diff options
20 files changed, 911 insertions, 198 deletions
diff --git a/Documentation/admin-guide/pm/amd-pstate.rst b/Documentation/admin-guide/pm/amd-pstate.rst index 2f066df4ee9c..1923cb25073b 100644 --- a/Documentation/admin-guide/pm/amd-pstate.rst +++ b/Documentation/admin-guide/pm/amd-pstate.rst @@ -369,6 +369,32 @@ governor (for the policies it is attached to), or by the ``CPUFreq`` core (for t policies with other scaling governors). +Tracer Tool +------------- + +``amd_pstate_tracer.py`` can record and parse ``amd-pstate`` trace log, then +generate performance plots. This utility can be used to debug and tune the +performance of ``amd-pstate`` driver. The tracer tool needs to import intel +pstate tracer. + +Tracer tool located in ``linux/tools/power/x86/amd_pstate_tracer``. It can be +used in two ways. If trace file is available, then directly parse the file +with command :: + + ./amd_pstate_trace.py [-c cpus] -t <trace_file> -n <test_name> + +Or generate trace file with root privilege, then parse and plot with command :: + + sudo ./amd_pstate_trace.py [-c cpus] -n <test_name> -i <interval> [-m kbytes] + +The test result can be found in ``results/test_name``. Following is the example +about part of the output. :: + + common_cpu common_secs common_usecs min_perf des_perf max_perf freq mperf apef tsc load duration_ms sample_num elapsed_time common_comm + CPU_005 712 116384 39 49 166 0.7565 9645075 2214891 38431470 25.1 11.646 469 2.496 kworker/5:0-40 + CPU_006 712 116408 39 49 166 0.6769 8950227 1839034 37192089 24.06 11.272 470 2.496 kworker/6:0-1264 + + Reference =========== diff --git a/MAINTAINERS b/MAINTAINERS index 1ba1e4af2cbc..6d888b6dbe05 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1002,6 +1002,7 @@ L: linux-pm@vger.kernel.org S: Supported F: Documentation/admin-guide/pm/amd-pstate.rst F: drivers/cpufreq/amd-pstate* +F: tools/power/x86/amd_pstate_tracer/amd_pstate_trace.py AMD PTDMA DRIVER M: Sanjay R Mehta <sanju.mehta@amd.com> diff --git a/drivers/cpufreq/amd-pstate-trace.h b/drivers/cpufreq/amd-pstate-trace.h index 647505957d4f..35f38ae67fb1 100644 --- a/drivers/cpufreq/amd-pstate-trace.h +++ b/drivers/cpufreq/amd-pstate-trace.h @@ -27,6 +27,10 @@ TRACE_EVENT(amd_pstate_perf, TP_PROTO(unsigned long min_perf, unsigned long target_perf, unsigned long capacity, + u64 freq, + u64 mperf, + u64 aperf, + u64 tsc, unsigned int cpu_id, bool changed, bool fast_switch @@ -35,6 +39,10 @@ TRACE_EVENT(amd_pstate_perf, TP_ARGS(min_perf, target_perf, capacity, + freq, + mperf, + aperf, + tsc, cpu_id, changed, fast_switch @@ -44,6 +52,10 @@ TRACE_EVENT(amd_pstate_perf, __field(unsigned long, min_perf) __field(unsigned long, target_perf) __field(unsigned long, capacity) + __field(unsigned long long, freq) + __field(unsigned long long, mperf) + __field(unsigned long long, aperf) + __field(unsigned long long, tsc) __field(unsigned int, cpu_id) __field(bool, changed) __field(bool, fast_switch) @@ -53,15 +65,23 @@ TRACE_EVENT(amd_pstate_perf, __entry->min_perf = min_perf; __entry->target_perf = target_perf; __entry->capacity = capacity; + __entry->freq = freq; + __entry->mperf = mperf; + __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 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 changed=%s fast_switch=%s", (unsigned long)__entry->min_perf, (unsigned long)__entry->target_perf, (unsigned long)__entry->capacity, + (unsigned long long)__entry->freq, + (unsigned long long)__entry->mperf, + (unsigned long long)__entry->aperf, + (unsigned long long)__entry->tsc, (unsigned int)__entry->cpu_id, (__entry->changed) ? "true" : "false", (__entry->fast_switch) ? "true" : "false" diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index 9ce75ed11f8e..7be38bc6a673 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -66,6 +66,18 @@ MODULE_PARM_DESC(shared_mem, static struct cpufreq_driver amd_pstate_driver; /** + * 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 @@ -81,6 +93,9 @@ static struct cpufreq_driver amd_pstate_driver; * @min_freq: the frequency that mapped to lowest_perf * @nominal_freq: the frequency that mapped to nominal_perf * @lowest_nonlinear_freq: the frequency 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 * @boost_supported: check whether the Processor or SBIOS supports boost mode * * The amd_cpudata is key private data for each CPU thread in AMD P-State, and @@ -102,6 +117,10 @@ struct amd_cpudata { u32 nominal_freq; u32 lowest_nonlinear_freq; + struct amd_aperf_mperf cur; + struct amd_aperf_mperf prev; + + u64 freq; bool boost_supported; }; @@ -211,6 +230,39 @@ static inline void amd_pstate_update_perf(struct amd_cpudata *cpudata, max_perf, fast_switch); } +static inline bool amd_pstate_sample(struct amd_cpudata *cpudata) +{ + u64 aperf, mperf, tsc; + unsigned long flags; + + local_irq_save(flags); + rdmsrl(MSR_IA32_APERF, aperf); + rdmsrl(MSR_IA32_MPERF, mperf); + tsc = rdtsc(); + + if (cpudata->prev.mperf == mperf || cpudata->prev.tsc == tsc) { + local_irq_restore(flags); + return false; + } + + local_irq_restore(flags); + + cpudata->cur.aperf = aperf; + cpudata->cur.mperf = mperf; + cpudata->cur.tsc = tsc; + cpudata->cur.aperf -= cpudata->prev.aperf; + cpudata->cur.mperf -= cpudata->prev.mperf; + cpudata->cur.tsc -= cpudata->prev.tsc; + + cpudata->prev.aperf = aperf; + cpudata->prev.mperf = mperf; + cpudata->prev.tsc = tsc; + + cpudata->freq = div64_u64((cpudata->cur.aperf * cpu_khz), cpudata->cur.mperf); + + return true; +} + static void amd_pstate_update(struct amd_cpudata *cpudata, u32 min_perf, u32 des_perf, u32 max_perf, bool fast_switch) { @@ -226,8 +278,11 @@ static void amd_pstate_update(struct amd_cpudata *cpudata, u32 min_perf, value &= ~AMD_CPPC_MAX_PERF(~0L); value |= AMD_CPPC_MAX_PERF(max_perf); - trace_amd_pstate_perf(min_perf, des_perf, max_perf, - cpudata->cpu, (value != prev), fast_switch); + 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); + } if (value == prev) return; diff --git a/tools/power/cpupower/Makefile b/tools/power/cpupower/Makefile index 3b1594447f29..e9b6de314654 100644 --- a/tools/power/cpupower/Makefile +++ b/tools/power/cpupower/Makefile @@ -143,9 +143,9 @@ UTIL_HEADERS = utils/helpers/helpers.h utils/idle_monitor/cpupower-monitor.h \ utils/helpers/bitmask.h \ utils/idle_monitor/idle_monitors.h utils/idle_monitor/idle_monitors.def -LIB_HEADERS = lib/cpufreq.h lib/cpupower.h lib/cpuidle.h -LIB_SRC = lib/cpufreq.c lib/cpupower.c lib/cpuidle.c -LIB_OBJS = lib/cpufreq.o lib/cpupower.o lib/cpuidle.o +LIB_HEADERS = lib/cpufreq.h lib/cpupower.h lib/cpuidle.h lib/acpi_cppc.h +LIB_SRC = lib/cpufreq.c lib/cpupower.c lib/cpuidle.c lib/acpi_cppc.c +LIB_OBJS = lib/cpufreq.o lib/cpupower.o lib/cpuidle.o lib/acpi_cppc.o LIB_OBJS := $(addprefix $(OUTPUT),$(LIB_OBJS)) override CFLAGS += -pipe diff --git a/tools/power/cpupower/ToDo b/tools/power/cpupower/TODO index b196a139a3e4..b196a139a3e4 100644 --- a/tools/power/cpupower/ToDo +++ b/tools/power/cpupower/TODO diff --git a/tools/power/cpupower/lib/acpi_cppc.c b/tools/power/cpupower/lib/acpi_cppc.c new file mode 100644 index 000000000000..c401ac331e9f --- /dev/null +++ b/tools/power/cpupower/lib/acpi_cppc.c @@ -0,0 +1,59 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <stdio.h> +#include <errno.h> +#include <stdlib.h> +#include <string.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <unistd.h> + +#include "cpupower_intern.h" +#include "acpi_cppc.h" + +/* ACPI CPPC sysfs access ***********************************************/ + +static int acpi_cppc_read_file(unsigned int cpu, const char *fname, + char *buf, size_t buflen) +{ + char path[SYSFS_PATH_MAX]; + + snprintf(path, sizeof(path), PATH_TO_CPU "cpu%u/acpi_cppc/%s", + cpu, fname); + return cpupower_read_sysfs(path, buf, buflen); +} + +static const char * const acpi_cppc_value_files[] = { + [HIGHEST_PERF] = "highest_perf", + [LOWEST_PERF] = "lowest_perf", + [NOMINAL_PERF] = "nominal_perf", + [LOWEST_NONLINEAR_PERF] = "lowest_nonlinear_perf", + [LOWEST_FREQ] = "lowest_freq", + [NOMINAL_FREQ] = "nominal_freq", + [REFERENCE_PERF] = "reference_perf", + [WRAPAROUND_TIME] = "wraparound_time" +}; + +unsigned long acpi_cppc_get_data(unsigned int cpu, enum acpi_cppc_value which) +{ + unsigned long long value; + unsigned int len; + char linebuf[MAX_LINE_LEN]; + char *endp; + + if (which >= MAX_CPPC_VALUE_FILES) + return 0; + + len = acpi_cppc_read_file(cpu, acpi_cppc_value_files[which], + linebuf, sizeof(linebuf)); + if (len == 0) + return 0; + + value = strtoull(linebuf, &endp, 0); + + if (endp == linebuf || errno == ERANGE) + return 0; + + return value; +} diff --git a/tools/power/cpupower/lib/acpi_cppc.h b/tools/power/cpupower/lib/acpi_cppc.h new file mode 100644 index 000000000000..85ca83080316 --- /dev/null +++ b/tools/power/cpupower/lib/acpi_cppc.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef __ACPI_CPPC_H__ +#define __ACPI_CPPC_H__ + +enum acpi_cppc_value { + HIGHEST_PERF, + LOWEST_PERF, + NOMINAL_PERF, + LOWEST_NONLINEAR_PERF, + LOWEST_FREQ, + NOMINAL_FREQ, + REFERENCE_PERF, + WRAPAROUND_TIME, + MAX_CPPC_VALUE_FILES +}; + +unsigned long acpi_cppc_get_data(unsigned int cpu, + enum acpi_cppc_value which); + +#endif /* _ACPI_CPPC_H */ diff --git a/tools/power/cpupower/lib/cpufreq.c b/tools/power/cpupower/lib/cpufreq.c index c3b56db8b921..1516d23c17c9 100644 --- a/tools/power/cpupower/lib/cpufreq.c +++ b/tools/power/cpupower/lib/cpufreq.c @@ -83,20 +83,21 @@ static const char *cpufreq_value_files[MAX_CPUFREQ_VALUE_READ_FILES] = { [STATS_NUM_TRANSITIONS] = "stats/total_trans" }; - -static unsigned long sysfs_cpufreq_get_one_value(unsigned int cpu, - enum cpufreq_value which) +unsigned long cpufreq_get_sysfs_value_from_table(unsigned int cpu, + const char **table, + unsigned int index, + unsigned int size) { unsigned long value; unsigned int len; char linebuf[MAX_LINE_LEN]; char *endp; - if (which >= MAX_CPUFREQ_VALUE_READ_FILES) + if (!table || index >= size || !table[index]) return 0; - len = sysfs_cpufreq_read_file(cpu, cpufreq_value_files[which], - linebuf, sizeof(linebuf)); + len = sysfs_cpufreq_read_file(cpu, table[index], linebuf, + sizeof(linebuf)); if (len == 0) return 0; @@ -109,6 +110,14 @@ static unsigned long sysfs_cpufreq_get_one_value(unsigned int cpu, return value; } +static unsigned long sysfs_cpufreq_get_one_value(unsigned int cpu, + enum cpufreq_value which) +{ + return cpufreq_get_sysfs_value_from_table(cpu, cpufreq_value_files, + which, + MAX_CPUFREQ_VALUE_READ_FILES); +} + /* read access to files which contain one string */ enum cpufreq_string { @@ -124,7 +133,7 @@ static const char *cpufreq_string_files[MAX_CPUFREQ_STRING_FILES] = { static char *sysfs_cpufreq_get_one_string(unsigned int cpu, - enum cpufreq_string which) + enum cpufreq_string which) { char linebuf[MAX_LINE_LEN]; char *result; diff --git a/tools/power/cpupower/lib/cpufreq.h b/tools/power/cpupower/lib/cpufreq.h index 95f4fd9e2656..2f3c84035806 100644 --- a/tools/power/cpupower/lib/cpufreq.h +++ b/tools/power/cpupower/lib/cpufreq.h @@ -203,6 +203,18 @@ int cpufreq_modify_policy_governor(unsigned int cpu, char *governor); int cpufreq_set_frequency(unsigned int cpu, unsigned long target_frequency); +/* + * get the sysfs value from specific table + * + * Read the value with the sysfs file name from specific table. Does + * only work if the cpufreq driver has the specific sysfs interfaces. + */ + +unsigned long cpufreq_get_sysfs_value_from_table(unsigned int cpu, + const char **table, + unsigned int index, + unsigned int size); + #ifdef __cplusplus } #endif diff --git a/tools/power/cpupower/man/cpupower-frequency-info.1 b/tools/power/cpupower/man/cpupower-frequency-info.1 index 6aa8d239dff9..dd545b499480 100644 --- a/tools/power/cpupower/man/cpupower-frequency-info.1 +++ b/tools/power/cpupower/man/cpupower-frequency-info.1 @@ -53,6 +53,9 @@ human\-readable output for the \-f, \-w, \-s and \-y parameters. \fB\-n\fR \fB\-\-no-rounding\fR Output frequencies and latencies without rounding off values. .TP +\fB\-c\fR \fB\-\-perf\fR +Get performances and frequencies capabilities of CPPC, by reading it from hardware (only available on the hardware with CPPC). +.TP .SH "REMARKS" .LP By default only values of core zero