Skip to content

K
Kernel

openeuler / Kernel
1 年多 前同步成功

通知 8
Star 0
Fork 0
K
Kernel
切换分支/标签
  1. 25 2月, 2020 1 次提交
  3. 05 12月, 2019 1 次提交
  5. 16 11月, 2019 1 次提交
  7. 19 10月, 2019 1 次提交
  9. 27 9月, 2019 1 次提交
  11. 14 9月, 2019 1 次提交
    • W
      ip: support SO_MARK cmsg · c6af0c22
      由 Willem de Bruijn 提交于 
      Enable setting skb->mark for UDP and RAW sockets using cmsg.

This is analogous to existing support for TOS, TTL, txtime, etc.

Packet sockets already support this as of commit c7d39e32
("packet: support per-packet fwmark for af_packet sendmsg").

Similar to other fields, implement by
1. initialize the sockcm_cookie.mark from socket option sk_mark
2. optionally overwrite this in ip_cmsg_send/ip6_datagram_send_ctl
3. initialize inet_cork.mark from sockcm_cookie.mark
4. initialize each (usually just one) skb->mark from inet_cork.mark

Step 1 is handled in one location for most protocols by ipcm_init_sk
as of commit 35178206 ("ipv4: ipcm_cookie initializers").
Signed-off-by: NWillem de Bruijn <willemb@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      c6af0c22
  13. 27 6月, 2019 1 次提交
  15. 12 6月, 2019 1 次提交
  17. 04 6月, 2019 1 次提交
    • E
      net: fix use-after-free in kfree_skb_list · b7034146
      由 Eric Dumazet 提交于 
      syzbot reported nasty use-after-free [1]

Lets remove frag_list field from structs ip_fraglist_iter
and ip6_fraglist_iter. This seens not needed anyway.

[1] :
BUG: KASAN: use-after-free in kfree_skb_list+0x5d/0x60 net/core/skbuff.c:706
Read of size 8 at addr ffff888085a3cbc0 by task syz-executor303/8947

CPU: 0 PID: 8947 Comm: syz-executor303 Not tainted 5.2.0-rc2+ #12
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x172/0x1f0 lib/dump_stack.c:113
 print_address_description.cold+0x7c/0x20d mm/kasan/report.c:188
 __kasan_report.cold+0x1b/0x40 mm/kasan/report.c:317
 kasan_report+0x12/0x20 mm/kasan/common.c:614
 __asan_report_load8_noabort+0x14/0x20 mm/kasan/generic_report.c:132
 kfree_skb_list+0x5d/0x60 net/core/skbuff.c:706
 ip6_fragment+0x1ef4/0x2680 net/ipv6/ip6_output.c:882
 __ip6_finish_output+0x577/0xaa0 net/ipv6/ip6_output.c:144
 ip6_finish_output+0x38/0x1f0 net/ipv6/ip6_output.c:156
 NF_HOOK_COND include/linux/netfilter.h:294 [inline]
 ip6_output+0x235/0x7f0 net/ipv6/ip6_output.c:179
 dst_output include/net/dst.h:433 [inline]
 ip6_local_out+0xbb/0x1b0 net/ipv6/output_core.c:179
 ip6_send_skb+0xbb/0x350 net/ipv6/ip6_output.c:1796
 ip6_push_pending_frames+0xc8/0xf0 net/ipv6/ip6_output.c:1816
 rawv6_push_pending_frames net/ipv6/raw.c:617 [inline]
 rawv6_sendmsg+0x2993/0x35e0 net/ipv6/raw.c:947
 inet_sendmsg+0x141/0x5d0 net/ipv4/af_inet.c:802
 sock_sendmsg_nosec net/socket.c:652 [inline]
 sock_sendmsg+0xd7/0x130 net/socket.c:671
 ___sys_sendmsg+0x803/0x920 net/socket.c:2292
 __sys_sendmsg+0x105/0x1d0 net/socket.c:2330
 __do_sys_sendmsg net/socket.c:2339 [inline]
 __se_sys_sendmsg net/socket.c:2337 [inline]
 __x64_sys_sendmsg+0x78/0xb0 net/socket.c:2337
 do_syscall_64+0xfd/0x680 arch/x86/entry/common.c:301
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x44add9
Code: e8 7c e6 ff ff 48 83 c4 18 c3 0f 1f 80 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 1b 05 fc ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007f826f33bce8 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 00000000006e7a18 RCX: 000000000044add9
RDX: 0000000000000000 RSI: 0000000020000240 RDI: 0000000000000005
RBP: 00000000006e7a10 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00000000006e7a1c
R13: 00007ffcec4f7ebf R14: 00007f826f33c9c0 R15: 20c49ba5e353f7cf

