mirror of
https://github.com/torvalds/linux.git
synced 2024-11-05 11:32:04 +00:00
8e5eb54d30
sk->sk_refcnt is dirtied for every TCP/UDP incoming packet.
This is a performance issue if multiple cpus hit a common socket,
or multiple sockets are chained due to SO_REUSEPORT.
By moving sk_refcnt 8 bytes further, first 128 bytes of sockets
are mostly read. As they contain the lookup keys, this has
a considerable performance impact, as cpus can cache them.
These 8 bytes are not wasted, we use them as a place holder
for various fields, depending on the socket type.
Tested:
SYN flood hitting a 16 RX queues NIC.
TCP listener using 16 sockets and SO_REUSEPORT
and SO_INCOMING_CPU for proper siloing.
Could process 6.0 Mpps SYN instead of 4.2 Mpps
Kernel profile looked like :
11.68% [kernel] [k] sha_transform
6.51% [kernel] [k] __inet_lookup_listener
5.07% [kernel] [k] __inet_lookup_established
4.15% [kernel] [k] memcpy_erms
3.46% [kernel] [k] ipt_do_table
2.74% [kernel] [k] fib_table_lookup
2.54% [kernel] [k] tcp_make_synack
2.34% [kernel] [k] tcp_conn_request
2.05% [kernel] [k] __netif_receive_skb_core
2.03% [kernel] [k] kmem_cache_alloc
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
143 lines
4.1 KiB
C
143 lines
4.1 KiB
C
/*
|
|
* 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/kmemcheck.h>
|
|
#include <linux/list.h>
|
|
#include <linux/timer.h>
|
|
#include <linux/types.h>
|
|
#include <linux/workqueue.h>
|
|
|
|
#include <net/inet_sock.h>
|
|
#include <net/sock.h>
|
|
#include <net/tcp_states.h>
|
|
#include <net/timewait_sock.h>
|
|
|
|
#include <linux/atomic.h>
|
|
|
|
struct inet_hashinfo;
|
|
|
|
struct inet_timewait_death_row {
|
|
atomic_t tw_count;
|
|
|
|
struct inet_hashinfo *hashinfo ____cacheline_aligned_in_smp;
|
|
int sysctl_tw_recycle;
|
|
int sysctl_max_tw_buckets;
|
|
};
|
|
|
|
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_ipv6only __tw_common.skc_ipv6only
|
|
#define tw_bound_dev_if __tw_common.skc_bound_dev_if
|
|
#define tw_node __tw_common.skc_nulls_node
|
|
#define tw_bind_node __tw_common.skc_bind_node
|
|
#define tw_refcnt __tw_common.skc_refcnt
|
|
#define tw_hash __tw_common.skc_hash
|
|
#define tw_prot __tw_common.skc_prot
|
|
#define tw_net __tw_common.skc_net
|
|
#define tw_daddr __tw_common.skc_daddr
|
|
#define tw_v6_daddr __tw_common.skc_v6_daddr
|
|
#define tw_rcv_saddr __tw_common.skc_rcv_saddr
|
|
#define tw_v6_rcv_saddr __tw_common.skc_v6_rcv_saddr
|
|
#define tw_dport __tw_common.skc_dport
|
|
#define tw_num __tw_common.skc_num
|
|
#define tw_cookie __tw_common.skc_cookie
|
|
#define tw_dr __tw_common.skc_tw_dr
|
|
|
|
int tw_timeout;
|
|
volatile unsigned char tw_substate;
|
|
unsigned char tw_rcv_wscale;
|
|
|
|
/* Socket demultiplex comparisons on incoming packets. */
|
|
/* these three are in inet_sock */
|
|
__be16 tw_sport;
|
|
kmemcheck_bitfield_begin(flags);
|
|
/* And these are ours. */
|
|
unsigned int tw_kill : 1,
|
|
tw_transparent : 1,
|
|
tw_flowlabel : 20,
|
|
tw_pad : 2, /* 2 bits hole */
|
|
tw_tos : 8;
|
|
kmemcheck_bitfield_end(flags);
|
|
struct timer_list tw_timer;
|
|
struct inet_bind_bucket *tw_tb;
|
|
};
|
|
#define tw_tclass tw_tos
|
|
|
|
static inline struct inet_timewait_sock *inet_twsk(const struct sock *sk)
|
|
{
|
|
return (struct inet_timewait_sock *)sk;
|
|
}
|
|
|
|
void inet_twsk_free(struct inet_timewait_sock *tw);
|
|
void inet_twsk_put(struct inet_timewait_sock *tw);
|
|
|
|
void inet_twsk_bind_unhash(struct inet_timewait_sock *tw,
|
|
struct inet_hashinfo *hashinfo);
|
|
|
|
struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk,
|
|
struct inet_timewait_death_row *dr,
|
|
const int state);
|
|
|
|
void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
|
|
struct inet_hashinfo *hashinfo);
|
|
|
|
void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo,
|
|
bool rearm);
|
|
|
|
static void inline inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo)
|
|
{
|
|
__inet_twsk_schedule(tw, timeo, false);
|
|
}
|
|
|
|
static void inline inet_twsk_reschedule(struct inet_timewait_sock *tw, int timeo)
|
|
{
|
|
__inet_twsk_schedule(tw, timeo, true);
|
|
}
|
|
|
|
void inet_twsk_deschedule_put(struct inet_timewait_sock *tw);
|
|
|
|
void inet_twsk_purge(struct inet_hashinfo *hashinfo,
|
|
struct inet_timewait_death_row *twdr, int family);
|
|
|
|
static inline
|
|
struct net *twsk_net(const struct inet_timewait_sock *twsk)
|
|
{
|
|
return read_pnet(&twsk->tw_net);
|
|
}
|
|
|
|
static inline
|
|
void twsk_net_set(struct inet_timewait_sock *twsk, struct net *net)
|
|
{
|
|
write_pnet(&twsk->tw_net, net);
|
|
}
|
|
#endif /* _INET_TIMEWAIT_SOCK_ */
|