Commit Graph

261 Commits

Author SHA1 Message Date
Stephen Hemminger
7faffa1c7f [TCP]: add tcp_slow_start helper
Move all the code that does linear TCP slowstart to one
inline function to ease later patch to add ABC support.

Signed-off-by: Stephen Hemminger <shemminger@osdl.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-11-10 17:07:24 -08:00
Stephen Hemminger
f4805eded7 [TCP]: fix congestion window update when using TSO deferal
TCP peformance with TSO over networks with delay is awful.
On a 100Mbit link with 150ms delay, we get 4Mbits/sec with TSO and
50Mbits/sec without TSO.

The problem is with TSO, we intentionally do not keep the maximum
number of packets in flight to fill the window, we hold out to until 
we can send a MSS chunk. But, we also don't update the congestion window 
unless we have filled, as per RFC2861.

This patch replaces the check for the congestion window being full
with something smarter that accounts for TSO.

Signed-off-by: Stephen Hemminger <shemminger@osdl.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-11-10 16:53:30 -08:00
Herbert Xu
fb286bb299 [NET]: Detect hardware rx checksum faults correctly
Here is the patch that introduces the generic skb_checksum_complete
which also checks for hardware RX checksum faults.  If that happens,
it'll call netdev_rx_csum_fault which currently prints out a stack
trace with the device name.  In future it can turn off RX checksum.

I've converted every spot under net/ that does RX checksum checks to
use skb_checksum_complete or __skb_checksum_complete with the
exceptions of:

* Those places where checksums are done bit by bit.  These will call
netdev_rx_csum_fault directly.

* The following have not been completely checked/converted:

ipmr
ip_vs
netfilter
dccp

This patch is based on patches and suggestions from Stephen Hemminger
and David S. Miller.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-11-10 13:01:24 -08:00
Thomas Graf
482a8524f8 [NETLINK]: Generic netlink family
The generic netlink family builds on top of netlink and provides
simplifies access for the less demanding netlink users. It solves
the problem of protocol numbers running out by introducing a so
called controller taking care of id management and name resolving.

Generic netlink modules register themself after filling out their
id card (struct genl_family), after successful registration the
modules are able to register callbacks to command numbers by
filling out a struct genl_ops and calling genl_register_op(). The
registered callbacks are invoked with attributes parsed making
life of simple modules a lot easier.

Although generic netlink modules can request static identifiers,
it is recommended to use GENL_ID_GENERATE and to let the controller
assign a unique identifier to the module. Userspace applications
will then ask the controller and lookup the idenfier by the module
name.

Due to the current multicast implementation of netlink, the number
of generic netlink modules is restricted to 1024 to avoid wasting
memory for the per socket multiacst subscription bitmask.

Signed-off-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-11-10 02:26:41 +01:00
Thomas Graf
82ace47a72 [NETLINK]: Generic netlink receive queue processor
Introduces netlink_run_queue() to handle the receive queue of
a netlink socket in a generic way. Processes as much as there
was in the queue upon entry and invokes a callback function
for each netlink message found. The callback function may
refuse a message by returning a negative error code but setting
the error pointer to 0 in which case netlink_run_queue() will
return with a qlen != 0.

Signed-off-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-11-10 02:26:40 +01:00
Thomas Graf
bfa83a9e03 [NETLINK]: Type-safe netlink messages/attributes interface
Introduces a new type-safe interface for netlink message and
attributes handling. The interface is fully binary compatible
with the old interface towards userspace. Besides type safety,
this interface features attribute validation capabilities,
simplified message contstruction, and documentation.

The resulting netlink code should be smaller, less error prone
and easier to understand.

Signed-off-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-11-10 02:26:40 +01:00
Yasuyuki Kozakai
9fb9cbb108 [NETFILTER]: Add nf_conntrack subsystem.
The existing connection tracking subsystem in netfilter can only
handle ipv4.  There were basically two choices present to add
connection tracking support for ipv6.  We could either duplicate all
of the ipv4 connection tracking code into an ipv6 counterpart, or (the
choice taken by these patches) we could design a generic layer that
could handle both ipv4 and ipv6 and thus requiring only one sub-protocol
(TCP, UDP, etc.) connection tracking helper module to be written.

