From: Carolina Jubran cjubran@nvidia.com

Introduce support for specifying relative bandwidth shares between traffic classes (TC) in the devlink-rate API. This new option allows users to allocate bandwidth across multiple traffic classes in a single command.

This feature provides a more granular control over traffic management, especially for scenarios requiring Enhanced Transmission Selection.

Users can now define a relative bandwidth share for each traffic class. For example, assigning share values of 20 to TC0 (TCP/UDP) and 80 to TC5 (RoCE) will result in TC0 receiving 20% and TC5 receiving 80% of the total bandwidth. The actual percentage each class receives depends on the ratio of its share value to the sum of all shares.

Example: DEV=pci/0000:08:00.0

$ devlink port function rate add $DEV/vfs_group tx_share 10Gbit \ tx_max 50Gbit tc-bw 0:20 1:0 2:0 3:0 4:0 5:80 6:0 7:0

$ devlink port function rate set $DEV/vfs_group \ tc-bw 0:20 1:0 2:0 3:0 4:0 5:20 6:60 7:0

Example usage with ynl:

./tools/net/ynl/cli.py --spec Documentation/netlink/specs/devlink.yaml \ --do rate-set --json '{ "bus-name": "pci", "dev-name": "0000:08:00.0", "port-index": 1, "rate-tc-bws": [ {"rate-tc-index": 0, "rate-tc-bw": 50}, {"rate-tc-index": 1, "rate-tc-bw": 50}, {"rate-tc-index": 2, "rate-tc-bw": 0}, {"rate-tc-index": 3, "rate-tc-bw": 0}, {"rate-tc-index": 4, "rate-tc-bw": 0}, {"rate-tc-index": 5, "rate-tc-bw": 0}, {"rate-tc-index": 6, "rate-tc-bw": 0}, {"rate-tc-index": 7, "rate-tc-bw": 0} ] }'

./tools/net/ynl/cli.py --spec Documentation/netlink/specs/devlink.yaml \ --do rate-get --json '{ "bus-name": "pci", "dev-name": "0000:08:00.0", "port-index": 1 }'

output for rate-get: {'bus-name': 'pci', 'dev-name': '0000:08:00.0', 'port-index': 1, 'rate-tc-bws': [{'rate-tc-bw': 50, 'rate-tc-index': 0}, {'rate-tc-bw': 50, 'rate-tc-index': 1}, {'rate-tc-bw': 0, 'rate-tc-index': 2}, {'rate-tc-bw': 0, 'rate-tc-index': 3}, {'rate-tc-bw': 0, 'rate-tc-index': 4}, {'rate-tc-bw': 0, 'rate-tc-index': 5}, {'rate-tc-bw': 0, 'rate-tc-index': 6}, {'rate-tc-bw': 0, 'rate-tc-index': 7}], 'rate-tx-max': 0, 'rate-tx-priority': 0, 'rate-tx-share': 0, 'rate-tx-weight': 0, 'rate-type': 'leaf'}

Signed-off-by: Carolina Jubran cjubran@nvidia.com Reviewed-by: Cosmin Ratiu cratiu@nvidia.com Reviewed-by: Jiri Pirko jiri@nvidia.com Signed-off-by: Tariq Toukan tariqt@nvidia.com Signed-off-by: Mark Bloch mbloch@nvidia.com --- Documentation/netlink/specs/devlink.yaml | 32 ++++- .../networking/devlink/devlink-port.rst | 8 ++ include/net/devlink.h | 8 ++ include/uapi/linux/devlink.h | 9 ++ net/devlink/netlink_gen.c | 15 +- net/devlink/netlink_gen.h | 1 + net/devlink/rate.c | 129 ++++++++++++++++++ 7 files changed, 197 insertions(+), 5 deletions(-)

diff --git a/Documentation/netlink/specs/devlink.yaml b/Documentation/netlink/specs/devlink.yaml index ad56093d6ead..c66ea7e325b7 100644 --- a/Documentation/netlink/specs/devlink.yaml +++ b/Documentation/netlink/specs/devlink.yaml @@ -224,6 +224,10 @@ definitions: value: 10 - name: binary + - + name: rate-tc-index-max + type: const + value: 7

