aboutsummaryrefslogtreecommitdiffstats
path: root/tools/power
diff options
context:
space:
mode:
Diffstat (limited to 'tools/power')
-rw-r--r--tools/power/cpupower/.gitignore7
-rw-r--r--tools/power/cpupower/Makefile3
-rw-r--r--tools/power/cpupower/debug/i386/Makefile5
-rw-r--r--tools/power/cpupower/man/cpupower-monitor.115
-rw-r--r--tools/power/cpupower/utils/helpers/cpuid.c2
-rw-r--r--tools/power/cpupower/utils/helpers/helpers.h18
-rw-r--r--tools/power/cpupower/utils/helpers/sysfs.c19
-rw-r--r--tools/power/cpupower/utils/helpers/topology.c53
-rw-r--r--tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c21
-rw-r--r--tools/power/cpupower/utils/idle_monitor/cpupower-monitor.h17
-rw-r--r--tools/power/cpupower/utils/idle_monitor/snb_idle.c10
-rw-r--r--tools/power/x86/turbostat/Makefile21
-rw-r--r--tools/power/x86/turbostat/turbostat.8103
-rw-r--r--tools/power/x86/turbostat/turbostat.c677
-rw-r--r--tools/power/x86/x86_energy_perf_policy/Makefile6
-rw-r--r--tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c2
16 files changed, 838 insertions, 141 deletions
diff --git a/tools/power/cpupower/.gitignore b/tools/power/cpupower/.gitignore
index 8a83dd2..d42073f 100644
--- a/tools/power/cpupower/.gitignore
+++ b/tools/power/cpupower/.gitignore
@@ -20,3 +20,10 @@ utils/cpufreq-set.o
utils/cpufreq-aperf.o
cpupower
bench/cpufreq-bench
+debug/kernel/Module.symvers
+debug/i386/centrino-decode
+debug/i386/dump_psb
+debug/i386/intel_gsic
+debug/i386/powernow-k8-decode
+debug/x86_64/centrino-decode
+debug/x86_64/powernow-k8-decode
diff --git a/tools/power/cpupower/Makefile b/tools/power/cpupower/Makefile
index cf397bd..d875a74 100644
--- a/tools/power/cpupower/Makefile
+++ b/tools/power/cpupower/Makefile
@@ -253,7 +253,8 @@ clean:
| xargs rm -f
-rm -f $(OUTPUT)cpupower
-rm -f $(OUTPUT)libcpupower.so*
- -rm -rf $(OUTPUT)po/*.{gmo,pot}
+ -rm -rf $(OUTPUT)po/*.gmo
+ -rm -rf $(OUTPUT)po/*.pot
$(MAKE) -C bench O=$(OUTPUT) clean
diff --git a/tools/power/cpupower/debug/i386/Makefile b/tools/power/cpupower/debug/i386/Makefile
index 3ba158f..c05cc0a 100644
--- a/tools/power/cpupower/debug/i386/Makefile
+++ b/tools/power/cpupower/debug/i386/Makefile
@@ -26,7 +26,10 @@ $(OUTPUT)powernow-k8-decode: powernow-k8-decode.c
all: $(OUTPUT)centrino-decode $(OUTPUT)dump_psb $(OUTPUT)intel_gsic $(OUTPUT)powernow-k8-decode
clean:
- rm -rf $(OUTPUT){centrino-decode,dump_psb,intel_gsic,powernow-k8-decode}
+ rm -rf $(OUTPUT)centrino-decode
+ rm -rf $(OUTPUT)dump_psb
+ rm -rf $(OUTPUT)intel_gsic
+ rm -rf $(OUTPUT)powernow-k8-decode
install:
$(INSTALL) -d $(DESTDIR)${bindir}
diff --git a/tools/power/cpupower/man/cpupower-monitor.1 b/tools/power/cpupower/man/cpupower-monitor.1
index 1141c20..e01c35d 100644
--- a/tools/power/cpupower/man/cpupower-monitor.1
+++ b/tools/power/cpupower/man/cpupower-monitor.1
@@ -7,11 +7,11 @@ cpupower\-monitor \- Report processor frequency and idle statistics
.RB "\-l"
.B cpupower monitor
-.RB [ "\-m <mon1>," [ "<mon2>,..." ] ]
+.RB [ -c ] [ "\-m <mon1>," [ "<mon2>,..." ] ]
.RB [ "\-i seconds" ]
.br
.B cpupower monitor
-.RB [ "\-m <mon1>," [ "<mon2>,..." ] ]
+.RB [ -c ][ "\-m <mon1>," [ "<mon2>,..." ] ]
.RB command
.br
.SH DESCRIPTION
@@ -64,6 +64,17 @@ Only display specific monitors. Use the monitor string(s) provided by \-l option
Measure intervall.
.RE
.PP
+\-c
+.RS 4
+Schedule the process on every core before starting and ending measuring.
+This could be needed for the Idle_Stats monitor when no other MSR based
+monitor (has to be run on the core that is measured) is run in parallel.
+This is to wake up the processors from deeper sleep states and let the
+kernel re
+-account its cpuidle (C-state) information before reading the
+cpuidle timings from sysfs.
+.RE
+.PP
command
.RS 4
Measure idle and frequency characteristics of an arbitrary command/workload.
diff --git a/tools/power/cpupower/utils/helpers/cpuid.c b/tools/power/cpupower/utils/helpers/cpuid.c
index 906895d..93b0aa7 100644
--- a/tools/power/cpupower/utils/helpers/cpuid.c
+++ b/tools/power/cpupower/utils/helpers/cpuid.c
@@ -158,6 +158,8 @@ out:
cpu_info->caps |= CPUPOWER_CAP_HAS_TURBO_RATIO;
case 0x2A: /* SNB */
case 0x2D: /* SNB Xeon */
+ case 0x3A: /* IVB */
+ case 0x3E: /* IVB Xeon */
cpu_info->caps |= CPUPOWER_CAP_HAS_TURBO_RATIO;
cpu_info->caps |= CPUPOWER_CAP_IS_SNB;
break;
diff --git a/tools/power/cpupower/utils/helpers/helpers.h b/tools/power/cpupower/utils/helpers/helpers.h
index 2eb584c..aa9e954 100644
--- a/tools/power/cpupower/utils/helpers/helpers.h
+++ b/tools/power/cpupower/utils/helpers/helpers.h
@@ -92,6 +92,14 @@ extern int get_cpu_info(unsigned int cpu, struct cpupower_cpu_info *cpu_info);
extern struct cpupower_cpu_info cpupower_cpu_info;
/* cpuid and cpuinfo helpers **************************/
+struct cpuid_core_info {
+ int pkg;
+ int core;
+ int cpu;
+
+ /* flags */
+ unsigned int is_online:1;
+};
/* CPU topology/hierarchy parsing ******************/
struct cpupower_topology {
@@ -101,18 +109,12 @@ struct cpupower_topology {
unsigned int threads; /* per core */
/* Array gets mallocated with cores entries, holding per core info */
- struct {
- int pkg;
- int core;
- int cpu;
-
- /* flags */
- unsigned int is_online:1;
- } *core_info;
+ struct cpuid_core_info *core_info;
};
extern int get_cpu_topology(struct cpupower_topology *cpu_top);
extern void cpu_topology_release(struct cpupower_topology cpu_top);
+
/* CPU topology/hierarchy parsing ******************/
/* X86 ONLY ****************************************/
diff --git a/tools/power/cpupower/utils/helpers/sysfs.c b/tools/power/cpupower/utils/helpers/sysfs.c
index 96e28c1..38ab916 100644
--- a/tools/power/cpupower/utils/helpers/sysfs.c
+++ b/tools/power/cpupower/utils/helpers/sysfs.c
@@ -37,25 +37,6 @@ unsigned int sysfs_read_file(const char *path, char *buf, size_t buflen)
return (unsigned int) numread;
}
-static unsigned int sysfs_write_file(const char *path,
- const char *value, size_t len)
-{
- int fd;
- ssize_t numwrite;
-
- fd = open(path, O_WRONLY);
- if (fd == -1)
- return 0;
-
- numwrite = write(fd, value, len);
- if (numwrite < 1) {
- close(fd);
- return 0;
- }
- close(fd);
- return (unsigned int) numwrite;
-}
-
/*
* Detect whether a CPU is online
*
diff --git a/tools/power/cpupower/utils/helpers/topology.c b/tools/power/cpupower/utils/helpers/topology.c
index 4eae2c4..c13120a 100644
--- a/tools/power/cpupower/utils/helpers/topology.c
+++ b/tools/power/cpupower/utils/helpers/topology.c
@@ -20,9 +20,8 @@
#include <helpers/sysfs.h>
/* returns -1 on failure, 0 on success */
-int sysfs_topology_read_file(unsigned int cpu, const char *fname)
+static int sysfs_topology_read_file(unsigned int cpu, const char *fname, int *result)
{
- unsigned long value;
char linebuf[MAX_LINE_LEN];
char *endp;
char path[SYSFS_PATH_MAX];
@@ -31,20 +30,12 @@ int sysfs_topology_read_file(unsigned int cpu, const char *fname)
cpu, fname);
if (sysfs_read_file(path, linebuf, MAX_LINE_LEN) == 0)
return -1;
- value = strtoul(linebuf, &endp, 0);
+ *result = strtol(linebuf, &endp, 0);
if (endp == linebuf || errno == ERANGE)
return -1;
- return value;
+ return 0;
}
-struct cpuid_core_info {
