inet6_hashtables.c 9.0 KB
Newer Older
1 2 3 4 5 6 7
/*
 * 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.
 *
 *		Generic INET6 transport hashtables
 *
8 9
 * Authors:	Lotsa people, from code originally in tcp, generalised here
 * 		by Arnaldo Carvalho de Melo <acme@mandriva.com>
10 11 12 13 14 15 16 17
 *
 *	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.
 */

#include <linux/module.h>
18
#include <linux/random.h>
19 20 21 22

#include <net/inet_connection_sock.h>
#include <net/inet_hashtables.h>
#include <net/inet6_hashtables.h>
23
#include <net/ip.h>
24

25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59
void __inet6_hash(struct inet_hashinfo *hashinfo,
				struct sock *sk)
{
	struct hlist_head *list;
	rwlock_t *lock;

	BUG_TRAP(sk_unhashed(sk));

	if (sk->sk_state == TCP_LISTEN) {
		list = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)];
		lock = &hashinfo->lhash_lock;
		inet_listen_wlock(hashinfo);
	} else {
		unsigned int hash;
		sk->sk_hash = hash = inet6_sk_ehashfn(sk);
		hash &= (hashinfo->ehash_size - 1);
		list = &hashinfo->ehash[hash].chain;
		lock = &hashinfo->ehash[hash].lock;
		write_lock(lock);
	}

	__sk_add_node(sk, list);
	sock_prot_inc_use(sk->sk_prot);
	write_unlock(lock);
}
EXPORT_SYMBOL(__inet6_hash);

/*
 * Sockets in TCP_CLOSE state are _always_ taken out of the hash, so
 * we need not check it for TCP lookups anymore, thanks Alexey. -DaveM
 *
 * The sockhash lock must be held as a reader here.
 */
struct sock *__inet6_lookup_established(struct inet_hashinfo *hashinfo,
					   const struct in6_addr *saddr,
A
Al Viro 已提交
60
					   const __be16 sport,
61 62 63 64 65 66
					   const struct in6_addr *daddr,
					   const u16 hnum,
					   const int dif)
{
	struct sock *sk;
	const struct hlist_node *node;
A
Al Viro 已提交
67
	const __portpair ports = INET_COMBINED_PORTS(sport, hnum);
68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84
	/* Optimize here for direct hit, only listening connections can
	 * have wildcards anyways.
	 */
	unsigned int hash = inet6_ehashfn(daddr, hnum, saddr, sport);
	struct inet_ehash_bucket *head = inet_ehash_bucket(hashinfo, hash);

	prefetch(head->chain.first);
	read_lock(&head->lock);
	sk_for_each(sk, node, &head->chain) {
		/* For IPV6 do the cheaper port and family tests first. */
		if (INET6_MATCH(sk, hash, saddr, daddr, ports, dif))
			goto hit; /* You sunk my battleship! */
	}
	/* Must check for a TIME_WAIT'er before going to listener hash. */
	sk_for_each(sk, node, &(head + hashinfo->ehash_size)->chain) {
		const struct inet_timewait_sock *tw = inet_twsk(sk);

A
Al Viro 已提交
85
		if(*((__portpair *)&(tw->tw_dport))	== ports	&&
86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104
		   sk->sk_family		== PF_INET6) {
			const struct inet6_timewait_sock *tw6 = inet6_twsk(sk);

			if (ipv6_addr_equal(&tw6->tw_v6_daddr, saddr)	&&
			    ipv6_addr_equal(&tw6->tw_v6_rcv_saddr, daddr)	&&
			    (!sk->sk_bound_dev_if || sk->sk_bound_dev_if == dif))
				goto hit;
		}
	}
	read_unlock(&head->lock);
	return NULL;

hit:
	sock_hold(sk);
	read_unlock(&head->lock);
	return sk;
}
EXPORT_SYMBOL(__inet6_lookup_established);

