Skip to content

cloud-kernel
cloud-kernel

openanolis / cloud-kernel
1 年多 前同步成功

通知 160
Star 36
Fork 7
cloud-kernel
cloud-kernel
切换分支/标签
  1. 18 12月, 2013 1 次提交
    • E
      tcp: refine TSO splits · d4589926
      由 Eric Dumazet 提交于 
      While investigating performance problems on small RPC workloads,
I noticed linux TCP stack was always splitting the last TSO skb
into two parts (skbs). One being a multiple of MSS, and a small one
with the Push flag. This split is done even if TCP_NODELAY is set,
or if no small packet is in flight.

Example with request/response of 4K/4K

IP A > B: . ack 68432 win 2783 <nop,nop,timestamp 6524593 6525001>
IP A > B: . 65537:68433(2896) ack 69632 win 2783 <nop,nop,timestamp 6524593 6525001>
IP A > B: P 68433:69633(1200) ack 69632 win 2783 <nop,nop,timestamp 6524593 6525001>
IP B > A: . ack 68433 win 2768 <nop,nop,timestamp 6525001 6524593>
IP B > A: . 69632:72528(2896) ack 69633 win 2768 <nop,nop,timestamp 6525001 6524593>
IP B > A: P 72528:73728(1200) ack 69633 win 2768 <nop,nop,timestamp 6525001 6524593>
IP A > B: . ack 72528 win 2783 <nop,nop,timestamp 6524593 6525001>
IP A > B: . 69633:72529(2896) ack 73728 win 2783 <nop,nop,timestamp 6524593 6525001>
IP A > B: P 72529:73729(1200) ack 73728 win 2783 <nop,nop,timestamp 6524593 6525001>

We can avoid this split by including the Nagle tests at the right place.

Note : If some NIC had trouble sending TSO packets with a partial
last segment, we would have hit the problem in GRO/forwarding workload already.

tcp_minshall_update() is moved to tcp_output.c and is updated as we might
feed a TSO packet with a partial last segment.

This patch tremendously improves performance, as the traffic now looks
like :

IP A > B: . ack 98304 win 2783 <nop,nop,timestamp 6834277 6834685>
IP A > B: P 94209:98305(4096) ack 98304 win 2783 <nop,nop,timestamp 6834277 6834685>
IP B > A: . ack 98305 win 2768 <nop,nop,timestamp 6834686 6834277>
IP B > A: P 98304:102400(4096) ack 98305 win 2768 <nop,nop,timestamp 6834686 6834277>
IP A > B: . ack 102400 win 2783 <nop,nop,timestamp 6834279 6834686>
IP A > B: P 98305:102401(4096) ack 102400 win 2783 <nop,nop,timestamp 6834279 6834686>
IP B > A: . ack 102401 win 2768 <nop,nop,timestamp 6834687 6834279>
IP B > A: P 102400:106496(4096) ack 102401 win 2768 <nop,nop,timestamp 6834687 6834279>
IP A > B: . ack 106496 win 2783 <nop,nop,timestamp 6834280 6834687>
IP A > B: P 102401:106497(4096) ack 106496 win 2783 <nop,nop,timestamp 6834280 6834687>
IP B > A: . ack 106497 win 2768 <nop,nop,timestamp 6834688 6834280>
IP B > A: P 106496:110592(4096) ack 106497 win 2768 <nop,nop,timestamp 6834688 6834280>

Before :

lpq83:~# nstat >/dev/null;perf stat ./super_netperf 200 -t TCP_RR -H lpq84 -l 20 -- -r 4K,4K
280774

 Performance counter stats for './super_netperf 200 -t TCP_RR -H lpq84 -l 20 -- -r 4K,4K':

     205719.049006 task-clock                #    9.278 CPUs utilized
         8,449,968 context-switches          #    0.041 M/sec
         1,935,997 CPU-migrations            #    0.009 M/sec
           160,541 page-faults               #    0.780 K/sec
   548,478,722,290 cycles                    #    2.666 GHz                     [83.20%]
   455,240,670,857 stalled-cycles-frontend   #   83.00% frontend cycles idle    [83.48%]
   272,881,454,275 stalled-cycles-backend    #   49.75% backend  cycles idle    [66.73%]
   166,091,460,030 instructions              #    0.30  insns per cycle
                                             #    2.74  stalled cycles per insn [83.39%]
    29,150,229,399 branches                  #  141.699 M/sec                   [83.30%]
     1,943,814,026 branch-misses             #    6.67% of all branches         [83.32%]

