signal.c

Kernel code of linux kernel

	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, pid_t 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);

/*
 * 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));
	/*
	 * We must hold ->siglock while testing q->list
	 * to serialize with collect_signal() or with
	 * __exit_signal()->flush_sigqueue().
	 */
	spin_lock_irqsave(lock, flags);
	q->flags &= ~SIGQUEUE_PREALLOC;
	/*
	 * If it is queued it will be freed when dequeued,
	 * like the "regular" sigqueue.
	 */
	if (!list_empty(&q->list))
		q = NULL;
	spin_unlock_irqrestore(lock, flags);

	if (q)
		__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;
	}
	q->info.si_overrun = 0;

	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.
 *
 * Returns -1 if our parent ignored us and so we've switched to
 * self-reaping, or else @sig.
 */
int do_notify_parent(struct task_struct *tsk, int sig)
{
	struct siginfo info;
	unsigned long flags;
	struct sighand_struct *psig;
	int ret = sig;

	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;

	info.si_utime = cputime_to_clock_t(cputime_add(tsk->utime,
						       tsk->signal->utime));
	info.si_stime = cputime_to_clock_t(cputime_add(tsk->stime,
						       tsk->signal->stime));

	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).
		 */
		ret = tsk->exit_signal = -1;
		if (psig->action[SIGCHLD-1].sa.sa_handler == SIG_IGN)
			sig = -1;
	}
	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);

	return ret;
}

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;

	info.si_utime = cputime_to_clock_t(tsk->utime);
	info.si_stime = cputime_to_clock_t(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);
}

static inline int may_ptrace_stop(void)
{
	if (!likely(current->ptrace & PT_PTRACED))
		return 0;
	/*
	 * Are we in the middle of do_coredump?
	 * If so and our tracer is also part of the coredump stopping
	 * is a deadlock situation, and pointless because our tracer
	 * is dead so don't allow us to stop.
	 * If SIGKILL was already sent before the caller unlocked
	 * ->siglock we must see ->core_state != NULL. Otherwise it
	 * is safe to enter schedule().
	 */
	if (unlikely(current->mm->core_state) &&
	    unlikely(current->mm == current->parent->mm))
		return 0;

	return 1;
}

/*
 * Return nonzero if there is a SIGKILL that should be waking us up.
 * Called with the siglock held.
 */
static int sigkill_pending(struct task_struct *tsk)
{
	return	sigismember(&tsk->pending.signal, SIGKILL) ||
		sigismember(&tsk->signal->shared_pending.signal, SIGKILL);
}

/*
 * 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 keep current->exit_code unless clear_code.
 */
static void ptrace_stop(int exit_code, int clear_code, siginfo_t *info)
{
	if (arch_ptrace_stop_needed(exit_code, info)) {
		/*
		 * The arch code has something special to do before a
		 * ptrace stop.  This is allowed to block, e.g. for faults
		 * on user stack pages.  We can't keep the siglock while
		 * calling arch_ptrace_stop, so we must release it now.
		 * To preserve proper semantics, we must do this before
		 * any signal bookkeeping like checking group_stop_count.
		 * Meanwhile, a SIGKILL could come in before we retake the
		 * siglock.  That must prevent us from sleeping in TASK_TRACED.
		 * So after regaining the lock, we must check for SIGKILL.
		 */
		spin_unlock_irq(&current->sighand->siglock);
		arch_ptrace_stop(exit_code, info);
		spin_lock_irq(&current->sighand->siglock);
		if (sigkill_pending(current))
			return;
	}

	/*
	 * 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);