1 files changed, 147 insertions, 32 deletions

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 939b8d2595bc..0b485952a71c 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -384,7 +384,7 @@ static int sctp_do_bind(struct sock *sk, union sctp_addr *addr, int len)
 		}
 	}
 
-	if (snum && snum < inet_prot_sock(net) &&
+	if (snum && inet_port_requires_bind_service(net, snum) &&
 	    !ns_capable(net->user_ns, CAP_NET_BIND_SERVICE))
 		return -EACCES;
 
@@ -1061,7 +1061,7 @@ static int sctp_connect_new_asoc(struct sctp_endpoint *ep,
 		if (sctp_autobind(sk))
 			return -EAGAIN;
 	} else {
-		if (ep->base.bind_addr.port < inet_prot_sock(net) &&
+		if (inet_port_requires_bind_service(net, ep->base.bind_addr.port) &&
 		    !ns_capable(net->user_ns, CAP_NET_BIND_SERVICE))
 			return -EACCES;
 	}
@@ -3943,18 +3943,22 @@ static int sctp_setsockopt_auto_asconf(struct sock *sk, char __user *optval,
  */
 static int sctp_setsockopt_paddr_thresholds(struct sock *sk,
 					    char __user *optval,
-					    unsigned int optlen)
+					    unsigned int optlen, bool v2)
 {
-	struct sctp_paddrthlds val;
+	struct sctp_paddrthlds_v2 val;
 	struct sctp_transport *trans;
 	struct sctp_association *asoc;
+	int len;
 
-	if (optlen < sizeof(struct sctp_paddrthlds))
+	len = v2 ? sizeof(val) : sizeof(struct sctp_paddrthlds);
+	if (optlen < len)
 		return -EINVAL;
-	if (copy_from_user(&val, (struct sctp_paddrthlds __user *)optval,
-			   sizeof(struct sctp_paddrthlds)))
+	if (copy_from_user(&val, optval, len))
 		return -EFAULT;
 
+	if (v2 && val.spt_pathpfthld > val.spt_pathcpthld)
+		return -EINVAL;
+
 	if (!sctp_is_any(sk, (const union sctp_addr *)&val.spt_address)) {
 		trans = sctp_addr_id2transport(sk, &val.spt_address,
 					       val.spt_assoc_id);
@@ -3963,6 +3967,8 @@ static int sctp_setsockopt_paddr_thresholds(struct sock *sk,
 
 		if (val.spt_pathmaxrxt)
 			trans->pathmaxrxt = val.spt_pathmaxrxt;
+		if (v2)
+			trans->ps_retrans = val.spt_pathcpthld;
 		trans->pf_retrans = val.spt_pathpfthld;
 
 		return 0;
@@ -3978,17 +3984,23 @@ static int sctp_setsockopt_paddr_thresholds(struct sock *sk,
 				    transports) {
 			if (val.spt_pathmaxrxt)
 				trans->pathmaxrxt = val.spt_pathmaxrxt;
+			if (v2)
+				trans->ps_retrans = val.spt_pathcpthld;
 			trans->pf_retrans = val.spt_pathpfthld;
 		}
 
 		if (val.spt_pathmaxrxt)
 			asoc->pathmaxrxt = val.spt_pathmaxrxt;
+		if (v2)
+			asoc->ps_retrans = val.spt_pathcpthld;
 		asoc->pf_retrans = val.spt_pathpfthld;
 	} else {
 		struct sctp_sock *sp = sctp_sk(sk);
 
 		if (val.spt_pathmaxrxt)
 			sp->pathmaxrxt = val.spt_pathmaxrxt;
+		if (v2)
+			sp->ps_retrans = val.spt_pathcpthld;
 		sp->pf_retrans = val.spt_pathpfthld;
 	}
 
