diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2012-10-03 01:32:35 (GMT) |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2012-10-03 01:32:35 (GMT) |
| commit | 16642a2e7be23bbda013fc32d8f6c68982eab603 (patch) | |
| tree | 346ae485f485f6901e5d8150f0d34d178a7dd448 /drivers | |
| parent | 51562cba98939da0a1d10fe7c25359b77a069033 (diff) | |
| parent | b9142167a2bb979b58b98ffcd928a311b55cbd9f (diff) | |
| download | linux-16642a2e7be23bbda013fc32d8f6c68982eab603.tar.xz | |
Merge tag 'pm-for-3.7-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm
Pull power management updates from Rafael J Wysocki:
- Improved system suspend/resume and runtime PM handling for the SH
TMU, CMT and MTU2 clock event devices (also used by ARM/shmobile).
- Generic PM domains framework extensions related to cpuidle support
and domain objects lookup using names.
- ARM/shmobile power management updates including improved support for
the SH7372's A4S power domain containing the CPU core.
- cpufreq changes related to AMD CPUs support from Matthew Garrett,
Andre Przywara and Borislav Petkov.
- cpu0 cpufreq driver from Shawn Guo.
- cpufreq governor fixes related to the relaxing of limit from Michal
Pecio.
- OMAP cpufreq updates from Axel Lin and Richard Zhao.
- cpuidle ladder governor fixes related to the disabling of states from
Carsten Emde and me.
- Runtime PM core updates related to the interactions with the system
suspend core from Alan Stern and Kevin Hilman.
- Wakeup sources modification allowing more helper functions to be
called from interrupt context from John Stultz and additional
diagnostic code from Todd Poynor.
- System suspend error code path fix from Feng Hong.
Fixed up conflicts in cpufreq/powernow-k8 that stemmed from the
workqueue fixes conflicting fairly badly with the removal of support for
hardware P-state chips. The changes were independent but somewhat
intertwined.
* tag 'pm-for-3.7-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (76 commits)
Revert "PM QoS: Use spinlock in the per-device PM QoS constraints code"
PM / Runtime: let rpm_resume() succeed if RPM_ACTIVE, even when disabled, v2
cpuidle: rename function name "__cpuidle_register_driver", v2
cpufreq: OMAP: Check IS_ERR() instead of NULL for omap_device_get_by_hwmod_name
cpuidle: remove some empty lines
PM: Prevent runtime suspend during system resume
PM QoS: Use spinlock in the per-device PM QoS constraints code
PM / Sleep: use resume event when call dpm_resume_early
cpuidle / ACPI : move cpuidle_device field out of the acpi_processor_power structure
ACPI / processor: remove pointless variable initialization
ACPI / processor: remove unused function parameter
cpufreq: OMAP: remove loops_per_jiffy recalculate for smp
sections: fix section conflicts in drivers/cpufreq
cpufreq: conservative: update frequency when limits are relaxed
cpufreq / ondemand: update frequency when limits are relaxed
properly __init-annotate pm_sysrq_init()
cpufreq: Add a generic cpufreq-cpu0 driver
PM / OPP: Initialize OPP table from device tree
ARM: add cpufreq transiton notifier to adjust loops_per_jiffy for smp
cpufreq: Remove support for hardware P-state chips from powernow-k8
...
Diffstat (limited to 'drivers')
28 files changed, 1272 insertions, 596 deletions
diff --git a/drivers/acpi/processor_driver.c b/drivers/acpi/processor_driver.c index bfc31cb..e78c2a5 100644 --- a/drivers/acpi/processor_driver.c +++ b/drivers/acpi/processor_driver.c @@ -475,7 +475,7 @@ static __ref int acpi_processor_start(struct acpi_processor *pr) acpi_processor_get_limit_info(pr); if (!cpuidle_get_driver() || cpuidle_get_driver() == &acpi_idle_driver) - acpi_processor_power_init(pr, device); + acpi_processor_power_init(pr); pr->cdev = thermal_cooling_device_register("Processor", device, &processor_cooling_ops); @@ -509,7 +509,7 @@ err_remove_sysfs_thermal: err_thermal_unregister: thermal_cooling_device_unregister(pr->cdev); err_power_exit: - acpi_processor_power_exit(pr, device); + acpi_processor_power_exit(pr); return result; } @@ -620,7 +620,7 @@ static int acpi_processor_remove(struct acpi_device *device, int type) return -EINVAL; } - acpi_processor_power_exit(pr, device); + acpi_processor_power_exit(pr); sysfs_remove_link(&device->dev.kobj, "sysdev"); @@ -905,8 +905,6 @@ static int __init acpi_processor_init(void) if (acpi_disabled) return 0; - memset(&errata, 0, sizeof(errata)); - result = acpi_bus_register_driver(&acpi_processor_driver); if (result < 0) return result; diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c index ad3730b..3655ab9 100644 --- a/drivers/acpi/processor_idle.c +++ b/drivers/acpi/processor_idle.c @@ -79,6 +79,8 @@ module_param(bm_check_disable, uint, 0000); static unsigned int latency_factor __read_mostly = 2; module_param(latency_factor, uint, 0644); +static DEFINE_PER_CPU(struct cpuidle_device *, acpi_cpuidle_device); + static int disabled_by_idle_boot_param(void) { return boot_option_idle_override == IDLE_POLL || @@ -483,8 +485,6 @@ static int acpi_processor_get_power_info_cst(struct acpi_processor *pr) if (obj->type != ACPI_TYPE_INTEGER) continue; - cx.power = obj->integer.value; - current_count++; memcpy(&(pr->power.states[current_count]), &cx, sizeof(cx)); @@ -1000,7 +1000,7 @@ static int acpi_processor_setup_cpuidle_cx(struct acpi_processor *pr) int i, count = CPUIDLE_DRIVER_STATE_START; struct acpi_processor_cx *cx; struct cpuidle_state_usage *state_usage; - struct cpuidle_device *dev = &pr->power.dev; + struct cpuidle_device *dev = per_cpu(acpi_cpuidle_device, pr->id); if (!pr->flags.power_setup_done) return -EINVAL; @@ -1132,6 +1132,7 @@ static int acpi_processor_setup_cpuidle_states(struct acpi_processor *pr) int acpi_processor_hotplug(struct acpi_processor *pr) { int ret = 0; + struct cpuidle_device *dev = per_cpu(acpi_cpuidle_device, pr->id); if (disabled_by_idle_boot_param()) return 0; @@ -1147,11 +1148,11 @@ int acpi_processor_hotplug(struct acpi_processor *pr) return -ENODEV; cpuidle_pause_and_lock(); - cpuidle_disable_device(&pr->power.dev); + cpuidle_disable_device(dev); acpi_processor_get_power_info(pr); if (pr->flags.power) { acpi_processor_setup_cpuidle_cx(pr); - ret = cpuidle_enable_device(&pr->power.dev); + ret = cpuidle_enable_device(dev); } cpuidle_resume_and_unlock(); @@ -1162,6 +1163,7 @@ int acpi_processor_cst_has_changed(struct acpi_processor *pr) { int cpu; struct acpi_processor *_pr; + struct cpuidle_device *dev; if (disabled_by_idle_boot_param()) return 0; @@ -1192,7 +1194,8 @@ int acpi_processor_cst_has_changed(struct acpi_processor *pr) _pr = per_cpu(processors, cpu); if (!_pr || !_pr->flags.power_setup_done) continue; - cpuidle_disable_device(&_pr->power.dev); + dev = per_cpu(acpi_cpuidle_device, cpu); + cpuidle_disable_device(dev); } /* Populate Updated C-state information */ @@ -1206,7 +1209,8 @@ int acpi_processor_cst_has_changed(struct acpi_processor *pr) acpi_processor_get_power_info(_pr); if (_pr->flags.power) { acpi_processor_setup_cpuidle_cx(_pr); - cpuidle_enable_device(&_pr->power.dev); + dev = per_cpu(acpi_cpuidle_device, cpu); + cpuidle_enable_device(dev); } } put_online_cpus(); @@ -1218,11 +1222,11 @@ int acpi_processor_cst_has_changed(struct acpi_processor *pr) static int acpi_processor_registered; -int __cpuinit acpi_processor_power_init(struct acpi_processor *pr, - struct acpi_device *device) +int __cpuinit acpi_processor_power_init(struct acpi_processor *pr) { acpi_status status = 0; int retval; + struct cpuidle_device *dev; static int first_run; if (disabled_by_idle_boot_param()) @@ -1268,11 +1272,18 @@ int __cpuinit acpi_processor_power_init(struct acpi_processor *pr, printk(KERN_DEBUG "ACPI: %s registered with cpuidle\n", acpi_idle_driver.name); } + + dev = kzalloc(sizeof(*dev), GFP_KERNEL); + if (!dev) + return -ENOMEM; + per_cpu(acpi_cpuidle_device, pr->id) = dev; + + acpi_processor_setup_cpuidle_cx(pr); + /* Register per-cpu cpuidle_device. Cpuidle driver * must already be registered before registering device */ - acpi_processor_setup_cpuidle_cx(pr); - retval = cpuidle_register_device(&pr->power.dev); + retval = cpuidle_register_device(dev); if (retval) { if (acpi_processor_registered == 0) cpuidle_unregister_driver(&acpi_idle_driver); @@ -1283,14 +1294,15 @@ int __cpuinit acpi_processor_power_init(struct acpi_processor *pr, return 0; } -int acpi_processor_power_exit(struct acpi_processor *pr, - struct acpi_device *device) +int acpi_processor_power_exit(struct acpi_processor *pr) { + struct cpuidle_device *dev = per_cpu(acpi_cpuidle_device, pr->id); + if (disabled_by_idle_boot_param()) return 0; if (pr->flags.power) { - cpuidle_unregister_device(&pr->power.dev); + cpuidle_unregister_device(dev); acpi_processor_registered--; if (acpi_processor_registered == 0) cpuidle_unregister_driver(&acpi_idle_driver); diff --git a/drivers/acpi/processor_perflib.c b/drivers/acpi/processor_perflib.c index a093dc1..836bfe0 100644 --- a/drivers/acpi/processor_perflib.c +++ b/drivers/acpi/processor_perflib.c @@ -324,6 +324,34 @@ static int acpi_processor_get_performance_control(struct acpi_processor *pr) return result; } +#ifdef CONFIG_X86 +/* + * Some AMDs have 50MHz frequency multiples, but only provide 100MHz rounding + * in their ACPI data. Calculate the real values and fix up the _PSS data. + */ +static void amd_fixup_frequency(struct acpi_processor_px *px, int i) +{ + u32 hi, lo, fid, did; + int index = px->control & 0x00000007; + + if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) + return; + + if ((boot_cpu_data.x86 == 0x10 && boot_cpu_data.x86_model < 10) + || boot_cpu_data.x86 == 0x11) { + rdmsr(MSR_AMD_PSTATE_DEF_BASE + index, lo, hi); + fid = lo & 0x3f; + did = (lo >> 6) & 7; + if (boot_cpu_data.x86 == 0x10) + px->core_frequency = (100 * (fid + 0x10)) >> did; + else + px->core_frequency = (100 * (fid + 8)) >> did; + } +} +#else +static void amd_fixup_frequency(struct acpi_processor_px *px, int i) {}; +#endif + static int acpi_processor_get_performance_states(struct acpi_processor *pr) { int result = 0; @@ -379,6 +407,8 @@ static int acpi_processor_get_performance_states(struct acpi_processor *pr) goto end; } + amd_fixup_frequency(px, i); + ACPI_DEBUG_PRINT((ACPI_DB_INFO, "State [%d]: core_frequency[%d] power[%d] transition_latency[%d] bus_master_latency[%d] control[0x%x] status[0x%x]\n", i, diff --git a/drivers/base/platform.c b/drivers/base/platform.c index ddeca14..8727e9c 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -23,6 +23,7 @@ #include <linux/idr.h> #include "base.h" +#include "power/power.h" /* For automatically allocated device IDs */ static DEFINE_IDA(platform_devid_ida); @@ -983,6 +984,7 @@ void __init early_platform_add_devices(struct platform_device **devs, int num) dev = &devs[i]->dev; if (!dev->devres_head.next) { + pm_runtime_early_init(dev); INIT_LIST_HEAD(&dev->devres_head); list_add_tail(&dev->devres_head, &early_platform_device_list); diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index ba3487c..c22b869 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -53,6 +53,24 @@ static LIST_HEAD(gpd_list); static DEFINE_MUTEX(gpd_list_lock); +static struct generic_pm_domain *pm_genpd_lookup_name(const char *domain_name) +{ + struct generic_pm_domain *genpd = NULL, *gpd; + + if (IS_ERR_OR_NULL(domain_name)) + return NULL; + + mutex_lock(&gpd_list_lock); + list_for_each_entry(gpd, &gpd_list, gpd_list_node) { + if (!strcmp(gpd->name, domain_name)) { + genpd = gpd; + break; + } + } + mutex_unlock(&gpd_list_lock); + return genpd; +} + #ifdef CONFIG_PM struct generic_pm_domain *dev_to_genpd(struct device *dev) @@ -256,10 +274,28 @@ int pm_genpd_poweron(struct generic_pm_domain *genpd) return ret; } +/** + * pm_genpd_name_poweron - Restore power to a given PM domain and its masters. + * @domain_name: Name of the PM domain to power up. + */ +int pm_genpd_name_poweron(const char *domain_name) +{ + struct generic_pm_domain *genpd; + + genpd = pm_genpd_lookup_name(domain_name); + return genpd ? pm_genpd_poweron(genpd) : -EINVAL; +} + #endif /* CONFIG_PM */ #ifdef CONFIG_PM_RUNTIME +static int genpd_start_dev_no_timing(struct generic_pm_domain *genpd, + struct device *dev) +{ + return GENPD_DEV_CALLBACK(genpd, int, start, dev); +} + static int genpd_save_dev(struct generic_pm_domain *genpd, struct device *dev) { return