      22.173517844 seconds time elapsed

lpq83:~# nstat | egrep "IpOutRequests|IpExtOutOctets"
IpOutRequests                   16851063           0.0
IpExtOutOctets                  23878580777        0.0

After patch :

lpq83:~# nstat >/dev/null;perf stat ./super_netperf 200 -t TCP_RR -H lpq84 -l 20 -- -r 4K,4K
280877

 Performance counter stats for './super_netperf 200 -t TCP_RR -H lpq84 -l 20 -- -r 4K,4K':

     107496.071918 task-clock                #    4.847 CPUs utilized
         5,635,458 context-switches          #    0.052 M/sec
         1,374,707 CPU-migrations            #    0.013 M/sec
           160,920 page-faults               #    0.001 M/sec
   281,500,010,924 cycles                    #    2.619 GHz                     [83.28%]
   228,865,069,307 stalled-cycles-frontend   #   81.30% frontend cycles idle    [83.38%]
   142,462,742,658 stalled-cycles-backend    #   50.61% backend  cycles idle    [66.81%]
    95,227,712,566 instructions              #    0.34  insns per cycle
                                             #    2.40  stalled cycles per insn [83.43%]
    16,209,868,171 branches                  #  150.795 M/sec                   [83.20%]
       874,252,952 branch-misses             #    5.39% of all branches         [83.37%]

      22.175821286 seconds time elapsed

lpq83:~# nstat | egrep "IpOutRequests|IpExtOutOctets"
IpOutRequests                   11239428           0.0
IpExtOutOctets                  23595191035        0.0

Indeed, the occupancy of tx skbs (IpExtOutOctets/IpOutRequests) is higher :
2099 instead of 1417, thus helping GRO to be more efficient when using FQ packet
scheduler.

Many thanks to Neal for review and ideas.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Nandita Dukkipati <nanditad@google.com>
Cc: Van Jacobson <vanj@google.com>
Acked-by: NNeal Cardwell <ncardwell@google.com>
Tested-by: NNeal Cardwell <ncardwell@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      d4589926
  3. 14 12月, 2013 1 次提交
  5. 13 12月, 2013 1 次提交
    • J
      net-gro: Prepare GRO stack for the upcoming tunneling support · 299603e8
      由 Jerry Chu 提交于 
      This patch modifies the GRO stack to avoid the use of "network_header"
and associated macros like ip_hdr() and ipv6_hdr() in order to allow
an arbitary number of IP hdrs (v4 or v6) to be used in the
encapsulation chain. This lays the foundation for various IP
tunneling support (IP-in-IP, GRE, VXLAN, SIT,...) to be added later.

With this patch, the GRO stack traversing now is mostly based on
skb_gro_offset rather than special hdr offsets saved in skb (e.g.,
skb->network_header). As a result all but the top layer (i.e., the
the transport layer) must have hdrs of the same length in order for
a pkt to be considered for aggregation. Therefore when adding a new
encap layer (e.g., for tunneling), one must check and skip flows
(e.g., by setting NAPI_GRO_CB(p)->same_flow to 0) that have a
different hdr length.

Note that unlike the network header, the transport header can and
will continue to be set by the GRO code since there will be at
most one "transport layer" in the encap chain.
Signed-off-by: NH.K. Jerry Chu <hkchu@google.com>
Suggested-by: NEric Dumazet <edumazet@google.com>
Reviewed-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      299603e8
  7. 12 12月, 2013 1 次提交
  9. 11 12月, 2013 2 次提交
  11. 10 12月, 2013 3 次提交
  13. 07 12月, 2013 3 次提交
    • E
      tcp: auto corking · f54b3111
      由 Eric Dumazet 提交于 
      With the introduction of TCP Small Queues, TSO auto sizing, and TCP
pacing, we can implement Automatic Corking in the kernel, to help
applications doing small write()/sendmsg() to TCP sockets.

Idea is to change tcp_push() to check if the current skb payload is
under skb optimal size (a multiple of MSS bytes)

If under 'size_goal', and at least one packet is still in Qdisc or
NIC TX queues, set the TCP Small Queue Throttled bit, so that the push
will be delayed up to TX completion time.

