FRTO controls cwnd when it still processes the ACK input or it
has just reverted back to conventional RTO recovery; the normal
rules apply when FRTO has reverted to standard congestion
control.
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
Because TCP is not in Loss state during FRTO recovery, fast
recovery could be triggered by accident. Non-SACK FRTO is more
robust than not yet included SACK-enhanced version (that can
receiver high number of duplicate ACKs with SACK blocks during
FRTO), at least with unidirectional transfers, but under
extraordinary patterns fast recovery can be incorrectly
triggered, e.g., Data loss+ACK losses => cumulative ACK with
enough SACK blocks to meet sacked_out >= dupthresh condition).
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
Since purpose is to reduce CWND, we prevent immediate growth. This
is not a major issue nor is "the correct way" specified anywhere.
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
The FRTO detection did not care how ACK pattern affects to cwnd
calculation of the conventional recovery. This caused incorrect
setting of cwnd when the fallback becames necessary. The
knowledge tcp_process_frto() has about the incoming ACK is now
passed on to tcp_enter_frto_loss() in allowed_segments parameter
that gives the number of segments that must be added to
packets-in-flight while calculating the new cwnd.
Instead of snd_una we use FLAG_DATA_ACKED in duplicate ACK
detection because RFC4138 states (in Section 2.2):
If the first acknowledgment after the RTO retransmission
does not acknowledge all of the data that was retransmitted
in step 1, the TCP sender reverts to the conventional RTO
recovery. Otherwise, a malicious receiver acknowledging
partial segments could cause the sender to declare the
timeout spurious in a case where data was lost.
If the next ACK after RTO is duplicate, we do not retransmit
anything, which is equal to what conservative conventional
recovery does in such case.
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
Handles RFC4138 shortcoming (in step 2); it should also have case
c) which ignores ACKs that are not duplicates nor advance window
(opposite dir data, winupdate).
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
Retransmission counter assumptions are to be changed. Forcing
reason to do this exist: Using sysctl in check would be racy
as soon as FRTO starts to ignore some ACKs (doing that in the
following patches). Userspace may disable it at any moment
giving nice oops if timing is right. frto_counter would be
inaccessible from userspace, but with SACK enhanced FRTO
retrans_out can include other than head, and possibly leaving
it non-zero after spurious RTO, boom again.
Luckily, solution seems rather simple: never go directly to Open
state but use Disorder instead. This does not really change much,
since TCP could anyway change its state to Disorder during FRTO
using path tcp_fastretrans_alert -> tcp_try_to_open (e.g., when
a SACK block makes ACK dubious). Besides, Disorder seems to be
the state where TCP should be if not recovering (in Recovery or
Loss state) while having some retransmissions in-flight (see
tcp_try_to_open), which is exactly what happens with FRTO.
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
In case a latency spike causes more than one RTO, the later should not
cause the already reduced ssthresh to propagate into the prior_ssthresh
since FRTO declares all such RTOs spurious at once or none of them. In
treating of ssthresh, we mimic what tcp_enter_loss() does.
The previous state (in frto_counter) must be available until we have
checked it in tcp_enter_frto(), and also ACK information flag in
process_frto().
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
Moved comments out from the body of process_frto() to the head
(preferred way; see Documentation/CodingStyle). Bonus: it's much
easier to read in this compacted form.
FRTO algorithm and implementation is described in greater detail.
For interested reader, more information is available in RFC4138.
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
FRTO spurious RTO detection algorithm (RFC4138) does not include response
to a detected spurious RTO but can use different response algorithms.
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
FRTO was slightly too brave... Should only clear
TCPCB_SACKED_RETRANS bit.
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
Reply to NETLINK_FIB_LOOKUP messages were misrouted back to kernel,
which resulted in infinite recursion and stack overflow.
The bug is present in all kernel versions since the feature appeared.
The patch also makes some minimal cleanup:
1. Return something consistent (-ENOENT) when fib table is missing
2. Do not crash when queue is empty (does not happen, but yet)
3. Put result of lookup
Signed-off-by: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
Oops, thinko. The test for accempting a RH0 was exatly the wrong way
around.
Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
A security issue is emerging. Disallow Routing Header Type 0 by default
as we have been doing for IPv4.
Note: We allow RH2 by default because it is harmless.
Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
draft-nikander-esp-beet-mode-07.txt is not entirely clear on how the length
value of the pseudo header should be calculated, it states "The Header Length
field contains the length of the pseudo header, IPv4 options, and padding in
8 octets units.", but also states "Length in octets (Header Len + 1) * 8".
draft-nikander-esp-beet-mode-08-pre1.txt [1] clarifies this, the header length
should not include the first 8 byte.
This change affects backwards compatibility, but option encapsulation didn't
work until very recently anyway.
[1] http://users.piuha.net/jmelen/BEET/draft-nikander-esp-beet-mode-08-pre1.txt
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Change to defer congestion control initialization.
If setsockopt() was used to change TCP_CONGESTION before
connection is established, then protocols that use sequence numbers
to keep track of one RTT interval (vegas, illinois, ...) get confused.
Change the init hook to be called after handshake.
Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Fix a regression due to the patch "NFS: disconnect before retrying NFSv4
requests over TCP"
The assumption made in xprt_transmit() that the condition
"req->rq_bytes_sent == 0 and request is on the receive list"
should imply that we're dealing with a retransmission is false.
Firstly, it may simply happen that the socket send queue was full
at the time the request was initially sent through xprt_transmit().
Secondly, doing this for each request that was retransmitted implies
that we disconnect and reconnect for _every_ request that happened to
be retransmitted irrespective of whether or not a disconnection has
already occurred.
Fix is to move this logic into the call_status request timeout handler.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
There is a race between netlink_dump_start() and netlink_release()
that can lead to the situation when a netlink socket with non-zero
callback is freed.
Here it is:
CPU1: CPU2
netlink_release(): netlink_dump_start():
sk = netlink_lookup(); /* OK */
netlink_remove();
spin_lock(&nlk->cb_lock);
if (nlk->cb) { /* false */
...
}
spin_unlock(&nlk->cb_lock);
spin_lock(&nlk->cb_lock);
if (nlk->cb) { /* false */
...
}
nlk->cb = cb;
spin_unlock(&nlk->cb_lock);
...
sock_orphan(sk);
/*
* proceed with releasing
* the socket
*/
The proposal it to make sock_orphan before detaching the callback
in netlink_release() and to check for the sock to be SOCK_DEAD in
netlink_dump_start() before setting a new callback.
Signed-off-by: Denis Lunev <den@openvz.org>
Signed-off-by: Kirill Korotaev <dev@openvz.org>
Signed-off-by: Pavel Emelianov <xemul@openvz.org>
Acked-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch fixes an oops first reported in mid 2006 - see
http://lkml.org/lkml/2006/8/29/358 The cause of this bug report is that
when an error is signalled on the socket, irda_recvmsg_stream returns
without removing a local wait_queue variable from the socket's sk_sleep
queue. This causes havoc further down the road.
In response to this problem, a patch was made that invoked sock_orphan on
the socket when receiving a disconnect indication. This is not a good fix,
as this sets sk_sleep to NULL, causing applications sleeping in recvmsg
(and other places) to oops.
This is against the latest net-2.6 and should be considered for -stable
inclusion.
Signed-off-by: Olaf Kirch <olaf.kirch@oracle.com>
Signed-off-by: Samuel Ortiz <samuel@sortiz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
The way partial delivery is currently implemnted, it is possible to
intereleave a message (either from another steram, or unordered) that
is not part of partial delivery process. The only way to this is for
a message to not be a fragment and be 'in order' or unorderd for a
given stream. This will result in bypassing the reassembly/ordering
queues where things live duing partial delivery, and the
message will be delivered to the socket in the middle of partial delivery.
This is a two-fold problem, in that:
1. the app now must check the stream-id and flags which it may not
be doing.
2. this clearing partial delivery state from the association and results
in ulp hanging.
This patch is a band-aid over a much bigger problem in that we
don't do stream interleave.
