From 33e4f80ee69b5168badf37edbfed796eb48434b9 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 12 Jun 2017 22:56:34 +0200 Subject: ACPI / PM: Ignore spurious SCI wakeups from suspend-to-idle The ACPI SCI (System Control Interrupt) is set up as a wakeup IRQ during suspend-to-idle transitions and, consequently, any events signaled through it wake up the system from that state. However, on some systems some of the events signaled via the ACPI SCI while suspended to idle should not cause the system to wake up. In fact, quite often they should just be discarded. Arguably, systems should not resume entirely on such events, but in order to decide which events really should cause the system to resume and which are spurious, it is necessary to resume up to the point when ACPI SCIs are actually handled and processed, which is after executing dpm_resume_noirq() in the system resume path. For this reasons, add a loop around freeze_enter() in which the platforms can process events signaled via multiplexed IRQ lines like the ACPI SCI and add suspend-to-idle hooks that can be used for this purpose to struct platform_freeze_ops. In the ACPI case, the ->wake hook is used for checking if the SCI has triggered while suspended and deferring the interrupt-induced system wakeup until the events signaled through it are actually processed sufficiently to decide whether or not the system should resume. In turn, the ->sync hook allows all of the relevant event queues to be flushed so as to prevent events from being missed due to race conditions. In addition to that, some ACPI code processing wakeup events needs to be modified to use the "hard" version of wakeup triggers, so that it will cause a system resume to happen on device-induced wakeup events even if the "soft" mechanism to prevent the system from suspending is not enabled. However, to preserve the existing behavior with respect to suspend-to-RAM, this only is done in the suspend-to-idle case and only if an SCI has occurred while suspended. Signed-off-by: Rafael J. Wysocki --- include/linux/suspend.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/suspend.h b/include/linux/suspend.h index d9718378a8be..0b1cf32edfd7 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -189,6 +189,8 @@ struct platform_suspend_ops { struct platform_freeze_ops { int (*begin)(void); int (*prepare)(void); + void (*wake)(void); + void (*sync)(void); void (*restore)(void); void (*end)(void); }; @@ -428,7 +430,8 @@ extern unsigned int pm_wakeup_irq; extern bool pm_wakeup_pending(void); extern void pm_system_wakeup(void); -extern void pm_wakeup_clear(void); +extern void pm_system_cancel_wakeup(void); +extern void pm_wakeup_clear(bool reset); extern void pm_system_irq_wakeup(unsigned int irq_number); extern bool pm_get_wakeup_count(unsigned int *count, bool block); extern bool pm_save_wakeup_count(unsigned int count); @@ -478,7 +481,7 @@ static inline int unregister_pm_notifier(struct notifier_block *nb) static inline bool pm_wakeup_pending(void) { return false; } static inline void pm_system_wakeup(void) {} -static inline void pm_wakeup_clear(void) {} +static inline void pm_wakeup_clear(bool reset) {} static inline void pm_system_irq_wakeup(unsigned int irq_number) {} static inline void lock_system_sleep(void) {} -- cgit v1.2.3 From 829a4e8c0e9aab17bcfe2ddb070388b8ada26292 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Wed, 21 Jun 2017 10:29:13 +0530 Subject: PM / OPP: Add dev_pm_opp_{set|put}_clkname() In order to support OPP switching, OPP layer needs to get pointer to the clock for the device. Simple cases work fine without using the routines added by this patch (i.e. by passing connection-id as NULL), but for a device with multiple clocks available, the OPP core needs to know the exact name of the clk to use. Add a new set of APIs to get that done. Tested-by: Rajendra Nayak Signed-off-by: Viresh Kumar Reviewed-by: Stephen Boyd Signed-off-by: Rafael J. Wysocki --- include/linux/pm_opp.