From a380f2edef65b2447a043251bb3c00a9d2153a8b Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 25 Sep 2017 14:56:44 +0200 Subject: PM / core: Drop legacy class suspend/resume operations There are no classes using the legacy suspend/resume operations in the tree any more, so drop these operations and update the code referring to them accordingly. Signed-off-by: Rafael J. Wysocki Acked-by: Greg Kroah-Hartman --- include/linux/device.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include') diff --git a/include/linux/device.h b/include/linux/device.h index 1d2607923a24..c1527f887050 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -372,9 +372,6 @@ int subsys_virtual_register(struct bus_type *subsys, * @devnode: Callback to provide the devtmpfs. * @class_release: Called to release this class. * @dev_release: Called to release the device. - * @suspend: Used to put the device to sleep mode, usually to a low power - * state. - * @resume: Used to bring the device from the sleep mode. * @shutdown_pre: Called at shut-down time before driver shutdown. * @ns_type: Callbacks so sysfs can detemine namespaces. * @namespace: Namespace of the device belongs to this class. @@ -402,8 +399,6 @@ struct class { void (*class_release)(struct class *class); void (*dev_release)(struct device *dev); - int (*suspend)(struct device *dev, pm_message_t state); - int (*resume)(struct device *dev); int (*shutdown_pre)(struct device *dev); const struct kobj_ns_type_operations *ns_type; -- cgit v1.2.3 From e7d5459dfaf613799915e901189d296bdc7534f9 Mon Sep 17 00:00:00 2001 From: Dietmar Eggemann Date: Tue, 26 Sep 2017 17:41:07 +0100 Subject: cpufreq: provide default frequency-invariance setter function Frequency-invariant accounting support based on the ratio of current frequency and maximum supported frequency is an optional feature an arch can implement. Since there are cpufreq drivers (e.g. cpufreq-dt) which can be build for different arch's a default implementation of the frequency-invariance setter function arch_set_freq_scale() is needed. This default implementation is an empty weak function which will be overwritten by a strong function in case the arch provides one. The setter function passes the cpumask of related (to the frequency change) cpus (online and offline cpus), the (new) current frequency and the maximum supported frequency. Signed-off-by: Dietmar Eggemann Acked-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 537ff842ff73..28734ee185a7 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -919,6 +919,9 @@ static inline bool policy_has_boost_freq(struct cpufreq_policy *policy) extern unsigned int arch_freq_get_on_cpu(int cpu); +extern void arch_set_freq_scale(struct cpumask *cpus, unsigned long cur_freq, + unsigned long max_freq); + /* the following are really really optional */ extern struct freq_attr cpufreq_freq_attr_scaling_available_freqs; extern struct freq_attr cpufreq_freq_attr_scaling_boost_freqs; -- cgit v1.2.3 From 0e27c567d1673137b06aa96bb7aef635fb657dee Mon Sep 17 00:00:00 2001 From: Dietmar Eggemann Date: Tue, 26 Sep 2017 17:41:10 +0100 Subject: drivers base/arch_topology: provide frequency-invariant accounting support Implements the arch-specific (arm and arm64) frequency-invariance setter function arch_set_freq_scale() which provides the following frequency scaling factor: current_freq(cpu) << SCHED_CAPACITY_SHIFT / max_supported_freq(cpu) One possible consumer of the frequency-invariance getter function topology_get_freq_scale() is the Per-Entity Load Tracking (PELT) mechanism of the task scheduler. Allow inlining of topology_get_freq_scale() into the task scheduler fast path (e.g. __update_load_avg_se()) by coding it as a static inline function in the arch topology header file. Signed-off-by: Dietmar Eggemann Acked-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/arch_topology.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h index 716ce587247e..f6e490312e4d 100644 --- a/include/linux/arch_topology.h +++ b/include/linux/arch_topology.h @@ -5,6 +5,7 @@ #define _LINUX_ARCH_TOPOLOGY_H_ #include +#include void topology_normalize_cpu_scale(void); @@ -16,4 +17,12 @@ unsigned long topology_get_cpu_scale(struct sched_domain *sd, int cpu); void topology_set_cpu_scale(unsigned int cpu, unsigned long capacity); +DECLARE_PER_CPU(unsigned long, freq_scale); + +static inline +unsigned long topology_get_freq_scale(struct sched_domain *sd, int cpu) +{ + return per_cpu(freq_scale, cpu); +} + #endif /* _LINUX_ARCH_TOPOLOGY_H_ */ -- cgit v1.2.3 From 8216f588b52b61ce36fc0080218e4730435e58b7 Mon Sep 17 00:00:00 2001 From: Dietmar Eggemann Date: Tue, 26 Sep 2017 17:41:11 +0100 Subject: drivers base/arch_topology: allow inlining cpu-invariant accounting support Allow inlining of topology_get_cpu_scale() into the task scheduler fast path (e.g. __update_load_avg_se()) by coding it as a static inline function in the arch topology header file. Signed-off-by: Dietmar Eggemann Acked-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/arch_topology.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h index f6e490312e4d..c189de3ef5df 100644 --- a/include/linux/arch_topology.h +++ b/include/linux/arch_topology.h @@ -12,8 +12,14 @@ void topology_normalize_cpu_scale(void); struct device_node; bool topology_parse_cpu_capacity(struct device_node *cpu_node, int cpu); +DECLARE_PER_CPU(unsigned long, cpu_scale); + struct sched_domain; -unsigned long topology_get_cpu_scale(struct sched_domain *sd, int cpu); +static inline +unsigned long topology_get_cpu_scale(struct sched_domain *sd, int cpu) +{ + return per_cpu(cpu_scale, cpu); +} void topology_set_cpu_scale(unsigned int cpu, unsigned long capacity); -- cgit v1.2.3 From 8055af0a4fddb45a8cd925fb9bc71f4b52628c9a Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Fri, 6 Oct 2017 09:08:34 +0200 Subject: ACPI / PM: Remove stale function header acpi_dev_pm_get_node() isn't used or implemented, so remove it. Signed-off-by: Ulf Hansson Acked-by: Pavel Machek Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 502af53ec012..3b89b4fe6812 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -868,17 +868,12 @@ int acpi_dev_runtime_suspend(struct device *dev); int acpi_dev_runtime_resume(struct device *dev); int acpi_subsys_runtime_suspend(struct device *dev); int acpi_subsys_runtime_resume(struct device *dev); -struct acpi_device *acpi_dev_pm_get_node(struct device *dev); int acpi_dev_pm_attach(struct device *dev, bool power_on); #else static inline int acpi_dev_runtime_suspend(struct device *dev) { return 0; } static inline int acpi_dev_runtime_resume(struct device *dev) { return 0; } static inline int acpi_subsys_runtime_suspend(struct device *dev) { return 0; } static inline int acpi_subsys_runtime_resume(struct device *dev) { return 0; } -static inline struct acpi_device *acpi_dev_pm_get_node(struct device *dev) -{ - return NULL; -} static inline int acpi_dev_pm_attach(struct device *dev, bool power_on) { return -ENODEV; -- cgit v1.2.3 From 604a7aeb4325b8ecb23df163c89fc12248302a4e Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Thu, 5 Oct 2017 17:26:21 +0530 Subject: PM / OPP: Rename dev_pm_opp_register_put_opp_helper() The routine is named incorrectly since the first attempt as there is nothing like a put_opp() helper. We wanted to unregister the set_opp() helper here and so it should rather be named as dev_pm_opp_unregister_set_opp_helper(). Signed-off-by: Viresh Kumar Reviewed-by: Stephen Boyd Signed-off-by: Rafael J. Wysocki --- include/linux/pm_opp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 51ec727b4824..849d21dc4ca7 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -124,7 +124,7 @@ void dev_pm_opp_put_regulators(struct opp_table *opp_table); struct opp_table *dev_pm_opp_set_clkname(struct device *dev, const char * name); void dev_pm_opp_put_clkname(struct opp_table *opp_table); struct opp_table *dev_pm_opp_register_set_opp_helper(struct device *dev, int (*set_opp)(struct dev_pm_set_opp_data *data)); -void dev_pm_opp_register_put_opp_helper(struct opp_table *opp_table); +void dev_pm_opp_unregister_set_opp_helper(struct opp_table *opp_table); int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq); int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev, const struct cpumask *cpumask); int dev_pm_opp_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask); @@ -243,7 +243,7 @@ static inline struct opp_table *dev_pm_opp_register_set_opp_helper(struct device return ERR_PTR(-ENOTSUPP); } -static inline void dev_pm_opp_register_put_opp_helper(struct opp_table *opp_table) {} +static inline void dev_pm_opp_unregister_set_opp_helper(struct opp_table *opp_table) {} static inline struct opp_table *dev_pm_opp_set_prop_name(struct device *dev, const char *name) { -- cgit v1.2.3 From 63705c406a8adbd6f26691148b09d466dd4d8d2f Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 10 Oct 2017 18:49:22 +0200 Subject: ACPI / PM: Combine two identical device resume routines Notice that acpi_dev_runtime_resume() and acpi_dev_resume_early() are actually literally identical after some more-or-less recent changes, so rename acpi_dev_runtime_resume() to acpi_dev_resume(), use it everywhere instead of acpi_dev_resume_early() and drop the latter. Signed-off-by: Rafael J. Wysocki Reviewed-by: Ulf Hansson --- include/linux/acpi.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 3b89b4fe6812..d18c92d4ba19 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -865,7 +865,7 @@ static inline void arch_reserve_mem_area(acpi_physical_address addr, #if defined(CONFIG_ACPI) && defined(CONFIG_PM) int acpi_dev_runtime_suspend(struct device *dev); -int acpi_dev_runtime_resume(struct device *dev); +int acpi_dev_resume(struct device *dev); int acpi_subsys_runtime_suspend(struct device *dev); int acpi_subsys_runtime_resume(struct device *dev); int acpi_dev_pm_attach(struct device *dev, bool power_on); @@ -882,7 +882,6 @@ static inline int acpi_dev_pm_attach(struct device *dev, bool power_on) #if defined(CONFIG_ACPI) && defined(CONFIG_PM_SLEEP) int acpi_dev_suspend_late(struct device *dev); -int acpi_dev_resume_early(struct device *dev); int acpi_subsys_prepare(struct device *dev); void acpi_subsys_complete(struct device *dev); int acpi_subsys_suspend_late(struct device *dev); -- cgit v1.2.3 From eeb2d80d502af28e5660ff4bbe00f90ceb82c2db Mon Sep 17 00:00:00 2001 From: Srinivas Pandruvada Date: Thu, 5 Oct 2017 16:24:03 -0700 Subject: ACPI / LPIT: Add Low Power Idle Table (LPIT) support Add functionality to read LPIT table, which provides: - Sysfs interface to read residency counters via /sys/devices/system/cpu/cpuidle/low_power_idle_cpu_residency_us /sys/devices/system/cpu/cpuidle/low_power_idle_system_residency_us Here the count "low_power_idle_cpu_residency_us" shows the time spent by CPU package in low power state. This is read via MSR interface, which points to MSR for PKG C10. Here the count "low_power_idle_system_residency_us" show the count the system was in low power state. This is read via MMIO interface. This is mapped to SLP_S0 residency on modern Intel systems. This residency is achieved only when CPU is in PKG C10 and all functional blocks are in low power state. It is possible that none of the above counters present or anyone of the counter present or all counters present. For example: On my Kabylake system both of the above counters present. After suspend to idle these counts updated and prints: 6916179 6998564 This counter can be read by tools like turbostat to display. Or it can be used to debug, if modern systems are reaching desired low power state. - Provides an interface to read residency counter memory address This address can be used to get the base address of PMC memory mapped IO. This is utilized by intel_pmc_core driver to print more debug information. In addition, to avoid code duplication to read iomem, removed the read of iomem from acpi_os_read_memory() in osl.c and made a common function acpi_os_read_iomem(). This new function is used for reading iomem in in both osl.c and acpi_lpit.c. Link: http://www.uefi.org/sites/default/files/resources/Intel_ACPI_Low_Power_S0_Idle.pdf Signed-off-by: Srinivas Pandruvada Signed-off-by: Rafael J. Wysocki --- include/acpi/acpiosxf.h | 2 ++ include/linux/acpi.h | 9 +++++++++ 2 files changed, 11 insertions(+) (limited to 'include') diff --git a/include/acpi/acpiosxf.h b/include/acpi/acpiosxf.h index c66eb8ffa454..d5c0f5153c4e 100644 --- a/include/acpi/acpiosxf.h +++ b/include/acpi/acpiosxf.h @@ -287,6 +287,8 @@ acpi_status acpi_os_write_port(acpi_io_address address, u32 value, u32 width); /* * Platform and hardware-independent physical memory interfaces */ +int acpi_os_read_iomem(void __iomem *virt_addr, u64 *value, u32 width); + #ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_read_memory acpi_status acpi_os_read_memory(acpi_physical_address address, u64 *value, u32 width); diff --git a/include/linux/acpi.h b/include/linux/acpi.h index d18c92d4ba19..2b1738f840ab 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1248,4 +1248,13 @@ int acpi_irq_get(acpi_handle handle, unsigned int index, struct resource *res) } #endif +#ifdef CONFIG_ACPI_LPIT +int lpit_read_residency_count_address(u64 *address); +#else +static inline int lpit_read_residency_count_address(u64 *address) +{ + return -EINVAL; +} +#endif + #endif /*_LINUX_ACPI_H*/ -- cgit v1.2.3 From 0e708fc602531b8355b5de6ea7c98f09129b223f Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Tue, 3 Oct 2017 09:11:07 +0200 Subject: PM / sleep: Remove pm_complete_with_resume_check() According to recent changes for ACPI, the are longer any users of pm_complete_with_resume_check(), thus let's drop it. Signed-off-by: Ulf Hansson Signed-off-by: Rafael J. Wysocki --- include/linux/pm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/pm.h b/include/linux/pm.h index 47ded8aa8a5d..a0ceeccf2846 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -736,7 +736,6 @@ extern int pm_generic_poweroff_noirq(struct device *dev); extern int pm_generic_poweroff_late(struct device *dev); extern int pm_generic_poweroff(struct device *dev); extern void pm_generic_complete(struct device *dev); -extern void pm_complete_with_resume_check(struct device *dev); #else /* !CONFIG_PM_SLEEP */ -- cgit v1.2.3 From 42f6284ae602469762ee721ec31ddfc6170e00bc Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Thu, 12 Oct 2017 15:07:23 +0530 Subject: PM / Domains: Add support to select performance-state of domains Some platforms have the capability to configure the performance state of PM domains. This patch enhances the genpd core to support such platforms. The performance levels (within the genpd core) are identified by positive integer values, a lower value represents lower performance state. This patch adds a new genpd API, which is called by user drivers (like OPP framework): - int dev_pm_genpd_set_performance_state(struct device *dev, unsigned int state); This updates the performance state constraint of the device on its PM domain. On success, the genpd will have its performance state set to a value which is >= "state" passed to this routine. The genpd core calls the genpd->set_performance_state() callback, if implemented, else -ENODEV is returned to the caller. The PM domain drivers need to implement the following callback if they want to support performance states. - int (*set_performance_state)(struct generic_pm_domain *genpd, unsigned int state); This is called internally by the genpd core on several occasions. The genpd core passes the genpd pointer and the aggregate of the performance states of the devices supported by that genpd to this callback. This callback must update the performance state of the genpd (in a platform dependent way). The power domains can avoid supplying above callback, if they don't support setting performance-states. Currently we aren't propagating performance state changes of a subdomain to its masters as we don't have hardware that needs it right now. Over that, the performance states of subdomain and its masters may not have one-to-one mapping and would require additional information. We can get back to this once we have hardware that needs it. Tested-by: Rajendra Nayak Signed-off-by: Viresh Kumar Acked-by: Ulf Hansson Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 84f423d5633e..9af0356bd69c 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -64,8 +64,11 @@ struct generic_pm_domain { unsigned int device_count; /* Number of devices */ unsigned int suspended_count; /* System suspend device counter */ unsigned int prepared_count; /* Suspend counter of prepared devices */ + unsigned int performance_state; /* Aggregated max performance state */ int (*power_off)(struct generic_pm_domain *domain); int (*power_on)(struct generic_pm_domain *domain); + int (*set_performance_state)(struct generic_pm_domain *genpd, + unsigned int state); struct gpd_dev_ops dev_ops; s64 max_off_time_ns; /* Maximum allowed "suspended" time. */ bool max_off_time_changed; @@ -121,6 +124,7 @@ struct generic_pm_domain_data { struct pm_domain_data base; struct gpd_timing_data td; struct notifier_block nb; + unsigned int performance_state; void *data; }; @@ -148,6 +152,8 @@ extern int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd, extern int pm_genpd_init(struct generic_pm_domain *genpd, struct dev_power_governor *gov, bool is_off); extern int pm_genpd_remove(struct generic_pm_domain *genpd); +extern int dev_pm_genpd_set_performance_state(struct device *dev, + unsigned int state); extern struct dev_power_governor simple_qos_governor; extern struct dev_power_governor pm_domain_always_on_gov; @@ -188,6 +194,12 @@ static inline int pm_genpd_remove(struct generic_pm_domain *genpd) return -ENOTSUPP; } +static inline int dev_pm_genpd_set_performance_state(struct device *dev, + unsigned int state) +{ + return -ENOTSUPP; +} + #define simple_qos_governor (*(struct dev_power_governor *)(NULL)) #define pm_domain_always_on_gov (*(struct dev_power_governor *)(NULL)) #endif -- cgit v1.2.3 From b6aa98364f842f943495408895627702ad7ad44b Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Wed, 11 Oct 2017 12:54:15 +0530 Subject: PM / OPP: Add dev_pm_opp_{un}register_get_pstate_helper() This adds the dev_pm_opp_{un}register_get_pstate_helper() helper routines which will be used to set the get_pstate() callback for a device. This callback will be later called internally by the OPP core to get performance state corresponding to an OPP. This is required temporarily until the time we have proper DT bindings to include the performance state information. Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/pm_opp.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 849d21dc4ca7..6c2d2e88f066 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -125,6 +125,8 @@ struct opp_table *dev_pm_opp_set_clkname(struct device *dev, const char * name); void dev_pm_opp_put_clkname(struct opp_table *opp_table); struct opp_table *dev_pm_opp_register_set_opp_helper(struct device *dev, int (*set_opp)(struct dev_pm_set_opp_data *data)); void dev_pm_opp_unregister_set_opp_helper(struct opp_table *opp_table); +struct opp_table *dev_pm_opp_register_get_pstate_helper(struct device *dev, int (*get_pstate)(struct device *dev, unsigned long rate)); +void dev_pm_opp_unregister_get_pstate_helper(struct opp_table *opp_table); int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq); int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev, const struct cpumask *cpumask); int dev_pm_opp_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask); @@ -245,6 +247,14 @@ static inline struct opp_table *dev_pm_opp_register_set_opp_helper(struct device static inline void dev_pm_opp_unregister_set_opp_helper(struct opp_table *opp_table) {} +static inline struct opp_table *dev_pm_opp_register_get_pstate_helper(struct device *dev, + int (*get_pstate)(struct device *dev, unsigned long rate)) +{ + return ERR_PTR(-ENOTSUPP); +} + +static inline void dev_pm_opp_unregister_get_pstate_helper(struct opp_table *opp_table) {} + static inline struct opp_table *dev_pm_opp_set_prop_name(struct device *dev, const char *name) { return ERR_PTR(-ENOTSUPP); -- cgit v1.2.3 From 20f97caf1120bd02e8ff4adbad3b44b63626feb5 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 13 Oct 2017 15:27:24 +0200 Subject: PM / QoS: Drop PM_QOS_FLAG_REMOTE_WAKEUP The PM QoS flag PM_QOS_FLAG_REMOTE_WAKEUP is not used consistently and the vast majority of code simply assumes that remote wakeup should be enabled for devices in runtime suspend if they can generate wakeup signals, so drop it. Signed-off-by: Rafael J. Wysocki Acked-by: Ulf Hansson Reviewed-by: Mika Westerberg --- include/linux/pm_qos.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/pm_qos.h b/include/linux/pm_qos.h index 032b55909145..51f0d7e0b15f 100644 --- a/include/linux/pm_qos.h +++ b/include/linux/pm_qos.h @@ -39,7 +39,6 @@ enum pm_qos_flags_status { #define PM_QOS_LATENCY_ANY ((s32)(~(__u32)0 >> 1)) #define PM_QOS_FLAG_NO_POWER_OFF (1 << 0) -#define PM_QOS_FLAG_REMOTE_WAKEUP (1 << 1) struct pm_qos_request { struct plist_node node; -- cgit v1.2.3 From cbe25ce37d6c2623b5ac09128987e98848a54c6c Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sat, 14 Oct 2017 17:43:15 +0200 Subject: ACPI / PM: Combine device suspend routines On top of a previous change getting rid of the PM QoS flag PM_QOS_FLAG_REMOTE_WAKEUP, combine two ACPI device suspend routines, acpi_dev_runtime_suspend() and acpi_dev_suspend_late(), into one, acpi_dev_suspend(), to eliminate some code duplication. It also avoids enabling wakeup for devices handled by the ACPI LPSS middle layer on driver removal. Signed-off-by: Rafael J. Wysocki Reviewed-by: Ulf Hansson --- include/linux/acpi.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 2b1738f840ab..0ada2a948b44 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -864,7 +864,7 @@ static inline void arch_reserve_mem_area(acpi_physical_address addr, #endif #if defined(CONFIG_ACPI) && defined(CONFIG_PM) -int acpi_dev_runtime_suspend(struct device *dev); +int acpi_dev_suspend(struct device *dev, bool wakeup); int acpi_dev_resume(struct device *dev); int acpi_subsys_runtime_suspend(struct device *dev); int acpi_subsys_runtime_resume(struct device *dev); @@ -889,7 +889,6 @@ int acpi_subsys_resume_early(struct device *dev); int acpi_subsys_suspend(struct device *dev); int acpi_subsys_freeze(struct device *dev); #else -static inline int acpi_dev_suspend_late(struct device *dev) { return 0; } static inline int acpi_dev_resume_early(struct device *dev) { return 0; } static inline int acpi_subsys_prepare(struct device *dev) { return 0; } static inline void acpi_subsys_complete(struct device *dev) {} -- cgit v1.2.3 From f1d981eaecf8ace68ec1d15bf05f28a4887ea6fb Mon Sep 17 00:00:00 2001 From: Chanwoo Choi Date: Mon, 23 Oct 2017 10:32:08 +0900 Subject: PM / devfreq: Use the available min/max frequency The commit a76caf55e5b35 ("thermal: Add devfreq cooling") is able to disable OPP as a cooling device. In result, both update_devfreq() and {min|max}_freq_show() have to consider the 'opp->available' status of each OPP. So, this patch adds the 'scaling_{min|max}_freq' to struct devfreq in order to indicate the available mininum and maximum frequency by adjusting OPP interface such as dev_pm_opp_{disable|enable}(). The 'scaling_{min|max}_freq' are used for on both update_devfreq() and {min|max}_freq_show(). Signed-off-by: Chanwoo Choi Signed-off-by: MyungJoo Ham --- include/linux/devfreq.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h index 597294e0cc40..997a9eb34191 100644 --- a/include/linux/devfreq.h +++ b/include/linux/devfreq.h @@ -120,6 +120,8 @@ struct devfreq_dev_profile { * touch this. * @min_freq: Limit minimum frequency requested by user (0: none) * @max_freq: Limit maximum frequency requested by user (0: none) + * @scaling_min_freq: Limit minimum frequency requested by OPP interface + * @scaling_max_freq: Limit maximum frequency requested by OPP interface * @stop_polling: devfreq polling status of a device. * @total_trans: Number of devfreq transitions * @trans_table: Statistics of devfreq transitions @@ -153,6 +155,8 @@ struct devfreq { unsigned long min_freq; unsigned long max_freq; + unsigned long scaling_min_freq; + unsigned long scaling_max_freq; bool stop_polling; /* information for device frequency transition */ -- cgit v1.2.3 From 416b46a2627ae8de1466f90787dede6f9c5a1bfa Mon Sep 17 00:00:00 2001 From: Chanwoo Choi Date: Mon, 23 Oct 2017 10:32:10 +0900 Subject: PM / devfreq: Show the all available frequencies The commit a76caf55e5b35 ("thermal: Add devfreq cooling") allows the devfreq device to use the cooling device. When the cooling down are required, the devfreq_cooling.c disables the OPP entry with the dev_pm_opp_disable(). In result, 'available_frequencies'[1] sysfs node never came to show the all available frequencies. [1] /sys/class/devfreq/.../available_frequencies So, this patch uses the 'freq_table' in the 'struct devfreq_dev_profile' in order to show the all available frequencies. - If 'freq_table' is NULL, devfreq core initializes them by using OPP values. - If 'freq_table' is initialized, devfreq core just uses the 'freq_table'. And this patch adds some comment about the sort way of 'freq_table'. Signed-off-by: Chanwoo Choi Signed-off-by: MyungJoo Ham --- include/linux/devfreq.