GENPD_DEV_TIMED_CALLBACK(genpd, int, save_state, dev, @@ -436,7 +472,7 @@ static int pm_genpd_poweroff(struct generic_pm_domain *genpd) not_suspended = 0; list_for_each_entry(pdd, &genpd->dev_list, list_node) if (pdd->dev->driver && (!pm_runtime_suspended(pdd->dev) - || pdd->dev->power.irq_safe || to_gpd_data(pdd)->always_on)) + || pdd->dev->power.irq_safe)) not_suspended++; if (not_suspended > genpd->in_progress) @@ -578,9 +614,6 @@ static int pm_genpd_runtime_suspend(struct device *dev) might_sleep_if(!genpd->dev_irq_safe); - if (dev_gpd_data(dev)->always_on) - return -EBUSY; - stop_ok = genpd->gov ? genpd->gov->stop_ok : NULL; if (stop_ok && !stop_ok(dev)) return -EBUSY; @@ -629,7 +662,7 @@ static int pm_genpd_runtime_resume(struct device *dev) /* If power.irq_safe, the PM domain is never powered off. */ if (dev->power.irq_safe) - return genpd_start_dev(genpd, dev); + return genpd_start_dev_no_timing(genpd, dev); mutex_lock(&genpd->lock); ret = __pm_genpd_poweron(genpd); @@ -697,6 +730,24 @@ static inline void genpd_power_off_work_fn(struct work_struct *work) {} #ifdef CONFIG_PM_SLEEP +/** + * pm_genpd_present - Check if the given PM domain has been initialized. + * @genpd: PM domain to check. + */ +static bool pm_genpd_present(struct generic_pm_domain *genpd) +{ + struct generic_pm_domain *gpd; + + if (IS_ERR_OR_NULL(genpd)) + return false; + + list_for_each_entry(gpd, &gpd_list, gpd_list_node) + if (gpd == genpd) + return true; + + return false; +} + static bool genpd_dev_active_wakeup(struct generic_pm_domain *genpd, struct device *dev) { @@ -750,9 +801,10 @@ static int genpd_thaw_dev(struct generic_pm_domain *genpd, struct device *dev) * Check if the given PM domain can be powered off (during system suspend or * hibernation) and do that if so. Also, in that case propagate to its masters. * - * This function is only called in "noirq" stages of system power transitions, - * so it need not acquire locks (all of the "noirq" callbacks are executed - * sequentially, so it is guaranteed that it will never run twice in parallel). + * This function is only called in "noirq" and "syscore" stages of system power + * transitions, so it need not acquire locks (all of the "noirq" callbacks are + * executed sequentially, so it is guaranteed that it will never run twice in + * parallel). */ static void pm_genpd_sync_poweroff(struct generic_pm_domain *genpd) { @@ -777,6 +829,33 @@ static void pm_genpd_sync_poweroff(struct generic_pm_domain *genpd) } /** + * pm_genpd_sync_poweron - Synchronously power on a PM domain and its masters. + * @genpd: PM domain to power on. + * + * This function is only called in "noirq" and "syscore" stages of system power + * transitions, so it need not acquire locks (all of the "noirq" callbacks are + * executed sequentially, so it is guaranteed that it will never run twice in + * parallel). + */ +static void pm_genpd_sync_poweron(struct generic_pm_domain *genpd) +{ + struct gpd_link *link; + + if (genpd->status != GPD_STATE_POWER_OFF) + return; + + list_for_each_entry(link, &genpd->slave_links, slave_node) { + pm_genpd_sync_poweron(link->master); + genpd_sd_counter_inc(link->master); + } + + if (genpd->power_on) + genpd->power_on(genpd); + + genpd->status = GPD_STATE_ACTIVE; +} + +/** * resume_needed - Check whether to resume a device before system suspend. * @dev: Device to check. * @genpd: PM domain the device belongs to. @@ -937,7 +1016,7 @@ static int pm_genpd_suspend_noirq(struct device *dev) if (IS_ERR(genpd)) return -EINVAL; - if (genpd->suspend_power_off || dev_gpd_data(dev)->always_on + if (genpd->suspend_power_off || (dev->power.wakeup_path && genpd_dev_active_wakeup(genpd, dev))) return 0; @@ -970,7 +1049,7 @@ static int pm_genpd_resume_noirq(struct device *dev) if (IS_ERR(genpd)) return -EINVAL; - if (genpd->suspend_power_off || dev_gpd_data(dev)->always_on + if (genpd->suspend_power_off || (dev->power.wakeup_path && genpd_dev_active_wakeup(genpd, dev))) return 0; @@ -979,7 +1058,7 @@ static int pm_genpd_resume_noirq(struct device *dev) * guaranteed that this function will never run twice in parallel for * the same PM domain, so it is not necessary to use locking here. */ - pm_genpd_poweron(genpd); + pm_genpd_sync_poweron(genpd); genpd->suspended_count--; return genpd_start_dev(genpd, dev); @@ -1090,8 +1169,7 @@ static int pm_genpd_freeze_noirq(struct device *dev) if (IS_ERR(genpd)) return -EINVAL; - return genpd->suspend_power_off || dev_gpd_data(dev)->always_on ? - 0 : genpd_stop_dev(genpd, dev); + return genpd->suspend_power_off ? 0 : genpd_stop_dev(genpd, dev); } /** @@ -1111,8 +1189,7 @@ static int pm_genpd_thaw_noirq(struct device *dev) if (IS_ERR(genpd)) return -EINVAL; - return genpd->suspend_power_off || dev_gpd_data(dev)->always_on ? - 0 : genpd_start_dev(genpd, dev); + return genpd->suspend_power_off ? 0 : genpd_start_dev(genpd, dev); } /** @@ -1186,8 +1263,8 @@ static int pm_genpd_restore_noirq(struct device *dev) if (genpd->suspended_count++ == 0) { /* * The boot kernel might put the domain into arbitrary state, - * so make it appear as powered off to pm_genpd_poweron(), so - * that it tries to power it on in case it was really off. + * so make it appear as powered off to pm_genpd_sync_poweron(), + * so that it tries to power it on in case it was really off. */ genpd->status = GPD_STATE_POWER_OFF; if (genpd->suspend_power_off) { @@ -1205,9 +1282,9 @@ static int pm_genpd_restore_noirq(struct device *dev) if (genpd->suspend_power_off) return 0; - pm_genpd_poweron(genpd); + pm_genpd_sync_poweron(genpd); - return dev_gpd_data(dev)->always_on ? 0 : genpd_start_dev(genpd, dev); + return genpd_start_dev(genpd, dev); } /** @@ -1246,6 +1323,31 @@ static void pm_genpd_complete(struct device *dev) } } +/** + * pm_genpd_syscore_switch - Switch power during system core suspend or resume. + * @dev: Device that normally is marked as "always on" to switch power for. + * + * This routine may only be called during the system core (syscore) suspend or + * resume phase for devices whose "always on" flags are set. + */ +void pm_genpd_syscore_switch(struct device *dev, bool suspend) +{ + struct generic_pm_domain *genpd; + + genpd = dev_to_genpd(dev); + if (!pm_genpd_present(genpd)) + return; + + if (suspend) { + genpd->suspended_count++; + pm_genpd_sync_poweroff(genpd); + } else { + pm_genpd_sync_poweron(genpd); + genpd->suspended_count--; + } +} +EXPORT_SYMBOL_GPL(pm_genpd_syscore_switch); + #else #define pm_genpd_prepare NULL @@ -1393,6 +1495,19 @@ int __pm_genpd_of_add_device(struct device_node *genpd_node, struct device *dev, return __pm_genpd_add_device(genpd, dev, td); } + +/** + * __pm_genpd_name_add_device - Find I/O PM domain and add a device to it. + * @domain_name: Name of the PM domain to add the device to. + * @dev: Device to be added. + * @td: Set of PM QoS timing parameters to attach to the device. + */ +int __pm_genpd_name_add_device(const char *domain_name, struct device *dev, + struct gpd_timing_data *td) +{ + return __pm_genpd_add_device(pm_genpd_lookup_name(domain_name), dev, td); +} + /** * pm_genpd_remove_device - Remove a device from an I/O PM domain. * @genpd: PM domain to remove the device from. @@ -1455,26 +1570,6 @@ int pm_genpd_remove_device(struct generic_pm_domain *genpd, } /** - * pm_genpd_dev_always_on - Set/unset the "always on" flag for a given device. - * @dev: Device to set/unset the flag for. - * @val: The new value of the device's "always on" flag. - */ -void pm_genpd_dev_always_on(struct device *dev, bool val) -{ - struct pm_subsys_data *psd; - unsigned long flags; - - spin_lock_irqsave(&dev->power.lock, flags); - - psd = dev_to_psd(dev); - if (psd && psd->domain_data) - to_gpd_data(psd->domain_data)->always_on = val; - - spin_unlock_irqrestore(&dev->power.lock, flags); -} -EXPORT_SYMBOL_GPL(pm_genpd_dev_always_on); - -/** * pm_genpd_dev_need_restore - Set/unset the device's "need restore" flag. * @dev: Device to set/unset the flag for. * @val: The new value of the device's "need restore" flag. @@ -1505,7 +1600,8 @@ int pm_genpd_add_subdomain(struct generic_pm_domain *genpd, struct gpd_link *link; int ret = 0; - if (IS_ERR_OR_NULL(genpd) || IS_ERR_OR_NULL(subdomain)) + if (IS_ERR_OR_NULL(genpd) || IS_ERR_OR_NULL(subdomain) + || genpd == subdomain) return -EINVAL; start: @@ -1552,6 +1648,35 @@ int pm_genpd_add_subdomain(struct generic_pm_domain *genpd, } /** + * pm_genpd_add_subdomain_names - Add a subdomain to an I/O PM domain. + * @master_name: Name of the master PM domain to add the subdomain to. + * @subdomain_name: Name of the subdomain to be added. + */ +int pm_genpd_add_subdomain_names(const char *master_name, + const char *subdomain_name) +{ + struct generic_pm_domain *master = NULL, *subdomain = NULL, *gpd; + + if (IS_ERR_OR_NULL(master_name) || IS_ERR_OR_NULL(subdomain_name)) + return -EINVAL; + + mutex_lock(&gpd_list_lock); + list_for_each_entry(gpd, &gpd_list, gpd_list_node) { + if (!master && !strcmp(gpd->name, master_name)) + master = gpd; + + if (!subdomain && !strcmp(gpd->name, subdomain_name)) + subdomain = gpd; + + if (master && subdomain) + break; + } + mutex_unlock(&gpd_list_lock); + + return pm_genpd_add_subdomain(master, subdomain); +} + +/** * pm_genpd_remove_subdomain - Remove a subdomain from an I/O PM domain. * @genpd: Master PM domain to remove the subdomain from. * @subdomain: Subdomain to be removed. @@ -1704,7 +1829,16 @@ int __pm_genpd_remove_callbacks(struct device *dev, bool clear_td) } EXPORT_SYMBOL_GPL(__pm_genpd_remove_callbacks); -int genpd_attach_cpuidle(struct generic_pm_domain *genpd, int state) +/** + * pm_genpd_attach_cpuidle - Connect the given PM domain with cpuidle. + * @genpd: PM domain to be connected with cpuidle. + * @state: cpuidle state this domain can disable/enable. + * + * Make a PM domain behave as though it contained a CPU core, that is, instead + * of calling its power down routine it will enable the given cpuidle state so + * that the cpuidle subsystem can power it down (if possible and desirable). + */ +int pm_genpd_attach_cpuidle(struct generic_pm_domain *genpd, int state) { struct cpuidle_driver *cpuidle_drv; struct gpd_cpu_data *cpu_data; @@ -1753,7 +1887,24 @@ int genpd_attach_cpuidle(struct generic_pm_domain *genpd, int state) goto out; } -int genpd_detach_cpuidle(struct generic_pm_domain *genpd) +/** + * pm_genpd_name_attach_cpuidle - Find PM domain and connect cpuidle to it. + * @name: Name of the domain to connect to cpuidle. + * @state: cpuidle state this domain can manipulate. + */ +int pm_genpd_name_attach_cpuidle(const char *name, int state) +{ + return pm_genpd_attach_cpuidle(pm_genpd_lookup_name(name), state); +} + +/** + * pm_genpd_detach_cpuidle - Remove the cpuidle connection from a PM domain. + * @genpd: PM domain to remove the cpuidle connection from. + * + * Remove the cpuidle connection set up by pm_genpd_attach_cpuidle() from the + * given PM domain. + */ +int pm_genpd_detach_cpuidle(struct generic_pm_domain *genpd) { struct gpd_cpu_data *cpu_data; struct cpuidle_state *idle_state; @@ -1784,6 +1935,15 @@ int genpd_detach_cpuidle(struct generic_pm_domain *genpd) return ret; } +/** + * pm_genpd_name_detach_cpuidle - Find PM domain and disconnect cpuidle from it. + * @name: Name of the domain to disconnect cpuidle from. + */ +int pm_genpd_name_detach_cpuidle(const char *name) +{ + return pm_genpd_detach_cpuidle(pm_genpd_lookup_name(name)); +} + /* Default device callbacks for generic PM domains. */ /** diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index b0b072a..a3c1404 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -57,20 +57,17 @@ static pm_message_t pm_transition; static int async_error; /** - * device_pm_init - Initialize the PM-related part of a device object. + * device_pm_sleep_init - Initialize system suspend-related device fields. * @dev: Device object being initialized. */ -void device_pm_init(struct device *dev) +void device_pm_sleep_init(struct device *dev) { dev->power.is_prepared = false; dev->power.is_suspended = false; init_completion(&dev->power.completion); complete_all(&dev->power.completion); dev->power.wakeup = NULL; - spin_lock_init(&dev->power.lock); - pm_runtime_init(dev); INIT_LIST_HEAD(&dev->power.entry); - dev->power.power_state = PMSG_INVALID; } /** @@ -408,6 +405,9 @@ static int device_resume_noirq(struct device *dev, pm_message_t state) TRACE_DEVICE(dev); TRACE_RESUME(0); + if (dev->power.syscore) + goto Out; + if (dev->pm_domain) { info = "noirq power domain "; callback = pm_noirq_op(&dev->pm_domain->ops, state); @@ -429,6 +429,7 @@ static int device_resume_noirq(struct device *dev, pm_message_t state) error = dpm_run_callback(callback, dev, state, info); + Out: TRACE_RESUME(error); return error; } @@ -486,6 +487,9 @@ static int device_resume_early(struct device *dev, pm_message_t state) TRACE_DEVICE(dev); TRACE_RESUME(0); + if (dev->power.syscore) + goto Out; + if (dev->pm_domain) { info = "early power domain "; callback = pm_late_early_op(&dev->pm_domain->ops, state); @@ -507,6 +511,7 @@ static int device_resume_early(struct device *dev, pm_message_t state) error = dpm_run_callback(callback, dev, state, info); + Out: TRACE_RESUME(error); return error; } @@ -565,11 +570,13 @@ static int device_resume(struct device *dev, pm_message_t state, bool async) pm_callback_t callback = NULL; char *info = NULL; int error = 0; - bool put = false; TRACE_DEVICE(dev); TRACE_RESUME(0); + if (dev->power.syscore) + goto Complete; + dpm_wait(dev->parent, async); device_lock(dev); @@ -583,7 +590,6 @@ static int device_resume(struct device *dev, pm_message_t state, bool async) goto Unlock; pm_runtime_enable(dev); - put = true; if (dev->pm_domain) { info = "power domain "; @@ -632,13 +638,12 @@ static int device_resume(struct device *dev, pm_message_t state, bool async) Unlock: device_unlock(dev); + + Complete: complete_all(&dev->power.completion); TRACE_RESUME(error); - if (put) - pm_runtime_put_sync(dev); - return error; } @@ -722,6 +727,9 @@ static void device_complete(struct device *dev, pm_message_t state) void (*callback)(struct device *) = NULL; char *info = NULL; + if (dev->power.syscore) + return; + device_lock(dev); if (dev->pm_domain) { @@ -749,6 +757,8 @@ static void device_complete(struct device *dev, pm_message_t state) } device_unlock(dev); + + pm_runtime_put_sync(dev); } /** @@ -834,6 +844,9 @@ static int device_suspend_noirq(struct device *dev, pm_message_t state) pm_callback_t callback = NULL; char *info = NULL; + if (dev->power.syscore) + return 0; + if (dev->pm_domain) { info = "noirq power domain "; callback = pm_noirq_op(&dev->pm_domain->ops, state); @@ -917,6 +930,9 @@ static int device_suspend_late(struct device *dev, pm_message_t state) pm_callback_t callback = NULL; char *info = NULL; + if (dev->power.syscore) + return 0; + if (dev->pm_domain) { info = "late power domain "; callback = pm_late_early_op(&dev->pm_domain->ops, state); @@ -996,7 +1012,7 @@ int dpm_suspend_end(pm_message_t state) error = dpm_suspend_noirq(state); if (error) { - dpm_resume_early(state); + dpm_resume_early(resume_event(state)); return error; } @@ -1043,16 +1059,23 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async) if (async_error) goto Complete; - pm_runtime_get_noresume(dev); + /* + * If a device configured to wake up the system from sleep states + * has been suspended at run time and there's a resume request pending + * for it, this is equivalent to the device signaling wakeup, so the + * system suspend operation should be aborted. + */ if (pm_runtime_barrier(dev) && device_may_wakeup(dev)) pm_wakeup_event(dev, 0); if (pm_wakeup_pending()) { - pm_runtime_put_sync(dev); async_error = -EBUSY; goto Complete; } + if (dev->power.syscore) + goto Complete; + device_lock(dev); if (dev->pm_domain) { @@ -1111,12 +1134,10 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async) Complete: complete_all(&dev->power.completion); - if (error) { - pm_runtime_put_sync(dev); + if (error) async_error = error; - } else if (dev->power.is_suspended) { + else if (dev->power.is_suspended) __pm_runtime_disable(dev, false); - } return error; } @@ -1209,6 +1230,17 @@ static int device_prepare(struct device *dev, pm_message_t state) char *info = NULL; int error = 0; + if (dev->power.syscore) + return 0; + + /* + * If a device's parent goes into runtime suspend at the wrong time, + * it won't be possible to resume the device. To prevent this we + * block runtime suspend here, during the prepare phase, and allow + * it again during the complete phase. + */ + pm_runtime_get_noresume(dev); + device_lock(dev); dev->power.wakeup_path = device_may_wakeup(dev); diff --git a/drivers/base/power/opp.c b/drivers/base/power/opp.c index ac993ea..d946864 100644 --- a/drivers/base/power/opp.c +++ b/drivers/base/power/opp.c @@ -22,6 +22,7 @@ #include <linux/rculist.h> #include <linux/rcupdate.h> #include <linux/opp.h> +#include <linux/of.h> /* * Internal data structure organization with the OPP layer library is as @@ -674,3 +675,49 @@ struct srcu_notifier_head *opp_get_notifier(struct device *dev) return &dev_opp->head; } + +#ifdef CONFIG_OF +/** + * of_init_opp_table() - Initialize opp table from device tree + * @dev: device pointer used to lookup device OPPs. + * + * Register the initial OPP table with the OPP library for given device. + */ +int of_init_opp_table(struct device *dev) +{ + const struct property *prop; + const __be32 *val; + int nr; + + prop = of_find_property(dev->of_node, "operating-points", NULL); + if (!prop) + return -ENODEV; + if (!prop->value) + return -ENODATA; + + /* + * Each OPP is a set of tuples consisting of frequency and + * voltage like <freq-kHz vol-uV>. + */ + nr = prop->length / sizeof(u32); + if (nr % 2) { + dev_err(dev, "%s: Invalid OPP list\n", __func__); + return -EINVAL; + } + + val = prop->value; + while (nr) { + unsigned long freq = be32_to_cpup(val++) * 1000; + unsigned long volt = be32_to_cpup(val++); + + if (opp_add(dev, freq, volt)) { + dev_warn(dev, "%s: Failed to add OPP %ld\n", + __func__, freq); + continue; + } + nr -= 2; + } + + return 0; +} +#endif diff --git a/drivers/base/power/power.h b/drivers/base/power/power.h index eeb4bff..0dbfdf4 100644 --- a/drivers/base/power/power.h +++ b/drivers/base/power/power.h @@ -1,12 +1,32 @@ #include <linux/pm_qos.h> +static inline void device_pm_init_common(struct device *dev) +{ + if (!dev->power.early_init) { + spin_lock_init(&dev->power.lock); + dev->power.power_state = PMSG_INVALID; + dev->power.early_init = true; + } +} + #ifdef CONFIG_PM_RUNTIME +static inline void pm_runtime_early_init(struct device *dev) +{ + dev->power.disable_depth = 1; + device_pm_init_common(dev); +} + extern void pm_runtime_init(struct device *dev); extern void pm_runtime_remove(struct device *dev); #else /* !CONFIG_PM_RUNTIME */ +static inline void pm_runtime_early_init(struct device *dev) +{ + device_pm_init_common(dev); +} + static inline void pm_runtime_init(struct device *dev) {} static inline void pm_runtime_remove(struct device *dev) {} @@ -25,7 +45,7 @@ static inline struct device *to_device(struct list_head *entry) return container_of(entry, struct device, power.entry); } -extern void device_pm_init(struct device *dev); +extern void device_pm_sleep_init(struct device *dev); extern void device_pm_add(struct device *); extern void device_pm_remove(struct device *); extern void device_pm_move_before(struct device *, struct device *); @@ -34,12 +54,7 @@ extern void device_pm_move_last(struct device *); #else /* !CONFIG_PM_SLEEP */ -static inline void device_pm_init(struct device *dev) -{ - spin_lock_init(&dev->power.lock); - dev->power.power_state = PMSG_INVALID; - pm_runtime_init(dev); -} +static inline void device_pm_sleep_init(struct device *dev) {} static inline void device_pm_add(struct device *dev) { @@ -60,6 +75,13 @@ static inline void device_pm_move_last(struct device *dev) {} #endif /* !CONFIG_PM_SLEEP */ +static inline void device_pm_init(struct device *dev) +{ + device_pm_init_common(dev); + device_pm_sleep_init(dev); + pm_runtime_init(dev); +} + #ifdef CONFIG_PM /* diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index 7d9c1cb..3148b10 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -509,6 +509,9 @@ static int rpm_resume(struct device *dev, int rpmflags) repeat: if (dev->power.runtime_error) retval = -EINVAL; + else if (dev->power.disable_depth == 1 && dev->power.is_suspended + && dev->power.runtime_status == RPM_ACTIVE) + retval = 1; else if (dev->power.disable_depth > 0) retval = -EACCES; if (retval) diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c index cbb463b..e6ee5e8 100644 --- a/drivers/base/power/wakeup.c +++ b/drivers/base/power/wakeup.c @@ -127,6 +127,8 @@ EXPORT_SYMBOL_GPL(wakeup_source_destroy); */ void wakeup_source_add(struct wakeup_source *ws) { + unsigned long flags; + if (WARN_ON(!ws)) return; @@ -135,9 +137,9 @@ void wakeup_source_add(struct wakeup_source *ws) ws->active = false; ws->last_time = ktime_get(); - spin_lock_irq(&events_lock); + spin_lock_irqsave(&events_lock, flags); list_add_rcu(&ws->entry, &wakeup_sources); - spin_unlock_irq(&events_lock); + spin_unlock_irqrestore(&events_lock, flags); } EXPORT_SYMBOL_GPL(wakeup_source_add); @@ -147,12 +149,14 @@ EXPORT_SYMBOL_GPL(wakeup_source_add); */ void wakeup_source_remove(struct wakeup_source *ws) { + unsigned long flags; + if (WARN_ON(!ws)) return; - spin_lock_irq(&events_lock); + spin_lock_irqsave(&events_lock, flags); list_del_rcu(&ws->entry); - spin_unlock_irq(&events_lock); + spin_unlock_irqrestore(&events_lock, flags); synchronize_rcu(); } EXPORT_SYMBOL_GPL(wakeup_source_remove); @@ -649,6 +653,31 @@ void pm_wakeup_event(struct device *dev, unsigned int msec) } EXPORT_SYMBOL_GPL(pm_wakeup_event); +static void print_active_wakeup_sources(void) +{ + struct wakeup_source *ws; + int active = 0; + struct wakeup_source *last_activity_ws = NULL; + + rcu_read_lock(); + list_for_each_entry_rcu(ws, &wakeup_sources, entry) { + if (ws->active) { + pr_info("active wakeup source: %s\n", ws->name); + active = 1; + } else if (!active && + (!last_activity_ws || + ktime_to_ns(ws->last_time) > + ktime_to_ns(last_activity_ws->last_time))) { + last_activity_ws = ws; + } + } + + if (!active && last_activity_ws) + pr_info("last active wakeup source: %s\n", + last_activity_ws->name); + rcu_read_unlock(); +} + /** * pm_wakeup_pending - Check if power transition in progress should be aborted. * @@ -671,6 +700,10 @@ bool pm_wakeup_pending(void) events_check_enabled = !ret; } spin_unlock_irqrestore(&events_lock, flags); + + if (ret) + print_active_wakeup_sources(); + return ret; } @@ -723,15 +756,16 @@ bool pm_get_wakeup_count(unsigned int *count, bool block) bool pm_save_wakeup_count(unsigned int count) { unsigned int cnt, inpr; + unsigned long flags; events_check_enabled = false; - spin_lock_irq(&events_lock); + spin_lock_irqsave(&events_lock, flags); split_counters(&cnt, &inpr); if (cnt == count && inpr == 0) { saved_count = count; events_check_enabled = true; } - spin_unlock_irq(&events_lock); + spin_unlock_irqrestore(&events_lock, flags); return events_check_enabled; } diff --git a/drivers/clocksource/sh_cmt.c b/drivers/clocksource/sh_cmt.c index 98b06ba..a5f7829 100644 --- a/drivers/clocksource/sh_cmt.c +++ b/drivers/clocksource/sh_cmt.c @@ -33,6 +33,7 @@ #include <linux/slab.h> #include <linux/module.h> #include <linux/pm_domain.h> +#include <linux/pm_runtime.h> struct sh_cmt_priv { void __iomem *mapbase; @@ -52,6 +53,7 @@ struct sh_cmt_priv { struct clock_event_device ced; struct clocksource cs; unsigned long total_cycles; + bool cs_enabled; }; static DEFINE_RAW_SPINLOCK(sh_cmt_lock); @@ -155,6 +157,9 @@ static int sh_cmt_enable(struct sh_cmt_priv *p, unsigned long *rate) { int k, ret; + pm_runtime_get_sync(&p->pdev->dev); + dev_pm_syscore_device(&p->pdev->dev, true); + /* enable clock */ ret = clk_enable(p->clk); if (ret) { @@ -221,6 +226,9 @@ static void sh_cmt_disable(struct sh_cmt_priv *p) /* stop clock */ clk_disable(p->clk); + + dev_pm_syscore_device(&p->pdev->dev, false); + pm_runtime_put(&p->pdev->dev); } /* private flags */ @@ -451,22 +459,42 @@ static int sh_cmt_clocksource_enable(struct clocksource *cs) int ret; struct sh_cmt_priv *p = cs_to_sh_cmt(cs); + WARN_ON(p->cs_enabled); + p->total_cycles = 0; ret = sh_cmt_start(p, FLAG_CLOCKSOURCE); - if (!ret) + if (!ret) { __clocksource_updatefreq_hz(cs, p->rate); + p->cs_enabled = true; + } return ret; } static void sh_cmt_clocksource_disable(struct clocksource *cs) { - sh_cmt_stop(cs_to_sh_cmt(cs), FLAG_CLOCKSOURCE); + struct