[PATCH net-next V6 00/14] devlink and mlx5: Support cross-function rate scheduling

@@ -0,0 +1,94 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+============================
+Devlink Shared Instances
+============================
+
+Overview
+========
+
+Shared devlink instances allow multiple physical functions (PFs) on the same
+chip to share an additional devlink instance for chip-wide operations. This
+is implemented within individual drivers alongside the individual PF devlink
+instances, not replacing them.
+
+Multiple PFs may reside on the same physical chip, running a single firmware.
+Some of the resources and configurations may be shared among these PFs. The
+shared devlink instance provides an object to pin configuration knobs on.
+
+The shared devlink instance is backed by a faux device and provides a common
+interface for operations that affect the entire chip rather than individual PFs.
+A faux device is used as a backing device for the 'entire chip' since there's no
+additional real device instantiated by hardware besides the PF devices.
+
+Implementation
+==============
+
+Architecture
+------------
+
+The implementation uses:
+
+* **Faux device**: Virtual device backing the shared devlink instance
+* **Chip identification**: PFs are grouped by chip using a driver-specific identifier
+* **Shared instance management**: Global list of shared instances with reference counting
+
+API Functions
+-------------
+
+The following functions are provided for managing shared devlink instances:
+
+* ``devlink_shd_get()``: Get or create a shared devlink instance identified by a string ID
+* ``devlink_shd_put()``: Release a reference on a shared devlink instance
+* ``devlink_shd_get_priv()``: Get private data from shared devlink instance
+
+Initialization Flow
+-------------------
+
+1. **PF calls shared devlink init** during driver probe
+2. **Chip identification** using driver-specific method to determine device identity
+3. **Get or create shared instance** using ``devlink_shd_get()``:
+
+   * The function looks up existing instance by identifier
+   * If none exists, creates new instance:
+     - Creates faux device with chip identifier as name
+     - Allocates and registers devlink instance
+     - Adds to global shared instances list
+     - Increments reference count
+
+4. **Set nested devlink instance** for the PF devlink instance using
+   ``devl_nested_devlink_set()`` before registering the PF devlink instance
+
+Cleanup Flow
+------------
+
+1. **Cleanup** when PF is removed
+2. **Call** ``devlink_shd_put()`` to release reference (decrements reference count)
+3. **Shared instance is automatically destroyed** when the last PF removes (device list becomes empty)
+
+Chip Identification
+-------------------
+
+PFs belonging to the same chip are identified using a driver-specific method.
+The driver is free to choose any identifier that is suitable for determining
+whether two PFs are part of the same device. Examples include:
+
+* **PCI VPD serial numbers**: Extract from PCI VPD
+* **Device tree properties**: Read chip identifier from device tree
+* **Other hardware-specific identifiers**: Any unique identifier that groups PFs by chip
+
+Locking
+-------
+
+A global mutex (``shd_mutex``) protects the shared instances list during
+registration/deregistration.
+
+Similarly to other nested devlink instance relationships, devlink lock of
+the shared instance should be always taken after the devlink lock of PF.
+
+Reference Counting
+------------------
+
+Each shared devlink instance maintains a reference count (``refcount_t refcount``).
+The reference count is incremented when ``devlink_shd_get()`` is called and
+decremented when ``devlink_shd_put()`` is called. When the reference count
+reaches zero, the shared instance is automatically destroyed.

@@ -68,6 +68,7 @@ general.
    devlink-resource
    devlink-selftests
    devlink-trap
+   devlink-shared
 
 Driver-specific documentation
 -----------------------------

@@ -1644,6 +1644,12 @@ void devlink_register(struct devlink *devlink);
 void devlink_unregister(struct devlink *devlink);
 void devlink_free(struct devlink *devlink);
 
+struct devlink *devlink_shd_get(const char *id,
+				const struct devlink_ops *ops,
+				size_t priv_size);
+void devlink_shd_put(struct devlink *devlink);
+void *devlink_shd_get_priv(struct devlink *devlink);
+
 /**
  * struct devlink_port_ops - Port operations
  * @port_split: Callback used to split the port into multiple ones.

