signal.c 69.7 KB
Newer Older
Linus Torvalds's avatar
Linus Torvalds committed
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25
/*
 *  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/config.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/smp_lock.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>
#include <linux/posix-timers.h>
26
#include <linux/signal.h>
27
#include <linux/audit.h>
28
#include <linux/capability.h>
Linus Torvalds's avatar
Linus Torvalds committed
29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149
#include <asm/param.h>
#include <asm/uaccess.h>
#include <asm/unistd.h>
#include <asm/siginfo.h>

/*
 * SLAB caches for signal bits.
 */

static kmem_cache_t *sigqueue_cachep;

/*
 * In POSIX a signal is sent either to a specific thread (Linux task)
 * or to the process as a whole (Linux thread group).  How the signal
 * is sent determines whether it's to one thread or the whole group,
 * which determines which signal mask(s) are involved in blocking it
 * from being delivered until later.  When the signal is delivered,
 * either it's caught or ignored by a user handler or it has a default
 * effect that applies to the whole thread group (POSIX process).
 *
 * The possible effects an unblocked signal set to SIG_DFL can have are:
 *   ignore	- Nothing Happens
 *   terminate	- kill the process, i.e. all threads in the group,
 * 		  similar to exit_group.  The group leader (only) reports
 *		  WIFSIGNALED status to its parent.
 *   coredump	- write a core dump file describing all threads using
 *		  the same mm and then kill all those threads
 *   stop 	- stop all the threads in the group, i.e. TASK_STOPPED state
 *
 * SIGKILL and SIGSTOP cannot be caught, blocked, or ignored.
 * Other signals when not blocked and set to SIG_DFL behaves as follows.
 * The job control signals also have other special effects.
 *
 *	+--------------------+------------------+
 *	|  POSIX signal      |  default action  |
 *	+--------------------+------------------+
 *	|  SIGHUP            |  terminate	|
 *	|  SIGINT            |	terminate	|
 *	|  SIGQUIT           |	coredump 	|
 *	|  SIGILL            |	coredump 	|
 *	|  SIGTRAP           |	coredump 	|
 *	|  SIGABRT/SIGIOT    |	coredump 	|
 *	|  SIGBUS            |	coredump 	|
 *	|  SIGFPE            |	coredump 	|
 *	|  SIGKILL           |	terminate(+)	|
 *	|  SIGUSR1           |	terminate	|
 *	|  SIGSEGV           |	coredump 	|
 *	|  SIGUSR2           |	terminate	|
 *	|  SIGPIPE           |	terminate	|
 *	|  SIGALRM           |	terminate	|
 *	|  SIGTERM           |	terminate	|
 *	|  SIGCHLD           |	ignore   	|
 *	|  SIGCONT           |	ignore(*)	|
 *	|  SIGSTOP           |	stop(*)(+)  	|
 *	|  SIGTSTP           |	stop(*)  	|
 *	|  SIGTTIN           |	stop(*)  	|
 *	|  SIGTTOU           |	stop(*)  	|
 *	|  SIGURG            |	ignore   	|
 *	|  SIGXCPU           |	coredump 	|
 *	|  SIGXFSZ           |	coredump 	|
 *	|  SIGVTALRM         |	terminate	|
 *	|  SIGPROF           |	terminate	|
 *	|  SIGPOLL/SIGIO     |	terminate	|
 *	|  SIGSYS/SIGUNUSED  |	coredump 	|
 *	|  SIGSTKFLT         |	terminate	|
 *	|  SIGWINCH          |	ignore   	|
 *	|  SIGPWR            |	terminate	|
 *	|  SIGRTMIN-SIGRTMAX |	terminate       |
 *	+--------------------+------------------+
 *	|  non-POSIX signal  |  default action  |
 *	+--------------------+------------------+
 *	|  SIGEMT            |  coredump	|
 *	+--------------------+------------------+
 *
 * (+) For SIGKILL and SIGSTOP the action is "always", not just "default".
 * (*) Special job control effects:
 * When SIGCONT is sent, it resumes the process (all threads in the group)
 * from TASK_STOPPED state and also clears any pending/queued stop signals
 * (any of those marked with "stop(*)").  This happens regardless of blocking,
 * catching, or ignoring SIGCONT.  When any stop signal is sent, it clears
 * any pending/queued SIGCONT signals; this happens regardless of blocking,
 * catching, or ignored the stop signal, though (except for SIGSTOP) the
 * default action of stopping the process may happen later or never.
 */

