diff options
| -rw-r--r-- | kernel/sched/topology.c | 83 |
1 files changed, 58 insertions, 25 deletions
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index f1ebc60d967f..439e6ce9900b 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -2347,36 +2347,69 @@ static struct sched_domain *build_sched_domain(struct sched_domain_topology_leve /* * Ensure topology masks are sane, i.e. there are no conflicts (overlaps) for - * any two given CPUs at this (non-NUMA) topology level. + * any two given CPUs on non-NUMA topology levels. */ -static bool topology_span_sane(struct sched_domain_topology_level *tl, - const struct cpumask *cpu_map, int cpu) +static bool topology_span_sane(const struct cpumask *cpu_map) { - int i = cpu + 1; + struct sched_domain_topology_level *tl; + const struct cpumask **masks; + struct cpumask *covered; + int cpu, id; + bool ret = false; - /* NUMA levels are allowed to overlap */ - if (tl->flags & SDTL_OVERLAP) - return true; + lockdep_assert_held(&sched_domains_mutex); + covered = sched_domains_tmpmask; + + masks = kmalloc_array(nr_cpu_ids, sizeof(struct cpumask *), GFP_KERNEL); + if (!masks) + return ret; + + for_each_sd_topology(tl) { + + /* NUMA levels are allowed to overlap */ + if (tl->flags & SDTL_OVERLAP) + continue; + + cpumask_clear(covered); + memset(masks, 0, nr_cpu_ids * sizeof(struct cpumask *)); - /* - * Non-NUMA levels cannot partially overlap - they must be either - * completely equal or completely disjoint. Otherwise we can end up - * breaking the sched_group lists - i.e. a later get_group() pass - * breaks the linking done for an earlier span. - */ - for_each_cpu_from(i, cpu_map) { /* - * We should 'and' all those masks with 'cpu_map' to exactly - * match the topology we're about to build, but that can only - * remove CPUs, which only lessens our ability to detect - * overlaps + * Non-NUMA levels cannot partially overlap - they must be either + * completely equal or completely disjoint. Otherwise we can end up + * breaking the sched_group lists - i.e. a later get_group() pass + * breaks the linking done for an earlier span. */ - if (!cpumask_equal(tl->mask(cpu), tl->mask(i)) && - cpumask_intersects(tl->mask(cpu), tl->mask(i))) - return false; + for_each_cpu(cpu, cpu_map) { + /* lowest bit set in this mask is used as a unique id */ + id = cpumask_first(tl->mask(cpu)); + + /* zeroed masks cannot possibly collide */ + if (id >= nr_cpu_ids) + continue; + + /* if this mask doesn't collide with what we've already seen */ + if (!cpumask_intersects(tl->mask(cpu), covered)) { + /* this failing would be an error in this algorithm */ + if (WARN_ON(masks[id])) + goto notsane; + + /* record the mask we saw for this id */ + masks[id] = tl->mask(cpu); + cpumask_or(covered, tl->mask(cpu), covered); + } else if ((!masks[id]) || !cpumask_equal(masks[id], tl->mask(cpu))) { + /* + * a collision with covered should have exactly matched + * a previously seen mask with the same id + */ + goto notsane; + } + } } + ret = true; - return true; + notsane: + kfree(masks); + return ret; } /* @@ -2408,9 +2441,6 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att sd = NULL; for_each_sd_topology(tl) { - if (WARN_ON(!topology_span_sane(tl, cpu_map, i))) - goto error; - sd = build_sched_domain(tl, cpu_map, attr, sd, i); has_asym |= sd->flags & SD_ASYM_CPUCAPACITY; @@ -2424,6 +2454,9 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att } } + if (WARN_ON(!topology_span_sane(cpu_map))) + goto error; + /* Build the groups for the domains */ for_each_cpu(i, cpu_map) { for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) { |