@@ -1,4 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
 
 obj-y := core.o netlink.o netlink_gen.o dev.o port.o sb.o dpipe.o \
-	 resource.o param.o region.o health.o trap.o rate.o linecard.o
+	 resource.o param.o region.o health.o trap.o rate.o linecard.o sh_dev.o

@@ -0,0 +1,163 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Copyright (c) 2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
+
+#include <linux/device/faux.h>
+#include <net/devlink.h>
+
+#include "devl_internal.h"
+
+static LIST_HEAD(shd_list);
+static DEFINE_MUTEX(shd_mutex); /* Protects shd_list and shd->list */
+
+/* This structure represents a shared devlink instance,
+ * there is one created per identifier (e.g., serial number).
+ */
+struct devlink_shd {
+	struct list_head list; /* Node in shd list */
+	const char *id; /* Identifier string (e.g., serial number) */
+	struct faux_device *faux_dev; /* Related faux device */
+	refcount_t refcount; /* Reference count */
+	char priv[] __aligned(NETDEV_ALIGN); /* Driver private data */
+};
+
+static struct devlink_shd *devlink_shd_lookup(const char *id)
+{
+	struct devlink_shd *shd;
+
+	list_for_each_entry(shd, &shd_list, list) {
+		if (!strcmp(shd->id, id))
+			return shd;
+	}
+
+	return NULL;
+}
+
+static struct devlink_shd *devlink_shd_create(const char *id,
+					      const struct devlink_ops *ops,
+					      size_t priv_size)
+{
+	struct faux_device *faux_dev;
+	struct devlink_shd *shd;
+	struct devlink *devlink;
+
+	/* Create faux device - probe will be called synchronously */
+	faux_dev = faux_device_create(id, NULL, NULL);
+	if (!faux_dev)
+		return NULL;
+
+	devlink = devlink_alloc(ops, sizeof(struct devlink_shd) + priv_size,
+				&faux_dev->dev);
+	if (!devlink)
+		goto err_devlink_alloc;
+	shd = devlink_priv(devlink);
+
+	shd->id = kstrdup(id, GFP_KERNEL);
+	if (!shd->id)
+		goto err_kstrdup_id;
+	shd->faux_dev = faux_dev;
+	refcount_set(&shd->refcount, 1);
+
+	devl_lock(devlink);
+	devl_register(devlink);
+	devl_unlock(devlink);
+
+	list_add_tail(&shd->list, &shd_list);
+
+	return shd;
+
+err_kstrdup_id:
+	devlink_free(devlink);
+
+err_devlink_alloc:
+	faux_device_destroy(faux_dev);
+	return NULL;
+}
+
+static void devlink_shd_destroy(struct devlink_shd *shd)
+{
+	struct devlink *devlink = priv_to_devlink(shd);
+	struct faux_device *faux_dev = shd->faux_dev;
+
+	list_del(&shd->list);
+	devl_lock(devlink);
+	devl_unregister(devlink);
+	devl_unlock(devlink);
+	kfree(shd->id);
+	devlink_free(devlink);
+	faux_device_destroy(faux_dev);
+}
+
+/**
+ * devlink_shd_get - Get or create a shared devlink instance
+ * @id: Identifier string (e.g., serial number) for the shared instance
+ * @ops: Devlink operations structure
+ * @priv_size: Size of private data structure
+ *
+ * Get an existing shared devlink instance identified by @id, or create
+ * a new one if it doesn't exist. The device is automatically added to
+ * the shared instance's device list. Return the devlink instance
+ * with a reference held. The caller must call devlink_shd_put() when done.
+ *
+ * Return: Pointer to the shared devlink instance on success,
+ *         NULL on failure
+ */
+struct devlink *devlink_shd_get(const char *id,
+				const struct devlink_ops *ops,
+				size_t priv_size)
+{
+	struct devlink_shd *shd;
+
+	if (WARN_ON(!id || !ops))
+		return NULL;
+
+	mutex_lock(&shd_mutex);
+
+	shd = devlink_shd_lookup(id);
+	if (!shd)
+		shd = devlink_shd_create(id, ops, priv_size);
+	else
+		refcount_inc(&shd->refcount);
+
+	mutex_unlock(&shd_mutex);
+	return shd ? priv_to_devlink(shd) : NULL;
+}
+EXPORT_SYMBOL_GPL(devlink_shd_get);
+
+/**
+ * devlink_shd_put - Release a reference on a shared devlink instance
+ * @devlink: Shared devlink instance
+ *
+ * Release a reference on a shared devlink instance obtained via
+ * devlink_shd_get().
+ */
+void devlink_shd_put(struct devlink *devlink)
+{
+	struct devlink_shd *shd;
+
+	if (WARN_ON(!devlink))
+		return;
+
+	mutex_lock(&shd_mutex);
+	shd = devlink_priv(devlink);
+	if (refcount_dec_and_test(&shd->refcount))
+		devlink_shd_destroy(shd);
+	mutex_unlock(&shd_mutex);
+}
+EXPORT_SYMBOL_GPL(devlink_shd_put);
+
+/**
+ * devlink_shd_get_priv - Get private data from shared devlink instance
+ * @devlink: Devlink instance
+ *
+ * Returns a pointer to the driver's private data structure within
+ * the shared devlink instance.
+ *
+ * Return: Pointer to private data
+ */
+void *devlink_shd_get_priv(struct devlink *devlink)
+{
+	struct devlink_shd *shd = devlink_priv(devlink);
+
+	return shd->priv;
+}
+EXPORT_SYMBOL_GPL(devlink_shd_get_priv);

