padata: Fix race on sequence number wrap

When padata_do_parallel() is called from multiple cpus for the same
padata instance, we can get object reordering on sequence number wrap
because testing for sequence number wrap and reseting the sequence
number must happen atomically but is implemented with two atomic
operations. This patch fixes this by converting the sequence number
from atomic_t to an unsigned int and protect the access with a
spin_lock. As a side effect, we get rid of the sequence number wrap
handling because the seqence number wraps back to null now without
the need to do anything.

Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
diff --git a/include/linux/padata.h b/include/linux/padata.h
index 4633b2f..86292be 100644
--- a/include/linux/padata.h
+++ b/include/linux/padata.h
@@ -46,7 +46,6 @@
 	struct list_head	list;
 	struct parallel_data	*pd;
 	int			cb_cpu;
-	int			seq_nr;
 	int			info;
 	void                    (*parallel)(struct padata_priv *padata);
 	void                    (*serial)(struct padata_priv *padata);
@@ -116,7 +115,6 @@
  * @pinst: padata instance.
  * @pqueue: percpu padata queues used for parallelization.
  * @squeue: percpu padata queues used for serialuzation.
- * @seq_nr: The sequence number that will be attached to the next object.
  * @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.
@@ -129,12 +127,12 @@
 	struct padata_instance		*pinst;
 	struct padata_parallel_queue	__percpu *pqueue;
 	struct padata_serial_queue	__percpu *squeue;
-	atomic_t			seq_nr;
 	atomic_t			reorder_objects;
 	atomic_t			refcnt;
-	unsigned int			max_seq_nr;
 	struct padata_cpumask		cpumask;
 	spinlock_t                      lock ____cacheline_aligned;
+	spinlock_t                      seq_lock;
+	unsigned int			seq_nr;
 	unsigned int			processed;
 	struct timer_list		timer;
 };