Merge branch 'sctp-refactor-MTU-handling'

Marcelo Ricardo Leitner says:

====================
sctp: refactor MTU handling

Currently MTU handling is spread over SCTP stack. There are multiple
places doing same/similar calculations and updating them is error prone
as one spot can easily be left out.

This patchset converges it into a more concise and consistent code. In
general, it moves MTU handling from functions with bigger objectives,
such as sctp_assoc_add_peer(), to specific functions.

It's also a preparation for the next patchset, which removes the
duplication between sctp_make_op_error_space and
sctp_make_op_error_fixed and relies on sctp_mtu_payload introduced here.

More details on each patch.
====================

Reviewed-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

8 files changed, 105 insertions, 134 deletions

diff --git a/include/net/sctp/constants.h b/include/net/sctp/constants.h
index 20ff237c5eb2..86f034b524d4 100644
--- a/include/net/sctp/constants.h
+++ b/include/net/sctp/constants.h
@@ -254,11 +254,10 @@ enum { SCTP_ARBITRARY_COOKIE_ECHO_LEN = 200 };
 #define SCTP_TSN_MAP_SIZE 4096
 
 /* We will not record more than this many duplicate TSNs between two
- * SACKs.  The minimum PMTU is 576.  Remove all the headers and there
- * is enough room for 131 duplicate reports.  Round down to the
+ * SACKs.  The minimum PMTU is 512.  Remove all the headers and there
+ * is enough room for 117 duplicate reports.  Round down to the
  * nearest power of 2.
  */
-enum { SCTP_MIN_PMTU = 576 };
 enum { SCTP_MAX_DUP_TSNS = 16 };
 enum { SCTP_MAX_GABS = 16 };
 
diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index 28b996d63490..f66d44350007 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -428,32 +428,6 @@ static inline int sctp_list_single_entry(struct list_head *head)
 	return (head->next != head) && (head->next == head->prev);
 }
 
-/* Break down data chunks at this point.  */
-static inline int sctp_frag_point(const struct sctp_association *asoc, int pmtu)
-{
-	struct sctp_sock *sp = sctp_sk(asoc->base.sk);
-	struct sctp_af *af = sp->pf->af;
-	int frag = pmtu;
-
-	frag -= af->ip_options_len(asoc->base.sk);
-	frag -= af->net_header_len;
-	frag -= sizeof(struct sctphdr) + sctp_datachk_len(&asoc->stream);
-
-	if (asoc->user_frag)
-		frag = min_t(int, frag, asoc->user_frag);
-
-	frag = SCTP_TRUNC4(min_t(int, frag, SCTP_MAX_CHUNK_LEN -
-					    sctp_datachk_len(&asoc->stream)));
-
-	return frag;
-}
-
-static inline void sctp_assoc_pending_pmtu(struct sctp_association *asoc)
-{
-	sctp_assoc_sync_pmtu(asoc);
-	asoc->pmtu_pending = 0;
-}
-
 static inline bool sctp_chunk_pending(const struct sctp_chunk *chunk)
 {
 	return !list_empty(&chunk->list);
@@ -607,17 +581,29 @@ static inline struct dst_entry *sctp_transport_dst_check(struct sctp_transport *
 	return t->dst;
 }
 
-static inline bool sctp_transport_pmtu_check(struct sctp_transport *t)
+/* Calculate max payload size given a MTU, or the total overhead if
+ * given MTU is zero
+ */
+static inline __u32 sctp_mtu_payload(const struct sctp_sock *sp,
+				     __u32 mtu, __u32 extra)
 {
-	__u32 pmtu = max_t(size_t, SCTP_TRUNC4(dst_mtu(t->dst)),
-			   SCTP_DEFAULT_MINSEGMENT);
+	__u32 overhead = sizeof(struct sctphdr) + extra;
 
-	if (t->pathmtu == pmtu)
-		return true;
+	if (sp)
+		overhead += sp->pf->af->net_header_len;
+	else
+		overhead += sizeof(struct ipv6hdr);
 
-	t->pathmtu = pmtu;
+	if (WARN_ON_ONCE(mtu && mtu <= overhead))
+		mtu = overhead;
 
