2005-08-10 07:09:30 +04:00
|
|
|
/*
|
|
|
|
* INET An implementation of the TCP/IP protocol suite for the LINUX
|
|
|
|
* operating system. INET is implemented using the BSD Socket
|
|
|
|
* interface as the means of communication with the user level.
|
|
|
|
*
|
|
|
|
* Definitions for a generic INET TIMEWAIT sock
|
|
|
|
*
|
|
|
|
* From code originally in net/tcp.h
|
|
|
|
*
|
|
|
|
* This program is free software; you can redistribute it and/or
|
|
|
|
* modify it under the terms of the GNU General Public License
|
|
|
|
* as published by the Free Software Foundation; either version
|
|
|
|
* 2 of the License, or (at your option) any later version.
|
|
|
|
*/
|
|
|
|
#ifndef _INET_TIMEWAIT_SOCK_
|
|
|
|
#define _INET_TIMEWAIT_SOCK_
|
|
|
|
|
|
|
|
|
|
|
|
#include <linux/list.h>
|
2005-10-11 08:25:23 +04:00
|
|
|
#include <linux/module.h>
|
2005-08-10 07:44:40 +04:00
|
|
|
#include <linux/timer.h>
|
2005-08-10 07:09:30 +04:00
|
|
|
#include <linux/types.h>
|
2005-08-10 07:44:40 +04:00
|
|
|
#include <linux/workqueue.h>
|
2005-08-10 07:09:30 +04:00
|
|
|
|
2005-12-27 07:43:12 +03:00
|
|
|
#include <net/inet_sock.h>
|
2005-08-10 07:09:30 +04:00
|
|
|
#include <net/sock.h>
|
|
|
|
#include <net/tcp_states.h>
|
2005-12-14 10:25:19 +03:00
|
|
|
#include <net/timewait_sock.h>
|
2005-08-10 07:09:30 +04:00
|
|
|
|
|
|
|
#include <asm/atomic.h>
|
|
|
|
|
2005-08-10 07:44:40 +04:00
|
|
|
struct inet_hashinfo;
|
|
|
|
|
|
|
|
#define INET_TWDR_RECYCLE_SLOTS_LOG 5
|
|
|
|
#define INET_TWDR_RECYCLE_SLOTS (1 << INET_TWDR_RECYCLE_SLOTS_LOG)
|
|
|
|
|
|
|
|
/*
|
|
|
|
* If time > 4sec, it is "slow" path, no recycling is required,
|
|
|
|
* so that we select tick to get range about 4 seconds.
|
|
|
|
*/
|
|
|
|
#if HZ <= 16 || HZ > 4096
|
|
|
|
# error Unsupported: HZ <= 16 or HZ > 4096
|
|
|
|
#elif HZ <= 32
|
|
|
|
# define INET_TWDR_RECYCLE_TICK (5 + 2 - INET_TWDR_RECYCLE_SLOTS_LOG)
|
|
|
|
#elif HZ <= 64
|
|
|
|
# define INET_TWDR_RECYCLE_TICK (6 + 2 - INET_TWDR_RECYCLE_SLOTS_LOG)
|
|
|
|
#elif HZ <= 128
|
|
|
|
# define INET_TWDR_RECYCLE_TICK (7 + 2 - INET_TWDR_RECYCLE_SLOTS_LOG)
|
|
|
|
#elif HZ <= 256
|
|
|
|
# define INET_TWDR_RECYCLE_TICK (8 + 2 - INET_TWDR_RECYCLE_SLOTS_LOG)
|
|
|
|
#elif HZ <= 512
|
|
|
|
# define INET_TWDR_RECYCLE_TICK (9 + 2 - INET_TWDR_RECYCLE_SLOTS_LOG)
|
|
|
|
#elif HZ <= 1024
|
|
|
|
# define INET_TWDR_RECYCLE_TICK (10 + 2 - INET_TWDR_RECYCLE_SLOTS_LOG)
|
|
|
|
#elif HZ <= 2048
|
|
|
|
# define INET_TWDR_RECYCLE_TICK (11 + 2 - INET_TWDR_RECYCLE_SLOTS_LOG)
|
|
|
|
#else
|
|
|
|
# define INET_TWDR_RECYCLE_TICK (12 + 2 - INET_TWDR_RECYCLE_SLOTS_LOG)
|
|
|
|
#endif
|
|
|
|
|
|
|
|
/* TIME_WAIT reaping mechanism. */
|
|
|
|
#define INET_TWDR_TWKILL_SLOTS 8 /* Please keep this a power of 2. */
|
|
|
|
|
|
|
|
#define INET_TWDR_TWKILL_QUOTA 100
|
|
|
|
|
|
|
|
struct inet_timewait_death_row {
|
|
|
|
/* Short-time timewait calendar */
|
|
|
|
int twcal_hand;
|
2007-03-06 00:32:48 +03:00
|
|
|
unsigned long twcal_jiffie;
|
2005-08-10 07:44:40 +04:00
|
|
|
struct timer_list twcal_timer;
|
|
|
|
struct hlist_head twcal_row[INET_TWDR_RECYCLE_SLOTS];
