Merge branch 'devlink-introduce-notifications-filtering'

Jiri Pirko says:

====================
devlink: introduce notifications filtering

From: Jiri Pirko <jiri@nvidia.com>

Currently the user listening on a socket for devlink notifications
gets always all messages for all existing devlink instances and objects,
even if he is interested only in one of those. That may cause
unnecessary overhead on setups with thousands of instances present.

User is currently able to narrow down the devlink objects replies
to dump commands by specifying select attributes.

Allow similar approach for notifications providing user a new
notify-filter-set command to select attributes with values
the notification message has to match. In that case, it is delivered
to the socket.

Note that the filtering is done per-socket, so multiple users may
specify different selection of attributes with values.

This patchset initially introduces support for following attributes:
DEVLINK_ATTR_BUS_NAME
DEVLINK_ATTR_DEV_NAME
DEVLINK_ATTR_PORT_INDEX

Patches #1 - #4 are preparations in devlink code, patch #3 is
                an optimization done on the way.
Patches #5 - #7 are preparations in netlink and generic netlink code.
Patch #8 is the main one in this set implementing of
         the notify-filter-set command and the actual
         per-socket filtering.
Patch #9 extends the infrastructure allowing to filter according
         to a port index.

Example:
$ devlink mon port pci/0000:08:00.0/32768
[port,new] pci/0000:08:00.0/32768: type notset flavour pcisf controller 0 pfnum 0 sfnum 107 splittable false
  function:
    hw_addr 00:00:00:00:00:00 state inactive opstate detached roce enable
[port,new] pci/0000:08:00.0/32768: type eth flavour pcisf controller 0 pfnum 0 sfnum 107 splittable false
  function:
    hw_addr 00:00:00:00:00:00 state inactive opstate detached roce enable
[port,new] pci/0000:08:00.0/32768: type eth netdev eth3 flavour pcisf controller 0 pfnum 0 sfnum 107 splittable false
  function:
    hw_addr 00:00:00:00:00:00 state inactive opstate detached roce enable
[port,new] pci/0000:08:00.0/32768: type eth netdev eth3 flavour pcisf controller 0 pfnum 0 sfnum 107 splittable false
  function:
    hw_addr 00:00:00:00:00:00 state inactive opstate detached roce enable
[port,new] pci/0000:08:00.0/32768: type eth flavour pcisf controller 0 pfnum 0 sfnum 107 splittable false
  function:
    hw_addr 00:00:00:00:00:00 state inactive opstate detached roce enable
[port,new] pci/0000:08:00.0/32768: type notset flavour pcisf controller 0 pfnum 0 sfnum 107 splittable false
  function:
    hw_addr 00:00:00:00:00:00 state inactive opstate detached roce enable
[port,del] pci/0000:08:00.0/32768: type notset flavour pcisf controller 0 pfnum 0 sfnum 107 splittable false
  function:
    hw_addr 00:00:00:00:00:00 state inactive opstate detached roce enable
====================

Link: https://lore.kernel.org/r/20231216123001.1293639-1-jiri@resnulli.usSigned-off-by: Paolo Abeni <pabeni@redhat.com>

Documentation/netlink/specs/devlink.yaml

@@ -2254,3 +2254,14 @@ operations:
             - bus-name
             - dev-name
             - selftests
+
+    -
+      name: notify-filter-set
+      doc: Set notification messages socket filter.
+      attribute-set: devlink
+      do:
+        request:
+          attributes:
+            - bus-name
+            - dev-name
+            - port-index

drivers/connector/connector.c

@@ -59,9 +59,8 @@ static int cn_already_initialized;
  * both, or if both are zero then the group is looked up and sent there.
  */
 int cn_netlink_send_mult(struct cn_msg *msg, u16 len, u32 portid, u32 __group,
-	gfp_t gfp_mask,
-	int (*filter)(struct sock *dsk, struct sk_buff *skb, void *data),
-	void *filter_data)
+			 gfp_t gfp_mask, netlink_filter_fn filter,
+			 void *filter_data)
 {
 	struct cn_callback_entry *__cbq;
 	unsigned int size;

include/linux/connector.h

@@ -100,8 +100,7 @@ void cn_del_callback(const struct cb_id *id);
  */
 int cn_netlink_send_mult(struct cn_msg *msg, u16 len, u32 portid,
 			 u32 group, gfp_t gfp_mask,
-			 int (*filter)(struct sock *dsk, struct sk_buff *skb,
-				       void *data),
+			 netlink_filter_fn filter,
 			 void *filter_data);
 
