signal.c 63.7 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/capability.h>
26
#include <linux/freezer.h>
27 28 29
#include <linux/pid_namespace.h>
#include <linux/nsproxy.h>

L
Linus Torvalds 已提交
30 31 32 33
#include <asm/param.h>
#include <asm/uaccess.h>
#include <asm/unistd.h>
#include <asm/siginfo.h>
34
#include "audit.h"	/* audit_signal_info() */
L
Linus Torvalds 已提交
35 36 37 38 39

/*
 * SLAB caches for signal bits.
 */

40
static struct kmem_cache *sigqueue_cachep;
L
Linus Torvalds 已提交
41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98


static int sig_ignored(struct task_struct *t, int sig)
{
	void __user * handler;

	/*
	 * Tracers always want to know about signals..
	 */
	if (t->ptrace & PT_PTRACED)
		return 0;

	/*
	 * Blocked signals are never ignored, since the
	 * signal handler may change by the time it is
	 * unblocked.
	 */
	if (sigismember(&t->blocked, sig))
		return 0;

	/* Is it explicitly or implicitly ignored? */
	handler = t->sighand->action[sig-1].sa.sa_handler;
	return   handler == SIG_IGN ||
		(handler == SIG_DFL && sig_kernel_ignore(sig));
}

/*
 * 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
99
static int recalc_sigpending_tsk(struct task_struct *t)
L
Linus Torvalds 已提交
100 101
{
	if (t->signal->group_stop_count > 0 ||
102
	    (freezing(t)) ||
L
Linus Torvalds 已提交
103
	    PENDING(&t->pending, &t->blocked) ||
R
Roland McGrath 已提交
104
	    PENDING(&t->signal->shared_pending, &t->blocked)) {
L
Linus Torvalds 已提交
105
		set_tsk_thread_flag(t, TIF_SIGPENDING);
R
Roland McGrath 已提交
106 107
		return 1;
	}
108 109 110 111 112
	/*
	 * 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
113 114 115 116 117 118 119 120 121 122 123
	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
124 125 126 127
}

void recalc_sigpending(void)
{
128 129 130
	if (!recalc_sigpending_tsk(current))
		clear_thread_flag(TIF_SIGPENDING);

L
Linus Torvalds 已提交
131 132 133 134
}

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

135
int next_signal(struct sigpending *pending, sigset_t *mask)
L
Linus Torvalds 已提交
136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167
{
	unsigned long i, *s, *m, x;
	int sig = 0;
	
	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;
	}
	
	return sig;
}

A
Al Viro 已提交
168
static struct sigqueue *__sigqueue_alloc(struct task_struct *t, gfp_t flags,
L
Linus Torvalds 已提交
169 170 171
					 int override_rlimit)
{
	struct sigqueue *q = NULL;
172
	struct user_struct *user;
L
Linus Torvalds 已提交
173

174 175 176 177 178 179 180
	/*
	 * In order to avoid problems with "switch_user()", we want to make
	 * sure that the compiler doesn't re-load "t->user"
	 */
	user = t->user;
	barrier();
	atomic_inc(&user->sigpending);
L
Linus Torvalds 已提交
181
	if (override_rlimit ||
182
	    atomic_read(&user->sigpending) <=
L
Linus Torvalds 已提交
183 184 185
			t->signal->rlim[RLIMIT_SIGPENDING].rlim_cur)
		q = kmem_cache_alloc(sigqueue_cachep, flags);
	if (unlikely(q == NULL)) {
186
		atomic_dec(&user->sigpending);
L
Linus Torvalds 已提交
187 188 189
	} else {
		INIT_LIST_HEAD(&q->list);
		q->flags = 0;
190
		q->user = get_uid(user);
L
Linus Torvalds 已提交
191 192 193 194
	}
	return(q);
}

195
static void __sigqueue_free(struct sigqueue *q)
L
Linus Torvalds 已提交
196 197 198 199 200 201 202 203
{
	if (q->flags & SIGQUEUE_PREALLOC)
		return;
	atomic_dec(&q->user->sigpending);
	free_uid(q->user);
	kmem_cache_free(sigqueue_cachep, q);
}

204
void flush_sigqueue(struct sigpending *queue)
L
Linus Torvalds 已提交
205 206 207 208 209 210 211 212 213 214 215 216 217 218
{
	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.
 */
219
void flush_signals(struct task_struct *t)
L
Linus Torvalds 已提交
220 221 222 223 224 225 226 227 228 229
{
	unsigned long flags;

	spin_lock_irqsave(&t->sighand->siglock, flags);
	clear_tsk_thread_flag(t,TIF_SIGPENDING);
	flush_sigqueue(&t->pending);
	flush_sigqueue(&t->signal->shared_pending);
	spin_unlock_irqrestore(&t->sighand->siglock, flags);
}

230 231 232 233 234 235 236 237 238 239
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
240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292
/*
 * 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++;
	}
}


/* 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);
}

293
static int collect_signal(int sig, struct sigpending *list, siginfo_t *info)
L
Linus Torvalds 已提交
294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338
{
	struct sigqueue *q, *first = NULL;
	int still_pending = 0;

	if (unlikely(!sigismember(&list->signal, sig)))
		return 0;

	/*
	 * 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) {
			if (first) {
				still_pending = 1;
				break;
			}
			first = q;
		}
	}
	if (first) {
		list_del_init(&first->list);
		copy_siginfo(info, &first->info);
		__sigqueue_free(first);
		if (!still_pending)
			sigdelset(&list->signal, sig);
	} 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.
		 */
		sigdelset(&list->signal, sig);
		info->si_signo = sig;
		info->si_errno = 0;
		info->si_code = 0;
		info->si_pid = 0;
		info->si_uid = 0;
	}
	return 1;
}

static int __dequeue_signal(struct sigpending *pending, sigset_t *mask,
			siginfo_t *info)
{
339
	int sig = next_signal(pending, mask);
L
Linus Torvalds 已提交
340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365

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

		if (!collect_signal(sig, pending, info))
			sig = 0;
	}

	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)
{
366 367 368 369 370 371 372
	int signr = 0;

	/* We only dequeue private signals from ourselves, we don't let
	 * signalfd steal them
	 */
	if (tsk == current)
		signr = __dequeue_signal(&tsk->pending, mask, info);
373
	if (!signr) {
L
Linus Torvalds 已提交
374 375
		signr = __dequeue_signal(&tsk->signal->shared_pending,
					 mask, info);
376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399
		/*
		 * 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);
			}
		}
	}
400 401
	if (likely(tsk == current))
		recalc_sigpending();
402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417
	if (signr && unlikely(sig_kernel_stop(signr))) {
		/*
		 * 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.
		 */
		if (!(tsk->signal->flags & SIGNAL_GROUP_EXIT))
			tsk->signal->flags |= SIGNAL_STOP_DEQUEUED;
	}
L
Linus Torvalds 已提交
418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464
	if ( signr &&
	     ((info->si_code & __SI_MASK) == __SI_TIMER) &&
	     info->si_sys_private){
		/*
		 * 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);

