Merge branch 'sctp-rfc7496-support'

Xin Long says:

====================
sctp: implement rfc7496 in sctp

This patchset implements "Additional Policies for the Partially Reliable
Stream Control Transmission Protocol Extension" described on RFC7496.

The Partially Reliable SCTP (PR-SCTP) extension defined in [RFC3758]
provides a generic method for senders to abandon user messages. The
decision to abandon a user message is sender side only, and the exact
condition is called a "PR-SCTP policy". This patchset implements 3
policies:

 1. Timed Reliability:  This allows the sender to specify a timeout for
    a user message after which the SCTP stack abandons the user message.

 2. Limited Retransmission Policy:  Allows limitation of the number of
    retransmissions.

 3. Priority Policy:  Allows removal of lower-priority messages if space
    for higher-priority messages is needed in the send buffer.

Patch 1-3 add some sockopts in sctp to set/get pr_sctp policy status.
Patch 4-6 implement these 3 policies one by one.
====================

Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

7 files changed, 384 insertions, 11 deletions

diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index e1849f3714ad..1c23060c41a6 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -268,6 +268,7 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a
 		goto fail_init;
 
 	asoc->active_key_id = ep->active_key_id;
+	asoc->prsctp_enable = ep->prsctp_enable;
 
 	/* Save the hmacs and chunks list into this association */
 	if (ep->auth_hmacs_list)
diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c
index 1eb94bf18ef4..a55e54738b81 100644
--- a/net/sctp/chunk.c
+++ b/net/sctp/chunk.c
@@ -335,13 +335,32 @@ errout:
 /* Check whether this message has expired. */
 int sctp_chunk_abandoned(struct sctp_chunk *chunk)
 {
-	struct sctp_datamsg *msg = chunk->msg;
+	if (!chunk->asoc->prsctp_enable ||
+	    !SCTP_PR_POLICY(chunk->sinfo.sinfo_flags)) {
+		struct sctp_datamsg *msg = chunk->msg;
+
+		if (!msg->can_abandon)
+			return 0;
+
+		if (time_after(jiffies, msg->expires_at))
+			return 1;
 
-	if (!msg->can_abandon)
 		return 0;
+	}
 
-	if (time_after(jiffies, msg->expires_at))
+	if (SCTP_PR_TTL_ENABLED(chunk->sinfo.sinfo_flags) &&
+	    time_after(jiffies, chunk->prsctp_param)) {
+		if (chunk->sent_count)
+			chunk->asoc->abandoned_sent[SCTP_PR_INDEX(TTL)]++;
+		else
+			chunk->asoc->abandoned_unsent[SCTP_PR_INDEX(TTL)]++;
+		return 1;
+	} else if (SCTP_PR_RTX_ENABLED(chunk->sinfo.sinfo_flags) &&
+		   chunk->sent_count > chunk->prsctp_param) {
+		chunk->asoc->abandoned_sent[SCTP_PR_INDEX(RTX)]++;
 		return 1;
+	}
+	/* PRIO policy is processed by sendmsg, not here */
 
 	return 0;
 }
diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c
index 9d494e35e7f9..1f03065686fe 100644
--- a/net/sctp/endpointola.c
+++ b/net/sctp/endpointola.c
@@ -163,6 +163,7 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep,
 	 */
 	ep->auth_hmacs_list = auth_hmacs;
 	ep->auth_chunk_list = auth_chunks;
+	ep->prsctp_enable = net->sctp.prsctp_enable;
 
 	return ep;
 
diff --git a/net/sctp/output.c b/net/sctp/output.c
index 2e9223bb1b3a..7425f6c23888 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -316,6 +316,8 @@ static sctp_xmit_t __sctp_packet_append_chunk(struct sctp_packet *packet,
 		packet->has_data = 1;
 		/* timestamp the chunk for rtx purposes */
 		chunk->sent_at = jiffies;
+		/* Mainly used for prsctp RTX policy */
+		chunk->sent_count++;
 		break;
 	case SCTP_CID_COOKIE_ECHO:
 		packet->has_cookie_echo = 1;
diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c
index 084718f9b3da..72e54a416af6 100644
--- a/net/sctp/outqueue.c
+++ b/net/sctp/outqueue.c
@@ -326,6 +326,9 @@ int sctp_outq_tail(struct sctp_outq *q, struct sctp_chunk *chunk, gfp_t gfp)
 
 			sctp_chunk_hold(chunk);
 			sctp_outq_tail_data(q, chunk);
+			if (chunk->asoc->prsctp_enable &&
+			    SCTP_PR_PRIO_ENABLED(chunk->sinfo.sinfo_flags))
+				chunk->asoc->sent_cnt_removable++;
 			if (chunk->chunk_hdr->flags & SCTP_DATA_UNORDERED)
 				SCTP_INC_STATS(net, SCTP_MIB_OUTUNORDERCHUNKS);
 			else
@@ -372,6 +375,96 @@ static void sctp_insert_list(struct list_head *head, struct list_head *new)
 		list_add_tail(new, head);
 }
 