@@ -4589,6 +4601,40 @@ out:
 	return retval;
 }
 
+static int sctp_setsockopt_pf_expose(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;
+	}
+
+	if (params.assoc_value > SCTP_PF_EXPOSE_MAX)
+		goto out;
+
+	asoc = sctp_id2assoc(sk, params.assoc_id);
+	if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC &&
+	    sctp_style(sk, UDP))
+		goto out;
+
+	if (asoc)
+		asoc->pf_expose = params.assoc_value;
+	else
+		sctp_sk(sk)->pf_expose = params.assoc_value;
+	retval = 0;
+
+out:
+	return retval;
+}
+
 /* API 6.2 setsockopt(), getsockopt()
  *
  * Applications use setsockopt() and getsockopt() to set or retrieve
@@ -4744,7 +4790,12 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname,
 		retval = sctp_setsockopt_auto_asconf(sk, optval, optlen);
 		break;
 	case SCTP_PEER_ADDR_THLDS:
-		retval = sctp_setsockopt_paddr_thresholds(sk, optval, optlen);
+		retval = sctp_setsockopt_paddr_thresholds(sk, optval, optlen,
+							  false);
+		break;
+	case SCTP_PEER_ADDR_THLDS_V2:
+		retval = sctp_setsockopt_paddr_thresholds(sk, optval, optlen,
+							  true);
 		break;
 	case SCTP_RECVRCVINFO:
 		retval = sctp_setsockopt_recvrcvinfo(sk, optval, optlen);
@@ -4798,6 +4849,9 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname,
 	case SCTP_ECN_SUPPORTED:
 		retval = sctp_setsockopt_ecn_supported(sk, optval, optlen);
 		break;
+	case SCTP_EXPOSE_POTENTIALLY_FAILED_STATE:
+		retval = sctp_setsockopt_pf_expose(sk, optval, optlen);
+		break;
 	default:
 		retval = -ENOPROTOOPT;
 		break;
@@ -5041,6 +5095,8 @@ static int sctp_init_sock(struct sock *sk)
 	sp->hbinterval  = net->sctp.hb_interval;
 	sp->pathmaxrxt  = net->sctp.max_retrans_path;
 	sp->pf_retrans  = net->sctp.pf_retrans;
+	sp->ps_retrans  = net->sctp.ps_retrans;
+	sp->pf_expose   = net->sctp.pf_expose;
 	sp->pathmtu     = 0; /* allow default discovery */
 	sp->sackdelay   = net->sctp.sack_timeout;
 	sp->sackfreq	= 2;
@@ -5521,8 +5577,16 @@ static int sctp_getsockopt_peer_addr_info(struct sock *sk, int len,
 
 	transport = sctp_addr_id2transport(sk, &pinfo.spinfo_address,
 					   pinfo.spinfo_assoc_id);
-	if (!transport)
-		return -EINVAL;
+	if (!transport) {
+		retval = -EINVAL;
+		goto out;
+	}
+
+	if (transport->state == SCTP_PF &&
+	    transport->asoc->pf_expose == SCTP_PF_EXPOSE_DISABLE) {
+		retval = -EACCES;
+		goto out;
+	}
 
 	pinfo.spinfo_assoc_id = sctp_assoc2id(transport->asoc);
 	pinfo.spinfo_state = transport->state;
@@ -7170,18 +7234,19 @@ static int sctp_getsockopt_assoc_ids(struct sock *sk, int len,
  * http://www.ietf.org/id/draft-nishida-tsvwg-sctp-failover-05.txt
  */
 static int sctp_getsockopt_paddr_thresholds(struct sock *sk,
-					    char __user *optval,
-					    int len,
-					    int __user *optlen)
+					    char __user *optval, int len,
+					    int __user *optlen, bool v2)
 {
-	struct sctp_paddrthlds val;
+	struct sctp_paddrthlds_v2 val;
 	struct sctp_transport *trans;
 	struct sctp_association *asoc;
+	int min;
 
-	if (len < sizeof(struct sctp_paddrthlds))
+	min = v2 ? sizeof(val) : sizeof(struct sctp_paddrthlds);
+	if (len < min)
 		return -EINVAL;
-	len = sizeof(struct sctp_paddrthlds);
-	if (copy_from_user(&val, (struct sctp_paddrthlds __user *)optval, len))
+	len = min;
+	if (copy_from_user(&val, optval, len))
 		return -EFAULT;
 
 	if (!sctp_is_any(sk, (const union sctp_addr *)&val.spt_address)) {
@@ -7192,6 +7257,7 @@ static int sctp_getsockopt_paddr_thresholds(struct sock *sk,
 
 		val.spt_pathmaxrxt = trans->pathmaxrxt;
 		val.spt_pathpfthld = trans->pf_retrans;
+		val.spt_pathcpthld = trans->ps_retrans;
 
