Commit Graph

61 Commits

Author SHA1 Message Date
Eric Dumazet
9327f7053e tcp: Fix a connect() race with timewait sockets
First patch changes __inet_hash_nolisten() and __inet6_hash()
to get a timewait parameter to be able to unhash it from ehash
at same time the new socket is inserted in hash.

This makes sure timewait socket wont be found by a concurrent
writer in __inet_check_established()

Reported-by: kapil dakhane <kdakhane@gmail.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-12-08 20:17:51 -08:00
Lucian Adrian Grijincu
5256f2ef3a inet: fix inet_bind_bucket_for_each
The first "node" is supposed to be the cursor used in the for_each.

The second "node" is ment literally and should not be macro expanded:
it's the name of the hlist_node field from the inet_bind_bucket.

This currently works because when inet_bind_bucket_for_each is called
it's argument is still "node".

Signed-off-by: Lucian Adrian Grijincu <lgrijincu@ixiacom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-11-13 20:46:56 -08:00
Eric Dumazet
c720c7e838 inet: rename some inet_sock fields
In order to have better cache layouts of struct sock (separate zones
for rx/tx paths), we need this preliminary patch.

Goal is to transfert fields used at lookup time in the first
read-mostly cache line (inside struct sock_common) and move sk_refcnt
to a separate cache line (only written by rx path)

This patch adds inet_ prefix to daddr, rcv_saddr, dport, num, saddr,
sport and id fields. This allows a future patch to define these
fields as macros, like sk_refcnt, without name clashes.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-10-18 18:52:53 -07:00
Eric Dumazet
f373b53b5f tcp: replace ehash_size by ehash_mask
Storing the mask (size - 1) instead of the size allows fast path to be
a bit faster.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-10-13 03:44:02 -07:00
Eric Dumazet
adf30907d6 net: skb->dst accessors
Define three accessors to get/set dst attached to a skb

struct dst_entry *skb_dst(const struct sk_buff *skb)

void skb_dst_set(struct sk_buff *skb, struct dst_entry *dst)

void skb_dst_drop(struct sk_buff *skb)
This one should replace occurrences of :
dst_release(skb->dst)
skb->dst = NULL;

Delete skb->dst field

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-06-03 02:51:04 -07:00
Eric Dumazet
24dd1fa184 net: move bsockets outside of read only beginning of struct inet_hashinfo
And switch bsockets to atomic_t since it might be changed in parallel.

Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Acked-by: Evgeniy Polyakov <zbr@ioremap.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-02-01 12:31:33 -08:00
David S. Miller
05bee47377 Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6
Conflicts:
	drivers/net/e1000/e1000_main.c
2009-01-30 14:31:07 -08:00
Eric Dumazet
94cd3e6cbe net: wrong test in inet_ehash_locks_alloc()
In commit 9db66bdcc8 (net: convert
TCP/DCCP ehash rwlocks to spinlocks), I forgot to change one
occurrence of rwlock_t to spinlock_t

I believe sizeof(raw_spinlock_t) might be > 0 on !CONFIG_SMP if
CONFIG_DEBUG_SPINLOCK while sizeof(raw_rwlock_t) should be 0 in this
case.

Fortunatly, CONFIG_DEBUG_SPINLOCK adds fields to both spinlock_t and
rwlock_t, but at this might change in the future (being able to debug
spinlocks but not rwlocks for example), better to be safe.

Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-01-27 17:45:10 -08:00
Evgeniy Polyakov
a9d8f9110d inet: Allowing more than 64k connections and heavily optimize bind(0) time.
With simple extension to the binding mechanism, which allows to bind more
than 64k sockets (or smaller amount, depending on sysctl parameters),
we have to traverse the whole bind hash table to find out empty bucket.
And while it is not a problem for example for 32k connections, bind()
completion time grows exponentially (since after each successful binding
we have to traverse one bucket more to find empty one) even if we start
each time from random offset inside the hash table.

