linux/include/net/inet_hashtables.h
Eric Dumazet 095dc8e0c3 tcp: fix/cleanup inet_ehash_locks_alloc()
If tcp ehash table is constrained to a very small number of buckets
(eg boot parameter thash_entries=128), then we can crash if spinlock
array has more entries.

While we are at it, un-inline inet_ehash_locks_alloc() and make
following changes :

- Budget 2 cache lines per cpu worth of 'spinlocks'
- Try to kmalloc() the array to avoid extra TLB pressure.
  (Most servers at Google allocate 8192 bytes for this hash table)
- Get rid of various #ifdef

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-05-26 19:48:46 -04:00

374 lines
12 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.
*
* Authors: Lotsa people, from code originally in tcp
*
* 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_HASHTABLES_H
#define _INET_HASHTABLES_H
#include <linux/interrupt.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/list.h>
#include <linux/slab.h>
#include <linux/socket.h>
#include <linux/spinlock.h>
#include <linux/types.h>
#include <linux/wait.h>
#include <net/inet_connection_sock.h>
#include <net/inet_sock.h>
#include <net/sock.h>
#include <net/route.h>
#include <net/tcp_states.h>
#include <net/netns/hash.h>
#include <linux/atomic.h>
#include <asm/byteorder.h>
/* This is for all connections with a full identity, no wildcards.
* The 'e' prefix stands for Establish, but we really put all sockets
* but LISTEN ones.
*/
struct inet_ehash_bucket {
struct hlist_nulls_head chain;
};
/* There are a few simple rules, which allow for local port reuse by
* an application. In essence:
*
* 1) Sockets bound to different interfaces may share a local port.
* Failing that, goto test 2.
* 2) If all sockets have sk->sk_reuse set, and none of them are in
* TCP_LISTEN state, the port may be shared.
* Failing that, goto test 3.
* 3) If all sockets are bound to a specific inet_sk(sk)->rcv_saddr local
* address, and none of them are the same, the port may be
* shared.
* Failing this, the port cannot be shared.
*
* The interesting point, is test #2. This is what an FTP server does
* all day. To optimize this case we use a specific flag bit defined
* below. As we add sockets to a bind bucket list, we perform a
* check of: (newsk->sk_reuse && (newsk->sk_state != TCP_LISTEN))
* As long as all sockets added to a bind bucket pass this test,
* the flag bit will be set.
* The resulting situation is that tcp_v[46]_verify_bind() can just check
* for this flag bit, if it is set and the socket trying to bind has
* sk->sk_reuse set, we don't even have to walk the owners list at all,
* we return that it is ok to bind this socket to the requested local port.
*
* Sounds like a lot of work, but it is worth it. In a more naive
* implementation (ie. current FreeBSD etc.) the entire list of ports
* must be walked for each data port opened by an ftp server. Needless
* to say, this does not scale at all. With a couple thousand FTP
* users logged onto your box, isn't it nice to know that new data
* ports are created in O(1) time? I thought so. ;-) -DaveM
*/
struct inet_bind_bucket {
possible_net_t ib_net;
unsigned short port;
signed char fastreuse;
signed char fastreuseport;
kuid_t fastuid;
int num_owners;
struct hlist_node node;
struct hlist_head owners;
};
static inline struct net *ib_net(struct inet_bind_bucket *ib)
{
return read_pnet(&ib->ib_net);
}
#define inet_bind_bucket_for_each(tb, head) \
hlist_for_each_entry(tb, head, node)
struct inet_bind_hashbucket {
spinlock_t lock;
struct hlist_head chain;
};
/*
* Sockets can be hashed in established or listening table
* We must use different 'nulls' end-of-chain value for listening
* hash table, or we might find a socket that was closed and
* reallocated/inserted into established hash table
*/
#define LISTENING_NULLS_BASE (1U << 29)
struct inet_listen_hashbucket {
spinlock_t lock;
struct hlist_nulls_head head;
};
/* This is for listening sockets, thus all sockets which possess wildcards. */
#define INET_LHTABLE_SIZE 32 /* Yes, really, this is all you need. */
struct inet_hashinfo {
/* This is for sockets with full identity only. Sockets here will
* always be without wildcards and will have the following invariant:
*
* TCP_ESTABLISHED <= sk->sk_state < TCP_CLOSE
*
*/
struct inet_ehash_bucket *ehash;
spinlock_t *ehash_locks;
unsigned int ehash_mask;
unsigned int ehash_locks_mask;
/* Ok, let's try this, I give up, we do need a local binding
* TCP hash as well as the others for fast bind/connect.
