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>

2 files changed, 22 insertions, 5 deletions

diff --git a/kernel/exit.c b/kernel/exit.c
index ef2dfa818bf1..7838b4d68774 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1097,6 +1097,7 @@ struct wait_opts {
 	int __user		*wo_stat;
 	struct rusage __user	*wo_rusage;
 
+	wait_queue_t		child_wait;
 	int			notask_error;
 };
 
@@ -1570,20 +1571,35 @@ static int ptrace_do_wait(struct wait_opts *wo, struct task_struct *tsk)
 	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 @@ notask:
 	}
 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;
 
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 417f7c994522..bb230d5d7085 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -2411,7 +2411,7 @@ static void selinux_bprm_committed_creds(struct linux_binprm *bprm)
 	/* Wake up the parent if it is waiting so that it can recheck
 	 * wait permission to the new task SID. */
 	read_lock(&tasklist_lock);
-	wake_up_interruptible(&current->real_parent->signal->wait_chldexit);
+	__wake_up_parent(current, current->real_parent);
 	read_unlock(&tasklist_lock);
 }