1. 13 Nov, 2016 7 commits
    • Stephen Suryaputra Lin's avatar
      ipv4: use new_gw for redirect neigh lookup · 969447f2
      Stephen Suryaputra Lin authored
      In v2.6, ip_rt_redirect() calls arp_bind_neighbour() which returns 0
      and then the state of the neigh for the new_gw is checked. If the state
      isn't valid then the redirected route is deleted. This behavior is
      maintained up to v3.5.7 by check_peer_redirect() because rt->rt_gateway
      is assigned to peer->redirect_learned.a4 before calling
      ipv4_neigh_lookup().
      
      After commit 5943634f ("ipv4: Maintain redirect and PMTU info in
      struct rtable again."), ipv4_neigh_lookup() is performed without the
      rt_gateway assigned to the new_gw. In the case when rt_gateway (old_gw)
      isn't zero, the function uses it as the key. The neigh is most likely
      valid since the old_gw is the one that sends the ICMP redirect message.
      Then the new_gw is assigned to fib_nh_exception. The problem is: the
      new_gw ARP may never gets resolved and the traffic is blackholed.
      
      So, use the new_gw for neigh lookup.
      
      Changes from v1:
       - use __ipv4_neigh_lookup instead (per Eric Dumazet).
      
      Fixes: 5943634f
      
       ("ipv4: Maintain redirect and PMTU info in struct rtable again.")
      Signed-off-by: default avatarStephen Suryaputra Lin <ssurya@ieee.org>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      969447f2
    • Guenter Roeck's avatar
      r8152: Fix error path in open function · ca0a7531
      Guenter Roeck authored
      
      
      If usb_submit_urb() called from the open function fails, the following
      crash may be observed.
      
      r8152 8-1:1.0 eth0: intr_urb submit failed: -19
      ...
      r8152 8-1:1.0 eth0: v1.08.3
      Unable to handle kernel paging request at virtual address 6b6b6b6b6b6b6b7b
      pgd = ffffffc0e7305000
      [6b6b6b6b6b6b6b7b] *pgd=0000000000000000, *pud=0000000000000000
      Internal error: Oops: 96000004 [#1] PREEMPT SMP
      ...
      PC is at notifier_chain_register+0x2c/0x58
      LR is at blocking_notifier_chain_register+0x54/0x70
      ...
      Call trace:
      [<ffffffc0002407f8>] notifier_chain_register+0x2c/0x58
      [<ffffffc000240bdc>] blocking_notifier_chain_register+0x54/0x70
      [<ffffffc00026991c>] register_pm_notifier+0x24/0x2c
      [<ffffffbffc183200>] rtl8152_open+0x3dc/0x3f8 [r8152]
      [<ffffffc000808000>] __dev_open+0xac/0x104
      [<ffffffc0008082f8>] __dev_change_flags+0xb0/0x148
      [<ffffffc0008083c4>] dev_change_flags+0x34/0x70
      [<ffffffc000818344>] do_setlink+0x2c8/0x888
      [<ffffffc0008199d4>] rtnl_newlink+0x328/0x644
      [<ffffffc000819e98>] rtnetlink_rcv_msg+0x1a8/0x1d4
      [<ffffffc0008373c8>] netlink_rcv_skb+0x68/0xd0
      [<ffffffc000817990>] rtnetlink_rcv+0x2c/0x3c
      [<ffffffc000836d1c>] netlink_unicast+0x16c/0x234
      [<ffffffc00083720c>] netlink_sendmsg+0x340/0x364
      [<ffffffc0007e85d0>] sock_sendmsg+0x48/0x60
      [<ffffffc0007e9c30>] SyS_sendto+0xe0/0x120
      [<ffffffc0007e9cb0>] SyS_send+0x40/0x4c
      [<ffffffc000203e34>] el0_svc_naked+0x24/0x28
      
      Clean up error handling to avoid registering the notifier if the open
      function is going to fail.
      Signed-off-by: default avatarGuenter Roeck <linux@roeck-us.net>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      ca0a7531
    • Baruch Siach's avatar
      net: bpqether.h: remove if_ether.h guard · 10b21768
      Baruch Siach authored
      
      
      __LINUX_IF_ETHER_H is not defined anywhere, and if_ether.h can keep itself from
      double inclusion, though it uses a single underscore prefix.
      Signed-off-by: default avatarBaruch Siach <baruch@tkos.co.il>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      10b21768
    • Eric Dumazet's avatar
      net: __skb_flow_dissect() must cap its return value · 34fad54c
      Eric Dumazet authored
      After Tom patch, thoff field could point past the end of the buffer,
      this could fool some callers.
      
