_params.param_0 = MLX5_REFORMAT_CONTEXT_ANCHOR_MAC_START; + reformat_params.param_1 = offsetof(struct vlan_ethhdr, h_vlan_proto); + reformat_params.size = sizeof(vlan_hdr); + reformat_params.data = &vlan_hdr; + pkt_reformat = mlx5_packet_reformat_alloc(esw->dev, + &reformat_params, + MLX5_FLOW_NAMESPACE_FDB); + if (IS_ERR(pkt_reformat)) { + esw_warn(esw->dev, "Failed to alloc packet reformat INSERT_HEADER (err=%ld)\n", + PTR_ERR(pkt_reformat)); + return PTR_ERR(pkt_reformat); + } + + vlan->pkt_reformat_push = pkt_reformat; + return 0; +} + +static void +mlx5_esw_bridge_vlan_push_cleanup(struct mlx5_esw_bridge_vlan *vlan, struct mlx5_eswitch *esw) +{ + mlx5_packet_reformat_dealloc(esw->dev, vlan->pkt_reformat_push); + vlan->pkt_reformat_push = NULL; +} + +static int +mlx5_esw_bridge_vlan_pop_create(struct mlx5_esw_bridge_vlan *vlan, struct mlx5_eswitch *esw) +{ + struct mlx5_pkt_reformat *pkt_reformat; + + if (!mlx5_esw_bridge_pkt_reformat_vlan_pop_supported(esw)) { + esw_warn(esw->dev, "Packet reformat REMOVE_HEADER is not supported\n"); + return -EOPNOTSUPP; + } + + pkt_reformat = mlx5_esw_bridge_pkt_reformat_vlan_pop_create(esw); + if (IS_ERR(pkt_reformat)) { + esw_warn(esw->dev, "Failed to alloc packet reformat REMOVE_HEADER (err=%ld)\n", + PTR_ERR(pkt_reformat)); + return PTR_ERR(pkt_reformat); + } + + vlan->pkt_reformat_pop = pkt_reformat; + return 0; +} + +static void +mlx5_esw_bridge_vlan_pop_cleanup(struct mlx5_esw_bridge_vlan *vlan, struct mlx5_eswitch *esw) +{ + mlx5_packet_reformat_dealloc(esw->dev, vlan->pkt_reformat_pop); + vlan->pkt_reformat_pop = NULL; +} + +static int +mlx5_esw_bridge_vlan_push_mark_create(struct mlx5_esw_bridge_vlan *vlan, struct mlx5_eswitch *esw) +{ + u8 action[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {}; + struct mlx5_modify_hdr *pkt_mod_hdr; + + MLX5_SET(set_action_in, action, action_type, MLX5_ACTION_TYPE_SET); + MLX5_SET(set_action_in, action, field, MLX5_ACTION_IN_FIELD_METADATA_REG_C_1); + MLX5_SET(set_action_in, action, offset, 8); + MLX5_SET(set_action_in, action, length, ESW_TUN_OPTS_BITS + ESW_TUN_ID_BITS); + MLX5_SET(set_action_in, action, data, ESW_TUN_BRIDGE_INGRESS_PUSH_VLAN); + + pkt_mod_hdr = mlx5_modify_header_alloc(esw->dev, MLX5_FLOW_NAMESPACE_FDB, 1, action); + if (IS_ERR(pkt_mod_hdr)) + return PTR_ERR(pkt_mod_hdr); + + vlan->pkt_mod_hdr_push_mark = pkt_mod_hdr; + return 0; +} + +static void +mlx5_esw_bridge_vlan_push_mark_cleanup(struct mlx5_esw_bridge_vlan *vlan, struct mlx5_eswitch *esw) +{ + mlx5_modify_header_dealloc(esw->dev, vlan->pkt_mod_hdr_push_mark); + vlan->pkt_mod_hdr_push_mark = NULL; +} + +static int +mlx5_esw_bridge_vlan_push_pop_create(u16 vlan_proto, u16 flags, struct mlx5_esw_bridge_vlan *vlan, + struct mlx5_eswitch *esw) +{ + int err; + + if (flags & BRIDGE_VLAN_INFO_PVID) { + err = mlx5_esw_bridge_vlan_push_create(vlan_proto, vlan, esw); + if (err) + return err; + + err = mlx5_esw_bridge_vlan_push_mark_create(vlan, esw); + if (err) + goto err_vlan_push_mark; + } + + if (flags & BRIDGE_VLAN_INFO_UNTAGGED) { + err = mlx5_esw_bridge_vlan_pop_create(vlan, esw); + if (err) + goto err_vlan_pop; + } + + return 0; + +err_vlan_pop: + if (vlan->pkt_mod_hdr_push_mark) + mlx5_esw_bridge_vlan_push_mark_cleanup(vlan, esw); +err_vlan_push_mark: + if (vlan->pkt_reformat_push) + mlx5_esw_bridge_vlan_push_cleanup(vlan, esw); + return err; +} + +static struct mlx5_esw_bridge_vlan * +mlx5_esw_bridge_vlan_create(u16 vlan_proto, u16 vid, u16 flags, struct mlx5_esw_bridge_port *port, + struct mlx5_eswitch *esw) +{ + struct mlx5_esw_bridge_vlan *vlan; + int err; + + vlan = kvzalloc(sizeof(*vlan), GFP_KERNEL); + if (!vlan) + return ERR_PTR(-ENOMEM); + + vlan->vid = vid; + vlan->flags = flags; + INIT_LIST_HEAD(&vlan->fdb_list); + + err = mlx5_esw_bridge_vlan_push_pop_create(vlan_proto, flags, vlan, esw); + if (err) + goto err_vlan_push_pop; + + err = xa_insert(&port->vlans, vid, vlan, GFP_KERNEL); + if (err) + goto err_xa_insert; + + trace_mlx5_esw_bridge_vlan_create(vlan); + return vlan; + +err_xa_insert: + if (vlan->pkt_reformat_pop) + mlx5_esw_bridge_vlan_pop_cleanup(vlan, esw); + if (vlan->pkt_mod_hdr_push_mark) + mlx5_esw_bridge_vlan_push_mark_cleanup(vlan, esw); + if (vlan->pkt_reformat_push) + mlx5_esw_bridge_vlan_push_cleanup(vlan, esw); +err_vlan_push_pop: + kvfree(vlan); + return ERR_PTR(err); +} + +static void mlx5_esw_bridge_vlan_erase(struct mlx5_esw_bridge_port *port, + struct mlx5_esw_bridge_vlan *vlan) +{ + xa_erase(&port->vlans, vlan->vid); +} + +static void mlx5_esw_bridge_vlan_flush(struct mlx5_esw_bridge_vlan *vlan, + struct mlx5_esw_bridge *bridge) +{ + struct mlx5_eswitch *esw = bridge->br_offloads->esw; + struct mlx5_esw_bridge_fdb_entry *entry, *tmp; + + list_for_each_entry_safe(entry, tmp, &vlan->fdb_list, vlan_list) + mlx5_esw_bridge_fdb_entry_notify_and_cleanup(entry, bridge); + + if (vlan->pkt_reformat_pop) + mlx5_esw_bridge_vlan_pop_cleanup(vlan, esw); + if (vlan->pkt_mod_hdr_push_mark) + mlx5_esw_bridge_vlan_push_mark_cleanup(vlan, esw); + if (vlan->pkt_reformat_push) + mlx5_esw_bridge_vlan_push_cleanup(vlan, esw); +} + +static void mlx5_esw_bridge_vlan_cleanup(struct mlx5_esw_bridge_port *port, + struct mlx5_esw_bridge_vlan *vlan, + struct mlx5_esw_bridge *bridge) +{ + trace_mlx5_esw_bridge_vlan_cleanup(vlan); + mlx5_esw_bridge_vlan_flush(vlan, bridge); + mlx5_esw_bridge_vlan_erase(port, vlan); + kvfree(vlan); +} + +static void mlx5_esw_bridge_port_vlans_flush(struct mlx5_esw_bridge_port *port, + struct mlx5_esw_bridge *bridge) +{ + struct mlx5_esw_bridge_vlan *vlan; + unsigned long index; + + xa_for_each(&port->vlans, index, vlan) + mlx5_esw_bridge_vlan_cleanup(port, vlan, bridge); +} + +static int mlx5_esw_bridge_port_vlans_recreate(struct mlx5_esw_bridge_port *port, + struct mlx5_esw_bridge *bridge) +{ + struct mlx5_esw_bridge_offloads *br_offloads = bridge->br_offloads; + struct mlx5_esw_bridge_vlan *vlan; + unsigned long i; + int err; + + xa_for_each(&port->vlans, i, vlan) { + mlx5_esw_bridge_vlan_flush(vlan, bridge); + err = mlx5_esw_bridge_vlan_push_pop_create(bridge->vlan_proto, vlan->flags, vlan, + br_offloads->esw); + if (err) { + esw_warn(br_offloads->esw->dev, + "Failed to create VLAN=%u(proto=%x) push/pop actions (vport=%u,err=%d)\n", + vlan->vid, bridge->vlan_proto, port->vport_num, + err); + return err; + } + } + + return 0; +} + +static int +mlx5_esw_bridge_vlans_recreate(struct mlx5_esw_bridge *bridge) +{ + struct mlx5_esw_bridge_offloads *br_offloads = bridge->br_offloads; + struct mlx5_esw_bridge_port *port; + unsigned long i; + int err; + + xa_for_each(&br_offloads->ports, i, port) { + if (port->bridge != bridge) + continue; + + err = mlx5_esw_bridge_port_vlans_recreate(port, bridge); + if (err) + return err; + } + + return 0; +} + +static struct mlx5_esw_bridge_vlan * +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, 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. + */ + esw_info(esw->dev, "Failed to lookup bridge port (vport=%u)\n", vport_num); + return ERR_PTR(-EINVAL); + } + + vlan = mlx5_esw_bridge_vlan_lookup(vid, port); + if (!vlan) { + /* FDB is added asynchronously on wq while vlan might have been deleted + * concurrently. Report on 'info' logging level and skip the FDB offload. + */ + esw_info(esw->dev, "Failed to lookup bridge port vlan metadata (vport=%u)\n", + vport_num); + return ERR_PTR(-EINVAL); + } + + return vlan; +} + +static struct mlx5_esw_bridge_fdb_entry * +mlx5_esw_bridge_fdb_lookup(struct mlx5_esw_bridge *bridge, + const unsigned char *addr, u16 vid) +{ + struct mlx5_esw_bridge_fdb_key key = {}; + + ether_addr_copy(key.addr, addr); + key.vid = vid; + return rhashtable_lookup_fast(&bridge->fdb_ht, &key, fdb_ht_params); +} + +static struct mlx5_esw_bridge_fdb_entry * +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; + int err; + + if (bridge->flags & MLX5_ESW_BRIDGE_VLAN_FILTERING_FLAG && vid) { + vlan = mlx5_esw_bridge_port_vlan_lookup(vid, vport_num, esw_owner_vhca_id, bridge, + esw); + if (IS_ERR(vlan)) + return ERR_CAST(vlan); + } + + entry = mlx5_esw_bridge_fdb_lookup(bridge, addr, vid); + if (entry) + mlx5_esw_bridge_fdb_entry_notify_and_cleanup(entry, bridge); + + entry = kvzalloc(sizeof(*entry), GFP_KERNEL); + if (!entry) + return ERR_PTR(-ENOMEM); + + ether_addr_copy(entry->key.addr, addr); + 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(esw->dev, true); + if (IS_ERR(counter)) { + err = PTR_ERR(counter); + goto err_ingress_fc_create; + } + entry->ingress_counter = counter; + + 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", + vport_num, err); + goto err_ingress_flow_create; + } + entry->ingress_handle = handle; + + if (bridge->flags & MLX5_ESW_BRIDGE_VLAN_FILTERING_FLAG) { + handle = mlx5_esw_bridge_ingress_filter_flow_create(vport_num, addr, bridge); + if (IS_ERR(handle)) { + err = PTR_ERR(handle); + esw_warn(esw->dev, "Failed to create ingress filter(vport=%u,err=%d)\n", + vport_num, err); + goto err_ingress_filter_flow_create; + } + entry->filter_handle = handle; + } + + 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", + vport_num, err); + goto err_egress_flow_create; + } + entry->egress_handle = handle; + + err = rhashtable_insert_fast(&bridge->fdb_ht, &entry->ht_node, fdb_ht_params); + if (err) { + esw_warn(esw->dev, "Failed to insert FDB flow(vport=%u,err=%d)\n", vport_num, err); + goto err_ht_init; + } + + if (vlan) + list_add(&entry->vlan_list, &vlan->fdb_list); + else + INIT_LIST_HEAD(&entry->vlan_list); + list_add(&entry->list, &bridge->fdb_list); + + trace_mlx5_esw_bridge_fdb_entry_init(entry); + return entry; + +err_ht_init: + mlx5_del_flow_rules(entry->egress_handle); +err_egress_flow_create: + if (entry->filter_handle) + mlx5_del_flow_rules(entry->filter_handle); +err_ingress_filter_flow_create: + mlx5_del_flow_rules(entry->ingress_handle); +err_ingress_flow_create: + 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(u16 vport_num, u16 esw_owner_vhca_id, unsigned long ageing_time, + struct mlx5_esw_bridge_offloads *br_offloads) +{ + struct mlx5_esw_bridge_port *port; + + port = mlx5_esw_bridge_port_lookup(vport_num, esw_owner_vhca_id, br_offloads); + if (!port) + return -EINVAL; + + port->bridge->ageing_time = clock_t_to_jiffies(ageing_time); + return 0; +} + +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; + + port = mlx5_esw_bridge_port_lookup(vport_num, esw_owner_vhca_id, br_offloads); + if (!port) + return -EINVAL; + + bridge = port->bridge; + filtering = bridge->flags & MLX5_ESW_BRIDGE_VLAN_FILTERING_FLAG; + if (filtering == enable) + return 0; + + mlx5_esw_bridge_fdb_flush(bridge); + if (enable) + bridge->flags |= MLX5_ESW_BRIDGE_VLAN_FILTERING_FLAG; + else + bridge->flags &= ~MLX5_ESW_BRIDGE_VLAN_FILTERING_FLAG; + + return 0; +} + +int mlx5_esw_bridge_vlan_proto_set(u16 vport_num, u16 esw_owner_vhca_id, u16 proto, + struct mlx5_esw_bridge_offloads *br_offloads) +{ + 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 -EINVAL; + + bridge = port->bridge; + if (bridge->vlan_proto == proto) + return 0; + if (proto != ETH_P_8021Q && proto != ETH_P_8021AD) { + esw_warn(br_offloads->esw->dev, "Can't set unsupported VLAN protocol %x", proto); + return -EOPNOTSUPP; + } + + mlx5_esw_bridge_fdb_flush(bridge); + bridge->vlan_proto = proto; + mlx5_esw_bridge_vlans_recreate(bridge); + + return 0; +} + +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) + return -ENOMEM; + + 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, br_offloads); + if (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); + + return 0; + +err_port_insert: + kvfree(port); + return err; +} + +static int mlx5_esw_bridge_vport_cleanup(struct mlx5_esw_bridge_offloads *br_offloads, + struct mlx5_esw_bridge_port *port) +{ + 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; + + list_for_each_entry_safe(entry, tmp, &bridge->fdb_list, list) + if (entry->vport_num == vport_num && entry->esw_owner_vhca_id == esw_owner_vhca_id) + mlx5_esw_bridge_fdb_entry_cleanup(entry, bridge); + + trace_mlx5_esw_bridge_vport_cleanup(port); + mlx5_esw_bridge_port_vlans_flush(port, bridge); + mlx5_esw_bridge_port_erase(port, br_offloads); + kvfree(port); + mlx5_esw_bridge_put(br_offloads, bridge); + return 0; +} + +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; + + 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(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_link(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_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; + + 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 (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, port); + if (err) + NL_SET_ERR_MSG_MOD(extack, "Port cleanup failed"); + return err; +} + +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_num, esw_owner_vhca_id, br_offloads); + if (!port) + return -EINVAL; + + vlan = mlx5_esw_bridge_vlan_lookup(vid, port); + if (vlan) { + if (vlan->flags == flags) + return 0; + mlx5_esw_bridge_vlan_cleanup(port, vlan, port->bridge); + } + + vlan = mlx5_esw_bridge_vlan_create(port->bridge->vlan_proto, 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); + } + return 0; +} + +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_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, port->bridge); +} + +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_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_lookup(bridge, fdb_info->addr, fdb_info->vid); + if (!entry) { + esw_debug(br_offloads->esw->dev, + "FDB entry with specified key not found (MAC=%pM,vid=%u,vport=%u)\n", + fdb_info->addr, fdb_info->vid, vport_num); + return; + } + + 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 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, u16 vport_num, u16 esw_owner_vhca_id, + struct mlx5_esw_bridge_offloads *br_offloads, + struct switchdev_notifier_fdb_info *fdb_info) +{ + struct mlx5_eswitch *esw = br_offloads->esw; + 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_lookup(bridge, fdb_info->addr, fdb_info->vid); + if (!entry) { + esw_warn(esw->dev, + "FDB entry with specified key not found (MAC=%pM,vid=%u,vport=%u)\n", + fdb_info->addr, fdb_info->vid, vport_num); + return; + } + + mlx5_esw_bridge_fdb_entry_notify_and_cleanup(entry, bridge); +} + +void mlx5_esw_bridge_update(struct mlx5_esw_bridge_offloads *br_offloads) +{ + struct mlx5_esw_bridge_fdb_entry *entry, *tmp; + struct mlx5_esw_bridge *bridge; + + list_for_each_entry(bridge, &br_offloads->bridges, list) { + list_for_each_entry_safe(entry, tmp, &bridge->fdb_list, list) { + unsigned long lastuse = + (unsigned long)mlx5_fc_query_lastuse(entry->ingress_counter); + + if (entry->flags & MLX5_ESW_BRIDGE_FLAG_ADDED_BY_USER) + continue; + + if (time_after(lastuse, entry->lastuse)) + 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_entry_notify_and_cleanup(entry, bridge); + } + } +} + +static void mlx5_esw_bridge_flush(struct mlx5_esw_bridge_offloads *br_offloads) +{ + struct mlx5_esw_bridge_port *port; + unsigned long i; + + 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"); +} + +struct mlx5_esw_bridge_offloads *mlx5_esw_bridge_init(struct mlx5_eswitch *esw) +{ + struct mlx5_esw_bridge_offloads *br_offloads; + + ASSERT_RTNL(); + + br_offloads = kvzalloc(sizeof(*br_offloads), GFP_KERNEL); + if (!br_offloads) + return ERR_PTR(-ENOMEM); + + INIT_LIST_HEAD(&br_offloads->bridges); + xa_init(&br_offloads->ports); + br_offloads->esw = esw; + esw->br_offloads = br_offloads; + + return br_offloads; +} + +void mlx5_esw_bridge_cleanup(struct mlx5_eswitch *esw) +{ + struct mlx5_esw_bridge_offloads *br_offloads = esw->br_offloads; + + ASSERT_RTNL(); + + if (!br_offloads) + 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 new file mode 100644 index 000000000..10851a515 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.h @@ -0,0 +1,73 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2021 Mellanox Technologies. */ + +#ifndef __MLX5_ESW_BRIDGE_H__ +#define __MLX5_ESW_BRIDGE_H__ + +#include <linux/notifier.h> +#include <linux/list.h> +#include <linux/workqueue.h> +#include <linux/xarray.h> +#include "eswitch.h" + +struct mlx5_flow_table; +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; + struct workqueue_struct *wq; + struct delayed_work update_work; + + struct mlx5_flow_table *ingress_ft; + struct mlx5_flow_group *ingress_vlan_fg; + struct mlx5_flow_group *ingress_vlan_filter_fg; + struct mlx5_flow_group *ingress_qinq_fg; + struct mlx5_flow_group *ingress_qinq_filter_fg; + struct mlx5_flow_group *ingress_mac_fg; + + struct mlx5_flow_table *skip_ft; +}; + +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, 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, 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(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_vlan_proto_set(u16 vport_num, u16 esw_owner_vhca_id, u16 proto, + 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 new file mode 100644 index 000000000..878311fe9 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_priv.h @@ -0,0 +1,63 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2021 Mellanox Technologies. */ + +#ifndef _MLX5_ESW_BRIDGE_PRIVATE_ +#define _MLX5_ESW_BRIDGE_PRIVATE_ + +#include <linux/netdevice.h> +#include <linux/if_bridge.h> +#include <linux/if_vlan.h> +#include <linux/if_ether.h> +#include <linux/rhashtable.h> +#include <linux/xarray.h> +#include "fs_core.h" + +struct mlx5_esw_bridge_fdb_key { + unsigned char addr[ETH_ALEN]; + u16 vid; +}; + +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 { + struct mlx5_esw_bridge_fdb_key key; + struct rhash_head