This delay might allow the application to coalesce more bytes
in the skb in following write()/sendmsg()/sendfile() system calls.

The exact duration of the delay is depending on the dynamics
of the system, and might be zero if no packet for this flow
is actually held in Qdisc or NIC TX ring.

Using FQ/pacing is a way to increase the probability of
autocorking being triggered.

Add a new sysctl (/proc/sys/net/ipv4/tcp_autocorking) to control
this feature and default it to 1 (enabled)

Add a new SNMP counter : nstat -a | grep TcpExtTCPAutoCorking
This counter is incremented every time we detected skb was under used
and its flush was deferred.

Tested:

Interesting effects when using line buffered commands under ssh.

Excellent performance results in term of cpu usage and total throughput.

lpq83:~# echo 1 >/proc/sys/net/ipv4/tcp_autocorking
lpq83:~# perf stat ./super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128
9410.39

 Performance counter stats for './super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128':

      35209.439626 task-clock                #    2.901 CPUs utilized
             2,294 context-switches          #    0.065 K/sec
               101 CPU-migrations            #    0.003 K/sec
             4,079 page-faults               #    0.116 K/sec
    97,923,241,298 cycles                    #    2.781 GHz                     [83.31%]
    51,832,908,236 stalled-cycles-frontend   #   52.93% frontend cycles idle    [83.30%]
    25,697,986,603 stalled-cycles-backend    #   26.24% backend  cycles idle    [66.70%]
   102,225,978,536 instructions              #    1.04  insns per cycle
                                             #    0.51  stalled cycles per insn [83.38%]
    18,657,696,819 branches                  #  529.906 M/sec                   [83.29%]
        91,679,646 branch-misses             #    0.49% of all branches         [83.40%]

      12.136204899 seconds time elapsed

lpq83:~# echo 0 >/proc/sys/net/ipv4/tcp_autocorking
lpq83:~# perf stat ./super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128
6624.89

 Performance counter stats for './super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128':
      40045.864494 task-clock                #    3.301 CPUs utilized
               171 context-switches          #    0.004 K/sec
                53 CPU-migrations            #    0.001 K/sec
             4,080 page-faults               #    0.102 K/sec
   111,340,458,645 cycles                    #    2.780 GHz                     [83.34%]
    61,778,039,277 stalled-cycles-frontend   #   55.49% frontend cycles idle    [83.31%]
    29,295,522,759 stalled-cycles-backend    #   26.31% backend  cycles idle    [66.67%]
   108,654,349,355 instructions              #    0.98  insns per cycle
                                             #    0.57  stalled cycles per insn [83.34%]
    19,552,170,748 branches                  #  488.244 M/sec                   [83.34%]
       157,875,417 branch-misses             #    0.81% of all branches         [83.34%]

      12.130267788 seconds time elapsed
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      f54b3111
    • E
      tcp: optimize some skb_shinfo(skb) uses · 7b7fc97a
      由 Eric Dumazet 提交于 
      Compiler doesn't know skb_shinfo(skb) pointer is usually constant.

By using a temporary variable, we help generating smaller code.

For example, tcp_init_nondata_skb() is inlined after this patch.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      7b7fc97a
    • J
      ipv4/ipv6: Fix FSF address in file headers · a99421d9
      由 Jeff Kirsher 提交于 
      Several files refer to an old address for the Free Software Foundation
in the file header comment.  Resolve by replacing the address with
the URL <http://www.gnu.org/licenses/> so that we do not have to keep
updating the header comments anytime the address changes.

CC: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
CC: James Morris <jmorris@namei.org>
CC: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org>
CC: Patrick McHardy <kaber@trash.net>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      a99421d9
  15. 06 12月, 2013 1 次提交
    • E
      tcp_memcontrol: Cleanup/fix cg_proto->memory_pressure handling. · 7f2cbdc2
      由 Eric W. Biederman 提交于 
      kill memcg_tcp_enter_memory_pressure.  The only function of
memcg_tcp_enter_memory_pressure was to reduce deal with the
unnecessary abstraction that was tcp_memcontrol.  Now that struct
tcp_memcontrol is gone remove this unnecessary function, the
unnecessary function pointer, and modify sk_enter_memory_pressure to
set this field directly, just as sk_leave_memory_pressure cleas this
field directly.

