powerpc/smp: Optimize remove_cpu_from_masks

While offlining a CPU, system currently iterate through all the CPUs in
the DIE to clear sibling, l2_cache and smallcore maps. However if there
are more cores in a DIE, system can end up spending more time iterating
through CPUs which are completely unrelated.

Optimize this by only iterating through smaller but relevant cpumap.
If shared_cache is set, cpu_l2_cache_map should be relevant else
cpu_sibling_map would be relevant.
Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Tested-by: Satheesh Rajendran <sathnaga@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200921095653.9701-5-srikar@linux.vnet.ibm.com

arch/powerpc/kernel/smp.c

@@ -1263,14 +1263,21 @@ static bool update_mask_by_l2(int cpu, struct cpumask *(*mask_fn)(int))
 #ifdef CONFIG_HOTPLUG_CPU
 static void remove_cpu_from_masks(int cpu)
 {
+	struct cpumask *(*mask_fn)(int) = cpu_sibling_mask;
 	int i;
 
-	for_each_cpu(i, cpu_cpu_mask(cpu)) {
+	if (shared_caches)
+		mask_fn = cpu_l2_cache_mask;
+
+	for_each_cpu(i, mask_fn(cpu)) {
 		set_cpus_unrelated(cpu, i, cpu_l2_cache_mask);
 		set_cpus_unrelated(cpu, i, cpu_sibling_mask);
 		if (has_big_cores)
 			set_cpus_unrelated(cpu, i, cpu_smallcore_mask);
-		if (has_coregroup_support())
+	}
+
+	if (has_coregroup_support()) {
+		for_each_cpu(i, cpu_coregroup_mask(cpu))
 			set_cpus_unrelated(cpu, i, cpu_coregroup_mask);
 	}
 }