Merge branch 'route-add-support-and-selftests-for-directed-broadcast-forwarding'

Xin Long says:

====================
route: add support and selftests for directed broadcast forwarding

Patch 1/2 is the feature and 2/2 is the selftest. Check the changelog
on each of them to know the details.

v1->v2:
  - fix a typo in changelog.
  - fix an uapi break that Davide noticed.
  - flush route cache when bc_forwarding is changed.
  - add the selftest for this patch as Ido's suggestion.

v2->v3:
  - fix an incorrect 'if check' in devinet_conf_proc as David Ahern
    noticed.
  - extend the selftest after one David Ahern fix for vrf.

v3->v4:
  - improve the output log in the selftest as David Ahern suggested.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

6 files changed, 252 insertions, 1 deletions

diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h
index 27650f1bff3d..c759d1cbcedd 100644
--- a/include/linux/inetdevice.h
+++ b/include/linux/inetdevice.h
@@ -93,6 +93,7 @@ static inline void ipv4_devconf_setall(struct in_device *in_dev)
 
 #define IN_DEV_FORWARD(in_dev)		IN_DEV_CONF_GET((in_dev), FORWARDING)
 #define IN_DEV_MFORWARD(in_dev)		IN_DEV_ANDCONF((in_dev), MC_FORWARDING)
+#define IN_DEV_BFORWARD(in_dev)		IN_DEV_ANDCONF((in_dev), BC_FORWARDING)
 #define IN_DEV_RPFILTER(in_dev)		IN_DEV_MAXCONF((in_dev), RP_FILTER)
 #define IN_DEV_SRC_VMARK(in_dev)    	IN_DEV_ORCONF((in_dev), SRC_VMARK)
 #define IN_DEV_SOURCE_ROUTE(in_dev)	IN_DEV_ANDCONF((in_dev), \
diff --git a/include/uapi/linux/ip.h b/include/uapi/linux/ip.h
index b24a742beae5..e42d13b55cf3 100644
--- a/include/uapi/linux/ip.h
+++ b/include/uapi/linux/ip.h
@@ -168,6 +168,7 @@ enum
 	IPV4_DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN,
 	IPV4_DEVCONF_DROP_UNICAST_IN_L2_MULTICAST,
 	IPV4_DEVCONF_DROP_GRATUITOUS_ARP,
+	IPV4_DEVCONF_BC_FORWARDING,
 	__IPV4_DEVCONF_MAX
 };
 
diff --git a/include/uapi/linux/netconf.h b/include/uapi/linux/netconf.h
index c84fcdfca862..fac4edd55379 100644
--- a/include/uapi/linux/netconf.h
+++ b/include/uapi/linux/netconf.h
@@ -18,6 +18,7 @@ enum {
 	NETCONFA_PROXY_NEIGH,
 	NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN,
 	NETCONFA_INPUT,
+	NETCONFA_BC_FORWARDING,
 	__NETCONFA_MAX
 };
 #define NETCONFA_MAX	(__NETCONFA_MAX - 1)
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index d7585ab1a77a..ea4bd8a52422 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1827,6 +1827,8 @@ static int inet_netconf_msgsize_devconf(int type)
 		size += nla_total_size(4);
 	if (all || type == NETCONFA_MC_FORWARDING)
 		size += nla_total_size(4);
+	if (all || type == NETCONFA_BC_FORWARDING)
+		size += nla_total_size(4);
 	if (all || type == NETCONFA_PROXY_NEIGH)
 		size += nla_total_size(4);
 	if (all || type == NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN)
@@ -1873,6 +1875,10 @@ static int inet_netconf_fill_devconf(struct sk_buff *skb, int ifindex,
 	    nla_put_s32(skb, NETCONFA_MC_FORWARDING,
 			IPV4_DEVCONF(*devconf, MC_FORWARDING)) < 0)
 		goto nla_put_failure;
+	if ((all || type == NETCONFA_BC_FORWARDING) &&
+	    nla_put_s32(skb, NETCONFA_BC_FORWARDING,
+			IPV4_DEVCONF(*devconf, BC_FORWARDING)) < 0)
+		goto nla_put_failure;
 	if ((all || type == NETCONFA_PROXY_NEIGH) &&
 	    nla_put_s32(skb, NETCONFA_PROXY_NEIGH,
 			IPV4_DEVCONF(*devconf, PROXY_ARP)) < 0)
@@ -2143,6 +2149,10 @@ static int devinet_conf_proc(struct ctl_table *ctl, int write,
 			if ((new_value == 0) && (old_value != 0))
 				rt_cache_flush(net);
 
