Commit 33068b61 authored by Rafael J. Wysocki's avatar Rafael J. Wysocki
Browse files

Merge branches 'pm-cpufreq' and 'pm-cpuidle' 

* pm-cpufreq:
  cpufreq: governor: Always schedule work on the CPU running update
  cpufreq: Always update current frequency before startig governor
  cpufreq: Introduce cpufreq_update_current_freq()
  cpufreq: Introduce cpufreq_start_governor()
  cpufreq: powernv: Add sysfs attributes to show throttle stats
  cpufreq: acpi-cpufreq: make Intel/AMD MSR access, io port access static
  cpufreq: powernv: Define per_cpu chip pointer to optimize hot-path
  cpufreq: acpi-cpufreq: Clean up hot plug notifier callback
  intel_pstate: Do not call wrmsrl_on_cpu() with disabled interrupts
  cpufreq: Make cpufreq_quick_get() safe to call

* pm-cpuidle:
  intel_idle: Support for Intel Xeon Phi Processor x200 Product Family
  intel_idle: prevent SKL-H boot failure when C8+C9+C10 enabled
  cpuidle: menu: Fall back to polling if next timer event is near
  cpuidle: menu: use high confidence factors only when considering polling
parents 277edbab 539a4c42 f70ce488

Documentation/ABI/testing/sysfs-devices-system-cpu

+69 −0
Original line number Diff line number Diff line
@@ -271,3 +271,72 @@ Description: Parameters for the CPU cache attributes 
			- WriteBack: data is written only to the cache line and

				     the modified cache line is written to main

				     memory only when it is replaced



What:		/sys/devices/system/cpu/cpuX/cpufreq/throttle_stats

		/sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/turbo_stat

		/sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/sub_turbo_stat

		/sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/unthrottle

		/sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/powercap

		/sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/overtemp

		/sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/supply_fault

		/sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/overcurrent

		/sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/occ_reset

Date:		March 2016

Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>

		Linux for PowerPC mailing list <linuxppc-dev@ozlabs.org>

Description:	POWERNV CPUFreq driver's frequency throttle stats directory and

		attributes



		'cpuX/cpufreq/throttle_stats' directory contains the CPU frequency

		throttle stat attributes for the chip. The throttle stats of a cpu

		is common across all the cpus belonging to a chip. Below are the

		throttle attributes exported in the 'throttle_stats' directory:



		- turbo_stat : This file gives the total number of times the max

		frequency is throttled to lower frequency in turbo (at and above

		nominal frequency) range of frequencies.



		- sub_turbo_stat : This file gives the total number of times the

		max frequency is throttled to lower frequency in sub-turbo(below

		nominal frequency) range of frequencies.



		- unthrottle : This file gives the total number of times the max

		frequency is unthrottled after being throttled.



		- powercap : This file gives the total number of times the max

		frequency is throttled due to 'Power Capping'.



		- overtemp : This file gives the total number of times the max

		frequency is throttled due to 'CPU Over Temperature'.



		- supply_fault : This file gives the total number of times the

		max frequency is throttled due to 'Power Supply Failure'.



		- overcurrent : This file gives the total number of times the

		max frequency is throttled due to 'Overcurrent'.



		- occ_reset : This file gives the total number of times the max

		frequency is throttled due to 'OCC Reset'.



		The sysfs attributes representing different throttle reasons like

		powercap, overtemp, supply_fault, overcurrent and occ_reset map to

		the reasons provided by OCC firmware for throttling the frequency.



What:		/sys/devices/system/cpu/cpufreq/policyX/throttle_stats

		/sys/devices/system/cpu/cpufreq/policyX/throttle_stats/turbo_stat

		/sys/devices/system/cpu/cpufreq/policyX/throttle_stats/sub_turbo_stat

		/sys/devices/system/cpu/cpufreq/policyX/throttle_stats/unthrottle

		/sys/devices/system/cpu/cpufreq/policyX/throttle_stats/powercap

		/sys/devices/system/cpu/cpufreq/policyX/throttle_stats/overtemp

		/sys/devices/system/cpu/cpufreq/policyX/throttle_stats/supply_fault

		/sys/devices/system/cpu/cpufreq/policyX/throttle_stats/overcurrent

		/sys/devices/system/cpu/cpufreq/policyX/throttle_stats/occ_reset

Date:		March 2016

Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>

		Linux for PowerPC mailing list <linuxppc-dev@ozlabs.org>

Description:	POWERNV CPUFreq driver's frequency throttle stats directory and

		attributes



		'policyX/throttle_stats' directory and all the attributes are same as

		the /sys/devices/system/cpu/cpuX/cpufreq/throttle_stats directory and

		attributes which give the frequency throttle information of the chip.