 /**

include/linux/netlink.h

@@ -228,10 +228,12 @@ bool netlink_strict_get_check(struct sk_buff *skb);
 int netlink_unicast(struct sock *ssk, struct sk_buff *skb, __u32 portid, int nonblock);
 int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, __u32 portid,
 		      __u32 group, gfp_t allocation);
+
+typedef int (*netlink_filter_fn)(struct sock *dsk, struct sk_buff *skb, void *data);
+
 int netlink_broadcast_filtered(struct sock *ssk, struct sk_buff *skb,
 			       __u32 portid, __u32 group, gfp_t allocation,
-			       int (*filter)(struct sock *dsk,
-					     struct sk_buff *skb, void *data),
+			       netlink_filter_fn filter,
 			       void *filter_data);
 int netlink_set_err(struct sock *ssk, __u32 portid, __u32 group, int code);
 int netlink_register_notifier(struct notifier_block *nb);

include/net/genetlink.h

@@ -51,6 +51,9 @@ struct genl_info;
  * @split_ops: the split do/dump form of operation definition
  * @n_split_ops: number of entries in @split_ops, not that with split do/dump
  *	ops the number of entries is not the same as number of commands
+ * @sock_priv_size: the size of per-socket private memory
+ * @sock_priv_init: the per-socket private memory initializer
+ * @sock_priv_destroy: the per-socket private memory destructor
  *
  * Attribute policies (the combination of @policy and @maxattr fields)
  * can be attached at the family level or at the operation level.
@@ -84,11 +87,17 @@ struct genl_family {
 	const struct genl_multicast_group *mcgrps;
 	struct module		*module;
 
+	size_t			sock_priv_size;
+	void			(*sock_priv_init)(void *priv);
+	void			(*sock_priv_destroy)(void *priv);
+
 /* private: internal use only */
 	/* protocol family identifier */
 	int			id;
 	/* starting number of multicast group IDs in this family */
 	unsigned int		mcgrp_offset;
+	/* list of per-socket privs */
+	struct xarray		*sock_privs;
 };
 
 /**
@@ -298,6 +307,8 @@ static inline bool genl_info_is_ntf(const struct genl_info *info)
 	return !info->nlhdr;
 }
 
+void *__genl_sk_priv_get(struct genl_family *family, struct sock *sk);
+void *genl_sk_priv_get(struct genl_family *family, struct sock *sk);
 int genl_register_family(struct genl_family *family);
 int genl_unregister_family(const struct genl_family *family);
 void genl_notify(const struct genl_family *family, struct sk_buff *skb,
@@ -437,6 +448,35 @@ static inline void genlmsg_cancel(struct sk_buff *skb, void *hdr)
 		nlmsg_cancel(skb, hdr - GENL_HDRLEN - NLMSG_HDRLEN);
 }
 
+/**
+ * genlmsg_multicast_netns_filtered - multicast a netlink message
+ *				      to a specific netns with filter
+ *				      function
+ * @family: the generic netlink family
+ * @net: the net namespace
+ * @skb: netlink message as socket buffer
+ * @portid: own netlink portid to avoid sending to yourself
+ * @group: offset of multicast group in groups array
+ * @flags: allocation flags
+ * @filter: filter function
+ * @filter_data: filter function private data
+ *
+ * Return: 0 on success, negative error code for failure.
+ */
+static inline int
+genlmsg_multicast_netns_filtered(const struct genl_family *family,
+				 struct net *net, struct sk_buff *skb,
+				 u32 portid, unsigned int group, gfp_t flags,
+				 netlink_filter_fn filter,
+				 void *filter_data)
+{
+	if (WARN_ON_ONCE(group >= family->n_mcgrps))
+		return -EINVAL;
+	group = family->mcgrp_offset + group;
+	return nlmsg_multicast_filtered(net->genl_sock, skb, portid, group,
+					flags, filter, filter_data);
+}
+
 /**
  * genlmsg_multicast_netns - multicast a netlink message to a specific netns
  * @family: the generic netlink family
@@ -450,10 +490,8 @@ static inline int genlmsg_multicast_netns(const struct genl_family *family,
 					  struct net *net, struct sk_buff *skb,
 					  u32 portid, unsigned int group, gfp_t flags)
 {
-	if (WARN_ON_ONCE(group >= family->n_mcgrps))
-		return -EINVAL;
-	group = family->mcgrp_offset + group;
-	return nlmsg_multicast(net->genl_sock, skb, portid, group, flags);
+	return genlmsg_multicast_netns_filtered(family, net, skb, portid,
+						group, flags, NULL, NULL);
 }
 
