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

Pull networking fixes from David Miller:
 "This is what we usually expect at this stage of the game, lots of
  little things, mostly in drivers.  With the occasional 'oops didn't
  mean to do that' kind of regressions in the core code."

 1) Uninitialized data in __ip_vs_get_timeouts(), from Arnd Bergmann

 2) Reject invalid ACK sequences in Fast Open sockets, from Jerry Chu.

 3) Lost error code on return from _rtl_usb_receive(), from Christian
    Lamparter.

 4) Fix reset resume on USB rt2x00, from Stanislaw Gruszka.

 5) Release resources on error in pch_gbe driver, from Veaceslav Falico.

 6) Default hop limit not set correctly in ip6_template_metrics[], fix
    from Li RongQing.

 7) Gianfar PTP code requests wrong kind of resource during probe, fix
    from Wei Yang.

 8) Fix VHOST net driver on big-endian, from Michael S Tsirkin.

 9) Mallenox driver bug fixes from Jack Morgenstein, Or Gerlitz, Moni
    Shoua, Dotan Barak, and Uri Habusha.

10) usbnet leaks memory on TX path, fix from Hemant Kumar.

11) Use socket state test, rather than presence of FIN bit packet, to
    determine FIONREAD/SIOCINQ value.  Fix from Eric Dumazet.

12) Fix cxgb4 build failure, from Vipul Pandya.

13) Provide a SYN_DATA_ACKED state to complement SYN_FASTOPEN in socket
    info dumps.  From Yuchung Cheng.

14) Fix leak of security path in kfree_skb_partial().  Fix from Eric
    Dumazet.

15) Handle RX FIFO overflows more resiliently in pch_gbe driver, from
    Veaceslav Falico.

16) Fix MAINTAINERS file pattern for networking drivers, from Jean
    Delvare.

17) Add iPhone5 IDs to IPHETH driver, from Jay Purohit.

18) VLAN device type change restriction is too strict, and should not
    trigger for the automatically generated vlan0 device.  Fix from Jiri
    Pirko.

19) Make PMTU/redirect flushing work properly again in ipv4, from
    Steffen Klassert.

20) Fix memory corruptions by using kfree_rcu() in netlink_release().
    From Eric Dumazet.

21) More qmi_wwan device IDs, from Bjørn Mork.

22) Fix unintentional change of SNAT/DNAT hooks in generic NAT
    infrastructure, from Elison Niven.

23) Fix 3.6.x regression in xt_TEE netfilter module, from Eric Dumazet.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (57 commits)
  tilegx: fix some issues in the SW TSO support
  qmi_wwan/cdc_ether: move Novatel 551 and E362 to qmi_wwan
  net: usb: Fix memory leak on Tx data path
  net/mlx4_core: Unmap UAR also in the case of error flow
  net/mlx4_en: Don't use vlan tag value as an indication for vlan presence
  net/mlx4_en: Fix double-release-range in tx-rings
  bas_gigaset: fix pre_reset handling
  vhost: fix mergeable bufs on BE hosts
  gianfar_ptp: use iomem, not ioports resource tree in probe
  ipv6: Set default hoplimit as zero.
  NET_VENDOR_TI: make available for am33xx as well
  pch_gbe: fix error handling in pch_gbe_up()
  b43: Fix oops on unload when firmware not found
  mwifiex: clean up scan state on error
  mwifiex: return -EBUSY if specific scan request cannot be honored
  brcmfmac: fix potential NULL dereference
  Revert "ath9k_hw: Updated AR9003 tx gain table for 5GHz"
  ath9k_htc: Add PID/VID for a Ubiquiti WiFiStation
  rt2x00: usb: fix reset resume
  rtlwifi: pass rx setup error code to caller
  ...

6 files changed, 26 insertions, 12 deletions

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 432f4bb77238..a8c651216fa6 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1163,8 +1163,12 @@ static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe,
         spin_lock_bh(&fnhe_lock);
 
         if (daddr == fnhe->fnhe_daddr) {
-                struct rtable *orig;
-
+                struct rtable *orig = rcu_dereference(fnhe->fnhe_rth);
+                if (orig && rt_is_expired(orig)) {
+                        fnhe->fnhe_gw = 0;
+                        fnhe->fnhe_pmtu = 0;
+                        fnhe->fnhe_expires = 0;
+                }
                 if (fnhe->fnhe_pmtu) {
                         unsigned long expires = fnhe->fnhe_expires;
                         unsigned long diff = expires - jiffies;
@@ -1181,7 +1185,6 @@ static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe,
                 } else if (!rt->rt_gateway)
                         rt->rt_gateway = daddr;
 
