signal.c 68.1 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22
/*
 *  linux/kernel/signal.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 *
 *  1997-11-02  Modified for POSIX.1b signals by Richard Henderson
 *
 *  2003-06-02  Jim Houston - Concurrent Computer Corp.
 *		Changes to use preallocated sigqueue structures
 *		to allow signals to be sent reliably.
 */

#include <linux/slab.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/sched.h>
#include <linux/fs.h>
#include <linux/tty.h>
#include <linux/binfmts.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/ptrace.h>
23
#include <linux/signal.h>
24
#include <linux/signalfd.h>
25
#include <linux/ratelimit.h>
26
#include <linux/tracehook.h>
27
#include <linux/capability.h>
28
#include <linux/freezer.h>
29 30
#include <linux/pid_namespace.h>
#include <linux/nsproxy.h>
31 32
#define CREATE_TRACE_POINTS
#include <trace/events/signal.h>
33

L
Linus Torvalds 已提交
34 35 36 37
#include <asm/param.h>
#include <asm/uaccess.h>
#include <asm/unistd.h>
#include <asm/siginfo.h>
38
#include "audit.h"	/* audit_signal_info() */
L
Linus Torvalds 已提交
39 40 41 42 43

/*
 * SLAB caches for signal bits.
 */

44
static struct kmem_cache *sigqueue_cachep;
L
Linus Torvalds 已提交
45

46 47
int print_fatal_signals __read_mostly;

48
static void __user *sig_handler(struct task_struct *t, int sig)
49
{
50 51
	return t->sighand->action[sig - 1].sa.sa_handler;
}
52

53 54
static int sig_handler_ignored(void __user *handler, int sig)
{
55 56 57 58
	/* Is it explicitly or implicitly ignored? */
	return handler == SIG_IGN ||
		(handler == SIG_DFL && sig_kernel_ignore(sig));
}
L
Linus Torvalds 已提交
59

60 61
static int sig_task_ignored(struct task_struct *t, int sig,
		int from_ancestor_ns)
L
Linus Torvalds 已提交
62
{
63
	void __user *handler;
L
Linus Torvalds 已提交
64

65 66 67
	handler = sig_handler(t, sig);

	if (unlikely(t->signal->flags & SIGNAL_UNKILLABLE) &&
68
			handler == SIG_DFL && !from_ancestor_ns)
69 70 71 72 73
		return 1;

	return sig_handler_ignored(handler, sig);
}

74
static int sig_ignored(struct task_struct *t, int sig, int from_ancestor_ns)
75
{
L
Linus Torvalds 已提交
76 77 78 79 80
	/*
	 * Blocked signals are never ignored, since the
	 * signal handler may change by the time it is
	 * unblocked.
	 */
81
	if (sigismember(&t->blocked, sig) || sigismember(&t->real_blocked, sig))
L
Linus Torvalds 已提交
82 83
		return 0;

84
	if (!sig_task_ignored(t, sig, from_ancestor_ns))
85 86 87 88 89
		return 0;

	/*
	 * Tracers may want to know about even ignored signals.
	 */
90
	return !tracehook_consider_ignored_signal(t, sig);
L
Linus Torvalds 已提交
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
}

/*
 * Re-calculate pending state from the set of locally pending
 * signals, globally pending signals, and blocked signals.
 */
static inline int has_pending_signals(sigset_t *signal, sigset_t *blocked)
{
	unsigned long ready;
	long i;

	switch (_NSIG_WORDS) {
	default:
		for (i = _NSIG_WORDS, ready = 0; --i >= 0 ;)
			ready |= signal->sig[i] &~ blocked->sig[i];
		break;

	case 4: ready  = signal->sig[3] &~ blocked->sig[3];
		ready |= signal->sig[2] &~ blocked->sig[2];
		ready |= signal->sig[1] &~ blocked->sig[1];
		ready |= signal->sig[0] &~ blocked->sig[0];
		break;

	case 2: ready  = signal->sig[1] &~ blocked->sig[1];
		ready |= signal->sig[0] &~ blocked->sig[0];
		break;

	case 1: ready  = signal->sig[0] &~ blocked->sig[0];
	}
	return ready !=	0;
}

#define PENDING(p,b) has_pending_signals(&(p)->signal, (b))

R
Roland McGrath 已提交
125
static int recalc_sigpending_tsk(struct task_struct *t)
L
Linus Torvalds 已提交
126 127 128
{
	if (t->signal->group_stop_count > 0 ||
	    PENDING(&t->pending, &t->blocked) ||
R
Roland McGrath 已提交
129
	    PENDING(&t->signal->shared_pending, &t->blocked)) {
L
Linus Torvalds 已提交
130
		set_tsk_thread_flag(t, TIF_SIGPENDING);
R
Roland McGrath 已提交
131 132
		return 1;
	}
133 134 135 136 137
	/*
	 * We must never clear the flag in another thread, or in current
	 * when it's possible the current syscall is returning -ERESTART*.
	 * So we don't clear it here, and only callers who know they should do.
	 */
R
Roland McGrath 已提交
138 139 140 141 142 143 144 145 146 147 148
	return 0;
}

/*
 * After recalculating TIF_SIGPENDING, we need to make sure the task wakes up.
 * This is superfluous when called on current, the wakeup is a harmless no-op.
 */
void recalc_sigpending_and_wake(struct task_struct *t)
{
	if (recalc_sigpending_tsk(t))
		signal_wake_up(t, 0);
L
Linus Torvalds 已提交
149 150 151 152
}

void recalc_sigpending(void)
{
153 154 155
	if (unlikely(tracehook_force_sigpending()))
		set_thread_flag(TIF_SIGPENDING);
	else if (!recalc_sigpending_tsk(current) && !freezing(current))
156 157
		clear_thread_flag(TIF_SIGPENDING);

L
Linus Torvalds 已提交
158 159 160 161
}

/* Given the mask, find the first available signal that should be serviced. */

162
int next_signal(struct sigpending *pending, sigset_t *mask)
L
Linus Torvalds 已提交
163 164 165
{
	unsigned long i, *s, *m, x;
	int sig = 0;
166

L
Linus Torvalds 已提交
167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190
	s = pending->signal.sig;
	m = mask->sig;
	switch (_NSIG_WORDS) {
	default:
		for (i = 0; i < _NSIG_WORDS; ++i, ++s, ++m)
			if ((x = *s &~ *m) != 0) {
				sig = ffz(~x) + i*_NSIG_BPW + 1;
				break;
			}
		break;

	case 2: if ((x = s[0] &~ m[0]) != 0)
			sig = 1;
		else if ((x = s[1] &~ m[1]) != 0)
			sig = _NSIG_BPW + 1;
		else
			break;
		sig += ffz(~x);
		break;

	case 1: if ((x = *s &~ *m) != 0)
			sig = ffz(~x) + 1;
		break;
	}
191

L
Linus Torvalds 已提交
192 193 194
	return sig;
}

195 196 197 198 199 200 201 202 203 204 205 206 207 208
static inline void print_dropped_signal(int sig)
{
	static DEFINE_RATELIMIT_STATE(ratelimit_state, 5 * HZ, 10);

	if (!print_fatal_signals)
		return;

	if (!__ratelimit(&ratelimit_state))
		return;

	printk(KERN_INFO "%s/%d: reached RLIMIT_SIGPENDING, dropped signal %d\n",
				current->comm, current->pid, sig);
}

209 210 211
/*
 * allocate a new signal queue record
 * - this may be called without locks if and only if t == current, otherwise an
D
David Howells 已提交
212
 *   appopriate lock must be held to stop the target task from exiting
213
 */
214 215
static struct sigqueue *
__sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimit)
L
Linus Torvalds 已提交
216 217
{
	struct sigqueue *q = NULL;
218
	struct user_struct *user;
L
Linus Torvalds 已提交
219

220
	/*
221 222 223 224
	 * We won't get problems with the target's UID changing under us
	 * because changing it requires RCU be used, and if t != current, the
	 * caller must be holding the RCU readlock (by way of a spinlock) and
	 * we use RCU protection here
225
	 */
D
David Howells 已提交
226
	user = get_uid(__task_cred(t)->user);
227
	atomic_inc(&user->sigpending);
228

L
Linus Torvalds 已提交
229
	if (override_rlimit ||
230
	    atomic_read(&user->sigpending) <=
231
			t->signal->rlim[RLIMIT_SIGPENDING].rlim_cur) {
L
Linus Torvalds 已提交
232
		q = kmem_cache_alloc(sigqueue_cachep, flags);
233 234 235 236
	} else {
		print_dropped_signal(sig);
	}

L
Linus Torvalds 已提交
237
	if (unlikely(q == NULL)) {
238
		atomic_dec(&user->sigpending);
D
David Howells 已提交
239
		free_uid(user);
L
Linus Torvalds 已提交
240 241 242
	} else {
		INIT_LIST_HEAD(&q->list);
		q->flags = 0;
D
David Howells 已提交
243
		q->user = user;
L
Linus Torvalds 已提交
244
	}
D
David Howells 已提交
245 246

	return q;
L
Linus Torvalds 已提交
247 248
}

249
static void __sigqueue_free(struct sigqueue *q)
L
Linus Torvalds 已提交
250 251 252 253 254 255 256 257
{
	if (q->flags & SIGQUEUE_PREALLOC)
		return;
	atomic_dec(&q->user->sigpending);
	free_uid(q->user);
	kmem_cache_free(sigqueue_cachep, q);
}

258
void flush_sigqueue(struct sigpending *queue)
L
Linus Torvalds 已提交
259 260 261 262 263 264 265 266 267 268 269 270 271 272
{
	struct sigqueue *q;

	sigemptyset(&queue->signal);
	while (!list_empty(&queue->list)) {
		q = list_entry(queue->list.next, struct sigqueue , list);
		list_del_init(&q->list);
		__sigqueue_free(q);
	}
}

/*
 * Flush all pending signals for a task.
 */
273 274 275 276 277 278 279
void __flush_signals(struct task_struct *t)
{
	clear_tsk_thread_flag(t, TIF_SIGPENDING);
	flush_sigqueue(&t->pending);
	flush_sigqueue(&t->signal->shared_pending);
}

280
void flush_signals(struct task_struct *t)
L
Linus Torvalds 已提交
281 282 283 284
{
	unsigned long flags;

	spin_lock_irqsave(&t->sighand->siglock, flags);
285
	__flush_signals(t);
L
Linus Torvalds 已提交
286 287 288
	spin_unlock_irqrestore(&t->sighand->siglock, flags);
}

289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322
static void __flush_itimer_signals(struct sigpending *pending)
{
	sigset_t signal, retain;
	struct sigqueue *q, *n;

	signal = pending->signal;
	sigemptyset(&retain);

	list_for_each_entry_safe(q, n, &pending->list, list) {
		int sig = q->info.si_signo;

		if (likely(q->info.si_code != SI_TIMER)) {
			sigaddset(&retain, sig);
		} else {
			sigdelset(&signal, sig);
			list_del_init(&q->list);
			__sigqueue_free(q);
		}
	}

	sigorsets(&pending->signal, &signal, &retain);
}

void flush_itimer_signals(void)
{
	struct task_struct *tsk = current;
	unsigned long flags;

	spin_lock_irqsave(&tsk->sighand->siglock, flags);
	__flush_itimer_signals(&tsk->pending);
	__flush_itimer_signals(&tsk->signal->shared_pending);
	spin_unlock_irqrestore(&tsk->sighand->siglock, flags);
}

323 324 325 326 327 328 329 330 331 332
void ignore_signals(struct task_struct *t)
{
	int i;

	for (i = 0; i < _NSIG; ++i)
		t->sighand->action[i].sa.sa_handler = SIG_IGN;

	flush_signals(t);
}

L
Linus Torvalds 已提交
333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350
/*
 * Flush all handlers for a task.
 */

void
flush_signal_handlers(struct task_struct *t, int force_default)
{
	int i;
	struct k_sigaction *ka = &t->sighand->action[0];
	for (i = _NSIG ; i != 0 ; i--) {
		if (force_default || ka->sa.sa_handler != SIG_IGN)
			ka->sa.sa_handler = SIG_DFL;
		ka->sa.sa_flags = 0;
		sigemptyset(&ka->sa.sa_mask);
		ka++;
	}
}

351 352
int unhandled_signal(struct task_struct *tsk, int sig)
{
353
	void __user *handler = tsk->sighand->action[sig-1].sa.sa_handler;
354
	if (is_global_init(tsk))
355
		return 1;
356
	if (handler != SIG_IGN && handler != SIG_DFL)
357
		return 0;
358
	return !tracehook_consider_fatal_signal(tsk, sig);
359 360
}

