diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c index 141413067b5c..0ae3de76833b 100644 --- a/drivers/devfreq/devfreq.c +++ b/drivers/devfreq/devfreq.c @@ -285,6 +285,44 @@ static int devfreq_notify_transition(struct devfreq *devfreq, return 0; } +static int devfreq_set_target(struct devfreq *devfreq, unsigned long new_freq, + u32 flags) +{ + struct devfreq_freqs freqs; + unsigned long cur_freq; + int err = 0; + + if (devfreq->profile->get_cur_freq) + devfreq->profile->get_cur_freq(devfreq->dev.parent, &cur_freq); + else + cur_freq = devfreq->previous_freq; + + freqs.old = cur_freq; + freqs.new = new_freq; + devfreq_notify_transition(devfreq, &freqs, DEVFREQ_PRECHANGE); + + err = devfreq->profile->target(devfreq->dev.parent, &new_freq, flags); + if (err) { + freqs.new = cur_freq; + devfreq_notify_transition(devfreq, &freqs, DEVFREQ_POSTCHANGE); + return err; + } + + freqs.new = new_freq; + devfreq_notify_transition(devfreq, &freqs, DEVFREQ_POSTCHANGE); + + if (devfreq_update_status(devfreq, new_freq)) + dev_err(&devfreq->dev, + "Couldn't update frequency transition information.\n"); + + devfreq->previous_freq = new_freq; + + if (devfreq->suspend_freq) + devfreq->resume_freq = cur_freq; + + return err; +} + /* Load monitoring helper functions for governors use */ /** @@ -296,8 +334,7 @@ static int devfreq_notify_transition(struct devfreq *devfreq, */ int update_devfreq(struct devfreq *devfreq) { - struct devfreq_freqs freqs; - unsigned long freq, cur_freq, min_freq, max_freq; + unsigned long freq, min_freq, max_freq; int err = 0; u32 flags = 0; @@ -333,31 +370,8 @@ int update_devfreq(struct devfreq *devfreq) flags |= DEVFREQ_FLAG_LEAST_UPPER_BOUND; /* Use LUB */ } - if (devfreq->profile->get_cur_freq) - devfreq->profile->get_cur_freq(devfreq->dev.parent, &cur_freq); - else - cur_freq = devfreq->previous_freq; + return devfreq_set_target(devfreq, freq, flags); - freqs.old = cur_freq; - freqs.new = freq; - devfreq_notify_transition(devfreq, &freqs, DEVFREQ_PRECHANGE); - - err = devfreq->profile->target(devfreq->dev.parent, &freq, flags); - if (err) { - freqs.new = cur_freq; - devfreq_notify_transition(devfreq, &freqs, DEVFREQ_POSTCHANGE); - return err; - } - - freqs.new = freq; - devfreq_notify_transition(devfreq, &freqs, DEVFREQ_POSTCHANGE); - - if (devfreq_update_status(devfreq, freq)) - dev_err(&devfreq->dev, - "Couldn't update frequency transition information.\n"); - - devfreq->previous_freq = freq; - return err; } EXPORT_SYMBOL(update_devfreq); @@ -657,6 +671,9 @@ struct devfreq *devfreq_add_device(struct device *dev, } devfreq->max_freq = devfreq->scaling_max_freq; + devfreq->suspend_freq = dev_pm_opp_get_suspend_opp_freq(dev); + atomic_set(&devfreq->suspend_count, 0); + dev_set_name(&devfreq->dev, "devfreq%d", atomic_inc_return(&devfreq_no)); err = device_register(&devfreq->dev); @@ -857,14 +874,28 @@ EXPORT_SYMBOL(devm_devfreq_remove_device); */ int devfreq_suspend_device(struct devfreq *devfreq) { + int ret; + if (!devfreq) return -EINVAL; - if (!devfreq->governor) + if (atomic_inc_return(&devfreq->suspend_count) > 1) return 0; - return devfreq->governor->event_handler(devfreq, - DEVFREQ_GOV_SUSPEND, NULL); + if (devfreq->governor) { + ret = devfreq->governor->event_handler(devfreq, + DEVFREQ_GOV_SUSPEND, NULL); + if (ret) + return ret; + } + + if (devfreq->suspend_freq) { + ret = devfreq_set_target(devfreq, devfreq->suspend_freq, 0); + if (ret) + return ret; + } + + return 0; } EXPORT_SYMBOL(devfreq_suspend_device); @@ -878,17 +909,75 @@ EXPORT_SYMBOL(devfreq_suspend_device); */ int devfreq_resume_device(struct devfreq *devfreq) { + int ret; + if (!devfreq) return -EINVAL; - if (!devfreq->governor) + if (atomic_dec_return(&devfreq->suspend_count) >= 1) return 0; - return devfreq->governor->event_handler(devfreq, - DEVFREQ_GOV_RESUME, NULL); + if (devfreq->resume_freq) { + ret = devfreq_set_target(devfreq, devfreq->resume_freq, 0); + if (ret) + return ret; + } + + if (devfreq->governor) { + ret = devfreq->governor->event_handler(devfreq, + DEVFREQ_GOV_RESUME, NULL); + if (ret) + return ret; + } + + return 0; } EXPORT_SYMBOL(devfreq_resume_device); +/** + * devfreq_suspend() - Suspend devfreq governors and devices + * + * Called during system wide Suspend/Hibernate cycles for suspending governors + * and devices preserving the state for resume. On some platforms the devfreq + * device must have precise state (frequency) after resume in order to provide + * fully operating setup. + */ +void devfreq_suspend(void) +{ + struct devfreq *devfreq; + int ret; + + mutex_lock(&devfreq_list_lock); + list_for_each_entry(devfreq, &devfreq_list, node) { + ret = devfreq_suspend_device(devfreq); + if (ret) + dev_err(&devfreq->dev, + "failed to suspend devfreq device\n"); + } + mutex_unlock(&devfreq_list_lock); +} + +/** + * devfreq_resume() - Resume devfreq governors and devices + * + * Called during system wide Suspend/Hibernate cycle for resuming governors and + * devices that are suspended with devfreq_suspend(). + */ +void devfreq_resume(void) +{ + struct devfreq *devfreq; + int ret; + + mutex_lock(&devfreq_list_lock); + list_for_each_entry(devfreq, &devfreq_list, node) { + ret = devfreq_resume_device(devfreq); + if (ret) + dev_warn(&devfreq->dev, + "failed to resume devfreq device\n"); + } + mutex_unlock(&devfreq_list_lock); +} + /** * devfreq_add_governor() - Add devfreq governor * @governor: the devfreq governor to be added diff --git a/drivers/power/avs/smartreflex.c b/drivers/power/avs/smartreflex.c index 1360a7fa542c..c96c01e09740 100644 --- a/drivers/power/avs/smartreflex.c +++ b/drivers/power/avs/smartreflex.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * OMAP SmartReflex Voltage Control * @@ -11,10 +12,6 @@ * * Copyright (C) 2007 Texas Instruments, Inc. * Lesly A M - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include @@ -37,7 +34,6 @@ static LIST_HEAD(sr_list); static struct omap_sr_class_data *sr_class; -static struct omap_sr_pmic_data *sr_pmic_data; static struct dentry *sr_dbg_dir; static inline void sr_write_reg(struct omap_sr *sr, unsigned offset, u32 value) @@ -780,25 +776,6 @@ void omap_sr_disable_reset_volt(struct voltagedomain *voltdm) sr_class->disable(sr, 1); } -/** - * omap_sr_register_pmic() - API to register pmic specific info. - * @pmic_data: The structure containing pmic specific data. - * - * This API is to be called from the PMIC specific code to register with - * smartreflex driver pmic specific info. Currently the only info required - * is the smartreflex init on the PMIC side. - */ -void omap_sr_register_pmic(struct omap_sr_pmic_data *pmic_data) -{ - if (!pmic_data) { - pr_warn("%s: Trying to register NULL PMIC data structure with smartreflex\n", - __func__); - return; - } - - sr_pmic_data = pmic_data; -} - /* PM Debug FS entries to enable and disable smartreflex. */ static int omap_sr_autocomp_show(void *data, u64 *val) { @@ -1010,8 +987,7 @@ static int omap_sr_remove(struct platform_device *pdev) if (sr_info->autocomp_active) sr_stop_vddautocomp(sr_info); - if (sr_info->dbg_dir) - debugfs_remove_recursive(sr_info->dbg_dir); + debugfs_remove_recursive(sr_info->dbg_dir); pm_runtime_disable(&pdev->dev); list_del(&sr_info->node); @@ -1065,17 +1041,6 @@ static int __init sr_init(void) { int ret = 0; - /* - * sr_init is a late init. If by then a pmic specific API is not - * registered either there is no need for anything to be done on - * the PMIC side or somebody has forgotten to register a PMIC - * handler. Warn for the second condition. - */ - if (sr_pmic_data && sr_pmic_data->sr_pmic_init) - sr_pmic_data->sr_pmic_init(); - else - pr_warn("%s: No PMIC hook to init smartreflex\n", __func__); - ret = platform_driver_register(&smartreflex_driver); if (ret) { pr_err("%s: platform driver register failed for SR\n", diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h index e4963b0f45da..fbffa74bfc1b 100644 --- a/include/linux/devfreq.h +++ b/include/linux/devfreq.h @@ -131,6 +131,9 @@ struct devfreq_dev_profile { * @scaling_min_freq: Limit minimum frequency requested by OPP interface * @scaling_max_freq: Limit maximum frequency requested by OPP interface * @stop_polling: devfreq polling status of a device. + * @suspend_freq: frequency of a device set during suspend phase. + * @resume_freq: frequency of a device set in resume phase. + * @suspend_count: suspend requests counter for a device. * @total_trans: Number of devfreq transitions * @trans_table: Statistics of devfreq transitions * @time_in_state: Statistics of devfreq states @@ -167,6 +170,10 @@ struct devfreq { unsigned long scaling_max_freq; bool stop_polling; + unsigned long suspend_freq; + unsigned long resume_freq; + atomic_t suspend_count; + /* information for device frequency transition */ unsigned int total_trans; unsigned int *trans_table; @@ -198,6 +205,9 @@ extern void devm_devfreq_remove_device(struct device *dev, extern int devfreq_suspend_device(struct devfreq *devfreq); extern int devfreq_resume_device(struct devfreq *devfreq); +extern void devfreq_suspend(void); +extern void devfreq_resume(void); + /** * update_devfreq() - Reevaluate the device and configure frequency * @devfreq: the devfreq device @@ -324,6 +334,9 @@ static inline int devfreq_resume_device(struct devfreq *devfreq) return 0; } +static inline void devfreq_suspend(void) {} +static inline void devfreq_resume(void) {} + static inline struct dev_pm_opp *devfreq_recommended_opp(struct device *dev, unsigned long *freq, u32 flags) { diff --git a/include/linux/power/smartreflex.h b/include/linux/power/smartreflex.h index 7b81dad712de..d0b37e937037 100644 --- a/include/linux/power/smartreflex.h +++ b/include/linux/power/smartreflex.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * OMAP Smartreflex Defines and Routines * @@ -11,10 +12,6 @@ * * Copyright (C) 2007 Texas Instruments, Inc. * Lesly A M - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #ifndef __POWER_SMARTREFLEX_H @@ -303,9 +300,6 @@ void omap_sr_enable(struct voltagedomain *voltdm); void omap_sr_disable(struct voltagedomain *voltdm); void omap_sr_disable_reset_volt(struct voltagedomain *voltdm); -/* API to register the pmic specific data with the smartreflex driver. */ -void omap_sr_register_pmic(struct omap_sr_pmic_data *pmic_data); - /* Smartreflex driver hooks to be called from Smartreflex class driver */ int sr_enable(struct omap_sr *sr, unsigned long volt); void sr_disable(struct omap_sr *sr); @@ -320,7 +314,5 @@ static inline void omap_sr_enable(struct voltagedomain *voltdm) {} static inline void omap_sr_disable(struct voltagedomain *voltdm) {} static inline void omap_sr_disable_reset_volt( struct voltagedomain *voltdm) {} -static inline void omap_sr_register_pmic( - struct omap_sr_pmic_data *pmic_data) {} #endif #endif diff --git a/tools/power/cpupower/Makefile b/tools/power/cpupower/Makefile index db66a952c173..fd8765af19bb 100644 --- a/tools/power/cpupower/Makefile +++ b/tools/power/cpupower/Makefile @@ -89,6 +89,7 @@ endif localedir ?= /usr/share/locale docdir ?= /usr/share/doc/packages/cpupower confdir ?= /etc/ +bash_completion_dir ?= /usr/share/bash-completion/completions # Toolchain: what tools do we use, and what options do they need: @@ -96,7 +97,8 @@ CP = cp -fpR INSTALL = /usr/bin/install -c INSTALL_PROGRAM = ${INSTALL} INSTALL_DATA = ${INSTALL} -m 644 -INSTALL_SCRIPT = ${INSTALL_PROGRAM} +#bash completion scripts get sourced and so they should be rw only. +INSTALL_SCRIPT = ${INSTALL} -m 644 # If you are running a cross compiler, you may want to set this # to something more interesting, like "arm-linux-". If you want @@ -288,6 +290,8 @@ install-lib: install-tools: $(INSTALL) -d $(DESTDIR)${bindir} $(INSTALL_PROGRAM) $(OUTPUT)cpupower $(DESTDIR)${bindir} + $(INSTALL) -d $(DESTDIR)${bash_completion_dir} + $(INSTALL_SCRIPT) cpupower-completion.sh '$(DESTDIR)${bash_completion_dir}/cpupower' install-man: $(INSTALL_DATA) -D man/cpupower.1 $(DESTDIR)${mandir}/man1/cpupower.1 diff --git a/tools/power/cpupower/cpupower-completion.sh b/tools/power/cpupower/cpupower-completion.sh new file mode 100644 index 000000000000..e10839cfcfc1 --- /dev/null +++ b/tools/power/cpupower/cpupower-completion.sh @@ -0,0 +1,128 @@ +# -*- shell-script -*- +# bash completion script for cpupower +# Taken from git.git's completion script. + +_cpupower_commands="frequency-info frequency-set idle-info idle-set set info monitor" + +_frequency_info () +{ + local flags="-f -w -l -d -p -g -a -s -y -o -m -n --freq --hwfreq --hwlimits --driver --policy --governors --related-cpus --affected-cpus --stats --latency --proc --human --no-rounding" + local prev="${COMP_WORDS[COMP_CWORD-1]}" + local cur="${COMP_WORDS[COMP_CWORD]}" + case "$prev" in + frequency-info) COMPREPLY=($(compgen -W "$flags" -- "$cur")) ;; + esac +} + +_frequency_set () +{ + local flags="-f -g --freq --governor -d --min -u --max -r --related" + local prev="${COMP_WORDS[COMP_CWORD-1]}" + local cur="${COMP_WORDS[COMP_CWORD]}" + case "$prev" in + -f| --freq | -d | --min | -u | --max) + if [ -d /sys/devices/system/cpu/cpufreq/ ] ; then + COMPREPLY=($(compgen -W '$(cat $(ls -d /sys/devices/system/cpu/cpufreq/policy* | head -1)/scaling_available_frequencies)' -- "$cur")) + fi ;; + -g| --governor) + if [ -d /sys/devices/system/cpu/cpufreq/ ] ; then + COMPREPLY=($(compgen -W '$(cat $(ls -d /sys/devices/system/cpu/cpufreq/policy* | head -1)/scaling_available_governors)' -- "$cur")) + fi;; + frequency-set) COMPREPLY=($(compgen -W "$flags" -- "$cur")) ;; + esac +} + +_idle_info() +{ + local flags="-f --silent" + local prev="${COMP_WORDS[COMP_CWORD-1]}" + local cur="${COMP_WORDS[COMP_CWORD]}" + case "$prev" in + idle-info) COMPREPLY=($(compgen -W "$flags" -- "$cur")) ;; + esac +} + +_idle_set() +{ + local flags="-d --disable -e --enable -D --disable-by-latency -E --enable-all" + local prev="${COMP_WORDS[COMP_CWORD-1]}" + local cur="${COMP_WORDS[COMP_CWORD]}" + case "$prev" in + idle-set) COMPREPLY=($(compgen -W "$flags" -- "$cur")) ;; + esac +} + +_set() +{ + local flags="--perf-bias, -b" + local prev="${COMP_WORDS[COMP_CWORD-1]}" + local cur="${COMP_WORDS[COMP_CWORD]}" + case "$prev" in + set) COMPREPLY=($(compgen -W "$flags" -- "$cur")) ;; + esac +} + +_monitor() +{ + local flags="-l -m -i -c -v" + local prev="${COMP_WORDS[COMP_CWORD-1]}" + local cur="${COMP_WORDS[COMP_CWORD]}" + case "$prev" in + monitor) COMPREPLY=($(compgen -W "$flags" -- "$cur")) ;; + esac +} + +_taskset() +{ + local prev_to_prev="${COMP_WORDS[COMP_CWORD-2]}" + local prev="${COMP_WORDS[COMP_CWORD-1]}" + local cur="${COMP_WORDS[COMP_CWORD]}" + case "$prev_to_prev" in + -c|--cpu) COMPREPLY=($(compgen -W "$_cpupower_commands" -- "$cur")) ;; + esac + case "$prev" in + frequency-info) _frequency_info ;; + frequency-set) _frequency_set ;; + idle-info) _idle_info ;; + idle-set) _idle_set ;; + set) _set ;; + monitor) _monitor ;; + esac + +} + +_cpupower () +{ + local i + local c=1 + local command + + while test $c -lt $COMP_CWORD; do + if test $c == 1; then + command="${COMP_WORDS[c]}" + fi + c=$((++c)) + done + + # Complete name of subcommand if the user has not finished typing it yet. + if test $c -eq $COMP_CWORD -a -z "$command"; then + COMPREPLY=($(compgen -W "help -v --version -c --cpu $_cpupower_commands" -- "${COMP_WORDS[COMP_CWORD]}")) + return + fi + + # Complete arguments to subcommands. + case "$command" in + -v|--version) return ;; + -c|--cpu) _taskset ;; + help) COMPREPLY=($(compgen -W "$_cpupower_commands" -- "${COMP_WORDS[COMP_CWORD]}")) ;; + frequency-info) _frequency_info ;; + frequency-set) _frequency_set ;; + idle-info) _idle_info ;; + idle-set) _idle_set ;; + set) _set ;; + monitor) _monitor ;; + esac +} + +complete -o bashdefault -o default -F _cpupower cpupower 2>/dev/null \ + || complete -o default -F _cpupower cpupower diff --git