Signed-off-by: Vlad Yasevich <vladislav.yasevich@hp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Make sure to actually assign the determined mode to
rq->sadb_x_ipsecrequest_mode.
Noticed by Joe Perches.
Signed-off-by: David S. Miller <davem@davemloft.net>
* master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6:
[BRIDGE]: Unaligned access when comparing ethernet addresses
[SCTP]: Unmap v4mapped addresses during SCTP_BINDX_REM_ADDR operation.
[SCTP]: Fix assertion (!atomic_read(&sk->sk_rmem_alloc)) failed message
[NET]: Set a separate lockdep class for neighbour table's proxy_queue
[NET]: Fix UDP checksum issue in net poll mode.
[KEY]: Fix conversion between IPSEC_MODE_xxx and XFRM_MODE_xxx.
[NET]: Get rid of alloc_skb_from_cache
sk_info_authunix is not being protected properly so the object that it
points to can be cache_put twice, leading to corruption.
We borrow svsk->sk_defer_lock to provide the protection. We should
probably rename that lock to have a more generic name - later.
Thanks to Gabriel for reporting this.
Cc: Greg Banks <gnb@melbourne.sgi.com>
Cc: Gabriel Barazer <gabriel@oxeva.fr>
Signed-off-by: Neil Brown <neilb@suse.de>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
compare_ether_addr() implicitly requires that the addresses
passed are 2-bytes aligned in memory.
This is not true for br_stp_change_bridge_id() and
br_stp_recalculate_bridge_id() in which one of the addresses
is unsigned char *, and thus may not be 2-bytes aligned.
Signed-off-by: Evgeny Kravtsunov <emkravts@openvz.org>
Signed-off-by: Kirill Korotaev <dev@openvz.org>
Signed-off-by: Pavel Emelianov <xemul@openvz.org>
During the sctp_bindx() call to add additional addresses to the
endpoint, any v4mapped addresses are converted and stored as regular
v4 addresses. However, when trying to remove these addresses, the
v4mapped addresses are not converted and the operation fails. This
patch unmaps the addresses on during the remove operation as well.
Signed-off-by: Paolo Galtieri <pgaltieri@mvista.com>
Signed-off-by: Vlad Yasevich <vladislav.yasevich@hp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In current implementation, LKSCTP does receive buffer accounting for
data in sctp_receive_queue and pd_lobby. However, LKSCTP don't do
accounting for data in frag_list when data is fragmented. In addition,
LKSCTP doesn't do accounting for data in reasm and lobby queue in
structure sctp_ulpq.
When there are date in these queue, assertion failed message is printed
in inet_sock_destruct because sk_rmem_alloc of oldsk does not become 0
when socket is destroyed.
Signed-off-by: Tsutomu Fujii <t-fujii@nb.jp.nec.com>
Signed-off-by: Vlad Yasevich <vladislav.yasevich@hp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Otherwise the following calltrace will lead to a wrong
lockdep warning:
neigh_proxy_process()
`- lock(neigh_table->proxy_queue.lock);
arp_redo /* via tbl->proxy_redo */
arp_process
neigh_event_ns
neigh_update
skb_queue_purge
`- lock(neighbor->arp_queue.lock);
This is not a deadlock actually, as neighbor table's proxy_queue
and the neighbor's arp_queue are different queues.
Lockdep thinks there is a deadlock as both queues are initialized
with skb_queue_head_init() and thus have a common class.
Signed-off-by: David S. Miller <davem@davemloft.net>
In net poll mode, the current checksum function doesn't consider the
kind of packet which is padded to reach a specific minimum length. I
believe that's the problem causing my test case failed. The following
patch fixed this issue.
Signed-off-by: Aubrey.Li <aubreylee@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We should not blindly convert between IPSEC_MODE_xxx and XFRM_MODE_xxx just
by incrementing / decrementing because the assumption is not true any longer.
Signed-off-by: Kazunori MIYAZAWA <miyazawa@linux-ipv6.org>
Singed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
Since this was added originally for Xen, and Xen has recently (~2.6.18)
stopped using this function, we can safely get rid of it. Good timing
too since this function has started to bit rot.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
There are two device string comparison loops in arp_packet_match().
