linux-toradex.git/drivers/cpufreq/cpufreq_interactive.c, branch T30_LinuxImageV2.0Alpha1_20130122 Linux kernel for Apalis and Colibri modules cpufreq: interactive: Unify Governor Lock Strategy 2012-09-20T13:27:24+00:00 Matt Wagner mwagner@nvidia.com 2012-09-17T23:06:15+00:00 ae934e1ea7243000e399486823508b4a180254b5 Change our locking strategy to be the same as the conservative and ondemand governor for GOV_START and GOV_STOP to allow for correct handling of multiple CPUs Bug 1049258 Change-Id: I15ab620e2f9d47b00ec8186c224eb719b9735aa7 Signed-off-by: Matt Wagner <mwagner@nvidia.com> Reviewed-on: http://git-master/r/133360 Reviewed-by: Satya Popuri <spopuri@nvidia.com> Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: Dan Willemsen <dwillemsen@nvidia.com> 
Change our locking strategy to be the same as the conservative
and ondemand governor for GOV_START and GOV_STOP to allow
for correct handling of multiple CPUs

Bug 1049258

Change-Id: I15ab620e2f9d47b00ec8186c224eb719b9735aa7
Signed-off-by: Matt Wagner <mwagner@nvidia.com>
Reviewed-on: http://git-master/r/133360
Reviewed-by: Satya Popuri <spopuri@nvidia.com>
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Dan Willemsen <dwillemsen@nvidia.com>
cpufreq: interactive: Add Uevent Signal on Gov Start 2012-09-12T00:21:15+00:00 Matt Wagner mwagner@nvidia.com 2012-09-06T18:46:13+00:00 205718b2801464cdb5369b2a6200d077b7d5e96b Sends kobject_uevent signal back to userspace to signal that the cpufreq governor has been set to interactive Bug 1039141 Change-Id: I699e9d5834a1874b36c675764c080112ccba0f9f Signed-off-by: Matt Wagner <mwagner@nvidia.com> Reviewed-on: http://git-master/r/131224 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: Dan Willemsen <dwillemsen@nvidia.com> 
Sends kobject_uevent signal back to userspace to signal that
the cpufreq governor has been set to interactive

Bug 1039141

Change-Id: I699e9d5834a1874b36c675764c080112ccba0f9f
Signed-off-by: Matt Wagner <mwagner@nvidia.com>
Reviewed-on: http://git-master/r/131224
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Dan Willemsen <dwillemsen@nvidia.com>
ARM: Tegra: Added support to run at two frequency modes 2012-08-02T00:39:25+00:00 Xiao Bo Zhao xiaoboz@nvidia.com 2012-06-29T19:46:11+00:00 9046d52e1aeec6bb5f133426733bf77b71f10118 CPU clock is now capped at an normal frequency that is below its maximum and allowed to run at a high frequency only once within a period of time. By default the delay is set to 5*DOWN_DELAY, allowing a maximum of 20% high frequency time. Sysfs knobs were also added that allows userspace tuning Bug 1003531 Change-Id: Ie4a0e565630187bdacd6f31b1f35778eb31bfc81 Signed-off-by: Xiao Bo Zhao <xiaoboz@nvidia.com> Reviewed-on: http://git-master/r/118163 Reviewed-by: Peter Boonstoppel <pboonstoppel@nvidia.com> Reviewed-by: Diwakar Tundlam <dtundlam@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Bharat Nihalani <bnihalani@nvidia.com> 
CPU clock is now capped at an normal frequency that is below
its maximum and allowed to run at a high frequency
only once within a period of time. By default the delay is set to
5*DOWN_DELAY, allowing a maximum of 20% high frequency time.

Sysfs knobs were also added that allows userspace tuning

Bug 1003531

Change-Id: Ie4a0e565630187bdacd6f31b1f35778eb31bfc81
Signed-off-by: Xiao Bo Zhao <xiaoboz@nvidia.com>
Reviewed-on: http://git-master/r/118163
Reviewed-by: Peter Boonstoppel <pboonstoppel@nvidia.com>
Reviewed-by: Diwakar Tundlam <dtundlam@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Bharat Nihalani <bnihalani@nvidia.com>
cpufreq: interactive: clean up sysfs declarations 2012-07-20T23:48:14+00:00 Ilan Aelion iaelion@nvidia.com 2012-07-02T18:27:45+00:00 4de320ac63d36c7a6821ebb5b9a967dc12ce925d Cosmetics: introducing a macro to define unsigned long sysfs nodes. Change-Id: I594a527dc977437405167237e8d5ac6d3a3167d2 Signed-off-by: Ilan Aelion <iaelion@nvidia.com> Reviewed-on: http://git-master/r/113020 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: Matthew Longnecker <mlongnecker@nvidia.com> Reviewed-by: Bharat Nihalani <bnihalani@nvidia.com> 
Cosmetics: introducing a macro to define unsigned long sysfs nodes.