L
Linus Torvalds 已提交
361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395

/* Notify the system that a driver wants to block all signals for this
 * process, and wants to be notified if any signals at all were to be
 * sent/acted upon.  If the notifier routine returns non-zero, then the
 * signal will be acted upon after all.  If the notifier routine returns 0,
 * then then signal will be blocked.  Only one block per process is
 * allowed.  priv is a pointer to private data that the notifier routine
 * can use to determine if the signal should be blocked or not.  */

void
block_all_signals(int (*notifier)(void *priv), void *priv, sigset_t *mask)
{
	unsigned long flags;

	spin_lock_irqsave(&current->sighand->siglock, flags);
	current->notifier_mask = mask;
	current->notifier_data = priv;
	current->notifier = notifier;
	spin_unlock_irqrestore(&current->sighand->siglock, flags);
}

/* Notify the system that blocking has ended. */

void
unblock_all_signals(void)
{
	unsigned long flags;

	spin_lock_irqsave(&current->sighand->siglock, flags);
	current->notifier = NULL;
	current->notifier_data = NULL;
	recalc_sigpending();
	spin_unlock_irqrestore(&current->sighand->siglock, flags);
}

396
static void collect_signal(int sig, struct sigpending *list, siginfo_t *info)
L
Linus Torvalds 已提交
397 398 399 400 401 402 403 404 405
{
	struct sigqueue *q, *first = NULL;

	/*
	 * Collect the siginfo appropriate to this signal.  Check if
	 * there is another siginfo for the same signal.
	*/
	list_for_each_entry(q, &list->list, list) {
		if (q->info.si_signo == sig) {
406 407
			if (first)
				goto still_pending;
L
Linus Torvalds 已提交
408 409 410
			first = q;
		}
	}
411 412 413

	sigdelset(&list->signal, sig);

L
Linus Torvalds 已提交
414
	if (first) {
415
still_pending:
L
Linus Torvalds 已提交
416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434
		list_del_init(&first->list);
		copy_siginfo(info, &first->info);
		__sigqueue_free(first);
	} else {
		/* Ok, it wasn't in the queue.  This must be
		   a fast-pathed signal or we must have been
		   out of queue space.  So zero out the info.
		 */
		info->si_signo = sig;
		info->si_errno = 0;
		info->si_code = 0;
		info->si_pid = 0;
		info->si_uid = 0;
	}
}

static int __dequeue_signal(struct sigpending *pending, sigset_t *mask,
			siginfo_t *info)
{
435
	int sig = next_signal(pending, mask);
L
Linus Torvalds 已提交
436 437 438 439 440 441 442 443 444 445 446

	if (sig) {
		if (current->notifier) {
			if (sigismember(current->notifier_mask, sig)) {
				if (!(current->notifier)(current->notifier_data)) {
					clear_thread_flag(TIF_SIGPENDING);
					return 0;
				}
			}
		}

447
		collect_signal(sig, pending, info);
L
Linus Torvalds 已提交
448 449 450 451 452 453 454 455 456 457 458 459 460
	}

	return sig;
}

/*
 * Dequeue a signal and return the element to the caller, which is 
 * expected to free it.
 *
 * All callers have to hold the siglock.
 */
int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info)
{
461
	int signr;
462 463 464 465

	/* We only dequeue private signals from ourselves, we don't let
	 * signalfd steal them
	 */
D
Davide Libenzi 已提交
466
	signr = __dequeue_signal(&tsk->pending, mask, info);
467
	if (!signr) {
L
Linus Torvalds 已提交
468 469
		signr = __dequeue_signal(&tsk->signal->shared_pending,
					 mask, info);
470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493
		/*
		 * itimer signal ?
		 *
		 * itimers are process shared and we restart periodic
		 * itimers in the signal delivery path to prevent DoS
		 * attacks in the high resolution timer case. This is
		 * compliant with the old way of self restarting
		 * itimers, as the SIGALRM is a legacy signal and only
		 * queued once. Changing the restart behaviour to
		 * restart the timer in the signal dequeue path is
		 * reducing the timer noise on heavy loaded !highres
		 * systems too.
		 */
		if (unlikely(signr == SIGALRM)) {
			struct hrtimer *tmr = &tsk->signal->real_timer;

			if (!hrtimer_is_queued(tmr) &&
			    tsk->signal->it_real_incr.tv64 != 0) {
				hrtimer_forward(tmr, tmr->base->get_time(),
						tsk->signal->it_real_incr);
				hrtimer_restart(tmr);
			}
		}
	}
494

D
Davide Libenzi 已提交
495
	recalc_sigpending();
496 497 498 499
	if (!signr)
		return 0;

	if (unlikely(sig_kernel_stop(signr))) {
500 501 502 503 504 505 506 507 508 509 510 511
		/*
		 * Set a marker that we have dequeued a stop signal.  Our
		 * caller might release the siglock and then the pending
		 * stop signal it is about to process is no longer in the
		 * pending bitmasks, but must still be cleared by a SIGCONT
		 * (and overruled by a SIGKILL).  So those cases clear this
		 * shared flag after we've set it.  Note that this flag may
		 * remain set after the signal we return is ignored or
		 * handled.  That doesn't matter because its only purpose
		 * is to alert stop-signal processing code when another
		 * processor has come along and cleared the flag.
		 */
512
		tsk->signal->flags |= SIGNAL_STOP_DEQUEUED;
513
	}
514
	if ((info->si_code & __SI_MASK) == __SI_TIMER && info->si_sys_private) {
L
Linus Torvalds 已提交
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
		/*
		 * Release the siglock to ensure proper locking order
		 * of timer locks outside of siglocks.  Note, we leave
		 * irqs disabled here, since the posix-timers code is
		 * about to disable them again anyway.
		 */
		spin_unlock(&tsk->sighand->siglock);
		do_schedule_next_timer(info);
		spin_lock(&tsk->sighand->siglock);
	}
	return signr;
}

/*
 * Tell a process that it has a new active signal..
 *
 * NOTE! we rely on the previous spin_lock to
 * lock interrupts for us! We can only be called with
 * "siglock" held, and the local interrupt must
 * have been disabled when that got acquired!
 *
 * No need to set need_resched since signal event passing
 * goes through ->blocked
 */
void signal_wake_up(struct task_struct *t, int resume)
{
	unsigned int mask;

	set_tsk_thread_flag(t, TIF_SIGPENDING);

	/*
M
Matthew Wilcox 已提交
546 547
	 * For SIGKILL, we want to wake it up in the stopped/traced/killable
	 * case. We don't check t->state here because there is a race with it
L
Linus Torvalds 已提交
548 549 550 551 552 553
	 * executing another processor and just now entering stopped state.
	 * By using wake_up_state, we ensure the process will wake up and
	 * handle its death signal.
	 */
	mask = TASK_INTERRUPTIBLE;
	if (resume)
M
Matthew Wilcox 已提交
554
		mask |= TASK_WAKEKILL;
L
Linus Torvalds 已提交
555 556 557 558
	if (!wake_up_state(t, mask))
		kick_process(t);
}

559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585
/*
 * Remove signals in mask from the pending set and queue.
 * Returns 1 if any signals were found.
 *
 * All callers must be holding the siglock.
 *
 * This version takes a sigset mask and looks at all signals,
 * not just those in the first mask word.
 */
static int rm_from_queue_full(sigset_t *mask, struct sigpending *s)
{
	struct sigqueue *q, *n;
	sigset_t m;

	sigandsets(&m, mask, &s->signal);
	if (sigisemptyset(&m))
		return 0;

	signandsets(&s->signal, &s->signal, mask);
	list_for_each_entry_safe(q, n, &s->list, list) {
		if (sigismember(mask, q->info.si_signo)) {
			list_del_init(&q->list);
			__sigqueue_free(q);
		}
	}
	return 1;
}
L
Linus Torvalds 已提交
586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609
/*
 * Remove signals in mask from the pending set and queue.
 * Returns 1 if any signals were found.
 *
 * All callers must be holding the siglock.
 */
static int rm_from_queue(unsigned long mask, struct sigpending *s)
{
	struct sigqueue *q, *n;

	if (!sigtestsetmask(&s->signal, mask))
		return 0;

	sigdelsetmask(&s->signal, mask);
	list_for_each_entry_safe(q, n, &s->list, list) {
		if (q->info.si_signo < SIGRTMIN &&
		    (mask & sigmask(q->info.si_signo))) {
			list_del_init(&q->list);
			__sigqueue_free(q);
		}
	}
	return 1;
}

610 611 612 613 614 615 616 617 618 619 620
static inline int is_si_special(const struct siginfo *info)
{
	return info <= SEND_SIG_FORCED;
}

static inline bool si_fromuser(const struct siginfo *info)
{
	return info == SEND_SIG_NOINFO ||
		(!is_si_special(info) && SI_FROMUSER(info));
}

L
Linus Torvalds 已提交
621 622
/*
 * Bad permissions for sending the signal
623
 * - the caller must hold at least the RCU read lock
L
Linus Torvalds 已提交
624 625 626 627
 */
static int check_kill_permission(int sig, struct siginfo *info,
				 struct task_struct *t)
{
628
	const struct cred *cred = current_cred(), *tcred;
629
	struct pid *sid;
630 631
	int error;

632
	if (!valid_signal(sig))
633 634
		return -EINVAL;

635
	if (!si_fromuser(info))
636
		return 0;
A
Amy Griffis 已提交
637

638 639
	error = audit_signal_info(sig, t); /* Let audit system see the signal */
	if (error)
L
Linus Torvalds 已提交
640
		return error;
641

642 643 644 645 646
	tcred = __task_cred(t);
	if ((cred->euid ^ tcred->suid) &&
	    (cred->euid ^ tcred->uid) &&
	    (cred->uid  ^ tcred->suid) &&
	    (cred->uid  ^ tcred->uid) &&
647 648 649 650 651 652 653 654 655 656 657 658 659 660
	    !capable(CAP_KILL)) {
		switch (sig) {
		case SIGCONT:
			sid = task_session(t);
			/*
			 * We don't return the error if sid == NULL. The
			 * task was unhashed, the caller must notice this.
			 */
			if (!sid || sid == task_session(current))
				break;
		default:
			return -EPERM;
		}
	}
661

A
Amy Griffis 已提交
662
	return security_task_kill(t, info, sig, 0);
L
Linus Torvalds 已提交
663 664 665
}

/*
666 667
 * Handle magic process-wide effects of stop/continue signals. Unlike
 * the signal actions, these happen immediately at signal-generation
L
Linus Torvalds 已提交
668 669
 * time regardless of blocking, ignoring, or handling.  This does the
 * actual continuing for SIGCONT, but not the actual stopping for stop
670 671 672 673
 * signals. The process stop is done as a signal action for SIG_DFL.
 *
 * Returns true if the signal should be actually delivered, otherwise
 * it should be dropped.
L
Linus Torvalds 已提交
674
 */
675
static int prepare_signal(int sig, struct task_struct *p, int from_ancestor_ns)
L
Linus Torvalds 已提交
676
{
677
	struct signal_struct *signal = p->signal;
L
Linus Torvalds 已提交
678 679
	struct task_struct *t;

680
	if (unlikely(signal->flags & SIGNAL_GROUP_EXIT)) {
L
Linus Torvalds 已提交
681
		/*
682
		 * The process is in the middle of dying, nothing to do.
L
Linus Torvalds 已提交
683
		 */
684
	} else if (sig_kernel_stop(sig)) {
L
Linus Torvalds 已提交
685 686 687
		/*
		 * This is a stop signal.  Remove SIGCONT from all queues.
		 */
688
		rm_from_queue(sigmask(SIGCONT), &signal->shared_pending);
L
Linus Torvalds 已提交
689 690 691
		t = p;
		do {
			rm_from_queue(sigmask(SIGCONT), &t->pending);
692
		} while_each_thread(p, t);
L
Linus Torvalds 已提交
693
	} else if (sig == SIGCONT) {
694
		unsigned int why;
L
Linus Torvalds 已提交
695 696 697 698
		/*
		 * Remove all stop signals from all queues,
		 * and wake all threads.
		 */
699
		rm_from_queue(SIG_KERNEL_STOP_MASK, &signal->shared_pending);
L
Linus Torvalds 已提交
700 701 702 703 704 705 706 707 708 709 710 711 712
		t = p;
		do {
			unsigned int state;
			rm_from_queue(SIG_KERNEL_STOP_MASK, &t->pending);
			/*
			 * If there is a handler for SIGCONT, we must make
			 * sure that no thread returns to user mode before
			 * we post the signal, in case it was the only
			 * thread eligible to run the signal handler--then
			 * it must not do anything between resuming and
			 * running the handler.  With the TIF_SIGPENDING
			 * flag set, the thread will pause and acquire the
			 * siglock that we hold now and until we've queued
713
			 * the pending signal.
L
Linus Torvalds 已提交
714 715 716 717
			 *
			 * Wake up the stopped thread _after_ setting
			 * TIF_SIGPENDING
			 */
M
Matthew Wilcox 已提交
718
			state = __TASK_STOPPED;
L
Linus Torvalds 已提交
719 720 721 722 723
			if (sig_user_defined(t, SIGCONT) && !sigismember(&t->blocked, SIGCONT)) {
				set_tsk_thread_flag(t, TIF_SIGPENDING);
				state |= TASK_INTERRUPTIBLE;
			}
			wake_up_state(t, state);
724
		} while_each_thread(p, t);
L
Linus Torvalds 已提交
725

