aboutsummaryrefslogtreecommitdiffstats
path: root/include/linux/srcu.h
blob: 55a5c52cbb25a7eee3dee42542016a65dd9db5c7 (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
/*
 * Sleepable Read-Copy Update mechanism for mutual exclusion
 *
 * 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.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
 *
 * Copyright (C) IBM Corporation, 2006
 *
 * Author: Paul McKenney <paulmck@us.ibm.com>
 *
 * For detailed explanation of Read-Copy Update mechanism see -
 * 		Documentation/RCU/ *.txt
 *
 */

#ifndef _LINUX_SRCU_H
#define _LINUX_SRCU_H

#include <linux/mutex.h>
#include <linux/rcupdate.h>
#include <linux/workqueue.h>

struct srcu_struct_array {
	unsigned long c[2];
	unsigned long seq[2];
};

struct rcu_batch {
	struct rcu_head *head, **tail;
};

struct srcu_struct {
	unsigned completed;
	struct srcu_struct_array __percpu *per_cpu_ref;
	spinlock_t queue_lock; /* protect ->batch_queue, ->running */
	bool running;
	/* callbacks just queued */
	struct rcu_batch batch_queue;
	/* callbacks try to do the first check_zero */
	struct rcu_batch batch_check0;
	/* callbacks done with the first check_zero and the flip */
	struct rcu_batch batch_check1;
	struct rcu_batch batch_done;
	struct delayed_work work;
#ifdef CONFIG_DEBUG_LOCK_ALLOC
	struct lockdep_map dep_map;
#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
};

#ifdef CONFIG_DEBUG_LOCK_ALLOC

int __init_srcu_struct(struct srcu_struct *sp, const char *name,
		       struct lock_class_key *key);

#define init_srcu_struct(sp) \
({ \
	static struct lock_class_key __srcu_key; \
	\
	__init_srcu_struct((sp), #sp, &__srcu_key); \
})

#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */

int init_srcu_struct(struct srcu_struct *sp);

#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */

/**
 * call_srcu() - Queue a callback for invocation after an SRCU grace period
 * @sp: srcu_struct in queue the callback
 * @head: structure to be used for queueing the SRCU callback.
 * @func: function to be invoked after the SRCU grace period
 *
 * The callback function will be invoked some time after a full SRCU
 * grace period elapses, in other words after all pre-existing SRCU
 * read-side critical sections have completed.  However, the callback
 * function might well execute concurrently with other SRCU read-side
 * critical sections that started after call_srcu() was invoked.  SRCU
 * read-side critical sections are delimited by srcu_read_lock() and
 * srcu_read_unlock(), and may be nested.
 *
 * The callback will be invoked from process context, but must nevertheless
 * be fast and must not block.
 */
void call_srcu(struct srcu_struct *sp, struct rcu_head *head,
		void (*func)(struct rcu_head *head));

void cleanup_srcu_struct(struct srcu_struct *sp);
int __srcu_read_lock(struct srcu_struct *sp) __acquires(sp);
void __srcu_read_unlock(struct srcu_struct *sp, int idx) __releases(sp);
void synchronize_srcu(struct srcu_struct *sp);
void synchronize_srcu_expedited(struct srcu_struct *sp);
long srcu_batches_completed(struct srcu_struct *sp);
void srcu_barrier(struct srcu_struct *sp);

#ifdef CONFIG_DEBUG_LOCK_ALLOC

/**
 * srcu_read_lock_held - might we be in SRCU read-side critical section?
 *
 * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an SRCU
 * read-side critical section.  In absence of CONFIG_DEBUG_LOCK_ALLOC,
 * this assumes we are in an SRCU read-side critical section unless it can
 * prove otherwise.
 *
 * Checks debug_lockdep_rcu_enabled() to prevent false positives during boot
 * and while lockdep is disabled.
 *
 * Note that if the CPU is in the idle loop from an RCU point of view
 * (ie: that we are in the section between rcu_idle_enter() and
 * rcu_idle_exit()) then srcu_read_lock_held() returns false even if
 * the CPU did an srcu_read_lock().  The reason for this is that RCU
 * ignores CPUs that are in such a section, considering these as in
 * extended quiescent state, so such a CPU is effectively never in an
 * RCU read-side critical section regardless of what RCU primitives it
 * invokes.  This state of affairs is required --- we need to keep an
 * RCU-free window in idle where the CPU may possibly enter into low
 * power mode. This way we can notice an extended quiescent state to
 * other CPUs that started a grace period. Otherwise we would delay any
 * grace period as long as we run in the idle task.
 *
 * Similarly, we avoid claiming an SRCU read lock held if the current
 * CPU is offline.
 */
static inline int srcu_read_lock_held(struct srcu_struct *sp)
{
	if (!debug_lockdep_rcu_enabled())
		return 1;
	if (rcu_is_cpu_idle())
		return 0;
	if (!rcu_lockdep_current_cpu_online())
		return 0;
	return lock_is_held(&sp->dep_map);
}

#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */

static inline int srcu_read_lock_held(struct srcu_struct *sp)
{
	return 1;
}

#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */

/**
 * srcu_dereference_check - fetch SRCU-protected pointer for later dereferencing
 * @p: the pointer to fetch and protect for later dereferencing
 * @sp: pointer to the srcu_struct, which is used to check that we
 *	really are in an SRCU read-side critical section.
 * @c: condition to check for update-side use
 *
 * If PROVE_RCU is enabled, invoking this outside of an RCU read-side
 * critical section will result in an RCU-lockdep splat, unless @c evaluates
 * to 1.  The @c argument will normally be a logical expression containing
 * lockdep_is_held() calls.
 */
#define srcu_dereference_check(p, sp, c) \
	__rcu_dereference_check((p), srcu_read_lock_held(sp) || (c), __rcu)

/**
 * srcu_dereference - fetch SRCU-protected pointer for later dereferencing
 * @p: the pointer to fetch and protect for later dereferencing
 * @sp: pointer to the srcu_struct, which is used to check that we
 *	really are in an SRCU read-side critical section.
 *
 * Makes rcu_dereference_check() do the dirty work.  If PROVE_RCU
 * is enabled, invoking this outside of an RCU read-side critical
 * section will result in an RCU-lockdep splat.
 */
#define srcu_dereference(p, sp) srcu_dereference_check((p), (sp), 0)

/**
 * srcu_read_lock - register a new reader for an SRCU-protected structure.
 * @sp: srcu_struct in which to register the new reader.
 *
 * Enter an SRCU read-side critical section.  Note that SRCU read-side
 * critical sections may be nested.  However, it is illegal to
 * call anything that waits on an SRCU grace period for the same
 * srcu_struct, whether directly or indirectly.  Please note that
 * one way to indirectly wait on an SRCU grace period is to acquire
 * a mutex that is held elsewhere while calling synchronize_srcu() or
 * synchronize_srcu_expedited().
 *
 * Note that srcu_read_lock() and the matching srcu_read_unlock() must
 * occur in the same context, for example, it is illegal to invoke
 * srcu_read_unlock() in an irq handler if the matching srcu_read_lock()
 * was invoked in process context.
 */
static inline int srcu_read_lock(struct srcu_struct *sp) __acquires(sp)
{
	int retval = __srcu_read_lock(sp);

	rcu_lock_acquire(&(sp)->dep_map);
	rcu_lockdep_assert(!rcu_is_cpu_idle(),
			   "srcu_read_lock() used illegally while idle");
	return retval;
}

/**
 * srcu_read_unlock - unregister a old reader from an SRCU-protected structure.
 * @sp: srcu_struct in which to unregister the old reader.
 * @idx: return value from corresponding srcu_read_lock().
 *
 * Exit an SRCU read-side critical section.
 */
static inline void srcu_read_unlock(struct srcu_struct *sp, int idx)
	__releases(sp)
{
	rcu_lockdep_assert(!rcu_is_cpu_idle(),
			   "srcu_read_unlock() used illegally while idle");
	rcu_lock_release(&(sp)->dep_map);
	__srcu_read_unlock(sp, idx);
}

