From 22098763a10d9c1340827fcf6edab66f153b27f0 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 13 Sep 2026 12:27:00 -0700 Subject: Merge tag 'trace-v7.3-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace Pull tracing fixes from Steven Rostedt: - Don't destroy user event fields when removal fails User event fields are destroyed before the event is removed from visibility. But that can fail leaving the still visible event with no fields. Move the destroying of the fields to after the event is successfully removed from visibility. - Initialize function graph state is fork before calling copy_exec_state() For non-CLONE_VM forks, copy_exec_state() allocates a new task_exec_state. If that allocation fails, ftrace_graph_exit_task() will free the tasks ret_stack pointer. Since that pointer is still using the parent's ret_stack, it mistakenly frees the parent's pointer too. Call ftrace_graph_init() on the task first which will NULL out the new tasks's ret_stack and if the copy fails, it will not free anything. - Remove FGRAPH_MAX_INDEX The macro FGRAPH_MAX_INDEX was added but never used. Remove it. - Save ent_size in function graph printing of nested functions The function graph tracer needs to look at the next event to see if the next event is the return of the current function entry. If it is, it prints a single line: ktime_get(); Otherwise it prints it like a nested function: tick_nohz_irq_exit() { ktime_get(); kcpustat_irq_exit(); } In order to look at the next event, it must save the current event so that it has the information to print from it. It saves the event in the iterator descriptor called "ent". What it doesn't save is the ent_size of the event which is now used to know if the function graph arguments are to be printed. The peek doesn't save the size so the size used happens to be that of the size of the last event that was seen. Save the entry event size in the iterator descriptor so that the correct size is used. - Fix several errors with freeing data in the histogram code The histogram code had a lot of leaked or or incorrect accounting when failures happen. Correct them. - Fix histogram regression of .percent and .graph modifiers Up until 6.3 histogram values could have "percent" or "graph" modifiers that changed how they were printed. But a change that added restricting histograms values from being strings, stack traces and other modifiers inadvertently prevented them from using the percent and graph modifiers, which were legal use cases for values. Put back the percent and graph modifiers. - Fix various typos in the comments - Set the trace_clock before initializing a histogram with clock argument The histogram API allows the user to specific which trace clock to use via a "clock=" string. The histogram is set up first before the clock is checked. If the passed in clock is not valid, it exits without fully fixing up the histogram leaving it on the list and a use-after-free can trigger. Update the clock argument first and if it fails then exit gracefully before the histogram trigger is placed on any lists. - Restore :mod: trailer after parsing in ftrace_set_clr_event The function ftrace_set_clr_event() modifies the parse string and needs to put it back to what was passed in. It searches for ":mod:" via a strsep() but fails to put back the first ':' in the string. Add back the ':' in the passed in string. - Take trace_array reference when opening a tracer options file The options files are dynamically created and some tracers add their own options. When a tracer adds their own list of options, the trace_array holding them has an array to hold the list of options for each tracer. This array increases in size via a krealloc(), and the new entry gets a newly allocated array to hold the options of the new tracer being added. The element in each entry of the tracer's option array holds a pointer back to the trace_array, a pointer to the tracer it is