105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148
struct sock *inet6_lookup_listener(struct inet_hashinfo *hashinfo,
				   const struct in6_addr *daddr,
				   const unsigned short hnum, const int dif)
{
	struct sock *sk;
	const struct hlist_node *node;
	struct sock *result = NULL;
	int score, hiscore = 0;

	read_lock(&hashinfo->lhash_lock);
	sk_for_each(sk, node, &hashinfo->listening_hash[inet_lhashfn(hnum)]) {
		if (inet_sk(sk)->num == hnum && sk->sk_family == PF_INET6) {
			const struct ipv6_pinfo *np = inet6_sk(sk);
			
			score = 1;
			if (!ipv6_addr_any(&np->rcv_saddr)) {
				if (!ipv6_addr_equal(&np->rcv_saddr, daddr))
					continue;
				score++;
			}
			if (sk->sk_bound_dev_if) {
				if (sk->sk_bound_dev_if != dif)
					continue;
				score++;
			}
			if (score == 3) {
				result = sk;
				break;
			}
			if (score > hiscore) {
				hiscore = score;
				result = sk;
			}
		}
	}
	if (result)
		sock_hold(result);
	read_unlock(&hashinfo->lhash_lock);
	return result;
}

EXPORT_SYMBOL_GPL(inet6_lookup_listener);

struct sock *inet6_lookup(struct inet_hashinfo *hashinfo,
A
Al Viro 已提交
149 150
			  const struct in6_addr *saddr, const __be16 sport,
			  const struct in6_addr *daddr, const __be16 dport,
151 152 153 154 155 156 157 158 159 160 161 162
			  const int dif)
{
	struct sock *sk;

	local_bh_disable();
	sk = __inet6_lookup(hashinfo, saddr, sport, daddr, ntohs(dport), dif);
	local_bh_enable();

	return sk;
}

EXPORT_SYMBOL_GPL(inet6_lookup);
163 164 165 166 167 168

static int __inet6_check_established(struct inet_timewait_death_row *death_row,
				     struct sock *sk, const __u16 lport,
				     struct inet_timewait_sock **twp)
{
	struct inet_hashinfo *hinfo = death_row->hashinfo;
169
	struct inet_sock *inet = inet_sk(sk);
170 171 172 173
	const struct ipv6_pinfo *np = inet6_sk(sk);
	const struct in6_addr *daddr = &np->rcv_saddr;
	const struct in6_addr *saddr = &np->daddr;
	const int dif = sk->sk_bound_dev_if;
A
Al Viro 已提交
174
	const __portpair ports = INET_COMBINED_PORTS(inet->dport, lport);
175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190
	const unsigned int hash = inet6_ehashfn(daddr, inet->num, saddr,
						inet->dport);
	struct inet_ehash_bucket *head = inet_ehash_bucket(hinfo, hash);
	struct sock *sk2;
	const struct hlist_node *node;
	struct inet_timewait_sock *tw;

	prefetch(head->chain.first);
	write_lock(&head->lock);

	/* Check TIME-WAIT sockets first. */
	sk_for_each(sk2, node, &(head + hinfo->ehash_size)->chain) {
		const struct inet6_timewait_sock *tw6 = inet6_twsk(sk2);

		tw = inet_twsk(sk2);

A
Al Viro 已提交
191
		if(*((__portpair *)&(tw->tw_dport)) == ports		 &&
192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210
		   sk2->sk_family	       == PF_INET6	 &&
		   ipv6_addr_equal(&tw6->tw_v6_daddr, saddr)	 &&
		   ipv6_addr_equal(&tw6->tw_v6_rcv_saddr, daddr) &&
		   sk2->sk_bound_dev_if == sk->sk_bound_dev_if) {
			if (twsk_unique(sk, sk2, twp))
				goto unique;
			else
				goto not_unique;
		}
	}
	tw = NULL;

