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

James Prestwood says:

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

Link: https://lore.kernel.org/r/20211101173630.300969-1-prestwoj@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

11 files changed, 281 insertions, 2 deletions

diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst
index 16b8bf72feaf..c61cc0219f4c 100644
--- a/Documentation/networking/ip-sysctl.rst
+++ b/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.
diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h
index a038feb63f23..518b484a7f07 100644
--- a/include/linux/inetdevice.h
+++ b/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;
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index c383630d3f06..20c1f968da7c 100644
--- a/include/linux/ipv6.h
+++ b/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;
 };
diff --git a/include/uapi/linux/ip.h b/include/uapi/linux/ip.h
index e42d13b55cf3..e00bbb9c47bb 100644
--- a/include/uapi/linux/ip.h
+++ b/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
 };
 
diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h
index b243a53fa985..d4178dace0bf 100644
--- a/include/uapi/linux/ipv6.h
+++ b/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
 };
 
diff --git a/include/uapi/linux/sysctl.h b/include/uapi/linux/sysctl.h
index 1e05d3caa712..6a3b194c50fe 100644
--- a/include/uapi/linux/sysctl.h
+++ b/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 */
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 922dd73e5740..857a144b1ea9 100644
--- a/net/ipv4/arp.c
+++ b/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:
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index f4468980b675..ec73a0d52d3e 100644
--- a/net/ipv4/devinet.c
+++ b/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"),
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 9e1463a2acae..3445f8017430 100644
--- a/net/ipv6/addrconf.c
+++ b/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)
@@ -6987,6 +6990,15 @@ static const struct ctl_table addrconf_sysctl[] = {
 		.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 */
 	}
 };
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 184190b9ea25..f03b597e4121 100644
--- a/net/ipv6/ndisc.c
+++ b/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:
diff --git a/tools/testing/selftests/net/arp_ndisc_evict_nocarrier.sh b/tools/testing/selftests/net/arp_ndisc_evict_nocarrier.sh
new file mode 100755
index 000000000000..b5af08af8559
--- /dev/null
+++ b/tools/testing/selftests/net/arp_ndisc_evict_nocarrier.sh
@@ -0,0 +1,220 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Tests sysctl options {arp,ndisc}_evict_nocarrier={0,1}
+#
+# Create a veth pair and set IPs/routes on both. Then ping to establish
+# an entry in the ARP/ND table. Depending on the test set sysctl option to
+# 1 or 0. Set remote veth down which will cause local veth to go into a no
+# carrier state. Depending on the test check the ARP/ND table:
+#
+# {arp,ndisc}_evict_nocarrier=1 should contain no ARP/ND after no carrier
+# {arp,ndisc}_evict_nocarrer=0 should still contain the single ARP/ND entry
+#
+
+readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)"
+readonly V4_ADDR0=10.0.10.1
+readonly V4_ADDR1=10.0.10.2
+readonly V6_ADDR0=2001:db8:91::1
+readonly V6_ADDR1=2001:db8:91::2
+nsid=100
+
+cleanup_v6()
+{
+    ip netns del me
+    ip netns del peer
+
+    sysctl -w net.ipv4.conf.veth0.ndisc_evict_nocarrier=1 >/dev/null 2>&1
+    sysctl -w net.ipv4.conf.all.ndisc_evict_nocarrier=1 >/dev/null 2>&1
+}
+
+create_ns()
+{
+    local n=${1}
+
+    ip netns del ${n} 2>/dev/null
+
+    ip netns add ${n}
+    ip netns set ${n} $((nsid++))
+    ip -netns ${n} link set lo up
+}
+
+
+setup_v6() {
+    create_ns me
+    create_ns peer
+
+    IP="ip -netns me"
+
+    $IP li add veth1 type veth peer name veth2
+    $IP li set veth1 up
+    $IP -6 addr add $V6_ADDR0/64 dev veth1 nodad
+    $IP li set veth2 netns peer up
+    ip -netns peer -6 addr add $V6_ADDR1/64 dev veth2 nodad
+
+    ip netns exec me sysctl -w $1 >/dev/null 2>&1
+
+    # Establish an ND cache entry
