sched/topology: Move comment about asymmetric node setups
authorLauro Ramos Venancio <lvenanci@redhat.com>
Thu, 20 Apr 2017 19:51:42 +0000 (16:51 -0300)
committerIngo Molnar <mingo@kernel.org>
Mon, 15 May 2017 08:15:27 +0000 (10:15 +0200)
Signed-off-by: Lauro Ramos Venancio <lvenanci@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: lwang@redhat.com
Cc: riel@redhat.com
Link: http://lkml.kernel.org/r/1492717903-5195-4-git-send-email-lvenanci@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
kernel/sched/topology.c

index 5a4d9ae..c10f44a 100644 (file)
@@ -495,14 +495,6 @@ enum s_alloc {
 /*
  * Build an iteration mask that can exclude certain CPUs from the upwards
  * domain traversal.
- *
- * Asymmetric node setups can result in situations where the domain tree is of
- * unequal depth, make sure to skip domains that already cover the entire
- * range.
- *
- * In that case build_sched_domains() will have terminated the iteration early
- * and our sibling sd spans will be empty. Domains should always include the
- * CPU they're built on, so check that.
  */
 static void build_group_mask(struct sched_domain *sd, struct sched_group *sg)
 {
@@ -590,7 +582,16 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu)
 
                sibling = *per_cpu_ptr(sdd->sd, i);
 
-               /* See the comment near build_group_mask(). */
+               /*
+                * Asymmetric node setups can result in situations where the
+                * domain tree is of unequal depth, make sure to skip domains
+                * that already cover the entire range.
+                *
+                * In that case build_sched_domains() will have terminated the
+                * iteration early and our sibling sd spans will be empty.
+                * Domains should always include the CPU they're built on, so
+                * check that.
+                */
                if (!cpumask_test_cpu(i, sched_domain_span(sibling)))
                        continue;