[RFC V2 net-next 1/2] devlink: Add eswitch mode boot defaults

[Mark Bloch <mbloch@nvidia.com>]

Add devlink= kernel command line support for configuring devlink
eswitch mode during device initialization.

The supported syntax selects either all devlink handles or one explicit
comma-separated handle list:

  devlink=[*]:esw:mode:<mode>
  devlink=[<handle>[,<handle>...]]:esw:mode:<mode>

where <mode> is one of legacy, switchdev or switchdev_inactive. All
selected handles receive the same mode. Comma-separated default groups are
not supported.

The default is applied through the existing eswitch_mode_set() devlink
operation, matching the userspace devlink eswitch set command.

Document the devlink= syntax and duplicate handle handling.

Signed-off-by: Mark Bloch <mbloch@nvidia.com>
---
 .../admin-guide/kernel-parameters.txt         |  24 ++
 .../networking/devlink/devlink-defaults.rst   |  93 ++++++
 Documentation/networking/devlink/index.rst    |   1 +
 include/net/devlink.h                         |   1 +
 net/devlink/core.c                            | 269 ++++++++++++++++++
 5 files changed, 388 insertions(+)
 create mode 100644 Documentation/networking/devlink/devlink-defaults.rst

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 7834ee927310..46435bdfe039 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1278,6 +1278,30 @@ Kernel parameters
 	dell_smm_hwmon.fan_max=
 			[HW] Maximum configurable fan speed.
 
+	devlink=	[NET]
+			Format:
+			[<selector>]:esw:mode:<mode>
+
+			<selector>:
+			* | <handle>[,<handle>...]
+
+			<handle>:
+			<bus-name>/<dev-name>
+
+			Configure default devlink settings for matching
+			devlink instances during device initialization.
+
+			Currently supported settings:
+			esw:mode:{ legacy | switchdev | switchdev_inactive }
+
+			Examples:
+			devlink=[*]:esw:mode:switchdev
+			devlink=[pci/0000:08:00.0]:esw:mode:switchdev
+			devlink=[pci/0000:08:00.0,pci/0000:09:00.1]:esw:mode:legacy
+
+			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
diff --git a/Documentation/networking/devlink/devlink-defaults.rst b/Documentation/networking/devlink/devlink-defaults.rst
new file mode 100644
index 000000000000..4db3025c540f
--- /dev/null
+++ b/Documentation/networking/devlink/devlink-defaults.rst
@@ -0,0 +1,93 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+================
+Devlink Defaults
+================
+
+Devlink defaults allow selected devlink settings 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=`` kernel command line parameter.
+
+The general syntax is::
+
+  devlink=[<selector>]:esw:mode:<mode>
+
+``<selector>`` is either ``*`` or one or more devlink handles::
+
+  * | <bus-name>/<dev-name>[,<bus-name>/<dev-name>...]
+
+``*`` applies the default to every devlink instance. All handles in the same
+``[]`` list receive the same eswitch mode setting.
+
+``<mode>`` is one of ``legacy``, ``switchdev`` or ``switchdev_inactive``.
+
+Syntax rules
+------------
+
+The following syntax rules apply:
+
+* Specify the default in one ``devlink=`` parameter. Repeated ``devlink=``
+  parameters are not accumulated.
+* The ``devlink=`` 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.
+* ``<bus-name>`` must not contain ``:``.
+* ``<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 inside ``[]`` separates handles.
+* Comma-separated default groups are not supported.
+* Duplicate handles are rejected and the devlink default is ignored.
+
+Supported defaults
+==================
+
+The supported command is ``esw``:
+
+.. list-table::
+   :widths: 10 25 35
+   :header-rows: 1
+
+   * - Command
+     - Options
+     - Values
+   * - ``esw``
+     - ``mode:<mode>``
+     - ``legacy``, ``switchdev``, ``switchdev_inactive``
+
+The ``esw:mode`` default corresponds to the userspace command::
+
+  devlink dev eswitch set <handle> mode <value>
+
+
+Examples
+========
+
+Set all devlink instances to switchdev mode::
+
+  devlink=[*]:esw:mode:switchdev
+
+Set one PCI devlink instance to switchdev mode::
+
+  devlink=[pci/0000:08:00.0]:esw:mode:switchdev
+
+Set two PCI devlink instances to legacy mode::
+
+  devlink=[pci/0000:08:00.0,pci/0000:09:00.1]:esw:mode:legacy
+
+The following is invalid because comma-separated default groups are not
+supported::
+
+  devlink=[pci/0000:08:00.0]:esw:mode:switchdev,[pci/0000:09:00.0]:esw:mode:switchdev_inactive
diff --git a/Documentation/networking/devlink/index.rst b/Documentation/networking/devlink/index.rst
index f7ba7dcf477d..0d27a7008b14 100644
--- a/Documentation/networking/devlink/index.rst
+++ b/Documentation/networking/devlink/index.rst
@@ -56,6 +56,7 @@ general.
    :maxdepth: 1
 