-                orig = rcu_dereference(fnhe->fnhe_rth);
                 rcu_assign_pointer(fnhe->fnhe_rth, rt);
                 if (orig)
                         rt_free(orig);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index f32c02e2a543..197c0008503c 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -549,14 +549,12 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
                          !tp->urg_data ||
                          before(tp->urg_seq, tp->copied_seq) ||
                          !before(tp->urg_seq, tp->rcv_nxt)) {
-                        struct sk_buff *skb;
 
                         answ = tp->rcv_nxt - tp->copied_seq;
 
-                        /* Subtract 1, if FIN is in queue. */
-                        skb = skb_peek_tail(&sk->sk_receive_queue);
-                        if (answ && skb)
-                                answ -= tcp_hdr(skb)->fin;
+                        /* Subtract 1, if FIN was received */
+                        if (answ && sock_flag(sk, SOCK_DONE))
+                                answ--;
                 } else
                         answ = tp->urg_seq - tp->copied_seq;
                 release_sock(sk);
@@ -2766,6 +2764,8 @@ void tcp_get_info(const struct sock *sk, struct tcp_info *info)
                 info->tcpi_options |= TCPI_OPT_ECN;
         if (tp->ecn_flags & TCP_ECN_SEEN)
                 info->tcpi_options |= TCPI_OPT_ECN_SEEN;
+        if (tp->syn_data_acked)
+                info->tcpi_options |= TCPI_OPT_SYN_DATA;
 
         info->tcpi_rto = jiffies_to_usecs(icsk->icsk_rto);
         info->tcpi_ato = jiffies_to_usecs(icsk->icsk_ack.ato);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 432c36649db3..1db663983587 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5646,6 +5646,7 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack,
                 tcp_rearm_rto(sk);
                 return true;
         }
+        tp->syn_data_acked = tp->syn_data;
         return false;
 }
 
@@ -5963,7 +5964,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
 
         req = tp->fastopen_rsk;
         if (req != NULL) {
-                BUG_ON(sk->sk_state != TCP_SYN_RECV &&
+                WARN_ON_ONCE(sk->sk_state != TCP_SYN_RECV &&
                     sk->sk_state != TCP_FIN_WAIT1);
 
                 if (tcp_check_req(sk, skb, req, NULL, true) == NULL)
@@ -6052,7 +6053,15 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
                          * ACK we have received, this would have acknowledged
                          * our SYNACK so stop the SYNACK timer.
                          */
-                        if (acceptable && req != NULL) {
+                        if (req != NULL) {
+                                /* Return RST if ack_seq is invalid.
+                                 * Note that RFC793 only says to generate a
+                                 * DUPACK for it but for TCP Fast Open it seems
+                                 * better to treat this case like TCP_SYN_RECV
+                                 * above.
+                                 */
+                                if (!acceptable)
+                                        return 1;
                                 /* We no longer need the request sock. */
                                 reqsk_fastopen_remove(sk, req, false);
                                 tcp_rearm_rto(sk);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index ef998b008a57..0c4a64355603 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1461,6 +1461,7 @@ static int tcp_v4_conn_req_fastopen(struct sock *sk,
                 skb_set_owner_r(skb, child);
                 __skb_queue_tail(&child->sk_receive_queue, skb);
                 tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
+                tp->syn_data_acked = 1;
         }
         sk->sk_data_ready(sk, 0);
         bh_unlock_sock(child);
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 27536ba16c9d..a7302d974f32 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -510,6 +510,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
                 newtp->rx_opt.mss_clamp = req->mss;
                 TCP_ECN_openreq_child(newtp, req);
                 newtp->fastopen_rsk = NULL;
+                newtp->syn_data_acked = 0;
 
                 TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_PASSIVEOPENS);
         }
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index fc04711e80c8..d47c1b4421a3 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -347,8 +347,8 @@ void tcp_retransmit_timer(struct sock *sk)
                 return;
         }
         if (tp->fastopen_rsk) {
-                BUG_ON(sk->sk_state != TCP_SYN_RECV &&
-                    sk->sk_state != TCP_FIN_WAIT1);
+                WARN_ON_ONCE(sk->sk_state != TCP_SYN_RECV &&
+                             sk->sk_state != TCP_FIN_WAIT1);
                 tcp_fastopen_synack_timer(sk);
                 /* Before we receive ACK to our SYN-ACK don't retransmit
                  * anything else (e.g., data or FIN segments).