<feed xmlns='http://www.w3.org/2005/Atom'>
<title>linux.git/tools/power/cpupower, branch v5.8</title>
<subtitle>Linux kernel source tree</subtitle>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/'/>
<entry>
<title>cpupower: Remove unneeded semicolon</title>
<updated>2020-05-08T16:13:26+00:00</updated>
<author>
<name>Zou Wei</name>
<email>zou_wei@huawei.com</email>
</author>
<published>2020-04-28T09:43:15+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=7b0bf99b9ee497cc0f079472566aff716d033d43'/>
<id>7b0bf99b9ee497cc0f079472566aff716d033d43</id>
<content type='text'>
Fixes coccicheck warnings:

tools/power/cpupower/utils/cpupower-info.c:65:2-3: Unneeded semicolon
tools/power/cpupower/utils/cpupower-set.c:75:2-3: Unneeded semicolon
tools/power/cpupower/utils/idle_monitor/amd_fam14h_idle.c:120:2-3: Unneeded semicolon
tools/power/cpupower/utils/idle_monitor/cpuidle_sysfs.c:175:2-3: Unneeded semicolon
tools/power/cpupower/utils/idle_monitor/cpuidle_sysfs.c:56:2-3: Unneeded semicolon
tools/power/cpupower/utils/idle_monitor/cpuidle_sysfs.c:75:2-3: Unneeded semicolon
tools/power/cpupower/utils/idle_monitor/hsw_ext_idle.c:82:2-3: Unneeded semicolon
tools/power/cpupower/utils/idle_monitor/nhm_idle.c:94:2-3: Unneeded semicolon
tools/power/cpupower/utils/idle_monitor/snb_idle.c:80:2-3: Unneeded semicolon

Reported-by: Hulk Robot &lt;hulkci@huawei.com&gt;
Signed-off-by: Zou Wei &lt;zou_wei@huawei.com&gt;
Signed-off-by: Shuah Khan &lt;skhan@linuxfoundation.org&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Fixes coccicheck warnings:

tools/power/cpupower/utils/cpupower-info.c:65:2-3: Unneeded semicolon
tools/power/cpupower/utils/cpupower-set.c:75:2-3: Unneeded semicolon
tools/power/cpupower/utils/idle_monitor/amd_fam14h_idle.c:120:2-3: Unneeded semicolon
tools/power/cpupower/utils/idle_monitor/cpuidle_sysfs.c:175:2-3: Unneeded semicolon
tools/power/cpupower/utils/idle_monitor/cpuidle_sysfs.c:56:2-3: Unneeded semicolon
tools/power/cpupower/utils/idle_monitor/cpuidle_sysfs.c:75:2-3: Unneeded semicolon
tools/power/cpupower/utils/idle_monitor/hsw_ext_idle.c:82:2-3: Unneeded semicolon
tools/power/cpupower/utils/idle_monitor/nhm_idle.c:94:2-3: Unneeded semicolon
tools/power/cpupower/utils/idle_monitor/snb_idle.c:80:2-3: Unneeded semicolon

Reported-by: Hulk Robot &lt;hulkci@huawei.com&gt;
Signed-off-by: Zou Wei &lt;zou_wei@huawei.com&gt;
Signed-off-by: Shuah Khan &lt;skhan@linuxfoundation.org&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>.gitignore: add SPDX License Identifier</title>
<updated>2020-03-25T10:50:48+00:00</updated>
<author>
<name>Masahiro Yamada</name>
<email>masahiroy@kernel.org</email>
</author>
<published>2020-03-03T13:35:59+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=d198b34f3855eee2571dda03eea75a09c7c31480'/>
<id>d198b34f3855eee2571dda03eea75a09c7c31480</id>
<content type='text'>
Add SPDX License Identifier to all .gitignore files.

Signed-off-by: Masahiro Yamada &lt;masahiroy@kernel.org&gt;
Signed-off-by: Greg Kroah-Hartman &lt;gregkh@linuxfoundation.org&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Add SPDX License Identifier to all .gitignore files.

