sched/pelt: Remove shift of thermal clock

The optional shift of the clock used by thermal/hw load avg has been
introduced to handle case where the signal was not always a high frequency
hw signal. Now that cpufreq provides a signal for firmware and
SW pressure, we can remove this exception and always keep this PELT signal
aligned with other signals.
Mark sysctl_sched_migration_cost boot parameter as deprecated

Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Lukasz Luba <lukasz.luba@arm.com>
Reviewed-by: Qais Yousef <qyousef@layalina.io>
Reviewed-by: Lukasz Luba <lukasz.luba@arm.com>
Link: https://lore.kernel.org/r/20240326091616.3696851-6-vincent.guittot@linaro.org

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index bb884c14b2f679dba3a36ba89755a1eca2fe6db2..3f390cc5f77e4f96ee5fd17c0de22bdbbd7ba953 100644 (file)
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -5807,6 +5807,7 @@
                        but is useful for debugging and performance tuning.
 
        sched_thermal_decay_shift=
+                       [Deprecated]
                        [KNL, SMP] Set a decay shift for scheduler thermal
                        pressure signal. Thermal pressure signal follows the
                        default decay period of other scheduler pelt

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 67a8302c3131e9fe946bb6b5191c4c8b4a94aa96..1a914388144aebbb6ed0e2a41835f73ae4510475 100644 (file)
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5680,7 +5680,7 @@ void sched_tick(void)
 
        update_rq_clock(rq);
        hw_pressure = arch_scale_hw_pressure(cpu_of(rq));
-       update_hw_load_avg(rq_clock_hw(rq), rq, hw_pressure);
+       update_hw_load_avg(rq_clock_task(rq), rq, hw_pressure);
        curr->sched_class->task_tick(rq, curr, 0);
        if (sched_feat(LATENCY_WARN))
                resched_latency = cpu_resched_latency(rq);

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index eef39ae3efcf0711647da24908cd7524c5a01b8c..9eb63573110c6c205d601a77bef5f0dbfd874def 100644 (file)
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -78,15 +78,9 @@ static unsigned int normalized_sysctl_sched_base_slice       = 750000ULL;
 
 const_debug unsigned int sysctl_sched_migration_cost   = 500000UL;
 
-int sched_hw_decay_shift;
 static int __init setup_sched_thermal_decay_shift(char *str)
 {
-       int _shift = 0;
-
-       if (kstrtoint(str, 0, &_shift))
-               pr_warn("Unable to set scheduler thermal pressure decay shift parameter\n");
-
-       sched_hw_decay_shift = clamp(_shift, 0, 10);
+       pr_warn("Ignoring the deprecated sched_thermal_decay_shift= option\n");
        return 1;
 }
 __setup("sched_thermal_decay_shift=", setup_sched_thermal_decay_shift);
@@ -9367,7 +9361,7 @@ static bool __update_blocked_others(struct rq *rq, bool *done)
 
        decayed = update_rt_rq_load_avg(now, rq, curr_class == &rt_sched_class) |
                  update_dl_rq_load_avg(now, rq, curr_class == &dl_sched_class) |
-                 update_hw_load_avg(rq_clock_hw(rq), rq, hw_pressure) |
+                 update_hw_load_avg(now, rq, hw_pressure) |
                  update_irq_load_avg(rq, 0);
 
        if (others_have_blocked(rq))

diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 993edb02fb0dc04f73af5480e21abf8af159e7d5..cb3792c04eeaeefdc6d2e542bb7103f3c6b837dd 100644 (file)
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1550,24 +1550,6 @@ static inline u64 rq_clock_task(struct rq *rq)
        return rq->clock_task;
 }
 
-/**
- * By default the decay is the default pelt decay period.
- * The decay shift can change the decay period in
- * multiples of 32.
- *  Decay shift                Decay period(ms)
- *     0                       32
- *     1                       64
- *     2                       128
- *     3                       256
- *     4                       512
- */
-extern int sched_hw_decay_shift;
-
-static inline u64 rq_clock_hw(struct rq *rq)
-{
-       return rq_clock_task(rq) >> sched_hw_decay_shift;
-}
-
 static inline void rq_clock_skip_update(struct rq *rq)
 {
        lockdep_assert_rq_held(rq);