This is a note to let you know that I've just added the patch titled
sched/uclamp: Fix fits_capacity() check in feec()
to the 5.15-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
sched-uclamp-fix-fits_capacity-check-in-feec.patch
and it can be found in the queue-5.15 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
>From stable-owner@xxxxxxxxxxxxxxx Wed Mar 8 17:22:30 2023
From: Qais Yousef <qyousef@xxxxxxxxxxx>
Date: Wed, 8 Mar 2023 16:22:01 +0000
Subject: sched/uclamp: Fix fits_capacity() check in feec()
To: stable@xxxxxxxxxxxxxxx
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>, Vincent Guittot <vincent.guittot@xxxxxxxxxx>, Dietmar Eggemann <dietmar.eggemann@xxxxxxx>, Qais Yousef <qais.yousef@xxxxxxx>, Yun Hsiang <hsiang023167@xxxxxxxxx>
Message-ID: <20230308162207.2886641-2-qyousef@xxxxxxxxxxx>
From: Qais Yousef <qais.yousef@xxxxxxx>
commit 244226035a1f9b2b6c326e55ae5188fab4f428cb upstream.
As reported by Yun Hsiang [1], if a task has its uclamp_min >= 0.8 * 1024,
it'll always pick the previous CPU because fits_capacity() will always
return false in this case.
The new util_fits_cpu() logic should handle this correctly for us beside
more corner cases where similar failures could occur, like when using
UCLAMP_MAX.
We open code uclamp_rq_util_with() except for the clamp() part,
util_fits_cpu() needs the 'raw' values to be passed to it.
Also introduce uclamp_rq_{set, get}() shorthand accessors to get uclamp
value for the rq. Makes the code more readable and ensures the right
rules (use READ_ONCE/WRITE_ONCE) are respected transparently.
[1] https://lists.linaro.org/pipermail/eas-dev/2020-July/001488.html
Fixes: 1d42509e475c ("sched/fair: Make EAS wakeup placement consider uclamp restrictions")
Reported-by: Yun Hsiang <hsiang023167@xxxxxxxxx>
Signed-off-by: Qais Yousef <qais.yousef@xxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Link: https://lore.kernel.org/r/20220804143609.515789-4-qais.yousef@xxxxxxx
(cherry picked from commit 244226035a1f9b2b6c326e55ae5188fab4f428cb)
[Conflict in kernel/sched/fair.c mainly due to new automatic variables
being added on master vs 5.15]
Signed-off-by: Qais Yousef (Google) <qyousef@xxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
kernel/sched/core.c | 10 +++++-----
kernel/sched/fair.c | 26 ++++++++++++++++++++++++--
kernel/sched/sched.h | 42 +++++++++++++++++++++++++++++++++++++++---
3 files changed, 68 insertions(+), 10 deletions(-)
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1335,7 +1335,7 @@ static inline void uclamp_idle_reset(str
if (!(rq->uclamp_flags & UCLAMP_FLAG_IDLE))
return;
- WRITE_ONCE(rq->uclamp[clamp_id].value, clamp_value);
+ uclamp_rq_set(rq, clamp_id, clamp_value);
}
static inline
@@ -1513,8 +1513,8 @@ static inline void uclamp_rq_inc_id(stru
if (bucket->tasks == 1 || uc_se->value > bucket->value)
bucket->value = uc_se->value;
- if (uc_se->value > READ_ONCE(uc_rq->value))
- WRITE_ONCE(uc_rq->value, uc_se->value);
+ if (uc_se->value > uclamp_rq_get(rq, clamp_id))
+ uclamp_rq_set(rq, clamp_id, uc_se->value);
}
/*
@@ -1580,7 +1580,7 @@ static inline void uclamp_rq_dec_id(stru
if (likely(bucket->tasks))
return;
- rq_clamp = READ_ONCE(uc_rq->value);
+ rq_clamp = uclamp_rq_get(rq, clamp_id);
/*
* Defensive programming: this should never happen. If it happens,
* e.g. due to future modification, warn and fixup the expected value.
@@ -1588,7 +1588,7 @@ static inline void uclamp_rq_dec_id(stru
SCHED_WARN_ON(bucket->value > rq_clamp);
if (bucket->value >= rq_clamp) {
bkt_clamp = uclamp_rq_max_value(rq, clamp_id, uc_se->value);
- WRITE_ONCE(uc_rq->value, bkt_clamp);
+ uclamp_rq_set(rq, clamp_id, bkt_clamp);
}
}
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6938,6 +6938,8 @@ compute_energy(struct task_struct *p, in
static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
{
unsigned long prev_delta = ULONG_MAX, best_delta = ULONG_MAX;
+ unsigned long p_util_min = uclamp_is_used() ? uclamp_eff_value(p, UCLAMP_MIN) : 0;
+ unsigned long p_util_max = uclamp_is_used() ? uclamp_eff_value(p, UCLAMP_MAX) : 1024;
struct root_domain *rd = cpu_rq(smp_processor_id())->rd;
int cpu, best_energy_cpu = prev_cpu, target = -1;
unsigned long cpu_cap, util, base_energy = 0;
@@ -6967,6 +6969,8 @@ static int find_energy_efficient_cpu(str
for (; pd; pd = pd->next) {
unsigned long cur_delta, spare_cap, max_spare_cap = 0;
+ unsigned long rq_util_min, rq_util_max;
+ unsigned long util_min, util_max;
bool compute_prev_delta = false;
unsigned long base_energy_pd;
int max_spare_cap_cpu = -1;
@@ -6987,8 +6991,26 @@ static int find_energy_efficient_cpu(str
* much capacity we can get out of the CPU; this is
* aligned with sched_cpu_util().
