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

Pull networking updates from David Miller:

 1) More iov_iter conversion work from Al Viro.

    [ The "crypto: switch af_alg_make_sg() to iov_iter" commit was
      wrong, and this pull actually adds an extra commit on top of the
      branch I'm pulling to fix that up, so that the pre-merge state is
      ok.   - Linus ]

 2) Various optimizations to the ipv4 forwarding information base trie
    lookup implementation.  From Alexander Duyck.

 3) Remove sock_iocb altogether, from CHristoph Hellwig.

 4) Allow congestion control algorithm selection via routing metrics.
    From Daniel Borkmann.

 5) Make ipv4 uncached route list per-cpu, from Eric Dumazet.

 6) Handle rfs hash collisions more gracefully, also from Eric Dumazet.

 7) Add xmit_more support to r8169, e1000, and e1000e drivers.  From
    Florian Westphal.

 8) Transparent Ethernet Bridging support for GRO, from Jesse Gross.

 9) Add BPF packet actions to packet scheduler, from Jiri Pirko.

10) Add support for uniqu flow IDs to openvswitch, from Joe Stringer.

11) New NetCP ethernet driver, from Muralidharan Karicheri and Wingman
    Kwok.

12) More sanely handle out-of-window dupacks, which can result in
    serious ACK storms.  From Neal Cardwell.

13) Various rhashtable bug fixes and enhancements, from Herbert Xu,
    Patrick McHardy, and Thomas Graf.

14) Support xmit_more in be2net, from Sathya Perla.

15) Group Policy extensions for vxlan, from Thomas Graf.

16) Remove Checksum Offload support for vxlan, from Tom Herbert.

17) Like ipv4, support lockless transmit over ipv6 UDP sockets.  From
    Vlad Yasevich.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1494+1 commits)
  crypto: fix af_alg_make_sg() conversion to iov_iter
  ipv4: Namespecify TCP PMTU mechanism
  i40e: Fix for stats init function call in Rx setup
  tcp: don't include Fast Open option in SYN-ACK on pure SYN-data
  openvswitch: Only set TUNNEL_VXLAN_OPT if VXLAN-GBP metadata is set
  ipv6: Make __ipv6_select_ident static
  ipv6: Fix fragment id assignment on LE arches.
  bridge: Fix inability to add non-vlan fdb entry
  net: Mellanox: Delete unnecessary checks before the function call "vunmap"
  cxgb4: Add support in cxgb4 to get expansion rom version via ethtool
  ethtool: rename reserved1 memeber in ethtool_drvinfo for expansion ROM version
  net: dsa: Remove redundant phy_attach()
  IB/mlx4: Reset flow support for IB kernel ULPs
  IB/mlx4: Always use the correct port for mirrored multicast attachments
  net/bonding: Fix potential bad memory access during bonding events
  tipc: remove tipc_snprintf
  tipc: nl compat add noop and remove legacy nl framework
  tipc: convert legacy nl stats show to nl compat
  tipc: convert legacy nl net id get to nl compat
  tipc: convert legacy nl net id set to nl compat
  ...

2 files changed, 31 insertions, 45 deletions

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 8e1b10274b0..526b6edab01 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1445,7 +1445,6 @@ static void maybe_add_creds(struct sk_buff *skb, const struct socket *sock,
 static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock,
 			      struct msghdr *msg, size_t len)
 {
-	struct sock_iocb *siocb = kiocb_to_siocb(kiocb);
 	struct sock *sk = sock->sk;
 	struct net *net = sock_net(sk);
 	struct unix_sock *u = unix_sk(sk);
@@ -1456,14 +1455,12 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock,
 	unsigned int hash;
 	struct sk_buff *skb;
 	long timeo;
-	struct scm_cookie tmp_scm;
+	struct scm_cookie scm;
 	int max_level;
 	int data_len = 0;
 
-	if (NULL == siocb->scm)
-		siocb->scm = &tmp_scm;
 	wait_for_unix_gc();
-	err = scm_send(sock, msg, siocb->scm, false);
+	err = scm_send(sock, msg, &scm, false);
 	if (err < 0)
 		return err;
 
@@ -1507,11 +1504,11 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock,
 	if (skb == NULL)
 		goto out;
 
