summaryrefslogtreecommitdiff
path: root/drivers/opp
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2019-03-06 12:59:46 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2019-03-06 12:59:46 -0800
commitef8006846a3a97d9d8bf49e63dba948d0d2dbbf0 (patch)
tree5929135c14913ba7aebe538567d0550b80a61d73 /drivers/opp
parent8dcd175bc3d50b78413c56d5b17d4bddd77412ef (diff)
parent1271d6d576b7e7c80519de211f250cfd4eebca1a (diff)
Merge tag 'pm-5.1-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm
Pull power management updates from Rafael Wysocki: "These are PM-runtime framework changes to use ktime instead of jiffies for accounting, new PM core flag to mark devices that don't need any form of power management, cpuidle updates including driver API documentation and a new governor, cpufreq updates including a new driver for Armada 8K, thermal cleanups and more, some energy-aware scheduling (EAS) enabling changes, new chips support in the intel_idle and RAPL drivers and assorted cleanups in some other places. Specifics: - Update the PM-runtime framework to use ktime instead of jiffies for accounting (Thara Gopinath, Vincent Guittot) - Optimize the autosuspend code in the PM-runtime framework somewhat (Ladislav Michl) - Add a PM core flag to mark devices that don't need any form of power management (Sudeep Holla) - Introduce driver API documentation for cpuidle and add a new cpuidle governor for tickless systems (Rafael Wysocki) - Add Jacobsville support to the intel_idle driver (Zhang Rui) - Clean up a cpuidle core header file and the cpuidle-dt and ACPI processor-idle drivers (Yangtao Li, Joseph Lo, Yazen Ghannam) - Add new cpufreq driver for Armada 8K (Gregory Clement) - Fix and clean up cpufreq core (Rafael Wysocki, Viresh Kumar, Amit Kucheria) - Add support for light-weight tear-down and bring-up of CPUs to the cpufreq core and use it in the cpufreq-dt driver (Viresh Kumar) - Fix cpu_cooling Kconfig dependencies, add support for CPU cooling auto-registration to the cpufreq core and use it in multiple cpufreq drivers (Amit Kucheria) - Fix some minor issues and do some cleanups in the davinci, e_powersaver, ap806, s5pv210, qcom and kryo cpufreq drivers (Bartosz Golaszewski, Gustavo Silva, Julia Lawall, Paweł Chmiel, Taniya Das, Viresh Kumar) - Add a Hisilicon CPPC quirk to the cppc_cpufreq driver (Xiongfeng Wang) - Clean up the intel_pstate and acpi-cpufreq drivers (Erwan Velu, Rafael Wysocki) - Clean up multiple cpufreq drivers (Yangtao Li) - Update cpufreq-related MAINTAINERS entries (Baruch Siach, Lukas Bulwahn) - Add support for exposing the Energy Model via debugfs and make multiple cpufreq drivers register an Energy Model to support energy-aware scheduling (Quentin Perret, Dietmar Eggemann, Matthias Kaehlcke) - Add Ice Lake mobile and Jacobsville support to the Intel RAPL power-capping driver (Gayatri Kammela, Zhang Rui) - Add a power estimation helper to the operating performance points (OPP) framework and clean up a core function in it (Quentin Perret, Viresh Kumar) - Make minor improvements in the generic power domains (genpd), OPP and system suspend frameworks and in the PM core (Aditya Pakki, Douglas Anderson, Greg Kroah-Hartman, Rafael Wysocki, Yangtao Li)" * tag 'pm-5.1-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (80 commits) cpufreq: kryo: Release OPP tables on module removal cpufreq: ap806: add missing of_node_put after of_device_is_available cpufreq: acpi-cpufreq: Report if CPU doesn't support boost technologies cpufreq: Pass updated policy to driver ->setpolicy() callback cpufreq: Fix two debug messages in cpufreq_set_policy() cpufreq: Reorder and simplify cpufreq_update_policy() cpufreq: Add kerneldoc comments for two core functions PM / core: Add support to skip power management in device/driver model cpufreq: intel_pstate: Rework iowait boosting to be less aggressive cpufreq: intel_pstate: Eliminate intel_pstate_get_base_pstate() cpufreq: intel_pstate: Avoid redundant initialization of local vars powercap/intel_rapl: add Ice Lake mobile ACPI / processor: Set P_LVL{2,3} idle state descriptions cpufreq / cppc: Work around for Hisilicon CPPC cpufreq ACPI / CPPC: Add a helper to get desired performance cpufreq: davinci: move configuration to include/linux/platform_data cpufreq: speedstep: convert BUG() to BUG_ON() cpufreq: powernv: fix missing check of return value in init_powernv_pstates() cpufreq: longhaul: remove unneeded semicolon cpufreq: pcc-cpufreq: remove unneeded semicolon ..
