mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-23 17:30:02 +00:00
![Linus Torvalds](/assets/img/avatar_default.png)
- Make cpufreq_show_cpus() more straightforward (Viresh Kumar). - Drop unnecessary CPU hotplug locking from store() used by cpufreq sysfs attributes (Viresh Kumar). - Make the ACPI cpufreq driver support the boost control interface on Zhaoxin/Centaur processors (Tony W Wang-oc). - Print a warning message on attempts to free an active cpufreq policy which should never happen (Viresh Kumar). - Fix grammar in the Kconfig help text for the loongson2 cpufreq driver (Randy Dunlap). - Use cpumask_var_t for an on-stack CPU mask in the ondemand cpufreq governor (Zhao Liu). - Add trace points for guest_halt_poll_ns grow/shrink to the haltpoll cpuidle driver (Eiichi Tsukata). - Modify intel_idle to treat C1 and C1E as independent idle states on Sapphire Rapids (Artem Bityutskiy). - Extend support for wakeirq to callback wrappers used during system suspend and resume (Ulf Hansson). - Defer waiting for device probe before loading a hibernation image till the first actual device access to avoid possible deadlocks reported by syzbot (Tetsuo Handa). - Unify device_init_wakeup() for PM_SLEEP and !PM_SLEEP (Bjorn Helgaas). - Add Raptor Lake-P to the list of processors supported by the Intel RAPL driver (George D Sworo). - Add Alder Lake-N and Raptor Lake-P to the list of processors for which Power Limit4 is supported in the Intel RAPL driver (Sumeet Pawnikar). - Make pm_genpd_remove() check genpd_debugfs_dir against NULL before attempting to remove it (Hsin-Yi Wang). - Change the Energy Model code to represent power in micro-Watts and adjust its users accordingly (Lukasz Luba). - Add new devfreq driver for Mediatek CCI (Cache Coherent Interconnect) (Johnson Wang). - Convert the Samsung Exynos SoC Bus bindings to DT schema of exynos-bus.c (Krzysztof Kozlowski). - Address kernel-doc warnings by adding the description for unused fucntion parameters in devfreq core (Mauro Carvalho Chehab). - Use NULL to pass a null pointer rather than zero according to the function propotype in imx-bus.c (Colin Ian King). - Print error message instead of error interger value in tegra30-devfreq.c (Dmitry Osipenko). - Add checks to prevent setting negative frequency QoS limits for CPUs (Shivnandan Kumar). - Update the pm-graph suite of utilities to the latest revision 5.9 including multiple improvements (Todd Brandt). - Drop pme_interrupt reference from the PCI power management documentation (Mario Limonciello). -----BEGIN PGP SIGNATURE----- iQJGBAABCAAwFiEE4fcc61cGeeHD/fCwgsRv/nhiVHEFAmLoKy8SHHJqd0Byand5 c29ja2kubmV0AAoJEILEb/54YlRx3+oQAJNVU+W14EaRPWXQRMuwBC5zk3hb6T9q JqmMd8coEd+9/4ABAeRAWso1B26rUzB6JyBvw3lGH9OXInpYmvnJEhEPrTpK2h0D U9HxEARuGJolrDm0X9NAkn7tKKMC9GnvPS9z2s7s+N97VFFWC/QiU+PHB0SypGNb JxRfbVJZQCuxmNG9UeK+xeHFQ9lM2Z9ZdTxR71G0n7nQPPR+sUvnFufFby3Aogf3 XnBYfia+YNqkUlefxxwB5a0cFwPXOUGsQkIf4d64gZnq1TgZ+71kht1GEF08PDFl wV8v1rOWuXEae8dozuf5xszp/eVyAqzgB+IShT9APREOO3Wg6I16XdBm8R1TGwCK JTdZqnm6HVKBNqchEwYViJILX69rrNUT+AwHBWhtKKDNh3qeTuwi/JGTeDVN++en xf3TNKx3LV31Nq6nWJFzDGLehfZMnAPkhfYohUBI7FNyblpk4mJRVcZ0bYI7UNnS als77uoipvb5KdFCtdhxYBHd/y867NvXKa1qsAuDxusAsfJHf4SnlMdbgOepBH2y jJg06CGrMDU3TZ8BL+WpqUYk4irQnAMs/159Txh7A6/dOnTjE7S9NHrENCwmt2og FrHSLH1eLX6Sa4RSibiGHPC7mNULP2/TOtryf3zFdlIVcjm3NEU3bnfzx7nlJn05 8t6ObMxgMhWT =XeLV -----END PGP SIGNATURE----- Merge tag 'pm-5.20-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm Pull power management updates from Rafael Wysocki: "These are mostly minor improvements all over including new CPU IDs for the Intel RAPL driver, an Energy Model rework to use micro-Watt as the power unit, cpufreq fixes and cleanus, cpuidle updates, devfreq