Merge branch 'ipvlan-addrs_lock-made-per-port'

Dmitry Skorodumov says:

====================
ipvlan: addrs_lock made per port

First patch fixes a rather minor issues that sometimes
ipvlan-addrs are modified without lock (because
for IPv6 addr can be sometimes added without RTNL)
====================

Link: https://patch.msgid.link/20260112142417.4039566-1-skorodumov.dmitry@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

6 files changed, 208 insertions, 30 deletions

diff --git a/drivers/net/ipvlan/ipvlan.h b/drivers/net/ipvlan/ipvlan.h
index 50de3ee204db..80f84fc87008 100644
--- a/drivers/net/ipvlan/ipvlan.h
+++ b/drivers/net/ipvlan/ipvlan.h
@@ -69,7 +69,6 @@ struct ipvl_dev {
 	DECLARE_BITMAP(mac_filters, IPVLAN_MAC_FILTER_SIZE);
 	netdev_features_t	sfeatures;
 	u32			msg_enable;
-	spinlock_t		addrs_lock;
 };
 
 struct ipvl_addr {
@@ -90,6 +89,7 @@ struct ipvl_port {
 	struct net_device	*dev;
 	possible_net_t		pnet;
 	struct hlist_head	hlhead[IPVLAN_HASH_SIZE];
+	spinlock_t		addrs_lock; /* guards hash-table and addrs */
 	struct list_head	ipvlans;
 	u16			mode;
 	u16			flags;
diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c
index 2efa3ba148aa..bdb3a46b327c 100644
--- a/drivers/net/ipvlan/ipvlan_core.c
+++ b/drivers/net/ipvlan/ipvlan_core.c
@@ -107,17 +107,15 @@ void ipvlan_ht_addr_del(struct ipvl_addr *addr)
 struct ipvl_addr *ipvlan_find_addr(const struct ipvl_dev *ipvlan,
 				   const void *iaddr, bool is_v6)
 {
-	struct ipvl_addr *addr, *ret = NULL;
+	struct ipvl_addr *addr;
 
-	rcu_read_lock();
-	list_for_each_entry_rcu(addr, &ipvlan->addrs, anode) {
-		if (addr_equal(is_v6, addr, iaddr)) {
-			ret = addr;
-			break;
-		}
+	assert_spin_locked(&ipvlan->port->addrs_lock);
+
+	list_for_each_entry(addr, &ipvlan->addrs, anode) {
+		if (addr_equal(is_v6, addr, iaddr))
+			return addr;
 	}
-	rcu_read_unlock();
-	return ret;
+	return NULL;
 }
 
 bool ipvlan_addr_busy(struct ipvl_port *port, void *iaddr, bool is_v6)
diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index 660f3db11766..baccdad695fd 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -75,6 +75,7 @@ static int ipvlan_port_create(struct net_device *dev)
 	for (idx = 0; idx < IPVLAN_HASH_SIZE; idx++)
 		INIT_HLIST_HEAD(&port->hlhead[idx]);
 
+	spin_lock_init(&port->addrs_lock);
 	skb_queue_head_init(&port->backlog);
 	INIT_WORK(&port->wq, ipvlan_process_multicast);
 	ida_init(&port->ida);
@@ -181,6 +182,7 @@ static void ipvlan_uninit(struct net_device *dev)
 static int ipvlan_open(struct net_device *dev)
 {
 	struct ipvl_dev *ipvlan = netdev_priv(dev);
+	struct ipvl_port *port = ipvlan->port;
 	struct ipvl_addr *addr;
 
 	if (ipvlan->port->mode == IPVLAN_MODE_L3 ||
@@ -189,10 +191,10 @@ static int ipvlan_open(struct net_device *dev)
 	else
 		dev->flags &= ~IFF_NOARP;
 
-	rcu_read_lock();
-	list_for_each_entry_rcu(addr, &ipvlan->addrs, anode)
+	spin_lock_bh(&port->addrs_lock);
+	list_for_each_entry(addr, &ipvlan->addrs, anode)
 		ipvlan_ht_addr_add(ipvlan, addr);
-	rcu_read_unlock();
+	spin_unlock_bh(&port->addrs_lock);
 
 	return 0;
 }
@@ -206,10 +208,10 @@ static int ipvlan_stop(struct net_device *dev)
 	dev_uc_unsync(phy_dev, dev);
 	dev_mc_unsync(phy_dev, dev);
 
