Age | Commit message (Collapse) | Author |
|
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>
|
|
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>
|
|
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>
|
|
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>
|
|
Prevents crash on cpufreq_stat_notifier_trans when cpufreq_stats_table
has been freed due to a core being hotplugged out.
Bug 948348
Change-Id: I2640a9a23c9a79cad8c76bfefd243a07162d2004
Signed-off-by: Peter Boonstoppel <pboonstoppel@nvidia.com>
(cherry picked from commit 03070a4b0b8eb74825c99c6bbfb108ddb36a041c)
Reviewed-on: http://git-master/r/114248
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Yu-Huan Hsu <yhsu@nvidia.com>
|
|
It takes read RW semaphore to access policy governor
bug 997731
Change-Id: Ibdc3dd54cf6076c0fef4bc58f144e4bcb4631d76
Signed-off-by: Puneet Saxena <puneets@nvidia.com>
Reviewed-on: http://git-master/r/107079
GVS: Gerrit_Virtual_Submit
Reviewed-by: Sang-Hun Lee <sanlee@nvidia.com>
Reviewed-by: Peter Boonstoppel <pboonstoppel@nvidia.com>
Reviewed-by: Bharat Nihalani <bnihalani@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>
|
|
bug 1001593
Change-Id: Ib1bf525e5c4c7ed633073a3d0b990703840dad77
Signed-off-by: Shaoming Feng <shaomingf@nvidia.com>
Reviewed-on: http://git-master/r/112025
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Peter Boonstoppel <pboonstoppel@nvidia.com>
Reviewed-by: Prajakta Gudadhe <pgudadhe@nvidia.com>
|
|
Clipping PM QoS requests to combined old policy limits that include
both PM QoS and user policy requests creates a circular dependency.
As a result new PM QoS maximum limit is rejected if it is above
previous PM QoS minimum limit even though the new PM QoS minimum
limit has been already lowered below new PM QoS maximum limit.
Instead clip PM QoS request to the old user policy limits only.
Change-Id: Ice0a53a699e0798f07f0e32d6b8a28586fe5db0c
Signed-off-by: Alex Frid <afrid@nvidia.com>
Reviewed-on: http://git-master/r/102386
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Donghan Ryu <dryu@nvidia.com>
Reviewed-by: Antti Miettinen <amiettinen@nvidia.com>
Reviewed-by: Diwakar Tundlam <dtundlam@nvidia.com>
Tested-by: Vikas Ramesh Kedigehalli <vikasr@nvidia.com>
|
|
This implementation sets governor for a cpu using existing
cpufreq interfaces.
bug 871958
Change-Id: Ic4e7e2a2b0babaf1829b559b5db211666d449b86
Signed-off-by: Puneet Saxena <puneets@nvidia.com>
Reviewed-on: http://git-master/r/97939
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Bharat Nihalani <bnihalani@nvidia.com>
|
|
Tune *timer_rate* used to increase cpu frequency.
bug 943712
Change-Id: I3ded757e21825c475606976c2dcfcd75d9467ef8
Signed-off-by: Shridhar Rasal <srasal@nvidia.com>
Reviewed-on: http://git-master/r/96525
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Aleksandr Frid <afrid@nvidia.com>
Reviewed-by: Satya Popuri <spopuri@nvidia.com>
Reviewed-by: Bharat Nihalani <bnihalani@nvidia.com>
Reviewed-by: Mayuresh Kulkarni <mkulkarni@nvidia.com>
Reviewed-by: Diwakar Tundlam <dtundlam@nvidia.com>
|
|
Simple tracepoints for measuring CPU scaling latencies.
Bug 960307
Change-Id: I6fd4e67e352a2ff134da58866d943457506d080b
Signed-off-by: Antti P Miettinen <amiettinen@nvidia.com>
Reviewed-on: http://git-master/r/93080
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Juha Tukkinen <jtukkinen@nvidia.com>
|
|
The min/max frequencies in cpufreq_policy are unsigned integers
but pm_qos_request() returns a signed int. Compare as unsigned,
frequencies are never negative.