/**
 * srcu_read_lock_raw - register a new reader for an SRCU-protected structure.
 * @sp: srcu_struct in which to register the new reader.
 *
 * Enter an SRCU read-side critical section.  Similar to srcu_read_lock(),
 * but avoids the RCU-lockdep checking.  This means that it is legal to
 * use srcu_read_lock_raw() in one context, for example, in an exception
 * handler, and then have the matching srcu_read_unlock_raw() in another
 * context, for example in the task that took the exception.
 *
 * However, the entire SRCU read-side critical section must reside within a
 * single task.  For example, beware of using srcu_read_lock_raw() in
 * a device interrupt handler and srcu_read_unlock() in the interrupted
 * task:  This will not work if interrupts are threaded.
 */
static inline int srcu_read_lock_raw(struct srcu_struct *sp)
{
	unsigned long flags;
	int ret;

	local_irq_save(flags);
	ret =  __srcu_read_lock(sp);
	local_irq_restore(flags);
	return ret;
}

/**
 * srcu_read_unlock_raw - unregister reader from an SRCU-protected structure.
 * @sp: srcu_struct in which to unregister the old reader.
 * @idx: return value from corresponding srcu_read_lock_raw().
 *
 * Exit an SRCU read-side critical section without lockdep-RCU checking.
 * See srcu_read_lock_raw() for more details.
 */
static inline void srcu_read_unlock_raw(struct srcu_struct *sp, int idx)
{
	unsigned long flags;

	local_irq_save(flags);
	__srcu_read_unlock(sp, idx);
	local_irq_restore(flags);
}

#endif
='#n1104'>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 1825 1826 1827 1828
/*
 *  linux/kernel/exit.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 */

#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/interrupt.h>
#include <linux/module.h>
#include <linux/capability.h>
#include <linux/completion.h>
#include <linux/personality.h>
#include <linux/tty.h>
#include <linux/mnt_namespace.h>
#include <linux/iocontext.h>
#include <linux/key.h>
#include <linux/security.h>
#include <linux/cpu.h>
#include <linux/acct.h>
#include <linux/tsacct_kern.h>
#include <linux/file.h>
#include <linux/fdtable.h>
#include <linux/binfmts.h>
#include <linux/nsproxy.h>
#include <linux/pid_namespace.h>
#include <linux/ptrace.h>
#include <linux/profile.h>
#include <linux/mount.h>
#include <linux/proc_fs.h>
#include <linux/kthread.h>
#include <linux/mempolicy.h>
#include <linux/taskstats_kern.h>
#include <linux/delayacct.h>
#include <linux/freezer.h>
#include <linux/cgroup.h>
#include <linux/syscalls.h>
#include <linux/signal.h>
#include <linux/posix-timers.h>
#include <linux/cn_proc.h>
#include <linux/mutex.h>
#include <linux/futex.h>
#include <linux/compat.h>
#include <linux/pipe_fs_i.h>
#include <linux/audit.h> /* for audit_free() */
#include <linux/resource.h>
#include <linux/blkdev.h>
#include <linux/task_io_accounting_ops.h>
#include <linux/tracehook.h>

#include <asm/uaccess.h>
#include <asm/unistd.h>
#include <asm/pgtable.h>
#include <asm/mmu_context.h>

static void exit_mm(struct task_struct * tsk);

static inline int task_detached(struct task_struct *p)
{
	return p->exit_signal == -1;
}

static void __unhash_process(struct task_struct *p)
{
	nr_threads--;
	detach_pid(p, PIDTYPE_PID);
	if (thread_group_leader(p)) {
		detach_pid(p, PIDTYPE_PGID);
		detach_pid(p, PIDTYPE_SID);

		list_del_rcu(&p->tasks);
		__get_cpu_var(process_counts)--;
	}
	list_del_rcu(&p->thread_group);
	list_del_init(&p->sibling);
}

/*
 * This function expects the tasklist_lock write-locked.
 */
static void __exit_signal(struct task_struct *tsk)
{
	struct signal_struct *sig = tsk->signal;
	struct sighand_struct *sighand;

	BUG_ON(!sig);
	BUG_ON(!atomic_read(&sig->count));

	sighand = rcu_dereference(tsk->sighand);
	spin_lock(&sighand->siglock);

	posix_cpu_timers_exit(tsk);
	if (atomic_dec_and_test(&sig->count))
		posix_cpu_timers_exit_group(tsk);
	else {
		/*
		 * If there is any task waiting for the group exit
		 * then notify it:
		 */
		if (sig->group_exit_task && atomic_read(&sig->count) == sig->notify_count)
			wake_up_process(sig->group_exit_task);

		if (tsk == sig->curr_target)
			sig->curr_target = next_thread(tsk);
		/*
		 * Accumulate here the counters for all threads but the
		 * group leader as they die, so they can be added into
		 * the process-wide totals when those are taken.
		 * The group leader stays around as a zombie as long
		 * as there are other threads.  When it gets reaped,
		 * the exit.c code will add its counts into these totals.
		 * We won't ever get here for the group leader, since it
		 * will have been the last reference on the signal_struct.
		 */
		sig->utime = cputime_add(sig->utime, task_utime(tsk));
		sig->stime = cputime_add(sig->stime, task_stime(tsk));
		sig->gtime = cputime_add(sig->gtime, task_gtime(tsk));
		sig->min_flt += tsk->min_flt;
		sig->maj_flt += tsk->maj_flt;
		sig->nvcsw += tsk->nvcsw;
		sig->nivcsw += tsk->nivcsw;
		sig->inblock += task_io_get_inblock(tsk);
		sig->oublock += task_io_get_oublock(tsk);
		task_io_accounting_add(&sig->ioac, &tsk->ioac);
		sig->sum_sched_runtime += tsk->se.sum_exec_runtime;
		sig = NULL; /* Marker for below. */
	}

	__unhash_process(tsk);

	/*
	 * Do this under ->siglock, we can race with another thread
	 * doing sigqueue_free() if we have SIGQUEUE_PREALLOC signals.
	 */
	flush_sigqueue(&tsk->pending);

	tsk->signal = NULL;
	tsk->sighand = NULL;
	spin_unlock(&sighand->siglock);

	__cleanup_sighand(sighand);
	clear_tsk_thread_flag(tsk,TIF_SIGPENDING);
	if (sig) {
		flush_sigqueue(&sig->shared_pending);
		taskstats_tgid_free(sig);
		__cleanup_signal(sig);
	}
}

static void delayed_put_task_struct(struct rcu_head *rhp)
{
	put_task_struct(container_of(rhp, struct task_struct, rcu));
}


void release_task(struct task_struct * p)
{
	struct task_struct *leader;
	int zap_leader;
repeat:
	tracehook_prepare_release_task(p);
	atomic_dec(&p->user->processes);
	proc_flush_task(p);
	write_lock_irq(&tasklist_lock);
	tracehook_finish_release_task(p);
	__exit_signal(p);

	/*
	 * If we are the last non-leader member of the thread
	 * group, and the leader is zombie, then notify the
	 * group leader's parent process. (if it wants notification.)
	 */
	zap_leader = 0;
	leader = p->group_leader;
	if (leader != p && thread_group_empty(leader) && leader->exit_state == EXIT_ZOMBIE) {
		BUG_ON(task_detached(leader));
		do_notify_parent(leader, leader->exit_signal);
		/*
		 * If we were the last child thread and the leader has
		 * exited already, and the leader's parent ignores SIGCHLD,
		 * then we are the one who should release the leader.
		 *
		 * do_notify_parent() will have marked it self-reaping in
		 * that case.
		 */
		zap_leader = task_detached(leader);

