aboutsummaryrefslogtreecommitdiffstats
path: root/lib/textsearch.c
blob: d608331b3e4798c23607471dea52bbc483c69760 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
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
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
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
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
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
/*
 * lib/textsearch.c	Generic text search interface
 *
 *		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.
 *
 * Authors:	Thomas Graf <tgraf@suug.ch>
 * 		Pablo Neira Ayuso <pablo@netfilter.org>
 *
 * ==========================================================================
 *
 * INTRODUCTION
 *
 *   The textsearch infrastructure provides text searching facitilies for
 *   both linear and non-linear data. Individual search algorithms are
 *   implemented in modules and chosen by the user.
 *
 * ARCHITECTURE
 *
 *      User
 *     +----------------+
 *     |        finish()|<--------------(6)-----------------+
 *     |get_next_block()|<--------------(5)---------------+ |
 *     |                |                     Algorithm   | |
 *     |                |                    +------------------------------+
 *     |                |                    |  init()   find()   destroy() |
 *     |                |                    +------------------------------+
 *     |                |       Core API           ^       ^          ^
 *     |                |      +---------------+  (2)     (4)        (8)
 *     |             (1)|----->| prepare()     |---+       |          |
 *     |             (3)|----->| find()/next() |-----------+          |
 *     |             (7)|----->| destroy()     |----------------------+
 *     +----------------+      +---------------+
 *  
 *   (1) User configures a search by calling _prepare() specifying the
 *       search parameters such as the pattern and algorithm name.
 *   (2) Core requests the algorithm to allocate and initialize a search
 *       configuration according to the specified parameters.
 *   (3) User starts the search(es) by calling _find() or _next() to
 *       fetch subsequent occurrences. A state variable is provided
 *       to the algorithm to store persistent variables.
 *   (4) Core eventually resets the search offset and forwards the find()
 *       request to the algorithm.
 *   (5) Algorithm calls get_next_block() provided by the user continously
 *       to fetch the data to be searched in block by block.
 *   (6) Algorithm invokes finish() after the last call to get_next_block
 *       to clean up any leftovers from get_next_block. (Optional)
 *   (7) User destroys the configuration by calling _destroy().
 *   (8) Core notifies the algorithm to destroy algorithm specific
 *       allocations. (Optional)
 *
 * USAGE
 *
 *   Before a search can be performed, a configuration must be created
 *   by calling textsearch_prepare() specifying the searching algorithm,
 *   the pattern to look for and flags. As a flag, you can set TS_IGNORECASE
 *   to perform case insensitive matching. But it might slow down
 *   performance of algorithm, so you should use it at own your risk.
 *   The returned configuration may then be used for an arbitary
 *   amount of times and even in parallel as long as a separate struct
 *   ts_state variable is provided to every instance.
 *
 *   The actual search is performed by either calling textsearch_find_-
 *   continuous() for linear data or by providing an own get_next_block()
 *   implementation and calling textsearch_find(). Both functions return
 *   the position of the first occurrence of the patern or UINT_MAX if
 *   no match was found. Subsequent occurences can be found by calling
 *   textsearch_next() regardless of the linearity of the data.
 *
 *   Once you're done using a configuration it must be given back via
 *   textsearch_destroy.
 *
 * EXAMPLE
 *
 *   int pos;
 *   struct ts_config *conf;
 *   struct ts_state state;
 *   const char *pattern = "chicken";
 *   const char *example = "We dance the funky chicken";
 *
 *   conf = textsearch_prepare("kmp", pattern, strlen(pattern),
 *                             GFP_KERNEL, TS_AUTOLOAD);
 *   if (IS_ERR(conf)) {
 *       err = PTR_ERR(conf);
 *       goto errout;
 *   }
 *
 *   pos = textsearch_find_continuous(conf, &state, example, strlen(example));
 *   if (pos != UINT_MAX)
 *       panic("Oh my god, dancing chickens at %d\n", pos);
 *
 *   textsearch_destroy(conf);
 * ==========================================================================
 */