Bug 949219
Change-Id: Iba0de9ad6bf221f7a2e5560f597aa56cbeb7b6f6
Signed-off-by: Antti P Miettinen <amiettinen@nvidia.com>
Reviewed-on: http://git-master/r/91214
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-by: Juha Tukkinen <jtukkinen@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>
|
|
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>
|
|
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>
|
|
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>
|
|
Protecting sysfs_remove_group() in CPUFREQ_GOV_STOP with dbs_mutex
Bug 946462
Signed-off-by: Peter Boonstoppel <pboonstoppel@nvidia.com>
Reviewed-on: http://git-master/r/86426
(cherry picked from commit d1131158e2ad4d5ccc53b3008743c29385650d86)
Change-Id: Iae810e83eaa6f0f7d970b56238cbcb61118af610
Reviewed-on: http://git-master/r/87392
Reviewed-by: Peter Boonstoppel <pboonstoppel@nvidia.com>
Reviewed-by: Diwakar Tundlam <dtundlam@nvidia.com>
Tested-by: Peter Boonstoppel <pboonstoppel@nvidia.com>
|
|
Change our added attributes' store functions to Google style
Change-Id: I5dc641112085698918e87b52378fe3a5bfe44360
Signed-off-by: Peter Boonstoppel <pboonstoppel@nvidia.com>
Reviewed-on: http://git-master/r/84452
Reviewed-by: Satya Popuri <spopuri@nvidia.com>
Reviewed-by: Diwakar Tundlam <dtundlam@nvidia.com>
|
|
Reduce permissions on the max_boost and go_maxspeed_load, the init
scripts will change their owner so the current users continue to work.
Bug 906796
Signed-off-by: Dan Willemsen <dwillemsen@nvidia.com>
Reviewed-on: http://git-master/r/79096
(cherry picked from commit f1d91095baff48e58a04af0062f579f394094b47)
Change-Id: Id9542a202bcf02f886cfee9c0bbe69cc83b8c200
Signed-off-by: Pritesh Raithatha <praithatha@nvidia.com>
Reviewed-on: http://git-master/r/82726
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Varun Wadekar <vwadekar@nvidia.com>
Tested-by: Varun Wadekar <vwadekar@nvidia.com>
|
|
typically PM QoS clients request the maximum cpu frequency by
setting cpu_freq_min to INT_MAX. Therefore, we need to clamp INT_MAX
to whatever the maximum frequency allowed by the policy to make
the requested cpu_freq_min is same as the maximum allowed cpu
frequency. Inverse logic applies to the cpu_freq_max as well.
Bug 932477
Signed-off-by: Donghan Ryu <dryu@nvidia.com>
Reviewed-on: http://git-master/r/78401
(cherry picked from commit 9688430a621515f3afe3e0ab358ea7ad5aab6d91)
Change-Id: Ie5edcd4a873ed5cce45ec0f9b981f28db6091ff1
Signed-off-by: Pritesh Raithatha <praithatha@nvidia.com>
Reviewed-on: http://git-master/r/80002
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Bharat Nihalani <bnihalani@nvidia.com>
|
|
Store the value received via sysfs as the user_policy
min/max value instead of the currently enforced min/max.
This allows restoring the user min/max values when
constraints on enforced min/max change.
Bug 888312
Change-Id: I8a5adf022585e5bd91fa3b1d8d448065efa6827a
Reviewed-on: http://git-master/r/73982
Signed-off-by: Antti P Miettinen <amiettinen@nvidia.com>
Signed-off-by: Varun Wadekar <vwadekar@nvidia.com>
Reviewed-on: http://git-master/r/75886
Reviewed-by: Automatic_Commit_Validation_User
|
|
Observe PM QoS CPU frequency minimum and maximum in addition
to policy settings.
Bug 888312
Change-Id: Ia4f60a1649a9952e02f6847c8add3b2ea5d47524
Reviewed-on: http://git-master/r/72207
Signed-off-by: Antti P Miettinen <amiettinen@nvidia.com>
Signed-off-by: Varun Wadekar <vwadekar@nvidia.com>
Reviewed-on: http://git-master/r/75884
Reviewed-by: Automatic_Commit_Validation_User
|
|
Add sysfs nodes for user_policy min and max settings.