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index a6685b3dde26..51ec727b4824 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -121,6 +121,8 @@ struct opp_table *dev_pm_opp_set_prop_name(struct device *dev, const char *name) void dev_pm_opp_put_prop_name(struct opp_table *opp_table); struct opp_table *dev_pm_opp_set_regulators(struct device *dev, const char * const names[], unsigned int count); 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); int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq); @@ -257,6 +259,13 @@ static inline struct opp_table *dev_pm_opp_set_regulators(struct device *dev, co static inline void dev_pm_opp_put_regulators(struct opp_table *opp_table) {} +static inline struct opp_table *dev_pm_opp_set_clkname(struct device *dev, const char * name) +{ + return ERR_PTR(-ENOTSUPP); +} + +static inline void dev_pm_opp_put_clkname(struct opp_table *opp_table) {} + static inline int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq) { return -ENOTSUPP; -- cgit v1.2.3 From f8475cef90082bf0902ddab106112de130d90395 Mon Sep 17 00:00:00 2001 From: Len Brown Date: Fri, 23 Jun 2017 22:11:52 -0700 Subject: x86: use common aperfmperf_khz_on_cpu() to calculate KHz using APERF/MPERF The goal of this change is to give users a uniform and meaningful result when they read /sys/...cpufreq/scaling_cur_freq on modern x86 hardware, as compared to what they get today. Modern x86 processors include the hardware needed to accurately calculate frequency over an interval -- APERF, MPERF, and the TSC. Here we provide an x86 routine to make this calculation on supported hardware, and use it in preference to any driver driver-specific cpufreq_driver.get() routine. MHz is computed like so: MHz = base_MHz * delta_APERF / delta_MPERF MHz is the average frequency of the busy processor over a measurement interval. The interval is defined to be the time between successive invocations of aperfmperf_khz_on_cpu(), which are expected to to happen on-demand when users read sysfs attribute cpufreq/scaling_cur_freq. As with previous methods of calculating MHz, idle time is excluded. base_MHz above is from TSC calibration global "cpu_khz". This x86 native method to calculate MHz returns a meaningful result no matter if P-states are controlled by hardware or firmware and/or if the Linux cpufreq sub-system is or is-not installed. When this routine is invoked more frequently, the measurement interval becomes shorter. However, the code limits re-computation to 10ms intervals so that average frequency remains meaningful. Discerning users are encouraged to take advantage of the turbostat(8) utility, which can gracefully handle concurrent measurement intervals of arbitrary length. Signed-off-by: Len Brown Reviewed-by: Thomas Gleixner Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index a5ce0bbeadb5..905117bd5012 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -883,6 +883,8 @@ static inline bool policy_has_boost_freq(struct cpufreq_policy *policy) } #endif +extern unsigned int arch_freq_get_on_cpu(int cpu); + /* 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 8370c2dc4c7b91be7e1231130f0ae08b5aebecf4 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sat, 24 Jun 2017 01:56:13 +0200 Subject: PCI / PM: Drop pme_interrupt flag from struct pci_dev The pme_interrupt flag in struct pci_dev is set when PMEs generated by the device are going to be signaled via root port PME interrupts. Ironically enough, that information is only used by the code setting up device wakeup through ACPI which returns as soon as it sees the pme_interrupt flag set while setting up "remote runtime wakeup". That is questionable, however, because in theory there may be PCIe devices using out-of-band PME signaling under root ports handled by the native PME code or devices requiring wakeup power setup to be carried out by AML. For such devices, ACPI wakeup should be invoked regardless of whether or not native PME signaling is used in general. For this reason, drop the pme_interrupt flag and rework the code using it which then allows the ACPI-based device wakeup handling in PCI to be consolidated to use one code path for both "runtime remote wakeup" and system wakeup (from sleep states). Signed-off-by: Rafael J. Wysocki Reviewed-by: Mika Westerberg Acked-by: Bjorn Helgaas --- include/linux/pci.