-	err = unix_scm_to_skb(siocb->scm, skb, true);
+	err = unix_scm_to_skb(&scm, skb, true);
 	if (err < 0)
 		goto out_free;
 	max_level = err + 1;
-	unix_get_secdata(siocb->scm, skb);
+	unix_get_secdata(&scm, skb);
 
 	skb_put(skb, len - data_len);
 	skb->data_len = data_len;
@@ -1606,7 +1603,7 @@ restart:
 	unix_state_unlock(other);
 	other->sk_data_ready(other);
 	sock_put(other);
-	scm_destroy(siocb->scm);
+	scm_destroy(&scm);
 	return len;
 
 out_unlock:
@@ -1616,7 +1613,7 @@ out_free:
 out:
 	if (other)
 		sock_put(other);
-	scm_destroy(siocb->scm);
+	scm_destroy(&scm);
 	return err;
 }
 
@@ -1628,21 +1625,18 @@ out:
 static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
 			       struct msghdr *msg, size_t len)
 {
-	struct sock_iocb *siocb = kiocb_to_siocb(kiocb);
 	struct sock *sk = sock->sk;
 	struct sock *other = NULL;
 	int err, size;
 	struct sk_buff *skb;
 	int sent = 0;
-	struct scm_cookie tmp_scm;
+	struct scm_cookie scm;
 	bool fds_sent = false;
 	int max_level;
 	int data_len;
 
-	if (NULL == siocb->scm)
-		siocb->scm = &tmp_scm;
 	wait_for_unix_gc();
-	err = scm_send(sock, msg, siocb->scm, false);
+	err = scm_send(sock, msg, &scm, false);
 	if (err < 0)
 		return err;
 
@@ -1683,7 +1677,7 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
 			goto out_err;
 
 		/* Only send the fds in the first buffer */
-		err = unix_scm_to_skb(siocb->scm, skb, !fds_sent);
+		err = unix_scm_to_skb(&scm, skb, !fds_sent);
 		if (err < 0) {
 			kfree_skb(skb);
 			goto out_err;
@@ -1715,8 +1709,7 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
 		sent += size;
 	}
 
-	scm_destroy(siocb->scm);
-	siocb->scm = NULL;
+	scm_destroy(&scm);
 
 	return sent;
 
@@ -1728,8 +1721,7 @@ pipe_err:
 		send_sig(SIGPIPE, current, 0);
 	err = -EPIPE;
 out_err:
-	scm_destroy(siocb->scm);
-	siocb->scm = NULL;
+	scm_destroy(&scm);
 	return sent ? : err;
 }
 
@@ -1778,8 +1770,7 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock,
 			      struct msghdr *msg, size_t size,
 			      int flags)
 {
-	struct sock_iocb *siocb = kiocb_to_siocb(iocb);
-	struct scm_cookie tmp_scm;
+	struct scm_cookie scm;
 	struct sock *sk = sock->sk;
 	struct unix_sock *u = unix_sk(sk);
 	int noblock = flags & MSG_DONTWAIT;
@@ -1831,16 +1822,14 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock,
 	if (sock_flag(sk, SOCK_RCVTSTAMP))
 		__sock_recv_timestamp(msg, sk, skb);
 
-	if (!siocb->scm) {
-		siocb->scm = &tmp_scm;
-		memset(&tmp_scm, 0, sizeof(tmp_scm));
-	}
-	scm_set_cred(siocb->scm, UNIXCB(skb).pid, UNIXCB(skb).uid, UNIXCB(skb).gid);
-	unix_set_secdata(siocb->scm, skb);
+	memset(&scm, 0, sizeof(scm));
+
+	scm_set_cred(&scm, UNIXCB(skb).pid, UNIXCB(skb).uid, UNIXCB(skb).gid);
+	unix_set_secdata(&scm, skb);
 
 	if (!(flags & MSG_PEEK)) {
 		if (UNIXCB(skb).fp)
-			unix_detach_fds(siocb->scm, skb);
+			unix_detach_fds(&scm, skb);
 
 		sk_peek_offset_bwd(sk, skb->len);
 	} else {
@@ -1860,11 +1849,11 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock,
 		sk_peek_offset_fwd(sk, size);
 
 		if (UNIXCB(skb).fp)
-			siocb->scm->fp = scm_fp_dup(UNIXCB(skb).fp);
+			scm.fp = scm_fp_dup(UNIXCB(skb).fp);
 	}
 	err = (flags & MSG_TRUNC) ? skb->len - skip : size;
 