	/*
	 * For SIGKILL, we want to wake it up in the stopped/traced case.
	 * We don't check t->state here because there is a race with it
	 * 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)
		mask |= TASK_STOPPED | TASK_TRACED;
	if (!wake_up_state(t, mask))
		kick_process(t);
}

465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491
/*
 * 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
492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522
/*
 * 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;
}

/*
 * Bad permissions for sending the signal
 */
static int check_kill_permission(int sig, struct siginfo *info,
				 struct task_struct *t)
{
	int error = -EINVAL;
523
	if (!valid_signal(sig))
L
Linus Torvalds 已提交
524
		return error;
A
Amy Griffis 已提交
525 526 527 528 529

	error = audit_signal_info(sig, t); /* Let audit system see the signal */
	if (error)
		return error;

L
Linus Torvalds 已提交
530
	error = -EPERM;
531
	if ((info == SEND_SIG_NOINFO || (!is_si_special(info) && SI_FROMUSER(info)))
L
Linus Torvalds 已提交
532
	    && ((sig != SIGCONT) ||
533
		(process_session(current) != process_session(t)))
L
Linus Torvalds 已提交
534 535 536 537
	    && (current->euid ^ t->suid) && (current->euid ^ t->uid)
	    && (current->uid ^ t->suid) && (current->uid ^ t->uid)
	    && !capable(CAP_KILL))
		return error;
538

A
Amy Griffis 已提交
539
	return security_task_kill(t, info, sig, 0);
L
Linus Torvalds 已提交
540 541 542
}

/* forward decl */
543
static void do_notify_parent_cldstop(struct task_struct *tsk, int why);
L
Linus Torvalds 已提交
544 545 546 547 548 549 550 551 552 553 554 555

/*
 * Handle magic process-wide effects of stop/continue signals.
 * Unlike the signal actions, these happen immediately at signal-generation
 * time regardless of blocking, ignoring, or handling.  This does the
 * actual continuing for SIGCONT, but not the actual stopping for stop
 * signals.  The process stop is done as a signal action for SIG_DFL.
 */
static void handle_stop_signal(int sig, struct task_struct *p)
{
	struct task_struct *t;

556
	if (p->signal->flags & SIGNAL_GROUP_EXIT)
L
Linus Torvalds 已提交
557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592
		/*
		 * The process is in the middle of dying already.
		 */
		return;

	if (sig_kernel_stop(sig)) {
		/*
		 * This is a stop signal.  Remove SIGCONT from all queues.
		 */
		rm_from_queue(sigmask(SIGCONT), &p->signal->shared_pending);
		t = p;
		do {
			rm_from_queue(sigmask(SIGCONT), &t->pending);
			t = next_thread(t);
		} while (t != p);
	} else if (sig == SIGCONT) {
		/*
		 * Remove all stop signals from all queues,
		 * and wake all threads.
		 */
		if (unlikely(p->signal->group_stop_count > 0)) {
			/*
			 * There was a group stop in progress.  We'll
			 * pretend it finished before we got here.  We are
			 * obliged to report it to the parent: if the
			 * SIGSTOP happened "after" this SIGCONT, then it
			 * would have cleared this pending SIGCONT.  If it
			 * happened "before" this SIGCONT, then the parent
			 * got the SIGCHLD about the stop finishing before
			 * the continue happened.  We do the notification
			 * now, and it's as if the stop had finished and
			 * the SIGCHLD was pending on entry to this kill.
			 */
			p->signal->group_stop_count = 0;
			p->signal->flags = SIGNAL_STOP_CONTINUED;
			spin_unlock(&p->sighand->siglock);
593
			do_notify_parent_cldstop(p, CLD_STOPPED);
L
Linus Torvalds 已提交
594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633
			spin_lock(&p->sighand->siglock);
		}
		rm_from_queue(SIG_KERNEL_STOP_MASK, &p->signal->shared_pending);
		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
			 * the pending signal. 
			 *
			 * Wake up the stopped thread _after_ setting
			 * TIF_SIGPENDING
			 */
			state = TASK_STOPPED;
			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);

			t = next_thread(t);
		} while (t != p);

		if (p->signal->flags & SIGNAL_STOP_STOPPED) {
			/*
			 * We were in fact stopped, and are now continued.
			 * Notify the parent with CLD_CONTINUED.
			 */
			p->signal->flags = SIGNAL_STOP_CONTINUED;
			p->signal->group_exit_code = 0;
			spin_unlock(&p->sighand->siglock);
634
			do_notify_parent_cldstop(p, CLD_CONTINUED);
L
Linus Torvalds 已提交
635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658
			spin_lock(&p->sighand->siglock);
		} 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.
			 */
			p->signal->flags = 0;
		}
	} else if (sig == SIGKILL) {
		/*
		 * Make sure that any pending stop signal already dequeued
		 * is undone by the wakeup for SIGKILL.
		 */
		p->signal->flags = 0;
	}
}

static int send_signal(int sig, struct siginfo *info, struct task_struct *t,
			struct sigpending *signals)
{
	struct sigqueue * q = NULL;
	int ret = 0;

659 660 661 662 663 664
	/*
	 * Deliver the signal to listening signalfds. This must be called
	 * with the sighand lock held.
	 */
	signalfd_notify(t, sig);

L
Linus Torvalds 已提交
665 666 667 668
	/*
	 * fast-pathed signals for kernel-internal things like SIGSTOP
	 * or SIGKILL.
	 */
669
	if (info == SEND_SIG_FORCED)
L
Linus Torvalds 已提交
670 671 672 673 674 675 676 677 678 679 680
		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.  */

	q = __sigqueue_alloc(t, GFP_ATOMIC, (sig < SIGRTMIN &&
681
					     (is_si_special(info) ||
L
Linus Torvalds 已提交
682 683 684 685
					      info->si_code >= 0)));
	if (q) {
		list_add_tail(&q->list, &signals->list);
		switch ((unsigned long) info) {
686
		case (unsigned long) SEND_SIG_NOINFO:
L
Linus Torvalds 已提交
687 688 689 690 691 692
			q->info.si_signo = sig;
			q->info.si_errno = 0;
			q->info.si_code = SI_USER;
			q->info.si_pid = current->pid;
			q->info.si_uid = current->uid;
			break;
693
		case (unsigned long) SEND_SIG_PRIV:
L
Linus Torvalds 已提交
694 695 696 697 698 699 700 701 702 703
			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);
			break;
		}
704 705
	} else if (!is_si_special(info)) {
		if (sig >= SIGRTMIN && info->si_code != SI_USER)
L
Linus Torvalds 已提交
706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726
		/*
		 * Queue overflow, abort.  We may abort if the signal was rt
		 * and sent by user using something other than kill().
		 */
			return -EAGAIN;
	}

out_set:
	sigaddset(&signals->signal, sig);
	return ret;
}

#define LEGACY_QUEUE(sigptr, sig) \
	(((sig) < SIGRTMIN) && sigismember(&(sigptr)->signal, (sig)))


static int
specific_send_sig_info(int sig, struct siginfo *info, struct task_struct *t)
{
	int ret = 0;