-	rcu_read_lock();
-	list_for_each_entry_rcu(addr, &ipvlan->addrs, anode)
+	spin_lock_bh(&ipvlan->port->addrs_lock);
+	list_for_each_entry(addr, &ipvlan->addrs, anode)
 		ipvlan_ht_addr_del(addr);
-	rcu_read_unlock();
+	spin_unlock_bh(&ipvlan->port->addrs_lock);
 
 	return 0;
 }
@@ -579,7 +581,6 @@ int ipvlan_link_new(struct net_device *dev, struct rtnl_newlink_params *params,
 	if (!tb[IFLA_MTU])
 		ipvlan_adjust_mtu(ipvlan, phy_dev);
 	INIT_LIST_HEAD(&ipvlan->addrs);
-	spin_lock_init(&ipvlan->addrs_lock);
 
 	/* TODO Probably put random address here to be presented to the
 	 * world but keep using the physical-dev address for the outgoing
@@ -657,13 +658,13 @@ void ipvlan_link_delete(struct net_device *dev, struct list_head *head)
 	struct ipvl_dev *ipvlan = netdev_priv(dev);
 	struct ipvl_addr *addr, *next;
 
-	spin_lock_bh(&ipvlan->addrs_lock);
+	spin_lock_bh(&ipvlan->port->addrs_lock);
 	list_for_each_entry_safe(addr, next, &ipvlan->addrs, anode) {
 		ipvlan_ht_addr_del(addr);
 		list_del_rcu(&addr->anode);
 		kfree_rcu(addr, rcu);
 	}
-	spin_unlock_bh(&ipvlan->addrs_lock);
+	spin_unlock_bh(&ipvlan->port->addrs_lock);
 
 	ida_free(&ipvlan->port->ida, dev->dev_id);
 	list_del_rcu(&ipvlan->pnode);
@@ -817,6 +818,8 @@ static int ipvlan_add_addr(struct ipvl_dev *ipvlan, void *iaddr, bool is_v6)
 {
 	struct ipvl_addr *addr;
 
+	assert_spin_locked(&ipvlan->port->addrs_lock);
+
 	addr = kzalloc(sizeof(struct ipvl_addr), GFP_ATOMIC);
 	if (!addr)
 		return -ENOMEM;
@@ -847,16 +850,16 @@ static void ipvlan_del_addr(struct ipvl_dev *ipvlan, void *iaddr, bool is_v6)
 {
 	struct ipvl_addr *addr;
 
-	spin_lock_bh(&ipvlan->addrs_lock);
+	spin_lock_bh(&ipvlan->port->addrs_lock);
 	addr = ipvlan_find_addr(ipvlan, iaddr, is_v6);
 	if (!addr) {
-		spin_unlock_bh(&ipvlan->addrs_lock);
+		spin_unlock_bh(&ipvlan->port->addrs_lock);
 		return;
 	}
 
 	ipvlan_ht_addr_del(addr);
 	list_del_rcu(&addr->anode);
-	spin_unlock_bh(&ipvlan->addrs_lock);
+	spin_unlock_bh(&ipvlan->port->addrs_lock);
 	kfree_rcu(addr, rcu);
 }
 
@@ -878,14 +881,14 @@ static int ipvlan_add_addr6(struct ipvl_dev *ipvlan, struct in6_addr *ip6_addr)
 {
 	int ret = -EINVAL;
 
-	spin_lock_bh(&ipvlan->addrs_lock);
+	spin_lock_bh(&ipvlan->port->addrs_lock);
 	if (ipvlan_addr_busy(ipvlan->port, ip6_addr, true))
 		netif_err(ipvlan, ifup, ipvlan->dev,
 			  "Failed to add IPv6=%pI6c addr for %s intf\n",
 			  ip6_addr, ipvlan->dev->name);
 	else
 		ret = ipvlan_add_addr(ipvlan, ip6_addr, true);
-	spin_unlock_bh(&ipvlan->addrs_lock);
+	spin_unlock_bh(&ipvlan->port->addrs_lock);
 	return ret;
 }
 
@@ -924,21 +927,24 @@ static int ipvlan_addr6_validator_event(struct notifier_block *unused,
 	struct in6_validator_info *i6vi = (struct in6_validator_info *)ptr;
 	struct net_device *dev = (struct net_device *)i6vi->i6vi_dev->dev;
 	struct ipvl_dev *ipvlan = netdev_priv(dev);
+	int ret = NOTIFY_OK;
 
 	if (!ipvlan_is_valid_dev(dev))
 		return NOTIFY_DONE;
 
 	switch (event) {
 	case NETDEV_UP:
+		spin_lock_bh(&ipvlan->port->addrs_lock);
 		if (ipvlan_addr_busy(ipvlan->port, &i6vi->i6vi_addr, true)) {
 			NL_SET_ERR_MSG(i6vi->extack,
 				       "Address already assigned to an ipvlan device");
-			return notifier_from_errno(-EADDRINUSE);
+			ret = notifier_from_errno(-EADDRINUSE);
 		}
+		spin_unlock_bh(&ipvlan->port->addrs_lock);
 		break;
 	}
 
