Skip to contentSkip to conversation

route: add support and selftests for directed broadcast forwarding

PATCH Superseded Xin Long 4 participants 20 messages Jul 2, 2018 – Jul 7, 2018

Subsystems (4)

v2 of 4 Superseded Latest is v4 →

lore
Share & tools
lore

Xin Long

author
#0 lore raw

v2 cover 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.

Xin Long (2):
route: add support for directed broadcast forwarding
selftests: add a selftest for directed broadcast forwarding

 include/linux/inetdevice.h                         |   1 +
 include/uapi/linux/ip.h                            |   1 +
 include/uapi/linux/netconf.h                       |   1 +
 net/ipv4/devinet.c                                 |  11 ++
 net/ipv4/route.c                                   |   6 +-
 .../selftests/net/forwarding/router_broadcast.sh   | 142 +++++++++++++++++++++
 6 files changed, 161 insertions(+), 1 deletion(-)
 create mode 100755 tools/testing/selftests/net/forwarding/router_broadcast.sh
Signature · 1 line
2.1.0
author
#1 lore raw

PATCH v2 1/2 route: add support for directed broadcast forwarding

This patch implements the feature described in rfc1812#section-5.3.5.2 and rfc2644. It allows the router to forward directed broadcast when sysctl bc_forwarding is enabled.

Note that this feature could be done by iptables -j TEE, but it would cause some problems:
- target TEE's gateway param has to be set with a specific address, and it's not flexible especially when the route wants forward all directed broadcasts.
- this duplicates the directed broadcasts so this may cause side effects to applications.

Besides, to keep consistent with other os router like BSD, it's also necessary to implement it in the route rx path.

Note that route cache needs to be flushed when bc_forwarding is changed.

---
 include/linux/inetdevice.h   |  1 +
 include/uapi/linux/ip.h      |  1 +
 include/uapi/linux/netconf.h |  1 +
 net/ipv4/devinet.c           | 11 +++++++++++
 net/ipv4/route.c             |  6 +++++-
 5 files changed, 19 insertions(+), 1 deletion(-)
include/linux/inetdevice.h +1 -0
index 27650f1..c759d1c 100644
@@ -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), \
include/uapi/linux/ip.h +1 -0
index b24a742..e42d13b 100644
@@ -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
 };
 
include/uapi/linux/netconf.h +1 -0
index c84fcdf..fac4edd 100644
@@ -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)
net/ipv4/devinet.c +11 -0
index d7585ab..80cb464 100644
@@ -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"),
net/ipv4/route.c +5 -1
index 1df6e97..b678466 100644
@@ -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;
 
Signature · 1 line
2.1.0
author
#2 lore raw

PATCH v2 2/2 selftests: add a selftest for directed broadcast forwarding

As Ido's suggestion, this patch is to add a selftest for directed broadcast forwarding with vrf. Just note that it puts the h2 into the main route space, so that ping_test could get echo_reply.

---
 .../selftests/net/forwarding/router_broadcast.sh   | 142 +++++++++++++++++++++
 1 file changed, 142 insertions(+)
 create mode 100755 tools/testing/selftests/net/forwarding/router_broadcast.sh
tools/testing/selftests/net/forwarding/router_broadcast.sh new file +142 -0
new file mode 100755
index 0000000..6917768
@@ -0,0 +1,142 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS="ping_ipv4"
+NUM_NETIFS=4
+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
+}
+
+h1_destroy()
+{
+	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()
+{
+	ip link set dev $h2 up
+
+	ip address add 198.51.100.2/24 dev $h2
+	ip route add 192.0.2.0/24 dev $h2 via 198.51.100.1
+}
+
+h2_destroy()
+{
+	ip route del 192.0.2.0/24 dev $h2 via 198.51.100.1
+	ip address del 198.51.100.2/24 dev $h2
+
+	ip link set dev $h2 down
+}
+
+router_create()
+{
+	vrf_create "vrf-r1"
+	ip link set dev $rp1 master vrf-r1
+	ip link set dev $rp2 master vrf-r1
+
+	ip link set dev vrf-r1 up
+	ip link set dev $rp1 up
+	ip link set dev $rp2 up
+
+	ip address add 192.0.2.1/24 dev $rp1
+	ip address add 198.51.100.1/24 dev $rp2
+}
+
+router_destroy()
+{
+	ip address del 198.51.100.1/24 dev $rp2
+	ip address del 192.0.2.1/24 dev $rp1
+
+	ip link set dev $rp2 down
+	ip link set dev $rp1 down
+	vrf_destroy "vrf-r1"
+}
+
+bc_forwarding_disable()
+{
+	sysctl_set net.ipv4.conf.all.bc_forwarding 0
+	sysctl_set net.ipv4.conf.$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
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	rp1=${NETIFS[p2]}
+
+	rp2=${NETIFS[p3]}
+	h2=${NETIFS[p4]}
+
+	vrf_prepare
+
+	h1_create
+	h2_create
+
+	router_create
+
+	forwarding_enable
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	forwarding_restore
+
+	router_destroy
+
+	h2_destroy
+	h1_destroy
+
+	vrf_cleanup
+}
+
+ping_ipv4()
+{
+	sysctl_set net.ipv4.icmp_echo_ignore_broadcasts 0
+	bc_forwarding_disable
+	ping_test $h1 198.51.100.255
+
+	iptables -A INPUT -i vrf-r1 -p icmp -j DROP
+	bc_forwarding_restore
+	bc_forwarding_enable
+	ping_test $h1 198.51.100.255
+
+	bc_forwarding_restore
+	iptables -D INPUT -i vrf-r1 -p icmp -j DROP
+	sysctl_restore net.ipv4.icmp_echo_ignore_broadcasts
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
Signature · 1 line
2.1.0
#3 lore raw