+static int sctp_prsctp_prune_sent(struct sctp_association *asoc,
+				  struct sctp_sndrcvinfo *sinfo,
+				  struct list_head *queue, int msg_len)
+{
+	struct sctp_chunk *chk, *temp;
+
+	list_for_each_entry_safe(chk, temp, queue, transmitted_list) {
+		if (!SCTP_PR_PRIO_ENABLED(chk->sinfo.sinfo_flags) ||
+		    chk->prsctp_param <= sinfo->sinfo_timetolive)
+			continue;
+
+		list_del_init(&chk->transmitted_list);
+		sctp_insert_list(&asoc->outqueue.abandoned,
+				 &chk->transmitted_list);
+
+		asoc->sent_cnt_removable--;
+		asoc->abandoned_sent[SCTP_PR_INDEX(PRIO)]++;
+
+		if (!chk->tsn_gap_acked) {
+			if (chk->transport)
+				chk->transport->flight_size -=
+						sctp_data_size(chk);
+			asoc->outqueue.outstanding_bytes -= sctp_data_size(chk);
+		}
+
+		msg_len -= SCTP_DATA_SNDSIZE(chk) +
+			   sizeof(struct sk_buff) +
+			   sizeof(struct sctp_chunk);
+		if (msg_len <= 0)
+			break;
+	}
+
+	return msg_len;
+}
+
+static int sctp_prsctp_prune_unsent(struct sctp_association *asoc,
+				    struct sctp_sndrcvinfo *sinfo,
+				    struct list_head *queue, int msg_len)
+{
+	struct sctp_chunk *chk, *temp;
+
+	list_for_each_entry_safe(chk, temp, queue, list) {
+		if (!SCTP_PR_PRIO_ENABLED(chk->sinfo.sinfo_flags) ||
+		    chk->prsctp_param <= sinfo->sinfo_timetolive)
+			continue;
+
+		list_del_init(&chk->list);
+		asoc->sent_cnt_removable--;
+		asoc->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++;
+
+		msg_len -= SCTP_DATA_SNDSIZE(chk) +
+			   sizeof(struct sk_buff) +
+			   sizeof(struct sctp_chunk);
+		sctp_chunk_free(chk);
+		if (msg_len <= 0)
+			break;
+	}
+
+	return msg_len;
+}
+
+/* Abandon the chunks according their priorities */
+void sctp_prsctp_prune(struct sctp_association *asoc,
+		       struct sctp_sndrcvinfo *sinfo, int msg_len)
+{
+	struct sctp_transport *transport;
+
+	if (!asoc->prsctp_enable || !asoc->sent_cnt_removable)
+		return;
+
+	msg_len = sctp_prsctp_prune_sent(asoc, sinfo,
+					 &asoc->outqueue.retransmit,
+					 msg_len);
+	if (msg_len <= 0)
+		return;
+
+	list_for_each_entry(transport, &asoc->peer.transport_addr_list,
+			    transports) {
+		msg_len = sctp_prsctp_prune_sent(asoc, sinfo,
+						 &transport->transmitted,
+						 msg_len);
+		if (msg_len <= 0)
+			return;
+	}
+
+	sctp_prsctp_prune_unsent(asoc, sinfo,
+				 &asoc->outqueue.out_chunk_list,
+				 msg_len);
+}
+
 /* Mark all the eligible packets on a transport for retransmission.  */
 void sctp_retransmit_mark(struct sctp_outq *q,
 			  struct sctp_transport *transport,
@@ -962,6 +1055,9 @@ static int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp)
 
