A SCTP endpoint may have a lot of associations on them and walking
the list is fairly inefficient.  Instead, use a hashed lookup,
and filter out the hash list based on the endopoing we already have.
Signed-off-by: Vlad Yasevich <vladislav.yasevich@hp.com>

There is a possible race condition where the timer code will
free the association and the next packet in the queue will also
attempt to free the same association.

The example is, when we receive an ABORT at about the same time
as the retransmission timer fires.  If the timer wins the race,
it will free the association.  Once it releases the lock, the
queue processing will recieve the ABORT and will try to free
the association again.
Signed-off-by: Vlad Yasevich <vladislav.yasevich@hp.com>

This patch adds a tunable that will allow ADD_IP to work without
AUTH for backward compatibility.  The default value is off since
the default value for ADD_IP is off as well.  People who need
to use ADD-IP with older implementations take risks of connection
hijacking and should consider upgrading or turning this tunable on.
Signed-off-by: Vlad Yasevich <vladislav.yasevich@hp.com>

Signed-off-by: Vlad Yasevich <vladislav.yasevich@hp.com>

After learning more about rcu, it looks like the ADD-IP hadling
doesn't need to call call_rcu_bh.  All the rcu critical sections
use rcu_read_lock, so using call_rcu_bh is wrong here.
Now, restore the local_bh_disable() code blocks and use normal
call_rcu() calls.  Also restore the missing return statement.
Signed-off-by: Vlad Yasevich <vladislav.yasevich@hp.com>

Commit d0ce9291 broke several retransmit
cases including fast retransmit.  The reason is that we should
only delay by rto while doing retranmists as a result of a timeout.
Retransmit as a result of path mtu discover, fast retransmit, or
other evernts that should trigger immidiate retransmissions got broken.

Also, since rto is doubled prior to marking of packets elegable for
retransmission, we never marked correct chunks anyway.

The fix is provide a reason for a given retransmission so that we
can mark chunks appropriately and to save the old rto value to do
comparisons against.

All regressions tests passed with this code.

Spotted by Wei Yongjun <yjwei@cn.fujitsu.com>
Signed-off-by: Vlad Yasevich <vladislav.yasevich@hp.com>

If ASCONF chunk is bundled with other chunks as the first chunk, when
process the ASCONF parameters, full packet data will be process as the
parameters of the ASCONF chunk, not only the real parameters. So if you
send a ASCONF chunk bundled with other chunks, you will get an unexpect
result.
This problem also exists when ASCONF-ACK chunk is bundled with other chunks.

This patch fix this problem.
Signed-off-by: Wei Yongjun <yjwei@cn.fujitsu.com>
Signed-off-by: Vlad Yasevich <vladislav.yasevich@hp.com>

Just fix the bad format of the comment in outqueue.c.
Signed-off-by: Wei Yongjun <yjwei@cn.fujitsu.com>
Signed-off-by: Vlad Yasevich <vladislav.yasevich@hp.com>

Commit ed6dcf4a in the history.git tree broke netlink_unicast timeouts
by moving the schedule_timeout() call to a new function that doesn't
propagate the remaining timeout back to the caller. This means on each
retry we start with the full timeout again.

ipc/mqueue.c seems to actually want to wait indefinitely so this
behaviour is retained.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

As done two years ago on IP route cache table (commit
22c047cc) , we can avoid using one
lock per hash bucket for the huge TCP/DCCP hash tables.

On a typical x86_64 platform, this saves about 2MB or 4MB of ram, for
litle performance differences. (we hit a different cache line for the
rwlock, but then the bucket cache line have a better sharing factor
among cpus, since we dirty it less often). For netstat or ss commands
that want a full scan of hash table, we perform fewer memory accesses.

Using a 'small' table of hashed rwlocks should be more than enough to
provide correct SMP concurrency between different buckets, without
using too much memory. Sizing of this table depends on
num_possible_cpus() and various CONFIG settings.

This patch provides some locking abstraction that may ease a future
work using a different model for TCP/DCCP table.
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Acked-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

This patch makes the master daemon to sync the connection when it is about
to close.  This makes the connections on the backup to close or timeout
according their state.  Before the sync was performed only if the
connection is in ESTABLISHED state which always made the connections to
timeout in the hard coded 3 minutes. However the Andy Gospodarek's patch
([IPVS]: use proper timeout instead of fixed value) effectively did nothing
more than increasing this to 15 minutes (Established state timeout).  So
this patch makes use of proper timeout since it syncs the connections on
status changes to FIN_WAIT (2min timeout) and CLOSE (10sec timeout).
However if the backup misses CLOSE hopefully it did not miss FIN_WAIT.
Otherwise we will just have to wait for the ESTABLISHED state timeout. As
it is without this patch.  This way the number of the hanging connections
on the backup is kept to minimum. And very few of them will be left to
timeout with a long timeout.