*/
- util = uclamp_rq_util_with(cpu_rq(cpu), util, p);
- if (!fits_capacity(util, cpu_cap))
+ if (uclamp_is_used()) {
+ if (uclamp_rq_is_idle(cpu_rq(cpu))) {
+ util_min = p_util_min;
+ util_max = p_util_max;
+ } else {
+ /*
+ * Open code uclamp_rq_util_with() except for
+ * the clamp() part. Ie: apply max aggregation
+ * only. util_fits_cpu() logic requires to
+ * operate on non clamped util but must use the
+ * max-aggregated uclamp_{min, max}.
+ */
+ rq_util_min = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MIN);
+ rq_util_max = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MAX);
+
+ util_min = max(rq_util_min, p_util_min);
+ util_max = max(rq_util_max, p_util_max);
+ }
+ }
+ if (!util_fits_cpu(util, util_min, util_max, cpu))
continue;
if (cpu == prev_cpu) {
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2855,6 +2855,23 @@ static inline void cpufreq_update_util(s
#ifdef CONFIG_UCLAMP_TASK
unsigned long uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id);
+static inline unsigned long uclamp_rq_get(struct rq *rq,
+ enum uclamp_id clamp_id)
+{
+ return READ_ONCE(rq->uclamp[clamp_id].value);
+}
+
+static inline void uclamp_rq_set(struct rq *rq, enum uclamp_id clamp_id,
+ unsigned int value)
+{
+ WRITE_ONCE(rq->uclamp[clamp_id].value, value);
+}
+
+static inline bool uclamp_rq_is_idle(struct rq *rq)
+{
+ return rq->uclamp_flags & UCLAMP_FLAG_IDLE;
+}
+
/**
* uclamp_rq_util_with - clamp @util with @rq and @p effective uclamp values.
* @rq: The rq to clamp against. Must not be NULL.
@@ -2890,12 +2907,12 @@ unsigned long uclamp_rq_util_with(struct
* Ignore last runnable task's max clamp, as this task will
* reset it. Similarly, no need to read the rq's min clamp.
*/
- if (rq->uclamp_flags & UCLAMP_FLAG_IDLE)
+ if (uclamp_rq_is_idle(rq))
goto out;
}
- min_util = max_t(unsigned long, min_util, READ_ONCE(rq->uclamp[UCLAMP_MIN].value));
- max_util = max_t(unsigned long, max_util, READ_ONCE(rq->uclamp[UCLAMP_MAX].value));
+ min_util = max_t(unsigned long, min_util, uclamp_rq_get(rq, UCLAMP_MIN));
+ max_util = max_t(unsigned long, max_util, uclamp_rq_get(rq, UCLAMP_MAX));
out:
/*
* Since CPU's {min,max}_util clamps are MAX aggregated considering
@@ -2941,6 +2958,25 @@ static inline bool uclamp_is_used(void)
{
return false;
}
+
+static inline unsigned long uclamp_rq_get(struct rq *rq,
+ enum uclamp_id clamp_id)
+{
+ if (clamp_id == UCLAMP_MIN)
+ return 0;
+
+ return SCHED_CAPACITY_SCALE;
+}
+
+static inline void uclamp_rq_set(struct rq *rq, enum uclamp_id clamp_id,
+ unsigned int value)
+{
+}
+
+static inline bool uclamp_rq_is_idle(struct rq *rq)
+{
+ return false;
+}
#endif /* CONFIG_UCLAMP_TASK */
#ifdef arch_scale_freq_capacity
Patches currently in stable-queue which might be from stable-owner@xxxxxxxxxxxxxxx are
queue-5.15/sched-fair-detect-capacity-inversion.patch
queue-5.15/sched-uclamp-make-cpu_overutilized-use-util_fits_cpu.patch
queue-5.15/sched-uclamp-fix-fits_capacity-check-in-feec.patch
queue-5.15/sched-fair-consider-capacity-inversion-in-util_fits_cpu.patch
queue-5.15/sched-fair-fixes-for-capacity-inversion-detection.patch
queue-5.15/sched-uclamp-fix-a-uninitialized-variable-warnings.patch
queue-5.15/sched-uclamp-cater-for-uclamp-in-find_energy_efficient_cpu-s-early-exit-condition.patch