ht_node; + struct net_device *dev; + 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; + struct mlx5_fc *ingress_counter; + unsigned long lastuse; + struct mlx5_flow_handle *egress_handle; + struct mlx5_flow_handle *filter_handle; +}; + +struct mlx5_esw_bridge_vlan { + u16 vid; + u16 flags; + struct list_head fdb_list; + struct mlx5_pkt_reformat *pkt_reformat_push; + struct mlx5_pkt_reformat *pkt_reformat_pop; + struct mlx5_modify_hdr *pkt_mod_hdr_push_mark; +}; + +struct mlx5_esw_bridge_port { + u16 vport_num; + u16 esw_owner_vhca_id; + u16 flags; + struct mlx5_esw_bridge *bridge; + struct xarray vlans; +}; + +#endif /* _MLX5_ESW_BRIDGE_PRIVATE_ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/debugfs.c new file mode 100644 index 000000000..2db13c71e --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/debugfs.c @@ -0,0 +1,182 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */ + +#include <linux/debugfs.h> +#include "eswitch.h" + +enum vnic_diag_counter { + MLX5_VNIC_DIAG_TOTAL_Q_UNDER_PROCESSOR_HANDLE, + MLX5_VNIC_DIAG_SEND_QUEUE_PRIORITY_UPDATE_FLOW, + MLX5_VNIC_DIAG_COMP_EQ_OVERRUN, + MLX5_VNIC_DIAG_ASYNC_EQ_OVERRUN, + MLX5_VNIC_DIAG_CQ_OVERRUN, + MLX5_VNIC_DIAG_INVALID_COMMAND, + MLX5_VNIC_DIAG_QOUTA_EXCEEDED_COMMAND, +}; + +static int mlx5_esw_query_vnic_diag(struct mlx5_vport *vport, enum vnic_diag_counter counter, + u32 *val) +{ + u32 out[MLX5_ST_SZ_DW(query_vnic_env_out)] = {}; + u32 in[MLX5_ST_SZ_DW(query_vnic_env_in)] = {}; + struct mlx5_core_dev *dev = vport->dev; + u16 vport_num = vport->vport; + void *vnic_diag_out; + int err; + + MLX5_SET(query_vnic_env_in, in, opcode, MLX5_CMD_OP_QUERY_VNIC_ENV); + MLX5_SET(query_vnic_env_in, in, vport_number, vport_num); + if (!mlx5_esw_is_manager_vport(dev->priv.eswitch, vport_num)) + MLX5_SET(query_vnic_env_in, in, other_vport, 1); + + err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); + if (err) + return err; + + vnic_diag_out = MLX5_ADDR_OF(query_vnic_env_out, out, vport_env); + switch (counter) { + case MLX5_VNIC_DIAG_TOTAL_Q_UNDER_PROCESSOR_HANDLE: + *val = MLX5_GET(vnic_diagnostic_statistics, vnic_diag_out, total_error_queues); + break; + case MLX5_VNIC_DIAG_SEND_QUEUE_PRIORITY_UPDATE_FLOW: + *val = MLX5_GET(vnic_diagnostic_statistics, vnic_diag_out, + send_queue_priority_update_flow); + break; + case MLX5_VNIC_DIAG_COMP_EQ_OVERRUN: + *val = MLX5_GET(vnic_diagnostic_statistics, vnic_diag_out, comp_eq_overrun); + break; + case MLX5_VNIC_DIAG_ASYNC_EQ_OVERRUN: + *val = MLX5_GET(vnic_diagnostic_statistics, vnic_diag_out, async_eq_overrun); + break; + case MLX5_VNIC_DIAG_CQ_OVERRUN: + *val = MLX5_GET(vnic_diagnostic_statistics, vnic_diag_out, cq_overrun); + break; + case MLX5_VNIC_DIAG_INVALID_COMMAND: + *val = MLX5_GET(vnic_diagnostic_statistics, vnic_diag_out, invalid_command); + break; + case MLX5_VNIC_DIAG_QOUTA_EXCEEDED_COMMAND: + *val = MLX5_GET(vnic_diagnostic_statistics, vnic_diag_out, quota_exceeded_command); + break; + } + + return 0; +} + +static int __show_vnic_diag(struct seq_file *file, struct mlx5_vport *vport, + enum vnic_diag_counter type) +{ + u32 val = 0; + int ret; + + ret = mlx5_esw_query_vnic_diag(vport, type, &val); + if (ret) + return ret; + + seq_printf(file, "%d\n", val); + return 0; +} + +static int total_q_under_processor_handle_show(struct seq_file *file, void *priv) +{ + return __show_vnic_diag(file, file->private, MLX5_VNIC_DIAG_TOTAL_Q_UNDER_PROCESSOR_HANDLE); +} + +static int send_queue_priority_update_flow_show(struct seq_file *file, void *priv) +{ + return __show_vnic_diag(file, file->private, + MLX5_VNIC_DIAG_SEND_QUEUE_PRIORITY_UPDATE_FLOW); +} + +static int comp_eq_overrun_show(struct seq_file *file, void *priv) +{ + return __show_vnic_diag(file, file->private, MLX5_VNIC_DIAG_COMP_EQ_OVERRUN); +} + +static int async_eq_overrun_show(struct seq_file *file, void *priv) +{ + return __show_vnic_diag(file, file->private, MLX5_VNIC_DIAG_ASYNC_EQ_OVERRUN); +} + +static int cq_overrun_show(struct seq_file *file, void *priv) +{ + return __show_vnic_diag(file, file->private, MLX5_VNIC_DIAG_CQ_OVERRUN); +} + +static int invalid_command_show(struct seq_file *file, void *priv) +{ + return __show_vnic_diag(file, file->private, MLX5_VNIC_DIAG_INVALID_COMMAND); +} + +static int quota_exceeded_command_show(struct seq_file *file, void *priv) +{ + return __show_vnic_diag(file, file->private, MLX5_VNIC_DIAG_QOUTA_EXCEEDED_COMMAND); +} + +DEFINE_SHOW_ATTRIBUTE(total_q_under_processor_handle); +DEFINE_SHOW_ATTRIBUTE(send_queue_priority_update_flow); +DEFINE_SHOW_ATTRIBUTE(comp_eq_overrun); +DEFINE_SHOW_ATTRIBUTE(async_eq_overrun); +DEFINE_SHOW_ATTRIBUTE(cq_overrun); +DEFINE_SHOW_ATTRIBUTE(invalid_command); +DEFINE_SHOW_ATTRIBUTE(quota_exceeded_command); + +void mlx5_esw_vport_debugfs_destroy(struct mlx5_eswitch *esw, u16 vport_num) +{ + struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num); + + debugfs_remove_recursive(vport->dbgfs); + vport->dbgfs = NULL; +} + +/* vnic diag dir name is "pf", "ecpf" or "{vf/sf}_xxxx" */ +#define VNIC_DIAG_DIR_NAME_MAX_LEN 8 + +void mlx5_esw_vport_debugfs_create(struct mlx5_eswitch *esw, u16 vport_num, bool is_sf, u16 sf_num) +{ + struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num); + struct dentry *vnic_diag; + char dir_name[VNIC_DIAG_DIR_NAME_MAX_LEN]; + int err; + + if (!MLX5_CAP_GEN(esw->dev, vport_group_manager)) + return; + + if (vport_num == MLX5_VPORT_PF) { + strcpy(dir_name, "pf"); + } else if (vport_num == MLX5_VPORT_ECPF) { + strcpy(dir_name, "ecpf"); + } else { + err = snprintf(dir_name, VNIC_DIAG_DIR_NAME_MAX_LEN, "%s_%d", is_sf ? "sf" : "vf", + is_sf ? sf_num : vport_num - MLX5_VPORT_FIRST_VF); + if (WARN_ON(err < 0)) + return; + } + + vport->dbgfs = debugfs_create_dir(dir_name, esw->dbgfs); + vnic_diag = debugfs_create_dir("vnic_diag", vport->dbgfs); + + if (MLX5_CAP_GEN(esw->dev, vnic_env_queue_counters)) { + debugfs_create_file("total_q_under_processor_handle", 0444, vnic_diag, vport, + &total_q_under_processor_handle_fops); + debugfs_create_file("send_queue_priority_update_flow", 0444, vnic_diag, vport, + &send_queue_priority_update_flow_fops); + } + + if (MLX5_CAP_GEN(esw->dev, eq_overrun_count)) { + debugfs_create_file("comp_eq_overrun", 0444, vnic_diag, vport, + &comp_eq_overrun_fops); + debugfs_create_file("async_eq_overrun", 0444, vnic_diag, vport, + &async_eq_overrun_fops); + } + + if (MLX5_CAP_GEN(esw->dev, vnic_env_cq_overrun)) + debugfs_create_file("cq_overrun", 0444, vnic_diag, vport, &cq_overrun_fops); + + if (MLX5_CAP_GEN(esw->dev, invalid_command_count)) + debugfs_create_file("invalid_command", 0444, vnic_diag, vport, + &invalid_command_fops); + + if (MLX5_CAP_GEN(esw->dev, quota_exceeded_count)) + debugfs_create_file("quota_exceeded_command", 0444, vnic_diag, vport, + "a_exceeded_command_fops); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c new file mode 100644 index 000000000..9bc7be95d --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c @@ -0,0 +1,190 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2020 Mellanox Technologies Ltd. */ + +#include <linux/mlx5/driver.h> +#include "eswitch.h" + +static void +mlx5_esw_get_port_parent_id(struct mlx5_core_dev *dev, struct netdev_phys_item_id *ppid) +{ + u64 parent_id; + + parent_id = mlx5_query_nic_system_image_guid(dev); + ppid->id_len = sizeof(parent_id); + memcpy(ppid->id, &parent_id, sizeof(parent_id)); +} + +static bool mlx5_esw_devlink_port_supported(struct mlx5_eswitch *esw, u16 vport_num) +{ + return vport_num == MLX5_VPORT_UPLINK || + (mlx5_core_is_ecpf(esw->dev) && vport_num == MLX5_VPORT_PF) || + mlx5_eswitch_is_vf_vport(esw, vport_num); +} + +static struct devlink_port *mlx5_esw_dl_port_alloc(struct mlx5_eswitch *esw, u16 vport_num) +{ + struct mlx5_core_dev *dev = esw->dev; + struct devlink_port_attrs attrs = {}; + struct netdev_phys_item_id ppid = {}; + struct devlink_port *dl_port; + u32 controller_num = 0; + bool external; + u16 pfnum; + + dl_port = kzalloc(sizeof(*dl_port), GFP_KERNEL); + if (!dl_port) + return NULL; + + mlx5_esw_get_port_parent_id(dev, &ppid); + pfnum = mlx5_get_dev_index(dev); + external = mlx5_core_is_ecpf_esw_manager(dev); + if (external) + controller_num = dev->priv.eswitch->offloads.host_number + 1; + + if (vport_num == MLX5_VPORT_UPLINK) { + attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL; + attrs.phys.port_number = pfnum; + memcpy(attrs.switch_id.id, ppid.id, ppid.id_len); + attrs.switch_id.id_len = ppid.id_len; + devlink_port_attrs_set(dl_port, &attrs); + } else if (vport_num == MLX5_VPORT_PF) { + memcpy(dl_port->attrs.switch_id.id, ppid.id, ppid.id_len); + dl_port->attrs.switch_id.id_len = ppid.id_len; + devlink_port_attrs_pci_pf_set(dl_port, controller_num, pfnum, external); + } else if (mlx5_eswitch_is_vf_vport(esw, vport_num)) { + memcpy(dl_port->attrs.switch_id.id, ppid.id, ppid.id_len); + dl_port->attrs.switch_id.id_len = ppid.id_len; + devlink_port_attrs_pci_vf_set(dl_port, controller_num, pfnum, + vport_num - 1, external); + } + return dl_port; +} + +static void mlx5_esw_dl_port_free(struct devlink_port *dl_port) +{ + kfree(dl_port); +} + +int mlx5_esw_offloads_devlink_port_register(struct mlx5_eswitch *esw, u16 vport_num) +{ + struct mlx5_core_dev *dev = esw->dev; + struct devlink_port *dl_port; + unsigned int dl_port_index; + struct mlx5_vport *vport; + struct devlink *devlink; + int err; + + if (!mlx5_esw_devlink_port_supported(esw, vport_num)) + return 0; + + vport = mlx5_eswitch_get_vport(esw, vport_num); + if (IS_ERR(vport)) + return PTR_ERR(vport); + + dl_port = mlx5_esw_dl_port_alloc(esw, vport_num); + if (!dl_port) + return -ENOMEM; + + devlink = priv_to_devlink(dev); + dl_port_index = mlx5_esw_vport_to_devlink_port_index(dev, vport_num); + err = devl_port_register(devlink, dl_port, dl_port_index); + if (err) + goto reg_err; + + err = devl_rate_leaf_create(dl_port, vport); + if (err) + goto rate_err; + + vport->dl_port = dl_port; + return 0; + +rate_err: + devl_port_unregister(dl_port); +reg_err: + mlx5_esw_dl_port_free(dl_port); + return err; +} + +void mlx5_esw_offloads_devlink_port_unregister(struct mlx5_eswitch *esw, u16 vport_num) +{ + struct mlx5_vport *vport; + + if (!mlx5_esw_devlink_port_supported(esw, vport_num)) + return; + + 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); + devl_rate_leaf_destroy(vport->dl_port); + } + + devl_port_unregister(vport->dl_port); + mlx5_esw_dl_port_free(vport->dl_port); + vport->dl_port = NULL; +} + +struct devlink_port *mlx5_esw_offloads_devlink_port(struct mlx5_eswitch *esw, u16 vport_num) +{ + struct mlx5_vport *vport; + + vport = mlx5_eswitch_get_vport(esw, vport_num); + return IS_ERR(vport) ? ERR_CAST(vport) : vport->dl_port; +} + +int mlx5_esw_devlink_sf_port_register(struct mlx5_eswitch *esw, struct devlink_port *dl_port, + u16 vport_num, u32 controller, u32 sfnum) +{ + struct mlx5_core_dev *dev = esw->dev; + struct netdev_phys_item_id ppid = {}; + unsigned int dl_port_index; + struct mlx5_vport *vport; + struct devlink *devlink; + u16 pfnum; + int err; + + vport = mlx5_eswitch_get_vport(esw, vport_num); + if (IS_ERR(vport)) + return PTR_ERR(vport); + + pfnum = mlx5_get_dev_index(dev); + mlx5_esw_get_port_parent_id(dev, &ppid); + memcpy(dl_port->attrs.switch_id.id, &ppid.id[0], ppid.id_len); + dl_port->attrs.switch_id.id_len = ppid.id_len; + devlink_port_attrs_pci_sf_set(dl_port, controller, pfnum, sfnum, !!controller); + devlink = priv_to_devlink(dev); + dl_port_index = mlx5_esw_vport_to_devlink_port_index(dev, vport_num); + err = devl_port_register(devlink, dl_port, dl_port_index); + if (err) + return err; + + err = devl_rate_leaf_create(dl_port, vport); + if (err) + goto rate_err; + + vport->dl_port = dl_port; + return 0; + +rate_err: + devl_port_unregister(dl_port); + return err; +} + +void mlx5_esw_devlink_sf_port_unregister(struct mlx5_eswitch *esw, u16 vport_num) +{ + struct mlx5_vport *vport; + + 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); + devl_rate_leaf_destroy(vport->dl_port); + } + + devl_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 new file mode 100644 index 000000000..51ac24e6e --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/diag/bridge_tracepoint.h @@ -0,0 +1,120 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2021 Mellanox Technologies. */ + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM mlx5 + +#if !defined(_MLX5_ESW_BRIDGE_TRACEPOINT_) || defined(TRACE_HEADER_MULTI_READ) +#define _MLX5_ESW_BRIDGE_TRACEPOINT_ + +#include <linux/tracepoint.h> +#include "../bridge_priv.h" + +DECLARE_EVENT_CLASS(mlx5_esw_bridge_fdb_template, + TP_PROTO(const struct mlx5_esw_bridge_fdb_entry *fdb), + TP_ARGS(fdb), + TP_STRUCT__entry( + __array(char, dev_name, IFNAMSIZ) + __array(unsigned char, addr, ETH_ALEN) + __field(u16, vid) + __field(u16, flags) + __field(unsigned int, used) + ), + TP_fast_assign( + strscpy(__entry->dev_name, + netdev_name(fdb->dev), + IFNAMSIZ); + memcpy(__entry->addr, fdb->key.addr, ETH_ALEN); + __entry->vid = fdb->key.vid; + __entry->flags = fdb->flags; + __entry->used = jiffies_to_msecs(jiffies - fdb->lastuse) + ), + TP_printk("net_device=%s addr=%pM vid=%hu flags=%hx used=%u", + __entry->dev_name, + __entry->addr, + __entry->vid, + __entry->flags, + __entry->used / 1000) + ); + +DEFINE_EVENT(mlx5_esw_bridge_fdb_template, + mlx5_esw_bridge_fdb_entry_init, + TP_PROTO(const struct mlx5_esw_bridge_fdb_entry *fdb), + TP_ARGS(fdb) + ); +DEFINE_EVENT(mlx5_esw_bridge_fdb_template, + mlx5_esw_bridge_fdb_entry_refresh, + TP_PROTO(const struct mlx5_esw_bridge_fdb_entry *fdb), + TP_ARGS(fdb) + ); +DEFINE_EVENT(mlx5_esw_bridge_fdb_template, + mlx5_esw_bridge_fdb_entry_cleanup, + TP_PROTO(const struct mlx5_esw_bridge_fdb_entry *fdb), + TP_ARGS(fdb) + ); + +DECLARE_EVENT_CLASS(mlx5_esw_bridge_vlan_template, + TP_PROTO(const struct mlx5_esw_bridge_vlan *vlan), + TP_ARGS(vlan), + TP_STRUCT__entry( + __field(u16, vid) + __field(u16, flags) + ), + TP_fast_assign( + __entry->vid = vlan->vid; + __entry->flags = vlan->flags; + ), + TP_printk("vid=%hu flags=%hx", + __entry->vid, + __entry->flags) + ); + +DEFINE_EVENT(mlx5_esw_bridge_vlan_template, + mlx5_esw_bridge_vlan_create, + TP_PROTO(const struct mlx5_esw_bridge_vlan *vlan), + TP_ARGS(vlan) + ); +DEFINE_EVENT(mlx5_esw_bridge_vlan_template, + mlx5_esw_bridge_vlan_cleanup, + TP_PROTO(const struct mlx5_esw_bridge_vlan *vlan), + TP_ARGS(vlan) + ); + +DECLARE_EVENT_CLASS(mlx5_esw_bridge_port_template, + TP_PROTO(const struct mlx5_esw_bridge_port *port), + 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 esw_owner_vhca_id=%hu flags=%hx", + __entry->vport_num, + __entry->esw_owner_vhca_id, + __entry->flags) + ); + +DEFINE_EVENT(mlx5_esw_bridge_port_template, + mlx5_esw_bridge_vport_init, + TP_PROTO(const struct mlx5_esw_bridge_port *port), + TP_ARGS(port) + ); +DEFINE_EVENT(mlx5_esw_bridge_port_template, + mlx5_esw_bridge_vport_cleanup, + TP_PROTO(const struct mlx5_esw_bridge_port *port), + TP_ARGS(port) + ); + +#endif + +/* This part must be outside protection */ +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH esw/diag +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE bridge_tracepoint +#include <trace/define_trace.h> 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 000000000..458baf0c6 --- /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/indir_table.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/indir_table.c new file mode 100644 index 000000000..8a94870c5 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/indir_table.c @@ -0,0 +1,390 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2021 Mellanox Technologies. */ + +#include <linux/etherdevice.h> +#include <linux/idr.h> +#include <linux/mlx5/driver.h> +#include <linux/mlx5/mlx5_ifc.h> +#include <linux/mlx5/vport.h> +#include <linux/mlx5/fs.h> +#include "mlx5_core.h" +#include "eswitch.h" +#include "en.h" +#include "en_tc.h" +#include "fs_core.h" +#include "esw/indir_table.h" +#include "lib/fs_chains.h" +#include "en/mod_hdr.h" + +#define MLX5_ESW_INDIR_TABLE_SIZE 2 +#define MLX5_ESW_INDIR_TABLE_RECIRC_IDX (MLX5_ESW_INDIR_TABLE_SIZE - 2) +#define MLX5_ESW_INDIR_TABLE_FWD_IDX (MLX5_ESW_INDIR_TABLE_SIZE - 1) + +struct mlx5_esw_indir_table_rule { + struct mlx5_flow_handle *handle; + struct mlx5_modify_hdr *mh; + refcount_t refcnt; +}; + +struct mlx5_esw_indir_table_entry { + struct hlist_node hlist; + struct mlx5_flow_table *ft; + struct mlx5_flow_group *recirc_grp; + struct mlx5_flow_group *fwd_grp; + struct mlx5_flow_handle *fwd_rule; + struct mlx5_esw_indir_table_rule *recirc_rule; + int fwd_ref; + + u16 vport; +}; + +struct mlx5_esw_indir_table { + struct mutex lock; /* protects table */ + DECLARE_HASHTABLE(table, 8); +}; + +struct mlx5_esw_indir_table * +mlx5_esw_indir_table_init(void) +{ + struct mlx5_esw_indir_table *indir = kvzalloc(sizeof(*indir), GFP_KERNEL); + + if (!indir) + return ERR_PTR(-ENOMEM); + + mutex_init(&indir->lock); + hash_init(indir->table); + return indir; +} + +void +mlx5_esw_indir_table_destroy(struct mlx5_esw_indir_table *indir) +{ + mutex_destroy(&indir->lock); + kvfree(indir); +} + +bool +mlx5_esw_indir_table_needed(struct mlx5_eswitch *esw, + struct mlx5_flow_attr *attr, + u16 vport_num, + struct mlx5_core_dev *dest_mdev) +{ + struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr; + bool vf_sf_vport; + + vf_sf_vport = mlx5_eswitch_is_vf_vport(esw, vport_num) || + mlx5_esw_is_sf_vport(esw, vport_num); + + /* Use indirect table for all IP traffic from UL to VF with vport + * destination when source rewrite flag is set. + */ + return esw_attr->in_rep->vport == MLX5_VPORT_UPLINK && + vf_sf_vport && + esw->dev == dest_mdev && + attr->flags & MLX5_ATTR_FLAG_SRC_REWRITE; +} + +u16 +mlx5_esw_indir_table_decap_vport(struct mlx5_flow_attr *attr) +{ + struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr; + + return esw_attr->rx_tun_attr ? esw_attr->rx_tun_attr->decap_vport : 0; +} + +static int mlx5_esw_indir_table_rule_get(struct mlx5_eswitch *esw, + struct mlx5_flow_attr *attr, + struct mlx5_esw_indir_table_entry *e) +{ + struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr; + struct mlx5_fs_chains *chains = esw_chains(esw); + struct mlx5e_tc_mod_hdr_acts mod_acts = {}; + struct mlx5_flow_destination dest = {}; + struct mlx5_esw_indir_table_rule *rule; + struct mlx5_flow_act flow_act = {}; + struct mlx5_flow_handle *handle; + int err = 0; + u32 data; + + if (e->recirc_rule) { + refcount_inc(&e->recirc_rule->refcnt); + return 0; + } + + rule = kzalloc(sizeof(*rule), GFP_KERNEL); + if (!rule) + return -ENOMEM; + + /* Modify flow source to recirculate packet */ + data = mlx5_eswitch_get_vport_metadata_for_set(esw, esw_attr->rx_tun_attr->decap_vport); + err = mlx5e_tc_match_to_reg_set(esw->dev, &mod_acts, MLX5_FLOW_NAMESPACE_FDB, + VPORT_TO_REG, data); + if (err) + goto err_mod_hdr_regc0; + + err = mlx5e_tc_match_to_reg_set(esw->dev, &mod_acts, MLX5_FLOW_NAMESPACE_FDB, + TUNNEL_TO_REG, ESW_TUN_SLOW_TABLE_GOTO_VPORT); + if (err) + goto err_mod_hdr_regc1; + + flow_act.modify_hdr = mlx5_modify_header_alloc(esw->dev, MLX5_FLOW_NAMESPACE_FDB, + mod_acts.num_actions, mod_acts.actions); + if (IS_ERR(flow_act.modify_hdr)) { + err = PTR_ERR(flow_act.modify_hdr); + goto err_mod_hdr_alloc; + } + + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_MOD_HDR; + flow_act.flags = FLOW_ACT_IGNORE_FLOW_LEVEL | FLOW_ACT_NO_APPEND; + flow_act.fg = e->recirc_grp; + dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; + dest.ft = mlx5_chains_get_table(chains, 0, 1, 0); + if (IS_ERR(dest.ft)) { + err = PTR_ERR(dest.ft); + goto err_table; + } + handle = mlx5_add_flow_rules(e->ft, NULL, &flow_act, &dest, 1); + if (IS_ERR(handle)) { + err = PTR_ERR(handle); + goto err_handle; + } + + mlx5e_mod_hdr_dealloc(&mod_acts); + rule->handle = handle; + rule->mh = flow_act.modify_hdr; + refcount_set(&rule->refcnt, 1); + e->recirc_rule = rule; + return 0; + +err_handle: + mlx5_chains_put_table(chains, 0, 1, 0); +err_table: + mlx5_modify_header_dealloc(esw->dev, flow_act.modify_hdr); +err_mod_hdr_alloc: +err_mod_hdr_regc1: + mlx5e_mod_hdr_dealloc(&mod_acts); +err_mod_hdr_regc0: + kfree(rule); + return err; +} + +static void mlx5_esw_indir_table_rule_put(struct mlx5_eswitch *esw, + struct mlx5_esw_indir_table_entry *e) +{ + struct mlx5_esw_indir_table_rule *rule = e->recirc_rule; + struct mlx5_fs_chains *chains = esw_chains(esw); + + if (!rule) + return; + + if (!refcount_dec_and_test(&rule->refcnt)) + return; + + mlx5_del_flow_rules(rule->handle); + mlx5_chains_put_table(chains, 0, 1, 0); + mlx5_modify_header_dealloc(esw->dev, rule->mh); + kfree(rule); + e->recirc_rule = NULL; +} + +static int mlx5_create_indir_recirc_group(struct mlx5_esw_indir_table_entry *e) +{ + int err = 0, inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + u32 *in; + + in = kvzalloc(inlen, GFP_KERNEL); + if (!in) + return -ENOMEM; + + MLX5_SET(create_flow_group_in, in, start_flow_index, 0); + MLX5_SET(create_flow_group_in, in, end_flow_index, MLX5_ESW_INDIR_TABLE_RECIRC_IDX); + e->recirc_grp = mlx5_create_flow_group(e->ft, in); + if (IS_ERR(e->recirc_grp)) + err = PTR_ERR(e->recirc_grp); + + kvfree(in); + return err; +} + +static int mlx5_create_indir_fwd_group(struct mlx5_eswitch *esw, + struct mlx5_esw_indir_table_entry *e) +{ + int err = 0, inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + struct mlx5_flow_destination dest = {}; + struct mlx5_flow_act flow_act = {}; + struct mlx5_flow_spec *spec; + u32 *in; + + in = kvzalloc(inlen, GFP_KERNEL); + if (!in) + return -ENOMEM; + + spec = kvzalloc(sizeof(*spec), GFP_KERNEL); + if (!spec) { + kvfree(in); + return -ENOMEM; + } + + /* Hold one entry */ + MLX5_SET(create_flow_group_in, in, start_flow_index, MLX5_ESW_INDIR_TABLE_FWD_IDX); + MLX5_SET(create_flow_group_in, in, end_flow_index, MLX5_ESW_INDIR_TABLE_FWD_IDX); + e->fwd_grp = mlx5_create_flow_group(e->ft, in); + if (IS_ERR(e->fwd_grp)) { + err = PTR_ERR(e->fwd_grp); + goto err_out; + } + + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; + flow_act.fg = e->fwd_grp; + dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT; + dest.vport.num = e->vport; + dest.vport.vhca_id = MLX5_CAP_GEN(esw->dev, vhca_id); + dest.vport.flags = MLX5_FLOW_DEST_VPORT_VHCA_ID; + e->fwd_rule = mlx5_add_flow_rules(e->ft, spec, &flow_act, &dest, 1); + if (IS_ERR(e->fwd_rule)) { + mlx5_destroy_flow_group(e->fwd_grp); + err = PTR_ERR(e->fwd_rule); + } + +err_out: + kvfree(spec); + kvfree(in); + return err; +} + +static struct mlx5_esw_indir_table_entry * +mlx5_esw_indir_table_entry_create(struct mlx5_eswitch *esw, struct mlx5_flow_attr *attr, + u16 vport, bool decap) +{ + struct mlx5_flow_table_attr ft_attr = {}; + struct mlx5_flow_namespace *root_ns; + struct mlx5_esw_indir_table_entry *e; + struct mlx5_flow_table *ft; + int err = 0; + + root_ns = mlx5_get_flow_namespace(esw->dev, MLX5_FLOW_NAMESPACE_FDB); + if (!root_ns) + return ERR_PTR(-ENOENT); + + e = kzalloc(sizeof(*e), GFP_KERNEL); + if (!e) + return ERR_PTR(-ENOMEM); + + ft_attr.prio = FDB_TC_OFFLOAD; + ft_attr.max_fte = MLX5_ESW_INDIR_TABLE_SIZE; + ft_attr.flags = MLX5_FLOW_TABLE_UNMANAGED; + ft_attr.level = 1; + + ft = mlx5_create_flow_table(root_ns, &ft_attr); + if (IS_ERR(ft)) { + err = PTR_ERR(ft); + goto tbl_err; + } + e->ft = ft; + e->vport = vport; + e->fwd_ref = !decap; + + err = mlx5_create_indir_recirc_group(e); + if (err) + goto recirc_grp_err; + + if (decap) { + err = mlx5_esw_indir_table_rule_get(esw, attr, e); + if (err) + goto recirc_rule_err; + } + + err = mlx5_create_indir_fwd_group(esw, e); + if (err) + goto fwd_grp_err; + + hash_add(esw->fdb_table.offloads.indir->table, &e->hlist, + vport << 16); + + return e; + +fwd_grp_err: + if (decap) + mlx5_esw_indir_table_rule_put(esw, e); +recirc_rule_err: + mlx5_destroy_flow_group(e->recirc_grp); +recirc_grp_err: + mlx5_destroy_flow_table(e->ft); +tbl_err: + kfree(e); + return ERR_PTR(err); +} + +static struct mlx5_esw_indir_table_entry * +mlx5_esw_indir_table_entry_lookup(struct mlx5_eswitch *esw, u16 vport) +{ + struct mlx5_esw_indir_table_entry *e; + u32 key = vport << 16; + + hash_for_each_possible(esw->fdb_table.offloads.indir->table, e, hlist, key) + if (e->vport == vport) + return e; + + return NULL; +} + +struct mlx5_flow_table *mlx5_esw_indir_table_get(struct mlx5_eswitch *esw, + struct mlx5_flow_attr *attr, + u16 vport, bool decap) +{ + struct mlx5_esw_indir_table_entry *e; + int err; + + mutex_lock(&esw->fdb_table.offloads.indir->lock); + e = mlx5_esw_indir_table_entry_lookup(esw, vport); + if (e) { + if (!decap) { + e->fwd_ref++; + } else { + err = mlx5_esw_indir_table_rule_get(esw, attr, e); + if (err) + goto out_err; + } + } else { + e = mlx5_esw_indir_table_entry_create(esw, attr, vport, decap); + if (IS_ERR(e)) { + err = PTR_ERR(e); + esw_warn(esw->dev, "Failed to create indirection table, err %d.\n", err); + goto out_err; + } + } + mutex_unlock(&esw->fdb_table.offloads.indir->lock); + return e->ft; + +out_err: + mutex_unlock(&esw->fdb_table.offloads.indir->lock); + return ERR_PTR(err); +} + +void mlx5_esw_indir_table_put(struct mlx5_eswitch *esw, + u16 vport, bool decap) +{ + struct mlx5_esw_indir_table_entry *e; + + mutex_lock(&esw->fdb_table.offloads.indir->lock); + e = mlx5_esw_indir_table_entry_lookup(esw, vport); + if (!e) + goto out; + + if (!decap) + e->fwd_ref--; + else + mlx5_esw_indir_table_rule_put(esw, e); + + if (e->fwd_ref || e->recirc_rule) + goto out; + + hash_del(&e->hlist); + mlx5_destroy_flow_group(e->recirc_grp); + mlx5_del_flow_rules(e->fwd_rule); + mlx5_destroy_flow_group(e->fwd_grp); + mlx5_destroy_flow_table(e->ft); + kfree(e); +out: + mutex_unlock(&esw->fdb_table.offloads.indir->lock); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/indir_table.