Re: [PATCH v5 04/12] sched: Allow all archs to set the capacity_orig

From: Peter Zijlstra
Date: Wed Sep 10 2014 - 09:50:49 EST


On Sat, Aug 30, 2014 at 10:37:40PM +0530, Preeti U Murthy wrote:
> > - if ((sd->flags & SD_SHARE_CPUCAPACITY) && weight > 1) {
> > - if (sched_feat(ARCH_CAPACITY))
>
> Aren't you missing this check above? I understand that it is not
> crucial, but that would also mean removing ARCH_CAPACITY sched_feat
> altogether, wouldn't it?

Yes he's missing that, I added the below bit on top.

So the argument last time:
lkml.kernel.org/r/20140709105721.GT19379@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
was that you cannot put sched_feat(ARCH_CAPACITY) inside a weak arch_*
function. The test has to be outside, seeing how it needs to decide to
call the arch function at all (or revert to the default implementation).

---
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5700,7 +5700,7 @@ unsigned long __weak arch_scale_freq_cap
return default_scale_capacity(sd, cpu);
}

-unsigned long __weak arch_scale_cpu_capacity(struct sched_domain *sd, int cpu)
+static unsigned long default_scale_cpu_capacity(struct sched_domain *sd, int cpu)
{
if ((sd->flags & SD_SHARE_CPUCAPACITY) && (sd->span_weight > 1))
return sd->smt_gain / sd->span_weight;
@@ -5708,6 +5708,11 @@ unsigned long __weak arch_scale_cpu_capa
return SCHED_CAPACITY_SCALE;
}

+unsigned long __weak arch_scale_cpu_capacity(struct sched_domain *sd, int cpu)
+{
+ return default_scale_cpu_capacity(sd, cpu);
+}
+
static unsigned long scale_rt_capacity(int cpu)
{
struct rq *rq = cpu_rq(cpu);
@@ -5747,7 +5752,10 @@ static void update_cpu_capacity(struct s
unsigned long capacity = SCHED_CAPACITY_SCALE;
struct sched_group *sdg = sd->groups;

- capacity *= arch_scale_cpu_capacity(sd, cpu);
+ if (sched_feat(ARCH_CAPACITY))
+ capacity *= arch_scale_cpu_capacity(sd, cpu);
+ else
+ capacity *= default_scale_cpu_capacity(sd, cpu);

capacity >>= SCHED_CAPACITY_SHIFT;

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/