diff options
32 files changed, 1055 insertions, 801 deletions
diff --git a/Documentation/scheduler/sched-design-CFS.rst b/Documentation/scheduler/sched-design-CFS.rst index f68919800f05..6cffffe26500 100644 --- a/Documentation/scheduler/sched-design-CFS.rst +++ b/Documentation/scheduler/sched-design-CFS.rst @@ -180,7 +180,7 @@ This is the (partial) list of the hooks: compat_yield sysctl is turned on; in that case, it places the scheduling entity at the right-most end of the red-black tree. - - check_preempt_curr(...) + - wakeup_preempt(...) This function checks if a task that entered the runnable state should preempt the currently running task. @@ -189,10 +189,10 @@ This is the (partial) list of the hooks: This function chooses the most appropriate task eligible to run next. - - set_curr_task(...) + - set_next_task(...) - This function is called when a task changes its scheduling class or changes - its task group. + This function is called when a task changes its scheduling class, changes + its task group or is scheduled. - task_tick(...) diff --git a/Documentation/scheduler/schedutil.rst b/Documentation/scheduler/schedutil.rst index 32c7d69fc86c..803fba8fc714 100644 --- a/Documentation/scheduler/schedutil.rst +++ b/Documentation/scheduler/schedutil.rst @@ -90,8 +90,8 @@ For more detail see: - Documentation/scheduler/sched-capacity.rst:"1. CPU Capacity + 2. Task utilization" -UTIL_EST / UTIL_EST_FASTUP -========================== +UTIL_EST +======== Because periodic tasks have their averages decayed while they sleep, even though when running their expected utilization will be the same, they suffer a @@ -99,8 +99,7 @@ though when running their expected utilization will be the same, they suffer a To alleviate this (a default enabled option) UTIL_EST drives an Infinite Impulse Response (IIR) EWMA with the 'running' value on dequeue -- when it is -highest. A further default enabled option UTIL_EST_FASTUP modifies the IIR -filter to instantly increase and only decay on decrease. +highest. UTIL_EST filters to instantly increase and only decay on decrease. A further runqueue wide sum (of runnable tasks) is maintained of: diff --git a/Documentation/translations/zh_CN/scheduler/sched-design-CFS.rst b/Documentation/translations/zh_CN/scheduler/sched-design-CFS.rst index 3076402406c4..abc6709ec3b2 100644 --- a/Documentation/translations/zh_CN/scheduler/sched-design-CFS.rst +++ b/Documentation/translations/zh_CN/scheduler/sched-design-CFS.rst @@ -80,7 +80,7 @@ p->se.vruntime。一旦p->se.vruntime变得足够大，其它的任务将成为 CFS使用纳秒粒度的计时，不依赖于任何jiffies或HZ的细节。因此CFS并不像之前的调度器那样 有“时间片”的概念，也没有任何启发式的设计。唯一可调的参数（你需要打开CONFIG_SCHED_DEBUG）是： - /sys/kernel/debug/sched/min_granularity_ns + /sys/kernel/debug/sched/base_slice_ns 它可以用来将调度器从“桌面”模式（也就是低时延）调节为“服务器”（也就是高批处理）模式。 它的默认设置是适合桌面的工作负载。SCHED_BATCH也被CFS调度器模块处理。 @@ -147,7 +147,7 @@ array）。 这个函数的行为基本上是出队，紧接着入队，除非compat_yield sysctl被开启。在那种情况下， 它将调度实体放在红黑树的最右端。 - - check_preempt_curr(...) + - wakeup_preempt(...) 这个函数检查进入可运行状态的任务能否抢占当前正在运行的任务。 @@ -155,9 +155,9 @@ array）。 这个函数选择接下来最适合运行的任务。 - - set_curr_task(...) + - set_next_task(...) - 这个函数在任务改变调度类或改变任务组时被调用。 + 这个函数在任务改变调度类，改变任务组时，或者任务被调度时被调用。 - task_tick(...) diff --git a/Documentation/translations/zh_CN/scheduler/schedutil.rst b/Documentation/translations/zh_CN/scheduler/schedutil.rst index d1ea68007520..7c8d87f21c42 100644 --- a/Documentation/translations/zh_CN/scheduler/schedutil.rst +++ b/Documentation/translations/zh_CN/scheduler/schedutil.rst @@ -89,16 +89,15 @@ r_cpu被定义为当前CPU的最高性能水平与系统中任何其它CPU的最 - Documentation/translations/zh_CN/scheduler/sched-capacity.rst:"1. CPU Capacity + 2. Task utilization" -UTIL_EST / UTIL_EST_FASTUP -========================== +UTIL_EST +======== 由于周期性任务的平均数在睡眠时会衰减，而在运行时其预期利用率会和睡眠前相同， 因此它们在再次运行后会面临（DVFS）的上涨。 为了缓解这个问题，（一个默认使能的编译选项）UTIL_EST驱动一个无限脉冲响应 （Infinite Impulse Response，IIR）的EWMA，“运行”值在出队时是最高的。 -另一个默认使能的编译选项UTIL_EST_FASTUP修改了IIR滤波器，使其允许立即增加， -仅在利用率下降时衰减。 +UTIL_EST滤波使其在遇到更高值时立刻增加，而遇到低值时会缓慢衰减。 进一步，运行队列的（可运行任务的）利用率之和由下式计算： diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h index c7d2510e5a78..853c4f81ba4a 100644 --- a/arch/arm/include/asm/topology.h +++ b/arch/arm/include/asm/topology.h @@ -13,6 +13,7 @@ #define arch_set_freq_scale topology_set_freq_scale #define arch_scale_freq_capacity topology_get_freq_scale #define arch_scale_freq_invariant topology_scale_freq_invariant +#define arch_scale_freq_ref topology_get_freq_ref #endif /* Replace task scheduler's default cpu-invariant accounting */ diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h index 9fab663dd2de..a323b109b9c4 100644 --- a/arch/arm64/include/asm/topology.h +++ b/arch/arm64/include/asm/topology.h @@ -23,6 +23,7 @@ void update_freq_counters_refs(void); #define arch_set_freq_scale topology_set_freq_scale #define arch_scale_freq_capacity topology_get_freq_scale #define arch_scale_freq_invariant topology_scale_freq_invariant +#define arch_scale_freq_ref topology_get_freq_ref #ifdef CONFIG_ACPI_CPPC_LIB #define arch_init_invariance_cppc topology_init_cpu_capacity_cppc diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c index 817d788cd866..1a2c72f3e7f8 100644 --- a/arch/arm64/kernel/topology.c +++ b/arch/arm64/kernel/topology.c @@ -82,7 +82,12 @@ int __init parse_acpi_topology(void) #undef pr_fmt #define pr_fmt(fmt) "AMU: " fmt -static DEFINE_PER_CPU_READ_MOSTLY(unsigned long, arch_max_freq_scale); +/* + * Ensure that amu_scale_freq_tick() will return SCHED_CAPACITY_SCALE until + * the CPU capacity and its associated frequency have been correctly + * initialized. + */ +static DEFINE_PER_CPU_READ_MOSTLY(unsigned long, arch_max_freq_scale) = 1UL << (2 * SCHED_CAPACITY_SHIFT); static DEFINE_PER_CPU(u64, arch_const_cycles_prev); static DEFINE_PER_CPU(u64, arch_core_cycles_prev); static cpumask_var_t amu_fie_cpus; @@ -112,14 +117,14 @@ static inline bool freq_counters_valid(int cpu) return true; } -static int freq_inv_set_max_ratio(int cpu, u64 max_rate, u64 ref_rate) +void freq_inv_set_max_ratio(int cpu, u64 max_rate) { - u64 ratio; + u64 ratio, ref_rate = arch_timer_get_rate(); if (unlikely(!max_rate || !ref_rate)) { - pr_debug("CPU%d: invalid maximum or reference frequency.\n", + WARN_ONCE(1, "CPU%d: invalid maximum or reference frequency.\n", cpu); - return -EINVAL; + return; } /* @@ -139,12 +144,10 @@ static int freq_inv_set_max_ratio(int cpu, u64 max_rate, u64 ref_rate) ratio = div64_u64(ratio, max_rate); if (!ratio) { WARN_ONCE(1, "Reference frequency too low.