arch

/*
 *  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>
#include <linux/signal.h>
#include <linux/signalfd.h>
#include <linux/capability.h>
#include <linux/freezer.h>
#include <linux/pid_namespace.h>
#include <linux/nsproxy.h>

#include <asm/param.h>
#include <asm/uaccess.h>
#include <asm/unistd.h>
#include <asm/siginfo.h>
#include "audit.h"	/* audit_signal_info() */

/*
 * SLAB caches for signal bits.
 */

static struct kmem_cache *sigqueue_cachep;

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

	/* 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));
}

static int sig_ignored(struct task_struct *t, int sig)
{
	/*
	 * 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) || sigismember(&t->real_blocked, sig))
		return 0;

	return __sig_ignored(t, 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))

static int recalc_sigpending_tsk(struct task_struct *t)
{
	if (t->signal->group_stop_count > 0 ||
	    PENDING(&t->pending, &t->blocked) ||
	    PENDING(&t->signal->shared_pending, &t->blocked)) {
		set_tsk_thread_flag(t, TIF_SIGPENDING);
		return 1;
	}
	/*
	 * 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.
	 */
	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);
}

void recalc_sigpending(void)
{
	if (!recalc_sigpending_tsk(current) && !freezing(current))
		clear_thread_flag(TIF_SIGPENDING);

}

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

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;
}

static struct sigqueue *__sigqueue_alloc(struct task_struct *t, gfp_t flags,
					 int override_rlimit)
{
	struct sigqueue *q = NULL;
	struct user_struct *user;

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

static void __sigqueue_free(struct sigqueue *q)
{
	if (q->flags & SIGQUEUE_PREALLOC)
		return;
	atomic_dec(&q->user->sigpending);
	free_uid(q->user);
	kmem_cache_free(sigqueue_cachep, q);
}

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.
 */
void flush_signals(struct task_struct *t)
{
	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);
}

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);
}

/*
 * 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++;
	}
}

int unhandled_signal(struct task_struct *tsk, int sig)
{
	if (is_global_init(tsk))
		return 1;
	if (tsk->ptrace & PT_PTRACED)
		return 0;
	return (tsk->sighand->action[sig-1].sa.sa_handler == SIG_IGN) ||
		(tsk->sighand->action[sig-1].sa.sa_handler == SIG_DFL);
}


/* 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);
}

static int collect_signal(int sig, struct sigpending *list, siginfo_t *info)
{
	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 = next_signal(pending, mask);

	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)
{
	int signr;

	/* We only dequeue private signals from ourselves, we don't let
	 * signalfd steal them
	 */
	signr = __dequeue_signal(&tsk->pending, mask, info);
	if (!signr) {
		signr = __dequeue_signal(&tsk->signal->shared_pending,
					 mask, info);
		/*
		 * 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);
			}
		}
	}

	recalc_sigpending();
	if (!signr)
		return 0;

	if (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;
	}
	if ((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/killable
	 * 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_WAKEKILL;
	if (!wake_up_state(t, mask))
		kick_process(t);
}

/*
 * 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;
}
/*
 * 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)
{
	struct pid *sid;
	int error;

	if (!valid_signal(sig))
		return -EINVAL;

	if (info != SEND_SIG_NOINFO && (is_si_special(info) || SI_FROMKERNEL(info)))
		return 0;

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

	if ((current->euid ^ t->suid) && (current->euid ^ t->uid) &&
	    (current->uid  ^ t->suid) && (current->uid  ^ t->uid) &&
	    !capable(CAP_KILL)) {
		switch (sig) {
		case SIGCONT:
			sid = task_session(t);
			/*
			 * We don't return the error if sid == NULL. The
			 * task was unhashed, the caller must notice this.
			 */
			if (!sid || sid == task_session(current))
				break;
		default:
			return -EPERM;
		}
	}

	return security_task_kill(t, info, sig, 0);
}

/* forward decl */
static void do_notify_parent_cldstop(struct task_struct *tsk, 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.
 *
 * Returns true if the signal should be actually delivered, otherwise
 * it should be dropped.
 */
static int prepare_signal(int sig, struct task_struct *p)
{
	struct signal_struct *signal = p->signal;
	struct task_struct *t;

	if (unlikely(signal->flags & SIGNAL_GROUP_EXIT)) {
		/*
		 * The process is in the middle of dying, nothing to do.
		 */
	} else if (sig_kernel_stop(sig)) {
		/*
		 * This is a stop signal.  Remove SIGCONT from all queues.
		 */
		rm_from_queue(sigmask(SIGCONT), &signal->shared_pending);
		t = p;
		do {
			rm_from_queue(sigmask(SIGCONT), &t->pending);
		} while_each_thread(p, t);
	} else if (sig == SIGCONT) {
		unsigned int why;
		/*
		 * Remove all stop signals from all queues,
		 * and wake all threads.
		 */
		rm_from_queue(SIG_KERNEL_STOP_MASK, &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);
		} while_each_thread(p, t);

