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

Pull networking updates from David Miller:

 1) Add TX fast path in mac80211, from Johannes Berg.

 2) Add TSO/GRO support to ibmveth, from Thomas Falcon

 3) Move away from cached routes in ipv6, just like ipv4, from Martin
    KaFai Lau.

 4) Lots of new rhashtable tests, from Thomas Graf.

 5) Run ingress qdisc lockless, from Alexei Starovoitov.

 6) Allow servers to fetch TCP packet headers for SYN packets of new
    connections, for fingerprinting.  From Eric Dumazet.

 7) Add mode parameter to pktgen, for testing receive.  From Alexei
    Starovoitov.

 8) Cache access optimizations via simplifications of build_skb(), from
    Alexander Duyck.

 9) Move page frag allocator under mm/, also from Alexander.

10) Add xmit_more support to hv_netvsc, from KY Srinivasan.

11) Add a counter guard in case we try to perform endless reclassify
    loops in the packet scheduler.

12) Extern flow dissector to be programmable and use it in new "Flower"
    classifier.  From Jiri Pirko.

13) AF_PACKET fanout rollover fixes, performance improvements, and new
    statistics.  From Willem de Bruijn.

14) Add netdev driver for GENEVE tunnels, from John W Linville.

15) Add ingress netfilter hooks and filtering, from Pablo Neira Ayuso.

16) Fix handling of epoll edge triggers in TCP, from Eric Dumazet.

17) Add an ECN retry fallback for the initial TCP handshake, from Daniel
    Borkmann.

18) Add tail call support to BPF, from Alexei Starovoitov.

19) Add several pktgen helper scripts, from Jesper Dangaard Brouer.

20) Add zerocopy support to AF_UNIX, from Hannes Frederic Sowa.

21) Favor even port numbers for allocation to connect() requests, and
    odd port numbers for bind(0), in an effort to help avoid
    ip_local_port_range exhaustion.  From Eric Dumazet.

22) Add Cavium ThunderX driver, from Sunil Goutham.

23) Allow bpf programs to access skb_iif and dev->ifindex SKB metadata,
    from Alexei Starovoitov.

24) Add support for T6 chips in cxgb4vf driver, from Hariprasad Shenai.

25) Double TCP Small Queues default to 256K to accomodate situations
    like the XEN driver and wireless aggregation.  From Wei Liu.

26) Add more entropy inputs to flow dissector, from Tom Herbert.

27) Add CDG congestion control algorithm to TCP, from Kenneth Klette
    Jonassen.

28) Convert ipset over to RCU locking, from Jozsef Kadlecsik.

29) Track and act upon link status of ipv4 route nexthops, from Andy
    Gospodarek.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1670 commits)
  bridge: vlan: flush the dynamically learned entries on port vlan delete
  bridge: multicast: add a comment to br_port_state_selection about blocking state
  net: inet_diag: export IPV6_V6ONLY sockopt
  stmmac: troubleshoot unexpected bits in des0 & des1
  net: ipv4 sysctl option to ignore routes when nexthop link is down
  net: track link-status of ipv4 nexthops
  net: switchdev: ignore unsupported bridge flags
  net: Cavium: Fix MAC address setting in shutdown state
  drivers: net: xgene: fix for ACPI support without ACPI
  ip: report the original address of ICMP messages
  net/mlx5e: Prefetch skb data on RX
  net/mlx5e: Pop cq outside mlx5e_get_cqe
  net/mlx5e: Remove mlx5e_cq.sqrq back-pointer
  net/mlx5e: Remove extra spaces
  net/mlx5e: Avoid TX CQE generation if more xmit packets expected
  net/mlx5e: Avoid redundant dev_kfree_skb() upon NOP completion
  net/mlx5e: Remove re-assignment of wq type in mlx5e_enable_rq()
  net/mlx5e: Use skb_shinfo(skb)->gso_segs rather than counting them
  net/mlx5e: Static mapping of netdev priv resources to/from netdev TX queues
  net/mlx4_en: Use HW counters for rx/tx bytes/packets in PF device
  ...