727
	BUG_ON(!irqs_disabled());
L
Linus Torvalds 已提交
728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749
	assert_spin_locked(&t->sighand->siglock);

	/* Short-circuit ignored signals.  */
	if (sig_ignored(t, sig))
		goto out;

	/* Support queueing exactly one non-rt signal, so that we
	   can get more detailed information about the cause of
	   the signal. */
	if (LEGACY_QUEUE(&t->pending, sig))
		goto out;

	ret = send_signal(sig, info, t, &t->pending);
	if (!ret && !sigismember(&t->blocked, sig))
		signal_wake_up(t, sig == SIGKILL);
out:
	return ret;
}

/*
 * Force a signal that the process can't ignore: if necessary
 * we unblock the signal and change any SIG_IGN to SIG_DFL.
750 751 752 753 754 755
 *
 * 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.
 *
 * We don't want to have recursive SIGSEGV's etc, for example.
L
Linus Torvalds 已提交
756 757 758 759 760
 */
int
force_sig_info(int sig, struct siginfo *info, struct task_struct *t)
{
	unsigned long int flags;
761 762
	int ret, blocked, ignored;
	struct k_sigaction *action;
L
Linus Torvalds 已提交
763 764

	spin_lock_irqsave(&t->sighand->siglock, flags);
765 766 767 768 769 770 771
	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
772
			recalc_sigpending_and_wake(t);
773
		}
L
Linus Torvalds 已提交
774 775 776 777 778 779 780 781 782 783
	}
	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)
{
784
	force_sig_info(sig, SEND_SIG_FORCED, t);
L
Linus Torvalds 已提交
785 786 787 788 789 790 791 792 793 794
}

/*
 * 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.
 */
795 796 797 798 799 800 801 802 803 804 805 806
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 (p->state & (TASK_STOPPED | TASK_TRACED))
		return 0;
	return task_curr(p) || !signal_pending(p);
}
L
Linus Torvalds 已提交
807 808 809 810 811 812 813 814 815 816 817 818

static void
__group_complete_signal(int sig, struct task_struct *p)
{
	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.
	 */
819
	if (wants_signal(sig, p))
L
Linus Torvalds 已提交
820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835
		t = p;
	else if (thread_group_empty(p))
		/*
		 * 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 = p->signal->curr_target;
		if (t == NULL)
			/* restart balancing at this thread */
			t = p->signal->curr_target = p;

836
		while (!wants_signal(sig, t)) {
L
Linus Torvalds 已提交
837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958
			t = next_thread(t);
			if (t == p->signal->curr_target)
				/*
				 * No thread needs to be woken.
				 * Any eligible threads will see
				 * the signal in the queue soon.
				 */
				return;
		}
		p->signal->curr_target = t;
	}

	/*
	 * Found a killable thread.  If the signal will be fatal,
	 * then start taking the whole group down immediately.
	 */
	if (sig_fatal(p, sig) && !(p->signal->flags & SIGNAL_GROUP_EXIT) &&
	    !sigismember(&t->real_blocked, sig) &&
	    (sig == SIGKILL || !(t->ptrace & PT_PTRACED))) {
		/*
		 * 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.
			 */
			p->signal->flags = SIGNAL_GROUP_EXIT;
			p->signal->group_exit_code = sig;
			p->signal->group_stop_count = 0;
			t = p;
			do {
				sigaddset(&t->pending.signal, SIGKILL);
				signal_wake_up(t, 1);
				t = next_thread(t);
			} while (t != p);
			return;
		}

		/*
		 * There will be a core dump.  We make all threads other
		 * than the chosen one go into a group stop so that nothing
		 * happens until it gets scheduled, takes the signal off
		 * the shared queue, and does the core dump.  This is a
		 * little more complicated than strictly necessary, but it
		 * keeps the signal state that winds up in the core dump
		 * unchanged from the death state, e.g. which thread had
		 * the core-dump signal unblocked.
		 */
		rm_from_queue(SIG_KERNEL_STOP_MASK, &t->pending);
		rm_from_queue(SIG_KERNEL_STOP_MASK, &p->signal->shared_pending);
		p->signal->group_stop_count = 0;
		p->signal->group_exit_task = t;
		t = p;
		do {
			p->signal->group_stop_count++;
			signal_wake_up(t, 0);
			t = next_thread(t);
		} while (t != p);
		wake_up_process(p->signal->group_exit_task);
		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;
}

int
__group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p)
{
	int ret = 0;

	assert_spin_locked(&p->sighand->siglock);
	handle_stop_signal(sig, p);

	/* Short-circuit ignored signals.  */
	if (sig_ignored(p, sig))
		return ret;

	if (LEGACY_QUEUE(&p->signal->shared_pending, sig))
		/* This is a non-RT signal and we already have one queued.  */
		return ret;

	/*
	 * Put this signal on the shared-pending queue, or fail with EAGAIN.
	 * We always use the shared queue for process-wide signals,
	 * to avoid several races.
	 */
	ret = send_signal(sig, info, p, &p->signal->shared_pending);
	if (unlikely(ret))
		return ret;

	__group_complete_signal(sig, p);
	return 0;
}

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

	p->signal->flags = SIGNAL_GROUP_EXIT;
	p->signal->group_stop_count = 0;

	if (thread_group_empty(p))
		return;

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

959
		/* SIGKILL will be handled before any pending SIGSTOP */
L
Linus Torvalds 已提交
960 961 962 963 964 965
		sigaddset(&t->pending.signal, SIGKILL);
		signal_wake_up(t, 1);
	}
}

/*
I
Ingo Molnar 已提交
966
 * Must be called under rcu_read_lock() or with tasklist_lock read-held.
L
Linus Torvalds 已提交
967
 */
968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985
struct sighand_struct *lock_task_sighand(struct task_struct *tsk, unsigned long *flags)
{
	struct sighand_struct *sighand;