    devlink-dpipe
+   devlink-defaults
    devlink-eswitch-attr
    devlink-flash
    devlink-health
diff --git a/include/net/devlink.h b/include/net/devlink.h
index bcd31de1f890..058654d6800f 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -1622,6 +1622,7 @@ int devl_trylock(struct devlink *devlink);
 void devl_unlock(struct devlink *devlink);
 void devl_assert_locked(struct devlink *devlink);
 bool devl_lock_is_held(struct devlink *devlink);
+int devl_apply_defaults(struct devlink *devlink);
 DEFINE_GUARD(devl, struct devlink *, devl_lock(_T), devl_unlock(_T));
 
 struct ib_device;
diff --git a/net/devlink/core.c b/net/devlink/core.c
index eeb6a71f5f56..2cfd50f9393b 100644
--- a/net/devlink/core.c
+++ b/net/devlink/core.c
@@ -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 +20,247 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_trap_report);
 
 DEFINE_XARRAY_FLAGS(devlinks, XA_FLAGS_ALLOC);
 
+static char *devlink_default;
+static bool devlink_default_match_all;
+static enum devlink_eswitch_mode devlink_default_eswitch_mode;
+static LIST_HEAD(devlink_default_nodes);
+
+struct devlink_default_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_cmd_parse(char *str)
+{
+	char *cmd;
+	char *attr;
+	char *mode;
+
+	cmd = strsep(&str, ":");
+	attr = strsep(&str, ":");
+	mode = strsep(&str, ":");
+	if (!cmd || strcmp(cmd, "esw") || !attr || strcmp(attr, "mode") ||
+	    !mode || !*mode || str)
+		return -EINVAL;
+
+	return devlink_default_esw_mode_to_value(mode,
+						 &devlink_default_eswitch_mode);
+}
+
+static int devlink_default_eswitch_apply(struct devlink *devlink)
+{
+	const struct devlink_ops *ops = devlink->ops;
+
+	if (!ops->eswitch_mode_set)
+		return -EOPNOTSUPP;
+
+	return ops->eswitch_mode_set(devlink, devlink_default_eswitch_mode,
+				     NULL);
+}
+
+static int __init
+devlink_default_handle_parse(char *handle, char **bus_name, char **dev_name)
+{
+	char *slash;
+	char *p;
+
+	if (!handle || !*handle)
+		return -EINVAL;
+
+	for (p = handle; *p; p++) {
+		if (*p == '[' || *p == ']' || *p == '*')
+			return -EINVAL;
+	}
+
+	slash = strchr(handle, '/');
+	if (!slash || slash == handle || !slash[1])
+		return -EINVAL;
+	if (strchr(slash + 1, '/'))
+		return -EINVAL;
+
+	*slash = '\0';
+	if (strchr(handle, ':'))
+		return -EINVAL;
+
+	*bus_name = handle;
+	*dev_name = slash + 1;
+	return 0;
+}
+
+static struct devlink_default_node *
+devlink_default_node_find(const char *bus_name, const char *dev_name)
+{
+	struct devlink_default_node *node;
+
+	list_for_each_entry(node, &devlink_default_nodes, list) {
+		if (!strcmp(node->bus_name, bus_name) &&
+		    !strcmp(node->dev_name, dev_name))
+			return node;
+	}
+
+	return NULL;
+}
+
+static int __init
+devlink_default_node_add(const char *bus_name, const char *dev_name)
+{
+	struct devlink_default_node *node;
+
+	if (devlink_default_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_nodes);
+	return 0;
+}
+
+static int __init devlink_default_handles_parse(char *handles)
+{
+	char *handle;
+	int err;
+
+	if (!strcmp(handles, "*")) {
+		devlink_default_match_all = true;
+		return 0;
+	}
+
+	while ((handle = strsep(&handles, ",")) != NULL) {
