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()
  ...

3 files changed, 34 insertions, 9 deletions

diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 124338a39e29..5ee56d0a8699 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -1651,7 +1651,6 @@ out:
         if (!err) {
                 ICMP6MSGOUT_INC_STATS(net, idev, ICMPV6_MLD2_REPORT);
                 ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
-                IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUTMCAST, payload_len);
         } else {
                 IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS);
         }
@@ -2015,7 +2014,6 @@ out:
         if (!err) {
                 ICMP6MSGOUT_INC_STATS(net, idev, type);
                 ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
-                IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUTMCAST, full_len);
         } else
                 IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS);
 
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index c8bc9b4ac328..6f01fe122abd 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -404,6 +404,14 @@ static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
         }
 }
 
+static bool __rt6_check_expired(const struct rt6_info *rt)
+{
+        if (rt->rt6i_flags & RTF_EXPIRES)
+                return time_after(jiffies, rt->dst.expires);
+        else
+                return false;
+}
+
 static bool rt6_check_expired(const struct rt6_info *rt)
 {
         if (rt->rt6i_flags & RTF_EXPIRES) {
@@ -1252,7 +1260,8 @@ static struct dst_entry *rt6_check(struct rt6_info *rt, u32 cookie)
 
 static struct dst_entry *rt6_dst_from_check(struct rt6_info *rt, u32 cookie)
 {
-        if (rt->dst.obsolete == DST_OBSOLETE_FORCE_CHK &&
+        if (!__rt6_check_expired(rt) &&
+            rt->dst.obsolete == DST_OBSOLETE_FORCE_CHK &&
             rt6_check((struct rt6_info *)(rt->dst.from), cookie))
                 return &rt->dst;
         else
@@ -1272,7 +1281,8 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie)
 
         rt6_dst_from_metrics_check(rt);
 
-        if ((rt->rt6i_flags & RTF_PCPU) || unlikely(dst->flags & DST_NOCACHE))
+        if (rt->rt6i_flags & RTF_PCPU ||
+            (unlikely(dst->flags & DST_NOCACHE) && rt->dst.from))
                 return rt6_dst_from_check(rt, cookie);
         else
                 return rt6_check(rt, cookie);
@@ -1322,6 +1332,12 @@ static void rt6_do_update_pmtu(struct rt6_info *rt, u32 mtu)
         rt6_update_expires(rt, net->ipv6.sysctl.ip6_rt_mtu_expires);
 }
 
+static bool rt6_cache_allowed_for_pmtu(const struct rt6_info *rt)
+{
+        return !(rt->rt6i_flags & RTF_CACHE) &&
+                (rt->rt6i_flags & RTF_PCPU || rt->rt6i_node);
+}
+
 static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
                                  const struct ipv6hdr *iph, u32 mtu)
 {
@@ -1335,7 +1351,7 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
         if (mtu >= dst_mtu(dst))
                 return;
 
-        if (rt6->rt6i_flags & RTF_CACHE) {
+        if (!rt6_cache_allowed_for_pmtu(rt6)) {
                 rt6_do_update_pmtu(rt6, mtu);
         } else {
                 const struct in6_addr *daddr, *saddr;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 5baa8e754e41..c5429a636f1a 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1690,6 +1690,8 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
         const struct tcp_sock *tp = tcp_sk(sp);
         const struct inet_connection_sock *icsk = inet_csk(sp);
         const struct fastopen_queue *fastopenq = &icsk->icsk_accept_queue.fastopenq;
+        int rx_queue;
+        int state;
 
         dest  = &sp->sk_v6_daddr;
         src   = &sp->sk_v6_rcv_saddr;
@@ -1710,6 +1712,15 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
                 timer_expires = jiffies;
         }
 
+        state = sk_state_load(sp);
+        if (state == TCP_LISTEN)
+                rx_queue = sp->sk_ack_backlog;
+        else
+                /* 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(seq,
                    "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X "
                    "%02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d %pK %lu %lu %u %u %d\n",
@@ -1718,9 +1729,9 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
                    src->s6_addr32[2], src->s6_addr32[3], srcp,
                    dest->s6_addr32[0], dest->s6_addr32[1],
                    dest->s6_addr32[2], dest->s6_addr32[3], destp,
-                   sp->sk_state,
-                   tp->write_seq-tp->snd_una,
-                   (sp->sk_state == TCP_LISTEN) ? sp->sk_ack_backlog : (tp->rcv_nxt - tp->copied_seq),
+                   state,
+                   tp->write_seq - tp->snd_una,
+                   rx_queue,
                    timer_active,
                    jiffies_delta_to_clock_t(timer_expires - jiffies),
                    icsk->icsk_retransmits,
@@ -1732,7 +1743,7 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
                    jiffies_to_clock_t(icsk->icsk_ack.ato),
                    (icsk->icsk_ack.quick << 1) | icsk->icsk_ack.pingpong,
                    tp->snd_cwnd,
-                   sp->sk_state == TCP_LISTEN ?
+                   state == TCP_LISTEN ?
                         fastopenq->max_qlen :
                         (tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh)
                    );