-	return NOTIFY_OK;
+	return ret;
 }
 #endif
 
@@ -946,14 +952,14 @@ static int ipvlan_add_addr4(struct ipvl_dev *ipvlan, struct in_addr *ip4_addr)
 {
 	int ret = -EINVAL;
 
-	spin_lock_bh(&ipvlan->addrs_lock);
+	spin_lock_bh(&ipvlan->port->addrs_lock);
 	if (ipvlan_addr_busy(ipvlan->port, ip4_addr, false))
 		netif_err(ipvlan, ifup, ipvlan->dev,
 			  "Failed to add IPv4=%pI4 on %s intf.\n",
 			  ip4_addr, ipvlan->dev->name);
 	else
 		ret = ipvlan_add_addr(ipvlan, ip4_addr, false);
-	spin_unlock_bh(&ipvlan->addrs_lock);
+	spin_unlock_bh(&ipvlan->port->addrs_lock);
 	return ret;
 }
 
@@ -995,21 +1001,24 @@ static int ipvlan_addr4_validator_event(struct notifier_block *unused,
 	struct in_validator_info *ivi = (struct in_validator_info *)ptr;
 	struct net_device *dev = (struct net_device *)ivi->ivi_dev->dev;
 	struct ipvl_dev *ipvlan = netdev_priv(dev);
+	int ret = NOTIFY_OK;
 
 	if (!ipvlan_is_valid_dev(dev))
 		return NOTIFY_DONE;
 
 	switch (event) {
 	case NETDEV_UP:
+		spin_lock_bh(&ipvlan->port->addrs_lock);
 		if (ipvlan_addr_busy(ipvlan->port, &ivi->ivi_addr, false)) {
 			NL_SET_ERR_MSG(ivi->extack,
 				       "Address already assigned to an ipvlan device");
-			return notifier_from_errno(-EADDRINUSE);
+			ret = notifier_from_errno(-EADDRINUSE);
 		}
+		spin_unlock_bh(&ipvlan->port->addrs_lock);
 		break;
 	}
 
