commit 0b7570e77f7c3abd43107dabc47ea89daf9a1cba
author Oleg Nesterov <oleg@redhat.com> Wed Sep 23 15:56:46 2009 -0700
committer Linus Torvalds <torvalds@linux-foundation.org> Thu Sep 24 07:20:59 2009 -0700
tree 8dd93b4a189b4e98384d4470a289ecfb7818cc26
parent a2322e1d272938d192d8c24cdacf57c0c7a2683f

do_wait() wakeup optimization: change __wake_up_parent() to use filtered wakeup

Ratan Nalumasu reported that in a process with many threads doing
unnecessary wakeups.  Every waiting thread in the process wakes up to loop
through the children and see that the only ones it cares about are still
not ready.

Now that we have struct wait_opts we can change do_wait/__wake_up_parent
to use filtered wakeups.

We can make child_wait_callback() more clever later, right now it only
checks eligible_child().

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Acked-by: Roland McGrath <roland@redhat.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Ratan Nalumasu <rnalumasu@gmail.com>
Cc: Vitaly Mayatskikh <vmayatsk@redhat.com>
Acked-by: James Morris <jmorris@namei.org>
Tested-by: Valdis Kletnieks <valdis.kletnieks@vt.edu>
Acked-by: David Howells <dhowells@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

kernel/exit.c

diff --git a/kernel/exit.c b/kernel/exit.c
index ef2dfa8..7838b4d 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1097,6 +1097,7 @@
 	int __user		*wo_stat;
 	struct rusage __user	*wo_rusage;
 
+	wait_queue_t		child_wait;
 	int			notask_error;
 };
 
@@ -1570,20 +1571,35 @@
 	return 0;
 }
 
+static int child_wait_callback(wait_queue_t *wait, unsigned mode,
+				int sync, void *key)
+{
+	struct wait_opts *wo = container_of(wait, struct wait_opts,
+						child_wait);
+	struct task_struct *p = key;
+
+	if (!eligible_child(wo, p))
+		return 0;
+
+	return default_wake_function(wait, mode, sync, key);
+}
+
 void __wake_up_parent(struct task_struct *p, struct task_struct *parent)
 {
-	wake_up_interruptible_sync(&parent->signal->wait_chldexit);
+	__wake_up_sync_key(&parent->signal->wait_chldexit,
+				TASK_INTERRUPTIBLE, 1, p);
 }
 
 static long do_wait(struct wait_opts *wo)
 {
-	DECLARE_WAITQUEUE(wait, current);
 	struct task_struct *tsk;
 	int retval;
 
 	trace_sched_process_wait(wo->wo_pid);
 
-	add_wait_queue(&current->signal->wait_chldexit,&wait);
+	init_waitqueue_func_entry(&wo->child_wait, child_wait_callback);
+	wo->child_wait.private = current;
+	add_wait_queue(&current->signal->wait_chldexit, &wo->child_wait);
 repeat:
 	/*
 	 * If there is nothing that can match our critiera just get out.
@@ -1624,7 +1640,8 @@
 	}
 end:
 	__set_current_state(TASK_RUNNING);
-	remove_wait_queue(&current->signal->wait_chldexit,&wait);
+	remove_wait_queue(&current->signal->wait_chldexit, &wo->child_wait);
+
 	if (wo->wo_info) {
 		struct siginfo __user *infop = wo->wo_info;