In fact nf_conntrack is capable of working with any layer 3
protocol.

The existing ipv4 specific conntrack code could also not deal
with the pecularities of doing connection tracking on ipv6,
which is also cured here.  For example, these issues include:

1) ICMPv6 handling, which is used for neighbour discovery in
   ipv6 thus some messages such as these should not participate
   in connection tracking since effectively they are like ARP
   messages

2) fragmentation must be handled differently in ipv6, because
   the simplistic "defrag, connection track and NAT, refrag"
   (which the existing ipv4 connection tracking does) approach simply
   isn't feasible in ipv6

3) ipv6 extension header parsing must occur at the correct spots
   before and after connection tracking decisions, and there were
   no provisions for this in the existing connection tracking
   design

4) ipv6 has no need for stateful NAT

The ipv4 specific conntrack layer is kept around, until all of
the ipv4 specific conntrack helpers are ported over to nf_conntrack
and it is feature complete.  Once that occurs, the old conntrack
stuff will get placed into the feature-removal-schedule and we will
fully kill it off 6 months later.

Signed-off-by: Yasuyuki Kozakai <yasuyuki.kozakai@toshiba.co.jp>
Signed-off-by: Harald Welte <laforge@netfilter.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>
2005-11-09 16:38:16 -08:00
Linus Torvalds
a7c243b544 Merge branch 'upstream-linus' of master.kernel.org:/pub/scm/linux/kernel/git/jgarzik/netdev-2.6 2005-11-09 08:34:36 -08:00
Christoph Hellwig
e3305626e0 ieee80211: cleanup crypto list handling, other minor cleanups. 2005-11-09 01:01:04 -05:00
Jeff Garzik
f24e09754b Merge rsync://bughost.org/repos/ieee80211-delta/ 2005-11-09 00:00:29 -05:00
Marcel Holtmann
be9d122730 [Bluetooth]: Remove the usage of /proc completely
This patch removes all relics of the /proc usage from the Bluetooth
subsystem core and its upper layers. All the previous information are
now available via /sys/class/bluetooth through appropriate functions.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-11-08 09:57:38 -08:00
Marcel Holtmann
1ebb92521d [Bluetooth]: Add endian annotations to the core
This patch adds the endian annotations to the Bluetooth core.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-11-08 09:57:21 -08:00
Stephen Hemminger
9ee6b535af [NET]: sk_add_backlog convert from macro to inline
There is no reason for sk_add_backlog to be a macro. It can
just be an inline function and get type checking.

Signed-off-by: Stephen Hemminger <shemminger@osdl.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-11-08 09:39:42 -08:00
YOSHIFUJI Hideaki
b1cacb6820 [IPV6]: Make ipv6_addr_type() more generic so that we can use it for source address selection.
Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-11-08 09:38:12 -08:00
YOSHIFUJI Hideaki
971f359ddc [IPV6]: Put addr_diff() into common header for future use.
Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-11-08 09:37:56 -08:00
James Ketrenos
d7e02edbc5 Update version ieee80211 stamp to 1.1.7 2005-11-07 16:19:17 -06:00
Arnaldo Carvalho de Melo
2d43f1128a Merge branch 'red' of 84.73.165.173:/home/tgr/repos/net-2.6 2005-11-05 22:30:29 -02:00
Stephen Hemminger
6df716340d [TCP/DCCP]: Randomize port selection
This patch randomizes the port selected on bind() for connections
to help with possible security attacks. It should also be faster
in most cases because there is no need for a global lock.

Signed-off-by: Stephen Hemminger <shemminger@osdl.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>
2005-11-05 21:23:15 -02:00
Thomas Graf
2566a509ca [NET]: Introduce INET_ECN_set_ce() function
Changes IP_ECN_set_ce() and IP6_ECN_set_ce() to return 0 if the CE
bits could not bet set because none of the ECT bits are set or 1
if the CE bits are already set or have been successfully set.

