[RFC][PATCH 1/7] wait: Provide infrastructure to deal with nested blocking

[Peter Zijlstra]

There are a few places that call blocking primitives from wait loops,
provide infrastructure to support this without the typical
task_struct::state collision.

We record the wakeup in wait_queue_t::flags which leaves
task_struct::state free to be used by others.

Signed-off-by: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
---
 include/linux/wait.h |    7 ++++++-
 kernel/sched/wait.c  |   29 +++++++++++++++++++++++++++++
 2 files changed, 35 insertions(+), 1 deletion(-)

--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -13,9 +13,12 @@ typedef struct __wait_queue wait_queue_t
 typedef int (*wait_queue_func_t)(wait_queue_t *wait, unsigned mode, int flags, void *key);
 int default_wake_function(wait_queue_t *wait, unsigned mode, int flags, void *key);
 
+/* __wait_queue::flags */
+#define WQ_FLAG_EXCLUSIVE	0x01
+#define WQ_FLAG_WOKEN		0x02
+
 struct __wait_queue {
 	unsigned int		flags;
-#define WQ_FLAG_EXCLUSIVE	0x01
 	void			*private;
 	wait_queue_func_t	func;
 	struct list_head	task_list;
@@ -825,6 +828,8 @@ void prepare_to_wait_exclusive(wait_queu
 long prepare_to_wait_event(wait_queue_head_t *q, wait_queue_t *wait, int state);
 void finish_wait(wait_queue_head_t *q, wait_queue_t *wait);
 void abort_exclusive_wait(wait_queue_head_t *q, wait_queue_t *wait, unsigned int mode, void *key);
+long wait_woken(wait_queue_t *wait, unsigned mode, long timeout);
+int woken_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key);
 int autoremove_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key);
 int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *key);
 
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -297,6 +297,35 @@ int autoremove_wake_function(wait_queue_
 }
 EXPORT_SYMBOL(autoremove_wake_function);
 
+long wait_woken(wait_queue_t *wait, unsigned mode, long timeout)
+{
+	set_current_state(mode);
+	if (!(wait->flags & WQ_FLAG_WOKEN))
+		timeout = schedule_timeout(timeout);
+	else
+		wait->flags &= ~WQ_FLAG_WOKEN;
+	__set_current_state(TASK_RUNNING);
+
+	return timeout;
+}
+EXPORT_SYMBOL(wait_woken);
+
+int woken_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key)
+{
+	/*
+	 * Although this function is called under waitqueue lock, LOCK
+	 * doesn't imply write barrier and the users expect write
+	 * barrier semantics on wakeup functions.  The following
+	 * smp_wmb() is equivalent to smp_wmb() in try_to_wake_up()
+	 * and is paired with set_mb() in wait_woken().
+	 */
+	smp_wmb();
+	wait->flags |= WQ_FLAG_WOKEN;
+
+	return default_wake_function(wait, mode, sync, key);
+}
+EXPORT_SYMBOL(woken_wake_function);
+
 int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *arg)
 {
 	struct wait_bit_key *key = arg;


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/