Merge branch 'devlink-code-split-and-structured-instance-walk'

Jakub Kicinski says:

====================
devlink: code split and structured instance walk

Split devlink.c into a handful of files, trying to keep the "core"
code away from all the command-specific implementations.
The core code has been quite scattered until now. Going forward we can
consider using a source file per-subobject, I think that it's quite
beneficial to newcomers (based on relative ease with which folks
contribute to ethtool vs devlink). But this series doesn't split
everything out, yet - partially due to backporting concerns,
but mostly due to lack of time. Bulk of the netlink command
handling is left in a leftover.c file.

Introduce a context structure for dumps, and use it to store
the devlink instance ID of the last dumped devlink instance.
This means we don't have to restart the walk from 0 each time.

Finally - introduce a "structured walk". A centralized dump handler
in devlink/netlink.c which walks the devlink instances, deals with
refcounting/locking, simplifying the per-object implementations quite
a bit. Inspired by the ethtool code.

v1: https://lore.kernel.org/all/20230104041636.226398-1-kuba@kernel.org/
RFC: https://lore.kernel.org/all/20221215020155.1619839-1-kuba@kernel.org/
====================

Link: https://lore.kernel.org/r/20230105040531.353563-1-kuba@kernel.orgSigned-off-by: Jakub Kicinski <kuba@kernel.org>

MAINTAINERS

@@ -6099,7 +6099,7 @@ S:	Supported
 F:	Documentation/networking/devlink
 F:	include/net/devlink.h
 F:	include/uapi/linux/devlink.h
-F:	net/core/devlink.c
+F:	net/devlink/
 
 DH ELECTRONICS IMX6 DHCOM/DHCOR BOARD SUPPORT
 M:	Christoph Niedermaier <cniedermaier@dh-electronics.com>

include/linux/netlink.h

@@ -263,6 +263,10 @@ struct netlink_callback {
 	};
 };
 
+#define NL_ASSET_DUMP_CTX_FITS(type_name)				\
+	BUILD_BUG_ON(sizeof(type_name) >				\
+		     sizeof_field(struct netlink_callback, ctx))
+
 struct netlink_notify {
 	struct net *net;
 	u32 portid;

net/Makefile

@@ -23,6 +23,7 @@ obj-$(CONFIG_BPFILTER)		+= bpfilter/
 obj-$(CONFIG_PACKET)		+= packet/
 obj-$(CONFIG_NET_KEY)		+= key/
 obj-$(CONFIG_BRIDGE)		+= bridge/
+obj-$(CONFIG_NET_DEVLINK)	+= devlink/
 obj-$(CONFIG_NET_DSA)		+= dsa/
 obj-$(CONFIG_ATALK)		+= appletalk/
 obj-$(CONFIG_X25)		+= x25/

net/core/Makefile

@@ -33,7 +33,6 @@ obj-$(CONFIG_LWTUNNEL) += lwtunnel.o
 obj-$(CONFIG_LWTUNNEL_BPF) += lwt_bpf.o
 obj-$(CONFIG_DST_CACHE) += dst_cache.o
 obj-$(CONFIG_HWBM) += hwbm.o
-obj-$(CONFIG_NET_DEVLINK) += devlink.o
 obj-$(CONFIG_GRO_CELLS) += gro_cells.o
 obj-$(CONFIG_FAILOVER) += failover.o
 obj-$(CONFIG_NET_SOCK_MSG) += skmsg.o