@@ -178,9 +178,7 @@ int devlink_rel_nested_in_add(u32 *rel_index, u32 devlink_index,
  * a notification of a change of this object should be sent
  * over netlink. The parent devlink instance lock needs to be
  * taken during the notification preparation.
- * However, since the devlink lock of nested instance is held here,
- * we would end with wrong devlink instance lock ordering and
- * deadlock. Therefore the work is utilized to avoid that.
+ * Since the parent may or may not be locked, 'work' is utilized.
  */
 void devlink_rel_nested_in_notify(struct devlink *devlink)
 {

@@ -67,6 +67,48 @@ static void __devlink_rel_put(struct devlink_rel *rel)
 		devlink_rel_free(rel);
 }
 
+struct devlink *devlink_nested_in_get_lock(struct devlink_rel *rel)
+{
+	struct devlink *devlink;
+
+	if (!rel)
+		return NULL;
+	devlink = devlinks_xa_get(rel->nested_in.devlink_index);
+	if (!devlink)
+		return NULL;
+	devl_lock(devlink);
+	if (devl_is_registered(devlink))
+		return devlink;
+	devl_unlock(devlink);
+	devlink_put(devlink);
+	return NULL;
+}
+
+/* Returns the nested in devlink object and validates its lock is held. */
+struct devlink *devlink_nested_in_get_locked(struct devlink_rel *rel)
+{
+	struct devlink *devlink;
+	unsigned long index;
+
+	if (!rel)
+		return NULL;
+	index = rel->nested_in.devlink_index;
+	devlink = xa_find(&devlinks, &index, index, DEVLINK_REGISTERED);
+	if (devlink)
+		devl_assert_locked(devlink);
+	return devlink;
+}
+
+void devlink_nested_in_put_unlock(struct devlink_rel *rel)
+{
+	struct devlink *devlink = devlink_nested_in_get_locked(rel);
+
+	if (devlink) {
+		devl_unlock(devlink);
+		devlink_put(devlink);
+	}
+}
+
 static void devlink_rel_nested_in_notify_work(struct work_struct *work)
 {
 	struct devlink_rel *rel = container_of(work, struct devlink_rel,

@@ -120,6 +120,9 @@ typedef void devlink_rel_notify_cb_t(struct devlink *devlink, u32 obj_index);
 typedef void devlink_rel_cleanup_cb_t(struct devlink *devlink, u32 obj_index,
 				      u32 rel_index);
 
+struct devlink *devlink_nested_in_get_lock(struct devlink_rel *rel);
+struct devlink *devlink_nested_in_get_locked(struct devlink_rel *rel);
+void devlink_nested_in_put_unlock(struct devlink_rel *rel);
 void devlink_rel_nested_in_clear(u32 rel_index);
 int devlink_rel_nested_in_add(u32 *rel_index, u32 devlink_index,
 			      u32 obj_index, devlink_rel_notify_cb_t *notify_cb,

@@ -517,7 +517,7 @@ void devlink_free(struct devlink *devlink)
 	WARN_ON(!list_empty(&devlink->resource_list));
 	WARN_ON(!list_empty(&devlink->dpipe_table_list));
 	WARN_ON(!list_empty(&devlink->sb_list));
-	WARN_ON(!list_empty(&devlink->rate_list));
+	WARN_ON(devlink_rates_check(devlink, NULL, NULL));
 	WARN_ON(!list_empty(&devlink->linecard_list));
 	WARN_ON(!xa_empty(&devlink->ports));
 

@@ -434,7 +434,7 @@ static void devlink_reload_reinit_sanity_check(struct devlink *devlink)
 	WARN_ON(!list_empty(&devlink->trap_list));
 	WARN_ON(!list_empty(&devlink->dpipe_table_list));
 	WARN_ON(!list_empty(&devlink->sb_list));
-	WARN_ON(!list_empty(&devlink->rate_list));
+	WARN_ON(devlink_rates_check(devlink, NULL, NULL));
 	WARN_ON(!list_empty(&devlink->linecard_list));
 	WARN_ON(!xa_empty(&devlink->ports));
 }