sh_cmt_priv *p = cs_to_sh_cmt(cs); + + WARN_ON(!p->cs_enabled); + + sh_cmt_stop(p, FLAG_CLOCKSOURCE); + p->cs_enabled = false; +} + +static void sh_cmt_clocksource_suspend(struct clocksource *cs) +{ + struct sh_cmt_priv *p = cs_to_sh_cmt(cs); + + sh_cmt_stop(p, FLAG_CLOCKSOURCE); + pm_genpd_syscore_poweroff(&p->pdev->dev); } static void sh_cmt_clocksource_resume(struct clocksource *cs) { - sh_cmt_start(cs_to_sh_cmt(cs), FLAG_CLOCKSOURCE); + struct sh_cmt_priv *p = cs_to_sh_cmt(cs); + + pm_genpd_syscore_poweron(&p->pdev->dev); + sh_cmt_start(p, FLAG_CLOCKSOURCE); } static int sh_cmt_register_clocksource(struct sh_cmt_priv *p, @@ -479,7 +507,7 @@ static int sh_cmt_register_clocksource(struct sh_cmt_priv *p, cs->read = sh_cmt_clocksource_read; cs->enable = sh_cmt_clocksource_enable; cs->disable = sh_cmt_clocksource_disable; - cs->suspend = sh_cmt_clocksource_disable; + cs->suspend = sh_cmt_clocksource_suspend; cs->resume = sh_cmt_clocksource_resume; cs->mask = CLOCKSOURCE_MASK(sizeof(unsigned long) * 8); cs->flags = CLOCK_SOURCE_IS_CONTINUOUS; @@ -562,6 +590,16 @@ static int sh_cmt_clock_event_next(unsigned long delta, return 0; } +static void sh_cmt_clock_event_suspend(struct clock_event_device *ced) +{ + pm_genpd_syscore_poweroff(&ced_to_sh_cmt(ced)->pdev->dev); +} + +static void sh_cmt_clock_event_resume(struct clock_event_device *ced) +{ + pm_genpd_syscore_poweron(&ced_to_sh_cmt(ced)->pdev->dev); +} + static void sh_cmt_register_clockevent(struct sh_cmt_priv *p, char *name, unsigned long rating) { @@ -576,6 +614,8 @@ static void sh_cmt_register_clockevent(struct sh_cmt_priv *p, ced->cpumask = cpumask_of(0); ced->set_next_event = sh_cmt_clock_event_next; ced->set_mode = sh_cmt_clock_event_mode; + ced->suspend = sh_cmt_clock_event_suspend; + ced->resume = sh_cmt_clock_event_resume; dev_info(&p->pdev->dev, "used for clock events\n"); clockevents_register_device(ced); @@ -670,6 +710,7 @@ static int sh_cmt_setup(struct sh_cmt_priv *p, struct platform_device *pdev) dev_err(&p->pdev->dev, "registration failed\n"); goto err1; } + p->cs_enabled = false; ret = setup_irq(irq, &p->irqaction); if (ret) { @@ -688,14 +729,17 @@ err0: static int __devinit sh_cmt_probe(struct platform_device *pdev) { struct sh_cmt_priv *p = platform_get_drvdata(pdev); + struct sh_timer_config *cfg = pdev->dev.platform_data; int ret; - if (!is_early_platform_device(pdev)) - pm_genpd_dev_always_on(&pdev->dev, true); + if (!is_early_platform_device(pdev)) { + pm_runtime_set_active(&pdev->dev); + pm_runtime_enable(&pdev->dev); + } if (p) { dev_info(&pdev->dev, "kept as earlytimer\n"); - return 0; + goto out; } p = kmalloc(sizeof(*p), GFP_KERNEL); @@ -708,8 +752,19 @@ static int __devinit sh_cmt_probe(struct platform_device *pdev) if (ret) { kfree(p); platform_set_drvdata(pdev, NULL); + pm_runtime_idle(&pdev->dev); + return ret; } - return ret; + if (is_early_platform_device(pdev)) + return 0; + + out: + if (cfg->clockevent_rating || cfg->clocksource_rating) + pm_runtime_irq_safe(&pdev->dev); + else + pm_runtime_idle(&pdev->dev); + + return 0; } static int __devexit sh_cmt_remove(struct platform_device *pdev) diff --git a/drivers/clocksource/sh_mtu2.c b/drivers/clocksource/sh_mtu2.c index d9b76ca..c5eea85 100644 --- a/drivers/clocksource/sh_mtu2.c +++ b/drivers/clocksource/sh_mtu2.c @@ -32,6 +32,7 @@ #include <linux/slab.h> #include <linux/module.h> #include <linux/pm_domain.h> +#include <linux/pm_runtime.h> struct sh_mtu2_priv { void __iomem *mapbase; @@ -123,6 +124,9 @@ static int sh_mtu2_enable(struct sh_mtu2_priv *p) { int ret; + pm_runtime_get_sync(&p->pdev->dev); + dev_pm_syscore_device(&p->pdev->dev, true); + /* enable clock */ ret = clk_enable(p->clk); if (ret) { @@ -157,6 +161,9 @@ static void sh_mtu2_disable(struct sh_mtu2_priv *p) /* stop clock */ clk_disable(p->clk); + + dev_pm_syscore_device(&p->pdev->dev, false); + pm_runtime_put(&p->pdev->dev); } static irqreturn_t sh_mtu2_interrupt(int irq, void *dev_id) @@ -208,6 +215,16 @@ static void sh_mtu2_clock_event_mode(enum clock_event_mode mode, } } +static void sh_mtu2_clock_event_suspend(struct clock_event_device *ced) +{ + pm_genpd_syscore_poweroff(&ced_to_sh_mtu2(ced)->pdev->dev); +} + +static void sh_mtu2_clock_event_resume(struct clock_event_device *ced) +{ + pm_genpd_syscore_poweron(&ced_to_sh_mtu2(ced)->pdev->dev); +} + static void sh_mtu2_register_clockevent(struct sh_mtu2_priv *p, char *name, unsigned long rating) { @@ -221,6 +238,8 @@ static void sh_mtu2_register_clockevent(struct sh_mtu2_priv *p, ced->rating = rating; ced->cpumask = cpumask_of(0); ced->set_mode = sh_mtu2_clock_event_mode; + ced->suspend = sh_mtu2_clock_event_suspend; + ced->resume = sh_mtu2_clock_event_resume; dev_info(&p->pdev->dev, "used for clock events\n"); clockevents_register_device(ced); @@ -305,14 +324,17 @@ static int sh_mtu2_setup(struct sh_mtu2_priv *p, struct platform_device *pdev) static int __devinit sh_mtu2_probe(struct platform_device *pdev) { struct sh_mtu2_priv *p = platform_get_drvdata(pdev); + struct sh_timer_config *cfg = pdev->dev.platform_data; int ret; - if (!is_early_platform_device(pdev)) - pm_genpd_dev_always_on(&pdev->dev, true); + if (!is_early_platform_device(pdev)) { + pm_runtime_set_active(&pdev->dev); + pm_runtime_enable(&pdev->dev); + } if (p) { dev_info(&pdev->dev, "kept as earlytimer\n"); - return 0; + goto out; } p = kmalloc(sizeof(*p), GFP_KERNEL); @@ -325,8 +347,19 @@ static int __devinit sh_mtu2_probe(struct platform_device *pdev) if (ret) { kfree(p); platform_set_drvdata(pdev, NULL); + pm_runtime_idle(&pdev->dev); + return ret; } - return ret; + if (is_early_platform_device(pdev)) + return 0; + + out: + if (cfg->clockevent_rating) + pm_runtime_irq_safe(&pdev->dev); + else + pm_runtime_idle(&pdev->dev); + + return 0; } static int __devexit sh_mtu2_remove(struct platform_device *pdev) diff --git a/drivers/clocksource/sh_tmu.c b/drivers/clocksource/sh_tmu.c index c1b51d4..0cc4add 100644 --- a/drivers/clocksource/sh_tmu.c +++ b/drivers/clocksource/sh_tmu.c @@ -33,6 +33,7 @@ #include <linux/slab.h> #include <linux/module.h> #include <linux/pm_domain.h> +#include <linux/pm_runtime.h> struct sh_tmu_priv { void __iomem *mapbase; @@ -43,6 +44,8 @@ struct sh_tmu_priv { unsigned long periodic; struct clock_event_device ced; struct clocksource cs; + bool cs_enabled; + unsigned int enable_count; }; static DEFINE_RAW_SPINLOCK(sh_tmu_lock); @@ -107,7 +110,7 @@ static void sh_tmu_start_stop_ch(struct sh_tmu_priv *p, int start) raw_spin_unlock_irqrestore(&sh_tmu_lock, flags); } -static int sh_tmu_enable(struct sh_tmu_priv *p) +static int __sh_tmu_enable(struct sh_tmu_priv *p) { int ret; @@ -135,7 +138,18 @@ static int sh_tmu_enable(struct sh_tmu_priv *p) return 0; } -static void sh_tmu_disable(struct sh_tmu_priv *p) +static int sh_tmu_enable(struct sh_tmu_priv *p) +{ + if (p->enable_count++ > 0) + return 0; + + pm_runtime_get_sync(&p->pdev->dev); + dev_pm_syscore_device(&p->pdev->dev, true); + + return __sh_tmu_enable(p); +} + +static void __sh_tmu_disable(struct sh_tmu_priv *p) { /* disable channel */ sh_tmu_start_stop_ch(p, 0); @@ -147,6 +161,20 @@ static void sh_tmu_disable(struct sh_tmu_priv *p) clk_disable(p->clk); } +static void sh_tmu_disable(struct sh_tmu_priv *p) +{ + if (WARN_ON(p->enable_count == 0)) + return; + + if (--p->enable_count > 0) + return; + + __sh_tmu_disable(p); + + dev_pm_syscore_device(&p->pdev->dev, false); + pm_runtime_put(&p->pdev->dev); +} + static void sh_tmu_set_next(struct sh_tmu_priv *p, unsigned long delta, int periodic) { @@ -203,15 +231,53 @@ static int sh_tmu_clocksource_enable(struct clocksource *cs) struct sh_tmu_priv *p = cs_to_sh_tmu(cs); int ret; + if (WARN_ON(p->cs_enabled)) + return 0; + ret = sh_tmu_enable(p); - if (!ret) + if (!ret) { __clocksource_updatefreq_hz(cs, p->rate); + p->cs_enabled = true; + } + return ret; } static void sh_tmu_clocksource_disable(struct clocksource *cs) { - sh_tmu_disable(cs_to_sh_tmu(cs)); + struct sh_tmu_priv *p = cs_to_sh_tmu(cs); + + if (WARN_ON(!p->cs_enabled)) + return; + + sh_tmu_disable(p); + p->cs_enabled = false; +} + +static void sh_tmu_clocksource_suspend(struct clocksource *cs) +{ + struct sh_tmu_priv *p = cs_to_sh_tmu(cs); + + if (!p->cs_enabled) + return; + + if (--p->enable_count == 0) { + __sh_tmu_disable(p); + pm_genpd_syscore_poweroff(&p->pdev->dev); + } +} + +static void sh_tmu_clocksource_resume(struct clocksource *cs) +{ + struct sh_tmu_priv *p = cs_to_sh_tmu(cs); + + if (!p->cs_enabled) + return; + + if (p->enable_count++ == 0) { + pm_genpd_syscore_poweron(&p->pdev->dev); + __sh_tmu_enable(p); + } } static int sh_tmu_register_clocksource(struct sh_tmu_priv *p, @@ -224,6 +290,8 @@ static int sh_tmu_register_clocksource(struct sh_tmu_priv *p, cs->read = sh_tmu_clocksource_read; cs->enable = sh_tmu_clocksource_enable; cs->disable = sh_tmu_clocksource_disable; + cs->suspend = sh_tmu_clocksource_suspend; + cs->resume = sh_tmu_clocksource_resume; cs->mask = CLOCKSOURCE_MASK(32); cs->flags = CLOCK_SOURCE_IS_CONTINUOUS; @@ -301,6 +369,16 @@ static int sh_tmu_clock_event_next(unsigned long delta, return 0; } +static void sh_tmu_clock_event_suspend(struct clock_event_device *ced) +{ + pm_genpd_syscore_poweroff(&ced_to_sh_tmu(ced)->pdev->dev); +} + +static void sh_tmu_clock_event_resume(struct clock_event_device *ced) +{ + pm_genpd_syscore_poweron(&ced_to_sh_tmu(ced)->pdev->dev); +} + static void sh_tmu_register_clockevent(struct sh_tmu_priv *p, char *name, unsigned long rating) { @@ -316,6 +394,8 @@ static void sh_tmu_register_clockevent(struct sh_tmu_priv *p, ced->cpumask = cpumask_of(0); ced->set_next_event = sh_tmu_clock_event_next; ced->set_mode = sh_tmu_clock_event_mode; + ced->suspend = sh_tmu_clock_event_suspend; + ced->resume = sh_tmu_clock_event_resume; dev_info(&p->pdev->dev, "used for clock events\n"); @@ -392,6 +472,8 @@ static int sh_tmu_setup(struct sh_tmu_priv *p, struct platform_device *pdev) ret = PTR_ERR(p->clk); goto err1; } + p->cs_enabled = false; + p->enable_count = 0; return sh_tmu_register(p, (char *)dev_name(&p->pdev->dev), cfg->clockevent_rating, @@ -405,14 +487,17 @@ static int sh_tmu_setup(struct sh_tmu_priv *p, struct platform_device *pdev) static int __devinit sh_tmu_probe(struct platform_device *pdev) { struct sh_tmu_priv *p = platform_get_drvdata(pdev); + struct sh_timer_config *cfg = pdev->dev.platform_data; int ret; - if (!is_early_platform_device(pdev)) - pm_genpd_dev_always_on(&pdev->dev, true); + if (!is_early_platform_device(pdev)) { + pm_runtime_set_active(&pdev->dev); + pm_runtime_enable(&pdev->dev); + } if (p) { dev_info(&pdev->dev, "kept as earlytimer\n"); - return 0; + goto out; } p = kmalloc(sizeof(*p), GFP_KERNEL); @@ -425,8 +510,19 @@ static int __devinit sh_tmu_probe(struct platform_device *pdev) if (ret) { kfree(p); platform_set_drvdata(pdev, NULL); + pm_runtime_idle(&pdev->dev); + return ret; } - return ret; + if (is_early_platform_device(pdev)) + return 0; + + out: + if (cfg->clockevent_rating || cfg->clocksource_rating) + pm_runtime_irq_safe(&pdev->dev); + else + pm_runtime_idle(&pdev->dev); + + return 0; } static int __devexit sh_tmu_remove(struct platform_device *pdev) diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig index e24a2a1..ea512f4 100644 --- a/drivers/cpufreq/Kconfig +++ b/drivers/cpufreq/Kconfig @@ -179,6 +179,17 @@ config CPU_FREQ_GOV_CONSERVATIVE If in doubt, say N. +config GENERIC_CPUFREQ_CPU0 + bool "Generic CPU0 cpufreq driver" + depends on HAVE_CLK && REGULATOR && PM_OPP && OF + select CPU_FREQ_TABLE + help + This adds a generic cpufreq driver for CPU0 frequency management. + It supports both uniprocessor (UP) and symmetric multiprocessor (SMP) + systems which share clock and voltage across all CPUs. + + If in doubt, say N. + menu "x86 CPU frequency scaling drivers" depends on X86 source "drivers/cpufreq/Kconfig.x86" diff --git a/drivers/cpufreq/Kconfig.x86 b/drivers/cpufreq/Kconfig.x86 index 78ff7ee..934854a 100644 --- a/drivers/cpufreq/Kconfig.x86 +++ b/drivers/cpufreq/Kconfig.x86 @@ -23,7 +23,8 @@ config X86_ACPI_CPUFREQ help This driver adds a CPUFreq driver which utilizes the ACPI Processor Performance States. - This driver also supports Intel Enhanced Speedstep. + This driver also supports Intel Enhanced Speedstep and newer + AMD CPUs. To compile