Bug 888312
Change-Id: Ife8ec07f8faebc0c04e7ecf6e24976a311bad73b
Reviewed-on: http://git-master/r/72201
Signed-off-by: Antti P Miettinen <amiettinen@nvidia.com>
Signed-off-by: Varun Wadekar <vwadekar@nvidia.com>
Reviewed-on: http://git-master/r/75882
Reviewed-by: Automatic_Commit_Validation_User
|
|
max_boost and go_maxspeed_load need to be writable for service that
controls balanced power mode
Cherry-picked from: http://git-master/r/#change,57965
Change-Id: I0e3a39ddf317a0f7ba3bb4908afc8a100db1b883
Signed-off-by: Daniel Solomon <daniels@nvidia.com>
Reviewed-on: http://git-master/r/65602
Reviewed-by: Simone Willett <swillett@nvidia.com>
Tested-by: Simone Willett <swillett@nvidia.com>
|
|
Attribute store functions used to return 0 upon success, but should
return count instead.
Change-Id: I2ab15e536d9affbf80bbcb2e557c6d217d5a9dfa
Signed-off-by: Peter Boonstoppel <pboonstoppel@nvidia.com>
Reviewed-on: http://git-master/r/68554
Reviewed-by: Aleksandr Frid <afrid@nvidia.com>
Tested-by: Daniel Solomon <daniels@nvidia.com>
Reviewed-by: Diwakar Tundlam <dtundlam@nvidia.com>
|
|
Allows you to specify a max increase in frequency, disabled by default.
Cherry-pick from: http://git-master/r/#change,57928
Change-Id: I8174e31faceaa7c27adfe52515e951a4092a39f3
Signed-off-by: Daniel Solomon <daniels@nvidia.com>
Reviewed-on: http://git-master/r/65601
Reviewed-by: Diwakar Tundlam <dtundlam@nvidia.com>
Reviewed-by: Peter Boonstoppel <pboonstoppel@nvidia.com>
Reviewed-by: Yu-Huan Hsu <yhsu@nvidia.com>
|
|
When governor starts initialize time_in_idle and idle_exit_time
variables with current data, and restart timer. This is required
to properly start governor on busy CPU that would not enter idle
state for a long time.
(cherry picked from commit 876dc6eddc68054e6abe23f6287cfbf5302a75b9)
(cherry picked from commit d0024f3ad1e4c6d4885355df3fda02435ccc471d)
Change-Id: I992ca9193cb95e64cc9ef8bfb86675b32ad6d43d
Reviewed-on: http://git-master/r/61712
Reviewed-by: Varun Colbert <vcolbert@nvidia.com>
Tested-by: Varun Colbert <vcolbert@nvidia.com>
Rebase-Id: Ra79d9a3ca97b0cfd49fb642ba7cafb98c11c04f1
|
|
Updated target frequency calculation algorithm to take into account
current rate CPU is running at:
- When CPU is running below go_maxspeed_load threshold, adjust the
target frequency based on current rate to reach tunable sustainable
load (instead of applying cpu load to max possible cpu rate).
Tuned by setting new node ("0" falls back to using max_rate):
/sys/devices/system/cpu/cpufreq/interactive/sustain_load
- When CPU is running at/above go_maxspeed_load threshold, ramp the
target frequency starting from current exponentially with tunable base
(instead of immediate jump to maximum cpu rate).
Tuned by setting new node ("0" falls back to jump to max_rate):
/sys/devices/system/cpu/cpufreq/interactive/boost_factor
Defaults for the new tunning parameters are set to "0" - so no changes
in governor default behavior.
Original-Change-Id: Ie845d747239ba177e6f06b73965c3213649f8135
Reviewed-on: http://git-master/r/34583
Reviewed-by: Aleksandr Frid <afrid@nvidia.com>
Tested-by: Aleksandr Frid <afrid@nvidia.com>
Reviewed-by: Chih-Lung Huang <lhuang@nvidia.com>
Reviewed-by: Scott Williams <scwilliams@nvidia.com>
Reviewed-by: Narendra Damahe <ndamahe@nvidia.com>
Reviewed-by: Yu-Huan Hsu <yhsu@nvidia.com>
Reviewed-by: Diwakar Tundlam <dtundlam@nvidia.com>
Rebase-Id: Re898a7b96d3c1b7343e773aab9788e4ff2b1d7f8
|
|
This reverts commit 6f312490bcf93bf51ad4ba8d4965a952f521cb7d.