- unsigned int pkg;
- unsigned int thread;
- unsigned int cpu;
- /* flags */
- unsigned int is_online:1;
-};
-
static int __compare(const void *t1, const void *t2)
{
struct cpuid_core_info *top1 = (struct cpuid_core_info *)t1;
@@ -53,9 +44,9 @@ static int __compare(const void *t1, const void *t2)
return -1;
else if (top1->pkg > top2->pkg)
return 1;
- else if (top1->thread < top2->thread)
+ else if (top1->core < top2->core)
return -1;
- else if (top1->thread > top2->thread)
+ else if (top1->core > top2->core)
return 1;
else if (top1->cpu < top2->cpu)
return -1;
@@ -73,28 +64,42 @@ static int __compare(const void *t1, const void *t2)
*/
int get_cpu_topology(struct cpupower_topology *cpu_top)
{
- int cpu, cpus = sysconf(_SC_NPROCESSORS_CONF);
+ int cpu, last_pkg, cpus = sysconf(_SC_NPROCESSORS_CONF);
- cpu_top->core_info = malloc(sizeof(struct cpupower_topology) * cpus);
+ cpu_top->core_info = malloc(sizeof(struct cpuid_core_info) * cpus);
if (cpu_top->core_info == NULL)
return -ENOMEM;
cpu_top->pkgs = cpu_top->cores = 0;
for (cpu = 0; cpu < cpus; cpu++) {
cpu_top->core_info[cpu].cpu = cpu;
cpu_top->core_info[cpu].is_online = sysfs_is_cpu_online(cpu);
- cpu_top->core_info[cpu].pkg =
- sysfs_topology_read_file(cpu, "physical_package_id");
- if ((int)cpu_top->core_info[cpu].pkg != -1 &&
- cpu_top->core_info[cpu].pkg > cpu_top->pkgs)
- cpu_top->pkgs = cpu_top->core_info[cpu].pkg;
- cpu_top->core_info[cpu].core =
- sysfs_topology_read_file(cpu, "core_id");
+ if(sysfs_topology_read_file(
+ cpu,
+ "physical_package_id",
+ &(cpu_top->core_info[cpu].pkg)) < 0)
+ return -1;
+ if(sysfs_topology_read_file(
+ cpu,
+ "core_id",
+ &(cpu_top->core_info[cpu].core)) < 0)
+ return -1;
}
- cpu_top->pkgs++;
qsort(cpu_top->core_info, cpus, sizeof(struct cpuid_core_info),
__compare);
+ /* Count the number of distinct pkgs values. This works
+ because the primary sort of the core_info struct was just
+ done by pkg value. */
+ last_pkg = cpu_top->core_info[0].pkg;
+ for(cpu = 1; cpu < cpus; cpu++) {
+ if(cpu_top->core_info[cpu].pkg != last_pkg) {
+ last_pkg = cpu_top->core_info[cpu].pkg;
+ cpu_top->pkgs++;
+ }
+ }
+ cpu_top->pkgs++;
+
/* Intel's cores count is not consecutively numbered, there may
* be a core_id of 3, but none of 2. Assume there always is 0
* Get amount of cores by counting duplicates in a package
diff --git a/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c b/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c
index 0d6571e..c4bae92 100644
--- a/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c
+++ b/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c
@@ -39,6 +39,7 @@ static int mode;
static int interval = 1;
static char *show_monitors_param;
static struct cpupower_topology cpu_top;
+static unsigned int wake_cpus;
/* ToDo: Document this in the manpage */
static char range_abbr[RANGE_MAX] = { 'T', 'C', 'P', 'M', };
@@ -84,7 +85,7 @@ int fill_string_with_spaces(char *s, int n)
void print_header(int topology_depth)
{
int unsigned mon;
- int state, need_len, pr_mon_len;
+ int state, need_len;
cstate_t s;
char buf[128] = "";
int percent_width = 4;
@@ -93,7 +94,6 @@ void print_header(int topology_depth)
printf("%s|", buf);
for (mon = 0; mon < avail_monitors; mon++) {
- pr_mon_len = 0;
need_len = monitors[mon]->hw_states_num * (percent_width + 3)
- 1;
if (mon != 0) {
@@ -315,16 +315,28 @@ int fork_it(char **argv)
int do_interval_measure(int i)
{
unsigned int num;
+ int cpu;
+
+ if (wake_cpus)
+ for (cpu = 0; cpu < cpu_count; cpu++)
+ bind_cpu(cpu);
for (num = 0; num < avail_monitors; num++) {
dprint("HW C-state residency monitor: %s - States: %d\n",
monitors[num]->name, monitors[num]->hw_states_num);
monitors[num]->start();
}
+
sleep(i);
+
+ if (wake_cpus)
+ for (cpu = 0; cpu < cpu_count; cpu++)
+ bind_cpu(cpu);
+
for (num = 0; num < avail_monitors; num++)
monitors[num]->stop();
+
return 0;
}
@@ -333,7 +345,7 @@ static void cmdline(int argc, char *argv[])
int opt;
progname = basename(argv[0]);
- while ((opt = getopt(argc, argv, "+li:m:")) != -1) {
+ while ((opt = getopt(argc, argv, "+lci:m:")) != -1) {
switch (opt) {
case 'l':
if (mode)
@@ -352,6 +364,9 @@ static void cmdline(int argc, char *argv[])
mode = show;
show_monitors_param = optarg;
break;
+ case 'c':
+ wake_cpus = 1;
+ break;
default:
print_wrong_arg_exit();
}
diff --git a/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.h b/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.h
index 9312ee1..9e43f33 100644
--- a/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.h
+++ b/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.h
@@ -65,4 +65,21 @@ extern long long timespec_diff_us(struct timespec start, struct timespec end);
"could be inaccurate\n"), mes, ov); \
}
+
+/* Taken over from x86info project sources -> return 0 on success */
+#include <sched.h>
+#include <sys/types.h>
+#include <unistd.h>
+static inline int bind_cpu(int cpu)
+{
+ cpu_set_t set;
+
+ if (sched_getaffinity(getpid(), sizeof(set), &set) == 0) {
+ CPU_ZERO(&set);
+ CPU_SET(cpu, &set);
+ return sched_setaffinity(getpid(), sizeof(set), &set);
+ }
+ return 1;
+}
+
#endif /* __CPUIDLE_INFO_HW__ */
diff --git a/tools/power/cpupower/utils/idle_monitor/snb_idle.c b/tools/power/cpupower/utils/idle_monitor/snb_idle.c
index a1bc07c..a99b43b 100644
--- a/tools/power/cpupower/utils/idle_monitor/snb_idle.c
+++ b/tools/power/cpupower/utils/idle_monitor/snb_idle.c
@@ -150,9 +150,15 @@ static struct cpuidle_monitor *snb_register(void)
|| cpupower_cpu_info.family != 6)
return NULL;
- if (cpupower_cpu_info.model != 0x2A
- && cpupower_cpu_info.model != 0x2D)
+ switch (cpupower_cpu_info.model) {
+ case 0x2A: /* SNB */
+ case 0x2D: /* SNB Xeon */
+ case 0x3A: /* IVB */
+ case 0x3E: /* IVB Xeon */
+ break;
+ default:
return NULL;
+ }
is_valid = calloc(cpu_count, sizeof(int));
for (num = 0; num < SNB_CSTATE_COUNT; num++) {
diff --git a/tools/power/x86/turbostat/Makefile b/tools/power/x86/turbostat/Makefile
index f856495..f09641d 100644
--- a/tools/power/x86/turbostat/Makefile
+++ b/tools/power/x86/turbostat/Makefile
@@ -1,9 +1,22 @@
+CC = $(CROSS_COMPILE)gcc
+BUILD_OUTPUT := $(PWD)
+PREFIX := /usr
+DESTDIR :=
+
turbostat : turbostat.c
CFLAGS += -Wall
+CFLAGS += -I../../../../arch/x86/include/uapi/
+
+%: %.c
+ @mkdir -p $(BUILD_OUTPUT)
+ $(CC) $(CFLAGS) $< -o $(BUILD_OUTPUT)/$@
+.PHONY : clean
clean :
- rm -f turbostat
+ @rm -f $(BUILD_OUTPUT)/turbostat
-install :
- install turbostat /usr/bin/turbostat
- install turbostat.8 /usr/share/man/man8
+install : turbostat
+ install -d $(DESTDIR)$(PREFIX)/bin
+ install $(BUILD_OUTPUT)/turbostat $(DESTDIR)$(PREFIX)/bin/turbostat
+ install -d $(DESTDIR)$(PREFIX)/share/man/man8
+ install turbostat.8 $(DESTDIR)$(PREFIX)/share/man/man8
diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8
index e4d0690..0d7dc2c 100644
--- a/tools/power/x86/turbostat/turbostat.8
+++ b/tools/power/x86/turbostat/turbostat.8
@@ -11,16 +11,16 @@ turbostat \- Report processor frequency and idle statistics
.RB [ Options ]
.RB [ "\-i interval_sec" ]
.SH DESCRIPTION
-\fBturbostat \fP reports processor topology, frequency
-and idle power state statistics on modern X86 processors.