This fixes a small bug I intruduced when killing struct tcp_memcontrol
that caused memcg_tcp_enter_memory_pressure to never be called and
thus failed to ever set cg_proto->memory_pressure.

Remove the cg_proto enter_memory_pressure function as it now serves
no useful purpose.

Don't test cg_proto->memory_presser in sk_leave_memory_pressure before
clearing it.  The test was originally there to ensure that the pointer
was non-NULL.  Now that cg_proto is not a pointer the pointer does not
matter.
Signed-off-by: N"Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      7f2cbdc2
  17. 30 11月, 2013 2 次提交
  19. 29 11月, 2013 1 次提交
  21. 24 11月, 2013 4 次提交
  23. 21 11月, 2013 1 次提交
    • A
      ipv4: fix race in concurrent ip_route_input_slow() · dcdfdf56
      由 Alexei Starovoitov 提交于 
      CPUs can ask for local route via ip_route_input_noref() concurrently.
if nh_rth_input is not cached yet, CPUs will proceed to allocate
equivalent DSTs on 'lo' and then will try to cache them in nh_rth_input
via rt_cache_route()
Most of the time they succeed, but on occasion the following two lines:
	orig = *p;
	prev = cmpxchg(p, orig, rt);
in rt_cache_route() do race and one of the cpus fails to complete cmpxchg.
But ip_route_input_slow() doesn't check the return code of rt_cache_route(),
so dst is leaking. dst_destroy() is never called and 'lo' device
refcnt doesn't go to zero, which can be seen in the logs as:
	unregister_netdevice: waiting for lo to become free. Usage count = 1
Adding mdelay() between above two lines makes it easily reproducible.
Fix it similar to nh_pcpu_rth_output case.

Fixes: d2d68ba9 ("ipv4: Cache input routes in fib_info nexthops.")
Signed-off-by: NAlexei Starovoitov <ast@plumgrid.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      dcdfdf56
  25. 20 11月, 2013 3 次提交
    • J
      genetlink: only pass array to genl_register_family_with_ops() · c53ed742
      由 Johannes Berg 提交于 
      As suggested by David Miller, make genl_register_family_with_ops()
a macro and pass only the array, evaluating ARRAY_SIZE() in the
macro, this is a little safer.

The openvswitch has some indirection, assing ops/n_ops directly in
that code. This might ultimately just assign the pointers in the
family initializations, saving the struct genl_family_and_ops and
code (once mcast groups are handled differently.)
Signed-off-by: NJohannes Berg <johannes.berg@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      c53ed742
    • A
      tcp: don't update snd_nxt, when a socket is switched from repair mode · dbde4979
      由 Andrey Vagin 提交于 
      snd_nxt must be updated synchronously with sk_send_head.  Otherwise
tp->packets_out may be updated incorrectly, what may bring a kernel panic.

Here is a kernel panic from my host.
[  103.043194] BUG: unable to handle kernel NULL pointer dereference at 0000000000000048
[  103.044025] IP: [<ffffffff815aaaaf>] tcp_rearm_rto+0xcf/0x150
...
[  146.301158] Call Trace:
[  146.301158]  [<ffffffff815ab7f0>] tcp_ack+0xcc0/0x12c0

Before this panic a tcp socket was restored. This socket had sent and
unsent data in the write queue. Sent data was restored in repair mode,
then the socket was switched from reapair mode and unsent data was
restored. After that the socket was switched back into repair mode.

In that moment we had a socket where write queue looks like this:
snd_una    snd_nxt   write_seq
   |_________|________|
             |
	  sk_send_head

After a second switching from repair mode the state of socket was
changed:

snd_una          snd_nxt, write_seq
   |_________ ________|
             |
	  sk_send_head

This state is inconsistent, because snd_nxt and sk_send_head are not
synchronized.

Bellow you can find a call trace, how packets_out can be incremented
twice for one skb, if snd_nxt and sk_send_head are not synchronized.
In this case packets_out will be always positive, even when
sk_write_queue is empty.

tcp_write_wakeup
	skb = tcp_send_head(sk);
	tcp_fragment
		if (!before(tp->snd_nxt, TCP_SKB_CB(buff)->end_seq))
			tcp_adjust_pcount(sk, skb, diff);
	tcp_event_new_data_sent
		tp->packets_out += tcp_skb_pcount(skb);

I think update of snd_nxt isn't required, when a socket is switched from
repair mode.  Because it's initialized in tcp_connect_init. Then when a
write queue is restored, snd_nxt is incremented in tcp_event_new_data_sent,
so it's always is in consistent state.

