1013 lines · 26.2 KB · C
RawDownload
// SPDX-License-Identifier: GPL-2.0-only/* * CPPC (Collaborative Processor Performance Control) driver for * interfacing with the CPUfreq layer and governors. See * cppc_acpi.c for CPPC specific methods. * * (C) Copyright 2014, 2015 Linaro Ltd. * Author: Ashwin Chaugule <ashwin.chaugule@linaro.org> */ #define pr_fmt(fmt)	"CPPC Cpufreq:"	fmt #include <linux/arch_topology.h>#include <linux/kernel.h>#include <linux/module.h>#include <linux/delay.h>#include <linux/cpu.h>#include <linux/cpufreq.h>#include <linux/dmi.h>#include <linux/irq_work.h>#include <linux/kthread.h>#include <linux/time.h>#include <linux/vmalloc.h>#include <uapi/linux/sched/types.h> #include <asm/unaligned.h> #include <acpi/cppc_acpi.h> /* Minimum struct length needed for the DMI processor entry we want */#define DMI_ENTRY_PROCESSOR_MIN_LENGTH	48 /* Offset in the DMI processor structure for the max frequency */#define DMI_PROCESSOR_MAX_SPEED		0x14 /* * This list contains information parsed from per CPU ACPI _CPC and _PSD * structures: e.g. the highest and lowest supported performance, capabilities, * desired performance, level requested etc. Depending on the share_type, not * all CPUs will have an entry in the list. */static LIST_HEAD(cpu_data_list); static bool boost_supported; struct cppc_workaround_oem_info {	char oem_id[ACPI_OEM_ID_SIZE + 1];	char oem_table_id[ACPI_OEM_TABLE_ID_SIZE + 1];	u32 oem_revision;}; static struct cppc_workaround_oem_info wa_info[] = {	{		.oem_id		= "HISI  ",		.oem_table_id	= "HIP07   ",		.oem_revision	= 0,	}, {		.oem_id		= "HISI  ",		.oem_table_id	= "HIP08   ",		.oem_revision	= 0,	}}; static struct cpufreq_driver cppc_cpufreq_driver; static enum {	FIE_UNSET = -1,	FIE_ENABLED,	FIE_DISABLED} fie_disabled = FIE_UNSET; #ifdef CONFIG_ACPI_CPPC_CPUFREQ_FIEmodule_param(fie_disabled, int, 0444);MODULE_PARM_DESC(fie_disabled, "Disable Frequency Invariance Engine (FIE)"); /* Frequency invariance support */struct cppc_freq_invariance {	int cpu;	struct irq_work irq_work;	struct kthread_work work;	struct cppc_perf_fb_ctrs prev_perf_fb_ctrs;	struct cppc_cpudata *cpu_data;}; static DEFINE_PER_CPU(struct cppc_freq_invariance, cppc_freq_inv);static struct kthread_worker *kworker_fie; static unsigned int hisi_cppc_cpufreq_get_rate(unsigned int cpu);static int cppc_perf_from_fbctrs(struct cppc_cpudata *cpu_data,				 struct cppc_perf_fb_ctrs *fb_ctrs_t0,				 struct cppc_perf_fb_ctrs *fb_ctrs_t1); /** * cppc_scale_freq_workfn - CPPC arch_freq_scale updater for frequency invariance * @work: The work item. * * The CPPC driver register itself with the topology core to provide its own * implementation (cppc_scale_freq_tick()) of topology_scale_freq_tick() which * gets called by the scheduler on every tick. * * Note that the arch specific counters have higher priority than CPPC counters, * if available, though the CPPC driver doesn't need to have any special * handling for that. * * On an invocation of cppc_scale_freq_tick(), we schedule an irq work (since we * reach here from hard-irq context), which then schedules a normal work item * and cppc_scale_freq_workfn() updates the per_cpu arch_freq_scale variable * based on the counter updates since the last tick. */static void cppc_scale_freq_workfn(struct kthread_work *work){	struct cppc_freq_invariance *cppc_fi;	