[PATCH net-next 09/14] sctp: do state transition when receiving an icmp TOOBIG packet

[Xin Long <lucien.xin@gmail.com>]

PLPMTUD will short-circuit the old process for icmp TOOBIG packets.
This part is described in rfc8899#section-4.6.2 (PL_PTB_SIZE =
PTB_SIZE - other_headers_len). Note that from rfc8899#section-5.2
State Machine, each case below is for some specific states only:

  a) PL_PTB_SIZE < MIN_PLPMTU || PL_PTB_SIZE >= PROBED_SIZE,
     discard it, for any state

  b) MIN_PLPMTU < PL_PTB_SIZE < BASE_PLPMTU,
     Base -> Error, for Base state

  c) BASE_PLPMTU <= PL_PTB_SIZE < PLPMTU,
     Search -> Base or Complete -> Base, for Search and Complete states.

  d) PLPMTU < PL_PTB_SIZE < PROBED_SIZE,
     set pl.probe_size to PL_PTB_SIZE then verify it, for Search state.

The most important one is case d), which will help find the optimal
fast during searching. Like when pathmtu = 1392 for SCTP over IPv4,
the search will be (20 is iphdr_len):

  1. probe with 1200 - 20
  2. probe with 1232 - 20
  3. probe with 1264 - 20
  ...
  7. probe with 1388 - 20
  8. probe with 1420 - 20

When sending the probe with 1420 - 20, TOOBIG may come with PL_PTB_SIZE =
1392 - 20. Then it matches case d), and saves some rounds to try with the
1392 - 20 probe. But of course, PLPMTUD doesn't trust TOOBIG packets, and
it will go back to the common searching once the probe with the new size
can't be verified.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
---
 net/sctp/input.c     |  4 +++-
 net/sctp/transport.c | 51 +++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 53 insertions(+), 2 deletions(-)

diff --git a/net/sctp/input.c b/net/sctp/input.c
index d508f6f3dd08..9ffdbd6526e9 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -385,7 +385,9 @@ static int sctp_add_backlog(struct sock *sk, struct sk_buff *skb)
 void sctp_icmp_frag_needed(struct sock *sk, struct sctp_association *asoc,
 			   struct sctp_transport *t, __u32 pmtu)
 {
-	if (!t || (t->pathmtu <= pmtu))
+	if (!t ||
+	    (t->pathmtu <= pmtu &&
+	     t->pl.probe_size + sctp_transport_pl_hlen(t) <= pmtu))
 		return;
 
 	if (sock_owned_by_user(sk)) {
diff --git a/net/sctp/transport.c b/net/sctp/transport.c
index 79ff5ca6b472..5cefb4eab8a0 100644
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -343,10 +343,55 @@ void sctp_transport_pl_recv(struct sctp_transport *t)
 	}
 }
 
+static bool sctp_transport_pl_toobig(struct sctp_transport *t, u32 pmtu)
+{
+	pr_debug("%s: PLPMTUD: transport: %p, state: %d, pmtu: %d, size: %d, ptb: %d\n",
+		 __func__, t, t->pl.state, t->pl.pmtu, t->pl.probe_size, pmtu);
+
+	if (pmtu < SCTP_MIN_PLPMTU || pmtu >= t->pl.probe_size)
+		return false;
+
+	if (t->pl.state == SCTP_PL_BASE) {
+		if (pmtu >= SCTP_MIN_PLPMTU && pmtu < SCTP_BASE_PLPMTU) {
+			t->pl.state = SCTP_PL_ERROR; /* Base -> Error */
+
+			t->pl.pmtu = SCTP_MIN_PLPMTU;
+			t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t);
+		}
+	} else if (t->pl.state == SCTP_PL_SEARCH) {
+		if (pmtu >= SCTP_BASE_PLPMTU && pmtu < t->pl.pmtu) {
+			t->pl.state = SCTP_PL_BASE;  /* Search -> Base */
+			t->pl.probe_size = SCTP_BASE_PLPMTU;
+			t->pl.probe_count = 0;
+
+			t->pl.probe_high = 0;
+			t->pl.pmtu = SCTP_BASE_PLPMTU;
+			t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t);
+		} else if (pmtu > t->pl.pmtu && pmtu < t->pl.probe_size) {
+			t->pl.probe_size = pmtu;
+			t->pl.probe_count = 0;
+
+			return false;
+		}
+	} else if (t->pl.state == SCTP_PL_COMPLETE) {
+		if (pmtu >= SCTP_BASE_PLPMTU && pmtu < t->pl.pmtu) {
+			t->pl.state = SCTP_PL_BASE;  /* Complete -> Base */
+			t->pl.probe_size = SCTP_BASE_PLPMTU;
+			t->pl.probe_count = 0;
+
+			t->pl.probe_high = 0;
+			t->pl.pmtu = SCTP_BASE_PLPMTU;
+			t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t);
+		}
+	}
+
+	return true;
+}
+
 bool sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu)
 {
-	struct dst_entry *dst = sctp_transport_dst_check(t);
 	struct sock *sk = t->asoc->base.sk;
+	struct dst_entry *dst;
 	bool change = true;
 
 	if (unlikely(pmtu < SCTP_DEFAULT_MINSEGMENT)) {
@@ -357,6 +402,10 @@ bool sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu)
 	}
 	pmtu = SCTP_TRUNC4(pmtu);
 
+	if (sctp_transport_pl_enabled(t))
+		return sctp_transport_pl_toobig(t, pmtu - sctp_transport_pl_hlen(t));
+
+	dst = sctp_transport_dst_check(t);
 	if (dst) {
 		struct sctp_pf *pf = sctp_get_pf_specific(dst->ops->family);
 		union sctp_addr addr;
-- 
2.27.0