+\fBturbostat \fP reports processor topology, frequency,
+idle power-state statistics, temperature and power on modern X86 processors.
Either \fBcommand\fP is forked and statistics are printed
upon its completion, or statistics are printed periodically.
\fBturbostat \fP
-requires that the processor
+must be run on root, and
+minimally requires that the processor
supports an "invariant" TSC, plus the APERF and MPERF MSRs.
-\fBturbostat \fP will report idle cpu power state residency
-on processors that additionally support C-state residency counters.
+Additional information is reported depending on hardware counter support.
.SS Options
The \fB-p\fP option limits output to the 1st thread in 1st core of each package.
@@ -57,7 +57,15 @@ Note that multiple CPUs per core indicate support for Intel(R) Hyper-Threading T
\fBGHz\fP average clock rate while the CPU was in c0 state.
\fBTSC\fP average GHz that the TSC ran during the entire interval.
\fB%c1, %c3, %c6, %c7\fP show the percentage residency in hardware core idle states.
+\fBCTMP\fP Degrees Celsius reported by the per-core Digital Thermal Sensor.
+\fBPTMP\fP Degrees Celsius reported by the per-package Package Thermal Monitor.
\fB%pc2, %pc3, %pc6, %pc7\fP percentage residency in hardware package idle states.
+\fBPkg_W\fP Watts consumed by the whole package.
+\fBCor_W\fP Watts consumed by the core part of the package.
+\fBGFX_W\fP Watts consumed by the Graphics part of the package -- available only on client processors.
+\fBRAM_W\fP Watts consumed by the DRAM DIMMS -- available only on server processors.
+\fBPKG_%\fP percent of the interval that RAPL throttling was active on the Package.
+\fBRAM_%\fP percent of the interval that RAPL throttling was active on DRAM.
.fi
.PP
.SH EXAMPLE
@@ -66,50 +74,73 @@ Without any parameters, turbostat prints out counters ever 5 seconds.
for turbostat to fork).
The first row of statistics is a summary for the entire system.
-Note that the summary is a weighted average.
+For residency % columns, the summary is a weighted average.
+For Temperature columns, the summary is the column maximum.
+For Watts columns, the summary is a system total.
Subsequent rows show per-CPU statistics.
.nf
-[root@x980]# ./turbostat
-cor CPU %c0 GHz TSC %c1 %c3 %c6 %pc3 %pc6
- 0.09 1.62 3.38 1.83 0.32 97.76 1.26 83.61
- 0 0 0.15 1.62 3.38 10.23 0.05 89.56 1.26 83.61
- 0 6 0.05 1.62 3.38 10.34
- 1 2 0.03 1.62 3.38 0.07 0.05 99.86
- 1 8 0.03 1.62 3.38 0.06
- 2 4 0.21 1.62 3.38 0.10 1.49 98.21
- 2 10 0.02 1.62 3.38 0.29
- 8 1 0.04 1.62 3.38 0.04 0.08 99.84
- 8 7 0.01 1.62 3.38 0.06
- 9 3 0.53 1.62 3.38 0.10 0.20 99.17
- 9 9 0.02 1.62 3.38 0.60
- 10 5 0.01 1.62 3.38 0.02 0.04 99.92
- 10 11 0.02 1.62 3.38 0.02
+[root@sandy]# ./turbostat
+cor CPU %c0 GHz TSC %c1 %c3 %c6 %c7 CTMP PTMP %pc2 %pc3 %pc6 %pc7 Pkg_W Cor_W GFX_W
+ 0.06 0.80 2.29 0.11 0.00 0.00 99.83 47 40 0.26 0.01 0.44 98.78 3.49 0.12 0.14
+ 0 0 0.07 0.80 2.29 0.07 0.00 0.00 99.86 40 40 0.26 0.01 0.44 98.78 3.49 0.12 0.14
+ 0 4 0.03 0.80 2.29 0.12
+ 1 1 0.04 0.80 2.29 0.25 0.01 0.00 99.71 40
+ 1 5 0.16 0.80 2.29 0.13
+ 2 2 0.05 0.80 2.29 0.06 0.01 0.00 99.88 40
+ 2 6 0.03 0.80 2.29 0.08
+ 3 3 0.05 0.80 2.29 0.08 0.00 0.00 99.87 47
+ 3 7 0.04 0.84 2.29 0.09
.fi
.SH SUMMARY EXAMPLE
The "-s" option prints the column headers just once,
and then the one line system summary for each sample interval.
.nf
-[root@x980]# ./turbostat -s
- %c0 GHz TSC %c1 %c3 %c6 %pc3 %pc6
- 0.23 1.67 3.38 2.00 0.30 97.47 1.07 82.12
- 0.10 1.62 3.38 1.87 2.25 95.77 12.02 72.60
- 0.20 1.64 3.38 1.98 0.11 97.72 0.30 83.36
- 0.11 1.70 3.38 1.86 1.81 96.22 9.71 74.90
+[root@wsm]# turbostat -S
+ %c0 GHz TSC %c1 %c3 %c6 CTMP %pc3 %pc6
+ 1.40 2.81 3.38 10.78 43.47 44.35 42 13.67 2.09
+ 1.34 2.90 3.38 11.48 58.96 28.23 41 19.89 0.15
+ 1.55 2.72 3.38 26.73 37.66 34.07 42 2.53 2.80
+ 1.37 2.83 3.38 16.95 60.05 21.63 42 5.76 0.20
.fi
.SH VERBOSE EXAMPLE
The "-v" option adds verbosity to the output:
.nf
-GenuineIntel 11 CPUID levels; family:model:stepping 0x6:2c:2 (6:44:2)
-12 * 133 = 1600 MHz max efficiency
-25 * 133 = 3333 MHz TSC frequency
-26 * 133 = 3467 MHz max turbo 4 active cores
-26 * 133 = 3467 MHz max turbo 3 active cores
-27 * 133 = 3600 MHz max turbo 2 active cores
-27 * 133 = 3600 MHz max turbo 1 active cores
-
+[root@ivy]# turbostat -v
+turbostat v3.0 November 23, 2012 - Len Brown <lenb@kernel.org>
+CPUID(0): GenuineIntel 13 CPUID levels; family:model:stepping 0x6:3a:9 (6:58:9)
+CPUID(6): APERF, DTS, PTM, EPB
+RAPL: 851 sec. Joule Counter Range
+cpu0: MSR_NHM_PLATFORM_INFO: 0x81010f0012300
+16 * 100 = 1600 MHz max efficiency
+35 * 100 = 3500 MHz TSC frequency
+cpu0: MSR_NHM_SNB_PKG_CST_CFG_CTL: 0x1e008402 (UNdemote-C3, UNdemote-C1, demote-C3, demote-C1, locked: pkg-cstate-limit=2: pc6-noret)
+cpu0: MSR_NHM_TURBO_RATIO_LIMIT: 0x25262727
+37 * 100 = 3700 MHz max turbo 4 active cores
+38 * 100 = 3800 MHz max turbo 3 active cores
+39 * 100 = 3900 MHz max turbo 2 active cores
+39 * 100 = 3900 MHz max turbo 1 active cores
+cpu0: MSR_IA32_ENERGY_PERF_BIAS: 0x00000006 (balanced)
+cpu0: MSR_RAPL_POWER_UNIT: 0x000a1003 (0.125000 Watts, 0.000015 Joules, 0.000977 sec.)
+cpu0: MSR_PKG_POWER_INFO: 0x01e00268 (77 W TDP, RAPL 60 - 0 W, 0.000000 sec.)