Diffstat (limited to 'drivers/opp')
-rw-r--r--drivers/opp/core.c22
-rw-r--r--drivers/opp/debugfs.c110
-rw-r--r--drivers/opp/of.c99
-rw-r--r--drivers/opp/opp.h15
4 files changed, 142 insertions, 104 deletions
diff --git a/drivers/opp/core.c b/drivers/opp/core.c
index e06a0ab05ad6..d7f97167cac3 100644
--- a/drivers/opp/core.c
+++ b/drivers/opp/core.c
@@ -551,9 +551,8 @@ static int _set_opp_voltage(struct device *dev, struct regulator *reg,
return ret;
}
-static inline int
-_generic_set_opp_clk_only(struct device *dev, struct clk *clk,
- unsigned long old_freq, unsigned long freq)
+static inline int _generic_set_opp_clk_only(struct device *dev, struct clk *clk,
+ unsigned long freq)
{
int ret;
@@ -590,7 +589,7 @@ static int _generic_set_opp_regulator(const struct opp_table *opp_table,
}
/* Change frequency */
- ret = _generic_set_opp_clk_only(dev, opp_table->clk, old_freq, freq);
+ ret = _generic_set_opp_clk_only(dev, opp_table->clk, freq);
if (ret)
goto restore_voltage;
@@ -604,7 +603,7 @@ static int _generic_set_opp_regulator(const struct opp_table *opp_table,
return 0;
restore_freq:
- if (_generic_set_opp_clk_only(dev, opp_table->clk, freq, old_freq))
+ if (_generic_set_opp_clk_only(dev, opp_table->clk, old_freq))
dev_err(dev, "%s: failed to restore old-freq (%lu Hz)\n",
__func__, old_freq);
restore_voltage:
@@ -777,7 +776,7 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
opp->supplies);
} else {
/* Only frequency scaling */
- ret = _generic_set_opp_clk_only(dev, clk, old_freq, freq);
+ ret = _generic_set_opp_clk_only(dev, clk, freq);
}
/* Scaling down? Configure required OPPs after frequency */
@@ -811,7 +810,6 @@ static struct opp_device *_add_opp_dev_unlocked(const struct device *dev,
struct opp_table *opp_table)
{
struct opp_device *opp_dev;
- int ret;
opp_dev = kzalloc(sizeof(*opp_dev), GFP_KERNEL);
if (!opp_dev)
@@ -823,10 +821,7 @@ static struct opp_device *_add_opp_dev_unlocked(const struct device *dev,
list_add(&opp_dev->node, &opp_table->dev_list);
/* Create debugfs entries for the opp_table */
- ret = opp_debug_register(opp_dev, opp_table);
- if (ret)
- dev_err(dev, "%s: Failed to register opp debugfs (%d)\n",
- __func__, ret);
+ opp_debug_register(opp_dev, opp_table);
return opp_dev;
}
@@ -1247,10 +1242,7 @@ int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
new_opp->opp_table = opp_table;
kref_init(&new_opp->kref);
- ret = opp_debug_create_one(new_opp, opp_table);
- if (ret)
- dev_err(dev, "%s: Failed to register opp to debugfs (%d)\n",
- __func__, ret);
+ opp_debug_create_one(new_opp, opp_table);
if (!_opp_supported_by_regulators(new_opp, opp_table)) {
new_opp->available = false;
diff --git a/drivers/opp/debugfs.c b/drivers/opp/debugfs.c
index e6828e5f81b0..a1c57fe14de4 100644
--- a/drivers/opp/debugfs.c
+++ b/drivers/opp/debugfs.c
@@ -35,7 +35,7 @@ void opp_debug_remove_one(struct dev_pm_opp *opp)
debugfs_remove_recursive(opp->dentry);
}
-static bool opp_debug_create_supplies(struct dev_pm_opp *opp,
+static void opp_debug_create_supplies(struct dev_pm_opp *opp,
struct opp_table *opp_table,