#include <linux/module.h>
#include <linux/types.h>
#include <linux/string.h>
#include <linux/init.h>
#include <linux/rculist.h>
#include <linux/rcupdate.h>
#include <linux/err.h>
#include <linux/textsearch.h>
#include <linux/slab.h>

static LIST_HEAD(ts_ops);
static DEFINE_SPINLOCK(ts_mod_lock);

static inline struct ts_ops *lookup_ts_algo(const char *name)
{
	struct ts_ops *o;

	rcu_read_lock();
	list_for_each_entry_rcu(o, &ts_ops, list) {
		if (!strcmp(name, o->name)) {
			if (!try_module_get(o->owner))
				o = NULL;
			rcu_read_unlock();
			return o;
		}
	}
	rcu_read_unlock();

	return NULL;
}

/**
 * textsearch_register - register a textsearch module
 * @ops: operations lookup table
 *
 * This function must be called by textsearch modules to announce
 * their presence. The specified &@ops must have %name set to a
 * unique identifier and the callbacks find(), init(), get_pattern(),
 * and get_pattern_len() must be implemented.
 *
 * Returns 0 or -EEXISTS if another module has already registered
 * with same name.
 */
int textsearch_register(struct ts_ops *ops)
{
	int err = -EEXIST;
	struct ts_ops *o;

	if (ops->name == NULL || ops->find == NULL || ops->init == NULL ||
	    ops->get_pattern == NULL || ops->get_pattern_len == NULL)
		return -EINVAL;

	spin_lock(&ts_mod_lock);
	list_for_each_entry(o, &ts_ops, list) {
		if (!strcmp(ops->name, o->name))
			goto errout;
	}

	list_add_tail_rcu(&ops->list, &ts_ops);
	err = 0;
errout:
	spin_unlock(&ts_mod_lock);
	return err;
}

/**
 * textsearch_unregister - unregister a textsearch module
 * @ops: operations lookup table
 *
 * This function must be called by textsearch modules to announce
 * their disappearance for examples when the module gets unloaded.
 * The &ops parameter must be the same as the one during the
 * registration.
 *
 * Returns 0 on success or -ENOENT if no matching textsearch
 * registration was found.
 */
int textsearch_unregister(struct ts_ops *ops)
{
	int err = 0;
	struct ts_ops *o;

	spin_lock(&ts_mod_lock);
	list_for_each_entry(o, &ts_ops, list) {
		if (o == ops) {
			list_del_rcu(&o->list);
			goto out;
		}
	}

	err = -ENOENT;
out:
	spin_unlock(&ts_mod_lock);
	return err;
}

struct ts_linear_state
{
	unsigned int	len;
	const void	*data;
};

static unsigned int get_linear_data(unsigned int consumed, const u8 **dst,
				    struct ts_config *conf,
				    struct ts_state *state)
{
	struct ts_linear_state *st = (struct ts_linear_state *) state->cb;

	if (likely(consumed < st->len)) {
		*dst = st->data + consumed;
		return st->len - consumed;
	}

	return 0;
}

/**
 * textsearch_find_continuous - search a pattern in continuous/linear data
 * @conf: search configuration
 * @state: search state
 * @data: data to search in
 * @len: length of data
 *
 * A simplified version of textsearch_find() for continuous/linear data.
 * Call textsearch_next() to retrieve subsequent matches.
 *
 * Returns the position of first occurrence of the pattern or
 * %UINT_MAX if no occurrence was found.
 */ 
unsigned int textsearch_find_continuous(struct ts_config *conf,
					struct ts_state *state,
					const void *data, unsigned int len)
{
	struct ts_linear_state *st = (struct ts_linear_state *) state->cb;

	conf->get_next_block = get_linear_data;
	st->data = data;
	st->len = len;

	return textsearch_find(conf, state);
}

/**
 * textsearch_prepare - Prepare a search
 * @algo: name of search algorithm
 * @pattern: pattern data
 * @len: length of pattern
 * @gfp_mask: allocation mask
 * @flags: search flags
 *
 * Looks up the search algorithm module and creates a new textsearch
 * configuration for the specified pattern. Upon completion all
 * necessary refcnts are held and the configuration must be put back
 * using textsearch_put() after usage.
 *
 * Note: The format of the pattern may not be compatible between
 *       the various search algorithms.
 *
 * Returns a new textsearch configuration according to the specified
 * parameters or a ERR_PTR(). If a zero length pattern is passed, this
 * function returns EINVAL.
 */
struct ts_config *textsearch_prepare(const char *algo, const void *pattern,
				     unsigned int len, gfp_t gfp_mask, int flags)
{
	int err = -ENOENT;
	struct ts_config *conf;
	struct ts_ops *ops;
	
	if (len == 0)
		return ERR_PTR(-EINVAL);