I have checked, that the bug is not reproduced with this patch and
all tests about restoring tcp connections work fine.

Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
Cc: James Morris <jmorris@namei.org>
Cc: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org>
Cc: Patrick McHardy <kaber@trash.net>
Signed-off-by: NAndrey Vagin <avagin@openvz.org>
Acked-by: NPavel Emelyanov <xemul@parallels.com>
Acked-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      dbde4979
    • F
      xfrm: Release dst if this dst is improper for vti tunnel · 236c9f84
      由 fan.du 提交于 
      After searching rt by the vti tunnel dst/src parameter,
if this rt has neither attached to any transformation
nor the transformation is not tunnel oriented, this rt
should be released back to ip layer.

otherwise causing dst memory leakage.
Signed-off-by: NFan Du <fan.du@windriver.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      236c9f84
  27. 19 11月, 2013 2 次提交
  29. 18 11月, 2013 1 次提交
  31. 15 11月, 2013 5 次提交
  33. 14 11月, 2013 1 次提交
    • A
      core/dev: do not ignore dmac in dev_forward_skb() · 81b9eab5
      由 Alexei Starovoitov 提交于 
      commit 06a23fe3
("core/dev: set pkt_type after eth_type_trans() in dev_forward_skb()")
and refactoring 64261f23
("dev: move skb_scrub_packet() after eth_type_trans()")

are forcing pkt_type to be PACKET_HOST when skb traverses veth.

which means that ip forwarding will kick in inside netns
even if skb->eth->h_dest != dev->dev_addr

Fix order of eth_type_trans() and skb_scrub_packet() in dev_forward_skb()
and in ip_tunnel_rcv()

Fixes: 06a23fe3 ("core/dev: set pkt_type after eth_type_trans() in dev_forward_skb()")
CC: Isaku Yamahata <yamahatanetdev@gmail.com>
CC: Maciej Zenczykowski <zenczykowski@gmail.com>
CC: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: NAlexei Starovoitov <ast@plumgrid.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      81b9eab5
  35. 08 11月, 2013 1 次提交
    • E
      inet: fix a UFO regression · dcd60771
      由 Eric Dumazet 提交于 
      While testing virtio_net and skb_segment() changes, Hannes reported
that UFO was sending wrong frames.

It appears this was introduced by a recent commit :
8c3a897b ("inet: restore gso for vxlan")

The old condition to perform IP frag was :

tunnel = !!skb->encapsulation;
...
        if (!tunnel && proto == IPPROTO_UDP) {

So the new one should be :

udpfrag = !skb->encapsulation && proto == IPPROTO_UDP;
...
        if (udpfrag) {

Initialization of udpfrag must be done before call
to ops->callbacks.gso_segment(skb, features), as
skb_udp_tunnel_segment() clears skb->encapsulation

(We want udpfrag to be true for UFO, false for VXLAN)

With help from Alexei Starovoitov
Reported-by: NHannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: NEric Dumazet <edumazet@google.com>
Cc: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      dcd60771
  37. 06 11月, 2013 2 次提交
    • J
      net: Explicitly initialize u64_stats_sync structures for lockdep · 827da44c
      由 John Stultz 提交于 
      In order to enable lockdep on seqcount/seqlock structures, we
must explicitly initialize any locks.

The u64_stats_sync structure, uses a seqcount, and thus we need
to introduce a u64_stats_init() function and use it to initialize
the structure.

This unfortunately adds a lot of fairly trivial initialization code
to a number of drivers. But the benefit of ensuring correctness makes
this worth while.

Because these changes are required for lockdep to be enabled, and the
changes are quite trivial, I've not yet split this patch out into 30-some
separate patches, as I figured it would be better to get the various
maintainers thoughts on how to best merge this change along with
the seqcount lockdep enablement.

