On Mon, Apr 24, 2017 at 03:03:26PM +0200, Peter Zijlstra wrote:
> Also, would it not make sense to re-order patch 2 to come after this,
> such that we _do_ have the group_mask available and don't have to jump
> through hoops in order to link up the sgc? Afaict we don't actually use
> the sgc until the above (reverse) loop computing the CPU capacities.
That is, if I force 4 on without 2, then doesn't something like the
below also do the right thing? (without duplicating part of the magic
already contained in build_group_mask)
---
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -498,13 +498,16 @@ enum s_alloc {
*
* This function can only be used when all the groups are already built.
*/
-static void build_group_mask(struct sched_domain *sd, struct sched_group *sg)
+static void
+build_group_mask(struct sched_domain *sd, struct sched_group *sg, struct
cpumask *mask)
{
const struct cpumask *sg_span = sched_group_cpus(sg);
struct sd_data *sdd = sd->private;
struct sched_domain *sibling;
int i;
+ cpumask_clear(mask);
+
for_each_cpu(i, sg_span) {
sibling = *per_cpu_ptr(sdd->sd, i);
@@ -514,7 +517,7 @@ static void build_group_mask(struct sche
if (!cpumask_equal(sg_span, sched_group_cpus(sibling->groups)))
continue;
- cpumask_set_cpu(i, sched_group_mask(sg));
+ cpumask_set_cpu(i, mask);
}
}
@@ -549,14 +552,19 @@ build_group_from_child_sched_domain(stru
}
static void init_overlap_sched_group(struct sched_domain *sd,
- struct sched_group *sg, int cpu)
+ struct sched_group *sg)
{
+ struct cpumask *mask = sched_domains_tmpmask;
struct sd_data *sdd = sd->private;
struct cpumask *sg_span;
+ int cpu;
+
+ build_group_mask(sd, sg, mask);
+ cpu = cpumask_first_and(sched_group_mask(sg), mask); /* balance cpu */
sg->sgc = *per_cpu_ptr(sdd->sgc, cpu);
if (atomic_inc_return(&sg->sgc->ref) == 1)
- build_group_mask(sd, sg);
+ cpumask_copy(sched_group_mask(sg), mask);
/*
* Initialize sgc->capacity such that even if we mess up the