-	scm_recv(sock, msg, siocb->scm, flags);
+	scm_recv(sock, msg, &scm, flags);
 
 out_free:
 	skb_free_datagram(sk, skb);
@@ -1915,8 +1904,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 			       struct msghdr *msg, size_t size,
 			       int flags)
 {
-	struct sock_iocb *siocb = kiocb_to_siocb(iocb);
-	struct scm_cookie tmp_scm;
+	struct scm_cookie scm;
 	struct sock *sk = sock->sk;
 	struct unix_sock *u = unix_sk(sk);
 	DECLARE_SOCKADDR(struct sockaddr_un *, sunaddr, msg->msg_name);
@@ -1943,10 +1931,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 	 * while sleeps in memcpy_tomsg
 	 */
 
-	if (!siocb->scm) {
-		siocb->scm = &tmp_scm;
-		memset(&tmp_scm, 0, sizeof(tmp_scm));
-	}
+	memset(&scm, 0, sizeof(scm));
 
 	err = mutex_lock_interruptible(&u->readlock);
 	if (unlikely(err)) {
@@ -2012,13 +1997,13 @@ again:
 
 		if (check_creds) {
 			/* Never glue messages from different writers */
-			if ((UNIXCB(skb).pid  != siocb->scm->pid) ||
-			    !uid_eq(UNIXCB(skb).uid, siocb->scm->creds.uid) ||
-			    !gid_eq(UNIXCB(skb).gid, siocb->scm->creds.gid))
+			if ((UNIXCB(skb).pid  != scm.pid) ||
+			    !uid_eq(UNIXCB(skb).uid, scm.creds.uid) ||
+			    !gid_eq(UNIXCB(skb).gid, scm.creds.gid))
 				break;
 		} else if (test_bit(SOCK_PASSCRED, &sock->flags)) {
 			/* Copy credentials */
-			scm_set_cred(siocb->scm, UNIXCB(skb).pid, UNIXCB(skb).uid, UNIXCB(skb).gid);
+			scm_set_cred(&scm, UNIXCB(skb).pid, UNIXCB(skb).uid, UNIXCB(skb).gid);
 			check_creds = 1;
 		}
 
@@ -2045,7 +2030,7 @@ again:
 			sk_peek_offset_bwd(sk, chunk);
 
 			if (UNIXCB(skb).fp)
-				unix_detach_fds(siocb->scm, skb);
+				unix_detach_fds(&scm, skb);
 
 			if (unix_skb_len(skb))
 				break;
@@ -2053,13 +2038,13 @@ again:
 			skb_unlink(skb, &sk->sk_receive_queue);
 			consume_skb(skb);
 
-			if (siocb->scm->fp)
+			if (scm.fp)
 				break;
 		} else {
 			/* It is questionable, see note in unix_dgram_recvmsg.
 			 */
 			if (UNIXCB(skb).fp)
-				siocb->scm->fp = scm_fp_dup(UNIXCB(skb).fp);
+				scm.fp = scm_fp_dup(UNIXCB(skb).fp);
 
 			sk_peek_offset_fwd(sk, chunk);
 
@@ -2068,7 +2053,7 @@ again:
 	} while (size);
 
 	mutex_unlock(&u->readlock);
-	scm_recv(sock, msg, siocb->scm, flags);
+	scm_recv(sock, msg, &scm, flags);
 out:
 	return copied ? : err;
 }
diff --git a/net/unix/diag.c b/net/unix/diag.c
index 86fa0f3b2ca..ef542fbca9f 100644
--- a/net/unix/diag.c
+++ b/net/unix/diag.c
@@ -155,7 +155,8 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_r
 	if (nla_put_u8(skb, UNIX_DIAG_SHUTDOWN, sk->sk_shutdown))
 		goto out_nlmsg_trim;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 out_nlmsg_trim:
 	nlmsg_cancel(skb, nlh);