 		goto out;
 	}
@@ -7204,11 +7270,13 @@ static int sctp_getsockopt_paddr_thresholds(struct sock *sk,
 	if (asoc) {
 		val.spt_pathpfthld = asoc->pf_retrans;
 		val.spt_pathmaxrxt = asoc->pathmaxrxt;
+		val.spt_pathcpthld = asoc->ps_retrans;
 	} else {
 		struct sctp_sock *sp = sctp_sk(sk);
 
 		val.spt_pathpfthld = sp->pf_retrans;
 		val.spt_pathmaxrxt = sp->pathmaxrxt;
+		val.spt_pathcpthld = sp->ps_retrans;
 	}
 
 out:
@@ -7900,6 +7968,45 @@ out:
 	return retval;
 }
 
+static int sctp_getsockopt_pf_expose(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_id != SCTP_FUTURE_ASSOC &&
+	    sctp_style(sk, UDP)) {
+		retval = -EINVAL;
+		goto out;
+	}
+
+	params.assoc_value = asoc ? asoc->pf_expose
+				  : sctp_sk(sk)->pf_expose;
+
+	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(struct sock *sk, int level, int optname,
 			   char __user *optval, int __user *optlen)
 {
@@ -8049,7 +8156,12 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname,
 		retval = sctp_getsockopt_auto_asconf(sk, len, optval, optlen);
 		break;
 	case SCTP_PEER_ADDR_THLDS:
-		retval = sctp_getsockopt_paddr_thresholds(sk, optval, len, optlen);
+		retval = sctp_getsockopt_paddr_thresholds(sk, optval, len,
+							  optlen, false);
+		break;
+	case SCTP_PEER_ADDR_THLDS_V2:
+		retval = sctp_getsockopt_paddr_thresholds(sk, optval, len,
+							  optlen, true);
 		break;
 	case SCTP_GET_ASSOC_STATS:
 		retval = sctp_getsockopt_assoc_stats(sk, len, optval, optlen);
@@ -8112,6 +8224,9 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname,
 	case SCTP_ECN_SUPPORTED:
 		retval = sctp_getsockopt_ecn_supported(sk, len, optval, optlen);
 		break;
+	case SCTP_EXPOSE_POTENTIALLY_FAILED_STATE:
+		retval = sctp_getsockopt_pf_expose(sk, len, optval, optlen);
+		break;
 	default:
 		retval = -ENOPROTOOPT;
 		break;
@@ -8152,6 +8267,7 @@ static int sctp_get_port_local(struct sock *sk, union sctp_addr *addr)
 	struct sctp_sock *sp = sctp_sk(sk);
 	bool reuse = (sk->sk_reuse || sp->reuse);
 	struct sctp_bind_hashbucket *head; /* hash list */
+	struct net *net = sock_net(sk);
 	kuid_t uid = sock_i_uid(sk);
 	struct sctp_bind_bucket *pp;
 	unsigned short snum;
@@ -8167,7 +8283,6 @@ static int sctp_get_port_local(struct sock *sk, union sctp_addr *addr)
 		/* Search for an available port. */
 		int low, high, remaining, index;
 		unsigned int rover;
-		struct net *net = sock_net(sk);
 
 		inet_get_local_port_range(net, &low, &high);
 		remaining = (high - low) + 1;
@@ -8179,12 +8294,12 @@ static int sctp_get_port_local(struct sock *sk, union sctp_addr *addr)
 				rover = low;
 			if (inet_is_local_reserved_port(net, rover))
 				continue;
-			index = sctp_phashfn(sock_net(sk), rover);
+			index = sctp_phashfn(net, rover);
 			head = &sctp_port_hashtable[index];
 			spin_lock(&head->lock);
 			sctp_for_each_hentry(pp, &head->chain)
 				if ((pp->port == rover) &&
-				    net_eq(sock_net(sk), pp->net))
+				    net_eq(net, pp->net))
 					goto next;
 			break;
 		next:
@@ -8208,10 +8323,10 @@ static int sctp_get_port_local(struct sock *sk, union sctp_addr *addr)
 		 * to the port number (snum) - we detect that with the
 		 * port iterator, pp being NULL.
 		 */
-		head = &sctp_port_hashtable[sctp_phashfn(sock_net(sk), snum)];
+		head = &sctp_port_hashtable[sctp_phashfn(net, snum)];
 		spin_lock(&head->lock);
 		sctp_for_each_hentry(pp, &head->chain) {
-			if ((pp->port == snum) && net_eq(pp->net, sock_net(sk)))
+			if ((pp->port == snum) && net_eq(pp->net, net))
 				goto pp_found;
 		}
 	}
@@ -8267,7 +8382,7 @@ pp_found:
 pp_not_found:
 	/* If there was a hash table miss, create a new port.  */
 	ret = 1;
-	if (!pp && !(pp = sctp_bucket_create(head, sock_net(sk), snum)))
+	if (!pp && !(pp = sctp_bucket_create(head, net, snum)))
 		goto fail_unlock;
 
