exit.c 44.1 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7 8 9 10
/*
 *  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>
11
#include <linux/capability.h>
L
Linus Torvalds 已提交
12 13 14
#include <linux/completion.h>
#include <linux/personality.h>
#include <linux/tty.h>
15
#include <linux/mnt_namespace.h>
L
Linus Torvalds 已提交
16 17 18 19
#include <linux/key.h>
#include <linux/security.h>
#include <linux/cpu.h>
#include <linux/acct.h>
20
#include <linux/tsacct_kern.h>
L
Linus Torvalds 已提交
21 22
#include <linux/file.h>
#include <linux/binfmts.h>
S
Serge E. Hallyn 已提交
23
#include <linux/nsproxy.h>
24
#include <linux/pid_namespace.h>
L
Linus Torvalds 已提交
25 26
#include <linux/ptrace.h>
#include <linux/profile.h>
27
#include <linux/signalfd.h>
L
Linus Torvalds 已提交
28 29
#include <linux/mount.h>
#include <linux/proc_fs.h>
30
#include <linux/kthread.h>
L
Linus Torvalds 已提交
31
#include <linux/mempolicy.h>
32
#include <linux/taskstats_kern.h>
33
#include <linux/delayacct.h>
34
#include <linux/freezer.h>
L
Linus Torvalds 已提交
35 36
#include <linux/cpuset.h>
#include <linux/syscalls.h>
37
#include <linux/signal.h>
38
#include <linux/posix-timers.h>
M
Matt Helsley 已提交
39
#include <linux/cn_proc.h>
40
#include <linux/mutex.h>
41
#include <linux/futex.h>
42
#include <linux/compat.h>
43
#include <linux/pipe_fs_i.h>
44
#include <linux/audit.h> /* for audit_free() */
A
Adrian Bunk 已提交
45
#include <linux/resource.h>
46
#include <linux/blkdev.h>
47
#include <linux/task_io_accounting_ops.h>
48
#include <linux/freezer.h>
L
Linus Torvalds 已提交
49 50 51 52 53 54 55 56

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

extern void sem_exit (void);

A
Adrian Bunk 已提交
57 58
static void exit_mm(struct task_struct * tsk);

L
Linus Torvalds 已提交
59 60 61 62 63 64 65
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);
66

67
		list_del_rcu(&p->tasks);
68
		__get_cpu_var(process_counts)--;
L
Linus Torvalds 已提交
69
	}
O
Oleg Nesterov 已提交
70
	list_del_rcu(&p->thread_group);
71
	remove_parent(p);
L
Linus Torvalds 已提交
72 73
}

74 75 76 77 78 79 80 81 82 83 84 85 86 87 88
/*
 * 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));

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

89 90 91 92 93 94 95 96
	/*
	 * Notify that this sighand has been detached. This must
	 * be called with the tsk->sighand lock held. Also, this
	 * access tsk->sighand internally, so it must be called
	 * before tsk->sighand is reset.
	 */
	signalfd_detach_locked(tsk);

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
	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);
			sig->group_exit_task = NULL;
		}
		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, tsk->utime);
		sig->stime = cputime_add(sig->stime, tsk->stime);
		sig->min_flt += tsk->min_flt;
		sig->maj_flt += tsk->maj_flt;
		sig->nvcsw += tsk->nvcsw;
		sig->nivcsw += tsk->nivcsw;
127 128
		sig->inblock += task_io_get_inblock(tsk);
		sig->oublock += task_io_get_oublock(tsk);
129
		sig->sum_sched_runtime += tsk->se.sum_exec_runtime;
130 131 132
		sig = NULL; /* Marker for below. */
	}

133 134
	__unhash_process(tsk);

135
	tsk->signal = NULL;
136
	tsk->sighand = NULL;
137 138 139
	spin_unlock(&sighand->siglock);
	rcu_read_unlock();

140
	__cleanup_sighand(sighand);
141 142 143 144
	clear_tsk_thread_flag(tsk,TIF_SIGPENDING);
	flush_sigqueue(&tsk->pending);
	if (sig) {
		flush_sigqueue(&sig->shared_pending);
145
		taskstats_tgid_free(sig);
146 147 148 149
		__cleanup_signal(sig);
	}
}

150 151 152 153 154
static void delayed_put_task_struct(struct rcu_head *rhp)
{
	put_task_struct(container_of(rhp, struct task_struct, rcu));
}

L
Linus Torvalds 已提交
155 156
void release_task(struct task_struct * p)
{
157
	struct task_struct *leader;
L
Linus Torvalds 已提交
158
	int zap_leader;
159
repeat:
L
Linus Torvalds 已提交
160 161
	atomic_dec(&p->user->processes);
	write_lock_irq(&tasklist_lock);
162
	ptrace_unlink(p);
L
Linus Torvalds 已提交
163 164
	BUG_ON(!list_empty(&p->ptrace_list) || !list_empty(&p->ptrace_children));
	__exit_signal(p);
165

L
Linus Torvalds 已提交
166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187
	/*
	 * 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(leader->exit_signal == -1);
		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 = (leader->exit_signal == -1);
	}

	write_unlock_irq(&tasklist_lock);
188
	proc_flush_task(p);
L
Linus Torvalds 已提交
189
	release_thread(p);
190
	call_rcu(&p->rcu, delayed_put_task_struct);
L
Linus Torvalds 已提交
191 192 193 194 195 196 197 198 199 200

	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...
201 202
 *
 * The caller must hold rcu lock or the tasklist lock.
L
Linus Torvalds 已提交
203
 */
204
struct pid *session_of_pgrp(struct pid *pgrp)
L
Linus Torvalds 已提交
205 206
{
	struct task_struct *p;
207
	struct pid *sid = NULL;
208