struct dentry *pdentry)
{
@@ -50,30 +50,21 @@ static bool opp_debug_create_supplies(struct dev_pm_opp *opp,
/* Create per-opp directory */
d = debugfs_create_dir(name, pdentry);
- if (!d)
- return false;
+ debugfs_create_ulong("u_volt_target", S_IRUGO, d,
+ &opp->supplies[i].u_volt);
- if (!debugfs_create_ulong("u_volt_target", S_IRUGO, d,
- &opp->supplies[i].u_volt))
- return false;
+ debugfs_create_ulong("u_volt_min", S_IRUGO, d,
+ &opp->supplies[i].u_volt_min);
- if (!debugfs_create_ulong("u_volt_min", S_IRUGO, d,
- &opp->supplies[i].u_volt_min))
- return false;
+ debugfs_create_ulong("u_volt_max", S_IRUGO, d,
+ &opp->supplies[i].u_volt_max);
- if (!debugfs_create_ulong("u_volt_max", S_IRUGO, d,
- &opp->supplies[i].u_volt_max))
- return false;
-
- if (!debugfs_create_ulong("u_amp", S_IRUGO, d,
- &opp->supplies[i].u_amp))
- return false;
+ debugfs_create_ulong("u_amp", S_IRUGO, d,
+ &opp->supplies[i].u_amp);
}
-
- return true;
}
-int opp_debug_create_one(struct dev_pm_opp *opp, struct opp_table *opp_table)
+void opp_debug_create_one(struct dev_pm_opp *opp, struct opp_table *opp_table)
{
struct dentry *pdentry = opp_table->dentry;
struct dentry *d;
@@ -95,40 +86,23 @@ int opp_debug_create_one(struct dev_pm_opp *opp, struct opp_table *opp_table)
/* Create per-opp directory */
d = debugfs_create_dir(name, pdentry);
- if (!d)
- return -ENOMEM;
-
- if (!debugfs_create_bool("available", S_IRUGO, d, &opp->available))
- return -ENOMEM;
-
- if (!debugfs_create_bool("dynamic", S_IRUGO, d, &opp->dynamic))
- return -ENOMEM;
-
- if (!debugfs_create_bool("turbo", S_IRUGO, d, &opp->turbo))
- return -ENOMEM;
-
- if (!debugfs_create_bool("suspend", S_IRUGO, d, &opp->suspend))
- return -ENOMEM;
-
- if (!debugfs_create_u32("performance_state", S_IRUGO, d, &opp->pstate))
- return -ENOMEM;
- if (!debugfs_create_ulong("rate_hz", S_IRUGO, d, &opp->rate))
- return -ENOMEM;
+ debugfs_create_bool("available", S_IRUGO, d, &opp->available);
+ debugfs_create_bool("dynamic", S_IRUGO, d, &opp->dynamic);
+ debugfs_create_bool("turbo", S_IRUGO, d, &opp->turbo);
+ debugfs_create_bool("suspend", S_IRUGO, d, &opp->suspend);
+ debugfs_create_u32("performance_state", S_IRUGO, d, &opp->pstate);
+ debugfs_create_ulong("rate_hz", S_IRUGO, d, &opp->rate);
+ debugfs_create_ulong("clock_latency_ns", S_IRUGO, d,
+ &opp->clock_latency_ns);
- if (!opp_debug_create_supplies(opp, opp_table, d))
- return -ENOMEM;
-
- if (!debugfs_create_ulong("clock_latency_ns", S_IRUGO, d,
- &opp->clock_latency_ns))
- return -ENOMEM;
+ opp_debug_create_supplies(opp, opp_table, d);
opp->dentry = d;
- return 0;
}
-static int opp_list_debug_create_dir(struct opp_device *opp_dev,
- struct opp_table *opp_table)
+static void opp_list_debug_create_dir(struct opp_device *opp_dev,
+ struct opp_table *opp_table)
{
const struct device *dev = opp_dev->dev;
struct dentry *d;
@@ -137,36 +111,21 @@ static int opp_list_debug_create_dir(struct opp_device *opp_dev,
/* Create device specific directory */
d = debugfs_create_dir(opp_table->dentry_name, rootdir);
- if (!d) {