attribute-sets: - @@ -844,7 +848,23 @@ attribute-sets: - name: region-direct type: flag - + - + name: rate-tc-bws + type: nest + multi-attr: true + nested-attributes: dl-rate-tc-bws + - + name: rate-tc-index + type: u8 + checks: + max: rate-tc-index-max + - + name: rate-tc-bw + type: u32 + doc: | + Specifies the bandwidth share assigned to the Traffic Class. + The bandwidth for the traffic class is determined + in proportion to the sum of the shares of all configured classes. - name: dl-dev-stats subset-of: devlink @@ -1249,6 +1269,14 @@ attribute-sets: - name: flash type: flag + - + name: dl-rate-tc-bws + subset-of: devlink + attributes: + - + name: rate-tc-index + - + name: rate-tc-bw

operations: enum-model: directional @@ -2176,6 +2204,7 @@ operations: - rate-tx-priority - rate-tx-weight - rate-parent-node-name + - rate-tc-bws

- name: rate-new @@ -2196,6 +2225,7 @@ operations: - rate-tx-priority - rate-tx-weight - rate-parent-node-name + - rate-tc-bws

- name: rate-del diff --git a/Documentation/networking/devlink/devlink-port.rst b/Documentation/networking/devlink/devlink-port.rst index 9d22d41a7cd1..5e397798a402 100644 --- a/Documentation/networking/devlink/devlink-port.rst +++ b/Documentation/networking/devlink/devlink-port.rst @@ -418,6 +418,14 @@ API allows to configure following rate object's parameters: to all node children limits. ``tx_max`` is an upper limit for children. ``tx_share`` is a total bandwidth distributed among children.

+``tc_bw`` + Allow users to set the bandwidth allocation per traffic class on rate + objects. This enables fine-grained QoS configurations by assigning a relative + share value to each traffic class. The bandwidth is distributed in proportion + to the share value for each class, relative to the sum of all shares. + When applied to a non-leaf node, tc_bw determines how bandwidth is shared + among its child elements. + ``tx_priority`` and ``tx_weight`` can be used simultaneously. In that case nodes with the same priority form a WFQ subgroup in the sibling group and arbitration among them is based on assigned weights. diff --git a/include/net/devlink.h b/include/net/devlink.h index 63517646a497..d0ce5a7e984c 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -118,6 +118,8 @@ struct devlink_rate {

u32 tx_priority; u32 tx_weight; + + u32 tc_bw[DEVLINK_RATE_TCS_MAX]; };

struct devlink_port { @@ -1486,6 +1488,9 @@ struct devlink_ops { u32 tx_priority, struct netlink_ext_ack *extack); int (*rate_leaf_tx_weight_set)(struct devlink_rate *devlink_rate, void *priv, u32 tx_weight, struct netlink_ext_ack *extack); + int (*rate_leaf_tc_bw_set)(struct devlink_rate *devlink_rate, + void *priv, u32 *tc_bw, + struct netlink_ext_ack *extack); int (*rate_node_tx_share_set)(struct devlink_rate *devlink_rate, void *priv, u64 tx_share, struct netlink_ext_ack *extack); int (*rate_node_tx_max_set)(struct devlink_rate *devlink_rate, void *priv, @@ -1494,6 +1499,9 @@ struct devlink_ops { u32 tx_priority, struct netlink_ext_ack *extack); int (*rate_node_tx_weight_set)(struct devlink_rate *devlink_rate, void *priv, u32 tx_weight, struct netlink_ext_ack *extack); + int (*rate_node_tc_bw_set)(struct devlink_rate *devlink_rate, + void *priv, u32 *tc_bw, + struct netlink_ext_ack *extack); int (*rate_node_new)(struct devlink_rate *rate_node, void **priv, struct netlink_ext_ack *extack); int (*rate_node_del)(struct devlink_rate *rate_node, void *priv, diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index a5ee0f13740a..e72bcc239afd 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -221,6 +221,11 @@ enum devlink_port_flavour { */ };