+    ip netns exec me ping -6 -c1 -Iveth1 $V6_ADDR1 >/dev/null 2>&1
+    # Should have the veth1 entry in ND table
+    ip netns exec me ip -6 neigh get $V6_ADDR1 dev veth1 >/dev/null 2>&1
+    if [ $? -ne 0 ]; then
+        cleanup_v6
+        echo "failed"
+        exit
+    fi
+
+    # Set veth2 down, which will put veth1 in NOCARRIER state
+    ip netns exec peer ip link set veth2 down
+}
+
+setup_v4() {
+    ip netns add "${PEER_NS}"
+    ip link add name veth0 type veth peer name veth1
+    ip link set dev veth0 up
+    ip link set dev veth1 netns "${PEER_NS}"
+    ip netns exec "${PEER_NS}" ip link set dev veth1 up
+    ip addr add $V4_ADDR0/24 dev veth0
+    ip netns exec "${PEER_NS}" ip addr add $V4_ADDR1/24 dev veth1
+    ip netns exec ${PEER_NS} ip route add default via $V4_ADDR1 dev veth1
+    ip route add default via $V4_ADDR0 dev veth0
+
+    sysctl -w "$1" >/dev/null 2>&1
+
+    # Establish an ARP cache entry
+    ping -c1 -I veth0 $V4_ADDR1 -q >/dev/null 2>&1
+    # Should have the veth1 entry in ARP table
+    ip neigh get $V4_ADDR1 dev veth0 >/dev/null 2>&1
+    if [ $? -ne 0 ]; then
+        cleanup_v4
+        echo "failed"
+        exit
+    fi
+
+    # Set veth1 down, which will put veth0 in NOCARRIER state
+    ip netns exec "${PEER_NS}" ip link set veth1 down
+}
+
+cleanup_v4() {
+    ip neigh flush dev veth0
+    ip link del veth0
+    local -r ns="$(ip netns list|grep $PEER_NS)"
+    [ -n "$ns" ] && ip netns del $ns 2>/dev/null
+
+    sysctl -w net.ipv4.conf.veth0.arp_evict_nocarrier=1 >/dev/null 2>&1
+    sysctl -w net.ipv4.conf.all.arp_evict_nocarrier=1 >/dev/null 2>&1
+}
+
+# Run test when arp_evict_nocarrier = 1 (default).
+run_arp_evict_nocarrier_enabled() {
+    echo "run arp_evict_nocarrier=1 test"
+    setup_v4 "net.ipv4.conf.veth0.arp_evict_nocarrier=1"
+
+    # ARP table should be empty
+    ip neigh get $V4_ADDR1 dev veth0 >/dev/null 2>&1
+
+    if [ $? -eq 0 ];then
+        echo "failed"
+    else
+        echo "ok"
+    fi
+
+    cleanup_v4
+}
+
+# Run test when arp_evict_nocarrier = 0
+run_arp_evict_nocarrier_disabled() {
+    echo "run arp_evict_nocarrier=0 test"
+    setup_v4 "net.ipv4.conf.veth0.arp_evict_nocarrier=0"
+
+    # ARP table should still contain the entry
+    ip neigh get $V4_ADDR1 dev veth0 >/dev/null 2>&1
+
+    if [ $? -eq 0 ];then
+        echo "ok"
+    else
+        echo "failed"
+    fi
+
+    cleanup_v4
+}
+
+run_arp_evict_nocarrier_disabled_all() {
+    echo "run all.arp_evict_nocarrier=0 test"
+    setup_v4 "net.ipv4.conf.all.arp_evict_nocarrier=0"
+
+    # ARP table should still contain the entry
+    ip neigh get $V4_ADDR1 dev veth0 >/dev/null 2>&1
+
+    if [ $? -eq 0 ];then
+        echo "ok"
+    else
+        echo "failed"
+    fi
+
+    cleanup_v4
+}
+
+run_ndisc_evict_nocarrier_enabled() {
+    echo "run ndisc_evict_nocarrier=1 test"
+
+    setup_v6 "net.ipv6.conf.veth1.ndisc_evict_nocarrier=1"
+
+    ip netns exec me ip -6 neigh get $V6_ADDR1 dev veth1 >/dev/null 2>&1
+
+    if [ $? -eq 0 ];then
+        echo "failed"
+    else
+        echo "ok"
+    fi
+
+    cleanup_v6
+}
+
+run_ndisc_evict_nocarrier_disabled() {
+    echo "run ndisc_evict_nocarrier=0 test"
+
+    setup_v6 "net.ipv6.conf.veth1.ndisc_evict_nocarrier=0"
+
+    ip netns exec me ip -6 neigh get $V6_ADDR1 dev veth1 >/dev/null 2>&1
+
+    if [ $? -eq 0 ];then
+        echo "ok"
+    else
+        echo "failed"
+    fi
+
+    cleanup_v6
+}
+
+run_ndisc_evict_nocarrier_disabled_all() {
+    echo "run all.ndisc_evict_nocarrier=0 test"
+
+    setup_v6 "net.ipv6.conf.all.ndisc_evict_nocarrier=0"
+
+    ip netns exec me ip -6 neigh get $V6_ADDR1 dev veth1 >/dev/null 2>&1
+
+    if [ $? -eq 0 ];then
+        echo "ok"
+    else
+        echo "failed"
+    fi
+
+    cleanup_v6
+}
+
+run_all_tests() {
+    run_arp_evict_nocarrier_enabled
+    run_arp_evict_nocarrier_disabled
+    run_arp_evict_nocarrier_disabled_all
+    run_ndisc_evict_nocarrier_enabled
+    run_ndisc_evict_nocarrier_disabled
+    run_ndisc_evict_nocarrier_disabled_all
+}
+
+if [ "$(id -u)" -ne 0 ];then
+	echo "SKIP: Need root privileges"
+	exit $ksft_skip;
+fi
+
+run_all_tests