@@ -1249,6 +1249,31 @@ Kernel parameters
 	dell_smm_hwmon.fan_max=
 			[HW] Maximum configurable fan speed.
 
+	devlink_eswitch_mode=
+			[NET]
+			Format:
+			<selector>=<mode>
+
+			<selector>:
+			* | <handle>[,<handle>...]
+
+			<handle>:
+			<bus-name>/<dev-name>
+
+			Configure default devlink eswitch mode for matching
+			devlink instances during device initialization.
+
+			<mode>:
+			legacy | switchdev | switchdev_inactive
+
+			Examples:
+			devlink_eswitch_mode=*=switchdev
+			devlink_eswitch_mode=pci/0000:08:00.0=switchdev
+			devlink_eswitch_mode=pci/0000:08:00.0,pci/0000:09:00.1=switchdev_inactive
+
+			See Documentation/networking/devlink/devlink-defaults.rst
+			for the full syntax.
+
 	dfltcc=		[HW,S390]
 			Format: { on | off | def_only | inf_only | always }
 			on:       s390 zlib hardware support for compression on

@@ -0,0 +1,78 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+==============================
+Devlink Eswitch Mode Defaults
+==============================
+
+Devlink eswitch mode defaults allow the eswitch mode to be provided on the
+kernel command line and applied to matching devlink instances during device
+initialization.
+
+The devlink device is selected by its devlink handle. For PCI devices this is
+the same handle shown by ``devlink dev show``, for example
+``pci/0000:08:00.0``.
+
+Kernel command line syntax
+==========================
+
+Defaults are specified with the ``devlink_eswitch_mode=`` kernel command line
+parameter.
+
+The general syntax is::
+
+  devlink_eswitch_mode=<selector>=<mode>
+
+``<selector>`` is either ``*`` or one or more devlink handles::
+
+  * | <bus-name>/<dev-name>[,<bus-name>/<dev-name>...]
+
+``*`` applies the mode to every devlink instance. All handles in the same
+selector receive the same eswitch mode.
+
+``<mode>`` is one of ``legacy``, ``switchdev`` or ``switchdev_inactive``.
+
+Syntax rules
+------------
+
+The following syntax rules apply:
+
+* Specify the default in one ``devlink_eswitch_mode=`` parameter. Repeated
+  ``devlink_eswitch_mode=`` parameters are not accumulated.
+* The ``devlink_eswitch_mode=`` value is limited by the kernel command line
+  size.
+* Whitespace is not allowed within the parameter value.
+* ``<selector>`` must be either ``*`` or a handle list. ``*`` cannot be
+  combined with explicit handles.
+* ``<bus-name>`` and ``<dev-name>`` must not be empty.
+* ``<dev-name>`` may contain ``:``. This allows PCI names such as
+  ``0000:08:00.0``.
+* Handles must not contain whitespace, ``*``, ``=`` or more than one ``/``.
+* A comma separates handles.
+* Comma-separated default assignments are not supported.
+* Duplicate handles are rejected and the devlink eswitch mode default is
+  ignored.
+
+The eswitch mode default corresponds to the userspace command::
+
+  devlink dev eswitch set <handle> mode <value>
+
+
+Examples
+========
+
+Set all devlink instances to switchdev mode::
+
+  devlink_eswitch_mode=*=switchdev
+
+Set one PCI devlink instance to switchdev mode::
+
+  devlink_eswitch_mode=pci/0000:08:00.0=switchdev
+
+Set two PCI devlink instances to switchdev inactive mode::
+
+  devlink_eswitch_mode=pci/0000:08:00.0,pci/0000:09:00.1=switchdev_inactive
+
+The following is invalid because comma-separated default assignments are not
+supported::
+
+  devlink_eswitch_mode=pci/0000:08:00.0=switchdev,pci/0000:09:00.0=switchdev_inactive

@@ -56,6 +56,7 @@ general.
    :maxdepth: 1
 
    devlink-dpipe
+   devlink-defaults
    devlink-eswitch-attr
    devlink-flash
    devlink-health

@@ -4,6 +4,10 @@
  * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com>
  */
 
+#include <linux/init.h>
+#include <linux/list.h>
+#include <linux/slab.h>
+#include <linux/string.h>
 #include <net/genetlink.h>
 #define CREATE_TRACE_POINTS
 #include <trace/events/devlink.h>

@@ -16,6 +20,193 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_trap_report);
 
 DEFINE_XARRAY_FLAGS(devlinks, XA_FLAGS_ALLOC);
 
+static char *devlink_default_esw_mode_param;
+static bool devlink_default_esw_mode_match_all;
+static enum devlink_eswitch_mode devlink_default_esw_mode;
+static LIST_HEAD(devlink_default_esw_mode_nodes);
+
+struct devlink_default_esw_mode_node {
+	struct list_head list;
+	char *bus_name;
+	char *dev_name;
+};
+
+static int __init
+devlink_default_esw_mode_to_value(const char *str,
+				  enum devlink_eswitch_mode *mode)
+{
+	if (!strcmp(str, "legacy")) {
+		*mode = DEVLINK_ESWITCH_MODE_LEGACY;
+		return 0;
+	}
+	if (!strcmp(str, "switchdev")) {
+		*mode = DEVLINK_ESWITCH_MODE_SWITCHDEV;
+		return 0;
+	}
+	if (!strcmp(str, "switchdev_inactive")) {
+		*mode = DEVLINK_ESWITCH_MODE_SWITCHDEV_INACTIVE;
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
+static int __init
+devlink_default_esw_mode_handle_parse(char *handle, char **bus_name,
+				      char **dev_name)
+{
+	char *slash;
+	char *p;
+
+	if (!*handle)
+		return -EINVAL;
+
+	for (p = handle; *p; p++) {
+		if (*p == '*' || *p == '=')
+			return -EINVAL;
+	}
+
+	slash = strchr(handle, '/');
+	if (!slash || slash == handle || !slash[1])
+		return -EINVAL;
+	if (strchr(slash + 1, '/'))
+		return -EINVAL;
+
+	*slash = '\0';
+
+	*bus_name = handle;
+	*dev_name = slash + 1;
+	return 0;
+}
+
+static struct devlink_default_esw_mode_node *
+devlink_default_esw_mode_node_find(const char *bus_name, const char *dev_name)
+{
+	struct devlink_default_esw_mode_node *node;
+
+	list_for_each_entry(node, &devlink_default_esw_mode_nodes, list) {
+		if (!strcmp(node->bus_name, bus_name) &&
+		    !strcmp(node->dev_name, dev_name))
+			return node;
+	}
+
+	return NULL;
+}
+
+static int __init
+devlink_default_esw_mode_node_add(const char *bus_name, const char *dev_name)
+{
+	struct devlink_default_esw_mode_node *node;
+
+	if (devlink_default_esw_mode_node_find(bus_name, dev_name))
+		return -EEXIST;
+
+	node = kzalloc_obj(*node);
+	if (!node)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&node->list);
+	node->bus_name = kstrdup(bus_name, GFP_KERNEL);
+	node->dev_name = kstrdup(dev_name, GFP_KERNEL);
+	if (!node->bus_name || !node->dev_name) {
+		kfree(node->bus_name);
+		kfree(node->dev_name);
+		kfree(node);
+		return -ENOMEM;
+	}
+
+	list_add_tail(&node->list, &devlink_default_esw_mode_nodes);
+	return 0;
+}
+
+static int __init devlink_default_esw_mode_handles_parse(char *handles)
+{
+	char *handle;
+	int err;
+
+	if (!strcmp(handles, "*")) {
+		devlink_default_esw_mode_match_all = true;
+		return 0;
+	}
+
+	while ((handle = strsep(&handles, ",")) != NULL) {
+		char *bus_name;
+		char *dev_name;
+
+		err = devlink_default_esw_mode_handle_parse(handle, &bus_name,
+							    &dev_name);
+		if (err)
+			return err;
+
+		err = devlink_default_esw_mode_node_add(bus_name, dev_name);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static void __init
+devlink_default_esw_mode_node_free(struct devlink_default_esw_mode_node *node)
+{
+	kfree(node->bus_name);
+	kfree(node->dev_name);
+	kfree(node);
+}
+
+static void __init devlink_default_esw_mode_nodes_clear(void)
+{
+	struct devlink_default_esw_mode_node *node;
+	struct devlink_default_esw_mode_node *node_tmp;
+
+	list_for_each_entry_safe(node, node_tmp,
+				 &devlink_default_esw_mode_nodes, list) {
+		list_del(&node->list);
+		devlink_default_esw_mode_node_free(node);
+	}
+
+	devlink_default_esw_mode_match_all = false;
+}
+
+static int __init devlink_default_esw_mode_parse(char *str)
+{
+	char *handles;
+	char *separator;
+	char *mode;
+	enum devlink_eswitch_mode esw_mode;
+	int err;
+
+	if (!*str)
+		return -EINVAL;
+
+	separator = strrchr(str, '=');
+	if (!separator || separator == str || !separator[1])
+		return -EINVAL;
+
+	*separator = '\0';
+	handles = str;
+	mode = separator + 1;
+
+	err = devlink_default_esw_mode_to_value(mode, &esw_mode);
+	if (err)
+		return err;
+
+	err = devlink_default_esw_mode_handles_parse(handles);
+	if (err)
+		devlink_default_esw_mode_nodes_clear();
+	else
+		devlink_default_esw_mode = esw_mode;
+
+	return err;
+}
+
+static int __init devlink_default_esw_mode_setup(char *str)
+{
+	devlink_default_esw_mode_param = str;
+	return 1;
+}
+__setup("devlink_eswitch_mode=", devlink_default_esw_mode_setup);
+
 static struct devlink *devlinks_xa_get(unsigned long index)
 {
 	struct devlink *devlink;

