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

Pull networking updates from David Miller:
 "Reasonably busy this cycle, but perhaps not as busy as in the 4.12
  merge window:

   1) Several optimizations for UDP processing under high load from
      Paolo Abeni.

   2) Support pacing internally in TCP when using the sch_fq packet
      scheduler for this is not practical. From Eric Dumazet.

   3) Support mutliple filter chains per qdisc, from Jiri Pirko.

   4) Move to 1ms TCP timestamp clock, from Eric Dumazet.

   5) Add batch dequeueing to vhost_net, from Jason Wang.

   6) Flesh out more completely SCTP checksum offload support, from
      Davide Caratti.

   7) More plumbing of extended netlink ACKs, from David Ahern, Pablo
      Neira Ayuso, and Matthias Schiffer.

   8) Add devlink support to nfp driver, from Simon Horman.

   9) Add RTM_F_FIB_MATCH flag to RTM_GETROUTE queries, from Roopa
      Prabhu.

  10) Add stack depth tracking to BPF verifier and use this information
      in the various eBPF JITs. From Alexei Starovoitov.

  11) Support XDP on qed device VFs, from Yuval Mintz.

  12) Introduce BPF PROG ID for better introspection of installed BPF
      programs. From Martin KaFai Lau.

  13) Add bpf_set_hash helper for TC bpf programs, from Daniel Borkmann.

  14) For loads, allow narrower accesses in bpf verifier checking, from
      Yonghong Song.

  15) Support MIPS in the BPF selftests and samples infrastructure, the
      MIPS eBPF JIT will be merged in via the MIPS GIT tree. From David
      Daney.

  16) Support kernel based TLS, from Dave Watson and others.

  17) Remove completely DST garbage collection, from Wei Wang.

  18) Allow installing TCP MD5 rules using prefixes, from Ivan
      Delalande.

  19) Add XDP support to Intel i40e driver, from Björn Töpel

  20) Add support for TC flower offload in nfp driver, from Simon
      Horman, Pieter Jansen van Vuuren, Benjamin LaHaise, Jakub
      Kicinski, and Bert van Leeuwen.

  21) IPSEC offloading support in mlx5, from Ilan Tayari.

  22) Add HW PTP support to macb driver, from Rafal Ozieblo.

  23) Networking refcount_t conversions, From Elena Reshetova.

  24) Add sock_ops support to BPF, from Lawrence Brako. This is useful
      for tuning the TCP sockopt settings of a group of applications,
      currently via CGROUPs"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1899 commits)
  net: phy: dp83867: add workaround for incorrect RX_CTRL pin strap
  dt-bindings: phy: dp83867: provide a workaround for incorrect RX_CTRL pin strap
  cxgb4: Support for get_ts_info ethtool method
  cxgb4: Add PTP Hardware Clock (PHC) support
  cxgb4: time stamping interface for PTP
  nfp: default to chained metadata prepend format
  nfp: remove legacy MAC address lookup
  nfp: improve order of interfaces in breakout mode
  net: macb: remove extraneous return when MACB_EXT_DESC is defined
  bpf: add missing break in for the TCP_BPF_SNDCWND_CLAMP case
  bpf: fix return in load_bpf_file
  mpls: fix rtm policy in mpls_getroute
  net, ax25: convert ax25_cb.refcount from atomic_t to refcount_t
  net, ax25: convert ax25_route.refcount from atomic_t to refcount_t
  net, ax25: convert ax25_uid_assoc.refcount from atomic_t to refcount_t
  net, sctp: convert sctp_ep_common.refcnt from atomic_t to refcount_t
  net, sctp: convert sctp_transport.refcnt from atomic_t to refcount_t
  net, sctp: convert sctp_chunk.refcnt from atomic_t to refcount_t
  net, sctp: convert sctp_datamsg.refcnt from atomic_t to refcount_t
  net, sctp: convert sctp_auth_bytes.refcnt from atomic_t to refcount_t
  ...