\n"); - return -EINVAL; + return; } - per_cpu(arch_max_freq_scale, cpu) = (unsigned long)ratio; - - return 0; + WRITE_ONCE(per_cpu(arch_max_freq_scale, cpu), (unsigned long)ratio); } static void amu_scale_freq_tick(void) @@ -195,10 +198,7 @@ static void amu_fie_setup(const struct cpumask *cpus) return; for_each_cpu(cpu, cpus) { - if (!freq_counters_valid(cpu) || - freq_inv_set_max_ratio(cpu, - cpufreq_get_hw_max_freq(cpu) * 1000ULL, - arch_timer_get_rate())) + if (!freq_counters_valid(cpu)) return; } diff --git a/arch/riscv/include/asm/topology.h b/arch/riscv/include/asm/topology.h index e316ab3b77f3..61183688bdd5 100644 --- a/arch/riscv/include/asm/topology.h +++ b/arch/riscv/include/asm/topology.h @@ -9,6 +9,7 @@ #define arch_set_freq_scale topology_set_freq_scale #define arch_scale_freq_capacity topology_get_freq_scale #define arch_scale_freq_invariant topology_scale_freq_invariant +#define arch_scale_freq_ref topology_get_freq_ref /* Replace task scheduler's default cpu-invariant accounting */ #define arch_scale_cpu_capacity topology_get_cpu_scale diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c index 7ff269a78c20..d155a86a8614 100644 --- a/drivers/acpi/cppc_acpi.c +++ b/drivers/acpi/cppc_acpi.c @@ -39,6 +39,9 @@ #include <linux/rwsem.h> #include <linux/wait.h> #include <linux/topology.h> +#include <linux/dmi.h> +#include <linux/units.h> +#include <asm/unaligned.h> #include <acpi/cppc_acpi.h> @@ -1760,3 +1763,104 @@ unsigned int cppc_get_transition_latency(int cpu_num) return latency_ns; } EXPORT_SYMBOL_GPL(cppc_get_transition_latency); + +/* 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 + +/* 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 KHZ_PER_MHZ * 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 freq) + */ +unsigned int cppc_perf_to_khz(struct cppc_perf_caps *caps, unsigned int perf) +{ + 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; + mul *= KHZ_PER_MHZ; + div = caps->nominal_perf - caps->lowest_perf; + offset = caps->nominal_freq * KHZ_PER_MHZ - + 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; +} +EXPORT_SYMBOL_GPL(cppc_perf_to_khz); + +unsigned int cppc_khz_to_perf(struct cppc_perf_caps *caps, unsigned int freq) +{ + 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; + /* + * We don't need to convert to kHz for computing offset and can + * directly use nominal_freq and lowest_freq as the div64_u64 + * will remove the frequency unit. + */ + offset = caps->nominal_perf - + div64_u64(caps->nominal_freq * mul, div); + /* But we need it for computing the perf level. */ + div *= KHZ_PER_MHZ; + } 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; +} +EXPORT_SYMBOL_GPL(cppc_khz_to_perf); diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c index b741b5ba82bd..5aaa0865625d 100644 --- a/drivers/base/arch_topology.c +++ b/drivers/base/arch_topology.c @@ -19,6 +19,7 @@ #include <linux/init.h> #include <linux/rcupdate.h> #include <linux/sched.h> +#include <linux/units.h> #define CREATE_TRACE_POINTS #include <trace/events/thermal_pressure.h> @@ -26,7 +27,8 @@ static DEFINE_PER_CPU(struct scale_freq_data __rcu *, sft_data); static struct cpumask scale_freq_counters_mask; static bool scale_freq_invariant; -static DEFINE_PER_CPU(u32, freq_factor) = 1; +DEFINE_PER_CPU(unsigned long, capacity_freq_ref) = 1; +EXPORT_PER_CPU_SYMBOL_GPL(capacity_freq_ref); static bool supports_scale_freq_counters(const struct cpumask *cpus) { @@ -170,9 +172,9 @@ DEFINE_PER_CPU(unsigned long, thermal_pressure); * operating