[SCTP]: Implement SCTP_FRAGMENT_INTERLEAVE socket option

This option was introduced in draft-ietf-tsvwg-sctpsocket-13.  It
prevents head-of-line blocking in the case of one-to-many endpoint.
Applications enabling this option really must enable SCTP_SNDRCV event
so that they would know where the data belongs.  Based on an
earlier patch by Ivan Skytte Jørgensen.

Additionally, this functionality now permits multiple associations
on the same endpoint to enter Partial Delivery.  Applications should
be extra careful, when using this functionality, to track EOR indicators.

Signed-off-by: Vlad Yasevich <vladislav.yasevich@hp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 77 insertions, 7 deletions

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index a1d026f..b4be473 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -2255,7 +2255,7 @@ static int sctp_setsockopt_peer_addr_params(struct sock *sk,
 	return 0;
 }
 
-/* 7.1.24. Delayed Ack Timer (SCTP_DELAYED_ACK_TIME)
+/* 7.1.23. Delayed Ack Timer (SCTP_DELAYED_ACK_TIME)
  *
  *   This options will get or set the delayed ack timer.  The time is set
  *   in milliseconds.  If the assoc_id is 0, then this sets or gets the
@@ -2792,6 +2792,46 @@ static int sctp_setsockopt_context(struct sock *sk, char __user *optval,
 	return 0;
 }
 
+/*
+ * 7.1.24.  Get or set fragmented interleave (SCTP_FRAGMENT_INTERLEAVE)
+ *
+ * This options will at a minimum specify if the implementation is doing
+ * fragmented interleave.  Fragmented interleave, for a one to many
+ * socket, is when subsequent calls to receive a message may return
+ * parts of messages from different associations.  Some implementations
+ * may allow you to turn this value on or off.  If so, when turned off,
+ * no fragment interleave will occur (which will cause a head of line
+ * blocking amongst multiple associations sharing the same one to many
+ * socket).  When this option is turned on, then each receive call may
+ * come from a different association (thus the user must receive data
+ * with the extended calls (e.g. sctp_recvmsg) to keep track of which
+ * association each receive belongs to.
+ *
+ * This option takes a boolean value.  A non-zero value indicates that
+ * fragmented interleave is on.  A value of zero indicates that
+ * fragmented interleave is off.
+ *
+ * Note that it is important that an implementation that allows this
+ * option to be turned on, have it off by default.  Otherwise an unaware
+ * application using the one to many model may become confused and act
+ * incorrectly.
+ */
+static int sctp_setsockopt_fragment_interleave(struct sock *sk,
+					       char __user *optval,
+					       int optlen)
+{
+	int val;
+
+	if (optlen != sizeof(int))
+		return -EINVAL;
+	if (get_user(val, (int __user *)optval))
+		return -EFAULT;
+
+	sctp_sk(sk)->frag_interleave = (val == 0) ? 0 : 1;
+
+	return 0;
+}
+
 /* API 6.2 setsockopt(), getsockopt()
  *
  * Applications use setsockopt() and getsockopt() to set or retrieve
@@ -2906,7 +2946,9 @@ SCTP_STATIC int sctp_setsockopt(struct sock *sk, int level, int optname,
 	case SCTP_CONTEXT:
 		retval = sctp_setsockopt_context(sk, optval, optlen);
 		break;
-
+	case SCTP_FRAGMENT_INTERLEAVE:
+		retval = sctp_setsockopt_fragment_interleave(sk, optval, optlen);
+		break;
 	default:
 		retval = -ENOPROTOOPT;
 		break;
@@ -3134,8 +3176,9 @@ SCTP_STATIC int sctp_init_sock(struct sock *sk)
 	sp->pf = sctp_get_pf_specific(sk->sk_family);
 
 	/* Control variables for partial data delivery. */
-	sp->pd_mode           = 0;
+	atomic_set(&sp->pd_mode, 0);
 	skb_queue_head_init(&sp->pd_lobby);
+	sp->frag_interleave = 0;
 
 	/* Create a per socket endpoint structure.  Even if we
 	 * change the data structure relationships, this may still
@@ -3642,7 +3685,7 @@ static int sctp_getsockopt_peer_addr_params(struct sock *sk, int len,
 	return 0;
 }
 
-/* 7.1.24. Delayed Ack Timer (SCTP_DELAYED_ACK_TIME)
+/* 7.1.23. Delayed Ack Timer (SCTP_DELAYED_ACK_TIME)
  *
  *   This options will get or set the delayed ack timer.  The time is set
  *   in milliseconds.  If the assoc_id is 0, then this sets or gets the
@@ -4536,6 +4579,29 @@ static int sctp_getsockopt_maxseg(struct sock *sk, int len,
 	return 0;
 }
 
+/*
+ * 7.1.24.  Get or set fragmented interleave (SCTP_FRAGMENT_INTERLEAVE)
+ * (chapter and verse is quoted at sctp_setsockopt_fragment_interleave())
+ */
+static int sctp_getsockopt_fragment_interleave(struct sock *sk, int len,
+					       char __user *optval, int __user *optlen)
+{
+	int val;
+
+	if (len < sizeof(int))
+		return -EINVAL;
+
+	len = sizeof(int);
+
+	val = sctp_sk(sk)->frag_interleave;
+	if (put_user(len, optlen))
+		return -EFAULT;
+	if (copy_to_user(optval, &val, len))
+		return -EFAULT;
+
+	return 0;
+}
+
 SCTP_STATIC int sctp_getsockopt(struct sock *sk, int level, int optname,
 				char __user *optval, int __user *optlen)
 {
@@ -4648,6 +4714,10 @@ SCTP_STATIC int sctp_getsockopt(struct sock *sk, int level, int optname,
 	case SCTP_CONTEXT:
 		retval = sctp_getsockopt_context(sk, len, optval, optlen);
 		break;
+	case SCTP_FRAGMENT_INTERLEAVE:
+		retval = sctp_getsockopt_fragment_interleave(sk, len, optval,
+							     optlen);
+		break;
 	default:
 		retval = -ENOPROTOOPT;
 		break;
@@ -5742,9 +5812,9 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk,
 	 * 3) Peeling off non-partial delivery; move pd_lobby to receive_queue.
 	 */
 	skb_queue_head_init(&newsp->pd_lobby);
-	sctp_sk(newsk)->pd_mode = assoc->ulpq.pd_mode;
+	atomic_set(&sctp_sk(newsk)->pd_mode, assoc->ulpq.pd_mode);
 
-	if (sctp_sk(oldsk)->pd_mode) {
+	if (atomic_read(&sctp_sk(oldsk)->pd_mode)) {
 		struct sk_buff_head *queue;
 
 		/* Decide which queue to move pd_lobby skbs to. */
@@ -5770,7 +5840,7 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk,
 		 * delivery to finish.
 		 */
 		if (assoc->ulpq.pd_mode)
-			sctp_clear_pd(oldsk);
+			sctp_clear_pd(oldsk, NULL);
 
 	}