drivers/cpufreq/acpi-cpufreq.c

+10 −8
Original line number Diff line number Diff line
@@ -245,7 +245,7 @@ static unsigned extract_freq(u32 val, struct acpi_cpufreq_data *data) 
	}

}



u32 cpu_freq_read_intel(struct acpi_pct_register *not_used)

static u32 cpu_freq_read_intel(struct acpi_pct_register *not_used)

{

	u32 val, dummy;
@@ -253,7 +253,7 @@ u32 cpu_freq_read_intel(struct acpi_pct_register *not_used) 
	return val;

}



void cpu_freq_write_intel(struct acpi_pct_register *not_used, u32 val)

static void cpu_freq_write_intel(struct acpi_pct_register *not_used, u32 val)

{

	u32 lo, hi;
@@ -262,7 +262,7 @@ void cpu_freq_write_intel(struct acpi_pct_register *not_used, u32 val) 
	wrmsr(MSR_IA32_PERF_CTL, lo, hi);

}



u32 cpu_freq_read_amd(struct acpi_pct_register *not_used)

static u32 cpu_freq_read_amd(struct acpi_pct_register *not_used)

{

	u32 val, dummy;
@@ -270,12 +270,12 @@ u32 cpu_freq_read_amd(struct acpi_pct_register *not_used) 
	return val;

}



void cpu_freq_write_amd(struct acpi_pct_register *not_used, u32 val)

static void cpu_freq_write_amd(struct acpi_pct_register *not_used, u32 val)

{

	wrmsr(MSR_AMD_PERF_CTL, val, 0);

}



u32 cpu_freq_read_io(struct acpi_pct_register *reg)

static u32 cpu_freq_read_io(struct acpi_pct_register *reg)

{

	u32 val;
@@ -283,7 +283,7 @@ u32 cpu_freq_read_io(struct acpi_pct_register *reg) 
	return val;

}



void cpu_freq_write_io(struct acpi_pct_register *reg, u32 val)

static void cpu_freq_write_io(struct acpi_pct_register *reg, u32 val)

{

	acpi_os_write_port(reg->address, val, reg->bit_width);

}
@@ -514,8 +514,10 @@ static int boost_notify(struct notifier_block *nb, unsigned long action, 
	 */



	switch (action) {

	case CPU_UP_PREPARE:

	case CPU_UP_PREPARE_FROZEN:

	case CPU_DOWN_FAILED:

	case CPU_DOWN_FAILED_FROZEN:

	case CPU_ONLINE:

	case CPU_ONLINE_FROZEN:

		boost_set_msrs(acpi_cpufreq_driver.boost_enabled, cpumask);

		break;

drivers/cpufreq/cpufreq.c

+54 −44
Original line number Diff line number Diff line
@@ -76,6 +76,7 @@ static inline bool has_target(void) 
/* internal prototypes */

static int cpufreq_governor(struct cpufreq_policy *policy, unsigned int event);

static unsigned int __cpufreq_get(struct cpufreq_policy *policy);

static int cpufreq_start_governor(struct cpufreq_policy *policy);



/**

 * Two notifier lists: the "policy" list is involved in the
@@ -964,10 +965,7 @@ static int cpufreq_add_policy_cpu(struct cpufreq_policy *policy, unsigned int cp 
	cpumask_set_cpu(cpu, policy->cpus);



	if (has_target()) {

		ret = cpufreq_governor(policy, CPUFREQ_GOV_START);

		if (!ret)

			ret = cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);



		ret = cpufreq_start_governor(policy);

		if (ret)

			pr_err("%s: Failed to start governor\n", __func__);

	}
@@ -1308,10 +1306,7 @@ static void cpufreq_offline(unsigned int cpu) 
	/* Start governor again for active policy */

	if (!policy_is_inactive(policy)) {

		if (has_target()) {

			ret = cpufreq_governor(policy, CPUFREQ_GOV_START);

			if (!ret)

				ret = cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);



			ret = cpufreq_start_governor(policy);

			if (ret)

				pr_err("%s: Failed to start governor\n", __func__);