Introduces INET_ECN_set_ce(skb) to enable CE bits for all supported
protocols.

Signed-off-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>
2005-11-05 22:02:24 +01:00
Thomas Graf
a783474591 [PKT_SCHED]: Generic RED layer
Extracts the RED algorithm from sch_red.c and puts it into include/net/red.h
for use by other RED based modules. The statistics are extended to be more
fine grained in order to differ between probability/forced marks/drops.
We now reset the average queue length when setting new parameters, leaving
it might result in an unreasonable qavg for a while depending on the value of W.

Signed-off-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>
2005-11-05 22:02:24 +01:00
Linus Torvalds
62d3af1b5f Merge branch 'upstream-linus' of master.kernel.org:/pub/scm/linux/kernel/git/jgarzik/netdev-2.6 2005-10-29 11:25:16 -07:00
Arnaldo Carvalho de Melo
974f7bc578 Merge master.kernel.org:/pub/scm/linux/kernel/git/sridhar/lksctp-2.6 2005-10-28 23:35:02 -02:00
Jeff Garzik
596c96ba06 Merge branch 'master' 2005-10-28 18:48:57 -04:00
Ivan Skytte Jorgensen
eaa5c54dbe [SCTP] Rename SCTP specific control message flags.
Rename SCTP specific control message flags to use SCTP_ prefix rather than
MSG_ prefix as per the latest sctp sockets API draft.

Signed-off-by: Ivan Skytte Jorgensen <isj-sctp@i1.dk>
Signed-off-by: Sridhar Samudrala <sri@us.ibm.com>
2005-10-28 15:10:00 -07:00
Jesper Juhl
b4558ea93d drivers/net: Remove pointless checks for NULL prior to calling kfree() 2005-10-28 16:53:13 -04:00
Arnaldo Carvalho de Melo
de5144164f Merge master.kernel.org:/pub/scm/linux/kernel/git/holtmann/bluetooth-2.6 2005-10-28 15:49:24 -02:00
Marcel Holtmann
6516455d3b [Bluetooth] Make more functions static
This patch makes another bunch of functions static.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
2005-10-28 19:20:48 +02:00
Marcel Holtmann
408c1ce271 [Bluetooth] Move CRC table into RFCOMM core
This patch moves rfcomm_crc_table[] into the RFCOMM core, because there
is no need to keep it in a separate file.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
2005-10-28 19:20:36 +02:00
Linus Torvalds
e5dfa9282f Merge branch 'upstream' of master.kernel.org:/pub/scm/linux/kernel/git/jgarzik/netdev-2.6 2005-10-28 09:05:25 -07:00
Linus Torvalds
236fa08168 Merge master.kernel.org:/pub/scm/linux/kernel/git/acme/net-2.6.15 2005-10-28 08:50:37 -07:00
Al Viro
7d877f3bda [PATCH] gfp_t: net/*
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-28 08:16:47 -07:00
Jeff Garzik
1f57389a38 Merge branch 'master' 2005-10-26 01:06:45 -04:00
Herbert Xu
80b30c1023 [IPSEC]: Kill obsolete get_mss function
Now that we've switched over to storing MTUs in the xfrm_dst entries,
we no longer need the dst's get_mss methods.  This patch gets rid of
them.

It also documents the fact that our MTU calculation is not optimal
for ESP.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>
2005-10-26 00:48:45 -02:00
Jochen Friedrich
5ed688a716 [LLC]: Strip RIF flag from source MAC address
Signed-off-by: Jochen Friedrich <jochen@scram.de>
Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>
2005-10-25 21:34:39 -02:00
Ralf Baechle
4595f25105 [AX.25]: Fix signed char bug
On architectures where the char type defaults to unsigned some of the
arithmetic in the AX.25 stack to fail, resulting in some packets being dropped
on receive.

Credits for tracking this down and the original patch to
Bob Brose N0QBJ <linuxhams@n0qbj-11.ampr.org>.