	ops = lookup_ts_algo(algo);
#ifdef CONFIG_MODULES
	/*
	 * Why not always autoload you may ask. Some users are
	 * in a situation where requesting a module may deadlock,
	 * especially when the module is located on a NFS mount.
	 */
	if (ops == NULL && flags & TS_AUTOLOAD) {
		request_module("ts_%s", algo);
		ops = lookup_ts_algo(algo);
	}
#endif

	if (ops == NULL)
		goto errout;

	conf = ops->init(pattern, len, gfp_mask, flags);
	if (IS_ERR(conf)) {
		err = PTR_ERR(conf);
		goto errout;
	}

	conf->ops = ops;
	return conf;

errout:
	if (ops)
		module_put(ops->owner);
		
	return ERR_PTR(err);
}

/**
 * textsearch_destroy - destroy a search configuration
 * @conf: search configuration
 *
 * Releases all references of the configuration and frees
 * up the memory.
 */
void textsearch_destroy(struct ts_config *conf)
{
	if (conf->ops) {
		if (conf->ops->destroy)
			conf->ops->destroy(conf);
		module_put(conf->ops->owner);
	}

	kfree(conf);
}

EXPORT_SYMBOL(textsearch_register);
EXPORT_SYMBOL(textsearch_unregister);
EXPORT_SYMBOL(textsearch_prepare);
EXPORT_SYMBOL(textsearch_find_continuous);
EXPORT_SYMBOL(textsearch_destroy);
#n1077'>1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824
/*
 * xfrm_state.c
 *
 * Changes:
 *	Mitsuru KANDA @USAGI
 * 	Kazunori MIYAZAWA @USAGI
 * 	Kunihiro Ishiguro <kunihiro@ipinfusion.com>
 * 		IPv6 support
 * 	YOSHIFUJI Hideaki @USAGI
 * 		Split up af-specific functions
 *	Derek Atkins <derek@ihtfp.com>
 *		Add UDP Encapsulation
 *
 */

#include <linux/workqueue.h>
#include <net/xfrm.h>
#include <linux/pfkeyv2.h>
#include <linux/ipsec.h>
#include <linux/module.h>
#include <linux/cache.h>
#include <asm/uaccess.h>
#include <linux/audit.h>
#include <linux/cache.h>

#include "xfrm_hash.h"

struct sock *xfrm_nl;
EXPORT_SYMBOL(xfrm_nl);

u32 sysctl_xfrm_aevent_etime __read_mostly = XFRM_AE_ETIME;
EXPORT_SYMBOL(sysctl_xfrm_aevent_etime);

u32 sysctl_xfrm_aevent_rseqth __read_mostly = XFRM_AE_SEQT_SIZE;
EXPORT_SYMBOL(sysctl_xfrm_aevent_rseqth);

u32 sysctl_xfrm_acq_expires __read_mostly = 30;

/* Each xfrm_state may be linked to two tables:

   1. Hash table by (spi,daddr,ah/esp) to find SA by SPI. (input,ctl)
   2. Hash table by (daddr,family,reqid) to find what SAs exist for given
      destination/tunnel endpoint. (output)
 */

static DEFINE_SPINLOCK(xfrm_state_lock);

/* Hash table to find appropriate SA towards given target (endpoint
 * of tunnel or destination of transport mode) allowed by selector.
 *
 * Main use is finding SA after policy selected tunnel or transport mode.
 * Also, it can be used by ah/esp icmp error handler to find offending SA.
 */
static struct hlist_head *xfrm_state_bydst __read_mostly;
static struct hlist_head *xfrm_state_bysrc __read_mostly;
static struct hlist_head *xfrm_state_byspi __read_mostly;
static unsigned int xfrm_state_hmask __read_mostly;
static unsigned int xfrm_state_hashmax __read_mostly = 1 * 1024 * 1024;
static unsigned int xfrm_state_num;
static unsigned int xfrm_state_genid;

static inline unsigned int xfrm_dst_hash(xfrm_address_t *daddr,
					 xfrm_address_t *saddr,
					 u32 reqid,
					 unsigned short family)
{
	return __xfrm_dst_hash(daddr, saddr, reqid, family, xfrm_state_hmask);
}

static inline unsigned int xfrm_src_hash(xfrm_address_t *daddr,
					 xfrm_address_t *saddr,
					 unsigned short family)
{
	return __xfrm_src_hash(daddr, saddr, family, xfrm_state_hmask);
}

