ipv4: Reject routes specifying ECN bits in rtm_tos

Use the new dscp_t type to replace the fc_tos field of fib_config, to
ensure IPv4 routes aren't influenced by ECN bits when configured with
non-zero rtm_tos.

Before this patch, IPv4 routes specifying an rtm_tos with some of the
ECN bits set were accepted. However they wouldn't work (never match) as
IPv4 normally clears the ECN bits with IPTOS_RT_MASK before doing a FIB
lookup (although a few buggy code paths don't).

After this patch, IPv4 routes specifying an rtm_tos with any ECN bit
set is rejected.

Note: IPv6 routes ignore rtm_tos altogether, any rtm_tos is accepted,
but treated as if it were 0.

Signed-off-by: Guillaume Nault <gnault@redhat.com>
Acked-by: David Ahern <dsahern@kernel.org>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index c4297704bbcbaac0ad5da1675ae47dee1e133df4..6a82bcb8813bc9f4df936f073561864574ef22ce 100644 (file)
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -17,6 +17,7 @@
 #include <linux/rcupdate.h>
 #include <net/fib_notifier.h>
 #include <net/fib_rules.h>
+#include <net/inet_dscp.h>
 #include <net/inetpeer.h>
 #include <linux/percpu.h>
 #include <linux/notifier.h>
@@ -24,7 +25,7 @@
 
 struct fib_config {
        u8                      fc_dst_len;
-       u8                      fc_tos;
+       dscp_t                  fc_dscp;
        u8                      fc_protocol;
        u8                      fc_scope;
        u8                      fc_type;

diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 4d61ddd8a0ecfc4cc47b4802eb5a573beb84ee44..c60e1d1ed2b0a373c0b21e250ef97bb03d92b777 100644 (file)
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -32,6 +32,7 @@
 #include <linux/list.h>
 #include <linux/slab.h>
 
+#include <net/inet_dscp.h>
 #include <net/ip.h>
 #include <net/protocol.h>
 #include <net/route.h>
@@ -735,8 +736,16 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
        memset(cfg, 0, sizeof(*cfg));
 
        rtm = nlmsg_data(nlh);
+
+       if (!inet_validate_dscp(rtm->rtm_tos)) {
+               NL_SET_ERR_MSG(extack,
+                              "Invalid dsfield (tos): ECN bits must be 0");
+               err = -EINVAL;
+               goto errout;
+       }
+       cfg->fc_dscp = inet_dsfield_to_dscp(rtm->rtm_tos);
+
        cfg->fc_dst_len = rtm->rtm_dst_len;
-       cfg->fc_tos = rtm->rtm_tos;
        cfg->fc_table = rtm->rtm_table;
        cfg->fc_protocol = rtm->rtm_protocol;
        cfg->fc_scope = rtm->rtm_scope;

diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 8060524f425667d008470c2826f2ac835c8e25d2..d937eeebb812c85f0468b3c06f998b1c07c5847e 100644 (file)
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -61,6 +61,7 @@
 #include <linux/vmalloc.h>
 #include <linux/notifier.h>
 #include <net/net_namespace.h>
+#include <net/inet_dscp.h>
 #include <net/ip.h>
 #include <net/protocol.h>
 #include <net/route.h>
@@ -1210,9 +1211,9 @@ int fib_table_insert(struct net *net, struct fib_table *tb,
        struct fib_info *fi;
        u8 plen = cfg->fc_dst_len;
        u8 slen = KEYLENGTH - plen;
-       u8 tos = cfg->fc_tos;
        u32 key;
        int err;
+       u8 tos;
 
        key = ntohl(cfg->fc_dst);
 
@@ -1227,6 +1228,7 @@ int fib_table_insert(struct net *net, struct fib_table *tb,
                goto err;
        }
 
+       tos = inet_dscp_to_dsfield(cfg->fc_dscp);
        l = fib_find_node(t, &tp, key);
        fa = l ? fib_find_alias(&l->leaf, slen, tos, fi->fib_priority,
                                tb->tb_id, false) : NULL;
@@ -1703,8 +1705,8 @@ int fib_table_delete(struct net *net, struct fib_table *tb,
        struct key_vector *l, *tp;
        u8 plen = cfg->fc_dst_len;
        u8 slen = KEYLENGTH - plen;
-       u8 tos = cfg->fc_tos;
        u32 key;
+       u8 tos;
 
        key = ntohl(cfg->fc_dst);
 
@@ -1715,6 +1717,7 @@ int fib_table_delete(struct net *net, struct fib_table *tb,
        if (!l)
                return -ESRCH;
 
+       tos = inet_dscp_to_dsfield(cfg->fc_dscp);
        fa = fib_find_alias(&l->leaf, slen, tos, 0, tb->tb_id, false);
        if (!fa)
                return -ESRCH;

diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index 996af1ae3d3ddb4cf4f97eb0dec71c9b99c007f2..bb73235976b37bcb729f56e7ca7dcc38c99d161a 100755 (executable)
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -1447,6 +1447,81 @@ ipv4_local_rt_cache()
        log_test $? 0 "Cached route removed from VRF port device"
 }
 
+ipv4_rt_dsfield()
+{
+       echo
+       echo "IPv4 route with dsfield tests"
+
+       run_cmd "$IP route flush 172.16.102.0/24"
+
+       # New routes should reject dsfield options that interfere with ECN
+       run_cmd "$IP route add 172.16.102.0/24 dsfield 0x01 via 172.16.101.2"
+       log_test $? 2 "Reject route with dsfield 0x01"
+
+       run_cmd "$IP route add 172.16.102.0/24 dsfield 0x02 via 172.16.101.2"
+       log_test $? 2 "Reject route with dsfield 0x02"
+
+       run_cmd "$IP route add 172.16.102.0/24 dsfield 0x03 via 172.16.101.2"
+       log_test $? 2 "Reject route with dsfield 0x03"
+
+       # A generic route that doesn't take DSCP into account
+       run_cmd "$IP route add 172.16.102.0/24 via 172.16.101.2"
+
+       # A more specific route for DSCP 0x10
+       run_cmd "$IP route add 172.16.102.0/24 dsfield 0x10 via 172.16.103.2"
+
+       # 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"
+       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"
+       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"
+       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"
+       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"
+       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"
+       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"
+       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"
+       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"
+       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"
+       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"
+       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"
+       log_test $? 0 "IPv4 route with no DSCP and ECN:CE"
+}
+
 ipv4_route_test()
 {
        route_setup
@@ -1454,6 +1529,7 @@ ipv4_route_test()
        ipv4_rt_add
        ipv4_rt_replace
        ipv4_local_rt_cache
+       ipv4_rt_dsfield
 
        route_cleanup
 }