associated to, a pointer to the flags of the option. The issue is that these arrays are freed when the trace_array is freed when its instance it represents is removed from the instances directory. There's a race that an open of one of these options files can happen when the instance is being removed. Add a new helper function to be called by the open function of the options file to iterate all existing trace_arrays under a lock and find the one that has the given option element in one of it's tracer arrays. If found, then update the associated trace_array's reference counter to keep it from being freed. If not found, have the open call return -ENODEV. - Disable interrupts when acquiring the lock in rb_wake_up_waiters() The function rb_wake_up_waiters() assumes it will be called in interrupt context and does not disable irqs when taking cpu_buffer->reader_lock, which can be called in hard interrupt context. The issue is in PREEMPT_RT, this function is called in thread context leaving this lock open to a deadlock. Take the lock with interrupts disabled. - Use rcu_assign_pointer() for tmp_ops filter hash The tmp_ops used in update_ftrace_direct_mod() assigns its filter_hash field directly, but that field is annotated as __rcu and sparse complains. Assign it with rcu_assign_pointer() - Fix use-after-free in enable_trigger_private_data_free() The trace_event_call is accessed through the event_trigger_data's trace_event_file pointer to put the trace_event_call on freeing. The issue is that the trace_event_file data may have been freed already causing a use-after-free. Add a field to the event_trigger_data that points directly to the trace_event_call so that it can decrement its reference directly without needing to go through the trace_event_file. - Fix accounting of buffer data remote headers trace_buffer_desc_size() and trace_remote_alloc_buffer() undercount the number of pages is needed for the asked for size as it doesn't take into account the meta data on each page. Add a helper function to do the calculation properly and use that in these functions. - Catch nr_page_va overflow in ring_buffer_desc sizing The number of pages per remote ring buffer is capped by ring_buffer_desc::nr_page_va (32 bits). A buffer_size large enough to overflow that field would silently allocate a descriptor smaller than what was asked for. - Do not resize the subbuf order if any per_cpu buffer is disabled The mmapping of ring buffers disables resizing the subbuffers, but it is done per-cpu whereas the subbuf size change is done for all the per_cpu buffers under the buffer->mutex. It could change the size of some while the mapping is happening on others. Have the resize of the subbuf order check all the per_cpu buffers under the lock to see if any of them is disabled before starting and causing an inconsistency between buffers that are being mapped. * tag 'trace-v7.3-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: (25 commits) ring-buffer: Check resize_disabled before publishing the new subbuf order tracing/remotes: Catch nr_page_va overflow in ring_buffer_desc sizing tracing/remotes: Account for ring buffer page header in size calculation tracing: Don't dereference trace_event_file in deferred trigger free ftrace: Use rcu_assign_pointer() for tmp_ops filter hash ring-buffer: Acquire the lock with irqsave in rb_wake_up_waiters() tracing: Take trace_array reference when opening a tracer options file tracing: Fix ring_buffer_read_page_size() kernel-doc tracing: Restore :mod: trailer after parsing in ftrace_set_clr_event() tracing: Fix memory corruption from a "STACKTRACE" histogram key tracing: Fix memory corruption from the histogram stacktrace modifier tracing: Undo the registration when enabling the histogram trigger fails tracing: Take the reference before publishing the named histogram trigger tracing: Set the trace clock before registering the histogram trigger tracing: Fix typo "preceeded" in comment tracing: Fix typo "availabe" in comment tracing: Let histogram values keep the percent and graph modifiers tracing: Keep the entry count when the histogram stats allocation fails tracing: Free histogram the field rejected for a bad modifier tracing: Free histogram the var ref when its initialization fails ... --- drivers/cpufreq/cppc_cpufreq.c | 1090 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 1090 insertions(+) create mode 100644 drivers/cpufreq/cppc_cpufreq.c (limited to 'drivers/cpufreq/cppc_cpufreq.c') diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c new file mode 100644 index 000000000..808938443 --- /dev/null +++ b/drivers/cpufreq/cppc_cpufreq.c @@ -0,0 +1,1090 @@ +// 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 + */ + +#define pr_fmt(fmt) "CPPC Cpufreq:" fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include + +static struct cpufreq_driver cppc_cpufreq_driver; + +#ifdef CONFIG_ACPI_CPPC_CPUFREQ_FIE +static enum { + FIE_UNSET = -1, + FIE_ENABLED, + FIE_DISABLED +} fie_disabled = FIE_UNSET; + +module_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 int cppc_perf_from_fbctrs(u64 reference_perf, + struct cppc_perf_fb_ctrs *fb_ctrs_t0, + struct cppc_perf_fb_ctrs *fb_ctrs_t1); + +/** + * __cppc_scale_freq_tick - CPPC arch_freq_scale updater for frequency invariance + * @cppc_fi: per-cpu CPPC FIE data. + * + * The CPPC driver registers 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. + */ +static void __cppc_scale_freq_tick(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, ref_perf; + + 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; + } + + ref_perf = cpu_data->perf_caps.reference_perf; + perf = cppc_perf_from_fbctrs(ref_perf, + &cppc_fi->prev_perf_fb_ctrs, &fb_ctrs); + if (!perf) + return; + + 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_scale_freq_tick(void) +{ + __cppc_scale_freq_tick(&per_cpu(cppc_freq_inv, smp_processor_id())); +} + +static struct scale_freq_data cppc_sftd = { + .source = SCALE_FREQ_SOURCE_CPPC, + .set_freq_scale = cppc_scale_freq_tick, +}; + +static void cppc_scale_freq_workfn(struct kthread_work *work) +{ + struct cppc_freq_invariance *cppc_fi; + + cppc_fi = container_of(work, struct cppc_freq_invariance, work); + __cppc_scale_freq_tick(cppc_fi); +} + +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); +} + +/* + * Reading perf counters may sleep if the CPC regs are in PCC. Thus, we + * schedule an irq work in scale_freq_tick (since we reach here from hard-irq + * context), which then schedules a normal work item cppc_scale_freq_workfn() + * that updates the per_cpu arch_freq_scale variable based on the counter + * updates since the last tick. + */ +static void cppc_scale_freq_tick_pcc(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_pcc = { + .source = SCALE_FREQ_SOURCE_CPPC, + .set_freq_scale = cppc_scale_freq_tick_pcc, +}; + +static void cppc_cpufreq_cpu_fie_init(struct cpufreq_policy *policy) +{ + struct scale_freq_data *sftd = &cppc_sftd; + 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; + if (cppc_perf_ctrs_in_pcc_cpu(cpu)) { + kthread_init_work(&cppc_fi->work, cppc_scale_freq_workfn); + init_irq_work(&cppc_fi->irq_work, cppc_irq_work); + sftd = &cppc_sftd_pcc; + } + + ret = cppc_get_perf_ctrs(cpu, &cppc_fi->prev_perf_fb_ctrs); + + /* + * Don't abort as the CPU was offline while the driver was + * getting registered. + */ + if (ret && cpu_online(cpu)) { + pr_debug("%s: failed to read perf counters for cpu:%d: %d\n", + __func__, cpu, ret); + return; + } + } + + /* Register for freq-invariance */ + topology_set_scale_freq_source(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) { + if (!cppc_perf_ctrs_in_pcc_cpu(cpu)) + continue; + cppc_fi = &per_cpu(cppc_freq_inv, cpu); + irq_work_sync(&cppc_fi->irq_work); + kthread_cancel_work_sync(&cppc_fi->work); + } +} + +static void cppc_fie_kworker_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 = NSEC_PER_MSEC, + .sched_deadline = 10 * NSEC_PER_MSEC, + .sched_period = 10 * NSEC_PER_MSEC, + }; + int ret; + + kworker_fie = kthread_run_worker(0, "cppc_fie"); + if (IS_ERR(kworker_fie)) { + pr_warn("%s: failed to create kworker_fie: %ld\n", __func__, + PTR_ERR(kworker_fie)); + fie_disabled = FIE_DISABLED; + kworker_fie = NULL; + 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); + fie_disabled = FIE_DISABLED; + kworker_fie = NULL; + } +} + +static void __init cppc_freq_invariance_init(void) +{ + bool perf_ctrs_in_pcc = cppc_perf_ctrs_in_pcc(); + + if (fie_disabled == FIE_UNSET) { + if (perf_ctrs_in_pcc) { + pr_info("FIE not enabled on systems with registers in PCC\n"); + fie_disabled = FIE_DISABLED; + } else { + fie_disabled = FIE_ENABLED; + } + } + + if (fie_disabled || !perf_ctrs_in_pcc) + return; + + cppc_fie_kworker_init(); +} + +static void cppc_freq_invariance_exit(void) +{ + if (kworker_fie) + kthread_destroy_worker(kworker_fie); +} + +#else +static 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 */ + +static void cppc_cpufreq_get_perf_limits(struct cppc_cpudata *cpu_data, + struct cpufreq_policy *policy, + u32 *min_perf, u32 *max_perf) +{ + struct cppc_perf_caps *caps = &cpu_data->perf_caps; + unsigned int min_freq, max_freq; + u32 min, max; + + min_freq = READ_ONCE(policy->min); + max_freq = READ_ONCE(policy->max); + if (unlikely(min_freq > max_freq)) + min_freq = max_freq; + + min = cppc_khz_to_perf(caps, min_freq); + max = cppc_khz_to_perf(caps, max_freq); + + *min_perf = clamp_t(u32, min, caps->lowest_perf, caps->highest_perf); + *max_perf = clamp_t(u32, max, caps->lowest_perf, caps->highest_perf); +} + +static void cppc_cpufreq_update_perf_limits(struct cppc_cpudata *cpu_data, + struct cpufreq_policy *policy) +{ + cppc_cpufreq_get_perf_limits(cpu_data, policy, + &cpu_data->perf_ctrls.min_perf, + &cpu_data->perf_ctrls.max_perf); +} + +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; + int ret = 0; + + cpu_data->perf_ctrls.desired_perf = + cppc_khz_to_perf(&cpu_data->perf_caps, target_freq); + cppc_cpufreq_update_perf_limits(cpu_data, policy); + + 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_khz_to_perf(&cpu_data->perf_caps, target_freq); + cpu_data->perf_ctrls.desired_perf = desired_perf; + cppc_cpufreq_update_perf_limits(cpu_data, policy); + + 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; +} + +static unsigned int __cppc_cpufreq_get_transition_delay_us(unsigned int cpu) +{ + int transition_latency_ns = cppc_get_transition_latency(cpu); + + if (transition_latency_ns < 0) + return CPUFREQ_DEFAULT_TRANSITION_LATENCY_NS / NSEC_PER_USEC; + + return transition_latency_ns / NSEC_PER_USEC; +} + +/* + * 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 + +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_cpufreq_get_transition_delay_us(cpu); +} +#else +static unsigned int cppc_cpufreq_get_transition_delay_us(unsigned int cpu) +{ + return __cppc_cpufreq_get_transition_delay_us(cpu); +} +#endif + +#if defined(CONFIG_ARM64) && defined(CONFIG_ENERGY_MODEL) + +static DEFINE_PER_CPU(unsigned int, efficiency_class); + +/* 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((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) +{ + return CPPC_EM_COST_GAP * per_cpu(efficiency_class, cpu) + + step * CPPC_EM_COST_STEP; +} + +static int cppc_get_cpu_power(struct device *cpu_dev, + unsigned long *power, unsigned long *KHz) +{ + unsigned long perf_step, perf_prev, perf, perf_check; + unsigned int min_step, max_step, step, step_check; + unsigned long prev_freq = *KHz; + unsigned int min_cap, max_cap; + struct cpufreq_policy *policy; + + struct cppc_perf_caps *perf_caps; + struct cppc_cpudata *cpu_data; + + policy = cpufreq_cpu_get_raw(cpu_dev->id); + if (!policy) + return -EINVAL; + + cpu_data = policy->driver_data; + perf_caps = &cpu_data->perf_caps; + max_cap = arch_scale_cpu_capacity(cpu_dev->id); + min_cap = div_u64((u64)max_cap * perf_caps->lowest_perf, + perf_caps->highest_perf); + perf_step = div_u64((u64)CPPC_EM_CAP_STEP * perf_caps->highest_perf, + max_cap); + min_step = min_cap / CPPC_EM_CAP_STEP; + max_step = max_cap / CPPC_EM_CAP_STEP; + + perf_prev = cppc_khz_to_perf(perf_caps, *KHz); + step = perf_prev / perf_step; + + if (step > max_step) + return -EINVAL; + + if (min_step == max_step) { + step = max_step; + perf = perf_caps->highest_perf; + } else if (step < min_step) { + step = min_step; + perf = perf_caps->lowest_perf; + } else { + step++; + if (step == max_step) + perf = perf_caps->highest_perf; + else + perf = step * perf_step; + } + + *KHz = cppc_perf_to_khz(perf_caps, perf); + perf_check = cppc_khz_to_perf(perf_caps, *KHz); + step_check = perf_check / perf_step; + + /* + * To avoid bad integer approximation, check that new frequency value + * increased and that the new frequency will be converted to the + * desired step value. + */ + while ((*KHz == prev_freq) || (step_check != step)) { + perf++; + *KHz = cppc_perf_to_khz(perf_caps, perf); + perf_check = cppc_khz_to_perf(perf_caps, *KHz); + step_check = perf_check / perf_step; + } + + /* + * With an artificial EM, only the cost value is used. Still the power + * is populated such as 0 < power < EM_MAX_POWER. This allows to add + * more sense to the artificial performance states. + */ + *power = compute_cost(cpu_dev->id, step); + + return 0; +} + +static int cppc_get_cpu_cost(struct device *cpu_dev, unsigned long KHz, + unsigned long *cost) +{ + unsigned long perf_step, perf_prev; + struct cppc_perf_caps *perf_caps; + struct cpufreq_policy *policy; + struct cppc_cpudata *cpu_data; + unsigned int max_cap; + int step; + + policy = cpufreq_cpu_get_raw(cpu_dev->id); + if (!policy) + return -EINVAL; + + cpu_data = policy->driver_data; + perf_caps = &cpu_data->perf_caps; + max_cap = arch_scale_cpu_capacity(cpu_dev->id); + + perf_prev = cppc_khz_to_perf(perf_caps, KHz); + perf_step = CPPC_EM_CAP_STEP * perf_caps->highest_perf / max_cap; + step = perf_prev / perf_step; + + *cost = compute_cost(cpu_dev->id, step); + + return 0; +} + +static void cppc_cpufreq_register_em(struct cpufreq_policy *policy) +{ + struct cppc_cpudata *cpu_data; + struct em_data_callback em_cb = + EM_ADV_DATA_CB(cppc_get_cpu_power, cppc_get_cpu_cost); + + cpu_data = policy->driver_data; + em_dev_register_perf_domain(get_cpu_device(policy->cpu), + get_perf_level_count(policy), &em_cb, + cpu_data->shared_cpu_map, 0); +} + +static void populate_efficiency_class(void) +{ + struct acpi_madt_generic_interrupt *gicc; + DECLARE_BITMAP(used_classes, 256) = {}; + int class, cpu, index; + + for_each_possible_cpu(cpu) { + gicc = acpi_cpu_get_madt_gicc(cpu); + class = gicc->efficiency_class; + bitmap_set(used_classes, class, 1); + } + + if (bitmap_weight(used_classes, 256) <= 1) { + pr_debug("Efficiency classes are all equal (=%d). " + "No EM registered", class); + return; + } + + /* + * Squeeze efficiency class values on [0:#efficiency_class-1]. + * Values are per spec in [0:255]. + */ + index = 0; + for_each_set_bit(class, used_classes, 256) { + for_each_possible_cpu(cpu) { + gicc = acpi_cpu_get_madt_gicc(cpu); + if (gicc->efficiency_class == class) + per_cpu(efficiency_class, cpu) = index; + } + index++; + } + cppc_cpufreq_driver.register_em = cppc_cpufreq_register_em; +} + +#else +static void populate_efficiency_class(void) +{ +} +#endif + +static struct cppc_cpudata *cppc_cpufreq_get_cpu_data(unsigned int cpu) +{ + struct cppc_cpudata *cpu_data; + int ret; + + cpu_data = kzalloc_obj(struct cppc_cpudata); + if (!cpu_data) + goto out; + + if (!zalloc_cpumask_var(&cpu_data->shared_cpu_map, GFP_KERNEL)) + goto free_cpu; + + ret = acpi_get_psd_map(cpu, cpu_data); + if (ret) { + pr_debug("Err parsing CPU%d PSD data: ret:%d\n", cpu, ret); + goto free_mask; + } + + ret = cppc_get_perf_caps(cpu, &cpu_data->perf_caps); + if (ret) { + pr_debug("Err