- dev_err(dev, "%s: Failed to create debugfs dir\n", __func__);
- return -ENOMEM;
- }
opp_dev->dentry = d;
opp_table->dentry = d;
-
- return 0;
}
-static int opp_list_debug_create_link(struct opp_device *opp_dev,
- struct opp_table *opp_table)
+static void opp_list_debug_create_link(struct opp_device *opp_dev,
+ struct opp_table *opp_table)
{
- const struct device *dev = opp_dev->dev;
char name[NAME_MAX];
- struct dentry *d;
opp_set_dev_name(opp_dev->dev, name);
/* Create device specific directory link */
- d = debugfs_create_symlink(name, rootdir, opp_table->dentry_name);
- if (!d) {
- dev_err(dev, "%s: Failed to create link\n", __func__);
- return -ENOMEM;
- }
-
- opp_dev->dentry = d;
-
- return 0;
+ opp_dev->dentry = debugfs_create_symlink(name, rootdir,
+ opp_table->dentry_name);
}
/**
@@ -177,20 +136,13 @@ static int opp_list_debug_create_link(struct opp_device *opp_dev,
* Dynamically adds device specific directory in debugfs 'opp' directory. If the
* device-opp is shared with other devices, then links will be created for all
* devices except the first.
- *
- * Return: 0 on success, otherwise negative error.
*/
-int opp_debug_register(struct opp_device *opp_dev, struct opp_table *opp_table)
+void opp_debug_register(struct opp_device *opp_dev, struct opp_table *opp_table)
{
- if (!rootdir) {
- pr_debug("%s: Uninitialized rootdir\n", __func__);
- return -EINVAL;
- }
-
if (opp_table->dentry)
- return opp_list_debug_create_link(opp_dev, opp_table);
-
- return opp_list_debug_create_dir(opp_dev, opp_table);
+ opp_list_debug_create_link(opp_dev, opp_table);
+ else
+ opp_list_debug_create_dir(opp_dev, opp_table);
}
static void opp_migrate_dentry(struct opp_device *opp_dev,
@@ -252,10 +204,6 @@ static int __init opp_debug_init(void)
{
/* Create /sys/kernel/debug/opp directory */
rootdir = debugfs_create_dir("opp", NULL);
- if (!rootdir) {
- pr_err("%s: Failed to create root directory\n", __func__);
- return -ENOMEM;
- }
return 0;
}
diff --git a/drivers/opp/of.c b/drivers/opp/of.c
index 1779f2c93291..62504b18f198 100644
--- a/drivers/opp/of.c
+++ b/drivers/opp/of.c
@@ -20,6 +20,7 @@
#include <linux/pm_domain.h>
#include <linux/slab.h>
#include <linux/export.h>
+#include <linux/energy_model.h>
#include "opp.h"
@@ -1049,3 +1050,101 @@ struct device_node *dev_pm_opp_get_of_node(struct dev_pm_opp *opp)
return of_node_get(opp->np);
}
EXPORT_SYMBOL_GPL(dev_pm_opp_get_of_node);
+
+/*
+ * Callback function provided to the Energy Model framework upon registration.
+ * This computes the power estimated by @CPU at @kHz if it is the frequency
+ * of an existing OPP, or at the frequency of the first OPP above @kHz otherwise
+ * (see dev_pm_opp_find_freq_ceil()). This function updates @kHz to the ceiled
+ * frequency and @mW to the associated power. The power is estimated as
+ * P = C * V^2 * f with C being the CPU's capacitance and V and f respectively
+ * the voltage and frequency of the OPP.
+ *
+ * Returns -ENODEV if the CPU device cannot be found, -EINVAL if the power
+ * calculation failed because of missing parameters, 0 otherwise.