on stale data when hot-plug is used for some CPUs. The * @capped_freq reflects the currently allowed max CPUs frequency due to * thermal capping. It might be also a boost frequency value, which is bigger - * than the internal 'freq_factor' max frequency. In such case the pressure - * value should simply be removed, since this is an indication that there is - * no thermal throttling. The @capped_freq must be provided in kHz. + * than the internal 'capacity_freq_ref' max frequency. In such case the + * pressure value should simply be removed, since this is an indication that + * there is no thermal throttling. The @capped_freq must be provided in kHz. */ void topology_update_thermal_pressure(const struct cpumask *cpus, unsigned long capped_freq) @@ -183,10 +185,7 @@ void topology_update_thermal_pressure(const struct cpumask *cpus, cpu = cpumask_first(cpus); max_capacity = arch_scale_cpu_capacity(cpu); - max_freq = per_cpu(freq_factor, cpu); - - /* Convert to MHz scale which is used in 'freq_factor' */ - capped_freq /= 1000; + max_freq = arch_scale_freq_ref(cpu); /* * Handle properly the boost frequencies, which should simply clean @@ -279,13 +278,13 @@ void topology_normalize_cpu_scale(void) capacity_scale = 1; for_each_possible_cpu(cpu) { - capacity = raw_capacity[cpu] * per_cpu(freq_factor, cpu); + capacity = raw_capacity[cpu] * per_cpu(capacity_freq_ref, cpu); capacity_scale = max(capacity, capacity_scale); } pr_debug("cpu_capacity: capacity_scale=%llu\n", capacity_scale); for_each_possible_cpu(cpu) { - capacity = raw_capacity[cpu] * per_cpu(freq_factor, cpu); + capacity = raw_capacity[cpu] * per_cpu(capacity_freq_ref, cpu); capacity = div64_u64(capacity << SCHED_CAPACITY_SHIFT, capacity_scale); topology_set_cpu_scale(cpu, capacity); @@ -321,15 +320,15 @@ bool __init topology_parse_cpu_capacity(struct device_node *cpu_node, int cpu) cpu_node, raw_capacity[cpu]); /* - * Update freq_factor for calculating early boot cpu capacities. + * Update capacity_freq_ref for calculating early boot CPU capacities. * For non-clk CPU DVFS mechanism, there's no way to get the * frequency value now, assuming they are running at the same - * frequency (by keeping the initial freq_factor value). + * frequency (by keeping the initial capacity_freq_ref value). */ cpu_clk = of_clk_get(cpu_node, 0); if (!PTR_ERR_OR_ZERO(cpu_clk)) { - per_cpu(freq_factor, cpu) = - clk_get_rate(cpu_clk) / 1000; + per_cpu(capacity_freq_ref, cpu) = + clk_get_rate(cpu_clk) / HZ_PER_KHZ; clk_put(cpu_clk); } } else { @@ -345,11 +344,16 @@ bool __init topology_parse_cpu_capacity(struct device_node *cpu_node, int cpu) return !ret; } +void __weak freq_inv_set_max_ratio(int cpu, u64 max_rate) +{ +} + #ifdef CONFIG_ACPI_CPPC_LIB #include <acpi/cppc_acpi.h> void topology_init_cpu_capacity_cppc(void) { + u64 capacity, capacity_scale = 0; struct cppc_perf_caps perf_caps; int cpu; @@ -366,6 +370,10 @@ void topology_init_cpu_capacity_cppc(void) (perf_caps.highest_perf >= perf_caps.nominal_perf) && (perf_caps.highest_perf >= perf_caps.lowest_perf)) { raw_capacity[cpu] = perf_caps.highest_perf; + capacity_scale = max_t(u64, capacity_scale, raw_capacity[cpu]); + + per_cpu(capacity_freq_ref, cpu) = cppc_perf_to_khz(&perf_caps, raw_capacity[cpu]); + pr_debug("cpu_capacity: CPU%d cpu_capacity=%u (raw).