diff mbox series

[net-next,V3,3/8] devlink: Extend devlink rate API with traffic classes bandwidth management

Message ID 20241117205046.736499-4-tariqt@nvidia.com (mailing list archive)
State New
Delegated to: Netdev Maintainers
Headers show
Series net/mlx5: ConnectX-8 SW Steering + Rate management on traffic classes | expand

Checks

Context Check Description
netdev/series_format success Posting correctly formatted
netdev/tree_selection success Clearly marked for net-next
netdev/ynl success Generated files up to date; no warnings/errors; GEN HAS DIFF 2 files changed, 64 insertions(+);
netdev/fixes_present success Fixes tag not required for -next series
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 3 this patch: 3
netdev/build_tools success Errors and warnings before: 0 (+0) this patch: 0 (+0)
netdev/cc_maintainers warning 3 maintainers not CCed: donald.hunter@gmail.com horms@kernel.org swarupkotikalapudi@gmail.com
netdev/build_clang success Errors and warnings before: 5 this patch: 5
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/deprecated_api success None detected
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 528 this patch: 528
netdev/checkpatch warning WARNING: line length of 101 exceeds 80 columns WARNING: line length of 81 exceeds 80 columns WARNING: line length of 82 exceeds 80 columns WARNING: line length of 87 exceeds 80 columns WARNING: line length of 88 exceeds 80 columns WARNING: line length of 89 exceeds 80 columns WARNING: line length of 95 exceeds 80 columns WARNING: line length of 97 exceeds 80 columns WARNING: line length of 99 exceeds 80 columns
netdev/build_clang_rust success No Rust files in patch. Skipping build
netdev/kdoc success Errors and warnings before: 2 this patch: 2
netdev/source_inline success Was 0 now: 0
netdev/contest pending net-next-2024-11-18--00-00 (tests: 0)

Commit Message

Tariq Toukan Nov. 17, 2024, 8:50 p.m. UTC 
From: Carolina Jubran <cjubran@nvidia.com>

Introduce support for specifying bandwidth proportions 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 specific bandwidth share for each traffic class,
such as allocating 20% for TC0 (TCP/UDP) and 80% for TC5 (RoCE).

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

Signed-off-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Cosmin Ratiu <cratiu@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
---
 Documentation/netlink/specs/devlink.yaml | 22 ++++++++
 include/net/devlink.h                    |  7 +++
 include/uapi/linux/devlink.h             |  3 +
 net/devlink/netlink_gen.c                | 14 +++--
 net/devlink/netlink_gen.h                |  1 +
 net/devlink/rate.c                       | 71 +++++++++++++++++++++++-
 6 files changed, 113 insertions(+), 5 deletions(-)
diff mbox series

Patch

diff --git a/Documentation/netlink/specs/devlink.yaml b/Documentation/netlink/specs/devlink.yaml
index 09fbb4c03fc8..fece78ed60fe 100644
--- a/Documentation/netlink/specs/devlink.yaml
+++ b/Documentation/netlink/specs/devlink.yaml
@@ -820,6 +820,19 @@  attribute-sets:
       -
         name: region-direct
         type: flag
+      -
+        name: rate-tc-bw
+        type: u32
+        doc: |
+             Specifies the bandwidth allocation for the Traffic Class as a
+             percentage.
+        checks:
+          min: 0
+          max: 100
+      -
+        name: rate-tc-bw-values
+        type: nest
+        nested-attributes: dl-rate-tc-bw-values
 
   -
     name: dl-dev-stats
@@ -1225,6 +1238,13 @@  attribute-sets:
       -
         name: flash
         type: flag
+  -
+    name: dl-rate-tc-bw-values
+    subset-of: devlink
+    attributes:
+      -
+        name: rate-tc-bw
+        type: u32
 
 operations:
   enum-model: directional
@@ -2149,6 +2169,7 @@  operations:
             - rate-tx-priority
             - rate-tx-weight
             - rate-parent-node-name
+            - rate-tc-bw-values
 
     -
       name: rate-new
@@ -2169,6 +2190,7 @@  operations:
             - rate-tx-priority
             - rate-tx-weight
             - rate-parent-node-name
+            - rate-tc-bw-values
 
     -
       name: rate-del
diff --git a/include/net/devlink.h b/include/net/devlink.h
index fbb9a2668e24..277b826cdd60 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -20,6 +20,7 @@ 
 #include <uapi/linux/devlink.h>
 #include <linux/xarray.h>
 #include <linux/firmware.h>
+#include <linux/dcbnl.h>
 
 struct devlink;
 struct devlink_linecard;
@@ -117,6 +118,8 @@  struct devlink_rate {
 
 	u32 tx_priority;
 	u32 tx_weight;
+
+	u32 tc_bw[IEEE_8021QAZ_MAX_TCS];
 };
 
 struct devlink_port {
@@ -1469,6 +1472,8 @@  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,
@@ -1477,6 +1482,8 @@  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 9401aa343673..0940f8770319 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -614,6 +614,9 @@  enum devlink_attr {
 