reading CPU%d perf caps: ret:%d\n", cpu, ret); + goto free_mask; + } + + ret = cppc_get_perf(cpu, &cpu_data->perf_ctrls); + if (ret) { + pr_debug("Err reading CPU%d perf ctrls: ret:%d\n", cpu, ret); + goto free_mask; + } + + return cpu_data; + +free_mask: + free_cpumask_var(cpu_data->shared_cpu_map); +free_cpu: + kfree(cpu_data); +out: + return NULL; +} + +static void cppc_cpufreq_put_cpu_data(struct cpufreq_policy *policy) +{ + struct cppc_cpudata *cpu_data = policy->driver_data; + + free_cpumask_var(cpu_data->shared_cpu_map); + kfree(cpu_data); + policy->driver_data = NULL; +} + +static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy) +{ + unsigned int cpu = policy->cpu; + struct cppc_cpudata *cpu_data; + struct cppc_perf_caps *caps; + int ret; + + cpu_data = cppc_cpufreq_get_cpu_data(cpu); + if (!cpu_data) { + pr_err("Error in acquiring _CPC/_PSD data for CPU%d.\n", cpu); + return -ENODEV; + } + caps = &cpu_data->perf_caps; + policy->driver_data = cpu_data; + + /* + * Set min to lowest nonlinear perf to avoid any efficiency penalty (see + * Section 8.4.7.1.1.5 of ACPI 6.1 spec) + */ + policy->min = cppc_perf_to_khz(caps, caps->lowest_nonlinear_perf); + + /* + * Set cpuinfo.min_freq to Lowest to make the full range of performance + * available if userspace wants to use any perf between lowest & lowest + * nonlinear perf + */ + policy->cpuinfo.min_freq = cppc_perf_to_khz(caps, caps->lowest_perf); + policy->cpuinfo.max_freq = cppc_perf_to_khz(caps, policy->boost_enabled ? + caps->highest_perf : caps->nominal_perf); + + policy->transition_delay_us = cppc_cpufreq_get_transition_delay_us(cpu); + policy->shared_type = cpu_data->shared_type; + + switch (policy->shared_type) { + case CPUFREQ_SHARED_TYPE_HW: + case CPUFREQ_SHARED_TYPE_NONE: + /* Nothing to be done - we'll have a policy for each CPU */ + break; + case CPUFREQ_SHARED_TYPE_ANY: + /* + * All CPUs in the domain will share a policy and all cpufreq + * operations will use a single cppc_cpudata structure stored + * in policy->driver_data. + */ + cpumask_copy(policy->cpus, cpu_data->shared_cpu_map); + break; + default: + pr_debug("Unsupported CPU co-ord type: %d\n", + policy->shared_type); + ret = -EFAULT; + goto out; + } + + policy->fast_switch_possible = cppc_allow_fast_switch(policy->cpus); + policy->dvfs_possible_from_any_cpu = true; + + /* + * If 'highest_perf' is greater than 'nominal_perf', we assume CPU Boost + * is supported. + */ + if (caps->highest_perf > caps->nominal_perf) + policy->boost_supported = true; + + /* Set policy->cur to max now. The governors will adjust later. */ + policy->cur = cppc_perf_to_khz(caps, caps->highest_perf); + cpu_data->perf_ctrls.desired_perf = caps->highest_perf; + + ret = cppc_set_perf(cpu, &cpu_data->perf_ctrls); + if (ret) { + pr_debug("Err setting perf value:%d on CPU:%d. ret:%d\n", + caps->highest_perf, cpu, ret); + goto out; + } + + cppc_cpufreq_cpu_fie_init(policy); + return 0; + +out: + cppc_cpufreq_put_cpu_data(policy); + return ret; +} + +static void cppc_cpufreq_cpu_exit(struct cpufreq_policy *policy) +{ + struct cppc_cpudata *cpu_data = policy->driver_data; + struct cppc_perf_caps *caps = &cpu_data->perf_caps; + unsigned int cpu = policy->cpu; + int ret; + + cppc_cpufreq_cpu_fie_exit(policy); + + cpu_data->perf_ctrls.desired_perf = caps->lowest_perf; + + ret = cppc_set_perf(cpu, &cpu_data->perf_ctrls); + if (ret) + pr_debug("Err setting perf value:%d on CPU:%d. ret:%d\n", + caps->lowest_perf, cpu, ret); + + cppc_cpufreq_put_cpu_data(policy); +} + +static inline u64 get_delta(u64 t1, u64 t0) +{ + if (t1 > t0 || t0 > ~(u32)0) + return t1 - t0; + + return (u32)t1 - (u32)t0; +} + +static int cppc_perf_from_fbctrs(u64 reference_perf, + struct cppc_perf_fb_ctrs *fb_ctrs_t0, + struct cppc_perf_fb_ctrs *fb_ctrs_t1) +{ + u64 delta_reference, delta_delivered; + + delta_reference = get_delta(fb_ctrs_t1->reference, + fb_ctrs_t0->reference); + delta_delivered = get_delta(fb_ctrs_t1->delivered, + fb_ctrs_t0->delivered); + + /* + * Avoid divide-by zero and unchanged feedback counters. + * Leave it for callers to handle. + */ + if (!delta_reference || !delta_delivered) + return 0; + + return (reference_perf * delta_delivered) / delta_reference; +} + +static int cppc_get_perf_ctrs_sample(int cpu, + struct cppc_perf_fb_ctrs *fb_ctrs_t0, + struct cppc_perf_fb_ctrs *fb_ctrs_t1) +{ + int ret; + + ret = cppc_get_perf_ctrs(cpu, fb_ctrs_t0); + if (ret) + return ret; + + udelay(2); /* 2usec delay between sampling */ + + return cppc_get_perf_ctrs(cpu, fb_ctrs_t1); +} + +static unsigned int cppc_cpufreq_get_rate(unsigned int cpu) +{ + struct cpufreq_policy *policy __free(put_cpufreq_policy) = cpufreq_cpu_get(cpu); + struct cppc_perf_fb_ctrs fb_ctrs_t0 = {0}, fb_ctrs_t1 = {0}; + struct cppc_cpudata *cpu_data; + u64 delivered_perf, reference_perf; + int ret; + + if (!policy) + return 0; + + cpu_data = policy->driver_data; + + ret = cppc_get_perf_ctrs_sample(cpu, &fb_ctrs_t0, &fb_ctrs_t1); + if (ret) { + if (ret == -EFAULT) + /* Any of the associated CPPC regs is 0. */ + goto out_invalid_counters; + else + return 0; + } + + reference_perf = cpu_data->perf_caps.reference_perf; + delivered_perf = cppc_perf_from_fbctrs(reference_perf, + &fb_ctrs_t0, &fb_ctrs_t1); + if (!delivered_perf) + goto out_invalid_counters; + + return cppc_perf_to_khz(&cpu_data->perf_caps, delivered_perf); + +out_invalid_counters: + /* + * Feedback counters could be unchanged or 0 when a cpu enters a + * low-power idle state, e.g. clock-gated or power-gated. + * Use desired perf for reflecting frequency. Get the latest register + * value first as some platforms may update the actual delivered perf + * there; if failed, resort to the cached desired perf. + */ + if (cppc_get_desired_perf(cpu, &delivered_perf) || !delivered_perf) + delivered_perf = cpu_data->perf_ctrls.desired_perf; + + return cppc_perf_to_khz(&cpu_data->perf_caps, delivered_perf); +} + +static int cppc_cpufreq_set_boost(struct cpufreq_policy *policy, int state) +{ + struct cppc_cpudata *cpu_data = policy->driver_data; + struct cppc_perf_caps *caps = &cpu_data->perf_caps; + + if (state) + policy->cpuinfo.max_freq = cppc_perf_to_khz(caps, caps->highest_perf); + else + policy->cpuinfo.max_freq = cppc_perf_to_khz(caps, caps->nominal_perf); + + return 0; +} + +static ssize_t show_freqdomain_cpus(struct cpufreq_policy *policy, char *buf) +{ + struct cppc_cpudata *cpu_data = policy->driver_data; + + return cpufreq_show_cpus(cpu_data->shared_cpu_map, buf); +} + +static ssize_t show_auto_select(struct cpufreq_policy *policy, char *buf) +{ + bool val; + int ret; + + ret = cppc_get_auto_sel(policy->cpu, &val); + + /* show "" when this register is not supported by cpc */ + if (ret == -EOPNOTSUPP) + return sysfs_emit(buf, "\n"); + + if (ret) + return ret; + + return sysfs_emit(buf, "%d\n", val); +} + +static ssize_t store_auto_select(struct cpufreq_policy *policy, + const char *buf, size_t count) +{ + struct cppc_cpudata *cpu_data = policy->driver_data; + bool val; + int ret; + + ret = kstrtobool(buf, &val); + if (ret) + return ret; + + ret = cppc_set_auto_sel(policy->cpu, val); + if (ret) + return ret; + + cpu_data->perf_ctrls.auto_sel = val; + + if (val) { + u32 old_min_perf = cpu_data->perf_ctrls.min_perf; + u32 old_max_perf = cpu_data->perf_ctrls.max_perf; + + /* + * When enabling autonomous selection, program MIN_PERF and + * MAX_PERF from current policy limits so that the platform + * uses the correct performance bounds immediately. + */ + cppc_cpufreq_update_perf_limits(cpu_data, policy); + + ret = cppc_set_perf(policy->cpu, &cpu_data->perf_ctrls); + if (ret) { + cpu_data->perf_ctrls.min_perf = old_min_perf; + cpu_data->perf_ctrls.max_perf = old_max_perf; + cppc_set_auto_sel(policy->cpu, false); + cpu_data->perf_ctrls.auto_sel = false; + return ret; + } + } + + return count; +} + +static ssize_t