| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20241113180034.714102-4-tariqt@nvidia.com>
Date: Wed, 13 Nov 2024 20:00:28 +0200
From: Tariq Toukan <tariqt@...dia.com>
To: "David S. Miller" <davem@...emloft.net>, Jakub Kicinski <kuba@...nel.org>,
Paolo Abeni <pabeni@...hat.com>, Eric Dumazet <edumazet@...gle.com>, "Andrew
Lunn" <andrew+netdev@...n.ch>
CC: <netdev@...r.kernel.org>, Saeed Mahameed <saeedm@...dia.com>, Gal Pressman
<gal@...dia.com>, Leon Romanovsky <leonro@...dia.com>, Jiri Pirko
<jiri@...nulli.us>, Carolina Jubran <cjubran@...dia.com>, Cosmin Ratiu
<cratiu@...dia.com>, Tariq Toukan <tariqt@...dia.com>
Subject: [PATCH net-next 3/8] devlink: Extend devlink rate API with traffic classes bandwidth management
From: Carolina Jubran <cjubran@...dia.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 5:10 6:60 7:0
Signed-off-by: Carolina Jubran <cjubran@...dia.com>
Reviewed-by: Cosmin Ratiu <cratiu@...dia.com>
Signed-off-by: Tariq Toukan <tariqt@...dia.com>
---
Documentation/netlink/specs/devlink.yaml | 50 ++++++++++++++++++++
include/net/devlink.h | 6 +++
include/uapi/linux/devlink.h | 10 ++++
net/devlink/netlink_gen.c | 21 +++++++--
net/devlink/netlink_gen.h | 1 +
net/devlink/rate.c | 60 ++++++++++++++++++++++--
6 files changed, 141 insertions(+), 7 deletions(-)
diff --git a/Documentation/netlink/specs/devlink.yaml b/Documentation/netlink/specs/devlink.yaml
index 09fbb4c03fc8..41fdc2514f69 100644
--- a/Documentation/netlink/specs/devlink.yaml
+++ b/Documentation/netlink/specs/devlink.yaml
@@ -817,6 +817,34 @@ attribute-sets:
-
name: rate-tx-weight
type: u32
+ -
+ name: rate-tc-0-bw
+ type: u32
+ -
+ name: rate-tc-1-bw
+ type: u32
+ -
+ name: rate-tc-2-bw
+ type: u32
+ -
+ name: rate-tc-3-bw
+ type: u32
+ -
+ name: rate-tc-4-bw
+ type: u32
+ -
+ name: rate-tc-5-bw
+ type: u32
+ -
+ name: rate-tc-6-bw
+ type: u32
+ -
+ name: rate-tc-7-bw
+ type: u32
+ -
+ name: rate-tc-bw
+ type: nest
+ nested-attributes: dl-rate-tc-bw-values
-
name: region-direct
type: flag
@@ -1225,6 +1253,26 @@ attribute-sets:
-
name: flash
type: flag
+ -
+ name: dl-rate-tc-bw-values
+ subset-of: devlink
+ attributes:
+ -
+ name: rate-tc-0-bw
+ -
+ name: rate-tc-1-bw
+ -
+ name: rate-tc-2-bw
+ -
+ name: rate-tc-3-bw
+ -
+ name: rate-tc-4-bw
+ -
+ name: rate-tc-5-bw
+ -
+ name: rate-tc-6-bw
+ -
+ name: rate-tc-7-bw
operations:
enum-model: directional
@@ -2148,6 +2196,7 @@ operations:
- rate-tx-max
- rate-tx-priority
- rate-tx-weight
+ - rate-tc-bw
- rate-parent-node-name
-
@@ -2168,6 +2217,7 @@ operations:
- rate-tx-max
- rate-tx-priority
- rate-tx-weight
+ - rate-tc-bw
- rate-parent-node-name
-
diff --git a/include/net/devlink.h b/include/net/devlink.h
index fbb9a2668e24..917bc006a5a4 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -117,6 +117,8 @@ struct devlink_rate {
u32 tx_priority;
u32 tx_weight;
+
+ u32 tc_bw[IEEE_8021QAZ_MAX_TCS];
};
struct devlink_port {
@@ -1469,6 +1471,8 @@ 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 +1481,8 @@ 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..c369726a262a 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -614,6 +614,16 @@ enum devlink_attr {
DEVLINK_ATTR_REGION_DIRECT, /* flag */
+ DEVLINK_ATTR_RATE_TC_0_BW, /* u32 */
+ DEVLINK_ATTR_RATE_TC_1_BW, /* u32 */
+ DEVLINK_ATTR_RATE_TC_2_BW, /* u32 */
+ DEVLINK_ATTR_RATE_TC_3_BW, /* u32 */
+ DEVLINK_ATTR_RATE_TC_4_BW, /* u32 */
+ DEVLINK_ATTR_RATE_TC_5_BW, /* u32 */
+ DEVLINK_ATTR_RATE_TC_6_BW, /* u32 */
+ DEVLINK_ATTR_RATE_TC_7_BW, /* u32 */
+ DEVLINK_ATTR_RATE_TC_BW, /* 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..546766bdd836 100644
--- a/net/devlink/netlink_gen.c
+++ b/net/devlink/netlink_gen.c
@@ -18,6 +18,17 @@ 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_nl_policy[DEVLINK_ATTR_RATE_TC_7_BW + 1] = {
+ [DEVLINK_ATTR_RATE_TC_0_BW] = { .type = NLA_U32, },
