summaryrefslogtreecommitdiff
path: root/kernel/sched
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/sched')
-rw-r--r--kernel/sched/topology.c91
1 files changed, 61 insertions, 30 deletions
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 09d35044bd88..12f80587e127 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -723,35 +723,6 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
for (tmp = sd; tmp; tmp = tmp->parent)
numa_distance += !!(tmp->flags & SD_NUMA);
- /*
- * FIXME: Diameter >=3 is misrepresented.
- *
- * Smallest diameter=3 topology is:
- *
- * node 0 1 2 3
- * 0: 10 20 30 40
- * 1: 20 10 20 30
- * 2: 30 20 10 20
- * 3: 40 30 20 10
- *
- * 0 --- 1 --- 2 --- 3
- *
- * NUMA-3 0-3 N/A N/A 0-3
- * groups: {0-2},{1-3} {1-3},{0-2}
- *
- * NUMA-2 0-2 0-3 0-3 1-3
- * groups: {0-1},{1-3} {0-2},{2-3} {1-3},{0-1} {2-3},{0-2}
- *
- * NUMA-1 0-1 0-2 1-3 2-3
- * groups: {0},{1} {1},{2},{0} {2},{3},{1} {3},{2}
- *
- * NUMA-0 0 1 2 3
- *
- * The NUMA-2 groups for nodes 0 and 3 are obviously buggered, as the
- * group span isn't a subset of the domain span.
- */
- WARN_ONCE(numa_distance > 2, "Shortest NUMA path spans too many nodes\n");
-
sched_domain_debug(sd, cpu);
rq_attach_root(rq, rd);
@@ -982,6 +953,31 @@ static void init_overlap_sched_group(struct sched_domain *sd,
sg->sgc->max_capacity = SCHED_CAPACITY_SCALE;
}
+static struct sched_domain *
+find_descended_sibling(struct sched_domain *sd, struct sched_domain *sibling)
+{
+ /*
+ * The proper descendant would be the one whose child won't span out
+ * of sd
+ */
+ while (sibling->child &&
+ !cpumask_subset(sched_domain_span(sibling->child),
+ sched_domain_span(sd)))
+ sibling = sibling->child;
+
+ /*
+ * As we are referencing sgc across different topology level, we need
+ * to go down to skip those sched_domains which don't contribute to
+ * scheduling because they will be degenerated in cpu_attach_domain
+ */
+ while (sibling->child &&
+ cpumask_equal(sched_domain_span(sibling->child),
+ sched_domain_span(sibling)))
+ sibling = sibling->child;
+
+ return sibling;
+}
+
static int
build_overlap_sched_groups(struct sched_domain *sd, int cpu)
{
@@ -1015,6 +1011,41 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu)
if (!cpumask_test_cpu(i, sched_domain_span(sibling)))
continue;
+ /*
+ * Usually we build sched_group by sibling's child sched_domain
+ * But for machines whose NUMA diameter are 3 or above, we move
+ * to build sched_group by sibling's proper descendant's child
+ * domain because sibling's child sched_domain will span out of
+ * the sched_domain being built as below.
+ *
+ * Smallest diameter=3 topology is:
+ *
+ * node 0 1 2 3
+ * 0: 10 20 30 40
+ * 1: 20 10 20 30
+ * 2: 30 20 10 20
+ * 3: 40 30 20 10
+ *
+ * 0 --- 1 --- 2 --- 3
+ *
+ * NUMA-3 0-3 N/A N/A 0-3
+ * groups: {0-2},{1-3} {1-3},{0-2}
+ *
+ * NUMA-2 0-2 0-3 0-3 1-3
+ * groups: {0-1},{1-3} {0-2},{2-3} {1-3},{0-1} {2-3},{0-2}
+ *
+ * NUMA-1 0-1 0-2 1-3 2-3
+ * groups: {0},{1} {1},{2},{0} {2},{3},{1} {3},{2}
+ *
+ * NUMA-0 0 1 2 3
+ *
+ * The NUMA-2 groups for nodes 0 and 3 are obviously buggered, as the
+ * group span isn't a subset of the domain span.
+ */
+ if (sibling->child &&
+ !cpumask_subset(sched_domain_span(sibling->child), span))
+ sibling = find_descended_sibling(sd, sibling);
+
sg = build_group_from_child_sched_domain(sibling, cpu);
if (!sg)
goto fail;
@@ -1022,7 +1053,7 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu)
sg_span = sched_group_span(sg);
cpumask_or(covered, covered, sg_span);
- init_overlap_sched_group(sd, sg);
+ init_overlap_sched_group(sibling, sg);
if (!first)
first = sg;