[PATCH 11/13] sched/numa: Find an alternative idle CPU if the CPU is part of an active NUMA balance

[Mel Gorman]

Multiple tasks can attempt to select and idle CPU but fail because
numa_migrate_on is already set and the migration fails. Instead of failing,
scan for an alternative idle CPU. select_idle_sibling is not used because
it requires IRQs to be disabled and it ignores numa_migrate_on allowing
multiple tasks to stack. This scan may still fail if there are idle
candidate CPUs due to races but if this occurs, it's best that a task
stay on an available CPU that move to a contended one.

Signed-off-by: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>
---
 kernel/sched/fair.c | 40 ++++++++++++++++++++++------------------
 1 file changed, 22 insertions(+), 18 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 91f8156c0b0f..b216e9e84d07 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1624,15 +1624,34 @@ static void task_numa_assign(struct task_numa_env *env,
 {
 	struct rq *rq = cpu_rq(env->dst_cpu);
 
-	/* Bail out if run-queue part of active NUMA balance. */
-	if (env->best_cpu != env->dst_cpu && xchg(&rq->numa_migrate_on, 1))
+	/* Check if run-queue part of active NUMA balance. */
+	if (env->best_cpu != env->dst_cpu && xchg(&rq->numa_migrate_on, 1)) {
+		int cpu;
+		int start = env->dst_cpu;
+
+		/* Find alternative idle CPU. */
+		for_each_cpu_wrap(cpu, cpumask_of_node(env->dst_nid), start) {
+			if (cpu == env->best_cpu || !idle_cpu(cpu) ||
+			    !cpumask_test_cpu(cpu, env->p->cpus_ptr)) {
+				continue;
+			}
+
+			env->dst_cpu = cpu;
+			rq = cpu_rq(env->dst_cpu);
+			if (!xchg(&rq->numa_migrate_on, 1))
+				goto assign;
+		}
+
+		/* Failed to find an alternative idle CPU */
 		return;
+	}
 
+assign:
 	/*
 	 * Clear previous best_cpu/rq numa-migrate flag, since task now
 	 * found a better CPU to move/swap.
 	 */
-	if (env->best_cpu != -1) {
+	if (env->best_cpu != -1 && env->best_cpu != env->dst_cpu) {
 		rq = cpu_rq(env->best_cpu);
 		WRITE_ONCE(rq->numa_migrate_on, 0);
 	}
@@ -1806,21 +1825,6 @@ static void task_numa_compare(struct task_numa_env *env,
 			cpu = env->best_cpu;
 		}
 
-		/*
-		 * Use select_idle_sibling if the previously found idle CPU is
-		 * not idle any more.
-		 */
-		if (!idle_cpu(cpu)) {
-			/*
-			 * select_idle_siblings() uses an per-CPU cpumask that
-			 * can be used from IRQ context.
-			 */
-			local_irq_disable();
-			cpu = select_idle_sibling(env->p, env->src_cpu,
-						   env->dst_cpu);
-			local_irq_enable();
-		}
-
 		env->dst_cpu = cpu;
 	}
 
-- 
2.16.4