#ifdef SIGEMT
#define M_SIGEMT	M(SIGEMT)
#else
#define M_SIGEMT	0
#endif

#if SIGRTMIN > BITS_PER_LONG
#define M(sig) (1ULL << ((sig)-1))
#else
#define M(sig) (1UL << ((sig)-1))
#endif
#define T(sig, mask) (M(sig) & (mask))

#define SIG_KERNEL_ONLY_MASK (\
	M(SIGKILL)   |  M(SIGSTOP)                                   )

#define SIG_KERNEL_STOP_MASK (\
	M(SIGSTOP)   |  M(SIGTSTP)   |  M(SIGTTIN)   |  M(SIGTTOU)   )

#define SIG_KERNEL_COREDUMP_MASK (\
        M(SIGQUIT)   |  M(SIGILL)    |  M(SIGTRAP)   |  M(SIGABRT)   | \
        M(SIGFPE)    |  M(SIGSEGV)   |  M(SIGBUS)    |  M(SIGSYS)    | \
        M(SIGXCPU)   |  M(SIGXFSZ)   |  M_SIGEMT                     )

#define SIG_KERNEL_IGNORE_MASK (\
        M(SIGCONT)   |  M(SIGCHLD)   |  M(SIGWINCH)  |  M(SIGURG)    )

#define sig_kernel_only(sig) \
		(((sig) < SIGRTMIN)  && T(sig, SIG_KERNEL_ONLY_MASK))
#define sig_kernel_coredump(sig) \
		(((sig) < SIGRTMIN)  && T(sig, SIG_KERNEL_COREDUMP_MASK))
#define sig_kernel_ignore(sig) \
		(((sig) < SIGRTMIN)  && T(sig, SIG_KERNEL_IGNORE_MASK))
#define sig_kernel_stop(sig) \
		(((sig) < SIGRTMIN)  && T(sig, SIG_KERNEL_STOP_MASK))

150 151 152
#define sig_needs_tasklist(sig) \
		(((sig) < SIGRTMIN)  && T(sig, SIG_KERNEL_STOP_MASK | M(SIGCONT)))

Linus Torvalds's avatar
Linus Torvalds committed
153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219
#define sig_user_defined(t, signr) \
	(((t)->sighand->action[(signr)-1].sa.sa_handler != SIG_DFL) &&	\
	 ((t)->sighand->action[(signr)-1].sa.sa_handler != SIG_IGN))

#define sig_fatal(t, signr) \
	(!T(signr, SIG_KERNEL_IGNORE_MASK|SIG_KERNEL_STOP_MASK) && \
	 (t)->sighand->action[(signr)-1].sa.sa_handler == SIG_DFL)

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))

fastcall void recalc_sigpending_tsk(struct task_struct *t)
{
	if (t->signal->group_stop_count > 0 ||
220
	    (freezing(t)) ||
Linus Torvalds's avatar
Linus Torvalds committed
221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268
	    PENDING(&t->pending, &t->blocked) ||
	    PENDING(&t->signal->shared_pending, &t->blocked))
		set_tsk_thread_flag(t, TIF_SIGPENDING);
	else
		clear_tsk_thread_flag(t, TIF_SIGPENDING);
}

void recalc_sigpending(void)
{
	recalc_sigpending_tsk(current);
}

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

static int
next_signal(struct sigpending *pending, sigset_t *mask)
{
	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;
}

269
static struct sigqueue *__sigqueue_alloc(struct task_struct *t, gfp_t flags,
Linus Torvalds's avatar
Linus Torvalds committed
270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288
					 int override_rlimit)
{
	struct sigqueue *q = NULL;

	atomic_inc(&t->user->sigpending);
	if (override_rlimit ||
	    atomic_read(&t->user->sigpending) <=
			t->signal->rlim[RLIMIT_SIGPENDING].rlim_cur)
		q = kmem_cache_alloc(sigqueue_cachep, flags);
	if (unlikely(q == NULL)) {
		atomic_dec(&t->user->sigpending);
	} else {
		INIT_LIST_HEAD(&q->list);
		q->flags = 0;
		q->user = get_uid(t->user);
	}
	return(q);
}