static inline unsigned int
xfrm_spi_hash(xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family)
{
	return __xfrm_spi_hash(daddr, spi, proto, family, xfrm_state_hmask);
}

static void xfrm_hash_transfer(struct hlist_head *list,
			       struct hlist_head *ndsttable,
			       struct hlist_head *nsrctable,
			       struct hlist_head *nspitable,
			       unsigned int nhashmask)
{
	struct hlist_node *entry, *tmp;
	struct xfrm_state *x;

	hlist_for_each_entry_safe(x, entry, tmp, list, bydst) {
		unsigned int h;

		h = __xfrm_dst_hash(&x->id.daddr, &x->props.saddr,
				    x->props.reqid, x->props.family,
				    nhashmask);
		hlist_add_head(&x->bydst, ndsttable+h);

		h = __xfrm_src_hash(&x->id.daddr, &x->props.saddr,
				    x->props.family,
				    nhashmask);
		hlist_add_head(&x->bysrc, nsrctable+h);

		if (x->id.spi) {
			h = __xfrm_spi_hash(&x->id.daddr, x->id.spi,
					    x->id.proto, x->props.family,
					    nhashmask);
			hlist_add_head(&x->byspi, nspitable+h);
		}
	}
}

static unsigned long xfrm_hash_new_size(void)
{
	return ((xfrm_state_hmask + 1) << 1) *
		sizeof(struct hlist_head);
}

static DEFINE_MUTEX(hash_resize_mutex);

static void xfrm_hash_resize(struct work_struct *__unused)
{
	struct hlist_head *ndst, *nsrc, *nspi, *odst, *osrc, *ospi;
	unsigned long nsize, osize;
	unsigned int nhashmask, ohashmask;
	int i;

	mutex_lock(&hash_resize_mutex);

	nsize = xfrm_hash_new_size();
	ndst = xfrm_hash_alloc(nsize);
	if (!ndst)
		goto out_unlock;
	nsrc = xfrm_hash_alloc(nsize);
	if (!nsrc) {
		xfrm_hash_free(ndst, nsize);
		goto out_unlock;
	}
	nspi = xfrm_hash_alloc(nsize);
	if (!nspi) {
		xfrm_hash_free(ndst, nsize);
		xfrm_hash_free(nsrc, nsize);
		goto out_unlock;
	}

	spin_lock_bh(&xfrm_state_lock);

	nhashmask = (nsize / sizeof(struct hlist_head)) - 1U;
	for (i = xfrm_state_hmask; i >= 0; i--)
		xfrm_hash_transfer(xfrm_state_bydst+i, ndst, nsrc, nspi,
				   nhashmask);

	odst = xfrm_state_bydst;
	osrc = xfrm_state_bysrc;
	ospi = xfrm_state_byspi;
	ohashmask = xfrm_state_hmask;

	xfrm_state_bydst = ndst;
	xfrm_state_bysrc = nsrc;
	xfrm_state_byspi = nspi;
	xfrm_state_hmask = nhashmask;

	spin_unlock_bh(&xfrm_state_lock);

	osize = (ohashmask + 1) * sizeof(struct hlist_head);
	xfrm_hash_free(odst, osize);
	xfrm_hash_free(osrc, osize);
	xfrm_hash_free(ospi, osize);

out_unlock:
	mutex_unlock(&hash_resize_mutex);
}

static DECLARE_WORK(xfrm_hash_work, xfrm_hash_resize);

DECLARE_WAIT_QUEUE_HEAD(km_waitq);
EXPORT_SYMBOL(km_waitq);

static DEFINE_RWLOCK(xfrm_state_afinfo_lock);
static struct xfrm_state_afinfo *xfrm_state_afinfo[NPROTO];

static struct work_struct xfrm_state_gc_work;
static HLIST_HEAD(xfrm_state_gc_list);
static DEFINE_SPINLOCK(xfrm_state_gc_lock);

int __xfrm_state_delete(struct xfrm_state *x);

int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol);
void km_state_expired(struct xfrm_state *x, int hard, u32 pid);

static void xfrm_state_gc_destroy(struct xfrm_state *x)
{
	del_timer_sync(&x->timer);
	del_timer_sync(&x->rtimer);
	kfree(x->aalg);
	kfree(x->ealg);
	kfree(x->calg);
	kfree(x->encap);
	kfree(x->coaddr);
	if (x->mode)
		xfrm_put_mode(x->mode);
	if (x->type) {
		x->type->destructor(x);
		xfrm_put_type(x->type);
	}
	security_xfrm_state_free(x);
	kfree(x);
}