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/indir_table.h new file mode 100644 index 000000000..036f5b3a3 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/indir_table.h @@ -0,0 +1,72 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2021 Mellanox Technologies. */ + +#ifndef __MLX5_ESW_FT_H__ +#define __MLX5_ESW_FT_H__ + +#ifdef CONFIG_MLX5_CLS_ACT + +struct mlx5_esw_indir_table * +mlx5_esw_indir_table_init(void); +void +mlx5_esw_indir_table_destroy(struct mlx5_esw_indir_table *indir); + +struct mlx5_flow_table *mlx5_esw_indir_table_get(struct mlx5_eswitch *esw, + struct mlx5_flow_attr *attr, + u16 vport, bool decap); +void mlx5_esw_indir_table_put(struct mlx5_eswitch *esw, + u16 vport, bool decap); + +bool +mlx5_esw_indir_table_needed(struct mlx5_eswitch *esw, + struct mlx5_flow_attr *attr, + u16 vport_num, + struct mlx5_core_dev *dest_mdev); + +u16 +mlx5_esw_indir_table_decap_vport(struct mlx5_flow_attr *attr); + +#else +/* indir API stubs */ +static inline struct mlx5_esw_indir_table * +mlx5_esw_indir_table_init(void) +{ + return NULL; +} + +static inline void +mlx5_esw_indir_table_destroy(struct mlx5_esw_indir_table *indir) +{ +} + +static inline struct mlx5_flow_table * +mlx5_esw_indir_table_get(struct mlx5_eswitch *esw, + struct mlx5_flow_attr *attr, + u16 vport, bool decap) +{ + return ERR_PTR(-EOPNOTSUPP); +} + +static inline void +mlx5_esw_indir_table_put(struct mlx5_eswitch *esw, + u16 vport, bool decap) +{ +} + +static inline bool +mlx5_esw_indir_table_needed(struct mlx5_eswitch *esw, + struct mlx5_flow_attr *attr, + u16 vport_num, + struct mlx5_core_dev *dest_mdev) +{ + return false; +} + +static inline u16 +mlx5_esw_indir_table_decap_vport(struct mlx5_flow_attr *attr) +{ + return 0; +} +#endif + +#endif /* __MLX5_ESW_FT_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c new file mode 100644 index 000000000..fabe49a35 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c @@ -0,0 +1,529 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2021 Mellanox Technologies Ltd */ + +#include <linux/etherdevice.h> +#include <linux/mlx5/driver.h> +#include <linux/mlx5/mlx5_ifc.h> +#include <linux/mlx5/vport.h> +#include <linux/mlx5/fs.h> +#include "esw/acl/lgcy.h" +#include "esw/legacy.h" +#include "mlx5_core.h" +#include "eswitch.h" +#include "fs_core.h" +#include "fs_ft_pool.h" +#include "esw/qos.h" + +enum { + LEGACY_VEPA_PRIO = 0, + LEGACY_FDB_PRIO, +}; + +static int esw_create_legacy_vepa_table(struct mlx5_eswitch *esw) +{ + struct mlx5_flow_table_attr ft_attr = {}; + struct mlx5_core_dev *dev = esw->dev; + struct mlx5_flow_namespace *root_ns; + struct mlx5_flow_table *fdb; + int err; + + root_ns = mlx5_get_fdb_sub_ns(dev, 0); + if (!root_ns) { + esw_warn(dev, "Failed to get FDB flow namespace\n"); + return -EOPNOTSUPP; + } + + /* num FTE 2, num FG 2 */ + ft_attr.prio = LEGACY_VEPA_PRIO; + ft_attr.max_fte = 2; + ft_attr.autogroup.max_num_groups = 2; + fdb = mlx5_create_auto_grouped_flow_table(root_ns, &ft_attr); + if (IS_ERR(fdb)) { + err = PTR_ERR(fdb); + esw_warn(dev, "Failed to create VEPA FDB err %d\n", err); + return err; + } + esw->fdb_table.legacy.vepa_fdb = fdb; + + return 0; +} + +static void esw_destroy_legacy_fdb_table(struct mlx5_eswitch *esw) +{ + esw_debug(esw->dev, "Destroy FDB Table\n"); + if (!esw->fdb_table.legacy.fdb) + return; + + if (esw->fdb_table.legacy.promisc_grp) + mlx5_destroy_flow_group(esw->fdb_table.legacy.promisc_grp); + if (esw->fdb_table.legacy.allmulti_grp) + mlx5_destroy_flow_group(esw->fdb_table.legacy.allmulti_grp); + if (esw->fdb_table.legacy.addr_grp) + mlx5_destroy_flow_group(esw->fdb_table.legacy.addr_grp); + mlx5_destroy_flow_table(esw->fdb_table.legacy.fdb); + + esw->fdb_table.legacy.fdb = NULL; + esw->fdb_table.legacy.addr_grp = NULL; + esw->fdb_table.legacy.allmulti_grp = NULL; + esw->fdb_table.legacy.promisc_grp = NULL; + atomic64_set(&esw->user_count, 0); +} + +static int esw_create_legacy_fdb_table(struct mlx5_eswitch *esw) +{ + int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + struct mlx5_flow_table_attr ft_attr = {}; + struct mlx5_core_dev *dev = esw->dev; + struct mlx5_flow_namespace *root_ns; + struct mlx5_flow_table *fdb; + struct mlx5_flow_group *g; + void *match_criteria; + int table_size; + u32 *flow_group_in; + u8 *dmac; + int err = 0; + + esw_debug(dev, "Create FDB log_max_size(%d)\n", + MLX5_CAP_ESW_FLOWTABLE_FDB(dev, log_max_ft_size)); + + root_ns = mlx5_get_fdb_sub_ns(dev, 0); + if (!root_ns) { + esw_warn(dev, "Failed to get FDB flow namespace\n"); + return -EOPNOTSUPP; + } + + flow_group_in = kvzalloc(inlen, GFP_KERNEL); + if (!flow_group_in) + return -ENOMEM; + + ft_attr.max_fte = POOL_NEXT_SIZE; + ft_attr.prio = LEGACY_FDB_PRIO; + fdb = mlx5_create_flow_table(root_ns, &ft_attr); + if (IS_ERR(fdb)) { + err = PTR_ERR(fdb); + esw_warn(dev, "Failed to create FDB Table err %d\n", err); + goto out; + } + esw->fdb_table.legacy.fdb = fdb; + table_size = fdb->max_fte; + + /* Addresses group : Full match unicast/multicast addresses */ + MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable, + MLX5_MATCH_OUTER_HEADERS); + match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in, match_criteria); + dmac = MLX5_ADDR_OF(fte_match_param, match_criteria, outer_headers.dmac_47_16); + MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 0); + /* Preserve 2 entries for allmulti and promisc rules*/ + MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, table_size - 3); + eth_broadcast_addr(dmac); + g = mlx5_create_flow_group(fdb, flow_group_in); + if (IS_ERR(g)) { + err = PTR_ERR(g); + esw_warn(dev, "Failed to create flow group err(%d)\n", err); + goto out; + } + esw->fdb_table.legacy.addr_grp = g; + + /* Allmulti group : One rule that forwards any mcast traffic */ + MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable, + MLX5_MATCH_OUTER_HEADERS); + MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, table_size - 2); + MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, table_size - 2); + eth_zero_addr(dmac); + dmac[0] = 0x01; + g = mlx5_create_flow_group(fdb, flow_group_in); + if (IS_ERR(g)) { + err = PTR_ERR(g); + esw_warn(dev, "Failed to create allmulti flow group err(%d)\n", err); + goto out; + } + esw->fdb_table.legacy.allmulti_grp = g; + + /* Promiscuous group : + * One rule that forward all unmatched traffic from previous groups + */ + eth_zero_addr(dmac); + MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable, + MLX5_MATCH_MISC_PARAMETERS); + MLX5_SET_TO_ONES(fte_match_param, match_criteria, misc_parameters.source_port); + MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, table_size - 1); + MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, table_size - 1); + g = mlx5_create_flow_group(fdb, flow_group_in); + if (IS_ERR(g)) { + err = PTR_ERR(g); + esw_warn(dev, "Failed to create promisc flow group err(%d)\n", err); + goto out; + } + esw->fdb_table.legacy.promisc_grp = g; + +out: + if (err) + esw_destroy_legacy_fdb_table(esw); + + kvfree(flow_group_in); + return err; +} + +static void esw_destroy_legacy_vepa_table(struct mlx5_eswitch *esw) +{ + esw_debug(esw->dev, "Destroy VEPA Table\n"); + if (!esw->fdb_table.legacy.vepa_fdb) + return; + + mlx5_destroy_flow_table(esw->fdb_table.legacy.vepa_fdb); + esw->fdb_table.legacy.vepa_fdb = NULL; +} + +static int esw_create_legacy_table(struct mlx5_eswitch *esw) +{ + int err; + + memset(&esw->fdb_table.legacy, 0, sizeof(struct legacy_fdb)); + atomic64_set(&esw->user_count, 0); + + err = esw_create_legacy_vepa_table(esw); + if (err) + return err; + + err = esw_create_legacy_fdb_table(esw); + if (err) + esw_destroy_legacy_vepa_table(esw); + + return err; +} + +static void esw_cleanup_vepa_rules(struct mlx5_eswitch *esw) +{ + if (esw->fdb_table.legacy.vepa_uplink_rule) + mlx5_del_flow_rules(esw->fdb_table.legacy.vepa_uplink_rule); + + if (esw->fdb_table.legacy.vepa_star_rule) + mlx5_del_flow_rules(esw->fdb_table.legacy.vepa_star_rule); + + esw->fdb_table.legacy.vepa_uplink_rule = NULL; + esw->fdb_table.legacy.vepa_star_rule = NULL; +} + +static void esw_destroy_legacy_table(struct mlx5_eswitch *esw) +{ + esw_cleanup_vepa_rules(esw); + esw_destroy_legacy_fdb_table(esw); + esw_destroy_legacy_vepa_table(esw); +} + +#define MLX5_LEGACY_SRIOV_VPORT_EVENTS (MLX5_VPORT_UC_ADDR_CHANGE | \ + MLX5_VPORT_MC_ADDR_CHANGE | \ + MLX5_VPORT_PROMISC_CHANGE) + +int esw_legacy_enable(struct mlx5_eswitch *esw) +{ + struct mlx5_vport *vport; + unsigned long i; + int ret; + + ret = esw_create_legacy_table(esw); + if (ret) + return ret; + + mlx5_esw_for_each_vf_vport(esw, i, vport, esw->esw_funcs.num_vfs) + vport->info.link_state = MLX5_VPORT_ADMIN_STATE_AUTO; + + ret = mlx5_eswitch_enable_pf_vf_vports(esw, MLX5_LEGACY_SRIOV_VPORT_EVENTS); + if (ret) + esw_destroy_legacy_table(esw); + return ret; +} + +void esw_legacy_disable(struct mlx5_eswitch *esw) +{ + struct esw_mc_addr *mc_promisc; + + mlx5_eswitch_disable_pf_vf_vports(esw); + + mc_promisc = &esw->mc_promisc; + if (mc_promisc->uplink_rule) + mlx5_del_flow_rules(mc_promisc->uplink_rule); + + esw_destroy_legacy_table(esw); +} + +static int _mlx5_eswitch_set_vepa_locked(struct mlx5_eswitch *esw, + u8 setting) +{ + struct mlx5_flow_destination dest = {}; + struct mlx5_flow_act flow_act = {}; + struct mlx5_flow_handle *flow_rule; + struct mlx5_flow_spec *spec; + int err = 0; + void *misc; + + if (!setting) { + esw_cleanup_vepa_rules(esw); + return 0; + } + + if (esw->fdb_table.legacy.vepa_uplink_rule) + return 0; + + spec = kvzalloc(sizeof(*spec), GFP_KERNEL); + if (!spec) + return -ENOMEM; + + /* Uplink rule forward uplink traffic to FDB */ + misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters); + MLX5_SET(fte_match_set_misc, misc, source_port, MLX5_VPORT_UPLINK); + + misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters); + MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port); + + spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS; + dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; + dest.ft = esw->fdb_table.legacy.fdb; + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; + flow_rule = mlx5_add_flow_rules(esw->fdb_table.legacy.vepa_fdb, spec, + &flow_act, &dest, 1); + if (IS_ERR(flow_rule)) { + err = PTR_ERR(flow_rule); + goto out; + } else { + esw->fdb_table.legacy.vepa_uplink_rule = flow_rule; + } + + /* Star rule to forward all traffic to uplink vport */ + memset(&dest, 0, sizeof(dest)); + dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT; + dest.vport.num = MLX5_VPORT_UPLINK; + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; + flow_rule = mlx5_add_flow_rules(esw->fdb_table.legacy.vepa_fdb, NULL, + &flow_act, &dest, 1); + if (IS_ERR(flow_rule)) { + err = PTR_ERR(flow_rule); + goto out; + } else { + esw->fdb_table.legacy.vepa_star_rule = flow_rule; + } + +out: + kvfree(spec); + if (err) + esw_cleanup_vepa_rules(esw); + return err; +} + +int mlx5_eswitch_set_vepa(struct mlx5_eswitch *esw, u8 setting) +{ + int err = 0; + + if (!esw) + return -EOPNOTSUPP; + + if (!mlx5_esw_allowed(esw)) + return -EPERM; + + mutex_lock(&esw->state_lock); + if (esw->mode != MLX5_ESWITCH_LEGACY) { + err = -EOPNOTSUPP; + goto out; + } + + err = _mlx5_eswitch_set_vepa_locked(esw, setting); + +out: + mutex_unlock(&esw->state_lock); + return err; +} + +int mlx5_eswitch_get_vepa(struct mlx5_eswitch *esw, u8 *setting) +{ + if (!esw) + return -EOPNOTSUPP; + + if (!mlx5_esw_allowed(esw)) + return -EPERM; + + if (esw->mode != MLX5_ESWITCH_LEGACY) + return -EOPNOTSUPP; + + *setting = esw->fdb_table.legacy.vepa_uplink_rule ? 1 : 0; + return 0; +} + +int esw_legacy_vport_acl_setup(struct mlx5_eswitch *esw, struct mlx5_vport *vport) +{ + int ret; + + /* Only non manager vports need ACL in legacy mode */ + if (mlx5_esw_is_manager_vport(esw, vport->vport)) + return 0; + + ret = esw_acl_ingress_lgcy_setup(esw, vport); + if (ret) + goto ingress_err; + + ret = esw_acl_egress_lgcy_setup(esw, vport); + if (ret) + goto egress_err; + + return 0; + +egress_err: + esw_acl_ingress_lgcy_cleanup(esw, vport); +ingress_err: + return ret; +} + +void esw_legacy_vport_acl_cleanup(struct mlx5_eswitch *esw, struct mlx5_vport *vport) +{ + if (mlx5_esw_is_manager_vport(esw, vport->vport)) + return; + + esw_acl_egress_lgcy_cleanup(esw, vport); + esw_acl_ingress_lgcy_cleanup(esw, vport); +} + +int mlx5_esw_query_vport_drop_stats(struct mlx5_core_dev *dev, + struct mlx5_vport *vport, + struct mlx5_vport_drop_stats *stats) +{ + u64 rx_discard_vport_down, tx_discard_vport_down; + struct mlx5_eswitch *esw = dev->priv.eswitch; + u64 bytes = 0; + int err = 0; + + if (esw->mode != MLX5_ESWITCH_LEGACY) + return 0; + + mutex_lock(&esw->state_lock); + if (!vport->enabled) + goto unlock; + + if (!IS_ERR_OR_NULL(vport->egress.legacy.drop_counter)) + mlx5_fc_query(dev, vport->egress.legacy.drop_counter, + &stats->rx_dropped, &bytes); + + if (vport->ingress.legacy.drop_counter) + mlx5_fc_query(dev, vport->ingress.legacy.drop_counter, + &stats->tx_dropped, &bytes); + + if (!MLX5_CAP_GEN(dev, receive_discard_vport_down) && + !MLX5_CAP_GEN(dev, transmit_discard_vport_down)) + goto unlock; + + err = mlx5_query_vport_down_stats(dev, vport->vport, 1, + &rx_discard_vport_down, + &tx_discard_vport_down); + if (err) + goto unlock; + + if (MLX5_CAP_GEN(dev, receive_discard_vport_down)) + stats->rx_dropped += rx_discard_vport_down; + if (MLX5_CAP_GEN(dev, transmit_discard_vport_down)) + stats->tx_dropped += tx_discard_vport_down; + +unlock: + mutex_unlock(&esw->state_lock); + return err; +} + +int mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw, + u16 vport, u16 vlan, u8 qos) +{ + u8 set_flags = 0; + int err = 0; + + if (!mlx5_esw_allowed(esw)) + return vlan ? -EPERM : 0; + + if (vlan || qos) + set_flags = SET_VLAN_STRIP | SET_VLAN_INSERT; + + mutex_lock(&esw->state_lock); + if (esw->mode != MLX5_ESWITCH_LEGACY) { + if (!vlan) + goto unlock; /* compatibility with libvirt */ + + err = -EOPNOTSUPP; + goto unlock; + } + + err = __mlx5_eswitch_set_vport_vlan(esw, vport, vlan, qos, set_flags); + +unlock: + mutex_unlock(&esw->state_lock); + return err; +} + +int mlx5_eswitch_set_vport_spoofchk(struct mlx5_eswitch *esw, + u16 vport, bool spoofchk) +{ + struct mlx5_vport *evport = mlx5_eswitch_get_vport(esw, vport); + bool pschk; + int err = 0; + + if (!mlx5_esw_allowed(esw)) + return -EPERM; + if (IS_ERR(evport)) + return PTR_ERR(evport); + + mutex_lock(&esw->state_lock); + if (esw->mode != MLX5_ESWITCH_LEGACY) { + err = -EOPNOTSUPP; + goto unlock; + } + pschk = evport->info.spoofchk; + evport->info.spoofchk = spoofchk; + if (pschk && !is_valid_ether_addr(evport->info.mac)) + mlx5_core_warn(esw->dev, + "Spoofchk in set while MAC is invalid, vport(%d)\n", + evport->vport); + if (evport->enabled && esw->mode == MLX5_ESWITCH_LEGACY) + err = esw_acl_ingress_lgcy_setup(esw, evport); + if (err) + evport->info.spoofchk = pschk; + +unlock: + mutex_unlock(&esw->state_lock); + return err; +} + +int mlx5_eswitch_set_vport_trust(struct mlx5_eswitch *esw, + u16 vport, bool setting) +{ + struct mlx5_vport *evport = mlx5_eswitch_get_vport(esw, vport); + int err = 0; + + if (!mlx5_esw_allowed(esw)) + return -EPERM; + if (IS_ERR(evport)) + return PTR_ERR(evport); + + mutex_lock(&esw->state_lock); + if (esw->mode != MLX5_ESWITCH_LEGACY) { + err = -EOPNOTSUPP; + goto unlock; + } + evport->info.trusted = setting; + if (evport->enabled) + esw_vport_change_handle_locked(evport); + +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_rate(esw, evport, max_rate, min_rate); + mutex_unlock(&esw->state_lock); + return err; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.h new file mode 100644 index 000000000..e0820bb72 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2021 Mellanox Technologies Ltd */ + +#ifndef __MLX5_ESW_LEGACY_H__ +#define __MLX5_ESW_LEGACY_H__ + +#define MLX5_LEGACY_SRIOV_VPORT_EVENTS (MLX5_VPORT_UC_ADDR_CHANGE | \ + MLX5_VPORT_MC_ADDR_CHANGE | \ + MLX5_VPORT_PROMISC_CHANGE) + +struct mlx5_eswitch; + +int esw_legacy_enable(struct mlx5_eswitch *esw); +void esw_legacy_disable(struct mlx5_eswitch *esw); + +int esw_legacy_vport_acl_setup(struct mlx5_eswitch *esw, struct mlx5_vport *vport); +void esw_legacy_vport_acl_cleanup(struct mlx5_eswitch *esw, struct mlx5_vport *vport); + +int mlx5_esw_query_vport_drop_stats(struct mlx5_core_dev *dev, + struct mlx5_vport *vport, + struct mlx5_vport_drop_stats *stats); +#endif 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 000000000..75015d370 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c @@ -0,0 +1,943 @@ +// 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 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, 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, + 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_core_dev *dev = esw->dev; + int err; + + if (!vport->qos.enabled) + return -EIO; + + err = esw_qos_tsar_config(dev, sched_ctx, 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 && 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; +} + +static int 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; +} + +static int 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 || new_group->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; + + 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); + if (mlx5_destroy_scheduling_element_cmd(esw->dev, + SCHEDULING_HIERARCHY_E_SWITCH, + group->tsar_ix)) + 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_get(struct mlx5_eswitch *esw, struct netlink_ext_ack *extack); +static void esw_qos_put(struct mlx5_eswitch *esw); + +static struct mlx5_esw_rate_group * +esw_qos_create_rate_group(struct mlx5_eswitch *esw, struct netlink_ext_ack *extack) +{ + struct mlx5_esw_rate_group *group; + int err; + + if (!MLX5_CAP_QOS(esw->dev, log_esw_max_sched_depth)) + return ERR_PTR(-EOPNOTSUPP); + + err = esw_qos_get(esw, extack); + if (err) + return ERR_PTR(err); + + group = __esw_qos_create_rate_group(esw, extack); + if (IS_ERR(group)) + esw_qos_put(esw); + + return group; +} + +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 int esw_qos_destroy_rate_group(struct mlx5_eswitch *esw, + struct mlx5_esw_rate_group *group, + struct netlink_ext_ack *extack) +{ + int err; + + err = __esw_qos_destroy_rate_group(esw, group, extack); + esw_qos_put(esw); + + 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; +} + +static int esw_qos_create(struct mlx5_eswitch *esw, struct netlink_ext_ack *extack) +{ + 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 -EOPNOTSUPP; + + if (!esw_qos_element_type_supported(dev, SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR)) + return -EOPNOTSUPP; + + 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); + return err; + } + + 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, extack); + if (IS_ERR(esw->qos.group0)) { + esw_warn(dev, "E-Switch create rate group 0 failed (%ld)\n", + PTR_ERR(esw->qos.group0)); + err = PTR_ERR(esw->qos.group0); + goto err_group0; + } + } + refcount_set(&esw->qos.refcnt, 1); + + return 0; + +err_group0: + if (mlx5_destroy_scheduling_element_cmd(esw->dev, SCHEDULING_HIERARCHY_E_SWITCH, + esw->qos.root_tsar_ix)) + esw_warn(esw->dev, "E-Switch destroy root TSAR failed.