+cpu0: MSR_PKG_POWER_LIMIT: 0x830000148268 (UNlocked)
+cpu0: PKG Limit #1: ENabled (77.000000 Watts, 1.000000 sec, clamp DISabled)
+cpu0: PKG Limit #2: ENabled (96.000000 Watts, 0.000977* sec, clamp DISabled)
+cpu0: MSR_PP0_POLICY: 0
+cpu0: MSR_PP0_POWER_LIMIT: 0x00000000 (UNlocked)
+cpu0: Cores Limit: DISabled (0.000000 Watts, 0.000977 sec, clamp DISabled)
+cpu0: MSR_PP1_POLICY: 0
+cpu0: MSR_PP1_POWER_LIMIT: 0x00000000 (UNlocked)
+cpu0: GFX Limit: DISabled (0.000000 Watts, 0.000977 sec, clamp DISabled)
+cpu0: MSR_IA32_TEMPERATURE_TARGET: 0x00691400 (105 C)
+cpu0: MSR_IA32_PACKAGE_THERM_STATUS: 0x884e0000 (27 C)
+cpu0: MSR_IA32_THERM_STATUS: 0x88560000 (19 C +/- 1)
+cpu1: MSR_IA32_THERM_STATUS: 0x88560000 (19 C +/- 1)
+cpu2: MSR_IA32_THERM_STATUS: 0x88540000 (21 C +/- 1)
+cpu3: MSR_IA32_THERM_STATUS: 0x884e0000 (27 C +/- 1)
+ ...
.fi
The \fBmax efficiency\fP frequency, a.k.a. Low Frequency Mode, is the frequency
available at the minimum package voltage. The \fBTSC frequency\fP is the nominal
@@ -142,7 +173,7 @@ cor CPU %c0 GHz TSC %c1 %c3 %c6 %pc3 %pc6
10 5 1.42 3.43 3.38 2.14 30.99 65.44
10 11 0.16 2.88 3.38 3.40
.fi
-Above the cycle soaker drives cpu7 up its 3.6 Ghz turbo limit
+Above the cycle soaker drives cpu7 up its 3.6 GHz turbo limit
while the other processors are generally in various states of idle.
Note that cpu1 and cpu7 are HT siblings within core8.
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index ea095ab..ce6d460 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -20,6 +20,7 @@
*/
#define _GNU_SOURCE
+#include <asm/msr.h>
#include <stdio.h>
#include <unistd.h>
#include <sys/types.h>
@@ -35,28 +36,18 @@
#include <ctype.h>
#include <sched.h>
-#define MSR_NEHALEM_PLATFORM_INFO 0xCE
-#define MSR_NEHALEM_TURBO_RATIO_LIMIT 0x1AD
-#define MSR_IVT_TURBO_RATIO_LIMIT 0x1AE
-#define MSR_APERF 0xE8
-#define MSR_MPERF 0xE7
-#define MSR_PKG_C2_RESIDENCY 0x60D /* SNB only */
-#define MSR_PKG_C3_RESIDENCY 0x3F8
-#define MSR_PKG_C6_RESIDENCY 0x3F9
-#define MSR_PKG_C7_RESIDENCY 0x3FA /* SNB only */
-#define MSR_CORE_C3_RESIDENCY 0x3FC
-#define MSR_CORE_C6_RESIDENCY 0x3FD
-#define MSR_CORE_C7_RESIDENCY 0x3FE /* SNB only */
-
char *proc_stat = "/proc/stat";
unsigned int interval_sec = 5; /* set with -i interval_sec */
unsigned int verbose; /* set with -v */
+unsigned int rapl_verbose; /* set with -R */
+unsigned int thermal_verbose; /* set with -T */
unsigned int summary_only; /* set with -s */
unsigned int skip_c0;
unsigned int skip_c1;
unsigned int do_nhm_cstates;
unsigned int do_snb_cstates;
unsigned int has_aperf;
+unsigned int has_epb;
unsigned int units = 1000000000; /* Ghz etc */
unsigned int genuine_intel;
unsigned int has_invariant_tsc;
@@ -74,6 +65,23 @@ unsigned int show_cpu;
unsigned int show_pkg_only;
unsigned int show_core_only;
char *output_buffer, *outp;
+unsigned int do_rapl;
+unsigned int do_dts;
+unsigned int do_ptm;
+unsigned int tcc_activation_temp;
+unsigned int tcc_activation_temp_override;
+double rapl_power_units, rapl_energy_units, rapl_time_units;
+double rapl_joule_counter_range;
+
+#define RAPL_PKG (1 << 0)
+#define RAPL_CORES (1 << 1)
+#define RAPL_GFX (1 << 2)
+#define RAPL_DRAM (1 << 3)
+#define RAPL_PKG_PERF_STATUS (1 << 4)
+#define RAPL_DRAM_PERF_STATUS (1 << 5)
+#define TJMAX_DEFAULT 100
+
+#define MAX(a, b) ((a) > (b) ? (a) : (b))
int aperf_mperf_unstable;
int backwards_count;
@@ -101,6 +109,7 @@ struct core_data {
unsigned long long c3;
unsigned long long c6;
unsigned long long c7;
+ unsigned int core_temp_c;
unsigned int core_id;
} *core_even, *core_odd;
@@ -110,6 +119,14 @@ struct pkg_data {
unsigned long long pc6;
unsigned long long pc7;
unsigned int package_id;
+ unsigned int energy_pkg; /* MSR_PKG_ENERGY_STATUS */
+ unsigned int energy_dram; /* MSR_DRAM_ENERGY_STATUS */
+ unsigned int energy_cores; /* MSR_PP0_ENERGY_STATUS */
+ unsigned int energy_gfx; /* MSR_PP1_ENERGY_STATUS */
+ unsigned int rapl_pkg_perf_status; /* MSR_PKG_PERF_STATUS */
+ unsigned int rapl_dram_perf_status; /* MSR_DRAM_PERF_STATUS */
+ unsigned int pkg_temp_c;
+
} *package_even, *package_odd;
#define ODD_COUNTERS thread_odd, core_odd, package_odd
@@ -247,6 +264,12 @@ void print_header(void)
outp += sprintf(outp, " %%c6");
if (do_snb_cstates)
outp += sprintf(outp, " %%c7");
+
+ if (do_dts)
+ outp += sprintf(outp, " CTMP");
+ if (do_ptm)
+ outp += sprintf(outp, " PTMP");
+
if (do_snb_cstates)
outp += sprintf(outp, " %%pc2");
if (do_nhm_cstates)
@@ -256,6 +279,19 @@ void print_header(void)
if (do_snb_cstates)
outp += sprintf(outp, " %%pc7");
+ if (do_rapl & RAPL_PKG)
+ outp += sprintf(outp, " Pkg_W");
+ if (do_rapl & RAPL_CORES)
+ outp += sprintf(outp, " Cor_W");
+ if (do_rapl & RAPL_GFX)
+ outp += sprintf(outp, " GFX_W");
+ if (do_rapl & RAPL_DRAM)
+ outp += sprintf(outp, " RAM_W");
+ if (do_rapl & RAPL_PKG_PERF_STATUS)
+ outp += sprintf(outp, " PKG_%%");
+ if (do_rapl & RAPL_DRAM_PERF_STATUS)
+ outp += sprintf(outp, " RAM_%%");
+
outp += sprintf(outp, "\n");
}
@@ -285,6 +321,7 @@ int dump_counters(struct thread_data *t, struct core_data *c,
fprintf(stderr, "c3: %016llX\n", c->c3);
fprintf(stderr, "c6: %016llX\n", c->c6);
fprintf(stderr, "c7: %016llX\n", c->c7);
+ fprintf(stderr, "DTS: %dC\n", c->core_temp_c);
}
if (p) {
@@ -293,6 +330,13 @@ int dump_counters(struct thread_data *t, struct core_data *c,
fprintf(stderr, "pc3: %016llX\n", p->pc3);
fprintf(stderr, "pc6: %016llX\n", p->pc6);
fprintf(stderr, "pc7: %016llX\n", p->pc7);
+ fprintf(stderr, "Joules PKG: %0X\n", p->energy_pkg);
+ fprintf(stderr, "Joules COR: %0X\n", p->energy_cores);
+ fprintf(stderr, "Joules GFX: %0X\n", p->energy_gfx);
+ fprintf(stderr, "Joules RAM: %0X\n", p->energy_dram);
+ fprintf(stderr, "Throttle PKG: %0X\n", p->rapl_pkg_perf_status);
+ fprintf(stderr, "Throttle RAM: %0X\n", p->rapl_dram_perf_status);
+ fprintf(stderr, "PTM: %dC\n", p->pkg_temp_c);
}
return 0;
}
@@ -302,14 +346,21 @@ int dump_counters(struct thread_data *t, struct core_data *c,
* package: "pk" 2 columns %2d
* core: "cor" 3 columns %3d
* CPU: "CPU" 3 columns %3d
+ * Pkg_W: %6.2
+ * Cor_W: %6.2
+ * GFX_W: %5.2
+ * RAM_W: %5.2
* GHz: "GHz" 3 columns %3.2
* TSC: "TSC" 3 columns %3.2
* percentage " %pc3" %6.2
+ * Perf Status percentage: %5.2
+ * "CTMP" 4 columns %4d
*/
int format_counters(struct thread_data *t, struct core_data *c,
struct pkg_data *p)
{
double interval_float;
+ char *fmt5, *fmt6;
/* if showing only 1st thread in core and this isn't one, bail out */
if (show_core_only && !(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
@@ -349,7 +400,6 @@ int format_counters(struct thread_data *t, struct core_data *c,
if (show_cpu)
outp += sprintf(outp, " %3d", t->cpu_id);
}
-
/* %c0 */
if (do_nhm_cstates) {
if (show_pkg || show_core || show_cpu)
@@ -414,10 +464,16 @@ int format_counters(struct thread_data *t, struct core_data *c,
if (do_snb_cstates)
outp += sprintf(outp, " %6.2f", 100.0 * c->c7/t->tsc);
+ if (do_dts)
+ outp += sprintf(outp, " %4d", c->core_temp_c);
+
/* print per-package data only for 1st core in package */
if (!(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
goto done;
+ if (do_ptm)
+ outp += sprintf(outp, " %4d", p->pkg_temp_c);
+
if (do_snb_cstates)
outp += sprintf(outp, " %6.2f", 100.0 * p->pc2/t->tsc);
if (do_nhm_cstates)
@@ -426,6 +482,32 @@ int format_counters(struct thread_data *t, struct core_data *c,
outp += sprintf(outp, " %6.2f", 100.0 * p->pc6/t->tsc);
if (do_snb_cstates)
outp += sprintf(outp, " %6.2f", 100.0 * p->pc7/t->tsc);
+
+ /*
+ * If measurement interval exceeds minimum RAPL Joule Counter range,
+ * indicate that results are suspect by printing "**" in fraction place.