static void xfrm_state_gc_task(struct work_struct *data)
{
	struct xfrm_state *x;
	struct hlist_node *entry, *tmp;
	struct hlist_head gc_list;

	spin_lock_bh(&xfrm_state_gc_lock);
	gc_list.first = xfrm_state_gc_list.first;
	INIT_HLIST_HEAD(&xfrm_state_gc_list);
	spin_unlock_bh(&xfrm_state_gc_lock);

	hlist_for_each_entry_safe(x, entry, tmp, &gc_list, bydst)
		xfrm_state_gc_destroy(x);

	wake_up(&km_waitq);
}

static inline unsigned long make_jiffies(long secs)
{
	if (secs >= (MAX_SCHEDULE_TIMEOUT-1)/HZ)
		return MAX_SCHEDULE_TIMEOUT-1;
	else
		return secs*HZ;
}

static void xfrm_timer_handler(unsigned long data)
{
	struct xfrm_state *x = (struct xfrm_state*)data;
	unsigned long now = get_seconds();
	long next = LONG_MAX;
	int warn = 0;
	int err = 0;

	spin_lock(&x->lock);
	if (x->km.state == XFRM_STATE_DEAD)
		goto out;
	if (x->km.state == XFRM_STATE_EXPIRED)
		goto expired;
	if (x->lft.hard_add_expires_seconds) {
		long tmo = x->lft.hard_add_expires_seconds +
			x->curlft.add_time - now;
		if (tmo <= 0)
			goto expired;
		if (tmo < next)
			next = tmo;
	}
	if (x->lft.hard_use_expires_seconds) {
		long tmo = x->lft.hard_use_expires_seconds +
			(x->curlft.use_time ? : now) - now;
		if (tmo <= 0)
			goto expired;
		if (tmo < next)
			next = tmo;
	}
	if (x->km.dying)
		goto resched;
	if (x->lft.soft_add_expires_seconds) {
		long tmo = x->lft.soft_add_expires_seconds +
			x->curlft.add_time - now;
		if (tmo <= 0)
			warn = 1;
		else if (tmo < next)
			next = tmo;
	}
	if (x->lft.soft_use_expires_seconds) {
		long tmo = x->lft.soft_use_expires_seconds +
			(x->curlft.use_time ? : now) - now;
		if (tmo <= 0)
			warn = 1;
		else if (tmo < next)
			next = tmo;
	}

	x->km.dying = warn;
	if (warn)
		km_state_expired(x, 0, 0);
resched:
	if (next != LONG_MAX)
		mod_timer(&x->timer, jiffies + make_jiffies(next));

	goto out;

expired:
	if (x->km.state == XFRM_STATE_ACQ && x->id.spi == 0) {
		x->km.state = XFRM_STATE_EXPIRED;
		wake_up(&km_waitq);
		next = 2;
		goto resched;
	}

	err = __xfrm_state_delete(x);
	if (!err && x->id.spi)
		km_state_expired(x, 1, 0);

	xfrm_audit_log(audit_get_loginuid(current->audit_context), 0,
		       AUDIT_MAC_IPSEC_DELSA, err ? 0 : 1, NULL, x);

out:
	spin_unlock(&x->lock);
}

static void xfrm_replay_timer_handler(unsigned long data);

struct xfrm_state *xfrm_state_alloc(void)
{
	struct xfrm_state *x;

	x = kzalloc(sizeof(struct xfrm_state), GFP_ATOMIC);

	if (x) {
		atomic_set(&x->refcnt, 1);
		atomic_set(&x->tunnel_users, 0);
		INIT_HLIST_NODE(&x->bydst);
		INIT_HLIST_NODE(&x->bysrc);
		INIT_HLIST_NODE(&x->byspi);
		init_timer(&x->timer);
		x->timer.function = xfrm_timer_handler;
		x->timer.data	  = (unsigned long)x;
		init_timer(&x->rtimer);
		x->rtimer.function = xfrm_replay_timer_handler;
		x->rtimer.data     = (unsigned long)x;
		x->curlft.add_time = get_seconds();
		x->lft.soft_byte_limit = XFRM_INF;
		x->lft.soft_packet_limit = XFRM_INF;
		x->lft.hard_byte_limit = XFRM_INF;
		x->lft.hard_packet_limit = XFRM_INF;
		x->replay_maxage = 0;
		x->replay_maxdiff = 0;
		spin_lock_init(&x->lock);
	}
	return x;
}
EXPORT_SYMBOL(xfrm_state_alloc);