Re: [PATCHv2 net-next 2/2] selftests: add a selftest for directed broadcast forwarding

Quoted 5 lines · Xin Long
tools/testing/selftests/net/forwarding/router_broadcast.sh new file +5 -0
+ping_ipv4()
+{
+	sysctl_set net.ipv4.icmp_echo_ignore_broadcasts 0
+	bc_forwarding_disable
+	ping_test $h1 198.51.100.255

tools/testing/selftests/net/forwarding/router_broadcast.sh line 133

Quoted 10 lines
tools/testing/selftests/net/forwarding/router_broadcast.sh new file +10 -0
+
+	iptables -A INPUT -i vrf-r1 -p icmp -j DROP
+	bc_forwarding_restore
+	bc_forwarding_enable
+	ping_test $h1 198.51.100.255
+
+	bc_forwarding_restore
+	iptables -D INPUT -i vrf-r1 -p icmp -j DROP
+	sysctl_restore net.ipv4.icmp_echo_ignore_broadcasts
+}

Both tests fail for me:
TEST: ping [FAIL]
TEST: ping [FAIL]

Why the need for the iptables rule?

And, PAUSE_ON_FAIL is not working to take a look at why tests are failing. e.g.,

PAUSE_ON_FAIL=yes ./router_broadcast.sh

just continues on. Might be something with the infrastructure scripts.

author
#4 lore raw

Re: [PATCHv2 net-next 2/2] selftests: add a selftest for directed broadcast forwarding

Quoted 12 lines · David Ahern
Quoted 11 lines · Xin Long
tools/testing/selftests/net/forwarding/router_broadcast.sh new file +11 -0
+ping_ipv4()
+{
+     sysctl_set net.ipv4.icmp_echo_ignore_broadcasts 0
+     bc_forwarding_disable
+     ping_test $h1 198.51.100.255
+
+     iptables -A INPUT -i vrf-r1 -p icmp -j DROP
+     bc_forwarding_restore
+     bc_forwarding_enable
+     ping_test $h1 198.51.100.255
+
Quoted 8 lines

tools/testing/selftests/net/forwarding/router_broadcast.sh line 133

Quoted 4 lines
tools/testing/selftests/net/forwarding/router_broadcast.sh new file +4 -0
+     bc_forwarding_restore
+     iptables -D INPUT -i vrf-r1 -p icmp -j DROP
+     sysctl_restore net.ipv4.icmp_echo_ignore_broadcasts
+}

Both tests fail for me:
TEST: ping [FAIL]
TEST: ping [FAIL]

I think 'ip vrf exec ...' is not working in your env, while the testing is using "ip vrf exec vrf-h1 ping ..."

You can test it by:

# ip link add dev vrf-test type vrf table 1111
# ip vrf exec vrf-test ls
Quoted 2 lines

Why the need for the iptables rule?

This iptables rule is to block the echo_request packet going to route's local_in.
When bc_forwarding is NOT doing forwarding well but the packet goes to the route's local_in, it will fail.