209
	p = pid_task(pgrp, PIDTYPE_PGID);
210
	if (p == NULL)
211
		p = pid_task(pgrp, PIDTYPE_PID);
212
	if (p != NULL)
213
		sid = task_session(p);
214

L
Linus Torvalds 已提交
215 216 217 218 219 220 221 222 223 224 225
	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?"
 */
226
static int will_become_orphaned_pgrp(struct pid *pgrp, struct task_struct *ignored_task)
L
Linus Torvalds 已提交
227 228 229 230
{
	struct task_struct *p;
	int ret = 1;

231
	do_each_pid_task(pgrp, PIDTYPE_PGID, p) {
L
Linus Torvalds 已提交
232 233
		if (p == ignored_task
				|| p->exit_state
234
				|| is_init(p->real_parent))
L
Linus Torvalds 已提交
235
			continue;
236 237
		if (task_pgrp(p->real_parent) != pgrp &&
		    task_session(p->real_parent) == task_session(p)) {
L
Linus Torvalds 已提交
238 239 240
			ret = 0;
			break;
		}
241
	} while_each_pid_task(pgrp, PIDTYPE_PGID, p);
L
Linus Torvalds 已提交
242 243 244
	return ret;	/* (sighing) "Often!" */
}

245
int is_current_pgrp_orphaned(void)
L
Linus Torvalds 已提交
246 247 248 249
{
	int retval;

	read_lock(&tasklist_lock);
250
	retval = will_become_orphaned_pgrp(task_pgrp(current), NULL);
L
Linus Torvalds 已提交
251 252 253 254 255
	read_unlock(&tasklist_lock);

	return retval;
}

256
static int has_stopped_jobs(struct pid *pgrp)
L
Linus Torvalds 已提交
257 258 259 260
{
	int retval = 0;
	struct task_struct *p;

261
	do_each_pid_task(pgrp, PIDTYPE_PGID, p) {
L
Linus Torvalds 已提交
262 263 264 265
		if (p->state != TASK_STOPPED)
			continue;
		retval = 1;
		break;
266
	} while_each_pid_task(pgrp, PIDTYPE_PGID, p);
L
Linus Torvalds 已提交
267 268 269 270
	return retval;
}

/**
271
 * reparent_to_kthreadd - Reparent the calling kernel thread to kthreadd
L
Linus Torvalds 已提交
272 273
 *
 * If a kernel thread is launched as a result of a system call, or if
274 275
 * 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.
L
Linus Torvalds 已提交
276 277 278 279
 *
 * 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.
 *
280
 * NOTE that reparent_to_kthreadd() gives the caller full capabilities.
L
Linus Torvalds 已提交
281
 */
282
static void reparent_to_kthreadd(void)
L
Linus Torvalds 已提交
283 284 285 286 287
{
	write_lock_irq(&tasklist_lock);

	ptrace_unlink(current);
	/* Reparent to init */
288
	remove_parent(current);
289
	current->real_parent = current->parent = kthreadd_task;
290
	add_parent(current);
L
Linus Torvalds 已提交
291 292 293 294

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

295
	if (task_nice(current) < 0)
L
Linus Torvalds 已提交
296 297 298 299 300 301 302 303 304 305 306 307 308 309
		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(pid_t session, pid_t pgrp)
{
310
	struct task_struct *curr = current->group_leader;
L
Linus Torvalds 已提交
311

312
	if (process_session(curr) != session) {
L
Linus Torvalds 已提交
313
		detach_pid(curr, PIDTYPE_SID);
314
		set_signal_session(curr->signal, session);
315
		attach_pid(curr, PIDTYPE_SID, find_pid(session));
L
Linus Torvalds 已提交
316 317 318 319
	}
	if (process_group(curr) != pgrp) {
		detach_pid(curr, PIDTYPE_PGID);
		curr->signal->pgrp = pgrp;
320
		attach_pid(curr, PIDTYPE_PGID, find_pid(pgrp));
L
Linus Torvalds 已提交
321 322 323
	}
}

324
static void set_special_pids(pid_t session, pid_t pgrp)
L
Linus Torvalds 已提交
325 326 327 328 329 330 331 332 333 334 335 336 337
{
	write_lock_irq(&tasklist_lock);
	__set_special_pids(session, pgrp);
	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)
{
338
	if (!valid_signal(sig) || sig < 1)
L
Linus Torvalds 已提交
339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358
		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)
{
359
	if (!valid_signal(sig) || sig < 1)
L
Linus Torvalds 已提交
360 361 362
		return -EINVAL;

	spin_lock_irq(&current->sighand->siglock);
363
	current->sighand->action[(sig)-1].sa.sa_handler = SIG_IGN;
L
Linus Torvalds 已提交
364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391
	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);
392 393 394 395 396
	/*
	 * We don't want to have TIF_FREEZE set if the system-wide hibernation
	 * or suspend transition begins right now.
	 */
	current->flags |= PF_NOFREEZE;
L
Linus Torvalds 已提交
397 398

	set_special_pids(1, 1);
399
	proc_clear_tty(current);
L
Linus Torvalds 已提交
400 401 402 403 404 405 406 407 408 409 410 411

	/* 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);
S
Serge E. Hallyn 已提交
412

413
	exit_task_namespaces(current);
S
Serge E. Hallyn 已提交
414 415 416
	current->nsproxy = init_task.nsproxy;
	get_task_namespaces(current);