726 727 728 729 730 731 732 733 734
		/*
		 * Notify the parent with CLD_CONTINUED if we were stopped.
		 *
		 * If we were in the middle of a group stop, we pretend it
		 * was already finished, and then continued. Since SIGCHLD
		 * doesn't queue we report only CLD_STOPPED, as if the next
		 * CLD_CONTINUED was dropped.
		 */
		why = 0;
735
		if (signal->flags & SIGNAL_STOP_STOPPED)
736
			why |= SIGNAL_CLD_CONTINUED;
737
		else if (signal->group_stop_count)
738 739 740
			why |= SIGNAL_CLD_STOPPED;

		if (why) {
741
			/*
742
			 * The first thread which returns from do_signal_stop()
743 744 745
			 * will take ->siglock, notice SIGNAL_CLD_MASK, and
			 * notify its parent. See get_signal_to_deliver().
			 */
746 747 748
			signal->flags = why | SIGNAL_STOP_CONTINUED;
			signal->group_stop_count = 0;
			signal->group_exit_code = 0;
L
Linus Torvalds 已提交
749 750 751 752 753 754
		} else {
			/*
			 * We are not stopped, but there could be a stop
			 * signal in the middle of being processed after
			 * being removed from the queue.  Clear that too.
			 */
755
			signal->flags &= ~SIGNAL_STOP_DEQUEUED;
L
Linus Torvalds 已提交
756 757
		}
	}
758

759
	return !sig_ignored(p, sig, from_ancestor_ns);
L
Linus Torvalds 已提交
760 761
}

762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782
/*
 * Test if P wants to take SIG.  After we've checked all threads with this,
 * it's equivalent to finding no threads not blocking SIG.  Any threads not
 * blocking SIG were ruled out because they are not running and already
 * have pending signals.  Such threads will dequeue from the shared queue
 * as soon as they're available, so putting the signal on the shared queue
 * will be equivalent to sending it to one such thread.
 */
static inline int wants_signal(int sig, struct task_struct *p)
{
	if (sigismember(&p->blocked, sig))
		return 0;
	if (p->flags & PF_EXITING)
		return 0;
	if (sig == SIGKILL)
		return 1;
	if (task_is_stopped_or_traced(p))
		return 0;
	return task_curr(p) || !signal_pending(p);
}

783
static void complete_signal(int sig, struct task_struct *p, int group)
784 785 786 787 788 789 790 791 792 793 794 795
{
	struct signal_struct *signal = p->signal;
	struct task_struct *t;

	/*
	 * Now find a thread we can wake up to take the signal off the queue.
	 *
	 * If the main thread wants the signal, it gets first crack.
	 * Probably the least surprising to the average bear.
	 */
	if (wants_signal(sig, p))
		t = p;
796
	else if (!group || thread_group_empty(p))
797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823
		/*
		 * There is just one thread and it does not need to be woken.
		 * It will dequeue unblocked signals before it runs again.
		 */
		return;
	else {
		/*
		 * Otherwise try to find a suitable thread.
		 */
		t = signal->curr_target;
		while (!wants_signal(sig, t)) {
			t = next_thread(t);
			if (t == signal->curr_target)
				/*
				 * No thread needs to be woken.
				 * Any eligible threads will see
				 * the signal in the queue soon.
				 */
				return;
		}
		signal->curr_target = t;
	}

	/*
	 * Found a killable thread.  If the signal will be fatal,
	 * then start taking the whole group down immediately.
	 */
824 825
	if (sig_fatal(p, sig) &&
	    !(signal->flags & (SIGNAL_UNKILLABLE | SIGNAL_GROUP_EXIT)) &&
826
	    !sigismember(&t->real_blocked, sig) &&
827
	    (sig == SIGKILL ||
828
	     !tracehook_consider_fatal_signal(t, sig))) {
829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858
		/*
		 * This signal will be fatal to the whole group.
		 */
		if (!sig_kernel_coredump(sig)) {
			/*
			 * Start a group exit and wake everybody up.
			 * This way we don't have other threads
			 * running and doing things after a slower
			 * thread has the fatal signal pending.
			 */
			signal->flags = SIGNAL_GROUP_EXIT;
			signal->group_exit_code = sig;
			signal->group_stop_count = 0;
			t = p;
			do {
				sigaddset(&t->pending.signal, SIGKILL);
				signal_wake_up(t, 1);
			} while_each_thread(p, t);
			return;
		}
	}

	/*
	 * The signal is already in the shared-pending queue.
	 * Tell the chosen thread to wake up and dequeue it.
	 */
	signal_wake_up(t, sig == SIGKILL);
	return;
}

859 860 861 862 863
static inline int legacy_queue(struct sigpending *signals, int sig)
{
	return (sig < SIGRTMIN) && sigismember(&signals->signal, sig);
}

864 865
static int __send_signal(int sig, struct siginfo *info, struct task_struct *t,
			int group, int from_ancestor_ns)
L
Linus Torvalds 已提交
866
{
867
	struct sigpending *pending;
868
	struct sigqueue *q;
869
	int override_rlimit;
L
Linus Torvalds 已提交
870

871
	trace_signal_generate(sig, info, t);
872

873
	assert_spin_locked(&t->sighand->siglock);
874 875

	if (!prepare_signal(sig, t, from_ancestor_ns))
876
		return 0;
877 878

	pending = group ? &t->signal->shared_pending : &t->pending;
879 880 881 882 883
	/*
	 * Short-circuit ignored signals and support queuing
	 * exactly one non-rt signal, so that we can get more
	 * detailed information about the cause of the signal.
	 */
884
	if (legacy_queue(pending, sig))
885
		return 0;
L
Linus Torvalds 已提交
886 887 888 889
	/*
	 * fast-pathed signals for kernel-internal things like SIGSTOP
	 * or SIGKILL.
	 */
890
	if (info == SEND_SIG_FORCED)
L
Linus Torvalds 已提交
891 892 893 894 895 896 897 898 899 900
		goto out_set;

	/* Real-time signals must be queued if sent by sigqueue, or
	   some other real-time mechanism.  It is implementation
	   defined whether kill() does so.  We attempt to do so, on
	   the principle of least surprise, but since kill is not
	   allowed to fail with EAGAIN when low on memory we just
	   make sure at least one signal gets delivered and don't
	   pass on the info struct.  */

901 902 903 904 905
	if (sig < SIGRTMIN)
		override_rlimit = (is_si_special(info) || info->si_code >= 0);
	else
		override_rlimit = 0;

906
	q = __sigqueue_alloc(sig, t, GFP_ATOMIC | __GFP_NOTRACK_FALSE_POSITIVE,
907
		override_rlimit);
L
Linus Torvalds 已提交
908
	if (q) {
909
		list_add_tail(&q->list, &pending->list);
L
Linus Torvalds 已提交
910
		switch ((unsigned long) info) {
911
		case (unsigned long) SEND_SIG_NOINFO:
L
Linus Torvalds 已提交
912 913 914
			q->info.si_signo = sig;
			q->info.si_errno = 0;
			q->info.si_code = SI_USER;
915
			q->info.si_pid = task_tgid_nr_ns(current,
916
							task_active_pid_ns(t));
917
			q->info.si_uid = current_uid();
L
Linus Torvalds 已提交
918
			break;
919
		case (unsigned long) SEND_SIG_PRIV:
L
Linus Torvalds 已提交
920 921 922 923 924 925 926 927
			q->info.si_signo = sig;
			q->info.si_errno = 0;
			q->info.si_code = SI_KERNEL;
			q->info.si_pid = 0;
			q->info.si_uid = 0;
			break;
		default:
			copy_siginfo(&q->info, info);
928 929
			if (from_ancestor_ns)
				q->info.si_pid = 0;
L
Linus Torvalds 已提交
930 931
			break;
		}
932
	} else if (!is_si_special(info)) {
933 934 935 936 937 938 939
		if (sig >= SIGRTMIN && info->si_code != SI_USER) {
			/*
			 * Queue overflow, abort.  We may abort if the
			 * signal was rt and sent by user using something
			 * other than kill().
			 */
			trace_signal_overflow_fail(sig, group, info);
L
Linus Torvalds 已提交
940
			return -EAGAIN;
941 942 943 944 945 946 947
		} else {
			/*
			 * This is a silent loss of information.  We still
			 * send the signal, but the *info bits are lost.
			 */
			trace_signal_lose_info(sig, group, info);
		}
L
Linus Torvalds 已提交
948 949 950
	}

out_set:
951
	signalfd_notify(t, sig);
952
	sigaddset(&pending->signal, sig);
953 954
	complete_signal(sig, t, group);
	return 0;
L
Linus Torvalds 已提交
955 956
}

957 958 959
static int send_signal(int sig, struct siginfo *info, struct task_struct *t,
			int group)
{
960 961 962 963 964 965 966 967 968
	int from_ancestor_ns = 0;

#ifdef CONFIG_PID_NS
	if (!is_si_special(info) && SI_FROMUSER(info) &&
			task_pid_nr_ns(current, task_active_pid_ns(t)) <= 0)
		from_ancestor_ns = 1;
#endif

	return __send_signal(sig, info, t, group, from_ancestor_ns);
969 970
}

I
Ingo Molnar 已提交
971 972 973
static void print_fatal_signal(struct pt_regs *regs, int signr)
{
	printk("%s/%d: potentially unexpected fatal signal %d.\n",
974
		current->comm, task_pid_nr(current), signr);
I
Ingo Molnar 已提交
975

A
Al Viro 已提交
976
#if defined(__i386__) && !defined(__arch_um__)
977
	printk("code at %08lx: ", regs->ip);
I
Ingo Molnar 已提交
978 979 980 981 982
	{
		int i;
		for (i = 0; i < 16; i++) {
			unsigned char insn;

983
			__get_user(insn, (unsigned char *)(regs->ip + i));
I
Ingo Molnar 已提交
984 985 986 987 988
			printk("%02x ", insn);
		}
	}
#endif
	printk("\n");
989
	preempt_disable();
I
Ingo Molnar 已提交
990
	show_regs(regs);
991
	preempt_enable();
I
Ingo Molnar 已提交
992 993 994 995 996 997 998 999 1000 1001
}

static int __init setup_print_fatal_signals(char *str)
{
	get_option (&str, &print_fatal_signals);

	return 1;
}

__setup("print-fatal-signals=", setup_print_fatal_signals);
L
Linus Torvalds 已提交
1002

1003 1004 1005 1006 1007 1008
int
__group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p)
{
	return send_signal(sig, info, p, 1);
}

L
Linus Torvalds 已提交
1009 1010 1011
static int
specific_send_sig_info(int sig, struct siginfo *info, struct task_struct *t)
{
1012
	return send_signal(sig, info, t, 0);
L
Linus Torvalds 已提交
1013 1014
}

1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028
int do_send_sig_info(int sig, struct siginfo *info, struct task_struct *p,
			bool group)
{
	unsigned long flags;
	int ret = -ESRCH;

	if (lock_task_sighand(p, &flags)) {
		ret = send_signal(sig, info, p, group);
		unlock_task_sighand(p, &flags);
	}

	return ret;
}

L
Linus Torvalds 已提交
1029 1030 1031
/*
 * Force a signal that the process can't ignore: if necessary
 * we unblock the signal and change any SIG_IGN to SIG_DFL.
1032 1033 1034 1035 1036
 *
 * Note: If we unblock the signal, we always reset it to SIG_DFL,
 * since we do not want to have a signal handler that was blocked
 * be invoked when user space had explicitly blocked it.
 *
1037 1038
 * We don't want to have recursive SIGSEGV's etc, for example,
 * that is why we also clear SIGNAL_UNKILLABLE.
L
Linus Torvalds 已提交
1039 1040 1041 1042 1043
 */
int
force_sig_info(int sig, struct siginfo *info, struct task_struct *t)
{
	unsigned long int flags;
1044 1045
	int ret, blocked, ignored;
	struct k_sigaction *action;
L
Linus Torvalds 已提交
1046 1047

	spin_lock_irqsave(&t->sighand->siglock, flags);
1048 1049 1050 1051 1052 1053 1054
	action = &t->sighand->action[sig-1];
	ignored = action->sa.sa_handler == SIG_IGN;
	blocked = sigismember(&t->blocked, sig);
	if (blocked || ignored) {
		action->sa.sa_handler = SIG_DFL;
		if (blocked) {
			sigdelset(&t->blocked, sig);
R
Roland McGrath 已提交
1055
			recalc_sigpending_and_wake(t);
1056
		}
L
Linus Torvalds 已提交
1057
	}
1058 1059
	if (action->sa.sa_handler == SIG_DFL)
		t->signal->flags &= ~SIGNAL_UNKILLABLE;
L
Linus Torvalds 已提交
1060 1061 1062 1063 1064 1065 1066 1067 1068
	ret = specific_send_sig_info(sig, info, t);
	spin_unlock_irqrestore(&t->sighand->siglock, flags);

	return ret;
}

void
force_sig_specific(int sig, struct task_struct *t)
{
1069
	force_sig_info(sig, SEND_SIG_FORCED, t);
L
Linus Torvalds 已提交
1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087
}

