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

Pull networking fixes from David Miller:

 1) Fix list tests in netfilter ingress support, from Florian Westphal.

 2) Fix reversal of input and output interfaces in ingress hook
    invocation, from Pablo Neira Ayuso.

 3) We have a use after free in r8169, caught by Dave Jones, fixed by
    Francois Romieu.

 4) Splice use-after-free fix in AF_UNIX frmo Hannes Frederic Sowa.

 5) Three ipv6 route handling bug fixes from Martin KaFai Lau:
    a) Don't create clone routes not managed by the fib6 tree
    b) Don't forget to check expiration of DST_NOCACHE routes.
    c) Handle rt->dst.from == NULL properly.

 6) Several AF_PACKET fixes wrt transport header setting and SKB
    protocol setting, from Daniel Borkmann.

 7) Fix thunder driver crash on shutdown, from Pavel Fedin.

 8) Several Mellanox driver fixes (max MTU calculations, use of correct
    DMA unmap in TX path, etc.) from Saeed Mahameed, Tariq Toukan, Doron
    Tsur, Achiad Shochat, Eran Ben Elisha, and Noa Osherovich.

 9) Several mv88e6060 DSA driver fixes (wrong bit definitions for
    certain registers, etc.) from Neil Armstrong.

10) Make sure to disable preemption while updating per-cpu stats of ip
    tunnels, from Jason A.  Donenfeld.

11) Various ARM64 bpf JIT fixes, from Yang Shi.

12) Flush icache properly in ARM JITs, from Daniel Borkmann.

13) Fix masking of RX and TX interrupts in ravb driver, from Masaru
    Nagai.

14) Fix netdev feature propagation for devices not implementing
    ->ndo_set_features().  From Nikolay Aleksandrov.

15) Big endian fix in vmxnet3 driver, from Shrikrishna Khare.

16) RAW socket code increments incorrect SNMP counters, fix from Ben
    Cartwright-Cox.

17) IPv6 multicast SNMP counters are bumped twice, fix from Neil Horman.

18) Fix handling of VLAN headers on stacked devices when REORDER is
    disabled.  From Vlad Yasevich.

19) Fix SKB leaks and use-after-free in ipvlan and macvlan drivers, from
    Sabrina Dubroca.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (83 commits)
  MAINTAINERS: Update Mellanox's Eth NIC driver entries
  net/core: revert "net: fix __netdev_update_features return.." and add comment
  af_unix: take receive queue lock while appending new skb
  rtnetlink: fix frame size warning in rtnl_fill_ifinfo
  net: use skb_clone to avoid alloc_pages failure.
  packet: Use PAGE_ALIGNED macro
  packet: Don't check frames_per_block against negative values
  net: phy: Use interrupts when available in NOLINK state
  phy: marvell: Add support for 88E1540 PHY
  arm64: bpf: make BPF prologue and epilogue align with ARM64 AAPCS
  macvlan: fix leak in macvlan_handle_frame
  ipvlan: fix use after free of skb
  ipvlan: fix leak in ipvlan_rcv_frame
  vlan: Do not put vlan headers back on bridge and macvlan ports
  vlan: Fix untag operations of stacked vlans with REORDER_HEADER off
  via-velocity: unconditionally drop frames with bad l2 length
  ipg: Remove ipg driver
  dl2k: Add support for IP1000A-based cards
  snmp: Remove duplicate OUTMCAST stat increment
  net: thunder: Check for driver data in nicvf_remove()
  ...