+ */
+static int __maybe_unused _get_cpu_power(unsigned long *mW, unsigned long *kHz,
+ int cpu)
+{
+ struct device *cpu_dev;
+ struct dev_pm_opp *opp;
+ struct device_node *np;
+ unsigned long mV, Hz;
+ u32 cap;
+ u64 tmp;
+ int ret;
+
+ cpu_dev = get_cpu_device(cpu);
+ if (!cpu_dev)
+ return -ENODEV;
+
+ np = of_node_get(cpu_dev->of_node);
+ if (!np)
+ return -EINVAL;
+
+ ret = of_property_read_u32(np, "dynamic-power-coefficient", &cap);
+ of_node_put(np);
+ if (ret)
+ return -EINVAL;
+
+ Hz = *kHz * 1000;
+ opp = dev_pm_opp_find_freq_ceil(cpu_dev, &Hz);
+ if (IS_ERR(opp))
+ return -EINVAL;
+
+ mV = dev_pm_opp_get_voltage(opp) / 1000;
+ dev_pm_opp_put(opp);
+ if (!mV)
+ return -EINVAL;
+
+ tmp = (u64)cap * mV * mV * (Hz / 1000000);
+ do_div(tmp, 1000000000);
+
+ *mW = (unsigned long)tmp;
+ *kHz = Hz / 1000;
+
+ return 0;
+}
+
+/**
+ * dev_pm_opp_of_register_em() - Attempt to register an Energy Model
+ * @cpus : CPUs for which an Energy Model has to be registered
+ *
+ * This checks whether the "dynamic-power-coefficient" devicetree property has
+ * been specified, and tries to register an Energy Model with it if it has.
+ */
+void dev_pm_opp_of_register_em(struct cpumask *cpus)
+{
+ struct em_data_callback em_cb = EM_DATA_CB(_get_cpu_power);
+ int ret, nr_opp, cpu = cpumask_first(cpus);
+ struct device *cpu_dev;
+ struct device_node *np;
+ u32 cap;
+
+ cpu_dev = get_cpu_device(cpu);
+ if (!cpu_dev)
+ return;
+
+ nr_opp = dev_pm_opp_get_opp_count(cpu_dev);
+ if (nr_opp <= 0)
+ return;
+
+ np = of_node_get(cpu_dev->of_node);
+ if (!np)
+ return;
+
+ /*
+ * Register an EM only if the 'dynamic-power-coefficient' property is
+ * set in devicetree. It is assumed the voltage values are known if that
+ * property is set since it is useless otherwise. If voltages are not
+ * known, just let the EM registration fail with an error to alert the
+ * user about the inconsistent configuration.
+ */
+ ret = of_property_read_u32(np, "dynamic-power-coefficient", &cap);
+ of_node_put(np);
+ if (ret || !cap)
+ return;
+
+ em_register_perf_domain(cpus, nr_opp, &em_cb);
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_of_register_em);
diff --git a/drivers/opp/opp.h b/drivers/opp/opp.h
index 4458175aa661..569b3525aa67 100644
--- a/drivers/opp/opp.h
+++ b/drivers/opp/opp.h
@@ -238,18 +238,17 @@ static inline void _of_opp_free_required_opps(struct opp_table *opp_table,
#ifdef CONFIG_DEBUG_FS
void opp_debug_remove_one(struct dev_pm_opp *opp);
-int opp_debug_create_one(struct dev_pm_opp *opp, struct opp_table *opp_table);
-int opp_debug_register(struct opp_device *opp_dev, struct opp_table *opp_table);
+void opp_debug_create_one(struct dev_pm_opp *opp, struct opp_table *opp_table);
+void opp_debug_register(struct opp_device *opp_dev, struct opp_table *opp_table);
void opp_debug_unregister(struct opp_device *opp_dev, struct opp_table *opp_table);
#else
static inline void opp_debug_remove_one(struct dev_pm_opp *opp) {}
-static inline int opp_debug_create_one(struct dev_pm_opp *opp,
- struct opp_table *opp_table)
-{ return 0; }
-static inline int opp_debug_register(struct opp_device *opp_dev,
- struct opp_table *opp_table)
-{ return 0; }
+static inline void opp_debug_create_one(struct dev_pm_opp *opp,
+ struct opp_table *opp_table) { }
+
+static inline void opp_debug_register(struct opp_device *opp_dev,
+ struct opp_table *opp_table) { }
static inline void opp_debug_unregister(struct opp_device *opp_dev,
struct opp_table *opp_table)