289
static void __sigqueue_free(struct sigqueue *q)
Linus Torvalds's avatar
Linus Torvalds committed
290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312
{
	if (q->flags & SIGQUEUE_PREALLOC)
		return;
	atomic_dec(&q->user->sigpending);
	free_uid(q->user);
	kmem_cache_free(sigqueue_cachep, q);
}

static void flush_sigqueue(struct sigpending *queue)
{
	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.
 */
313
void flush_signals(struct task_struct *t)
Linus Torvalds's avatar
Linus Torvalds committed
314 315 316 317 318 319 320 321 322 323 324 325 326 327 328
{
	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);
}

/*
 * This function expects the tasklist_lock write-locked.
 */
void __exit_signal(struct task_struct *tsk)
{
329 330 331 332 333
	struct signal_struct *sig = tsk->signal;
	struct sighand_struct *sighand;

	BUG_ON(!sig);
	BUG_ON(!atomic_read(&sig->count));
Linus Torvalds's avatar
Linus Torvalds committed
334

Ingo Molnar's avatar
Ingo Molnar committed
335 336
	rcu_read_lock();
	sighand = rcu_dereference(tsk->sighand);
Linus Torvalds's avatar
Linus Torvalds committed
337
	spin_lock(&sighand->siglock);
338

Linus Torvalds's avatar
Linus Torvalds committed
339
	posix_cpu_timers_exit(tsk);
340
	if (atomic_dec_and_test(&sig->count))
Linus Torvalds's avatar
Linus Torvalds committed
341
		posix_cpu_timers_exit_group(tsk);
342
	else {
Linus Torvalds's avatar
Linus Torvalds committed
343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369
		/*
		 * If there is any task waiting for the group exit
		 * then notify it:
		 */
		if (sig->group_exit_task && atomic_read(&sig->count) == sig->notify_count) {
			wake_up_process(sig->group_exit_task);
			sig->group_exit_task = NULL;
		}
		if (tsk == sig->curr_target)
			sig->curr_target = next_thread(tsk);
		/*
		 * Accumulate here the counters for all threads but the
		 * group leader as they die, so they can be added into
		 * the process-wide totals when those are taken.
		 * The group leader stays around as a zombie as long
		 * as there are other threads.  When it gets reaped,
		 * the exit.c code will add its counts into these totals.
		 * We won't ever get here for the group leader, since it
		 * will have been the last reference on the signal_struct.
		 */
		sig->utime = cputime_add(sig->utime, tsk->utime);
		sig->stime = cputime_add(sig->stime, tsk->stime);
		sig->min_flt += tsk->min_flt;
		sig->maj_flt += tsk->maj_flt;
		sig->nvcsw += tsk->nvcsw;
		sig->nivcsw += tsk->nivcsw;
		sig->sched_time += tsk->sched_time;
370
		sig = NULL; /* Marker for below. */
Linus Torvalds's avatar
Linus Torvalds committed
371
	}
372 373

	tsk->signal = NULL;
374
	cleanup_sighand(tsk);
375
	spin_unlock(&sighand->siglock);
Ingo Molnar's avatar
Ingo Molnar committed
376
	rcu_read_unlock();
377

Linus Torvalds's avatar
Linus Torvalds committed
378 379 380
	clear_tsk_thread_flag(tsk,TIF_SIGPENDING);
	flush_sigqueue(&tsk->pending);
	if (sig) {
381
		flush_sigqueue(&sig->shared_pending);
382
		__cleanup_signal(sig);
Linus Torvalds's avatar
Linus Torvalds committed
383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438
	}
}

/*
 * 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);
}

439
static int collect_signal(int sig, struct sigpending *list, siginfo_t *info)
Linus Torvalds's avatar
Linus Torvalds committed
440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486
{
	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)
{
	int sig = 0;

487
	sig = next_signal(pending, mask);
Linus Torvalds's avatar
Linus Torvalds committed
488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531
	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;
				
	}
	recalc_sigpending();

	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)
{
	int signr = __dequeue_signal(&tsk->pending, mask, info);
	if (!signr)
		signr = __dequeue_signal(&tsk->signal->shared_pending,
					 mask, info);
 	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.
 		 */
532 533
 		if (!(tsk->signal->flags & SIGNAL_GROUP_EXIT))
 			tsk->signal->flags |= SIGNAL_STOP_DEQUEUED;
Linus Torvalds's avatar
Linus Torvalds committed
534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581
 	}
	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);
}