1 files changed, 89 insertions, 31 deletions

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 3a8318e518f1..1db478e34520 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -103,7 +103,7 @@ static int sctp_autobind(struct sock *sk);
 static void sctp_sock_migrate(struct sock *, struct sock *,
 			      struct sctp_association *, sctp_socket_type_t);
 
-static int sctp_memory_pressure;
+static unsigned long sctp_memory_pressure;
 static atomic_long_t sctp_memory_allocated;
 struct percpu_counter sctp_sockets_allocated;
 
@@ -164,7 +164,7 @@ static inline void sctp_set_owner_w(struct sctp_chunk *chunk)
 				sizeof(struct sk_buff) +
 				sizeof(struct sctp_chunk);
 
-	atomic_add(sizeof(struct sctp_chunk), &sk->sk_wmem_alloc);
+	refcount_add(sizeof(struct sctp_chunk), &sk->sk_wmem_alloc);
 	sk->sk_wmem_queued += chunk->skb->truesize;
 	sk_mem_charge(sk, chunk->skb->truesize);
 }
@@ -1494,7 +1494,7 @@ static void sctp_close(struct sock *sk, long timeout)
 
 	pr_debug("%s: sk:%p, timeout:%ld\n", __func__, sk, timeout);
 
-	lock_sock(sk);
+	lock_sock_nested(sk, SINGLE_DEPTH_NESTING);
 	sk->sk_shutdown = SHUTDOWN_MASK;
 	sk->sk_state = SCTP_SS_CLOSING;
 
@@ -1544,7 +1544,7 @@ static void sctp_close(struct sock *sk, long timeout)
 	 * held and that should be grabbed before socket lock.
 	 */
 	spin_lock_bh(&net->sctp.addr_wq_lock);
-	bh_lock_sock(sk);
+	bh_lock_sock_nested(sk);
 
 	/* Hold the sock, since sk_common_release() will put sock_put()
 	 * and we have just a little more cleanup.
@@ -1920,7 +1920,7 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len)
 	}
 
 	/* Check for invalid stream. */
-	if (sinfo->sinfo_stream >= asoc->stream->outcnt) {
+	if (sinfo->sinfo_stream >= asoc->stream.outcnt) {
 		err = -EINVAL;
 		goto out_free;
 	}
@@ -4497,8 +4497,8 @@ int sctp_get_sctp_info(struct sock *sk, struct sctp_association *asoc,
 	info->sctpi_rwnd = asoc->a_rwnd;
 	info->sctpi_unackdata = asoc->unack_data;
 	info->sctpi_penddata = sctp_tsnmap_pending(&asoc->peer.tsn_map);
-	info->sctpi_instrms = asoc->stream->incnt;
-	info->sctpi_outstrms = asoc->stream->outcnt;
+	info->sctpi_instrms = asoc->stream.incnt;
+	info->sctpi_outstrms = asoc->stream.outcnt;
 	list_for_each(pos, &asoc->base.inqueue.in_chunk_list)
 		info->sctpi_inqueue++;
 	list_for_each(pos, &asoc->outqueue.out_chunk_list)
@@ -4726,8 +4726,8 @@ static int sctp_getsockopt_sctp_status(struct sock *sk, int len,
 	status.sstat_unackdata = asoc->unack_data;
 
 	status.sstat_penddata = sctp_tsnmap_pending(&asoc->peer.tsn_map);
-	status.sstat_instrms = asoc->stream->incnt;
-	status.sstat_outstrms = asoc->stream->outcnt;
+	status.sstat_instrms = asoc->stream.incnt;
+	status.sstat_outstrms = asoc->stream.outcnt;
 	status.sstat_fragmentation_point = asoc->frag_point;
 	status.sstat_primary.spinfo_assoc_id = sctp_assoc2id(transport->asoc);
 	memcpy(&status.sstat_primary.spinfo_address, &transport->ipaddr,
@@ -4933,11 +4933,47 @@ int sctp_do_peeloff(struct sock *sk, sctp_assoc_t id, struct socket **sockp)
 }
 EXPORT_SYMBOL(sctp_do_peeloff);
 
