Some processors use the Interrupt Response Time Limit (IRTL) MSR value
to describe the maximum IRQ response time latency for deep
package C-states. (Though others have the register, but do not use it)
Lets print it out to give insight into the cases where it is used.
IRTL begain in SNB, with PC3/PC6/PC7, and HSW added PC8/PC9/PC10.
Signed-off-by: Len Brown <len.brown@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
The CPUID.SGX bit was printed, even if --debug was used
Signed-off-by: Len Brown <len.brown@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Pull turbostat updates for 4.6 from Len Brown.
* 'turbostat' of git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux:
tools/power turbostat: bugfix: TDP MSRs print bits fixing
tools/power turbostat: correct output for MSR_NHM_SNB_PKG_CST_CFG_CTL dump
tools/power turbostat: call __cpuid() instead of __get_cpuid()
tools/power turbostat: indicate SMX and SGX support
tools/power turbostat: detect and work around syscall jitter
tools/power turbostat: show GFX%rc6
tools/power turbostat: show GFXMHz
tools/power turbostat: show IRQs per CPU
tools/power turbostat: make fewer systems calls
tools/power turbostat: fix compiler warnings
tools/power turbostat: add --out option for saving output in a file
tools/power turbostat: re-name "%Busy" field to "Busy%"
tools/power turbostat: Intel Xeon x200: fix turbo-ratio decoding
tools/power turbostat: Intel Xeon x200: fix erroneous bclk value
tools/power turbostat: allow sub-sec intervals
tools/power turbostat: Decode MSR_MISC_PWR_MGMT
tools/power turbostat: decode HWP registers
x86 msr-index: Simplify syntax for HWP fields
tools/power turbostat: CPUID(0x16) leaf shows base, max, and bus frequency
tools/power turbostat: decode more CPUID fields
MSR_CONFIG_TDP_NOMINAL:
should print all 8 bits of base_ratio (bit 0:7) 0xFF
MSR_CONFIG_TDP_LEVEL_1:
should print all 15 bits of PKG_MIN_PWR_LVL1 (bit 48:62) 0x7FFF
should print all 15 bits of PKG_MAX_PWR_LVL1 (bit 32:46) 0x7FFF
should print all 8 bits of LVL1_RATIO (bit 16:23) 0xFF
should print all 15 bits of PKG_TDP_LVL1 (bit 0:14) 0x7FFF
And the same modification to MSR_CONFIG_TDP_LEVEL_2.
MSR_TURBO_ACTIVATION_RATIO:
should print all 8 bits of MAX_NON_TURBO_RATIO (bit 0:7) 0xFF
Signed-off-by: Chen Yu <yu.c.chen@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
MSR_NHM_SNB_PKG_CST_CFG_CTL: 0x1e008008 (...pkg-cstate-limit=0: unlimited)
should print as
MSR_NHM_SNB_PKG_CST_CFG_CTL: 0x1e008008 (...pkg-cstate-limit=8: unlimited)
Signed-off-by: Len Brown <len.brown@intel.com>
turbostat already checks whether calling each cpuid leavf is legal,
and it doesn't look at the function return value,
so call the simpler gcc intrinsic __cpuid() instead of __get_cpuid().
syntax only, no functional change
Signed-off-by: Len Brown <len.brown@intel.com>
The accuracy of Bzy_Mhz and Busy% depend on reading
the TSC, APERF, and MPERF close together in time.
When there is a very short measurement interval,
or a large system is profoundly idle, the changes
in APERF and MPERF may be very small.
They can be small enough that an expensive interrupt
between reading APERF and MPERF can cause the APERF/MPERF
ratio to become inaccurate, resulting in invalid
calculation and display of Bzy_MHz.
A dummy APERF read of APERF makes this problem
much more rare. Apparently this 1st systemn call
after exiting a long stretch of idle is when we
typically see expensive timer interrupts that cause
large jitter.
For the cases that dummy APERF read fails to prevent,
we compare the latency of the APERF and MPERF reads.
If they differ by more than 2x, we re-issue them.
Signed-off-by: Len Brown <len.brown@intel.com>
The column "GFX%c6" show the percentage of time the GPU
is in the "render C6" state, rc6. Deep package C-states on several
systems depend on the GPU being in RC6.
This information comes from the counter
/sys/class/drm/card0/power/rc6_residency_ms,
as read before and after the measurement interval.
Signed-off-by: Len Brown <len.brown@intel.com>
Under the column "GFXMHz", show a snapshot of this attribute:
/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz
This is an instantaneous snapshot of what sysfs presents
at the end of the measurement interval. turbostat does
not average or otherwise perform any math on this value.