+ */
+ if (interval_float < rapl_joule_counter_range) {
+ fmt5 = " %5.2f";
+ fmt6 = " %6.2f";
+ } else {
+ fmt5 = " %3.0f**";
+ fmt6 = " %4.0f**";
+ }
+
+ if (do_rapl & RAPL_PKG)
+ outp += sprintf(outp, fmt6, p->energy_pkg * rapl_energy_units / interval_float);
+ if (do_rapl & RAPL_CORES)
+ outp += sprintf(outp, fmt6, p->energy_cores * rapl_energy_units / interval_float);
+ if (do_rapl & RAPL_GFX)
+ outp += sprintf(outp, fmt5, p->energy_gfx * rapl_energy_units / interval_float);
+ if (do_rapl & RAPL_DRAM)
+ outp += sprintf(outp, fmt5, p->energy_dram * rapl_energy_units / interval_float);
+ if (do_rapl & RAPL_PKG_PERF_STATUS )
+ outp += sprintf(outp, fmt5, 100.0 * p->rapl_pkg_perf_status * rapl_time_units / interval_float);
+ if (do_rapl & RAPL_DRAM_PERF_STATUS )
+ outp += sprintf(outp, fmt5, 100.0 * p->rapl_dram_perf_status * rapl_time_units / interval_float);
+
done:
outp += sprintf(outp, "\n");
@@ -435,6 +517,7 @@ done:
void flush_stdout()
{
fputs(output_buffer, stdout);
+ fflush(stdout);
outp = output_buffer;
}
void flush_stderr()
@@ -461,6 +544,13 @@ void format_all_counters(struct thread_data *t, struct core_data *c, struct pkg_
for_all_cpus(format_counters, t, c, p);
}
+#define DELTA_WRAP32(new, old) \
+ if (new > old) { \
+ old = new - old; \
+ } else { \
+ old = 0x100000000 + new - old; \
+ }
+
void
delta_package(struct pkg_data *new, struct pkg_data *old)
{
@@ -468,6 +558,14 @@ delta_package(struct pkg_data *new, struct pkg_data *old)
old->pc3 = new->pc3 - old->pc3;
old->pc6 = new->pc6 - old->pc6;
old->pc7 = new->pc7 - old->pc7;
+ old->pkg_temp_c = new->pkg_temp_c;
+
+ DELTA_WRAP32(new->energy_pkg, old->energy_pkg);
+ DELTA_WRAP32(new->energy_cores, old->energy_cores);
+ DELTA_WRAP32(new->energy_gfx, old->energy_gfx);
+ DELTA_WRAP32(new->energy_dram, old->energy_dram);
+ DELTA_WRAP32(new->rapl_pkg_perf_status, old->rapl_pkg_perf_status);
+ DELTA_WRAP32(new->rapl_dram_perf_status, old->rapl_dram_perf_status);
}
void
@@ -476,6 +574,7 @@ delta_core(struct core_data *new, struct core_data *old)
old->c3 = new->c3 - old->c3;
old->c6 = new->c6 - old->c6;
old->c7 = new->c7 - old->c7;
+ old->core_temp_c = new->core_temp_c;
}
/*
@@ -582,11 +681,20 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data
c->c3 = 0;
c->c6 = 0;
c->c7 = 0;
+ c->core_temp_c = 0;
p->pc2 = 0;
p->pc3 = 0;
p->pc6 = 0;
p->pc7 = 0;
+
+ p->energy_pkg = 0;
+ p->energy_dram = 0;
+ p->energy_cores = 0;
+ p->energy_gfx = 0;
+ p->rapl_pkg_perf_status = 0;
+ p->rapl_dram_perf_status = 0;
+ p->pkg_temp_c = 0;
}
int sum_counters(struct thread_data *t, struct core_data *c,
struct pkg_data *p)
@@ -607,6 +715,8 @@ int sum_counters(struct thread_data *t, struct core_data *c,
average.cores.c6 += c->c6;
average.cores.c7 += c->c7;
+ average.cores.core_temp_c = MAX(average.cores.core_temp_c, c->core_temp_c);
+
/* sum per-pkg values only for 1st core in pkg */
if (!(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
return 0;
@@ -616,6 +726,15 @@ int sum_counters(struct thread_data *t, struct core_data *c,
average.packages.pc6 += p->pc6;
average.packages.pc7 += p->pc7;
+ average.packages.energy_pkg += p->energy_pkg;
+ average.packages.energy_dram += p->energy_dram;
+ average.packages.energy_cores += p->energy_cores;
+ average.packages.energy_gfx += p->energy_gfx;
+
+ average.packages.pkg_temp_c = MAX(average.packages.pkg_temp_c, p->pkg_temp_c);
+
+ average.packages.rapl_pkg_perf_status += p->rapl_pkg_perf_status;
+ average.packages.rapl_dram_perf_status += p->rapl_dram_perf_status;
return 0;
}
/*
@@ -667,23 +786,26 @@ static unsigned long long rdtsc(void)
int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
{
int cpu = t->cpu_id;
+ unsigned long long msr;
- if (cpu_migrate(cpu))
+ if (cpu_migrate(cpu)) {
+ fprintf(stderr, "Could not migrate to CPU %d\n", cpu);
return -1;
+ }
t->tsc = rdtsc(); /* we are running on local CPU of interest */
if (has_aperf) {
- if (get_msr(cpu, MSR_APERF, &t->aperf))
+ if (get_msr(cpu, MSR_IA32_APERF, &t->aperf))
return -3;
- if (get_msr(cpu, MSR_MPERF, &t->mperf))
+ if (get_msr(cpu, MSR_IA32_MPERF, &t->mperf))
return -4;
}
if (extra_delta_offset32) {
- if (get_msr(cpu, extra_delta_offset32, &t->extra_delta32))
+ if (get_msr(cpu, extra_delta_offset32, &msr))
return -5;
- t->extra_delta32 &= 0xFFFFFFFF;
+ t->extra_delta32 = msr & 0xFFFFFFFF;
}
if (extra_delta_offset64)
@@ -691,9 +813,9 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
return -5;
if (extra_msr_offset32) {
- if (get_msr(cpu, extra_msr_offset32, &t->extra_msr32))
+ if (get_msr(cpu, extra_msr_offset32, &msr))
return -5;
- t->extra_msr32 &= 0xFFFFFFFF;
+ t->extra_msr32 = msr & 0xFFFFFFFF;
}
if (extra_msr_offset64)
@@ -715,6 +837,13 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
if (get_msr(cpu, MSR_CORE_C7_RESIDENCY, &c->c7))
return -8;
+ if (do_dts) {
+ if (get_msr(cpu, MSR_IA32_THERM_STATUS, &msr))
+ return -9;
+ c->core_temp_c = tcc_activation_temp - ((msr >> 16) & 0x7F);
+ }
+
+
/* collect package counters only for 1st core in package */
if (!(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
return 0;
@@ -731,6 +860,41 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
if (get_msr(cpu, MSR_PKG_C7_RESIDENCY, &p->pc7))
return -12;
}
+ if (do_rapl & RAPL_PKG) {
+ if (get_msr(cpu, MSR_PKG_ENERGY_STATUS, &msr))
+ return -13;
+ p->energy_pkg = msr & 0xFFFFFFFF;
+ }
+ if (do_rapl & RAPL_CORES) {
+ if (get_msr(cpu, MSR_PP0_ENERGY_STATUS, &msr))
+ return -14;
+ p->energy_cores = msr & 0xFFFFFFFF;
+ }
+ if (do_rapl & RAPL_DRAM) {
+ if (get_msr(cpu, MSR_DRAM_ENERGY_STATUS, &msr))
+ return -15;
+ p->energy_dram = msr & 0xFFFFFFFF;
+ }
+ if (do_rapl & RAPL_GFX) {
+ if (get_msr(cpu, MSR_PP1_ENERGY_STATUS, &msr))
+ return -16;
+ p->energy_gfx = msr & 0xFFFFFFFF;
+ }
+ if (do_rapl & RAPL_PKG_PERF_STATUS) {