net/devlink/Makefile

+# SPDX-License-Identifier: GPL-2.0
+
+obj-y := leftover.o core.o netlink.o

net/devlink/core.c

+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2016 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com>
+ */
+
+#include <net/genetlink.h>
+
+#include "devl_internal.h"
+
+DEFINE_XARRAY_FLAGS(devlinks, XA_FLAGS_ALLOC);
+
+void *devlink_priv(struct devlink *devlink)
+{
+	return &devlink->priv;
+}
+EXPORT_SYMBOL_GPL(devlink_priv);
+
+struct devlink *priv_to_devlink(void *priv)
+{
+	return container_of(priv, struct devlink, priv);
+}
+EXPORT_SYMBOL_GPL(priv_to_devlink);
+
+struct device *devlink_to_dev(const struct devlink *devlink)
+{
+	return devlink->dev;
+}
+EXPORT_SYMBOL_GPL(devlink_to_dev);
+
+struct net *devlink_net(const struct devlink *devlink)
+{
+	return read_pnet(&devlink->_net);
+}
+EXPORT_SYMBOL_GPL(devlink_net);
+
+void devl_assert_locked(struct devlink *devlink)
+{
+	lockdep_assert_held(&devlink->lock);
+}
+EXPORT_SYMBOL_GPL(devl_assert_locked);
+
+#ifdef CONFIG_LOCKDEP
+/* For use in conjunction with LOCKDEP only e.g. rcu_dereference_protected() */
+bool devl_lock_is_held(struct devlink *devlink)
+{
+	return lockdep_is_held(&devlink->lock);
+}
+EXPORT_SYMBOL_GPL(devl_lock_is_held);
+#endif
+
+void devl_lock(struct devlink *devlink)
+{
+	mutex_lock(&devlink->lock);
+}
+EXPORT_SYMBOL_GPL(devl_lock);
+
+int devl_trylock(struct devlink *devlink)
+{
+	return mutex_trylock(&devlink->lock);
+}
+EXPORT_SYMBOL_GPL(devl_trylock);
+
+void devl_unlock(struct devlink *devlink)
+{
+	mutex_unlock(&devlink->lock);
+}
+EXPORT_SYMBOL_GPL(devl_unlock);
+
+struct devlink *__must_check devlink_try_get(struct devlink *devlink)
+{
+	if (refcount_inc_not_zero(&devlink->refcount))
+		return devlink;
+	return NULL;
+}
+
+static void __devlink_put_rcu(struct rcu_head *head)
+{
+	struct devlink *devlink = container_of(head, struct devlink, rcu);
+
+	complete(&devlink->comp);
+}
+
+void devlink_put(struct devlink *devlink)
+{
+	if (refcount_dec_and_test(&devlink->refcount))
+		/* Make sure unregister operation that may await the completion
+		 * is unblocked only after all users are after the end of
+		 * RCU grace period.
+		 */
+		call_rcu(&devlink->rcu, __devlink_put_rcu);
+}
+
+struct devlink *
+devlinks_xa_find_get(struct net *net, unsigned long *indexp,
+		     void * (*xa_find_fn)(struct xarray *, unsigned long *,
+					  unsigned long, xa_mark_t))
+{
+	struct devlink *devlink;
+
+	rcu_read_lock();
+retry:
+	devlink = xa_find_fn(&devlinks, indexp, ULONG_MAX, DEVLINK_REGISTERED);
+	if (!devlink)
+		goto unlock;
+
+	/* In case devlink_unregister() was already called and "unregistering"
+	 * mark was set, do not allow to get a devlink reference here.
+	 * This prevents live-lock of devlink_unregister() wait for completion.
+	 */
+	if (xa_get_mark(&devlinks, *indexp, DEVLINK_UNREGISTERING))
+		goto retry;
+
+	/* For a possible retry, the xa_find_after() should be always used */
+	xa_find_fn = xa_find_after;
+	if (!devlink_try_get(devlink))
+		goto retry;
+	if (!net_eq(devlink_net(devlink), net)) {
+		devlink_put(devlink);
+		goto retry;
+	}
+unlock:
+	rcu_read_unlock();
+	return devlink;
+}
+
+struct devlink *
+devlinks_xa_find_get_first(struct net *net, unsigned long *indexp)
+{
+	return devlinks_xa_find_get(net, indexp, xa_find);
+}
+
+struct devlink *
+devlinks_xa_find_get_next(struct net *net, unsigned long *indexp)
+{
+	return devlinks_xa_find_get(net, indexp, xa_find_after);
+}
+
+/**
+ *	devlink_set_features - Set devlink supported features
+ *
+ *	@devlink: devlink
+ *	@features: devlink support features
+ *
+ *	This interface allows us to set reload ops separatelly from
+ *	the devlink_alloc.
+ */
+void devlink_set_features(struct devlink *devlink, u64 features)
+{
+	ASSERT_DEVLINK_NOT_REGISTERED(devlink);
+
+	WARN_ON(features & DEVLINK_F_RELOAD &&
+		!devlink_reload_supported(devlink->ops));
+	devlink->features = features;
+}
+EXPORT_SYMBOL_GPL(devlink_set_features);
+
+/**
+ *	devlink_register - Register devlink instance
+ *
+ *	@devlink: devlink
+ */
+void devlink_register(struct devlink *devlink)
+{
+	ASSERT_DEVLINK_NOT_REGISTERED(devlink);
+	/* Make sure that we are in .probe() routine */
+
+	xa_set_mark(&devlinks, devlink->index, DEVLINK_REGISTERED);
+	devlink_notify_register(devlink);
+}
+EXPORT_SYMBOL_GPL(devlink_register);
+
+/**
+ *	devlink_unregister - Unregister devlink instance
+ *
+ *	@devlink: devlink
+ */
+void devlink_unregister(struct devlink *devlink)
+{
+	ASSERT_DEVLINK_REGISTERED(devlink);
+	/* Make sure that we are in .remove() routine */
+
+	xa_set_mark(&devlinks, devlink->index, DEVLINK_UNREGISTERING);
