devlink: Add parent dev to devlink API

Upcoming changes to the rate commands need the parent devlink specified.
This change adds a nested 'parent-dev' attribute to the API and helpers
to obtain and put a reference to the parent devlink instance in
info->ctx.

To avoid deadlocks, the parent devlink is unlocked before obtaining the
main devlink instance that is the target of the request.
A reference to the parent is kept until the end of the request to avoid
it suddenly disappearing.

This means that this reference is of limited use without additional
protection.

Signed-off-by: Cosmin Ratiu <cratiu@nvidia.com>
Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20260701073254.754518-6-tariqt@nvidia.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

Documentation/netlink/specs/devlink.yaml

@@ -895,6 +895,16 @@ attribute-sets:
           resource-dump response. Bit 0 (dev) selects device-level
           resources; bit 1 (port) selects port-level resources.
           When absent all classes are returned.
+      -
+        name: parent-dev
+        type: nest
+        nested-attributes: dl-parent-dev
+        doc: |
+          Identifies the devlink instance which owns the parent rate node.
+          Used with rate-set and rate-new to parent a rate object to a node on
+          a different devlink instance, enabling cross-device rate scheduling.
+          When absent, the parent node is resolved on the same instance.
+
   -
     name: dl-dev-stats
     subset-of: devlink
@@ -1317,6 +1327,16 @@ attribute-sets:
              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-parent-dev
+    subset-of: devlink
+    attributes:
+      -
+        name: bus-name
+      -
+        name: dev-name
+      -
+        name: index
 
 operations:
   enum-model: directional

include/uapi/linux/devlink.h

@@ -648,6 +648,8 @@ enum devlink_attr {
 	DEVLINK_ATTR_INDEX,			/* uint */
 	DEVLINK_ATTR_RESOURCE_SCOPE_MASK,	/* u32 */
 
+	DEVLINK_ATTR_PARENT_DEV,		/* nested */
+
 	/* Add new attributes above here, update the spec in
 	 * Documentation/netlink/specs/devlink.yaml and re-generate
 	 * net/devlink/netlink_gen.c.

net/devlink/devl_internal.h

@@ -154,6 +154,7 @@ int devlink_rel_devlink_handle_put(struct sk_buff *msg, struct devlink *devlink,
 struct devlink_nl_ctx {
 	struct devlink *devlink;
 	struct devlink_port *devlink_port;
+	struct devlink *parent_devlink;
 };
 
 static inline struct devlink_nl_ctx *
@@ -197,6 +198,8 @@ typedef int devlink_nl_dump_one_func_t(struct sk_buff *msg,
 struct devlink *
 devlink_get_from_attrs_lock(struct net *net, struct nlattr **attrs,
 			    bool dev_lock);
+struct devlink *
+devlink_get_parent_from_attrs_lock(struct net *net, struct nlattr **attrs);
 
 int devlink_nl_dumpit(struct sk_buff *msg, struct netlink_callback *cb,
 		      devlink_nl_dump_one_func_t *dump_one);

net/devlink/netlink.c

@@ -12,6 +12,7 @@
 #define DEVLINK_NL_FLAG_NEED_PORT		BIT(0)
 #define DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT	BIT(1)
 #define DEVLINK_NL_FLAG_NEED_DEV_LOCK		BIT(2)
+#define DEVLINK_NL_FLAG_OPTIONAL_PARENT_DEV	BIT(3)
 
 static const struct genl_multicast_group devlink_nl_mcgrps[] = {
 	[DEVLINK_MCGRP_CONFIG] = { .name = DEVLINK_GENL_MCGRP_CONFIG_NAME },
@@ -239,19 +240,39 @@ devlink_get_from_attrs_lock(struct net *net, struct nlattr **attrs,
 	return ERR_PTR(-ENODEV);
 }
 
+struct devlink *
+devlink_get_parent_from_attrs_lock(struct net *net, struct nlattr **attrs)
+{
+	return ERR_PTR(-EOPNOTSUPP);
+}
+
 static int __devlink_nl_pre_doit(struct sk_buff *skb, struct genl_info *info,
 				 u8 flags)
 {
+	bool parent_dev = flags & DEVLINK_NL_FLAG_OPTIONAL_PARENT_DEV;
 	bool dev_lock = flags & DEVLINK_NL_FLAG_NEED_DEV_LOCK;
+	struct devlink *devlink, *parent_devlink = NULL;
+	struct net *net = genl_info_net(info);
+	struct nlattr **attrs = info->attrs;
 	struct devlink_port *devlink_port;
-	struct devlink *devlink;
 	int err;
 
-	devlink = devlink_get_from_attrs_lock(genl_info_net(info), info->attrs,
-					      dev_lock);
-	if (IS_ERR(devlink))
-		return PTR_ERR(devlink);
+	if (parent_dev && attrs[DEVLINK_ATTR_PARENT_DEV]) {
+		parent_devlink = devlink_get_parent_from_attrs_lock(net, attrs);
+		if (IS_ERR(parent_devlink))
+			return PTR_ERR(parent_devlink);
+		devlink_nl_ctx(info)->parent_devlink = parent_devlink;
+		/* Drop the parent devlink lock but don't release the reference.
+		 * This will keep it alive until the end of the request.
+		 */
+		devl_unlock(parent_devlink);
+	}
 
+	devlink = devlink_get_from_attrs_lock(net, attrs, dev_lock);
+	if (IS_ERR(devlink)) {
+		err = PTR_ERR(devlink);
+		goto parent_put;
+	}
 	devlink_nl_ctx(info)->devlink = devlink;
 	if (flags & DEVLINK_NL_FLAG_NEED_PORT) {
 		devlink_port = devlink_port_get_from_info(devlink, info);
@@ -270,6 +291,9 @@ static int __devlink_nl_pre_doit(struct sk_buff *skb, struct genl_info *info,
 unlock:
 	devl_dev_unlock(devlink, dev_lock);
 	devlink_put(devlink);
+parent_put:
+	if (parent_dev && parent_devlink)
+		devlink_put(parent_devlink);
 	return err;
 }
 
@@ -307,6 +331,8 @@ static void __devlink_nl_post_doit(struct sk_buff *skb, struct genl_info *info,
 	devlink = devlink_nl_ctx(info)->devlink;
 	devl_dev_unlock(devlink, dev_lock);
 	devlink_put(devlink);
+	if (devlink_nl_ctx(info)->parent_devlink)
+		devlink_put(devlink_nl_ctx(info)->parent_devlink);
 }
 
 void devlink_nl_post_doit(const struct genl_split_ops *ops,