diff options
Diffstat (limited to 'drivers')
| -rw-r--r-- | drivers/net/ethernet/mellanox/mlx5/core/devlink.c | 2 | ||||
| -rw-r--r-- | drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c | 1037 | ||||
| -rw-r--r-- | drivers/net/ethernet/mellanox/mlx5/core/esw/qos.h | 8 | ||||
| -rw-r--r-- | drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 14 | ||||
| -rw-r--r-- | drivers/net/netdevsim/dev.c | 43 | ||||
| -rw-r--r-- | drivers/net/netdevsim/netdevsim.h | 1 | ||||
| -rw-r--r-- | drivers/net/vxlan/vxlan_vnifilter.c | 13 |
7 files changed, 1075 insertions, 43 deletions
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c index 42218834183a..3ffa3fbacd16 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c @@ -376,6 +376,8 @@ static const struct devlink_ops mlx5_devlink_ops = { .eswitch_encap_mode_get = mlx5_devlink_eswitch_encap_mode_get, .rate_leaf_tx_share_set = mlx5_esw_devlink_rate_leaf_tx_share_set, .rate_leaf_tx_max_set = mlx5_esw_devlink_rate_leaf_tx_max_set, + .rate_leaf_tc_bw_set = mlx5_esw_devlink_rate_leaf_tc_bw_set, + .rate_node_tc_bw_set = mlx5_esw_devlink_rate_node_tc_bw_set, .rate_node_tx_share_set = mlx5_esw_devlink_rate_node_tx_share_set, .rate_node_tx_max_set = mlx5_esw_devlink_rate_node_tx_max_set, .rate_node_new = mlx5_esw_devlink_rate_node_new, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c index b6ae384396b3..154bbb17ec0e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c @@ -64,11 +64,19 @@ static void esw_qos_domain_release(struct mlx5_eswitch *esw) enum sched_node_type { SCHED_NODE_TYPE_VPORTS_TSAR, SCHED_NODE_TYPE_VPORT, + SCHED_NODE_TYPE_TC_ARBITER_TSAR, + SCHED_NODE_TYPE_RATE_LIMITER, + SCHED_NODE_TYPE_VPORT_TC, + SCHED_NODE_TYPE_VPORTS_TC_TSAR, }; static const char * const sched_node_type_str[] = { [SCHED_NODE_TYPE_VPORTS_TSAR] = "vports TSAR", [SCHED_NODE_TYPE_VPORT] = "vport", + [SCHED_NODE_TYPE_TC_ARBITER_TSAR] = "TC Arbiter TSAR", + [SCHED_NODE_TYPE_RATE_LIMITER] = "Rate Limiter", + [SCHED_NODE_TYPE_VPORT_TC] = "vport TC", + [SCHED_NODE_TYPE_VPORTS_TC_TSAR] = "vports TC TSAR", }; struct mlx5_esw_sched_node { @@ -92,6 +100,8 @@ struct mlx5_esw_sched_node { struct mlx5_vport *vport; /* Level in the hierarchy. The root node level is 1. */ u8 level; + /* Valid only when this node represents a traffic class. */ + u8 tc; }; static void esw_qos_node_attach_to_parent(struct mlx5_esw_sched_node *node) @@ -106,6 +116,13 @@ static void esw_qos_node_attach_to_parent(struct mlx5_esw_sched_node *node) } } +static int esw_qos_num_tcs(struct mlx5_core_dev *dev) +{ + int num_tcs = mlx5_max_tc(dev) + 1; + + return num_tcs < DEVLINK_RATE_TCS_MAX ? num_tcs : DEVLINK_RATE_TCS_MAX; +} + static void esw_qos_node_set_parent(struct mlx5_esw_sched_node *node, struct mlx5_esw_sched_node *parent) { @@ -116,8 +133,38 @@ esw_qos_node_set_parent(struct mlx5_esw_sched_node *node, struct mlx5_esw_sched_ esw_qos_node_attach_to_parent(node); } +static void esw_qos_nodes_set_parent(struct list_head *nodes, + struct mlx5_esw_sched_node *parent) +{ + struct mlx5_esw_sched_node *node, *tmp; + + list_for_each_entry_safe(node, tmp, nodes, entry) { + esw_qos_node_set_parent(node, parent); + if (!list_empty(&node->children) && + parent->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR) { + struct mlx5_esw_sched_node *child; + + list_for_each_entry(child, &node->children, entry) { + struct mlx5_vport *vport = child->vport; + + if (vport) + vport->qos.sched_node->parent = parent; + } + } + } +} + void mlx5_esw_qos_vport_qos_free(struct mlx5_vport *vport) { + if (vport->qos.sched_nodes) { + int num_tcs = esw_qos_num_tcs(vport->qos.sched_node->esw->dev); + int i; + + for (i = 0; i < num_tcs; i++) + kfree(vport->qos.sched_nodes[i]); + kfree(vport->qos.sched_nodes); + } + kfree(vport->qos.sched_node); memset(&vport->qos, 0, sizeof(vport->qos)); } @@ -141,16 +188,37 @@ mlx5_esw_qos_vport_get_parent(const struct mlx5_vport *vport) static void esw_qos_sched_elem_warn(struct mlx5_esw_sched_node *node, int err, const char *op) { - if (node->vport) { + switch (node->type) { + case SCHED_NODE_TYPE_VPORTS_TC_TSAR: + esw_warn(node->esw->dev, + "E-Switch %s %s scheduling element failed (tc=%d,err=%d)\n", + op, sched_node_type_str[node->type], node->tc, err); + break; + case SCHED_NODE_TYPE_VPORT_TC: + esw_warn(node->esw->dev, + "E-Switch %s %s scheduling element failed (vport=%d,tc=%d,err=%d)\n", + op, + sched_node_type_str[node->type], + node->vport->vport, node->tc, err); + break; + case SCHED_NODE_TYPE_VPORT: esw_warn(node->esw->dev, "E-Switch %s %s scheduling element failed (vport=%d,err=%d)\n", op, sched_node_type_str[node->type], node->vport->vport, err); - return; + break; + case SCHED_NODE_TYPE_RATE_LIMITER: + case SCHED_NODE_TYPE_TC_ARBITER_TSAR: + case SCHED_NODE_TYPE_VPORTS_TSAR: + esw_warn(node->esw->dev, + "E-Switch %s %s scheduling element failed (err=%d)\n", + op, sched_node_type_str[node->type], err); + break; + default: + esw_warn(node->esw->dev, + "E-Switch %s scheduling element failed (err=%d)\n", + op, err); + break; } - - esw_warn(node->esw->dev, - "E-Switch %s %s scheduling element failed (err=%d)\n", - op, sched_node_type_str[node->type], err); } static int esw_qos_node_create_sched_element(struct mlx5_esw_sched_node *node, void *ctx, @@ -233,6 +301,24 @@ static int esw_qos_sched_elem_config(struct mlx5_esw_sched_node *node, u32 max_r return 0; } +static int esw_qos_create_rate_limit_element(struct mlx5_esw_sched_node *node, + struct netlink_ext_ack *extack) +{ + u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {}; + + if (!mlx5_qos_element_type_supported( + node->esw->dev, + SCHEDULING_CONTEXT_ELEMENT_TYPE_RATE_LIMIT, + SCHEDULING_HIERARCHY_E_SWITCH)) + return -EOPNOTSUPP; + + MLX5_SET(scheduling_context, sched_ctx, max_average_bw, node->max_rate); + MLX5_SET(scheduling_context, sched_ctx, element_type, + SCHEDULING_CONTEXT_ELEMENT_TYPE_RATE_LIMIT); + + return esw_qos_node_create_sched_element(node, sched_ctx, extack); +} + static u32 esw_qos_calculate_min_rate_divider(struct mlx5_eswitch *esw, struct mlx5_esw_sched_node *parent) { @@ -266,11 +352,13 @@ static u32 esw_qos_calculate_min_rate_divider(struct mlx5_eswitch *esw, return 0; } -static u32 esw_qos_calc_bw_share(u32 min_rate, u32 divider, u32 fw_max) +static u32 esw_qos_calc_bw_share(u32 value, u32 divider, u32 fw_max) { if (!divider) return 0; - return min_t(u32, max_t(u32, DIV_ROUND_UP(min_rate, divider), MLX5_MIN_BW_SHARE), fw_max); + return min_t(u32, fw_max, + max_t(u32, + DIV_ROUND_UP(value, divider), MLX5_MIN_BW_SHARE)); } static void esw_qos_update_sched_node_bw_share(struct mlx5_esw_sched_node *node, @@ -297,7 +385,13 @@ static void esw_qos_normalize_min_rate(struct mlx5_eswitch *esw, if (node->esw != esw || node->ix == esw->qos.root_tsar_ix) continue; - esw_qos_update_sched_node_bw_share(node, divider, extack); + /* Vports TC TSARs don't have a minimum rate configured, + * so there's no need to update the bw_share on them. + */ + if (node->type != SCHED_NODE_TYPE_VPORTS_TC_TSAR) { + esw_qos_update_sched_node_bw_share(node, divider, + extack); + } if (list_empty(&node->children)) continue; @@ -306,6 +400,20 @@ static void esw_qos_normalize_min_rate(struct mlx5_eswitch *esw, } } +static u32 esw_qos_calculate_tc_bw_divider(u32 *tc_bw) +{ + u32 total = 0; + int i; + + for (i = 0; i < DEVLINK_RATE_TCS_MAX; i++) + total += tc_bw[i]; + + /* If total is zero, tc-bw config is disabled and we shouldn't reach + * here. + */ + return WARN_ON(!total) ? 1 : total; +} + static int esw_qos_set_node_min_rate(struct mlx5_esw_sched_node *node, u32 min_rate, struct netlink_ext_ack *extack) { @@ -350,28 +458,64 @@ esw_qos_create_node_sched_elem(struct mlx5_core_dev *dev, u32 parent_element_id, tsar_ix); } -static int esw_qos_vport_create_sched_element(struct mlx5_esw_sched_node *vport_node, - struct netlink_ext_ack *extack) +static int +esw_qos_vport_create_sched_element(struct mlx5_esw_sched_node *vport_node, + struct netlink_ext_ack *extack) { u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {}; struct mlx5_core_dev *dev = vport_node->esw->dev; void *attr; - if (!mlx5_qos_element_type_supported(dev, - SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT, - SCHEDULING_HIERARCHY_E_SWITCH)) + if (!mlx5_qos_element_type_supported( + dev, + SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT, + SCHEDULING_HIERARCHY_E_SWITCH)) return -EOPNOTSUPP; MLX5_SET(scheduling_context, sched_ctx, element_type, SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT); attr = MLX5_ADDR_OF(scheduling_context, sched_ctx, element_attributes); MLX5_SET(vport_element, attr, vport_number, vport_node->vport->vport); - MLX5_SET(scheduling_context, sched_ctx, parent_element_id, vport_node->parent->ix); - MLX5_SET(scheduling_context, sched_ctx, max_average_bw, vport_node->max_rate); + MLX5_SET(scheduling_context, sched_ctx, parent_element_id, + vport_node->parent->ix); + MLX5_SET(scheduling_context, sched_ctx, max_average_bw, + vport_node->max_rate); return esw_qos_node_create_sched_element(vport_node, sched_ctx, extack); } +static int +esw_qos_vport_tc_create_sched_element(struct mlx5_esw_sched_node *vport_tc_node, + u32 rate_limit_elem_ix, + struct netlink_ext_ack *extack) +{ + u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {}; + struct mlx5_core_dev *dev = vport_tc_node->esw->dev; + void *attr; + + if (!mlx5_qos_element_type_supported( + dev, + SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT_TC, + SCHEDULING_HIERARCHY_E_SWITCH)) + return -EOPNOTSUPP; + + MLX5_SET(scheduling_context, sched_ctx, element_type, + SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT_TC); + attr = MLX5_ADDR_OF(scheduling_context, sched_ctx, element_attributes); + MLX5_SET(vport_tc_element, attr, vport_number, + vport_tc_node->vport->vport); + MLX5_SET(vport_tc_element, attr, traffic_class, vport_tc_node->tc); + MLX5_SET(scheduling_context, sched_ctx, max_bw_obj_id, + rate_limit_elem_ix); + MLX5_SET(scheduling_context, sched_ctx, parent_element_id, + vport_tc_node->parent->ix); + MLX5_SET(scheduling_context, sched_ctx, bw_share, + vport_tc_node->bw_share); + + return esw_qos_node_create_sched_element(vport_tc_node, sched_ctx, + extack); +} + static struct mlx5_esw_sched_node * __esw_qos_alloc_node(struct mlx5_eswitch *esw, u32 tsar_ix, enum sched_node_type type, struct mlx5_esw_sched_node *parent) @@ -388,6 +532,14 @@ __esw_qos_alloc_node(struct mlx5_eswitch *esw, u32 tsar_ix, enum sched_node_type node->parent = parent; INIT_LIST_HEAD(&node->children); esw_qos_node_attach_to_parent(node); + if (!parent) { + /* The caller is responsible for inserting the node into the + * parent list if necessary. This function can also be used with + * a NULL parent, which doesn't necessarily indicate that it + * refers to the root scheduling element. + */ + list_del_init(&node->entry); + } return node; } @@ -404,6 +556,149 @@ static void esw_qos_destroy_node(struct mlx5_esw_sched_node *node, struct netlin __esw_qos_free_node(node); } +static int esw_qos_create_vports_tc_node(struct mlx5_esw_sched_node *parent, + u8 tc, struct netlink_ext_ack *extack) +{ + u32 tsar_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {}; + struct mlx5_core_dev *dev = parent->esw->dev; + struct mlx5_esw_sched_node *vports_tc_node; + void *attr; + int err; + + if (!mlx5_qos_element_type_supported( + dev, + SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR, + SCHEDULING_HIERARCHY_E_SWITCH) || + !mlx5_qos_tsar_type_supported(dev, + TSAR_ELEMENT_TSAR_TYPE_DWRR, + SCHEDULING_HIERARCHY_E_SWITCH)) + return -EOPNOTSUPP; + + vports_tc_node = __esw_qos_alloc_node(parent->esw, 0, + SCHED_NODE_TYPE_VPORTS_TC_TSAR, + parent); + if (!vports_tc_node) { + NL_SET_ERR_MSG_MOD(extack, "E-Switch alloc node failed"); + esw_warn(dev, "Failed to alloc vports TC node (tc=%d)\n", tc); + return -ENOMEM; + } + + attr = MLX5_ADDR_OF(scheduling_context, tsar_ctx, element_attributes); + MLX5_SET(tsar_element, attr, tsar_type, TSAR_ELEMENT_TSAR_TYPE_DWRR); + MLX5_SET(tsar_element, attr, traffic_class, tc); + MLX5_SET(scheduling_context, tsar_ctx, parent_element_id, parent->ix); + MLX5_SET(scheduling_context, tsar_ctx, element_type, + SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR); + + err = esw_qos_node_create_sched_element(vports_tc_node, tsar_ctx, + extack); + if (err) + goto err_create_sched_element; + + vports_tc_node->tc = tc; + + return 0; + +err_create_sched_element: + __esw_qos_free_node(vports_tc_node); + return err; +} + +static void +esw_qos_tc_arbiter_get_bw_shares(struct mlx5_esw_sched_node *tc_arbiter_node, + u32 *tc_bw) +{ + struct mlx5_esw_sched_node *vports_tc_node; + + list_for_each_entry(vports_tc_node, &tc_arbiter_node->children, entry) + tc_bw[vports_tc_node->tc] = vports_tc_node->bw_share; +} + +static void +esw_qos_set_tc_arbiter_bw_shares(struct mlx5_esw_sched_node *tc_arbiter_node, + u32 *tc_bw, struct netlink_ext_ack *extack) +{ + struct mlx5_eswitch *esw = tc_arbiter_node->esw; + struct mlx5_esw_sched_node *vports_tc_node; + u32 divider, fw_max_bw_share; + + fw_max_bw_share = MLX5_CAP_QOS(esw->dev, max_tsar_bw_share); + divider = esw_qos_calculate_tc_bw_divider(tc_bw); + list_for_each_entry(vports_tc_node, &tc_arbiter_node->children, entry) { + u8 tc = vports_tc_node->tc; + u32 bw_share; + + bw_share = tc_bw[tc] * fw_max_bw_share; + bw_share = esw_qos_calc_bw_share(bw_share, divider, + fw_max_bw_share); + esw_qos_sched_elem_config(vports_tc_node, 0, bw_share, extack); + } +} + +static void +esw_qos_destroy_vports_tc_nodes(struct mlx5_esw_sched_node *tc_arbiter_node, + struct netlink_ext_ack *extack) +{ + struct mlx5_esw_sched_node *vports_tc_node, *tmp; + + list_for_each_entry_safe(vports_tc_node, tmp, + &tc_arbiter_node->children, entry) + esw_qos_destroy_node(vports_tc_node, extack); +} + +static int +esw_qos_create_vports_tc_nodes(struct mlx5_esw_sched_node *tc_arbiter_node, + struct netlink_ext_ack *extack) +{ + struct mlx5_eswitch *esw = tc_arbiter_node->esw; + int err, i, num_tcs = esw_qos_num_tcs(esw->dev); + + for (i = 0; i < num_tcs; i++) { + err = esw_qos_create_vports_tc_node(tc_arbiter_node, i, extack); + if (err) + goto err_tc_node_create; + } + + return 0; + +err_tc_node_create: + esw_qos_destroy_vports_tc_nodes(tc_arbiter_node, NULL); + return err; +} + +static int esw_qos_create_tc_arbiter_sched_elem( + struct mlx5_esw_sched_node *tc_arbiter_node, + struct netlink_ext_ack *extack) +{ + u32 tsar_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {}; + u32 tsar_parent_ix; + void *attr; + + if (!mlx5_qos_tsar_type_supported(tc_arbiter_node->esw->dev, + TSAR_ELEMENT_TSAR_TYPE_TC_ARB, + SCHEDULING_HIERARCHY_E_SWITCH)) { + NL_SET_ERR_MSG_MOD(extack, + "E-Switch TC Arbiter scheduling element is not supported"); + return -EOPNOTSUPP; + } + + attr = MLX5_ADDR_OF(scheduling_context, tsar_ctx, element_attributes); + MLX5_SET(tsar_element, attr, tsar_type, TSAR_ELEMENT_TSAR_TYPE_TC_ARB); + tsar_parent_ix = tc_arbiter_node->parent ? tc_arbiter_node->parent->ix : + tc_arbiter_node->esw->qos.root_tsar_ix; + MLX5_SET(scheduling_context, tsar_ctx, parent_element_id, + tsar_parent_ix); + MLX5_SET(scheduling_context, tsar_ctx, element_type, + SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR); + MLX5_SET(scheduling_context, tsar_ctx, max_average_bw, + tc_arbiter_node->max_rate); + MLX5_SET(scheduling_context, tsar_ctx, bw_share, + tc_arbiter_node->bw_share); + + return esw_qos_node_create_sched_element(tc_arbiter_node, tsar_ctx, + extack); +} + static struct mlx5_esw_sched_node * __esw_qos_create_vports_sched_node(struct mlx5_eswitch *esw, struct mlx5_esw_sched_node *parent, struct netlink_ext_ack *extack) @@ -426,6 +721,7 @@ __esw_qos_create_vports_sched_node(struct mlx5_eswitch *esw, struct mlx5_esw_sch goto err_alloc_node; } + list_add_tail(&node->entry, &esw->qos.domain->nodes); esw_qos_normalize_min_rate(esw, NULL, extack); trace_mlx5_esw_node_qos_create(esw->dev, node, node->ix); @@ -467,6 +763,9 @@ static void __esw_qos_destroy_node(struct mlx5_esw_sched_node *node, struct netl { struct mlx5_eswitch *esw = node->esw; + if (node->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR) + esw_qos_destroy_vports_tc_nodes(node, extack); + trace_mlx5_esw_node_qos_destroy(esw->dev, node, node->ix); esw_qos_destroy_node(node, extack); esw_qos_normalize_min_rate(esw, NULL, extack); @@ -498,6 +797,9 @@ static int esw_qos_create(struct mlx5_eswitch *esw, struct netlink_ext_ack *exta SCHED_NODE_TYPE_VPORTS_TSAR, NULL)) esw->qos.node0 = ERR_PTR(-ENOMEM); + else + list_add_tail(&esw->qos.node0->entry, + &esw->qos.domain->nodes); } if (IS_ERR(esw->qos.node0)) { err = PTR_ERR(esw->qos.node0); @@ -555,12 +857,239 @@ static void esw_qos_put(struct mlx5_eswitch *esw) esw_qos_destroy(esw); } +static void +esw_qos_tc_arbiter_scheduling_teardown(struct mlx5_esw_sched_node *node, + struct netlink_ext_ack *extack) +{ + /* Clean up all Vports TC nodes within the TC arbiter node. */ + esw_qos_destroy_vports_tc_nodes(node, extack); + /* Destroy the scheduling element for the TC arbiter node itself. */ + esw_qos_node_destroy_sched_element(node, extack); +} + +static int esw_qos_tc_arbiter_scheduling_setup(struct mlx5_esw_sched_node *node, + struct netlink_ext_ack *extack) +{ + u32 curr_ix = node->ix; + int err; + + err = esw_qos_create_tc_arbiter_sched_elem(node, extack); + if (err) + return err; + /* Initialize the vports TC nodes within created TC arbiter TSAR. */ + err = esw_qos_create_vports_tc_nodes(node, extack); + if (err) + goto err_vports_tc_nodes; + + node->type = SCHED_NODE_TYPE_TC_ARBITER_TSAR; + + return 0; + +err_vports_tc_nodes: + /* If initialization fails, clean up the scheduling element + * for the TC arbiter node. + */ + esw_qos_node_destroy_sched_element(node, NULL); + node->ix = curr_ix; + return err; +} + +static int +esw_qos_create_vport_tc_sched_node(struct mlx5_vport *vport, + u32 rate_limit_elem_ix, + struct mlx5_esw_sched_node *vports_tc_node, + struct netlink_ext_ack *extack) +{ + struct mlx5_esw_sched_node *vport_node = vport->qos.sched_node; + struct mlx5_esw_sched_node *vport_tc_node; + u8 tc = vports_tc_node->tc; + int err; + + vport_tc_node = __esw_qos_alloc_node(vport_node->esw, 0, + SCHED_NODE_TYPE_VPORT_TC, + vports_tc_node); + if (!vport_tc_node) + return -ENOMEM; + + vport_tc_node->min_rate = vport_node->min_rate; + vport_tc_node->tc = tc; + vport_tc_node->vport = vport; + err = esw_qos_vport_tc_create_sched_element(vport_tc_node, + rate_limit_elem_ix, + extack); + if (err) + goto err_out; + + vport->qos.sched_nodes[tc] = vport_tc_node; + + return 0; +err_out: + __esw_qos_free_node(vport_tc_node); + return err; +} + +static void +esw_qos_destroy_vport_tc_sched_elements(struct mlx5_vport *vport, + struct netlink_ext_ack *extack) +{ + int i, num_tcs = esw_qos_num_tcs(vport->qos.sched_node->esw->dev); + + for (i = 0; i < num_tcs; i++) { + if (vport->qos.sched_nodes[i]) { + __esw_qos_destroy_node(vport->qos.sched_nodes[i], + extack); + } + } + + kfree(vport->qos.sched_nodes); + vport->qos.sched_nodes = NULL; +} + +static int +esw_qos_create_vport_tc_sched_elements(struct mlx5_vport *vport, + enum sched_node_type type, + struct netlink_ext_ack *extack) +{ + struct mlx5_esw_sched_node *vport_node = vport->qos.sched_node; + struct mlx5_esw_sched_node *tc_arbiter_node, *vports_tc_node; + int err, num_tcs = esw_qos_num_tcs(vport_node->esw->dev); + u32 rate_limit_elem_ix; + + vport->qos.sched_nodes = kcalloc(num_tcs, + sizeof(struct mlx5_esw_sched_node *), + GFP_KERNEL); + if (!vport->qos.sched_nodes) { + NL_SET_ERR_MSG_MOD(extack, + "Allocating the vport TC scheduling elements failed."); + return -ENOMEM; + } + + rate_limit_elem_ix = type == SCHED_NODE_TYPE_RATE_LIMITER ? + vport_node->ix : 0; + tc_arbiter_node = type == SCHED_NODE_TYPE_RATE_LIMITER ? + vport_node->parent : vport_node; + list_for_each_entry(vports_tc_node, &tc_arbiter_node->children, entry) { + err = esw_qos_create_vport_tc_sched_node(vport, + rate_limit_elem_ix, + vports_tc_node, + extack); + if (err) + goto err_create_vport_tc; + } + + return 0; + +err_create_vport_tc: + esw_qos_destroy_vport_tc_sched_elements(vport, NULL); + + return err; +} + +static int +esw_qos_vport_tc_enable(struct mlx5_vport *vport, enum sched_node_type type, + struct netlink_ext_ack *extack) +{ + struct mlx5_esw_sched_node *vport_node = vport->qos.sched_node; + int err, new_level, max_level; + + if (type == SCHED_NODE_TYPE_TC_ARBITER_TSAR) { + /* Increase the parent's level by 2 to account for both the + * TC arbiter and the vports TC scheduling element. + */ + new_level = vport_node->parent->level + 2; + max_level = 1 << MLX5_CAP_QOS(vport_node->esw->dev, + log_esw_max_sched_depth); + if (new_level > max_level) { + NL_SET_ERR_MSG_MOD(extack, + "TC arbitration on leafs is not supported beyond max scheduling depth"); + return -EOPNOTSUPP; + } + } + + esw_assert_qos_lock_held(vport->dev->priv.eswitch); + + if (type == SCHED_NODE_TYPE_RATE_LIMITER) + err = esw_qos_create_rate_limit_element(vport_node, extack); + else + err = esw_qos_tc_arbiter_scheduling_setup(vport_node, extack); + if (err) + return err; + + /* Rate limiters impact multiple nodes not directly connected to them + * and are not direct members of the QoS hierarchy. + * Unlink it from the parent to reflect that. + */ + if (type == SCHED_NODE_TYPE_RATE_LIMITER) { + list_del_init(&vport_node->entry); + vport_node->level = 0; + } + + err = esw_qos_create_vport_tc_sched_elements(vport, type, extack); + if (err) + goto err_sched_nodes; + + return 0; + +err_sched_nodes: + if (type == SCHED_NODE_TYPE_RATE_LIMITER) { + esw_qos_node_destroy_sched_element(vport_node, NULL); + list_add_tail(&vport_node->entry, + &vport_node->parent->children); + vport_node->level = vport_node->parent->level + 1; + } else { + esw_qos_tc_arbiter_scheduling_teardown(vport_node, NULL); + } + return err; +} + +static void esw_qos_vport_tc_disable(struct mlx5_vport *vport, + struct netlink_ext_ack *extack) +{ + struct mlx5_esw_sched_node *vport_node = vport->qos.sched_node; + enum sched_node_type curr_type = vport_node->type; + + esw_qos_destroy_vport_tc_sched_elements(vport, extack); + + if (curr_type == SCHED_NODE_TYPE_RATE_LIMITER) + esw_qos_node_destroy_sched_element(vport_node, extack); + else + esw_qos_tc_arbiter_scheduling_teardown(vport_node, extack); +} + +static int esw_qos_set_vport_tcs_min_rate(struct mlx5_vport *vport, + u32 min_rate, + struct netlink_ext_ack *extack) +{ + struct mlx5_esw_sched_node *vport_node = vport->qos.sched_node; + int err, i, num_tcs = esw_qos_num_tcs(vport_node->esw->dev); + + for (i = 0; i < num_tcs; i++) { + err = esw_qos_set_node_min_rate(vport->qos.sched_nodes[i], + min_rate, extack); + if (err) + goto err_out; + } + vport_node->min_rate = min_rate; + + return 0; +err_out: + for (--i; i >= 0; i--) { + esw_qos_set_node_min_rate(vport->qos.sched_nodes[i], + vport_node->min_rate, extack); + } + return err; +} + static void esw_qos_vport_disable(struct mlx5_vport *vport, struct netlink_ext_ack *extack) { struct mlx5_esw_sched_node *vport_node = vport->qos.sched_node; struct