this driver as a module, choose M here: the module will be called acpi-cpufreq. @@ -32,6 +33,18 @@ config X86_ACPI_CPUFREQ If in doubt, say N. +config X86_ACPI_CPUFREQ_CPB + default y + bool "Legacy cpb sysfs knob support for AMD CPUs" + depends on X86_ACPI_CPUFREQ && CPU_SUP_AMD + help + The powernow-k8 driver used to provide a sysfs knob called "cpb" + to disable the Core Performance Boosting feature of AMD CPUs. This + file has now been superseeded by the more generic "boost" entry. + + By enabling this option the acpi_cpufreq driver provides the old + entry in addition to the new boost ones, for compatibility reasons. + config ELAN_CPUFREQ tristate "AMD Elan SC400 and SC410" select CPU_FREQ_TABLE @@ -95,7 +108,8 @@ config X86_POWERNOW_K8 select CPU_FREQ_TABLE depends on ACPI && ACPI_PROCESSOR help - This adds the CPUFreq driver for K8/K10 Opteron/Athlon64 processors. + This adds the CPUFreq driver for K8/early Opteron/Athlon64 processors. + Support for K10 and newer processors is now in acpi-cpufreq. To compile this driver as a module, choose M here: the module will be called powernow-k8. diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile index 9531fc2..1bc90e1 100644 --- a/drivers/cpufreq/Makefile +++ b/drivers/cpufreq/Makefile @@ -13,13 +13,15 @@ obj-$(CONFIG_CPU_FREQ_GOV_CONSERVATIVE) += cpufreq_conservative.o # CPUfreq cross-arch helpers obj-$(CONFIG_CPU_FREQ_TABLE) += freq_table.o +obj-$(CONFIG_GENERIC_CPUFREQ_CPU0) += cpufreq-cpu0.o + ################################################################################## # x86 drivers. # Link order matters. K8 is preferred to ACPI because of firmware bugs in early # K8 systems. ACPI is preferred to all other hardware-specific drivers. # speedstep-* is preferred over p4-clockmod. -obj-$(CONFIG_X86_POWERNOW_K8) += powernow-k8.o mperf.o +obj-$(CONFIG_X86_POWERNOW_K8) += powernow-k8.o obj-$(CONFIG_X86_ACPI_CPUFREQ) += acpi-cpufreq.o mperf.o obj-$(CONFIG_X86_PCC_CPUFREQ) += pcc-cpufreq.o obj-$(CONFIG_X86_POWERNOW_K6) += powernow-k6.o diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c index 56c6c6b..0d048f6 100644 --- a/drivers/cpufreq/acpi-cpufreq.c +++ b/drivers/cpufreq/acpi-cpufreq.c @@ -51,13 +51,19 @@ MODULE_AUTHOR("Paul Diefenbaugh, Dominik Brodowski"); MODULE_DESCRIPTION("ACPI Processor P-States Driver"); MODULE_LICENSE("GPL"); +#define PFX "acpi-cpufreq: " + enum { UNDEFINED_CAPABLE = 0, SYSTEM_INTEL_MSR_CAPABLE, + SYSTEM_AMD_MSR_CAPABLE, SYSTEM_IO_CAPABLE, }; #define INTEL_MSR_RANGE (0xffff) +#define AMD_MSR_RANGE (0x7) + +#define MSR_K7_HWCR_CPB_DIS (1ULL << 25) struct acpi_cpufreq_data { struct acpi_processor_performance *acpi_data; @@ -74,6 +80,116 @@ static struct acpi_processor_performance __percpu *acpi_perf_data; static struct cpufreq_driver acpi_cpufreq_driver; static unsigned int acpi_pstate_strict; +static bool boost_enabled, boost_supported; +static struct msr __percpu *msrs; + +static bool boost_state(unsigned int cpu) +{ + u32 lo, hi; + u64 msr; + + switch (boot_cpu_data.x86_vendor) { + case X86_VENDOR_INTEL: + rdmsr_on_cpu(cpu, MSR_IA32_MISC_ENABLE, &lo, &hi); + msr = lo | ((u64)hi << 32); + return !(msr & MSR_IA32_MISC_ENABLE_TURBO_DISABLE); + case X86_VENDOR_AMD: + rdmsr_on_cpu(cpu, MSR_K7_HWCR, &lo, &hi); + msr = lo | ((u64)hi << 32); + return !(msr & MSR_K7_HWCR_CPB_DIS); + } + return false; +} + +static void boost_set_msrs(bool enable, const struct cpumask *cpumask) +{ + u32 cpu; + u32 msr_addr; + u64 msr_mask; + + switch (boot_cpu_data.x86_vendor) { + case X86_VENDOR_INTEL: + msr_addr = MSR_IA32_MISC_ENABLE; + msr_mask = MSR_IA32_MISC_ENABLE_TURBO_DISABLE; + break; + case X86_VENDOR_AMD: + msr_addr = MSR_K7_HWCR; + msr_mask = MSR_K7_HWCR_CPB_DIS; + break; + default: + return; + } + + rdmsr_on_cpus(cpumask, msr_addr, msrs); + + for_each_cpu(cpu, cpumask) { + struct msr *reg = per_cpu_ptr(msrs, cpu); + if (enable) + reg->q &= ~msr_mask; + else + reg->q |= msr_mask; + } + + wrmsr_on_cpus(cpumask, msr_addr, msrs); +} + +static ssize_t _store_boost(const char *buf, size_t count) +{ + int ret; + unsigned long val = 0; + + if (!boost_supported) + return -EINVAL; + + ret = kstrtoul(buf, 10, &val); + if (ret || (val > 1)) + return -EINVAL; + + if ((val && boost_enabled) || (!val && !boost_enabled)) + return count; + + get_online_cpus(); + + boost_set_msrs(val, cpu_online_mask); + + put_online_cpus(); + + boost_enabled = val; + pr_debug("Core Boosting %sabled.\n", val ? "en" : "dis"); + + return count; +} + +static ssize_t store_global_boost(struct kobject *kobj, struct attribute *attr, + const char *buf, size_t count) +{ + return _store_boost(buf, count); +} + +static ssize_t show_global_boost(struct kobject *kobj, + struct attribute *attr, char *buf) +{ + return sprintf(buf, "%u\n", boost_enabled); +} + +static struct global_attr global_boost = __ATTR(boost, 0644, + show_global_boost, + store_global_boost); + +#ifdef CONFIG_X86_ACPI_CPUFREQ_CPB +static ssize_t store_cpb(struct cpufreq_policy *policy, const char *buf, + size_t count) +{ + return _store_boost(buf, count); +} + +static ssize_t show_cpb(struct cpufreq_policy *policy, char *buf) +{ + return sprintf(buf, "%u\n", boost_enabled); +} + +static struct freq_attr cpb = __ATTR(cpb, 0644, show_cpb, store_cpb); +#endif static int check_est_cpu(unsigned int cpuid) { @@ -82,6 +198,13 @@ static int check_est_cpu(unsigned int cpuid) return cpu_has(cpu, X86_FEATURE_EST); } +static int check_amd_hwpstate_cpu(unsigned int cpuid) +{ + struct cpuinfo_x86 *cpu = &cpu_data(cpuid); + + return cpu_has(cpu, X86_FEATURE_HW_PSTATE); +} + static unsigned extract_io(u32 value, struct acpi_cpufreq_data *data) { struct acpi_processor_performance *perf; @@ -101,7 +224,11 @@ static unsigned extract_msr(u32 msr, struct acpi_cpufreq_data *data) int i; struct acpi_processor_performance *perf; - msr &= INTEL_MSR_RANGE; + if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) + msr &= AMD_MSR_RANGE; + else + msr &= INTEL_MSR_RANGE; + perf = data->acpi_data; for (i = 0; data->freq_table[i].frequency != CPUFREQ_TABLE_END; i++) { @@ -115,6 +242,7 @@ static unsigned extract_freq(u32 val, struct acpi_cpufreq_data *data) { switch (data->cpu_feature) { case SYSTEM_INTEL_MSR_CAPABLE: + case SYSTEM_AMD_MSR_CAPABLE: return extract_msr(val, data); case SYSTEM_IO_CAPABLE: return extract_io(val, data); @@ -150,6 +278,7 @@ static void do_drv_read(void *_cmd) switch (cmd->type) { case SYSTEM_INTEL_MSR_CAPABLE: + case SYSTEM_AMD_MSR_CAPABLE: rdmsr(cmd->addr.msr.reg, cmd->val, h); break; case SYSTEM_IO_CAPABLE: @@ -174,6 +303,9 @@ static void do_drv_write(void *_cmd) lo = (lo & ~INTEL_MSR_RANGE) | (cmd->val & INTEL_MSR_RANGE); wrmsr(cmd->addr.msr.reg, lo, hi); break; + case SYSTEM_AMD_MSR_CAPABLE: + wrmsr(cmd->addr.msr.reg, cmd->val, 0); + break; case SYSTEM_IO_CAPABLE: acpi_os_write_port((acpi_io_address)cmd->addr.io.port, cmd->val, @@ -217,6 +349,10 @@ static u32 get_cur_val(const struct cpumask *mask) cmd.type = SYSTEM_INTEL_MSR_CAPABLE; cmd.addr.msr.reg = MSR_IA32_PERF_STATUS; break; + case SYSTEM_AMD_MSR_CAPABLE: + cmd.type = SYSTEM_AMD_MSR_CAPABLE; + cmd.addr.msr.reg = MSR_AMD_PERF_STATUS; + break; case SYSTEM_IO_CAPABLE: cmd.type = SYSTEM_IO_CAPABLE; perf = per_cpu(acfreq_data, cpumask_first(mask))->acpi_data; @@ -326,6 +462,11 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy, cmd.addr.msr.reg = MSR_IA32_PERF_CTL; cmd.val = (u32) perf->states[next_perf_state].control; break; + case SYSTEM_AMD_MSR_CAPABLE: + cmd.type = SYSTEM_AMD_MSR_CAPABLE; + cmd.addr.msr.reg = MSR_AMD_PERF_CTL; + cmd.val = (u32) perf->states[next_perf_state].control; + break; case SYSTEM_IO_CAPABLE: cmd.type = SYSTEM_IO_CAPABLE; cmd.addr.io.port = perf->control_register.address; @@ -419,6 +560,44 @@ static void free_acpi_perf_data(void) free_percpu(acpi_perf_data); } +static int boost_notify(struct notifier_block *nb, unsigned long action, + void *hcpu) +{ + unsigned cpu = (long)hcpu; + const struct cpumask *cpumask; + + cpumask = get_cpu_mask(cpu); + + /* + * Clear the boost-disable bit on the CPU_DOWN path so that + * this cpu cannot block the remaining ones from boosting. On + * the CPU_UP path we simply keep the boost-disable flag in + * sync with the current global state. + */ + + switch (action) { + case CPU_UP_PREPARE: + case CPU_UP_PREPARE_FROZEN: + boost_set_msrs(boost_enabled, cpumask); + break; + + case CPU_DOWN_PREPARE: + case CPU_DOWN_PREPARE_FROZEN: + boost_set_msrs(1, cpumask); + break; + + default: + break; + } + + return NOTIFY_OK; +} + + +static struct notifier_block boost_nb = { + .notifier_call = boost_notify, +}; + /* * acpi_cpufreq_early_init - initialize ACPI P-States library * @@ -559,6 +738,14 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy) policy->shared_type = CPUFREQ_SHARED_TYPE_ALL; cpumask_copy(policy->cpus, cpu_core_mask(cpu)); } + + if (check_amd_hwpstate_cpu(cpu) && !acpi_pstate_strict) { + cpumask_clear(policy->cpus); + cpumask_set_cpu(cpu, policy->cpus); + cpumask_copy(policy->related_cpus, cpu_sibling_mask(cpu)); + policy->shared_type = CPUFREQ_SHARED_TYPE_HW; + pr_info_once(PFX "overriding BIOS provided _PSD data\n"); + } #endif /* capability check */ @@ -580,12 +767,16 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy) break; case ACPI_ADR_SPACE_FIXED_HARDWARE: pr_debug("HARDWARE addr space\n"); - if (!check_est_cpu(cpu)) { - result = -ENODEV; - goto err_unreg; + if (check_est_cpu(cpu)) { + data->cpu_feature = SYSTEM_INTEL_MSR_CAPABLE; + break; } - data->cpu_feature = SYSTEM_INTEL_MSR_CAPABLE; - break; + if (check_amd_hwpstate_cpu(cpu)) { + data->cpu_feature = SYSTEM_AMD_MSR_CAPABLE; + break; + } + result = -ENODEV; + goto err_unreg; default: pr_debug("Unknown addr space %d\n", (u32) (perf->control_register.space_id)); @@ -718,6 +909,7 @@ static int acpi_cpufreq_resume(struct cpufreq_policy *policy) static struct freq_attr *acpi_cpufreq_attr[] = { &cpufreq_freq_attr_scaling_available_freqs, + NULL, /* this is a placeholder for cpb, do not remove */ NULL, }; @@ -733,6 +925,49 @@ static struct cpufreq_driver acpi_cpufreq_driver = { .attr = acpi_cpufreq_attr, }; +static void __init acpi_cpufreq_boost_init(void) +{ + if (boot_cpu_has(X86_FEATURE_CPB) || boot_cpu_has(X86_FEATURE_IDA)) { + msrs = msrs_alloc(); + + if (!msrs) + return; + + boost_supported = true; + boost_enabled = boost_state(0); + + get_online_cpus(); + + /* Force all MSRs to the same value */ + boost_set_msrs(boost_enabled, cpu_online_mask); + + register_cpu_notifier(&boost_nb); + + put_online_cpus(); + } else + global_boost.attr.mode = 0444; + + /* We create the boost file in any case, though for systems without + * hardware support it will be read-only and hardwired to return 0. + */ + if (sysfs_create_file(cpufreq_global_kobject, &(global_boost.attr))) + pr_warn(PFX "could not register global boost sysfs file\n"); + else + pr_debug("registered global boost sysfs file\n"); +} + +static void __exit acpi_cpufreq_boost_exit(void) +{ + sysfs_remove_file(cpufreq_global_kobject, &(global_boost.attr)); + + if (msrs) { + unregister_cpu_notifier(&boost_nb); + + msrs_free(msrs); + msrs = NULL; + } +} + static int __init acpi_cpufreq_init(void) { int ret; @@ -746,9 +981,32 @@ static int __init acpi_cpufreq_init(void) if (ret) return ret; +#ifdef CONFIG_X86_ACPI_CPUFREQ_CPB + /* this is a sysfs file with a strange name and an even stranger + * semantic - per CPU instantiation, but system global effect. + * Lets enable it only on AMD CPUs for compatibility reasons and + * only if configured. This is considered legacy code, which + * will probably be removed at some point in the future. + */ + if (check_amd_hwpstate_cpu(0)) { + struct freq_attr **iter; + + pr_debug("adding sysfs entry for cpb\n"); + + for (iter = acpi_cpufreq_attr; *iter != NULL; iter++) + ; + + /* make sure there is a terminator behind it */ + if (iter[1] == NULL) + *iter = &cpb; + } +#endif + ret = cpufreq_register_driver(&acpi_cpufreq_driver); if (ret) free_acpi_perf_data(); + else + acpi_cpufreq_boost_init(); return ret; } @@ -757,6 +1015,8 @@ static void __exit acpi_cpufreq_exit(void) { pr_debug("acpi_cpufreq_exit\n"); + acpi_cpufreq_boost_exit(); + cpufreq_unregister_driver(&acpi_cpufreq_driver); free_acpi_perf_data(); diff --git a/drivers/cpufreq/cpufreq-cpu0.c b/drivers/cpufreq/cpufreq-cpu0.c new file mode 100644 index 0000000..e915827 --- /dev/null +++ b/drivers/cpufreq/cpufreq-cpu0.c @@ -0,0 +1,269 @@ +/* + * Copyright (C) 2012 Freescale Semiconductor, Inc. + * + * The OPP code in function cpu0_set_target() is reused from + * drivers/cpufreq/omap-cpufreq.c + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/clk.h> +#include <linux/cpu.h> +#include <linux/cpufreq.h> +#include <linux/err.