		}
@@ -1401,9 +1396,17 @@ unsigned int cpufreq_quick_get(unsigned int cpu) 
{

	struct cpufreq_policy *policy;

	unsigned int ret_freq = 0;

	unsigned long flags;



	if (cpufreq_driver && cpufreq_driver->setpolicy && cpufreq_driver->get)

		return cpufreq_driver->get(cpu);

	read_lock_irqsave(&cpufreq_driver_lock, flags);



	if (cpufreq_driver && cpufreq_driver->setpolicy && cpufreq_driver->get) {

		ret_freq = cpufreq_driver->get(cpu);

		read_unlock_irqrestore(&cpufreq_driver_lock, flags);

		return ret_freq;

	}



	read_unlock_irqrestore(&cpufreq_driver_lock, flags);



	policy = cpufreq_cpu_get(cpu);

	if (policy) {
@@ -1484,6 +1487,24 @@ unsigned int cpufreq_get(unsigned int cpu) 
}

EXPORT_SYMBOL(cpufreq_get);



static unsigned int cpufreq_update_current_freq(struct cpufreq_policy *policy)

{

	unsigned int new_freq;



	new_freq = cpufreq_driver->get(policy->cpu);

	if (!new_freq)

		return 0;



	if (!policy->cur) {

		pr_debug("cpufreq: Driver did not initialize current freq\n");

		policy->cur = new_freq;

	} else if (policy->cur != new_freq && has_target()) {

		cpufreq_out_of_sync(policy, new_freq);

	}



	return new_freq;

}



static struct subsys_interface cpufreq_interface = {

	.name		= "cpufreq",

	.subsys		= &cpu_subsys,
@@ -1583,9 +1604,7 @@ void cpufreq_resume(void) 
				policy);

		} else {

			down_write(&policy->rwsem);

			ret = cpufreq_governor(policy, CPUFREQ_GOV_START);

			if (!ret)

				cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);

			ret = cpufreq_start_governor(policy);

			up_write(&policy->rwsem);



			if (ret)
@@ -1593,17 +1612,6 @@ void cpufreq_resume(void) 
				       __func__, policy);

		}

	}



	/*

	 * schedule call cpufreq_update_policy() for first-online CPU, as that

	 * wouldn't be hotplugged-out on suspend. It will verify that the

	 * current freq is in sync with what we believe it to be.

	 */

	policy = cpufreq_cpu_get_raw(cpumask_first(cpu_online_mask));

	if (WARN_ON(!policy))

		return;



	schedule_work(&policy->update);

}



/**
@@ -1927,6 +1935,17 @@ static int cpufreq_governor(struct cpufreq_policy *policy, unsigned int event) 
	return ret;

}



static int cpufreq_start_governor(struct cpufreq_policy *policy)

{

	int ret;



	if (cpufreq_driver->get && !cpufreq_driver->setpolicy)

		cpufreq_update_current_freq(policy);



	ret = cpufreq_governor(policy, CPUFREQ_GOV_START);

	return ret ? ret : cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);

}



int cpufreq_register_governor(struct cpufreq_governor *governor)

{

	int err;
@@ -2063,8 +2082,10 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy, 
		return cpufreq_driver->setpolicy(new_policy);

	}



	if (new_policy->governor == policy->governor)

		goto out;

	if (new_policy->governor == policy->governor) {

		pr_debug("cpufreq: governor limits update\n");

		return cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);

	}



	pr_debug("governor switch\n");
@@ -2092,10 +2113,11 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy, 
	policy->governor = new_policy->governor;

	ret = cpufreq_governor(policy, CPUFREQ_GOV_POLICY_INIT);

	if (!ret) {

		ret = cpufreq_governor(policy, CPUFREQ_GOV_START);

		if (!ret)

			goto out;



		ret = cpufreq_start_governor(policy);

		if (!ret) {

			pr_debug("cpufreq: governor change\n");

			return 0;

		}

		cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT);

	}
@@ -2106,14 +2128,10 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy, 
		if (cpufreq_governor(policy, CPUFREQ_GOV_POLICY_INIT))

			policy->governor = NULL;

		else

			cpufreq_governor(policy, CPUFREQ_GOV_START);

			cpufreq_start_governor(policy);

	}



	return ret;



 out:

	pr_debug("governor: change or update limits\n");

	return cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);

}



/**
@@ -2144,19 +2162,11 @@ int cpufreq_update_policy(unsigned int cpu) 
	 * -> ask driver for current freq and notify governors about a change

