Tariq has pointed out that drivers allocating IRQ vectors would benefit
from having smarter NUMA-awareness - cpumask_local_spread() only knows
about the local node and everything outside is in the same bucket.

sched_domains_numa_masks is pretty much what we want to hand out (a cpumask
of CPUs reachable within a given distance budget), introduce
sched_numa_hop_mask() to export those cpumasks. Add in an iteration helper
to iterate over CPUs at an incremental distance from a given node.

Link: http://lore.kernel.org/r/20220728191203.4055-1-tariqt@nvidia.com (local)
Signed-off-by: Valentin Schneider <vschneid@redhat.com>
---
  include/linux/topology.h | 12 ++++++++++++
  kernel/sched/topology.c  | 28 ++++++++++++++++++++++++++++
  2 files changed, 40 insertions(+)

diff --git a/include/linux/topology.h b/include/linux/topology.h
index 4564faafd0e1..d66e3cf40823 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h

@@ -245,5 +245,17 @@ static inline const struct cpumask *cpu_cpu_mask(int cpu)
  	return cpumask_of_node(cpu_to_node(cpu));
  }
  
+#ifdef CONFIG_NUMA
+extern const struct cpumask *sched_numa_hop_mask(int node, int hops);
+#else
+static inline const struct cpumask *sched_numa_hop_mask(int node, int hops)
+{
+	return -ENOTSUPP;

+}
+#endif	/* CONFIG_NUMA */
+
+#define for_each_numa_hop_mask(node, hops, mask)			\
+	for (mask = sched_numa_hop_mask(node, hops); !IS_ERR_OR_NULL(mask); \
+	     mask = sched_numa_hop_mask(node, ++hops))
  
  #endif /* _LINUX_TOPOLOGY_H */

diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 8739c2a5a54e..f0236a0ae65c 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c

@@ -2067,6 +2067,34 @@ int sched_numa_find_closest(const struct cpumask *cpus, int cpu)
  	return found;
  }
  
+/**
+ * sched_numa_hop_mask() - Get the cpumask of CPUs at most @hops hops away.
+ * @node: The node to count hops from.
+ * @hops: Include CPUs up to that many hops away. 0 means local node.
+ *
+ * Requires rcu_lock to be held. Returned cpumask is only valid within that
+ * read-side section, copy it if required beyond that.
+ *
+ * Note that not all hops are equal in size; see sched_init_numa() for how
+ * distances and masks are handled.
+ *
+ * Also note that this is a reflection of sched_domains_numa_masks, which may change
+ * during the lifetime of the system (offline nodes are taken out of the masks).
+ */
+const struct cpumask *sched_numa_hop_mask(int node, int hops)
+{
+	struct cpumask ***masks = rcu_dereference(sched_domains_numa_masks);
+
+	if (node >= nr_node_ids || hops >= sched_domains_numa_levels)
+		return ERR_PTR(-EINVAL);
+
+	if (!masks)
+		return NULL;
+
+	return masks[hops][node];
+}
+EXPORT_SYMBOL_GPL(sched_numa_hop_mask);
+
  #endif /* CONFIG_NUMA */
  
  static int __sdt_alloc(const struct cpumask *cpu_map)