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h index 997a9eb34191..19520625ea94 100644 --- a/include/linux/devfreq.h +++ b/include/linux/devfreq.h @@ -84,8 +84,9 @@ struct devfreq_dev_status { * from devfreq_remove_device() call. If the user * has registered devfreq->nb at a notifier-head, * this is the time to unregister it. - * @freq_table: Optional list of frequencies to support statistics. - * @max_state: The size of freq_table. + * @freq_table: Optional list of frequencies to support statistics + * and freq_table must be generated in ascending order. + * @max_state: The size of freq_table. */ struct devfreq_dev_profile { unsigned long initial_freq; -- cgit v1.2.3 From aa7c352f9841ab3fee5bf1de127a45e6310124a6 Mon Sep 17 00:00:00 2001 From: Chanwoo Choi Date: Mon, 23 Oct 2017 10:32:12 +0900 Subject: PM / devfreq: Define the constant governor name Prior to that, the devfreq device uses the governor name when adding the itself. In order to prevent the mistake used the wrong governor name, this patch defines the governor name as a constant and then uses them instead of using the string directly. Signed-off-by: Chanwoo Choi Signed-off-by: MyungJoo Ham Cc: Kukjin Kim Cc: Krzysztof Kozlowski Cc: linux-samsung-soc@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-kernel@vger.kernel.org --- include/linux/devfreq.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h index 19520625ea94..3aae5b3af87c 100644 --- a/include/linux/devfreq.h +++ b/include/linux/devfreq.h @@ -19,6 +19,13 @@ #define DEVFREQ_NAME_LEN 16 +/* DEVFREQ governor name */ +#define DEVFREQ_GOV_SIMPLE_ONDEMAND "simple_ondemand" +#define DEVFREQ_GOV_PERFORMANCE "performance" +#define DEVFREQ_GOV_POWERSAVE "powersave" +#define DEVFREQ_GOV_USERSPACE "userspace" +#define DEVFREQ_GOV_PASSIVE "passive" + /* DEVFREQ notifier interface */ #define DEVFREQ_TRANSITION_NOTIFIER (0) -- cgit v1.2.3 From 08810a4119aaebf6318f209ec5dd9828e969cba4 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 25 Oct 2017 14:12:29 +0200 Subject: PM / core: Add NEVER_SKIP and SMART_PREPARE driver flags The motivation for this change is to provide a way to work around a problem with the direct-complete mechanism used for avoiding system suspend/resume handling for devices in runtime suspend. The problem is that some middle layer code (the PCI bus type and the ACPI PM domain in particular) returns positive values from its system suspend ->prepare callbacks regardless of whether the driver's ->prepare returns a positive value or 0, which effectively prevents drivers from being able to control the direct-complete feature. Some drivers need that control, however, and the PCI bus type has grown its own flag to deal with this issue, but since it is not limited to PCI, it is better to address it by adding driver flags at the core level. To that end, add a driver_flags field to struct dev_pm_info for flags that can be set by device drivers at the probe time to inform the PM core and/or bus types, PM domains and so on on the capabilities and/or preferences of device drivers. Also add two static inline helpers for setting that field and testing it against a given set of flags and make the driver core clear it automatically on driver remove and probe failures. Define and document two PM driver flags related to the direct- complete feature: NEVER_SKIP and SMART_PREPARE that can be used, respectively, to indicate to the PM core that the direct-complete mechanism should never be used for the device and to inform the middle layer code (bus types, PM domains etc) that it can only request the PM core to use the direct-complete mechanism for the device (by returning a positive value from its ->prepare callback) if it also has been requested by the driver. While at it, make the core check pm_runtime_suspended() when setting power.direct_complete so that it doesn't need to be checked by ->prepare callbacks. Signed-off-by: Rafael J. Wysocki Acked-by: Greg Kroah-Hartman Acked-by: Bjorn Helgaas Reviewed-by: Ulf Hansson --- include/linux/device.h | 10 ++++++++++ include/linux/pm.h | 20 ++++++++++++++++++++ 2 files changed, 30 insertions(+) (limited to 'include') diff --git a/include/linux/device.h b/include/linux/device.h index c32e6f974d4a..fb9451599aca 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1070,6 +1070,16 @@ static inline void dev_pm_syscore_device(struct device *dev, bool val) #endif } +static inline void dev_pm_set_driver_flags(struct device *dev, u32 flags) +{ + dev->power.driver_flags = flags; +} + +static inline bool dev_pm_test_driver_flags(struct device *dev, u32 flags) +{ + return !!