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
  ...

1 files changed, 30 insertions, 93 deletions

diff --git a/net/socket.c b/net/socket.c
index 418795caa897..bbedbfcb42c2 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -113,10 +113,8 @@ unsigned int sysctl_net_busy_read __read_mostly;
 unsigned int sysctl_net_busy_poll __read_mostly;
 #endif
 
-static ssize_t sock_aio_read(struct kiocb *iocb, const struct iovec *iov,
-			 unsigned long nr_segs, loff_t pos);
-static ssize_t sock_aio_write(struct kiocb *iocb, const struct iovec *iov,
-			  unsigned long nr_segs, loff_t pos);
+static ssize_t sock_read_iter(struct kiocb *iocb, struct iov_iter *to);
+static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from);
 static int sock_mmap(struct file *file, struct vm_area_struct *vma);
 
 static int sock_close(struct inode *inode, struct file *file);
@@ -142,8 +140,10 @@ static ssize_t sock_splice_read(struct file *file, loff_t *ppos,
 static const struct file_operations socket_file_ops = {
 	.owner =	THIS_MODULE,
 	.llseek =	no_llseek,
-	.aio_read =	sock_aio_read,
-	.aio_write =	sock_aio_write,
+	.read =		new_sync_read,
+	.write =	new_sync_write,
+	.read_iter =	sock_read_iter,
+	.write_iter =	sock_write_iter,
 	.poll =		sock_poll,
 	.unlocked_ioctl = sock_ioctl,
 #ifdef CONFIG_COMPAT
@@ -613,13 +613,6 @@ EXPORT_SYMBOL(__sock_tx_timestamp);
 static inline int __sock_sendmsg_nosec(struct kiocb *iocb, struct socket *sock,
 				       struct msghdr *msg, size_t size)
 {
-	struct sock_iocb *si = kiocb_to_siocb(iocb);
-
-	si->sock = sock;
-	si->scm = NULL;
-	si->msg = msg;
-	si->size = size;
-
 	return sock->ops->sendmsg(iocb, sock, msg, size);
 }
 
@@ -635,11 +628,9 @@ static int do_sock_sendmsg(struct socket *sock, struct msghdr *msg,
 			   size_t size, bool nosec)
 {
 	struct kiocb iocb;
-	struct sock_iocb siocb;
 	int ret;
 
 	init_sync_kiocb(&iocb, NULL);
-	iocb.private = &siocb;
 	ret = nosec ? __sock_sendmsg_nosec(&iocb, sock, msg, size) :
 		      __sock_sendmsg(&iocb, sock, msg, size);
 	if (-EIOCBQUEUED == ret)
@@ -756,14 +747,6 @@ EXPORT_SYMBOL_GPL(__sock_recv_ts_and_drops);
 static inline int __sock_recvmsg_nosec(struct kiocb *iocb, struct socket *sock,
 				       struct msghdr *msg, size_t size, int flags)
 {
-	struct sock_iocb *si = kiocb_to_siocb(iocb);
-
-	si->sock = sock;
-	si->scm = NULL;
-	si->msg = msg;
-	si->size = size;
-	si->flags = flags;
-
 	return sock->ops->recvmsg(iocb, sock, msg, size, flags);
 }
 
@@ -779,11 +762,9 @@ int sock_recvmsg(struct socket *sock, struct msghdr *msg,
 		 size_t size, int flags)
 {
 	struct kiocb iocb;
-	struct sock_iocb siocb;
 	int ret;
 
 	init_sync_kiocb(&iocb, NULL);
-	iocb.private = &siocb;
 	ret = __sock_recvmsg(&iocb, sock, msg, size, flags);
 	if (-EIOCBQUEUED == ret)
 		ret = wait_on_sync_kiocb(&iocb);
@@ -795,11 +776,9 @@ static int sock_recvmsg_nosec(struct socket *sock, struct msghdr *msg,
 			      size_t size, int flags)
 {
 	struct kiocb iocb;
-	struct sock_iocb siocb;
 	int ret;
 
 	init_sync_kiocb(&iocb, NULL);
-	iocb.private = &siocb;
 	ret = __sock_recvmsg_nosec(&iocb, sock, msg, size, flags);
 	if (-EIOCBQUEUED == ret)
 		ret = wait_on_sync_kiocb(&iocb);
@@ -866,89 +845,47 @@ static ssize_t sock_splice_read(struct file *file, loff_t *ppos,
 	return sock->ops->splice_read(sock, ppos, pipe, len, flags);
 }
 