+ if (get_msr(cpu, MSR_PKG_PERF_STATUS, &msr))
+ return -16;
+ p->rapl_pkg_perf_status = msr & 0xFFFFFFFF;
+ }
+ if (do_rapl & RAPL_DRAM_PERF_STATUS) {
+ if (get_msr(cpu, MSR_DRAM_PERF_STATUS, &msr))
+ return -16;
+ p->rapl_dram_perf_status = msr & 0xFFFFFFFF;
+ }
+ if (do_ptm) {
+ if (get_msr(cpu, MSR_IA32_PACKAGE_THERM_STATUS, &msr))
+ return -17;
+ p->pkg_temp_c = tcc_activation_temp - ((msr >> 16) & 0x7F);
+ }
return 0;
}
@@ -742,10 +906,10 @@ void print_verbose_header(void)
if (!do_nehalem_platform_info)
return;
- get_msr(0, MSR_NEHALEM_PLATFORM_INFO, &msr);
+ get_msr(0, MSR_NHM_PLATFORM_INFO, &msr);
- if (verbose > 1)
- fprintf(stderr, "MSR_NEHALEM_PLATFORM_INFO: 0x%llx\n", msr);
+ if (verbose)
+ fprintf(stderr, "cpu0: MSR_NHM_PLATFORM_INFO: 0x%08llx\n", msr);
ratio = (msr >> 40) & 0xFF;
fprintf(stderr, "%d * %.0f = %.0f MHz max efficiency\n",
@@ -760,8 +924,8 @@ void print_verbose_header(void)
get_msr(0, MSR_IVT_TURBO_RATIO_LIMIT, &msr);
- if (verbose > 1)
- fprintf(stderr, "MSR_IVT_TURBO_RATIO_LIMIT: 0x%llx\n", msr);
+ if (verbose)
+ fprintf(stderr, "cpu0: MSR_IVT_TURBO_RATIO_LIMIT: 0x%08llx\n", msr);
ratio = (msr >> 56) & 0xFF;
if (ratio)
@@ -804,14 +968,56 @@ void print_verbose_header(void)
ratio, bclk, ratio * bclk);
print_nhm_turbo_ratio_limits:
+ get_msr(0, MSR_NHM_SNB_PKG_CST_CFG_CTL, &msr);
+
+#define SNB_C1_AUTO_UNDEMOTE (1UL << 27)
+#define SNB_C3_AUTO_UNDEMOTE (1UL << 28)
+
+ fprintf(stderr, "cpu0: MSR_NHM_SNB_PKG_CST_CFG_CTL: 0x%08llx", msr);
+
+ fprintf(stderr, " (%s%s%s%s%slocked: pkg-cstate-limit=%d: ",
+ (msr & SNB_C3_AUTO_UNDEMOTE) ? "UNdemote-C3, " : "",
+ (msr & SNB_C1_AUTO_UNDEMOTE) ? "UNdemote-C1, " : "",
+ (msr & NHM_C3_AUTO_DEMOTE) ? "demote-C3, " : "",
+ (msr & NHM_C1_AUTO_DEMOTE) ? "demote-C1, " : "",
+ (msr & (1 << 15)) ? "" : "UN",
+ (unsigned int)msr & 7);
+
+
+ switch(msr & 0x7) {
+ case 0:
+ fprintf(stderr, "pc0");
+ break;
+ case 1:
+ fprintf(stderr, do_snb_cstates ? "pc2" : "pc0");
+ break;
+ case 2:
+ fprintf(stderr, do_snb_cstates ? "pc6-noret" : "pc3");
+ break;
+ case 3:
+ fprintf(stderr, "pc6");
+ break;
+ case 4:
+ fprintf(stderr, "pc7");
+ break;
+ case 5:
+ fprintf(stderr, do_snb_cstates ? "pc7s" : "invalid");
+ break;
+ case 7:
+ fprintf(stderr, "unlimited");
+ break;
+ default:
+ fprintf(stderr, "invalid");
+ }
+ fprintf(stderr, ")\n");
if (!do_nehalem_turbo_ratio_limit)
return;
- get_msr(0, MSR_NEHALEM_TURBO_RATIO_LIMIT, &msr);
+ get_msr(0, MSR_NHM_TURBO_RATIO_LIMIT, &msr);
- if (verbose > 1)
- fprintf(stderr, "MSR_NEHALEM_TURBO_RATIO_LIMIT: 0x%llx\n", msr);
+ if (verbose)
+ fprintf(stderr, "cpu0: MSR_NHM_TURBO_RATIO_LIMIT: 0x%08llx\n", msr);
ratio = (msr >> 56) & 0xFF;
if (ratio)
@@ -1100,15 +1306,22 @@ int mark_cpu_present(int cpu)
void turbostat_loop()
{
int retval;
+ int restarted = 0;
restart:
+ restarted++;
+
retval = for_all_cpus(get_counters, EVEN_COUNTERS);
if (retval < -1) {
exit(retval);
} else if (retval == -1) {
+ if (restarted > 1) {
+ exit(retval);
+ }
re_initialize();
goto restart;
}
+ restarted = 0;
gettimeofday(&tv_even, (struct timezone *)NULL);
while (1) {
@@ -1207,6 +1420,299 @@ int has_ivt_turbo_ratio_limit(unsigned int family, unsigned int model)
}
}
+/*
+ * print_epb()
+ * Decode the ENERGY_PERF_BIAS MSR
+ */
+int print_epb(struct thread_data *t, struct core_data *c, struct pkg_data *p)
+{
+ unsigned long long msr;
+ char *epb_string;
+ int cpu;
+
+ if (!has_epb)
+ return 0;
+
+ cpu = t->cpu_id;
+
+ /* EPB is per-package */
+ if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE) || !(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
+ return 0;
+
+ if (cpu_migrate(cpu)) {
+ fprintf(stderr, "Could not migrate to CPU %d\n", cpu);
+ return -1;
+ }
+
+ if (get_msr(cpu, MSR_IA32_ENERGY_PERF_BIAS, &msr))
+ return 0;
+
+ switch (msr & 0x7) {
+ case ENERGY_PERF_BIAS_PERFORMANCE:
+ epb_string = "performance";
+ break;
+ case ENERGY_PERF_BIAS_NORMAL:
+ epb_string = "balanced";
+ break;
+ case ENERGY_PERF_BIAS_POWERSAVE:
+ epb_string = "powersave";
+ break;
+ default:
+ epb_string = "custom";
+ break;
+ }
+ fprintf(stderr, "cpu%d: MSR_IA32_ENERGY_PERF_BIAS: 0x%08llx (%s)\n", cpu, msr, epb_string);
+
+ return 0;
+}
+
+#define RAPL_POWER_GRANULARITY 0x7FFF /* 15 bit power granularity */
+#define RAPL_TIME_GRANULARITY 0x3F /* 6 bit time granularity */
+
+/*
+ * rapl_probe()
+ *
+ * sets do_rapl
+ */
+void rapl_probe(unsigned int family, unsigned int model)
+{
+ unsigned long long msr;
+ double tdp;
+
+ if (!genuine_intel)
+ return;
+
+ if (family != 6)
+ return;
+
+ switch (model) {
+ case 0x2A:
+ case 0x3A:
+ do_rapl = RAPL_PKG | RAPL_CORES | RAPL_GFX;
+ break;
+ case 0x2D:
+ case 0x3E:
+ do_rapl = RAPL_PKG | RAPL_CORES | RAPL_DRAM | RAPL_PKG_PERF_STATUS | RAPL_DRAM_PERF_STATUS;
+ break;
+ default:
+ return;
+ }
+
+ /* units on package 0, verify later other packages match */
+ if (get_msr(0, MSR_RAPL_POWER_UNIT, &msr))
+ return;
+
+ rapl_power_units = 1.0 / (1 << (msr & 0xF));
+ rapl_energy_units = 1.0 / (1 << (msr >> 8 & 0x1F));
+ rapl_time_units = 1.0 / (1 << (msr >> 16 & 0xF));
+
+ /* get TDP to determine energy counter range */
+ if (get_msr(0, MSR_PKG_POWER_INFO, &msr))
+ return;
+
+ tdp = ((msr >> 0) & RAPL_POWER_GRANULARITY) * rapl_power_units;
+
+ rapl_joule_counter_range = 0xFFFFFFFF * rapl_energy_units / tdp;
+
+ if (verbose)
+ fprintf(stderr, "RAPL: %.0f sec. Joule Counter Range\n", rapl_joule_counter_range);
+
+ return;
+}
+
+int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p)
+{
+ unsigned long long msr;
+ unsigned int dts;
+ int cpu;
+
+ if (!(do_dts || do_ptm))
+ return 0;
+
+ cpu = t->cpu_id;
+
+ /* DTS is per-core, no need to print for each thread */
+ if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
+ return 0;
+
+ if (cpu_migrate(cpu)) {
