diff --git a/crypto/pcrypt.c b/crypto/pcrypt.c
index 898a71c7386b3d728aaf29d8d2cf8e320e6a32f9..4542b48b5afd56918b8a33f451ce3e59451ee74e 100644
--- a/crypto/pcrypt.c
+++ b/crypto/pcrypt.c
@@ -70,35 +70,6 @@ struct pcrypt_aead_ctx {
 	unsigned int cb_cpu;
 };
 
-static int pcrypt_do_parallel(struct padata_priv *padata, unsigned int *cb_cpu,
-			      struct padata_pcrypt *pcrypt)
-{
-	unsigned int cpu_index, cpu, i;
-	struct pcrypt_cpumask *cpumask;
-
-	cpu = *cb_cpu;
-
-	rcu_read_lock_bh();
-	cpumask = rcu_dereference_bh(pcrypt->cb_cpumask);
-	if (cpumask_test_cpu(cpu, cpumask->mask))
-			goto out;
-
-	if (!cpumask_weight(cpumask->mask))
-			goto out;
-
-	cpu_index = cpu % cpumask_weight(cpumask->mask);
-
-	cpu = cpumask_first(cpumask->mask);
-	for (i = 0; i < cpu_index; i++)
-		cpu = cpumask_next(cpu, cpumask->mask);
-
-	*cb_cpu = cpu;
-
-out:
-	rcu_read_unlock_bh();
-	return padata_do_parallel(pcrypt->pinst, padata, cpu);
-}
-
 static int pcrypt_aead_setkey(struct crypto_aead *parent,
 			      const u8 *key, unsigned int keylen)
 {
@@ -172,7 +143,7 @@ static int pcrypt_aead_encrypt(struct aead_request *req)
 			       req->cryptlen, req->iv);
 	aead_request_set_ad(creq, req->assoclen);
 
-	err = pcrypt_do_parallel(padata, &ctx->cb_cpu, &pencrypt);
+	err = padata_do_parallel(pencrypt.pinst, padata, &ctx->cb_cpu);
 	if (!err)
 		return -EINPROGRESS;
 	if (err == -EBUSY) {
@@ -220,7 +191,7 @@ static int pcrypt_aead_decrypt(struct aead_request *req)
 			       req->cryptlen, req->iv);
 	aead_request_set_ad(creq, req->assoclen);
 
-	err = pcrypt_do_parallel(padata, &ctx->cb_cpu, &pdecrypt);
+	err = padata_do_parallel(pdecrypt.pinst, padata, &ctx->cb_cpu);
 	if (!err)
 		return -EINPROGRESS;
 	if (err == -EBUSY) {
diff --git a/include/linux/padata.h b/include/linux/padata.h
index d803397a28f70be39443e57816d546baffbda43a..8d2267926a64ee9589a7ede6a906a73e4f11430c 100644
--- a/include/linux/padata.h
+++ b/include/linux/padata.h
@@ -167,7 +167,7 @@ extern struct padata_instance *padata_alloc_possible(
 					struct workqueue_struct *wq);
 extern void padata_free(struct padata_instance *pinst);
 extern int padata_do_parallel(struct padata_instance *pinst,
-			      struct padata_priv *padata, int cb_cpu);
+			      struct padata_priv *padata, int *cb_cpu);
 extern void padata_do_serial(struct padata_priv *padata);
 extern int padata_set_cpumask(struct padata_instance *pinst, int cpumask_type,
 			      cpumask_var_t cpumask);
diff --git a/kernel/padata.c b/kernel/padata.c
index 848e40e3581b8095f6db6aee6cbd4b560ff2f818..3518c2e60965e621663e1ae42c6b083fc54c40c3 100644
--- a/kernel/padata.c
+++ b/kernel/padata.c
@@ -96,17 +96,19 @@ static void padata_parallel_worker(struct work_struct *parallel_work)
  *
  * @pinst: padata instance
  * @padata: object to be parallelized
- * @cb_cpu: cpu the serialization callback function will run on,
- *          must be in the serial cpumask of padata(i.e. cpumask.cbcpu).
+ * @cb_cpu: pointer to the CPU that the serialization callback function should
+ *          run on.  If it's not in the serial cpumask of @pinst
+ *          (i.e. cpumask.cbcpu), this function selects a fallback CPU and if
+ *          none found, returns -EINVAL.
  *
  * The parallelization callback function will run with BHs off.
  * Note: Every object which is parallelized by padata_do_parallel
  * must be seen by padata_do_serial.
  */
 int padata_do_parallel(struct padata_instance *pinst,
-		       struct padata_priv *padata, int cb_cpu)
+		       struct padata_priv *padata, int *cb_cpu)
 {
-	int target_cpu, err;
+	int i, cpu, cpu_index, target_cpu, err;
 	struct padata_parallel_queue *queue;
 	struct parallel_data *pd;
 
@@ -118,8 +120,19 @@ int padata_do_parallel(struct padata_instance *pinst,
 	if (!(pinst->flags & PADATA_INIT) || pinst->flags & PADATA_INVALID)
 		goto out;
 
-	if (!cpumask_test_cpu(cb_cpu, pd->cpumask.cbcpu))
-		goto out;
+	if (!cpumask_test_cpu(*cb_cpu, pd->cpumask.cbcpu)) {
+		if (!cpumask_weight(pd->cpumask.cbcpu))
+			goto out;
+
+		/* Select an alternate fallback CPU and notify the caller. */
+		cpu_index = *cb_cpu % cpumask_weight(pd->cpumask.cbcpu);
+
+		cpu = cpumask_first(pd->cpumask.cbcpu);
+		for (i = 0; i < cpu_index; i++)
+			cpu = cpumask_next(cpu, pd->cpumask.cbcpu);
+
+		*cb_cpu = cpu;
+	}
 
 	err = -EBUSY;
 	if ((pinst->flags & PADATA_RESET))
@@ -131,7 +144,7 @@ int padata_do_parallel(struct padata_instance *pinst,
 	err = 0;
 	atomic_inc(&pd->refcnt);
 	padata->pd = pd;
-	padata->cb_cpu = cb_cpu;
+	padata->cb_cpu = *cb_cpu;
 
 	target_cpu = padata_cpu_hash(pd);
 	padata->cpu = target_cpu;