 /**

include/net/netlink.h

@@ -1087,27 +1087,50 @@ static inline void nlmsg_free(struct sk_buff *skb)
 }
 
 /**
- * nlmsg_multicast - multicast a netlink message
+ * nlmsg_multicast_filtered - multicast a netlink message with filter function
  * @sk: netlink socket to spread messages to
  * @skb: netlink message as socket buffer
  * @portid: own netlink portid to avoid sending to yourself
  * @group: multicast group id
  * @flags: allocation flags
+ * @filter: filter function
+ * @filter_data: filter function private data
+ *
+ * Return: 0 on success, negative error code for failure.
  */
-static inline int nlmsg_multicast(struct sock *sk, struct sk_buff *skb,
-				  u32 portid, unsigned int group, gfp_t flags)
+static inline int nlmsg_multicast_filtered(struct sock *sk, struct sk_buff *skb,
+					   u32 portid, unsigned int group,
+					   gfp_t flags,
+					   netlink_filter_fn filter,
+					   void *filter_data)
 {
 	int err;
 
 	NETLINK_CB(skb).dst_group = group;
 
-	err = netlink_broadcast(sk, skb, portid, group, flags);
+	err = netlink_broadcast_filtered(sk, skb, portid, group, flags,
+					 filter, filter_data);
 	if (err > 0)
 		err = 0;
 
 	return err;
 }
 
+/**
+ * nlmsg_multicast - multicast a netlink message
+ * @sk: netlink socket to spread messages to
+ * @skb: netlink message as socket buffer
+ * @portid: own netlink portid to avoid sending to yourself
+ * @group: multicast group id
+ * @flags: allocation flags
+ */
+static inline int nlmsg_multicast(struct sock *sk, struct sk_buff *skb,
+				  u32 portid, unsigned int group, gfp_t flags)
+{
+	return nlmsg_multicast_filtered(sk, skb, portid, group, flags,
+					NULL, NULL);
+}
+
 /**
  * nlmsg_unicast - unicast a netlink message
  * @sk: netlink socket to spread message to

include/uapi/linux/devlink.h

@@ -139,6 +139,8 @@ enum devlink_command {
 	DEVLINK_CMD_SELFTESTS_GET,	/* can dump */
 	DEVLINK_CMD_SELFTESTS_RUN,
 
+	DEVLINK_CMD_NOTIFY_FILTER_SET,
+
 	/* add new commands above here */
 	__DEVLINK_CMD_MAX,
 	DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1

net/devlink/dev.c

@@ -202,7 +202,10 @@ static void devlink_notify(struct devlink *devlink, enum devlink_command cmd)
 	int err;
 
 	WARN_ON(cmd != DEVLINK_CMD_NEW && cmd != DEVLINK_CMD_DEL);
-	WARN_ON(!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED));
+	WARN_ON(!devl_is_registered(devlink));
+
+	if (!devlink_nl_notify_need(devlink))
+		return;
 
 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
 	if (!msg)
@@ -214,8 +217,7 @@ static void devlink_notify(struct devlink *devlink, enum devlink_command cmd)
 		return;
 	}
 
-	genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink),
-				msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
+	devlink_nl_notify_send(devlink, msg);
 }
 
 int devlink_nl_get_doit(struct sk_buff *skb, struct genl_info *info)
@@ -999,7 +1001,7 @@ static void __devlink_flash_update_notify(struct devlink *devlink,
 		cmd != DEVLINK_CMD_FLASH_UPDATE_END &&
 		cmd != DEVLINK_CMD_FLASH_UPDATE_STATUS);
 
-	if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED))
+	if (!devl_is_registered(devlink) || !devlink_nl_notify_need(devlink))
 		return;
 
 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
@@ -1010,8 +1012,7 @@ static void __devlink_flash_update_notify(struct devlink *devlink,
 	if (err)
 		goto out_free_msg;
 
-	genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink),
-				msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
+	devlink_nl_notify_send(devlink, msg);
 	return;
 
 out_free_msg:

net/devlink/devl_internal.h

@@ -91,10 +91,15 @@ extern struct genl_family devlink_nl_family;
 
 struct devlink *devlinks_xa_find_get(struct net *net, unsigned long *indexp);
 
+static inline bool __devl_is_registered(struct devlink *devlink)
+{
+	return xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED);
+}
+
 static inline bool devl_is_registered(struct devlink *devlink)
 {
 	devl_assert_locked(devlink);
-	return xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED);
+	return __devl_is_registered(devlink);
 }
 
 static inline void devl_dev_lock(struct devlink *devlink, bool dev_lock)
@@ -180,6 +185,58 @@ int devlink_nl_put_nested_handle(struct sk_buff *msg, struct net *net,
 				 struct devlink *devlink, int attrtype);
 int devlink_nl_msg_reply_and_new(struct sk_buff **msg, struct genl_info *info);
 