 				/* Mark as failed send. */
 				sctp_chunk_fail(chunk, SCTP_ERROR_INV_STRM);
+				if (asoc->prsctp_enable &&
+				    SCTP_PR_PRIO_ENABLED(chunk->sinfo.sinfo_flags))
+					asoc->sent_cnt_removable--;
 				sctp_chunk_free(chunk);
 				continue;
 			}
@@ -1251,6 +1347,9 @@ int sctp_outq_sack(struct sctp_outq *q, struct sctp_chunk *chunk)
 		tsn = ntohl(tchunk->subh.data_hdr->tsn);
 		if (TSN_lte(tsn, ctsn)) {
 			list_del_init(&tchunk->transmitted_list);
+			if (asoc->prsctp_enable &&
+			    SCTP_PR_PRIO_ENABLED(chunk->sinfo.sinfo_flags))
+				asoc->sent_cnt_removable--;
 			sctp_chunk_free(tchunk);
 		}
 	}
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index 56f364d8f932..1c96f4740e67 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -261,7 +261,7 @@ struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc,
 	chunksize += WORD_ROUND(SCTP_SAT_LEN(num_types));
 	chunksize += sizeof(ecap_param);
 
-	if (net->sctp.prsctp_enable)
+	if (asoc->prsctp_enable)
 		chunksize += sizeof(prsctp_param);
 
 	/* ADDIP: Section 4.2.7:
@@ -355,7 +355,7 @@ struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc,
 		sctp_addto_param(retval, num_ext, extensions);
 	}
 
-	if (net->sctp.prsctp_enable)
+	if (asoc->prsctp_enable)
 		sctp_addto_chunk(retval, sizeof(prsctp_param), &prsctp_param);
 
 	if (sp->adaptation_ind) {
@@ -711,6 +711,20 @@ nodata:
 	return retval;
 }
 
+static void sctp_set_prsctp_policy(struct sctp_chunk *chunk,
+				   const struct sctp_sndrcvinfo *sinfo)
+{
+	if (!chunk->asoc->prsctp_enable)
+		return;
+
+	if (SCTP_PR_TTL_ENABLED(sinfo->sinfo_flags))
+		chunk->prsctp_param =
+			jiffies + msecs_to_jiffies(sinfo->sinfo_timetolive);
+	else if (SCTP_PR_RTX_ENABLED(sinfo->sinfo_flags) ||
+		 SCTP_PR_PRIO_ENABLED(sinfo->sinfo_flags))
+		chunk->prsctp_param = sinfo->sinfo_timetolive;
+}
+
 /* Make a DATA chunk for the given association from the provided
  * parameters.  However, do not populate the data payload.
  */
@@ -744,6 +758,7 @@ struct sctp_chunk *sctp_make_datafrag_empty(struct sctp_association *asoc,
 
 	retval->subh.data_hdr = sctp_addto_chunk(retval, sizeof(dp), &dp);
 	memcpy(&retval->sinfo, sinfo, sizeof(struct sctp_sndrcvinfo));
+	sctp_set_prsctp_policy(retval, sinfo);
 
 nodata:
 	return retval;
@@ -2024,8 +2039,8 @@ static void sctp_process_ext_param(struct sctp_association *asoc,
 	for (i = 0; i < num_ext; i++) {
 		switch (param.ext->chunks[i]) {
 		case SCTP_CID_FWD_TSN:
-			if (net->sctp.prsctp_enable && !asoc->peer.prsctp_capable)
-				    asoc->peer.prsctp_capable = 1;
+			if (asoc->prsctp_enable && !asoc->peer.prsctp_capable)
+				asoc->peer.prsctp_capable = 1;
 			break;
 		case SCTP_CID_AUTH:
 			/* if the peer reports AUTH, assume that he
@@ -2169,7 +2184,7 @@ static sctp_ierror_t sctp_verify_param(struct net *net,
 		break;
 
 	case SCTP_PARAM_FWD_TSN_SUPPORT:
-		if (net->sctp.prsctp_enable)
+		if (ep->prsctp_enable)
 			break;
 		goto fallthrough;
 
@@ -2653,7 +2668,7 @@ do_addr_param:
 		break;
 
 	case SCTP_PARAM_FWD_TSN_SUPPORT:
-		if (net->sctp.prsctp_enable) {
+		if (asoc->prsctp_enable) {
 			asoc->peer.prsctp_capable = 1;
 			break;
 		}
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index cdabbd8219b1..71c7dc5ea62e 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -1914,6 +1914,9 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len)
 		goto out_free;
 	}
 
+	if (sctp_wspace(asoc) < msg_len)
+		sctp_prsctp_prune(asoc, sinfo, msg_len - sctp_wspace(asoc));
+
 	timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
 	if (!sctp_wspace(asoc)) {
 		err = sctp_wait_for_sndbuf(asoc, &timeo, msg_len);
@@ -3661,6 +3664,80 @@ static int sctp_setsockopt_recvnxtinfo(struct sock *sk,
 	return 0;
 }
 