@@ -713,10 +713,11 @@ int devlink_nl_eswitch_set_doit(struct sk_buff *skb, struct genl_info *info)
 	if (info->attrs[DEVLINK_ATTR_ESWITCH_MODE]) {
 		if (!ops->eswitch_mode_set)
 			return -EOPNOTSUPP;
-		mode = nla_get_u16(info->attrs[DEVLINK_ATTR_ESWITCH_MODE]);
-		err = devlink_rate_nodes_check(devlink, mode, info->extack);
+		err = devlink_rates_check(devlink, devlink_rate_is_node,
+					  info->extack);
 		if (err)
 			return err;
+		mode = nla_get_u16(info->attrs[DEVLINK_ATTR_ESWITCH_MODE]);
 		err = ops->eswitch_mode_set(devlink, mode, info->extack);
 		if (err)
 			return err;

@@ -300,8 +300,10 @@ int devlink_resources_validate(struct devlink *devlink,
 			       struct genl_info *info);
 
 /* Rates */
-int devlink_rate_nodes_check(struct devlink *devlink, u16 mode,
-			     struct netlink_ext_ack *extack);
+bool devlink_rate_is_node(const struct devlink_rate *devlink_rate);
+int devlink_rates_check(struct devlink *devlink,
+			bool (*rate_filter)(const struct devlink_rate *),
+			struct netlink_ext_ack *extack);
 
 /* Linecards */
 unsigned int devlink_linecard_index(struct devlink_linecard *linecard);

@@ -12,8 +12,7 @@ devlink_rate_is_leaf(struct devlink_rate *devlink_rate)
 	return devlink_rate->type == DEVLINK_RATE_TYPE_LEAF;
 }
 
-static inline bool
-devlink_rate_is_node(struct devlink_rate *devlink_rate)
+bool devlink_rate_is_node(const struct devlink_rate *devlink_rate)
 {
 	return devlink_rate->type == DEVLINK_RATE_TYPE_NODE;
 }

@@ -688,14 +687,16 @@ int devlink_nl_rate_del_doit(struct sk_buff *skb, struct genl_info *info)
 	return err;
 }
 
-int devlink_rate_nodes_check(struct devlink *devlink, u16 mode,
-			     struct netlink_ext_ack *extack)
+int devlink_rates_check(struct devlink *devlink,
+			bool (*rate_filter)(const struct devlink_rate *),
+			struct netlink_ext_ack *extack)
 {
 	struct devlink_rate *devlink_rate;
 
 	list_for_each_entry(devlink_rate, &devlink->rate_list, list)
-		if (devlink_rate_is_node(devlink_rate)) {
-			NL_SET_ERR_MSG(extack, "Rate node(s) exists.");
+		if (!rate_filter || rate_filter(devlink_rate)) {
+			if (extack)
+				NL_SET_ERR_MSG(extack, "Rate node(s) exists.");
 			return -EBUSY;
 		}
 	return 0;

@@ -1820,6 +1820,8 @@ void devlink_port_attrs_pci_sf_set(struct devlink_port *devlink_port,
 				   bool external);
 int devl_port_fn_devlink_set(struct devlink_port *devlink_port,
 			     struct devlink *fn_devlink);
+struct devlink *devl_rate_lock(struct devlink *devlink);
+void devl_rate_unlock(struct devlink *devlink);
 struct devlink_rate *
 devl_rate_node_create(struct devlink *devlink, void *priv, char *node_name,
 		      struct devlink_rate *parent);

@@ -30,13 +30,31 @@ devlink_rate_leaf_get_from_info(struct devlink *devlink, struct genl_info *info)
 	return devlink_rate ?: ERR_PTR(-ENODEV);
 }
 
+struct devlink *devl_rate_lock(struct devlink *devlink)
+{
+	return devlink;
+}
+
+static struct devlink *
+devl_get_rate_node_instance_locked(struct devlink *devlink)
+{
+	return devlink;
+}
+
+void devl_rate_unlock(struct devlink *devlink)
+{
+}
+
 static struct devlink_rate *
 devlink_rate_node_get_by_name(struct devlink *devlink, const char *node_name)
 {
 	struct devlink_rate *devlink_rate;
+	struct devlink *rate_devlink;
 
-	list_for_each_entry(devlink_rate, &devlink->rate_list, list) {
-		if (devlink_rate_is_node(devlink_rate) &&
+	rate_devlink = devl_get_rate_node_instance_locked(devlink);
+	list_for_each_entry(devlink_rate, &rate_devlink->rate_list, list) {
+		if (devlink_rate->devlink == devlink &&
+		    devlink_rate_is_node(devlink_rate) &&
 		    !strcmp(node_name, devlink_rate->name))
 			return devlink_rate;
 	}