void __xfrm_state_destroy(struct xfrm_state *x)
{
	BUG_TRAP(x->km.state == XFRM_STATE_DEAD);

	spin_lock_bh(&xfrm_state_gc_lock);
	hlist_add_head(&x->bydst, &xfrm_state_gc_list);
	spin_unlock_bh(&xfrm_state_gc_lock);
	schedule_work(&xfrm_state_gc_work);
}
EXPORT_SYMBOL(__xfrm_state_destroy);

int __xfrm_state_delete(struct xfrm_state *x)
{
	int err = -ESRCH;

	if (x->km.state != XFRM_STATE_DEAD) {
		x->km.state = XFRM_STATE_DEAD;
		spin_lock(&xfrm_state_lock);
		hlist_del(&x->bydst);
		hlist_del(&x->bysrc);
		if (x->id.spi)
			hlist_del(&x->byspi);
		xfrm_state_num--;
		spin_unlock(&xfrm_state_lock);

		/* All xfrm_state objects are created by xfrm_state_alloc.
		 * The xfrm_state_alloc call gives a reference, and that
		 * is what we are dropping here.
		 */
		__xfrm_state_put(x);
		err = 0;
	}

	return err;
}
EXPORT_SYMBOL(__xfrm_state_delete);

int xfrm_state_delete(struct xfrm_state *x)
{
	int err;

	spin_lock_bh(&x->lock);
	err = __xfrm_state_delete(x);
	spin_unlock_bh(&x->lock);

	return err;
}
EXPORT_SYMBOL(xfrm_state_delete);

#ifdef CONFIG_SECURITY_NETWORK_XFRM
static inline int
xfrm_state_flush_secctx_check(u8 proto, struct xfrm_audit *audit_info)
{
	int i, err = 0;

	for (i = 0; i <= xfrm_state_hmask; i++) {
		struct hlist_node *entry;
		struct xfrm_state *x;

		hlist_for_each_entry(x, entry, xfrm_state_bydst+i, bydst) {
			if (xfrm_id_proto_match(x->id.proto, proto) &&
			   (err = security_xfrm_state_delete(x)) != 0) {
				xfrm_audit_log(audit_info->loginuid,
					       audit_info->secid,
					       AUDIT_MAC_IPSEC_DELSA,
					       0, NULL, x);

				return err;
			}
		}
	}

	return err;
}
#else
static inline int
xfrm_state_flush_secctx_check(u8 proto, struct xfrm_audit *audit_info)
{
	return 0;
}
#endif

int xfrm_state_flush(u8 proto, struct xfrm_audit *audit_info)
{
	int i, err = 0;

	spin_lock_bh(&xfrm_state_lock);
	err = xfrm_state_flush_secctx_check(proto, audit_info);
	if (err)
		goto out;

	for (i = 0; i <= xfrm_state_hmask; i++) {
		struct hlist_node *entry;
		struct xfrm_state *x;
restart:
		hlist_for_each_entry(x, entry, xfrm_state_bydst+i, bydst) {
			if (!xfrm_state_kern(x) &&
			    xfrm_id_proto_match(x->id.proto, proto)) {
				xfrm_state_hold(x);
				spin_unlock_bh(&xfrm_state_lock);

				err = xfrm_state_delete(x);
				xfrm_audit_log(audit_info->loginuid,
					       audit_info->secid,
					       AUDIT_MAC_IPSEC_DELSA,
					       err ? 0 : 1, NULL, x);
				xfrm_state_put(x);

				spin_lock_bh(&xfrm_state_lock);
				goto restart;
			}
		}
	}
	err = 0;

out:
	spin_unlock_bh(&xfrm_state_lock);
	wake_up(&km_waitq);
	return err;
}
EXPORT_SYMBOL(xfrm_state_flush);

void xfrm_sad_getinfo(struct xfrmk_sadinfo *si)
{
	spin_lock_bh(&xfrm_state_lock);
	si->sadcnt = xfrm_state_num;
	si->sadhcnt = xfrm_state_hmask;
	si->sadhmcnt = xfrm_state_hashmax;
	spin_unlock_bh(&xfrm_state_lock);
}
EXPORT_SYMBOL(xfrm_sad_getinfo);

