Merge "sched: avoid migrating when softint on tgt cpu should be short"

1 files changed, 41 insertions, 6 deletions

diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index fd27394354a1..c03d51a017bf 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -5,6 +5,7 @@
 
 #include "sched.h"
 
+#include <linux/interrupt.h>
 #include <linux/slab.h>
 #include <linux/irq_work.h>
 #include <trace/events/sched.h>
@@ -1459,11 +1460,30 @@ select_task_rq_rt_hmp(struct task_struct *p, int cpu, int sd_flag, int flags)
 }
 #endif
 
+/*
+ * Return whether the task on the given cpu is currently non-preemptible
+ * while handling a potentially long softint, or if the task is likely
+ * to block preemptions soon because it is a ksoftirq thread that is
+ * handling slow softints.
+ */
+bool
+task_may_not_preempt(struct task_struct *task, int cpu)
+{
+	__u32 softirqs = per_cpu(active_softirqs, cpu) |
+			 __IRQ_STAT(cpu, __softirq_pending);
+	struct task_struct *cpu_ksoftirqd = per_cpu(ksoftirqd, cpu);
+
+	return ((softirqs & LONG_SOFTIRQ_MASK) &&
+		(task == cpu_ksoftirqd ||
+		 task_thread_info(task)->preempt_count & SOFTIRQ_MASK));
+}
+
 static int
 select_task_rq_rt(struct task_struct *p, int cpu, int sd_flag, int flags)
 {
 	struct task_struct *curr;
 	struct rq *rq;
+	bool may_not_preempt;
 
 #ifdef CONFIG_SCHED_HMP
 	return select_task_rq_rt_hmp(p, cpu, sd_flag, flags);
@@ -1479,7 +1499,17 @@ select_task_rq_rt(struct task_struct *p, int cpu, int sd_flag, int flags)
 	curr = READ_ONCE(rq->curr); /* unlocked access */
 
 	/*
-	 * If the current task on @p's runqueue is an RT task, then
+	 * If the current task on @p's runqueue is a softirq task,
+	 * it may run without preemption for a time that is
+	 * ill-suited for a waiting RT task. Therefore, try to
+	 * wake this RT task on another runqueue.
+	 *
+	 * Also, if the current task on @p's runqueue is an RT task, then
+	 * it may run without preemption for a time that is
+	 * ill-suited for a waiting RT task. Therefore, try to
+	 * wake this RT task on another runqueue.
+	 *
+	 * Also, if the current task on @p's runqueue is an RT task, then
 	 * try to see if we can wake this RT task up on another
 	 * runqueue. Otherwise simply start this RT task
 	 * on its current runqueue.
@@ -1500,17 +1530,22 @@ select_task_rq_rt(struct task_struct *p, int cpu, int sd_flag, int flags)
 	 * This test is optimistic, if we get it wrong the load-balancer
 	 * will have to sort it out.
 	 */
-	if (curr && unlikely(rt_task(curr)) &&
+	may_not_preempt = task_may_not_preempt(curr, cpu);
+	if (may_not_preempt ||
+	    (unlikely(rt_task(curr)) &&
 	    (curr->nr_cpus_allowed < 2 ||
-	     curr->prio <= p->prio)) {
+	     curr->prio <= p->prio))) {
 		int target = find_lowest_rq(p);
 
 		/*
-		 * Don't bother moving it if the destination CPU is
-		 * not running a lower priority task.
+		 * If cpu is non-preemptible, prefer remote cpu
+		 * even if it's running a higher-prio task.
+		 * Otherwise: Don't bother moving it if the
+		 * destination CPU is not running a lower priority task.
 		 */
 		if (target != -1 &&
-		    p->prio < cpu_rq(target)->rt.highest_prio.curr)
+		   (may_not_preempt ||
+		    p->prio < cpu_rq(target)->rt.highest_prio.curr))
 			cpu = target;
 	}
 	rcu_read_unlock();