@@ -190,17 +208,25 @@ static void devlink_rate_notify(struct devlink_rate *devlink_rate,
 void devlink_rates_notify_register(struct devlink *devlink)
 {
 	struct devlink_rate *rate_node;
+	struct devlink *rate_devlink;
 
-	list_for_each_entry(rate_node, &devlink->rate_list, list)
-		devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_NEW);
+	rate_devlink = devl_rate_lock(devlink);
+	list_for_each_entry(rate_node, &rate_devlink->rate_list, list)
+		if (rate_node->devlink == devlink)
+			devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_NEW);
+	devl_rate_unlock(devlink);
 }
 
 void devlink_rates_notify_unregister(struct devlink *devlink)
 {
 	struct devlink_rate *rate_node;
+	struct devlink *rate_devlink;
 
-	list_for_each_entry_reverse(rate_node, &devlink->rate_list, list)
-		devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_DEL);
+	rate_devlink = devl_rate_lock(devlink);
+	list_for_each_entry_reverse(rate_node, &rate_devlink->rate_list, list)
+		if (rate_node->devlink == devlink)
+			devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_DEL);
+	devl_rate_unlock(devlink);
 }
 
 static int

@@ -209,17 +235,20 @@ devlink_nl_rate_get_dump_one(struct sk_buff *msg, struct devlink *devlink,
 {
 	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
 	struct devlink_rate *devlink_rate;
+	struct devlink *rate_devlink;
 	int idx = 0;
 	int err = 0;
 
-	list_for_each_entry(devlink_rate, &devlink->rate_list, list) {
+	rate_devlink = devl_rate_lock(devlink);
+	list_for_each_entry(devlink_rate, &rate_devlink->rate_list, list) {
 		enum devlink_command cmd = DEVLINK_CMD_RATE_NEW;
 		u32 id = NETLINK_CB(cb->skb).portid;
 
-		if (idx < state->idx) {
+		if (idx < state->idx || devlink_rate->devlink != devlink) {
 			idx++;
 			continue;
 		}
+
 		err = devlink_nl_rate_fill(msg, devlink_rate, cmd, id,
 					   cb->nlh->nlmsg_seq, flags, NULL);
 		if (err) {

@@ -228,6 +257,7 @@ devlink_nl_rate_get_dump_one(struct sk_buff *msg, struct devlink *devlink,
 		}
 		idx++;
 	}
+	devl_rate_unlock(devlink);
 
 	return err;
 }

@@ -244,23 +274,33 @@ int devlink_nl_rate_get_doit(struct sk_buff *skb, struct genl_info *info)
 	struct sk_buff *msg;
 	int err;
 
+	devl_rate_lock(devlink);
 	devlink_rate = devlink_rate_get_from_info(devlink, info);
-	if (IS_ERR(devlink_rate))
-		return PTR_ERR(devlink_rate);
+	if (IS_ERR(devlink_rate)) {
+		err = PTR_ERR(devlink_rate);
+		goto unlock;
+	}
 
 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
-	if (!msg)
-		return -ENOMEM;
+	if (!msg) {
+		err = -ENOMEM;
+		goto unlock;
+	}
 
 	err = devlink_nl_rate_fill(msg, devlink_rate, DEVLINK_CMD_RATE_NEW,
 				   info->snd_portid, info->snd_seq, 0,
 				   info->extack);
-	if (err) {
-		nlmsg_free(msg);
-		return err;
-	}
+	if (err)
+		goto err_fill;
 
+	devl_rate_unlock(devlink);
 	return genlmsg_reply(msg, info);
+
+err_fill:
+	nlmsg_free(msg);
+unlock:
+	devl_rate_unlock(devlink);
+	return err;
 }
 
 static bool

@@ -590,24 +630,32 @@ int devlink_nl_rate_set_doit(struct sk_buff *skb, struct genl_info *info)
 	const struct devlink_ops *ops;
 	int err;
 
+	devl_rate_lock(devlink);
 	devlink_rate = devlink_rate_get_from_info(devlink, info);
-	if (IS_ERR(devlink_rate))
-		return PTR_ERR(devlink_rate);
+	if (IS_ERR(devlink_rate)) {
+		err = PTR_ERR(devlink_rate);
+		goto unlock;
+	}
 
 	ops = devlink->ops;
-	if (!ops || !devlink_rate_set_ops_supported(ops, info, devlink_rate->type))
-		return -EOPNOTSUPP;
+	if (!ops ||
+	    !devlink_rate_set_ops_supported(ops, info, devlink_rate->type)) {
+		err = -EOPNOTSUPP;
+		goto unlock;
+	}
 
 	err = devlink_nl_rate_set(devlink_rate, ops, info);
 
 	if (!err)
 		devlink_rate_notify(devlink_rate, DEVLINK_CMD_RATE_NEW);
+unlock:
+	devl_rate_unlock(devlink);
 	return err;
 }
 
 int devlink_nl_rate_new_doit(struct sk_buff *skb, struct genl_info *info)
 {
-	struct devlink *devlink = info->user_ptr[0];
+	struct devlink *rate_devlink, *devlink = info->user_ptr[0];
 	struct devlink_rate *rate_node;
 	const struct devlink_ops *ops;
 	int err;