Change-Id: I594a527dc977437405167237e8d5ac6d3a3167d2
Signed-off-by: Ilan Aelion <iaelion@nvidia.com>
Reviewed-on: http://git-master/r/113020
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Matthew Longnecker <mlongnecker@nvidia.com>
Reviewed-by: Bharat Nihalani <bnihalani@nvidia.com>
cpufreq: mid-range frequency bias 2012-07-06T16:48:09+00:00 satya popuri spopuri@nvidia.com 2012-06-22T16:38:26+00:00 7d8a8d73ca38d663675ba0c56dde51c4a95be9bd Restrict go_maxspeed_load and max_boost at mid-range frequencies. Change-Id: I9e3c59bbe708b428e12ce4dbef2144be09751d5a Signed-off-by: satya popuri <spopuri@nvidia.com> Reviewed-on: http://git-master/r/111754 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: Karthikeyan Samynathan <ksamynathan@nvidia.com> Reviewed-by: Bharat Nihalani <bnihalani@nvidia.com> Reviewed-by: Aleksandr Frid <afrid@nvidia.com> Reviewed-by: Yu-Huan Hsu <yhsu@nvidia.com> 
Restrict go_maxspeed_load and max_boost at mid-range frequencies.

Change-Id: I9e3c59bbe708b428e12ce4dbef2144be09751d5a
Signed-off-by: satya popuri <spopuri@nvidia.com>
Reviewed-on: http://git-master/r/111754
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Karthikeyan Samynathan <ksamynathan@nvidia.com>
Reviewed-by: Bharat Nihalani <bnihalani@nvidia.com>
Reviewed-by: Aleksandr Frid <afrid@nvidia.com>
Reviewed-by: Yu-Huan Hsu <yhsu@nvidia.com>
cpufreq: interactive: change timer rate 2012-05-09T16:25:19+00:00 Shridhar Rasal srasal@nvidia.com 2012-04-13T15:04:42+00:00 c2a03d186704c4e28c68f5108f3b600a4f0e2c44 Tune *timer_rate* used to increase cpu frequency. bug 980120 Signed-off-by: Shridhar Rasal <srasal@nvidia.com> Reviewed-on: http://git-master/r/96525 (cherry picked from commit f8bcc67d13d72deb7b506b4a1cad581f3caf45dd) Change-Id: Iacc2e3f030c225a4aadbfc4611fe9e64d9181fa0 Reviewed-on: http://git-master/r/99989 Reviewed-by: Shridhar Rasal <srasal@nvidia.com> Tested-by: Shridhar Rasal <srasal@nvidia.com> GVS: Gerrit_Virtual_Submit <kchilds@nvidia.com> Reviewed-by: Bharat Nihalani <bnihalani@nvidia.com> 
Tune *timer_rate* used to increase cpu frequency.

bug 980120

Signed-off-by: Shridhar Rasal <srasal@nvidia.com>
Reviewed-on: http://git-master/r/96525
(cherry picked from commit f8bcc67d13d72deb7b506b4a1cad581f3caf45dd)

Change-Id: Iacc2e3f030c225a4aadbfc4611fe9e64d9181fa0
Reviewed-on: http://git-master/r/99989
Reviewed-by: Shridhar Rasal <srasal@nvidia.com>
Tested-by: Shridhar Rasal <srasal@nvidia.com>
GVS: Gerrit_Virtual_Submit <kchilds@nvidia.com>
Reviewed-by: Bharat Nihalani <bnihalani@nvidia.com>
cpufreq: set go_maxspeed_load to 85% 2012-03-21T16:12:11+00:00 Shridhar Rasal srasal@nvidia.com 2012-03-20T06:45:52+00:00 806fff65dfa3f000316ccaafda53b9183700243e To get better performance setting it to 85% from 95% bug 941275 Change-Id: I08bc711ea159d070cf6b62ce25506c8a5bdd7ac4 Signed-off-by: Shridhar Rasal <srasal@nvidia.com> Reviewed-on: http://git-master/r/91159 Reviewed-by: Rohan Somvanshi <rsomvanshi@nvidia.com> Tested-by: Rohan Somvanshi <rsomvanshi@nvidia.com> 
To get better performance setting it to 85% from 95%

bug 941275

Change-Id: I08bc711ea159d070cf6b62ce25506c8a5bdd7ac4
Signed-off-by: Shridhar Rasal <srasal@nvidia.com>
Reviewed-on: http://git-master/r/91159
Reviewed-by: Rohan Somvanshi <rsomvanshi@nvidia.com>
Tested-by: Rohan Somvanshi <rsomvanshi@nvidia.com>
cpufreq: update target freq always 2012-03-20T23:55:46+00:00 Shridhar Rasal srasal@nvidia.com 2012-03-19T16:08:57+00:00 4e1ec69f7c1b5a259d7df0435647e9005f1e033c set determined target freq always bug 941275 Change-Id: If72936ed145867abd32b43c5c5100290df2fc187 Signed-off-by: Shridhar Rasal <srasal@nvidia.com> Reviewed-on: http://git-master/r/91010 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: Satya Popuri <spopuri@nvidia.com> Reviewed-by: Peter Boonstoppel <pboonstoppel@nvidia.com> Reviewed-by: Bharat Nihalani <bnihalani@nvidia.com> 
set determined target freq always