1 files changed, 118 insertions, 52 deletions

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index bf6e76643f78..dea925388a5b 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -76,17 +76,18 @@ struct listeners {
 };
 
 /* state bits */
-#define NETLINK_CONGESTED	0x0
+#define NETLINK_S_CONGESTED		0x0
 
 /* flags */
-#define NETLINK_KERNEL_SOCKET	0x1
-#define NETLINK_RECV_PKTINFO	0x2
-#define NETLINK_BROADCAST_SEND_ERROR	0x4
-#define NETLINK_RECV_NO_ENOBUFS	0x8
+#define NETLINK_F_KERNEL_SOCKET		0x1
+#define NETLINK_F_RECV_PKTINFO		0x2
+#define NETLINK_F_BROADCAST_SEND_ERROR	0x4
+#define NETLINK_F_RECV_NO_ENOBUFS	0x8
+#define NETLINK_F_LISTEN_ALL_NSID	0x10
 
 static inline int netlink_is_kernel(struct sock *sk)
 {
-	return nlk_sk(sk)->flags & NETLINK_KERNEL_SOCKET;
+	return nlk_sk(sk)->flags & NETLINK_F_KERNEL_SOCKET;
 }
 
 struct netlink_table *nl_table __read_mostly;
@@ -256,8 +257,9 @@ static void netlink_overrun(struct sock *sk)
 {
 	struct netlink_sock *nlk = nlk_sk(sk);
 
-	if (!(nlk->flags & NETLINK_RECV_NO_ENOBUFS)) {
-		if (!test_and_set_bit(NETLINK_CONGESTED, &nlk_sk(sk)->state)) {
+	if (!(nlk->flags & NETLINK_F_RECV_NO_ENOBUFS)) {
+		if (!test_and_set_bit(NETLINK_S_CONGESTED,
+				      &nlk_sk(sk)->state)) {
 			sk->sk_err = ENOBUFS;
 			sk->sk_error_report(sk);
 		}
@@ -270,8 +272,8 @@ static void netlink_rcv_wake(struct sock *sk)
 	struct netlink_sock *nlk = nlk_sk(sk);
 
 	if (skb_queue_empty(&sk->sk_receive_queue))
-		clear_bit(NETLINK_CONGESTED, &nlk->state);
-	if (!test_bit(NETLINK_CONGESTED, &nlk->state))
+		clear_bit(NETLINK_S_CONGESTED, &nlk->state);
+	if (!test_bit(NETLINK_S_CONGESTED, &nlk->state))
 		wake_up_interruptible(&nlk->wait);
 }
 
@@ -1118,14 +1120,15 @@ static struct proto netlink_proto = {
 };
 
 static int __netlink_create(struct net *net, struct socket *sock,
-			    struct mutex *cb_mutex, int protocol)
+			    struct mutex *cb_mutex, int protocol,
+			    int kern)
 {
 	struct sock *sk;
 	struct netlink_sock *nlk;
 
 	sock->ops = &netlink_ops;
 
-	sk = sk_alloc(net, PF_NETLINK, GFP_KERNEL, &netlink_proto);
+	sk = sk_alloc(net, PF_NETLINK, GFP_KERNEL, &netlink_proto, kern);
 	if (!sk)
 		return -ENOMEM;
 
@@ -1187,7 +1190,7 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol,
 	if (err < 0)
 		goto out;
 
-	err = __netlink_create(net, sock, cb_mutex, protocol);
+	err = __netlink_create(net, sock, cb_mutex, protocol, kern);
 	if (err < 0)
 		goto out_module;
 
@@ -1297,20 +1300,24 @@ static int netlink_autobind(struct socket *sock)
 	struct netlink_table *table = &nl_table[sk->sk_protocol];
 	s32 portid = task_tgid_vnr(current);
 	int err;
-	static s32 rover = -4097;
+	s32 rover = -4096;
+	bool ok;
 
 retry:
 	cond_resched();
 	rcu_read_lock();
-	if (__netlink_lookup(table, portid, net)) {
+	ok = !__netlink_lookup(table, portid, net);
+	rcu_read_unlock();
+	if (!ok) {
 		/* Bind collision, search negative portid values. */
-		portid = rover--;
-		if (rover > -4097)
+		if (rover == -4096)
+			/* rover will be in range [S32_MIN, -4097] */
+			rover = S32_MIN + prandom_u32_max(-4096 - S32_MIN);
+		else if (rover >= -4096)
 			rover = -4097;
-		rcu_read_unlock();
+		portid = rover--;
 		goto retry;
 	}
-	rcu_read_unlock();
 