L
Linus Torvalds 已提交
417 418 419 420
 	exit_files(current);
	current->files = init_task.files;
	atomic_inc(&current->files->count);

421
	reparent_to_kthreadd();
L
Linus Torvalds 已提交
422 423 424 425
}

EXPORT_SYMBOL(daemonize);

426
static void close_files(struct files_struct * files)
L
Linus Torvalds 已提交
427 428
{
	int i, j;
429
	struct fdtable *fdt;
L
Linus Torvalds 已提交
430 431

	j = 0;
432 433 434 435 436 437

	/*
	 * It is safe to dereference the fd table without RCU or
	 * ->file_lock because this is the last reference to the
	 * files structure.
	 */
438
	fdt = files_fdtable(files);
L
Linus Torvalds 已提交
439 440 441
	for (;;) {
		unsigned long set;
		i = j * __NFDBITS;
442
		if (i >= fdt->max_fds)
L
Linus Torvalds 已提交
443
			break;
444
		set = fdt->open_fds->fds_bits[j++];
L
Linus Torvalds 已提交
445 446
		while (set) {
			if (set & 1) {
447
				struct file * file = xchg(&fdt->fd[i], NULL);
448
				if (file) {
L
Linus Torvalds 已提交
449
					filp_close(file, files);
450 451
					cond_resched();
				}
L
Linus Torvalds 已提交
452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473
			}
			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 fastcall put_files_struct(struct files_struct *files)
{
474 475
	struct fdtable *fdt;

L
Linus Torvalds 已提交
476 477 478 479
	if (atomic_dec_and_test(&files->count)) {
		close_files(files);
		/*
		 * Free the fd and fdset arrays if we expanded them.
480 481 482
		 * If the fdtable was embedded, pass files for freeing
		 * at the end of the RCU grace period. Otherwise,
		 * you can free files immediately.
L
Linus Torvalds 已提交
483
		 */
484
		fdt = files_fdtable(files);
485
		if (fdt != &files->fdtab)
486
			kmem_cache_free(files_cachep, files);
487
		free_fdtable(fdt);
L
Linus Torvalds 已提交
488 489 490 491 492
	}
}

EXPORT_SYMBOL(put_files_struct);

493 494 495 496 497 498 499 500 501 502 503 504
void reset_files_struct(struct task_struct *tsk, struct files_struct *files)
{
	struct files_struct *old;

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

L
Linus Torvalds 已提交
505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565
static inline 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 exit_files(struct task_struct *tsk)
{
	__exit_files(tsk);
}

static inline 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)) {
		dput(fs->root);
		mntput(fs->rootmnt);
		dput(fs->pwd);
		mntput(fs->pwdmnt);
		if (fs->altroot) {
			dput(fs->altroot);
			mntput(fs->altrootmnt);
		}
		kmem_cache_free(fs_cachep, fs);
	}
}

void put_fs_struct(struct fs_struct *fs)
{
	__put_fs_struct(fs);
}

static inline 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);
	}
}

void exit_fs(struct task_struct *tsk)
{
	__exit_fs(tsk);
}

EXPORT_SYMBOL_GPL(exit_fs);

/*
 * Turn us into a lazy TLB process if we
 * aren't already..
 */
A
Adrian Bunk 已提交
566
static void exit_mm(struct task_struct * tsk)
L
Linus Torvalds 已提交
567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591
{
	struct mm_struct *mm = tsk->mm;

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

		wait_for_completion(&mm->core_done);
		down_read(&mm->mmap_sem);
	}
	atomic_inc(&mm->mm_count);
E
Eric Sesterhenn 已提交
592
	BUG_ON(mm != tsk->active_mm);
L
Linus Torvalds 已提交
593 594 595 596 597
	/* more a memory barrier than a real lock */
	task_lock(tsk);
	tsk->mm = NULL;
	up_read(&mm->mmap_sem);
	enter_lazy_tlb(mm, current);
598 599
	/* We don't want this task to be frozen prematurely */
	clear_freeze_flag(tsk);
L
Linus Torvalds 已提交
600 601 602 603
	task_unlock(tsk);
	mmput(mm);
}

604 605
static inline void
choose_new_parent(struct task_struct *p, struct task_struct *reaper)
L
Linus Torvalds 已提交
606 607 608 609 610
{
	/*
	 * Make sure we're not reparenting to ourselves and that
	 * the parent is not a zombie.
	 */
611
	BUG_ON(p == reaper || reaper->exit_state);
L
Linus Torvalds 已提交
612 613 614
	p->real_parent = reaper;
}

615 616
static void
reparent_thread(struct task_struct *p, struct task_struct *father, int traced)
L
Linus Torvalds 已提交
617
{
618 619 620 621
	if (p->pdeath_signal)
		/* We already hold the tasklist_lock here.  */
		group_send_sig_info(p->pdeath_signal, SEND_SIG_NOINFO, p);

L
Linus Torvalds 已提交
622 623 624 625 626 627 628 629 630 631 632
	/* Move the child from its dying parent to the new one.  */
	if (unlikely(traced)) {
		/* Preserve ptrace links if someone else is tracing this child.  */
		list_del_init(&p->ptrace_list);
		if (p->parent != p->real_parent)
			list_add(&p->ptrace_list, &p->real_parent->ptrace_children);
	} else {
		/* If this child is being traced, then we're the one tracing it
		 * anyway, so let go of it.
		 */
		p->ptrace = 0;
633
		remove_parent(p);
L
Linus Torvalds 已提交
634
		p->parent = p->real_parent;
635
		add_parent(p);
L
Linus Torvalds 已提交
636