		/*
		 * This maintains the invariant that release_task()
		 * only runs on a task in EXIT_DEAD, just for sanity.
		 */
		if (zap_leader)
			leader->exit_state = EXIT_DEAD;
	}

	write_unlock_irq(&tasklist_lock);
	release_thread(p);
	call_rcu(&p->rcu, delayed_put_task_struct);

	p = leader;
	if (unlikely(zap_leader))
		goto repeat;
}

/*
 * This checks not only the pgrp, but falls back on the pid if no
 * satisfactory pgrp is found. I dunno - gdb doesn't work correctly
 * without this...
 *
 * The caller must hold rcu lock or the tasklist lock.
 */
struct pid *session_of_pgrp(struct pid *pgrp)
{
	struct task_struct *p;
	struct pid *sid = NULL;

	p = pid_task(pgrp, PIDTYPE_PGID);
	if (p == NULL)
		p = pid_task(pgrp, PIDTYPE_PID);
	if (p != NULL)
		sid = task_session(p);

	return sid;
}

/*
 * Determine if a process group is "orphaned", according to the POSIX
 * definition in 2.2.2.52.  Orphaned process groups are not to be affected
 * by terminal-generated stop signals.  Newly orphaned process groups are
 * to receive a SIGHUP and a SIGCONT.
 *
 * "I ask you, have you ever known what it is to be an orphan?"
 */
static int will_become_orphaned_pgrp(struct pid *pgrp, struct task_struct *ignored_task)
{
	struct task_struct *p;

	do_each_pid_task(pgrp, PIDTYPE_PGID, p) {
		if ((p == ignored_task) ||
		    (p->exit_state && thread_group_empty(p)) ||
		    is_global_init(p->real_parent))
			continue;

		if (task_pgrp(p->real_parent) != pgrp &&
		    task_session(p->real_parent) == task_session(p))
			return 0;
	} while_each_pid_task(pgrp, PIDTYPE_PGID, p);

	return 1;
}

int is_current_pgrp_orphaned(void)
{
	int retval;

	read_lock(&tasklist_lock);
	retval = will_become_orphaned_pgrp(task_pgrp(current), NULL);
	read_unlock(&tasklist_lock);

	return retval;
}

static int has_stopped_jobs(struct pid *pgrp)
{
	int retval = 0;
	struct task_struct *p;

	do_each_pid_task(pgrp, PIDTYPE_PGID, p) {
		if (!task_is_stopped(p))
			continue;
		retval = 1;
		break;
	} while_each_pid_task(pgrp, PIDTYPE_PGID, p);
	return retval;
}

/*
 * Check to see if any process groups have become orphaned as
 * a result of our exiting, and if they have any stopped jobs,
 * send them a SIGHUP and then a SIGCONT. (POSIX 3.2.2.2)
 */
static void
kill_orphaned_pgrp(struct task_struct *tsk, struct task_struct *parent)
{
	struct pid *pgrp = task_pgrp(tsk);
	struct task_struct *ignored_task = tsk;

	if (!parent)
		 /* exit: our father is in a different pgrp than
		  * we are and we were the only connection outside.
		  */
		parent = tsk->real_parent;
	else
		/* reparent: our child is in a different pgrp than
		 * we are, and it was the only connection outside.
		 */
		ignored_task = NULL;

	if (task_pgrp(parent) != pgrp &&
	    task_session(parent) == task_session(tsk) &&
	    will_become_orphaned_pgrp(pgrp, ignored_task) &&
	    has_stopped_jobs(pgrp)) {
		__kill_pgrp_info(SIGHUP, SEND_SIG_PRIV, pgrp);
		__kill_pgrp_info(SIGCONT, SEND_SIG_PRIV, pgrp);
	}
}

/**
 * reparent_to_kthreadd - Reparent the calling kernel thread to kthreadd
 *
 * If a kernel thread is launched as a result of a system call, or if
 * it ever exits, it should generally reparent itself to kthreadd so it
 * isn't in the way of other processes and is correctly cleaned up on exit.
 *
 * The various task state such as scheduling policy and priority may have
 * been inherited from a user process, so we reset them to sane values here.
 *
 * NOTE that reparent_to_kthreadd() gives the caller full capabilities.
 */
static void reparent_to_kthreadd(void)
{
	write_lock_irq(&tasklist_lock);

	ptrace_unlink(current);
	/* Reparent to init */
	current->real_parent = current->parent = kthreadd_task;
	list_move_tail(&current->sibling, &current->real_parent->children);

	/* Set the exit signal to SIGCHLD so we signal init on exit */
	current->exit_signal = SIGCHLD;

	if (task_nice(current) < 0)
		set_user_nice(current, 0);
	/* cpus_allowed? */
	/* rt_priority? */
	/* signals? */
	security_task_reparent_to_init(current);
	memcpy(current->signal->rlim, init_task.signal->rlim,
	       sizeof(current->signal->rlim));
	atomic_inc(&(INIT_USER->__count));
	write_unlock_irq(&tasklist_lock);
	switch_uid(INIT_USER);
}

void __set_special_pids(struct pid *pid)
{
	struct task_struct *curr = current->group_leader;
	pid_t nr = pid_nr(pid);

	if (task_session(curr) != pid) {
		change_pid(curr, PIDTYPE_SID, pid);
		set_task_session(curr, nr);
	}
	if (task_pgrp(curr) != pid) {
		change_pid(curr, PIDTYPE_PGID, pid);
		set_task_pgrp(curr, nr);
	}
}

static void set_special_pids(struct pid *pid)
{
	write_lock_irq(&tasklist_lock);
	__set_special_pids(pid);
	write_unlock_irq(&tasklist_lock);
}

/*
 * Let kernel threads use this to say that they
 * allow a certain signal (since daemonize() will
 * have disabled all of them by default).
 */
int allow_signal(int sig)
{
	if (!valid_signal(sig) || sig < 1)
		return -EINVAL;

	spin_lock_irq(&current->sighand->siglock);
	sigdelset(&current->blocked, sig);
	if (!current->mm) {
		/* Kernel threads handle their own signals.
		   Let the signal code know it'll be handled, so
		   that they don't get converted to SIGKILL or
		   just silently dropped */
		current->sighand->action[(sig)-1].sa.sa_handler = (void __user *)2;
	}
	recalc_sigpending();
	spin_unlock_irq(&current->sighand->siglock);
	return 0;
}

EXPORT_SYMBOL(allow_signal);

int disallow_signal(int sig)
{
	if (!valid_signal(sig) || sig < 1)
		return -EINVAL;

	spin_lock_irq(&current->sighand->siglock);
	current->sighand->action[(sig)-1].sa.sa_handler = SIG_IGN;
	recalc_sigpending();
	spin_unlock_irq(&current->sighand->siglock);
	return 0;
}

EXPORT_SYMBOL(disallow_signal);

/*
 *	Put all the gunge required to become a kernel thread without
 *	attached user resources in one place where it belongs.
 */

void daemonize(const char *name, ...)
{
	va_list args;
	struct fs_struct *fs;
	sigset_t blocked;

	va_start(args, name);
	vsnprintf(current->comm, sizeof(current->comm), name, args);
	va_end(args);

	/*
	 * If we were started as result of loading a module, close all of the
	 * user space pages.  We don't need them, and if we didn't close them
	 * they would be locked into memory.
	 */
	exit_mm(current);
	/*
	 * We don't want to have TIF_FREEZE set if the system-wide hibernation
	 * or suspend transition begins right now.
	 */
	current->flags |= (PF_NOFREEZE | PF_KTHREAD);

	if (current->nsproxy != &init_nsproxy) {
		get_nsproxy(&init_nsproxy);
		switch_task_namespaces(current, &init_nsproxy);
	}
	set_special_pids(&init_struct_pid);
	proc_clear_tty(current);

	/* Block and flush all signals */
	sigfillset(&blocked);
	sigprocmask(SIG_BLOCK, &blocked, NULL);
	flush_signals(current);

	/* Become as one with the init task */

	exit_fs(current);	/* current->fs->count--; */
	fs = init_task.fs;
	current->fs = fs;
	atomic_inc(&fs->count);

	exit_files(current);
	current->files = init_task.files;
	atomic_inc(&current->files->count);

	reparent_to_kthreadd();
}

EXPORT_SYMBOL(daemonize);

static void close_files(struct files_struct * files)
{
	int i, j;
	struct fdtable *fdt;

	j = 0;