-	return false;
+	return mtu ? mtu - overhead : overhead;
+}
+
+static inline __u32 sctp_dst_mtu(const struct dst_entry *dst)
+{
+	return SCTP_TRUNC4(max_t(__u32, dst_mtu(dst),
+				 SCTP_DEFAULT_MINSEGMENT));
 }
 
 #endif /* __net_sctp_h__ */
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 05594b248e52..ebf809eed33a 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -2097,6 +2097,8 @@ int sctp_assoc_update(struct sctp_association *old,
 
 __u32 sctp_association_get_next_tsn(struct sctp_association *);
 
+void sctp_assoc_update_frag_point(struct sctp_association *asoc);
+void sctp_assoc_set_pmtu(struct sctp_association *asoc, __u32 pmtu);
 void sctp_assoc_sync_pmtu(struct sctp_association *asoc);
 void sctp_assoc_rwnd_increase(struct sctp_association *, unsigned int);
 void sctp_assoc_rwnd_decrease(struct sctp_association *, unsigned int);
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index a8f3b088fcb2..039fdb862b17 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -652,33 +652,20 @@ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *asoc,
 	 */
 	peer->param_flags = asoc->param_flags;
 
-	sctp_transport_route(peer, NULL, sp);
-
 	/* Initialize the pmtu of the transport. */
-	if (peer->param_flags & SPP_PMTUD_DISABLE) {
-		if (asoc->pathmtu)
-			peer->pathmtu = asoc->pathmtu;
-		else
-			peer->pathmtu = SCTP_DEFAULT_MAXSEGMENT;
-	}
+	sctp_transport_route(peer, NULL, sp);
 
 	/* If this is the first transport addr on this association,
 	 * initialize the association PMTU to the peer's PMTU.
 	 * If not and the current association PMTU is higher than the new
 	 * peer's PMTU, reset the association PMTU to the new peer's PMTU.
 	 */
-	if (asoc->pathmtu)
-		asoc->pathmtu = min_t(int, peer->pathmtu, asoc->pathmtu);
-	else
-		asoc->pathmtu = peer->pathmtu;
-
-	pr_debug("%s: association:%p PMTU set to %d\n", __func__, asoc,
-		 asoc->pathmtu);
+	sctp_assoc_set_pmtu(asoc, asoc->pathmtu ?
+				  min_t(int, peer->pathmtu, asoc->pathmtu) :
+				  peer->pathmtu);
 
 	peer->pmtu_pending = 0;
 
-	asoc->frag_point = sctp_frag_point(asoc, asoc->pathmtu);
-
 	/* The asoc->peer.port might not be meaningful yet, but
 	 * initialize the packet structure anyway.
 	 */
@@ -1381,6 +1368,31 @@ sctp_assoc_choose_alter_transport(struct sctp_association *asoc,
 	}
 }
 
+void sctp_assoc_update_frag_point(struct sctp_association *asoc)
+{
+	int frag = sctp_mtu_payload(sctp_sk(asoc->base.sk), asoc->pathmtu,
+				    sctp_datachk_len(&asoc->stream));
+
+	if (asoc->user_frag)
+		frag = min_t(int, frag, asoc->user_frag);
+
+	frag = min_t(int, frag, SCTP_MAX_CHUNK_LEN -
+				sctp_datachk_len(&asoc->stream));
+
+	asoc->frag_point = SCTP_TRUNC4(frag);
+}
+
+void sctp_assoc_set_pmtu(struct sctp_association *asoc, __u32 pmtu)
+{
+	if (asoc->pathmtu != pmtu) {
+		asoc->pathmtu = pmtu;
+		sctp_assoc_update_frag_point(asoc);
+	}
+
+	pr_debug("%s: asoc:%p, pmtu:%d, frag_point:%d\n", __func__, asoc,
+		 asoc->pathmtu, asoc->frag_point);
+}
+
 /* Update the association's pmtu and frag_point by going through all the
  * transports. This routine is called when a transport's PMTU has changed.
  */
@@ -1393,24 +1405,16 @@ void sctp_assoc_sync_pmtu(struct sctp_association *asoc)
 		return;
 