/*
 * Nuke all other threads in the group.
 */
void zap_other_threads(struct task_struct *p)
{
	struct task_struct *t;

	p->signal->group_stop_count = 0;

	for (t = next_thread(p); t != p; t = next_thread(t)) {
		/*
		 * Don't bother with already dead threads
		 */
		if (t->exit_state)
			continue;

1088
		/* SIGKILL will be handled before any pending SIGSTOP */
L
Linus Torvalds 已提交
1089 1090 1091 1092 1093
		sigaddset(&t->pending.signal, SIGKILL);
		signal_wake_up(t, 1);
	}
}

1094 1095 1096 1097
struct sighand_struct *lock_task_sighand(struct task_struct *tsk, unsigned long *flags)
{
	struct sighand_struct *sighand;

1098
	rcu_read_lock();
1099 1100 1101 1102 1103 1104 1105 1106 1107 1108
	for (;;) {
		sighand = rcu_dereference(tsk->sighand);
		if (unlikely(sighand == NULL))
			break;

		spin_lock_irqsave(&sighand->siglock, *flags);
		if (likely(sighand == tsk->sighand))
			break;
		spin_unlock_irqrestore(&sighand->siglock, *flags);
	}
1109
	rcu_read_unlock();
1110 1111 1112 1113

	return sighand;
}

1114 1115 1116 1117
/*
 * send signal info to all the members of a group
 * - the caller must hold the RCU read lock at least
 */
L
Linus Torvalds 已提交
1118 1119
int group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p)
{
1120
	int ret = check_kill_permission(sig, info, p);
1121

1122 1123
	if (!ret && sig)
		ret = do_send_sig_info(sig, info, p, true);
L
Linus Torvalds 已提交
1124 1125 1126 1127 1128

	return ret;
}

/*
1129
 * __kill_pgrp_info() sends a signal to a process group: this is what the tty
L
Linus Torvalds 已提交
1130
 * control characters do (^C, ^Z etc)
1131
 * - the caller must hold at least a readlock on tasklist_lock
L
Linus Torvalds 已提交
1132
 */
1133
int __kill_pgrp_info(int sig, struct siginfo *info, struct pid *pgrp)
L
Linus Torvalds 已提交
1134 1135 1136 1137 1138 1139
{
	struct task_struct *p = NULL;
	int retval, success;

	success = 0;
	retval = -ESRCH;
1140
	do_each_pid_task(pgrp, PIDTYPE_PGID, p) {
L
Linus Torvalds 已提交
1141 1142 1143
		int err = group_send_sig_info(sig, info, p);
		success |= !err;
		retval = err;
1144
	} while_each_pid_task(pgrp, PIDTYPE_PGID, p);
L
Linus Torvalds 已提交
1145 1146 1147
	return success ? 0 : retval;
}

1148
int kill_pid_info(int sig, struct siginfo *info, struct pid *pid)
L
Linus Torvalds 已提交
1149
{
1150
	int error = -ESRCH;
L
Linus Torvalds 已提交
1151 1152
	struct task_struct *p;

I
Ingo Molnar 已提交
1153
	rcu_read_lock();
1154
retry:
1155
	p = pid_task(pid, PIDTYPE_PID);
1156
	if (p) {
L
Linus Torvalds 已提交
1157
		error = group_send_sig_info(sig, info, p);
1158 1159 1160 1161 1162 1163 1164 1165 1166
		if (unlikely(error == -ESRCH))
			/*
			 * The task was unhashed in between, try again.
			 * If it is dead, pid_task() will return NULL,
			 * if we race with de_thread() it will find the
			 * new leader.
			 */
			goto retry;
	}
I
Ingo Molnar 已提交
1167
	rcu_read_unlock();
1168

L
Linus Torvalds 已提交
1169 1170 1171
	return error;
}

1172 1173
int
kill_proc_info(int sig, struct siginfo *info, pid_t pid)
1174 1175 1176
{
	int error;
	rcu_read_lock();
1177
	error = kill_pid_info(sig, info, find_vpid(pid));
1178 1179 1180 1181
	rcu_read_unlock();
	return error;
}

1182 1183
/* like kill_pid_info(), but doesn't use uid/euid of "current" */
int kill_pid_info_as_uid(int sig, struct siginfo *info, struct pid *pid,
1184
		      uid_t uid, uid_t euid, u32 secid)
1185 1186 1187
{
	int ret = -EINVAL;
	struct task_struct *p;
1188
	const struct cred *pcred;
1189 1190 1191 1192 1193

	if (!valid_signal(sig))
		return ret;

	read_lock(&tasklist_lock);
1194
	p = pid_task(pid, PIDTYPE_PID);
1195 1196 1197 1198
	if (!p) {
		ret = -ESRCH;
		goto out_unlock;
	}
1199
	pcred = __task_cred(p);
1200
	if (si_fromuser(info) &&
1201 1202
	    euid != pcred->suid && euid != pcred->uid &&
	    uid  != pcred->suid && uid  != pcred->uid) {
1203 1204 1205
		ret = -EPERM;
		goto out_unlock;
	}
1206 1207 1208
	ret = security_task_kill(p, info, sig, secid);
	if (ret)
		goto out_unlock;
1209 1210 1211
	if (sig && p->sighand) {
		unsigned long flags;
		spin_lock_irqsave(&p->sighand->siglock, flags);
1212
		ret = __send_signal(sig, info, p, 1, 0);
1213 1214 1215 1216 1217 1218
		spin_unlock_irqrestore(&p->sighand->siglock, flags);
	}
out_unlock:
	read_unlock(&tasklist_lock);
	return ret;
}
1219
EXPORT_SYMBOL_GPL(kill_pid_info_as_uid);
L
Linus Torvalds 已提交
1220 1221 1222 1223 1224 1225 1226 1227

/*
 * kill_something_info() interprets pid in interesting ways just like kill(2).
 *
 * POSIX specifies that kill(-1,sig) is unspecified, but what we have
 * is probably wrong.  Should make it like BSD or SYSV.
 */

1228
static int kill_something_info(int sig, struct siginfo *info, pid_t pid)
L
Linus Torvalds 已提交
1229
{
1230
	int ret;
1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243

	if (pid > 0) {
		rcu_read_lock();
		ret = kill_pid_info(sig, info, find_vpid(pid));
		rcu_read_unlock();
		return ret;
	}

	read_lock(&tasklist_lock);
	if (pid != -1) {
		ret = __kill_pgrp_info(sig, info,
				pid ? find_vpid(-pid) : task_pgrp(current));
	} else {
L
Linus Torvalds 已提交
1244 1245 1246 1247
		int retval = 0, count = 0;
		struct task_struct * p;

		for_each_process(p) {
1248 1249
			if (task_pid_vnr(p) > 1 &&
					!same_thread_group(p, current)) {
L
Linus Torvalds 已提交
1250 1251 1252 1253 1254 1255
				int err = group_send_sig_info(sig, info, p);
				++count;
				if (err != -EPERM)
					retval = err;
			}
		}
1256
		ret = count ? retval : -ESRCH;
L
Linus Torvalds 已提交
1257
	}
1258 1259
	read_unlock(&tasklist_lock);

1260
	return ret;
L
Linus Torvalds 已提交
1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273
}

/*
 * These are for backward compatibility with the rest of the kernel source.
 */

int
send_sig_info(int sig, struct siginfo *info, struct task_struct *p)
{
	/*
	 * Make sure legacy kernel users don't send in bad values
	 * (normal paths check this in check_kill_permission).
	 */
1274
	if (!valid_signal(sig))
L
Linus Torvalds 已提交
1275 1276
		return -EINVAL;

1277
	return do_send_sig_info(sig, info, p, false);
L
Linus Torvalds 已提交
1278 1279
}

1280 1281 1282
#define __si_special(priv) \
	((priv) ? SEND_SIG_PRIV : SEND_SIG_NOINFO)

L
Linus Torvalds 已提交
1283 1284 1285
int
send_sig(int sig, struct task_struct *p, int priv)
{
1286
	return send_sig_info(sig, __si_special(priv), p);
L
Linus Torvalds 已提交
1287 1288 1289 1290 1291
}

void
force_sig(int sig, struct task_struct *p)
{
1292
	force_sig_info(sig, SEND_SIG_PRIV, p);
L
Linus Torvalds 已提交
1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313
}

/*
 * When things go south during signal handling, we
 * will force a SIGSEGV. And if the signal that caused
 * the problem was already a SIGSEGV, we'll want to
 * make sure we don't even try to deliver the signal..
 */
int
force_sigsegv(int sig, struct task_struct *p)
{
	if (sig == SIGSEGV) {
		unsigned long flags;
		spin_lock_irqsave(&p->sighand->siglock, flags);
		p->sighand->action[sig - 1].sa.sa_handler = SIG_DFL;
		spin_unlock_irqrestore(&p->sighand->siglock, flags);
	}
	force_sig(SIGSEGV, p);
	return 0;
}

1314 1315
int kill_pgrp(struct pid *pid, int sig, int priv)
{
1316 1317 1318 1319 1320 1321 1322
	int ret;

	read_lock(&tasklist_lock);
	ret = __kill_pgrp_info(sig, __si_special(priv), pid);
	read_unlock(&tasklist_lock);

	return ret;
1323 1324 1325 1326 1327 1328 1329 1330 1331
}
EXPORT_SYMBOL(kill_pgrp);

int kill_pid(struct pid *pid, int sig, int priv)
{
	return kill_pid_info(sig, __si_special(priv), pid);
}
EXPORT_SYMBOL(kill_pid);

L
Linus Torvalds 已提交
1332 1333 1334 1335
/*
 * These functions support sending signals using preallocated sigqueue
 * structures.  This is needed "because realtime applications cannot
 * afford to lose notifications of asynchronous events, like timer
1336
 * expirations or I/O completions".  In the case of Posix Timers
L
Linus Torvalds 已提交
1337 1338 1339 1340 1341 1342
 * we allocate the sigqueue structure from the timer_create.  If this
 * allocation fails we are able to report the failure to the application
 * with an EAGAIN error.
 */
struct sigqueue *sigqueue_alloc(void)
{
1343
	struct sigqueue *q = __sigqueue_alloc(-1, current, GFP_KERNEL, 0);
L
Linus Torvalds 已提交
1344

1345
	if (q)
L
Linus Torvalds 已提交
1346
		q->flags |= SIGQUEUE_PREALLOC;
1347 1348

	return q;
L
Linus Torvalds 已提交
1349 1350 1351 1352 1353
}

void sigqueue_free(struct sigqueue *q)
{
	unsigned long flags;
1354 1355
	spinlock_t *lock = &current->sighand->siglock;

L
Linus Torvalds 已提交
1356 1357
	BUG_ON(!(q->flags & SIGQUEUE_PREALLOC));
	/*
1358 1359
	 * We must hold ->siglock while testing q->list
	 * to serialize with collect_signal() or with
1360
	 * __exit_signal()->flush_sigqueue().
L
Linus Torvalds 已提交
1361
	 */
1362
	spin_lock_irqsave(lock, flags);
1363 1364 1365 1366 1367
	q->flags &= ~SIGQUEUE_PREALLOC;
	/*
	 * If it is queued it will be freed when dequeued,
	 * like the "regular" sigqueue.
	 */
1368
	if (!list_empty(&q->list))
1369
		q = NULL;
1370 1371
	spin_unlock_irqrestore(lock, flags);

1372 1373
	if (q)
		__sigqueue_free(q);
L
Linus Torvalds 已提交
1374 1375
}

1376
int send_sigqueue(struct sigqueue *q, struct task_struct *t, int group)
1377
{
1378
	int sig = q->info.si_signo;
1379
	struct sigpending *pending;
1380 1381
	unsigned long flags;
	int ret;
1382

1383
	BUG_ON(!(q->flags & SIGQUEUE_PREALLOC));
1384 1385 1386 1387 1388

	ret = -1;
	if (!likely(lock_task_sighand(t, &flags)))
		goto ret;