	/*
	 * It is safe to dereference the fd table without RCU or
	 * ->file_lock because this is the last reference to the
	 * files structure.
	 */
	fdt = files_fdtable(files);
	for (;;) {
		unsigned long set;
		i = j * __NFDBITS;
		if (i >= fdt->max_fds)
			break;
		set = fdt->open_fds->fds_bits[j++];
		while (set) {
			if (set & 1) {
				struct file * file = xchg(&fdt->fd[i], NULL);
				if (file) {
					filp_close(file, files);
					cond_resched();
				}
			}
			i++;
			set >>= 1;
		}
	}
}

struct files_struct *get_files_struct(struct task_struct *task)
{
	struct files_struct *files;

	task_lock(task);
	files = task->files;
	if (files)
		atomic_inc(&files->count);
	task_unlock(task);

	return files;
}

void put_files_struct(struct files_struct *files)
{
	struct fdtable *fdt;

	if (atomic_dec_and_test(&files->count)) {
		close_files(files);
		/*
		 * Free the fd and fdset arrays if we expanded them.
		 * If the fdtable was embedded, pass files for freeing
		 * at the end of the RCU grace period. Otherwise,
		 * you can free files immediately.
		 */
		fdt = files_fdtable(files);
		if (fdt != &files->fdtab)
			kmem_cache_free(files_cachep, files);
		free_fdtable(fdt);
	}
}

void reset_files_struct(struct files_struct *files)
{
	struct task_struct *tsk = current;
	struct files_struct *old;

	old = tsk->files;
	task_lock(tsk);
	tsk->files = files;
	task_unlock(tsk);
	put_files_struct(old);
}

void exit_files(struct task_struct *tsk)
{
	struct files_struct * files = tsk->files;

	if (files) {
		task_lock(tsk);
		tsk->files = NULL;
		task_unlock(tsk);
		put_files_struct(files);
	}
}

void put_fs_struct(struct fs_struct *fs)
{
	/* No need to hold fs->lock if we are killing it */
	if (atomic_dec_and_test(&fs->count)) {
		path_put(&fs->root);
		path_put(&fs->pwd);
		kmem_cache_free(fs_cachep, fs);
	}
}

void exit_fs(struct task_struct *tsk)
{
	struct fs_struct * fs = tsk->fs;

	if (fs) {
		task_lock(tsk);
		tsk->fs = NULL;
		task_unlock(tsk);
		put_fs_struct(fs);
	}
}

EXPORT_SYMBOL_GPL(exit_fs);

#ifdef CONFIG_MM_OWNER
/*
 * Task p is exiting and it owned mm, lets find a new owner for it
 */
static inline int
mm_need_new_owner(struct mm_struct *mm, struct task_struct *p)
{
	/*
	 * If there are other users of the mm and the owner (us) is exiting
	 * we need to find a new owner to take on the responsibility.
	 */
	if (!mm)
		return 0;
	if (atomic_read(&mm->mm_users) <= 1)
		return 0;
	if (mm->owner != p)
		return 0;
	return 1;
}

void mm_update_next_owner(struct mm_struct *mm)
{
	struct task_struct *c, *g, *p = current;

retry:
	if (!mm_need_new_owner(mm, p))
		return;

	read_lock(&tasklist_lock);
	/*
	 * Search in the children
	 */
	list_for_each_entry(c, &p->children, sibling) {
		if (c->mm == mm)
			goto assign_new_owner;
	}

	/*
	 * Search in the siblings
	 */
	list_for_each_entry(c, &p->parent->children, sibling) {
		if (c->mm == mm)
			goto assign_new_owner;
	}

	/*
	 * Search through everything else. We should not get
	 * here often
	 */
	do_each_thread(g, c) {
		if (c->mm == mm)
			goto assign_new_owner;
	} while_each_thread(g, c);

	read_unlock(&tasklist_lock);
	return;

assign_new_owner:
	BUG_ON(c == p);
	get_task_struct(c);
	/*
	 * The task_lock protects c->mm from changing.
	 * We always want mm->owner->mm == mm
	 */
	task_lock(c);
	/*
	 * Delay read_unlock() till we have the task_lock()
	 * to ensure that c does not slip away underneath us
	 */
	read_unlock(&tasklist_lock);
	if (c->mm != mm) {
		task_unlock(c);
		put_task_struct(c);
		goto retry;
	}
	cgroup_mm_owner_callbacks(mm->owner, c);
	mm->owner = c;
	task_unlock(c);
	put_task_struct(c);
}
#endif /* CONFIG_MM_OWNER */

/*
 * Turn us into a lazy TLB process if we
 * aren't already..
 */
static void exit_mm(struct task_struct * tsk)
{
	struct mm_struct *mm = tsk->mm;
	struct core_state *core_state;

	mm_release(tsk, mm);
	if (!mm)
		return;
	/*
	 * Serialize with any possible pending coredump.
	 * We must hold mmap_sem around checking core_state
	 * and clearing tsk->mm.  The core-inducing thread
	 * will increment ->nr_threads for each thread in the
	 * group with ->mm != NULL.
	 */
	down_read(&mm->mmap_sem);
	core_state = mm->core_state;
	if (core_state) {
		struct core_thread self;
		up_read(&mm->mmap_sem);

		self.task = tsk;
		self.next = xchg(&core_state->dumper.next, &self);
		/*
		 * Implies mb(), the result of xchg() must be visible
		 * to core_state->dumper.
		 */
		if (atomic_dec_and_test(&core_state->nr_threads))
			complete(&core_state->startup);

		for (;;) {
			set_task_state(tsk, TASK_UNINTERRUPTIBLE);
			if (!self.task) /* see coredump_finish() */
				break;
			schedule();
		}
		__set_task_state(tsk, TASK_RUNNING);
		down_read(&mm->mmap_sem);
	}
	atomic_inc(&mm->mm_count);
	BUG_ON(mm != tsk->active_mm);
	/* more a memory barrier than a real lock */
	task_lock(tsk);
	tsk->mm = NULL;
	up_read(&mm->mmap_sem);
	enter_lazy_tlb(mm, current);
	/* We don't want this task to be frozen prematurely */
	clear_freeze_flag(tsk);
	task_unlock(tsk);
	mm_update_next_owner(mm);
	mmput(mm);
}

/*
 * Return nonzero if @parent's children should reap themselves.
 *
 * Called with write_lock_irq(&tasklist_lock) held.
 */
static int ignoring_children(struct task_struct *parent)
{
	int ret;
	struct sighand_struct *psig = parent->sighand;
	unsigned long flags;
	spin_lock_irqsave(&psig->siglock, flags);
	ret = (psig->action[SIGCHLD-1].sa.sa_handler == SIG_IGN ||
	       (psig->action[SIGCHLD-1].sa.sa_flags & SA_NOCLDWAIT));
	spin_unlock_irqrestore(&psig->siglock, flags);
	return ret;
}

/*
 * Detach all tasks we were using ptrace on.
 * Any that need to be release_task'd are put on the @dead list.
 *
 * Called with write_lock(&tasklist_lock) held.
 */
static void ptrace_exit(struct task_struct *parent, struct list_head *dead)
{
	struct task_struct *p, *n;
	int ign = -1;

	list_for_each_entry_safe(p, n, &parent->ptraced, ptrace_entry) {
		__ptrace_unlink(p);

		if (p->exit_state != EXIT_ZOMBIE)
			continue;

		/*
		 * If it's a zombie, our attachedness prevented normal
		 * parent notification or self-reaping.  Do notification
		 * now if it would have happened earlier.  If it should
		 * reap itself, add it to the @dead list.  We can't call
		 * release_task() here because we already hold tasklist_lock.
		 *
		 * If it's our own child, there is no notification to do.
		 * But if our normal children self-reap, then this child
		 * was prevented by ptrace and we must reap it now.
		 */
		if (!task_detached(p) && thread_group_empty(p)) {
			if (!same_thread_group(p->real_parent, parent))
				do_notify_parent(p, p->exit_signal);
			else {
				if (ign < 0)
					ign = ignoring_children(parent);
				if (ign)
					p->exit_signal = -1;
			}
		}

		if (task_detached(p)) {
			/*
			 * Mark it as in the process of being reaped.
			 */
			p->exit_state = EXIT_DEAD;
			list_add(&p->ptrace_entry, dead);
		}
	}
}