static int
xfrm_init_tempsel(struct xfrm_state *x, struct flowi *fl,
		  struct xfrm_tmpl *tmpl,
		  xfrm_address_t *daddr, xfrm_address_t *saddr,
		  unsigned short family)
{
	struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family);
	if (!afinfo)
		return -1;
	afinfo->init_tempsel(x, fl, tmpl, daddr, saddr);
	xfrm_state_put_afinfo(afinfo);
	return 0;
}

static struct xfrm_state *__xfrm_state_lookup(xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family)
{
	unsigned int h = xfrm_spi_hash(daddr, spi, proto, family);
	struct xfrm_state *x;
	struct hlist_node *entry;

	hlist_for_each_entry(x, entry, xfrm_state_byspi+h, byspi) {
		if (x->props.family != family ||
		    x->id.spi       != spi ||
		    x->id.proto     != proto)
			continue;

		switch (family) {
		case AF_INET:
			if (x->id.daddr.a4 != daddr->a4)
				continue;
			break;
		case AF_INET6:
			if (!ipv6_addr_equal((struct in6_addr *)daddr,
					     (struct in6_addr *)
					     x->id.daddr.a6))
				continue;
			break;
		}

		xfrm_state_hold(x);
		return x;
	}

	return NULL;
}

static struct xfrm_state *__xfrm_state_lookup_byaddr(xfrm_address_t *daddr, xfrm_address_t *saddr, u8 proto, unsigned short family)
{
	unsigned int h = xfrm_src_hash(daddr, saddr, family);
	struct xfrm_state *x;
	struct hlist_node *entry;

	hlist_for_each_entry(x, entry, xfrm_state_bysrc+h, bysrc) {
		if (x->props.family != family ||
		    x->id.proto     != proto)
			continue;

		switch (family) {
		case AF_INET:
			if (x->id.daddr.a4 != daddr->a4 ||
			    x->props.saddr.a4 != saddr->a4)
				continue;
			break;
		case AF_INET6:
			if (!ipv6_addr_equal((struct in6_addr *)daddr,
					     (struct in6_addr *)
					     x->id.daddr.a6) ||
			    !ipv6_addr_equal((struct in6_addr *)saddr,
					     (struct in6_addr *)
					     x->props.saddr.a6))
				continue;
			break;
		}

		xfrm_state_hold(x);
		return x;
	}

	return NULL;
}

static inline struct xfrm_state *
__xfrm_state_locate(struct xfrm_state *x, int use_spi, int family)
{
	if (use_spi)
		return __xfrm_state_lookup(&x->id.daddr, x->id.spi,
					   x->id.proto, family);
	else
		return __xfrm_state_lookup_byaddr(&x->id.daddr,
						  &x->props.saddr,
						  x->id.proto, family);
}

static void xfrm_hash_grow_check(int have_hash_collision)
{
	if (have_hash_collision &&
	    (xfrm_state_hmask + 1) < xfrm_state_hashmax &&
	    xfrm_state_num > xfrm_state_hmask)
		schedule_work(&xfrm_hash_work);
}

struct xfrm_state *
xfrm_state_find(xfrm_address_t *daddr, xfrm_address_t *saddr,
		struct flowi *fl, struct xfrm_tmpl *tmpl,
		struct xfrm_policy *pol, int *err,
		unsigned short family)
{
	unsigned int h = xfrm_dst_hash(daddr, saddr, tmpl->reqid, family);
	struct hlist_node *entry;
	struct xfrm_state *x, *x0;
	int acquire_in_progress = 0;
	int error = 0;
	struct xfrm_state *best = NULL;

	spin_lock_bh(&xfrm_state_lock);
	hlist_for_each_entry(x, entry, xfrm_state_bydst+h, bydst) {
		if (x->props.family == family &&
		    x->props.reqid == tmpl->reqid &&
		    !(x->props.flags & XFRM_STATE_WILDRECV) &&
		    xfrm_state_addr_check(x, daddr, saddr, family) &&
		    tmpl->mode == x->props.mode &&
		    tmpl->id.proto == x->id.proto &&
		    (tmpl->id.spi == x->id.spi || !tmpl->id.spi)) {
			/* Resolution logic:
			   1. There is a valid state with matching selector.
			      Done.
			   2. Valid state with inappropriate selector. Skip.

			   Entering area of "sysdeps".

