padata: allocate workqueue internally

Move workqueue allocation inside of padata to prepare for further
changes to how padata uses workqueues.

Guarantees the workqueue is created with max_active=1, which padata
relies on to work correctly.  No functional change.

Signed-off-by: Daniel Jordan <daniel.m.jordan@oracle.com>
Acked-by: Steffen Klassert <steffen.klassert@secunet.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Lai Jiangshan <jiangshanlai@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: linux-crypto@vger.kernel.org
Cc: linux-doc@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

Documentation/padata.txt

@@ -16,10 +16,12 @@ overall control of how tasks are to be run::
 
     #include <linux/padata.h>
 
-    struct padata_instance *padata_alloc(struct workqueue_struct *wq,
+    struct padata_instance *padata_alloc(const char *name,
 					 const struct cpumask *pcpumask,
 					 const struct cpumask *cbcpumask);
 
+'name' simply identifies the instance.
+
 The pcpumask describes which processors will be used to execute work
 submitted to this instance in parallel. The cbcpumask defines which
 processors are allowed to be used as the serialization callback processor.
@@ -128,8 +130,7 @@ in that CPU mask or about a not running instance.
 
 Each task submitted to padata_do_parallel() will, in turn, be passed to
 exactly one call to the above-mentioned parallel() function, on one CPU, so
-true parallelism is achieved by submitting multiple tasks.  Despite the
+true parallelism is achieved by submitting multiple tasks.  parallel() runs with
-fact that the workqueue is used to make these calls, parallel() is run with
 software interrupts disabled and thus cannot sleep.  The parallel()
 function gets the padata_priv structure pointer as its lone parameter;
 information about the actual work to be done is probably obtained by using
@@ -148,7 +149,7 @@ fact with a call to::
 At some point in the future, padata_do_serial() will trigger a call to the
 serial() function in the padata_priv structure.  That call will happen on
 the CPU requested in the initial call to padata_do_parallel(); it, too, is
-done through the workqueue, but with local software interrupts disabled.
+run with local software interrupts disabled.
 Note that this call may be deferred for a while since the padata code takes
 pains to ensure that tasks are completed in the order in which they were
 submitted.
@@ -159,5 +160,4 @@ when a padata instance is no longer needed::
     void padata_free(struct padata_instance *pinst);
 
 This function will busy-wait while any remaining tasks are completed, so it
-might be best not to call it while there is work outstanding.  Shutting
+might be best not to call it while there is work outstanding.
-down the workqueue, if necessary, should be done separately.

crypto/pcrypt.c

@@ -20,7 +20,6 @@
 
 struct padata_pcrypt {
 	struct padata_instance *pinst;
-	struct workqueue_struct *wq;
 
 	/*
 	 * Cpumask for callback CPUs. It should be
@@ -397,14 +396,9 @@ static int pcrypt_init_padata(struct padata_pcrypt *pcrypt,
 
 	get_online_cpus();
 
-	pcrypt->wq = alloc_workqueue("%s", WQ_MEM_RECLAIM | WQ_CPU_INTENSIVE,
+	pcrypt->pinst = padata_alloc_possible(name);
-				     1, name);
-	if (!pcrypt->wq)
-		goto err;
-
-	pcrypt->pinst = padata_alloc_possible(pcrypt->wq);
 	if (!pcrypt->pinst)
-		goto err_destroy_workqueue;
+		goto err;
 
 	mask = kmalloc(sizeof(*mask), GFP_KERNEL);
 	if (!mask)
@@ -437,8 +431,6 @@ err_free_cpumask:
 	kfree(mask);
 err_free_padata:
 	padata_free(pcrypt->pinst);
-err_destroy_workqueue:
-	destroy_workqueue(pcrypt->wq);
 err:
 	put_online_cpus();
 
@@ -452,7 +444,6 @@ static void pcrypt_fini_padata(struct padata_pcrypt *pcrypt)
 
 	padata_stop(pcrypt->pinst);
 	padata_unregister_cpumask_notifier(pcrypt->pinst, &pcrypt->nblock);
-	destroy_workqueue(pcrypt->wq);
 	padata_free(pcrypt->pinst);
 }
 

include/linux/padata.h

@@ -151,8 +151,7 @@ struct padata_instance {
 #define	PADATA_INVALID	4
 };
 
