lib: Restrict cpumask_local_spread to houskeeping CPUs

The current implementation of cpumask_local_spread() does not respect the
isolated CPUs, i.e., even if a CPU has been isolated for Real-Time task,
it will return it to the caller for pinning of its IRQ threads. Having
these unwanted IRQ threads on an isolated CPU adds up to a latency
overhead.

Restrict the CPUs that are returned for spreading IRQs only to the
available housekeeping CPUs.
Signed-off-by: Alex Belits <abelits@marvell.com>
Signed-off-by: Nitesh Narayan Lal <nitesh@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200625223443.2684-2-nitesh@redhat.com

lib/cpumask.c

@@ -6,6 +6,7 @@
 #include <linux/export.h>
 #include <linux/memblock.h>
 #include <linux/numa.h>
+#include <linux/sched/isolation.h>
 
 /**
  * cpumask_next - get the next cpu in a cpumask
@@ -205,22 +206,27 @@ void __init free_bootmem_cpumask_var(cpumask_var_t mask)
  */
 unsigned int cpumask_local_spread(unsigned int i, int node)
 {
-	int cpu;
+	int cpu, hk_flags;
+	const struct cpumask *mask;
 
+	hk_flags = HK_FLAG_DOMAIN | HK_FLAG_MANAGED_IRQ;
+	mask = housekeeping_cpumask(hk_flags);
 	/* Wrap: we always want a cpu. */
-	i %= num_online_cpus();
+	i %= cpumask_weight(mask);
 
 	if (node == NUMA_NO_NODE) {
-		for_each_cpu(cpu, cpu_online_mask)
+		for_each_cpu(cpu, mask) {
 			if (i-- == 0)
 				return cpu;
+		}
 	} else {
 		/* NUMA first. */
-		for_each_cpu_and(cpu, cpumask_of_node(node), cpu_online_mask)
+		for_each_cpu_and(cpu, cpumask_of_node(node), mask) {
 			if (i-- == 0)
 				return cpu;
+		}
 
-		for_each_cpu(cpu, cpu_online_mask) {
+		for_each_cpu(cpu, mask) {
 			/* Skip NUMA nodes, done above. */
 			if (cpumask_test_cpu(cpu, cpumask_of_node(node)))
 				continue;