+		if (i == IPV4_DEVCONF_BC_FORWARDING - 1 &&
+		    new_value != old_value)
+			rt_cache_flush(net);
+
 		if (i == IPV4_DEVCONF_RP_FILTER - 1 &&
 		    new_value != old_value) {
 			ifindex = devinet_conf_ifindex(net, cnf);
@@ -2259,6 +2269,7 @@ static struct devinet_sysctl_table {
 		DEVINET_SYSCTL_COMPLEX_ENTRY(FORWARDING, "forwarding",
 					     devinet_sysctl_forward),
 		DEVINET_SYSCTL_RO_ENTRY(MC_FORWARDING, "mc_forwarding"),
+		DEVINET_SYSCTL_RW_ENTRY(BC_FORWARDING, "bc_forwarding"),
 
 		DEVINET_SYSCTL_RW_ENTRY(ACCEPT_REDIRECTS, "accept_redirects"),
 		DEVINET_SYSCTL_RW_ENTRY(SECURE_REDIRECTS, "secure_redirects"),
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 1df6e97106d7..b678466da451 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1996,8 +1996,11 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 		goto no_route;
 	}
 
-	if (res->type == RTN_BROADCAST)
+	if (res->type == RTN_BROADCAST) {
+		if (IN_DEV_BFORWARD(in_dev))
+			goto make_route;
 		goto brd_input;
+	}
 
 	if (res->type == RTN_LOCAL) {
 		err = fib_validate_source(skb, saddr, daddr, tos,
@@ -2014,6 +2017,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	if (res->type != RTN_UNICAST)
 		goto martian_destination;
 
+make_route:
 	err = ip_mkroute_input(skb, res, in_dev, daddr, saddr, tos, flkeys);
 out:	return err;
 