 	/* Get the lowest pmtu of all the transports. */
-	list_for_each_entry(t, &asoc->peer.transport_addr_list,
-				transports) {
+	list_for_each_entry(t, &asoc->peer.transport_addr_list, transports) {
 		if (t->pmtu_pending && t->dst) {
-			sctp_transport_update_pmtu(
-					t, SCTP_TRUNC4(dst_mtu(t->dst)));
+			sctp_transport_update_pmtu(t, sctp_dst_mtu(t->dst));
 			t->pmtu_pending = 0;
 		}
 		if (!pmtu || (t->pathmtu < pmtu))
 			pmtu = t->pathmtu;
 	}
 
-	if (pmtu) {
-		asoc->pathmtu = pmtu;
-		asoc->frag_point = sctp_frag_point(asoc, pmtu);
-	}
-
-	pr_debug("%s: asoc:%p, pmtu:%d, frag_point:%d\n", __func__, asoc,
-		 asoc->pathmtu, asoc->frag_point);
+	sctp_assoc_set_pmtu(asoc, pmtu);
 }
 
 /* Should we send a SACK to update our peer? */
diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c
index be296d633e95..79daa98208c3 100644
--- a/net/sctp/chunk.c
+++ b/net/sctp/chunk.c
@@ -172,8 +172,6 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc,
 	struct list_head *pos, *temp;
 	struct sctp_chunk *chunk;
 	struct sctp_datamsg *msg;
-	struct sctp_sock *sp;
-	struct sctp_af *af;
 	int err;
 
 	msg = sctp_datamsg_new(GFP_KERNEL);
@@ -192,12 +190,7 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc,
 	/* This is the biggest possible DATA chunk that can fit into
 	 * the packet
 	 */
-	sp = sctp_sk(asoc->base.sk);
-	af = sp->pf->af;
-	max_data = asoc->pathmtu - af->net_header_len -
-		   sizeof(struct sctphdr) - sctp_datachk_len(&asoc->stream) -
-		   af->ip_options_len(asoc->base.sk);
-	max_data = SCTP_TRUNC4(max_data);
+	max_data = asoc->frag_point;
 
 	/* If the the peer requested that we authenticate DATA chunks
 	 * we need to account for bundling of the AUTH chunks along with
@@ -222,9 +215,6 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc,
 		}
 	}
 
-	/* Check what's our max considering the above */
-	max_data = min_t(size_t, max_data, asoc->frag_point);
-
 	/* Set first_len and then account for possible bundles on first frag */
 	first_len = max_data;
 
diff --git a/net/sctp/output.c b/net/sctp/output.c
index 690d8557bb7b..e672dee302c7 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -90,8 +90,8 @@ void sctp_packet_config(struct sctp_packet *packet, __u32 vtag,
 {
 	struct sctp_transport *tp = packet->transport;
 	struct sctp_association *asoc = tp->asoc;
+	struct sctp_sock *sp = NULL;
 	struct sock *sk;
-	size_t overhead = sizeof(struct ipv6hdr) + sizeof(struct sctphdr);
 
 	pr_debug("%s: packet:%p vtag:0x%x\n", __func__, packet, vtag);
 	packet->vtag = vtag;
@@ -102,28 +102,20 @@ void sctp_packet_config(struct sctp_packet *packet, __u32 vtag,
 
 	/* set packet max_size with pathmtu, then calculate overhead */
 	packet->max_size = tp->pathmtu;
+
 	if (asoc) {
-		struct sctp_sock *sp = sctp_sk(asoc->base.sk);
-		struct sctp_af *af = sp->pf->af;
-
-		overhead = af->net_header_len +
-			   af->ip_options_len(asoc->base.sk);
-		overhead += sizeof(struct sctphdr);
-		packet->overhead = overhead;
-		packet->size = overhead;
-	} else {
-		packet->overhead = overhead;
-		packet->size = overhead;
-		return;
+		sk = asoc->base.sk;
+		sp = sctp_sk(sk);
 	}
+	packet->overhead = sctp_mtu_payload(sp, 0, 0);
+	packet->size = packet->overhead;
+
+	if (!asoc)
+		return;
 