582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608
/*
 * 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;
}
Linus Torvalds's avatar
Linus Torvalds committed
609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639
/*
 * 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;
640
	if (!valid_signal(sig))
Linus Torvalds's avatar
Linus Torvalds committed
641 642
		return error;
	error = -EPERM;
643
	if ((info == SEND_SIG_NOINFO || (!is_si_special(info) && SI_FROMUSER(info)))
Linus Torvalds's avatar
Linus Torvalds committed
644 645 646 647 648 649
	    && ((sig != SIGCONT) ||
		(current->signal->session != t->signal->session))
	    && (current->euid ^ t->suid) && (current->euid ^ t->uid)
	    && (current->uid ^ t->suid) && (current->uid ^ t->uid)
	    && !capable(CAP_KILL))
		return error;
650 651 652 653 654

	error = security_task_kill(t, info, sig);
	if (!error)
		audit_signal_info(sig, t); /* Let audit system see the signal */
	return error;
Linus Torvalds's avatar
Linus Torvalds committed
655 656 657 658
}

/* forward decl */
static void do_notify_parent_cldstop(struct task_struct *tsk,
659
				     int to_self,
Linus Torvalds's avatar
Linus Torvalds committed
660 661 662 663 664 665 666 667 668 669 670 671 672
				     int why);

/*
 * 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;

673
	if (p->signal->flags & SIGNAL_GROUP_EXIT)
Linus Torvalds's avatar
Linus Torvalds committed
674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709
		/*
		 * 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);
710
			do_notify_parent_cldstop(p, (p->ptrace & PT_PTRACED), CLD_STOPPED);
Linus Torvalds's avatar
Linus Torvalds committed
711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750
			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);
751
			do_notify_parent_cldstop(p, (p->ptrace & PT_PTRACED), CLD_CONTINUED);
Linus Torvalds's avatar
Linus Torvalds committed
752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779
			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;

	/*
	 * fast-pathed signals for kernel-internal things like SIGSTOP
	 * or SIGKILL.
	 */
780
	if (info == SEND_SIG_FORCED)
Linus Torvalds's avatar
Linus Torvalds committed
781 782 783 784 785 786 787 788 789 790 791
		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 &&
792
					     (is_si_special(info) ||
Linus Torvalds's avatar
Linus Torvalds committed
793 794 795 796
					      info->si_code >= 0)));
	if (q) {
		list_add_tail(&q->list, &signals->list);
		switch ((unsigned long) info) {
797
		case (unsigned long) SEND_SIG_NOINFO:
Linus Torvalds's avatar
Linus Torvalds committed
798 799 800 801 802 803
			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;
804
		case (unsigned long) SEND_SIG_PRIV:
Linus Torvalds's avatar
Linus Torvalds committed
805 806 807 808 809 810 811 812 813 814
			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;
		}
815 816
	} else if (!is_si_special(info)) {
		if (sig >= SIGRTMIN && info->si_code != SI_USER)
Linus Torvalds's avatar
Linus Torvalds committed
817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870
		/*
		 * 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;

	if (!irqs_disabled())
		BUG();
	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.
 */

int
force_sig_info(int sig, struct siginfo *info, struct task_struct *t)
{
	unsigned long int flags;
	int ret;

	spin_lock_irqsave(&t->sighand->siglock, flags);
871
	if (t->sighand->action[sig-1].sa.sa_handler == SIG_IGN) {
Linus Torvalds's avatar
Linus Torvalds committed
872
		t->sighand->action[sig-1].sa.sa_handler = SIG_DFL;
873 874
	}
	if (sigismember(&t->blocked, sig)) {
Linus Torvalds's avatar
Linus Torvalds committed
875 876
		sigdelset(&t->blocked, sig);
	}
877
	recalc_sigpending_tsk(t);
Linus Torvalds's avatar
Linus Torvalds committed
878 879 880 881 882 883 884 885 886
	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)
{
887
	force_sig_info(sig, SEND_SIG_FORCED, t);
Linus Torvalds's avatar
Linus Torvalds committed
888 889 890 891 892 893 894 895 896 897
}

/*
 * 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.
 */
898 899 900 901 902 903 904 905 906 907 908 909
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);
}
Linus Torvalds's avatar
Linus Torvalds committed
910 911 912 913 914 915 916 917 918 919 920 921