+ fprintf(stderr, "Could not migrate to CPU %d\n", cpu);
+ return -1;
+ }
+
+ if (do_ptm && (t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE)) {
+ if (get_msr(cpu, MSR_IA32_PACKAGE_THERM_STATUS, &msr))
+ return 0;
+
+ dts = (msr >> 16) & 0x7F;
+ fprintf(stderr, "cpu%d: MSR_IA32_PACKAGE_THERM_STATUS: 0x%08llx (%d C)\n",
+ cpu, msr, tcc_activation_temp - dts);
+
+#ifdef THERM_DEBUG
+ if (get_msr(cpu, MSR_IA32_PACKAGE_THERM_INTERRUPT, &msr))
+ return 0;
+
+ dts = (msr >> 16) & 0x7F;
+ dts2 = (msr >> 8) & 0x7F;
+ fprintf(stderr, "cpu%d: MSR_IA32_PACKAGE_THERM_INTERRUPT: 0x%08llx (%d C, %d C)\n",
+ cpu, msr, tcc_activation_temp - dts, tcc_activation_temp - dts2);
+#endif
+ }
+
+
+ if (do_dts) {
+ unsigned int resolution;
+
+ if (get_msr(cpu, MSR_IA32_THERM_STATUS, &msr))
+ return 0;
+
+ dts = (msr >> 16) & 0x7F;
+ resolution = (msr >> 27) & 0xF;
+ fprintf(stderr, "cpu%d: MSR_IA32_THERM_STATUS: 0x%08llx (%d C +/- %d)\n",
+ cpu, msr, tcc_activation_temp - dts, resolution);
+
+#ifdef THERM_DEBUG
+ if (get_msr(cpu, MSR_IA32_THERM_INTERRUPT, &msr))
+ return 0;
+
+ dts = (msr >> 16) & 0x7F;
+ dts2 = (msr >> 8) & 0x7F;
+ fprintf(stderr, "cpu%d: MSR_IA32_THERM_INTERRUPT: 0x%08llx (%d C, %d C)\n",
+ cpu, msr, tcc_activation_temp - dts, tcc_activation_temp - dts2);
+#endif
+ }
+
+ return 0;
+}
+
+void print_power_limit_msr(int cpu, unsigned long long msr, char *label)
+{
+ fprintf(stderr, "cpu%d: %s: %sabled (%f Watts, %f sec, clamp %sabled)\n",
+ cpu, label,
+ ((msr >> 15) & 1) ? "EN" : "DIS",
+ ((msr >> 0) & 0x7FFF) * rapl_power_units,
+ (1.0 + (((msr >> 22) & 0x3)/4.0)) * (1 << ((msr >> 17) & 0x1F)) * rapl_time_units,
+ (((msr >> 16) & 1) ? "EN" : "DIS"));
+
+ return;
+}
+
+int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
+{
+ unsigned long long msr;
+ int cpu;
+ double local_rapl_power_units, local_rapl_energy_units, local_rapl_time_units;
+
+ if (!do_rapl)
+ return 0;
+
+ /* RAPL counters are per package, so print only for 1st thread/package */
+ if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE) || !(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
+ return 0;
+
+ cpu = t->cpu_id;
+ if (cpu_migrate(cpu)) {
+ fprintf(stderr, "Could not migrate to CPU %d\n", cpu);
+ return -1;
+ }
+
+ if (get_msr(cpu, MSR_RAPL_POWER_UNIT, &msr))
+ return -1;
+
+ local_rapl_power_units = 1.0 / (1 << (msr & 0xF));
+ local_rapl_energy_units = 1.0 / (1 << (msr >> 8 & 0x1F));
+ local_rapl_time_units = 1.0 / (1 << (msr >> 16 & 0xF));
+
+ if (local_rapl_power_units != rapl_power_units)
+ fprintf(stderr, "cpu%d, ERROR: Power units mis-match\n", cpu);
+ if (local_rapl_energy_units != rapl_energy_units)
+ fprintf(stderr, "cpu%d, ERROR: Energy units mis-match\n", cpu);
+ if (local_rapl_time_units != rapl_time_units)
+ fprintf(stderr, "cpu%d, ERROR: Time units mis-match\n", cpu);
+
+ if (verbose) {
+ fprintf(stderr, "cpu%d: MSR_RAPL_POWER_UNIT: 0x%08llx "
+ "(%f Watts, %f Joules, %f sec.)\n", cpu, msr,
+ local_rapl_power_units, local_rapl_energy_units, local_rapl_time_units);
+ }
+ if (do_rapl & RAPL_PKG) {
+ if (get_msr(cpu, MSR_PKG_POWER_INFO, &msr))
+ return -5;
+
+
+ fprintf(stderr, "cpu%d: MSR_PKG_POWER_INFO: 0x%08llx (%.0f W TDP, RAPL %.0f - %.0f W, %f sec.)\n",
+ cpu, msr,
+ ((msr >> 0) & RAPL_POWER_GRANULARITY) * rapl_power_units,
+ ((msr >> 16) & RAPL_POWER_GRANULARITY) * rapl_power_units,
+ ((msr >> 32) & RAPL_POWER_GRANULARITY) * rapl_power_units,
+ ((msr >> 48) & RAPL_TIME_GRANULARITY) * rapl_time_units);
+
+ if (get_msr(cpu, MSR_PKG_POWER_LIMIT, &msr))
+ return -9;
+
+ fprintf(stderr, "cpu%d: MSR_PKG_POWER_LIMIT: 0x%08llx (%slocked)\n",
+ cpu, msr, (msr >> 63) & 1 ? "": "UN");
+
+ print_power_limit_msr(cpu, msr, "PKG Limit #1");
+ fprintf(stderr, "cpu%d: PKG Limit #2: %sabled (%f Watts, %f* sec, clamp %sabled)\n",
+ cpu,
+ ((msr >> 47) & 1) ? "EN" : "DIS",
+ ((msr >> 32) & 0x7FFF) * rapl_power_units,
+ (1.0 + (((msr >> 54) & 0x3)/4.0)) * (1 << ((msr >> 49) & 0x1F)) * rapl_time_units,
+ ((msr >> 48) & 1) ? "EN" : "DIS");
+ }
+
+ if (do_rapl & RAPL_DRAM) {
+ if (get_msr(cpu, MSR_DRAM_POWER_INFO, &msr))
+ return -6;
+
+
+ fprintf(stderr, "cpu%d: MSR_DRAM_POWER_INFO,: 0x%08llx (%.0f W TDP, RAPL %.0f - %.0f W, %f sec.)\n",
+ cpu, msr,
+ ((msr >> 0) & RAPL_POWER_GRANULARITY) * rapl_power_units,
+ ((msr >> 16) & RAPL_POWER_GRANULARITY) * rapl_power_units,
+ ((msr >> 32) & RAPL_POWER_GRANULARITY) * rapl_power_units,
+ ((msr >> 48) & RAPL_TIME_GRANULARITY) * rapl_time_units);
+
+
+ if (get_msr(cpu, MSR_DRAM_POWER_LIMIT, &msr))
+ return -9;
+ fprintf(stderr, "cpu%d: MSR_DRAM_POWER_LIMIT: 0x%08llx (%slocked)\n",
+ cpu, msr, (msr >> 31) & 1 ? "": "UN");
+
+ print_power_limit_msr(cpu, msr, "DRAM Limit");
+ }
+ if (do_rapl & RAPL_CORES) {
+ if (verbose) {
+ if (get_msr(cpu, MSR_PP0_POLICY, &msr))
+ return -7;
+
+ fprintf(stderr, "cpu%d: MSR_PP0_POLICY: %lld\n", cpu, msr & 0xF);
+
+ if (get_msr(cpu, MSR_PP0_POWER_LIMIT, &msr))
+ return -9;
+ fprintf(stderr, "cpu%d: MSR_PP0_POWER_LIMIT: 0x%08llx (%slocked)\n",
+ cpu, msr, (msr >> 31) & 1 ? "": "UN");
+ print_power_limit_msr(cpu, msr, "Cores Limit");
+ }
+ }
+ if (do_rapl & RAPL_GFX) {
+ if (verbose) {
+ if (get_msr(cpu, MSR_PP1_POLICY, &msr))
+ return -8;
+
+ fprintf(stderr, "cpu%d: MSR_PP1_POLICY: %lld\n", cpu, msr & 0xF);
+
+ if (get_msr(cpu, MSR_PP1_POWER_LIMIT, &msr))
+ return -9;
+ fprintf(stderr, "cpu%d: MSR_PP1_POWER_LIMIT: 0x%08llx (%slocked)\n",
+ cpu, msr, (msr >> 31) & 1 ? "": "UN");
+ print_power_limit_msr(cpu, msr, "GFX Limit");
+ }
+ }
+ return 0;
+}
+
int is_snb(unsigned int family, unsigned int model)
{
@@ -1231,6 +1737,72 @@ double discover_bclk(unsigned int family, unsigned int model)
return 133.33;
}
+/*
+ * MSR_IA32_TEMPERATURE_TARGET indicates the temperature where
+ * the Thermal Control Circuit (TCC) activates.
