sctp: allow GSO frags to access the chunk too

SCTP will try to access original IP headers on sctp_recvmsg in order to
copy the addresses used. There are also other places that do similar access
to IP or even SCTP headers. But after 90017accff61 ("sctp: Add GSO
support") they aren't always there because they are only present in the
header skb.

SCTP handles the queueing of incoming data by cloning the incoming skb
and limiting to only the relevant payload. This clone has its cb updated
to something different and it's then queued on socket rx queue. Thus we
need to fix this in two moments.

For rx path, not related to socket queue yet, this patch uses a
partially copied sctp_input_cb to such GSO frags. This restores the
ability to access the headers for this part of the code.

Regarding the socket rx queue, it removes iif member from sctp_event and
also add a chunk pointer on it.

With these changes we're always able to reach the headers again.

The biggest change here is that now the sctp_chunk struct and the
original skb are only freed after the application consumed the buffer.
Note however that the original payload was already like this due to the
skb cloning.

For iif, SCTP's IPv4 code doesn't use it, so no change is necessary.
IPv6 now can fetch it directly from original's IPv6 CB as the original
skb is still accessible.

In the future we probably can simplify sctp_v*_skb_iif() stuff, as
sctp_v4_skb_iif() was called but it's return value not used, and now
it's not even called, but such cleanup is out of scope for this change.

Fixes: 90017accff61 ("sctp: Add GSO support")
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

6 files changed, 30 insertions, 10 deletions

diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c
index edabbbdfca54..147d975b0455 100644
--- a/net/sctp/inqueue.c
+++ b/net/sctp/inqueue.c
@@ -218,6 +218,13 @@ new_skb:
 		chunk->has_asconf = 0;
 		chunk->end_of_packet = 0;
 		chunk->ecn_ce_done = 0;
+		if (chunk->head_skb) {
+			struct sctp_input_cb
+				*cb = SCTP_INPUT_CB(chunk->skb),
+				*head_cb = SCTP_INPUT_CB(chunk->head_skb);
+
+			cb->chunk = head_cb->chunk;
+		}
 	}
 
 	chunk->chunk_hdr = ch;
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 0657d18a85bf..ae6f1a2178ba 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -420,6 +420,7 @@ static void sctp_v6_from_skb(union sctp_addr *addr, struct sk_buff *skb,
 	addr->v6.sin6_flowinfo = 0; /* FIXME */
 	addr->v6.sin6_scope_id = ((struct inet6_skb_parm *)skb->cb)->iif;
 
+	/* Always called on head skb, so this is safe */
 	sh = sctp_hdr(skb);
 	if (is_saddr) {
 		*port  = sh->source;
@@ -710,8 +711,7 @@ static int sctp_v6_addr_to_user(struct sctp_sock *sp, union sctp_addr *addr)
 /* Where did this skb come from?  */
 static int sctp_v6_skb_iif(const struct sk_buff *skb)
 {
-	struct inet6_skb_parm *opt = (struct inet6_skb_parm *) skb->cb;
-	return opt->iif;
+	return IP6CB(skb)->iif;
 }
 
 /* Was this packet marked by Explicit Congestion Notification? */
@@ -780,15 +780,14 @@ static void sctp_inet6_skb_msgname(struct sk_buff *skb, char *msgname,
 	if (ip_hdr(skb)->version == 4) {
 		addr->v4.sin_family = AF_INET;
 		addr->v4.sin_port = sh->source;
-		addr->v4.sin_addr.s_addr =  ip_hdr(skb)->saddr;
+		addr->v4.sin_addr.s_addr = ip_hdr(skb)->saddr;
 	} else {
 		addr->v6.sin6_family = AF_INET6;
 		addr->v6.sin6_flowinfo = 0;
 		addr->v6.sin6_port = sh->source;
 		addr->v6.sin6_addr = ipv6_hdr(skb)->saddr;
 		if (ipv6_addr_type(&addr->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL) {
-			struct sctp_ulpevent *ev = sctp_skb2event(skb);
-			addr->v6.sin6_scope_id = ev->iif;
+			addr->v6.sin6_scope_id = sctp_v6_skb_iif(skb);
 		}
 	}
 