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.
	 */
922
	if (wants_signal(sig, p))
Linus Torvalds's avatar
Linus Torvalds committed
923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939
		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;
		BUG_ON(t->tgid != p->tgid);

940
		while (!wants_signal(sig, t)) {
Linus Torvalds's avatar
Linus Torvalds committed
941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073
			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;

		/*
		 * We don't want to notify the parent, since we are
		 * killed as part of a thread group due to another
		 * thread doing an execve() or similar. So set the
		 * exit signal to -1 to allow immediate reaping of
		 * the process.  But don't detach the thread group
		 * leader.
		 */
		if (t != p->group_leader)
			t->exit_signal = -1;

1074
		/* SIGKILL will be handled before any pending SIGSTOP */
Linus Torvalds's avatar
Linus Torvalds committed
1075 1076 1077 1078 1079 1080
		sigaddset(&t->pending.signal, SIGKILL);
		signal_wake_up(t, 1);
	}
}

/*
Ingo Molnar's avatar
Ingo Molnar committed
1081
 * Must be called under rcu_read_lock() or with tasklist_lock read-held.
Linus Torvalds's avatar
Linus Torvalds committed
1082
 */
1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100
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;
}

Linus Torvalds's avatar
Linus Torvalds committed
1101 1102 1103 1104 1105 1106
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);
1107 1108 1109 1110 1111 1112

	if (!ret && sig) {
		ret = -ESRCH;
		if (lock_task_sighand(p, &flags)) {
			ret = __group_send_sig_info(sig, info, p);
			unlock_task_sighand(p, &flags);
1113
		}
Linus Torvalds's avatar
Linus Torvalds committed
1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157
	}

	return ret;
}

/*
 * kill_pg_info() sends a signal to a process group: this is what the tty
 * control characters do (^C, ^Z etc)
 */

int __kill_pg_info(int sig, struct siginfo *info, pid_t pgrp)
{
	struct task_struct *p = NULL;
	int retval, success;

	if (pgrp <= 0)
		return -EINVAL;

	success = 0;
	retval = -ESRCH;
	do_each_task_pid(pgrp, PIDTYPE_PGID, p) {
		int err = group_send_sig_info(sig, info, p);
		success |= !err;
		retval = err;
	} while_each_task_pid(pgrp, PIDTYPE_PGID, p);
	return success ? 0 : retval;
}

int
kill_pg_info(int sig, struct siginfo *info, pid_t pgrp)
{
	int retval;

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

	return retval;
}

int
kill_proc_info(int sig, struct siginfo *info, pid_t pid)
{
	int error;
Ingo Molnar's avatar
Ingo Molnar committed
1158
	int acquired_tasklist_lock = 0;
Linus Torvalds's avatar
Linus Torvalds committed
1159 1160
	struct task_struct *p;

Ingo Molnar's avatar
Ingo Molnar committed
1161
	rcu_read_lock();
1162
	if (unlikely(sig_needs_tasklist(sig))) {
Ingo Molnar's avatar
Ingo Molnar committed
1163 1164 1165
		read_lock(&tasklist_lock);
		acquired_tasklist_lock = 1;
	}
Linus Torvalds's avatar
Linus Torvalds committed
1166 1167 1168 1169
	p = find_task_by_pid(pid);
	error = -ESRCH;
	if (p)
		error = group_send_sig_info(sig, info, p);
Ingo Molnar's avatar
Ingo Molnar committed
1170 1171 1172
	if (unlikely(acquired_tasklist_lock))
		read_unlock(&tasklist_lock);
	rcu_read_unlock();
Linus Torvalds's avatar
Linus Torvalds committed
1173 1174 1175
	return error;
}

1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191
/* like kill_proc_info(), but doesn't use uid/euid of "current" */
int kill_proc_info_as_uid(int sig, struct siginfo *info, pid_t pid,
		      uid_t uid, uid_t euid)
{
	int ret = -EINVAL;
	struct task_struct *p;

	if (!valid_signal(sig))
		return ret;

	read_lock(&tasklist_lock);
	p = find_task_by_pid(pid);
	if (!p) {
		ret = -ESRCH;
		goto out_unlock;
	}
1192
	if ((info == SEND_SIG_NOINFO || (!is_si_special(info) && SI_FROMUSER(info)))
1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208
	    && (euid != p->suid) && (euid != p->uid)
	    && (uid != p->suid) && (uid != p->uid)) {
		ret = -EPERM;
		goto out_unlock;
	}
	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;
}
EXPORT_SYMBOL_GPL(kill_proc_info_as_uid);
Linus Torvalds's avatar
Linus Torvalds committed
1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260

