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

Pull networking changes from David S Miller:

 1) Remove the ipv4 routing cache.  Now lookups go directly into the FIB
    trie and use prebuilt routes cached there.

    No more garbage collection, no more rDOS attacks on the routing
    cache.  Instead we now get predictable and consistent performance,
    no matter what the pattern of traffic we service.

    This has been almost 2 years in the making.  Special thanks to
    Julian Anastasov, Eric Dumazet, Steffen Klassert, and others who
    have helped along the way.

    I'm sure that with a change of this magnitude there will be some
    kind of fallout, but such things ought the be simple to fix at this
    point.  Luckily I'm not European so I'll be around all of August to
    fix things :-)

    The major stages of this work here are each fronted by a forced
    merge commit whose commit message contains a top-level description
    of the motivations and implementation issues.

 2) Pre-demux of established ipv4 TCP sockets, saves a route demux on
    input.

 3) TCP SYN/ACK performance tweaks from Eric Dumazet.

 4) Add namespace support for netfilter L4 conntrack helpers, from Gao
    Feng.

 5) Add config mechanism for Energy Efficient Ethernet to ethtool, from
    Yuval Mintz.

 6) Remove quadratic behavior from /proc/net/unix, from Eric Dumazet.

 7) Support for connection tracker helpers in userspace, from Pablo
    Neira Ayuso.

 8) Allow userspace driven TX load balancing functions in TEAM driver,
    from Jiri Pirko.

 9) Kill off NLMSG_PUT and RTA_PUT macros, more gross stuff with
    embedded gotos.

10) TCP Small Queues, essentially minimize the amount of TCP data queued
    up in the packet scheduler layer.  Whereas the existing BQL (Byte
    Queue Limits) limits the pkt_sched --> netdevice queuing levels,
    this controls the TCP --> pkt_sched queueing levels.

    From Eric Dumazet.

11) Reduce the number of get_page/put_page ops done on SKB fragments,
    from Alexander Duyck.

12) Implement protection against blind resets in TCP (RFC 5961), from
    Eric Dumazet.

13) Support the client side of TCP Fast Open, basically the ability to
    send data in the SYN exchange, from Yuchung Cheng.

    Basically, the sender queues up data with a sendmsg() call using
    MSG_FASTOPEN, then they do the connect() which emits the queued up
    fastopen data.

14) Avoid all the problems we get into in TCP when timers or PMTU events
    hit a locked socket.  The TCP Small Queues changes added a
    tcp_release_cb() that allows us to queue work up to the
    release_sock() caller, and that's what we use here too.  From Eric
    Dumazet.

15) Zero copy on TX support for TUN driver, from Michael S. Tsirkin.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1870 commits)
  genetlink: define lockdep_genl_is_held() when CONFIG_LOCKDEP
  r8169: revert "add byte queue limit support".
  ipv4: Change rt->rt_iif encoding.
  net: Make skb->skb_iif always track skb->dev
  ipv4: Prepare for change of rt->rt_iif encoding.
  ipv4: Remove all RTCF_DIRECTSRC handliing.
  ipv4: Really ignore ICMP address requests/replies.
  decnet: Don't set RTCF_DIRECTSRC.
  net/ipv4/ip_vti.c: Fix __rcu warnings detected by sparse.
  ipv4: Remove redundant assignment
  rds: set correct msg_namelen
  openvswitch: potential NULL deref in sample()
  tcp: dont drop MTU reduction indications
  bnx2x: Add new 57840 device IDs
  tcp: avoid oops in tcp_metrics and reset tcpm_stamp
  niu: Change niu_rbr_fill() to use unlikely() to check niu_rbr_add_page() return value
  niu: Fix to check for dma mapping errors.
  net: Fix references to out-of-scope variables in put_cmsg_compat()
  net: ethernet: davinci_emac: add pm_runtime support
  net: ethernet: davinci_emac: Remove unnecessary #include
  ...