Allocated by task 8947:
 save_stack+0x23/0x90 mm/kasan/common.c:71
 set_track mm/kasan/common.c:79 [inline]
 __kasan_kmalloc mm/kasan/common.c:489 [inline]
 __kasan_kmalloc.constprop.0+0xcf/0xe0 mm/kasan/common.c:462
 kasan_slab_alloc+0xf/0x20 mm/kasan/common.c:497
 slab_post_alloc_hook mm/slab.h:437 [inline]
 slab_alloc_node mm/slab.c:3269 [inline]
 kmem_cache_alloc_node+0x131/0x710 mm/slab.c:3579
 __alloc_skb+0xd5/0x5e0 net/core/skbuff.c:199
 alloc_skb include/linux/skbuff.h:1058 [inline]
 __ip6_append_data.isra.0+0x2a24/0x3640 net/ipv6/ip6_output.c:1519
 ip6_append_data+0x1e5/0x320 net/ipv6/ip6_output.c:1688
 rawv6_sendmsg+0x1467/0x35e0 net/ipv6/raw.c:940
 inet_sendmsg+0x141/0x5d0 net/ipv4/af_inet.c:802
 sock_sendmsg_nosec net/socket.c:652 [inline]
 sock_sendmsg+0xd7/0x130 net/socket.c:671
 ___sys_sendmsg+0x803/0x920 net/socket.c:2292
 __sys_sendmsg+0x105/0x1d0 net/socket.c:2330
 __do_sys_sendmsg net/socket.c:2339 [inline]
 __se_sys_sendmsg net/socket.c:2337 [inline]
 __x64_sys_sendmsg+0x78/0xb0 net/socket.c:2337
 do_syscall_64+0xfd/0x680 arch/x86/entry/common.c:301
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Freed by task 8947:
 save_stack+0x23/0x90 mm/kasan/common.c:71
 set_track mm/kasan/common.c:79 [inline]
 __kasan_slab_free+0x102/0x150 mm/kasan/common.c:451
 kasan_slab_free+0xe/0x10 mm/kasan/common.c:459
 __cache_free mm/slab.c:3432 [inline]
 kmem_cache_free+0x86/0x260 mm/slab.c:3698
 kfree_skbmem net/core/skbuff.c:625 [inline]
 kfree_skbmem+0xc5/0x150 net/core/skbuff.c:619
 __kfree_skb net/core/skbuff.c:682 [inline]
 kfree_skb net/core/skbuff.c:699 [inline]
 kfree_skb+0xf0/0x390 net/core/skbuff.c:693
 kfree_skb_list+0x44/0x60 net/core/skbuff.c:708
 __dev_xmit_skb net/core/dev.c:3551 [inline]
 __dev_queue_xmit+0x3034/0x36b0 net/core/dev.c:3850
 dev_queue_xmit+0x18/0x20 net/core/dev.c:3914
 neigh_direct_output+0x16/0x20 net/core/neighbour.c:1532
 neigh_output include/net/neighbour.h:511 [inline]
 ip6_finish_output2+0x1034/0x2550 net/ipv6/ip6_output.c:120
 ip6_fragment+0x1ebb/0x2680 net/ipv6/ip6_output.c:863
 __ip6_finish_output+0x577/0xaa0 net/ipv6/ip6_output.c:144
 ip6_finish_output+0x38/0x1f0 net/ipv6/ip6_output.c:156
 NF_HOOK_COND include/linux/netfilter.h:294 [inline]
 ip6_output+0x235/0x7f0 net/ipv6/ip6_output.c:179
 dst_output include/net/dst.h:433 [inline]
 ip6_local_out+0xbb/0x1b0 net/ipv6/output_core.c:179
 ip6_send_skb+0xbb/0x350 net/ipv6/ip6_output.c:1796
 ip6_push_pending_frames+0xc8/0xf0 net/ipv6/ip6_output.c:1816
 rawv6_push_pending_frames net/ipv6/raw.c:617 [inline]
 rawv6_sendmsg+0x2993/0x35e0 net/ipv6/raw.c:947
 inet_sendmsg+0x141/0x5d0 net/ipv4/af_inet.c:802
 sock_sendmsg_nosec net/socket.c:652 [inline]
 sock_sendmsg+0xd7/0x130 net/socket.c:671
 ___sys_sendmsg+0x803/0x920 net/socket.c:2292
 __sys_sendmsg+0x105/0x1d0 net/socket.c:2330
 __do_sys_sendmsg net/socket.c:2339 [inline]
 __se_sys_sendmsg net/socket.c:2337 [inline]
 __x64_sys_sendmsg+0x78/0xb0 net/socket.c:2337
 do_syscall_64+0xfd/0x680 arch/x86/entry/common.c:301
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