(dev->power.driver_flags & flags); +} + static inline void device_lock(struct device *dev) { mutex_lock(&dev->mutex); diff --git a/include/linux/pm.h b/include/linux/pm.h index a0ceeccf2846..f10bad831bfa 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -550,6 +550,25 @@ struct pm_subsys_data { #endif }; +/* + * Driver flags to control system suspend/resume behavior. + * + * These flags can be set by device drivers at the probe time. They need not be + * cleared by the drivers as the driver core will take care of that. + * + * NEVER_SKIP: Do not skip system suspend/resume callbacks for the device. + * SMART_PREPARE: Check the return value of the driver's ->prepare callback. + * + * Setting SMART_PREPARE instructs bus types and PM domains which may want + * system suspend/resume callbacks to be skipped for the device to return 0 from + * their ->prepare callbacks if the driver's ->prepare callback returns 0 (in + * other words, the system suspend/resume callbacks can only be skipped for the + * device if its driver doesn't object against that). This flag has no effect + * if NEVER_SKIP is set. + */ +#define DPM_FLAG_NEVER_SKIP BIT(0) +#define DPM_FLAG_SMART_PREPARE BIT(1) + struct dev_pm_info { pm_message_t power_state; unsigned int can_wakeup:1; @@ -561,6 +580,7 @@ struct dev_pm_info { bool is_late_suspended:1; bool early_init:1; /* Owned by the PM core */ bool direct_complete:1; /* Owned by the PM core */ + u32 driver_flags; spinlock_t lock; #ifdef CONFIG_PM_SLEEP struct list_head entry; -- cgit v1.2.3 From c2eac4d3a115e2f511844e7bcf73f4e877fbf5da Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 25 Oct 2017 14:16:46 +0200 Subject: PCI / PM: Use the NEVER_SKIP driver flag Replace the PCI-specific flag PCI_DEV_FLAGS_NEEDS_RESUME with the PM core's DPM_FLAG_NEVER_SKIP one everywhere and drop it. Signed-off-by: Rafael J. Wysocki Acked-by: Greg Kroah-Hartman Acked-by: Bjorn Helgaas Reviewed-by: Ulf Hansson --- include/linux/pci.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/pci.h b/include/linux/pci.h index f4f8ee5a7362..4b65fa4fb94e 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -205,13 +205,8 @@ enum pci_dev_flags { PCI_DEV_FLAGS_BRIDGE_XLATE_ROOT = (__force pci_dev_flags_t) (1 << 9), /* Do not use FLR even if device advertises PCI_AF_CAP */ PCI_DEV_FLAGS_NO_FLR_RESET = (__force pci_dev_flags_t) (1 << 10), - /* - * Resume before calling the driver's system suspend hooks, disabling - * the direct_complete optimization. - */ - PCI_DEV_FLAGS_NEEDS_RESUME = (__force pci_dev_flags_t) (1 << 11), /* Don't use Relaxed Ordering for TLPs directed at this device */ - PCI_DEV_FLAGS_NO_RELAXED_ORDERING = (__force pci_dev_flags_t) (1 << 12), + PCI_DEV_FLAGS_NO_RELAXED_ORDERING = (__force pci_dev_flags_t) (1 << 11), }; enum pci_irq_reroute_variant { -- cgit v1.2.3 From 0eab11c9ae3b3cc5dd76f20b81d0247647a6e96f Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 26 Oct 2017 12:12:08 +0200 Subject: PM / core: Add SMART_SUSPEND driver flag Define and document a SMART_SUSPEND flag to instruct bus types and PM domains that the system suspend callbacks provided by the driver can cope with runtime-suspended devices, so from the driver's perspective it should be safe to leave devices in runtime suspend during system suspend. Setting that flag may also cause middle-layer code (bus types, PM domains etc.) to skip invocations of the ->suspend_late and ->suspend_noirq callbacks provided by the driver if the device is in runtime suspend at the beginning of the "late" phase of the system-wide suspend transition, in which case the driver's system-wide resume callbacks may be invoked back-to-back with its ->runtime_suspend callback, so the driver has to be able to cope with that too. Signed-off-by: Rafael J. Wysocki Acked-by: Greg Kroah-Hartman Reviewed-by: Ulf Hansson --- include/linux/pm.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/pm.h b/include/linux/pm.h index f10bad831bfa..43b5418e05bb 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -558,6 +558,7 @@ struct pm_subsys_data { * * NEVER_SKIP: Do not skip system suspend/resume callbacks for the device. * SMART_PREPARE: Check the return value of the driver's ->prepare callback. + * SMART_SUSPEND: No need to resume the device from runtime suspend. * * Setting SMART_PREPARE instructs bus types and PM domains which may want * system suspend/resume callbacks to be skipped for the device to return 0 from @@ -565,9 +566,16 @@ struct pm_subsys_data { * other words, the system suspend/resume callbacks can only be skipped for the * device if its driver doesn't object against that). This flag has no effect * if NEVER_SKIP is set. + * + * Setting SMART_SUSPEND instructs bus types and PM domains which may want to + * runtime resume the device upfront during system suspend that doing so is not + * necessary from the driver's perspective. It also may cause them to skip + * invocations of the ->suspend_late and ->suspend_noirq callbacks provided by + * the driver if they decide to leave the device in runtime suspend. */ #define DPM_FLAG_NEVER_SKIP BIT(0) #define DPM_FLAG_SMART_PREPARE BIT(1) +#define DPM_FLAG_SMART_SUSPEND BIT(2) struct dev_pm_info { pm_message_t power_state; -- cgit v1.2.3 From c4b65157aeefad29b2351a00a010e8c40ce7fd0e Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 26 Oct 2017 12:12:22 +0200 Subject: PCI / PM: Take SMART_SUSPEND driver flag into account Make the PCI bus type take DPM_FLAG_SMART_SUSPEND into account in its system-wide PM callbacks and make sure that all code that should not run in parallel with pci_pm_runtime_resume() is executed in the "late" phases of system suspend, freeze and poweroff transitions. [Note that the pm_runtime_suspended() check in pci_dev_keep_suspended() is an optimization, because if is not passed, all of the subsequent checks may be skipped and some of them are much more overhead in general.] Also use the observation that if the device is in runtime suspend at the beginning of the "late" phase of a system-wide suspend-like transition, its state cannot change going forward (runtime PM is disabled for it at that time) until the transition is over and the subsequent system-wide PM callbacks should be skipped for it (as they generally assume the device to not be suspended), so add checks for that in pci_pm_suspend_late/noirq(), pci_pm_freeze_late/noirq() and pci_pm_poweroff_late/noirq(). Moreover, if pci_pm_resume_noirq() or pci_pm_restore_noirq() is called during the subsequent system-wide resume transition and if the device was left in runtime suspend previously, its runtime PM status needs to be changed to "active" as it is going to be put into the full-power state, so add checks for that too to these functions. In turn, if pci_pm_thaw_noirq() runs after the device has been left in runtime suspend, the subsequent "thaw" callbacks need to be