 	/* update dst or transport pathmtu if in need */
-	sk = asoc->base.sk;
 	if (!sctp_transport_dst_check(tp)) {
-		sctp_transport_route(tp, NULL, sctp_sk(sk));
-		if (asoc->param_flags & SPP_PMTUD_ENABLE)
-			sctp_assoc_sync_pmtu(asoc);
-	} else if (!sctp_transport_pmtu_check(tp)) {
+		sctp_transport_route(tp, NULL, sp);
 		if (asoc->param_flags & SPP_PMTUD_ENABLE)
 			sctp_assoc_sync_pmtu(asoc);
 	}
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 80835ac26d2c..1b4593b842b0 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -644,16 +644,15 @@ static int sctp_send_asconf_add_ip(struct sock		*sk,
 
 			list_for_each_entry(trans,
 			    &asoc->peer.transport_addr_list, transports) {
-				/* Clear the source and route cache */
-				sctp_transport_dst_release(trans);
 				trans->cwnd = min(4*asoc->pathmtu, max_t(__u32,
 				    2*asoc->pathmtu, 4380));
 				trans->ssthresh = asoc->peer.i.a_rwnd;
 				trans->rto = asoc->rto_initial;
 				sctp_max_rto(asoc, trans);
 				trans->rtt = trans->srtt = trans->rttvar = 0;
+				/* Clear the source and route cache */
 				sctp_transport_route(trans, NULL,
-				    sctp_sk(asoc->base.sk));
+						     sctp_sk(asoc->base.sk));
 			}
 		}
 		retval = sctp_send_asconf(asoc, chunk);
@@ -896,7 +895,6 @@ skip_mkasconf:
 		 */
 		list_for_each_entry(transport, &asoc->peer.transport_addr_list,
 					transports) {
-			sctp_transport_dst_release(transport);
 			sctp_transport_route(transport, NULL,
 					     sctp_sk(asoc->base.sk));
 		}
@@ -1895,6 +1893,7 @@ static int sctp_sendmsg_to_asoc(struct sctp_association *asoc,
 				struct sctp_sndrcvinfo *sinfo)
 {
 	struct sock *sk = asoc->base.sk;
+	struct sctp_sock *sp = sctp_sk(sk);
 	struct net *net = sock_net(sk);
 	struct sctp_datamsg *datamsg;
 	bool wait_connect = false;
@@ -1913,13 +1912,16 @@ static int sctp_sendmsg_to_asoc(struct sctp_association *asoc,
 			goto err;
 	}
 
-	if (sctp_sk(sk)->disable_fragments && msg_len > asoc->frag_point) {
+	if (sp->disable_fragments && msg_len > asoc->frag_point) {
 		err = -EMSGSIZE;
 		goto err;
 	}
 
-	if (asoc->pmtu_pending)
-		sctp_assoc_pending_pmtu(asoc);
+	if (asoc->pmtu_pending) {
+		if (sp->param_flags & SPP_PMTUD_ENABLE)
+			sctp_assoc_sync_pmtu(asoc);
+		asoc->pmtu_pending = 0;
+	}
 
 	if (sctp_wspace(asoc) < msg_len)
 		sctp_prsctp_prune(asoc, sinfo, msg_len - sctp_wspace(asoc));
@@ -1936,7 +1938,7 @@ static int sctp_sendmsg_to_asoc(struct sctp_association *asoc,
 		if (err)
 			goto err;
 
-		if (sctp_sk(sk)->strm_interleave) {
+		if (sp->strm_interleave) {
 			timeo = sock_sndtimeo(sk, 0);
 			err = sctp_wait_for_connect(asoc, &timeo);
 			if (err)
@@ -2539,7 +2541,7 @@ static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params,
 			trans->pathmtu = params->spp_pathmtu;
 			sctp_assoc_sync_pmtu(asoc);
 		} else if (asoc) {
-			asoc->pathmtu = params->spp_pathmtu;
+			sctp_assoc_set_pmtu(asoc, params->spp_pathmtu);
 		} else {
 			sp->pathmtu = params->spp_pathmtu;
 		}
@@ -3209,7 +3211,6 @@ static int sctp_setsockopt_mappedv4(struct sock *sk, char __user *optval, unsign
 static int sctp_setsockopt_maxseg(struct sock *sk, char __user *optval, unsigned int optlen)
 {
 	struct sctp_sock *sp = sctp_sk(sk);
-	struct sctp_af *af = sp->pf->af;
 	struct sctp_assoc_value params;
 	struct sctp_association *asoc;
 	int val;
@@ -3231,30 +3232,24 @@ static int sctp_setsockopt_maxseg(struct sock *sk, char __user *optval, unsigned
 		return -EINVAL;
 	}
 