The buggy address belongs to the object at ffff888085a3cbc0
 which belongs to the cache skbuff_head_cache of size 224
The buggy address is located 0 bytes inside of
 224-byte region [ffff888085a3cbc0, ffff888085a3cca0)
The buggy address belongs to the page:
page:ffffea0002168f00 refcount:1 mapcount:0 mapping:ffff88821b6f63c0 index:0x0
flags: 0x1fffc0000000200(slab)
raw: 01fffc0000000200 ffffea00027bbf88 ffffea0002105b88 ffff88821b6f63c0
raw: 0000000000000000 ffff888085a3c080 000000010000000c 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff888085a3ca80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
 ffff888085a3cb00: 00 00 00 00 00 00 00 00 00 00 00 00 fc fc fc fc
>ffff888085a3cb80: fc fc fc fc fc fc fc fc fb fb fb fb fb fb fb fb
                                           ^
 ffff888085a3cc00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff888085a3cc80: fb fb fb fb fc fc fc fc fc fc fc fc fc fc fc fc

Fixes: 0feca619 ("net: ipv6: add skbuff fraglist splitter")
Fixes: c8b17be0 ("net: ipv4: add skbuff fraglist splitter")
Signed-off-by: NEric Dumazet <edumazet@google.com>
Cc: Pablo Neira Ayuso <pablo@netfilter.org>
Acked-by: NPablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      b7034146
  19. 01 6月, 2019 1 次提交
  21. 31 5月, 2019 4 次提交
    • W
      net: correct zerocopy refcnt with udp MSG_MORE · 100f6d8e
      由 Willem de Bruijn 提交于 
      TCP zerocopy takes a uarg reference for every skb, plus one for the
tcp_sendmsg_locked datapath temporarily, to avoid reaching refcnt zero
as it builds, sends and frees skbs inside its inner loop.

UDP and RAW zerocopy do not send inside the inner loop so do not need
the extra sock_zerocopy_get + sock_zerocopy_put pair. Commit
52900d22288ed ("udp: elide zerocopy operation in hot path") introduced
extra_uref to pass the initial reference taken in sock_zerocopy_alloc
to the first generated skb.

But, sock_zerocopy_realloc takes this extra reference at the start of
every call. With MSG_MORE, no new skb may be generated to attach the
extra_uref to, so refcnt is incorrectly 2 with only one skb.

Do not take the extra ref if uarg && !tcp, which implies MSG_MORE.
Update extra_uref accordingly.

This conditional assignment triggers a false positive may be used
uninitialized warning, so have to initialize extra_uref at define.