-extern struct padata_instance *padata_alloc_possible(
+extern struct padata_instance *padata_alloc_possible(const char *name);
-					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);

kernel/padata.c

@@ -805,6 +805,7 @@ static void __padata_free(struct padata_instance *pinst)
 	padata_free_pd(pinst->pd);
 	free_cpumask_var(pinst->cpumask.pcpu);
 	free_cpumask_var(pinst->cpumask.cbcpu);
+	destroy_workqueue(pinst->wq);
 	kfree(pinst);
 }
 
@@ -938,13 +939,13 @@ static struct kobj_type padata_attr_type = {
  * padata_alloc - allocate and initialize a padata instance and specify
  *                cpumasks for serial and parallel workers.
  *
- * @wq: workqueue to use for the allocated padata instance
+ * @name: used to identify the instance
  * @pcpumask: cpumask that will be used for padata parallelization
  * @cbcpumask: cpumask that will be used for padata serialization
  *
  * Must be called from a cpus_read_lock() protected region
  */
-static struct padata_instance *padata_alloc(struct workqueue_struct *wq,
+static struct padata_instance *padata_alloc(const char *name,
 					    const struct cpumask *pcpumask,
 					    const struct cpumask *cbcpumask)
 {
@@ -955,11 +956,16 @@ static struct padata_instance *padata_alloc(struct workqueue_struct *wq,
 	if (!pinst)
 		goto err;
 
-	if (!alloc_cpumask_var(&pinst->cpumask.pcpu, GFP_KERNEL))
+	pinst->wq = alloc_workqueue("%s", WQ_MEM_RECLAIM | WQ_CPU_INTENSIVE,
+				    1, name);
+	if (!pinst->wq)
 		goto err_free_inst;
+
+	if (!alloc_cpumask_var(&pinst->cpumask.pcpu, GFP_KERNEL))
+		goto err_free_wq;
 	if (!alloc_cpumask_var(&pinst->cpumask.cbcpu, GFP_KERNEL)) {
 		free_cpumask_var(pinst->cpumask.pcpu);
-		goto err_free_inst;
+		goto err_free_wq;
 	}
 	if (!padata_validate_cpumask(pinst, pcpumask) ||
 	    !padata_validate_cpumask(pinst, cbcpumask))
@@ -971,8 +977,6 @@ static struct padata_instance *padata_alloc(struct workqueue_struct *wq,
 
 	rcu_assign_pointer(pinst->pd, pd);
 
-	pinst->wq = wq;
-
 	cpumask_copy(pinst->cpumask.pcpu, pcpumask);
 	cpumask_copy(pinst->cpumask.cbcpu, cbcpumask);
 
@@ -990,6 +994,8 @@ static struct padata_instance *padata_alloc(struct workqueue_struct *wq,
 err_free_masks:
 	free_cpumask_var(pinst->cpumask.pcpu);
 	free_cpumask_var(pinst->cpumask.cbcpu);
+err_free_wq:
+	destroy_workqueue(pinst->wq);
 err_free_inst:
 	kfree(pinst);
 err:
@@ -1001,14 +1007,14 @@ err:
  *                         Use the cpu_possible_mask for serial and
  *                         parallel workers.
  *
- * @wq: workqueue to use for the allocated padata instance
+ * @name: used to identify the instance
  *
  * Must be called from a cpus_read_lock() protected region
  */
-struct padata_instance *padata_alloc_possible(struct workqueue_struct *wq)
+struct padata_instance *padata_alloc_possible(const char *name)
 {
 	lockdep_assert_cpus_held();
-	return padata_alloc(wq, cpu_possible_mask, cpu_possible_mask);
+	return padata_alloc(name, cpu_possible_mask, cpu_possible_mask);
 }
 EXPORT_SYMBOL(padata_alloc_possible);