	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);
	}

	return sighand;
}

L
Linus Torvalds 已提交
986 987 988 989 990 991
int group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p)
{
	unsigned long flags;
	int ret;

	ret = check_kill_permission(sig, info, p);
992 993 994 995 996 997

	if (!ret && sig) {
		ret = -ESRCH;
		if (lock_task_sighand(p, &flags)) {
			ret = __group_send_sig_info(sig, info, p);
			unlock_task_sighand(p, &flags);
998
		}
L
Linus Torvalds 已提交
999 1000 1001 1002 1003 1004
	}

	return ret;
}

/*
1005
 * kill_pgrp_info() sends a signal to a process group: this is what the tty
L
Linus Torvalds 已提交
1006 1007 1008
 * control characters do (^C, ^Z etc)
 */

1009
int __kill_pgrp_info(int sig, struct siginfo *info, struct pid *pgrp)
L
Linus Torvalds 已提交
1010 1011 1012 1013 1014 1015
{
	struct task_struct *p = NULL;
	int retval, success;

	success = 0;
	retval = -ESRCH;
1016
	do_each_pid_task(pgrp, PIDTYPE_PGID, p) {
L
Linus Torvalds 已提交
1017 1018 1019
		int err = group_send_sig_info(sig, info, p);
		success |= !err;
		retval = err;
1020
	} while_each_pid_task(pgrp, PIDTYPE_PGID, p);
L
Linus Torvalds 已提交
1021 1022 1023
	return success ? 0 : retval;
}

1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035
int kill_pgrp_info(int sig, struct siginfo *info, struct pid *pgrp)
{
	int retval;

	read_lock(&tasklist_lock);
	retval = __kill_pgrp_info(sig, info, pgrp);
	read_unlock(&tasklist_lock);

	return retval;
}

int kill_pid_info(int sig, struct siginfo *info, struct pid *pid)
L
Linus Torvalds 已提交
1036 1037 1038 1039
{
	int error;
	struct task_struct *p;

I
Ingo Molnar 已提交
1040
	rcu_read_lock();
1041
	if (unlikely(sig_needs_tasklist(sig)))
I
Ingo Molnar 已提交
1042
		read_lock(&tasklist_lock);
1043

1044
	p = pid_task(pid, PIDTYPE_PID);
L
Linus Torvalds 已提交
1045 1046 1047
	error = -ESRCH;
	if (p)
		error = group_send_sig_info(sig, info, p);
1048 1049

	if (unlikely(sig_needs_tasklist(sig)))
I
Ingo Molnar 已提交
1050 1051
		read_unlock(&tasklist_lock);
	rcu_read_unlock();
L
Linus Torvalds 已提交
1052 1053 1054
	return error;
}

1055 1056
int
kill_proc_info(int sig, struct siginfo *info, pid_t pid)
1057 1058 1059 1060 1061 1062 1063 1064
{
	int error;
	rcu_read_lock();
	error = kill_pid_info(sig, info, find_pid(pid));
	rcu_read_unlock();
	return error;
}

1065 1066
/* 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,
1067
		      uid_t uid, uid_t euid, u32 secid)
1068 1069 1070 1071 1072 1073 1074 1075
{
	int ret = -EINVAL;
	struct task_struct *p;

	if (!valid_signal(sig))
		return ret;

	read_lock(&tasklist_lock);
1076
	p = pid_task(pid, PIDTYPE_PID);
1077 1078 1079 1080
	if (!p) {
		ret = -ESRCH;
		goto out_unlock;
	}
1081
	if ((info == SEND_SIG_NOINFO || (!is_si_special(info) && SI_FROMUSER(info)))
1082 1083 1084 1085 1086
	    && (euid != p->suid) && (euid != p->uid)
	    && (uid != p->suid) && (uid != p->uid)) {
		ret = -EPERM;
		goto out_unlock;
	}
1087 1088 1089
	ret = security_task_kill(p, info, sig, secid);
	if (ret)
		goto out_unlock;
1090 1091 1092 1093 1094 1095 1096 1097 1098 1099
	if (sig && p->sighand) {
		unsigned long flags;
		spin_lock_irqsave(&p->sighand->siglock, flags);
		ret = __group_send_sig_info(sig, info, p);
		spin_unlock_irqrestore(&p->sighand->siglock, flags);
	}
out_unlock:
	read_unlock(&tasklist_lock);
	return ret;
}
1100
EXPORT_SYMBOL_GPL(kill_pid_info_as_uid);
L
Linus Torvalds 已提交
1101 1102 1103 1104 1105 1106 1107 1108 1109 1110

/*
 * 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.
 */

static int kill_something_info(int sig, struct siginfo *info, int pid)
{
1111 1112
	int ret;
	rcu_read_lock();
L
Linus Torvalds 已提交
1113
	if (!pid) {
1114
		ret = kill_pgrp_info(sig, info, task_pgrp(current));
L
Linus Torvalds 已提交
1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128
	} else if (pid == -1) {
		int retval = 0, count = 0;
		struct task_struct * p;

		read_lock(&tasklist_lock);
		for_each_process(p) {
			if (p->pid > 1 && p->tgid != current->tgid) {
				int err = group_send_sig_info(sig, info, p);
				++count;
				if (err != -EPERM)
					retval = err;
			}
		}
		read_unlock(&tasklist_lock);
1129
		ret = count ? retval : -ESRCH;
L
Linus Torvalds 已提交
1130
	} else if (pid < 0) {
1131
		ret = kill_pgrp_info(sig, info, find_pid(-pid));
L
Linus Torvalds 已提交
1132
	} else {
1133
		ret = kill_pid_info(sig, info, find_pid(pid));
L
Linus Torvalds 已提交
1134
	}
1135 1136
	rcu_read_unlock();
	return ret;
L
Linus Torvalds 已提交
1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156
}

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

/*
 * These two are the most common entry points.  They send a signal
 * just to the specific thread.
 */
int
send_sig_info(int sig, struct siginfo *info, struct task_struct *p)
{
	int ret;
	unsigned long flags;

	/*
	 * Make sure legacy kernel users don't send in bad values
	 * (normal paths check this in check_kill_permission).
	 */
1157
	if (!valid_signal(sig))
L
Linus Torvalds 已提交
1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173
		return -EINVAL;

	/*
	 * We need the tasklist lock even for the specific
	 * thread case (when we don't need to follow the group
	 * lists) in order to avoid races with "p->sighand"
	 * going away or changing from under us.
	 */
	read_lock(&tasklist_lock);  
	spin_lock_irqsave(&p->sighand->siglock, flags);
	ret = specific_send_sig_info(sig, info, p);
	spin_unlock_irqrestore(&p->sighand->siglock, flags);
	read_unlock(&tasklist_lock);
	return ret;
}