Without this rule, the 2nd ping will always succeed, we can't tell the echo_reply is from route or h2.

Or you have a better way to test this?

Quoted 7 lines

And, PAUSE_ON_FAIL is not working to take a look at why tests are failing. e.g.,

PAUSE_ON_FAIL=yes ./router_broadcast.sh

just continues on. Might be something with the infrastructure scripts.

Yes, in ./router_broadcast.sh, it loads lib.sh where it loads forwarding.config where it has "PAUSE_ON_FAIL=no", which would override your "PAUSE_ON_FAIL=yes".

#5 lore raw

Re: [PATCHv2 net-next 2/2] selftests: add a selftest for directed broadcast forwarding

Quoted 21 lines · Xin Long
Quoted 12 lines · David Ahern
Quoted 11 lines · Xin Long
tools/testing/selftests/net/forwarding/router_broadcast.sh new file +11 -0
+ping_ipv4()
+{
+     sysctl_set net.ipv4.icmp_echo_ignore_broadcasts 0
+     bc_forwarding_disable
+     ping_test $h1 198.51.100.255
+
+     iptables -A INPUT -i vrf-r1 -p icmp -j DROP
+     bc_forwarding_restore
+     bc_forwarding_enable
+     ping_test $h1 198.51.100.255
+
Quoted 8 lines

tools/testing/selftests/net/forwarding/router_broadcast.sh line 133

Quoted 4 lines
tools/testing/selftests/net/forwarding/router_broadcast.sh new file +4 -0
+     bc_forwarding_restore
+     iptables -D INPUT -i vrf-r1 -p icmp -j DROP
+     sysctl_restore net.ipv4.icmp_echo_ignore_broadcasts
+}

Both tests fail for me:
TEST: ping [FAIL]
TEST: ping [FAIL]

Quoted 6 lines

I think 'ip vrf exec ...' is not working in your env, while the testing is using "ip vrf exec vrf-h1 ping ..."

You can test it by:

# ip link add dev vrf-test type vrf table 1111
# ip vrf exec vrf-test ls

well, that's embarrassing. yes, I updated ip and forgot to apply the bpf workaround to define the syscall number (not defined in jessie).

Quoted 8 lines
Quoted 3 lines

Why the need for the iptables rule?

This iptables rule is to block the echo_request packet going to route's local_in.
When bc_forwarding is NOT doing forwarding well but the packet goes to the route's local_in, it will fail.

Quoted 4 lines

Without this rule, the 2nd ping will always succeed, we can't tell the echo_reply is from route or h2.

Or you have a better way to test this?

your commands are not a proper test. The test should succeed and fail based on the routing lookup, not iptables rules.

Quoted 5 lines
Quoted 5 lines

And, PAUSE_ON_FAIL is not working to take a look at why tests are failing. e.g.,

Quoted 7 lines
Quoted 3 lines

PAUSE_ON_FAIL=yes ./router_broadcast.sh

just continues on. Might be something with the infrastructure scripts.

Yes, in ./router_broadcast.sh, it loads lib.sh where it loads forwarding.config where it has "PAUSE_ON_FAIL=no", which would override your "PAUSE_ON_FAIL=yes".

ack. bit by that as well.

author
#6 lore raw

Re: [PATCHv2 net-next 2/2] selftests: add a selftest for directed broadcast forwarding

Quoted 40 lines · David Ahern
Quoted 21 lines · Xin Long
Quoted 12 lines · David Ahern
Quoted 11 lines · Xin Long
tools/testing/selftests/net/forwarding/router_broadcast.sh new file +11 -0
+ping_ipv4()
+{
+     sysctl_set net.ipv4.icmp_echo_ignore_broadcasts 0
+     bc_forwarding_disable
+     ping_test $h1 198.51.100.255
+
+     iptables -A INPUT -i vrf-r1 -p icmp -j DROP
+     bc_forwarding_restore
+     bc_forwarding_enable
+     ping_test $h1 198.51.100.255
+
Quoted 8 lines

tools/testing/selftests/net/forwarding/router_broadcast.sh line 133

Quoted 4 lines
tools/testing/selftests/net/forwarding/router_broadcast.sh new file +4 -0
+     bc_forwarding_restore
+     iptables -D INPUT -i vrf-r1 -p icmp -j DROP
+     sysctl_restore net.ipv4.icmp_echo_ignore_broadcasts
+}

Both tests fail for me:
TEST: ping [FAIL]
TEST: ping [FAIL]

Quoted 6 lines

I think 'ip vrf exec ...' is not working in your env, while the testing is using "ip vrf exec vrf-h1 ping ..."