@@ -382,6 +573,14 @@ struct devlink *devlinks_xa_lookup_get(struct net *net, unsigned long index)
 /**
  * devl_register - Register devlink instance
  * @devlink: devlink
+ *
+ * Make @devlink visible to userspace. Drivers must call this only after the
+ * instance is fully initialized and its devlink operations can be called.
+ *
+ * Context: Caller must hold the devlink instance lock. Use devlink_register()
+ * when the lock is not already held.
+ *
+ * Return: 0 on success.
  */
 int devl_register(struct devlink *devlink)
 {

@@ -580,6 +779,31 @@ static int __init devlink_init(void)
 {
 	int err;
 
+	if (devlink_default_esw_mode_param) {
+		char *def;
+
+		def = kstrdup(devlink_default_esw_mode_param, GFP_KERNEL);
+		if (!def) {
+			devlink_default_esw_mode_param = NULL;
+			pr_warn("devlink: devlink_eswitch_mode parameter ignored, failed to allocate memory\n");
+		} else {
+			err = devlink_default_esw_mode_parse(def);
+			kfree(def);
+			if (err == -EEXIST) {
+				devlink_default_esw_mode_param = NULL;
+				pr_warn("devlink: duplicate eswitch mode handles ignored\n");
+			} else if (err == -EINVAL) {
+				devlink_default_esw_mode_param = NULL;
+				pr_warn("devlink: invalid devlink_eswitch_mode parameter ignored\n");
+			} else if (err == -ENOMEM) {
+				devlink_default_esw_mode_param = NULL;
+				pr_warn("devlink: devlink_eswitch_mode parameter ignored, failed to allocate memory\n");
+			} else if (err) {
+				goto out;
+			}
+		}
+	}
+
 	err = register_pernet_subsys(&devlink_pernet_ops);
 	if (err)
 		goto out;

@@ -595,7 +819,10 @@ static int __init devlink_init(void)
 out_unreg_pernet_subsys:
 	unregister_pernet_subsys(&devlink_pernet_ops);
 out:
+	if (err)
+		devlink_default_esw_mode_nodes_clear();
 	WARN_ON(err);
+
 	return err;
 }