1174 1175 1176
#define __si_special(priv) \
	((priv) ? SEND_SIG_PRIV : SEND_SIG_NOINFO)

L
Linus Torvalds 已提交
1177 1178 1179
int
send_sig(int sig, struct task_struct *p, int priv)
{
1180
	return send_sig_info(sig, __si_special(priv), p);
L
Linus Torvalds 已提交
1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199
}

/*
 * This is the entry point for "process-wide" signals.
 * They will go to an appropriate thread in the thread group.
 */
int
send_group_sig_info(int sig, struct siginfo *info, struct task_struct *p)
{
	int ret;
	read_lock(&tasklist_lock);
	ret = group_send_sig_info(sig, info, p);
	read_unlock(&tasklist_lock);
	return ret;
}

void
force_sig(int sig, struct task_struct *p)
{
1200
	force_sig_info(sig, SEND_SIG_PRIV, p);
L
Linus Torvalds 已提交
1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221
}

/*
 * 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;
}

1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233
int kill_pgrp(struct pid *pid, int sig, int priv)
{
	return kill_pgrp_info(sig, __si_special(priv), pid);
}
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
1234 1235 1236
int
kill_proc(pid_t pid, int sig, int priv)
{
1237
	return kill_proc_info(sig, __si_special(priv), pid);
L
Linus Torvalds 已提交
1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267
}

/*
 * 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
 * expirations or I/O completions".  In the case of Posix Timers 
 * 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)
{
	struct sigqueue *q;

	if ((q = __sigqueue_alloc(current, GFP_KERNEL, 0)))
		q->flags |= SIGQUEUE_PREALLOC;
	return(q);
}

void sigqueue_free(struct sigqueue *q)
{
	unsigned long flags;
	BUG_ON(!(q->flags & SIGQUEUE_PREALLOC));
	/*
	 * If the signal is still pending remove it from the
	 * pending queue.
	 */
	if (unlikely(!list_empty(&q->list))) {
O
Oleg Nesterov 已提交
1268 1269 1270
		spinlock_t *lock = &current->sighand->siglock;
		read_lock(&tasklist_lock);
		spin_lock_irqsave(lock, flags);
L
Linus Torvalds 已提交
1271 1272
		if (!list_empty(&q->list))
			list_del_init(&q->list);
O
Oleg Nesterov 已提交
1273
		spin_unlock_irqrestore(lock, flags);
L
Linus Torvalds 已提交
1274 1275 1276 1277 1278 1279
		read_unlock(&tasklist_lock);
	}
	q->flags &= ~SIGQUEUE_PREALLOC;
	__sigqueue_free(q);
}

1280
int send_sigqueue(int sig, struct sigqueue *q, struct task_struct *p)
L
Linus Torvalds 已提交
1281 1282 1283 1284 1285
{
	unsigned long flags;
	int ret = 0;

	BUG_ON(!(q->flags & SIGQUEUE_PREALLOC));
I
Ingo Molnar 已提交
1286 1287 1288 1289 1290 1291 1292 1293 1294 1295

	/*
	 * The rcu based delayed sighand destroy makes it possible to
	 * run this without tasklist lock held. The task struct itself
	 * cannot go away as create_timer did get_task_struct().
	 *
	 * We return -1, when the task is marked exiting, so
	 * posix_timer_event can redirect it to the group leader
	 */
	rcu_read_lock();
1296

1297
	if (!likely(lock_task_sighand(p, &flags))) {
1298 1299 1300 1301
		ret = -1;
		goto out_err;
	}

L
Linus Torvalds 已提交
1302 1303 1304 1305 1306
	if (unlikely(!list_empty(&q->list))) {
		/*
		 * If an SI_TIMER entry is already queue just increment
		 * the overrun count.
		 */
1307
		BUG_ON(q->info.si_code != SI_TIMER);
L
Linus Torvalds 已提交
1308 1309
		q->info.si_overrun++;
		goto out;
1310
	}
L
Linus Torvalds 已提交
1311 1312 1313 1314 1315
	/* Short-circuit ignored signals.  */
	if (sig_ignored(p, sig)) {
		ret = 1;
		goto out;
	}
1316 1317 1318 1319 1320
	/*
	 * Deliver the signal to listening signalfds. This must be called
	 * with the sighand lock held.
	 */
	signalfd_notify(p, sig);
L
Linus Torvalds 已提交
1321 1322 1323 1324 1325 1326 1327

	list_add_tail(&q->list, &p->pending.list);
	sigaddset(&p->pending.signal, sig);
	if (!sigismember(&p->blocked, sig))
		signal_wake_up(p, sig == SIGKILL);

out:
1328
	unlock_task_sighand(p, &flags);
1329
out_err:
I
Ingo Molnar 已提交
1330
	rcu_read_unlock();
1331 1332

	return ret;
L
Linus Torvalds 已提交
1333 1334 1335 1336 1337 1338 1339 1340 1341
}

int
send_group_sigqueue(int sig, struct sigqueue *q, struct task_struct *p)
{
	unsigned long flags;
	int ret = 0;

	BUG_ON(!(q->flags & SIGQUEUE_PREALLOC));
I
Ingo Molnar 已提交
1342

L
Linus Torvalds 已提交
1343
	read_lock(&tasklist_lock);
I
Ingo Molnar 已提交
1344
	/* Since it_lock is held, p->sighand cannot be NULL. */
L
Linus Torvalds 已提交
1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359
	spin_lock_irqsave(&p->sighand->siglock, flags);
	handle_stop_signal(sig, p);

	/* Short-circuit ignored signals.  */
	if (sig_ignored(p, sig)) {
		ret = 1;
		goto out;
	}

	if (unlikely(!list_empty(&q->list))) {
		/*
		 * If an SI_TIMER entry is already queue just increment
		 * the overrun count.  Other uses should not try to
		 * send the signal multiple times.
		 */
1360
		BUG_ON(q->info.si_code != SI_TIMER);
L
Linus Torvalds 已提交
1361 1362 1363
		q->info.si_overrun++;
		goto out;
	} 
1364 1365 1366 1367 1368
	/*
	 * Deliver the signal to listening signalfds. This must be called
	 * with the sighand lock held.
	 */
	signalfd_notify(p, sig);
L
Linus Torvalds 已提交
1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381

	/*
	 * Put this signal on the shared-pending queue.
	 * We always use the shared queue for process-wide signals,
	 * to avoid several races.
	 */
	list_add_tail(&q->list, &p->signal->shared_pending.list);
	sigaddset(&p->signal->shared_pending.signal, sig);