Signed-off-by: Ralf Baechle DL5RB <ralf@linux-mips.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>
2005-10-22 17:20:50 -02:00
James Ketrenos
519a62bb8a Update version ieee80211 stamp to 1.1.6 2005-10-21 13:00:40 -05:00
Jeff Garzik
59aee3c2a1 Merge branch 'master' 2005-10-13 21:22:27 -04:00
Arnaldo Carvalho de Melo
eeb2b85606 [TWSK]: Grab the module refcount for timewait sockets
This is required to avoid unloading a module that has active timewait
sockets, such as DCCP.

Signed-off-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-10-10 21:25:23 -07:00
Al Viro
dd0fc66fb3 [PATCH] gfp flags annotations - part 1
- added typedef unsigned int __nocast gfp_t;

 - replaced __nocast uses for gfp flags with gfp_t - it gives exactly
   the same warnings as far as sparse is concerned, doesn't change
   generated code (from gcc point of view we replaced unsigned int with
   typedef) and documents what's going on far better.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-08 15:00:57 -07:00
Sridhar Samudrala
20c9c825b1 [SCTP] Fix SCTP socket options to work with 32-bit apps on 64-bit kernels.
Adds alignment attribute to a few structures used with SCTP socket
options so that the sizes and offsets remain the same when built using
either 32 or 64 bit tools.

Signed-off-by: Sridhar Samudrala <sri@us.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-10-06 21:37:01 -07:00
Ivan Skytte Jørgensen
5fe467ee97 [SCTP] Fix sctp_get{pl}addrs() API to work with 32-bit apps on 64-bit kernels.
The old socket options are marked with a _OLD suffix so that the
existing 32-bit apps on 32-bit kernels do not break.

Signed-off-by: Ivan Skytte Jørgensen <isj-sctp@i1.dk>
Signed-off-by: Sridhar Samudrala <sri@us.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-10-06 21:36:17 -07:00
Herbert Xu
77d8d7a684 [IPSEC]: Document that policy direction is derived from the index.
Here is a patch that adds a helper called xfrm_policy_id2dir to
document the fact that the policy direction can be and is derived
from the index.

This is based on a patch by YOSHIFUJI Hideaki and 210313105@suda.edu.cn.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-10-05 12:15:12 -07:00
Randy Dunlap
83fa3400eb [XFRM]: fix sparse gfp nocast warnings
Fix implicit nocast warnings in xfrm code:
net/xfrm/xfrm_policy.c:232:47: warning: implicit cast to nocast type

Signed-off-by: Randy Dunlap <rdunlap@xenotime.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-10-04 22:45:35 -07:00
Randy Dunlap
8eea00a44d [IPVS]: fix sparse gfp nocast warnings
From: Randy Dunlap <rdunlap@xenotime.net>

Fix implicit nocast warnings in ip_vs code:
net/ipv4/ipvs/ip_vs_app.c:631:54: warning: implicit cast to nocast type

Signed-off-by: Randy Dunlap <rdunlap@xenotime.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-10-04 22:42:15 -07:00
Randy Dunlap
f4a19a56e3 [DECNET]: fix sparse gfp nocast warnings
Fix implicit nocast warnings in decnet code:
net/decnet/af_decnet.c:458:40: warning: implicit cast to nocast type
net/decnet/dn_nsp_out.c:125:35: warning: implicit cast to nocast type
net/decnet/dn_nsp_out.c:219:29: warning: implicit cast to nocast type

Signed-off-by: Randy Dunlap <rdunlap@xenotime.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-10-04 22:41:48 -07:00
Eric Dumazet
6d2553612f [INET]: Shrink struct inet_ehash_bucket on 32 bits UP
No need to align struct inet_ehash_bucket on a 8 bytes boundary.

