This small change allows for easy per-route workarounds for broken hosts or
middleboxes that are not compliant with TCP standards for window scaling.
Rather than having to turn off window scaling globally. This patch allows
reducing or disabling window scaling if window clamp is present.
Example: Mark Lord reported a problem with 2.6.17 kernel being unable to
access http://www.everymac.com
# ip route add 216.145.246.23/32 via 10.8.0.1 window 65535
Signed-off-by: Stephen Hemminger <shemminger@osdl.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
table->private might change because of ruleset changes, don't use it
without holding the lock.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
table->private might change because of ruleset changes, don't use it without
holding the lock.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
ip_conntrack_put must not be called while holding ip_conntrack_lock
since destroy_conntrack takes it again.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Found in 2.4 by Yixin Pan <yxpan@hotmail.com>.
> When I read fib_semantics.c of Linux-2.4.32, write_lock(&fib_info_lock) =
> is used in fib_release_info() instead of write_lock_bh(&fib_info_lock). =
> Is the following case possible: a BH interrupts fib_release_info() while =
> holding the write lock, and calls ip_check_fib_default() which calls =
> read_lock(&fib_info_lock), and spin forever.
Signed-off-by: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
This fixes source filter leakage when a device is removed and a
process leaves the group thereafter.
This also includes corresponding fixes for IPv6 multicast source
filters on device removal.
Signed-off-by: David L Stevens <dlstevens@us.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
There is a leak of a socket's multicast source filter list structure
on closing a socket with a multicast source filter set on an interface
that does not exist any more.
Signed-off-by: Michal Ruzicka <michal.ruzicka@comstar.cz>
Acked-by: David L Stevens <dlstevens@us.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The IPv4/IPv6 datagram output path was using skb_trim to trim paged
packets because they know that the packet has not been cloned yet
(since the packet hasn't been given to anything else in the system).
This broke because skb_trim no longer allows paged packets to be
trimmed. Paged packets must be given to one of the pskb_trim functions
instead.
This patch adds a new pskb_trim_unique function to cover the IPv4/IPv6
datagram output path scenario and replaces the corresponding skb_trim
calls with it.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
Fix kernel panic on various SMP machines. The culprit is a null
ub->skb in ulog_send(). If ulog_timer() has already been scheduled on
one CPU and is spinning on the lock, and ipt_ulog_packet() flushes the
queue on another CPU by calling ulog_send() right before it exits,
there will be no skbuff when ulog_timer() acquires the lock and calls
ulog_send(). Cancelling the timer in ulog_send() doesn't help because
it has already been scheduled and is running on the first CPU.
Similar problem exists in ebt_ulog.c and nfnetlink_log.c.
Signed-off-by: Mark Huang <mlhuang@cs.princeton.edu>
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Neither of {arp,ip,ip6}_tables cleans up behind itself when something goes
wrong during initialization.
Noticed by Rennie deGraaf <degraaf@cpsc.ucalgary.ca>
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Hashlimit doesn't account for the first packet, which is inconsistent
with the limit match.
Reported by ryan.castellucci@gmail.com, netfilter bugzilla #500.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Somehow I clobbered James's original fix and only my
subsequent compiler warning change went in for that
changeset.
Get the real fix in there.
Noticed by Jesper Juhl.
Signed-off-by: David S. Miller <davem@davemloft.net>
From: Kirill Korotaev <dev@sw.ru>
During OpenVZ stress testing we found that UDP traffic with random src
can generate too much excessive rt hash growing leading finally to OOM
and kernel panics.
It was found that for 4GB i686 system (having 1048576 total pages and
225280 normal zone pages) kernel allocates the following route hash:
syslog: IP route cache hash table entries: 262144 (order: 8, 1048576
bytes) => ip_rt_max_size = 4194304 entries, i.e. max rt size is
4194304 * 256b = 1Gb of RAM > normal_zone
Attached the patch which removes HASH_HIGHMEM flag from
alloc_large_system_hash() call.
Signed-off-by: David S. Miller <davem@davemloft.net>
Whenever a transfer is application limited, we are allowed at least
initial window worth of data per window unless cwnd is previously
less than that.
