When uclamp_max is being used, the util of the task could be higher than
the spare capacity of the CPU, but due to uclamp_max value we force fit
it there.
The way the condition for checking for max_spare_cap in
find_energy_efficient_cpu() was constructed; it ignored any CPU that has
its spare_cap less than or _equal_ to max_spare_cap. Since we initialize
max_spare_cap to 0; this lead to never setting max_spare_cap_cpu and
hence ending up never performing compute_energy() for this cluster and
missing an opportunity for a better energy efficient placement to honour
uclamp_max setting.
max_spare_cap = 0;
cpu_cap = capacity_of(cpu) - task_util(p); // 0 if task_util(p) is high
...
util_fits_cpu(...); // will return true if uclamp_max forces it to fit
...
// this logic will fail to update max_spare_cap_cpu if cpu_cap is 0
if (cpu_cap > max_spare_cap) {
max_spare_cap = cpu_cap;
max_spare_cap_cpu = cpu;
}
prev_spare_cap suffers from a similar problem.
Fix the logic by converting the variables into long and treating -1
value as 'not populated' instead of 0 which is a viable and correct
spare capacity value. We need to be careful signed comparison is used
when comparing with cpu_cap in one of the conditions.
Fixes: 1d42509e475c ("sched/fair: Make EAS wakeup placement consider uclamp restrictions")
Signed-off-by: Qais Yousef (Google) <qyousef@layalina.io>
---
kernel/sched/fair.c | 11 +++++------
1 file changed, 5 insertions(+), 6 deletions(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 0cd1cdbae534..d489eece5a0d 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7596,11 +7596,10 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
for (; pd; pd = pd->next) {
unsigned long util_min = p_util_min, util_max = p_util_max;
unsigned long cpu_cap, cpu_thermal_cap, util;
- unsigned long cur_delta, max_spare_cap = 0;
+ long prev_spare_cap = -1, max_spare_cap = -1;
unsigned long rq_util_min, rq_util_max;
- unsigned long prev_spare_cap = 0;
+ unsigned long cur_delta, base_energy;
int max_spare_cap_cpu = -1;
- unsigned long base_energy;
int fits, max_fits = -1;
cpumask_and(cpus, perf_domain_span(pd), cpu_online_mask);
@@ -7663,7 +7662,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
prev_spare_cap = cpu_cap;
prev_fits = fits;
} else if ((fits > max_fits) ||
- ((fits == max_fits) && (cpu_cap > max_spare_cap))) {
+ ((fits == max_fits) && ((long)cpu_cap > max_spare_cap))) {
/*
* Find the CPU with the maximum spare capacity
* among the remaining CPUs in the performance
@@ -7675,7 +7674,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
}
}
- if (max_spare_cap_cpu < 0 && prev_spare_cap == 0)
+ if (max_spare_cap_cpu < 0 && prev_spare_cap < 0)
continue;
eenv_pd_busy_time(&eenv, cpus, p);
@@ -7683,7 +7682,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
base_energy = compute_energy(&eenv, pd, cpus, p, -1);
/* Evaluate the energy impact of using prev_cpu. */
- if (prev_spare_cap > 0) {
+ if (prev_spare_cap > -1) {
prev_delta = compute_energy(&eenv, pd, cpus, p,
prev_cpu);
/* CPU utilization has changed */
--
2.25.1On Mon, 17 Jul 2023 at 23:57, Qais Yousef <qyousef@layalina.io> wrote:
>
> When uclamp_max is being used, the util of the task could be higher than
> the spare capacity of the CPU, but due to uclamp_max value we force fit
> it there.
>
> The way the condition for checking for max_spare_cap in
> find_energy_efficient_cpu() was constructed; it ignored any CPU that has
> its spare_cap less than or _equal_ to max_spare_cap. Since we initialize
> max_spare_cap to 0; this lead to never setting max_spare_cap_cpu and
> hence ending up never performing compute_energy() for this cluster and
> missing an opportunity for a better energy efficient placement to honour
> uclamp_max setting.
>
> max_spare_cap = 0;
> cpu_cap = capacity_of(cpu) - task_util(p); // 0 if task_util(p) is high
>
> ...
>
> util_fits_cpu(...); // will return true if uclamp_max forces it to fit
>
> ...
>
> // this logic will fail to update max_spare_cap_cpu if cpu_cap is 0
> if (cpu_cap > max_spare_cap) {
> max_spare_cap = cpu_cap;
> max_spare_cap_cpu = cpu;
> }
>
> prev_spare_cap suffers from a similar problem.
>
> Fix the logic by converting the variables into long and treating -1
> value as 'not populated' instead of 0 which is a viable and correct
> spare capacity value. We need to be careful signed comparison is used
> when comparing with cpu_cap in one of the conditions.
>
> Fixes: 1d42509e475c ("sched/fair: Make EAS wakeup placement consider uclamp restrictions")
> Signed-off-by: Qais Yousef (Google) <qyousef@layalina.io>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
> ---
> kernel/sched/fair.c | 11 +++++------
> 1 file changed, 5 insertions(+), 6 deletions(-)
>
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 0cd1cdbae534..d489eece5a0d 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -7596,11 +7596,10 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
> for (; pd; pd = pd->next) {
> unsigned long util_min = p_util_min, util_max = p_util_max;
> unsigned long cpu_cap, cpu_thermal_cap, util;
> - unsigned long cur_delta, max_spare_cap = 0;
> + long prev_spare_cap = -1, max_spare_cap = -1;
> unsigned long rq_util_min, rq_util_max;
> - unsigned long prev_spare_cap = 0;
> + unsigned long cur_delta, base_energy;
> int max_spare_cap_cpu = -1;
> - unsigned long base_energy;
> int fits, max_fits = -1;
>
> cpumask_and(cpus, perf_domain_span(pd), cpu_online_mask);
> @@ -7663,7 +7662,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
> prev_spare_cap = cpu_cap;
> prev_fits = fits;
> } else if ((fits > max_fits) ||
> - ((fits == max_fits) && (cpu_cap > max_spare_cap))) {
> + ((fits == max_fits) && ((long)cpu_cap > max_spare_cap))) {
> /*
> * Find the CPU with the maximum spare capacity
> * among the remaining CPUs in the performance
> @@ -7675,7 +7674,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
> }
> }
>
> - if (max_spare_cap_cpu < 0 && prev_spare_cap == 0)
> + if (max_spare_cap_cpu < 0 && prev_spare_cap < 0)
> continue;
>
> eenv_pd_busy_time(&eenv, cpus, p);
> @@ -7683,7 +7682,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
> base_energy = compute_energy(&eenv, pd, cpus, p, -1);
>
> /* Evaluate the energy impact of using prev_cpu. */
> - if (prev_spare_cap > 0) {
> + if (prev_spare_cap > -1) {
> prev_delta = compute_energy(&eenv, pd, cpus, p,
> prev_cpu);
> /* CPU utilization has changed */
> --
> 2.25.1
>
© 2016 - 2026 Red Hat, Inc.