/*
 * Finish up exit-time ptrace cleanup.
 *
 * Called without locks.
 */
static void ptrace_exit_finish(struct task_struct *parent,
			       struct list_head *dead)
{
	struct task_struct *p, *n;

	BUG_ON(!list_empty(&parent->ptraced));

	list_for_each_entry_safe(p, n, dead, ptrace_entry) {
		list_del_init(&p->ptrace_entry);
		release_task(p);
	}
}

static void reparent_thread(struct task_struct *p, struct task_struct *father)
{
	if (p->pdeath_signal)
		/* We already hold the tasklist_lock here.  */
		group_send_sig_info(p->pdeath_signal, SEND_SIG_NOINFO, p);

	list_move_tail(&p->sibling, &p->real_parent->children);

	/* If this is a threaded reparent there is no need to
	 * notify anyone anything has happened.
	 */
	if (same_thread_group(p->real_parent, father))
		return;

	/* We don't want people slaying init.  */
	if (!task_detached(p))
		p->exit_signal = SIGCHLD;

	/* If we'd notified the old parent about this child's death,
	 * also notify the new parent.
	 */
	if (!ptrace_reparented(p) &&
	    p->exit_state == EXIT_ZOMBIE &&
	    !task_detached(p) && thread_group_empty(p))
		do_notify_parent(p, p->exit_signal);

	kill_orphaned_pgrp(p, father);
}

/*
 * When we die, we re-parent all our children.
 * Try to give them to another thread in our thread
 * group, and if no such member exists, give it to
 * the child reaper process (ie "init") in our pid
 * space.
 */
static struct task_struct *find_new_reaper(struct task_struct *father)
{
	struct pid_namespace *pid_ns = task_active_pid_ns(father);
	struct task_struct *thread;

	thread = father;
	while_each_thread(father, thread) {
		if (thread->flags & PF_EXITING)
			continue;
		if (unlikely(pid_ns->child_reaper == father))
			pid_ns->child_reaper = thread;
		return thread;
	}

	if (unlikely(pid_ns->child_reaper == father)) {
		write_unlock_irq(&tasklist_lock);
		if (unlikely(pid_ns == &init_pid_ns))
			panic("Attempted to kill init!");

		zap_pid_ns_processes(pid_ns);
		write_lock_irq(&tasklist_lock);
		/*
		 * We can not clear ->child_reaper or leave it alone.
		 * There may by stealth EXIT_DEAD tasks on ->children,
		 * forget_original_parent() must move them somewhere.
		 */
		pid_ns->child_reaper = init_pid_ns.child_reaper;
	}

	return pid_ns->child_reaper;
}

static void forget_original_parent(struct task_struct *father)
{
	struct task_struct *p, *n, *reaper;
	LIST_HEAD(ptrace_dead);

	write_lock_irq(&tasklist_lock);
	reaper = find_new_reaper(father);
	/*
	 * First clean up ptrace if we were using it.
	 */
	ptrace_exit(father, &ptrace_dead);

	list_for_each_entry_safe(p, n, &father->children, sibling) {
		p->real_parent = reaper;
		if (p->parent == father) {
			BUG_ON(p->ptrace);
			p->parent = p->real_parent;
		}
		reparent_thread(p, father);
	}

	write_unlock_irq(&tasklist_lock);
	BUG_ON(!list_empty(&father->children));

	ptrace_exit_finish(father, &ptrace_dead);
}

/*
 * Send signals to all our closest relatives so that they know
 * to properly mourn us..
 */
static void exit_notify(struct task_struct *tsk, int group_dead)
{
	int signal;
	void *cookie;

	/*
	 * This does two things:
	 *
  	 * A.  Make init inherit all the child processes
	 * B.  Check to see if any process groups have become orphaned
	 *	as a result of our exiting, and if they have any stopped
	 *	jobs, send them a SIGHUP and then a SIGCONT.  (POSIX 3.2.2.2)
	 */
	forget_original_parent(tsk);
	exit_task_namespaces(tsk);

	write_lock_irq(&tasklist_lock);
	if (group_dead)
		kill_orphaned_pgrp(tsk->group_leader, NULL);

	/* Let father know we died
	 *
	 * Thread signals are configurable, but you aren't going to use
	 * that to send signals to arbitary processes.
	 * That stops right now.
	 *
	 * If the parent exec id doesn't match the exec id we saved
	 * when we started then we know the parent has changed security
	 * domain.
	 *
	 * If our self_exec id doesn't match our parent_exec_id then
	 * we have changed execution domain as these two values started
	 * the same after a fork.
	 */
	if (tsk->exit_signal != SIGCHLD && !task_detached(tsk) &&
	    (tsk->parent_exec_id != tsk->real_parent->self_exec_id ||
	     tsk->self_exec_id != tsk->parent_exec_id) &&
	    !capable(CAP_KILL))
		tsk->exit_signal = SIGCHLD;

	signal = tracehook_notify_death(tsk, &cookie, group_dead);
	if (signal >= 0)
		signal = do_notify_parent(tsk, signal);

	tsk->exit_state = signal == DEATH_REAP ? EXIT_DEAD : EXIT_ZOMBIE;

	/* mt-exec, de_thread() is waiting for us */
	if (thread_group_leader(tsk) &&
	    tsk->signal->group_exit_task &&
	    tsk->signal->notify_count < 0)
		wake_up_process(tsk->signal->group_exit_task);

	write_unlock_irq(&tasklist_lock);

	tracehook_report_death(tsk, signal, cookie, group_dead);

	/* If the process is dead, release it - nobody will wait for it */
	if (signal == DEATH_REAP)
		release_task(tsk);
}

#ifdef CONFIG_DEBUG_STACK_USAGE
static void check_stack_usage(void)
{
	static DEFINE_SPINLOCK(low_water_lock);
	static int lowest_to_date = THREAD_SIZE;
	unsigned long *n = end_of_stack(current);
	unsigned long free;

	while (*n == 0)
		n++;
	free = (unsigned long)n - (unsigned long)end_of_stack(current);

	if (free >= lowest_to_date)
		return;

	spin_lock(&low_water_lock);
	if (free < lowest_to_date) {
		printk(KERN_WARNING "%s used greatest stack depth: %lu bytes "
				"left\n",
				current->comm, free);
		lowest_to_date = free;
	}
	spin_unlock(&low_water_lock);
}
#else
static inline void check_stack_usage(void) {}
#endif

NORET_TYPE void do_exit(long code)
{
	struct task_struct *tsk = current;
	int group_dead;

	profile_task_exit(tsk);

	WARN_ON(atomic_read(&tsk->fs_excl));

	if (unlikely(in_interrupt()))
		panic("Aiee, killing interrupt handler!");
	if (unlikely(!tsk->pid))
		panic("Attempted to kill the idle task!");

	tracehook_report_exit(&code);

	/*
	 * We're taking recursive faults here in do_exit. Safest is to just
	 * leave this task alone and wait for reboot.
	 */
	if (unlikely(tsk->flags & PF_EXITING)) {
		printk(KERN_ALERT
			"Fixing recursive fault but reboot is needed!\n");
		/*
		 * We can do this unlocked here. The futex code uses
		 * this flag just to verify whether the pi state
		 * cleanup has been done or not. In the worst case it
		 * loops once more. We pretend that the cleanup was
		 * done as there is no way to return. Either the
		 * OWNER_DIED bit is set by now or we push the blocked
		 * task into the wait for ever nirwana as well.
		 */
		tsk->flags |= PF_EXITPIDONE;
		if (tsk->io_context)
			exit_io_context();
		set_current_state(TASK_UNINTERRUPTIBLE);
		schedule();
	}

	exit_signals(tsk);  /* sets PF_EXITING */
	/*
	 * tsk->flags are checked in the futex code to protect against
	 * an exiting task cleaning up the robust pi futexes.
	 */
	smp_mb();
	spin_unlock_wait(&tsk->pi_lock);

	if (unlikely(in_atomic()))
		printk(KERN_INFO "note: %s[%d] exited with preempt_count %d\n",
				current->comm, task_pid_nr(current),
				preempt_count());