1 files changed, 55 insertions, 60 deletions

diff --git a/net/unix/diag.c b/net/unix/diag.c
index 47d3002737f5..750b13408449 100644
--- a/net/unix/diag.c
+++ b/net/unix/diag.c
@@ -8,40 +8,31 @@
 #include <net/af_unix.h>
 #include <net/tcp_states.h>
 
-#define UNIX_DIAG_PUT(skb, attrtype, attrlen) \
-	RTA_DATA(__RTA_PUT(skb, attrtype, attrlen))
-
 static int sk_diag_dump_name(struct sock *sk, struct sk_buff *nlskb)
 {
 	struct unix_address *addr = unix_sk(sk)->addr;
-	char *s;
-
-	if (addr) {
-		s = UNIX_DIAG_PUT(nlskb, UNIX_DIAG_NAME, addr->len - sizeof(short));
-		memcpy(s, addr->name->sun_path, addr->len - sizeof(short));
-	}
 
-	return 0;
+	if (!addr)
+		return 0;
 
-rtattr_failure:
-	return -EMSGSIZE;
+	return nla_put(nlskb, UNIX_DIAG_NAME, addr->len - sizeof(short),
+		       addr->name->sun_path);
 }
 
 static int sk_diag_dump_vfs(struct sock *sk, struct sk_buff *nlskb)
 {
 	struct dentry *dentry = unix_sk(sk)->path.dentry;
-	struct unix_diag_vfs *uv;
 
 	if (dentry) {
-		uv = UNIX_DIAG_PUT(nlskb, UNIX_DIAG_VFS, sizeof(*uv));
-		uv->udiag_vfs_ino = dentry->d_inode->i_ino;
-		uv->udiag_vfs_dev = dentry->d_sb->s_dev;
+		struct unix_diag_vfs uv = {
+			.udiag_vfs_ino = dentry->d_inode->i_ino,
+			.udiag_vfs_dev = dentry->d_sb->s_dev,
+		};
+
+		return nla_put(nlskb, UNIX_DIAG_VFS, sizeof(uv), &uv);
 	}
 
 	return 0;
-
-rtattr_failure:
-	return -EMSGSIZE;
 }
 
 static int sk_diag_dump_peer(struct sock *sk, struct sk_buff *nlskb)
@@ -56,24 +47,28 @@ static int sk_diag_dump_peer(struct sock *sk, struct sk_buff *nlskb)
 		unix_state_unlock(peer);
 		sock_put(peer);
 
-		RTA_PUT_U32(nlskb, UNIX_DIAG_PEER, ino);
+		return nla_put_u32(nlskb, UNIX_DIAG_PEER, ino);
 	}
 
 	return 0;
-rtattr_failure:
-	return -EMSGSIZE;
 }
 
 static int sk_diag_dump_icons(struct sock *sk, struct sk_buff *nlskb)
 {
 	struct sk_buff *skb;
+	struct nlattr *attr;
 	u32 *buf;
 	int i;
 
 	if (sk->sk_state == TCP_LISTEN) {
 		spin_lock(&sk->sk_receive_queue.lock);
-		buf = UNIX_DIAG_PUT(nlskb, UNIX_DIAG_ICONS,
-				sk->sk_receive_queue.qlen * sizeof(u32));
+
+		attr = nla_reserve(nlskb, UNIX_DIAG_ICONS,
+				   sk->sk_receive_queue.qlen * sizeof(u32));
+		if (!attr)
+			goto errout;
+
+		buf = nla_data(attr);
 		i = 0;
 		skb_queue_walk(&sk->sk_receive_queue, skb) {
 			struct sock *req, *peer;
@@ -94,43 +89,38 @@ static int sk_diag_dump_icons(struct sock *sk, struct sk_buff *nlskb)
 
 	return 0;
 
