Merge branch 'pm-tools'

Merge power management utilities changes for 5.18-rc1:

 - Add tracer tool for the amd-pstate driver (Jinzhou Su).

 - Fix PC6 displaying in turbostat on some systems (Artem Bityutskiy).

 - Add AMD P-State support to the cpupower utility (Huang Rui).

* pm-tools:
  Documentation: amd-pstate: add tracer tool introduction
  tools/power/x86/amd_pstate_tracer: Add tracer tool for AMD P-state
  tools/power/x86/intel_pstate_tracer: make tracer as a module
  cpufreq: amd-pstate: Add more tracepoint for AMD P-State module
  turbostat: fix PC6 displaying on some systems
  cpupower: Add "perf" option to print AMD P-State information
  cpupower: Add function to print AMD P-State performance capabilities
  cpupower: Move print_speed function into misc helper
  cpupower: Enable boost state support for AMD P-State module
  cpupower: Add AMD P-State sysfs definition and access helper
  cpupower: Introduce ACPI CPPC library
  cpupower: Add the function to get the sysfs value from specific table
  cpupower: Initial AMD P-State capability
  cpupower: Add the function to check AMD P-State enabled
  cpupower: Add AMD P-State capability flag
  tools/power/cpupower/{ToDo => TODO}: Rename the todo file
  tools: cpupower: fix typo in cpupower-idle-set(1) manpage

Author: rafaeljw

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
 ===========
 

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>

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"

drivers/cpufreq/amd-pstate.c

@@ -65,6 +65,18 @@ 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
@@ -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;

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

tools/power/cpupower/ToDo tools/power/cpupower/TODOtools/power/cpupower/ToDo renamed to tools/power/cpupower/TODO

@@ -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;
+}

tools/power/cpupower/lib/acpi_cppc.c

@@ -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 */

tools/power/cpupower/lib/acpi_cppc.h

@@ -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;

tools/power/cpupower/lib/cpufreq.c

@@ -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