			   3. If state is not valid, selector is temporary,
			      it selects only session which triggered
			      previous resolution. Key manager will do
			      something to install a state with proper
			      selector.
			 */
			if (x->km.state == XFRM_STATE_VALID) {
				if (!xfrm_selector_match(&x->sel, fl, x->sel.family) ||
				    !security_xfrm_state_pol_flow_match(x, pol, fl))
					continue;
				if (!best ||
				    best->km.dying > x->km.dying ||
				    (best->km.dying == x->km.dying &&
				     best->curlft.add_time < x->curlft.add_time))
					best = x;
			} else if (x->km.state == XFRM_STATE_ACQ) {
				acquire_in_progress = 1;
			} else if (x->km.state == XFRM_STATE_ERROR ||
				   x->km.state == XFRM_STATE_EXPIRED) {
				if (xfrm_selector_match(&x->sel, fl, x->sel.family) &&
				    security_xfrm_state_pol_flow_match(x, pol, fl))
					error = -ESRCH;
			}
		}
	}

	x = best;
	if (!x && !error && !acquire_in_progress) {
		if (tmpl->id.spi &&
		    (x0 = __xfrm_state_lookup(daddr, tmpl->id.spi,
					      tmpl->id.proto, family)) != NULL) {
			xfrm_state_put(x0);
			error = -EEXIST;
			goto out;
		}
		x = xfrm_state_alloc();
		if (x == NULL) {
			error = -ENOMEM;
			goto out;
		}
		/* Initialize temporary selector matching only
		 * to current session. */
		xfrm_init_tempsel(x, fl, tmpl, daddr, saddr, family);

		error = security_xfrm_state_alloc_acquire(x, pol->security, fl->secid);
		if (error) {
			x->km.state = XFRM_STATE_DEAD;
			xfrm_state_put(x);
			x = NULL;
			goto out;
		}

		if (km_query(x, tmpl, pol) == 0) {
			x->km.state = XFRM_STATE_ACQ;
			hlist_add_head(&x->bydst, xfrm_state_bydst+h);
			h = xfrm_src_hash(daddr, saddr, family);
			hlist_add_head(&x->bysrc, xfrm_state_bysrc+h);
			if (x->id.spi) {
				h = xfrm_spi_hash(&x->id.daddr, x->id.spi, x->id.proto, family);
				hlist_add_head(&x->byspi, xfrm_state_byspi+h);
			}
			x->lft.hard_add_expires_seconds = sysctl_xfrm_acq_expires;
			x->timer.expires = jiffies + sysctl_xfrm_acq_expires*HZ;
			add_timer(&x->timer);
			xfrm_state_num++;
			xfrm_hash_grow_check(x->bydst.next != NULL);
		} else {
			x->km.state = XFRM_STATE_DEAD;
			xfrm_state_put(x);
			x = NULL;
			error = -ESRCH;
		}
	}
out:
	if (x)
		xfrm_state_hold(x);
	else
		*err = acquire_in_progress ? -EAGAIN : error;
	spin_unlock_bh(&xfrm_state_lock);
	return x;
}

struct xfrm_state *
xfrm_stateonly_find(xfrm_address_t *daddr, xfrm_address_t *saddr,
		    unsigned short family, u8 mode, u8 proto, u32 reqid)
{
	unsigned int h = xfrm_dst_hash(daddr, saddr, reqid, family);
	struct xfrm_state *rx = NULL, *x = NULL;
	struct hlist_node *entry;

	spin_lock(&xfrm_state_lock);
	hlist_for_each_entry(x, entry, xfrm_state_bydst+h, bydst) {
		if (x->props.family == family &&
		    x->props.reqid == reqid &&
		    !(x->props.flags & XFRM_STATE_WILDRECV) &&
		    xfrm_state_addr_check(x, daddr, saddr, family) &&
		    mode == x->props.mode &&
		    proto == x->id.proto &&
		    x->km.state == XFRM_STATE_VALID) {
			rx = x;
			break;
		}
	}

	if (rx)
		xfrm_state_hold(rx);
	spin_unlock(&xfrm_state_lock);


	return rx;
}
EXPORT_SYMBOL(xfrm_stateonly_find);

static void __xfrm_state_insert(struct xfrm_state *x)
{
	unsigned int h;

	x->genid = ++xfrm_state_genid;

	h = xfrm_dst_hash(&x->id.daddr, &x->props.saddr,