+	devlink_put(devlink);
+	wait_for_completion(&devlink->comp);
+
+	devlink_notify_unregister(devlink);
+	xa_clear_mark(&devlinks, devlink->index, DEVLINK_REGISTERED);
+	xa_clear_mark(&devlinks, devlink->index, DEVLINK_UNREGISTERING);
+}
+EXPORT_SYMBOL_GPL(devlink_unregister);
+
+/**
+ *	devlink_alloc_ns - Allocate new devlink instance resources
+ *	in specific namespace
+ *
+ *	@ops: ops
+ *	@priv_size: size of user private data
+ *	@net: net namespace
+ *	@dev: parent device
+ *
+ *	Allocate new devlink instance resources, including devlink index
+ *	and name.
+ */
+struct devlink *devlink_alloc_ns(const struct devlink_ops *ops,
+				 size_t priv_size, struct net *net,
+				 struct device *dev)
+{
+	struct devlink *devlink;
+	static u32 last_id;
+	int ret;
+
+	WARN_ON(!ops || !dev);
+	if (!devlink_reload_actions_valid(ops))
+		return NULL;
+
+	devlink = kzalloc(sizeof(*devlink) + priv_size, GFP_KERNEL);
+	if (!devlink)
+		return NULL;
+
+	ret = xa_alloc_cyclic(&devlinks, &devlink->index, devlink, xa_limit_31b,
+			      &last_id, GFP_KERNEL);
+	if (ret < 0)
+		goto err_xa_alloc;
+
+	devlink->netdevice_nb.notifier_call = devlink_port_netdevice_event;
+	ret = register_netdevice_notifier_net(net, &devlink->netdevice_nb);
+	if (ret)
+		goto err_register_netdevice_notifier;
+
+	devlink->dev = dev;
+	devlink->ops = ops;
+	xa_init_flags(&devlink->ports, XA_FLAGS_ALLOC);
+	xa_init_flags(&devlink->snapshot_ids, XA_FLAGS_ALLOC);
+	write_pnet(&devlink->_net, net);
+	INIT_LIST_HEAD(&devlink->rate_list);
+	INIT_LIST_HEAD(&devlink->linecard_list);
+	INIT_LIST_HEAD(&devlink->sb_list);
+	INIT_LIST_HEAD_RCU(&devlink->dpipe_table_list);
+	INIT_LIST_HEAD(&devlink->resource_list);
+	INIT_LIST_HEAD(&devlink->param_list);
+	INIT_LIST_HEAD(&devlink->region_list);
+	INIT_LIST_HEAD(&devlink->reporter_list);
+	INIT_LIST_HEAD(&devlink->trap_list);
+	INIT_LIST_HEAD(&devlink->trap_group_list);
+	INIT_LIST_HEAD(&devlink->trap_policer_list);
+	lockdep_register_key(&devlink->lock_key);
+	mutex_init(&devlink->lock);
+	lockdep_set_class(&devlink->lock, &devlink->lock_key);
+	mutex_init(&devlink->reporters_lock);
+	mutex_init(&devlink->linecards_lock);
+	refcount_set(&devlink->refcount, 1);
+	init_completion(&devlink->comp);
+
+	return devlink;
+
+err_register_netdevice_notifier:
+	xa_erase(&devlinks, devlink->index);
+err_xa_alloc:
+	kfree(devlink);
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(devlink_alloc_ns);
+
+/**
+ *	devlink_free - Free devlink instance resources
+ *
+ *	@devlink: devlink
+ */
+void devlink_free(struct devlink *devlink)
+{
+	ASSERT_DEVLINK_NOT_REGISTERED(devlink);
+
+	mutex_destroy(&devlink->linecards_lock);
+	mutex_destroy(&devlink->reporters_lock);
+	mutex_destroy(&devlink->lock);
+	lockdep_unregister_key(&devlink->lock_key);
+	WARN_ON(!list_empty(&devlink->trap_policer_list));
+	WARN_ON(!list_empty(&devlink->trap_group_list));
+	WARN_ON(!list_empty(&devlink->trap_list));
+	WARN_ON(!list_empty(&devlink->reporter_list));
+	WARN_ON(!list_empty(&devlink->region_list));
+	WARN_ON(!list_empty(&devlink->param_list));
+	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(!list_empty(&devlink->linecard_list));
+	WARN_ON(!xa_empty(&devlink->ports));
+
+	xa_destroy(&devlink->snapshot_ids);
+	xa_destroy(&devlink->ports);
+
+	WARN_ON_ONCE(unregister_netdevice_notifier_net(devlink_net(devlink),
+						       &devlink->netdevice_nb));
+
+	xa_erase(&devlinks, devlink->index);
+
+	kfree(devlink);
+}
+EXPORT_SYMBOL_GPL(devlink_free);
+
+static void __net_exit devlink_pernet_pre_exit(struct net *net)
+{
+	struct devlink *devlink;
+	u32 actions_performed;
+	unsigned long index;
+	int err;
+
+	/* In case network namespace is getting destroyed, reload
+	 * all devlink instances from this namespace into init_net.
+	 */
+	devlinks_xa_for_each_registered_get(net, index, devlink) {
+		WARN_ON(!(devlink->features & DEVLINK_F_RELOAD));
+		mutex_lock(&devlink->lock);
+		err = devlink_reload(devlink, &init_net,
+				     DEVLINK_RELOAD_ACTION_DRIVER_REINIT,
+				     DEVLINK_RELOAD_LIMIT_UNSPEC,
+				     &actions_performed, NULL);
+		mutex_unlock(&devlink->lock);
+		if (err && err != -EOPNOTSUPP)
+			pr_warn("Failed to reload devlink instance into init_net\n");
+		devlink_put(devlink);
+	}
+}
+
+static struct pernet_operations devlink_pernet_ops __net_initdata = {
+	.pre_exit = devlink_pernet_pre_exit,
+};
+
+static int __init devlink_init(void)
+{
+	int err;
+
+	err = genl_register_family(&devlink_nl_family);
+	if (err)
+		goto out;
+	err = register_pernet_subsys(&devlink_pernet_ops);
+
+out:
+	WARN_ON(err);
+	return err;
+}
+
+subsys_initcall(devlink_init);