	__group_complete_signal(sig, p);
out:
	spin_unlock_irqrestore(&p->sighand->siglock, flags);
	read_unlock(&tasklist_lock);
I
Ingo Molnar 已提交
1382
	return ret;
L
Linus Torvalds 已提交
1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435
}

/*
 * Wake up any threads in the parent blocked in wait* syscalls.
 */
static inline void __wake_up_parent(struct task_struct *p,
				    struct task_struct *parent)
{
	wake_up_interruptible_sync(&parent->signal->wait_chldexit);
}

/*
 * Let a parent know about the death of a child.
 * For a stopped/continued status change, use do_notify_parent_cldstop instead.
 */

void do_notify_parent(struct task_struct *tsk, int sig)
{
	struct siginfo info;
	unsigned long flags;
	struct sighand_struct *psig;

	BUG_ON(sig == -1);

 	/* do_notify_parent_cldstop should have been called instead.  */
 	BUG_ON(tsk->state & (TASK_STOPPED|TASK_TRACED));

	BUG_ON(!tsk->ptrace &&
	       (tsk->group_leader != tsk || !thread_group_empty(tsk)));

	info.si_signo = sig;
	info.si_errno = 0;
	info.si_pid = tsk->pid;
	info.si_uid = tsk->uid;

	/* FIXME: find out whether or not this is supposed to be c*time. */
	info.si_utime = cputime_to_jiffies(cputime_add(tsk->utime,
						       tsk->signal->utime));
	info.si_stime = cputime_to_jiffies(cputime_add(tsk->stime,
						       tsk->signal->stime));

	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);
1436
	if (!tsk->ptrace && sig == SIGCHLD &&
L
Linus Torvalds 已提交
1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457
	    (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).
		 */
		tsk->exit_signal = -1;
		if (psig->action[SIGCHLD-1].sa.sa_handler == SIG_IGN)
			sig = 0;
	}
1458
	if (valid_signal(sig) && sig > 0)
L
Linus Torvalds 已提交
1459 1460 1461 1462 1463
		__group_send_sig_info(sig, &info, tsk->parent);
	__wake_up_parent(tsk, tsk->parent);
	spin_unlock_irqrestore(&psig->siglock, flags);
}

1464
static void do_notify_parent_cldstop(struct task_struct *tsk, int why)
L
Linus Torvalds 已提交
1465 1466 1467
{
	struct siginfo info;
	unsigned long flags;
1468
	struct task_struct *parent;
L
Linus Torvalds 已提交
1469 1470
	struct sighand_struct *sighand;

1471
	if (tsk->ptrace & PT_PTRACED)
1472 1473 1474 1475 1476 1477
		parent = tsk->parent;
	else {
		tsk = tsk->group_leader;
		parent = tsk->real_parent;
	}

L
Linus Torvalds 已提交
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
	info.si_signo = SIGCHLD;
	info.si_errno = 0;
	info.si_pid = tsk->pid;
	info.si_uid = tsk->uid;

	/* FIXME: find out whether or not this is supposed to be c*time. */
	info.si_utime = cputime_to_jiffies(tsk->utime);
	info.si_stime = cputime_to_jiffies(tsk->stime);

 	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);
}

1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542
static inline int may_ptrace_stop(void)
{
	if (!likely(current->ptrace & PT_PTRACED))
		return 0;

	if (unlikely(current->parent == current->real_parent &&
		    (current->ptrace & PT_ATTACHED)))
		return 0;

	if (unlikely(current->signal == current->parent->signal) &&
	    unlikely(current->signal->flags & SIGNAL_GROUP_EXIT))
		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
	 * ->siglock we must see ->core_waiters != 0. Otherwise it
	 * is safe to enter schedule().
	 */
	if (unlikely(current->mm->core_waiters) &&
	    unlikely(current->mm == current->parent->mm))
		return 0;

	return 1;
}

L
Linus Torvalds 已提交
1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568
/*
 * 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.
 *
 * If we actually decide not to stop at all because the tracer is gone,
 * we leave nostop_code in current->exit_code.
 */
static void ptrace_stop(int exit_code, int nostop_code, siginfo_t *info)
{
	/*
	 * 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.  */
	set_current_state(TASK_TRACED);
	spin_unlock_irq(&current->sighand->siglock);
1569
	try_to_freeze();
L
Linus Torvalds 已提交
1570
	read_lock(&tasklist_lock);
1571
	if (may_ptrace_stop()) {
1572
		do_notify_parent_cldstop(current, CLD_TRAPPED);
L
Linus Torvalds 已提交
1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595
		read_unlock(&tasklist_lock);
		schedule();
	} else {
		/*
		 * By the time we got the lock, our tracer went away.
		 * Don't stop here.
		 */
		read_unlock(&tasklist_lock);
		set_current_state(TASK_RUNNING);
		current->exit_code = nostop_code;
	}

	/*
	 * 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.
1596
	 * This sets TIF_SIGPENDING, but never clears it.
L
Linus Torvalds 已提交
1597
	 */
1598
	recalc_sigpending_tsk(current);
L
Linus Torvalds 已提交
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
}

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;
	info.si_pid = current->pid;
	info.si_uid = current->uid;

	/* Let the debugger run.  */
	spin_lock_irq(&current->sighand->siglock);
	ptrace_stop(exit_code, 0, &info);
	spin_unlock_irq(&current->sighand->siglock);
}

static void
finish_stop(int stop_count)
{
	/*
	 * 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.
	 */
1627 1628 1629 1630 1631
	if (stop_count == 0 || (current->ptrace & PT_PTRACED)) {
		read_lock(&tasklist_lock);
		do_notify_parent_cldstop(current, CLD_STOPPED);
		read_unlock(&tasklist_lock);
	}
1632

1633 1634 1635
	do {
		schedule();
	} while (try_to_freeze());
L
Linus Torvalds 已提交
1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647
	/*
	 * Now we don't run again until continued.
	 */
	current->exit_code = 0;
}

/*
 * 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.
 */
1648
static int do_signal_stop(int signr)
L
Linus Torvalds 已提交
1649 1650
{
	struct signal_struct *sig = current->signal;
1651
	int stop_count;
L
Linus Torvalds 已提交
1652 1653 1654 1655 1656 1657 1658 1659 1660 1661

	if (!likely(sig->flags & SIGNAL_STOP_DEQUEUED))
		return 0;

	if (sig->group_stop_count > 0) {
		/*
		 * There is a group stop in progress.  We don't need to
		 * start another one.
		 */
		stop_count = --sig->group_stop_count;
1662
	} else {
L
Linus Torvalds 已提交
1663 1664
		/*
		 * There is no group stop already in progress.
1665
		 * We must initiate one now.
L
Linus Torvalds 已提交
1666 1667 1668
		 */
		struct task_struct *t;