 	err = netlink_insert(sk, portid);
 	if (err == -EADDRINUSE)
@@ -1657,7 +1664,7 @@ int netlink_attachskb(struct sock *sk, struct sk_buff *skb,
 	nlk = nlk_sk(sk);
 
 	if ((atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf ||
-	     test_bit(NETLINK_CONGESTED, &nlk->state)) &&
+	     test_bit(NETLINK_S_CONGESTED, &nlk->state)) &&
 	    !netlink_skb_is_mmaped(skb)) {
 		DECLARE_WAITQUEUE(wait, current);
 		if (!*timeo) {
@@ -1672,7 +1679,7 @@ int netlink_attachskb(struct sock *sk, struct sk_buff *skb,
 		add_wait_queue(&nlk->wait, &wait);
 
 		if ((atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf ||
-		     test_bit(NETLINK_CONGESTED, &nlk->state)) &&
+		     test_bit(NETLINK_S_CONGESTED, &nlk->state)) &&
 		    !sock_flag(sk, SOCK_DEAD))
 			*timeo = schedule_timeout(*timeo);
 
@@ -1896,7 +1903,7 @@ static int netlink_broadcast_deliver(struct sock *sk, struct sk_buff *skb)
 	struct netlink_sock *nlk = nlk_sk(sk);
 
 	if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf &&
-	    !test_bit(NETLINK_CONGESTED, &nlk->state)) {
+	    !test_bit(NETLINK_S_CONGESTED, &nlk->state)) {
 		netlink_skb_set_owner_r(skb, sk);
 		__netlink_sendskb(sk, skb);
 		return atomic_read(&sk->sk_rmem_alloc) > (sk->sk_rcvbuf >> 1);
@@ -1932,8 +1939,17 @@ static void do_one_broadcast(struct sock *sk,
 	    !test_bit(p->group - 1, nlk->groups))
 		return;
 
-	if (!net_eq(sock_net(sk), p->net))
-		return;
+	if (!net_eq(sock_net(sk), p->net)) {
+		if (!(nlk->flags & NETLINK_F_LISTEN_ALL_NSID))
+			return;
+
+		if (!peernet_has_id(sock_net(sk), p->net))
+			return;
+
+		if (!file_ns_capable(sk->sk_socket->file, p->net->user_ns,
+				     CAP_NET_BROADCAST))
+			return;
+	}
 
 	if (p->failure) {
 		netlink_overrun(sk);
@@ -1957,23 +1973,33 @@ static void do_one_broadcast(struct sock *sk,
 		netlink_overrun(sk);
 		/* Clone failed. Notify ALL listeners. */
 		p->failure = 1;
-		if (nlk->flags & NETLINK_BROADCAST_SEND_ERROR)
+		if (nlk->flags & NETLINK_F_BROADCAST_SEND_ERROR)
 			p->delivery_failure = 1;
-	} else if (p->tx_filter && p->tx_filter(sk, p->skb2, p->tx_data)) {
+		goto out;
+	}
+	if (p->tx_filter && p->tx_filter(sk, p->skb2, p->tx_data)) {
 		kfree_skb(p->skb2);
 		p->skb2 = NULL;
-	} else if (sk_filter(sk, p->skb2)) {
+		goto out;
+	}
+	if (sk_filter(sk, p->skb2)) {
 		kfree_skb(p->skb2);
 		p->skb2 = NULL;
-	} else if ((val = netlink_broadcast_deliver(sk, p->skb2)) < 0) {
+		goto out;
+	}
+	NETLINK_CB(p->skb2).nsid = peernet2id(sock_net(sk), p->net);
+	NETLINK_CB(p->skb2).nsid_is_set = true;
+	val = netlink_broadcast_deliver(sk, p->skb2);
+	if (val < 0) {
 		netlink_overrun(sk);
-		if (nlk->flags & NETLINK_BROADCAST_SEND_ERROR)
+		if (nlk->flags & NETLINK_F_BROADCAST_SEND_ERROR)
 			p->delivery_failure = 1;
 	} else {
 		p->congested |= val;
 		p->delivered = 1;
 		p->skb2 = NULL;
 	}
+out:
 	sock_put(sk);
 }
 