+static inline bool devlink_nl_notify_need(struct devlink *devlink)
+{
+	return genl_has_listeners(&devlink_nl_family, devlink_net(devlink),
+				  DEVLINK_MCGRP_CONFIG);
+}
+
+struct devlink_obj_desc {
+	struct rcu_head rcu;
+	const char *bus_name;
+	const char *dev_name;
+	unsigned int port_index;
+	bool port_index_valid;
+	long data[];
+};
+
+static inline void devlink_nl_obj_desc_init(struct devlink_obj_desc *desc,
+					    struct devlink *devlink)
+{
+	memset(desc, 0, sizeof(*desc));
+	desc->bus_name = devlink->dev->bus->name;
+	desc->dev_name = dev_name(devlink->dev);
+}
+
+static inline void devlink_nl_obj_desc_port_set(struct devlink_obj_desc *desc,
+						struct devlink_port *devlink_port)
+{
+	desc->port_index = devlink_port->index;
+	desc->port_index_valid = true;
+}
+
+int devlink_nl_notify_filter(struct sock *dsk, struct sk_buff *skb, void *data);
+
+static inline void devlink_nl_notify_send_desc(struct devlink *devlink,
+					       struct sk_buff *msg,
+					       struct devlink_obj_desc *desc)
+{
+	genlmsg_multicast_netns_filtered(&devlink_nl_family,
+					 devlink_net(devlink),
+					 msg, 0, DEVLINK_MCGRP_CONFIG,
+					 GFP_KERNEL,
+					 devlink_nl_notify_filter, desc);
+}
+
+static inline void devlink_nl_notify_send(struct devlink *devlink,
+					  struct sk_buff *msg)
+{
+	struct devlink_obj_desc desc;
+
+	devlink_nl_obj_desc_init(&desc, devlink);
+	devlink_nl_notify_send_desc(devlink, msg, &desc);
+}
+
 /* Notify */
 void devlink_notify_register(struct devlink *devlink);
 void devlink_notify_unregister(struct devlink *devlink);

net/devlink/health.c

@@ -490,12 +490,16 @@ static void devlink_recover_notify(struct devlink_health_reporter *reporter,
 				   enum devlink_command cmd)
 {
 	struct devlink *devlink = reporter->devlink;
+	struct devlink_obj_desc desc;
 	struct sk_buff *msg;
 	int err;
 
 	WARN_ON(cmd != DEVLINK_CMD_HEALTH_REPORTER_RECOVER);
 	ASSERT_DEVLINK_REGISTERED(devlink);
 
+	if (!devlink_nl_notify_need(devlink))
+		return;
+
 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
 	if (!msg)
 		return;
@@ -506,8 +510,10 @@ static void devlink_recover_notify(struct devlink_health_reporter *reporter,
 		return;
 	}
 
-	genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), msg,
-				0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
+	devlink_nl_obj_desc_init(&desc, devlink);
+	if (reporter->devlink_port)
+		devlink_nl_obj_desc_port_set(&desc, reporter->devlink_port);
+	devlink_nl_notify_send_desc(devlink, msg, &desc);
 }
 
 void

net/devlink/linecard.c

@@ -136,7 +136,7 @@ static void devlink_linecard_notify(struct devlink_linecard *linecard,
 	WARN_ON(cmd != DEVLINK_CMD_LINECARD_NEW &&
 		cmd != DEVLINK_CMD_LINECARD_DEL);
 
-	if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED))
+	if (!__devl_is_registered(devlink) || !devlink_nl_notify_need(devlink))
 		return;
 
 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
@@ -150,8 +150,7 @@ static void devlink_linecard_notify(struct devlink_linecard *linecard,
 		return;
 	}
 
-	genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink),
-				msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
+	devlink_nl_notify_send(devlink, msg);
 }
 
 void devlink_linecards_notify_register(struct devlink *devlink)

net/devlink/netlink.c

@@ -17,6 +17,119 @@ static const struct genl_multicast_group devlink_nl_mcgrps[] = {
 	[DEVLINK_MCGRP_CONFIG] = { .name = DEVLINK_GENL_MCGRP_CONFIG_NAME },
 };
 