+static int sctp_setsockopt_pr_supported(struct sock *sk,
+					char __user *optval,
+					unsigned int optlen)
+{
+	struct sctp_assoc_value params;
+	struct sctp_association *asoc;
+	int retval = -EINVAL;
+
+	if (optlen != sizeof(params))
+		goto out;
+
+	if (copy_from_user(&params, optval, optlen)) {
+		retval = -EFAULT;
+		goto out;
+	}
+
+	asoc = sctp_id2assoc(sk, params.assoc_id);
+	if (asoc) {
+		asoc->prsctp_enable = !!params.assoc_value;
+	} else if (!params.assoc_id) {
+		struct sctp_sock *sp = sctp_sk(sk);
+
+		sp->ep->prsctp_enable = !!params.assoc_value;
+	} else {
+		goto out;
+	}
+
+	retval = 0;
+
+out:
+	return retval;
+}
+
+static int sctp_setsockopt_default_prinfo(struct sock *sk,
+					  char __user *optval,
+					  unsigned int optlen)
+{
+	struct sctp_default_prinfo info;
+	struct sctp_association *asoc;
+	int retval = -EINVAL;
+
+	if (optlen != sizeof(info))
+		goto out;
+
+	if (copy_from_user(&info, optval, sizeof(info))) {
+		retval = -EFAULT;
+		goto out;
+	}
+
+	if (info.pr_policy & ~SCTP_PR_SCTP_MASK)
+		goto out;
+
+	if (info.pr_policy == SCTP_PR_SCTP_NONE)
+		info.pr_value = 0;
+
+	asoc = sctp_id2assoc(sk, info.pr_assoc_id);
+	if (asoc) {
+		SCTP_PR_SET_POLICY(asoc->default_flags, info.pr_policy);
+		asoc->default_timetolive = info.pr_value;
+	} else if (!info.pr_assoc_id) {
+		struct sctp_sock *sp = sctp_sk(sk);
+
+		SCTP_PR_SET_POLICY(sp->default_flags, info.pr_policy);
+		sp->default_timetolive = info.pr_value;
+	} else {
+		goto out;
+	}
+
+	retval = 0;
+
+out:
+	return retval;
+}
+
 /* API 6.2 setsockopt(), getsockopt()
  *
  * Applications use setsockopt() and getsockopt() to set or retrieve
@@ -3821,6 +3898,12 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname,
 	case SCTP_RECVNXTINFO:
 		retval = sctp_setsockopt_recvnxtinfo(sk, optval, optlen);
 		break;
+	case SCTP_PR_SUPPORTED:
+		retval = sctp_setsockopt_pr_supported(sk, optval, optlen);
+		break;
+	case SCTP_DEFAULT_PRINFO:
+		retval = sctp_setsockopt_default_prinfo(sk, optval, optlen);
+		break;
 	default:
 		retval = -ENOPROTOOPT;
 		break;
@@ -6166,6 +6249,148 @@ static int sctp_getsockopt_recvnxtinfo(struct sock *sk,	int len,
 	return 0;
 }
 