	/* And established part... */
	sk_for_each(sk2, node, &head->chain) {
		if (INET6_MATCH(sk2, hash, saddr, daddr, ports, dif))
			goto not_unique;
	}

unique:
211 212 213 214
	/* Must record num and sport now. Otherwise we will see
	 * in hash table socket with a funny identity. */
	inet->num = lport;
	inet->sport = htons(lport);
215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343
	BUG_TRAP(sk_unhashed(sk));
	__sk_add_node(sk, &head->chain);
	sk->sk_hash = hash;
	sock_prot_inc_use(sk->sk_prot);
	write_unlock(&head->lock);

	if (twp != NULL) {
		*twp = tw;
		NET_INC_STATS_BH(LINUX_MIB_TIMEWAITRECYCLED);
	} else if (tw != NULL) {
		/* Silly. Should hash-dance instead... */
		inet_twsk_deschedule(tw, death_row);
		NET_INC_STATS_BH(LINUX_MIB_TIMEWAITRECYCLED);

		inet_twsk_put(tw);
	}
	return 0;

not_unique:
	write_unlock(&head->lock);
	return -EADDRNOTAVAIL;
}

static inline u32 inet6_sk_port_offset(const struct sock *sk)
{
	const struct inet_sock *inet = inet_sk(sk);
	const struct ipv6_pinfo *np = inet6_sk(sk);
	return secure_ipv6_port_ephemeral(np->rcv_saddr.s6_addr32,
					  np->daddr.s6_addr32,
					  inet->dport);
}

int inet6_hash_connect(struct inet_timewait_death_row *death_row,
		       struct sock *sk)
{
	struct inet_hashinfo *hinfo = death_row->hashinfo;
	const unsigned short snum = inet_sk(sk)->num;
 	struct inet_bind_hashbucket *head;
 	struct inet_bind_bucket *tb;
	int ret;

 	if (snum == 0) {
 		const int low = sysctl_local_port_range[0];
 		const int high = sysctl_local_port_range[1];
		const int range = high - low;
 		int i, port;
		static u32 hint;
		const u32 offset = hint + inet6_sk_port_offset(sk);
		struct hlist_node *node;
 		struct inet_timewait_sock *tw = NULL;

 		local_bh_disable();
		for (i = 1; i <= range; i++) {
			port = low + (i + offset) % range;
 			head = &hinfo->bhash[inet_bhashfn(port, hinfo->bhash_size)];
 			spin_lock(&head->lock);

 			/* Does not bother with rcv_saddr checks,
 			 * because the established check is already
 			 * unique enough.
 			 */
			inet_bind_bucket_for_each(tb, node, &head->chain) {
 				if (tb->port == port) {
 					BUG_TRAP(!hlist_empty(&tb->owners));
 					if (tb->fastreuse >= 0)
 						goto next_port;
 					if (!__inet6_check_established(death_row,
								       sk, port,
								       &tw))
 						goto ok;
 					goto next_port;
 				}
 			}

 			tb = inet_bind_bucket_create(hinfo->bind_bucket_cachep,
						     head, port);
 			if (!tb) {
 				spin_unlock(&head->lock);
 				break;
 			}
 			tb->fastreuse = -1;
 			goto ok;

 		next_port:
 			spin_unlock(&head->lock);
 		}
 		local_bh_enable();

 		return -EADDRNOTAVAIL;

ok:
		hint += i;

 		/* Head lock still held and bh's disabled */
 		inet_bind_hash(sk, tb, port);
		if (sk_unhashed(sk)) {
 			inet_sk(sk)->sport = htons(port);
 			__inet6_hash(hinfo, sk);
 		}
 		spin_unlock(&head->lock);

 		if (tw) {
 			inet_twsk_deschedule(tw, death_row);
 			inet_twsk_put(tw);
 		}

		ret = 0;
		goto out;
 	}

 	head = &hinfo->bhash[inet_bhashfn(snum, hinfo->bhash_size)];
 	tb   = inet_csk(sk)->icsk_bind_hash;
	spin_lock_bh(&head->lock);

	if (sk_head(&tb->owners) == sk && sk->sk_bind_node.next == NULL) {
		__inet6_hash(hinfo, sk);
		spin_unlock_bh(&head->lock);
		return 0;
	} else {
		spin_unlock(&head->lock);
		/* No definite answer... Walk to established hash table */
		ret = __inet6_check_established(death_row, sk, snum, NULL);
out:
		local_bh_enable();
		return ret;
	}
}

EXPORT_SYMBOL_GPL(inet6_hash_connect);