From 269b14dd6e1037ff5b2cf2936b8f511f5d24cb3d Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Thu, 28 Oct 2021 05:36:01 -0400
Subject: [PATCH] sctp: allow IP fragmentation when PLPMTUD enters Error state
Git-commit: 40171248bb8934537fec8fbaf718e57c8add187c
Patch-mainline: v5.16-rc1
References: stable-5.14.19

[ Upstream commit 40171248bb8934537fec8fbaf718e57c8add187c ]

Currently when PLPMTUD enters Error state, transport pathmtu will be set
to MIN_PLPMTU(512) while probe is continuing with BASE_PLPMTU(1200). It
will cause pathmtu to stay in a very small value, even if the real pmtu
is some value like 1000.

RFC8899 doesn't clearly say how to set the value in Error state. But one
possibility could be keep using BASE_PLPMTU for the real pmtu, but allow
to do IP fragmentation when it's in Error state.

As it says in rfc8899#section-5.4:

   Some paths could be unable to sustain packets of the BASE_PLPMTU
   size.  The Error State could be implemented to provide robustness to
   such paths.  This allows fallback to a smaller than desired PLPMTU
   rather than suffer connectivity failure.  This could utilize methods
   such as endpoint IP fragmentation to enable the PL sender to
   communicate using packets smaller than the BASE_PLPMTU.

This patch is to set pmtu to BASE_PLPMTU instead of MIN_PLPMTU for Error
state in sctp_transport_pl_send/toobig(), and set packet ipfragok for
non-probe packets when it's in Error state.

Fixes: 1dc68c194571 ("sctp: do state transition when PROBE_COUNT == MAX_PROBES on HB send path")
Reported-by: Ying Xu <yinxu@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
Acked-by: Takashi Iwai <tiwai@suse.de>

---
 net/sctp/output.c    | 13 ++++++++-----
 net/sctp/transport.c |  4 ++--
 2 files changed, 10 insertions(+), 7 deletions(-)

diff --git a/net/sctp/output.c b/net/sctp/output.c
index 4dfb5ea82b05..cdfdbd353c67 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -581,13 +581,16 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp)
 	chunk = list_entry(packet->chunk_list.next, struct sctp_chunk, list);
 	sk = chunk->skb->sk;
 
-	/* check gso */
 	if (packet->size > tp->pathmtu && !packet->ipfragok && !chunk->pmtu_probe) {
-		if (!sk_can_gso(sk)) {
-			pr_err_once("Trying to GSO but underlying device doesn't support it.");
-			goto out;
+		if (tp->pl.state == SCTP_PL_ERROR) { /* do IP fragmentation if in Error state */
+			packet->ipfragok = 1;
+		} else {
+			if (!sk_can_gso(sk)) { /* check gso */
+				pr_err_once("Trying to GSO but underlying device doesn't support it.");
+				goto out;
+			}
+			gso = 1;
 		}
-		gso = 1;
 	}
 
 	/* alloc head skb */
diff --git a/net/sctp/transport.c b/net/sctp/transport.c
index a3d3ca6dd63d..1f2dfad768d5 100644
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -269,7 +269,7 @@ bool sctp_transport_pl_send(struct sctp_transport *t)
 		if (t->pl.probe_size == SCTP_BASE_PLPMTU) { /* BASE_PLPMTU Confirmation Failed */
 			t->pl.state = SCTP_PL_ERROR; /* Base -> Error */
 
-			t->pl.pmtu = SCTP_MIN_PLPMTU;
+			t->pl.pmtu = SCTP_BASE_PLPMTU;
 			t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t);
 			sctp_assoc_sync_pmtu(t->asoc);
 		}
@@ -366,7 +366,7 @@ static bool sctp_transport_pl_toobig(struct sctp_transport *t, u32 pmtu)
 		if (pmtu >= SCTP_MIN_PLPMTU && pmtu < SCTP_BASE_PLPMTU) {
 			t->pl.state = SCTP_PL_ERROR; /* Base -> Error */
 
-			t->pl.pmtu = SCTP_MIN_PLPMTU;
+			t->pl.pmtu = SCTP_BASE_PLPMTU;
 			t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t);
 		}
 	} else if (t->pl.state == SCTP_PL_SEARCH) {
-- 
2.26.2