6 files changed, 28 insertions, 23 deletions

diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 1feb15f23de8..46b9c887bede 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -563,7 +563,7 @@ static void reqsk_timer_handler(unsigned long data)
 	int max_retries, thresh;
 	u8 defer_accept;
 
-	if (sk_listener->sk_state != TCP_LISTEN)
+	if (sk_state_load(sk_listener) != TCP_LISTEN)
 		goto drop;
 
 	max_retries = icsk->icsk_syn_retries ? : sysctl_tcp_synack_retries;
@@ -749,7 +749,7 @@ int inet_csk_listen_start(struct sock *sk, int backlog)
 	 * It is OK, because this socket enters to hash table only
 	 * after validation is complete.
 	 */
-	sk->sk_state = TCP_LISTEN;
+	sk_state_store(sk, TCP_LISTEN);
 	if (!sk->sk_prot->get_port(sk, inet->inet_num)) {
 		inet->inet_sport = htons(inet->inet_num);
 
diff --git a/net/ipv4/netfilter/nf_nat_pptp.c b/net/ipv4/netfilter/nf_nat_pptp.c
index 657d2307f031..b3ca21b2ba9b 100644
--- a/net/ipv4/netfilter/nf_nat_pptp.c
+++ b/net/ipv4/netfilter/nf_nat_pptp.c
@@ -45,7 +45,7 @@ static void pptp_nat_expected(struct nf_conn *ct,
 	struct net *net = nf_ct_net(ct);
 	const struct nf_conn *master = ct->master;
 	struct nf_conntrack_expect *other_exp;
-	struct nf_conntrack_tuple t;
+	struct nf_conntrack_tuple t = {};
 	const struct nf_ct_pptp_master *ct_pptp_info;
 	const struct nf_nat_pptp *nat_pptp_info;
 	struct nf_nat_range range;
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 8c0d0bdc2a7c..63e5be0abd86 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -406,10 +406,12 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
 			ip_select_ident(net, skb, NULL);
 
 		iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
+		skb->transport_header += iphlen;
+		if (iph->protocol == IPPROTO_ICMP &&
+		    length >= iphlen + sizeof(struct icmphdr))
+			icmp_out_count(net, ((struct icmphdr *)
+				skb_transport_header(skb))->type);
 	}
-	if (iph->protocol == IPPROTO_ICMP)
-		icmp_out_count(net, ((struct icmphdr *)
-			skb_transport_header(skb))->type);
 
 	err = NF_HOOK(NFPROTO_IPV4, NF_INET_LOCAL_OUT,
 		      net, sk, skb, NULL, rt->dst.dev,
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 0cfa7c0c1e80..c1728771cf89 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -451,11 +451,14 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 	unsigned int mask;
 	struct sock *sk = sock->sk;
 	const struct tcp_sock *tp = tcp_sk(sk);
+	int state;
 
 	sock_rps_record_flow(sk);
 
 	sock_poll_wait(file, sk_sleep(sk), wait);
-	if (sk->sk_state == TCP_LISTEN)
+
+	state = sk_state_load(sk);
+	if (state == TCP_LISTEN)
 		return inet_csk_listen_poll(sk);
 
 	/* Socket is not locked. We are protected from async events
@@ -492,14 +495,14 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 	 * NOTE. Check for TCP_CLOSE is added. The goal is to prevent
 	 * blocking on fresh not-connected or disconnected socket. --ANK
 	 */
-	if (sk->sk_shutdown == SHUTDOWN_MASK || sk->sk_state == TCP_CLOSE)
+	if (sk->sk_shutdown == SHUTDOWN_MASK || state == TCP_CLOSE)
 		mask |= POLLHUP;
 	if (sk->sk_shutdown & RCV_SHUTDOWN)
 		mask |= POLLIN | POLLRDNORM | POLLRDHUP;
 
 	/* Connected or passive Fast Open socket? */
-	if (sk->sk_state != TCP_SYN_SENT &&
-	    (sk->sk_state != TCP_SYN_RECV || tp->fastopen_rsk)) {
+	if (state != TCP_SYN_SENT &&
+	    (state != TCP_SYN_RECV || tp->fastopen_rsk)) {
 		int target = sock_rcvlowat(sk, 0, INT_MAX);
 
 		if (tp->urg_seq == tp->copied_seq &&
@@ -507,9 +510,6 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 		    tp->urg_data)
 			target++;
 