+/* IEEE 802.1Qaz standard supported values. */ + +#define DEVLINK_RATE_TCS_MAX 8 +#define DEVLINK_RATE_TC_INDEX_MAX (DEVLINK_RATE_TCS_MAX - 1) + enum devlink_rate_type { DEVLINK_RATE_TYPE_LEAF, DEVLINK_RATE_TYPE_NODE, @@ -629,6 +634,10 @@ enum devlink_attr {

DEVLINK_ATTR_REGION_DIRECT, /* flag */

+ DEVLINK_ATTR_RATE_TC_BWS, /* nested */ + DEVLINK_ATTR_RATE_TC_INDEX, /* u8 */ + DEVLINK_ATTR_RATE_TC_BW, /* u32 */ + /* Add new attributes above here, update the spec in * Documentation/netlink/specs/devlink.yaml and re-generate * net/devlink/netlink_gen.c. diff --git a/net/devlink/netlink_gen.c b/net/devlink/netlink_gen.c index e340d955cf3b..c50436433c18 100644 --- a/net/devlink/netlink_gen.c +++ b/net/devlink/netlink_gen.c @@ -45,6 +45,11 @@ const struct nla_policy devlink_dl_port_function_nl_policy[DEVLINK_PORT_FN_ATTR_ [DEVLINK_PORT_FN_ATTR_CAPS] = NLA_POLICY_BITFIELD32(15), };

+const struct nla_policy devlink_dl_rate_tc_bws_nl_policy[DEVLINK_ATTR_RATE_TC_BW + 1] = { + [DEVLINK_ATTR_RATE_TC_INDEX] = NLA_POLICY_MAX(NLA_U8, DEVLINK_RATE_TC_INDEX_MAX), + [DEVLINK_ATTR_RATE_TC_BW] = { .type = NLA_U32, }, +}; + const struct nla_policy devlink_dl_selftest_id_nl_policy[DEVLINK_ATTR_SELFTEST_ID_FLASH + 1] = { [DEVLINK_ATTR_SELFTEST_ID_FLASH] = { .type = NLA_FLAG, }, }; @@ -523,7 +528,7 @@ static const struct nla_policy devlink_rate_get_dump_nl_policy[DEVLINK_ATTR_DEV_ };

/* DEVLINK_CMD_RATE_SET - do */ -static const struct nla_policy devlink_rate_set_nl_policy[DEVLINK_ATTR_RATE_TX_WEIGHT + 1] = { +static const struct nla_policy devlink_rate_set_nl_policy[DEVLINK_ATTR_RATE_TC_BWS + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, [DEVLINK_ATTR_RATE_NODE_NAME] = { .type = NLA_NUL_STRING, }, @@ -532,10 +537,11 @@ static const struct nla_policy devlink_rate_set_nl_policy[DEVLINK_ATTR_RATE_TX_W [DEVLINK_ATTR_RATE_TX_PRIORITY] = { .type = NLA_U32, }, [DEVLINK_ATTR_RATE_TX_WEIGHT] = { .type = NLA_U32, }, [DEVLINK_ATTR_RATE_PARENT_NODE_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_RATE_TC_BWS] = NLA_POLICY_NESTED(devlink_dl_rate_tc_bws_nl_policy), };

/* DEVLINK_CMD_RATE_NEW - do */ -static const struct nla_policy devlink_rate_new_nl_policy[DEVLINK_ATTR_RATE_TX_WEIGHT + 1] = { +static const struct nla_policy devlink_rate_new_nl_policy[DEVLINK_ATTR_RATE_TC_BWS + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, [DEVLINK_ATTR_RATE_NODE_NAME] = { .type = NLA_NUL_STRING, }, @@ -544,6 +550,7 @@ static const struct nla_policy devlink_rate_new_nl_policy[DEVLINK_ATTR_RATE_TX_W [DEVLINK_ATTR_RATE_TX_PRIORITY] = { .type = NLA_U32, }, [DEVLINK_ATTR_RATE_TX_WEIGHT] = { .type = NLA_U32, }, [DEVLINK_ATTR_RATE_PARENT_NODE_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_RATE_TC_BWS] = NLA_POLICY_NESTED(devlink_dl_rate_tc_bws_nl_policy), };