1389
	ret = 1; /* the signal is ignored */
1390
	if (!prepare_signal(sig, t, 0))
1391 1392 1393
		goto out;

	ret = 0;
1394 1395 1396 1397 1398 1399 1400
	if (unlikely(!list_empty(&q->list))) {
		/*
		 * If an SI_TIMER entry is already queue just increment
		 * the overrun count.
		 */
		BUG_ON(q->info.si_code != SI_TIMER);
		q->info.si_overrun++;
1401
		goto out;
1402
	}
1403
	q->info.si_overrun = 0;
1404 1405

	signalfd_notify(t, sig);
1406
	pending = group ? &t->signal->shared_pending : &t->pending;
1407 1408
	list_add_tail(&q->list, &pending->list);
	sigaddset(&pending->signal, sig);
1409
	complete_signal(sig, t, group);
1410 1411 1412 1413
out:
	unlock_task_sighand(t, &flags);
ret:
	return ret;
1414 1415
}

L
Linus Torvalds 已提交
1416 1417 1418
/*
 * Let a parent know about the death of a child.
 * For a stopped/continued status change, use do_notify_parent_cldstop instead.
R
Roland McGrath 已提交
1419 1420 1421
 *
 * Returns -1 if our parent ignored us and so we've switched to
 * self-reaping, or else @sig.
L
Linus Torvalds 已提交
1422
 */
R
Roland McGrath 已提交
1423
int do_notify_parent(struct task_struct *tsk, int sig)
L
Linus Torvalds 已提交
1424 1425 1426 1427
{
	struct siginfo info;
	unsigned long flags;
	struct sighand_struct *psig;
R
Roland McGrath 已提交
1428
	int ret = sig;
L
Linus Torvalds 已提交
1429 1430 1431 1432

	BUG_ON(sig == -1);

 	/* do_notify_parent_cldstop should have been called instead.  */
M
Matthew Wilcox 已提交
1433
 	BUG_ON(task_is_stopped_or_traced(tsk));
L
Linus Torvalds 已提交
1434

1435
	BUG_ON(!task_ptrace(tsk) &&
L
Linus Torvalds 已提交
1436 1437 1438 1439
	       (tsk->group_leader != tsk || !thread_group_empty(tsk)));

	info.si_signo = sig;
	info.si_errno = 0;
1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453
	/*
	 * we are under tasklist_lock here so our parent is tied to
	 * us and cannot exit and release its namespace.
	 *
	 * the only it can is to switch its nsproxy with sys_unshare,
	 * bu uncharing pid namespaces is not allowed, so we'll always
	 * see relevant namespace
	 *
	 * write_lock() currently calls preempt_disable() which is the
	 * same as rcu_read_lock(), but according to Oleg, this is not
	 * correct to rely on this
	 */
	rcu_read_lock();
	info.si_pid = task_pid_nr_ns(tsk, tsk->parent->nsproxy->pid_ns);
1454
	info.si_uid = __task_cred(tsk)->uid;
1455 1456
	rcu_read_unlock();

1457 1458 1459 1460
	info.si_utime = cputime_to_clock_t(cputime_add(tsk->utime,
				tsk->signal->utime));
	info.si_stime = cputime_to_clock_t(cputime_add(tsk->stime,
				tsk->signal->stime));
L
Linus Torvalds 已提交
1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473

	info.si_status = tsk->exit_code & 0x7f;
	if (tsk->exit_code & 0x80)
		info.si_code = CLD_DUMPED;
	else if (tsk->exit_code & 0x7f)
		info.si_code = CLD_KILLED;
	else {
		info.si_code = CLD_EXITED;
		info.si_status = tsk->exit_code >> 8;
	}

	psig = tsk->parent->sighand;
	spin_lock_irqsave(&psig->siglock, flags);
1474
	if (!task_ptrace(tsk) && sig == SIGCHLD &&
L
Linus Torvalds 已提交
1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491
	    (psig->action[SIGCHLD-1].sa.sa_handler == SIG_IGN ||
	     (psig->action[SIGCHLD-1].sa.sa_flags & SA_NOCLDWAIT))) {
		/*
		 * We are exiting and our parent doesn't care.  POSIX.1
		 * defines special semantics for setting SIGCHLD to SIG_IGN
		 * or setting the SA_NOCLDWAIT flag: we should be reaped
		 * automatically and not left for our parent's wait4 call.
		 * Rather than having the parent do it as a magic kind of
		 * signal handler, we just set this to tell do_exit that we
		 * can be cleaned up without becoming a zombie.  Note that
		 * we still call __wake_up_parent in this case, because a
		 * blocked sys_wait4 might now return -ECHILD.
		 *
		 * Whether we send SIGCHLD or not for SA_NOCLDWAIT
		 * is implementation-defined: we do (if you don't want
		 * it, just use SIG_IGN instead).
		 */
R
Roland McGrath 已提交
1492
		ret = tsk->exit_signal = -1;
L
Linus Torvalds 已提交
1493
		if (psig->action[SIGCHLD-1].sa.sa_handler == SIG_IGN)
R
Roland McGrath 已提交
1494
			sig = -1;
L
Linus Torvalds 已提交
1495
	}
1496
	if (valid_signal(sig) && sig > 0)
L
Linus Torvalds 已提交
1497 1498 1499
		__group_send_sig_info(sig, &info, tsk->parent);
	__wake_up_parent(tsk, tsk->parent);
	spin_unlock_irqrestore(&psig->siglock, flags);
R
Roland McGrath 已提交
1500

R
Roland McGrath 已提交
1501
	return ret;
L
Linus Torvalds 已提交
1502 1503
}

1504
static void do_notify_parent_cldstop(struct task_struct *tsk, int why)
L
Linus Torvalds 已提交
1505 1506 1507
{
	struct siginfo info;
	unsigned long flags;
1508
	struct task_struct *parent;
L
Linus Torvalds 已提交
1509 1510
	struct sighand_struct *sighand;

1511
	if (task_ptrace(tsk))
1512 1513 1514 1515 1516 1517
		parent = tsk->parent;
	else {
		tsk = tsk->group_leader;
		parent = tsk->real_parent;
	}

L
Linus Torvalds 已提交
1518 1519
	info.si_signo = SIGCHLD;
	info.si_errno = 0;
1520 1521 1522 1523
	/*
	 * see comment in do_notify_parent() abot the following 3 lines
	 */
	rcu_read_lock();
1524
	info.si_pid = task_pid_nr_ns(tsk, parent->nsproxy->pid_ns);
1525
	info.si_uid = __task_cred(tsk)->uid;
1526 1527
	rcu_read_unlock();

1528 1529
	info.si_utime = cputime_to_clock_t(tsk->utime);
	info.si_stime = cputime_to_clock_t(tsk->stime);
L
Linus Torvalds 已提交
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

 	info.si_code = why;
 	switch (why) {
 	case CLD_CONTINUED:
 		info.si_status = SIGCONT;
 		break;
 	case CLD_STOPPED:
 		info.si_status = tsk->signal->group_exit_code & 0x7f;
 		break;
 	case CLD_TRAPPED:
 		info.si_status = tsk->exit_code & 0x7f;
 		break;
 	default:
 		BUG();
 	}

	sighand = parent->sighand;
	spin_lock_irqsave(&sighand->siglock, flags);
	if (sighand->action[SIGCHLD-1].sa.sa_handler != SIG_IGN &&
	    !(sighand->action[SIGCHLD-1].sa.sa_flags & SA_NOCLDSTOP))
		__group_send_sig_info(SIGCHLD, &info, parent);
	/*
	 * Even if SIGCHLD is not generated, we must wake up wait4 calls.
	 */
	__wake_up_parent(tsk, parent);
	spin_unlock_irqrestore(&sighand->siglock, flags);
}

1558 1559
static inline int may_ptrace_stop(void)
{
1560
	if (!likely(task_ptrace(current)))
1561 1562 1563 1564 1565 1566 1567
		return 0;
	/*
	 * Are we in the middle of do_coredump?
	 * If so and our tracer is also part of the coredump stopping
	 * is a deadlock situation, and pointless because our tracer
	 * is dead so don't allow us to stop.
	 * If SIGKILL was already sent before the caller unlocked
1568
	 * ->siglock we must see ->core_state != NULL. Otherwise it
1569 1570
	 * is safe to enter schedule().
	 */
1571
	if (unlikely(current->mm->core_state) &&
1572 1573 1574 1575 1576 1577
	    unlikely(current->mm == current->parent->mm))
		return 0;

	return 1;
}

R
Roland McGrath 已提交
1578 1579 1580 1581 1582 1583
/*
 * Return nonzero if there is a SIGKILL that should be waking us up.
 * Called with the siglock held.
 */
static int sigkill_pending(struct task_struct *tsk)
{
1584 1585
	return	sigismember(&tsk->pending.signal, SIGKILL) ||
		sigismember(&tsk->signal->shared_pending.signal, SIGKILL);
R
Roland McGrath 已提交
1586 1587
}

L
Linus Torvalds 已提交
1588 1589 1590 1591 1592 1593 1594 1595
/*
 * This must be called with current->sighand->siglock held.
 *
 * This should be the path for all ptrace stops.
 * We always set current->last_siginfo while stopped here.
 * That makes it a way to test a stopped process for
 * being ptrace-stopped vs being job-control-stopped.
 *
1596 1597
 * If we actually decide not to stop at all because the tracer
 * is gone, we keep current->exit_code unless clear_code.
L
Linus Torvalds 已提交
1598
 */
1599
static void ptrace_stop(int exit_code, int clear_code, siginfo_t *info)
L
Linus Torvalds 已提交
1600
{
R
Roland McGrath 已提交
1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615
	if (arch_ptrace_stop_needed(exit_code, info)) {
		/*
		 * The arch code has something special to do before a
		 * ptrace stop.  This is allowed to block, e.g. for faults
		 * on user stack pages.  We can't keep the siglock while
		 * calling arch_ptrace_stop, so we must release it now.
		 * To preserve proper semantics, we must do this before
		 * any signal bookkeeping like checking group_stop_count.
		 * Meanwhile, a SIGKILL could come in before we retake the
		 * siglock.  That must prevent us from sleeping in TASK_TRACED.
		 * So after regaining the lock, we must check for SIGKILL.
		 */
		spin_unlock_irq(&current->sighand->siglock);
		arch_ptrace_stop(exit_code, info);
		spin_lock_irq(&current->sighand->siglock);
1616 1617
		if (sigkill_pending(current))
			return;
R
Roland McGrath 已提交
1618 1619
	}

L
Linus Torvalds 已提交
1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630
	/*
	 * If there is a group stop in progress,
	 * we must participate in the bookkeeping.
	 */
	if (current->signal->group_stop_count > 0)
		--current->signal->group_stop_count;

	current->last_siginfo = info;
	current->exit_code = exit_code;

	/* Let the debugger run.  */
1631
	__set_current_state(TASK_TRACED);
L
Linus Torvalds 已提交
1632 1633
	spin_unlock_irq(&current->sighand->siglock);
	read_lock(&tasklist_lock);
1634
	if (may_ptrace_stop()) {
1635
		do_notify_parent_cldstop(current, CLD_TRAPPED);
M
Miklos Szeredi 已提交
1636 1637 1638 1639 1640 1641 1642
		/*
		 * Don't want to allow preemption here, because
		 * sys_ptrace() needs this task to be inactive.
		 *
		 * XXX: implement read_unlock_no_resched().
		 */
		preempt_disable();
L
Linus Torvalds 已提交
1643
		read_unlock(&tasklist_lock);
M
Miklos Szeredi 已提交
1644
		preempt_enable_no_resched();
L
Linus Torvalds 已提交
1645 1646 1647 1648
		schedule();
	} else {
		/*
		 * By the time we got the lock, our tracer went away.
1649
		 * Don't drop the lock yet, another tracer may come.
L
Linus Torvalds 已提交
1650
		 */
1651
		__set_current_state(TASK_RUNNING);
1652 1653
		if (clear_code)
			current->exit_code = 0;
1654
		read_unlock(&tasklist_lock);
L
Linus Torvalds 已提交
1655 1656
	}

R
Roland McGrath 已提交
1657 1658 1659 1660 1661 1662 1663
	/*
	 * While in TASK_TRACED, we were considered "frozen enough".
	 * Now that we woke up, it's crucial if we're supposed to be
	 * frozen that we freeze now before running anything substantial.
	 */
	try_to_freeze();

L
Linus Torvalds 已提交
1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674
	/*
	 * We are back.  Now reacquire the siglock before touching
	 * last_siginfo, so that we are sure to have synchronized with
	 * any signal-sending on another CPU that wants to examine it.
	 */
	spin_lock_irq(&current->sighand->siglock);
	current->last_siginfo = NULL;

	/*
	 * Queued signals ignored us while we were stopped for tracing.
	 * So check for any that we should take before resuming user mode.
1675
	 * This sets TIF_SIGPENDING, but never clears it.
L
Linus Torvalds 已提交
1676
	 */
1677
	recalc_sigpending_tsk(current);
L
Linus Torvalds 已提交
1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688
}

void ptrace_notify(int exit_code)
{
	siginfo_t info;

	BUG_ON((exit_code & (0x7f | ~0xffff)) != SIGTRAP);

	memset(&info, 0, sizeof info);
	info.si_signo = SIGTRAP;
	info.si_code = exit_code;
1689
	info.si_pid = task_pid_vnr(current);
1690
	info.si_uid = current_uid();
L
Linus Torvalds 已提交
1691 1692 1693