Signed-off-by: Len Brown <len.brown@intel.com>
The new IRQ column shows how many interrupts have occurred on each CPU
during the measurement inteval. This information comes from
the difference between /proc/interrupts shapshots made before
and after the measurement interval.
The first row, the system summary, shows the sum of the IRQS
for all CPUs during that interval.
Signed-off-by: Len Brown <len.brown@intel.com>
skip the open(2)/close(2) on each msr read
by keeping the /dev/cpu/*/msr files open.
The remaining read(2) is generally far fewer cycles
than the removed open(2) system call.
Signed-off-by: Len Brown <len.brown@intel.com>
By default...
Turbostat --debug gconfiguration info goes to stderr.
In FORK mode, turbostat statistics go to stderr.
In PERIODIC mode, turbostat statistics go to stdout.
These defaults do not change, but an option "--out file"
will send all output above only to the specified file.
Signed-off-by: Len Brown <len.brown@intel.com>
some tools processing turbostat output
have difficulty with items that begin with %...
Reported-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
Following changes have been made:
- changed MSR_NHM_TURBO_RATIO_LIMIT to MSR_TURBO_RATIO_LIMIT in debug print
for consistency with Developer Manual
- updated definition of bitfields in MSR_TURBO_RATIO_LIMIT and appropriate
parsing code
- added x200 to list of architectures that do not support Nahlem compatible
definition of MSR_TURBO_RATIO_LIMIT register (x200 has the register but
bits definition is custom)
- fixed typo in code that parses MSR_TURBO_RATIO_LIMIT
(logical instead of bitwise operator)
- changed MSR_TURBO_RATIO_LIMIT parsing algorithm so the print out had the
same order as implementations for other platforms
Signed-off-by: Hubert Chrzaniuk <hubert.chrzaniuk@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
x200 does not enable any way to programmatically obtain bus clock
speed. Bclk for the architecture has a fixed value of 100 MHz.
At the same time x200 cannot be included in has_snb_msrs since
it does not support C7 idle state.
prior to this patch, MHz values reported on this chip
were erroneously calculated using bclk of 133MHz,
causing MHz values to be reported 33% higher than actual.
Signed-off-by: Hubert Chrzaniuk <hubert.chrzaniuk@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
turbostat -i interval_sec
will sample and display statistics every interval_sec.
interval_sec used to be a whole number of seconds,
but now we accept a decimal, as small as 0.001 sec (1 ms).
Signed-off-by: Len Brown <len.brown@intel.com>
for debugging, dump a few more fields:
CPUID(1): SSE3 MONITOR EIST TM2 TSC MSR ACPI-TM TM
cpu0: MSR_IA32_MISC_ENABLE: 0x00850089 (TCC EIST MONITOR)
Signed-off-by: Len Brown <len.brown@intel.com>
Fix the following build error by including limits.h -
utils/cpufreq-info.c: In function ‘get_latency’:
utils/cpufreq-info.c:437:29: error: ‘UINT_MAX’ undeclared (first use in
this function)
if (!latency || latency == UINT_MAX) {
^
Signed-off-by: Shreyas B. Prabhu <shreyas@linux.vnet.ibm.com>
Fixes: e98f033f94 (cpupower: fix how "cpupower frequency-info" interprets latency)
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
All tool/utility signons.
Dual-license module header.
Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
* pm-sleep:
PM / sleep: Add support for read-only sysfs attributes
* pm-tools:
cpupower: fix how "cpupower frequency-info" interprets latency
cpupower: rework the "cpupower frequency-info" command
cpupower: Do not analyse offlined cpus
cpupower: Provide STATIC variable in Makefile for debug builds
cpupower: Fix precedence issue
ACPICA commit 0d784a90bc3aac75227c4459c3553de18b9ebe7a
Document one of the option string operators.
Link: https://github.com/acpica/acpica/commit/0d784a90
Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
ACPICA commit dfa394471f6c01b2ee9433dbc143ec70cb9bca72
Mostly indentation inconsistencies across the code. Split
some long lines, etc.
Link: https://github.com/acpica/acpica/commit/dfa39447
Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
This patch adds a userspace tool to access Linux kernel AML debugger
interface.
Tow modes are supported by this tool:
1. Interactive: Users are able to launch a debugging shell to talk with
in-kernel AML debugger.
Note that it's user duty to ensure kernel runtime integrity by using
this debugging tool:
A. Some control methods evaluated by the users may result in kernel
panics if those control methods shouldn't be evaluated by the OSPMs
according to the current BIOS/OS configurations.