1669
		sig->group_exit_code = signr;
L
Linus Torvalds 已提交
1670

1671 1672
		stop_count = 0;
		for (t = next_thread(current); t != current; t = next_thread(t))
L
Linus Torvalds 已提交
1673
			/*
1674 1675 1676
			 * 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
1677
			 */
1678 1679 1680 1681 1682 1683
			if (!t->exit_state &&
			    !(t->state & (TASK_STOPPED|TASK_TRACED))) {
				stop_count++;
				signal_wake_up(t, 0);
			}
		sig->group_stop_count = stop_count;
L
Linus Torvalds 已提交
1684 1685
	}

1686 1687 1688 1689 1690 1691
	if (stop_count == 0)
		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
1692 1693 1694 1695 1696 1697 1698 1699 1700 1701
	finish_stop(stop_count);
	return 1;
}

/*
 * Do appropriate magic when group_stop_count > 0.
 * We return nonzero if we stopped, after releasing the siglock.
 * We return zero if we still hold the siglock and should look
 * for another signal without checking group_stop_count again.
 */
1702
static int handle_group_stop(void)
L
Linus Torvalds 已提交
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
{
	int stop_count;

	if (current->signal->group_exit_task == current) {
		/*
		 * Group stop is so we can do a core dump,
		 * We are the initiating thread, so get on with it.
		 */
		current->signal->group_exit_task = NULL;
		return 0;
	}

	if (current->signal->flags & SIGNAL_GROUP_EXIT)
		/*
		 * Group stop is so another thread can do a core dump,
		 * or else we are racing against a death signal.
		 * Just punt the stop so we can get the next signal.
		 */
		return 0;

	/*
	 * There is a group stop in progress.  We stop
	 * without any associated signal being in our queue.
	 */
	stop_count = --current->signal->group_stop_count;
	if (stop_count == 0)
		current->signal->flags = SIGNAL_STOP_STOPPED;
	current->exit_code = current->signal->group_exit_code;
	set_current_state(TASK_STOPPED);
	spin_unlock_irq(&current->sighand->siglock);
	finish_stop(stop_count);
	return 1;
}

int get_signal_to_deliver(siginfo_t *info, struct k_sigaction *return_ka,
			  struct pt_regs *regs, void *cookie)
{
	sigset_t *mask = &current->blocked;
	int signr = 0;

1743 1744
	try_to_freeze();

L
Linus Torvalds 已提交
1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764
relock:
	spin_lock_irq(&current->sighand->siglock);
	for (;;) {
		struct k_sigaction *ka;

		if (unlikely(current->signal->group_stop_count > 0) &&
		    handle_group_stop())
			goto relock;

		signr = dequeue_signal(current, mask, info);

		if (!signr)
			break; /* will return 0 */

		if ((current->ptrace & PT_PTRACED) && signr != SIGKILL) {
			ptrace_signal_deliver(regs, cookie);

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

1765
			/* We're back.  Did the debugger cancel the sig?  */
L
Linus Torvalds 已提交
1766
			signr = current->exit_code;
1767
			if (signr == 0)
L
Linus Torvalds 已提交
1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809
				continue;

			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 = current->parent->pid;
				info->si_uid = current->parent->uid;
			}

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

		ka = &current->sighand->action[signr-1];
		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;

1810 1811 1812 1813 1814 1815
		/*
		 * Init of a pid space gets no signals it doesn't want from
		 * within that pid space. It can of course get signals from
		 * its parent pid space.
		 */
		if (current == child_reaper(current))
L
Linus Torvalds 已提交
1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833
			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) {
				spin_unlock_irq(&current->sighand->siglock);

				/* signals can be posted during this window */

1834
				if (is_current_pgrp_orphaned())
L
Linus Torvalds 已提交
1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926
					goto relock;

				spin_lock_irq(&current->sighand->siglock);
			}

			if (likely(do_signal_stop(signr))) {
				/* It released the siglock.  */
				goto relock;
			}

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

		spin_unlock_irq(&current->sighand->siglock);

		/*
		 * Anything else is fatal, maybe with a core dump.
		 */
		current->flags |= PF_SIGNALED;
		if (sig_kernel_coredump(signr)) {
			/*
			 * 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.
			 */
			do_coredump((long)signr, signr, regs);
		}

		/*
		 * Death signals, no core dump.
		 */
		do_group_exit(signr);
		/* NOTREACHED */
	}
	spin_unlock_irq(&current->sighand->siglock);
	return signr;
}

EXPORT_SYMBOL(recalc_sigpending);
EXPORT_SYMBOL_GPL(dequeue_signal);
EXPORT_SYMBOL(flush_signals);
EXPORT_SYMBOL(force_sig);
EXPORT_SYMBOL(kill_proc);
EXPORT_SYMBOL(ptrace_notify);
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.
 */

asmlinkage long sys_restart_syscall(void)
{
	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);
1927 1928 1929
	if (oldset)
		*oldset = current->blocked;

L
Linus Torvalds 已提交
1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945
	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);
1946

L
Linus Torvalds 已提交
1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029
	return error;
}

asmlinkage long
sys_rt_sigprocmask(int how, sigset_t __user *set, sigset_t __user *oset, size_t sigsetsize)
{
	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;
}	

asmlinkage long
sys_rt_sigpending(sigset_t __user *set, size_t sigsetsize)
{
	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.
2030 2031
	 * Please remember to update the signalfd_copyinfo() function
	 * inside fs/signalfd.c too, in case siginfo_t changes.
L
Linus Torvalds 已提交
2032 2033 2034 2035 2036 2037 2038 2039 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 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 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
	 * 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

asmlinkage long
sys_rt_sigtimedwait(const sigset_t __user *uthese,
		    siginfo_t __user *uinfo,
		    const struct timespec __user *uts,
		    size_t sigsetsize)
{
	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);

2133
			timeout = schedule_timeout_interruptible(timeout);
L
Linus Torvalds 已提交
2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172

			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;
}

asmlinkage long
sys_kill(int pid, int sig)
{
	struct siginfo info;

	info.si_signo = sig;
	info.si_errno = 0;
	info.si_code = SI_USER;
	info.si_pid = current->tgid;
	info.si_uid = current->uid;

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

2173
static int do_tkill(int tgid, int pid, int sig)
L
Linus Torvalds 已提交
2174 2175
{
	int error;
2176
	struct siginfo info;
L
Linus Torvalds 已提交
2177 2178
	struct task_struct *p;