/* DEVLINK_CMD_RATE_DEL - do */ @@ -1191,7 +1198,7 @@ const struct genl_split_ops devlink_nl_ops[74] = { .doit = devlink_nl_rate_set_doit, .post_doit = devlink_nl_post_doit, .policy = devlink_rate_set_nl_policy, - .maxattr = DEVLINK_ATTR_RATE_TX_WEIGHT, + .maxattr = DEVLINK_ATTR_RATE_TC_BWS, .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, }, { @@ -1201,7 +1208,7 @@ const struct genl_split_ops devlink_nl_ops[74] = { .doit = devlink_nl_rate_new_doit, .post_doit = devlink_nl_post_doit, .policy = devlink_rate_new_nl_policy, - .maxattr = DEVLINK_ATTR_RATE_TX_WEIGHT, + .maxattr = DEVLINK_ATTR_RATE_TC_BWS, .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, }, { diff --git a/net/devlink/netlink_gen.h b/net/devlink/netlink_gen.h index 8f2bd50ddf5e..fb733b5d4ff1 100644 --- a/net/devlink/netlink_gen.h +++ b/net/devlink/netlink_gen.h @@ -13,6 +13,7 @@

/* Common nested types */ extern const struct nla_policy devlink_dl_port_function_nl_policy[DEVLINK_PORT_FN_ATTR_CAPS + 1]; +extern const struct nla_policy devlink_dl_rate_tc_bws_nl_policy[DEVLINK_ATTR_RATE_TC_BW + 1]; extern const struct nla_policy devlink_dl_selftest_id_nl_policy[DEVLINK_ATTR_SELFTEST_ID_FLASH + 1];

/* Ops table for devlink */ diff --git a/net/devlink/rate.c b/net/devlink/rate.c index 8828ffaf6cbc..181d443ab3fc 100644 --- a/net/devlink/rate.c +++ b/net/devlink/rate.c @@ -80,6 +80,29 @@ devlink_rate_get_from_info(struct devlink *devlink, struct genl_info *info) return ERR_PTR(-EINVAL); }

+static int devlink_rate_put_tc_bws(struct sk_buff *msg, u32 *tc_bw) +{ + struct nlattr *nla_tc_bw; + int i; + + for (i = 0; i < DEVLINK_RATE_TCS_MAX; i++) { + nla_tc_bw = nla_nest_start(msg, DEVLINK_ATTR_RATE_TC_BWS); + if (!nla_tc_bw) + return -EMSGSIZE; + + if (nla_put_u8(msg, DEVLINK_ATTR_RATE_TC_INDEX, i) || + nla_put_u32(msg, DEVLINK_ATTR_RATE_TC_BW, tc_bw[i])) + goto nla_put_failure; + + nla_nest_end(msg, nla_tc_bw); + } + return 0; + +nla_put_failure: + nla_nest_cancel(msg, nla_tc_bw); + return -EMSGSIZE; +} + static int devlink_nl_rate_fill(struct sk_buff *msg, struct devlink_rate *devlink_rate, enum devlink_command cmd, u32 portid, u32 seq, @@ -129,6 +152,9 @@ static int devlink_nl_rate_fill(struct sk_buff *msg, devlink_rate->parent->name)) goto nla_put_failure;

+ if (devlink_rate_put_tc_bws(msg, devlink_rate->tc_bw)) + goto nla_put_failure; + genlmsg_end(msg, hdr); return 0;

@@ -316,6 +342,89 @@ devlink_nl_rate_parent_node_set(struct devlink_rate *devlink_rate, return 0; }