637
		if (p->state == TASK_TRACED) {
L
Linus Torvalds 已提交
638 639 640 641 642 643 644 645 646
			/*
			 * If it was at a trace stop, turn it into
			 * a normal stop since it's no longer being
			 * traced.
			 */
			ptrace_untrace(p);
		}
	}

647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663
	/* If this is a threaded reparent there is no need to
	 * notify anyone anything has happened.
	 */
	if (p->real_parent->group_leader == father->group_leader)
		return;

	/* We don't want people slaying init.  */
	if (p->exit_signal != -1)
		p->exit_signal = SIGCHLD;

	/* If we'd notified the old parent about this child's death,
	 * also notify the new parent.
	 */
	if (!traced && p->exit_state == EXIT_ZOMBIE &&
	    p->exit_signal != -1 && thread_group_empty(p))
		do_notify_parent(p, p->exit_signal);

L
Linus Torvalds 已提交
664 665 666 667 668 669
	/*
	 * process group orphan check
	 * Case ii: Our child is in a different pgrp
	 * than we are, and it was the only connection
	 * outside, so the child pgrp is now orphaned.
	 */
670 671 672
	if ((task_pgrp(p) != task_pgrp(father)) &&
	    (task_session(p) == task_session(father))) {
		struct pid *pgrp = task_pgrp(p);
L
Linus Torvalds 已提交
673

674 675
		if (will_become_orphaned_pgrp(pgrp, NULL) &&
		    has_stopped_jobs(pgrp)) {
676 677
			__kill_pgrp_info(SIGHUP, SEND_SIG_PRIV, pgrp);
			__kill_pgrp_info(SIGCONT, SEND_SIG_PRIV, pgrp);
L
Linus Torvalds 已提交
678 679 680 681 682 683 684 685
		}
	}
}

/*
 * 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
686 687
 * the child reaper process (ie "init") in our pid
 * space.
L
Linus Torvalds 已提交
688
 */
689 690
static void
forget_original_parent(struct task_struct *father, struct list_head *to_release)
L
Linus Torvalds 已提交
691 692 693 694 695 696 697
{
	struct task_struct *p, *reaper = father;
	struct list_head *_p, *_n;

	do {
		reaper = next_thread(reaper);
		if (reaper == father) {
698
			reaper = child_reaper(father);
L
Linus Torvalds 已提交
699 700 701 702 703 704 705 706 707 708 709 710 711 712
			break;
		}
	} while (reaper->exit_state);

	/*
	 * There are only two places where our children can be:
	 *
	 * - in our child list
	 * - in our ptraced child list
	 *
	 * Search them and reparent children.
	 */
	list_for_each_safe(_p, _n, &father->children) {
		int ptrace;
713
		p = list_entry(_p, struct task_struct, sibling);
L
Linus Torvalds 已提交
714 715 716 717 718 719 720 721

		ptrace = p->ptrace;

		/* if father isn't the real parent, then ptrace must be enabled */
		BUG_ON(father != p->real_parent && !ptrace);

		if (father == p->real_parent) {
			/* reparent with a reaper, real father it's us */
722
			choose_new_parent(p, reaper);
L
Linus Torvalds 已提交
723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741
			reparent_thread(p, father, 0);
		} else {
			/* reparent ptraced task to its real parent */
			__ptrace_unlink (p);
			if (p->exit_state == EXIT_ZOMBIE && p->exit_signal != -1 &&
			    thread_group_empty(p))
				do_notify_parent(p, p->exit_signal);
		}

		/*
		 * if the ptraced child is a zombie with exit_signal == -1
		 * we must collect it before we exit, or it will remain
		 * zombie forever since we prevented it from self-reap itself
		 * while it was being traced by us, to be able to see it in wait4.
		 */
		if (unlikely(ptrace && p->exit_state == EXIT_ZOMBIE && p->exit_signal == -1))
			list_add(&p->ptrace_list, to_release);
	}
	list_for_each_safe(_p, _n, &father->ptrace_children) {
742
		p = list_entry(_p, struct task_struct, ptrace_list);
743
		choose_new_parent(p, reaper);
L
Linus Torvalds 已提交
744 745 746 747 748 749 750 751 752 753 754 755 756
		reparent_thread(p, father, 1);
	}
}

/*
 * Send signals to all our closest relatives so that they know
 * to properly mourn us..
 */
static void exit_notify(struct task_struct *tsk)
{
	int state;
	struct task_struct *t;
	struct list_head ptrace_dead, *_p, *_n;
757
	struct pid *pgrp;
L
Linus Torvalds 已提交
758 759 760 761 762 763 764 765 766 767 768 769 770 771 772

	if (signal_pending(tsk) && !(tsk->signal->flags & SIGNAL_GROUP_EXIT)
	    && !thread_group_empty(tsk)) {
		/*
		 * This occurs when there was a race between our exit
		 * syscall and a group signal choosing us as the one to
		 * wake up.  It could be that we are the only thread
		 * alerted to check for pending signals, but another thread
		 * should be woken now to take the signal since we will not.
		 * Now we'll wake all the threads in the group just to make
		 * sure someone gets all the pending signals.
		 */
		read_lock(&tasklist_lock);
		spin_lock_irq(&tsk->sighand->siglock);
		for (t = next_thread(tsk); t != tsk; t = next_thread(t))
R
Roland McGrath 已提交
773 774
			if (!signal_pending(t) && !(t->flags & PF_EXITING))
				recalc_sigpending_and_wake(t);
L
Linus Torvalds 已提交
775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806
		spin_unlock_irq(&tsk->sighand->siglock);
		read_unlock(&tasklist_lock);
	}

	write_lock_irq(&tasklist_lock);

