From 41ce2236860d4f0e9c7e9f7a3659080c19bbdd66 Mon Sep 17 00:00:00 2001 From: Patrick Bellasi Date: Tue, 9 Feb 2021 11:09:11 +0530 Subject: [PATCH] UPSTREAM: sched/uclamp: Enforce last task's UCLAMP_MAX When a task sleeps it removes its max utilization clamp from its CPU. However, the blocked utilization on that CPU can be higher than the max clamp value enforced while the task was running. This allows undesired CPU frequency increases while a CPU is idle, for example, when another CPU on the same frequency domain triggers a frequency update, since schedutil can now see the full not clamped blocked utilization of the idle CPU. Fix this by using: uclamp_rq_dec_id(p, rq, UCLAMP_MAX) uclamp_rq_max_value(rq, UCLAMP_MAX, clamp_value) to detect when a CPU has no more RUNNABLE clamped tasks and to flag this condition. Don't track any minimum utilization clamps since an idle CPU never requires a minimum frequency. The decay of the blocked utilization is good enough to reduce the CPU frequency. Bug: 120440300 Signed-off-by: Patrick Bellasi Signed-off-by: Peter Zijlstra (Intel) Cc: Alessio Balsini Cc: Dietmar Eggemann Cc: Joel Fernandes Cc: Juri Lelli Cc: Linus Torvalds Cc: Morten Rasmussen Cc: Paul Turner Cc: Peter Zijlstra Cc: Quentin Perret Cc: Rafael J . Wysocki Cc: Steve Muckle Cc: Suren Baghdasaryan Cc: Tejun Heo Cc: Thomas Gleixner Cc: Todd Kjos Cc: Vincent Guittot Cc: Viresh Kumar Link: https://lkml.kernel.org/r/20190621084217.8167-4-patrick.bellasi@arm.com Signed-off-by: Ingo Molnar (cherry picked from commit e496187da71070687b55ff455e7d8d7d7f0ae0b9) Signed-off-by: Qais Yousef Change-Id: Ie9eab897eb654ec9d4fba5eda20f66a91a712817 Signed-off-by: Quentin Perret --- kernel/sched/core.c | 49 +++++++++++++++++++++++++++++++++++++++----- kernel/sched/sched.h | 3 ++- 2 files changed, 46 insertions(+), 6 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 45604c4d78fa..50ebad32a4cf 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -786,8 +786,36 @@ static inline void uclamp_se_set(struct uclamp_se *uc_se, unsigned int value) uc_se->bucket_id = uclamp_bucket_id(value); } +static inline unsigned int +uclamp_idle_value(struct rq *rq, unsigned int clamp_id, + unsigned int clamp_value) +{ + /* + * Avoid blocked utilization pushing up the frequency when we go + * idle (which drops the max-clamp) by retaining the last known + * max-clamp. + */ + if (clamp_id == UCLAMP_MAX) { + rq->uclamp_flags |= UCLAMP_FLAG_IDLE; + return clamp_value; + } + + return uclamp_none(UCLAMP_MIN); +} + +static inline void uclamp_idle_reset(struct rq *rq, unsigned int clamp_id, + unsigned int clamp_value) +{ + /* Reset max-clamp retention only on idle exit */ + if (!(rq->uclamp_flags & UCLAMP_FLAG_IDLE)) + return; + + WRITE_ONCE(rq->uclamp[clamp_id].value, clamp_value); +} + static inline -unsigned int uclamp_rq_max_value(struct rq *rq, unsigned int clamp_id) +unsigned int uclamp_rq_max_value(struct rq *rq, unsigned int clamp_id, + unsigned int clamp_value) { struct uclamp_bucket *bucket = rq->uclamp[clamp_id].bucket; int bucket_id = UCLAMP_BUCKETS - 1; @@ -803,7 +831,7 @@ unsigned int uclamp_rq_max_value(struct rq *rq, unsigned int clamp_id) } /* No tasks -- default clamp values */ - return uclamp_none(clamp_id); + return uclamp_idle_value(rq, clamp_id, clamp_value); } /* @@ -828,6 +856,8 @@ static inline void uclamp_rq_inc_id(struct rq *rq, struct task_struct *p, bucket = &uc_rq->bucket[uc_se->bucket_id]; bucket->tasks++; + uclamp_idle_reset(rq, clamp_id, uc_se->value); + /* * Local max aggregation: rq buckets always track the max * "requested" clamp value of its RUNNABLE tasks. @@ -854,6 +884,7 @@ static inline void uclamp_rq_dec_id(struct rq *rq, struct task_struct *p, struct uclamp_rq *uc_rq = &rq->uclamp[clamp_id]; struct uclamp_se *uc_se = &p->uclamp[clamp_id]; struct uclamp_bucket *bucket; + unsigned int bkt_clamp; unsigned int rq_clamp; lockdep_assert_held(&rq->lock); @@ -878,8 +909,10 @@ static inline void uclamp_rq_dec_id(struct rq *rq, struct task_struct *p, * e.g. due to future modification, warn and fixup the expected value. */ SCHED_WARN_ON(bucket->value > rq_clamp); - if (bucket->value >= rq_clamp) - WRITE_ONCE(uc_rq->value, uclamp_rq_max_value(rq, clamp_id)); + if (bucket->value >= rq_clamp) { + bkt_clamp = uclamp_rq_max_value(rq, clamp_id, uc_se->value); + WRITE_ONCE(uc_rq->value, bkt_clamp); + } } static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p) @@ -891,6 +924,10 @@ static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p) for_each_clamp_id(clamp_id) uclamp_rq_inc_id(rq, p, clamp_id); + + /* Reset clamp idle holding when there is one RUNNABLE task */ + if (rq->uclamp_flags & UCLAMP_FLAG_IDLE) + rq->uclamp_flags &= ~UCLAMP_FLAG_IDLE; } static inline void uclamp_rq_dec(struct rq *rq, struct task_struct *p) @@ -909,8 +946,10 @@ static void __init init_uclamp(void) unsigned int clamp_id; int cpu; - for_each_possible_cpu(cpu) + for_each_possible_cpu(cpu) { memset(&cpu_rq(cpu)->uclamp, 0, sizeof(struct uclamp_rq)); + cpu_rq(cpu)->uclamp_flags = 0; + } for_each_clamp_id(clamp_id) { uclamp_se_set(&init_task.uclamp[clamp_id], diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 812d4fa23fa0..2e8dbb4a12cb 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -855,8 +855,9 @@ struct rq { #ifdef CONFIG_UCLAMP_TASK /* Utilization clamp values based on CPU's RUNNABLE tasks */ struct uclamp_rq uclamp[UCLAMP_CNT] ____cacheline_aligned; + unsigned int uclamp_flags; +#define UCLAMP_FLAG_IDLE 0x01 #endif - struct cfs_rq cfs; struct rt_rq rt; struct dl_rq dl;