+struct devlink_nl_sock_priv {
+	struct devlink_obj_desc __rcu *flt;
+	spinlock_t flt_lock; /* Protects flt. */
+};
+
+static void devlink_nl_sock_priv_init(void *priv)
+{
+	struct devlink_nl_sock_priv *sk_priv = priv;
+
+	spin_lock_init(&sk_priv->flt_lock);
+}
+
+static void devlink_nl_sock_priv_destroy(void *priv)
+{
+	struct devlink_nl_sock_priv *sk_priv = priv;
+	struct devlink_obj_desc *flt;
+
+	flt = rcu_dereference_protected(sk_priv->flt, true);
+	kfree_rcu(flt, rcu);
+}
+
+int devlink_nl_notify_filter_set_doit(struct sk_buff *skb,
+				      struct genl_info *info)
+{
+	struct devlink_nl_sock_priv *sk_priv;
+	struct nlattr **attrs = info->attrs;
+	struct devlink_obj_desc *flt;
+	size_t data_offset = 0;
+	size_t data_size = 0;
+	char *pos;
+
+	if (attrs[DEVLINK_ATTR_BUS_NAME])
+		data_size = size_add(data_size,
+				     nla_len(attrs[DEVLINK_ATTR_BUS_NAME]) + 1);
+	if (attrs[DEVLINK_ATTR_DEV_NAME])
+		data_size = size_add(data_size,
+				     nla_len(attrs[DEVLINK_ATTR_DEV_NAME]) + 1);
+
+	flt = kzalloc(size_add(sizeof(*flt), data_size), GFP_KERNEL);
+	if (!flt)
+		return -ENOMEM;
+
+	pos = (char *) flt->data;
+	if (attrs[DEVLINK_ATTR_BUS_NAME]) {
+		data_offset += nla_strscpy(pos,
+					   attrs[DEVLINK_ATTR_BUS_NAME],
+					   data_size) + 1;
+		flt->bus_name = pos;
+		pos += data_offset;
+	}
+	if (attrs[DEVLINK_ATTR_DEV_NAME]) {
+		nla_strscpy(pos, attrs[DEVLINK_ATTR_DEV_NAME],
+			    data_size - data_offset);
+		flt->dev_name = pos;
+	}
+
+	if (attrs[DEVLINK_ATTR_PORT_INDEX]) {
+		flt->port_index = nla_get_u32(attrs[DEVLINK_ATTR_PORT_INDEX]);
+		flt->port_index_valid = true;
+	}
+
+	/* Don't attach empty filter. */
+	if (!flt->bus_name && !flt->dev_name && !flt->port_index_valid) {
+		kfree(flt);
+		flt = NULL;
+	}
+
+	sk_priv = genl_sk_priv_get(&devlink_nl_family, NETLINK_CB(skb).sk);
+	if (IS_ERR(sk_priv)) {
+		kfree(flt);
+		return PTR_ERR(sk_priv);
+	}
+	spin_lock(&sk_priv->flt_lock);
+	flt = rcu_replace_pointer(sk_priv->flt, flt,
+				  lockdep_is_held(&sk_priv->flt_lock));
+	spin_unlock(&sk_priv->flt_lock);
+	kfree_rcu(flt, rcu);
+	return 0;
+}
+
+static bool devlink_obj_desc_match(const struct devlink_obj_desc *desc,
+				   const struct devlink_obj_desc *flt)
+{
+	if (desc->bus_name && flt->bus_name &&
+	    strcmp(desc->bus_name, flt->bus_name))
+		return false;
+	if (desc->dev_name && flt->dev_name &&
+	    strcmp(desc->dev_name, flt->dev_name))
+		return false;
+	if (desc->port_index_valid && flt->port_index_valid &&
+	    desc->port_index != flt->port_index)
+		return false;
+	return true;
+}
+
+int devlink_nl_notify_filter(struct sock *dsk, struct sk_buff *skb, void *data)
+{
+	struct devlink_obj_desc *desc = data;
+	struct devlink_nl_sock_priv *sk_priv;
+	struct devlink_obj_desc *flt;
+	int ret = 0;
+
+	rcu_read_lock();
+	sk_priv = __genl_sk_priv_get(&devlink_nl_family, dsk);
+	if (!IS_ERR_OR_NULL(sk_priv)) {
+		flt = rcu_dereference(sk_priv->flt);
+		if (flt)
+			ret = !devlink_obj_desc_match(desc, flt);
+	}
+	rcu_read_unlock();
+	return ret;
+}
+
 int devlink_nl_put_nested_handle(struct sk_buff *msg, struct net *net,
 				 struct devlink *devlink, int attrtype)
 {
@@ -256,4 +369,7 @@ struct genl_family devlink_nl_family __ro_after_init = {
 	.resv_start_op	= DEVLINK_CMD_SELFTESTS_RUN + 1,
 	.mcgrps		= devlink_nl_mcgrps,
 	.n_mcgrps	= ARRAY_SIZE(devlink_nl_mcgrps),
+	.sock_priv_size		= sizeof(struct devlink_nl_sock_priv),
+	.sock_priv_init		= devlink_nl_sock_priv_init,
+	.sock_priv_destroy	= devlink_nl_sock_priv_destroy,
 };

net/devlink/netlink_gen.c

@@ -560,8 +560,15 @@ static const struct nla_policy devlink_selftests_run_nl_policy[DEVLINK_ATTR_SELF
 	[DEVLINK_ATTR_SELFTESTS] = NLA_POLICY_NESTED(devlink_dl_selftest_id_nl_policy),
 };
 