You can test it by:

# ip link add dev vrf-test type vrf table 1111
# ip vrf exec vrf-test ls

well, that's embarrassing. yes, I updated ip and forgot to apply the bpf workaround to define the syscall number (not defined in jessie).

Quoted 8 lines
Quoted 3 lines

Why the need for the iptables rule?

This iptables rule is to block the echo_request packet going to route's local_in.
When bc_forwarding is NOT doing forwarding well but the packet goes to the route's local_in, it will fail.

Quoted 7 lines
Quoted 4 lines

Without this rule, the 2nd ping will always succeed, we can't tell the echo_reply is from route or h2.

Or you have a better way to test this?

your commands are not a proper test. The test should succeed and fail based on the routing lookup, not iptables rules.

A proper test can be done easily with netns, as vrf can't isolate much. I don't want to bother forwarding/ directory with netns, so I will probably just drop this selftest, and let the feature patch go first.

What do you think?

Quoted 15 lines
Quoted 6 lines
Quoted 6 lines

And, PAUSE_ON_FAIL is not working to take a look at why tests are failing. e.g.,

Quoted 7 lines
Quoted 3 lines

PAUSE_ON_FAIL=yes ./router_broadcast.sh

just continues on. Might be something with the infrastructure scripts.

Yes, in ./router_broadcast.sh, it loads lib.sh where it loads forwarding.config where it has "PAUSE_ON_FAIL=no", which would override your "PAUSE_ON_FAIL=yes".

ack. bit by that as well.

#7 lore raw

Re: [PATCHv2 net-next 2/2] selftests: add a selftest for directed broadcast forwarding

Quoted 6 lines · Xin Long

A proper test can be done easily with netns, as vrf can't isolate much. I don't want to bother forwarding/ directory with netns, so I will probably just drop this selftest, and let the feature patch go first.

What do you think?

I think I would like to see a proper test case for this.

If it does not fit the model that Ido and others are using under the forwarding directory, then how about one in tools/testing/selftests/net then.

#8 lore raw

Re: [PATCHv2 net-next 2/2] selftests: add a selftest for directed broadcast forwarding

In reply to Xin Long
Quoted 6 lines · Xin Long
Quoted 2 lines

your commands are not a proper test. The test should succeed and fail based on the routing lookup, not iptables rules.

A proper test can be done easily with netns, as vrf can't isolate much. I don't want to bother forwarding/ directory with netns, so I will probably just drop this selftest, and let the feature patch go first.

BTW, VRF isolates at the routing layer and this is a routing change. We need to understand why it does not work with VRF. Perhaps another tweak is needed for VRF.

author
#9 lore raw

Re: [PATCHv2 net-next 2/2] selftests: add a selftest for directed broadcast forwarding

Quoted 4 lines · David Ahern
Quoted 2 lines · Xin Long
Quoted 2 lines

your commands are not a proper test. The test should succeed and fail based on the routing lookup, not iptables rules.

Quoted 8 lines
Quoted 4 lines

A proper test can be done easily with netns, as vrf can't isolate much. I don't want to bother forwarding/ directory with netns, so I will probably just drop this selftest, and let the feature patch go first.

BTW, VRF isolates at the routing layer and this is a routing change. We need to understand why it does not work with VRF. Perhaps another tweak is needed for VRF.

One problem was that the peer may not use the address on the dev that echo_request comes from as the src IP of echo_reply when the echo_request's dst IP is broadcast, but try to get another one by looking up a route without ".flowi4_oif" set. See:

icmp_reply()->fib_compute_spec_dst():

                struct flowi4 fl4 = {
                        .flowi4_iif = LOOPBACK_IFINDEX,
                        .daddr = ip_hdr(skb)->saddr,
                        .flowi4_tos = RT_TOS(ip_hdr(skb)->tos),
                        .flowi4_scope = scope,
                        .flowi4_mark = IN_DEV_SRC_VMARK(in_dev) ? skb->mark : 0,
                };
                if (!fib_lookup(net, &fl4, &res, 0))
                        return FIB_RES_PREFSRC(net, res);

Without ".flowi4_oif" set, it won't match the vrf route. That's why I had to make h2 NOT into a vrf so that h1 can get the echo_reply. But it can't tell if this echo_reply is from h2 or r1, as r1's echo_reply will also use the same src IP which is actually got from main route space as ".flowi4_oif" is not set.
(hope I this description is clear to you) :)

So i'm not sure if we can do any tweak for VRF.

