From 338bb57e4c2a1c2c6fc92f9c0bd35be7587adca7 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Mon, 15 Jul 2024 17:23:53 +0300 Subject: [PATCH 1/2] ipv4: Fix incorrect TOS in route get reply The TOS value that is returned to user space in the route get reply is the one with which the lookup was performed ('fl4->flowi4_tos'). This is fine when the matched route is configured with a TOS as it would not match if its TOS value did not match the one with which the lookup was performed. However, matching on TOS is only performed when the route's TOS is not zero. It is therefore possible to have the kernel incorrectly return a non-zero TOS: # ip link add name dummy1 up type dummy # ip address add 192.0.2.1/24 dev dummy1 # ip route get 192.0.2.2 tos 0xfc 192.0.2.2 tos 0x1c dev dummy1 src 192.0.2.1 uid 0 cache Fix by adding a DSCP field to the FIB result structure (inside an existing 4 bytes hole), populating it in the route lookup and using it when filling the route get reply. Output after the patch: # ip link add name dummy1 up type dummy # ip address add 192.0.2.1/24 dev dummy1 # ip route get 192.0.2.2 tos 0xfc 192.0.2.2 dev dummy1 src 192.0.2.1 uid 0 cache Fixes: 1a00fee4ffb2 ("ipv4: Remove rt_key_{src,dst,tos} from struct rtable.") Signed-off-by: Ido Schimmel Reviewed-by: David Ahern Reviewed-by: Guillaume Nault Signed-off-by: Paolo Abeni --- include/net/ip_fib.h | 1 + net/ipv4/fib_trie.c | 1 + net/ipv4/route.c | 14 +++++++------- 3 files changed, 9 insertions(+), 7 deletions(-) diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 6e7984bfb986..72af2f223e59 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -173,6 +173,7 @@ struct fib_result { unsigned char type; unsigned char scope; u32 tclassid; + dscp_t dscp; struct fib_nh_common *nhc; struct fib_info *fi; struct fib_table *table; diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index f474106464d2..8f30e3f00b7f 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1629,6 +1629,7 @@ int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp, res->nhc = nhc; res->type = fa->fa_type; res->scope = fi->fib_scope; + res->dscp = fa->fa_dscp; res->fi = fi; res->table = tb; res->fa_head = &n->leaf; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 54512acbead7..82b8fe8faeb7 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2867,9 +2867,9 @@ EXPORT_SYMBOL_GPL(ip_route_output_flow); /* called with rcu_read_lock held */ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, - struct rtable *rt, u32 table_id, struct flowi4 *fl4, - struct sk_buff *skb, u32 portid, u32 seq, - unsigned int flags) + struct rtable *rt, u32 table_id, dscp_t dscp, + struct flowi4 *fl4, struct sk_buff *skb, u32 portid, + u32 seq, unsigned int flags) { struct rtmsg *r; struct nlmsghdr *nlh; @@ -2885,7 +2885,7 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, r->rtm_family = AF_INET; r->rtm_dst_len = 32; r->rtm_src_len = 0; - r->rtm_tos = fl4 ? fl4->flowi4_tos : 0; + r->rtm_tos = inet_dscp_to_dsfield(dscp); r->rtm_table = table_id < 256 ? table_id : RT_TABLE_COMPAT; if (nla_put_u32(skb, RTA_TABLE, table_id)) goto nla_put_failure; @@ -3035,7 +3035,7 @@ static int fnhe_dump_bucket(struct net *net, struct sk_buff *skb, goto next; err = rt_fill_info(net, fnhe->fnhe_daddr, 0, rt, - table_id, NULL, skb, + table_id, 0, NULL, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, flags); if (err) @@ -3358,8 +3358,8 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, err = fib_dump_info(skb, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, RTM_NEWROUTE, &fri, 0); } else { - err = rt_fill_info(net, dst, src, rt, table_id, &fl4, skb, - NETLINK_CB(in_skb).portid, + err = rt_fill_info(net, dst, src, rt, table_id, res.dscp, &fl4, + skb, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, 0); } if (err < 0) From f036e68212c11e5a7edbb59b5e25299341829485 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Mon, 15 Jul 2024 17:23:54 +0300 Subject: [PATCH 2/2] ipv4: Fix incorrect TOS in fibmatch route get reply The TOS value that is returned to user space in the route get reply is the one with which the lookup was performed ('fl4->flowi4_tos'). This is fine when the matched route is configured with a TOS as it would not match if its TOS value