padata: simplify serialization mechanism

We count the number of processed objects on a percpu basis,
so we need to go through all the percpu reorder queues to calculate
the sequence number of the next object that needs serialization.
This patch changes this to count the number of processed objects
global. So we can calculate the sequence number and the percpu
reorder queue of the next object that needs serialization without
searching through the percpu reorder queues. This avoids some
accesses to memory of foreign cpus.

Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

1 files changed, 3 insertions, 3 deletions

diff --git a/include/linux/padata.h b/include/linux/padata.h
index e4c17f9b7c9..8844b851191 100644
--- a/include/linux/padata.h
+++ b/include/linux/padata.h
@@ -67,7 +67,6 @@ struct padata_list {
  * @pwork: work struct for parallelization.
  * @swork: work struct for serialization.
  * @pd: Backpointer to the internal control structure.
- * @num_obj: Number of objects that are processed by this cpu.
  * @cpu_index: Index of the cpu.
  */
 struct padata_queue {
@@ -77,7 +76,6 @@ struct padata_queue {
 	struct work_struct	pwork;
 	struct work_struct	swork;
 	struct parallel_data    *pd;
-	atomic_t		num_obj;
 	int			cpu_index;
 };
 
@@ -93,6 +91,7 @@ struct padata_queue {
  * @max_seq_nr:  Maximal used sequence number.
  * @cpumask: cpumask in use.
  * @lock: Reorder lock.
+ * @processed: Number of already processed objects.
  * @timer: Reorder timer.
  */
 struct parallel_data {
@@ -103,7 +102,8 @@ struct parallel_data {
 	atomic_t                refcnt;
 	unsigned int		max_seq_nr;
 	cpumask_var_t		cpumask;
-	spinlock_t              lock;
+	spinlock_t              lock ____cacheline_aligned;
+	unsigned int            processed;
 	struct timer_list       timer;
 };