#10 lore raw

Re: [PATCHv2 net-next 2/2] selftests: add a selftest for directed broadcast forwarding

Quoted 30 lines · Xin Long
Quoted 4 lines · David Ahern
Quoted 2 lines · Xin Long
Quoted 2 lines

your commands are not a proper test. The test should succeed and fail based on the routing lookup, not iptables rules.

Quoted 8 lines
Quoted 4 lines

A proper test can be done easily with netns, as vrf can't isolate much. I don't want to bother forwarding/ directory with netns, so I will probably just drop this selftest, and let the feature patch go first.

BTW, VRF isolates at the routing layer and this is a routing change. We need to understand why it does not work with VRF. Perhaps another tweak is needed for VRF.

One problem was that the peer may not use the address on the dev that echo_request comes from as the src IP of echo_reply when the echo_request's dst IP is broadcast, but try to get another one by looking up a route without ".flowi4_oif" set. See:

icmp_reply()->fib_compute_spec_dst():

                struct flowi4 fl4 = {
                        .flowi4_iif = LOOPBACK_IFINDEX,
                        .daddr = ip_hdr(skb)->saddr,
                        .flowi4_tos = RT_TOS(ip_hdr(skb)->tos),
                        .flowi4_scope = scope,
                        .flowi4_mark = IN_DEV_SRC_VMARK(in_dev) ? skb->mark : 0,
                };
                if (!fib_lookup(net, &fl4, &res, 0))
                        return FIB_RES_PREFSRC(net, res);
Quoted 9 lines

Without ".flowi4_oif" set, it won't match the vrf route. That's why I had to make h2 NOT into a vrf so that h1 can get the echo_reply. But it can't tell if this echo_reply is from h2 or r1, as r1's echo_reply will also use the same src IP which is actually got from main route space as ".flowi4_oif" is not set.
(hope I this description is clear to you) :)

So i'm not sure if we can do any tweak for VRF.

Try this:

net/ipv4/fib_frontend.c +1 -0
index b21833651394..e46cdd310e5f 100644
@@ -300,6 +300,7 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb)
        if (!ipv4_is_zeronet(ip_hdr(skb)->saddr)) {
                struct flowi4 fl4 = {
                        .flowi4_iif = LOOPBACK_IFINDEX,
+                       .flowi4_oif = l3mdev_master_ifindex_rcu(dev),
                        .daddr = ip_hdr(skb)->saddr,
                        .flowi4_tos = RT_TOS(ip_hdr(skb)->tos),
                        .flowi4_scope = scope,
author
#11 lore raw

Re: [PATCHv2 net-next 2/2] selftests: add a selftest for directed broadcast forwarding

Quoted 48 lines · David Ahern
Quoted 30 lines · Xin Long
Quoted 4 lines · David Ahern
Quoted 2 lines · Xin Long
Quoted 2 lines

your commands are not a proper test. The test should succeed and fail based on the routing lookup, not iptables rules.

Quoted 8 lines
Quoted 4 lines

A proper test can be done easily with netns, as vrf can't isolate much. I don't want to bother forwarding/ directory with netns, so I will probably just drop this selftest, and let the feature patch go first.

BTW, VRF isolates at the routing layer and this is a routing change. We need to understand why it does not work with VRF. Perhaps another tweak is needed for VRF.

One problem was that the peer may not use the address on the dev that echo_request comes from as the src IP of echo_reply when the echo_request's dst IP is broadcast, but try to get another one by looking up a route without ".flowi4_oif" set. See:

icmp_reply()->fib_compute_spec_dst():

                struct flowi4 fl4 = {
                        .flowi4_iif = LOOPBACK_IFINDEX,
                        .daddr = ip_hdr(skb)->saddr,
                        .flowi4_tos = RT_TOS(ip_hdr(skb)->tos),
                        .flowi4_scope = scope,
                        .flowi4_mark = IN_DEV_SRC_VMARK(in_dev) ? skb->mark : 0,
                };
                if (!fib_lookup(net, &fl4, &res, 0))
                        return FIB_RES_PREFSRC(net, res);
Quoted 9 lines

Without ".flowi4_oif" set, it won't match the vrf route. That's why I had to make h2 NOT into a vrf so that h1 can get the echo_reply. But it can't tell if this echo_reply is from h2 or r1, as r1's echo_reply will also use the same src IP which is actually got from main route space as ".flowi4_oif" is not set.
(hope I this description is clear to you) :)

So i'm not sure if we can do any tweak for VRF.

