1. 15 Dec, 2018 1 commit
  2. 08 Nov, 2018 1 commit
    • Paolo Abeni's avatar
      udp: implement GRO for plain UDP sockets. · e20cf8d3
      Paolo Abeni authored
      This is the RX counterpart of commit bec1f6f6 ("udp: generate gso
      with UDP_SEGMENT"). When UDP_GRO is enabled, such socket is also
      eligible for GRO in the rx path: UDP segments directed to such socket
      are assembled into a larger GSO_UDP_L4 packet.
      
      The core UDP GRO support is enabled with setsockopt(UDP_GRO).
      
      Initial benchmark numbers:
      
      Before:
      udp rx:   1079 MB/s   769065 calls/s
      
      After:
      udp rx:   1466 MB/s    24877 calls/s
      
      This change introduces a side effect in respect to UDP tunnels:
      after a UDP tunnel creation, now the kernel performs a lookup per ingress
      UDP packet, while before such lookup happened only if the ingress packet
      carried a valid internal header csum.
      
      rfc v2 -> rfc v3:
       - fixed typos in macro name and comments
       - really enforce UDP_GRO_CNT_MAX, instead of UDP_GRO_CNT_MAX + 1
       - acquire socket lock in UDP_GRO setsockopt
      
      rfc v1 -> rfc v2:
       - use a new option to enable UDP GRO
       - use static keys to protect the UDP GRO socket lookup
      Signed-off-by: default avatarPaolo Abeni <pabeni@redhat.com>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      e20cf8d3
  3. 05 Oct, 2018 1 commit
  4. 26 Jun, 2018 1 commit
    • David Miller's avatar
      net: Convert GRO SKB handling to list_head. · d4546c25
      David Miller authored
      Manage pending per-NAPI GRO packets via list_head.
      
      Return an SKB pointer from the GRO receive handlers.  When GRO receive
      handlers return non-NULL, it means that this SKB needs to be completed
      at this time and removed from the NAPI queue.
      
      Several operations are greatly simplified by this transformation,
      especially timing out the oldest SKB in the list when gro_count
      exceeds MAX_GRO_SKBS, and napi_gro_flush() which walks the queue
      in reverse order.
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      d4546c25
  5. 09 May, 2018 3 commits
  6. 26 Apr, 2018 1 commit
    • Willem de Bruijn's avatar
      udp: add udp gso · ee80d1eb
      Willem de Bruijn authored
      Implement generic segmentation offload support for udp datagrams. A
      follow-up patch adds support to the protocol stack to generate such
      packets.
      
      UDP GSO is not UFO. UFO fragments a single large datagram. GSO splits
      a large payload into a number of discrete UDP datagrams.
      
      The implementation adds a GSO type SKB_UDP_GSO_L4 to differentiate it
      from UFO (SKB_UDP_GSO).
      
      IPPROTO_UDPLITE is excluded, as that protocol has no gso handler
      registered.
      
      [ Export __udp_gso_segment for ipv6. -DaveM ]
      Signed-off-by: default avatarWillem de Bruijn <willemb@google.com>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      ee80d1eb
  7. 22 Jan, 2018 1 commit
  8. 23 Nov, 2017 1 commit
    • Willem de Bruijn's avatar
      net: accept UFO datagrams from tuntap and packet · 0c19f846
      Willem de Bruijn authored
      Tuntap and similar devices can inject GSO packets. Accept type
      VIRTIO_NET_HDR_GSO_UDP, even though not generating UFO natively.
      
      Processes are expected to use feature negotiation such as TUNSETOFFLOAD
      to detect supported offload types and refrain from injecting other
      packets. This process breaks down with live migration: guest kernels
      do not renegotiate flags, so destination hosts need to expose all
      features that the source host does.
      
      Partially revert the UFO removal from 182e0b6b~1..d9d30adf.
      This patch introduces nearly(*) no new code to simplify verification.
      It brings back verbatim tuntap UFO negotiation, VIRTIO_NET_HDR_GSO_UDP
      insertion and software UFO segmentation.
      