+/* DEVLINK_CMD_NOTIFY_FILTER_SET - do */
+static const struct nla_policy devlink_notify_filter_set_nl_policy[DEVLINK_ATTR_PORT_INDEX + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, },
+};
+
 /* Ops table for devlink */
-const struct genl_split_ops devlink_nl_ops[73] = {
+const struct genl_split_ops devlink_nl_ops[74] = {
 	{
 		.cmd		= DEVLINK_CMD_GET,
 		.validate	= GENL_DONT_VALIDATE_STRICT,
@@ -1233,4 +1240,11 @@ const struct genl_split_ops devlink_nl_ops[73] = {
 		.maxattr	= DEVLINK_ATTR_SELFTESTS,
 		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
 	},
+	{
+		.cmd		= DEVLINK_CMD_NOTIFY_FILTER_SET,
+		.doit		= devlink_nl_notify_filter_set_doit,
+		.policy		= devlink_notify_filter_set_nl_policy,
+		.maxattr	= DEVLINK_ATTR_PORT_INDEX,
+		.flags		= GENL_CMD_CAP_DO,
+	},
 };

net/devlink/netlink_gen.h

@@ -16,7 +16,7 @@ extern const struct nla_policy devlink_dl_port_function_nl_policy[DEVLINK_PORT_F
 extern const struct nla_policy devlink_dl_selftest_id_nl_policy[DEVLINK_ATTR_SELFTEST_ID_FLASH + 1];
 
 /* Ops table for devlink */
-extern const struct genl_split_ops devlink_nl_ops[73];
+extern const struct genl_split_ops devlink_nl_ops[74];
 
 int devlink_nl_pre_doit(const struct genl_split_ops *ops, struct sk_buff *skb,
 			struct genl_info *info);
@@ -142,5 +142,7 @@ int devlink_nl_selftests_get_doit(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_selftests_get_dumpit(struct sk_buff *skb,
 				    struct netlink_callback *cb);
 int devlink_nl_selftests_run_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_notify_filter_set_doit(struct sk_buff *skb,
+				      struct genl_info *info);
 
 #endif /* _LINUX_DEVLINK_GEN_H */

net/devlink/param.c

@@ -343,7 +343,7 @@ static void devlink_param_notify(struct devlink *devlink,
 	 * will replay the notifications if the params are added/removed
 	 * outside of the lifetime of the instance.
 	 */
-	if (!devl_is_registered(devlink))
+	if (!devl_is_registered(devlink) || !devlink_nl_notify_need(devlink))
 		return;
 
 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
@@ -356,8 +356,7 @@ static void devlink_param_notify(struct devlink *devlink,
 		return;
 	}
 
-	genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink),
-				msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
+	devlink_nl_notify_send(devlink, msg);
 }
 
 static void devlink_params_notify(struct devlink *devlink,

net/devlink/port.c

@@ -507,12 +507,13 @@ static void devlink_port_notify(struct devlink_port *devlink_port,
 				enum devlink_command cmd)
 {
 	struct devlink *devlink = devlink_port->devlink;
+	struct devlink_obj_desc desc;
 	struct sk_buff *msg;
 	int err;
 
 	WARN_ON(cmd != DEVLINK_CMD_PORT_NEW && cmd != DEVLINK_CMD_PORT_DEL);
 
-	if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED))
+	if (!__devl_is_registered(devlink) || !devlink_nl_notify_need(devlink))
 		return;
 
 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
@@ -525,8 +526,9 @@ static void devlink_port_notify(struct devlink_port *devlink_port,
 		return;
 	}
 
-	genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), msg,
-				0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
+	devlink_nl_obj_desc_init(&desc, devlink);
+	devlink_nl_obj_desc_port_set(&desc, devlink_port);
+	devlink_nl_notify_send_desc(devlink, msg, &desc);
 }
 
 static void devlink_ports_notify(struct devlink *devlink,

net/devlink/rate.c

@@ -146,7 +146,7 @@ static void devlink_rate_notify(struct devlink_rate *devlink_rate,
 
 	WARN_ON(cmd != DEVLINK_CMD_RATE_NEW && cmd != DEVLINK_CMD_RATE_DEL);
 
-	if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED))
+	if (!devl_is_registered(devlink) || !devlink_nl_notify_need(devlink))
 		return;
 
 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
@@ -159,8 +159,7 @@ static void devlink_rate_notify(struct devlink_rate *devlink_rate,
 		return;
 	}
 
-	genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), msg,
-				0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
+	devlink_nl_notify_send(devlink, msg);
 }
 
 void devlink_rates_notify_register(struct devlink *devlink)

net/devlink/region.c

@@ -234,15 +234,15 @@ static void devlink_nl_region_notify(struct devlink_region *region,
 	struct sk_buff *msg;
 