*/
struct inet_bind_hashbucket *bhash;
unsigned int bhash_size;
/* 4 bytes hole on 64 bit */
struct kmem_cache *bind_bucket_cachep;
/* All the above members are written once at bootup and
* never written again _or_ are predominantly read-access.
*
* Now align to a new cache line as all the following members
* might be often dirty.
*/
/* All sockets in TCP_LISTEN state will be in here. This is the only
* table where wildcard'd TCP sockets can exist. Hash function here
* is just local port number.
*/
struct inet_listen_hashbucket listening_hash[INET_LHTABLE_SIZE]
____cacheline_aligned_in_smp;
};
static inline struct inet_ehash_bucket *inet_ehash_bucket(
struct inet_hashinfo *hashinfo,
unsigned int hash)
{
return &hashinfo->ehash[hash & hashinfo->ehash_mask];
}
static inline spinlock_t *inet_ehash_lockp(
struct inet_hashinfo *hashinfo,
unsigned int hash)
{
return &hashinfo->ehash_locks[hash & hashinfo->ehash_locks_mask];
}
int inet_ehash_locks_alloc(struct inet_hashinfo *hashinfo);
static inline void inet_ehash_locks_free(struct inet_hashinfo *hashinfo)
{
kvfree(hashinfo->ehash_locks);
hashinfo->ehash_locks = NULL;
}
struct inet_bind_bucket *
inet_bind_bucket_create(struct kmem_cache *cachep, struct net *net,
struct inet_bind_hashbucket *head,
const unsigned short snum);
void inet_bind_bucket_destroy(struct kmem_cache *cachep,
struct inet_bind_bucket *tb);
static inline u32 inet_bhashfn(const struct net *net, const __u16 lport,
const u32 bhash_size)
{
return (lport + net_hash_mix(net)) & (bhash_size - 1);
}
void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb,
const unsigned short snum);
/* These can have wildcards, don't try too hard. */
static inline u32 inet_lhashfn(const struct net *net, const unsigned short num)
{
return (num + net_hash_mix(net)) & (INET_LHTABLE_SIZE - 1);
}
static inline int inet_sk_listen_hashfn(const struct sock *sk)
{
return inet_lhashfn(sock_net(sk), inet_sk(sk)->inet_num);
}
/* Caller must disable local BH processing. */
int __inet_inherit_port(struct sock *sk, struct sock *child);
void inet_put_port(struct sock *sk);
void inet_hashinfo_init(struct inet_hashinfo *h);
int __inet_hash_nolisten(struct sock *sk, struct inet_timewait_sock *tw);
int __inet_hash(struct sock *sk, struct inet_timewait_sock *tw);
void inet_hash(struct sock *sk);
void inet_unhash(struct sock *sk);
struct sock *__inet_lookup_listener(struct net *net,
struct inet_hashinfo *hashinfo,
const __be32 saddr, const __be16 sport,
const __be32 daddr,
const unsigned short hnum,
const int dif);
static inline struct sock *inet_lookup_listener(struct net *net,
struct inet_hashinfo *hashinfo,
__be32 saddr, __be16 sport,
__be32 daddr, __be16 dport, int dif)
{
return __inet_lookup_listener(net, hashinfo, saddr, sport,
daddr, ntohs(dport), dif);
}
/* Socket demux engine toys. */
/* What happens here is ugly; 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. Let's at least
make sure that it's not mixed with anything else...
On 64bit targets we combine comparisons with pair of adjacent __be32
fields in the same way.