updates, documentation cleanups and a new version of the pm-graph suite of utilities. Specifics: - Make cpufreq_show_cpus() more straightforward (Viresh Kumar). - Drop unnecessary CPU hotplug locking from store() used by cpufreq sysfs attributes (Viresh Kumar). - Make the ACPI cpufreq driver support the boost control interface on Zhaoxin/Centaur processors (Tony W Wang-oc). - Print a warning message on attempts to free an active cpufreq policy which should never happen (Viresh Kumar). - Fix grammar in the Kconfig help text for the loongson2 cpufreq driver (Randy Dunlap). - Use cpumask_var_t for an on-stack CPU mask in the ondemand cpufreq governor (Zhao Liu). - Add trace points for guest_halt_poll_ns grow/shrink to the haltpoll cpuidle driver (Eiichi Tsukata). - Modify intel_idle to treat C1 and C1E as independent idle states on Sapphire Rapids (Artem Bityutskiy). - Extend support for wakeirq to callback wrappers used during system suspend and resume (Ulf Hansson). - Defer waiting for device probe before loading a hibernation image till the first actual device access to avoid possible deadlocks reported by syzbot (Tetsuo Handa). - Unify device_init_wakeup() for PM_SLEEP and !PM_SLEEP (Bjorn Helgaas). - Add Raptor Lake-P to the list of processors supported by the Intel RAPL driver (George D Sworo). - Add Alder Lake-N and Raptor Lake-P to the list of processors for which Power Limit4 is supported in the Intel RAPL driver (Sumeet Pawnikar). - Make pm_genpd_remove() check genpd_debugfs_dir against NULL before attempting to remove it (Hsin-Yi Wang). - Change the Energy Model code to represent power in micro-Watts and adjust its users accordingly (Lukasz Luba). - Add new devfreq driver for Mediatek CCI (Cache Coherent Interconnect) (Johnson Wang). - Convert the Samsung Exynos SoC Bus bindings to DT schema of exynos-bus.c (Krzysztof Kozlowski). - Address kernel-doc warnings by adding the description for unused function parameters in devfreq core (Mauro Carvalho Chehab). - Use NULL to pass a null pointer rather than zero according to the function propotype in imx-bus.c (Colin Ian King). - Print error message instead of error interger value in tegra30-devfreq.c (Dmitry Osipenko). - Add checks to prevent setting negative frequency QoS limits for CPUs (Shivnandan Kumar). - Update the pm-graph suite of utilities to the latest revision 5.9 including multiple improvements (Todd Brandt). - Drop pme_interrupt reference from the PCI power management documentation (Mario Limonciello)" * tag 'pm-5.20-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (27 commits) powercap: RAPL: Add Power Limit4 support for Alder Lake-N and Raptor Lake-P PM: QoS: Add check to make sure CPU freq is non-negative PM: hibernate: defer device probing when resuming from hibernation intel_idle: make SPR C1 and C1E be independent cpufreq: ondemand: Use cpumask_var_t for on-stack cpu mask cpufreq: loongson2: fix Kconfig "its" grammar pm-graph v5.9 cpufreq: Warn users while freeing active policy cpufreq: scmi: Support the power scale in micro-Watts in SCMI v3.1 firmware: arm_scmi: Get detailed power scale from perf Documentation: EM: Switch to micro-Watts scale PM: EM: convert power field to micro-Watts precision and align drivers PM / devfreq: tegra30: Add error message for devm_devfreq_add_device() PM / devfreq: imx-bus: use NULL to pass a null pointer rather than zero PM / devfreq: shut up kernel-doc warnings dt-bindings: interconnect: samsung,exynos-bus: convert to dtschema PM / devfreq: mediatek: Introduce MediaTek CCI devfreq driver dt-bindings: interconnect: Add MediaTek CCI dt-bindings PM: domains: Ensure genpd_debugfs_dir exists before remove PM: runtime: Extend support for wakeirq for force_suspend|resume ...