Signed-off-by: Masahiro Yamada &lt;masahiroy@kernel.org&gt;
Signed-off-by: Greg Kroah-Hartman &lt;gregkh@linuxfoundation.org&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>cpupower: avoid multiple definition with gcc -fno-common</title>
<updated>2020-03-02T15:53:34+00:00</updated>
<author>
<name>Mike Gilbert</name>
<email>floppym@gentoo.org</email>
</author>
<published>2020-02-26T19:33:59+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=2de7fb60a4740135e03cf55c1982e393ccb87b6b'/>
<id>2de7fb60a4740135e03cf55c1982e393ccb87b6b</id>
<content type='text'>
Building cpupower with -fno-common in CFLAGS results in errors due to
multiple definitions of the 'cpu_count' and 'start_time' variables.

./utils/idle_monitor/snb_idle.o:./utils/idle_monitor/cpupower-monitor.h:28:
multiple definition of `cpu_count';
./utils/idle_monitor/nhm_idle.o:./utils/idle_monitor/cpupower-monitor.h:28:
first defined here
...
./utils/idle_monitor/cpuidle_sysfs.o:./utils/idle_monitor/cpuidle_sysfs.c:22:
multiple definition of `start_time';
./utils/idle_monitor/amd_fam14h_idle.o:./utils/idle_monitor/amd_fam14h_idle.c:85:
first defined here

The -fno-common option will be enabled by default in GCC 10.

Bug: https://bugs.gentoo.org/707462
Signed-off-by: Mike Gilbert &lt;floppym@gentoo.org&gt;
Signed-off-by: Shuah Khan &lt;skhan@linuxfoundation.org&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Building cpupower with -fno-common in CFLAGS results in errors due to
multiple definitions of the 'cpu_count' and 'start_time' variables.

./utils/idle_monitor/snb_idle.o:./utils/idle_monitor/cpupower-monitor.h:28:
multiple definition of `cpu_count';
./utils/idle_monitor/nhm_idle.o:./utils/idle_monitor/cpupower-monitor.h:28:
first defined here
...
./utils/idle_monitor/cpuidle_sysfs.o:./utils/idle_monitor/cpuidle_sysfs.c:22:
multiple definition of `start_time';
./utils/idle_monitor/amd_fam14h_idle.o:./utils/idle_monitor/amd_fam14h_idle.c:85:
first defined here

The -fno-common option will be enabled by default in GCC 10.

Bug: https://bugs.gentoo.org/707462
Signed-off-by: Mike Gilbert &lt;floppym@gentoo.org&gt;
Signed-off-by: Shuah Khan &lt;skhan@linuxfoundation.org&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>Correction to manpage of cpupower</title>
<updated>2020-01-27T15:43:31+00:00</updated>
<author>
<name>Brahadambal Srinivasan</name>
<email>latha@linux.vnet.ibm.com</email>
</author>
<published>2020-01-23T14:33:19+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=8c30fa7666ff08dad632411d1a9b9883940e53ef'/>
<id>8c30fa7666ff08dad632411d1a9b9883940e53ef</id>
<content type='text'>
Manpage of cpupower is listing wrong sub-commands in "See Also"
section. The option for cpupower-idle(1) should actually be
cpupower-idle-info(1) and cpupower-idle-set(1). This patch corrects
this anomaly.

Signed-off-by: Brahadambal Srinivasan &lt;latha@linux.vnet.ibm.com&gt;
Signed-off-by: Shuah Khan &lt;skhan@linuxfoundation.org&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Manpage of cpupower is listing wrong sub-commands in "See Also"
section. The option for cpupower-idle(1) should actually be
cpupower-idle-info(1) and cpupower-idle-set(1). This patch corrects
this anomaly.

