Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:

 1) Significantly shrink the core networking routing structures. Result
    of http://vger.kernel.org/~davem/seoul2017_netdev_keynote.pdf

 2) Add netdevsim driver for testing various offloads, from Jakub
    Kicinski.

 3) Support cross-chip FDB operations in DSA, from Vivien Didelot.

 4) Add a 2nd listener hash table for TCP, similar to what was done for
    UDP. From Martin KaFai Lau.

 5) Add eBPF based queue selection to tun, from Jason Wang.

 6) Lockless qdisc support, from John Fastabend.

 7) SCTP stream interleave support, from Xin Long.

 8) Smoother TCP receive autotuning, from Eric Dumazet.

 9) Lots of erspan tunneling enhancements, from William Tu.

10) Add true function call support to BPF, from Alexei Starovoitov.

11) Add explicit support for GRO HW offloading, from Michael Chan.

12) Support extack generation in more netlink subsystems. From Alexander
    Aring, Quentin Monnet, and Jakub Kicinski.

13) Add 1000BaseX, flow control, and EEE support to mvneta driver. From
    Russell King.

14) Add flow table abstraction to netfilter, from Pablo Neira Ayuso.

15) Many improvements and simplifications to the NFP driver bpf JIT,
    from Jakub Kicinski.

16) Support for ipv6 non-equal cost multipath routing, from Ido
    Schimmel.

17) Add resource abstration to devlink, from Arkadi Sharshevsky.

18) Packet scheduler classifier shared filter block support, from Jiri
    Pirko.

19) Avoid locking in act_csum, from Davide Caratti.

20) devinet_ioctl() simplifications from Al viro.

21) More TCP bpf improvements from Lawrence Brakmo.

22) Add support for onlink ipv6 route flag, similar to ipv4, from David
    Ahern.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1925 commits)
  tls: Add support for encryption using async offload accelerator
  ip6mr: fix stale iterator
  net/sched: kconfig: Remove blank help texts
  openvswitch: meter: Use 64-bit arithmetic instead of 32-bit
  tcp_nv: fix potential integer overflow in tcpnv_acked
  r8169: fix RTL8168EP take too long to complete driver initialization.
  qmi_wwan: Add support for Quectel EP06
  rtnetlink: enable IFLA_IF_NETNSID for RTM_NEWLINK
  ipmr: Fix ptrdiff_t print formatting
  ibmvnic: Wait for device response when changing MAC
  qlcnic: fix deadlock bug
  tcp: release sk_frag.page in tcp_disconnect
  ipv4: Get the address of interface correctly.
  net_sched: gen_estimator: fix lockdep splat
  net: macb: Handle HRESP error
  net/mlx5e: IPoIB, Fix copy-paste bug in flow steering refactoring
  ipv6: addrconf: break critical section in addrconf_verify_rtnl()
  ipv6: change route cache aging logic
  i40e/i40evf: Update DESC_NEEDED value to reflect larger value
  bnxt_en: cleanup DIM work on device shutdown
  ...

1 files changed, 131 insertions, 29 deletions

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 737e551fbf67..356e387f82e7 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -201,6 +201,22 @@ static void sctp_for_each_tx_datachunk(struct sctp_association *asoc,
 		cb(chunk);
 }
 
+static void sctp_for_each_rx_skb(struct sctp_association *asoc, struct sock *sk,
+				 void (*cb)(struct sk_buff *, struct sock *))
+
+{
+	struct sk_buff *skb, *tmp;
+
+	sctp_skb_for_each(skb, &asoc->ulpq.lobby, tmp)
+		cb(skb, sk);
+
+	sctp_skb_for_each(skb, &asoc->ulpq.reasm, tmp)
+		cb(skb, sk);
+
+	sctp_skb_for_each(skb, &asoc->ulpq.reasm_uo, tmp)
+		cb(skb, sk);
+}
+
 /* Verify that this is a valid address. */
 static inline int sctp_verify_addr(struct sock *sk, union sctp_addr *addr,
 				   int len)
@@ -1489,7 +1505,7 @@ static void sctp_close(struct sock *sk, long timeout)
 
 	lock_sock_nested(sk, SINGLE_DEPTH_NESTING);
 	sk->sk_shutdown = SHUTDOWN_MASK;
-	sk->sk_state = SCTP_SS_CLOSING;
+	inet_sk_set_state(sk, SCTP_SS_CLOSING);
 
 	ep = sctp_sk(sk)->ep;
 
