diff options
author | Dietmar Eggemann <dietmar.eggemann@arm.com> | 2022-06-21 12:04:12 +0300 |
---|---|---|
committer | Peter Zijlstra <peterz@infradead.org> | 2022-06-28 10:17:47 +0300 |
commit | 9b340131a4bcf6d0a282a2bdcd8ca268a74da709 (patch) | |
tree | 24a580e4e02dd7a00e07247ec187dbd32b9fa7c9 /kernel/sched | |
parent | ec4fc801a02d96180c597238fe87141471b70971 (diff) | |
download | linux-9b340131a4bcf6d0a282a2bdcd8ca268a74da709.tar.xz |
sched/fair: Use the same cpumask per-PD throughout find_energy_efficient_cpu()
The Perf Domain (PD) cpumask (struct em_perf_domain.cpus) stays
invariant after Energy Model creation, i.e. it is not updated after
CPU hotplug operations.
That's why the PD mask is used in conjunction with the cpu_online_mask
(or Sched Domain cpumask). Thereby the cpu_online_mask is fetched
multiple times (in compute_energy()) during a run-queue selection
for a task.
cpu_online_mask may change during this time which can lead to wrong
energy calculations.
To be able to avoid this, use the select_rq_mask per-cpu cpumask to
create a cpumask out of PD cpumask and cpu_online_mask and pass it
through the function calls of the EAS run-queue selection path.
The PD cpumask for max_spare_cap_cpu/compute_prev_delta selection
(find_energy_efficient_cpu()) is now ANDed not only with the SD mask
but also with the cpu_online_mask. This is fine since this cpumask
has to be in syc with the one used for energy computation
(compute_energy()).
An exclusive cpuset setup with at least one asymmetric CPU capacity
island (hence the additional AND with the SD cpumask) is the obvious
exception here.
Signed-off-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Tested-by: Lukasz Luba <lukasz.luba@arm.com>
Link: https://lkml.kernel.org/r/20220621090414.433602-6-vdonnefort@google.com
Diffstat (limited to 'kernel/sched')
-rw-r--r-- | kernel/sched/fair.c | 22 |
1 files changed, 13 insertions, 9 deletions
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index e3f750135f78..46d669297b1f 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -6709,14 +6709,14 @@ static unsigned long cpu_util_without(int cpu, struct task_struct *p) * task. */ static long -compute_energy(struct task_struct *p, int dst_cpu, struct perf_domain *pd) +compute_energy(struct task_struct *p, int dst_cpu, struct cpumask *cpus, + struct perf_domain *pd) { - struct cpumask *pd_mask = perf_domain_span(pd); unsigned long max_util = 0, sum_util = 0, cpu_cap; int cpu; - cpu_cap = arch_scale_cpu_capacity(cpumask_first(pd_mask)); - cpu_cap -= arch_scale_thermal_pressure(cpumask_first(pd_mask)); + cpu_cap = arch_scale_cpu_capacity(cpumask_first(cpus)); + cpu_cap -= arch_scale_thermal_pressure(cpumask_first(cpus)); /* * The capacity state of CPUs of the current rd can be driven by CPUs @@ -6727,7 +6727,7 @@ compute_energy(struct task_struct *p, int dst_cpu, struct perf_domain *pd) * If an entire pd is outside of the current rd, it will not appear in * its pd list and will not be accounted by compute_energy(). */ - for_each_cpu_and(cpu, pd_mask, cpu_online_mask) { + for_each_cpu(cpu, cpus) { unsigned long util_freq = cpu_util_next(cpu, p, dst_cpu); unsigned long cpu_util, util_running = util_freq; struct task_struct *tsk = NULL; @@ -6814,6 +6814,7 @@ compute_energy(struct task_struct *p, int dst_cpu, struct perf_domain *pd) */ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) { + struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_rq_mask); unsigned long prev_delta = ULONG_MAX, best_delta = ULONG_MAX; struct root_domain *rd = cpu_rq(smp_processor_id())->rd; int cpu, best_energy_cpu = prev_cpu, target = -1; @@ -6848,7 +6849,9 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) unsigned long base_energy_pd; int max_spare_cap_cpu = -1; - for_each_cpu_and(cpu, perf_domain_span(pd), sched_domain_span(sd)) { + cpumask_and(cpus, perf_domain_span(pd), cpu_online_mask); + + for_each_cpu_and(cpu, cpus, sched_domain_span(sd)) { if (!cpumask_test_cpu(cpu, p->cpus_ptr)) continue; @@ -6885,12 +6888,12 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) continue; /* Compute the 'base' energy of the pd, without @p */ - base_energy_pd = compute_energy(p, -1, pd); + base_energy_pd = compute_energy(p, -1, cpus, pd); base_energy += base_energy_pd; /* Evaluate the energy impact of using prev_cpu. */ if (compute_prev_delta) { - prev_delta = compute_energy(p, prev_cpu, pd); + prev_delta = compute_energy(p, prev_cpu, cpus, pd); if (prev_delta < base_energy_pd) goto unlock; prev_delta -= base_energy_pd; @@ -6899,7 +6902,8 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) /* Evaluate the energy impact of using max_spare_cap_cpu. */ if (max_spare_cap_cpu >= 0) { - cur_delta = compute_energy(p, max_spare_cap_cpu, pd); + cur_delta = compute_energy(p, max_spare_cap_cpu, cpus, + pd); if (cur_delta < base_energy_pd) goto unlock; cur_delta -= base_energy_pd; |