B. Currently if a single stepping evaluation couldn't run to an end,
then the synchronization primitives acquired by the evaluation may
block normal OSPM control method evaluations.
2. Batch: Users are able to execute debugger commands in a script.
Note that in addition to the above duties, it's user duty to ensure
script runtime integrity by using this debugging tool in this mode:
C. Currently only those commands that are not used for single stepping
are suitable to be used in this mode.
D. If the execution of the command may cause a failure that could result
in an endless kernel execution, the execution of the script may also
get blocked.
To exit the utility, currently "exit/quit" commands are recommended, but
ctrl-C" can also be used.
Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
the intel-pstate driver does not support the ondemand governor and does not
have a valid value in
/sys/devices/system/cpu/cpu[x]/cpufreq/cpuinfo_transition_latency. The
intel-pstate driver sets cpuinfo_transition_latency to CPUFREQ_ETERNAL (-1),
the value written into cpuinfo_transition_latency is defind as an unsigned
int so checking the read value against max unsigned int will determine if the
value is valid.
Signed-off-by: Jacob Tanenbaum <jtanenba@redhat.com>
Signed-off-by: Thomas Renninger <trenn@suse.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
this patch makes two changes to the way that "cpupower
frequancy-info" operates
1. make it so that querying individual values always returns a
message to the user
currently cpupower frequency info doesn't return anything to the user when
querying an individual value cannot be returned
[root@amd-dinar-09 cpupower]# cpupower -c 4 frequency-info -d
analyzing CPU 4:
[root@amd-dinar-09 cpupower]#
I added messages so that each query prints a message to the terminal
[root@amd-dinar-09 cpupower]# ./cpupower -c 4 frequency-info -d
analyzing CPU 4:
no or unknown cpufreq driver is active on this CPU
[root@amd-dinar-09 cpupower]#
(this is just one example)
2. change debug_output_one() to use the functions already provided
by cpufreq-info.c to query individual values of interest.
Signed-off-by: Jacob Tanenbaum <jtanenba@redhat.com>
Signed-off-by: Thomas Renninger <trenn@suse.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Use sysfs_is_cpu_online(cpu) instead of cpufreq_cpu_exists(cpu) to detect offlined cpus.
Re-arrange printfs slightly to have a consistent output even if you have multiple CPUs
as output and even if offlined cores are in between.
Signed-off-by: Thomas Renninger <trenn@suse.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
When working on cpupower code, you often want to compile library code into the
binary.
This allows to execute modified cpupower code, even with library changes
without doing "make install"
Signed-off-by: Thomas Renninger <trenn@suse.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
MSR_PLATFORM_INFO is the new name for MSR_NHM_PLATFORM_INFO
no functional change
Signed-off-by: Len Brown <len.brown@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
* pm-tools:
Creating a common structure initialization pattern for struct option
cpupower: Enable disabled Cstates if they are below max latency
cpupower: Remove debug message when using cpupower idle-set -D switch
cpupower: cpupower monitor reports uninitialized values for offline cpus
tools/power turbostat: bugfix: print MAX_NON_TURBO_RATIO
tools/power turbostat: simplify Bzy_MHz calculation
This patch tries to creates a common structure initialization
within the cpupower tool.
Previously the ``struct option`` was initialized
using `designated initializer` technique which was
not needed. There were conflicting initialization methods seen with
bench/main.c & others.
Signed-off-by: Sriram Raghunathan <sriram@marirs.net.in>
Signed-off-by: Thomas Renninger <trenn@suse.de>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
cpupower idle-set -D <latency>
currently only disables all C-states that have a higher latency than the
specified <latency>. But if deep sleep states were already disabled and
have a lower latency, they should get enabled again.
For example:
This call:
cpupower idle-set -D 30
disables all C-states with a higher or equal latency than 30.
If one then calls:
cpupower idle-set -D 100
C-states with a latency between 30-99 will get enabled again with this patch
now. It is ensured that only C-states with a latency of 100 and higher are
disabled.
Signed-off-by: Thomas Renninger <trenn@suse.de>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
[root@hp-dl980g7-02 linux]# cpupower monitor
...
5472| 0| 1|******|******|******|******|| 0.00| 0.00| 0.00| 0.00| 0.00 *is offline
10567| 0| 159|******|******|******|******|| 0.00| 0.00| 0.00| 0.00| 0.00 *is offline
1661206560|859272560| 150|******|******|******|******|| 0.00| 0.00| 0.00| 0.00| 0.00 *is offline
1661206560|943093104| 140|******|******|******|******|| 0.00| 0.00| 0.00| 0.00| 0.00 *is offline
because of this cpupower also holds the incorrect value for the number
of physical packages in the machine
Changed cpupower to initialize the values of an offline cpu's socket and
core to -1, warn the user that one or more cpus is/are
offline and not print statistics for offline cpus.