-static struct sock_iocb *alloc_sock_iocb(struct kiocb *iocb,
-					 struct sock_iocb *siocb)
-{
-	siocb->kiocb = iocb;
-	iocb->private = siocb;
-	return siocb;
-}
-
-static ssize_t do_sock_read(struct msghdr *msg, struct kiocb *iocb,
-		struct file *file, const struct iovec *iov,
-		unsigned long nr_segs)
+static ssize_t sock_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
+	struct file *file = iocb->ki_filp;
 	struct socket *sock = file->private_data;
-	size_t size = 0;
-	int i;
-
-	for (i = 0; i < nr_segs; i++)
-		size += iov[i].iov_len;
-
-	msg->msg_name = NULL;
-	msg->msg_namelen = 0;
-	msg->msg_control = NULL;
-	msg->msg_controllen = 0;
-	iov_iter_init(&msg->msg_iter, READ, iov, nr_segs, size);
-	msg->msg_flags = (file->f_flags & O_NONBLOCK) ? MSG_DONTWAIT : 0;
-
-	return __sock_recvmsg(iocb, sock, msg, size, msg->msg_flags);
-}
+	struct msghdr msg = {.msg_iter = *to};
+	ssize_t res;
 
-static ssize_t sock_aio_read(struct kiocb *iocb, const struct iovec *iov,
-				unsigned long nr_segs, loff_t pos)
-{
-	struct sock_iocb siocb, *x;
+	if (file->f_flags & O_NONBLOCK)
+		msg.msg_flags = MSG_DONTWAIT;
 
-	if (pos != 0)
+	if (iocb->ki_pos != 0)
 		return -ESPIPE;
 
 	if (iocb->ki_nbytes == 0)	/* Match SYS5 behaviour */
 		return 0;
 
-
-	x = alloc_sock_iocb(iocb, &siocb);
-	if (!x)
-		return -ENOMEM;
-	return do_sock_read(&x->async_msg, iocb, iocb->ki_filp, iov, nr_segs);
+	res = __sock_recvmsg(iocb, sock, &msg,
+			     iocb->ki_nbytes, msg.msg_flags);
+	*to = msg.msg_iter;
+	return res;
 }
 
-static ssize_t do_sock_write(struct msghdr *msg, struct kiocb *iocb,
-			struct file *file, const struct iovec *iov,
-			unsigned long nr_segs)
+static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
+	struct file *file = iocb->ki_filp;
 	struct socket *sock = file->private_data;
-	size_t size = 0;
-	int i;
-
-	for (i = 0; i < nr_segs; i++)
-		size += iov[i].iov_len;
-
-	msg->msg_name = NULL;
-	msg->msg_namelen = 0;
-	msg->msg_control = NULL;
-	msg->msg_controllen = 0;
-	iov_iter_init(&msg->msg_iter, WRITE, iov, nr_segs, size);
-	msg->msg_flags = (file->f_flags & O_NONBLOCK) ? MSG_DONTWAIT : 0;
-	if (sock->type == SOCK_SEQPACKET)
-		msg->msg_flags |= MSG_EOR;
-
-	return __sock_sendmsg(iocb, sock, msg, size);
-}
+	struct msghdr msg = {.msg_iter = *from};
+	ssize_t res;
 
-static ssize_t sock_aio_write(struct kiocb *iocb, const struct iovec *iov,
-			  unsigned long nr_segs, loff_t pos)
-{
-	struct sock_iocb siocb, *x;
-
-	if (pos != 0)
+	if (iocb->ki_pos != 0)
 		return -ESPIPE;
 
-	x = alloc_sock_iocb(iocb, &siocb);
-	if (!x)
-		return -ENOMEM;
+	if (file->f_flags & O_NONBLOCK)
+		msg.msg_flags = MSG_DONTWAIT;
+
+	if (sock->type == SOCK_SEQPACKET)
+		msg.msg_flags |= MSG_EOR;
 
-	return do_sock_write(&x->async_msg, iocb, iocb->ki_filp, iov, nr_segs);
+	res = __sock_sendmsg(iocb, sock, &msg, iocb->ki_nbytes);
+	*from = msg.msg_iter;
+	return res;
 }
 
 /*