struct cppc_perf_fb_ctrs fb_ctrs = {0};	struct cppc_cpudata *cpu_data;	unsigned long local_freq_scale;	u64 perf; 	cppc_fi = container_of(work, struct cppc_freq_invariance, work);	cpu_data = cppc_fi->cpu_data; 	if (cppc_get_perf_ctrs(cppc_fi->cpu, &fb_ctrs)) {		pr_warn("%s: failed to read perf counters\n", __func__);		return;	} 	perf = cppc_perf_from_fbctrs(cpu_data, &cppc_fi->prev_perf_fb_ctrs,				     &fb_ctrs);	cppc_fi->prev_perf_fb_ctrs = fb_ctrs; 	perf <<= SCHED_CAPACITY_SHIFT;	local_freq_scale = div64_u64(perf, cpu_data->perf_caps.highest_perf); 	/* This can happen due to counter's overflow */	if (unlikely(local_freq_scale > 1024))		local_freq_scale = 1024; 	per_cpu(arch_freq_scale, cppc_fi->cpu) = local_freq_scale;} static void cppc_irq_work(struct irq_work *irq_work){	struct cppc_freq_invariance *cppc_fi; 	cppc_fi = container_of(irq_work, struct cppc_freq_invariance, irq_work);	kthread_queue_work(kworker_fie, &cppc_fi->work);} static void cppc_scale_freq_tick(void){	struct cppc_freq_invariance *cppc_fi = &per_cpu(cppc_freq_inv, smp_processor_id()); 	/*	 * cppc_get_perf_ctrs() can potentially sleep, call that from the right	 * context.	 */	irq_work_queue(&cppc_fi->irq_work);} static struct scale_freq_data cppc_sftd = {	.source = SCALE_FREQ_SOURCE_CPPC,	.set_freq_scale = cppc_scale_freq_tick,}; static void cppc_cpufreq_cpu_fie_init(struct cpufreq_policy *policy){	struct cppc_freq_invariance *cppc_fi;	int cpu, ret; 	if (fie_disabled)		return; 	for_each_cpu(cpu, policy->cpus) {		cppc_fi = &per_cpu(cppc_freq_inv, cpu);		cppc_fi->cpu = cpu;		cppc_fi->cpu_data = policy->driver_data;		kthread_init_work(&cppc_fi->work, cppc_scale_freq_workfn);		init_irq_work(&cppc_fi->irq_work, cppc_irq_work); 		ret = cppc_get_perf_ctrs(cpu, &cppc_fi->prev_perf_fb_ctrs);		if (ret) {			pr_warn("%s: failed to read perf counters for cpu:%d: %d\n",				__func__, cpu, ret); 			/*			 * Don't abort if the CPU was offline while the driver			 * was getting registered.			 */			if (cpu_online(cpu))				return;		}	} 	/* Register for freq-invariance */	topology_set_scale_freq_source(&cppc_sftd, policy->cpus);} /* * We free all the resources on policy's removal and not on CPU removal as the * irq-work are per-cpu and the hotplug core takes care of flushing the pending * irq-works (hint: smpcfd_dying_cpu()) on CPU hotplug. Even if the kthread-work * fires on another CPU after the concerned CPU is removed, it won't harm. * * We just need to make sure to remove them all on policy->exit(). */static void cppc_cpufreq_cpu_fie_exit(struct cpufreq_policy *policy){	struct cppc_freq_invariance *cppc_fi;	int cpu; 	if (fie_disabled)		return; 	/* policy->cpus will be empty here, use related_cpus instead */	topology_clear_scale_freq_source(SCALE_FREQ_SOURCE_CPPC, policy->related_cpus); 	for_each_cpu(cpu, policy->related_cpus) {		cppc_fi = &per_cpu(cppc_freq_inv, cpu);		irq_work_sync(&cppc_fi->irq_work);		kthread_cancel_work_sync(&cppc_fi->work);	}} static void __init cppc_freq_invariance_init(void){	struct sched_attr attr = {		.size		= sizeof(struct sched_attr),		.sched_policy	= SCHED_DEADLINE,		.sched_nice	= 0,		.sched_priority	= 0,		/*		 * Fake (unused) bandwidth; workaround to "fix"		 * priority inheritance.		 */		.sched_runtime	= 1000000,		.sched_deadline = 10000000,		.sched_period	= 10000000,	};	int ret; 	if (fie_disabled != FIE_ENABLED && fie_disabled != FIE_DISABLED) {		fie_disabled = FIE_ENABLED;		if (cppc_perf_ctrs_in_pcc()) {			pr_info("FIE not enabled on systems with registers in PCC\n");			fie_disabled = FIE_DISABLED;		}	} 	if (fie_disabled)		return; 	kworker_fie = kthread_create_worker(0, "cppc_fie");	if (IS_ERR(kworker_fie))		return; 	ret = sched_setattr_nocheck(kworker_fie->task, &attr);	if (ret) {		pr_warn("%s: failed to set SCHED_DEADLINE: %d\n", __func__,			ret);		kthread_destroy_worker(kworker_fie);		return;	}} static void cppc_freq_invariance_exit(void){	if (fie_disabled)		return; 	kthread_destroy_worker(kworker_fie);	kworker_fie = NULL;} #elsestatic inline void cppc_cpufreq_cpu_fie_init(struct cpufreq_policy *policy){} static inline void cppc_cpufreq_cpu_fie_exit(struct cpufreq_policy *policy){} static inline void cppc_freq_invariance_init(void){} static inline void cppc_freq_invariance_exit(void){}#endif /* CONFIG_ACPI_CPPC_CPUFREQ_FIE */ /* Callback function used to retrieve the max frequency from DMI */static void cppc_find_dmi_mhz(const struct dmi_header *dm, void *private){	const u8 *dmi_data = (const u8 *)dm;	u16 *mhz = (u16 *)private; 	if (dm->type == DMI_ENTRY_PROCESSOR &&	    dm->length >= DMI_ENTRY_PROCESSOR_MIN_LENGTH) {		u16 val = (u16)get_unaligned((const u16 *)				(dmi_data + DMI_PROCESSOR_MAX_SPEED));		*mhz = val > *mhz ? val : *mhz;	}} /* Look up the max frequency in DMI */static u64 cppc_get_dmi_max_khz(void){	u16 mhz = 0; 	dmi_walk(cppc_find_dmi_mhz, &mhz); 	/*	 * Real stupid fallback value, just in case there is no	 * actual value set.	 */	mhz = mhz ? mhz : 1; 	return (1000 * mhz);} /* * If CPPC lowest_freq and nominal_freq registers are exposed then we can * use them to convert perf to freq and vice versa. The conversion is * extrapolated as an affine function passing by the 2 points: *  - (Low perf, Low freq) *  - (Nominal perf, Nominal perf) */static unsigned int cppc_cpufreq_perf_to_khz(struct cppc_cpudata *cpu_data,					     unsigned int perf){	struct cppc_perf_caps *caps = &cpu_data->perf_caps;	s64 retval, offset = 0;	static u64 max_khz;	u64 mul, div; 	if (caps->lowest_freq && caps->nominal_freq) {		mul = caps->nominal_freq - caps->lowest_freq;		div = caps->nominal_perf - caps->lowest_perf;		offset = caps->nominal_freq - div64_u64(caps->nominal_perf * mul, div);	} else {		if (!max_khz)			max_khz = cppc_get_dmi_max_khz();		mul = max_khz;		div = caps->highest_perf;	} 	retval = offset + div64_u64(perf * mul, div);	if (retval >= 0)		return retval;	return 0;} static unsigned int cppc_cpufreq_khz_to_perf(struct cppc_cpudata *cpu_data,					     unsigned int freq){	struct cppc_perf_caps *caps = &cpu_data->perf_caps;	s64 retval, offset = 0;	static u64 max_khz;	u64  mul, div; 	if (caps->lowest_freq && caps->nominal_freq) {		mul = caps->nominal_perf - caps->lowest_perf;		div = caps->nominal_freq - caps->lowest_freq;		offset = caps->nominal_perf - div64_u64(caps->nominal_freq * mul, div);	} else {		if (!max_khz)			max_khz = cppc_get_dmi_max_khz();		mul = caps->highest_perf;		div = max_khz;	} 	retval = offset + div64_u64(freq * mul, div);	if (retval >= 0)		return retval;	return 0;} static int cppc_cpufreq_set_target(struct cpufreq_policy *policy,				   unsigned int target_freq,				   unsigned int relation) {	struct cppc_cpudata *cpu_data = policy->driver_data;	unsigned int cpu = policy->cpu;	struct cpufreq_freqs freqs;	u32 desired_perf;	int ret = 0; 	desired_perf = cppc_cpufreq_khz_to_perf(cpu_data, target_freq);	/* Return if it is exactly the same perf */	if (desired_perf == cpu_data->perf_ctrls.desired_perf)		return ret; 	cpu_data->perf_ctrls.desired_perf = desired_perf;	freqs.old = policy->cur;	freqs.new = target_freq; 	cpufreq_freq_transition_begin(policy, &freqs);	ret = cppc_set_perf(cpu, &cpu_data->perf_ctrls);	cpufreq_freq_transition_end(policy, &freqs, ret != 0); 	if (ret)		pr_debug("Failed to set target on CPU:%d. ret:%d\n",			 cpu, ret); 	return ret;} static unsigned int cppc_cpufreq_fast_switch(struct cpufreq_policy *policy,					      unsigned int target_freq){	struct cppc_cpudata *cpu_data = policy->driver_data;	unsigned int cpu = policy->cpu;	u32 desired_perf;	int ret; 	desired_perf = cppc_cpufreq_khz_to_perf(cpu_data, target_freq);	cpu_data->perf_ctrls.desired_perf = desired_perf;	ret = cppc_set_perf(cpu, &cpu_data->perf_ctrls); 	if (ret) {		pr_debug("Failed to set target on CPU:%d. ret:%d\n",			 cpu, ret);		return 0;	} 	return target_freq;} static int cppc_verify_policy(struct cpufreq_policy_data *policy){	cpufreq_verify_within_cpu_limits(policy);	return 0;} /* * The PCC subspace describes the rate at which platform can accept commands * on the shared PCC channel (including READs which do not count towards freq * transition requests), so ideally we need to use the PCC values as a fallback * if we don't have a platform specific transition_delay_us */#ifdef CONFIG_ARM64#include <asm/cputype.h> static unsigned int cppc_cpufreq_get_transition_delay_us(unsigned int cpu){	unsigned long implementor = read_cpuid_implementor();	unsigned long part_num = read_cpuid_part_number(); 	switch (implementor) {	case ARM_CPU_IMP_QCOM:		switch (part_num) {		case QCOM_CPU_PART_FALKOR_V1:		case QCOM_CPU_PART_FALKOR:			return 10000;		}	}	return cppc_get_transition_latency(cpu) / NSEC_PER_USEC;}#elsestatic unsigned int cppc_cpufreq_get_transition_delay_us(unsigned int cpu){	return cppc_get_transition_latency(cpu) / NSEC_PER_USEC;}#endif #if defined(CONFIG_ARM64) && defined(CONFIG_ENERGY_MODEL) static DEFINE_PER_CPU(unsigned int, efficiency_class);static void cppc_cpufreq_register_em(struct cpufreq_policy *policy); /* Create an artificial performance state every CPPC_EM_CAP_STEP capacity unit. */#define CPPC_EM_CAP_STEP	(20)/* Increase the cost value by CPPC_EM_COST_STEP every performance state. */#define CPPC_EM_COST_STEP	(1)/* Add a cost gap correspnding to the energy of 4 CPUs. */#define CPPC_EM_COST_GAP	(4 * SCHED_CAPACITY_SCALE * CPPC_EM_COST_STEP \				/ CPPC_EM_CAP_STEP) static unsigned int get_perf_level_count(struct cpufreq_policy *policy){	struct cppc_perf_caps *perf_caps;	unsigned int min_cap, max_cap;	struct cppc_cpudata *cpu_data;	int cpu = policy->cpu; 	cpu_data = policy->driver_data;	perf_caps = &cpu_data->perf_caps;	max_cap = arch_scale_cpu_capacity(cpu);	min_cap = div_u64(max_cap * perf_caps->lowest_perf, perf_caps->highest_perf);	if ((min_cap == 0) || (max_cap < min_cap))		return 0;	return 1 + max_cap / CPPC_EM_CAP_STEP - min_cap / CPPC_EM_CAP_STEP;} /* * The cost is defined as: *   cost = power * max_frequency / frequency */static inline unsigned long compute_cost(int cpu, int step)

Lines 1–500 of 1013.