Commit Graph

34 Commits

Author SHA1 Message Date
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
Arnaldo Carvalho de Melo
20380731bc [NET]: Fix sparse warnings
Of this type, mostly:

CHECK   net/ipv6/netfilter.c
net/ipv6/netfilter.c:96:12: warning: symbol 'ipv6_netfilter_init' was not declared. Should it be static?
net/ipv6/netfilter.c:101:6: warning: symbol 'ipv6_netfilter_fini' was not declared. Should it be static?

Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-29 16:01:32 -07:00
Arnaldo Carvalho de Melo
6687e988d9 [ICSK]: Move TCP congestion avoidance members to icsk
This changeset basically moves tcp_sk()->{ca_ops,ca_state,etc} to inet_csk(),
minimal renaming/moving done in this changeset to ease review.

Most of it is just changes of struct tcp_sock * to struct sock * parameters.

With this we move to a state closer to two interesting goals:

1. Generalisation of net/ipv4/tcp_diag.c, becoming inet_diag.c, being used
   for any INET transport protocol that has struct inet_hashinfo and are
   derived from struct inet_connection_sock. Keeps the userspace API, that will
   just not display DCCP sockets, while newer versions of tools can support
   DCCP.

2. INET generic transport pluggable Congestion Avoidance infrastructure, using
   the current TCP CA infrastructure with DCCP.

Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-29 15:56:18 -07:00
Patrick McHardy
64ce207306 [NET]: Make NETDEBUG pure printk wrappers
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-29 15:56:08 -07:00
Arnaldo Carvalho de Melo
295ff7edb8 [TIMEWAIT]: Introduce inet_timewait_death_row
That groups all of the tables and variables associated to the TCP timewait
schedulling/recycling/killing code, that now can be isolated from the TCP
specific code and used by other transport protocols, such as DCCP.

Next changeset will move this code to net/ipv4/inet_timewait_sock.c

Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-29 15:55:48 -07:00
Arnaldo Carvalho de Melo
0a5578cf8e [ICSK]: Generalise tcp_listen_{start,stop}
This also moved inet_iif from tcp to inet_hashtables.h, as it is
needed by the inet_lookup callers, perhaps this needs a bit of
polishing, but for now seems fine.

Signed-off-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-29 15:49:24 -07:00
Arnaldo Carvalho de Melo
3f421baa47 [NET]: Just move the inet_connection_sock function from tcp sources
Completing the previous changeset, this also generalises tcp_v4_synq_add,
renaming it to inet_csk_reqsk_queue_hash_add, already geing used in the
DCCP tree, which I plan to merge RSN.

Signed-off-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-29 15:49:14 -07:00
Arnaldo Carvalho de Melo
463c84b97f [NET]: Introduce inet_connection_sock
This creates struct inet_connection_sock, moving members out of struct
tcp_sock that are shareable with other INET connection oriented
protocols, such as DCCP, that in my private tree already uses most of
these members.

The functions that operate on these members were renamed, using a
inet_csk_ prefix while not being moved yet to a new file, so as to
ease the review of these changes.

Signed-off-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-29 15:43:19 -07:00
Arnaldo Carvalho de Melo
e48c414ee6 [INET]: Generalise the TCP sock ID lookup routines
And also some TIME_WAIT functions.

[acme@toy net-2.6.14]$ grep built-in /tmp/before.size /tmp/after.size
/tmp/before.size: 282955   13122    9312  305389   4a8ed net/ipv4/built-in.o
/tmp/after.size:  281566   13122    9312  304000   4a380 net/ipv4/built-in.o
[acme@toy net-2.6.14]$

I kept them still inlined, will uninline at some point to see what
would be the performance difference.

Signed-off-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-29 15:42:18 -07:00
Arnaldo Carvalho de Melo
8feaf0c0a5 [INET]: Generalise tcp_tw_bucket, aka TIME_WAIT sockets
This paves the way to generalise the rest of the sock ID lookup
routines and saves some bytes in TCPv4 TIME_WAIT sockets on distro
kernels (where IPv6 is always built as a module):

[root@qemu ~]# grep tw_sock /proc/slabinfo
tw_sock_TCPv6  0  0  128  31  1
tw_sock_TCP    0  0   96  41  1
[root@qemu ~]#

Now if a protocol wants to use the TIME_WAIT generic infrastructure it
only has to set the sk_prot->twsk_obj_size field with the size of its
inet_timewait_sock derived sock and proto_register will create
sk_prot->twsk_slab, for now its only for INET sockets, but we can
introduce timewait_sock later if some non INET transport protocolo
wants to use this stuff.