So, when hash table is full, and we want to add another socket, we have
to traverse the whole table no matter what, so effectivelly this will be
the worst case performance and it will be constant.

Attached picture shows bind() time depending on number of already bound
sockets.

Green area corresponds to the usual binding to zero port process, which
turns on kernel port selection as described above. Red area is the bind
process, when number of reuse-bound sockets is not limited by 64k (or
sysctl parameters). The same exponential growth (hidden by the green
area) before number of ports reaches sysctl limit.

At this time bind hash table has exactly one reuse-enbaled socket in a
bucket, but it is possible that they have different addresses. Actually
kernel selects the first port to try randomly, so at the beginning bind
will take roughly constant time, but with time number of port to check
after random start will increase. And that will have exponential growth,
but because of above random selection, not every next port selection
will necessary take longer time than previous. So we have to consider
the area below in the graph (if you could zoom it, you could find, that
there are many different times placed there), so area can hide another.

Blue area corresponds to the port selection optimization.

This is rather simple design approach: hashtable now maintains (unprecise
and racely updated) number of currently bound sockets, and when number
of such sockets becomes greater than predefined value (I use maximum
port range defined by sysctls), we stop traversing the whole bind hash
table and just stop at first matching bucket after random start. Above
limit roughly corresponds to the case, when bind hash table is full and
we turned on mechanism of allowing to bind more reuse-enabled sockets,
so it does not change behaviour of other sockets.

Signed-off-by: Evgeniy Polyakov <zbr@ioremap.net>
Tested-by: Denys Fedoryschenko <denys@visp.net.lb>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-01-21 14:34:31 -08:00
Eric Dumazet
c25eb3bfb9 net: Convert TCP/DCCP listening hash tables to use RCU
This is the last step to be able to perform full RCU lookups
in __inet_lookup() : After established/timewait tables, we
add RCU lookups to listening hash table.

The only trick here is that a socket of a given type (TCP ipv4,
TCP ipv6, ...) can now flight between two different tables
(established and listening) during a RCU grace period, so we
must use different 'nulls' end-of-chain values for two tables.

We define a large value :

#define LISTENING_NULLS_BASE (1U << 29)

So that slots in listening table are guaranteed to have different
end-of-chain values than slots in established table. A reader can
still detect it finished its lookup in the right chain.

Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-11-23 17:22:55 -08:00
Eric Dumazet
f757fec4b0 net: use net_eq() in INET_MATCH and INET_TW_MATCH
We can avoid some useless instructions if !CONFIG_NET_NS

Because of RCU, we use INET_MATCH or INET_TW_MATCH twice for the found
socket, so thats six instructions less per incoming TCP packet.

Yet another tbench speedup :)

Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-11-21 15:49:19 -08:00
Eric Dumazet
9db66bdcc8 net: convert TCP/DCCP ehash rwlocks to spinlocks
Now TCP & DCCP use RCU lookups, we can convert ehash rwlocks to spinlocks.

/proc/net/tcp and other seq_file 'readers' can safely be converted to 'writers'.

This should speedup writers, since spin_lock()/spin_unlock()
only use one atomic operation instead of two for write_lock()/write_unlock()

Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-11-20 20:39:09 -08:00
Eric Dumazet
5caea4ea70 net: listening_hash get a spinlock per bucket
This patch prepares RCU migration of listening_hash table for
TCP/DCCP protocols.

listening_hash table being small (32 slots per protocol), we add
a spinlock for each slot, instead of a single rwlock for whole table.

This should reduce hold time of readers, and writers concurrency.

Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-11-20 00:40:07 -08:00
Eric Dumazet
3ab5aee7fe net: Convert TCP & DCCP hash tables to use RCU / hlist_nulls
RCU was added to UDP lookups, using a fast infrastructure :
- sockets kmem_cache use SLAB_DESTROY_BY_RCU and dont pay the
  price of call_rcu() at freeing time.
- hlist_nulls permits to use few memory barriers.