net/devlink/devl_internal.h

+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/* Copyright (c) 2016 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com>
+ */
+
+#include <linux/mutex.h>
+#include <linux/netdevice.h>
+#include <linux/notifier.h>
+#include <linux/types.h>
+#include <linux/xarray.h>
+#include <net/devlink.h>
+#include <net/net_namespace.h>
+
+#define DEVLINK_REGISTERED XA_MARK_1
+#define DEVLINK_UNREGISTERING XA_MARK_2
+
+#define DEVLINK_RELOAD_STATS_ARRAY_SIZE \
+	(__DEVLINK_RELOAD_LIMIT_MAX * __DEVLINK_RELOAD_ACTION_MAX)
+
+struct devlink_dev_stats {
+	u32 reload_stats[DEVLINK_RELOAD_STATS_ARRAY_SIZE];
+	u32 remote_reload_stats[DEVLINK_RELOAD_STATS_ARRAY_SIZE];
+};
+
+struct devlink {
+	u32 index;
+	struct xarray ports;
+	struct list_head rate_list;
+	struct list_head sb_list;
+	struct list_head dpipe_table_list;
+	struct list_head resource_list;
+	struct list_head param_list;
+	struct list_head region_list;
+	struct list_head reporter_list;
+	struct mutex reporters_lock; /* protects reporter_list */
+	struct devlink_dpipe_headers *dpipe_headers;
+	struct list_head trap_list;
+	struct list_head trap_group_list;
+	struct list_head trap_policer_list;
+	struct list_head linecard_list;
+	struct mutex linecards_lock; /* protects linecard_list */
+	const struct devlink_ops *ops;
+	u64 features;
+	struct xarray snapshot_ids;
+	struct devlink_dev_stats stats;
+	struct device *dev;
+	possible_net_t _net;
+	/* Serializes access to devlink instance specific objects such as
+	 * port, sb, dpipe, resource, params, region, traps and more.
+	 */
+	struct mutex lock;
+	struct lock_class_key lock_key;
+	u8 reload_failed:1;
+	refcount_t refcount;
+	struct completion comp;
+	struct rcu_head rcu;
+	struct notifier_block netdevice_nb;
+	char priv[] __aligned(NETDEV_ALIGN);
+};
+
+extern struct xarray devlinks;
+extern struct genl_family devlink_nl_family;
+
+/* devlink instances are open to the access from the user space after
+ * devlink_register() call. Such logical barrier allows us to have certain
+ * expectations related to locking.
+ *
+ * Before *_register() - we are in initialization stage and no parallel
+ * access possible to the devlink instance. All drivers perform that phase
+ * by implicitly holding device_lock.
+ *
+ * After *_register() - users and driver can access devlink instance at
+ * the same time.
+ */
+#define ASSERT_DEVLINK_REGISTERED(d)                                           \
+	WARN_ON_ONCE(!xa_get_mark(&devlinks, (d)->index, DEVLINK_REGISTERED))
+#define ASSERT_DEVLINK_NOT_REGISTERED(d)                                       \
+	WARN_ON_ONCE(xa_get_mark(&devlinks, (d)->index, DEVLINK_REGISTERED))
+
+/* Iterate over devlink pointers which were possible to get reference to.
+ * devlink_put() needs to be called for each iterated devlink pointer
+ * in loop body in order to release the reference.
+ */
+#define devlinks_xa_for_each_registered_get(net, index, devlink)	\
+	for (index = 0,							\
+	     devlink = devlinks_xa_find_get_first(net, &index);	\
+	     devlink; devlink = devlinks_xa_find_get_next(net, &index))
+
+struct devlink *
+devlinks_xa_find_get(struct net *net, unsigned long *indexp,
+		     void * (*xa_find_fn)(struct xarray *, unsigned long *,
+					  unsigned long, xa_mark_t));
+struct devlink *
+devlinks_xa_find_get_first(struct net *net, unsigned long *indexp);
+struct devlink *
+devlinks_xa_find_get_next(struct net *net, unsigned long *indexp);
+
+/* Netlink */
+#define DEVLINK_NL_FLAG_NEED_PORT		BIT(0)
+#define DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT	BIT(1)
+#define DEVLINK_NL_FLAG_NEED_RATE		BIT(2)