297 lines
6.8 KiB
C
297 lines
6.8 KiB
C
// SPDX-License-Identifier: GPL-2.0-only
|
|
/*
|
|
* Copyright 2020 Linaro Limited
|
|
*
|
|
* Author: Daniel Lezcano <daniel.lezcano@linaro.org>
|
|
*
|
|
* The DTPM CPU is based on the energy model. It hooks the CPU in the
|
|
* DTPM tree which in turns update the power number by propagating the
|
|
* power number from the CPU energy model information to the parents.
|
|
*
|
|
* The association between the power and the performance state, allows
|
|
* to set the power of the CPU at the OPP granularity.
|
|
*
|
|
* The CPU hotplug is supported and the power numbers will be updated
|
|
* if a CPU is hot plugged / unplugged.
|
|
*/
|
|
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
|
|
|
|
#include <linux/cpumask.h>
|
|
#include <linux/cpufreq.h>
|
|
#include <linux/cpuhotplug.h>
|
|
#include <linux/dtpm.h>
|
|
#include <linux/energy_model.h>
|
|
#include <linux/of.h>
|
|
#include <linux/pm_qos.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/units.h>
|
|
|
|
struct dtpm_cpu {
|
|
struct dtpm dtpm;
|
|
struct freq_qos_request qos_req;
|
|
int cpu;
|
|
};
|
|
|
|
static DEFINE_PER_CPU(struct dtpm_cpu *, dtpm_per_cpu);
|
|
|
|
static struct dtpm_cpu *to_dtpm_cpu(struct dtpm *dtpm)
|
|
{
|
|
return container_of(dtpm, struct dtpm_cpu, dtpm);
|
|
}
|
|
|
|
static u64 set_pd_power_limit(struct dtpm *dtpm, u64 power_limit)
|
|
{
|
|
struct dtpm_cpu *dtpm_cpu = to_dtpm_cpu(dtpm);
|
|
struct em_perf_domain *pd = em_cpu_get(dtpm_cpu->cpu);
|
|
struct cpumask cpus;
|
|
unsigned long freq;
|
|
u64 power;
|
|
int i, nr_cpus;
|
|
|
|
cpumask_and(&cpus, cpu_online_mask, to_cpumask(pd->cpus));
|
|
nr_cpus = cpumask_weight(&cpus);
|
|
|
|
for (i = 0; i < pd->nr_perf_states; i++) {
|
|
|
|
power = pd->table[i].power * nr_cpus;
|
|
|
|
if (power > power_limit)
|
|
break;
|
|
}
|
|
|
|
freq = pd->table[i - 1].frequency;
|
|
|
|
freq_qos_update_request(&dtpm_cpu->qos_req, freq);
|
|
|
|
power_limit = pd->table[i - 1].power * nr_cpus;
|
|
|
|
return power_limit;
|
|
}
|
|
|
|
static u64 scale_pd_power_uw(struct cpumask *pd_mask, u64 power)
|
|
{
|
|
unsigned long max, sum_util = 0;
|
|
int cpu;
|
|
|
|
/*
|
|
* The capacity is the same for all CPUs belonging to
|
|
* the same perf domain.
|
|
*/
|
|
max = arch_scale_cpu_capacity(cpumask_first(pd_mask));
|
|
|
|
for_each_cpu_and(cpu, pd_mask, cpu_online_mask)
|
|
sum_util += sched_cpu_util(cpu);
|
|
|
|
return (power * ((sum_util << 10) / max)) >> 10;
|
|
}
|
|
|
|
static u64 get_pd_power_uw(struct dtpm *dtpm)
|
|
{
|
|
struct dtpm_cpu *dtpm_cpu = to_dtpm_cpu(dtpm);
|
|
struct em_perf_domain *pd;
|
|
struct cpumask *pd_mask;
|
|
unsigned long freq;
|
|
int i;
|
|
|
|
pd = em_cpu_get(dtpm_cpu->cpu);
|
|
|
|
pd_mask = em_span_cpus(pd);
|
|
|
|
freq = cpufreq_quick_get(dtpm_cpu->cpu);
|
|
|
|
for (i = 0; i < pd->nr_perf_states; i++) {
|
|
|
|
if (pd->table[i].frequency < freq)
|
|
continue;
|
|
|
|
return scale_pd_power_uw(pd_mask, pd->table[i].power *
|
|
MICROWATT_PER_MILLIWATT);
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int update_pd_power_uw(struct dtpm *dtpm)
|
|
{
|
|
struct dtpm_cpu *dtpm_cpu = to_dtpm_cpu(dtpm);
|
|
struct em_perf_domain *em = em_cpu_get(dtpm_cpu->cpu);
|
|
struct cpumask cpus;
|
|
int nr_cpus;
|
|
|
|
cpumask_and(&cpus, cpu_online_mask, to_cpumask(em->cpus));
|
|
nr_cpus = cpumask_weight(&cpus);
|
|
|
|
dtpm->power_min = em->table[0].power;
|
|
dtpm->power_min *= MICROWATT_PER_MILLIWATT;
|
|
dtpm->power_min *= nr_cpus;
|
|
|
|
dtpm->power_max = em->table[em->nr_perf_states - 1].power;
|
|
dtpm->power_max *= MICROWATT_PER_MILLIWATT;
|
|
dtpm->power_max *= nr_cpus;
|
|
|
|
return 0;
|
|
}
|
|
|
|
static void pd_release(struct dtpm *dtpm)
|
|
{
|
|
struct dtpm_cpu *dtpm_cpu = to_dtpm_cpu(dtpm);
|
|
struct cpufreq_policy *policy;
|
|
|
|
if (freq_qos_request_active(&dtpm_cpu->qos_req))
|
|
freq_qos_remove_request(&dtpm_cpu->qos_req);
|
|
|
|
policy = cpufreq_cpu_get(dtpm_cpu->cpu);
|
|
if (policy) {
|
|
for_each_cpu(dtpm_cpu->cpu, policy->related_cpus)
|
|
per_cpu(dtpm_per_cpu, dtpm_cpu->cpu) = NULL;
|
|
}
|
|
|
|
kfree(dtpm_cpu);
|
|
}
|
|
|
|
static struct dtpm_ops dtpm_ops = {
|
|
.set_power_uw = set_pd_power_limit,
|
|
.get_power_uw = get_pd_power_uw,
|
|
.update_power_uw = update_pd_power_uw,
|
|
.release = pd_release,
|
|
};
|
|
|
|
static int cpuhp_dtpm_cpu_offline(unsigned int cpu)
|
|
{
|
|
struct dtpm_cpu *dtpm_cpu;
|
|
|
|
dtpm_cpu = per_cpu(dtpm_per_cpu, cpu);
|
|
if (dtpm_cpu)
|
|
dtpm_update_power(&dtpm_cpu->dtpm);
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int cpuhp_dtpm_cpu_online(unsigned int cpu)
|
|
{
|
|
struct dtpm_cpu *dtpm_cpu;
|
|
|
|
dtpm_cpu = per_cpu(dtpm_per_cpu, cpu);
|
|
if (dtpm_cpu)
|
|
return dtpm_update_power(&dtpm_cpu->dtpm);
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int __dtpm_cpu_setup(int cpu, struct dtpm *parent)
|
|
{
|
|
struct dtpm_cpu *dtpm_cpu;
|
|
struct cpufreq_policy *policy;
|
|
struct em_perf_domain *pd;
|
|
char name[CPUFREQ_NAME_LEN];
|
|
int ret = -ENOMEM;
|
|
|
|
dtpm_cpu = per_cpu(dtpm_per_cpu, cpu);
|
|
if (dtpm_cpu)
|
|