	/* Let the debugger run.  */
	spin_lock_irq(&current->sighand->siglock);
1694
	ptrace_stop(exit_code, 1, &info);
L
Linus Torvalds 已提交
1695 1696 1697 1698 1699 1700 1701 1702 1703
	spin_unlock_irq(&current->sighand->siglock);
}

/*
 * This performs the stopping for SIGSTOP and other stop signals.
 * We have to stop all threads in the thread group.
 * Returns nonzero if we've actually stopped and released the siglock.
 * Returns zero if we didn't stop and still hold the siglock.
 */
1704
static int do_signal_stop(int signr)
L
Linus Torvalds 已提交
1705 1706
{
	struct signal_struct *sig = current->signal;
1707
	int notify;
L
Linus Torvalds 已提交
1708

1709
	if (!sig->group_stop_count) {
1710 1711
		struct task_struct *t;

1712
		if (!likely(sig->flags & SIGNAL_STOP_DEQUEUED) ||
1713
		    unlikely(signal_group_exit(sig)))
1714
			return 0;
L
Linus Torvalds 已提交
1715 1716
		/*
		 * There is no group stop already in progress.
1717
		 * We must initiate one now.
L
Linus Torvalds 已提交
1718
		 */
1719
		sig->group_exit_code = signr;
L
Linus Torvalds 已提交
1720

1721
		sig->group_stop_count = 1;
1722
		for (t = next_thread(current); t != current; t = next_thread(t))
L
Linus Torvalds 已提交
1723
			/*
1724 1725 1726
			 * Setting state to TASK_STOPPED for a group
			 * stop is always done with the siglock held,
			 * so this check has no races.
L
Linus Torvalds 已提交
1727
			 */
O
Oleg Nesterov 已提交
1728
			if (!(t->flags & PF_EXITING) &&
M
Matthew Wilcox 已提交
1729
			    !task_is_stopped_or_traced(t)) {
1730
				sig->group_stop_count++;
1731 1732
				signal_wake_up(t, 0);
			}
L
Linus Torvalds 已提交
1733
	}
1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752
	/*
	 * If there are no other threads in the group, or if there is
	 * a group stop in progress and we are the last to stop, report
	 * to the parent.  When ptraced, every thread reports itself.
	 */
	notify = sig->group_stop_count == 1 ? CLD_STOPPED : 0;
	notify = tracehook_notify_jctl(notify, CLD_STOPPED);
	/*
	 * tracehook_notify_jctl() can drop and reacquire siglock, so
	 * we keep ->group_stop_count != 0 before the call. If SIGCONT
	 * or SIGKILL comes in between ->group_stop_count == 0.
	 */
	if (sig->group_stop_count) {
		if (!--sig->group_stop_count)
			sig->flags = SIGNAL_STOP_STOPPED;
		current->exit_code = sig->group_exit_code;
		__set_current_state(TASK_STOPPED);
	}
	spin_unlock_irq(&current->sighand->siglock);
L
Linus Torvalds 已提交
1753

1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766
	if (notify) {
		read_lock(&tasklist_lock);
		do_notify_parent_cldstop(current, notify);
		read_unlock(&tasklist_lock);
	}

	/* Now we don't run again until woken by SIGCONT or SIGKILL */
	do {
		schedule();
	} while (try_to_freeze());

	tracehook_finish_jctl();
	current->exit_code = 0;
1767

L
Linus Torvalds 已提交
1768 1769 1770
	return 1;
}

R
Roland McGrath 已提交
1771 1772 1773
static int ptrace_signal(int signr, siginfo_t *info,
			 struct pt_regs *regs, void *cookie)
{
1774
	if (!task_ptrace(current))
R
Roland McGrath 已提交
1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797
		return signr;

	ptrace_signal_deliver(regs, cookie);

	/* Let the debugger run.  */
	ptrace_stop(signr, 0, info);

	/* We're back.  Did the debugger cancel the sig?  */
	signr = current->exit_code;
	if (signr == 0)
		return signr;

	current->exit_code = 0;

	/* Update the siginfo structure if the signal has
	   changed.  If the debugger wanted something
	   specific in the siginfo structure then it should
	   have updated *info via PTRACE_SETSIGINFO.  */
	if (signr != info->si_signo) {
		info->si_signo = signr;
		info->si_errno = 0;
		info->si_code = SI_USER;
		info->si_pid = task_pid_vnr(current->parent);
1798
		info->si_uid = task_uid(current->parent);
R
Roland McGrath 已提交
1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809
	}

	/* If the (new) signal is now blocked, requeue it.  */
	if (sigismember(&current->blocked, signr)) {
		specific_send_sig_info(signr, info, current);
		signr = 0;
	}

	return signr;
}

L
Linus Torvalds 已提交
1810 1811 1812
int get_signal_to_deliver(siginfo_t *info, struct k_sigaction *return_ka,
			  struct pt_regs *regs, void *cookie)
{
1813 1814 1815
	struct sighand_struct *sighand = current->sighand;
	struct signal_struct *signal = current->signal;
	int signr;
L
Linus Torvalds 已提交
1816

R
Roland McGrath 已提交
1817 1818 1819 1820 1821 1822 1823
relock:
	/*
	 * We'll jump back here after any time we were stopped in TASK_STOPPED.
	 * While in TASK_STOPPED, we were considered "frozen enough".
	 * Now that we woke up, it's crucial if we're supposed to be
	 * frozen that we freeze now before running anything substantial.
	 */
1824 1825
	try_to_freeze();

1826
	spin_lock_irq(&sighand->siglock);
1827 1828 1829 1830 1831
	/*
	 * Every stopped thread goes here after wakeup. Check to see if
	 * we should notify the parent, prepare_signal(SIGCONT) encodes
	 * the CLD_ si_code into SIGNAL_CLD_MASK bits.
	 */
1832 1833
	if (unlikely(signal->flags & SIGNAL_CLD_MASK)) {
		int why = (signal->flags & SIGNAL_STOP_CONTINUED)
1834
				? CLD_CONTINUED : CLD_STOPPED;
1835
		signal->flags &= ~SIGNAL_CLD_MASK;
1836

1837 1838
		why = tracehook_notify_jctl(why, CLD_CONTINUED);
		spin_unlock_irq(&sighand->siglock);
R
Roland McGrath 已提交
1839

1840 1841 1842 1843 1844
		if (why) {
			read_lock(&tasklist_lock);
			do_notify_parent_cldstop(current->group_leader, why);
			read_unlock(&tasklist_lock);
		}
1845 1846 1847
		goto relock;
	}

L
Linus Torvalds 已提交
1848 1849 1850
	for (;;) {
		struct k_sigaction *ka;

1851
		if (unlikely(signal->group_stop_count > 0) &&
1852
		    do_signal_stop(0))
L
Linus Torvalds 已提交
1853 1854
			goto relock;

1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867
		/*
		 * Tracing can induce an artifical signal and choose sigaction.
		 * The return value in @signr determines the default action,
		 * but @info->si_signo is the signal number we will report.
		 */
		signr = tracehook_get_signal(current, regs, info, return_ka);
		if (unlikely(signr < 0))
			goto relock;
		if (unlikely(signr != 0))
			ka = return_ka;
		else {
			signr = dequeue_signal(current, &current->blocked,
					       info);
L
Linus Torvalds 已提交
1868

R
Roland McGrath 已提交
1869
			if (!signr)
1870 1871 1872 1873 1874 1875 1876 1877 1878 1879
				break; /* will return 0 */

			if (signr != SIGKILL) {
				signr = ptrace_signal(signr, info,
						      regs, cookie);
				if (!signr)
					continue;
			}

			ka = &sighand->action[signr-1];
L
Linus Torvalds 已提交
1880 1881
		}

1882 1883 1884
		/* Trace actually delivered signals. */
		trace_signal_deliver(signr, info, ka);

L
Linus Torvalds 已提交
1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902
		if (ka->sa.sa_handler == SIG_IGN) /* Do nothing.  */
			continue;
		if (ka->sa.sa_handler != SIG_DFL) {
			/* Run the handler.  */
			*return_ka = *ka;

			if (ka->sa.sa_flags & SA_ONESHOT)
				ka->sa.sa_handler = SIG_DFL;

			break; /* will return non-zero "signr" value */
		}

		/*
		 * Now we are doing the default action for this signal.
		 */
		if (sig_kernel_ignore(signr)) /* Default is nothing. */
			continue;

1903
		/*
1904
		 * Global init gets no signals it doesn't want.
1905 1906 1907 1908 1909 1910 1911
		 * Container-init gets no signals it doesn't want from same
		 * container.
		 *
		 * Note that if global/container-init sees a sig_kernel_only()
		 * signal here, the signal must have been generated internally
		 * or must have come from an ancestor namespace. In either
		 * case, the signal cannot be dropped.
1912
		 */
1913
		if (unlikely(signal->flags & SIGNAL_UNKILLABLE) &&
1914
				!sig_kernel_only(signr))
L
Linus Torvalds 已提交
1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928
			continue;

		if (sig_kernel_stop(signr)) {
			/*
			 * The default action is to stop all threads in
			 * the thread group.  The job control signals
			 * do nothing in an orphaned pgrp, but SIGSTOP
			 * always works.  Note that siglock needs to be
			 * dropped during the call to is_orphaned_pgrp()
			 * because of lock ordering with tasklist_lock.
			 * This allows an intervening SIGCONT to be posted.
			 * We need to check for that and bail out if necessary.
			 */
			if (signr != SIGSTOP) {
1929
				spin_unlock_irq(&sighand->siglock);
L
Linus Torvalds 已提交
1930 1931 1932

				/* signals can be posted during this window */

1933
				if (is_current_pgrp_orphaned())
L
Linus Torvalds 已提交
1934 1935
					goto relock;

1936
				spin_lock_irq(&sighand->siglock);
L
Linus Torvalds 已提交
1937 1938
			}

1939
			if (likely(do_signal_stop(info->si_signo))) {
L
Linus Torvalds 已提交
1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950
				/* It released the siglock.  */
				goto relock;
			}

			/*
			 * We didn't actually stop, due to a race
			 * with SIGCONT or something like that.
			 */
			continue;
		}

1951
		spin_unlock_irq(&sighand->siglock);
L
Linus Torvalds 已提交
1952 1953 1954 1955 1956

		/*
		 * Anything else is fatal, maybe with a core dump.
		 */
		current->flags |= PF_SIGNALED;
1957

L
Linus Torvalds 已提交
1958
		if (sig_kernel_coredump(signr)) {
1959
			if (print_fatal_signals)
1960
				print_fatal_signal(regs, info->si_signo);
L
Linus Torvalds 已提交
1961 1962 1963 1964 1965 1966 1967 1968
			/*
			 * If it was able to dump core, this kills all
			 * other threads in the group and synchronizes with
			 * their demise.  If we lost the race with another
			 * thread getting here, it set group_exit_code
			 * first and our do_group_exit call below will use
			 * that value and ignore the one we pass it.
			 */
1969
			do_coredump(info->si_signo, info->si_signo, regs);
L
Linus Torvalds 已提交
1970 1971 1972 1973 1974
		}

		/*
		 * Death signals, no core dump.
		 */
1975
		do_group_exit(info->si_signo);
L
Linus Torvalds 已提交
1976 1977
		/* NOTREACHED */
	}
1978
	spin_unlock_irq(&sighand->siglock);
L
Linus Torvalds 已提交
1979 1980 1981
	return signr;
}

O
Oleg Nesterov 已提交
1982 1983 1984
void exit_signals(struct task_struct *tsk)
{
	int group_stop = 0;
1985
	struct task_struct *t;
O
Oleg Nesterov 已提交
1986

1987 1988 1989
	if (thread_group_empty(tsk) || signal_group_exit(tsk->signal)) {
		tsk->flags |= PF_EXITING;
		return;
O
Oleg Nesterov 已提交
1990 1991
	}

1992
	spin_lock_irq(&tsk->sighand->siglock);
O
Oleg Nesterov 已提交
1993 1994 1995 1996 1997
	/*
	 * From now this task is not visible for group-wide signals,
	 * see wants_signal(), do_signal_stop().
	 */
	tsk->flags |= PF_EXITING;
1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011
	if (!signal_pending(tsk))
		goto out;

	/* It could be that __group_complete_signal() choose us to
	 * notify about group-wide signal. Another thread should be
	 * woken now to take the signal since we will not.
	 */
	for (t = tsk; (t = next_thread(t)) != tsk; )
		if (!signal_pending(t) && !(t->flags & PF_EXITING))
			recalc_sigpending_and_wake(t);

	if (unlikely(tsk->signal->group_stop_count) &&
			!--tsk->signal->group_stop_count) {
		tsk->signal->flags = SIGNAL_STOP_STOPPED;
2012
		group_stop = tracehook_notify_jctl(CLD_STOPPED, CLD_STOPPED);
2013 2014
	}
out:
O
Oleg Nesterov 已提交
2015 2016
	spin_unlock_irq(&tsk->sighand->siglock);