This is important if we want to make use of the fix for the real server
overcommit on master/backup fail-over.
Signed-off-by: Rumen G. Bogdanovski <rumen@voicecho.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
Signed-off-by: David S. Miller <davem@davemloft.net>

This patch fixes the problem with node overload on director fail-over.
Given the scenario: 2 nodes each accepting 3 connections at a time and 2
directors, director failover occurs when the nodes are fully loaded (6
connections to the cluster) in this case the new director will assign
another 6 connections to the cluster, If the same real servers exist
there.

The problem turned to be in not binding the inherited connections to
the real servers (destinations) on the backup director. Therefore:
"ipvsadm -l" reports 0 connections:
root@test2:~# ipvsadm -l
IP Virtual Server version 1.2.1 (size=4096)
Prot LocalAddress:Port Scheduler Flags
  -> RemoteAddress:Port           Forward Weight ActiveConn InActConn
TCP  test2.local:5999 wlc
  -> node473.local:5999           Route   1000   0          0
  -> node484.local:5999           Route   1000   0          0

while "ipvs -lnc" is right
root@test2:~# ipvsadm -lnc
IPVS connection entries
pro expire state       source             virtual            destination
TCP 14:56  ESTABLISHED 192.168.0.10:39164 192.168.0.222:5999
192.168.0.51:5999
TCP 14:59  ESTABLISHED 192.168.0.10:39165 192.168.0.222:5999
192.168.0.52:5999

So the patch I am sending fixes the problem by binding the received
connections to the appropriate service on the backup director, if it
exists, else the connection will be handled the old way. So if the
master and the backup directors are synchronized in terms of real
services there will be no problem with server over-committing since
new connections will not be created on the nonexistent real services
on the backup. However if the service is created later on the backup,
the binding will be performed when the next connection update is
received. With this patch the inherited connections will show as
inactive on the backup:

root@test2:~# ipvsadm -l
IP Virtual Server version 1.2.1 (size=4096)
Prot LocalAddress:Port Scheduler Flags
  -> RemoteAddress:Port           Forward Weight ActiveConn InActConn
TCP  test2.local:5999 wlc
  -> node473.local:5999           Route   1000   0          1
  -> node484.local:5999           Route   1000   0          1

rumen@test2:~$ cat /proc/net/ip_vs
IP Virtual Server version 1.2.1 (size=4096)
Prot LocalAddress:Port Scheduler Flags
  -> RemoteAddress:Port Forward Weight ActiveConn InActConn
TCP  C0A800DE:176F wlc
  -> C0A80033:176F      Route   1000   0          1
  -> C0A80032:176F      Route   1000   0          1

Regards,
Rumen Bogdanovski
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Rumen G. Bogdanovski <rumen@voicecho.com>
Signed-off-by: Simon Horman <horms@verge.net.au>

There's no no point in keeping documentation for a driver that was
removed many years ago.
Signed-off-by: Adrian Bunk <bunk@kernel.org>
Acked-by: Alan Cox <alan@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

This file is so outdated that I can't see any value in keeping it.
Signed-off-by: Adrian Bunk <bunk@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

Newsflash: There once was a version of NCSA telnet that had some bug.

Spotted by Pekka Pietikainen.
Signed-off-by: Adrian Bunk <bunk@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

The drivers have already been removed 3.5 years ago.
Signed-off-by: Adrian Bunk <bunk@kernel.org>
Acked-by: Alan Cox <alan@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

After more than 11 years this file does no longer contain much useful
information.
Signed-off-by: Adrian Bunk <bunk@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

The struct proto has the per-cpu "inuse" counter, which is handled
with a special care. All the handling code hides under the ifdef
CONFIG_SMP and it introduces some code duplication and makes it
look worse than it could.

Clean this.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

The function crypto_alloc_comp returns an errno instead of NULL
to indicate error.  So it needs to be tested with IS_ERR.

