1 files changed, 26 insertions, 35 deletions

diff --git a/kernel/padata.c b/kernel/padata.c
index e4a8f8d9b31a..6939111b3cbe 100644
--- a/kernel/padata.c
+++ b/kernel/padata.c
@@ -34,6 +34,8 @@
 
 #define MAX_OBJ_NUM 1000
 
+static void padata_free_pd(struct parallel_data *pd);
+
 static int padata_index_to_cpu(struct parallel_data *pd, int cpu_index)
 {
 	int cpu, target_cpu;
@@ -274,7 +276,12 @@ static void padata_reorder(struct parallel_data *pd)
 	 * The next object that needs serialization might have arrived to
 	 * the reorder queues in the meantime, we will be called again
 	 * from the timer function if no one else cares for it.
+	 *
+	 * Ensure reorder_objects is read after pd->lock is dropped so we see
+	 * an increment from another task in padata_do_serial.  Pairs with
+	 * smp_mb__after_atomic in padata_do_serial.
 	 */
+	smp_mb();
 	if (atomic_read(&pd->reorder_objects)
 			&& !(pinst->flags & PADATA_RESET))
 		mod_timer(&pd->timer, jiffies + HZ);
@@ -296,6 +303,7 @@ static void padata_serial_worker(struct work_struct *serial_work)
 	struct padata_serial_queue *squeue;
 	struct parallel_data *pd;
 	LIST_HEAD(local_list);
+	int cnt;
 
 	local_bh_disable();
 	squeue = container_of(serial_work, struct padata_serial_queue, work);
@@ -305,6 +313,8 @@ static void padata_serial_worker(struct work_struct *serial_work)
 	list_replace_init(&squeue->serial.list, &local_list);
 	spin_unlock(&squeue->serial.lock);
 
+	cnt = 0;
+
 	while (!list_empty(&local_list)) {
 		struct padata_priv *padata;
 
@@ -314,9 +324,12 @@ static void padata_serial_worker(struct work_struct *serial_work)
 		list_del_init(&padata->list);
 
 		padata->serial(padata);
-		atomic_dec(&pd->refcnt);
+		cnt++;
 	}
 	local_bh_enable();
+
+	if (atomic_sub_and_test(cnt, &pd->refcnt))
+		padata_free_pd(pd);
 }
 
 /**
@@ -343,6 +356,13 @@ void padata_do_serial(struct padata_priv *padata)
 	list_add_tail(&padata->list, &pqueue->reorder.list);
 	spin_unlock(&pqueue->reorder.lock);
 
+	/*
+	 * Ensure the atomic_inc of reorder_objects above is ordered correctly
+	 * with the trylock of pd->lock in padata_reorder.  Pairs with smp_mb
+	 * in padata_reorder.
+	 */
+	smp_mb__after_atomic();
+
 	put_cpu();
 
 	padata_reorder(pd);
@@ -432,7 +452,7 @@ static struct parallel_data *padata_alloc_pd(struct padata_instance *pinst,
 	setup_timer(&pd->timer, padata_reorder_timer, (unsigned long)pd);
 	atomic_set(&pd->seq_nr, -1);
 	atomic_set(&pd->reorder_objects, 0);
-	atomic_set(&pd->refcnt, 0);
+	atomic_set(&pd->refcnt, 1);
 	pd->pinst = pinst;
 	spin_lock_init(&pd->lock);
 
@@ -457,31 +477,6 @@ static void padata_free_pd(struct parallel_data *pd)
 	kfree(pd);
 }
 
-/* Flush all objects out of the padata queues. */
-static void padata_flush_queues(struct parallel_data *pd)
-{
-	int cpu;
-	struct padata_parallel_queue *pqueue;
-	struct padata_serial_queue *squeue;
-
-	for_each_cpu(cpu, pd->cpumask.pcpu) {
-		pqueue = per_cpu_ptr(pd->pqueue, cpu);
-		flush_work(&pqueue->work);
-	}
-
-	del_timer_sync(&pd->timer);
-
-	if (atomic_read(&pd->reorder_objects))
-		padata_reorder(pd);
-
-	for_each_cpu(cpu, pd->cpumask.cbcpu) {
-		squeue = per_cpu_ptr(pd->squeue, cpu);
-		flush_work(&squeue->work);
-	}
-
-	BUG_ON(atomic_read(&pd->refcnt) != 0);
-}
-
 static void __padata_start(struct padata_instance *pinst)
 {
 	pinst->flags |= PADATA_INIT;
@@ -495,10 +490,6 @@ static void __padata_stop(struct padata_instance *pinst)
 	pinst->flags &= ~PADATA_INIT;
 
 	synchronize_rcu();
-
-	get_online_cpus();
-	padata_flush_queues(pinst->pd);
-	put_online_cpus();
 }
 
 /* Replace the internal control structure with a new one. */
@@ -519,8 +510,8 @@ static void padata_replace(struct padata_instance *pinst,
 	if (!cpumask_equal(pd_old->cpumask.cbcpu, pd_new->cpumask.cbcpu))
 		notification_mask |= PADATA_CPU_SERIAL;
 
-	padata_flush_queues(pd_old);
-	padata_free_pd(pd_old);
+	if (atomic_dec_and_test(&pd_old->refcnt))
+		padata_free_pd(pd_old);
 
 	if (notification_mask)
 		blocking_notifier_call_chain(&pinst->cpumask_change_notifier,
@@ -623,8 +614,8 @@ int padata_set_cpumask(struct padata_instance *pinst, int cpumask_type,
 	struct cpumask *serial_mask, *parallel_mask;
 	int err = -EINVAL;
 
-	mutex_lock(&pinst->lock);
 	get_online_cpus();
+	mutex_lock(&pinst->lock);
 
 	switch (cpumask_type) {
 	case PADATA_CPU_PARALLEL:
@@ -642,8 +633,8 @@ int padata_set_cpumask(struct padata_instance *pinst, int cpumask_type,
 	err =  __padata_set_cpumasks(pinst, parallel_mask, serial_mask);
 
 out:
-	put_online_cpus();
 	mutex_unlock(&pinst->lock);
+	put_online_cpus();
 
 	return err;
 }