a/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py b/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py index 84e2b648e622..2fa3c5757bcb 100755 --- a/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py +++ b/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py @@ -585,9 +585,9 @@ current_max_cpu = 0 read_trace_data(filename) -clear_trace_file() -# Free the memory if interval: + clear_trace_file() + # Free the memory free_trace_buffer() if graph_data_present == False: diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index 328f62e6ea02..9327c0ddc3a5 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -1,6 +1,6 @@ /* * turbostat -- show CPU frequency and C-state residency - * on modern Intel turbo-capable processors. + * on modern Intel and AMD processors. * * Copyright (c) 2013 Intel Corporation. * Len Brown @@ -71,6 +71,8 @@ unsigned int do_irtl_snb; unsigned int do_irtl_hsw; unsigned int units = 1000000; /* MHz etc */ unsigned int genuine_intel; +unsigned int authentic_amd; +unsigned int max_level, max_extended_level; unsigned int has_invariant_tsc; unsigned int do_nhm_platform_info; unsigned int no_MSR_MISC_PWR_MGMT; @@ -1667,30 +1669,51 @@ int get_mp(int cpu, struct msr_counter *mp, unsigned long long *counterp) void get_apic_id(struct thread_data *t) { - unsigned int eax, ebx, ecx, edx, max_level; + unsigned int eax, ebx, ecx, edx; - eax = ebx = ecx = edx = 0; + if (DO_BIC(BIC_APIC)) { + eax = ebx = ecx = edx = 0; + __cpuid(1, eax, ebx, ecx, edx); + + t->apic_id = (ebx >> 24) & 0xff; + } + + if (!DO_BIC(BIC_X2APIC)) + return; + + if (authentic_amd) { + unsigned int topology_extensions; + + if (max_extended_level < 0x8000001e) + return; + + eax = ebx = ecx = edx = 0; + __cpuid(0x80000001, eax, ebx, ecx, edx); + topology_extensions = ecx & (1 << 22); + + if (topology_extensions == 0) + return; + + eax = ebx = ecx = edx = 0; + __cpuid(0x8000001e, eax, ebx, ecx, edx); + + t->x2apic_id = eax; + return; + } if (!genuine_intel) return; - __cpuid(0, max_level, ebx, ecx, edx); - - __cpuid(1, eax, ebx, ecx, edx); - t->apic_id = (ebx >> 24) & 0xf; - if (max_level < 0xb) return; - if (!DO_BIC(BIC_X2APIC)) - return; - ecx = 0; __cpuid(0xb, eax, ebx, ecx, edx); t->x2apic_id = edx; - if (debug && (t->apic_id != t->x2apic_id)) - fprintf(outf, "cpu%d: apic 0x%x x2apic 0x%x\n", t->cpu_id, t->apic_id, t->x2apic_id); + if (debug && (t->apic_id != (t->x2apic_id & 0xff))) + fprintf(outf, "cpu%d: BIOS BUG: apic 0x%x x2apic 0x%x\n", + t->cpu_id, t->apic_id, t->x2apic_id); } /* @@ -1953,11 +1976,12 @@ done: #define PCL_7S 11 /* PC7 Shrink */ #define PCL__8 12 /* PC8 */ #define PCL__9 13 /* PC9 */ -#define PCLUNL 14 /* Unlimited */ +#define PCL_10 14 /* PC10 */ +#define PCLUNL 15 /* Unlimited */ int pkg_cstate_limit = PCLUKN; char *pkg_cstate_limit_strings[] = { "reserved", "unknown", "pc0", "pc1", "pc2", - "pc3", "pc4", "pc6", "pc6n", "pc6r", "pc7", "pc7s", "pc8", "pc9", "unlimited"}; + "pc3", "pc4", "pc6", "pc6n", "pc6r", "pc7", "pc7s", "pc8", "pc9", "pc10", "unlimited"}; int nhm_pkg_cstate_limits[16] = {PCL__0, PCL__1, PCL__3, PCL__6, PCL__7, PCLRSV, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV}; int snb_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCL__7, PCL_7S, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV}; @@ -1965,7 +1989,7 @@ int hsw_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL__3, PCL__6, PCL__7, PCL_7S, int slv_pkg_cstate_limits[16] = {PCL__0, PCL__1, PCLRSV, PCLRSV, PCL__4, PCLRSV, PCL__6, PCL__7, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCL__6, PCL__7}; int amt_pkg_cstate_limits[16] = {PCLUNL, PCL__1, PCL__2, PCLRSV, PCLRSV, PCLRSV, PCL__6, PCL__7, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV}; int phi_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCLRSV, PCLRSV, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV}; -int bxt_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV}; +int