+		char *bus_name;
+		char *dev_name;
+
+		err = devlink_default_handle_parse(handle, &bus_name,
+						   &dev_name);
+		if (err)
+			return err;
+
+		err = devlink_default_node_add(bus_name, dev_name);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static void __init devlink_default_node_free(struct devlink_default_node *node)
+{
+	kfree(node->bus_name);
+	kfree(node->dev_name);
+	kfree(node);
+}
+
+static void __init devlink_default_nodes_clear(void)
+{
+	struct devlink_default_node *node;
+	struct devlink_default_node *node_tmp;
+
+	list_for_each_entry_safe(node, node_tmp, &devlink_default_nodes, list) {
+		list_del(&node->list);
+		devlink_default_node_free(node);
+	}
+
+	devlink_default_match_all = false;
+}
+
+static int __init devlink_default_parse(char *str)
+{
+	char *handles_end;
+	char *handles;
+	char *cmd;
+	int err;
+
+	if (!str || *str != '[')
+		return -EINVAL;
+
+	handles = str + 1;
+	handles_end = strchr(handles, ']');
+	if (!handles_end || handles_end[1] != ':' || !handles_end[2])
+		return -EINVAL;
+
+	*handles_end = '\0';
+	cmd = handles_end + 2;
+	if (!*handles)
+		return -EINVAL;
+
+	err = devlink_default_cmd_parse(cmd);
+	if (err)
+		return err;
+
+	err = devlink_default_handles_parse(handles);
+	if (err)
+		devlink_default_nodes_clear();
+
+	return err;
+}
+
+/**
+ * devl_apply_defaults - Apply defaults matching the devlink instance
+ * @devlink: devlink
+ *
+ * The caller must hold the devlink instance lock.
+ *
+ * Return: 0 on success, negative error code otherwise.
+ */
+int devl_apply_defaults(struct devlink *devlink)
+{
+	const char *bus_name = devlink_bus_name(devlink);
+	const char *dev_name = devlink_dev_name(devlink);
+	struct devlink_default_node *node;
+
+	devl_assert_locked(devlink);
+
+	if (devlink_default_match_all)
+		return devlink_default_eswitch_apply(devlink);
+
+	node = devlink_default_node_find(bus_name, dev_name);
+	if (node)
+		return devlink_default_eswitch_apply(devlink);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(devl_apply_defaults);
+
+static int __init devlink_default_setup(char *str)
+{
+	devlink_default = str;
+	return 1;
+}
+__setup("devlink=", devlink_default_setup);
+
 static struct devlink *devlinks_xa_get(unsigned long index)
 {
 	struct devlink *devlink;
@@ -578,6 +823,27 @@ static int __init devlink_init(void)
 {
 	int err;
 
+	if (devlink_default) {
+		char *def;
+
+		def = kstrdup(devlink_default, GFP_KERNEL);
+		if (!def) {
+			err = -ENOMEM;
+			goto out;
+		}
+		err = devlink_default_parse(def);
+		kfree(def);
+		if (err == -EEXIST) {
+			devlink_default = NULL;
+			pr_warn("devlink: duplicate handles ignored\n");
+		} else if (err == -EINVAL) {
+			devlink_default = NULL;
+			pr_warn("devlink: invalid command line parameter ignored\n");
+		} else if (err) {
+			goto out;
+		}
+	}
+
 	err = register_pernet_subsys(&devlink_pernet_ops);
 	if (err)
 		goto out;
@@ -593,7 +859,10 @@ static int __init devlink_init(void)
 out_unreg_pernet_subsys:
 	unregister_pernet_subsys(&devlink_pernet_ops);
 out:
+	if (err)
+		devlink_default_nodes_clear();
 	WARN_ON(err);
+
 	return err;
 }
 
-- 
2.34.1