Similarly to the inner loop, in the outer loop we can use for_each_cpu()
macro, and skip CPUs that have been copied.

With this patch, the function becomes O(1), despite that it's a
double-loop.

While here, add a comment why we can't merge the inner and outer logic.

Signed-off-by: Yury Norov <yury.norov@gmail.com>
---
 lib/group_cpus.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/lib/group_cpus.c b/lib/group_cpus.c
index 0a8ac7cb1a5d..952aac9eaa81 100644
--- a/lib/group_cpus.c
+++ b/lib/group_cpus.c
@@ -17,16 +17,17 @@ static void grp_spread_init_one(struct cpumask *irqmsk, struct cpumask *nmsk,
 	const struct cpumask *siblmsk;
 	int cpu, sibl;
 
-	for ( ; cpus_per_grp > 0; ) {
-		cpu = cpumask_first(nmsk);
-
-		/* Should not happen, but I'm too lazy to think about it */
-		if (cpu >= nr_cpu_ids)
+	for_each_cpu(cpu, nmsk) {
+		if (cpus_per_grp-- == 0)
 			return;
 
+		/*
+		 * If a caller wants to spread IRQa on offline CPUs, we need to
+		 * take care of it explicitly because those offline CPUS are not
+		 * included in siblings cpumask.
+		 */
 		__cpumask_clear_cpu(cpu, nmsk);
 		__cpumask_set_cpu(cpu, irqmsk);
-		cpus_per_grp--;
 
 		/* If the cpu has siblings, use them first */
 		siblmsk = topology_sibling_cpumask(cpu);
@@ -38,6 +39,7 @@ static void grp_spread_init_one(struct cpumask *irqmsk, struct cpumask *nmsk,
 
 			__cpumask_clear_cpu(sibl, nmsk);
 			__cpumask_set_cpu(sibl, irqmsk);
+			cpu = sibl + 1;
 		}
 	}
 }
-- 
2.40.1