+#define DEVLINK_NL_FLAG_NEED_RATE_NODE		BIT(3)
+#define DEVLINK_NL_FLAG_NEED_LINECARD		BIT(4)
+
+enum devlink_multicast_groups {
+	DEVLINK_MCGRP_CONFIG,
+};
+
+/* state held across netlink dumps */
+struct devlink_nl_dump_state {
+	unsigned long instance;
+	int idx;
+	union {
+		/* DEVLINK_CMD_REGION_READ */
+		struct {
+			u64 start_offset;
+		};
+		/* DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET */
+		struct {
+			u64 dump_ts;
+		};
+	};
+};
+
+struct devlink_gen_cmd {
+	int (*dump_one)(struct sk_buff *msg, struct devlink *devlink,
+			struct netlink_callback *cb);
+};
+
+/* Iterate over registered devlink instances for devlink dump.
+ * devlink_put() needs to be called for each iterated devlink pointer
+ * in loop body in order to release the reference.
+ * Note: this is NOT a generic iterator, it makes assumptions about the use
+ *	 of @state and can only be used once per dumpit implementation.
+ */
+#define devlink_dump_for_each_instance_get(msg, state, devlink)		\
+	for (; (devlink = devlinks_xa_find_get(sock_net(msg->sk),	\
+					       &state->instance, xa_find)); \
+	     state->instance++, state->idx = 0)
+
+extern const struct genl_small_ops devlink_nl_ops[56];
+
+struct devlink *devlink_get_from_attrs(struct net *net, struct nlattr **attrs);
+
+void devlink_notify_unregister(struct devlink *devlink);
+void devlink_notify_register(struct devlink *devlink);
+
+int devlink_nl_instance_iter_dump(struct sk_buff *msg,
+				  struct netlink_callback *cb);
+
+static inline struct devlink_nl_dump_state *
+devlink_dump_state(struct netlink_callback *cb)
+{
+	NL_ASSET_DUMP_CTX_FITS(struct devlink_nl_dump_state);
+
+	return (struct devlink_nl_dump_state *)cb->ctx;
+}
+
+/* gen cmds */
+extern const struct devlink_gen_cmd devl_gen_inst;
+extern const struct devlink_gen_cmd devl_gen_port;
+extern const struct devlink_gen_cmd devl_gen_sb;
+extern const struct devlink_gen_cmd devl_gen_sb_pool;
+extern const struct devlink_gen_cmd devl_gen_sb_port_pool;
+extern const struct devlink_gen_cmd devl_gen_sb_tc_pool_bind;
+extern const struct devlink_gen_cmd devl_gen_selftests;
+extern const struct devlink_gen_cmd devl_gen_param;
+extern const struct devlink_gen_cmd devl_gen_region;
+extern const struct devlink_gen_cmd devl_gen_info;
+extern const struct devlink_gen_cmd devl_gen_trap;
+extern const struct devlink_gen_cmd devl_gen_trap_group;
+extern const struct devlink_gen_cmd devl_gen_trap_policer;
+
+/* Ports */
+int devlink_port_netdevice_event(struct notifier_block *nb,
+				 unsigned long event, void *ptr);
+
+struct devlink_port *
+devlink_port_get_from_info(struct devlink *devlink, struct genl_info *info);
+
+/* Reload */
+bool devlink_reload_actions_valid(const struct devlink_ops *ops);
+int devlink_reload(struct devlink *devlink, struct net *dest_net,
+		   enum devlink_reload_action action,
+		   enum devlink_reload_limit limit,
+		   u32 *actions_performed, struct netlink_ext_ack *extack);
+
+static inline bool devlink_reload_supported(const struct devlink_ops *ops)
+{
+	return ops->reload_down && ops->reload_up;
+}
+
+/* Line cards */
+struct devlink_linecard;
+
+struct devlink_linecard *
+devlink_linecard_get_from_info(struct devlink *devlink, struct genl_info *info);
+void devlink_linecard_put(struct devlink_linecard *linecard);
+
+/* Rates */
+extern const struct devlink_gen_cmd devl_gen_rate_get;
+
+struct devlink_rate *
+devlink_rate_get_from_info(struct devlink *devlink, struct genl_info *info);
+struct devlink_rate *
+devlink_rate_node_get_from_info(struct devlink *devlink,
+				struct genl_info *info);