Signed-off-by: Dan Willemsen <dwillemsen@nvidia.com>
Rebase-Id: Rf54be39acd2c92decd9e5c4522d2b2e47589d84e
|
|
This reverts commit 460145c8b1d2ff8a2488baa10d7421e1d8179b7d.
Signed-off-by: Dan Willemsen <dwillemsen@nvidia.com>
Rebase-Id: Racc6c054ac5c67c38dec7281c7190c6650bfb8bd
|
|
This reverts commit d7e7e4f15c62464dfa5d2c58d73bc66f131795bc.
Signed-off-by: Dan Willemsen <dwillemsen@nvidia.com>
Rebase-Id: R4a8c8c91c64c2c1d64ecb22dfe8a7c2cd133fd39
|
|
This reverts commit 4714e5222b5a9b11030eda6df7b8159034be0008.
Signed-off-by: Dan Willemsen <dwillemsen@nvidia.com>
Rebase-Id: Rc7c804305f9c37c4b93d5d7eecce0b9b93499e27
|
|
Conflicts:
arch/arm/mach-tegra/Kconfig
arch/arm/mach-tegra/board-ventana.c
drivers/misc/Kconfig
drivers/video/tegra/dc/hdmi.c
Signed-off-by: Dan Willemsen <dwillemsen@nvidia.com>
|
|
When cpu runs at frequency not in cpufreq table (because of other
frequency governing mechanisms), bill time spent at that frequency to
next lower frequency in cpufreq stats table.
Original-Change-Id: I9cfda4e7a223ca3f773f1adb145d242483209799
Reviewed-on: http://git-master/r/47929
Reviewed-by: Peter Boonstoppel <pboonstoppel@nvidia.com>
Tested-by: Peter Boonstoppel <pboonstoppel@nvidia.com>
Tested-by: Diwakar Tundlam <dtundlam@nvidia.com>
Reviewed-by: Diwakar Tundlam <dtundlam@nvidia.com>
Reviewed-by: Scott Williams <scwilliams@nvidia.com>
Rebase-Id: Rd25650679bddec2837d92c75b18f8568c7569336
|
|
When cpu runs at a frequency not in cpufreq table (because of other
frequency governing mechanisms), freq_table_get_index() returns -1
which gets used as an array index.
Original-Change-Id: Id8fa5d5125c3cd1e2aad8b48ff7bd619f39c57d8
Reviewed-on: http://git-master/r/47887
Reviewed-by: Peter Boonstoppel <pboonstoppel@nvidia.com>
Tested-by: Peter Boonstoppel <pboonstoppel@nvidia.com>
Reviewed-by: Diwakar Tundlam <dtundlam@nvidia.com>
Reviewed-by: Aleksandr Frid <afrid@nvidia.com>
Tested-by: Diwakar Tundlam <dtundlam@nvidia.com>
Reviewed-by: Scott Williams <scwilliams@nvidia.com>
Rebase-Id: R032fc27d227d3308e5afa17d909f64d6925e05cc
|
|
Change-Id: Ie9952f07b38667f2932474090044195c57976faa
Signed-off-by: Todd Poynor <toddpoynor@google.com>
|
|
* Add attribute hispeed_freq, which defaults to max.
* Rename go_maxspeed_load to go_hispeed_load.
* If hit go_hispeed_load and at min speed, go to hispeed_freq;
if hit go_hispeed_load and already above min speed go to max
speed.
Change-Id: I1050dec5f013fc1177387352ba787a7e1c68703e
Signed-off-by: Todd Poynor <toddpoynor@google.com>
|
|
Change-Id: Ieffb2aa56b5290036285c948718be7be0d3af9e8
Signed-off-by: Todd Poynor <toddpoynor@google.com>
|
|
Calculate intermediate speed by applyng CPU load to current speed, not
max speed.
Change-Id: Idecf598b9a203b07c989c5d9e9c6efc67a1afc2e
Signed-off-by: Todd Poynor <toddpoynor@google.com>
|
|
Lower the default time at which a higher speed is allowed to run
before lowering based on lower CPU load from 80ms to 20ms. Most
Android devices should trade power for performance here,
although tablets and non-battery-powered devices may want to
override this default.