/*
 * 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)
{
	if (!pid) {
		return kill_pg_info(sig, info, process_group(current));
	} 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);
		return count ? retval : -ESRCH;
	} else if (pid < 0) {
		return kill_pg_info(sig, info, -pid);
	} else {
		return kill_proc_info(sig, info, pid);
	}
}

/*
 * 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).
	 */
1261
	if (!valid_signal(sig))
Linus Torvalds's avatar
Linus Torvalds committed
1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277
		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;
}

1278 1279 1280
#define __si_special(priv) \
	((priv) ? SEND_SIG_PRIV : SEND_SIG_NOINFO)

Linus Torvalds's avatar
Linus Torvalds committed
1281 1282 1283
int
send_sig(int sig, struct task_struct *p, int priv)
{
1284
	return send_sig_info(sig, __si_special(priv), p);
Linus Torvalds's avatar
Linus Torvalds committed
1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303
}

/*
 * 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)
{
1304
	force_sig_info(sig, SEND_SIG_PRIV, p);
Linus Torvalds's avatar
Linus Torvalds committed
1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328
}

/*
 * 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;
}

int
kill_pg(pid_t pgrp, int sig, int priv)
{
1329
	return kill_pg_info(sig, __si_special(priv), pgrp);
Linus Torvalds's avatar
Linus Torvalds committed
1330 1331 1332 1333 1334
}

int
kill_proc(pid_t pid, int sig, int priv)
{
1335
	return kill_proc_info(sig, __si_special(priv), pid);
Linus Torvalds's avatar
Linus Torvalds committed
1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365
}

/*
 * 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))) {
Oleg Nesterov's avatar
Oleg Nesterov committed
1366 1367 1368
		spinlock_t *lock = &current->sighand->siglock;
		read_lock(&tasklist_lock);
		spin_lock_irqsave(lock, flags);
Linus Torvalds's avatar
Linus Torvalds committed
1369 1370
		if (!list_empty(&q->list))
			list_del_init(&q->list);
Oleg Nesterov's avatar
Oleg Nesterov committed
1371
		spin_unlock_irqrestore(lock, flags);
Linus Torvalds's avatar
Linus Torvalds committed
1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382
		read_unlock(&tasklist_lock);
	}
	q->flags &= ~SIGQUEUE_PREALLOC;
	__sigqueue_free(q);
}

int
send_sigqueue(int sig, struct sigqueue *q, struct task_struct *p)
{
	unsigned long flags;
	int ret = 0;
Ingo Molnar's avatar
Ingo Molnar committed
1383
	struct sighand_struct *sh;
Linus Torvalds's avatar
Linus Torvalds committed
1384 1385

	BUG_ON(!(q->flags & SIGQUEUE_PREALLOC));
Ingo Molnar's avatar
Ingo Molnar committed
1386 1387 1388 1389 1390 1391 1392 1393 1394 1395

	/*
	 * 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();
1396 1397 1398 1399 1400 1401

	if (unlikely(p->flags & PF_EXITING)) {
		ret = -1;
		goto out_err;
	}

Ingo Molnar's avatar
Ingo Molnar committed
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
retry:
	sh = rcu_dereference(p->sighand);

	spin_lock_irqsave(&sh->siglock, flags);
	if (p->sighand != sh) {
		/* We raced with exec() in a multithreaded process... */
		spin_unlock_irqrestore(&sh->siglock, flags);
		goto retry;
	}