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 3b56ae55aba3..1adb9270e317 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -240,6 +240,7 @@ static void sctp_v4_from_skb(union sctp_addr *addr, struct sk_buff *skb,
 	port = &addr->v4.sin_port;
 	addr->v4.sin_family = AF_INET;
 
+	/* Always called on head skb, so this is safe */
 	sh = sctp_hdr(skb);
 	if (is_saddr) {
 		*port  = sh->source;
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index f1f08c8f277b..5aabf42065e2 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -6125,7 +6125,8 @@ static int sctp_eat_data(const struct sctp_association *asoc,
 		af = sctp_get_af_specific(
 			ipver2af(ip_hdr(chunk->skb)->version));
 
-		if (af && af->is_ce(chunk->skb) && asoc->peer.ecn_capable) {
+		if (af && af->is_ce(sctp_gso_headskb(chunk->skb)) &&
+		    asoc->peer.ecn_capable) {
 			/* Do real work as sideffect. */
 			sctp_add_cmd_sf(commands, SCTP_CMD_ECN_CE,
 					SCTP_U32(tsn));
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 71c7dc5ea62e..52fdd540a9ef 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -2066,7 +2066,7 @@ static int sctp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 {
 	struct sctp_ulpevent *event = NULL;
 	struct sctp_sock *sp = sctp_sk(sk);
-	struct sk_buff *skb;
+	struct sk_buff *skb, *head_skb;
 	int copied;
 	int err = 0;
 	int skb_len;
@@ -2102,12 +2102,16 @@ static int sctp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 	if (err)
 		goto out_free;
 
-	sock_recv_ts_and_drops(msg, sk, skb);
+	if (event->chunk && event->chunk->head_skb)
+		head_skb = event->chunk->head_skb;
+	else
+		head_skb = skb;
+	sock_recv_ts_and_drops(msg, sk, head_skb);
 	if (sctp_ulpevent_is_notification(event)) {
 		msg->msg_flags |= MSG_NOTIFICATION;
 		sp->pf->event_msgname(event, msg->msg_name, addr_len);
 	} else {
-		sp->pf->skb_msgname(skb, msg->msg_name, addr_len);
+		sp->pf->skb_msgname(head_skb, msg->msg_name, addr_len);
 	}
 
 	/* Check if we allow SCTP_NXTINFO. */
diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c
index 706f5bc9f0c3..f6219b164b42 100644
--- a/net/sctp/ulpevent.c
+++ b/net/sctp/ulpevent.c
@@ -701,6 +701,12 @@ struct sctp_ulpevent *sctp_ulpevent_make_rcvmsg(struct sctp_association *asoc,
 
 	sctp_ulpevent_receive_data(event, asoc);
 
+	/* And hold the chunk as we need it for getting the IP headers
+	 * later in recvmsg
+	 */
+	sctp_chunk_hold(chunk);
+	event->chunk = chunk;
+
 	event->stream = ntohs(chunk->subh.data_hdr->stream);
 	event->ssn = ntohs(chunk->subh.data_hdr->ssn);
 	event->ppid = chunk->subh.data_hdr->ppid;
@@ -710,11 +716,11 @@ struct sctp_ulpevent *sctp_ulpevent_make_rcvmsg(struct sctp_association *asoc,
 	}
 	event->tsn = ntohl(chunk->subh.data_hdr->tsn);
 	event->msg_flags |= chunk->chunk_hdr->flags;
-	event->iif = sctp_chunk_iif(chunk);
 
 	return event;
 
 fail_mark:
+	sctp_chunk_put(chunk);
 	kfree_skb(skb);
 fail:
 	return NULL;
@@ -1007,6 +1013,7 @@ static void sctp_ulpevent_release_data(struct sctp_ulpevent *event)
 
 done:
 	sctp_assoc_rwnd_increase(event->asoc, len);
+	sctp_chunk_put(event->chunk);
 	sctp_ulpevent_release_owner(event);
 }
 
@@ -1029,6 +1036,7 @@ static void sctp_ulpevent_release_frag_data(struct sctp_ulpevent *event)
 	}
 
 done:
+	sctp_chunk_put(event->chunk);
 	sctp_ulpevent_release_owner(event);
 }