bug 941275

Change-Id: If72936ed145867abd32b43c5c5100290df2fc187
Signed-off-by: Shridhar Rasal <srasal@nvidia.com>
Reviewed-on: http://git-master/r/91010
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Satya Popuri <spopuri@nvidia.com>
Reviewed-by: Peter Boonstoppel <pboonstoppel@nvidia.com>
Reviewed-by: Bharat Nihalani <bnihalani@nvidia.com>
cpufreq: Add a knob to treat IO wait as busy 2012-03-15T15:45:00+00:00 satya popuri spopuri@nvidia.com 2012-03-09T18:57:31+00:00 c8c6328fac300f8b93cb61c99e8280981692fa56 The new sysfs node io_is_busy enables the interactive governor to account any time spent by the CPU waiting for IO as non-idle time. This helps us improve run-time of IO bound tasks by making up for lost IO time in speeding up the CPU bound parts of the task. Reviewed on http://git-master/r/#change,86894 cherry picked from 13a15aadc1134b5dae05cdcf9687396644f87411 Signed-off-by: satya popuri <spopuri@nvidia.com> Change-Id: I4a14ed7fef5fbce00054bb02d52d2d3e0f011f70 Reviewed-on: http://git-master/r/89218 Reviewed-by: Satya Popuri <spopuri@nvidia.com> Tested-by: Satya Popuri <spopuri@nvidia.com> Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: Diwakar Tundlam <dtundlam@nvidia.com> 
The new sysfs node io_is_busy enables the interactive governor to
account any time spent by the CPU waiting for IO as non-idle time.
This helps us improve run-time of IO bound tasks by making up for
lost IO time in speeding up the CPU bound parts of the task.

Reviewed on http://git-master/r/#change,86894
cherry picked from 13a15aadc1134b5dae05cdcf9687396644f87411
Signed-off-by: satya popuri <spopuri@nvidia.com>

Change-Id: I4a14ed7fef5fbce00054bb02d52d2d3e0f011f70
Reviewed-on: http://git-master/r/89218
Reviewed-by: Satya Popuri <spopuri@nvidia.com>
Tested-by: Satya Popuri <spopuri@nvidia.com>
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Diwakar Tundlam <dtundlam@nvidia.com>
cpufreq: change min_sample_time 2012-03-15T15:44:43+00:00 satya popuri spopuri@nvidia.com 2012-03-09T18:41:33+00:00 5bfda21810b190dd50185e839d9a4b650e5fa8f1 We prefer a min_sample_time of 30ms. This is tied to our cluster switch and auto-hotplug artificial delays. Signed-off-by: satya popuri <spopuri@nvidia.com> original commit message: cpufreq: reduce min_sample_time Reduce the minimum amount of time the interactive governor spends at a frequency before ramping down. This parameter (min_sample_time) was 80ms now reduced to 30 ms based on perf and power sweep numbers. Reviewed-on: http://git-master/r/86900 (cherry picked from commit 581f20a5b7b8c3e4ee2c211b28dbc81510af2ae7). Signed-off-by: satya popuri <spopuri@nvidia.com> Change-Id: I24f4cd52737950fd4e78a36b4ee34a84551e0e12 Reviewed-on: http://git-master/r/89217 Reviewed-by: Satya Popuri <spopuri@nvidia.com> Tested-by: Satya Popuri <spopuri@nvidia.com> Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: Diwakar Tundlam <dtundlam@nvidia.com> 
We prefer a min_sample_time of 30ms. This is tied to our cluster switch
and auto-hotplug artificial delays.

Signed-off-by: satya popuri <spopuri@nvidia.com>

original commit message:

cpufreq: reduce min_sample_time

Reduce the minimum amount of time the interactive governor spends at a
frequency before ramping down. This parameter (min_sample_time) was 80ms
now reduced to 30 ms based on perf and power sweep numbers.

Reviewed-on: http://git-master/r/86900 (cherry picked from commit
581f20a5b7b8c3e4ee2c211b28dbc81510af2ae7).
Signed-off-by: satya popuri <spopuri@nvidia.com>

Change-Id: I24f4cd52737950fd4e78a36b4ee34a84551e0e12
Reviewed-on: http://git-master/r/89217
Reviewed-by: Satya Popuri <spopuri@nvidia.com>
Tested-by: Satya Popuri <spopuri@nvidia.com>
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Diwakar Tundlam <dtundlam@nvidia.com>