	/*
	 * 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)
	 */

	INIT_LIST_HEAD(&ptrace_dead);
	forget_original_parent(tsk, &ptrace_dead);
	BUG_ON(!list_empty(&tsk->children));
	BUG_ON(!list_empty(&tsk->ptrace_children));

	/*
	 * 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)
	 *
	 * Case i: Our father is in a different pgrp than we are
	 * and we were the only connection outside, so our pgrp
	 * is about to become orphaned.
	 */
	 
	t = tsk->real_parent;
	
807 808
	pgrp = task_pgrp(tsk);
	if ((task_pgrp(t) != pgrp) &&
809
	    (task_session(t) == task_session(tsk)) &&
810 811 812 813
	    will_become_orphaned_pgrp(pgrp, tsk) &&
	    has_stopped_jobs(pgrp)) {
		__kill_pgrp_info(SIGHUP, SEND_SIG_PRIV, pgrp);
		__kill_pgrp_info(SIGCONT, SEND_SIG_PRIV, pgrp);
L
Linus Torvalds 已提交
814 815
	}

816
	/* Let father know we died
L
Linus Torvalds 已提交
817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848
	 *
	 * 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 && tsk->exit_signal != -1 &&
	    ( tsk->parent_exec_id != t->self_exec_id  ||
	      tsk->self_exec_id != tsk->parent_exec_id)
	    && !capable(CAP_KILL))
		tsk->exit_signal = SIGCHLD;


	/* If something other than our normal parent is ptracing us, then
	 * send it a SIGCHLD instead of honoring exit_signal.  exit_signal
	 * only has special meaning to our real parent.
	 */
	if (tsk->exit_signal != -1 && thread_group_empty(tsk)) {
		int signal = tsk->parent == tsk->real_parent ? tsk->exit_signal : SIGCHLD;
		do_notify_parent(tsk, signal);
	} else if (tsk->ptrace) {
		do_notify_parent(tsk, SIGCHLD);
	}

	state = EXIT_ZOMBIE;
849
	if (tsk->exit_signal == -1 && likely(!tsk->ptrace))
L
Linus Torvalds 已提交
850 851 852 853 854 855 856
		state = EXIT_DEAD;
	tsk->exit_state = state;

	write_unlock_irq(&tasklist_lock);

	list_for_each_safe(_p, _n, &ptrace_dead) {
		list_del_init(_p);
857
		t = list_entry(_p, struct task_struct, ptrace_list);
L
Linus Torvalds 已提交
858 859 860 861 862 863 864 865
		release_task(t);
	}

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

866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893
#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

L
Linus Torvalds 已提交
894 895 896 897 898 899 900
fastcall NORET_TYPE void do_exit(long code)
{
	struct task_struct *tsk = current;
	int group_dead;

	profile_task_exit(tsk);

901 902
	WARN_ON(atomic_read(&tsk->fs_excl));

L
Linus Torvalds 已提交
903 904 905 906
	if (unlikely(in_interrupt()))
		panic("Aiee, killing interrupt handler!");
	if (unlikely(!tsk->pid))
		panic("Attempted to kill the idle task!");
907 908 909 910 911 912 913
	if (unlikely(tsk == child_reaper(tsk))) {
		if (tsk->nsproxy->pid_ns != &init_pid_ns)
			tsk->nsproxy->pid_ns->child_reaper = init_pid_ns.child_reaper;
		else
			panic("Attempted to kill init!");
	}

L
Linus Torvalds 已提交
914 915 916 917 918 919

	if (unlikely(current->ptrace & PT_TRACE_EXIT)) {
		current->ptrace_message = code;
		ptrace_notify((PTRACE_EVENT_EXIT << 8) | SIGTRAP);
	}

920 921 922 923 924 925 926
	/*
	 * 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");
927 928 929 930 931 932 933 934 935 936
		/*
		 * 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;
937 938
		if (tsk->io_context)
			exit_io_context();
939 940 941 942
		set_current_state(TASK_UNINTERRUPTIBLE);
		schedule();
	}

943 944 945 946 947
	/*
	 * tsk->flags are checked in the futex code to protect against
	 * an exiting task cleaning up the robust pi futexes.
	 */
	spin_lock_irq(&tsk->pi_lock);
L
Linus Torvalds 已提交
948
	tsk->flags |= PF_EXITING;
949
	spin_unlock_irq(&tsk->pi_lock);
L
Linus Torvalds 已提交
950 951 952 953 954 955 956

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

	acct_update_integrals(tsk);
957 958 959 960
	if (tsk->mm) {
		update_hiwater_rss(tsk->mm);
		update_hiwater_vm(tsk->mm);
	}
L
Linus Torvalds 已提交
961
	group_dead = atomic_dec_and_test(&tsk->signal->live);
962
	if (group_dead) {
963
		hrtimer_cancel(&tsk->signal->real_timer);
964
		exit_itimers(tsk->signal);
965
	}
966
	acct_collect(code, group_dead);
967 968
	if (unlikely(tsk->robust_list))
		exit_robust_list(tsk);
969
#if defined(CONFIG_FUTEX) && defined(CONFIG_COMPAT)
970 971 972
	if (unlikely(tsk->compat_robust_list))
		compat_exit_robust_list(tsk);
#endif
M
Miloslav Trmac 已提交
973 974
	if (group_dead)
		tty_audit_exit();
975 976
	if (unlikely(tsk->audit_context))
		audit_free(tsk);
977 978

	taskstats_exit(tsk, group_dead);
979

L
Linus Torvalds 已提交
980 981
	exit_mm(tsk);

