diff options
| author | Linus Torvalds | 2019-07-09 19:05:22 +0200 |
|---|---|---|
| committer | Linus Torvalds | 2019-07-09 19:05:22 +0200 |
| commit | cf2d213e49fdf47e4c10dc629a3659e0026a54b8 (patch) | |
| tree | a3a1bded510f0c855a4a9b1c450cf9dd3344ebb7 /drivers | |
| parent | Merge tag 'sound-5.3-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/ti... (diff) | |
| parent | Merge branch 'pm-cpufreq' (diff) | |
| download | kernel-qcow2-linux-cf2d213e49fdf47e4c10dc629a3659e0026a54b8.tar.gz kernel-qcow2-linux-cf2d213e49fdf47e4c10dc629a3659e0026a54b8.tar.xz kernel-qcow2-linux-cf2d213e49fdf47e4c10dc629a3659e0026a54b8.zip | |
Merge tag 'pm-5.3-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm
Pull power management updates from Rafael Wysocki:
"These update PCI and ACPI power management (improved handling of ACPI
power resources and PCIe link delays, fixes related to corner cases,
hibernation handling rework), fix and extend the operating performance
points (OPP) framework, add new cpufreq drivers for Raspberry Pi and
imx8m chips, update some other cpufreq drivers, clean up assorted
pieces of PM code and documentation and update tools.
Specifics:
- Improve the handling of shared ACPI power resources in the PCI bus
type layer (Mika Westerberg).
- Make the PCI layer take link delays required by the PCIe spec into
account as appropriate and avoid polling devices in D3cold for PME
(Mika Westerberg).
- Fix some corner case issues in ACPI device power management and in
the PCI bus type layer, optimiza and clean up the handling of
runtime-suspended PCI devices during system-wide transitions to
sleep states (Rafael Wysocki).
- Rework hibernation handling in the ACPI core and the PCI bus type
to resume runtime-suspended devices before hibernation (which
allows some functional problems to be avoided) and fix some ACPI
power management issues related to hiberation (Rafael Wysocki).
- Extend the operating performance points (OPP) framework to support
a wider range of devices (Rajendra Nayak, Stehpen Boyd).
- Fix issues related to genpd_virt_devs and issues with platforms
using the set_opp() callback in the OPP framework (Viresh Kumar,
Dmitry Osipenko).
- Add new cpufreq driver for Raspberry Pi (Nicolas Saenz Julienne).
- Add new cpufreq driver for imx8m and imx7d chips (Leonard Crestez).
- Fix and clean up the pcc-cpufreq, brcmstb-avs-cpufreq, s5pv210, and
armada-37xx cpufreq drivers (David Arcari, Florian Fainelli, Paweł
Chmiel, YueHaibing).
- Clean up and fix the cpufreq core (Viresh Kumar, Daniel Lezcano).
- Fix minor issue in the ACPI system sleep support code and export
one function from it (Lenny Szubowicz, Dexuan Cui).
- Clean up assorted pieces of PM code and documentation (Kefeng Wang,
Andy Shevchenko, Bart Van Assche, Greg Kroah-Hartman, Fuqian Huang,
Geert Uytterhoeven, Mathieu Malaterre, Rafael Wysocki).
- Update the pm-graph utility to v5.4 (Todd Brandt).
- Fix and clean up the cpupower utility (Abhishek Goel, Nick Black)"
* tag 'pm-5.3-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (57 commits)
ACPI: PM: Make acpi_sleep_state_supported() non-static
PM: sleep: Drop dev_pm_skip_next_resume_phases()
ACPI: PM: Unexport acpi_device_get_power()
Documentation: ABI: power: Add missing newline at end of file
ACPI: PM: Drop unused function and function header
ACPI: PM: Introduce "poweroff" callbacks for ACPI PM domain and LPSS
ACPI: PM: Simplify and fix PM domain hibernation callbacks
PCI: PM: Simplify bus-level hibernation callbacks
PM: ACPI/PCI: Resume all devices during hibernation
cpufreq: Avoid calling cpufreq_verify_current_freq() from handle_update()
cpufreq: Consolidate cpufreq_update_current_freq() and __cpufreq_get()
kernel: power: swap: use kzalloc() instead of kmalloc() followed by memset()
cpufreq: Don't skip frequency validation for has_target() drivers
PCI: PM/ACPI: Refresh all stale power state data in pci_pm_complete()
PCI / ACPI: Add _PR0 dependent devices
ACPI / PM: Introduce concept of a _PR0 dependent device
PCI / ACPI: Use cached ACPI device state to get PCI device power state
ACPI: PM: Allow transitions to D0 to occur in special cases
ACPI: PM: Avoid evaluating _PS3 on transitions from D3hot to D3cold
cpufreq: Use has_target() instead of !setpolicy
...
Diffstat (limited to 'drivers')
29 files changed, 995 insertions, 389 deletions
diff --git a/drivers/acpi/acpi_lpit.c b/drivers/acpi/acpi_lpit.c index 6116b0fb86d4..433376e819bb 100644 --- a/drivers/acpi/acpi_lpit.c +++ b/drivers/acpi/acpi_lpit.c @@ -129,7 +129,7 @@ static void lpit_update_residency(struct lpit_residency_info *info, static void lpit_process(u64 begin, u64 end) { - while (begin + sizeof(struct acpi_lpit_native) < end) { + while (begin + sizeof(struct acpi_lpit_native) <= end) { struct acpi_lpit_native *lpit_native = (struct acpi_lpit_native *)begin; if (!lpit_native->header.type && !lpit_native->header.flags) { @@ -148,7 +148,6 @@ static void lpit_process(u64 begin, u64 end) void acpi_init_lpit(void) { acpi_status status; - u64 lpit_begin; struct acpi_table_lpit *lpit; status = acpi_get_table(ACPI_SIG_LPIT, 0, (struct acpi_table_header **)&lpit); @@ -156,6 +155,6 @@ void acpi_init_lpit(void) if (ACPI_FAILURE(status)) return; - lpit_begin = (u64)lpit + sizeof(*lpit); - lpit_process(lpit_begin, lpit_begin + lpit->header.length); + lpit_process((u64)lpit + sizeof(*lpit), + (u64)lpit + lpit->header.length); } diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c index 23484aa877b6..398451839178 100644 --- a/drivers/acpi/acpi_lpss.c +++ b/drivers/acpi/acpi_lpss.c @@ -1061,6 +1061,13 @@ static int acpi_lpss_suspend_noirq(struct device *dev) int ret; if (pdata->dev_desc->resume_from_noirq) { + /* + * The driver's ->suspend_late callback will be invoked by + * acpi_lpss_do_suspend_late(), with the assumption that the + * driver really wanted to run that code in ->suspend_noirq, but + * it could not run after acpi_dev_suspend() and the driver + * expected the latter to be called in the "late" phase. + */ ret = acpi_lpss_do_suspend_late(dev); if (ret) return ret; @@ -1091,16 +1098,99 @@ static int acpi_lpss_resume_noirq(struct device *dev) struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev)); int ret; - ret = acpi_subsys_resume_noirq(dev); + /* Follow acpi_subsys_resume_noirq(). */ + if (dev_pm_may_skip_resume(dev)) + return 0; + + if (dev_pm_smart_suspend_and_suspended(dev)) + pm_runtime_set_active(dev); + + ret = pm_generic_resume_noirq(dev); if (ret) return ret; - if (!dev_pm_may_skip_resume(dev) && pdata->dev_desc->resume_from_noirq) - ret = acpi_lpss_do_resume_early(dev); + if (!pdata->dev_desc->resume_from_noirq) + return 0; - return ret; + /* + * The driver's ->resume_early callback will be invoked by + * acpi_lpss_do_resume_early(), with the assumption that the driver + * really wanted to run that code in ->resume_noirq, but it could not + * run before acpi_dev_resume() and the driver expected the latter to be + * called in the "early" phase. + */ + return acpi_lpss_do_resume_early(dev); +} + +static int acpi_lpss_do_restore_early(struct device *dev) +{ + int ret = acpi_lpss_resume(dev); + + return ret ? ret : pm_generic_restore_early(dev); } +static int acpi_lpss_restore_early(struct device *dev) +{ + struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev)); + + if (pdata->dev_desc->resume_from_noirq) + return 0; + + return acpi_lpss_do_restore_early(dev); +} + +static int acpi_lpss_restore_noirq(struct device *dev) +{ + struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev)); + int ret; + + ret = pm_generic_restore_noirq(dev); + if (ret) + return ret; + + if (!pdata->dev_desc->resume_from_noirq) + return 0; + + /* This is analogous to what happens in acpi_lpss_resume_noirq(). */ + return acpi_lpss_do_restore_early(dev); +} + +static int acpi_lpss_do_poweroff_late(struct device *dev) +{ + int ret = pm_generic_poweroff_late(dev); + + return ret ? ret : acpi_lpss_suspend(dev, device_may_wakeup(dev)); +} + +static int acpi_lpss_poweroff_late(struct device *dev) +{ + struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev)); + + if (dev_pm_smart_suspend_and_suspended(dev)) + return 0; + + if (pdata->dev_desc->resume_from_noirq) + return 0; + + return acpi_lpss_do_poweroff_late(dev); +} + +static int acpi_lpss_poweroff_noirq(struct device *dev) +{ + struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev)); + + if (dev_pm_smart_suspend_and_suspended(dev)) + return 0; + + if (pdata->dev_desc->resume_from_noirq) { + /* This is analogous to the acpi_lpss_suspend_noirq() case. */ + int ret = acpi_lpss_do_poweroff_late(dev); + if (ret) + return ret; + } + + return pm_generic_poweroff_noirq(dev); +} #endif /* CONFIG_PM_SLEEP */ static int acpi_lpss_runtime_suspend(struct device *dev) @@ -1134,14 +1224,11 @@ static struct dev_pm_domain acpi_lpss_pm_domain = { .resume_noirq = acpi_lpss_resume_noirq, .resume_early = acpi_lpss_resume_early, .freeze = acpi_subsys_freeze, - .freeze_late = acpi_subsys_freeze_late, - .freeze_noirq = acpi_subsys_freeze_noirq, - .thaw_noirq = acpi_subsys_thaw_noirq, - .poweroff = acpi_subsys_suspend, - .poweroff_late = acpi_lpss_suspend_late, - .poweroff_noirq = acpi_lpss_suspend_noirq, - .restore_noirq = acpi_lpss_resume_noirq, - .restore_early = acpi_lpss_resume_early, + .poweroff = acpi_subsys_poweroff, + .poweroff_late = acpi_lpss_poweroff_late, + .poweroff_noirq = acpi_lpss_poweroff_noirq, + .restore_noirq = acpi_lpss_restore_noirq, + .restore_early = acpi_lpss_restore_early, #endif .runtime_suspend = acpi_lpss_runtime_suspend, .runtime_resume = acpi_lpss_runtime_resume, diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c index e54956ae93d3..28cffaaf9d82 100644 --- a/drivers/acpi/device_pm.c +++ b/drivers/acpi/device_pm.c @@ -45,6 +45,19 @@ const char *acpi_power_state_string(int state) } } +static int acpi_dev_pm_explicit_get(struct acpi_device *device, int *state) +{ + unsigned long long psc; + acpi_status status; + + status = acpi_evaluate_integer(device->handle, "_PSC", NULL, &psc); + if (ACPI_FAILURE(status)) + return -ENODEV; + + *state = psc; + return 0; +} + /** * acpi_device_get_power - Get power state of an ACPI device. * @device: Device to get the power state of. @@ -53,10 +66,16 @@ const char *acpi_power_state_string(int state) * This function