Try this:

net/ipv4/fib_frontend.c +0 -0
index b21833651394..e46cdd310e5f 100644

net/ipv4/fib_frontend.c __be32 fib_compute_spec_dst(struct sk_buff *skb) · line 306

Quoted 7 lines
net/ipv4/fib_frontend.c +1 -0
@@ -300,6 +300,7 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb)
        if (!ipv4_is_zeronet(ip_hdr(skb)->saddr)) {
                struct flowi4 fl4 = {
                        .flowi4_iif = LOOPBACK_IFINDEX,
+                       .flowi4_oif = l3mdev_master_ifindex_rcu(dev),
                        .daddr = ip_hdr(skb)->saddr,
                        .flowi4_tos = RT_TOS(ip_hdr(skb)->tos),
                        .flowi4_scope = scope,

Great, with your fix, I can extend more for this selftest. but I hope no side effects would be caused.

Thank you.

author
#12 lore raw

Re: [PATCHv2 net-next 2/2] selftests: add a selftest for directed broadcast forwarding

Quoted 44 lines · Xin Long
Quoted 43 lines · David Ahern
Quoted 30 lines · Xin Long
Quoted 4 lines · David Ahern
Quoted 2 lines · Xin Long
Quoted 2 lines

your commands are not a proper test. The test should succeed and fail based on the routing lookup, not iptables rules.

Quoted 8 lines
Quoted 4 lines

A proper test can be done easily with netns, as vrf can't isolate much. I don't want to bother forwarding/ directory with netns, so I will probably just drop this selftest, and let the feature patch go first.

BTW, VRF isolates at the routing layer and this is a routing change. We need to understand why it does not work with VRF. Perhaps another tweak is needed for VRF.

One problem was that the peer may not use the address on the dev that echo_request comes from as the src IP of echo_reply when the echo_request's dst IP is broadcast, but try to get another one by looking up a route without ".flowi4_oif" set. See:

icmp_reply()->fib_compute_spec_dst():

                struct flowi4 fl4 = {
                        .flowi4_iif = LOOPBACK_IFINDEX,
                        .daddr = ip_hdr(skb)->saddr,
                        .flowi4_tos = RT_TOS(ip_hdr(skb)->tos),
                        .flowi4_scope = scope,
                        .flowi4_mark = IN_DEV_SRC_VMARK(in_dev) ? skb->mark : 0,
                };
                if (!fib_lookup(net, &fl4, &res, 0))
                        return FIB_RES_PREFSRC(net, res);
Quoted 9 lines

Without ".flowi4_oif" set, it won't match the vrf route. That's why I had to make h2 NOT into a vrf so that h1 can get the echo_reply. But it can't tell if this echo_reply is from h2 or r1, as r1's echo_reply will also use the same src IP which is actually got from main route space as ".flowi4_oif" is not set.
(hope I this description is clear to you) :)

So i'm not sure if we can do any tweak for VRF.

Try this:

Quoted 12 lines

net/ipv4/fib_frontend.c __be32 fib_compute_spec_dst(struct sk_buff *skb) · line 306

Quoted 12 lines
net/ipv4/fib_frontend.c +1 -0
index b21833651394..e46cdd310e5f 100644
@@ -300,6 +300,7 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb)
        if (!ipv4_is_zeronet(ip_hdr(skb)->saddr)) {
                struct flowi4 fl4 = {
                        .flowi4_iif = LOOPBACK_IFINDEX,
+                       .flowi4_oif = l3mdev_master_ifindex_rcu(dev),
                        .daddr = ip_hdr(skb)->saddr,
                        .flowi4_tos = RT_TOS(ip_hdr(skb)->tos),
                        .flowi4_scope = scope,

If this patch can be applied, I would be able to make a proper selftest like:

...
ping_test_from()
{
local oif=$1
local dip=$2
local from=$3
local fail=$4

RET=0

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 $?
log_test "ping_test_from"
}

ping_ipv4()
{
sysctl_set net.ipv4.icmp_echo_ignore_broadcasts 0

bc_forwarding_disable
ping_test_from $h1 198.51.100.255 192.0.2.1 ping_test_from $h1 198.51.200.255 192.0.2.1 ping_test_from $h1 192.0.2.255 192.0.2.1 ping_test_from $h1 255.255.255.255 192.0.2.1

ping_test_from $h2 192.0.2.255 198.51.100.1 ping_test_from $h2 198.51.200.255 198.51.100.1 ping_test_from $h2 198.51.100.255 198.51.100.1 ping_test_from $h2 255.255.255.255 198.51.100.1 bc_forwarding_restore

bc_forwarding_enable
ping_test_from $h1 198.51.100.255 198.51.100.2 ping_test_from $h1 198.51.200.255 198.51.200.2 ping_test_from $h1 192.0.2.255 192.0.2.1 1 ping_test_from $h1 255.255.255.255 192.0.2.1

ping_test_from $h2 192.0.2.255 192.0.2.2 ping_test_from $h2 198.51.200.255 198.51.200.2 ping_test_from $h2 198.51.100.255 198.51.100.1 1 ping_test_from $h2 255.255.255.255 198.51.100.1 bc_forwarding_restore

sysctl_restore net.ipv4.icmp_echo_ignore_broadcasts }

Quoted 4 lines

Great, with your fix, I can extend more for this selftest. but I hope no side effects would be caused.

Thank you.

#13 lore raw

Re: [PATCHv2 net-next 2/2] selftests: add a selftest for directed broadcast forwarding

Quoted 15 lines · Xin Long
Quoted 14 lines
Quoted 7 lines

Try this:

net/ipv4/fib_frontend.c +0 -0
index b21833651394..e46cdd310e5f 100644

net/ipv4/fib_frontend.c __be32 fib_compute_spec_dst(struct sk_buff *skb) · line 306

Quoted 7 lines
net/ipv4/fib_frontend.c +1 -0
@@ -300,6 +300,7 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb)
        if (!ipv4_is_zeronet(ip_hdr(skb)->saddr)) {
                struct flowi4 fl4 = {
                        .flowi4_iif = LOOPBACK_IFINDEX,
+                       .flowi4_oif = l3mdev_master_ifindex_rcu(dev),
                        .daddr = ip_hdr(skb)->saddr,
                        .flowi4_tos = RT_TOS(ip_hdr(skb)->tos),
                        .flowi4_scope = scope,

If this patch can be applied, I would be able to make a proper selftest like:

Forgot to send the patch yesterday. Will do so sometime this weekend.

#14 lore raw

Re: [PATCHv2 net-next 2/2] selftests: add a selftest for directed broadcast forwarding

In reply to Xin Long
Quoted 8 lines · Xin Long
Quoted 2 lines · David Ahern

your commands are not a proper test. The test should succeed and fail based on the routing lookup, not iptables rules.

A proper test can be done easily with netns, as vrf can't isolate much. I don't want to bother forwarding/ directory with netns, so I will probably just drop this selftest, and let the feature patch go first.

What do you think?

You can add a tc rule on the ingress of h2 and make sure that in the first case ping succeeds and the tc rule wasn't hit. In the second case ping should also succeed, but the tc rule should be hit. This is similar to your original netns test.

You can look at tc_flower.sh for reference and in particular at tc_check_packets().

author
#15 lore raw

Re: [PATCHv2 net-next 2/2] selftests: add a selftest for directed broadcast forwarding

Quoted 8 lines · Ido Schimmel
Quoted 7 lines · Xin Long
Quoted 2 lines · David Ahern

your commands are not a proper test. The test should succeed and fail based on the routing lookup, not iptables rules.

A proper test can be done easily with netns, as vrf can't isolate much. I don't want to bother forwarding/ directory with netns, so I will probably just drop this selftest, and let the feature patch go first.

Quoted 6 lines
Quoted 1 line

What do you think?

You can add a tc rule on the ingress of h2 and make sure that in the first case ping succeeds and the tc rule wasn't hit. In the second case ping should also succeed, but the tc rule should be hit. This is similar to your original netns test.

With netns, it will be much easier to use
sysctl net.ipv4.icmp_echo_ignore_broadcasts
to block the echo_request on r1 or h2, and check if ping works. (this's more like the idea of using 'iptables' above) :D

Quoted 3 lines

You can look at tc_flower.sh for reference and in particular at tc_check_packets().

