| Message ID | 20231104105907.1365392-1-vincent.guittot@linaro.org |
|---|---|
| Headers | show |
| Series | consolidate and cleanup CPU capacity | expand |
On Sat, Nov 4, 2023 at 11:59 AM Vincent Guittot <vincent.guittot@linaro.org> wrote: > > Move and rename cppc_cpufreq_perf_to_khz and cppc_cpufreq_khz_to_perf to > use them outside cppc_cpufreq in topology_init_cpu_capacity_cppc(). > > Modify the interface to use struct cppc_perf_caps *caps instead of > struct cppc_cpudata *cpu_data as we only use the fields of cppc_perf_caps. > > cppc_cpufreq was converting the lowest and nominal freq from MHz to kHz > before using them. We move this conversion inside cppc_perf_to_khz and > cppc_khz_to_perf to make them generic and usable outside cppc_cpufreq. > > No functional change > > Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Acked-by: Rafael J. Wysocki <rafael@kernel.org> > --- > drivers/acpi/cppc_acpi.c | 104 ++++++++++++++++++++++++ > drivers/cpufreq/cppc_cpufreq.c | 139 ++++----------------------------- > include/acpi/cppc_acpi.h | 2 + > 3 files changed, 123 insertions(+), 122 deletions(-) > > 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/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/include/acpi/cppc_acpi.h b/include/acpi/cppc_acpi.h > index 6126c977ece0..3a0995f8bce8 100644 > --- a/include/acpi/cppc_acpi.h > +++ b/include/acpi/cppc_acpi.h > @@ -144,6 +144,8 @@ extern int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls); > extern int cppc_set_enable(int cpu, bool enable); > extern int cppc_get_perf_caps(int cpu, struct cppc_perf_caps *caps); > extern bool cppc_perf_ctrs_in_pcc(void); > +extern unsigned int cppc_perf_to_khz(struct cppc_perf_caps *caps, unsigned int perf); > +extern unsigned int cppc_khz_to_perf(struct cppc_perf_caps *caps, unsigned int freq); > extern bool acpi_cpc_valid(void); > extern bool cppc_allow_fast_switch(void); > extern int acpi_get_psd_map(unsigned int cpu, struct cppc_cpudata *cpu_data); > -- > 2.34.1 >
This is the 1st part of consolidating how the max compute capacity is used in the scheduler and how we calculate the frequency for a level of utilization. Fix some unconsistancy when computing frequency for an utilization. There can be a mismatch between energy model and schedutil. Next step will be to make a difference between the original max compute capacity of a CPU and what is currently available when there is a capping applying forever (i.e. seconds or more). Changes since v4: - Capitalize the verb in subject - Remove usless parentheses in cppc_get_dmi_max_khz() - Use freq_ref pattern everywhere - Fix MHz / kHz units conversion for cppc_cpufreq - Move default definition of arch_scale_freq_ref() in include/linux/sched/topology.h beside arch_scale_cpu_capacity which faces similar default declaration behavior. This location covers all cases with arch and CONFIG_* which was not the case with previous attempts. Changes since v3: - Split patch 5 cpufreq/cppc - Fix topology_init_cpu_capacity_cppc() - Fix init if AMU ratio - Added some tags Changes since v2: - Remove the 1st patch which has been queued in tip - Rework how to initialize the reference frequency for cppc_cpufreq and change topology_init_cpu_capacity_cppc() to also set capacity_ref_freq - Add a RFC to convert AMU to use arch_scale_freq_ref and move the config of the AMU ratio to be done when intializing cpu capacity and capacity_ref_freq - Added some tags Changes since v1: - Fix typos - Added changes in cpufreq to use arch_scale_freq_ref() when calling arch_set_freq_scale (patch 3). - arch_scale_freq_ref() is always defined and returns 0 (as proposed by Ionela) when not defined by the arch. This simplifies the code with the addition of patch 3. - Simplify Energy Model which always uses arch_scale_freq_ref(). The latter returns 0 when not defined by arch instead of last item of the perf domain. This is not a problem because the function is only defined for compilation purpose in this case and we don't care about the returned value. (patch 5) - Added changes in cppc cpufreq to set capacity_ref_freq (patch 6) - Added reviewed tag for patch 1 which got a minor change but not for others as I did some changes which could make previous reviewed tag no more relevant. Vincent Guittot (7): topology: Add a new arch_scale_freq_reference cpufreq: Use the fixed and coherent frequency for scaling capacity cpufreq/schedutil: Use a fixed reference frequency energy_model: Use a fixed reference frequency cpufreq/cppc: Move and rename cppc_cpufreq_{perf_to_khz|khz_to_perf} cpufreq/cppc: Set the frequency used for computing the capacity arm64/amu: Use capacity_ref_freq to set AMU ratio arch/arm/include/asm/topology.h | 1 + arch/arm64/include/asm/topology.h | 1 + arch/arm64/kernel/topology.c | 26 +++--- arch/riscv/include/asm/topology.h | 1 + drivers/acpi/cppc_acpi.c | 104 ++++++++++++++++++++++ drivers/base/arch_topology.c | 56 ++++++++---- drivers/cpufreq/cppc_cpufreq.c | 139 ++++-------------------------- drivers/cpufreq/cpufreq.c | 4 +- include/acpi/cppc_acpi.h | 2 + include/linux/arch_topology.h | 8 ++ include/linux/cpufreq.h | 1 + include/linux/energy_model.h | 6 +- include/linux/sched/topology.h | 8 ++ kernel/sched/cpufreq_schedutil.c | 26 +++++- 14 files changed, 225 insertions(+), 158 deletions(-)