|
|
|
|
|
|
|
|
spinlock_t death_lock;
|
|
|
|
int tw_count;
|
|
|
|
int period;
|
|
|
|
u32 thread_slots;
|
|
|
|
struct work_struct twkill_work;
|
|
|
|
struct timer_list tw_timer;
|
|
|
|
int slot;
|
|
|
|
struct hlist_head cells[INET_TWDR_TWKILL_SLOTS];
|
|
|
|
struct inet_hashinfo *hashinfo;
|
|
|
|
int sysctl_tw_recycle;
|
|
|
|
int sysctl_max_tw_buckets;
|
|
|
|
};
|
|
|
|
|
2005-08-10 07:45:03 +04:00
|
|
|
extern void inet_twdr_hangman(unsigned long data);
|
2006-11-22 17:55:48 +03:00
|
|
|
extern void inet_twdr_twkill_work(struct work_struct *work);
|
2005-08-10 07:45:03 +04:00
|
|
|
extern void inet_twdr_twcal_tick(unsigned long data);
|
|
|
|
|
2005-08-10 07:09:30 +04:00
|
|
|
#if (BITS_PER_LONG == 64)
|
|
|
|
#define INET_TIMEWAIT_ADDRCMP_ALIGN_BYTES 8
|
|
|
|
#else
|
|
|
|
#define INET_TIMEWAIT_ADDRCMP_ALIGN_BYTES 4
|
|
|
|
#endif
|
|
|
|
|
|
|
|
struct inet_bind_bucket;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* This is a TIME_WAIT sock. It works around the memory consumption
|
|
|
|
* problems of sockets in such a state on heavily loaded servers, but
|
|
|
|
* without violating the protocol specification.
|
|
|
|
*/
|
|
|
|
struct inet_timewait_sock {
|
|
|
|
/*
|
|
|
|
* Now struct sock also uses sock_common, so please just
|
|
|
|
* don't add nothing before this first member (__tw_common) --acme
|
|
|
|
*/
|
|
|
|
struct sock_common __tw_common;
|
|
|
|
#define tw_family __tw_common.skc_family
|
|
|
|
#define tw_state __tw_common.skc_state
|
|
|
|
#define tw_reuse __tw_common.skc_reuse
|
|
|
|
#define tw_bound_dev_if __tw_common.skc_bound_dev_if
|
|
|
|
#define tw_node __tw_common.skc_node
|
|
|
|
#define tw_bind_node __tw_common.skc_bind_node
|
|
|
|
#define tw_refcnt __tw_common.skc_refcnt
|
[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>
2005-10-04 01:13:38 +04:00
|
|
|
#define tw_hash __tw_common.skc_hash
|
2005-08-10 07:09:30 +04:00
|
|
|
#define tw_prot __tw_common.skc_prot
|
2007-09-12 13:58:02 +04:00
|
|
|
#define tw_net __tw_common.skc_net
|
2008-02-03 15:08:26 +03:00
|
|
|
int tw_timeout;
|
2005-08-10 07:09:30 +04:00
|
|
|
volatile unsigned char tw_substate;
|
|
|
|
/* 3 bits hole, try to pack */
|
|
|
|
unsigned char tw_rcv_wscale;
|
|
|
|
/* Socket demultiplex comparisons on incoming packets. */
|
|
|
|
/* these five are in inet_sock */
|
2006-09-28 05:43:50 +04:00
|
|
|
__be16 tw_sport;
|
|
|
|
__be32 tw_daddr __attribute__((aligned(INET_TIMEWAIT_ADDRCMP_ALIGN_BYTES)));
|
|
|
|
__be32 tw_rcv_saddr;
|
|
|
|
__be16 tw_dport;
|
2005-08-10 07:09:30 +04:00
|
|
|
__u16 tw_num;
|
|
|
|
/* And these are ours. */
|
|
|
|
__u8 tw_ipv6only:1;
|
2005-12-14 10:23:09 +03:00
|
|
|
/* 15 bits hole, try to pack */
|
|
|
|
__u16 tw_ipv6_offset;
|
2005-08-10 07:09:30 +04:00
|
|
|
unsigned long tw_ttd;
|
|
|
|
struct inet_bind_bucket *tw_tb;
|
|
|
|
struct hlist_node tw_death_node;
|
|
|
|
};
|
|
|
|
|
|
|
|
static inline void inet_twsk_add_node(struct inet_timewait_sock *tw,
|
|
|
|
struct hlist_head *list)
|
|
|
|
{
|
|
|
|
hlist_add_head(&tw->tw_node, list);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void inet_twsk_add_bind_node(struct inet_timewait_sock *tw,