 	DEVLINK_ATTR_REGION_DIRECT,		/* flag */
 
+	DEVLINK_ATTR_RATE_TC_BW,		/* u32 */
+	DEVLINK_ATTR_RATE_TC_BW_VALUES,		/* nested */
+
 	/* 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 f9786d51f68f..231c2752538f 100644
--- a/net/devlink/netlink_gen.c
+++ b/net/devlink/netlink_gen.c
@@ -18,6 +18,10 @@  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_bw_values_nl_policy[DEVLINK_ATTR_RATE_TC_BW + 1] = {
+	[DEVLINK_ATTR_RATE_TC_BW] = NLA_POLICY_RANGE(NLA_U32, 0, 100),
+};
+
 const struct nla_policy devlink_dl_selftest_id_nl_policy[DEVLINK_ATTR_SELFTEST_ID_FLASH + 1] = {
 	[DEVLINK_ATTR_SELFTEST_ID_FLASH] = { .type = NLA_FLAG, },
 };
@@ -496,7 +500,7 @@  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_BW_VALUES + 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, },
@@ -505,10 +509,11 @@  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_BW_VALUES] = NLA_POLICY_NESTED(devlink_dl_rate_tc_bw_values_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_BW_VALUES + 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, },
@@ -517,6 +522,7 @@  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_BW_VALUES] = NLA_POLICY_NESTED(devlink_dl_rate_tc_bw_values_nl_policy),
 };
 
 /* DEVLINK_CMD_RATE_DEL - do */
@@ -1164,7 +1170,7 @@  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_BW_VALUES,
 		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
 	},
 	{
@@ -1174,7 +1180,7 @@  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_BW_VALUES,
 		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
 	},
 	{
diff --git a/net/devlink/netlink_gen.h b/net/devlink/netlink_gen.h
index 8f2bd50ddf5e..a8f0f20f6f0b 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_bw_values_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..4eb0598d40f9 100644
--- a/net/devlink/rate.c
+++ b/net/devlink/rate.c
@@ -86,7 +86,9 @@  static int devlink_nl_rate_fill(struct sk_buff *msg,
 				int flags, struct netlink_ext_ack *extack)
 {
 	struct devlink *devlink = devlink_rate->devlink;
+	struct nlattr *nla_tc_bw;
 	void *hdr;
+	int i;
 
 	hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
 	if (!hdr)
@@ -129,6 +131,19 @@  static int devlink_nl_rate_fill(struct sk_buff *msg,
 				   devlink_rate->parent->name))
 			goto nla_put_failure;
 
+	nla_tc_bw = nla_nest_start(msg, DEVLINK_ATTR_RATE_TC_BW_VALUES);
+	if (!nla_tc_bw)
+		goto nla_put_failure;
+
+	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
+		if (nla_put_u32(msg, DEVLINK_ATTR_RATE_TC_BW, devlink_rate->tc_bw[i])) {
+			nla_nest_cancel(msg, nla_tc_bw);
+			goto nla_put_failure;
+		}
+	}
+
+	nla_nest_end(msg, nla_tc_bw);
+
 	genlmsg_end(msg, hdr);
 	return 0;
 
@@ -316,11 +331,46 @@  devlink_nl_rate_parent_node_set(struct devlink_rate *devlink_rate,
 	return 0;
 }
 
+static int devlink_nl_rate_tc_bw_set(struct devlink_rate *devlink_rate,
+				     struct genl_info *info,
+				     struct nlattr *nla_tc_bw)
+{
+	struct devlink *devlink = devlink_rate->devlink;
+	const struct devlink_ops *ops = devlink->ops;
+	u32 tc_bw[IEEE_8021QAZ_MAX_TCS] = {0};
+	struct nlattr *nla_tc_entry;
+	int rem, err = 0, i = 0;
+
+	nla_for_each_nested(nla_tc_entry, nla_tc_bw, rem) {
+		if (i >= IEEE_8021QAZ_MAX_TCS || nla_type(nla_tc_entry) != DEVLINK_ATTR_RATE_TC_BW)
+			return -EINVAL;
+
+		tc_bw[i++] = nla_get_u32(nla_tc_entry);
+	}
+
+	if (i != IEEE_8021QAZ_MAX_TCS)
+		return -EINVAL;
+
+	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)
 {
-	struct nlattr *nla_parent, **attrs = info->attrs;
+	struct nlattr *nla_parent, *nla_tc_bw, **attrs = info->attrs;
 	int err = -EOPNOTSUPP;
 	u32 priority;
 	u32 weight;
@@ -380,6 +430,13 @@  static int devlink_nl_rate_set(struct devlink_rate *devlink_rate,
 		devlink_rate->tx_weight = weight;
 	}
 
+	nla_tc_bw = attrs[DEVLINK_ATTR_RATE_TC_BW_VALUES];
+	if (nla_tc_bw) {
+		err = devlink_nl_rate_tc_bw_set(devlink_rate, info, nla_tc_bw);
+		if (err)
+			return err;
+	}
+
 	nla_parent = attrs[DEVLINK_ATTR_RATE_PARENT_NODE_NAME];
 	if (nla_parent) {
 		err = devlink_nl_rate_parent_node_set(devlink_rate, info,
@@ -423,6 +480,12 @@  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_BW_VALUES] && !ops->rate_leaf_tc_bw_set) {
+			NL_SET_ERR_MSG_ATTR(info->extack,
+					    attrs[DEVLINK_ATTR_RATE_TC_BW_VALUES],
+					    "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 +512,12 @@  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_BW_VALUES] && !ops->rate_node_tc_bw_set) {
+			NL_SET_ERR_MSG_ATTR(info->extack,
+					    attrs[DEVLINK_ATTR_RATE_TC_BW_VALUES],
+					    "TC bandwidth set isn't supported for the nodes");
+			return false;
+		}
 	} else {
 		WARN(1, "Unknown type of rate object");
 		return false;