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
From: Catherine Zhang <cxzhang@watson.ibm.com>
This patch implements a cleaner fix for the memory leak problem of the
original unix datagram getpeersec patch. Instead of creating a
security context each time a unix datagram is sent, we only create the
security context when the receiver requests it.
This new design requires modification of the current
unix_getsecpeer_dgram LSM hook and addition of two new hooks, namely,
secid_to_secctx and release_secctx. The former retrieves the security
context and the latter releases it. A hook is required for releasing
the security context because it is up to the security module to decide
how that's done. In the case of Selinux, it's a simple kfree
operation.
Acked-by: Stephen Smalley <sds@tycho.nsa.gov>
Signed-off-by: David S. Miller <davem@davemloft.net>
When I tested linux kernel 2.6.71.7 about statistics
"ipv6IfStatsOutFragCreates", and found that it couldn't increase
correctly. The criteria is RFC 2465:
ipv6IfStatsOutFragCreates OBJECT-TYPE
SYNTAX Counter32
MAX-ACCESS read-only
STATUS current
DESCRIPTION
"The number of output datagram fragments that have
been generated as a result of fragmentation at
this output interface."
::= { ipv6IfStatsEntry 15 }
I think there are two issues in Linux kernel.
1st:
RFC2465 specifies the counter is "The number of output datagram
fragments...". I think increasing this counter after output a fragment
successfully is better. And it should not be increased even though a
fragment is created but failed to output.
2nd:
If we send a big ICMP/ICMPv6 echo request to a host, and receive
ICMP/ICMPv6 echo reply consisted of some fragments. As we know that in
Linux kernel first fragmentation occurs in ICMP layer(maybe saying
transport layer is better), but this is not the "real"
fragmentation,just do some "pre-fragment" -- allocate space for date,
and form a frag_list, etc. The "real" fragmentation happens in IP layer
-- set offset and MF flag and so on. So I think in "fast path" for
ip_fragment/ip6_fragment, if we send a fragment which "pre-fragment" by
upper layer we should also increase "ipv6IfStatsOutFragCreates".
Signed-off-by: Wei Dong <weid@nanjing-fnst.com>
Acked-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
The hashlimit table name and the textsearch algorithm need to be
terminated, the textsearch pattern length must not exceed the
maximum size.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Since we don't know in which direction the first packet will arrive, we
need to create one expectation for each direction, which is currently
prevented by max_expected beeing set to 1.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Based upon guidance from Alexey Kuznetsov.
When linger2 is active, we check to see if the fin_wait2
timeout is longer than the timewait. If it is, we schedule
the keepalive timer for the difference between the timewait
timeout and the fin_wait2 timeout.
When this orphan socket is seen by tcp_keepalive_timer()
it will try to transform this fin_wait2 socket into a
fin_wait2 mini-socket, again if linger2 is active.
Not all paths were setting this initial keepalive timer correctly.
The tcp input path was doing it correctly, but tcp_close() wasn't,
potentially making the socket linger longer than it really needs to.
Signed-off-by: David S. Miller <davem@davemloft.net>
Generate netevents for:
- neighbour changes
- routing redirects
- pmtu changes
Signed-off-by: Tom Tucker <tom@opengridcomputing.com>
Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Refer to RFC2012, tcpAttemptFails is defined as following:
tcpAttemptFails OBJECT-TYPE
SYNTAX Counter32
MAX-ACCESS read-only
STATUS current
DESCRIPTION
"The number of times TCP connections have made a direct
transition to the CLOSED state from either the SYN-SENT
state or the SYN-RCVD state, plus the number of times TCP
connections have made a direct transition to the LISTEN
state from the SYN-RCVD state."
::= { tcp 7 }
When I lookup into RFC793, I found that the state change should occured
under following condition:
1. SYN-SENT -> CLOSED
a) Received ACK,RST segment when SYN-SENT state.
2. SYN-RCVD -> CLOSED
b) Received SYN segment when SYN-RCVD state(came from LISTEN).
c) Received RST segment when SYN-RCVD state(came from SYN-SENT).
d) Received SYN segment when SYN-RCVD state(came from SYN-SENT).