      It does not reinstate protocol stack support, hardware offload
      (NETIF_F_UFO), SKB_GSO_UDP tunneling in SKB_GSO_SOFTWARE or reception
      of VIRTIO_NET_HDR_GSO_UDP packets in tuntap.
      
      To support SKB_GSO_UDP reappearing in the stack, also reinstate
      logic in act_csum and openvswitch. Achieve equivalence with v4.13 HEAD
      by squashing in commit 93991221 ("net: skb_needs_check() removes
      CHECKSUM_UNNECESSARY check for tx.") and reverting commit 8d63bee6
      ("net: avoid skb_warn_bad_offload false positives on UFO").
      
      (*) To avoid having to bring back skb_shinfo(skb)->ip6_frag_id,
      ipv6_proxy_select_ident is changed to return a __be32 and this is
      assigned directly to the frag_hdr. Also, SKB_GSO_UDP is inserted
      at the end of the enum to minimize code churn.
      
      Tested
        Booted a v4.13 guest kernel with QEMU. On a host kernel before this
        patch `ethtool -k eth0` shows UFO disabled. After the patch, it is
        enabled, same as on a v4.13 host kernel.
      
        A UFO packet sent from the guest appears on the tap device:
          host:
            nc -l -p -u 8000 &
            tcpdump -n -i tap0
      
          guest:
            dd if=/dev/zero of=payload.txt bs=1 count=2000
            nc -u 192.16.1.1 8000 < payload.txt
      
        Direct tap to tap transmission of VIRTIO_NET_HDR_GSO_UDP succeeds,
        packets arriving fragmented:
      
          ./with_tap_pair.sh ./tap_send_ufo tap0 tap1
          (from https://github.com/wdebruij/kerneltools/tree/master/tests)
      
      Changes
        v1 -> v2
          - simplified set_offload change (review comment)
          - documented test procedure
      
      Link: http://lkml.kernel.org/r/<CAF=yD-LuUeDuL9YWPJD9ykOZ0QCjNeznPDr6whqZ9NGMNF12Mw@mail.gmail.com>
      Fixes: fb652fdf ("macvlan/macvtap: Remove NETIF_F_UFO advertisement.")
      Reported-by: default avatarMichal Kubecek <mkubecek@suse.cz>
      Signed-off-by: default avatarWillem de Bruijn <willemb@google.com>
      Acked-by: default avatarJason Wang <jasowang@redhat.com>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      0c19f846
  9. 09 Aug, 2017 1 commit
    • Willem de Bruijn's avatar
      net: avoid skb_warn_bad_offload false positives on UFO · 8d63bee6
      Willem de Bruijn authored
      skb_warn_bad_offload triggers a warning when an skb enters the GSO
      stack at __skb_gso_segment that does not have CHECKSUM_PARTIAL
      checksum offload set.
      
      Commit b2504a5d ("net: reduce skb_warn_bad_offload() noise")
      observed that SKB_GSO_DODGY producers can trigger the check and
      that passing those packets through the GSO handlers will fix it
      up. But, the software UFO handler will set ip_summed to
      CHECKSUM_NONE.
      
      When __skb_gso_segment is called from the receive path, this
      triggers the warning again.
      
      Make UFO set CHECKSUM_UNNECESSARY instead of CHECKSUM_NONE. On
      Tx these two are equivalent. On Rx, this better matches the
      skb state (checksum computed), as CHECKSUM_NONE here means no
      checksum computed.
      
      See also this thread for context:
      http://patchwork.ozlabs.org/patch/799015/
      
      Fixes: b2504a5d ("net: reduce skb_warn_bad_offload() noise")
      Signed-off-by: default avatarWillem de Bruijn <willemb@google.com>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      8d63bee6
  10. 17 Jul, 2017 1 commit
  11. 18 May, 2017 1 commit
  12. 17 May, 2017 1 commit
    • Craig Gallek's avatar
      ipv6: Prevent overrun when parsing v6 header options · 2423496a
      Craig Gallek authored
      The KASAN warning repoted below was discovered with a syzkaller
      program.  The reproducer is basically:
        int s = socket(AF_INET6, SOCK_RAW, NEXTHDR_HOP);
        send(s, &one_byte_of_data, 1, MSG_MORE);
        send(s, &more_than_mtu_bytes_data, 2000, 0);
      
      The socket() call sets the nexthdr field of the v6 header to
      NEXTHDR_HOP, the first send call primes the payload with a non zero
      byte of data, and the second send call triggers the fragmentation path.
      