+static int devlink_nl_rate_tc_bw_parse(struct nlattr *parent_nest, u32 *tc_bw, + unsigned long *bitmap, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[DEVLINK_ATTR_MAX + 1]; + u8 tc_index; + int err; + + err = nla_parse_nested(tb, DEVLINK_ATTR_MAX, parent_nest, + devlink_dl_rate_tc_bws_nl_policy, extack); + if (err) + return err; + + if (!tb[DEVLINK_ATTR_RATE_TC_INDEX]) { + NL_SET_ERR_ATTR_MISS(extack, parent_nest, + DEVLINK_ATTR_RATE_TC_INDEX); + return -EINVAL; + } + + tc_index = nla_get_u8(tb[DEVLINK_ATTR_RATE_TC_INDEX]); + + if (!tb[DEVLINK_ATTR_RATE_TC_BW]) { + NL_SET_ERR_ATTR_MISS(extack, parent_nest, + DEVLINK_ATTR_RATE_TC_BW); + return -EINVAL; + } + + if (test_and_set_bit(tc_index, bitmap)) { + NL_SET_ERR_MSG_FMT(extack, + "Duplicate traffic class index specified (%u)", + tc_index); + return -EINVAL; + } + + tc_bw[tc_index] = nla_get_u32(tb[DEVLINK_ATTR_RATE_TC_BW]); + + return 0; +} + +static int devlink_nl_rate_tc_bw_set(struct devlink_rate *devlink_rate, + struct genl_info *info) +{ + DECLARE_BITMAP(bitmap, DEVLINK_RATE_TCS_MAX) = {}; + struct devlink *devlink = devlink_rate->devlink; + const struct devlink_ops *ops = devlink->ops; + int rem, err = -EOPNOTSUPP, i, total = 0; + u32 tc_bw[DEVLINK_RATE_TCS_MAX] = {}; + struct nlattr *attr; + + nlmsg_for_each_attr_type(attr, DEVLINK_ATTR_RATE_TC_BWS, info->nlhdr, + GENL_HDRLEN, rem) { + err = devlink_nl_rate_tc_bw_parse(attr, tc_bw, bitmap, + info->extack); + if (err) + return err; + } + + for (i = 0; i < DEVLINK_RATE_TCS_MAX; i++) { + if (!test_bit(i, bitmap)) { + NL_SET_ERR_MSG_FMT(info->extack, + "Bandwidth values must be specified for all %u traffic classes", + DEVLINK_RATE_TCS_MAX); + return -EINVAL; + } + + total += tc_bw[i]; + } + + if (devlink_rate_is_leaf(devlink_rate)) + err = ops->rate_leaf_tc_bw_set(devlink_rate, devlink_rate->priv, + tc_bw, info->extack); + else if (devlink_rate_is_node(devlink_rate)) + err = ops->rate_node_tc_bw_set(devlink_rate, devlink_rate->priv, + tc_bw, info->extack); + + if (err) + return err; + + memcpy(devlink_rate->tc_bw, tc_bw, sizeof(tc_bw)); + + return 0; +} + static int devlink_nl_rate_set(struct devlink_rate *devlink_rate, const struct devlink_ops *ops, struct genl_info *info) @@ -388,6 +497,12 @@ static int devlink_nl_rate_set(struct devlink_rate *devlink_rate, return err; }

+ if (attrs[DEVLINK_ATTR_RATE_TC_BWS]) { + err = devlink_nl_rate_tc_bw_set(devlink_rate, info); + if (err) + return err; + } + return 0; }