+static int sctp_getsockopt_peeloff_common(struct sock *sk, sctp_peeloff_arg_t *peeloff,
+					  struct file **newfile, unsigned flags)
+{
+	struct socket *newsock;
+	int retval;
+
+	retval = sctp_do_peeloff(sk, peeloff->associd, &newsock);
+	if (retval < 0)
+		goto out;
+
+	/* Map the socket to an unused fd that can be returned to the user.  */
+	retval = get_unused_fd_flags(flags & SOCK_CLOEXEC);
+	if (retval < 0) {
+		sock_release(newsock);
+		goto out;
+	}
+
+	*newfile = sock_alloc_file(newsock, 0, NULL);
+	if (IS_ERR(*newfile)) {
+		put_unused_fd(retval);
+		sock_release(newsock);
+		retval = PTR_ERR(*newfile);
+		*newfile = NULL;
+		return retval;
+	}
+
+	pr_debug("%s: sk:%p, newsk:%p, sd:%d\n", __func__, sk, newsock->sk,
+		 retval);
+
+	peeloff->sd = retval;
+
+	if (flags & SOCK_NONBLOCK)
+		(*newfile)->f_flags |= O_NONBLOCK;
+out:
+	return retval;
+}
+
 static int sctp_getsockopt_peeloff(struct sock *sk, int len, char __user *optval, int __user *optlen)
 {
 	sctp_peeloff_arg_t peeloff;
-	struct socket *newsock;
-	struct file *newfile;
+	struct file *newfile = NULL;
 	int retval = 0;
 
 	if (len < sizeof(sctp_peeloff_arg_t))
@@ -4946,26 +4982,44 @@ static int sctp_getsockopt_peeloff(struct sock *sk, int len, char __user *optval
 	if (copy_from_user(&peeloff, optval, len))
 		return -EFAULT;
 
-	retval = sctp_do_peeloff(sk, peeloff.associd, &newsock);
+	retval = sctp_getsockopt_peeloff_common(sk, &peeloff, &newfile, 0);
 	if (retval < 0)
 		goto out;
 
-	/* Map the socket to an unused fd that can be returned to the user.  */
-	retval = get_unused_fd_flags(0);
-	if (retval < 0) {
-		sock_release(newsock);
-		goto out;
+	/* Return the fd mapped to the new socket.  */
+	if (put_user(len, optlen)) {
+		fput(newfile);
+		put_unused_fd(retval);
+		return -EFAULT;
 	}
 
-	newfile = sock_alloc_file(newsock, 0, NULL);
-	if (IS_ERR(newfile)) {
+	if (copy_to_user(optval, &peeloff, len)) {
+		fput(newfile);
 		put_unused_fd(retval);
-		sock_release(newsock);
-		return PTR_ERR(newfile);
+		return -EFAULT;
 	}
+	fd_install(retval, newfile);
+out:
+	return retval;
+}
 
-	pr_debug("%s: sk:%p, newsk:%p, sd:%d\n", __func__, sk, newsock->sk,
-		 retval);
+static int sctp_getsockopt_peeloff_flags(struct sock *sk, int len,
+					 char __user *optval, int __user *optlen)
+{
+	sctp_peeloff_flags_arg_t peeloff;
+	struct file *newfile = NULL;
+	int retval = 0;
+
+	if (len < sizeof(sctp_peeloff_flags_arg_t))
+		return -EINVAL;
+	len = sizeof(sctp_peeloff_flags_arg_t);
+	if (copy_from_user(&peeloff, optval, len))
+		return -EFAULT;
+
+	retval = sctp_getsockopt_peeloff_common(sk, &peeloff.p_arg,
+						&newfile, peeloff.flags);
+	if (retval < 0)
+		goto out;
 