net/devlink/netlink.c

+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2016 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com>
+ */
+
+#include <net/genetlink.h>
+#include <net/sock.h>
+
+#include "devl_internal.h"
+
+static const struct genl_multicast_group devlink_nl_mcgrps[] = {
+	[DEVLINK_MCGRP_CONFIG] = { .name = DEVLINK_GENL_MCGRP_CONFIG_NAME },
+};
+
+static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
+	[DEVLINK_ATTR_UNSPEC] = { .strict_start_type =
+		DEVLINK_ATTR_TRAP_POLICER_ID },
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING },
+	[DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32 },
+	[DEVLINK_ATTR_PORT_TYPE] = NLA_POLICY_RANGE(NLA_U16, DEVLINK_PORT_TYPE_AUTO,
+						    DEVLINK_PORT_TYPE_IB),
+	[DEVLINK_ATTR_PORT_SPLIT_COUNT] = { .type = NLA_U32 },
+	[DEVLINK_ATTR_SB_INDEX] = { .type = NLA_U32 },
+	[DEVLINK_ATTR_SB_POOL_INDEX] = { .type = NLA_U16 },
+	[DEVLINK_ATTR_SB_POOL_TYPE] = { .type = NLA_U8 },
+	[DEVLINK_ATTR_SB_POOL_SIZE] = { .type = NLA_U32 },
+	[DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE] = { .type = NLA_U8 },
+	[DEVLINK_ATTR_SB_THRESHOLD] = { .type = NLA_U32 },
+	[DEVLINK_ATTR_SB_TC_INDEX] = { .type = NLA_U16 },
+	[DEVLINK_ATTR_ESWITCH_MODE] = NLA_POLICY_RANGE(NLA_U16, DEVLINK_ESWITCH_MODE_LEGACY,
+						       DEVLINK_ESWITCH_MODE_SWITCHDEV),
+	[DEVLINK_ATTR_ESWITCH_INLINE_MODE] = { .type = NLA_U8 },
+	[DEVLINK_ATTR_ESWITCH_ENCAP_MODE] = { .type = NLA_U8 },
+	[DEVLINK_ATTR_DPIPE_TABLE_NAME] = { .type = NLA_NUL_STRING },
+	[DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED] = { .type = NLA_U8 },
+	[DEVLINK_ATTR_RESOURCE_ID] = { .type = NLA_U64},
+	[DEVLINK_ATTR_RESOURCE_SIZE] = { .type = NLA_U64},
+	[DEVLINK_ATTR_PARAM_NAME] = { .type = NLA_NUL_STRING },
+	[DEVLINK_ATTR_PARAM_TYPE] = { .type = NLA_U8 },
+	[DEVLINK_ATTR_PARAM_VALUE_CMODE] = { .type = NLA_U8 },
+	[DEVLINK_ATTR_REGION_NAME] = { .type = NLA_NUL_STRING },
+	[DEVLINK_ATTR_REGION_SNAPSHOT_ID] = { .type = NLA_U32 },
+	[DEVLINK_ATTR_REGION_CHUNK_ADDR] = { .type = NLA_U64 },
+	[DEVLINK_ATTR_REGION_CHUNK_LEN] = { .type = NLA_U64 },
+	[DEVLINK_ATTR_HEALTH_REPORTER_NAME] = { .type = NLA_NUL_STRING },
+	[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD] = { .type = NLA_U64 },
+	[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER] = { .type = NLA_U8 },
+	[DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME] = { .type = NLA_NUL_STRING },
+	[DEVLINK_ATTR_FLASH_UPDATE_COMPONENT] = { .type = NLA_NUL_STRING },
+	[DEVLINK_ATTR_FLASH_UPDATE_OVERWRITE_MASK] =
+		NLA_POLICY_BITFIELD32(DEVLINK_SUPPORTED_FLASH_OVERWRITE_SECTIONS),
+	[DEVLINK_ATTR_TRAP_NAME] = { .type = NLA_NUL_STRING },
+	[DEVLINK_ATTR_TRAP_ACTION] = { .type = NLA_U8 },
+	[DEVLINK_ATTR_TRAP_GROUP_NAME] = { .type = NLA_NUL_STRING },
+	[DEVLINK_ATTR_NETNS_PID] = { .type = NLA_U32 },
+	[DEVLINK_ATTR_NETNS_FD] = { .type = NLA_U32 },
+	[DEVLINK_ATTR_NETNS_ID] = { .type = NLA_U32 },
+	[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_DUMP] = { .type = NLA_U8 },
+	[DEVLINK_ATTR_TRAP_POLICER_ID] = { .type = NLA_U32 },
+	[DEVLINK_ATTR_TRAP_POLICER_RATE] = { .type = NLA_U64 },