On 32 bits Uniprocessor, that's a waste of 4 bytes per struct (50 %)

On other platforms, the attribute is useless, natual alignement is already 8.

platform     | Size before | Size after patch
-------------+-------------+------------------
32 bits, UP  |         8   |     4
32 bits, SMP |         8   |     8
64 bits, UP  |         8   |     8
64 bits, SMP |        16   |    16

Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-10-04 15:55:51 -07:00
Jeff Garzik
13d1ef29bc Merge rsync://bughost.org/repos/ieee80211-delta/ 2005-10-04 08:22:13 -04:00
Jeff Garzik
3c8c7b2f32 Merge branch 'upstream-fixes' 2005-10-03 22:06:19 -04:00
Eric Dumazet
81c3d5470e [INET]: speedup inet (tcp/dccp) lookups
Arnaldo and I agreed it could be applied now, because I have other
pending patches depending on this one (Thank you Arnaldo)

(The other important patch moves skc_refcnt in a separate cache line,
so that the SMP/NUMA performance doesnt suffer from cache line ping pongs)

1) First some performance data :
--------------------------------

tcp_v4_rcv() wastes a *lot* of time in __inet_lookup_established()

The most time critical code is :

sk_for_each(sk, node, &head->chain) {
     if (INET_MATCH(sk, acookie, saddr, daddr, ports, dif))
         goto hit; /* You sunk my battleship! */
}

The sk_for_each() does use prefetch() hints but only the begining of
"struct sock" is prefetched.

As INET_MATCH first comparison uses inet_sk(__sk)->daddr, wich is far
away from the begining of "struct sock", it has to bring into CPU
cache cold cache line. Each iteration has to use at least 2 cache
lines.

This can be problematic if some chains are very long.

2) The goal
-----------

The idea I had is to change things so that INET_MATCH() may return
FALSE in 99% of cases only using the data already in the CPU cache,
using one cache line per iteration.

3) Description of the patch
---------------------------

Adds a new 'unsigned int skc_hash' field in 'struct sock_common',
filling a 32 bits hole on 64 bits platform.

struct sock_common {
	unsigned short		skc_family;
	volatile unsigned char	skc_state;
	unsigned char		skc_reuse;
	int			skc_bound_dev_if;
	struct hlist_node	skc_node;
	struct hlist_node	skc_bind_node;
	atomic_t		skc_refcnt;
+	unsigned int		skc_hash;
	struct proto		*skc_prot;
};

Store in this 32 bits field the full hash, not masked by (ehash_size -
1) Using this full hash as the first comparison done in INET_MATCH
permits us immediatly skip the element without touching a second cache
line in case of a miss.

Suppress the sk_hashent/tw_hashent fields since skc_hash (aliased to
sk_hash and tw_hash) already contains the slot number if we mask with
(ehash_size - 1)

File include/net/inet_hashtables.h

64 bits platforms :
#define INET_MATCH(__sk, __hash, __cookie, __saddr, __daddr, __ports, __dif)\
     (((__sk)->sk_hash == (__hash))
     ((*((__u64 *)&(inet_sk(__sk)->daddr)))== (__cookie))   &&  \
     ((*((__u32 *)&(inet_sk(__sk)->dport))) == (__ports))   &&  \
     (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif))))

32bits platforms:
#define TCP_IPV4_MATCH(__sk, __hash, __cookie, __saddr, __daddr, __ports, __dif)\
     (((__sk)->sk_hash == (__hash))                 &&  \
     (inet_sk(__sk)->daddr          == (__saddr))   &&  \
     (inet_sk(__sk)->rcv_saddr      == (__daddr))   &&  \
     (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif))))


- Adds a prefetch(head->chain.first) in 
__inet_lookup_established()/__tcp_v4_check_established() and 
__inet6_lookup_established()/__tcp_v6_check_established() and 
__dccp_v4_check_established() to bring into cache the first element of the 
list, before the {read|write}_lock(&head->lock);

Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Acked-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-10-03 14:13:38 -07:00
James Ketrenos
ff0037b259 Lindent and trailing whitespace script executed ieee80211 subsystem
Signed-off-by: James Ketrenos <jketreno@linux.intel.com>
2005-10-03 10:23:42 -05:00