1 files changed, 127 insertions, 114 deletions

diff --git a/kernel/signal.c b/kernel/signal.c
index 64c5deeaca5..6b982f2cf52 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -22,12 +22,14 @@
 #include <linux/ptrace.h>
 #include <linux/signal.h>
 #include <linux/signalfd.h>
+#include <linux/ratelimit.h>
 #include <linux/tracehook.h>
 #include <linux/capability.h>
 #include <linux/freezer.h>
 #include <linux/pid_namespace.h>
 #include <linux/nsproxy.h>
-#include <trace/events/sched.h>
+#define CREATE_TRACE_POINTS
+#include <trace/events/signal.h>
 
 #include <asm/param.h>
 #include <asm/uaccess.h>
@@ -41,6 +43,8 @@
 
 static struct kmem_cache *sigqueue_cachep;
 
+int print_fatal_signals __read_mostly;
+
 static void __user *sig_handler(struct task_struct *t, int sig)
 {
 	return t->sighand->action[sig - 1].sa.sa_handler;
@@ -159,7 +163,7 @@ 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) {
@@ -184,17 +188,31 @@ int next_signal(struct sigpending *pending, sigset_t *mask)
 			sig = ffz(~x) + 1;
 		break;
 	}
-	
+
 	return sig;
 }
 
+static inline void print_dropped_signal(int sig)
+{
+	static DEFINE_RATELIMIT_STATE(ratelimit_state, 5 * HZ, 10);
+
+	if (!print_fatal_signals)
+		return;
+
+	if (!__ratelimit(&ratelimit_state))
+		return;
+
+	printk(KERN_INFO "%s/%d: reached RLIMIT_SIGPENDING, dropped signal %d\n",
+				current->comm, current->pid, sig);
+}
+
 /*
  * allocate a new signal queue record
  * - this may be called without locks if and only if t == current, otherwise an
  *   appopriate lock must be held to stop the target task from exiting
  */
-static struct sigqueue *__sigqueue_alloc(struct task_struct *t, gfp_t flags,
-					 int override_rlimit)
+static struct sigqueue *
+__sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimit)
 {
 	struct sigqueue *q = NULL;
 	struct user_struct *user;
@@ -207,10 +225,15 @@ static struct sigqueue *__sigqueue_alloc(struct task_struct *t, gfp_t flags,
 	 */
 	user = get_uid(__task_cred(t)->user);
 	atomic_inc(&user->sigpending);
+
 	if (override_rlimit ||
 	    atomic_read(&user->sigpending) <=
-			t->signal->rlim[RLIMIT_SIGPENDING].rlim_cur)
+			t->signal->rlim[RLIMIT_SIGPENDING].rlim_cur) {
 		q = kmem_cache_alloc(sigqueue_cachep, flags);
+	} else {
+		print_dropped_signal(sig);
+	}
+
 	if (unlikely(q == NULL)) {
 		atomic_dec(&user->sigpending);
 		free_uid(user);
@@ -705,7 +728,7 @@ static int prepare_signal(int sig, struct task_struct *p, int from_ancestor_ns)
 
 		if (why) {
 			/*
-			 * The first thread which returns from finish_stop()
+			 * The first thread which returns from do_signal_stop()
 			 * will take ->siglock, notice SIGNAL_CLD_MASK, and
 			 * notify its parent. See get_signal_to_deliver().
 			 */
@@ -834,7 +857,7 @@ static int __send_signal(int sig, struct siginfo *info, struct task_struct *t,
 	struct sigqueue *q;
 	int override_rlimit;
 
-	trace_sched_signal_send(sig, t);
+	trace_signal_generate(sig, info, t);
 
 	assert_spin_locked(&t->sighand->siglock);
 
@@ -869,7 +892,7 @@ static int __send_signal(int sig, struct siginfo *info, struct task_struct *t,
 	else
 		override_rlimit = 0;
 
-	q = __sigqueue_alloc(t, GFP_ATOMIC | __GFP_NOTRACK_FALSE_POSITIVE,
+	q = __sigqueue_alloc(sig, t, GFP_ATOMIC | __GFP_NOTRACK_FALSE_POSITIVE,
 		override_rlimit);
 	if (q) {
 		list_add_tail(&q->list, &pending->list);
@@ -896,12 +919,21 @@ static int __send_signal(int sig, struct siginfo *info, struct task_struct *t,
 			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().
-		 */
+		if (sig >= SIGRTMIN && info->si_code != SI_USER) {
+			/*
+			 * Queue overflow, abort.  We may abort if the
+			 * signal was rt and sent by user using something
+			 * other than kill().
+			 */
+			trace_signal_overflow_fail(sig, group, info);
 			return -EAGAIN;
+		} else {
+			/*
+			 * This is a silent loss of information.  We still
+			 * send the signal, but the *info bits are lost.
+			 */
+			trace_signal_lose_info(sig, group, info);
+		}
 	}
 
 out_set:
@@ -925,8 +957,6 @@ static int send_signal(int sig, struct siginfo *info, struct task_struct *t,
 	return __send_signal(sig, info, t, group, from_ancestor_ns);
 }
 
