diff options
author | Rafael J. Wysocki <rafael.j.wysocki@intel.com> | 2024-06-25 16:25:31 +0200 |
---|---|---|
committer | Rafael J. Wysocki <rafael.j.wysocki@intel.com> | 2024-06-25 16:25:31 +0200 |
commit | 787025a462c7e85d1cfe6294a70c65f1f74031f2 (patch) | |
tree | c7ed7869ad34e04f03656cccb2a8c32cdb94e4c8 /drivers/cpufreq | |
parent | 5e62d53c763aa44be07a7b7ecb5a94a269bb0ed1 (diff) | |
parent | 2240d3e60bb3e7a00422596412d012aeb54c1573 (diff) | |
download | lwn-787025a462c7e85d1cfe6294a70c65f1f74031f2.tar.gz lwn-787025a462c7e85d1cfe6294a70c65f1f74031f2.zip |
Merge tag 'amd-pstate-v6.11-2024-06-24' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/superm1/linux
Merge the second round of changes for amd-pstate in 6.11 from Mario
Limonciello:
"* Enables amd-pstate by default in "shared memory" designs without
a dedicated MSR.
* Adds extra infrastructure for debugging problems.
* Bug fixes found for init/unload failure."
* tag 'amd-pstate-v6.11-2024-06-24' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/superm1/linux:
cpufreq: simplify boolean parsing with kstrtobool in store function
cpufreq: amd-pstate: Don't create attributes when registration fails
cpufreq: amd-pstate: Make amd-pstate unit tests depend on amd-pstate
cpufreq/amd-pstate: fix setting policy current frequency value
cpufreq: amd-pstate: auto-load pstate driver by default
cpufreq: amd-pstate: enable shared memory type CPPC by default
cpufreq: amd-pstate: switch boot_cpu_has() to cpu_feature_enabled()
Documentation: PM: amd-pstate: add guided mode to the Operation mode
cpufreq: amd-pstate: add debug message while CPPC is supported and disabled by SBIOS
cpufreq: amd-pstate: show CPPC debug message if CPPC is not supported
cpufreq: amd-pstate: remove unused variable nominal_freq
cpufreq: amd-pstate: optimize the initial frequency values verification
cpufreq: amd-pstate: Allow users to write 'default' EPP string
Diffstat (limited to 'drivers/cpufreq')
-rw-r--r-- | drivers/cpufreq/Kconfig.x86 | 1 | ||||
-rw-r--r-- | drivers/cpufreq/amd-pstate.c | 176 | ||||
-rw-r--r-- | drivers/cpufreq/amd-pstate.h | 1 | ||||
-rw-r--r-- | drivers/cpufreq/cpufreq.c | 11 |
4 files changed, 121 insertions, 68 deletions
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/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index fda8f86c90e0..afcf398574f6 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -86,15 +86,6 @@ struct quirk_entry { 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; @@ -158,7 +149,7 @@ static int __init dmi_matched_7k62_bios_bug(const struct dmi_system_id *dmi) * broken BIOS lack of nominal_freq and lowest_freq capabilities * definition in ACPI tables */ - if (boot_cpu_has(X86_FEATURE_ZEN2)) { + 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; @@ -200,7 +191,7 @@ static s16 amd_pstate_get_epp(struct amd_cpudata *cpudata, u64 cppc_req_cached) u64 epp; int ret; - if (boot_cpu_has(X86_FEATURE_CPPC)) { + if (cpu_feature_enabled(X86_FEATURE_CPPC)) { if (!cppc_req_cached) { epp = rdmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, &cppc_req_cached); @@ -253,7 +244,7 @@ static int amd_pstate_set_epp(struct amd_cpudata *cpudata, u32 epp) int ret; struct cppc_perf_ctrls perf_ctrls; - if (boot_cpu_has(X86_FEATURE_CPPC)) { + if (cpu_feature_enabled(X86_FEATURE_CPPC)) { u64 value = READ_ONCE(cpudata->cppc_req_cached); value &= ~GENMASK_ULL(31, 24); @@ -282,10 +273,8 @@ static int amd_pstate_set_energy_pref_index(struct amd_cpudata *cpudata, int epp = -EINVAL; int ret; - if (!pref_index) { - pr_debug("EPP pref_index is invalid\n"); - return -EINVAL; - } + if (!pref_index) + epp = cpudata->epp_default; if (epp == -EINVAL) epp = epp_values[pref_index]; @@ -522,6 +511,8 @@ 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) { + unsigned long max_freq; + struct cpufreq_policy *policy = cpufreq_cpu_get(cpudata->cpu); u64 prev = READ_ONCE(cpudata->cppc_req_cached); u64 value = prev; @@ -531,6 +522,9 @@ static void amd_pstate_update(struct amd_cpudata *cpudata, u32 min_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; @@ -652,10 +646,9 @@ 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; if (policy->min != cpudata->min_limit_freq || policy->max != cpudata->max_limit_freq) amd_pstate_update_min_max_limit(policy); @@ -663,7 +656,6 @@ 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) @@ -681,8 +673,6 @@ static void amd_pstate_adjust_perf(unsigned int cpu, 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); @@ -754,7 +744,7 @@ static int amd_pstate_get_highest_perf(int cpu, u32 *highest_perf) { int ret; - if (boot_cpu_has(X86_FEATURE_CPPC)) { + if (cpu_feature_enabled(X86_FEATURE_CPPC)) { u64 cap1; ret = rdmsrl_safe_on_cpu(cpu, MSR_AMD_CPPC_CAP1, &cap1); @@ -926,12 +916,30 @@ static int amd_pstate_init_freq(struct amd_cpudata *cpudata) WRITE_ONCE(cpudata->nominal_freq, nominal_freq); WRITE_ONCE(cpudata->max_freq, max_freq); + /** + * 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 * 1000); + return -EINVAL; + } + + if (lowest_nonlinear_freq <= min_freq || lowest_nonlinear_freq > nominal_freq * 1000) { + 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 * 1000); + return -EINVAL; + } + return 0; } static int amd_pstate_cpu_init(struct cpufreq_policy *policy) { - int min_freq, max_freq, nominal_freq, ret; + int min_freq, max_freq, ret; struct device *dev; struct amd_cpudata *cpudata; @@ -962,16 +970,6 @@ static int amd_pstate_cpu_init(struct cpufreq_policy *policy) min_freq = READ_ONCE(cpudata->min_freq); max_freq = READ_ONCE(cpudata->max_freq); - nominal_freq = READ_ONCE(cpudata->nominal_freq); - - if (min_freq <= 0 || max_freq <= 0 || - nominal_freq <= 0 || min_freq > max_freq) { - dev_err(dev, - "min_freq(%d) or max_freq(%d) or nominal_freq (%d) value is incorrect, check _CPC in ACPI tables\n", - min_freq, max_freq, nominal_freq); - ret = -EINVAL; - goto free_cpudata1; - } policy->cpuinfo.transition_latency = amd_pstate_get_transition_latency(policy->cpu); policy->transition_delay_us = amd_pstate_get_transition_delay_us(policy->cpu); @@ -985,7 +983,7 @@ static int amd_pstate_cpu_init(struct cpufreq_policy *policy) /* 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], @@ -1218,7 +1216,7 @@ 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) { @@ -1391,7 +1389,7 @@ 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, ret; + int min_freq, max_freq, ret; struct amd_cpudata *cpudata; struct device *dev; u64 value; @@ -1424,15 +1422,6 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy) min_freq = READ_ONCE(cpudata->min_freq); max_freq = READ_ONCE(cpudata->max_freq); - nominal_freq = READ_ONCE(cpudata->nominal_freq); - if (min_freq <= 0 || max_freq <= 0 || - nominal_freq <= 0 || min_freq > max_freq) { - dev_err(dev, - "min_freq(%d) or max_freq(%d) or nominal_freq(%d) value is incorrect, check _CPC in ACPI tables\n", - min_freq, max_freq, nominal_freq); - ret = -EINVAL; - goto free_cpudata1; - } policy->cpuinfo.min_freq = min_freq; policy->cpuinfo.max_freq = max_freq; @@ -1441,7 +1430,7 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy) policy->driver_data = cpudata; - cpudata->epp_cached = amd_pstate_get_epp(cpudata, 0); + cpudata->epp_cached = cpudata->epp_default = amd_pstate_get_epp(cpudata, 0); policy->min = policy->cpuinfo.min_freq; policy->max = policy->cpuinfo.max_freq; @@ -1456,7 +1445,7 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy) else policy->policy = CPUFREQ_POLICY_POWERSAVE; - 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; @@ -1546,7 +1535,7 @@ static void amd_pstate_epp_update_limit(struct cpufreq_policy *policy) epp = 0; /* Set initial EPP value */ - if (boot_cpu_has(X86_FEATURE_CPPC)) { + if (cpu_feature_enabled(X86_FEATURE_CPPC)) { value &= ~GENMASK_ULL(31, 24); value |= (u64)epp << 24; } @@ -1569,6 +1558,12 @@ static int amd_pstate_epp_set_policy(struct cpufreq_policy *policy) amd_pstate_epp_update_limit(policy); + /* + * 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; } @@ -1585,7 +1580,7 @@ static void amd_pstate_epp_reenable(struct amd_cpudata *cpudata) value = READ_ONCE(cpudata->cppc_req_cached); max_perf = READ_ONCE(cpudata->highest_perf); - if (boot_cpu_has(X86_FEATURE_CPPC)) { + if (cpu_feature_enabled(X86_FEATURE_CPPC)) { wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, value); } else { perf_ctrls.max_perf = max_perf; @@ -1619,7 +1614,7 @@ static void amd_pstate_epp_offline(struct cpufreq_policy *policy) value = READ_ONCE(cpudata->cppc_req_cached); mutex_lock(&amd_pstate_limits_lock); - if (boot_cpu_has(X86_FEATURE_CPPC)) { + if (cpu_feature_enabled(X86_FEATURE_CPPC)) { cpudata->epp_policy = CPUFREQ_POLICY_UNKNOWN; /* Set max perf same as min perf */ @@ -1746,6 +1741,46 @@ static int __init amd_pstate_set_driver(int mode_idx) return -EINVAL; } +/** + * 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) +{ + struct cpuinfo_x86 *c = &cpu_data(0); + bool warn = false; + + 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; + } + + /* + * If the CPPC feature is disabled in the BIOS for processors that support MSR-based CPPC, + * the AMD Pstate driver may not function correctly. + * Check the CPPC flag and display a warning message if the platform supports CPPC. + * Note: below checking code will not abort the driver registeration process because of + * the code is added for debugging purposes. + */ + if (!cpu_feature_enabled(X86_FEATURE_CPPC)) { + if (cpu_feature_enabled(X86_FEATURE_ZEN1) || cpu_feature_enabled(X86_FEATURE_ZEN2)) { + if (c->x86_model > 0x60 && c->x86_model < 0xaf) + warn = true; + } else if (cpu_feature_enabled(X86_FEATURE_ZEN3) || cpu_feature_enabled(X86_FEATURE_ZEN4)) { + if ((c->x86_model > 0x10 && c->x86_model < 0x1F) || + (c->x86_model > 0x40 && c->x86_model < 0xaf)) + warn = true; + } else if (cpu_feature_enabled(X86_FEATURE_ZEN5)) { + warn = true; + } + } + + 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) { struct device *dev_root; @@ -1754,6 +1789,11 @@ 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; @@ -1768,35 +1808,43 @@ static int __init amd_pstate_init(void) /* check if this machine need CPPC quirks */ dmi_check_system(amd_pstate_quirks_table); - switch (cppc_state) { - case AMD_PSTATE_UNDEFINED: + /* + * 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 */ 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()) { 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; + /* get driver mode from kernel config option [1:4] */ + cppc_state = CONFIG_X86_AMD_PSTATE_DEFAULT_MODE; + } + + switch (cppc_state) { case 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: + ret = amd_pstate_set_driver(cppc_state); + if (ret) + return ret; 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; @@ -1810,13 +1858,15 @@ static int __init amd_pstate_init(void) /* enable amd pstate feature */ ret = amd_pstate_enable(true); if (ret) { - pr_err("failed to enable with return %d\n", ret); + pr_err("failed to enable driver mode(%d)\n", cppc_state); return ret; } ret = cpufreq_register_driver(current_pstate_driver); - if (ret) + if (ret) { pr_err("failed to register with return %d\n", ret); + goto disable_driver; + } dev_root = bus_get_dev_root(&cpu_subsys); if (dev_root) { @@ -1832,6 +1882,8 @@ static int __init amd_pstate_init(void) global_attr_free: cpufreq_unregister_driver(current_pstate_driver); +disable_driver: + amd_pstate_enable(false); return ret; } device_initcall(amd_pstate_init); diff --git a/drivers/cpufreq/amd-pstate.h b/drivers/cpufreq/amd-pstate.h index e6a28e7f4dbf..f80b33fa5d43 100644 --- a/drivers/cpufreq/amd-pstate.h +++ b/drivers/cpufreq/amd-pstate.h @@ -99,6 +99,7 @@ struct amd_cpudata { u32 policy; u64 cppc_cap1_cached; bool suspended; + s16 epp_default; }; #endif /* _LINUX_AMD_PSTATE_H */ diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index e678ea7b0891..82c500389a40 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -614,10 +614,9 @@ static ssize_t show_boost(struct kobject *kobj, 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)) { @@ -641,10 +640,10 @@ 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) |