glm_pkg_cstate_limits[16] = {PCLUNL, PCL__1, PCL__3, PCL__6, PCL__7, PCL_7S, PCL__8, PCL__9, PCL_10, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV}; int skx_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCLRSV, PCLRSV, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV}; @@ -3113,13 +3137,8 @@ int probe_nhm_msrs(unsigned int family, unsigned int model) bclk = discover_bclk(family, model); switch (model) { - case INTEL_FAM6_NEHALEM_EP: /* Core i7, Xeon 5500 series - Bloomfield, Gainstown NHM-EP */ case INTEL_FAM6_NEHALEM: /* Core i7 and i5 Processor - Clarksfield, Lynnfield, Jasper Forest */ - case 0x1F: /* Core i7 and i5 Processor - Nehalem */ - case INTEL_FAM6_WESTMERE: /* Westmere Client - Clarkdale, Arrandale */ - case INTEL_FAM6_WESTMERE_EP: /* Westmere EP - Gulftown */ case INTEL_FAM6_NEHALEM_EX: /* Nehalem-EX Xeon - Beckton */ - case INTEL_FAM6_WESTMERE_EX: /* Westmere-EX Xeon - Eagleton */ pkg_cstate_limits = nhm_pkg_cstate_limits; break; case INTEL_FAM6_SANDYBRIDGE: /* SNB */ @@ -3131,16 +3150,11 @@ int probe_nhm_msrs(unsigned int family, unsigned int model) break; case INTEL_FAM6_HASWELL_CORE: /* HSW */ case INTEL_FAM6_HASWELL_X: /* HSX */ - case INTEL_FAM6_HASWELL_ULT: /* HSW */ case INTEL_FAM6_HASWELL_GT3E: /* HSW */ case INTEL_FAM6_BROADWELL_CORE: /* BDW */ case INTEL_FAM6_BROADWELL_GT3E: /* BDW */ case INTEL_FAM6_BROADWELL_X: /* BDX */ - case INTEL_FAM6_BROADWELL_XEON_D: /* BDX-DE */ case INTEL_FAM6_SKYLAKE_MOBILE: /* SKL */ - case INTEL_FAM6_SKYLAKE_DESKTOP: /* SKL */ - case INTEL_FAM6_KABYLAKE_MOBILE: /* KBL */ - case INTEL_FAM6_KABYLAKE_DESKTOP: /* KBL */ case INTEL_FAM6_CANNONLAKE_MOBILE: /* CNL */ pkg_cstate_limits = hsw_pkg_cstate_limits; has_misc_feature_control = 1; @@ -3159,13 +3173,12 @@ int probe_nhm_msrs(unsigned int family, unsigned int model) no_MSR_MISC_PWR_MGMT = 1; break; case INTEL_FAM6_XEON_PHI_KNL: /* PHI */ - case INTEL_FAM6_XEON_PHI_KNM: pkg_cstate_limits = phi_pkg_cstate_limits; break; case INTEL_FAM6_ATOM_GOLDMONT: /* BXT */ case INTEL_FAM6_ATOM_GOLDMONT_PLUS: case INTEL_FAM6_ATOM_GOLDMONT_X: /* DNV */ - pkg_cstate_limits = bxt_pkg_cstate_limits; + pkg_cstate_limits = glm_pkg_cstate_limits; break; default: return 0; @@ -3220,7 +3233,6 @@ int is_bdx(unsigned int family, unsigned int model) switch (model) { case INTEL_FAM6_BROADWELL_X: - case INTEL_FAM6_BROADWELL_XEON_D: return 1; } return 0; @@ -3246,9 +3258,7 @@ int has_turbo_ratio_limit(unsigned int family, unsigned int model) switch (model) { /* Nehalem compatible, but do not include turbo-ratio limit support */ case INTEL_FAM6_NEHALEM_EX: /* Nehalem-EX Xeon - Beckton */ - case INTEL_FAM6_WESTMERE_EX: /* Westmere-EX Xeon - Eagleton */ case INTEL_FAM6_XEON_PHI_KNL: /* PHI - Knights Landing (different MSR definition) */ - case INTEL_FAM6_XEON_PHI_KNM: return 0; default: return 1; @@ -3303,7 +3313,6 @@ int has_knl_turbo_ratio_limit(unsigned int family, unsigned int model) switch (model) { case INTEL_FAM6_XEON_PHI_KNL: /* Knights Landing */ - case INTEL_FAM6_XEON_PHI_KNM: return 1; default: return 0; @@ -3337,21 +3346,15 @@ int has_config_tdp(unsigned int family, unsigned int model) case INTEL_FAM6_IVYBRIDGE: /* IVB */ case INTEL_FAM6_HASWELL_CORE: /* HSW */ case INTEL_FAM6_HASWELL_X: /* HSX */ - case INTEL_FAM6_HASWELL_ULT: /* HSW */ case INTEL_FAM6_HASWELL_GT3E: /* HSW */ case INTEL_FAM6_BROADWELL_CORE: /* BDW */ case INTEL_FAM6_BROADWELL_GT3E: /* BDW */ case INTEL_FAM6_BROADWELL_X: /* BDX */ - case INTEL_FAM6_BROADWELL_XEON_D: /* BDX-DE */ case INTEL_FAM6_SKYLAKE_MOBILE: /* SKL */ - case INTEL_FAM6_SKYLAKE_DESKTOP: /* SKL */ - case INTEL_FAM6_KABYLAKE_MOBILE: /* KBL */ - case INTEL_FAM6_KABYLAKE_DESKTOP: /* KBL */ case INTEL_FAM6_CANNONLAKE_MOBILE: /* CNL */ case INTEL_FAM6_SKYLAKE_X: /* SKX */ case INTEL_FAM6_XEON_PHI_KNL: /* Knights Landing */ - case INTEL_FAM6_XEON_PHI_KNM: return 1; default: return 0; @@ -3744,9 +3747,7 @@ rapl_dram_energy_units_probe(int model, double rapl_energy_units) switch (model) { case