are displayed. How to display settings of diff --git a/tools/power/cpupower/man/cpupower-idle-set.1 b/tools/power/cpupower/man/cpupower-idle-set.1 index 21916cff7516..8cef3c71e19e 100644 --- a/tools/power/cpupower/man/cpupower-idle-set.1 +++ b/tools/power/cpupower/man/cpupower-idle-set.1 @@ -4,7 +4,7 @@ cpupower\-idle\-set \- Utility to set cpu idle state specific kernel options .SH "SYNTAX" .LP -cpupower [ \-c cpulist ] idle\-info [\fIoptions\fP] +cpupower [ \-c cpulist ] idle\-set [\fIoptions\fP] .SH "DESCRIPTION" .LP The cpupower idle\-set subcommand allows to set cpu idle, also called cpu diff --git a/tools/power/cpupower/utils/cpufreq-info.c b/tools/power/cpupower/utils/cpufreq-info.c index f9895e31ff5a..0646f615fe2d 100644 --- a/tools/power/cpupower/utils/cpufreq-info.c +++ b/tools/power/cpupower/utils/cpufreq-info.c @@ -84,43 +84,6 @@ static void proc_cpufreq_output(void) } static int no_rounding; -static void print_speed(unsigned long speed) -{ - unsigned long tmp; - - if (no_rounding) { - if (speed > 1000000) - printf("%u.%06u GHz", ((unsigned int) speed/1000000), - ((unsigned int) speed%1000000)); - else if (speed > 1000) - printf("%u.%03u MHz", ((unsigned int) speed/1000), - (unsigned int) (speed%1000)); - else - printf("%lu kHz", speed); - } else { - if (speed > 1000000) { - tmp = speed%10000; - if (tmp >= 5000) - speed += 10000; - printf("%u.%02u GHz", ((unsigned int) speed/1000000), - ((unsigned int) (speed%1000000)/10000)); - } else if (speed > 100000) { - tmp = speed%1000; - if (tmp >= 500) - speed += 1000; - printf("%u MHz", ((unsigned int) speed/1000)); - } else if (speed > 1000) { - tmp = speed%100; - if (tmp >= 50) - speed += 100; - printf("%u.%01u MHz", ((unsigned int) speed/1000), - ((unsigned int) (speed%1000)/100)); - } - } - - return; -} - static void print_duration(unsigned long duration) { unsigned long tmp; @@ -183,9 +146,12 @@ static int get_boost_mode_x86(unsigned int cpu) printf(_(" Supported: %s\n"), support ? _("yes") : _("no")); printf(_(" Active: %s\n"), active ? _("yes") : _("no")); - if ((cpupower_cpu_info.vendor == X86_VENDOR_AMD && - cpupower_cpu_info.family >= 0x10) || - cpupower_cpu_info.vendor == X86_VENDOR_HYGON) { + if (cpupower_cpu_info.vendor == X86_VENDOR_AMD && + cpupower_cpu_info.caps & CPUPOWER_CAP_AMD_PSTATE) { + return 0; + } else if ((cpupower_cpu_info.vendor == X86_VENDOR_AMD && + cpupower_cpu_info.family >= 0x10) || + cpupower_cpu_info.vendor == X86_VENDOR_HYGON) { ret = decode_pstates(cpu, b_states, pstates, &pstate_no); if (ret) return ret; @@ -254,11 +220,11 @@ static int get_boost_mode(unsigned int cpu) if (freqs) { printf(_(" boost frequency steps: ")); while (freqs->next) { - print_speed(freqs->frequency); + print_speed(freqs->frequency, no_rounding); printf(", "); freqs = freqs->next; } - print_speed(freqs->frequency); + print_speed(freqs->frequency, no_rounding); printf("\n"); cpufreq_put_available_frequencies(freqs); } @@ -277,7 +243,7 @@ static int get_freq_kernel(unsigned int cpu, unsigned int human) return -EINVAL; } if (human) { - print_speed(freq); + print_speed(freq, no_rounding); } else printf("%lu", freq); printf(_(" (asserted by call to kernel)\n")); @@ -296,7 +262,7 @@ static int get_freq_hardware(unsigned int cpu, unsigned int human) return -EINVAL; } if (human) { - print_speed(freq); + print_speed(freq, no_rounding); } else printf("%lu", freq); printf(_(" (asserted by call to hardware)\n")); @@ -316,9 +282,9 @@ static int get_hardware_limits(unsigned int cpu, unsigned int human) if (human) { printf(_(" hardware limits: ")); - print_speed(min); + print_speed(min, no_rounding); printf(" - "); - print_speed(max); + print_speed(max, no_rounding); printf("\n"); } else { printf("%lu %lu\n", min, max); @@ -350,9 +316,9 @@ static int get_policy(unsigned int cpu) return -EINVAL; } printf(_(" current policy: frequency should be within ")); - print_speed(policy->min); + print_speed(policy->min, no_rounding); printf(_(" and ")); - print_speed(policy->max); + print_speed(policy->max, no_rounding); printf(".\n "); printf(_("The governor \"%s\" may decide which speed to use\n" @@ -436,7 +402,7 @@ static int get_freq_stats(unsigned int cpu, unsigned int human) struct cpufreq_stats *stats = cpufreq_get_stats(cpu, &total_time); while (stats) { if (human) { - print_speed(stats->frequency); + print_speed(stats->frequency, no_rounding); printf(":%.2f%%", (100.0 * stats->time_in_state) / total_time); } else @@ -472,6 +438,17 @@ static int get_latency(unsigned int cpu, unsigned int human) return 0; } +/* --performance / -c */ + +static int get_perf_cap(unsigned int cpu) +{ + if (cpupower_cpu_info.vendor == X86_VENDOR_AMD && + cpupower_cpu_info.caps & CPUPOWER_CAP_AMD_PSTATE) + amd_pstate_show_perf_and_freq(cpu, no_rounding); + + return 0; +} + static void debug_output_one(unsigned int cpu) { struct cpufreq_available_frequencies *freqs; @@ -486,11 +463,11 @@ static void debug_output_one(unsigned int cpu) if (freqs) { printf(_(" available frequency steps: ")); while (freqs->next) { - print_speed(freqs->frequency); + print_speed(freqs->frequency, no_rounding); printf(", "); freqs = freqs->next; } - print_speed(freqs->frequency); + print_speed(freqs->frequency, no_rounding); printf("\n"); cpufreq_put_available_frequencies(freqs); } @@ -500,6 +477,7 @@ static void debug_output_one(unsigned int cpu) if (get_freq_hardware(cpu, 1) < 0) get_freq_kernel(cpu, 1); get_boost_mode(cpu); + get_perf_cap(cpu); } static struct option info_opts[] = { @@ -518,6 +496,7 @@ static struct option info_opts[] = { {"proc", no_argument, NULL, 'o'}, {"human", no_argument, NULL, 'm'}, {"no-rounding", no_argument, NULL, 'n'}, + {"performance", no_argument, NULL, 'c'}, { }, }; @@ -531,7 +510,7 @@ int cmd_freq_info(int argc, char **argv) int output_param = 0; do { - ret = getopt_long(argc, argv, "oefwldpgrasmybn", info_opts, + ret = getopt_long(argc, argv, "oefwldpgrasmybnc", info_opts, NULL); switch (ret) { case '?': @@ -554,6 +533,7 @@ int cmd_freq_info(int argc, char **argv) case 'e': case 's': case 'y': + case 'c': if (output_param) { output_param = -1; cont = 