return 0;
|
|
|
|
policy = cpufreq_cpu_get(cpu);
|
|
if (!policy)
|
|
return 0;
|
|
|
|
pd = em_cpu_get(cpu);
|
|
if (!pd || em_is_artificial(pd))
|
|
return -EINVAL;
|
|
|
|
dtpm_cpu = kzalloc(sizeof(*dtpm_cpu), GFP_KERNEL);
|
|
if (!dtpm_cpu)
|
|
return -ENOMEM;
|
|
|
|
dtpm_init(&dtpm_cpu->dtpm, &dtpm_ops);
|
|
dtpm_cpu->cpu = cpu;
|
|
|
|
for_each_cpu(cpu, policy->related_cpus)
|
|
per_cpu(dtpm_per_cpu, cpu) = dtpm_cpu;
|
|
|
|
snprintf(name, sizeof(name), "cpu%d-cpufreq", dtpm_cpu->cpu);
|
|
|
|
ret = dtpm_register(name, &dtpm_cpu->dtpm, parent);
|
|
if (ret)
|
|
goto out_kfree_dtpm_cpu;
|
|
|
|
ret = freq_qos_add_request(&policy->constraints,
|
|
&dtpm_cpu->qos_req, FREQ_QOS_MAX,
|
|
pd->table[pd->nr_perf_states - 1].frequency);
|
|
if (ret)
|
|
goto out_dtpm_unregister;
|
|
|
|
return 0;
|
|
|
|
out_dtpm_unregister:
|
|
dtpm_unregister(&dtpm_cpu->dtpm);
|
|
dtpm_cpu = NULL;
|
|
|
|
out_kfree_dtpm_cpu:
|
|
for_each_cpu(cpu, policy->related_cpus)
|
|
per_cpu(dtpm_per_cpu, cpu) = NULL;
|
|
kfree(dtpm_cpu);
|
|
|
|
return ret;
|
|
}
|
|
|
|
static int dtpm_cpu_setup(struct dtpm *dtpm, struct device_node *np)
|
|
{
|
|
int cpu;
|
|
|
|
cpu = of_cpu_node_to_id(np);
|
|
if (cpu < 0)
|
|
return 0;
|
|
|
|
return __dtpm_cpu_setup(cpu, dtpm);
|
|
}
|
|
|
|
static int dtpm_cpu_init(void)
|
|
{
|
|
int ret;
|
|
|
|
/*
|
|
* The callbacks at CPU hotplug time are calling
|
|
* dtpm_update_power() which in turns calls update_pd_power().
|
|
*
|
|
* The function update_pd_power() uses the online mask to
|
|
* figure out the power consumption limits.
|
|
*
|
|
* At CPUHP_AP_ONLINE_DYN, the CPU is present in the CPU
|
|
* online mask when the cpuhp_dtpm_cpu_online function is
|
|
* called, but the CPU is still in the online mask for the
|
|
* tear down callback. So the power can not be updated when
|
|
* the CPU is unplugged.
|
|
*
|
|
* At CPUHP_AP_DTPM_CPU_DEAD, the situation is the opposite as
|
|
* above. The CPU online mask is not up to date when the CPU
|
|
* is plugged in.
|
|
*
|
|
* For this reason, we need to call the online and offline
|
|
* callbacks at different moments when the CPU online mask is
|
|
* consistent with the power numbers we want to update.
|
|
*/
|
|
ret = cpuhp_setup_state(CPUHP_AP_DTPM_CPU_DEAD, "dtpm_cpu:offline",
|
|
NULL, cpuhp_dtpm_cpu_offline);
|
|
if (ret < 0)
|
|
return ret;
|
|
|
|
ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "dtpm_cpu:online",
|
|
cpuhp_dtpm_cpu_online, NULL);
|
|
if (ret < 0)
|
|
return ret;
|
|
|
|
return 0;
|
|
}
|
|
|
|
static void dtpm_cpu_exit(void)
|
|
{
|
|
cpuhp_remove_state_nocalls(CPUHP_AP_ONLINE_DYN);
|
|
cpuhp_remove_state_nocalls(CPUHP_AP_DTPM_CPU_DEAD);
|
|
}
|
|
|
|
struct dtpm_subsys_ops dtpm_cpu_ops = {
|
|
.name = KBUILD_MODNAME,
|
|
.init = dtpm_cpu_init,
|
|
.exit = dtpm_cpu_exit,
|
|
.setup = dtpm_cpu_setup,
|
|
};
|