INTEL_FAM6_HASWELL_X: /* HSX */ case INTEL_FAM6_BROADWELL_X: /* BDX */ - case INTEL_FAM6_BROADWELL_XEON_D: /* BDX-DE */ case INTEL_FAM6_XEON_PHI_KNL: /* KNL */ - case INTEL_FAM6_XEON_PHI_KNM: return (rapl_dram_energy_units = 15.3 / 1000000); default: return (rapl_energy_units); @@ -3775,7 +3776,6 @@ void rapl_probe(unsigned int family, unsigned int model) case INTEL_FAM6_SANDYBRIDGE: case INTEL_FAM6_IVYBRIDGE: case INTEL_FAM6_HASWELL_CORE: /* HSW */ - case INTEL_FAM6_HASWELL_ULT: /* HSW */ case INTEL_FAM6_HASWELL_GT3E: /* HSW */ case INTEL_FAM6_BROADWELL_CORE: /* BDW */ case INTEL_FAM6_BROADWELL_GT3E: /* BDW */ @@ -3799,9 +3799,6 @@ void rapl_probe(unsigned int family, unsigned int model) BIC_PRESENT(BIC_PkgWatt); break; case INTEL_FAM6_SKYLAKE_MOBILE: /* SKL */ - case INTEL_FAM6_SKYLAKE_DESKTOP: /* SKL */ - case INTEL_FAM6_KABYLAKE_MOBILE: /* KBL */ - case INTEL_FAM6_KABYLAKE_DESKTOP: /* KBL */ case INTEL_FAM6_CANNONLAKE_MOBILE: /* CNL */ do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_GFX | RAPL_PKG_POWER_INFO; BIC_PRESENT(BIC_PKG__); @@ -3820,10 +3817,8 @@ void rapl_probe(unsigned int family, unsigned int model) break; case INTEL_FAM6_HASWELL_X: /* HSX */ case INTEL_FAM6_BROADWELL_X: /* BDX */ - case INTEL_FAM6_BROADWELL_XEON_D: /* BDX-DE */ case INTEL_FAM6_SKYLAKE_X: /* SKX */ case INTEL_FAM6_XEON_PHI_KNL: /* KNL */ - case INTEL_FAM6_XEON_PHI_KNM: do_rapl = RAPL_PKG | RAPL_DRAM | RAPL_DRAM_POWER_INFO | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO; BIC_PRESENT(BIC_PKG__); BIC_PRESENT(BIC_RAM__); @@ -3916,7 +3911,6 @@ void perf_limit_reasons_probe(unsigned int family, unsigned int model) switch (model) { case INTEL_FAM6_HASWELL_CORE: /* HSW */ - case INTEL_FAM6_HASWELL_ULT: /* HSW */ case INTEL_FAM6_HASWELL_GT3E: /* HSW */ do_gfx_perf_limit_reasons = 1; case INTEL_FAM6_HASWELL_X: /* HSX */ @@ -4128,16 +4122,11 @@ int has_snb_msrs(unsigned int family, unsigned int model) case INTEL_FAM6_IVYBRIDGE_X: /* IVB Xeon */ case INTEL_FAM6_HASWELL_CORE: /* HSW */ case INTEL_FAM6_HASWELL_X: /* HSW */ - case INTEL_FAM6_HASWELL_ULT: /* HSW */ case INTEL_FAM6_HASWELL_GT3E: /* HSW */ case INTEL_FAM6_BROADWELL_CORE: /* BDW */ case INTEL_FAM6_BROADWELL_GT3E: /* BDW */ case INTEL_FAM6_BROADWELL_X: /* BDX */ - case INTEL_FAM6_BROADWELL_XEON_D: /* BDX-DE */ case INTEL_FAM6_SKYLAKE_MOBILE: /* SKL */ - case INTEL_FAM6_SKYLAKE_DESKTOP: /* SKL */ - case INTEL_FAM6_KABYLAKE_MOBILE: /* KBL */ - case INTEL_FAM6_KABYLAKE_DESKTOP: /* KBL */ case INTEL_FAM6_CANNONLAKE_MOBILE: /* CNL */ case INTEL_FAM6_SKYLAKE_X: /* SKX */ case INTEL_FAM6_ATOM_GOLDMONT: /* BXT */ @@ -4166,12 +4155,9 @@ int has_hsw_msrs(unsigned int family, unsigned int model) return 0; switch (model) { - case INTEL_FAM6_HASWELL_ULT: /* HSW */ + case INTEL_FAM6_HASWELL_CORE: case INTEL_FAM6_BROADWELL_CORE: /* BDW */ case INTEL_FAM6_SKYLAKE_MOBILE: /* SKL */ - case INTEL_FAM6_SKYLAKE_DESKTOP: /* SKL */ - case INTEL_FAM6_KABYLAKE_MOBILE: /* KBL */ - case INTEL_FAM6_KABYLAKE_DESKTOP: /* KBL */ case INTEL_FAM6_CANNONLAKE_MOBILE: /* CNL */ case INTEL_FAM6_ATOM_GOLDMONT: /* BXT */ case INTEL_FAM6_ATOM_GOLDMONT_PLUS: @@ -4195,9 +4181,6 @@ int has_skl_msrs(unsigned int family, unsigned int model) switch (model) { case INTEL_FAM6_SKYLAKE_MOBILE: /* SKL */ - case INTEL_FAM6_SKYLAKE_DESKTOP: /* SKL */ - case INTEL_FAM6_KABYLAKE_MOBILE: /* KBL */ - case INTEL_FAM6_KABYLAKE_DESKTOP: /* KBL */ case INTEL_FAM6_CANNONLAKE_MOBILE: /* CNL */ return 1; } @@ -4222,7 +4205,6 @@ int is_knl(unsigned int family, unsigned int model) return 0; switch (model) { case INTEL_FAM6_XEON_PHI_KNL: /* KNL */ - case INTEL_FAM6_XEON_PHI_KNM: return 1; } return 0; @@ -4436,18 +4418,56 @@ void decode_c6_demotion_policy_msr(void) base_cpu, msr, msr & (1 << 0) ? "EN" : "DIS"); } +/* + * When models are the same, for the purpose of turbostat, reuse + */ +unsigned int intel_model_duplicates(unsigned int model) +{ + + switch(model) { + case INTEL_FAM6_NEHALEM_EP: /* Core i7, Xeon 