	/*
	 * We do the check here again to handle the following scenario:
	 *
	 * CPU 0		CPU 1
	 * send_sigqueue
	 * check PF_EXITING
	 * interrupt		exit code running
	 *			__exit_signal
	 *			lock sighand->siglock
	 *			unlock sighand->siglock
	 * lock sh->siglock
	 * add(tsk->pending) 	flush_sigqueue(tsk->pending)
	 *
	 */

	if (unlikely(p->flags & PF_EXITING)) {
		ret = -1;
		goto out;
	}
1431

Linus Torvalds's avatar
Linus Torvalds committed
1432 1433 1434 1435 1436 1437 1438 1439 1440
	if (unlikely(!list_empty(&q->list))) {
		/*
		 * If an SI_TIMER entry is already queue just increment
		 * the overrun count.
		 */
		if (q->info.si_code != SI_TIMER)
			BUG();
		q->info.si_overrun++;
		goto out;
1441
	}
Linus Torvalds's avatar
Linus Torvalds committed
1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453
	/* Short-circuit ignored signals.  */
	if (sig_ignored(p, sig)) {
		ret = 1;
		goto out;
	}

	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:
Ingo Molnar's avatar
Ingo Molnar committed
1454
	spin_unlock_irqrestore(&sh->siglock, flags);
1455
out_err:
Ingo Molnar's avatar
Ingo Molnar committed
1456
	rcu_read_unlock();
1457 1458

	return ret;
Linus Torvalds's avatar
Linus Torvalds committed
1459 1460 1461 1462 1463 1464 1465 1466 1467
}

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));
Ingo Molnar's avatar
Ingo Molnar committed
1468

Linus Torvalds's avatar
Linus Torvalds committed
1469
	read_lock(&tasklist_lock);
Ingo Molnar's avatar
Ingo Molnar committed
1470
	/* Since it_lock is held, p->sighand cannot be NULL. */
Linus Torvalds's avatar
Linus Torvalds committed
1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503
	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.
		 */
		if (q->info.si_code != SI_TIMER)
			BUG();
		q->info.si_overrun++;
		goto out;
	} 

	/*
	 * 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);
Ingo Molnar's avatar
Ingo Molnar committed
1504
	return ret;
Linus Torvalds's avatar
Linus Torvalds committed
1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557
}

/*
 * 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);
1558
	if (!tsk->ptrace && sig == SIGCHLD &&
Linus Torvalds's avatar
Linus Torvalds committed
1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579
	    (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;
	}
1580
	if (valid_signal(sig) && sig > 0)
Linus Torvalds's avatar
Linus Torvalds committed
1581 1582 1583 1584 1585
		__group_send_sig_info(sig, &info, tsk->parent);
	__wake_up_parent(tsk, tsk->parent);
	spin_unlock_irqrestore(&psig->siglock, flags);
}

1586
static void do_notify_parent_cldstop(struct task_struct *tsk, int to_self, int why)
Linus Torvalds's avatar
Linus Torvalds committed
1587 1588 1589
{
	struct siginfo info;
	unsigned long flags;
1590
	struct task_struct *parent;
Linus Torvalds's avatar
Linus Torvalds committed
1591 1592
	struct sighand_struct *sighand;

1593 1594 1595 1596 1597 1598 1599
	if (to_self)
		parent = tsk->parent;
	else {
		tsk = tsk->group_leader;
		parent = tsk->real_parent;
	}

Linus Torvalds's avatar
Linus Torvalds committed
1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667
	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);
}

/*
 * 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);
	read_lock(&tasklist_lock);
	if (likely(current->ptrace & PT_PTRACED) &&
	    likely(current->parent != current->real_parent ||
		   !(current->ptrace & PT_ATTACHED)) &&
	    (likely(current->parent->signal != current->signal) ||
	     !unlikely(current->signal->flags & SIGNAL_GROUP_EXIT))) {
1668
		do_notify_parent_cldstop(current, 1, CLD_TRAPPED);
Linus Torvalds's avatar
Linus Torvalds committed
1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716
		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.
	 */
	recalc_sigpending();
}

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)
{
1717 1718
	int to_self;

Linus Torvalds's avatar
Linus Torvalds committed
1719 1720 1721 1722 1723
	/*
	 * 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.
	 */
1724 1725 1726 1727 1728 1729
	if (stop_count < 0 || (current->ptrace & PT_PTRACED))
		to_self = 1;
	else if (stop_count == 0)
		to_self = 0;
	else
		goto out;
Linus Torvalds's avatar
Linus Torvalds committed
1730

1731 1732 1733 1734 1735
	read_lock(&tasklist_lock);
	do_notify_parent_cldstop(current, to_self, CLD_STOPPED);
	read_unlock(&tasklist_lock);

out:
Linus Torvalds's avatar
Linus Torvalds committed
1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754