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

Pull networking fixes from David Miller:
 "A little more than usual this time around. Been travelling, so that is
  part of it.

  Anyways, here are the highlights:

   1) Deal with memcontrol races wrt. listener dismantle, from Eric
      Dumazet.

   2) Handle page allocation failures properly in nfp driver, from Jaku
      Kicinski.

   3) Fix memory leaks in macsec, from Sabrina Dubroca.

   4) Fix crashes in pppol2tp_session_ioctl(), from Guillaume Nault.

   5) Several fixes in bnxt_en driver, including preventing potential
      NVRAM parameter corruption from Michael Chan.

   6) Fix for KRACK attacks in wireless, from Johannes Berg.

   7) rtnetlink event generation fixes from Xin Long.

   8) Deadlock in mlxsw driver, from Ido Schimmel.

   9) Disallow arithmetic operations on context pointers in bpf, from
      Jakub Kicinski.

  10) Missing sock_owned_by_user() check in sctp_icmp_redirect(), from
      Xin Long.

  11) Only TCP is supported for sockmap, make that explicit with a
      check, from John Fastabend.

  12) Fix IP options state races in DCCP and TCP, from Eric Dumazet.

  13) Fix panic in packet_getsockopt(), also from Eric Dumazet.

  14) Add missing locked in hv_sock layer, from Dexuan Cui.

  15) Various aquantia bug fixes, including several statistics handling
      cures. From Igor Russkikh et al.

  16) Fix arithmetic overflow in devmap code, from John Fastabend.

  17) Fix busted socket memory accounting when we get a fault in the tcp
      zero copy paths. From Willem de Bruijn.

  18) Don't leave opt->tot_len uninitialized in ipv6, from Eric Dumazet"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (106 commits)
  stmmac: Don't access tx_q->dirty_tx before netif_tx_lock
  ipv6: flowlabel: do not leave opt->tot_len with garbage
  of_mdio: Fix broken PHY IRQ in case of probe deferral
  textsearch: fix typos in library helpers
  rxrpc: Don't release call mutex on error pointer
  net: stmmac: Prevent infinite loop in get_rx_timestamp_status()
  net: stmmac: Fix stmmac_get_rx_hwtstamp()
  net: stmmac: Add missing call to dev_kfree_skb()
  mlxsw: spectrum_router: Configure TIGCR on init
  mlxsw: reg: Add Tunneling IPinIP General Configuration Register
  net: ethtool: remove error check for legacy setting transceiver type
  soreuseport: fix initialization race
  net: bridge: fix returning of vlan range op errors
  sock: correct sk_wmem_queued accounting on efault in tcp zerocopy
  bpf: add test cases to bpf selftests to cover all access tests
  bpf: fix pattern matches for direct packet access
  bpf: fix off by one for range markings with L{T, E} patterns
  bpf: devmap fix arithmetic overflow in bitmap_size calculation
  net: aquantia: Bad udp rate on default interrupt coalescing
  net: aquantia: Enable coalescing management via ethtool interface
  ...

1 files changed, 13 insertions, 9 deletions

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 85164d4d3e53..4c43365c374c 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -877,7 +877,7 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst,
 
                 err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr,
                                             ireq->ir_rmt_addr,
-                                            ireq->opt);
+                                            rcu_dereference(ireq->ireq_opt));
                 err = net_xmit_eval(err);
         }
 
@@ -889,7 +889,7 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst,
  */
 static void tcp_v4_reqsk_destructor(struct request_sock *req)
 {
-        kfree(inet_rsk(req)->opt);
+        kfree(rcu_dereference_protected(inet_rsk(req)->ireq_opt, 1));
 }
 
 #ifdef CONFIG_TCP_MD5SIG
@@ -1265,10 +1265,11 @@ static void tcp_v4_init_req(struct request_sock *req,
                             struct sk_buff *skb)
 {
         struct inet_request_sock *ireq = inet_rsk(req);
+        struct net *net = sock_net(sk_listener);
 
         sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr);
         sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr);
-        ireq->opt = tcp_v4_save_options(sock_net(sk_listener), skb);
+        RCU_INIT_POINTER(ireq->ireq_opt, tcp_v4_save_options(net, skb));
 }
 
 static struct dst_entry *tcp_v4_route_req(const struct sock *sk,
@@ -1355,10 +1356,9 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
         sk_daddr_set(newsk, ireq->ir_rmt_addr);
         sk_rcv_saddr_set(newsk, ireq->ir_loc_addr);
         newsk->sk_bound_dev_if = ireq->ir_iif;
-        newinet->inet_saddr           = ireq->ir_loc_addr;
-        inet_opt              = ireq->opt;
-        rcu_assign_pointer(newinet->inet_opt, inet_opt);
-        ireq->opt             = NULL;
+        newinet->inet_saddr   = ireq->ir_loc_addr;
+        inet_opt              = rcu_dereference(ireq->ireq_opt);
+        RCU_INIT_POINTER(newinet->inet_opt, inet_opt);
         newinet->mc_index     = inet_iif(skb);
         newinet->mc_ttl       = ip_hdr(skb)->ttl;
         newinet->rcv_tos      = ip_hdr(skb)->tos;
@@ -1403,9 +1403,12 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
         if (__inet_inherit_port(sk, newsk) < 0)
                 goto put_and_exit;
         *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash));
-        if (*own_req)
+        if (likely(*own_req)) {
                 tcp_move_syn(newtp, req);
-
+                ireq->ireq_opt = NULL;
+        } else {
+                newinet->inet_opt = NULL;
+        }
         return newsk;
 
 exit_overflow:
@@ -1416,6 +1419,7 @@ exit:
         tcp_listendrop(sk);
         return NULL;
 put_and_exit:
+        newinet->inet_opt = NULL;
         inet_csk_prepare_forced_close(newsk);
         tcp_done(newsk);
         goto exit;