+ [DEVLINK_ATTR_RATE_TC_1_BW] = { .type = NLA_U32, },
+ [DEVLINK_ATTR_RATE_TC_2_BW] = { .type = NLA_U32, },
+ [DEVLINK_ATTR_RATE_TC_3_BW] = { .type = NLA_U32, },
+ [DEVLINK_ATTR_RATE_TC_4_BW] = { .type = NLA_U32, },
+ [DEVLINK_ATTR_RATE_TC_5_BW] = { .type = NLA_U32, },
+ [DEVLINK_ATTR_RATE_TC_6_BW] = { .type = NLA_U32, },
+ [DEVLINK_ATTR_RATE_TC_7_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, },
};
@@ -496,7 +507,7 @@ 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 + 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 +516,11 @@ 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] = NLA_POLICY_NESTED(devlink_dl_rate_tc_bw_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 + 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 +529,7 @@ 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] = NLA_POLICY_NESTED(devlink_dl_rate_tc_bw_nl_policy),
};
/* DEVLINK_CMD_RATE_DEL - do */
@@ -1164,7 +1177,7 @@ 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,
.flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
},
{
@@ -1174,7 +1187,7 @@ 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,
.flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
},
{
diff --git a/net/devlink/netlink_gen.h b/net/devlink/netlink_gen.h
index 8f2bd50ddf5e..084ad5026d4f 100644
--- a/net/devlink/netlink_gen.h
+++ b/net/devlink/netlink_gen.h
@@ -14,6 +14,7 @@
/* 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_selftest_id_nl_policy[DEVLINK_ATTR_SELFTEST_ID_FLASH + 1];
+extern const struct nla_policy devlink_dl_rate_tc_bw_nl_policy[DEVLINK_ATTR_RATE_TC_7_BW + 1];
/* Ops table for devlink */
extern const struct genl_split_ops devlink_nl_ops[74];
diff --git a/net/devlink/rate.c b/net/devlink/rate.c
index 8828ffaf6cbc..9bffda6783f9 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)
@@ -124,10 +126,19 @@ static int devlink_nl_rate_fill(struct sk_buff *msg,
devlink_rate->tx_weight))
goto nla_put_failure;
- if (devlink_rate->parent)
- if (nla_put_string(msg, DEVLINK_ATTR_RATE_PARENT_NODE_NAME,
- devlink_rate->parent->name))
+ nla_tc_bw = nla_nest_start(msg, DEVLINK_ATTR_RATE_TC_BW);
+ 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_0_BW + i,
+ 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;
@@ -321,6 +332,7 @@ static int devlink_nl_rate_set(struct devlink_rate *devlink_rate,
struct genl_info *info)
{
struct nlattr *nla_parent, **attrs = info->attrs;
+ u32 tc_bw[IEEE_8021QAZ_MAX_TCS];
int err = -EOPNOTSUPP;
u32 priority;
u32 weight;
@@ -380,6 +392,36 @@ static int devlink_nl_rate_set(struct devlink_rate *devlink_rate,
devlink_rate->tx_weight = weight;
}
+ if (attrs[DEVLINK_ATTR_RATE_TC_BW]) {
+ struct nlattr *nla_tc_bw = attrs[DEVLINK_ATTR_RATE_TC_BW];
+ struct nlattr *tb[DEVLINK_ATTR_RATE_TC_7_BW + 1];
+ int i;
+
+ err = nla_parse_nested(tb, DEVLINK_ATTR_RATE_TC_7_BW, nla_tc_bw,
+ devlink_dl_rate_tc_bw_nl_policy, info->extack);
+ if (err)
+ return err;
+
+ for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
+ if (tb[DEVLINK_ATTR_RATE_TC_0_BW + i])
+ tc_bw[i] = nla_get_u32(tb[DEVLINK_ATTR_RATE_TC_0_BW + i]);
+ else
+ tc_bw[i] = 0;
+ }
+
+ 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));
+ }
+
nla_parent = attrs[DEVLINK_ATTR_RATE_PARENT_NODE_NAME];
if (nla_parent) {
err = devlink_nl_rate_parent_node_set(devlink_rate, info,
@@ -423,6 +465,12 @@ 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] && !ops->rate_leaf_tc_bw_set) {
+ NL_SET_ERR_MSG_ATTR(info->extack,
+ attrs[DEVLINK_ATTR_RATE_TC_BW],
+ "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 +497,12 @@ 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] && !ops->rate_node_tc_bw_set) {
+ NL_SET_ERR_MSG_ATTR(info->extack,
+ attrs[DEVLINK_ATTR_RATE_TC_BW],
+ "TC bandwidth set isn't supported for the nodes");
+ return false;
+ }
} else {
WARN(1, "Unknown type of rate object");
return false;
--
2.44.0
Powered by blists - more mailing lists