From cc35c3d1edf7a8373a1a5daa80a912dec96a9cd5 Mon Sep 17 00:00:00 2001 From: Marcelo Ricardo Leitner Date: Fri, 5 Jan 2018 11:17:17 -0200 Subject: [PATCH 1/2] sctp: do not retransmit upon FragNeeded if PMTU discovery is disabled Currently, if PMTU discovery is disabled on a given transport, but the configured value is higher than the actual PMTU, it is likely that we will get some icmp Frag Needed. The issue is, if PMTU discovery is disabled, we won't update the information and will issue a retransmission immediately, which may very well trigger another ICMP, and another retransmission, leading to a loop. The fix is to simply not trigger immediate retransmissions if PMTU discovery is disabled on the given transport. Changes from v2: - updated stale comment, noticed by Xin Long Signed-off-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- net/sctp/input.c | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/net/sctp/input.c b/net/sctp/input.c index 621b5ca3fd1c..9320661cc41d 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -399,20 +399,20 @@ void sctp_icmp_frag_needed(struct sock *sk, struct sctp_association *asoc, return; } - if (t->param_flags & SPP_PMTUD_ENABLE) { - /* Update transports view of the MTU */ - sctp_transport_update_pmtu(t, pmtu); + if (!(t->param_flags & SPP_PMTUD_ENABLE)) + /* We can't allow retransmitting in such case, as the + * retransmission would be sized just as before, and thus we + * would get another icmp, and retransmit again. + */ + return; - /* Update association pmtu. */ - sctp_assoc_sync_pmtu(asoc); - } + /* Update transports view of the MTU */ + sctp_transport_update_pmtu(t, pmtu); - /* Retransmit with the new pmtu setting. - * Normally, if PMTU discovery is disabled, an ICMP Fragmentation - * Needed will never be sent, but if a message was sent before - * PMTU discovery was disabled that was larger than the PMTU, it - * would not be fragmented, so it must be re-transmitted fragmented. - */ + /* Update association pmtu. */ + sctp_assoc_sync_pmtu(asoc); + + /* Retransmit with the new pmtu setting. */ sctp_retransmit(&asoc->outqueue, t, SCTP_RTXR_PMTUD); } From b6c5734db07079c9410147b32407f2366d584e6c Mon Sep 17 00:00:00 2001 From: Marcelo Ricardo Leitner Date: Fri, 5 Jan 2018 11:17:18 -0200 Subject: [PATCH 2/2] sctp: fix the handling of ICMP Frag Needed for too small MTUs syzbot reported a hang involving SCTP, on which it kept flooding dmesg with the message: [ 246.742374] sctp: sctp_transport_update_pmtu: Reported pmtu 508 too low, using default minimum of 512 That happened because whenever SCTP hits an ICMP Frag Needed, it tries to adjust to the new MTU and triggers an immediate retransmission. But it didn't consider the fact that MTUs smaller than the SCTP minimum MTU allowed (512) would not cause the PMTU to change, and issued the retransmission anyway (thus leading to another ICMP Frag Needed, and so on). As IPv4 (ip_rt_min_pmtu=556) and IPv6 (IPV6_MIN_MTU=1280) minimum MTU are higher than that, sctp_transport_update_pmtu() is changed to re-fetch the PMTU that got set after our request, and with that, detect if there was an actual change or not. The fix, thus, skips the immediate retransmission if the received ICMP resulted in no change, in the hope that SCTP will select another path. Note: The value being used for the minimum MTU (512, SCTP_DEFAULT_MINSEGMENT) is not right and instead it should be (576, SCTP_MIN_PMTU), but such change belongs to another patch. Changes from v1: - do not disable PMTU discovery, in the light of commit 06ad391919b2 ("[SCTP] Don't disable PMTU discovery when mtu is small") and as suggested by Xin Long. - changed the way to break the rtx loop by detecting if the icmp resulted in a change or not Changes from v2: none See-also: https://lkml.org/lkml/2017/12/22/811 Reported-by: syzbot Signed-off-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 2 +- net/sctp/input.c | 8 ++++++-- net/sctp/transport.c | 29 +++++++++++++++++++---------- 3 files changed, 26 insertions(+), 13 deletions(-) diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 2f8f93da5dc2..9a5ccf03a59b 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -966,7 +966,7 @@ void sctp_transport_burst_limited(struct sctp_transport *); void sctp_transport_burst_reset(struct sctp_transport *); unsigned long sctp_transport_timeout(struct sctp_transport *); void sctp_transport_reset(struct sctp_transport *t); -void sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu); +bool sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu); void sctp_transport_immediate_rtx(struct sctp_transport *); void sctp_transport_dst_release(struct sctp_transport *t); void sctp_transport_dst_confirm(struct sctp_transport *t); diff --git a/net/sctp/input.c b/net/sctp/input.c index 9320661cc41d..141c9c466ec1 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -406,8 +406,12 @@ void sctp_icmp_frag_needed(struct sock *sk, struct sctp_association *asoc, */ return; - /* Update transports view of the MTU */ - sctp_transport_update_pmtu(t, pmtu); + /* Update transports view of the MTU. Return if no update was needed. + * If an update wasn't needed/possible, it also doesn't make sense to + * try to retransmit now. + */ + if (!sctp_transport_update_pmtu(t, pmtu)) + return; /* Update association pmtu. */ sctp_assoc_sync_pmtu(asoc); diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 1e5a22430cf5..47f82bd794d9 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -248,28 +248,37 @@ void sctp_transport_pmtu(struct sctp_transport *transport, struct sock *sk) transport->pathmtu = SCTP_DEFAULT_MAXSEGMENT; } -void sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu) +bool sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu) { struct dst_entry *dst = sctp_transport_dst_check(t); + bool change = true; if (unlikely(pmtu < SCTP_DEFAULT_MINSEGMENT)) { - pr_warn("%s: Reported pmtu %d too low, using default minimum of %d\n", - __func__, pmtu, SCTP_DEFAULT_MINSEGMENT); - /* Use default minimum segment size and disable - * pmtu discovery on this transport. - */ - t->pathmtu = SCTP_DEFAULT_MINSEGMENT; - } else { - t->pathmtu = pmtu; + pr_warn_ratelimited("%s: Reported pmtu %d too low, using default minimum of %d\n", + __func__, pmtu, SCTP_DEFAULT_MINSEGMENT); + /* Use default minimum segment instead */ + pmtu = SCTP_DEFAULT_MINSEGMENT; } + pmtu = SCTP_TRUNC4(pmtu); if (dst) { dst->ops->update_pmtu(dst, t->asoc->base.sk, NULL, pmtu); dst = sctp_transport_dst_check(t); } - if (!dst) + if (!dst) { t->af_specific->get_dst(t, &t->saddr, &t->fl, t->asoc->base.sk); + dst = t->dst; + } + + if (dst) { + /* Re-fetch, as under layers may have a higher minimum size */ + pmtu = SCTP_TRUNC4(dst_mtu(dst)); + change = t->pathmtu != pmtu; + } + t->pathmtu = pmtu; + + return change; } /* Caches the dst entry and source address for a transport's destination