[PATCH net-next V7 09/14] devlink: Allow rate node parents from other devlinks

@@ -417,6 +417,8 @@ API allows to configure following rate object's parameters:
   Parent node name. Parent node rate limits are considered as additional limits
   to all node children limits. ``tx_max`` is an upper limit for children.
   ``tx_share`` is a total bandwidth distributed among children.
+  If the device supports cross-function scheduling, the parent can be from a
+  different function of the same underlying device.
 
 ``tc_bw``
   Allow users to set the bandwidth allocation per traffic class on rate

@@ -1585,6 +1585,11 @@ struct devlink_ops {
 				    struct devlink_rate *parent,
 				    void *priv_child, void *priv_parent,
 				    struct netlink_ext_ack *extack);
+	/* Indicates if cross-device rate nodes are supported.
+	 * This also requires a shared common ancestor object all devices that
+	 * could share rate nodes are nested in.
+	 */
+	bool supported_cross_device_rate_nodes;
 	/**
 	 * selftests_check() - queries if selftest is supported
 	 * @devlink: devlink instance

@@ -30,20 +30,56 @@ devlink_rate_leaf_get_from_info(struct devlink *devlink, struct genl_info *info)
 	return devlink_rate ?: ERR_PTR(-ENODEV);
 }
 
+/* Repeatedly locks the nested-in devlink instances while cross device rate
+ * nodes are supported. Returns the devlink instance where rates should be
+ * stored.
+ */
 struct devlink *devl_rate_lock(struct devlink *devlink)
 {
-	return devlink;
+	struct devlink *rate_devlink = devlink;
+
+	while (rate_devlink->ops &&
+	       rate_devlink->ops->supported_cross_device_rate_nodes) {
+		devlink = devlink_nested_in_get_lock(rate_devlink->rel);
+		if (!devlink)
+			break;
+		rate_devlink = devlink;
+	}
+	return rate_devlink;
 }
+EXPORT_SYMBOL_GPL(devl_rate_lock);
 
+/* Variant of the above for when the nested-in devlink instances are already
+ * locked.
+ */
 static struct devlink *
 devl_get_rate_node_instance_locked(struct devlink *devlink)
 {
-	return devlink;
+	struct devlink *rate_devlink = devlink;
+
+	while (rate_devlink->ops &&
+	       rate_devlink->ops->supported_cross_device_rate_nodes) {
+		devlink = devlink_nested_in_get_locked(rate_devlink->rel);
+		if (!devlink)
+			break;
+		rate_devlink = devlink;
+	}
+	return rate_devlink;
 }
 
+/* Repeatedly unlocks the nested-in devlink instances of 'devlink' while cross
+ * device nodes are supported.
+ */
 void devl_rate_unlock(struct devlink *devlink)
 {
+	if (!devlink || !devlink->ops ||
+	    !devlink->ops->supported_cross_device_rate_nodes)
+		return;
+
+	devl_rate_unlock(devlink_nested_in_get_locked(devlink->rel));
+	devlink_nested_in_put_unlock(devlink->rel);
 }
+EXPORT_SYMBOL_GPL(devl_rate_unlock);
 
 static struct devlink_rate *
 devlink_rate_node_get_by_name(struct devlink *devlink, const char *node_name)

@@ -120,6 +156,24 @@ static int devlink_rate_put_tc_bws(struct sk_buff *msg, u32 *tc_bw)
 	return -EMSGSIZE;
 }
 
+static int devlink_nl_rate_parent_fill(struct sk_buff *msg,
+				       struct devlink_rate *devlink_rate)
+{
+	struct devlink_rate *parent = devlink_rate->parent;
+	struct devlink *devlink = parent->devlink;
+
+	if (nla_put_string(msg, DEVLINK_ATTR_RATE_PARENT_NODE_NAME,
+			   parent->name))
+		return -EMSGSIZE;
+
+	if (devlink != devlink_rate->devlink &&
+	    devlink_nl_put_nested_handle(msg, devlink_net(devlink), devlink,
+					 DEVLINK_ATTR_PARENT_DEV))
+		return -EMSGSIZE;
+
+	return 0;
+}
+
 static int devlink_nl_rate_fill(struct sk_buff *msg,
 				struct devlink_rate *devlink_rate,
 				enum devlink_command cmd, u32 portid, u32 seq,

@@ -164,10 +218,9 @@ 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))
-			goto nla_put_failure;
+	if (devlink_rate->parent &&
+	    devlink_nl_rate_parent_fill(msg, devlink_rate))
+		goto nla_put_failure;
 
 	if (devlink_rate_put_tc_bws(msg, devlink_rate->tc_bw))
 		goto nla_put_failure;

@@ -320,13 +373,14 @@ devlink_nl_rate_parent_node_set(struct devlink_rate *devlink_rate,
 				struct genl_info *info,
 				struct nlattr *nla_parent)
 {
-	struct devlink *devlink = devlink_rate->devlink;
+	struct devlink *devlink = devlink_rate->devlink, *parent_devlink;
 	const char *parent_name = nla_data(nla_parent);
 	const struct devlink_ops *ops = devlink->ops;
 	size_t len = strlen(parent_name);
 	struct devlink_rate *parent;
 	int err = -EOPNOTSUPP;
 
+	parent_devlink = info->user_ptr[1] ? : devlink;
 	parent = devlink_rate->parent;
 
 	if (parent && !len) {

@@ -344,7 +398,13 @@ devlink_nl_rate_parent_node_set(struct devlink_rate *devlink_rate,
 		refcount_dec(&parent->refcnt);
 		devlink_rate->parent = NULL;
 	} else if (len) {
-		parent = devlink_rate_node_get_by_name(devlink, parent_name);
+		/* parent_devlink (when different than devlink) isn't locked,
+		 * but the rate node devlink instance is, so nobody from the
+		 * same group of devices sharing rates could change the used
+		 * fields or unregister the parent.
+		 */
+		parent = devlink_rate_node_get_by_name(parent_devlink,
+						       parent_name);
 		if (IS_ERR(parent))
 			return -ENODEV;
 

@@ -644,6 +704,14 @@ int devlink_nl_rate_set_doit(struct sk_buff *skb, struct genl_info *info)
 		goto unlock;
 	}
 
+	if (info->user_ptr[1] && info->user_ptr[1] != devlink &&
+	    !ops->supported_cross_device_rate_nodes) {
+		NL_SET_ERR_MSG(info->extack,
+			       "Cross-device rate parents aren't supported");
+		err = -EOPNOTSUPP;
+		goto unlock;
+	}
+
 	err = devlink_nl_rate_set(devlink_rate, ops, info);
 
 	if (!err)

@@ -669,6 +737,13 @@ int devlink_nl_rate_new_doit(struct sk_buff *skb, struct genl_info *info)
 	if (!devlink_rate_set_ops_supported(ops, info, DEVLINK_RATE_TYPE_NODE))
 		return -EOPNOTSUPP;
 
+	if (info->user_ptr[1] && info->user_ptr[1] != devlink &&
+	    !ops->supported_cross_device_rate_nodes) {
+		NL_SET_ERR_MSG(info->extack,
+			       "Cross-device rate parents aren't supported");
+		return -EOPNOTSUPP;
+	}
+
 	rate_devlink = devl_rate_lock(devlink);
 	rate_node = devlink_rate_node_get_from_attrs(devlink, info->attrs);
 	if (!IS_ERR(rate_node)) {