@@ -1515,6 +1531,7 @@ static void sctp_close(struct sock *sk, long timeout)
 
 		if (data_was_unread || !skb_queue_empty(&asoc->ulpq.lobby) ||
 		    !skb_queue_empty(&asoc->ulpq.reasm) ||
+		    !skb_queue_empty(&asoc->ulpq.reasm_uo) ||
 		    (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime)) {
 			struct sctp_chunk *chunk;
 
@@ -1969,7 +1986,20 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len)
 		if (err < 0)
 			goto out_free;
 
-		wait_connect = true;
+		/* If stream interleave is enabled, wait_connect has to be
+		 * done earlier than data enqueue, as it needs to make data
+		 * or idata according to asoc->intl_enable which is set
+		 * after connection is done.
+		 */
+		if (sctp_sk(asoc->base.sk)->strm_interleave) {
+			timeo = sock_sndtimeo(sk, 0);
+			err = sctp_wait_for_connect(asoc, &timeo);
+			if (err)
+				goto out_unlock;
+		} else {
+			wait_connect = true;
+		}
+
 		pr_debug("%s: we associated primitively\n", __func__);
 	}
 
@@ -2248,7 +2278,7 @@ static int sctp_setsockopt_events(struct sock *sk, char __user *optval,
 			if (!event)
 				return -ENOMEM;
 
-			sctp_ulpq_tail_event(&asoc->ulpq, event);
+			asoc->stream.si->enqueue_event(&asoc->ulpq, event);
 		}
 	}
 
@@ -3147,7 +3177,7 @@ static int sctp_setsockopt_maxseg(struct sock *sk, char __user *optval, unsigned
 		if (val == 0) {
 			val = asoc->pathmtu - sp->pf->af->net_header_len;
 			val -= sizeof(struct sctphdr) +
-			       sizeof(struct sctp_data_chunk);
+			       sctp_datachk_len(&asoc->stream);
 		}
 		asoc->user_frag = val;
 		asoc->frag_point = sctp_frag_point(asoc, asoc->pathmtu);
@@ -3317,7 +3347,10 @@ static int sctp_setsockopt_fragment_interleave(struct sock *sk,
 	if (get_user(val, (int __user *)optval))
 		return -EFAULT;
 
-	sctp_sk(sk)->frag_interleave = (val == 0) ? 0 : 1;
+	sctp_sk(sk)->frag_interleave = !!val;
+
+	if (!sctp_sk(sk)->frag_interleave)
+		sctp_sk(sk)->strm_interleave = 0;
 
 	return 0;
 }
@@ -4000,6 +4033,40 @@ out:
 	return retval;
 }
 
+static int sctp_setsockopt_interleaving_supported(struct sock *sk,
+						  char __user *optval,
+						  unsigned int optlen)
+{
+	struct sctp_sock *sp = sctp_sk(sk);
+	struct net *net = sock_net(sk);
+	struct sctp_assoc_value params;
+	int retval = -EINVAL;
+
+	if (optlen < sizeof(params))
+		goto out;
+
+	optlen = sizeof(params);
+	if (copy_from_user(&params, optval, optlen)) {
+		retval = -EFAULT;
+		goto out;
+	}
+
+	if (params.assoc_id)
+		goto out;
+
+	if (!net->sctp.intl_enable || !sp->frag_interleave) {
+		retval = -EPERM;
+		goto out;
+	}
+
+	sp->strm_interleave = !!params.assoc_value;
+
+	retval = 0;
+
+out:
+	return retval;
+}
+
 /* API 6.2 setsockopt(), getsockopt()
  *
  * Applications use setsockopt() and getsockopt() to set or retrieve
@@ -4187,6 +4254,10 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname,
 	case SCTP_STREAM_SCHEDULER_VALUE:
 		retval = sctp_setsockopt_scheduler_value(sk, optval, optlen);
 		break;
+	case SCTP_INTERLEAVING_SUPPORTED:
+		retval = sctp_setsockopt_interleaving_supported(sk, optval,
+								optlen);
+		break;
 	default:
 		retval = -ENOPROTOOPT;
 		break;
@@ -4563,7 +4634,7 @@ static void sctp_shutdown(struct sock *sk, int how)
 	if (how & SEND_SHUTDOWN && !list_empty(&ep->asocs)) {
 		struct sctp_association *asoc;
 