 	WARN_ON(cmd != DEVLINK_CMD_REGION_NEW && cmd != DEVLINK_CMD_REGION_DEL);
-	if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED))
+
+	if (!__devl_is_registered(devlink) || !devlink_nl_notify_need(devlink))
 		return;
 
 	msg = devlink_nl_region_notify_build(region, snapshot, cmd, 0, 0);
 	if (IS_ERR(msg))
 		return;
 
-	genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), msg,
-				0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
+	devlink_nl_notify_send(devlink, msg);
 }
 
 void devlink_regions_notify_register(struct devlink *devlink)

net/devlink/trap.c

@@ -1173,7 +1173,8 @@ devlink_trap_group_notify(struct devlink *devlink,
 
 	WARN_ON_ONCE(cmd != DEVLINK_CMD_TRAP_GROUP_NEW &&
 		     cmd != DEVLINK_CMD_TRAP_GROUP_DEL);
-	if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED))
+
+	if (!devl_is_registered(devlink) || !devlink_nl_notify_need(devlink))
 		return;
 
 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
@@ -1187,8 +1188,7 @@ devlink_trap_group_notify(struct devlink *devlink,
 		return;
 	}
 
-	genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink),
-				msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
+	devlink_nl_notify_send(devlink, msg);
 }
 
 void devlink_trap_groups_notify_register(struct devlink *devlink)
@@ -1234,7 +1234,8 @@ static void devlink_trap_notify(struct devlink *devlink,
 
 	WARN_ON_ONCE(cmd != DEVLINK_CMD_TRAP_NEW &&
 		     cmd != DEVLINK_CMD_TRAP_DEL);
-	if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED))
+
+	if (!devl_is_registered(devlink) || !devlink_nl_notify_need(devlink))
 		return;
 
 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
@@ -1247,8 +1248,7 @@ static void devlink_trap_notify(struct devlink *devlink,
 		return;
 	}
 
-	genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink),
-				msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
+	devlink_nl_notify_send(devlink, msg);
 }
 
 void devlink_traps_notify_register(struct devlink *devlink)
@@ -1710,7 +1710,8 @@ devlink_trap_policer_notify(struct devlink *devlink,
 
 	WARN_ON_ONCE(cmd != DEVLINK_CMD_TRAP_POLICER_NEW &&
 		     cmd != DEVLINK_CMD_TRAP_POLICER_DEL);
-	if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED))
+
+	if (!devl_is_registered(devlink) || !devlink_nl_notify_need(devlink))
 		return;
 
 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
@@ -1724,8 +1725,7 @@ devlink_trap_policer_notify(struct devlink *devlink,
 		return;
 	}
 
-	genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink),
-				msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
+	devlink_nl_notify_send(devlink, msg);
 }
 
 void devlink_trap_policers_notify_register(struct devlink *devlink)

net/netlink/af_netlink.c

@@ -1519,8 +1519,7 @@ static void do_one_broadcast(struct sock *sk,
 int netlink_broadcast_filtered(struct sock *ssk, struct sk_buff *skb,
 			       u32 portid,
 			       u32 group, gfp_t allocation,
-			       int (*filter)(struct sock *dsk,
-					     struct sk_buff *skb, void *data),
+			       netlink_filter_fn filter,
 			       void *filter_data)
 {
 	struct net *net = sock_net(ssk);

net/netlink/genetlink.c

@@ -631,6 +631,138 @@ static int genl_validate_ops(const struct genl_family *family)
 	return 0;
 }
 
