The following commit has been merged into the sched/core branch of tip:
Commit-ID: d37aee9018e68b0d356195caefbb651910e0bbfa
Gitweb: https://git.kernel.org/tip/d37aee9018e68b0d356195caefbb651910e0bbfa
Author: Qais Yousef <qais.yousef@xxxxxxx>
AuthorDate: Thu, 16 Dec 2021 22:53:20
Committer: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
CommitterDate: Thu, 27 Jan 2022 12:57:19 +01:00
sched/uclamp: Fix iowait boost escaping uclamp restriction
iowait_boost signal is applied independently of util and doesn't take
into account uclamp settings of the rq. An io heavy task that is capped
by uclamp_max could still request higher frequency because
sugov_iowait_apply() doesn't clamp the boost via uclamp_rq_util_with()
like effective_cpu_util() does.
Make sure that iowait_boost honours uclamp requests by calling
uclamp_rq_util_with() when applying the boost.
Fixes: 982d9cdc22c9 ("sched/cpufreq, sched/uclamp: Add clamps for FAIR and RT tasks")
Signed-off-by: Qais Yousef <qais.yousef@xxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@xxxxxxxxx>
Link: https://lore.kernel.org/r/20211216225320.2957053-3-qais.yousef@xxxxxxx
---
kernel/sched/cpufreq_schedutil.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 62d98b0..6d65ab6 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -289,6 +289,7 @@ static void sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time)
* into the same scale so we can compare.
*/
boost = (sg_cpu->iowait_boost * sg_cpu->max) >> SCHED_CAPACITY_SHIFT;
+ boost = uclamp_rq_util_with(cpu_rq(sg_cpu->cpu), boost, NULL);
if (sg_cpu->util < boost)
sg_cpu->util = boost;
}
|