mlx5_esw_sched_node *parent = vport_node->parent; + enum sched_node_type curr_type = vport_node->type; - esw_qos_node_destroy_sched_element(vport_node, extack); + if (curr_type == SCHED_NODE_TYPE_VPORT) + esw_qos_node_destroy_sched_element(vport_node, extack); + else + esw_qos_vport_tc_disable(vport, extack); vport_node->bw_share = 0; list_del_init(&vport_node->entry); @@ -569,7 +1098,9 @@ static void esw_qos_vport_disable(struct mlx5_vport *vport, struct netlink_ext_a trace_mlx5_esw_vport_qos_destroy(vport_node->esw->dev, vport); } -static int esw_qos_vport_enable(struct mlx5_vport *vport, struct mlx5_esw_sched_node *parent, +static int esw_qos_vport_enable(struct mlx5_vport *vport, + enum sched_node_type type, + struct mlx5_esw_sched_node *parent, struct netlink_ext_ack *extack) { int err; @@ -577,10 +1108,16 @@ static int esw_qos_vport_enable(struct mlx5_vport *vport, struct mlx5_esw_sched_ esw_assert_qos_lock_held(vport->dev->priv.eswitch); esw_qos_node_set_parent(vport->qos.sched_node, parent); - err = esw_qos_vport_create_sched_element(vport->qos.sched_node, extack); + if (type == SCHED_NODE_TYPE_VPORT) { + err = esw_qos_vport_create_sched_element(vport->qos.sched_node, + extack); + } else { + err = esw_qos_vport_tc_enable(vport, type, extack); + } if (err) return err; + vport->qos.sched_node->type = type; esw_qos_normalize_min_rate(parent->esw, parent, extack); trace_mlx5_esw_vport_qos_create(vport->dev, vport, vport->qos.sched_node->max_rate, @@ -611,9 +1148,8 @@ static int mlx5_esw_qos_vport_enable(struct mlx5_vport *vport, enum sched_node_t sched_node->min_rate = min_rate; sched_node->vport = vport; vport->qos.sched_node = sched_node; - err = esw_qos_vport_enable(vport, parent, extack); + err = esw_qos_vport_enable(vport, type, parent, extack); if (err) { - __esw_qos_free_node(sched_node); esw_qos_put(esw); vport->qos.sched_node = NULL; } @@ -666,6 +1202,8 @@ static int mlx5_esw_qos_set_vport_min_rate(struct mlx5_vport *vport, u32 min_rat if (!vport_node) return mlx5_esw_qos_vport_enable(vport, SCHED_NODE_TYPE_VPORT, NULL, 0, min_rate, extack); + else if (vport_node->type == SCHED_NODE_TYPE_RATE_LIMITER) + return esw_qos_set_vport_tcs_min_rate(vport, min_rate, extack); else return esw_qos_set_node_min_rate(vport_node, min_rate, extack); } @@ -698,12 +1236,73 @@ bool mlx5_esw_qos_get_vport_rate(struct mlx5_vport *vport, u32 *max_rate, u32 *m return enabled; } +static int esw_qos_vport_tc_check_type(enum sched_node_type curr_type, + enum sched_node_type new_type, + struct netlink_ext_ack *extack) +{ + if (curr_type == SCHED_NODE_TYPE_TC_ARBITER_TSAR && + new_type == SCHED_NODE_TYPE_RATE_LIMITER) { + NL_SET_ERR_MSG_MOD(extack, + "Cannot switch from vport-level TC arbitration to node-level TC arbitration"); + return -EOPNOTSUPP; + } + + if (curr_type == SCHED_NODE_TYPE_RATE_LIMITER && + new_type == SCHED_NODE_TYPE_TC_ARBITER_TSAR) { + NL_SET_ERR_MSG_MOD(extack, + "Cannot switch from node-level TC arbitration to vport-level TC arbitration"); + return -EOPNOTSUPP; + } + + return 0; +} + +static int esw_qos_vport_update(struct mlx5_vport *vport, + enum sched_node_type type, + struct mlx5_esw_sched_node *parent, + struct netlink_ext_ack *extack) +{ + struct mlx5_esw_sched_node *curr_parent = vport->qos.sched_node->parent; + enum sched_node_type curr_type = vport->qos.sched_node->type; + u32 curr_tc_bw[DEVLINK_RATE_TCS_MAX] = {0}; + int err; + + esw_assert_qos_lock_held(vport->dev->priv.eswitch); + parent = parent ?: curr_parent; + if (curr_type == type && curr_parent == parent) + return 0; + + err = esw_qos_vport_tc_check_type(curr_type, type, extack); + if (err) + return err; + + if (curr_type == SCHED_NODE_TYPE_TC_ARBITER_TSAR && curr_type == type) { + esw_qos_tc_arbiter_get_bw_shares(vport->qos.sched_node, + curr_tc_bw); + } + + esw_qos_vport_disable(vport, extack); + + err = esw_qos_vport_enable(vport, type, parent, extack); + if (err) { + esw_qos_vport_enable(vport, curr_type, curr_parent, NULL); + extack = NULL; + } + + if (curr_type == SCHED_NODE_TYPE_TC_ARBITER_TSAR && curr_type == type) { + esw_qos_set_tc_arbiter_bw_shares(vport->qos.sched_node, + curr_tc_bw, extack); + } + + return err; +} + static int esw_qos_vport_update_parent(struct mlx5_vport *vport, struct mlx5_esw_sched_node *parent, struct netlink_ext_ack *extack) { struct mlx5_eswitch *esw = vport->dev->priv.eswitch; struct mlx5_esw_sched_node *curr_parent; - int err; + enum sched_node_type type; esw_assert_qos_lock_held(esw); curr_parent = vport->qos.sched_node->parent; @@ -711,15 +1310,205 @@ static int esw_qos_vport_update_parent(struct mlx5_vport *vport, struct mlx5_esw if (curr_parent == parent) return 0; - esw_qos_vport_disable(vport, extack); + /* Set vport QoS type based on parent node type if different from + * default QoS; otherwise, use the vport's current QoS type. + */ + if (parent->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR) + type = SCHED_NODE_TYPE_RATE_LIMITER; + else if (curr_parent->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR) + type = SCHED_NODE_TYPE_VPORT; + else + type = vport->qos.sched_node->type; + + return esw_qos_vport_update(vport, type, parent, extack); +} - err = esw_qos_vport_enable(vport, parent, extack); +static void +esw_qos_switch_vport_tcs_to_vport(struct mlx5_esw_sched_node *tc_arbiter_node, + struct mlx5_esw_sched_node *node, + struct netlink_ext_ack *extack) +{ + struct mlx5_esw_sched_node *vports_tc_node, *vport_tc_node, *tmp; + + vports_tc_node = list_first_entry(&tc_arbiter_node->children, + struct mlx5_esw_sched_node, + entry); + + list_for_each_entry_safe(vport_tc_node, tmp, &vports_tc_node->children, + entry) + esw_qos_vport_update_parent(vport_tc_node->vport, node, extack); +} + +static int