+static void *genl_sk_priv_alloc(struct genl_family *family)
+{
+	void *priv;
+
+	priv = kzalloc(family->sock_priv_size, GFP_KERNEL);
+	if (!priv)
+		return ERR_PTR(-ENOMEM);
+
+	if (family->sock_priv_init)
+		family->sock_priv_init(priv);
+
+	return priv;
+}
+
+static void genl_sk_priv_free(const struct genl_family *family, void *priv)
+{
+	if (family->sock_priv_destroy)
+		family->sock_priv_destroy(priv);
+	kfree(priv);
+}
+
+static int genl_sk_privs_alloc(struct genl_family *family)
+{
+	if (!family->sock_priv_size)
+		return 0;
+
+	family->sock_privs = kzalloc(sizeof(*family->sock_privs), GFP_KERNEL);
+	if (!family->sock_privs)
+		return -ENOMEM;
+	xa_init(family->sock_privs);
+	return 0;
+}
+
+static void genl_sk_privs_free(const struct genl_family *family)
+{
+	unsigned long id;
+	void *priv;
+
+	if (!family->sock_priv_size)
+		return;
+
+	xa_for_each(family->sock_privs, id, priv)
+		genl_sk_priv_free(family, priv);
+
+	xa_destroy(family->sock_privs);
+	kfree(family->sock_privs);
+}
+
+static void genl_sk_priv_free_by_sock(struct genl_family *family,
+				      struct sock *sk)
+{
+	void *priv;
+
+	if (!family->sock_priv_size)
+		return;
+	priv = xa_erase(family->sock_privs, (unsigned long) sk);
+	if (!priv)
+		return;
+	genl_sk_priv_free(family, priv);
+}
+
+static void genl_release(struct sock *sk, unsigned long *groups)
+{
+	struct genl_family *family;
+	unsigned int id;
+
+	down_read(&cb_lock);
+
+	idr_for_each_entry(&genl_fam_idr, family, id)
+		genl_sk_priv_free_by_sock(family, sk);
+
+	up_read(&cb_lock);
+}
+
+/**
+ * __genl_sk_priv_get - Get family private pointer for socket, if exists
+ *
+ * @family: family
+ * @sk: socket
+ *
+ * Lookup a private memory for a Generic netlink family and specified socket.
+ *
+ * Caller should make sure this is called in RCU read locked section.
+ *
+ * Return: valid pointer on success, otherwise negative error value
+ * encoded by ERR_PTR(), NULL in case priv does not exist.
+ */
+void *__genl_sk_priv_get(struct genl_family *family, struct sock *sk)
+{
+	if (WARN_ON_ONCE(!family->sock_privs))
+		return ERR_PTR(-EINVAL);
+	return xa_load(family->sock_privs, (unsigned long) sk);
+}
+
+/**
+ * genl_sk_priv_get - Get family private pointer for socket
+ *
+ * @family: family
+ * @sk: socket
+ *
+ * Lookup a private memory for a Generic netlink family and specified socket.
+ * Allocate the private memory in case it was not already done.
+ *
+ * Return: valid pointer on success, otherwise negative error value
+ * encoded by ERR_PTR().
+ */
+void *genl_sk_priv_get(struct genl_family *family, struct sock *sk)
+{
+	void *priv, *old_priv;
+
+	priv = __genl_sk_priv_get(family, sk);
+	if (priv)
+		return priv;
+
+	/* priv for the family does not exist so far, create it. */
+
+	priv = genl_sk_priv_alloc(family);
+	if (IS_ERR(priv))
+		return ERR_CAST(priv);
+
+	old_priv = xa_cmpxchg(family->sock_privs, (unsigned long) sk, NULL,
+			      priv, GFP_KERNEL);
+	if (old_priv) {
+		genl_sk_priv_free(family, priv);
+		if (xa_is_err(old_priv))
+			return ERR_PTR(xa_err(old_priv));
+		/* Race happened, priv for the socket was already inserted. */
+		return old_priv;
+	}
+	return priv;
+}
+
 /**
  * genl_register_family - register a generic netlink family
  * @family: generic netlink family
@@ -659,6 +791,10 @@ int genl_register_family(struct genl_family *family)
 		goto errout_locked;
 	}
 
+	err = genl_sk_privs_alloc(family);
+	if (err)
+		goto errout_locked;
+
 	/*
 	 * Sadly, a few cases need to be special-cased
 	 * due to them having previously abused the API
@@ -679,7 +815,7 @@ int genl_register_family(struct genl_family *family)
 				      start, end + 1, GFP_KERNEL);
 	if (family->id < 0) {
 		err = family->id;
-		goto errout_locked;
+		goto errout_sk_privs_free;
 	}
 
 	err = genl_validate_assign_mc_groups(family);
@@ -698,6 +834,8 @@ int genl_register_family(struct genl_family *family)
 
 errout_remove:
 	idr_remove(&genl_fam_idr, family->id);
+errout_sk_privs_free:
+	genl_sk_privs_free(family);
 errout_locked:
 	genl_unlock_all();
 	return err;
@@ -728,6 +866,9 @@ int genl_unregister_family(const struct genl_family *family)
 	up_write(&cb_lock);
 	wait_event(genl_sk_destructing_waitq,
 		   atomic_read(&genl_sk_destructing_cnt) == 0);
+
+	genl_sk_privs_free(family);
+
 	genl_unlock();
 
 	genl_ctrl_event(CTRL_CMD_DELFAMILY, family, NULL, 0);
@@ -1708,6 +1849,7 @@ static int __net_init genl_pernet_init(struct net *net)
 		.input		= genl_rcv,
 		.flags		= NL_CFG_F_NONROOT_RECV,
 		.bind		= genl_bind,
+		.release	= genl_release,
 	};
 
 	/* we'll bump the group number right afterwards */