@@ -621,15 +669,21 @@ 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;
 
+	rate_devlink = devl_rate_lock(devlink);
 	rate_node = devlink_rate_node_get_from_attrs(devlink, info->attrs);
-	if (!IS_ERR(rate_node))
-		return -EEXIST;
-	else if (rate_node == ERR_PTR(-EINVAL))
-		return -EINVAL;
+	if (!IS_ERR(rate_node)) {
+		err = -EEXIST;
+		goto unlock;
+	} else if (rate_node == ERR_PTR(-EINVAL)) {
+		err = -EINVAL;
+		goto unlock;
+	}
 
 	rate_node = kzalloc(sizeof(*rate_node), GFP_KERNEL);
-	if (!rate_node)
-		return -ENOMEM;
+	if (!rate_node) {
+		err = -ENOMEM;
+		goto unlock;
+	}
 
 	rate_node->devlink = devlink;
 	rate_node->type = DEVLINK_RATE_TYPE_NODE;

@@ -648,8 +702,9 @@ int devlink_nl_rate_new_doit(struct sk_buff *skb, struct genl_info *info)
 		goto err_rate_set;
 
 	refcount_set(&rate_node->refcnt, 1);
-	list_add(&rate_node->list, &devlink->rate_list);
+	list_add(&rate_node->list, &rate_devlink->rate_list);
 	devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_NEW);
+	devl_rate_unlock(devlink);
 	return 0;
 
 err_rate_set:

@@ -658,6 +713,8 @@ int devlink_nl_rate_new_doit(struct sk_buff *skb, struct genl_info *info)
 	kfree(rate_node->name);
 err_strdup:
 	kfree(rate_node);
+unlock:
+	devl_rate_unlock(devlink);
 	return err;
 }
 

@@ -667,13 +724,17 @@ int devlink_nl_rate_del_doit(struct sk_buff *skb, struct genl_info *info)
 	struct devlink_rate *rate_node;
 	int err;
 
+	devl_rate_lock(devlink);
 	rate_node = devlink_rate_node_get_from_info(devlink, info);
-	if (IS_ERR(rate_node))
-		return PTR_ERR(rate_node);
+	if (IS_ERR(rate_node)) {
+		err = PTR_ERR(rate_node);
+		goto unlock;
+	}
 
 	if (refcount_read(&rate_node->refcnt) > 1) {
 		NL_SET_ERR_MSG(info->extack, "Node has children. Cannot delete node.");
-		return -EBUSY;
+		err = -EBUSY;
+		goto unlock;
 	}
 
 	devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_DEL);

@@ -684,6 +745,8 @@ int devlink_nl_rate_del_doit(struct sk_buff *skb, struct genl_info *info)
 	list_del(&rate_node->list);
 	kfree(rate_node->name);
 	kfree(rate_node);
+unlock:
+	devl_rate_unlock(devlink);
 	return err;
 }
 

@@ -692,14 +755,20 @@ int devlink_rates_check(struct devlink *devlink,
 			struct netlink_ext_ack *extack)
 {
 	struct devlink_rate *devlink_rate;
+	struct devlink *rate_devlink;
+	int err = 0;
 
-	list_for_each_entry(devlink_rate, &devlink->rate_list, list)
-		if (!rate_filter || rate_filter(devlink_rate)) {
+	rate_devlink = devl_rate_lock(devlink);
+	list_for_each_entry(devlink_rate, &rate_devlink->rate_list, list)
+		if (devlink_rate->devlink == devlink &&
+		    (!rate_filter || rate_filter(devlink_rate))) {
 			if (extack)
 				NL_SET_ERR_MSG(extack, "Rate node(s) exists.");
-			return -EBUSY;
+			err = -EBUSY;
+			break;
 		}
-	return 0;
+	devl_rate_unlock(devlink);
+	return err;
 }
 
 /**

@@ -716,14 +785,20 @@ devl_rate_node_create(struct devlink *devlink, void *priv, char *node_name,
 		      struct devlink_rate *parent)
 {
 	struct devlink_rate *rate_node;
+	struct devlink *rate_devlink;
 
+	rate_devlink = devl_rate_lock(devlink);
 	rate_node = devlink_rate_node_get_by_name(devlink, node_name);
-	if (!IS_ERR(rate_node))
-		return ERR_PTR(-EEXIST);
+	if (!IS_ERR(rate_node)) {
+		rate_node = ERR_PTR(-EEXIST);
+		goto unlock;
+	}
 
 	rate_node = kzalloc(sizeof(*rate_node), GFP_KERNEL);
-	if (!rate_node)
-		return ERR_PTR(-ENOMEM);
+	if (!rate_node) {
+		rate_node = ERR_PTR(-ENOMEM);
+		goto unlock;
+	}
 
 	if (parent) {
 		rate_node->parent = parent;

@@ -737,12 +812,15 @@ devl_rate_node_create(struct devlink *devlink, void *priv, char *node_name,
 	rate_node->name = kstrdup(node_name, GFP_KERNEL);
 	if (!rate_node->name) {
 		kfree(rate_node);
-		return ERR_PTR(-ENOMEM);
+		rate_node = ERR_PTR(-ENOMEM);
+		goto unlock;
 	}
 
 	refcount_set(&rate_node->refcnt, 1);
-	list_add(&rate_node->list, &devlink->rate_list);
+	list_add(&rate_node->list, &rate_devlink->rate_list);
 	devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_NEW);
+unlock:
+	devl_rate_unlock(devlink);
 	return rate_node;
 }
 EXPORT_SYMBOL_GPL(devl_rate_node_create);

@@ -758,10 +836,10 @@ EXPORT_SYMBOL_GPL(devl_rate_node_create);
 int devl_rate_leaf_create(struct devlink_port *devlink_port, void *priv,
 			  struct devlink_rate *parent)
 {
-	struct devlink *devlink = devlink_port->devlink;
+	struct devlink *rate_devlink, *devlink = devlink_port->devlink;
 	struct devlink_rate *devlink_rate;
 
-	devl_assert_locked(devlink_port->devlink);
+	devl_assert_locked(devlink);
 
 	if (WARN_ON(devlink_port->devlink_rate))
 		return -EBUSY;

@@ -770,6 +848,7 @@ int devl_rate_leaf_create(struct devlink_port *devlink_port, void *priv,
 	if (!devlink_rate)
 		return -ENOMEM;
 
+	rate_devlink = devl_rate_lock(devlink);
 	if (parent) {
 		devlink_rate->parent = parent;
 		refcount_inc(&devlink_rate->parent->refcnt);

@@ -779,9 +858,10 @@ int devl_rate_leaf_create(struct devlink_port *devlink_port, void *priv,
 	devlink_rate->devlink = devlink;
 	devlink_rate->devlink_port = devlink_port;
 	devlink_rate->priv = priv;
-	list_add_tail(&devlink_rate->list, &devlink->rate_list);
+	list_add_tail(&devlink_rate->list, &rate_devlink->rate_list);
 	devlink_port->devlink_rate = devlink_rate;
 	devlink_rate_notify(devlink_rate, DEVLINK_CMD_RATE_NEW);
+	devl_rate_unlock(devlink);
 
 	return 0;
 }

@@ -797,16 +877,19 @@ EXPORT_SYMBOL_GPL(devl_rate_leaf_create);
 void devl_rate_leaf_destroy(struct devlink_port *devlink_port)
 {
 	struct devlink_rate *devlink_rate = devlink_port->devlink_rate;
+	struct devlink *devlink = devlink_port->devlink;
 
-	devl_assert_locked(devlink_port->devlink);
+	devl_assert_locked(devlink);
 	if (!devlink_rate)
 		return;
 
+	devl_rate_lock(devlink);
 	devlink_rate_notify(devlink_rate, DEVLINK_CMD_RATE_DEL);
 	if (devlink_rate->parent)
 		refcount_dec(&devlink_rate->parent->refcnt);
 	list_del(&devlink_rate->list);
 	devlink_port->devlink_rate = NULL;
+	devl_rate_unlock(devlink);
 	kfree(devlink_rate);
 }
 EXPORT_SYMBOL_GPL(devl_rate_leaf_destroy);

@@ -815,18 +898,22 @@ EXPORT_SYMBOL_GPL(devl_rate_leaf_destroy);
  * devl_rate_nodes_destroy - destroy all devlink rate nodes on device
  * @devlink: devlink instance
  *
- * Unset parent for all rate objects and destroy all rate nodes
- * on specified device.
+ * Unset parent for all rate objects involving this device and destroy all rate
+ * nodes on it.
  */
 void devl_rate_nodes_destroy(struct devlink *devlink)
 {
 	const struct devlink_ops *ops = devlink->ops;
 	struct devlink_rate *devlink_rate, *tmp;
+	struct devlink *rate_devlink;
 
 	devl_assert_locked(devlink);
+	rate_devlink = devl_rate_lock(devlink);
 