	 */

	if (cpufreq_driver->get && !cpufreq_driver->setpolicy) {

		new_policy.cur = cpufreq_driver->get(cpu);

		new_policy.cur = cpufreq_update_current_freq(policy);

		if (WARN_ON(!new_policy.cur)) {

			ret = -EIO;

			goto unlock;

		}



		if (!policy->cur) {

			pr_debug("Driver did not initialize current freq\n");

			policy->cur = new_policy.cur;

		} else {

			if (policy->cur != new_policy.cur && has_target())

				cpufreq_out_of_sync(policy, new_policy.cur);

		}

	}



	ret = cpufreq_set_policy(policy, &new_policy);

drivers/cpufreq/cpufreq_governor.c

+1 −1
Original line number Diff line number Diff line
@@ -329,7 +329,7 @@ static void dbs_irq_work(struct irq_work *irq_work) 
	struct policy_dbs_info *policy_dbs;



	policy_dbs = container_of(irq_work, struct policy_dbs_info, irq_work);

	schedule_work(&policy_dbs->work);

	schedule_work_on(smp_processor_id(), &policy_dbs->work);

}



static void dbs_update_util_handler(struct update_util_data *data, u64 time,

drivers/cpufreq/intel_pstate.c

+43 −30
Original line number Diff line number Diff line
@@ -134,7 +134,7 @@ struct pstate_funcs { 
	int (*get_min)(void);

	int (*get_turbo)(void);

	int (*get_scaling)(void);

	void (*set)(struct cpudata*, int pstate);

	u64 (*get_val)(struct cpudata*, int pstate);

	void (*get_vid)(struct cpudata *);

	int32_t (*get_target_pstate)(struct cpudata *);

};
@@ -565,7 +565,7 @@ static int atom_get_turbo_pstate(void) 
	return value & 0x7F;

}



static void atom_set_pstate(struct cpudata *cpudata, int pstate)

static u64 atom_get_val(struct cpudata *cpudata, int pstate)

{

	u64 val;

	int32_t vid_fp;
@@ -585,9 +585,7 @@ static void atom_set_pstate(struct cpudata *cpudata, int pstate) 
	if (pstate > cpudata->pstate.max_pstate)

		vid = cpudata->vid.turbo;



	val |= vid;



	wrmsrl_on_cpu(cpudata->cpu, MSR_IA32_PERF_CTL, val);

	return val | vid;

}



static int silvermont_get_scaling(void)
@@ -711,7 +709,7 @@ static inline int core_get_scaling(void) 
	return 100000;

}



static void core_set_pstate(struct cpudata *cpudata, int pstate)

static u64 core_get_val(struct cpudata *cpudata, int pstate)

{

	u64 val;
@@ -719,7 +717,7 @@ static void core_set_pstate(struct cpudata *cpudata, int pstate) 
	if (limits->no_turbo && !limits->turbo_disabled)

		val |= (u64)1 << 32;



	wrmsrl(MSR_IA32_PERF_CTL, val);

	return val;

}



static int knl_get_turbo_pstate(void)
@@ -750,7 +748,7 @@ static struct cpu_defaults core_params = { 
		.get_min = core_get_min_pstate,

		.get_turbo = core_get_turbo_pstate,

		.get_scaling = core_get_scaling,

		.set = core_set_pstate,

		.get_val = core_get_val,

		.get_target_pstate = get_target_pstate_use_performance,

	},

};
@@ -769,7 +767,7 @@ static struct cpu_defaults silvermont_params = { 
		.get_max_physical = atom_get_max_pstate,

		.get_min = atom_get_min_pstate,

		.get_turbo = atom_get_turbo_pstate,

		.set = atom_set_pstate,

		.get_val = atom_get_val,

		.get_scaling = silvermont_get_scaling,

		.get_vid = atom_get_vid,

		.get_target_pstate = get_target_pstate_use_cpu_load,
@@ -790,7 +788,7 @@ static struct cpu_defaults airmont_params = { 
		.get_max_physical = atom_get_max_pstate,

		.get_min = atom_get_min_pstate,

		.get_turbo = atom_get_turbo_pstate,

		.set = atom_set_pstate,

		.get_val = atom_get_val,

		.get_scaling = airmont_get_scaling,

		.get_vid = atom_get_vid,

		.get_target_pstate = get_target_pstate_use_cpu_load,
@@ -812,7 +810,7 @@ static struct cpu_defaults knl_params = { 
		.get_min = core_get_min_pstate,

