aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--kernel/sched/cpufreq_schedutil.c15
-rw-r--r--kernel/sched/fair.c4
-rw-r--r--kernel/sched/rt.c4
-rw-r--r--kernel/sched/sched.h23
4 files changed, 43 insertions, 3 deletions
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 7c4ce69067c4..d84e036a7536 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -202,8 +202,10 @@ unsigned long schedutil_freq_util(int cpu, unsigned long util_cfs,
unsigned long dl_util, util, irq;
struct rq *rq = cpu_rq(cpu);
- if (type == FREQUENCY_UTIL && rt_rq_is_runnable(&rq->rt))
+ if (!IS_BUILTIN(CONFIG_UCLAMP_TASK) &&
+ type == FREQUENCY_UTIL && rt_rq_is_runnable(&rq->rt)) {
return max;
+ }
/*
* Early check to see if IRQ/steal time saturates the CPU, can be
@@ -219,9 +221,16 @@ unsigned long schedutil_freq_util(int cpu, unsigned long util_cfs,
* CFS tasks and we use the same metric to track the effective
* utilization (PELT windows are synchronized) we can directly add them
* to obtain the CPU's actual utilization.
+ *
+ * CFS and RT utilization can be boosted or capped, depending on
+ * utilization clamp constraints requested by currently RUNNABLE
+ * tasks.
+ * When there are no CFS RUNNABLE tasks, clamps are released and
+ * frequency will be gracefully reduced with the utilization decay.
*/
- util = util_cfs;
- util += cpu_util_rt(rq);
+ util = util_cfs + cpu_util_rt(rq);
+ if (type == FREQUENCY_UTIL)
+ util = uclamp_util(rq, util);
dl_util = cpu_util_dl(rq);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 3bdcd3c718bc..28db7ce5c3a6 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -10393,6 +10393,10 @@ const struct sched_class fair_sched_class = {
#ifdef CONFIG_FAIR_GROUP_SCHED
.task_change_group = task_change_group_fair,
#endif
+
+#ifdef CONFIG_UCLAMP_TASK
+ .uclamp_enabled = 1,
+#endif
};
#ifdef CONFIG_SCHED_DEBUG
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 63ad7c90822c..a532558a5176 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -2400,6 +2400,10 @@ const struct sched_class rt_sched_class = {
.switched_to = switched_to_rt,
.update_curr = update_curr_rt,
+
+#ifdef CONFIG_UCLAMP_TASK
+ .uclamp_enabled = 1,
+#endif
};
#ifdef CONFIG_RT_GROUP_SCHED
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 0d2ba8bb2cb3..9b0c77a99346 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2265,6 +2265,29 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags)
static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {}
#endif /* CONFIG_CPU_FREQ */
+#ifdef CONFIG_UCLAMP_TASK
+static inline unsigned int uclamp_util(struct rq *rq, unsigned int util)
+{
+ unsigned int min_util = READ_ONCE(rq->uclamp[UCLAMP_MIN].value);
+ unsigned int max_util = READ_ONCE(rq->uclamp[UCLAMP_MAX].value);
+
+ /*
+ * Since CPU's {min,max}_util clamps are MAX aggregated considering
+ * RUNNABLE tasks with _different_ clamps, we can end up with an
+ * inversion. Fix it now when the clamps are applied.
+ */
+ if (unlikely(min_util >= max_util))
+ return min_util;
+
+ return clamp(util, min_util, max_util);
+}
+#else /* CONFIG_UCLAMP_TASK */
+static inline unsigned int uclamp_util(struct rq *rq, unsigned int util)
+{
+ return util;
+}
+#endif /* CONFIG_UCLAMP_TASK */
+
#ifdef arch_scale_freq_capacity
# ifndef arch_scale_freq_invariant
# define arch_scale_freq_invariant() true