2017
	if (unlikely(group_stop)) {
O
Oleg Nesterov 已提交
2018
		read_lock(&tasklist_lock);
2019
		do_notify_parent_cldstop(tsk, group_stop);
O
Oleg Nesterov 已提交
2020 2021 2022 2023
		read_unlock(&tasklist_lock);
	}
}

L
Linus Torvalds 已提交
2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038
EXPORT_SYMBOL(recalc_sigpending);
EXPORT_SYMBOL_GPL(dequeue_signal);
EXPORT_SYMBOL(flush_signals);
EXPORT_SYMBOL(force_sig);
EXPORT_SYMBOL(send_sig);
EXPORT_SYMBOL(send_sig_info);
EXPORT_SYMBOL(sigprocmask);
EXPORT_SYMBOL(block_all_signals);
EXPORT_SYMBOL(unblock_all_signals);


/*
 * System call entry points.
 */

2039
SYSCALL_DEFINE0(restart_syscall)
L
Linus Torvalds 已提交
2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068
{
	struct restart_block *restart = &current_thread_info()->restart_block;
	return restart->fn(restart);
}

long do_no_restart_syscall(struct restart_block *param)
{
	return -EINTR;
}

/*
 * We don't need to get the kernel lock - this is all local to this
 * particular thread.. (and that's good, because this is _heavily_
 * used by various programs)
 */

/*
 * This is also useful for kernel threads that want to temporarily
 * (or permanently) block certain signals.
 *
 * NOTE! Unlike the user-mode sys_sigprocmask(), the kernel
 * interface happily blocks "unblockable" signals like SIGKILL
 * and friends.
 */
int sigprocmask(int how, sigset_t *set, sigset_t *oldset)
{
	int error;

	spin_lock_irq(&current->sighand->siglock);
2069 2070 2071
	if (oldset)
		*oldset = current->blocked;

L
Linus Torvalds 已提交
2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087
	error = 0;
	switch (how) {
	case SIG_BLOCK:
		sigorsets(&current->blocked, &current->blocked, set);
		break;
	case SIG_UNBLOCK:
		signandsets(&current->blocked, &current->blocked, set);
		break;
	case SIG_SETMASK:
		current->blocked = *set;
		break;
	default:
		error = -EINVAL;
	}
	recalc_sigpending();
	spin_unlock_irq(&current->sighand->siglock);
2088

L
Linus Torvalds 已提交
2089 2090 2091
	return error;
}

2092 2093
SYSCALL_DEFINE4(rt_sigprocmask, int, how, sigset_t __user *, set,
		sigset_t __user *, oset, size_t, sigsetsize)
L
Linus Torvalds 已提交
2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151
{
	int error = -EINVAL;
	sigset_t old_set, new_set;

	/* XXX: Don't preclude handling different sized sigset_t's.  */
	if (sigsetsize != sizeof(sigset_t))
		goto out;

	if (set) {
		error = -EFAULT;
		if (copy_from_user(&new_set, set, sizeof(*set)))
			goto out;
		sigdelsetmask(&new_set, sigmask(SIGKILL)|sigmask(SIGSTOP));

		error = sigprocmask(how, &new_set, &old_set);
		if (error)
			goto out;
		if (oset)
			goto set_old;
	} else if (oset) {
		spin_lock_irq(&current->sighand->siglock);
		old_set = current->blocked;
		spin_unlock_irq(&current->sighand->siglock);

	set_old:
		error = -EFAULT;
		if (copy_to_user(oset, &old_set, sizeof(*oset)))
			goto out;
	}
	error = 0;
out:
	return error;
}

long do_sigpending(void __user *set, unsigned long sigsetsize)
{
	long error = -EINVAL;
	sigset_t pending;

	if (sigsetsize > sizeof(sigset_t))
		goto out;

	spin_lock_irq(&current->sighand->siglock);
	sigorsets(&pending, &current->pending.signal,
		  &current->signal->shared_pending.signal);
	spin_unlock_irq(&current->sighand->siglock);

	/* Outside the lock because only this thread touches it.  */
	sigandsets(&pending, &current->blocked, &pending);

	error = -EFAULT;
	if (!copy_to_user(set, &pending, sigsetsize))
		error = 0;

out:
	return error;
}	

2152
SYSCALL_DEFINE2(rt_sigpending, sigset_t __user *, set, size_t, sigsetsize)
L
Linus Torvalds 已提交
2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170
{
	return do_sigpending(set, sigsetsize);
}

#ifndef HAVE_ARCH_COPY_SIGINFO_TO_USER

int copy_siginfo_to_user(siginfo_t __user *to, siginfo_t *from)
{
	int err;

	if (!access_ok (VERIFY_WRITE, to, sizeof(siginfo_t)))
		return -EFAULT;
	if (from->si_code < 0)
		return __copy_to_user(to, from, sizeof(siginfo_t))
			? -EFAULT : 0;
	/*
	 * If you change siginfo_t structure, please be sure
	 * this code is fixed accordingly.
2171 2172
	 * Please remember to update the signalfd_copyinfo() function
	 * inside fs/signalfd.c too, in case siginfo_t changes.
L
Linus Torvalds 已提交
2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222
	 * It should never copy any pad contained in the structure
	 * to avoid security leaks, but must copy the generic
	 * 3 ints plus the relevant union member.
	 */
	err = __put_user(from->si_signo, &to->si_signo);
	err |= __put_user(from->si_errno, &to->si_errno);
	err |= __put_user((short)from->si_code, &to->si_code);
	switch (from->si_code & __SI_MASK) {
	case __SI_KILL:
		err |= __put_user(from->si_pid, &to->si_pid);
		err |= __put_user(from->si_uid, &to->si_uid);
		break;
	case __SI_TIMER:
		 err |= __put_user(from->si_tid, &to->si_tid);
		 err |= __put_user(from->si_overrun, &to->si_overrun);
		 err |= __put_user(from->si_ptr, &to->si_ptr);
		break;
	case __SI_POLL:
		err |= __put_user(from->si_band, &to->si_band);
		err |= __put_user(from->si_fd, &to->si_fd);
		break;
	case __SI_FAULT:
		err |= __put_user(from->si_addr, &to->si_addr);
#ifdef __ARCH_SI_TRAPNO
		err |= __put_user(from->si_trapno, &to->si_trapno);
#endif
		break;
	case __SI_CHLD:
		err |= __put_user(from->si_pid, &to->si_pid);
		err |= __put_user(from->si_uid, &to->si_uid);
		err |= __put_user(from->si_status, &to->si_status);
		err |= __put_user(from->si_utime, &to->si_utime);
		err |= __put_user(from->si_stime, &to->si_stime);
		break;
	case __SI_RT: /* This is not generated by the kernel as of now. */
	case __SI_MESGQ: /* But this is */
		err |= __put_user(from->si_pid, &to->si_pid);
		err |= __put_user(from->si_uid, &to->si_uid);
		err |= __put_user(from->si_ptr, &to->si_ptr);
		break;
	default: /* this is just in case for now ... */
		err |= __put_user(from->si_pid, &to->si_pid);
		err |= __put_user(from->si_uid, &to->si_uid);
		break;
	}
	return err;
}

#endif

2223 2224 2225
SYSCALL_DEFINE4(rt_sigtimedwait, const sigset_t __user *, uthese,
		siginfo_t __user *, uinfo, const struct timespec __user *, uts,
		size_t, sigsetsize)
L
Linus Torvalds 已提交
2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271
{
	int ret, sig;
	sigset_t these;
	struct timespec ts;
	siginfo_t info;
	long timeout = 0;

	/* XXX: Don't preclude handling different sized sigset_t's.  */
	if (sigsetsize != sizeof(sigset_t))
		return -EINVAL;

	if (copy_from_user(&these, uthese, sizeof(these)))
		return -EFAULT;
		
	/*
	 * Invert the set of allowed signals to get those we
	 * want to block.
	 */
	sigdelsetmask(&these, sigmask(SIGKILL)|sigmask(SIGSTOP));
	signotset(&these);

	if (uts) {
		if (copy_from_user(&ts, uts, sizeof(ts)))
			return -EFAULT;
		if (ts.tv_nsec >= 1000000000L || ts.tv_nsec < 0
		    || ts.tv_sec < 0)
			return -EINVAL;
	}

	spin_lock_irq(&current->sighand->siglock);
	sig = dequeue_signal(current, &these, &info);
	if (!sig) {
		timeout = MAX_SCHEDULE_TIMEOUT;
		if (uts)
			timeout = (timespec_to_jiffies(&ts)
				   + (ts.tv_sec || ts.tv_nsec));

		if (timeout) {
			/* None ready -- temporarily unblock those we're
			 * interested while we are sleeping in so that we'll
			 * be awakened when they arrive.  */
			current->real_blocked = current->blocked;
			sigandsets(&current->blocked, &current->blocked, &these);
			recalc_sigpending();
			spin_unlock_irq(&current->sighand->siglock);

2272
			timeout = schedule_timeout_interruptible(timeout);
L
Linus Torvalds 已提交
2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297

			spin_lock_irq(&current->sighand->siglock);
			sig = dequeue_signal(current, &these, &info);
			current->blocked = current->real_blocked;
			siginitset(&current->real_blocked, 0);
			recalc_sigpending();
		}
	}
	spin_unlock_irq(&current->sighand->siglock);

	if (sig) {
		ret = sig;
		if (uinfo) {
			if (copy_siginfo_to_user(uinfo, &info))
				ret = -EFAULT;
		}
	} else {
		ret = -EAGAIN;
		if (timeout)
			ret = -EINTR;
	}

	return ret;
}

2298
SYSCALL_DEFINE2(kill, pid_t, pid, int, sig)
L
Linus Torvalds 已提交
2299 2300 2301 2302 2303 2304
{
	struct siginfo info;

	info.si_signo = sig;
	info.si_errno = 0;
	info.si_code = SI_USER;
2305
	info.si_pid = task_tgid_vnr(current);
2306
	info.si_uid = current_uid();
L
Linus Torvalds 已提交
2307 2308 2309 2310

	return kill_something_info(sig, &info, pid);
}

T
Thomas Gleixner 已提交
2311 2312
static int
do_send_specific(pid_t tgid, pid_t pid, int sig, struct siginfo *info)
L
Linus Torvalds 已提交
2313 2314
{
	struct task_struct *p;
T
Thomas Gleixner 已提交
2315
	int error = -ESRCH;
L
Linus Torvalds 已提交
2316

2317
	rcu_read_lock();
2318
	p = find_task_by_vpid(pid);
2319
	if (p && (tgid <= 0 || task_tgid_vnr(p) == tgid)) {
T
Thomas Gleixner 已提交
2320
		error = check_kill_permission(sig, info, p);
L
Linus Torvalds 已提交
2321 2322 2323 2324
		/*
		 * The null signal is a permissions and process existence
		 * probe.  No signal is actually delivered.
		 */
2325 2326 2327 2328 2329 2330 2331 2332 2333
		if (!error && sig) {
			error = do_send_sig_info(sig, info, p, false);
			/*
			 * If lock_task_sighand() failed we pretend the task
			 * dies after receiving the signal. The window is tiny,
			 * and the signal is private anyway.
			 */
			if (unlikely(error == -ESRCH))
				error = 0;
L
Linus Torvalds 已提交
2334 2335
		}
	}
2336
	rcu_read_unlock();
2337

L
Linus Torvalds 已提交
2338 2339 2340
	return error;
}

T
Thomas Gleixner 已提交
2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353
static int do_tkill(pid_t tgid, pid_t pid, int sig)
{
	struct siginfo info;

	info.si_signo = sig;
	info.si_errno = 0;
	info.si_code = SI_TKILL;
	info.si_pid = task_tgid_vnr(current);
	info.si_uid = current_uid();

	return do_send_specific(tgid, pid, sig, &info);
}

2354 2355 2356 2357 2358 2359
/**
 *  sys_tgkill - send signal to one specific thread
 *  @tgid: the thread group ID of the thread
 *  @pid: the PID of the thread
 *  @sig: signal to be sent
 *
2360
 *  This syscall also checks the @tgid and returns -ESRCH even if the PID
2361 2362 2363
 *  exists but it's not belonging to the target process anymore. This
 *  method solves the problem of threads exiting and PIDs getting reused.
 */
2364
SYSCALL_DEFINE3(tgkill, pid_t, tgid, pid_t, pid, int, sig)
2365 2366 2367 2368 2369 2370 2371 2372
{
	/* This is only valid for single tasks */
	if (pid <= 0 || tgid <= 0)
		return -EINVAL;

	return do_tkill(tgid, pid, sig);
}

L
Linus Torvalds 已提交
2373 2374 2375
/*
 *  Send a signal to only one task, even if it's a CLONE_THREAD task.
 */
2376
SYSCALL_DEFINE2(tkill, pid_t, pid, int, sig)
L
Linus Torvalds 已提交
2377 2378 2379 2380 2381
{
	/* This is only valid for single tasks */
	if (pid <= 0)
		return -EINVAL;