skipped for it (as they may not work correctly with a suspended device), so set the power.direct_complete flag for the device then to make the PM core skip those callbacks. In addition to the above add a core helper for checking if DPM_FLAG_SMART_SUSPEND is set and the device runtime PM status is "suspended" at the same time, which is done quite often in the new code (and will be done elsewhere going forward too). Signed-off-by: Rafael J. Wysocki Acked-by: Greg Kroah-Hartman Acked-by: Bjorn Helgaas --- include/linux/pm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/pm.h b/include/linux/pm.h index 43b5418e05bb..65d39115f06d 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -765,6 +765,8 @@ extern int pm_generic_poweroff_late(struct device *dev); extern int pm_generic_poweroff(struct device *dev); extern void pm_generic_complete(struct device *dev); +extern bool dev_pm_smart_suspend_and_suspended(struct device *dev); + #else /* !CONFIG_PM_SLEEP */ #define device_pm_lock() do {} while (0) -- cgit v1.2.3 From 05087360fd7acf2cc9b7bbb243c12765c44c7693 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 27 Oct 2017 10:10:16 +0200 Subject: ACPI / PM: Take SMART_SUSPEND driver flag into account Make the ACPI PM domain take DPM_FLAG_SMART_SUSPEND into account in its system suspend callbacks. [Note that the pm_runtime_suspended() check in acpi_dev_needs_resume() is an optimization, because if is not passed, all of the subsequent checks may be skipped and some of them are much more overhead in general.] Also use the observation that if the device is in runtime suspend at the beginning of the "late" phase of a system-wide suspend-like transition, its state cannot change going forward (runtime PM is disabled for it at that time) until the transition is over and the subsequent system-wide PM callbacks should be skipped for it (as they generally assume the device to not be suspended), so add checks for that in acpi_subsys_suspend_late/noirq() and acpi_subsys_freeze_late/noirq(). Moreover, if acpi_subsys_resume_noirq() is called during the subsequent system-wide resume transition and if the device was left in runtime suspend previously, its runtime PM status needs to be changed to "active" as it is going to be put into the full-power state going forward, so add a check for that too in there. In turn, if acpi_subsys_thaw_noirq() runs after the device has been left in runtime suspend, the subsequent "thaw" callbacks need to be skipped for it (as they may not work correctly with a suspended device), so set the power.direct_complete flag for the device then to make the PM core skip those callbacks. On top of the above, make the analogous changes in the acpi_lpss driver that uses the ACPI PM domain callbacks. Signed-off-by: Rafael J. Wysocki Acked-by: Greg Kroah-Hartman --- include/linux/acpi.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 0ada2a948b44..dc1ebfeeb5ec 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -885,17 +885,27 @@ int acpi_dev_suspend_late(struct device *dev); int acpi_subsys_prepare(struct device *dev); void acpi_subsys_complete(struct device *dev); int acpi_subsys_suspend_late(struct device *dev); +int acpi_subsys_suspend_noirq(struct device *dev); +int acpi_subsys_resume_noirq(struct device *dev); int acpi_subsys_resume_early(struct device *dev); int acpi_subsys_suspend(struct device *dev); int acpi_subsys_freeze(struct device *dev); +int acpi_subsys_freeze_late(struct device *dev); +int acpi_subsys_freeze_noirq(struct device *dev); +int acpi_subsys_thaw_noirq(struct device *dev); #else static inline int acpi_dev_resume_early(struct device *dev) { return 0; } static inline int acpi_subsys_prepare(struct device *dev) { return 0; } static inline void acpi_subsys_complete(struct device *dev) {} static inline int acpi_subsys_suspend_late(struct device *dev) { return 0; } +static inline int acpi_subsys_suspend_noirq(struct device *dev) { return 0; } +static inline int acpi_subsys_resume_noirq(struct device *dev) { return 0; } static inline int acpi_subsys_resume_early(struct device *dev) { return 0; } static inline int acpi_subsys_suspend(struct device *dev) { return 0; } static inline int acpi_subsys_freeze(struct device *dev) { return 0; } +static inline int acpi_subsys_freeze_late(struct device *dev) { return 0; } +static inline int acpi_subsys_freeze_noirq(struct device *dev) { return 0; } +static inline int acpi_subsys_thaw_noirq(struct device *dev) { return 0; } #endif #ifdef CONFIG_ACPI -- cgit v1.2.3 From 95a20ef6f7e54c6a982715a7d0da2fd81790db28 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Tue, 7 Nov 2017 13:48:11 +0100 Subject: PM / Domains: Allow genpd users to specify default active wakeup behavior It is quite common for PM Domains to require slave devices to be kept active during system suspend if they are to be used as wakeup sources. To enable this, currently each PM Domain or driver has to provide its own gpd_dev_ops.active_wakeup() callback. Introduce a new flag GENPD_FLAG_ACTIVE_WAKEUP to consolidate this. If specified, all slave devices configured as wakeup sources will be kept active during system suspend. PM Domains that need more fine-grained controls, based on the slave device, can still provide their own callbacks, as before. Signed-off-by: Geert Uytterhoeven Acked-by: Ulf Hansson Reviewed-by: Kevin Hilman Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 9af0356bd69c..28c24c58d479 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -18,9 +18,10 @@ #include /* Defines used for the flags field in the struct generic_pm_domain */ -#define GENPD_FLAG_PM_CLK (1U << 0) /* PM domain uses PM clk */ -#define GENPD_FLAG_IRQ_SAFE (1U << 1) /* PM domain operates in atomic */ -#define GENPD_FLAG_ALWAYS_ON (1U << 2) /* PM domain is always powered on */ +#define GENPD_FLAG_PM_CLK (1U << 0) /* PM domain uses PM clk */ +#define GENPD_FLAG_IRQ_SAFE (1U << 1) /* PM domain operates in atomic */ +#define GENPD_FLAG_ALWAYS_ON (1U << 2) /* PM domain is always powered on */ +#define GENPD_FLAG_ACTIVE_WAKEUP (1U << 3) /* Keep devices active if wakeup */ enum gpd_status { GPD_STATE_ACTIVE = 0, /* PM domain