Next changesets will take advantage of this new infrastructure to
generalise even more TCP code.

[acme@toy net-2.6.14]$ grep built-in /tmp/before.size /tmp/after.size
/tmp/before.size: 188646   11764    5068  205478   322a6 net/ipv4/built-in.o
/tmp/after.size:  188144   11764    5068  204976   320b0 net/ipv4/built-in.o
[acme@toy net-2.6.14]$

Tested with both IPv4 & IPv6 (::1 (localhost) & ::ffff:172.20.0.1
(qemu host)).

Signed-off-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-29 15:42:13 -07:00
Arnaldo Carvalho de Melo
33b6223190 [INET]: Generalise tcp_v4_lookup_listener
[acme@toy net-2.6.14]$ grep built-in /tmp/before /tmp/after
/tmp/before: 282560       13122    9312  304994   4a762 net/ipv4/built-in.o
/tmp/after:  282560       13122    9312  304994   4a762 net/ipv4/built-in.o

Will be used in DCCP, not exporting it right now not to get in Adrian
Bunk's exported-but-not-used-on-modules radar 8)

Signed-off-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-29 15:42:08 -07:00
Arnaldo Carvalho de Melo
81849d106b [INET]: Generalise tcp_v4_hash & tcp_unhash
It really just makes the existing code be a helper function that
tcp_v4_hash and tcp_unhash uses, specifying the right inet_hashinfo,
tcp_hashinfo.

One thing I'll investigate at some point is to have the inet_hashinfo
pointer in sk_prot, so that we get all the hashtable information from
the sk pointer, this can lead to some extra indirections that may well
hurt performance/code size, we'll see. Ultimate idea would be that
sk_prot would provide _all_ the information about a protocol
implementation.

Signed-off-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-29 15:42:02 -07:00
Arnaldo Carvalho de Melo
f3f05f7046 [INET]: Generalise the tcp_listen_ lock routines
Signed-off-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-29 15:41:49 -07:00
Arnaldo Carvalho de Melo
6e04e02165 [INET]: Move tcp_port_rover to inet_hashinfo
Also expose all of the tcp_hashinfo members, i.e. killing those
tcp_ehash, etc macros, this will more clearly expose already generic
functions and some that need just a bit of work to become generic, as
we'll see in the upcoming changesets.

Signed-off-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-29 15:41:44 -07:00
Arnaldo Carvalho de Melo
2d8c4ce519 [INET]: Generalise tcp_bind_hash & tcp_inherit_port
This required moving tcp_bucket_cachep to inet_hashinfo.

Signed-off-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-29 15:40:29 -07:00
Arnaldo Carvalho de Melo
a55ebcc4c4 [INET]: Move bind_hash from tcp_sk to inet_sk
This should really be in a inet_connection_sock, but I'm leaving it
for a later optimization, when some more fields common to INET
transport protocols now in tcp_sk or inet_sk will be chunked out into
inet_connection_sock, for now its better to concentrate on getting the
changes in the core merged to leave the DCCP tree with only DCCP
specific code.

Next changesets will take advantage of this move to generalise things
like tcp_bind_hash, tcp_put_port, tcp_inherit_port, making the later
receive a inet_hashinfo parameter, and even __tcp_tw_hashdance, etc in
the future, when tcp_tw_bucket gets transformed into the struct
timewait_sock hierarchy.

tcp_destroy_sock also is eligible as soon as tcp_orphan_count gets
moved to sk_prot.

A cascade of incremental changes will ultimately make the tcp_lookup
functions be fully generic.

Signed-off-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-29 15:38:48 -07:00
Arnaldo Carvalho de Melo
77d8bf9c62 [INET]: Move the TCP hashtable functions/structs to inet_hashtables.[ch]
Signed-off-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-29 15:38:39 -07:00
Arnaldo Carvalho de Melo
0f7ff9274e [INET]: Just rename the TCP hashtable functions/structs to inet_
This is to break down the complexity of the series of patches,
making it very clear that this one just does:

1. renames tcp_ prefixed hashtable functions and data structures that
   were already mostly generic to inet_ to share it with DCCP and
   other INET transport protocols.