This patch uses same infrastructure for TCP/DCCP established
and timewait sockets.

Thanks to SLAB_DESTROY_BY_RCU, no slowdown for applications
using short lived TCP connections. A followup patch, converting
rwlocks to spinlocks will even speedup this case.

__inet_lookup_established() is pretty fast now we dont have to
dirty a contended cache line (read_lock/read_unlock)

Only established and timewait hashtable are converted to RCU
(bind table and listen table are still using traditional locking)

Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-11-16 19:40:17 -08:00
Eric Dumazet
7a9546ee35 net: ib_net pointer should depends on CONFIG_NET_NS
We can shrink size of "struct inet_bind_bucket" by 50%, using
read_pnet() and write_pnet()

Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-11-12 00:54:20 -08:00
KOVACS Krisztian
23542618de inet: Don't lookup the socket if there's a socket attached to the skb
Use the socket cached in the skb if it's present.

Signed-off-by: KOVACS Krisztian <hidden@sch.bme.hu>
Acked-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-10-07 12:41:01 -07:00
Arnaldo Carvalho de Melo
9a1f27c480 inet_hashtables: Add inet_lookup_skb helpers
To be able to use the cached socket reference in the skb during input
processing we add a new set of lookup functions that receive the skb on
their argument list.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: KOVACS Krisztian <hidden@sch.bme.hu>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-10-07 11:41:57 -07:00
Pavel Emelyanov
0b4419162a netns: introduce the net_hash_mix "salt" for hashes
There are many possible ways to add this "salt", thus I made this
patch to be the last in the series to change it if required.

Currently I propose to use the struct net pointer itself as this 
salt, but since this pointer is most often cache-line aligned, shift 
this right to eliminate the bits, that are most often zeroed.

After this, simply add this mix to prepared hashfn-s.

For CONFIG_NET_NS=n case this salt is 0 and no changes in hashfn
appear.

Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-06-16 17:14:11 -07:00
Pavel Emelyanov
2086a65078 inet: add struct net argument to inet_lhashfn
Listening-on-one-port sockets in many namespaces produce long 
chains in the listening_hash-es, so prepare the inet_lhashfn to 
take struct net into account.

Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-06-16 17:13:08 -07:00
Pavel Emelyanov
7f635ab71e inet: add struct net argument to inet_bhashfn
Binding to some port in many namespaces may create too long
chains in bhash-es, so prepare the hashfn to take struct net
into account.

Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-06-16 17:12:49 -07:00
Pavel Emelyanov
53083773dc [INET]: Uninline the __inet_inherit_port call.
This deblats ~200 bytes when ipv6 and dccp are 'y'.

Besides, this will ease compilation issues for patches
I'm working on to make inet hash tables more scalable 
wrt net namespaces.

Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-04-17 23:18:15 -07:00
Pavel Emelyanov
e56d8b8a2e [INET]: Drop the inet_inherit_port() call.
As I can see from the code, two places (tcp_v6_syn_recv_sock and
dccp_v6_request_recv_sock) that call this one already run with
BHs disabled, so it's safe to call __inet_inherit_port there.

Besides (in case I missed smth with code review) the calltrace
tcp_v6_syn_recv_sock
 `- tcp_v4_syn_recv_sock
     `- __inet_inherit_port
and the similar for DCCP are valid, but assumes BHs to be disabled.

Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-04-17 23:17:34 -07:00
YOSHIFUJI Hideaki
3b1e0a655f [NET] NETNS: Omit sock->sk_net without CONFIG_NET_NS.
Introduce per-sock inlines: sock_net(), sock_net_set()
and per-inet_timewait_sock inlines: twsk_net(), twsk_net_set().
Without CONFIG_NET_NS, no namespace other than &init_net exists.
Let's explicitly define them to help compiler optimizations.

Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
2008-03-26 04:39:55 +09:00
Pavel Emelyanov
39d8cda76c [SOCK]: Add udp_hash member to struct proto.
Inspired by the commit ab1e0a13 ([SOCK] proto: Add hashinfo member to 
struct proto) from Arnaldo, I made similar thing for UDP/-Lite IPv4 
and -v6 protocols.

The result is not that exciting, but it removes some levels of
indirection in udpxxx_get_port and saves some space in code and text.

The first step is to union existing hashinfo and new udp_hash on the
struct proto and give a name to this union, since future initialization 
of tcpxxx_prot, dccp_vx_protinfo and udpxxx_protinfo will cause gcc 
warning about inability to initialize anonymous member this way.

Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-03-22 16:50:58 -07:00
Pavel Emelyanov
5d8c0aa943 [INET]: Fix accidentally broken inet(6)_hash_connect's port offset calculations.
The port offset calculations depend on the protocol family, but, as
Adrian noticed, I broke this logic with the commit

	5ee31fc1ec
	[INET]: Consolidate inet(6)_hash_connect.

Return this logic back, by passing the port offset directly into the
consolidated function.

Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Noticed-by: Adrian Bunk <bunk@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-02-05 03:14:44 -08:00
Arnaldo Carvalho de Melo
ab1e0a13d7 [SOCK] proto: Add hashinfo member to struct proto
This way we can remove TCP and DCCP specific versions of

sk->sk_prot->get_port: both v4 and v6 use inet_csk_get_port
sk->sk_prot->hash:     inet_hash is directly used, only v6 need
                       a specific version to deal with mapped sockets
sk->sk_prot->unhash:   both v4 and v6 use inet_hash directly

struct inet_connection_sock_af_ops also gets a new member, bind_conflict, so
that inet_csk_get_port can find the per family routine.

Now only the lookup routines receive as a parameter a struct inet_hashtable.

With this we further reuse code, reducing the difference among INET transport
protocols.

Eventually work has to be done on UDP and SCTP to make them share this
infrastructure and get as a bonus inet_diag interfaces so that iproute can be
used with these protocols.

net-2.6/net/ipv4/inet_hashtables.c:
  struct proto			     |   +8
  struct inet_connection_sock_af_ops |   +8
 2 structs changed
  __inet_hash_nolisten               |  +18
  __inet_hash                        | -210
  inet_put_port                      |   +8
  inet_bind_bucket_create            |   +1
  __inet_hash_connect                |   -8
 5 functions changed, 27 bytes added, 218 bytes removed, diff: -191

net-2.6/net/core/sock.c:
  proto_seq_show                     |   +3
 1 function changed, 3 bytes added, diff: +3

net-2.6/net/ipv4/inet_connection_sock.c:
  inet_csk_get_port                  |  +15
 1 function changed, 15 bytes added, diff: +15

net-2.6/net/ipv4/tcp.c:
  tcp_set_state                      |   -7
 1 function changed, 7 bytes removed, diff: -7

net-2.6/net/ipv4/tcp_ipv4.c:
  tcp_v4_get_port                    |  -31
  tcp_v4_hash                        |  -48
  tcp_v4_destroy_sock                |   -7
  tcp_v4_syn_recv_sock               |   -2
  tcp_unhash                         | -179
 5 functions changed, 267 bytes removed, diff: -267

net-2.6/net/ipv6/inet6_hashtables.c:
  __inet6_hash |   +8
 1 function changed, 8 bytes added, diff: +8

net-2.6/net/ipv4/inet_hashtables.c:
  inet_unhash                        | +190
  inet_hash                          | +242
 2 functions changed, 432 bytes added, diff: +432

vmlinux:
 16 functions changed, 485 bytes added, 492 bytes removed, diff: -7

/home/acme/git/net-2.6/net/ipv6/tcp_ipv6.c:
  tcp_v6_get_port                    |  -31
  tcp_v6_hash                        |   -7
  tcp_v6_syn_recv_sock               |   -9
 3 functions changed, 47 bytes removed, diff: -47