0; @@ -660,6 +640,9 @@ int cmd_freq_info(int argc, char **argv) case 'y': ret = get_latency(cpu, human); break; + case 'c': + ret = get_perf_cap(cpu); + break; } if (ret) return ret; diff --git a/tools/power/cpupower/utils/helpers/amd.c b/tools/power/cpupower/utils/helpers/amd.c index 97f2c857048e..c519cc89c97f 100644 --- a/tools/power/cpupower/utils/helpers/amd.c +++ b/tools/power/cpupower/utils/helpers/amd.c @@ -8,7 +8,10 @@ #include <pci/pci.h> #include "helpers/helpers.h" +#include "cpufreq.h" +#include "acpi_cppc.h" +/* ACPI P-States Helper Functions for AMD Processors ***************/ #define MSR_AMD_PSTATE_STATUS 0xc0010063 #define MSR_AMD_PSTATE 0xc0010064 #define MSR_AMD_PSTATE_LIMIT 0xc0010061 @@ -146,4 +149,78 @@ int amd_pci_get_num_boost_states(int *active, int *states) pci_cleanup(pci_acc); return 0; } + +/* ACPI P-States Helper Functions for AMD Processors ***************/ + +/* AMD P-State Helper Functions ************************************/ +enum amd_pstate_value { + AMD_PSTATE_HIGHEST_PERF, + AMD_PSTATE_MAX_FREQ, + AMD_PSTATE_LOWEST_NONLINEAR_FREQ, + MAX_AMD_PSTATE_VALUE_READ_FILES, +}; + +static const char *amd_pstate_value_files[MAX_AMD_PSTATE_VALUE_READ_FILES] = { + [AMD_PSTATE_HIGHEST_PERF] = "amd_pstate_highest_perf", + [AMD_PSTATE_MAX_FREQ] = "amd_pstate_max_freq", + [AMD_PSTATE_LOWEST_NONLINEAR_FREQ] = "amd_pstate_lowest_nonlinear_freq", +}; + +static unsigned long amd_pstate_get_data(unsigned int cpu, + enum amd_pstate_value value) +{ + return cpufreq_get_sysfs_value_from_table(cpu, + amd_pstate_value_files, + value, + MAX_AMD_PSTATE_VALUE_READ_FILES); +} + +void amd_pstate_boost_init(unsigned int cpu, int *support, int *active) +{ + unsigned long highest_perf, nominal_perf, cpuinfo_min, + cpuinfo_max, amd_pstate_max; + + highest_perf = amd_pstate_get_data(cpu, AMD_PSTATE_HIGHEST_PERF); + nominal_perf = acpi_cppc_get_data(cpu, NOMINAL_PERF); + + *support = highest_perf > nominal_perf ? 1 : 0; + if (!(*support)) + return; + + cpufreq_get_hardware_limits(cpu, &cpuinfo_min, &cpuinfo_max); + amd_pstate_max = amd_pstate_get_data(cpu, AMD_PSTATE_MAX_FREQ); + + *active = cpuinfo_max == amd_pstate_max ? 1 : 0; +} + +void amd_pstate_show_perf_and_freq(unsigned int cpu, int no_rounding) +{ + printf(_(" AMD PSTATE Highest Performance: %lu. Maximum Frequency: "), + amd_pstate_get_data(cpu, AMD_PSTATE_HIGHEST_PERF)); + /* + * If boost isn't active, the cpuinfo_max doesn't indicate real max + * frequency. So we read it back from amd-pstate sysfs entry. + */ + print_speed(amd_pstate_get_data(cpu, AMD_PSTATE_MAX_FREQ), no_rounding); + printf(".\n"); + + printf(_(" AMD PSTATE Nominal Performance: %lu. Nominal Frequency: "), + acpi_cppc_get_data(cpu, NOMINAL_PERF)); + print_speed(acpi_cppc_get_data(cpu, NOMINAL_FREQ) * 1000, + no_rounding); + printf(".\n"); + + printf(_(" AMD PSTATE Lowest Non-linear Performance: %lu. Lowest Non-linear Frequency: "), + acpi_cppc_get_data(cpu, LOWEST_NONLINEAR_PERF)); + print_speed(amd_pstate_get_data(cpu, AMD_PSTATE_LOWEST_NONLINEAR_FREQ), + no_rounding); + printf(".\n"); + + printf(_(" AMD PSTATE Lowest Performance: %lu. Lowest Frequency: "), + acpi_cppc_get_data(cpu, LOWEST_PERF)); + print_speed(acpi_cppc_get_data(cpu, LOWEST_FREQ) * 1000, no_rounding); + printf(".\n"); +} + +/* AMD P-State Helper Functions ************************************/ #endif /* defined(__i386__) || defined(__x86_64__) */ diff --git a/tools/power/cpupower/utils/helpers/cpuid.c b/tools/power/cpupower/utils/helpers/cpuid.c index 72eb43593180..eae91f11d187 100644 --- a/tools/power/cpupower/utils/helpers/cpuid.c +++ b/tools/power/cpupower/utils/helpers/cpuid.c @@ -149,6 +149,19 @@ out: if (ext_cpuid_level >= 0x80000008 && cpuid_ebx(0x80000008) & (1 << 4)) cpu_info->caps |= CPUPOWER_CAP_AMD_RDPRU; + + if (cpupower_amd_pstate_enabled()) { + cpu_info->caps |= CPUPOWER_CAP_AMD_PSTATE; + + /* + * If AMD P-State is enabled, the firmware will treat + * AMD P-State function as high priority. + */ + cpu_info->caps &= ~CPUPOWER_CAP_AMD_CPB; + cpu_info->caps &= ~CPUPOWER_CAP_AMD_CPB_MSR; + cpu_info->caps &= ~CPUPOWER_CAP_AMD_HW_PSTATE; + cpu_info->caps &= ~CPUPOWER_CAP_AMD_PSTATEDEF; + } } if (cpu_info->vendor == X86_VENDOR_INTEL) { diff --git a/tools/power/cpupower/utils/helpers/helpers.h b/tools/power/cpupower/utils/helpers/helpers.h index 33ffacee7fcb..96e4bede078b 100644 --- a/tools/power/cpupower/utils/helpers/helpers.h +++ b/tools/power/cpupower/utils/helpers/helpers.h @@ -11,6 +11,7 @@ #include <libintl.h> #include <locale.h> +#include <stdbool.h> #include "helpers/bitmask.h" #include <cpupower.h> @@ -73,6 +74,7 @@ enum cpupower_cpu_vendor {X86_VENDOR_UNKNOWN = 0, X86_VENDOR_INTEL, #define CPUPOWER_CAP_AMD_HW_PSTATE 0x00000100 #define CPUPOWER_CAP_AMD_PSTATEDEF 0x00000200 #define CPUPOWER_CAP_AMD_CPB_MSR 0x00000400 +#define CPUPOWER_CAP_AMD_PSTATE 0x00000800 #define CPUPOWER_AMD_CPBDIS 0x02000000 @@ -135,6 +137,16 @@ extern int decode_pstates(unsigned int cpu, int boost_states, extern int cpufreq_has_boost_support(unsigned int cpu, int *support, int *active, int * states); + +/* AMD P-State stuff **************************/ +bool cpupower_amd_pstate_enabled(void); +void amd_pstate_boost_init(unsigned int cpu, + int *support, int *active); +void amd_pstate_show_perf_and_freq(unsigned int cpu, + int no_rounding); + +/* AMD P-State stuff **************************/ + /* * CPUID functions returning a single datum */ @@ -167,6 +179,15 @@ static inline int cpufreq_has_boost_support(unsigned int cpu, int *support, int *active, int * states) { return -1; } +static inline bool cpupower_amd_pstate_enabled(void) +{ return false; } +static inline void amd_pstate_boost_init(unsigned int cpu, int *support, + int *active) +{} +static inline void amd_pstate_show_perf_and_freq(unsigned int cpu, + int no_rounding) +{} + /* cpuid and cpuinfo helpers **************************/ static inline unsigned int cpuid_eax(unsigned int op) { return 0; }; @@ -184,5 +205,6 @@ extern struct bitmask *offline_cpus; void get_cpustate(void); void print_online_cpus(void); void print_offline_cpus(void); +void