The first one goes byte-by-byte but the second one tries to be
clever and cast the string to a long and compare by longs.
The device name strings in the arp table entries are not guarenteed
to be aligned enough to make this value, so just use byte-by-byte
for both cases.
Based upon a report by <drraid@gmail.com>.
Signed-off-by: David S. Miller <davem@davemloft.net>
A packet which is being discarded because of no routes in the
forwarding path should not be counted as OutNoRoutes but as
InNoRoutes.
Additionally, on this occasion, a packet whose destinaion is
not valid should be counted as InAddrErrors separately.
Based on patch from Mitsuru Chinen <mitch@linux.vnet.ibm.com>.
Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
When sending a security context of 50+ characters in an ACQUIRE
message, following kernel panic occurred.
kernel BUG in xfrm_send_acquire at net/xfrm/xfrm_user.c:1781!
cpu 0x3: Vector: 700 (Program Check) at [c0000000421bb2e0]
pc: c00000000033b074: .xfrm_send_acquire+0x240/0x2c8
lr: c00000000033b014: .xfrm_send_acquire+0x1e0/0x2c8
sp: c0000000421bb560
msr: 8000000000029032
current = 0xc00000000fce8f00
paca = 0xc000000000464b00
pid = 2303, comm = ping
kernel BUG in xfrm_send_acquire at net/xfrm/xfrm_user.c:1781!
enter ? for help
3:mon> t
[c0000000421bb650] c00000000033538c .km_query+0x6c/0xec
[c0000000421bb6f0] c000000000337374 .xfrm_state_find+0x7f4/0xb88
[c0000000421bb7f0] c000000000332350 .xfrm_tmpl_resolve+0xc4/0x21c
[c0000000421bb8d0] c0000000003326e8 .xfrm_lookup+0x1a0/0x5b0
[c0000000421bba00] c0000000002e6ea0 .ip_route_output_flow+0x88/0xb4
[c0000000421bbaa0] c0000000003106d8 .ip4_datagram_connect+0x218/0x374
[c0000000421bbbd0] c00000000031bc00 .inet_dgram_connect+0xac/0xd4
[c0000000421bbc60] c0000000002b11ac .sys_connect+0xd8/0x120
[c0000000421bbd90] c0000000002d38d0 .compat_sys_socketcall+0xdc/0x214
[c0000000421bbe30] c00000000000869c syscall_exit+0x0/0x40
--- Exception: c00 (System Call) at 0000000007f0ca9c
SP (fc0ef8f0) is in userspace
We are using size of security context from xfrm_policy to determine
how much space to alloc skb and then putting security context from
xfrm_state into skb. Should have been using size of security context
from xfrm_state to alloc skb. Following fix does that
Signed-off-by: Joy Latten <latten@austin.ibm.com>
Acked-by: James Morris <jmorris@namei.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
When a VLAN interface is created on top of a bridge interface and
netfilter is enabled to see the bridged packets, the packets can be
corrupted when passing through the netfilter code. This is caused by the
VLAN driver not setting the 'protocol' and 'nh' members of the sk_buff
structure. In general, this is no problem as the VLAN interface is mostly
connected to a physical ethernet interface which does not use the
'protocol' and 'nh' members. For a bridge interface, however, these
members do matter.
Signed-off-by: Jerome Borsboom <j.borsboom@erasmusmc.nl>
Signed-off-by: David S. Miller <davem@davemloft.net>
The pktgen module prevents suspend-to-disk. Fix.
Acked-by: "Michal Piotrowski" <michal.k.k.piotrowski@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use put_unaligned to fix warnings about unaligned accesses.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
The clusterip_config_find_get() already increases entries reference
counter, so there is no reason to do it twice in checkentry() callback.
This causes the config to be freed before it is removed from the list,
resulting in a crash when adding the next rule.