      The fragmentation code tries to parse the header options in order
      to figure out where to insert the fragment option.  Since nexthdr points
      to an invalid option, the calculation of the size of the network header
      can made to be much larger than the linear section of the skb and data
      is read outside of it.
      
      This fix makes ip6_find_1stfrag return an error if it detects
      running out-of-bounds.
      
      [   42.361487] ==================================================================
      [   42.364412] BUG: KASAN: slab-out-of-bounds in ip6_fragment+0x11c8/0x3730
      [   42.365471] Read of size 840 at addr ffff88000969e798 by task ip6_fragment-oo/3789
      [   42.366469]
      [   42.366696] CPU: 1 PID: 3789 Comm: ip6_fragment-oo Not tainted 4.11.0+ #41
      [   42.367628] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.1-1ubuntu1 04/01/2014
      [   42.368824] Call Trace:
      [   42.369183]  dump_stack+0xb3/0x10b
      [   42.369664]  print_address_description+0x73/0x290
      [   42.370325]  kasan_report+0x252/0x370
      [   42.370839]  ? ip6_fragment+0x11c8/0x3730
      [   42.371396]  check_memory_region+0x13c/0x1a0
      [   42.371978]  memcpy+0x23/0x50
      [   42.372395]  ip6_fragment+0x11c8/0x3730
      [   42.372920]  ? nf_ct_expect_unregister_notifier+0x110/0x110
      [   42.373681]  ? ip6_copy_metadata+0x7f0/0x7f0
      [   42.374263]  ? ip6_forward+0x2e30/0x2e30
      [   42.374803]  ip6_finish_output+0x584/0x990
      [   42.375350]  ip6_output+0x1b7/0x690
      [   42.375836]  ? ip6_finish_output+0x990/0x990
      [   42.376411]  ? ip6_fragment+0x3730/0x3730
      [   42.376968]  ip6_local_out+0x95/0x160
      [   42.377471]  ip6_send_skb+0xa1/0x330
      [   42.377969]  ip6_push_pending_frames+0xb3/0xe0
      [   42.378589]  rawv6_sendmsg+0x2051/0x2db0
      [   42.379129]  ? rawv6_bind+0x8b0/0x8b0
      [   42.379633]  ? _copy_from_user+0x84/0xe0
      [   42.380193]  ? debug_check_no_locks_freed+0x290/0x290
      [   42.380878]  ? ___sys_sendmsg+0x162/0x930
      [   42.381427]  ? rcu_read_lock_sched_held+0xa3/0x120
      [   42.382074]  ? sock_has_perm+0x1f6/0x290
      [   42.382614]  ? ___sys_sendmsg+0x167/0x930
      [   42.383173]  ? lock_downgrade+0x660/0x660
      [   42.383727]  inet_sendmsg+0x123/0x500
      [   42.384226]  ? inet_sendmsg+0x123/0x500
      [   42.384748]  ? inet_recvmsg+0x540/0x540
      [   42.385263]  sock_sendmsg+0xca/0x110
      [   42.385758]  SYSC_sendto+0x217/0x380
      [   42.386249]  ? SYSC_connect+0x310/0x310
      [   42.386783]  ? __might_fault+0x110/0x1d0
      [   42.387324]  ? lock_downgrade+0x660/0x660
      [   42.387880]  ? __fget_light+0xa1/0x1f0
      [   42.388403]  ? __fdget+0x18/0x20
      [   42.388851]  ? sock_common_setsockopt+0x95/0xd0
      [   42.389472]  ? SyS_setsockopt+0x17f/0x260
      [   42.390021]  ? entry_SYSCALL_64_fastpath+0x5/0xbe
      [   42.390650]  SyS_sendto+0x40/0x50
      [   42.391103]  entry_SYSCALL_64_fastpath+0x1f/0xbe
      [   42.391731] RIP: 0033:0x7fbbb711e383
      [   42.392217] RSP: 002b:00007ffff4d34f28 EFLAGS: 00000246 ORIG_RAX: 000000000000002c
      [   42.393235] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007fbbb711e383
      [   42.394195] RDX: 0000000000001000 RSI: 00007ffff4d34f60 RDI: 0000000000000003
      [   42.395145] RBP: 0000000000000046 R08: 00007ffff4d34f40 R09: 0000000000000018
      [   42.396056] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000400aad
      [   42.396598] R13: 0000000000000066 R14: 00007ffff4d34ee0 R15: 00007fbbb717af00
      [   42.397257]
      [   42.397411] Allocated by task 3789:
      [   42.397702]  save_stack_trace+0x16/0x20
      [   42.398005]  save_stack+0x46/0xd0