does not update the device's power.state field, but it may * update its parent's power.state field (when the parent's power state is * unknown and the device's power state turns out to be D0). + * + * Also, it does not update power resource reference counters to ensure that + * the power state returned by it will be persistent and it may return a power + * state shallower than previously set by acpi_device_set_power() for @device + * (if that power state depends on any power resources). */ int acpi_device_get_power(struct acpi_device *device, int *state) { int result = ACPI_STATE_UNKNOWN; + int error; if (!device || !state) return -EINVAL; @@ -73,18 +92,16 @@ int acpi_device_get_power(struct acpi_device *device, int *state) * if available. */ if (device->power.flags.power_resources) { - int error = acpi_power_get_inferred_state(device, &result); + error = acpi_power_get_inferred_state(device, &result); if (error) return error; } if (device->power.flags.explicit_get) { - acpi_handle handle = device->handle; - unsigned long long psc; - acpi_status status; + int psc; - status = acpi_evaluate_integer(handle, "_PSC", NULL, &psc); - if (ACPI_FAILURE(status)) - return -ENODEV; + error = acpi_dev_pm_explicit_get(device, &psc); + if (error) + return error; /* * The power resources settings may indicate a power state @@ -118,7 +135,6 @@ int acpi_device_get_power(struct acpi_device *device, int *state) return 0; } -EXPORT_SYMBOL(acpi_device_get_power); static int acpi_dev_pm_explicit_set(struct acpi_device *adev, int state) { @@ -152,7 +168,8 @@ int acpi_device_set_power(struct acpi_device *device, int state) /* Make sure this is a valid target state */ - if (state == device->power.state) { + /* There is a special case for D0 addressed below. */ + if (state > ACPI_STATE_D0 && state == device->power.state) { ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Device [%s] already in %s\n", device->pnp.bus_id, acpi_power_state_string(state))); @@ -202,9 +219,15 @@ int acpi_device_set_power(struct acpi_device *device, int state) return -ENODEV; } - result = acpi_dev_pm_explicit_set(device, state); - if (result) - goto end; + /* + * If the device goes from D3hot to D3cold, _PS3 has been + * evaluated for it already, so skip it in that case. + */ + if (device->power.state < ACPI_STATE_D3_HOT) { + result = acpi_dev_pm_explicit_set(device, state); + if (result) + goto end; + } if (device->power.flags.power_resources) result = acpi_power_transition(device, target_state); @@ -214,6 +237,30 @@ int acpi_device_set_power(struct acpi_device *device, int state) if (result) goto end; } + + if (device->power.state == ACPI_STATE_D0) { + int psc; + + /* Nothing to do here if _PSC is not present. */ + if (!device->power.flags.explicit_get) + return 0; + + /* + * The power state of the device was set to D0 last + * time, but that might have happened before a + * system-wide transition involving the platform + * firmware, so it may be necessary to evaluate _PS0 + * for the device here. However, use extra care here + * and evaluate _PSC to check the device's current power + * state, and only invoke _PS0 if the evaluation of _PSC + * is successful and it returns a power state different + * from D0. + */ + result = acpi_dev_pm_explicit_get(device, &psc); + if (result || psc == ACPI_STATE_D0) + return 0; + } + result = acpi_dev_pm_explicit_set(device, ACPI_STATE_D0); } @@ -1073,7 +1120,7 @@ EXPORT_SYMBOL_GPL(acpi_subsys_suspend_noirq); * acpi_subsys_resume_noirq - Run the device driver's "noirq" resume callback. * @dev: Device to handle. */ -int acpi_subsys_resume_noirq(struct device *dev) +static int acpi_subsys_resume_noirq(struct device *dev) { if (dev_pm_may_skip_resume(dev)) return 0; @@ -1088,7 +1135,6 @@ int acpi_subsys_resume_noirq(struct device *dev) return pm_generic_resume_noirq(dev); } -EXPORT_SYMBOL_GPL(acpi_subsys_resume_noirq); /** * acpi_subsys_resume_early - Resume device using ACPI. @@ -1098,12 +1144,11 @@ EXPORT_SYMBOL_GPL(acpi_subsys_resume_noirq); * generic early resume procedure for it during system transition into the * working state. */ -int acpi_subsys_resume_early(struct device *dev) +static int acpi_subsys_resume_early(struct device *dev) { int ret = acpi_dev_resume(dev); return ret ? ret : pm_generic_resume_early(dev); } -EXPORT_SYMBOL_GPL(acpi_subsys_resume_early); /** * acpi_subsys_freeze - Run the device driver's freeze callback. @@ -1112,65 +1157,81 @@ EXPORT_SYMBOL_GPL(acpi_subsys_resume_early); int acpi_subsys_freeze(struct device *dev) { /* - * This used to be done in acpi_subsys_prepare() for all devices and - * some drivers may depend on it, so do it here. Ideally, however, - * runtime-suspended devices should not be touched during freeze/thaw - * transitions. + * Resume all runtime-suspended devices before creating a snapshot + * image of system memory, because the restore kernel generally cannot + * be expected to always handle them consistently and they need to be + * put into the runtime-active metastate during system resume anyway, + * so it is better to ensure that the state saved in the image will be + * always consistent with that. */ - if (!dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND)) - pm_runtime_resume(dev); + pm_runtime_resume(dev); return pm_generic_freeze(dev); } EXPORT_SYMBOL_GPL(acpi_subsys_freeze); /** - * acpi_subsys_freeze_late - Run the device driver's "late" freeze callback. - * @dev: Device to handle. + * acpi_subsys_restore_early - Restore device using ACPI. + * @dev: Device to restore. */ -int acpi_subsys_freeze_late(struct device *dev) +int acpi_subsys_restore_early(struct device *dev) { + int ret = acpi_dev_resume(dev); + return ret ? ret : pm_generic_restore_early(dev); +} +EXPORT_SYMBOL_GPL(acpi_subsys_restore_early); - if (dev_pm_smart_suspend_and_suspended(dev)) - return 0; +/** + * acpi_subsys_poweroff - Run the device driver's poweroff callback. + * @dev: Device to handle. + * + * Follow PCI and resume devices from runtime suspend before running their + * system poweroff callbacks, unless the driver can cope with runtime-suspended + * devices during system suspend and there are no ACPI-specific reasons for + * resuming them. + */ +int acpi_subsys_poweroff(struct device *dev) +{ + if (!dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND) || + acpi_dev_needs_resume(dev, ACPI_COMPANION(dev))) + pm_runtime_resume(dev); - return pm_generic_freeze_late(dev); + return pm_generic_poweroff(dev); } -EXPORT_SYMBOL_GPL(acpi_subsys_freeze_late); +EXPORT_SYMBOL_GPL(acpi_subsys_poweroff); /** - * acpi_subsys_freeze_noirq - Run the device driver's "noirq" freeze callback. + * acpi_subsys_poweroff_late - Run the device driver's poweroff callback. * @dev: Device to handle. + * + * Carry out the generic late poweroff procedure for @dev and use ACPI to put + * it into a low-power state during system transition into a sleep state. */ -int acpi_subsys_freeze_noirq(struct device *dev) +static int acpi_subsys_poweroff_late(struct device *dev) { + int ret; if (dev_pm_smart_suspend_and_suspended(dev)) return 0; - return pm_generic_freeze_noirq(dev); + ret = pm_generic_poweroff_late(dev); + if (ret) + return ret; + + return acpi_dev_suspend(dev, device_may_wakeup(dev)); } -EXPORT_SYMBOL_GPL(acpi_subsys_freeze_noirq); /** - * acpi_subsys_thaw_noirq - Run the device driver's "noirq" thaw callback. - * @dev: Device to handle. + * acpi_subsys_poweroff_noirq - Run the driver's "noirq" poweroff callback. + * @dev: Device to suspend. */ -int acpi_subsys_thaw_noirq(struct device *dev) +static int acpi_subsys_poweroff_noirq(struct device *dev) { - /* - * If the device is in runtime suspend, the "thaw" code may not work - * correctly with it, so skip the driver callback and make the PM core - * skip all of the subsequent "thaw" callbacks for the device. - */ - if (dev_pm_smart_suspend_and_suspended(dev)) { - dev_pm_skip_next_resume_phases(dev); + if (dev_pm_smart_suspend_and_suspended(dev)) return 0; - } - return pm_generic_thaw_noirq(dev); + return pm_generic_poweroff_noirq(dev); } -EXPORT_SYMBOL_GPL(acpi_subsys_thaw_noirq); #endif /* CONFIG_PM_SLEEP */ static struct dev_pm_domain acpi_general_pm_domain = { @@ -1186,14 +1247,10 @@ static struct dev_pm_domain acpi_general_pm_domain = { .resume_noirq = acpi_subsys_resume_noirq, .resume_early = acpi_subsys_resume_early, .freeze = acpi_subsys_freeze, - .freeze_late = acpi_subsys_freeze_late, - .freeze_noirq = acpi_subsys_freeze_noirq, - .thaw_noirq = acpi_subsys_thaw_noirq, - .poweroff = acpi_subsys_suspend, - .poweroff_late = acpi_subsys_suspend_late, - .poweroff_noirq = acpi_subsys_suspend_noirq, - .restore_noirq = acpi_subsys_resume_noirq, - .restore_early = acpi_subsys_resume_early, + .poweroff = acpi_subsys_poweroff, + .poweroff_late = acpi_subsys_poweroff_late, + .poweroff_noirq = acpi_subsys_poweroff_noirq, + .restore_early = acpi_subsys_restore_early, #endif }, }; diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h index f6157d4d637a..f4c2fe6be4f2 100644 --- a/drivers/acpi/internal.h +++ b/drivers/acpi/internal.h @@ -139,8 +139,15 @@ int acpi_power_get_inferred_state(struct acpi_device *device, int *state); int acpi_power_on_resources(struct acpi_device *device, int state); int acpi_power_transition(struct acpi_device *device, int state); +/* -------------------------------------------------------------------------- + Device Power Management + -------------------------------------------------------------------------- */ +int acpi_device_get_power(struct acpi_device *device, int *state); int acpi_wakeup_device_init(void); +/* -------------------------------------------------------------------------- + Processor + -------------------------------------------------------------------------- */ #ifdef CONFIG_ARCH_MIGHT_HAVE_ACPI_PDC void acpi_early_processor_set_pdc(void); #else diff --git a/drivers/acpi/power.c b/drivers/acpi/power.c index a916417b9e70..fe1e7bc91a5e 100644 --- a/drivers/acpi/power.c +++ b/drivers/acpi/power.c @@ -42,6 +42,11 @@ ACPI_MODULE_NAME("power"); #define ACPI_POWER_RESOURCE_STATE_ON 0x01 #define ACPI_POWER_RESOURCE_STATE_UNKNOWN 0xFF +struct acpi_power_dependent_device { + struct device *dev; + struct list_head node; +}; + struct acpi_power_resource { struct acpi_device device; struct list_head