Merge branch 'make-neighbor-eviction-controllable-by-userspace'

James Prestwood says:

====================
Make neighbor eviction controllable by userspace
====================

Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>

Author: kuba-moo

Documentation/networking/ip-sysctl.rst

@@ -1611,6 +1611,15 @@ arp_accept - BOOLEAN
 	gratuitous arp frame, the arp table will be updated regardless
 	if this setting is on or off.
 
+arp_evict_nocarrier - BOOLEAN
+	Clears the ARP cache on NOCARRIER events. This option is important for
+	wireless devices where the ARP cache should not be cleared when roaming
+	between access points on the same network. In most cases this should
+	remain as the default (1).
+
+	- 1 - (default): Clear the ARP cache on NOCARRIER events
+	- 0 - Do not clear ARP cache on NOCARRIER events
+
 mcast_solicit - INTEGER
 	The maximum number of multicast probes in INCOMPLETE state,
 	when the associated hardware address is unknown.  Defaults
@@ -2341,6 +2350,15 @@ ndisc_tclass - INTEGER
 
 	* 0 - (default)
 
+ndisc_evict_nocarrier - BOOLEAN
+	Clears the neighbor discovery table on NOCARRIER events. This option is
+	important for wireless devices where the neighbor discovery cache should
+	not be cleared when roaming between access points on the same network.
+	In most cases this should remain as the default (1).
+
+	- 1 - (default): Clear neighbor discover cache on NOCARRIER events.
+	- 0 - Do not clear neighbor discovery cache on NOCARRIER events.
+
 mldv1_unsolicited_report_interval - INTEGER
 	The interval in milliseconds in which the next unsolicited
 	MLDv1 report retransmit will take place.

include/linux/inetdevice.h

@@ -133,6 +133,8 @@ static inline void ipv4_devconf_setall(struct in_device *in_dev)
 #define IN_DEV_ARP_ANNOUNCE(in_dev)	IN_DEV_MAXCONF((in_dev), ARP_ANNOUNCE)
 #define IN_DEV_ARP_IGNORE(in_dev)	IN_DEV_MAXCONF((in_dev), ARP_IGNORE)
 #define IN_DEV_ARP_NOTIFY(in_dev)	IN_DEV_MAXCONF((in_dev), ARP_NOTIFY)
+#define IN_DEV_ARP_EVICT_NOCARRIER(in_dev) IN_DEV_ANDCONF((in_dev), \
+							  ARP_EVICT_NOCARRIER)
 
 struct in_ifaddr {
 	struct hlist_node	hash;

include/linux/ipv6.h

@@ -79,6 +79,7 @@ struct ipv6_devconf {
 	__u32		ioam6_id;
 	__u32		ioam6_id_wide;
 	__u8		ioam6_enabled;
+	__u8		ndisc_evict_nocarrier;
 
 	struct ctl_table_header *sysctl_header;
 };

include/uapi/linux/ip.h

@@ -169,6 +169,7 @@ enum
 	IPV4_DEVCONF_DROP_UNICAST_IN_L2_MULTICAST,
 	IPV4_DEVCONF_DROP_GRATUITOUS_ARP,
 	IPV4_DEVCONF_BC_FORWARDING,
+	IPV4_DEVCONF_ARP_EVICT_NOCARRIER,
 	__IPV4_DEVCONF_MAX
 };
 

include/uapi/linux/ipv6.h

@@ -193,6 +193,7 @@ enum {
 	DEVCONF_IOAM6_ENABLED,
 	DEVCONF_IOAM6_ID,
 	DEVCONF_IOAM6_ID_WIDE,
+	DEVCONF_NDISC_EVICT_NOCARRIER,
 	DEVCONF_MAX
 };
 

include/uapi/linux/sysctl.h

@@ -482,6 +482,7 @@ enum
 	NET_IPV4_CONF_PROMOTE_SECONDARIES=20,
 	NET_IPV4_CONF_ARP_ACCEPT=21,
 	NET_IPV4_CONF_ARP_NOTIFY=22,
+	NET_IPV4_CONF_ARP_EVICT_NOCARRIER=23,
 };
 
 /* /proc/sys/net/ipv4/netfilter */

net/ipv4/arp.c

@@ -1247,6 +1247,8 @@ static int arp_netdev_event(struct notifier_block *this, unsigned long event,
 {
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 	struct netdev_notifier_change_info *change_info;
+	struct in_device *in_dev;
+	bool evict_nocarrier;
 
 	switch (event) {
 	case NETDEV_CHANGEADDR:
@@ -1257,7 +1259,14 @@ static int arp_netdev_event(struct notifier_block *this, unsigned long event,
 		change_info = ptr;
 		if (change_info->flags_changed & IFF_NOARP)
 			neigh_changeaddr(&arp_tbl, dev);
-		if (!netif_carrier_ok(dev))
+
+		in_dev = __in_dev_get_rtnl(dev);
+		if (!in_dev)
+			evict_nocarrier = true;
+		else
+			evict_nocarrier = IN_DEV_ARP_EVICT_NOCARRIER(in_dev);
+
+		if (evict_nocarrier && !netif_carrier_ok(dev))
 			neigh_carrier_down(&arp_tbl, dev);
 		break;
 	default:

net/ipv4/devinet.c

@@ -75,6 +75,7 @@ static struct ipv4_devconf ipv4_devconf = {
 		[IPV4_DEVCONF_SHARED_MEDIA - 1] = 1,
 		[IPV4_DEVCONF_IGMPV2_UNSOLICITED_REPORT_INTERVAL - 1] = 10000 /*ms*/,
 		[IPV4_DEVCONF_IGMPV3_UNSOLICITED_REPORT_INTERVAL - 1] =  1000 /*ms*/,
+		[IPV4_DEVCONF_ARP_EVICT_NOCARRIER - 1] = 1,
 	},
 };
 
