diff options
Diffstat (limited to 'drivers/cpufreq')
64 files changed, 3424 insertions, 1571 deletions
diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig index 35efb53d5492..d64b07ec48e5 100644 --- a/drivers/cpufreq/Kconfig +++ b/drivers/cpufreq/Kconfig @@ -217,8 +217,22 @@ config CPUFREQ_DT If in doubt, say N. +config CPUFREQ_VIRT + tristate "Virtual cpufreq driver" + depends on GENERIC_ARCH_TOPOLOGY + help + This adds a virtualized cpufreq driver for guest kernels that + read/writes to a MMIO region for a virtualized cpufreq device to + communicate with the host. It sends performance requests to the host + which gets used as a hint to schedule vCPU threads and select CPU + frequency. If a VM does not support a virtualized FIE such as AMUs, + it updates the frequency scaling factor by polling host CPU frequency + to enable accurate Per-Entity Load Tracking for tasks running in the guest. + + If in doubt, say N. + config CPUFREQ_DT_PLATDEV - tristate "Generic DT based cpufreq platdev driver" + bool "Generic DT based cpufreq platdev driver" depends on OF help This adds a generic DT based cpufreq platdev driver for frequency @@ -231,9 +245,7 @@ if X86 source "drivers/cpufreq/Kconfig.x86" endif -if ARM || ARM64 source "drivers/cpufreq/Kconfig.arm" -endif if PPC32 || PPC64 source "drivers/cpufreq/Kconfig.powerpc" @@ -262,6 +274,18 @@ config LOONGSON2_CPUFREQ If in doubt, say N. endif +if LOONGARCH +config LOONGSON3_CPUFREQ + tristate "Loongson3 CPUFreq Driver" + help + This option adds a CPUFreq driver for Loongson processors which + support software configurable cpu frequency. + + Loongson-3 family processors support this feature. + + If in doubt, say N. +endif + if SPARC64 config SPARC_US3_CPUFREQ tristate "UltraSPARC-III CPU Frequency driver" @@ -301,5 +325,34 @@ config QORIQ_CPUFREQ This adds the CPUFreq driver support for Freescale QorIQ SoCs which are capable of changing the CPU's frequency dynamically. +config ACPI_CPPC_CPUFREQ + tristate "CPUFreq driver based on the ACPI CPPC spec" + depends on ACPI_PROCESSOR + depends on ARM || ARM64 || RISCV + select ACPI_CPPC_LIB + help + This adds a CPUFreq driver which uses CPPC methods + as described in the ACPIv5.1 spec. CPPC stands for + Collaborative Processor Performance Controls. It + is based on an abstract continuous scale of CPU + performance values which allows the remote power + processor to flexibly optimize for power and + performance. CPPC relies on power management firmware + support for its operation. + + If in doubt, say N. + +config ACPI_CPPC_CPUFREQ_FIE + bool "Frequency Invariance support for CPPC cpufreq driver" + depends on ACPI_CPPC_CPUFREQ && GENERIC_ARCH_TOPOLOGY + depends on ARM || ARM64 || RISCV + default y + help + This extends frequency invariance support in the CPPC cpufreq driver, + by using CPPC delivered and reference performance counters. + + If in doubt, say N. + endif + endmenu diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm index f911606897b8..9e46960f6a86 100644 --- a/drivers/cpufreq/Kconfig.arm +++ b/drivers/cpufreq/Kconfig.arm @@ -3,35 +3,9 @@ # ARM CPU Frequency scaling drivers # -config ACPI_CPPC_CPUFREQ - tristate "CPUFreq driver based on the ACPI CPPC spec" - depends on ACPI_PROCESSOR - select ACPI_CPPC_LIB - help - This adds a CPUFreq driver which uses CPPC methods - as described in the ACPIv5.1 spec. CPPC stands for - Collaborative Processor Performance Controls. It - is based on an abstract continuous scale of CPU - performance values which allows the remote power - processor to flexibly optimize for power and - performance. CPPC relies on power management firmware - support for its operation. - - If in doubt, say N. - -config ACPI_CPPC_CPUFREQ_FIE - bool "Frequency Invariance support for CPPC cpufreq driver" - depends on ACPI_CPPC_CPUFREQ && GENERIC_ARCH_TOPOLOGY - default y - help - This extends frequency invariance support in the CPPC cpufreq driver, - by using CPPC delivered and reference performance counters. - - If in doubt, say N. - config ARM_ALLWINNER_SUN50I_CPUFREQ_NVMEM tristate "Allwinner nvmem based SUN50I CPUFreq driver" - depends on ARCH_SUNXI + depends on ARCH_SUNXI || COMPILE_TEST depends on NVMEM_SUNXI_SID select PM_OPP help @@ -41,6 +15,15 @@ config ARM_ALLWINNER_SUN50I_CPUFREQ_NVMEM To compile this driver as a module, choose M here: the module will be called sun50i-cpufreq-nvmem. +config ARM_AIROHA_SOC_CPUFREQ + tristate "Airoha EN7581 SoC CPUFreq support" + depends on ARCH_AIROHA || COMPILE_TEST + depends on OF + select PM_OPP + default ARCH_AIROHA + help + This adds the CPUFreq driver for Airoha EN7581 SoCs. + config ARM_APPLE_SOC_CPUFREQ tristate "Apple Silicon SoC CPUFreq support" depends on ARCH_APPLE || (COMPILE_TEST && 64BIT) @@ -52,15 +35,17 @@ config ARM_APPLE_SOC_CPUFREQ config ARM_ARMADA_37XX_CPUFREQ tristate "Armada 37xx CPUFreq support" - depends on ARCH_MVEBU && CPUFREQ_DT + depends on ARCH_MVEBU || COMPILE_TEST + depends on CPUFREQ_DT help This adds the CPUFreq driver support for Marvell Armada 37xx SoCs. The Armada 37xx PMU supports 4 frequency and VDD levels. config ARM_ARMADA_8K_CPUFREQ tristate "Armada 8K CPUFreq driver" - depends on ARCH_MVEBU && CPUFREQ_DT - select ARMADA_AP_CPU_CLK + depends on ARCH_MVEBU || COMPILE_TEST + depends on CPUFREQ_DT + select ARMADA_AP_CPU_CLK if COMMON_CLK help This enables the CPUFreq driver support for Marvell Armada8k SOCs. @@ -82,7 +67,7 @@ config ARM_SCPI_CPUFREQ config ARM_VEXPRESS_SPC_CPUFREQ tristate "Versatile Express SPC based CPUfreq driver" depends on ARM_CPU_TOPOLOGY && HAVE_CLK - depends on ARCH_VEXPRESS_SPC + depends on ARCH_VEXPRESS_SPC || COMPILE_TEST select PM_OPP help This add the CPUfreq driver support for Versatile Express @@ -101,7 +86,8 @@ config ARM_BRCMSTB_AVS_CPUFREQ config ARM_HIGHBANK_CPUFREQ tristate "Calxeda Highbank-based" - depends on ARCH_HIGHBANK && CPUFREQ_DT && REGULATOR + depends on ARCH_HIGHBANK || COMPILE_TEST + depends on CPUFREQ_DT && REGULATOR && PL320_MBOX default m help This adds the CPUFreq driver for Calxeda Highbank SoC @@ -122,7 +108,8 @@ config ARM_IMX6Q_CPUFREQ config ARM_IMX_CPUFREQ_DT tristate "Freescale i.MX8M cpufreq support" - depends on ARCH_MXC && CPUFREQ_DT + depends on CPUFREQ_DT + depends on ARCH_MXC || COMPILE_TEST help This adds cpufreq driver support for Freescale i.MX7/i.MX8M series SoCs, based on cpufreq-dt. @@ -137,7 +124,8 @@ config ARM_KIRKWOOD_CPUFREQ config ARM_MEDIATEK_CPUFREQ tristate "CPU Frequency scaling support for MediaTek SoCs" - depends on ARCH_MEDIATEK && REGULATOR + depends on ARCH_MEDIATEK || COMPILE_TEST + depends on REGULATOR select PM_OPP help This adds the CPUFreq driver support for MediaTek SoCs. @@ -156,12 +144,12 @@ config ARM_MEDIATEK_CPUFREQ_HW config ARM_OMAP2PLUS_CPUFREQ bool "TI OMAP2+" - depends on ARCH_OMAP2PLUS + depends on ARCH_OMAP2PLUS || COMPILE_TEST default ARCH_OMAP2PLUS config ARM_QCOM_CPUFREQ_NVMEM tristate "Qualcomm nvmem based CPUFreq" - depends on ARCH_QCOM + depends on ARCH_QCOM || COMPILE_TEST depends on NVMEM_QCOM_QFPROM depends on QCOM_SMEM select PM_OPP @@ -173,6 +161,7 @@ config ARM_QCOM_CPUFREQ_NVMEM config ARM_QCOM_CPUFREQ_HW tristate "QCOM CPUFreq HW driver" depends on ARCH_QCOM || COMPILE_TEST + depends on COMMON_CLK help Support for the CPUFreq HW driver. Some QCOM chipsets have a HW engine to offload the steps @@ -191,7 +180,7 @@ config ARM_RASPBERRYPI_CPUFREQ config ARM_S3C64XX_CPUFREQ bool "Samsung S3C64XX" - depends on CPU_S3C6410 + depends on CPU_S3C6410 || COMPILE_TEST default y help This adds the CPUFreq driver for Samsung S3C6410 SoC. @@ -200,7 +189,7 @@ config ARM_S3C64XX_CPUFREQ config ARM_S5PV210_CPUFREQ bool "Samsung S5PV210 and S5PC110" - depends on CPU_S5PV210 + depends on CPU_S5PV210 || COMPILE_TEST default y help This adds the CPUFreq driver for Samsung S5PV210 and @@ -224,14 +213,15 @@ config ARM_SCMI_CPUFREQ config ARM_SPEAR_CPUFREQ bool "SPEAr CPUFreq support" - depends on PLAT_SPEAR + depends on PLAT_SPEAR || COMPILE_TEST default y help This adds the CPUFreq driver support for SPEAr SOCs. config ARM_STI_CPUFREQ tristate "STi CPUFreq support" - depends on CPUFREQ_DT && SOC_STIH407 + depends on CPUFREQ_DT + depends on SOC_STIH407 || COMPILE_TEST help This driver uses the generic OPP framework to match the running platform with a predefined set of suitable values. If not provided @@ -241,34 +231,38 @@ config ARM_STI_CPUFREQ config ARM_TEGRA20_CPUFREQ tristate "Tegra20/30 CPUFreq support" - depends on ARCH_TEGRA && CPUFREQ_DT + depends on ARCH_TEGRA || COMPILE_TEST + depends on CPUFREQ_DT default y help This adds the CPUFreq driver support for Tegra20/30 SOCs. config ARM_TEGRA124_CPUFREQ bool "Tegra124 CPUFreq support" - depends on ARCH_TEGRA && CPUFREQ_DT + depends on ARCH_TEGRA || COMPILE_TEST + depends on CPUFREQ_DT default y help This adds the CPUFreq driver support for Tegra124 SOCs. config ARM_TEGRA186_CPUFREQ tristate "Tegra186 CPUFreq support" - depends on ARCH_TEGRA && TEGRA_BPMP + depends on ARCH_TEGRA || COMPILE_TEST + depends on TEGRA_BPMP help This adds the CPUFreq driver support for Tegra186 SOCs. config ARM_TEGRA194_CPUFREQ tristate "Tegra194 CPUFreq support" - depends on ARCH_TEGRA_194_SOC && TEGRA_BPMP + depends on ARCH_TEGRA_194_SOC || (64BIT && COMPILE_TEST) + depends on TEGRA_BPMP default y help This adds CPU frequency driver support for Tegra194 SOCs. config ARM_TI_CPUFREQ bool "Texas Instruments CPUFreq support" - depends on ARCH_OMAP2PLUS || ARCH_K3 + depends on ARCH_OMAP2PLUS || ARCH_K3 || COMPILE_TEST default y help This driver enables valid OPPs on the running platform based on @@ -280,7 +274,7 @@ config ARM_TI_CPUFREQ config ARM_PXA2xx_CPUFREQ tristate "Intel PXA2xx CPUfreq driver" - depends on PXA27x || PXA25x + depends on PXA27x || PXA25x || COMPILE_TEST help This add the CPUFreq driver support for Intel PXA2xx SOCs. diff --git a/drivers/cpufreq/Kconfig.powerpc b/drivers/cpufreq/Kconfig.powerpc index 58151ca56695..eb678fa5260a 100644 --- a/drivers/cpufreq/Kconfig.powerpc +++ b/drivers/cpufreq/Kconfig.powerpc @@ -17,13 +17,6 @@ config CPU_FREQ_CBE_PMI frequencies. Using PMI, the processor will not only be able to run at lower speed, but also at lower core voltage. -config CPU_FREQ_MAPLE - bool "Support for Maple 970FX Evaluation Board" - depends on PPC_MAPLE - help - This adds support for frequency switching on Maple 970FX - Evaluation Board and compatible boards (IBM JS2x blades). - config CPU_FREQ_PMAC bool "Support for Apple PowerBooks" depends on ADB_PMU && PPC32 diff --git a/drivers/cpufreq/Kconfig.x86 b/drivers/cpufreq/Kconfig.x86 index 438c9e75a04d..97c2d4f15d76 100644 --- a/drivers/cpufreq/Kconfig.x86 +++ b/drivers/cpufreq/Kconfig.x86 @@ -71,6 +71,7 @@ config X86_AMD_PSTATE_DEFAULT_MODE config X86_AMD_PSTATE_UT tristate "selftest for AMD Processor P-State driver" depends on X86 && ACPI_PROCESSOR + depends on X86_AMD_PSTATE default n help This kernel module is used for testing. It's safe to say M here. diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile index 8d141c71b016..890fff99f37d 100644 --- a/drivers/cpufreq/Makefile +++ b/drivers/cpufreq/Makefile @@ -16,6 +16,7 @@ obj-$(CONFIG_CPU_FREQ_GOV_ATTR_SET) += cpufreq_governor_attr_set.o obj-$(CONFIG_CPUFREQ_DT) += cpufreq-dt.o obj-$(CONFIG_CPUFREQ_DT_PLATDEV) += cpufreq-dt-platdev.o +obj-$(CONFIG_CPUFREQ_VIRT) += virtual-cpufreq.o # Traces CFLAGS_amd-pstate-trace.o := -I$(src) @@ -52,6 +53,7 @@ obj-$(CONFIG_X86_AMD_FREQ_SENSITIVITY) += amd_freq_sensitivity.o ################################################################################## # ARM SoC drivers +obj-$(CONFIG_ARM_AIROHA_SOC_CPUFREQ) += airoha-cpufreq.o obj-$(CONFIG_ARM_APPLE_SOC_CPUFREQ) += apple-soc-cpufreq.o obj-$(CONFIG_ARM_ARMADA_37XX_CPUFREQ) += armada-37xx-cpufreq.o obj-$(CONFIG_ARM_ARMADA_8K_CPUFREQ) += armada-8k-cpufreq.o @@ -92,7 +94,6 @@ obj-$(CONFIG_ARM_VEXPRESS_SPC_CPUFREQ) += vexpress-spc-cpufreq.o obj-$(CONFIG_CPU_FREQ_CBE) += ppc-cbe-cpufreq.o ppc-cbe-cpufreq-y += ppc_cbe_cpufreq_pervasive.o ppc_cbe_cpufreq.o obj-$(CONFIG_CPU_FREQ_CBE_PMI) += ppc_cbe_cpufreq_pmi.o -obj-$(CONFIG_CPU_FREQ_MAPLE) += maple-cpufreq.o obj-$(CONFIG_QORIQ_CPUFREQ) += qoriq-cpufreq.o obj-$(CONFIG_CPU_FREQ_PMAC) += pmac32-cpufreq.o obj-$(CONFIG_CPU_FREQ_PMAC64) += pmac64-cpufreq.o @@ -103,6 +104,7 @@ obj-$(CONFIG_POWERNV_CPUFREQ) += powernv-cpufreq.o # Other platform drivers obj-$(CONFIG_BMIPS_CPUFREQ) += bmips-cpufreq.o obj-$(CONFIG_LOONGSON2_CPUFREQ) += loongson2_cpufreq.o +obj-$(CONFIG_LOONGSON3_CPUFREQ) += loongson3_cpufreq.o obj-$(CONFIG_SH_CPU_FREQ) += sh-cpufreq.o obj-$(CONFIG_SPARC_US2E_CPUFREQ) += sparc-us2e-cpufreq.o obj-$(CONFIG_SPARC_US3_CPUFREQ) += sparc-us3-cpufreq.o diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c index 37f1cdf46d29..463b69a2dff5 100644 --- a/drivers/cpufreq/acpi-cpufreq.c +++ b/drivers/cpufreq/acpi-cpufreq.c @@ -50,8 +50,6 @@ enum { #define AMD_MSR_RANGE (0x7) #define HYGON_MSR_RANGE (0x7) -#define MSR_K7_HWCR_CPB_DIS (1ULL << 25) - struct acpi_cpufreq_data { unsigned int resume; unsigned int cpu_feature; @@ -75,20 +73,17 @@ static unsigned int acpi_pstate_strict; static bool boost_state(unsigned int cpu) { - u32 lo, hi; u64 msr; switch (boot_cpu_data.x86_vendor) { case X86_VENDOR_INTEL: case X86_VENDOR_CENTAUR: case X86_VENDOR_ZHAOXIN: - rdmsr_on_cpu(cpu, MSR_IA32_MISC_ENABLE, &lo, &hi); - msr = lo | ((u64)hi << 32); + rdmsrl_on_cpu(cpu, MSR_IA32_MISC_ENABLE, &msr); return !(msr & MSR_IA32_MISC_ENABLE_TURBO_DISABLE); case X86_VENDOR_HYGON: case X86_VENDOR_AMD: - rdmsr_on_cpu(cpu, MSR_K7_HWCR, &lo, &hi); - msr = lo | ((u64)hi << 32); + rdmsrl_on_cpu(cpu, MSR_K7_HWCR, &msr); return !(msr & MSR_K7_HWCR_CPB_DIS); } return false; @@ -628,7 +623,14 @@ static int acpi_cpufreq_blacklist(struct cpuinfo_x86 *c) #endif #ifdef CONFIG_ACPI_CPPC_LIB -static u64 get_max_boost_ratio(unsigned int cpu) +/* + * get_max_boost_ratio: Computes the max_boost_ratio as the ratio + * between the highest_perf and the nominal_perf. + * + * Returns the max_boost_ratio for @cpu. Returns the CPPC nominal + * frequency via @nominal_freq if it is non-NULL pointer. + */ +static u64 get_max_boost_ratio(unsigned int cpu, u64 *nominal_freq) { struct cppc_perf_caps perf_caps; u64 highest_perf, nominal_perf; @@ -644,13 +646,22 @@ static u64 get_max_boost_ratio(unsigned int cpu) return 0; } - if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) - highest_perf = amd_get_highest_perf(); - else + if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) { + ret = amd_get_boost_ratio_numerator(cpu, &highest_perf); + if (ret) { + pr_debug("CPU%d: Unable to get boost ratio numerator (%d)\n", + cpu, ret); + return 0; + } + } else { highest_perf = perf_caps.highest_perf; + } nominal_perf = perf_caps.nominal_perf; + if (nominal_freq) + *nominal_freq = perf_caps.nominal_freq; + if (!highest_perf || !nominal_perf) { pr_debug("CPU%d: highest or nominal performance missing\n", cpu); return 0; @@ -663,8 +674,12 @@ static u64 get_max_boost_ratio(unsigned int cpu) return div_u64(highest_perf << SCHED_CAPACITY_SHIFT, nominal_perf); } + #else -static inline u64 get_max_boost_ratio(unsigned int cpu) { return 0; } +static inline u64 get_max_boost_ratio(unsigned int cpu, u64 *nominal_freq) +{ + return 0; +} #endif static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy) @@ -674,9 +689,9 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy) struct acpi_cpufreq_data *data; unsigned int cpu = policy->cpu; struct cpuinfo_x86 *c = &cpu_data(cpu); + u64 max_boost_ratio, nominal_freq = 0; unsigned int valid_states = 0; unsigned int result = 0; - u64 max_boost_ratio; unsigned int i; #ifdef CONFIG_SMP static int blacklisted; @@ -826,16 +841,20 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy) } freq_table[valid_states].frequency = CPUFREQ_TABLE_END; - max_boost_ratio = get_max_boost_ratio(cpu); + max_boost_ratio = get_max_boost_ratio(cpu, &nominal_freq); if (max_boost_ratio) { - unsigned int freq = freq_table[0].frequency; + unsigned int freq = nominal_freq; /* - * Because the loop above sorts the freq_table entries in the - * descending order, freq is the maximum frequency in the table. - * Assume that it corresponds to the CPPC nominal frequency and - * use it to set cpuinfo.max_freq. + * The loop above sorts the freq_table entries in the + * descending order. If ACPI CPPC has not advertised + * the nominal frequency (this is possible in CPPC + * revisions prior to 3), then use the first entry in + * the pstate table as a proxy for nominal frequency. */ + if (!freq) + freq = freq_table[0].frequency; + policy->cpuinfo.max_freq = freq * max_boost_ratio >> SCHED_CAPACITY_SHIFT; } else { /* @@ -890,9 +909,6 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy) if (perf->states[0].core_frequency * 1000 != freq_table[0].frequency) pr_warn(FW_WARN "P-state 0 is not max freq\n"); - if (acpi_cpufreq_driver.set_boost) - set_boost(policy, acpi_cpufreq_driver.boost_enabled); - return result; err_unreg: @@ -906,7 +922,7 @@ err_free: return result; } -static int acpi_cpufreq_cpu_exit(struct cpufreq_policy *policy) +static void acpi_cpufreq_cpu_exit(struct cpufreq_policy *policy) { struct acpi_cpufreq_data *data = policy->driver_data; @@ -919,8 +935,6 @@ static int acpi_cpufreq_cpu_exit(struct cpufreq_policy *policy) free_cpumask_var(data->freqdomain_cpus); kfree(policy->freq_table); kfree(data); - - return 0; } static int acpi_cpufreq_resume(struct cpufreq_policy *policy) @@ -1024,7 +1038,7 @@ static struct platform_driver acpi_cpufreq_platdrv = { .driver = { .name = "acpi-cpufreq", }, - .remove_new = acpi_cpufreq_remove, + .remove = acpi_cpufreq_remove, }; static int __init acpi_cpufreq_init(void) diff --git a/drivers/cpufreq/airoha-cpufreq.c b/drivers/cpufreq/airoha-cpufreq.c new file mode 100644 index 000000000000..4fe39eadd163 --- /dev/null +++ b/drivers/cpufreq/airoha-cpufreq.c @@ -0,0 +1,152 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bitfield.h> +#include <linux/cpufreq.h> +#include <linux/module.h> +#include <linux/platform_device.h> +#include <linux/pm_domain.h> +#include <linux/pm_runtime.h> +#include <linux/slab.h> + +#include "cpufreq-dt.h" + +struct airoha_cpufreq_priv { + int opp_token; + struct dev_pm_domain_list *pd_list; + struct platform_device *cpufreq_dt; +}; + +static struct platform_device *cpufreq_pdev; + +/* NOP function to disable OPP from setting clock */ +static int airoha_cpufreq_config_clks_nop(struct device *dev, + struct opp_table *opp_table, + struct dev_pm_opp *opp, + void *data, bool scaling_down) +{ + return 0; +} + +static const char * const airoha_cpufreq_clk_names[] = { "cpu", NULL }; +static const char * const airoha_cpufreq_pd_names[] = { "perf" }; + +static int airoha_cpufreq_probe(struct platform_device *pdev) +{ + const struct dev_pm_domain_attach_data attach_data = { + .pd_names = airoha_cpufreq_pd_names, + .num_pd_names = ARRAY_SIZE(airoha_cpufreq_pd_names), + .pd_flags = PD_FLAG_DEV_LINK_ON | PD_FLAG_REQUIRED_OPP, + }; + struct dev_pm_opp_config config = { + .clk_names = airoha_cpufreq_clk_names, + .config_clks = airoha_cpufreq_config_clks_nop, + }; + struct platform_device *cpufreq_dt; + struct airoha_cpufreq_priv *priv; + struct device *dev = &pdev->dev; + struct device *cpu_dev; + int ret; + + /* CPUs refer to the same OPP table */ + cpu_dev = get_cpu_device(0); + if (!cpu_dev) + return -ENODEV; + + priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + /* Set OPP table conf with NOP config_clks */ + priv->opp_token = dev_pm_opp_set_config(cpu_dev, &config); + if (priv->opp_token < 0) + return dev_err_probe(dev, priv->opp_token, "Failed to set OPP config\n"); + + /* Attach PM for OPP */ + ret = dev_pm_domain_attach_list(cpu_dev, &attach_data, + &priv->pd_list); + if (ret) + goto clear_opp_config; + + cpufreq_dt = platform_device_register_simple("cpufreq-dt", -1, NULL, 0); + ret = PTR_ERR_OR_ZERO(cpufreq_dt); + if (ret) { + dev_err(dev, "failed to create cpufreq-dt device: %d\n", ret); + goto detach_pm; + } + + priv->cpufreq_dt = cpufreq_dt; + platform_set_drvdata(pdev, priv); + + return 0; + +detach_pm: + dev_pm_domain_detach_list(priv->pd_list); +clear_opp_config: + dev_pm_opp_clear_config(priv->opp_token); + + return ret; +} + +static void airoha_cpufreq_remove(struct platform_device *pdev) +{ + struct airoha_cpufreq_priv *priv = platform_get_drvdata(pdev); + + platform_device_unregister(priv->cpufreq_dt); + + dev_pm_domain_detach_list(priv->pd_list); + + dev_pm_opp_clear_config(priv->opp_token); +} + +static struct platform_driver airoha_cpufreq_driver = { + .probe = airoha_cpufreq_probe, + .remove = airoha_cpufreq_remove, + .driver = { + .name = "airoha-cpufreq", + }, +}; + +static const struct of_device_id airoha_cpufreq_match_list[] __initconst = { + { .compatible = "airoha,en7581" }, + {}, +}; +MODULE_DEVICE_TABLE(of, airoha_cpufreq_match_list); + +static int __init airoha_cpufreq_init(void) +{ + struct device_node *np = of_find_node_by_path("/"); + const struct of_device_id *match; + int ret; + + if (!np) + return -ENODEV; + + match = of_match_node(airoha_cpufreq_match_list, np); + of_node_put(np); + if (!match) + return -ENODEV; + + ret = platform_driver_register(&airoha_cpufreq_driver); + if (unlikely(ret < 0)) + return ret; + + cpufreq_pdev = platform_device_register_data(NULL, "airoha-cpufreq", + -1, match, sizeof(*match)); + ret = PTR_ERR_OR_ZERO(cpufreq_pdev); + if (ret) + platform_driver_unregister(&airoha_cpufreq_driver); + + return ret; +} +module_init(airoha_cpufreq_init); + +static void __exit airoha_cpufreq_exit(void) +{ + platform_device_unregister(cpufreq_pdev); + platform_driver_unregister(&airoha_cpufreq_driver); +} +module_exit(airoha_cpufreq_exit); + +MODULE_AUTHOR("Christian Marangi <ansuelsmth@gmail.com>"); +MODULE_DESCRIPTION("CPUfreq driver for Airoha SoCs"); +MODULE_LICENSE("GPL"); diff --git a/drivers/cpufreq/amd-pstate-trace.h b/drivers/cpufreq/amd-pstate-trace.h index 35f38ae67fb1..8d692415d905 100644 --- a/drivers/cpufreq/amd-pstate-trace.h +++ b/drivers/cpufreq/amd-pstate-trace.h @@ -32,7 +32,6 @@ TRACE_EVENT(amd_pstate_perf, u64 aperf, u64 tsc, unsigned int cpu_id, - bool changed, bool fast_switch ), @@ -44,7 +43,6 @@ TRACE_EVENT(amd_pstate_perf, aperf, tsc, cpu_id, - changed, fast_switch ), @@ -57,7 +55,6 @@ TRACE_EVENT(amd_pstate_perf, __field(unsigned long long, aperf) __field(unsigned long long, tsc) __field(unsigned int, cpu_id) - __field(bool, changed) __field(bool, fast_switch) ), @@ -70,11 +67,10 @@ TRACE_EVENT(amd_pstate_perf, __entry->aperf = aperf; __entry->tsc = tsc; __entry->cpu_id = cpu_id; - __entry->changed = changed; __entry->fast_switch = fast_switch; ), - TP_printk("amd_min_perf=%lu amd_des_perf=%lu amd_max_perf=%lu freq=%llu mperf=%llu aperf=%llu tsc=%llu cpu_id=%u changed=%s fast_switch=%s", + TP_printk("amd_min_perf=%lu amd_des_perf=%lu amd_max_perf=%lu freq=%llu mperf=%llu aperf=%llu tsc=%llu cpu_id=%u fast_switch=%s", (unsigned long)__entry->min_perf, (unsigned long)__entry->target_perf, (unsigned long)__entry->capacity, @@ -83,11 +79,55 @@ TRACE_EVENT(amd_pstate_perf, (unsigned long long)__entry->aperf, (unsigned long long)__entry->tsc, (unsigned int)__entry->cpu_id, - (__entry->changed) ? "true" : "false", (__entry->fast_switch) ? "true" : "false" ) ); +TRACE_EVENT(amd_pstate_epp_perf, + + TP_PROTO(unsigned int cpu_id, + unsigned int highest_perf, + unsigned int epp, + unsigned int min_perf, + unsigned int max_perf, + bool boost + ), + + TP_ARGS(cpu_id, + highest_perf, + epp, + min_perf, + max_perf, + boost), + + TP_STRUCT__entry( + __field(unsigned int, cpu_id) + __field(unsigned int, highest_perf) + __field(unsigned int, epp) + __field(unsigned int, min_perf) + __field(unsigned int, max_perf) + __field(bool, boost) + ), + + TP_fast_assign( + __entry->cpu_id = cpu_id; + __entry->highest_perf = highest_perf; + __entry->epp = epp; + __entry->min_perf = min_perf; + __entry->max_perf = max_perf; + __entry->boost = boost; + ), + + TP_printk("cpu%u: [%u<->%u]/%u, epp=%u, boost=%u", + (unsigned int)__entry->cpu_id, + (unsigned int)__entry->min_perf, + (unsigned int)__entry->max_perf, + (unsigned int)__entry->highest_perf, + (unsigned int)__entry->epp, + (bool)__entry->boost + ) +); + #endif /* _AMD_PSTATE_TRACE_H */ /* This part must be outside protection */ diff --git a/drivers/cpufreq/amd-pstate-ut.c b/drivers/cpufreq/amd-pstate-ut.c index f04ae67dda37..3a0a380c3590 100644 --- a/drivers/cpufreq/amd-pstate-ut.c +++ b/drivers/cpufreq/amd-pstate-ut.c @@ -26,10 +26,11 @@ #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/fs.h> -#include <linux/amd-pstate.h> #include <acpi/cppc_acpi.h> +#include "amd-pstate.h" + /* * Abbreviations: * amd_pstate_ut: used as a shortform for AMD P-State unit test. @@ -53,12 +54,14 @@ static void amd_pstate_ut_acpi_cpc_valid(u32 index); static void amd_pstate_ut_check_enabled(u32 index); static void amd_pstate_ut_check_perf(u32 index); static void amd_pstate_ut_check_freq(u32 index); +static void amd_pstate_ut_check_driver(u32 index); static struct amd_pstate_ut_struct amd_pstate_ut_cases[] = { {"amd_pstate_ut_acpi_cpc_valid", amd_pstate_ut_acpi_cpc_valid }, {"amd_pstate_ut_check_enabled", amd_pstate_ut_check_enabled }, {"amd_pstate_ut_check_perf", amd_pstate_ut_check_perf }, - {"amd_pstate_ut_check_freq", amd_pstate_ut_check_freq } + {"amd_pstate_ut_check_freq", amd_pstate_ut_check_freq }, + {"amd_pstate_ut_check_driver", amd_pstate_ut_check_driver } }; static bool get_shared_mem(void) @@ -159,14 +162,17 @@ static void amd_pstate_ut_check_perf(u32 index) lowest_perf = AMD_CPPC_LOWEST_PERF(cap1); } - if ((highest_perf != READ_ONCE(cpudata->highest_perf)) || - (nominal_perf != READ_ONCE(cpudata->nominal_perf)) || + if (highest_perf != READ_ONCE(cpudata->highest_perf) && !cpudata->hw_prefcore) { + pr_err("%s cpu%d highest=%d %d highest perf doesn't match\n", + __func__, cpu, highest_perf, cpudata->highest_perf); + goto skip_test; + } + if ((nominal_perf != READ_ONCE(cpudata->nominal_perf)) || (lowest_nonlinear_perf != READ_ONCE(cpudata->lowest_nonlinear_perf)) || (lowest_perf != READ_ONCE(cpudata->lowest_perf))) { amd_pstate_ut_cases[index].result = AMD_PSTATE_UT_RESULT_FAIL; - pr_err("%s cpu%d highest=%d %d nominal=%d %d lowest_nonlinear=%d %d lowest=%d %d, they should be equal!\n", - __func__, cpu, highest_perf, cpudata->highest_perf, - nominal_perf, cpudata->nominal_perf, + pr_err("%s cpu%d nominal=%d %d lowest_nonlinear=%d %d lowest=%d %d, they should be equal!\n", + __func__, cpu, nominal_perf, cpudata->nominal_perf, lowest_nonlinear_perf, cpudata->lowest_nonlinear_perf, lowest_perf, cpudata->lowest_perf); goto skip_test; @@ -219,10 +225,10 @@ static void amd_pstate_ut_check_freq(u32 index) goto skip_test; } - if (cpudata->min_freq != policy->min) { + if (cpudata->lowest_nonlinear_freq != policy->min) { amd_pstate_ut_cases[index].result = AMD_PSTATE_UT_RESULT_FAIL; - pr_err("%s cpu%d cpudata_min_freq=%d policy_min=%d, they should be equal!\n", - __func__, cpu, cpudata->min_freq, policy->min); + pr_err("%s cpu%d cpudata_lowest_nonlinear_freq=%d policy_min=%d, they should be equal!\n", + __func__, cpu, cpudata->lowest_nonlinear_freq, policy->min); goto skip_test; } @@ -251,6 +257,43 @@ skip_test: cpufreq_cpu_put(policy); } +static int amd_pstate_set_mode(enum amd_pstate_mode mode) +{ + const char *mode_str = amd_pstate_get_mode_string(mode); + + pr_debug("->setting mode to %s\n", mode_str); + + return amd_pstate_update_status(mode_str, strlen(mode_str)); +} + +static void amd_pstate_ut_check_driver(u32 index) +{ + enum amd_pstate_mode mode1, mode2 = AMD_PSTATE_DISABLE; + int ret; + + for (mode1 = AMD_PSTATE_DISABLE; mode1 < AMD_PSTATE_MAX; mode1++) { + ret = amd_pstate_set_mode(mode1); + if (ret) + goto out; + for (mode2 = AMD_PSTATE_DISABLE; mode2 < AMD_PSTATE_MAX; mode2++) { + if (mode1 == mode2) + continue; + ret = amd_pstate_set_mode(mode2); + if (ret) + goto out; + } + } +out: + if (ret) + pr_warn("%s: failed to update status for %s->%s: %d\n", __func__, + amd_pstate_get_mode_string(mode1), + amd_pstate_get_mode_string(mode2), ret); + + amd_pstate_ut_cases[index].result = ret ? + AMD_PSTATE_UT_RESULT_FAIL : + AMD_PSTATE_UT_RESULT_PASS; +} + static int __init amd_pstate_ut_init(void) { u32 i = 0, arr_size = ARRAY_SIZE(amd_pstate_ut_cases); diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index 1791d37fbc53..313550fa62d4 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -22,6 +22,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/bitfield.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/init.h> @@ -36,7 +37,7 @@ #include <linux/delay.h> #include <linux/uaccess.h> #include <linux/static_call.h> -#include <linux/amd-pstate.h> +#include <linux/topology.h> #include <acpi/processor.h> #include <acpi/cppc_acpi.h> @@ -45,25 +46,53 @@ #include <asm/processor.h> #include <asm/cpufeature.h> #include <asm/cpu_device_id.h> + +#include "amd-pstate.h" #include "amd-pstate-trace.h" #define AMD_PSTATE_TRANSITION_LATENCY 20000 #define AMD_PSTATE_TRANSITION_DELAY 1000 +#define AMD_PSTATE_FAST_CPPC_TRANSITION_DELAY 600 + +#define AMD_CPPC_EPP_PERFORMANCE 0x00 +#define AMD_CPPC_EPP_BALANCE_PERFORMANCE 0x80 +#define AMD_CPPC_EPP_BALANCE_POWERSAVE 0xBF +#define AMD_CPPC_EPP_POWERSAVE 0xFF + +static const char * const amd_pstate_mode_string[] = { + [AMD_PSTATE_UNDEFINED] = "undefined", + [AMD_PSTATE_DISABLE] = "disable", + [AMD_PSTATE_PASSIVE] = "passive", + [AMD_PSTATE_ACTIVE] = "active", + [AMD_PSTATE_GUIDED] = "guided", + NULL, +}; + +const char *amd_pstate_get_mode_string(enum amd_pstate_mode mode) +{ + if (mode < 0 || mode >= AMD_PSTATE_MAX) + return NULL; + return amd_pstate_mode_string[mode]; +} +EXPORT_SYMBOL_GPL(amd_pstate_get_mode_string); + +struct quirk_entry { + u32 nominal_freq; + u32 lowest_freq; +}; -/* - * TODO: We need more time to fine tune processors with shared memory solution - * with community together. - * - * There are some performance drops on the CPU benchmarks which reports from - * Suse. We are co-working with them to fine tune the shared memory solution. So - * we disable it by default to go acpi-cpufreq on these processors and add a - * module parameter to be able to enable it manually for debugging. - */ static struct cpufreq_driver *current_pstate_driver; static struct cpufreq_driver amd_pstate_driver; static struct cpufreq_driver amd_pstate_epp_driver; static int cppc_state = AMD_PSTATE_UNDEFINED; static bool cppc_enabled; +static bool amd_pstate_prefcore = true; +static struct quirk_entry *quirks; + +#define AMD_CPPC_MAX_PERF_MASK GENMASK(7, 0) +#define AMD_CPPC_MIN_PERF_MASK GENMASK(15, 8) +#define AMD_CPPC_DES_PERF_MASK GENMASK(23, 16) +#define AMD_CPPC_EPP_PERF_MASK GENMASK(31, 24) /* * AMD Energy Preference Performance (EPP) @@ -108,6 +137,41 @@ static unsigned int epp_values[] = { typedef int (*cppc_mode_transition_fn)(int); +static struct quirk_entry quirk_amd_7k62 = { + .nominal_freq = 2600, + .lowest_freq = 550, +}; + +static int __init dmi_matched_7k62_bios_bug(const struct dmi_system_id *dmi) +{ + /** + * match the broken bios for family 17h processor support CPPC V2 + * broken BIOS lack of nominal_freq and lowest_freq capabilities + * definition in ACPI tables + */ + if (cpu_feature_enabled(X86_FEATURE_ZEN2)) { + quirks = dmi->driver_data; + pr_info("Overriding nominal and lowest frequencies for %s\n", dmi->ident); + return 1; + } + + return 0; +} + +static const struct dmi_system_id amd_pstate_quirks_table[] __initconst = { + { + .callback = dmi_matched_7k62_bios_bug, + .ident = "AMD EPYC 7K62", + .matches = { + DMI_MATCH(DMI_BIOS_VERSION, "5.14"), + DMI_MATCH(DMI_BIOS_RELEASE, "12/12/2019"), + }, + .driver_data = &quirk_amd_7k62, + }, + {} +}; +MODULE_DEVICE_TABLE(dmi, amd_pstate_quirks_table); + static inline int get_mode_idx_from_str(const char *str, size_t size) { int i; @@ -122,99 +186,145 @@ static inline int get_mode_idx_from_str(const char *str, size_t size) static DEFINE_MUTEX(amd_pstate_limits_lock); static DEFINE_MUTEX(amd_pstate_driver_lock); -static s16 amd_pstate_get_epp(struct amd_cpudata *cpudata, u64 cppc_req_cached) +static s16 msr_get_epp(struct amd_cpudata *cpudata) +{ + u64 value; + int ret; + + ret = rdmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, &value); + if (ret < 0) { + pr_debug("Could not retrieve energy perf value (%d)\n", ret); + return ret; + } + + return FIELD_GET(AMD_CPPC_EPP_PERF_MASK, value); +} + +DEFINE_STATIC_CALL(amd_pstate_get_epp, msr_get_epp); + +static inline s16 amd_pstate_get_epp(struct amd_cpudata *cpudata) +{ + return static_call(amd_pstate_get_epp)(cpudata); +} + +static s16 shmem_get_epp(struct amd_cpudata *cpudata) { u64 epp; int ret; - if (boot_cpu_has(X86_FEATURE_CPPC)) { - if (!cppc_req_cached) { - epp = rdmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, - &cppc_req_cached); - if (epp) - return epp; - } - epp = (cppc_req_cached >> 24) & 0xFF; - } else { - ret = cppc_get_epp_perf(cpudata->cpu, &epp); - if (ret < 0) { - pr_debug("Could not retrieve energy perf value (%d)\n", ret); - return -EIO; - } + ret = cppc_get_epp_perf(cpudata->cpu, &epp); + if (ret < 0) { + pr_debug("Could not retrieve energy perf value (%d)\n", ret); + return ret; } return (s16)(epp & 0xff); } -static int amd_pstate_get_energy_pref_index(struct amd_cpudata *cpudata) +static int msr_update_perf(struct amd_cpudata *cpudata, u32 min_perf, + u32 des_perf, u32 max_perf, u32 epp, bool fast_switch) { - s16 epp; - int index = -EINVAL; + u64 value, prev; - epp = amd_pstate_get_epp(cpudata, 0); - if (epp < 0) - return epp; + value = prev = READ_ONCE(cpudata->cppc_req_cached); - switch (epp) { - case AMD_CPPC_EPP_PERFORMANCE: - index = EPP_INDEX_PERFORMANCE; - break; - case AMD_CPPC_EPP_BALANCE_PERFORMANCE: - index = EPP_INDEX_BALANCE_PERFORMANCE; - break; - case AMD_CPPC_EPP_BALANCE_POWERSAVE: - index = EPP_INDEX_BALANCE_POWERSAVE; - break; - case AMD_CPPC_EPP_POWERSAVE: - index = EPP_INDEX_POWERSAVE; - break; - default: - break; + value &= ~(AMD_CPPC_MAX_PERF_MASK | AMD_CPPC_MIN_PERF_MASK | + AMD_CPPC_DES_PERF_MASK | AMD_CPPC_EPP_PERF_MASK); + value |= FIELD_PREP(AMD_CPPC_MAX_PERF_MASK, max_perf); + value |= FIELD_PREP(AMD_CPPC_DES_PERF_MASK, des_perf); + value |= FIELD_PREP(AMD_CPPC_MIN_PERF_MASK, min_perf); + value |= FIELD_PREP(AMD_CPPC_EPP_PERF_MASK, epp); + + if (value == prev) + return 0; + + if (fast_switch) { + wrmsrl(MSR_AMD_CPPC_REQ, value); + return 0; + } else { + int ret = wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, value); + + if (ret) + return ret; } - return index; + WRITE_ONCE(cpudata->cppc_req_cached, value); + WRITE_ONCE(cpudata->epp_cached, epp); + + return 0; } -static int amd_pstate_set_epp(struct amd_cpudata *cpudata, u32 epp) +DEFINE_STATIC_CALL(amd_pstate_update_perf, msr_update_perf); + +static inline int amd_pstate_update_perf(struct amd_cpudata *cpudata, + u32 min_perf, u32 des_perf, + u32 max_perf, u32 epp, + bool fast_switch) { + return static_call(amd_pstate_update_perf)(cpudata, min_perf, des_perf, + max_perf, epp, fast_switch); +} + +static int msr_set_epp(struct amd_cpudata *cpudata, u32 epp) +{ + u64 value, prev; int ret; - struct cppc_perf_ctrls perf_ctrls; - if (boot_cpu_has(X86_FEATURE_CPPC)) { - u64 value = READ_ONCE(cpudata->cppc_req_cached); + value = prev = READ_ONCE(cpudata->cppc_req_cached); + value &= ~AMD_CPPC_EPP_PERF_MASK; + value |= FIELD_PREP(AMD_CPPC_EPP_PERF_MASK, epp); - value &= ~GENMASK_ULL(31, 24); - value |= (u64)epp << 24; - WRITE_ONCE(cpudata->cppc_req_cached, value); + if (value == prev) + return 0; - ret = wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, value); - if (!ret) - cpudata->epp_cached = epp; - } else { - perf_ctrls.energy_perf = epp; - ret = cppc_set_epp_perf(cpudata->cpu, &perf_ctrls, 1); - if (ret) { - pr_debug("failed to set energy perf value (%d)\n", ret); - return ret; - } - cpudata->epp_cached = epp; + ret = wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, value); + if (ret) { + pr_err("failed to set energy perf value (%d)\n", ret); + return ret; } + /* update both so that msr_update_perf() can effectively check */ + WRITE_ONCE(cpudata->epp_cached, epp); + WRITE_ONCE(cpudata->cppc_req_cached, value); + return ret; } -static int amd_pstate_set_energy_pref_index(struct amd_cpudata *cpudata, - int pref_index) +DEFINE_STATIC_CALL(amd_pstate_set_epp, msr_set_epp); + +static inline int amd_pstate_set_epp(struct amd_cpudata *cpudata, u32 epp) +{ + return static_call(amd_pstate_set_epp)(cpudata, epp); +} + +static int shmem_set_epp(struct amd_cpudata *cpudata, u32 epp) { - int epp = -EINVAL; int ret; + struct cppc_perf_ctrls perf_ctrls; - if (!pref_index) { - pr_debug("EPP pref_index is invalid\n"); - return -EINVAL; + if (epp == cpudata->epp_cached) + return 0; + + perf_ctrls.energy_perf = epp; + ret = cppc_set_epp_perf(cpudata->cpu, &perf_ctrls, 1); + if (ret) { + pr_debug("failed to set energy perf value (%d)\n", ret); + return ret; } + WRITE_ONCE(cpudata->epp_cached, epp); + + return ret; +} - if (epp == -EINVAL) +static int amd_pstate_set_energy_pref_index(struct cpufreq_policy *policy, + int pref_index) +{ + struct amd_cpudata *cpudata = policy->driver_data; + int epp; + + if (!pref_index) + epp = cpudata->epp_default; + else epp = epp_values[pref_index]; if (epp > 0 && cpudata->policy == CPUFREQ_POLICY_PERFORMANCE) { @@ -222,21 +332,33 @@ static int amd_pstate_set_energy_pref_index(struct amd_cpudata *cpudata, return -EBUSY; } - ret = amd_pstate_set_epp(cpudata, epp); + if (trace_amd_pstate_epp_perf_enabled()) { + trace_amd_pstate_epp_perf(cpudata->cpu, cpudata->highest_perf, + epp, + FIELD_GET(AMD_CPPC_MIN_PERF_MASK, cpudata->cppc_req_cached), + FIELD_GET(AMD_CPPC_MAX_PERF_MASK, cpudata->cppc_req_cached), + policy->boost_enabled); + } - return ret; + return amd_pstate_set_epp(cpudata, epp); } -static inline int pstate_enable(bool enable) +static inline int msr_cppc_enable(bool enable) { int ret, cpu; unsigned long logical_proc_id_mask = 0; + /* + * MSR_AMD_CPPC_ENABLE is write-once, once set it cannot be cleared. + */ + if (!enable) + return 0; + if (enable == cppc_enabled) return 0; for_each_present_cpu(cpu) { - unsigned long logical_id = topology_logical_die_id(cpu); + unsigned long logical_id = topology_logical_package_id(cpu); if (test_bit(logical_id, &logical_proc_id_mask)) continue; @@ -253,7 +375,7 @@ static inline int pstate_enable(bool enable) return 0; } -static int cppc_enable(bool enable) +static int shmem_cppc_enable(bool enable) { int cpu, ret = 0; struct cppc_perf_ctrls perf_ctrls; @@ -280,60 +402,56 @@ static int cppc_enable(bool enable) return ret; } -DEFINE_STATIC_CALL(amd_pstate_enable, pstate_enable); +DEFINE_STATIC_CALL(amd_pstate_cppc_enable, msr_cppc_enable); -static inline int amd_pstate_enable(bool enable) +static inline int amd_pstate_cppc_enable(bool enable) { - return static_call(amd_pstate_enable)(enable); + return static_call(amd_pstate_cppc_enable)(enable); } -static int pstate_init_perf(struct amd_cpudata *cpudata) +static int msr_init_perf(struct amd_cpudata *cpudata) { - u64 cap1; - u32 highest_perf; + u64 cap1, numerator; int ret = rdmsrl_safe_on_cpu(cpudata->cpu, MSR_AMD_CPPC_CAP1, &cap1); if (ret) return ret; - /* - * TODO: Introduce AMD specific power feature. - * - * CPPC entry doesn't indicate the highest performance in some ASICs. - */ - highest_perf = amd_get_highest_perf(); - if (highest_perf > AMD_CPPC_HIGHEST_PERF(cap1)) - highest_perf = AMD_CPPC_HIGHEST_PERF(cap1); + ret = amd_get_boost_ratio_numerator(cpudata->cpu, &numerator); + if (ret) + return ret; - WRITE_ONCE(cpudata->highest_perf, highest_perf); - WRITE_ONCE(cpudata->max_limit_perf, highest_perf); + WRITE_ONCE(cpudata->highest_perf, numerator); + WRITE_ONCE(cpudata->max_limit_perf, numerator); WRITE_ONCE(cpudata->nominal_perf, AMD_CPPC_NOMINAL_PERF(cap1)); WRITE_ONCE(cpudata->lowest_nonlinear_perf, AMD_CPPC_LOWNONLIN_PERF(cap1)); WRITE_ONCE(cpudata->lowest_perf, AMD_CPPC_LOWEST_PERF(cap1)); + WRITE_ONCE(cpudata->prefcore_ranking, AMD_CPPC_HIGHEST_PERF(cap1)); WRITE_ONCE(cpudata->min_limit_perf, AMD_CPPC_LOWEST_PERF(cap1)); return 0; } -static int cppc_init_perf(struct amd_cpudata *cpudata) +static int shmem_init_perf(struct amd_cpudata *cpudata) { struct cppc_perf_caps cppc_perf; - u32 highest_perf; + u64 numerator; int ret = cppc_get_perf_caps(cpudata->cpu, &cppc_perf); if (ret) return ret; - highest_perf = amd_get_highest_perf(); - if (highest_perf > cppc_perf.highest_perf) - highest_perf = cppc_perf.highest_perf; + ret = amd_get_boost_ratio_numerator(cpudata->cpu, &numerator); + if (ret) + return ret; - WRITE_ONCE(cpudata->highest_perf, highest_perf); - WRITE_ONCE(cpudata->max_limit_perf, highest_perf); + WRITE_ONCE(cpudata->highest_perf, numerator); + WRITE_ONCE(cpudata->max_limit_perf, numerator); WRITE_ONCE(cpudata->nominal_perf, cppc_perf.nominal_perf); WRITE_ONCE(cpudata->lowest_nonlinear_perf, cppc_perf.lowest_nonlinear_perf); WRITE_ONCE(cpudata->lowest_perf, cppc_perf.lowest_perf); + WRITE_ONCE(cpudata->prefcore_ranking, cppc_perf.highest_perf); WRITE_ONCE(cpudata->min_limit_perf, cppc_perf.lowest_perf); if (cppc_state == AMD_PSTATE_ACTIVE) @@ -354,44 +472,30 @@ static int cppc_init_perf(struct amd_cpudata *cpudata) return ret; } -DEFINE_STATIC_CALL(amd_pstate_init_perf, pstate_init_perf); +DEFINE_STATIC_CALL(amd_pstate_init_perf, msr_init_perf); static inline int amd_pstate_init_perf(struct amd_cpudata *cpudata) { return static_call(amd_pstate_init_perf)(cpudata); } -static void pstate_update_perf(struct amd_cpudata *cpudata, u32 min_perf, - u32 des_perf, u32 max_perf, bool fast_switch) -{ - if (fast_switch) - wrmsrl(MSR_AMD_CPPC_REQ, READ_ONCE(cpudata->cppc_req_cached)); - else - wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, - READ_ONCE(cpudata->cppc_req_cached)); -} - -static void cppc_update_perf(struct amd_cpudata *cpudata, - u32 min_perf, u32 des_perf, - u32 max_perf, bool fast_switch) +static int shmem_update_perf(struct amd_cpudata *cpudata, u32 min_perf, + u32 des_perf, u32 max_perf, u32 epp, bool fast_switch) { struct cppc_perf_ctrls perf_ctrls; + if (cppc_state == AMD_PSTATE_ACTIVE) { + int ret = shmem_set_epp(cpudata, epp); + + if (ret) + return ret; + } + perf_ctrls.max_perf = max_perf; perf_ctrls.min_perf = min_perf; perf_ctrls.desired_perf = des_perf; - cppc_set_perf(cpudata->cpu, &perf_ctrls); -} - -DEFINE_STATIC_CALL(amd_pstate_update_perf, pstate_update_perf); - -static inline void amd_pstate_update_perf(struct amd_cpudata *cpudata, - u32 min_perf, u32 des_perf, - u32 max_perf, bool fast_switch) -{ - static_call(amd_pstate_update_perf)(cpudata, min_perf, des_perf, - max_perf, fast_switch); + return cppc_set_perf(cpudata->cpu, &perf_ctrls); } static inline bool amd_pstate_sample(struct amd_cpudata *cpudata) @@ -430,58 +534,73 @@ static inline bool amd_pstate_sample(struct amd_cpudata *cpudata) static void amd_pstate_update(struct amd_cpudata *cpudata, u32 min_perf, u32 des_perf, u32 max_perf, bool fast_switch, int gov_flags) { - u64 prev = READ_ONCE(cpudata->cppc_req_cached); - u64 value = prev; + unsigned long max_freq; + struct cpufreq_policy *policy = cpufreq_cpu_get(cpudata->cpu); + u32 nominal_perf = READ_ONCE(cpudata->nominal_perf); - min_perf = clamp_t(unsigned long, min_perf, cpudata->min_limit_perf, - cpudata->max_limit_perf); - max_perf = clamp_t(unsigned long, max_perf, cpudata->min_limit_perf, - cpudata->max_limit_perf); des_perf = clamp_t(unsigned long, des_perf, min_perf, max_perf); + max_freq = READ_ONCE(cpudata->max_limit_freq); + policy->cur = div_u64(des_perf * max_freq, max_perf); + if ((cppc_state == AMD_PSTATE_GUIDED) && (gov_flags & CPUFREQ_GOV_DYNAMIC_SWITCHING)) { min_perf = des_perf; des_perf = 0; } - value &= ~AMD_CPPC_MIN_PERF(~0L); - value |= AMD_CPPC_MIN_PERF(min_perf); - - value &= ~AMD_CPPC_DES_PERF(~0L); - value |= AMD_CPPC_DES_PERF(des_perf); - - value &= ~AMD_CPPC_MAX_PERF(~0L); - value |= AMD_CPPC_MAX_PERF(max_perf); + /* limit the max perf when core performance boost feature is disabled */ + if (!cpudata->boost_supported) + max_perf = min_t(unsigned long, nominal_perf, max_perf); if (trace_amd_pstate_perf_enabled() && amd_pstate_sample(cpudata)) { trace_amd_pstate_perf(min_perf, des_perf, max_perf, cpudata->freq, cpudata->cur.mperf, cpudata->cur.aperf, cpudata->cur.tsc, - cpudata->cpu, (value != prev), fast_switch); + cpudata->cpu, fast_switch); } - if (value == prev) - return; + amd_pstate_update_perf(cpudata, min_perf, des_perf, max_perf, 0, fast_switch); - WRITE_ONCE(cpudata->cppc_req_cached, value); - - amd_pstate_update_perf(cpudata, min_perf, des_perf, - max_perf, fast_switch); + cpufreq_cpu_put(policy); } -static int amd_pstate_verify(struct cpufreq_policy_data *policy) +static int amd_pstate_verify(struct cpufreq_policy_data *policy_data) { - cpufreq_verify_within_cpu_limits(policy); + /* + * Initialize lower frequency limit (i.e.policy->min) with + * lowest_nonlinear_frequency which is the most energy efficient + * frequency. Override the initial value set by cpufreq core and + * amd-pstate qos_requests. + */ + if (policy_data->min == FREQ_QOS_MIN_DEFAULT_VALUE) { + struct cpufreq_policy *policy = cpufreq_cpu_get(policy_data->cpu); + struct amd_cpudata *cpudata; + + if (!policy) + return -EINVAL; + + cpudata = policy->driver_data; + policy_data->min = cpudata->lowest_nonlinear_freq; + cpufreq_cpu_put(policy); + } + + cpufreq_verify_within_cpu_limits(policy_data); + pr_debug("policy_max =%d, policy_min=%d\n", policy_data->max, policy_data->min); return 0; } static int amd_pstate_update_min_max_limit(struct cpufreq_policy *policy) { - u32 max_limit_perf, min_limit_perf; + u32 max_limit_perf, min_limit_perf, max_perf, max_freq; struct amd_cpudata *cpudata = policy->driver_data; - max_limit_perf = div_u64(policy->max * cpudata->highest_perf, cpudata->max_freq); - min_limit_perf = div_u64(policy->min * cpudata->highest_perf, cpudata->max_freq); + max_perf = READ_ONCE(cpudata->highest_perf); + max_freq = READ_ONCE(cpudata->max_freq); + max_limit_perf = div_u64(policy->max * max_perf, max_freq); + min_limit_perf = div_u64(policy->min * max_perf, max_freq); + + if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE) + min_limit_perf = min(cpudata->nominal_perf, max_limit_perf); WRITE_ONCE(cpudata->max_limit_perf, max_limit_perf); WRITE_ONCE(cpudata->min_limit_perf, min_limit_perf); @@ -553,10 +672,14 @@ static void amd_pstate_adjust_perf(unsigned int cpu, unsigned long capacity) { unsigned long max_perf, min_perf, des_perf, - cap_perf, lowest_nonlinear_perf, max_freq; + cap_perf, lowest_nonlinear_perf; struct cpufreq_policy *policy = cpufreq_cpu_get(cpu); - struct amd_cpudata *cpudata = policy->driver_data; - unsigned int target_freq; + struct amd_cpudata *cpudata; + + if (!policy) + return; + + cpudata = policy->driver_data; if (policy->min != cpudata->min_limit_freq || policy->max != cpudata->max_limit_freq) amd_pstate_update_min_max_limit(policy); @@ -564,151 +687,280 @@ static void amd_pstate_adjust_perf(unsigned int cpu, cap_perf = READ_ONCE(cpudata->highest_perf); lowest_nonlinear_perf = READ_ONCE(cpudata->lowest_nonlinear_perf); - max_freq = READ_ONCE(cpudata->max_freq); des_perf = cap_perf; if (target_perf < capacity) des_perf = DIV_ROUND_UP(cap_perf * target_perf, capacity); - min_perf = READ_ONCE(cpudata->highest_perf); + min_perf = READ_ONCE(cpudata->lowest_perf); if (_min_perf < capacity) min_perf = DIV_ROUND_UP(cap_perf * _min_perf, capacity); if (min_perf < lowest_nonlinear_perf) min_perf = lowest_nonlinear_perf; - max_perf = cap_perf; + max_perf = cpudata->max_limit_perf; if (max_perf < min_perf) max_perf = min_perf; des_perf = clamp_t(unsigned long, des_perf, min_perf, max_perf); - target_freq = div_u64(des_perf * max_freq, max_perf); - policy->cur = target_freq; amd_pstate_update(cpudata, min_perf, des_perf, max_perf, true, policy->governor->flags); cpufreq_cpu_put(policy); } -static int amd_get_min_freq(struct amd_cpudata *cpudata) +static int amd_pstate_cpu_boost_update(struct cpufreq_policy *policy, bool on) { - struct cppc_perf_caps cppc_perf; + struct amd_cpudata *cpudata = policy->driver_data; + u32 nominal_freq, max_freq; + int ret = 0; - int ret = cppc_get_perf_caps(cpudata->cpu, &cppc_perf); - if (ret) - return ret; + nominal_freq = READ_ONCE(cpudata->nominal_freq); + max_freq = READ_ONCE(cpudata->max_freq); + + if (on) + policy->cpuinfo.max_freq = max_freq; + else if (policy->cpuinfo.max_freq > nominal_freq) + policy->cpuinfo.max_freq = nominal_freq; + + policy->max = policy->cpuinfo.max_freq; - /* Switch to khz */ - return cppc_perf.lowest_freq * 1000; + if (cppc_state == AMD_PSTATE_PASSIVE) { + ret = freq_qos_update_request(&cpudata->req[1], policy->cpuinfo.max_freq); + if (ret < 0) + pr_debug("Failed to update freq constraint: CPU%d\n", cpudata->cpu); + } + + return ret < 0 ? ret : 0; } -static int amd_get_max_freq(struct amd_cpudata *cpudata) +static int amd_pstate_set_boost(struct cpufreq_policy *policy, int state) { - struct cppc_perf_caps cppc_perf; - u32 max_perf, max_freq, nominal_freq, nominal_perf; - u64 boost_ratio; + struct amd_cpudata *cpudata = policy->driver_data; + int ret; - int ret = cppc_get_perf_caps(cpudata->cpu, &cppc_perf); - if (ret) - return ret; + if (!cpudata->boost_supported) { + pr_err("Boost mode is not supported by this processor or SBIOS\n"); + return -EOPNOTSUPP; + } + guard(mutex)(&amd_pstate_driver_lock); - nominal_freq = cppc_perf.nominal_freq; - nominal_perf = READ_ONCE(cpudata->nominal_perf); - max_perf = READ_ONCE(cpudata->highest_perf); + ret = amd_pstate_cpu_boost_update(policy, state); + refresh_frequency_limits(policy); - boost_ratio = div_u64(max_perf << SCHED_CAPACITY_SHIFT, - nominal_perf); + return ret; +} - max_freq = nominal_freq * boost_ratio >> SCHED_CAPACITY_SHIFT; +static int amd_pstate_init_boost_support(struct amd_cpudata *cpudata) +{ + u64 boost_val; + int ret = -1; - /* Switch to khz */ - return max_freq * 1000; + /* + * If platform has no CPB support or disable it, initialize current driver + * boost_enabled state to be false, it is not an error for cpufreq core to handle. + */ + if (!cpu_feature_enabled(X86_FEATURE_CPB)) { + pr_debug_once("Boost CPB capabilities not present in the processor\n"); + ret = 0; + goto exit_err; + } + + ret = rdmsrl_on_cpu(cpudata->cpu, MSR_K7_HWCR, &boost_val); + if (ret) { + pr_err_once("failed to read initial CPU boost state!\n"); + ret = -EIO; + goto exit_err; + } + + if (!(boost_val & MSR_K7_HWCR_CPB_DIS)) + cpudata->boost_supported = true; + + return 0; + +exit_err: + cpudata->boost_supported = false; + return ret; } -static int amd_get_nominal_freq(struct amd_cpudata *cpudata) +static void amd_perf_ctl_reset(unsigned int cpu) { - struct cppc_perf_caps cppc_perf; + wrmsrl_on_cpu(cpu, MSR_AMD_PERF_CTL, 0); +} - int ret = cppc_get_perf_caps(cpudata->cpu, &cppc_perf); - if (ret) - return ret; +/* + * Set amd-pstate preferred core enable can't be done directly from cpufreq callbacks + * due to locking, so queue the work for later. + */ +static void amd_pstste_sched_prefcore_workfn(struct work_struct *work) +{ + sched_set_itmt_support(); +} +static DECLARE_WORK(sched_prefcore_work, amd_pstste_sched_prefcore_workfn); + +#define CPPC_MAX_PERF U8_MAX + +static void amd_pstate_init_prefcore(struct amd_cpudata *cpudata) +{ + /* user disabled or not detected */ + if (!amd_pstate_prefcore) + return; + + cpudata->hw_prefcore = true; + + /* + * The priorities can be set regardless of whether or not + * sched_set_itmt_support(true) has been called and it is valid to + * update them at any time after it has been called. + */ + sched_set_itmt_core_prio((int)READ_ONCE(cpudata->prefcore_ranking), cpudata->cpu); - /* Switch to khz */ - return cppc_perf.nominal_freq * 1000; + schedule_work(&sched_prefcore_work); } -static int amd_get_lowest_nonlinear_freq(struct amd_cpudata *cpudata) +static void amd_pstate_update_limits(unsigned int cpu) { - struct cppc_perf_caps cppc_perf; - u32 lowest_nonlinear_freq, lowest_nonlinear_perf, - nominal_freq, nominal_perf; - u64 lowest_nonlinear_ratio; + struct cpufreq_policy *policy = NULL; + struct amd_cpudata *cpudata; + u32 prev_high = 0, cur_high = 0; + int ret; + bool highest_perf_changed = false; - int ret = cppc_get_perf_caps(cpudata->cpu, &cppc_perf); - if (ret) - return ret; + if (!amd_pstate_prefcore) + return; - nominal_freq = cppc_perf.nominal_freq; - nominal_perf = READ_ONCE(cpudata->nominal_perf); + policy = cpufreq_cpu_get(cpu); + if (!policy) + return; - lowest_nonlinear_perf = cppc_perf.lowest_nonlinear_perf; + cpudata = policy->driver_data; - lowest_nonlinear_ratio = div_u64(lowest_nonlinear_perf << SCHED_CAPACITY_SHIFT, - nominal_perf); + guard(mutex)(&amd_pstate_driver_lock); - lowest_nonlinear_freq = nominal_freq * lowest_nonlinear_ratio >> SCHED_CAPACITY_SHIFT; + ret = amd_get_highest_perf(cpu, &cur_high); + if (ret) { + cpufreq_cpu_put(policy); + return; + } + + prev_high = READ_ONCE(cpudata->prefcore_ranking); + highest_perf_changed = (prev_high != cur_high); + if (highest_perf_changed) { + WRITE_ONCE(cpudata->prefcore_ranking, cur_high); + + if (cur_high < CPPC_MAX_PERF) + sched_set_itmt_core_prio((int)cur_high, cpu); + } + cpufreq_cpu_put(policy); + + if (!highest_perf_changed) + cpufreq_update_policy(cpu); - /* Switch to khz */ - return lowest_nonlinear_freq * 1000; } -static int amd_pstate_set_boost(struct cpufreq_policy *policy, int state) +/* + * Get pstate transition delay time from ACPI tables that firmware set + * instead of using hardcode value directly. + */ +static u32 amd_pstate_get_transition_delay_us(unsigned int cpu) { - struct amd_cpudata *cpudata = policy->driver_data; - int ret; + u32 transition_delay_ns; - if (!cpudata->boost_supported) { - pr_err("Boost mode is not supported by this processor or SBIOS\n"); - return -EINVAL; + transition_delay_ns = cppc_get_transition_latency(cpu); + if (transition_delay_ns == CPUFREQ_ETERNAL) { + if (cpu_feature_enabled(X86_FEATURE_AMD_FAST_CPPC)) + return AMD_PSTATE_FAST_CPPC_TRANSITION_DELAY; + else + return AMD_PSTATE_TRANSITION_DELAY; } - if (state) - policy->cpuinfo.max_freq = cpudata->max_freq; - else - policy->cpuinfo.max_freq = cpudata->nominal_freq; + return transition_delay_ns / NSEC_PER_USEC; +} - policy->max = policy->cpuinfo.max_freq; +/* + * Get pstate transition latency value from ACPI tables that firmware + * set instead of using hardcode value directly. + */ +static u32 amd_pstate_get_transition_latency(unsigned int cpu) +{ + u32 transition_latency; - ret = freq_qos_update_request(&cpudata->req[1], - policy->cpuinfo.max_freq); - if (ret < 0) - return ret; + transition_latency = cppc_get_transition_latency(cpu); + if (transition_latency == CPUFREQ_ETERNAL) + return AMD_PSTATE_TRANSITION_LATENCY; - return 0; + return transition_latency; } -static void amd_pstate_boost_init(struct amd_cpudata *cpudata) +/* + * amd_pstate_init_freq: Initialize the max_freq, min_freq, + * nominal_freq and lowest_nonlinear_freq for + * the @cpudata object. + * + * Requires: highest_perf, lowest_perf, nominal_perf and + * lowest_nonlinear_perf members of @cpudata to be + * initialized. + * + * Returns 0 on success, non-zero value on failure. + */ +static int amd_pstate_init_freq(struct amd_cpudata *cpudata) { - u32 highest_perf, nominal_perf; + int ret; + u32 min_freq, max_freq; + u32 highest_perf, nominal_perf, nominal_freq; + u32 lowest_nonlinear_perf, lowest_nonlinear_freq; + struct cppc_perf_caps cppc_perf; + + ret = cppc_get_perf_caps(cpudata->cpu, &cppc_perf); + if (ret) + return ret; + + if (quirks && quirks->lowest_freq) + min_freq = quirks->lowest_freq; + else + min_freq = cppc_perf.lowest_freq; + + if (quirks && quirks->nominal_freq) + nominal_freq = quirks->nominal_freq; + else + nominal_freq = cppc_perf.nominal_freq; highest_perf = READ_ONCE(cpudata->highest_perf); nominal_perf = READ_ONCE(cpudata->nominal_perf); + max_freq = div_u64((u64)highest_perf * nominal_freq, nominal_perf); - if (highest_perf <= nominal_perf) - return; + lowest_nonlinear_perf = READ_ONCE(cpudata->lowest_nonlinear_perf); + lowest_nonlinear_freq = div_u64((u64)nominal_freq * lowest_nonlinear_perf, nominal_perf); + WRITE_ONCE(cpudata->min_freq, min_freq * 1000); + WRITE_ONCE(cpudata->lowest_nonlinear_freq, lowest_nonlinear_freq * 1000); + WRITE_ONCE(cpudata->nominal_freq, nominal_freq * 1000); + WRITE_ONCE(cpudata->max_freq, max_freq * 1000); + + /** + * Below values need to be initialized correctly, otherwise driver will fail to load + * max_freq is calculated according to (nominal_freq * highest_perf)/nominal_perf + * lowest_nonlinear_freq is a value between [min_freq, nominal_freq] + * Check _CPC in ACPI table objects if any values are incorrect + */ + if (min_freq <= 0 || max_freq <= 0 || nominal_freq <= 0 || min_freq > max_freq) { + pr_err("min_freq(%d) or max_freq(%d) or nominal_freq(%d) value is incorrect\n", + min_freq, max_freq, nominal_freq); + return -EINVAL; + } - cpudata->boost_supported = true; - current_pstate_driver->boost_enabled = true; -} + if (lowest_nonlinear_freq <= min_freq || lowest_nonlinear_freq > nominal_freq) { + pr_err("lowest_nonlinear_freq(%d) value is out of range [min_freq(%d), nominal_freq(%d)]\n", + lowest_nonlinear_freq, min_freq, nominal_freq); + return -EINVAL; + } -static void amd_perf_ctl_reset(unsigned int cpu) -{ - wrmsrl_on_cpu(cpu, MSR_AMD_PERF_CTL, 0); + return 0; } static int amd_pstate_cpu_init(struct cpufreq_policy *policy) { - int min_freq, max_freq, nominal_freq, lowest_nonlinear_freq, ret; + int min_freq, max_freq, ret; struct device *dev; struct amd_cpudata *cpudata; @@ -731,20 +983,21 @@ static int amd_pstate_cpu_init(struct cpufreq_policy *policy) if (ret) goto free_cpudata1; - min_freq = amd_get_min_freq(cpudata); - max_freq = amd_get_max_freq(cpudata); - nominal_freq = amd_get_nominal_freq(cpudata); - lowest_nonlinear_freq = amd_get_lowest_nonlinear_freq(cpudata); + amd_pstate_init_prefcore(cpudata); - if (min_freq < 0 || max_freq < 0 || min_freq > max_freq) { - dev_err(dev, "min_freq(%d) or max_freq(%d) value is incorrect\n", - min_freq, max_freq); - ret = -EINVAL; + ret = amd_pstate_init_freq(cpudata); + if (ret) goto free_cpudata1; - } - policy->cpuinfo.transition_latency = AMD_PSTATE_TRANSITION_LATENCY; - policy->transition_delay_us = AMD_PSTATE_TRANSITION_DELAY; + ret = amd_pstate_init_boost_support(cpudata); + if (ret) + goto free_cpudata1; + + min_freq = READ_ONCE(cpudata->min_freq); + max_freq = READ_ONCE(cpudata->max_freq); + + policy->cpuinfo.transition_latency = amd_pstate_get_transition_latency(policy->cpu); + policy->transition_delay_us = amd_pstate_get_transition_delay_us(policy->cpu); policy->min = min_freq; policy->max = max_freq; @@ -752,14 +1005,16 @@ static int amd_pstate_cpu_init(struct cpufreq_policy *policy) policy->cpuinfo.min_freq = min_freq; policy->cpuinfo.max_freq = max_freq; + policy->boost_enabled = READ_ONCE(cpudata->boost_supported); + /* It will be updated by governor */ policy->cur = policy->cpuinfo.min_freq; - if (boot_cpu_has(X86_FEATURE_CPPC)) + if (cpu_feature_enabled(X86_FEATURE_CPPC)) policy->fast_switch_possible = true; ret = freq_qos_add_request(&policy->constraints, &cpudata->req[0], - FREQ_QOS_MIN, policy->cpuinfo.min_freq); + FREQ_QOS_MIN, FREQ_QOS_MIN_DEFAULT_VALUE); if (ret < 0) { dev_err(dev, "Failed to add min-freq constraint (%d)\n", ret); goto free_cpudata1; @@ -772,17 +1027,11 @@ static int amd_pstate_cpu_init(struct cpufreq_policy *policy) goto free_cpudata2; } - /* Initial processor data capability frequencies */ - cpudata->max_freq = max_freq; - cpudata->min_freq = min_freq; cpudata->max_limit_freq = max_freq; cpudata->min_limit_freq = min_freq; - cpudata->nominal_freq = nominal_freq; - cpudata->lowest_nonlinear_freq = lowest_nonlinear_freq; policy->driver_data = cpudata; - amd_pstate_boost_init(cpudata); if (!current_pstate_driver->adjust_perf) current_pstate_driver->adjust_perf = amd_pstate_adjust_perf; @@ -795,7 +1044,7 @@ free_cpudata1: return ret; } -static int amd_pstate_cpu_exit(struct cpufreq_policy *policy) +static void amd_pstate_cpu_exit(struct cpufreq_policy *policy) { struct amd_cpudata *cpudata = policy->driver_data; @@ -803,15 +1052,13 @@ static int amd_pstate_cpu_exit(struct cpufreq_policy *policy) freq_qos_remove_request(&cpudata->req[0]); policy->fast_switch_possible = false; kfree(cpudata); - - return 0; } static int amd_pstate_cpu_resume(struct cpufreq_policy *policy) { int ret; - ret = amd_pstate_enable(true); + ret = amd_pstate_cppc_enable(true); if (ret) pr_err("failed to enable amd-pstate during resume, return %d\n", ret); @@ -822,7 +1069,7 @@ static int amd_pstate_cpu_suspend(struct cpufreq_policy *policy) { int ret; - ret = amd_pstate_enable(false); + ret = amd_pstate_cppc_enable(false); if (ret) pr_err("failed to disable amd-pstate during suspend, return %d\n", ret); @@ -842,7 +1089,7 @@ static ssize_t show_amd_pstate_max_freq(struct cpufreq_policy *policy, int max_freq; struct amd_cpudata *cpudata = policy->driver_data; - max_freq = amd_get_max_freq(cpudata); + max_freq = READ_ONCE(cpudata->max_freq); if (max_freq < 0) return max_freq; @@ -855,7 +1102,7 @@ static ssize_t show_amd_pstate_lowest_nonlinear_freq(struct cpufreq_policy *poli int freq; struct amd_cpudata *cpudata = policy->driver_data; - freq = amd_get_lowest_nonlinear_freq(cpudata); + freq = READ_ONCE(cpudata->lowest_nonlinear_freq); if (freq < 0) return freq; @@ -877,6 +1124,28 @@ static ssize_t show_amd_pstate_highest_perf(struct cpufreq_policy *policy, return sysfs_emit(buf, "%u\n", perf); } +static ssize_t show_amd_pstate_prefcore_ranking(struct cpufreq_policy *policy, + char *buf) +{ + u32 perf; + struct amd_cpudata *cpudata = policy->driver_data; + + perf = READ_ONCE(cpudata->prefcore_ranking); + + return sysfs_emit(buf, "%u\n", perf); +} + +static ssize_t show_amd_pstate_hw_prefcore(struct cpufreq_policy *policy, + char *buf) +{ + bool hw_prefcore; + struct amd_cpudata *cpudata = policy->driver_data; + + hw_prefcore = READ_ONCE(cpudata->hw_prefcore); + + return sysfs_emit(buf, "%s\n", str_enabled_disabled(hw_prefcore)); +} + static ssize_t show_energy_performance_available_preferences( struct cpufreq_policy *policy, char *buf) { @@ -899,7 +1168,6 @@ static ssize_t show_energy_performance_available_preferences( static ssize_t store_energy_performance_preference( struct cpufreq_policy *policy, const char *buf, size_t count) { - struct amd_cpudata *cpudata = policy->driver_data; char str_preference[21]; ssize_t ret; @@ -911,11 +1179,11 @@ static ssize_t store_energy_performance_preference( if (ret < 0) return -EINVAL; - mutex_lock(&amd_pstate_limits_lock); - ret = amd_pstate_set_energy_pref_index(cpudata, ret); - mutex_unlock(&amd_pstate_limits_lock); + guard(mutex)(&amd_pstate_limits_lock); + + ret = amd_pstate_set_energy_pref_index(policy, ret); - return ret ?: count; + return ret ? ret : count; } static ssize_t show_energy_performance_preference( @@ -924,37 +1192,79 @@ static ssize_t show_energy_performance_preference( struct amd_cpudata *cpudata = policy->driver_data; int preference; - preference = amd_pstate_get_energy_pref_index(cpudata); - if (preference < 0) - return preference; + switch (cpudata->epp_cached) { + case AMD_CPPC_EPP_PERFORMANCE: + preference = EPP_INDEX_PERFORMANCE; + break; + case AMD_CPPC_EPP_BALANCE_PERFORMANCE: + preference = EPP_INDEX_BALANCE_PERFORMANCE; + break; + case AMD_CPPC_EPP_BALANCE_POWERSAVE: + preference = EPP_INDEX_BALANCE_POWERSAVE; + break; + case AMD_CPPC_EPP_POWERSAVE: + preference = EPP_INDEX_POWERSAVE; + break; + default: + return -EINVAL; + } return sysfs_emit(buf, "%s\n", energy_perf_strings[preference]); } static void amd_pstate_driver_cleanup(void) { - amd_pstate_enable(false); + amd_pstate_cppc_enable(false); cppc_state = AMD_PSTATE_DISABLE; current_pstate_driver = NULL; } +static int amd_pstate_set_driver(int mode_idx) +{ + if (mode_idx >= AMD_PSTATE_DISABLE && mode_idx < AMD_PSTATE_MAX) { + cppc_state = mode_idx; + if (cppc_state == AMD_PSTATE_DISABLE) + pr_info("driver is explicitly disabled\n"); + + if (cppc_state == AMD_PSTATE_ACTIVE) + current_pstate_driver = &amd_pstate_epp_driver; + + if (cppc_state == AMD_PSTATE_PASSIVE || cppc_state == AMD_PSTATE_GUIDED) + current_pstate_driver = &amd_pstate_driver; + + return 0; + } + + return -EINVAL; +} + static int amd_pstate_register_driver(int mode) { int ret; - if (mode == AMD_PSTATE_PASSIVE || mode == AMD_PSTATE_GUIDED) - current_pstate_driver = &amd_pstate_driver; - else if (mode == AMD_PSTATE_ACTIVE) - current_pstate_driver = &amd_pstate_epp_driver; - else - return -EINVAL; + ret = amd_pstate_set_driver(mode); + if (ret) + return ret; cppc_state = mode; + + ret = amd_pstate_cppc_enable(true); + if (ret) { + pr_err("failed to enable cppc during amd-pstate driver registration, return %d\n", + ret); + amd_pstate_driver_cleanup(); + return ret; + } + + /* at least one CPU supports CPB */ + current_pstate_driver->boost_enabled = cpu_feature_enabled(X86_FEATURE_CPB); + ret = cpufreq_register_driver(current_pstate_driver); if (ret) { amd_pstate_driver_cleanup(); return ret; } + return 0; } @@ -971,7 +1281,7 @@ static int amd_pstate_change_mode_without_dvr_change(int mode) cppc_state = mode; - if (boot_cpu_has(X86_FEATURE_CPPC) || cppc_state == AMD_PSTATE_ACTIVE) + if (cpu_feature_enabled(X86_FEATURE_CPPC) || cppc_state == AMD_PSTATE_ACTIVE) return 0; for_each_present_cpu(cpu) { @@ -1031,7 +1341,7 @@ static ssize_t amd_pstate_show_status(char *buf) return sysfs_emit(buf, "%s\n", amd_pstate_mode_string[cppc_state]); } -static int amd_pstate_update_status(const char *buf, size_t size) +int amd_pstate_update_status(const char *buf, size_t size) { int mode_idx; @@ -1048,17 +1358,15 @@ static int amd_pstate_update_status(const char *buf, size_t size) return 0; } +EXPORT_SYMBOL_GPL(amd_pstate_update_status); static ssize_t status_show(struct device *dev, struct device_attribute *attr, char *buf) { - ssize_t ret; - mutex_lock(&amd_pstate_driver_lock); - ret = amd_pstate_show_status(buf); - mutex_unlock(&amd_pstate_driver_lock); + guard(mutex)(&amd_pstate_driver_lock); - return ret; + return amd_pstate_show_status(buf); } static ssize_t status_store(struct device *a, struct device_attribute *b, @@ -1067,25 +1375,35 @@ static ssize_t status_store(struct device *a, struct device_attribute *b, char *p = memchr(buf, '\n', count); int ret; - mutex_lock(&amd_pstate_driver_lock); + guard(mutex)(&amd_pstate_driver_lock); ret = amd_pstate_update_status(buf, p ? p - buf : count); - mutex_unlock(&amd_pstate_driver_lock); return ret < 0 ? ret : count; } +static ssize_t prefcore_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "%s\n", str_enabled_disabled(amd_pstate_prefcore)); +} + cpufreq_freq_attr_ro(amd_pstate_max_freq); cpufreq_freq_attr_ro(amd_pstate_lowest_nonlinear_freq); cpufreq_freq_attr_ro(amd_pstate_highest_perf); +cpufreq_freq_attr_ro(amd_pstate_prefcore_ranking); +cpufreq_freq_attr_ro(amd_pstate_hw_prefcore); cpufreq_freq_attr_rw(energy_performance_preference); cpufreq_freq_attr_ro(energy_performance_available_preferences); static DEVICE_ATTR_RW(status); +static DEVICE_ATTR_RO(prefcore); static struct freq_attr *amd_pstate_attr[] = { &amd_pstate_max_freq, &amd_pstate_lowest_nonlinear_freq, &amd_pstate_highest_perf, + &amd_pstate_prefcore_ranking, + &amd_pstate_hw_prefcore, NULL, }; @@ -1093,6 +1411,8 @@ static struct freq_attr *amd_pstate_epp_attr[] = { &amd_pstate_max_freq, &amd_pstate_lowest_nonlinear_freq, &amd_pstate_highest_perf, + &amd_pstate_prefcore_ranking, + &amd_pstate_hw_prefcore, &energy_performance_preference, &energy_performance_available_preferences, NULL, @@ -1100,6 +1420,7 @@ static struct freq_attr *amd_pstate_epp_attr[] = { static struct attribute *pstate_global_attributes[] = { &dev_attr_status.attr, + &dev_attr_prefcore.attr, NULL }; @@ -1130,7 +1451,7 @@ static bool amd_pstate_acpi_pm_profile_undefined(void) static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy) { - int min_freq, max_freq, nominal_freq, lowest_nonlinear_freq, ret; + int min_freq, max_freq, ret; struct amd_cpudata *cpudata; struct device *dev; u64 value; @@ -1149,52 +1470,50 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy) return -ENOMEM; cpudata->cpu = policy->cpu; - cpudata->epp_policy = 0; ret = amd_pstate_init_perf(cpudata); if (ret) goto free_cpudata1; - min_freq = amd_get_min_freq(cpudata); - max_freq = amd_get_max_freq(cpudata); - nominal_freq = amd_get_nominal_freq(cpudata); - lowest_nonlinear_freq = amd_get_lowest_nonlinear_freq(cpudata); - if (min_freq < 0 || max_freq < 0 || min_freq > max_freq) { - dev_err(dev, "min_freq(%d) or max_freq(%d) value is incorrect\n", - min_freq, max_freq); - ret = -EINVAL; + amd_pstate_init_prefcore(cpudata); + + ret = amd_pstate_init_freq(cpudata); + if (ret) + goto free_cpudata1; + + ret = amd_pstate_init_boost_support(cpudata); + if (ret) goto free_cpudata1; - } + + min_freq = READ_ONCE(cpudata->min_freq); + max_freq = READ_ONCE(cpudata->max_freq); policy->cpuinfo.min_freq = min_freq; policy->cpuinfo.max_freq = max_freq; /* It will be updated by governor */ policy->cur = policy->cpuinfo.min_freq; - /* Initial processor data capability frequencies */ - cpudata->max_freq = max_freq; - cpudata->min_freq = min_freq; - cpudata->nominal_freq = nominal_freq; - cpudata->lowest_nonlinear_freq = lowest_nonlinear_freq; - policy->driver_data = cpudata; - cpudata->epp_cached = amd_pstate_get_epp(cpudata, 0); - policy->min = policy->cpuinfo.min_freq; policy->max = policy->cpuinfo.max_freq; + policy->boost_enabled = READ_ONCE(cpudata->boost_supported); + /* * Set the policy to provide a valid fallback value in case * the default cpufreq governor is neither powersave nor performance. */ if (amd_pstate_acpi_pm_profile_server() || - amd_pstate_acpi_pm_profile_undefined()) + amd_pstate_acpi_pm_profile_undefined()) { policy->policy = CPUFREQ_POLICY_PERFORMANCE; - else + cpudata->epp_default = amd_pstate_get_epp(cpudata); + } else { policy->policy = CPUFREQ_POLICY_POWERSAVE; + cpudata->epp_default = AMD_CPPC_EPP_BALANCE_PERFORMANCE; + } - if (boot_cpu_has(X86_FEATURE_CPPC)) { + if (cpu_feature_enabled(X86_FEATURE_CPPC)) { ret = rdmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, &value); if (ret) return ret; @@ -1205,7 +1524,11 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy) return ret; WRITE_ONCE(cpudata->cppc_cap1_cached, value); } - amd_pstate_boost_init(cpudata); + ret = amd_pstate_set_epp(cpudata, cpudata->epp_default); + if (ret) + return ret; + + current_pstate_driver->adjust_perf = NULL; return 0; @@ -1214,75 +1537,45 @@ free_cpudata1: return ret; } -static int amd_pstate_epp_cpu_exit(struct cpufreq_policy *policy) +static void amd_pstate_epp_cpu_exit(struct cpufreq_policy *policy) { + struct amd_cpudata *cpudata = policy->driver_data; + + if (cpudata) { + kfree(cpudata); + policy->driver_data = NULL; + } + pr_debug("CPU %d exiting\n", policy->cpu); - return 0; } -static void amd_pstate_epp_update_limit(struct cpufreq_policy *policy) +static int amd_pstate_epp_update_limit(struct cpufreq_policy *policy) { struct amd_cpudata *cpudata = policy->driver_data; - u32 max_perf, min_perf, min_limit_perf, max_limit_perf; - u64 value; - s16 epp; - - max_perf = READ_ONCE(cpudata->highest_perf); - min_perf = READ_ONCE(cpudata->lowest_perf); - max_limit_perf = div_u64(policy->max * cpudata->highest_perf, cpudata->max_freq); - min_limit_perf = div_u64(policy->min * cpudata->highest_perf, cpudata->max_freq); - - WRITE_ONCE(cpudata->max_limit_perf, max_limit_perf); - WRITE_ONCE(cpudata->min_limit_perf, min_limit_perf); + u32 epp; - max_perf = clamp_t(unsigned long, max_perf, cpudata->min_limit_perf, - cpudata->max_limit_perf); - min_perf = clamp_t(unsigned long, min_perf, cpudata->min_limit_perf, - cpudata->max_limit_perf); - value = READ_ONCE(cpudata->cppc_req_cached); - - if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE) - min_perf = max_perf; - - /* Initial min/max values for CPPC Performance Controls Register */ - value &= ~AMD_CPPC_MIN_PERF(~0L); - value |= AMD_CPPC_MIN_PERF(min_perf); - - value &= ~AMD_CPPC_MAX_PERF(~0L); - value |= AMD_CPPC_MAX_PERF(max_perf); - - /* CPPC EPP feature require to set zero to the desire perf bit */ - value &= ~AMD_CPPC_DES_PERF(~0L); - value |= AMD_CPPC_DES_PERF(0); - - cpudata->epp_policy = cpudata->policy; - - /* Get BIOS pre-defined epp value */ - epp = amd_pstate_get_epp(cpudata, value); - if (epp < 0) { - /** - * This return value can only be negative for shared_memory - * systems where EPP register read/write not supported. - */ - return; - } + amd_pstate_update_min_max_limit(policy); if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE) epp = 0; + else + epp = READ_ONCE(cpudata->epp_cached); - /* Set initial EPP value */ - if (boot_cpu_has(X86_FEATURE_CPPC)) { - value &= ~GENMASK_ULL(31, 24); - value |= (u64)epp << 24; + if (trace_amd_pstate_epp_perf_enabled()) { + trace_amd_pstate_epp_perf(cpudata->cpu, cpudata->highest_perf, epp, + cpudata->min_limit_perf, + cpudata->max_limit_perf, + policy->boost_enabled); } - WRITE_ONCE(cpudata->cppc_req_cached, value); - amd_pstate_set_epp(cpudata, epp); + return amd_pstate_update_perf(cpudata, cpudata->min_limit_perf, 0U, + cpudata->max_limit_perf, epp, false); } static int amd_pstate_epp_set_policy(struct cpufreq_policy *policy) { struct amd_cpudata *cpudata = policy->driver_data; + int ret; if (!policy->cpuinfo.max_freq) return -ENODEV; @@ -1292,96 +1585,76 @@ static int amd_pstate_epp_set_policy(struct cpufreq_policy *policy) cpudata->policy = policy->policy; - amd_pstate_epp_update_limit(policy); + ret = amd_pstate_epp_update_limit(policy); + if (ret) + return ret; + + /* + * policy->cur is never updated with the amd_pstate_epp driver, but it + * is used as a stale frequency value. So, keep it within limits. + */ + policy->cur = policy->min; return 0; } -static void amd_pstate_epp_reenable(struct amd_cpudata *cpudata) +static int amd_pstate_epp_reenable(struct cpufreq_policy *policy) { - struct cppc_perf_ctrls perf_ctrls; - u64 value, max_perf; + struct amd_cpudata *cpudata = policy->driver_data; + u64 max_perf; int ret; - ret = amd_pstate_enable(true); + ret = amd_pstate_cppc_enable(true); if (ret) pr_err("failed to enable amd pstate during resume, return %d\n", ret); - value = READ_ONCE(cpudata->cppc_req_cached); max_perf = READ_ONCE(cpudata->highest_perf); - if (boot_cpu_has(X86_FEATURE_CPPC)) { - wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, value); - } else { - perf_ctrls.max_perf = max_perf; - perf_ctrls.energy_perf = AMD_CPPC_ENERGY_PERF_PREF(cpudata->epp_cached); - cppc_set_perf(cpudata->cpu, &perf_ctrls); + if (trace_amd_pstate_epp_perf_enabled()) { + trace_amd_pstate_epp_perf(cpudata->cpu, cpudata->highest_perf, + cpudata->epp_cached, + FIELD_GET(AMD_CPPC_MIN_PERF_MASK, cpudata->cppc_req_cached), + max_perf, policy->boost_enabled); } + + return amd_pstate_update_perf(cpudata, 0, 0, max_perf, cpudata->epp_cached, false); } static int amd_pstate_epp_cpu_online(struct cpufreq_policy *policy) { struct amd_cpudata *cpudata = policy->driver_data; + int ret; pr_debug("AMD CPU Core %d going online\n", cpudata->cpu); - if (cppc_state == AMD_PSTATE_ACTIVE) { - amd_pstate_epp_reenable(cpudata); - cpudata->suspended = false; - } + ret = amd_pstate_epp_reenable(policy); + if (ret) + return ret; + cpudata->suspended = false; return 0; } -static void amd_pstate_epp_offline(struct cpufreq_policy *policy) -{ - struct amd_cpudata *cpudata = policy->driver_data; - struct cppc_perf_ctrls perf_ctrls; - int min_perf; - u64 value; - - min_perf = READ_ONCE(cpudata->lowest_perf); - value = READ_ONCE(cpudata->cppc_req_cached); - - mutex_lock(&amd_pstate_limits_lock); - if (boot_cpu_has(X86_FEATURE_CPPC)) { - cpudata->epp_policy = CPUFREQ_POLICY_UNKNOWN; - - /* Set max perf same as min perf */ - value &= ~AMD_CPPC_MAX_PERF(~0L); - value |= AMD_CPPC_MAX_PERF(min_perf); - value &= ~AMD_CPPC_MIN_PERF(~0L); - value |= AMD_CPPC_MIN_PERF(min_perf); - wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, value); - } else { - perf_ctrls.desired_perf = 0; - perf_ctrls.max_perf = min_perf; - perf_ctrls.energy_perf = AMD_CPPC_ENERGY_PERF_PREF(HWP_EPP_BALANCE_POWERSAVE); - cppc_set_perf(cpudata->cpu, &perf_ctrls); - } - mutex_unlock(&amd_pstate_limits_lock); -} - static int amd_pstate_epp_cpu_offline(struct cpufreq_policy *policy) { struct amd_cpudata *cpudata = policy->driver_data; - - pr_debug("AMD CPU Core %d going offline\n", cpudata->cpu); + int min_perf; if (cpudata->suspended) return 0; - if (cppc_state == AMD_PSTATE_ACTIVE) - amd_pstate_epp_offline(policy); + min_perf = READ_ONCE(cpudata->lowest_perf); - return 0; -} + guard(mutex)(&amd_pstate_limits_lock); -static int amd_pstate_epp_verify_policy(struct cpufreq_policy_data *policy) -{ - cpufreq_verify_within_cpu_limits(policy); - pr_debug("policy_max =%d, policy_min=%d\n", policy->max, policy->min); - return 0; + if (trace_amd_pstate_epp_perf_enabled()) { + trace_amd_pstate_epp_perf(cpudata->cpu, cpudata->highest_perf, + AMD_CPPC_EPP_BALANCE_POWERSAVE, + min_perf, min_perf, policy->boost_enabled); + } + + return amd_pstate_update_perf(cpudata, min_perf, 0, min_perf, + AMD_CPPC_EPP_BALANCE_POWERSAVE, false); } static int amd_pstate_epp_suspend(struct cpufreq_policy *policy) @@ -1397,7 +1670,7 @@ static int amd_pstate_epp_suspend(struct cpufreq_policy *policy) cpudata->suspended = true; /* disable CPPC in lowlevel firmware */ - ret = amd_pstate_enable(false); + ret = amd_pstate_cppc_enable(false); if (ret) pr_err("failed to suspend, return %d\n", ret); @@ -1409,12 +1682,10 @@ static int amd_pstate_epp_resume(struct cpufreq_policy *policy) struct amd_cpudata *cpudata = policy->driver_data; if (cpudata->suspended) { - mutex_lock(&amd_pstate_limits_lock); + guard(mutex)(&amd_pstate_limits_lock); /* enable amd pstate from suspend state*/ - amd_pstate_epp_reenable(cpudata); - - mutex_unlock(&amd_pstate_limits_lock); + amd_pstate_epp_reenable(policy); cpudata->suspended = false; } @@ -1432,13 +1703,14 @@ static struct cpufreq_driver amd_pstate_driver = { .suspend = amd_pstate_cpu_suspend, .resume = amd_pstate_cpu_resume, .set_boost = amd_pstate_set_boost, + .update_limits = amd_pstate_update_limits, .name = "amd-pstate", .attr = amd_pstate_attr, }; static struct cpufreq_driver amd_pstate_epp_driver = { .flags = CPUFREQ_CONST_LOOPS, - .verify = amd_pstate_epp_verify_policy, + .verify = amd_pstate_verify, .setpolicy = amd_pstate_epp_set_policy, .init = amd_pstate_epp_cpu_init, .exit = amd_pstate_epp_cpu_exit, @@ -1446,27 +1718,64 @@ static struct cpufreq_driver amd_pstate_epp_driver = { .online = amd_pstate_epp_cpu_online, .suspend = amd_pstate_epp_suspend, .resume = amd_pstate_epp_resume, + .update_limits = amd_pstate_update_limits, + .set_boost = amd_pstate_set_boost, .name = "amd-pstate-epp", .attr = amd_pstate_epp_attr, }; -static int __init amd_pstate_set_driver(int mode_idx) +/* + * CPPC function is not supported for family ID 17H with model_ID ranging from 0x10 to 0x2F. + * show the debug message that helps to check if the CPU has CPPC support for loading issue. + */ +static bool amd_cppc_supported(void) { - if (mode_idx >= AMD_PSTATE_DISABLE && mode_idx < AMD_PSTATE_MAX) { - cppc_state = mode_idx; - if (cppc_state == AMD_PSTATE_DISABLE) - pr_info("driver is explicitly disabled\n"); + struct cpuinfo_x86 *c = &cpu_data(0); + bool warn = false; - if (cppc_state == AMD_PSTATE_ACTIVE) - current_pstate_driver = &amd_pstate_epp_driver; - - if (cppc_state == AMD_PSTATE_PASSIVE || cppc_state == AMD_PSTATE_GUIDED) - current_pstate_driver = &amd_pstate_driver; + if ((boot_cpu_data.x86 == 0x17) && (boot_cpu_data.x86_model < 0x30)) { + pr_debug_once("CPPC feature is not supported by the processor\n"); + return false; + } - return 0; + /* + * If the CPPC feature is disabled in the BIOS for processors + * that support MSR-based CPPC, the AMD Pstate driver may not + * function correctly. + * + * For such processors, check the CPPC flag and display a + * warning message if the platform supports CPPC. + * + * Note: The code check below will not abort the driver + * registration process because of the code is added for + * debugging purposes. Besides, it may still be possible for + * the driver to work using the shared-memory mechanism. + */ + if (!cpu_feature_enabled(X86_FEATURE_CPPC)) { + if (cpu_feature_enabled(X86_FEATURE_ZEN2)) { + switch (c->x86_model) { + case 0x60 ... 0x6F: + case 0x80 ... 0xAF: + warn = true; + break; + } + } else if (cpu_feature_enabled(X86_FEATURE_ZEN3) || + cpu_feature_enabled(X86_FEATURE_ZEN4)) { + switch (c->x86_model) { + case 0x10 ... 0x1F: + case 0x40 ... 0xAF: + warn = true; + break; + } + } else if (cpu_feature_enabled(X86_FEATURE_ZEN5)) { + warn = true; + } } - return -EINVAL; + if (warn) + pr_warn_once("The CPPC feature is supported but currently disabled by the BIOS.\n" + "Please enable it if your BIOS has the CPPC option.\n"); + return true; } static int __init amd_pstate_init(void) @@ -1477,6 +1786,11 @@ static int __init amd_pstate_init(void) if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) return -ENODEV; + /* show debug message only if CPPC is not supported */ + if (!amd_cppc_supported()) + return -EOPNOTSUPP; + + /* show warning message when BIOS broken or ACPI disabled */ if (!acpi_cpc_valid()) { pr_warn_once("the _CPC object is not present in SBIOS or ACPI disabled\n"); return -ENODEV; @@ -1486,55 +1800,59 @@ static int __init amd_pstate_init(void) if (cpufreq_get_current_driver()) return -EEXIST; - switch (cppc_state) { - case AMD_PSTATE_UNDEFINED: + quirks = NULL; + + /* check if this machine need CPPC quirks */ + dmi_check_system(amd_pstate_quirks_table); + + /* + * determine the driver mode from the command line or kernel config. + * If no command line input is provided, cppc_state will be AMD_PSTATE_UNDEFINED. + * command line options will override the kernel config settings. + */ + + if (cppc_state == AMD_PSTATE_UNDEFINED) { /* Disable on the following configs by default: * 1. Undefined platforms - * 2. Server platforms - * 3. Shared memory designs + * 2. Server platforms with CPUs older than Family 0x1A. */ if (amd_pstate_acpi_pm_profile_undefined() || - amd_pstate_acpi_pm_profile_server() || - !boot_cpu_has(X86_FEATURE_CPPC)) { + (amd_pstate_acpi_pm_profile_server() && boot_cpu_data.x86 < 0x1A)) { pr_info("driver load is disabled, boot with specific mode to enable this\n"); return -ENODEV; } - ret = amd_pstate_set_driver(CONFIG_X86_AMD_PSTATE_DEFAULT_MODE); - if (ret) - return ret; - break; - case AMD_PSTATE_DISABLE: + /* get driver mode from kernel config option [1:4] */ + cppc_state = CONFIG_X86_AMD_PSTATE_DEFAULT_MODE; + } + + if (cppc_state == AMD_PSTATE_DISABLE) { + pr_info("driver load is disabled, boot with specific mode to enable this\n"); return -ENODEV; - case AMD_PSTATE_PASSIVE: - case AMD_PSTATE_ACTIVE: - case AMD_PSTATE_GUIDED: - break; - default: - return -EINVAL; } /* capability check */ - if (boot_cpu_has(X86_FEATURE_CPPC)) { + if (cpu_feature_enabled(X86_FEATURE_CPPC)) { pr_debug("AMD CPPC MSR based functionality is supported\n"); - if (cppc_state != AMD_PSTATE_ACTIVE) - current_pstate_driver->adjust_perf = amd_pstate_adjust_perf; } else { pr_debug("AMD CPPC shared memory based functionality is supported\n"); - static_call_update(amd_pstate_enable, cppc_enable); - static_call_update(amd_pstate_init_perf, cppc_init_perf); - static_call_update(amd_pstate_update_perf, cppc_update_perf); + static_call_update(amd_pstate_cppc_enable, shmem_cppc_enable); + static_call_update(amd_pstate_init_perf, shmem_init_perf); + static_call_update(amd_pstate_update_perf, shmem_update_perf); + static_call_update(amd_pstate_get_epp, shmem_get_epp); + static_call_update(amd_pstate_set_epp, shmem_set_epp); } - /* enable amd pstate feature */ - ret = amd_pstate_enable(true); - if (ret) { - pr_err("failed to enable with return %d\n", ret); - return ret; + if (amd_pstate_prefcore) { + ret = amd_detect_prefcore(&amd_pstate_prefcore); + if (ret) + return ret; } - ret = cpufreq_register_driver(current_pstate_driver); - if (ret) + ret = amd_pstate_register_driver(cppc_state); + if (ret) { pr_err("failed to register with return %d\n", ret); + return ret; + } dev_root = bus_get_dev_root(&cpu_subsys); if (dev_root) { @@ -1550,6 +1868,7 @@ static int __init amd_pstate_init(void) global_attr_free: cpufreq_unregister_driver(current_pstate_driver); + amd_pstate_cppc_enable(false); return ret; } device_initcall(amd_pstate_init); @@ -1567,7 +1886,17 @@ static int __init amd_pstate_param(char *str) return amd_pstate_set_driver(mode_idx); } + +static int __init amd_prefcore_param(char *str) +{ + if (!strcmp(str, "disable")) + amd_pstate_prefcore = false; + + return 0; +} + early_param("amd_pstate", amd_pstate_param); +early_param("amd_prefcore", amd_prefcore_param); MODULE_AUTHOR("Huang Rui <ray.huang@amd.com>"); MODULE_DESCRIPTION("AMD Processor P-state Frequency Driver"); diff --git a/drivers/cpufreq/amd-pstate.h b/drivers/cpufreq/amd-pstate.h new file mode 100644 index 000000000000..9747e3be6cee --- /dev/null +++ b/drivers/cpufreq/amd-pstate.h @@ -0,0 +1,117 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2022 Advanced Micro Devices, Inc. + * + * Author: Meng Li <li.meng@amd.com> + */ + +#ifndef _LINUX_AMD_PSTATE_H +#define _LINUX_AMD_PSTATE_H + +#include <linux/pm_qos.h> + +/********************************************************************* + * AMD P-state INTERFACE * + *********************************************************************/ +/** + * struct amd_aperf_mperf + * @aperf: actual performance frequency clock count + * @mperf: maximum performance frequency clock count + * @tsc: time stamp counter + */ +struct amd_aperf_mperf { + u64 aperf; + u64 mperf; + u64 tsc; +}; + +/** + * struct amd_cpudata - private CPU data for AMD P-State + * @cpu: CPU number + * @req: constraint request to apply + * @cppc_req_cached: cached performance request hints + * @highest_perf: the maximum performance an individual processor may reach, + * assuming ideal conditions + * For platforms that do not support the preferred core feature, the + * highest_pef may be configured with 166 or 255, to avoid max frequency + * calculated wrongly. we take the fixed value as the highest_perf. + * @nominal_perf: the maximum sustained performance level of the processor, + * assuming ideal operating conditions + * @lowest_nonlinear_perf: the lowest performance level at which nonlinear power + * savings are achieved + * @lowest_perf: the absolute lowest performance level of the processor + * @prefcore_ranking: the preferred core ranking, the higher value indicates a higher + * priority. + * @min_limit_perf: Cached value of the performance corresponding to policy->min + * @max_limit_perf: Cached value of the performance corresponding to policy->max + * @min_limit_freq: Cached value of policy->min (in khz) + * @max_limit_freq: Cached value of policy->max (in khz) + * @max_freq: the frequency (in khz) that mapped to highest_perf + * @min_freq: the frequency (in khz) that mapped to lowest_perf + * @nominal_freq: the frequency (in khz) that mapped to nominal_perf + * @lowest_nonlinear_freq: the frequency (in khz) that mapped to lowest_nonlinear_perf + * @cur: Difference of Aperf/Mperf/tsc count between last and current sample + * @prev: Last Aperf/Mperf/tsc count value read from register + * @freq: current cpu frequency value (in khz) + * @boost_supported: check whether the Processor or SBIOS supports boost mode + * @hw_prefcore: check whether HW supports preferred core featue. + * Only when hw_prefcore and early prefcore param are true, + * AMD P-State driver supports preferred core featue. + * @epp_cached: Cached CPPC energy-performance preference value + * @policy: Cpufreq policy value + * @cppc_cap1_cached Cached MSR_AMD_CPPC_CAP1 register value + * + * The amd_cpudata is key private data for each CPU thread in AMD P-State, and + * represents all the attributes and goals that AMD P-State requests at runtime. + */ +struct amd_cpudata { + int cpu; + + struct freq_qos_request req[2]; + u64 cppc_req_cached; + + u32 highest_perf; + u32 nominal_perf; + u32 lowest_nonlinear_perf; + u32 lowest_perf; + u32 prefcore_ranking; + u32 min_limit_perf; + u32 max_limit_perf; + u32 min_limit_freq; + u32 max_limit_freq; + + u32 max_freq; + u32 min_freq; + u32 nominal_freq; + u32 lowest_nonlinear_freq; + + struct amd_aperf_mperf cur; + struct amd_aperf_mperf prev; + + u64 freq; + bool boost_supported; + bool hw_prefcore; + + /* EPP feature related attributes*/ + s16 epp_cached; + u32 policy; + u64 cppc_cap1_cached; + bool suspended; + s16 epp_default; +}; + +/* + * enum amd_pstate_mode - driver working mode of amd pstate + */ +enum amd_pstate_mode { + AMD_PSTATE_UNDEFINED = 0, + AMD_PSTATE_DISABLE, + AMD_PSTATE_PASSIVE, + AMD_PSTATE_ACTIVE, + AMD_PSTATE_GUIDED, + AMD_PSTATE_MAX, +}; +const char *amd_pstate_get_mode_string(enum amd_pstate_mode mode); +int amd_pstate_update_status(const char *buf, size_t size); + +#endif /* _LINUX_AMD_PSTATE_H */ diff --git a/drivers/cpufreq/apple-soc-cpufreq.c b/drivers/cpufreq/apple-soc-cpufreq.c index 021f423705e1..269b18c62d04 100644 --- a/drivers/cpufreq/apple-soc-cpufreq.c +++ b/drivers/cpufreq/apple-soc-cpufreq.c @@ -22,11 +22,14 @@ #include <linux/pm_opp.h> #include <linux/slab.h> -#define APPLE_DVFS_CMD 0x20 -#define APPLE_DVFS_CMD_BUSY BIT(31) -#define APPLE_DVFS_CMD_SET BIT(25) -#define APPLE_DVFS_CMD_PS2 GENMASK(16, 12) -#define APPLE_DVFS_CMD_PS1 GENMASK(4, 0) +#define APPLE_DVFS_CMD 0x20 +#define APPLE_DVFS_CMD_BUSY BIT(31) +#define APPLE_DVFS_CMD_SET BIT(25) +#define APPLE_DVFS_CMD_PS1_S5L8960X GENMASK(24, 22) +#define APPLE_DVFS_CMD_PS1_S5L8960X_SHIFT 22 +#define APPLE_DVFS_CMD_PS2 GENMASK(15, 12) +#define APPLE_DVFS_CMD_PS1 GENMASK(4, 0) +#define APPLE_DVFS_CMD_PS1_SHIFT 0 /* Same timebase as CPU counter (24MHz) */ #define APPLE_DVFS_LAST_CHG_TIME 0x38 @@ -35,6 +38,9 @@ * Apple ran out of bits and had to shift this in T8112... */ #define APPLE_DVFS_STATUS 0x50 +#define APPLE_DVFS_STATUS_CUR_PS_S5L8960X GENMASK(5, 3) +#define APPLE_DVFS_STATUS_CUR_PS_SHIFT_S5L8960X 3 +#define APPLE_DVFS_STATUS_TGT_PS_S5L8960X GENMASK(2, 0) #define APPLE_DVFS_STATUS_CUR_PS_T8103 GENMASK(7, 4) #define APPLE_DVFS_STATUS_CUR_PS_SHIFT_T8103 4 #define APPLE_DVFS_STATUS_TGT_PS_T8103 GENMASK(3, 0) @@ -52,12 +58,15 @@ #define APPLE_DVFS_PLL_FACTOR_MULT GENMASK(31, 16) #define APPLE_DVFS_PLL_FACTOR_DIV GENMASK(15, 0) -#define APPLE_DVFS_TRANSITION_TIMEOUT 100 +#define APPLE_DVFS_TRANSITION_TIMEOUT 400 struct apple_soc_cpufreq_info { + bool has_ps2; u64 max_pstate; u64 cur_pstate_mask; u64 cur_pstate_shift; + u64 ps1_mask; + u64 ps1_shift; }; struct apple_cpu_priv { @@ -68,24 +77,46 @@ struct apple_cpu_priv { static struct cpufreq_driver apple_soc_cpufreq_driver; +static const struct apple_soc_cpufreq_info soc_s5l8960x_info = { + .has_ps2 = false, + .max_pstate = 7, + .cur_pstate_mask = APPLE_DVFS_STATUS_CUR_PS_S5L8960X, + .cur_pstate_shift = APPLE_DVFS_STATUS_CUR_PS_SHIFT_S5L8960X, + .ps1_mask = APPLE_DVFS_CMD_PS1_S5L8960X, + .ps1_shift = APPLE_DVFS_CMD_PS1_S5L8960X_SHIFT, +}; + static const struct apple_soc_cpufreq_info soc_t8103_info = { + .has_ps2 = true, .max_pstate = 15, .cur_pstate_mask = APPLE_DVFS_STATUS_CUR_PS_T8103, .cur_pstate_shift = APPLE_DVFS_STATUS_CUR_PS_SHIFT_T8103, + .ps1_mask = APPLE_DVFS_CMD_PS1, + .ps1_shift = APPLE_DVFS_CMD_PS1_SHIFT, }; static const struct apple_soc_cpufreq_info soc_t8112_info = { + .has_ps2 = false, .max_pstate = 31, .cur_pstate_mask = APPLE_DVFS_STATUS_CUR_PS_T8112, .cur_pstate_shift = APPLE_DVFS_STATUS_CUR_PS_SHIFT_T8112, + .ps1_mask = APPLE_DVFS_CMD_PS1, + .ps1_shift = APPLE_DVFS_CMD_PS1_SHIFT, }; static const struct apple_soc_cpufreq_info soc_default_info = { + .has_ps2 = false, .max_pstate = 15, .cur_pstate_mask = 0, /* fallback */ + .ps1_mask = APPLE_DVFS_CMD_PS1, + .ps1_shift = APPLE_DVFS_CMD_PS1_SHIFT, }; -static const struct of_device_id apple_soc_cpufreq_of_match[] = { +static const struct of_device_id apple_soc_cpufreq_of_match[] __maybe_unused = { + { + .compatible = "apple,s5l8960x-cluster-cpufreq", + .data = &soc_s5l8960x_info, + }, { .compatible = "apple,t8103-cluster-cpufreq", .data = &soc_t8103_info, @@ -109,7 +140,7 @@ static unsigned int apple_soc_cpufreq_get_rate(unsigned int cpu) unsigned int pstate; if (priv->info->cur_pstate_mask) { - u64 reg = readq_relaxed(priv->reg_base + APPLE_DVFS_STATUS); + u32 reg = readl_relaxed(priv->reg_base + APPLE_DVFS_STATUS); pstate = (reg & priv->info->cur_pstate_mask) >> priv->info->cur_pstate_shift; } else { @@ -148,9 +179,12 @@ static int apple_soc_cpufreq_set_target(struct cpufreq_policy *policy, return -EIO; } - reg &= ~(APPLE_DVFS_CMD_PS1 | APPLE_DVFS_CMD_PS2); - reg |= FIELD_PREP(APPLE_DVFS_CMD_PS1, pstate); - reg |= FIELD_PREP(APPLE_DVFS_CMD_PS2, pstate); + reg &= ~priv->info->ps1_mask; + reg |= pstate << priv->info->ps1_shift; + if (priv->info->has_ps2) { + reg &= ~APPLE_DVFS_CMD_PS2; + reg |= FIELD_PREP(APPLE_DVFS_CMD_PS2, pstate); + } reg |= APPLE_DVFS_CMD_SET; writeq_relaxed(reg, priv->reg_base + APPLE_DVFS_CMD); @@ -275,7 +309,7 @@ static int apple_soc_cpufreq_init(struct cpufreq_policy *policy) transition_latency = dev_pm_opp_get_max_transition_latency(cpu_dev); if (!transition_latency) - transition_latency = CPUFREQ_ETERNAL; + transition_latency = APPLE_DVFS_TRANSITION_TIMEOUT * NSEC_PER_USEC; policy->cpuinfo.transition_latency = transition_latency; policy->dvfs_possible_from_any_cpu = true; @@ -305,7 +339,7 @@ out_iounmap: return ret; } -static int apple_soc_cpufreq_exit(struct cpufreq_policy *policy) +static void apple_soc_cpufreq_exit(struct cpufreq_policy *policy) { struct apple_cpu_priv *priv = policy->driver_data; @@ -313,8 +347,6 @@ static int apple_soc_cpufreq_exit(struct cpufreq_policy *policy) dev_pm_opp_remove_all_dynamic(priv->cpu_dev); iounmap(priv->reg_base); kfree(priv); - - return 0; } static struct cpufreq_driver apple_soc_cpufreq_driver = { diff --git a/drivers/cpufreq/armada-8k-cpufreq.c b/drivers/cpufreq/armada-8k-cpufreq.c index ce5a5641b6dd..7a979db81f09 100644 --- a/drivers/cpufreq/armada-8k-cpufreq.c +++ b/drivers/cpufreq/armada-8k-cpufreq.c @@ -132,7 +132,7 @@ static int __init armada_8k_cpufreq_init(void) int ret = 0, opps_index = 0, cpu, nb_cpus; struct freq_table *freq_tables; struct device_node *node; - struct cpumask cpus; + static struct cpumask cpus; node = of_find_matching_node_and_match(NULL, armada_8k_cpufreq_of_match, NULL); diff --git a/drivers/cpufreq/bmips-cpufreq.c b/drivers/cpufreq/bmips-cpufreq.c index 39221a9a187a..17a4c174553d 100644 --- a/drivers/cpufreq/bmips-cpufreq.c +++ b/drivers/cpufreq/bmips-cpufreq.c @@ -121,11 +121,9 @@ static int bmips_cpufreq_target_index(struct cpufreq_policy *policy, return 0; } -static int bmips_cpufreq_exit(struct cpufreq_policy *policy) +static void bmips_cpufreq_exit(struct cpufreq_policy *policy) { kfree(policy->freq_table); - - return 0; } static int bmips_cpufreq_init(struct cpufreq_policy *policy) diff --git a/drivers/cpufreq/brcmstb-avs-cpufreq.c b/drivers/cpufreq/brcmstb-avs-cpufreq.c index 35fb3a559ea9..2fd0f6be6fa3 100644 --- a/drivers/cpufreq/brcmstb-avs-cpufreq.c +++ b/drivers/cpufreq/brcmstb-avs-cpufreq.c @@ -474,14 +474,19 @@ static bool brcm_avs_is_firmware_loaded(struct private_data *priv) rc = brcm_avs_get_pmap(priv, NULL); magic = readl(priv->base + AVS_MBOX_MAGIC); - return (magic == AVS_FIRMWARE_MAGIC) && ((rc != -ENOTSUPP) || - (rc != -EINVAL)); + return (magic == AVS_FIRMWARE_MAGIC) && (rc != -ENOTSUPP) && + (rc != -EINVAL); } static unsigned int brcm_avs_cpufreq_get(unsigned int cpu) { struct cpufreq_policy *policy = cpufreq_cpu_get(cpu); - struct private_data *priv = policy->driver_data; + struct private_data *priv; + + if (!policy) + return 0; + + priv = policy->driver_data; cpufreq_cpu_put(policy); @@ -772,7 +777,7 @@ static struct platform_driver brcm_avs_cpufreq_platdrv = { .of_match_table = brcm_avs_cpufreq_match, }, .probe = brcm_avs_cpufreq_probe, - .remove_new = brcm_avs_cpufreq_remove, + .remove = brcm_avs_cpufreq_remove, }; module_platform_driver(brcm_avs_cpufreq_platdrv); diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c index 64420d9cfd1e..8f512448382f 100644 --- a/drivers/cpufreq/cppc_cpufreq.c +++ b/drivers/cpufreq/cppc_cpufreq.c @@ -22,7 +22,7 @@ #include <linux/vmalloc.h> #include <uapi/linux/sched/types.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <acpi/cppc_acpi.h> @@ -36,33 +36,15 @@ 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; +#ifdef CONFIG_ACPI_CPPC_CPUFREQ_FIE static enum { FIE_UNSET = -1, FIE_ENABLED, FIE_DISABLED } fie_disabled = FIE_UNSET; -#ifdef CONFIG_ACPI_CPPC_CPUFREQ_FIE module_param(fie_disabled, int, 0444); MODULE_PARM_DESC(fie_disabled, "Disable Frequency Invariance Engine (FIE)"); @@ -78,7 +60,6 @@ struct cppc_freq_invariance { 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); @@ -118,6 +99,9 @@ static void cppc_scale_freq_workfn(struct kthread_work *work) perf = cppc_perf_from_fbctrs(cpu_data, &cppc_fi->prev_perf_fb_ctrs, &fb_ctrs); + if (!perf) + return; + cppc_fi->prev_perf_fb_ctrs = fb_ctrs; perf <<= SCHED_CAPACITY_SHIFT; @@ -224,9 +208,9 @@ static void __init cppc_freq_invariance_init(void) * Fake (unused) bandwidth; workaround to "fix" * priority inheritance. */ - .sched_runtime = 1000000, - .sched_deadline = 10000000, - .sched_period = 10000000, + .sched_runtime = NSEC_PER_MSEC, + .sched_deadline = 10 * NSEC_PER_MSEC, + .sched_period = 10 * NSEC_PER_MSEC, }; int ret; @@ -241,7 +225,7 @@ static void __init cppc_freq_invariance_init(void) if (fie_disabled) return; - kworker_fie = kthread_create_worker(0, "cppc_fie"); + 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)); @@ -291,15 +275,10 @@ static int cppc_cpufreq_set_target(struct cpufreq_policy *policy, 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_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; - - cpu_data->perf_ctrls.desired_perf = desired_perf; + cpu_data->perf_ctrls.desired_perf = + cppc_khz_to_perf(&cpu_data->perf_caps, target_freq); freqs.old = policy->cur; freqs.new = target_freq; @@ -425,6 +404,9 @@ static int cppc_get_cpu_power(struct device *cpu_dev, 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); @@ -492,6 +474,9 @@ static int cppc_get_cpu_cost(struct device *cpu_dev, unsigned long KHz, 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); @@ -626,7 +611,8 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy) * Section 8.4.7.1.1.5 of ACPI 6.1 spec) */ policy->min = cppc_perf_to_khz(caps, caps->lowest_nonlinear_perf); - policy->max = cppc_perf_to_khz(caps, caps->nominal_perf); + policy->max = cppc_perf_to_khz(caps, policy->boost_enabled ? + caps->highest_perf : caps->nominal_perf); /* * Set cpuinfo.min_freq to Lowest to make the full range of performance @@ -634,7 +620,7 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy) * nonlinear 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->cpuinfo.max_freq = policy->max; policy->transition_delay_us = cppc_cpufreq_get_transition_delay_us(cpu); policy->shared_type = cpu_data->shared_type; @@ -688,7 +674,7 @@ out: return ret; } -static int cppc_cpufreq_cpu_exit(struct cpufreq_policy *policy) +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; @@ -705,7 +691,6 @@ static int cppc_cpufreq_cpu_exit(struct cpufreq_policy *policy) caps->lowest_perf, cpu, ret); cppc_cpufreq_put_cpu_data(policy); - return 0; } static inline u64 get_delta(u64 t1, u64 t0) @@ -730,35 +715,72 @@ static int cppc_perf_from_fbctrs(struct cppc_cpudata *cpu_data, delta_delivered = get_delta(fb_ctrs_t1->delivered, fb_ctrs_t0->delivered); - /* Check to avoid divide-by zero and invalid delivered_perf */ + /* + * Avoid divide-by zero and unchanged feedback counters. + * Leave it for callers to handle. + */ if (!delta_reference || !delta_delivered) - return cpu_data->perf_ctrls.desired_perf; + 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 cppc_perf_fb_ctrs fb_ctrs_t0 = {0}, fb_ctrs_t1 = {0}; struct cpufreq_policy *policy = cpufreq_cpu_get(cpu); - struct cppc_cpudata *cpu_data = policy->driver_data; + struct cppc_cpudata *cpu_data; u64 delivered_perf; int ret; - cpufreq_cpu_put(policy); + if (!policy) + return -ENODEV; - ret = cppc_get_perf_ctrs(cpu, &fb_ctrs_t0); - if (ret) - return 0; + cpu_data = policy->driver_data; - udelay(2); /* 2usec delay between sampling */ + cpufreq_cpu_put(policy); - ret = cppc_get_perf_ctrs(cpu, &fb_ctrs_t1); - if (ret) - return 0; + 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; + } delivered_perf = cppc_perf_from_fbctrs(cpu_data, &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 = cpu_data->perf_ctrls.desired_perf; return cppc_perf_to_khz(&cpu_data->perf_caps, delivered_perf); } @@ -813,52 +835,6 @@ static struct cpufreq_driver cppc_cpufreq_driver = { .name = "cppc_cpufreq", }; -/* - * HISI platform does not support delivered performance counter and - * reference performance counter. It can calculate the performance using the - * platform specific mechanism. We reuse the desired performance register to - * store the real performance calculated by the platform. - */ -static unsigned int hisi_cppc_cpufreq_get_rate(unsigned int cpu) -{ - struct cpufreq_policy *policy = cpufreq_cpu_get(cpu); - struct cppc_cpudata *cpu_data = policy->driver_data; - u64 desired_perf; - int ret; - - cpufreq_cpu_put(policy); - - ret = cppc_get_desired_perf(cpu, &desired_perf); - if (ret < 0) - return -EIO; - - return cppc_perf_to_khz(&cpu_data->perf_caps, desired_perf); -} - -static void cppc_check_hisi_workaround(void) -{ - struct acpi_table_header *tbl; - acpi_status status = AE_OK; - int i; - - status = acpi_get_table(ACPI_SIG_PCCT, 0, &tbl); - if (ACPI_FAILURE(status) || !tbl) - return; - - for (i = 0; i < ARRAY_SIZE(wa_info); i++) { - if (!memcmp(wa_info[i].oem_id, tbl->oem_id, ACPI_OEM_ID_SIZE) && - !memcmp(wa_info[i].oem_table_id, tbl->oem_table_id, ACPI_OEM_TABLE_ID_SIZE) && - wa_info[i].oem_revision == tbl->oem_revision) { - /* Overwrite the get() callback */ - cppc_cpufreq_driver.get = hisi_cppc_cpufreq_get_rate; - fie_disabled = FIE_DISABLED; - break; - } - } - - acpi_put_table(tbl); -} - static int __init cppc_cpufreq_init(void) { int ret; @@ -866,7 +842,6 @@ static int __init cppc_cpufreq_init(void) if (!acpi_cpc_valid()) return -ENODEV; - cppc_check_hisi_workaround(); cppc_freq_invariance_init(); populate_efficiency_class(); diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c index bd1e1357cef8..2aa00769cf09 100644 --- a/drivers/cpufreq/cpufreq-dt-platdev.c +++ b/drivers/cpufreq/cpufreq-dt-platdev.c @@ -103,7 +103,13 @@ static const struct of_device_id allowlist[] __initconst = { * platforms using "operating-points-v2" property. */ static const struct of_device_id blocklist[] __initconst = { + { .compatible = "airoha,en7581", }, + + { .compatible = "allwinner,sun50i-a100" }, { .compatible = "allwinner,sun50i-h6", }, + { .compatible = "allwinner,sun50i-h616", }, + { .compatible = "allwinner,sun50i-h618", }, + { .compatible = "allwinner,sun50i-h700", }, { .compatible = "apple,arm-platform", }, @@ -156,12 +162,14 @@ static const struct of_device_id blocklist[] __initconst = { { .compatible = "qcom,sc7280", }, { .compatible = "qcom,sc8180x", }, { .compatible = "qcom,sc8280xp", }, + { .compatible = "qcom,sdm670", }, { .compatible = "qcom,sdm845", }, { .compatible = "qcom,sdx75", }, { .compatible = "qcom,sm6115", }, { .compatible = "qcom,sm6350", }, { .compatible = "qcom,sm6375", }, { .compatible = "qcom,sm7225", }, + { .compatible = "qcom,sm7325", }, { .compatible = "qcom,sm8150", }, { .compatible = "qcom,sm8250", }, { .compatible = "qcom,sm8350", }, @@ -194,19 +202,18 @@ static const struct of_device_id blocklist[] __initconst = { static bool __init cpu0_node_has_opp_v2_prop(void) { - struct device_node *np = of_cpu_device_node_get(0); + struct device_node *np __free(device_node) = of_cpu_device_node_get(0); bool ret = false; if (of_property_present(np, "operating-points-v2")) ret = true; - of_node_put(np); return ret; } static int __init cpufreq_dt_platdev_init(void) { - struct device_node *np = of_find_node_by_path("/"); + struct device_node *np __free(device_node) = of_find_node_by_path("/"); const struct of_device_id *match; const void *data = NULL; @@ -222,14 +229,11 @@ static int __init cpufreq_dt_platdev_init(void) if (cpu0_node_has_opp_v2_prop() && !of_match_node(blocklist, np)) goto create_pdev; - of_node_put(np); return -ENODEV; create_pdev: - of_node_put(np); return PTR_ERR_OR_ZERO(platform_device_register_data(NULL, "cpufreq-dt", -1, data, sizeof(struct cpufreq_dt_platform_data))); } core_initcall(cpufreq_dt_platdev_init); -MODULE_LICENSE("GPL"); diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c index 8bd6e5e8f121..3a7c3372bda7 100644 --- a/drivers/cpufreq/cpufreq-dt.c +++ b/drivers/cpufreq/cpufreq-dt.c @@ -68,36 +68,22 @@ static int set_target(struct cpufreq_policy *policy, unsigned int index) */ static const char *find_supply_name(struct device *dev) { - struct device_node *np; - struct property *pp; + struct device_node *np __free(device_node) = of_node_get(dev->of_node); int cpu = dev->id; - const char *name = NULL; - - np = of_node_get(dev->of_node); /* This must be valid for sure */ if (WARN_ON(!np)) return NULL; /* Try "cpu0" for older DTs */ - if (!cpu) { - pp = of_find_property(np, "cpu0-supply", NULL); - if (pp) { - name = "cpu0"; - goto node_put; - } - } + if (!cpu && of_property_present(np, "cpu0-supply")) + return "cpu0"; - pp = of_find_property(np, "cpu-supply", NULL); - if (pp) { - name = "cpu"; - goto node_put; - } + if (of_property_present(np, "cpu-supply")) + return "cpu"; dev_dbg(dev, "no regulator for cpu%d\n", cpu); -node_put: - of_node_put(np); - return name; + return NULL; } static int cpufreq_init(struct cpufreq_policy *policy) @@ -166,10 +152,9 @@ static int cpufreq_offline(struct cpufreq_policy *policy) return 0; } -static int cpufreq_exit(struct cpufreq_policy *policy) +static void cpufreq_exit(struct cpufreq_policy *policy) { clk_put(policy->clk); - return 0; } static struct cpufreq_driver dt_cpufreq_driver = { @@ -208,7 +193,7 @@ static int dt_cpufreq_early_init(struct device *dev, int cpu) if (!priv) return -ENOMEM; - if (!alloc_cpumask_var(&priv->cpus, GFP_KERNEL)) + if (!zalloc_cpumask_var(&priv->cpus, GFP_KERNEL)) return -ENOMEM; cpumask_set_cpu(cpu, priv->cpus); @@ -360,7 +345,7 @@ static struct platform_driver dt_cpufreq_platdrv = { .name = "cpufreq-dt", }, .probe = dt_cpufreq_probe, - .remove_new = dt_cpufreq_remove, + .remove = dt_cpufreq_remove, }; module_platform_driver(dt_cpufreq_platdrv); diff --git a/drivers/cpufreq/cpufreq-nforce2.c b/drivers/cpufreq/cpufreq-nforce2.c index f7a7bcf6f52e..fedad1081973 100644 --- a/drivers/cpufreq/cpufreq-nforce2.c +++ b/drivers/cpufreq/cpufreq-nforce2.c @@ -359,11 +359,6 @@ static int nforce2_cpu_init(struct cpufreq_policy *policy) return 0; } -static int nforce2_cpu_exit(struct cpufreq_policy *policy) -{ - return 0; -} - static struct cpufreq_driver nforce2_driver = { .name = "nforce2", .flags = CPUFREQ_NO_AUTO_DYNAMIC_SWITCHING, @@ -371,7 +366,6 @@ static struct cpufreq_driver nforce2_driver = { .target = nforce2_target, .get = nforce2_get, .init = nforce2_cpu_init, - .exit = nforce2_cpu_exit, }; #ifdef MODULE diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 44db4f59c4cc..30ffbddc7ece 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -25,6 +25,7 @@ #include <linux/mutex.h> #include <linux/pm_qos.h> #include <linux/slab.h> +#include <linux/string_choices.h> #include <linux/suspend.h> #include <linux/syscore_ops.h> #include <linux/tick.h> @@ -575,21 +576,11 @@ unsigned int cpufreq_policy_transition_delay_us(struct cpufreq_policy *policy) return policy->transition_delay_us; latency = policy->cpuinfo.transition_latency / NSEC_PER_USEC; - if (latency) { - /* - * For platforms that can change the frequency very fast (< 10 - * us), the above formula gives a decent transition delay. But - * for platforms where transition_latency is in milliseconds, it - * ends up giving unrealistic values. - * - * Cap the default transition delay to 10 ms, which seems to be - * a reasonable amount of time after which we should reevaluate - * the frequency. - */ - return min(latency * LATENCY_MULTIPLIER, (unsigned int)10000); - } + if (latency) + /* Give a 50% breathing room between updates */ + return latency + (latency >> 1); - return LATENCY_MULTIPLIER; + return USEC_PER_MSEC; } EXPORT_SYMBOL_GPL(cpufreq_policy_transition_delay_us); @@ -599,26 +590,25 @@ EXPORT_SYMBOL_GPL(cpufreq_policy_transition_delay_us); static ssize_t show_boost(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - return sprintf(buf, "%d\n", cpufreq_driver->boost_enabled); + return sysfs_emit(buf, "%d\n", cpufreq_driver->boost_enabled); } static ssize_t store_boost(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { - int ret, enable; + bool enable; - ret = sscanf(buf, "%d", &enable); - if (ret != 1 || enable < 0 || enable > 1) + if (kstrtobool(buf, &enable)) return -EINVAL; if (cpufreq_boost_trigger_state(enable)) { pr_err("%s: Cannot %s BOOST!\n", - __func__, enable ? "enable" : "disable"); + __func__, str_enable_disable(enable)); return -EINVAL; } pr_debug("%s: cpufreq BOOST %s\n", - __func__, enable ? "enabled" : "disabled"); + __func__, str_enabled_disabled(enable)); return count; } @@ -632,10 +622,10 @@ static ssize_t show_local_boost(struct cpufreq_policy *policy, char *buf) static ssize_t store_local_boost(struct cpufreq_policy *policy, const char *buf, size_t count) { - int ret, enable; + int ret; + bool enable; - ret = kstrtoint(buf, 10, &enable); - if (ret || enable < 0 || enable > 1) + if (kstrtobool(buf, &enable)) return -EINVAL; if (!cpufreq_driver->boost_enabled) @@ -644,14 +634,16 @@ static ssize_t store_local_boost(struct cpufreq_policy *policy, if (policy->boost_enabled == enable) return count; + policy->boost_enabled = enable; + cpus_read_lock(); ret = cpufreq_driver->set_boost(policy, enable); cpus_read_unlock(); - if (ret) + if (ret) { + policy->boost_enabled = !policy->boost_enabled; return ret; - - policy->boost_enabled = enable; + } return count; } @@ -728,7 +720,7 @@ static struct cpufreq_governor *cpufreq_parse_governor(char *str_governor) static ssize_t show_##file_name \ (struct cpufreq_policy *policy, char *buf) \ { \ - return sprintf(buf, "%u\n", policy->object); \ + return sysfs_emit(buf, "%u\n", policy->object); \ } show_one(cpuinfo_min_freq, cpuinfo.min_freq); @@ -749,11 +741,11 @@ static ssize_t show_scaling_cur_freq(struct cpufreq_policy *policy, char *buf) freq = arch_freq_get_on_cpu(policy->cpu); if (freq) - ret = sprintf(buf, "%u\n", freq); + ret = sysfs_emit(buf, "%u\n", freq); else if (cpufreq_driver->setpolicy && cpufreq_driver->get) - ret = sprintf(buf, "%u\n", cpufreq_driver->get(policy->cpu)); + ret = sysfs_emit(buf, "%u\n", cpufreq_driver->get(policy->cpu)); else - ret = sprintf(buf, "%u\n", policy->cur); + ret = sysfs_emit(buf, "%u\n", policy->cur); return ret; } @@ -787,9 +779,9 @@ static ssize_t show_cpuinfo_cur_freq(struct cpufreq_policy *policy, unsigned int cur_freq = __cpufreq_get(policy); if (cur_freq) - return sprintf(buf, "%u\n", cur_freq); + return sysfs_emit(buf, "%u\n", cur_freq); - return sprintf(buf, "<unknown>\n"); + return sysfs_emit(buf, "<unknown>\n"); } /* @@ -798,12 +790,11 @@ static ssize_t show_cpuinfo_cur_freq(struct cpufreq_policy *policy, static ssize_t show_scaling_governor(struct cpufreq_policy *policy, char *buf) { if (policy->policy == CPUFREQ_POLICY_POWERSAVE) - return sprintf(buf, "powersave\n"); + return sysfs_emit(buf, "powersave\n"); else if (policy->policy == CPUFREQ_POLICY_PERFORMANCE) - return sprintf(buf, "performance\n"); + return sysfs_emit(buf, "performance\n"); else if (policy->governor) - return scnprintf(buf, CPUFREQ_NAME_PLEN, "%s\n", - policy->governor->name); + return sysfs_emit(buf, "%s\n", policy->governor->name); return -EINVAL; } @@ -862,7 +853,7 @@ static ssize_t show_scaling_available_governors(struct cpufreq_policy *policy, struct cpufreq_governor *t; if (!has_target()) { - i += sprintf(buf, "performance powersave"); + i += sysfs_emit(buf, "performance powersave"); goto out; } @@ -871,11 +862,11 @@ static ssize_t show_scaling_available_governors(struct cpufreq_policy *policy, if (i >= (ssize_t) ((PAGE_SIZE / sizeof(char)) - (CPUFREQ_NAME_LEN + 2))) break; - i += scnprintf(&buf[i], CPUFREQ_NAME_PLEN, "%s ", t->name); + i += sysfs_emit_at(buf, i, "%s ", t->name); } mutex_unlock(&cpufreq_governor_mutex); out: - i += sprintf(&buf[i], "\n"); + i += sysfs_emit_at(buf, i, "\n"); return i; } @@ -885,7 +876,7 @@ ssize_t cpufreq_show_cpus(const struct cpumask *mask, char *buf) unsigned int cpu; for_each_cpu(cpu, mask) { - i += scnprintf(&buf[i], (PAGE_SIZE - i - 2), "%u ", cpu); + i += sysfs_emit_at(buf, i, "%u ", cpu); if (i >= (PAGE_SIZE - 5)) break; } @@ -893,7 +884,7 @@ ssize_t cpufreq_show_cpus(const struct cpumask *mask, char *buf) /* Remove the extra space at the end */ i--; - i += sprintf(&buf[i], "\n"); + i += sysfs_emit_at(buf, i, "\n"); return i; } EXPORT_SYMBOL_GPL(cpufreq_show_cpus); @@ -936,7 +927,7 @@ static ssize_t store_scaling_setspeed(struct cpufreq_policy *policy, static ssize_t show_scaling_setspeed(struct cpufreq_policy *policy, char *buf) { if (!policy->governor || !policy->governor->show_setspeed) - return sprintf(buf, "<unsupported>\n"); + return sysfs_emit(buf, "<unsupported>\n"); return policy->governor->show_setspeed(policy, buf); } @@ -950,8 +941,8 @@ static ssize_t show_bios_limit(struct cpufreq_policy *policy, char *buf) int ret; ret = cpufreq_driver->bios_limit(policy->cpu, &limit); if (!ret) - return sprintf(buf, "%u\n", limit); - return sprintf(buf, "%u\n", policy->cpuinfo.max_freq); + return sysfs_emit(buf, "%u\n", limit); + return sysfs_emit(buf, "%u\n", policy->cpuinfo.max_freq); } cpufreq_freq_attr_ro_perm(cpuinfo_cur_freq, 0400); @@ -1481,6 +1472,10 @@ static int cpufreq_online(unsigned int cpu) blocking_notifier_call_chain(&cpufreq_policy_notifier_list, CPUFREQ_CREATE_POLICY, policy); + } else { + ret = freq_qos_update_request(policy->max_freq_req, policy->max); + if (ret < 0) + goto out_destroy_policy; } if (cpufreq_driver->get && has_target()) { @@ -1526,7 +1521,7 @@ static int cpufreq_online(unsigned int cpu) * frequency for longer duration. Hence, a BUG_ON(). */ BUG_ON(ret); - pr_info("%s: CPU%d: Running at unlisted initial frequency: %u KHz, changing to: %u KHz\n", + pr_info("%s: CPU%d: Running at unlisted initial frequency: %u kHz, changing to: %u kHz\n", __func__, policy->cpu, old_freq, policy->cur); } } @@ -1544,7 +1539,7 @@ static int cpufreq_online(unsigned int cpu) /* * Register with the energy model before - * sugov_eas_rebuild_sd() is called, which will result + * em_rebuild_sched_domains() is called, which will result * in rebuilding of the sched domains, which should only be done * once the energy model is properly initialized for the policy * first. @@ -1571,9 +1566,23 @@ static int cpufreq_online(unsigned int cpu) if (cpufreq_driver->ready) cpufreq_driver->ready(policy); - if (cpufreq_thermal_control_enabled(cpufreq_driver)) + /* Register cpufreq cooling only for a new policy */ + if (new_policy && cpufreq_thermal_control_enabled(cpufreq_driver)) policy->cdev = of_cpufreq_cooling_register(policy); + /* Let the per-policy boost flag mirror the cpufreq_driver boost during init */ + if (cpufreq_driver->set_boost && + policy->boost_enabled != cpufreq_boost_enabled()) { + policy->boost_enabled = cpufreq_boost_enabled(); + ret = cpufreq_driver->set_boost(policy, policy->boost_enabled); + if (ret) { + /* If the set_boost fails, the online operation is not affected */ + pr_info("%s: CPU%d: Cannot %s BOOST\n", __func__, policy->cpu, + policy->boost_enabled ? "enable" : "disable"); + policy->boost_enabled = !policy->boost_enabled; + } + } + pr_debug("initialization complete\n"); return 0; @@ -1655,11 +1664,6 @@ static void __cpufreq_offline(unsigned int cpu, struct cpufreq_policy *policy) else policy->last_policy = policy->policy; - if (cpufreq_thermal_control_enabled(cpufreq_driver)) { - cpufreq_cooling_unregister(policy->cdev); - policy->cdev = NULL; - } - if (has_target()) cpufreq_exit_governor(policy); @@ -1669,10 +1673,13 @@ static void __cpufreq_offline(unsigned int cpu, struct cpufreq_policy *policy) */ if (cpufreq_driver->offline) { cpufreq_driver->offline(policy); - } else if (cpufreq_driver->exit) { - cpufreq_driver->exit(policy); - policy->freq_table = NULL; + return; } + + if (cpufreq_driver->exit) + cpufreq_driver->exit(policy); + + policy->freq_table = NULL; } static int cpufreq_offline(unsigned int cpu) @@ -1720,8 +1727,17 @@ static void cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif) return; } + /* + * Unregister cpufreq cooling once all the CPUs of the policy are + * removed. + */ + if (cpufreq_thermal_control_enabled(cpufreq_driver)) { + cpufreq_cooling_unregister(policy->cdev); + policy->cdev = NULL; + } + /* We did light-weight exit earlier, do full tear down now */ - if (cpufreq_driver->offline) + if (cpufreq_driver->offline && cpufreq_driver->exit) cpufreq_driver->exit(policy); up_write(&policy->rwsem); @@ -2563,6 +2579,40 @@ int cpufreq_get_policy(struct cpufreq_policy *policy, unsigned int cpu) } EXPORT_SYMBOL(cpufreq_get_policy); +DEFINE_PER_CPU(unsigned long, cpufreq_pressure); + +/** + * cpufreq_update_pressure() - Update cpufreq pressure for CPUs + * @policy: cpufreq policy of the CPUs. + * + * Update the value of cpufreq pressure for all @cpus in the policy. + */ +static void cpufreq_update_pressure(struct cpufreq_policy *policy) +{ + unsigned long max_capacity, capped_freq, pressure; + u32 max_freq; + int cpu; + + cpu = cpumask_first(policy->related_cpus); + max_freq = arch_scale_freq_ref(cpu); + capped_freq = policy->max; + + /* + * Handle properly the boost frequencies, which should simply clean + * the cpufreq pressure value. + */ + if (max_freq <= capped_freq) { + pressure = 0; + } else { + max_capacity = arch_scale_cpu_capacity(cpu); + pressure = max_capacity - + mult_frac(max_capacity, capped_freq, max_freq); + } + + for_each_cpu(cpu, policy->related_cpus) + WRITE_ONCE(per_cpu(cpufreq_pressure, cpu), pressure); +} + /** * cpufreq_set_policy - Modify cpufreq policy parameters. * @policy: Policy object to modify. @@ -2618,6 +2668,8 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy, policy->max = __resolve_freq(policy, policy->max, CPUFREQ_RELATION_H); trace_cpu_frequency_limits(policy); + cpufreq_update_pressure(policy); + policy->cached_target_freq = UINT_MAX; pr_debug("new min and max freqs are %u - %u kHz\n", @@ -2755,11 +2807,12 @@ int cpufreq_boost_trigger_state(int state) cpus_read_lock(); for_each_active_policy(policy) { + policy->boost_enabled = state; ret = cpufreq_driver->set_boost(policy, state); - if (ret) + if (ret) { + policy->boost_enabled = !policy->boost_enabled; goto err_reset_state; - - policy->boost_enabled = state; + } } cpus_read_unlock(); @@ -2773,7 +2826,7 @@ err_reset_state: write_unlock_irqrestore(&cpufreq_driver_lock, flags); pr_err("%s: Cannot %s BOOST\n", - __func__, state ? "enable" : "disable"); + __func__, str_enable_disable(state)); return ret; } @@ -2816,7 +2869,7 @@ int cpufreq_enable_boost_support(void) } EXPORT_SYMBOL_GPL(cpufreq_enable_boost_support); -int cpufreq_boost_enabled(void) +bool cpufreq_boost_enabled(void) { return cpufreq_driver->boost_enabled; } diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c index c52d19d67557..a7c38b8b3e78 100644 --- a/drivers/cpufreq/cpufreq_ondemand.c +++ b/drivers/cpufreq/cpufreq_ondemand.c @@ -22,7 +22,6 @@ #define DEF_SAMPLING_DOWN_FACTOR (1) #define MAX_SAMPLING_DOWN_FACTOR (100000) #define MICRO_FREQUENCY_UP_THRESHOLD (95) -#define MICRO_FREQUENCY_MIN_SAMPLE_RATE (10000) #define MIN_FREQUENCY_UP_THRESHOLD (1) #define MAX_FREQUENCY_UP_THRESHOLD (100) diff --git a/drivers/cpufreq/davinci-cpufreq.c b/drivers/cpufreq/davinci-cpufreq.c index 7d2754411d8c..8736be3a06ce 100644 --- a/drivers/cpufreq/davinci-cpufreq.c +++ b/drivers/cpufreq/davinci-cpufreq.c @@ -145,7 +145,7 @@ static struct platform_driver davinci_cpufreq_driver = { .driver = { .name = "cpufreq-davinci", }, - .remove_new = __exit_p(davinci_cpufreq_remove), + .remove = __exit_p(davinci_cpufreq_remove), }; int __init davinci_cpufreq_init(void) diff --git a/drivers/cpufreq/e_powersaver.c b/drivers/cpufreq/e_powersaver.c index ab93bce8ae77..6e958b09e1b5 100644 --- a/drivers/cpufreq/e_powersaver.c +++ b/drivers/cpufreq/e_powersaver.c @@ -360,14 +360,13 @@ static int eps_cpu_init(struct cpufreq_policy *policy) return 0; } -static int eps_cpu_exit(struct cpufreq_policy *policy) +static void eps_cpu_exit(struct cpufreq_policy *policy) { unsigned int cpu = policy->cpu; /* Bye */ kfree(eps_cpu[cpu]); eps_cpu[cpu] = NULL; - return 0; } static struct cpufreq_driver eps_driver = { diff --git a/drivers/cpufreq/freq_table.c b/drivers/cpufreq/freq_table.c index c4d4643b6ca6..10e80d912b8d 100644 --- a/drivers/cpufreq/freq_table.c +++ b/drivers/cpufreq/freq_table.c @@ -40,7 +40,7 @@ int cpufreq_frequency_table_cpuinfo(struct cpufreq_policy *policy, cpufreq_for_each_valid_entry(pos, table) { freq = pos->frequency; - if (!cpufreq_boost_enabled() + if ((!cpufreq_boost_enabled() || !policy->boost_enabled) && (pos->flags & CPUFREQ_BOOST_FREQ)) continue; @@ -70,7 +70,7 @@ int cpufreq_frequency_table_verify(struct cpufreq_policy_data *policy, struct cpufreq_frequency_table *table) { struct cpufreq_frequency_table *pos; - unsigned int freq, next_larger = ~0; + unsigned int freq, prev_smaller = 0; bool found = false; pr_debug("request for verification of policy (%u - %u kHz) for cpu %u\n", @@ -86,12 +86,12 @@ int cpufreq_frequency_table_verify(struct cpufreq_policy_data *policy, break; } - if ((next_larger > freq) && (freq > policy->max)) - next_larger = freq; + if ((prev_smaller < freq) && (freq <= policy->max)) + prev_smaller = freq; } if (!found) { - policy->max = next_larger; + policy->max = prev_smaller; cpufreq_verify_within_cpu_limits(policy); } @@ -194,7 +194,7 @@ int cpufreq_table_index_unsorted(struct cpufreq_policy *policy, } if (optimal.driver_data > i) { if (suboptimal.driver_data > i) { - WARN(1, "Invalid frequency table: %d\n", policy->cpu); + WARN(1, "Invalid frequency table: %u\n", policy->cpu); return 0; } @@ -254,7 +254,7 @@ static ssize_t show_available_freqs(struct cpufreq_policy *policy, char *buf, if (show_boost ^ (pos->flags & CPUFREQ_BOOST_FREQ)) continue; - count += sprintf(&buf[count], "%d ", pos->frequency); + count += sprintf(&buf[count], "%u ", pos->frequency); } count += sprintf(&buf[count], "\n"); diff --git a/drivers/cpufreq/imx-cpufreq-dt.c b/drivers/cpufreq/imx-cpufreq-dt.c index 577bb9e2f112..1492c92ffc1a 100644 --- a/drivers/cpufreq/imx-cpufreq-dt.c +++ b/drivers/cpufreq/imx-cpufreq-dt.c @@ -183,7 +183,7 @@ static void imx_cpufreq_dt_remove(struct platform_device *pdev) static struct platform_driver imx_cpufreq_dt_driver = { .probe = imx_cpufreq_dt_probe, - .remove_new = imx_cpufreq_dt_remove, + .remove = imx_cpufreq_dt_remove, .driver = { .name = "imx-cpufreq-dt", }, diff --git a/drivers/cpufreq/imx6q-cpufreq.c b/drivers/cpufreq/imx6q-cpufreq.c index 33728c242f66..f3c99f378ad6 100644 --- a/drivers/cpufreq/imx6q-cpufreq.c +++ b/drivers/cpufreq/imx6q-cpufreq.c @@ -14,6 +14,8 @@ #include <linux/pm_opp.h> #include <linux/platform_device.h> #include <linux/regulator/consumer.h> +#include <linux/mfd/syscon.h> +#include <linux/regmap.h> #define PU_SOC_VOLTAGE_NORMAL 1250000 #define PU_SOC_VOLTAGE_HIGH 1275000 @@ -225,8 +227,6 @@ static void imx6x_disable_freq_in_opp(struct device *dev, unsigned long freq) static int imx6q_opp_check_speed_grading(struct device *dev) { - struct device_node *np; - void __iomem *base; u32 val; int ret; @@ -235,16 +235,11 @@ static int imx6q_opp_check_speed_grading(struct device *dev) if (ret) return ret; } else { - np = of_find_compatible_node(NULL, NULL, "fsl,imx6q-ocotp"); - if (!np) - return -ENOENT; + struct regmap *ocotp; - base = of_iomap(np, 0); - of_node_put(np); - if (!base) { - dev_err(dev, "failed to map ocotp\n"); - return -EFAULT; - } + ocotp = syscon_regmap_lookup_by_compatible("fsl,imx6q-ocotp"); + if (IS_ERR(ocotp)) + return -ENOENT; /* * SPEED_GRADING[1:0] defines the max speed of ARM: @@ -254,8 +249,7 @@ static int imx6q_opp_check_speed_grading(struct device *dev) * 2b'00: 792000000Hz; * We need to set the max speed of ARM according to fuse map. */ - val = readl_relaxed(base + OCOTP_CFG3); - iounmap(base); + regmap_read(ocotp, OCOTP_CFG3, &val); } val >>= OCOTP_CFG3_SPEED_SHIFT; @@ -290,25 +284,16 @@ static int imx6ul_opp_check_speed_grading(struct device *dev) if (ret) return ret; } else { - struct device_node *np; - void __iomem *base; - - np = of_find_compatible_node(NULL, NULL, "fsl,imx6ul-ocotp"); - if (!np) - np = of_find_compatible_node(NULL, NULL, - "fsl,imx6ull-ocotp"); - if (!np) - return -ENOENT; + struct regmap *ocotp; - base = of_iomap(np, 0); - of_node_put(np); - if (!base) { - dev_err(dev, "failed to map ocotp\n"); - return -EFAULT; - } + ocotp = syscon_regmap_lookup_by_compatible("fsl,imx6ul-ocotp"); + if (IS_ERR(ocotp)) + ocotp = syscon_regmap_lookup_by_compatible("fsl,imx6ull-ocotp"); + + if (IS_ERR(ocotp)) + return -ENOENT; - val = readl_relaxed(base + OCOTP_CFG3); - iounmap(base); + regmap_read(ocotp, OCOTP_CFG3, &val); } /* @@ -537,7 +522,7 @@ static struct platform_driver imx6q_cpufreq_platdrv = { .name = "imx6q-cpufreq", }, .probe = imx6q_cpufreq_probe, - .remove_new = imx6q_cpufreq_remove, + .remove = imx6q_cpufreq_remove, }; module_platform_driver(imx6q_cpufreq_platdrv); diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 79619227ea51..9c4cc01fd51a 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -16,6 +16,7 @@ #include <linux/tick.h> #include <linux/slab.h> #include <linux/sched/cpufreq.h> +#include <linux/sched/smt.h> #include <linux/list.h> #include <linux/cpu.h> #include <linux/cpufreq.h> @@ -25,7 +26,9 @@ #include <linux/acpi.h> #include <linux/vmalloc.h> #include <linux/pm_qos.h> +#include <linux/bitfield.h> #include <trace/events/power.h> +#include <linux/units.h> #include <asm/cpu.h> #include <asm/div64.h> @@ -172,7 +175,6 @@ struct vid_data { * based on the MSR_IA32_MISC_ENABLE value and whether or * not the maximum reported turbo P-state is different from * the maximum reported non-turbo one. - * @turbo_disabled_mf: The @turbo_disabled value reflected by cpuinfo.max_freq. * @min_perf_pct: Minimum capacity limit in percent of the maximum turbo * P-state capacity. * @max_perf_pct: Maximum capacity limit in percent of the maximum turbo @@ -181,7 +183,6 @@ struct vid_data { struct global_params { bool no_turbo; bool turbo_disabled; - bool turbo_disabled_mf; int max_perf_pct; int min_perf_pct; }; @@ -201,8 +202,6 @@ struct global_params { * @prev_aperf: Last APERF value read from APERF MSR * @prev_mperf: Last MPERF value read from MPERF MSR * @prev_tsc: Last timestamp counter (TSC) value - * @prev_cummulative_iowait: IO Wait time difference from last and - * current sample * @sample: Storage for storing last Sample data * @min_perf_ratio: Minimum capacity in terms of PERF or HWP ratios * @max_perf_ratio: Maximum capacity in terms of PERF or HWP ratios @@ -214,10 +213,11 @@ struct global_params { * @epp_policy: Last saved policy used to set EPP/EPB * @epp_default: Power on default HWP energy performance * preference/bias - * @epp_cached Cached HWP energy-performance preference value + * @epp_cached: Cached HWP energy-performance preference value * @hwp_req_cached: Cached value of the last HWP Request MSR * @hwp_cap_cached: Cached value of the last HWP Capabilities MSR * @last_io_update: Last time when IO wake flag was set + * @capacity_perf: Highest perf used for scale invariance * @sched_flags: Store scheduler flags for possible cross CPU update * @hwp_boost_min: Last HWP boosted min performance * @suspended: Whether or not the driver has been suspended. @@ -241,7 +241,6 @@ struct cpudata { u64 prev_aperf; u64 prev_mperf; u64 prev_tsc; - u64 prev_cummulative_iowait; struct sample sample; int32_t min_perf_ratio; int32_t max_perf_ratio; @@ -257,6 +256,7 @@ struct cpudata { u64 hwp_req_cached; u64 hwp_cap_cached; u64 last_io_update; + unsigned int capacity_perf; unsigned int sched_flags; u32 hwp_boost_min; bool suspended; @@ -294,18 +294,20 @@ struct pstate_funcs { static struct pstate_funcs pstate_funcs __read_mostly; -static int hwp_active __read_mostly; -static int hwp_mode_bdw __read_mostly; -static bool per_cpu_limits __read_mostly; +static bool hwp_active __ro_after_init; +static int hwp_mode_bdw __ro_after_init; +static bool per_cpu_limits __ro_after_init; +static bool hwp_forced __ro_after_init; static bool hwp_boost __read_mostly; -static bool hwp_forced __read_mostly; +static bool hwp_is_hybrid; static struct cpufreq_driver *intel_pstate_driver __read_mostly; -#define HYBRID_SCALING_FACTOR 78741 +#define HYBRID_SCALING_FACTOR_ADL 78741 #define HYBRID_SCALING_FACTOR_MTL 80000 +#define HYBRID_SCALING_FACTOR_LNL 86957 -static int hybrid_scaling_factor = HYBRID_SCALING_FACTOR; +static int hybrid_scaling_factor; static inline int core_get_scaling(void) { @@ -359,15 +361,14 @@ static void intel_pstate_set_itmt_prio(int cpu) int ret; ret = cppc_get_perf_caps(cpu, &cppc_perf); - if (ret) - return; - /* - * On some systems with overclocking enabled, CPPC.highest_perf is hardcoded to 0xff. - * In this case we can't use CPPC.highest_perf to enable ITMT. - * In this case we can look at MSR_HWP_CAPABILITIES bits [8:0] to decide. + * If CPPC is not available, fall back to MSR_HWP_CAPABILITIES bits [8:0]. + * + * Also, on some systems with overclocking enabled, CPPC.highest_perf is + * hardcoded to 0xff, so CPPC.highest_perf cannot be used to enable ITMT. + * Fall back to MSR_HWP_CAPABILITIES then too. */ - if (cppc_perf.highest_perf == CPPC_MAX_PERF) + if (ret || cppc_perf.highest_perf == CPPC_MAX_PERF) cppc_perf.highest_perf = HWP_HIGHEST_PERF(READ_ONCE(all_cpu_data[cpu]->hwp_cap_cached)); /* @@ -414,18 +415,15 @@ static int intel_pstate_get_cppc_guaranteed(int cpu) static int intel_pstate_cppc_get_scaling(int cpu) { struct cppc_perf_caps cppc_perf; - int ret; - - ret = cppc_get_perf_caps(cpu, &cppc_perf); /* - * If the nominal frequency and the nominal performance are not - * zero and the ratio between them is not 100, return the hybrid - * scaling factor. + * Compute the perf-to-frequency scaling factor for the given CPU if + * possible, unless it would be 0. */ - if (!ret && cppc_perf.nominal_perf && cppc_perf.nominal_freq && - cppc_perf.nominal_perf * 100 != cppc_perf.nominal_freq) - return hybrid_scaling_factor; + if (!cppc_get_perf_caps(cpu, &cppc_perf) && + cppc_perf.nominal_perf && cppc_perf.nominal_freq) + return div_u64(cppc_perf.nominal_freq * KHZ_PER_MHZ, + cppc_perf.nominal_perf); return core_get_scaling(); } @@ -596,12 +594,13 @@ static void intel_pstate_hybrid_hwp_adjust(struct cpudata *cpu) cpu->pstate.min_pstate = intel_pstate_freq_to_hwp(cpu, freq); } -static inline void update_turbo_state(void) +static bool turbo_is_disabled(void) { u64 misc_en; rdmsrl(MSR_IA32_MISC_ENABLE, misc_en); - global.turbo_disabled = misc_en & MSR_IA32_MISC_ENABLE_TURBO_DISABLE; + + return !!(misc_en & MSR_IA32_MISC_ENABLE_TURBO_DISABLE); } static int min_perf_pct_min(void) @@ -937,6 +936,148 @@ static struct freq_attr *hwp_cpufreq_attrs[] = { NULL, }; +static struct cpudata *hybrid_max_perf_cpu __read_mostly; +/* + * Protects hybrid_max_perf_cpu, the capacity_perf fields in struct cpudata, + * and the x86 arch scale-invariance information from concurrent updates. + */ +static DEFINE_MUTEX(hybrid_capacity_lock); + +static void hybrid_set_cpu_capacity(struct cpudata *cpu) +{ + arch_set_cpu_capacity(cpu->cpu, cpu->capacity_perf, + hybrid_max_perf_cpu->capacity_perf, + cpu->capacity_perf, + cpu->pstate.max_pstate_physical); + + pr_debug("CPU%d: perf = %u, max. perf = %u, base perf = %d\n", cpu->cpu, + cpu->capacity_perf, hybrid_max_perf_cpu->capacity_perf, + cpu->pstate.max_pstate_physical); +} + +static void hybrid_clear_cpu_capacity(unsigned int cpunum) +{ + arch_set_cpu_capacity(cpunum, 1, 1, 1, 1); +} + +static void hybrid_get_capacity_perf(struct cpudata *cpu) +{ + if (READ_ONCE(global.no_turbo)) { + cpu->capacity_perf = cpu->pstate.max_pstate_physical; + return; + } + + cpu->capacity_perf = HWP_HIGHEST_PERF(READ_ONCE(cpu->hwp_cap_cached)); +} + +static void hybrid_set_capacity_of_cpus(void) +{ + int cpunum; + + for_each_online_cpu(cpunum) { + struct cpudata *cpu = all_cpu_data[cpunum]; + + if (cpu) + hybrid_set_cpu_capacity(cpu); + } +} + +static void hybrid_update_cpu_capacity_scaling(void) +{ + struct cpudata *max_perf_cpu = NULL; + unsigned int max_cap_perf = 0; + int cpunum; + + for_each_online_cpu(cpunum) { + struct cpudata *cpu = all_cpu_data[cpunum]; + + if (!cpu) + continue; + + /* + * During initialization, CPU performance at full capacity needs + * to be determined. + */ + if (!hybrid_max_perf_cpu) + hybrid_get_capacity_perf(cpu); + + /* + * If hybrid_max_perf_cpu is not NULL at this point, it is + * being replaced, so don't take it into account when looking + * for the new one. + */ + if (cpu == hybrid_max_perf_cpu) + continue; + + if (cpu->capacity_perf > max_cap_perf) { + max_cap_perf = cpu->capacity_perf; + max_perf_cpu = cpu; + } + } + + if (max_perf_cpu) { + hybrid_max_perf_cpu = max_perf_cpu; + hybrid_set_capacity_of_cpus(); + } else { + pr_info("Found no CPUs with nonzero maximum performance\n"); + /* Revert to the flat CPU capacity structure. */ + for_each_online_cpu(cpunum) + hybrid_clear_cpu_capacity(cpunum); + } +} + +static void __hybrid_refresh_cpu_capacity_scaling(void) +{ + hybrid_max_perf_cpu = NULL; + hybrid_update_cpu_capacity_scaling(); +} + +static void hybrid_refresh_cpu_capacity_scaling(void) +{ + guard(mutex)(&hybrid_capacity_lock); + + __hybrid_refresh_cpu_capacity_scaling(); +} + +static void hybrid_init_cpu_capacity_scaling(bool refresh) +{ + /* + * If hybrid_max_perf_cpu is set at this point, the hybrid CPU capacity + * scaling has been enabled already and the driver is just changing the + * operation mode. + */ + if (refresh) { + hybrid_refresh_cpu_capacity_scaling(); + return; + } + + /* + * On hybrid systems, use asym capacity instead of ITMT, but because + * the capacity of SMT threads is not deterministic even approximately, + * do not do that when SMT is in use. + */ + if (hwp_is_hybrid && !sched_smt_active() && arch_enable_hybrid_capacity_scale()) { + hybrid_refresh_cpu_capacity_scaling(); + /* + * Disabling ITMT causes sched domains to be rebuilt to disable asym + * packing and enable asym capacity. + */ + sched_clear_itmt_support(); + } +} + +static bool hybrid_clear_max_perf_cpu(void) +{ + bool ret; + + guard(mutex)(&hybrid_capacity_lock); + + ret = !!hybrid_max_perf_cpu; + hybrid_max_perf_cpu = NULL; + + return ret; +} + static void __intel_pstate_get_hwp_cap(struct cpudata *cpu) { u64 cap; @@ -965,6 +1106,43 @@ static void intel_pstate_get_hwp_cap(struct cpudata *cpu) } } +static void hybrid_update_capacity(struct cpudata *cpu) +{ + unsigned int max_cap_perf; + + mutex_lock(&hybrid_capacity_lock); + + if (!hybrid_max_perf_cpu) + goto unlock; + + /* + * The maximum performance of the CPU may have changed, but assume + * that the performance of the other CPUs has not changed. + */ + max_cap_perf = hybrid_max_perf_cpu->capacity_perf; + + intel_pstate_get_hwp_cap(cpu); + + hybrid_get_capacity_perf(cpu); + /* Should hybrid_max_perf_cpu be replaced by this CPU? */ + if (cpu->capacity_perf > max_cap_perf) { + hybrid_max_perf_cpu = cpu; + hybrid_set_capacity_of_cpus(); + goto unlock; + } + + /* If this CPU is hybrid_max_perf_cpu, should it be replaced? */ + if (cpu == hybrid_max_perf_cpu && cpu->capacity_perf < max_cap_perf) { + hybrid_update_cpu_capacity_scaling(); + goto unlock; + } + + hybrid_set_cpu_capacity(cpu); + +unlock: + mutex_unlock(&hybrid_capacity_lock); +} + static void intel_pstate_hwp_set(unsigned int cpu) { struct cpudata *cpu_data = all_cpu_data[cpu]; @@ -1073,6 +1251,22 @@ static void intel_pstate_hwp_offline(struct cpudata *cpu) value |= HWP_ENERGY_PERF_PREFERENCE(HWP_EPP_POWERSAVE); wrmsrl_on_cpu(cpu->cpu, MSR_HWP_REQUEST, value); + + mutex_lock(&hybrid_capacity_lock); + + if (!hybrid_max_perf_cpu) { + mutex_unlock(&hybrid_capacity_lock); + + return; + } + + if (hybrid_max_perf_cpu == cpu) + hybrid_update_cpu_capacity_scaling(); + + mutex_unlock(&hybrid_capacity_lock); + + /* Reset the capacity of the CPU going offline to the initial value. */ + hybrid_clear_cpu_capacity(cpu->cpu); } #define POWER_CTL_EE_ENABLE 1 @@ -1156,42 +1350,58 @@ static void intel_pstate_update_policies(void) static void __intel_pstate_update_max_freq(struct cpudata *cpudata, struct cpufreq_policy *policy) { - policy->cpuinfo.max_freq = global.turbo_disabled_mf ? + if (hwp_active) + intel_pstate_get_hwp_cap(cpudata); + + policy->cpuinfo.max_freq = READ_ONCE(global.no_turbo) ? cpudata->pstate.max_freq : cpudata->pstate.turbo_freq; + refresh_frequency_limits(policy); } -static void intel_pstate_update_max_freq(unsigned int cpu) +static void intel_pstate_update_limits(unsigned int cpu) { struct cpufreq_policy *policy = cpufreq_cpu_acquire(cpu); + struct cpudata *cpudata; if (!policy) return; - __intel_pstate_update_max_freq(all_cpu_data[cpu], policy); + cpudata = all_cpu_data[cpu]; + + __intel_pstate_update_max_freq(cpudata, policy); + + /* Prevent the driver from being unregistered now. */ + mutex_lock(&intel_pstate_driver_lock); cpufreq_cpu_release(policy); + + hybrid_update_capacity(cpudata); + + mutex_unlock(&intel_pstate_driver_lock); } -static void intel_pstate_update_limits(unsigned int cpu) +static void intel_pstate_update_limits_for_all(void) { - mutex_lock(&intel_pstate_driver_lock); + int cpu; - update_turbo_state(); - /* - * If turbo has been turned on or off globally, policy limits for - * all CPUs need to be updated to reflect that. - */ - if (global.turbo_disabled_mf != global.turbo_disabled) { - global.turbo_disabled_mf = global.turbo_disabled; - arch_set_max_freq_ratio(global.turbo_disabled); - for_each_possible_cpu(cpu) - intel_pstate_update_max_freq(cpu); - } else { - cpufreq_update_policy(cpu); + for_each_possible_cpu(cpu) { + struct cpufreq_policy *policy = cpufreq_cpu_acquire(cpu); + + if (!policy) + continue; + + __intel_pstate_update_max_freq(all_cpu_data[cpu], policy); + + cpufreq_cpu_release(policy); } - mutex_unlock(&intel_pstate_driver_lock); + mutex_lock(&hybrid_capacity_lock); + + if (hybrid_max_perf_cpu) + __hybrid_refresh_cpu_capacity_scaling(); + + mutex_unlock(&hybrid_capacity_lock); } /************************** sysfs begin ************************/ @@ -1289,11 +1499,7 @@ static ssize_t show_no_turbo(struct kobject *kobj, return -EAGAIN; } - update_turbo_state(); - if (global.turbo_disabled) - ret = sprintf(buf, "%u\n", global.turbo_disabled); - else - ret = sprintf(buf, "%u\n", global.no_turbo); + ret = sprintf(buf, "%u\n", global.no_turbo); mutex_unlock(&intel_pstate_driver_lock); @@ -1304,32 +1510,39 @@ static ssize_t store_no_turbo(struct kobject *a, struct kobj_attribute *b, const char *buf, size_t count) { unsigned int input; - int ret; + bool no_turbo; - ret = sscanf(buf, "%u", &input); - if (ret != 1) + if (sscanf(buf, "%u", &input) != 1) return -EINVAL; mutex_lock(&intel_pstate_driver_lock); if (!intel_pstate_driver) { - mutex_unlock(&intel_pstate_driver_lock); - return -EAGAIN; + count = -EAGAIN; + goto unlock_driver; } - mutex_lock(&intel_pstate_limits_lock); + no_turbo = !!clamp_t(int, input, 0, 1); - update_turbo_state(); - if (global.turbo_disabled) { - pr_notice_once("Turbo disabled by BIOS or unavailable on processor\n"); - mutex_unlock(&intel_pstate_limits_lock); - mutex_unlock(&intel_pstate_driver_lock); - return -EPERM; + WRITE_ONCE(global.turbo_disabled, turbo_is_disabled()); + if (global.turbo_disabled && !no_turbo) { + pr_notice("Turbo disabled by BIOS or unavailable on processor\n"); + count = -EPERM; + if (global.no_turbo) + goto unlock_driver; + else + no_turbo = 1; } - global.no_turbo = clamp_t(int, input, 0, 1); + if (no_turbo == global.no_turbo) { + goto unlock_driver; + } + + WRITE_ONCE(global.no_turbo, no_turbo); + + mutex_lock(&intel_pstate_limits_lock); - if (global.no_turbo) { + if (no_turbo) { struct cpudata *cpu = all_cpu_data[0]; int pct = cpu->pstate.max_pstate * 100 / cpu->pstate.turbo_pstate; @@ -1340,9 +1553,10 @@ static ssize_t store_no_turbo(struct kobject *a, struct kobj_attribute *b, mutex_unlock(&intel_pstate_limits_lock); - intel_pstate_update_policies(); - arch_set_max_freq_ratio(global.no_turbo); + intel_pstate_update_limits_for_all(); + arch_set_max_freq_ratio(no_turbo); +unlock_driver: mutex_unlock(&intel_pstate_driver_lock); return count; @@ -1623,94 +1837,98 @@ static void intel_pstate_notify_work(struct work_struct *work) struct cpufreq_policy *policy = cpufreq_cpu_acquire(cpudata->cpu); if (policy) { - intel_pstate_get_hwp_cap(cpudata); __intel_pstate_update_max_freq(cpudata, policy); cpufreq_cpu_release(policy); + + /* + * The driver will not be unregistered while this function is + * running, so update the capacity without acquiring the driver + * lock. + */ + hybrid_update_capacity(cpudata); } wrmsrl_on_cpu(cpudata->cpu, MSR_HWP_STATUS, 0); } -static DEFINE_SPINLOCK(hwp_notify_lock); +static DEFINE_RAW_SPINLOCK(hwp_notify_lock); static cpumask_t hwp_intr_enable_mask; +#define HWP_GUARANTEED_PERF_CHANGE_STATUS BIT(0) +#define HWP_HIGHEST_PERF_CHANGE_STATUS BIT(3) + void notify_hwp_interrupt(void) { unsigned int this_cpu = smp_processor_id(); - struct cpudata *cpudata; + u64 value, status_mask; unsigned long flags; - u64 value; - if (!READ_ONCE(hwp_active) || !boot_cpu_has(X86_FEATURE_HWP_NOTIFY)) + if (!hwp_active || !cpu_feature_enabled(X86_FEATURE_HWP_NOTIFY)) return; + status_mask = HWP_GUARANTEED_PERF_CHANGE_STATUS; + if (cpu_feature_enabled(X86_FEATURE_HWP_HIGHEST_PERF_CHANGE)) + status_mask |= HWP_HIGHEST_PERF_CHANGE_STATUS; + rdmsrl_safe(MSR_HWP_STATUS, &value); - if (!(value & 0x01)) + if (!(value & status_mask)) return; - spin_lock_irqsave(&hwp_notify_lock, flags); + raw_spin_lock_irqsave(&hwp_notify_lock, flags); if (!cpumask_test_cpu(this_cpu, &hwp_intr_enable_mask)) goto ack_intr; - /* - * Currently we never free all_cpu_data. And we can't reach here - * without this allocated. But for safety for future changes, added - * check. - */ - if (unlikely(!READ_ONCE(all_cpu_data))) - goto ack_intr; - - /* - * The free is done during cleanup, when cpufreq registry is failed. - * We wouldn't be here if it fails on init or switch status. But for - * future changes, added check. - */ - cpudata = READ_ONCE(all_cpu_data[this_cpu]); - if (unlikely(!cpudata)) - goto ack_intr; - - schedule_delayed_work(&cpudata->hwp_notify_work, msecs_to_jiffies(10)); + schedule_delayed_work(&all_cpu_data[this_cpu]->hwp_notify_work, + msecs_to_jiffies(10)); - spin_unlock_irqrestore(&hwp_notify_lock, flags); + raw_spin_unlock_irqrestore(&hwp_notify_lock, flags); return; ack_intr: wrmsrl_safe(MSR_HWP_STATUS, 0); - spin_unlock_irqrestore(&hwp_notify_lock, flags); + raw_spin_unlock_irqrestore(&hwp_notify_lock, flags); } static void intel_pstate_disable_hwp_interrupt(struct cpudata *cpudata) { - unsigned long flags; + bool cancel_work; - if (!boot_cpu_has(X86_FEATURE_HWP_NOTIFY)) + if (!cpu_feature_enabled(X86_FEATURE_HWP_NOTIFY)) return; /* wrmsrl_on_cpu has to be outside spinlock as this can result in IPC */ wrmsrl_on_cpu(cpudata->cpu, MSR_HWP_INTERRUPT, 0x00); - spin_lock_irqsave(&hwp_notify_lock, flags); - if (cpumask_test_and_clear_cpu(cpudata->cpu, &hwp_intr_enable_mask)) - cancel_delayed_work(&cpudata->hwp_notify_work); - spin_unlock_irqrestore(&hwp_notify_lock, flags); + raw_spin_lock_irq(&hwp_notify_lock); + cancel_work = cpumask_test_and_clear_cpu(cpudata->cpu, &hwp_intr_enable_mask); + raw_spin_unlock_irq(&hwp_notify_lock); + + if (cancel_work) + cancel_delayed_work_sync(&cpudata->hwp_notify_work); } +#define HWP_GUARANTEED_PERF_CHANGE_REQ BIT(0) +#define HWP_HIGHEST_PERF_CHANGE_REQ BIT(2) + static void intel_pstate_enable_hwp_interrupt(struct cpudata *cpudata) { - /* Enable HWP notification interrupt for guaranteed performance change */ + /* Enable HWP notification interrupt for performance change */ if (boot_cpu_has(X86_FEATURE_HWP_NOTIFY)) { - unsigned long flags; + u64 interrupt_mask = HWP_GUARANTEED_PERF_CHANGE_REQ; - spin_lock_irqsave(&hwp_notify_lock, flags); + raw_spin_lock_irq(&hwp_notify_lock); INIT_DELAYED_WORK(&cpudata->hwp_notify_work, intel_pstate_notify_work); cpumask_set_cpu(cpudata->cpu, &hwp_intr_enable_mask); - spin_unlock_irqrestore(&hwp_notify_lock, flags); + raw_spin_unlock_irq(&hwp_notify_lock); + + if (cpu_feature_enabled(X86_FEATURE_HWP_HIGHEST_PERF_CHANGE)) + interrupt_mask |= HWP_HIGHEST_PERF_CHANGE_REQ; /* wrmsrl_on_cpu has to be outside spinlock as this can result in IPC */ - wrmsrl_on_cpu(cpudata->cpu, MSR_HWP_INTERRUPT, 0x01); + wrmsrl_on_cpu(cpudata->cpu, MSR_HWP_INTERRUPT, interrupt_mask); wrmsrl_on_cpu(cpudata->cpu, MSR_HWP_STATUS, 0); } } @@ -1793,7 +2011,7 @@ static u64 atom_get_val(struct cpudata *cpudata, int pstate) u32 vid; val = (u64)pstate << 8; - if (global.no_turbo && !global.turbo_disabled) + if (READ_ONCE(global.no_turbo) && !READ_ONCE(global.turbo_disabled)) val |= (u64)1 << 32; vid_fp = cpudata->vid.min + mul_fp( @@ -1958,7 +2176,7 @@ static u64 core_get_val(struct cpudata *cpudata, int pstate) u64 val; val = (u64)pstate << 8; - if (global.no_turbo && !global.turbo_disabled) + if (READ_ONCE(global.no_turbo) && !READ_ONCE(global.turbo_disabled)) val |= (u64)1 << 32; return val; @@ -1991,24 +2209,30 @@ static void hybrid_get_type(void *data) static int hwp_get_cpu_scaling(int cpu) { - u8 cpu_type = 0; + if (hybrid_scaling_factor) { + u8 cpu_type = 0; + + smp_call_function_single(cpu, hybrid_get_type, &cpu_type, 1); + + /* + * Return the hybrid scaling factor for P-cores and use the + * default core scaling for E-cores. + */ + if (cpu_type == 0x40) + return hybrid_scaling_factor; - smp_call_function_single(cpu, hybrid_get_type, &cpu_type, 1); - /* P-cores have a smaller perf level-to-freqency scaling factor. */ - if (cpu_type == 0x40) - return hybrid_scaling_factor; + if (cpu_type == 0x20) + return core_get_scaling(); + } - /* Use default core scaling for E-cores */ - if (cpu_type == 0x20) + /* Use core scaling on non-hybrid systems. */ + if (!cpu_feature_enabled(X86_FEATURE_HYBRID_CPU)) return core_get_scaling(); /* - * If reached here, this system is either non-hybrid (like Tiger - * Lake) or hybrid-capable (like Alder Lake or Raptor Lake) with - * no E cores (in which case CPUID for hybrid support is 0). - * - * The CPPC nominal_frequency field is 0 for non-hybrid systems, - * so the default core scaling will be used for them. + * The system is hybrid, but the hybrid scaling factor is not known or + * the CPU type is not one of the above, so use CPPC to compute the + * scaling factor for this CPU. */ return intel_pstate_cppc_get_scaling(cpu); } @@ -2031,14 +2255,6 @@ static void intel_pstate_set_min_pstate(struct cpudata *cpu) intel_pstate_set_pstate(cpu, cpu->pstate.min_pstate); } -static void intel_pstate_max_within_limits(struct cpudata *cpu) -{ - int pstate = max(cpu->pstate.min_pstate, cpu->max_perf_ratio); - - update_turbo_state(); - intel_pstate_set_pstate(cpu, pstate); -} - static void intel_pstate_get_cpu_pstates(struct cpudata *cpu) { int perf_ctl_max_phys = pstate_funcs.get_max_physical(cpu->cpu); @@ -2053,11 +2269,18 @@ static void intel_pstate_get_cpu_pstates(struct cpudata *cpu) if (pstate_funcs.get_cpu_scaling) { cpu->pstate.scaling = pstate_funcs.get_cpu_scaling(cpu->cpu); - if (cpu->pstate.scaling != perf_ctl_scaling) + if (cpu->pstate.scaling != perf_ctl_scaling) { intel_pstate_hybrid_hwp_adjust(cpu); + hwp_is_hybrid = true; + } } else { cpu->pstate.scaling = perf_ctl_scaling; } + /* + * If the CPU is going online for the first time and it was + * offline initially, asym capacity scaling needs to be updated. + */ + hybrid_update_capacity(cpu); } else { cpu->pstate.scaling = perf_ctl_scaling; cpu->pstate.max_pstate = pstate_funcs.get_max(cpu->cpu); @@ -2264,7 +2487,7 @@ static inline int32_t get_target_pstate(struct cpudata *cpu) sample->busy_scaled = busy_frac * 100; - target = global.no_turbo || global.turbo_disabled ? + target = READ_ONCE(global.no_turbo) ? cpu->pstate.max_pstate : cpu->pstate.turbo_pstate; target += target >> 2; target = mul_fp(target, busy_frac); @@ -2308,8 +2531,6 @@ static void intel_pstate_adjust_pstate(struct cpudata *cpu) struct sample *sample; int target_pstate; - update_turbo_state(); - target_pstate = get_target_pstate(cpu); target_pstate = intel_pstate_prepare_request(cpu, target_pstate); trace_cpu_frequency(target_pstate * cpu->pstate.scaling, cpu->cpu); @@ -2404,52 +2625,58 @@ static const struct pstate_funcs knl_funcs = { .get_val = core_get_val, }; -#define X86_MATCH(model, policy) \ - X86_MATCH_VENDOR_FAM_MODEL_FEATURE(INTEL, 6, INTEL_FAM6_##model, \ - X86_FEATURE_APERFMPERF, &policy) +#define X86_MATCH(vfm, policy) \ + X86_MATCH_VFM_FEATURE(vfm, X86_FEATURE_APERFMPERF, &policy) static const struct x86_cpu_id intel_pstate_cpu_ids[] = { - X86_MATCH(SANDYBRIDGE, core_funcs), - X86_MATCH(SANDYBRIDGE_X, core_funcs), - X86_MATCH(ATOM_SILVERMONT, silvermont_funcs), - X86_MATCH(IVYBRIDGE, core_funcs), - X86_MATCH(HASWELL, core_funcs), - X86_MATCH(BROADWELL, core_funcs), - X86_MATCH(IVYBRIDGE_X, core_funcs), - X86_MATCH(HASWELL_X, core_funcs), - X86_MATCH(HASWELL_L, core_funcs), - X86_MATCH(HASWELL_G, core_funcs), - X86_MATCH(BROADWELL_G, core_funcs), - X86_MATCH(ATOM_AIRMONT, airmont_funcs), - X86_MATCH(SKYLAKE_L, core_funcs), - X86_MATCH(BROADWELL_X, core_funcs), - X86_MATCH(SKYLAKE, core_funcs), - X86_MATCH(BROADWELL_D, core_funcs), - X86_MATCH(XEON_PHI_KNL, knl_funcs), - X86_MATCH(XEON_PHI_KNM, knl_funcs), - X86_MATCH(ATOM_GOLDMONT, core_funcs), - X86_MATCH(ATOM_GOLDMONT_PLUS, core_funcs), - X86_MATCH(SKYLAKE_X, core_funcs), - X86_MATCH(COMETLAKE, core_funcs), - X86_MATCH(ICELAKE_X, core_funcs), - X86_MATCH(TIGERLAKE, core_funcs), - X86_MATCH(SAPPHIRERAPIDS_X, core_funcs), - X86_MATCH(EMERALDRAPIDS_X, core_funcs), + X86_MATCH(INTEL_SANDYBRIDGE, core_funcs), + X86_MATCH(INTEL_SANDYBRIDGE_X, core_funcs), + X86_MATCH(INTEL_ATOM_SILVERMONT, silvermont_funcs), + X86_MATCH(INTEL_IVYBRIDGE, core_funcs), + X86_MATCH(INTEL_HASWELL, core_funcs), + X86_MATCH(INTEL_BROADWELL, core_funcs), + X86_MATCH(INTEL_IVYBRIDGE_X, core_funcs), + X86_MATCH(INTEL_HASWELL_X, core_funcs), + X86_MATCH(INTEL_HASWELL_L, core_funcs), + X86_MATCH(INTEL_HASWELL_G, core_funcs), + X86_MATCH(INTEL_BROADWELL_G, core_funcs), + X86_MATCH(INTEL_ATOM_AIRMONT, airmont_funcs), + X86_MATCH(INTEL_SKYLAKE_L, core_funcs), + X86_MATCH(INTEL_BROADWELL_X, core_funcs), + X86_MATCH(INTEL_SKYLAKE, core_funcs), + X86_MATCH(INTEL_BROADWELL_D, core_funcs), + X86_MATCH(INTEL_XEON_PHI_KNL, knl_funcs), + X86_MATCH(INTEL_XEON_PHI_KNM, knl_funcs), + X86_MATCH(INTEL_ATOM_GOLDMONT, core_funcs), + X86_MATCH(INTEL_ATOM_GOLDMONT_PLUS, core_funcs), + X86_MATCH(INTEL_SKYLAKE_X, core_funcs), + X86_MATCH(INTEL_COMETLAKE, core_funcs), + X86_MATCH(INTEL_ICELAKE_X, core_funcs), + X86_MATCH(INTEL_TIGERLAKE, core_funcs), + X86_MATCH(INTEL_SAPPHIRERAPIDS_X, core_funcs), + X86_MATCH(INTEL_EMERALDRAPIDS_X, core_funcs), {} }; MODULE_DEVICE_TABLE(x86cpu, intel_pstate_cpu_ids); +#ifdef CONFIG_ACPI static const struct x86_cpu_id intel_pstate_cpu_oob_ids[] __initconst = { - X86_MATCH(BROADWELL_D, core_funcs), - X86_MATCH(BROADWELL_X, core_funcs), - X86_MATCH(SKYLAKE_X, core_funcs), - X86_MATCH(ICELAKE_X, core_funcs), - X86_MATCH(SAPPHIRERAPIDS_X, core_funcs), + X86_MATCH(INTEL_BROADWELL_D, core_funcs), + X86_MATCH(INTEL_BROADWELL_X, core_funcs), + X86_MATCH(INTEL_SKYLAKE_X, core_funcs), + X86_MATCH(INTEL_ICELAKE_X, core_funcs), + X86_MATCH(INTEL_SAPPHIRERAPIDS_X, core_funcs), + X86_MATCH(INTEL_EMERALDRAPIDS_X, core_funcs), + X86_MATCH(INTEL_GRANITERAPIDS_D, core_funcs), + X86_MATCH(INTEL_GRANITERAPIDS_X, core_funcs), + X86_MATCH(INTEL_ATOM_CRESTMONT, core_funcs), + X86_MATCH(INTEL_ATOM_CRESTMONT_X, core_funcs), {} }; +#endif static const struct x86_cpu_id intel_pstate_cpu_ee_disable_ids[] = { - X86_MATCH(KABYLAKE, core_funcs), + X86_MATCH(INTEL_KABYLAKE, core_funcs), {} }; @@ -2486,7 +2713,7 @@ static int intel_pstate_init_cpu(unsigned int cpunum) } cpu->epp_powersave = -EINVAL; - cpu->epp_policy = 0; + cpu->epp_policy = CPUFREQ_POLICY_UNKNOWN; intel_pstate_get_cpu_pstates(cpu); @@ -2528,7 +2755,7 @@ static void intel_pstate_clear_update_util_hook(unsigned int cpu) static int intel_pstate_get_max_freq(struct cpudata *cpu) { - return global.turbo_disabled || global.no_turbo ? + return READ_ONCE(global.no_turbo) ? cpu->pstate.max_freq : cpu->pstate.turbo_freq; } @@ -2613,12 +2840,14 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy) intel_pstate_update_perf_limits(cpu, policy->min, policy->max); if (cpu->policy == CPUFREQ_POLICY_PERFORMANCE) { + int pstate = max(cpu->pstate.min_pstate, cpu->max_perf_ratio); + /* * NOHZ_FULL CPUs need this as the governor callback may not * be invoked on them. */ intel_pstate_clear_update_util_hook(policy->cpu); - intel_pstate_max_within_limits(cpu); + intel_pstate_set_pstate(cpu, pstate); } else { intel_pstate_set_update_util_hook(policy->cpu); } @@ -2661,10 +2890,9 @@ static void intel_pstate_verify_cpu_policy(struct cpudata *cpu, { int max_freq; - update_turbo_state(); if (hwp_active) { intel_pstate_get_hwp_cap(cpu); - max_freq = global.no_turbo || global.turbo_disabled ? + max_freq = READ_ONCE(global.no_turbo) ? cpu->pstate.max_freq : cpu->pstate.turbo_freq; } else { max_freq = intel_pstate_get_max_freq(cpu); @@ -2721,6 +2949,8 @@ static int intel_pstate_cpu_online(struct cpufreq_policy *policy) */ intel_pstate_hwp_reenable(cpu); cpu->suspended = false; + + hybrid_update_capacity(cpu); } return 0; @@ -2733,13 +2963,11 @@ static int intel_pstate_cpu_offline(struct cpufreq_policy *policy) return intel_cpufreq_cpu_offline(policy); } -static int intel_pstate_cpu_exit(struct cpufreq_policy *policy) +static void intel_pstate_cpu_exit(struct cpufreq_policy *policy) { pr_debug("CPU %d exiting\n", policy->cpu); policy->fast_switch_possible = false; - - return 0; } static int __intel_pstate_cpu_init(struct cpufreq_policy *policy) @@ -2758,9 +2986,7 @@ static int __intel_pstate_cpu_init(struct cpufreq_policy *policy) /* cpuinfo and default policy values */ policy->cpuinfo.min_freq = cpu->pstate.min_freq; - update_turbo_state(); - global.turbo_disabled_mf = global.turbo_disabled; - policy->cpuinfo.max_freq = global.turbo_disabled ? + policy->cpuinfo.max_freq = READ_ONCE(global.no_turbo) ? cpu->pstate.max_freq : cpu->pstate.turbo_freq; policy->min = policy->cpuinfo.min_freq; @@ -2925,8 +3151,6 @@ static int intel_cpufreq_target(struct cpufreq_policy *policy, struct cpufreq_freqs freqs; int target_pstate; - update_turbo_state(); - freqs.old = policy->cur; freqs.new = target_freq; @@ -2948,8 +3172,6 @@ static unsigned int intel_cpufreq_fast_switch(struct cpufreq_policy *policy, struct cpudata *cpu = all_cpu_data[policy->cpu]; int target_pstate; - update_turbo_state(); - target_pstate = intel_pstate_freq_to_hwp(cpu, target_freq); target_pstate = intel_cpufreq_update_pstate(policy, target_pstate, true); @@ -2967,9 +3189,9 @@ static void intel_cpufreq_adjust_perf(unsigned int cpunum, int old_pstate = cpu->pstate.current_pstate; int cap_pstate, min_pstate, max_pstate, target_pstate; - update_turbo_state(); - cap_pstate = global.turbo_disabled ? HWP_GUARANTEED_PERF(hwp_cap) : - HWP_HIGHEST_PERF(hwp_cap); + cap_pstate = READ_ONCE(global.no_turbo) ? + HWP_GUARANTEED_PERF(hwp_cap) : + HWP_HIGHEST_PERF(hwp_cap); /* Optimization: Avoid unnecessary divisions. */ @@ -3076,7 +3298,7 @@ pstate_exit: return ret; } -static int intel_cpufreq_cpu_exit(struct cpufreq_policy *policy) +static void intel_cpufreq_cpu_exit(struct cpufreq_policy *policy) { struct freq_qos_request *req; @@ -3086,7 +3308,7 @@ static int intel_cpufreq_cpu_exit(struct cpufreq_policy *policy) freq_qos_remove_request(req); kfree(req); - return intel_pstate_cpu_exit(policy); + intel_pstate_cpu_exit(policy); } static int intel_cpufreq_suspend(struct cpufreq_policy *policy) @@ -3137,10 +3359,8 @@ static void intel_pstate_driver_cleanup(void) if (intel_pstate_driver == &intel_pstate) intel_pstate_clear_update_util_hook(cpu); - spin_lock(&hwp_notify_lock); kfree(all_cpu_data[cpu]); WRITE_ONCE(all_cpu_data[cpu], NULL); - spin_unlock(&hwp_notify_lock); } } cpus_read_unlock(); @@ -3150,6 +3370,7 @@ static void intel_pstate_driver_cleanup(void) static int intel_pstate_register_driver(struct cpufreq_driver *driver) { + bool refresh_cpu_cap_scaling; int ret; if (driver == &intel_pstate) @@ -3157,6 +3378,12 @@ static int intel_pstate_register_driver(struct cpufreq_driver *driver) memset(&global, 0, sizeof(global)); global.max_perf_pct = 100; + global.turbo_disabled = turbo_is_disabled(); + global.no_turbo = global.turbo_disabled; + + arch_set_max_freq_ratio(global.turbo_disabled); + + refresh_cpu_cap_scaling = hybrid_clear_max_perf_cpu(); intel_pstate_driver = driver; ret = cpufreq_register_driver(intel_pstate_driver); @@ -3167,6 +3394,8 @@ static int intel_pstate_register_driver(struct cpufreq_driver *driver) global.min_perf_pct = min_perf_pct_min(); + hybrid_init_cpu_capacity_scaling(refresh_cpu_cap_scaling); + return 0; } @@ -3388,14 +3617,13 @@ static inline void intel_pstate_request_control_from_smm(void) {} #define INTEL_PSTATE_HWP_BROADWELL 0x01 -#define X86_MATCH_HWP(model, hwp_mode) \ - X86_MATCH_VENDOR_FAM_MODEL_FEATURE(INTEL, 6, INTEL_FAM6_##model, \ - X86_FEATURE_HWP, hwp_mode) +#define X86_MATCH_HWP(vfm, hwp_mode) \ + X86_MATCH_VFM_FEATURE(vfm, X86_FEATURE_HWP, hwp_mode) static const struct x86_cpu_id hwp_support_ids[] __initconst = { - X86_MATCH_HWP(BROADWELL_X, INTEL_PSTATE_HWP_BROADWELL), - X86_MATCH_HWP(BROADWELL_D, INTEL_PSTATE_HWP_BROADWELL), - X86_MATCH_HWP(ANY, 0), + X86_MATCH_HWP(INTEL_BROADWELL_X, INTEL_PSTATE_HWP_BROADWELL), + X86_MATCH_HWP(INTEL_BROADWELL_D, INTEL_PSTATE_HWP_BROADWELL), + X86_MATCH_HWP(INTEL_ANY, 0), {} }; @@ -3407,19 +3635,47 @@ static bool intel_pstate_hwp_is_enabled(void) return !!(value & 0x1); } -static const struct x86_cpu_id intel_epp_balance_perf[] = { +#define POWERSAVE_MASK GENMASK(7, 0) +#define BALANCE_POWER_MASK GENMASK(15, 8) +#define BALANCE_PERFORMANCE_MASK GENMASK(23, 16) +#define PERFORMANCE_MASK GENMASK(31, 24) + +#define HWP_SET_EPP_VALUES(powersave, balance_power, balance_perf, performance) \ + (FIELD_PREP_CONST(POWERSAVE_MASK, powersave) |\ + FIELD_PREP_CONST(BALANCE_POWER_MASK, balance_power) |\ + FIELD_PREP_CONST(BALANCE_PERFORMANCE_MASK, balance_perf) |\ + FIELD_PREP_CONST(PERFORMANCE_MASK, performance)) + +#define HWP_SET_DEF_BALANCE_PERF_EPP(balance_perf) \ + (HWP_SET_EPP_VALUES(HWP_EPP_POWERSAVE, HWP_EPP_BALANCE_POWERSAVE,\ + balance_perf, HWP_EPP_PERFORMANCE)) + +static const struct x86_cpu_id intel_epp_default[] = { /* * Set EPP value as 102, this is the max suggested EPP * which can result in one core turbo frequency for * AlderLake Mobile CPUs. */ - X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, 102), - X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, 32), + X86_MATCH_VFM(INTEL_ALDERLAKE_L, HWP_SET_DEF_BALANCE_PERF_EPP(102)), + X86_MATCH_VFM(INTEL_SAPPHIRERAPIDS_X, HWP_SET_DEF_BALANCE_PERF_EPP(32)), + X86_MATCH_VFM(INTEL_EMERALDRAPIDS_X, HWP_SET_DEF_BALANCE_PERF_EPP(32)), + X86_MATCH_VFM(INTEL_GRANITERAPIDS_X, HWP_SET_DEF_BALANCE_PERF_EPP(32)), + X86_MATCH_VFM(INTEL_GRANITERAPIDS_D, HWP_SET_DEF_BALANCE_PERF_EPP(32)), + X86_MATCH_VFM(INTEL_METEORLAKE_L, HWP_SET_EPP_VALUES(HWP_EPP_POWERSAVE, + 179, 64, 16)), + X86_MATCH_VFM(INTEL_ARROWLAKE, HWP_SET_EPP_VALUES(HWP_EPP_POWERSAVE, + 179, 64, 16)), {} }; static const struct x86_cpu_id intel_hybrid_scaling_factor[] = { - X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE_L, HYBRID_SCALING_FACTOR_MTL), + X86_MATCH_VFM(INTEL_ALDERLAKE, HYBRID_SCALING_FACTOR_ADL), + X86_MATCH_VFM(INTEL_ALDERLAKE_L, HYBRID_SCALING_FACTOR_ADL), + X86_MATCH_VFM(INTEL_RAPTORLAKE, HYBRID_SCALING_FACTOR_ADL), + X86_MATCH_VFM(INTEL_RAPTORLAKE_P, HYBRID_SCALING_FACTOR_ADL), + X86_MATCH_VFM(INTEL_RAPTORLAKE_S, HYBRID_SCALING_FACTOR_ADL), + X86_MATCH_VFM(INTEL_METEORLAKE_L, HYBRID_SCALING_FACTOR_MTL), + X86_MATCH_VFM(INTEL_LUNARLAKE_M, HYBRID_SCALING_FACTOR_LNL), {} }; @@ -3451,7 +3707,7 @@ static int __init intel_pstate_init(void) * deal with it. */ if ((!no_hwp && boot_cpu_has(X86_FEATURE_HWP_EPP)) || hwp_forced) { - WRITE_ONCE(hwp_active, 1); + hwp_active = true; hwp_mode_bdw = id->driver_data; intel_pstate.attr = hwp_cpufreq_attrs; intel_cpufreq.attr = hwp_cpufreq_attrs; @@ -3512,11 +3768,24 @@ hwp_cpu_matched: intel_pstate_sysfs_expose_params(); if (hwp_active) { - const struct x86_cpu_id *id = x86_match_cpu(intel_epp_balance_perf); + const struct x86_cpu_id *id = x86_match_cpu(intel_epp_default); const struct x86_cpu_id *hybrid_id = x86_match_cpu(intel_hybrid_scaling_factor); - if (id) - epp_values[EPP_INDEX_BALANCE_PERFORMANCE] = id->driver_data; + if (id) { + epp_values[EPP_INDEX_POWERSAVE] = + FIELD_GET(POWERSAVE_MASK, id->driver_data); + epp_values[EPP_INDEX_BALANCE_POWERSAVE] = + FIELD_GET(BALANCE_POWER_MASK, id->driver_data); + epp_values[EPP_INDEX_BALANCE_PERFORMANCE] = + FIELD_GET(BALANCE_PERFORMANCE_MASK, id->driver_data); + epp_values[EPP_INDEX_PERFORMANCE] = + FIELD_GET(PERFORMANCE_MASK, id->driver_data); + pr_debug("Updated EPPs powersave:%x balanced power:%x balanced perf:%x performance:%x\n", + epp_values[EPP_INDEX_POWERSAVE], + epp_values[EPP_INDEX_BALANCE_POWERSAVE], + epp_values[EPP_INDEX_BALANCE_PERFORMANCE], + epp_values[EPP_INDEX_PERFORMANCE]); + } if (hybrid_id) { hybrid_scaling_factor = hybrid_id->driver_data; diff --git a/drivers/cpufreq/kirkwood-cpufreq.c b/drivers/cpufreq/kirkwood-cpufreq.c index fd20b986d1f2..312f2654d1d5 100644 --- a/drivers/cpufreq/kirkwood-cpufreq.c +++ b/drivers/cpufreq/kirkwood-cpufreq.c @@ -189,7 +189,7 @@ static void kirkwood_cpufreq_remove(struct platform_device *pdev) static struct platform_driver kirkwood_cpufreq_platform_driver = { .probe = kirkwood_cpufreq_probe, - .remove_new = kirkwood_cpufreq_remove, + .remove = kirkwood_cpufreq_remove, .driver = { .name = "kirkwood-cpufreq", }, diff --git a/drivers/cpufreq/longhaul.c b/drivers/cpufreq/longhaul.c index 4c57c6725c13..bd6fe8638d39 100644 --- a/drivers/cpufreq/longhaul.c +++ b/drivers/cpufreq/longhaul.c @@ -236,8 +236,9 @@ static void do_powersaver(int cx_address, unsigned int mults_index, } /** - * longhaul_set_cpu_frequency() - * @mults_index : bitpattern of the new multiplier. + * longhaul_setstate() + * @policy: cpufreq_policy structure containing the current policy. + * @table_index: index of the frequency within the cpufreq_frequency_table. * * Sets a new clock ratio. */ diff --git a/drivers/cpufreq/loongson2_cpufreq.c b/drivers/cpufreq/loongson2_cpufreq.c index afc59b292153..ed1a6dbad638 100644 --- a/drivers/cpufreq/loongson2_cpufreq.c +++ b/drivers/cpufreq/loongson2_cpufreq.c @@ -85,18 +85,12 @@ static int loongson2_cpufreq_cpu_init(struct cpufreq_policy *policy) return 0; } -static int loongson2_cpufreq_exit(struct cpufreq_policy *policy) -{ - return 0; -} - static struct cpufreq_driver loongson2_cpufreq_driver = { .name = "loongson2", .init = loongson2_cpufreq_cpu_init, .verify = cpufreq_generic_frequency_table_verify, .target_index = loongson2_cpufreq_target, .get = cpufreq_generic_get, - .exit = loongson2_cpufreq_exit, .attr = cpufreq_generic_attr, }; @@ -154,7 +148,9 @@ static int __init cpufreq_init(void) ret = cpufreq_register_driver(&loongson2_cpufreq_driver); - if (!ret && !nowait) { + if (ret) { + platform_driver_unregister(&platform_driver); + } else if (!nowait) { saved_cpu_wait = cpu_wait; cpu_wait = loongson2_cpu_wait; } diff --git a/drivers/cpufreq/loongson3_cpufreq.c b/drivers/cpufreq/loongson3_cpufreq.c new file mode 100644 index 000000000000..bd34bf0fafa5 --- /dev/null +++ b/drivers/cpufreq/loongson3_cpufreq.c @@ -0,0 +1,398 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * CPUFreq driver for the Loongson-3 processors. + * + * All revisions of Loongson-3 processor support cpu_has_scalefreq feature. + * + * Author: Huacai Chen <chenhuacai@loongson.cn> + * Copyright (C) 2024 Loongson Technology Corporation Limited + */ +#include <linux/cpufreq.h> +#include <linux/delay.h> +#include <linux/module.h> +#include <linux/platform_device.h> +#include <linux/units.h> + +#include <asm/idle.h> +#include <asm/loongarch.h> +#include <asm/loongson.h> + +/* Message */ +union smc_message { + u32 value; + struct { + u32 id : 4; + u32 info : 4; + u32 val : 16; + u32 cmd : 6; + u32 extra : 1; + u32 complete : 1; + }; +}; + +/* Command return values */ +#define CMD_OK 0 /* No error */ +#define CMD_ERROR 1 /* Regular error */ +#define CMD_NOCMD 2 /* Command does not support */ +#define CMD_INVAL 3 /* Invalid Parameter */ + +/* Version commands */ +/* + * CMD_GET_VERSION - Get interface version + * Input: none + * Output: version + */ +#define CMD_GET_VERSION 0x1 + +/* Feature commands */ +/* + * CMD_GET_FEATURE - Get feature state + * Input: feature ID + * Output: feature flag + */ +#define CMD_GET_FEATURE 0x2 + +/* + * CMD_SET_FEATURE - Set feature state + * Input: feature ID, feature flag + * output: none + */ +#define CMD_SET_FEATURE 0x3 + +/* Feature IDs */ +#define FEATURE_SENSOR 0 +#define FEATURE_FAN 1 +#define FEATURE_DVFS 2 + +/* Sensor feature flags */ +#define FEATURE_SENSOR_ENABLE BIT(0) +#define FEATURE_SENSOR_SAMPLE BIT(1) + +/* Fan feature flags */ +#define FEATURE_FAN_ENABLE BIT(0) +#define FEATURE_FAN_AUTO BIT(1) + +/* DVFS feature flags */ +#define FEATURE_DVFS_ENABLE BIT(0) +#define FEATURE_DVFS_BOOST BIT(1) +#define FEATURE_DVFS_AUTO BIT(2) +#define FEATURE_DVFS_SINGLE_BOOST BIT(3) + +/* Sensor commands */ +/* + * CMD_GET_SENSOR_NUM - Get number of sensors + * Input: none + * Output: number + */ +#define CMD_GET_SENSOR_NUM 0x4 + +/* + * CMD_GET_SENSOR_STATUS - Get sensor status + * Input: sensor ID, type + * Output: sensor status + */ +#define CMD_GET_SENSOR_STATUS 0x5 + +/* Sensor types */ +#define SENSOR_INFO_TYPE 0 +#define SENSOR_INFO_TYPE_TEMP 1 + +/* Fan commands */ +/* + * CMD_GET_FAN_NUM - Get number of fans + * Input: none + * Output: number + */ +#define CMD_GET_FAN_NUM 0x6 + +/* + * CMD_GET_FAN_INFO - Get fan status + * Input: fan ID, type + * Output: fan info + */ +#define CMD_GET_FAN_INFO 0x7 + +/* + * CMD_SET_FAN_INFO - Set fan status + * Input: fan ID, type, value + * Output: none + */ +#define CMD_SET_FAN_INFO 0x8 + +/* Fan types */ +#define FAN_INFO_TYPE_LEVEL 0 + +/* DVFS commands */ +/* + * CMD_GET_FREQ_LEVEL_NUM - Get number of freq levels + * Input: CPU ID + * Output: number + */ +#define CMD_GET_FREQ_LEVEL_NUM 0x9 + +/* + * CMD_GET_FREQ_BOOST_LEVEL - Get the first boost level + * Input: CPU ID + * Output: number + */ +#define CMD_GET_FREQ_BOOST_LEVEL 0x10 + +/* + * CMD_GET_FREQ_LEVEL_INFO - Get freq level info + * Input: CPU ID, level ID + * Output: level info + */ +#define CMD_GET_FREQ_LEVEL_INFO 0x11 + +/* + * CMD_GET_FREQ_INFO - Get freq info + * Input: CPU ID, type + * Output: freq info + */ +#define CMD_GET_FREQ_INFO 0x12 + +/* + * CMD_SET_FREQ_INFO - Set freq info + * Input: CPU ID, type, value + * Output: none + */ +#define CMD_SET_FREQ_INFO 0x13 + +/* Freq types */ +#define FREQ_INFO_TYPE_FREQ 0 +#define FREQ_INFO_TYPE_LEVEL 1 + +#define FREQ_MAX_LEVEL 16 + +struct loongson3_freq_data { + unsigned int def_freq_level; + struct cpufreq_frequency_table table[]; +}; + +static struct mutex cpufreq_mutex[MAX_PACKAGES]; +static struct cpufreq_driver loongson3_cpufreq_driver; +static DEFINE_PER_CPU(struct loongson3_freq_data *, freq_data); + +static inline int do_service_request(u32 id, u32 info, u32 cmd, u32 val, u32 extra) +{ + int retries; + unsigned int cpu = raw_smp_processor_id(); + unsigned int package = cpu_data[cpu].package; + union smc_message msg, last; + + mutex_lock(&cpufreq_mutex[package]); + + last.value = iocsr_read32(LOONGARCH_IOCSR_SMCMBX); + if (!last.complete) { + mutex_unlock(&cpufreq_mutex[package]); + return -EPERM; + } + + msg.id = id; + msg.info = info; + msg.cmd = cmd; + msg.val = val; + msg.extra = extra; + msg.complete = 0; + + iocsr_write32(msg.value, LOONGARCH_IOCSR_SMCMBX); + iocsr_write32(iocsr_read32(LOONGARCH_IOCSR_MISC_FUNC) | IOCSR_MISC_FUNC_SOFT_INT, + LOONGARCH_IOCSR_MISC_FUNC); + + for (retries = 0; retries < 10000; retries++) { + msg.value = iocsr_read32(LOONGARCH_IOCSR_SMCMBX); + if (msg.complete) + break; + + usleep_range(8, 12); + } + + if (!msg.complete || msg.cmd != CMD_OK) { + mutex_unlock(&cpufreq_mutex[package]); + return -EPERM; + } + + mutex_unlock(&cpufreq_mutex[package]); + + return msg.val; +} + +static unsigned int loongson3_cpufreq_get(unsigned int cpu) +{ + int ret; + + ret = do_service_request(cpu, FREQ_INFO_TYPE_FREQ, CMD_GET_FREQ_INFO, 0, 0); + + return ret * KILO; +} + +static int loongson3_cpufreq_target(struct cpufreq_policy *policy, unsigned int index) +{ + int ret; + + ret = do_service_request(cpu_data[policy->cpu].core, + FREQ_INFO_TYPE_LEVEL, CMD_SET_FREQ_INFO, index, 0); + + return (ret >= 0) ? 0 : ret; +} + +static int configure_freq_table(int cpu) +{ + int i, ret, boost_level, max_level, freq_level; + struct platform_device *pdev = cpufreq_get_driver_data(); + struct loongson3_freq_data *data; + + if (per_cpu(freq_data, cpu)) + return 0; + + ret = do_service_request(cpu, 0, CMD_GET_FREQ_LEVEL_NUM, 0, 0); + if (ret < 0) + return ret; + max_level = ret; + + ret = do_service_request(cpu, 0, CMD_GET_FREQ_BOOST_LEVEL, 0, 0); + if (ret < 0) + return ret; + boost_level = ret; + + freq_level = min(max_level, FREQ_MAX_LEVEL); + data = devm_kzalloc(&pdev->dev, struct_size(data, table, freq_level + 1), GFP_KERNEL); + if (!data) + return -ENOMEM; + + data->def_freq_level = boost_level - 1; + + for (i = 0; i < freq_level; i++) { + ret = do_service_request(cpu, FREQ_INFO_TYPE_FREQ, CMD_GET_FREQ_LEVEL_INFO, i, 0); + if (ret < 0) { + devm_kfree(&pdev->dev, data); + return ret; + } + + data->table[i].frequency = ret * KILO; + data->table[i].flags = (i >= boost_level) ? CPUFREQ_BOOST_FREQ : 0; + } + + data->table[freq_level].flags = 0; + data->table[freq_level].frequency = CPUFREQ_TABLE_END; + + per_cpu(freq_data, cpu) = data; + + return 0; +} + +static int loongson3_cpufreq_cpu_init(struct cpufreq_policy *policy) +{ + int i, ret, cpu = policy->cpu; + + ret = configure_freq_table(cpu); + if (ret < 0) + return ret; + + policy->cpuinfo.transition_latency = 10000; + policy->freq_table = per_cpu(freq_data, cpu)->table; + policy->suspend_freq = policy->freq_table[per_cpu(freq_data, cpu)->def_freq_level].frequency; + cpumask_copy(policy->cpus, topology_sibling_cpumask(cpu)); + + for_each_cpu(i, policy->cpus) { + if (i != cpu) + per_cpu(freq_data, i) = per_cpu(freq_data, cpu); + } + + if (policy_has_boost_freq(policy)) { + ret = cpufreq_enable_boost_support(); + if (ret < 0) { + pr_warn("cpufreq: Failed to enable boost: %d\n", ret); + return ret; + } + loongson3_cpufreq_driver.boost_enabled = true; + } + + return 0; +} + +static void loongson3_cpufreq_cpu_exit(struct cpufreq_policy *policy) +{ + int cpu = policy->cpu; + + loongson3_cpufreq_target(policy, per_cpu(freq_data, cpu)->def_freq_level); +} + +static int loongson3_cpufreq_cpu_online(struct cpufreq_policy *policy) +{ + return 0; +} + +static int loongson3_cpufreq_cpu_offline(struct cpufreq_policy *policy) +{ + return 0; +} + +static struct cpufreq_driver loongson3_cpufreq_driver = { + .name = "loongson3", + .flags = CPUFREQ_CONST_LOOPS, + .init = loongson3_cpufreq_cpu_init, + .exit = loongson3_cpufreq_cpu_exit, + .online = loongson3_cpufreq_cpu_online, + .offline = loongson3_cpufreq_cpu_offline, + .get = loongson3_cpufreq_get, + .target_index = loongson3_cpufreq_target, + .attr = cpufreq_generic_attr, + .verify = cpufreq_generic_frequency_table_verify, + .suspend = cpufreq_generic_suspend, +}; + +static int loongson3_cpufreq_probe(struct platform_device *pdev) +{ + int i, ret; + + for (i = 0; i < MAX_PACKAGES; i++) { + ret = devm_mutex_init(&pdev->dev, &cpufreq_mutex[i]); + if (ret) + return ret; + } + + ret = do_service_request(0, 0, CMD_GET_VERSION, 0, 0); + if (ret <= 0) + return -EPERM; + + ret = do_service_request(FEATURE_DVFS, 0, CMD_SET_FEATURE, + FEATURE_DVFS_ENABLE | FEATURE_DVFS_BOOST, 0); + if (ret < 0) + return -EPERM; + + loongson3_cpufreq_driver.driver_data = pdev; + + ret = cpufreq_register_driver(&loongson3_cpufreq_driver); + if (ret) + return ret; + + pr_info("cpufreq: Loongson-3 CPU frequency driver.\n"); + + return 0; +} + +static void loongson3_cpufreq_remove(struct platform_device *pdev) +{ + cpufreq_unregister_driver(&loongson3_cpufreq_driver); +} + +static struct platform_device_id cpufreq_id_table[] = { + { "loongson3_cpufreq", }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(platform, cpufreq_id_table); + +static struct platform_driver loongson3_platform_driver = { + .driver = { + .name = "loongson3_cpufreq", + }, + .id_table = cpufreq_id_table, + .probe = loongson3_cpufreq_probe, + .remove = loongson3_cpufreq_remove, +}; +module_platform_driver(loongson3_platform_driver); + +MODULE_AUTHOR("Huacai Chen <chenhuacai@loongson.cn>"); +MODULE_DESCRIPTION("CPUFreq driver for Loongson-3 processors"); +MODULE_LICENSE("GPL"); diff --git a/drivers/cpufreq/maple-cpufreq.c b/drivers/cpufreq/maple-cpufreq.c deleted file mode 100644 index f9306410a07f..000000000000 --- a/drivers/cpufreq/maple-cpufreq.c +++ /dev/null @@ -1,241 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (C) 2011 Dmitry Eremin-Solenikov - * Copyright (C) 2002 - 2005 Benjamin Herrenschmidt <benh@kernel.crashing.org> - * and Markus Demleitner <msdemlei@cl.uni-heidelberg.de> - * - * This driver adds basic cpufreq support for SMU & 970FX based G5 Macs, - * that is iMac G5 and latest single CPU desktop. - */ - -#undef DEBUG - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include <linux/module.h> -#include <linux/types.h> -#include <linux/errno.h> -#include <linux/kernel.h> -#include <linux/delay.h> -#include <linux/sched.h> -#include <linux/cpufreq.h> -#include <linux/init.h> -#include <linux/completion.h> -#include <linux/mutex.h> -#include <linux/time.h> -#include <linux/of.h> - -#define DBG(fmt...) pr_debug(fmt) - -/* see 970FX user manual */ - -#define SCOM_PCR 0x0aa001 /* PCR scom addr */ - -#define PCR_HILO_SELECT 0x80000000U /* 1 = PCR, 0 = PCRH */ -#define PCR_SPEED_FULL 0x00000000U /* 1:1 speed value */ -#define PCR_SPEED_HALF 0x00020000U /* 1:2 speed value */ -#define PCR_SPEED_QUARTER 0x00040000U /* 1:4 speed value */ -#define PCR_SPEED_MASK 0x000e0000U /* speed mask */ -#define PCR_SPEED_SHIFT 17 -#define PCR_FREQ_REQ_VALID 0x00010000U /* freq request valid */ -#define PCR_VOLT_REQ_VALID 0x00008000U /* volt request valid */ -#define PCR_TARGET_TIME_MASK 0x00006000U /* target time */ -#define PCR_STATLAT_MASK 0x00001f00U /* STATLAT value */ -#define PCR_SNOOPLAT_MASK 0x000000f0U /* SNOOPLAT value */ -#define PCR_SNOOPACC_MASK 0x0000000fU /* SNOOPACC value */ - -#define SCOM_PSR 0x408001 /* PSR scom addr */ -/* warning: PSR is a 64 bits register */ -#define PSR_CMD_RECEIVED 0x2000000000000000U /* command received */ -#define PSR_CMD_COMPLETED 0x1000000000000000U /* command completed */ -#define PSR_CUR_SPEED_MASK 0x0300000000000000U /* current speed */ -#define PSR_CUR_SPEED_SHIFT (56) - -/* - * The G5 only supports two frequencies (Quarter speed is not supported) - */ -#define CPUFREQ_HIGH 0 -#define CPUFREQ_LOW 1 - -static struct cpufreq_frequency_table maple_cpu_freqs[] = { - {0, CPUFREQ_HIGH, 0}, - {0, CPUFREQ_LOW, 0}, - {0, 0, CPUFREQ_TABLE_END}, -}; - -/* Power mode data is an array of the 32 bits PCR values to use for - * the various frequencies, retrieved from the device-tree - */ -static int maple_pmode_cur; - -static const u32 *maple_pmode_data; -static int maple_pmode_max; - -/* - * SCOM based frequency switching for 970FX rev3 - */ -static int maple_scom_switch_freq(int speed_mode) -{ - unsigned long flags; - int to; - - local_irq_save(flags); - - /* Clear PCR high */ - scom970_write(SCOM_PCR, 0); - /* Clear PCR low */ - scom970_write(SCOM_PCR, PCR_HILO_SELECT | 0); - /* Set PCR low */ - scom970_write(SCOM_PCR, PCR_HILO_SELECT | - maple_pmode_data[speed_mode]); - - /* Wait for completion */ - for (to = 0; to < 10; to++) { - unsigned long psr = scom970_read(SCOM_PSR); - - if ((psr & PSR_CMD_RECEIVED) == 0 && - (((psr >> PSR_CUR_SPEED_SHIFT) ^ - (maple_pmode_data[speed_mode] >> PCR_SPEED_SHIFT)) & 0x3) - == 0) - break; - if (psr & PSR_CMD_COMPLETED) - break; - udelay(100); - } - - local_irq_restore(flags); - - maple_pmode_cur = speed_mode; - ppc_proc_freq = maple_cpu_freqs[speed_mode].frequency * 1000ul; - - return 0; -} - -static int maple_scom_query_freq(void) -{ - unsigned long psr = scom970_read(SCOM_PSR); - int i; - - for (i = 0; i <= maple_pmode_max; i++) - if ((((psr >> PSR_CUR_SPEED_SHIFT) ^ - (maple_pmode_data[i] >> PCR_SPEED_SHIFT)) & 0x3) == 0) - break; - return i; -} - -/* - * Common interface to the cpufreq core - */ - -static int maple_cpufreq_target(struct cpufreq_policy *policy, - unsigned int index) -{ - return maple_scom_switch_freq(index); -} - -static unsigned int maple_cpufreq_get_speed(unsigned int cpu) -{ - return maple_cpu_freqs[maple_pmode_cur].frequency; -} - -static int maple_cpufreq_cpu_init(struct cpufreq_policy *policy) -{ - cpufreq_generic_init(policy, maple_cpu_freqs, 12000); - return 0; -} - -static struct cpufreq_driver maple_cpufreq_driver = { - .name = "maple", - .flags = CPUFREQ_CONST_LOOPS, - .init = maple_cpufreq_cpu_init, - .verify = cpufreq_generic_frequency_table_verify, - .target_index = maple_cpufreq_target, - .get = maple_cpufreq_get_speed, - .attr = cpufreq_generic_attr, -}; - -static int __init maple_cpufreq_init(void) -{ - struct device_node *cpunode; - unsigned int psize; - unsigned long max_freq; - const u32 *valp; - u32 pvr_hi; - int rc = -ENODEV; - - /* - * Behave here like powermac driver which checks machine compatibility - * to ease merging of two drivers in future. - */ - if (!of_machine_is_compatible("Momentum,Maple") && - !of_machine_is_compatible("Momentum,Apache")) - return 0; - - /* Get first CPU node */ - cpunode = of_cpu_device_node_get(0); - if (cpunode == NULL) { - pr_err("Can't find any CPU 0 node\n"); - goto bail_noprops; - } - - /* Check 970FX for now */ - /* we actually don't care on which CPU to access PVR */ - pvr_hi = PVR_VER(mfspr(SPRN_PVR)); - if (pvr_hi != 0x3c && pvr_hi != 0x44) { - pr_err("Unsupported CPU version (%x)\n", pvr_hi); - goto bail_noprops; - } - - /* Look for the powertune data in the device-tree */ - /* - * On Maple this property is provided by PIBS in dual-processor config, - * not provided by PIBS in CPU0 config and also not provided by SLOF, - * so YMMV - */ - maple_pmode_data = of_get_property(cpunode, "power-mode-data", &psize); - if (!maple_pmode_data) { - DBG("No power-mode-data !\n"); - goto bail_noprops; - } - maple_pmode_max = psize / sizeof(u32) - 1; - - /* - * From what I see, clock-frequency is always the maximal frequency. - * The current driver can not slew sysclk yet, so we really only deal - * with powertune steps for now. We also only implement full freq and - * half freq in this version. So far, I haven't yet seen a machine - * supporting anything else. - */ - valp = of_get_property(cpunode, "clock-frequency", NULL); - if (!valp) - goto bail_noprops; - max_freq = (*valp)/1000; - maple_cpu_freqs[0].frequency = max_freq; - maple_cpu_freqs[1].frequency = max_freq/2; - - /* Force apply current frequency to make sure everything is in - * sync (voltage is right for example). Firmware may leave us with - * a strange setting ... - */ - msleep(10); - maple_pmode_cur = -1; - maple_scom_switch_freq(maple_scom_query_freq()); - - pr_info("Registering Maple CPU frequency driver\n"); - pr_info("Low: %d Mhz, High: %d Mhz, Cur: %d MHz\n", - maple_cpu_freqs[1].frequency/1000, - maple_cpu_freqs[0].frequency/1000, - maple_cpu_freqs[maple_pmode_cur].frequency/1000); - - rc = cpufreq_register_driver(&maple_cpufreq_driver); - -bail_noprops: - of_node_put(cpunode); - - return rc; -} - -module_init(maple_cpufreq_init); - - -MODULE_LICENSE("GPL"); diff --git a/drivers/cpufreq/mediatek-cpufreq-hw.c b/drivers/cpufreq/mediatek-cpufreq-hw.c index d46afb3c0092..9252ebd60373 100644 --- a/drivers/cpufreq/mediatek-cpufreq-hw.c +++ b/drivers/cpufreq/mediatek-cpufreq-hw.c @@ -13,6 +13,7 @@ #include <linux/of.h> #include <linux/of_platform.h> #include <linux/platform_device.h> +#include <linux/regulator/consumer.h> #include <linux/slab.h> #define LUT_MAX_ENTRIES 32U @@ -61,7 +62,7 @@ mtk_cpufreq_get_cpu_power(struct device *cpu_dev, unsigned long *uW, policy = cpufreq_cpu_get_raw(cpu_dev->id); if (!policy) - return 0; + return -EINVAL; data = policy->driver_data; @@ -259,7 +260,7 @@ static int mtk_cpufreq_hw_cpu_init(struct cpufreq_policy *policy) return 0; } -static int mtk_cpufreq_hw_cpu_exit(struct cpufreq_policy *policy) +static void mtk_cpufreq_hw_cpu_exit(struct cpufreq_policy *policy) { struct mtk_cpufreq_data *data = policy->driver_data; struct resource *res = data->res; @@ -269,8 +270,6 @@ static int mtk_cpufreq_hw_cpu_exit(struct cpufreq_policy *policy) writel_relaxed(0x0, data->reg_bases[REG_FREQ_ENABLE]); iounmap(base); release_mem_region(res->start, resource_size(res)); - - return 0; } static void mtk_cpufreq_register_em(struct cpufreq_policy *policy) @@ -300,7 +299,23 @@ static struct cpufreq_driver cpufreq_mtk_hw_driver = { static int mtk_cpufreq_hw_driver_probe(struct platform_device *pdev) { const void *data; - int ret; + int ret, cpu; + struct device *cpu_dev; + struct regulator *cpu_reg; + + /* Make sure that all CPU supplies are available before proceeding. */ + for_each_possible_cpu(cpu) { + cpu_dev = get_cpu_device(cpu); + if (!cpu_dev) + return dev_err_probe(&pdev->dev, -EPROBE_DEFER, + "Failed to get cpu%d device\n", cpu); + + cpu_reg = devm_regulator_get(cpu_dev, "cpu"); + if (IS_ERR(cpu_reg)) + return dev_err_probe(&pdev->dev, PTR_ERR(cpu_reg), + "CPU%d regulator get failed\n", cpu); + } + data = of_device_get_match_data(&pdev->dev); if (!data) @@ -329,7 +344,7 @@ MODULE_DEVICE_TABLE(of, mtk_cpufreq_hw_match); static struct platform_driver mtk_cpufreq_hw_driver = { .probe = mtk_cpufreq_hw_driver_probe, - .remove_new = mtk_cpufreq_hw_driver_remove, + .remove = mtk_cpufreq_hw_driver_remove, .driver = { .name = "mtk-cpufreq-hw", .of_match_table = mtk_cpufreq_hw_match, diff --git a/drivers/cpufreq/mediatek-cpufreq.c b/drivers/cpufreq/mediatek-cpufreq.c index a0a61919bc4c..663f61565cf7 100644 --- a/drivers/cpufreq/mediatek-cpufreq.c +++ b/drivers/cpufreq/mediatek-cpufreq.c @@ -390,28 +390,23 @@ static int mtk_cpu_dvfs_info_init(struct mtk_cpu_dvfs_info *info, int cpu) int ret; cpu_dev = get_cpu_device(cpu); - if (!cpu_dev) { - dev_err(cpu_dev, "failed to get cpu%d device\n", cpu); - return -ENODEV; - } + if (!cpu_dev) + return dev_err_probe(cpu_dev, -ENODEV, "failed to get cpu%d device\n", cpu); info->cpu_dev = cpu_dev; info->ccifreq_bound = false; if (info->soc_data->ccifreq_supported) { info->cci_dev = of_get_cci(info->cpu_dev); - if (IS_ERR(info->cci_dev)) { - ret = PTR_ERR(info->cci_dev); - dev_err(cpu_dev, "cpu%d: failed to get cci device\n", cpu); - return -ENODEV; - } + if (IS_ERR(info->cci_dev)) + return dev_err_probe(cpu_dev, PTR_ERR(info->cci_dev), + "cpu%d: failed to get cci device\n", + cpu); } info->cpu_clk = clk_get(cpu_dev, "cpu"); - if (IS_ERR(info->cpu_clk)) { - ret = PTR_ERR(info->cpu_clk); - return dev_err_probe(cpu_dev, ret, + if (IS_ERR(info->cpu_clk)) + return dev_err_probe(cpu_dev, PTR_ERR(info->cpu_clk), "cpu%d: failed to get cpu clk\n", cpu); - } info->inter_clk = clk_get(cpu_dev, "intermediate"); if (IS_ERR(info->inter_clk)) { @@ -431,7 +426,7 @@ static int mtk_cpu_dvfs_info_init(struct mtk_cpu_dvfs_info *info, int cpu) ret = regulator_enable(info->proc_reg); if (ret) { - dev_warn(cpu_dev, "cpu%d: failed to enable vproc\n", cpu); + dev_err_probe(cpu_dev, ret, "cpu%d: failed to enable vproc\n", cpu); goto out_free_proc_reg; } @@ -439,14 +434,17 @@ static int mtk_cpu_dvfs_info_init(struct mtk_cpu_dvfs_info *info, int cpu) info->sram_reg = regulator_get_optional(cpu_dev, "sram"); if (IS_ERR(info->sram_reg)) { ret = PTR_ERR(info->sram_reg); - if (ret == -EPROBE_DEFER) + if (ret == -EPROBE_DEFER) { + dev_err_probe(cpu_dev, ret, + "cpu%d: Failed to get sram regulator\n", cpu); goto out_disable_proc_reg; + } info->sram_reg = NULL; } else { ret = regulator_enable(info->sram_reg); if (ret) { - dev_warn(cpu_dev, "cpu%d: failed to enable vsram\n", cpu); + dev_err_probe(cpu_dev, ret, "cpu%d: failed to enable vsram\n", cpu); goto out_free_sram_reg; } } @@ -454,31 +452,34 @@ static int mtk_cpu_dvfs_info_init(struct mtk_cpu_dvfs_info *info, int cpu) /* Get OPP-sharing information from "operating-points-v2" bindings */ ret = dev_pm_opp_of_get_sharing_cpus(cpu_dev, &info->cpus); if (ret) { - dev_err(cpu_dev, + dev_err_probe(cpu_dev, ret, "cpu%d: failed to get OPP-sharing information\n", cpu); goto out_disable_sram_reg; } ret = dev_pm_opp_of_cpumask_add_table(&info->cpus); if (ret) { - dev_warn(cpu_dev, "cpu%d: no OPP table\n", cpu); + dev_err_probe(cpu_dev, ret, "cpu%d: no OPP table\n", cpu); goto out_disable_sram_reg; } ret = clk_prepare_enable(info->cpu_clk); - if (ret) + if (ret) { + dev_err_probe(cpu_dev, ret, "cpu%d: failed to enable cpu clk\n", cpu); goto out_free_opp_table; + } ret = clk_prepare_enable(info->inter_clk); - if (ret) + if (ret) { + dev_err_probe(cpu_dev, ret, "cpu%d: failed to enable inter clk\n", cpu); goto out_disable_mux_clock; + } if (info->soc_data->ccifreq_supported) { info->vproc_on_boot = regulator_get_voltage(info->proc_reg); if (info->vproc_on_boot < 0) { - ret = info->vproc_on_boot; - dev_err(info->cpu_dev, - "invalid Vproc value: %d\n", info->vproc_on_boot); + ret = dev_err_probe(info->cpu_dev, info->vproc_on_boot, + "invalid Vproc value\n"); goto out_disable_inter_clock; } } @@ -487,8 +488,8 @@ static int mtk_cpu_dvfs_info_init(struct mtk_cpu_dvfs_info *info, int cpu) rate = clk_get_rate(info->inter_clk); opp = dev_pm_opp_find_freq_ceil(cpu_dev, &rate); if (IS_ERR(opp)) { - dev_err(cpu_dev, "cpu%d: failed to get intermediate opp\n", cpu); - ret = PTR_ERR(opp); + ret = dev_err_probe(cpu_dev, PTR_ERR(opp), + "cpu%d: failed to get intermediate opp\n", cpu); goto out_disable_inter_clock; } info->intermediate_voltage = dev_pm_opp_get_voltage(opp); @@ -501,7 +502,7 @@ static int mtk_cpu_dvfs_info_init(struct mtk_cpu_dvfs_info *info, int cpu) info->opp_nb.notifier_call = mtk_cpufreq_opp_notifier; ret = dev_pm_opp_register_notifier(cpu_dev, &info->opp_nb); if (ret) { - dev_err(cpu_dev, "cpu%d: failed to register opp notifier\n", cpu); + dev_err_probe(cpu_dev, ret, "cpu%d: failed to register opp notifier\n", cpu); goto out_disable_inter_clock; } @@ -599,13 +600,11 @@ static int mtk_cpufreq_init(struct cpufreq_policy *policy) return 0; } -static int mtk_cpufreq_exit(struct cpufreq_policy *policy) +static void mtk_cpufreq_exit(struct cpufreq_policy *policy) { struct mtk_cpu_dvfs_info *info = policy->driver_data; dev_pm_opp_free_cpufreq_table(info->cpu_dev, &policy->freq_table); - - return 0; } static struct cpufreq_driver mtk_cpufreq_driver = { @@ -629,11 +628,9 @@ static int mtk_cpufreq_probe(struct platform_device *pdev) int cpu, ret; data = dev_get_platdata(&pdev->dev); - if (!data) { - dev_err(&pdev->dev, - "failed to get mtk cpufreq platform data\n"); - return -ENODEV; - } + if (!data) + return dev_err_probe(&pdev->dev, -ENODEV, + "failed to get mtk cpufreq platform data\n"); for_each_possible_cpu(cpu) { info = mtk_cpu_dvfs_info_lookup(cpu); @@ -642,25 +639,22 @@ static int mtk_cpufreq_probe(struct platform_device *pdev) info = devm_kzalloc(&pdev->dev, sizeof(*info), GFP_KERNEL); if (!info) { - ret = -ENOMEM; + ret = dev_err_probe(&pdev->dev, -ENOMEM, + "Failed to allocate dvfs_info\n"); goto release_dvfs_info_list; } info->soc_data = data; ret = mtk_cpu_dvfs_info_init(info, cpu); - if (ret) { - dev_err(&pdev->dev, - "failed to initialize dvfs info for cpu%d\n", - cpu); + if (ret) goto release_dvfs_info_list; - } list_add(&info->list_head, &dvfs_info_list); } ret = cpufreq_register_driver(&mtk_cpufreq_driver); if (ret) { - dev_err(&pdev->dev, "failed to register mtk cpufreq driver\n"); + dev_err_probe(&pdev->dev, ret, "failed to register mtk cpufreq driver\n"); goto release_dvfs_info_list; } @@ -707,6 +701,15 @@ static const struct mtk_cpufreq_platform_data mt7623_platform_data = { .ccifreq_supported = false, }; +static const struct mtk_cpufreq_platform_data mt7988_platform_data = { + .min_volt_shift = 100000, + .max_volt_shift = 200000, + .proc_max_volt = 900000, + .sram_min_volt = 0, + .sram_max_volt = 1150000, + .ccifreq_supported = true, +}; + static const struct mtk_cpufreq_platform_data mt8183_platform_data = { .min_volt_shift = 100000, .max_volt_shift = 200000, @@ -735,11 +738,12 @@ static const struct mtk_cpufreq_platform_data mt8516_platform_data = { }; /* List of machines supported by this driver */ -static const struct of_device_id mtk_cpufreq_machines[] __initconst = { +static const struct of_device_id mtk_cpufreq_machines[] __initconst __maybe_unused = { { .compatible = "mediatek,mt2701", .data = &mt2701_platform_data }, { .compatible = "mediatek,mt2712", .data = &mt2701_platform_data }, { .compatible = "mediatek,mt7622", .data = &mt7622_platform_data }, { .compatible = "mediatek,mt7623", .data = &mt7623_platform_data }, + { .compatible = "mediatek,mt7988a", .data = &mt7988_platform_data }, { .compatible = "mediatek,mt8167", .data = &mt8516_platform_data }, { .compatible = "mediatek,mt817x", .data = &mt2701_platform_data }, { .compatible = "mediatek,mt8173", .data = &mt2701_platform_data }, diff --git a/drivers/cpufreq/omap-cpufreq.c b/drivers/cpufreq/omap-cpufreq.c index 895690856665..106220c0fd11 100644 --- a/drivers/cpufreq/omap-cpufreq.c +++ b/drivers/cpufreq/omap-cpufreq.c @@ -28,9 +28,6 @@ #include <linux/platform_device.h> #include <linux/regulator/consumer.h> -#include <asm/smp_plat.h> -#include <asm/cpu.h> - /* OPP tolerance in percentage */ #define OPP_TOLERANCE 4 @@ -135,11 +132,10 @@ static int omap_cpu_init(struct cpufreq_policy *policy) return 0; } -static int omap_cpu_exit(struct cpufreq_policy *policy) +static void omap_cpu_exit(struct cpufreq_policy *policy) { freq_table_free(); clk_put(policy->clk); - return 0; } static struct cpufreq_driver omap_driver = { @@ -192,7 +188,7 @@ static struct platform_driver omap_cpufreq_platdrv = { .name = "omap-cpufreq", }, .probe = omap_cpufreq_probe, - .remove_new = omap_cpufreq_remove, + .remove = omap_cpufreq_remove, }; module_platform_driver(omap_cpufreq_platdrv); diff --git a/drivers/cpufreq/pasemi-cpufreq.c b/drivers/cpufreq/pasemi-cpufreq.c index 039a66bbe1be..5fc9cb480516 100644 --- a/drivers/cpufreq/pasemi-cpufreq.c +++ b/drivers/cpufreq/pasemi-cpufreq.c @@ -204,21 +204,19 @@ out: return err; } -static int pas_cpufreq_cpu_exit(struct cpufreq_policy *policy) +static void pas_cpufreq_cpu_exit(struct cpufreq_policy *policy) { /* * We don't support CPU hotplug. Don't unmap after the system * has already made it to a running state. */ if (system_state >= SYSTEM_RUNNING) - return 0; + return; if (sdcasr_mapbase) iounmap(sdcasr_mapbase); if (sdcpwr_mapbase) iounmap(sdcpwr_mapbase); - - return 0; } static int pas_cpufreq_target(struct cpufreq_policy *policy, @@ -271,5 +269,6 @@ static void __exit pas_cpufreq_exit(void) module_init(pas_cpufreq_init); module_exit(pas_cpufreq_exit); +MODULE_DESCRIPTION("cpufreq driver for PA Semi PWRficient"); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Egor Martovetsky <egor@pasemi.com>, Olof Johansson <olof@lixom.net>"); diff --git a/drivers/cpufreq/pcc-cpufreq.c b/drivers/cpufreq/pcc-cpufreq.c index 6f8b5ea7aeae..ac2e90a65f0c 100644 --- a/drivers/cpufreq/pcc-cpufreq.c +++ b/drivers/cpufreq/pcc-cpufreq.c @@ -562,18 +562,12 @@ out: return result; } -static int pcc_cpufreq_cpu_exit(struct cpufreq_policy *policy) -{ - return 0; -} - static struct cpufreq_driver pcc_cpufreq_driver = { .flags = CPUFREQ_CONST_LOOPS, .get = pcc_get_freq, .verify = pcc_cpufreq_verify, .target = pcc_cpufreq_target, .init = pcc_cpufreq_cpu_init, - .exit = pcc_cpufreq_cpu_exit, .name = "pcc-cpufreq", }; @@ -621,7 +615,7 @@ static struct platform_driver pcc_cpufreq_platdrv = { .driver = { .name = "pcc-cpufreq", }, - .remove_new = pcc_cpufreq_remove, + .remove = pcc_cpufreq_remove, }; static int __init pcc_cpufreq_init(void) diff --git a/drivers/cpufreq/pmac32-cpufreq.c b/drivers/cpufreq/pmac32-cpufreq.c index df3567c1e93b..6c9f0888a2a7 100644 --- a/drivers/cpufreq/pmac32-cpufreq.c +++ b/drivers/cpufreq/pmac32-cpufreq.c @@ -120,9 +120,9 @@ static int cpu_750fx_cpu_speed(int low_speed) /* tweak L2 for high voltage */ if (has_cpu_l2lve) { - hid2 = mfspr(SPRN_HID2); + hid2 = mfspr(SPRN_HID2_750FX); hid2 &= ~0x2000; - mtspr(SPRN_HID2, hid2); + mtspr(SPRN_HID2_750FX, hid2); } } #ifdef CONFIG_PPC_BOOK3S_32 @@ -131,9 +131,9 @@ static int cpu_750fx_cpu_speed(int low_speed) if (low_speed == 1) { /* tweak L2 for low voltage */ if (has_cpu_l2lve) { - hid2 = mfspr(SPRN_HID2); + hid2 = mfspr(SPRN_HID2_750FX); hid2 |= 0x2000; - mtspr(SPRN_HID2, hid2); + mtspr(SPRN_HID2_750FX, hid2); } /* ramping down, set voltage last */ diff --git a/drivers/cpufreq/pmac64-cpufreq.c b/drivers/cpufreq/pmac64-cpufreq.c index 2cd2b06849a2..74ff6c47df29 100644 --- a/drivers/cpufreq/pmac64-cpufreq.c +++ b/drivers/cpufreq/pmac64-cpufreq.c @@ -505,7 +505,7 @@ static int __init g5_pm72_cpufreq_init(struct device_node *cpunode) continue; if (strcmp(loc, "CPU CLOCK")) continue; - if (!of_get_property(hwclock, "platform-get-frequency", NULL)) + if (!of_property_present(hwclock, "platform-get-frequency")) continue; break; } @@ -671,4 +671,5 @@ static int __init g5_cpufreq_init(void) module_init(g5_cpufreq_init); +MODULE_DESCRIPTION("cpufreq driver for SMU & 970FX based G5 Macs"); MODULE_LICENSE("GPL"); diff --git a/drivers/cpufreq/powernow-k6.c b/drivers/cpufreq/powernow-k6.c index 41eefef95d87..f0a4a6c31204 100644 --- a/drivers/cpufreq/powernow-k6.c +++ b/drivers/cpufreq/powernow-k6.c @@ -219,7 +219,7 @@ have_busfreq: } -static int powernow_k6_cpu_exit(struct cpufreq_policy *policy) +static void powernow_k6_cpu_exit(struct cpufreq_policy *policy) { unsigned int i; @@ -234,10 +234,9 @@ static int powernow_k6_cpu_exit(struct cpufreq_policy *policy) cpufreq_freq_transition_begin(policy, &freqs); powernow_k6_target(policy, i); cpufreq_freq_transition_end(policy, &freqs, 0); - break; + return; } } - return 0; } static unsigned int powernow_k6_get(unsigned int cpu) diff --git a/drivers/cpufreq/powernow-k7.c b/drivers/cpufreq/powernow-k7.c index 5d515fc34836..4271446c8725 100644 --- a/drivers/cpufreq/powernow-k7.c +++ b/drivers/cpufreq/powernow-k7.c @@ -644,7 +644,7 @@ static int powernow_cpu_init(struct cpufreq_policy *policy) return 0; } -static int powernow_cpu_exit(struct cpufreq_policy *policy) +static void powernow_cpu_exit(struct cpufreq_policy *policy) { #ifdef CONFIG_X86_POWERNOW_K7_ACPI if (acpi_processor_perf) { @@ -655,7 +655,6 @@ static int powernow_cpu_exit(struct cpufreq_policy *policy) #endif kfree(powernow_table); - return 0; } static struct cpufreq_driver powernow_driver = { diff --git a/drivers/cpufreq/powernow-k8.c b/drivers/cpufreq/powernow-k8.c index b10f7a1b77f1..a01170f7d01c 100644 --- a/drivers/cpufreq/powernow-k8.c +++ b/drivers/cpufreq/powernow-k8.c @@ -1089,13 +1089,13 @@ err_out: return -ENODEV; } -static int powernowk8_cpu_exit(struct cpufreq_policy *pol) +static void powernowk8_cpu_exit(struct cpufreq_policy *pol) { struct powernow_k8_data *data = per_cpu(powernow_data, pol->cpu); int cpu; if (!data) - return -EINVAL; + return; powernow_k8_cpu_exit_acpi(data); @@ -1104,8 +1104,6 @@ static int powernowk8_cpu_exit(struct cpufreq_policy *pol) /* pol->cpus will be empty here, use related_cpus instead. */ for_each_cpu(cpu, pol->related_cpus) per_cpu(powernow_data, cpu) = NULL; - - return 0; } static void query_values_on_cpu(void *_err) diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c index fddbd1ea1635..ae79d909943b 100644 --- a/drivers/cpufreq/powernv-cpufreq.c +++ b/drivers/cpufreq/powernv-cpufreq.c @@ -18,6 +18,7 @@ #include <linux/of.h> #include <linux/reboot.h> #include <linux/slab.h> +#include <linux/string_choices.h> #include <linux/cpu.h> #include <linux/hashtable.h> #include <trace/events/power.h> @@ -281,7 +282,7 @@ next: pr_info("cpufreq pstate min 0x%x nominal 0x%x max 0x%x\n", pstate_min, pstate_nominal, pstate_max); pr_info("Workload Optimized Frequency is %s in the platform\n", - (powernv_pstate_info.wof_enabled) ? "enabled" : "disabled"); + str_enabled_disabled(powernv_pstate_info.wof_enabled)); pstate_ids = of_get_property(power_mgt, "ibm,pstate-ids", &len_ids); if (!pstate_ids) { @@ -692,7 +693,7 @@ static void gpstate_timer_handler(struct timer_list *t) } /* - * If PMCR was last updated was using fast_swtich then + * If PMCR was last updated was using fast_switch then * We may have wrong in gpstate->last_lpstate_idx * value. Hence, read from PMCR to get correct data. */ @@ -874,7 +875,7 @@ static int powernv_cpufreq_cpu_init(struct cpufreq_policy *policy) return 0; } -static int powernv_cpufreq_cpu_exit(struct cpufreq_policy *policy) +static void powernv_cpufreq_cpu_exit(struct cpufreq_policy *policy) { struct powernv_smp_call_data freq_data; struct global_pstate_info *gpstates = policy->driver_data; @@ -886,8 +887,6 @@ static int powernv_cpufreq_cpu_exit(struct cpufreq_policy *policy) del_timer_sync(&gpstates->timer); kfree(policy->driver_data); - - return 0; } static int powernv_cpufreq_reboot_notifier(struct notifier_block *nb, @@ -1162,5 +1161,6 @@ static void __exit powernv_cpufreq_exit(void) } module_exit(powernv_cpufreq_exit); +MODULE_DESCRIPTION("cpufreq driver for IBM/OpenPOWER powernv systems"); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Vaidyanathan Srinivasan <svaidy at linux.vnet.ibm.com>"); diff --git a/drivers/cpufreq/ppc_cbe_cpufreq.c b/drivers/cpufreq/ppc_cbe_cpufreq.c index 88afc49941b7..98595b3ea13f 100644 --- a/drivers/cpufreq/ppc_cbe_cpufreq.c +++ b/drivers/cpufreq/ppc_cbe_cpufreq.c @@ -113,10 +113,9 @@ static int cbe_cpufreq_cpu_init(struct cpufreq_policy *policy) return 0; } -static int cbe_cpufreq_cpu_exit(struct cpufreq_policy *policy) +static void cbe_cpufreq_cpu_exit(struct cpufreq_policy *policy) { cbe_cpufreq_pmi_policy_exit(policy); - return 0; } static int cbe_cpufreq_target(struct cpufreq_policy *policy, @@ -169,5 +168,6 @@ static void __exit cbe_cpufreq_exit(void) module_init(cbe_cpufreq_init); module_exit(cbe_cpufreq_exit); +MODULE_DESCRIPTION("cpufreq driver for Cell BE processors"); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Christian Krafft <krafft@de.ibm.com>"); diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c index 70b0f21968a0..b2e7e89feaac 100644 --- a/drivers/cpufreq/qcom-cpufreq-hw.c +++ b/drivers/cpufreq/qcom-cpufreq-hw.c @@ -9,6 +9,7 @@ #include <linux/init.h> #include <linux/interconnect.h> #include <linux/interrupt.h> +#include <linux/io.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/of.h> @@ -142,14 +143,12 @@ static unsigned long qcom_lmh_get_throttle_freq(struct qcom_cpufreq_data *data) } /* Get the frequency requested by the cpufreq core for the CPU */ -static unsigned int qcom_cpufreq_get_freq(unsigned int cpu) +static unsigned int qcom_cpufreq_get_freq(struct cpufreq_policy *policy) { struct qcom_cpufreq_data *data; const struct qcom_cpufreq_soc_data *soc_data; - struct cpufreq_policy *policy; unsigned int index; - policy = cpufreq_cpu_get_raw(cpu); if (!policy) return 0; @@ -162,12 +161,10 @@ static unsigned int qcom_cpufreq_get_freq(unsigned int cpu) return policy->freq_table[index].frequency; } -static unsigned int qcom_cpufreq_hw_get(unsigned int cpu) +static unsigned int __qcom_cpufreq_hw_get(struct cpufreq_policy *policy) { struct qcom_cpufreq_data *data; - struct cpufreq_policy *policy; - policy = cpufreq_cpu_get_raw(cpu); if (!policy) return 0; @@ -176,7 +173,12 @@ static unsigned int qcom_cpufreq_hw_get(unsigned int cpu) if (data->throttle_irq >= 0) return qcom_lmh_get_throttle_freq(data) / HZ_PER_KHZ; - return qcom_cpufreq_get_freq(cpu); + return qcom_cpufreq_get_freq(policy); +} + +static unsigned int qcom_cpufreq_hw_get(unsigned int cpu) +{ + return __qcom_cpufreq_hw_get(cpufreq_cpu_get_raw(cpu)); } static unsigned int qcom_cpufreq_hw_fast_switch(struct cpufreq_policy *policy, @@ -347,8 +349,8 @@ static void qcom_lmh_dcvs_notify(struct qcom_cpufreq_data *data) throttled_freq = freq_hz / HZ_PER_KHZ; - /* Update thermal pressure (the boost frequencies are accepted) */ - arch_update_thermal_pressure(policy->related_cpus, throttled_freq); + /* Update HW pressure (the boost frequencies are accepted) */ + arch_update_hw_pressure(policy->related_cpus, throttled_freq); /* * In the unlikely case policy is unregistered do not enable @@ -362,7 +364,7 @@ static void qcom_lmh_dcvs_notify(struct qcom_cpufreq_data *data) * If h/w throttled frequency is higher than what cpufreq has requested * for, then stop polling and switch back to interrupt mechanism. */ - if (throttled_freq >= qcom_cpufreq_get_freq(cpu)) + if (throttled_freq >= qcom_cpufreq_get_freq(cpufreq_cpu_get_raw(cpu))) enable_irq(data->throttle_irq); else mod_delayed_work(system_highpri_wq, &data->throttle_work, @@ -440,7 +442,6 @@ static int qcom_cpufreq_hw_lmh_init(struct cpufreq_policy *policy, int index) return data->throttle_irq; data->cancel_throttle = false; - data->policy = policy; mutex_init(&data->throttle_lock); INIT_DEFERRABLE_WORK(&data->throttle_work, qcom_lmh_dcvs_poll); @@ -551,6 +552,7 @@ static int qcom_cpufreq_hw_cpu_init(struct cpufreq_policy *policy) policy->driver_data = data; policy->dvfs_possible_from_any_cpu = true; + data->policy = policy; ret = qcom_cpufreq_hw_read_lut(cpu_dev, policy); if (ret) { @@ -573,7 +575,7 @@ static int qcom_cpufreq_hw_cpu_init(struct cpufreq_policy *policy) return qcom_cpufreq_hw_lmh_init(policy, index); } -static int qcom_cpufreq_hw_cpu_exit(struct cpufreq_policy *policy) +static void qcom_cpufreq_hw_cpu_exit(struct cpufreq_policy *policy) { struct device *cpu_dev = get_cpu_device(policy->cpu); struct qcom_cpufreq_data *data = policy->driver_data; @@ -583,8 +585,6 @@ static int qcom_cpufreq_hw_cpu_exit(struct cpufreq_policy *policy) qcom_cpufreq_hw_lmh_exit(data); kfree(policy->freq_table); kfree(data); - - return 0; } static void qcom_cpufreq_ready(struct cpufreq_policy *policy) @@ -623,11 +623,24 @@ static unsigned long qcom_cpufreq_hw_recalc_rate(struct clk_hw *hw, unsigned lon { struct qcom_cpufreq_data *data = container_of(hw, struct qcom_cpufreq_data, cpu_clk); - return qcom_lmh_get_throttle_freq(data); + return __qcom_cpufreq_hw_get(data->policy) * HZ_PER_KHZ; +} + +/* + * Since we cannot determine the closest rate of the target rate, let's just + * return the actual rate at which the clock is running at. This is needed to + * make clk_set_rate() API work properly. + */ +static int qcom_cpufreq_hw_determine_rate(struct clk_hw *hw, struct clk_rate_request *req) +{ + req->rate = qcom_cpufreq_hw_recalc_rate(hw, 0); + + return 0; } static const struct clk_ops qcom_cpufreq_hw_clk_ops = { .recalc_rate = qcom_cpufreq_hw_recalc_rate, + .determine_rate = qcom_cpufreq_hw_determine_rate, }; static int qcom_cpufreq_hw_driver_probe(struct platform_device *pdev) @@ -737,7 +750,7 @@ static void qcom_cpufreq_hw_driver_remove(struct platform_device *pdev) static struct platform_driver qcom_cpufreq_hw_driver = { .probe = qcom_cpufreq_hw_driver_probe, - .remove_new = qcom_cpufreq_hw_driver_remove, + .remove = qcom_cpufreq_hw_driver_remove, .driver = { .name = "qcom-cpufreq-hw", .of_match_table = qcom_cpufreq_hw_match, diff --git a/drivers/cpufreq/qcom-cpufreq-nvmem.c b/drivers/cpufreq/qcom-cpufreq-nvmem.c index ea05d9d67490..3a8ed723a23e 100644 --- a/drivers/cpufreq/qcom-cpufreq-nvmem.c +++ b/drivers/cpufreq/qcom-cpufreq-nvmem.c @@ -52,12 +52,13 @@ struct qcom_cpufreq_match_data { struct nvmem_cell *speedbin_nvmem, char **pvs_name, struct qcom_cpufreq_drv *drv); - const char **genpd_names; + const char **pd_names; + unsigned int num_pd_names; }; struct qcom_cpufreq_drv_cpu { int opp_token; - struct device **virt_devs; + struct dev_pm_domain_list *pd_list; }; struct qcom_cpufreq_drv { @@ -191,6 +192,7 @@ static int qcom_cpufreq_kryo_name_version(struct device *cpu_dev, case QCOM_ID_IPQ5312: case QCOM_ID_IPQ5302: case QCOM_ID_IPQ5300: + case QCOM_ID_IPQ5321: case QCOM_ID_IPQ9514: case QCOM_ID_IPQ9550: case QCOM_ID_IPQ9554: @@ -394,8 +396,6 @@ static int qcom_cpufreq_ipq8074_name_version(struct device *cpu_dev, return 0; } -static const char *generic_genpd_names[] = { "perf", NULL }; - static const struct qcom_cpufreq_match_data match_data_kryo = { .get_version = qcom_cpufreq_kryo_name_version, }; @@ -406,13 +406,13 @@ static const struct qcom_cpufreq_match_data match_data_krait = { static const struct qcom_cpufreq_match_data match_data_msm8909 = { .get_version = qcom_cpufreq_simple_get_version, - .genpd_names = generic_genpd_names, + .pd_names = (const char *[]) { "perf" }, + .num_pd_names = 1, }; -static const char *qcs404_genpd_names[] = { "cpr", NULL }; - static const struct qcom_cpufreq_match_data match_data_qcs404 = { - .genpd_names = qcs404_genpd_names, + .pd_names = (const char *[]) { "cpr" }, + .num_pd_names = 1, }; static const struct qcom_cpufreq_match_data match_data_ipq6018 = { @@ -427,35 +427,22 @@ static const struct qcom_cpufreq_match_data match_data_ipq8074 = { .get_version = qcom_cpufreq_ipq8074_name_version, }; -static void qcom_cpufreq_suspend_virt_devs(struct qcom_cpufreq_drv *drv, unsigned int cpu) -{ - const char * const *name = drv->data->genpd_names; - int i; - - if (!drv->cpus[cpu].virt_devs) - return; - - for (i = 0; *name; i++, name++) - device_set_awake_path(drv->cpus[cpu].virt_devs[i]); -} - -static void qcom_cpufreq_put_virt_devs(struct qcom_cpufreq_drv *drv, unsigned int cpu) +static void qcom_cpufreq_suspend_pd_devs(struct qcom_cpufreq_drv *drv, unsigned int cpu) { - const char * const *name = drv->data->genpd_names; + struct dev_pm_domain_list *pd_list = drv->cpus[cpu].pd_list; int i; - if (!drv->cpus[cpu].virt_devs) + if (!pd_list) return; - for (i = 0; *name; i++, name++) - pm_runtime_put(drv->cpus[cpu].virt_devs[i]); + for (i = 0; i < pd_list->num_pds; i++) + device_set_awake_path(pd_list->pd_devs[i]); } static int qcom_cpufreq_probe(struct platform_device *pdev) { struct qcom_cpufreq_drv *drv; struct nvmem_cell *speedbin_nvmem; - struct device_node *np; struct device *cpu_dev; char pvs_name_buffer[] = "speedXX-pvsXX-vXX"; char *pvs_name = pvs_name_buffer; @@ -467,16 +454,15 @@ static int qcom_cpufreq_probe(struct platform_device *pdev) if (!cpu_dev) return -ENODEV; - np = dev_pm_opp_of_get_opp_desc_node(cpu_dev); + struct device_node *np __free(device_node) = + dev_pm_opp_of_get_opp_desc_node(cpu_dev); if (!np) return -ENOENT; ret = of_device_is_compatible(np, "operating-points-v2-kryo-cpu") || of_device_is_compatible(np, "operating-points-v2-krait-cpu"); - if (!ret) { - of_node_put(np); + if (!ret) return -ENOENT; - } drv = devm_kzalloc(&pdev->dev, struct_size(drv, cpus, num_possible_cpus()), GFP_KERNEL); @@ -502,10 +488,8 @@ static int qcom_cpufreq_probe(struct platform_device *pdev) } nvmem_cell_put(speedbin_nvmem); } - of_node_put(np); for_each_possible_cpu(cpu) { - struct device **virt_devs = NULL; struct dev_pm_opp_config config = { .supported_hw = NULL, }; @@ -524,12 +508,7 @@ static int qcom_cpufreq_probe(struct platform_device *pdev) config.prop_name = pvs_name; } - if (drv->data->genpd_names) { - config.genpd_names = drv->data->genpd_names; - config.virt_devs = &virt_devs; - } - - if (config.supported_hw || config.genpd_names) { + if (config.supported_hw) { drv->cpus[cpu].opp_token = dev_pm_opp_set_config(cpu_dev, &config); if (drv->cpus[cpu].opp_token < 0) { ret = drv->cpus[cpu].opp_token; @@ -538,25 +517,18 @@ static int qcom_cpufreq_probe(struct platform_device *pdev) } } - if (virt_devs) { - const char * const *name = config.genpd_names; - int i, j; - - for (i = 0; *name; i++, name++) { - ret = pm_runtime_resume_and_get(virt_devs[i]); - if (ret) { - dev_err(cpu_dev, "failed to resume %s: %d\n", - *name, ret); - - /* Rollback previous PM runtime calls */ - name = config.genpd_names; - for (j = 0; *name && j < i; j++, name++) - pm_runtime_put(virt_devs[j]); - - goto free_opp; - } - } - drv->cpus[cpu].virt_devs = virt_devs; + if (drv->data->pd_names) { + struct dev_pm_domain_attach_data attach_data = { + .pd_names = drv->data->pd_names, + .num_pd_names = drv->data->num_pd_names, + .pd_flags = PD_FLAG_DEV_LINK_ON | + PD_FLAG_REQUIRED_OPP, + }; + + ret = dev_pm_domain_attach_list(cpu_dev, &attach_data, + &drv->cpus[cpu].pd_list); + if (ret < 0) + goto free_opp; } } @@ -572,7 +544,7 @@ static int qcom_cpufreq_probe(struct platform_device *pdev) free_opp: for_each_possible_cpu(cpu) { - qcom_cpufreq_put_virt_devs(drv, cpu); + dev_pm_domain_detach_list(drv->cpus[cpu].pd_list); dev_pm_opp_clear_config(drv->cpus[cpu].opp_token); } return ret; @@ -586,7 +558,7 @@ static void qcom_cpufreq_remove(struct platform_device *pdev) platform_device_unregister(cpufreq_dt_pdev); for_each_possible_cpu(cpu) { - qcom_cpufreq_put_virt_devs(drv, cpu); + dev_pm_domain_detach_list(drv->cpus[cpu].pd_list); dev_pm_opp_clear_config(drv->cpus[cpu].opp_token); } } @@ -597,7 +569,7 @@ static int qcom_cpufreq_suspend(struct device *dev) unsigned int cpu; for_each_possible_cpu(cpu) - qcom_cpufreq_suspend_virt_devs(drv, cpu); + qcom_cpufreq_suspend_pd_devs(drv, cpu); return 0; } @@ -606,14 +578,14 @@ static DEFINE_SIMPLE_DEV_PM_OPS(qcom_cpufreq_pm_ops, qcom_cpufreq_suspend, NULL) static struct platform_driver qcom_cpufreq_driver = { .probe = qcom_cpufreq_probe, - .remove_new = qcom_cpufreq_remove, + .remove = qcom_cpufreq_remove, .driver = { .name = "qcom-cpufreq-nvmem", .pm = pm_sleep_ptr(&qcom_cpufreq_pm_ops), }, }; -static const struct of_device_id qcom_cpufreq_match_list[] __initconst = { +static const struct of_device_id qcom_cpufreq_match_list[] __initconst __maybe_unused = { { .compatible = "qcom,apq8096", .data = &match_data_kryo }, { .compatible = "qcom,msm8909", .data = &match_data_msm8909 }, { .compatible = "qcom,msm8996", .data = &match_data_kryo }, @@ -638,7 +610,7 @@ MODULE_DEVICE_TABLE(of, qcom_cpufreq_match_list); */ static int __init qcom_cpufreq_init(void) { - struct device_node *np = of_find_node_by_path("/"); + struct device_node *np __free(device_node) = of_find_node_by_path("/"); const struct of_device_id *match; int ret; @@ -646,7 +618,6 @@ static int __init qcom_cpufreq_init(void) return -ENODEV; match = of_match_node(qcom_cpufreq_match_list, np); - of_node_put(np); if (!match) return -ENODEV; diff --git a/drivers/cpufreq/qoriq-cpufreq.c b/drivers/cpufreq/qoriq-cpufreq.c index 0aecaecbb0e6..a37ce051236c 100644 --- a/drivers/cpufreq/qoriq-cpufreq.c +++ b/drivers/cpufreq/qoriq-cpufreq.c @@ -225,7 +225,7 @@ err_np: return -ENODEV; } -static int qoriq_cpufreq_cpu_exit(struct cpufreq_policy *policy) +static void qoriq_cpufreq_cpu_exit(struct cpufreq_policy *policy) { struct cpu_data *data = policy->driver_data; @@ -233,8 +233,6 @@ static int qoriq_cpufreq_cpu_exit(struct cpufreq_policy *policy) kfree(data->table); kfree(data); policy->driver_data = NULL; - - return 0; } static int qoriq_cpufreq_target(struct cpufreq_policy *policy, @@ -298,7 +296,7 @@ static struct platform_driver qoriq_cpufreq_platform_driver = { .name = "qoriq-cpufreq", }, .probe = qoriq_cpufreq_probe, - .remove_new = qoriq_cpufreq_remove, + .remove = qoriq_cpufreq_remove, }; module_platform_driver(qoriq_cpufreq_platform_driver); diff --git a/drivers/cpufreq/raspberrypi-cpufreq.c b/drivers/cpufreq/raspberrypi-cpufreq.c index e0705cc9a57d..5050932954e3 100644 --- a/drivers/cpufreq/raspberrypi-cpufreq.c +++ b/drivers/cpufreq/raspberrypi-cpufreq.c @@ -85,7 +85,7 @@ static struct platform_driver raspberrypi_cpufreq_driver = { .name = "raspberrypi-cpufreq", }, .probe = raspberrypi_cpufreq_probe, - .remove_new = raspberrypi_cpufreq_remove, + .remove = raspberrypi_cpufreq_remove, }; module_platform_driver(raspberrypi_cpufreq_driver); diff --git a/drivers/cpufreq/s3c64xx-cpufreq.c b/drivers/cpufreq/s3c64xx-cpufreq.c index c6bdfc308e99..9cef71528076 100644 --- a/drivers/cpufreq/s3c64xx-cpufreq.c +++ b/drivers/cpufreq/s3c64xx-cpufreq.c @@ -24,6 +24,7 @@ struct s3c64xx_dvfs { unsigned int vddarm_max; }; +#ifdef CONFIG_REGULATOR static struct s3c64xx_dvfs s3c64xx_dvfs_table[] = { [0] = { 1000000, 1150000 }, [1] = { 1050000, 1150000 }, @@ -31,6 +32,7 @@ static struct s3c64xx_dvfs s3c64xx_dvfs_table[] = { [3] = { 1200000, 1350000 }, [4] = { 1300000, 1350000 }, }; +#endif static struct cpufreq_frequency_table s3c64xx_freq_table[] = { { 0, 0, 66000 }, @@ -51,15 +53,16 @@ static struct cpufreq_frequency_table s3c64xx_freq_table[] = { static int s3c64xx_cpufreq_set_target(struct cpufreq_policy *policy, unsigned int index) { - struct s3c64xx_dvfs *dvfs; - unsigned int old_freq, new_freq; + unsigned int new_freq = s3c64xx_freq_table[index].frequency; int ret; +#ifdef CONFIG_REGULATOR + struct s3c64xx_dvfs *dvfs; + unsigned int old_freq; + old_freq = clk_get_rate(policy->clk) / 1000; - new_freq = s3c64xx_freq_table[index].frequency; dvfs = &s3c64xx_dvfs_table[s3c64xx_freq_table[index].driver_data]; -#ifdef CONFIG_REGULATOR if (vddarm && new_freq > old_freq) { ret = regulator_set_voltage(vddarm, dvfs->vddarm_min, diff --git a/drivers/cpufreq/scmi-cpufreq.c b/drivers/cpufreq/scmi-cpufreq.c index 4ee23f4ebf4a..b8fe758aeb01 100644 --- a/drivers/cpufreq/scmi-cpufreq.c +++ b/drivers/cpufreq/scmi-cpufreq.c @@ -16,6 +16,7 @@ #include <linux/export.h> #include <linux/module.h> #include <linux/pm_opp.h> +#include <linux/pm_qos.h> #include <linux/slab.h> #include <linux/scmi_protocol.h> #include <linux/types.h> @@ -26,10 +27,13 @@ struct scmi_data { int nr_opp; struct device *cpu_dev; cpumask_var_t opp_shared_cpus; + struct notifier_block limit_notify_nb; + struct freq_qos_request limits_freq_req; }; static struct scmi_protocol_handle *ph; static const struct scmi_perf_proto_ops *perf_ops; +static struct cpufreq_driver scmi_cpufreq_driver; static unsigned int scmi_cpufreq_get_rate(unsigned int cpu) { @@ -62,9 +66,9 @@ static unsigned int scmi_cpufreq_fast_switch(struct cpufreq_policy *policy, unsigned int target_freq) { struct scmi_data *priv = policy->driver_data; + unsigned long freq = target_freq; - if (!perf_ops->freq_set(ph, priv->domain_id, - target_freq * 1000, true)) + if (!perf_ops->freq_set(ph, priv->domain_id, freq * 1000, true)) return target_freq; return 0; @@ -144,6 +148,51 @@ scmi_get_cpu_power(struct device *cpu_dev, unsigned long *power, return 0; } +static int +scmi_get_rate_limit(u32 domain, bool has_fast_switch) +{ + int ret, rate_limit; + + if (has_fast_switch) { + /* + * Fast channels are used whenever available, + * so use their rate_limit value if populated. + */ + ret = perf_ops->fast_switch_rate_limit(ph, domain, + &rate_limit); + if (!ret && rate_limit) + return rate_limit; + } + + ret = perf_ops->rate_limit_get(ph, domain, &rate_limit); + if (ret) + return 0; + + return rate_limit; +} + +static struct freq_attr *scmi_cpufreq_hw_attr[] = { + &cpufreq_freq_attr_scaling_available_freqs, + NULL, + NULL, +}; + +static int scmi_limit_notify_cb(struct notifier_block *nb, unsigned long event, void *data) +{ + struct scmi_data *priv = container_of(nb, struct scmi_data, limit_notify_nb); + struct scmi_perf_limits_report *limit_notify = data; + unsigned int limit_freq_khz; + int ret; + + limit_freq_khz = limit_notify->range_max_freq / HZ_PER_KHZ; + + ret = freq_qos_update_request(&priv->limits_freq_req, limit_freq_khz); + if (ret < 0) + pr_warn("failed to update freq constraint: %d\n", ret); + + return NOTIFY_OK; +} + static int scmi_cpufreq_init(struct cpufreq_policy *policy) { int ret, nr_opp, domain; @@ -151,6 +200,7 @@ static int scmi_cpufreq_init(struct cpufreq_policy *policy) struct device *cpu_dev; struct scmi_data *priv; struct cpufreq_frequency_table *freq_table; + struct scmi_device *sdev = cpufreq_get_driver_data(); cpu_dev = get_cpu_device(policy->cpu); if (!cpu_dev) { @@ -250,8 +300,41 @@ static int scmi_cpufreq_init(struct cpufreq_policy *policy) policy->fast_switch_possible = perf_ops->fast_switch_possible(ph, domain); + policy->transition_delay_us = + scmi_get_rate_limit(domain, policy->fast_switch_possible); + + if (policy_has_boost_freq(policy)) { + ret = cpufreq_enable_boost_support(); + if (ret) { + dev_warn(cpu_dev, "failed to enable boost: %d\n", ret); + goto out_free_table; + } else { + scmi_cpufreq_hw_attr[1] = &cpufreq_freq_attr_scaling_boost_freqs; + scmi_cpufreq_driver.boost_enabled = true; + } + } + + ret = freq_qos_add_request(&policy->constraints, &priv->limits_freq_req, FREQ_QOS_MAX, + FREQ_QOS_MAX_DEFAULT_VALUE); + if (ret < 0) { + dev_err(cpu_dev, "failed to add qos limits request: %d\n", ret); + goto out_free_table; + } + + priv->limit_notify_nb.notifier_call = scmi_limit_notify_cb; + ret = sdev->handle->notify_ops->event_notifier_register(sdev->handle, SCMI_PROTOCOL_PERF, + SCMI_EVENT_PERFORMANCE_LIMITS_CHANGED, + &priv->domain_id, + &priv->limit_notify_nb); + if (ret) + dev_warn(&sdev->dev, + "failed to register for limits change notifier for domain %d\n", + priv->domain_id); + return 0; +out_free_table: + dev_pm_opp_free_cpufreq_table(cpu_dev, &freq_table); out_free_opp: dev_pm_opp_remove_all_dynamic(cpu_dev); @@ -264,16 +347,20 @@ out_free_priv: return ret; } -static int scmi_cpufreq_exit(struct cpufreq_policy *policy) +static void scmi_cpufreq_exit(struct cpufreq_policy *policy) { struct scmi_data *priv = policy->driver_data; + struct scmi_device *sdev = cpufreq_get_driver_data(); + sdev->handle->notify_ops->event_notifier_unregister(sdev->handle, SCMI_PROTOCOL_PERF, + SCMI_EVENT_PERFORMANCE_LIMITS_CHANGED, + &priv->domain_id, + &priv->limit_notify_nb); + freq_qos_remove_request(&priv->limits_freq_req); dev_pm_opp_free_cpufreq_table(priv->cpu_dev, &policy->freq_table); dev_pm_opp_remove_all_dynamic(priv->cpu_dev); free_cpumask_var(priv->opp_shared_cpus); kfree(priv); - - return 0; } static void scmi_cpufreq_register_em(struct cpufreq_policy *policy) @@ -308,7 +395,7 @@ static struct cpufreq_driver scmi_cpufreq_driver = { CPUFREQ_NEED_INITIAL_FREQ_CHECK | CPUFREQ_IS_COOLING_DEV, .verify = cpufreq_generic_frequency_table_verify, - .attr = cpufreq_generic_attr, + .attr = scmi_cpufreq_hw_attr, .target_index = scmi_cpufreq_set_target, .fast_switch = scmi_cpufreq_fast_switch, .get = scmi_cpufreq_get_rate, @@ -328,6 +415,8 @@ static int scmi_cpufreq_probe(struct scmi_device *sdev) if (!handle) return -ENODEV; + scmi_cpufreq_driver.driver_data = sdev; + perf_ops = handle->devm_protocol_get(sdev, SCMI_PROTOCOL_PERF, &ph); if (IS_ERR(perf_ops)) return PTR_ERR(perf_ops); diff --git a/drivers/cpufreq/scpi-cpufreq.c b/drivers/cpufreq/scpi-cpufreq.c index d33be56983ed..cd89c1b9832c 100644 --- a/drivers/cpufreq/scpi-cpufreq.c +++ b/drivers/cpufreq/scpi-cpufreq.c @@ -167,7 +167,7 @@ out_free_opp: return ret; } -static int scpi_cpufreq_exit(struct cpufreq_policy *policy) +static void scpi_cpufreq_exit(struct cpufreq_policy *policy) { struct scpi_data *priv = policy->driver_data; @@ -175,8 +175,6 @@ static int scpi_cpufreq_exit(struct cpufreq_policy *policy) dev_pm_opp_free_cpufreq_table(priv->cpu_dev, &policy->freq_table); dev_pm_opp_remove_all_dynamic(priv->cpu_dev); kfree(priv); - - return 0; } static struct cpufreq_driver scpi_cpufreq_driver = { @@ -219,7 +217,7 @@ static struct platform_driver scpi_cpufreq_platdrv = { .name = "scpi-cpufreq", }, .probe = scpi_cpufreq_probe, - .remove_new = scpi_cpufreq_remove, + .remove = scpi_cpufreq_remove, }; module_platform_driver(scpi_cpufreq_platdrv); diff --git a/drivers/cpufreq/sh-cpufreq.c b/drivers/cpufreq/sh-cpufreq.c index b8704232c27b..aa74036d0420 100644 --- a/drivers/cpufreq/sh-cpufreq.c +++ b/drivers/cpufreq/sh-cpufreq.c @@ -135,14 +135,12 @@ static int sh_cpufreq_cpu_init(struct cpufreq_policy *policy) return 0; } -static int sh_cpufreq_cpu_exit(struct cpufreq_policy *policy) +static void sh_cpufreq_cpu_exit(struct cpufreq_policy *policy) { unsigned int cpu = policy->cpu; struct clk *cpuclk = &per_cpu(sh_cpuclk, cpu); clk_put(cpuclk); - - return 0; } static struct cpufreq_driver sh_cpufreq_driver = { diff --git a/drivers/cpufreq/sparc-us2e-cpufreq.c b/drivers/cpufreq/sparc-us2e-cpufreq.c index 2783d3d55fce..15899dd77c08 100644 --- a/drivers/cpufreq/sparc-us2e-cpufreq.c +++ b/drivers/cpufreq/sparc-us2e-cpufreq.c @@ -296,10 +296,9 @@ static int us2e_freq_cpu_init(struct cpufreq_policy *policy) return 0; } -static int us2e_freq_cpu_exit(struct cpufreq_policy *policy) +static void us2e_freq_cpu_exit(struct cpufreq_policy *policy) { us2e_freq_target(policy, 0); - return 0; } static struct cpufreq_driver cpufreq_us2e_driver = { @@ -324,7 +323,7 @@ static int __init us2e_freq_init(void) impl = ((ver >> 32) & 0xffff); if (manuf == 0x17 && impl == 0x13) { - us2e_freq_table = kzalloc(NR_CPUS * sizeof(*us2e_freq_table), + us2e_freq_table = kcalloc(NR_CPUS, sizeof(*us2e_freq_table), GFP_KERNEL); if (!us2e_freq_table) return -ENOMEM; diff --git a/drivers/cpufreq/sparc-us3-cpufreq.c b/drivers/cpufreq/sparc-us3-cpufreq.c index 6c3657679a88..de50a2f3b124 100644 --- a/drivers/cpufreq/sparc-us3-cpufreq.c +++ b/drivers/cpufreq/sparc-us3-cpufreq.c @@ -140,10 +140,9 @@ static int us3_freq_cpu_init(struct cpufreq_policy *policy) return 0; } -static int us3_freq_cpu_exit(struct cpufreq_policy *policy) +static void us3_freq_cpu_exit(struct cpufreq_policy *policy) { us3_freq_target(policy, 0); - return 0; } static struct cpufreq_driver cpufreq_us3_driver = { @@ -172,7 +171,7 @@ static int __init us3_freq_init(void) impl == CHEETAH_PLUS_IMPL || impl == JAGUAR_IMPL || impl == PANTHER_IMPL)) { - us3_freq_table = kzalloc(NR_CPUS * sizeof(*us3_freq_table), + us3_freq_table = kcalloc(NR_CPUS, sizeof(*us3_freq_table), GFP_KERNEL); if (!us3_freq_table) return -ENOMEM; diff --git a/drivers/cpufreq/spear-cpufreq.c b/drivers/cpufreq/spear-cpufreq.c index 78b875db6b66..d8ab5b01d46d 100644 --- a/drivers/cpufreq/spear-cpufreq.c +++ b/drivers/cpufreq/spear-cpufreq.c @@ -171,10 +171,9 @@ static struct cpufreq_driver spear_cpufreq_driver = { static int spear_cpufreq_probe(struct platform_device *pdev) { struct device_node *np; - const struct property *prop; struct cpufreq_frequency_table *freq_tbl; - const __be32 *val; - int cnt, i, ret; + u32 val; + int cnt, ret, i = 0; np = of_cpu_device_node_get(0); if (!np) { @@ -186,26 +185,23 @@ static int spear_cpufreq_probe(struct platform_device *pdev) &spear_cpufreq.transition_latency)) spear_cpufreq.transition_latency = CPUFREQ_ETERNAL; - prop = of_find_property(np, "cpufreq_tbl", NULL); - if (!prop || !prop->value) { + cnt = of_property_count_u32_elems(np, "cpufreq_tbl"); + if (cnt <= 0) { pr_err("Invalid cpufreq_tbl\n"); ret = -ENODEV; goto out_put_node; } - cnt = prop->length / sizeof(u32); - val = prop->value; - freq_tbl = kcalloc(cnt + 1, sizeof(*freq_tbl), GFP_KERNEL); if (!freq_tbl) { ret = -ENOMEM; goto out_put_node; } - for (i = 0; i < cnt; i++) - freq_tbl[i].frequency = be32_to_cpup(val++); + of_property_for_each_u32(np, "cpufreq_tbl", val) + freq_tbl[i++].frequency = val; - freq_tbl[i].frequency = CPUFREQ_TABLE_END; + freq_tbl[cnt].frequency = CPUFREQ_TABLE_END; spear_cpufreq.freq_tbl = freq_tbl; diff --git a/drivers/cpufreq/speedstep-centrino.c b/drivers/cpufreq/speedstep-centrino.c index 75b10ecdb60f..3fafedb983b5 100644 --- a/drivers/cpufreq/speedstep-centrino.c +++ b/drivers/cpufreq/speedstep-centrino.c @@ -400,16 +400,12 @@ static int centrino_cpu_init(struct cpufreq_policy *policy) return 0; } -static int centrino_cpu_exit(struct cpufreq_policy *policy) +static void centrino_cpu_exit(struct cpufreq_policy *policy) { unsigned int cpu = policy->cpu; - if (!per_cpu(centrino_model, cpu)) - return -ENODEV; - - per_cpu(centrino_model, cpu) = NULL; - - return 0; + if (per_cpu(centrino_model, cpu)) + per_cpu(centrino_model, cpu) = NULL; } /** @@ -520,10 +516,10 @@ static struct cpufreq_driver centrino_driver = { * or ASCII model IDs. */ static const struct x86_cpu_id centrino_ids[] = { - X86_MATCH_VENDOR_FAM_MODEL_FEATURE(INTEL, 6, 9, X86_FEATURE_EST, NULL), - X86_MATCH_VENDOR_FAM_MODEL_FEATURE(INTEL, 6, 13, X86_FEATURE_EST, NULL), - X86_MATCH_VENDOR_FAM_MODEL_FEATURE(INTEL, 15, 3, X86_FEATURE_EST, NULL), - X86_MATCH_VENDOR_FAM_MODEL_FEATURE(INTEL, 15, 4, X86_FEATURE_EST, NULL), + X86_MATCH_VFM_FEATURE(IFM( 6, 9), X86_FEATURE_EST, NULL), + X86_MATCH_VFM_FEATURE(IFM( 6, 13), X86_FEATURE_EST, NULL), + X86_MATCH_VFM_FEATURE(IFM(15, 3), X86_FEATURE_EST, NULL), + X86_MATCH_VFM_FEATURE(IFM(15, 4), X86_FEATURE_EST, NULL), {} }; diff --git a/drivers/cpufreq/sti-cpufreq.c b/drivers/cpufreq/sti-cpufreq.c index 9c542e723a15..b15b3142b5fe 100644 --- a/drivers/cpufreq/sti-cpufreq.c +++ b/drivers/cpufreq/sti-cpufreq.c @@ -18,7 +18,7 @@ #include <linux/regmap.h> #define VERSION_ELEMENTS 3 -#define MAX_PCODE_NAME_LEN 7 +#define MAX_PCODE_NAME_LEN 16 #define VERSION_SHIFT 28 #define HW_INFO_INDEX 1 @@ -267,7 +267,7 @@ static int __init sti_cpufreq_init(void) goto skip_voltage_scaling; } - if (!of_get_property(ddata.cpu->of_node, "operating-points-v2", NULL)) { + if (!of_property_present(ddata.cpu->of_node, "operating-points-v2")) { dev_err(ddata.cpu, "OPP-v2 not supported\n"); goto skip_voltage_scaling; } @@ -293,6 +293,7 @@ module_init(sti_cpufreq_init); static const struct of_device_id __maybe_unused sti_cpufreq_of_match[] = { { .compatible = "st,stih407" }, { .compatible = "st,stih410" }, + { .compatible = "st,stih418" }, { }, }; MODULE_DEVICE_TABLE(of, sti_cpufreq_of_match); diff --git a/drivers/cpufreq/sun50i-cpufreq-nvmem.c b/drivers/cpufreq/sun50i-cpufreq-nvmem.c index 32a9c88f8ff6..17d6a149f580 100644 --- a/drivers/cpufreq/sun50i-cpufreq-nvmem.c +++ b/drivers/cpufreq/sun50i-cpufreq-nvmem.c @@ -10,6 +10,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/arm-smccc.h> #include <linux/cpu.h> #include <linux/module.h> #include <linux/nvmem-consumer.h> @@ -18,76 +19,223 @@ #include <linux/pm_opp.h> #include <linux/slab.h> -#define MAX_NAME_LEN 7 - #define NVMEM_MASK 0x7 #define NVMEM_SHIFT 5 +#define SUN50I_A100_NVMEM_MASK 0xf +#define SUN50I_A100_NVMEM_SHIFT 12 + static struct platform_device *cpufreq_dt_pdev, *sun50i_cpufreq_pdev; +struct sunxi_cpufreq_data { + u32 (*efuse_xlate)(u32 speedbin); +}; + +static u32 sun50i_h6_efuse_xlate(u32 speedbin) +{ + u32 efuse_value; + + efuse_value = (speedbin >> NVMEM_SHIFT) & NVMEM_MASK; + + /* + * We treat unexpected efuse values as if the SoC was from + * the slowest bin. Expected efuse values are 1-3, slowest + * to fastest. + */ + if (efuse_value >= 1 && efuse_value <= 3) + return efuse_value - 1; + else + return 0; +} + +static u32 sun50i_a100_efuse_xlate(u32 speedbin) +{ + u32 efuse_value; + + efuse_value = (speedbin >> SUN50I_A100_NVMEM_SHIFT) & + SUN50I_A100_NVMEM_MASK; + + switch (efuse_value) { + case 0b100: + return 2; + case 0b010: + return 1; + default: + return 0; + } +} + +static int get_soc_id_revision(void) +{ +#ifdef CONFIG_HAVE_ARM_SMCCC_DISCOVERY + return arm_smccc_get_soc_id_revision(); +#else + return SMCCC_RET_NOT_SUPPORTED; +#endif +} + +/* + * Judging by the OPP tables in the vendor BSP, the quality order of the + * returned speedbin index is 4 -> 0/2 -> 3 -> 1, from worst to best. + * 0 and 2 seem identical from the OPP tables' point of view. + */ +static u32 sun50i_h616_efuse_xlate(u32 speedbin) +{ + int ver_bits = get_soc_id_revision(); + u32 value = 0; + + switch (speedbin & 0xffff) { + case 0x2000: + value = 0; + break; + case 0x2400: + case 0x7400: + case 0x2c00: + case 0x7c00: + if (ver_bits != SMCCC_RET_NOT_SUPPORTED && ver_bits <= 1) { + /* ic version A/B */ + value = 1; + } else { + /* ic version C and later version */ + value = 2; + } + break; + case 0x5000: + case 0x5400: + case 0x6000: + value = 3; + break; + case 0x5c00: + value = 4; + break; + case 0x5d00: + value = 0; + break; + case 0x6c00: + value = 5; + break; + default: + pr_warn("sun50i-cpufreq-nvmem: unknown speed bin 0x%x, using default bin 0\n", + speedbin & 0xffff); + value = 0; + break; + } + + return value; +} + +static struct sunxi_cpufreq_data sun50i_h6_cpufreq_data = { + .efuse_xlate = sun50i_h6_efuse_xlate, +}; + +static struct sunxi_cpufreq_data sun50i_a100_cpufreq_data = { + .efuse_xlate = sun50i_a100_efuse_xlate, +}; + +static struct sunxi_cpufreq_data sun50i_h616_cpufreq_data = { + .efuse_xlate = sun50i_h616_efuse_xlate, +}; + +static const struct of_device_id cpu_opp_match_list[] = { + { .compatible = "allwinner,sun50i-h6-operating-points", + .data = &sun50i_h6_cpufreq_data, + }, + { .compatible = "allwinner,sun50i-a100-operating-points", + .data = &sun50i_a100_cpufreq_data, + }, + { .compatible = "allwinner,sun50i-h616-operating-points", + .data = &sun50i_h616_cpufreq_data, + }, + {} +}; + +/** + * dt_has_supported_hw() - Check if any OPPs use opp-supported-hw + * + * If we ask the cpufreq framework to use the opp-supported-hw feature, it + * will ignore every OPP node without that DT property. If none of the OPPs + * have it, the driver will fail probing, due to the lack of OPPs. + * + * Returns true if we have at least one OPP with the opp-supported-hw property. + */ +static bool dt_has_supported_hw(void) +{ + bool has_opp_supported_hw = false; + struct device *cpu_dev; + + cpu_dev = get_cpu_device(0); + if (!cpu_dev) + return false; + + struct device_node *np __free(device_node) = + dev_pm_opp_of_get_opp_desc_node(cpu_dev); + if (!np) + return false; + + for_each_child_of_node_scoped(np, opp) { + if (of_property_present(opp, "opp-supported-hw")) { + has_opp_supported_hw = true; + break; + } + } + + return has_opp_supported_hw; +} + /** * sun50i_cpufreq_get_efuse() - Determine speed grade from efuse value - * @versions: Set to the value parsed from efuse * - * Returns 0 if success. + * Returns non-negative speed bin index on success, a negative error + * value otherwise. */ -static int sun50i_cpufreq_get_efuse(u32 *versions) +static int sun50i_cpufreq_get_efuse(void) { + const struct sunxi_cpufreq_data *opp_data; struct nvmem_cell *speedbin_nvmem; - struct device_node *np; + const struct of_device_id *match; struct device *cpu_dev; - u32 *speedbin, efuse_value; - size_t len; + u32 *speedbin; int ret; cpu_dev = get_cpu_device(0); if (!cpu_dev) return -ENODEV; - np = dev_pm_opp_of_get_opp_desc_node(cpu_dev); + struct device_node *np __free(device_node) = + dev_pm_opp_of_get_opp_desc_node(cpu_dev); if (!np) return -ENOENT; - ret = of_device_is_compatible(np, - "allwinner,sun50i-h6-operating-points"); - if (!ret) { - of_node_put(np); + match = of_match_node(cpu_opp_match_list, np); + if (!match) return -ENOENT; - } + + opp_data = match->data; speedbin_nvmem = of_nvmem_cell_get(np, NULL); - of_node_put(np); if (IS_ERR(speedbin_nvmem)) return dev_err_probe(cpu_dev, PTR_ERR(speedbin_nvmem), "Could not get nvmem cell\n"); - speedbin = nvmem_cell_read(speedbin_nvmem, &len); + speedbin = nvmem_cell_read(speedbin_nvmem, NULL); nvmem_cell_put(speedbin_nvmem); if (IS_ERR(speedbin)) return PTR_ERR(speedbin); - efuse_value = (*speedbin >> NVMEM_SHIFT) & NVMEM_MASK; - - /* - * We treat unexpected efuse values as if the SoC was from - * the slowest bin. Expected efuse values are 1-3, slowest - * to fastest. - */ - if (efuse_value >= 1 && efuse_value <= 3) - *versions = efuse_value - 1; - else - *versions = 0; + ret = opp_data->efuse_xlate(*speedbin); kfree(speedbin); - return 0; + + return ret; }; static int sun50i_cpufreq_nvmem_probe(struct platform_device *pdev) { int *opp_tokens; - char name[MAX_NAME_LEN]; - unsigned int cpu; - u32 speed = 0; + char name[] = "speedXXXXXXXXXXX"; /* Integers can take 11 chars max */ + unsigned int cpu, supported_hw; + struct dev_pm_opp_config config = {}; + int speed; int ret; opp_tokens = kcalloc(num_possible_cpus(), sizeof(*opp_tokens), @@ -95,13 +243,24 @@ static int sun50i_cpufreq_nvmem_probe(struct platform_device *pdev) if (!opp_tokens) return -ENOMEM; - ret = sun50i_cpufreq_get_efuse(&speed); - if (ret) { + speed = sun50i_cpufreq_get_efuse(); + if (speed < 0) { kfree(opp_tokens); - return ret; + return speed; } - snprintf(name, MAX_NAME_LEN, "speed%d", speed); + /* + * We need at least one OPP with the "opp-supported-hw" property, + * or else the upper layers will ignore every OPP and will bail out. + */ + if (dt_has_supported_hw()) { + supported_hw = 1U << speed; + config.supported_hw = &supported_hw; + config.supported_hw_count = 1; + } + + snprintf(name, sizeof(name), "speed%d", speed); + config.prop_name = name; for_each_possible_cpu(cpu) { struct device *cpu_dev = get_cpu_device(cpu); @@ -111,12 +270,11 @@ static int sun50i_cpufreq_nvmem_probe(struct platform_device *pdev) goto free_opp; } - opp_tokens[cpu] = dev_pm_opp_set_prop_name(cpu_dev, name); - if (opp_tokens[cpu] < 0) { - ret = opp_tokens[cpu]; - pr_err("Failed to set prop name\n"); + ret = dev_pm_opp_set_config(cpu_dev, &config); + if (ret < 0) goto free_opp; - } + + opp_tokens[cpu] = ret; } cpufreq_dt_pdev = platform_device_register_simple("cpufreq-dt", -1, @@ -131,7 +289,7 @@ static int sun50i_cpufreq_nvmem_probe(struct platform_device *pdev) free_opp: for_each_possible_cpu(cpu) - dev_pm_opp_put_prop_name(opp_tokens[cpu]); + dev_pm_opp_clear_config(opp_tokens[cpu]); kfree(opp_tokens); return ret; @@ -145,14 +303,14 @@ static void sun50i_cpufreq_nvmem_remove(struct platform_device *pdev) platform_device_unregister(cpufreq_dt_pdev); for_each_possible_cpu(cpu) - dev_pm_opp_put_prop_name(opp_tokens[cpu]); + dev_pm_opp_clear_config(opp_tokens[cpu]); kfree(opp_tokens); } static struct platform_driver sun50i_cpufreq_driver = { .probe = sun50i_cpufreq_nvmem_probe, - .remove_new = sun50i_cpufreq_nvmem_remove, + .remove = sun50i_cpufreq_nvmem_remove, .driver = { .name = "sun50i-cpufreq-nvmem", }, @@ -160,20 +318,19 @@ static struct platform_driver sun50i_cpufreq_driver = { static const struct of_device_id sun50i_cpufreq_match_list[] = { { .compatible = "allwinner,sun50i-h6" }, + { .compatible = "allwinner,sun50i-a100" }, + { .compatible = "allwinner,sun50i-h616" }, + { .compatible = "allwinner,sun50i-h618" }, + { .compatible = "allwinner,sun50i-h700" }, {} }; MODULE_DEVICE_TABLE(of, sun50i_cpufreq_match_list); static const struct of_device_id *sun50i_cpufreq_match_node(void) { - const struct of_device_id *match; - struct device_node *np; - - np = of_find_node_by_path("/"); - match = of_match_node(sun50i_cpufreq_match_list, np); - of_node_put(np); + struct device_node *np __free(device_node) = of_find_node_by_path("/"); - return match; + return of_match_node(sun50i_cpufreq_match_list, np); } /* diff --git a/drivers/cpufreq/tegra124-cpufreq.c b/drivers/cpufreq/tegra124-cpufreq.c index aae951d4e77c..514146d98bca 100644 --- a/drivers/cpufreq/tegra124-cpufreq.c +++ b/drivers/cpufreq/tegra124-cpufreq.c @@ -52,12 +52,15 @@ out: static int tegra124_cpufreq_probe(struct platform_device *pdev) { + struct device_node *np __free(device_node) = of_cpu_device_node_get(0); struct tegra124_cpufreq_priv *priv; - struct device_node *np; struct device *cpu_dev; struct platform_device_info cpufreq_dt_devinfo = {}; int ret; + if (!np) + return -ENODEV; + priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; @@ -66,15 +69,9 @@ static int tegra124_cpufreq_probe(struct platform_device *pdev) if (!cpu_dev) return -ENODEV; - np = of_cpu_device_node_get(0); - if (!np) - return -ENODEV; - priv->cpu_clk = of_clk_get_by_name(np, "cpu_g"); - if (IS_ERR(priv->cpu_clk)) { - ret = PTR_ERR(priv->cpu_clk); - goto out_put_np; - } + if (IS_ERR(priv->cpu_clk)) + return PTR_ERR(priv->cpu_clk); priv->dfll_clk = of_clk_get_by_name(np, "dfll"); if (IS_ERR(priv->dfll_clk)) { @@ -110,8 +107,6 @@ static int tegra124_cpufreq_probe(struct platform_device *pdev) platform_set_drvdata(pdev, priv); - of_node_put(np); - return 0; out_put_pllp_clk: @@ -122,8 +117,6 @@ out_put_dfll_clk: clk_put(priv->dfll_clk); out_put_cpu_clk: clk_put(priv->cpu_clk); -out_put_np: - of_node_put(np); return ret; } diff --git a/drivers/cpufreq/tegra186-cpufreq.c b/drivers/cpufreq/tegra186-cpufreq.c index 7b8fcfa55038..c7761eb99f3c 100644 --- a/drivers/cpufreq/tegra186-cpufreq.c +++ b/drivers/cpufreq/tegra186-cpufreq.c @@ -276,7 +276,7 @@ static struct platform_driver tegra186_cpufreq_platform_driver = { .of_match_table = tegra186_cpufreq_of_match, }, .probe = tegra186_cpufreq_probe, - .remove_new = tegra186_cpufreq_remove, + .remove = tegra186_cpufreq_remove, }; module_platform_driver(tegra186_cpufreq_platform_driver); diff --git a/drivers/cpufreq/tegra194-cpufreq.c b/drivers/cpufreq/tegra194-cpufreq.c index 59865ea455a8..9055dd398e7f 100644 --- a/drivers/cpufreq/tegra194-cpufreq.c +++ b/drivers/cpufreq/tegra194-cpufreq.c @@ -551,14 +551,12 @@ static int tegra194_cpufreq_offline(struct cpufreq_policy *policy) return 0; } -static int tegra194_cpufreq_exit(struct cpufreq_policy *policy) +static void tegra194_cpufreq_exit(struct cpufreq_policy *policy) { struct device *cpu_dev = get_cpu_device(policy->cpu); dev_pm_opp_remove_all_dynamic(cpu_dev); dev_pm_opp_of_cpumask_remove_table(policy->related_cpus); - - return 0; } static int tegra194_cpufreq_set_target(struct cpufreq_policy *policy, @@ -820,7 +818,7 @@ static struct platform_driver tegra194_ccplex_driver = { .of_match_table = tegra194_cpufreq_of_match, }, .probe = tegra194_cpufreq_probe, - .remove_new = tegra194_cpufreq_remove, + .remove = tegra194_cpufreq_remove, }; module_platform_driver(tegra194_ccplex_driver); diff --git a/drivers/cpufreq/ti-cpufreq.c b/drivers/cpufreq/ti-cpufreq.c index 46c41e2ca727..5a5147277cd0 100644 --- a/drivers/cpufreq/ti-cpufreq.c +++ b/drivers/cpufreq/ti-cpufreq.c @@ -16,6 +16,7 @@ #include <linux/pm_opp.h> #include <linux/regmap.h> #include <linux/slab.h> +#include <linux/sys_soc.h> #define REVISION_MASK 0xF #define REVISION_SHIFT 28 @@ -47,6 +48,35 @@ #define AM625_SUPPORT_S_MPU_OPP BIT(1) #define AM625_SUPPORT_T_MPU_OPP BIT(2) +enum { + AM62A7_EFUSE_M_MPU_OPP = 13, + AM62A7_EFUSE_N_MPU_OPP, + AM62A7_EFUSE_O_MPU_OPP, + AM62A7_EFUSE_P_MPU_OPP, + AM62A7_EFUSE_Q_MPU_OPP, + AM62A7_EFUSE_R_MPU_OPP, + AM62A7_EFUSE_S_MPU_OPP, + /* + * The V, U, and T speed grade numbering is out of order + * to align with the AM625 more uniformly. I promise I know + * my ABCs ;) + */ + AM62A7_EFUSE_V_MPU_OPP, + AM62A7_EFUSE_U_MPU_OPP, + AM62A7_EFUSE_T_MPU_OPP, +}; + +#define AM62A7_SUPPORT_N_MPU_OPP BIT(0) +#define AM62A7_SUPPORT_R_MPU_OPP BIT(1) +#define AM62A7_SUPPORT_V_MPU_OPP BIT(2) + +#define AM62P5_EFUSE_O_MPU_OPP 15 +#define AM62P5_EFUSE_S_MPU_OPP 19 +#define AM62P5_EFUSE_U_MPU_OPP 21 + +#define AM62P5_SUPPORT_O_MPU_OPP BIT(0) +#define AM62P5_SUPPORT_U_MPU_OPP BIT(2) + #define VERSION_COUNT 2 struct ti_cpufreq_data; @@ -61,6 +91,11 @@ struct ti_cpufreq_soc_data { unsigned long efuse_shift; unsigned long rev_offset; bool multi_regulator; +/* Backward compatibility hack: Might have missing syscon */ +#define TI_QUIRK_SYSCON_MAY_BE_MISSING 0x1 +/* Backward compatibility hack: new syscon size is 1 register wide */ +#define TI_QUIRK_SYSCON_IS_SINGLE_REG 0x2 + u8 quirks; }; struct ti_cpufreq_data { @@ -112,6 +147,49 @@ static unsigned long omap3_efuse_xlate(struct ti_cpufreq_data *opp_data, return BIT(efuse); } +static unsigned long am62p5_efuse_xlate(struct ti_cpufreq_data *opp_data, + unsigned long efuse) +{ + unsigned long calculated_efuse = AM62P5_SUPPORT_O_MPU_OPP; + + switch (efuse) { + case AM62P5_EFUSE_U_MPU_OPP: + case AM62P5_EFUSE_S_MPU_OPP: + calculated_efuse |= AM62P5_SUPPORT_U_MPU_OPP; + fallthrough; + case AM62P5_EFUSE_O_MPU_OPP: + calculated_efuse |= AM62P5_SUPPORT_O_MPU_OPP; + } + + return calculated_efuse; +} + +static unsigned long am62a7_efuse_xlate(struct ti_cpufreq_data *opp_data, + unsigned long efuse) +{ + unsigned long calculated_efuse = AM62A7_SUPPORT_N_MPU_OPP; + + switch (efuse) { + case AM62A7_EFUSE_V_MPU_OPP: + case AM62A7_EFUSE_U_MPU_OPP: + case AM62A7_EFUSE_T_MPU_OPP: + case AM62A7_EFUSE_S_MPU_OPP: + calculated_efuse |= AM62A7_SUPPORT_V_MPU_OPP; + fallthrough; + case AM62A7_EFUSE_R_MPU_OPP: + case AM62A7_EFUSE_Q_MPU_OPP: + case AM62A7_EFUSE_P_MPU_OPP: + case AM62A7_EFUSE_O_MPU_OPP: + calculated_efuse |= AM62A7_SUPPORT_R_MPU_OPP; + fallthrough; + case AM62A7_EFUSE_N_MPU_OPP: + case AM62A7_EFUSE_M_MPU_OPP: + calculated_efuse |= AM62A7_SUPPORT_N_MPU_OPP; + } + + return calculated_efuse; +} + static unsigned long am625_efuse_xlate(struct ti_cpufreq_data *opp_data, unsigned long efuse) { @@ -182,6 +260,7 @@ static struct ti_cpufreq_soc_data omap34xx_soc_data = { .efuse_mask = BIT(3), .rev_offset = OMAP3_CONTROL_IDCODE - OMAP3_SYSCON_BASE, .multi_regulator = false, + .quirks = TI_QUIRK_SYSCON_MAY_BE_MISSING, }; /* @@ -209,6 +288,7 @@ static struct ti_cpufreq_soc_data omap36xx_soc_data = { .efuse_mask = BIT(9), .rev_offset = OMAP3_CONTROL_IDCODE - OMAP3_SYSCON_BASE, .multi_regulator = true, + .quirks = TI_QUIRK_SYSCON_MAY_BE_MISSING, }; /* @@ -223,6 +303,14 @@ static struct ti_cpufreq_soc_data am3517_soc_data = { .efuse_mask = 0, .rev_offset = OMAP3_CONTROL_IDCODE - OMAP3_SYSCON_BASE, .multi_regulator = false, + .quirks = TI_QUIRK_SYSCON_MAY_BE_MISSING, +}; + +static const struct soc_device_attribute k3_cpufreq_soc[] = { + { .family = "AM62X", .revision = "SR1.0" }, + { .family = "AM62AX", .revision = "SR1.0" }, + { .family = "AM62PX", .revision = "SR1.0" }, + { /* sentinel */ } }; static struct ti_cpufreq_soc_data am625_soc_data = { @@ -230,7 +318,23 @@ static struct ti_cpufreq_soc_data am625_soc_data = { .efuse_offset = 0x0018, .efuse_mask = 0x07c0, .efuse_shift = 0x6, - .rev_offset = 0x0014, + .multi_regulator = false, + .quirks = TI_QUIRK_SYSCON_IS_SINGLE_REG, +}; + +static struct ti_cpufreq_soc_data am62a7_soc_data = { + .efuse_xlate = am62a7_efuse_xlate, + .efuse_offset = 0x0, + .efuse_mask = 0x07c0, + .efuse_shift = 0x6, + .multi_regulator = false, +}; + +static struct ti_cpufreq_soc_data am62p5_soc_data = { + .efuse_xlate = am62p5_efuse_xlate, + .efuse_offset = 0x0, + .efuse_mask = 0x07c0, + .efuse_shift = 0x6, .multi_regulator = false, }; @@ -250,7 +354,11 @@ static int ti_cpufreq_get_efuse(struct ti_cpufreq_data *opp_data, ret = regmap_read(opp_data->syscon, opp_data->soc_data->efuse_offset, &efuse); - if (ret == -EIO) { + + if (opp_data->soc_data->quirks & TI_QUIRK_SYSCON_IS_SINGLE_REG && ret == -EIO) + ret = regmap_read(opp_data->syscon, 0x0, &efuse); + + if (opp_data->soc_data->quirks & TI_QUIRK_SYSCON_MAY_BE_MISSING && ret == -EIO) { /* not a syscon register! */ void __iomem *regs = ioremap(OMAP3_SYSCON_BASE + opp_data->soc_data->efuse_offset, 4); @@ -288,10 +396,20 @@ static int ti_cpufreq_get_rev(struct ti_cpufreq_data *opp_data, struct device *dev = opp_data->cpu_dev; u32 revision; int ret; + if (soc_device_match(k3_cpufreq_soc)) { + /* + * Since the SR is 1.0, hard code the revision_value as + * 0x1 here. This way we avoid re using the same register + * that is giving us required information inside socinfo + * anyway. + */ + *revision_value = 0x1; + goto done; + } ret = regmap_read(opp_data->syscon, opp_data->soc_data->rev_offset, &revision); - if (ret == -EIO) { + if (opp_data->soc_data->quirks & TI_QUIRK_SYSCON_MAY_BE_MISSING && ret == -EIO) { /* not a syscon register! */ void __iomem *regs = ioremap(OMAP3_SYSCON_BASE + opp_data->soc_data->rev_offset, 4); @@ -310,6 +428,7 @@ static int ti_cpufreq_get_rev(struct ti_cpufreq_data *opp_data, *revision_value = BIT((revision >> REVISION_SHIFT) & REVISION_MASK); +done: return 0; } @@ -329,7 +448,7 @@ static int ti_cpufreq_setup_syscon_register(struct ti_cpufreq_data *opp_data) return 0; } -static const struct of_device_id ti_cpufreq_of_match[] = { +static const struct of_device_id ti_cpufreq_of_match[] __maybe_unused = { { .compatible = "ti,am33xx", .data = &am3x_soc_data, }, { .compatible = "ti,am3517", .data = &am3517_soc_data, }, { .compatible = "ti,am43", .data = &am4x_soc_data, }, @@ -337,8 +456,8 @@ static const struct of_device_id ti_cpufreq_of_match[] = { { .compatible = "ti,omap34xx", .data = &omap34xx_soc_data, }, { .compatible = "ti,omap36xx", .data = &omap36xx_soc_data, }, { .compatible = "ti,am625", .data = &am625_soc_data, }, - { .compatible = "ti,am62a7", .data = &am625_soc_data, }, - { .compatible = "ti,am62p5", .data = &am625_soc_data, }, + { .compatible = "ti,am62a7", .data = &am62a7_soc_data, }, + { .compatible = "ti,am62p5", .data = &am62p5_soc_data, }, /* legacy */ { .compatible = "ti,omap3430", .data = &omap34xx_soc_data, }, { .compatible = "ti,omap3630", .data = &omap36xx_soc_data, }, @@ -347,12 +466,10 @@ static const struct of_device_id ti_cpufreq_of_match[] = { static const struct of_device_id *ti_cpufreq_match_node(void) { - struct device_node *np; + struct device_node *np __free(device_node) = of_find_node_by_path("/"); const struct of_device_id *match; - np = of_find_node_by_path("/"); match = of_match_node(ti_cpufreq_of_match, np); - of_node_put(np); return match; } @@ -419,7 +536,7 @@ static int ti_cpufreq_probe(struct platform_device *pdev) ret = dev_pm_opp_set_config(opp_data->cpu_dev, &config); if (ret < 0) { - dev_err(opp_data->cpu_dev, "Failed to set OPP config\n"); + dev_err_probe(opp_data->cpu_dev, ret, "Failed to set OPP config\n"); goto fail_put_node; } diff --git a/drivers/cpufreq/vexpress-spc-cpufreq.c b/drivers/cpufreq/vexpress-spc-cpufreq.c index 9ac4ea50b874..0f86cdb7ec8a 100644 --- a/drivers/cpufreq/vexpress-spc-cpufreq.c +++ b/drivers/cpufreq/vexpress-spc-cpufreq.c @@ -447,7 +447,7 @@ static int ve_spc_cpufreq_init(struct cpufreq_policy *policy) return 0; } -static int ve_spc_cpufreq_exit(struct cpufreq_policy *policy) +static void ve_spc_cpufreq_exit(struct cpufreq_policy *policy) { struct device *cpu_dev; @@ -455,11 +455,10 @@ static int ve_spc_cpufreq_exit(struct cpufreq_policy *policy) if (!cpu_dev) { pr_err("%s: failed to get cpu%d device\n", __func__, policy->cpu); - return -ENODEV; + return; } put_cluster_clk_and_freq_table(cpu_dev, policy->related_cpus); - return 0; } static struct cpufreq_driver ve_spc_cpufreq_driver = { @@ -566,7 +565,7 @@ static struct platform_driver ve_spc_cpufreq_platdrv = { .name = "vexpress-spc-cpufreq", }, .probe = ve_spc_cpufreq_probe, - .remove_new = ve_spc_cpufreq_remove, + .remove = ve_spc_cpufreq_remove, }; module_platform_driver(ve_spc_cpufreq_platdrv); diff --git a/drivers/cpufreq/virtual-cpufreq.c b/drivers/cpufreq/virtual-cpufreq.c new file mode 100644 index 000000000000..a050b3a6737f --- /dev/null +++ b/drivers/cpufreq/virtual-cpufreq.c @@ -0,0 +1,333 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2024 Google LLC + */ + +#include <linux/arch_topology.h> +#include <linux/cpufreq.h> +#include <linux/init.h> +#include <linux/sched.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/of_address.h> +#include <linux/of_platform.h> +#include <linux/platform_device.h> +#include <linux/slab.h> + +/* + * CPU0..CPUn + * +-------------+-------------------------------+--------+-------+ + * | Register | Description | Offset | Len | + * +-------------+-------------------------------+--------+-------+ + * | cur_perf | read this register to get | 0x0 | 0x4 | + * | | the current perf (integer val | | | + * | | representing perf relative to | | | + * | | max performance) | | | + * | | that vCPU is running at | | | + * +-------------+-------------------------------+--------+-------+ + * | set_perf | write to this register to set | 0x4 | 0x4 | + * | | perf value of the vCPU | | | + * +-------------+-------------------------------+--------+-------+ + * | perftbl_len | number of entries in perf | 0x8 | 0x4 | + * | | table. A single entry in the | | | + * | | perf table denotes no table | | | + * | | and the entry contains | | | + * | | the maximum perf value | | | + * | | that this vCPU supports. | | | + * | | The guest can request any | | | + * | | value between 1 and max perf | | | + * | | when perftbls are not used. | | | + * +---------------------------------------------+--------+-------+ + * | perftbl_sel | write to this register to | 0xc | 0x4 | + * | | select perf table entry to | | | + * | | read from | | | + * +---------------------------------------------+--------+-------+ + * | perftbl_rd | read this register to get | 0x10 | 0x4 | + * | | perf value of the selected | | | + * | | entry based on perftbl_sel | | | + * +---------------------------------------------+--------+-------+ + * | perf_domain | performance domain number | 0x14 | 0x4 | + * | | that this vCPU belongs to. | | | + * | | vCPUs sharing the same perf | | | + * | | domain number are part of the | | | + * | | same performance domain. | | | + * +-------------+-------------------------------+--------+-------+ + */ + +#define REG_CUR_PERF_STATE_OFFSET 0x0 +#define REG_SET_PERF_STATE_OFFSET 0x4 +#define REG_PERFTBL_LEN_OFFSET 0x8 +#define REG_PERFTBL_SEL_OFFSET 0xc +#define REG_PERFTBL_RD_OFFSET 0x10 +#define REG_PERF_DOMAIN_OFFSET 0x14 +#define PER_CPU_OFFSET 0x1000 + +#define PERFTBL_MAX_ENTRIES 64U + +static void __iomem *base; +static DEFINE_PER_CPU(u32, perftbl_num_entries); + +static void virt_scale_freq_tick(void) +{ + int cpu = smp_processor_id(); + u32 max_freq = (u32)cpufreq_get_hw_max_freq(cpu); + u64 cur_freq; + unsigned long scale; + + cur_freq = (u64)readl_relaxed(base + cpu * PER_CPU_OFFSET + + REG_CUR_PERF_STATE_OFFSET); + + cur_freq <<= SCHED_CAPACITY_SHIFT; + scale = (unsigned long)div_u64(cur_freq, max_freq); + scale = min(scale, SCHED_CAPACITY_SCALE); + + this_cpu_write(arch_freq_scale, scale); +} + +static struct scale_freq_data virt_sfd = { + .source = SCALE_FREQ_SOURCE_VIRT, + .set_freq_scale = virt_scale_freq_tick, +}; + +static unsigned int virt_cpufreq_set_perf(struct cpufreq_policy *policy, + unsigned int target_freq) +{ + writel_relaxed(target_freq, + base + policy->cpu * PER_CPU_OFFSET + REG_SET_PERF_STATE_OFFSET); + return 0; +} + +static unsigned int virt_cpufreq_fast_switch(struct cpufreq_policy *policy, + unsigned int target_freq) +{ + virt_cpufreq_set_perf(policy, target_freq); + return target_freq; +} + +static u32 virt_cpufreq_get_perftbl_entry(int cpu, u32 idx) +{ + writel_relaxed(idx, base + cpu * PER_CPU_OFFSET + + REG_PERFTBL_SEL_OFFSET); + return readl_relaxed(base + cpu * PER_CPU_OFFSET + + REG_PERFTBL_RD_OFFSET); +} + +static int virt_cpufreq_target(struct cpufreq_policy *policy, + unsigned int target_freq, + unsigned int relation) +{ + struct cpufreq_freqs freqs; + int ret = 0; + + freqs.old = policy->cur; + freqs.new = target_freq; + + cpufreq_freq_transition_begin(policy, &freqs); + ret = virt_cpufreq_set_perf(policy, target_freq); + cpufreq_freq_transition_end(policy, &freqs, ret != 0); + + return ret; +} + +static int virt_cpufreq_get_sharing_cpus(struct cpufreq_policy *policy) +{ + u32 cur_perf_domain, perf_domain; + struct device *cpu_dev; + int cpu; + + cur_perf_domain = readl_relaxed(base + policy->cpu * + PER_CPU_OFFSET + REG_PERF_DOMAIN_OFFSET); + + for_each_possible_cpu(cpu) { + cpu_dev = get_cpu_device(cpu); + if (!cpu_dev) + continue; + + perf_domain = readl_relaxed(base + cpu * + PER_CPU_OFFSET + REG_PERF_DOMAIN_OFFSET); + + if (perf_domain == cur_perf_domain) + cpumask_set_cpu(cpu, policy->cpus); + } + + return 0; +} + +static int virt_cpufreq_get_freq_info(struct cpufreq_policy *policy) +{ + struct cpufreq_frequency_table *table; + u32 num_perftbl_entries, idx; + + num_perftbl_entries = per_cpu(perftbl_num_entries, policy->cpu); + + if (num_perftbl_entries == 1) { + policy->cpuinfo.min_freq = 1; + policy->cpuinfo.max_freq = virt_cpufreq_get_perftbl_entry(policy->cpu, 0); + + policy->min = policy->cpuinfo.min_freq; + policy->max = policy->cpuinfo.max_freq; + + policy->cur = policy->max; + return 0; + } + + table = kcalloc(num_perftbl_entries + 1, sizeof(*table), GFP_KERNEL); + if (!table) + return -ENOMEM; + + for (idx = 0; idx < num_perftbl_entries; idx++) + table[idx].frequency = virt_cpufreq_get_perftbl_entry(policy->cpu, idx); + + table[idx].frequency = CPUFREQ_TABLE_END; + policy->freq_table = table; + + return 0; +} + +static int virt_cpufreq_cpu_init(struct cpufreq_policy *policy) +{ + struct device *cpu_dev; + int ret; + + cpu_dev = get_cpu_device(policy->cpu); + if (!cpu_dev) + return -ENODEV; + + ret = virt_cpufreq_get_freq_info(policy); + if (ret) { + dev_warn(cpu_dev, "failed to get cpufreq info\n"); + return ret; + } + + ret = virt_cpufreq_get_sharing_cpus(policy); + if (ret) { + dev_warn(cpu_dev, "failed to get sharing cpumask\n"); + return ret; + } + + /* + * To simplify and improve latency of handling frequency requests on + * the host side, this ensures that the vCPU thread triggering the MMIO + * abort is the same thread whose performance constraints (Ex. uclamp + * settings) need to be updated. This simplifies the VMM (Virtual + * Machine Manager) having to find the correct vCPU thread and/or + * facing permission issues when configuring other threads. + */ + policy->dvfs_possible_from_any_cpu = false; + policy->fast_switch_possible = true; + + /* + * Using the default SCALE_FREQ_SOURCE_CPUFREQ is insufficient since + * the actual physical CPU frequency may not match requested frequency + * from the vCPU thread due to frequency update latencies or other + * inputs to the physical CPU frequency selection. This additional FIE + * source allows for more accurate freq_scale updates and only takes + * effect if another FIE source such as AMUs have not been registered. + */ + topology_set_scale_freq_source(&virt_sfd, policy->cpus); + + return 0; +} + +static void virt_cpufreq_cpu_exit(struct cpufreq_policy *policy) +{ + topology_clear_scale_freq_source(SCALE_FREQ_SOURCE_VIRT, policy->related_cpus); + kfree(policy->freq_table); +} + +static int virt_cpufreq_online(struct cpufreq_policy *policy) +{ + /* Nothing to restore. */ + return 0; +} + +static int virt_cpufreq_offline(struct cpufreq_policy *policy) +{ + /* Dummy offline() to avoid exit() being called and freeing resources. */ + return 0; +} + +static int virt_cpufreq_verify_policy(struct cpufreq_policy_data *policy) +{ + if (policy->freq_table) + return cpufreq_frequency_table_verify(policy, policy->freq_table); + + cpufreq_verify_within_cpu_limits(policy); + return 0; +} + +static struct cpufreq_driver cpufreq_virt_driver = { + .name = "virt-cpufreq", + .init = virt_cpufreq_cpu_init, + .exit = virt_cpufreq_cpu_exit, + .online = virt_cpufreq_online, + .offline = virt_cpufreq_offline, + .verify = virt_cpufreq_verify_policy, + .target = virt_cpufreq_target, + .fast_switch = virt_cpufreq_fast_switch, + .attr = cpufreq_generic_attr, +}; + +static int virt_cpufreq_driver_probe(struct platform_device *pdev) +{ + u32 num_perftbl_entries; + int ret, cpu; + + base = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(base)) + return PTR_ERR(base); + + for_each_possible_cpu(cpu) { + num_perftbl_entries = readl_relaxed(base + cpu * PER_CPU_OFFSET + + REG_PERFTBL_LEN_OFFSET); + + if (!num_perftbl_entries || num_perftbl_entries > PERFTBL_MAX_ENTRIES) + return -ENODEV; + + per_cpu(perftbl_num_entries, cpu) = num_perftbl_entries; + } + + ret = cpufreq_register_driver(&cpufreq_virt_driver); + if (ret) { + dev_err(&pdev->dev, "Virtual CPUFreq driver failed to register: %d\n", ret); + return ret; + } + + dev_dbg(&pdev->dev, "Virtual CPUFreq driver initialized\n"); + return 0; +} + +static void virt_cpufreq_driver_remove(struct platform_device *pdev) +{ + cpufreq_unregister_driver(&cpufreq_virt_driver); +} + +static const struct of_device_id virt_cpufreq_match[] = { + { .compatible = "qemu,virtual-cpufreq", .data = NULL}, + {} +}; +MODULE_DEVICE_TABLE(of, virt_cpufreq_match); + +static struct platform_driver virt_cpufreq_driver = { + .probe = virt_cpufreq_driver_probe, + .remove = virt_cpufreq_driver_remove, + .driver = { + .name = "virt-cpufreq", + .of_match_table = virt_cpufreq_match, + }, +}; + +static int __init virt_cpufreq_init(void) +{ + return platform_driver_register(&virt_cpufreq_driver); +} +postcore_initcall(virt_cpufreq_init); + +static void __exit virt_cpufreq_exit(void) +{ + platform_driver_unregister(&virt_cpufreq_driver); +} +module_exit(virt_cpufreq_exit); + +MODULE_DESCRIPTION("Virtual cpufreq driver"); +MODULE_LICENSE("GPL"); |