list_node; @@ -51,6 +56,7 @@ struct acpi_power_resource { unsigned int ref_count; bool wakeup_enabled; struct mutex resource_lock; + struct list_head dependents; }; struct acpi_power_resource_entry { @@ -232,8 +238,121 @@ static int acpi_power_get_list_state(struct list_head *list, int *state) return 0; } +static int +acpi_power_resource_add_dependent(struct acpi_power_resource *resource, + struct device *dev) +{ + struct acpi_power_dependent_device *dep; + int ret = 0; + + mutex_lock(&resource->resource_lock); + list_for_each_entry(dep, &resource->dependents, node) { + /* Only add it once */ + if (dep->dev == dev) + goto unlock; + } + + dep = kzalloc(sizeof(*dep), GFP_KERNEL); + if (!dep) { + ret = -ENOMEM; + goto unlock; + } + + dep->dev = dev; + list_add_tail(&dep->node, &resource->dependents); + dev_dbg(dev, "added power dependency to [%s]\n", resource->name); + +unlock: + mutex_unlock(&resource->resource_lock); + return ret; +} + +static void +acpi_power_resource_remove_dependent(struct acpi_power_resource *resource, + struct device *dev) +{ + struct acpi_power_dependent_device *dep; + + mutex_lock(&resource->resource_lock); + list_for_each_entry(dep, &resource->dependents, node) { + if (dep->dev == dev) { + list_del(&dep->node); + kfree(dep); + dev_dbg(dev, "removed power dependency to [%s]\n", + resource->name); + break; + } + } + mutex_unlock(&resource->resource_lock); +} + +/** + * acpi_device_power_add_dependent - Add dependent device of this ACPI device + * @adev: ACPI device pointer + * @dev: Dependent device + * + * If @adev has non-empty _PR0 the @dev is added as dependent device to all + * power resources returned by it. This means that whenever these power + * resources are turned _ON the dependent devices get runtime resumed. This + * is needed for devices such as PCI to allow its driver to re-initialize + * it after it went to D0uninitialized. + * + * If @adev does not have _PR0 this does nothing. + * + * Returns %0 in case of success and negative errno otherwise. + */ +int acpi_device_power_add_dependent(struct acpi_device *adev, + struct device *dev) +{ + struct acpi_power_resource_entry *entry; + struct list_head *resources; + int ret; + + if (!adev->flags.power_manageable) + return 0; + + resources = &adev->power.states[ACPI_STATE_D0].resources; + list_for_each_entry(entry, resources, node) { + ret = acpi_power_resource_add_dependent(entry->resource, dev); + if (ret) + goto err; + } + + return 0; + +err: + list_for_each_entry(entry, resources, node) + acpi_power_resource_remove_dependent(entry->resource, dev); + + return ret; +} + +/** + * acpi_device_power_remove_dependent - Remove dependent device + * @adev: ACPI device pointer + * @dev: Dependent device + * + * Does the opposite of acpi_device_power_add_dependent() and removes the + * dependent device if it is found. Can be called to @adev that does not + * have _PR0 as well. + */ +void acpi_device_power_remove_dependent(struct acpi_device *adev, + struct device *dev) +{ + struct acpi_power_resource_entry *entry; + struct list_head *resources; + + if (!adev->flags.power_manageable) + return; + + resources = &adev->power.states[ACPI_STATE_D0].resources; + list_for_each_entry_reverse(entry, resources, node) + acpi_power_resource_remove_dependent(entry->resource, dev); +} + static int __acpi_power_on(struct acpi_power_resource *resource) { + struct acpi_power_dependent_device *dep; acpi_status status = AE_OK; status = acpi_evaluate_object(resource->device.handle, "_ON", NULL, NULL); @@ -243,6 +362,21 @@ static int __acpi_power_on(struct acpi_power_resource *resource) ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Power resource [%s] turned on\n", resource->name)); + /* + * If there are other dependents on this power resource we need to + * resume them now so that their drivers can re-initialize the + * hardware properly after it went back to D0. + */ + if (list_empty(&resource->dependents) || + list_is_singular(&resource->dependents)) + return 0; + + list_for_each_entry(dep, &resource->dependents, node) { + dev_dbg(dep->dev, "runtime resuming because [%s] turned on\n", + resource->name); + pm_request_resume(dep->dev); + } + return 0; } @@ -810,6 +944,7 @@ int acpi_add_power_resource(acpi_handle handle) ACPI_STA_DEFAULT); mutex_init(&resource->resource_lock); INIT_LIST_HEAD(&resource->list_node); + INIT_LIST_HEAD(&resource->dependents); resource->name = device->pnp.bus_id; strcpy(acpi_device_name(device), ACPI_POWER_DEVICE_NAME); strcpy(acpi_device_class(device), ACPI_POWER_CLASS); diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c index 8ff08e531443..f0fe7c15d657 100644 --- a/drivers/acpi/sleep.c +++ b/drivers/acpi/sleep.c @@ -77,7 +77,7 @@ static int acpi_sleep_prepare(u32 acpi_state) return 0; } -static bool acpi_sleep_state_supported(u8 sleep_state) +bool acpi_sleep_state_supported(u8 sleep_state) { acpi_status status; u8 type_a, type_b; @@ -452,14 +452,6 @@ static int acpi_pm_prepare(void) return error; } -static int find_powerf_dev(struct device *dev, void *data) -{ - struct acpi_device *device = to_acpi_device(dev); - const char *hid = acpi_device_hid(device); - - return !strcmp(hid, ACPI_BUTTON_HID_POWERF); -} - /** * acpi_pm_finish - Instruct the platform to leave a sleep state. * @@ -468,7 +460,7 @@ static int find_powerf_dev(struct device *dev, void *data) */ static void acpi_pm_finish(void) { - struct device *pwr_btn_dev; + struct acpi_device *pwr_btn_adev; u32 acpi_state = acpi_target_sleep_state; acpi_ec_unblock_transactions(); @@ -499,11 +491,11 @@ static void acpi_pm_finish(void) return; pwr_btn_event_pending = false; - pwr_btn_dev = bus_find_device(&acpi_bus_type, NULL, NULL, - find_powerf_dev); - if (pwr_btn_dev) { - pm_wakeup_event(pwr_btn_dev, 0); - put_device(pwr_btn_dev); + pwr_btn_adev = acpi_dev_get_first_match_dev(ACPI_BUTTON_HID_POWERF, + NULL, -1); + if (pwr_btn_adev) { + pm_wakeup_event(&pwr_btn_adev->dev, 0); + acpi_dev_put(pwr_btn_adev); } } diff --git a/drivers/base/power/clock_ops.c b/drivers/base/power/clock_ops.c index 59d19dd64928..ced6863a16a5 100644 --- a/drivers/base/power/clock_ops.c +++ b/drivers/base/power/clock_ops.c @@ -12,6 +12,7 @@ #include <linux/pm_clock.h> #include <linux/clk.h> #include <linux/clkdev.h> +#include <linux/of_clk.h> #include <linux/slab.h> #include <linux/err.h> #include <linux/pm_domain.h> @@ -92,8 +93,6 @@ static int __pm_clk_add(struct device *dev, const char *con_id, if (con_id) { ce->con_id = kstrdup(con_id, GFP_KERNEL); if (!ce->con_id) { - dev_err(dev, - "Not enough memory for clock connection ID.\n"); kfree(ce); return -ENOMEM; } @@ -195,8 +194,7 @@ int of_pm_clk_add_clks(struct device *dev) if (!dev || !dev->of_node) return -EINVAL; - count = of_count_phandle_with_args(dev->of_node, "clocks", - "#clock-cells"); + count = of_clk_get_parent_count(dev->of_node); if (count <= 0) return -ENODEV; diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index dcfc0a36c8f7..7fb2c39bc725 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -530,21 +530,6 @@ static void dpm_watchdog_clear(struct dpm_watchdog *wd) /*------------------------- Resume routines -------------------------*/ /** - * dev_pm_skip_next_resume_phases - Skip next system resume phases for device. - * @dev: Target device. - * - * Make the core skip the "early resume" and "resume" phases for @dev. - * - * This function can be called by middle-layer code during the "noirq" phase of - * system resume if necessary, but not by device drivers. - */ -void dev_pm_skip_next_resume_phases(struct device *dev) -{ - dev->power.is_late_suspended = false; - dev->power.is_suspended = false; -} - -/** * suspend_event - Return a "suspend" message for given "resume" one. * @resume_msg: PM message representing a system-wide resume transition. */ @@ -681,6 +666,9 @@ Skip: dev->power.is_noirq_suspended = false; if (skip_resume) { + /* Make the next phases of resume skip the device. */ + dev->power.is_late_suspended = false; + dev->power.is_suspended = false; /* * The device is going to be left in suspend, but it might not * have been in runtime suspend before the system suspended, so @@ -689,7 +677,6 @@ Skip: * device again. */ pm_runtime_set_suspended(dev); - dev_pm_skip_next_resume_phases(dev); } Out: @@ -1631,17 +1618,20 @@ int dpm_suspend_late(pm_message_t state) */ int dpm_suspend_end(pm_message_t state) { - int error = dpm_suspend_late(state); + ktime_t starttime = ktime_get(); + int error; + + error = dpm_suspend_late(state); if (error) - return error; + goto out; error = dpm_suspend_noirq(state); - if (error) { + if (error) dpm_resume_early(resume_event(state)); - return error; - } - return 0; +out: + dpm_show_time(starttime, state, error, "end"); + return error; } EXPORT_SYMBOL_GPL(dpm_suspend_end); @@ -2034,6 +2024,7 @@ int dpm_prepare(pm_message_t state) */ int dpm_suspend_start(pm_message_t state) { + ktime_t starttime = ktime_get(); int error; error = dpm_prepare(state); @@ -2042,6 +2033,7 @@ int dpm_suspend_start(pm_message_t state) dpm_save_failed_step(SUSPEND_PREPARE); } else error = dpm_suspend(state); + dpm_show_time(starttime, state, error, "start"); return error; } EXPORT_SYMBOL_GPL(dpm_suspend_start); diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c index 5b2b6a05a4f3..ee31d4f8d856 100644 --- a/drivers/base/power/wakeup.c +++ b/drivers/base/power/wakeup.c @@ -968,8 +968,6 @@ void pm_wakep_autosleep_enabled(bool set) } #endif /* CONFIG_PM_AUTOSLEEP */ -static struct dentry *wakeup_sources_stats_dentry; - /** * print_wakeup_source_stats - Print wakeup source statistics information. * @m: seq_file to print the statistics into. @@ -1099,8 +1097,8 @@ static const struct file_operations wakeup_sources_stats_fops = { static int __init wakeup_sources_debugfs_init(void) { - wakeup_sources_stats_dentry = debugfs_create_file("wakeup_sources", - S_IRUGO, NULL, NULL, &wakeup_sources_stats_fops); + debugfs_create_file("wakeup_sources", S_IRUGO, NULL, NULL, + &wakeup_sources_stats_fops); return 0; } diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm index f8129edc145e..56c31a78c692 100644 --- a/drivers/cpufreq/Kconfig.arm +++ b/drivers/cpufreq/Kconfig.arm @@ -93,6 +93,15 @@ config ARM_IMX6Q_CPUFREQ If in doubt, say N. +config ARM_IMX_CPUFREQ_DT + tristate "Freescale i.MX8M cpufreq support" + depends