982
	if (group_dead)
983
		acct_process();
L
Linus Torvalds 已提交
984 985 986
	exit_sem(tsk);
	__exit_files(tsk);
	__exit_fs(tsk);
987
	check_stack_usage();
L
Linus Torvalds 已提交
988 989 990 991 992 993 994
	exit_thread();
	cpuset_exit(tsk);
	exit_keys(tsk);

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

A
Al Viro 已提交
995
	module_put(task_thread_info(tsk)->exec_domain->module);
L
Linus Torvalds 已提交
996 997 998 999
	if (tsk->binfmt)
		module_put(tsk->binfmt->module);

	tsk->exit_code = code;
M
Matt Helsley 已提交
1000
	proc_exit_connector(tsk);
1001
	exit_task_namespaces(tsk);
1002
	exit_notify(tsk);
L
Linus Torvalds 已提交
1003 1004 1005 1006
#ifdef CONFIG_NUMA
	mpol_free(tsk->mempolicy);
	tsk->mempolicy = NULL;
#endif
1007 1008 1009 1010 1011 1012 1013 1014
	/*
	 * 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);
1015
	/*
1016
	 * Make sure we are holding no locks:
1017
	 */
1018
	debug_check_no_locks_held(tsk);
1019 1020 1021 1022 1023 1024
	/*
	 * 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;
L
Linus Torvalds 已提交
1025

1026 1027 1028
	if (tsk->io_context)
		exit_io_context();

1029 1030 1031
	if (tsk->splice_pipe)
		__free_pipe_info(tsk->splice_pipe);

C
Coywolf Qi Hunt 已提交
1032
	preempt_disable();
O
Oleg Nesterov 已提交
1033
	/* causes final put_task_struct in finish_task_switch(). */
1034
	tsk->state = TASK_DEAD;
C
Coywolf Qi Hunt 已提交
1035

L
Linus Torvalds 已提交
1036 1037 1038
	schedule();
	BUG();
	/* Avoid "noreturn function does return".  */
A
Alan Cox 已提交
1039 1040
	for (;;)
		cpu_relax();	/* For when BUG is null */
L
Linus Torvalds 已提交
1041 1042
}

1043 1044
EXPORT_SYMBOL_GPL(do_exit);

L
Linus Torvalds 已提交
1045 1046 1047 1048
NORET_TYPE void complete_and_exit(struct completion *comp, long code)
{
	if (comp)
		complete(comp);
O
Oleg Nesterov 已提交
1049

L
Linus Torvalds 已提交
1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098
	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)
{
	BUG_ON(exit_code & 0x80); /* core dumps don't get here */

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

1099
static int eligible_child(pid_t pid, int options, struct task_struct *p)
L
Linus Torvalds 已提交
1100
{
1101 1102
	int err;

L
Linus Torvalds 已提交
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
	if (pid > 0) {
		if (p->pid != pid)
			return 0;
	} else if (!pid) {
		if (process_group(p) != process_group(current))
			return 0;
	} else if (pid != -1) {
		if (process_group(p) != -pid)
			return 0;
	}

	/*
	 * Do not consider detached threads that are
	 * not ptraced:
	 */
	if (p->exit_signal == -1 && !p->ptrace)
		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;
	/*
	 * Do not consider thread group leaders that are
	 * in a non-empty thread group:
	 */
1133
	if (delay_group_leader(p))
L
Linus Torvalds 已提交
1134 1135
		return 2;

1136 1137 1138
	err = security_task_wait(p);
	if (err)
		return err;
L
Linus Torvalds 已提交
1139 1140 1141 1142

	return 1;
}

1143
static int wait_noreap_copyout(struct task_struct *p, pid_t pid, uid_t uid,
L
Linus Torvalds 已提交
1144 1145 1146 1147 1148
			       int why, int status,
			       struct siginfo __user *infop,
			       struct rusage __user *rusagep)
{
	int retval = rusagep ? getrusage(p, RUSAGE_BOTH, rusagep) : 0;
1149

L
Linus Torvalds 已提交
1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173
	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.
 */
1174
static int wait_task_zombie(struct task_struct *p, int noreap,
L
Linus Torvalds 已提交
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
			    struct siginfo __user *infop,
			    int __user *stat_addr, struct rusage __user *ru)
{
	unsigned long state;
	int retval;
	int status;

	if (unlikely(noreap)) {
		pid_t pid = p->pid;
		uid_t uid = p->uid;
		int exit_code = p->exit_code;
		int why, status;

		if (unlikely(p->exit_state != EXIT_ZOMBIE))
			return 0;
		if (unlikely(p->exit_signal == -1 && p->ptrace == 0))
			return 0;
		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;
	}
	if (unlikely(p->exit_signal == -1 && p->ptrace == 0)) {
		/*
		 * This can only happen in a race with a ptraced thread
		 * dying on another processor.
		 */
		return 0;
	}

	if (likely(p->real_parent == p->parent) && likely(p->signal)) {
1223 1224 1225
		struct signal_struct *psig;
		struct signal_struct *sig;