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 8039f9f0ca05..d3d5bca82b43 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -307,7 +307,6 @@ struct pci_dev { u8 pm_cap; /* PM capability offset */ unsigned int pme_support:5; /* Bitmask of states from which PME# can be generated */ - unsigned int pme_interrupt:1; unsigned int pme_poll:1; /* Poll device's PME status bit */ unsigned int d1_support:1; /* Low power state D1 is supported */ unsigned int d2_support:1; /* Low power state D2 is supported */ -- cgit v1.2.3 From 0847684cfc5f0e9f009919bfdcb041d60e19b856 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sat, 24 Jun 2017 01:57:35 +0200 Subject: PCI / PM: Simplify device wakeup settings code After previous changes it is not necessary to distinguish between device wakeup for run time and device wakeup from system sleep states any more, so rework the PCI device wakeup settings code accordingly. Signed-off-by: Rafael J. Wysocki Reviewed-by: Mika Westerberg Acked-by: Bjorn Helgaas --- include/linux/pci.h | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index d3d5bca82b43..ff200c84240b 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1097,8 +1097,7 @@ int pci_set_power_state(struct pci_dev *dev, pci_power_t state); pci_power_t pci_choose_state(struct pci_dev *dev, pm_message_t state); bool pci_pme_capable(struct pci_dev *dev, pci_power_t state); void pci_pme_active(struct pci_dev *dev, bool enable); -int __pci_enable_wake(struct pci_dev *dev, pci_power_t state, - bool runtime, bool enable); +int pci_enable_wake(struct pci_dev *dev, pci_power_t state, bool enable); int pci_wake_from_d3(struct pci_dev *dev, bool enable); int pci_prepare_to_sleep(struct pci_dev *dev); int pci_back_from_sleep(struct pci_dev *dev); @@ -1108,12 +1107,6 @@ void pci_pme_wakeup_bus(struct pci_bus *bus); void pci_d3cold_enable(struct pci_dev *dev); void pci_d3cold_disable(struct pci_dev *dev); -static inline int pci_enable_wake(struct pci_dev *dev, pci_power_t state, - bool enable) -{ - return __pci_enable_wake(dev, state, false, enable); -} - /* PCI Virtual Channel */ int pci_save_vc_state(struct pci_dev *dev); void pci_restore_vc_state(struct pci_dev *dev); -- cgit v1.2.3 From de3ef1eb1cd0cc3a75f7a3661e10ed827f370ab8 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sat, 24 Jun 2017 01:58:53 +0200 Subject: PM / core: Drop run_wake flag from struct dev_pm_info The run_wake flag in struct dev_pm_info is used to indicate whether or not the device is capable of generating remote wakeup signals at run time (or in the system working state), but the distinction between runtime remote wakeup and system wakeup signaling has always been rather artificial. The only practical reason for it to exist at the core level was that ACPI and PCI treated those two cases differently, but that's not the case any more after recent changes. For this reason, get rid of the run_wake flag and, when applicable, use device_set_wakeup_capable() and device_can_wakeup() instead of device_set_run_wake() and device_run_wake(), respectively. Signed-off-by: Rafael J. Wysocki Reviewed-by: Mika Westerberg Acked-by: Bjorn Helgaas --- include/linux/pm.h | 1 - include/linux/pm_runtime.h | 12 ------------ 2 files changed, 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm.h b/include/linux/pm.h index a0894bc52bb4..b8b4df09fd8f 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -584,7 +584,6 @@ struct dev_pm_info { unsigned int idle_notification:1; unsigned int request_pending:1; unsigned int deferred_resume:1; - unsigned int run_wake:1; unsigned int runtime_auto:1; bool ignore_children:1; unsigned int no_callbacks:1; diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index ca4823e675e2..2efb08a60e63 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -76,16 +76,6 @@ static inline void pm_runtime_put_noidle(struct device *dev) atomic_add_unless(&dev->power.usage_count, -1, 0); } -static inline bool device_run_wake(struct device *dev) -{ - return dev->power.run_wake; -} - -static inline void device_set_run_wake(struct device *dev, bool enable) -{ - dev->power.run_wake = enable; -} - static inline bool pm_runtime_suspended(struct device *dev) { return dev->power.runtime_status == RPM_SUSPENDED @@ -163,8 +153,6 @@ static inline void pm_runtime_forbid(struct device *dev) {} static inline void pm_suspend_ignore_children(struct device *dev, bool enable) {} static inline void pm_runtime_get_noresume(struct device *dev) {} static inline void pm_runtime_put_noidle(struct device *dev) {} -static inline bool device_run_wake(struct device *dev) { return false; } -static inline void device_set_run_wake(struct device *dev, bool enable) {} static inline bool pm_runtime_suspended(struct device *dev) { return false; } static inline bool pm_runtime_active(struct device *dev) { return true; } static inline bool pm_runtime_status_suspended(struct device *dev) { return false; } -- cgit v1.2.3