This fix hides offlined cores where topology cannot be accessed.
With a recent kernel patch suggested from Prarit Bhargava it may be possible
that soft offlined cores' topology can still be parsed.
This patch would then show which cores in which package/socket are offline,
when sane toplogoy information is available.
Signed-off-by: Jacob Tanenbaum <jtanenba@redhat.com>
Signed-off-by: Thomas Renninger <trenn@suse.de>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
MSR_TURBO_ACTIVATION_RATIO: 0x00000016 (MAX_NON_TURBO_RATIO=6 lock=0)
should print all 7 bits of MAX_NON_TURBO_RATIO (in decimal):
MSR_TURBO_ACTIVATION_RATIO: 0x00000016 (MAX_NON_TURBO_RATIO=22 lock=0)
Signed-off-by: Len Brown <len.brown@intel.com>
ACPICA commit bed456ed2976bdaafdef406b982fdf6c539befc0
Removed some extraneous defines, reordered others.
Link: https://github.com/acpica/acpica/commit/bed456ed
Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Bzy_MHz = TSC_delta*tsc_tweak/APERF_delta/MPERF_delta/measurement_interval
becomes
Bzy_MHz = base_mhz/APERF_delta/MPERF_delta
on systems which support MSR_NHM_PLATFORM_INFO.
base_mhz is calculated directly from the base_ratio
reported in MSR_NHM_PLATFORM_INFO * bclk,
and bclk is discovered via MSR or cpuid.
This reduces the dependency of Bzy_MHz calculation on the TSC.
Previously, there were 4 TSC readings required in each caculation,
the raw TSC delta combined with the measurement_interval.
This also removes the "tsc_tweak" correction factor used when
TSC runs on a different base clock from the CPU's bclk.
After this change, tsc_tweak is used only for %Busy.
The end-result should be a Bzy_MHz result slightly less prone to jitter.
Signed-off-by: Len Brown <len.brown@intel.com>
On a Skylake with 1500MHz base frequency,
the TSC runs at 1512MHz.
This is because the TSC is no longer in the n*100 MHz BCLK domain,
but is now in the m*24MHz crystal clock domain. (24 MHz * 63 = 1512 MHz)
This adds error to several calculations in turbostat,
unless the TSC sample sizes are adjusted for this difference.
Note that calculations in the time domain are immune
from this issue, as the timing sub-system has already
calibrated the TSC against a known wall clock.
AVG_MHz = APERF_delta/measurement_interval
need no adjustment. APERF_delta is in the BCLK domain,
and measurement_interval is in the time domain.
TSC_MHz = TSC_delta/measurement_interval
needs no adjustment -- as we really do want to report
the actual measured TSC delta here, and measurement_interval
is in the accurate time domain.
%Busy = MPERF_delta/TSC_delta
needs adjustment to use TSC_BCLK_DOMAIN_delta.
TSC_BCLK_DOMAIN_delta = TSC_delta * base_hz / tsc_hz
Bzy_MHz = TSC_delta/APERF_delta/MPERF_delta/measurement_interval
need adjustment as above.
No other metrics in turbostat need to be adjusted.
Before:
CPU Avg_MHz %Busy Bzy_MHz TSC_MHz
- 550 24.84 2216 1512
0 2191 98.73 2219 1514
2 0 0.01 2130 1512
1 9 0.43 2016 1512
3 2 0.08 2016 1512
After:
CPU Avg_MHz %Busy Bzy_MHz TSC_MHz
- 550 25.05 2198 1512
0 2190 99.62 2199 1512
2 0 0.01 2152 1512
1 9 0.46 2000 1512
3 2 0.10 2000 1512
Note that in this example, the "Before" Bzy_MHz
was reported as exceeding the 2200 max turbo rate.
Also, even a pinned spin loop would not be reported
as over 99% busy.
Signed-off-by: Len Brown <len.brown@intel.com>
KNL increments APERF and MPERF every 1024 clocks.
This is compliant with the architecture specification,
which requires that only the ratio of APERF/MPERF need be valid.
However, turbostat takes advantage of the fact that these
two MSRs increment every un-halted clock
at the actual and base frequency:
AVG_MHz = APERF_delta/measurement_interval
%Busy = MPERF_delta/TSC_delta
This quirk is needed for these calculations to also work on KNL,
which would otherwise show a value 1024x smaller than expected.
Signed-off-by: Hubert Chrzaniuk <hubert.chrzaniuk@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
