netfilter: handle the connecting collision properly in nf_conntrack_proto_sctp

[ Upstream commit 8e56b063c86569e51eed1c5681ce6361fa97fc7a ]

In Scenario A and B below, as the delayed INIT_ACK always changes the peer
vtag, SCTP ct with the incorrect vtag may cause packet loss.

Scenario A: INIT_ACK is delayed until the peer receives its own INIT_ACK

  192.168.1.2 > 192.168.1.1: [INIT] [init tag: 1328086772]
    192.168.1.1 > 192.168.1.2: [INIT] [init tag: 1414468151]
    192.168.1.2 > 192.168.1.1: [INIT ACK] [init tag: 1328086772]
  192.168.1.1 > 192.168.1.2: [INIT ACK] [init tag: 1650211246] *
  192.168.1.2 > 192.168.1.1: [COOKIE ECHO]
    192.168.1.1 > 192.168.1.2: [COOKIE ECHO]
    192.168.1.2 > 192.168.1.1: [COOKIE ACK]

Scenario B: INIT_ACK is delayed until the peer completes its own handshake

  192.168.1.2 > 192.168.1.1: sctp (1) [INIT] [init tag: 3922216408]
    192.168.1.1 > 192.168.1.2: sctp (1) [INIT] [init tag: 144230885]
    192.168.1.2 > 192.168.1.1: sctp (1) [INIT ACK] [init tag: 3922216408]
    192.168.1.1 > 192.168.1.2: sctp (1) [COOKIE ECHO]
    192.168.1.2 > 192.168.1.1: sctp (1) [COOKIE ACK]
  192.168.1.1 > 192.168.1.2: sctp (1) [INIT ACK] [init tag: 3914796021] *

This patch fixes it as below:

In SCTP_CID_INIT processing:
- clear ct->proto.sctp.init[!dir] if ct->proto.sctp.init[dir] &&
  ct->proto.sctp.init[!dir]. (Scenario E)
- set ct->proto.sctp.init[dir].

In SCTP_CID_INIT_ACK processing:
- drop it if !ct->proto.sctp.init[!dir] && ct->proto.sctp.vtag[!dir] &&
  ct->proto.sctp.vtag[!dir] != ih->init_tag. (Scenario B, Scenario C)
- drop it if ct->proto.sctp.init[dir] && ct->proto.sctp.init[!dir] &&
  ct->proto.sctp.vtag[!dir] != ih->init_tag. (Scenario A)

In SCTP_CID_COOKIE_ACK processing:
- clear ct->proto.sctp.init[dir] and ct->proto.sctp.init[!dir].
  (Scenario D)

Also, it's important to allow the ct state to move forward with cookie_echo
and cookie_ack from the opposite dir for the collision scenarios.

There are also other Scenarios where it should allow the packet through,
addressed by the processing above:

Scenario C: new CT is created by INIT_ACK.

Scenario D: start INIT on the existing ESTABLISHED ct.

Scenario E: start INIT after the old collision on the existing ESTABLISHED
ct.

  192.168.1.2 > 192.168.1.1: sctp (1) [INIT] [init tag: 3922216408]
  192.168.1.1 > 192.168.1.2: sctp (1) [INIT] [init tag: 144230885]
  (both side are stopped, then start new connection again in hours)
  192.168.1.2 > 192.168.1.1: sctp (1) [INIT] [init tag: 242308742]

Fixes: 9fb9cbb1082d ("[NETFILTER]: Add nf_conntrack subsystem.")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>

diff --git a/include/linux/netfilter/nf_conntrack_sctp.h b/include/linux/netfilter/nf_conntrack_sctp.h
index 625f491b95de87904892dc52e6e5bf5bba8a57fa..fb31312825ae530f95577f3866e8fbd235dadd2a 100644 (file)
--- a/include/linux/netfilter/nf_conntrack_sctp.h
+++ b/include/linux/netfilter/nf_conntrack_sctp.h
@@ -9,6 +9,7 @@ struct ip_ct_sctp {
        enum sctp_conntrack state;
 