-		sk->sk_state = SCTP_SS_CLOSING;
+		inet_sk_set_state(sk, SCTP_SS_CLOSING);
 		asoc = list_entry(ep->asocs.next,
 				  struct sctp_association, asocs);
 		sctp_primitive_SHUTDOWN(net, asoc, NULL);
@@ -4657,20 +4728,11 @@ int sctp_get_sctp_info(struct sock *sk, struct sctp_association *asoc,
 EXPORT_SYMBOL_GPL(sctp_get_sctp_info);
 
 /* use callback to avoid exporting the core structure */
-int sctp_transport_walk_start(struct rhashtable_iter *iter)
+void sctp_transport_walk_start(struct rhashtable_iter *iter)
 {
-	int err;
-
 	rhltable_walk_enter(&sctp_transport_hashtable, iter);
 
-	err = rhashtable_walk_start(iter);
-	if (err && err != -EAGAIN) {
-		rhashtable_walk_stop(iter);
-		rhashtable_walk_exit(iter);
-		return err;
-	}
-
-	return 0;
+	rhashtable_walk_start(iter);
 }
 
 void sctp_transport_walk_stop(struct rhashtable_iter *iter)
@@ -4764,9 +4826,8 @@ int sctp_for_each_transport(int (*cb)(struct sctp_transport *, void *),
 	int ret;
 
 again:
-	ret = sctp_transport_walk_start(&hti);
-	if (ret)
-		return ret;
+	ret = 0;
+	sctp_transport_walk_start(&hti);
 
 	tsp = sctp_transport_get_idx(net, &hti, *pos + 1);
 	for (; !IS_ERR_OR_NULL(tsp); tsp = sctp_transport_get_next(net, &hti)) {
@@ -6965,6 +7026,47 @@ out:
 	return retval;
 }
 
+static int sctp_getsockopt_interleaving_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->intl_enable;
+	} else if (!params.assoc_id) {
+		struct sctp_sock *sp = sctp_sk(sk);
+
+		params.assoc_value = sp->strm_interleave;
+	} 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(struct sock *sk, int level, int optname,
 			   char __user *optval, int __user *optlen)
 {
@@ -7155,6 +7257,10 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname,
 		retval = sctp_getsockopt_scheduler_value(sk, len, optval,
 							 optlen);
 		break;
+	case SCTP_INTERLEAVING_SUPPORTED:
+		retval = sctp_getsockopt_interleaving_supported(sk, len, optval,
+								optlen);
+		break;
 	default:
 		retval = -ENOPROTOOPT;
 		break;
@@ -7389,13 +7495,13 @@ static int sctp_listen_start(struct sock *sk, int backlog)
 	 * sockets.
 	 *
 	 */
-	sk->sk_state = SCTP_SS_LISTENING;
+	inet_sk_set_state(sk, SCTP_SS_LISTENING);
 	if (!ep->base.bind_addr.port) {
 		if (sctp_autobind(sk))
 			return -EAGAIN;
 	} else {
 		if (sctp_get_port(sk, inet_sk(sk)->inet_num)) {
-			sk->sk_state = SCTP_SS_CLOSED;
+			inet_sk_set_state(sk, SCTP_SS_CLOSED);
 			return -EADDRINUSE;
 		}
 	}
@@ -8388,11 +8494,7 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk,
 
 	}
 
-	sctp_skb_for_each(skb, &assoc->ulpq.reasm, tmp)
-		sctp_skb_set_owner_r_frag(skb, newsk);
-
-	sctp_skb_for_each(skb, &assoc->ulpq.lobby, tmp)
-		sctp_skb_set_owner_r_frag(skb, newsk);
+	sctp_for_each_rx_skb(assoc, newsk, sctp_skb_set_owner_r_frag);
 
 	/* Set the type of socket to indicate that it is peeled off from the
 	 * original UDP-style socket or created with the accept() call on a
@@ -8418,10 +8520,10 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk,
 	 * is called, set RCV_SHUTDOWN flag.
 	 */
 	if (sctp_state(assoc, CLOSED) && sctp_style(newsk, TCP)) {
-		newsk->sk_state = SCTP_SS_CLOSED;
+		inet_sk_set_state(newsk, SCTP_SS_CLOSED);
 		newsk->sk_shutdown |= RCV_SHUTDOWN;
 	} else {
-		newsk->sk_state = SCTP_SS_ESTABLISHED;
+		inet_sk_set_state(newsk, SCTP_SS_ESTABLISHED);
 	}
 
 	release_sock(newsk);