\n", cpu, raw_capacity[cpu]); continue; @@ -376,7 +384,18 @@ void topology_init_cpu_capacity_cppc(void) goto exit; } - topology_normalize_cpu_scale(); + for_each_possible_cpu(cpu) { + freq_inv_set_max_ratio(cpu, + per_cpu(capacity_freq_ref, cpu) * HZ_PER_KHZ); + + capacity = raw_capacity[cpu]; + capacity = div64_u64(capacity << SCHED_CAPACITY_SHIFT, + capacity_scale); + topology_set_cpu_scale(cpu, capacity); + pr_debug("cpu_capacity: CPU%d cpu_capacity=%lu\n", + cpu, topology_get_cpu_scale(cpu)); + } + schedule_work(&update_topology_flags_work); pr_debug("cpu_capacity: cpu_capacity initialization done\n"); @@ -410,8 +429,11 @@ init_cpu_capacity_callback(struct notifier_block *nb, cpumask_andnot(cpus_to_visit, cpus_to_visit, policy->related_cpus); - for_each_cpu(cpu, policy->related_cpus) - per_cpu(freq_factor, cpu) = policy->cpuinfo.max_freq / 1000; + for_each_cpu(cpu, policy->related_cpus) { + per_cpu(capacity_freq_ref, cpu) = policy->cpuinfo.max_freq; + freq_inv_set_max_ratio(cpu, + per_cpu(capacity_freq_ref, cpu) * HZ_PER_KHZ); + } if (cpumask_empty(cpus_to_visit)) { topology_normalize_cpu_scale(); diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c index fe08ca419b3d..64420d9cfd1e 100644 --- a/drivers/cpufreq/cppc_cpufreq.c +++ b/drivers/cpufreq/cppc_cpufreq.c @@ -16,7 +16,6 @@ #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> @@ -27,12 +26,6 @@ #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, @@ -291,97 +284,9 @@ 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; @@ -389,7 +294,7 @@ static int cppc_cpufreq_set_target(struct cpufreq_policy *policy, u32 desired_perf; int ret = 0; - desired_perf = cppc_cpufreq_khz_to_perf(cpu_data, target_freq); + desired_perf = cppc_khz_to_perf(&cpu_data->perf_caps, target_freq); /* Return if it is exactly the same perf */ if (desired_perf == cpu_data->perf_ctrls.desired_perf) return ret; @@ -417,7 +322,7 @@ static unsigned int cppc_cpufreq_fast_switch(struct cpufreq_policy *policy, u32 desired_perf; int ret; - desired_perf = cppc_cpufreq_khz_to_perf(cpu_data, target_freq); + desired_perf = cppc_khz_to_perf(&cpu_data->perf_caps, target_freq); cpu_data->perf_ctrls.desired_perf = desired_perf; ret = cppc_set_perf(cpu, &cpu_data->perf_ctrls); @@ -530,7 +435,7 @@ static int cppc_get_cpu_power(struct device *cpu_dev, min_step = min_cap / CPPC_EM_CAP_STEP; max_step = max_cap / CPPC_EM_CAP_STEP; - perf_prev = cppc_cpufreq_khz_to_perf(cpu_data, *KHz); + perf_prev = cppc_khz_to_perf(perf_caps, *KHz); step = perf_prev / perf_step; if (step > max_step) @@ -550,8 +455,8 @@ static int cppc_get_cpu_power(struct device *cpu_dev, perf = step * perf_step; } - *KHz = cppc_cpufreq_perf_to_khz(cpu_data, perf); - perf_check = cppc_cpufreq_khz_to_perf(cpu_data, *KHz); + *KHz = cppc_perf_to_khz(perf_caps, perf); + perf_check = cppc_khz_to_perf(perf_caps, *KHz); step_check = perf_check / perf_step; /* @@ -561,8 +466,8 @@ static int cppc_get_cpu_power(struct device *cpu_dev, */ while ((*KHz == prev_freq) || (step_check != step)) { perf++; - *KHz = cppc_cpufreq_perf_to_khz(cpu_data, perf); - perf_check = cppc_cpufreq_khz_to_perf(cpu_data, *KHz); + *KHz = cppc_perf_to_khz(perf_caps, perf); + perf_check = cppc_khz_to_perf(perf_caps, *KHz); step_check = perf_check / perf_step; } @@ -591,7 +496,7 @@ static int cppc_get_cpu_cost(struct device *cpu_dev, unsigned long KHz, perf_caps = &cpu_data->perf_caps; max_cap = arch_scale_cpu_capacity(cpu_dev->id); - perf_prev = cppc_cpufreq_khz_to_perf(cpu_data, KHz); + 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; @@ -679,10 +584,6 @@ static struct cppc_cpudata *cppc_cpufreq_get_cpu_data(unsigned int cpu) goto free_mask; } - /* Convert the lowest and nominal freq from MHz to KHz */ - cpu_data->perf_caps.lowest_freq *= 1000; - cpu_data->perf_caps.nominal_freq *= 1000; - list_add(&cpu_data->node, &cpu_data_list); return cpu_data; @@ -724,20 +625,16 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy) * 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_cpufreq_perf_to_khz(cpu_data, - caps->lowest_nonlinear_perf); - policy->max = cppc_cpufreq_perf_to_khz(cpu_data, - caps->nominal_perf); + policy->min = cppc_perf_to_khz(caps, caps->lowest_nonlinear_perf); + policy->max = cppc_perf_to_khz(caps, caps->nominal_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_cpufreq_perf_to_khz(cpu_data, - caps->lowest_perf); - policy->cpuinfo.max_freq = cppc_cpufreq_perf_to_khz(cpu_data, - caps->nominal_perf); + policy->cpuinfo.min_freq = cppc_perf_to_khz(caps, caps->lowest_perf); + policy->cpuinfo.max_freq = cppc_perf_to_khz(caps, caps->nominal_perf); policy->transition_delay_us = cppc_cpufreq_get_transition_delay_us(cpu); policy->shared_type = cpu_data->shared_type; @@ -773,7 +670,7 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy) boost_supported = true; /* Set policy->cur to max now. The governors will adjust later. */ - policy->cur = cppc_cpufreq_perf_to_khz(cpu_data, caps->highest_perf); + 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); @@ -863,7 +760,7 @@ static unsigned int cppc_cpufreq_get_rate(unsigned int cpu) delivered_perf = cppc_perf_from_fbctrs(cpu_data, &fb_ctrs_t0, &fb_ctrs_t1); - return cppc_cpufreq_perf_to_khz(cpu_data, delivered_perf); + return cppc_perf_to_khz(&cpu_data->perf_caps, delivered_perf); } static int cppc_cpufreq_set_boost(struct cpufreq_policy *policy, int state) @@ -878,11 +775,9 @@ static int cppc_cpufreq_set_boost(struct cpufreq_policy *policy, int state) } if (state) - policy->max = cppc_cpufreq_perf_to_khz(cpu_data, - caps->highest_perf); + policy->max = cppc_perf_to_khz(caps, caps->highest_perf); else - policy->max = cppc_cpufreq_perf_to_khz(cpu_data, - caps->nominal_perf); + policy->max = cppc_perf_to_khz(caps, caps->nominal_perf); policy->cpuinfo.max_freq = policy->max; ret = freq_qos_update_request(policy->max_freq_req, policy->max); @@ -937,7 +832,7 @@ static unsigned int hisi_cppc_cpufreq_get_rate(unsigned int cpu) if (ret < 0) return -EIO; - return cppc_cpufreq_perf_to_khz(cpu_data, desired_perf); + return cppc_perf_to_khz(&cpu_data->perf_caps, desired_perf); } static void cppc_check_hisi_workaround(void) diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 934d35f570b7..44db4f59c4cc 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -454,7 +454,7 @@ void cpufreq_freq_transition_end(struct cpufreq_policy *policy, arch_set_freq_scale(policy->related_cpus, policy->cur, - policy->cpuinfo.max_freq); + arch_scale_freq_ref(policy->cpu)); spin_lock(&policy->transition_lock); policy->transition_ongoing = false; @@ -2174,7 +2174,7 @@ unsigned int cpufreq_driver_fast_switch(struct cpufreq_policy *policy, |