+	[DEVLINK_ATTR_TRAP_POLICER_BURST] = { .type = NLA_U64 },
+	[DEVLINK_ATTR_PORT_FUNCTION] = { .type = NLA_NESTED },
+	[DEVLINK_ATTR_RELOAD_ACTION] = NLA_POLICY_RANGE(NLA_U8, DEVLINK_RELOAD_ACTION_DRIVER_REINIT,
+							DEVLINK_RELOAD_ACTION_MAX),
+	[DEVLINK_ATTR_RELOAD_LIMITS] = NLA_POLICY_BITFIELD32(DEVLINK_RELOAD_LIMITS_VALID_MASK),
+	[DEVLINK_ATTR_PORT_FLAVOUR] = { .type = NLA_U16 },
+	[DEVLINK_ATTR_PORT_PCI_PF_NUMBER] = { .type = NLA_U16 },
+	[DEVLINK_ATTR_PORT_PCI_SF_NUMBER] = { .type = NLA_U32 },
+	[DEVLINK_ATTR_PORT_CONTROLLER_NUMBER] = { .type = NLA_U32 },
+	[DEVLINK_ATTR_RATE_TYPE] = { .type = NLA_U16 },
+	[DEVLINK_ATTR_RATE_TX_SHARE] = { .type = NLA_U64 },
+	[DEVLINK_ATTR_RATE_TX_MAX] = { .type = NLA_U64 },
+	[DEVLINK_ATTR_RATE_NODE_NAME] = { .type = NLA_NUL_STRING },
+	[DEVLINK_ATTR_RATE_PARENT_NODE_NAME] = { .type = NLA_NUL_STRING },
+	[DEVLINK_ATTR_LINECARD_INDEX] = { .type = NLA_U32 },
+	[DEVLINK_ATTR_LINECARD_TYPE] = { .type = NLA_NUL_STRING },
+	[DEVLINK_ATTR_SELFTESTS] = { .type = NLA_NESTED },
+	[DEVLINK_ATTR_RATE_TX_PRIORITY] = { .type = NLA_U32 },
+	[DEVLINK_ATTR_RATE_TX_WEIGHT] = { .type = NLA_U32 },
+	[DEVLINK_ATTR_REGION_DIRECT] = { .type = NLA_FLAG },
+};
+
+struct devlink *devlink_get_from_attrs(struct net *net, struct nlattr **attrs)
+{
+	struct devlink *devlink;
+	unsigned long index;
+	char *busname;
+	char *devname;
+
+	if (!attrs[DEVLINK_ATTR_BUS_NAME] || !attrs[DEVLINK_ATTR_DEV_NAME])
+		return ERR_PTR(-EINVAL);
+
+	busname = nla_data(attrs[DEVLINK_ATTR_BUS_NAME]);
+	devname = nla_data(attrs[DEVLINK_ATTR_DEV_NAME]);
+
+	devlinks_xa_for_each_registered_get(net, index, devlink) {
+		if (strcmp(devlink->dev->bus->name, busname) == 0 &&
+		    strcmp(dev_name(devlink->dev), devname) == 0)
+			return devlink;
+		devlink_put(devlink);
+	}
+
+	return ERR_PTR(-ENODEV);
+}
+
+static int devlink_nl_pre_doit(const struct genl_split_ops *ops,
+			       struct sk_buff *skb, struct genl_info *info)
+{
+	struct devlink_linecard *linecard;
+	struct devlink_port *devlink_port;
+	struct devlink *devlink;
+	int err;
+
+	devlink = devlink_get_from_attrs(genl_info_net(info), info->attrs);
+	if (IS_ERR(devlink))
+		return PTR_ERR(devlink);
+	devl_lock(devlink);
+	info->user_ptr[0] = devlink;
+	if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_PORT) {
+		devlink_port = devlink_port_get_from_info(devlink, info);
+		if (IS_ERR(devlink_port)) {
+			err = PTR_ERR(devlink_port);
+			goto unlock;
+		}
+		info->user_ptr[1] = devlink_port;
+	} else if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT) {
+		devlink_port = devlink_port_get_from_info(devlink, info);
+		if (!IS_ERR(devlink_port))
+			info->user_ptr[1] = devlink_port;
+	} else if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_RATE) {
+		struct devlink_rate *devlink_rate;
+
+		devlink_rate = devlink_rate_get_from_info(devlink, info);
+		if (IS_ERR(devlink_rate)) {
+			err = PTR_ERR(devlink_rate);
+			goto unlock;
+		}
+		info->user_ptr[1] = devlink_rate;
+	} else if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_RATE_NODE) {
+		struct devlink_rate *rate_node;
+
+		rate_node = devlink_rate_node_get_from_info(devlink, info);
+		if (IS_ERR(rate_node)) {