on ARCH_MXC && CPUFREQ_DT + help + This adds cpufreq driver support for Freescale i.MX8M series SoCs, + based on cpufreq-dt. + + If in doubt, say N. + config ARM_KIRKWOOD_CPUFREQ def_bool MACH_KIRKWOOD help @@ -133,6 +142,14 @@ config ARM_QCOM_CPUFREQ_HW The driver implements the cpufreq interface for this HW engine. Say Y if you want to support CPUFreq HW. +config ARM_RASPBERRYPI_CPUFREQ + tristate "Raspberry Pi cpufreq support" + depends on CLK_RASPBERRYPI || COMPILE_TEST + help + This adds the CPUFreq driver for Raspberry Pi + + If in doubt, say N. + config ARM_S3C_CPUFREQ bool help diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile index 689b26c6f949..5a6c70d26c98 100644 --- a/drivers/cpufreq/Makefile +++ b/drivers/cpufreq/Makefile @@ -56,6 +56,7 @@ obj-$(CONFIG_ACPI_CPPC_CPUFREQ) += cppc_cpufreq.o obj-$(CONFIG_ARCH_DAVINCI) += davinci-cpufreq.o obj-$(CONFIG_ARM_HIGHBANK_CPUFREQ) += highbank-cpufreq.o obj-$(CONFIG_ARM_IMX6Q_CPUFREQ) += imx6q-cpufreq.o +obj-$(CONFIG_ARM_IMX_CPUFREQ_DT) += imx-cpufreq-dt.o obj-$(CONFIG_ARM_KIRKWOOD_CPUFREQ) += kirkwood-cpufreq.o obj-$(CONFIG_ARM_MEDIATEK_CPUFREQ) += mediatek-cpufreq.o obj-$(CONFIG_MACH_MVEBU_V7) += mvebu-cpufreq.o @@ -64,6 +65,7 @@ obj-$(CONFIG_ARM_PXA2xx_CPUFREQ) += pxa2xx-cpufreq.o obj-$(CONFIG_PXA3xx) += pxa3xx-cpufreq.o obj-$(CONFIG_ARM_QCOM_CPUFREQ_HW) += qcom-cpufreq-hw.o obj-$(CONFIG_ARM_QCOM_CPUFREQ_KRYO) += qcom-cpufreq-kryo.o +obj-$(CONFIG_ARM_RASPBERRYPI_CPUFREQ) += raspberrypi-cpufreq.o obj-$(CONFIG_ARM_S3C2410_CPUFREQ) += s3c2410-cpufreq.o obj-$(CONFIG_ARM_S3C2412_CPUFREQ) += s3c2412-cpufreq.o obj-$(CONFIG_ARM_S3C2416_CPUFREQ) += s3c2416-cpufreq.o diff --git a/drivers/cpufreq/armada-37xx-cpufreq.c b/drivers/cpufreq/armada-37xx-cpufreq.c index 0df16eb1eb3c..aa0f06dec959 100644 --- a/drivers/cpufreq/armada-37xx-cpufreq.c +++ b/drivers/cpufreq/armada-37xx-cpufreq.c @@ -257,7 +257,7 @@ static void __init armada37xx_cpufreq_avs_configure(struct regmap *base, static void __init armada37xx_cpufreq_avs_setup(struct regmap *base, struct armada_37xx_dvfs *dvfs) { - unsigned int avs_val = 0, freq; + unsigned int avs_val = 0; int load_level = 0; if (base == NULL) @@ -275,8 +275,6 @@ static void __init armada37xx_cpufreq_avs_setup(struct regmap *base, for (load_level = 1; load_level < LOAD_LEVEL_NR; load_level++) { - freq = dvfs->cpu_freq_max / dvfs->divider[load_level]; - avs_val = dvfs->avs[load_level]; regmap_update_bits(base, ARMADA_37XX_AVS_VSET(load_level-1), ARMADA_37XX_AVS_VDD_MASK << ARMADA_37XX_AVS_HIGH_VDD_LIMIT | diff --git a/drivers/cpufreq/brcmstb-avs-cpufreq.c b/drivers/cpufreq/brcmstb-avs-cpufreq.c index e6f9cbe5835f..77b0e5d0fb13 100644 --- a/drivers/cpufreq/brcmstb-avs-cpufreq.c +++ b/drivers/cpufreq/brcmstb-avs-cpufreq.c @@ -384,12 +384,12 @@ static int brcm_avs_set_pstate(struct private_data *priv, unsigned int pstate) return __issue_avs_command(priv, AVS_CMD_SET_PSTATE, true, args); } -static unsigned long brcm_avs_get_voltage(void __iomem *base) +static u32 brcm_avs_get_voltage(void __iomem *base) { return readl(base + AVS_MBOX_VOLTAGE1); } -static unsigned long brcm_avs_get_frequency(void __iomem *base) +static u32 brcm_avs_get_frequency(void __iomem *base) { return readl(base + AVS_MBOX_FREQUENCY) * 1000; /* in kHz */ } @@ -446,8 +446,8 @@ static bool brcm_avs_is_firmware_loaded(struct private_data *priv) rc = brcm_avs_get_pmap(priv, NULL); magic = readl(priv->base + AVS_MBOX_MAGIC); - return (magic == AVS_FIRMWARE_MAGIC) && (rc != -ENOTSUPP) && - (rc != -EINVAL); + return (magic == AVS_FIRMWARE_MAGIC) && ((rc != -ENOTSUPP) || + (rc != -EINVAL)); } static unsigned int brcm_avs_cpufreq_get(unsigned int cpu) @@ -653,14 +653,14 @@ static ssize_t show_brcm_avs_voltage(struct cpufreq_policy *policy, char *buf) { struct private_data *priv = policy->driver_data; - return sprintf(buf, "0x%08lx\n", brcm_avs_get_voltage(priv->base)); + return sprintf(buf, "0x%08x\n", brcm_avs_get_voltage(priv->base)); } static ssize_t show_brcm_avs_frequency(struct cpufreq_policy *policy, char *buf) { struct private_data *priv = policy->driver_data; - return sprintf(buf, "0x%08lx\n", brcm_avs_get_frequency(priv->base)); + return sprintf(buf, "0x%08x\n", brcm_avs_get_frequency(priv->base)); } cpufreq_freq_attr_ro(brcm_avs_pstate); diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c index 88e00683eaeb..03dc4244ab00 100644 --- a/drivers/cpufreq/cpufreq-dt-platdev.c +++ b/drivers/cpufreq/cpufreq-dt-platdev.c @@ -37,7 +37,6 @@ static const struct of_device_id whitelist[] __initconst = { { .compatible = "fsl,imx27", }, { .compatible = "fsl,imx51", }, { .compatible = "fsl,imx53", }, - { .compatible = "fsl,imx7d", }, { .compatible = "marvell,berlin", }, { .compatible = "marvell,pxa250", }, @@ -105,6 +104,10 @@ static const struct of_device_id blacklist[] __initconst = { { .compatible = "calxeda,highbank", }, { .compatible = "calxeda,ecx-2000", }, + { .compatible = "fsl,imx7d", }, + { .compatible = "fsl,imx8mq", }, + { .compatible = "fsl,imx8mm", }, + { .compatible = "marvell,armadaxp", }, { .compatible = "mediatek,mt2701", }, diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index e84bf0eb7239..0a9f675f2af4 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -356,12 +356,10 @@ static void cpufreq_notify_transition(struct cpufreq_policy *policy, * which is not equal to what the cpufreq core thinks is * "old frequency". */ - if (!(cpufreq_driver->flags & CPUFREQ_CONST_LOOPS)) { - if (policy->cur && (policy->cur != freqs->old)) { - pr_debug("Warning: CPU frequency is %u, cpufreq assumed %u kHz\n", - freqs->old, policy->cur); - freqs->old = policy->cur; - } + if (policy->cur && policy->cur != freqs->old) { + pr_debug("Warning: CPU frequency is %u, cpufreq assumed %u kHz\n", + freqs->old, policy->cur); + freqs->old = policy->cur; } srcu_notifier_call_chain(&cpufreq_transition_notifier_list, @@ -631,7 +629,7 @@ static int cpufreq_parse_policy(char *str_governor, } /** - * cpufreq_parse_governor - parse a governor string only for !setpolicy + * cpufreq_parse_governor - parse a governor string only for has_target() */ static int cpufreq_parse_governor(char *str_governor, struct cpufreq_policy *policy) @@ -1114,13 +1112,25 @@ static int cpufreq_add_policy_cpu(struct cpufreq_policy *policy, unsigned int cp return ret; } +static void refresh_frequency_limits(struct cpufreq_policy *policy) +{ + struct cpufreq_policy new_policy = *policy; + + pr_debug("updating policy for CPU %u\n", policy->cpu); + + new_policy.min = policy->user_policy.min; + new_policy.max = policy->user_policy.max; + + cpufreq_set_policy(policy, &new_policy); +} + static void handle_update(struct work_struct *work) { struct cpufreq_policy *policy = container_of(work, struct cpufreq_policy, update); - unsigned int cpu = policy->cpu; - pr_debug("handle_update for cpu %u called\n", cpu); - cpufreq_update_policy(cpu); + + pr_debug("handle_update for cpu %u called\n", policy->cpu); + refresh_frequency_limits(policy); } static struct cpufreq_policy *cpufreq_policy_alloc(unsigned int cpu) @@ -1300,7 +1310,7 @@ static int cpufreq_online(unsigned int cpu) policy->max = policy->user_policy.max; } - if (cpufreq_driver->get && !cpufreq_driver->setpolicy) { + if (cpufreq_driver->get && has_target()) { policy->cur = cpufreq_driver->get(policy->cpu); if (!policy->cur) { pr_err("%s: ->get() failed\n", __func__); @@ -1375,8 +1385,7 @@ static int cpufreq_online(unsigned int cpu) if (cpufreq_driver->ready) cpufreq_driver->ready(policy); - if (IS_ENABLED(CONFIG_CPU_THERMAL) && - cpufreq_driver->flags & CPUFREQ_IS_COOLING_DEV) + if (cpufreq_thermal_control_enabled(cpufreq_driver)) policy->cdev = of_cpufreq_cooling_register(policy); pr_debug("initialization complete\n"); @@ -1466,8 +1475,7 @@ static int cpufreq_offline(unsigned int cpu) goto unlock; } - if (IS_ENABLED(CONFIG_CPU_THERMAL) && - cpufreq_driver->flags & CPUFREQ_IS_COOLING_DEV) { + if (cpufreq_thermal_control_enabled(cpufreq_driver)) { cpufreq_cooling_unregister(policy->cdev); policy->cdev = NULL; } @@ -1546,6 +1554,30 @@ static void cpufreq_out_of_sync(struct cpufreq_policy *policy, cpufreq_freq_transition_end(policy, &freqs, 0); } +static unsigned int cpufreq_verify_current_freq(struct cpufreq_policy *policy, bool update) +{ + unsigned int new_freq; + + new_freq = cpufreq_driver->get(policy->cpu); + if (!new_freq) + return 0; + + /* + * If fast frequency switching is used with the given policy, the check + * against policy->cur is pointless, so skip it in that case. + */ + if (policy->fast_switch_enabled || !has_target()) + return new_freq; + + if (policy->cur != new_freq) { + cpufreq_out_of_sync(policy, new_freq); + if (update) + schedule_work(&policy->update); + } + + return new_freq; +} + /** * cpufreq_quick_get - get the CPU frequency (in kHz) from policy->cur * @cpu: CPU number @@ -1601,31 +1633,10 @@ EXPORT_SYMBOL(cpufreq_quick_get_max); static unsigned int __cpufreq_get(struct cpufreq_policy *policy) { - unsigned int ret_freq = 0; - if (unlikely(policy_is_inactive(policy))) - return ret_freq; - - ret_freq = cpufreq_driver->get(policy->cpu); - - /* - * If fast frequency switching is used with the given policy, the check - * against policy->cur is pointless, so skip it in that case too. - */ - if (policy->fast_switch_enabled) - return ret_freq; - - if (ret_freq && policy->cur && - !