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/opp.h> +#include <linux/regulator/consumer.h> +#include <linux/slab.h> + +static unsigned int transition_latency; +static unsigned int voltage_tolerance; /* in percentage */ + +static struct device *cpu_dev; +static struct clk *cpu_clk; +static struct regulator *cpu_reg; +static struct cpufreq_frequency_table *freq_table; + +static int cpu0_verify_speed(struct cpufreq_policy *policy) +{ + return cpufreq_frequency_table_verify(policy, freq_table); +} + +static unsigned int cpu0_get_speed(unsigned int cpu) +{ + return clk_get_rate(cpu_clk) / 1000; +} + +static int cpu0_set_target(struct cpufreq_policy *policy, + unsigned int target_freq, unsigned int relation) +{ + struct cpufreq_freqs freqs; + struct opp *opp; + unsigned long freq_Hz, volt = 0, volt_old = 0, tol = 0; + unsigned int index, cpu; + int ret; + + ret = cpufreq_frequency_table_target(policy, freq_table, target_freq, + relation, &index); + if (ret) { + pr_err("failed to match target freqency %d: %d\n", + target_freq, ret); + return ret; + } + + freq_Hz = clk_round_rate(cpu_clk, freq_table[index].frequency * 1000); + if (freq_Hz < 0) + freq_Hz = freq_table[index].frequency * 1000; + freqs.new = freq_Hz / 1000; + freqs.old = clk_get_rate(cpu_clk) / 1000; + + if (freqs.old == freqs.new) + return 0; + + for_each_online_cpu(cpu) { + freqs.cpu = cpu; + cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE); + } + + if (cpu_reg) { + opp = opp_find_freq_ceil(cpu_dev, &freq_Hz); + if (IS_ERR(opp)) { + pr_err("failed to find OPP for %ld\n", freq_Hz); + return PTR_ERR(opp); + } + volt = opp_get_voltage(opp); + tol = volt * voltage_tolerance / 100; + volt_old = regulator_get_voltage(cpu_reg); + } + + pr_debug("%u MHz, %ld mV --> %u MHz, %ld mV\n", + freqs.old / 1000, volt_old ? volt_old / 1000 : -1, + freqs.new / 1000, volt ? volt / 1000 : -1); + + /* scaling up? scale voltage before frequency */ + if (cpu_reg && freqs.new > freqs.old) { + ret = regulator_set_voltage_tol(cpu_reg, volt, tol); + if (ret) { + pr_err("failed to scale voltage up: %d\n", ret); + freqs.new = freqs.old; + return ret; + } + } + + ret = clk_set_rate(cpu_clk, freqs.new * 1000); + if (ret) { + pr_err("failed to set clock rate: %d\n", ret); + if (cpu_reg) + regulator_set_voltage_tol(cpu_reg, volt_old, tol); + return ret; + } + + /* scaling down? scale voltage after frequency */ + if (cpu_reg && freqs.new < freqs.old) { + ret = regulator_set_voltage_tol(cpu_reg, volt, tol); + if (ret) { + pr_err("failed to scale voltage down: %d\n", ret); + clk_set_rate(cpu_clk, freqs.old * 1000); + freqs.new = freqs.old; + return ret; + } + } + + for_each_online_cpu(cpu) { + freqs.cpu = cpu; + cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE); + } + + return 0; +} + +static int cpu0_cpufreq_init(struct cpufreq_policy *policy) +{ + int ret; + + if (policy->cpu != 0) + return -EINVAL; + + ret = cpufreq_frequency_table_cpuinfo(policy, freq_table); + if (ret) { + pr_err("invalid frequency table: %d\n", ret); + return ret; + } + + policy->cpuinfo.transition_latency = transition_latency; + policy->cur = clk_get_rate(cpu_clk) / 1000; + + /* + * The driver only supports the SMP configuartion where all processors + * share the clock and voltage and clock. Use cpufreq affected_cpus + * interface to have all CPUs scaled together. + */ + policy->shared_type = CPUFREQ_SHARED_TYPE_ANY; + cpumask_setall(policy->cpus); + + cpufreq_frequency_table_get_attr(freq_table, policy->cpu); + + return 0; +} + +static int cpu0_cpufreq_exit(struct cpufreq_policy *policy) +{ + cpufreq_frequency_table_put_attr(policy->cpu); + + return 0; +} + +static struct freq_attr *cpu0_cpufreq_attr[] = { + &cpufreq_freq_attr_scaling_available_freqs, + NULL, +}; + +static struct cpufreq_driver cpu0_cpufreq_driver = { + .flags = CPUFREQ_STICKY, + .verify = cpu0_verify_speed, + .target = cpu0_set_target, + .get = cpu0_get_speed, + .init = cpu0_cpufreq_init, + .exit = cpu0_cpufreq_exit, + .name = "generic_cpu0", + .attr = cpu0_cpufreq_attr, +}; + +static int __devinit cpu0_cpufreq_driver_init(void) +{ + struct device_node *np; + int ret; + + np = of_find_node_by_path("/cpus/cpu@0"); + if (!np) { + pr_err("failed to find cpu0 node\n"); + return -ENOENT; + } + + cpu_dev = get_cpu_device(0); + if (!cpu_dev) { + pr_err("failed to get cpu0 device\n"); + ret = -ENODEV; + goto out_put_node; + } + + cpu_dev->of_node = np; + + cpu_clk = clk_get(cpu_dev, NULL); + if (IS_ERR(cpu_clk)) { + ret = PTR_ERR(cpu_clk); + pr_err("failed to get cpu0 clock: %d\n", ret); + goto out_put_node; + } + + cpu_reg = regulator_get(cpu_dev, "cpu0"); + if (IS_ERR(cpu_reg)) { + pr_warn("failed to get cpu0 regulator\n"); + cpu_reg = NULL; + } + + ret = of_init_opp_table(cpu_dev); + if (ret) { + pr_err("failed to init OPP table: %d\n", ret); + goto out_put_node; + } + + ret = opp_init_cpufreq_table(cpu_dev, &freq_table); + if (ret) { + pr_err("failed to init cpufreq table: %d\n", ret); + goto out_put_node; + } + + of_property_read_u32(np, "voltage-tolerance", &voltage_tolerance); + + if (of_property_read_u32(np, "clock-latency", &transition_latency)) + transition_latency = CPUFREQ_ETERNAL; + + if (cpu_reg) { + struct opp *opp; + unsigned long min_uV, max_uV; + int i; + + /* + * OPP is maintained in order of increasing frequency, and + * freq_table initialised from OPP is therefore sorted in the + * same order. + */ + for (i = 0; freq_table[i].frequency != CPUFREQ_TABLE_END; i++) + ; + opp = opp_find_freq_exact(cpu_dev, + freq_table[0].frequency * 1000, true); + min_uV = opp_get_voltage(opp); + opp = opp_find_freq_exact(cpu_dev, + freq_table[i-1].frequency * 1000, true); + max_uV = opp_get_voltage(opp); + ret = regulator_set_voltage_time(cpu_reg, min_uV, max_uV); + if (ret > 0) + transition_latency += ret * 1000; + } + + ret = cpufreq_register_driver(&cpu0_cpufreq_driver); + if (ret) { + pr_err("failed register driver: %d\n", ret); + goto out_free_table; + } + + of_node_put(np); + return 0; + +out_free_table: + opp_free_cpufreq_table(cpu_dev, &freq_table); +out_put_node: + of_node_put(np); + return ret; +} +late_initcall(cpu0_cpufreq_driver_init); + +MODULE_AUTHOR("Shawn Guo <shawn.guo@linaro.org>"); +MODULE_DESCRIPTION("Generic CPU0 cpufreq driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/cpufreq/cpufreq_conservative.c b/drivers/cpufreq/cpufreq_conservative.c index 55f0354..a152af7 100644 --- a/drivers/cpufreq/cpufreq_conservative.c +++ b/drivers/cpufreq/cpufreq_conservative.c @@ -504,6 +504,7 @@ static int cpufreq_governor_dbs(struct cpufreq_policy *policy, j_dbs_info->prev_cpu_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE]; } + this_dbs_info->cpu = cpu; this_dbs_info->down_skip = 0; this_dbs_info->requested_freq = policy->cur; @@ -583,6 +584,7 @@ static int cpufreq_governor_dbs(struct cpufreq_policy *policy, __cpufreq_driver_target( this_dbs_info->cur_policy, policy->min, CPUFREQ_RELATION_L); + dbs_check_cpu(this_dbs_info); mutex_unlock(&this_dbs_info->timer_mutex); break; diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c index 14c1af5..396322f 100644 --- a/drivers/cpufreq/cpufreq_ondemand.c +++ b/drivers/cpufreq/cpufreq_ondemand.c @@ -761,6 +761,7 @@ static int cpufreq_governor_dbs(struct cpufreq_policy *policy, else if (policy->min > this_dbs_info->cur_policy->cur) __cpufreq_driver_target(this_dbs_info->cur_policy, policy->min, CPUFREQ_RELATION_L); + dbs_check_cpu(this_dbs_info); mutex_unlock(&this_dbs_info->timer_mutex); break; } diff --git a/drivers/cpufreq/longhaul.h b/drivers/cpufreq/longhaul.h index cbf48fb..e2dc436 100644 --- a/drivers/cpufreq/longhaul.h +++ b/drivers/cpufreq/longhaul.h @@ -56,7 +56,7 @@ union msr_longhaul { /* * VIA C3 Samuel 1 & Samuel 2 (stepping 0) */ -static const int __cpuinitdata samuel1_mults[16] = { +static const int __cpuinitconst samuel1_mults[16] = { -1, /* 0000 -> RESERVED */ 30, /* 0001 -> 3.0x */ 40, /* 0010 -> 4.0x */ @@ -75,7 +75,7 @@ static const int __cpuinitdata samuel1_mults[16] = { -1, /* 1111 -> RESERVED */ }; -static const int __cpuinitdata samuel1_eblcr[16] = { +static const int __cpuinitconst samuel1_eblcr[16] = { 50, /* 0000 -> RESERVED */ 30, /* 0001 -> 3.0x */ 40, /* 0010 -> 4.0x */ @@ -97,7 +97,7 @@ static const int __cpuinitdata samuel1_eblcr[16] = { /* * VIA C3 Samuel2 Stepping 1->15 */ -static const int __cpuinitdata samuel2_eblcr[16] = { +static const int __cpuinitconst samuel2_eblcr[16] = { 50, /* 0000 -> 5.0x */ 30, /* 0001 -> 3.0x */ 40, /* 0010 -> 4.0x */ @@ -119,7 +119,7 @@ static const int __cpuinitdata samuel2_eblcr[16] = { /* * VIA C3 Ezra */ -static const int __cpuinitdata ezra_mults[16] = { +static const int __cpuinitconst ezra_mults[16] = { 100, /* 0000 -> 10.0x */ 30, /* 0001 -> 3.0x */ 40, /* 0010 -> 4.0x */ @@ -138,7 +138,7 @@ static const int __cpuinitdata ezra_mults[16] = { 120, /* 1111 -> 12.0x */ }; -static const int __cpuinitdata ezra_eblcr[16] = { +static const int __cpuinitconst ezra_eblcr[16] = { 50, /* 0000 -> 5.0x */ 30, /* 0001 -> 3.0x */ 40, /* 0010 -> 4.0x */ @@ -160,7 +160,7 @@ static const int __cpuinitdata ezra_eblcr[16] = { /* * VIA C3 (Ezra-T) [C5M]. */ -static const int __cpuinitdata ezrat_mults[32] = { +static const int __cpuinitconst ezrat_mults[32] = { 100, /* 0000 -> 10.0x */ 30, /* 0001 -> 3.0x */ 40, /* 0010 -> 4.0x */ @@ -196,7 +196,7 @@ static const int __cpuinitdata ezrat_mults[32] = { -1, /* 1111 -> RESERVED (12.0x) */ }; -static const int __cpuinitdata ezrat_eblcr[32] = { +static const int __cpuinitconst ezrat_eblcr[32] = { 50, /* 0000 -> 5.0x */ 30, /* 0001 -> 3.0x */ 40, /* 0010 -> 4.0x */ @@ -235,7 +235,7 @@ static const int __cpuinitdata ezrat_eblcr[32] = { /* * VIA C3 Nehemiah */ -static const int __cpuinitdata nehemiah_mults[32] = { +static const int __cpuinitconst nehemiah_mults[32] = { 100, /* 0000 -> 10.0x */ -1, /* 0001 -> 16.0x */ 40, /* 0010 -> 4.0x */ @@ -270,7 +270,7 @@ static const int __cpuinitdata nehemiah_mults[32] = { -1, /* 1111 -> 12.0x */ }; -static const int __cpuinitdata nehemiah_eblcr[32] = { +static const int __cpuinitconst nehemiah_eblcr[32] = { 50, /* 0000 -> 5.0x */ 160, /* 0001 -> 16.0x */ 40, /* 0010 -> 4.0x */ @@ -315,7 +315,7 @@ struct mV_pos { unsigned short pos; }; -static const struct mV_pos __cpuinitdata vrm85_mV[32] = { +static const struct mV_pos __cpuinitconst vrm85_mV[32] = { {1250, 8}, {1200, 6}, {1150, 4}, {1100, 2}, {1050, 0}, {1800, 30}, {1750, 28}, {1700, 26}, {1650, 24}, {1600, 22}, {1550, 20}, {1500, 18}, @@ -326,14 +326,14 @@ static const struct mV_pos __cpuinitdata vrm85_mV[32] = { {1475, 17}, {1425, 15}, {1375, 13}, {1325, 11} }; -static const unsigned char __cpuinitdata mV_vrm85[32] = { +static const unsigned char __cpuinitconst mV_vrm85[32] = { 0x04, 0x14, 0x03, 0x13, 0x02, 0x12, 0x01, 0x11, 0x00, 0x10, 0x0f, 0x1f, 0x0e, 0x1e, 0x0d, 0x1d, 0x0c, 0x1c, 0x0b, 0x1b, 0x0a, 0x1a, 0x09, 0x19, 0x08, 0x18, 0x07, 0x17, 0x06, 0x16, 0x05, 0x15 }; -static const struct mV_pos __cpuinitdata mobilevrm_mV[32] = { +static const struct mV_pos __cpuinitconst mobilevrm_mV[32] = { {1750, 31}, {1700, 30}, {1650, 29}, {1600, 28}, {1550, 27}, {1500, 26}, {1450, 25}, {1400, 24}, {1350, 23}, {1300, 22}, {1250, 21}, {1200, 20}, @@ -344,7 +344,7 @@ static const struct mV_pos __cpuinitdata mobilevrm_mV[32] = { {675, 3}, {650, 2}, {625, 1}, {600, 0} }; -static const unsigned char __cpuinitdata mV_mobilevrm[32] = { +static const unsigned char __cpuinitconst mV_mobilevrm[32] = { 0x1f, 0x1e, 0x1d, 0x1c, 0x1b, 0x1a, 0x19, 0x18, 0x17, 0x16, 0x15, 0x14, 0x13, 0x12, 0x11, 0x10, 0x0f, 0x0e, 0x0d, 0x0c, 0x0b, 0x0a, 0x09, 0x08, diff --git a/drivers/cpufreq/omap-cpufreq.c b/drivers/cpufreq/omap-cpufreq.c index b47034e..65f8e9a 100644 --- a/drivers/cpufreq/omap-cpufreq.c +++ b/drivers/cpufreq/omap-cpufreq.c @@ -40,16 +40,6 @@ /* OPP tolerance in percentage */ #define OPP_TOLERANCE 4 -#ifdef CONFIG_SMP -struct lpj_info { - unsigned long ref; - unsigned int freq; -}; - -static DEFINE_PER_CPU(struct lpj_info, lpj_ref); -static struct lpj_info global_lpj_ref; -#endif - static struct cpufreq_frequency_table *freq_table; static atomic_t freq_table_users = ATOMIC_INIT(0); static struct clk *mpu_clk; @@ -161,31 +151,6 @@ static int omap_target(struct cpufreq_policy *policy, } freqs.new = omap_getspeed(policy->cpu); -#ifdef CONFIG_SMP - /* - * Note that loops_per_jiffy is not updated on SMP systems in - * cpufreq driver. So, update the per-CPU loops_per_jiffy value - * on frequency transition. We need to update all dependent CPUs. - */ - for_each_cpu(i, policy->cpus) { - struct lpj_info *lpj = &per_cpu(lpj_ref, i); - if (!lpj->freq) { - lpj->ref = per_cpu(cpu_data, i).loops_per_jiffy; - lpj->freq = freqs.old; - } - - per_cpu(cpu_data, i).loops_per_jiffy = - cpufreq_scale(lpj->ref, lpj->freq, freqs.new); - } - - /* And don't forget to adjust the global one */ - if (!global_lpj_ref.freq) { - global_lpj_ref.ref = loops_per_jiffy; - global_lpj_ref.freq = freqs.old; - } - loops_per_jiffy = cpufreq_scale(global_lpj_ref.ref, global_lpj_ref.freq, - freqs.new); -#endif done: /* notifiers */ @@ -301,9 +266,9 @@ static int __init omap_cpufreq_init(void) } mpu_dev = omap_device_get_by_hwmod_name("mpu"); - if (!mpu_dev) { + if (IS_ERR(mpu_dev)) { pr_warning("%s: unable to get the mpu device\n", __func__); - return -EINVAL; + return PTR_ERR(mpu_dev); } mpu_reg = regulator_get(mpu_dev, "vcc"); diff --git a/drivers/cpufreq/powernow-k8.c b/drivers/cpufreq/powernow-k8.c index 1a40935..129e80b 100644 --- a/drivers/cpufreq/powernow-k8.c +++ b/drivers/cpufreq/powernow-k8.c @@ -48,22 +48,12 @@ #define PFX "powernow-k8: " #define VERSION "version 2.20.00" #include "powernow-k8.h" -#include "mperf.h" /* serialize freq changes */ static DEFINE_MUTEX(fidvid_mutex); static DEFINE_PER_CPU(struct powernow_k8_data *, powernow_data); -static int cpu_family = CPU_OPTERON; - -/* array to map SW pstate number to acpi state */ -static u32 ps_to_as[8]; - -/* core performance boost */ -static bool cpb_capable, cpb_enabled; -static struct msr __percpu *msrs; - static struct cpufreq_driver cpufreq_amd64_driver; #ifndef CONFIG_SMP @@ -85,12 +75,6 @@ static u32 find_khz_freq_from_fid(u32 fid) return 1000 * find_freq_from_fid(fid); } -static u32 find_khz_freq_from_pstate(struct cpufreq_frequency_table *data, - u32 pstate) -{ - return data[ps_to_as[pstate]].frequency; -} - /* Return the vco fid for an input fid * * Each "low" fid has corresponding "high" fid, and you can get to "low" fids @@ -113,9 +97,6 @@ static int pending_bit_stuck(void) { u32 lo, hi; - if (cpu_family == CPU_HW_PSTATE) - return 0; - rdmsr(MSR_FIDVID_STATUS, lo, hi); return lo & MSR_S_LO_CHANGE_PENDING ? 1 : 0; } @@ -129,20 +110,6 @@ static int query_current_values_with_pending_wait(struct powernow_k8_data *data) u32 lo, hi; u32 i = 0; - if (cpu_family == CPU_HW_PSTATE) { - rdmsr(MSR_PSTATE_STATUS, lo, hi); - i = lo & HW_PSTATE_MASK; - data->currpstate = i; - - /* - * a workaround for family 11h erratum 311 might cause - * an "out-of-range Pstate if the core is in Pstate-0 - */ - if ((boot_cpu_data.x86 == 0x11) && (i >= data->numps)) - data->currpstate = HW_PSTATE_0; - - return 0; - } do { if (i++ > 10000) { pr_debug("detected change pending stuck\n"); @@ -299,14 +266,6 @@ static int decrease_vid_code_by_step(struct powernow_k8_data *data, return 0; } -/* Change hardware pstate by single MSR write */ -static int transition_pstate(struct powernow_k8_data *data, u32 pstate) -{ - wrmsr(MSR_PSTATE_CTRL, pstate, 0); - data->currpstate = pstate; - return 0; -} - /* Change Opteron/Athlon64 fid and vid, by the 3 phases. */ static int transition_fid_vid(struct powernow_k8_data *data, u32 reqfid, u32 reqvid) @@ -523,8 +482,6 @@ static int core_voltage_post_transition(struct powernow_k8_data *data, static const struct x86_cpu_id powernow_k8_ids[] = { /* IO based frequency switching */ { X86_VENDOR_AMD, 0xf }, - /* MSR based frequency switching supported */ - X86_FEATURE_MATCH(X86_FEATURE_HW_PSTATE), {} }; MODULE_DEVICE_TABLE(x86cpu, powernow_k8_ids); @@ -560,15 +517,8 @@ static void check_supported_cpu(void *_rc) "Power state transitions not supported\n"); return; } - } else { /* must be a HW Pstate capable processor */ - cpuid(CPUID_FREQ_VOLT_CAPABILITIES, &eax, &ebx, &ecx, &edx); - if ((edx & USE_HW_PSTATE) == USE_HW_PSTATE) - cpu_family = CPU_HW_PSTATE; - else - return; + *rc = 0; } - - *rc = 0; } static int check_pst_table(struct powernow_k8_data *data, struct pst_s *pst, @@ -632,18 +582,11 @@ static void print_basics(struct powernow_k8_data *data) for (j = 0; j < data->numps; j++) { if (data->powernow_table[j].frequency != CPUFREQ_ENTRY_INVALID) { - if (cpu_family == CPU_HW_PSTATE) { - printk(KERN_INFO PFX - " %d : pstate %d (%d MHz)\n", j, - data->powernow_table[j].index, - data->powernow_table[j].frequency/1000); - } else { printk(KERN_INFO PFX "fid 0x%x (%d MHz), vid 0x%x\n", data->powernow_table[j].index & 0xff, data->powernow_table[j].frequency/1000, data->powernow_table[j].index >> 8); - } } } if (data->batps) @@ -651,20 +594,6 @@ static void print_basics(struct powernow_k8_data *data) data->batps); } -static u32 freq_from_fid_did(u32 fid, u32 did) -{ - u32 mhz = 0; - - if (boot_cpu_data.x86 == 0x10) - mhz = (100 * (fid + 0x10)) >> did; - else if (boot_cpu_data.x86 == 0x11) - mhz = (100 * (fid + 8)) >> did; - else - BUG(); - - return mhz * 1000; -} - static int fill_powernow_table(struct powernow_k8_data *data, struct pst_s *pst, u8 maxvid) { @@ -824,7 +753,7 @@ static void powernow_k8_acpi_pst_values(struct powernow_k8_data *data, { u64 control; - if (!data->acpi_data.state_count || (cpu_family == CPU_HW_PSTATE)) + if (!data->acpi_data.state_count) return; control = data->acpi_data.states[index].control; @@ -875,10 +804,7 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data) data->numps = data->acpi_data.state_count; powernow_k8_acpi_pst_values(data, 0); - if (cpu_family == CPU_HW_PSTATE) - ret_val = fill_powernow_table_pstate(data, powernow_table); - else - ret_val = fill_powernow_table_fidvid(data, powernow_table); + ret_val = fill_powernow_table_fidvid(data, powernow_table); if (ret_val) goto err_out_mem; @@ -915,51 +841,6 @@ err_out: return ret_val; } -static int fill_powernow_table_pstate(struct powernow_k8_data *data, - struct cpufreq_frequency_table *powernow_table) -{ - int i; - u32 hi = 0, lo = 0; - rdmsr(MSR_PSTATE_CUR_LIMIT, lo, hi); - data->max_hw_pstate = (lo & HW_PSTATE_MAX_MASK) >> HW_PSTATE_MAX_SHIFT; - - for (i = 0; i < data->acpi_data.state_count; i++) { - u32 index; - - index = data->acpi_data.states[i].control & HW_PSTATE_MASK; - if (index > data->max_hw_pstate) { - printk(KERN_ERR PFX "invalid pstate %d - " - "bad value %d.\n", i, index); - printk(KERN_ERR PFX "Please report to BIOS " - "manufacturer\n"); - invalidate_entry(powernow_table, i); - continue; - } - - ps_to_as[index] = i; - - /* Frequency may be rounded for these */ - if ((boot_cpu_data.x86 == 0x10 && boot_cpu_data.x86_model < 10) - || boot_cpu_data.x86 == 0x11) { - - rdmsr(MSR_PSTATE_DEF_BASE + index, lo, hi); - if (!(hi & HW_PSTATE_VALID_MASK)) { - pr_debug("invalid pstate %d, ignoring\n", index); - invalidate_entry(powernow_table, i); - continue; - } - - powernow_table[i].frequency = - freq_from_fid_did(lo & 0x3f, (lo >> 6) & 7); - } else - powernow_table[i].frequency = - data->acpi_data.states[i].core_frequency * 1000; - - powernow_table[i].index = index; - } - return 0; -} - static int fill_powernow_table_fidvid(struct powernow_k8_data *data, struct cpufreq_frequency_table *powernow_table) { @@ -1036,15 +917,7 @@ static int get_transition_latency(struct powernow_k8_data *data) max_latency = cur_latency; } if (max_latency == 0) { - /* - * Fam 11h and later may return 0 as transition latency. This - * is intended and means "very fast". While cpufreq core and - * governors currently can handle that gracefully, better set it - * to 1 to avoid problems in the future. - */ - if (boot_cpu_data.x86 < 0x11) - printk(KERN_ERR FW_WARN PFX "Invalid zero transition " - "latency\n"); + pr_err(FW_WARN PFX "Invalid zero transition latency\n"); max_latency = 1; } /* value in usecs, needs to be in nanoseconds */ @@ -1104,40 +977,6 @@ static int transition_frequency_fidvid(struct powernow_k8_data *data, return res; } -/* Take a frequency, and issue the hardware pstate transition command */ -static int transition_frequency_pstate(struct powernow_k8_data *data, - unsigned int index) -{ - u32 pstate = 0; - int res, i; - struct cpufreq_freqs freqs; - - pr_debug("cpu %d transition to index %u\n", smp_processor_id(), index); - - /* get MSR index for hardware pstate transition */ - pstate = index & HW_PSTATE_MASK; - if (pstate > data->max_hw_pstate) - return -EINVAL; - - freqs.old = find_khz_freq_from_pstate(data->powernow_table, - data->currpstate); - freqs.new = find_khz_freq_from_pstate(data->powernow_table, pstate); - - for_each_cpu(i, data->available_cores) { - freqs.cpu = i; - cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE); - } - - res = transition_pstate(data, pstate); - freqs.new = find_khz_freq_from_pstate(data->powernow_table, pstate); - - for_each_cpu(i, data->available_cores) { - freqs.cpu = i; - cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE); - } - return res; -} - struct powernowk8_target_arg { struct cpufreq_policy *pol; unsigned targfreq; @@ -1173,18 +1012,15 @@ static long powernowk8_target_fn(void *arg) if (query_current_values_with_pending_wait(data)) return -EIO; - if (cpu_family != CPU_HW_PSTATE) { - pr_debug("targ: curr fid 0x%x, vid 0x%x\n", - data->currfid, data->currvid); + pr_debug("targ: curr fid 0x%x, vid 0x%x\n", + data->currfid, data->currvid); - if ((checkvid != data->currvid) || - (checkfid != data->currfid)) { - printk(KERN_INFO PFX - "error - out of sync, fix 0x%x 0x%x, " - "vid 0x%x 0x%x\n", - checkfid, data->currfid, - checkvid, data->currvid); - } + if ((checkvid != data->currvid) || + (checkfid != data->currfid)) { + pr_info(PFX + "error - out of sync, fix 0x%x 0x%x, vid 0x%x 0x%x\n", + checkfid, data->currfid, + checkvid, data->currvid); } if (cpufreq_frequency_table_target(pol, data->powernow_table, @@ -1195,11 +1031,8 @@ static long powernowk8_target_fn(void *arg) powernow_k8_acpi_pst_values(data, newstate); - if (cpu_family == CPU_HW_PSTATE) - ret = transition_frequency_pstate(data, - data->powernow_table[newstate].index); - else - ret = transition_frequency_fidvid(data, newstate); + ret = transition_frequency_fidvid(data, newstate); + if (ret) { printk(KERN_ERR PFX "transition frequency failed\n"); mutex_unlock(&fidvid_mutex); @@ -1207,11 +1040,7 @@ static long powernowk8_target_fn(void *arg) } mutex_unlock(&fidvid_mutex); - if (cpu_family == CPU_HW_PSTATE) - pol->cur = find_khz_freq_from_pstate(data->powernow_table, - data->powernow_table[newstate].index); - else - pol->cur = find_khz_freq_from_fid(data->currfid); + pol->cur = find_khz_freq_from_fid(data->currfid); return 0; } @@ -1264,22 +1093,23 @@ static void __cpuinit powernowk8_cpu_init_on_cpu(void *_init_on_cpu) return; } - if (cpu_family == CPU_OPTERON) - fidvid_msr_init(); + fidvid_msr_init(); init_on_cpu->rc = 0; } +static const char missing_pss_msg[] = + KERN_ERR + FW_BUG PFX "No compatible ACPI _PSS objects found.\n" + FW_BUG PFX "First, make sure Cool'N'Quiet is enabled in the BIOS.\n" + FW_BUG PFX "If that doesn't help, try upgrading your BIOS.\n"; + /* per CPU init entry point to the driver */ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol) { - static const char ACPI_PSS_BIOS_BUG_MSG[] = - KERN_ERR FW_BUG PFX "No compatible ACPI _PSS objects found.\n" - FW_BUG PFX "Try again with latest BIOS.