        __be32 vtag[IP_CT_DIR_MAX];
+       u8 init[IP_CT_DIR_MAX];
        u8 last_dir;
        u8 flags;
 };

diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c
index 7247af51bdfc47696d104a89142fc5b668837364..c94a9971d790c1ff1f0308001ec20e98e905f62c 100644 (file)
--- a/net/netfilter/nf_conntrack_proto_sctp.c
+++ b/net/netfilter/nf_conntrack_proto_sctp.c
@@ -112,7 +112,7 @@ static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = {
 /* shutdown_ack */ {sSA, sCL, sCW, sCE, sES, sSA, sSA, sSA, sSA},
 /* error        */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL},/* Can't have Stale cookie*/
 /* cookie_echo  */ {sCL, sCL, sCE, sCE, sES, sSS, sSR, sSA, sCL},/* 5.2.4 - Big TODO */
-/* cookie_ack   */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL},/* Can't come in orig dir */
+/* cookie_ack   */ {sCL, sCL, sCW, sES, sES, sSS, sSR, sSA, sCL},/* Can't come in orig dir */
 /* shutdown_comp*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sCL, sCL},
 /* heartbeat    */ {sHS, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS},
 /* heartbeat_ack*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS},
@@ -126,7 +126,7 @@ static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = {
 /* shutdown     */ {sIV, sCL, sCW, sCE, sSR, sSS, sSR, sSA, sIV},
 /* shutdown_ack */ {sIV, sCL, sCW, sCE, sES, sSA, sSA, sSA, sIV},
 /* error        */ {sIV, sCL, sCW, sCL, sES, sSS, sSR, sSA, sIV},
-/* cookie_echo  */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV},/* Can't come in reply dir */
+/* cookie_echo  */ {sIV, sCL, sCE, sCE, sES, sSS, sSR, sSA, sIV},/* Can't come in reply dir */
 /* cookie_ack   */ {sIV, sCL, sCW, sES, sES, sSS, sSR, sSA, sIV},
 /* shutdown_comp*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sCL, sIV},
 /* heartbeat    */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS},
@@ -426,6 +426,9 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct,
                        /* (D) vtag must be same as init_vtag as found in INIT_ACK */
                        if (sh->vtag != ct->proto.sctp.vtag[dir])
                                goto out_unlock;
+               } else if (sch->type == SCTP_CID_COOKIE_ACK) {
+                       ct->proto.sctp.init[dir] = 0;
+                       ct->proto.sctp.init[!dir] = 0;
                } else if (sch->type == SCTP_CID_HEARTBEAT) {
                        if (ct->proto.sctp.vtag[dir] == 0) {
                                pr_debug("Setting %d vtag %x for dir %d\n", sch->type, sh->vtag, dir);
@@ -474,16 +477,18 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct,
                }
 
                /* If it is an INIT or an INIT ACK note down the vtag */
-               if (sch->type == SCTP_CID_INIT ||
-                   sch->type == SCTP_CID_INIT_ACK) {
-                       struct sctp_inithdr _inithdr, *ih;
+               if (sch->type == SCTP_CID_INIT) {
+                       struct sctp_inithdr _ih, *ih;
 
-                       ih = skb_header_pointer(skb, offset + sizeof(_sch),
-                                               sizeof(_inithdr), &_inithdr);
-                       if (ih == NULL)
+                       ih = skb_header_pointer(skb, offset + sizeof(_sch), sizeof(*ih), &_ih);
+                       if (!ih)
                                goto out_unlock;
-                       pr_debug("Setting vtag %x for dir %d\n",
-                                ih->init_tag, !dir);
+
+                       if (ct->proto.sctp.init[dir] && ct->proto.sctp.init[!dir])
+                               ct->proto.sctp.init[!dir] = 0;
+                       ct->proto.sctp.init[dir] = 1;
+
+                       pr_debug("Setting vtag %x for dir %d\n", ih->init_tag, !dir);
                        ct->proto.sctp.vtag[!dir] = ih->init_tag;
 
                        /* don't renew timeout on init retransmit so
@@ -494,6 +499,24 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct,
                            old_state == SCTP_CONNTRACK_CLOSED &&
                            nf_ct_is_confirmed(ct))
                                ignore = true;
+               } else if (sch->type == SCTP_CID_INIT_ACK) {
+                       struct sctp_inithdr _ih, *ih;
+                       __be32 vtag;
+
+                       ih = skb_header_pointer(skb, offset + sizeof(_sch), sizeof(*ih), &_ih);
+                       if (!ih)
+                               goto out_unlock;
+
+                       vtag = ct->proto.sctp.vtag[!dir];
+                       if (!ct->proto.sctp.init[!dir] && vtag && vtag != ih->init_tag)
+                               goto out_unlock;
+                       /* collision */
+                       if (ct->proto.sctp.init[dir] && ct->proto.sctp.init[!dir] &&
+                           vtag != ih->init_tag)
+                               goto out_unlock;
+
+                       pr_debug("Setting vtag %x for dir %d\n", ih->init_tag, !dir);
+                       ct->proto.sctp.vtag[!dir] = ih->init_tag;
                }
 
                ct->proto.sctp.state = new_state;