This is based on a patch by Vicen Beltran Querol.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>

Based on report and patch by Doug Kehn <rdkehn@yahoo.com>:

vconfig returns the following error when attempting to execute the
set_ingress_map command:

vconfig: socket or ioctl error for set_ingress_map: Operation not permitted

In vlan.c, vlan_ioctl_handler for SET_VLAN_INGRESS_PRIORITY_CMD
sets err = -EPERM and calls vlan_dev_set_ingress_priority.
vlan_dev_set_ingress_priority is a void function so err remains
at -EPERM and results in the vconfig error (even though the ingress
map was set).

Fix by setting err = 0 after the vlan_dev_set_ingress_priority call.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

Because net_free is called by copy_net_ns before its declaration, the
compiler gives an error. This patch puts net_free before copy_net_ns
to fix this.

The compiler error:
net/core/net_namespace.c: In function 'copy_net_ns':
net/core/net_namespace.c:97: error: implicit declaration of function 'net_free'
net/core/net_namespace.c: At top level:
net/core/net_namespace.c:104: warning: conflicting types for 'net_free'
net/core/net_namespace.c:104: error: static declaration of 'net_free' follows non-static declaration
net/core/net_namespace.c:97: error: previous implicit declaration of 'net_free' was here

The error was introduced by the '[NET]: Hide the dead code in the
net_namespace.c' patch (6a1a3b9f).
Signed-off-by: Johann Felix Soden <johfel@users.sourceforge.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

We conciously make a change here - we permit mode and speed setting to
be done in things like SLIP mode. There isn't actually a technical
reason to disallow this. It's usually a silly thing to do but we can
do it and soemone might wish to do so.
Signed-off-by: Alan Cox <alan@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Dave Miller noted various cases where line disciplines for things like
ppp go poking around in termios themselves in ways that broke with the
new termios code. Rather than have them all learning about termios
internals provide proper methods for this

- tty_mode_ioctl()

	This handles all the terminal mode handling for speed/carrier
etc and none of the methods are ldisc dependant so they can be called
by any user

- tty_perform_flush()

	This extracts the flush functionality and enables pppd the ppp
layer to share it cleanly.

The existing n_tty_ioctl code is refactored in this patch to provide
the new functions and to call them itself appropriately. This patch
has no (intended) behaviour changes and simply prepares for the other
fixes.
Signed-off-by: Alan Cox <alan@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

While trying to implement u32 hashes in my shaping machine I ran into
a possible bug in the u32 hash/bucket computing algorithm
(net/sched/cls_u32.c).

The problem occurs only with hash masks that extend over the octet
boundary, on little endian machines (where htonl() actually does
something).

Let's say that I would like to use 0x3fc0 as the hash mask. This means
8 contiguous "1" bits starting at b6. With such a mask, the expected
(and logical) behavior is to hash any address in, for instance,
192.168.0.0/26 in bucket 0, then any address in 192.168.0.64/26 in
bucket 1, then 192.168.0.128/26 in bucket 2 and so on.

This is exactly what would happen on a big endian machine, but on
little endian machines, what would actually happen with current
implementation is 0x3fc0 being reversed (into 0xc03f0000) by htonl()
in the userspace tool and then applied to 192.168.x.x in the u32
classifier. When shifting right by 16 bits (rank of first "1" bit in
the reversed mask) and applying the divisor mask (0xff for divisor
256), what would actually remain is 0x3f applied on the "168" octet of
the address.

One could say is this can be easily worked around by taking endianness
into account in userspace and supplying an appropriate mask (0xfc03)
that would be turned into contiguous "1" bits when reversed
(0x03fc0000). But the actual problem is the network address (inside
the packet) not being converted to host order, but used as a
host-order value when computing the bucket.

Let's say the network address is written as n31 n30 ... n0, with n0
being the least significant bit. When used directly (without any
conversion) on a little endian machine, it becomes n7 ... n0 n8 ..n15
etc in the machine's registers. Thus bits n7 and n8 would no longer be
adjacent and 192.168.64.0/26 and 192.168.128.0/26 would no longer be
consecutive.

The fix is to apply ntohl() on the hmask before computing fshift,
and in u32_hash_fold() convert the packet data to host order before
shifting down by fshift.

With helpful feedback from Jamal Hadi Salim and Jarek Poplawski.
Signed-off-by: David S. Miller <davem@davemloft.net>

Removing duplicit #includes for net/
Signed-off-by: Jiri Olsa <olsajiri@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

All this USB_USBNET_MII trickery is simply not worth it considering how
few code it saves.