diff --git a/tools/testing/selftests/net/forwarding/router_broadcast.sh b/tools/testing/selftests/net/forwarding/router_broadcast.sh
new file mode 100755
index 000000000000..7bd2ebb6e9de
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/router_broadcast.sh
@@ -0,0 +1,233 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS="ping_ipv4"
+NUM_NETIFS=6
+source lib.sh
+
+h1_create()
+{
+	vrf_create "vrf-h1"
+	ip link set dev $h1 master vrf-h1
+
+	ip link set dev vrf-h1 up
+	ip link set dev $h1 up
+
+	ip address add 192.0.2.2/24 dev $h1
+
+	ip route add 198.51.100.0/24 vrf vrf-h1 nexthop via 192.0.2.1
+	ip route add 198.51.200.0/24 vrf vrf-h1 nexthop via 192.0.2.1
+}
+
+h1_destroy()
+{
+	ip route del 198.51.200.0/24 vrf vrf-h1
+	ip route del 198.51.100.0/24 vrf vrf-h1
+
+	ip address del 192.0.2.2/24 dev $h1
+
+	ip link set dev $h1 down
+	vrf_destroy "vrf-h1"
+}
+
+h2_create()
+{
+	vrf_create "vrf-h2"
+	ip link set dev $h2 master vrf-h2
+
+	ip link set dev vrf-h2 up
+	ip link set dev $h2 up
+
+	ip address add 198.51.100.2/24 dev $h2
+
+	ip route add 192.0.2.0/24 vrf vrf-h2 nexthop via 198.51.100.1
+	ip route add 198.51.200.0/24 vrf vrf-h2 nexthop via 198.51.100.1
+}
+
+h2_destroy()
+{
+	ip route del 198.51.200.0/24 vrf vrf-h2
+	ip route del 192.0.2.0/24 vrf vrf-h2
+
+	ip address del 198.51.100.2/24 dev $h2
+
+	ip link set dev $h2 down
+	vrf_destroy "vrf-h2"
+}
+
+h3_create()
+{
+	vrf_create "vrf-h3"
+	ip link set dev $h3 master vrf-h3
+
+	ip link set dev vrf-h3 up
+	ip link set dev $h3 up
+
+	ip address add 198.51.200.2/24 dev $h3
+
+	ip route add 192.0.2.0/24 vrf vrf-h3 nexthop via 198.51.200.1
+	ip route add 198.51.100.0/24 vrf vrf-h3 nexthop via 198.51.200.1
+}
+
+h3_destroy()
+{
+	ip route del 198.51.100.0/24 vrf vrf-h3
+	ip route del 192.0.2.0/24 vrf vrf-h3
+
+	ip address del 198.51.200.2/24 dev $h3
+
+	ip link set dev $h3 down
+	vrf_destroy "vrf-h3"
+}
+
+router_create()
+{
+	ip link set dev $rp1 up
+	ip link set dev $rp2 up
+	ip link set dev $rp3 up
+
+	ip address add 192.0.2.1/24 dev $rp1
+
+	ip address add 198.51.100.1/24 dev $rp2
+	ip address add 198.51.200.1/24 dev $rp3
+}
+
+router_destroy()
+{
+	ip address del 198.51.200.1/24 dev $rp3
+	ip address del 198.51.100.1/24 dev $rp2
+
+	ip address del 192.0.2.1/24 dev $rp1
+
+	ip link set dev $rp3 down
+	ip link set dev $rp2 down
+	ip link set dev $rp1 down
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	rp1=${NETIFS[p2]}
+
+	rp2=${NETIFS[p3]}
+	h2=${NETIFS[p4]}
+
+	rp3=${NETIFS[p5]}
+	h3=${NETIFS[p6]}
+
+	vrf_prepare
+
+	h1_create
+	h2_create
+	h3_create
+
+	router_create
+
+	forwarding_enable
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	forwarding_restore
+
+	router_destroy
+
+	h3_destroy
+	h2_destroy
+	h1_destroy
+
+	vrf_cleanup
+}
+
+bc_forwarding_disable()
+{
+	sysctl_set net.ipv4.conf.all.bc_forwarding 0
+	sysctl_set net.ipv4.conf.$rp1.bc_forwarding 0
+}
+
+bc_forwarding_enable()
+{
+	sysctl_set net.ipv4.conf.all.bc_forwarding 1
+	sysctl_set net.ipv4.conf.$rp1.bc_forwarding 1
+}
+
+bc_forwarding_restore()
+{
+	sysctl_restore net.ipv4.conf.$rp1.bc_forwarding
+	sysctl_restore net.ipv4.conf.all.bc_forwarding
+}
+
+ping_test_from()
+{
+	local oif=$1
+	local dip=$2
+	local from=$3
+	local fail=${4:-0}
+
+	RET=0
+
+	log_info "ping $dip, expected reply from $from"
+	ip vrf exec $(master_name_get $oif) \
+	$PING -I $oif $dip -c 10 -i 0.1 -w 2 -b 2>&1 | grep $from &> /dev/null
+	check_err_fail $fail $?
+}
+
+ping_ipv4()
+{
+	sysctl_set net.ipv4.icmp_echo_ignore_broadcasts 0
+
+	bc_forwarding_disable
+	log_info "bc_forwarding disabled on r1 =>"
+	ping_test_from $h1 198.51.100.255 192.0.2.1
+	log_test "h1 -> net2: reply from r1 (not forwarding)"
+	ping_test_from $h1 198.51.200.255 192.0.2.1
+	log_test "h1 -> net3: reply from r1 (not forwarding)"
+	ping_test_from $h1 192.0.2.255 192.0.2.1
+	log_test "h1 -> net1: reply from r1 (not dropping)"
+	ping_test_from $h1 255.255.255.255 192.0.2.1
+	log_test "h1 -> 255.255.255.255: reply from r1 (not forwarding)"
+
+	ping_test_from $h2 192.0.2.255 198.51.100.1
+	log_test "h2 -> net1: reply from r1 (not forwarding)"
+	ping_test_from $h2 198.51.200.255 198.51.100.1
+	log_test "h2 -> net3: reply from r1 (not forwarding)"
+	ping_test_from $h2 198.51.100.255 198.51.100.1
+	log_test "h2 -> net2: reply from r1 (not dropping)"
+	ping_test_from $h2 255.255.255.255 198.51.100.1
+	log_test "h2 -> 255.255.255.255: reply from r1 (not forwarding)"
+	bc_forwarding_restore
+
+	bc_forwarding_enable
+	log_info "bc_forwarding enabled on r1 =>"
+	ping_test_from $h1 198.51.100.255 198.51.100.2
+	log_test "h1 -> net2: reply from h2 (forwarding)"
+	ping_test_from $h1 198.51.200.255 198.51.200.2
+	log_test "h1 -> net3: reply from h3 (forwarding)"
+	ping_test_from $h1 192.0.2.255 192.0.2.1 1
+	log_test "h1 -> net1: no reply (dropping)"
+	ping_test_from $h1 255.255.255.255 192.0.2.1
+	log_test "h1 -> 255.255.255.255: reply from r1 (not forwarding)"
+
+	ping_test_from $h2 192.0.2.255 192.0.2.2
+	log_test "h2 -> net1: reply from h1 (forwarding)"
+	ping_test_from $h2 198.51.200.255 198.51.200.2
+	log_test "h2 -> net3: reply from h3 (forwarding)"
+	ping_test_from $h2 198.51.100.255 198.51.100.1 1
+	log_test "h2 -> net2: no reply (dropping)"
+	ping_test_from $h2 255.255.255.255 198.51.100.1
+	log_test "h2 -> 255.255.255.255: reply from r1 (not forwarding)"
+	bc_forwarding_restore
+
+	sysctl_restore net.ipv4.icmp_echo_ignore_broadcasts
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS