workqueue: Schedule workers on CPU0 or 0-3 by default

For regular bound workers that don't request to be queued onto a specific
CPU, just use CPU0 to save power. Additionally, adjust the CPU affinity of
unbound workqueues to force their workers onto the power cluster (CPUs 0-3)
to further improve power consumption.

Signed-off-by: Sultanxda <sultanxda@gmail.com>
Signed-off-by: Panchajanya1999 <panchajanya@azure-dev.live>
Signed-off-by: Adithya R <gh0strider.2k18.reborn@gmail.com>
Signed-off-by: sohamxda7 <sensoham135@gmail.com>
Signed-off-by: RyuujiX <saputradenny712@gmail.com>
Signed-off-by: wHo-EM-i <ehteshammalik18998@gmail.com>
Signed-off-by: Santhosh <santhosh.user.why.red@gmail.com>

kernel/workqueue.c

@@ -1425,6 +1425,9 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
 	if (unlikely(wq->flags & __WQ_DRAINING) &&
 	    WARN_ON_ONCE(!is_chained_work(wq)))
 		return;
+
+	if (req_cpu == WORK_CPU_UNBOUND)
+		cpu = wq_select_unbound_cpu(0);
 retry:
 	/* pwq which will be used unless @work is executing elsewhere */
 	if (wq->flags & WQ_UNBOUND) {
@@ -1577,7 +1580,7 @@ static void __queue_delayed_work(int cpu, struct workqueue_struct *wq,
 	if (unlikely(cpu != WORK_CPU_UNBOUND))
 		add_timer_on(timer, cpu);
 	else
-		add_timer(timer);
+		add_timer_on(timer, 0);
 }
 
 /**
@@ -3280,14 +3283,15 @@ void free_workqueue_attrs(struct workqueue_attrs *attrs)
 struct workqueue_attrs *alloc_workqueue_attrs(gfp_t gfp_mask)
 {
 	struct workqueue_attrs *attrs;
+	const unsigned long allowed_cpus = 0xf;
 
 	attrs = kzalloc(sizeof(*attrs), gfp_mask);
 	if (!attrs)
 		goto fail;
 	if (!alloc_cpumask_var(&attrs->cpumask, gfp_mask))
 		goto fail;
 
-	cpumask_copy(attrs->cpumask, cpu_possible_mask);
+	cpumask_copy(attrs->cpumask, to_cpumask(&allowed_cpus));
 	return attrs;
 fail:
 	free_workqueue_attrs(attrs);
@@ -4429,7 +4433,7 @@ bool workqueue_congested(int cpu, struct workqueue_struct *wq)
 	rcu_read_lock_sched();
 
 	if (cpu == WORK_CPU_UNBOUND)
-		cpu = smp_processor_id();
+		cpu = 0;
 
 	if (!(wq->flags & WQ_UNBOUND))
 		pwq = per_cpu_ptr(wq->cpu_pwqs, cpu);