sctp: fix src address selection if using secondary addresses for ipv6

Commit 0ca50d12fe46 ("sctp: fix src address selection if using secondary
addresses") has fixed a src address selection issue when using secondary
addresses for ipv4.

Now sctp ipv6 also has the similar issue. When using a secondary address,
sctp_v6_get_dst tries to choose the saddr which has the most same bits
with the daddr by sctp_v6_addr_match_len. It may make some cases not work
as expected.

hostA:
  [1] fd21:356b:459a:cf10::11 (eth1)
  [2] fd21:356b:459a:cf20::11 (eth2)

hostB:
  [a] fd21:356b:459a:cf30::2  (eth1)
  [b] fd21:356b:459a:cf40::2  (eth2)

route from hostA to hostB:
  fd21:356b:459a:cf30::/64 dev eth1  metric 1024  mtu 1500

The expected path should be:
  fd21:356b:459a:cf10::11 <-> fd21:356b:459a:cf30::2
But addr[2] matches addr[a] more bits than addr[1] does, according to
sctp_v6_addr_match_len. It causes the path to be:
  fd21:356b:459a:cf20::11 <-> fd21:356b:459a:cf30::2

This patch is to fix it with the same way as Marcelo's fix for sctp ipv4.
As no ip_dev_find for ipv6, this patch is to use ipv6_chk_addr to check
if the saddr is in a dev instead.

Note that for backwards compatibility, it will still do the addr_match_len
check here when no optimal is found.

Reported-by: Patrick Talbert <ptalbert@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 961ee59f696a0b0a8b6c2bade0031a073dff53ad..142b70e959af9142ce35b88749ad2160327c8267 100644 (file)
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -240,12 +240,10 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
        struct sctp_bind_addr *bp;
        struct ipv6_pinfo *np = inet6_sk(sk);
        struct sctp_sockaddr_entry *laddr;
-       union sctp_addr *baddr = NULL;
        union sctp_addr *daddr = &t->ipaddr;
        union sctp_addr dst_saddr;
        struct in6_addr *final_p, final;
        __u8 matchlen = 0;
-       __u8 bmatchlen;
        sctp_scope_t scope;
 
        memset(fl6, 0, sizeof(struct flowi6));
@@ -312,23 +310,37 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
         */
        rcu_read_lock();
        list_for_each_entry_rcu(laddr, &bp->address_list, list) {
-               if (!laddr->valid)
+               struct dst_entry *bdst;
+               __u8 bmatchlen;
+
+               if (!laddr->valid ||
+                   laddr->state != SCTP_ADDR_SRC ||
+                   laddr->a.sa.sa_family != AF_INET6 ||
+                   scope > sctp_scope(&laddr->a))
                        continue;
-               if ((laddr->state == SCTP_ADDR_SRC) &&
-                   (laddr->a.sa.sa_family == AF_INET6) &&
-                   (scope <= sctp_scope(&laddr->a))) {
-                       bmatchlen = sctp_v6_addr_match_len(daddr, &laddr->a);
-                       if (!baddr || (matchlen < bmatchlen)) {
-                               baddr = &laddr->a;
-                               matchlen = bmatchlen;
-                       }
-               }
-       }
-       if (baddr) {
-               fl6->saddr = baddr->v6.sin6_addr;
-               fl6->fl6_sport = baddr->v6.sin6_port;
+
+               fl6->saddr = laddr->a.v6.sin6_addr;
+               fl6->fl6_sport = laddr->a.v6.sin6_port;
                final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final);
-               dst = ip6_dst_lookup_flow(sk, fl6, final_p);
+               bdst = ip6_dst_lookup_flow(sk, fl6, final_p);
+
+               if (!IS_ERR(bdst) &&
+                   ipv6_chk_addr(dev_net(bdst->dev),
+                                 &laddr->a.v6.sin6_addr, bdst->dev, 1)) {
+                       if (!IS_ERR_OR_NULL(dst))
+                               dst_release(dst);
+                       dst = bdst;
+                       break;
+               }
+
+               bmatchlen = sctp_v6_addr_match_len(daddr, &laddr->a);
+               if (matchlen > bmatchlen)
+                       continue;
+
+               if (!IS_ERR_OR_NULL(dst))
+                       dst_release(dst);
+               dst = bdst;
+               matchlen = bmatchlen;
        }
        rcu_read_unlock();