Signed-off-by: Brahadambal Srinivasan &lt;latha@linux.vnet.ibm.com&gt;
Signed-off-by: Shuah Khan &lt;skhan@linuxfoundation.org&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>cpupower: Revert library ABI changes from commit ae2917093fb60bdc1ed3e</title>
<updated>2020-01-17T22:21:42+00:00</updated>
<author>
<name>Thomas Renninger</name>
<email>trenn@suse.de</email>
</author>
<published>2020-01-17T07:55:54+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=41ddb7e1f79693d904502ae9bea609837973eff8'/>
<id>41ddb7e1f79693d904502ae9bea609837973eff8</id>
<content type='text'>
Commit ae2917093fb6 ("tools/power/cpupower: Display boost frequency
separately") modified the library function:

struct cpufreq_available_frequencies
*cpufreq_get_available_frequencies(unsigned int cpu)

to
struct cpufreq_frequencies
*cpufreq_get_frequencies(const char *type, unsigned int cpu)

This patch recovers the old API and implements the new functionality
in a newly introduce method:
struct cpufreq_boost_frequencies
*cpufreq_get_available_frequencies(unsigned int cpu)

This one should get merged into stable kernels back to 5.0 when
the above had been introduced.

Fixes: ae2917093fb6 ("tools/power/cpupower: Display boost frequency separately")

Cc: stable@vger.kernel.org
Signed-off-by: Thomas Renninger &lt;trenn@suse.de&gt;
Signed-off-by: Shuah Khan &lt;skhan@linuxfoundation.org&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Commit ae2917093fb6 ("tools/power/cpupower: Display boost frequency
separately") modified the library function:

struct cpufreq_available_frequencies
*cpufreq_get_available_frequencies(unsigned int cpu)

to
struct cpufreq_frequencies
*cpufreq_get_frequencies(const char *type, unsigned int cpu)

This patch recovers the old API and implements the new functionality
in a newly introduce method:
struct cpufreq_boost_frequencies
*cpufreq_get_available_frequencies(unsigned int cpu)

This one should get merged into stable kernels back to 5.0 when
the above had been introduced.

Fixes: ae2917093fb6 ("tools/power/cpupower: Display boost frequency separately")

Cc: stable@vger.kernel.org
Signed-off-by: Thomas Renninger &lt;trenn@suse.de&gt;
Signed-off-by: Shuah Khan &lt;skhan@linuxfoundation.org&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>cpupower: ToDo: Update ToDo with ideas for per_cpu_schedule handling</title>
<updated>2019-11-06T00:23:23+00:00</updated>
<author>
<name>Janakarajan Natarajan</name>
<email>Janakarajan.Natarajan@amd.com</email>
</author>
<published>2019-11-05T17:16:57+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=4611a4fb0cce3973dce8c9d74e5d6261ffa4210f'/>
<id>4611a4fb0cce3973dce8c9d74e5d6261ffa4210f</id>
<content type='text'>
Based on Thomas Renninger's feedback/ideas. Re-structure the code
to better handle the per_cpu_schedule mechanism which was introduced
when adding support for AMD Zen based processors.

Signed-off-by: Janakarajan Natarajan &lt;Janakarajan.Natarajan@amd.com&gt;
Acked-by: Thomas Renninger &lt;trenn@suse.de&gt;
Signed-off-by: Shuah Khan &lt;skhan@linuxfoundation.org&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Based on Thomas Renninger's feedback/ideas. Re-structure the code
to better handle the per_cpu_schedule mechanism which was introduced
when adding support for AMD Zen based processors.

Signed-off-by: Janakarajan Natarajan &lt;Janakarajan.Natarajan@amd.com&gt;
Acked-by: Thomas Renninger &lt;trenn@suse.de&gt;
Signed-off-by: Shuah Khan &lt;skhan@linuxfoundation.org&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>cpupower: mperf_monitor: Update cpupower to use the RDPRU instruction</title>
<updated>2019-11-06T00:22:56+00:00</updated>
<author>
<name>Janakarajan Natarajan</name>
<email>Janakarajan.Natarajan@amd.com</email>
</author>
<published>2019-11-05T17:16:55+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=6af2ed53f0402c09b36d2b38698e18a25ca732a7'/>
<id>6af2ed53f0402c09b36d2b38698e18a25ca732a7</id>
<content type='text'>
AMD Zen 2 introduces the RDPRU instruction which can be used to access some
processor registers which are typically only accessible in privilege level
0. ECX specifies the register to read and EDX:EAX will contain the value read.