-rtattr_failure:
+errout:
 	spin_unlock(&sk->sk_receive_queue.lock);
 	return -EMSGSIZE;
 }
 
 static int sk_diag_show_rqlen(struct sock *sk, struct sk_buff *nlskb)
 {
-	struct unix_diag_rqlen *rql;
-
-	rql = UNIX_DIAG_PUT(nlskb, UNIX_DIAG_RQLEN, sizeof(*rql));
+	struct unix_diag_rqlen rql;
 
 	if (sk->sk_state == TCP_LISTEN) {
-		rql->udiag_rqueue = sk->sk_receive_queue.qlen;
-		rql->udiag_wqueue = sk->sk_max_ack_backlog;
+		rql.udiag_rqueue = sk->sk_receive_queue.qlen;
+		rql.udiag_wqueue = sk->sk_max_ack_backlog;
 	} else {
-		rql->udiag_rqueue = (__u32)unix_inq_len(sk);
-		rql->udiag_wqueue = (__u32)unix_outq_len(sk);
+		rql.udiag_rqueue = (u32) unix_inq_len(sk);
+		rql.udiag_wqueue = (u32) unix_outq_len(sk);
 	}
 
-	return 0;
-
-rtattr_failure:
-	return -EMSGSIZE;
+	return nla_put(nlskb, UNIX_DIAG_RQLEN, sizeof(rql), &rql);
 }
 
 static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_req *req,
 		u32 pid, u32 seq, u32 flags, int sk_ino)
 {
-	unsigned char *b = skb_tail_pointer(skb);
 	struct nlmsghdr *nlh;
 	struct unix_diag_msg *rep;
 
-	nlh = NLMSG_PUT(skb, pid, seq, SOCK_DIAG_BY_FAMILY, sizeof(*rep));
-	nlh->nlmsg_flags = flags;
-
-	rep = NLMSG_DATA(nlh);
+	nlh = nlmsg_put(skb, pid, seq, SOCK_DIAG_BY_FAMILY, sizeof(*rep),
+			flags);
+	if (!nlh)
+		return -EMSGSIZE;
 
+	rep = nlmsg_data(nlh);
 	rep->udiag_family = AF_UNIX;
 	rep->udiag_type = sk->sk_type;
 	rep->udiag_state = sk->sk_state;
@@ -139,33 +129,32 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_r
 
 	if ((req->udiag_show & UDIAG_SHOW_NAME) &&
 	    sk_diag_dump_name(sk, skb))
-		goto nlmsg_failure;
+		goto out_nlmsg_trim;
 
 	if ((req->udiag_show & UDIAG_SHOW_VFS) &&
 	    sk_diag_dump_vfs(sk, skb))
-		goto nlmsg_failure;
+		goto out_nlmsg_trim;
 
 	if ((req->udiag_show & UDIAG_SHOW_PEER) &&
 	    sk_diag_dump_peer(sk, skb))
-		goto nlmsg_failure;
+		goto out_nlmsg_trim;
 
 	if ((req->udiag_show & UDIAG_SHOW_ICONS) &&
 	    sk_diag_dump_icons(sk, skb))
-		goto nlmsg_failure;
+		goto out_nlmsg_trim;
 
 	if ((req->udiag_show & UDIAG_SHOW_RQLEN) &&
 	    sk_diag_show_rqlen(sk, skb))
-		goto nlmsg_failure;
+		goto out_nlmsg_trim;
 
 	if ((req->udiag_show & UDIAG_SHOW_MEMINFO) &&
 	    sock_diag_put_meminfo(sk, skb, UNIX_DIAG_MEMINFO))
-		goto nlmsg_failure;
+		goto out_nlmsg_trim;
 
-	nlh->nlmsg_len = skb_tail_pointer(skb) - b;
-	return skb->len;
+	return nlmsg_end(skb, nlh);
 
-nlmsg_failure:
-	nlmsg_trim(skb, b);
+out_nlmsg_trim:
+	nlmsg_cancel(skb, nlh);
 	return -EMSGSIZE;
 }
 