+	asoc = sctp_id2assoc(sk, params.assoc_id);
+
 	if (val) {
 		int min_len, max_len;
+		__u16 datasize = asoc ? sctp_datachk_len(&asoc->stream) :
+				 sizeof(struct sctp_data_chunk);
 
-		min_len = SCTP_DEFAULT_MINSEGMENT - af->net_header_len;
-		min_len -= af->ip_options_len(sk);
-		min_len -= sizeof(struct sctphdr) +
-			   sizeof(struct sctp_data_chunk);
-
-		max_len = SCTP_MAX_CHUNK_LEN - sizeof(struct sctp_data_chunk);
+		min_len = sctp_mtu_payload(sp, SCTP_DEFAULT_MINSEGMENT,
+					   datasize);
+		max_len = SCTP_MAX_CHUNK_LEN - datasize;
 
 		if (val < min_len || val > max_len)
 			return -EINVAL;
 	}
 
-	asoc = sctp_id2assoc(sk, params.assoc_id);
 	if (asoc) {
-		if (val == 0) {
-			val = asoc->pathmtu - af->net_header_len;
-			val -= af->ip_options_len(sk);
-			val -= sizeof(struct sctphdr) +
-			       sctp_datachk_len(&asoc->stream);
-		}
 		asoc->user_frag = val;
-		asoc->frag_point = sctp_frag_point(asoc, asoc->pathmtu);
+		sctp_assoc_update_frag_point(asoc);
 	} else {
 		if (params.assoc_id && sctp_style(sk, UDP))
 			return -EINVAL;
diff --git a/net/sctp/transport.c b/net/sctp/transport.c
index 47f82bd794d9..4a95e260b674 100644
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -242,9 +242,18 @@ void sctp_transport_pmtu(struct sctp_transport *transport, struct sock *sk)
 						&transport->fl, sk);
 	}
 
-	if (transport->dst) {
-		transport->pathmtu = SCTP_TRUNC4(dst_mtu(transport->dst));
-	} else
+	if (transport->param_flags & SPP_PMTUD_DISABLE) {
+		struct sctp_association *asoc = transport->asoc;
+
+		if (!transport->pathmtu && asoc && asoc->pathmtu)
+			transport->pathmtu = asoc->pathmtu;
+		if (transport->pathmtu)
+			return;
+	}
+
+	if (transport->dst)
+		transport->pathmtu = sctp_dst_mtu(transport->dst);
+	else
 		transport->pathmtu = SCTP_DEFAULT_MAXSEGMENT;
 }
 
@@ -290,6 +299,7 @@ void sctp_transport_route(struct sctp_transport *transport,
 	struct sctp_association *asoc = transport->asoc;
 	struct sctp_af *af = transport->af_specific;
 
+	sctp_transport_dst_release(transport);
 	af->get_dst(transport, saddr, &transport->fl, sctp_opt2sk(opt));
 
 	if (saddr)
@@ -297,21 +307,14 @@ void sctp_transport_route(struct sctp_transport *transport,
 	else
 		af->get_saddr(opt, transport, &transport->fl);
 
-	if ((transport->param_flags & SPP_PMTUD_DISABLE) && transport->pathmtu) {
-		return;
-	}
-	if (transport->dst) {
-		transport->pathmtu = SCTP_TRUNC4(dst_mtu(transport->dst));
+	sctp_transport_pmtu(transport, sctp_opt2sk(opt));
 
-		/* Initialize sk->sk_rcv_saddr, if the transport is the
-		 * association's active path for getsockname().
-		 */
-		if (asoc && (!asoc->peer.primary_path ||
-				(transport == asoc->peer.active_path)))
-			opt->pf->to_sk_saddr(&transport->saddr,
-					     asoc->base.sk);
-	} else
-		transport->pathmtu = SCTP_DEFAULT_MAXSEGMENT;
+	/* Initialize sk->sk_rcv_saddr, if the transport is the
+	 * association's active path for getsockname().
+	 */
+	if (transport->dst && asoc &&
+	    (!asoc->peer.primary_path || transport == asoc->peer.active_path))
+		opt->pf->to_sk_saddr(&transport->saddr, asoc->base.sk);
 }
 
 /* Hold a reference to a transport.  */