From: Cheng Jian
ohos inclusion
category: bugfix
issue: #I3ZXZF
CVE: NA
----------------------------------------
e221d028bb ("sched,rt: fix isolated CPUs leaving
root_task_group indefinitely throttled") only fixes
isolated CPUs leaving root_task_group, and not fix
all other ordinary task_groutask_group.
In some scenarios where we need attach task bind to
isolated CPUs in task_group, the same problem will occur.
Isolated CPUs and non-isolate CPUs are not in the same
root_domain. and the hrtimer only check the cpumask of
this_rq's root_domain. so when the handler of RT_BANDWIDTH
hrtimer is running on the isolated CPU, it will leaved
the non-isolated CPUs indefinitely throttled. Because
bandwidth period hrtimer can't resume them. and viceversa.
Let the bandwidth timer check all the rt_rq of cpu_online_mask.
Signed-off-by: Cheng Jian
Reviewed-by: Xie XiuQi
Signed-off-by: zhangyi (F)
Signed-off-by: Lu Jialin
Reviewed-by: xiu jianfeng
Signed-off-by: Chen Jun
Signed-off-by: Yu Changchun
---
kernel/sched/rt.c | 16 +++++++---------
1 file changed, 7 insertions(+), 9 deletions(-)
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 40f1183f3e94..71a04c491508 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -858,16 +858,14 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
span = sched_rt_period_mask();
#ifdef CONFIG_RT_GROUP_SCHED
/*
- * FIXME: isolated CPUs should really leave the root task group,
- * whether they are isolcpus or were isolated via cpusets, lest
- * the timer run on a CPU which does not service all runqueues,
- * potentially leaving other CPUs indefinitely throttled. If
- * isolation is really required, the user will turn the throttle
- * off to kill the perturbations it causes anyway. Meanwhile,
- * this maintains functionality for boot and/or troubleshooting.
+ * When the tasks in the task_group run on either isolated
+ * CPUs or non-isolated CPUs, whether they are isolcpus or
+ * were isolated via cpusets, check all the online rt_rq
+ * to lest the timer run on a CPU which does not service
+ * all runqueues, potentially leaving other CPUs indefinitely
+ * throttled.
*/
- if (rt_b == &root_task_group.rt_bandwidth)
- span = cpu_online_mask;
+ span = cpu_online_mask;
#endif
for_each_cpu(i, span) {
int enqueue = 0;
--
2.22.0