      [   42.398267]  kasan_kmalloc+0xad/0xe0
      [   42.398548]  kasan_slab_alloc+0x12/0x20
      [   42.398848]  __kmalloc_node_track_caller+0xcb/0x380
      [   42.399224]  __kmalloc_reserve.isra.32+0x41/0xe0
      [   42.399654]  __alloc_skb+0xf8/0x580
      [   42.400003]  sock_wmalloc+0xab/0xf0
      [   42.400346]  __ip6_append_data.isra.41+0x2472/0x33d0
      [   42.400813]  ip6_append_data+0x1a8/0x2f0
      [   42.401122]  rawv6_sendmsg+0x11ee/0x2db0
      [   42.401505]  inet_sendmsg+0x123/0x500
      [   42.401860]  sock_sendmsg+0xca/0x110
      [   42.402209]  ___sys_sendmsg+0x7cb/0x930
      [   42.402582]  __sys_sendmsg+0xd9/0x190
      [   42.402941]  SyS_sendmsg+0x2d/0x50
      [   42.403273]  entry_SYSCALL_64_fastpath+0x1f/0xbe
      [   42.403718]
      [   42.403871] Freed by task 1794:
      [   42.404146]  save_stack_trace+0x16/0x20
      [   42.404515]  save_stack+0x46/0xd0
      [   42.404827]  kasan_slab_free+0x72/0xc0
      [   42.405167]  kfree+0xe8/0x2b0
      [   42.405462]  skb_free_head+0x74/0xb0
      [   42.405806]  skb_release_data+0x30e/0x3a0
      [   42.406198]  skb_release_all+0x4a/0x60
      [   42.406563]  consume_skb+0x113/0x2e0
      [   42.406910]  skb_free_datagram+0x1a/0xe0
      [   42.407288]  netlink_recvmsg+0x60d/0xe40
      [   42.407667]  sock_recvmsg+0xd7/0x110
      [   42.408022]  ___sys_recvmsg+0x25c/0x580
      [   42.408395]  __sys_recvmsg+0xd6/0x190
      [   42.408753]  SyS_recvmsg+0x2d/0x50
      [   42.409086]  entry_SYSCALL_64_fastpath+0x1f/0xbe
      [   42.409513]
      [   42.409665] The buggy address belongs to the object at ffff88000969e780
      [   42.409665]  which belongs to the cache kmalloc-512 of size 512
      [   42.410846] The buggy address is located 24 bytes inside of
      [   42.410846]  512-byte region [ffff88000969e780, ffff88000969e980)
      [   42.411941] The buggy address belongs to the page:
      [   42.412405] page:ffffea000025a780 count:1 mapcount:0 mapping:          (null) index:0x0 compound_mapcount: 0
      [   42.413298] flags: 0x100000000008100(slab|head)
      [   42.413729] raw: 0100000000008100 0000000000000000 0000000000000000 00000001800c000c
      [   42.414387] raw: ffffea00002a9500 0000000900000007 ffff88000c401280 0000000000000000
      [   42.415074] page dumped because: kasan: bad access detected
      [   42.415604]
      [   42.415757] Memory state around the buggy address:
      [   42.416222]  ffff88000969e880: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
      [   42.416904]  ffff88000969e900: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
      [   42.417591] >ffff88000969e980: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
      [   42.418273]                    ^
      [   42.418588]  ffff88000969ea00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
      [   42.419273]  ffff88000969ea80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
      [   42.419882] ==================================================================
      Reported-by: default avatarAndrey Konovalov <andreyknvl@google.com>
      Signed-off-by: default avatarCraig Gallek <kraig@google.com>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      2423496a
  13. 20 May, 2016 1 commit
    • Tom Herbert's avatar
      gso: Remove arbitrary checks for unsupported GSO · 5c7cdf33
      Tom Herbert authored
      In several gso_segment functions there are checks of gso_type against
      a seemingly arbitrary list of SKB_GSO_* flags. This seems like an
      attempt to identify unsupported GSO types, but since the stack is
      the one that set these GSO types in the first place this seems
      unnecessary to do. If a combination isn't valid in the first
      place that stack should not allow setting it.
      