5500 series - Bloomfield, Gainstown NHM-EP */ + case INTEL_FAM6_NEHALEM: /* Core i7 and i5 Processor - Clarksfield, Lynnfield, Jasper Forest */ + case 0x1F: /* Core i7 and i5 Processor - Nehalem */ + case INTEL_FAM6_WESTMERE: /* Westmere Client - Clarkdale, Arrandale */ + case INTEL_FAM6_WESTMERE_EP: /* Westmere EP - Gulftown */ + return INTEL_FAM6_NEHALEM; + + case INTEL_FAM6_NEHALEM_EX: /* Nehalem-EX Xeon - Beckton */ + case INTEL_FAM6_WESTMERE_EX: /* Westmere-EX Xeon - Eagleton */ + return INTEL_FAM6_NEHALEM_EX; + + case INTEL_FAM6_XEON_PHI_KNM: + return INTEL_FAM6_XEON_PHI_KNL; + + case INTEL_FAM6_HASWELL_ULT: + return INTEL_FAM6_HASWELL_CORE; + + case INTEL_FAM6_BROADWELL_X: + case INTEL_FAM6_BROADWELL_XEON_D: /* BDX-DE */ + return INTEL_FAM6_BROADWELL_X; + + case INTEL_FAM6_SKYLAKE_MOBILE: + case INTEL_FAM6_SKYLAKE_DESKTOP: + case INTEL_FAM6_KABYLAKE_MOBILE: + case INTEL_FAM6_KABYLAKE_DESKTOP: + return INTEL_FAM6_SKYLAKE_MOBILE; + } + return model; +} void process_cpuid() { - unsigned int eax, ebx, ecx, edx, max_level, max_extended_level; - unsigned int fms, family, model, stepping; + unsigned int eax, ebx, ecx, edx; + unsigned int fms, family, model, stepping, ecx_flags, edx_flags; unsigned int has_turbo; eax = ebx = ecx = edx = 0; __cpuid(0, max_level, ebx, ecx, edx); - if (ebx == 0x756e6547 && edx == 0x49656e69 && ecx == 0x6c65746e) + if (ebx == 0x756e6547 && ecx == 0x6c65746e && edx == 0x49656e69) genuine_intel = 1; + else if (ebx == 0x68747541 && ecx == 0x444d4163 && edx == 0x69746e65) + authentic_amd = 1; if (!quiet) fprintf(outf, "CPUID(0): %.4s%.4s%.4s ", @@ -4461,25 +4481,8 @@ void process_cpuid() family += (fms >> 20) & 0xff; if (family >= 6) model += ((fms >> 16) & 0xf) << 4; - - if (!quiet) { - fprintf(outf, "%d CPUID levels; family:model:stepping 0x%x:%x:%x (%d:%d:%d)\n", - max_level, family, model, stepping, family, model, stepping); - fprintf(outf, "CPUID(1): %s %s %s %s %s %s %s %s %s %s\n", - ecx & (1 << 0) ? "SSE3" : "-", - ecx & (1 << 3) ? "MONITOR" : "-", - ecx & (1 << 6) ? "SMX" : "-", - ecx & (1 << 7) ? "EIST" : "-", - ecx & (1 << 8) ? "TM2" : "-", - edx & (1 << 4) ? "TSC" : "-", - edx & (1 << 5) ? "MSR" : "-", - edx & (1 << 22) ? "ACPI-TM" : "-", - edx & (1 << 28) ? "HT" : "-", - edx & (1 << 29) ? "TM" : "-"); - } - - if (!(edx & (1 << 5))) - errx(1, "CPUID: no MSR"); + ecx_flags = ecx; + edx_flags = edx; /* * check max extended function levels of CPUID. @@ -4489,6 +4492,27 @@ void process_cpuid() ebx = ecx = edx = 0; __cpuid(0x80000000, max_extended_level, ebx, ecx, edx); + if (!quiet) { + fprintf(outf, "0x%x CPUID levels; 0x%x xlevels; family:model:stepping 0x%x:%x:%x (%d:%d:%d)\n", + max_level, max_extended_level, family, model, stepping, family, model, stepping); + fprintf(outf, "CPUID(1): %s %s %s %s %s %s %s %s %s %s\n", + ecx_flags & (1 << 0) ? "SSE3" : "-", + ecx_flags & (1 << 3) ? "MONITOR" : "-", + ecx_flags & (1 << 6) ? "SMX" : "-", + ecx_flags & (1 << 7) ? "EIST" : "-", + ecx_flags & (1 << 8) ? "TM2" : "-", + edx_flags & (1 << 4) ? "TSC" : "-", + edx_flags & (1 << 5) ? "MSR" : "-", + edx_flags & (1 << 22) ? "ACPI-TM" : "-", + edx_flags & (1 << 28) ? "HT" : "-", + edx_flags & (1 << 29) ? "TM" : "-"); + } + if (genuine_intel) + model = intel_model_duplicates(model); + + if (!(edx_flags & (1 << 5))) + errx(1, "CPUID: no MSR"); + if (max_extended_level >= 0x80000007) { /* @@ -4576,9 +4600,6 @@ void process_cpuid() if (crystal_hz == 0) switch(model) { case INTEL_FAM6_SKYLAKE_MOBILE: /* SKL */ - case INTEL_FAM6_SKYLAKE_DESKTOP: /* SKL */ - case INTEL_FAM6_KABYLAKE_MOBILE: /* KBL */ - case INTEL_FAM6_KABYLAKE_DESKTOP: /* KBL */ crystal_hz = 24000000; /* 24.0 MHz */ break; case INTEL_FAM6_ATOM_GOLDMONT_X: /* DNV */ @@ -4860,6 +4881,8 @@ void topology_probe() return; for (i = 0; i <= topo.max_cpu_num; ++i) { + if (cpu_is_not_present(i)) + continue; fprintf(outf, "cpu %d pkg %d node %d lnode %d core %d thread %d\n", i, cpus[i].physical_package_id,