On Thu, Nov 10, 2022 at 08:00:26PM -0800, Yury Norov wrote: > The function finds Nth set CPU in a given cpumask starting from a given > node. > > Leveraging the fact that each hop in sched_domains_numa_masks includes the > same or greater number of CPUs than the previous one, we can use binary > search on hops instead of linear walk, which makes the overall complexity > of O(log n) in terms of number of cpumask_weight() calls. > > Signed-off-by: Yury Norov <yury.norov@xxxxxxxxx> > --- > include/linux/topology.h | 8 ++++++++ > kernel/sched/topology.c | 42 ++++++++++++++++++++++++++++++++++++++++ > 2 files changed, 50 insertions(+) > > diff --git a/include/linux/topology.h b/include/linux/topology.h > index 4564faafd0e1..63048ac3207c 100644 > --- a/include/linux/topology.h > +++ b/include/linux/topology.h > @@ -245,5 +245,13 @@ static inline const struct cpumask *cpu_cpu_mask(int cpu) > return cpumask_of_node(cpu_to_node(cpu)); > } > > +#ifdef CONFIG_NUMA > +int sched_numa_find_nth_cpu(const struct cpumask *cpus, int cpu, int node); > +#else > +int sched_numa_find_nth_cpu(const struct cpumask *cpus, int cpu, int node) Ah, this should be static of course. > +{ > + return cpumask_nth(cpu, cpus); > +} > +#endif /* CONFIG_NUMA */ > > #endif /* _LINUX_TOPOLOGY_H */ > diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c > index 8739c2a5a54e..c8f56287de46 100644 > --- a/kernel/sched/topology.c > +++ b/kernel/sched/topology.c > @@ -2067,6 +2067,48 @@ int sched_numa_find_closest(const struct cpumask *cpus, int cpu) > return found; > } > > +/* > + * sched_numa_find_nth_cpu() - given the NUMA topology, find the Nth next cpu > + * closest to @cpu from @cpumask. > + * cpumask: cpumask to find a cpu from > + * cpu: Nth cpu to find > + * > + * returns: cpu, or >= nr_cpu_ids when nothing found. > + */ > +int sched_numa_find_nth_cpu(const struct cpumask *cpus, int cpu, int node) > +{ > + unsigned int first = 0, mid, last = sched_domains_numa_levels; > + struct cpumask ***masks; > + int w, ret = nr_cpu_ids; > + > + rcu_read_lock(); > + masks = rcu_dereference(sched_domains_numa_masks); > + if (!masks) > + goto out; > + > + while (last >= first) { > + mid = (last + first) / 2; > + > + if (cpumask_weight_and(cpus, masks[mid][node]) <= cpu) { > + first = mid + 1; > + continue; > + } > + > + w = (mid == 0) ? 0 : cpumask_weight_and(cpus, masks[mid - 1][node]); > + if (w <= cpu) > + break; > + > + last = mid - 1; > + } > + > + ret = (mid == 0) ? > + cpumask_nth_and(cpu - w, cpus, masks[mid][node]) : > + cpumask_nth_and_andnot(cpu - w, cpus, masks[mid][node], masks[mid - 1][node]); > +out: > + rcu_read_unlock(); > + return ret; > +} > +EXPORT_SYMBOL_GPL(sched_numa_find_nth_cpu); > #endif /* CONFIG_NUMA */ > > static int __sdt_alloc(const struct cpumask *cpu_map) > -- > 2.34.1