\n"; struct powernow_k8_data *data; struct init_on_cpu init_on_cpu; int rc; - struct cpuinfo_x86 *c = &cpu_data(pol->cpu); if (!cpu_online(pol->cpu)) return -ENODEV; @@ -1295,7 +1125,6 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol) } data->cpu = pol->cpu; - data->currpstate = HW_PSTATE_INVALID; if (powernow_k8_cpu_init_acpi(data)) { /* @@ -1303,7 +1132,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol) * an UP version, and is deprecated by AMD. */ if (num_online_cpus() != 1) { - printk_once(ACPI_PSS_BIOS_BUG_MSG); + printk_once(missing_pss_msg); goto err_out; } if (pol->cpu != 0) { @@ -1332,17 +1161,10 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol) if (rc != 0) goto err_out_exit_acpi; - if (cpu_family == CPU_HW_PSTATE) - cpumask_copy(pol->cpus, cpumask_of(pol->cpu)); - else - cpumask_copy(pol->cpus, cpu_core_mask(pol->cpu)); + cpumask_copy(pol->cpus, cpu_core_mask(pol->cpu)); data->available_cores = pol->cpus; - if (cpu_family == CPU_HW_PSTATE) - pol->cur = find_khz_freq_from_pstate(data->powernow_table, - data->currpstate); - else - pol->cur = find_khz_freq_from_fid(data->currfid); + pol->cur = find_khz_freq_from_fid(data->currfid); pr_debug("policy current frequency %d kHz\n", pol->cur); /* min/max the cpu is capable of */ @@ -1354,18 +1176,10 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol) return -EINVAL; } - /* Check for APERF/MPERF support in hardware */ - if (cpu_has(c, X86_FEATURE_APERFMPERF)) - cpufreq_amd64_driver.getavg = cpufreq_get_measured_perf; - cpufreq_frequency_table_get_attr(data->powernow_table, pol->cpu); - if (cpu_family == CPU_HW_PSTATE) - pr_debug("cpu_init done, current pstate 0x%x\n", - data->currpstate); - else - pr_debug("cpu_init done, current fid 0x%x, vid 0x%x\n", - data->currfid, data->currvid); + pr_debug("cpu_init done, current fid 0x%x, vid 0x%x\n", + data->currfid, data->currvid); per_cpu(powernow_data, pol->cpu) = data; @@ -1418,88 +1232,15 @@ static unsigned int powernowk8_get(unsigned int cpu) if (err) goto out; - if (cpu_family == CPU_HW_PSTATE) - khz = find_khz_freq_from_pstate(data->powernow_table, - data->currpstate); - else - khz = find_khz_freq_from_fid(data->currfid); + khz = find_khz_freq_from_fid(data->currfid); out: return khz; } -static void _cpb_toggle_msrs(bool t) -{ - int cpu; - - get_online_cpus(); - - rdmsr_on_cpus(cpu_online_mask, MSR_K7_HWCR, msrs); - - for_each_cpu(cpu, cpu_online_mask) { - struct msr *reg = per_cpu_ptr(msrs, cpu); - if (t) - reg->l &= ~BIT(25); - else - reg->l |= BIT(25); - } - wrmsr_on_cpus(cpu_online_mask, MSR_K7_HWCR, msrs); - - put_online_cpus(); -} - -/* - * Switch on/off core performance boosting. - * - * 0=disable - * 1=enable. - */ -static void cpb_toggle(bool t) -{ - if (!cpb_capable) - return; - - if (t && !cpb_enabled) { - cpb_enabled = true; - _cpb_toggle_msrs(t); - printk(KERN_INFO PFX "Core Boosting enabled.\n"); - } else if (!t && cpb_enabled) { - cpb_enabled = false; - _cpb_toggle_msrs(t); - printk(KERN_INFO PFX "Core Boosting disabled.\n"); - } -} - -static ssize_t store_cpb(struct cpufreq_policy *policy, const char *buf, - size_t count) -{ - int ret = -EINVAL; - unsigned long val = 0; - - ret = strict_strtoul(buf, 10, &val); - if (!ret && (val == 0 || val == 1) && cpb_capable) - cpb_toggle(val); - else - return -EINVAL; - - return count; -} - -static ssize_t show_cpb(struct cpufreq_policy *policy, char *buf) -{ - return sprintf(buf, "%u\n", cpb_enabled); -} - -#define define_one_rw(_name) \ -static struct freq_attr _name = \ -__ATTR(_name, 0644, show_##_name, store_##_name) - -define_one_rw(cpb); - static struct freq_attr *powernow_k8_attr[] = { &cpufreq_freq_attr_scaling_available_freqs, - &cpb, NULL, }; @@ -1515,53 +1256,18 @@ static struct cpufreq_driver cpufreq_amd64_driver = { .attr = powernow_k8_attr, }; -/* - * Clear the boost-disable flag on the CPU_DOWN path so that this cpu - * cannot block the remaining ones from boosting. On the CPU_UP path we - * simply keep the boost-disable flag in sync with the current global - * state. - */ -static int cpb_notify(struct notifier_block *nb, unsigned long action, - void *hcpu) -{ - unsigned cpu = (long)hcpu; - u32 lo, hi; - - switch (action) { - case CPU_UP_PREPARE: - case CPU_UP_PREPARE_FROZEN: - - if (!cpb_enabled) { - rdmsr_on_cpu(cpu, MSR_K7_HWCR, &lo, &hi); - lo |= BIT(25); - wrmsr_on_cpu(cpu, MSR_K7_HWCR, lo, hi); - } - break; - - case CPU_DOWN_PREPARE: - case CPU_DOWN_PREPARE_FROZEN: - rdmsr_on_cpu(cpu, MSR_K7_HWCR, &lo, &hi); - lo &= ~BIT(25); - wrmsr_on_cpu(cpu, MSR_K7_HWCR, lo, hi); - break; - - default: - break; - } - - return NOTIFY_OK; -} - -static struct notifier_block cpb_nb = { - .notifier_call = cpb_notify, -}; - /* driver entry point for init */ static int __cpuinit powernowk8_init(void) { - unsigned int i, supported_cpus = 0, cpu; + unsigned int i, supported_cpus = 0; int rv; + if (static_cpu_has(X86_FEATURE_HW_PSTATE)) { + pr_warn(PFX "this CPU is not supported anymore, using acpi-cpufreq instead.\n"); + request_module("acpi-cpufreq"); + return -ENODEV; + } + if (!x86_match_cpu(powernow_k8_ids)) return -ENODEV; @@ -1575,38 +1281,13 @@ static int __cpuinit powernowk8_init(void) if (supported_cpus != num_online_cpus()) return -ENODEV; - printk(KERN_INFO PFX "Found %d %s (%d cpu cores) (" VERSION ")\n", - num_online_nodes(), boot_cpu_data.x86_model_id, supported_cpus); - - if (boot_cpu_has(X86_FEATURE_CPB)) { - - cpb_capable = true; - - msrs = msrs_alloc(); - if (!msrs) { - printk(KERN_ERR "%s: Error allocating msrs!\n", __func__); - return -ENOMEM; - } - - register_cpu_notifier(&cpb_nb); - - rdmsr_on_cpus(cpu_online_mask, MSR_K7_HWCR, msrs); + rv = cpufreq_register_driver(&cpufreq_amd64_driver); - for_each_cpu(cpu, cpu_online_mask) { - struct msr *reg = per_cpu_ptr(msrs, cpu); - cpb_enabled |= !(!!(reg->l & BIT(25))); - } + if (!rv) + pr_info(PFX "Found %d %s (%d cpu cores) (" VERSION ")\n", + num_online_nodes(), boot_cpu_data.x86_model_id, + supported_cpus); - printk(KERN_INFO PFX "Core Performance Boosting: %s.\n", - (cpb_enabled ? "on" : "off")); - } - - rv = cpufreq_register_driver(&cpufreq_amd64_driver); - if (rv < 0 && boot_cpu_has(X86_FEATURE_CPB)) { - unregister_cpu_notifier(&cpb_nb); - msrs_free(msrs); - msrs = NULL; - } return rv; } @@ -1615,13 +1296,6 @@ static void __exit powernowk8_exit(void) { pr_debug("exit\n"); - if (boot_cpu_has(X86_FEATURE_CPB)) { - msrs_free(msrs); - msrs = NULL; - - unregister_cpu_notifier(&cpb_nb); - } - cpufreq_unregister_driver(&cpufreq_amd64_driver); } diff --git a/drivers/cpufreq/powernow-k8.h b/drivers/cpufreq/powernow-k8.h index 3744d26..79329d4 100644 --- a/drivers/cpufreq/powernow-k8.h +++ b/drivers/cpufreq/powernow-k8.h @@ -5,24 +5,11 @@ * http://www.gnu.org/licenses/gpl.html */ -enum pstate { - HW_PSTATE_INVALID = 0xff, - HW_PSTATE_0 = 0, - HW_PSTATE_1 = 1, - HW_PSTATE_2 = 2, - HW_PSTATE_3 = 3, - HW_PSTATE_4 = 4, - HW_PSTATE_5 = 5, - HW_PSTATE_6 = 6, - HW_PSTATE_7 = 7, -}; - struct powernow_k8_data { unsigned int cpu; u32 numps; /* number of p-states */ u32 batps; /* number of p-states supported on battery */ - u32 max_hw_pstate; /* maximum legal hardware pstate */ /* these values are constant when the PSB is used to determine * vid/fid pairings, but are modified during the ->target() call @@ -37,7 +24,6 @@ struct powernow_k8_data { /* keep track of the current fid / vid or pstate */ u32 currvid; u32 currfid; - enum pstate currpstate; /* the powernow_table includes all frequency and vid/fid pairings: * fid are the lower 8 bits of the index, vid are the upper 8 bits. @@ -97,23 +83,6 @@ struct powernow_k8_data { #define MSR_S_HI_CURRENT_VID 0x0000003f #define MSR_C_HI_STP_GNT_BENIGN 0x00000001 - -/* Hardware Pstate _PSS and MSR definitions */ -#define USE_HW_PSTATE 0x00000080 -#define HW_PSTATE_MASK 0x00000007 -#define HW_PSTATE_VALID_MASK 0x80000000 -#define HW_PSTATE_MAX_MASK 0x000000f0 -#define HW_PSTATE_MAX_SHIFT 4 -#define MSR_PSTATE_DEF_BASE 0xc0010064 /* base of Pstate MSRs */ -#define MSR_PSTATE_STATUS 0xc0010063 /* Pstate Status MSR */ -#define MSR_PSTATE_CTRL 0xc0010062 /* Pstate control MSR */ -#define MSR_PSTATE_CUR_LIMIT 0xc0010061 /* pstate current limit MSR */ - -/* define the two driver architectures */ -#define CPU_OPTERON 0 -#define CPU_HW_PSTATE 1 - - /* * There are restrictions frequencies have to follow: * - only 1 entry in the low fid table ( <=1.4GHz ) @@ -218,5 +187,4 @@ static int core_frequency_transition(struct powernow_k8_data *data, u32 reqfid); static void powernow_k8_acpi_pst_values(struct powernow_k8_data *data, unsigned int index); -static int fill_powernow_table_pstate(struct powernow_k8_data *data, struct cpufreq_frequency_table *powernow_table); static int fill_powernow_table_fidvid(struct powernow_k8_data *data, struct cpufreq_frequency_table *powernow_table); diff --git a/drivers/cpuidle/driver.c b/drivers/cpuidle/driver.c index 58bf3b1..87db387 100644 --- a/drivers/cpuidle/driver.c +++ b/drivers/cpuidle/driver.c @@ -18,9 +18,10 @@ static struct cpuidle_driver *cpuidle_curr_driver; DEFINE_SPINLOCK(cpuidle_driver_lock); int cpuidle_driver_refcount; -static void __cpuidle_register_driver(struct cpuidle_driver *drv) +static void set_power_states(struct cpuidle_driver *drv) { int i; + /* * cpuidle driver should set the drv->power_specified bit * before registering if the driver provides @@ -35,13 +36,10 @@ static void __cpuidle_register_driver(struct cpuidle_driver *drv) * an power value of -1. So we use -2, -3, etc, for other * c-states. */ - if (!drv->power_specified) { - for (i = CPUIDLE_DRIVER_STATE_START; i < drv->state_count; i++) - drv->states[i].power_usage = -1 - i; - } + for (i = CPUIDLE_DRIVER_STATE_START; i < drv->state_count; i++) + drv->states[i].power_usage = -1 - i; } - /** * cpuidle_register_driver - registers a driver * @drv: the driver @@ -59,13 +57,16 @@ int cpuidle_register_driver(struct cpuidle_driver *drv) spin_unlock(&cpuidle_driver_lock); return -EBUSY; } - __cpuidle_register_driver(drv); + + if (!drv->power_specified) + set_power_states(drv); + cpuidle_curr_driver = drv; + spin_unlock(&cpuidle_driver_lock); return 0; } - EXPORT_SYMBOL_GPL(cpuidle_register_driver); /** @@ -96,7 +97,6 @@ void cpuidle_unregister_driver(struct cpuidle_driver *drv) spin_unlock(&cpuidle_driver_lock); } - EXPORT_SYMBOL_GPL(cpuidle_unregister_driver); struct cpuidle_driver *cpuidle_driver_ref(void) diff --git a/drivers/cpuidle/governors/ladder.c b/drivers/cpuidle/governors/ladder.c index b6a09ea..9b78405 100644 --- a/drivers/cpuidle/governors/ladder.c +++ b/drivers/cpuidle/governors/ladder.c @@ -88,6 +88,8 @@ static int ladder_select_state(struct cpuidle_driver *drv, /* consider promotion */ if (last_idx < drv->state_count - 1 && + !drv->states[last_idx + 1].disabled && + !dev->states_usage[last_idx + 1].disable && last_residency > last_state->threshold.promotion_time && drv->states[last_idx + 1].exit_latency <= latency_req) { last_state->stats.promotion_count++; @@ -100,7 +102,9 @@ static int ladder_select_state(struct cpuidle_driver *drv, /* consider demotion */ if (last_idx > CPUIDLE_DRIVER_STATE_START && - drv->states[last_idx].exit_latency > latency_req) { + (drv->states[last_idx].disabled || + dev->states_usage[last_idx].disable || + drv->states[last_idx].exit_latency > latency_req)) { int i; for (i = last_idx - 1; i > CPUIDLE_DRIVER_STATE_START; i--) { diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index 9e1d295..94c6e2a 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -607,21 +607,6 @@ static int pci_pm_prepare(struct device *dev) int error = 0; /* - * If a PCI device configured to wake up the system from sleep states - * has been suspended at run time and there's a resume request pending - * for it, this is equivalent to the device signaling wakeup, so the - * system suspend operation should be aborted. - */ - pm_runtime_get_noresume(dev); - if (pm_runtime_barrier(dev) && device_may_wakeup(dev)) - pm_wakeup_event(dev, 0); - - if (pm_wakeup_pending()) { - pm_runtime_put_sync(dev); - return -EBUSY; - } - - /* * PCI devices suspended at run time need to be resumed at this * point, because in general it is necessary to reconfigure them for * system suspend. Namely, if the device is supposed to wake up the @@ -644,8 +629,6 @@ static void pci_pm_complete(struct device *dev) if (drv && drv->pm && drv->pm->complete) drv->pm->complete(dev); - - pm_runtime_put_sync(dev); } #else /* !CONFIG_PM_SLEEP */ diff --git a/drivers/xen/xen-acpi-processor.c b/drivers/xen/xen-acpi-processor.c index b590ee0..316df65 100644 --- a/drivers/xen/xen-acpi-processor.c +++ b/drivers/xen/xen-acpi-processor.c @@ -98,7 +98,6 @@ static int push_cxx_to_hypervisor(struct acpi_processor *_pr) dst_cx->type = cx->type; dst_cx->latency = cx->latency; - dst_cx->power = cx->power; dst_cx->dpcnt = 0; set_xen_guest_handle(dst_cx->dp, NULL); |