      If an skb was provided, skb->len should be the upper limit.
      If not, hlen is supposed to be the upper limit.
      
      Fixes: a6e544b0
      
       ("flow_dissector: Jump to exit code in __skb_flow_dissect")
      Signed-off-by: default avatarEric Dumazet <edumazet@google.com>
      Reported-by: Yibin Yang <yibyang@cisco.com
      Acked-by: default avatarAlexander Duyck <alexander.h.duyck@intel.com>
      Acked-by: default avatarWillem de Bruijn <willemb@google.com>
      Acked-by: default avatarAlexei Starovoitov <ast@kernel.org>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      34fad54c
    • David S. Miller's avatar
      Merge branch 'fix-bpf_redirect' · 79774d6b
      David S. Miller authored
      
      
      Martin KaFai Lau says:
      
      ====================
      bpf: Fix bpf_redirect to an ipip/ip6tnl dev
      
      This patch set fixes a bug in bpf_redirect(dev, flags) when dev is an
      ipip/ip6tnl.  The current problem is IP-EthHdr-IP is sent out instead of
      IP-IP.
      
      Patch 1 adds a dev->type test similar to dev_is_mac_header_xmit()
      in act_mirred.c which is only available in net-next.  We can consider to
      refactor it once this patch is pulled into net-next from net.
      ====================
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      79774d6b
    • Martin KaFai Lau's avatar
      bpf: Add test for bpf_redirect to ipip/ip6tnl · 90e02896
      Martin KaFai Lau authored
      
      
      The test creates two netns, ns1 and ns2.  The host (the default netns)
      has an ipip or ip6tnl dev configured for tunneling traffic to the ns2.
      
          ping VIPS from ns1 <----> host <--tunnel--> ns2 (VIPs at loopback)
      
      The test is to have ns1 pinging VIPs configured at the loopback
      interface in ns2.
      
      The VIPs are 10.10.1.102 and 2401:face::66 (which are configured
      at lo@ns2). [Note: 0x66 => 102].
      
      At ns1, the VIPs are routed _via_ the host.
      
      At the host, bpf programs are installed at the veth to redirect packets
      from a veth to the ipip/ip6tnl.  The test is configured in a way so
      that both ingress and egress can be tested.
      
      At ns2, the ipip/ip6tnl dev is configured with the local and remote address
      specified.  The return path is routed to the dev ipip/ip6tnl.
      
      During egress test, the host also locally tests pinging the VIPs to ensure
      that bpf_redirect at egress also works for the direct egress (i.e. not
      forwarding from dev ve1 to ve2).
      Acked-by: default avatarAlexei Starovoitov <ast@fb.com>
      Signed-off-by: default avatarMartin KaFai Lau <kafai@fb.com>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      90e02896
    • Martin KaFai Lau's avatar
      bpf: Fix bpf_redirect to an ipip/ip6tnl dev · 4e3264d2
      Martin KaFai Lau authored
      If the bpf program calls bpf_redirect(dev, 0) and dev is
      an ipip/ip6tnl, it currently includes the mac header.
      e.g. If dev is ipip, the end result is IP-EthHdr-IP instead
      of IP-IP.
      
      The fix is to pull the mac header.  At ingress, skb_postpull_rcsum()
      is not needed because the ethhdr should have been pulled once already
      and then got pushed back just before calling the bpf_prog.
      At egress, this patch calls skb_postpull_rcsum().
      
      If bpf_redirect(dev, BPF_F_INGRESS) is called,
      it also fails now because it calls dev_forward_skb() which
      eventually calls eth_type_trans(skb, dev).  The eth_type_trans()
      will set skb->type = PACKET_OTHERHOST because the mac address
      does not match the redirecting dev->dev_addr.  The PACKET_OTHERHOST
      will eventually cause the ip_rcv() errors out.  To fix this,
      ____dev_forward_skb() is added.
      
      Joint work with Daniel Borkmann.
      
      Fixes: cfc7381b ("ip_tunnel: add collect_md mode to IPIP tunnel")
      Fixes: 8d79266b
      
       ("ip6_tunnel: add collect_md mode to IPv6 tunnels")
      Acked-by: default avatarDaniel Borkmann <daniel@iogearbox.net>
      Acked-by: default avatarAlexei Starovoitov <ast@fb.com>
      Signed-off-by: default avatarMartin KaFai Lau <kafai@fb.com>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      4e3264d2
  2. 10 Nov, 2016 11 commits
  3. 09 Nov, 2016 12 commits
  4. 08 Nov, 2016 9 commits
  5. 07 Nov, 2016 1 commit