This is a way similar idea of using tcpdump, I just feel it's too much, this test should be an as simple test as route.sh. :)

author
#16 lore raw

Re: [PATCHv2 net-next 2/2] selftests: add a selftest for directed broadcast forwarding

Quoted 11 lines · Xin Long
Quoted 10 lines · Ido Schimmel
Quoted 8 lines · Xin Long
Quoted 2 lines · David Ahern

your commands are not a proper test. The test should succeed and fail based on the routing lookup, not iptables rules.

A proper test can be done easily with netns, as vrf can't isolate much. I don't want to bother forwarding/ directory with netns, so I will probably just drop this selftest, and let the feature patch go first.

What do you think?

Quoted 12 lines
Quoted 4 lines

You can add a tc rule on the ingress of h2 and make sure that in the first case ping succeeds and the tc rule wasn't hit. In the second case ping should also succeed, but the tc rule should be hit. This is similar to your original netns test.

With netns, it will be much easier to use
sysctl net.ipv4.icmp_echo_ignore_broadcasts
to block the echo_request on r1 or h2, and check if ping works. (this's more like the idea of using 'iptables' above) :D

Quoted 3 lines

You can look at tc_flower.sh for reference and in particular at tc_check_packets().

Just noticed this doesn't require reply with MZ. that's better. Thanks.

Quoted 2 lines

This is a way similar idea of using tcpdump, I just feel it's too much, this test should be an as simple test as route.sh. :)

Acked-by on v2 1/2
#17 lore raw

Re: [PATCHv2 net-next 1/2] route: add support for directed broadcast forwarding

In reply to Xin Long
Quoted 124 lines · Xin Long

This patch implements the feature described in rfc1812#section-5.3.5.2 and rfc2644. It allows the router to forward directed broadcast when sysctl bc_forwarding is enabled.

Note that this feature could be done by iptables -j TEE, but it would cause some problems:
- target TEE's gateway param has to be set with a specific address, and it's not flexible especially when the route wants forward all directed broadcasts.
- this duplicates the directed broadcasts so this may cause side effects to applications.

Besides, to keep consistent with other os router like BSD, it's also necessary to implement it in the route rx path.

Note that route cache needs to be flushed when bc_forwarding is changed.

---
 include/linux/inetdevice.h   |  1 +
 include/uapi/linux/ip.h      |  1 +
 include/uapi/linux/netconf.h |  1 +
 net/ipv4/devinet.c           | 11 +++++++++++
 net/ipv4/route.c             |  6 +++++-
 5 files changed, 19 insertions(+), 1 deletion(-)
include/linux/inetdevice.h +1 -0
index 27650f1..c759d1c 100644
@@ -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), \
include/uapi/linux/ip.h +1 -0
index b24a742..e42d13b 100644
@@ -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
 };
 
include/uapi/linux/netconf.h +1 -0
index c84fcdf..fac4edd 100644
@@ -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)
net/ipv4/devinet.c +11 -0
index d7585ab..80cb464 100644
@@ -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"),
net/ipv4/route.c +4 -1
index 1df6e97..b678466 100644
@@ -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,

net/ipv4/route.c static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, · line 2023

Quoted 7 lines
net/ipv4/route.c +1 -0
@@ -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;
 
#18 lore raw

Re: [PATCHv2 net-next 1/2] route: add support for directed broadcast forwarding

In reply to Xin Long

net/ipv4/devinet.c static int devinet_conf_proc(struct ctl_table *ctl, int write, · line 2155

Quoted 8 lines · Xin Long
net/ipv4/devinet.c +4 -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);
+

Shouldn't that be '&&' instead of '||' otherwise you are bumping the fib gen id any time the old and new values do not equal regardless of which setting is changed.

author
#19 lore raw

Re: [PATCHv2 net-next 1/2] route: add support for directed broadcast forwarding

Quoted 5 lines · David Ahern
Quoted 4 lines · Xin Long
net/ipv4/devinet.c +0 -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);
 
Quoted 8 lines

net/ipv4/devinet.c static int devinet_conf_proc(struct ctl_table *ctl, int write, · line 2155

Quoted 4 lines
net/ipv4/devinet.c +4 -0
+             if (i == IPV4_DEVCONF_BC_FORWARDING - 1 ||
+                 new_value != old_value)
+                     rt_cache_flush(net);
+

Shouldn't that be '&&' instead of '||' otherwise you are bumping the fib gen id any time the old and new values do not equal regardless of which setting is changed.

ah right, It's a copy-paste mistake, sorry