2. Removes not used functions (__tb_head & tb_head)

3. Removes some leftover prototypes in the headers (tcp_bucket_unlock &
   tcp_v4_build_header)

Next changesets will move tcp_sk(sk)->bind_hash to inet_sock so that we can
make functions such as tcp_inherit_port, __tcp_inherit_port, tcp_v4_get_port,
__tcp_put_port,  generic and get others like tcp_destroy_sock closer to generic
(tcp_orphan_count will go to sk->sk_prot to allow this).

Eventually most of these functions will be used passing the transport protocol
inet_hashinfo structure.

Signed-off-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-29 15:38:32 -07:00
Arnaldo Carvalho de Melo
304a16180f [INET]: Move the TCP ehash functions to include/net/inet_hashtables.h
To be shared with DCCP (and others), this is the start of a series of patches
that will expose the already generic TCP hash table routines.

The few changes noticed when calling gcc -S before/after on a pentium4 were of
this type:

        movl    40(%esp), %edx
        cmpl    %esi, 472(%edx)
        je      .L168
-       pushl   $291
+       pushl   $272
        pushl   $.LC0
        pushl   $.LC1
        pushl   $.LC2

[acme@toy net-2.6.14]$ size net/ipv4/tcp_ipv4.before.o net/ipv4/tcp_ipv4.after.o
   text    data     bss     dec     hex filename
  17804     516     140   18460    481c net/ipv4/tcp_ipv4.before.o
  17804     516     140   18460    481c net/ipv4/tcp_ipv4.after.o

Holler if some weird architecture has issues with things like this 8)

Signed-off-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-29 15:38:22 -07:00
Arnaldo Carvalho de Melo
32519f11d3 [INET]: Introduce inet_sk_rebuild_header
From tcp_v4_rebuild_header, that already was pretty generic, I only
needed to use sk->sk_protocol instead of the hardcoded IPPROTO_TCP and
establish the requirement that INET transport layer protocols that
want to use this function map TCP_SYN_SENT to its equivalent state.

Signed-off-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-29 15:37:55 -07:00
Arnaldo Carvalho de Melo
6cbb0df788 [SOCK]: Introduce sk_setup_caps
From tcp_v4_setup_caps, that always is preceded by a call to
__sk_dst_set, so coalesce this sequence into sk_setup_caps, removing
one call to a TCP function in the IP layer.

Signed-off-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-29 15:37:48 -07:00
Arnaldo Carvalho de Melo
614c6cb4f2 [SOCK]: Rename __tcp_v4_rehash to __sk_prot_rehash
This operation was already generic and DCCP will use it.

Signed-off-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-29 15:37:42 -07:00
David S. Miller
d5d283751e [TCP]: Document non-trivial locking path in tcp_v{4,6}_get_port().
This trips up a lot of folks reading this code.
Put an unlikely() around the port-exhaustion test
for good measure.

Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-23 10:49:54 -07:00
Heikki Orsila
ca9334523c [IPV4]: Debug cleanup
Here's a small patch to cleanup NETDEBUG() use in net/ipv4/ for Linux 
kernel 2.6.13-rc5. Also weird use of indentation is changed in some
places.

Signed-off-by: Heikki Orsila <heikki.orsila@iki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-08 14:26:52 -07:00
David S. Miller
c1b4a7e695 [TCP]: Move to new TSO segmenting scheme.
Make TSO segment transmit size decisions at send time not earlier.

The basic scheme is that we try to build as large a TSO frame as
possible when pulling in the user data, but the size of the TSO frame
output to the card is determined at transmit time.

This is guided by tp->xmit_size_goal.  It is always set to a multiple
of MSS and tells sendmsg/sendpage how large an SKB to try and build.

Later, tcp_write_xmit() and tcp_push_one() chop up the packet if
necessary and conditions warrant.  These routines can also decide to
"defer" in order to wait for more ACKs to arrive and thus allow larger
TSO frames to be emitted.

A general observation is that TSO elongates the pipe, thus requiring a
larger congestion window and larger buffering especially at the sender
side.  Therefore, it is important that applications 1) get a large
enough socket send buffer (this is accomplished by our dynamic send
buffer expansion code) 2) do large enough writes.