2382
	return do_tkill(0, pid, sig);
L
Linus Torvalds 已提交
2383 2384
}

2385 2386
SYSCALL_DEFINE3(rt_sigqueueinfo, pid_t, pid, int, sig,
		siginfo_t __user *, uinfo)
L
Linus Torvalds 已提交
2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402
{
	siginfo_t info;

	if (copy_from_user(&info, uinfo, sizeof(siginfo_t)))
		return -EFAULT;

	/* Not even root can pretend to send signals from the kernel.
	   Nor can they impersonate a kill(), which adds source info.  */
	if (info.si_code >= 0)
		return -EPERM;
	info.si_signo = sig;

	/* POSIX.1b doesn't mention process groups.  */
	return kill_proc_info(sig, &info, pid);
}

2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428
long do_rt_tgsigqueueinfo(pid_t tgid, pid_t pid, int sig, siginfo_t *info)
{
	/* This is only valid for single tasks */
	if (pid <= 0 || tgid <= 0)
		return -EINVAL;

	/* Not even root can pretend to send signals from the kernel.
	   Nor can they impersonate a kill(), which adds source info.  */
	if (info->si_code >= 0)
		return -EPERM;
	info->si_signo = sig;

	return do_send_specific(tgid, pid, sig, info);
}

SYSCALL_DEFINE4(rt_tgsigqueueinfo, pid_t, tgid, pid_t, pid, int, sig,
		siginfo_t __user *, uinfo)
{
	siginfo_t info;

	if (copy_from_user(&info, uinfo, sizeof(siginfo_t)))
		return -EFAULT;

	return do_rt_tgsigqueueinfo(tgid, pid, sig, &info);
}

2429
int do_sigaction(int sig, struct k_sigaction *act, struct k_sigaction *oact)
L
Linus Torvalds 已提交
2430
{
2431
	struct task_struct *t = current;
L
Linus Torvalds 已提交
2432
	struct k_sigaction *k;
2433
	sigset_t mask;
L
Linus Torvalds 已提交
2434

2435
	if (!valid_signal(sig) || sig < 1 || (act && sig_kernel_only(sig)))
L
Linus Torvalds 已提交
2436 2437
		return -EINVAL;

2438
	k = &t->sighand->action[sig-1];
L
Linus Torvalds 已提交
2439 2440 2441 2442 2443 2444

	spin_lock_irq(&current->sighand->siglock);
	if (oact)
		*oact = *k;

	if (act) {
2445 2446
		sigdelsetmask(&act->sa.sa_mask,
			      sigmask(SIGKILL) | sigmask(SIGSTOP));
2447
		*k = *act;
L
Linus Torvalds 已提交
2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458
		/*
		 * POSIX 3.3.1.3:
		 *  "Setting a signal action to SIG_IGN for a signal that is
		 *   pending shall cause the pending signal to be discarded,
		 *   whether or not it is blocked."
		 *
		 *  "Setting a signal action to SIG_DFL for a signal that is
		 *   pending and whose default action is to ignore the signal
		 *   (for example, SIGCHLD), shall cause the pending signal to
		 *   be discarded, whether or not it is blocked"
		 */
2459
		if (sig_handler_ignored(sig_handler(t, sig), sig)) {
2460 2461 2462
			sigemptyset(&mask);
			sigaddset(&mask, sig);
			rm_from_queue_full(&mask, &t->signal->shared_pending);
L
Linus Torvalds 已提交
2463
			do {
2464
				rm_from_queue_full(&mask, &t->pending);
L
Linus Torvalds 已提交
2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479
				t = next_thread(t);
			} while (t != current);
		}
	}

	spin_unlock_irq(&current->sighand->siglock);
	return 0;
}

int 
do_sigaltstack (const stack_t __user *uss, stack_t __user *uoss, unsigned long sp)
{
	stack_t oss;
	int error;

2480 2481 2482
	oss.ss_sp = (void __user *) current->sas_ss_sp;
	oss.ss_size = current->sas_ss_size;
	oss.ss_flags = sas_ss_flags(sp);
L
Linus Torvalds 已提交
2483 2484 2485 2486 2487 2488 2489

	if (uss) {
		void __user *ss_sp;
		size_t ss_size;
		int ss_flags;

		error = -EFAULT;
L
Linus Torvalds 已提交
2490 2491 2492 2493 2494 2495
		if (!access_ok(VERIFY_READ, uss, sizeof(*uss)))
			goto out;
		error = __get_user(ss_sp, &uss->ss_sp) |
			__get_user(ss_flags, &uss->ss_flags) |
			__get_user(ss_size, &uss->ss_size);
		if (error)
L
Linus Torvalds 已提交
2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526
			goto out;

		error = -EPERM;
		if (on_sig_stack(sp))
			goto out;

		error = -EINVAL;
		/*
		 *
		 * Note - this code used to test ss_flags incorrectly
		 *  	  old code may have been written using ss_flags==0
		 *	  to mean ss_flags==SS_ONSTACK (as this was the only
		 *	  way that worked) - this fix preserves that older
		 *	  mechanism
		 */
		if (ss_flags != SS_DISABLE && ss_flags != SS_ONSTACK && ss_flags != 0)
			goto out;

		if (ss_flags == SS_DISABLE) {
			ss_size = 0;
			ss_sp = NULL;
		} else {
			error = -ENOMEM;
			if (ss_size < MINSIGSTKSZ)
				goto out;
		}

		current->sas_ss_sp = (unsigned long) ss_sp;
		current->sas_ss_size = ss_size;
	}

2527
	error = 0;
L
Linus Torvalds 已提交
2528 2529
	if (uoss) {
		error = -EFAULT;
2530
		if (!access_ok(VERIFY_WRITE, uoss, sizeof(*uoss)))
L
Linus Torvalds 已提交
2531
			goto out;
2532 2533 2534
		error = __put_user(oss.ss_sp, &uoss->ss_sp) |
			__put_user(oss.ss_size, &uoss->ss_size) |
			__put_user(oss.ss_flags, &uoss->ss_flags);
L
Linus Torvalds 已提交
2535 2536 2537 2538 2539 2540 2541 2542
	}

out:
	return error;
}

#ifdef __ARCH_WANT_SYS_SIGPENDING

2543
SYSCALL_DEFINE1(sigpending, old_sigset_t __user *, set)
L
Linus Torvalds 已提交
2544 2545 2546 2547 2548 2549 2550 2551 2552 2553
{
	return do_sigpending(set, sizeof(*set));
}

#endif

#ifdef __ARCH_WANT_SYS_SIGPROCMASK
/* Some platforms have their own version with special arguments others
   support only sys_rt_sigprocmask.  */

2554 2555
SYSCALL_DEFINE3(sigprocmask, int, how, old_sigset_t __user *, set,
		old_sigset_t __user *, oset)
L
Linus Torvalds 已提交
2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604
{
	int error;
	old_sigset_t old_set, new_set;

	if (set) {
		error = -EFAULT;
		if (copy_from_user(&new_set, set, sizeof(*set)))
			goto out;
		new_set &= ~(sigmask(SIGKILL) | sigmask(SIGSTOP));

		spin_lock_irq(&current->sighand->siglock);
		old_set = current->blocked.sig[0];

		error = 0;
		switch (how) {
		default:
			error = -EINVAL;
			break;
		case SIG_BLOCK:
			sigaddsetmask(&current->blocked, new_set);
			break;
		case SIG_UNBLOCK:
			sigdelsetmask(&current->blocked, new_set);
			break;
		case SIG_SETMASK:
			current->blocked.sig[0] = new_set;
			break;
		}

		recalc_sigpending();
		spin_unlock_irq(&current->sighand->siglock);
		if (error)
			goto out;
		if (oset)
			goto set_old;
	} else if (oset) {
		old_set = current->blocked.sig[0];
	set_old:
		error = -EFAULT;
		if (copy_to_user(oset, &old_set, sizeof(*oset)))
			goto out;
	}
	error = 0;
out:
	return error;
}
#endif /* __ARCH_WANT_SYS_SIGPROCMASK */

#ifdef __ARCH_WANT_SYS_RT_SIGACTION
2605 2606 2607 2608
SYSCALL_DEFINE4(rt_sigaction, int, sig,
		const struct sigaction __user *, act,
		struct sigaction __user *, oact,
		size_t, sigsetsize)
L
Linus Torvalds 已提交
2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637
{
	struct k_sigaction new_sa, old_sa;
	int ret = -EINVAL;

	/* XXX: Don't preclude handling different sized sigset_t's.  */
	if (sigsetsize != sizeof(sigset_t))
		goto out;

	if (act) {
		if (copy_from_user(&new_sa.sa, act, sizeof(new_sa.sa)))
			return -EFAULT;
	}

	ret = do_sigaction(sig, act ? &new_sa : NULL, oact ? &old_sa : NULL);

	if (!ret && oact) {
		if (copy_to_user(oact, &old_sa.sa, sizeof(old_sa.sa)))
			return -EFAULT;
	}
out:
	return ret;
}
#endif /* __ARCH_WANT_SYS_RT_SIGACTION */

#ifdef __ARCH_WANT_SYS_SGETMASK

/*
 * For backwards compatibility.  Functionality superseded by sigprocmask.
 */
2638
SYSCALL_DEFINE0(sgetmask)
L
Linus Torvalds 已提交
2639 2640 2641 2642 2643
{
	/* SMP safe */
	return current->blocked.sig[0];
}

2644
SYSCALL_DEFINE1(ssetmask, int, newmask)
L
Linus Torvalds 已提交
2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663
{
	int old;

	spin_lock_irq(&current->sighand->siglock);
	old = current->blocked.sig[0];

	siginitset(&current->blocked, newmask & ~(sigmask(SIGKILL)|
						  sigmask(SIGSTOP)));
	recalc_sigpending();
	spin_unlock_irq(&current->sighand->siglock);

	return old;
}
#endif /* __ARCH_WANT_SGETMASK */

#ifdef __ARCH_WANT_SYS_SIGNAL
/*
 * For backwards compatibility.  Functionality superseded by sigaction.
 */
2664
SYSCALL_DEFINE2(signal, int, sig, __sighandler_t, handler)
L
Linus Torvalds 已提交
2665 2666 2667 2668 2669 2670
{
	struct k_sigaction new_sa, old_sa;
	int ret;

	new_sa.sa.sa_handler = handler;
	new_sa.sa.sa_flags = SA_ONESHOT | SA_NOMASK;
2671
	sigemptyset(&new_sa.sa.sa_mask);
L
Linus Torvalds 已提交
2672 2673 2674 2675 2676 2677 2678 2679 2680

	ret = do_sigaction(sig, &new_sa, &old_sa);

	return ret ? ret : (unsigned long)old_sa.sa.sa_handler;
}
#endif /* __ARCH_WANT_SYS_SIGNAL */

#ifdef __ARCH_WANT_SYS_PAUSE

2681
SYSCALL_DEFINE0(pause)
L
Linus Torvalds 已提交
2682 2683 2684 2685 2686 2687 2688 2689
{
	current->state = TASK_INTERRUPTIBLE;
	schedule();
	return -ERESTARTNOHAND;
}

#endif

2690
#ifdef __ARCH_WANT_SYS_RT_SIGSUSPEND
2691
SYSCALL_DEFINE2(rt_sigsuspend, sigset_t __user *, unewset, size_t, sigsetsize)
2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710
{
	sigset_t newset;

	/* XXX: Don't preclude handling different sized sigset_t's.  */
	if (sigsetsize != sizeof(sigset_t))
		return -EINVAL;

	if (copy_from_user(&newset, unewset, sizeof(newset)))
		return -EFAULT;
	sigdelsetmask(&newset, sigmask(SIGKILL)|sigmask(SIGSTOP));

	spin_lock_irq(&current->sighand->siglock);
	current->saved_sigmask = current->blocked;
	current->blocked = newset;
	recalc_sigpending();
	spin_unlock_irq(&current->sighand->siglock);

	current->state = TASK_INTERRUPTIBLE;
	schedule();
2711
	set_restore_sigmask();
2712 2713 2714 2715
	return -ERESTARTNOHAND;
}
#endif /* __ARCH_WANT_SYS_RT_SIGSUSPEND */

2716 2717 2718 2719 2720
__attribute__((weak)) const char *arch_vma_name(struct vm_area_struct *vma)
{
	return NULL;
}

L
Linus Torvalds 已提交
2721 2722
void __init signals_init(void)
{
2723
	sigqueue_cachep = KMEM_CACHE(sigqueue, SLAB_PANIC);
L
Linus Torvalds 已提交
2724
}