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, 56 insertions, 44 deletions

diff --git a/net/core/datagram.c b/net/core/datagram.c
index f9653987c0f9..6877c43cc92d 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -161,6 +161,45 @@ done:
 	return skb;
 }
 
+struct sk_buff *__skb_try_recv_from_queue(struct sock *sk,
+					  struct sk_buff_head *queue,
+					  unsigned int flags,
+					  void (*destructor)(struct sock *sk,
+							   struct sk_buff *skb),
+					  int *peeked, int *off, int *err,
+					  struct sk_buff **last)
+{
+	struct sk_buff *skb;
+	int _off = *off;
+
+	*last = queue->prev;
+	skb_queue_walk(queue, skb) {
+		if (flags & MSG_PEEK) {
+			if (_off >= skb->len && (skb->len || _off ||
+						 skb->peeked)) {
+				_off -= skb->len;
+				continue;
+			}
+			if (!skb->len) {
+				skb = skb_set_peeked(skb);
+				if (unlikely(IS_ERR(skb))) {
+					*err = PTR_ERR(skb);
+					return NULL;
+				}
+			}
+			*peeked = 1;
+			refcount_inc(&skb->users);
+		} else {
+			__skb_unlink(skb, queue);
+			if (destructor)
+				destructor(sk, skb);
+		}
+		*off = _off;
+		return skb;
+	}
+	return NULL;
+}
+
 /**
  *	__skb_try_recv_datagram - Receive a datagram skbuff
  *	@sk: socket
@@ -222,40 +261,14 @@ struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned int flags,
 		 * Look at current nfs client by the way...
 		 * However, this function was correct in any case. 8)
 		 */
-		int _off = *off;
-
-		*last = (struct sk_buff *)queue;
 		spin_lock_irqsave(&queue->lock, cpu_flags);
-		skb_queue_walk(queue, skb) {
-			*last = skb;
-			if (flags & MSG_PEEK) {
-				if (_off >= skb->len && (skb->len || _off ||
-							 skb->peeked)) {
-					_off -= skb->len;
-					continue;
-				}
-				if (!skb->len) {
-					skb = skb_set_peeked(skb);
-					if (IS_ERR(skb)) {
-						error = PTR_ERR(skb);
-						spin_unlock_irqrestore(&queue->lock,
-								       cpu_flags);
-						goto no_packet;
-					}
-				}
-				*peeked = 1;
-				atomic_inc(&skb->users);
-			} else {
-				__skb_unlink(skb, queue);
-				if (destructor)
-					destructor(sk, skb);
-			}
-			spin_unlock_irqrestore(&queue->lock, cpu_flags);
-			*off = _off;
-			return skb;
-		}
-
+		skb = __skb_try_recv_from_queue(sk, queue, flags, destructor,
+						peeked, off, &error, last);
 		spin_unlock_irqrestore(&queue->lock, cpu_flags);
+		if (error)
+			goto no_packet;
+		if (skb)
+			return skb;
 
 		if (!sk_can_busy_loop(sk))
 			break;
@@ -317,9 +330,7 @@ void __skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb, int len)
 {
 	bool slow;
 
-	if (likely(atomic_read(&skb->users) == 1))
-		smp_rmb();
-	else if (likely(!atomic_dec_and_test(&skb->users))) {
+	if (!skb_unref(skb)) {
 		sk_peek_offset_bwd(sk, len);
 		return;
 	}
@@ -335,8 +346,8 @@ void __skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb, int len)
 }
 EXPORT_SYMBOL(__skb_free_datagram_locked);
 
-int __sk_queue_drop_skb(struct sock *sk, struct sk_buff *skb,
-			unsigned int flags,
+int __sk_queue_drop_skb(struct sock *sk, struct sk_buff_head *sk_queue,
+			struct sk_buff *skb, unsigned int flags,
 			void (*destructor)(struct sock *sk,
 					   struct sk_buff *skb))
 {
@@ -344,15 +355,15 @@ int __sk_queue_drop_skb(struct sock *sk, struct sk_buff *skb,
 
 	if (flags & MSG_PEEK) {
 		err = -ENOENT;
-		spin_lock_bh(&sk->sk_receive_queue.lock);
-		if (skb == skb_peek(&sk->sk_receive_queue)) {
-			__skb_unlink(skb, &sk->sk_receive_queue);
-			atomic_dec(&skb->users);
+		spin_lock_bh(&sk_queue->lock);
+		if (skb == skb_peek(sk_queue)) {
+			__skb_unlink(skb, sk_queue);
+			refcount_dec(&skb->users);
 			if (destructor)
 				destructor(sk, skb);
 			err = 0;
 		}
-		spin_unlock_bh(&sk->sk_receive_queue.lock);
+		spin_unlock_bh(&sk_queue->lock);
 	}
 
 	atomic_inc(&sk->sk_drops);
@@ -383,7 +394,8 @@ EXPORT_SYMBOL(__sk_queue_drop_skb);
 
 int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags)
 {
-	int err = __sk_queue_drop_skb(sk, skb, flags, NULL);
+	int err = __sk_queue_drop_skb(sk, &sk->sk_receive_queue, skb, flags,
+				      NULL);
 
 	kfree_skb(skb);
 	sk_mem_reclaim_partial(sk);
@@ -602,7 +614,7 @@ int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *from)
 		skb->data_len += copied;
 		skb->len += copied;
 		skb->truesize += truesize;
-		atomic_add(truesize, &skb->sk->sk_wmem_alloc);
+		refcount_add(truesize, &skb->sk->sk_wmem_alloc);
 		while (copied) {
 			int size = min_t(int, copied, PAGE_SIZE - start);
 			skb_fill_page_desc(skb, frag++, pages[n], start, size);