L
Linus Torvalds 已提交
1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241
		/*
		 * 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);
1242 1243 1244 1245
		psig = p->parent->signal;
		sig = p->signal;
		psig->cutime =
			cputime_add(psig->cutime,
L
Linus Torvalds 已提交
1246
			cputime_add(p->utime,
1247 1248 1249 1250
			cputime_add(sig->utime,
				    sig->cutime)));
		psig->cstime =
			cputime_add(psig->cstime,
L
Linus Torvalds 已提交
1251
			cputime_add(p->stime,
1252 1253 1254 1255 1256 1257 1258 1259 1260 1261
			cputime_add(sig->stime,
				    sig->cstime)));
		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;
1262 1263 1264 1265 1266 1267
		psig->cinblock +=
			task_io_get_inblock(p) +
			sig->inblock + sig->cinblock;
		psig->coublock +=
			task_io_get_oublock(p) +
			sig->oublock + sig->coublock;
L
Linus Torvalds 已提交
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
		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(p->pid, &infop->si_pid);
	if (!retval && infop)
		retval = put_user(p->uid, &infop->si_uid);
	if (retval) {
		// TODO: is this safe?
		p->exit_state = EXIT_ZOMBIE;
		return retval;
	}
	retval = p->pid;
	if (p->real_parent != p->parent) {
		write_lock_irq(&tasklist_lock);
		/* Double-check with lock held.  */
		if (p->real_parent != p->parent) {
			__ptrace_unlink(p);
			// TODO: is this safe?
			p->exit_state = EXIT_ZOMBIE;
			/*
			 * If this is not a detached task, notify the parent.
			 * If it's still not detached after that, don't release
			 * it now.
			 */
			if (p->exit_signal != -1) {
				do_notify_parent(p, p->exit_signal);
				if (p->exit_signal != -1)
					p = NULL;
			}
		}
		write_unlock_irq(&tasklist_lock);
	}
	if (p != NULL)
		release_task(p);
	BUG_ON(!retval);
	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.
 */
1342 1343
static int wait_task_stopped(struct task_struct *p, int delayed_group_leader,
			     int noreap, struct siginfo __user *infop,
L
Linus Torvalds 已提交
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
			     int __user *stat_addr, struct rusage __user *ru)
{
	int retval, exit_code;

	if (!p->exit_code)
		return 0;
	if (delayed_group_leader && !(p->ptrace & PT_PTRACED) &&
	    p->signal && 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.
		 */
		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);
	read_unlock(&tasklist_lock);

	if (unlikely(noreap)) {
		pid_t pid = p->pid;
		uid_t uid = p->uid;
		int why = (p->ptrace & PT_PTRACED) ? CLD_TRAPPED : CLD_STOPPED;

		exit_code = p->exit_code;
		if (unlikely(!exit_code) ||
1375
		    unlikely(p->state & TASK_TRACED))
L
Linus Torvalds 已提交
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
			goto bail_ref;
		return wait_noreap_copyout(p, pid, uid,
					   why, (exit_code << 8) | 0x7f,
					   infop, ru);
	}

	write_lock_irq(&tasklist_lock);

	/*
	 * This uses xchg to be atomic with the thread resuming and setting
	 * it.  It must also be done with the write lock held to prevent a
	 * race with the EXIT_ZOMBIE case.
	 */
	exit_code = xchg(&p->exit_code, 0);
	if (unlikely(p->exit_state)) {
		/*
		 * The task resumed and then died.  Let the next iteration
		 * catch it in EXIT_ZOMBIE.  Note that exit_code might
		 * already be zero here if it resumed and did _exit(0).
		 * The task itself is dead and won't touch exit_code again;
		 * other processors in this function are locked out.
		 */
		p->exit_code = exit_code;
		exit_code = 0;
	}
	if (unlikely(exit_code == 0)) {
		/*
		 * Another thread in this function got to it first, or it
		 * resumed, or it resumed and then died.
		 */
		write_unlock_irq(&tasklist_lock);
bail_ref:
		put_task_struct(p);
		/*
		 * We are returning to the wait loop without having successfully
		 * removed the process and having released the lock. We cannot
		 * continue, since the "p" task pointer is potentially stale.
		 *
		 * Return -EAGAIN, and do_wait() will restart the loop from the
		 * beginning. Do _not_ re-acquire the lock.
		 */
		return -EAGAIN;
	}

	/* move to end of parent's list to avoid starvation */
	remove_parent(p);
1422
	add_parent(p);
L
Linus Torvalds 已提交
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

	write_unlock_irq(&tasklist_lock);

	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)((p->ptrace & PT_PTRACED)
					  ? CLD_TRAPPED : CLD_STOPPED),
				  &infop->si_code);
	if (!retval && infop)
		retval = put_user(exit_code, &infop->si_status);
	if (!retval && infop)
		retval = put_user(p->pid, &infop->si_pid);
	if (!retval && infop)
		retval = put_user(p->uid, &infop->si_uid);
	if (!retval)
		retval = p->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.
 */
1457
static int wait_task_continued(struct task_struct *p, int noreap,
L
Linus Torvalds 已提交
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
			       struct siginfo __user *infop,
			       int __user *stat_addr, struct rusage __user *ru)
{
	int retval;
	pid_t pid;
	uid_t uid;

	if (unlikely(!p->signal))
		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 (!noreap)
		p->signal->flags &= ~SIGNAL_STOP_CONTINUED;
	spin_unlock_irq(&p->sighand->siglock);

	pid = p->pid;
	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 = p->pid;
	} else {
		retval = wait_noreap_copyout(p, pid, uid,
					     CLD_CONTINUED, SIGCONT,
					     infop, ru);
		BUG_ON(retval == 0);
	}

	return retval;
}


static inline int my_ptrace_child(struct task_struct *p)
{
	if (!(p->ptrace & PT_PTRACED))
		return 0;
	if (!(p->ptrace & PT_ATTACHED))
		return 1;
	/*
	 * This child was PTRACE_ATTACH'd.  We should be seeing it only if
	 * we are the attacher.  If we are the real parent, this is a race
	 * inside ptrace_attach.  It is waiting for the tasklist_lock,
	 * which we have to switch the parent links, but has already set
	 * the flags in p->ptrace.
	 */
	return (p->parent != p->real_parent);
}

