On 19/04/23 22:19, Yury Norov wrote:
> +/*
> + * sched_numa_find_next_cpu() - given the NUMA topology, find the next cpu
> + * cpumask: cpumask to find a cpu from
> + * cpu: current cpu
> + * node: local node
> + * hop: (in/out) indicates distance order of current CPU to a local node
> + *
> + * The function searches for next cpu at a given NUMA distance, indicated
> + * by hop, and if nothing found, tries to find CPUs at a greater distance,
> + * starting from the beginning.
> + *
> + * Return: cpu, or >= nr_cpu_ids when nothing found.
> + */
> +int sched_numa_find_next_cpu(const struct cpumask *cpus, int cpu, int node, unsigned int *hop)
> +{
> + unsigned long *cur, *prev;
> + struct cpumask ***masks;
> + unsigned int ret;
> +
> + if (*hop >= sched_domains_numa_levels)
> + return nr_cpu_ids;
> +
> + masks = rcu_dereference(sched_domains_numa_masks);
> + cur = cpumask_bits(masks[*hop][node]);
> + if (*hop == 0)
> + ret = find_next_and_bit(cpumask_bits(cpus), cur, nr_cpu_ids, cpu);
> + else {
> + prev = cpumask_bits(masks[*hop - 1][node]);
> + ret = find_next_and_andnot_bit(cpumask_bits(cpus), cur, prev, nr_cpu_ids, cpu);
> + }
> +
> + if (ret < nr_cpu_ids)
> + return ret;
> +
> + *hop += 1;
> + return sched_numa_find_next_cpu(cpus, 0, node, hop);
sched_domains_numa_levels is a fairly small number, so the recursion depth
isn't something we really need to worry about - still, the iterative
variant of this is fairly straightforward to get to:
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index e850f16c003ae..4c9a9e48fef6d 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -2151,23 +2151,27 @@ int sched_numa_find_next_cpu(const struct cpumask *cpus, int cpu, int node, unsi
struct cpumask ***masks;
unsigned int ret;
- if (*hop >= sched_domains_numa_levels)
- return nr_cpu_ids;
+ /*
+ * Reset @cpu to 0 when increasing @hop, since CPU numbering has no
+ * relationship with NUMA distance: a search at @hop+1 may yield CPUs
+ * of lower ID than previously seen!
+ */
+ for (; *hop >= sched_domains_numa_levels; *hop += 1, cpu = 0) {
+ masks = rcu_dereference(sched_domains_numa_masks);
+ cur = cpumask_bits(masks[*hop][node]);
+
+ if (*hop == 0) {
+ ret = find_next_and_bit(cpumask_bits(cpus), cur, nr_cpu_ids, cpu);
+ } else {
+ prev = cpumask_bits(masks[*hop - 1][node]);
+ ret = find_next_and_andnot_bit(cpumask_bits(cpus), cur, prev, nr_cpu_ids, cpu);
+ }
- masks = rcu_dereference(sched_domains_numa_masks);
- cur = cpumask_bits(masks[*hop][node]);
- if (*hop == 0)
- ret = find_next_and_bit(cpumask_bits(cpus), cur, nr_cpu_ids, cpu);
- else {
- prev = cpumask_bits(masks[*hop - 1][node]);
- ret = find_next_and_andnot_bit(cpumask_bits(cpus), cur, prev, nr_cpu_ids, cpu);
+ if (ret < nr_cpu_ids)
+ return ret;
}
- if (ret < nr_cpu_ids)
- return ret;
-
- *hop += 1;
- return sched_numa_find_next_cpu(cpus, 0, node, hop);
+ return nr_cpu_ids;
}
EXPORT_SYMBOL_GPL(sched_numa_find_next_cpu);