		/*
		 * Notify the parent with CLD_CONTINUED if we were stopped.
		 *
		 * If we were in the middle of a group stop, we pretend it
		 * was already finished, and then continued. Since SIGCHLD
		 * doesn't queue we report only CLD_STOPPED, as if the next
		 * CLD_CONTINUED was dropped.
		 */
		why = 0;
		if (signal->flags & SIGNAL_STOP_STOPPED)
			why |= SIGNAL_CLD_CONTINUED;
		else if (signal->group_stop_count)
			why |= SIGNAL_CLD_STOPPED;

		if (why) {
			/*
			 * The first thread which returns from finish_stop()
			 * will take ->siglock, notice SIGNAL_CLD_MASK, and
			 * notify its parent. See get_signal_to_deliver().
			 */
			signal->flags = why | SIGNAL_STOP_CONTINUED;
			signal->group_stop_count = 0;
			signal->group_exit_code = 0;
		} 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.
			 */
			signal->flags &= ~SIGNAL_STOP_DEQUEUED;
		}
	}

	return !sig_ignored(p, sig);
}

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

static void complete_signal(int sig, struct task_struct *p, int group)
{
	struct signal_struct *signal = p->signal;
	struct task_struct *t;

	/*
	 * Now find a thread we can wake up to take the signal off the queue.
	 *
	 * If the main thread wants the signal, it gets first crack.
	 * Probably the least surprising to the average bear.
	 */
	if (wants_signal(sig, p))
		t = p;
	else if (!group || 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 = signal->curr_target;
		while (!wants_signal(sig, t)) {
			t = next_thread(t);
			if (t == signal->curr_target)
				/*
				 * No thread needs to be woken.
				 * Any eligible threads will see
				 * the signal in the queue soon.
				 */
				return;
		}
		signal->curr_target = t;
	}

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

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

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

static int send_signal(int sig, struct siginfo *info, struct task_struct *t,
			int group)
{
	struct sigpending *pending;
	struct sigqueue *q;

	assert_spin_locked(&t->sighand->siglock);
	if (!prepare_signal(sig, t))
		return 0;

	pending = group ? &t->signal->shared_pending : &t->pending;
	/*
	 * Short-circuit ignored signals and support queuing
	 * exactly one non-rt signal, so that we can get more
	 * detailed information about the cause of the signal.
	 */
	if (legacy_queue(pending, sig))
		return 0;
	/*
	 * fast-pathed signals for kernel-internal things like SIGSTOP
	 * or SIGKILL.
	 */
	if (info == SEND_SIG_FORCED)
		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 &&
					     (is_si_special(info) ||
					      info->si_code >= 0)));
	if (q) {
		list_add_tail(&q->list, &pending->list);
		switch ((unsigned long) info) {
		case (unsigned long) SEND_SIG_NOINFO:
			q->info.si_signo = sig;
			q->info.si_errno = 0;
			q->info.si_code = SI_USER;
			q->info.si_pid = task_pid_vnr(current);
			q->info.si_uid = current->uid;
			break;
		case (unsigned long) SEND_SIG_PRIV:
			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;
		}
	} else if (!is_si_special(info)) {
		if (sig >= SIGRTMIN && info->si_code != SI_USER)
		/*
		 * Queue overflow, abort.  We may abort if the signal was rt
		 * and sent by user using something other than kill().
		 */
			return -EAGAIN;
	}

out_set:
	signalfd_notify(t, sig);
	sigaddset(&pending->signal, sig);
	complete_signal(sig, t, group);
	return 0;
}

int print_fatal_signals;

static void print_fatal_signal(struct pt_regs *regs, int signr)
{
	printk("%s/%d: potentially unexpected fatal signal %d.\n",
		current->comm, task_pid_nr(current), signr);

#if defined(__i386__) && !defined(__arch_um__)
	printk("code at %08lx: ", regs->ip);
	{
		int i;
		for (i = 0; i < 16; i++) {
			unsigned char insn;

			__get_user(insn, (unsigned char *)(regs->ip + i));
			printk("%02x ", insn);
		}
	}
#endif
	printk("\n");
	show_regs(regs);
}

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

	return 1;
}

__setup("print-fatal-signals=", setup_print_fatal_signals);

int
__group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p)
{
	return send_signal(sig, info, p, 1);
}

static int
specific_send_sig_info(int sig, struct siginfo *info, struct task_struct *t)
{
	return send_signal(sig, info, t, 0);
}