 	/* In either case (hit or miss), make sure fastreuse is 1 only
@@ -8376,7 +8491,7 @@ static int sctp_listen_start(struct sock *sk, int backlog)
 		}
 	}
 
-	sk->sk_max_ack_backlog = backlog;
+	WRITE_ONCE(sk->sk_max_ack_backlog, backlog);
 	return sctp_hash_endpoint(ep);
 }
 
@@ -8430,7 +8545,7 @@ int sctp_inet_listen(struct socket *sock, int backlog)
 
 	/* If we are already listening, just update the backlog */
 	if (sctp_sstate(sk, LISTENING))
-		sk->sk_max_ack_backlog = backlog;
+		WRITE_ONCE(sk->sk_max_ack_backlog, backlog);
 	else {
 		err = sctp_listen_start(sk, backlog);
 		if (err)
@@ -8476,7 +8591,7 @@ __poll_t sctp_poll(struct file *file, struct socket *sock, poll_table *wait)
 	mask = 0;
 
 	/* Is there any exceptional events?  */
-	if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
+	if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue))
 		mask |= EPOLLERR |
 			(sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0);
 	if (sk->sk_shutdown & RCV_SHUTDOWN)
@@ -8485,7 +8600,7 @@ __poll_t sctp_poll(struct file *file, struct socket *sock, poll_table *wait)
 		mask |= EPOLLHUP;
 
 	/* Is it readable?  Reconsider this code with TCP-style support.  */
-	if (!skb_queue_empty(&sk->sk_receive_queue))
+	if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
 		mask |= EPOLLIN | EPOLLRDNORM;
 
 	/* The association is either gone or not ready.  */
@@ -8871,7 +8986,7 @@ struct sk_buff *sctp_skb_recv_datagram(struct sock *sk, int flags,
 		if (sk_can_busy_loop(sk)) {
 			sk_busy_loop(sk, noblock);
 
-			if (!skb_queue_empty(&sk->sk_receive_queue))
+			if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
 				continue;
 		}
 
@@ -9306,7 +9421,7 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk,
 	newinet->inet_rcv_saddr = inet->inet_rcv_saddr;
 	newinet->inet_dport = htons(asoc->peer.port);
 	newinet->pmtudisc = inet->pmtudisc;
-	newinet->inet_id = asoc->next_tsn ^ jiffies;
+	newinet->inet_id = prandom_u32();
 
 	newinet->uc_ttl = inet->uc_ttl;
 	newinet->mc_loop = 1;
@@ -9500,7 +9615,7 @@ struct proto sctp_prot = {
 	.backlog_rcv =	sctp_backlog_rcv,
 	.hash        =	sctp_hash,
 	.unhash      =	sctp_unhash,
-	.get_port    =	sctp_get_port,
+	.no_autobind =	true,
 	.obj_size    =  sizeof(struct sctp_sock),
 	.useroffset  =  offsetof(struct sctp_sock, subscribe),
 	.usersize    =  offsetof(struct sctp_sock, initmsg) -
@@ -9542,7 +9657,7 @@ struct proto sctpv6_prot = {
 	.backlog_rcv	= sctp_backlog_rcv,
 	.hash		= sctp_hash,
 	.unhash		= sctp_unhash,
-	.get_port	= sctp_get_port,
+	.no_autobind	= true,
 	.obj_size	= sizeof(struct sctp6_sock),
 	.useroffset	= offsetof(struct sctp6_sock, sctp.subscribe),
 	.usersize	= offsetof(struct sctp6_sock, sctp.initmsg) -