Signed-off-by: David S. Miller <davem@davemloft.net>
2005-07-05 15:24:38 -07:00
Stephen Hemminger
5f8ef48d24 [TCP]: Allow choosing TCP congestion control via sockopt.
Allow using setsockopt to set TCP congestion control to use on a per
socket basis.

Signed-off-by: Stephen Hemminger <shemminger@osdl.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-06-23 20:37:36 -07:00
Stephen Hemminger
317a76f9a4 [TCP]: Add pluggable congestion control algorithm infrastructure.
Allow TCP to have multiple pluggable congestion control algorithms.
Algorithms are defined by a set of operations and can be built in
or modules.  The legacy "new RENO" algorithm is used as a starting
point and fallback.

Signed-off-by: Stephen Hemminger <shemminger@osdl.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-06-23 12:19:55 -07:00
David S. Miller
e52c1f17e4 [NET]: Move sysctl_max_syn_backlog into request_sock.c
This fixes the CONFIG_INET=n build failure noticed
by Andrew Morton.

Signed-off-by: David S. Miller <davem@davemloft.net>
2005-06-18 22:49:40 -07:00
Arnaldo Carvalho de Melo
2ad69c55a2 [NET] rename struct tcp_listen_opt to struct listen_sock
Signed-off-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-06-18 22:48:55 -07:00
Arnaldo Carvalho de Melo
0e87506fcc [NET] Generalise tcp_listen_opt
This chunks out the accept_queue and tcp_listen_opt code and moves
them to net/core/request_sock.c and include/net/request_sock.h, to
make it useful for other transport protocols, DCCP being the first one
to use it.

Next patches will rename tcp_listen_opt to accept_sock and remove the
inline tcp functions that just call a reqsk_queue_ function.

Signed-off-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-06-18 22:47:59 -07:00
Arnaldo Carvalho de Melo
60236fdd08 [NET] Rename open_request to request_sock
Ok, this one just renames some stuff to have a better namespace and to
dissassociate it from TCP:

struct open_request  -> struct request_sock
tcp_openreq_alloc    -> reqsk_alloc
tcp_openreq_free     -> reqsk_free
tcp_openreq_fastfree -> __reqsk_free

With this most of the infrastructure closely resembles a struct
sock methods subset.

Signed-off-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-06-18 22:47:21 -07:00
Arnaldo Carvalho de Melo
2e6599cb89 [NET] Generalise TCP's struct open_request minisock infrastructure
Kept this first changeset minimal, without changing existing names to
ease peer review.

Basicaly tcp_openreq_alloc now receives the or_calltable, that in turn
has two new members:

->slab, that replaces tcp_openreq_cachep
->obj_size, to inform the size of the openreq descendant for
  a specific protocol

The protocol specific fields in struct open_request were moved to a
class hierarchy, with the things that are common to all connection
oriented PF_INET protocols in struct inet_request_sock, the TCP ones
in tcp_request_sock, that is an inet_request_sock, that is an
open_request.

I.e. this uses the same approach used for the struct sock class
hierarchy, with sk_prot indicating if the protocol wants to use the
open_request infrastructure by filling in sk_prot->rsk_prot with an
or_calltable.

Results? Performance is improved and TCP v4 now uses only 64 bytes per
open request minisock, down from 96 without this patch :-)

Next changeset will rename some of the structs, fields and functions
mentioned above, struct or_calltable is way unclear, better name it
struct request_sock_ops, s/struct open_request/struct request_sock/g,
etc.

Signed-off-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-06-18 22:46:52 -07:00
Folkert van Heusden
0b2531bdc5 [TCP]: Optimize check in port-allocation code.
Signed-off-by: Folkert van Heusden <folkert@vanheusden.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-05-03 14:36:08 -07:00
Linus Torvalds
1da177e4c3 Linux-2.6.12-rc2
Initial git repository build. I'm not bothering with the full history,
even though we have it. We can create a separate "historical" git
archive of that later if we want to, and in the meantime it's about
3.2GB when imported into git - space that would just make the early
git days unnecessarily complicated, when we don't have a lot of good
infrastructure for it.

Let it rip!
2005-04-16 15:20:36 -07:00