sched/numa: Fix NULL pointer dereference in task_numa_migrate()

The cpusets code can split up the scheduler's domain tree into
smaller domains.  Some of those smaller domains may not cross
NUMA nodes at all, leading to a NULL pointer dereference on the
per-cpu sd_numa pointer.

Tasks cannot be migrated out of their domain, so the patch
also sets p->numa_preferred_nid to whereever they are, to
prevent the migration from being retried over and over again.

Reported-by: Prarit Bhargava <prarit@redhat.com>
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Mel Gorman <mgorman@suse.de>
Link: http://lkml.kernel.org/n/tip-oosqomw0Jput0Jkvoowhrqtu@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 13 insertions, 1 deletions

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index df77c605c7a6..c11e36ff5ea0 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1201,9 +1201,21 @@ static int task_numa_migrate(struct task_struct *p)
 	 */
 	rcu_read_lock();
 	sd = rcu_dereference(per_cpu(sd_numa, env.src_cpu));
-	env.imbalance_pct = 100 + (sd->imbalance_pct - 100) / 2;
+	if (sd)
+		env.imbalance_pct = 100 + (sd->imbalance_pct - 100) / 2;
 	rcu_read_unlock();
 
+	/*
+	 * Cpusets can break the scheduler domain tree into smaller
+	 * balance domains, some of which do not cross NUMA boundaries.
+	 * Tasks that are "trapped" in such domains cannot be migrated
+	 * elsewhere, so there is no point in (re)trying.
+	 */
+	if (unlikely(!sd)) {
+		p->numa_preferred_nid = cpu_to_node(task_cpu(p));
+		return -EINVAL;
+	}
+
 	taskweight = task_weight(p, env.src_nid);
 	groupweight = group_weight(p, env.src_nid);
 	update_numa_stats(&env.src_stats, env.src_nid);