linux.git/tools/power/cpupower, branch v4.5

cpupower: Fix build error in cpufreq-info

2016-01-19T00:17:23+00:00

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 
Fixes: e98f033f94f3 (cpupower: fix how "cpupower frequency-info" interprets latency)
Signed-off-by: Rafael J. Wysocki

cpupower: fix how "cpupower frequency-info" interprets latency

2015-12-03T01:30:30+00:00

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 
Signed-off-by: Thomas Renninger 
Signed-off-by: Rafael J. Wysocki

cpupower: rework the "cpupower frequency-info" command

2015-12-03T01:30:30+00:00

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 
Signed-off-by: Thomas Renninger 
Signed-off-by: Rafael J. Wysocki

cpupower: Do not analyse offlined cpus

2015-12-03T01:30:30+00:00

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 
Signed-off-by: Rafael J. Wysocki

cpupower: Provide STATIC variable in Makefile for debug builds

2015-12-03T01:30:30+00:00

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 
Signed-off-by: Rafael J. Wysocki

cpupower: Fix precedence issue

2015-12-03T01:30:29+00:00

Signed-off-by: Thomas Renninger 
Signed-off-by: Rafael J. Wysocki

Creating a common structure initialization pattern for struct option

2015-11-02T01:28:59+00:00

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 
Signed-off-by: Thomas Renninger 
Signed-off-by: Rafael J. Wysocki

cpupower: Enable disabled Cstates if they are below max latency

2015-11-02T01:28:59+00:00

cpupower idle-set -D 
currently only disables all C-states that have a higher latency than the
specified . 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 
Signed-off-by: Rafael J. Wysocki

cpupower: Remove debug message when using cpupower idle-set -D switch

2015-11-02T01:28:59+00:00

Signed-off-by: Thomas Renninger 
Signed-off-by: Rafael J. Wysocki

cpupower: cpupower monitor reports uninitialized values for offline cpus

2015-11-02T01:28:59+00:00

[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 
Signed-off-by: Thomas Renninger 
Signed-off-by: Rafael J. Wysocki