kevin/linux
1
Fork 0
Code
aebda156a5
linux/include/net/inet_sock.h
Eric Dumazet 08dcdbf6a7 ipv6: use a stronger hash for tcp 
It looks like its possible to open thousands of TCP IPv6
sessions on a server, all landing in a single slot of TCP hash
table. Incoming packets have to lookup sockets in a very
long list.

We should hash all bits from foreign IPv6 addresses, using
a salt and hash mix, not a simple XOR.

inet6_ehashfn() can also separately use the ports, instead
of xoring them.

Reported-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-02-21 18:15:58 -05:00

254 lines
6.3 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 inet_sock
*
* Authors: Many, reorganised here by
* Arnaldo Carvalho de Melo <acme@mandriva.com>
*
* 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_SOCK_H
#define _INET_SOCK_H
#include <linux/kmemcheck.h>
#include <linux/string.h>
#include <linux/types.h>
#include <linux/jhash.h>
#include <linux/netdevice.h>
#include <net/flow.h>
#include <net/sock.h>
#include <net/request_sock.h>
#include <net/netns/hash.h>
/** struct ip_options - IP Options
*
* @faddr - Saved first hop address
* @nexthop - Saved nexthop address in LSRR and SSRR
* @is_data - Options in __data, rather than skb
* @is_strictroute - Strict source route
* @srr_is_hit - Packet destination addr was our one
* @is_changed - IP checksum more not valid
* @rr_needaddr - Need to record addr of outgoing dev
* @ts_needtime - Need to record timestamp
* @ts_needaddr - Need to record addr of outgoing dev
*/
struct ip_options {
__be32 faddr;
__be32 nexthop;
unsigned char optlen;
unsigned char srr;
unsigned char rr;
unsigned char ts;
unsigned char is_strictroute:1,
srr_is_hit:1,
is_changed:1,
rr_needaddr:1,
ts_needtime:1,
ts_needaddr:1;
unsigned char router_alert;
unsigned char cipso;
unsigned char __pad2;
unsigned char __data[0];
};
struct ip_options_rcu {
struct rcu_head rcu;
struct ip_options opt;
};
struct ip_options_data {
struct ip_options_rcu opt;
char data[40];
};
struct inet_request_sock {
struct request_sock req;
#if IS_ENABLED(CONFIG_IPV6)
u16 inet6_rsk_offset;
#endif
__be16 loc_port;
__be32 loc_addr;
__be32 rmt_addr;
__be16 rmt_port;
kmemcheck_bitfield_begin(flags);
u16 snd_wscale : 4,
rcv_wscale : 4,
tstamp_ok : 1,
sack_ok : 1,
wscale_ok : 1,
ecn_ok : 1,
acked : 1,
no_srccheck: 1;
kmemcheck_bitfield_end(flags);
struct ip_options_rcu *opt;
};
static inline struct inet_request_sock *inet_rsk(const struct request_sock *sk)
{
return (struct inet_request_sock *)sk;
}
struct inet_cork {
unsigned int flags;
__be32 addr;
struct ip_options *opt;
unsigned int fragsize;
int length; /* Total length of all frames */
struct dst_entry *dst;
u8 tx_flags;
};
struct inet_cork_full {
struct inet_cork base;
struct flowi fl;
};
struct ip_mc_socklist;
struct ipv6_pinfo;
struct rtable;
/** struct inet_sock - representation of INET sockets
*
* @sk - ancestor class
* @pinet6 - pointer to IPv6 control block
* @inet_daddr - Foreign IPv4 addr
* @inet_rcv_saddr - Bound local IPv4 addr
* @inet_dport - Destination port
* @inet_num - Local port
* @inet_saddr - Sending source
* @uc_ttl - Unicast TTL
* @inet_sport - Source port