	acct_update_integrals(tsk);
	if (tsk->mm) {
		update_hiwater_rss(tsk->mm);
		update_hiwater_vm(tsk->mm);
	}
	group_dead = atomic_dec_and_test(&tsk->signal->live);
	if (group_dead) {
		hrtimer_cancel(&tsk->signal->real_timer);
		exit_itimers(tsk->signal);
	}
	acct_collect(code, group_dead);
#ifdef CONFIG_FUTEX
	if (unlikely(tsk->robust_list))
		exit_robust_list(tsk);
#ifdef CONFIG_COMPAT
	if (unlikely(tsk->compat_robust_list))
		compat_exit_robust_list(tsk);
#endif
#endif
	if (group_dead)
		tty_audit_exit();
	if (unlikely(tsk->audit_context))
		audit_free(tsk);

	tsk->exit_code = code;
	taskstats_exit(tsk, group_dead);

	exit_mm(tsk);

	if (group_dead)
		acct_process();
	exit_sem(tsk);
	exit_files(tsk);
	exit_fs(tsk);
	check_stack_usage();
	exit_thread();
	cgroup_exit(tsk, 1);
	exit_keys(tsk);

	if (group_dead && tsk->signal->leader)
		disassociate_ctty(1);

	module_put(task_thread_info(tsk)->exec_domain->module);
	if (tsk->binfmt)
		module_put(tsk->binfmt->module);

	proc_exit_connector(tsk);
	exit_notify(tsk, group_dead);
#ifdef CONFIG_NUMA
	mpol_put(tsk->mempolicy);
	tsk->mempolicy = NULL;
#endif
#ifdef CONFIG_FUTEX
	/*
	 * This must happen late, after the PID is not
	 * hashed anymore:
	 */
	if (unlikely(!list_empty(&tsk->pi_state_list)))
		exit_pi_state_list(tsk);
	if (unlikely(current->pi_state_cache))
		kfree(current->pi_state_cache);
#endif
	/*
	 * Make sure we are holding no locks:
	 */
	debug_check_no_locks_held(tsk);
	/*
	 * We can do this unlocked here. The futex code uses this flag
	 * just to verify whether the pi state cleanup has been done
	 * or not. In the worst case it loops once more.
	 */
	tsk->flags |= PF_EXITPIDONE;

	if (tsk->io_context)
		exit_io_context();

	if (tsk->splice_pipe)
		__free_pipe_info(tsk->splice_pipe);

	preempt_disable();
	/* causes final put_task_struct in finish_task_switch(). */
	tsk->state = TASK_DEAD;

	schedule();
	BUG();
	/* Avoid "noreturn function does return".  */
	for (;;)
		cpu_relax();	/* For when BUG is null */
}

EXPORT_SYMBOL_GPL(do_exit);

NORET_TYPE void complete_and_exit(struct completion *comp, long code)
{
	if (comp)
		complete(comp);

	do_exit(code);
}

EXPORT_SYMBOL(complete_and_exit);

asmlinkage long sys_exit(int error_code)
{
	do_exit((error_code&0xff)<<8);
}

/*
 * Take down every thread in the group.  This is called by fatal signals
 * as well as by sys_exit_group (below).
 */
NORET_TYPE void
do_group_exit(int exit_code)
{
	struct signal_struct *sig = current->signal;

	BUG_ON(exit_code & 0x80); /* core dumps don't get here */

	if (signal_group_exit(sig))
		exit_code = sig->group_exit_code;
	else if (!thread_group_empty(current)) {
		struct sighand_struct *const sighand = current->sighand;
		spin_lock_irq(&sighand->siglock);
		if (signal_group_exit(sig))
			/* Another thread got here before we took the lock.  */
			exit_code = sig->group_exit_code;
		else {
			sig->group_exit_code = exit_code;
			sig->flags = SIGNAL_GROUP_EXIT;
			zap_other_threads(current);
		}
		spin_unlock_irq(&sighand->siglock);
	}

	do_exit(exit_code);
	/* NOTREACHED */
}

/*
 * this kills every thread in the thread group. Note that any externally
 * wait4()-ing process will get the correct exit code - even if this
 * thread is not the thread group leader.
 */
asmlinkage void sys_exit_group(int error_code)
{
	do_group_exit((error_code & 0xff) << 8);
}

static struct pid *task_pid_type(struct task_struct *task, enum pid_type type)
{
	struct pid *pid = NULL;
	if (type == PIDTYPE_PID)
		pid = task->pids[type].pid;
	else if (type < PIDTYPE_MAX)
		pid = task->group_leader->pids[type].pid;
	return pid;
}

static int eligible_child(enum pid_type type, struct pid *pid, int options,
			  struct task_struct *p)
{
	int err;

	if (type < PIDTYPE_MAX) {
		if (task_pid_type(p, type) != pid)
			return 0;
	}

	/* Wait for all children (clone and not) if __WALL is set;
	 * otherwise, wait for clone children *only* if __WCLONE is
	 * set; otherwise, wait for non-clone children *only*.  (Note:
	 * A "clone" child here is one that reports to its parent
	 * using a signal other than SIGCHLD.) */
	if (((p->exit_signal != SIGCHLD) ^ ((options & __WCLONE) != 0))
	    && !(options & __WALL))
		return 0;

	err = security_task_wait(p);
	if (err)
		return err;

	return 1;
}

static int wait_noreap_copyout(struct task_struct *p, pid_t pid, uid_t uid,
			       int why, int status,
			       struct siginfo __user *infop,
			       struct rusage __user *rusagep)
{
	int retval = rusagep ? getrusage(p, RUSAGE_BOTH, rusagep) : 0;

	put_task_struct(p);
	if (!retval)
		retval = put_user(SIGCHLD, &infop->si_signo);
	if (!retval)
		retval = put_user(0, &infop->si_errno);
	if (!retval)
		retval = put_user((short)why, &infop->si_code);
	if (!retval)
		retval = put_user(pid, &infop->si_pid);
	if (!retval)
		retval = put_user(uid, &infop->si_uid);
	if (!retval)
		retval = put_user(status, &infop->si_status);
	if (!retval)
		retval = pid;
	return retval;
}

/*
 * Handle sys_wait4 work for one task in state EXIT_ZOMBIE.  We hold
 * read_lock(&tasklist_lock) on entry.  If we return zero, we still hold
 * the lock and this task is uninteresting.  If we return nonzero, we have
 * released the lock and the system call should return.
 */
static int wait_task_zombie(struct task_struct *p, int options,
			    struct siginfo __user *infop,
			    int __user *stat_addr, struct rusage __user *ru)
{
	unsigned long state;
	int retval, status, traced;
	pid_t pid = task_pid_vnr(p);

	if (!likely(options & WEXITED))
		return 0;

	if (unlikely(options & WNOWAIT)) {
		uid_t uid = p->uid;
		int exit_code = p->exit_code;
		int why, status;

		get_task_struct(p);
		read_unlock(&tasklist_lock);
		if ((exit_code & 0x7f) == 0) {
			why = CLD_EXITED;
			status = exit_code >> 8;
		} else {
			why = (exit_code & 0x80) ? CLD_DUMPED : CLD_KILLED;
			status = exit_code & 0x7f;
		}
		return wait_noreap_copyout(p, pid, uid, why,
					   status, infop, ru);
	}

	/*
	 * Try to move the task's state to DEAD
	 * only one thread is allowed to do this:
	 */
	state = xchg(&p->exit_state, EXIT_DEAD);
	if (state != EXIT_ZOMBIE) {
		BUG_ON(state != EXIT_DEAD);
		return 0;
	}

	traced = ptrace_reparented(p);

	if (likely(!traced)) {
		struct signal_struct *psig;
		struct signal_struct *sig;