 	/* Return the fd mapped to the new socket.  */
 	if (put_user(len, optlen)) {
@@ -4973,7 +5027,7 @@ static int sctp_getsockopt_peeloff(struct sock *sk, int len, char __user *optval
 		put_unused_fd(retval);
 		return -EFAULT;
 	}
-	peeloff.sd = retval;
+
 	if (copy_to_user(optval, &peeloff, len)) {
 		fput(newfile);
 		put_unused_fd(retval);
@@ -6033,7 +6087,8 @@ static int sctp_getsockopt_hmac_ident(struct sock *sk, int len,
 		return -EACCES;
 
 	hmacs = ep->auth_hmacs_list;
-	data_len = ntohs(hmacs->param_hdr.length) - sizeof(sctp_paramhdr_t);
+	data_len = ntohs(hmacs->param_hdr.length) -
+		   sizeof(struct sctp_paramhdr);
 
 	if (len < sizeof(struct sctp_hmacalgo) + data_len)
 		return -EINVAL;
@@ -6117,7 +6172,7 @@ static int sctp_getsockopt_peer_auth_chunks(struct sock *sk, int len,
 		goto num;
 
 	/* See if the user provided enough room for all the data */
-	num_chunks = ntohs(ch->param_hdr.length) - sizeof(sctp_paramhdr_t);
+	num_chunks = ntohs(ch->param_hdr.length) - sizeof(struct sctp_paramhdr);
 	if (len < num_chunks)
 		return -EINVAL;
 
@@ -6165,7 +6220,7 @@ static int sctp_getsockopt_local_auth_chunks(struct sock *sk, int len,
 	if (!ch)
 		goto num;
 
-	num_chunks = ntohs(ch->param_hdr.length) - sizeof(sctp_paramhdr_t);
+	num_chunks = ntohs(ch->param_hdr.length) - sizeof(struct sctp_paramhdr);
 	if (len < sizeof(struct sctp_authchunks) + num_chunks)
 		return -EINVAL;
 
@@ -6599,10 +6654,10 @@ static int sctp_getsockopt_pr_streamstatus(struct sock *sk, int len,
 		goto out;
 
 	asoc = sctp_id2assoc(sk, params.sprstat_assoc_id);
-	if (!asoc || params.sprstat_sid >= asoc->stream->outcnt)
+	if (!asoc || params.sprstat_sid >= asoc->stream.outcnt)
 		goto out;
 
-	streamout = &asoc->stream->out[params.sprstat_sid];
+	streamout = &asoc->stream.out[params.sprstat_sid];
 	if (policy == SCTP_PR_SCTP_NONE) {
 		params.sprstat_abandoned_unsent = 0;
 		params.sprstat_abandoned_sent = 0;
@@ -6758,6 +6813,9 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname,
 	case SCTP_SOCKOPT_PEELOFF:
 		retval = sctp_getsockopt_peeloff(sk, len, optval, optlen);
 		break;
+	case SCTP_SOCKOPT_PEELOFF_FLAGS:
+		retval = sctp_getsockopt_peeloff_flags(sk, len, optval, optlen);
+		break;
 	case SCTP_PEER_ADDR_PARAMS:
 		retval = sctp_getsockopt_peer_addr_params(sk, len, optval,
 							  optlen);
@@ -7563,7 +7621,7 @@ struct sk_buff *sctp_skb_recv_datagram(struct sock *sk, int flags,
 		if (flags & MSG_PEEK) {
 			skb = skb_peek(&sk->sk_receive_queue);
 			if (skb)
-				atomic_inc(&skb->users);
+				refcount_inc(&skb->users);
 		} else {
 			skb = __skb_dequeue(&sk->sk_receive_queue);
 		}
@@ -7684,7 +7742,7 @@ static void sctp_wfree(struct sk_buff *skb)
 				sizeof(struct sk_buff) +
 				sizeof(struct sctp_chunk);
 
-	atomic_sub(sizeof(struct sctp_chunk), &sk->sk_wmem_alloc);
+	WARN_ON(refcount_sub_and_test(sizeof(struct sctp_chunk), &sk->sk_wmem_alloc));
 
 	/*
 	 * This undoes what is done via sctp_set_owner_w and sk_mem_charge