WorkStruct: Pass the work_struct pointer instead of context data

Pass the work_struct pointer to the work function rather than context data.
The work function can use container_of() to work out the data.

For the cases where the container of the work_struct may go away the moment the
pending bit is cleared, it is made possible to defer the release of the
structure by deferring the clearing of the pending bit.

To make this work, an extra flag is introduced into the management side of the
work_struct.  This governs auto-release of the structure upon execution.

Ordinarily, the work queue executor would release the work_struct for further
scheduling or deallocation by clearing the pending bit prior to jumping to the
work function.  This means that, unless the driver makes some guarantee itself
that the work_struct won't go away, the work function may not access anything
else in the work_struct or its container lest they be deallocated..  This is a
problem if the auxiliary data is taken away (as done by the last patch).

However, if the pending bit is *not* cleared before jumping to the work
function, then the work function *may* access the work_struct and its container
with no problems.  But then the work function must itself release the
work_struct by calling work_release().

In most cases, automatic release is fine, so this is the default.  Special
initiators exist for the non-auto-release case (ending in _NAR).


Signed-Off-By: David Howells <dhowells@redhat.com>

1 files changed, 8 insertions, 11 deletions

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 967479756511..8d1e7cb8a51a 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -241,14 +241,14 @@ static void run_workqueue(struct cpu_workqueue_struct *cwq)
 		struct work_struct *work = list_entry(cwq->worklist.next,
 						struct work_struct, entry);
 		work_func_t f = work->func;
-		void *data = work->data;
 
 		list_del_init(cwq->worklist.next);
 		spin_unlock_irqrestore(&cwq->lock, flags);
 
 		BUG_ON(get_wq_data(work) != cwq);
-		clear_bit(WORK_STRUCT_PENDING, &work->management);
-		f(data);
+		if (!test_bit(WORK_STRUCT_NOAUTOREL, &work->management))
+			work_release(work);
+		f(work);
 
 		spin_lock_irqsave(&cwq->lock, flags);
 		cwq->remove_sequence++;
@@ -527,7 +527,6 @@ EXPORT_SYMBOL(schedule_delayed_work_on);
 /**
  * schedule_on_each_cpu - call a function on each online CPU from keventd
  * @func: the function to call
- * @info: a pointer to pass to func()
  *
  * Returns zero on success.
  * Returns -ve errno on failure.
@@ -536,7 +535,7 @@ EXPORT_SYMBOL(schedule_delayed_work_on);
  *
  * schedule_on_each_cpu() is very slow.
  */
-int schedule_on_each_cpu(work_func_t func, void *info)
+int schedule_on_each_cpu(work_func_t func)
 {
 	int cpu;
 	struct work_struct *works;
@@ -547,7 +546,7 @@ int schedule_on_each_cpu(work_func_t func, void *info)
 
 	mutex_lock(&workqueue_mutex);
 	for_each_online_cpu(cpu) {
-		INIT_WORK(per_cpu_ptr(works, cpu), func, info);
+		INIT_WORK(per_cpu_ptr(works, cpu), func);
 		__queue_work(per_cpu_ptr(keventd_wq->cpu_wq, cpu),
 				per_cpu_ptr(works, cpu));
 	}
@@ -591,7 +590,6 @@ EXPORT_SYMBOL(cancel_rearming_delayed_work);
 /**
  * execute_in_process_context - reliably execute the routine with user context
  * @fn:		the function to execute
- * @data:	data to pass to the function
  * @ew:		guaranteed storage for the execute work structure (must
  *		be available when the work executes)
  *
@@ -601,15 +599,14 @@ EXPORT_SYMBOL(cancel_rearming_delayed_work);
  * Returns:	0 - function was executed
  *		1 - function was scheduled for execution
  */
-int execute_in_process_context(work_func_t fn, void *data,
-			       struct execute_work *ew)
+int execute_in_process_context(work_func_t fn, struct execute_work *ew)
 {
 	if (!in_interrupt()) {
-		fn(data);
+		fn(&ew->work);
 		return 0;
 	}
 
-	INIT_WORK(&ew->work, fn, data);
+	INIT_WORK(&ew->work, fn);
 	schedule_work(&ew->work);
 
 	return 1;