Changes v1->v2: fix typo in Fixes SHA1

Fixes: 52900d22 ("udp: elide zerocopy operation in hot path")
Reported-by: Nsyzbot <syzkaller@googlegroups.com>
Diagnosed-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NWillem de Bruijn <willemb@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      100f6d8e
    • P
      net: ipv6: split skbuff into fragments transformer · 8a6a1f17
      由 Pablo Neira Ayuso 提交于 
      This patch exposes a new API to refragment a skbuff. This allows you to
split either a linear skbuff or to force the refragmentation of an
existing fraglist using a different mtu. The API consists of:

* ip6_frag_init(), that initializes the internal state of the transformer.
* ip6_frag_next(), that allows you to fetch the next fragment. This function
  internally allocates the skbuff that represents the fragment, it pushes
  the IPv6 header, and it also copies the payload for each fragment.

The ip6_frag_state object stores the internal state of the splitter.

This code has been extracted from ip6_fragment(). Symbols are also
exported to allow to reuse this iterator from the bridge codepath to
build its own refragmentation routine by reusing the existing codebase.
Signed-off-by: NPablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      8a6a1f17
    • P
      net: ipv6: add skbuff fraglist splitter · 0feca619
      由 Pablo Neira Ayuso 提交于 
      This patch adds the skbuff fraglist split iterator. This API provides an
iterator to transform the fraglist into single skbuff objects, it
consists of:

* ip6_fraglist_init(), that initializes the internal state of the
  fraglist iterator.
* ip6_fraglist_prepare(), that restores the IPv6 header on the fragment.
* ip6_fraglist_next(), that retrieves the fragment from the fraglist and
  updates the internal state of the iterator to point to the next
  fragment in the fraglist.

The ip6_fraglist_iter object stores the internal state of the iterator.

This code has been extracted from ip6_fragment(). Symbols are also
exported to allow to reuse this iterator from the bridge codepath to
build its own refragmentation routine by reusing the existing codebase.
Signed-off-by: NPablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      0feca619
    • T
      treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 152 · 2874c5fd
      由 Thomas Gleixner 提交于 
      Based on 1 normalized pattern(s):

  this program is free software you can redistribute it and or modify
  it under the terms of the gnu general public license as published by
  the free software foundation either version 2 of the license or at
  your option any later version

extracted by the scancode license scanner the SPDX license identifier

  GPL-2.0-or-later

has been chosen to replace the boilerplate/reference in 3029 file(s).
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Reviewed-by: NAllison Randal <allison@lohutok.net>
Cc: linux-spdx@vger.kernel.org
Link: https://lkml.kernel.org/r/20190527070032.746973796@linutronix.deSigned-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>
      2874c5fd
  23. 09 4月, 2019 1 次提交
    • D
      neighbor: Add skip_cache argument to neigh_output · 0353f282
      由 David Ahern 提交于 
      A later patch allows an IPv6 gateway with an IPv4 route. The neighbor
entry will exist in the v6 ndisc table and the cached header will contain
the ipv6 protocol which is wrong for an IPv4 packet. For an IPv4 packet to
use the v6 neighbor entry, neigh_output needs to skip the cached header
and just use the output callback for the neigh entry.

A future patchset can look at expanding the hh_cache to handle 2
protocols. For now, IPv6 gateways with an IPv4 route will take the
extra overhead of generating the header.
Signed-off-by: NDavid Ahern <dsahern@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      0353f282
  25. 04 4月, 2019 1 次提交
  27. 04 3月, 2019 1 次提交
  29. 20 12月, 2018 1 次提交
    • F
      sk_buff: add skb extension infrastructure · df5042f4
      由 Florian Westphal 提交于 
      This adds an optional extension infrastructure, with ispec (xfrm) and
bridge netfilter as first users.
objdiff shows no changes if kernel is built without xfrm and br_netfilter
support.

The third (planned future) user is Multipath TCP which is still
out-of-tree.
MPTCP needs to map logical mptcp sequence numbers to the tcp sequence
numbers used by individual subflows.

This DSS mapping is read/written from tcp option space on receive and
written to tcp option space on transmitted tcp packets that are part of
and MPTCP connection.