ECX: 0 - Register MPERF
     1 - Register APERF

This has the added advantage of not having to use the msr module, since the
userspace to kernel transitions which occur during each read_msr() might
cause APERF and MPERF to go out of sync.

Signed-off-by: Janakarajan Natarajan &lt;Janakarajan.Natarajan@amd.com&gt;
Acked-by: Thomas Renninger &lt;trenn@suse.de&gt;
Signed-off-by: Shuah Khan &lt;skhan@linuxfoundation.org&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
AMD Zen 2 introduces the RDPRU instruction which can be used to access some
processor registers which are typically only accessible in privilege level
0. ECX specifies the register to read and EDX:EAX will contain the value read.

ECX: 0 - Register MPERF
     1 - Register APERF

This has the added advantage of not having to use the msr module, since the
userspace to kernel transitions which occur during each read_msr() might
cause APERF and MPERF to go out of sync.

Signed-off-by: Janakarajan Natarajan &lt;Janakarajan.Natarajan@amd.com&gt;
Acked-by: Thomas Renninger &lt;trenn@suse.de&gt;
Signed-off-by: Shuah Khan &lt;skhan@linuxfoundation.org&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>cpupower: mperf_monitor: Introduce per_cpu_schedule flag</title>
<updated>2019-11-06T00:22:46+00:00</updated>
<author>
<name>Janakarajan Natarajan</name>
<email>Janakarajan.Natarajan@amd.com</email>
</author>
<published>2019-11-05T17:16:54+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=7adafe541fe5e015261a92d39db8b163db477337'/>
<id>7adafe541fe5e015261a92d39db8b163db477337</id>
<content type='text'>
The per_cpu_schedule flag is used to move the cpupower process to the cpu
on which we are looking to read the APERF/MPERF registers.

This prevents IPIs from being generated by read_msr()s as we are already
on the cpu of interest.

Ex: If cpupower is running on CPU 0 and we execute

    read_msr(20, MSR_APERF, val) then,
    read_msr(20, MSR_MPERF, val)

    the msr module will generate an IPI from CPU 0 to CPU 20 to query
    for the MSR_APERF and then the MSR_MPERF in separate IPIs.

This delay, caused by IPI latency, between reading the APERF and MPERF
registers may cause both of them to go out of sync.

The use of the per_cpu_schedule flag reduces the probability of this
from happening. It comes at the cost of a negligible increase in cpu
consumption caused by the migration of cpupower across each of the
cpus of the system.

Signed-off-by: Janakarajan Natarajan &lt;Janakarajan.Natarajan@amd.com&gt;
Acked-by: Thomas Renninger &lt;trenn@suse.de&gt;
Signed-off-by: Shuah Khan &lt;skhan@linuxfoundation.org&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
The per_cpu_schedule flag is used to move the cpupower process to the cpu
on which we are looking to read the APERF/MPERF registers.

This prevents IPIs from being generated by read_msr()s as we are already
on the cpu of interest.

Ex: If cpupower is running on CPU 0 and we execute

    read_msr(20, MSR_APERF, val) then,
    read_msr(20, MSR_MPERF, val)

    the msr module will generate an IPI from CPU 0 to CPU 20 to query
    for the MSR_APERF and then the MSR_MPERF in separate IPIs.

This delay, caused by IPI latency, between reading the APERF and MPERF
registers may cause both of them to go out of sync.

The use of the per_cpu_schedule flag reduces the probability of this
from happening. It comes at the cost of a negligible increase in cpu
consumption caused by the migration of cpupower across each of the
cpus of the system.