@@ -423,6 +538,13 @@ static bool devlink_rate_set_ops_supported(const struct devlink_ops *ops, "TX weight set isn't supported for the leafs"); return false; } + if (attrs[DEVLINK_ATTR_RATE_TC_BWS] && + !ops->rate_leaf_tc_bw_set) { + NL_SET_ERR_MSG_ATTR(info->extack, + attrs[DEVLINK_ATTR_RATE_TC_BWS], + "TC bandwidth set isn't supported for the leafs"); + return false; + } } else if (type == DEVLINK_RATE_TYPE_NODE) { if (attrs[DEVLINK_ATTR_RATE_TX_SHARE] && !ops->rate_node_tx_share_set) { NL_SET_ERR_MSG(info->extack, "TX share set isn't supported for the nodes"); @@ -449,6 +571,13 @@ static bool devlink_rate_set_ops_supported(const struct devlink_ops *ops, "TX weight set isn't supported for the nodes"); return false; } + if (attrs[DEVLINK_ATTR_RATE_TC_BWS] && + !ops->rate_node_tc_bw_set) { + NL_SET_ERR_MSG_ATTR(info->extack, + attrs[DEVLINK_ATTR_RATE_TC_BWS], + "TC bandwidth set isn't supported for the nodes"); + return false; + } } else { WARN(1, "Unknown type of rate object"); return false;

From: Carolina Jubran cjubran@nvidia.com

Test verifies that netdevsim correctly implements devlink ops callbacks that set tc-bw on leaf or node rate object.

Signed-off-by: Carolina Jubran cjubran@nvidia.com Reviewed-by: Cosmin Ratiu cratiu@nvidia.com Signed-off-by: Tariq Toukan tariqt@nvidia.com Signed-off-by: Mark Bloch mbloch@nvidia.com --- drivers/net/netdevsim/dev.c | 43 ++++++++++++++++ drivers/net/netdevsim/netdevsim.h | 1 + .../drivers/net/netdevsim/devlink.sh | 51 +++++++++++++++++++ 3 files changed, 95 insertions(+)

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/tools/testing/selftests/drivers/net/netdevsim/devlink.sh b/tools/testing/selftests/drivers/net/netdevsim/devlink.sh index b5ea2526f23c..09068d69d2cc 100755 --- a/tools/testing/selftests/drivers/net/netdevsim/devlink.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/devlink.sh @@ -608,6 +608,44 @@ rate_attr_parent_check() check_err $? "Unexpected parent attr value $api_value != $parent" }

+rate_attr_tc_bw_check() +{ + local handle=$1 + local tc_bw=$2 + local debug_file=$3 + + local tc_bw_str="" + for bw in $tc_bw; do + local tc=${bw%%:*} + local value=${bw##*:} + tc_bw_str="$tc_bw_str $tc:$value" + done + tc_bw_str=${tc_bw_str# } + + rate_attr_set $handle tc-bw "$tc_bw_str" + check_err $? "Failed to set tc-bw values" + + for bw in $tc_bw; do + local tc=${bw%%:*} + local value=${bw##*:} + local debug_value=$(cat $debug_file/tc${tc}_bw) + check_err $? "Failed to read tc-bw value from debugfs for tc$tc" + [ "$debug_value" == "$value" ] + check_err $? "Unexpected tc-bw debug value for tc$tc: $debug_value != $value" + done + + for bw in $tc_bw; do + local tc=${bw%%:*} + local expected_value=${bw##*:} + local api_value=$(rate_attr_get $handle tc_$tc) + if [ "$api_value" = "null" ]; then + api_value=0 + fi + [ "$api_value" == "$expected_value" ] + check_err $? "Unexpected tc-bw value for tc$tc: $api_value != $expected_value" + done +} + rate_node_add() { local handle=$1 @@ -649,6 +687,13 @@ rate_test() rate=$(($rate+100)) done

+ local tc_bw="0:0 1:40 2:0 3:0 4:0 5:0 6:60 7:0" + for r_obj in $leafs + do + rate_attr_tc_bw_check $r_obj "$tc_bw" \ + $DEBUGFS_DIR/ports/${r_obj##*/} + done + local node1_name='group1' local node1="$DL_HANDLE/$node1_name" rate_node_add "$node1" @@ -666,6 +711,12 @@ rate_test() rate_attr_tx_rate_check $node1 tx_max $node_tx_max \ $DEBUGFS_DIR/rate_nodes/${node1##*/}/tx_max