print_speed(unsigned long speed, int no_rounding); #endif /* __CPUPOWERUTILS_HELPERS__ */ diff --git a/tools/power/cpupower/utils/helpers/misc.c b/tools/power/cpupower/utils/helpers/misc.c index fc6e34511721..9547b29254a7 100644 --- a/tools/power/cpupower/utils/helpers/misc.c +++ b/tools/power/cpupower/utils/helpers/misc.c @@ -3,9 +3,11 @@ #include <stdio.h> #include <errno.h> #include <stdlib.h> +#include <string.h> #include "helpers/helpers.h" #include "helpers/sysfs.h" +#include "cpufreq.h" #if defined(__i386__) || defined(__x86_64__) @@ -39,6 +41,8 @@ int cpufreq_has_boost_support(unsigned int cpu, int *support, int *active, if (ret) return ret; } + } else if (cpupower_cpu_info.caps & CPUPOWER_CAP_AMD_PSTATE) { + amd_pstate_boost_init(cpu, support, active); } else if (cpupower_cpu_info.caps & CPUPOWER_CAP_INTEL_IDA) *support = *active = 1; return 0; @@ -83,6 +87,22 @@ int cpupower_intel_set_perf_bias(unsigned int cpu, unsigned int val) return 0; } +bool cpupower_amd_pstate_enabled(void) +{ + char *driver = cpufreq_get_driver(0); + bool ret = false; + + if (!driver) + return ret; + + if (!strcmp(driver, "amd-pstate")) + ret = true; + + cpufreq_put_driver(driver); + + return ret; +} + #endif /* #if defined(__i386__) || defined(__x86_64__) */ /* get_cpustate @@ -144,3 +164,43 @@ void print_offline_cpus(void) printf(_("cpupower set operation was not performed on them\n")); } } + +/* + * print_speed + * + * Print the exact CPU frequency with appropriate unit + */ +void print_speed(unsigned long speed, int no_rounding) +{ + unsigned long tmp; + + if (no_rounding) { + if (speed > 1000000) + printf("%u.%06u GHz", ((unsigned int)speed / 1000000), + ((unsigned int)speed % 1000000)); + else if (speed > 1000) + printf("%u.%03u MHz", ((unsigned int)speed / 1000), + (unsigned int)(speed % 1000)); + else + printf("%lu kHz", speed); + } else { + if (speed > 1000000) { + tmp = speed % 10000; + if (tmp >= 5000) + speed += 10000; + printf("%u.%02u GHz", ((unsigned int)speed / 1000000), + ((unsigned int)(speed % 1000000) / 10000)); + } else if (speed > 100000) { + tmp = speed % 1000; + if (tmp >= 500) + speed += 1000; + printf("%u MHz", ((unsigned int)speed / 1000)); + } else if (speed > 1000) { + tmp = speed % 100; + if (tmp >= 50) + speed += 100; + printf("%u.%01u MHz", ((unsigned int)speed / 1000), + ((unsigned int)(speed % 1000) / 100)); + } + } +} diff --git a/tools/power/x86/amd_pstate_tracer/amd_pstate_trace.py b/tools/power/x86/amd_pstate_tracer/amd_pstate_trace.py new file mode 100755 index 000000000000..2dea4032ac56 --- /dev/null +++ b/tools/power/x86/amd_pstate_tracer/amd_pstate_trace.py @@ -0,0 +1,354 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0-only +# -*- coding: utf-8 -*- +# +""" This utility can be used to debug and tune the performance of the +AMD P-State driver. It imports intel_pstate_tracer to analyze AMD P-State +trace event. + +Prerequisites: + Python version 2.7.x or higher + gnuplot 5.0 or higher + gnuplot-py 1.8 or higher + (Most of the distributions have these required packages. They may be called + gnuplot-py, phython-gnuplot or phython3-gnuplot, gnuplot-nox, ... ) + + Kernel config for Linux trace is enabled + + see print_help(): for Usage and Output details + +""" +from __future__ import print_function +from datetime import datetime +import subprocess +import os +import time +import re +import signal +import sys +import getopt +import Gnuplot +from numpy import * +from decimal import * +sys.path.append('../intel_pstate_tracer') +#import intel_pstate_tracer +import intel_pstate_tracer as ipt + +__license__ = "GPL version 2" + +MAX_CPUS = 256 +# Define the csv file columns +C_COMM = 15 +C_ELAPSED = 14 +C_SAMPLE = 13 +C_DURATION = 12 +C_LOAD = 11 +C_TSC = 10 +C_APERF = 9 +C_MPERF = 8 +C_FREQ = 7 +C_MAX_PERF = 6 +C_DES_PERF = 5 +C_MIN_PERF = 4 +C_USEC = 3 +C_SEC = 2 +C_CPU = 1 + +global sample_num, last_sec_cpu, last_usec_cpu, start_time, test_name, trace_file + +getcontext().prec = 11 + +sample_num =0 +last_sec_cpu = [0] * MAX_CPUS +last_usec_cpu = [0] * MAX_CPUS + +def plot_per_cpu_freq(cpu_index): + """ Plot per cpu frequency """ + + file_name = 'cpu{:0>3}.csv'.format(cpu_index) + if os.path.exists(file_name): + output_png = "cpu%03d_frequency.png" % cpu_index + g_plot = ipt.common_gnuplot_settings() + g_plot('set output "' + output_png + '"') + g_plot('set yrange [0:7]') + g_plot('set ytics 0, 1') + g_plot('set ylabel "CPU Frequency (GHz)"') + g_plot('set title "{} : frequency : CPU {:0>3} : {:%F %H:%M}"'.format(test_name, cpu_index, datetime.now())) + g_plot('set ylabel "CPU frequency"') + g_plot('set key off') + ipt.set_4_plot_linestyles(g_plot) + g_plot('plot "' + file_name + '" using {:d}:{:d} with linespoints linestyle 1 axis x1y1'.format(C_ELAPSED, C_FREQ)) + +def plot_per_cpu_des_perf(cpu_index): + """ Plot per cpu desired perf """ + + file_name = 'cpu{:0>3}.csv'.format(cpu_index) + if os.path.exists(file_name): + output_png = "cpu%03d_des_perf.png" % cpu_index + g_plot = ipt.common_gnuplot_settings() + g_plot('set output "' + output_png + '"') + g_plot('set yrange [0:255]') + g_plot('set ylabel "des perf"') + g_plot('set title "{} : cpu des perf : CPU {:0>3} : {:%F %H:%M}"'.format(test_name, cpu_index, datetime.now())) + g_plot('set key off') + ipt.set_4_plot_linestyles(g_plot) + g_plot('plot "' + file_name + '" using {:d}:{:d} with linespoints linestyle 1 axis x1y1'.format(C_ELAPSED, C_DES_PERF)) + +def plot_per_cpu_load(cpu_index): + """ Plot per cpu load """ + + file_name = 'cpu{:0>3}.csv'.format(cpu_index) + if os.path.exists(file_name): + output_png = "cpu%03d_load.png" % cpu_index + g_plot = ipt.common_gnuplot_settings() + g_plot('set output "' + output_png + '"') + g_plot('set yrange [0:100]') + g_plot('set ytics 0, 10') + g_plot('set ylabel "CPU load (percent)"') + g_plot('set title "{} : cpu load : CPU {:0>3} : {:%F %H:%M}"'.format(test_name, cpu_index, datetime.now())) + g_plot('set key off') + ipt.set_4_plot_linestyles(g_plot) + g_plot('plot "' + file_name + '" using {:d}:{:d} with linespoints linestyle 1 axis x1y1'.format(C_ELAPSED, C_LOAD)) + +def