Signed-off-by: Janakarajan Natarajan &lt;Janakarajan.Natarajan@amd.com&gt;
Acked-by: Thomas Renninger &lt;trenn@suse.de&gt;
Signed-off-by: Shuah Khan &lt;skhan@linuxfoundation.org&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>cpupower: Move needs_root variable into a sub-struct</title>
<updated>2019-11-06T00:22:01+00:00</updated>
<author>
<name>Janakarajan Natarajan</name>
<email>Janakarajan.Natarajan@amd.com</email>
</author>
<published>2019-11-05T17:16:52+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=d3f5d2a192a299f56579ae6e6283f9011b00208f'/>
<id>d3f5d2a192a299f56579ae6e6283f9011b00208f</id>
<content type='text'>
Move the needs_root variable into a sub-struct. This is in preparation
for adding a new flag for cpuidle_monitor.

Update all uses of the needs_root variable to reflect this change.

Signed-off-by: Janakarajan Natarajan &lt;Janakarajan.Natarajan@amd.com&gt;
Acked-by: Thomas Renninger &lt;trenn@suse.de&gt;
Signed-off-by: Shuah Khan &lt;skhan@linuxfoundation.org&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Move the needs_root variable into a sub-struct. This is in preparation
for adding a new flag for cpuidle_monitor.

Update all uses of the needs_root variable to reflect this change.

Signed-off-by: Janakarajan Natarajan &lt;Janakarajan.Natarajan@amd.com&gt;
Acked-by: Thomas Renninger &lt;trenn@suse.de&gt;
Signed-off-by: Shuah Khan &lt;skhan@linuxfoundation.org&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>cpupower : Handle set and info subcommands correctly</title>
<updated>2019-11-04T20:11:57+00:00</updated>
<author>
<name>Abhishek Goel</name>
<email>huntbag@linux.vnet.ibm.com</email>
</author>
<published>2019-10-17T05:56:39+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=d80a4ac20800035c46a3868ad9e11ebda0049c7d'/>
<id>d80a4ac20800035c46a3868ad9e11ebda0049c7d</id>
<content type='text'>
Cpupower tool has set and info options which are being used only by
x86 machines. This patch removes support for these two subcommands
from cpupower utility for POWER. Thus, these two subcommands will now be
available only for intel.
This removes the ambiguous error message while using set option in case
of using non-intel systems.

Without this patch on a POWER system:

root@ubuntu:~# cpupower info
System does not support Intel's performance bias setting

root@ubuntu:~# cpupower set -b 10
Error setting perf-bias value on CPU

With this patch on a POWER box:

root@ubuntu:~# cpupower info
Subcommand not supported on POWER

Same result for set subcommand.
This patch does not affect results on a intel box.

Signed-off-by: Abhishek Goel &lt;huntbag@linux.vnet.ibm.com&gt;
Acked-by: Thomas Renninger &lt;trenn@suse.de&gt;
Reviewed-by: Shuah Khan &lt;skhan@linuxfoundation.org&gt;
Signed-off-by: Shuah Khan &lt;skhan@linuxfoundation.org&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Cpupower tool has set and info options which are being used only by
x86 machines. This patch removes support for these two subcommands
from cpupower utility for POWER. Thus, these two subcommands will now be
available only for intel.
This removes the ambiguous error message while using set option in case
of using non-intel systems.

Without this patch on a POWER system:

root@ubuntu:~# cpupower info
System does not support Intel's performance bias setting

root@ubuntu:~# cpupower set -b 10
Error setting perf-bias value on CPU

With this patch on a POWER box:

root@ubuntu:~# cpupower info
Subcommand not supported on POWER

Same result for set subcommand.
This patch does not affect results on a intel box.

Signed-off-by: Abhishek Goel &lt;huntbag@linux.vnet.ibm.com&gt;
Acked-by: Thomas Renninger &lt;trenn@suse.de&gt;
Reviewed-by: Shuah Khan &lt;skhan@linuxfoundation.org&gt;
Signed-off-by: Shuah Khan &lt;skhan@linuxfoundation.org&gt;
</pre>
</div>
</content>
</entry>
</feed>
