Re: [PATCH 3/4] workqueue: add schedule_on_each_cpumask helper

[Marcelo Tosatti <mtosatti@redhat.com>]

On Tue, May 30, 2023 at 01:09:47PM -0700, Andrew Morton wrote:
> On Tue, 30 May 2023 11:52:37 -0300 Marcelo Tosatti <mtosatti@redhat.com> wrote:
> 
> > Add a schedule_on_each_cpumask function, equivalent to
> > schedule_on_each_cpu but accepting a cpumask to operate.
> > 
> > Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
> > 
> > ---
> > 
> > Index: linux-vmstat-remote/kernel/workqueue.c
> > ===================================================================
> > --- linux-vmstat-remote.orig/kernel/workqueue.c
> > +++ linux-vmstat-remote/kernel/workqueue.c
> > @@ -3455,6 +3455,56 @@ int schedule_on_each_cpu(work_func_t fun
> >  	return 0;
> >  }
> >  
> > +
> > +/**
> > + * schedule_on_each_cpumask - execute a function synchronously on each
> > + * CPU in "cpumask", for those which are online.
> > + *
> > + * @func: the function to call
> > + * @mask: the CPUs which to call function on
> > + *
> > + * schedule_on_each_cpu() executes @func on each specified CPU that is online,
> > + * using the system workqueue and blocks until all such CPUs have completed.
> > + * schedule_on_each_cpu() is very slow.
> > + *
> > + * Return:
> > + * 0 on success, -errno on failure.
> > + */
> > +int schedule_on_each_cpumask(work_func_t func, cpumask_t *cpumask)
> > +{
> > +	int cpu;
> > +	struct work_struct __percpu *works;
> > +	cpumask_var_t effmask;
> > +
> > +	works = alloc_percpu(struct work_struct);
> > +	if (!works)
> > +		return -ENOMEM;
> > +
> > +	if (!alloc_cpumask_var(&effmask, GFP_KERNEL)) {
> > +		free_percpu(works);
> > +		return -ENOMEM;
> > +	}
> > +
> > +	cpumask_and(effmask, cpumask, cpu_online_mask);
> > +
> > +	cpus_read_lock();
> > +
> > +	for_each_cpu(cpu, effmask) {
> 
> Should we check here that the cpu is still online?
> 
> > +		struct work_struct *work = per_cpu_ptr(works, cpu);
> > +
> > +		INIT_WORK(work, func);
> > +		schedule_work_on(cpu, work);
> > +	}
> > +
> > +	for_each_cpu(cpu, effmask)
> > +		flush_work(per_cpu_ptr(works, cpu));
> > +
> > +	cpus_read_unlock();
> > +	free_percpu(works);
> > +	free_cpumask_var(effmask);
> > +	return 0;
> > +}
> > +
> >  /**
> >   * execute_in_process_context - reliably execute the routine with user context
> >   * @fn:		the function to execute
> > --- linux-vmstat-remote.orig/include/linux/workqueue.h
> > +++ linux-vmstat-remote/include/linux/workqueue.h
> > @@ -450,6 +450,7 @@ extern void __flush_workqueue(struct wor
> >  extern void drain_workqueue(struct workqueue_struct *wq);
> >  
> >  extern int schedule_on_each_cpu(work_func_t func);
> > +extern int schedule_on_each_cpumask(work_func_t func, cpumask_t *cpumask);
> 
> May as well make schedule_on_each_cpu() call
> schedule_on_each_cpumask()?  Save a bit of text, and they're hardly
> performance-critical to that extent.

Agree, will wait for Michal's review before resending -v2.


workqueue: add schedule_on_each_cpumask helper

Add a schedule_on_each_cpumask function, equivalent to
schedule_on_each_cpu but accepting a cpumask to operate.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

---

v2: - cpu_online_mask reference should happen with cpus_read_lock held	(Andrew Morton)
    - have schedule_on_each_cpu call _cpumask variant			(Andrew Morton)

Index: linux-vmstat-remote/kernel/workqueue.c
===================================================================
--- linux-vmstat-remote.orig/kernel/workqueue.c
+++ linux-vmstat-remote/kernel/workqueue.c
@@ -3431,27 +3431,56 @@ EXPORT_SYMBOL(cancel_delayed_work_sync);
  */
 int schedule_on_each_cpu(work_func_t func)
 {
+	return schedule_on_each_cpumask(func, cpu_possible_mask);
+}
+
+
+/**
+ * schedule_on_each_cpumask - execute a function synchronously on each
+ * CPU in "cpumask", for those which are online.
+ *
+ * @func: the function to call
+ * @mask: the CPUs which to call function on
+ *
+ * schedule_on_each_cpu() executes @func on each specified CPU that is online,
+ * using the system workqueue and blocks until all such CPUs have completed.
+ * schedule_on_each_cpu() is very slow.
+ *
+ * Return:
+ * 0 on success, -errno on failure.
+ */
+int schedule_on_each_cpumask(work_func_t func, cpumask_t *cpumask)
+{
 	int cpu;
 	struct work_struct __percpu *works;
+	cpumask_var_t effmask;
 
 	works = alloc_percpu(struct work_struct);
 	if (!works)
 		return -ENOMEM;
 
+	if (!alloc_cpumask_var(&effmask, GFP_KERNEL)) {
+		free_percpu(works);
+		return -ENOMEM;
+	}
+
 	cpus_read_lock();
 
-	for_each_online_cpu(cpu) {
+	cpumask_and(effmask, cpumask, cpu_online_mask);
+
+	for_each_cpu(cpu, effmask) {
 		struct work_struct *work = per_cpu_ptr(works, cpu);
 
 		INIT_WORK(work, func);
 		schedule_work_on(cpu, work);
 	}
 
-	for_each_online_cpu(cpu)
+	for_each_cpu(cpu, effmask)
 		flush_work(per_cpu_ptr(works, cpu));
 
 	cpus_read_unlock();
 	free_percpu(works);
+	free_cpumask_var(effmask);
 	return 0;
 }
 
Index: linux-vmstat-remote/include/linux/workqueue.h
===================================================================
--- linux-vmstat-remote.orig/include/linux/workqueue.h
+++ linux-vmstat-remote/include/linux/workqueue.h
@@ -450,6 +450,7 @@ extern void __flush_workqueue(struct wor
 extern void drain_workqueue(struct workqueue_struct *wq);
 
 extern int schedule_on_each_cpu(work_func_t func);
+extern int schedule_on_each_cpumask(work_func_t func, cpumask_t *cpumask);
 
 int execute_in_process_context(work_func_t fn, struct execute_work *);