+ * This is usually equal to tjMax.
+ *
+ * Older processors do not have this MSR, so there we guess,
+ * but also allow cmdline over-ride with -T.
+ *
+ * Several MSR temperature values are in units of degrees-C
+ * below this value, including the Digital Thermal Sensor (DTS),
+ * Package Thermal Management Sensor (PTM), and thermal event thresholds.
+ */
+int set_temperature_target(struct thread_data *t, struct core_data *c, struct pkg_data *p)
+{
+ unsigned long long msr;
+ unsigned int target_c_local;
+ int cpu;
+
+ /* tcc_activation_temp is used only for dts or ptm */
+ if (!(do_dts || do_ptm))
+ return 0;
+
+ /* this is a per-package concept */
+ if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE) || !(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
+ return 0;
+
+ cpu = t->cpu_id;
+ if (cpu_migrate(cpu)) {
+ fprintf(stderr, "Could not migrate to CPU %d\n", cpu);
+ return -1;
+ }
+
+ if (tcc_activation_temp_override != 0) {
+ tcc_activation_temp = tcc_activation_temp_override;
+ fprintf(stderr, "cpu%d: Using cmdline TCC Target (%d C)\n",
+ cpu, tcc_activation_temp);
+ return 0;
+ }
+
+ /* Temperature Target MSR is Nehalem and newer only */
+ if (!do_nehalem_platform_info)
+ goto guess;
+
+ if (get_msr(0, MSR_IA32_TEMPERATURE_TARGET, &msr))
+ goto guess;
+
+ target_c_local = (msr >> 16) & 0x7F;
+
+ if (verbose)
+ fprintf(stderr, "cpu%d: MSR_IA32_TEMPERATURE_TARGET: 0x%08llx (%d C)\n",
+ cpu, msr, target_c_local);
+
+ if (target_c_local < 85 || target_c_local > 120)
+ goto guess;
+
+ tcc_activation_temp = target_c_local;
+
+ return 0;
+
+guess:
+ tcc_activation_temp = TJMAX_DEFAULT;
+ fprintf(stderr, "cpu%d: Guessing tjMax %d C, Please use -T to specify\n",
+ cpu, tcc_activation_temp);
+
+ return 0;
+}
void check_cpuid()
{
unsigned int eax, ebx, ecx, edx, max_level;
@@ -1244,7 +1816,7 @@ void check_cpuid()
genuine_intel = 1;
if (verbose)
- fprintf(stderr, "%.4s%.4s%.4s ",
+ fprintf(stderr, "CPUID(0): %.4s%.4s%.4s ",
(char *)&ebx, (char *)&edx, (char *)&ecx);
asm("cpuid" : "=a" (fms), "=c" (ecx), "=d" (edx) : "a" (1) : "ebx");
@@ -1295,10 +1867,19 @@ void check_cpuid()
asm("cpuid" : "=a" (eax), "=b" (ebx), "=c" (ecx), "=d" (edx) : "a" (0x6));
has_aperf = ecx & (1 << 0);
- if (!has_aperf) {
- fprintf(stderr, "No APERF MSR\n");
- exit(1);
- }
+ do_dts = eax & (1 << 0);
+ do_ptm = eax & (1 << 6);
+ has_epb = ecx & (1 << 3);
+
+ if (verbose)
+ fprintf(stderr, "CPUID(6): %s%s%s%s\n",
+ has_aperf ? "APERF" : "No APERF!",
+ do_dts ? ", DTS" : "",
+ do_ptm ? ", PTM": "",
+ has_epb ? ", EPB": "");
+
+ if (!has_aperf)
+ exit(-1);
do_nehalem_platform_info = genuine_intel && has_invariant_tsc;
do_nhm_cstates = genuine_intel; /* all Intel w/ non-stop TSC have NHM counters */
@@ -1307,12 +1888,15 @@ void check_cpuid()
do_nehalem_turbo_ratio_limit = has_nehalem_turbo_ratio_limit(family, model);
do_ivt_turbo_ratio_limit = has_ivt_turbo_ratio_limit(family, model);
+ rapl_probe(family, model);
+
+ return;
}
void usage()
{
- fprintf(stderr, "%s: [-v][-p|-P|-S][-c MSR# | -s]][-C MSR#][-m MSR#][-M MSR#][-i interval_sec | command ...]\n",
+ fprintf(stderr, "%s: [-v][-R][-T][-p|-P|-S][-c MSR# | -s]][-C MSR#][-m MSR#][-M MSR#][-i interval_sec | command ...]\n",
progname);
exit(1);
}
@@ -1548,6 +2132,17 @@ void turbostat_init()
if (verbose)
print_verbose_header();
+
+ if (verbose)
+ for_all_cpus(print_epb, ODD_COUNTERS);
+
+ if (verbose)
+ for_all_cpus(print_rapl, ODD_COUNTERS);
+
+ for_all_cpus(set_temperature_target, ODD_COUNTERS);
+
+ if (verbose)
+ for_all_cpus(print_thermal, ODD_COUNTERS);
}
int fork_it(char **argv)
@@ -1604,7 +2199,7 @@ void cmdline(int argc, char **argv)
progname = argv[0];
- while ((opt = getopt(argc, argv, "+pPSvi:sc:sC:m:M:")) != -1) {
+ while ((opt = getopt(argc, argv, "+pPSvi:sc:sC:m:M:RT:")) != -1) {
switch (opt) {
case 'p':
show_core_only++;
@@ -1636,6 +2231,12 @@ void cmdline(int argc, char **argv)
case 'M':
sscanf(optarg, "%x", &extra_msr_offset64);
break;
+ case 'R':
+ rapl_verbose++;
+ break;
+ case 'T':
+ tcc_activation_temp_override = atoi(optarg);
+ break;
default:
usage();
}
@@ -1646,8 +2247,8 @@ int main(int argc, char **argv)
{
cmdline(argc, argv);
- if (verbose > 1)
- fprintf(stderr, "turbostat v2.1 October 6, 2012"
+ if (verbose)
+ fprintf(stderr, "turbostat v3.0 November 23, 2012"
" - Len Brown <lenb@kernel.org>\n");
turbostat_init();
diff --git a/tools/power/x86/x86_energy_perf_policy/Makefile b/tools/power/x86/x86_energy_perf_policy/Makefile
index f458237..971c9ff 100644
--- a/tools/power/x86/x86_energy_perf_policy/Makefile
+++ b/tools/power/x86/x86_energy_perf_policy/Makefile
@@ -1,8 +1,10 @@
+DESTDIR ?=
+
x86_energy_perf_policy : x86_energy_perf_policy.c
clean :
rm -f x86_energy_perf_policy
install :
- install x86_energy_perf_policy /usr/bin/
- install x86_energy_perf_policy.8 /usr/share/man/man8/
+ install x86_energy_perf_policy ${DESTDIR}/usr/bin/
+ install x86_energy_perf_policy.8 ${DESTDIR}/usr/share/man/man8/
diff --git a/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c b/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c
index 33c5c7e..40b3e54 100644
--- a/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c
+++ b/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c
@@ -289,7 +289,7 @@ void for_every_cpu(void (func)(int))
"cpu%u %*d %*d %*d %*d %*d %*d %*d %*d %*d %*d\n",
&cpu);
if (retval != 1)
- return;
+ break;
func(cpu);
}
generated by cgit v1.1 at 2025-01-15 20:54:17 +0000