-int print_fatal_signals;
-
 static void print_fatal_signal(struct pt_regs *regs, int signr)
 {
 	printk("%s/%d: potentially unexpected fatal signal %d.\n",
@@ -971,6 +1001,20 @@ specific_send_sig_info(int sig, struct siginfo *info, struct task_struct *t)
 	return send_signal(sig, info, t, 0);
 }
 
+int do_send_sig_info(int sig, struct siginfo *info, struct task_struct *p,
+			bool group)
+{
+	unsigned long flags;
+	int ret = -ESRCH;
+
+	if (lock_task_sighand(p, &flags)) {
+		ret = send_signal(sig, info, p, group);
+		unlock_task_sighand(p, &flags);
+	}
+
+	return ret;
+}
+
 /*
  * Force a signal that the process can't ignore: if necessary
  * we unblock the signal and change any SIG_IGN to SIG_DFL.
@@ -1036,12 +1080,6 @@ void zap_other_threads(struct task_struct *p)
 	}
 }
 
-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;
@@ -1068,18 +1106,10 @@ struct sighand_struct *lock_task_sighand(struct task_struct *tsk, unsigned long
  */
 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);
+	int 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);
-		}
-	}
+	if (!ret && sig)
+		ret = do_send_sig_info(sig, info, p, true);
 
 	return ret;
 }
@@ -1224,15 +1254,9 @@ static int kill_something_info(int sig, struct siginfo *info, pid_t pid)
  * 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).
@@ -1240,10 +1264,7 @@ send_sig_info(int sig, struct siginfo *info, struct task_struct *p)
 	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;
+	return do_send_sig_info(sig, info, p, false);
 }
 
 #define __si_special(priv) \
@@ -1302,19 +1323,19 @@ 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 
+ * 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;
+	struct sigqueue *q = __sigqueue_alloc(-1, current, GFP_KERNEL, 0);
 
-	if ((q = __sigqueue_alloc(current, GFP_KERNEL, 0)))
+	if (q)
 		q->flags |= SIGQUEUE_PREALLOC;
-	return(q);
+
+	return q;
 }
 
 void sigqueue_free(struct sigqueue *q)
@@ -1383,15 +1404,6 @@ 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.
  *
@@ -1673,29 +1685,6 @@ void ptrace_notify(int exit_code)
 	spin_unlock_irq(&current->sighand->siglock);
 }
 
-static void
-finish_stop(int stop_count)
-{
-	/*
-	 * If there are no other threads in the group, or if there is
-	 * a group stop in progress and we are the last to stop,
-	 * report to the parent.  When ptraced, every thread reports itself.
-	 */
-	if (tracehook_notify_jctl(stop_count == 0, CLD_STOPPED)) {
-		read_lock(&tasklist_lock);
-		do_notify_parent_cldstop(current, CLD_STOPPED);
-		read_unlock(&tasklist_lock);
-	}
-
-	do {
-		schedule();
-	} while (try_to_freeze());
-	/*
-	 * Now we don't run again until continued.
-	 */
-	current->exit_code = 0;
-}
-
 /*
  * This performs the stopping for SIGSTOP and other stop signals.
  * We have to stop all threads in the thread group.
@@ -1705,15 +1694,9 @@ finish_stop(int stop_count)
 static int do_signal_stop(int signr)
 {
 	struct signal_struct *sig = current->signal;
-	int stop_count;
+	int notify;
 
-	if (sig->group_stop_count > 0) {
-		/*
-		 * There is a group stop in progress.  We don't need to
-		 * start another one.
-		 */
-		stop_count = --sig->group_stop_count;
-	} else {
+	if (!sig->group_stop_count) {
 		struct task_struct *t;
 
 		if (!likely(sig->flags & SIGNAL_STOP_DEQUEUED) ||
@@ -1725,7 +1708,7 @@ static int do_signal_stop(int signr)
 		 */
 		sig->group_exit_code = signr;
 
-		stop_count = 0;
+		sig->group_stop_count = 1;
 		for (t = next_thread(current); t != current; t = next_thread(t))
 			/*
 			 * Setting state to TASK_STOPPED for a group
@@ -1734,19 +1717,44 @@ static int do_signal_stop(int signr)
 			 */
 			if (!(t->flags & PF_EXITING) &&
 			    !task_is_stopped_or_traced(t)) {
-				stop_count++;
+				sig->group_stop_count++;
 				signal_wake_up(t, 0);
 			}
-		sig->group_stop_count = stop_count;
 	}
+	/*
+	 * If there are no other threads in the group, or if there is
+	 * a group stop in progress and we are the last to stop, report
+	 * to the parent.  When ptraced, every thread reports itself.
+	 */
+	notify = sig->group_stop_count == 1 ? CLD_STOPPED : 0;
+	notify = tracehook_notify_jctl(notify, CLD_STOPPED);
+	/*
+	 * tracehook_notify_jctl() can drop and reacquire siglock, so
+	 * we keep ->group_stop_count != 0 before the call. If SIGCONT
+	 * or SIGKILL comes in between ->group_stop_count == 0.
+	 */
+	if (sig->group_stop_count) {
+		if (!--sig->group_stop_count)
+			sig->flags = SIGNAL_STOP_STOPPED;
+		current->exit_code = sig->group_exit_code;
+		__set_current_state(TASK_STOPPED);
+	}
+	spin_unlock_irq(&current->sighand->siglock);
 