static long do_wait(pid_t pid, int options, struct siginfo __user *infop,
		    int __user *stat_addr, struct rusage __user *ru)
{
	DECLARE_WAITQUEUE(wait, current);
	struct task_struct *tsk;
	int flag, retval;
1526
	int allowed, denied;
L
Linus Torvalds 已提交
1527 1528 1529 1530 1531 1532 1533 1534

	add_wait_queue(&current->signal->wait_chldexit,&wait);
repeat:
	/*
	 * We will set this flag if we see any child that might later
	 * match our criteria, even if we are not able to reap it yet.
	 */
	flag = 0;
1535
	allowed = denied = 0;
L
Linus Torvalds 已提交
1536 1537 1538 1539 1540 1541 1542 1543 1544
	current->state = TASK_INTERRUPTIBLE;
	read_lock(&tasklist_lock);
	tsk = current;
	do {
		struct task_struct *p;
		struct list_head *_p;
		int ret;

		list_for_each(_p,&tsk->children) {
1545
			p = list_entry(_p, struct task_struct, sibling);
L
Linus Torvalds 已提交
1546 1547 1548 1549 1550

			ret = eligible_child(pid, options, p);
			if (!ret)
				continue;

1551 1552 1553 1554 1555 1556
			if (unlikely(ret < 0)) {
				denied = ret;
				continue;
			}
			allowed = 1;

L
Linus Torvalds 已提交
1557 1558
			switch (p->state) {
			case TASK_TRACED:
1559 1560 1561 1562 1563 1564 1565 1566 1567
				/*
				 * When we hit the race with PTRACE_ATTACH,
				 * we will not report this child.  But the
				 * race means it has not yet been moved to
				 * our ptrace_children list, so we need to
				 * set the flag here to avoid a spurious ECHILD
				 * when the race happens with the only child.
				 */
				flag = 1;
L
Linus Torvalds 已提交
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
				if (!my_ptrace_child(p))
					continue;
				/*FALLTHROUGH*/
			case TASK_STOPPED:
				/*
				 * It's stopped now, so it might later
				 * continue, exit, or stop again.
				 */
				flag = 1;
				if (!(options & WUNTRACED) &&
				    !my_ptrace_child(p))
					continue;
				retval = wait_task_stopped(p, ret == 2,
							   (options & WNOWAIT),
							   infop,
							   stat_addr, ru);
				if (retval == -EAGAIN)
					goto repeat;
				if (retval != 0) /* He released the lock.  */
					goto end;
				break;
			default:
			// case EXIT_DEAD:
				if (p->exit_state == EXIT_DEAD)
					continue;
			// case EXIT_ZOMBIE:
				if (p->exit_state == EXIT_ZOMBIE) {
					/*
					 * Eligible but we cannot release
					 * it yet:
					 */
					if (ret == 2)
						goto check_continued;
					if (!likely(options & WEXITED))
						continue;
					retval = wait_task_zombie(
						p, (options & WNOWAIT),
						infop, stat_addr, ru);
					/* He released the lock.  */
					if (retval != 0)
						goto end;
					break;
				}
check_continued:
				/*
				 * It's running now, so it might later
				 * exit, stop, or stop and then continue.
				 */
				flag = 1;
				if (!unlikely(options & WCONTINUED))
					continue;
				retval = wait_task_continued(
					p, (options & WNOWAIT),
					infop, stat_addr, ru);
				if (retval != 0) /* He released the lock.  */
					goto end;
				break;
			}
		}
		if (!flag) {
			list_for_each(_p, &tsk->ptrace_children) {
				p = list_entry(_p, struct task_struct,
						ptrace_list);
				if (!eligible_child(pid, options, p))
					continue;
				flag = 1;
				break;
			}
		}
		if (options & __WNOTHREAD)
			break;
		tsk = next_thread(tsk);
E
Eric Sesterhenn 已提交
1640
		BUG_ON(tsk->signal != current->signal);
L
Linus Torvalds 已提交
1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654
	} while (tsk != current);

	read_unlock(&tasklist_lock);
	if (flag) {
		retval = 0;
		if (options & WNOHANG)
			goto end;
		retval = -ERESTARTSYS;
		if (signal_pending(current))
			goto end;
		schedule();
		goto repeat;
	}
	retval = -ECHILD;
1655 1656
	if (unlikely(denied) && !allowed)
		retval = denied;
L
Linus Torvalds 已提交
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
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 pid,
			   struct siginfo __user *infop, int options,
			   struct rusage __user *ru)
{
	long ret;

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

	switch (which) {
	case P_ALL:
		pid = -1;
		break;
	case P_PID:
		if (pid <= 0)
			return -EINVAL;
		break;
	case P_PGID:
		if (pid <= 0)
			return -EINVAL;
		pid = -pid;
		break;
	default:
		return -EINVAL;
	}

	ret = do_wait(pid, options, infop, NULL, ru);

	/* avoid REGPARM breakage on x86: */
	prevent_tail_call(ret);
	return ret;
}

asmlinkage long sys_wait4(pid_t pid, int __user *stat_addr,
			  int options, struct rusage __user *ru)
{
	long ret;

	if (options & ~(WNOHANG|WUNTRACED|WCONTINUED|
			__WNOTHREAD|__WCLONE|__WALL))
		return -EINVAL;
	ret = do_wait(pid, options | WEXITED, NULL, stat_addr, ru);

	/* avoid REGPARM breakage on x86: */
	prevent_tail_call(ret);
	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