/*
 * Force a signal that the process can't ignore: if necessary
 * we unblock the signal and change any SIG_IGN to SIG_DFL.
 *
 * 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,
 * that is why we also clear SIGNAL_UNKILLABLE.
 */
int
force_sig_info(int sig, struct siginfo *info, struct task_struct *t)
{
	unsigned long int flags;
	int ret, blocked, ignored;
	struct k_sigaction *action;

	spin_lock_irqsave(&t->sighand->siglock, flags);
	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);
			recalc_sigpending_and_wake(t);
		}
	}
	if (action->sa.sa_handler == SIG_DFL)
		t->signal->flags &= ~SIGNAL_UNKILLABLE;
	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)
{
	force_sig_info(sig, SEND_SIG_FORCED, t);
}

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

	p->signal->group_stop_count = 0;

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

		/* SIGKILL will be handled before any pending SIGSTOP */
		sigaddset(&t->pending.signal, SIGKILL);
		signal_wake_up(t, 1);
	}
}

int __fatal_signal_pending(struct task_struct *tsk)
{
	return sigismember(&tsk->pending.signal, SIGKILL);
}
EXPORT_SYMBOL(__fatal_signal_pending);

struct sighand_struct *lock_task_sighand(struct task_struct *tsk, unsigned long *flags)
{
	struct sighand_struct *sighand;

	rcu_read_lock();
	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);
	}
	rcu_read_unlock();

	return sighand;
}

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);

	if (!ret && sig) {
		ret = -ESRCH;
		if (lock_task_sighand(p, &flags)) {
			ret = __group_send_sig_info(sig, info, p);
			unlock_task_sighand(p, &flags);
		}
	}

	return ret;
}

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

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

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

int kill_pid_info(int sig, struct siginfo *info, struct pid *pid)
{
	int error = -ESRCH;
	struct task_struct *p;

	rcu_read_lock();
retry:
	p = pid_task(pid, PIDTYPE_PID);
	if (p) {
		error = group_send_sig_info(sig, info, p);
		if (unlikely(error == -ESRCH))
			/*
			 * The task was unhashed in between, try again.
			 * If it is dead, pid_task() will return NULL,
			 * if we race with de_thread() it will find the
			 * new leader.
			 */
			goto retry;
	}
	rcu_read_unlock();

	return error;
}

int
kill_proc_info(int sig, struct siginfo *info, pid_t pid)
{
	int error;
	rcu_read_lock();
	error = kill_pid_info(sig, info, find_vpid(pid));
	rcu_read_unlock();
	return error;
}

/* 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,
		      uid_t uid, uid_t euid, u32 secid)
{
	int ret = -EINVAL;
	struct task_struct *p;

	if (!valid_signal(sig))
		return ret;

	read_lock(&tasklist_lock);
	p = pid_task(pid, PIDTYPE_PID);
	if (!p) {
		ret = -ESRCH;
		goto out_unlock;
	}
	if ((info == SEND_SIG_NOINFO || (!is_si_special(info) && SI_FROMUSER(info)))
	    && (euid != p->suid) && (euid != p->uid)
	    && (uid != p->suid) && (uid != p->uid)) {
		ret = -EPERM;
		goto out_unlock;
	}
	ret = security_task_kill(p, info, sig, secid);
	if (ret)
		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_pid_info_as_uid);

/*
 * 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)
{
	int ret;

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

	read_lock(&tasklist_lock);
	if (pid != -1) {
		ret = __kill_pgrp_info(sig, info,
				pid ? find_vpid(-pid) : task_pgrp(current));
	} else {
		int retval = 0, count = 0;
		struct task_struct * p;

		for_each_process(p) {
			if (p->pid > 1 && !same_thread_group(p, current)) {
				int err = group_send_sig_info(sig, info, p);
				++count;
				if (err != -EPERM)
					retval = err;
			}
		}
		ret = count ? retval : -ESRCH;
	}
	read_unlock(&tasklist_lock);

	return ret;
}

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

/*
 * The caller must ensure the task can't exit.
 */
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).
	 */
	if (!valid_signal(sig))
		return -EINVAL;

	spin_lock_irqsave(&p->sighand->siglock, flags);
	ret = specific_send_sig_info(sig, info, p);
	spin_unlock_irqrestore(&p->sighand->siglock, flags);
	return ret;
}

#define __si_special(priv) \
	((priv) ? SEND_SIG_PRIV : SEND_SIG_NOINFO)

int
send_sig(int sig, struct task_struct *p, int priv)
{
	return send_sig_info(sig, __si_special(priv), p);
}

void
force_sig(int sig, struct task_struct *p)
{
	force_sig_info(sig, SEND_SIG_PRIV, p);
}

