padata: Replace delayed timer with immediate workqueue in padata_reorder

The function padata_reorder will use a timer when it cannot progress
while completed jobs are outstanding (pd->reorder_objects > 0).  This
is suboptimal as if we do end up using the timer then it would have
introduced a gratuitous delay of one second.

In fact we can easily distinguish between whether completed jobs
are outstanding and whether we can make progress.  All we have to
do is look at the next pqueue list.

This patch does that by replacing pd->processed with pd->cpu so
that the next pqueue is more accessible.

A work queue is used instead of the original try_again to avoid
hogging the CPU.

Note that we don't bother removing the work queue in
padata_flush_queues because the whole premise is broken.  You
cannot flush async crypto requests so it makes no sense to even
try.  A subsequent patch will fix it by replacing it with a ref
counting scheme.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

1 files changed, 4 insertions, 9 deletions

diff --git a/include/linux/padata.h b/include/linux/padata.h
index 56f09e36f770..8da673861d99 100644
--- a/include/linux/padata.h
+++ b/include/linux/padata.h
@@ -12,7 +12,6 @@
 #include <linux/workqueue.h>
 #include <linux/spinlock.h>
 #include <linux/list.h>
-#include <linux/timer.h>
 #include <linux/notifier.h>
 #include <linux/kobject.h>
 
@@ -73,18 +72,14 @@ struct padata_serial_queue {
  * @serial: List to wait for serialization after reordering.
  * @pwork: work struct for parallelization.
  * @swork: work struct for serialization.
- * @pd: Backpointer to the internal control structure.
  * @work: work struct for parallelization.
- * @reorder_work: work struct for reordering.
  * @num_obj: Number of objects that are processed by this cpu.
  * @cpu_index: Index of the cpu.
  */
 struct padata_parallel_queue {
        struct padata_list    parallel;
        struct padata_list    reorder;
-       struct parallel_data *pd;
        struct work_struct    work;
-       struct work_struct    reorder_work;
        atomic_t              num_obj;
        int                   cpu_index;
 };
@@ -110,10 +105,10 @@ struct padata_cpumask {
  * @reorder_objects: Number of objects waiting in the reorder queues.
  * @refcnt: Number of objects holding a reference on this parallel_data.
  * @max_seq_nr:  Maximal used sequence number.
+ * @cpu: Next CPU to be processed.
  * @cpumask: The cpumasks in use for parallel and serial workers.
+ * @reorder_work: work struct for reordering.
  * @lock: Reorder lock.
- * @processed: Number of already processed objects.
- * @timer: Reorder timer.
  */
 struct parallel_data {
 	struct padata_instance		*pinst;
@@ -122,10 +117,10 @@ struct parallel_data {
 	atomic_t			reorder_objects;
 	atomic_t			refcnt;
 	atomic_t			seq_nr;
+	int				cpu;
 	struct padata_cpumask		cpumask;
+	struct work_struct		reorder_work;
 	spinlock_t                      lock ____cacheline_aligned;
-	unsigned int			processed;
-	struct timer_list		timer;
 };
 
 /**