@@ -188,19 +177,24 @@ static int unix_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
 {
 	struct unix_diag_req *req;
 	int num, s_num, slot, s_slot;
+	struct net *net = sock_net(skb->sk);
 
-	req = NLMSG_DATA(cb->nlh);
+	req = nlmsg_data(cb->nlh);
 
 	s_slot = cb->args[0];
 	num = s_num = cb->args[1];
 
 	spin_lock(&unix_table_lock);
-	for (slot = s_slot; slot <= UNIX_HASH_SIZE; s_num = 0, slot++) {
+	for (slot = s_slot;
+	     slot < ARRAY_SIZE(unix_socket_table);
+	     s_num = 0, slot++) {
 		struct sock *sk;
 		struct hlist_node *node;
 
 		num = 0;
 		sk_for_each(sk, node, &unix_socket_table[slot]) {
+			if (!net_eq(sock_net(sk), net))
+				continue;
 			if (num < s_num)
 				goto next;
 			if (!(req->udiag_states & (1 << sk->sk_state)))
@@ -228,7 +222,7 @@ static struct sock *unix_lookup_by_ino(int ino)
 	struct sock *sk;
 
 	spin_lock(&unix_table_lock);
-	for (i = 0; i <= UNIX_HASH_SIZE; i++) {
+	for (i = 0; i < ARRAY_SIZE(unix_socket_table); i++) {
 		struct hlist_node *node;
 
 		sk_for_each(sk, node, &unix_socket_table[i])
@@ -252,6 +246,7 @@ static int unix_diag_get_exact(struct sk_buff *in_skb,
 	struct sock *sk;
 	struct sk_buff *rep;
 	unsigned int extra_len;
+	struct net *net = sock_net(in_skb->sk);
 
 	if (req->udiag_ino == 0)
 		goto out_nosk;
@@ -268,22 +263,21 @@ static int unix_diag_get_exact(struct sk_buff *in_skb,
 	extra_len = 256;
 again:
 	err = -ENOMEM;
-	rep = alloc_skb(NLMSG_SPACE((sizeof(struct unix_diag_msg) + extra_len)),
-			GFP_KERNEL);
+	rep = nlmsg_new(sizeof(struct unix_diag_msg) + extra_len, GFP_KERNEL);
 	if (!rep)
 		goto out;
 
 	err = sk_diag_fill(sk, rep, req, NETLINK_CB(in_skb).pid,
 			   nlh->nlmsg_seq, 0, req->udiag_ino);
 	if (err < 0) {
-		kfree_skb(rep);
+		nlmsg_free(rep);
 		extra_len += 256;
 		if (extra_len >= PAGE_SIZE)
 			goto out;
 
 		goto again;
 	}
-	err = netlink_unicast(sock_diag_nlsk, rep, NETLINK_CB(in_skb).pid,
+	err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).pid,
 			      MSG_DONTWAIT);
 	if (err > 0)
 		err = 0;
@@ -297,6 +291,7 @@ out_nosk:
 static int unix_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h)
 {
 	int hdrlen = sizeof(struct unix_diag_req);
+	struct net *net = sock_net(skb->sk);
 
 	if (nlmsg_len(h) < hdrlen)
 		return -EINVAL;
@@ -305,9 +300,9 @@ static int unix_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h)
 		struct netlink_dump_control c = {
 			.dump = unix_diag_dump,
 		};
-		return netlink_dump_start(sock_diag_nlsk, skb, h, &c);
+		return netlink_dump_start(net->diag_nlsk, skb, h, &c);
 	} else
-		return unix_diag_get_exact(skb, h, (struct unix_diag_req *)NLMSG_DATA(h));
+		return unix_diag_get_exact(skb, h, nlmsg_data(h));
 }
 
 static const struct sock_diag_handler unix_diag_handler = {