      This is a code simplication especially for add new GSO types.
      Signed-off-by: default avatarTom Herbert <tom@herbertland.com>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      5c7cdf33
  14. 07 Apr, 2016 1 commit
    • Tom Herbert's avatar
      udp: Add GRO functions to UDP socket · a6024562
      Tom Herbert authored
      This patch adds GRO functions (gro_receive and gro_complete) to UDP
      sockets. udp_gro_receive is changed to perform socket lookup on a
      packet. If a socket is found the related GRO functions are called.
      
      This features obsoletes using UDP offload infrastructure for GRO
      (udp_offload). This has the advantage of not being limited to provide
      offload on a per port basis, GRO is now applied to whatever individual
      UDP sockets are bound to.  This also allows the possbility of
      "application defined GRO"-- that is we can attach something like
      a BPF program to a UDP socket to perfrom GRO on an application
      layer protocol.
      Signed-off-by: default avatarTom Herbert <tom@herbertland.com>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      a6024562
  15. 26 Feb, 2016 1 commit
    • Alexander Duyck's avatar
      GSO: Provide software checksum of tunneled UDP fragmentation offload · 22463876
      Alexander Duyck authored
      On reviewing the code I realized that GRE and UDP tunnels could cause a
      kernel panic if we used GSO to segment a large UDP frame that was sent
      through the tunnel with an outer checksum and hardware offloads were not
      available.
      
      In order to correct this we need to update the feature flags that are
      passed to the skb_segment function so that in the event of UDP
      fragmentation being requested for the inner header the segmentation
      function will correctly generate the checksum for the payload if we cannot
      segment the outer header.
      Signed-off-by: default avatarAlexander Duyck <aduyck@mirantis.com>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      22463876
  16. 25 Mar, 2015 1 commit
  17. 20 Mar, 2015 1 commit
  18. 11 Feb, 2015 1 commit
  19. 04 Feb, 2015 1 commit
    • Vlad Yasevich's avatar
      ipv6: Select fragment id during UFO segmentation if not set. · 0508c07f
      Vlad Yasevich authored
      If the IPv6 fragment id has not been set and we perform
      fragmentation due to UFO, select a new fragment id.
      We now consider a fragment id of 0 as unset and if id selection
      process returns 0 (after all the pertrubations), we set it to
      0x80000000, thus giving us ample space not to create collisions
      with the next packet we may have to fragment.
      
      When doing UFO integrity checking, we also select the
      fragment id if it has not be set yet.   This is stored into
      the skb_shinfo() thus allowing UFO to function correclty.
      