Extending skb_shared_info or adding a private data field to skb fclones
doesn't work for incoming skb, so a different DSS propagation method would
be required for the receive side.

mptcp has same requirements as secpath/bridge netfilter:

1. extension memory is released when the sk_buff is free'd.
2. data is shared after cloning an skb (clone inherits extension)
3. adding extension to an skb will COW the extension buffer if needed.

The "MPTCP upstreaming" effort adds SKB_EXT_MPTCP extension to store the
mapping for tx and rx processing.

Two new members are added to sk_buff:
1. 'active_extensions' byte (filling a hole), telling which extensions
   are available for this skb.
   This has two purposes.
   a) avoids the need to initialize the pointer.
   b) allows to "delete" an extension by clearing its bit
   value in ->active_extensions.

   While it would be possible to store the active_extensions byte
   in the extension struct instead of sk_buff, there is one problem
   with this:
    When an extension has to be disabled, we can always clear the
    bit in skb->active_extensions.  But in case it would be stored in the
    extension buffer itself, we might have to COW it first, if
    we are dealing with a cloned skb.  On kmalloc failure we would
    be unable to turn an extension off.

2. extension pointer, located at the end of the sk_buff.
   If the active_extensions byte is 0, the pointer is undefined,
   it is not initialized on skb allocation.

This adds extra code to skb clone and free paths (to deal with
refcount/free of extension area) but this replaces similar code that
manages skb->nf_bridge and skb->sp structs in the followup patches of
the series.

It is possible to add support for extensions that are not preseved on
clones/copies.

To do this, it would be needed to define a bitmask of all extensions that
need copy/cow semantics, and change __skb_ext_copy() to check
->active_extensions & SKB_EXT_PRESERVE_ON_CLONE, then just set
->active_extensions to 0 on the new clone.

This isn't done here because all extensions that get added here
need the copy/cow semantics.

v2:
Allocate entire extension space using kmem_cache.
Upside is that this allows better tracking of used memory,
downside is that we will allocate more space than strictly needed in
most cases (its unlikely that all extensions are active/needed at same
time for same skb).
The allocated memory (except the small extension header) is not cleared,
so no additonal overhead aside from memory usage.

Avoid atomic_dec_and_test operation on skb_ext_put()
by using similar trick as kfree_skbmem() does with fclone_ref:
If recount is 1, there is no concurrent user and we can free right away.
Signed-off-by: NFlorian Westphal <fw@strlen.de>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      df5042f4
  31. 16 12月, 2018 1 次提交
  33. 09 12月, 2018 1 次提交
  35. 08 12月, 2018 1 次提交
    • S
      ipv6: Check available headroom in ip6_xmit() even without options · 66033f47
      由 Stefano Brivio 提交于 
      Even if we send an IPv6 packet without options, MAX_HEADER might not be
enough to account for the additional headroom required by alignment of
hardware headers.

On a configuration without HYPERV_NET, WLAN, AX25, and with IPV6_TUNNEL,
sending short SCTP packets over IPv4 over L2TP over IPv6, we start with
100 bytes of allocated headroom in sctp_packet_transmit(), end up with 54
bytes after l2tp_xmit_skb(), and 14 bytes in ip6_finish_output2().

Those would be enough to append our 14 bytes header, but we're going to
align that to 16 bytes, and write 2 bytes out of the allocated slab in
neigh_hh_output().

KASan says:

[  264.967848] ==================================================================
[  264.967861] BUG: KASAN: slab-out-of-bounds in ip6_finish_output2+0x1aec/0x1c70
[  264.967866] Write of size 16 at addr 000000006af1c7fe by task netperf/6201
[  264.967870]
[  264.967876] CPU: 0 PID: 6201 Comm: netperf Not tainted 4.20.0-rc4+ #1
[  264.967881] Hardware name: IBM 2827 H43 400 (z/VM 6.4.0)
[  264.967887] Call Trace:
[  264.967896] ([<00000000001347d6>] show_stack+0x56/0xa0)
[  264.967903]  [<00000000017e379c>] dump_stack+0x23c/0x290
[  264.967912]  [<00000000007bc594>] print_address_description+0xf4/0x290
[  264.967919]  [<00000000007bc8fc>] kasan_report+0x13c/0x240
[  264.967927]  [<000000000162f5e4>] ip6_finish_output2+0x1aec/0x1c70
[  264.967935]  [<000000000163f890>] ip6_finish_output+0x430/0x7f0
[  264.967943]  [<000000000163fe44>] ip6_output+0x1f4/0x580
[  264.967953]  [<000000000163882a>] ip6_xmit+0xfea/0x1ce8
[  264.967963]  [<00000000017396e2>] inet6_csk_xmit+0x282/0x3f8
[  264.968033]  [<000003ff805fb0ba>] l2tp_xmit_skb+0xe02/0x13e0 [l2tp_core]
[  264.968037]  [<000003ff80631192>] l2tp_eth_dev_xmit+0xda/0x150 [l2tp_eth]
[  264.968041]  [<0000000001220020>] dev_hard_start_xmit+0x268/0x928
[  264.968069]  [<0000000001330e8e>] sch_direct_xmit+0x7ae/0x1350
[  264.968071]  [<000000000122359c>] __dev_queue_xmit+0x2b7c/0x3478
[  264.968075]  [<00000000013d2862>] ip_finish_output2+0xce2/0x11a0
[  264.968078]  [<00000000013d9b14>] ip_finish_output+0x56c/0x8c8
[  264.968081]  [<00000000013ddd1e>] ip_output+0x226/0x4c0
[  264.968083]  [<00000000013dbd6c>] __ip_queue_xmit+0x894/0x1938
[  264.968100]  [<000003ff80bc3a5c>] sctp_packet_transmit+0x29d4/0x3648 [sctp]
[  264.968116]  [<000003ff80b7bf68>] sctp_outq_flush_ctrl.constprop.5+0x8d0/0xe50 [sctp]
[  264.968131]  [<000003ff80b7c716>] sctp_outq_flush+0x22e/0x7d8 [sctp]
[  264.968146]  [<000003ff80b35c68>] sctp_cmd_interpreter.isra.16+0x530/0x6800 [sctp]
[  264.968161]  [<000003ff80b3410a>] sctp_do_sm+0x222/0x648 [sctp]
[  264.968177]  [<000003ff80bbddac>] sctp_primitive_ASSOCIATE+0xbc/0xf8 [sctp]
[  264.968192]  [<000003ff80b93328>] __sctp_connect+0x830/0xc20 [sctp]
[  264.968208]  [<000003ff80bb11ce>] sctp_inet_connect+0x2e6/0x378 [sctp]
[  264.968212]  [<0000000001197942>] __sys_connect+0x21a/0x450
[  264.968215]  [<000000000119aff8>] sys_socketcall+0x3d0/0xb08
[  264.968218]  [<000000000184ea7a>] system_call+0x2a2/0x2c0

[...]

Just like ip_finish_output2() does for IPv4, check that we have enough
headroom in ip6_xmit(), and reallocate it if we don't.

This issue is older than git history.
Reported-by: NJianlin Shi <jishi@redhat.com>
Signed-off-by: NStefano Brivio <sbrivio@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      66033f47
  37. 05 12月, 2018 1 次提交
  39. 04 12月, 2018 2 次提交
    • W
      udp: elide zerocopy operation in hot path · 52900d22
      由 Willem de Bruijn 提交于 
      With MSG_ZEROCOPY, each skb holds a reference to a struct ubuf_info.
Release of its last reference triggers a completion notification.

The TCP stack in tcp_sendmsg_locked holds an extra ref independent of
the skbs, because it can build, send and free skbs within its loop,
possibly reaching refcount zero and freeing the ubuf_info too soon.

The UDP stack currently also takes this extra ref, but does not need
it as all skbs are sent after return from __ip(6)_append_data.

Avoid the extra refcount_inc and refcount_dec_and_test, and generally
the sock_zerocopy_put in the common path, by passing the initial
reference to the first skb.

This approach is taken instead of initializing the refcount to 0, as
that would generate error "refcount_t: increment on 0" on the
next skb_zcopy_set.

Changes
  v3 -> v4
    - Move skb_zcopy_set below the only kfree_skb that might cause
      a premature uarg destroy before skb_zerocopy_put_abort
      - Move the entire skb_shinfo assignment block, to keep that
        cacheline access in one place
Signed-off-by: NWillem de Bruijn <willemb@google.com>
Acked-by: NPaolo Abeni <pabeni@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      52900d22
    • W
      udp: msg_zerocopy · b5947e5d
      由 Willem de Bruijn 提交于 
      Extend zerocopy to udp sockets. Allow setting sockopt SO_ZEROCOPY and
interpret flag MSG_ZEROCOPY.

This patch was previously part of the zerocopy RFC patchsets. Zerocopy
is not effective at small MTU. With segmentation offload building
larger datagrams, the benefit of page flipping outweights the cost of
generating a completion notification.

tools/testing/selftests/net/msg_zerocopy.sh after applying follow-on
test patch and making skb_orphan_frags_rx same as skb_orphan_frags:

    ipv4 udp -t 1
    tx=191312 (11938 MB) txc=0 zc=n
    rx=191312 (11938 MB)
    ipv4 udp -z -t 1
    tx=304507 (19002 MB) txc=304507 zc=y
    rx=304507 (19002 MB)
    ok
    ipv6 udp -t 1
    tx=174485 (10888 MB) txc=0 zc=n
    rx=174485 (10888 MB)
    ipv6 udp -z -t 1
    tx=294801 (18396 MB) txc=294801 zc=y
    rx=294801 (18396 MB)
    ok

Changes
  v1 -> v2
    - Fixup reverse christmas tree violation
  v2 -> v3
    - Split refcount avoidance optimization into separate patch
      - Fix refcount leak on error in fragmented case
        (thanks to Paolo Abeni for pointing this one out!)
      - Fix refcount inc on zero
      - Test sock_flag SOCK_ZEROCOPY directly in __ip_append_data.
        This is needed since commit 5cf4a853 ("tcp: really ignore
	MSG_ZEROCOPY if no SO_ZEROCOPY") did the same for tcp.
Signed-off-by: NWillem de Bruijn <willemb@google.com>
Acked-by: NPaolo Abeni <pabeni@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      b5947e5d
  41. 25 11月, 2018 1 次提交
    • W
      net: always initialize pagedlen · aba36930
      由 Willem de Bruijn 提交于 
      In ip packet generation, pagedlen is initialized for each skb at the
start of the loop in __ip(6)_append_data, before label alloc_new_skb.

Depending on compiler options, code can be generated that jumps to
this label, triggering use of an an uninitialized variable.

In practice, at -O2, the generated code moves the initialization below
the label. But the code should not rely on that for correctness.

Fixes: 15e36f5b ("udp: paged allocation with gso")
Signed-off-by: NWillem de Bruijn <willemb@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      aba36930
  43. 17 9月, 2018 1 次提交
  45. 11 9月, 2018 1 次提交
  47. 24 7月, 2018 1 次提交
    • P
      ip: hash fragments consistently · 3dd1c9a1
      由 Paolo Abeni 提交于 
      The skb hash for locally generated ip[v6] fragments belonging
to the same datagram can vary in several circumstances:
* for connected UDP[v6] sockets, the first fragment get its hash
  via set_owner_w()/skb_set_hash_from_sk()
* for unconnected IPv6 UDPv6 sockets, the first fragment can get
  its hash via ip6_make_flowlabel()/skb_get_hash_flowi6(), if
  auto_flowlabel is enabled

For the following frags the hash is usually computed via
skb_get_hash().
The above can cause OoO for unconnected IPv6 UDPv6 socket: in that
scenario the egress tx queue can be selected on a per packet basis
via the skb hash.
It may also fool flow-oriented schedulers to place fragments belonging
to the same datagram in different flows.

Fix the issue by copying the skb hash from the head frag into
the others at fragmentation time.