+ + local tc_bw="0:20 1:0 2:0 3:0 4:0 5:20 6:60 7:0" + rate_attr_tc_bw_check $node1 "$tc_bw" \ + $DEBUGFS_DIR/rate_nodes/${node1##*/} + + rate_node_del "$node1" check_err $? "Failed to delete node $node1" local num_nodes=`rate_nodes_get $DL_HANDLE | wc -w`

From: Carolina Jubran cjubran@nvidia.com

Introduce support for enabling and disabling Traffic Class (TC) arbitration for existing devlink rate nodes. This patch adds support for a new scheduling node type, `SCHED_NODE_TYPE_TC_ARBITER_TSAR`.

Key changes include:

- New helper functions for transitioning existing rate nodes to TC arbiter nodes and vice versa. These functions handle the allocation of TC arbiter nodes, copying of child nodes, and restoring vport QoS settings when TC arbitration is disabled.

- Implementation of `mlx5_esw_devlink_rate_node_tc_bw_set()` to manage tc-bw configuration on nodes.

- Introduced stubs for `esw_qos_tc_arbiter_scheduling_setup()` and `esw_qos_tc_arbiter_scheduling_teardown()`, which will be extended in future patches to provide full support for tc-bw on devlink rate objects.

- Validation functions for tc-bw settings, allowing graceful handling of unsupported traffic class bandwidth configurations.

- Updated `__esw_qos_alloc_node()` to insert the new node into the parent’s children list only if the parent is not NULL. For the root TSAR, the new node is inserted directly after the allocation call.

- Don't allow `tc-bw` configuration for nodes containing non-leaf children.

This patch lays the groundwork for future support for configuring tc-bw on devlink rate nodes. Although the infrastructure is in place, full support for tc-bw is not yet implemented; attempts to set tc-bw on nodes will return `-EOPNOTSUPP`.

No functional changes are introduced at this stage.

Signed-off-by: Carolina Jubran cjubran@nvidia.com Reviewed-by: Cosmin Ratiu cratiu@nvidia.com Signed-off-by: Tariq Toukan tariqt@nvidia.com Signed-off-by: Mark Bloch mbloch@nvidia.com --- .../net/ethernet/mellanox/mlx5/core/esw/qos.c | 313 +++++++++++++++++- 1 file changed, 304 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c index ec706e9352e1..1066992c1503 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c @@ -64,11 +64,13 @@ 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, };

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", };

struct mlx5_esw_sched_node { @@ -106,6 +108,13 @@ 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) { @@ -116,6 +125,27 @@ 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) { kfree(vport->qos.sched_node); @@ -141,16 +171,24 @@ 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_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_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, @@ -388,6 +426,14 @@ __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; } @@ -426,6 +472,7 @@ __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);

@@ -498,6 +545,9 @@ 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); @@ -555,6 +605,18 @@ 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) +{} + +static int esw_qos_tc_arbiter_scheduling_setup(struct mlx5_esw_sched_node *node, + struct netlink_ext_ack *extack) +{ + NL_SET_ERR_MSG_MOD(extack, "TC arbiter elements are not supported."); + return -EOPNOTSUPP; +} + 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; @@ -723,6 +785,195 @@ static int esw_qos_vport_update_parent(struct mlx5_vport *vport, struct mlx5_esw return err; }

+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) { + 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; +} + static u32 mlx5_esw_qos_lag_link_speed_get_locked(struct mlx5_core_dev *mdev) { struct ethtool_link_ksettings lksettings; @@ -848,6 +1099,31 @@ 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_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) @@ -921,9 +1197,28 @@ int mlx5_esw_devlink_rate_node_tc_bw_set(struct devlink_rate *rate_node, u32 *tc_bw, struct netlink_ext_ack *extack) { - NL_SET_ERR_MSG_MOD(extack, - "TC bandwidth shares are not supported on nodes"); - return -EOPNOTSUPP; + 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); +unlock: + esw_qos_unlock(esw); + return err; }

int mlx5_esw_devlink_rate_node_tx_share_set(struct devlink_rate *rate_node, void *priv,

From: Carolina Jubran cjubran@nvidia.com

Introduce support for managing Traffic Class (TC) arbiter nodes and associated vports TC nodes within the E-Switch QoS hierarchy. This patch adds support for the new scheduling node type, `SCHED_NODE_TYPE_VPORTS_TC_TSAR`, and implements full support for setting tc-bw on both vports and nodes.