		.get_turbo = knl_get_turbo_pstate,

		.get_scaling = core_get_scaling,

		.set = core_set_pstate,

		.get_val = core_get_val,

		.get_target_pstate = get_target_pstate_use_performance,

	},

};
@@ -839,25 +837,24 @@ static void intel_pstate_get_min_max(struct cpudata *cpu, int *min, int *max) 
	*min = clamp_t(int, min_perf, cpu->pstate.min_pstate, max_perf);

}



static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate, bool force)

static inline void intel_pstate_record_pstate(struct cpudata *cpu, int pstate)

{

	int max_perf, min_perf;



	if (force) {

		update_turbo_state();



		intel_pstate_get_min_max(cpu, &min_perf, &max_perf);



		pstate = clamp_t(int, pstate, min_perf, max_perf);



		if (pstate == cpu->pstate.current_pstate)

			return;

	}

	trace_cpu_frequency(pstate * cpu->pstate.scaling, cpu->cpu);



	cpu->pstate.current_pstate = pstate;

}



static void intel_pstate_set_min_pstate(struct cpudata *cpu)

{

	int pstate = cpu->pstate.min_pstate;



	pstate_funcs.set(cpu, pstate);

	intel_pstate_record_pstate(cpu, pstate);

	/*

	 * Generally, there is no guarantee that this code will always run on

	 * the CPU being updated, so force the register update to run on the

	 * right CPU.

	 */

	wrmsrl_on_cpu(cpu->cpu, MSR_IA32_PERF_CTL,

		      pstate_funcs.get_val(cpu, pstate));

}



static void intel_pstate_get_cpu_pstates(struct cpudata *cpu)
@@ -870,7 +867,8 @@ static void intel_pstate_get_cpu_pstates(struct cpudata *cpu) 


	if (pstate_funcs.get_vid)

		pstate_funcs.get_vid(cpu);

	intel_pstate_set_pstate(cpu, cpu->pstate.min_pstate, false);



	intel_pstate_set_min_pstate(cpu);

}



static inline void intel_pstate_calc_busy(struct cpudata *cpu)
@@ -997,6 +995,21 @@ static inline int32_t get_target_pstate_use_performance(struct cpudata *cpu) 
	return cpu->pstate.current_pstate - pid_calc(&cpu->pid, core_busy);

}



static inline void intel_pstate_update_pstate(struct cpudata *cpu, int pstate)

{

	int max_perf, min_perf;



	update_turbo_state();



	intel_pstate_get_min_max(cpu, &min_perf, &max_perf);

	pstate = clamp_t(int, pstate, min_perf, max_perf);

	if (pstate == cpu->pstate.current_pstate)

		return;



	intel_pstate_record_pstate(cpu, pstate);

	wrmsrl(MSR_IA32_PERF_CTL, pstate_funcs.get_val(cpu, pstate));

}



static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu)

{

	int from, target_pstate;
@@ -1006,7 +1019,7 @@ static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu) 


	target_pstate = pstate_funcs.get_target_pstate(cpu);



	intel_pstate_set_pstate(cpu, target_pstate, true);

	intel_pstate_update_pstate(cpu, target_pstate);



	sample = &cpu->sample;

	trace_pstate_sample(fp_toint(sample->core_pct_busy),
@@ -1180,7 +1193,7 @@ static void intel_pstate_stop_cpu(struct cpufreq_policy *policy) 
	if (hwp_active)

		return;



	intel_pstate_set_pstate(cpu, cpu->pstate.min_pstate, false);

	intel_pstate_set_min_pstate(cpu);

}



static int intel_pstate_cpu_init(struct cpufreq_policy *policy)
@@ -1255,7 +1268,7 @@ static void copy_cpu_funcs(struct pstate_funcs *funcs) 
	pstate_funcs.get_min   = funcs->get_min;

	pstate_funcs.get_turbo = funcs->get_turbo;

	pstate_funcs.get_scaling = funcs->get_scaling;

	pstate_funcs.set       = funcs->set;

	pstate_funcs.get_val   = funcs->get_val;

	pstate_funcs.get_vid   = funcs->get_vid;

	pstate_funcs.get_target_pstate = funcs->get_target_pstate;

CRA Git | Maintained and supported by SUSTech CRA and CCSE