plot_all_cpu_frequency(): + """ Plot all cpu frequencies """ + + output_png = 'all_cpu_frequencies.png' + g_plot = ipt.common_gnuplot_settings() + g_plot('set output "' + output_png + '"') + g_plot('set ylabel "CPU Frequency (GHz)"') + g_plot('set title "{} : cpu frequencies : {:%F %H:%M}"'.format(test_name, datetime.now())) + + title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).decode('utf-8').replace('\n', ' ') + plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_FREQ) + g_plot('title_list = "{}"'.format(title_list)) + g_plot(plot_str) + +def plot_all_cpu_des_perf(): + """ Plot all cpu desired perf """ + + output_png = 'all_cpu_des_perf.png' + g_plot = ipt.common_gnuplot_settings() + g_plot('set output "' + output_png + '"') + g_plot('set ylabel "des perf"') + g_plot('set title "{} : cpu des perf : {:%F %H:%M}"'.format(test_name, datetime.now())) + + title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).decode('utf-8').replace('\n', ' ') + plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 255 ps 1 title i".format(C_ELAPSED, C_DES_PERF) + g_plot('title_list = "{}"'.format(title_list)) + g_plot(plot_str) + +def plot_all_cpu_load(): + """ Plot all cpu load """ + + output_png = 'all_cpu_load.png' + g_plot = ipt.common_gnuplot_settings() + g_plot('set output "' + output_png + '"') + g_plot('set yrange [0:100]') + g_plot('set ylabel "CPU load (percent)"') + g_plot('set title "{} : cpu load : {:%F %H:%M}"'.format(test_name, datetime.now())) + + title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).decode('utf-8').replace('\n', ' ') + plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 255 ps 1 title i".format(C_ELAPSED, C_LOAD) + g_plot('title_list = "{}"'.format(title_list)) + g_plot(plot_str) + +def store_csv(cpu_int, time_pre_dec, time_post_dec, min_perf, des_perf, max_perf, freq_ghz, mperf, aperf, tsc, common_comm, load, duration_ms, sample_num, elapsed_time, cpu_mask): + """ Store master csv file information """ + + global graph_data_present + + if cpu_mask[cpu_int] == 0: + return + + try: + f_handle = open('cpu.csv', 'a') + string_buffer = "CPU_%03u, %05u, %06u, %u, %u, %u, %.4f, %u, %u, %u, %.2f, %.3f, %u, %.3f, %s\n" % (cpu_int, int(time_pre_dec), int(time_post_dec), int(min_perf), int(des_perf), int(max_perf), freq_ghz, int(mperf), int(aperf), int(tsc), load, duration_ms, sample_num, elapsed_time, common_comm) + f_handle.write(string_buffer) + f_handle.close() + except: + print('IO error cpu.csv') + return + + graph_data_present = True; + + +def cleanup_data_files(): + """ clean up existing data files """ + + if os.path.exists('cpu.csv'): + os.remove('cpu.csv') + f_handle = open('cpu.csv', 'a') + f_handle.write('common_cpu, common_secs, common_usecs, min_perf, des_perf, max_perf, freq, mperf, aperf, tsc, load, duration_ms, sample_num, elapsed_time, common_comm') + f_handle.write('\n') + f_handle.close() + +def read_trace_data(file_name, cpu_mask): + """ Read and parse trace data """ + + global current_max_cpu + global sample_num, last_sec_cpu, last_usec_cpu, start_time + + try: + data = open(file_name, 'r').read() + except: + print('Error opening ', file_name) + sys.exit(2) + + for line in data.splitlines(): + search_obj = \ + re.search(r'(^(.*?)\[)((\d+)[^\]])(.*?)(\d+)([.])(\d+)(.*?amd_min_perf=)(\d+)(.*?amd_des_perf=)(\d+)(.*?amd_max_perf=)(\d+)(.*?freq=)(\d+)(.*?mperf=)(\d+)(.*?aperf=)(\d+)(.*?tsc=)(\d+)' + , line) + + if search_obj: + cpu = search_obj.group(3) + cpu_int = int(cpu) + cpu = str(cpu_int) + + time_pre_dec = search_obj.group(6) + time_post_dec = search_obj.group(8) + min_perf = search_obj.group(10) + des_perf = search_obj.group(12) + max_perf = search_obj.group(14) + freq = search_obj.group(16) + mperf = search_obj.group(18) + aperf = search_obj.group(20) + tsc = search_obj.group(22) + + common_comm = search_obj.group(2).replace(' ', '') + + if sample_num == 0 : + start_time = Decimal(time_pre_dec) + Decimal(time_post_dec) / Decimal(1000000) + sample_num += 1 + + if last_sec_cpu[cpu_int] == 0 : + last_sec_cpu[cpu_int] = time_pre_dec + last_usec_cpu[cpu_int] = time_post_dec + else : + duration_us = (int(time_pre_dec) - int(last_sec_cpu[cpu_int])) * 1000000 + (int(time_post_dec) - int(last_usec_cpu[cpu_int])) + duration_ms = Decimal(duration_us) / Decimal(1000) + last_sec_cpu[cpu_int] = time_pre_dec + last_usec_cpu[cpu_int] = time_post_dec + elapsed_time = Decimal(time_pre_dec) + Decimal(time_post_dec) / Decimal(1000000) - start_time + load = Decimal(int(mperf)*100)/ Decimal(tsc) + freq_ghz = Decimal(freq)/Decimal(1000000) + store_csv(cpu_int, time_pre_dec, time_post_dec, min_perf, des_perf, max_perf, freq_ghz, mperf, aperf, tsc, common_comm, load, duration_ms, sample_num, elapsed_time, cpu_mask) + + if cpu_int > current_max_cpu: + current_max_cpu = cpu_int +# Now separate the main overall csv file into per CPU csv files. + ipt.split_csv(current_max_cpu, cpu_mask) + + +def signal_handler(signal, frame): + print(' SIGINT: Forcing cleanup before exit.') + if interval: + ipt.disable_trace(trace_file) + ipt.clear_trace_file() + ipt.free_trace_buffer() + sys.exit(0) + +trace_file = "/sys/kernel/debug/tracing/events/amd_cpu/enable" +signal.signal(signal.SIGINT, signal_handler) + +interval = "" +file_name = "" +cpu_list = "" +test_name = "" +memory = "10240" +graph_data_present = False; + +valid1 = False +valid2 = False + +cpu_mask = zeros((MAX_CPUS,), dtype=int) + + +try: + opts, args = getopt.getopt(sys.argv[1:],"ht:i:c:n:m:",["help","trace_file=","interval=","cpu=","name=","memory="]) +except getopt.GetoptError: + ipt.print_help('amd_pstate') + sys.exit(2) +for opt, arg in opts: + if opt == '-h': + print() + sys.exit() + elif opt in ("-t", "--trace_file"): + valid1 = True + location = os.path.realpath(os.path.join(os.getcwd(), os.path.dirname(__file__))) + file_name = os.path.join(location, arg) + elif opt in ("-i", "--interval"): + valid1 = True + interval = arg + elif opt in ("-c", "--cpu"): + cpu_list = arg + elif opt in ("-n", "--name"): + valid2 = True + test_name = arg + elif opt in ("-m", "--memory"): + memory = arg + +if not (valid1 and valid2): + ipt.print_help('amd_pstate') + sys.exit() + +if cpu_list: + for p in re.split("[,]", cpu_list): + if int(p) < MAX_CPUS : + cpu_mask[int(p)] = 1 +else: + for i in range (0, MAX_CPUS): + cpu_mask[i] = 1 + +if not os.path.exists('results'): + os.mkdir('results') + ipt.fix_ownership('results') + +os.chdir('results') +if os.path.exists(test_name): + print('The test name directory already exists. Please provide a unique test name. Test re-run not supported, yet.') + sys.exit() +os.mkdir(test_name) +ipt.fix_ownership(test_name) +os.chdir(test_name) + +cur_version = sys.version_info +print('python version (should be >= 2.7):') +print(cur_version) + +cleanup_data_files() + +if interval: + file_name = "/sys/kernel/debug/tracing/trace" + ipt.clear_trace_file() + ipt.set_trace_buffer_size(memory) + ipt.enable_trace(trace_file) + time.sleep(int(interval)) + ipt.disable_trace(trace_file) + +current_max_cpu = 0 + +read_trace_data(file_name, cpu_mask) + +if interval: + ipt.clear_trace_file() + ipt.free_trace_buffer() + +if graph_data_present == False: + print('No valid data to plot') + sys.exit(2) + +for cpu_no in range(0, current_max_cpu + 1): + plot_per_cpu_freq(cpu_no) + plot_per_cpu_des_perf(cpu_no) + plot_per_cpu_load(cpu_no) + +plot_all_cpu_des_perf() +plot_all_cpu_frequency() +plot_all_cpu_load() + +for root, dirs, files in os.walk('.'): + for f in files: + ipt.fix_ownership(f) + +os.chdir('../../') 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 e15e20696d17..b46e9eb8f5aa 100755 --- a/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py +++ b/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py @@ -63,7 +63,7 @@ C_USEC = 3 C_SEC = 2 C_CPU = 1 -global sample_num, last_sec_cpu, last_usec_cpu, start_time, testname +global sample_num, last_sec_cpu, last_usec_cpu, start_time, testname, trace_file # 11 digits covers uptime to 115 days getcontext().prec = 11 @@ -72,17 +72,17 @@ sample_num =0 last_sec_cpu = [0] * MAX_CPUS last_usec_cpu = [0] * MAX_CPUS -def print_help(): - print('intel_pstate_tracer.py:') +def print_help(driver_name): + print('%s_tracer.py:'%driver_name) print(' Usage:') print(' If the trace file is available, then to simply parse and plot, use (sudo not required):') - print(' ./intel_pstate_tracer.py [-c cpus] -t <trace_file> -n <test_name>') + print(' ./%s_tracer.py [-c cpus] -t <trace_file> -n <test_name>'%driver_name) print(' Or') - print(' ./intel_pstate_tracer.py [--cpu cpus] ---trace_file <trace_file> --name <test_name>') + print(' ./%s_tracer.py [--cpu cpus] ---trace_file <trace_file> --name <test_name>'%driver_name) print(' To generate trace file, parse and plot, use (sudo required):') - print(' sudo ./intel_pstate_tracer.py [-c cpus] -i <interval> -n <test_name> -m <kbytes>') + print(' sudo ./%s_tracer.py [-c cpus] -i <interval> -n <test_name> -m <kbytes>'%driver_name) print(' Or') - print(' sudo ./intel_pstate_tracer.py [--cpu cpus] --interval <interval> --name <test_name> --memory <kbytes>') + print(' sudo ./%s_tracer.py [--cpu cpus] --interval <interval> --name <test_name> --memory <kbytes>'%driver_name) print(' Optional argument:') print(' cpus: comma separated list of CPUs') print(' kbytes: Kilo bytes of memory per CPU to allocate to the trace buffer. Default: 10240') @@ -323,7 +323,7 @@ def set_4_plot_linestyles(g_plot): g_plot('set style line 3 linetype 1 linecolor rgb "purple" pointtype -1') g_plot('set style line 4 linetype 1 linecolor rgb "blue" pointtype -1') -def store_csv(cpu_int, time_pre_dec, time_post_dec, core_busy, scaled, _from, _to, mperf, aperf, tsc, freq_ghz, io_boost, common_comm, load, duration_ms, sample_num, elapsed_time, tsc_ghz): +def store_csv(cpu_int, time_pre_dec, time_post_dec, core_busy, scaled, _from, _to, mperf, aperf, tsc, freq_ghz, io_boost, common_comm, load, duration_ms, sample_num, elapsed_time, tsc_ghz, cpu_mask): """ Store master csv file information """ global graph_data_present @@ -342,11 +342,9 @@ def store_csv(cpu_int, time_pre_dec, time_post_dec, core_busy, scaled, _from, _t graph_data_present = True; -def split_csv(): +def split_csv(current_max_cpu, cpu_mask): """ seperate the all csv file into per CPU csv files. """ - global current_max_cpu - if os.path.exists('cpu.csv'): for index in range(0, current_max_cpu + 1): if cpu_mask[int(index)] != 0: @@ -381,27 +379,25 @@ def clear_trace_file(): print('IO error clearing trace file ') sys.exit(2) -def enable_trace(): +def enable_trace(trace_file): """ Enable trace """ try: - open('/sys/kernel/debug/tracing/events/power/pstate_sample/enable' - , 'w').write("1") + open(trace_file,'w').write("1") except: print('IO error enabling trace ') sys.exit(2) -def disable_trace(): +def disable_trace(trace_file): """ Disable trace """ try: - open('/sys/kernel/debug/tracing/events/power/pstate_sample/enable' - , 'w').write("0") + open(trace_file, 'w').write("0") except: print('IO error disabling trace ') sys.exit(2) -def set_trace_buffer_size(): +def set_trace_buffer_size(memory): """ Set trace buffer size """ try: @@ -421,7 +417,7 @@ def free_trace_buffer(): print('IO error freeing trace buffer ') sys.exit(2) -def read_trace_data(filename): +def read_trace_data(filename, cpu_mask): """ Read and parse trace data """ global current_max_cpu @@ -481,135 +477,137 @@ def read_trace_data(filename): tsc_ghz = Decimal(0) if duration_ms != Decimal(0) : tsc_ghz = Decimal(tsc)/duration_ms/Decimal(1000000) - store_csv(cpu_int, time_pre_dec, time_post_dec, core_busy, scaled, _from, _to, mperf, aperf, tsc, freq_ghz, io_boost, common_comm, load, duration_ms, sample_num, elapsed_time, tsc_ghz) + store_csv(cpu_int, time_pre_dec, time_post_dec, core_busy, scaled, _from, _to, mperf, aperf, tsc, freq_ghz, io_boost, common_comm, load, duration_ms, sample_num, elapsed_time, tsc_ghz, cpu_mask) if cpu_int > current_max_cpu: current_max_cpu = cpu_int # End of for each trace line loop # Now seperate the main overall csv file into per CPU csv files. - split_csv() + split_csv(current_max_cpu, cpu_mask) def signal_handler(signal, frame): print(' SIGINT: Forcing cleanup before exit.') if interval: - disable_trace() + disable_trace(trace_file) clear_trace_file() # Free the memory free_trace_buffer() sys.exit(0) -signal.signal(signal.SIGINT, signal_handler) +if __name__ == "__main__": + trace_file = "/sys/kernel/debug/tracing/events/power/pstate_sample/enable" + signal.signal(signal.SIGINT, signal_handler) -interval = "" -filename = "" -cpu_list = "" -testname = "" -memory = "10240" -graph_data_present = False; + interval = "" + filename = "" + cpu_list = "" + testname = "" + memory = "10240" + graph_data_present = False; -valid1 = False -valid2 = False + valid1 = False + valid2 = False -cpu_mask = zeros((MAX_CPUS,), dtype=int) + cpu_mask = zeros((MAX_CPUS,), dtype=int) -try: - opts, args = getopt.getopt(sys.argv[1:],"ht:i:c:n:m:",["help","trace_file=","interval=","cpu=","name=","memory="]) -except getopt.GetoptError: - print_help() - sys.exit(2) -for opt, arg in opts: - if opt == '-h': - print() + try: + opts, args = getopt.getopt(sys.argv[1:],"ht:i:c:n:m:",["help","trace_file=","interval=","cpu=","name=","memory="]) + except getopt.GetoptError: + print_help('intel_pstate') + sys.exit(2) + for opt, arg in opts: + if opt == '-h': + print_help('intel_pstate') + sys.exit() + elif opt in ("-t", "--trace_file"): + valid1 = True + location = os.path.realpath(os.path.join(os.getcwd(), os.path.dirname(__file__))) + filename = os.path.join(location, arg) + elif opt in ("-i", "--interval"): + valid1 = True + interval = arg + elif opt in ("-c", "--cpu"): + cpu_list = arg + elif opt in ("-n", "--name"): + valid2 = True + testname = arg + elif opt in ("-m", "--memory"): + memory = arg + + if not (valid1 and valid2): + print_help('intel_pstate') sys.exit() - elif opt in ("-t", "--trace_file"): - valid1 = True - location = os.path.realpath(os.path.join(os.getcwd(), os.path.dirname(__file__))) - filename = os.path.join(location, arg) - elif opt in ("-i", "--interval"): - valid1 = True - interval = arg - elif opt in ("-c", "--cpu"): - cpu_list = arg - elif opt in ("-n", "--name"): - valid2 = True - testname = arg - elif opt in ("-m", "--memory"): - memory = arg - -if not (valid1 and valid2): - print_help() - sys.exit() - -if cpu_list: - for p in re.split("[,]", cpu_list): - if int(p) < MAX_CPUS : - cpu_mask[int(p)] = 1 -else: - for i in range (0, MAX_CPUS): - cpu_mask[i] = 1 - -if not os.path.exists('results'): - os.mkdir('results') + + if cpu_list: + for p in re.split("[,]", cpu_list): + if int(p) < MAX_CPUS : + cpu_mask[int(p)] = 1 + else: + for i in range (0, MAX_CPUS): + cpu_mask[i] = 1 + + if not os.path.exists('results'): + os.mkdir('results') + # The regular user needs to own the directory, not root. + fix_ownership('results') + + os.chdir('results') + if os.path.exists(testname): + print('The test name directory already exists. Please provide a unique test name. Test re-run not supported, yet.') + sys.exit() + os.mkdir(testname) # The regular user needs to own the directory, not root. - fix_ownership('results') - -os.chdir('results') -if os.path.exists(testname): - print('The test name directory already exists. Please provide a unique test name. Test re-run not supported, yet.') - sys.exit() -os.mkdir(testname) -# The regular user needs to own the directory, not root. -fix_ownership(testname) -os.chdir(testname) - -# Temporary (or perhaps not) -cur_version = sys.version_info -print('python version (should be >= 2.7):') -print(cur_version) - -# Left as "cleanup" for potential future re-run ability. -cleanup_data_files() - -if interval: - filename = "/sys/kernel/debug/tracing/trace" - clear_trace_file() - set_trace_buffer_size() - enable_trace() - print('Sleeping for ', interval, 'seconds') - time.sleep(int(interval)) - disable_trace() - -current_max_cpu = 0 - -read_trace_data(filename) - -if interval: - clear_trace_file() - # Free the memory - free_trace_buffer() - -if graph_data_present == False: - print('No valid data to plot') - sys.exit(2) - -for cpu_no in range(0, current_max_cpu + 1): - plot_perf_busy_with_sample(cpu_no) - plot_perf_busy(cpu_no) - plot_durations(cpu_no) - plot_loads(cpu_no) - -plot_pstate_cpu_with_sample() -plot_pstate_cpu() -plot_load_cpu() -plot_frequency_cpu() -plot_duration_cpu() -plot_scaled_cpu() -plot_boost_cpu() -plot_ghz_cpu() - -# It is preferrable, but not necessary, that the regular user owns the files, not root. -for root, dirs, files in os.walk('.'): - for f in files: - fix_ownership(f) - -os.chdir('../../') + fix_ownership(testname) + os.chdir(testname) + + # Temporary (or perhaps not) + cur_version = sys.version_info + print('python version (should be >= 2.7):') + print(cur_version) + + # Left as "cleanup" for potential future re-run ability. + cleanup_data_files() + + if interval: + filename = "/sys/kernel/debug/tracing/trace" + clear_trace_file() + set_trace_buffer_size(memory) + enable_trace(trace_file) + print('Sleeping for ', interval, 'seconds') + time.sleep(int(interval)) + disable_trace(trace_file) + + current_max_cpu = 0 + + read_trace_data(filename, cpu_mask) + + if interval: + clear_trace_file() + # Free the memory + free_trace_buffer() + + if graph_data_present == False: + print('No valid data to plot') + sys.exit(2) + + for cpu_no in range(0, current_max_cpu + 1): + plot_perf_busy_with_sample(cpu_no) + plot_perf_busy(cpu_no) + plot_durations(cpu_no) + plot_loads(cpu_no) + + plot_pstate_cpu_with_sample() + plot_pstate_cpu() + plot_load_cpu() + plot_frequency_cpu() + plot_duration_cpu() + plot_scaled_cpu() + plot_boost_cpu() + plot_ghz_cpu() + + # It is preferrable, but not necessary, that the regular user owns the files, not root. + for root, dirs, files in os.walk('.'): + for f in files: + fix_ownership(f) + + os.chdir('../../') diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index 47d3ba895d6d..bc5ae0872fed 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -2323,7 +2323,7 @@ int skx_pkg_cstate_limits[16] = }; int icx_pkg_cstate_limits[16] = - { PCL__0, PCL__2, PCL__6, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, + { PCL__0, PCL__2, PCL__6, PCL__6, PCLRSV, PCLRSV, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV }; |