/*
 * 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_pgrp(struct pid *pid, int sig, int priv)
{
	int ret;

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

	return ret;
}
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);

int
kill_proc(pid_t pid, int sig, int priv)
{
	int ret;

	rcu_read_lock();
	ret = kill_pid_info(sig, __si_special(priv), find_pid(pid));
	rcu_read_unlock();
	return ret;
}

/*
 * 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;
	spinlock_t *lock = &current->sighand->siglock;

	BUG_ON(!(q->flags & SIGQUEUE_PREALLOC));
	/*
	 * If the signal is still pending remove it from the
	 * pending queue. We must hold ->siglock while testing
	 * q->list to serialize with collect_signal().
	 */
	spin_lock_irqsave(lock, flags);
	if (!list_empty(&q->list))
		list_del_init(&q->list);
	spin_unlock_irqrestore(lock, flags);

	q->flags &= ~SIGQUEUE_PREALLOC;
	__sigqueue_free(q);
}

int send_sigqueue(struct sigqueue *q, struct task_struct *t, int group)
{
	int sig = q->info.si_signo;
	struct sigpending *pending;
	unsigned long flags;
	int ret;

	BUG_ON(!(q->flags & SIGQUEUE_PREALLOC));

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

	ret = 1; /* the signal is ignored */
	if (!prepare_signal(sig, t))
		goto out;

	ret = 0;
	if (unlikely(!list_empty(&q->list))) {
		/*
		 * If an SI_TIMER entry is already queue just increment
		 * the overrun count.
		 */
		BUG_ON(q->info.si_code != SI_TIMER);
		q->info.si_overrun++;
		goto out;
	}

	signalfd_notify(t, sig);
	pending = group ? &t->signal->shared_pending : &t->pending;
	list_add_tail(&q->list, &pending->list);
	sigaddset(&pending->signal, sig);
	complete_signal(sig, t, group);
out:
	unlock_task_sighand(t, &flags);
ret:
	return ret;
}

/*
 * 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(task_is_stopped_or_traced(tsk));

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

	info.si_signo = sig;
	info.si_errno = 0;
	/*
	 * we are under tasklist_lock here so our parent is tied to
	 * us and cannot exit and release its namespace.
	 *
	 * the only it can is to switch its nsproxy with sys_unshare,
	 * bu uncharing pid namespaces is not allowed, so we'll always
	 * see relevant namespace
	 *
	 * write_lock() currently calls preempt_disable() which is the
	 * same as rcu_read_lock(), but according to Oleg, this is not
	 * correct to rely on this
	 */
	rcu_read_lock();
	info.si_pid = task_pid_nr_ns(tsk, tsk->parent->nsproxy->pid_ns);
	rcu_read_unlock();

	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);
	if (!tsk->ptrace && sig == SIGCHLD &&
	    (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;
	}
	if (valid_signal(sig) && sig > 0)
		__group_send_sig_info(sig, &info, tsk->parent);
	__wake_up_parent(tsk, tsk->parent);
	spin_unlock_irqrestore(&psig->siglock, flags);
}

static void do_notify_parent_cldstop(struct task_struct *tsk, int why)
{
	struct siginfo info;
	unsigned long flags;
	struct task_struct *parent;
	struct sighand_struct *sighand;

	if (tsk->ptrace & PT_PTRACED)
		parent = tsk->parent;
	else {
		tsk = tsk->group_leader;
		parent = tsk->real_parent;
	}

	info.si_signo = SIGCHLD;
	info.si_errno = 0;
	/*
	 * see comment in do_notify_parent() abot the following 3 lines
	 */
	rcu_read_lock();
	info.si_pid = task_pid_nr_ns(tsk, tsk->parent->nsproxy->pid_ns);
	rcu_read_unlock();

	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);
}
Mode	Name	Size
d---------	alpha	342	log stats plain
d---------	arm	1352	log stats plain
d---------	arm26	382	log stats plain
d---------	cris	281	log stats plain
d---------	frv	311	log stats plain
d---------	h8300	419	log stats plain
d---------	i386	708	log stats plain
d---------	ia64	569	log stats plain
d---------	m32r	542	log stats plain
d---------	m68k	766	log stats plain
d---------	m68knommu	276	log stats plain
d---------	mips	1283	log stats plain
d---------	parisc	484	log stats plain
d---------	powerpc	404	log stats plain
d---------	ppc	536	log stats plain
d---------	s390	410	log stats plain
d---------	sh	436	log stats plain
d---------	sh64	451	log stats plain
d---------	sparc	338	log stats plain
d---------	sparc64	407	log stats plain
d---------	um	993	log stats plain
d---------	v850	243	log stats plain
d---------	x86_64	401	log stats plain
d---------	xtensa	308	log stats plain