Feedback would be appreciated!
Signed-off-by: NJohn Stultz <john.stultz@linaro.org>
Acked-by: NJulian Anastasov <ja@ssi.bg>
Signed-off-by: NPeter Zijlstra <peterz@infradead.org>
Cc: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org>
Cc: James Morris <jmorris@namei.org>
Cc: Jesse Gross <jesse@nicira.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Mirko Lindner <mlindner@marvell.com>
Cc: Patrick McHardy <kaber@trash.net>
Cc: Roger Luethi <rl@hellgate.ch>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Simon Horman <horms@verge.net.au>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Cc: Wensong Zhang <wensong@linux-vs.org>
Cc: netdev@vger.kernel.org
Link: http://lkml.kernel.org/r/1381186321-4906-2-git-send-email-john.stultz@linaro.orgSigned-off-by: NIngo Molnar <mingo@kernel.org>
      827da44c
    • H
      ipv4: introduce new IP_MTU_DISCOVER mode IP_PMTUDISC_INTERFACE · 482fc609
      由 Hannes Frederic Sowa 提交于 
      Sockets marked with IP_PMTUDISC_INTERFACE won't do path mtu discovery,
their sockets won't accept and install new path mtu information and they
will always use the interface mtu for outgoing packets. It is guaranteed
that the packet is not fragmented locally. But we won't set the DF-Flag
on the outgoing frames.

Florian Weimer had the idea to use this flag to ensure DNS servers are
never generating outgoing fragments. They may well be fragmented on the
path, but the server never stores or usees path mtu values, which could
well be forged in an attack.

(The root of the problem with path MTU discovery is that there is
no reliable way to authenticate ICMP Fragmentation Needed But DF Set
messages because they are sent from intermediate routers with their
source addresses, and the IMCP payload will not always contain sufficient
information to identify a flow.)

Recent research in the DNS community showed that it is possible to
implement an attack where DNS cache poisoning is feasible by spoofing
fragments. This work was done by Amir Herzberg and Haya Shulman:
<https://sites.google.com/site/hayashulman/files/fragmentation-poisoning.pdf>

This issue was previously discussed among the DNS community, e.g.
<http://www.ietf.org/mail-archive/web/dnsext/current/msg01204.html>,
without leading to fixes.

This patch depends on the patch "ipv4: fix DO and PROBE pmtu mode
regarding local fragmentation with UFO/CORK" for the enforcement of the
non-fragmentable checks. If other users than ip_append_page/data should
use this semantic too, we have to add a new flag to IPCB(skb)->flags to
suppress local fragmentation and check for this in ip_finish_output.

Many thanks to Florian Weimer for the idea and feedback while implementing
this patch.

Cc: David S. Miller <davem@davemloft.net>
Suggested-by: NFlorian Weimer <fweimer@redhat.com>
Signed-off-by: NHannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      482fc609
  39. 05 11月, 2013 2 次提交
    • Y
      tcp: properly handle stretch acks in slow start · 9f9843a7
      由 Yuchung Cheng 提交于 
      Slow start now increases cwnd by 1 if an ACK acknowledges some packets,
regardless the number of packets. Consequently slow start performance
is highly dependent on the degree of the stretch ACKs caused by
receiver or network ACK compression mechanisms (e.g., delayed-ACK,
GRO, etc).  But slow start algorithm is to send twice the amount of
packets of packets left so it should process a stretch ACK of degree
N as if N ACKs of degree 1, then exits when cwnd exceeds ssthresh. A
follow up patch will use the remainder of the N (if greater than 1)
to adjust cwnd in the congestion avoidance phase.

In addition this patch retires the experimental limited slow start
(LSS) feature. LSS has multiple drawbacks but questionable benefit. The
fractional cwnd increase in LSS requires a loop in slow start even
though it's rarely used. Configuring such an increase step via a global
sysctl on different BDPS seems hard. Finally and most importantly the
slow start overshoot concern is now better covered by the Hybrid slow
start (hystart) enabled by default.
Signed-off-by: NYuchung Cheng <ycheng@google.com>
Signed-off-by: NNeal Cardwell <ncardwell@google.com>
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      9f9843a7
    • Y
      tcp: enable sockets to use MSG_FASTOPEN by default · 0d41cca4
      由 Yuchung Cheng 提交于 
      Applications have started to use Fast Open (e.g., Chrome browser has
such an optional flag) and the feature has gone through several
generations of kernels since 3.7 with many real network tests. It's
time to enable this flag by default for applications to test more
conveniently and extensively.
Signed-off-by: NYuchung Cheng <ycheng@google.com>
Signed-off-by: NNeal Cardwell <ncardwell@google.com>
Acked-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      0d41cca4
  41. 04 11月, 2013 1 次提交
  43. 01 11月, 2013 1 次提交