-		/* Potential race condition. If read of tp below will
-		 * escape above sk->sk_state, we can be illegally awaken
-		 * in SYN_* states. */
 		if (tp->rcv_nxt - tp->copied_seq >= target)
 			mask |= POLLIN | POLLRDNORM;
 
@@ -1934,7 +1934,7 @@ void tcp_set_state(struct sock *sk, int state)
 	/* Change state AFTER socket is unhashed to avoid closed
 	 * socket sitting in hash tables.
 	 */
-	sk->sk_state = state;
+	sk_state_store(sk, state);
 
 #ifdef STATE_TRACE
 	SOCK_DEBUG(sk, "TCP sk=%p, State %s -> %s\n", sk, statename[oldstate], statename[state]);
@@ -2644,7 +2644,8 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 	if (sk->sk_type != SOCK_STREAM)
 		return;
 
-	info->tcpi_state = sk->sk_state;
+	info->tcpi_state = sk_state_load(sk);
+
 	info->tcpi_ca_state = icsk->icsk_ca_state;
 	info->tcpi_retransmits = icsk->icsk_retransmits;
 	info->tcpi_probes = icsk->icsk_probes_out;
@@ -2672,7 +2673,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 	info->tcpi_snd_mss = tp->mss_cache;
 	info->tcpi_rcv_mss = icsk->icsk_ack.rcv_mss;
 
-	if (sk->sk_state == TCP_LISTEN) {
+	if (info->tcpi_state == TCP_LISTEN) {
 		info->tcpi_unacked = sk->sk_ack_backlog;
 		info->tcpi_sacked = sk->sk_max_ack_backlog;
 	} else {
diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c
index 479f34946177..b31604086edd 100644
--- a/net/ipv4/tcp_diag.c
+++ b/net/ipv4/tcp_diag.c
@@ -21,7 +21,7 @@ static void tcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r,
 {
 	struct tcp_info *info = _info;
 
-	if (sk->sk_state == TCP_LISTEN) {
+	if (sk_state_load(sk) == TCP_LISTEN) {
 		r->idiag_rqueue = sk->sk_ack_backlog;
 		r->idiag_wqueue = sk->sk_max_ack_backlog;
 	} else if (sk->sk_type == SOCK_STREAM) {
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 950e28c0cdf2..ba09016d1bfd 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2158,6 +2158,7 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i)
 	__u16 destp = ntohs(inet->inet_dport);
 	__u16 srcp = ntohs(inet->inet_sport);
 	int rx_queue;
+	int state;
 
 	if (icsk->icsk_pending == ICSK_TIME_RETRANS ||
 	    icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||
@@ -2175,17 +2176,18 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i)
 		timer_expires = jiffies;
 	}
 
-	if (sk->sk_state == TCP_LISTEN)
+	state = sk_state_load(sk);
+	if (state == TCP_LISTEN)
 		rx_queue = sk->sk_ack_backlog;
 	else
-		/*
-		 * because we dont lock socket, we might find a transient negative value
+		/* Because we don't lock the socket,
+		 * we might find a transient negative value.
 		 */
 		rx_queue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0);
 
 	seq_printf(f, "%4d: %08X:%04X %08X:%04X %02X %08X:%08X %02X:%08lX "
 			"%08X %5u %8d %lu %d %pK %lu %lu %u %u %d",
-		i, src, srcp, dest, destp, sk->sk_state,
+		i, src, srcp, dest, destp, state,
 		tp->write_seq - tp->snd_una,
 		rx_queue,
 		timer_active,
@@ -2199,8 +2201,8 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i)
 		jiffies_to_clock_t(icsk->icsk_ack.ato),
 		(icsk->icsk_ack.quick << 1) | icsk->icsk_ack.pingpong,
 		tp->snd_cwnd,
-		sk->sk_state == TCP_LISTEN ?
-		    (fastopenq ? fastopenq->max_qlen : 0) :
+		state == TCP_LISTEN ?
+		    fastopenq->max_qlen :
 		    (tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh));
 }