@@ -2058,7 +2084,7 @@ static int do_one_set_err(struct sock *sk, struct netlink_set_err_data *p)
 	    !test_bit(p->group - 1, nlk->groups))
 		goto out;
 
-	if (p->code == ENOBUFS && nlk->flags & NETLINK_RECV_NO_ENOBUFS) {
+	if (p->code == ENOBUFS && nlk->flags & NETLINK_F_RECV_NO_ENOBUFS) {
 		ret = 1;
 		goto out;
 	}
@@ -2077,7 +2103,7 @@ out:
  * @code: error code, must be negative (as usual in kernelspace)
  *
  * This function returns the number of broadcast listeners that have set the
- * NETLINK_RECV_NO_ENOBUFS socket option.
+ * NETLINK_NO_ENOBUFS socket option.
  */
 int netlink_set_err(struct sock *ssk, u32 portid, u32 group, int code)
 {
@@ -2137,9 +2163,9 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname,
 	switch (optname) {
 	case NETLINK_PKTINFO:
 		if (val)
-			nlk->flags |= NETLINK_RECV_PKTINFO;
+			nlk->flags |= NETLINK_F_RECV_PKTINFO;
 		else
-			nlk->flags &= ~NETLINK_RECV_PKTINFO;
+			nlk->flags &= ~NETLINK_F_RECV_PKTINFO;
 		err = 0;
 		break;
 	case NETLINK_ADD_MEMBERSHIP:
@@ -2168,18 +2194,18 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname,
 	}
 	case NETLINK_BROADCAST_ERROR:
 		if (val)
-			nlk->flags |= NETLINK_BROADCAST_SEND_ERROR;
+			nlk->flags |= NETLINK_F_BROADCAST_SEND_ERROR;
 		else
-			nlk->flags &= ~NETLINK_BROADCAST_SEND_ERROR;
+			nlk->flags &= ~NETLINK_F_BROADCAST_SEND_ERROR;
 		err = 0;
 		break;
 	case NETLINK_NO_ENOBUFS:
 		if (val) {
-			nlk->flags |= NETLINK_RECV_NO_ENOBUFS;
-			clear_bit(NETLINK_CONGESTED, &nlk->state);
+			nlk->flags |= NETLINK_F_RECV_NO_ENOBUFS;
+			clear_bit(NETLINK_S_CONGESTED, &nlk->state);
 			wake_up_interruptible(&nlk->wait);
 		} else {
-			nlk->flags &= ~NETLINK_RECV_NO_ENOBUFS;
+			nlk->flags &= ~NETLINK_F_RECV_NO_ENOBUFS;
 		}
 		err = 0;
 		break;
@@ -2202,6 +2228,16 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname,
 		break;
 	}
 #endif /* CONFIG_NETLINK_MMAP */
+	case NETLINK_LISTEN_ALL_NSID:
+		if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_BROADCAST))
+			return -EPERM;
+
+		if (val)
+			nlk->flags |= NETLINK_F_LISTEN_ALL_NSID;
+		else
+			nlk->flags &= ~NETLINK_F_LISTEN_ALL_NSID;
+		err = 0;
+		break;
 	default:
 		err = -ENOPROTOOPT;
 	}
@@ -2228,7 +2264,7 @@ static int netlink_getsockopt(struct socket *sock, int level, int optname,
 		if (len < sizeof(int))
 			return -EINVAL;
 		len = sizeof(int);
-		val = nlk->flags & NETLINK_RECV_PKTINFO ? 1 : 0;
+		val = nlk->flags & NETLINK_F_RECV_PKTINFO ? 1 : 0;
 		if (put_user(len, optlen) ||
 		    put_user(val, optval))
 			return -EFAULT;
@@ -2238,7 +2274,7 @@ static int netlink_getsockopt(struct socket *sock, int level, int optname,
 		if (len < sizeof(int))
 			return -EINVAL;
 		len = sizeof(int);
-		val = nlk->flags & NETLINK_BROADCAST_SEND_ERROR ? 1 : 0;
+		val = nlk->flags & NETLINK_F_BROADCAST_SEND_ERROR ? 1 : 0;
 		if (put_user(len, optlen) ||
 		    put_user(val, optval))
 			return -EFAULT;
@@ -2248,12 +2284,34 @@ static int netlink_getsockopt(struct socket *sock, int level, int optname,
 		if (len < sizeof(int))
 			return -EINVAL;
 		len = sizeof(int);
-		val = nlk->flags & NETLINK_RECV_NO_ENOBUFS ? 1 : 0;
+		val = nlk->flags & NETLINK_F_RECV_NO_ENOBUFS ? 1 : 0;
 		if (put_user(len, optlen) ||
 		    put_user(val, optval))
 			return -EFAULT;
 		err = 0;
 		break;
+	case NETLINK_LIST_MEMBERSHIPS: {
+		int pos, idx, shift;
+
+		err = 0;
+		netlink_table_grab();
+		for (pos = 0; pos * 8 < nlk->ngroups; pos += sizeof(u32)) {
+			if (len - pos < sizeof(u32))
+				break;
+
+			idx = pos / sizeof(unsigned long);
+			shift = (pos % sizeof(unsigned long)) * 8;
+			if (put_user((u32)(nlk->groups[idx] >> shift),
+				     (u32 __user *)(optval + pos))) {
+				err = -EFAULT;
+				break;
+			}
+		}
+		if (put_user(ALIGN(nlk->ngroups / 8, sizeof(u32)), optlen))
+			err = -EFAULT;
+		netlink_table_ungrab();
+		break;
+	}
 	default:
 		err = -ENOPROTOOPT;
 	}
@@ -2268,6 +2326,16 @@ static void netlink_cmsg_recv_pktinfo(struct msghdr *msg, struct sk_buff *skb)
 	put_cmsg(msg, SOL_NETLINK, NETLINK_PKTINFO, sizeof(info), &info);
 }
 