/home/acme/git/net-2.6/net/dccp/proto.c:
  dccp_destroy_sock                  |   -7
  dccp_unhash                        | -179
  dccp_hash                          |  -49
  dccp_set_state                     |   -7
  dccp_done                          |   +1
 5 functions changed, 1 bytes added, 242 bytes removed, diff: -241

/home/acme/git/net-2.6/net/dccp/ipv4.c:
  dccp_v4_get_port                   |  -31
  dccp_v4_request_recv_sock          |   -2
 2 functions changed, 33 bytes removed, diff: -33

/home/acme/git/net-2.6/net/dccp/ipv6.c:
  dccp_v6_get_port                   |  -31
  dccp_v6_hash                       |   -7
  dccp_v6_request_recv_sock          |   +5
 3 functions changed, 5 bytes added, 38 bytes removed, diff: -33

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-02-03 04:28:52 -08:00
Pavel Emelyanov
c67499c0e7 [NETNS]: Tcp-v4 sockets per-net lookup.
Add a net argument to inet_lookup and propagate it further
into lookup calls. Plus tune the __inet_check_established.

The dccp and inet_diag, which use that lookup functions
pass the init_net into them.

Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-01-31 19:28:19 -08:00
Pavel Emelyanov
941b1d22cc [NETNS]: Make bind buckets live in net namespaces.
This tags the inet_bind_bucket struct with net pointer,
initializes it during creation and makes a filtering
during lookup.

A better hashfn, that takes the net into account is to
be done in the future, but currently all bind buckets
with similar port will be in one hash chain.

Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-01-31 19:28:18 -08:00
Pavel Emelyanov
5ee31fc1ec [INET]: Consolidate inet(6)_hash_connect.
These two functions are the same except for what they call
to "check_established" and "hash" for a socket.

This saves half-a-kilo for ipv4 and ipv6.

 add/remove: 1/0 grow/shrink: 1/4 up/down: 582/-1128 (-546)
 function                                     old     new   delta
 __inet_hash_connect                            -     577    +577
 arp_ignore                                   108     113      +5
 static.hint                                    8       4      -4
 rt_worker_func                               376     372      -4
 inet6_hash_connect                           584      25    -559
 inet_hash_connect                            586      25    -561

Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-01-31 19:28:17 -08:00
Eric Dumazet
65f7651788 [NET]: prot_inuse cleanups and optimizations
1) Cleanups (all functions are prefixed by sock_prot_inuse)

sock_prot_inc_use(prot) -> sock_prot_inuse_add(prot,-1)
sock_prot_dec_use(prot) -> sock_prot_inuse_add(prot,-1)
sock_prot_inuse()       -> sock_prot_inuse_get()

New functions :

sock_prot_inuse_init() and sock_prot_inuse_free() to abstract pcounter use.

2) if CONFIG_PROC_FS=n, we can zap 'inuse' member from "struct proto",
since nobody wants to read the inuse value.

This saves 1372 bytes on i386/SMP and some cpu cycles.

Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-01-28 15:00:36 -08:00
Pavel Emelyanov
77a5ba55da [INET]: Uninline the __inet_lookup_established function.
This is -700 bytes from the net/ipv4/built-in.o

add/remove: 1/0 grow/shrink: 1/3 up/down: 340/-1040 (-700)
function                                     old     new   delta
__inet_lookup_established                      -     339    +339
tcp_sacktag_write_queue                     2254    2255      +1
tcp_v4_err                                  1304     973    -331
tcp_v4_rcv                                  2089    1744    -345
tcp_v4_do_rcv                                826     462    -364

Exporting is for dccp module (used via e.g. inet_lookup).

Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-01-28 14:59:27 -08:00
Pavel Emelyanov
152da81deb [INET]: Uninline the __inet_hash function.
This one is used in quite many places in the networking code and
seems to big to be inline.

After the patch net/ipv4/build-in.o loses ~650 bytes:
add/remove: 2/0 grow/shrink: 0/5 up/down: 461/-1114 (-653)
function                                     old     new   delta
__inet_hash_nolisten                           -     282    +282
__inet_hash                                    -     179    +179
tcp_sacktag_write_queue                     2255    2254      -1
__inet_lookup_listener                       284     274     -10
tcp_v4_syn_recv_sock                         755     493    -262
tcp_v4_hash                                  389      35    -354
inet_hash_connect                           1086     599    -487

This version addresses the issue pointed by Eric, that
while being inline this function was optimized by gcc
in respect to the 'listen_possible' argument.

Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-01-28 14:59:26 -08:00
Pavel Emelyanov
218ad12f42 [IPV4]: Fix memory leak in inet_hashtables.h when NUMA is on
The inet_ehash_locks_alloc() looks like this:

#ifdef CONFIG_NUMA
	if (size > PAGE_SIZE)
		x = vmalloc(...);
	else
#endif
		x = kmalloc(...);

Unlike it, the inet_ehash_locks_alloc() looks like this:

#ifdef CONFIG_NUMA
	if (size > PAGE_SIZE)
		vfree(x);
	else
#else
		kfree(x);
#endif

The error is obvious - if the NUMA is on and the size
is less than the PAGE_SIZE we leak the pointer (kfree is
inside the #else branch).

Compiler doesn't warn us because after the kfree(x) there's
a "x = NULL" assignment, so here's another (minor?) bug: we 
don't set x to NULL under certain circumstances.

Boring explanation, I know... Patch explains it better.

Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2007-11-26 20:23:31 +08:00
Eric Dumazet
9e4505c459 [INET]: Add a missing include <linux/vmalloc.h> to inet_hashtables.h
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-11-10 21:18:39 -08:00
Eric Dumazet
230140cffa [INET]: Remove per bucket rwlock in tcp/dccp ehash table.
As done two years ago on IP route cache table (commit
22c047ccbc) , 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>
2007-11-07 04:15:11 -08:00
Vlad Yasevich
fee9dee730 [UDP]: Make use of inet_iif() when doing socket lookups.
UDP currently uses skb->dev->ifindex which may provide the wrong
information when the socket bound to a specific interface.
This patch makes inet_iif() accessible to UDP and makes UDP use it.

The scenario we are trying to fix is when a client is running on
the same system and the server and both client and server bind to
a non-loopback device.

Signed-off-by: Vlad Yasevich <vladislav.yasevich@hp.com>
Acked-by: David L Stevens <dlstevens@us.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-25 18:54:46 -07:00
Stephen Hemminger
cfcabdcc2d [NET]: sparse warning fixes
Fix a bunch of sparse warnings. Mostly about 0 used as
NULL pointer, and shadowed variable declarations.
One notable case was that hash size should have been unsigned.

Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-10 16:54:48 -07:00
Eric Dumazet
dbca9b2750 [NET]: change layout of ehash table
ehash table layout is currently this one :

First half of this table is used by sockets not in TIME_WAIT state
Second half of it is used by sockets in TIME_WAIT state.

This is non optimal because of for a given hash or socket, the two chain heads 
are located in separate cache lines.
Moreover the locks of the second half are never used.

If instead of this halving, we use two list heads in inet_ehash_bucket instead 
of only one, we probably can avoid one cache miss, and reduce ram usage, 
particularly if sizeof(rwlock_t) is big (various CONFIG_DEBUG_SPINLOCK, 
CONFIG_DEBUG_LOCK_ALLOC settings). So we still halves the table but we keep 
together related chains to speedup lookups and socket state change.