cppc_cpufreq_sysfs_show_u64(unsigned int cpu, + int (*get_func)(int, u64 *), + char *buf) +{ + u64 val; + int ret = get_func((int)cpu, &val); + + if (ret == -EOPNOTSUPP) + return sysfs_emit(buf, "\n"); + + if (ret) + return ret; + + return sysfs_emit(buf, "%llu\n", val); +} + +static ssize_t cppc_cpufreq_sysfs_store_u64(unsigned int cpu, + int (*set_func)(int, u64), + const char *buf, size_t count) +{ + u64 val; + int ret; + + ret = kstrtou64(buf, 0, &val); + if (ret) + return ret; + + ret = set_func((int)cpu, val); + + return ret ? ret : count; +} + +#define CPPC_CPUFREQ_ATTR_RW_U64(_name, _get_func, _set_func) \ +static ssize_t show_##_name(struct cpufreq_policy *policy, char *buf) \ +{ \ + return cppc_cpufreq_sysfs_show_u64(policy->cpu, _get_func, buf);\ +} \ +static ssize_t store_##_name(struct cpufreq_policy *policy, \ + const char *buf, size_t count) \ +{ \ + return cppc_cpufreq_sysfs_store_u64(policy->cpu, _set_func, \ + buf, count); \ +} + +CPPC_CPUFREQ_ATTR_RW_U64(auto_act_window, cppc_get_auto_act_window, + cppc_set_auto_act_window) + +static ssize_t +show_energy_performance_preference_val(struct cpufreq_policy *policy, char *buf) +{ + return cppc_cpufreq_sysfs_show_u64(policy->cpu, cppc_get_epp_perf, buf); +} + +static ssize_t +store_energy_performance_preference_val(struct cpufreq_policy *policy, + const char *buf, size_t count) +{ + struct cppc_cpudata *cpu_data = policy->driver_data; + u64 val; + int ret; + + ret = kstrtou64(buf, 0, &val); + if (ret) + return ret; + + ret = cppc_set_epp(policy->cpu, val); + if (ret) + return ret; + + cpu_data->perf_ctrls.energy_perf = val; + + return count; +} + +static int cppc_get_perf_limited_filtered(int cpu, u64 *perf_limited) +{ + struct cpufreq_policy *policy; + struct cppc_cpudata *cpu_data; + int ret; + + ret = cppc_get_perf_limited(cpu, perf_limited); + if (ret) + return ret; + + policy = cpufreq_cpu_get_raw(cpu); + if (!policy) + return -EINVAL; + + cpu_data = policy->driver_data; + + /* + * Desired Excursion is ignored when autonomous selection is + * enabled. Clear the bit to avoid exposing meaningless state + * to userspace. + */ + if (cpu_data && cpu_data->perf_ctrls.auto_sel) + *perf_limited &= ~CPPC_PERF_LIMITED_DESIRED_EXCURSION; + + return 0; +} + +CPPC_CPUFREQ_ATTR_RW_U64(perf_limited, cppc_get_perf_limited_filtered, + cppc_set_perf_limited) + +cpufreq_freq_attr_ro(freqdomain_cpus); +cpufreq_freq_attr_rw(auto_select); +cpufreq_freq_attr_rw(auto_act_window); +cpufreq_freq_attr_rw(energy_performance_preference_val); +cpufreq_freq_attr_rw(perf_limited); + +static struct freq_attr *cppc_cpufreq_attr[] = { + &freqdomain_cpus, + &auto_select, + &auto_act_window, + &energy_performance_preference_val, + &perf_limited, + NULL, +}; + +static struct cpufreq_driver cppc_cpufreq_driver = { + .flags = CPUFREQ_CONST_LOOPS | CPUFREQ_NEED_UPDATE_LIMITS, + .verify = cppc_verify_policy, + .target = cppc_cpufreq_set_target, + .get = cppc_cpufreq_get_rate, + .fast_switch = cppc_cpufreq_fast_switch, + .init = cppc_cpufreq_cpu_init, + .exit = cppc_cpufreq_cpu_exit, + .set_boost = cppc_cpufreq_set_boost, + .attr = cppc_cpufreq_attr, + .name = "cppc_cpufreq", +}; + +static int __init cppc_cpufreq_init(void) +{ + int ret; + + if (!acpi_cpc_valid()) + return -ENODEV; + + cppc_freq_invariance_init(); + populate_efficiency_class(); + + ret = cpufreq_register_driver(&cppc_cpufreq_driver); + if (ret) + cppc_freq_invariance_exit(); + + return ret; +} + +static void __exit cppc_cpufreq_exit(void) +{ + cpufreq_unregister_driver(&cppc_cpufreq_driver); + cppc_freq_invariance_exit(); +} + +module_exit(cppc_cpufreq_exit); +MODULE_AUTHOR("Ashwin Chaugule"); +MODULE_DESCRIPTION("CPUFreq driver based on the ACPI CPPC v5.0+ spec"); +MODULE_LICENSE("GPL"); + +late_initcall(cppc_cpufreq_init); + +static const struct acpi_device_id cppc_acpi_ids[] __used = { + {ACPI_PROCESSOR_DEVICE_HID, }, + {} +}; + +MODULE_DEVICE_TABLE(acpi, cppc_acpi_ids); -- cgit v1.3.1