esw_qos_switch_tc_arbiter_node_to_vports( + struct mlx5_esw_sched_node *tc_arbiter_node, + struct mlx5_esw_sched_node *node, + struct netlink_ext_ack *extack) +{ + u32 parent_tsar_ix = node->parent ? + node->parent->ix : node->esw->qos.root_tsar_ix; + int err; + + err = esw_qos_create_node_sched_elem(node->esw->dev, parent_tsar_ix, + node->max_rate, node->bw_share, + &node->ix); if (err) { - if (esw_qos_vport_enable(vport, curr_parent, NULL)) - esw_warn(parent->esw->dev, "vport restore QoS failed (vport=%d)\n", - vport->vport); + NL_SET_ERR_MSG_MOD(extack, + "Failed to create scheduling element for vports node when disabliing vports TC QoS"); + return err; + } + + node->type = SCHED_NODE_TYPE_VPORTS_TSAR; + + /* Disable TC QoS for vports in the arbiter node. */ + esw_qos_switch_vport_tcs_to_vport(tc_arbiter_node, node, extack); + + return 0; +} + +static int esw_qos_switch_vports_node_to_tc_arbiter( + struct mlx5_esw_sched_node *node, + struct mlx5_esw_sched_node *tc_arbiter_node, + struct netlink_ext_ack *extack) +{ + struct mlx5_esw_sched_node *vport_node, *tmp; + struct mlx5_vport *vport; + int err; + + /* Enable TC QoS for each vport in the node. */ + list_for_each_entry_safe(vport_node, tmp, &node->children, entry) { + vport = vport_node->vport; + err = esw_qos_vport_update_parent(vport, tc_arbiter_node, + extack); + if (err) + goto err_out; + } + + /* Destroy the current vports node TSAR. */ + err = mlx5_destroy_scheduling_element_cmd(node->esw->dev, + SCHEDULING_HIERARCHY_E_SWITCH, + node->ix); + if (err) + goto err_out; + + return 0; +err_out: + /* Restore vports back into the node if an error occurs. */ + esw_qos_switch_vport_tcs_to_vport(tc_arbiter_node, node, NULL); + + return err; +} + +static struct mlx5_esw_sched_node * +esw_qos_move_node(struct mlx5_esw_sched_node *curr_node) +{ + struct mlx5_esw_sched_node *new_node; + + new_node = __esw_qos_alloc_node(curr_node->esw, curr_node->ix, + curr_node->type, NULL); + if (!IS_ERR(new_node)) + esw_qos_nodes_set_parent(&curr_node->children, new_node); + + return new_node; +} + +static int esw_qos_node_disable_tc_arbitration(struct mlx5_esw_sched_node *node, + struct netlink_ext_ack *extack) +{ + struct mlx5_esw_sched_node *curr_node; + int err; + + if (node->type != SCHED_NODE_TYPE_TC_ARBITER_TSAR) + return 0; + + /* Allocate a new rate node to hold the current state, which will allow + * for restoring the vports back to this node after disabling TC + * arbitration. + */ + curr_node = esw_qos_move_node(node); + if (IS_ERR(curr_node)) { + NL_SET_ERR_MSG_MOD(extack, "Failed setting up vports node"); + return PTR_ERR(curr_node); + } + + /* Disable TC QoS for all vports, and assign them back to the node. */ + err = esw_qos_switch_tc_arbiter_node_to_vports(curr_node, node, extack); + if (err) + goto err_out; + + /* Clean up the TC arbiter node after disabling TC QoS for vports. */ + esw_qos_tc_arbiter_scheduling_teardown(curr_node, extack); + goto out; +err_out: + esw_qos_nodes_set_parent(&curr_node->children, node); +out: + __esw_qos_free_node(curr_node); + return err; +} + +static int esw_qos_node_enable_tc_arbitration(struct mlx5_esw_sched_node *node, + struct netlink_ext_ack *extack) +{ + struct mlx5_esw_sched_node *curr_node, *child; + int err, new_level, max_level; + + if (node->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR) + return 0; + + /* Increase the hierarchy level by one to account for the additional + * vports TC scheduling node, and verify that the new level does not + * exceed the maximum allowed depth. + */ + new_level = node->level + 1; + max_level = 1 << MLX5_CAP_QOS(node->esw->dev, log_esw_max_sched_depth); + if (new_level > max_level) { + NL_SET_ERR_MSG_MOD(extack, + "TC arbitration on nodes is not supported beyond max scheduling depth"); + return -EOPNOTSUPP; + } + + /* Ensure the node does not contain non-leaf children before assigning + * TC bandwidth. + */ + if (!list_empty(&node->children)) { + list_for_each_entry(child, &node->children, entry) { + if (!child->vport) { + NL_SET_ERR_MSG_MOD(extack, + "Cannot configure TC bandwidth on a node with non-leaf children"); + return -EOPNOTSUPP; + } + } } + /* Allocate a new node that will store the information of the current + * node. This will be used later to restore the node if necessary. + */ + curr_node = esw_qos_move_node(node); + if (IS_ERR(curr_node)) { + NL_SET_ERR_MSG_MOD(extack, "Failed setting up node TC QoS"); + return PTR_ERR(curr_node); + } + + /* Initialize the TC arbiter node for QoS management. + * This step prepares the node for handling Traffic Class arbitration. + */ + err = esw_qos_tc_arbiter_scheduling_setup(node, extack); + if (err) + goto err_setup; + + /* Enable TC QoS for each vport within the current node. */ + err = esw_qos_switch_vports_node_to_tc_arbiter(curr_node, node, extack); + if (err) + goto err_switch_vports; + goto out; + +err_switch_vports: + esw_qos_tc_arbiter_scheduling_teardown(node, NULL); + node->ix = curr_node->ix; + node->type = curr_node->type; +err_setup: + esw_qos_nodes_set_parent(&curr_node->children, node); +out: + __esw_qos_free_node(curr_node); return err; } @@ -848,6 +1637,41 @@ static int esw_qos_devlink_rate_to_mbps(struct mlx5_core_dev *mdev, const char * return 0; } +static bool esw_qos_validate_unsupported_tc_bw(struct mlx5_eswitch *esw, + u32 *tc_bw) +{ + int i, num_tcs = esw_qos_num_tcs(esw->dev); + + for (i = num_tcs; i < DEVLINK_RATE_TCS_MAX; i++) { + if (tc_bw[i]) + return false; + } + + return true; +} + +static bool esw_qos_vport_validate_unsupported_tc_bw(struct mlx5_vport *vport, + u32 *tc_bw) +{ + struct mlx5_eswitch *esw = vport->qos.sched_node ? + vport->qos.sched_node->parent->esw : + vport->dev->priv.eswitch; + + return esw_qos_validate_unsupported_tc_bw(esw, tc_bw); +} + +static