* @inet_id - ID counter for DF pkts
* @tos - TOS
* @mc_ttl - Multicasting TTL
* @is_icsk - is this an inet_connection_sock?
* @uc_index - Unicast outgoing device index
* @mc_index - Multicast device index
* @mc_list - Group array
* @cork - info to build ip hdr on each ip frag while socket is corked
*/
struct inet_sock {
/* sk and pinet6 has to be the first two members of inet_sock */
struct sock sk;
#if IS_ENABLED(CONFIG_IPV6)
struct ipv6_pinfo *pinet6;
#endif
/* Socket demultiplex comparisons on incoming packets. */
#define inet_daddr sk.__sk_common.skc_daddr
#define inet_rcv_saddr sk.__sk_common.skc_rcv_saddr
#define inet_addrpair sk.__sk_common.skc_addrpair
#define inet_dport sk.__sk_common.skc_dport
#define inet_num sk.__sk_common.skc_num
#define inet_portpair sk.__sk_common.skc_portpair
__be32 inet_saddr;
__s16 uc_ttl;
__u16 cmsg_flags;
__be16 inet_sport;
__u16 inet_id;
struct ip_options_rcu __rcu *inet_opt;
int rx_dst_ifindex;
__u8 tos;
__u8 min_ttl;
__u8 mc_ttl;
__u8 pmtudisc;
__u8 recverr:1,
is_icsk:1,
freebind:1,
hdrincl:1,
mc_loop:1,
transparent:1,
mc_all:1,
nodefrag:1;
__u8 rcv_tos;
int uc_index;
int mc_index;
__be32 mc_addr;
struct ip_mc_socklist __rcu *mc_list;
struct inet_cork_full cork;
};
#define IPCORK_OPT 1 /* ip-options has been held in ipcork.opt */
#define IPCORK_ALLFRAG 2 /* always fragment (for ipv6 for now) */
static inline struct inet_sock *inet_sk(const struct sock *sk)
{
return (struct inet_sock *)sk;
}
static inline void __inet_sk_copy_descendant(struct sock *sk_to,
const struct sock *sk_from,
const int ancestor_size)
{
memcpy(inet_sk(sk_to) + 1, inet_sk(sk_from) + 1,
sk_from->sk_prot->obj_size - ancestor_size);
}
#if !(IS_ENABLED(CONFIG_IPV6))
static inline void inet_sk_copy_descendant(struct sock *sk_to,
const struct sock *sk_from)
{
__inet_sk_copy_descendant(sk_to, sk_from, sizeof(struct inet_sock));
}
#endif
extern int inet_sk_rebuild_header(struct sock *sk);
extern u32 inet_ehash_secret;
extern u32 ipv6_hash_secret;
extern void build_ehash_secret(void);
static inline unsigned int inet_ehashfn(struct net *net,
const __be32 laddr, const __u16 lport,
const __be32 faddr, const __be16 fport)
{
return jhash_3words((__force __u32) laddr,
(__force __u32) faddr,
((__u32) lport) << 16 | (__force __u32)fport,
inet_ehash_secret + net_hash_mix(net));
}
static inline int inet_sk_ehashfn(const struct sock *sk)
{
const struct inet_sock *inet = inet_sk(sk);
const __be32 laddr = inet->inet_rcv_saddr;
const __u16 lport = inet->inet_num;
const __be32 faddr = inet->inet_daddr;
const __be16 fport = inet->inet_dport;
struct net *net = sock_net(sk);
return inet_ehashfn(net, laddr, lport, faddr, fport);
}
static inline struct request_sock *inet_reqsk_alloc(struct request_sock_ops *ops)
{
struct request_sock *req = reqsk_alloc(ops);
struct inet_request_sock *ireq = inet_rsk(req);
if (req != NULL) {
kmemcheck_annotate_bitfield(ireq, flags);
ireq->opt = NULL;
}
return req;
}
static inline __u8 inet_sk_flowi_flags(const struct sock *sk)
{
__u8 flags = 0;
if (inet_sk(sk)->transparent || inet_sk(sk)->hdrincl)
flags |= FLOWI_FLAG_ANYSRC;
return flags;
}
#endif /* _INET_SOCK_H */
View Git Blame Copy Permalink