|
|
|
|
struct hlist_head *list)
|
|
|
|
{
|
|
|
|
hlist_add_head(&tw->tw_bind_node, list);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline int inet_twsk_dead_hashed(const struct inet_timewait_sock *tw)
|
|
|
|
{
|
2006-04-29 02:21:23 +04:00
|
|
|
return !hlist_unhashed(&tw->tw_death_node);
|
2005-08-10 07:09:30 +04:00
|
|
|
}
|
|
|
|
|
|
|
|
static inline void inet_twsk_dead_node_init(struct inet_timewait_sock *tw)
|
|
|
|
{
|
|
|
|
tw->tw_death_node.pprev = NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void __inet_twsk_del_dead_node(struct inet_timewait_sock *tw)
|
|
|
|
{
|
|
|
|
__hlist_del(&tw->tw_death_node);
|
|
|
|
inet_twsk_dead_node_init(tw);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline int inet_twsk_del_dead_node(struct inet_timewait_sock *tw)
|
|
|
|
{
|
|
|
|
if (inet_twsk_dead_hashed(tw)) {
|
|
|
|
__inet_twsk_del_dead_node(tw);
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
#define inet_twsk_for_each(tw, node, head) \
|
|
|
|
hlist_for_each_entry(tw, node, head, tw_node)
|
|
|
|
|
|
|
|
#define inet_twsk_for_each_inmate(tw, node, jail) \
|
|
|
|
hlist_for_each_entry(tw, node, jail, tw_death_node)
|
|
|
|
|
|
|
|
#define inet_twsk_for_each_inmate_safe(tw, node, safe, jail) \
|
|
|
|
hlist_for_each_entry_safe(tw, node, safe, jail, tw_death_node)
|
|
|
|
|
|
|
|
static inline struct inet_timewait_sock *inet_twsk(const struct sock *sk)
|
|
|
|
{
|
|
|
|
return (struct inet_timewait_sock *)sk;
|
|
|
|
}
|
|
|
|
|
2006-09-28 05:44:10 +04:00
|
|
|
static inline __be32 inet_rcv_saddr(const struct sock *sk)
|
2005-08-10 07:09:30 +04:00
|
|
|
{
|
|
|
|
return likely(sk->sk_state != TCP_TIME_WAIT) ?
|
|
|
|
inet_sk(sk)->rcv_saddr : inet_twsk(sk)->tw_rcv_saddr;
|
|
|
|
}
|
|
|
|
|
2007-12-21 02:32:54 +03:00
|
|
|
extern void inet_twsk_put(struct inet_timewait_sock *tw);
|
2005-08-10 07:09:46 +04:00
|
|
|
|
2005-08-10 07:09:59 +04:00
|
|
|
extern struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk,
|
|
|
|
const int state);
|
|
|
|
|
2005-08-10 07:09:46 +04:00
|
|
|
extern void __inet_twsk_hashdance(struct inet_timewait_sock *tw,
|
|
|
|
struct sock *sk,
|
|
|
|
struct inet_hashinfo *hashinfo);
|
2005-08-10 07:45:03 +04:00
|
|
|
|
|
|
|
extern void inet_twsk_schedule(struct inet_timewait_sock *tw,
|
|
|
|
struct inet_timewait_death_row *twdr,
|
|
|
|
const int timeo, const int timewait_len);
|
|
|
|
extern void inet_twsk_deschedule(struct inet_timewait_sock *tw,
|
|
|
|
struct inet_timewait_death_row *twdr);
|
2008-03-25 20:26:21 +03:00
|
|
|
|
|
|
|
static inline
|
|
|
|
struct net *twsk_net(const struct inet_timewait_sock *twsk)
|
|
|
|
{
|
|
|
|
#ifdef CONFIG_NET_NS
|
|
|
|
return twsk->tw_net;
|
|
|
|
#else
|
|
|
|
return &init_net;
|
|
|
|
#endif
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline
|
|
|
|
void twsk_net_set(struct inet_timewait_sock *twsk, const struct net *net)
|
|
|
|
{
|
|
|
|
#ifdef CONFIG_NET_NS
|
|
|
|
twsk->tw_net = net;
|
|
|
|
#endif
|
|
|
|
}
|
2005-08-10 07:09:30 +04:00
|
|
|
#endif /* _INET_TIMEWAIT_SOCK_ */
|