did not match the one with which the lookup was performed. However, matching on TOS is only performed when the route's TOS is not zero. It is therefore possible to have the kernel incorrectly return a non-zero TOS: # ip link add name dummy1 up type dummy # ip address add 192.0.2.1/24 dev dummy1 # ip route get fibmatch 192.0.2.2 tos 0xfc 192.0.2.0/24 tos 0x1c dev dummy1 proto kernel scope link src 192.0.2.1 Fix by instead returning the DSCP field from the FIB result structure which was populated during the route lookup. Output after the patch: # ip link add name dummy1 up type dummy # ip address add 192.0.2.1/24 dev dummy1 # ip route get fibmatch 192.0.2.2 tos 0xfc 192.0.2.0/24 dev dummy1 proto kernel scope link src 192.0.2.1 Extend the existing selftests to not only verify that the correct route is returned, but that it is also returned with correct "tos" value (or without it). Fixes: b61798130f1b ("net: ipv4: RTM_GETROUTE: return matched fib result when requested") Signed-off-by: Ido Schimmel Reviewed-by: David Ahern Reviewed-by: Guillaume Nault Signed-off-by: Paolo Abeni --- net/ipv4/route.c | 2 +- tools/testing/selftests/net/fib_tests.sh | 24 ++++++++++++------------ 2 files changed, 13 insertions(+), 13 deletions(-) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 82b8fe8faeb7..5090912533d6 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -3331,7 +3331,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, fri.tb_id = table_id; fri.dst = res.prefix; fri.dst_len = res.prefixlen; - fri.dscp = inet_dsfield_to_dscp(fl4.flowi4_tos); + fri.dscp = res.dscp; fri.type = rt->rt_type; fri.offload = 0; fri.trap = 0; diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 73895711cdf4..5f3c28fc8624 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -1737,53 +1737,53 @@ ipv4_rt_dsfield() # DSCP 0x10 should match the specific route, no matter the ECN bits $IP route get fibmatch 172.16.102.1 dsfield 0x10 | \ - grep -q "via 172.16.103.2" + grep -q "172.16.102.0/24 tos 0x10 via 172.16.103.2" log_test $? 0 "IPv4 route with DSCP and ECN:Not-ECT" $IP route get fibmatch 172.16.102.1 dsfield 0x11 | \ - grep -q "via 172.16.103.2" + grep -q "172.16.102.0/24 tos 0x10 via 172.16.103.2" log_test $? 0 "IPv4 route with DSCP and ECN:ECT(1)" $IP route get fibmatch 172.16.102.1 dsfield 0x12 | \ - grep -q "via 172.16.103.2" + grep -q "172.16.102.0/24 tos 0x10 via 172.16.103.2" log_test $? 0 "IPv4 route with DSCP and ECN:ECT(0)" $IP route get fibmatch 172.16.102.1 dsfield 0x13 | \ - grep -q "via 172.16.103.2" + grep -q "172.16.102.0/24 tos 0x10 via 172.16.103.2" log_test $? 0 "IPv4 route with DSCP and ECN:CE" # Unknown DSCP should match the generic route, no matter the ECN bits $IP route get fibmatch 172.16.102.1 dsfield 0x14 | \ - grep -q "via 172.16.101.2" + grep -q "172.16.102.0/24 via 172.16.101.2" log_test $? 0 "IPv4 route with unknown DSCP and ECN:Not-ECT" $IP route get fibmatch 172.16.102.1 dsfield 0x15 | \ - grep -q "via 172.16.101.2" + grep -q "172.16.102.0/24 via 172.16.101.2" log_test $? 0 "IPv4 route with unknown DSCP and ECN:ECT(1)" $IP route get fibmatch 172.16.102.1 dsfield 0x16 | \ - grep -q "via 172.16.101.2" + grep -q "172.16.102.0/24 via 172.16.101.2" log_test $? 0 "IPv4 route with unknown DSCP and ECN:ECT(0)" $IP route get fibmatch 172.16.102.1 dsfield 0x17 | \ - grep -q "via 172.16.101.2" + grep -q "172.16.102.0/24 via 172.16.101.2" log_test $? 0 "IPv4 route with unknown DSCP and ECN:CE" # Null DSCP should match the generic route, no matter the ECN bits $IP route get fibmatch 172.16.102.1 dsfield 0x00 | \ - grep -q "via 172.16.101.2" + grep -q "172.16.102.0/24 via 172.16.101.2" log_test $? 0 "IPv4 route with no DSCP and ECN:Not-ECT" $IP route get fibmatch 172.16.102.1 dsfield 0x01 | \ - grep -q "via 172.16.101.2" + grep -q "172.16.102.0/24 via 172.16.101.2" log_test $? 0 "IPv4 route with no DSCP and ECN:ECT(1)" $IP route get fibmatch 172.16.102.1 dsfield 0x02 | \ - grep -q "via 172.16.101.2" + grep -q "172.16.102.0/24 via 172.16.101.2" log_test $? 0 "IPv4 route with no DSCP and ECN:ECT(0)" $IP route get fibmatch 172.16.102.1 dsfield 0x03 | \ - grep -q "via 172.16.101.2" + grep -q "172.16.102.0/24 via 172.16.101.2" log_test $? 0 "IPv4 route with no DSCP and ECN:CE" }