Signed-off-by: Jaroslav Kysela <perex@suse.cz>
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
For the cases that slow_start_after_idle are meant to deal
with, it is almost a certainty that the congestion window
tests will think the connection is application limited and
we'll thus decrease the cwnd there too. This defeats the
whole point of setting slow_start_after_idle to zero.
So test it there too.
We do not cancel out the entire tcp_cwnd_validate() function
so that if the sysctl is changed we still have the validation
state maintained.
Signed-off-by: David S. Miller <davem@davemloft.net>
Userspace uses an integer for TCA_TCINDEX_SHIFT, the kernel was changed
to expect and use a u16 value in 2.6.11, which broke compatibility on
big endian machines. Change back to use int.
Reported by Ole Reinartz <ole.reinartz@gmx.de>
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Beet mode looks for the beet pseudo header after the outer IP header,
which is wrong since that is followed by the ESP header. Additionally
it needs to adjust the packet length after removing the pseudo header
and point the data pointer to the real data location.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Beet mode decapsulation fails to properly set up the skb pointers, which
only works by accident in combination with CONFIG_NETFILTER, since in that
case the skb is fixed up in xfrm4_input before passing it to the netfilter
hooks.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
draft-nikander-esp-beet-mode-07.txt states "The padding MUST be filled
with NOP options as defined in Internet Protocol [1] section 3.1
Internet header format.", so do that.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Beet mode calculates an incorrect value for the transport header location
when IP options are present, resulting in encapsulation errors.
The correct location is 4 or 8 bytes before the end of the original IP
header, depending on whether the pseudo header is padded.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Up until this point we've accepted replay window settings greater than
32 but our bit mask can only accomodate 32 packets. Thus any packet
with a sequence number within the window but outside the bit mask would
be accepted.
This patch causes those packets to be rejected instead.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
Incoming trancated packets are counted as not only InTruncatedPkts but
also InHdrErrors. They should be counted as InTruncatedPkts only.
Signed-off-by: Mitsuru Chinen <mitch@linux.vnet.ibm.com>
Acked-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
When we receive an AppleTalk frame shorter than what its header says,
we still attempt to verify its checksum, and trip on the BUG_ON() at
the end of function atalk_sum_skb() because of the length mismatch.
This has security implications because this can be triggered by simply
sending a specially crafted ethernet frame to a target victim,
effectively crashing that host. Thus this qualifies, I think, as a
remote DoS. Here is the frame I used to trigger the crash, in npg
format:
<Appletalk Killer>
{
# Ethernet header -----
XX XX XX XX XX XX # Destination MAC
00 00 00 00 00 00 # Source MAC
00 1D # Length
# LLC header -----
AA AA 03
08 00 07 80 9B # Appletalk
# Appletalk header -----
00 1B # Packet length (invalid)
00 01 # Fake checksum
00 00 00 00 # Destination and source networks
00 00 00 00 # Destination and source nodes and ports
# Payload -----
0C 0D 0E 0F 10 11 12 13
14
}
The destination MAC address must be set to those of the victim.
The severity is mitigated by two requirements:
* The target host must have the appletalk kernel module loaded. I
suspect this isn't so frequent.
* AppleTalk frames are non-IP, thus I guess they can only travel on
local networks. I am no network expert though, maybe it is possible
to somehow encapsulate AppleTalk packets over IP.
The bug has been reported back in June 2004:
http://bugzilla.kernel.org/show_bug.cgi?id=2979
But it wasn't investigated, and was closed in July 2006 as both
reporters had vanished meanwhile.
This code was new in kernel 2.6.0-test5:
http://git.kernel.org/?p=linux/kernel/git/tglx/history.git;a=commitdiff;h=7ab442d7e0a76402c12553ee256f756097cae2d2
And not modified since then, so we can assume that vanilla kernels
2.6.0-test5 and later, and distribution kernels based thereon, are
affected.
Note that I still do not know for sure what triggered the bug in the
real-world cases. The frame could have been corrupted by the kernel if
we have a bug hiding somewhere. But more likely, we are receiving the
faulty frame from the network.
Signed-off-by: Jean Delvare <jdelvare@suse.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