+			err = PTR_ERR(rate_node);
+			goto unlock;
+		}
+		info->user_ptr[1] = rate_node;
+	} else if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_LINECARD) {
+		linecard = devlink_linecard_get_from_info(devlink, info);
+		if (IS_ERR(linecard)) {
+			err = PTR_ERR(linecard);
+			goto unlock;
+		}
+		info->user_ptr[1] = linecard;
+	}
+	return 0;
+
+unlock:
+	devl_unlock(devlink);
+	devlink_put(devlink);
+	return err;
+}
+
+static void devlink_nl_post_doit(const struct genl_split_ops *ops,
+				 struct sk_buff *skb, struct genl_info *info)
+{
+	struct devlink_linecard *linecard;
+	struct devlink *devlink;
+
+	devlink = info->user_ptr[0];
+	if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_LINECARD) {
+		linecard = info->user_ptr[1];
+		devlink_linecard_put(linecard);
+	}
+	devl_unlock(devlink);
+	devlink_put(devlink);
+}
+
+static const struct devlink_gen_cmd *devl_gen_cmds[] = {
+	[DEVLINK_CMD_GET]		= &devl_gen_inst,
+	[DEVLINK_CMD_PORT_GET]		= &devl_gen_port,
+	[DEVLINK_CMD_SB_GET]		= &devl_gen_sb,
+	[DEVLINK_CMD_SB_POOL_GET]	= &devl_gen_sb_pool,
+	[DEVLINK_CMD_SB_PORT_POOL_GET]	= &devl_gen_sb_port_pool,
+	[DEVLINK_CMD_SB_TC_POOL_BIND_GET] = &devl_gen_sb_tc_pool_bind,
+	[DEVLINK_CMD_PARAM_GET]		= &devl_gen_param,
+	[DEVLINK_CMD_REGION_GET]	= &devl_gen_region,
+	[DEVLINK_CMD_INFO_GET]		= &devl_gen_info,
+	[DEVLINK_CMD_RATE_GET]		= &devl_gen_rate_get,
+	[DEVLINK_CMD_TRAP_GET]		= &devl_gen_trap,
+	[DEVLINK_CMD_TRAP_GROUP_GET]	= &devl_gen_trap_group,
+	[DEVLINK_CMD_TRAP_POLICER_GET]	= &devl_gen_trap_policer,
+	[DEVLINK_CMD_SELFTESTS_GET]	= &devl_gen_selftests,
+};
+
+int devlink_nl_instance_iter_dump(struct sk_buff *msg,
+				  struct netlink_callback *cb)
+{
+	const struct genl_dumpit_info *info = genl_dumpit_info(cb);
+	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
+	const struct devlink_gen_cmd *cmd;
+	struct devlink *devlink;
+	int err = 0;
+
+	cmd = devl_gen_cmds[info->op.cmd];
+
+	devlink_dump_for_each_instance_get(msg, state, devlink) {
+		devl_lock(devlink);
+		err = cmd->dump_one(msg, devlink, cb);
+		devl_unlock(devlink);
+		devlink_put(devlink);
+
+		if (err)
+			break;
+
+		/* restart sub-object walk for the next instance */
+		state->idx = 0;
+	}
+
+	if (err != -EMSGSIZE)
+		return err;
+	return msg->len;
+}
+
+struct genl_family devlink_nl_family __ro_after_init = {
+	.name		= DEVLINK_GENL_NAME,
+	.version	= DEVLINK_GENL_VERSION,
+	.maxattr	= DEVLINK_ATTR_MAX,
+	.policy		= devlink_nl_policy,
+	.netnsok	= true,
+	.parallel_ops	= true,
+	.pre_doit	= devlink_nl_pre_doit,
+	.post_doit	= devlink_nl_post_doit,
+	.module		= THIS_MODULE,
+	.small_ops	= devlink_nl_ops,
+	.n_small_ops	= ARRAY_SIZE(devlink_nl_ops),
+	.resv_start_op	= DEVLINK_CMD_SELFTESTS_RUN + 1,
+	.mcgrps		= devlink_nl_mcgrps,
+	.n_mcgrps	= ARRAY_SIZE(devlink_nl_mcgrps),
+};

net/netfilter/nf_conntrack_netlink.c

@@ -3866,7 +3866,7 @@ static int __init ctnetlink_init(void)
 {
 	int ret;
 
-	BUILD_BUG_ON(sizeof(struct ctnetlink_list_dump_ctx) > sizeof_field(struct netlink_callback, ctx));
+	NL_ASSET_DUMP_CTX_FITS(struct ctnetlink_list_dump_ctx);
 
 	ret = nfnetlink_subsys_register(&ctnl_subsys);
 	if (ret < 0) {