		/*
		 * The resource counters for the group leader are in its
		 * own task_struct.  Those for dead threads in the group
		 * are in its signal_struct, as are those for the child
		 * processes it has previously reaped.  All these
		 * accumulate in the parent's signal_struct c* fields.
		 *
		 * We don't bother to take a lock here to protect these
		 * p->signal fields, because they are only touched by
		 * __exit_signal, which runs with tasklist_lock
		 * write-locked anyway, and so is excluded here.  We do
		 * need to protect the access to p->parent->signal fields,
		 * as other threads in the parent group can be right
		 * here reaping other children at the same time.
		 */
		spin_lock_irq(&p->parent->sighand->siglock);
		psig = p->parent->signal;
		sig = p->signal;
		psig->cutime =
			cputime_add(psig->cutime,
			cputime_add(p->utime,
			cputime_add(sig->utime,
				    sig->cutime)));
		psig->cstime =
			cputime_add(psig->cstime,
			cputime_add(p->stime,
			cputime_add(sig->stime,
				    sig->cstime)));
		psig->cgtime =
			cputime_add(psig->cgtime,
			cputime_add(p->gtime,
			cputime_add(sig->gtime,
				    sig->cgtime)));
		psig->cmin_flt +=
			p->min_flt + sig->min_flt + sig->cmin_flt;
		psig->cmaj_flt +=
			p->maj_flt + sig->maj_flt + sig->cmaj_flt;
		psig->cnvcsw +=
			p->nvcsw + sig->nvcsw + sig->cnvcsw;
		psig->cnivcsw +=
			p->nivcsw + sig->nivcsw + sig->cnivcsw;
		psig->cinblock +=
			task_io_get_inblock(p) +
			sig->inblock + sig->cinblock;
		psig->coublock +=
			task_io_get_oublock(p) +
			sig->oublock + sig->coublock;
		task_io_accounting_add(&psig->ioac, &p->ioac);
		task_io_accounting_add(&psig->ioac, &sig->ioac);
		spin_unlock_irq(&p->parent->sighand->siglock);
	}

	/*
	 * Now we are sure this task is interesting, and no other
	 * thread can reap it because we set its state to EXIT_DEAD.
	 */
	read_unlock(&tasklist_lock);

	retval = ru ? getrusage(p, RUSAGE_BOTH, ru) : 0;
	status = (p->signal->flags & SIGNAL_GROUP_EXIT)
		? p->signal->group_exit_code : p->exit_code;
	if (!retval && stat_addr)
		retval = put_user(status, stat_addr);
	if (!retval && infop)
		retval = put_user(SIGCHLD, &infop->si_signo);
	if (!retval && infop)
		retval = put_user(0, &infop->si_errno);
	if (!retval && infop) {
		int why;

		if ((status & 0x7f) == 0) {
			why = CLD_EXITED;
			status >>= 8;
		} else {
			why = (status & 0x80) ? CLD_DUMPED : CLD_KILLED;
			status &= 0x7f;
		}
		retval = put_user((short)why, &infop->si_code);
		if (!retval)
			retval = put_user(status, &infop->si_status);
	}
	if (!retval && infop)
		retval = put_user(pid, &infop->si_pid);
	if (!retval && infop)
		retval = put_user(p->uid, &infop->si_uid);
	if (!retval)
		retval = pid;

	if (traced) {
		write_lock_irq(&tasklist_lock);
		/* We dropped tasklist, ptracer could die and untrace */
		ptrace_unlink(p);
		/*
		 * If this is not a detached task, notify the parent.
		 * If it's still not detached after that, don't release
		 * it now.
		 */
		if (!task_detached(p)) {
			do_notify_parent(p, p->exit_signal);
			if (!task_detached(p)) {
				p->exit_state = EXIT_ZOMBIE;
				p = NULL;
			}
		}
		write_unlock_irq(&tasklist_lock);
	}
	if (p != NULL)
		release_task(p);

	return retval;
}

/*
 * Handle sys_wait4 work for one task in state TASK_STOPPED.  We hold
 * read_lock(&tasklist_lock) on entry.  If we return zero, we still hold
 * the lock and this task is uninteresting.  If we return nonzero, we have
 * released the lock and the system call should return.
 */
static int wait_task_stopped(int ptrace, struct task_struct *p,
			     int options, struct siginfo __user *infop,
			     int __user *stat_addr, struct rusage __user *ru)
{
	int retval, exit_code, why;
	uid_t uid = 0; /* unneeded, required by compiler */
	pid_t pid;

	if (!(options & WUNTRACED))
		return 0;

	exit_code = 0;
	spin_lock_irq(&p->sighand->siglock);

	if (unlikely(!task_is_stopped_or_traced(p)))
		goto unlock_sig;

	if (!ptrace && p->signal->group_stop_count > 0)
		/*
		 * A group stop is in progress and this is the group leader.
		 * We won't report until all threads have stopped.
		 */
		goto unlock_sig;

	exit_code = p->exit_code;
	if (!exit_code)
		goto unlock_sig;

	if (!unlikely(options & WNOWAIT))
		p->exit_code = 0;

	uid = p->uid;
unlock_sig:
	spin_unlock_irq(&p->sighand->siglock);
	if (!exit_code)
		return 0;

	/*
	 * Now we are pretty sure this task is interesting.
	 * Make sure it doesn't get reaped out from under us while we
	 * give up the lock and then examine it below.  We don't want to
	 * keep holding onto the tasklist_lock while we call getrusage and
	 * possibly take page faults for user memory.
	 */
	get_task_struct(p);
	pid = task_pid_vnr(p);
	why = ptrace ? CLD_TRAPPED : CLD_STOPPED;
	read_unlock(&tasklist_lock);

	if (unlikely(options & WNOWAIT))
		return wait_noreap_copyout(p, pid, uid,
					   why, exit_code,
					   infop, ru);

	retval = ru ? getrusage(p, RUSAGE_BOTH, ru) : 0;
	if (!retval && stat_addr)
		retval = put_user((exit_code << 8) | 0x7f, stat_addr);
	if (!retval && infop)
		retval = put_user(SIGCHLD, &infop->si_signo);
	if (!retval && infop)
		retval = put_user(0, &infop->si_errno);
	if (!retval && infop)
		retval = put_user((short)why, &infop->si_code);
	if (!retval && infop)
		retval = put_user(exit_code, &infop->si_status);
	if (!retval && infop)
		retval = put_user(pid, &infop->si_pid);
	if (!retval && infop)
		retval = put_user(uid, &infop->si_uid);
	if (!retval)
		retval = pid;
	put_task_struct(p);

	BUG_ON(!retval);
	return retval;
}

/*
 * Handle do_wait work for one task in a live, non-stopped state.
 * read_lock(&tasklist_lock) on entry.  If we return zero, we still hold
 * the lock and this task is uninteresting.  If we return nonzero, we have
 * released the lock and the system call should return.
 */
static int wait_task_continued(struct task_struct *p, int options,
			       struct siginfo __user *infop,
			       int __user *stat_addr, struct rusage __user *ru)
{
	int retval;
	pid_t pid;
	uid_t uid;

	if (!unlikely(options & WCONTINUED))
		return 0;

	if (!(p->signal->flags & SIGNAL_STOP_CONTINUED))
		return 0;

	spin_lock_irq(&p->sighand->siglock);
	/* Re-check with the lock held.  */
	if (!(p->signal->flags & SIGNAL_STOP_CONTINUED)) {
		spin_unlock_irq(&p->sighand->siglock);
		return 0;
	}
	if (!unlikely(options & WNOWAIT))
		p->signal->flags &= ~SIGNAL_STOP_CONTINUED;
	spin_unlock_irq(&p->sighand->siglock);

	pid = task_pid_vnr(p);
	uid = p->uid;
	get_task_struct(p);
	read_unlock(&tasklist_lock);

	if (!infop) {
		retval = ru ? getrusage(p, RUSAGE_BOTH, ru) : 0;
		put_task_struct(p);
		if (!retval && stat_addr)
			retval = put_user(0xffff, stat_addr);
		if (!retval)
			retval = pid;
	} else {
		retval = wait_noreap_copyout(p, pid, uid,
					     CLD_CONTINUED, SIGCONT,
					     infop, ru);
		BUG_ON(retval == 0);
	}

	return retval;
}

/*
 * Consider @p for a wait by @parent.
 *
 * -ECHILD should be in *@notask_error before the first call.
 * Returns nonzero for a final return, when we have unlocked tasklist_lock.
 * Returns zero if the search for a child should continue;
 * then *@notask_error is 0 if @p is an eligible child,
 * or another error from security_task_wait(), or still -ECHILD.
 */
static int wait_consider_task(struct task_struct *parent, int ptrace,
			      struct task_struct *p, int *notask_error,
			      enum pid_type type, struct pid *pid, int options,
			      struct siginfo __user *infop,
			      int __user *stat_addr, struct rusage __user *ru)
{
	int ret = eligible_child(type, pid, options, p);
	if (!ret)
		return ret;

	if (unlikely(ret < 0)) {
		/*
		 * If we have not yet seen any eligible child,
		 * then let this error code replace -ECHILD.
		 * A permission error will give the user a clue
		 * to look for security policy problems, rather
		 * than for mysterious wait bugs.
		 */
		if (*notask_error)
			*notask_error = ret;
	}

	if (likely(!ptrace) && unlikely(p->ptrace)) {
		/*
		 * This child is hidden by ptrace.
		 * We aren't allowed to see it now, but eventually we will.
		 */
		*notask_error = 0;
		return 0;
	}

	if (p->exit_state == EXIT_DEAD)
		return 0;