      This patch also removes duplicate fragment id generation code
      and moves ipv6_select_ident() into the header as it may be
      used during GSO.
      Signed-off-by: default avatarVladislav Yasevich <vyasevic@redhat.com>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      0508c07f
  20. 06 Nov, 2014 1 commit
  21. 05 Nov, 2014 1 commit
  22. 03 Oct, 2014 1 commit
    • Tom Herbert's avatar
      fou: eliminate IPv4,v6 specific GRO functions · efc98d08
      Tom Herbert authored
      This patch removes fou[46]_gro_receive and fou[46]_gro_complete
      functions. The v4 or v6 variants were chosen for the UDP offloads
      based on the address family of the socket this is not necessary
      or correct. Alternatively, this patch adds is_ipv6 to napi_gro_skb.
      This is set in udp6_gro_receive and unset in udp4_gro_receive. In
      fou_gro_receive the value is used to select the correct inet_offloads
      for the protocol of the outer IP header.
      Signed-off-by: default avatarTom Herbert <therbert@google.com>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      efc98d08
  23. 02 Oct, 2014 1 commit
    • Tom Herbert's avatar
      udp: Generalize skb_udp_segment · 8bce6d7d
      Tom Herbert authored
      skb_udp_segment is the function called from udp4_ufo_fragment to
      segment a UDP tunnel packet. This function currently assumes
      segmentation is transparent Ethernet bridging (i.e. VXLAN
      encapsulation). This patch generalizes the function to
      operate on either Ethertype or IP protocol.
      
      The inner_protocol field must be set to the protocol of the inner
      header. This can now be either an Ethertype or an IP protocol
      (in a union). A new flag in the skbuff indicates which type is
      effective. skb_set_inner_protocol and skb_set_inner_ipproto
      helper functions were added to set the inner_protocol. These
      functions are called from the point where the tunnel encapsulation
      is occuring.
      
      When skb_udp_tunnel_segment is called, the function to segment the
      inner packet is selected based on the inner IP or Ethertype. In the
      case of an IP protocol encapsulation, the function is derived from
      inet[6]_offloads. In the case of Ethertype, skb->protocol is
      set to the inner_protocol and skb_mac_gso_segment is called. (GRE
      currently does this, but it might be possible to lookup the protocol
      in offload_base and call the appropriate segmenation function
      directly).
      Signed-off-by: default avatarTom Herbert <therbert@google.com>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      8bce6d7d
  24. 26 Sep, 2014 2 commits
  25. 12 Sep, 2014 1 commit
    • Scott Wood's avatar
      udp: Fix inverted NAPI_GRO_CB(skb)->flush test · 2d8f7e2c
      Scott Wood authored
      Commit 2abb7cdc ("udp: Add support for doing checksum unnecessary
      conversion") caused napi_gro_cb structs with the "flush" field zero to
      take the "udp_gro_receive" path rather than the "set flush to 1" path
      that they would previously take.  As a result I saw booting from an NFS
      root hang shortly after starting userspace, with "server not
      responding" messages.
      
      This change to the handling of "flush == 0" packets appears to be
      incidental to the goal of adding new code in the case where
      skb_gro_checksum_validate_zero_check() returns zero.  Based on that and
      the fact that it breaks things, I'm assuming that it is unintentional.
      
      Fixes: 2abb7cdc ("udp: Add support for doing checksum unnecessary conversion")
      Cc: Tom Herbert <therbert@google.com>
      Signed-off-by: default avatarScott Wood <scottwood@freescale.com>
      Acked-by: default avatarEric Dumazet <edumazet@google.com>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      2d8f7e2c
  26. 10 Sep, 2014 1 commit
  27. 02 Sep, 2014 1 commit
    • Tom Herbert's avatar
      udp: Add support for doing checksum unnecessary conversion · 2abb7cdc
      Tom Herbert authored
      Add support for doing CHECKSUM_UNNECESSARY to CHECKSUM_COMPLETE
      conversion in UDP tunneling path.
      
      In the normal UDP path, we call skb_checksum_try_convert after locating
      the UDP socket. The check is that checksum conversion is enabled for
      the socket (new flag in UDP socket) and that checksum field is
      non-zero.
      