Key changes include:

- Introduced the new scheduling node type, `SCHED_NODE_TYPE_VPORTS_TC_TSAR`, for managing vports within the TC arbiter node.

- New helper functions for creating and destroying vports TC nodes under the TC arbiter.

- Updated the minimum rate normalization function to skip nodes of type `SCHED_NODE_TYPE_VPORTS_TC_TSAR`. Vports TC TSARs have bandwidth shares configured on them but not minimum rates, so their `min_rate` cannot be normalized.

- Implementation of `esw_qos_tc_arbiter_scheduling_setup()` and `esw_qos_tc_arbiter_scheduling_teardown()` for initializing and cleaning up TC arbiter scheduling elements. These functions now fully support tc-bw configuration on TC arbiter nodes.

- Introduced a new helper `esw_qos_calculate_tc_bw_divider()` to compute the total TC bandwidth share, which is used as a divider for normalizing each TC's share.

- Added `esw_qos_tc_arbiter_get_bw_shares()` and `esw_qos_set_tc_arbiter_bw_shares()` to handle the settings of bandwidth shares for vports traffic class TSARs.

- `esw_qos_set_tc_arbiter_bw_shares()` normalizes each TC share based on the total and the firmware's maximum allowed TSAR bandwidth share.

- Refactored `mlx5_esw_devlink_rate_node_tc_bw_set()` and `mlx5_esw_devlink_rate_leaf_tc_bw_set()` to fully support configuring tc-bw on devlink rate nodes and vports, respectively.

- Refactored `mlx5_esw_qos_node_update_parent()` to ensure that tc-bw configuration remains compatible with setting a parent on a rate node, preserving level hierarchy functionality.

- Refactored `esw_qos_calc_bw_share()` to generalize its input so it can be used for both minimum rate and bandwidth share calculations.

Signed-off-by: Carolina Jubran cjubran@nvidia.com Reviewed-by: Cosmin Ratiu cratiu@nvidia.com Signed-off-by: Tariq Toukan tariqt@nvidia.com Signed-off-by: Mark Bloch mbloch@nvidia.com --- .../net/ethernet/mellanox/mlx5/core/esw/qos.c | 294 +++++++++++++++++- 1 file changed, 285 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c index dec3bed682b7..154bbb17ec0e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c @@ -67,6 +67,7 @@ enum sched_node_type { 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[] = { @@ -75,6 +76,7 @@ static const char * const sched_node_type_str[] = { [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 { @@ -187,6 +189,11 @@ 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) { 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", @@ -345,11 +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, @@ -376,7 +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; @@ -385,6 +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) { @@ -527,6 +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) @@ -591,6 +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); @@ -685,13 +860,38 @@ static void esw_qos_put(struct mlx5_eswitch *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) { - NL_SET_ERR_MSG_MOD(extack, "TC arbiter elements are not supported."); - return -EOPNOTSUPP; + 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 @@ -1064,6 +1264,7 @@ static int esw_qos_vport_update(struct mlx5_vport *vport, { 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); @@ -1075,11 +1276,23 @@ static int esw_qos_vport_update(struct mlx5_vport *vport, 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) + 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; } @@ -1563,6 +1776,8 @@ int mlx5_esw_devlink_rate_leaf_tc_bw_set(struct devlink_rate *rate_leaf, 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; @@ -1592,6 +1807,8 @@ int mlx5_esw_devlink_rate_node_tc_bw_set(struct devlink_rate *rate_node, }

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; @@ -1716,6 +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, @@ -1729,13 +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, @@ -1746,6 +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) @@ -1791,7 +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;