-	if (stop_count == 0)
-		sig->flags = SIGNAL_STOP_STOPPED;
-	current->exit_code = sig->group_exit_code;
-	__set_current_state(TASK_STOPPED);
+	if (notify) {
+		read_lock(&tasklist_lock);
+		do_notify_parent_cldstop(current, notify);
+		read_unlock(&tasklist_lock);
+	}
+
+	/* Now we don't run again until woken by SIGCONT or SIGKILL */
+	do {
+		schedule();
+	} while (try_to_freeze());
+
+	tracehook_finish_jctl();
+	current->exit_code = 0;
 
-	spin_unlock_irq(&current->sighand->siglock);
-	finish_stop(stop_count);
 	return 1;
 }
 
@@ -1815,14 +1823,15 @@ relock:
 		int why = (signal->flags & SIGNAL_STOP_CONTINUED)
 				? CLD_CONTINUED : CLD_STOPPED;
 		signal->flags &= ~SIGNAL_CLD_MASK;
-		spin_unlock_irq(&sighand->siglock);
 
-		if (unlikely(!tracehook_notify_jctl(1, why)))
-			goto relock;
+		why = tracehook_notify_jctl(why, CLD_CONTINUED);
+		spin_unlock_irq(&sighand->siglock);
 
-		read_lock(&tasklist_lock);
-		do_notify_parent_cldstop(current->group_leader, why);
-		read_unlock(&tasklist_lock);
+		if (why) {
+			read_lock(&tasklist_lock);
+			do_notify_parent_cldstop(current->group_leader, why);
+			read_unlock(&tasklist_lock);
+		}
 		goto relock;
 	}
 
@@ -1860,6 +1869,9 @@ relock:
 			ka = &sighand->action[signr-1];
 		}
 
+		/* Trace actually delivered signals. */
+		trace_signal_deliver(signr, info, ka);
+
 		if (ka->sa.sa_handler == SIG_IGN) /* Do nothing.  */
 			continue;
 		if (ka->sa.sa_handler != SIG_DFL) {
@@ -1987,14 +1999,14 @@ void exit_signals(struct task_struct *tsk)
 	if (unlikely(tsk->signal->group_stop_count) &&
 			!--tsk->signal->group_stop_count) {
 		tsk->signal->flags = SIGNAL_STOP_STOPPED;
-		group_stop = 1;
+		group_stop = tracehook_notify_jctl(CLD_STOPPED, CLD_STOPPED);
 	}
 out:
 	spin_unlock_irq(&tsk->sighand->siglock);
 
-	if (unlikely(group_stop) && tracehook_notify_jctl(1, CLD_STOPPED)) {
+	if (unlikely(group_stop)) {
 		read_lock(&tasklist_lock);
-		do_notify_parent_cldstop(tsk, CLD_STOPPED);
+		do_notify_parent_cldstop(tsk, group_stop);
 		read_unlock(&tasklist_lock);
 	}
 }
@@ -2290,7 +2302,6 @@ static int
 do_send_specific(pid_t tgid, pid_t pid, int sig, struct siginfo *info)
 {
 	struct task_struct *p;
-	unsigned long flags;
 	int error = -ESRCH;
 
 	rcu_read_lock();
@@ -2300,14 +2311,16 @@ do_send_specific(pid_t tgid, pid_t pid, int sig, struct siginfo *info)
 		/*
 		 * The null signal is a permissions and process existence
 		 * probe.  No signal is actually delivered.
-		 *
-		 * If lock_task_sighand() fails we pretend the task dies
-		 * after receiving the signal. The window is tiny, and the
-		 * signal is private anyway.
 		 */
-		if (!error && sig && lock_task_sighand(p, &flags)) {
-			error = specific_send_sig_info(sig, info, p);
-			unlock_task_sighand(p, &flags);
+		if (!error && sig) {
+			error = do_send_sig_info(sig, info, p, false);
+			/*
+			 * If lock_task_sighand() failed we pretend the task
+			 * dies after receiving the signal. The window is tiny,
+			 * and the signal is private anyway.
+			 */
+			if (unlikely(error == -ESRCH))
+				error = 0;
 		}
 	}
 	rcu_read_unlock();