(cpufreq_driver->flags & CPUFREQ_CONST_LOOPS)) { - /* verify no discrepancy between actual and - saved value exists */ - if (unlikely(ret_freq != policy->cur)) { - cpufreq_out_of_sync(policy, ret_freq); - schedule_work(&policy->update); - } - } + return 0; - return ret_freq; + return cpufreq_verify_current_freq(policy, true); } /** @@ -1652,24 +1663,6 @@ unsigned int cpufreq_get(unsigned int cpu) } EXPORT_SYMBOL(cpufreq_get); -static unsigned int cpufreq_update_current_freq(struct cpufreq_policy *policy) -{ - unsigned int new_freq; - - new_freq = cpufreq_driver->get(policy->cpu); - if (!new_freq) - return 0; - - if (!policy->cur) { - pr_debug("cpufreq: Driver did not initialize current freq\n"); - policy->cur = new_freq; - } else if (policy->cur != new_freq && has_target()) { - cpufreq_out_of_sync(policy, new_freq); - } - - return new_freq; -} - static struct subsys_interface cpufreq_interface = { .name = "cpufreq", .subsys = &cpu_subsys, @@ -2150,8 +2143,8 @@ static int cpufreq_start_governor(struct cpufreq_policy *policy) pr_debug("%s: for CPU %u\n", __func__, policy->cpu); - if (cpufreq_driver->get && !cpufreq_driver->setpolicy) - cpufreq_update_current_freq(policy); + if (cpufreq_driver->get) + cpufreq_verify_current_freq(policy, false); if (policy->governor->start) { ret = policy->governor->start(policy); @@ -2392,7 +2385,6 @@ int cpufreq_set_policy(struct cpufreq_policy *policy, void cpufreq_update_policy(unsigned int cpu) { struct cpufreq_policy *policy = cpufreq_cpu_acquire(cpu); - struct cpufreq_policy new_policy; if (!policy) return; @@ -2401,16 +2393,11 @@ void cpufreq_update_policy(unsigned int cpu) * BIOS might change freq behind our back * -> ask driver for current freq and notify governors about a change */ - if (cpufreq_driver->get && !cpufreq_driver->setpolicy && - (cpufreq_suspended || WARN_ON(!cpufreq_update_current_freq(policy)))) + if (cpufreq_driver->get && has_target() && + (cpufreq_suspended || WARN_ON(!cpufreq_verify_current_freq(policy, false)))) goto unlock; - pr_debug("updating policy for CPU %u\n", cpu); - memcpy(&new_policy, policy, sizeof(*policy)); - new_policy.min = policy->user_policy.min; - new_policy.max = policy->user_policy.max; - - cpufreq_set_policy(policy, &new_policy); + refresh_frequency_limits(policy); unlock: cpufreq_cpu_release(policy); diff --git a/drivers/cpufreq/imx-cpufreq-dt.c b/drivers/cpufreq/imx-cpufreq-dt.c new file mode 100644 index 000000000000..b54fd26ea7df --- /dev/null +++ b/drivers/cpufreq/imx-cpufreq-dt.c @@ -0,0 +1,97 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright 2019 NXP + */ + +#include <linux/cpu.h> +#include <linux/err.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/nvmem-consumer.h> +#include <linux/of.h> +#include <linux/platform_device.h> +#include <linux/pm_opp.h> +#include <linux/slab.h> + +#define OCOTP_CFG3_SPEED_GRADE_SHIFT 8 +#define OCOTP_CFG3_SPEED_GRADE_MASK (0x3 << 8) +#define OCOTP_CFG3_MKT_SEGMENT_SHIFT 6 +#define OCOTP_CFG3_MKT_SEGMENT_MASK (0x3 << 6) + +/* cpufreq-dt device registered by imx-cpufreq-dt */ +static struct platform_device *cpufreq_dt_pdev; +static struct opp_table *cpufreq_opp_table; + +static int imx_cpufreq_dt_probe(struct platform_device *pdev) +{ + struct device *cpu_dev = get_cpu_device(0); + u32 cell_value, supported_hw[2]; + int speed_grade, mkt_segment; + int ret; + + ret = nvmem_cell_read_u32(cpu_dev, "speed_grade", &cell_value); + if (ret) + return ret; + + speed_grade = (cell_value & OCOTP_CFG3_SPEED_GRADE_MASK) >> OCOTP_CFG3_SPEED_GRADE_SHIFT; + mkt_segment = (cell_value & OCOTP_CFG3_MKT_SEGMENT_MASK) >> OCOTP_CFG3_MKT_SEGMENT_SHIFT; + + /* + * Early samples without fuses written report "0 0" which means + * consumer segment and minimum speed grading. + * + * According to datasheet minimum speed grading is not supported for + * consumer parts so clamp to 1 to avoid warning for "no OPPs" + * + * Applies to 8mq and 8mm. + */ + if (mkt_segment == 0 && speed_grade == 0 && ( + of_machine_is_compatible("fsl,imx8mm") || + of_machine_is_compatible("fsl,imx8mq"))) + speed_grade = 1; + + supported_hw[0] = BIT(speed_grade); + supported_hw[1] = BIT(mkt_segment); + dev_info(&pdev->dev, "cpu speed grade %d mkt segment %d supported-hw %#x %#x\n", + speed_grade, mkt_segment, supported_hw[0], supported_hw[1]); + + cpufreq_opp_table = dev_pm_opp_set_supported_hw(cpu_dev, supported_hw, 2); + if (IS_ERR(cpufreq_opp_table)) { + ret = PTR_ERR(cpufreq_opp_table); + dev_err(&pdev->dev, "Failed to set supported opp: %d\n", ret); + return ret; + } + + cpufreq_dt_pdev = platform_device_register_data( + &pdev->dev, "cpufreq-dt", -1, NULL, 0); + if (IS_ERR(cpufreq_dt_pdev)) { + dev_pm_opp_put_supported_hw(cpufreq_opp_table); + ret = PTR_ERR(cpufreq_dt_pdev); + dev_err(&pdev->dev, "Failed to register cpufreq-dt: %d\n", ret); + return ret; + } + + return 0; +} + +static int imx_cpufreq_dt_remove(struct platform_device *pdev) +{ + platform_device_unregister(cpufreq_dt_pdev); + dev_pm_opp_put_supported_hw(cpufreq_opp_table); + + return 0; +} + +static struct platform_driver imx_cpufreq_dt_driver = { + .probe = imx_cpufreq_dt_probe, + .remove = imx_cpufreq_dt_remove, + .driver = { + .name = "imx-cpufreq-dt", + }, +}; +module_platform_driver(imx_cpufreq_dt_driver); + +MODULE_ALIAS("platform:imx-cpufreq-dt"); +MODULE_DESCRIPTION("Freescale i.MX cpufreq speed grading driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/cpufreq/pcc-cpufreq.c b/drivers/cpufreq/pcc-cpufreq.c index 1e5e64643c3a..fdc767fdbe6a 100644 --- a/drivers/cpufreq/pcc-cpufreq.c +++ b/drivers/cpufreq/pcc-cpufreq.c @@ -582,10 +582,10 @@ static int __init pcc_cpufreq_init(void) /* Skip initialization if another cpufreq driver is there. */ if (cpufreq_get_current_driver()) - return 0; + return -EEXIST; if (acpi_disabled) - return 0; + return -ENODEV; ret = pcc_cpufreq_probe(); if (ret) { diff --git a/drivers/cpufreq/raspberrypi-cpufreq.c b/drivers/cpufreq/raspberrypi-cpufreq.c new file mode 100644 index 000000000000..2bc7d9734272 --- /dev/null +++ b/drivers/cpufreq/raspberrypi-cpufreq.c @@ -0,0 +1,97 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Raspberry Pi cpufreq driver + * + * Copyright (C) 2019, Nicolas Saenz Julienne <nsaenzjulienne@suse.de> + */ + +#include <linux/clk.h> +#include <linux/cpu.h> +#include <linux/cpufreq.h> +#include <linux/module.h> +#include <linux/platform_device.h> +#include <linux/pm_opp.h> + +#define RASPBERRYPI_FREQ_INTERVAL 100000000 + +static struct platform_device *cpufreq_dt; + +static int raspberrypi_cpufreq_probe(struct platform_device *pdev) +{ + struct device *cpu_dev; + unsigned long min, max; + unsigned long rate; + struct clk *clk; + int ret; + + cpu_dev = get_cpu_device(0); + if (!cpu_dev) { + pr_err("Cannot get CPU for cpufreq driver\n"); + return -ENODEV; + } + + clk = clk_get(cpu_dev, NULL); + if (IS_ERR(clk)) { + dev_err(cpu_dev, "Cannot get clock for CPU0\n"); + return PTR_ERR(clk); + } + + /* + * The max and min frequencies are configurable in the Raspberry Pi + * firmware, so we query them at runtime. + */ + min = roundup(clk_round_rate(clk, 0), RASPBERRYPI_FREQ_INTERVAL); + max = roundup(clk_round_rate(clk, ULONG_MAX), RASPBERRYPI_FREQ_INTERVAL); + clk_put(clk); + + for (rate = min; rate <= max; rate += RASPBERRYPI_FREQ_INTERVAL) { + ret = dev_pm_opp_add(cpu_dev, rate, 0); + if (ret) + goto remove_opp; + } + + cpufreq_dt = platform_device_register_simple("cpufreq-dt", -1, NULL, 0); + ret = PTR_ERR_OR_ZERO(cpufreq_dt); + if (ret) { + dev_err(cpu_dev, "Failed to create platform device, %d\n", ret); + goto remove_opp; + } + + return 0; + +remove_opp: + dev_pm_opp_remove_all_dynamic(cpu_dev); + + return ret; +} + +static int raspberrypi_cpufreq_remove(struct platform_device *pdev) +{ + struct device *cpu_dev; + + cpu_dev = get_cpu_device(0); + if (cpu_dev) + dev_pm_opp_remove_all_dynamic(cpu_dev); + + platform_device_unregister(cpufreq_dt); + + return 0; +} + +/* + * Since the driver depends on clk-raspberrypi, which may return EPROBE_DEFER, + * all the activity is performed in the probe, which may be defered as well. + */ +static struct platform_driver raspberrypi_cpufreq_driver = { + .driver = { + .name = "raspberrypi-cpufreq", + }, + .probe = raspberrypi_cpufreq_probe, + .remove = raspberrypi_cpufreq_remove, +}; +module_platform_driver(raspberrypi_cpufreq_driver); + +MODULE_AUTHOR("Nicolas Saenz Julienne <nsaenzjulienne@suse.de"); +MODULE_DESCRIPTION("Raspberry Pi cpufreq driver"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("platform:raspberrypi-cpufreq"); diff --git a/drivers/cpufreq/s5pv210-cpufreq.c b/drivers/cpufreq/s5pv210-cpufreq.c index 57e5374592bd..e5cb17d4be7b 100644 --- a/drivers/cpufreq/s5pv210-cpufreq.c +++ b/drivers/cpufreq/s5pv210-cpufreq.c @@ -478,7 +478,7 @@ static int s5pv210_target(struct cpufreq_policy *policy, unsigned int index) arm_volt, arm_volt_max); } - printk(KERN_DEBUG "Perf changed[L%d]\n", index); + pr_debug("Perf changed[L%d]\n", index); exit: mutex_unlock(&set_freq_lock); diff --git a/drivers/input/serio/i8042.c b/drivers/input/serio/i8042.c index e4352741c467..b695094290ab 100644 --- a/drivers/input/serio/i8042.c +++ b/drivers/input/serio/i8042.c @@ -1406,7 +1406,7 @@ static void __init i8042_register_ports(void) * behavior on many platforms using suspend-to-RAM (ACPI S3) * by default. */ - if (pm_suspend_via_s2idle() && i == I8042_KBD_PORT_NO) + if (pm_suspend_default_s2idle() && i == I8042_KBD_PORT_NO) device_set_wakeup_enable(&serio->dev, true); } } diff --git a/drivers/opp/core.c b/drivers/opp/core.c index 3a9789388bfb..c094d5d20fd7 100644 --- a/drivers/opp/core.c +++ b/drivers/opp/core.c @@ -682,7 +682,7 @@ static int _set_opp_custom(const struct opp_table *opp_table, data->old_opp.rate = old_freq; size = sizeof(*old_supply) * opp_table->regulator_count; - if (IS_ERR(old_supply)) + if (!old_supply) memset(data->old_opp.supplies, 0, size); else memcpy(data->old_opp.supplies, old_supply, size); @@ -708,7 +708,7 @@ static int _set_required_opps(struct device *dev, /* Single genpd case */ if (!genpd_virt_devs) { - pstate = opp->required_opps[0]->pstate; + pstate = likely(opp) ? opp->required_opps[0]->pstate : 0; ret = dev_pm_genpd_set_performance_state(dev, pstate); if (ret) { dev_err(dev, "Failed to set performance state of %s: %d (%d)\n", @@ -726,7 +726,7 @@ static int _set_required_opps(struct device *dev, mutex_lock(&opp_table->genpd_virt_dev_lock); for (i = 0; i < opp_table->required_opp_count; i++) { - pstate = opp->required_opps[i]->pstate; + pstate = likely(opp) ? opp->required_opps[i]->pstate : 0; if (!genpd_virt_devs[i]) continue; @@ -748,29 +748,37 @@ static int _set_required_opps(struct device *dev, * @dev: device for which we do this operation * @target_freq: frequency to achieve * - * This configures the power-supplies and clock source to the levels specified - * by the OPP corresponding to the target_freq. + * This configures the power-supplies to the levels specified by the OPP + * corresponding to the target_freq, and programs the clock to a value <= + * target_freq, as rounded by clk_round_rate(). Device wanting to run at fmax + * provided by the opp, should have already rounded to the target OPP's + * frequency. */ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq) { struct