      In the UDP GRO path, we call skb_gro_checksum_try_convert after
      checksum is validated and checksum field is non-zero. Since this is
      already in GRO we assume that checksum conversion is always wanted.
      Signed-off-by: default avatarTom Herbert <therbert@google.com>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      2abb7cdc
  28. 25 Aug, 2014 1 commit
  29. 05 Jun, 2014 2 commits
  30. 22 Feb, 2014 1 commit
  31. 06 Nov, 2013 1 commit
  32. 21 Oct, 2013 1 commit
    • Eric Dumazet's avatar
      ipv6: sit: add GSO/TSO support · 61c1db7f
      Eric Dumazet authored
      Now ipv6_gso_segment() is stackable, its relatively easy to
      implement GSO/TSO support for SIT tunnels
      
      Performance results, when segmentation is done after tunnel
      device (as no NIC is yet enabled for TSO SIT support) :
      
      Before patch :
      
      lpq84:~# ./netperf -H 2002:af6:1153:: -Cc
      MIGRATED TCP STREAM TEST from ::0 (::) port 0 AF_INET6 to 2002:af6:1153:: () port 0 AF_INET6
      Recv   Send    Send                          Utilization       Service Demand
      Socket Socket  Message  Elapsed              Send     Recv     Send    Recv
      Size   Size    Size     Time     Throughput  local    remote   local   remote
      bytes  bytes   bytes    secs.    10^6bits/s  % S      % S      us/KB   us/KB
      
       87380  16384  16384    10.00      3168.31   4.81     4.64     2.988   2.877
      
      After patch :
      
      lpq84:~# ./netperf -H 2002:af6:1153:: -Cc
      MIGRATED TCP STREAM TEST from ::0 (::) port 0 AF_INET6 to 2002:af6:1153:: () port 0 AF_INET6
      Recv   Send    Send                          Utilization       Service Demand
      Socket Socket  Message  Elapsed              Send     Recv     Send    Recv
      Size   Size    Size     Time     Throughput  local    remote   local   remote
      bytes  bytes   bytes    secs.    10^6bits/s  % S      % S      us/KB   us/KB
      
       87380  16384  16384    10.00      5525.00   7.76     5.17     2.763   1.840
      Signed-off-by: default avatarEric Dumazet <edumazet@google.com>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      61c1db7f
  33. 19 Oct, 2013 1 commit
    • Eric Dumazet's avatar
      ipip: add GSO/TSO support · cb32f511
      Eric Dumazet authored
      Now inet_gso_segment() is stackable, its relatively easy to
      implement GSO/TSO support for IPIP
      
      Performance results, when segmentation is done after tunnel
      device (as no NIC is yet enabled for TSO IPIP support) :
      
      Before patch :
      
      lpq83:~# ./netperf -H 7.7.9.84 -Cc
      MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 7.7.9.84 () port 0 AF_INET
      Recv   Send    Send                          Utilization       Service Demand
      Socket Socket  Message  Elapsed              Send     Recv     Send    Recv
      Size   Size    Size     Time     Throughput  local    remote   local   remote
      bytes  bytes   bytes    secs.    10^6bits/s  % S      % S      us/KB   us/KB
      
       87380  16384  16384    10.00      3357.88   5.09     3.70     2.983   2.167
      
      After patch :
      
      lpq83:~# ./netperf -H 7.7.9.84 -Cc
      MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 7.7.9.84 () port 0 AF_INET
      Recv   Send    Send                          Utilization       Service Demand
      Socket Socket  Message  Elapsed              Send     Recv     Send    Recv
      Size   Size    Size     Time     Throughput  local    remote   local   remote
      bytes  bytes   bytes    secs.    10^6bits/s  % S      % S      us/KB   us/KB
      
       87380  16384  16384    10.00      7710.19   4.52     6.62     1.152   1.687
      Signed-off-by: default avatarEric Dumazet <edumazet@google.com>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      cb32f511
  34. 01 Sep, 2013 2 commits
  35. 01 Jun, 2013 1 commit