As a side effect, this also fixes the following compile error reported
by Toralf Frster:

<--  snip  -->

...
  LD      .tmp_vmlinux1
drivers/built-in.o: In function `usbnet_set_settings':
(.text+0xf1876): undefined reference to `mii_ethtool_sset'
drivers/built-in.o: In function `usbnet_get_settings':
(.text+0xf1836): undefined reference to `mii_ethtool_gset'
drivers/built-in.o: In function `usbnet_get_link':
(.text+0xf18d6): undefined reference to `mii_link_ok'
drivers/built-in.o: In function `usbnet_nway_reset':
(.text+0xf18f6): undefined reference to `mii_nway_restart'
make: *** [.tmp_vmlinux1] Error 1

<--  snip  -->
Signed-off-by: Adrian Bunk <bunk@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

Drivers have no business changing these values.
Signed-off-by: David S. Miller <davem@davemloft.net>

Use SO_RCVBUFFORCE instead.
Signed-off-by: David S. Miller <davem@davemloft.net>

There are places that check for CONFIG_IP_MULTIPLE_TABLES
twice in the same file, but the internals of these #ifdefs
can be merged.

As a side effect - remove one ifdef from inside a function.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

It'd also be nice to mention "containers" somewhere in the help text
(I'm assuming that's what it's for?).
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>

There are no more users.
Signed-off-by: David S. Miller <davem@davemloft.net>

This removes last proc_net_create() user. Kudos to Benjamin Thery and
Stephen Hemminger for comments on previous version.
Signed-off-by: Alexey Dobriyan <adobriyan@sw.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>

tecl_reset() is called from deactivate and qdisc is set to noop already,
but subsequent teql_xmit does not know about it and dereference private
data as teql qdisc and thus oopses.
not catch it first :)
Signed-off-by: Evgeniy Polyakov <johnpol@2ka.mipt.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>

Signed-off-by: David S. Miller <davem@davemloft.net>

Trivial patch to make "sctcp,sctpv6" protocols uses the fast "inuse
sockets" infrastructure

Each protocol use then a static percpu var, instead of a dynamic one.
This saves some ram and some cpu cycles
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Trivial patch to make "tcpv6,udpv6,udplitev6,rawv6" protocols uses the
fast "inuse sockets" infrastructure

Each protocol use then a static percpu var, instead of a dynamic one.
This saves some ram and some cpu cycles
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Trivial patch to make "tcp,udp,udplite,raw" protocols uses the fast
"inuse sockets" infrastructure

Each protocol use then a static percpu var, instead of a dynamic one.
This saves some ram and some cpu cycles
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

"struct proto" currently uses an array stats[NR_CPUS] to track change on
'inuse' sockets per protocol.

If NR_CPUS is big, this means we use a big memory area for this.
Moreover, all this memory area is located on a single node on NUMA
machines, increasing memory pressure on the boot node.

In this patch, I tried to :

- Keep a fast !CONFIG_SMP implementation
- Keep a fast CONFIG_SMP implementation for often used protocols
(tcp,udp,raw,...)
- Introduce a NUMA efficient implementation

Some helper macros are defined in include/net/sock.h
These macros take into account CONFIG_SMP

If a "struct proto" is declared without using DEFINE_PROTO_INUSE /
REF_PROTO_INUSE
macros, it will automatically use a default implementation, using a
dynamically allocated percpu zone.
This default implementation will be NUMA efficient, but might use 32/64
bytes per possible cpu
because of current alloc_percpu() implementation.
However it still should be better than previous implementation based on
stats[NR_CPUS] field.

When a "struct proto" is changed to use the new macros, we use a single
static "int" percpu variable,
lowering the memory and cpu costs, still preserving NUMA efficiency.
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Changes made on 18-sep to fix skb handling in the pppol2tp driver
broke the transmit and receive paths. Users are only running into this
now because distros are now using 2.6.23 and I must have messed up
when I tested the change.

For receive, we now do our own calculation of how much to pull from
the skb (variable length L2TP header) rather than using
skb_transport_offset(). Also, if the skb isn't a data packet, it must
be passed back to UDP with skb->data pointing to the UDP header.

For transmit, make sure skb->sk is set up because ip_queue_xmit()
needs it.
Signed-off-by: James Chapman <jchapman@katalix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The #idfed CONFIG_IP_MROUTE is sometimes places inside the if-s,
which looks completely bad. Similar ifdefs inside the functions
looks a bit better, but they are also not recommended to be used.

Provide an ifdef-ed ip_mroute_opt() helper to cleanup the code.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>