3. SYN-RCVD -> LISTEN
e) Received RST segment when SYN-RCVD state(came from LISTEN).
In my test, those direct state transition can not be counted to
tcpAttemptFails.
Signed-off-by: Wei Yongjun <yjwei@nanjing-fnst.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Based upon a patch by Jesper Juhl.
Signed-off-by: James Morris <jmorris@namei.org>
Acked-by: Stephen Hemminger <shemminger@osdl.org>
Acked-by: Jesper Juhl <jesper.juhl@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
From: Tetsuo Handa from-linux-kernel@i-love.sakura.ne.jp
The recvmsg() for raw socket seems to return random u16 value
from the kernel stack memory since port field is not initialized.
But I'm not sure this patch is correct.
Does raw socket return any information stored in port field?
[ BSD defines RAW IP recvmsg to return a sin_port value of zero.
This is described in Steven's TCP/IP Illustrated Volume 2 on
page 1055, which is discussing the BSD rip_input() implementation. ]
Acked-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
IP multicast route code was reusing an skb which causes use after free
and double free.
From: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
Note, it is real skb_clone(), not alloc_skb(). Equeued skb contains
the whole half-prepared netlink message plus room for the rest.
It could be also skb_copy(), if we want to be puristic about mangling
cloned data, but original copy is really not going to be used.
Acked-by: Stephen Hemminger <shemminger@osdl.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
An RCF message containing a timeout results in a NULL-ptr dereference if
no RRQ has been seen before.
Noticed by the "SATURN tool", reported by Thomas Dillig <tdillig@stanford.edu>
and Isil Dillig <isil@stanford.edu>.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Routing realms exist per nexthop, but are only returned to userspace
for the first nexthop. This is due to the fact that iproute2 only
allows to set the realm for the first nexthop and the kernel refuses
multipath routes where only a single realm is present.
Dump all realms for multipath routes to enable iproute to correctly
display them.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Now that we always zero the IPCB->opts in ip_rcv, it is no longer
necessary to do so before calling netif_rx for tunneled packets.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
when data arrives at IP through loopback (and possibly other devices).
So the field needs to be cleared before it confuses the route code.
This was seen when running netem over loopback, but there are probably
other device cases. Maybe this should go into stable?
Signed-off-by: Stephen Hemminger <shemminger@osdl.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
The error handling around fib_insert_node was broken because we always
zeroed the error before checking it.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
The truesize check has uncovered the fact that we forgot to update truesize
after pskb_expand_head. Unfortunately pskb_expand_head can't update it for
us because it's used in all sorts of different contexts, some of which would
not allow truesize to be updated by itself.
So the solution for now is to simply update it in IPComp.
This patch also changes skb_put to __skb_put since we've just expanded
tailroom by exactly that amount so we know it's there (but gcc does not).
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
I think there is still a problem with the AIMD parameter update in
HighSpeed TCP code.
Line 125~138 of the code (net/ipv4/tcp_highspeed.c):
/* Update AIMD parameters */
if (tp->snd_cwnd > hstcp_aimd_vals[ca->ai].cwnd) {
while (tp->snd_cwnd > hstcp_aimd_vals[ca->ai].cwnd &&
ca->ai < HSTCP_AIMD_MAX - 1)
ca->ai++;
} else if (tp->snd_cwnd < hstcp_aimd_vals[ca->ai].cwnd) {
while (tp->snd_cwnd > hstcp_aimd_vals[ca->ai].cwnd &&
ca->ai > 0)
ca->ai--;
In fact, the second part (decreasing ca->ai) never decreases since the
while loop's inequality is in the reverse direction. This leads to
unfairness with multiple flows (once a flow happens to enjoy a higher
ca->ai, it keeps enjoying that even its cwnd decreases)
Here is a tentative fix (I also added a comment, trying to keep the
change clear):
Acked-by: Stephen Hemminger <shemminger@osdl.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
This reverts: f890f92104
The inclusion of TCP Compound needs to be reverted at this time
because it is not 100% certain that this code conforms to the
requirements of Developer's Certificate of Origin 1.1 paragraph (b).
