path: root/kernel/sched
diff options
authorDietmar Eggemann <>2021-06-02 16:58:08 +0200
committerPeter Zijlstra <>2021-06-03 15:47:23 +0200
commit68d7a190682aa4eb02db477328088ebad15acc83 (patch)
treeb69fb60b812faf894f79fb38fb3e9896ab01c958 /kernel/sched
parentfcf6631f3736985ec89bdd76392d3c7bfb60119f (diff)
sched/fair: Fix util_est UTIL_AVG_UNCHANGED handling
The util_est internal UTIL_AVG_UNCHANGED flag which is used to prevent unnecessary util_est updates uses the LSB of util_est.enqueued. It is exposed via _task_util_est() (and task_util_est()). Commit 92a801e5d5b7 ("sched/fair: Mask UTIL_AVG_UNCHANGED usages") mentions that the LSB is lost for util_est resolution but find_energy_efficient_cpu() checks if task_util_est() returns 0 to return prev_cpu early. _task_util_est() returns the max value of util_est.ewma and util_est.enqueued or'ed w/ UTIL_AVG_UNCHANGED. So task_util_est() returning the max of task_util() and _task_util_est() will never return 0 under the default SCHED_FEAT(UTIL_EST, true). To fix this use the MSB of util_est.enqueued instead and keep the flag util_est internal, i.e. don't export it via _task_util_est(). The maximal possible util_avg value for a task is 1024 so the MSB of 'unsigned int util_est.enqueued' isn't used to store a util value. As a caveat the code behind the util_est_se trace point has to filter UTIL_AVG_UNCHANGED to see the real util_est.enqueued value which should be easy to do. This also fixes an issue report by Xuewen Yan that util_est_update() only used UTIL_AVG_UNCHANGED for the subtrahend of the equation: last_enqueued_diff = ue.enqueued - (task_util() | UTIL_AVG_UNCHANGED) Fixes: b89997aa88f0b sched/pelt: Fix task util_est update filtering Signed-off-by: Dietmar Eggemann <> Signed-off-by: Peter Zijlstra (Intel) <> Reviewed-by: Xuewen Yan <> Reviewed-by: Vincent Donnefort <> Reviewed-by: Vincent Guittot <> Link:
Diffstat (limited to 'kernel/sched')
3 files changed, 6 insertions, 13 deletions
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 9c882f20803e..c5aacbd492a1 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -885,6 +885,7 @@ static const struct seq_operations sched_debug_sops = {
#define __PS(S, F) SEQ_printf(m, "%-45s:%21Ld\n", S, (long long)(F))
#define __P(F) __PS(#F, F)
#define P(F) __PS(#F, p->F)
+#define PM(F, M) __PS(#F, p->F & (M))
#define __PSN(S, F) SEQ_printf(m, "%-45s:%14Ld.%06ld\n", S, SPLIT_NS((long long)(F)))
#define __PN(F) __PSN(#F, F)
#define PN(F) __PSN(#F, p->F)
@@ -1011,7 +1012,7 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
- P(se.avg.util_est.enqueued);
+ PM(se.avg.util_est.enqueued, ~UTIL_AVG_UNCHANGED);
__PS("uclamp.min", p->uclamp_req[UCLAMP_MIN].value);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 7b98fb37330a..2c8a9352590d 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3907,7 +3907,7 @@ static inline unsigned long _task_util_est(struct task_struct *p)
struct util_est ue = READ_ONCE(p->se.avg.util_est);
- return (max(ue.ewma, ue.enqueued) | UTIL_AVG_UNCHANGED);
+ return max(ue.ewma, (ue.enqueued & ~UTIL_AVG_UNCHANGED));
static inline unsigned long task_util_est(struct task_struct *p)
@@ -4007,7 +4007,7 @@ static inline void util_est_update(struct cfs_rq *cfs_rq,
* Reset EWMA on utilization increases, the moving average is used only
* to smooth utilization decreases.
- ue.enqueued = (task_util(p) | UTIL_AVG_UNCHANGED);
+ ue.enqueued = task_util(p);
if (sched_feat(UTIL_EST_FASTUP)) {
if (ue.ewma < ue.enqueued) {
ue.ewma = ue.enqueued;
@@ -4056,6 +4056,7 @@ static inline void util_est_update(struct cfs_rq *cfs_rq,
ue.ewma += last_ewma_diff;
+ ue.enqueued |= UTIL_AVG_UNCHANGED;
WRITE_ONCE(p->se.avg.util_est, ue);
diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h
index 1462846d244e..cfe94ffd2b38 100644
--- a/kernel/sched/pelt.h
+++ b/kernel/sched/pelt.h
@@ -42,15 +42,6 @@ static inline u32 get_pelt_divider(struct sched_avg *avg)
return LOAD_AVG_MAX - 1024 + avg->period_contrib;
- * When a task is dequeued, its estimated utilization should not be update if
- * its util_avg has not been updated at least once.
- * This flag is used to synchronize util_avg updates with util_est updates.
- * We map this information into the LSB bit of the utilization saved at
- * dequeue time (i.e. util_est.dequeued).
- */
static inline void cfs_se_util_change(struct sched_avg *avg)
unsigned int enqueued;
@@ -58,7 +49,7 @@ static inline void cfs_se_util_change(struct sched_avg *avg)
if (!sched_feat(UTIL_EST))
- /* Avoid store if the flag has been already set */
+ /* Avoid store if the flag has been already reset */
enqueued = avg->util_est.enqueued;
if (!(enqueued & UTIL_AVG_UNCHANGED))