Minki/linux
1
0
Fork 1
mirror of https://github.com/torvalds/linux.git synced 2024-12-19 17:41:29 +00:00
Code Issues Packages Projects Releases Wiki Activity
61c9eaf900
linux/include/net/udp.h
Eric Dumazet 645ca708f9 udp: introduce struct udp_table and multiple spinlocks 
UDP sockets are hashed in a 128 slots hash table.

This hash table is protected by *one* rwlock.

This rwlock is readlocked each time an incoming UDP message is handled.

This rwlock is writelocked each time a socket must be inserted in
hash table (bind time), or deleted from this table (close time)

This is not scalable on SMP machines :

1) Even in read mode, lock() and unlock() are atomic operations and
 must dirty a contended cache line, shared by all cpus.

2) A writer might be starved if many readers are 'in flight'. This can
 happen on a machine with some NIC receiving many UDP messages. User
 process can be delayed a long time at socket creation/dismantle time.

This patch prepares RCU migration, by introducing 'struct udp_table
and struct udp_hslot', and using one spinlock per chain, to reduce
contention on central rwlock.

Introducing one spinlock per chain reduces latencies, for port
randomization on heavily loaded UDP servers. This also speedup
bindings to specific ports.

udp_lib_unhash() was uninlined, becoming to big.

Some cleanups were done to ease review of following patch
(RCUification of UDP Unicast lookups)

Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-10-29 01:41:45 -07:00

211 lines
6.1 KiB
C
Raw Blame History

/*
* 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 the UDP module.
*
* Version: @(#)udp.h 1.0.2 05/07/93
*
* Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
*
* Fixes:
* Alan Cox : Turned on udp checksums. I don't want to
* chase 'memory corruption' bugs that aren't!
*
* 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 _UDP_H
#define _UDP_H
#include <linux/list.h>
#include <net/inet_sock.h>
#include <net/sock.h>
#include <net/snmp.h>
#include <net/ip.h>
#include <linux/ipv6.h>
#include <linux/seq_file.h>
#include <linux/poll.h>
/**
* struct udp_skb_cb - UDP(-Lite) private variables
*
* @header: private variables used by IPv4/IPv6
* @cscov: checksum coverage length (UDP-Lite only)
* @partial_cov: if set indicates partial csum coverage
*/
struct udp_skb_cb {
union {
struct inet_skb_parm h4;
#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
struct inet6_skb_parm h6;
#endif
} header;
__u16 cscov;
__u8 partial_cov;
};
#define UDP_SKB_CB(__skb) ((struct udp_skb_cb *)((__skb)->cb))
struct udp_hslot {
struct hlist_head head;
spinlock_t lock;
} __attribute__((aligned(2 * sizeof(long))));
struct udp_table {
struct udp_hslot hash[UDP_HTABLE_SIZE];
};
extern struct udp_table udp_table;
extern void udp_table_init(struct udp_table *);
/* Note: this must match 'valbool' in sock_setsockopt */
#define UDP_CSUM_NOXMIT 1
/* Used by SunRPC/xprt layer. */
#define UDP_CSUM_NORCV 2
/* Default, as per the RFC, is to always do csums. */
#define UDP_CSUM_DEFAULT 0
extern struct proto udp_prot;
extern atomic_t udp_memory_allocated;
/* sysctl variables for udp */
extern int sysctl_udp_mem[3];
extern int sysctl_udp_rmem_min;
extern int sysctl_udp_wmem_min;
struct sk_buff;
/*
* Generic checksumming routines for UDP(-Lite) v4 and v6
*/
static inline __sum16 __udp_lib_checksum_complete(struct sk_buff *skb)
{
return __skb_checksum_complete_head(skb, UDP_SKB_CB(skb)->cscov);
}
static inline int udp_lib_checksum_complete(struct sk_buff *skb)
{
return !skb_csum_unnecessary(skb) &&
__udp_lib_checksum_complete(skb);
}
/**
* udp_csum_outgoing - compute UDPv4/v6 checksum over fragments
* @sk: socket we are writing to
* @skb: sk_buff containing the filled-in UDP header
* (checksum field must be zeroed out)
*/
static inline __wsum udp_csum_outgoing(struct sock *sk, struct sk_buff *skb)
{
__wsum csum = csum_partial(skb_transport_header(skb),
sizeof(struct udphdr), 0);
skb_queue_walk(&sk->sk_write_queue, skb) {
csum = csum_add(csum, skb->csum);
}
return csum;
}
/* hash routines shared between UDPv4/6 and UDP-Litev4/6 */
static inline void udp_lib_hash(struct sock *sk)
{
BUG();
}
extern void udp_lib_unhash(struct sock *sk);
static inline void udp_lib_close(struct sock *sk, long timeout)
{
sk_common_release(sk);
}
extern int udp_lib_get_port(struct sock *sk, unsigned short snum,
int (*)(const struct sock*,const struct sock*));
/* net/ipv4/udp.c */
extern int udp_get_port(struct sock *sk, unsigned short snum,
int (*saddr_cmp)(const struct sock *, const struct sock *));
extern void udp_err(struct sk_buff *, u32);
extern int udp_sendmsg(struct kiocb *iocb, struct sock *sk,
struct msghdr *msg, size_t len);
extern void udp_flush_pending_frames(struct sock *sk);
extern int udp_rcv(struct sk_buff *skb);
extern int udp_ioctl(struct sock *sk, int cmd, unsigned long arg);
extern int udp_disconnect(struct sock *sk, int flags);
extern unsigned int udp_poll(struct file *file, struct socket *sock,
poll_table *wait);
extern int udp_lib_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen);
extern int udp_lib_setsockopt(struct sock *sk, int level, int optname,
char __user *optval, int optlen,
int (*push_pending_frames)(struct sock *));
extern struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
__be32 daddr, __be16 dport,
int dif);
/*
* SNMP statistics for UDP and UDP-Lite
*/
#define UDP_INC_STATS_USER(net, field, is_udplite) do { \
if (is_udplite) SNMP_INC_STATS_USER((net)->mib.udplite_statistics, field); \
else SNMP_INC_STATS_USER((net)->mib.udp_statistics, field); } while(0)
#define UDP_INC_STATS_BH(net, field, is_udplite) do { \
if (is_udplite) SNMP_INC_STATS_BH((net)->mib.udplite_statistics, field); \
else SNMP_INC_STATS_BH((net)->mib.udp_statistics, field); } while(0)
#define UDP6_INC_STATS_BH(net, field, is_udplite) do { \
if (is_udplite) SNMP_INC_STATS_BH((net)->mib.udplite_stats_in6, field);\
else SNMP_INC_STATS_BH((net)->mib.udp_stats_in6, field); \
} while(0)
#define UDP6_INC_STATS_USER(net, field, __lite) do { \
if (__lite) SNMP_INC_STATS_USER((net)->mib.udplite_stats_in6, field); \
else SNMP_INC_STATS_USER((net)->mib.udp_stats_in6, field); \
} while(0)
#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
#define UDPX_INC_STATS_BH(sk, field) \
do { \
if ((sk)->sk_family == AF_INET) \
UDP_INC_STATS_BH(sock_net(sk), field, 0); \
else \
UDP6_INC_STATS_BH(sock_net(sk), field, 0); \
} while (0);
#else
#define UDPX_INC_STATS_BH(sk, field) UDP_INC_STATS_BH(sock_net(sk), field, 0)
#endif
/* /proc */
struct udp_seq_afinfo {
char *name;
sa_family_t family;
struct udp_table *udp_table;
struct file_operations seq_fops;
struct seq_operations seq_ops;
};
struct udp_iter_state {
struct seq_net_private p;
sa_family_t family;
int bucket;
struct udp_table *udp_table;
};
#ifdef CONFIG_PROC_FS
extern int udp_proc_register(struct net *net, struct udp_seq_afinfo *afinfo);
extern void udp_proc_unregister(struct net *net, struct udp_seq_afinfo *afinfo);
extern int udp4_proc_init(void);
extern void udp4_proc_exit(void);
#endif
extern void udp_init(void);
#endif /* _UDP_H */
Reference in New Issue View Git Blame Copy Permalink