Signed-off-by: David S. Miller <davem@davemloft.net>
The variable peer_total is protected by a lock. The volatile marker
makes no sense. This shaves off 20 bytes on i386.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
When more rules are present than fit in a single skb, the remaining
rules are incorrectly skipped.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Certain subsystems in the stack (e.g., netfilter) can break the partial
checksum on GSO packets. Until they're fixed, this patch allows this to
work by recomputing the partial checksums through the GSO mechanism.
Once they've all been converted to update the partial checksum instead of
clearing it, this workaround can be removed.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds the wrapper function skb_is_gso which can be used instead
of directly testing skb_shinfo(skb)->gso_size. This makes things a little
nicer and allows us to change the primary key for indicating whether an skb
is GSO (if we ever want to do that).
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
We don't want nasty Xen guests to pass a TCPv6 packet in with gso_type set
to TCPv4 or even UDP (or a packet that's both TCP and UDP).
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
Teach special (recursive) locking code to the lock validator. Has no effect
on non-lockdep kernels.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: "David S. Miller" <davem@davemloft.net>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
On lockdep we have a quite big spinlock_t, so keep the size down.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: "David S. Miller" <davem@davemloft.net>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Use the lock validator framework to prove spinlock and rwlock locking
correctness.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Locking init improvement:
- introduce and use __SPIN_LOCK_UNLOCKED for array initializations,
to pass in the name string of locks, used by debugging
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6:
[IPV6]: Added GSO support for TCPv6
[NET]: Generalise TSO-specific bits from skb_setup_caps
[IPV6]: Added GSO support for TCPv6
[IPV6]: Remove redundant length check on input
[NETFILTER]: SCTP conntrack: fix crash triggered by packet without chunks
[TG3]: Update version and reldate
[TG3]: Add TSO workaround using GSO
[TG3]: Turn on hw fix for ASF problems
[TG3]: Add rx BD workaround
[TG3]: Add tg3_netif_stop() in vlan functions
[TCP]: Reset gso_segs if packet is dodgy
This patch adds GSO support for IPv6 and TCPv6. This is based on a patch
by Ananda Raju <Ananda.Raju@neterion.com>. His original description is:
This patch enables TSO over IPv6. Currently Linux network stacks
restricts TSO over IPv6 by clearing of the NETIF_F_TSO bit from
"dev->features". This patch will remove this restriction.
This patch will introduce a new flag NETIF_F_TSO6 which will be used
to check whether device supports TSO over IPv6. If device support TSO
over IPv6 then we don't clear of NETIF_F_TSO and which will make the
TCP layer to create TSO packets. Any device supporting TSO over IPv6
will set NETIF_F_TSO6 flag in "dev->features" along with NETIF_F_TSO.
In case when user disables TSO using ethtool, NETIF_F_TSO will get
cleared from "dev->features". So even if we have NETIF_F_TSO6 we don't
get TSO packets created by TCP layer.
SKB_GSO_TCPV4 renamed to SKB_GSO_TCP to make it generic GSO packet.
SKB_GSO_UDPV4 renamed to SKB_GSO_UDP as UFO is not a IPv4 feature.
UFO is supported over IPv6 also
The following table shows there is significant improvement in
throughput with normal frames and CPU usage for both normal and jumbo.
--------------------------------------------------
| | 1500 | 9600 |
| ------------------|-------------------|
| | thru CPU | thru CPU |
--------------------------------------------------
| TSO OFF | 2.00 5.5% id | 5.66 20.0% id |
--------------------------------------------------
| TSO ON | 2.63 78.0 id | 5.67 39.0% id |
--------------------------------------------------
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch generalises the TSO-specific bits from sk_setup_caps by adding
the sk_gso_type member to struct sock. This makes sk_setup_caps generic
so that it can be used by TCPv6 or UFO.
The only catch is that whoever uses this must provide a GSO implementation
for their protocol which I think is a fair deal :) For now UFO continues to
live without a GSO implementation which is OK since it doesn't use the sock
caps field at the moment.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