is active */ -- cgit v1.2.3 From d0af45f1f6528949e05385976eb61c5ebd31854e Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Tue, 7 Nov 2017 13:48:15 +0100 Subject: PM / Domains: Remove gpd_dev_ops.active_wakeup() callback There are no more users left of the gpd_dev_ops.active_wakeup() callback. All have been converted to GENPD_FLAG_ACTIVE_WAKEUP. Hence remove the callback. Signed-off-by: Geert Uytterhoeven Acked-by: Ulf Hansson Reviewed-by: Kevin Hilman Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 28c24c58d479..04dbef9847d3 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -36,7 +36,6 @@ struct dev_power_governor { struct gpd_dev_ops { int (*start)(struct device *dev); int (*stop)(struct device *dev); - bool (*active_wakeup)(struct device *dev); }; struct genpd_power_state { -- cgit v1.2.3 From 0759e80b84e34a84e7e46e2b1adb528c83d84a47 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 7 Nov 2017 11:33:49 +0100 Subject: PM / QoS: Fix device resume latency framework The special value of 0 for device resume latency PM QoS means "no restriction", but there are two problems with that. First, device resume latency PM QoS requests with 0 as the value are always put in front of requests with positive values in the priority lists used internally by the PM QoS framework, causing 0 to be chosen as an effective constraint value. However, that 0 is then interpreted as "no restriction" effectively overriding the other requests with specific restrictions which is incorrect. Second, the users of device resume latency PM QoS have no way to specify that *any* resume latency at all should be avoided, which is an artificial limitation in general. To address these issues, modify device resume latency PM QoS to use S32_MAX as the "no constraint" value and 0 as the "no latency at all" one and rework its users (the cpuidle menu governor, the genpd QoS governor and the runtime PM framework) to follow these changes. Also add a special "n/a" value to the corresponding user space I/F to allow user space to indicate that it cannot accept any resume latencies at all for the given device. Fixes: 85dc0b8a4019 (PM / QoS: Make it possible to expose PM QoS latency constraints) Link: https://bugzilla.kernel.org/show_bug.cgi?id=197323 Reported-by: Reinette Chatre Signed-off-by: Rafael J. Wysocki Tested-by: Reinette Chatre Tested-by: Geert Uytterhoeven Tested-by: Tero Kristo Reviewed-by: Ramesh Thomas --- include/linux/pm_qos.h | 26 ++++++++++++++++++-------- 1 file changed, 18 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/pm_qos.h b/include/linux/pm_qos.h index 51f0d7e0b15f..2a3b36da61b1 100644 --- a/include/linux/pm_qos.h +++ b/include/linux/pm_qos.h @@ -27,16 +27,19 @@ enum pm_qos_flags_status { PM_QOS_FLAGS_ALL, }; -#define PM_QOS_DEFAULT_VALUE -1 +#define PM_QOS_DEFAULT_VALUE (-1) +#define PM_QOS_LATENCY_ANY S32_MAX +#define PM_QOS_LATENCY_ANY_NS ((s64)PM_QOS_LATENCY_ANY * NSEC_PER_USEC) #define PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE (2000 * USEC_PER_SEC) #define PM_QOS_NETWORK_LAT_DEFAULT_VALUE (2000 * USEC_PER_SEC) #define PM_QOS_NETWORK_THROUGHPUT_DEFAULT_VALUE 0 #define PM_QOS_MEMORY_BANDWIDTH_DEFAULT_VALUE 0 -#define PM_QOS_RESUME_LATENCY_DEFAULT_VALUE 0 +#define PM_QOS_RESUME_LATENCY_DEFAULT_VALUE PM_QOS_LATENCY_ANY +#define PM_QOS_RESUME_LATENCY_NO_CONSTRAINT PM_QOS_LATENCY_ANY +#define PM_QOS_RESUME_LATENCY_NO_CONSTRAINT_NS PM_QOS_LATENCY_ANY_NS #define PM_QOS_LATENCY_TOLERANCE_DEFAULT_VALUE 0 #define PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT (-1) -#define PM_QOS_LATENCY_ANY ((s32)(~(__u32)0 >> 1)) #define PM_QOS_FLAG_NO_POWER_OFF (1 << 0) @@ -173,7 +176,8 @@ static inline s32 dev_pm_qos_requested_flags(struct device *dev) static inline s32 dev_pm_qos_raw_read_value(struct device *dev) { return IS_ERR_OR_NULL(dev->power.qos) ? - 0 : pm_qos_read_value(&dev->power.qos->resume_latency); + PM_QOS_RESUME_LATENCY_NO_CONSTRAINT : + pm_qos_read_value(&dev->power.qos->resume_latency); } #else static inline enum pm_qos_flags_status __dev_pm_qos_flags(struct device *dev, @@ -183,9 +187,9 @@ static inline enum pm_qos_flags_status dev_pm_qos_flags(struct device *dev, s32 mask) { return PM_QOS_FLAGS_UNDEFINED; } static inline s32 __dev_pm_qos_read_value(struct device *dev) - { return 0; } + { return PM_QOS_RESUME_LATENCY_NO_CONSTRAINT; } static inline s32 dev_pm_qos_read_value(struct device *dev) - { return 0; } + { return PM_QOS_RESUME_LATENCY_NO_CONSTRAINT; } static inline int dev_pm_qos_add_request(struct device *dev, struct dev_pm_qos_request *req, enum dev_pm_qos_req_type type, @@ -231,9 +235,15 @@ static inline int dev_pm_qos_expose_latency_tolerance(struct device *dev) { return 0; } static inline void dev_pm_qos_hide_latency_tolerance(struct device *dev) {} -static inline s32 dev_pm_qos_requested_resume_latency(struct device *dev) { return 0; } +static inline s32 dev_pm_qos_requested_resume_latency(struct device *dev) +{ + return PM_QOS_RESUME_LATENCY_NO_CONSTRAINT; +} static inline s32 dev_pm_qos_requested_flags(struct device *dev) { return 0; } -static inline s32 dev_pm_qos_raw_read_value(struct device *dev) { return 0; } +static inline s32 dev_pm_qos_raw_read_value(struct device *dev) +{ + return PM_QOS_RESUME_LATENCY_NO_CONSTRAINT; +} #endif #endif -- cgit v1.2.3 From 2dd9789c76ffde05d5f4c56f45c3cb71b3936694 Mon Sep 17 00:00:00 2001 From: Himanshu Jha Date: Sun, 5 Nov 2017 03:27:32 +0530 Subject: freezer: Fix typo in freezable_schedule_timeout() comment Signed-off-by: Himanshu Jha Acked-by: Luis R. Rodriguez Acked-by: Pavel Machek Signed-off-by: Rafael J. Wysocki --- include/linux/freezer.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/freezer.h b/include/linux/freezer.h index dd03e837ebb7..5b2cf48b2a7c 100644 --- a/include/linux/freezer.h +++ b/include/linux/freezer.h @@ -181,7 +181,7 @@ static inline void freezable_schedule_unsafe(void) } /* - * Like freezable_schedule_timeout(), but should not block the freezer. Do not + * Like schedule_timeout(), but should not block the freezer. Do not * call this with locks held. */ static inline long freezable_schedule_timeout(long timeout) -- cgit v1.2.3