-	return NOTIFY_OK;
+	return ret;
 }
 
 static struct notifier_block ipvlan_addr4_notifier_block __read_mostly = {
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index b66ba04f19d9..45c4ea381bc3 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -48,6 +48,7 @@ TEST_PROGS := \
 	ipv6_flowlabel.sh \
 	ipv6_force_forwarding.sh \
 	ipv6_route_update_soft_lockup.sh \
+	ipvtap_test.sh \
 	l2_tos_ttl_inherit.sh \
 	l2tp.sh \
 	link_netns.py \
diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config
index 1e1f253118f5..b84362b9b508 100644
--- a/tools/testing/selftests/net/config
+++ b/tools/testing/selftests/net/config
@@ -48,6 +48,7 @@ CONFIG_IPV6_SEG6_LWTUNNEL=y
 CONFIG_IPV6_SIT=y
 CONFIG_IPV6_VTI=y
 CONFIG_IPVLAN=m
+CONFIG_IPVTAP=m
 CONFIG_KALLSYMS=y
 CONFIG_L2TP=m
 CONFIG_L2TP_ETH=m
@@ -116,6 +117,7 @@ CONFIG_PROC_SYSCTL=y
 CONFIG_PSAMPLE=m
 CONFIG_RPS=y
 CONFIG_SYSFS=y
+CONFIG_TAP=m
 CONFIG_TCP_MD5SIG=y
 CONFIG_TEST_BLACKHOLE_DEV=m
 CONFIG_TEST_BPF=m
diff --git a/tools/testing/selftests/net/ipvtap_test.sh b/tools/testing/selftests/net/ipvtap_test.sh
new file mode 100755
index 000000000000..354ca7ce8584
--- /dev/null
+++ b/tools/testing/selftests/net/ipvtap_test.sh
@@ -0,0 +1,168 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Simple tests for ipvtap
+
+
+#
+# The testing environment looks this way:
+#
+# |------HNS-------|     |------PHY-------|
+# |      veth<----------------->veth      |
+# |------|--|------|     |----------------|
+#        |  |
+#        |  |            |-----TST0-------|
+#        |  |------------|----ipvlan      |
+#        |               |----------------|
+#        |
+#        |               |-----TST1-------|
+#        |---------------|----ipvlan      |
+#                        |----------------|
+#
+
+ALL_TESTS="
+	test_ip_set
+"
+
+source lib.sh
+
+DEBUG=0
+
+VETH_HOST=vethtst.h
+VETH_PHY=vethtst.p
+
+NS_COUNT=32
+IP_ITERATIONS=1024
+IPSET_TIMEOUT="60s"
+
+ns_run() {
+	ns=$1
+	shift
+	if [[ "$ns" == "global" ]]; then
+		"$@" >/dev/null
+	else
+		ip netns exec "$ns" "$@" >/dev/null
+	fi
+}
+
+test_ip_setup_env() {
+	setup_ns NS_PHY
+	setup_ns HST_NS
+
+	# setup simulated other-host (phy) and host itself
+	ns_run "$HST_NS" ip link add $VETH_HOST type veth peer name $VETH_PHY \
+		netns "$NS_PHY" >/dev/null
+	ns_run "$HST_NS" ip link set $VETH_HOST up
+	ns_run "$NS_PHY" ip link set $VETH_PHY up
+
+	for ((i=0; i<NS_COUNT; i++)); do
+		setup_ns ipvlan_ns_$i
+		ns="ipvlan_ns_$i"
+		if [ "$DEBUG" = "1" ]; then
+			echo "created NS ${!ns}"
+		fi
+		if ! ns_run "$HST_NS" ip link add netns ${!ns} ipvlan0 \
+		    link $VETH_HOST \
+		    type ipvtap mode l2 bridge; then
+			exit_error "FAIL: Failed to configure ipvlan link."
+		fi
+	done
+}
+
+test_ip_cleanup_env() {
+	ns_run "$HST_NS" ip link del $VETH_HOST
+	cleanup_all_ns
+}
+
+exit_error() {
+	echo "$1"
+	exit $ksft_fail
+}
+
+rnd() {
+	echo $(( RANDOM % 32 + 16 ))
+}
+
+test_ip_set_thread() {
+	# Here we are trying to create some IP conflicts between namespaces.
+	# If just add/remove IP, nothing interesting will happen.
+	# But if add random IP and then remove random IP,
+	# eventually conflicts start to apear.
+	ip link set ipvlan0 up
+	for ((i=0; i<IP_ITERATIONS; i++)); do
+		v=$(rnd)
+		ip a a "172.25.0.$v/24" dev ipvlan0 2>/dev/null
+		ip a a "fc00::$v/64" dev ipvlan0 2>/dev/null
+		v=$(rnd)
+		ip a d "172.25.0.$v/24" dev ipvlan0 2>/dev/null
+		ip a d "fc00::$v/64" dev ipvlan0 2>/dev/null
+	done
+}
+
+test_ip_set() {
+	RET=0
+
+	trap test_ip_cleanup_env EXIT
+
+	test_ip_setup_env
+
+	declare -A ns_pids
+	for ((i=0; i<NS_COUNT; i++)); do
+		ns="ipvlan_ns_$i"
+		ns_run ${!ns} timeout "$IPSET_TIMEOUT" \
+			bash -c "$0 test_ip_set_thread"&
+		ns_pids[$i]=$!
+	done
+
+	for ((i=0; i<NS_COUNT; i++)); do
+		wait "${ns_pids[$i]}"
+	done
+
+	declare -A all_ips
+	for ((i=0; i<NS_COUNT; i++)); do
+		ns="ipvlan_ns_$i"
+		ip_output=$(ip netns exec ${!ns} ip a l dev ipvlan0 | grep inet)
+		while IFS= read -r nsip_out; do
+			if [[ -z $nsip_out ]]; then
+				continue;
+			fi
+			nsip=$(awk '{print $2}' <<< "$nsip_out")
+			if [[ -v all_ips[$nsip] ]]; then
+				RET=$ksft_fail
+				log_test "conflict for $nsip"
+				return "$RET"
+			else
+				all_ips[$nsip]=$i
+			fi
+		done <<< "$ip_output"
+	done
+
+	if [ "$DEBUG" = "1" ]; then
+		for key in "${!all_ips[@]}"; do
+			echo "$key: ${all_ips[$key]}"
+		done
+	fi
+
+	trap - EXIT
+	test_ip_cleanup_env
+
+	log_test "test multithreaded ip set"
+}
+
+if [[ "$1" == "-d" ]]; then
+	DEBUG=1
+	shift
+fi
+
+if [[ "$1" == "-t" ]]; then
+	shift
+	TESTS="$*"
+fi
+
+if [[ "$1" == "test_ip_set_thread" ]]; then
+	test_ip_set_thread
+else
+	require_command ip
+
+	tests_run
+fi