Change-Id: I1a4f7faeca12793c51d5b92db30a63cca8d4f1be
Signed-off-by: Todd Poynor <toddpoynor@google.com>
|
|
Modify default timer from 30ms to 10ms, sampling 2 jiffies after
idle exit on ARM as in Honeycomb.
Modify default go_maxspeed_load from 85% loaded to 95% loaded, for
use in phones where power savings is more important (tablets may be
best served overriding this).
Change-Id: I3361a6279979bfae1df5262666a2e30ea7a44328
Signed-off-by: Todd Poynor <toddpoynor@google.com>
|
|
The following dump was seen sometimes while resuming,
the only division by zero on this function can happen after
delta_time is reassigned, since at the start of the
function, there is jump that protects against values
less than 1000.
After that, If delta_time and delta_idle == 0,
we will hit a div 0
Division by zero in kernel.
Backtrace:
[<c0057184>] (dump_backtrace+0x0/0x110) from [<c05d5ecc>] (dump_stack+0x18/0x1c)
r6:010f3000 r5:c113dfb0 r4:c004afb0 r3:c6ff0000
[<c05d5eb4>] (dump_stack+0x0/0x1c) from [<c00572cc>] (__div0+0x1c/0x20)
[<c00572b0>] (__div0+0x0/0x20) from [<c02195d4>] (Ldiv0+0x8/0x10)
[<c03dfd64>] (cpufreq_interactive_timer+0x0/0x2c0) from [<c00a7efc>] (run_timer_softirq+0x154/0x260)
[<c00a7da8>] (run_timer_softirq+0x0/0x260) from [<c00a0c8c>] (__do_softirq+0xc8/0x194)
[<c00a0bc4>] (__do_softirq+0x0/0x194) from [<c00a1008>] (irq_exit+0xb4/0xb8)
[<c00a0f54>] (irq_exit+0x0/0xb8) from [<c00584b4>] (ipi_timer+0x44/0x48)
r4:c004a040 r3:00000001
[<c0058470>] (ipi_timer+0x0/0x48) from [<c004c3e4>] (do_local_timer+0x68/0x84)
r5:c004ae2c r4:c07991e8
[<c004c37c>] (do_local_timer+0x0/0x84) from [<c0052948>] (__irq_svc+0x48/0xe0)
Change-Id: I639882db67b8d711c5710778ebc212f0f6a998e3
Acked-by: Nishanth Menon <nm@ti.com>
Signed-off-by: Axel Haslam <axelhaslam@ti.com>
|
|
The interactive governor relies on quirks of the Tegra 2 cpufreq
implementation for handling SMP systems where the CPUs do not have
separate rate controls. It needs to determine the maximum rate
for all CPUs covered by the policy and set that speed.
Change-Id: I1ed9fa171e5a9c45a1fa5944e3fa823eb157e81f
Signed-off-by: Todd Poynor <toddpoynor@google.com>
|
|
Fix up checkpatch warning introduced by long lines in timer_rate
patch.
Change-Id: I22b105dafb1b49390799bb7577464da03f0f8afb
Signed-off-by: Allen Martin <amartin@nvidia.com>
|
|
Cleanup some style warnings reported by checkpatch
Change-Id: Ie2e6903d52867fb3347e009d7efa3bc4ca755cea
Signed-off-by: Allen Martin <amartin@nvidia.com>
|
|
Update the Kconfig help paragraph to give more detail about
interactive governor.
Change-Id: I607b817b370accac3a685001649a15e2f7894f59
Signed-off-by: Allen Martin <amartin@nvidia.com>
|
|
Add a new sysfs control that tunes the rate of the timer used to
increase cpu frequency
Change-Id: I1aa13ae54bb43aff5b3688984d2955f56aae1658
Signed-off-by: Allen Martin <amartin@nvidia.com>
|
|
This adds better error checking on tunable parameters on sysfs
interfaces. Also fixes return value from these functions, previously
on success they would return 0 which would cause a infinite loop.
Change-Id: Ic05038492166f8673d007202092471f98a2f0dfa
Signed-off-by: Allen Martin <amartin@nvidia.com>
|
|
Convert interactive governor to use idle notifier instead of
hooking pm_idle directly.
Change-Id: I47e007f330468ac559240a0ae8a3cb06a89ccb67
Signed-off-by: Allen Martin <amartin@nvidia.com>
|