	/*
	 * We don't reap group leaders with subthreads.
	 */
	if (p->exit_state == EXIT_ZOMBIE && !delay_group_leader(p))
		return wait_task_zombie(p, options, infop, stat_addr, ru);

	/*
	 * It's stopped or running now, so it might
	 * later continue, exit, or stop again.
	 */
	*notask_error = 0;

	if (task_is_stopped_or_traced(p))
		return wait_task_stopped(ptrace, p, options,
					 infop, stat_addr, ru);

	return wait_task_continued(p, options, infop, stat_addr, ru);
}

/*
 * Do the work of do_wait() for one thread in the group, @tsk.
 *
 * -ECHILD should be in *@notask_error before the first call.
 * Returns nonzero for a final return, when we have unlocked tasklist_lock.
 * Returns zero if the search for a child should continue; then
 * *@notask_error is 0 if there were any eligible children,
 * or another error from security_task_wait(), or still -ECHILD.
 */
static int do_wait_thread(struct task_struct *tsk, int *notask_error,
			  enum pid_type type, struct pid *pid, int options,
			  struct siginfo __user *infop, int __user *stat_addr,
			  struct rusage __user *ru)
{
	struct task_struct *p;

	list_for_each_entry(p, &tsk->children, sibling) {
		/*
		 * Do not consider detached threads.
		 */
		if (!task_detached(p)) {
			int ret = wait_consider_task(tsk, 0, p, notask_error,
						     type, pid, options,
						     infop, stat_addr, ru);
			if (ret)
				return ret;
		}
	}

	return 0;
}

static int ptrace_do_wait(struct task_struct *tsk, int *notask_error,
			  enum pid_type type, struct pid *pid, int options,
			  struct siginfo __user *infop, int __user *stat_addr,
			  struct rusage __user *ru)
{
	struct task_struct *p;

	/*
	 * Traditionally we see ptrace'd stopped tasks regardless of options.
	 */
	options |= WUNTRACED;

	list_for_each_entry(p, &tsk->ptraced, ptrace_entry) {
		int ret = wait_consider_task(tsk, 1, p, notask_error,
					     type, pid, options,
					     infop, stat_addr, ru);
		if (ret)
			return ret;
	}

	return 0;
}

static long do_wait(enum pid_type type, struct pid *pid, int options,
		    struct siginfo __user *infop, int __user *stat_addr,
		    struct rusage __user *ru)
{
	DECLARE_WAITQUEUE(wait, current);
	struct task_struct *tsk;
	int retval;

	add_wait_queue(&current->signal->wait_chldexit,&wait);
repeat:
	/*
	 * If there is nothing that can match our critiera just get out.
	 * We will clear @retval to zero if we see any child that might later
	 * match our criteria, even if we are not able to reap it yet.
	 */
	retval = -ECHILD;
	if ((type < PIDTYPE_MAX) && (!pid || hlist_empty(&pid->tasks[type])))
		goto end;

	current->state = TASK_INTERRUPTIBLE;
	read_lock(&tasklist_lock);
	tsk = current;
	do {
		int tsk_result = do_wait_thread(tsk, &retval,
						type, pid, options,
						infop, stat_addr, ru);
		if (!tsk_result)
			tsk_result = ptrace_do_wait(tsk, &retval,
						    type, pid, options,
						    infop, stat_addr, ru);
		if (tsk_result) {
			/*
			 * tasklist_lock is unlocked and we have a final result.
			 */
			retval = tsk_result;
			goto end;
		}

		if (options & __WNOTHREAD)
			break;
		tsk = next_thread(tsk);
		BUG_ON(tsk->signal != current->signal);
	} while (tsk != current);
	read_unlock(&tasklist_lock);

	if (!retval && !(options & WNOHANG)) {
		retval = -ERESTARTSYS;
		if (!signal_pending(current)) {
			schedule();
			goto repeat;
		}
	}

end:
	current->state = TASK_RUNNING;
	remove_wait_queue(&current->signal->wait_chldexit,&wait);
	if (infop) {
		if (retval > 0)
			retval = 0;
		else {
			/*
			 * For a WNOHANG return, clear out all the fields
			 * we would set so the user can easily tell the
			 * difference.
			 */
			if (!retval)
				retval = put_user(0, &infop->si_signo);
			if (!retval)
				retval = put_user(0, &infop->si_errno);
			if (!retval)
				retval = put_user(0, &infop->si_code);
			if (!retval)
				retval = put_user(0, &infop->si_pid);
			if (!retval)
				retval = put_user(0, &infop->si_uid);
			if (!retval)
				retval = put_user(0, &infop->si_status);
		}
	}
	return retval;
}

asmlinkage long sys_waitid(int which, pid_t upid,
			   struct siginfo __user *infop, int options,
			   struct rusage __user *ru)
{
	struct pid *pid = NULL;
	enum pid_type type;
	long ret;

	if (options & ~(WNOHANG|WNOWAIT|WEXITED|WSTOPPED|WCONTINUED))
		return -EINVAL;
	if (!(options & (WEXITED|WSTOPPED|WCONTINUED)))
		return -EINVAL;

	switch (which) {
	case P_ALL:
		type = PIDTYPE_MAX;
		break;
	case P_PID:
		type = PIDTYPE_PID;
		if (upid <= 0)
			return -EINVAL;
		break;
	case P_PGID:
		type = PIDTYPE_PGID;
		if (upid <= 0)
			return -EINVAL;
		break;
	default:
		return -EINVAL;
	}

	if (type < PIDTYPE_MAX)
		pid = find_get_pid(upid);
	ret = do_wait(type, pid, options, infop, NULL, ru);
	put_pid(pid);

	/* avoid REGPARM breakage on x86: */
	asmlinkage_protect(5, ret, which, upid, infop, options, ru);
	return ret;
}

asmlinkage long sys_wait4(pid_t upid, int __user *stat_addr,
			  int options, struct rusage __user *ru)
{
	struct pid *pid = NULL;
	enum pid_type type;
	long ret;

	if (options & ~(WNOHANG|WUNTRACED|WCONTINUED|
			__WNOTHREAD|__WCLONE|__WALL))
		return -EINVAL;

	if (upid == -1)
		type = PIDTYPE_MAX;
	else if (upid < 0) {
		type = PIDTYPE_PGID;
		pid = find_get_pid(-upid);
	} else if (upid == 0) {
		type = PIDTYPE_PGID;
		pid = get_pid(task_pgrp(current));
	} else /* upid > 0 */ {
		type = PIDTYPE_PID;
		pid = find_get_pid(upid);
	}

	ret = do_wait(type, pid, options | WEXITED, NULL, stat_addr, ru);
	put_pid(pid);

	/* avoid REGPARM breakage on x86: */
	asmlinkage_protect(4, ret, upid, stat_addr, options, ru);
	return ret;
}

#ifdef __ARCH_WANT_SYS_WAITPID

/*
 * sys_waitpid() remains for compatibility. waitpid() should be
 * implemented by calling sys_wait4() from libc.a.
 */
asmlinkage long sys_waitpid(pid_t pid, int __user *stat_addr, int options)
{
	return sys_wait4(pid, stat_addr, options, NULL);
}

#endif