-	list_for_each_entry(devlink_rate, &devlink->rate_list, list) {
-		if (!devlink_rate->parent)
+	list_for_each_entry(devlink_rate, &rate_devlink->rate_list, list) {
+		if (!devlink_rate->parent ||
+		    (devlink_rate->devlink != devlink &&
+		     devlink_rate->parent->devlink != devlink))
 			continue;
 
 		if (devlink_rate_is_leaf(devlink_rate))

@@ -839,13 +926,16 @@ void devl_rate_nodes_destroy(struct devlink *devlink)
 		refcount_dec(&devlink_rate->parent->refcnt);
 		devlink_rate->parent = NULL;
 	}
-	list_for_each_entry_safe(devlink_rate, tmp, &devlink->rate_list, list) {
-		if (devlink_rate_is_node(devlink_rate)) {
+	list_for_each_entry_safe(devlink_rate, tmp, &rate_devlink->rate_list,
+				 list) {
+		if (devlink_rate->devlink == devlink &&
+		    devlink_rate_is_node(devlink_rate)) {
 			ops->rate_node_del(devlink_rate, devlink_rate->priv, NULL);
 			list_del(&devlink_rate->list);
 			kfree(devlink_rate->name);
 			kfree(devlink_rate);
 		}
 	}
+	devl_rate_unlock(devlink);
 }
 EXPORT_SYMBOL_GPL(devl_rate_nodes_destroy);

@@ -867,6 +867,10 @@ attribute-sets:
         type: flag
         doc: Request restoring parameter to its default value.
         value: 183
+
+      - name: parent-dev
+        type: nest
+        nested-attributes: dl-parent-dev
   -
     name: dl-dev-stats
     subset-of: devlink

@@ -1289,6 +1293,14 @@ 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
 
 operations:
   enum-model: directional

@@ -642,6 +642,8 @@ enum devlink_attr {
 	DEVLINK_ATTR_PARAM_VALUE_DEFAULT,	/* dynamic */
 	DEVLINK_ATTR_PARAM_RESET_DEFAULT,	/* flag */
 
+	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.

@@ -162,6 +162,8 @@ 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);

@@ -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 },

@@ -206,19 +207,51 @@ 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)
+{
+	struct nlattr *tb[DEVLINK_ATTR_DEV_NAME + 1];
+	int err;
+
+	if (!attrs[DEVLINK_ATTR_PARENT_DEV])
+		return ERR_PTR(-EINVAL);
+
+	err = nla_parse_nested(tb, DEVLINK_ATTR_DEV_NAME,
+			       attrs[DEVLINK_ATTR_PARENT_DEV],
+			       devlink_dl_parent_dev_nl_policy, NULL);
+	if (err)
+		return ERR_PTR(err);
+
+	return devlink_get_from_attrs_lock(net, tb, false);
+}
+
 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);
+		info->user_ptr[1] = 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;
+	}
 	info->user_ptr[0] = devlink;
 	if (flags & DEVLINK_NL_FLAG_NEED_PORT) {
 		devlink_port = devlink_port_get_from_info(devlink, info);

@@ -237,6 +270,9 @@ 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;
 }
 

@@ -265,6 +301,14 @@ int devlink_nl_pre_doit_port_optional(const struct genl_split_ops *ops,
 	return __devlink_nl_pre_doit(skb, info, DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT);
 }
 
+int devlink_nl_pre_doit_parent_dev_optional(const struct genl_split_ops *ops,
+					    struct sk_buff *skb,
+					    struct genl_info *info)
+{
+	return __devlink_nl_pre_doit(skb, info,
+				     DEVLINK_NL_FLAG_OPTIONAL_PARENT_DEV);
+}
+
 static void __devlink_nl_post_doit(struct sk_buff *skb, struct genl_info *info,
 				   u8 flags)
 {

@@ -274,6 +318,11 @@ static void __devlink_nl_post_doit(struct sk_buff *skb, struct genl_info *info,
 	devlink = info->user_ptr[0];
 	devl_dev_unlock(devlink, dev_lock);
 	devlink_put(devlink);
+	if ((flags & DEVLINK_NL_FLAG_OPTIONAL_PARENT_DEV) &&
+	    info->user_ptr[1]) {
+		devlink = info->user_ptr[1];
+		devlink_put(devlink);
+	}
 }
 
 void devlink_nl_post_doit(const struct genl_split_ops *ops,