sched/fair: Clean up active balance nr_balance_failed trickery

When triggering an active load balance, sd->nr_balance_failed is set to
such a value that any further can_migrate_task() using said sd will ignore
the output of task_hot().

This behaviour makes sense, as active load balance intentionally preempts a
rq's running task to migrate it right away, but this asynchronous write is
a bit shoddy, as the stopper thread might run active_load_balance_cpu_stop
before the sd->nr_balance_failed write either becomes visible to the
stopper's CPU or even happens on the CPU that appended the stopper work.

Add a struct lb_env flag to denote active balancing, and use it in
can_migrate_task(). Remove the sd->nr_balance_failed write that served the
same purpose. Cleanup the LBF_DST_PINNED active balance special case.

Signed-off-by: Valentin Schneider <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Reviewed-by: Dietmar Eggemann <[email protected]>
Reviewed-by: Vincent Guittot <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]

Author: Valentin Schneider

kernel/sched/fair.c

@@ -7453,6 +7453,7 @@ enum migration_type {
 #define LBF_NEED_BREAK	0x02
 #define LBF_DST_PINNED  0x04
 #define LBF_SOME_PINNED	0x08
+#define LBF_ACTIVE_LB	0x10
 
 struct lb_env {
 	struct sched_domain	*sd;
@@ -7614,10 +7615,13 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
 		 * our sched_group. We may want to revisit it if we couldn't
 		 * meet load balance goals by pulling other tasks on src_cpu.
 		 *
-		 * Avoid computing new_dst_cpu for NEWLY_IDLE or if we have
-		 * already computed one in current iteration.
+		 * Avoid computing new_dst_cpu
+		 * - for NEWLY_IDLE
+		 * - if we have already computed one in current iteration
+		 * - if it's an active balance
 		 */
-		if (env->idle == CPU_NEWLY_IDLE || (env->flags & LBF_DST_PINNED))
+		if (env->idle == CPU_NEWLY_IDLE ||
+		    env->flags & (LBF_DST_PINNED | LBF_ACTIVE_LB))
 			return 0;
 
 		/* Prevent to re-select dst_cpu via env's CPUs: */
@@ -7642,10 +7646,14 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
 
 	/*
 	 * Aggressive migration if:
-	 * 1) destination numa is preferred
-	 * 2) task is cache cold, or
-	 * 3) too many balance attempts have failed.
+	 * 1) active balance
+	 * 2) destination numa is preferred
+	 * 3) task is cache cold, or
+	 * 4) too many balance attempts have failed.
 	 */
+	if (env->flags & LBF_ACTIVE_LB)
+		return 1;
+
 	tsk_cache_hot = migrate_degrades_locality(p, env);
 	if (tsk_cache_hot == -1)
 		tsk_cache_hot = task_hot(p, env);
@@ -9836,9 +9844,6 @@ static int load_balance(int this_cpu, struct rq *this_rq,
 					active_load_balance_cpu_stop, busiest,
 					&busiest->active_balance_work);
 			}
-
-			/* We've kicked active balancing, force task migration. */
-			sd->nr_balance_failed = sd->cache_nice_tries+1;
 		}
 	} else {
 		sd->nr_balance_failed = 0;
@@ -9988,13 +9993,7 @@ static int active_load_balance_cpu_stop(void *data)
 			.src_cpu	= busiest_rq->cpu,
 			.src_rq		= busiest_rq,
 			.idle		= CPU_IDLE,
-			/*
-			 * can_migrate_task() doesn't need to compute new_dst_cpu
-			 * for active balancing. Since we have CPU_IDLE, but no
-			 * @dst_grpmask we need to make that test go away with lying
-			 * about DST_PINNED.
-			 */
-			.flags		= LBF_DST_PINNED,
+			.flags		= LBF_ACTIVE_LB,
 		};
 
 		schedstat_inc(sd->alb_count);