bool esw_qos_tc_bw_disabled(u32 *tc_bw) +{ + int i; + + for (i = 0; i < DEVLINK_RATE_TCS_MAX; i++) { + if (tc_bw[i]) + return false; + } + + return true; +} + int mlx5_esw_qos_init(struct mlx5_eswitch *esw) { if (esw->qos.domain) @@ -906,6 +1730,90 @@ int mlx5_esw_devlink_rate_leaf_tx_max_set(struct devlink_rate *rate_leaf, void * return err; } +int mlx5_esw_devlink_rate_leaf_tc_bw_set(struct devlink_rate *rate_leaf, + void *priv, + u32 *tc_bw, + struct netlink_ext_ack *extack) +{ + struct mlx5_esw_sched_node *vport_node; + struct mlx5_vport *vport = priv; + struct mlx5_eswitch *esw; + bool disable; + int err = 0; + + esw = vport->dev->priv.eswitch; + if (!mlx5_esw_allowed(esw)) + return -EPERM; + + disable = esw_qos_tc_bw_disabled(tc_bw); + esw_qos_lock(esw); + + if (!esw_qos_vport_validate_unsupported_tc_bw(vport, tc_bw)) { + NL_SET_ERR_MSG_MOD(extack, + "E-Switch traffic classes number is not supported"); + err = -EOPNOTSUPP; + goto unlock; + } + + vport_node = vport->qos.sched_node; + if (disable && !vport_node) + goto unlock; + + if (disable) { + if (vport_node->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR) + err = esw_qos_vport_update(vport, SCHED_NODE_TYPE_VPORT, + NULL, extack); + goto unlock; + } + + if (!vport_node) { + err = mlx5_esw_qos_vport_enable(vport, + SCHED_NODE_TYPE_TC_ARBITER_TSAR, + NULL, 0, 0, extack); + vport_node = vport->qos.sched_node; + } else { + err = esw_qos_vport_update(vport, + SCHED_NODE_TYPE_TC_ARBITER_TSAR, + NULL, extack); + } + if (!err) + esw_qos_set_tc_arbiter_bw_shares(vport_node, tc_bw, extack); +unlock: + esw_qos_unlock(esw); + return err; +} + +int mlx5_esw_devlink_rate_node_tc_bw_set(struct devlink_rate *rate_node, + void *priv, + u32 *tc_bw, + struct netlink_ext_ack *extack) +{ + struct mlx5_esw_sched_node *node = priv; + struct mlx5_eswitch *esw = node->esw; + bool disable; + int err; + + if (!esw_qos_validate_unsupported_tc_bw(esw, tc_bw)) { + NL_SET_ERR_MSG_MOD(extack, + "E-Switch traffic classes number is not supported"); + return -EOPNOTSUPP; + } + + disable = esw_qos_tc_bw_disabled(tc_bw); + esw_qos_lock(esw); + if (disable) { + err = esw_qos_node_disable_tc_arbitration(node, extack); + goto unlock; + } + + err = esw_qos_node_enable_tc_arbitration(node, extack); + if (!err) + esw_qos_set_tc_arbiter_bw_shares(node, tc_bw, extack); +unlock: + esw_qos_unlock(esw); + 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) { @@ -996,10 +1904,16 @@ int mlx5_esw_qos_vport_update_parent(struct mlx5_vport *vport, struct mlx5_esw_s } esw_qos_lock(esw); - if (!vport->qos.sched_node && parent) - err = mlx5_esw_qos_vport_enable(vport, SCHED_NODE_TYPE_VPORT, parent, 0, 0, extack); - else if (vport->qos.sched_node) + if (!vport->qos.sched_node && parent) { + enum sched_node_type type; + + type = parent->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR ? + SCHED_NODE_TYPE_RATE_LIMITER : SCHED_NODE_TYPE_VPORT; + err = mlx5_esw_qos_vport_enable(vport, type, parent, 0, 0, + extack); + } else if (vport->qos.sched_node) { err = esw_qos_vport_update_parent(vport, parent, extack); + } esw_qos_unlock(esw); return err; } @@ -1019,6 +1933,20 @@ int mlx5_esw_devlink_rate_leaf_parent_set(struct devlink_rate *devlink_rate, return mlx5_esw_qos_vport_update_parent(vport, node, extack); } +static bool esw_qos_is_node_empty(struct mlx5_esw_sched_node *node) +{ + if (list_empty(&node->children)) + return true; + + if (node->type != SCHED_NODE_TYPE_TC_ARBITER_TSAR) + return false; + + node = list_first_entry(&node->children, struct mlx5_esw_sched_node, + entry); + + return esw_qos_is_node_empty(node); +} + static int mlx5_esw_qos_node_validate_set_parent(struct mlx5_esw_sched_node *node, struct mlx5_esw_sched_node *parent, @@ -1032,13 +1960,26 @@ mlx5_esw_qos_node_validate_set_parent(struct mlx5_esw_sched_node *node, return -EOPNOTSUPP; } - if (!list_empty(&node->children)) { + if (!esw_qos_is_node_empty(node)) { NL_SET_ERR_MSG_MOD(extack, "Cannot reassign a node that contains rate objects"); return -EOPNOTSUPP; } + if (parent && parent->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR) { + NL_SET_ERR_MSG_MOD(extack, + "Cannot attach a node to a parent with TC bandwidth configured"); + return -EOPNOTSUPP; + } + new_level = parent ? parent->level + 1 : 2; + if (node->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR) { + /* Increase by one to account for the vports TC scheduling + * element. + */ + new_level += 1; + } + max_level = 1 << MLX5_CAP_QOS(node->esw->dev, log_esw_max_sched_depth); if (new_level > max_level) { NL_SET_ERR_MSG_MOD(extack, @@ -1049,6 +1990,32 @@ mlx5_esw_qos_node_validate_set_parent(struct mlx5_esw_sched_node *node, return 0; } +static int +esw_qos_tc_arbiter_node_update_parent(struct mlx5_esw_sched_node *node, + struct mlx5_esw_sched_node *parent, + struct netlink_ext_ack *extack) +{ + struct mlx5_esw_sched_node *curr_parent = node->parent; + u32 curr_tc_bw[DEVLINK_RATE_TCS_MAX] = {0}; + struct mlx5_eswitch *esw = node->esw; + int err; + + esw_qos_tc_arbiter_get_bw_shares(node, curr_tc_bw); + esw_qos_tc_arbiter_scheduling_teardown(node, extack); + esw_qos_node_set_parent(node, parent); + err = esw_qos_tc_arbiter_scheduling_setup(node, extack); + if (err) { + esw_qos_node_set_parent(node, curr_parent); + if (esw_qos_tc_arbiter_scheduling_setup(node, extack)) { + esw_warn(esw->dev, "Node restore QoS failed\n"); + return err; + } + } + esw_qos_set_tc_arbiter_bw_shares(node, curr_tc_bw, extack); + + return err; +} + static int esw_qos_vports_node_update_parent(struct mlx5_esw_sched_node *node, struct mlx5_esw_sched_node *parent, struct netlink_ext_ack *extack) @@ -1094,7 +2061,13 @@ static int mlx5_esw_qos_node_update_parent(struct mlx5_esw_sched_node *node, esw_qos_lock(esw); curr_parent = node->parent; - err = esw_qos_vports_node_update_parent(node, parent, extack); + if (node->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR) { + err = esw_qos_tc_arbiter_node_update_parent(node, parent, + extack); + } else { + err = esw_qos_vports_node_update_parent(node, parent, extack); + } + if (err) goto out; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.h index ed40ec8f027e..0a50982b0e27 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.h @@ -21,6 +21,14 @@ int mlx5_esw_devlink_rate_leaf_tx_share_set(struct devlink_rate *rate_leaf, void 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_leaf_tc_bw_set(struct devlink_rate *rate_node, + void *priv, + u32 *tc_bw, + struct netlink_ext_ack *extack); +int mlx5_esw_devlink_rate_node_tc_bw_set(struct devlink_rate *rate_node, + void *priv, + u32 *tc_bw, + 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, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 8573d36785f4..d59fdcb29cb8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -212,10 +212,20 @@ struct mlx5_vport { struct mlx5_vport_info info; - /* Protected with the E-Switch qos domain lock. */ + /* Protected with the E-Switch qos domain lock. The Vport QoS can + * either be disabled (sched_node is NULL) or in one of three states: + * 1. Regular QoS (sched_node is a vport node). + * 2. TC QoS enabled on the vport (sched_node is a TC arbiter). + * 3. TC QoS enabled on the vport's parent node + * (sched_node is a rate limit node). + * When TC is enabled in either mode, the vport owns vport TC scheduling + * nodes. + */ struct { - /* Vport scheduling element node. */ + /* Vport scheduling node. */ struct mlx5_esw_sched_node *sched_node; + /* Array of vport traffic class scheduling nodes. */ + struct mlx5_esw_sched_node **sched_nodes; } qos; u16 vport; diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c index 3e0b61202f0c..b3647691060c 100644 --- a/drivers/net/netdevsim/dev.c +++ b/drivers/net/netdevsim/dev.c @@ -388,6 +388,17 @@ static const struct file_operations nsim_dev_rate_parent_fops = { .owner = THIS_MODULE, }; +static void nsim_dev_tc_bw_debugfs_init(struct dentry *ddir, u32 *tc_bw) +{ + int i; + + for (i = 0; i < DEVLINK_RATE_TCS_MAX; i++) { + char name[16]; + + snprintf(name, sizeof(name), "tc%d_bw", i); + debugfs_create_u32(name, 0400, ddir, &tc_bw[i]); + } +} static int nsim_dev_port_debugfs_init(struct nsim_dev *nsim_dev, struct nsim_dev_port *nsim_dev_port) { @@ -415,6 +426,8 @@ static int nsim_dev_port_debugfs_init(struct nsim_dev *nsim_dev, nsim_dev_port->ddir, &nsim_dev_port->parent_name, &nsim_dev_rate_parent_fops); + nsim_dev_tc_bw_debugfs_init(nsim_dev_port->ddir, + nsim_dev_port->tc_bw); } debugfs_create_symlink("dev", nsim_dev_port->ddir, dev_link_name); @@ -1172,6 +1185,19 @@ static int nsim_rate_bytes_to_units(char *name, u64 *rate, struct netlink_ext_ac return 0; } +static int nsim_leaf_tc_bw_set(struct devlink_rate *devlink_rate, + void *priv, u32 *tc_bw, + struct netlink_ext_ack *extack) +{ + struct nsim_dev_port *nsim_dev_port = priv; + int i; + + for (i = 0; i < DEVLINK_RATE_TCS_MAX; i++) + nsim_dev_port->tc_bw[i] = tc_bw[i]; + + return 0; +} + static int nsim_leaf_tx_share_set(struct devlink_rate *devlink_rate, void *priv, u64 tx_share, struct netlink_ext_ack *extack) { @@ -1210,8 +1236,21 @@ struct nsim_rate_node { char *parent_name; u16 tx_share; u16 tx_max; + u32 tc_bw[DEVLINK_RATE_TCS_MAX]; }; +static int nsim_node_tc_bw_set(struct devlink_rate *devlink_rate, void *priv, + u32 *tc_bw, struct netlink_ext_ack *extack) +{ + struct nsim_rate_node *nsim_node = priv; + int i; + + for (i = 0; i < DEVLINK_RATE_TCS_MAX; i++) + nsim_node->tc_bw[i] = tc_bw[i]; + + return 0; +} + static int nsim_node_tx_share_set(struct devlink_rate *devlink_rate, void *priv, u64 tx_share, struct netlink_ext_ack *extack) { @@ -1264,6 +1303,8 @@ static int nsim_rate_node_new(struct devlink_rate *node, void **priv, &nsim_node->parent_name, &nsim_dev_rate_parent_fops); + nsim_dev_tc_bw_debugfs_init(nsim_node->ddir, nsim_node->tc_bw); + *priv = nsim_node; return 0; } @@ -1340,8 +1381,10 @@ static const struct devlink_ops nsim_dev_devlink_ops = { .trap_policer_counter_get = nsim_dev_devlink_trap_policer_counter_get, .rate_leaf_tx_share_set = nsim_leaf_tx_share_set, .rate_leaf_tx_max_set = nsim_leaf_tx_max_set, + .rate_leaf_tc_bw_set = nsim_leaf_tc_bw_set, .rate_node_tx_share_set = nsim_node_tx_share_set, .rate_node_tx_max_set = nsim_node_tx_max_set, + .rate_node_tc_bw_set = nsim_node_tc_bw_set, .rate_node_new = nsim_rate_node_new, .rate_node_del = nsim_rate_node_del, .rate_leaf_parent_set = nsim_rate_leaf_parent_set, diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h index 4a0c48c7a384..809dd29fc5fe 100644 --- a/drivers/net/netdevsim/netdevsim.h +++ b/drivers/net/netdevsim/netdevsim.h @@ -276,6 +276,7 @@ struct nsim_dev_port { struct dentry *ddir; struct dentry *rate_parent; char *parent_name; + u32 tc_bw[DEVLINK_RATE_TCS_MAX]; struct netdevsim *ns; }; diff --git a/drivers/net/vxlan/vxlan_vnifilter.c b/drivers/net/vxlan/vxlan_vnifilter.c index 4ff56d9f8f28..adc89e651e27 100644 --- a/drivers/net/vxlan/vxlan_vnifilter.c +++ b/drivers/net/vxlan/vxlan_vnifilter.c @@ -971,15 +971,10 @@ static int vxlan_vnifilter_process(struct sk_buff *skb, struct nlmsghdr *nlh, if (!(vxlan->cfg.flags & VXLAN_F_VNIFILTER)) return -EOPNOTSUPP; - nlmsg_for_each_attr(attr, nlh, sizeof(*tmsg), rem) { - switch (nla_type(attr)) { - case VXLAN_VNIFILTER_ENTRY: - err = vxlan_process_vni_filter(vxlan, attr, - nlh->nlmsg_type, extack); - break; - default: - continue; - } + nlmsg_for_each_attr_type(attr, VXLAN_VNIFILTER_ENTRY, nlh, + sizeof(*tmsg), rem) { + err = vxlan_process_vni_filter(vxlan, attr, nlh->nlmsg_type, + extack); vnis++; if (err) break; |