opp_table *opp_table; - unsigned long freq, old_freq; + unsigned long freq, old_freq, temp_freq; struct dev_pm_opp *old_opp, *opp; struct clk *clk; int ret; - if (unlikely(!target_freq)) { - dev_err(dev, "%s: Invalid target frequency %lu\n", __func__, - target_freq); - return -EINVAL; - } - opp_table = _find_opp_table(dev); if (IS_ERR(opp_table)) { dev_err(dev, "%s: device opp doesn't exist\n", __func__); return PTR_ERR(opp_table); } + if (unlikely(!target_freq)) { + if (opp_table->required_opp_tables) { + ret = _set_required_opps(dev, opp_table, NULL); + } else { + dev_err(dev, "target frequency can't be 0\n"); + ret = -EINVAL; + } + + goto put_opp_table; + } + clk = opp_table->clk; if (IS_ERR(clk)) { dev_err(dev, "%s: No clock available for the device\n", @@ -793,13 +801,15 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq) goto put_opp_table; } - old_opp = _find_freq_ceil(opp_table, &old_freq); + temp_freq = old_freq; + old_opp = _find_freq_ceil(opp_table, &temp_freq); if (IS_ERR(old_opp)) { dev_err(dev, "%s: failed to find current OPP for freq %lu (%ld)\n", __func__, old_freq, PTR_ERR(old_opp)); } - opp = _find_freq_ceil(opp_table, &freq); + temp_freq = freq; + opp = _find_freq_ceil(opp_table, &temp_freq); if (IS_ERR(opp)) { ret = PTR_ERR(opp); dev_err(dev, "%s: failed to find OPP for freq %lu (%d)\n", @@ -1741,91 +1751,137 @@ void dev_pm_opp_unregister_set_opp_helper(struct opp_table *opp_table) } EXPORT_SYMBOL_GPL(dev_pm_opp_unregister_set_opp_helper); +static void _opp_detach_genpd(struct opp_table *opp_table) +{ + int index; + + for (index = 0; index < opp_table->required_opp_count; index++) { + if (!opp_table->genpd_virt_devs[index]) + continue; + + dev_pm_domain_detach(opp_table->genpd_virt_devs[index], false); + opp_table->genpd_virt_devs[index] = NULL; + } + + kfree(opp_table->genpd_virt_devs); + opp_table->genpd_virt_devs = NULL; +} + /** - * dev_pm_opp_set_genpd_virt_dev - Set virtual genpd device for an index - * @dev: Consumer device for which the genpd device is getting set. - * @virt_dev: virtual genpd device. - * @index: index. + * dev_pm_opp_attach_genpd - Attach genpd(s) for the device and save virtual device pointer + * @dev: Consumer device for which the genpd is getting attached. + * @names: Null terminated array of pointers containing names of genpd to attach. * * Multiple generic power domains for a device are supported with the help of * virtual genpd devices, which are created for each consumer device - genpd * pair. These are the device structures which are attached to the power domain * and are required by the OPP core to set the performance state of the genpd. + * The same API also works for the case where single genpd is available and so + * we don't need to support that separately. * * This helper will normally be called by the consumer driver of the device - * "dev", as only that has details of the genpd devices. + * "dev", as only that has details of the genpd names. * - * This helper needs to be called once for each of those virtual devices, but - * only if multiple domains are available for a device. Otherwise the original - * device structure will be used instead by the OPP core. + * This helper needs to be called once with a list of all genpd to attach. + * Otherwise the original device structure will be used instead by the OPP core. */ -struct opp_table *dev_pm_opp_set_genpd_virt_dev(struct device *dev, - struct device *virt_dev, - int index) +struct opp_table *dev_pm_opp_attach_genpd(struct device *dev, const char **names) { struct opp_table *opp_table; + struct device *virt_dev; + int index, ret = -EINVAL; + const char **name = names; opp_table = dev_pm_opp_get_opp_table(dev); if (!opp_table) return ERR_PTR(-ENOMEM); + /* + * If the genpd's OPP table isn't already initialized, parsing of the + * required-opps fail for dev. We should retry this after genpd's OPP + * table is added. + */ + if (!opp_table->required_opp_count) { + ret = -EPROBE_DEFER; + goto put_table; + } + mutex_lock(&opp_table->genpd_virt_dev_lock); - if (unlikely(!opp_table->genpd_virt_devs || - index >= opp_table->required_opp_count || - opp_table->genpd_virt_devs[index])) { + opp_table->genpd_virt_devs = kcalloc(opp_table->required_opp_count, + sizeof(*opp_table->genpd_virt_devs), + GFP_KERNEL); + if (!opp_table->genpd_virt_devs) + goto unlock; - dev_err(dev, "Invalid request to set required device\n"); - dev_pm_opp_put_opp_table(opp_table); - mutex_unlock(&opp_table->genpd_virt_dev_lock); + while (*name) { + index = of_property_match_string(dev->of_node, + "power-domain-names", *name); + if (index < 0) { + dev_err(dev, "Failed to find power domain: %s (%d)\n", + *name, index); + goto err; + } - return ERR_PTR(-EINVAL); + if (index >= opp_table->required_opp_count) { + dev_err(dev, "Index can't be greater than required-opp-count - 1, %s (%d : %d)\n", + *name, opp_table->required_opp_count, index); + goto err; + } + + if (opp_table->genpd_virt_devs[index]) { + dev_err(dev, "Genpd virtual device already set %s\n", + *name); + goto err; + } + + virt_dev = dev_pm_domain_attach_by_name(dev, *name); + if (IS_ERR(virt_dev)) { + ret = PTR_ERR(virt_dev); + dev_err(dev, "Couldn't attach to pm_domain: %d\n", ret); + goto err; + } + + opp_table->genpd_virt_devs[index] = virt_dev; + name++; } - opp_table->genpd_virt_devs[index] = virt_dev; mutex_unlock(&opp_table->genpd_virt_dev_lock); return opp_table; + +err: + _opp_detach_genpd(opp_table); +unlock: + mutex_unlock(&opp_table->genpd_virt_dev_lock); + +put_table: + dev_pm_opp_put_opp_table(opp_table); + + return ERR_PTR(ret); } +EXPORT_SYMBOL_GPL(dev_pm_opp_attach_genpd); /** - * dev_pm_opp_put_genpd_virt_dev() - Releases resources blocked for genpd device. - * @opp_table: OPP table returned by dev_pm_opp_set_genpd_virt_dev(). - * @virt_dev: virtual genpd device. + * dev_pm_opp_detach_genpd() - Detach genpd(s) from the device. + * @opp_table: OPP table returned by dev_pm_opp_attach_genpd(). * - * This releases the resource previously acquired with a call to - * dev_pm_opp_set_genpd_virt_dev(). The consumer driver shall call this helper - * if it doesn't want OPP core to update performance state of a power domain - * anymore. + * This detaches the genpd(s), resets the virtual device pointers, and puts the + * OPP table. */ -void dev_pm_opp_put_genpd_virt_dev(struct opp_table *opp_table, - struct device *virt_dev) +void dev_pm_opp_detach_genpd(struct opp_table *opp_table) { - int i; - /* * Acquire genpd_virt_dev_lock to make sure virt_dev isn't getting * used in parallel. */ mutex_lock(&opp_table->genpd_virt_dev_lock); - - for (i = 0; i < opp_table->required_opp_count; i++) { - if (opp_table->genpd_virt_devs[i] != virt_dev) - continue; - - opp_table->genpd_virt_devs[i] = NULL; - dev_pm_opp_put_opp_table(opp_table); - - /* Drop the vote */ - dev_pm_genpd_set_performance_state(virt_dev, 0); - break; - } - + _opp_detach_genpd(opp_table); mutex_unlock(&opp_table->genpd_virt_dev_lock); - if (unlikely(i == opp_table->required_opp_count)) - dev_err(virt_dev, "Failed to find required device entry\n"); + dev_pm_opp_put_opp_table(opp_table); } +EXPORT_SYMBOL_GPL(dev_pm_opp_detach_genpd); /** * dev_pm_opp_xlate_performance_state() - Find required OPP's pstate for src_table. diff --git a/drivers/opp/of.c b/drivers/opp/of.c index b7d81c408242..b313aca9894f 100644 --- a/drivers/opp/of.c +++ b/drivers/opp/of.c @@ -138,7 +138,6 @@ err: static void _opp_table_free_required_tables(struct opp_table *opp_table) { struct opp_table **required_opp_tables = opp_table->required_opp_tables; - struct device **genpd_virt_devs = opp_table->genpd_virt_devs; int i; if (!required_opp_tables) @@ -152,10 +151,8 @@ static void _opp_table_free_required_tables(struct opp_table *opp_table) } kfree(required_opp_tables); - kfree(genpd_virt_devs); opp_table->required_opp_count = 0; - opp_table->genpd_virt_devs = NULL; opp_table->required_opp_tables = NULL; } @@ -168,9 +165,8 @@ static void _opp_table_alloc_required_tables(struct opp_table *opp_table, struct device_node *opp_np) { struct opp_table **required_opp_tables; - struct device **genpd_virt_devs = NULL; struct device_node *required_np, *np; - int count, count_pd, i; + int count, i; /* Traversing the first OPP node is all we need */ np = of_get_next_available_child(opp_np, NULL); @@ -183,33 +179,11 @@ static void _opp_table_alloc_required_tables(struct opp_table *opp_table, if (!count) goto put_np; - /* - * Check the number of power-domains to know if we need to deal - * with virtual devices. In some cases we have devices with multiple - * power domains but with only one of them being scalable, hence - * 'count' could be 1, but we still have to deal with multiple genpds - * and virtual devices. - */ - count_pd = of_count_phandle_with_args(dev->of_node, "power-domains", - "#power-domain-cells"); - if (!count_pd) - goto put_np; - - if (count_pd > 1) { - genpd_virt_devs = kcalloc(count, sizeof(*genpd_virt_devs), - GFP_KERNEL); - if (!genpd_virt_devs) - goto put_np; - } - required_opp_tables = kcalloc(count, sizeof(*required_opp_tables), GFP_KERNEL); - if (!required_opp_tables) { - kfree(genpd_virt_devs); + if (!required_opp_tables) goto put_np; - } - opp_table->genpd_virt_devs = genpd_virt_devs; opp_table->required_opp_tables = required_opp_tables; opp_table->required_opp_count = count; diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c index 1897847ceb0c..45049f558860 100644 --- a/drivers/pci/pci-acpi.c +++ b/drivers/pci/pci-acpi.c @@ -685,12 +685,21 @@ static pci_power_t acpi_pci_get_power_state(struct pci_dev *dev) if (!adev || !acpi_device_power_manageable(adev)) return PCI_UNKNOWN; - if (acpi_device_get_power(adev, &state) || state == ACPI_STATE_UNKNOWN) + state = adev->power.state; + if (state == ACPI_STATE_UNKNOWN) return PCI_UNKNOWN; return state_conv[state]; } +static void acpi_pci_refresh_power_state(struct pci_dev *dev) +{ + struct acpi_device *adev = ACPI_COMPANION(&dev->dev); + + if (adev && acpi_device_power_manageable(adev)) + acpi_device_update_power(adev, NULL); +} + static int acpi_pci_propagate_wakeup(struct pci_bus *bus, bool enable) { while (bus->parent) { @@ -748,6 +757,7 @@ static const struct pci_platform_pm_ops acpi_pci_platform_pm = { .is_manageable = acpi_pci_power_manageable, .set_state = acpi_pci_set_power_state, .get_state = acpi_pci_get_power_state, + .refresh_state = acpi_pci_refresh_power_state, .choose_state = acpi_pci_choose_state, .set_wakeup = acpi_pci_wakeup, .need_resume = acpi_pci_need_resume, @@ -901,6 +911,7 @@ static void pci_acpi_setup(struct device *dev) device_wakeup_enable(dev); acpi_pci_wakeup(pci_dev, false); + acpi_device_power_add_dependent(adev, dev); } static void pci_acpi_cleanup(struct device *dev) @@ -913,6 +924,7 @@ static void pci_acpi_cleanup(struct device *dev) pci_acpi_remove_pm_notifier(adev); if (adev->wakeup.flags.valid) { + acpi_device_power_remove_dependent(adev, dev); if (pci_dev->bridge_d3) device_wakeup_disable(dev); diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index ca3793002e2f..36dbe960306b 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -678,6 +678,7 @@ static bool pci_has_legacy_pm_support(struct pci_dev *pci_dev) static int pci_pm_prepare(struct device *dev) { struct device_driver *drv = dev->driver; + struct pci_dev *pci_dev = to_pci_dev(dev); if (drv && drv->pm && drv->pm->prepare) { int error = drv->pm->prepare(dev); @@ -687,7 +688,15 @@ static int pci_pm_prepare(struct device *dev) if (!error && dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_PREPARE)) return 0; } - return pci_dev_keep_suspended(to_pci_dev(dev)); + if (pci_dev_need_resume(pci_dev)) + return 0; + + /* + * The PME setting needs to be adjusted here in case the direct-complete + * optimization is used with respect to this device. + */ + pci_dev_adjust_pme(pci_dev); + return 1; } static void pci_pm_complete(struct device *dev) @@ -701,7 +710,14 @@ static void pci_pm_complete(struct device *dev) if (pm_runtime_suspended(dev) && pm_resume_via_firmware()) { pci_power_t pre_sleep_state = pci_dev->current_state; - pci_update_current_state(pci_dev, pci_dev->current_state); + pci_refresh_power_state(pci_dev); + /* + * On platforms with ACPI this check may also trigger for + * devices sharing power resources if one of those power + * resources has been activated as a result of a change of the + * power state of another device sharing it. However, in that + * case it is also better to resume the device, in general. + */ if (pci_dev->current_state < pre_sleep_state) pm_request_resume(dev); } @@ -757,9 +773,11 @@ static int pci_pm_suspend(struct device *dev) * better to resume the device from runtime suspend here. */ if (!dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND) || - !pci_dev_keep_suspended(pci_dev)) { + pci_dev_need_resume(pci_dev)) { pm_runtime_resume(dev); pci_dev->state_saved = false; + } else { + pci_dev_adjust_pme(pci_dev); } if (pm->suspend) { @@ -994,15 +1012,15 @@ static int pci_pm_freeze(struct device *dev) } /* - * This used to be done in pci_pm_prepare() for all devices and some - * drivers may depend on it, so do it here. Ideally, runtime-suspended - * devices should not be touched during freeze/thaw transitions, - * however. + * Resume all runtime-suspended devices before creating a snapshot + * image of system memory, because the restore kernel generally cannot + * be expected to always handle them consistently and they need to be + * put into the runtime-active metastate during system resume anyway, + * so it is better to ensure that the state saved in the image will be + * always consistent with that. */ - if (!dev_pm_smart_suspend_and_suspended(dev)) { - pm_runtime_resume(dev); - pci_dev->state_saved = false; - } + pm_runtime_resume(dev); + pci_dev->state_saved = false; if (pm->freeze) { int error; @@ -1016,22 +1034,11 @@ static int pci_pm_freeze(struct device *dev) return 0; } -static int pci_pm_freeze_late(struct device *dev) -{ - if (dev_pm_smart_suspend_and_suspended(dev)) - return 0; - - return pm_generic_freeze_late(dev); -} - static int pci_pm_freeze_noirq(struct device *dev) { struct pci_dev *pci_dev = to_pci_dev(dev); struct device_driver *drv = dev->driver; - if (dev_pm_smart_suspend_and_suspended(dev)) - return 0; - if (pci_has_legacy_pm_support(pci_dev)) return pci_legacy_suspend_late(dev, PMSG_FREEZE); @@ -1061,16 +1068,6 @@ static int pci_pm_thaw_noirq(struct device *dev) struct device_driver *drv = dev->driver; int error = 0; - /* - * If the device is in runtime suspend, the code below may not work - * correctly with it, so skip that code and make the PM core skip all of - * the subsequent "thaw" callbacks for the device. - */ - if (dev_pm_smart_suspend_and_suspended(dev)) { - dev_pm_skip_next_resume_phases(dev); - return 0; - } - if (pcibios_pm_ops.thaw_noirq) { error = pcibios_pm_ops.thaw_noirq(dev); if (error) @@ -1130,10 +1127,13 @@ static int pci_pm_poweroff(struct device *dev) /* The reason to do that is the same as in pci_pm_suspend(). */ if (!dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND) || - !pci_dev_keep_suspended(pci_dev)) + pci_dev_need_resume(pci_dev)) { pm_runtime_resume(dev); + pci_dev->state_saved = false; + } else { + pci_dev_adjust_pme(pci_dev); + } - pci_dev->state_saved = false; if (pm->poweroff) { int error; @@ -1205,10 +1205,6 @@ static int pci_pm_restore_noirq(struct device *dev) struct device_driver *drv = dev->driver; int error = 0; - /* This is analogous to the pci_pm_resume_noirq() case. */ - if (dev_pm_smart_suspend_and_suspended(dev)) - pm_runtime_set_active(dev); - if (pcibios_pm_ops.restore_noirq) { error = pcibios_pm_ops.restore_noirq(dev); if (error) @@ -1258,7 +1254,6 @@ static int pci_pm_restore(struct device *dev) #else /* !CONFIG_HIBERNATE_CALLBACKS */ #define pci_pm_freeze NULL -#define pci_pm_freeze_late NULL #define pci_pm_freeze_noirq NULL #define pci_pm_thaw NULL #define pci_pm_thaw_noirq NULL @@ -1384,7 +1379,6 @@ static const struct dev_pm_ops pci_dev_pm_ops = { .suspend_late = pci_pm_suspend_late, .resume = pci_pm_resume, .freeze = pci_pm_freeze, - .freeze_late = pci_pm_freeze_late, .thaw = pci_pm_thaw, .poweroff = pci_pm_poweroff, .poweroff_late = pci_pm_poweroff_late, diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 8abc843b1615..b1f563916036 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -777,6 +777,12 @@ static inline pci_power_t platform_pci_get_power_state(struct pci_dev *dev) return pci_platform_pm ? pci_platform_pm->get_state(dev) : PCI_UNKNOWN; } +static inline void platform_pci_refresh_power_state(struct pci_dev *dev) +{ + if (pci_platform_pm && pci_platform_pm->refresh_state) + pci_platform_pm->refresh_state(dev); +} + static inline pci_power_t platform_pci_choose_state(struct pci_dev *dev) { return pci_platform_pm ? @@ -938,6 +944,21 @@ void pci_update_current_state(struct pci_dev *dev, pci_power_t state) } /** + * pci_refresh_power_state - Refresh the given device's power state data + * @dev: Target PCI device. + * + * Ask the platform to refresh the devices power state information and invoke + * pci_update_current_state() to update its current PCI power state. + */ +void pci_refresh_power_state(struct pci_dev *dev) +{ + if (platform_pci_power_manageable(dev)) + platform_pci_refresh_power_state(dev); + + pci_update_current_state(dev, dev->current_state); +} + +/** * pci_power_up - Put the given device into D0 forcibly * @dev: PCI device to power up */ @@ -1004,15 +1025,10 @@ static void __pci_start_power_transition(struct pci_dev *dev, pci_power_t state) if (state == PCI_D0) { pci_platform_power_transition(dev, PCI_D0); /* - * Mandatory power management transition delays, see - * PCI Express Base Specification Revision 2.0 Section - * 6.6.1: Conventional Reset. Do not delay for - * devices powered on/off by corresponding bridge, - * because have already delayed for the bridge. + * Mandatory power management transition delays are + * handled in the PCIe portdrv resume hooks. */ if (dev->runtime_d3cold) { - if (dev->d3cold_delay && !dev->imm_ready) - msleep(dev->d3cold_delay); /* * When powering on a bridge from D3cold, the * whole hierarchy may be powered on into @@ -2065,6 +2081,13 @@ static void pci_pme_list_scan(struct work_struct *work) */ if (bridge && bridge->current_state != PCI_D0) continue; + /* + * If the device is in D3cold it should not be + * polled either. + */ + if (pme_dev->dev->current_state == PCI_D3cold) + continue; + pci_pme_wakeup(pme_dev->dev, NULL); } else { list_del(&pme_dev->list); @@ -2459,45 +2482,56 @@ bool pci_dev_run_wake(struct pci_dev *dev) EXPORT_SYMBOL_GPL(pci_dev_run_wake); /** - * pci_dev_keep_suspended - Check if the device can stay in the suspended state. + * pci_dev_need_resume - Check if it is necessary to resume the device. * @pci_dev: Device to check. * - * Return 'true' if the device is runtime-suspended, it doesn't have to be + * Return 'true' if the device is not runtime-suspended or it has to be * reconfigured due to wakeup settings difference between system and runtime - * suspend and the current power state of it is suitable for the upcoming - * (system) transition. - * - * If the device is not configured for system wakeup, disable PME for it before - * returning 'true' to prevent it from waking up the system unnecessarily. + * suspend, or the current power state of it is not suitable for the upcoming + * (system-wide) transition. */ -bool pci_dev_keep_suspended(struct pci_dev *pci_dev) +bool pci_dev_need_resume(struct pci_dev *pci_dev) { struct device *dev = &pci_dev->dev; - bool wakeup = device_may_wakeup(dev); + pci_power_t target_state; - if (!pm_runtime_suspended(dev) - || pci_target_state(pci_dev, wakeup) != pci_dev->current_state - || platform_pci_need_resume(pci_dev)) - return false; + if (!pm_runtime_suspended(dev) || platform_pci_need_resume(pci_dev)) + return true; + + target_state = pci_target_state(pci_dev, device_may_wakeup(dev)); /* - * At this point the device is good to go unless it's been configured - * to generate PME at the runtime suspend time, but it is not supposed - * to wake up the system. In that case, simply disable PME for it - * (it will have to be re-enabled on exit from system resume). - * - * If the device's power state is D3cold and the platform check above - * hasn't triggered, the device's configuration is suitable and we don't - * need to manipulate it at all. + * If the earlier platform check has not triggered, D3cold is just power + * removal on top of D3hot, so no need to resume the device in that + * case. */ + return target_state != pci_dev->current_state && + target_state != PCI_D3cold && + pci_dev->current_state != PCI_D3hot; +} + +/** + * pci_dev_adjust_pme - Adjust PME setting for a suspended device. + * @pci_dev: Device to check. + * + * If the device is suspended and it is not configured for system wakeup, + * disable PME for it to prevent it from waking up the system unnecessarily. + * + * Note that if the device's power state is D3cold and the platform check in + * pci_dev_need_resume() has not triggered, the device's configuration need not + * be changed. + */ +void pci_dev_adjust_pme(struct pci_dev *pci_dev) +{ + struct device *dev = &pci_dev->dev; + spin_lock_irq(&dev->power.lock); - if (pm_runtime_suspended(dev) && pci_dev->current_state < PCI_D3cold && - !wakeup) + if (pm_runtime_suspended(dev) && !device_may_wakeup(dev) && + pci_dev->current_state < PCI_D3cold) __pci_pme_active(pci_dev, false); spin_unlock_irq(&dev->power.lock); - return true; } /** @@ -4568,14 +4602,16 @@ static int pci_pm_reset(struct pci_dev *dev, int probe) return pci_dev_wait(dev, "PM D3->D0", PCIE_RESET_READY_POLL_MS); } + /** - * pcie_wait_for_link - Wait until link is active or inactive + * pcie_wait_for_link_delay - Wait until link is active or inactive * @pdev: Bridge device * @active: waiting for active or inactive? + * @delay: Delay to wait after link has become active (in ms) * * Use this to wait till link becomes active or inactive. */ -bool pcie_wait_for_link(struct pci_dev *pdev, bool active) +bool pcie_wait_for_link_delay(struct pci_dev *pdev, bool active, int delay) { int timeout = 1000; bool ret; @@ -4612,13 +4648,25 @@ bool pcie_wait_for_link(struct pci_dev *pdev, bool active) timeout -= 10; } if (active && ret) - msleep(100); + msleep(delay); else if (ret != active) pci_info(pdev, "Data Link Layer Link Active not %s in 1000 msec\n", active ? "set" : "cleared"); return ret == active; } +/** + * pcie_wait_for_link - Wait until link is active or inactive + * @pdev: Bridge device + * @active: waiting for active or inactive? + * + * Use this to wait till link becomes active or inactive. + */ +bool pcie_wait_for_link(struct pci_dev *pdev, bool active) +{ + return pcie_wait_for_link_delay(pdev, active, 100); +} + void pci_reset_secondary_bus(struct pci_dev *dev) { u16 ctrl; diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 9cb99380c61e..5db6f985f16d 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -51,6 +51,8 @@ int pci_bus_error_reset(struct pci_dev *dev); * * @get_state: queries the platform firmware for a device's current power state * + * @refresh_state: asks the platform to refresh the device's power state data + * * @choose_state: returns PCI power state of given device preferred by the * platform; to be used during system-wide transitions from a * sleeping state to the working state and vice versa @@ -69,6 +71,7 @@ struct pci_platform_pm_ops { bool (*is_manageable)(struct pci_dev *dev); int (*set_state)(struct pci_dev *dev, pci_power_t state); pci_power_t (*get_state)(struct pci_dev *dev); + void (*refresh_state)(struct pci_dev *dev); pci_power_t (*choose_state)(struct pci_dev *dev); int (*set_wakeup)(struct pci_dev *dev, bool enable); bool (*need_resume)(struct pci_dev *dev); @@ -76,13 +79,15 @@ struct pci_platform_pm_ops { int pci_set_platform_pm(const struct pci_platform_pm_ops *ops); void pci_update_current_state(struct pci_dev *dev, pci_power_t state); +void pci_refresh_power_state(struct pci_dev *dev); void pci_power_up(struct pci_dev *dev); void pci_disable_enabled_device(struct pci_dev *dev); int pci_finish_runtime_suspend(struct pci_dev *dev); void pcie_clear_root_pme_status(struct pci_dev *dev); int __pci_pme_wakeup(struct pci_dev *dev, void *ign); void pci_pme_restore(struct pci_dev *dev); -bool pci_dev_keep_suspended(struct pci_dev *dev); +bool pci_dev_need_resume(struct pci_dev *dev); +void pci_dev_adjust_pme(struct pci_dev *dev); void pci_dev_complete_resume(struct pci_dev *pci_dev); void pci_config_pm_runtime_get(struct pci_dev *dev); void pci_config_pm_runtime_put(struct pci_dev *dev); @@ -493,6 +498,7 @@ static inline int pci_dev_specific_disable_acs_redir(struct pci_dev *dev) void pcie_do_recovery(struct pci_dev *dev, enum pci_channel_state state, u32 service); +bool pcie_wait_for_link_delay(struct pci_dev *pdev, bool active, int delay); bool pcie_wait_for_link(struct pci_dev *pdev, bool active); #ifdef CONFIG_PCIEASPM void pcie_aspm_init_link_state(struct pci_dev *pdev); diff --git a/drivers/pci/pcie/portdrv_core.c b/drivers/pci/pcie/portdrv_core.c index 1b330129089f..308c3e0c4a34 100644 --- a/drivers/pci/pcie/portdrv_core.c +++ b/drivers/pci/pcie/portdrv_core.c @@ -9,6 +9,7 @@ #include <linux/module.h> #include <linux/pci.h> #include <linux/kernel.h> +#include <linux/delay.h> #include <linux/errno.h> #include <linux/pm.h> #include <linux/pm_runtime.h> @@ -378,6 +379,67 @@ static int pm_iter(struct device *dev, void *data) return 0; } +static int get_downstream_delay(struct pci_bus *bus) +{ + struct pci_dev *pdev; + int min_delay = 100; + int max_delay = 0; + + list_for_each_entry(pdev, &bus->devices, bus_list) { + if (!pdev->imm_ready) + min_delay = 0; + else if (pdev->d3cold_delay < min_delay) + min_delay = pdev->d3cold_delay; + if (pdev->d3cold_delay > max_delay) + max_delay = pdev->d3cold_delay; + } + + return max(min_delay, max_delay); +} + +/* + * wait_for_downstream_link - Wait for downstream link to establish + * @pdev: PCIe port whose downstream link is waited + * + * Handle delays according to PCIe 4.0 section 6.6.1 before configuration + * access to the downstream component is permitted. + * + * This blocks PCI core resume of the hierarchy below this port until the + * link is trained. Should be called before resuming port services to + * prevent pciehp from starting to tear-down the hierarchy too soon. + */ +static void wait_for_downstream_link(struct pci_dev *pdev) +{ + int delay; + + if (pci_pcie_type(pdev) != PCI_EXP_TYPE_ROOT_PORT && + pci_pcie_type(pdev) != PCI_EXP_TYPE_DOWNSTREAM) + return; + + if (pci_dev_is_disconnected(pdev)) + return; + + if (!pdev->subordinate || list_empty(&pdev->subordinate->devices) || + !pdev->bridge_d3) + return; + + delay = get_downstream_delay(pdev->subordinate); + if (!delay) + return; + + dev_dbg(&pdev->dev, "waiting downstream link for %d ms\n", delay); + + /* + * If downstream port does not support speeds greater than 5 GT/s + * need to wait 100ms. For higher speeds (gen3) we need to wait + * first for the data link layer to become active. + */ + if (pcie_get_speed_cap(pdev) <= PCIE_SPEED_5_0GT) + msleep(delay); + else + pcie_wait_for_link_delay(pdev, true, delay); +} + /** * pcie_port_device_suspend - suspend port services associated with a PCIe port * @dev: PCI Express port to handle @@ -391,6 +453,8 @@ int pcie_port_device_suspend(struct device *dev) int pcie_port_device_resume_noirq(struct device *dev) { size_t off = offsetof(struct pcie_port_service_driver, resume_noirq); + + wait_for_downstream_link(to_pci_dev(dev)); return device_for_each_child(dev, &off, pm_iter); } @@ -421,6 +485,8 @@ int pcie_port_device_runtime_suspend(struct device *dev) int pcie_port_device_runtime_resume(struct device *dev) { size_t off = offsetof(struct pcie_port_service_driver, runtime_resume); + + wait_for_downstream_link(to_pci_dev(dev)); return device_for_each_child(dev, &off, pm_iter); } #endif /* PM */ diff --git a/drivers/power/avs/smartreflex.c b/drivers/power/avs/smartreflex.c index c96c01e09740..4684e7df833a 100644 --- a/drivers/power/avs/smartreflex.c +++ b/drivers/power/avs/smartreflex.c @@ -899,38 +899,19 @@ static int omap_sr_probe(struct platform_device *pdev) } dev_info(&pdev->dev, "%s: SmartReflex driver initialized\n", __func__); - if (!sr_dbg_dir) { + if (!sr_dbg_dir) sr_dbg_dir = debugfs_create_dir("smartreflex", NULL); - if (IS_ERR_OR_NULL(sr_dbg_dir)) { - ret = PTR_ERR(sr_dbg_dir); - pr_err("%s:sr debugfs dir creation failed(%d)\n", - __func__, ret); - goto err_list_del; - } - } sr_info->dbg_dir = debugfs_create_dir(sr_info->name, sr_dbg_dir); - if (IS_ERR_OR_NULL(sr_info->dbg_dir)) { - dev_err(&pdev->dev, "%s: Unable to create debugfs directory\n", - __func__); - ret = PTR_ERR(sr_info->dbg_dir); - goto err_debugfs; - } - (void) debugfs_create_file("autocomp", S_IRUGO | S_IWUSR, - sr_info->dbg_dir, (void *)sr_info, &pm_sr_fops); - (void) debugfs_create_x32("errweight", S_IRUGO, sr_info->dbg_dir, - &sr_info->err_weight); - (void) debugfs_create_x32("errmaxlimit", S_IRUGO, sr_info->dbg_dir, - &sr_info->err_maxlimit); + debugfs_create_file("autocomp", S_IRUGO | S_IWUSR, sr_info->dbg_dir, + (void *)sr_info, &pm_sr_fops); + debugfs_create_x32("errweight", S_IRUGO, sr_info->dbg_dir, + &sr_info->err_weight); + debugfs_create_x32("errmaxlimit", S_IRUGO, sr_info->dbg_dir, + &sr_info->err_maxlimit); nvalue_dir = debugfs_create_dir("nvalue", sr_info->dbg_dir); - if (IS_ERR_OR_NULL(nvalue_dir)) { - dev_err(&pdev->dev, "%s: Unable to create debugfs directory for n-values\n", - __func__); - ret = PTR_ERR(nvalue_dir); - goto err_debugfs; - } if (sr_info->nvalue_count == 0 || !sr_info->nvalue_table) { dev_warn(&pdev->dev, "%s: %s: No Voltage table for the corresponding vdd. Cannot create debugfs entries for n-values\n", @@ -945,12 +926,12 @@ static int omap_sr_probe(struct platform_device *pdev) snprintf(name, sizeof(name), "volt_%lu", sr_info->nvalue_table[i].volt_nominal); - (void) debugfs_create_x32(name, S_IRUGO | S_IWUSR, nvalue_dir, - &(sr_info->nvalue_table[i].nvalue)); + debugfs_create_x32(name, S_IRUGO | S_IWUSR, nvalue_dir, + &(sr_info->nvalue_table[i].nvalue)); snprintf(name, sizeof(name), "errminlimit_%lu", sr_info->nvalue_table[i].volt_nominal); - (void) debugfs_create_x32(name, S_IRUGO | S_IWUSR, nvalue_dir, - &(sr_info->nvalue_table[i].errminlimit)); + debugfs_create_x32(name, S_IRUGO | S_IWUSR, nvalue_dir, + &(sr_info->nvalue_table[i].errminlimit)); } diff --git a/drivers/soc/imx/soc-imx8.c b/drivers/soc/imx/soc-imx8.c index fc6429f9170a..b1bd8e2543ac 100644 --- a/drivers/soc/imx/soc-imx8.c +++ b/drivers/soc/imx/soc-imx8.c @@ -103,6 +103,9 @@ static int __init imx8_soc_init(void) if (IS_ERR(soc_dev)) goto free_rev; + if (IS_ENABLED(CONFIG_ARM_IMX_CPUFREQ_DT)) + platform_device_register_simple("imx-cpufreq-dt", -1, NULL, 0); + return 0; free_rev: |