2179
	error = -ESRCH;
L
Linus Torvalds 已提交
2180 2181 2182 2183 2184 2185 2186 2187
	info.si_signo = sig;
	info.si_errno = 0;
	info.si_code = SI_TKILL;
	info.si_pid = current->tgid;
	info.si_uid = current->uid;

	read_lock(&tasklist_lock);
	p = find_task_by_pid(pid);
2188
	if (p && (tgid <= 0 || p->tgid == tgid)) {
L
Linus Torvalds 已提交
2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201
		error = check_kill_permission(sig, &info, p);
		/*
		 * The null signal is a permissions and process existence
		 * probe.  No signal is actually delivered.
		 */
		if (!error && sig && p->sighand) {
			spin_lock_irq(&p->sighand->siglock);
			handle_stop_signal(sig, p);
			error = specific_send_sig_info(sig, &info, p);
			spin_unlock_irq(&p->sighand->siglock);
		}
	}
	read_unlock(&tasklist_lock);
2202

L
Linus Torvalds 已提交
2203 2204 2205
	return error;
}

2206 2207 2208 2209 2210 2211
/**
 *  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
 *
2212
 *  This syscall also checks the @tgid and returns -ESRCH even if the PID
2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224
 *  exists but it's not belonging to the target process anymore. This
 *  method solves the problem of threads exiting and PIDs getting reused.
 */
asmlinkage long sys_tgkill(int tgid, int pid, int sig)
{
	/* 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
2225 2226 2227 2228 2229 2230 2231 2232 2233 2234
/*
 *  Send a signal to only one task, even if it's a CLONE_THREAD task.
 */
asmlinkage long
sys_tkill(int pid, int sig)
{
	/* This is only valid for single tasks */
	if (pid <= 0)
		return -EINVAL;

2235
	return do_tkill(0, pid, sig);
L
Linus Torvalds 已提交
2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255
}

asmlinkage long
sys_rt_sigqueueinfo(int pid, int sig, siginfo_t __user *uinfo)
{
	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);
}

2256
int do_sigaction(int sig, struct k_sigaction *act, struct k_sigaction *oact)
L
Linus Torvalds 已提交
2257 2258
{
	struct k_sigaction *k;
2259
	sigset_t mask;
L
Linus Torvalds 已提交
2260

2261
	if (!valid_signal(sig) || sig < 1 || (act && sig_kernel_only(sig)))
L
Linus Torvalds 已提交
2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279
		return -EINVAL;

	k = &current->sighand->action[sig-1];

	spin_lock_irq(&current->sighand->siglock);
	if (signal_pending(current)) {
		/*
		 * If there might be a fatal signal pending on multiple
		 * threads, make sure we take it before changing the action.
		 */
		spin_unlock_irq(&current->sighand->siglock);
		return -ERESTARTNOINTR;
	}

	if (oact)
		*oact = *k;

	if (act) {
2280 2281
		sigdelsetmask(&act->sa.sa_mask,
			      sigmask(SIGKILL) | sigmask(SIGSTOP));
2282
		*k = *act;
L
Linus Torvalds 已提交
2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294
		/*
		 * 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"
		 */
		if (act->sa.sa_handler == SIG_IGN ||
2295
		   (act->sa.sa_handler == SIG_DFL && sig_kernel_ignore(sig))) {
L
Linus Torvalds 已提交
2296
			struct task_struct *t = current;
2297 2298 2299
			sigemptyset(&mask);
			sigaddset(&mask, sig);
			rm_from_queue_full(&mask, &t->signal->shared_pending);
L
Linus Torvalds 已提交
2300
			do {
2301
				rm_from_queue_full(&mask, &t->pending);
R
Roland McGrath 已提交
2302
				recalc_sigpending_and_wake(t);
L
Linus Torvalds 已提交
2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 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 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510
				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;

	if (uoss) {
		oss.ss_sp = (void __user *) current->sas_ss_sp;
		oss.ss_size = current->sas_ss_size;
		oss.ss_flags = sas_ss_flags(sp);
	}

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

		error = -EFAULT;
		if (!access_ok(VERIFY_READ, uss, sizeof(*uss))
		    || __get_user(ss_sp, &uss->ss_sp)
		    || __get_user(ss_flags, &uss->ss_flags)
		    || __get_user(ss_size, &uss->ss_size))
			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;
	}

	if (uoss) {
		error = -EFAULT;
		if (copy_to_user(uoss, &oss, sizeof(oss)))
			goto out;
	}

	error = 0;
out:
	return error;
}

#ifdef __ARCH_WANT_SYS_SIGPENDING

asmlinkage long
sys_sigpending(old_sigset_t __user *set)
{
	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.  */

asmlinkage long
sys_sigprocmask(int how, old_sigset_t __user *set, old_sigset_t __user *oset)
{
	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
asmlinkage long
sys_rt_sigaction(int sig,
		 const struct sigaction __user *act,
		 struct sigaction __user *oact,
		 size_t sigsetsize)
{
	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.
 */
asmlinkage long
sys_sgetmask(void)
{
	/* SMP safe */
	return current->blocked.sig[0];
}

asmlinkage long
sys_ssetmask(int newmask)
{
	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.
 */
asmlinkage unsigned long
sys_signal(int sig, __sighandler_t handler)
{
	struct k_sigaction new_sa, old_sa;
	int ret;

	new_sa.sa.sa_handler = handler;
	new_sa.sa.sa_flags = SA_ONESHOT | SA_NOMASK;
2511
	sigemptyset(&new_sa.sa.sa_mask);
L
Linus Torvalds 已提交
2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530

	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

asmlinkage long
sys_pause(void)
{
	current->state = TASK_INTERRUPTIBLE;
	schedule();
	return -ERESTARTNOHAND;
}

#endif

2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556
#ifdef __ARCH_WANT_SYS_RT_SIGSUSPEND
asmlinkage long sys_rt_sigsuspend(sigset_t __user *unewset, size_t sigsetsize)
{
	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();
	set_thread_flag(TIF_RESTORE_SIGMASK);
	return -ERESTARTNOHAND;
}
#endif /* __ARCH_WANT_SYS_RT_SIGSUSPEND */

2557 2558 2559 2560 2561
__attribute__((weak)) const char *arch_vma_name(struct vm_area_struct *vma)
{
	return NULL;
}

L
Linus Torvalds 已提交
2562 2563
void __init signals_init(void)
{
2564
	sigqueue_cachep = KMEM_CACHE(sigqueue, SLAB_PANIC);
L
Linus Torvalds 已提交
2565
}