+static void netlink_cmsg_listen_all_nsid(struct sock *sk, struct msghdr *msg,
+					 struct sk_buff *skb)
+{
+	if (!NETLINK_CB(skb).nsid_is_set)
+		return;
+
+	put_cmsg(msg, SOL_NETLINK, NETLINK_LISTEN_ALL_NSID, sizeof(int),
+		 &NETLINK_CB(skb).nsid);
+}
+
 static int netlink_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 {
 	struct sock *sk = sock->sk;
@@ -2419,8 +2487,10 @@ static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 		msg->msg_namelen = sizeof(*addr);
 	}
 
-	if (nlk->flags & NETLINK_RECV_PKTINFO)
+	if (nlk->flags & NETLINK_F_RECV_PKTINFO)
 		netlink_cmsg_recv_pktinfo(msg, skb);
+	if (nlk->flags & NETLINK_F_LISTEN_ALL_NSID)
+		netlink_cmsg_listen_all_nsid(sk, msg, skb);
 
 	memset(&scm, 0, sizeof(scm));
 	scm.creds = *NETLINK_CREDS(skb);
@@ -2474,17 +2544,10 @@ __netlink_kernel_create(struct net *net, int unit, struct module *module,
 	if (sock_create_lite(PF_NETLINK, SOCK_DGRAM, unit, &sock))
 		return NULL;
 
-	/*
-	 * We have to just have a reference on the net from sk, but don't
-	 * get_net it. Besides, we cannot get and then put the net here.
-	 * So we create one inside init_net and the move it to net.
-	 */
-
-	if (__netlink_create(&init_net, sock, cb_mutex, unit) < 0)
+	if (__netlink_create(net, sock, cb_mutex, unit, 1) < 0)
 		goto out_sock_release_nosk;
 
 	sk = sock->sk;
-	sk_change_net(sk, net);
 
 	if (!cfg || cfg->groups < 32)
 		groups = 32;
@@ -2503,7 +2566,7 @@ __netlink_kernel_create(struct net *net, int unit, struct module *module,
 		goto out_sock_release;
 
 	nlk = nlk_sk(sk);
-	nlk->flags |= NETLINK_KERNEL_SOCKET;
+	nlk->flags |= NETLINK_F_KERNEL_SOCKET;
 
 	netlink_table_grab();
 	if (!nl_table[unit].registered) {
@@ -2540,7 +2603,10 @@ EXPORT_SYMBOL(__netlink_kernel_create);
 void
 netlink_kernel_release(struct sock *sk)
 {
-	sk_release_kernel(sk);
+	if (sk == NULL || sk->sk_socket == NULL)
+		return;
+
+	sock_release(sk->sk_socket);
 }
 EXPORT_SYMBOL(netlink_kernel_release);