+static int sctp_getsockopt_pr_supported(struct sock *sk, int len,
+					char __user *optval,
+					int __user *optlen)
+{
+	struct sctp_assoc_value params;
+	struct sctp_association *asoc;
+	int retval = -EFAULT;
+
+	if (len < sizeof(params)) {
+		retval = -EINVAL;
+		goto out;
+	}
+
+	len = sizeof(params);
+	if (copy_from_user(&params, optval, len))
+		goto out;
+
+	asoc = sctp_id2assoc(sk, params.assoc_id);
+	if (asoc) {
+		params.assoc_value = asoc->prsctp_enable;
+	} else if (!params.assoc_id) {
+		struct sctp_sock *sp = sctp_sk(sk);
+
+		params.assoc_value = sp->ep->prsctp_enable;
+	} else {
+		retval = -EINVAL;
+		goto out;
+	}
+
+	if (put_user(len, optlen))
+		goto out;
+
+	if (copy_to_user(optval, &params, len))
+		goto out;
+
+	retval = 0;
+
+out:
+	return retval;
+}
+
+static int sctp_getsockopt_default_prinfo(struct sock *sk, int len,
+					  char __user *optval,
+					  int __user *optlen)
+{
+	struct sctp_default_prinfo info;
+	struct sctp_association *asoc;
+	int retval = -EFAULT;
+
+	if (len < sizeof(info)) {
+		retval = -EINVAL;
+		goto out;
+	}
+
+	len = sizeof(info);
+	if (copy_from_user(&info, optval, len))
+		goto out;
+
+	asoc = sctp_id2assoc(sk, info.pr_assoc_id);
+	if (asoc) {
+		info.pr_policy = SCTP_PR_POLICY(asoc->default_flags);
+		info.pr_value = asoc->default_timetolive;
+	} else if (!info.pr_assoc_id) {
+		struct sctp_sock *sp = sctp_sk(sk);
+
+		info.pr_policy = SCTP_PR_POLICY(sp->default_flags);
+		info.pr_value = sp->default_timetolive;
+	} else {
+		retval = -EINVAL;
+		goto out;
+	}
+
+	if (put_user(len, optlen))
+		goto out;
+
+	if (copy_to_user(optval, &info, len))
+		goto out;
+
+	retval = 0;
+
+out:
+	return retval;
+}
+
+static int sctp_getsockopt_pr_assocstatus(struct sock *sk, int len,
+					  char __user *optval,
+					  int __user *optlen)
+{
+	struct sctp_prstatus params;
+	struct sctp_association *asoc;
+	int policy;
+	int retval = -EINVAL;
+
+	if (len < sizeof(params))
+		goto out;
+
+	len = sizeof(params);
+	if (copy_from_user(&params, optval, len)) {
+		retval = -EFAULT;
+		goto out;
+	}
+
+	policy = params.sprstat_policy;
+	if (policy & ~SCTP_PR_SCTP_MASK)
+		goto out;
+
+	asoc = sctp_id2assoc(sk, params.sprstat_assoc_id);
+	if (!asoc)
+		goto out;
+
+	if (policy == SCTP_PR_SCTP_NONE) {
+		params.sprstat_abandoned_unsent = 0;
+		params.sprstat_abandoned_sent = 0;
+		for (policy = 0; policy <= SCTP_PR_INDEX(MAX); policy++) {
+			params.sprstat_abandoned_unsent +=
+				asoc->abandoned_unsent[policy];
+			params.sprstat_abandoned_sent +=
+				asoc->abandoned_sent[policy];
+		}
+	} else {
+		params.sprstat_abandoned_unsent =
+			asoc->abandoned_unsent[__SCTP_PR_INDEX(policy)];
+		params.sprstat_abandoned_sent =
+			asoc->abandoned_sent[__SCTP_PR_INDEX(policy)];
+	}
+
+	if (put_user(len, optlen)) {
+		retval = -EFAULT;
+		goto out;
+	}
+
+	if (copy_to_user(optval, &params, len)) {
+		retval = -EFAULT;
+		goto out;
+	}
+
+	retval = 0;
+
+out:
+	return retval;
+}
+
 static int sctp_getsockopt(struct sock *sk, int level, int optname,
 			   char __user *optval, int __user *optlen)
 {
@@ -6319,6 +6544,17 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname,
 	case SCTP_RECVNXTINFO:
 		retval = sctp_getsockopt_recvnxtinfo(sk, len, optval, optlen);
 		break;
+	case SCTP_PR_SUPPORTED:
+		retval = sctp_getsockopt_pr_supported(sk, len, optval, optlen);
+		break;
+	case SCTP_DEFAULT_PRINFO:
+		retval = sctp_getsockopt_default_prinfo(sk, len, optval,
+							optlen);
+		break;
+	case SCTP_PR_ASSOC_STATUS:
+		retval = sctp_getsockopt_pr_assocstatus(sk, len, optval,
+							optlen);
+		break;
 	default:
 		retval = -ENOPROTOOPT;
 		break;
@@ -6866,7 +7102,7 @@ static int sctp_msghdr_parse(const struct msghdr *msg, sctp_cmsgs_t *cmsgs)
 
 			if (cmsgs->srinfo->sinfo_flags &
 			    ~(SCTP_UNORDERED | SCTP_ADDR_OVER |
-			      SCTP_SACK_IMMEDIATELY |
+			      SCTP_SACK_IMMEDIATELY | SCTP_PR_SCTP_MASK |
 			      SCTP_ABORT | SCTP_EOF))
 				return -EINVAL;
 			break;
@@ -6890,7 +7126,7 @@ static int sctp_msghdr_parse(const struct msghdr *msg, sctp_cmsgs_t *cmsgs)
 
 			if (cmsgs->sinfo->snd_flags &
 			    ~(SCTP_UNORDERED | SCTP_ADDR_OVER |
-			      SCTP_SACK_IMMEDIATELY |
+			      SCTP_SACK_IMMEDIATELY | SCTP_PR_SCTP_MASK |
 			      SCTP_ABORT | SCTP_EOF))
 				return -EINVAL;
 			break;