@@ -87,6 +88,7 @@ static struct ipv4_devconf ipv4_devconf_dflt = {
 		[IPV4_DEVCONF_ACCEPT_SOURCE_ROUTE - 1] = 1,
 		[IPV4_DEVCONF_IGMPV2_UNSOLICITED_REPORT_INTERVAL - 1] = 10000 /*ms*/,
 		[IPV4_DEVCONF_IGMPV3_UNSOLICITED_REPORT_INTERVAL - 1] =  1000 /*ms*/,
+		[IPV4_DEVCONF_ARP_EVICT_NOCARRIER - 1] = 1,
 	},
 };
 
@@ -2532,6 +2534,8 @@ static struct devinet_sysctl_table {
 		DEVINET_SYSCTL_RW_ENTRY(ARP_IGNORE, "arp_ignore"),
 		DEVINET_SYSCTL_RW_ENTRY(ARP_ACCEPT, "arp_accept"),
 		DEVINET_SYSCTL_RW_ENTRY(ARP_NOTIFY, "arp_notify"),
+		DEVINET_SYSCTL_RW_ENTRY(ARP_EVICT_NOCARRIER,
+					"arp_evict_nocarrier"),
 		DEVINET_SYSCTL_RW_ENTRY(PROXY_ARP_PVLAN, "proxy_arp_pvlan"),
 		DEVINET_SYSCTL_RW_ENTRY(FORCE_IGMP_VERSION,
 					"force_igmp_version"),

net/ipv6/addrconf.c

@@ -241,6 +241,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = {
 	.ioam6_enabled		= 0,
 	.ioam6_id               = IOAM6_DEFAULT_IF_ID,
 	.ioam6_id_wide		= IOAM6_DEFAULT_IF_ID_WIDE,
+	.ndisc_evict_nocarrier	= 1,
 };
 
 static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
@@ -300,6 +301,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
 	.ioam6_enabled		= 0,
 	.ioam6_id               = IOAM6_DEFAULT_IF_ID,
 	.ioam6_id_wide		= IOAM6_DEFAULT_IF_ID_WIDE,
+	.ndisc_evict_nocarrier	= 1,
 };
 
 /* Check if link is ready: is it up and is a valid qdisc available */
@@ -5545,6 +5547,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf,
 	array[DEVCONF_IOAM6_ENABLED] = cnf->ioam6_enabled;
 	array[DEVCONF_IOAM6_ID] = cnf->ioam6_id;
 	array[DEVCONF_IOAM6_ID_WIDE] = cnf->ioam6_id_wide;
+	array[DEVCONF_NDISC_EVICT_NOCARRIER] = cnf->ndisc_evict_nocarrier;
 }
 
 static inline size_t inet6_ifla6_size(void)
@@ -6986,6 +6989,15 @@ static const struct ctl_table addrconf_sysctl[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_douintvec,
 	},
+	{
+		.procname	= "ndisc_evict_nocarrier",
+		.data		= &ipv6_devconf.ndisc_evict_nocarrier,
+		.maxlen		= sizeof(u8),
+		.mode		= 0644,
+		.proc_handler	= proc_dou8vec_minmax,
+		.extra1		= (void *)SYSCTL_ZERO,
+		.extra2		= (void *)SYSCTL_ONE,
+	},
 	{
 		/* sentinel */
 	}

net/ipv6/ndisc.c

@@ -1794,6 +1794,7 @@ static int ndisc_netdev_event(struct notifier_block *this, unsigned long event,
 	struct netdev_notifier_change_info *change_info;
 	struct net *net = dev_net(dev);
 	struct inet6_dev *idev;
+	bool evict_nocarrier;
 
 	switch (event) {
 	case NETDEV_CHANGEADDR:
@@ -1810,10 +1811,19 @@ static int ndisc_netdev_event(struct notifier_block *this, unsigned long event,
 		in6_dev_put(idev);
 		break;
 	case NETDEV_CHANGE:
+		idev = in6_dev_get(dev);
+		if (!idev)
+			evict_nocarrier = true;
+		else {
+			evict_nocarrier = idev->cnf.ndisc_evict_nocarrier &&
+					  net->ipv6.devconf_all->ndisc_evict_nocarrier;
+			in6_dev_put(idev);
+		}
+
 		change_info = ptr;
 		if (change_info->flags_changed & IFF_NOARP)
 			neigh_changeaddr(&nd_tbl, dev);
-		if (!netif_carrier_ok(dev))
+		if (evict_nocarrier && !netif_carrier_ok(dev))
 			neigh_carrier_down(&nd_tbl, dev);
 		break;
 	case NETDEV_DOWN: