From 1f5e62f5fb217f2c1e003236be7d03cf606c26c4 Mon Sep 17 00:00:00 2001 From: Srinivas Pandruvada Date: Thu, 2 Mar 2023 20:14:11 -0800 Subject: [PATCH 01/12] cpufreq: intel_pstate: Enable HWP IO boost for all servers The HWP IO boost results in slight improvements for IO performance on both Ice Lake and Sapphire Rapid servers. Currently there is a CPU model check for Skylake desktop and server along with the ACPI PM profile for performance and enterprise servers to enable IO boost. Remove the CPU model check, so that all current server models enable HWP IO boost by default. Signed-off-by: Srinivas Pandruvada Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/intel_pstate.c | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 48a4613cef1e..2a1a6779d82d 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -2384,12 +2384,6 @@ static const struct x86_cpu_id intel_pstate_cpu_ee_disable_ids[] = { {} }; -static const struct x86_cpu_id intel_pstate_hwp_boost_ids[] = { - X86_MATCH(SKYLAKE_X, core_funcs), - X86_MATCH(SKYLAKE, core_funcs), - {} -}; - static int intel_pstate_init_cpu(unsigned int cpunum) { struct cpudata *cpu; @@ -2408,12 +2402,9 @@ static int intel_pstate_init_cpu(unsigned int cpunum) cpu->epp_default = -EINVAL; if (hwp_active) { - const struct x86_cpu_id *id; - intel_pstate_hwp_enable(cpu); - id = x86_match_cpu(intel_pstate_hwp_boost_ids); - if (id && intel_pstate_acpi_pm_profile_server()) + if (intel_pstate_acpi_pm_profile_server()) hwp_boost = true; } } else if (hwp_active) { From 76531df5e13b5b997a17940d6980a168c616e962 Mon Sep 17 00:00:00 2001 From: Wyes Karny Date: Tue, 7 Mar 2023 11:27:35 +0000 Subject: [PATCH 02/12] ACPI: CPPC: Add min and max perf register writing support Currently writing of min and max perf register is deferred in cppc_set_perf function. In CPPC guided mode, these registers needed to be written to guide the platform about min and max perf levels. Add this support to make guided mode work properly on AMD shared memory systems. Acked-by: Huang Rui Reviewed-by: Mario Limonciello Tested-by: Oleksandr Natalenko Signed-off-by: Wyes Karny [ rjw: Fixed up a multiline comment, subject edits ] Signed-off-by: Rafael J. Wysocki --- drivers/acpi/cppc_acpi.c | 24 ++++++++++++++++-------- 1 file changed, 16 insertions(+), 8 deletions(-) diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c index c51d3ccb4cca..523bad4e3a0c 100644 --- a/drivers/acpi/cppc_acpi.c +++ b/drivers/acpi/cppc_acpi.c @@ -1488,7 +1488,7 @@ EXPORT_SYMBOL_GPL(cppc_set_enable); int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls) { struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpu); - struct cpc_register_resource *desired_reg; + struct cpc_register_resource *desired_reg, *min_perf_reg, *max_perf_reg; int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpu); struct cppc_pcc_data *pcc_ss_data = NULL; int ret = 0; @@ -1499,6 +1499,8 @@ int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls) } desired_reg = &cpc_desc->cpc_regs[DESIRED_PERF]; + min_perf_reg = &cpc_desc->cpc_regs[MIN_PERF]; + max_perf_reg = &cpc_desc->cpc_regs[MAX_PERF]; /* * This is Phase-I where we want to write to CPC registers @@ -1507,7 +1509,7 @@ int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls) * Since read_lock can be acquired by multiple CPUs simultaneously we * achieve that goal here */ - if (CPC_IN_PCC(desired_reg)) { + if (CPC_IN_PCC(desired_reg) || CPC_IN_PCC(min_perf_reg) || CPC_IN_PCC(max_perf_reg)) { if (pcc_ss_id < 0) { pr_debug("Invalid pcc_ss_id\n"); return -ENODEV; @@ -1530,13 +1532,19 @@ int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls) cpc_desc->write_cmd_status = 0; } - /* - * Skip writing MIN/MAX until Linux knows how to come up with - * useful values. - */ cpc_write(cpu, desired_reg, perf_ctrls->desired_perf); - if (CPC_IN_PCC(desired_reg)) + /* + * Only write if min_perf and max_perf not zero. Some drivers pass zero + * value to min and max perf, but they don't mean to set the zero value, + * they just don't want to write to those registers. + */ + if (perf_ctrls->min_perf) + cpc_write(cpu, min_perf_reg, perf_ctrls->min_perf); + if (perf_ctrls->max_perf) + cpc_write(cpu, max_perf_reg, perf_ctrls->max_perf); + + if (CPC_IN_PCC(desired_reg) || CPC_IN_PCC(min_perf_reg) || CPC_IN_PCC(max_perf_reg)) up_read(&pcc_ss_data->pcc_lock); /* END Phase-I */ /* * This is Phase-II where we transfer the ownership of PCC to Platform @@ -1584,7 +1592,7 @@ int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls) * case during a CMD_READ and if there are pending writes it delivers * the write command before servicing the read command */ - if (CPC_IN_PCC(desired_reg)) { + if (CPC_IN_PCC(desired_reg) || CPC_IN_PCC(min_perf_reg) || CPC_IN_PCC(max_perf_reg)) { if (down_write_trylock(&pcc_ss_data->pcc_lock)) {/* BEGIN Phase-II */ /* Update only if there are pending write commands */ if (pcc_ss_data->pending_pcc_write_cmd) From c984f5d5d45bd5f80d6a9d8541e809300c963aca Mon Sep 17 00:00:00 2001 From: Wyes Karny Date: Tue, 7 Mar 2023 11:27:36 +0000 Subject: [PATCH 03/12] ACPI: CPPC: Add auto select register read/write support For some AMD shared memory based systems, the autonomous selection bit needed to be set explicitly. Add autonomous selection register related APIs to acpi driver, which amd_pstate driver uses later. Acked-by: Huang Rui Reviewed-by: Mario Limonciello Tested-by: Oleksandr Natalenko Signed-off-by: Wyes Karny [ rjw: Fixed up kerneldoc comments, white space adjustment, subject edits ] Signed-off-by: Rafael J. Wysocki --- drivers/acpi/cppc_acpi.c | 96 ++++++++++++++++++++++++++++++++++++++++ include/acpi/cppc_acpi.h | 11 +++++ 2 files changed, 107 insertions(+) diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c index 523bad4e3a0c..7ff269a78c20 100644 --- a/drivers/acpi/cppc_acpi.c +++ b/drivers/acpi/cppc_acpi.c @@ -1433,6 +1433,102 @@ int cppc_set_epp_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls, bool enable) } EXPORT_SYMBOL_GPL(cppc_set_epp_perf); +/** + * cppc_get_auto_sel_caps - Read autonomous selection register. + * @cpunum : CPU from which to read register. + * @perf_caps : struct where autonomous selection register value is updated. + */ +int cppc_get_auto_sel_caps(int cpunum, struct cppc_perf_caps *perf_caps) +{ + struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpunum); + struct cpc_register_resource *auto_sel_reg; + u64 auto_sel; + + if (!cpc_desc) { + pr_debug("No CPC descriptor for CPU:%d\n", cpunum); + return -ENODEV; + } + + auto_sel_reg = &cpc_desc->cpc_regs[AUTO_SEL_ENABLE]; + + if (!CPC_SUPPORTED(auto_sel_reg)) + pr_warn_once("Autonomous mode is not unsupported!\n"); + + if (CPC_IN_PCC(auto_sel_reg)) { + int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpunum); + struct cppc_pcc_data *pcc_ss_data = NULL; + int ret = 0; + + if (pcc_ss_id < 0) + return -ENODEV; + + pcc_ss_data = pcc_data[pcc_ss_id]; + + down_write(&pcc_ss_data->pcc_lock); + + if (send_pcc_cmd(pcc_ss_id, CMD_READ) >= 0) { + cpc_read(cpunum, auto_sel_reg, &auto_sel); + perf_caps->auto_sel = (bool)auto_sel; + } else { + ret = -EIO; + } + + up_write(&pcc_ss_data->pcc_lock); + + return ret; + } + + return 0; +} +EXPORT_SYMBOL_GPL(cppc_get_auto_sel_caps); + +/** + * cppc_set_auto_sel - Write autonomous selection register. + * @cpu : CPU to which to write register. + * @enable : the desired value of autonomous selection resiter to be updated. + */ +int cppc_set_auto_sel(int cpu, bool enable) +{ + int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpu); + struct cpc_register_resource *auto_sel_reg; + struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpu); + struct cppc_pcc_data *pcc_ss_data = NULL; + int ret = -EINVAL; + + if (!cpc_desc) { + pr_debug("No CPC descriptor for CPU:%d\n", cpu); + return -ENODEV; + } + + auto_sel_reg = &cpc_desc->cpc_regs[AUTO_SEL_ENABLE]; + + if (CPC_IN_PCC(auto_sel_reg)) { + if (pcc_ss_id < 0) { + pr_debug("Invalid pcc_ss_id\n"); + return -ENODEV; + } + + if (CPC_SUPPORTED(auto_sel_reg)) { + ret = cpc_write(cpu, auto_sel_reg, enable); + if (ret) + return ret; + } + + pcc_ss_data = pcc_data[pcc_ss_id]; + + down_write(&pcc_ss_data->pcc_lock); + /* after writing CPC, transfer the ownership of PCC to platform */ + ret = send_pcc_cmd(pcc_ss_id, CMD_WRITE); + up_write(&pcc_ss_data->pcc_lock); + } else { + ret = -ENOTSUPP; + pr_debug("_CPC in PCC is not supported\n"); + } + + return ret; +} +EXPORT_SYMBOL_GPL(cppc_set_auto_sel); + /** * cppc_set_enable - Set to enable CPPC on the processor by writing the * Continuous Performance Control package EnableRegister field. diff --git a/include/acpi/cppc_acpi.h b/include/acpi/cppc_acpi.h index 6b487a5bd638..6126c977ece0 100644 --- a/include/acpi/cppc_acpi.h +++ b/include/acpi/cppc_acpi.h @@ -109,6 +109,7 @@ struct cppc_perf_caps { u32 lowest_freq; u32 nominal_freq; u32 energy_perf; + bool auto_sel; }; struct cppc_perf_ctrls { @@ -153,6 +154,8 @@ extern int cpc_read_ffh(int cpunum, struct cpc_reg *reg, u64 *val); extern int cpc_write_ffh(int cpunum, struct cpc_reg *reg, u64 val); extern int cppc_get_epp_perf(int cpunum, u64 *epp_perf); extern int cppc_set_epp_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls, bool enable); +extern int cppc_get_auto_sel_caps(int cpunum, struct cppc_perf_caps *perf_caps); +extern int cppc_set_auto_sel(int cpu, bool enable); #else /* !CONFIG_ACPI_CPPC_LIB */ static inline int cppc_get_desired_perf(int cpunum, u64 *desired_perf) { @@ -214,6 +217,14 @@ static inline int cppc_get_epp_perf(int cpunum, u64 *epp_perf) { return -ENOTSUPP; } +static inline int cppc_set_auto_sel(int cpu, bool enable) +{ + return -ENOTSUPP; +} +static inline int cppc_get_auto_sel_caps(int cpunum, struct cppc_perf_caps *perf_caps) +{ + return -ENOTSUPP; +} #endif /* !CONFIG_ACPI_CPPC_LIB */ #endif /* _CPPC_ACPI_H*/ From 3e6e078057640751654bda9fd2278a944f61fa4a Mon Sep 17 00:00:00 2001 From: Wyes Karny Date: Tue, 7 Mar 2023 11:27:37 +0000 Subject: [PATCH 04/12] Documentation: cpufreq: amd-pstate: Move amd_pstate param to alphabetical order Move amd_pstate command line param description to correct alphabetical order. Acked-by: Huang Rui Reviewed-by: Mario Limonciello Tested-by: Oleksandr Natalenko Signed-off-by: Wyes Karny Signed-off-by: Rafael J. Wysocki --- .../admin-guide/kernel-parameters.txt | 35 ++++++++++--------- 1 file changed, 18 insertions(+), 17 deletions(-) diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 6221a1d057dd..1e38f3ae0e62 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -339,6 +339,24 @@ This mode requires kvm-amd.avic=1. (Default when IOMMU HW support is present.) + amd_pstate= [X86] + disable + Do not enable amd_pstate as the default + scaling driver for the supported processors + passive + Use amd_pstate as a scaling driver, driver requests a + desired performance on this abstract scale and the power + management firmware translates the requests into actual + hardware states (core frequency, data fabric and memory + clocks etc.) + active + Use amd_pstate_epp driver instance as the scaling driver, + driver provides a hint to the hardware if software wants + to bias toward performance (0x0) or energy efficiency (0xff) + to the CPPC firmware. then CPPC power algorithm will + calculate the runtime workload and adjust the realtime cores + frequency. + amijoy.map= [HW,JOY] Amiga joystick support Map of devices attached to JOY0DAT and JOY1DAT Format: , @@ -7059,20 +7077,3 @@ xmon commands. off xmon is disabled. - amd_pstate= [X86] - disable - Do not enable amd_pstate as the default - scaling driver for the supported processors - passive - Use amd_pstate as a scaling driver, driver requests a - desired performance on this abstract scale and the power - management firmware translates the requests into actual - hardware states (core frequency, data fabric and memory - clocks etc.) - active - Use amd_pstate_epp driver instance as the scaling driver, - driver provides a hint to the hardware if software wants - to bias toward performance (0x0) or energy efficiency (0xff) - to the CPPC firmware. then CPPC power algorithm will - calculate the runtime workload and adjust the realtime cores - frequency. From 2dd6d0ebf74049256160a3d03dabbd92fe0b8599 Mon Sep 17 00:00:00 2001 From: Wyes Karny Date: Tue, 7 Mar 2023 11:27:38 +0000 Subject: [PATCH 05/12] cpufreq: amd-pstate: Add guided autonomous mode From ACPI spec below 3 modes for CPPC can be defined: 1. Non autonomous: OS scaling governor specifies operating frequency/ performance level through `Desired Performance` register and platform follows that. 2. Guided autonomous: OS scaling governor specifies min and max frequencies/ performance levels through `Minimum Performance` and `Maximum Performance` register, and platform can autonomously select an operating frequency in this range. 3. Fully autonomous: OS only hints (via EPP) to platform for the required energy performance preference for the workload and platform autonomously scales the frequency. Currently (1) is supported by amd_pstate as passive mode, and (3) is implemented by EPP support. This change is to support (2). In guided autonomous mode the min_perf is based on the input from the scaling governor. For example, in case of schedutil this value depends on the current utilization. And max_perf is set to max capacity. To activate guided auto mode ``amd_pstate=guided`` command line parameter has to be passed in the kernel. Acked-by: Huang Rui Reviewed-by: Mario Limonciello Tested-by: Oleksandr Natalenko Signed-off-by: Wyes Karny Signed-off-by: Rafael J. Wysocki --- .../admin-guide/kernel-parameters.txt | 15 +++++--- drivers/cpufreq/amd-pstate.c | 34 +++++++++++++++---- include/linux/amd-pstate.h | 2 ++ 3 files changed, 40 insertions(+), 11 deletions(-) diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 1e38f3ae0e62..1e5fe4891dd7 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -344,11 +344,11 @@ Do not enable amd_pstate as the default scaling driver for the supported processors passive - Use amd_pstate as a scaling driver, driver requests a - desired performance on this abstract scale and the power - management firmware translates the requests into actual - hardware states (core frequency, data fabric and memory - clocks etc.) + Use amd_pstate with passive mode as a scaling driver. + In this mode autonomous selection is disabled. + Driver requests a desired performance level and platform + tries to match the same performance level if it is + satisfied by guaranteed performance level. active Use amd_pstate_epp driver instance as the scaling driver, driver provides a hint to the hardware if software wants @@ -356,6 +356,11 @@ to the CPPC firmware. then CPPC power algorithm will calculate the runtime workload and adjust the realtime cores frequency. + guided + Activate guided autonomous mode. Driver requests minimum and + maximum performance level and the platform autonomously + selects a performance level in this range and appropriate + to the current workload. amijoy.map= [HW,JOY] Amiga joystick support Map of devices attached to JOY0DAT and JOY1DAT diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index 73c7643b2697..61dcd7b89b26 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -308,7 +308,22 @@ static int cppc_init_perf(struct amd_cpudata *cpudata) cppc_perf.lowest_nonlinear_perf); WRITE_ONCE(cpudata->lowest_perf, cppc_perf.lowest_perf); - return 0; + if (cppc_state == AMD_PSTATE_ACTIVE) + return 0; + + ret = cppc_get_auto_sel_caps(cpudata->cpu, &cppc_perf); + if (ret) { + pr_warn("failed to get auto_sel, ret: %d\n", ret); + return 0; + } + + ret = cppc_set_auto_sel(cpudata->cpu, + (cppc_state == AMD_PSTATE_PASSIVE) ? 0 : 1); + + if (ret) + pr_warn("failed to set auto_sel, ret: %d\n", ret); + + return ret; } DEFINE_STATIC_CALL(amd_pstate_init_perf, pstate_init_perf); @@ -385,12 +400,18 @@ 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) + u32 des_perf, u32 max_perf, bool fast_switch, int gov_flags) { u64 prev = READ_ONCE(cpudata->cppc_req_cached); u64 value = prev; des_perf = clamp_t(unsigned long, des_perf, min_perf, 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); @@ -445,7 +466,7 @@ static int amd_pstate_target(struct cpufreq_policy *policy, cpufreq_freq_transition_begin(policy, &freqs); amd_pstate_update(cpudata, min_perf, des_perf, - max_perf, false); + max_perf, false, policy->governor->flags); cpufreq_freq_transition_end(policy, &freqs, false); return 0; @@ -479,7 +500,8 @@ static void amd_pstate_adjust_perf(unsigned int cpu, if (max_perf < min_perf) max_perf = min_perf; - amd_pstate_update(cpudata, min_perf, des_perf, max_perf, true); + amd_pstate_update(cpudata, min_perf, des_perf, max_perf, true, + policy->governor->flags); cpufreq_cpu_put(policy); } @@ -1279,7 +1301,7 @@ static int __init amd_pstate_init(void) /* capability check */ if (boot_cpu_has(X86_FEATURE_CPPC)) { pr_debug("AMD CPPC MSR based functionality is supported\n"); - if (cppc_state == AMD_PSTATE_PASSIVE) + 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"); @@ -1341,7 +1363,7 @@ static int __init amd_pstate_param(char *str) if (cppc_state == AMD_PSTATE_ACTIVE) current_pstate_driver = &amd_pstate_epp_driver; - if (cppc_state == AMD_PSTATE_PASSIVE) + if (cppc_state == AMD_PSTATE_PASSIVE || cppc_state == AMD_PSTATE_GUIDED) current_pstate_driver = &amd_pstate_driver; return 0; diff --git a/include/linux/amd-pstate.h b/include/linux/amd-pstate.h index f5f22418e64b..c10ebf8c42e6 100644 --- a/include/linux/amd-pstate.h +++ b/include/linux/amd-pstate.h @@ -97,6 +97,7 @@ enum amd_pstate_mode { AMD_PSTATE_DISABLE = 0, AMD_PSTATE_PASSIVE, AMD_PSTATE_ACTIVE, + AMD_PSTATE_GUIDED, AMD_PSTATE_MAX, }; @@ -104,6 +105,7 @@ static const char * const amd_pstate_mode_string[] = { [AMD_PSTATE_DISABLE] = "disable", [AMD_PSTATE_PASSIVE] = "passive", [AMD_PSTATE_ACTIVE] = "active", + [AMD_PSTATE_GUIDED] = "guided", NULL, }; #endif /* _LINUX_AMD_PSTATE_H */ From 3ca7bc818d8ccf399cb0366d8d9a915c04a446f9 Mon Sep 17 00:00:00 2001 From: Wyes Karny Date: Tue, 7 Mar 2023 11:27:39 +0000 Subject: [PATCH 06/12] cpufreq: amd-pstate: Add guided mode control support via sysfs amd_pstate driver's `status` sysfs entry helps to control the driver's mode dynamically by user. After the addition of guided mode the combinations of mode transitions have been increased (16 combinations). Therefore optimise the amd_pstate_update_status function by implementing a state transition table. There are 4 states amd_pstate supports, namely: 'disable', 'passive', 'active', and 'guided'. The transition from any state to any other state is possible after this change. Sysfs interface: To disable amd_pstate driver: # echo disable > /sys/devices/system/cpu/amd_pstate/status To enable passive mode: # echo passive > /sys/devices/system/cpu/amd_pstate/status To change mode to active: # echo active > /sys/devices/system/cpu/amd_pstate/status To change mode to guided: # echo guided > /sys/devices/system/cpu/amd_pstate/status Acked-by: Huang Rui Reviewed-by: Mario Limonciello Tested-by: Oleksandr Natalenko Signed-off-by: Wyes Karny Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/amd-pstate.c | 143 +++++++++++++++++++++++++---------- 1 file changed, 101 insertions(+), 42 deletions(-) diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index 61dcd7b89b26..7955cfc91c31 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -106,6 +106,8 @@ static unsigned int epp_values[] = { [EPP_INDEX_POWERSAVE] = AMD_CPPC_EPP_POWERSAVE, }; +typedef int (*cppc_mode_transition_fn)(int); + static inline int get_mode_idx_from_str(const char *str, size_t size) { int i; @@ -838,6 +840,98 @@ static ssize_t show_energy_performance_preference( return sysfs_emit(buf, "%s\n", energy_perf_strings[preference]); } +static void amd_pstate_driver_cleanup(void) +{ + amd_pstate_enable(false); + cppc_state = AMD_PSTATE_DISABLE; + current_pstate_driver = NULL; +} + +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; + + cppc_state = mode; + ret = cpufreq_register_driver(current_pstate_driver); + if (ret) { + amd_pstate_driver_cleanup(); + return ret; + } + return 0; +} + +static int amd_pstate_unregister_driver(int dummy) +{ + cpufreq_unregister_driver(current_pstate_driver); + amd_pstate_driver_cleanup(); + return 0; +} + +static int amd_pstate_change_mode_without_dvr_change(int mode) +{ + int cpu = 0; + + cppc_state = mode; + + if (boot_cpu_has(X86_FEATURE_CPPC) || cppc_state == AMD_PSTATE_ACTIVE) + return 0; + + for_each_present_cpu(cpu) { + cppc_set_auto_sel(cpu, (cppc_state == AMD_PSTATE_PASSIVE) ? 0 : 1); + } + + return 0; +} + +static int amd_pstate_change_driver_mode(int mode) +{ + int ret; + + ret = amd_pstate_unregister_driver(0); + if (ret) + return ret; + + ret = amd_pstate_register_driver(mode); + if (ret) + return ret; + + return 0; +} + +cppc_mode_transition_fn mode_state_machine[AMD_PSTATE_MAX][AMD_PSTATE_MAX] = { + [AMD_PSTATE_DISABLE] = { + [AMD_PSTATE_DISABLE] = NULL, + [AMD_PSTATE_PASSIVE] = amd_pstate_register_driver, + [AMD_PSTATE_ACTIVE] = amd_pstate_register_driver, + [AMD_PSTATE_GUIDED] = amd_pstate_register_driver, + }, + [AMD_PSTATE_PASSIVE] = { + [AMD_PSTATE_DISABLE] = amd_pstate_unregister_driver, + [AMD_PSTATE_PASSIVE] = NULL, + [AMD_PSTATE_ACTIVE] = amd_pstate_change_driver_mode, + [AMD_PSTATE_GUIDED] = amd_pstate_change_mode_without_dvr_change, + }, + [AMD_PSTATE_ACTIVE] = { + [AMD_PSTATE_DISABLE] = amd_pstate_unregister_driver, + [AMD_PSTATE_PASSIVE] = amd_pstate_change_driver_mode, + [AMD_PSTATE_ACTIVE] = NULL, + [AMD_PSTATE_GUIDED] = amd_pstate_change_driver_mode, + }, + [AMD_PSTATE_GUIDED] = { + [AMD_PSTATE_DISABLE] = amd_pstate_unregister_driver, + [AMD_PSTATE_PASSIVE] = amd_pstate_change_mode_without_dvr_change, + [AMD_PSTATE_ACTIVE] = amd_pstate_change_driver_mode, + [AMD_PSTATE_GUIDED] = NULL, + }, +}; + static ssize_t amd_pstate_show_status(char *buf) { if (!current_pstate_driver) @@ -846,57 +940,22 @@ static ssize_t amd_pstate_show_status(char *buf) return sysfs_emit(buf, "%s\n", amd_pstate_mode_string[cppc_state]); } -static void amd_pstate_driver_cleanup(void) -{ - current_pstate_driver = NULL; -} - static int amd_pstate_update_status(const char *buf, size_t size) { - int ret = 0; int mode_idx; - if (size > 7 || size < 6) + if (size > strlen("passive") || size < strlen("active")) return -EINVAL; + mode_idx = get_mode_idx_from_str(buf, size); - switch(mode_idx) { - case AMD_PSTATE_DISABLE: - if (!current_pstate_driver) - return -EINVAL; - if (cppc_state == AMD_PSTATE_ACTIVE) - return -EBUSY; - cpufreq_unregister_driver(current_pstate_driver); - amd_pstate_driver_cleanup(); - break; - case AMD_PSTATE_PASSIVE: - if (current_pstate_driver) { - if (current_pstate_driver == &amd_pstate_driver) - return 0; - cpufreq_unregister_driver(current_pstate_driver); - cppc_state = AMD_PSTATE_PASSIVE; - current_pstate_driver = &amd_pstate_driver; - } + if (mode_idx < 0 || mode_idx >= AMD_PSTATE_MAX) + return -EINVAL; - ret = cpufreq_register_driver(current_pstate_driver); - break; - case AMD_PSTATE_ACTIVE: - if (current_pstate_driver) { - if (current_pstate_driver == &amd_pstate_epp_driver) - return 0; - cpufreq_unregister_driver(current_pstate_driver); - current_pstate_driver = &amd_pstate_epp_driver; - cppc_state = AMD_PSTATE_ACTIVE; - } + if (mode_state_machine[cppc_state][mode_idx]) + return mode_state_machine[cppc_state][mode_idx](mode_idx); - ret = cpufreq_register_driver(current_pstate_driver); - break; - default: - ret = -EINVAL; - break; - } - - return ret; + return 0; } static ssize_t show_status(struct kobject *kobj, From 7a9dec665f6875f61fe0c2e71b25842daade5110 Mon Sep 17 00:00:00 2001 From: Wyes Karny Date: Tue, 7 Mar 2023 11:27:40 +0000 Subject: [PATCH 07/12] Documentation: cpufreq: amd-pstate: Update amd_pstate status sysfs for guided Update amd_pstate status sysfs for guided mode. Acked-by: Huang Rui Reviewed-by: Bagas Sanjaya Reviewed-by: Mario Limonciello Tested-by: Oleksandr Natalenko Signed-off-by: Wyes Karny Signed-off-by: Rafael J. Wysocki --- Documentation/admin-guide/pm/amd-pstate.rst | 31 ++++++++++++++++----- 1 file changed, 24 insertions(+), 7 deletions(-) diff --git a/Documentation/admin-guide/pm/amd-pstate.rst b/Documentation/admin-guide/pm/amd-pstate.rst index 6e5298b521b1..1cf40f69278c 100644 --- a/Documentation/admin-guide/pm/amd-pstate.rst +++ b/Documentation/admin-guide/pm/amd-pstate.rst @@ -303,13 +303,18 @@ efficiency frequency management method on AMD processors. AMD Pstate Driver Operation Modes ================================= -``amd_pstate`` CPPC has two operation modes: CPPC Autonomous(active) mode and -CPPC non-autonomous(passive) mode. -active mode and passive mode can be chosen by different kernel parameters. -When in Autonomous mode, CPPC ignores requests done in the Desired Performance -Target register and takes into account only the values set to the Minimum requested -performance, Maximum requested performance, and Energy Performance Preference -registers. When Autonomous is disabled, it only considers the Desired Performance Target. +``amd_pstate`` CPPC has 3 operation modes: autonomous (active) mode, +non-autonomous (passive) mode and guided autonomous (guided) mode. +Active/passive/guided mode can be chosen by different kernel parameters. + +- In autonomous mode, platform ignores the desired performance level request + and takes into account only the values set to the minimum, maximum and energy + performance preference registers. +- In non-autonomous mode, platform gets desired performance level + from OS directly through Desired Performance Register. +- In guided-autonomous mode, platform sets operating performance level + autonomously according to the current workload and within the limits set by + OS through min and max performance registers. Active Mode ------------ @@ -338,6 +343,15 @@ to the Performance Reduction Tolerance register. Above the nominal performance l processor must provide at least nominal performance requested and go higher if current operating conditions allow. +Guided Mode +----------- + +``amd_pstate=guided`` + +If ``amd_pstate=guided`` is passed to kernel command line option then this mode +is activated. In this mode, driver requests minimum and maximum performance +level and the platform autonomously selects a performance level in this range +and appropriate to the current workload. User Space Interface in ``sysfs`` - General =========================================== @@ -358,6 +372,9 @@ control its functionality at the system level. They are located in the "passive" The driver is functional and in the ``passive mode`` + "guided" + The driver is functional and in the ``guided mode`` + "disable" The driver is unregistered and not functional now. From 877d5cd2aeed8fddeb3afe174c6b9eb77cd56f8b Mon Sep 17 00:00:00 2001 From: qinyu Date: Mon, 20 Mar 2023 16:17:02 +0800 Subject: [PATCH 08/12] cpufreq: warn about invalid vals to scaling_max/min_freq interfaces When echo an invalid val to scaling_min_freq: > echo 123abc123 > scaling_min_freq It looks weird to have a return val of 0: > echo $? > 0 Sane people won't echo strings like that into these interfaces but fuzz tests may do. Also, maybe it's better to inform people if input is invalid. After this: > echo 123abc123 > scaling_min_freq > -bash: echo: write error: Invalid argument Signed-off-by: qinyu Tested-by: zhangxiaofeng Acked-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/cpufreq.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 6d8fd3b8dcb5..d61f7308f63c 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -725,9 +725,9 @@ static ssize_t store_##file_name \ unsigned long val; \ int ret; \ \ - ret = sscanf(buf, "%lu", &val); \ - if (ret != 1) \ - return -EINVAL; \ + ret = kstrtoul(buf, 0, &val); \ + if (ret) \ + return ret; \ \ ret = freq_qos_update_request(policy->object##_freq_req, val);\ return ret >= 0 ? count : ret; \ From 8ffdb1fe9121f85232171630a8cfb0574cbf81b2 Mon Sep 17 00:00:00 2001 From: Jingyu Wang Date: Wed, 8 Mar 2023 20:28:30 +0800 Subject: [PATCH 09/12] cpufreq: Fix typo in the ARM_BRCMSTB_AVS_CPUFREQ Kconfig entry Delete the redundant word 'to' from the help text in the ARM_BRCMSTB_AVS_CPUFREQ Kconfig entry. Signed-off-by: Jingyu Wang [ rjw: Subject and changelog edits ] Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/Kconfig.arm | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm index 97acaa2136fd..123b4bbfcfee 100644 --- a/drivers/cpufreq/Kconfig.arm +++ b/drivers/cpufreq/Kconfig.arm @@ -95,7 +95,7 @@ config ARM_BRCMSTB_AVS_CPUFREQ help Some Broadcom STB SoCs use a co-processor running proprietary firmware ("AVS") to handle voltage and frequency scaling. This driver provides - a standard CPUfreq interface to to the firmware. + a standard CPUfreq interface to the firmware. Say Y, if you have a Broadcom SoC with AVS support for DFS or DVFS. From 175c9df15aef7a1446fb67154a186b73dd892b50 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Fri, 10 Mar 2023 08:47:03 -0600 Subject: [PATCH 10/12] cpufreq: pmac32: Use of_property_read_bool() for boolean properties It is preferred to use typed property access functions (i.e. of_property_read_ functions) rather than low-level of_get_property/of_find_property functions for reading properties. Convert reading boolean properties to to of_property_read_bool(). Signed-off-by: Rob Herring Acked-by: Viresh Kumar Reviewed-by: Michael Ellerman Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/pmac32-cpufreq.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/cpufreq/pmac32-cpufreq.c b/drivers/cpufreq/pmac32-cpufreq.c index 4b8ee2014da6..7ec6d1bb4592 100644 --- a/drivers/cpufreq/pmac32-cpufreq.c +++ b/drivers/cpufreq/pmac32-cpufreq.c @@ -546,7 +546,7 @@ static int pmac_cpufreq_init_7447A(struct device_node *cpunode) { struct device_node *volt_gpio_np; - if (of_get_property(cpunode, "dynamic-power-step", NULL) == NULL) + if (!of_property_read_bool(cpunode, "dynamic-power-step")) return 1; volt_gpio_np = of_find_node_by_name(NULL, "cpu-vcore-select"); @@ -576,7 +576,7 @@ static int pmac_cpufreq_init_750FX(struct device_node *cpunode) u32 pvr; const u32 *value; - if (of_get_property(cpunode, "dynamic-power-step", NULL) == NULL) + if (!of_property_read_bool(cpunode, "dynamic-power-step")) return 1; hi_freq = cur_freq; @@ -632,7 +632,7 @@ static int __init pmac_cpufreq_setup(void) /* Check for 7447A based MacRISC3 */ if (of_machine_is_compatible("MacRISC3") && - of_get_property(cpunode, "dynamic-power-step", NULL) && + of_property_read_bool(cpunode, "dynamic-power-step") && PVR_VER(mfspr(SPRN_PVR)) == 0x8003) { pmac_cpufreq_init_7447A(cpunode); From a038895e25b296ca1ef0254f92673ea64bc1a2ee Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 4 Apr 2023 05:09:10 +0530 Subject: [PATCH 11/12] cpufreq: drivers with target_index() must set freq_table Since the cpufreq core directly uses freq_table, for cpufreq drivers that set their target_index() callback, make it mandatory for them to set the same. Since this is set per policy and normally from policy->init(), do this from cpufreq_table_validate_and_sort() which gets called right after ->init(). Reported-by: Yajun Deng Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/cpufreq.c | 5 +++++ drivers/cpufreq/freq_table.c | 7 ++++++- include/linux/cpufreq.h | 1 + 3 files changed, 12 insertions(+), 1 deletion(-) diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index d61f7308f63c..b24ed81ba8bd 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -73,6 +73,11 @@ static inline bool has_target(void) return cpufreq_driver->target_index || cpufreq_driver->target; } +bool has_target_index(void) +{ + return !!cpufreq_driver->target_index; +} + /* internal prototypes */ static unsigned int __cpufreq_get(struct cpufreq_policy *policy); static int cpufreq_init_governor(struct cpufreq_policy *policy); diff --git a/drivers/cpufreq/freq_table.c b/drivers/cpufreq/freq_table.c index 67e56cf638ef..ddd4832bcc0d 100644 --- a/drivers/cpufreq/freq_table.c +++ b/drivers/cpufreq/freq_table.c @@ -355,8 +355,13 @@ int cpufreq_table_validate_and_sort(struct cpufreq_policy *policy) { int ret; - if (!policy->freq_table) + if (!policy->freq_table) { + /* Freq table must be passed by drivers with target_index() */ + if (has_target_index()) + return -EINVAL; + return 0; + } ret = cpufreq_frequency_table_cpuinfo(policy, policy->freq_table); if (ret) diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 65623233ab2f..541013487a0e 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -237,6 +237,7 @@ bool cpufreq_supports_freq_invariance(void); struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy); void cpufreq_enable_fast_switch(struct cpufreq_policy *policy); void cpufreq_disable_fast_switch(struct cpufreq_policy *policy); +bool has_target_index(void); #else static inline unsigned int cpufreq_get(unsigned int cpu) { From 11fa52fe619acfa945712d94a0bc27c0f5bc49de Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Mon, 3 Apr 2023 20:33:37 -0400 Subject: [PATCH 12/12] cpufreq: amd-pstate: Make varaiable mode_state_machine static smatch reports drivers/cpufreq/amd-pstate.c:907:25: warning: symbol 'mode_state_machine' was not declared. Should it be static? This variable is only used in one file so it should be static. Signed-off-by: Tom Rix Reviewed-by: Wyes Karny Tested-by: Wyes Karny Reviewed-by: Dhruva Gole [ rjw: Subject edits ] Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/amd-pstate.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index 7955cfc91c31..fcb54a6f6598 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -905,7 +905,7 @@ static int amd_pstate_change_driver_mode(int mode) return 0; } -cppc_mode_transition_fn mode_state_machine[AMD_PSTATE_MAX][AMD_PSTATE_MAX] = { +static cppc_mode_transition_fn mode_state_machine[AMD_PSTATE_MAX][AMD_PSTATE_MAX] = { [AMD_PSTATE_DISABLE] = { [AMD_PSTATE_DISABLE] = NULL, [AMD_PSTATE_PASSIVE] = amd_pstate_register_driver,