In this patch I did not try to align struct inet_ehash_bucket, but a future 
patch could try to make this structure have a convenient size (a power of two 
or a multiple of L1_CACHE_SIZE).
I guess rwlock will just vanish as soon as RCU is plugged into ehash :) , so 
maybe we dont need to scratch our heads to align the bucket...

Note : In case struct inet_ehash_bucket is not a power of two, we could 
probably change alloc_large_system_hash() (in case it use __get_free_pages()) 
to free the unused space. It currently allocates a big zone, but the last 
quarter of it could be freed. Again, this should be a temporary 'problem'.

Patch tested on ipv4 tcp only, but should be OK for IPV6 and DCCP.

Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-02-08 14:16:46 -08:00
Christoph Lameter
e18b890bb0 [PATCH] slab: remove kmem_cache_t
Replace all uses of kmem_cache_t with struct kmem_cache.

The patch was generated using the following script:

	#!/bin/sh
	#
	# Replace one string by another in all the kernel sources.
	#

	set -e

	for file in `find * -name "*.c" -o -name "*.h"|xargs grep -l $1`; do
		quilt add $file
		sed -e "1,\$s/$1/$2/g" $file >/tmp/$$
		mv /tmp/$$ $file
		quilt refresh
	done

The script was run like this

	sh replace kmem_cache_t "struct kmem_cache"

Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-07 08:39:25 -08:00
Al Viro
fb99c848e5 [IPV4]: annotate inet_lookup() and friends
inet_lookup() annotated along with helper functions (__inet_lookup(),
__inet_lookup_established(), inet_lookup_established(),
inet_lookup_listener(), __inet_lookup_listener() and inet_ehashfn())

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
2006-09-28 18:02:26 -07:00
Al Viro
4f765d842f [IPV4]: INET_MATCH() annotations
INET_MATCH() and friends depend on an interesting set of kludges:
	* there's a pair of adjacent fields in struct inet_sock - __be16 dport
followed by __u16 num.  We want to search by pair, so we combine the keys into
a single 32bit value and compare with 32bit value read from &...->dport.
	* on 64bit targets we combine comparisons with pair of adjacent __be32
fields in the same way.

Make sure that we don't mix those values with anything else and that pairs
we form them from have correct types.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
2006-09-28 18:02:25 -07:00
Herbert Xu
8f491069b4 [IPV4]: Use network-order dport for all visible inet_lookup_*
Right now most inet_lookup_* functions take a host-order hnum instead
of a network-order dport because that's how it is represented
internally.

This means that users of these functions have to be careful about
using the right byte-order.  To add more confusion, inet_lookup takes
a network-order dport unlike all other functions.

So this patch changes all visible inet_lookup functions to take a
dport and move all dport->hnum conversion inside them.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
2006-09-22 14:54:14 -07:00
Herbert Xu
99a92ff504 [IPV4]: Uninline inet_lookup_listener
By modern standards this function is way too big to be inlined.  It's
even bigger than __inet_lookup_listener :)

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
2006-09-22 14:54:11 -07:00
David Woodhouse
62c4f0a2d5 Don't include linux/config.h from anywhere else in include/
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
2006-04-26 12:56:16 +01:00
Arnaldo Carvalho de Melo
14c850212e [INET_SOCK]: Move struct inet_sock & helper functions to net/inet_sock.h
To help in reducing the number of include dependencies, several files were
touched as they were getting needed headers indirectly for stuff they use.

Thanks also to Alan Menegotto for pointing out that net/dccp/proto.c had
linux/dccp.h include twice.

Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2006-01-03 13:11:21 -08:00
Arnaldo Carvalho de Melo
a7f5e7f164 [INET]: Generalise tcp_v4_hash_connect
Renaming it to inet_hash_connect, making it possible to ditch
dccp_v4_hash_connect and share the same code with TCP instead.

Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2006-01-03 13:10:55 -08:00
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
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
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
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