Before this commit:
perf probe -a "dev_queue_xmit skb skb->hash skb->l4_hash:b1@0/8 skb->sw_hash:b1@1/8"
netperf -H $IPV4 -t UDP_STREAM -l 5 -- -m 2000 -n &
perf record -e probe:dev_queue_xmit -e probe:skb_set_owner_w -a sleep 0.1
perf script
probe:dev_queue_xmit: (ffffffff8c6b1b20) hash=3713014309 l4_hash=1 sw_hash=0
probe:dev_queue_xmit: (ffffffff8c6b1b20) hash=0 l4_hash=0 sw_hash=0

After this commit:
probe:dev_queue_xmit: (ffffffff8c6b1b20) hash=2171763177 l4_hash=1 sw_hash=0
probe:dev_queue_xmit: (ffffffff8c6b1b20) hash=2171763177 l4_hash=1 sw_hash=0

Fixes: b73c3d0e ("net: Save TX flow hash in sock and set in skbuf on xmit")
Fixes: 67800f9b ("ipv6: Call skb_get_hash_flowi6 to get skb->hash in ip6_make_flowlabel")
Signed-off-by: NPaolo Abeni <pabeni@redhat.com>
Reviewed-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      3dd1c9a1
  49. 07 7月, 2018 3 次提交
  51. 04 7月, 2018 1 次提交
  53. 20 6月, 2018 1 次提交
  55. 04 6月, 2018 1 次提交
  57. 18 5月, 2018 1 次提交
  59. 27 4月, 2018 3 次提交
    • W
      udp: paged allocation with gso · 15e36f5b
      由 Willem de Bruijn 提交于 
      When sending large datagrams that are later segmented, store data in
page frags to avoid copying from linear in skb_segment.
Signed-off-by: NWillem de Bruijn <willemb@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      15e36f5b
    • W
      udp: generate gso with UDP_SEGMENT · bec1f6f6
      由 Willem de Bruijn 提交于 
      Support generic segmentation offload for udp datagrams. Callers can
concatenate and send at once the payload of multiple datagrams with
the same destination.

To set segment size, the caller sets socket option UDP_SEGMENT to the
length of each discrete payload. This value must be smaller than or
equal to the relevant MTU.

A follow-up patch adds cmsg UDP_SEGMENT to specify segment size on a
per send call basis.

Total byte length may then exceed MTU. If not an exact multiple of
segment size, the last segment will be shorter.

The implementation adds a gso_size field to the udp socket, ip(v6)
cmsg cookie and inet_cork structure to be able to set the value at
setsockopt or cmsg time and to work with both lockless and corked
paths.

Initial benchmark numbers show UDP GSO about as expensive as TCP GSO.

    tcp tso
     3197 MB/s 54232 msg/s 54232 calls/s
         6,457,754,262      cycles

    tcp gso
     1765 MB/s 29939 msg/s 29939 calls/s
        11,203,021,806      cycles

    tcp without tso/gso *
      739 MB/s 12548 msg/s 12548 calls/s
        11,205,483,630      cycles

    udp
      876 MB/s 14873 msg/s 624666 calls/s
        11,205,777,429      cycles

    udp gso
     2139 MB/s 36282 msg/s 36282 calls/s
        11,204,374,561      cycles

   [*] after reverting commit 0a6b2a1d
       ("tcp: switch to GSO being always on")

Measured total system cycles ('-a') for one core while pinning both
the network receive path and benchmark process to that core:

  perf stat -a -C 12 -e cycles \
    ./udpgso_bench_tx -C 12 -4 -D "$DST" -l 4

Note the reduction in calls/s with GSO. Bytes per syscall drops
increases from 1470 to 61818.
Signed-off-by: NWillem de Bruijn <willemb@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      bec1f6f6
    • W
      udp: expose inet cork to udp · 1cd7884d
      由 Willem de Bruijn 提交于 
      UDP segmentation offload needs access to inet_cork in the udp layer.
Pass the struct to ip(6)_make_skb instead of allocating it on the
stack in that function itself.

This patch is a noop otherwise.
Signed-off-by: NWillem de Bruijn <willemb@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      1cd7884d
  61. 22 4月, 2018 2 次提交