*/
#ifdef __BIG_ENDIAN
#define INET_COMBINED_PORTS(__sport, __dport) \
((__force __portpair)(((__force __u32)(__be16)(__sport) << 16) | (__u32)(__dport)))
#else /* __LITTLE_ENDIAN */
#define INET_COMBINED_PORTS(__sport, __dport) \
((__force __portpair)(((__u32)(__dport) << 16) | (__force __u32)(__be16)(__sport)))
#endif
#if (BITS_PER_LONG == 64)
#ifdef __BIG_ENDIAN
#define INET_ADDR_COOKIE(__name, __saddr, __daddr) \
const __addrpair __name = (__force __addrpair) ( \
(((__force __u64)(__be32)(__saddr)) << 32) | \
((__force __u64)(__be32)(__daddr)))
#else /* __LITTLE_ENDIAN */
#define INET_ADDR_COOKIE(__name, __saddr, __daddr) \
const __addrpair __name = (__force __addrpair) ( \
(((__force __u64)(__be32)(__daddr)) << 32) | \
((__force __u64)(__be32)(__saddr)))
#endif /* __BIG_ENDIAN */
#define INET_MATCH(__sk, __net, __cookie, __saddr, __daddr, __ports, __dif) \
(((__sk)->sk_portpair == (__ports)) && \
((__sk)->sk_addrpair == (__cookie)) && \
(!(__sk)->sk_bound_dev_if || \
((__sk)->sk_bound_dev_if == (__dif))) && \
net_eq(sock_net(__sk), (__net)))
#else /* 32-bit arch */
#define INET_ADDR_COOKIE(__name, __saddr, __daddr) \
const int __name __deprecated __attribute__((unused))
#define INET_MATCH(__sk, __net, __cookie, __saddr, __daddr, __ports, __dif) \
(((__sk)->sk_portpair == (__ports)) && \
((__sk)->sk_daddr == (__saddr)) && \
((__sk)->sk_rcv_saddr == (__daddr)) && \
(!(__sk)->sk_bound_dev_if || \
((__sk)->sk_bound_dev_if == (__dif))) && \
net_eq(sock_net(__sk), (__net)))
#endif /* 64-bit arch */
/*
* Sockets in TCP_CLOSE state are _always_ taken out of the hash, so we need
* not check it for lookups anymore, thanks Alexey. -DaveM
*
* Local BH must be disabled here.
*/
struct sock *__inet_lookup_established(struct net *net,
struct inet_hashinfo *hashinfo,
const __be32 saddr, const __be16 sport,
const __be32 daddr, const u16 hnum,
const int dif);
static inline struct sock *
inet_lookup_established(struct net *net, struct inet_hashinfo *hashinfo,
const __be32 saddr, const __be16 sport,
const __be32 daddr, const __be16 dport,
const int dif)
{
return __inet_lookup_established(net, hashinfo, saddr, sport, daddr,
ntohs(dport), dif);
}
static inline struct sock *__inet_lookup(struct net *net,
struct inet_hashinfo *hashinfo,
const __be32 saddr, const __be16 sport,
const __be32 daddr, const __be16 dport,
const int dif)
{
u16 hnum = ntohs(dport);
struct sock *sk = __inet_lookup_established(net, hashinfo,
saddr, sport, daddr, hnum, dif);
return sk ? : __inet_lookup_listener(net, hashinfo, saddr, sport,
daddr, hnum, dif);
}
static inline struct sock *inet_lookup(struct net *net,
struct inet_hashinfo *hashinfo,
const __be32 saddr, const __be16 sport,
const __be32 daddr, const __be16 dport,
const int dif)
{
struct sock *sk;
local_bh_disable();
sk = __inet_lookup(net, hashinfo, saddr, sport, daddr, dport, dif);
local_bh_enable();
return sk;
}
static inline struct sock *__inet_lookup_skb(struct inet_hashinfo *hashinfo,
struct sk_buff *skb,
const __be16 sport,
const __be16 dport)
{
struct sock *sk = skb_steal_sock(skb);
const struct iphdr *iph = ip_hdr(skb);
if (sk)
return sk;
else
return __inet_lookup(dev_net(skb_dst(skb)->dev), hashinfo,
iph->saddr, sport,
iph->daddr, dport, inet_iif(skb));
}
u32 sk_ehashfn(const struct sock *sk);
u32 inet6_ehashfn(const struct net *net,
const struct in6_addr *laddr, const u16 lport,
const struct in6_addr *faddr, const __be16 fport);
static inline void sk_daddr_set(struct sock *sk, __be32 addr)
{
sk->sk_daddr = addr; /* alias of inet_daddr */
#if IS_ENABLED(CONFIG_IPV6)
ipv6_addr_set_v4mapped(addr, &sk->sk_v6_daddr);
#endif
}
static inline void sk_rcv_saddr_set(struct sock *sk, __be32 addr)
{
sk->sk_rcv_saddr = addr; /* alias of inet_rcv_saddr */
#if IS_ENABLED(CONFIG_IPV6)
ipv6_addr_set_v4mapped(addr, &sk->sk_v6_rcv_saddr);
#endif
}
int __inet_hash_connect(struct inet_timewait_death_row *death_row,
struct sock *sk, u32 port_offset,
int (*check_established)(struct inet_timewait_death_row *,
struct sock *, __u16,
struct inet_timewait_sock **));
int inet_hash_connect(struct inet_timewait_death_row *death_row,
struct sock *sk);
#endif /* _INET_HASHTABLES_H */