\n"); + + return err; +} + +static void esw_qos_destroy(struct mlx5_eswitch *esw) +{ + int err; + + 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); +} + +static int esw_qos_get(struct mlx5_eswitch *esw, struct netlink_ext_ack *extack) +{ + int err = 0; + + lockdep_assert_held(&esw->state_lock); + + if (!refcount_inc_not_zero(&esw->qos.refcnt)) { + /* esw_qos_create() set refcount to 1 only on success. + * No need to decrement on failure. + */ + err = esw_qos_create(esw, extack); + } + + return err; +} + +static void esw_qos_put(struct mlx5_eswitch *esw) +{ + lockdep_assert_held(&esw->state_lock); + if (refcount_dec_and_test(&esw->qos.refcnt)) + esw_qos_destroy(esw); +} + +static int esw_qos_vport_enable(struct mlx5_eswitch *esw, struct mlx5_vport *vport, + u32 max_rate, u32 bw_share, struct netlink_ext_ack *extack) +{ + int err; + + lockdep_assert_held(&esw->state_lock); + if (vport->qos.enabled) + return 0; + + err = esw_qos_get(esw, extack); + if (err) + return err; + + vport->qos.group = esw->qos.group0; + + err = esw_qos_vport_create_sched_element(esw, vport, max_rate, bw_share); + if (err) + goto err_out; + + vport->qos.enabled = true; + trace_mlx5_esw_vport_qos_create(vport, bw_share, max_rate); + + return 0; + +err_out: + esw_qos_put(esw); + + 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 (!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); + + memset(&vport->qos, 0, sizeof(vport->qos)); + trace_mlx5_esw_vport_qos_destroy(vport); + + esw_qos_put(esw); +} + +int mlx5_esw_qos_set_vport_rate(struct mlx5_eswitch *esw, struct mlx5_vport *vport, + u32 max_rate, u32 min_rate) +{ + int err; + + lockdep_assert_held(&esw->state_lock); + err = esw_qos_vport_enable(esw, vport, 0, 0, NULL); + if (err) + return err; + + err = esw_qos_set_vport_min_rate(esw, vport, min_rate, NULL); + if (!err) + err = esw_qos_set_vport_max_rate(esw, vport, max_rate, NULL); + + return err; +} + +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; + int err; + + vport = mlx5_eswitch_get_vport(esw, vport_num); + if (IS_ERR(vport)) + return PTR_ERR(vport); + + mutex_lock(&esw->state_lock); + if (!vport->qos.enabled) { + /* Eswitch QoS wasn't enabled yet. Enable it and vport QoS. */ + err = esw_qos_vport_enable(esw, vport, rate_mbps, vport->qos.bw_share, NULL); + } else { + MLX5_SET(scheduling_context, ctx, max_average_bw, rate_mbps); + + bitmask = MODIFY_SCHEDULING_ELEMENT_IN_MODIFY_BITMASK_MAX_AVERAGE_BW; + err = mlx5_modify_scheduling_element_cmd(esw->dev, + SCHEDULING_HIERARCHY_E_SWITCH, + ctx, + vport->qos.esw_tsar_ix, + bitmask); + } + mutex_unlock(&esw->state_lock); + + return err; +} + +#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 = esw_qos_vport_enable(esw, vport, 0, 0, extack); + if (err) + goto unlock; + + err = esw_qos_set_vport_min_rate(esw, vport, tx_share, extack); +unlock: + 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 = esw_qos_vport_enable(esw, vport, 0, 0, extack); + if (err) + goto unlock; + + err = esw_qos_set_vport_max_rate(esw, vport, tx_max, extack); +unlock: + 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 = 0; + + mutex_lock(&esw->state_lock); + if (!vport->qos.enabled && !group) + goto unlock; + + err = esw_qos_vport_enable(esw, vport, 0, 0, extack); + if (!err) + err = esw_qos_vport_update_group(esw, vport, group, extack); +unlock: + 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 000000000..0141e9d52 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.h @@ -0,0 +1,31 @@ +/* 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_rate(struct mlx5_eswitch *esw, struct mlx5_vport *evport, + u32 max_rate, u32 min_rate); +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/vporttbl.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/vporttbl.c new file mode 100644 index 000000000..749c3957a --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/vporttbl.c @@ -0,0 +1,150 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +// Copyright (c) 2021 Mellanox Technologies. + +#include "eswitch.h" + +/* This struct is used as a key to the hash table and we need it to be packed + * so hash result is consistent + */ +struct mlx5_vport_key { + u32 chain; + u16 prio; + u16 vport; + u16 vhca_id; + struct esw_vport_tbl_namespace *vport_ns; +} __packed; + +struct mlx5_vport_table { + struct hlist_node hlist; + struct mlx5_flow_table *fdb; + u32 num_rules; + struct mlx5_vport_key key; +}; + +static void +esw_vport_tbl_init(struct mlx5_eswitch *esw, struct esw_vport_tbl_namespace *ns) +{ + if (esw->offloads.encap != DEVLINK_ESWITCH_ENCAP_MODE_NONE) + ns->flags |= (MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT | + MLX5_FLOW_TABLE_TUNNEL_EN_DECAP); +} + +static struct mlx5_flow_table * +esw_vport_tbl_create(struct mlx5_eswitch *esw, struct mlx5_flow_namespace *ns, + const struct esw_vport_tbl_namespace *vport_ns) +{ + struct mlx5_flow_table_attr ft_attr = {}; + struct mlx5_flow_table *fdb; + + if (vport_ns->max_num_groups) + ft_attr.autogroup.max_num_groups = vport_ns->max_num_groups; + else + ft_attr.autogroup.max_num_groups = esw->params.large_group_num; + ft_attr.max_fte = vport_ns->max_fte; + ft_attr.prio = FDB_PER_VPORT; + ft_attr.flags = vport_ns->flags; + fdb = mlx5_create_auto_grouped_flow_table(ns, &ft_attr); + if (IS_ERR(fdb)) { + esw_warn(esw->dev, "Failed to create per vport FDB Table err %ld\n", + PTR_ERR(fdb)); + } + + return fdb; +} + +static u32 flow_attr_to_vport_key(struct mlx5_eswitch *esw, + struct mlx5_vport_tbl_attr *attr, + struct mlx5_vport_key *key) +{ + key->vport = attr->vport; + key->chain = attr->chain; + key->prio = attr->prio; + key->vhca_id = MLX5_CAP_GEN(esw->dev, vhca_id); + key->vport_ns = attr->vport_ns; + return jhash(key, sizeof(*key), 0); +} + +/* caller must hold vports.lock */ +static struct mlx5_vport_table * +esw_vport_tbl_lookup(struct mlx5_eswitch *esw, struct mlx5_vport_key *skey, u32 key) +{ + struct mlx5_vport_table *e; + + hash_for_each_possible(esw->fdb_table.offloads.vports.table, e, hlist, key) + if (!memcmp(&e->key, skey, sizeof(*skey))) + return e; + + return NULL; +} + +struct mlx5_flow_table * +mlx5_esw_vporttbl_get(struct mlx5_eswitch *esw, struct mlx5_vport_tbl_attr *attr) +{ + struct mlx5_core_dev *dev = esw->dev; + struct mlx5_flow_namespace *ns; + struct mlx5_flow_table *fdb; + struct mlx5_vport_table *e; + struct mlx5_vport_key skey; + u32 hkey; + + mutex_lock(&esw->fdb_table.offloads.vports.lock); + esw_vport_tbl_init(esw, attr->vport_ns); + hkey = flow_attr_to_vport_key(esw, attr, &skey); + e = esw_vport_tbl_lookup(esw, &skey, hkey); + if (e) { + e->num_rules++; + goto out; + } + + e = kzalloc(sizeof(*e), GFP_KERNEL); + if (!e) { + fdb = ERR_PTR(-ENOMEM); + goto err_alloc; + } + + ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_FDB); + if (!ns) { + esw_warn(dev, "Failed to get FDB namespace\n"); + fdb = ERR_PTR(-ENOENT); + goto err_ns; + } + + fdb = esw_vport_tbl_create(esw, ns, attr->vport_ns); + if (IS_ERR(fdb)) + goto err_ns; + + e->fdb = fdb; + e->num_rules = 1; + e->key = skey; + hash_add(esw->fdb_table.offloads.vports.table, &e->hlist, hkey); +out: + mutex_unlock(&esw->fdb_table.offloads.vports.lock); + return e->fdb; + +err_ns: + kfree(e); +err_alloc: + mutex_unlock(&esw->fdb_table.offloads.vports.lock); + return fdb; +} + +void +mlx5_esw_vporttbl_put(struct mlx5_eswitch *esw, struct mlx5_vport_tbl_attr *attr) +{ + struct mlx5_vport_table *e; + struct mlx5_vport_key key; + u32 hkey; + + mutex_lock(&esw->fdb_table.offloads.vports.lock); + esw_vport_tbl_init(esw, attr->vport_ns); + hkey = flow_attr_to_vport_key(esw, attr, &key); + e = esw_vport_tbl_lookup(esw, &key, hkey); + if (!e || --e->num_rules) + goto out; + + hash_del(&e->hlist); + mlx5_destroy_flow_table(e->fdb); + kfree(e); +out: + mutex_unlock(&esw->fdb_table.offloads.vports.lock); +} |